diff --git a/.clippy.toml b/.clippy.toml index e4c4eef10b28..815c94732ed7 100644 --- a/.clippy.toml +++ b/.clippy.toml @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +msrv = "1.78.0" + check-private-items = true disallowed-macros = [ diff --git a/.gitignore b/.gitignore index 6839cf84acda..5937c74d3dc1 100644 --- a/.gitignore +++ b/.gitignore @@ -22,6 +22,7 @@ *.dtb.S *.dtbo.S *.dwo +*.dylib *.elf *.gcno *.gcda diff --git a/.mailmap b/.mailmap index 5ff0e5d681e7..ae0adc499f4a 100644 --- a/.mailmap +++ b/.mailmap @@ -83,6 +83,13 @@ Anirudh Ghayal Antoine Tenart Antoine Tenart Antonio Ospite +Antonio Quartulli +Antonio Quartulli +Antonio Quartulli +Antonio Quartulli +Antonio Quartulli +Antonio Quartulli +Antonio Quartulli Anup Patel Archit Taneja Ard Biesheuvel @@ -121,6 +128,8 @@ Ben Widawsky Benjamin Poirier Benjamin Tissoires Benjamin Tissoires +Bingwu Zhang +Bingwu Zhang Bjorn Andersson Bjorn Andersson Bjorn Andersson @@ -133,13 +142,17 @@ Boris Brezillon Boris Brezillon Brendan Higgins Brian Avery +Brian Cain +Brian Cain Brian King Brian Silverman Bryan Tan Cai Huoqing Can Guo Carl Huang -Carlos Bilbao +Carlos Bilbao +Carlos Bilbao +Carlos Bilbao Changbin Du Changbin Du Chao Yu @@ -156,6 +169,7 @@ Christian Brauner Christian Brauner Christian Marangi Christophe Ricard +Christopher Obbard Christoph Hellwig Chuck Lever Chuck Lever @@ -200,6 +214,7 @@ Elliot Berman Enric Balletbo i Serra Enric Balletbo i Serra Erik Kaneda +Ethan Carter Edwards Ethan Edwards Eugen Hristev Eugen Hristev Evgeniy Polyakov @@ -251,6 +266,7 @@ Guo Ren Guru Das Srinagesh Gustavo Padovan Gustavo Padovan +Hamza Mahfooz Hanjun Guo Hans Verkuil Hans Verkuil @@ -405,6 +421,7 @@ Liam Mark Linas Vepstas Linus Lüssing Linus Lüssing +Linus Lüssing Li Yang Li Yang @@ -427,6 +444,8 @@ Marcin Nowakowski Marc Zyngier Marek Behún Marek Behún Marek Behun +Marek Lindner +Marek Lindner Mark Brown Mark Starovoytov Markus Schneider-Pargmann @@ -435,7 +454,7 @@ Martin Kepplinger Martin Kepplinger Martin Kepplinger Martyna Szapar-Mudlaw -Mathieu Othacehe +Mathieu Othacehe Mat Martineau Mat Martineau Matthew Wilcox @@ -529,6 +548,8 @@ Oleksij Rempel Oleksij Rempel Oleksij Rempel Oleksij Rempel +Oliver Hartkopp +Oliver Hartkopp Oliver Upton Ondřej Jirman Oza Pawandeep @@ -640,6 +661,11 @@ Simona Vetter Simon Horman Simon Horman Simon Kelley +Simon Wunderlich +Simon Wunderlich +Simon Wunderlich +Simon Wunderlich +Simon Wunderlich Sricharan Ramabadhran Srinivas Ramana Sriram R @@ -660,6 +686,11 @@ Sudarshan Rajagopalan Sudeep Holla Sudeep KarkadaNagesha Sumit Semwal Surabhi Vishnoi +Sven Eckelmann +Sven Eckelmann +Sven Eckelmann +Sven Eckelmann +Sven Eckelmann Takashi YOSHII Tamizh Chelvam Raja Taniya Das @@ -735,6 +766,8 @@ Wolfram Sang Wolfram Sang Yakir Yang Yanteng Si +Ying Huang +Yosry Ahmed Yusuke Goda Zack Rusin Zhu Yanjun diff --git a/CREDITS b/CREDITS index b1777b53c63a..1f9f0f078b4a 100644 --- a/CREDITS +++ b/CREDITS @@ -20,6 +20,10 @@ N: Thomas Abraham E: thomas.ab@samsung.com D: Samsung pin controller driver +N: Jose Abreu +E: jose.abreu@synopsys.com +D: Synopsys DesignWare XPCS MDIO/PCS driver. + N: Dragos Acostachioaie E: dragos@iname.com W: http://www.arbornet.org/~dragos @@ -1428,6 +1432,10 @@ S: 8124 Constitution Apt. 7 S: Sterling Heights, Michigan 48313 S: USA +N: Andy Gospodarek +E: andy@greyhouse.net +D: Maintenance and contributions to the network interface bonding driver. + N: Wolfgang Grandegger E: wg@grandegger.com D: Controller Area Network (device drivers) @@ -1812,6 +1820,10 @@ D: Author/maintainer of most DRM drivers (especially ATI, MGA) D: Core DRM templates, general DRM and 3D-related hacking S: No fixed address +N: Woojung Huh +E: woojung.huh@microchip.com +D: Microchip LAN78XX USB Ethernet driver + N: Kenn Humborg E: kenn@wombat.ie D: Mods to loop device to support sparse backing files @@ -4327,7 +4339,7 @@ D: Freescale Highspeed USB device driver D: Freescale QE SoC support and Ethernet driver S: B-1206 Jingmao Guojigongyu S: 16 Baliqiao Nanjie, Beijing 101100 -S: People's Repulic of China +S: People's Republic of China N: Vlad Yasevich E: vyasevich@gmail.com diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/obsolete/sysfs-class-cxl similarity index 99% rename from Documentation/ABI/testing/sysfs-class-cxl rename to Documentation/ABI/obsolete/sysfs-class-cxl index cfc48a87706b..8cba1b626985 100644 --- a/Documentation/ABI/testing/sysfs-class-cxl +++ b/Documentation/ABI/obsolete/sysfs-class-cxl @@ -1,3 +1,6 @@ +The cxl driver is no longer maintained, and will be removed from the kernel in +the near future. + Please note that attributes that are shared between devices are stored in the directory pointed to by the symlink device/. For example, the real path of the attribute /sys/class/cxl/afu0.0s/irqs_max is diff --git a/Documentation/ABI/stable/sysfs-class-bluetooth b/Documentation/ABI/stable/sysfs-class-bluetooth new file mode 100644 index 000000000000..36be02471174 --- /dev/null +++ b/Documentation/ABI/stable/sysfs-class-bluetooth @@ -0,0 +1,9 @@ +What: /sys/class/bluetooth/hci/reset +Date: 14-Jan-2025 +KernelVersion: 6.13 +Contact: linux-bluetooth@vger.kernel.org +Description: This write-only attribute allows users to trigger the vendor reset + method on the Bluetooth device when arbitrary data is written. + The reset may or may not be done through the device transport + (e.g., UART/USB), and can also be done through an out-of-band + approach such as GPIO. diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-dummy-source b/Documentation/ABI/testing/sysfs-bus-coresight-devices-dummy-source new file mode 100644 index 000000000000..0830661ef656 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-dummy-source @@ -0,0 +1,15 @@ +What: /sys/bus/coresight/devices/dummy_source/enable_source +Date: Dec 2024 +KernelVersion: 6.14 +Contact: Mao Jinlong +Description: (RW) Enable/disable tracing of dummy source. A sink should be activated + before enabling the source. The path of coresight components linking + the source to the sink is configured and managed automatically by the + coresight framework. + +What: /sys/bus/coresight/devices/dummy_source/traceid +Date: Dec 2024 +KernelVersion: 6.14 +Contact: Mao Jinlong +Description: (R) Show the trace ID that will appear in the trace stream + coming from this trace entity. diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices b/Documentation/ABI/testing/sysfs-bus-event_source-devices new file mode 100644 index 000000000000..79b268319df1 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices @@ -0,0 +1,24 @@ +What: /sys/bus/event_source/devices/ +Date: 2014/02/24 +Contact: Linux kernel mailing list +Description: Performance Monitoring Unit () + + Each directory, for a PMU device, is a name + optionally followed by an underscore and then either a + decimal or hexadecimal number. For example, cpu is a + PMU name without a suffix as is intel_bts, + uncore_imc_0 is a PMU name with a 0 numeric suffix, + ddr_pmu_87e1b0000000 is a PMU name with a hex + suffix. The hex suffix must be more than two + characters long to avoid ambiguity with PMUs like the + S390 cpum_cf. + + Tools can treat PMUs with the same name that differ by + suffix as instances of the same PMU for the sake of, + for example, opening an event. For example, the PMUs + uncore_imc_free_running_0 and + uncore_imc_free_running_1 have an event data_read; + opening the data_read event on a PMU specified as + uncore_imc_free_running should be treated as opening + the data_read event on PMU uncore_imc_free_running_0 + and PMU uncore_imc_free_running_1. diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events index e7efeab2ee83..0fe1b9487202 100644 --- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events @@ -37,11 +37,13 @@ Description: Per-pmu performance monitoring events specific to the running syste performance monitoring event supported by the . The name of the file is the name of the event. - As performance monitoring event names are case - insensitive in the perf tool, the perf tool only looks - for lower or upper case event names in sysfs to avoid + As performance monitoring event names are case insensitive + in the perf tool, the perf tool only looks for all lower + case or all upper case event names in sysfs to avoid scanning the directory. It is therefore required the - name of the event here is either lower or upper case. + name of the event here is either completely lower or upper + case, with no mixed-case characters. Numbers, '.', '_', and + '-' are also allowed. File contents: diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index f83bd6829285..25d366d452a5 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -168,18 +168,6 @@ Description: is required is a consistent labeling. Units after application of scale and offset are millivolts. -What: /sys/bus/iio/devices/iio:deviceX/in_currentY_raw -What: /sys/bus/iio/devices/iio:deviceX/in_currentY_supply_raw -KernelVersion: 3.17 -Contact: linux-iio@vger.kernel.org -Description: - Raw (unscaled no bias removal etc.) current measurement from - channel Y. In special cases where the channel does not - correspond to externally available input one of the named - versions may be used. The number must always be specified and - unique to allow association with event codes. Units after - application of scale and offset are milliamps. - What: /sys/bus/iio/devices/iio:deviceX/in_powerY_raw KernelVersion: 4.5 Contact: linux-iio@vger.kernel.org @@ -227,7 +215,7 @@ Description: same scaling as _raw. What: /sys/bus/iio/devices/iio:deviceX/in_temp_raw -What: /sys/bus/iio/devices/iio:deviceX/in_tempX_raw +What: /sys/bus/iio/devices/iio:deviceX/in_tempY_raw What: /sys/bus/iio/devices/iio:deviceX/in_temp_x_raw What: /sys/bus/iio/devices/iio:deviceX/in_temp_y_raw What: /sys/bus/iio/devices/iio:deviceX/in_temp_ambient_raw @@ -416,11 +404,11 @@ Contact: linux-iio@vger.kernel.org Description: Scaled humidity measurement in milli percent. -What: /sys/bus/iio/devices/iio:deviceX/in_X_mean_raw +What: /sys/bus/iio/devices/iio:deviceX/in_Y_mean_raw KernelVersion: 3.5 Contact: linux-iio@vger.kernel.org Description: - Averaged raw measurement from channel X. The number of values + Averaged raw measurement from channel Y. The number of values used for averaging is device specific. The converting rules for normal raw values also applies to the averaged raw values. @@ -448,7 +436,7 @@ What: /sys/bus/iio/devices/iio:deviceX/in_humidityrelative_offset What: /sys/bus/iio/devices/iio:deviceX/in_magn_offset What: /sys/bus/iio/devices/iio:deviceX/in_rot_offset What: /sys/bus/iio/devices/iio:deviceX/in_angl_offset -What: /sys/bus/iio/devices/iio:deviceX/in_capacitanceX_offset +What: /sys/bus/iio/devices/iio:deviceX/in_capacitanceY_offset KernelVersion: 2.6.35 Contact: linux-iio@vger.kernel.org Description: @@ -508,6 +496,9 @@ What: /sys/bus/iio/devices/iio:deviceX/in_angl_scale What: /sys/bus/iio/devices/iio:deviceX/in_intensity_x_scale What: /sys/bus/iio/devices/iio:deviceX/in_intensity_y_scale What: /sys/bus/iio/devices/iio:deviceX/in_intensity_z_scale +What: /sys/bus/iio/devices/iio:deviceX/in_intensity_red_scale +What: /sys/bus/iio/devices/iio:deviceX/in_intensity_green_scale +What: /sys/bus/iio/devices/iio:deviceX/in_intensity_blue_scale What: /sys/bus/iio/devices/iio:deviceX/in_concentration_co2_scale KernelVersion: 2.6.35 Contact: linux-iio@vger.kernel.org @@ -660,10 +651,10 @@ What: /sys/.../iio:deviceX/in_magn_scale_available What: /sys/.../iio:deviceX/in_illuminance_scale_available What: /sys/.../iio:deviceX/in_intensity_scale_available What: /sys/.../iio:deviceX/in_proximity_scale_available -What: /sys/.../iio:deviceX/in_voltageX_scale_available +What: /sys/.../iio:deviceX/in_voltageY_scale_available What: /sys/.../iio:deviceX/in_voltage-voltage_scale_available -What: /sys/.../iio:deviceX/out_voltageX_scale_available -What: /sys/.../iio:deviceX/out_altvoltageX_scale_available +What: /sys/.../iio:deviceX/out_voltageY_scale_available +What: /sys/.../iio:deviceX/out_altvoltageY_scale_available What: /sys/.../iio:deviceX/in_capacitance_scale_available What: /sys/.../iio:deviceX/in_pressure_scale_available What: /sys/.../iio:deviceX/in_pressureY_scale_available @@ -681,6 +672,7 @@ What: /sys/bus/iio/devices/iio:deviceX/in_intensity_red_hardwaregain What: /sys/bus/iio/devices/iio:deviceX/in_intensity_green_hardwaregain What: /sys/bus/iio/devices/iio:deviceX/in_intensity_blue_hardwaregain What: /sys/bus/iio/devices/iio:deviceX/in_intensity_clear_hardwaregain +What: /sys/bus/iio/devices/iio:deviceX/in_illuminance_hardwaregain KernelVersion: 2.6.35 Contact: linux-iio@vger.kernel.org Description: @@ -1562,7 +1554,7 @@ Description: This attribute is used to read the amount of quadrature error present in the device at a given time. -What: /sys/.../iio:deviceX/in_accelX_power_mode +What: /sys/.../iio:deviceX/in_accelY_power_mode KernelVersion: 3.11 Contact: linux-iio@vger.kernel.org Description: @@ -1633,6 +1625,10 @@ What: /sys/.../iio:deviceX/in_intensityY_uv_raw What: /sys/.../iio:deviceX/in_intensityY_uva_raw What: /sys/.../iio:deviceX/in_intensityY_uvb_raw What: /sys/.../iio:deviceX/in_intensityY_duv_raw +What: /sys/.../iio:deviceX/in_intensity_red_raw +What: /sys/.../iio:deviceX/in_intensity_green_raw +What: /sys/.../iio:deviceX/in_intensity_blue_raw +What: /sys/.../iio:deviceX/in_intensity_clear_raw KernelVersion: 3.4 Contact: linux-iio@vger.kernel.org Description: @@ -1691,16 +1687,19 @@ Description: Raw value of rotation from true/magnetic north measured with or without compensation from tilt sensors. -What: /sys/bus/iio/devices/iio:deviceX/in_currentX_raw -What: /sys/bus/iio/devices/iio:deviceX/in_currentX_i_raw -What: /sys/bus/iio/devices/iio:deviceX/in_currentX_q_raw -KernelVersion: 3.18 +What: /sys/bus/iio/devices/iio:deviceX/in_currentY_raw +What: /sys/bus/iio/devices/iio:deviceX/in_currentY_supply_raw +What: /sys/bus/iio/devices/iio:deviceX/in_currentY_i_raw +What: /sys/bus/iio/devices/iio:deviceX/in_currentY_q_raw +KernelVersion: 3.17 Contact: linux-iio@vger.kernel.org Description: - Raw current measurement from channel X. Units are in milliamps + Raw current measurement from channel Y. Units are in milliamps after application of scale and offset. If no offset or scale is present, output should be considered as processed with the - unit in milliamps. + unit in milliamps. In special cases where the channel does not + correspond to externally available input one of the named + versions may be used. Channels with 'i' and 'q' modifiers always exist in pairs and both channels refer to the same signal. The 'i' channel contains the in-phase @@ -1864,9 +1863,9 @@ Description: hardware fifo watermark level. What: /sys/bus/iio/devices/iio:deviceX/in_temp_calibemissivity -What: /sys/bus/iio/devices/iio:deviceX/in_tempX_calibemissivity +What: /sys/bus/iio/devices/iio:deviceX/in_tempY_calibemissivity What: /sys/bus/iio/devices/iio:deviceX/in_temp_object_calibemissivity -What: /sys/bus/iio/devices/iio:deviceX/in_tempX_object_calibemissivity +What: /sys/bus/iio/devices/iio:deviceX/in_tempY_object_calibemissivity KernelVersion: 4.1 Contact: linux-iio@vger.kernel.org Description: @@ -1887,17 +1886,17 @@ Description: is considered as one sample for [_name]_sampling_frequency. What: /sys/bus/iio/devices/iio:deviceX/in_concentration_raw -What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationY_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentration_co2_raw -What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_co2_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationY_co2_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentration_ethanol_raw -What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_ethanol_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationY_ethanol_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentration_h2_raw -What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_h2_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationY_h2_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentration_o2_raw -What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_o2_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationY_o2_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentration_voc_raw -What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationY_voc_raw KernelVersion: 4.3 Contact: linux-iio@vger.kernel.org Description: @@ -1905,9 +1904,9 @@ Description: after application of scale and offset are percents. What: /sys/bus/iio/devices/iio:deviceX/in_resistance_raw -What: /sys/bus/iio/devices/iio:deviceX/in_resistanceX_raw +What: /sys/bus/iio/devices/iio:deviceX/in_resistanceY_raw What: /sys/bus/iio/devices/iio:deviceX/out_resistance_raw -What: /sys/bus/iio/devices/iio:deviceX/out_resistanceX_raw +What: /sys/bus/iio/devices/iio:deviceX/out_resistanceY_raw KernelVersion: 4.3 Contact: linux-iio@vger.kernel.org Description: @@ -2096,7 +2095,7 @@ Description: One of the following thermocouple types: B, E, J, K, N, R, S, T. What: /sys/bus/iio/devices/iio:deviceX/in_temp_object_calibambient -What: /sys/bus/iio/devices/iio:deviceX/in_tempX_object_calibambient +What: /sys/bus/iio/devices/iio:deviceX/in_tempY_object_calibambient KernelVersion: 5.10 Contact: linux-iio@vger.kernel.org Description: @@ -2172,9 +2171,9 @@ Description: - a range specified as "[min step max]" -What: /sys/bus/iio/devices/iio:deviceX/in_voltageX_sampling_frequency +What: /sys/bus/iio/devices/iio:deviceX/in_voltageY_sampling_frequency What: /sys/bus/iio/devices/iio:deviceX/in_powerY_sampling_frequency -What: /sys/bus/iio/devices/iio:deviceX/in_currentZ_sampling_frequency +What: /sys/bus/iio/devices/iio:deviceX/in_currentY_sampling_frequency KernelVersion: 5.20 Contact: linux-iio@vger.kernel.org Description: diff --git a/Documentation/ABI/testing/sysfs-bus-iio-adc-ad-sigma-delta b/Documentation/ABI/testing/sysfs-bus-iio-adc-ad-sigma-delta new file mode 100644 index 000000000000..a5a8a579f4f3 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-iio-adc-ad-sigma-delta @@ -0,0 +1,23 @@ +What: /sys/bus/iio/devices/iio:deviceX/in_voltageY_sys_calibration +KernelVersion: 5.5 +Contact: linux-iio@vger.kernel.org +Description: + This attribute, if available, initiates the system calibration procedure. This is done on a + single channel at a time. Write '1' to start the calibration. + +What: /sys/bus/iio/devices/iio:deviceX/in_voltageY_sys_calibration_mode_available +KernelVersion: 5.5 +Contact: linux-iio@vger.kernel.org +Description: + This attribute, if available, returns a list with the possible calibration modes. + There are two available options: + "zero_scale" - calibrate to zero scale + "full_scale" - calibrate to full scale + +What: /sys/bus/iio/devices/iio:deviceX/in_voltageY_sys_calibration_mode +KernelVersion: 5.5 +Contact: linux-iio@vger.kernel.org +Description: + This attribute, if available, sets up the calibration mode used in the system calibration + procedure. Reading returns the current calibration mode. + Writing sets the system calibration mode. diff --git a/Documentation/ABI/testing/sysfs-bus-iio-adc-ad7192 b/Documentation/ABI/testing/sysfs-bus-iio-adc-ad7192 index f8315202c8f0..28be1cabf112 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-adc-ad7192 +++ b/Documentation/ABI/testing/sysfs-bus-iio-adc-ad7192 @@ -19,33 +19,9 @@ Description: the bridge can be disconnected (when it is not being used using the bridge_switch_en attribute. -What: /sys/bus/iio/devices/iio:deviceX/in_voltagex_sys_calibration -KernelVersion: -Contact: linux-iio@vger.kernel.org -Description: - Initiates the system calibration procedure. This is done on a - single channel at a time. Write '1' to start the calibration. - What: /sys/bus/iio/devices/iio:deviceX/in_voltage2-voltage2_shorted_raw KernelVersion: Contact: linux-iio@vger.kernel.org Description: Measure voltage from AIN2 pin connected to AIN(+) and AIN(-) shorted. - -What: /sys/bus/iio/devices/iio:deviceX/in_voltagex_sys_calibration_mode_available -KernelVersion: -Contact: linux-iio@vger.kernel.org -Description: - Reading returns a list with the possible calibration modes. - There are two available options: - "zero_scale" - calibrate to zero scale - "full_scale" - calibrate to full scale - -What: /sys/bus/iio/devices/iio:deviceX/in_voltagex_sys_calibration_mode -KernelVersion: -Contact: linux-iio@vger.kernel.org -Description: - Sets up the calibration mode used in the system calibration - procedure. Reading returns the current calibration mode. - Writing sets the system calibration mode. diff --git a/Documentation/ABI/testing/sysfs-class-platform-profile b/Documentation/ABI/testing/sysfs-class-platform-profile new file mode 100644 index 000000000000..dc72adfb830a --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-platform-profile @@ -0,0 +1,48 @@ +What: /sys/class/platform-profile/platform-profile-X/name +Date: March 2025 +KernelVersion: 6.14 +Description: Name of the class device given by the driver. + + RO + +What: /sys/class/platform-profile/platform-profile-X/choices +Date: March 2025 +KernelVersion: 6.14 +Description: This file contains a space-separated list of profiles supported + for this device. + + Drivers must use the following standard profile-names: + + ==================== ======================================== + low-power Low power consumption + cool Cooler operation + quiet Quieter operation + balanced Balance between low power consumption + and performance + balanced-performance Balance between performance and low + power consumption with a slight bias + towards performance + performance High performance operation + custom Driver defined custom profile + ==================== ======================================== + + RO + +What: /sys/class/platform-profile/platform-profile-X/profile +Date: March 2025 +KernelVersion: 6.14 +Description: Reading this file gives the current selected profile for this + device. Writing this file with one of the strings from + platform_profile_choices changes the profile to the new value. + + This file can be monitored for changes by polling for POLLPRI, + POLLPRI will be signaled on any changes, independent of those + changes coming from a userspace write; or coming from another + source such as e.g. a hotkey triggered profile change handled + either directly by the embedded-controller or fully handled + inside the kernel. + + This file may also emit the string 'custom' to indicate + that the driver is using a driver defined custom profile. + + RW diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power index 45180b62d426..2a5c1a09a28f 100644 --- a/Documentation/ABI/testing/sysfs-class-power +++ b/Documentation/ABI/testing/sysfs-class-power @@ -407,10 +407,30 @@ Description: Access: Read, Write + Reading this returns the current active value, e.g. 'Standard'. + Check charge_types to get the values supported by the battery. + Valid values: "Unknown", "N/A", "Trickle", "Fast", "Standard", "Adaptive", "Custom", "Long Life", "Bypass" +What: /sys/class/power_supply//charge_types +Date: December 2024 +Contact: linux-pm@vger.kernel.org +Description: + Identical to charge_type but reading returns a list of supported + charge-types with the currently active type surrounded by square + brackets, e.g.: "Fast [Standard] Long_Life". + + power_supply class devices may support both charge_type and + charge_types for backward compatibility. In this case both will + always have the same active value and the active value can be + changed by writing either property. + + Note charge-types which contain a space such as "Long Life" will + have the space replaced by a '_' resulting in e.g. "Long_Life". + When writing charge-types both variants are accepted. + What: /sys/class/power_supply//charge_term_current Date: July 2014 Contact: linux-pm@vger.kernel.org @@ -433,7 +453,7 @@ Description: Valid values: "Unknown", "Good", "Overheat", "Dead", - "Over voltage", "Unspecified failure", "Cold", + "Over voltage", "Under voltage", "Unspecified failure", "Cold", "Watchdog timer expire", "Safety timer expire", "Over current", "Calibration required", "Warm", "Cool", "Hot", "No battery" @@ -793,3 +813,12 @@ Description: Access: Read Valid values: 1-31 + +What: /sys/class/power_supply//extensions/ +Date: March 2025 +Contact: linux-pm@vger.kernel.org +Description: + Reports the extensions registered to the power supply. + Each entry is a link to the device which registered the extension. + + Access: Read diff --git a/Documentation/ABI/testing/sysfs-class-power-max1720x b/Documentation/ABI/testing/sysfs-class-power-max1720x new file mode 100644 index 000000000000..7d895bfda9ce --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-power-max1720x @@ -0,0 +1,32 @@ +What: /sys/class/power_supply/max1720x/temp_ain1 +Date: January 2025 +KernelVersion: 6.14 +Contact: Dimitri Fedrau +Description: + Reports the current temperature reading from AIN1 thermistor. + + Access: Read + + Valid values: Represented in 1/10 Degrees Celsius + +What: /sys/class/power_supply/max1720x/temp_ain2 +Date: January 2025 +KernelVersion: 6.14 +Contact: Dimitri Fedrau +Description: + Reports the current temperature reading from AIN2 thermistor. + + Access: Read + + Valid values: Represented in 1/10 Degrees Celsius + +What: /sys/class/power_supply/max1720x/temp_int +Date: January 2025 +KernelVersion: 6.14 +Contact: Dimitri Fedrau +Description: + Reports the current temperature reading from internal die. + + Access: Read + + Valid values: Represented in 1/10 Degrees Celsius diff --git a/Documentation/ABI/testing/sysfs-kernel-livepatch b/Documentation/ABI/testing/sysfs-kernel-livepatch index 3735d868013d..3c3f36b32b57 100644 --- a/Documentation/ABI/testing/sysfs-kernel-livepatch +++ b/Documentation/ABI/testing/sysfs-kernel-livepatch @@ -55,6 +55,15 @@ Description: An attribute which indicates whether the patch supports atomic-replace. +What: /sys/kernel/livepatch//stack_order +Date: Jan 2025 +KernelVersion: 6.14.0 +Description: + This attribute specifies the sequence in which live patch modules + are applied to the system. If multiple live patches modify the same + function, the implementation with the biggest 'stack_order' number + is used, unless a transition is currently in progress. + What: /sys/kernel/livepatch// Date: Nov 2014 KernelVersion: 3.19.0 diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon index f1b90cf1249b..b057eddefbfc 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-damon +++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -355,10 +355,15 @@ Description: If 'target' is written to the 'type' file, writing to or What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//filters//matching Date: Dec 2022 Contact: SeongJae Park -Description: Writing 'Y' or 'N' to this file sets whether to filter out - pages that do or do not match to the 'type' and 'memcg_path', - respectively. Filter out means the action of the scheme will - not be applied to. +Description: Writing 'Y' or 'N' to this file sets whether the filter is for + the memory of the 'type', or all except the 'type'. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//filters//allow +Date: Jan 2025 +Contact: SeongJae Park +Description: Writing 'Y' or 'N' to this file sets whether to allow or reject + applying the scheme's action to the memory that satisfies the + 'type' and the 'matching' of the directory. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/nr_tried Date: Mar 2022 @@ -384,6 +389,12 @@ Contact: SeongJae Park Description: Reading this file returns the total size of regions that the action of the scheme has successfully applied in bytes. +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/sz_ops_filter_passed +Date: Dec 2024 +Contact: SeongJae Park +Description: Reading this file returns the total size of memory that passed + DAMON operations layer-handled filters of the scheme in bytes. + What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/qt_exceeds Date: Mar 2022 Contact: SeongJae Park @@ -424,3 +435,10 @@ Contact: SeongJae Park Description: Reading this file returns the 'age' of a memory region that corresponding DAMON-based Operation Scheme's action has tried to be applied. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//tried_regions//sz_filter_passed +Date: Dec 2024 +Contact: SeongJae Park +Description: Reading this file returns the size of the memory in the region + that passed DAMON operations layer-handled filters of the + scheme in bytes. diff --git a/Documentation/ABI/testing/sysfs-platform-mellanox-pmc b/Documentation/ABI/testing/sysfs-platform-mellanox-pmc new file mode 100644 index 000000000000..29b3f9c58e00 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-platform-mellanox-pmc @@ -0,0 +1,64 @@ +HID Driver Description +MLNXBFD0 mlxbf-pmc Performance counters (BlueField-1) +MLNXBFD1 mlxbf-pmc Performance counters (BlueField-2) +MLNXBFD2 mlxbf-pmc Performance counters (BlueField-3) + +What: /sys/bus/platform/devices//hwmon/hwmonX//event_list +Date: Dec 2020 +KernelVersion: 5.10 +Contact: "Shravan Kumar Ramani " +Description: + List of events supported by the counters in the specific block. + It is used to extract the event number or ID associated with + each event. + +What: /sys/bus/platform/devices//hwmon/hwmonX//event +Date: Dec 2020 +KernelVersion: 5.10 +Contact: "Shravan Kumar Ramani " +Description: + Event monitored by corresponding counter. This is used to + program or read back the event that should be or is currently + being monitored by counter. + +What: /sys/bus/platform/devices//hwmon/hwmonX//counter +Date: Dec 2020 +KernelVersion: 5.10 +Contact: "Shravan Kumar Ramani " +Description: + Counter value of the event being monitored. This is used to + read the counter value of the event which was programmed using + event. This is also used to clear or reset the counter value + by writing 0 to the counter sysfs. + +What: /sys/bus/platform/devices//hwmon/hwmonX//enable +Date: Dec 2020 +KernelVersion: 5.10 +Contact: "Shravan Kumar Ramani " +Description: + Start or stop counters. This is used to start the counters + for monitoring the programmed events and also to stop the + counters after the desired duration. Writing value 1 will + start all the counters in the block, and writing 0 will + stop all the counters together. + +What: /sys/bus/platform/devices//hwmon/hwmonX// +Date: Dec 2020 +KernelVersion: 5.10 +Contact: "Shravan Kumar Ramani " +Description: + Value of register. This is used to read or reset the registers + where various performance statistics are counted for each block. + Writing 0 to the sysfs will clear the counter, writing any other + value is not allowed. + +What: /sys/bus/platform/devices//hwmon/hwmonX//count_clock +Date: Mar 2025 +KernelVersion: 6.14 +Contact: "Shravan Kumar Ramani " +Description: + Use a counter for counting cycles. This is used to repurpose/dedicate + any of the counters in the block to counting cycles. Each counter is + represented by a bit (bit 0 for counter0, bit1 for counter1 and so on) + and setting the corresponding bit will reserve that specific counter + for counting cycles and override the event setting. diff --git a/Documentation/ABI/testing/sysfs-platform_profile b/Documentation/ABI/testing/sysfs-platform_profile index baf1d125f9f8..125324ab53a9 100644 --- a/Documentation/ABI/testing/sysfs-platform_profile +++ b/Documentation/ABI/testing/sysfs-platform_profile @@ -33,3 +33,8 @@ Description: Reading this file gives the current selected profile for this source such as e.g. a hotkey triggered profile change handled either directly by the embedded-controller or fully handled inside the kernel. + + This file may also emit the string 'custom' to indicate + that multiple platform profiles drivers are in use but + have different values. This string can not be written to + this interface and is solely for informational purposes. diff --git a/Documentation/ABI/testing/sysfs-pps-gen b/Documentation/ABI/testing/sysfs-pps-gen new file mode 100644 index 000000000000..2519207b88fd --- /dev/null +++ b/Documentation/ABI/testing/sysfs-pps-gen @@ -0,0 +1,43 @@ +What: /sys/class/pps-gen/ +Date: February 2025 +KernelVersion: 6.13 +Contact: Rodolfo Giometti +Description: + The /sys/class/pps-gen/ directory contains files and + directories that provide a unified interface to the PPS + generators. + +What: /sys/class/pps-gen/pps-genX/ +Date: February 2025 +KernelVersion: 6.13 +Contact: Rodolfo Giometti +Description: + The /sys/class/pps-gen/pps-genX/ directory is related to X-th + PPS generator in the system. Each directory contain files to + manage and control its PPS generator. + +What: /sys/class/pps-gen/pps-genX/enable +Date: February 2025 +KernelVersion: 6.13 +Contact: Rodolfo Giometti +Description: + This write-only file enables or disables generation of the + PPS signal. + +What: /sys/class/pps-gen/pps-genX/system +Date: February 2025 +KernelVersion: 6.13 +Contact: Rodolfo Giometti +Description: + This read-only file returns "1" if the generator takes the + timing from the system clock, while it returns "0" if not + (i.e. from a peripheral device clock). + +What: /sys/class/pps-gen/pps-genX/time +Date: February 2025 +KernelVersion: 6.13 +Contact: Rodolfo Giometti +Description: + This read-only file contains the current time stored into the + generator clock as two integers representing the current time + seconds and nanoseconds. diff --git a/Documentation/Makefile b/Documentation/Makefile index fa71602ec961..52c6c5a3efa9 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -104,7 +104,7 @@ quiet_cmd_sphinx = SPHINX $@ --> file://$(abspath $(BUILDDIR)/$3/$4) YNL_INDEX:=$(srctree)/Documentation/networking/netlink_spec/index.rst YNL_RST_DIR:=$(srctree)/Documentation/networking/netlink_spec YNL_YAML_DIR:=$(srctree)/Documentation/netlink/specs -YNL_TOOL:=$(srctree)/tools/net/ynl/ynl-gen-rst.py +YNL_TOOL:=$(srctree)/tools/net/ynl/pyynl/ynl_gen_rst.py YNL_RST_FILES_TMP := $(patsubst %.yaml,%.rst,$(wildcard $(YNL_YAML_DIR)/*.yaml)) YNL_RST_FILES := $(patsubst $(YNL_YAML_DIR)%,$(YNL_RST_DIR)%, $(YNL_RST_FILES_TMP)) diff --git a/Documentation/PCI/endpoint/index.rst b/Documentation/PCI/endpoint/index.rst index 4d2333e7ae06..dd1f62e731c9 100644 --- a/Documentation/PCI/endpoint/index.rst +++ b/Documentation/PCI/endpoint/index.rst @@ -15,6 +15,7 @@ PCI Endpoint Framework pci-ntb-howto pci-vntb-function pci-vntb-howto + pci-nvme-function function/binding/pci-test function/binding/pci-ntb diff --git a/Documentation/PCI/endpoint/pci-nvme-function.rst b/Documentation/PCI/endpoint/pci-nvme-function.rst new file mode 100644 index 000000000000..df57b8e7d066 --- /dev/null +++ b/Documentation/PCI/endpoint/pci-nvme-function.rst @@ -0,0 +1,13 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================= +PCI NVMe Function +================= + +:Author: Damien Le Moal + +The PCI NVMe endpoint function implements a PCI NVMe controller using the NVMe +subsystem target core code. The driver for this function resides with the NVMe +subsystem as drivers/nvme/target/nvmet-pciep.c. + +See Documentation/nvme/nvme-pci-endpoint-target.rst for more details. diff --git a/Documentation/PCI/endpoint/pci-test-howto.rst b/Documentation/PCI/endpoint/pci-test-howto.rst index 909f770a07d6..aafc17ef3fd3 100644 --- a/Documentation/PCI/endpoint/pci-test-howto.rst +++ b/Documentation/PCI/endpoint/pci-test-howto.rst @@ -81,8 +81,8 @@ device, the following commands can be used:: # echo 0x104c > functions/pci_epf_test/func1/vendorid # echo 0xb500 > functions/pci_epf_test/func1/deviceid - # echo 16 > functions/pci_epf_test/func1/msi_interrupts - # echo 8 > functions/pci_epf_test/func1/msix_interrupts + # echo 32 > functions/pci_epf_test/func1/msi_interrupts + # echo 2048 > functions/pci_epf_test/func1/msix_interrupts Binding pci-epf-test Device to EP Controller @@ -123,113 +123,83 @@ above:: Using Endpoint Test function Device ----------------------------------- -pcitest.sh added in tools/pci/ can be used to run all the default PCI endpoint -tests. To compile this tool the following commands should be used:: +Kselftest added in tools/testing/selftests/pci_endpoint can be used to run all +the default PCI endpoint tests. To build the Kselftest for PCI endpoint +subsystem, the following commands should be used:: # cd - # make -C tools/pci + # make -C tools/testing/selftests/pci_endpoint or if you desire to compile and install in your system:: # cd - # make -C tools/pci install + # make -C tools/testing/selftests/pci_endpoint INSTALL_PATH=/usr/bin install -The tool and script will be located in /usr/bin/ +The test will be located in /usr/bin/ - -pcitest.sh Output -~~~~~~~~~~~~~~~~~ +Kselftest Output +~~~~~~~~~~~~~~~~ :: - # pcitest.sh - BAR tests + # pci_endpoint_test + TAP version 13 + 1..16 + # Starting 16 tests from 9 test cases. + # RUN pci_ep_bar.BAR0.BAR_TEST ... + # OK pci_ep_bar.BAR0.BAR_TEST + ok 1 pci_ep_bar.BAR0.BAR_TEST + # RUN pci_ep_bar.BAR1.BAR_TEST ... + # OK pci_ep_bar.BAR1.BAR_TEST + ok 2 pci_ep_bar.BAR1.BAR_TEST + # RUN pci_ep_bar.BAR2.BAR_TEST ... + # OK pci_ep_bar.BAR2.BAR_TEST + ok 3 pci_ep_bar.BAR2.BAR_TEST + # RUN pci_ep_bar.BAR3.BAR_TEST ... + # OK pci_ep_bar.BAR3.BAR_TEST + ok 4 pci_ep_bar.BAR3.BAR_TEST + # RUN pci_ep_bar.BAR4.BAR_TEST ... + # OK pci_ep_bar.BAR4.BAR_TEST + ok 5 pci_ep_bar.BAR4.BAR_TEST + # RUN pci_ep_bar.BAR5.BAR_TEST ... + # OK pci_ep_bar.BAR5.BAR_TEST + ok 6 pci_ep_bar.BAR5.BAR_TEST + # RUN pci_ep_basic.CONSECUTIVE_BAR_TEST ... + # OK pci_ep_basic.CONSECUTIVE_BAR_TEST + ok 7 pci_ep_basic.CONSECUTIVE_BAR_TEST + # RUN pci_ep_basic.LEGACY_IRQ_TEST ... + # OK pci_ep_basic.LEGACY_IRQ_TEST + ok 8 pci_ep_basic.LEGACY_IRQ_TEST + # RUN pci_ep_basic.MSI_TEST ... + # OK pci_ep_basic.MSI_TEST + ok 9 pci_ep_basic.MSI_TEST + # RUN pci_ep_basic.MSIX_TEST ... + # OK pci_ep_basic.MSIX_TEST + ok 10 pci_ep_basic.MSIX_TEST + # RUN pci_ep_data_transfer.memcpy.READ_TEST ... + # OK pci_ep_data_transfer.memcpy.READ_TEST + ok 11 pci_ep_data_transfer.memcpy.READ_TEST + # RUN pci_ep_data_transfer.memcpy.WRITE_TEST ... + # OK pci_ep_data_transfer.memcpy.WRITE_TEST + ok 12 pci_ep_data_transfer.memcpy.WRITE_TEST + # RUN pci_ep_data_transfer.memcpy.COPY_TEST ... + # OK pci_ep_data_transfer.memcpy.COPY_TEST + ok 13 pci_ep_data_transfer.memcpy.COPY_TEST + # RUN pci_ep_data_transfer.dma.READ_TEST ... + # OK pci_ep_data_transfer.dma.READ_TEST + ok 14 pci_ep_data_transfer.dma.READ_TEST + # RUN pci_ep_data_transfer.dma.WRITE_TEST ... + # OK pci_ep_data_transfer.dma.WRITE_TEST + ok 15 pci_ep_data_transfer.dma.WRITE_TEST + # RUN pci_ep_data_transfer.dma.COPY_TEST ... + # OK pci_ep_data_transfer.dma.COPY_TEST + ok 16 pci_ep_data_transfer.dma.COPY_TEST + # PASSED: 16 / 16 tests passed. + # Totals: pass:16 fail:0 xfail:0 xpass:0 skip:0 error:0 - BAR0: OKAY - BAR1: OKAY - BAR2: OKAY - BAR3: OKAY - BAR4: NOT OKAY - BAR5: NOT OKAY - Interrupt tests +Testcase 16 (pci_ep_data_transfer.dma.COPY_TEST) will fail for most of the DMA +capable endpoint controllers due to the absence of the MEMCPY over DMA. For such +controllers, it is advisable to skip this testcase using this +command:: - SET IRQ TYPE TO LEGACY: OKAY - LEGACY IRQ: NOT OKAY - SET IRQ TYPE TO MSI: OKAY - MSI1: OKAY - MSI2: OKAY - MSI3: OKAY - MSI4: OKAY - MSI5: OKAY - MSI6: OKAY - MSI7: OKAY - MSI8: OKAY - MSI9: OKAY - MSI10: OKAY - MSI11: OKAY - MSI12: OKAY - MSI13: OKAY - MSI14: OKAY - MSI15: OKAY - MSI16: OKAY - MSI17: NOT OKAY - MSI18: NOT OKAY - MSI19: NOT OKAY - MSI20: NOT OKAY - MSI21: NOT OKAY - MSI22: NOT OKAY - MSI23: NOT OKAY - MSI24: NOT OKAY - MSI25: NOT OKAY - MSI26: NOT OKAY - MSI27: NOT OKAY - MSI28: NOT OKAY - MSI29: NOT OKAY - MSI30: NOT OKAY - MSI31: NOT OKAY - MSI32: NOT OKAY - SET IRQ TYPE TO MSI-X: OKAY - MSI-X1: OKAY - MSI-X2: OKAY - MSI-X3: OKAY - MSI-X4: OKAY - MSI-X5: OKAY - MSI-X6: OKAY - MSI-X7: OKAY - MSI-X8: OKAY - MSI-X9: NOT OKAY - MSI-X10: NOT OKAY - MSI-X11: NOT OKAY - MSI-X12: NOT OKAY - MSI-X13: NOT OKAY - MSI-X14: NOT OKAY - MSI-X15: NOT OKAY - MSI-X16: NOT OKAY - [...] - MSI-X2047: NOT OKAY - MSI-X2048: NOT OKAY - - Read Tests - - SET IRQ TYPE TO MSI: OKAY - READ ( 1 bytes): OKAY - READ ( 1024 bytes): OKAY - READ ( 1025 bytes): OKAY - READ (1024000 bytes): OKAY - READ (1024001 bytes): OKAY - - Write Tests - - WRITE ( 1 bytes): OKAY - WRITE ( 1024 bytes): OKAY - WRITE ( 1025 bytes): OKAY - WRITE (1024000 bytes): OKAY - WRITE (1024001 bytes): OKAY - - Copy Tests - - COPY ( 1 bytes): OKAY - COPY ( 1024 bytes): OKAY - COPY ( 1025 bytes): OKAY - COPY (1024000 bytes): OKAY - COPY (1024001 bytes): OKAY + # pci_endpoint_test -f pci_ep_bar -f pci_ep_basic -v memcpy -T COPY_TEST -v dma diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst index f61c01fc376e..210c194d4a7b 100644 --- a/Documentation/accounting/delay-accounting.rst +++ b/Documentation/accounting/delay-accounting.rst @@ -100,29 +100,29 @@ Get delays, since system boot, for pid 10:: # ./getdelays -d -p 10 (output similar to next case) -Get sum of delays, since system boot, for all pids with tgid 5:: +Get sum and peak of delays, since system boot, for all pids with tgid 242:: - # ./getdelays -d -t 5 + bash-4.4# ./getdelays -d -t 242 print delayacct stats ON - TGID 5 + TGID 242 - CPU count real total virtual total delay total delay average - 8 7000000 6872122 3382277 0.423ms - IO count delay total delay average - 0 0 0.000ms - SWAP count delay total delay average - 0 0 0.000ms - RECLAIM count delay total delay average - 0 0 0.000ms - THRASHING count delay total delay average - 0 0 0.000ms - COMPACT count delay total delay average - 0 0 0.000ms - WPCOPY count delay total delay average - 0 0 0.000ms - IRQ count delay total delay average - 0 0 0.000ms + CPU count real total virtual total delay total delay average delay max delay min + 39 156000000 156576579 2111069 0.054ms 0.212296ms 0.031307ms + IO count delay total delay average delay max delay min + 0 0 0.000ms 0.000000ms 0.000000ms + SWAP count delay total delay average delay max delay min + 0 0 0.000ms 0.000000ms 0.000000ms + RECLAIM count delay total delay average delay max delay min + 0 0 0.000ms 0.000000ms 0.000000ms + THRASHING count delay total delay average delay max delay min + 0 0 0.000ms 0.000000ms 0.000000ms + COMPACT count delay total delay average delay max delay min + 0 0 0.000ms 0.000000ms 0.000000ms + WPCOPY count delay total delay average delay max delay min + 156 11215873 0.072ms 0.207403ms 0.033913ms + IRQ count delay total delay average delay max delay min + 0 0 0.000ms 0.000000ms 0.000000ms Get IO accounting for pid 1, it works only with -p:: diff --git a/Documentation/accounting/taskstats-struct.rst b/Documentation/accounting/taskstats-struct.rst index ca90fd489c9a..acca51c34157 100644 --- a/Documentation/accounting/taskstats-struct.rst +++ b/Documentation/accounting/taskstats-struct.rst @@ -47,7 +47,7 @@ should not change the relative position of each field within the struct. 1) Common and basic accounting fields:: /* The version number of this struct. This field is always set to - * TAKSTATS_VERSION, which is defined in . + * TASKSTATS_VERSION, which is defined in . * Each time the struct is changed, the value should be incremented. */ __u16 version; diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst index f2bebff6a733..eb9452668909 100644 --- a/Documentation/admin-guide/README.rst +++ b/Documentation/admin-guide/README.rst @@ -356,5 +356,5 @@ instructions at 'Documentation/admin-guide/reporting-issues.rst'. Hints on understanding kernel bug reports are in 'Documentation/admin-guide/bug-hunting.rst'. More on debugging the kernel -with gdb is in 'Documentation/dev-tools/gdb-kernel-debugging.rst' and -'Documentation/dev-tools/kgdb.rst'. +with gdb is in 'Documentation/process/debugging/gdb-kernel-debugging.rst' and +'Documentation/process/debugging/kgdb.rst'. diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst index 714a5171bfc0..1576fb93f06c 100644 --- a/Documentation/admin-guide/blockdev/zram.rst +++ b/Documentation/admin-guide/blockdev/zram.rst @@ -121,14 +121,14 @@ compression algorithm to use external pre-trained dictionary, pass full path to the `dict` along with other parameters:: #pass path to pre-trained zstd dictionary - echo "algo=zstd dict=/etc/dictioary" > /sys/block/zram0/algorithm_params + echo "algo=zstd dict=/etc/dictionary" > /sys/block/zram0/algorithm_params #same, but using algorithm priority - echo "priority=1 dict=/etc/dictioary" > \ + echo "priority=1 dict=/etc/dictionary" > \ /sys/block/zram0/algorithm_params #pass path to pre-trained zstd dictionary and compression level - echo "algo=zstd level=8 dict=/etc/dictioary" > \ + echo "algo=zstd level=8 dict=/etc/dictionary" > \ /sys/block/zram0/algorithm_params Parameters are algorithm specific: not all algorithms support pre-trained diff --git a/Documentation/admin-guide/braille-console.rst b/Documentation/admin-guide/braille-console.rst index 18e79337dcfd..153472e93cae 100644 --- a/Documentation/admin-guide/braille-console.rst +++ b/Documentation/admin-guide/braille-console.rst @@ -21,8 +21,8 @@ override the baud rate to 115200, etc. By default, the braille device will just show the last kernel message (console mode). To review previous messages, press the Insert key to switch to the VT review mode. In review mode, the arrow keys permit to browse in the VT content, -:kbd:`PAGE-UP`/:kbd:`PAGE-DOWN` keys go at the top/bottom of the screen, and -the :kbd:`HOME` key goes back +`PAGE-UP`/`PAGE-DOWN` keys go at the top/bottom of the screen, and +the `HOME` key goes back to the cursor, hence providing very basic screen reviewing facility. Sound feedback can be obtained by adding the ``braille_console.sound=1`` kernel diff --git a/Documentation/admin-guide/bug-hunting.rst b/Documentation/admin-guide/bug-hunting.rst index 1d0f8ceb3075..ce6f4e8ca487 100644 --- a/Documentation/admin-guide/bug-hunting.rst +++ b/Documentation/admin-guide/bug-hunting.rst @@ -368,12 +368,3 @@ processed by ``klogd``:: Aug 29 09:51:01 blizard kernel: Call Trace: [oops:_oops_ioctl+48/80] [_sys_ioctl+254/272] [_system_call+82/128] Aug 29 09:51:01 blizard kernel: Code: c7 00 05 00 00 00 eb 08 90 90 90 90 90 90 90 90 89 ec 5d c3 ---------------------------------------------------------------------------- - -:: - - Dr. G.W. Wettstein Oncology Research Div. Computing Facility - Roger Maris Cancer Center INTERNET: greg@wind.rmcc.com - 820 4th St. N. - Fargo, ND 58122 - Phone: 701-234-7556 diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 315ede811c9d..cb1b4e759b7e 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -64,13 +64,14 @@ v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst . There are also arch-specific kernel-parameters not documented here. -See for example . Note that ALL kernel parameters listed below are CASE SENSITIVE, and that a trailing = on the name of any parameter states that that parameter will diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 3872bc6ec49d..fb8752b42ec8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -21,6 +21,10 @@ strictly ACPI specification compliant. rsdt -- prefer RSDT over (default) XSDT copy_dsdt -- copy DSDT to memory + nocmcff -- Disable firmware first mode for corrected + errors. This disables parsing the HEST CMC error + source to check if firmware has set the FF flag. This + may result in duplicate corrected error reports. nospcr -- disable console in ACPI SPCR table as default _serial_ console on ARM64 For ARM64, ONLY "acpi=off", "acpi=on", "acpi=force" or @@ -405,6 +409,8 @@ not play well with APC CPU idle - disable it if you have APC and your system crashes randomly. + apic [APIC,X86-64] Use IO-APIC. Default. + apic= [APIC,X86,EARLY] Advanced Programmable Interrupt Controller Change the output verbosity while booting Format: { quiet (default) | verbose | debug } @@ -424,6 +430,10 @@ useful so that a dump capture kernel won't be shot down by NMI + apicpmtimer Do APIC timer calibration using the pmtimer. Implies + apicmaintimer. Useful when your PIT timer is totally + broken. + autoconf= [IPV6] See Documentation/networking/ipv6.rst. @@ -1726,6 +1736,8 @@ off: Disable GDS mitigation. + gbpages [X86] Use GB pages for kernel direct mappings. + gcov_persist= [GCOV] When non-zero (default), profiling data for kernel modules is saved and remains accessible via debugfs, even when the module is unloaded/reloaded. @@ -2008,12 +2020,21 @@ idle= [X86,EARLY] Format: idle=poll, idle=halt, idle=nomwait - Poll forces a polling idle loop that can slightly - improve the performance of waking up a idle CPU, but - will use a lot of power and make the system run hot. - Not recommended. + + idle=poll: Don't do power saving in the idle loop + using HLT, but poll for rescheduling event. This will + make the CPUs eat a lot more power, but may be useful + to get slightly better performance in multiprocessor + benchmarks. It also makes some profiling using + performance counters more accurate. Please note that + on systems with MONITOR/MWAIT support (like Intel + EM64T CPUs) this option has no performance advantage + over the normal idle loop. It may also interact badly + with hyperthreading. + idle=halt: Halt is forced to be used for CPU idle. In such case C2/C3 won't be used again. + idle=nomwait: Disable mwait for CPU C-states idxd.sva= [HW] @@ -2311,20 +2332,73 @@ relaxed iommu= [X86,EARLY] + off + Don't initialize and use any kind of IOMMU. + force + Force the use of the hardware IOMMU even when + it is not actually needed (e.g. because < 3 GB + memory). + noforce + Don't force hardware IOMMU usage when it is not + needed. (default). + biomerge panic nopanic merge nomerge + soft - pt [X86] - nopt [X86] - nobypass [PPC/POWERNV] + Use software bounce buffering (SWIOTLB) (default for + Intel machines). This can be used to prevent the usage + of an available hardware IOMMU. + + [X86] + pt + [X86] + nopt + [PPC/POWERNV] + nobypass Disable IOMMU bypass, using IOMMU for PCI devices. + [X86] + AMD Gart HW IOMMU-specific options: + + + Set the size of the remapping area in bytes. + + allowed + Overwrite iommu off workarounds for specific chipsets + + fullflush + Flush IOMMU on each allocation (default). + + nofullflush + Don't use IOMMU fullflush. + + memaper[=] + Allocate an own aperture over RAM with size + 32MB<1 and 1=>0 transitions of the number of VMs. - Enabling virtualization at module lode avoids potential + Enabling virtualization at module load avoids potential latency for creation of the 0=>1 VM, as KVM serializes virtualization enabling across all online CPUs. The "cost" of enabling virtualization when KVM is loaded, @@ -2748,17 +2824,21 @@ nvhe: Standard nVHE-based mode, without support for protected guests. - protected: nVHE-based mode with support for guests whose - state is kept private from the host. + protected: Mode with support for guests whose state is + kept private from the host, using VHE or + nVHE depending on HW support. nested: VHE-based mode with support for nested - virtualization. Requires at least ARMv8.3 - hardware. + virtualization. Requires at least ARMv8.4 + hardware (with FEAT_NV2). Defaults to VHE/nVHE based on hardware support. Setting mode to "protected" will disable kexec and hibernation - for the host. "nested" is experimental and should be - used with extreme caution. + for the host. To force nVHE on VHE hardware, add + "arm64_sw.hvhe=0 id_aa64mmfr1.vh=0" to the + command-line. + "nested" is experimental and should be used with + extreme caution. kvm-arm.vgic_v3_group0_trap= [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0 @@ -3259,9 +3339,77 @@ devices can be requested on-demand with the /dev/loop-control interface. - mce [X86-32] Machine Check Exception + mce= [X86-{32,64}] + + Please see Documentation/arch/x86/x86_64/machinecheck.rst for sysfs runtime tunables. + + off + disable machine check + + no_cmci + disable CMCI(Corrected Machine Check Interrupt) that + Intel processor supports. Usually this disablement is + not recommended, but it might be handy if your + hardware is misbehaving. + + Note that you'll get more problems without CMCI than + with due to the shared banks, i.e. you might get + duplicated error logs. + + dont_log_ce + don't make logs for corrected errors. All events + reported as corrected are silently cleared by OS. This + option will be useful if you have no interest in any + of corrected errors. + + ignore_ce + disable features for corrected errors, e.g. + polling timer and CMCI. All events reported as + corrected are not cleared by OS and remained in its + error banks. + + Usually this disablement is not recommended, however + if there is an agent checking/clearing corrected + errors (e.g. BIOS or hardware monitoring + applications), conflicting with OS's error handling, + and you cannot deactivate the agent, then this option + will be a help. + + no_lmce + do not opt-in to Local MCE delivery. Use legacy method + to broadcast MCEs. + + bootlog + enable logging of machine checks left over from + booting. Disabled by default on AMD Fam10h and older + because some BIOS leave bogus ones. + + If your BIOS doesn't do that it's a good idea to + enable though to make sure you log even machine check + events that result in a reboot. On Intel systems it is + enabled by default. + + nobootlog + disable boot machine check logging. + + monarchtimeout (number) + sets the time in us to wait for other CPUs on machine + checks. 0 to disable. + + bios_cmci_threshold + don't overwrite the bios-set CMCI threshold. This boot + option prevents Linux from overwriting the CMCI + threshold set by the bios. Without this option, Linux + always sets the CMCI threshold to 1. Enabling this may + make memory predictive failure analysis less effective + if the bios sets thresholds for memory errors since we + will not see details for all errors. + + recovery + force-enable recoverable machine check code paths + + Everything else is in sysfs now. - mce=option [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst md= [HW] RAID subsystems devices and level See Documentation/admin-guide/md.rst. @@ -3351,8 +3499,8 @@ [KNL] Set the initial state for the memory hotplug onlining policy. If not specified, the default value is set according to the - CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config - option. + CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel config + options. See Documentation/admin-guide/mm/memory-hotplug.rst. memmap=exactmap [KNL,X86,EARLY] Enable setting of an exact @@ -3887,6 +4035,8 @@ noapic [SMP,APIC,EARLY] Tells the kernel to not make use of any IOAPICs that may be present in the system. + noapictimer [APIC,X86] Don't set up the APIC timer + noautogroup Disable scheduler automatic task group creation. nocache [ARM,EARLY] @@ -3934,6 +4084,8 @@ register save and restore. The kernel will only save legacy floating-point registers on task switch. + nogbpages [X86] Do not use GB pages for kernel direct mappings. + no_hash_pointers [KNL,EARLY] Force pointers printed to the console or buffers to be @@ -3960,6 +4112,8 @@ the impact of the sleep instructions. This is also useful when using JTAG debugger. + nohpet [X86] Don't use the HPET timer. + nohugeiomap [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge I/O mappings. nohugevmalloc [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge vmalloc mappings. @@ -4111,8 +4265,10 @@ nosync [HW,M68K] Disables sync negotiation for all devices. - no_timer_check [X86,APIC] Disables the code which tests for - broken timer IRQ sources. + no_timer_check [X86,APIC] Disables the code which tests for broken + timer IRQ sources, i.e., the IO-APIC timer. This can + work around problems with incorrect timer + initialization on some boards. no_uaccess_flush [PPC,EARLY] Don't flush the L1-D cache after accessing user data. @@ -4192,6 +4348,11 @@ If given as an integer followed by 'U', it will divide each physical node into N emulated nodes. + numa=noacpi [X86] Don't parse the SRAT table for NUMA setup + + numa=nohmat [X86] Don't parse the HMAT table for NUMA setup, or + soft-reserved memory partitioning. + numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic NUMA balancing. Allowed values are enable and disable @@ -4673,7 +4834,7 @@ '1' – force enabled 'x' – unchanged For example, - pci=config_acs=10x + pci=config_acs=10x@pci:0:0 would configure all devices that support ACS to enable P2P Request Redirect, disable Translation Blocking, and leave Source @@ -5367,7 +5528,42 @@ rcutorture.gp_cond= [KNL] Use conditional/asynchronous update-side - primitives, if available. + normal-grace-period primitives, if available. + + rcutorture.gp_cond_exp= [KNL] + Use conditional/asynchronous update-side + expedited-grace-period primitives, if available. + + rcutorture.gp_cond_full= [KNL] + Use conditional/asynchronous update-side + normal-grace-period primitives that also take + concurrent expedited grace periods into account, + if available. + + rcutorture.gp_cond_exp_full= [KNL] + Use conditional/asynchronous update-side + expedited-grace-period primitives that also take + concurrent normal grace periods into account, + if available. + + rcutorture.gp_cond_wi= [KNL] + Nominal wait interval for normal conditional + grace periods (specified by rcutorture's + gp_cond and gp_cond_full module parameters), + in microseconds. The actual wait interval will + be randomly selected to nanosecond granularity up + to this wait interval. Defaults to 16 jiffies, + for example, 16,000 microseconds on a system + with HZ=1000. + + rcutorture.gp_cond_wi_exp= [KNL] + Nominal wait interval for expedited conditional + grace periods (specified by rcutorture's + gp_cond_exp and gp_cond_exp_full module + parameters), in microseconds. The actual wait + interval will be randomly selected to nanosecond + granularity up to this wait interval. Defaults to + 128 microseconds. rcutorture.gp_exp= [KNL] Use expedited update-side primitives, if available. @@ -5376,6 +5572,43 @@ Use normal (non-expedited) asynchronous update-side primitives, if available. + rcutorture.gp_poll= [KNL] + Use polled update-side normal-grace-period + primitives, if available. + + rcutorture.gp_poll_exp= [KNL] + Use polled update-side expedited-grace-period + primitives, if available. + + rcutorture.gp_poll_full= [KNL] + Use polled update-side normal-grace-period + primitives that also take concurrent expedited + grace periods into account, if available. + + rcutorture.gp_poll_exp_full= [KNL] + Use polled update-side expedited-grace-period + primitives that also take concurrent normal + grace periods into account, if available. + + rcutorture.gp_poll_wi= [KNL] + Nominal wait interval for normal conditional + grace periods (specified by rcutorture's + gp_poll and gp_poll_full module parameters), + in microseconds. The actual wait interval will + be randomly selected to nanosecond granularity up + to this wait interval. Defaults to 16 jiffies, + for example, 16,000 microseconds on a system + with HZ=1000. + + rcutorture.gp_poll_wi_exp= [KNL] + Nominal wait interval for expedited conditional + grace periods (specified by rcutorture's + gp_poll_exp and gp_poll_exp_full module + parameters), in microseconds. The actual wait + interval will be randomly selected to nanosecond + granularity up to this wait interval. Defaults to + 128 microseconds. + rcutorture.gp_sync= [KNL] Use normal (non-expedited) synchronous update-side primitives, if available. If all @@ -5429,6 +5662,22 @@ Set time (jiffies) between CPU-hotplug operations, or zero to disable CPU-hotplug testing. + rcutorture.preempt_duration= [KNL] + Set duration (in milliseconds) of preemptions + by a high-priority FIFO real-time task. Set to + zero (the default) to disable. The CPUs to + preempt are selected randomly from the set that + are online at a given point in time. Races with + CPUs going offline are ignored, with that attempt + at preemption skipped. + + rcutorture.preempt_interval= [KNL] + Set interval (in milliseconds, defaulting to one + second) between preemptions by a high-priority + FIFO real-time task. This delay is mediated + by an hrtimer and is further fuzzed to avoid + inadvertent synchronizations. + rcutorture.read_exit_burst= [KNL] The number of times in a given read-then-exit episode that a set of read-then-exit kthreads @@ -5715,6 +5964,55 @@ reboot_cpu is s[mp]#### with #### being the processor to be used for rebooting. + acpi + Use the ACPI RESET_REG in the FADT. If ACPI is not + configured or the ACPI reset does not work, the reboot + path attempts the reset using the keyboard controller. + + bios + Use the CPU reboot vector for warm reset + + cold + Set the cold reboot flag + + default + There are some built-in platform specific "quirks" + - you may see: "reboot: series board detected. + Selecting for reboots." In the case where you + think the quirk is in error (e.g. you have newer BIOS, + or newer board) using this option will ignore the + built-in quirk table, and use the generic default + reboot actions. + + efi + Use efi reset_system runtime service. If EFI is not + configured or the EFI reset does not work, the reboot + path attempts the reset using the keyboard controller. + + force + Don't stop other CPUs on reboot. This can make reboot + more reliable in some cases. + + kbd + Use the keyboard controller. cold reset (default) + + pci + Use a write to the PCI config space register 0xcf9 to + trigger reboot. + + triple + Force a triple fault (init) + + warm + Don't set the cold reboot flag + + Using warm reset will be much faster especially on big + memory systems because the BIOS will not go through + the memory check. Disadvantage is that not all + hardware will be completely reinitialized on reboot so + there may be boot problems on some systems. + + refscale.holdoff= [KNL] Set test-start holdoff period. The purpose of this parameter is to delay the start of the @@ -6106,7 +6404,16 @@ serialnumber [BUGS=X86-32] - sev=option[,option...] [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst + sev=option[,option...] [X86-64] + + debug + Enable debug messages. + + nosnp + Do not enable SEV-SNP (applies to host/hypervisor + only). Setting 'nosnp' avoids the RMP check overhead + in memory accesses when users do not want to run + SEV-SNP guests. shapers= [NET] Maximal number of shapers. @@ -6858,6 +7165,14 @@ comma-separated list of trace events to enable. See also Documentation/trace/events.rst + To enable modules, use :mod: keyword: + + trace_event=:mod: + + The value before :mod: will only enable specific events + that are part of the module. See the above mentioned + document for more information. + trace_instance=[instance-info] [FTRACE] Create a ring buffer instance early in boot up. This will be listed in: @@ -6992,6 +7307,13 @@ See Documentation/admin-guide/mm/transhuge.rst for more details. + transparent_hugepage_tmpfs= [KNL] + Format: [always|within_size|advise|never] + Can be used to control the default hugepage allocation policy + for the tmpfs mount. + See Documentation/admin-guide/mm/transhuge.rst + for more details. + trusted.source= [KEYS] Format: This parameter identifies the trust source as a backend @@ -7474,7 +7796,7 @@ vt.cur_default= [VT] Default cursor shape. Format: 0xCCBBAA, where AA, BB, and CC are the same as the parameters of the [?A;B;Cc escape sequence; - see VGA-softcursor.txt. Default: 2 = underline. + see vga-softcursor.rst. Default: 2 = underline. vt.default_blu= [VT] Format: ,,,..., diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst index 7f674a6cfa8a..4ab0fef7d440 100644 --- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst +++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst @@ -445,8 +445,10 @@ event code Key Notes 0x1008 0x07 FN+F8 IBM: toggle screen expand Lenovo: configure UltraNav, or toggle screen expand. - On newer platforms (2024+) - replaced by 0x131f (see below) + On 2024 platforms replaced by + 0x131f (see below) and on newer + platforms (2025 +) keycode is + replaced by 0x1401 (see below). 0x1009 0x08 FN+F9 - @@ -506,9 +508,11 @@ event code Key Notes 0x1019 0x18 unknown -0x131f ... FN+F8 Platform Mode change. +0x131f ... FN+F8 Platform Mode change (2024 systems). Implemented in driver. +0x1401 ... FN+F8 Platform Mode change (2025 + systems). + Implemented in driver. ... ... ... 0x1020 0x1F unknown diff --git a/Documentation/admin-guide/media/ipu3.rst b/Documentation/admin-guide/media/ipu3.rst index 83b3cd03b35c..9c190942932e 100644 --- a/Documentation/admin-guide/media/ipu3.rst +++ b/Documentation/admin-guide/media/ipu3.rst @@ -98,7 +98,7 @@ frames in packed raw Bayer format to IPU3 CSI2 receiver. # and that ov5670 sensor is connected to i2c bus 10 with address 0x36 export SDEV=$(media-ctl -d $MDEV -e "ov5670 10-0036") - # Establish the link for the media devices using media-ctl [#f3]_ + # Establish the link for the media devices using media-ctl media-ctl -d $MDEV -l "ov5670:0 -> ipu3-csi2 0:0[1]" # Set the format for the media devices @@ -589,12 +589,8 @@ preserved. References ========== -.. [#f5] drivers/staging/media/ipu3/include/uapi/intel-ipu3.h - .. [#f1] https://github.com/intel/nvt .. [#f2] http://git.ideasonboard.org/yavta.git -.. [#f3] http://git.ideasonboard.org/?p=media-ctl.git;a=summary - .. [#f4] ImgU limitation requires an additional 16x16 for all input resolutions diff --git a/Documentation/admin-guide/mm/damon/start.rst b/Documentation/admin-guide/mm/damon/start.rst index c4dddf6733cd..ede14b679d02 100644 --- a/Documentation/admin-guide/mm/damon/start.rst +++ b/Documentation/admin-guide/mm/damon/start.rst @@ -42,32 +42,45 @@ the execution. :: $ git clone https://github.com/sjp38/masim; cd masim; make $ sudo damo start "./masim ./configs/stairs.cfg --quiet" - $ sudo ./damo show - 0 addr [85.541 TiB , 85.541 TiB ) (57.707 MiB ) access 0 % age 10.400 s - 1 addr [85.541 TiB , 85.542 TiB ) (413.285 MiB) access 0 % age 11.400 s - 2 addr [127.649 TiB , 127.649 TiB) (57.500 MiB ) access 0 % age 1.600 s - 3 addr [127.649 TiB , 127.649 TiB) (32.500 MiB ) access 0 % age 500 ms - 4 addr [127.649 TiB , 127.649 TiB) (9.535 MiB ) access 100 % age 300 ms - 5 addr [127.649 TiB , 127.649 TiB) (8.000 KiB ) access 60 % age 0 ns - 6 addr [127.649 TiB , 127.649 TiB) (6.926 MiB ) access 0 % age 1 s - 7 addr [127.998 TiB , 127.998 TiB) (120.000 KiB) access 0 % age 11.100 s - 8 addr [127.998 TiB , 127.998 TiB) (8.000 KiB ) access 40 % age 100 ms - 9 addr [127.998 TiB , 127.998 TiB) (4.000 KiB ) access 0 % age 11 s - total size: 577.590 MiB - $ sudo ./damo stop + $ sudo damo report access + heatmap: 641111111000000000000000000000000000000000000000000000[...]33333333333333335557984444[...]7 + # min/max temperatures: -1,840,000,000, 370,010,000, column size: 3.925 MiB + 0 addr 86.182 TiB size 8.000 KiB access 0 % age 14.900 s + 1 addr 86.182 TiB size 8.000 KiB access 60 % age 0 ns + 2 addr 86.182 TiB size 3.422 MiB access 0 % age 4.100 s + 3 addr 86.182 TiB size 2.004 MiB access 95 % age 2.200 s + 4 addr 86.182 TiB size 29.688 MiB access 0 % age 14.100 s + 5 addr 86.182 TiB size 29.516 MiB access 0 % age 16.700 s + 6 addr 86.182 TiB size 29.633 MiB access 0 % age 17.900 s + 7 addr 86.182 TiB size 117.652 MiB access 0 % age 18.400 s + 8 addr 126.990 TiB size 62.332 MiB access 0 % age 9.500 s + 9 addr 126.990 TiB size 13.980 MiB access 0 % age 5.200 s + 10 addr 126.990 TiB size 9.539 MiB access 100 % age 3.700 s + 11 addr 126.990 TiB size 16.098 MiB access 0 % age 6.400 s + 12 addr 127.987 TiB size 132.000 KiB access 0 % age 2.900 s + total size: 314.008 MiB + $ sudo damo stop The first command of the above example downloads and builds an artificial memory access generator program called ``masim``. The second command asks DAMO -to execute the artificial generator process start via the given command and -make DAMON monitors the generator process. The third command retrieves the -current snapshot of the monitored access pattern of the process from DAMON and -shows the pattern in a human readable format. +to start the program via the given command and make DAMON monitors the newly +started process. The third command retrieves the current snapshot of the +monitored access pattern of the process from DAMON and shows the pattern in a +human readable format. -Each line of the output shows which virtual address range (``addr [XX, XX)``) -of the process is how frequently (``access XX %``) accessed for how long time -(``age XX``). For example, the fifth region of ~9 MiB size is being most -frequently accessed for last 300 milliseconds. Finally, the fourth command -stops DAMON. +The first line of the output shows the relative access temperature (hotness) of +the regions in a single row hetmap format. Each column on the heatmap +represents regions of same size on the monitored virtual address space. The +position of the colun on the row and the number on the column represents the +relative location and access temperature of the region. ``[...]`` means +unmapped huge regions on the virtual address spaces. The second line shows +additional information for better understanding the heatmap. + +Each line of the output from the third line shows which virtual address range +(``addr XX size XX``) of the process is how frequently (``access XX %``) +accessed for how long time (``age XX``). For example, the evelenth region of +~9.5 MiB size is being most frequently accessed for last 3.7 seconds. Finally, +the fourth command stops DAMON. Note that DAMON can monitor not only virtual address spaces but multiple types of address spaces including the physical address space. @@ -95,7 +108,7 @@ Visualizing Recorded Patterns You can visualize the pattern in a heatmap, showing which memory region (x-axis) got accessed when (y-axis) and how frequently (number).:: - $ sudo damo report heats --heatmap stdout + $ sudo damo report heatmap 22222222222222222222222222222222222222211111111111111111111111111111111111111100 44444444444444444444444444444444444444434444444444444444444444444444444444443200 44444444444444444444444444444444444444433444444444444444444444444444444444444200 @@ -160,6 +173,6 @@ Data Access Pattern Aware Memory Management Below command makes every memory region of size >=4K that has not accessed for >=60 seconds in your workload to be swapped out. :: - $ sudo damo schemes --damos_access_rate 0 0 --damos_sz_region 4K max \ - --damos_age 60s max --damos_action pageout \ - + $ sudo damo start --damos_access_rate 0 0 --damos_sz_region 4K max \ + --damos_age 60s max --damos_action pageout \ + diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index d9be9f7caa7d..47a44bd348ab 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -26,12 +26,6 @@ DAMON provides below interfaces for different users. writing kernel space DAMON application programs for you. You can even extend DAMON for various address spaces. For detail, please refer to the interface :doc:`document `. -- *debugfs interface. (DEPRECATED!)* - :ref:`This ` is almost identical to :ref:`sysfs interface - `. This is deprecated, so users should move to the - :ref:`sysfs interface `. If you depend on this and cannot - move, please report your usecase to damon@lists.linux.dev and - linux-mm@kvack.org. .. _sysfs_interface: @@ -89,10 +83,10 @@ comma (","). │ │ │ │ │ │ │ │ │ 0/target_metric,target_value,current_value │ │ │ │ │ │ │ :ref:`watermarks `/metric,interval_us,high,mid,low │ │ │ │ │ │ │ :ref:`filters `/nr_filters - │ │ │ │ │ │ │ │ 0/type,matching,memcg_id - │ │ │ │ │ │ │ :ref:`stats `/nr_tried,sz_tried,nr_applied,sz_applied,qt_exceeds + │ │ │ │ │ │ │ │ 0/type,matching,allow,memcg_path,addr_start,addr_end,target_idx + │ │ │ │ │ │ │ :ref:`stats `/nr_tried,sz_tried,nr_applied,sz_applied,sz_ops_filter_passed,qt_exceeds │ │ │ │ │ │ │ :ref:`tried_regions `/total_bytes - │ │ │ │ │ │ │ │ 0/start,end,nr_accesses,age + │ │ │ │ │ │ │ │ 0/start,end,nr_accesses,age,sz_filter_passed │ │ │ │ │ │ │ │ ... │ │ │ │ │ │ ... │ │ │ │ ... @@ -412,59 +406,62 @@ number (``N``) to the file creates the number of child directories named ``0`` to ``N-1``. Each directory represents each filter. The filters are evaluated in the numeric order. -Each filter directory contains six files, namely ``type``, ``matcing``, -``memcg_path``, ``addr_start``, ``addr_end``, and ``target_idx``. To ``type`` -file, you can write one of five special keywords: ``anon`` for anonymous pages, -``memcg`` for specific memory cgroup, ``young`` for young pages, ``addr`` for -specific address range (an open-ended interval), or ``target`` for specific -DAMON monitoring target filtering. In case of the memory cgroup filtering, you -can specify the memory cgroup of the interest by writing the path of the memory -cgroup from the cgroups mount point to ``memcg_path`` file. In case of the -address range filtering, you can specify the start and end address of the range -to ``addr_start`` and ``addr_end`` files, respectively. For the DAMON -monitoring target filtering, you can specify the index of the target between -the list of the DAMON context's monitoring targets list to ``target_idx`` file. -You can write ``Y`` or ``N`` to ``matching`` file to filter out pages that does -or does not match to the type, respectively. Then, the scheme's action will -not be applied to the pages that specified to be filtered out. +Each filter directory contains seven files, namely ``type``, ``matching``, +``allow``, ``memcg_path``, ``addr_start``, ``addr_end``, and ``target_idx``. +To ``type`` file, you can write one of five special keywords: ``anon`` for +anonymous pages, ``memcg`` for specific memory cgroup, ``young`` for young +pages, ``addr`` for specific address range (an open-ended interval), or +``target`` for specific DAMON monitoring target filtering. Meaning of the +types are same to the description on the :ref:`design doc +`. + +In case of the memory cgroup filtering, you can specify the memory cgroup of +the interest by writing the path of the memory cgroup from the cgroups mount +point to ``memcg_path`` file. In case of the address range filtering, you can +specify the start and end address of the range to ``addr_start`` and +``addr_end`` files, respectively. For the DAMON monitoring target filtering, +you can specify the index of the target between the list of the DAMON context's +monitoring targets list to ``target_idx`` file. + +You can write ``Y`` or ``N`` to ``matching`` file to specify whether the filter +is for memory that matches the ``type``. You can write ``Y`` or ``N`` to +``allow`` file to specify if applying the action to the memory that satisfies +the ``type`` and ``matching`` should be allowed or not. For example, below restricts a DAMOS action to be applied to only non-anonymous pages of all memory cgroups except ``/having_care_already``.:: # echo 2 > nr_filters - # # filter out anonymous pages + # # disallow anonymous pages echo anon > 0/type echo Y > 0/matching + echo N > 0/allow # # further filter out all cgroups except one at '/having_care_already' echo memcg > 1/type echo /having_care_already > 1/memcg_path echo Y > 1/matching + echo N > 1/allow -Note that ``anon`` and ``memcg`` filters are currently supported only when -``paddr`` :ref:`implementation ` is being used. - -Also, memory regions that are filtered out by ``addr`` or ``target`` filters -are not counted as the scheme has tried to those, while regions that filtered -out by other type filters are counted as the scheme has tried to. The -difference is applied to :ref:`stats ` and -:ref:`tried regions `. +Refer to the :ref:`DAMOS filters design documentation +` for more details including how multiple filters +of different ``allow`` works, when each of the filters are supported, and +differences on stats. .. _sysfs_schemes_stats: schemes//stats/ ------------------ -DAMON counts the total number and bytes of regions that each scheme is tried to -be applied, the two numbers for the regions that each scheme is successfully -applied, and the total number of the quota limit exceeds. This statistics can -be used for online analysis or tuning of the schemes. +DAMON counts statistics for each scheme. This statistics can be used for +online analysis or tuning of the schemes. Refer to :ref:`design doc +` for more details about the stats. The statistics can be retrieved by reading the files under ``stats`` directory -(``nr_tried``, ``sz_tried``, ``nr_applied``, ``sz_applied``, and -``qt_exceeds``), respectively. The files are not updated in real time, so you -should ask DAMON sysfs interface to update the content of the files for the -stats by writing a special keyword, ``update_schemes_stats`` to the relevant -``kdamonds//state`` file. +(``nr_tried``, ``sz_tried``, ``nr_applied``, ``sz_applied``, +``sz_ops_filter_passed``, and ``qt_exceeds``), respectively. The files are not +updated in real time, so you should ask DAMON sysfs interface to update the +content of the files for the stats by writing a special keyword, +``update_schemes_stats`` to the relevant ``kdamonds//state`` file. .. _sysfs_schemes_tried_regions: @@ -501,10 +498,10 @@ set the ``access pattern`` as their interested pattern that they want to query. tried_regions// ------------------ -In each region directory, you will find four files (``start``, ``end``, -``nr_accesses``, and ``age``). Reading the files will show the start and end -addresses, ``nr_accesses``, and ``age`` of the region that corresponding -DAMON-based operation scheme ``action`` has tried to be applied. +In each region directory, you will find five files (``start``, ``end``, +``nr_accesses``, ``age``, and ``sz_filter_passed``). Reading the files will +show the properties of the region that corresponding DAMON-based operation +scheme ``action`` has tried to be applied. Example ~~~~~~~ @@ -600,306 +597,3 @@ fields are as usual. It shows the index of the DAMON context (``ctx_idx=X``) of the scheme in the list of the contexts of the context's kdamond, the index of the scheme (``scheme_idx=X``) in the list of the schemes of the context, in addition to the output of ``damon_aggregated`` tracepoint. - - -.. _debugfs_interface: - -debugfs Interface (DEPRECATED!) -=============================== - -.. note:: - - THIS IS DEPRECATED! - - DAMON debugfs interface is deprecated, so users should move to the - :ref:`sysfs interface `. If you depend on this and cannot - move, please report your usecase to damon@lists.linux.dev and - linux-mm@kvack.org. - -DAMON exports nine files, ``DEPRECATED``, ``attrs``, ``target_ids``, -``init_regions``, ``schemes``, ``monitor_on_DEPRECATED``, ``kdamond_pid``, -``mk_contexts`` and ``rm_contexts`` under its debugfs directory, -``/damon/``. - - -``DEPRECATED`` is a read-only file for the DAMON debugfs interface deprecation -notice. Reading it returns the deprecation notice, as below:: - - # cat DEPRECATED - DAMON debugfs interface is deprecated, so users should move to DAMON_SYSFS. If you cannot, please report your usecase to damon@lists.linux.dev and linux-mm@kvack.org. - - -Attributes ----------- - -Users can get and set the ``sampling interval``, ``aggregation interval``, -``update interval``, and min/max number of monitoring target regions by -reading from and writing to the ``attrs`` file. To know about the monitoring -attributes in detail, please refer to the :doc:`/mm/damon/design`. For -example, below commands set those values to 5 ms, 100 ms, 1,000 ms, 10 and -1000, and then check it again:: - - # cd /damon - # echo 5000 100000 1000000 10 1000 > attrs - # cat attrs - 5000 100000 1000000 10 1000 - - -Target IDs ----------- - -Some types of address spaces supports multiple monitoring target. For example, -the virtual memory address spaces monitoring can have multiple processes as the -monitoring targets. Users can set the targets by writing relevant id values of -the targets to, and get the ids of the current targets by reading from the -``target_ids`` file. In case of the virtual address spaces monitoring, the -values should be pids of the monitoring target processes. For example, below -commands set processes having pids 42 and 4242 as the monitoring targets and -check it again:: - - # cd /damon - # echo 42 4242 > target_ids - # cat target_ids - 42 4242 - -Users can also monitor the physical memory address space of the system by -writing a special keyword, "``paddr\n``" to the file. Because physical address -space monitoring doesn't support multiple targets, reading the file will show a -fake value, ``42``, as below:: - - # cd /damon - # echo paddr > target_ids - # cat target_ids - 42 - -Note that setting the target ids doesn't start the monitoring. - - -Initial Monitoring Target Regions ---------------------------------- - -In case of the virtual address space monitoring, DAMON automatically sets and -updates the monitoring target regions so that entire memory mappings of target -processes can be covered. However, users can want to limit the monitoring -region to specific address ranges, such as the heap, the stack, or specific -file-mapped area. Or, some users can know the initial access pattern of their -workloads and therefore want to set optimal initial regions for the 'adaptive -regions adjustment'. - -In contrast, DAMON do not automatically sets and updates the monitoring target -regions in case of physical memory monitoring. Therefore, users should set the -monitoring target regions by themselves. - -In such cases, users can explicitly set the initial monitoring target regions -as they want, by writing proper values to the ``init_regions`` file. The input -should be a sequence of three integers separated by white spaces that represent -one region in below form.:: - - - -The ``target idx`` should be the index of the target in ``target_ids`` file, -starting from ``0``, and the regions should be passed in address order. For -example, below commands will set a couple of address ranges, ``1-100`` and -``100-200`` as the initial monitoring target region of pid 42, which is the -first one (index ``0``) in ``target_ids``, and another couple of address -ranges, ``20-40`` and ``50-100`` as that of pid 4242, which is the second one -(index ``1``) in ``target_ids``.:: - - # cd /damon - # cat target_ids - 42 4242 - # echo "0 1 100 \ - 0 100 200 \ - 1 20 40 \ - 1 50 100" > init_regions - -Note that this sets the initial monitoring target regions only. In case of -virtual memory monitoring, DAMON will automatically updates the boundary of the -regions after one ``update interval``. Therefore, users should set the -``update interval`` large enough in this case, if they don't want the -update. - - -Schemes -------- - -Users can get and set the DAMON-based operation :ref:`schemes -` by reading from and writing to ``schemes`` debugfs file. -Reading the file also shows the statistics of each scheme. To the file, each -of the schemes should be represented in each line in below form:: - - - -You can disable schemes by simply writing an empty string to the file. - -Target Access Pattern -~~~~~~~~~~~~~~~~~~~~~ - -The target access :ref:`pattern ` of the -scheme. The ```` is constructed with three ranges in -below form:: - - min-size max-size min-acc max-acc min-age max-age - -Specifically, bytes for the size of regions (``min-size`` and ``max-size``), -number of monitored accesses per aggregate interval for access frequency -(``min-acc`` and ``max-acc``), number of aggregate intervals for the age of -regions (``min-age`` and ``max-age``) are specified. Note that the ranges are -closed interval. - -Action -~~~~~~ - -The ```` is a predefined integer for memory management :ref:`actions -`. The mapping between the ```` values and -the memory management actions is as below. For the detailed meaning of the -action and DAMON operations set supporting each action, please refer to the -list on :ref:`design doc `. - - - 0: ``willneed`` - - 1: ``cold`` - - 2: ``pageout`` - - 3: ``hugepage`` - - 4: ``nohugepage`` - - 5: ``stat`` - -Quota -~~~~~ - -Users can set the :ref:`quotas ` of the given scheme -via the ```` in below form:: - - - -This makes DAMON to try to use only up to ```` milliseconds for applying -the action to memory regions of the ``target access pattern`` within the -```` milliseconds, and to apply the action to only up to -```` bytes of memory regions within the ````. Setting both -```` and ```` zero disables the quota limits. - -For the :ref:`prioritization `, users -can set the weights for the three properties in ```` in below -form:: - - - -Watermarks -~~~~~~~~~~ - -Users can specify :ref:`watermarks ` of the -given scheme via ```` in below form:: - - - -```` is a predefined integer for the metric to be checked. The -supported numbers and their meanings are as below. - - - 0: Ignore the watermarks - - 1: System's free memory rate (per thousand) - -The value of the metric is checked every ```` microseconds. - -If the value is higher than ```` or lower than ````, the -scheme is deactivated. If the value is lower than ````, the scheme -is activated. - -.. _damos_stats: - -Statistics -~~~~~~~~~~ - -It also counts the total number and bytes of regions that each scheme is tried -to be applied, the two numbers for the regions that each scheme is successfully -applied, and the total number of the quota limit exceeds. This statistics can -be used for online analysis or tuning of the schemes. - -The statistics can be shown by reading the ``schemes`` file. Reading the file -will show each scheme you entered in each line, and the five numbers for the -statistics will be added at the end of each line. - -Example -~~~~~~~ - -Below commands applies a scheme saying "If a memory region of size in [4KiB, -8KiB] is showing accesses per aggregate interval in [0, 5] for aggregate -interval in [10, 20], page out the region. For the paging out, use only up to -10ms per second, and also don't page out more than 1GiB per second. Under the -limitation, page out memory regions having longer age first. Also, check the -free memory rate of the system every 5 seconds, start the monitoring and paging -out when the free memory rate becomes lower than 50%, but stop it if the free -memory rate becomes larger than 60%, or lower than 30%".:: - - # cd /damon - # scheme="4096 8192 0 5 10 20 2" # target access pattern and action - # scheme+=" 10 $((1024*1024*1024)) 1000" # quotas - # scheme+=" 0 0 100" # prioritization weights - # scheme+=" 1 5000000 600 500 300" # watermarks - # echo "$scheme" > schemes - - -Turning On/Off --------------- - -Setting the files as described above doesn't incur effect unless you explicitly -start the monitoring. You can start, stop, and check the current status of the -monitoring by writing to and reading from the ``monitor_on_DEPRECATED`` file. -Writing ``on`` to the file starts the monitoring of the targets with the -attributes. Writing ``off`` to the file stops those. DAMON also stops if -every target process is terminated. Below example commands turn on, off, and -check the status of DAMON:: - - # cd /damon - # echo on > monitor_on_DEPRECATED - # echo off > monitor_on_DEPRECATED - # cat monitor_on_DEPRECATED - off - -Please note that you cannot write to the above-mentioned debugfs files while -the monitoring is turned on. If you write to the files while DAMON is running, -an error code such as ``-EBUSY`` will be returned. - - -Monitoring Thread PID ---------------------- - -DAMON does requested monitoring with a kernel thread called ``kdamond``. You -can get the pid of the thread by reading the ``kdamond_pid`` file. When the -monitoring is turned off, reading the file returns ``none``. :: - - # cd /damon - # cat monitor_on_DEPRECATED - off - # cat kdamond_pid - none - # echo on > monitor_on_DEPRECATED - # cat kdamond_pid - 18594 - - -Using Multiple Monitoring Threads ---------------------------------- - -One ``kdamond`` thread is created for each monitoring context. You can create -and remove monitoring contexts for multiple ``kdamond`` required use case using -the ``mk_contexts`` and ``rm_contexts`` files. - -Writing the name of the new context to the ``mk_contexts`` file creates a -directory of the name on the DAMON debugfs directory. The directory will have -DAMON debugfs files for the context. :: - - # cd /damon - # ls foo - # ls: cannot access 'foo': No such file or directory - # echo foo > mk_contexts - # ls foo - # attrs init_regions kdamond_pid schemes target_ids - -If the context is not needed anymore, you can remove it and the corresponding -directory by putting the name of the context to the ``rm_contexts`` file. :: - - # echo foo > rm_contexts - # ls foo - # ls: cannot access 'foo': No such file or directory - -Note that ``mk_contexts``, ``rm_contexts``, and ``monitor_on_DEPRECATED`` files -are in the root directory only. diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index cb2c080f400c..33c886f3d198 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -280,8 +280,8 @@ The following files are currently defined: blocks; configure auto-onlining. The default value depends on the - CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel configuration - option. + CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel configuration + options. See the ``state`` property of memory blocks for details. ``block_size_bytes`` read-only: the size in bytes of a memory block. diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 5034915f4e8e..dff8d5985f0f 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -332,6 +332,12 @@ allocation policy for the internal shmem mount by using the kernel parameter seven valid policies for shmem (``always``, ``within_size``, ``advise``, ``never``, ``deny``, and ``force``). +Similarly to ``transparent_hugepage_shmem``, you can control the default +hugepage allocation policy for the tmpfs mount by using the kernel parameter +``transparent_hugepage_tmpfs=``, where ```` is one of the +four valid policies for tmpfs (``always``, ``within_size``, ``advise``, +``never``). The tmpfs mount default policy is ``never``. + In the same manner as ``thp_anon`` controls each supported anonymous THP size, ``thp_shmem`` controls each supported shmem THP size. ``thp_shmem`` has the same format as ``thp_anon``, but also supports the policy @@ -352,8 +358,21 @@ default to ``never``. Hugepages in tmpfs/shmem ======================== -You can control hugepage allocation policy in tmpfs with mount option -``huge=``. It can have following values: +Traditionally, tmpfs only supported a single huge page size ("PMD"). Today, +it also supports smaller sizes just like anonymous memory, often referred +to as "multi-size THP" (mTHP). Huge pages of any size are commonly +represented in the kernel as "large folios". + +While there is fine control over the huge page sizes to use for the internal +shmem mount (see below), ordinary tmpfs mounts will make use of all available +huge page sizes without any control over the exact sizes, behaving more like +other file systems. + +tmpfs mounts +------------ + +The THP allocation policy for tmpfs mounts can be adjusted using the mount +option: ``huge=``. It can have following values: always Attempt to allocate huge pages every time we need a new page; @@ -363,24 +382,24 @@ never within_size Only allocate huge page if it will be fully within i_size. - Also respect fadvise()/madvise() hints; + Also respect madvise() hints; advise - Only allocate huge pages if requested with fadvise()/madvise(); + Only allocate huge pages if requested with madvise(); -The default policy is ``never``. +Remember, that the kernel may use huge pages of all available sizes, and +that no fine control as for the internal tmpfs mount is available. + +The default policy in the past was ``never``, but it can now be adjusted +using the kernel parameter ``transparent_hugepage_tmpfs=``. ``mount -o remount,huge= /mountpoint`` works fine after mount: remounting ``huge=never`` will not attempt to break up huge pages at all, just stop more from being allocated. -There's also sysfs knob to control hugepage allocation policy for internal -shmem mount: /sys/kernel/mm/transparent_hugepage/shmem_enabled. The mount -is used for SysV SHM, memfds, shared anonymous mmaps (of /dev/zero or -MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem. - -In addition to policies listed above, shmem_enabled allows two further -values: +In addition to policies listed above, the sysfs knob +/sys/kernel/mm/transparent_hugepage/shmem_enabled will affect the +allocation policy of tmpfs mounts, when set to the following values: deny For use in emergencies, to force the huge option off from @@ -388,13 +407,24 @@ deny force Force the huge option on for all - very useful for testing; -Shmem can also use "multi-size THP" (mTHP) by adding a new sysfs knob to -control mTHP allocation: -'/sys/kernel/mm/transparent_hugepage/hugepages-kB/shmem_enabled', -and its value for each mTHP is essentially consistent with the global -setting. An 'inherit' option is added to ensure compatibility with these -global settings. Conversely, the options 'force' and 'deny' are dropped, -which are rather testing artifacts from the old ages. +shmem / internal tmpfs +---------------------- +The mount internal tmpfs mount is used for SysV SHM, memfds, shared anonymous +mmaps (of /dev/zero or MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem. + +To control the THP allocation policy for this internal tmpfs mount, the +sysfs knob /sys/kernel/mm/transparent_hugepage/shmem_enabled and the knobs +per THP size in +'/sys/kernel/mm/transparent_hugepage/hugepages-kB/shmem_enabled' +can be used. + +The global knob has the same semantics as the ``huge=`` mount options +for tmpfs mounts, except that the different huge page sizes can be controlled +individually, and will only use the setting of the global knob when the +per-size knob is set to 'inherit'. + +The options 'force' and 'deny' are dropped for the individual sizes, which +are rather testing artifacts from the old ages. always Attempt to allocate huge pages every time we need a new page; @@ -408,10 +438,10 @@ never within_size Only allocate huge page if it will be fully within i_size. - Also respect fadvise()/madvise() hints; + Also respect madvise() hints; advise - Only allocate huge pages if requested with fadvise()/madvise(); + Only allocate huge pages if requested with madvise(); Need of application restart =========================== @@ -436,7 +466,7 @@ AnonHugePmdMapped). The number of file transparent huge pages mapped to userspace is available by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``. To identify what applications are mapping file transparent huge pages, it -is necessary to read ``/proc/PID/smaps`` and count the FileHugeMapped fields +is necessary to read ``/proc/PID/smaps`` and count the FilePmdMapped fields for each mapping. Note that reading the smaps file is expensive and reading it @@ -561,6 +591,16 @@ swpin is incremented every time a huge page is swapped in from a non-zswap swap device in one piece. +swpin_fallback + is incremented if swapin fails to allocate or charge a huge page + and instead falls back to using huge pages with lower orders or + small pages. + +swpin_fallback_charge + is incremented if swapin fails to charge a huge page and instead + falls back to using huge pages with lower orders or small pages + even though the allocation was successful. + swpout is incremented every time a huge page is swapped out to a non-zswap swap device in one piece without splitting. diff --git a/Documentation/admin-guide/nvme-multipath.rst b/Documentation/admin-guide/nvme-multipath.rst new file mode 100644 index 000000000000..97ca1ccef459 --- /dev/null +++ b/Documentation/admin-guide/nvme-multipath.rst @@ -0,0 +1,72 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +Linux NVMe multipath +==================== + +This document describes NVMe multipath and its path selection policies supported +by the Linux NVMe host driver. + + +Introduction +============ + +The NVMe multipath feature in Linux integrates namespaces with the same +identifier into a single block device. Using multipath enhances the reliability +and stability of I/O access while improving bandwidth performance. When a user +sends I/O to this merged block device, the multipath mechanism selects one of +the underlying block devices (paths) according to the configured policy. +Different policies result in different path selections. + + +Policies +======== + +All policies follow the ANA (Asymmetric Namespace Access) mechanism, meaning +that when an optimized path is available, it will be chosen over a non-optimized +one. Current the NVMe multipath policies include numa(default), round-robin and +queue-depth. + +To set the desired policy (e.g., round-robin), use one of the following methods: + 1. echo -n "round-robin" > /sys/module/nvme_core/parameters/iopolicy + 2. or add the "nvme_core.iopolicy=round-robin" to cmdline. + + +NUMA +---- + +The NUMA policy selects the path closest to the NUMA node of the current CPU for +I/O distribution. This policy maintains the nearest paths to each NUMA node +based on network interface connections. + +When to use the NUMA policy: + 1. Multi-core Systems: Optimizes memory access in multi-core and + multi-processor systems, especially under NUMA architecture. + 2. High Affinity Workloads: Binds I/O processing to the CPU to reduce + communication and data transfer delays across nodes. + + +Round-Robin +----------- + +The round-robin policy distributes I/O requests evenly across all paths to +enhance throughput and resource utilization. Each I/O operation is sent to the +next path in sequence. + +When to use the round-robin policy: + 1. Balanced Workloads: Effective for balanced and predictable workloads with + similar I/O size and type. + 2. Homogeneous Path Performance: Utilizes all paths efficiently when + performance characteristics (e.g., latency, bandwidth) are similar. + + +Queue-Depth +----------- + +The queue-depth policy manages I/O requests based on the current queue depth +of each path, selecting the path with the least number of in-flight I/Os. + +When to use the queue-depth policy: + 1. High load with small I/Os: Effectively balances load across paths when + the load is high, and I/O operations consist of small, relatively + fixed-sized requests. diff --git a/Documentation/admin-guide/perf/dwc_pcie_pmu.rst b/Documentation/admin-guide/perf/dwc_pcie_pmu.rst index 39b8e1fdd0cd..cb376f335f40 100644 --- a/Documentation/admin-guide/perf/dwc_pcie_pmu.rst +++ b/Documentation/admin-guide/perf/dwc_pcie_pmu.rst @@ -60,7 +60,7 @@ description of available events and configuration options in sysfs, see The "format" directory describes format of the config fields of the perf_event_attr structure. The "events" directory provides configuration templates for all documented events. For example, -"Rx_PCIe_TLP_Data_Payload" is an equivalent of "eventid=0x22,type=0x1". +"rx_pcie_tlp_data_payload" is an equivalent of "eventid=0x21,type=0x0". The "perf list" command shall list the available events from sysfs, e.g.:: @@ -79,8 +79,8 @@ Example usage of counting PCIe RX TLP data payload (Units of bytes):: The average RX/TX bandwidth can be calculated using the following formula: - PCIe RX Bandwidth = Rx_PCIe_TLP_Data_Payload / Measure_Time_Window - PCIe TX Bandwidth = Tx_PCIe_TLP_Data_Payload / Measure_Time_Window + PCIe RX Bandwidth = rx_pcie_tlp_data_payload / Measure_Time_Window + PCIe TX Bandwidth = tx_pcie_tlp_data_payload / Measure_Time_Window Lane Event Usage ------------------------------- diff --git a/Documentation/admin-guide/perf/hisi-pmu.rst b/Documentation/admin-guide/perf/hisi-pmu.rst index 5cc248d18c63..48992a0b8e94 100644 --- a/Documentation/admin-guide/perf/hisi-pmu.rst +++ b/Documentation/admin-guide/perf/hisi-pmu.rst @@ -35,7 +35,10 @@ e.g. hisi_sccl1_hha0/rx_operations is RX_OPERATIONS event of HHA index #0 in SCCL ID #1. The driver also provides a "cpumask" sysfs attribute, which shows the CPU core -ID used to count the uncore PMU event. +ID used to count the uncore PMU event. An "associated_cpus" sysfs attribute is +also provided to show the CPUs associated with this PMU. The "cpumask" indicates +the CPUs to open the events, usually as a hint for userspaces tools like perf. +It only contains one associated CPU from the "associated_cpus". Example usage of perf:: diff --git a/Documentation/admin-guide/perf/index.rst b/Documentation/admin-guide/perf/index.rst index a58bd3f7e190..072b510385c4 100644 --- a/Documentation/admin-guide/perf/index.rst +++ b/Documentation/admin-guide/perf/index.rst @@ -14,6 +14,8 @@ Performance monitor support qcom_l2_pmu qcom_l3_pmu starfive_starlink_pmu + mrvl-odyssey-ddr-pmu + mrvl-odyssey-tad-pmu arm-ccn arm-cmn arm-ni diff --git a/Documentation/admin-guide/perf/mrvl-odyssey-ddr-pmu.rst b/Documentation/admin-guide/perf/mrvl-odyssey-ddr-pmu.rst new file mode 100644 index 000000000000..2e817593a4d9 --- /dev/null +++ b/Documentation/admin-guide/perf/mrvl-odyssey-ddr-pmu.rst @@ -0,0 +1,80 @@ +=================================================================== +Marvell Odyssey DDR PMU Performance Monitoring Unit (PMU UNCORE) +=================================================================== + +Odyssey DRAM Subsystem supports eight counters for monitoring performance +and software can program those counters to monitor any of the defined +performance events. Supported performance events include those counted +at the interface between the DDR controller and the PHY, interface between +the DDR Controller and the CHI interconnect, or within the DDR Controller. + +Additionally DSS also supports two fixed performance event counters, one +for ddr reads and the other for ddr writes. + +The counter will be operating in either manual or auto mode. + +The PMU driver exposes the available events and format options under sysfs:: + + /sys/bus/event_source/devices/mrvl_ddr_pmu_<>/events/ + /sys/bus/event_source/devices/mrvl_ddr_pmu_<>/format/ + +Examples:: + + $ perf list | grep ddr + mrvl_ddr_pmu_<>/ddr_act_bypass_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_bsm_alloc/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_bsm_starvation/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_cam_active_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_cam_mwr/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_cam_rd_active_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_cam_rd_or_wr_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_cam_read/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_cam_wr_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_cam_write/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_capar_error/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_crit_ref/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_ddr_reads/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_ddr_writes/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_dfi_cmd_is_retry/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_dfi_cycles/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_dfi_parity_poison/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_dfi_rd_data_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_dfi_wr_data_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_dqsosc_mpc/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_dqsosc_mrr/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_enter_mpsm/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_enter_powerdown/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_enter_selfref/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_hif_pri_rdaccess/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_hif_rd_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_hif_rd_or_wr_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_hif_rmw_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_hif_wr_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_hpri_sched_rd_crit_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_load_mode/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_lpri_sched_rd_crit_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_precharge/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_precharge_for_other/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_precharge_for_rdwr/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_raw_hazard/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_rd_bypass_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_rd_crc_error/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_rd_uc_ecc_error/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_rdwr_transitions/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_refresh/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_retry_fifo_full/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_spec_ref/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_tcr_mrr/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_war_hazard/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_waw_hazard/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_win_limit_reached_rd/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_win_limit_reached_wr/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_wr_crc_error/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_wr_trxn_crit_access/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_write_combine/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_zqcl/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_zqlatch/ [Kernel PMU event] + mrvl_ddr_pmu_<>/ddr_zqstart/ [Kernel PMU event] + + $ perf stat -e ddr_cam_read,ddr_cam_write,ddr_cam_active_access,ddr_cam + rd_or_wr_access,ddr_cam_rd_active_access,ddr_cam_mwr diff --git a/Documentation/admin-guide/perf/mrvl-odyssey-tad-pmu.rst b/Documentation/admin-guide/perf/mrvl-odyssey-tad-pmu.rst new file mode 100644 index 000000000000..ad1975b14087 --- /dev/null +++ b/Documentation/admin-guide/perf/mrvl-odyssey-tad-pmu.rst @@ -0,0 +1,37 @@ +==================================================================== +Marvell Odyssey LLC-TAD Performance Monitoring Unit (PMU UNCORE) +==================================================================== + +Each TAD provides eight 64-bit counters for monitoring +cache behavior.The driver always configures the same counter for +all the TADs. The user would end up effectively reserving one of +eight counters in every TAD to look across all TADs. +The occurrences of events are aggregated and presented to the user +at the end of running the workload. The driver does not provide a +way for the user to partition TADs so that different TADs are used for +different applications. + +The performance events reflect various internal or interface activities. +By combining the values from multiple performance counters, cache +performance can be measured in terms such as: cache miss rate, cache +allocations, interface retry rate, internal resource occupancy, etc. + +The PMU driver exposes the available events and format options under sysfs:: + + /sys/bus/event_source/devices/tad/events/ + /sys/bus/event_source/devices/tad/format/ + +Examples:: + + $ perf list | grep tad + tad/tad_alloc_any/ [Kernel PMU event] + tad/tad_alloc_dtg/ [Kernel PMU event] + tad/tad_alloc_ltg/ [Kernel PMU event] + tad/tad_hit_any/ [Kernel PMU event] + tad/tad_hit_dtg/ [Kernel PMU event] + tad/tad_hit_ltg/ [Kernel PMU event] + tad/tad_req_msh_in_exlmn/ [Kernel PMU event] + tad/tad_tag_rd/ [Kernel PMU event] + tad/tad_tot_cycle/ [Kernel PMU event] + + $ perf stat -e tad_alloc_dtg,tad_alloc_ltg,tad_alloc_any,tad_hit_dtg,tad_hit_ltg,tad_hit_any,tad_tag_rd diff --git a/Documentation/admin-guide/perf/nvidia-pmu.rst b/Documentation/admin-guide/perf/nvidia-pmu.rst index 2e0d47cfe7ea..f538ef67e0e8 100644 --- a/Documentation/admin-guide/perf/nvidia-pmu.rst +++ b/Documentation/admin-guide/perf/nvidia-pmu.rst @@ -34,7 +34,7 @@ strongly-ordered (SO) PCIE write traffic to local/remote memory. Please see traffic coverage. The events and configuration options of this PMU device are described in sysfs, -see /sys/bus/event_sources/devices/nvidia_scf_pmu_. +see /sys/bus/event_source/devices/nvidia_scf_pmu_. Example usage: @@ -66,7 +66,7 @@ Please see :ref:`NVIDIA_Uncore_PMU_Traffic_Coverage_Section` for more info about the PMU traffic coverage. The events and configuration options of this PMU device are described in sysfs, -see /sys/bus/event_sources/devices/nvidia_nvlink_c2c0_pmu_. +see /sys/bus/event_source/devices/nvidia_nvlink_c2c0_pmu_. Example usage: @@ -86,6 +86,22 @@ Example usage: perf stat -a -e nvidia_nvlink_c2c0_pmu_3/event=0x0/ +The NVLink-C2C has two ports that can be connected to one GPU (occupying both +ports) or to two GPUs (one GPU per port). The user can use "port" bitmap +parameter to select the port(s) to monitor. Each bit represents the port number, +e.g. "port=0x1" corresponds to port 0 and "port=0x3" is for port 0 and 1. The +PMU will monitor both ports by default if not specified. + +Example for port filtering: + +* Count event id 0x0 from the GPU connected with socket 0 on port 0:: + + perf stat -a -e nvidia_nvlink_c2c0_pmu_0/event=0x0,port=0x1/ + +* Count event id 0x0 from the GPUs connected with socket 0 on port 0 and port 1:: + + perf stat -a -e nvidia_nvlink_c2c0_pmu_0/event=0x0,port=0x3/ + NVLink-C2C1 PMU ------------------- @@ -96,7 +112,7 @@ Please see :ref:`NVIDIA_Uncore_PMU_Traffic_Coverage_Section` for more info about the PMU traffic coverage. The events and configuration options of this PMU device are described in sysfs, -see /sys/bus/event_sources/devices/nvidia_nvlink_c2c1_pmu_. +see /sys/bus/event_source/devices/nvidia_nvlink_c2c1_pmu_. Example usage: @@ -116,6 +132,22 @@ Example usage: perf stat -a -e nvidia_nvlink_c2c1_pmu_3/event=0x0/ +The NVLink-C2C has two ports that can be connected to one GPU (occupying both +ports) or to two GPUs (one GPU per port). The user can use "port" bitmap +parameter to select the port(s) to monitor. Each bit represents the port number, +e.g. "port=0x1" corresponds to port 0 and "port=0x3" is for port 0 and 1. The +PMU will monitor both ports by default if not specified. + +Example for port filtering: + +* Count event id 0x0 from the GPU connected with socket 0 on port 0:: + + perf stat -a -e nvidia_nvlink_c2c1_pmu_0/event=0x0,port=0x1/ + +* Count event id 0x0 from the GPUs connected with socket 0 on port 0 and port 1:: + + perf stat -a -e nvidia_nvlink_c2c1_pmu_0/event=0x0,port=0x3/ + CNVLink PMU --------------- @@ -125,13 +157,14 @@ to local memory. For PCIE traffic, this PMU captures read and relaxed ordered for more info about the PMU traffic coverage. The events and configuration options of this PMU device are described in sysfs, -see /sys/bus/event_sources/devices/nvidia_cnvlink_pmu_. +see /sys/bus/event_source/devices/nvidia_cnvlink_pmu_. Each SoC socket can be connected to one or more sockets via CNVLink. The user can use "rem_socket" bitmap parameter to select the remote socket(s) to monitor. Each bit represents the socket number, e.g. "rem_socket=0xE" corresponds to -socket 1 to 3. -/sys/bus/event_sources/devices/nvidia_cnvlink_pmu_/format/rem_socket +socket 1 to 3. The PMU will monitor all remote sockets by default if not +specified. +/sys/bus/event_source/devices/nvidia_cnvlink_pmu_/format/rem_socket shows the valid bits that can be set in the "rem_socket" parameter. The PMU can not distinguish the remote traffic initiator, therefore it does not @@ -165,12 +198,13 @@ local/remote memory. Please see :ref:`NVIDIA_Uncore_PMU_Traffic_Coverage_Section for more info about the PMU traffic coverage. The events and configuration options of this PMU device are described in sysfs, -see /sys/bus/event_sources/devices/nvidia_pcie_pmu_. +see /sys/bus/event_source/devices/nvidia_pcie_pmu_. Each SoC socket can support multiple root ports. The user can use "root_port" bitmap parameter to select the port(s) to monitor, i.e. -"root_port=0xF" corresponds to root port 0 to 3. -/sys/bus/event_sources/devices/nvidia_pcie_pmu_/format/root_port +"root_port=0xF" corresponds to root port 0 to 3. The PMU will monitor all root +ports by default if not specified. +/sys/bus/event_source/devices/nvidia_pcie_pmu_/format/root_port shows the valid bits that can be set in the "root_port" parameter. Example usage: diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst index 210a808b74ec..412423c54f25 100644 --- a/Documentation/admin-guide/pm/amd-pstate.rst +++ b/Documentation/admin-guide/pm/amd-pstate.rst @@ -251,9 +251,7 @@ performance supported in `AMD CPPC Performance Capability `_). In some ASICs, the highest CPPC performance is not the one in the ``_CPC`` table, so we need to expose it to sysfs. If boost is not active, but still supported, this maximum frequency will be larger than the one in -``cpuinfo``. On systems that support preferred core, the driver will have -different values for some cores than others and this will reflect the values -advertised by the platform at bootup. +``cpuinfo``. This attribute is read-only. ``amd_pstate_lowest_nonlinear_freq`` diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst index 19754beb5a4e..eb58d7a5affd 100644 --- a/Documentation/admin-guide/pm/cpuidle.rst +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -269,27 +269,7 @@ Namely, when invoked to select an idle state for a CPU (i.e. an idle state that the CPU will ask the processor hardware to enter), it attempts to predict the idle duration and uses the predicted value for idle state selection. -It first obtains the time until the closest timer event with the assumption -that the scheduler tick will be stopped. That time, referred to as the *sleep -length* in what follows, is the upper bound on the time before the next CPU -wakeup. It is used to determine the sleep length range, which in turn is needed -to get the sleep length correction factor. - -The ``menu`` governor maintains two arrays of sleep length correction factors. -One of them is used when tasks previously running on the given CPU are waiting -for some I/O operations to complete and the other one is used when that is not -the case. Each array contains several correction factor values that correspond -to different sleep length ranges organized so that each range represented in the -array is approximately 10 times wider than the previous one. - -The correction factor for the given sleep length range (determined before -selecting the idle state for the CPU) is updated after the CPU has been woken -up and the closer the sleep length is to the observed idle duration, the closer -to 1 the correction factor becomes (it must fall between 0 and 1 inclusive). -The sleep length is multiplied by the correction factor for the range that it -falls into to obtain the first approximation of the predicted idle duration. - -Next, the governor uses a simple pattern recognition algorithm to refine its +It first uses a simple pattern recognition algorithm to obtain a preliminary idle duration prediction. Namely, it saves the last 8 observed idle duration values and, when predicting the idle duration next time, it computes the average and variance of them. If the variance is small (smaller than 400 square @@ -301,29 +281,39 @@ Again, if the variance of them is small (in the above sense), the average is taken as the "typical interval" value and so on, until either the "typical interval" is determined or too many data points are disregarded, in which case the "typical interval" is assumed to equal "infinity" (the maximum unsigned -integer value). The "typical interval" computed this way is compared with the -sleep length multiplied by the correction factor and the minimum of the two is -taken as the predicted idle duration. +integer value). -Then, the governor computes an extra latency limit to help "interactive" -workloads. It uses the observation that if the exit latency of the selected -idle state is comparable with the predicted idle duration, the total time spent -in that state probably will be very short and the amount of energy to save by -entering it will be relatively small, so likely it is better to avoid the -overhead related to entering that state and exiting it. Thus selecting a -shallower state is likely to be a better option then. The first approximation -of the extra latency limit is the predicted idle duration itself which -additionally is divided by a value depending on the number of tasks that -previously ran on the given CPU and now they are waiting for I/O operations to -complete. The result of that division is compared with the latency limit coming -from the power management quality of service, or `PM QoS `_, -framework and the minimum of the two is taken as the limit for the idle states' -exit latency. +If the "typical interval" computed this way is long enough, the governor obtains +the time until the closest timer event with the assumption that the scheduler +tick will be stopped. That time, referred to as the *sleep length* in what follows, +is the upper bound on the time before the next CPU wakeup. It is used to determine +the sleep length range, which in turn is needed to get the sleep length correction +factor. + +The ``menu`` governor maintains an array containing several correction factor +values that correspond to different sleep length ranges organized so that each +range represented in the array is approximately 10 times wider than the previous +one. + +The correction factor for the given sleep length range (determined before +selecting the idle state for the CPU) is updated after the CPU has been woken +up and the closer the sleep length is to the observed idle duration, the closer +to 1 the correction factor becomes (it must fall between 0 and 1 inclusive). +The sleep length is multiplied by the correction factor for the range that it +falls into to obtain an approximation of the predicted idle duration that is +compared to the "typical interval" determined previously and the minimum of +the two is taken as the idle duration prediction. + +If the "typical interval" value is small, which means that the CPU is likely +to be woken up soon enough, the sleep length computation is skipped as it may +be costly and the idle duration is simply predicted to equal the "typical +interval" value. Now, the governor is ready to walk the list of idle states and choose one of them. For this purpose, it compares the target residency of each state with -the predicted idle duration and the exit latency of it with the computed latency -limit. It selects the state with the target residency closest to the predicted +the predicted idle duration and the exit latency of it with the with the latency +limit coming from the power management quality of service, or `PM QoS `_, +framework. It selects the state with the target residency closest to the predicted idle duration, but still below it, and exit latency that does not exceed the limit. diff --git a/Documentation/admin-guide/quickly-build-trimmed-linux.rst b/Documentation/admin-guide/quickly-build-trimmed-linux.rst index f08149bc53f8..07cfd8863b46 100644 --- a/Documentation/admin-guide/quickly-build-trimmed-linux.rst +++ b/Documentation/admin-guide/quickly-build-trimmed-linux.rst @@ -733,7 +733,7 @@ can easily happen that your self-built kernel will lack modules for tasks you did not perform before utilizing this make target. That's because those tasks require kernel modules that are normally autoloaded when you perform that task for the first time; if you didn't perform that task at least once before using -localmodonfig, the latter will thus assume these modules are superfluous and +localmodconfig, the latter will thus assume these modules are superfluous and disable them. You can try to avoid this by performing typical tasks that often will autoload diff --git a/Documentation/admin-guide/sysctl/fs.rst b/Documentation/admin-guide/sysctl/fs.rst index f5ec6c9312e1..08e89e031714 100644 --- a/Documentation/admin-guide/sysctl/fs.rst +++ b/Documentation/admin-guide/sysctl/fs.rst @@ -41,7 +41,7 @@ pre-allocation or re-sizing of any kernel data structures. dentry-negative ---------------------------- -Policy for negative dentries. Set to 1 to to always delete the dentry when a +Policy for negative dentries. Set to 1 to always delete the dentry when a file is removed, and 0 to disable it. By default, this behavior is disabled. dentry-state diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index b2b36d0c3094..a43b78b4b646 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -1544,6 +1544,13 @@ constant ``FUTEX_TID_MASK`` (0x3fffffff). If a value outside of this range is written to ``threads-max`` an ``EINVAL`` error occurs. +timer_migration +=============== + +When set to a non-zero value, attempt to migrate timers away from idle cpus to +allow them to remain in low power states longer. + +Default is set (1). traceoff_on_warning =================== diff --git a/Documentation/admin-guide/sysrq.rst b/Documentation/admin-guide/sysrq.rst index a85b3384d1e7..9c7aa817adc7 100644 --- a/Documentation/admin-guide/sysrq.rst +++ b/Documentation/admin-guide/sysrq.rst @@ -49,26 +49,26 @@ How do I use the magic SysRq key? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ On x86 - You press the key combo :kbd:`ALT-SysRq-`. + You press the key combo `ALT-SysRq-`. .. note:: Some keyboards may not have a key labeled 'SysRq'. The 'SysRq' key is also known as the 'Print Screen' key. Also some keyboards cannot handle so many keys being pressed at the same time, so you might - have better luck with press :kbd:`Alt`, press :kbd:`SysRq`, - release :kbd:`SysRq`, press :kbd:``, release everything. + have better luck with press `Alt`, press `SysRq`, + release `SysRq`, press ``, release everything. On SPARC - You press :kbd:`ALT-STOP-`, I believe. + You press `ALT-STOP-`, I believe. On the serial console (PC style standard serial ports only) You send a ``BREAK``, then within 5 seconds a command key. Sending ``BREAK`` twice is interpreted as a normal BREAK. On PowerPC - Press :kbd:`ALT - Print Screen` (or :kbd:`F13`) - :kbd:``. - :kbd:`Print Screen` (or :kbd:`F13`) - :kbd:`` may suffice. + Press `ALT - Print Screen` (or `F13`) - ``. + `Print Screen` (or `F13`) - `` may suffice. On other If you know of the key combos for other architectures, please @@ -88,7 +88,7 @@ On all echo _reisub > /proc/sysrq-trigger -The :kbd:`` is case sensitive. +The `` is case sensitive. What are the 'command' keys? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -225,9 +225,9 @@ Sometimes SysRq seems to get 'stuck' after using it, what can I do? When this happens, try tapping shift, alt and control on both sides of the keyboard, and hitting an invalid sysrq sequence again. (i.e., something like -:kbd:`alt-sysrq-z`). +`alt-sysrq-z`). -Switching to another virtual console (:kbd:`ALT+Fn`) and then back again +Switching to another virtual console (`ALT+Fn`) and then back again should also help. I hit SysRq, but nothing seems to happen, what's wrong? @@ -290,7 +290,7 @@ exception the header line from the sysrq command is passed to all console consumers as if the current loglevel was maximum. If only the header is emitted it is almost certain that the kernel loglevel is too low. Should you require the output on the console channel then you will need -to temporarily up the console loglevel using :kbd:`alt-sysrq-8` or:: +to temporarily up the console loglevel using `alt-sysrq-8` or:: echo 8 > /proc/sysrq-trigger diff --git a/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst b/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst index 6281eae9e6bc..03c55151346c 100644 --- a/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst +++ b/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst @@ -1431,7 +1431,7 @@ can easily happen that your self-built kernels will lack modules for tasks you did not perform at least once before utilizing this make target. That happens when a task requires kernel modules which are only autoloaded when you execute it for the first time. So when you never performed that task since starting your -kernel the modules will not have been loaded -- and from localmodonfig's point +kernel the modules will not have been loaded -- and from localmodconfig's point of view look superfluous, which thus disables them to reduce the amount of code to be compiled. diff --git a/Documentation/admin-guide/workload-tracing.rst b/Documentation/admin-guide/workload-tracing.rst index b2e254ec8ee8..6be38c1b9c5b 100644 --- a/Documentation/admin-guide/workload-tracing.rst +++ b/Documentation/admin-guide/workload-tracing.rst @@ -83,7 +83,7 @@ scripts/ver_linux is a good way to check if your system already has the necessary tools:: sudo apt-get build-essentials flex bison yacc - sudo apt install libelf-dev systemtap-sdt-dev libaudit-dev libslang2-dev libperl-dev libdw-dev + sudo apt install libelf-dev systemtap-sdt-dev libslang2-dev libperl-dev libdw-dev cscope is a good tool to browse kernel sources. Let's install it now:: diff --git a/Documentation/arch/arm64/asymmetric-32bit.rst b/Documentation/arch/arm64/asymmetric-32bit.rst index 64a0b505da7d..1ca2b359a907 100644 --- a/Documentation/arch/arm64/asymmetric-32bit.rst +++ b/Documentation/arch/arm64/asymmetric-32bit.rst @@ -153,3 +153,11 @@ asymmetric system, a broken guest at EL1 could still attempt to execute mode will return to host userspace with an ``exit_reason`` of ``KVM_EXIT_FAIL_ENTRY`` and will remain non-runnable until successfully re-initialised by a subsequent ``KVM_ARM_VCPU_INIT`` operation. + +NOHZ FULL +--------- + +To avoid perturbing an adaptive-ticks CPU (specified using +``nohz_full=``) when a 32-bit task is forcefully migrated, these CPUs +are treated as 64-bit-only when support for asymmetric 32-bit systems +is enabled. diff --git a/Documentation/arch/arm64/booting.rst b/Documentation/arch/arm64/booting.rst index 3278fb4bf219..cad6fdc96b98 100644 --- a/Documentation/arch/arm64/booting.rst +++ b/Documentation/arch/arm64/booting.rst @@ -449,6 +449,18 @@ Before jumping into the kernel, the following conditions must be met: - HFGWTR_EL2.nGCS_EL0 (bit 52) must be initialised to 0b1. + - For CPUs with debug architecture i.e FEAT_Debugv8pN (all versions): + + - If EL3 is present: + + - MDCR_EL3.TDA (bit 9) must be initialized to 0b0 + + - For CPUs with FEAT_PMUv3: + + - If EL3 is present: + + - MDCR_EL3.TPM (bit 6) must be initialized to 0b0 + The requirements described above for CPU mode, caches, MMUs, architected timers, coherency and system registers apply to all CPUs. All CPUs must enter the kernel in the same exception level. Where the values documented diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index 2ff922a406ad..69d7afe56853 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -174,26 +174,82 @@ HWCAP_GCS Functionality implied by ID_AA64PFR1_EL1.GCS == 0b1, as described by Documentation/arch/arm64/gcs.rst. +HWCAP_CMPBR + Functionality implied by ID_AA64ISAR2_EL1.CSSC == 0b0010. + +HWCAP_FPRCVT + Functionality implied by ID_AA64ISAR3_EL1.FPRCVT == 0b0001. + +HWCAP_F8MM8 + Functionality implied by ID_AA64FPFR0_EL1.F8MM8 == 0b0001. + +HWCAP_F8MM4 + Functionality implied by ID_AA64FPFR0_EL1.F8MM4 == 0b0001. + +HWCAP_SVE_F16MM + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.F16MM == 0b0001. + +HWCAP_SVE_ELTPERM + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.ELTPERM == 0b0001. + +HWCAP_SVE_AES2 + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.AES == 0b0011. + +HWCAP_SVE_BFSCALE + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.B16B16 == 0b0010. + +HWCAP_SVE2P2 + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SVEver == 0b0011. + +HWCAP_SME2P2 + Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0011. + +HWCAP_SME_SBITPERM + Functionality implied by ID_AA64SMFR0_EL1.SBitPerm == 0b1. + +HWCAP_SME_AES + Functionality implied by ID_AA64SMFR0_EL1.AES == 0b1. + +HWCAP_SME_SFEXPA + Functionality implied by ID_AA64SMFR0_EL1.SFEXPA == 0b1. + +HWCAP_SME_STMOP + Functionality implied by ID_AA64SMFR0_EL1.STMOP == 0b1. + +HWCAP_SME_SMOP4 + Functionality implied by ID_AA64SMFR0_EL1.SMOP4 == 0b1. + HWCAP2_DCPODP Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010. HWCAP2_SVE2 - Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SVEver == 0b0001. HWCAP2_SVEAES - Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.AES == 0b0001. HWCAP2_SVEPMULL - Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.AES == 0b0010. HWCAP2_SVEBITPERM - Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.BitPerm == 0b0001. HWCAP2_SVESHA3 - Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SHA3 == 0b0001. HWCAP2_SVESM4 - Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SM4 == 0b0001. HWCAP2_FLAGM2 Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0010. @@ -202,16 +258,20 @@ HWCAP2_FRINT Functionality implied by ID_AA64ISAR1_EL1.FRINTTS == 0b0001. HWCAP2_SVEI8MM - Functionality implied by ID_AA64ZFR0_EL1.I8MM == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.I8MM == 0b0001. HWCAP2_SVEF32MM - Functionality implied by ID_AA64ZFR0_EL1.F32MM == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.F32MM == 0b0001. HWCAP2_SVEF64MM - Functionality implied by ID_AA64ZFR0_EL1.F64MM == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.F64MM == 0b0001. HWCAP2_SVEBF16 - Functionality implied by ID_AA64ZFR0_EL1.BF16 == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.BF16 == 0b0001. HWCAP2_I8MM Functionality implied by ID_AA64ISAR1_EL1.I8MM == 0b0001. @@ -277,7 +337,8 @@ HWCAP2_EBF16 Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0010. HWCAP2_SVE_EBF16 - Functionality implied by ID_AA64ZFR0_EL1.BF16 == 0b0010. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.BF16 == 0b0010. HWCAP2_CSSC Functionality implied by ID_AA64ISAR2_EL1.CSSC == 0b0001. @@ -286,7 +347,8 @@ HWCAP2_RPRFM Functionality implied by ID_AA64ISAR2_EL1.RPRFM == 0b0001. HWCAP2_SVE2P1 - Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0010. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SVEver == 0b0010. HWCAP2_SME2 Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0001. @@ -313,7 +375,8 @@ HWCAP2_HBC Functionality implied by ID_AA64ISAR2_EL1.BC == 0b0001. HWCAP2_SVE_B16B16 - Functionality implied by ID_AA64ZFR0_EL1.B16B16 == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.B16B16 == 0b0001. HWCAP2_LRCPC3 Functionality implied by ID_AA64ISAR1_EL1.LRCPC == 0b0011. diff --git a/Documentation/arch/arm64/memory.rst b/Documentation/arch/arm64/memory.rst index 8a658984b8bb..678fbb418c3a 100644 --- a/Documentation/arch/arm64/memory.rst +++ b/Documentation/arch/arm64/memory.rst @@ -23,71 +23,6 @@ swapper_pg_dir contains only kernel (global) mappings while the user pgd contains only user (non-global) mappings. The swapper_pg_dir address is written to TTBR1 and never written to TTBR0. - -AArch64 Linux memory layout with 4KB pages + 4 levels (48-bit):: - - Start End Size Use - ----------------------------------------------------------------------- - 0000000000000000 0000ffffffffffff 256TB user - ffff000000000000 ffff7fffffffffff 128TB kernel logical memory map - [ffff600000000000 ffff7fffffffffff] 32TB [kasan shadow region] - ffff800000000000 ffff80007fffffff 2GB modules - ffff800080000000 fffffbffefffffff 124TB vmalloc - fffffbfff0000000 fffffbfffdffffff 224MB fixed mappings (top down) - fffffbfffe000000 fffffbfffe7fffff 8MB [guard region] - fffffbfffe800000 fffffbffff7fffff 16MB PCI I/O space - fffffbffff800000 fffffbffffffffff 8MB [guard region] - fffffc0000000000 fffffdffffffffff 2TB vmemmap - fffffe0000000000 ffffffffffffffff 2TB [guard region] - - -AArch64 Linux memory layout with 64KB pages + 3 levels (52-bit with HW support):: - - Start End Size Use - ----------------------------------------------------------------------- - 0000000000000000 000fffffffffffff 4PB user - fff0000000000000 ffff7fffffffffff ~4PB kernel logical memory map - [fffd800000000000 ffff7fffffffffff] 512TB [kasan shadow region] - ffff800000000000 ffff80007fffffff 2GB modules - ffff800080000000 fffffbffefffffff 124TB vmalloc - fffffbfff0000000 fffffbfffdffffff 224MB fixed mappings (top down) - fffffbfffe000000 fffffbfffe7fffff 8MB [guard region] - fffffbfffe800000 fffffbffff7fffff 16MB PCI I/O space - fffffbffff800000 fffffbffffffffff 8MB [guard region] - fffffc0000000000 ffffffdfffffffff ~4TB vmemmap - ffffffe000000000 ffffffffffffffff 128GB [guard region] - - -Translation table lookup with 4KB pages:: - - +--------+--------+--------+--------+--------+--------+--------+--------+ - |63 56|55 48|47 40|39 32|31 24|23 16|15 8|7 0| - +--------+--------+--------+--------+--------+--------+--------+--------+ - | | | | | | - | | | | | v - | | | | | [11:0] in-page offset - | | | | +-> [20:12] L3 index - | | | +-----------> [29:21] L2 index - | | +---------------------> [38:30] L1 index - | +-------------------------------> [47:39] L0 index - +----------------------------------------> [55] TTBR0/1 - - -Translation table lookup with 64KB pages:: - - +--------+--------+--------+--------+--------+--------+--------+--------+ - |63 56|55 48|47 40|39 32|31 24|23 16|15 8|7 0| - +--------+--------+--------+--------+--------+--------+--------+--------+ - | | | | | - | | | | v - | | | | [15:0] in-page offset - | | | +----------> [28:16] L3 index - | | +--------------------------> [41:29] L2 index - | +-------------------------------> [47:42] L1 index (48-bit) - | [51:42] L1 index (52-bit) - +----------------------------------------> [55] TTBR0/1 - - When using KVM without the Virtualization Host Extensions, the hypervisor maps kernel pages in EL2 at a fixed (and potentially random) offset from the linear mapping. See the kern_hyp_va macro and diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index b42fea07c5ce..f074f6219f5c 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -198,7 +198,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ -| ARM | MMU-500 | #841119,826419 | N/A | +| ARM | MMU-500 | #841119,826419 | ARM_SMMU_MMU_500_CPRE_ERRATA| +| | | #562869,1047329 | | +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-600 | #1076982,1209401| N/A | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst index 955fbcd19ce9..f273ea15a8e8 100644 --- a/Documentation/arch/riscv/hwprobe.rst +++ b/Documentation/arch/riscv/hwprobe.rst @@ -293,3 +293,13 @@ The following keys are defined: * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED`: Misaligned vector accesses are not supported at all and will generate a misaligned address fault. + +* :c:macro:`RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0`: A bitmask containing the + thead vendor extensions that are compatible with the + :c:macro:`RISCV_HWPROBE_BASE_BEHAVIOR_IMA`: base system behavior. + + * T-HEAD + + * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR`: The xtheadvector vendor + extension is supported in the T-Head ISA extensions spec starting from + commit a18c801634 ("Add T-Head VECTOR vendor extension. "). diff --git a/Documentation/arch/x86/amd-memory-encryption.rst b/Documentation/arch/x86/amd-memory-encryption.rst index 6df3264f23b9..bd840df708ea 100644 --- a/Documentation/arch/x86/amd-memory-encryption.rst +++ b/Documentation/arch/x86/amd-memory-encryption.rst @@ -130,8 +130,126 @@ SNP feature support. More details in AMD64 APM[1] Vol 2: 15.34.10 SEV_STATUS MSR +Reverse Map Table (RMP) +======================= + +The RMP is a structure in system memory that is used to ensure a one-to-one +mapping between system physical addresses and guest physical addresses. Each +page of memory that is potentially assignable to guests has one entry within +the RMP. + +The RMP table can be either contiguous in memory or a collection of segments +in memory. + +Contiguous RMP +-------------- + +Support for this form of the RMP is present when support for SEV-SNP is +present, which can be determined using the CPUID instruction:: + + 0x8000001f[eax]: + Bit[4] indicates support for SEV-SNP + +The location of the RMP is identified to the hardware through two MSRs:: + + 0xc0010132 (RMP_BASE): + System physical address of the first byte of the RMP + + 0xc0010133 (RMP_END): + System physical address of the last byte of the RMP + +Hardware requires that RMP_BASE and (RPM_END + 1) be 8KB aligned, but SEV +firmware increases the alignment requirement to require a 1MB alignment. + +The RMP consists of a 16KB region used for processor bookkeeping followed +by the RMP entries, which are 16 bytes in size. The size of the RMP +determines the range of physical memory that the hypervisor can assign to +SEV-SNP guests. The RMP covers the system physical address from:: + + 0 to ((RMP_END + 1 - RMP_BASE - 16KB) / 16B) x 4KB. + +The current Linux support relies on BIOS to allocate/reserve the memory for +the RMP and to set RMP_BASE and RMP_END appropriately. Linux uses the MSR +values to locate the RMP and determine the size of the RMP. The RMP must +cover all of system memory in order for Linux to enable SEV-SNP. + +Segmented RMP +------------- + +Segmented RMP support is a new way of representing the layout of an RMP. +Initial RMP support required the RMP table to be contiguous in memory. +RMP accesses from a NUMA node on which the RMP doesn't reside +can take longer than accesses from a NUMA node on which the RMP resides. +Segmented RMP support allows the RMP entries to be located on the same +node as the memory the RMP is covering, potentially reducing latency +associated with accessing an RMP entry associated with the memory. Each +RMP segment covers a specific range of system physical addresses. + +Support for this form of the RMP can be determined using the CPUID +instruction:: + + 0x8000001f[eax]: + Bit[23] indicates support for segmented RMP + +If supported, segmented RMP attributes can be found using the CPUID +instruction:: + + 0x80000025[eax]: + Bits[5:0] minimum supported RMP segment size + Bits[11:6] maximum supported RMP segment size + + 0x80000025[ebx]: + Bits[9:0] number of cacheable RMP segment definitions + Bit[10] indicates if the number of cacheable RMP segments + is a hard limit + +To enable a segmented RMP, a new MSR is available:: + + 0xc0010136 (RMP_CFG): + Bit[0] indicates if segmented RMP is enabled + Bits[13:8] contains the size of memory covered by an RMP + segment (expressed as a power of 2) + +The RMP segment size defined in the RMP_CFG MSR applies to all segments +of the RMP. Therefore each RMP segment covers a specific range of system +physical addresses. For example, if the RMP_CFG MSR value is 0x2401, then +the RMP segment coverage value is 0x24 => 36, meaning the size of memory +covered by an RMP segment is 64GB (1 << 36). So the first RMP segment +covers physical addresses from 0 to 0xF_FFFF_FFFF, the second RMP segment +covers physical addresses from 0x10_0000_0000 to 0x1F_FFFF_FFFF, etc. + +When a segmented RMP is enabled, RMP_BASE points to the RMP bookkeeping +area as it does today (16K in size). However, instead of RMP entries +beginning immediately after the bookkeeping area, there is a 4K RMP +segment table (RST). Each entry in the RST is 8-bytes in size and represents +an RMP segment:: + + Bits[19:0] mapped size (in GB) + The mapped size can be less than the defined segment size. + A value of zero, indicates that no RMP exists for the range + of system physical addresses associated with this segment. + Bits[51:20] segment physical address + This address is left shift 20-bits (or just masked when + read) to form the physical address of the segment (1MB + alignment). + +The RST can hold 512 segment entries but can be limited in size to the number +of cacheable RMP segments (CPUID 0x80000025_EBX[9:0]) if the number of cacheable +RMP segments is a hard limit (CPUID 0x80000025_EBX[10]). + +The current Linux support relies on BIOS to allocate/reserve the memory for +the segmented RMP (the bookkeeping area, RST, and all segments), build the RST +and to set RMP_BASE, RMP_END, and RMP_CFG appropriately. Linux uses the MSR +values to locate the RMP and determine the size and location of the RMP +segments. The RMP must cover all of system memory in order for Linux to enable +SEV-SNP. + +More details in the AMD64 APM Vol 2, section "15.36.3 Reverse Map Table", +docID: 24593. + Secure VM Service Module (SVSM) =============================== + SNP provides a feature called Virtual Machine Privilege Levels (VMPL) which defines four privilege levels at which guest software can run. The most privileged level is 0 and numerically higher numbers have lesser privileges. diff --git a/Documentation/arch/x86/boot.rst b/Documentation/arch/x86/boot.rst index ad2d8ddad27f..76f53d3450e7 100644 --- a/Documentation/arch/x86/boot.rst +++ b/Documentation/arch/x86/boot.rst @@ -77,7 +77,7 @@ Protocol 2.14 BURNT BY INCORRECT COMMIT Protocol 2.15 (Kernel 5.5) Added the kernel_info and kernel_info.setup_type_max. ============= ============================================================ - .. note:: +.. note:: The protocol version number should be changed only if the setup header is changed. There is no need to update the version number if boot_params or kernel_info are changed. Additionally, it is recommended to use @@ -95,27 +95,27 @@ Memory Layout The traditional memory map for the kernel loader, used for Image or zImage kernels, typically looks like:: - | | - 0A0000 +------------------------+ - | Reserved for BIOS | Do not use. Reserved for BIOS EBDA. - 09A000 +------------------------+ - | Command line | - | Stack/heap | For use by the kernel real-mode code. - 098000 +------------------------+ - | Kernel setup | The kernel real-mode code. - 090200 +------------------------+ - | Kernel boot sector | The kernel legacy boot sector. - 090000 +------------------------+ - | Protected-mode kernel | The bulk of the kernel image. - 010000 +------------------------+ - | Boot loader | <- Boot sector entry point 0000:7C00 - 001000 +------------------------+ - | Reserved for MBR/BIOS | - 000800 +------------------------+ - | Typically used by MBR | - 000600 +------------------------+ - | BIOS use only | - 000000 +------------------------+ + | | + 0A0000 +------------------------+ + | Reserved for BIOS | Do not use. Reserved for BIOS EBDA. + 09A000 +------------------------+ + | Command line | + | Stack/heap | For use by the kernel real-mode code. + 098000 +------------------------+ + | Kernel setup | The kernel real-mode code. + 090200 +------------------------+ + | Kernel boot sector | The kernel legacy boot sector. + 090000 +------------------------+ + | Protected-mode kernel | The bulk of the kernel image. + 010000 +------------------------+ + | Boot loader | <- Boot sector entry point 0000:7C00 + 001000 +------------------------+ + | Reserved for MBR/BIOS | + 000800 +------------------------+ + | Typically used by MBR | + 000600 +------------------------+ + | BIOS use only | + 000000 +------------------------+ When using bzImage, the protected-mode kernel was relocated to 0x100000 ("high memory"), and the kernel real-mode block (boot sector, @@ -142,28 +142,28 @@ above the 0x9A000 point; too many BIOSes will break above that point. For a modern bzImage kernel with boot protocol version >= 2.02, a memory layout like the following is suggested:: - ~ ~ - | Protected-mode kernel | - 100000 +------------------------+ - | I/O memory hole | - 0A0000 +------------------------+ - | Reserved for BIOS | Leave as much as possible unused - ~ ~ - | Command line | (Can also be below the X+10000 mark) - X+10000 +------------------------+ - | Stack/heap | For use by the kernel real-mode code. - X+08000 +------------------------+ - | Kernel setup | The kernel real-mode code. - | Kernel boot sector | The kernel legacy boot sector. - X +------------------------+ - | Boot loader | <- Boot sector entry point 0000:7C00 - 001000 +------------------------+ - | Reserved for MBR/BIOS | - 000800 +------------------------+ - | Typically used by MBR | - 000600 +------------------------+ - | BIOS use only | - 000000 +------------------------+ + ~ ~ + | Protected-mode kernel | + 100000 +------------------------+ + | I/O memory hole | + 0A0000 +------------------------+ + | Reserved for BIOS | Leave as much as possible unused + ~ ~ + | Command line | (Can also be below the X+10000 mark) + X+10000 +------------------------+ + | Stack/heap | For use by the kernel real-mode code. + X+08000 +------------------------+ + | Kernel setup | The kernel real-mode code. + | Kernel boot sector | The kernel legacy boot sector. + X +------------------------+ + | Boot loader | <- Boot sector entry point 0000:7C00 + 001000 +------------------------+ + | Reserved for MBR/BIOS | + 000800 +------------------------+ + | Typically used by MBR | + 000600 +------------------------+ + | BIOS use only | + 000000 +------------------------+ ... where the address X is as low as the design of the boot loader permits. @@ -229,22 +229,22 @@ Offset/Size Proto Name Meaning =========== ======== ===================== ============================================ .. note:: - (1) For backwards compatibility, if the setup_sects field contains 0, the - real value is 4. + (1) For backwards compatibility, if the setup_sects field contains 0, + the real value is 4. - (2) For boot protocol prior to 2.04, the upper two bytes of the syssize - field are unusable, which means the size of a bzImage kernel - cannot be determined. + (2) For boot protocol prior to 2.04, the upper two bytes of the syssize + field are unusable, which means the size of a bzImage kernel + cannot be determined. - (3) Ignored, but safe to set, for boot protocols 2.02-2.09. + (3) Ignored, but safe to set, for boot protocols 2.02-2.09. If the "HdrS" (0x53726448) magic number is not found at offset 0x202, the boot protocol version is "old". Loading an old kernel, the following parameters should be assumed:: - Image type = zImage - initrd not supported - Real-mode kernel must be located at 0x90000. + Image type = zImage + initrd not supported + Real-mode kernel must be located at 0x90000. Otherwise, the "version" field contains the protocol version, e.g. protocol version 2.01 will contain 0x0201 in this field. When @@ -265,7 +265,7 @@ All general purpose boot loaders should write the fields marked nonstandard address should fill in the fields marked (reloc); other boot loaders can ignore those fields. -The byte order of all fields is littleendian (this is x86, after all.) +The byte order of all fields is little endian (this is x86, after all.) ============ =========== Field name: setup_sects @@ -365,7 +365,7 @@ Offset/size: 0x206/2 Protocol: 2.00+ ============ ======= - Contains the boot protocol version, in (major << 8)+minor format, + Contains the boot protocol version, in (major << 8) + minor format, e.g. 0x0204 for version 2.04, and 0x0a11 for a hypothetical version 10.17. @@ -397,17 +397,17 @@ Protocol: 2.00+ If set to a nonzero value, contains a pointer to a NUL-terminated human-readable kernel version number string, less 0x200. This can be used to display the kernel version to the user. This value - should be less than (0x200*setup_sects). + should be less than (0x200 * setup_sects). For example, if this value is set to 0x1c00, the kernel version number string can be found at offset 0x1e00 in the kernel file. This is a valid value if and only if the "setup_sects" field contains the value 15 or higher, as:: - 0x1c00 < 15*0x200 (= 0x1e00) but - 0x1c00 >= 14*0x200 (= 0x1c00) + 0x1c00 < 15 * 0x200 (= 0x1e00) but + 0x1c00 >= 14 * 0x200 (= 0x1c00) - 0x1c00 >> 9 = 14, So the minimum value for setup_secs is 15. + 0x1c00 >> 9 = 14, So the minimum value for setup_secs is 15. ============ ================== Field name: type_of_loader @@ -427,9 +427,9 @@ Protocol: 2.00+ For example, for T = 0x15, V = 0x234, write:: - type_of_loader <- 0xE4 - ext_loader_type <- 0x05 - ext_loader_ver <- 0x23 + type_of_loader <- 0xE4 + ext_loader_type <- 0x05 + ext_loader_ver <- 0x23 Assigned boot loader ids (hexadecimal): @@ -686,7 +686,7 @@ Protocol: 2.10+ If a boot loader makes use of this field, it should update the kernel_alignment field with the alignment unit desired; typically:: - kernel_alignment = 1 << min_alignment + kernel_alignment = 1 << min_alignment; There may be a considerable performance cost with an excessively misaligned kernel. Therefore, a loader should typically try each @@ -754,7 +754,7 @@ Protocol: 2.07+ 0x00000000 The default x86/PC environment 0x00000001 lguest 0x00000002 Xen - 0x00000003 Moorestown MID + 0x00000003 Intel MID (Moorestown, CloverTrail, Merrifield, Moorefield) 0x00000004 CE4100 TV Platform ========== ============================== @@ -808,13 +808,13 @@ Protocol: 2.09+ parameters passing mechanism. The definition of struct setup_data is as follow:: - struct setup_data { - u64 next; - u32 type; - u32 len; - u8 data[0]; - }; - + struct setup_data { + __u64 next; + __u32 type; + __u32 len; + __u8 data[]; + } + Where, the next is a 64-bit physical pointer to the next node of linked list, the next field of the last node is 0; the type is used to identify the contents of data; the len is the length of data @@ -834,12 +834,12 @@ Protocol: 2.09+ Thus setup_indirect struct and SETUP_INDIRECT type were introduced in protocol 2.15:: - struct setup_indirect { - __u32 type; - __u32 reserved; /* Reserved, must be set to zero. */ - __u64 len; - __u64 addr; - }; + struct setup_indirect { + __u32 type; + __u32 reserved; /* Reserved, must be set to zero. */ + __u64 len; + __u64 addr; + }; The type member is a SETUP_INDIRECT | SETUP_* type. However, it cannot be SETUP_INDIRECT itself since making the setup_indirect a tree structure @@ -849,17 +849,17 @@ Protocol: 2.09+ Let's give an example how to point to SETUP_E820_EXT data using setup_indirect. In this case setup_data and setup_indirect will look like this:: - struct setup_data { - __u64 next = 0 or ; - __u32 type = SETUP_INDIRECT; - __u32 len = sizeof(setup_indirect); - __u8 data[sizeof(setup_indirect)] = struct setup_indirect { - __u32 type = SETUP_INDIRECT | SETUP_E820_EXT; - __u32 reserved = 0; - __u64 len = ; - __u64 addr = ; - } - } + struct setup_data { + .next = 0, /* or */ + .type = SETUP_INDIRECT, + .len = sizeof(setup_indirect), + .data[sizeof(setup_indirect)] = (struct setup_indirect) { + .type = SETUP_INDIRECT | SETUP_E820_EXT, + .reserved = 0, + .len = , + .addr = , + }, + } .. note:: SETUP_INDIRECT | SETUP_NONE objects cannot be properly distinguished @@ -896,19 +896,19 @@ Offset/size: 0x260/4 The kernel runtime start address is determined by the following algorithm:: - if (relocatable_kernel) { - if (load_address < pref_address) - load_address = pref_address; - runtime_start = align_up(load_address, kernel_alignment); - } else { - runtime_start = pref_address; - } + if (relocatable_kernel) { + if (load_address < pref_address) + load_address = pref_address; + runtime_start = align_up(load_address, kernel_alignment); + } else { + runtime_start = pref_address; + } Hence the necessary memory window location and size can be estimated by a boot loader as:: - memory_window_start = runtime_start; - memory_window_size = init_size; + memory_window_start = runtime_start; + memory_window_size = init_size; ============ =============== Field name: handover_offset @@ -938,12 +938,12 @@ The kernel_info =============== The relationships between the headers are analogous to the various data -sections: +sections:: setup_header = .data boot_params/setup_data = .bss -What is missing from the above list? That's right: +What is missing from the above list? That's right:: kernel_info = .rodata @@ -975,22 +975,22 @@ after kernel_info_var_len_data label. Each chunk of variable size data has to be prefixed with header/magic and its size, e.g.:: kernel_info: - .ascii "LToP" /* Header, Linux top (structure). */ - .long kernel_info_var_len_data - kernel_info - .long kernel_info_end - kernel_info - .long 0x01234567 /* Some fixed size data for the bootloaders. */ + .ascii "LToP" /* Header, Linux top (structure). */ + .long kernel_info_var_len_data - kernel_info + .long kernel_info_end - kernel_info + .long 0x01234567 /* Some fixed size data for the bootloaders. */ kernel_info_var_len_data: - example_struct: /* Some variable size data for the bootloaders. */ - .ascii "0123" /* Header/Magic. */ - .long example_struct_end - example_struct - .ascii "Struct" - .long 0x89012345 + example_struct: /* Some variable size data for the bootloaders. */ + .ascii "0123" /* Header/Magic. */ + .long example_struct_end - example_struct + .ascii "Struct" + .long 0x89012345 example_struct_end: - example_strings: /* Some variable size data for the bootloaders. */ - .ascii "ABCD" /* Header/Magic. */ - .long example_strings_end - example_strings - .asciz "String_0" - .asciz "String_1" + example_strings: /* Some variable size data for the bootloaders. */ + .ascii "ABCD" /* Header/Magic. */ + .long example_strings_end - example_strings + .asciz "String_0" + .asciz "String_1" example_strings_end: kernel_info_end: @@ -1139,67 +1139,63 @@ mode segment. Such a boot loader should enter the following fields in the header:: - unsigned long base_ptr; /* base address for real-mode segment */ + unsigned long base_ptr; /* base address for real-mode segment */ - if ( setup_sects == 0 ) { - setup_sects = 4; - } + if (setup_sects == 0) + setup_sects = 4; - if ( protocol >= 0x0200 ) { - type_of_loader = ; - if ( loading_initrd ) { - ramdisk_image = ; - ramdisk_size = ; - } + if (protocol >= 0x0200) { + type_of_loader = ; + if (loading_initrd) { + ramdisk_image = ; + ramdisk_size = ; + } - if ( protocol >= 0x0202 && loadflags & 0x01 ) - heap_end = 0xe000; - else - heap_end = 0x9800; + if (protocol >= 0x0202 && loadflags & 0x01) + heap_end = 0xe000; + else + heap_end = 0x9800; - if ( protocol >= 0x0201 ) { - heap_end_ptr = heap_end - 0x200; - loadflags |= 0x80; /* CAN_USE_HEAP */ - } + if (protocol >= 0x0201) { + heap_end_ptr = heap_end - 0x200; + loadflags |= 0x80; /* CAN_USE_HEAP */ + } - if ( protocol >= 0x0202 ) { - cmd_line_ptr = base_ptr + heap_end; - strcpy(cmd_line_ptr, cmdline); - } else { - cmd_line_magic = 0xA33F; - cmd_line_offset = heap_end; - setup_move_size = heap_end + strlen(cmdline)+1; - strcpy(base_ptr+cmd_line_offset, cmdline); - } - } else { - /* Very old kernel */ + if (protocol >= 0x0202) { + cmd_line_ptr = base_ptr + heap_end; + strcpy(cmd_line_ptr, cmdline); + } else { + cmd_line_magic = 0xA33F; + cmd_line_offset = heap_end; + setup_move_size = heap_end + strlen(cmdline) + 1; + strcpy(base_ptr + cmd_line_offset, cmdline); + } + } else { + /* Very old kernel */ - heap_end = 0x9800; + heap_end = 0x9800; - cmd_line_magic = 0xA33F; - cmd_line_offset = heap_end; + cmd_line_magic = 0xA33F; + cmd_line_offset = heap_end; - /* A very old kernel MUST have its real-mode code - loaded at 0x90000 */ + /* A very old kernel MUST have its real-mode code loaded at 0x90000 */ + if (base_ptr != 0x90000) { + /* Copy the real-mode kernel */ + memcpy(0x90000, base_ptr, (setup_sects + 1) * 512); + base_ptr = 0x90000; /* Relocated */ + } - if ( base_ptr != 0x90000 ) { - /* Copy the real-mode kernel */ - memcpy(0x90000, base_ptr, (setup_sects+1)*512); - base_ptr = 0x90000; /* Relocated */ - } + strcpy(0x90000 + cmd_line_offset, cmdline); - strcpy(0x90000+cmd_line_offset, cmdline); - - /* It is recommended to clear memory up to the 32K mark */ - memset(0x90000 + (setup_sects+1)*512, 0, - (64-(setup_sects+1))*512); - } + /* It is recommended to clear memory up to the 32K mark */ + memset(0x90000 + (setup_sects + 1) * 512, 0, (64 - (setup_sects + 1)) * 512); + } Loading The Rest of The Kernel ============================== -The 32-bit (non-real-mode) kernel starts at offset (setup_sects+1)*512 +The 32-bit (non-real-mode) kernel starts at offset (setup_sects + 1) * 512 in the kernel file (again, if setup_sects == 0 the real value is 4.) It should be loaded at address 0x10000 for Image/zImage kernels and 0x100000 for bzImage kernels. @@ -1207,13 +1203,14 @@ It should be loaded at address 0x10000 for Image/zImage kernels and The kernel is a bzImage kernel if the protocol >= 2.00 and the 0x01 bit (LOAD_HIGH) in the loadflags field is set:: - is_bzImage = (protocol >= 0x0200) && (loadflags & 0x01); - load_address = is_bzImage ? 0x100000 : 0x10000; + is_bzImage = (protocol >= 0x0200) && (loadflags & 0x01); + load_address = is_bzImage ? 0x100000 : 0x10000; -Note that Image/zImage kernels can be up to 512K in size, and thus use -the entire 0x10000-0x90000 range of memory. This means it is pretty -much a requirement for these kernels to load the real-mode part at -0x90000. bzImage kernels allow much more flexibility. +.. note:: + Image/zImage kernels can be up to 512K in size, and thus use the entire + 0x10000-0x90000 range of memory. This means it is pretty much a + requirement for these kernels to load the real-mode part at 0x90000. + bzImage kernels allow much more flexibility. Special Command Line Options ============================ @@ -1282,19 +1279,20 @@ es = ss. In our example from above, we would do:: - /* Note: in the case of the "old" kernel protocol, base_ptr must - be == 0x90000 at this point; see the previous sample code */ + /* + * Note: in the case of the "old" kernel protocol, base_ptr must + * be == 0x90000 at this point; see the previous sample code. + */ + seg = base_ptr >> 4; - seg = base_ptr >> 4; + cli(); /* Enter with interrupts disabled! */ - cli(); /* Enter with interrupts disabled! */ + /* Set up the real-mode kernel stack */ + _SS = seg; + _SP = heap_end; - /* Set up the real-mode kernel stack */ - _SS = seg; - _SP = heap_end; - - _DS = _ES = _FS = _GS = seg; - jmp_far(seg+0x20, 0); /* Run the kernel */ + _DS = _ES = _FS = _GS = seg; + jmp_far(seg + 0x20, 0); /* Run the kernel */ If your boot sector accesses a floppy drive, it is recommended to switch off the floppy motor before running the kernel, since the @@ -1349,7 +1347,7 @@ from offset 0x01f1 of kernel image on should be loaded into struct boot_params and examined. The end of setup header can be calculated as follow:: - 0x0202 + byte value at offset 0x0201 + 0x0202 + byte value at offset 0x0201 In addition to read/modify/write the setup header of the struct boot_params as that of 16-bit boot protocol, the boot loader should @@ -1385,7 +1383,7 @@ Then, the setup header at offset 0x01f1 of kernel image on should be loaded into struct boot_params and examined. The end of setup header can be calculated as follows:: - 0x0202 + byte value at offset 0x0201 + 0x0202 + byte value at offset 0x0201 In addition to read/modify/write the setup header of the struct boot_params as that of 16-bit boot protocol, the boot loader should @@ -1427,7 +1425,7 @@ execution context provided by the EFI firmware. The function prototype for the handover entry point looks like this:: - efi_stub_entry(void *handle, efi_system_table_t *table, struct boot_params *bp) + void efi_stub_entry(void *handle, efi_system_table_t *table, struct boot_params *bp); 'handle' is the EFI image handle passed to the boot loader by the EFI firmware, 'table' is the EFI system table - these are the first two @@ -1442,12 +1440,13 @@ The boot loader *must* fill out the following fields in bp:: All other fields should be zero. -NOTE: The EFI Handover Protocol is deprecated in favour of the ordinary PE/COFF - entry point, combined with the LINUX_EFI_INITRD_MEDIA_GUID based initrd - loading protocol (refer to [0] for an example of the bootloader side of - this), which removes the need for any knowledge on the part of the EFI - bootloader regarding the internal representation of boot_params or any - requirements/limitations regarding the placement of the command line - and ramdisk in memory, or the placement of the kernel image itself. +.. note:: + The EFI Handover Protocol is deprecated in favour of the ordinary PE/COFF + entry point, combined with the LINUX_EFI_INITRD_MEDIA_GUID based initrd + loading protocol (refer to [0] for an example of the bootloader side of + this), which removes the need for any knowledge on the part of the EFI + bootloader regarding the internal representation of boot_params or any + requirements/limitations regarding the placement of the command line + and ramdisk in memory, or the placement of the kernel image itself. [0] https://github.com/u-boot/u-boot/commit/ec80b4735a593961fe701cc3a5d717d4739b0fd0 diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst index a824affd741d..6768fc1fad16 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/arch/x86/resctrl.rst @@ -384,6 +384,16 @@ When monitoring is enabled all MON groups will also contain: Available only with debug option. The identifier used by hardware for the monitor group. On x86 this is the RMID. +When the "mba_MBps" mount option is used all CTRL_MON groups will also contain: + +"mba_MBps_event": + Reading this file shows which memory bandwidth event is used + as input to the software feedback loop that keeps memory bandwidth + below the value specified in the schemata file. Writing the + name of one of the supported memory bandwidth events found in + /sys/fs/resctrl/info/L3_MON/mon_features changes the input + event. + Resource allocation rules ------------------------- diff --git a/Documentation/arch/x86/topology.rst b/Documentation/arch/x86/topology.rst index 7352ab89a55a..c12837e61bda 100644 --- a/Documentation/arch/x86/topology.rst +++ b/Documentation/arch/x86/topology.rst @@ -135,6 +135,10 @@ Thread-related topology information in the kernel: The ID of the core to which a thread belongs. It is also printed in /proc/cpuinfo "core_id." + - topology_logical_core_id(); + + The logical core ID to which a thread belongs. + System topology examples diff --git a/Documentation/arch/x86/x86_64/boot-options.rst b/Documentation/arch/x86/x86_64/boot-options.rst deleted file mode 100644 index d69e3cfbdba5..000000000000 --- a/Documentation/arch/x86/x86_64/boot-options.rst +++ /dev/null @@ -1,312 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -=========================== -AMD64 Specific Boot Options -=========================== - -There are many others (usually documented in driver documentation), but -only the AMD64 specific ones are listed here. - -Machine check -============= -Please see Documentation/arch/x86/x86_64/machinecheck.rst for sysfs runtime tunables. - - mce=off - Disable machine check - mce=no_cmci - Disable CMCI(Corrected Machine Check Interrupt) that - Intel processor supports. Usually this disablement is - not recommended, but it might be handy if your hardware - is misbehaving. - Note that you'll get more problems without CMCI than with - due to the shared banks, i.e. you might get duplicated - error logs. - mce=dont_log_ce - Don't make logs for corrected errors. All events reported - as corrected are silently cleared by OS. - This option will be useful if you have no interest in any - of corrected errors. - mce=ignore_ce - Disable features for corrected errors, e.g. polling timer - and CMCI. All events reported as corrected are not cleared - by OS and remained in its error banks. - Usually this disablement is not recommended, however if - there is an agent checking/clearing corrected errors - (e.g. BIOS or hardware monitoring applications), conflicting - with OS's error handling, and you cannot deactivate the agent, - then this option will be a help. - mce=no_lmce - Do not opt-in to Local MCE delivery. Use legacy method - to broadcast MCEs. - mce=bootlog - Enable logging of machine checks left over from booting. - Disabled by default on AMD Fam10h and older because some BIOS - leave bogus ones. - If your BIOS doesn't do that it's a good idea to enable though - to make sure you log even machine check events that result - in a reboot. On Intel systems it is enabled by default. - mce=nobootlog - Disable boot machine check logging. - mce=monarchtimeout (number) - monarchtimeout: - Sets the time in us to wait for other CPUs on machine checks. 0 - to disable. - mce=bios_cmci_threshold - Don't overwrite the bios-set CMCI threshold. This boot option - prevents Linux from overwriting the CMCI threshold set by the - bios. Without this option, Linux always sets the CMCI - threshold to 1. Enabling this may make memory predictive failure - analysis less effective if the bios sets thresholds for memory - errors since we will not see details for all errors. - mce=recovery - Force-enable recoverable machine check code paths - - nomce (for compatibility with i386) - same as mce=off - - Everything else is in sysfs now. - -APICs -===== - - apic - Use IO-APIC. Default - - noapic - Don't use the IO-APIC. - - disableapic - Don't use the local APIC - - nolapic - Don't use the local APIC (alias for i386 compatibility) - - pirq=... - See Documentation/arch/x86/i386/IO-APIC.rst - - noapictimer - Don't set up the APIC timer - - no_timer_check - Don't check the IO-APIC timer. This can work around - problems with incorrect timer initialization on some boards. - - apicpmtimer - Do APIC timer calibration using the pmtimer. Implies - apicmaintimer. Useful when your PIT timer is totally broken. - -Timing -====== - - notsc - Deprecated, use tsc=unstable instead. - - nohpet - Don't use the HPET timer. - -Idle loop -========= - - idle=poll - Don't do power saving in the idle loop using HLT, but poll for rescheduling - event. This will make the CPUs eat a lot more power, but may be useful - to get slightly better performance in multiprocessor benchmarks. It also - makes some profiling using performance counters more accurate. - Please note that on systems with MONITOR/MWAIT support (like Intel EM64T - CPUs) this option has no performance advantage over the normal idle loop. - It may also interact badly with hyperthreading. - -Rebooting -========= - - reboot=b[ios] | t[riple] | k[bd] | a[cpi] | e[fi] | p[ci] [, [w]arm | [c]old] - bios - Use the CPU reboot vector for warm reset - warm - Don't set the cold reboot flag - cold - Set the cold reboot flag - triple - Force a triple fault (init) - kbd - Use the keyboard controller. cold reset (default) - acpi - Use the ACPI RESET_REG in the FADT. If ACPI is not configured or - the ACPI reset does not work, the reboot path attempts the reset - using the keyboard controller. - efi - Use efi reset_system runtime service. If EFI is not configured or - the EFI reset does not work, the reboot path attempts the reset using - the keyboard controller. - pci - Use a write to the PCI config space register 0xcf9 to trigger reboot. - - Using warm reset will be much faster especially on big memory - systems because the BIOS will not go through the memory check. - Disadvantage is that not all hardware will be completely reinitialized - on reboot so there may be boot problems on some systems. - - reboot=force - Don't stop other CPUs on reboot. This can make reboot more reliable - in some cases. - - reboot=default - There are some built-in platform specific "quirks" - you may see: - "reboot: series board detected. Selecting for reboots." - In the case where you think the quirk is in error (e.g. you have - newer BIOS, or newer board) using this option will ignore the built-in - quirk table, and use the generic default reboot actions. - -NUMA -==== - - numa=off - Only set up a single NUMA node spanning all memory. - - numa=noacpi - Don't parse the SRAT table for NUMA setup - - numa=nohmat - Don't parse the HMAT table for NUMA setup, or soft-reserved memory - partitioning. - -ACPI -==== - - acpi=off - Don't enable ACPI - acpi=ht - Use ACPI boot table parsing, but don't enable ACPI interpreter - acpi=force - Force ACPI on (currently not needed) - acpi=strict - Disable out of spec ACPI workarounds. - acpi_sci={edge,level,high,low} - Set up ACPI SCI interrupt. - acpi=noirq - Don't route interrupts - acpi=nocmcff - Disable firmware first mode for corrected errors. This - disables parsing the HEST CMC error source to check if - firmware has set the FF flag. This may result in - duplicate corrected error reports. - -PCI -=== - - pci=off - Don't use PCI - pci=conf1 - Use conf1 access. - pci=conf2 - Use conf2 access. - pci=rom - Assign ROMs. - pci=assign-busses - Assign busses - pci=irqmask=MASK - Set PCI interrupt mask to MASK - pci=lastbus=NUMBER - Scan up to NUMBER busses, no matter what the mptable says. - pci=noacpi - Don't use ACPI to set up PCI interrupt routing. - -IOMMU (input/output memory management unit) -=========================================== -Multiple x86-64 PCI-DMA mapping implementations exist, for example: - - 1. : use no hardware/software IOMMU at all - (e.g. because you have < 3 GB memory). - Kernel boot message: "PCI-DMA: Disabling IOMMU" - - 2. : AMD GART based hardware IOMMU. - Kernel boot message: "PCI-DMA: using GART IOMMU" - - 3. : Software IOMMU implementation. Used - e.g. if there is no hardware IOMMU in the system and it is need because - you have >3GB memory or told the kernel to us it (iommu=soft)) - Kernel boot message: "PCI-DMA: Using software bounce buffering - for IO (SWIOTLB)" - -:: - - iommu=[][,noagp][,off][,force][,noforce] - [,memaper[=]][,merge][,fullflush][,nomerge] - [,noaperture] - -General iommu options: - - off - Don't initialize and use any kind of IOMMU. - noforce - Don't force hardware IOMMU usage when it is not needed. (default). - force - Force the use of the hardware IOMMU even when it is - not actually needed (e.g. because < 3 GB memory). - soft - Use software bounce buffering (SWIOTLB) (default for - Intel machines). This can be used to prevent the usage - of an available hardware IOMMU. - -iommu options only relevant to the AMD GART hardware IOMMU: - - - Set the size of the remapping area in bytes. - allowed - Overwrite iommu off workarounds for specific chipsets. - fullflush - Flush IOMMU on each allocation (default). - nofullflush - Don't use IOMMU fullflush. - memaper[=] - Allocate an own aperture over RAM with size 32MB<[,force,noforce] - - Prereserve that many 2K slots for the software IO bounce buffering. - force - Force all IO through the software TLB. - noforce - Do not initialize the software TLB. - - -Miscellaneous -============= - - nogbpages - Do not use GB pages for kernel direct mappings. - gbpages - Use GB pages for kernel direct mappings. - - -AMD SEV (Secure Encrypted Virtualization) -========================================= -Options relating to AMD SEV, specified via the following format: - -:: - - sev=option1[,option2] - -The available options are: - - debug - Enable debug messages. - - nosnp - Do not enable SEV-SNP (applies to host/hypervisor only). Setting - 'nosnp' avoids the RMP check overhead in memory accesses when - users do not want to run SEV-SNP guests. diff --git a/Documentation/arch/x86/x86_64/fake-numa-for-cpusets.rst b/Documentation/arch/x86/x86_64/fake-numa-for-cpusets.rst index ba74617d4999..970ee94eb551 100644 --- a/Documentation/arch/x86/x86_64/fake-numa-for-cpusets.rst +++ b/Documentation/arch/x86/x86_64/fake-numa-for-cpusets.rst @@ -18,7 +18,7 @@ For more information on the features of cpusets, see Documentation/admin-guide/cgroup-v1/cpusets.rst. There are a number of different configurations you can use for your needs. For more information on the numa=fake command line option and its various ways of -configuring fake nodes, see Documentation/arch/x86/x86_64/boot-options.rst. +configuring fake nodes, see Documentation/admin-guide/kernel-parameters.txt For the purposes of this introduction, we'll assume a very primitive NUMA emulation setup of "numa=fake=4*512,". This will split our system memory into diff --git a/Documentation/arch/x86/x86_64/index.rst b/Documentation/arch/x86/x86_64/index.rst index ad15e9bd623f..a0261957a08a 100644 --- a/Documentation/arch/x86/x86_64/index.rst +++ b/Documentation/arch/x86/x86_64/index.rst @@ -7,7 +7,6 @@ x86_64 Support .. toctree:: :maxdepth: 2 - boot-options uefi mm 5level-paging diff --git a/Documentation/arch/x86/x86_64/uefi.rst b/Documentation/arch/x86/x86_64/uefi.rst index fbc30c9a071d..e84592dbd6c1 100644 --- a/Documentation/arch/x86/x86_64/uefi.rst +++ b/Documentation/arch/x86/x86_64/uefi.rst @@ -12,14 +12,20 @@ with EFI firmware and specifications are listed below. 1. UEFI specification: http://www.uefi.org -2. Booting Linux kernel on UEFI x86_64 platform requires bootloader - support. Elilo with x86_64 support can be used. +2. Booting Linux kernel on UEFI x86_64 platform can either be + done using the or using a + separate bootloader. 3. x86_64 platform with EFI/UEFI firmware. Mechanics --------- +Refer to to learn how to use the EFI stub. + +Below are general EFI setup guidelines on the x86_64 platform, +regardless of whether you use the EFI stub or a separate bootloader. + - Build the kernel with the following configuration:: CONFIG_FB_EFI=y @@ -31,16 +37,27 @@ Mechanics CONFIG_EFI=y CONFIG_EFIVAR_FS=y or m # optional -- Create a VFAT partition on the disk -- Copy the following to the VFAT partition: +- Create a VFAT partition on the disk with the EFI System flag + You can do this with fdisk with the following commands: - elilo bootloader with x86_64 support, elilo configuration file, - kernel image built in first step and corresponding - initrd. Instructions on building elilo and its dependencies - can be found in the elilo sourceforge project. + 1. g - initialize a GPT partition table + 2. n - create a new partition + 3. t - change the partition type to "EFI System" (number 1) + 4. w - write and save the changes + + Afterwards, initialize the VFAT filesystem by running mkfs:: + + mkfs.fat /dev/ + +- Copy the boot files to the VFAT partition: + If you use the EFI stub method, the kernel acts also as an EFI executable. + + You can just copy the bzImage to the EFI/boot/bootx64.efi path on the partition + so that it will automatically get booted, see the page + for additional instructions regarding passage of kernel parameters and initramfs. + + If you use a custom bootloader, refer to the relevant documentation for help on this part. -- Boot to EFI shell and invoke elilo choosing the kernel image built - in first step. - If some or all EFI runtime services don't work, you can try following kernel command line parameters to turn off some or all EFI runtime services. diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst index 51665a3e6a50..1e0e7358e14a 100644 --- a/Documentation/block/ublk.rst +++ b/Documentation/block/ublk.rst @@ -333,6 +333,4 @@ References .. [#userspace_readme] https://github.com/ming1/ubdsrv/blob/master/README -.. [#stefan] https://lore.kernel.org/linux-block/YoOr6jBfgVm8GvWg@stefanha-x1.localdomain/ - .. [#xiaoguang] https://lore.kernel.org/linux-block/YoOr6jBfgVm8GvWg@stefanha-x1.localdomain/ diff --git a/Documentation/core-api/cgroup.rst b/Documentation/core-api/cgroup.rst new file mode 100644 index 000000000000..734ea21e1e17 --- /dev/null +++ b/Documentation/core-api/cgroup.rst @@ -0,0 +1,9 @@ +================== +Cgroup Kernel APIs +================== + +Device Memory Cgroup API (dmemcg) +================================= +.. kernel-doc:: kernel/cgroup/dmem.c + :export: + diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index 563b8fc0002f..e9789bd381d8 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -53,6 +53,7 @@ Library functionality that is used throughout the kernel. floating-point union_find min_heap + parser Low level entry and exit ======================== @@ -109,6 +110,7 @@ more memory-management documentation in Documentation/mm/index.rst. dma-isa-lpc swiotlb mm-api + cgroup genalloc pin_user_pages boot-time-mm diff --git a/Documentation/core-api/kref.rst b/Documentation/core-api/kref.rst index c61eea6f1bf2..8db9ff03d952 100644 --- a/Documentation/core-api/kref.rst +++ b/Documentation/core-api/kref.rst @@ -3,7 +3,7 @@ Adding reference counters (krefs) to kernel objects =================================================== :Author: Corey Minyard -:Author: Thomas Hellstrom +:Author: Thomas Hellström A lot of this was lifted from Greg Kroah-Hartman's 2004 OLS paper and presentation on krefs, which can be found at: @@ -321,3 +321,8 @@ rcu grace period after release_entry_rcu was called. That can be accomplished by using kfree_rcu(entry, rhead) as done above, or by calling synchronize_rcu() before using kfree, but note that synchronize_rcu() may sleep for a substantial amount of time. + +Functions and structures +======================== + +.. kernel-doc:: include/linux/kref.h diff --git a/Documentation/core-api/min_heap.rst b/Documentation/core-api/min_heap.rst index 0c636c8b7aa5..683bc6d09f00 100644 --- a/Documentation/core-api/min_heap.rst +++ b/Documentation/core-api/min_heap.rst @@ -4,6 +4,8 @@ Min Heap API ============ +:Author: Kuan-Wei Chiu + Introduction ============ diff --git a/Documentation/core-api/packing.rst b/Documentation/core-api/packing.rst index 821691f23c54..0ce2078c8e13 100644 --- a/Documentation/core-api/packing.rst +++ b/Documentation/core-api/packing.rst @@ -227,11 +227,119 @@ Intended use Drivers that opt to use this API first need to identify which of the above 3 quirk combinations (for a total of 8) match what the hardware documentation -describes. Then they should wrap the packing() function, creating a new -xxx_packing() that calls it using the proper QUIRK_* one-hot bits set. +describes. + +There are 3 supported usage patterns, detailed below. + +packing() +^^^^^^^^^ + +This API function is deprecated. The packing() function returns an int-encoded error code, which protects the programmer against incorrect API use. The errors are not expected to occur -during runtime, therefore it is reasonable for xxx_packing() to return void -and simply swallow those errors. Optionally it can dump stack or print the -error description. +during runtime, therefore it is reasonable to wrap packing() into a custom +function which returns void and swallows those errors. Optionally it can +dump stack or print the error description. + +.. code-block:: c + + void my_packing(void *buf, u64 *val, int startbit, int endbit, + size_t len, enum packing_op op) + { + int err; + + /* Adjust quirks accordingly */ + err = packing(buf, val, startbit, endbit, len, op, QUIRK_LSW32_IS_FIRST); + if (likely(!err)) + return; + + if (err == -EINVAL) { + pr_err("Start bit (%d) expected to be larger than end (%d)\n", + startbit, endbit); + } else if (err == -ERANGE) { + if ((startbit - endbit + 1) > 64) + pr_err("Field %d-%d too large for 64 bits!\n", + startbit, endbit); + else + pr_err("Cannot store %llx inside bits %d-%d (would truncate)\n", + *val, startbit, endbit); + } + dump_stack(); + } + +pack() and unpack() +^^^^^^^^^^^^^^^^^^^ + +These are const-correct variants of packing(), and eliminate the last "enum +packing_op op" argument. + +Calling pack(...) is equivalent, and preferred, to calling packing(..., PACK). + +Calling unpack(...) is equivalent, and preferred, to calling packing(..., UNPACK). + +pack_fields() and unpack_fields() +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The library exposes optimized functions for the scenario where there are many +fields represented in a buffer, and it encourages consumer drivers to avoid +repetitive calls to pack() and unpack() for each field, but instead use +pack_fields() and unpack_fields(), which reduces the code footprint. + +These APIs use field definitions in arrays of ``struct packed_field_u8`` or +``struct packed_field_u16``, allowing consumer drivers to minimize the size +of these arrays according to their custom requirements. + +The pack_fields() and unpack_fields() API functions are actually macros which +automatically select the appropriate function at compile time, based on the +type of the fields array passed in. + +An additional benefit over pack() and unpack() is that sanity checks on the +field definitions are handled at compile time with ``BUILD_BUG_ON`` rather +than only when the offending code is executed. These functions return void and +wrapping them to handle unexpected errors is not necessary. + +It is recommended, but not required, that you wrap your packed buffer into a +structured type with a fixed size. This generally makes it easier for the +compiler to enforce that the correct size buffer is used. + +Here is an example of how to use the fields APIs: + +.. code-block:: c + + /* Ordering inside the unpacked structure is flexible and can be different + * from the packed buffer. Here, it is optimized to reduce padding. + */ + struct data { + u64 field3; + u32 field4; + u16 field1; + u8 field2; + }; + + #define SIZE 13 + + typdef struct __packed { u8 buf[SIZE]; } packed_buf_t; + + static const struct packed_field_u8 fields[] = { + PACKED_FIELD(100, 90, struct data, field1), + PACKED_FIELD(90, 87, struct data, field2), + PACKED_FIELD(86, 30, struct data, field3), + PACKED_FIELD(29, 0, struct data, field4), + }; + + void unpack_your_data(const packed_buf_t *buf, struct data *unpacked) + { + BUILD_BUG_ON(sizeof(*buf) != SIZE; + + unpack_fields(buf, sizeof(*buf), unpacked, fields, + QUIRK_LITTLE_ENDIAN); + } + + void pack_your_data(const struct data *unpacked, packed_buf_t *buf) + { + BUILD_BUG_ON(sizeof(*buf) != SIZE; + + pack_fields(buf, sizeof(*buf), unpacked, fields, + QUIRK_LITTLE_ENDIAN); + } diff --git a/Documentation/core-api/parser.rst b/Documentation/core-api/parser.rst new file mode 100644 index 000000000000..45750d04b895 --- /dev/null +++ b/Documentation/core-api/parser.rst @@ -0,0 +1,17 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +============== +Generic parser +============== + +Overview +======== + +The generic parser is a simple parser for parsing mount options, +filesystem options, driver options, subsystem options, etc. + +Parser API +========== + +.. kernel-doc:: lib/parser.c + :export: diff --git a/Documentation/core-api/symbol-namespaces.rst b/Documentation/core-api/symbol-namespaces.rst index 27a9cccc792c..06f766a6aab2 100644 --- a/Documentation/core-api/symbol-namespaces.rst +++ b/Documentation/core-api/symbol-namespaces.rst @@ -41,9 +41,9 @@ entries. In addition to the macros EXPORT_SYMBOL() and EXPORT_SYMBOL_GPL(), that allow exporting of kernel symbols to the kernel symbol table, variants of these are available to export symbols into a certain namespace: EXPORT_SYMBOL_NS() and -EXPORT_SYMBOL_NS_GPL(). They take one additional argument: the namespace. -Please note that due to macro expansion that argument needs to be a -preprocessor symbol. E.g. to export the symbol ``usb_stor_suspend`` into the +EXPORT_SYMBOL_NS_GPL(). They take one additional argument: the namespace as a +string constant. Note that this string must not contain whitespaces. +E.g. to export the symbol ``usb_stor_suspend`` into the namespace ``USB_STORAGE``, use:: EXPORT_SYMBOL_NS(usb_stor_suspend, "USB_STORAGE"); @@ -78,11 +78,10 @@ as this argument has preference over a default symbol namespace. A second option to define the default namespace is directly in the compilation unit as preprocessor statement. The above example would then read:: - #undef DEFAULT_SYMBOL_NAMESPACE #define DEFAULT_SYMBOL_NAMESPACE "USB_COMMON" -within the corresponding compilation unit before any EXPORT_SYMBOL macro is -used. +within the corresponding compilation unit before the #include for +. Typically it's placed before the first #include statement. 3. How to use Symbols exported in Namespaces ============================================ diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index 77e0ece2b1d6..f6a3eef4fe7f 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -42,8 +42,8 @@ call xa_tag_pointer() to create an entry with a tag, xa_untag_pointer() to turn a tagged entry back into an untagged pointer and xa_pointer_tag() to retrieve the tag of an entry. Tagged pointers use the same bits that are used to distinguish value entries from normal pointers, so you must -decide whether they want to store value entries or tagged pointers in -any particular XArray. +decide whether you want to store value entries or tagged pointers in any +particular XArray. The XArray does not support storing IS_ERR() pointers as some conflict with value entries or internal entries. @@ -52,8 +52,9 @@ An unusual feature of the XArray is the ability to create entries which occupy a range of indices. Once stored to, looking up any index in the range will return the same entry as looking up any other index in the range. Storing to any index will store to all of them. Multi-index -entries can be explicitly split into smaller entries, or storing ``NULL`` -into any entry will cause the XArray to forget about the range. +entries can be explicitly split into smaller entries. Unsetting (using +xa_erase() or xa_store() with ``NULL``) any entry will cause the XArray +to forget about the range. Normal API ========== @@ -63,13 +64,14 @@ for statically allocated XArrays or xa_init() for dynamically allocated ones. A freshly-initialised XArray contains a ``NULL`` pointer at every index. -You can then set entries using xa_store() and get entries -using xa_load(). xa_store will overwrite any entry with the -new entry and return the previous entry stored at that index. You can -use xa_erase() instead of calling xa_store() with a -``NULL`` entry. There is no difference between an entry that has never -been stored to, one that has been erased and one that has most recently -had ``NULL`` stored to it. +You can then set entries using xa_store() and get entries using +xa_load(). xa_store() will overwrite any entry with the new entry and +return the previous entry stored at that index. You can unset entries +using xa_erase() or by setting the entry to ``NULL`` using xa_store(). +There is no difference between an entry that has never been stored to +and one that has been erased with xa_erase(); an entry that has most +recently had ``NULL`` stored to it is also equivalent except if the +XArray was initialized with ``XA_FLAGS_ALLOC``. You can conditionally replace an entry at an index by using xa_cmpxchg(). Like cmpxchg(), it will only succeed if diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst index 3c0ac08b2709..65c54b27a60b 100644 --- a/Documentation/dev-tools/index.rst +++ b/Documentation/dev-tools/index.rst @@ -10,6 +10,9 @@ whole; patches welcome! A brief overview of testing-specific tools can be found in Documentation/dev-tools/testing-overview.rst +Tools that are specific to debugging can be found in +Documentation/process/debugging/index.rst + .. toctree:: :caption: Table of contents :maxdepth: 2 @@ -27,8 +30,6 @@ Documentation/dev-tools/testing-overview.rst kmemleak kcsan kfence - gdb-kernel-debugging - kgdb kselftest kunit/index ktap diff --git a/Documentation/devicetree/bindings/arm/altera/socfpga-system.txt b/Documentation/devicetree/bindings/arm/altera/socfpga-system.txt deleted file mode 100644 index 82edbaaa3f85..000000000000 --- a/Documentation/devicetree/bindings/arm/altera/socfpga-system.txt +++ /dev/null @@ -1,25 +0,0 @@ -Altera SOCFPGA System Manager - -Required properties: -- compatible : "altr,sys-mgr" -- reg : Should contain 1 register ranges(address and length) -- cpu1-start-addr : CPU1 start address in hex. - -Example: - sysmgr@ffd08000 { - compatible = "altr,sys-mgr"; - reg = <0xffd08000 0x1000>; - cpu1-start-addr = <0xffd080c4>; - }; - -ARM64 - Stratix10 -Required properties: -- compatible : "altr,sys-mgr-s10" -- reg : Should contain 1 register range(address and length) - for system manager register. - -Example: - sysmgr@ffd12000 { - compatible = "altr,sys-mgr-s10"; - reg = <0xffd12000 0x228>; - }; diff --git a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml index 04a8c37b4aff..742dc4e25d3b 100644 --- a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml +++ b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml @@ -38,6 +38,12 @@ properties: enum: - arm,coresight-dummy-source + arm,static-trace-id: + description: If dummy source needs static id support, use this to set trace id. + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 1 + maximum: 111 + out-ports: $ref: /schemas/graph.yaml#/properties/ports diff --git a/Documentation/devicetree/bindings/arm/arm,coresight-static-replicator.yaml b/Documentation/devicetree/bindings/arm/arm,coresight-static-replicator.yaml index 1892a091ac35..a6f793ea03b6 100644 --- a/Documentation/devicetree/bindings/arm/arm,coresight-static-replicator.yaml +++ b/Documentation/devicetree/bindings/arm/arm,coresight-static-replicator.yaml @@ -45,7 +45,22 @@ properties: patternProperties: '^port@[01]$': description: Output connections to CoreSight Trace bus - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false + + properties: + endpoint: + $ref: /schemas/graph.yaml#/$defs/endpoint-base + unevaluatedProperties: false + + properties: + filter-source: + $ref: /schemas/types.yaml#/definitions/phandle + description: + phandle to the coresight trace source device matching the + hard coded filtering for this port + + remote-endpoint: true required: - compatible @@ -72,6 +87,7 @@ examples: reg = <0>; replicator_out_port0: endpoint { remote-endpoint = <&etb_in_port>; + filter-source = <&tpdm_video>; }; }; @@ -79,6 +95,7 @@ examples: reg = <1>; replicator_out_port1: endpoint { remote-endpoint = <&tpiu_in_port>; + filter-source = <&tpdm_mdss>; }; }; }; diff --git a/Documentation/devicetree/bindings/arm/arm,embedded-trace-extension.yaml b/Documentation/devicetree/bindings/arm/arm,embedded-trace-extension.yaml index f725e6940993..9c2c9ac9705a 100644 --- a/Documentation/devicetree/bindings/arm/arm,embedded-trace-extension.yaml +++ b/Documentation/devicetree/bindings/arm/arm,embedded-trace-extension.yaml @@ -23,7 +23,7 @@ description: | properties: $nodename: - pattern: "^ete([0-9a-f]+)$" + pattern: "^ete(-[0-9]+)?$" compatible: items: - const: arm,embedded-trace-extension @@ -55,13 +55,13 @@ examples: # An ETE node without legacy CoreSight connections - | - ete0 { + ete-0 { compatible = "arm,embedded-trace-extension"; cpu = <&cpu_0>; }; # An ETE node with legacy CoreSight connections - | - ete1 { + ete-1 { compatible = "arm,embedded-trace-extension"; cpu = <&cpu_1>; diff --git a/Documentation/devicetree/bindings/arm/aspeed/aspeed.yaml b/Documentation/devicetree/bindings/arm/aspeed/aspeed.yaml index 2f92b8ab08fa..01333ac111fb 100644 --- a/Documentation/devicetree/bindings/arm/aspeed/aspeed.yaml +++ b/Documentation/devicetree/bindings/arm/aspeed/aspeed.yaml @@ -74,6 +74,7 @@ properties: - description: AST2600 based boards items: - enum: + - ampere,mtjefferson-bmc - ampere,mtmitchell-bmc - aspeed,ast2600-evb - aspeed,ast2600-evb-a1 @@ -91,6 +92,7 @@ properties: - ibm,everest-bmc - ibm,fuji-bmc - ibm,rainier-bmc + - ibm,sbp1-bmc - ibm,system1-bmc - ibm,tacoma-bmc - inventec,starscream-bmc diff --git a/Documentation/devicetree/bindings/arm/atmel-at91.yaml b/Documentation/devicetree/bindings/arm/atmel-at91.yaml index 7160ec80ac1b..0ec29366e6c2 100644 --- a/Documentation/devicetree/bindings/arm/atmel-at91.yaml +++ b/Documentation/devicetree/bindings/arm/atmel-at91.yaml @@ -180,6 +180,13 @@ properties: - const: atmel,sama5d4 - const: atmel,sama5 + - description: Microchip SAMA7D65 Curiosity Board + items: + - const: microchip,sama7d65-curiosity + - const: microchip,sama7d65 + - const: microchip,sama7d6 + - const: microchip,sama7 + - items: - const: microchip,sama7g5ek # SAMA7G5 Evaluation Kit - const: microchip,sama7g5 diff --git a/Documentation/devicetree/bindings/arm/atmel-sysregs.txt b/Documentation/devicetree/bindings/arm/atmel-sysregs.txt index 76e2b7978250..1a173e92bb13 100644 --- a/Documentation/devicetree/bindings/arm/atmel-sysregs.txt +++ b/Documentation/devicetree/bindings/arm/atmel-sysregs.txt @@ -13,6 +13,7 @@ PIT Timer required properties: PIT64B Timer required properties: - compatible: Should be "microchip,sam9x60-pit64b" or "microchip,sam9x7-pit64b", "microchip,sam9x60-pit64b" + "microchip,sama7d65-pit64b", "microchip,sam9x60-pit64b" - reg: Should contain registers location and length - interrupts: Should contain interrupt for PIT64B timer - clocks: Should contain the available clock sources for PIT64B timer. @@ -27,12 +28,13 @@ Its subnodes can be: - watchdog: compatible should be "atmel,at91rm9200-wdt" RAMC SDRAM/DDR Controller required properties: -- compatible: Should be "atmel,at91rm9200-sdramc", "syscon" - "atmel,at91sam9260-sdramc", - "atmel,at91sam9g45-ddramc", - "atmel,sama5d3-ddramc", - "microchip,sam9x60-ddramc", - "microchip,sama7g5-uddrc", +- compatible: Should be "atmel,at91rm9200-sdramc", "syscon" or + "atmel,at91sam9260-sdramc" or + "atmel,at91sam9g45-ddramc" or + "atmel,sama5d3-ddramc" or + "microchip,sam9x60-ddramc" or + "microchip,sama7g5-uddrc" or + "microchip,sama7d65-uddrc", "microchip,sama7g5-uddrc" or "microchip,sam9x7-ddramc", "atmel,sama5d3-ddramc". - reg: Should contain registers location and length diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcmbca.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,bcmbca.yaml index 07892cbdd23c..354bb1420cdd 100644 --- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcmbca.yaml +++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcmbca.yaml @@ -34,6 +34,7 @@ properties: - enum: - netgear,r8000p - tplink,archer-c2300-v1 + - zyxel,ex3510b - const: brcm,bcm4906 - const: brcm,bcm4908 - const: brcm,bcmbca @@ -115,6 +116,7 @@ properties: items: - enum: - brcm,bcm96846 + - genexis,xg6846b - const: brcm,bcm6846 - const: brcm,bcmbca diff --git a/Documentation/devicetree/bindings/arm/blaize.yaml b/Documentation/devicetree/bindings/arm/blaize.yaml new file mode 100644 index 000000000000..af39e2756407 --- /dev/null +++ b/Documentation/devicetree/bindings/arm/blaize.yaml @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/arm/blaize.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Blaize Platforms + +maintainers: + - James Cowgill + - Matt Redfearn + - Neil Jones + - Nikolaos Pasaloukos + +description: | + Blaize Platforms using SoCs designed by Blaize Inc. + + The products based on the BLZP1600 SoC: + + - BLZP1600-SoM: SoM (System on Module) + - BLZP1600-CB2: Development board CB2 based on BLZP1600-SoM + + BLZP1600 SoC integrates a dual core ARM Cortex A53 cluster + and a Blaize Graph Streaming Processor for AI and ML workloads, + plus a suite of connectivity and other peripherals. + +properties: + $nodename: + const: '/' + compatible: + oneOf: + - description: Blaize BLZP1600 based boards + items: + - enum: + - blaize,blzp1600-cb2 + - const: blaize,blzp1600 + +additionalProperties: true + +... diff --git a/Documentation/devicetree/bindings/arm/fsl.yaml b/Documentation/devicetree/bindings/arm/fsl.yaml index 6e0dcf4307f1..0db2cbd7891f 100644 --- a/Documentation/devicetree/bindings/arm/fsl.yaml +++ b/Documentation/devicetree/bindings/arm/fsl.yaml @@ -1091,6 +1091,7 @@ properties: - dmo,imx8mp-data-modul-edm-sbc # i.MX8MP eDM SBC - emcraft,imx8mp-navqp # i.MX8MP Emcraft Systems NavQ+ Kit - fsl,imx8mp-evk # i.MX8MP EVK Board + - fsl,imx8mp-evk-revb4 # i.MX8MP EVK Rev B4 Board - gateworks,imx8mp-gw71xx-2x # i.MX8MP Gateworks Board - gateworks,imx8mp-gw72xx-2x # i.MX8MP Gateworks Board - gateworks,imx8mp-gw73xx-2x # i.MX8MP Gateworks Board @@ -1106,6 +1107,15 @@ properties: - ysoft,imx8mp-iota2-lumpy # Y Soft i.MX8MP IOTA2 Lumpy Board - const: fsl,imx8mp + - description: ABB Boards with i.MX8M Plus Modules from ADLink + items: + - enum: + - abb,imx8mp-aristanetos3-adpismarc # i.MX8MP ABB SoM on PI SMARC Board + - abb,imx8mp-aristanetos3-helios # i.MX8MP ABB SoM on helios Board + - abb,imx8mp-aristanetos3-proton2s # i.MX8MP ABB SoM on proton2s Board + - const: abb,imx8mp-aristanetos3-som # i.MX8MP ABB SoM + - const: fsl,imx8mp + - description: Avnet (MSC Branded) Boards with SM2S i.MX8M Plus Modules items: - const: avnet,sm2s-imx8mp-14N0600E-ep1 # SM2S-IMX8PLUS-14N0600E on SM2-MB-EP1 Carrier Board @@ -1262,6 +1272,7 @@ properties: items: - enum: - fsl,imx8qm-mek # i.MX8QM MEK Board + - fsl,imx8qm-mek-revd # i.MX8QM MEK Rev D Board - toradex,apalis-imx8 # Apalis iMX8 Modules - toradex,apalis-imx8-v1.1 # Apalis iMX8 V1.1 Modules - const: fsl,imx8qm @@ -1290,6 +1301,7 @@ properties: - enum: - einfochips,imx8qxp-ai_ml # i.MX8QXP AI_ML Board - fsl,imx8qxp-mek # i.MX8QXP MEK Board + - fsl,imx8qxp-mek-wcpu # i.MX8QXP MEK WCPU Board - const: fsl,imx8qxp - description: i.MX8DXL based Boards diff --git a/Documentation/devicetree/bindings/arm/mediatek.yaml b/Documentation/devicetree/bindings/arm/mediatek.yaml index 1d4bb50fcd8d..3ce34d68c213 100644 --- a/Documentation/devicetree/bindings/arm/mediatek.yaml +++ b/Documentation/devicetree/bindings/arm/mediatek.yaml @@ -239,6 +239,34 @@ properties: - enum: - mediatek,mt8183-pumpkin - const: mediatek,mt8183 + - description: Google Chinchou (Asus Chromebook CZ1104CM2A/CZ1204CM2A) + items: + - const: google,chinchou-sku0 + - const: google,chinchou-sku2 + - const: google,chinchou-sku4 + - const: google,chinchou-sku5 + - const: google,chinchou + - const: mediatek,mt8186 + - description: Google Chinchou (Asus Chromebook CZ1104FM2A/CZ1204FM2A/CZ1104CM2A/CZ1204CM2A) + items: + - const: google,chinchou-sku1 + - const: google,chinchou-sku3 + - const: google,chinchou-sku6 + - const: google,chinchou-sku7 + - const: google,chinchou-sku17 + - const: google,chinchou-sku20 + - const: google,chinchou-sku22 + - const: google,chinchou-sku23 + - const: google,chinchou + - const: mediatek,mt8186 + - description: Google Chinchou360 (Asus Chromebook CZ1104FM2A/CZ1204FM2A Flip) + items: + - const: google,chinchou-sku16 + - const: google,chinchou-sku18 + - const: google,chinchou-sku19 + - const: google,chinchou-sku21 + - const: google,chinchou + - const: mediatek,mt8186 - description: Google Magneton (Lenovo IdeaPad Slim 3 Chromebook (14M868)) items: - const: google,steelix-sku393219 @@ -263,6 +291,19 @@ properties: - const: google,steelix-sku196608 - const: google,steelix - const: mediatek,mt8186 + - description: Google Starmie (ASUS Chromebook Enterprise CM30 (CM3001)) + items: + - const: google,starmie-sku0 + - const: google,starmie-sku2 + - const: google,starmie-sku3 + - const: google,starmie + - const: mediatek,mt8186 + - description: Google Starmie (ASUS Chromebook Enterprise CM30 (CM3001)) + items: + - const: google,starmie-sku1 + - const: google,starmie-sku4 + - const: google,starmie + - const: mediatek,mt8186 - description: Google Steelix (Lenovo 300e Yoga Chromebook Gen 4) items: - enum: @@ -307,6 +348,19 @@ properties: - enum: - mediatek,mt8186-evb - const: mediatek,mt8186 + - description: Google Ciri (Lenovo Chromebook Duet (11", 9)) + items: + - enum: + - google,ciri-sku0 + - google,ciri-sku1 + - google,ciri-sku2 + - google,ciri-sku3 + - google,ciri-sku4 + - google,ciri-sku5 + - google,ciri-sku6 + - google,ciri-sku7 + - const: google,ciri + - const: mediatek,mt8188 - items: - enum: - mediatek,mt8188-evb @@ -316,12 +370,6 @@ properties: - const: google,hayato-rev1 - const: google,hayato - const: mediatek,mt8192 - - description: Google Hayato rev5 - items: - - const: google,hayato-rev5-sku2 - - const: google,hayato-sku2 - - const: google,hayato - - const: mediatek,mt8192 - description: Google Spherion (Acer Chromebook 514) items: - const: google,spherion-rev3 @@ -330,11 +378,6 @@ properties: - const: google,spherion-rev0 - const: google,spherion - const: mediatek,mt8192 - - description: Google Spherion rev4 (Acer Chromebook 514) - items: - - const: google,spherion-rev4 - - const: google,spherion - - const: mediatek,mt8192 - items: - enum: - mediatek,mt8192-evb diff --git a/Documentation/devicetree/bindings/arm/qcom-soc.yaml b/Documentation/devicetree/bindings/arm/qcom-soc.yaml index d0751a572af3..a77d68dcad4e 100644 --- a/Documentation/devicetree/bindings/arm/qcom-soc.yaml +++ b/Documentation/devicetree/bindings/arm/qcom-soc.yaml @@ -23,7 +23,7 @@ description: | select: properties: compatible: - pattern: "^qcom,.*(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1e)[0-9]+.*$" + pattern: "^qcom,.*(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sar|sc|sd[amx]|sm|x1[ep])[0-9]+.*$" required: - compatible @@ -31,7 +31,8 @@ properties: compatible: oneOf: # Preferred naming style for compatibles of SoC components: - - pattern: "^qcom,(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1e)[0-9]+(pro)?-.*$" + - pattern: "^qcom,(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1[ep])[0-9]+(pro)?-.*$" + - pattern: "^qcom,sar[0-9]+[a-z]?-.*$" - pattern: "^qcom,(sa|sc)8[0-9]+[a-z][a-z]?-.*$" # Legacy namings - variations of existing patterns/compatibles are OK, @@ -39,9 +40,9 @@ properties: - pattern: "^qcom,[ak]pss-wdt-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm)[0-9]+.*$" - pattern: "^qcom,gcc-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm)[0-9]+.*$" - pattern: "^qcom,mmcc-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm)[0-9]+.*$" - - pattern: "^qcom,pcie-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1e)[0-9]+.*$" + - pattern: "^qcom,pcie-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1[ep])[0-9]+.*$" - pattern: "^qcom,rpm-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm)[0-9]+.*$" - - pattern: "^qcom,scm-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1e)[0-9]+.*$" + - pattern: "^qcom,scm-(apq|ipq|mdm|msm|qcm|qcs|q[dr]u|sa|sc|sd[amx]|sm|x1[ep])[0-9]+.*$" - enum: - qcom,dsi-ctrl-6g-qcm2290 - qcom,gpucc-sdm630 diff --git a/Documentation/devicetree/bindings/arm/qcom.yaml b/Documentation/devicetree/bindings/arm/qcom.yaml index 9679fed7259b..618a87693ac1 100644 --- a/Documentation/devicetree/bindings/arm/qcom.yaml +++ b/Documentation/devicetree/bindings/arm/qcom.yaml @@ -19,29 +19,42 @@ description: | apq8016 apq8026 + apq8064 apq8074 apq8084 + apq8094 apq8096 ipq4018 + ipq4019 ipq5018 ipq5332 + ipq5424 ipq6018 + ipq8064 ipq8074 ipq9574 mdm9615 msm8226 + msm8660 msm8916 + msm8917 + msm8926 + msm8929 msm8939 msm8953 msm8956 msm8960 msm8974 + msm8974pro msm8976 msm8992 msm8994 msm8996 + msm8996pro msm8998 qcs404 + qcs615 + qcs8300 qcs8550 qcm2290 qcm6490 @@ -53,6 +66,7 @@ description: | sa8155p sa8540p sa8775p + sar2130p sc7180 sc7280 sc8180x @@ -84,7 +98,10 @@ description: | sm8450 sm8550 sm8650 + sm8750 + x1e78100 x1e80100 + x1p42100 There are many devices in the list below that run the standard ChromeOS bootloader setup and use the open source depthcharge bootloader to boot the @@ -250,6 +267,11 @@ properties: - yiming,uz801-v3 - const: qcom,msm8916 + - items: + - enum: + - xiaomi,riva + - const: qcom,msm8917 + - items: - enum: - motorola,potter @@ -352,6 +374,11 @@ properties: - qcom,ipq5332-ap-mi01.9 - const: qcom,ipq5332 + - items: + - enum: + - qcom,ipq5424-rdp466 + - const: qcom,ipq5424 + - items: - enum: - mikrotik,rb3011 @@ -408,6 +435,12 @@ properties: - qcom,qru1000-idp - const: qcom,qru1000 + - description: Qualcomm AR2 Gen1 platform + items: + - enum: + - qcom,qar2130p + - const: qcom,sar2130p + - items: - enum: - acer,aspire1 @@ -822,8 +855,10 @@ properties: - items: - enum: + - huawei,gaokun3 - lenovo,thinkpad-x13s - microsoft,arcata + - microsoft,blackrock - qcom,sc8280xp-crd - qcom,sc8280xp-qrd - const: qcom,sc8280xp @@ -898,6 +933,16 @@ properties: - const: qcom,qcs404-evb - const: qcom,qcs404 + - items: + - enum: + - qcom,qcs8300-ride + - const: qcom,qcs8300 + + - items: + - enum: + - qcom,qcs615-ride + - const: qcom,qcs615 + - items: - enum: - qcom,sa8155p-adp @@ -1064,6 +1109,18 @@ properties: - qcom,sm8650-qrd - const: qcom,sm8650 + - items: + - enum: + - qcom,sm8750-mtp + - qcom,sm8750-qrd + - const: qcom,sm8750 + + - items: + - enum: + - qcom,x1e001de-devkit + - const: qcom,x1e001de + - const: qcom,x1e80100 + - items: - enum: - lenovo,thinkpad-t14s @@ -1074,6 +1131,7 @@ properties: - enum: - asus,vivobook-s15 - dell,xps13-9345 + - hp,omnibook-x14 - lenovo,yoga-slim7x - microsoft,romulus13 - microsoft,romulus15 @@ -1081,6 +1139,11 @@ properties: - qcom,x1e80100-qcp - const: qcom,x1e80100 + - items: + - enum: + - qcom,x1p42100-crd + - const: qcom,x1p42100 + # Board compatibles go above qcom,msm-id: @@ -1158,6 +1221,7 @@ allOf: - qcom,apq8026 - qcom,apq8094 - qcom,apq8096 + - qcom,msm8917 - qcom,msm8939 - qcom,msm8953 - qcom,msm8956 diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml index 753199a12923..522a6f0450ea 100644 --- a/Documentation/devicetree/bindings/arm/rockchip.yaml +++ b/Documentation/devicetree/bindings/arm/rockchip.yaml @@ -81,6 +81,17 @@ properties: - const: azw,beelink-a1 - const: rockchip,rk3328 + - description: BigTreeTech CB2 Manta M4/8P + items: + - const: bigtreetech,cb2-manta + - const: bigtreetech,cb2 + - const: rockchip,rk3566 + + - description: BigTreeTech Pi 2 + items: + - const: bigtreetech,pi2 + - const: rockchip,rk3566 + - description: bq Curie 2 tablet items: - const: mundoreader,bq-curie2 @@ -167,6 +178,13 @@ properties: - const: engicam,px30-core - const: rockchip,px30 + - description: Firefly Core-3588J-based boards + items: + - enum: + - firefly,itx-3588j + - const: firefly,core-3588j + - const: rockchip,rk3588 + - description: Firefly Core-PX30-JD4 on MB-JD4-PX30 baseboard items: - const: firefly,px30-jd4-core-mb @@ -597,6 +615,11 @@ properties: - const: google,veyron - const: rockchip,rk3288 + - description: H96 Max V58 TV Box + items: + - const: haochuangyi,h96-max-v58 + - const: rockchip,rk3588 + - description: Haoyu MarsBoard RK3066 items: - const: haoyu,marsboard-rk3066 @@ -812,6 +835,12 @@ properties: - const: radxa,e20c - const: rockchip,rk3528 + - description: Radxa E52C + items: + - const: radxa,e52c + - const: rockchip,rk3582 + - const: rockchip,rk3588s + - description: Radxa Rock items: - const: radxa,rock @@ -1006,6 +1035,21 @@ properties: - const: rockchip,rk3399-sapphire-excavator - const: rockchip,rk3399 + - description: Rockchip RK3566 BOX Evaluation Demo board + items: + - const: rockchip,rk3566-box-demo + - const: rockchip,rk3566 + + - description: Rockchip RK3568 Evaluation board + items: + - const: rockchip,rk3568-evb1-v10 + - const: rockchip,rk3568 + + - description: Rockchip RK3576 Evaluation board + items: + - const: rockchip,rk3576-evb1-v10 + - const: rockchip,rk3576 + - description: Rockchip RK3588 Evaluation board items: - const: rockchip,rk3588-evb1-v10 @@ -1026,6 +1070,23 @@ properties: - const: rockchip,rk3588-toybrick-x0 - const: rockchip,rk3588 + - description: Sinovoip RK3308 Banana Pi P2 Pro + items: + - const: sinovoip,rk3308-bpi-p2pro + - const: rockchip,rk3308 + + - description: Sinovoip RK3568 Banana Pi R2 Pro + items: + - const: sinovoip,rk3568-bpi-r2pro + - const: rockchip,rk3568 + + - description: Sonoff iHost Smart Home Hub + items: + - const: itead,sonoff-ihost + - enum: + - rockchip,rv1126 + - rockchip,rv1109 + - description: Theobroma Systems PX30-uQ7 with Haikou baseboard items: - const: tsd,px30-ringneck-haikou @@ -1075,9 +1136,11 @@ properties: - const: xunlong,orangepi-3b - const: rockchip,rk3566 - - description: Xunlong Orange Pi 5 Plus + - description: Xunlong Orange Pi 5 Max/Plus items: - - const: xunlong,orangepi-5-plus + - enum: + - xunlong,orangepi-5-max + - xunlong,orangepi-5-plus - const: rockchip,rk3588 - description: Xunlong Orange Pi R1 Plus / LTS @@ -1099,33 +1162,6 @@ properties: - const: zkmagic,a95x-z2 - const: rockchip,rk3318 - - description: Rockchip RK3566 BOX Evaluation Demo board - items: - - const: rockchip,rk3566-box-demo - - const: rockchip,rk3566 - - - description: Rockchip RK3568 Evaluation board - items: - - const: rockchip,rk3568-evb1-v10 - - const: rockchip,rk3568 - - - description: Sinovoip RK3308 Banana Pi P2 Pro - items: - - const: sinovoip,rk3308-bpi-p2pro - - const: rockchip,rk3308 - - - description: Sinovoip RK3568 Banana Pi R2 Pro - items: - - const: sinovoip,rk3568-bpi-r2pro - - const: rockchip,rk3568 - - - description: Sonoff iHost Smart Home Hub - items: - - const: itead,sonoff-ihost - - enum: - - rockchip,rv1126 - - rockchip,rv1109 - additionalProperties: true ... diff --git a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml index b5ba5ffc36d6..fab29f95d8e6 100644 --- a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml +++ b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml @@ -240,6 +240,9 @@ properties: items: - enum: - samsung,c1s # Samsung Galaxy Note20 5G (SM-N981B) + - samsung,r8s # Samsung Galaxy S20 FE (SM-G780F) + - samsung,x1s # Samsung Galaxy S20 5G (SM-G981B) + - samsung,x1slte # Samsung Galaxy S20 (SM-G980F) - const: samsung,exynos990 - description: Exynos Auto v9 based boards diff --git a/Documentation/devicetree/bindings/arm/stm32/stm32.yaml b/Documentation/devicetree/bindings/arm/stm32/stm32.yaml index 703d4b574398..b6c56d4ce6b9 100644 --- a/Documentation/devicetree/bindings/arm/stm32/stm32.yaml +++ b/Documentation/devicetree/bindings/arm/stm32/stm32.yaml @@ -91,6 +91,13 @@ properties: - const: dh,stm32mp153c-dhcor-som - const: st,stm32mp153 + - description: Octavo OSD32MP153 System-in-Package based boards + items: + - enum: + - lxa,stm32mp153c-tac-gen3 # Linux Automation TAC (Generation 3) + - const: oct,stm32mp153x-osd32 + - const: st,stm32mp153 + - items: - enum: - shiratech,stm32mp157a-iot-box # IoT Box diff --git a/Documentation/devicetree/bindings/cache/qcom,llcc.yaml b/Documentation/devicetree/bindings/cache/qcom,llcc.yaml index 03b1941eaa33..e5effbb4a606 100644 --- a/Documentation/devicetree/bindings/cache/qcom,llcc.yaml +++ b/Documentation/devicetree/bindings/cache/qcom,llcc.yaml @@ -20,6 +20,7 @@ description: | properties: compatible: enum: + - qcom,ipq5424-llcc - qcom,qcs615-llcc - qcom,qcs8300-llcc - qcom,qdu1000-llcc @@ -42,11 +43,11 @@ properties: - qcom,x1e80100-llcc reg: - minItems: 2 + minItems: 1 maxItems: 10 reg-names: - minItems: 2 + minItems: 1 maxItems: 10 interrupts: @@ -66,6 +67,21 @@ required: - reg-names allOf: + - if: + properties: + compatible: + contains: + enum: + - qcom,ipq5424-llcc + then: + properties: + reg: + items: + - description: LLCC0 base register region + reg-names: + items: + - const: llcc0_base + - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/chrome/google,cros-kbd-led-backlight.yaml b/Documentation/devicetree/bindings/chrome/google,cros-kbd-led-backlight.yaml deleted file mode 100644 index c94ab8f9e0b8..000000000000 --- a/Documentation/devicetree/bindings/chrome/google,cros-kbd-led-backlight.yaml +++ /dev/null @@ -1,36 +0,0 @@ -# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/chrome/google,cros-kbd-led-backlight.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: ChromeOS keyboard backlight LED driver. - -maintainers: - - Tzung-Bi Shih - -properties: - compatible: - const: google,cros-kbd-led-backlight - -required: - - compatible - -additionalProperties: false - -examples: - - | - spi { - #address-cells = <1>; - #size-cells = <0>; - - cros_ec: ec@0 { - compatible = "google,cros-ec-spi"; - reg = <0>; - interrupts = <15 0>; - - kbd-led-backlight { - compatible = "google,cros-kbd-led-backlight"; - }; - }; - }; diff --git a/Documentation/devicetree/bindings/clock/atmel,at91rm9200-pmc.yaml b/Documentation/devicetree/bindings/clock/atmel,at91rm9200-pmc.yaml index c9eb60776b4d..885d47dd5724 100644 --- a/Documentation/devicetree/bindings/clock/atmel,at91rm9200-pmc.yaml +++ b/Documentation/devicetree/bindings/clock/atmel,at91rm9200-pmc.yaml @@ -43,6 +43,7 @@ properties: - atmel,sama5d4-pmc - microchip,sam9x60-pmc - microchip,sam9x7-pmc + - microchip,sama7d65-pmc - microchip,sama7g5-pmc - const: syscon @@ -90,6 +91,7 @@ allOf: enum: - microchip,sam9x60-pmc - microchip,sam9x7-pmc + - microchip,sama7d65-pmc - microchip,sama7g5-pmc then: properties: diff --git a/Documentation/devicetree/bindings/clock/atmel,at91sam9x5-sckc.yaml b/Documentation/devicetree/bindings/clock/atmel,at91sam9x5-sckc.yaml index c2283cd07f05..d4cf8ae2961e 100644 --- a/Documentation/devicetree/bindings/clock/atmel,at91sam9x5-sckc.yaml +++ b/Documentation/devicetree/bindings/clock/atmel,at91sam9x5-sckc.yaml @@ -20,6 +20,7 @@ properties: - items: - enum: - microchip,sam9x7-sckc + - microchip,sama7d65-sckc - microchip,sama7g5-sckc - const: microchip,sam9x60-sckc diff --git a/Documentation/devicetree/bindings/clock/qcom,ipq9574-cmn-pll.yaml b/Documentation/devicetree/bindings/clock/qcom,ipq9574-cmn-pll.yaml new file mode 100644 index 000000000000..f869b3739be8 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,ipq9574-cmn-pll.yaml @@ -0,0 +1,77 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,ipq9574-cmn-pll.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm CMN PLL Clock Controller on IPQ SoC + +maintainers: + - Bjorn Andersson + - Luo Jie + +description: + The CMN (or common) PLL clock controller expects a reference + input clock. This reference clock is from the on-board Wi-Fi. + The CMN PLL supplies a number of fixed rate output clocks to + the devices providing networking functions and to GCC. These + networking hardware include PPE (packet process engine), PCS + and the externally connected switch or PHY devices. The CMN + PLL block also outputs fixed rate clocks to GCC. The PLL's + primary function is to enable fixed rate output clocks for + networking hardware functions used with the IPQ SoC. + +properties: + compatible: + enum: + - qcom,ipq9574-cmn-pll + + reg: + maxItems: 1 + + clocks: + items: + - description: The reference clock. The supported clock rates include + 25000000, 31250000, 40000000, 48000000, 50000000 and 96000000 HZ. + - description: The AHB clock + - description: The SYS clock + description: + The reference clock is the source clock of CMN PLL, which is from the + Wi-Fi. The AHB and SYS clocks must be enabled to access CMN PLL + clock registers. + + clock-names: + items: + - const: ref + - const: ahb + - const: sys + + "#clock-cells": + const: 1 + +required: + - compatible + - reg + - clocks + - clock-names + - "#clock-cells" + +additionalProperties: false + +examples: + - | + #include + #include + + cmn_pll: clock-controller@9b000 { + compatible = "qcom,ipq9574-cmn-pll"; + reg = <0x0009b000 0x800>; + clocks = <&cmn_pll_ref_clk>, + <&gcc GCC_CMN_12GPLL_AHB_CLK>, + <&gcc GCC_CMN_12GPLL_SYS_CLK>; + clock-names = "ref", "ahb", "sys"; + #clock-cells = <1>; + assigned-clocks = <&cmn_pll CMN_PLL_CLK>; + assigned-clock-rates-u64 = /bits/ 64 <12000000000>; + }; +... diff --git a/Documentation/devicetree/bindings/clock/qcom,mmcc.yaml b/Documentation/devicetree/bindings/clock/qcom,mmcc.yaml index aa35a40648ba..59ac288ca5f1 100644 --- a/Documentation/devicetree/bindings/clock/qcom,mmcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,mmcc.yaml @@ -78,6 +78,7 @@ allOf: then: properties: clocks: + minItems: 8 items: - description: Board PXO source - description: PLL 3 clock @@ -87,8 +88,10 @@ allOf: - description: DSI phy instance 2 dsi clock - description: DSI phy instance 2 byte clock - description: HDMI phy PLL clock + - description: LVDS PLL clock clock-names: + minItems: 8 items: - const: pxo - const: pll3 @@ -98,6 +101,7 @@ allOf: - const: dsi2pll - const: dsi2pllbyte - const: hdmipll + - const: lvdspll - if: properties: diff --git a/Documentation/devicetree/bindings/clock/qcom,qcs615-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,qcs615-gcc.yaml new file mode 100644 index 000000000000..4a828e102d25 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,qcs615-gcc.yaml @@ -0,0 +1,59 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,qcs615-gcc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Global Clock & Reset Controller on QCS615 + +maintainers: + - Taniya Das + +description: | + Qualcomm global clock control module provides the clocks, resets and power + domains on QCS615. + + See also: include/dt-bindings/clock/qcom,qcs615-gcc.h + +properties: + compatible: + const: qcom,qcs615-gcc + + clocks: + items: + - description: Board XO source + - description: Board active XO source + - description: Sleep clock source + + clock-names: + items: + - const: bi_tcxo + - const: bi_tcxo_ao + - const: sleep_clk + +required: + - compatible + - clocks + - clock-names + - '#power-domain-cells' + +allOf: + - $ref: qcom,gcc.yaml# + +unevaluatedProperties: false + +examples: + - | + #include + clock-controller@100000 { + compatible = "qcom,qcs615-gcc"; + reg = <0x00100000 0x1f0000>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>; + clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk"; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; +... diff --git a/Documentation/devicetree/bindings/clock/qcom,rpmcc.yaml b/Documentation/devicetree/bindings/clock/qcom,rpmcc.yaml index 02fcffe93f1a..be3835e2e043 100644 --- a/Documentation/devicetree/bindings/clock/qcom,rpmcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,rpmcc.yaml @@ -33,6 +33,8 @@ properties: - qcom,rpmcc-msm8916 - qcom,rpmcc-msm8917 - qcom,rpmcc-msm8936 + - qcom,rpmcc-msm8937 + - qcom,rpmcc-msm8940 - qcom,rpmcc-msm8953 - qcom,rpmcc-msm8974 - qcom,rpmcc-msm8976 @@ -110,6 +112,8 @@ allOf: - qcom,rpmcc-msm8916 - qcom,rpmcc-msm8917 - qcom,rpmcc-msm8936 + - qcom,rpmcc-msm8937 + - qcom,rpmcc-msm8940 - qcom,rpmcc-msm8953 - qcom,rpmcc-msm8974 - qcom,rpmcc-msm8976 diff --git a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml index a561a306b947..dcb872b9cf3e 100644 --- a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml @@ -17,6 +17,7 @@ description: | properties: compatible: enum: + - qcom,qcs615-rpmh-clk - qcom,qdu1000-rpmh-clk - qcom,sa8775p-rpmh-clk - qcom,sar2130p-rpmh-clk @@ -37,6 +38,7 @@ properties: - qcom,sm8450-rpmh-clk - qcom,sm8550-rpmh-clk - qcom,sm8650-rpmh-clk + - qcom,sm8750-rpmh-clk - qcom,x1e80100-rpmh-clk clocks: diff --git a/Documentation/devicetree/bindings/clock/qcom,sc7280-lpasscorecc.yaml b/Documentation/devicetree/bindings/clock/qcom,sc7280-lpasscorecc.yaml index deee5423d66e..488d63959424 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sc7280-lpasscorecc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sc7280-lpasscorecc.yaml @@ -18,12 +18,6 @@ description: | include/dt-bindings/clock/qcom,lpassaudiocc-sc7280.h properties: - clocks: true - - clock-names: true - - reg: true - compatible: enum: - qcom,sc7280-lpassaoncc @@ -31,12 +25,24 @@ properties: - qcom,sc7280-lpasscorecc - qcom,sc7280-lpasshm - power-domains: - maxItems: 1 + reg: + minItems: 1 + maxItems: 2 + + clocks: + minItems: 1 + maxItems: 3 + + clock-names: + minItems: 1 + maxItems: 3 '#clock-cells': const: 1 + power-domains: + maxItems: 1 + '#power-domain-cells': const: 1 @@ -57,8 +63,6 @@ required: - '#clock-cells' - '#power-domain-cells' -additionalProperties: false - allOf: - if: properties: @@ -125,6 +129,9 @@ allOf: reg: maxItems: 1 + +additionalProperties: false + examples: - | #include diff --git a/Documentation/devicetree/bindings/clock/qcom,sdm845-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sdm845-camcc.yaml index 810b852ae371..fa95c3a1ba3a 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sdm845-camcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sdm845-camcc.yaml @@ -20,7 +20,11 @@ allOf: properties: compatible: - const: qcom,sdm845-camcc + oneOf: + - items: + - const: qcom,sdm670-camcc + - const: qcom,sdm845-camcc + - const: qcom,sdm845-camcc clocks: items: diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6115-lpasscc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6115-lpasscc.yaml new file mode 100644 index 000000000000..8cbab3fbb660 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,sm6115-lpasscc.yaml @@ -0,0 +1,46 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,sm6115-lpasscc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm LPASS Core & Audio Clock Controller on SM6115 + +maintainers: + - Konrad Dybcio + - Srinivas Kandagatla + +description: | + Qualcomm LPASS core and audio clock controllers provide audio-related resets + on SM6115 and its derivatives. + + See also:: + include/dt-bindings/clock/qcom,sm6115-lpasscc.h + +properties: + compatible: + enum: + - qcom,sm6115-lpassaudiocc + - qcom,sm6115-lpasscc + + reg: + maxItems: 1 + + '#reset-cells': + const: 1 + +required: + - compatible + - reg + - '#reset-cells' + +additionalProperties: false + +examples: + - | + lpass_audiocc: clock-controller@a6a9000 { + compatible = "qcom,sm6115-lpassaudiocc"; + reg = <0x0a6a9000 0x1000>; + #reset-cells = <1>; + }; +... diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml index 0766f66c7dc4..b88b6c9b399a 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml @@ -19,7 +19,6 @@ description: | include/dt-bindings/clock/qcom,sm8450-camcc.h include/dt-bindings/clock/qcom,sm8550-camcc.h include/dt-bindings/clock/qcom,sm8650-camcc.h - include/dt-bindings/clock/qcom,x1e80100-camcc.h properties: compatible: @@ -29,7 +28,6 @@ properties: - qcom,sm8475-camcc - qcom,sm8550-camcc - qcom,sm8650-camcc - - qcom,x1e80100-camcc clocks: items: diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml index 5c65f5ecf0f3..02968632fb3a 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml @@ -32,6 +32,7 @@ properties: - qcom,sm8550-gpucc - qcom,sm8650-gpucc - qcom,x1e80100-gpucc + - qcom,x1p42100-gpucc clocks: items: diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8550-dispcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8550-dispcc.yaml index c57d55a9293c..30e4b4631575 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm8550-dispcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm8550-dispcc.yaml @@ -12,11 +12,12 @@ maintainers: description: | Qualcomm display clock control module provides the clocks, resets and power - domains on SM8550. + domains on SM8550, SM8650, SM8750 and few other platforms. See also: - include/dt-bindings/clock/qcom,sm8550-dispcc.h - include/dt-bindings/clock/qcom,sm8650-dispcc.h + - include/dt-bindings/clock/qcom,sm8750-dispcc.h - include/dt-bindings/clock/qcom,x1e80100-dispcc.h properties: @@ -25,6 +26,7 @@ properties: - qcom,sar2130p-dispcc - qcom,sm8550-dispcc - qcom,sm8650-dispcc + - qcom,sm8750-dispcc - qcom,x1e80100-dispcc clocks: diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml index 3b546deb514a..f3afbb25e868 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml @@ -16,6 +16,7 @@ description: | See also: - include/dt-bindings/clock/qcom,sm8550-tcsr.h - include/dt-bindings/clock/qcom,sm8650-tcsr.h + - include/dt-bindings/clock/qcom,sm8750-tcsr.h properties: compatible: @@ -24,6 +25,7 @@ properties: - qcom,sar2130p-tcsr - qcom,sm8550-tcsr - qcom,sm8650-tcsr + - qcom,sm8750-tcsr - qcom,x1e80100-tcsr - const: syscon diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8750-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8750-gcc.yaml new file mode 100644 index 000000000000..aab7039fd28d --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,sm8750-gcc.yaml @@ -0,0 +1,62 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,sm8750-gcc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Global Clock & Reset Controller on SM8750 + +maintainers: + - Taniya Das + +description: | + Qualcomm global clock control module provides the clocks, resets and power + domains on SM8750 + + See also: include/dt-bindings/clock/qcom,sm8750-gcc.h + +properties: + compatible: + const: qcom,sm8750-gcc + + clocks: + items: + - description: Board XO source + - description: Board Always On XO source + - description: Sleep clock source + - description: PCIE 0 Pipe clock source + - description: UFS Phy Rx symbol 0 clock source + - description: UFS Phy Rx symbol 1 clock source + - description: UFS Phy Tx symbol 0 clock source + - description: USB3 Phy wrapper pipe clock source + +required: + - compatible + - clocks + - '#power-domain-cells' + +allOf: + - $ref: qcom,gcc.yaml# + +unevaluatedProperties: false + +examples: + - | + #include + clock-controller@100000 { + compatible = "qcom,sm8750-gcc"; + reg = <0x00100000 0x001f4200>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>, + <&pcie0_phy>, + <&ufs_mem_phy 0>, + <&ufs_mem_phy 1>, + <&ufs_mem_phy 2>, + <&usb_1_qmpphy>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + +... diff --git a/Documentation/devicetree/bindings/clock/qcom,x1e80100-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,x1e80100-camcc.yaml new file mode 100644 index 000000000000..5bbbaa15a260 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,x1e80100-camcc.yaml @@ -0,0 +1,74 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,x1e80100-camcc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Camera Clock & Reset Controller on x1e80100 + +maintainers: + - Bryan O'Donoghue + +description: | + Qualcomm camera clock control module provides the clocks, resets and power + domains on x1e80100. + + See also: + include/dt-bindings/clock/qcom,x1e80100-camcc.h + +allOf: + - $ref: qcom,gcc.yaml# + +properties: + compatible: + enum: + - qcom,x1e80100-camcc + + reg: + maxItems: 1 + + clocks: + items: + - description: Camera AHB clock from GCC + - description: Board XO source + - description: Board active XO source + - description: Sleep clock source + + power-domains: + items: + - description: A phandle to the MXC power-domain + - description: A phandle to the MMCX power-domain + + required-opps: + maxItems: 1 + description: + A phandle to an OPP node describing MMCX performance points. + +required: + - compatible + - clocks + - power-domains + - required-opps + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + clock-controller@ade0000 { + compatible = "qcom,x1e80100-camcc"; + reg = <0xade0000 0x20000>; + clocks = <&gcc GCC_CAMERA_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>; + power-domains = <&rpmhpd RPMHPD_MXC>, + <&rpmhpd RPMHPD_MMCX>; + required-opps = <&rpmhpd_opp_low_svs>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; +... diff --git a/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml index 5951a60ab081..28797d0c5d8d 100644 --- a/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml @@ -17,7 +17,11 @@ description: | properties: compatible: - const: qcom,x1e80100-gcc + oneOf: + - items: + - const: qcom,x1p42100-gcc + - const: qcom,x1e80100-gcc + - const: qcom,x1e80100-gcc clocks: items: diff --git a/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml b/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml index 42b6f80613f3..162d38035188 100644 --- a/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml +++ b/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml @@ -31,6 +31,7 @@ description: | properties: compatible: enum: + - renesas,5l35023 - renesas,5p35023 reg: diff --git a/Documentation/devicetree/bindings/clock/renesas,rzv2h-cpg.yaml b/Documentation/devicetree/bindings/clock/renesas,rzv2h-cpg.yaml index 926c503bed1f..c3fe76abd549 100644 --- a/Documentation/devicetree/bindings/clock/renesas,rzv2h-cpg.yaml +++ b/Documentation/devicetree/bindings/clock/renesas,rzv2h-cpg.yaml @@ -4,19 +4,22 @@ $id: http://devicetree.org/schemas/clock/renesas,rzv2h-cpg.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Renesas RZ/V2H(P) Clock Pulse Generator (CPG) +title: Renesas RZ/{G3E,V2H(P)} Clock Pulse Generator (CPG) maintainers: - Lad Prabhakar description: - On Renesas RZ/V2H(P) SoCs, the CPG (Clock Pulse Generator) handles generation - and control of clock signals for the IP modules, generation and control of resets, - and control over booting, low power consumption and power supply domains. + On Renesas RZ/{G3E,V2H(P)} SoCs, the CPG (Clock Pulse Generator) handles + generation and control of clock signals for the IP modules, generation and + control of resets, and control over booting, low power consumption and power + supply domains. properties: compatible: - const: renesas,r9a09g057-cpg + enum: + - renesas,r9a09g047-cpg # RZ/G3E + - renesas,r9a09g057-cpg # RZ/V2H reg: maxItems: 1 @@ -37,7 +40,7 @@ properties: description: | - For CPG core clocks, the two clock specifier cells must be "CPG_CORE" and a core clock reference, as defined in - , + , - For module clocks, the two clock specifier cells must be "CPG_MOD" and a module number. The module number is calculated as the CLKON register offset index multiplied by 16, plus the actual bit in the register diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos990-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos990-clock.yaml new file mode 100644 index 000000000000..9e7944b5f13b --- /dev/null +++ b/Documentation/devicetree/bindings/clock/samsung,exynos990-clock.yaml @@ -0,0 +1,121 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/samsung,exynos990-clock.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung Exynos990 SoC clock controller + +maintainers: + - Igor Belwon + - Chanwoo Choi + - Krzysztof Kozlowski + +description: | + Exynos990 clock controller is comprised of several CMU units, generating + clocks for different domains. Those CMU units are modeled as separate device + tree nodes, and might depend on each other. The root clock in that root tree + is an external clock: OSCCLK (26 MHz). This external clock must be defined + as a fixed-rate clock in dts. + + CMU_TOP is a top-level CMU, where all base clocks are prepared using PLLs and + dividers; all other clocks of function blocks (other CMUs) are usually + derived from CMU_TOP. + + Each clock is assigned an identifier and client nodes can use this identifier + to specify the clock which they consume. All clocks available for usage + in clock consumer nodes are defined as preprocessor macros in + 'include/dt-bindings/clock/samsung,exynos990.h' header. + +properties: + compatible: + enum: + - samsung,exynos990-cmu-hsi0 + - samsung,exynos990-cmu-top + + clocks: + minItems: 1 + maxItems: 5 + + clock-names: + minItems: 1 + maxItems: 5 + + "#clock-cells": + const: 1 + + reg: + maxItems: 1 + +required: + - compatible + - clocks + - clock-names + - "#clock-cells" + - reg + +allOf: + - if: + properties: + compatible: + contains: + const: samsung,exynos990-cmu-hsi0 + + then: + properties: + clocks: + items: + - description: External reference clock (26 MHz) + - description: CMU_HSI0 BUS clock (from CMU_TOP) + - description: CMU_HSI0 USB31DRD clock (from CMU_TOP) + - description: CMU_HSI0 USBDP_DEBUG clock (from CMU_TOP) + - description: CMU_HSI0 DPGTC clock (from CMU_TOP) + + clock-names: + items: + - const: oscclk + - const: bus + - const: usb31drd + - const: usbdp_debug + - const: dpgtc + + - if: + properties: + compatible: + contains: + const: samsung,exynos990-cmu-top + + then: + properties: + clocks: + items: + - description: External reference clock (26 MHz) + + clock-names: + items: + - const: oscclk + +additionalProperties: false + +examples: + - | + #include + + cmu_hsi0: clock-controller@10a00000 { + compatible = "samsung,exynos990-cmu-hsi0"; + reg = <0x10a00000 0x8000>; + #clock-cells = <1>; + + clocks = <&oscclk>, + <&cmu_top CLK_DOUT_CMU_HSI0_BUS>, + <&cmu_top CLK_DOUT_CMU_HSI0_USB31DRD>, + <&cmu_top CLK_DOUT_CMU_HSI0_USBDP_DEBUG>, + <&cmu_top CLK_DOUT_CMU_HSI0_DPGTC>; + clock-names = "oscclk", + "bus", + "usb31drd", + "usbdp_debug", + "dpgtc"; + }; + +... diff --git a/Documentation/devicetree/bindings/clock/st,stm32-rcc.txt b/Documentation/devicetree/bindings/clock/st,stm32-rcc.txt deleted file mode 100644 index cfa04b614d8a..000000000000 --- a/Documentation/devicetree/bindings/clock/st,stm32-rcc.txt +++ /dev/null @@ -1,138 +0,0 @@ -STMicroelectronics STM32 Reset and Clock Controller -=================================================== - -The RCC IP is both a reset and a clock controller. - -Please refer to clock-bindings.txt for common clock controller binding usage. -Please also refer to reset.txt for common reset controller binding usage. - -Required properties: -- compatible: Should be: - "st,stm32f42xx-rcc" - "st,stm32f469-rcc" - "st,stm32f746-rcc" - "st,stm32f769-rcc" - -- reg: should be register base and length as documented in the - datasheet -- #reset-cells: 1, see below -- #clock-cells: 2, device nodes should specify the clock in their "clocks" - property, containing a phandle to the clock device node, an index selecting - between gated clocks and other clocks and an index specifying the clock to - use. -- clocks: External oscillator clock phandle - - high speed external clock signal (HSE) - - external I2S clock (I2S_CKIN) - -Example: - - rcc: rcc@40023800 { - #reset-cells = <1>; - #clock-cells = <2> - compatible = "st,stm32f42xx-rcc", "st,stm32-rcc"; - reg = <0x40023800 0x400>; - clocks = <&clk_hse>, <&clk_i2s_ckin>; - }; - -Specifying gated clocks -======================= - -The primary index must be set to 0. - -The secondary index is the bit number within the RCC register bank, starting -from the first RCC clock enable register (RCC_AHB1ENR, address offset 0x30). - -It is calculated as: index = register_offset / 4 * 32 + bit_offset. -Where bit_offset is the bit offset within the register (LSB is 0, MSB is 31). - -To simplify the usage and to share bit definition with the reset and clock -drivers of the RCC IP, macros are available to generate the index in -human-readble format. - -For STM32F4 series, the macro are available here: - - include/dt-bindings/mfd/stm32f4-rcc.h - -Example: - - /* Gated clock, AHB1 bit 0 (GPIOA) */ - ... { - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOA)> - }; - - /* Gated clock, AHB2 bit 4 (CRYP) */ - ... { - clocks = <&rcc 0 STM32F4_AHB2_CLOCK(CRYP)> - }; - -Specifying other clocks -======================= - -The primary index must be set to 1. - -The secondary index is bound with the following magic numbers: - - 0 SYSTICK - 1 FCLK - 2 CLK_LSI (low-power clock source) - 3 CLK_LSE (generated from a 32.768 kHz low-speed external - crystal or ceramic resonator) - 4 CLK_HSE_RTC (HSE division factor for RTC clock) - 5 CLK_RTC (real-time clock) - 6 PLL_VCO_I2S (vco frequency of I2S pll) - 7 PLL_VCO_SAI (vco frequency of SAI pll) - 8 CLK_LCD (LCD-TFT) - 9 CLK_I2S (I2S clocks) - 10 CLK_SAI1 (audio clocks) - 11 CLK_SAI2 - 12 CLK_I2SQ_PDIV (post divisor of pll i2s q divisor) - 13 CLK_SAIQ_PDIV (post divisor of pll sai q divisor) - - 14 CLK_HSI (Internal ocscillator clock) - 15 CLK_SYSCLK (System Clock) - 16 CLK_HDMI_CEC (HDMI-CEC clock) - 17 CLK_SPDIF (SPDIF-Rx clock) - 18 CLK_USART1 (U(s)arts clocks) - 19 CLK_USART2 - 20 CLK_USART3 - 21 CLK_UART4 - 22 CLK_UART5 - 23 CLK_USART6 - 24 CLK_UART7 - 25 CLK_UART8 - 26 CLK_I2C1 (I2S clocks) - 27 CLK_I2C2 - 28 CLK_I2C3 - 29 CLK_I2C4 - 30 CLK_LPTIMER (LPTimer1 clock) - 31 CLK_PLL_SRC - 32 CLK_DFSDM1 - 33 CLK_ADFSDM1 - 34 CLK_F769_DSI -) - -Example: - - /* Misc clock, FCLK */ - ... { - clocks = <&rcc 1 STM32F4_APB1_CLOCK(TIM2)> - }; - - -Specifying softreset control of devices -======================================= - -Device nodes should specify the reset channel required in their "resets" -property, containing a phandle to the reset device node and an index specifying -which channel to use. -The index is the bit number within the RCC registers bank, starting from RCC -base address. -It is calculated as: index = register_offset / 4 * 32 + bit_offset. -Where bit_offset is the bit offset within the register. -For example, for CRC reset: - crc = AHB1RSTR_offset / 4 * 32 + CRCRST_bit_offset = 0x10 / 4 * 32 + 12 = 140 - -example: - - timer2 { - resets = <&rcc STM32F4_APB1_RESET(TIM2)>; - }; diff --git a/Documentation/devicetree/bindings/clock/st,stm32-rcc.yaml b/Documentation/devicetree/bindings/clock/st,stm32-rcc.yaml new file mode 100644 index 000000000000..f83a6120d65a --- /dev/null +++ b/Documentation/devicetree/bindings/clock/st,stm32-rcc.yaml @@ -0,0 +1,144 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/st,stm32-rcc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: STMicroelectronics STM32 Reset Clock Controller + +maintainers: + - Dario Binacchi + +description: | + The RCC IP is both a reset and a clock controller. + The reset phandle argument is the bit number within the RCC registers bank, + starting from RCC base address. + +properties: + compatible: + oneOf: + - items: + - enum: + - st,stm32f42xx-rcc + - st,stm32f746-rcc + - st,stm32h743-rcc + - const: st,stm32-rcc + - items: + - enum: + - st,stm32f469-rcc + - const: st,stm32f42xx-rcc + - const: st,stm32-rcc + - items: + - enum: + - st,stm32f769-rcc + - const: st,stm32f746-rcc + - const: st,stm32-rcc + + reg: + maxItems: 1 + + '#reset-cells': + const: 1 + + '#clock-cells': + enum: [1, 2] + + clocks: + minItems: 2 + maxItems: 3 + + st,syscfg: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Phandle to system configuration controller. It can be used to control the + power domain circuitry. + + st,ssc-modfreq-hz: + description: + The modulation frequency for main PLL (in Hz) + + st,ssc-moddepth-permyriad: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + The modulation rate for main PLL (in permyriad, i.e. 0.01%) + minimum: 25 + maximum: 200 + + st,ssc-modmethod: + $ref: /schemas/types.yaml#/definitions/string + description: + The modulation techniques for main PLL. + items: + enum: + - center-spread + - down-spread + +required: + - compatible + - reg + - '#reset-cells' + - '#clock-cells' + - clocks + - st,syscfg + +allOf: + - if: + properties: + compatible: + contains: + const: st,stm32h743-rcc + then: + properties: + '#clock-cells': + const: 1 + description: | + The clock index for the specified type. + clocks: + items: + - description: high speed external (HSE) clock input + - description: low speed external (LSE) clock input + - description: Inter-IC sound (I2S) clock input + st,ssc-modfreq-hz: false + st,ssc-moddepth-permyriad: false + st,ssc-modmethod: false + + else: + properties: + '#clock-cells': + const: 2 + description: | + - The first cell is the clock type, possible values are 0 for + gated clocks and 1 otherwise. + - The second cell is the clock index for the specified type. + clocks: + items: + - description: high speed external (HSE) clock input + - description: Inter-IC sound (I2S) clock input + +additionalProperties: false + +examples: + # Reset and Clock Control Module node: + - | + clock-controller@40023800 { + compatible = "st,stm32f42xx-rcc", "st,stm32-rcc"; + reg = <0x40023800 0x400>; + #clock-cells = <2>; + #reset-cells = <1>; + clocks = <&clk_hse>, <&clk_i2s_ckin>; + st,syscfg = <&pwrcfg>; + st,ssc-modfreq-hz = <10000>; + st,ssc-moddepth-permyriad = <200>; + st,ssc-modmethod = "center-spread"; + }; + - | + clock-controller@58024400 { + compatible = "st,stm32h743-rcc", "st,stm32-rcc"; + reg = <0x58024400 0x400>; + #clock-cells = <1>; + #reset-cells = <1>; + clocks = <&clk_hse>, <&clk_lse>, <&clk_i2s>; + st,syscfg = <&pwrcfg>; + }; + +... diff --git a/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml b/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml index 9b3aaae546cb..e72f46e79b90 100644 --- a/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml +++ b/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml @@ -21,7 +21,7 @@ description: | ================= All available clocks are defined as preprocessor macros in - dt-bindings/clock/stm32mp1-clks.h header and can be used in device + include/dt-bindings/clock/stm32mp1-clks.h header and can be used in device tree sources. Specifying softreset control of devices @@ -40,8 +40,8 @@ description: | = 0x180 / 4 * 32 + 0 = 3072 The list of valid indices for STM32MP1 is available in: - include/dt-bindings/reset-controller/stm32mp1-resets.h - include/dt-bindings/reset-controller/stm32mp13-resets.h + include/dt-bindings/reset/stm32mp1-resets.h + include/dt-bindings/reset/stm32mp13-resets.h This file implements defines like: #define LTDC_R 3072 diff --git a/Documentation/devicetree/bindings/clock/ti/composite.txt b/Documentation/devicetree/bindings/clock/ti/composite.txt deleted file mode 100644 index 238e6f7d74f8..000000000000 --- a/Documentation/devicetree/bindings/clock/ti/composite.txt +++ /dev/null @@ -1,55 +0,0 @@ -Binding for TI composite clock. - -This binding uses the common clock binding[1]. It assumes a -register-mapped composite clock with multiple different sub-types; - -a multiplexer clock with multiple input clock signals or parents, one -of which can be selected as output, this behaves exactly as [2] - -an adjustable clock rate divider, this behaves exactly as [3] - -a gating function which can be used to enable and disable the output -clock, this behaves exactly as [4] - -The binding must provide a list of the component clocks that shall be -merged to this clock. The component clocks shall be of one of the -"ti,*composite*-clock" types. - -[1] Documentation/devicetree/bindings/clock/clock-bindings.txt -[2] Documentation/devicetree/bindings/clock/ti/ti,mux-clock.yaml -[3] Documentation/devicetree/bindings/clock/ti/ti,divider-clock.yaml -[4] Documentation/devicetree/bindings/clock/ti/gate.txt - -Required properties: -- compatible : shall be: "ti,composite-clock" -- clocks : link phandles of component clocks -- #clock-cells : from common clock binding; shall be set to 0. - -Optional properties: -- clock-output-names : from common clock binding. - -Examples: - -usb_l4_gate_ick: usb_l4_gate_ick { - #clock-cells = <0>; - compatible = "ti,composite-interface-clock"; - clocks = <&l4_ick>; - ti,bit-shift = <5>; - reg = <0x0a10>; -}; - -usb_l4_div_ick: usb_l4_div_ick { - #clock-cells = <0>; - compatible = "ti,composite-divider-clock"; - clocks = <&l4_ick>; - ti,bit-shift = <4>; - ti,max-div = <1>; - reg = <0x0a40>; - ti,index-starts-at-one; -}; - -usb_l4_ick: usb_l4_ick { - #clock-cells = <0>; - compatible = "ti,composite-clock"; - clocks = <&usb_l4_gate_ick>, <&usb_l4_div_ick>; -}; diff --git a/Documentation/devicetree/bindings/clock/ti/gate.txt b/Documentation/devicetree/bindings/clock/ti/gate.txt deleted file mode 100644 index a8e0335b006a..000000000000 --- a/Documentation/devicetree/bindings/clock/ti/gate.txt +++ /dev/null @@ -1,105 +0,0 @@ -Binding for Texas Instruments gate clock. - -This binding uses the common clock binding[1]. This clock is -quite much similar to the basic gate-clock [2], however, -it supports a number of additional features. If no register -is provided for this clock, the code assumes that a clockdomain -will be controlled instead and the corresponding hw-ops for -that is used. - -[1] Documentation/devicetree/bindings/clock/clock-bindings.txt -[2] Documentation/devicetree/bindings/clock/gpio-gate-clock.yaml -[3] Documentation/devicetree/bindings/clock/ti/clockdomain.txt - -Required properties: -- compatible : shall be one of: - "ti,gate-clock" - basic gate clock - "ti,wait-gate-clock" - gate clock which waits until clock is active before - returning from clk_enable() - "ti,dss-gate-clock" - gate clock with DSS specific hardware handling - "ti,am35xx-gate-clock" - gate clock with AM35xx specific hardware handling - "ti,clkdm-gate-clock" - clockdomain gate clock, which derives its functional - clock directly from a clockdomain, see [3] how - to map clockdomains properly - "ti,hsdiv-gate-clock" - gate clock with OMAP36xx specific hardware handling, - required for a hardware errata - "ti,composite-gate-clock" - composite gate clock, to be part of composite - clock - "ti,composite-no-wait-gate-clock" - composite gate clock that does not wait - for clock to be active before returning - from clk_enable() -- #clock-cells : from common clock binding; shall be set to 0 -- clocks : link to phandle of parent clock -- reg : offset for register controlling adjustable gate, not needed for - ti,clkdm-gate-clock type - -Optional properties: -- clock-output-names : from common clock binding. -- ti,bit-shift : bit shift for programming the clock gate, invalid for - ti,clkdm-gate-clock type -- ti,set-bit-to-disable : inverts default gate programming. Setting the bit - gates the clock and clearing the bit ungates the clock. - -Examples: - mmchs2_fck: mmchs2_fck@48004a00 { - #clock-cells = <0>; - compatible = "ti,gate-clock"; - clocks = <&core_96m_fck>; - reg = <0x0a00>; - ti,bit-shift = <25>; - }; - - uart4_fck_am35xx: uart4_fck_am35xx { - #clock-cells = <0>; - compatible = "ti,wait-gate-clock"; - clocks = <&core_48m_fck>; - reg = <0x0a00>; - ti,bit-shift = <23>; - }; - - dss1_alwon_fck_3430es2: dss1_alwon_fck_3430es2@48004e00 { - #clock-cells = <0>; - compatible = "ti,dss-gate-clock"; - clocks = <&dpll4_m4x2_ck>; - reg = <0x0e00>; - ti,bit-shift = <0>; - }; - - emac_ick: emac_ick@4800259c { - #clock-cells = <0>; - compatible = "ti,am35xx-gate-clock"; - clocks = <&ipss_ick>; - reg = <0x059c>; - ti,bit-shift = <1>; - }; - - emu_src_ck: emu_src_ck { - #clock-cells = <0>; - compatible = "ti,clkdm-gate-clock"; - clocks = <&emu_src_mux_ck>; - }; - - dpll4_m2x2_ck: dpll4_m2x2_ck@48004d00 { - #clock-cells = <0>; - compatible = "ti,hsdiv-gate-clock"; - clocks = <&dpll4_m2x2_mul_ck>; - ti,bit-shift = <0x1b>; - reg = <0x0d00>; - ti,set-bit-to-disable; - }; - - vlynq_gate_fck: vlynq_gate_fck { - #clock-cells = <0>; - compatible = "ti,composite-gate-clock"; - clocks = <&core_ck>; - ti,bit-shift = <3>; - reg = <0x0200>; - }; - - sys_clkout2_src_gate: sys_clkout2_src_gate { - #clock-cells = <0>; - compatible = "ti,composite-no-wait-gate-clock"; - clocks = <&core_ck>; - ti,bit-shift = <15>; - reg = <0x0070>; - }; diff --git a/Documentation/devicetree/bindings/clock/ti/ti,composite-clock.yaml b/Documentation/devicetree/bindings/clock/ti/ti,composite-clock.yaml new file mode 100644 index 000000000000..31a6794852c7 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/ti/ti,composite-clock.yaml @@ -0,0 +1,82 @@ +# SPDX-License-Identifier: GPL-2.0-only +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/ti/ti,composite-clock.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments composite clock + +maintainers: + - Tero Kristo + +description: | + *Deprecated design pattern: one node per clock* + + This binding assumes a register-mapped composite clock with multiple + different sub-types: + + a multiplexer clock with multiple input clock signals or parents, one + of which can be selected as output, this behaves exactly as [1]. + + an adjustable clock rate divider, this behaves exactly as [2]. + + a gating function which can be used to enable and disable the output + clock, this behaves exactly as [3]. + + The binding must provide a list of the component clocks that shall be + merged to this clock. The component clocks shall be of one of the + "ti,*composite*-clock" types. + + [1] Documentation/devicetree/bindings/clock/ti/ti,mux-clock.yaml + [2] Documentation/devicetree/bindings/clock/ti/ti,divider-clock.yaml + [3] Documentation/devicetree/bindings/clock/ti/ti,gate-clock.yaml + +properties: + compatible: + const: ti,composite-clock + + "#clock-cells": + const: 0 + + clocks: true + + clock-output-names: + maxItems: 1 + +required: + - compatible + - "#clock-cells" + - clocks + +additionalProperties: false + +examples: + - | + bus { + #address-cells = <1>; + #size-cells = <0>; + + usb_l4_gate_ick: clock-controller@a10 { + #clock-cells = <0>; + compatible = "ti,composite-gate-clock"; + clocks = <&l4_ick>; + ti,bit-shift = <5>; + reg = <0x0a10>; + }; + + usb_l4_div_ick: clock-controller@a40 { + #clock-cells = <0>; + compatible = "ti,composite-divider-clock"; + clocks = <&l4_ick>; + ti,bit-shift = <4>; + ti,max-div = <1>; + reg = <0x0a40>; + ti,index-starts-at-one; + }; + }; + + clock-controller { + #clock-cells = <0>; + compatible = "ti,composite-clock"; + clocks = <&usb_l4_gate_ick>, <&usb_l4_div_ick>; + }; diff --git a/Documentation/devicetree/bindings/clock/ti/ti,gate-clock.yaml b/Documentation/devicetree/bindings/clock/ti/ti,gate-clock.yaml new file mode 100644 index 000000000000..eaa727ab0d7f --- /dev/null +++ b/Documentation/devicetree/bindings/clock/ti/ti,gate-clock.yaml @@ -0,0 +1,125 @@ +# SPDX-License-Identifier: GPL-2.0-only +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/ti/ti,gate-clock.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments gate clock + +maintainers: + - Tero Kristo + +description: | + *Deprecated design pattern: one node per clock* + + This clock is quite much similar to the basic gate-clock [1], however, + it supports a number of additional features. If no register + is provided for this clock, the code assumes that a clockdomain + will be controlled instead and the corresponding hw-ops for + that is used. + + [1] Documentation/devicetree/bindings/clock/gpio-gate-clock.yaml + [2] Documentation/devicetree/bindings/clock/ti/clockdomain.txt + +properties: + compatible: + enum: + - ti,gate-clock # basic gate clock + - ti,wait-gate-clock # gate clock which waits until clock is + # active before returning from clk_enable() + - ti,dss-gate-clock # gate clock with DSS specific hardware + # handling + - ti,am35xx-gate-clock # gate clock with AM35xx specific hardware + # handling + - ti,clkdm-gate-clock # clockdomain gate clock, which derives its + # functional clock directly from a + # clockdomain, see [2] how to map + # clockdomains properly + - ti,hsdiv-gate-clock # gate clock with OMAP36xx specific hardware + # handling, required for a hardware errata + - ti,composite-gate-clock # composite gate clock, to be part of + # composite clock + - ti,composite-no-wait-gate-clock # composite gate clock that does not + # wait for clock to be active before + # returning from clk_enable() + "#clock-cells": + const: 0 + + clocks: true + + clock-output-names: + maxItems: 1 + + reg: + maxItems: 1 + + ti,bit-shift: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Number of bits to shift the bit-mask + maximum: 31 + default: 0 + + ti,set-bit-to-disable: + type: boolean + description: + Inverts default gate programming. Setting the bit + gates the clock and clearing the bit ungates the clock. + + ti,set-rate-parent: + type: boolean + description: + clk_set_rate is propagated to parent clock, + +if: + properties: + compatible: + contains: + const: ti,clkdm-gate-clock +then: + properties: + reg: false + required: + - compatible + - "#clock-cells" + - clocks +else: + required: + - compatible + - "#clock-cells" + - clocks + - reg + +additionalProperties: false + +examples: + - | + bus { + #address-cells = <1>; + #size-cells = <0>; + + clock-controller@a00 { + #clock-cells = <0>; + compatible = "ti,gate-clock"; + clocks = <&core_96m_fck>; + reg = <0x0a00>; + ti,bit-shift = <25>; + }; + + clock-controller@d00 { + compatible = "ti,hsdiv-gate-clock"; + reg = <0x0d00>; + #clock-cells = <0>; + clocks = <&dpll4_m2x2_mul_ck>; + ti,bit-shift = <0x1b>; + ti,set-bit-to-disable; + }; + }; + + - | + clock-controller { + #clock-cells = <0>; + compatible = "ti,clkdm-gate-clock"; + clocks = <&emu_src_mux_ck>; + }; + diff --git a/Documentation/devicetree/bindings/clock/xlnx,vcu.yaml b/Documentation/devicetree/bindings/clock/xlnx,vcu.yaml new file mode 100644 index 000000000000..19dc923e2ee9 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/xlnx,vcu.yaml @@ -0,0 +1,59 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/xlnx,vcu.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# +title: LogicoreIP designed compatible with Xilinx ZYNQ family. + +maintainers: + - Rohit Visavalia + +description: + LogicoreIP design to provide the isolation between processing system + and programmable logic. Also provides the list of register set to configure + the frequency. + +properties: + compatible: + items: + - enum: + - xlnx,vcu + - xlnx,vcu-logicoreip-1.0 + + reg: + maxItems: 1 + + clocks: + items: + - description: pll ref clocksource + - description: aclk + + clock-names: + items: + - const: pll_ref + - const: aclk + + reset-gpios: + maxItems: 1 + +required: + - reg + - clocks + - clock-names + +additionalProperties: false + +examples: + - | + #include + fpga { + #address-cells = <2>; + #size-cells = <2>; + xlnx_vcu: vcu@a0040000 { + compatible = "xlnx,vcu-logicoreip-1.0"; + reg = <0x0 0xa0040000 0x0 0x1000>; + reset-gpios = <&gpio 78 GPIO_ACTIVE_HIGH>; + clocks = <&si570_1>, <&clkc 71>; + clock-names = "pll_ref", "aclk"; + }; + }; diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml index 67700440e23b..11e40d225b9f 100644 --- a/Documentation/devicetree/bindings/connector/usb-connector.yaml +++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml @@ -293,6 +293,13 @@ properties: PD negotiation till BC1.2 detection completes. default: 0 + pd-revision: + description: Specifies the maximum USB PD revision and version supported by + the connector. This property is specified in the following order; + . + $ref: /schemas/types.yaml#/definitions/uint8-array + maxItems: 4 + dependencies: sink-vdos-v1: [ sink-vdos ] sink-vdos: [ sink-vdos-v1 ] diff --git a/Documentation/devicetree/bindings/cpufreq/airoha,en7581-cpufreq.yaml b/Documentation/devicetree/bindings/cpufreq/airoha,en7581-cpufreq.yaml new file mode 100644 index 000000000000..7d4510b3219c --- /dev/null +++ b/Documentation/devicetree/bindings/cpufreq/airoha,en7581-cpufreq.yaml @@ -0,0 +1,55 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/cpufreq/airoha,en7581-cpufreq.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Airoha EN7581 CPUFreq + +maintainers: + - Christian Marangi + +description: | + On newer Airoha SoC, CPU Frequency is scaled indirectly with SMC commands + to ATF. + + A virtual clock is exposed. This virtual clock is a get-only clock and + is used to expose the current global CPU clock. The frequency info comes + by the output of the SMC command that reports the clock in MHz. + + The SMC sets the CPU clock by providing an index, this is modelled as + performance states in a power domain. + + CPUs can't be individually scaled as the CPU frequency is shared across + all CPUs and is global. + +properties: + compatible: + const: airoha,en7581-cpufreq + + '#clock-cells': + const: 0 + + '#power-domain-cells': + const: 0 + + operating-points-v2: true + +required: + - compatible + - '#clock-cells' + - '#power-domain-cells' + - operating-points-v2 + +additionalProperties: false + +examples: + - | + performance-domain { + compatible = "airoha,en7581-cpufreq"; + + operating-points-v2 = <&cpu_smcc_opp_table>; + + #power-domain-cells = <0>; + #clock-cells = <0>; + }; diff --git a/Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml b/Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml index 76cb9726660e..896276b8c6bb 100644 --- a/Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml +++ b/Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml @@ -24,9 +24,17 @@ properties: - apple,t8112-cluster-cpufreq - const: apple,cluster-cpufreq - items: - - const: apple,t6000-cluster-cpufreq + - enum: + - apple,s8000-cluster-cpufreq + - apple,t8010-cluster-cpufreq + - apple,t8015-cluster-cpufreq + - apple,t6000-cluster-cpufreq - const: apple,t8103-cluster-cpufreq - const: apple,cluster-cpufreq + - items: + - const: apple,t7000-cluster-cpufreq + - const: apple,s5l8960x-cluster-cpufreq + - const: apple,s5l8960x-cluster-cpufreq reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/crypto/fsl,sec-v4.0.yaml b/Documentation/devicetree/bindings/crypto/fsl,sec-v4.0.yaml index 9c8c9991f29a..f0c4a7c83568 100644 --- a/Documentation/devicetree/bindings/crypto/fsl,sec-v4.0.yaml +++ b/Documentation/devicetree/bindings/crypto/fsl,sec-v4.0.yaml @@ -114,8 +114,9 @@ patternProperties: table that specifies the PPID to LIODN mapping. Needed if the PAMU is used. Value is a 12 bit value where value is a LIODN ID for this JR. This property is normally set by boot firmware. - $ref: /schemas/types.yaml#/definitions/uint32 - maximum: 0xfff + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - maximum: 0xfff '^rtic@[0-9a-f]+$': type: object @@ -186,8 +187,9 @@ patternProperties: Needed if the PAMU is used. Value is a 12 bit value where value is a LIODN ID for this JR. This property is normally set by boot firmware. - $ref: /schemas/types.yaml#/definitions/uint32 - maximum: 0xfff + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - maximum: 0xfff fsl,rtic-region: description: diff --git a/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml b/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml index 0304f074cf08..08fe6a707a37 100644 --- a/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml +++ b/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml @@ -13,12 +13,14 @@ properties: compatible: items: - enum: + - qcom,qcs8300-inline-crypto-engine - qcom,sa8775p-inline-crypto-engine - qcom,sc7180-inline-crypto-engine - qcom,sc7280-inline-crypto-engine - qcom,sm8450-inline-crypto-engine - qcom,sm8550-inline-crypto-engine - qcom,sm8650-inline-crypto-engine + - qcom,sm8750-inline-crypto-engine - const: qcom,inline-crypto-engine reg: diff --git a/Documentation/devicetree/bindings/crypto/qcom,prng.yaml b/Documentation/devicetree/bindings/crypto/qcom,prng.yaml index 048b769a73c0..5e6f8b642545 100644 --- a/Documentation/devicetree/bindings/crypto/qcom,prng.yaml +++ b/Documentation/devicetree/bindings/crypto/qcom,prng.yaml @@ -17,12 +17,17 @@ properties: - qcom,prng-ee # 8996 and later using EE - items: - enum: + - qcom,ipq5332-trng + - qcom,ipq5424-trng + - qcom,ipq9574-trng + - qcom,qcs8300-trng - qcom,sa8255p-trng - qcom,sa8775p-trng - qcom,sc7280-trng - qcom,sm8450-trng - qcom,sm8550-trng - qcom,sm8650-trng + - qcom,sm8750-trng - const: qcom,trng reg: diff --git a/Documentation/devicetree/bindings/crypto/qcom-qce.yaml b/Documentation/devicetree/bindings/crypto/qcom-qce.yaml index c09be97434ac..3ed56d9d378e 100644 --- a/Documentation/devicetree/bindings/crypto/qcom-qce.yaml +++ b/Documentation/devicetree/bindings/crypto/qcom-qce.yaml @@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm crypto engine driver maintainers: - - Bhupesh Sharma + - Bjorn Andersson + - Konrad Dybcio description: This document defines the binding for the QCE crypto @@ -44,6 +45,7 @@ properties: - items: - enum: + - qcom,qcs8300-qce - qcom,sa8775p-qce - qcom,sc7280-qce - qcom,sm6350-qce @@ -52,6 +54,7 @@ properties: - qcom,sm8450-qce - qcom,sm8550-qce - qcom,sm8650-qce + - qcom,sm8750-qce - const: qcom,sm8150-qce - const: qcom,qce diff --git a/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.yaml b/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.yaml index 84d68b8cfccc..416fe263ac92 100644 --- a/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.yaml +++ b/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.yaml @@ -148,10 +148,10 @@ examples: /* TMDS Output */ hdmi_tx_tmds_port: port@1 { - reg = <1>; + reg = <1>; - hdmi_tx_tmds_out: endpoint { - remote-endpoint = <&hdmi_connector_in>; - }; + hdmi_tx_tmds_out: endpoint { + remote-endpoint = <&hdmi_connector_in>; + }; }; }; diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml index df20a3c9c744..ec89115c74e4 100644 --- a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml +++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml @@ -90,7 +90,7 @@ properties: adi,dsi-lanes: description: Number of DSI data lanes connected to the DSI host. $ref: /schemas/types.yaml#/definitions/uint32 - enum: [ 1, 2, 3, 4 ] + enum: [ 2, 3, 4 ] "#sound-dai-cells": const: 0 diff --git a/Documentation/devicetree/bindings/display/bridge/fsl,imx8mp-hdmi-tx.yaml b/Documentation/devicetree/bindings/display/bridge/fsl,imx8mp-hdmi-tx.yaml index 3791c9f4ebab..05442d437755 100644 --- a/Documentation/devicetree/bindings/display/bridge/fsl,imx8mp-hdmi-tx.yaml +++ b/Documentation/devicetree/bindings/display/bridge/fsl,imx8mp-hdmi-tx.yaml @@ -82,21 +82,21 @@ examples: power-domains = <&hdmi_blk_ctrl IMX8MP_HDMIBLK_PD_HDMI_TX>; reg-io-width = <1>; ports { - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; - hdmi_tx_from_pvi: endpoint { - remote-endpoint = <&pvi_to_hdmi_tx>; - }; - }; + endpoint { + remote-endpoint = <&pvi_to_hdmi_tx>; + }; + }; - port@1 { - reg = <1>; - hdmi_tx_out: endpoint { - remote-endpoint = <&hdmi0_con>; - }; - }; + port@1 { + reg = <1>; + endpoint { + remote-endpoint = <&hdmi0_con>; + }; + }; }; }; diff --git a/Documentation/devicetree/bindings/display/bridge/samsung,mipi-dsim.yaml b/Documentation/devicetree/bindings/display/bridge/samsung,mipi-dsim.yaml index 4ed7a799ba26..1acad99f3965 100644 --- a/Documentation/devicetree/bindings/display/bridge/samsung,mipi-dsim.yaml +++ b/Documentation/devicetree/bindings/display/bridge/samsung,mipi-dsim.yaml @@ -27,7 +27,9 @@ properties: - fsl,imx8mm-mipi-dsim - fsl,imx8mp-mipi-dsim - items: - - const: fsl,imx8mn-mipi-dsim + - enum: + - fsl,imx7d-mipi-dsim + - fsl,imx8mn-mipi-dsim - const: fsl,imx8mm-mipi-dsim reg: @@ -241,40 +243,40 @@ examples: #include dsi@13900000 { - compatible = "samsung,exynos5433-mipi-dsi"; - reg = <0x13900000 0xC0>; - interrupts = ; - phys = <&mipi_phy 1>; - phy-names = "dsim"; - clocks = <&cmu_disp CLK_PCLK_DSIM0>, - <&cmu_disp CLK_PHYCLK_MIPIDPHY0_BITCLKDIV8>, - <&cmu_disp CLK_PHYCLK_MIPIDPHY0_RXCLKESC0>, - <&cmu_disp CLK_SCLK_RGB_VCLK_TO_DSIM0>, - <&cmu_disp CLK_SCLK_DSIM0>; - clock-names = "bus_clk", - "phyclk_mipidphy0_bitclkdiv8", - "phyclk_mipidphy0_rxclkesc0", - "sclk_rgb_vclk_to_dsim0", - "sclk_mipi"; - power-domains = <&pd_disp>; - vddcore-supply = <&ldo6_reg>; - vddio-supply = <&ldo7_reg>; - samsung,burst-clock-frequency = <512000000>; - samsung,esc-clock-frequency = <16000000>; - samsung,pll-clock-frequency = <24000000>; - pinctrl-names = "default"; - pinctrl-0 = <&te_irq>; + compatible = "samsung,exynos5433-mipi-dsi"; + reg = <0x13900000 0xC0>; + interrupts = ; + phys = <&mipi_phy 1>; + phy-names = "dsim"; + clocks = <&cmu_disp CLK_PCLK_DSIM0>, + <&cmu_disp CLK_PHYCLK_MIPIDPHY0_BITCLKDIV8>, + <&cmu_disp CLK_PHYCLK_MIPIDPHY0_RXCLKESC0>, + <&cmu_disp CLK_SCLK_RGB_VCLK_TO_DSIM0>, + <&cmu_disp CLK_SCLK_DSIM0>; + clock-names = "bus_clk", + "phyclk_mipidphy0_bitclkdiv8", + "phyclk_mipidphy0_rxclkesc0", + "sclk_rgb_vclk_to_dsim0", + "sclk_mipi"; + power-domains = <&pd_disp>; + vddcore-supply = <&ldo6_reg>; + vddio-supply = <&ldo7_reg>; + samsung,burst-clock-frequency = <512000000>; + samsung,esc-clock-frequency = <16000000>; + samsung,pll-clock-frequency = <24000000>; + pinctrl-names = "default"; + pinctrl-0 = <&te_irq>; - ports { - #address-cells = <1>; - #size-cells = <0>; + ports { + #address-cells = <1>; + #size-cells = <0>; - port@0 { - reg = <0>; + port@0 { + reg = <0>; - dsi_to_mic: endpoint { - remote-endpoint = <&mic_to_dsi>; - }; - }; - }; + dsi_to_mic: endpoint { + remote-endpoint = <&mic_to_dsi>; + }; + }; + }; }; diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,aal.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,aal.yaml index 47ddba5c41af..5d2089dc596e 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,aal.yaml +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,aal.yaml @@ -104,30 +104,30 @@ examples: #size-cells = <2>; aal@14015000 { - compatible = "mediatek,mt8173-disp-aal"; - reg = <0 0x14015000 0 0x1000>; - interrupts = ; - power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>; - clocks = <&mmsys CLK_MM_DISP_AAL>; - mediatek,gce-client-reg = <&gce SUBSYS_1401XXXX 0x5000 0x1000>; + compatible = "mediatek,mt8173-disp-aal"; + reg = <0 0x14015000 0 0x1000>; + interrupts = ; + power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>; + clocks = <&mmsys CLK_MM_DISP_AAL>; + mediatek,gce-client-reg = <&gce SUBSYS_1401XXXX 0x5000 0x1000>; - ports { - #address-cells = <1>; - #size-cells = <0>; + ports { + #address-cells = <1>; + #size-cells = <0>; - port@0 { - reg = <0>; - aal0_in: endpoint { - remote-endpoint = <&ccorr0_out>; - }; - }; + port@0 { + reg = <0>; + endpoint { + remote-endpoint = <&ccorr0_out>; + }; + }; - port@1 { - reg = <1>; - aal0_out: endpoint { - remote-endpoint = <&gamma0_in>; - }; - }; - }; - }; + port@1 { + reg = <1>; + endpoint { + remote-endpoint = <&gamma0_in>; + }; + }; + }; + }; }; diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml index 2aef1eb32e11..75ce92f4a5fd 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml @@ -42,6 +42,9 @@ properties: interrupts: maxItems: 1 + '#sound-dai-cells': + const: 0 + ports: $ref: /schemas/graph.yaml#/properties/ports properties: @@ -85,7 +88,21 @@ required: - ports - max-linkrate-mhz -additionalProperties: false +allOf: + - $ref: /schemas/sound/dai-common.yaml# + - if: + not: + properties: + compatible: + contains: + enum: + - mediatek,mt8188-dp-tx + - mediatek,mt8195-dp-tx + then: + properties: + '#sound-dai-cells': false + +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,ovl.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,ovl.yaml index 9ea796a033b2..4f110635afb6 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,ovl.yaml +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,ovl.yaml @@ -26,6 +26,7 @@ properties: - mediatek,mt8173-disp-ovl - mediatek,mt8183-disp-ovl - mediatek,mt8192-disp-ovl + - mediatek,mt8195-disp-ovl - mediatek,mt8195-mdp3-ovl - items: - enum: @@ -36,16 +37,17 @@ properties: - enum: - mediatek,mt6795-disp-ovl - const: mediatek,mt8173-disp-ovl - - items: - - enum: - - mediatek,mt8188-disp-ovl - - mediatek,mt8195-disp-ovl - - const: mediatek,mt8183-disp-ovl - items: - enum: - mediatek,mt8186-disp-ovl - mediatek,mt8365-disp-ovl - const: mediatek,mt8192-disp-ovl + - items: + - const: mediatek,mt8188-disp-ovl + - const: mediatek,mt8195-disp-ovl + - items: + - const: mediatek,mt8188-mdp3-ovl + - const: mediatek,mt8195-mdp3-ovl reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml index a212f335d5ff..e00b88332f2f 100644 --- a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml +++ b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml @@ -8,6 +8,7 @@ title: MSM Display Port Controller maintainers: - Kuogee Hsieh + - Abhinav Kumar description: | Device tree bindings for DisplayPort host controller for MSM targets diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml index b0fd96b76ed1..ffbd1dc9470e 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml @@ -30,6 +30,7 @@ properties: - qcom,sdm845-dsi-ctrl - qcom,sm6115-dsi-ctrl - qcom,sm6125-dsi-ctrl + - qcom,sm6150-dsi-ctrl - qcom,sm6350-dsi-ctrl - qcom,sm6375-dsi-ctrl - qcom,sm7150-dsi-ctrl @@ -349,6 +350,7 @@ allOf: enum: - qcom,sc7180-dsi-ctrl - qcom,sc7280-dsi-ctrl + - qcom,sm6150-dsi-ctrl - qcom,sm7150-dsi-ctrl - qcom,sm8150-dsi-ctrl - qcom,sm8250-dsi-ctrl @@ -416,63 +418,63 @@ unevaluatedProperties: false examples: - | - #include - #include - #include - #include + #include + #include + #include + #include - dsi@ae94000 { - compatible = "qcom,sc7180-dsi-ctrl", "qcom,mdss-dsi-ctrl"; - reg = <0x0ae94000 0x400>; - reg-names = "dsi_ctrl"; + dsi@ae94000 { + compatible = "qcom,sc7180-dsi-ctrl", "qcom,mdss-dsi-ctrl"; + reg = <0x0ae94000 0x400>; + reg-names = "dsi_ctrl"; - #address-cells = <1>; - #size-cells = <0>; + #address-cells = <1>; + #size-cells = <0>; - interrupt-parent = <&mdss>; - interrupts = <4>; + interrupt-parent = <&mdss>; + interrupts = <4>; - clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK>, - <&dispcc DISP_CC_MDSS_BYTE0_INTF_CLK>, - <&dispcc DISP_CC_MDSS_PCLK0_CLK>, - <&dispcc DISP_CC_MDSS_ESC0_CLK>, - <&dispcc DISP_CC_MDSS_AHB_CLK>, - <&dispcc DISP_CC_MDSS_AXI_CLK>; - clock-names = "byte", - "byte_intf", - "pixel", - "core", - "iface", - "bus"; + clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK>, + <&dispcc DISP_CC_MDSS_BYTE0_INTF_CLK>, + <&dispcc DISP_CC_MDSS_PCLK0_CLK>, + <&dispcc DISP_CC_MDSS_ESC0_CLK>, + <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&dispcc DISP_CC_MDSS_AXI_CLK>; + clock-names = "byte", + "byte_intf", + "pixel", + "core", + "iface", + "bus"; - phys = <&dsi0_phy>; - phy-names = "dsi"; + phys = <&dsi0_phy>; + phy-names = "dsi"; - assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>, <&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>; - assigned-clock-parents = <&dsi_phy 0>, <&dsi_phy 1>; + assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>, <&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>; + assigned-clock-parents = <&dsi_phy 0>, <&dsi_phy 1>; - power-domains = <&rpmhpd SC7180_CX>; - operating-points-v2 = <&dsi_opp_table>; + power-domains = <&rpmhpd SC7180_CX>; + operating-points-v2 = <&dsi_opp_table>; - ports { - #address-cells = <1>; - #size-cells = <0>; + ports { + #address-cells = <1>; + #size-cells = <0>; - port@0 { - reg = <0>; - dsi0_in: endpoint { - remote-endpoint = <&dpu_intf1_out>; - }; - }; + port@0 { + reg = <0>; + endpoint { + remote-endpoint = <&dpu_intf1_out>; + }; + }; - port@1 { - reg = <1>; - dsi0_out: endpoint { - remote-endpoint = <&sn65dsi86_in>; - data-lanes = <0 1 2 3>; - qcom,te-source = "mdp_vsync_e"; - }; - }; - }; - }; + port@1 { + reg = <1>; + endpoint { + remote-endpoint = <&sn65dsi86_in>; + data-lanes = <0 1 2 3>; + qcom,te-source = "mdp_vsync_e"; + }; + }; + }; + }; ... diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml index 69d13867b7cf..fc9abf090f0d 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml @@ -74,28 +74,28 @@ unevaluatedProperties: false examples: - | - #include - #include + #include + #include - dsi-phy@ae94400 { - compatible = "qcom,dsi-phy-10nm"; - reg = <0x0ae94400 0x200>, - <0x0ae94600 0x280>, - <0x0ae94a00 0x1e0>; - reg-names = "dsi_phy", - "dsi_phy_lane", - "dsi_pll"; + dsi-phy@ae94400 { + compatible = "qcom,dsi-phy-10nm"; + reg = <0x0ae94400 0x200>, + <0x0ae94600 0x280>, + <0x0ae94a00 0x1e0>; + reg-names = "dsi_phy", + "dsi_phy_lane", + "dsi_pll"; - #clock-cells = <1>; - #phy-cells = <0>; + #clock-cells = <1>; + #phy-cells = <0>; - vdds-supply = <&vdda_mipi_dsi0_pll>; - clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, - <&rpmhcc RPMH_CXO_CLK>; - clock-names = "iface", "ref"; + vdds-supply = <&vdda_mipi_dsi0_pll>; + clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "ref"; - qcom,phy-rescode-offset-top = /bits/ 8 <0 0 0 0 0>; - qcom,phy-rescode-offset-bot = /bits/ 8 <0 0 0 0 0>; - qcom,phy-drive-ldo-level = <400>; - }; + qcom,phy-rescode-offset-top = /bits/ 8 <0 0 0 0 0>; + qcom,phy-rescode-offset-bot = /bits/ 8 <0 0 0 0 0>; + qcom,phy-drive-ldo-level = <400>; + }; ... diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml index 52bbe132e6da..206a9a4b3845 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml @@ -20,6 +20,7 @@ properties: - qcom,dsi-phy-14nm-660 - qcom,dsi-phy-14nm-8953 - qcom,sm6125-dsi-phy-14nm + - qcom,sm6150-dsi-phy-14nm reg: items: @@ -55,24 +56,24 @@ unevaluatedProperties: false examples: - | - #include - #include + #include + #include - dsi-phy@ae94400 { - compatible = "qcom,dsi-phy-14nm"; - reg = <0x0ae94400 0x200>, - <0x0ae94600 0x280>, - <0x0ae94a00 0x1e0>; - reg-names = "dsi_phy", - "dsi_phy_lane", - "dsi_pll"; + dsi-phy@ae94400 { + compatible = "qcom,dsi-phy-14nm"; + reg = <0x0ae94400 0x200>, + <0x0ae94600 0x280>, + <0x0ae94a00 0x1e0>; + reg-names = "dsi_phy", + "dsi_phy_lane", + "dsi_pll"; - #clock-cells = <1>; - #phy-cells = <0>; + #clock-cells = <1>; + #phy-cells = <0>; - vcca-supply = <&vcca_reg>; - clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, - <&rpmhcc RPMH_CXO_CLK>; - clock-names = "iface", "ref"; - }; + vcca-supply = <&vcca_reg>; + clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "ref"; + }; ... diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-20nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-20nm.yaml index 7e6687cb002b..93570052992a 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-20nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-20nm.yaml @@ -45,26 +45,26 @@ unevaluatedProperties: false examples: - | - #include - #include + #include + #include - dsi-phy@fd922a00 { - compatible = "qcom,dsi-phy-20nm"; - reg = <0xfd922a00 0xd4>, - <0xfd922b00 0x2b0>, - <0xfd922d80 0x7b>; - reg-names = "dsi_pll", - "dsi_phy", - "dsi_phy_regulator"; + dsi-phy@fd922a00 { + compatible = "qcom,dsi-phy-20nm"; + reg = <0xfd922a00 0xd4>, + <0xfd922b00 0x2b0>, + <0xfd922d80 0x7b>; + reg-names = "dsi_pll", + "dsi_phy", + "dsi_phy_regulator"; - #clock-cells = <1>; - #phy-cells = <0>; + #clock-cells = <1>; + #phy-cells = <0>; - vcca-supply = <&vcca_reg>; - vddio-supply = <&vddio_reg>; + vcca-supply = <&vcca_reg>; + vddio-supply = <&vddio_reg>; - clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, - <&rpmhcc RPMH_CXO_CLK>; - clock-names = "iface", "ref"; - }; + clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "ref"; + }; ... diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml index a55c2445d189..371befa9f9d2 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml @@ -51,25 +51,25 @@ unevaluatedProperties: false examples: - | - #include - #include + #include + #include - dsi-phy@fd922a00 { - compatible = "qcom,dsi-phy-28nm-lp"; - reg = <0xfd922a00 0xd4>, - <0xfd922b00 0x2b0>, - <0xfd922d80 0x7b>; - reg-names = "dsi_pll", - "dsi_phy", - "dsi_phy_regulator"; + dsi-phy@fd922a00 { + compatible = "qcom,dsi-phy-28nm-lp"; + reg = <0xfd922a00 0xd4>, + <0xfd922b00 0x2b0>, + <0xfd922d80 0x7b>; + reg-names = "dsi_pll", + "dsi_phy", + "dsi_phy_regulator"; - #clock-cells = <1>; - #phy-cells = <0>; + #clock-cells = <1>; + #phy-cells = <0>; - vddio-supply = <&vddio_reg>; + vddio-supply = <&vddio_reg>; - clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, - <&rpmhcc RPMH_CXO_CLK>; - clock-names = "iface", "ref"; - }; + clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "ref"; + }; ... diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml index 7e764eac3ef3..321470435e65 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml @@ -54,23 +54,23 @@ unevaluatedProperties: false examples: - | - #include - #include + #include + #include - dsi-phy@ae94400 { - compatible = "qcom,dsi-phy-7nm"; - reg = <0x0ae94400 0x200>, - <0x0ae94600 0x280>, - <0x0ae94900 0x260>; - reg-names = "dsi_phy", - "dsi_phy_lane", - "dsi_pll"; + dsi-phy@ae94400 { + compatible = "qcom,dsi-phy-7nm"; + reg = <0x0ae94400 0x200>, + <0x0ae94600 0x280>, + <0x0ae94900 0x260>; + reg-names = "dsi_phy", + "dsi_phy_lane", + "dsi_pll"; - #clock-cells = <1>; - #phy-cells = <0>; + #clock-cells = <1>; + #phy-cells = <0>; - vdds-supply = <&vreg_l5a_0p88>; - clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, - <&rpmhcc RPMH_CXO_CLK>; - clock-names = "iface", "ref"; - }; + vdds-supply = <&vreg_l5a_0p88>; + clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "ref"; + }; diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sa8775p-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sa8775p-mdss.yaml index 58f8a01f29c7..a90a8b3f1a9e 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sa8775p-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sa8775p-mdss.yaml @@ -78,7 +78,6 @@ examples: "mdp1-mem", "cpu-cfg"; - resets = <&dispcc_core_bcr>; power-domains = <&dispcc_gdsc>; @@ -129,7 +128,7 @@ examples: port@0 { reg = <0>; dpu_intf0_out: endpoint { - remote-endpoint = <&mdss0_dp0_in>; + remote-endpoint = <&mdss0_dp0_in>; }; }; }; @@ -168,7 +167,8 @@ examples: reg = <0xaf54000 0x104>, <0xaf54200 0x0c0>, <0xaf55000 0x770>, - <0xaf56000 0x09c>; + <0xaf56000 0x09c>, + <0xaf57000 0x09c>; interrupt-parent = <&mdss0>; interrupts = <12>; @@ -208,8 +208,8 @@ examples: }; port@1 { - reg = <1>; - mdss0_dp_out: endpoint { }; + reg = <1>; + mdss0_dp_out: endpoint { }; }; }; diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm6150-dpu.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm6150-dpu.yaml new file mode 100644 index 000000000000..b4f437172218 --- /dev/null +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm6150-dpu.yaml @@ -0,0 +1,108 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/msm/qcom,sm6150-dpu.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm SM6150 Display DPU + +maintainers: + - Abhinav Kumar + - Dmitry Baryshkov + +$ref: /schemas/display/msm/dpu-common.yaml# + +properties: + compatible: + const: qcom,sm6150-dpu + + reg: + items: + - description: Address offset and size for mdp register set + - description: Address offset and size for vbif register set + + reg-names: + items: + - const: mdp + - const: vbif + + clocks: + items: + - description: Display ahb clock + - description: Display hf axi clock + - description: Display core clock + - description: Display vsync clock + + clock-names: + items: + - const: iface + - const: bus + - const: core + - const: vsync + +unevaluatedProperties: false + +examples: + - | + #include + #include + + display-controller@ae01000 { + compatible = "qcom,sm6150-dpu"; + reg = <0x0ae01000 0x8f000>, + <0x0aeb0000 0x2008>; + reg-names = "mdp", "vbif"; + + clocks = <&dispcc_mdss_ahb_clk>, + <&gcc_disp_hf_axi_clk>, + <&dispcc_mdss_mdp_clk>, + <&dispcc_mdss_vsync_clk>; + clock-names = "iface", "bus", "core", "vsync"; + + assigned-clocks = <&dispcc_mdss_vsync_clk>; + assigned-clock-rates = <19200000>; + + operating-points-v2 = <&mdp_opp_table>; + power-domains = <&rpmhpd RPMHPD_CX>; + + interrupt-parent = <&mdss>; + interrupts = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dpu_intf0_out: endpoint { + }; + }; + + port@1 { + reg = <1>; + dpu_intf1_out: endpoint { + remote-endpoint = <&mdss_dsi0_in>; + }; + }; + }; + + mdp_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-19200000 { + opp-hz = /bits/ 64 <19200000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-25600000 { + opp-hz = /bits/ 64 <25600000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-307200000 { + opp-hz = /bits/ 64 <307200000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm6150-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm6150-mdss.yaml new file mode 100644 index 000000000000..9ac24f99d3ad --- /dev/null +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm6150-mdss.yaml @@ -0,0 +1,245 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/msm/qcom,sm6150-mdss.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm SM6150 Display MDSS + +maintainers: + - Abhinav Kumar + - Dmitry Baryshkov + +description: + Device tree bindings for MSM Mobile Display Subsystem(MDSS) that encapsulates + sub-blocks like DPU display controller, DSI and DP interfaces etc. Device tree + bindings of MDSS are mentioned for SM6150 target. + +$ref: /schemas/display/msm/mdss-common.yaml# + +properties: + compatible: + items: + - const: qcom,sm6150-mdss + + clocks: + items: + - description: Display AHB clock from gcc + - description: Display hf axi clock + - description: Display core clock + + clock-names: + items: + - const: iface + - const: bus + - const: core + + iommus: + maxItems: 1 + + interconnects: + maxItems: 2 + + interconnect-names: + maxItems: 2 + +patternProperties: + "^display-controller@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + compatible: + const: qcom,sm6150-dpu + + "^dsi@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + compatible: + items: + - const: qcom,sm6150-dsi-ctrl + - const: qcom,mdss-dsi-ctrl + + "^phy@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + compatible: + const: qcom,sm6150-dsi-phy-14nm + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + #include + #include + + display-subsystem@ae00000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "qcom,sm6150-mdss"; + reg = <0x0ae00000 0x1000>; + reg-names = "mdss"; + + interconnects = <&mmss_noc MASTER_MDP0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ACTIVE_ONLY>; + interconnect-names = "mdp0-mem", "cpu-cfg"; + + power-domains = <&dispcc_mdss_gdsc>; + + clocks = <&dispcc_mdss_ahb_clk>, + <&gcc_disp_hf_axi_clk>, + <&dispcc_mdss_mdp_clk>; + + interrupts = ; + interrupt-controller; + #interrupt-cells = <1>; + + iommus = <&apps_smmu 0x800 0x0>; + + ranges; + + display-controller@ae01000 { + compatible = "qcom,sm6150-dpu"; + reg = <0x0ae01000 0x8f000>, + <0x0aeb0000 0x2008>; + reg-names = "mdp", "vbif"; + + clocks = <&dispcc_mdss_ahb_clk>, + <&gcc_disp_hf_axi_clk>, + <&dispcc_mdss_mdp_clk>, + <&dispcc_mdss_vsync_clk>; + clock-names = "iface", "bus", "core", "vsync"; + + assigned-clocks = <&dispcc_mdss_vsync_clk>; + assigned-clock-rates = <19200000>; + + operating-points-v2 = <&mdp_opp_table>; + power-domains = <&rpmhpd RPMHPD_CX>; + + interrupt-parent = <&mdss>; + interrupts = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dpu_intf0_out: endpoint { + }; + }; + + port@1 { + reg = <1>; + dpu_intf1_out: endpoint { + remote-endpoint = <&mdss_dsi0_in>; + }; + }; + }; + + mdp_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-19200000 { + opp-hz = /bits/ 64 <19200000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-25600000 { + opp-hz = /bits/ 64 <25600000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-307200000 { + opp-hz = /bits/ 64 <307200000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; + + dsi@ae94000 { + compatible = "qcom,sm6150-dsi-ctrl", + "qcom,mdss-dsi-ctrl"; + reg = <0x0ae94000 0x400>; + reg-names = "dsi_ctrl"; + + interrupt-parent = <&mdss>; + interrupts = <4>; + + clocks = <&dispcc_mdss_byte0_clk>, + <&dispcc_mdss_byte0_intf_clk>, + <&dispcc_mdss_pclk0_clk>, + <&dispcc_mdss_esc0_clk>, + <&dispcc_mdss_ahb_clk>, + <&gcc_disp_hf_axi_clk>; + clock-names = "byte", + "byte_intf", + "pixel", + "core", + "iface", + "bus"; + + assigned-clocks = <&dispcc_mdss_byte0_clk_src>, + <&dispcc_mdss_pclk0_clk_src>; + assigned-clock-parents = <&mdss_dsi0_phy 0>, + <&mdss_dsi0_phy 1>; + + operating-points-v2 = <&dsi0_opp_table>; + + phys = <&mdss_dsi0_phy>; + + #address-cells = <1>; + #size-cells = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + mdss_dsi0_in: endpoint { + remote-endpoint = <&dpu_intf1_out>; + }; + }; + + port@1 { + reg = <1>; + mdss_dsi0_out: endpoint { + }; + }; + }; + + dsi0_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-164000000 { + opp-hz = /bits/ 64 <164000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + }; + }; + + mdss_dsi0_phy: phy@ae94400 { + compatible = "qcom,sm6150-dsi-phy-14nm"; + reg = <0x0ae94400 0x100>, + <0x0ae94500 0x300>, + <0x0ae94800 0x188>; + reg-names = "dsi_phy", + "dsi_phy_lane", + "dsi_pll"; + + #clock-cells = <1>; + #phy-cells = <0>; + + clocks = <&dispcc_mdss_ahb_clk>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "ref"; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml index 7cdd69ba6db0..e3ee3a332bb7 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml @@ -290,6 +290,8 @@ properties: - tianma,tm070jvhg33 # Tianma Micro-electronics TM070RVHG71 7.0" WXGA TFT LCD panel - tianma,tm070rvhg71 + # Topland TIAN-G07017-01 7.0" WSVGA TFT-LCD panel with capacitive touch + - topland,tian-g07017-01 # Toshiba 8.9" WXGA (1280x768) TFT LCD panel - toshiba,lt089ac29000 # TPK U.S.A. LLC Fusion 7" 800 x 480 (WVGA) LCD panel with capacitive touch diff --git a/Documentation/devicetree/bindings/display/renesas,cmm.yaml b/Documentation/devicetree/bindings/display/renesas,cmm.yaml index 561efaaa5a91..fc4933c343cd 100644 --- a/Documentation/devicetree/bindings/display/renesas,cmm.yaml +++ b/Documentation/devicetree/bindings/display/renesas,cmm.yaml @@ -58,10 +58,10 @@ examples: #include cmm0: cmm@fea40000 { - compatible = "renesas,r8a7796-cmm", - "renesas,rcar-gen3-cmm"; - reg = <0xfea40000 0x1000>; - power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; - clocks = <&cpg CPG_MOD 711>; - resets = <&cpg 711>; + compatible = "renesas,r8a7796-cmm", + "renesas,rcar-gen3-cmm"; + reg = <0xfea40000 0x1000>; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + clocks = <&cpg CPG_MOD 711>; + resets = <&cpg 711>; }; diff --git a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt b/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt deleted file mode 100644 index cd17684aaab5..000000000000 --- a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt +++ /dev/null @@ -1,61 +0,0 @@ -Analog Devices AXI-DMAC DMA controller - -Required properties: - - compatible: Must be "adi,axi-dmac-1.00.a". - - reg: Specification for the controllers memory mapped register map. - - interrupts: Specification for the controllers interrupt. - - clocks: Phandle and specifier to the controllers AXI interface clock - - #dma-cells: Must be 1. - -Required sub-nodes: - - adi,channels: This sub-node must contain a sub-node for each DMA channel. For - the channel sub-nodes the following bindings apply. They must match the - configuration options of the peripheral as it was instantiated. - -Required properties for adi,channels sub-node: - - #size-cells: Must be 0 - - #address-cells: Must be 1 - -Required channel sub-node properties: - - reg: Which channel this node refers to. - - adi,source-bus-width, - adi,destination-bus-width: Width of the source or destination bus in bits. - - adi,source-bus-type, - adi,destination-bus-type: Type of the source or destination bus. Must be one - of the following: - 0 (AXI_DMAC_TYPE_AXI_MM): Memory mapped AXI interface - 1 (AXI_DMAC_TYPE_AXI_STREAM): Streaming AXI interface - 2 (AXI_DMAC_TYPE_AXI_FIFO): FIFO interface - -Deprecated optional channel properties: - - adi,length-width: Width of the DMA transfer length register. - - adi,cyclic: Must be set if the channel supports hardware cyclic DMA - transfers. - - adi,2d: Must be set if the channel supports hardware 2D DMA transfers. - -DMA clients connected to the AXI-DMAC DMA controller must use the format -described in the dma.txt file using a one-cell specifier. The value of the -specifier refers to the DMA channel index. - -Example: - -dma: dma@7c420000 { - compatible = "adi,axi-dmac-1.00.a"; - reg = <0x7c420000 0x10000>; - interrupts = <0 57 0>; - clocks = <&clkc 16>; - #dma-cells = <1>; - - adi,channels { - #size-cells = <0>; - #address-cells = <1>; - - dma-channel@0 { - reg = <0>; - adi,source-bus-width = <32>; - adi,source-bus-type = ; - adi,destination-bus-width = <64>; - adi,destination-bus-type = ; - }; - }; -}; diff --git a/Documentation/devicetree/bindings/dma/adi,axi-dmac.yaml b/Documentation/devicetree/bindings/dma/adi,axi-dmac.yaml new file mode 100644 index 000000000000..63b6fb0423c2 --- /dev/null +++ b/Documentation/devicetree/bindings/dma/adi,axi-dmac.yaml @@ -0,0 +1,129 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/dma/adi,axi-dmac.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Analog Devices AXI-DMAC DMA controller + +description: | + FPGA-based DMA controller designed for use with high-speed converter hardware. + + http://analogdevicesinc.github.io/hdl/library/axi_dmac/index.html + +maintainers: + - Nuno Sa + +additionalProperties: false + +properties: + compatible: + const: adi,axi-dmac-1.00.a + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + "#dma-cells": + const: 1 + + adi,channels: + deprecated: true + type: object + description: + This sub-node must contain a sub-node for each DMA channel. This node is + only required for IP versions older than 4.3.a and should otherwise be + omitted. + additionalProperties: false + + properties: + "#size-cells": + const: 0 + "#address-cells": + const: 1 + + patternProperties: + "^dma-channel@[0-9a-f]+$": + type: object + description: + DMA channel properties based on HDL compile-time configuration. + additionalProperties: false + + properties: + reg: + maxItems: 1 + + adi,source-bus-width: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Width of the source bus in bits. + enum: [8, 16, 32, 64, 128] + + adi,destination-bus-width: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Width of the destination bus in bits. + enum: [8, 16, 32, 64, 128] + + adi,source-bus-type: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Type of the source bus. + + 0: Memory mapped AXI interface + 1: Streaming AXI interface + 2: FIFO interface + enum: [0, 1, 2] + + adi,destination-bus-type: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Type of the destination bus (see adi,source-bus-type). + enum: [0, 1, 2] + + adi,length-width: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: Width of the DMA transfer length register. + + adi,cyclic: + deprecated: true + type: boolean + description: + Must be set if the channel supports hardware cyclic DMA transfers. + + adi,2d: + deprecated: true + type: boolean + description: + Must be set if the channel supports hardware 2D DMA transfers. + + required: + - reg + - adi,source-bus-width + - adi,destination-bus-width + - adi,source-bus-type + - adi,destination-bus-type + + required: + - "#size-cells" + - "#address-cells" + +required: + - compatible + - reg + - interrupts + - clocks + - "#dma-cells" + +examples: + - | + dma-controller@7c420000 { + compatible = "adi,axi-dmac-1.00.a"; + reg = <0x7c420000 0x10000>; + interrupts = <0 57 0>; + clocks = <&clkc 16>; + #dma-cells = <1>; + }; diff --git a/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml b/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml index 02d5bd035409..9b5180c0a7c4 100644 --- a/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml +++ b/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml @@ -22,7 +22,9 @@ properties: number. compatible: - const: allwinner,sun4i-a10-dma + enum: + - allwinner,sun4i-a10-dma + - allwinner,suniv-f1c100s-dma reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/dma/atmel,sama5d4-dma.yaml b/Documentation/devicetree/bindings/dma/atmel,sama5d4-dma.yaml new file mode 100644 index 000000000000..9ca1c5d1f00f --- /dev/null +++ b/Documentation/devicetree/bindings/dma/atmel,sama5d4-dma.yaml @@ -0,0 +1,79 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/dma/atmel,sama5d4-dma.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip AT91 Extensible Direct Memory Access Controller + +maintainers: + - Nicolas Ferre + - Charan Pedumuru + +description: + The DMA Controller (XDMAC) is a AHB-protocol central direct memory access + controller. It performs peripheral data transfer and memory move operations + over one or two bus ports through the unidirectional communication + channel. Each channel is fully programmable and provides both peripheral + or memory-to-memory transfers. The channel features are configurable at + implementation. + +allOf: + - $ref: dma-controller.yaml# + +properties: + compatible: + oneOf: + - enum: + - atmel,sama5d4-dma + - microchip,sama7g5-dma + - items: + - enum: + - microchip,sam9x60-dma + - microchip,sam9x7-dma + - const: atmel,sama5d4-dma + + "#dma-cells": + description: | + Represents the number of integer cells in the `dmas` property of client + devices. The single cell specifies the channel configuration register: + - bit 13: SIF (Source Interface Identifier) for memory interface. + - bit 14: DIF (Destination Interface Identifier) for peripheral interface. + - bit 30-24: PERID (Peripheral Identifier). + const: 1 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + const: dma_clk + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - "#dma-cells" + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + dma-controller@f0008000 { + compatible = "atmel,sama5d4-dma"; + reg = <0xf0008000 0x1000>; + interrupts = <20 IRQ_TYPE_LEVEL_HIGH 0>; + #dma-cells = <1>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 20>; + clock-names = "dma_clk"; + }; diff --git a/Documentation/devicetree/bindings/dma/atmel-xdma.txt b/Documentation/devicetree/bindings/dma/atmel-xdma.txt deleted file mode 100644 index 76d649b3a25d..000000000000 --- a/Documentation/devicetree/bindings/dma/atmel-xdma.txt +++ /dev/null @@ -1,54 +0,0 @@ -* Atmel Extensible Direct Memory Access Controller (XDMAC) - -* XDMA Controller -Required properties: -- compatible: Should be "atmel,sama5d4-dma", "microchip,sam9x60-dma" or - "microchip,sama7g5-dma" or - "microchip,sam9x7-dma", "atmel,sama5d4-dma". -- reg: Should contain DMA registers location and length. -- interrupts: Should contain DMA interrupt. -- #dma-cells: Must be <1>, used to represent the number of integer cells in -the dmas property of client devices. - - The 1st cell specifies the channel configuration register: - - bit 13: SIF, source interface identifier, used to get the memory - interface identifier, - - bit 14: DIF, destination interface identifier, used to get the peripheral - interface identifier, - - bit 30-24: PERID, peripheral identifier. - -Example: - -dma1: dma-controller@f0004000 { - compatible = "atmel,sama5d4-dma"; - reg = <0xf0004000 0x200>; - interrupts = <50 4 0>; - #dma-cells = <1>; -}; - - -* DMA clients -DMA clients connected to the Atmel XDMA controller must use the format -described in the dma.txt file, using a one-cell specifier for each channel. -The two cells in order are: -1. A phandle pointing to the DMA controller. -2. Channel configuration register. Configurable fields are: - - bit 13: SIF, source interface identifier, used to get the memory - interface identifier, - - bit 14: DIF, destination interface identifier, used to get the peripheral - interface identifier, - - bit 30-24: PERID, peripheral identifier. - -Example: - -i2c2: i2c@f8024000 { - compatible = "atmel,at91sam9x5-i2c"; - reg = <0xf8024000 0x4000>; - interrupts = <34 4 6>; - dmas = <&dma1 - (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) - | AT91_XDMAC_DT_PERID(6))>, - <&dma1 - (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) - | AT91_XDMAC_DT_PERID(7))>; - dma-names = "tx", "rx"; -}; diff --git a/Documentation/devicetree/bindings/dma/fsl,edma.yaml b/Documentation/devicetree/bindings/dma/fsl,edma.yaml index d54140f18d34..4f925469533e 100644 --- a/Documentation/devicetree/bindings/dma/fsl,edma.yaml +++ b/Documentation/devicetree/bindings/dma/fsl,edma.yaml @@ -26,9 +26,13 @@ properties: - fsl,imx93-edma3 - fsl,imx93-edma4 - fsl,imx95-edma5 + - nxp,s32g2-edma - items: - const: fsl,ls1028a-edma - const: fsl,vf610-edma + - items: + - const: nxp,s32g3-edma + - const: nxp,s32g2-edma reg: minItems: 1 @@ -221,6 +225,36 @@ allOf: properties: power-domains: false + - if: + properties: + compatible: + contains: + const: nxp,s32g2-edma + then: + properties: + clocks: + minItems: 2 + maxItems: 2 + clock-names: + items: + - const: dmamux0 + - const: dmamux1 + interrupts: + minItems: 3 + maxItems: 3 + interrupt-names: + items: + - const: tx-0-15 + - const: tx-16-31 + - const: err + reg: + minItems: 3 + maxItems: 3 + "#dma-cells": + const: 2 + dma-channels: + const: 32 + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml index 877147e95ecc..d3f8c269916c 100644 --- a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml +++ b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml @@ -13,9 +13,6 @@ description: | maintainers: - Jon Hunter -allOf: - - $ref: dma-controller.yaml# - properties: compatible: oneOf: @@ -29,7 +26,19 @@ properties: - const: nvidia,tegra186-adma reg: - maxItems: 1 + description: + The 'page' region describes the address space of the page + used for accessing the DMA channel registers. The 'global' + region describes the address space of the global DMA registers. + In the absence of the 'reg-names' property, there must be a + single entry that covers the address space of the global DMA + registers and the DMA channel registers. + minItems: 1 + maxItems: 2 + + reg-names: + minItems: 1 + maxItems: 2 interrupts: description: | @@ -63,6 +72,49 @@ required: - clocks - clock-names +allOf: + - $ref: dma-controller.yaml# + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra210-adma + then: + properties: + reg: + items: + - description: Full address space range of DMA registers. + + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra186-adma + then: + anyOf: + - properties: + reg: + items: + - description: Full address space range of DMA registers. + - properties: + reg: + items: + - description: Channel Page address space range of DMA registers. + reg-names: + items: + - const: page + - properties: + reg: + items: + - description: Channel Page address space range of DMA registers. + - description: Global Page address space range of DMA registers. + reg-names: + items: + - const: page + - const: global + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml index 4ad56a409b9c..7052468b15c8 100644 --- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml +++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml @@ -25,7 +25,9 @@ properties: - items: - enum: - qcom,qcm2290-gpi-dma + - qcom,qcs8300-gpi-dma - qcom,qdu1000-gpi-dma + - qcom,sa8775p-gpi-dma - qcom,sar2130p-gpi-dma - qcom,sc7280-gpi-dma - qcom,sdx75-gpi-dma @@ -35,10 +37,12 @@ properties: - qcom,sm8450-gpi-dma - qcom,sm8550-gpi-dma - qcom,sm8650-gpi-dma + - qcom,sm8750-gpi-dma - qcom,x1e80100-gpi-dma - const: qcom,sm6350-gpi-dma - items: - enum: + - qcom,qcs615-gpi-dma - qcom,sdm670-gpi-dma - qcom,sm6125-gpi-dma - qcom,sm8150-gpi-dma diff --git a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml index f26c914a3a9a..b7bca1a83769 100644 --- a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml +++ b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml @@ -15,6 +15,16 @@ allOf: properties: "#dma-cells": const: 3 + description: | + Each cell represents the following: + 1. The mux input number/line for the request + 2. Bitfield representing DMA channel configuration that is passed + to the real DMA controller + 3. Bitfield representing device dependent DMA features passed to + the real DMA controller + + For bitfield definitions of cells 2 and 3, see the associated + bindings doc for the actual DMA controller in st,stm32-dma.yaml. compatible: const: st,stm32h7-dmamux diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml index 27b8e1636560..b5bc842c5a0e 100644 --- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml +++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml @@ -34,6 +34,7 @@ properties: - ti,am62a-dmss-bcdma-csirx - ti,am64-dmss-bcdma - ti,j721s2-dmss-bcdma-csi + - ti,j722s-dmss-bcdma-csi reg: minItems: 3 @@ -196,7 +197,9 @@ allOf: properties: compatible: contains: - const: ti,j721s2-dmss-bcdma-csi + enum: + - ti,j721s2-dmss-bcdma-csi + - ti,j722s-dmss-bcdma-csi then: properties: ti,sci-rm-range-bchan: false diff --git a/Documentation/devicetree/bindings/dts-coding-style.rst b/Documentation/devicetree/bindings/dts-coding-style.rst index 8a68331075a0..4772ded8a987 100644 --- a/Documentation/devicetree/bindings/dts-coding-style.rst +++ b/Documentation/devicetree/bindings/dts-coding-style.rst @@ -162,14 +162,17 @@ Example:: status = "okay"; } -Indentation ------------ +Indentation and wrapping +------------------------ -1. Use indentation according to Documentation/process/coding-style.rst. +1. Use indentation and wrap lines according to + Documentation/process/coding-style.rst. 2. Each entry in arrays with multiple cells, e.g. "reg" with two IO addresses, shall be enclosed in <>. -3. For arrays spanning across lines, it is preferred to align the continued - entries with opening < from the first line. +3. For arrays spanning across lines, it is preferred to split on item boundary + and align the continued entries with opening < from the first line. + Usually avoid splitting individual items unless they significantly exceed + line wrap limit. Example:: @@ -177,6 +180,9 @@ Example:: compatible = "qcom,sm8550-tsens", "qcom,tsens-v2"; reg = <0x0 0x0c271000 0x0 0x1000>, <0x0 0x0c222000 0x0 0x1000>; + /* Lines exceeding coding style line wrap limit: */ + interconnects = <&aggre1_noc MASTER_USB3_0 0 &mc_virt SLAVE_EBI1 0>, + <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3_0 0>; }; Organizing DTSI and DTS diff --git a/Documentation/devicetree/bindings/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml index 590ba0ef5fa2..c9e4afbdc448 100644 --- a/Documentation/devicetree/bindings/eeprom/at24.yaml +++ b/Documentation/devicetree/bindings/eeprom/at24.yaml @@ -134,9 +134,14 @@ properties: - const: atmel,24c64 - items: - enum: + - giantec,gt24p128f - renesas,r1ex24128 - samsung,s524ad0xd1 - const: atmel,24c128 + - items: + - enum: + - puya,p24c256c + - const: atmel,24c256 - items: - const: microchip,24aa025e48 - items: diff --git a/Documentation/devicetree/bindings/firmware/qcom,scm.yaml b/Documentation/devicetree/bindings/firmware/qcom,scm.yaml index 2ee030000007..8cdaac8011ba 100644 --- a/Documentation/devicetree/bindings/firmware/qcom,scm.yaml +++ b/Documentation/devicetree/bindings/firmware/qcom,scm.yaml @@ -26,6 +26,7 @@ properties: - qcom,scm-ipq4019 - qcom,scm-ipq5018 - qcom,scm-ipq5332 + - qcom,scm-ipq5424 - qcom,scm-ipq6018 - qcom,scm-ipq806x - qcom,scm-ipq8074 @@ -42,6 +43,7 @@ properties: - qcom,scm-msm8996 - qcom,scm-msm8998 - qcom,scm-qcm2290 + - qcom,scm-qcs615 - qcom,scm-qcs8300 - qcom,scm-qdu1000 - qcom,scm-sa8255p diff --git a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.yaml b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.yaml index f096f286da19..fbd69b4cecc7 100644 --- a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.yaml +++ b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.yaml @@ -64,6 +64,10 @@ properties: gpio-ranges: true + gpio-line-names: + minItems: 1 + maxItems: 128 + wakeup-source: type: boolean description: > diff --git a/Documentation/devicetree/bindings/gpio/fairchild,74hc595.yaml b/Documentation/devicetree/bindings/gpio/fairchild,74hc595.yaml index e8bc9f018edb..0e5c22929bde 100644 --- a/Documentation/devicetree/bindings/gpio/fairchild,74hc595.yaml +++ b/Documentation/devicetree/bindings/gpio/fairchild,74hc595.yaml @@ -6,6 +6,23 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Generic 8-bit shift register +description: | + NOTE: These chips nominally don't have a chip select pin. They do however + have a rising-edge triggered latch clock (or storage register clock) pin, + which behaves like an active-low chip select. + + After the bits are shifted into the shift register, CS# is driven high, which + the 74HC595 sees as a rising edge on the latch clock that results in a + transfer of the bits from the shift register to the storage register and thus + to the output pins. + _ _ _ _ + shift clock ____| |_| |_..._| |_| |_________ + + latch clock * trigger + ___ ________ + chip select# |___________________| + + maintainers: - Maxime Ripard diff --git a/Documentation/devicetree/bindings/gpio/fsl,qoriq-gpio.yaml b/Documentation/devicetree/bindings/gpio/fsl,qoriq-gpio.yaml index 84fd82291ee4..f1b60ab3f356 100644 --- a/Documentation/devicetree/bindings/gpio/fsl,qoriq-gpio.yaml +++ b/Documentation/devicetree/bindings/gpio/fsl,qoriq-gpio.yaml @@ -15,6 +15,7 @@ properties: - enum: - fsl,mpc5121-gpio - fsl,mpc5125-gpio + - fsl,mpc8314-gpio - fsl,mpc8349-gpio - fsl,mpc8572-gpio - fsl,mpc8610-gpio diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-utgard.yaml b/Documentation/devicetree/bindings/gpu/arm,mali-utgard.yaml index abd4aa335fbc..9318817ea135 100644 --- a/Documentation/devicetree/bindings/gpu/arm,mali-utgard.yaml +++ b/Documentation/devicetree/bindings/gpu/arm,mali-utgard.yaml @@ -33,6 +33,7 @@ properties: - rockchip,rk3188-mali - rockchip,rk3228-mali - samsung,exynos4210-mali + - st,stih410-mali - stericsson,db8500-mali - xlnx,zynqmp-mali - const: arm,mali-400 diff --git a/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml b/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml index 5b076d677395..fd79bf2e0d16 100644 --- a/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml +++ b/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml @@ -24,6 +24,7 @@ properties: enum: - adi,adm1075 - adi,adm1272 + - adi,adm1273 - adi,adm1275 - adi,adm1276 - adi,adm1278 @@ -79,6 +80,7 @@ allOf: contains: enum: - adi,adm1272 + - adi,adm1273 then: properties: adi,volt-curr-sample-average: diff --git a/Documentation/devicetree/bindings/hwmon/lm75.yaml b/Documentation/devicetree/bindings/hwmon/lm75.yaml index 29bd7460cc26..c38255243f57 100644 --- a/Documentation/devicetree/bindings/hwmon/lm75.yaml +++ b/Documentation/devicetree/bindings/hwmon/lm75.yaml @@ -28,6 +28,7 @@ properties: - maxim,max31725 - maxim,max31726 - maxim,mcp980x + - nxp,p3t1755 - nxp,pct2075 - st,stds75 - st,stlm75 diff --git a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml index cc8bba5537b9..70cc2ee9ee27 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml @@ -25,6 +25,7 @@ properties: - samsung,exynos5250-hsi2c # Exynos5250 and Exynos5420 - samsung,exynos5260-hsi2c # Exynos5260 - samsung,exynos7-hsi2c # Exynos7 + - samsung,exynos8895-hsi2c - samsung,exynosautov9-hsi2c - items: - enum: diff --git a/Documentation/devicetree/bindings/i2c/qcom,i2c-cci.yaml b/Documentation/devicetree/bindings/i2c/qcom,i2c-cci.yaml index ef26ba6eda28..73144473b9b2 100644 --- a/Documentation/devicetree/bindings/i2c/qcom,i2c-cci.yaml +++ b/Documentation/devicetree/bindings/i2c/qcom,i2c-cci.yaml @@ -34,6 +34,7 @@ properties: - qcom,sm8450-cci - qcom,sm8550-cci - qcom,sm8650-cci + - qcom,x1e80100-cci - const: qcom,msm8996-cci # CCI v2 "#address-cells": @@ -224,6 +225,7 @@ allOf: enum: - qcom,sm8550-cci - qcom,sm8650-cci + - qcom,x1e80100-cci then: properties: clocks: diff --git a/Documentation/devicetree/bindings/i2c/renesas,riic.yaml b/Documentation/devicetree/bindings/i2c/renesas,riic.yaml index 505a8ec92266..1b7fed232642 100644 --- a/Documentation/devicetree/bindings/i2c/renesas,riic.yaml +++ b/Documentation/devicetree/bindings/i2c/renesas,riic.yaml @@ -26,7 +26,9 @@ properties: - const: renesas,riic-rz # RZ/A or RZ/G2L - items: - - const: renesas,riic-r9a08g045 # RZ/G3S + - enum: + - renesas,riic-r9a08g045 # RZ/G3S + - renesas,riic-r9a09g047 # RZ/G3E - const: renesas,riic-r9a09g057 # RZ/V2H(P) - const: renesas,riic-r9a09g057 # RZ/V2H(P) @@ -89,6 +91,7 @@ if: - renesas,riic-r9a07g043 - renesas,riic-r9a07g044 - renesas,riic-r9a07g054 + - renesas,riic-r9a09g057 then: required: - resets diff --git a/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml b/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml index 280ed479ef5a..84d949392012 100644 --- a/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml +++ b/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml @@ -37,10 +37,17 @@ properties: interrupts: maxItems: 1 + interrupt-names: + items: + - enum: [INT1, INT2] + +dependencies: + interrupts: [ interrupt-names ] + interrupt-names: [ interrupts ] + required: - compatible - reg - - interrupts allOf: - $ref: /schemas/spi/spi-peripheral-props.yaml# @@ -61,6 +68,7 @@ examples: reg = <0x2a>; interrupt-parent = <&gpio0>; interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "INT1"; }; }; - | @@ -79,5 +87,6 @@ examples: spi-cpha; interrupt-parent = <&gpio0>; interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "INT2"; }; }; diff --git a/Documentation/devicetree/bindings/iio/accel/kionix,kx022a.yaml b/Documentation/devicetree/bindings/iio/accel/kionix,kx022a.yaml index 66ea894dbe55..f07c70e51c45 100644 --- a/Documentation/devicetree/bindings/iio/accel/kionix,kx022a.yaml +++ b/Documentation/devicetree/bindings/iio/accel/kionix,kx022a.yaml @@ -4,23 +4,26 @@ $id: http://devicetree.org/schemas/iio/accel/kionix,kx022a.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: ROHM/Kionix KX022A, KX132-1211 and KX132ACR-LBZ Accelerometers +title: ROHM/Kionix KX022A, KX132/134-1211 and KX132/134ACR-LBZ Accelerometers maintainers: - Matti Vaittinen description: | KX022A, KX132ACR-LBZ and KX132-1211 are 3-axis accelerometers supporting - +/- 2G, 4G, 8G and 16G ranges, variable output data-rates and a - hardware-fifo buffering. These accelerometers can be accessed either - via I2C or SPI. + +/- 2G, 4G, 8G and 16G ranges. The KX134ACR-LBZ and KX134-1211 support + +/- 8G, 16G, 32G and 64G. All the sensors also have variable output + data-rates and a hardware-fifo buffering. These accelerometers can be + accessed either via I2C or SPI. properties: compatible: enum: - kionix,kx022a - kionix,kx132-1211 + - kionix,kx134-1211 - rohm,kx132acr-lbz + - rohm,kx134acr-lbz reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/iio/accel/nxp,fxls8962af.yaml b/Documentation/devicetree/bindings/iio/accel/nxp,fxls8962af.yaml index 783c7ddfcd90..c175f4c4cbdb 100644 --- a/Documentation/devicetree/bindings/iio/accel/nxp,fxls8962af.yaml +++ b/Documentation/devicetree/bindings/iio/accel/nxp,fxls8962af.yaml @@ -14,12 +14,20 @@ description: | SPI and I2C interface. https://www.nxp.com/docs/en/data-sheet/FXLS8962AF.pdf https://www.nxp.com/docs/en/data-sheet/FXLS8964AF.pdf + https://www.nxp.com/docs/en/data-sheet/FXLS8967AF.pdf + https://www.nxp.com/docs/en/data-sheet/FXLS8974CF.pdf properties: compatible: - enum: - - nxp,fxls8962af - - nxp,fxls8964af + oneOf: + - enum: + - nxp,fxls8962af + - nxp,fxls8964af + - items: + - enum: + - nxp,fxls8967af + - nxp,fxls8974cf + - const: nxp,fxls8962af reg: maxItems: 1 @@ -38,6 +46,11 @@ properties: drive-open-drain: type: boolean + wakeup-source: + $ref: /schemas/types.yaml#/definitions/flag + description: + Enable wake on accelerometer event + required: - compatible - reg @@ -61,6 +74,7 @@ examples: interrupt-parent = <&gpio0>; interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "INT1"; + wakeup-source; }; }; - | diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad4000.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad4000.yaml index e413a9d8d2a2..96e01a97dd95 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad4000.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad4000.yaml @@ -19,49 +19,82 @@ description: | https://www.analog.com/media/en/technical-documentation/data-sheets/ad4020-4021-4022.pdf https://www.analog.com/media/en/technical-documentation/data-sheets/adaq4001.pdf https://www.analog.com/media/en/technical-documentation/data-sheets/adaq4003.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7685.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7686.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7687.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7688.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7690.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7691.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7693.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7942.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7946.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7980.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7982.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7983.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7984.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/ad7988-1_7988-5.pdf $ref: /schemas/spi/spi-peripheral-props.yaml# properties: compatible: oneOf: - - const: adi,ad4000 + - enum: + - adi,ad4000 + - adi,ad4001 + - adi,ad4002 + - adi,ad4003 + - adi,ad4020 + - adi,adaq4001 + - adi,adaq4003 + - adi,ad7687 + - adi,ad7691 + - adi,ad7942 + - adi,ad7946 + - adi,ad7983 - items: - enum: - adi,ad4004 - adi,ad4008 - const: adi,ad4000 - - - const: adi,ad4001 - items: - enum: - adi,ad4005 - const: adi,ad4001 - - - const: adi,ad4002 - items: - enum: - adi,ad4006 - adi,ad4010 - const: adi,ad4002 - - - const: adi,ad4003 - items: - enum: - adi,ad4007 - adi,ad4011 - const: adi,ad4003 - - - const: adi,ad4020 - items: - enum: - adi,ad4021 - adi,ad4022 - const: adi,ad4020 - - - const: adi,adaq4001 - - - const: adi,adaq4003 + - items: + - enum: + - adi,ad7685 + - adi,ad7686 + - adi,ad7980 + - adi,ad7988-1 + - adi,ad7988-5 + - const: adi,ad7983 + - items: + - enum: + - adi,ad7688 + - adi,ad7693 + - const: adi,ad7687 + - items: + - enum: + - adi,ad7690 + - adi,ad7982 + - adi,ad7984 + - const: adi,ad7691 reg: maxItems: 1 @@ -133,6 +166,22 @@ required: - ref-supply allOf: + # Single-channel PulSAR devices have SDI either tied to VIO, GND, or host CS. + - if: + properties: + compatible: + contains: + enum: + - adi,ad7687 + - adi,ad7691 + - adi,ad7942 + - adi,ad7946 + - adi,ad7983 + then: + properties: + adi,sdi-pin: + enum: [ high, low, cs ] + default: cs # The configuration register can only be accessed if SDI is connected to MOSI - if: required: diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml index 310f046e139f..7d2229dee444 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml @@ -134,8 +134,9 @@ patternProperties: description: Describes the common mode channel for single channels. 0xFF is REFGND and OxFE is COM. Macros are available for these values in - dt-bindings/iio/adi,ad4695.h. Values 1 to 15 correspond to INx inputs. - Only odd numbered INx inputs can be used as common mode channels. + dt-bindings/iio/adc/adi,ad4695.h. Values 1 to 15 correspond to INx + inputs. Only odd numbered INx inputs can be used as common mode + channels. enum: [1, 3, 5, 7, 9, 11, 13, 15, 0xFE, 0xFF] default: 0xFF @@ -209,7 +210,7 @@ unevaluatedProperties: false examples: - | #include - #include + #include spi { #address-cells = <1>; diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml index 35ed04350e28..7146a654ae38 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml @@ -37,6 +37,17 @@ properties: description: IRQ line for the ADC maxItems: 1 + rdy-gpios: + description: + GPIO reading the R̅D̅Y̅ line. Having such a GPIO is technically optional but + highly recommended because DOUT/R̅D̅Y̅ toggles during SPI transfers (in its + DOUT aka MISO role) and so usually triggers a spurious interrupt. The + distinction between such a spurious event and a real one can only be done + by reading such a GPIO. (There is a register telling the same + information, but accessing that one needs a SPI transfer which then + triggers another interrupt event.) + maxItems: 1 + '#address-cells': const: 1 @@ -111,6 +122,7 @@ unevaluatedProperties: false examples: - | + #include spi { #address-cells = <1>; #size-cells = <0>; @@ -121,6 +133,7 @@ examples: spi-max-frequency = <5000000>; interrupts = <25 2>; interrupt-parent = <&gpio>; + rdy-gpios = <&gpio 25 GPIO_ACTIVE_LOW>; refin1-supply = <&adc_vref>; clocks = <&ad7124_mclk>; clock-names = "mclk"; diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7173.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7173.yaml index ad15cf9bc2ff..21ee319d4675 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7173.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7173.yaml @@ -135,6 +135,17 @@ properties: '#clock-cells': const: 0 + rdy-gpios: + description: + GPIO reading the R̅D̅Y̅ line. Having such a GPIO is technically optional but + highly recommended because DOUT/R̅D̅Y̅ toggles during SPI transfers (in its + DOUT aka MISO role) and so usually triggers a spurious interrupt. The + distinction between such a spurious event and a real one can only be done + by reading such a GPIO. (There is a register telling the same + information, but accessing that one needs a SPI transfer which then + triggers another interrupt event.) + maxItems: 1 + patternProperties: "^channel@[0-9a-f]$": type: object @@ -443,6 +454,7 @@ examples: interrupts = <25 IRQ_TYPE_EDGE_FALLING>; interrupt-names = "rdy"; interrupt-parent = <&gpio>; + rdy-gpios = <&gpio 25 GPIO_ACTIVE_LOW>; spi-max-frequency = <5000000>; gpio-controller; #gpio-cells = <2>; diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml index 66dd1c549bd3..0bd2c6906c83 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml @@ -106,6 +106,17 @@ properties: description: see Documentation/devicetree/bindings/iio/adc/adc.yaml type: boolean + rdy-gpios: + description: + GPIO reading the R̅D̅Y̅ line. Having such a GPIO is technically optional but + highly recommended because DOUT/R̅D̅Y̅ toggles during SPI transfers (in its + DOUT aka MISO role) and so usually triggers a spurious interrupt. The + distinction between such a spurious event and a real one can only be done + by reading such a GPIO. (There is a register telling the same + information, but accessing that one needs a SPI transfer which then + triggers another interrupt event.) + maxItems: 1 + patternProperties: "^channel@[0-9a-f]+$": type: object @@ -181,6 +192,7 @@ unevaluatedProperties: false examples: - | + #include spi { #address-cells = <1>; #size-cells = <0>; @@ -195,6 +207,7 @@ examples: clock-names = "mclk"; interrupts = <25 0x2>; interrupt-parent = <&gpio>; + rdy-gpios = <&gpio 25 GPIO_ACTIVE_LOW>; aincom-supply = <&aincom>; dvdd-supply = <&dvdd>; avdd-supply = <&avdd>; @@ -207,6 +220,7 @@ examples: }; }; - | + #include spi { #address-cells = <1>; #size-cells = <0>; @@ -224,6 +238,7 @@ examples: #clock-cells = <0>; interrupts = <25 0x2>; interrupt-parent = <&gpio>; + rdy-gpios = <&gpio 25 GPIO_ACTIVE_LOW>; aincom-supply = <&aincom>; dvdd-supply = <&dvdd>; avdd-supply = <&avdd>; diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml index be2616ff9af6..5c8df45bfab0 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml @@ -63,6 +63,17 @@ properties: marked GPIO_ACTIVE_LOW. maxItems: 1 + rdy-gpios: + description: + GPIO reading the R̅D̅Y̅ line. Having such a GPIO is technically optional but + highly recommended because DOUT/R̅D̅Y̅ toggles during SPI transfers (in its + DOUT aka MISO role) and so usually triggers a spurious interrupt. The + distinction between such a spurious event and a real one can only be done + by reading such a GPIO. (There is a register telling the same + information, but accessing that one needs a SPI transfer which then + triggers another interrupt event.) + maxItems: 1 + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/iio/adc/renesas,rzg2l-adc.yaml b/Documentation/devicetree/bindings/iio/adc/renesas,rzg2l-adc.yaml index ba86c7b7d622..40341d541726 100644 --- a/Documentation/devicetree/bindings/iio/adc/renesas,rzg2l-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/renesas,rzg2l-adc.yaml @@ -17,12 +17,15 @@ description: | properties: compatible: - items: - - enum: - - renesas,r9a07g043-adc # RZ/G2UL and RZ/Five - - renesas,r9a07g044-adc # RZ/G2L - - renesas,r9a07g054-adc # RZ/V2L - - const: renesas,rzg2l-adc + oneOf: + - items: + - enum: + - renesas,r9a07g043-adc # RZ/G2UL and RZ/Five + - renesas,r9a07g044-adc # RZ/G2L + - renesas,r9a07g054-adc # RZ/V2L + - const: renesas,rzg2l-adc + - items: + - const: renesas,r9a08g045-adc # RZ/G3S reg: maxItems: 1 @@ -57,6 +60,9 @@ properties: '#size-cells': const: 0 + "#io-channel-cells": + const: 1 + required: - compatible - reg @@ -68,7 +74,7 @@ required: - reset-names patternProperties: - "^channel@[0-7]$": + "^channel@[0-8]$": $ref: adc.yaml type: object description: | @@ -78,6 +84,8 @@ patternProperties: reg: description: | The channel number. + minimum: 0 + maximum: 8 required: - reg @@ -92,18 +100,25 @@ allOf: const: renesas,r9a07g043-adc then: patternProperties: - "^channel@[2-7]$": false + "^channel@[2-8]$": false "^channel@[0-1]$": properties: reg: - minimum: 0 maximum: 1 - else: + + - if: + properties: + compatible: + contains: + enum: + - renesas,r9a07g044-adc + - renesas,r9a07g054-adc + then: patternProperties: + "^channel@[8]$": false "^channel@[0-7]$": properties: reg: - minimum: 0 maximum: 7 additionalProperties: false diff --git a/Documentation/devicetree/bindings/iio/chemical/bosch,bme680.yaml b/Documentation/devicetree/bindings/iio/chemical/bosch,bme680.yaml new file mode 100644 index 000000000000..fe98ec44f081 --- /dev/null +++ b/Documentation/devicetree/bindings/iio/chemical/bosch,bme680.yaml @@ -0,0 +1,62 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/iio/chemical/bosch,bme680.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Bosch BME680 Gas sensor + +maintainers: + - Vasileios Amoiridis + +description: > + BME680 is a gas sensor which combines relative humidity, barometric pressure, + ambient temperature and gas (VOC - Volatile Organic Compounds) measurements. + + https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bme680-ds001.pdf + +properties: + compatible: + const: bosch,bme680 + + reg: + maxItems: 1 + + vdd-supply: true + vddio-supply: true + +required: + - compatible + - reg + +allOf: + - $ref: /schemas/spi/spi-peripheral-props.yaml# + +unevaluatedProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + co2-sensor@77 { + compatible = "bosch,bme680"; + reg = <0x77>; + vddio-supply = <&vddio>; + vdd-supply = <&vdd>; + }; + }; + - | + spi { + #address-cells = <1>; + #size-cells = <0>; + + co2-sensor@0 { + compatible = "bosch,bme680"; + reg = <0>; + spi-max-frequency = <500000>; + vddio-supply = <&vddio>; + vdd-supply = <&vdd>; + }; + }; diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml index 79cb4b78a88a..2bd89e0aa46b 100644 --- a/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml @@ -91,7 +91,7 @@ examples: vrefn-supply = <&dac_vrefn>; reset-gpios = <&gpio_bd 16 GPIO_ACTIVE_LOW>; clear-gpios = <&gpio_bd 17 GPIO_ACTIVE_LOW>; - ldac-gpios = <&gpio_bd 18 GPIO_ACTIVE_HIGH>; + ldac-gpios = <&gpio_bd 18 GPIO_ACTIVE_LOW>; }; }; ... diff --git a/Documentation/devicetree/bindings/iio/dac/rohm,bd79703.yaml b/Documentation/devicetree/bindings/iio/dac/rohm,bd79703.yaml new file mode 100644 index 000000000000..941a49c93943 --- /dev/null +++ b/Documentation/devicetree/bindings/iio/dac/rohm,bd79703.yaml @@ -0,0 +1,62 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +# Copyright 2024 ROHM Semiconductor. +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/iio/dac/rohm,bd79703.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ROHM BD79703 DAC device driver + +maintainers: + - Matti Vaittinen + +description: | + The ROHM BD79703 is a 6 channel, 8-bit DAC. + Datasheet can be found here: + https://fscdn.rohm.com/en/products/databook/datasheet/ic/data_converter/dac/bd79702fv-lb_bd79703fv-lb-e.pdf + +properties: + compatible: + const: rohm,bd79703 + + reg: + maxItems: 1 + + spi-max-frequency: + maximum: 30000000 + + vfs-supply: + description: + The regulator to use as a full scale voltage. The voltage should be between 2.7V .. VCC + + vcc-supply: + description: + The regulator supplying the operating voltage. Should be between 2.7V ... 5.5V + +required: + - compatible + - reg + - spi-max-frequency + - vfs-supply + - vcc-supply + +allOf: + - $ref: /schemas/spi/spi-peripheral-props.yaml# + +additionalProperties: false + +examples: + - | + spi { + #address-cells = <1>; + #size-cells = <0>; + + dac@0 { + compatible = "rohm,bd79703"; + reg = <0>; + spi-max-frequency = <30000000>; + vcc-supply = <&vcc>; + vfs-supply = <&vref>; + }; + }; +... diff --git a/Documentation/devicetree/bindings/iio/imu/adi,adis16480.yaml b/Documentation/devicetree/bindings/iio/imu/adi,adis16480.yaml index e3eec38897bf..7a1a74fec281 100644 --- a/Documentation/devicetree/bindings/iio/imu/adi,adis16480.yaml +++ b/Documentation/devicetree/bindings/iio/imu/adi,adis16480.yaml @@ -11,24 +11,30 @@ maintainers: properties: compatible: - enum: - - adi,adis16375 - - adi,adis16480 - - adi,adis16485 - - adi,adis16488 - - adi,adis16490 - - adi,adis16495-1 - - adi,adis16495-2 - - adi,adis16495-3 - - adi,adis16497-1 - - adi,adis16497-2 - - adi,adis16497-3 - - adi,adis16545-1 - - adi,adis16545-2 - - adi,adis16545-3 - - adi,adis16547-1 - - adi,adis16547-2 - - adi,adis16547-3 + oneOf: + - enum: + - adi,adis16375 + - adi,adis16480 + - adi,adis16485 + - adi,adis16486 + - adi,adis16488 + - adi,adis16489 + - adi,adis16490 + - adi,adis16495-1 + - adi,adis16495-2 + - adi,adis16495-3 + - adi,adis16497-1 + - adi,adis16497-2 + - adi,adis16497-3 + - adi,adis16545-1 + - adi,adis16545-2 + - adi,adis16545-3 + - adi,adis16547-1 + - adi,adis16547-2 + - adi,adis16547-3 + - items: + - const: adi,adis16487 + - const: adi,adis16485 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/iio/imu/bosch,bmi160.yaml b/Documentation/devicetree/bindings/iio/imu/bosch,bmi160.yaml index 3b0a2d8b2e91..2cf8a0c7eb4c 100644 --- a/Documentation/devicetree/bindings/iio/imu/bosch,bmi160.yaml +++ b/Documentation/devicetree/bindings/iio/imu/bosch,bmi160.yaml @@ -37,6 +37,7 @@ properties: to "INT2" if INT2 pin should be used instead drive-open-drain: + type: boolean description: | set if the specified interrupt pin should be configured as open drain. If not set, defaults to push-pull. diff --git a/Documentation/devicetree/bindings/iio/imu/bosch,bmi270.yaml b/Documentation/devicetree/bindings/iio/imu/bosch,bmi270.yaml index 7b0cde1c9b0a..860a6c1fea3c 100644 --- a/Documentation/devicetree/bindings/iio/imu/bosch,bmi270.yaml +++ b/Documentation/devicetree/bindings/iio/imu/bosch,bmi270.yaml @@ -41,6 +41,7 @@ properties: - INT2 drive-open-drain: + type: boolean description: set if the specified interrupt pins should be configured as open drain. If not set, defaults to push-pull. diff --git a/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml b/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml index 64ef26e19669..7bf8294a8f2e 100644 --- a/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml +++ b/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml @@ -38,6 +38,7 @@ properties: - INT2 drive-open-drain: + type: boolean description: set if the specified interrupt pin should be configured as open drain. If not set, defaults to push-pull. diff --git a/Documentation/devicetree/bindings/iio/imu/invensense,mpu6050.yaml b/Documentation/devicetree/bindings/iio/imu/invensense,mpu6050.yaml index f91954870a44..0bce71529e34 100644 --- a/Documentation/devicetree/bindings/iio/imu/invensense,mpu6050.yaml +++ b/Documentation/devicetree/bindings/iio/imu/invensense,mpu6050.yaml @@ -16,6 +16,7 @@ properties: compatible: oneOf: - enum: + - invensense,iam20380 - invensense,iam20680 - invensense,icm20608 - invensense,icm20609 diff --git a/Documentation/devicetree/bindings/iio/light/rohm,bu27008.yaml b/Documentation/devicetree/bindings/iio/light/rohm,bu27008.yaml deleted file mode 100644 index 4f66fd47b016..000000000000 --- a/Documentation/devicetree/bindings/iio/light/rohm,bu27008.yaml +++ /dev/null @@ -1,49 +0,0 @@ -# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/iio/light/rohm,bu27008.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: ROHM BU27008 color sensor - -maintainers: - - Matti Vaittinen - -description: - The ROHM BU27008 is a sensor with 5 photodiodes (red, green, blue, clear - and IR) with four configurable channels. Red and green being always - available and two out of the rest three (blue, clear, IR) can be - selected to be simultaneously measured. Typical application is adjusting - LCD backlight of TVs, mobile phones and tablet PCs. - -properties: - compatible: - const: rohm,bu27008 - - reg: - maxItems: 1 - - interrupts: - maxItems: 1 - - vdd-supply: true - -required: - - compatible - - reg - -additionalProperties: false - -examples: - - | - i2c { - #address-cells = <1>; - #size-cells = <0>; - - light-sensor@38 { - compatible = "rohm,bu27008"; - reg = <0x38>; - }; - }; - -... diff --git a/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml b/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml deleted file mode 100644 index bed42d5d0d94..000000000000 --- a/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml +++ /dev/null @@ -1,50 +0,0 @@ -# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/iio/light/rohm,bu27010.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: ROHM BU27010 color sensor - -maintainers: - - Matti Vaittinen - -description: | - The ROHM BU27010 is a sensor with 6 photodiodes (red, green, blue, clear, - IR and flickering detection) with five configurable channels. Red, green - and flickering detection being always available and two out of the rest - three (blue, clear, IR) can be selected to be simultaneously measured. - Typical application is adjusting LCD/OLED backlight of TVs, mobile phones - and tablet PCs. - -properties: - compatible: - const: rohm,bu27010 - - reg: - maxItems: 1 - - interrupts: - maxItems: 1 - - vdd-supply: true - -required: - - compatible - - reg - - vdd-supply - -additionalProperties: false - -examples: - - | - i2c { - #address-cells = <1>; - #size-cells = <0>; - - light-sensor@38 { - compatible = "rohm,bu27010"; - reg = <0x38>; - vdd-supply = <&vdd>; - }; - }; diff --git a/Documentation/devicetree/bindings/iio/light/ti,opt4060.yaml b/Documentation/devicetree/bindings/iio/light/ti,opt4060.yaml new file mode 100644 index 000000000000..568fb2a9b7a3 --- /dev/null +++ b/Documentation/devicetree/bindings/iio/light/ti,opt4060.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/iio/light/ti,opt4060.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments OPT4060 RGBW Color Sensor + +maintainers: + - Per-Daniel Olsson + +description: + Texas Instrument RGBW high resolution color sensor over I2C. + https://www.ti.com/lit/gpn/opt4060 + +properties: + compatible: + enum: + - ti,opt4060 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + vdd-supply: true + +required: + - compatible + - reg + - vdd-supply + +additionalProperties: false + +examples: + - | + #include + i2c { + #address-cells = <1>; + #size-cells = <0>; + + light-sensor@44 { + compatible = "ti,opt4060"; + reg = <0x44>; + vdd-supply = <&vdd_reg>; + interrupt-parent = <&gpio5>; + interrupts = <13 IRQ_TYPE_EDGE_FALLING>; + }; + }; +... diff --git a/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml b/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml index cb201cecfa1a..706b7e24f182 100644 --- a/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml +++ b/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml @@ -55,12 +55,16 @@ properties: If not set, defaults to push-pull configuration. type: boolean + spi-max-frequency: + maximum: 10000000 + required: - compatible - vddd-supply - vdda-supply allOf: + - $ref: /schemas/spi/spi-peripheral-props.yaml# - if: properties: compatible: @@ -73,6 +77,16 @@ allOf: then: properties: interrupts: false + - if: + properties: + compatible: + contains: + enum: + - bosch,bmp085 + - bosch,bmp180 + then: + properties: + spi-max-frequency: false additionalProperties: false @@ -93,3 +107,18 @@ examples: vdda-supply = <&bar>; }; }; + - | + # include + # include + spi { + #address-cells = <1>; + #size-cells = <0>; + pressure@0 { + compatible = "bosch,bmp280"; + reg = <0>; + spi-max-frequency = <10000000>; + reset-gpios = <&gpio0 26 GPIO_ACTIVE_LOW>; + vddd-supply = <&foo>; + vdda-supply = <&bar>; + }; + }; diff --git a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml index 71c1ee33a393..e955eb8e8797 100644 --- a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml +++ b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml @@ -65,6 +65,7 @@ properties: - st,lsm9ds0-gyro - description: STMicroelectronics Magnetometers enum: + - st,iis2mdc - st,lis2mdl - st,lis3mdl-magn - st,lsm303agr-magn diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml index 47aac8794b68..517a4ac1bea3 100644 --- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml +++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml @@ -26,6 +26,9 @@ properties: - items: - enum: - mediatek,mt6873-keypad + - mediatek,mt8183-keypad + - mediatek,mt8365-keypad + - mediatek,mt8516-keypad - const: mediatek,mt6779-keypad reg: diff --git a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml index 60f09caa0e4c..b95435bd6a9b 100644 --- a/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml +++ b/Documentation/devicetree/bindings/input/mediatek,pmic-keys.yaml @@ -25,6 +25,7 @@ properties: compatible: enum: - mediatek,mt6323-keys + - mediatek,mt6328-keys - mediatek,mt6331-keys - mediatek,mt6357-keys - mediatek,mt6358-keys diff --git a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml index 251410aabf38..83bcf0575cd3 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml @@ -26,6 +26,7 @@ properties: - items: - enum: - qcom,qcm2290-cpu-bwmon + - qcom,qcs615-cpu-bwmon - qcom,qcs8300-cpu-bwmon - qcom,sa8775p-cpu-bwmon - qcom,sc7180-cpu-bwmon @@ -37,10 +38,12 @@ properties: - qcom,sm8250-cpu-bwmon - qcom,sm8550-cpu-bwmon - qcom,sm8650-cpu-bwmon + - qcom,sm8750-cpu-bwmon - qcom,x1e80100-cpu-bwmon - const: qcom,sdm845-bwmon # BWMON v4, unified register space - items: - enum: + - qcom,qcs615-llcc-bwmon - qcom,qcs8300-llcc-bwmon - qcom,sa8775p-llcc-bwmon - qcom,sc7180-llcc-bwmon diff --git a/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml b/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml index 21dae0b92819..4ac0863205b3 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml @@ -33,6 +33,7 @@ properties: - qcom,sm6375-cpucp-l3 - qcom,sm8250-epss-l3 - qcom,sm8350-epss-l3 + - qcom,sm8650-epss-l3 - const: qcom,epss-l3 reg: diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sm8750-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sm8750-rpmh.yaml new file mode 100644 index 000000000000..a816acc301e1 --- /dev/null +++ b/Documentation/devicetree/bindings/interconnect/qcom,sm8750-rpmh.yaml @@ -0,0 +1,136 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/interconnect/qcom,sm8750-rpmh.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm RPMh Network-On-Chip Interconnect on SM8750 + +maintainers: + - Abel Vesa + - Neil Armstrong + +description: | + RPMh interconnect providers support system bandwidth requirements through + RPMh hardware accelerators known as Bus Clock Manager (BCM). The provider is + able to communicate with the BCM through the Resource State Coordinator (RSC) + associated with each execution environment. Provider nodes must point to at + least one RPMh device child node pertaining to their RSC and each provider + can map to multiple RPMh resources. + + See also:: include/dt-bindings/interconnect/qcom,sm8750-rpmh.h + +properties: + compatible: + enum: + - qcom,sm8750-aggre1-noc + - qcom,sm8750-aggre2-noc + - qcom,sm8750-clk-virt + - qcom,sm8750-cnoc-main + - qcom,sm8750-config-noc + - qcom,sm8750-gem-noc + - qcom,sm8750-lpass-ag-noc + - qcom,sm8750-lpass-lpiaon-noc + - qcom,sm8750-lpass-lpicx-noc + - qcom,sm8750-mc-virt + - qcom,sm8750-mmss-noc + - qcom,sm8750-nsp-noc + - qcom,sm8750-pcie-anoc + - qcom,sm8750-system-noc + + reg: + maxItems: 1 + + clocks: + minItems: 1 + maxItems: 2 + +required: + - compatible + +allOf: + - $ref: qcom,rpmh-common.yaml# + - if: + properties: + compatible: + contains: + enum: + - qcom,sm8750-clk-virt + - qcom,sm8750-mc-virt + then: + properties: + reg: false + else: + required: + - reg + + - if: + properties: + compatible: + contains: + enum: + - qcom,sm8750-pcie-anoc + then: + properties: + clocks: + items: + - description: aggre-NOC PCIe AXI clock + - description: cfg-NOC PCIe a-NOC AHB clock + + - if: + properties: + compatible: + contains: + enum: + - qcom,sm8750-aggre1-noc + then: + properties: + clocks: + items: + - description: aggre UFS PHY AXI clock + - description: aggre USB3 PRIM AXI clock + + - if: + properties: + compatible: + contains: + enum: + - qcom,sm8750-aggre2-noc + then: + properties: + clocks: + items: + - description: RPMH CC IPA clock + + - if: + properties: + compatible: + contains: + enum: + - qcom,sm8750-aggre1-noc + - qcom,sm8750-aggre2-noc + - qcom,sm8750-pcie-anoc + then: + required: + - clocks + else: + properties: + clocks: false + +unevaluatedProperties: false + +examples: + - | + clk_virt: interconnect-0 { + compatible = "qcom,sm8750-clk-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + aggre1_noc: interconnect@16e0000 { + compatible = "qcom,sm8750-aggre1-noc"; + reg = <0x016e0000 0x16400>; + #interconnect-cells = <2>; + clocks = <&gcc_phy_axi_clk>, <&gcc_prim_axi_clk>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.yaml index a2846e493497..7173c4b5a228 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.yaml @@ -110,8 +110,8 @@ properties: interrupts: description: Interrupt source of the parent interrupt controller on - secondary GICs, or VGIC maintenance interrupt on primary GIC (see - below). + secondary GICs, or VGIC maintenance interrupt on primary GIC (see "GICv2 + with virtualization extensions" paragraph in the "reg" property). maxItems: 1 cpu-offset: diff --git a/Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2400-vic.yaml b/Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2400-vic.yaml index 73e8b9a39bd7..86516cd44b9d 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2400-vic.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2400-vic.yaml @@ -52,11 +52,11 @@ additionalProperties: false examples: - | interrupt-controller@1e6c0080 { - compatible = "aspeed,ast2400-vic"; - reg = <0x1e6c0080 0x80>; - interrupt-controller; - #interrupt-cells = <1>; - valid-sources = <0xffffffff 0x0007ffff>; + compatible = "aspeed,ast2400-vic"; + reg = <0x1e6c0080 0x80>; + interrupt-controller; + #interrupt-cells = <1>; + valid-sources = <0xffffffff 0x0007ffff>; }; ... diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.yaml b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.yaml index 786f2426399b..0fcbe304cd05 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.yaml @@ -130,23 +130,23 @@ required: examples: - | irq0_intc: interrupt-controller@f0406800 { - compatible = "brcm,bcm7120-l2-intc"; - interrupt-parent = <&intc>; - #interrupt-cells = <1>; - reg = <0xf0406800 0x8>; - interrupt-controller; - interrupts = <0x0 0x42 0x0>, <0x0 0x40 0x0>; - brcm,int-map-mask = <0xeb8>, <0x140>; - brcm,int-fwd-mask = <0x7>; + compatible = "brcm,bcm7120-l2-intc"; + interrupt-parent = <&intc>; + #interrupt-cells = <1>; + reg = <0xf0406800 0x8>; + interrupt-controller; + interrupts = <0x0 0x42 0x0>, <0x0 0x40 0x0>; + brcm,int-map-mask = <0xeb8>, <0x140>; + brcm,int-fwd-mask = <0x7>; }; - | irq1_intc: interrupt-controller@10000020 { - compatible = "brcm,bcm3380-l2-intc"; - reg = <0x10000024 0x4>, <0x1000002c 0x4>, - <0x10000020 0x4>, <0x10000028 0x4>; - interrupt-controller; - #interrupt-cells = <1>; - interrupt-parent = <&cpu_intc>; - interrupts = <2>; + compatible = "brcm,bcm3380-l2-intc"; + reg = <0x10000024 0x4>, <0x1000002c 0x4>, + <0x10000020 0x4>, <0x10000028 0x4>; + interrupt-controller; + #interrupt-cells = <1>; + interrupt-parent = <&cpu_intc>; + interrupts = <2>; }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml index a54da66a89e7..f06b40f88778 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.yaml @@ -26,6 +26,8 @@ properties: compatible: items: - enum: + - qcom,qcs615-pdc + - qcom,qcs8300-pdc - qcom,qdu1000-pdc - qcom,sa8255p-pdc - qcom,sa8775p-pdc @@ -47,6 +49,7 @@ properties: - qcom,sm8450-pdc - qcom,sm8550-pdc - qcom,sm8650-pdc + - qcom,sm8750-pdc - qcom,x1e80100-pdc - const: qcom,pdc diff --git a/Documentation/devicetree/bindings/interrupt-controller/riscv,imsics.yaml b/Documentation/devicetree/bindings/interrupt-controller/riscv,imsics.yaml index 84976f17a4a1..c23b5c09fdb9 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/riscv,imsics.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/riscv,imsics.yaml @@ -142,7 +142,7 @@ examples: <&cpu2_intc 11>, <&cpu3_intc 11>, <&cpu4_intc 11>; - reg = <0x28000000 0x4000>; + reg = <0x24000000 0x4000>; interrupt-controller; #interrupt-cells = <0>; msi-controller; diff --git a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml index 7e1451f9786a..3dfe425909d1 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml @@ -59,6 +59,7 @@ properties: - enum: - canaan,k210-plic - sifive,fu540-c000-plic + - spacemit,k1-plic - starfive,jh7100-plic - starfive,jh7110-plic - const: sifive,plic-1.0.0 diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu b/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu.txt similarity index 100% rename from Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu rename to Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu.txt diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index c1e11bc6b7a0..032fdc27127b 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -61,6 +61,7 @@ properties: - qcom,sm8450-smmu-500 - qcom,sm8550-smmu-500 - qcom,sm8650-smmu-500 + - qcom,sm8750-smmu-500 - qcom,x1e80100-smmu-500 - const: qcom,smmu-500 - const: arm,mmu-500 @@ -88,6 +89,7 @@ properties: items: - enum: - qcom,qcm2290-smmu-500 + - qcom,qcs615-smmu-500 - qcom,sa8255p-smmu-500 - qcom,sa8775p-smmu-500 - qcom,sar2130p-smmu-500 @@ -102,6 +104,7 @@ properties: - qcom,sm8450-smmu-500 - qcom,sm8550-smmu-500 - qcom,sm8650-smmu-500 + - qcom,sm8750-smmu-500 - qcom,x1e80100-smmu-500 - const: qcom,adreno-smmu - const: qcom,smmu-500 @@ -122,6 +125,7 @@ properties: - qcom,msm8996-smmu-v2 - qcom,sc7180-smmu-v2 - qcom,sdm630-smmu-v2 + - qcom,sdm670-smmu-v2 - qcom,sdm845-smmu-v2 - qcom,sm6350-smmu-v2 - qcom,sm7150-smmu-v2 @@ -474,6 +478,7 @@ allOf: items: - enum: - qcom,qcm2290-smmu-500 + - qcom,qcs615-smmu-500 - qcom,sm6115-smmu-500 - qcom,sm6125-smmu-500 - const: qcom,adreno-smmu @@ -550,6 +555,23 @@ allOf: - description: GPU SNoC bus clock - description: GPU AHB clock + - if: + properties: + compatible: + items: + - const: qcom,sm8750-smmu-500 + - const: qcom,adreno-smmu + - const: qcom,smmu-500 + - const: arm,mmu-500 + then: + properties: + clock-names: + items: + - const: hlos + clocks: + items: + - description: HLOS vote clock + # Disallow clocks for all other platforms with specific compatibles - if: properties: @@ -559,7 +581,6 @@ allOf: - cavium,smmu-v2 - marvell,ap806-smmu-500 - nvidia,smmu-500 - - qcom,qcs615-smmu-500 - qcom,qcs8300-smmu-500 - qcom,qdu1000-smmu-500 - qcom,sa8255p-smmu-500 diff --git a/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml b/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml index f8cebc9e8cd9..5ae9a628261f 100644 --- a/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml @@ -21,6 +21,7 @@ properties: - items: - enum: - qcom,msm8916-iommu + - qcom,msm8917-iommu - qcom,msm8953-iommu - const: qcom,msm-iommu-v1 - items: diff --git a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml index 621dde0e45d8..6ce41d11ff5e 100644 --- a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml @@ -25,6 +25,7 @@ properties: - rockchip,rk3568-iommu - items: - enum: + - rockchip,rk3576-iommu - rockchip,rk3588-iommu - const: rockchip,rk3568-iommu diff --git a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml index 34ef5215c150..f52f6304c79e 100644 --- a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml +++ b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml @@ -23,6 +23,12 @@ properties: description: I2C slave address of the microcontroller. maxItems: 1 + interrupts: + description: + Specifier for the global LED brightness changed by front button press + interrupt. + maxItems: 1 + "#address-cells": const: 1 @@ -56,6 +62,7 @@ additionalProperties: false examples: - | + #include #include i2c { @@ -65,6 +72,7 @@ examples: led-controller@2b { compatible = "cznic,turris-omnia-leds"; reg = <0x2b>; + interrupts-extended = <&mcu 11 IRQ_TYPE_NONE>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/leds/leds-class-multicolor.yaml b/Documentation/devicetree/bindings/leds/leds-class-multicolor.yaml index e850a8894758..bb40bb9e036e 100644 --- a/Documentation/devicetree/bindings/leds/leds-class-multicolor.yaml +++ b/Documentation/devicetree/bindings/leds/leds-class-multicolor.yaml @@ -27,7 +27,7 @@ properties: description: | For multicolor LED support this property should be defined as either LED_COLOR_ID_RGB or LED_COLOR_ID_MULTI which can be found in - include/linux/leds/common.h. + include/dt-bindings/leds/common.h. enum: [ 8, 9 ] required: diff --git a/Documentation/devicetree/bindings/leds/leds-lp8860.txt b/Documentation/devicetree/bindings/leds/leds-lp8860.txt deleted file mode 100644 index 8bb25749a3da..000000000000 --- a/Documentation/devicetree/bindings/leds/leds-lp8860.txt +++ /dev/null @@ -1,50 +0,0 @@ -* Texas Instruments - lp8860 4-Channel LED Driver - -The LP8860-Q1 is an high-efficiency LED -driver with boost controller. It has 4 high-precision -current sinks that can be controlled by a PWM input -signal, a SPI/I2C master, or both. - -Required properties: - - compatible : - "ti,lp8860" - - reg : I2C slave address - - #address-cells : 1 - - #size-cells : 0 - -Optional properties: - - enable-gpios : gpio pin to enable (active high)/disable the device. - - vled-supply : LED supply - -Required child properties: - - reg : 0 - -Optional child properties: - - function : see Documentation/devicetree/bindings/leds/common.txt - - color : see Documentation/devicetree/bindings/leds/common.txt - - label : see Documentation/devicetree/bindings/leds/common.txt (deprecated) - - linux,default-trigger : - see Documentation/devicetree/bindings/leds/common.txt - -Example: - -#include - -led-controller@2d { - compatible = "ti,lp8860"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0x2d>; - enable-gpios = <&gpio1 28 GPIO_ACTIVE_HIGH>; - vled-supply = <&vbatt>; - - led@0 { - reg = <0>; - function = LED_FUNCTION_BACKLIGHT; - color = ; - linux,default-trigger = "backlight"; - }; -} - -For more product information please see the link below: -https://www.ti.com/product/lp8860-q1 diff --git a/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml index 1ba607685f5f..bcf0ad4ea57e 100644 --- a/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml +++ b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml @@ -23,6 +23,7 @@ properties: items: - enum: - qcom,pm6150l-flash-led + - qcom,pm660l-flash-led - qcom,pm8150c-flash-led - qcom,pm8150l-flash-led - qcom,pm8350c-flash-led diff --git a/Documentation/devicetree/bindings/leds/st,led1202.yaml b/Documentation/devicetree/bindings/leds/st,led1202.yaml new file mode 100644 index 000000000000..f1e5e4efaa3a --- /dev/null +++ b/Documentation/devicetree/bindings/leds/st,led1202.yaml @@ -0,0 +1,132 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/leds/st,led1202.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ST LED1202 LED controllers + +maintainers: + - Vicentiu Galanopulo + +description: | + The LED1202 is a 12-channel low quiescent current LED controller + programmable via I2C; The output current can be adjusted separately + for each channel by 8-bit analog and 12-bit digital dimming control. + Datasheet available at + https://www.st.com/en/power-management/led1202.html + +properties: + compatible: + const: st,led1202 + + reg: + maxItems: 1 + + "#address-cells": + const: 1 + + "#size-cells": + const: 0 + +patternProperties: + "^led@[0-9a-f]$": + type: object + $ref: common.yaml# + unevaluatedProperties: false + + properties: + reg: + minimum: 0 + maximum: 11 + + required: + - reg + +required: + - compatible + - reg + - "#address-cells" + - "#size-cells" + +additionalProperties: false + +examples: + - | + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + led-controller@58 { + compatible = "st,led1202"; + reg = <0x58>; + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0x0>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <1>; + }; + + led@1 { + reg = <0x1>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <2>; + }; + + led@2 { + reg = <0x2>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <3>; + }; + + led@3 { + reg = <0x3>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <4>; + }; + + led@4 { + reg = <0x4>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <5>; + }; + + led@5 { + reg = <0x5>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <6>; + }; + + led@6 { + reg = <0x6>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <7>; + }; + + led@7 { + reg = <0x7>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <8>; + }; + + led@8 { + reg = <0x8>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <9>; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/leds/ti,lp8860.yaml b/Documentation/devicetree/bindings/leds/ti,lp8860.yaml new file mode 100644 index 000000000000..0ee357b02661 --- /dev/null +++ b/Documentation/devicetree/bindings/leds/ti,lp8860.yaml @@ -0,0 +1,90 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/leds/ti,lp8860.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments - lp8860 4-Channel LED Driver + +maintainers: + - Andrew Davis + +description: | + The LP8860-Q1 is an high-efficiency LED driver with boost controller. + It has 4 high-precision current sinks that can be controlled by a PWM input + signal, a SPI/I2C master, or both. + + For more product information please see the link below: + https://www.ti.com/product/lp8860-q1 + +properties: + compatible: + const: ti,lp8860 + + reg: + maxItems: 1 + description: I2C slave address + + "#address-cells": + const: 1 + + "#size-cells": + const: 0 + + enable-gpios: + maxItems: 1 + description: GPIO pin to enable (active high) / disable the device + + vled-supply: + description: LED supply + +patternProperties: + "^led(@[0-3])?$": + type: object + $ref: common.yaml# + unevaluatedProperties: false + + properties: + reg: + description: + Index of the LED. + maxItems: 1 + + function: true + color: true + label: true + linux,default-trigger: true + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + #include + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + led-controller@2d { + compatible = "ti,lp8860"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x2d>; + enable-gpios = <&gpio1 28 GPIO_ACTIVE_HIGH>; + vled-supply = <&vbatt>; + + led@0 { + reg = <0>; + function = LED_FUNCTION_BACKLIGHT; + color = ; + linux,default-trigger = "backlight"; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/mailbox/google,gs101-mbox.yaml b/Documentation/devicetree/bindings/mailbox/google,gs101-mbox.yaml new file mode 100644 index 000000000000..e249db4c1fbc --- /dev/null +++ b/Documentation/devicetree/bindings/mailbox/google,gs101-mbox.yaml @@ -0,0 +1,69 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Copyright 2024 Linaro Ltd. +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mailbox/google,gs101-mbox.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung Exynos Mailbox Controller + +maintainers: + - Tudor Ambarus + +description: + The Samsung Exynos mailbox controller, used on Google GS101 SoC, has 16 flag + bits for hardware interrupt generation and a shared register for passing + mailbox messages. When the controller is used by the ACPM interface + the shared register is ignored and the mailbox controller acts as a doorbell. + The controller just raises the interrupt to the firmware after the + ACPM interface has written the message to SRAM. + +properties: + compatible: + const: google,gs101-mbox + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + items: + - const: pclk + + interrupts: + description: IRQ line for the RX mailbox. + maxItems: 1 + + '#mbox-cells': + const: 0 + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + - '#mbox-cells' + +additionalProperties: false + +examples: + - | + #include + #include + + soc { + #address-cells = <1>; + #size-cells = <1>; + + ap2apm_mailbox: mailbox@17610000 { + compatible = "google,gs101-mbox"; + reg = <0x17610000 0x1000>; + clocks = <&cmu_apm CLK_GOUT_APM_MAILBOX_APM_AP_PCLK>; + clock-names = "pclk"; + interrupts = ; + #mbox-cells = <0>; + }; + }; diff --git a/Documentation/devicetree/bindings/mailbox/microchip,sbi-ipc.yaml b/Documentation/devicetree/bindings/mailbox/microchip,sbi-ipc.yaml new file mode 100644 index 000000000000..8ed67ea7c883 --- /dev/null +++ b/Documentation/devicetree/bindings/mailbox/microchip,sbi-ipc.yaml @@ -0,0 +1,123 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mailbox/microchip,sbi-ipc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip Inter-processor communication (IPC) mailbox controller + +maintainers: + - Valentina Fernandez + +description: + The Microchip Inter-processor Communication (IPC) facilitates + message passing between processors using an interrupt signaling + mechanism. + +properties: + compatible: + oneOf: + - description: + Intended for use by software running in supervisor privileged + mode (s-mode). This SBI interface is compatible with the Mi-V + Inter-hart Communication (IHC) IP. + const: microchip,sbi-ipc + + - description: + Intended for use by the SBI implementation in machine mode + (m-mode), this compatible string is for the MIV_IHC Soft-IP. + const: microchip,miv-ihc-rtl-v2 + + reg: + maxItems: 1 + + interrupts: + minItems: 1 + maxItems: 5 + + interrupt-names: + minItems: 1 + maxItems: 5 + items: + enum: + - hart-0 + - hart-1 + - hart-2 + - hart-3 + - hart-4 + - hart-5 + + "#mbox-cells": + description: > + For "microchip,sbi-ipc", the cell represents the global "logical" + channel IDs. The meaning of channel IDs are platform firmware dependent. + + For "microchip,miv-ihc-rtl-v2", the cell represents the physical + channel and does not vary based on the platform firmware. + const: 1 + + microchip,ihc-chan-disabled-mask: + description: > + Represents the enable/disable state of the bi-directional IHC + channels within the MIV-IHC IP configuration. + + A bit set to '1' indicates that the corresponding channel is disabled, + and any read or write operations to that channel will return zero. + + A bit set to '0' indicates that the corresponding channel is enabled + and will be accessible through its dedicated address range registers. + + The actual enable/disable state of each channel is determined by the + IP block’s configuration. + $ref: /schemas/types.yaml#/definitions/uint16 + maximum: 0x7fff + default: 0 + +required: + - compatible + - interrupts + - interrupt-names + - "#mbox-cells" + +allOf: + - if: + properties: + compatible: + contains: + const: microchip,sbi-ipc + then: + properties: + reg: + not: {} + description: + The 'microchip,sbi-ipc' operates in a programming model + that does not require memory-mapped I/O (MMIO) registers + since it uses SBI ecalls provided by the m-mode/firmware + SBI implementation to access hardware registers. + microchip,ihc-chan-disabled-mask: false + else: + required: + - reg + - microchip,ihc-chan-disabled-mask + +additionalProperties: false + +examples: + - | + mailbox { + compatible = "microchip,sbi-ipc"; + interrupt-parent = <&plic>; + interrupts = <180>, <179>, <178>; + interrupt-names = "hart-1", "hart-2", "hart-3"; + #mbox-cells = <1>; + }; + - | + mailbox@50000000 { + compatible = "microchip,miv-ihc-rtl-v2"; + microchip,ihc-chan-disabled-mask = /bits/ 16 <0>; + reg = <0x50000000 0x1c000>; + interrupt-parent = <&plic>; + interrupts = <180>, <179>, <178>; + interrupt-names = "hart-1", "hart-2", "hart-3"; + #mbox-cells = <1>; + }; diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml index 9d2dfd85b207..78f68dacd028 100644 --- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml +++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml @@ -20,6 +20,7 @@ properties: - enum: - qcom,ipq5018-apcs-apps-global - qcom,ipq5332-apcs-apps-global + - qcom,ipq5424-apcs-apps-global - qcom,ipq8074-apcs-apps-global - qcom,ipq9574-apcs-apps-global - const: qcom,ipq6018-apcs-apps-global @@ -44,6 +45,7 @@ properties: - const: qcom,msm8994-apcs-kpss-global - items: - enum: + - qcom,qcs615-apss-shared - qcom,sc7180-apss-shared - qcom,sc8180x-apss-shared - qcom,sm8150-apss-shared diff --git a/Documentation/devicetree/bindings/media/allwinner,sun50i-h6-vpu-g2.yaml b/Documentation/devicetree/bindings/media/allwinner,sun50i-h6-vpu-g2.yaml index a4f06bbdfe49..8ba5177ac631 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun50i-h6-vpu-g2.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun50i-h6-vpu-g2.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/allwinner,sun50i-h6-vpu-g2.yaml# diff --git a/Documentation/devicetree/bindings/media/amlogic,meson-ir-tx.yaml b/Documentation/devicetree/bindings/media/amlogic,meson-ir-tx.yaml index 377acce93423..6da8a6aded23 100644 --- a/Documentation/devicetree/bindings/media/amlogic,meson-ir-tx.yaml +++ b/Documentation/devicetree/bindings/media/amlogic,meson-ir-tx.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/amlogic,meson-ir-tx.yaml# diff --git a/Documentation/devicetree/bindings/media/amphion,vpu.yaml b/Documentation/devicetree/bindings/media/amphion,vpu.yaml index 9801de3ed84e..5a920d9e78c7 100644 --- a/Documentation/devicetree/bindings/media/amphion,vpu.yaml +++ b/Documentation/devicetree/bindings/media/amphion,vpu.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/amphion,vpu.yaml# diff --git a/Documentation/devicetree/bindings/media/fsl,imx6ull-pxp.yaml b/Documentation/devicetree/bindings/media/fsl,imx6ull-pxp.yaml index 84a5e894ace4..3f47744459aa 100644 --- a/Documentation/devicetree/bindings/media/fsl,imx6ull-pxp.yaml +++ b/Documentation/devicetree/bindings/media/fsl,imx6ull-pxp.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/fsl,imx6ull-pxp.yaml# diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx290.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx290.yaml index bf05ca48601a..fa69bd21c8da 100644 --- a/Documentation/devicetree/bindings/media/i2c/sony,imx290.yaml +++ b/Documentation/devicetree/bindings/media/i2c/sony,imx290.yaml @@ -33,6 +33,8 @@ properties: - sony,imx290lqr # Colour - sony,imx290llr # Monochrome - sony,imx327lqr # Colour + - sony,imx462lqr # Colour + - sony,imx462llr # Monochrome - const: sony,imx290 deprecated: true diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml index b401c67e3ba0..d726d141a434 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/mediatek,vcodec-decoder.yaml# diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml index b45743d0a9ec..110e8f5f1f9e 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/mediatek,vcodec-encoder.yaml# diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml index a500a585c692..5865e6f0be89 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/mediatek,vcodec-subdev-decoder.yaml# diff --git a/Documentation/devicetree/bindings/media/microchip,sama5d4-vdec.yaml b/Documentation/devicetree/bindings/media/microchip,sama5d4-vdec.yaml index 59b805ca47c5..ede086d55add 100644 --- a/Documentation/devicetree/bindings/media/microchip,sama5d4-vdec.yaml +++ b/Documentation/devicetree/bindings/media/microchip,sama5d4-vdec.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/microchip,sama5d4-vdec.yaml# @@ -36,12 +35,12 @@ additionalProperties: false examples: - | - #include - #include + #include + #include - vdec0: vdec@300000 { - compatible = "microchip,sama5d4-vdec"; - reg = <0x00300000 0x100000>; - interrupts = <19 IRQ_TYPE_LEVEL_HIGH 4>; - clocks = <&pmc PMC_TYPE_PERIPHERAL 19>; - }; + vdec@300000 { + compatible = "microchip,sama5d4-vdec"; + reg = <0x00300000 0x100000>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH 4>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 19>; + }; diff --git a/Documentation/devicetree/bindings/media/nxp,imx8-isi.yaml b/Documentation/devicetree/bindings/media/nxp,imx8-isi.yaml index 4d5348d456a1..f43b91984f01 100644 --- a/Documentation/devicetree/bindings/media/nxp,imx8-isi.yaml +++ b/Documentation/devicetree/bindings/media/nxp,imx8-isi.yaml @@ -21,6 +21,7 @@ properties: enum: - fsl,imx8mn-isi - fsl,imx8mp-isi + - fsl,imx8ulp-isi - fsl,imx93-isi reg: @@ -75,6 +76,7 @@ allOf: contains: enum: - fsl,imx8mn-isi + - fsl,imx8ulp-isi - fsl,imx93-isi then: properties: diff --git a/Documentation/devicetree/bindings/media/nxp,imx8mq-vpu.yaml b/Documentation/devicetree/bindings/media/nxp,imx8mq-vpu.yaml index 3d58f02b0c5d..19528262810a 100644 --- a/Documentation/devicetree/bindings/media/nxp,imx8mq-vpu.yaml +++ b/Documentation/devicetree/bindings/media/nxp,imx8mq-vpu.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/nxp,imx8mq-vpu.yaml# @@ -44,26 +43,26 @@ additionalProperties: false examples: - | - #include - #include - #include + #include + #include + #include - vpu_g1: video-codec@38300000 { - compatible = "nxp,imx8mq-vpu-g1"; - reg = <0x38300000 0x10000>; - interrupts = ; - clocks = <&clk IMX8MQ_CLK_VPU_G1_ROOT>; - power-domains = <&vpu_blk_ctrl IMX8MQ_VPUBLK_PD_G1>; - }; + video-codec@38300000 { + compatible = "nxp,imx8mq-vpu-g1"; + reg = <0x38300000 0x10000>; + interrupts = ; + clocks = <&clk IMX8MQ_CLK_VPU_G1_ROOT>; + power-domains = <&vpu_blk_ctrl IMX8MQ_VPUBLK_PD_G1>; + }; - | - #include - #include - #include + #include + #include + #include - vpu_g2: video-codec@38300000 { - compatible = "nxp,imx8mq-vpu-g2"; - reg = <0x38310000 0x10000>; - interrupts = ; - clocks = <&clk IMX8MQ_CLK_VPU_G2_ROOT>; - power-domains = <&vpu_blk_ctrl IMX8MQ_VPUBLK_PD_G2>; - }; + video-codec@38300000 { + compatible = "nxp,imx8mq-vpu-g2"; + reg = <0x38310000 0x10000>; + interrupts = ; + clocks = <&clk IMX8MQ_CLK_VPU_G2_ROOT>; + power-domains = <&vpu_blk_ctrl IMX8MQ_VPUBLK_PD_G2>; + }; diff --git a/Documentation/devicetree/bindings/media/qcom,msm8916-camss.yaml b/Documentation/devicetree/bindings/media/qcom,msm8916-camss.yaml index 9cc0a968a401..3469a43f00d4 100644 --- a/Documentation/devicetree/bindings/media/qcom,msm8916-camss.yaml +++ b/Documentation/devicetree/bindings/media/qcom,msm8916-camss.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/qcom,msm8916-camss.yaml# diff --git a/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml b/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml index 9410f13ca97c..da140c2e3d3f 100644 --- a/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml +++ b/Documentation/devicetree/bindings/media/qcom,msm8916-venus.yaml @@ -45,6 +45,7 @@ properties: required: - compatible + deprecated: true additionalProperties: false video-encoder: @@ -57,13 +58,12 @@ properties: required: - compatible + deprecated: true additionalProperties: false required: - compatible - iommus - - video-decoder - - video-encoder unevaluatedProperties: false @@ -83,12 +83,4 @@ examples: power-domains = <&gcc VENUS_GDSC>; iommus = <&apps_iommu 5>; memory-region = <&venus_mem>; - - video-decoder { - compatible = "venus-decoder"; - }; - - video-encoder { - compatible = "venus-encoder"; - }; }; diff --git a/Documentation/devicetree/bindings/media/qcom,msm8996-camss.yaml b/Documentation/devicetree/bindings/media/qcom,msm8996-camss.yaml index 5cb0e337ea6e..644646de338a 100644 --- a/Documentation/devicetree/bindings/media/qcom,msm8996-camss.yaml +++ b/Documentation/devicetree/bindings/media/qcom,msm8996-camss.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/qcom,msm8996-camss.yaml# diff --git a/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml b/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml index 5cec1d077cda..83c4a5d95f02 100644 --- a/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml +++ b/Documentation/devicetree/bindings/media/qcom,sc7180-venus.yaml @@ -70,6 +70,7 @@ properties: required: - compatible + deprecated: true additionalProperties: false video-encoder: @@ -82,14 +83,13 @@ properties: required: - compatible + deprecated: true additionalProperties: false required: - compatible - power-domain-names - iommus - - video-decoder - - video-encoder unevaluatedProperties: false @@ -114,12 +114,4 @@ examples: "vcodec0_core", "vcodec0_bus"; iommus = <&apps_smmu 0x0c00 0x60>; memory-region = <&venus_mem>; - - video-decoder { - compatible = "venus-decoder"; - }; - - video-encoder { - compatible = "venus-encoder"; - }; }; diff --git a/Documentation/devicetree/bindings/media/qcom,sc7280-camss.yaml b/Documentation/devicetree/bindings/media/qcom,sc7280-camss.yaml new file mode 100644 index 000000000000..e11141b812a0 --- /dev/null +++ b/Documentation/devicetree/bindings/media/qcom,sc7280-camss.yaml @@ -0,0 +1,425 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/media/qcom,sc7280-camss.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm SC7280 CAMSS ISP + +maintainers: + - Azam Sadiq Pasha Kapatrala Syed + - Hariram Purushothaman + +description: + The CAMSS IP is a CSI decoder and ISP present on Qualcomm platforms. + +properties: + compatible: + const: qcom,sc7280-camss + + reg: + maxItems: 15 + + reg-names: + items: + - const: csid0 + - const: csid1 + - const: csid2 + - const: csid_lite0 + - const: csid_lite1 + - const: csiphy0 + - const: csiphy1 + - const: csiphy2 + - const: csiphy3 + - const: csiphy4 + - const: vfe0 + - const: vfe1 + - const: vfe2 + - const: vfe_lite0 + - const: vfe_lite1 + + clocks: + maxItems: 33 + + clock-names: + items: + - const: camnoc_axi + - const: cpas_ahb + - const: csiphy0 + - const: csiphy0_timer + - const: csiphy1 + - const: csiphy1_timer + - const: csiphy2 + - const: csiphy2_timer + - const: csiphy3 + - const: csiphy3_timer + - const: csiphy4 + - const: csiphy4_timer + - const: gcc_camera_ahb + - const: gcc_cam_hf_axi + - const: icp_ahb + - const: vfe0 + - const: vfe0_axi + - const: vfe0_cphy_rx + - const: vfe0_csid + - const: vfe1 + - const: vfe1_axi + - const: vfe1_cphy_rx + - const: vfe1_csid + - const: vfe2 + - const: vfe2_axi + - const: vfe2_cphy_rx + - const: vfe2_csid + - const: vfe_lite0 + - const: vfe_lite0_cphy_rx + - const: vfe_lite0_csid + - const: vfe_lite1 + - const: vfe_lite1_cphy_rx + - const: vfe_lite1_csid + + interrupts: + maxItems: 15 + + interrupt-names: + items: + - const: csid0 + - const: csid1 + - const: csid2 + - const: csid_lite0 + - const: csid_lite1 + - const: csiphy0 + - const: csiphy1 + - const: csiphy2 + - const: csiphy3 + - const: csiphy4 + - const: vfe0 + - const: vfe1 + - const: vfe2 + - const: vfe_lite0 + - const: vfe_lite1 + + interconnects: + maxItems: 2 + + interconnect-names: + items: + - const: ahb + - const: hf_0 + + iommus: + maxItems: 1 + + power-domains: + items: + - description: IFE0 GDSC - Image Front End, Global Distributed Switch Controller. + - description: IFE1 GDSC - Image Front End, Global Distributed Switch Controller. + - description: IFE2 GDSC - Image Front End, Global Distributed Switch Controller. + - description: Titan GDSC - Titan ISP Block, Global Distributed Switch Controller. + + power-domain-names: + items: + - const: ife0 + - const: ife1 + - const: ife2 + - const: top + + vdda-phy-supply: + description: + Phandle to a regulator supply to PHY core block. + + vdda-pll-supply: + description: + Phandle to 1.8V regulator supply to PHY refclk pll block. + + ports: + $ref: /schemas/graph.yaml#/properties/ports + + description: + CSI input ports. + + properties: + port@0: + $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false + description: + Input port for receiving CSI data on CSIPHY 0. + + properties: + endpoint: + $ref: video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + minItems: 1 + maxItems: 4 + + required: + - data-lanes + + port@1: + $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false + description: + Input port for receiving CSI data on CSIPHY 1. + + properties: + endpoint: + $ref: video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + minItems: 1 + maxItems: 4 + + required: + - data-lanes + + port@2: + $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false + description: + Input port for receiving CSI data on CSIPHY 2. + + properties: + endpoint: + $ref: video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + minItems: 1 + maxItems: 4 + + required: + - data-lanes + + port@3: + $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false + description: + Input port for receiving CSI data on CSIPHY 3. + + properties: + endpoint: + $ref: video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + minItems: 1 + maxItems: 4 + + required: + - data-lanes + + port@4: + $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false + description: + Input port for receiving CSI data on CSIPHY 4. + + properties: + endpoint: + $ref: video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + minItems: 1 + maxItems: 4 + + required: + - data-lanes + +required: + - compatible + - reg + - reg-names + - clocks + - clock-names + - interrupts + - interrupt-names + - interconnects + - interconnect-names + - iommus + - power-domains + - power-domain-names + - vdda-phy-supply + - vdda-pll-supply + +additionalProperties: false + +examples: + - | + #include + #include + #include + #include + #include + #include + + soc { + #address-cells = <2>; + #size-cells = <2>; + + isp@acb3000 { + compatible = "qcom,sc7280-camss"; + + reg = <0x0 0x0acb3000 0x0 0x1000>, + <0x0 0x0acba000 0x0 0x1000>, + <0x0 0x0acc1000 0x0 0x1000>, + <0x0 0x0acc8000 0x0 0x1000>, + <0x0 0x0accf000 0x0 0x1000>, + <0x0 0x0ace0000 0x0 0x2000>, + <0x0 0x0ace2000 0x0 0x2000>, + <0x0 0x0ace4000 0x0 0x2000>, + <0x0 0x0ace6000 0x0 0x2000>, + <0x0 0x0ace8000 0x0 0x2000>, + <0x0 0x0acaf000 0x0 0x4000>, + <0x0 0x0acb6000 0x0 0x4000>, + <0x0 0x0acbd000 0x0 0x4000>, + <0x0 0x0acc4000 0x0 0x4000>, + <0x0 0x0accb000 0x0 0x4000>; + reg-names = "csid0", + "csid1", + "csid2", + "csid_lite0", + "csid_lite1", + "csiphy0", + "csiphy1", + "csiphy2", + "csiphy3", + "csiphy4", + "vfe0", + "vfe1", + "vfe2", + "vfe_lite0", + "vfe_lite1"; + + clocks = <&camcc CAM_CC_CAMNOC_AXI_CLK>, + <&camcc CAM_CC_CPAS_AHB_CLK>, + <&camcc CAM_CC_CSIPHY0_CLK>, + <&camcc CAM_CC_CSI0PHYTIMER_CLK>, + <&camcc CAM_CC_CSIPHY1_CLK>, + <&camcc CAM_CC_CSI1PHYTIMER_CLK>, + <&camcc CAM_CC_CSIPHY2_CLK>, + <&camcc CAM_CC_CSI2PHYTIMER_CLK>, + <&camcc CAM_CC_CSIPHY3_CLK>, + <&camcc CAM_CC_CSI3PHYTIMER_CLK>, + <&camcc CAM_CC_CSIPHY4_CLK>, + <&camcc CAM_CC_CSI4PHYTIMER_CLK>, + <&gcc GCC_CAMERA_AHB_CLK>, + <&gcc GCC_CAMERA_HF_AXI_CLK>, + <&camcc CAM_CC_ICP_AHB_CLK>, + <&camcc CAM_CC_IFE_0_CLK>, + <&camcc CAM_CC_IFE_0_AXI_CLK>, + <&camcc CAM_CC_IFE_0_CPHY_RX_CLK>, + <&camcc CAM_CC_IFE_0_CSID_CLK>, + <&camcc CAM_CC_IFE_1_CLK>, + <&camcc CAM_CC_IFE_1_AXI_CLK>, + <&camcc CAM_CC_IFE_1_CPHY_RX_CLK>, + <&camcc CAM_CC_IFE_1_CSID_CLK>, + <&camcc CAM_CC_IFE_2_CLK>, + <&camcc CAM_CC_IFE_2_AXI_CLK>, + <&camcc CAM_CC_IFE_2_CPHY_RX_CLK>, + <&camcc CAM_CC_IFE_2_CSID_CLK>, + <&camcc CAM_CC_IFE_LITE_0_CLK>, + <&camcc CAM_CC_IFE_LITE_0_CPHY_RX_CLK>, + <&camcc CAM_CC_IFE_LITE_0_CSID_CLK>, + <&camcc CAM_CC_IFE_LITE_1_CLK>, + <&camcc CAM_CC_IFE_LITE_1_CPHY_RX_CLK>, + <&camcc CAM_CC_IFE_LITE_1_CSID_CLK>; + clock-names = "camnoc_axi", + "cpas_ahb", + "csiphy0", + "csiphy0_timer", + "csiphy1", + "csiphy1_timer", + "csiphy2", + "csiphy2_timer", + "csiphy3", + "csiphy3_timer", + "csiphy4", + "csiphy4_timer", + "gcc_camera_ahb", + "gcc_cam_hf_axi", + "icp_ahb", + "vfe0", + "vfe0_axi", + "vfe0_cphy_rx", + "vfe0_csid", + "vfe1", + "vfe1_axi", + "vfe1_cphy_rx", + "vfe1_csid", + "vfe2", + "vfe2_axi", + "vfe2_cphy_rx", + "vfe2_csid", + "vfe_lite0", + "vfe_lite0_cphy_rx", + "vfe_lite0_csid", + "vfe_lite1", + "vfe_lite1_cphy_rx", + "vfe_lite1_csid"; + + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + interrupt-names = "csid0", + "csid1", + "csid2", + "csid_lite0", + "csid_lite1", + "csiphy0", + "csiphy1", + "csiphy2", + "csiphy3", + "csiphy4", + "vfe0", + "vfe1", + "vfe2", + "vfe_lite0", + "vfe_lite1"; + + interconnects = <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &cnoc2 SLAVE_CAMERA_CFG QCOM_ICC_TAG_ACTIVE_ONLY>, + <&mmss_noc MASTER_CAMNOC_HF QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "ahb", + "hf_0"; + + iommus = <&apps_smmu 0x800 0x4e0>; + + power-domains = <&camcc CAM_CC_IFE_0_GDSC>, + <&camcc CAM_CC_IFE_1_GDSC>, + <&camcc CAM_CC_IFE_2_GDSC>, + <&camcc CAM_CC_TITAN_TOP_GDSC>; + power-domain-names = "ife0", + "ife1", + "ife2", + "top"; + + vdda-phy-supply = <&vreg_l10c_0p88>; + vdda-pll-supply = <&vreg_l6b_1p2>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/media/qcom,sc7280-venus.yaml b/Documentation/devicetree/bindings/media/qcom,sc7280-venus.yaml index 10c334e6b3dc..413c5b4ee650 100644 --- a/Documentation/devicetree/bindings/media/qcom,sc7280-venus.yaml +++ b/Documentation/devicetree/bindings/media/qcom,sc7280-venus.yaml @@ -68,6 +68,7 @@ properties: required: - compatible + deprecated: true additionalProperties: false video-encoder: @@ -80,14 +81,13 @@ properties: required: - compatible + deprecated: true additionalProperties: false required: - compatible - power-domain-names - iommus - - video-decoder - - video-encoder unevaluatedProperties: false @@ -125,14 +125,6 @@ examples: memory-region = <&video_mem>; - video-decoder { - compatible = "venus-decoder"; - }; - - video-encoder { - compatible = "venus-encoder"; - }; - video-firmware { iommus = <&apps_smmu 0x21a2 0x0>; }; diff --git a/Documentation/devicetree/bindings/media/qcom,sc8280xp-camss.yaml b/Documentation/devicetree/bindings/media/qcom,sc8280xp-camss.yaml index c0bc31709873..9936f0132417 100644 --- a/Documentation/devicetree/bindings/media/qcom,sc8280xp-camss.yaml +++ b/Documentation/devicetree/bindings/media/qcom,sc8280xp-camss.yaml @@ -328,26 +328,26 @@ examples: vdda-phy-supply = <&vreg_l6d>; vdda-pll-supply = <&vreg_l4d>; - interrupts = , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - ; + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; interrupt-names = "csid1_lite", "vfe_lite1", diff --git a/Documentation/devicetree/bindings/media/qcom,sdm660-camss.yaml b/Documentation/devicetree/bindings/media/qcom,sdm660-camss.yaml index 584106e275f6..68d8670557f5 100644 --- a/Documentation/devicetree/bindings/media/qcom,sdm660-camss.yaml +++ b/Documentation/devicetree/bindings/media/qcom,sdm660-camss.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/qcom,sdm660-camss.yaml# diff --git a/Documentation/devicetree/bindings/media/qcom,sdm845-camss.yaml b/Documentation/devicetree/bindings/media/qcom,sdm845-camss.yaml index ec4380a0a03f..289494f561e5 100644 --- a/Documentation/devicetree/bindings/media/qcom,sdm845-camss.yaml +++ b/Documentation/devicetree/bindings/media/qcom,sdm845-camss.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/qcom,sdm845-camss.yaml# @@ -296,16 +295,16 @@ examples: "vfe_lite_cphy_rx", "vfe_lite_src"; - interrupts = , - , - , - , - , - , - , - , - , - ; + interrupts = , + , + , + , + , + , + , + , + , + ; interrupt-names = "csid0", "csid1", diff --git a/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml b/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml index 6228fd2b3246..c839cb1ebc09 100644 --- a/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml +++ b/Documentation/devicetree/bindings/media/qcom,sdm845-venus-v2.yaml @@ -70,6 +70,7 @@ properties: required: - compatible + deprecated: true additionalProperties: false video-core1: @@ -82,14 +83,13 @@ properties: required: - compatible + deprecated: true additionalProperties: false required: - compatible - power-domain-names - iommus - - video-core0 - - video-core1 unevaluatedProperties: false @@ -119,12 +119,4 @@ examples: iommus = <&apps_smmu 0x10a0 0x8>, <&apps_smmu 0x10b0 0x0>; memory-region = <&venus_mem>; - - video-core0 { - compatible = "venus-decoder"; - }; - - video-core1 { - compatible = "venus-encoder"; - }; }; diff --git a/Documentation/devicetree/bindings/media/qcom,sm8250-camss.yaml b/Documentation/devicetree/bindings/media/qcom,sm8250-camss.yaml index fa5073c0fd1e..a372d991e652 100644 --- a/Documentation/devicetree/bindings/media/qcom,sm8250-camss.yaml +++ b/Documentation/devicetree/bindings/media/qcom,sm8250-camss.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/qcom,sm8250-camss.yaml# @@ -329,20 +328,20 @@ examples: vdda-phy-supply = <&vreg_l5a_0p88>; vdda-pll-supply = <&vreg_l9a_1p2>; - interrupts = , - , - , - , - , - , - , - , - , - , - , - , - , - ; + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + ; interrupt-names = "csiphy0", "csiphy1", "csiphy2", diff --git a/Documentation/devicetree/bindings/media/qcom,sm8250-venus.yaml b/Documentation/devicetree/bindings/media/qcom,sm8250-venus.yaml index f66033ae8b59..da54493220c9 100644 --- a/Documentation/devicetree/bindings/media/qcom,sm8250-venus.yaml +++ b/Documentation/devicetree/bindings/media/qcom,sm8250-venus.yaml @@ -73,6 +73,7 @@ properties: required: - compatible + deprecated: true additionalProperties: false video-encoder: @@ -85,6 +86,7 @@ properties: required: - compatible + deprecated: true additionalProperties: false required: @@ -95,8 +97,6 @@ required: - iommus - resets - reset-names - - video-decoder - - video-encoder unevaluatedProperties: false @@ -132,12 +132,4 @@ examples: resets = <&gcc GCC_VIDEO_AXI0_CLK_ARES>, <&videocc VIDEO_CC_MVS0C_CLK_ARES>; reset-names = "bus", "core"; - - video-decoder { - compatible = "venus-decoder"; - }; - - video-encoder { - compatible = "venus-encoder"; - }; }; diff --git a/Documentation/devicetree/bindings/media/rockchip,rk3568-vepu.yaml b/Documentation/devicetree/bindings/media/rockchip,rk3568-vepu.yaml index 947ad699cc5e..d246f5d38427 100644 --- a/Documentation/devicetree/bindings/media/rockchip,rk3568-vepu.yaml +++ b/Documentation/devicetree/bindings/media/rockchip,rk3568-vepu.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/rockchip,rk3568-vepu.yaml# diff --git a/Documentation/devicetree/bindings/media/rockchip-vpu.yaml b/Documentation/devicetree/bindings/media/rockchip-vpu.yaml index 719aeb2dc593..8c2501634080 100644 --- a/Documentation/devicetree/bindings/media/rockchip-vpu.yaml +++ b/Documentation/devicetree/bindings/media/rockchip-vpu.yaml @@ -1,5 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) - %YAML 1.2 --- $id: http://devicetree.org/schemas/media/rockchip-vpu.yaml# @@ -92,18 +91,18 @@ additionalProperties: false examples: - | - #include - #include - #include + #include + #include + #include - vpu: video-codec@ff9a0000 { - compatible = "rockchip,rk3288-vpu"; - reg = <0xff9a0000 0x800>; - interrupts = , - ; - interrupt-names = "vepu", "vdpu"; - clocks = <&cru ACLK_VCODEC>, <&cru HCLK_VCODEC>; - clock-names = "aclk", "hclk"; - power-domains = <&power RK3288_PD_VIDEO>; - iommus = <&vpu_mmu>; - }; + video-codec@ff9a0000 { + compatible = "rockchip,rk3288-vpu"; + reg = <0xff9a0000 0x800>; + interrupts = , + ; + interrupt-names = "vepu", "vdpu"; + clocks = <&cru ACLK_VCODEC>, <&cru HCLK_VCODEC>; + clock-names = "aclk", "hclk"; + power-domains = <&power RK3288_PD_VIDEO>; + iommus = <&vpu_mmu>; + }; diff --git a/Documentation/devicetree/bindings/media/st,stm32-dcmipp.yaml b/Documentation/devicetree/bindings/media/st,stm32-dcmipp.yaml index 87731f3ce7bd..7b03a77adbce 100644 --- a/Documentation/devicetree/bindings/media/st,stm32-dcmipp.yaml +++ b/Documentation/devicetree/bindings/media/st,stm32-dcmipp.yaml @@ -12,7 +12,9 @@ maintainers: properties: compatible: - const: st,stm32mp13-dcmipp + enum: + - st,stm32mp13-dcmipp + - st,stm32mp25-dcmipp reg: maxItems: 1 @@ -21,11 +23,24 @@ properties: maxItems: 1 clocks: - maxItems: 1 + items: + - description: bus clock + - description: csi clock + minItems: 1 + + clock-names: + items: + - const: kclk + - const: mclk + minItems: 1 resets: maxItems: 1 + access-controllers: + minItems: 1 + maxItems: 2 + port: $ref: /schemas/graph.yaml#/$defs/port-base unevaluatedProperties: false @@ -39,7 +54,7 @@ properties: properties: bus-type: - enum: [5, 6] + enum: [4, 5, 6] default: 5 bus-width: @@ -50,9 +65,6 @@ properties: hsync-active: true vsync-active: true - required: - - pclk-sample - required: - compatible - reg @@ -61,6 +73,35 @@ required: - resets - port +allOf: + - if: + properties: + compatible: + contains: + enum: + - st,stm32mp13-dcmipp + then: + properties: + clocks: + maxItems: 1 + + clock-names: + maxItems: 1 + + port: + properties: + endpoint: + properties: + bus-type: + enum: [5, 6] + else: + properties: + clocks: + minItems: 2 + + clock-names: + minItems: 2 + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/media/st,stm32mp25-csi.yaml b/Documentation/devicetree/bindings/media/st,stm32mp25-csi.yaml new file mode 100644 index 000000000000..33bedfe41924 --- /dev/null +++ b/Documentation/devicetree/bindings/media/st,stm32mp25-csi.yaml @@ -0,0 +1,125 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/media/st,stm32mp25-csi.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: STMicroelectronics STM32 CSI controller + +description: + The STM32 CSI controller allows connecting a CSI based + camera to the DCMIPP camera pipeline. + +maintainers: + - Alain Volmat + +properties: + compatible: + enum: + - st,stm32mp25-csi + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 3 + + clock-names: + items: + - const: pclk + - const: txesc + - const: csi2phy + + resets: + maxItems: 1 + + vdd-supply: + description: Digital core power supply (0.91V) + + vdda18-supply: + description: System analog power supply (1.8V) + + access-controllers: + minItems: 1 + maxItems: 2 + + ports: + $ref: /schemas/graph.yaml#/properties/ports + + properties: + port@0: + $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false + description: + Input port node + + properties: + endpoint: + $ref: video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + minItems: 1 + items: + - const: 1 + - const: 2 + + required: + - data-lanes + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: + Output port node + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - resets + - ports + +additionalProperties: false + +examples: + - | + #include + #include + #include + #include + csi@48020000 { + compatible = "st,stm32mp25-csi"; + reg = <0x48020000 0x2000>; + interrupts = ; + resets = <&rcc CSI_R>; + clocks = <&rcc CK_KER_CSI>, <&rcc CK_KER_CSITXESC>, <&rcc CK_KER_CSIPHY>; + clock-names = "pclk", "txesc", "csi2phy"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + endpoint { + remote-endpoint = <&imx335_ep>; + data-lanes = <1 2>; + bus-type = ; + }; + }; + + port@1 { + reg = <1>; + endpoint { + remote-endpoint = <&dcmipp_0>; + }; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/media/video-interfaces.yaml b/Documentation/devicetree/bindings/media/video-interfaces.yaml index 26e3e7d7c67b..038e85b45bef 100644 --- a/Documentation/devicetree/bindings/media/video-interfaces.yaml +++ b/Documentation/devicetree/bindings/media/video-interfaces.yaml @@ -210,6 +210,27 @@ properties: lane-polarities property is omitted, the value must be interpreted as 0 (normal). This property is valid for serial busses only. + line-orders: + $ref: /schemas/types.yaml#/definitions/uint32-array + minItems: 1 + maxItems: 8 + items: + enum: + - 0 # ABC + - 1 # ACB + - 2 # BAC + - 3 # BCA + - 4 # CAB + - 5 # CBA + description: + An array of line orders of the CSI-2 C-PHY data lanes. The order of the + lanes are the same as in data-lanes property. Valid values are 0-5 as + defined in the MIPI Discovery and Configuration (DisCo) Specification for + Imaging. The length of the array must be the same length as the + data-lanes property. If the line-orders property is omitted, the value + shall be interpreted as 0 (ABC). This property is valid for CSI-2 C-PHY + busses only. + strobe: $ref: /schemas/types.yaml#/definitions/uint32 enum: [ 0, 1 ] diff --git a/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml b/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml index 0c511ab906bf..8b937f90a1fb 100644 --- a/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml @@ -52,10 +52,3 @@ examples: #qca,ddr-wb-channel-cells = <1>; }; - - interrupt-controller { - // ... - qca,ddr-wb-channel-interrupts = <2>, <3>, <4>, <5>; - qca,ddr-wb-channels = <&ddr_ctrl 3>, <&ddr_ctrl 2>, - <&ddr_ctrl 0>, <&ddr_ctrl 1>; - }; diff --git a/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-gpbr.yaml b/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-gpbr.yaml new file mode 100644 index 000000000000..f805545aa62a --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-gpbr.yaml @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mfd/atmel,at91sam9260-gpbr.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip AT91 General Purpose Backup Registers + +maintainers: + - Nicolas Ferre + +description: + The system controller embeds 256 bits of General Purpose Backup + registers organized as 8 32-bit registers. + +properties: + compatible: + oneOf: + - items: + - enum: + - atmel,at91sam9260-gpbr + - const: syscon + - items: + - enum: + - microchip,sam9x60-gpbr + - microchip,sam9x7-gpbr + - const: atmel,at91sam9260-gpbr + - const: syscon + + reg: + maxItems: 1 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + syscon@fffffd50 { + compatible = "atmel,at91sam9260-gpbr", "syscon"; + reg = <0xfffffd50 0x10>; + }; diff --git a/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-matrix.yaml b/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-matrix.yaml new file mode 100644 index 000000000000..447b3a3edbfc --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-matrix.yaml @@ -0,0 +1,52 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mfd/atmel,at91sam9260-matrix.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip AT91 Bus Matrix + +maintainers: + - Nicolas Ferre + +description: + The Bus Matrix (MATRIX) implements a multi-layer AHB, based on the + AHB-Lite protocol, that enables parallel access paths between multiple + masters and slaves in a system, thus increasing the overall bandwidth. + +properties: + compatible: + oneOf: + - items: + - enum: + - atmel,at91sam9260-matrix + - atmel,at91sam9261-matrix + - atmel,at91sam9263-matrix + - atmel,at91sam9rl-matrix + - atmel,at91sam9g45-matrix + - atmel,at91sam9n12-matrix + - atmel,at91sam9x5-matrix + - atmel,sama5d3-matrix + - const: syscon + - items: + - enum: + - microchip,sam9x60-matrix + - microchip,sam9x7-matrix + - const: atmel,at91sam9x5-matrix + - const: syscon + + reg: + maxItems: 1 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + syscon@ffffec00 { + compatible = "atmel,sama5d3-matrix", "syscon"; + reg = <0xffffec00 0x200>; + }; diff --git a/Documentation/devicetree/bindings/mfd/atmel-gpbr.txt b/Documentation/devicetree/bindings/mfd/atmel-gpbr.txt deleted file mode 100644 index 3c989d1760a2..000000000000 --- a/Documentation/devicetree/bindings/mfd/atmel-gpbr.txt +++ /dev/null @@ -1,18 +0,0 @@ -* Device tree bindings for Atmel GPBR (General Purpose Backup Registers) - -The GPBR are a set of battery-backed registers. - -Required properties: -- compatible: Should be one of the following: - "atmel,at91sam9260-gpbr", "syscon" - "microchip,sam9x60-gpbr", "syscon" - "microchip,sam9x7-gpbr", "microchip,sam9x60-gpbr", "syscon" -- reg: contains offset/length value of the GPBR memory - region. - -Example: - -gpbr: gpbr@fffffd50 { - compatible = "atmel,at91sam9260-gpbr", "syscon"; - reg = <0xfffffd50 0x10>; -}; diff --git a/Documentation/devicetree/bindings/mfd/atmel-matrix.txt b/Documentation/devicetree/bindings/mfd/atmel-matrix.txt deleted file mode 100644 index 6e5f83614e83..000000000000 --- a/Documentation/devicetree/bindings/mfd/atmel-matrix.txt +++ /dev/null @@ -1,26 +0,0 @@ -* Device tree bindings for Atmel Bus Matrix - -The Bus Matrix registers are used to configure Atmel SoCs internal bus -behavior (master/slave priorities, undefined burst length type, ...) - -Required properties: -- compatible: Should be one of the following - "atmel,at91sam9260-matrix", "syscon" - "atmel,at91sam9261-matrix", "syscon" - "atmel,at91sam9263-matrix", "syscon" - "atmel,at91sam9rl-matrix", "syscon" - "atmel,at91sam9g45-matrix", "syscon" - "atmel,at91sam9n12-matrix", "syscon" - "atmel,at91sam9x5-matrix", "syscon" - "atmel,sama5d3-matrix", "syscon" - "microchip,sam9x60-matrix", "syscon" - "microchip,sam9x7-matrix", "atmel,at91sam9x5-matrix", "syscon" -- reg: Contains offset/length value of the Bus Matrix - memory region. - -Example: - -matrix: matrix@ffffec00 { - compatible = "atmel,sama5d3-matrix", "syscon"; - reg = <0xffffec00 0x200>; -}; diff --git a/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml b/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml index aac8819bd00b..50f457090066 100644 --- a/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml +++ b/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml @@ -108,9 +108,6 @@ properties: pwm: $ref: /schemas/pwm/google,cros-ec-pwm.yaml# - kbd-led-backlight: - $ref: /schemas/chrome/google,cros-kbd-led-backlight.yaml# - keyboard-controller: $ref: /schemas/input/google,cros-ec-keyb.yaml# diff --git a/Documentation/devicetree/bindings/mfd/mediatek,mt6397.yaml b/Documentation/devicetree/bindings/mfd/mediatek,mt6397.yaml index 86451f151a6a..6a89b479d10f 100644 --- a/Documentation/devicetree/bindings/mfd/mediatek,mt6397.yaml +++ b/Documentation/devicetree/bindings/mfd/mediatek,mt6397.yaml @@ -36,6 +36,7 @@ properties: - enum: - mediatek,mt6323 - mediatek,mt6331 # "mediatek,mt6331" for PMIC MT6331 and MT6332. + - mediatek,mt6328 - mediatek,mt6358 - mediatek,mt6359 - mediatek,mt6397 @@ -88,6 +89,7 @@ properties: oneOf: - enum: - mediatek,mt6323-regulator + - mediatek,mt6328-regulator - mediatek,mt6358-regulator - mediatek,mt6359-regulator - mediatek,mt6397-regulator diff --git a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml index 79add913e35c..a503b67f2dbe 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml @@ -42,6 +42,7 @@ properties: - qcom,tcsr-apq8064 - qcom,tcsr-apq8084 - qcom,tcsr-ipq5332 + - qcom,tcsr-ipq5424 - qcom,tcsr-ipq6018 - qcom,tcsr-ipq8064 - qcom,tcsr-ipq8074 diff --git a/Documentation/devicetree/bindings/mfd/qnap,ts433-mcu.yaml b/Documentation/devicetree/bindings/mfd/qnap,ts433-mcu.yaml new file mode 100644 index 000000000000..877078ac172f --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/qnap,ts433-mcu.yaml @@ -0,0 +1,42 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mfd/qnap,ts433-mcu.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: QNAP NAS on-board Microcontroller + +maintainers: + - Heiko Stuebner + +description: + QNAP embeds a microcontroller on their NAS devices adding system feature + as PWM Fan control, additional LEDs, power button status and more. + +properties: + compatible: + enum: + - qnap,ts433-mcu + +patternProperties: + "^fan-[0-9]+$": + $ref: /schemas/hwmon/fan-common.yaml# + unevaluatedProperties: false + +required: + - compatible + +additionalProperties: false + +examples: + - | + uart { + mcu { + compatible = "qnap,ts433-mcu"; + + fan-0 { + #cooling-cells = <2>; + cooling-levels = <0 64 89 128 166 204 221 238>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd71815-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd71815-pmic.yaml index bb81307dc11b..4fc78efaa550 100644 --- a/Documentation/devicetree/bindings/mfd/rohm,bd71815-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/rohm,bd71815-pmic.yaml @@ -50,15 +50,15 @@ properties: minimum: 0 maximum: 1 - rohm,charger-sense-resistor-ohms: - minimum: 10000000 - maximum: 50000000 + rohm,charger-sense-resistor-micro-ohms: + minimum: 10000 + maximum: 50000 description: | - BD71827 and BD71828 have SAR ADC for measuring charging currents. - External sense resistor (RSENSE in data sheet) should be used. If - something other but 30MOhm resistor is used the resistance value - should be given here in Ohms. - default: 30000000 + BD71815 has SAR ADC for measuring charging currents. External sense + resistor (RSENSE in data sheet) should be used. If something other + but a 30 mOhm resistor is used the resistance value should be given + here in micro Ohms. + default: 30000 regulators: $ref: /schemas/regulator/rohm,bd71815-regulator.yaml @@ -67,7 +67,7 @@ properties: gpio-reserved-ranges: description: | - Usage of BD71828 GPIO pins can be changed via OTP. This property can be + Usage of BD71815 GPIO pins can be changed via OTP. This property can be used to mark the pins which should not be configured for GPIO. Please see the ../gpio/gpio.txt for more information. @@ -113,7 +113,7 @@ examples: gpio-controller; #gpio-cells = <2>; - rohm,charger-sense-resistor-ohms = <10000000>; + rohm,charger-sense-resistor-micro-ohms = <10000>; regulators { buck1: buck1 { diff --git a/Documentation/devicetree/bindings/mfd/sprd,sc2731.yaml b/Documentation/devicetree/bindings/mfd/sprd,sc2731.yaml index 8beec7e8e4c6..b023e1ef8d3c 100644 --- a/Documentation/devicetree/bindings/mfd/sprd,sc2731.yaml +++ b/Documentation/devicetree/bindings/mfd/sprd,sc2731.yaml @@ -67,15 +67,7 @@ patternProperties: "^efuse@[0-9a-f]+$": type: object - additionalProperties: true - properties: - compatible: - enum: - - sprd,sc2720-efuse - - sprd,sc2721-efuse - - sprd,sc2723-efuse - - sprd,sc2730-efuse - - sprd,sc2731-efuse + $ref: /schemas/nvmem/sprd,sc2731-efuse.yaml# "^fuel-gauge@[0-9a-f]+$": type: object @@ -199,7 +191,7 @@ examples: }; }; - adc@480 { + pmic_adc: adc@480 { compatible = "sprd,sc2731-adc"; reg = <0x480>; interrupt-parent = <&sc2731_pmic>; diff --git a/Documentation/devicetree/bindings/mfd/syscon.yaml b/Documentation/devicetree/bindings/mfd/syscon.yaml index b414de4fa779..4d67ff26d445 100644 --- a/Documentation/devicetree/bindings/mfd/syscon.yaml +++ b/Documentation/devicetree/bindings/mfd/syscon.yaml @@ -27,7 +27,7 @@ select: compatible: contains: enum: - - al,alpine-sysfabric-servic + - al,alpine-sysfabric-service - allwinner,sun8i-a83t-system-controller - allwinner,sun8i-h3-system-controller - allwinner,sun8i-v3s-system-controller @@ -103,6 +103,7 @@ select: - rockchip,rk3288-qos - rockchip,rk3368-qos - rockchip,rk3399-qos + - rockchip,rk3562-qos - rockchip,rk3568-qos - rockchip,rk3576-qos - rockchip,rk3588-qos @@ -201,6 +202,7 @@ properties: - rockchip,rk3288-qos - rockchip,rk3368-qos - rockchip,rk3399-qos + - rockchip,rk3562-qos - rockchip,rk3568-qos - rockchip,rk3576-qos - rockchip,rk3588-qos @@ -213,6 +215,7 @@ properties: - ti,am625-dss-oldi-io-ctrl - ti,am62p-cpsw-mac-efuse - ti,am654-dss-oldi-io-ctrl + - ti,j784s4-acspcie-proxy-ctrl - ti,j784s4-pcie-ctrl - ti,keystone-pllctrl - const: syscon diff --git a/Documentation/devicetree/bindings/misc/lwn,bk4-spi.yaml b/Documentation/devicetree/bindings/misc/lwn,bk4-spi.yaml new file mode 100644 index 000000000000..73fbf672e22a --- /dev/null +++ b/Documentation/devicetree/bindings/misc/lwn,bk4-spi.yaml @@ -0,0 +1,54 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/misc/lwn,bk4-spi.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Liebherr's BK4 external SPI controller + +maintainers: + - Lukasz Majewski + +description: | + Liebherr's BK4 external SPI controller is a device which handles data + acquisition from compatible industrial peripherals. + The SPI is used for data and management purposes in both master and + slave modes. + +allOf: + - $ref: /schemas/spi/spi-peripheral-props.yaml# + +properties: + compatible: + const: lwn,bk4-spi + + reg: + maxItems: 1 + + spi-max-frequency: + maximum: 30000000 + + fsl,spi-cs-sck-delay: true + + fsl,spi-sck-cs-delay: true + +required: + - compatible + - spi-max-frequency + +additionalProperties: false + +examples: + - | + spi { + #address-cells = <1>; + #size-cells = <0>; + + spidev@0 { + compatible = "lwn,bk4-spi"; + reg = <0>; + spi-max-frequency = <30000000>; + fsl,spi-cs-sck-delay = <200>; + fsl,spi-sck-cs-delay = <400>; + }; + }; diff --git a/Documentation/devicetree/bindings/misc/lwn-bk4.txt b/Documentation/devicetree/bindings/misc/lwn-bk4.txt deleted file mode 100644 index d6a8c188c087..000000000000 --- a/Documentation/devicetree/bindings/misc/lwn-bk4.txt +++ /dev/null @@ -1,26 +0,0 @@ -* Liebherr's BK4 controller external SPI - -A device which handles data acquisition from compatible industrial -peripherals. -The SPI is used for data and management purposes in both master and -slave modes. - -Required properties: - -- compatible : Should be "lwn,bk4" - -Required SPI properties: - -- reg : Should be address of the device chip select within - the controller. - -- spi-max-frequency : Maximum SPI clocking speed of device in Hz, should be - 30MHz at most for the Liebherr's BK4 external bus. - -Example: - -spidev0: spi@0 { - compatible = "lwn,bk4"; - spi-max-frequency = <30000000>; - reg = <0>; -}; diff --git a/Documentation/devicetree/bindings/mmc/amlogic,meson-mx-sdio.txt b/Documentation/devicetree/bindings/mmc/amlogic,meson-mx-sdio.txt deleted file mode 100644 index 8765c605e6bc..000000000000 --- a/Documentation/devicetree/bindings/mmc/amlogic,meson-mx-sdio.txt +++ /dev/null @@ -1,54 +0,0 @@ -* Amlogic Meson6, Meson8 and Meson8b SDIO/MMC controller - -The highspeed MMC host controller on Amlogic SoCs provides an interface -for MMC, SD, SDIO and SDHC types of memory cards. - -Supported maximum speeds are the ones of the eMMC standard 4.41 as well -as the speed of SD standard 2.0. - -The hardware provides an internal "mux" which allows up to three slots -to be controlled. Only one slot can be accessed at a time. - -Required properties: - - compatible : must be one of - - "amlogic,meson8-sdio" - - "amlogic,meson8b-sdio" - along with the generic "amlogic,meson-mx-sdio" - - reg : mmc controller base registers - - interrupts : mmc controller interrupt - - #address-cells : must be 1 - - size-cells : must be 0 - - clocks : phandle to clock providers - - clock-names : must contain "core" and "clkin" - -Required child nodes: -A node for each slot provided by the MMC controller is required. -NOTE: due to a driver limitation currently only one slot (= child node) - is supported! - -Required properties on each child node (= slot): - - compatible : must be "mmc-slot" (see mmc.txt within this directory) - - reg : the slot (or "port") ID - -Optional properties on each child node (= slot): - - bus-width : must be 1 or 4 (8-bit bus is not supported) - - for cd and all other additional generic mmc parameters - please refer to mmc.txt within this directory - -Examples: - mmc@c1108c20 { - compatible = "amlogic,meson8-sdio", "amlogic,meson-mx-sdio"; - reg = <0xc1108c20 0x20>; - interrupts = <0 28 1>; - #address-cells = <1>; - #size-cells = <0>; - clocks = <&clkc CLKID_SDIO>, <&clkc CLKID_CLK81>; - clock-names = "core", "clkin"; - - slot@1 { - compatible = "mmc-slot"; - reg = <1>; - - bus-width = <4>; - }; - }; diff --git a/Documentation/devicetree/bindings/mmc/amlogic,meson-mx-sdio.yaml b/Documentation/devicetree/bindings/mmc/amlogic,meson-mx-sdio.yaml new file mode 100644 index 000000000000..022682a977c6 --- /dev/null +++ b/Documentation/devicetree/bindings/mmc/amlogic,meson-mx-sdio.yaml @@ -0,0 +1,94 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mmc/amlogic,meson-mx-sdio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic Meson6, Meson8 and Meson8b SDIO/MMC controller + +description: | + The highspeed MMC host controller on Amlogic SoCs provides an interface + for MMC, SD, SDIO and SDHC types of memory cards. + + Supported maximum speeds are the ones of the eMMC standard 4.41 as well + as the speed of SD standard 2.0. + + The hardware provides an internal "mux" which allows up to three slots + to be controlled. Only one slot can be accessed at a time. + +maintainers: + - Neil Armstrong + +properties: + compatible: + items: + - enum: + - amlogic,meson8-sdio + - amlogic,meson8b-sdio + - const: amlogic,meson-mx-sdio + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 2 + + clock-names: + items: + - const: core + - const: clkin + + "#address-cells": + const: 1 + + "#size-cells": + const: 0 + +patternProperties: + "slot@[0-2]$": + $ref: mmc-slot.yaml# + description: + A node for each slot provided by the MMC controller + + properties: + reg: + enum: [0, 1, 2] + + bus-width: + enum: [1, 4] + + unevaluatedProperties: false + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - "#address-cells" + - "#size-cells" + +additionalProperties: false + +examples: + - | + #include + #include + mmc@c1108c20 { + compatible = "amlogic,meson8-sdio", "amlogic,meson-mx-sdio"; + reg = <0xc1108c20 0x20>; + interrupts = ; + clocks = <&clk_core>, <&clk_in>; + clock-names = "core", "clkin"; + #address-cells = <1>; + #size-cells = <0>; + + slot@1 { + compatible = "mmc-slot"; + reg = <1>; + bus-width = <4>; + }; + }; diff --git a/Documentation/devicetree/bindings/mmc/atmel,sama5d2-sdhci.yaml b/Documentation/devicetree/bindings/mmc/atmel,sama5d2-sdhci.yaml index 8c8ade88e8fe..ba75623b7778 100644 --- a/Documentation/devicetree/bindings/mmc/atmel,sama5d2-sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/atmel,sama5d2-sdhci.yaml @@ -22,6 +22,7 @@ properties: - items: - enum: - microchip,sam9x7-sdhci + - microchip,sama7d65-sdhci - microchip,sama7g5-sdhci - const: microchip,sam9x60-sdhci diff --git a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml index cfe6237716f4..3f48d8292d5b 100644 --- a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml @@ -38,15 +38,9 @@ properties: reg: minItems: 1 - maxItems: 2 - description: | - For "marvell,armada-3700-sdhci", two register areas. The first one - for Xenon IP register. The second one for the Armada 3700 SoC PHY PAD - Voltage Control register. Please follow the examples with compatible - "marvell,armada-3700-sdhci" in below. - Please also check property marvell,pad-type in below. - - For other compatible strings, one register area for Xenon IP. + items: + - description: Xenon IP registers + - description: Armada 3700 SoC PHY PAD Voltage Control register clocks: minItems: 1 @@ -61,6 +55,17 @@ properties: interrupts: maxItems: 1 + marvell,pad-type: + $ref: /schemas/types.yaml#/definitions/string + enum: + - sd + - fixed-1-8v + description: + Type of Armada 3700 SoC PHY PAD Voltage Controller register. If "sd" is + selected, SoC PHY PAD is set as 3.3V at the beginning and is switched to + 1.8V when later in higher speed mode. If "fixed-1-8v" is selected, SoC PHY + PAD is fixed 1.8V, such as for eMMC. + marvell,xenon-sdhc-id: $ref: /schemas/types.yaml#/definitions/uint32 minimum: 0 @@ -147,27 +152,18 @@ allOf: then: properties: reg: - items: - - description: Xenon IP registers - - description: Armada 3700 SoC PHY PAD Voltage Control register - - marvell,pad-type: - $ref: /schemas/types.yaml#/definitions/string - enum: - - sd - - fixed-1-8v - description: | - Type of Armada 3700 SoC PHY PAD Voltage Controller register. - If "sd" is selected, SoC PHY PAD is set as 3.3V at the beginning - and is switched to 1.8V when later in higher speed mode. - If "fixed-1-8v" is selected, SoC PHY PAD is fixed 1.8V, such as for - eMMC. - Please follow the examples with compatible - "marvell,armada-3700-sdhci" in below. + minItems: 2 required: - marvell,pad-type + else: + properties: + reg: + maxItems: 1 + + marvell,pad-type: false + - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml b/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml new file mode 100644 index 000000000000..9a7235439759 --- /dev/null +++ b/Documentation/devicetree/bindings/mmc/mmc-controller-common.yaml @@ -0,0 +1,357 @@ +# SPDX-License-Identifier: GPL-2.0 +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mmc/mmc-controller-common.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MMC Controller & Slots Common Properties + +maintainers: + - Ulf Hansson + +description: + These properties are common to multiple MMC host controllers and the + possible slots or ports for multi-slot controllers. + +properties: + "#address-cells": + const: 1 + description: + The cell is the SDIO function number if a function subnode is used. + + "#size-cells": + const: 0 + + # Card Detection. + # If none of these properties are supplied, the host native card + # detect will be used. Only one of them should be provided. + + broken-cd: + $ref: /schemas/types.yaml#/definitions/flag + description: + There is no card detection available; polling must be used. + + cd-gpios: + maxItems: 1 + description: + The card detection will be done using the GPIO provided. + + non-removable: + $ref: /schemas/types.yaml#/definitions/flag + description: + Non-removable slot (like eMMC); assume always present. + + # *NOTE* on CD and WP polarity. To use common for all SD/MMC host + # controllers line polarity properties, we have to fix the meaning + # of the "normal" and "inverted" line levels. We choose to follow + # the SDHCI standard, which specifies both those lines as "active + # low." Therefore, using the "cd-inverted" property means, that the + # CD line is active high, i.e. it is high, when a card is + # inserted. Similar logic applies to the "wp-inverted" property. + # + # CD and WP lines can be implemented on the hardware in one of two + # ways: as GPIOs, specified in cd-gpios and wp-gpios properties, or + # as dedicated pins. Polarity of dedicated pins can be specified, + # using *-inverted properties. GPIO polarity can also be specified + # using the GPIO_ACTIVE_LOW flag. This creates an ambiguity in the + # latter case. We choose to use the XOR logic for GPIO CD and WP + # lines. This means, the two properties are "superimposed," for + # example leaving the GPIO_ACTIVE_LOW flag clear and specifying the + # respective *-inverted property property results in a + # double-inversion and actually means the "normal" line polarity is + # in effect. + wp-inverted: + $ref: /schemas/types.yaml#/definitions/flag + description: + The Write Protect line polarity is inverted. + + cd-inverted: + $ref: /schemas/types.yaml#/definitions/flag + description: + The CD line polarity is inverted. + + # Other properties + + bus-width: + description: + Number of data lines. + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [1, 4, 8] + default: 1 + + max-frequency: + description: | + Maximum operating frequency of the bus: + - for eMMC, the maximum supported frequency is 200MHz, + - for SD/SDIO cards the SDR104 mode has a max supported + frequency of 208MHz, + - some mmc host controllers do support a max frequency upto + 384MHz. + So, lets keep the maximum supported value here. + + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 400000 + maximum: 384000000 + + disable-wp: + $ref: /schemas/types.yaml#/definitions/flag + description: + When set, no physical write-protect line is present. This + property should only be specified when the controller has a + dedicated write-protect detection logic. If a GPIO is always used + for the write-protect detection logic, it is sufficient to not + specify the wp-gpios property in the absence of a write-protect + line. Not used in combination with eMMC or SDIO. + + wp-gpios: + maxItems: 1 + description: + GPIO to use for the write-protect detection. + + cd-debounce-delay-ms: + description: + Set delay time before detecting card after card insert + interrupt. + + no-1-8-v: + $ref: /schemas/types.yaml#/definitions/flag + description: + When specified, denotes that 1.8V card voltage is not supported + on this system, even if the controller claims it. + + cap-sd-highspeed: + $ref: /schemas/types.yaml#/definitions/flag + description: + SD high-speed timing is supported. + + cap-mmc-highspeed: + $ref: /schemas/types.yaml#/definitions/flag + description: + MMC high-speed timing is supported. + + sd-uhs-sdr12: + $ref: /schemas/types.yaml#/definitions/flag + description: + SD UHS SDR12 speed is supported. + + sd-uhs-sdr25: + $ref: /schemas/types.yaml#/definitions/flag + description: + SD UHS SDR25 speed is supported. + + sd-uhs-sdr50: + $ref: /schemas/types.yaml#/definitions/flag + description: + SD UHS SDR50 speed is supported. + + sd-uhs-sdr104: + $ref: /schemas/types.yaml#/definitions/flag + description: + SD UHS SDR104 speed is supported. + + sd-uhs-ddr50: + $ref: /schemas/types.yaml#/definitions/flag + description: + SD UHS DDR50 speed is supported. + + cap-power-off-card: + $ref: /schemas/types.yaml#/definitions/flag + description: + Powering off the card is safe. + + cap-mmc-hw-reset: + $ref: /schemas/types.yaml#/definitions/flag + description: + eMMC hardware reset is supported + + cap-sdio-irq: + $ref: /schemas/types.yaml#/definitions/flag + description: + enable SDIO IRQ signalling on this interface + + full-pwr-cycle: + $ref: /schemas/types.yaml#/definitions/flag + description: + Full power cycle of the card is supported. + + full-pwr-cycle-in-suspend: + $ref: /schemas/types.yaml#/definitions/flag + description: + Full power cycle of the card in suspend is supported. + + mmc-ddr-1_2v: + $ref: /schemas/types.yaml#/definitions/flag + description: + eMMC high-speed DDR mode (1.2V I/O) is supported. + + mmc-ddr-1_8v: + $ref: /schemas/types.yaml#/definitions/flag + description: + eMMC high-speed DDR mode (1.8V I/O) is supported. + + mmc-ddr-3_3v: + $ref: /schemas/types.yaml#/definitions/flag + description: + eMMC high-speed DDR mode (3.3V I/O) is supported. + + mmc-hs200-1_2v: + $ref: /schemas/types.yaml#/definitions/flag + description: + eMMC HS200 mode (1.2V I/O) is supported. + + mmc-hs200-1_8v: + $ref: /schemas/types.yaml#/definitions/flag + description: + eMMC HS200 mode (1.8V I/O) is supported. + + mmc-hs400-1_2v: + $ref: /schemas/types.yaml#/definitions/flag + description: + eMMC HS400 mode (1.2V I/O) is supported. + + mmc-hs400-1_8v: + $ref: /schemas/types.yaml#/definitions/flag + description: + eMMC HS400 mode (1.8V I/O) is supported. + + mmc-hs400-enhanced-strobe: + $ref: /schemas/types.yaml#/definitions/flag + description: + eMMC HS400 enhanced strobe mode is supported + + no-mmc-hs400: + $ref: /schemas/types.yaml#/definitions/flag + description: + All eMMC HS400 modes are not supported. + + dsr: + description: + Value the card Driver Stage Register (DSR) should be programmed + with. + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 0xffff + + no-sdio: + $ref: /schemas/types.yaml#/definitions/flag + description: + Controller is limited to send SDIO commands during + initialization. + + no-sd: + $ref: /schemas/types.yaml#/definitions/flag + description: + Controller is limited to send SD commands during initialization. + + no-mmc: + $ref: /schemas/types.yaml#/definitions/flag + description: + Controller is limited to send MMC commands during + initialization. + + fixed-emmc-driver-type: + description: + For non-removable eMMC, enforce this driver type. The value is + the driver type as specified in the eMMC specification (table + 206 in spec version 5.1) + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 4 + + post-power-on-delay-ms: + description: + It was invented for MMC pwrseq-simple which could be referred to + mmc-pwrseq-simple.yaml. But now it\'s reused as a tunable delay + waiting for I/O signalling and card power supply to be stable, + regardless of whether pwrseq-simple is used. Default to 10ms if + no available. + default: 10 + + supports-cqe: + $ref: /schemas/types.yaml#/definitions/flag + description: + The presence of this property indicates that the corresponding + MMC host controller supports HW command queue feature. + + disable-cqe-dcmd: + $ref: /schemas/types.yaml#/definitions/flag + description: + The presence of this property indicates that the MMC + controller\'s command queue engine (CQE) does not support direct + commands (DCMDs). + + keep-power-in-suspend: + $ref: /schemas/types.yaml#/definitions/flag + description: + SDIO only. Preserves card power during a suspend/resume cycle. + + wakeup-source: + $ref: /schemas/types.yaml#/definitions/flag + description: + SDIO only. Enables wake up of host system on SDIO IRQ assertion. + + vmmc-supply: + description: + Supply for the card power + + vqmmc-supply: + description: + Supply for the bus IO line power, such as a level shifter. + If the level shifter is controlled by a GPIO line, this shall + be modeled as a "regulator-fixed" with a GPIO line for + switching the level shifter on/off. + + mmc-pwrseq: + $ref: /schemas/types.yaml#/definitions/phandle + description: + System-on-Chip designs may specify a specific MMC power + sequence. To successfully detect an (e)MMC/SD/SDIO card, that + power sequence must be maintained while initializing the card. + +patternProperties: + "^.*@[0-9]+$": + type: object + description: | + On embedded systems the cards connected to a host may need + additional properties. These can be specified in subnodes to the + host controller node. The subnodes are identified by the + standard \'reg\' property. Which information exactly can be + specified depends on the bindings for the SDIO function driver + for the subnode, as specified by the compatible string. + + properties: + compatible: + description: + Name of SDIO function following generic names recommended + practice + + reg: + items: + - minimum: 0 + maximum: 7 + description: + Must contain the SDIO function number of the function this + subnode describes. A value of 0 denotes the memory SD + function, values from 1 to 7 denote the SDIO functions. + + required: + - reg + + "^clk-phase-(legacy|sd-hs|mmc-(hs|hs[24]00|ddr52)|uhs-(sdr(12|25|50|104)|ddr50))$": + $ref: /schemas/types.yaml#/definitions/uint32-array + + minItems: 2 + maxItems: 2 + items: + minimum: 0 + maximum: 359 + description: + Set the clock (phase) delays which are to be configured in the + controller while switching to particular speed mode. These values + are in pair of degrees. + +dependencies: + cd-debounce-delay-ms: [ cd-gpios ] + fixed-emmc-driver-type: [ non-removable ] + +additionalProperties: true diff --git a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml index 58ae298cd2fc..9d7a1298c455 100644 --- a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml +++ b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml @@ -9,7 +9,7 @@ title: MMC Controller Common Properties maintainers: - Ulf Hansson -description: | +description: These properties are common to multiple MMC host controllers. Any host that requires the respective functionality should implement them using these definitions. @@ -18,351 +18,13 @@ description: | (and the corresponding mmcblkN devices) by defining an alias in the /aliases device tree node. +$ref: mmc-controller-common.yaml# + properties: $nodename: pattern: "^mmc(@.*)?$" - "#address-cells": - const: 1 - description: | - The cell is the slot ID if a function subnode is used. - - "#size-cells": - const: 0 - - # Card Detection. - # If none of these properties are supplied, the host native card - # detect will be used. Only one of them should be provided. - - broken-cd: - $ref: /schemas/types.yaml#/definitions/flag - description: - There is no card detection available; polling must be used. - - cd-gpios: - maxItems: 1 - description: - The card detection will be done using the GPIO provided. - - non-removable: - $ref: /schemas/types.yaml#/definitions/flag - description: - Non-removable slot (like eMMC); assume always present. - - # *NOTE* on CD and WP polarity. To use common for all SD/MMC host - # controllers line polarity properties, we have to fix the meaning - # of the "normal" and "inverted" line levels. We choose to follow - # the SDHCI standard, which specifies both those lines as "active - # low." Therefore, using the "cd-inverted" property means, that the - # CD line is active high, i.e. it is high, when a card is - # inserted. Similar logic applies to the "wp-inverted" property. - # - # CD and WP lines can be implemented on the hardware in one of two - # ways: as GPIOs, specified in cd-gpios and wp-gpios properties, or - # as dedicated pins. Polarity of dedicated pins can be specified, - # using *-inverted properties. GPIO polarity can also be specified - # using the GPIO_ACTIVE_LOW flag. This creates an ambiguity in the - # latter case. We choose to use the XOR logic for GPIO CD and WP - # lines. This means, the two properties are "superimposed," for - # example leaving the GPIO_ACTIVE_LOW flag clear and specifying the - # respective *-inverted property property results in a - # double-inversion and actually means the "normal" line polarity is - # in effect. - wp-inverted: - $ref: /schemas/types.yaml#/definitions/flag - description: - The Write Protect line polarity is inverted. - - cd-inverted: - $ref: /schemas/types.yaml#/definitions/flag - description: - The CD line polarity is inverted. - - # Other properties - - bus-width: - description: - Number of data lines. - $ref: /schemas/types.yaml#/definitions/uint32 - enum: [1, 4, 8] - default: 1 - - max-frequency: - description: | - Maximum operating frequency of the bus: - - for eMMC, the maximum supported frequency is 200MHz, - - for SD/SDIO cards the SDR104 mode has a max supported - frequency of 208MHz, - - some mmc host controllers do support a max frequency upto - 384MHz. - So, lets keep the maximum supported value here. - - $ref: /schemas/types.yaml#/definitions/uint32 - minimum: 400000 - maximum: 384000000 - - disable-wp: - $ref: /schemas/types.yaml#/definitions/flag - description: - When set, no physical write-protect line is present. This - property should only be specified when the controller has a - dedicated write-protect detection logic. If a GPIO is always used - for the write-protect detection logic, it is sufficient to not - specify the wp-gpios property in the absence of a write-protect - line. Not used in combination with eMMC or SDIO. - - wp-gpios: - maxItems: 1 - description: - GPIO to use for the write-protect detection. - - cd-debounce-delay-ms: - description: - Set delay time before detecting card after card insert - interrupt. - - no-1-8-v: - $ref: /schemas/types.yaml#/definitions/flag - description: - When specified, denotes that 1.8V card voltage is not supported - on this system, even if the controller claims it. - - cap-sd-highspeed: - $ref: /schemas/types.yaml#/definitions/flag - description: - SD high-speed timing is supported. - - cap-mmc-highspeed: - $ref: /schemas/types.yaml#/definitions/flag - description: - MMC high-speed timing is supported. - - sd-uhs-sdr12: - $ref: /schemas/types.yaml#/definitions/flag - description: - SD UHS SDR12 speed is supported. - - sd-uhs-sdr25: - $ref: /schemas/types.yaml#/definitions/flag - description: - SD UHS SDR25 speed is supported. - - sd-uhs-sdr50: - $ref: /schemas/types.yaml#/definitions/flag - description: - SD UHS SDR50 speed is supported. - - sd-uhs-sdr104: - $ref: /schemas/types.yaml#/definitions/flag - description: - SD UHS SDR104 speed is supported. - - sd-uhs-ddr50: - $ref: /schemas/types.yaml#/definitions/flag - description: - SD UHS DDR50 speed is supported. - - cap-power-off-card: - $ref: /schemas/types.yaml#/definitions/flag - description: - Powering off the card is safe. - - cap-mmc-hw-reset: - $ref: /schemas/types.yaml#/definitions/flag - description: - eMMC hardware reset is supported - - cap-sdio-irq: - $ref: /schemas/types.yaml#/definitions/flag - description: - enable SDIO IRQ signalling on this interface - - full-pwr-cycle: - $ref: /schemas/types.yaml#/definitions/flag - description: - Full power cycle of the card is supported. - - full-pwr-cycle-in-suspend: - $ref: /schemas/types.yaml#/definitions/flag - description: - Full power cycle of the card in suspend is supported. - - mmc-ddr-1_2v: - $ref: /schemas/types.yaml#/definitions/flag - description: - eMMC high-speed DDR mode (1.2V I/O) is supported. - - mmc-ddr-1_8v: - $ref: /schemas/types.yaml#/definitions/flag - description: - eMMC high-speed DDR mode (1.8V I/O) is supported. - - mmc-ddr-3_3v: - $ref: /schemas/types.yaml#/definitions/flag - description: - eMMC high-speed DDR mode (3.3V I/O) is supported. - - mmc-hs200-1_2v: - $ref: /schemas/types.yaml#/definitions/flag - description: - eMMC HS200 mode (1.2V I/O) is supported. - - mmc-hs200-1_8v: - $ref: /schemas/types.yaml#/definitions/flag - description: - eMMC HS200 mode (1.8V I/O) is supported. - - mmc-hs400-1_2v: - $ref: /schemas/types.yaml#/definitions/flag - description: - eMMC HS400 mode (1.2V I/O) is supported. - - mmc-hs400-1_8v: - $ref: /schemas/types.yaml#/definitions/flag - description: - eMMC HS400 mode (1.8V I/O) is supported. - - mmc-hs400-enhanced-strobe: - $ref: /schemas/types.yaml#/definitions/flag - description: - eMMC HS400 enhanced strobe mode is supported - - no-mmc-hs400: - $ref: /schemas/types.yaml#/definitions/flag - description: - All eMMC HS400 modes are not supported. - - dsr: - description: - Value the card Driver Stage Register (DSR) should be programmed - with. - $ref: /schemas/types.yaml#/definitions/uint32 - minimum: 0 - maximum: 0xffff - - no-sdio: - $ref: /schemas/types.yaml#/definitions/flag - description: - Controller is limited to send SDIO commands during - initialization. - - no-sd: - $ref: /schemas/types.yaml#/definitions/flag - description: - Controller is limited to send SD commands during initialization. - - no-mmc: - $ref: /schemas/types.yaml#/definitions/flag - description: - Controller is limited to send MMC commands during - initialization. - - fixed-emmc-driver-type: - description: - For non-removable eMMC, enforce this driver type. The value is - the driver type as specified in the eMMC specification (table - 206 in spec version 5.1) - $ref: /schemas/types.yaml#/definitions/uint32 - minimum: 0 - maximum: 4 - - post-power-on-delay-ms: - description: - It was invented for MMC pwrseq-simple which could be referred to - mmc-pwrseq-simple.yaml. But now it\'s reused as a tunable delay - waiting for I/O signalling and card power supply to be stable, - regardless of whether pwrseq-simple is used. Default to 10ms if - no available. - default: 10 - - supports-cqe: - $ref: /schemas/types.yaml#/definitions/flag - description: - The presence of this property indicates that the corresponding - MMC host controller supports HW command queue feature. - - disable-cqe-dcmd: - $ref: /schemas/types.yaml#/definitions/flag - description: - The presence of this property indicates that the MMC - controller\'s command queue engine (CQE) does not support direct - commands (DCMDs). - - keep-power-in-suspend: - $ref: /schemas/types.yaml#/definitions/flag - description: - SDIO only. Preserves card power during a suspend/resume cycle. - - wakeup-source: - $ref: /schemas/types.yaml#/definitions/flag - description: - SDIO only. Enables wake up of host system on SDIO IRQ assertion. - - vmmc-supply: - description: - Supply for the card power - - vqmmc-supply: - description: - Supply for the bus IO line power, such as a level shifter. - If the level shifter is controlled by a GPIO line, this shall - be modeled as a "regulator-fixed" with a GPIO line for - switching the level shifter on/off. - - mmc-pwrseq: - $ref: /schemas/types.yaml#/definitions/phandle - description: - System-on-Chip designs may specify a specific MMC power - sequence. To successfully detect an (e)MMC/SD/SDIO card, that - power sequence must be maintained while initializing the card. - -patternProperties: - "^.*@[0-9]+$": - type: object - description: | - On embedded systems the cards connected to a host may need - additional properties. These can be specified in subnodes to the - host controller node. The subnodes are identified by the - standard \'reg\' property. Which information exactly can be - specified depends on the bindings for the SDIO function driver - for the subnode, as specified by the compatible string. - - properties: - compatible: - description: | - Name of SDIO function following generic names recommended - practice - - reg: - items: - - minimum: 0 - maximum: 7 - description: - Must contain the SDIO function number of the function this - subnode describes. A value of 0 denotes the memory SD - function, values from 1 to 7 denote the SDIO functions. - - required: - - reg - - "^clk-phase-(legacy|sd-hs|mmc-(hs|hs[24]00|ddr52)|uhs-(sdr(12|25|50|104)|ddr50))$": - $ref: /schemas/types.yaml#/definitions/uint32-array - - minItems: 2 - maxItems: 2 - items: - minimum: 0 - maximum: 359 - description: - Set the clock (phase) delays which are to be configured in the - controller while switching to particular speed mode. These values - are in pair of degrees. - -dependencies: - cd-debounce-delay-ms: [ cd-gpios ] - fixed-emmc-driver-type: [ non-removable ] - -additionalProperties: true +unevaluatedProperties: true examples: - | diff --git a/Documentation/devicetree/bindings/mmc/mmc-slot.yaml b/Documentation/devicetree/bindings/mmc/mmc-slot.yaml new file mode 100644 index 000000000000..1f0667828063 --- /dev/null +++ b/Documentation/devicetree/bindings/mmc/mmc-slot.yaml @@ -0,0 +1,49 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mmc/mmc-slot.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MMC slot properties + +maintainers: + - Ulf Hansson + +description: + These properties defines slot properties for MMC controlers that + have multiple slots or ports provided by the same controller and + sharing the same resources. + +$ref: mmc-controller-common.yaml# + +properties: + $nodename: + pattern: "^slot(@.*)?$" + + compatible: + const: mmc-slot + + reg: + description: + the slot (or "port") ID + maxItems: 1 + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + mmc { + #address-cells = <1>; + #size-cells = <0>; + slot@0 { + compatible = "mmc-slot"; + reg = <0>; + bus-width = <4>; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.yaml b/Documentation/devicetree/bindings/mmc/mtk-sd.yaml index f86ebd81f5a5..0debccbd6519 100644 --- a/Documentation/devicetree/bindings/mmc/mtk-sd.yaml +++ b/Documentation/devicetree/bindings/mmc/mtk-sd.yaml @@ -235,11 +235,19 @@ allOf: properties: compatible: contains: - const: mediatek,mt8183-mmc + enum: + - mediatek,mt7986-mmc + - mediatek,mt7988-mmc + - mediatek,mt8183-mmc + - mediatek,mt8196-mmc then: properties: reg: minItems: 2 + else: + properties: + reg: + maxItems: 1 - if: properties: diff --git a/Documentation/devicetree/bindings/mmc/samsung,exynos-dw-mshc.yaml b/Documentation/devicetree/bindings/mmc/samsung,exynos-dw-mshc.yaml index 5fe65795f796..ef2d1d7c92fc 100644 --- a/Documentation/devicetree/bindings/mmc/samsung,exynos-dw-mshc.yaml +++ b/Documentation/devicetree/bindings/mmc/samsung,exynos-dw-mshc.yaml @@ -29,6 +29,7 @@ properties: - samsung,exynos5433-dw-mshc-smu - samsung,exynos7885-dw-mshc-smu - samsung,exynos850-dw-mshc-smu + - samsung,exynos8895-dw-mshc-smu - const: samsung,exynos7-dw-mshc-smu reg: diff --git a/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml b/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml index 8b393e26e025..eed9063e9bb3 100644 --- a/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml +++ b/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml @@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm SDHCI controller (sdhci-msm) maintainers: - - Bhupesh Sharma + - Bjorn Andersson + - Konrad Dybcio description: Secure Digital Host Controller Interface (SDHCI) present on diff --git a/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt b/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt deleted file mode 100644 index d2eada5044b2..000000000000 --- a/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt +++ /dev/null @@ -1,53 +0,0 @@ -* Cadence NAND controller - -Required properties: - - compatible : "cdns,hp-nfc" - - reg : Contains two entries, each of which is a tuple consisting of a - physical address and length. The first entry is the address and - length of the controller register set. The second entry is the - address and length of the Slave DMA data port. - - reg-names: should contain "reg" and "sdma" - - #address-cells: should be 1. The cell encodes the chip select connection. - - #size-cells : should be 0. - - interrupts : The interrupt number. - - clocks: phandle of the controller core clock (nf_clk). - -Optional properties: - - dmas: shall reference DMA channel associated to the NAND controller - - cdns,board-delay-ps : Estimated Board delay. The value includes the total - round trip delay for the signals and is used for deciding on values - associated with data read capture. The example formula for SDR mode is - the following: - board delay = RE#PAD delay + PCB trace to device + PCB trace from device - + DQ PAD delay - -Child nodes represent the available NAND chips. - -Required properties of NAND chips: - - reg: shall contain the native Chip Select ids from 0 to max supported by - the cadence nand flash controller - -See Documentation/devicetree/bindings/mtd/nand-controller.yaml for more details on -generic bindings. - -Example: - -nand_controller: nand-controller@60000000 { - compatible = "cdns,hp-nfc"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0x60000000 0x10000>, <0x80000000 0x10000>; - reg-names = "reg", "sdma"; - clocks = <&nf_clk>; - cdns,board-delay-ps = <4830>; - interrupts = <2 0>; - nand@0 { - reg = <0>; - label = "nand-1"; - }; - nand@1 { - reg = <1>; - label = "nand-2"; - }; - -}; diff --git a/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml b/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml new file mode 100644 index 000000000000..0bed37a994c3 --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml @@ -0,0 +1,75 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mtd/cdns,hp-nfc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Cadence NAND controller + +maintainers: + - Niravkumar L Rabara + +allOf: + - $ref: nand-controller.yaml + +properties: + compatible: + items: + - const: cdns,hp-nfc + + reg: + items: + - description: Controller register set + - description: Slave DMA data port register set + + reg-names: + items: + - const: reg + - const: sdma + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + dmas: + maxItems: 1 + + cdns,board-delay-ps: + description: | + Estimated Board delay. The value includes the total round trip + delay for the signals and is used for deciding on values associated + with data read capture. The example formula for SDR mode is the + following. + board delay = RE#PAD delay + PCB trace to device + PCB trace from device + + DQ PAD delay + +required: + - compatible + - reg + - reg-names + - interrupts + - clocks + +unevaluatedProperties: false + +examples: + - | + #include + + nand-controller@10b80000 { + compatible = "cdns,hp-nfc"; + reg = <0x10b80000 0x10000>, + <0x10840000 0x10000>; + reg-names = "reg", "sdma"; + #address-cells = <1>; + #size-cells = <0>; + interrupts = ; + clocks = <&nf_clk>; + cdns,board-delay-ps = <4830>; + + nand@0 { + reg = <0>; + }; + }; diff --git a/Documentation/devicetree/bindings/mtd/davinci-nand.txt b/Documentation/devicetree/bindings/mtd/davinci-nand.txt deleted file mode 100644 index eb8e2ff4dbd2..000000000000 --- a/Documentation/devicetree/bindings/mtd/davinci-nand.txt +++ /dev/null @@ -1,94 +0,0 @@ -Device tree bindings for Texas instruments Davinci/Keystone NAND controller - -This file provides information, what the device node for the davinci/keystone -NAND interface contains. - -Documentation: -Davinci DM646x - https://www.ti.com/lit/ug/sprueq7c/sprueq7c.pdf -Kestone - https://www.ti.com/lit/ug/sprugz3a/sprugz3a.pdf - -Required properties: - -- compatible: "ti,davinci-nand" - "ti,keystone-nand" - -- reg: Contains 2 offset/length values: - - offset and length for the access window. - - offset and length for accessing the AEMIF - control registers. - -- ti,davinci-chipselect: number of chipselect. Indicates on the - davinci_nand driver which chipselect is used - for accessing the nand. - Can be in the range [0-3]. - -Recommended properties : - -- ti,davinci-mask-ale: mask for ALE. Needed for executing address - phase. These offset will be added to the base - address for the chip select space the NAND Flash - device is connected to. - If not set equal to 0x08. - -- ti,davinci-mask-cle: mask for CLE. Needed for executing command - phase. These offset will be added to the base - address for the chip select space the NAND Flash - device is connected to. - If not set equal to 0x10. - -- ti,davinci-mask-chipsel: mask for chipselect address. Needed to mask - addresses for given chipselect. - -- nand-ecc-mode: operation mode of the NAND ecc mode. ECC mode - valid values for davinci driver: - - "none" - - "soft" - - "hw" - -- ti,davinci-ecc-bits: used ECC bits, currently supported 1 or 4. - -- nand-bus-width: buswidth 8 or 16. If not present 8. - -- nand-on-flash-bbt: use flash based bad block table support. OOB - identifier is saved in OOB area. If not present - false. - -Deprecated properties: - -- ti,davinci-ecc-mode: operation mode of the NAND ecc mode. ECC mode - valid values for davinci driver: - - "none" - - "soft" - - "hw" - -- ti,davinci-nand-buswidth: buswidth 8 or 16. If not present 8. - -- ti,davinci-nand-use-bbt: use flash based bad block table support. OOB - identifier is saved in OOB area. If not present - false. - -Nand device bindings may contain additional sub-nodes describing partitions of -the address space. See mtd.yaml for more detail. The NAND Flash timing -values must be programmed in the chip select’s node of AEMIF -memory-controller (see Documentation/devicetree/bindings/memory-controllers/ -davinci-aemif.txt). - -Example(da850 EVM ): - -nand_cs3@62000000 { - compatible = "ti,davinci-nand"; - reg = <0x62000000 0x807ff - 0x68000000 0x8000>; - ti,davinci-chipselect = <1>; - ti,davinci-mask-ale = <0>; - ti,davinci-mask-cle = <0>; - ti,davinci-mask-chipsel = <0>; - nand-ecc-mode = "hw"; - ti,davinci-ecc-bits = <4>; - nand-on-flash-bbt; - - partition@180000 { - label = "ubifs"; - reg = <0x180000 0x7e80000>; - }; -}; diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.yaml b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.yaml index 6e3afb42926e..335f8204aa1e 100644 --- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.yaml +++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.yaml @@ -96,6 +96,10 @@ properties: If "broken-flash-reset" is present then having this property does not make any difference. + vcc-supply: + description: + Supply for the SPI NOR power. + spi-cpol: true spi-cpha: true diff --git a/Documentation/devicetree/bindings/mtd/microchip,mchp48l640.yaml b/Documentation/devicetree/bindings/mtd/microchip,mchp48l640.yaml index 0ff32bd00bf6..5c6b628c608d 100644 --- a/Documentation/devicetree/bindings/mtd/microchip,mchp48l640.yaml +++ b/Documentation/devicetree/bindings/mtd/microchip,mchp48l640.yaml @@ -16,8 +16,9 @@ description: | properties: compatible: - items: - - const: microchip,48l640 + enum: + - fujitsu,mb85rs128ty + - microchip,48l640 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/mtd/nuvoton,ma35d1-nand.yaml b/Documentation/devicetree/bindings/mtd/nuvoton,ma35d1-nand.yaml new file mode 100644 index 000000000000..0b651450a8f1 --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/nuvoton,ma35d1-nand.yaml @@ -0,0 +1,95 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mtd/nuvoton,ma35d1-nand.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Nuvoton MA35D1 NAND Flash Interface (NFI) Controller + +maintainers: + - Hui-Ping Chen + +allOf: + - $ref: nand-controller.yaml# + +properties: + compatible: + enum: + - nuvoton,ma35d1-nand-controller + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + +patternProperties: + "^nand@[a-f0-9]$": + type: object + $ref: raw-nand-chip.yaml + properties: + reg: + minimum: 0 + maximum: 1 + + nand-ecc-step-size: + enum: [512, 1024] + + nand-ecc-strength: + enum: [8, 12, 24] + + required: + - reg + + unevaluatedProperties: false + +required: + - compatible + - reg + - interrupts + - clocks + +unevaluatedProperties: false + +examples: + - | + #include + #include + + soc { + #address-cells = <2>; + #size-cells = <2>; + + nand-controller@401A0000 { + compatible = "nuvoton,ma35d1-nand-controller"; + reg = <0x0 0x401A0000 0x0 0x1000>; + interrupts = ; + clocks = <&clk NAND_GATE>; + #address-cells = <1>; + #size-cells = <0>; + + nand@0 { + reg = <0>; + nand-on-flash-bbt; + nand-ecc-step-size = <512>; + nand-ecc-strength = <8>; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + uboot@0 { + label = "nand-uboot"; + read-only; + reg = <0x0 0x300000>; + }; + }; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml b/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml index 058253d6d889..62086366837c 100644 --- a/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml +++ b/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml @@ -82,7 +82,7 @@ examples: uimage@100000 { reg = <0x0100000 0x200000>; - compress = "lzma"; + compression = "lzma"; }; }; diff --git a/Documentation/devicetree/bindings/mtd/ti,davinci-nand.yaml b/Documentation/devicetree/bindings/mtd/ti,davinci-nand.yaml new file mode 100644 index 000000000000..ed24b0ea86e5 --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/ti,davinci-nand.yaml @@ -0,0 +1,124 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mtd/ti,davinci-nand.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: TI DaVinci NAND controller + +maintainers: + - Marcus Folkesson + +allOf: + - $ref: nand-controller.yaml + +properties: + compatible: + enum: + - ti,davinci-nand + - ti,keystone-nand + + reg: + items: + - description: Access window. + - description: AEMIF control registers. + + partitions: + $ref: /schemas/mtd/partitions/partitions.yaml + + ti,davinci-chipselect: + description: + Number of chipselect. Indicate on the davinci_nand driver which + chipselect is used for accessing the nand. + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [0, 1, 2, 3] + + ti,davinci-mask-ale: + description: + Mask for ALE. Needed for executing address phase. These offset will be + added to the base address for the chip select space the NAND Flash + device is connected to. + $ref: /schemas/types.yaml#/definitions/uint32 + default: 0x08 + + ti,davinci-mask-cle: + description: + Mask for CLE. Needed for executing command phase. These offset will be + added to the base address for the chip select space the NAND Flash device + is connected to. + $ref: /schemas/types.yaml#/definitions/uint32 + default: 0x10 + + ti,davinci-mask-chipsel: + description: + Mask for chipselect address. Needed to mask addresses for given + chipselect. + $ref: /schemas/types.yaml#/definitions/uint32 + default: 0 + + ti,davinci-ecc-bits: + description: Used ECC bits. + enum: [1, 4] + + ti,davinci-ecc-mode: + description: Operation mode of the NAND ECC mode. + $ref: /schemas/types.yaml#/definitions/string + enum: [none, soft, hw, on-die] + deprecated: true + + ti,davinci-nand-buswidth: + description: Bus width to the NAND chip. + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [8, 16] + default: 8 + deprecated: true + + ti,davinci-nand-use-bbt: + type: boolean + description: + Use flash based bad block table support. OOB identifier is saved in OOB + area. + deprecated: true + +required: + - compatible + - reg + - ti,davinci-chipselect + +unevaluatedProperties: false + +examples: + - | + bus { + #address-cells = <2>; + #size-cells = <1>; + + nand-controller@2000000,0 { + compatible = "ti,davinci-nand"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0 0x02000000 0x02000000>, + <1 0x00000000 0x00008000>; + + ti,davinci-chipselect = <1>; + ti,davinci-mask-ale = <0>; + ti,davinci-mask-cle = <0>; + ti,davinci-mask-chipsel = <0>; + + ti,davinci-nand-buswidth = <16>; + ti,davinci-ecc-mode = "hw"; + ti,davinci-ecc-bits = <4>; + ti,davinci-nand-use-bbt; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + label = "u-boot env"; + reg = <0 0x020000>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml index d1e2bca3c503..798a4c19f18c 100644 --- a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml @@ -166,11 +166,11 @@ unevaluatedProperties: false examples: - | ethmac: ethernet@c9410000 { - compatible = "amlogic,meson-gxbb-dwmac", "snps,dwmac"; - reg = <0xc9410000 0x10000>, <0xc8834540 0x8>; - interrupts = <8>; - interrupt-names = "macirq"; - clocks = <&clk_eth>, <&clk_fclk_div2>, <&clk_mpll2>, <&clk_fclk_div2>; - clock-names = "stmmaceth", "clkin0", "clkin1", "timing-adjustment"; - phy-mode = "rgmii"; + compatible = "amlogic,meson-gxbb-dwmac", "snps,dwmac"; + reg = <0xc9410000 0x10000>, <0xc8834540 0x8>; + interrupts = <8>; + interrupt-names = "macirq"; + clocks = <&clk_eth>, <&clk_fclk_div2>, <&clk_mpll2>, <&clk_fclk_div2>; + clock-names = "stmmaceth", "clkin0", "clkin1", "timing-adjustment"; + phy-mode = "rgmii"; }; diff --git a/Documentation/devicetree/bindings/net/asix,ax88178.yaml b/Documentation/devicetree/bindings/net/asix,ax88178.yaml index 768504ccbf74..03341b7438d5 100644 --- a/Documentation/devicetree/bindings/net/asix,ax88178.yaml +++ b/Documentation/devicetree/bindings/net/asix,ax88178.yaml @@ -63,8 +63,8 @@ examples: #size-cells = <0>; ethernet@1 { - compatible = "usbb95,772b"; - reg = <1>; + compatible = "usbb95,772b"; + reg = <1>; }; }; }; diff --git a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml index 7bb68311c609..a72152f7e29b 100644 --- a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml +++ b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml @@ -101,7 +101,10 @@ properties: max-speed: true firmware-name: - description: specify the name of nvm firmware to load + minItems: 1 + items: + - description: specify the name of nvm firmware to load + - description: specify the name of rampatch firmware to load local-bd-address: true @@ -154,16 +157,11 @@ allOf: - qcom,wcn6750-bt then: required: - - enable-gpios - - swctrl-gpios - - vddio-supply - vddaon-supply - - vddbtcxmx-supply - vddrfacmn-supply - vddrfa0p8-supply - vddrfa1p7-supply - vddrfa1p2-supply - - vddasd-supply - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.yaml b/Documentation/devicetree/bindings/net/brcm,bcmgenet.yaml index 7c90a4390531..0e3fb4e42e3f 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.yaml +++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.yaml @@ -85,16 +85,16 @@ examples: #size-cells = <1>; mdio0: mdio@e14 { - compatible = "brcm,genet-mdio-v4"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0xe14 0x8>; + compatible = "brcm,genet-mdio-v4"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0xe14 0x8>; - phy1: ethernet-phy@1 { + phy1: ethernet-phy@1 { max-speed = <1000>; reg = <1>; compatible = "ethernet-phy-ieee802.3-c22"; - }; + }; }; }; @@ -110,10 +110,10 @@ examples: interrupts = <0x0 0x16 0x0>, <0x0 0x17 0x0>; mdio1: mdio@e14 { - compatible = "brcm,genet-mdio-v4"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0xe14 0x8>; + compatible = "brcm,genet-mdio-v4"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0xe14 0x8>; }; }; @@ -129,15 +129,15 @@ examples: interrupts = <0x0 0x18 0x0>, <0x0 0x19 0x0>; mdio2: mdio@e14 { - compatible = "brcm,genet-mdio-v4"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0xe14 0x8>; + compatible = "brcm,genet-mdio-v4"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0xe14 0x8>; - phy0: ethernet-phy@0 { + phy0: ethernet-phy@0 { max-speed = <1000>; reg = <0>; compatible = "ethernet-phy-ieee802.3-c22"; - }; + }; }; }; diff --git a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.yaml b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.yaml index af96b4fd89d5..3f27746d9a56 100644 --- a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.yaml +++ b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.yaml @@ -38,43 +38,43 @@ unevaluatedProperties: false examples: - | - mdio_mux_iproc: mdio-mux@66020000 { + mdio-mux@66020000 { compatible = "brcm,mdio-mux-iproc"; reg = <0x66020000 0x250>; #address-cells = <1>; #size-cells = <0>; mdio@0 { - reg = <0x0>; - #address-cells = <1>; - #size-cells = <0>; + reg = <0x0>; + #address-cells = <1>; + #size-cells = <0>; - pci_phy0: pci-phy@0 { - compatible = "brcm,ns2-pcie-phy"; - reg = <0x0>; - #phy-cells = <0>; - }; + pci-phy@0 { + compatible = "brcm,ns2-pcie-phy"; + reg = <0x0>; + #phy-cells = <0>; + }; }; mdio@7 { - reg = <0x7>; - #address-cells = <1>; - #size-cells = <0>; + reg = <0x7>; + #address-cells = <1>; + #size-cells = <0>; - pci_phy1: pci-phy@0 { - compatible = "brcm,ns2-pcie-phy"; - reg = <0x0>; - #phy-cells = <0>; - }; + pci-phy@0 { + compatible = "brcm,ns2-pcie-phy"; + reg = <0x0>; + #phy-cells = <0>; + }; }; mdio@10 { - reg = <0x10>; - #address-cells = <1>; - #size-cells = <0>; + reg = <0x10>; + #address-cells = <1>; + #size-cells = <0>; - gphy0: eth-phy@10 { - reg = <0x10>; - }; + eth-phy@10 { + reg = <0x10>; + }; }; }; diff --git a/Documentation/devicetree/bindings/net/can/atmel,at91sam9263-can.yaml b/Documentation/devicetree/bindings/net/can/atmel,at91sam9263-can.yaml new file mode 100644 index 000000000000..c818c01a718b --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/atmel,at91sam9263-can.yaml @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/can/atmel,at91sam9263-can.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip AT91 CAN Controller + +maintainers: + - Nicolas Ferre + +allOf: + - $ref: can-controller.yaml# + +properties: + compatible: + oneOf: + - enum: + - atmel,at91sam9263-can + - atmel,at91sam9x5-can + - items: + - enum: + - microchip,sam9x60-can + - const: atmel,at91sam9x5-can + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + items: + - const: can_clk + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + +unevaluatedProperties: false + +examples: + - | + #include + #include + can@f000c000 { + compatible = "atmel,at91sam9263-can"; + reg = <0xf000c000 0x300>; + interrupts = <30 IRQ_TYPE_LEVEL_HIGH 3>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 12>; + clock-names = "can_clk"; + }; diff --git a/Documentation/devicetree/bindings/net/can/atmel-can.txt b/Documentation/devicetree/bindings/net/can/atmel-can.txt deleted file mode 100644 index 218a3b3eb27e..000000000000 --- a/Documentation/devicetree/bindings/net/can/atmel-can.txt +++ /dev/null @@ -1,15 +0,0 @@ -* AT91 CAN * - -Required properties: - - compatible: Should be "atmel,at91sam9263-can", "atmel,at91sam9x5-can" or - "microchip,sam9x60-can" - - reg: Should contain CAN controller registers location and length - - interrupts: Should contain IRQ line for the CAN controller - -Example: - - can0: can@f000c000 { - compatible = "atmel,at91sam9x5-can"; - reg = <0xf000c000 0x300>; - interrupts = <40 4 5> - }; diff --git a/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml b/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml index 4d7d67ee175a..ff1b59a0294e 100644 --- a/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml +++ b/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml @@ -99,11 +99,11 @@ examples: #include can@ffc00000 { - compatible = "bosch,d_can"; - reg = <0xffc00000 0x1000>; - interrupts = <0 131 4>, <0 132 4>, <0 133 4>, <0 134 4>; - clocks = <&can0_clk>; - resets = <&rst CAN0_RESET>; + compatible = "bosch,d_can"; + reg = <0xffc00000 0x1000>; + interrupts = <0 131 4>, <0 132 4>, <0 133 4>, <0 134 4>; + clocks = <&can0_clk>; + resets = <&rst CAN0_RESET>; }; - | can@0 { diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml index db446dde6842..e0ec53bc10c6 100644 --- a/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml +++ b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml @@ -56,15 +56,15 @@ examples: #size-cells = <0>; can@1 { - compatible = "microchip,mcp2515"; - reg = <1>; - clocks = <&clk24m>; - interrupt-parent = <&gpio4>; - interrupts = <13 IRQ_TYPE_LEVEL_LOW>; - vdd-supply = <®5v0>; - xceiver-supply = <®5v0>; - gpio-controller; - #gpio-cells = <2>; + compatible = "microchip,mcp2515"; + reg = <1>; + clocks = <&clk24m>; + interrupt-parent = <&gpio4>; + interrupts = <13 IRQ_TYPE_LEVEL_LOW>; + vdd-supply = <®5v0>; + xceiver-supply = <®5v0>; + gpio-controller; + #gpio-cells = <2>; }; }; diff --git a/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml b/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml index 01e4d4a54df6..1219c5cb601f 100644 --- a/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml +++ b/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml @@ -15,7 +15,11 @@ allOf: properties: compatible: - const: microchip,mpfs-can + oneOf: + - items: + - const: microchip,pic64gx-can + - const: microchip,mpfs-can + - const: microchip,mpfs-can reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml index de1d4298893b..c7510b00954a 100644 --- a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml +++ b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml @@ -63,7 +63,7 @@ properties: maxItems: 1 st,gcan: - $ref: /schemas/types.yaml#/definitions/phandle-array + $ref: /schemas/types.yaml#/definitions/phandle description: The phandle to the gcan node which allows to access the 512-bytes SRAM memory shared by the two bxCAN cells (CAN1 primary and CAN2 diff --git a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt deleted file mode 100644 index 20c0572c9853..000000000000 --- a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt +++ /dev/null @@ -1,48 +0,0 @@ -Texas Instruments TCAN4x5x CAN Controller -================================================ - -This file provides device node information for the TCAN4x5x interface contains. - -Required properties: - - compatible: - "ti,tcan4552", "ti,tcan4x5x" - "ti,tcan4553", "ti,tcan4x5x" or - "ti,tcan4x5x" - - reg: 0 - - #address-cells: 1 - - #size-cells: 0 - - spi-max-frequency: Maximum frequency of the SPI bus the chip can - operate at should be less than or equal to 18 MHz. - - interrupt-parent: the phandle to the interrupt controller which provides - the interrupt. - - interrupts: interrupt specification for data-ready. - -See Documentation/devicetree/bindings/net/can/bosch,m_can.yaml for additional -required property details. - -Optional properties: - - reset-gpios: Hardwired output GPIO. If not defined then software - reset. - - device-state-gpios: Input GPIO that indicates if the device is in - a sleep state or if the device is active. Not - available with tcan4552/4553. - - device-wake-gpios: Wake up GPIO to wake up the TCAN device. Not - available with tcan4552/4553. - - wakeup-source: Leave the chip running when suspended, and configure - the RX interrupt to wake up the device. - -Example: -tcan4x5x: tcan4x5x@0 { - compatible = "ti,tcan4x5x"; - reg = <0>; - #address-cells = <1>; - #size-cells = <1>; - spi-max-frequency = <10000000>; - bosch,mram-cfg = <0x0 0 0 16 0 0 1 1>; - interrupt-parent = <&gpio1>; - interrupts = <14 IRQ_TYPE_LEVEL_LOW>; - device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; - device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; - reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>; - wakeup-source; -}; diff --git a/Documentation/devicetree/bindings/net/can/ti,tcan4x5x.yaml b/Documentation/devicetree/bindings/net/can/ti,tcan4x5x.yaml new file mode 100644 index 000000000000..384e15da2713 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/ti,tcan4x5x.yaml @@ -0,0 +1,199 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/can/ti,tcan4x5x.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments TCAN4x5x CAN Controller + +maintainers: + - Marc Kleine-Budde + +properties: + compatible: + oneOf: + - items: + - enum: + - ti,tcan4552 + - ti,tcan4553 + - const: ti,tcan4x5x + - const: ti,tcan4x5x + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + description: The GPIO parent interrupt. + + clocks: + maxItems: 1 + + clock-names: + items: + - const: cclk + + reset-gpios: + description: Hardwired output GPIO. If not defined then software reset. + maxItems: 1 + + device-state-gpios: + description: + Input GPIO that indicates if the device is in a sleep state or if the + device is active. Not available with tcan4552/4553. + maxItems: 1 + + device-wake-gpios: + description: + Wake up GPIO to wake up the TCAN device. + Not available with tcan4552/4553. + maxItems: 1 + + bosch,mram-cfg: + description: | + Message RAM configuration data. + Multiple M_CAN instances can share the same Message RAM + and each element(e.g Rx FIFO or Tx Buffer and etc) number + in Message RAM is also configurable, so this property is + telling driver how the shared or private Message RAM are + used by this M_CAN controller. + + The format should be as follows: + + The 'offset' is an address offset of the Message RAM where + the following elements start from. This is usually set to + 0x0 if you're using a private Message RAM. The remain cells + are used to specify how many elements are used for each FIFO/Buffer. + + M_CAN includes the following elements according to user manual: + 11-bit Filter 0-128 elements / 0-128 words + 29-bit Filter 0-64 elements / 0-128 words + Rx FIFO 0 0-64 elements / 0-1152 words + Rx FIFO 1 0-64 elements / 0-1152 words + Rx Buffers 0-64 elements / 0-1152 words + Tx Event FIFO 0-32 elements / 0-64 words + Tx Buffers 0-32 elements / 0-576 words + + Please refer to 2.4.1 Message RAM Configuration in Bosch + M_CAN user manual for details. + $ref: /schemas/types.yaml#/definitions/int32-array + items: + - description: The 'offset' is an address offset of the Message RAM where + the following elements start from. This is usually set to 0x0 if + you're using a private Message RAM. + default: 0 + - description: 11-bit Filter 0-128 elements / 0-128 words + minimum: 0 + maximum: 128 + - description: 29-bit Filter 0-64 elements / 0-128 words + minimum: 0 + maximum: 64 + - description: Rx FIFO 0 0-64 elements / 0-1152 words + minimum: 0 + maximum: 64 + - description: Rx FIFO 1 0-64 elements / 0-1152 words + minimum: 0 + maximum: 64 + - description: Rx Buffers 0-64 elements / 0-1152 words + minimum: 0 + maximum: 64 + - description: Tx Event FIFO 0-32 elements / 0-64 words + minimum: 0 + maximum: 32 + - description: Tx Buffers 0-32 elements / 0-576 words + minimum: 0 + maximum: 32 + minItems: 1 + + spi-max-frequency: + description: + Must be half or less of "clocks" frequency. + maximum: 18000000 + + ti,nwkrq-voltage-vio: + type: boolean + description: + nWKRQ Pin GPO buffer voltage configuration. + Set nWKRQ to use VIO voltage rail. + When not set nWKRQ will use internal voltage rail. + + wakeup-source: + $ref: /schemas/types.yaml#/definitions/flag + description: + Enable CAN remote wakeup. + +allOf: + - $ref: can-controller.yaml# + - $ref: /schemas/spi/spi-peripheral-props.yaml# + - if: + properties: + compatible: + contains: + enum: + - ti,tcan4552 + - ti,tcan4553 + then: + properties: + device-state-gpios: false + device-wake-gpios: false + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - bosch,mram-cfg + +unevaluatedProperties: false + +examples: + - | + #include + #include + + spi { + #address-cells = <1>; + #size-cells = <0>; + + can@0 { + compatible = "ti,tcan4x5x"; + reg = <0>; + clocks = <&can0_osc>; + clock-names = "cclk"; + pinctrl-names = "default"; + pinctrl-0 = <&can0_pins>; + spi-max-frequency = <10000000>; + bosch,mram-cfg = <0x0 0 0 16 0 0 1 1>; + interrupt-parent = <&gpio1>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; + device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; + device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>; + ti,nwkrq-voltage-vio; + wakeup-source; + }; + }; + - | + #include + #include + + spi { + #address-cells = <1>; + #size-cells = <0>; + + can@0 { + compatible = "ti,tcan4552", "ti,tcan4x5x"; + reg = <0>; + clocks = <&can0_osc>; + clock-names = "cclk"; + pinctrl-names = "default"; + pinctrl-0 = <&can0_pins>; + spi-max-frequency = <10000000>; + bosch,mram-cfg = <0x0 0 0 16 0 0 1 1>; + interrupt-parent = <&gpio1>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; + reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>; + wakeup-source; + }; + }; diff --git a/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml b/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml index dedfad526666..a73fc5036905 100644 --- a/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml +++ b/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml @@ -129,6 +129,24 @@ properties: minimum: 0 maximum: 383 + rx-internal-delay-ps: + description: + RGMII Receive Clock Delay defined in pico seconds, used to select + the DLL phase shift between 1000 ps (45 degree shift at 1Gbps) and + 3300 ps (147 degree shift at 1Gbps). A value of 0 ps will disable + any delay. The Default is no delay. + enum: [0, 1000, 1700, 2000, 2500, 3000, 3300] + default: 0 + + tx-internal-delay-ps: + description: + RGMII Transmit Clock Delay defined in pico seconds, used to select + the DLL phase shift between 1000 ps (45 degree shift at 1Gbps) and + 3300 ps (147 degree shift at 1Gbps). A value of 0 ps will disable + any delay. The Default is no delay. + enum: [0, 1000, 1700, 2000, 2500, 3000, 3300] + default: 0 + required: - reg - phys diff --git a/Documentation/devicetree/bindings/net/nxp,s32-dwmac.yaml b/Documentation/devicetree/bindings/net/nxp,s32-dwmac.yaml new file mode 100644 index 000000000000..2b8b74c5feec --- /dev/null +++ b/Documentation/devicetree/bindings/net/nxp,s32-dwmac.yaml @@ -0,0 +1,105 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Copyright 2021-2024 NXP +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/nxp,s32-dwmac.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP S32G2xx/S32G3xx/S32R45 GMAC ethernet controller + +maintainers: + - Jan Petrous (OSS) + +description: + This device is a Synopsys DWC IP, integrated on NXP S32G/R SoCs. + The SoC series S32G2xx and S32G3xx feature one DWMAC instance, + the SoC S32R45 has two instances. The devices can use RGMII/RMII/MII + interface over Pinctrl device or the output can be routed + to the embedded SerDes for SGMII connectivity. + +properties: + compatible: + oneOf: + - const: nxp,s32g2-dwmac + - items: + - enum: + - nxp,s32g3-dwmac + - nxp,s32r45-dwmac + - const: nxp,s32g2-dwmac + + reg: + items: + - description: Main GMAC registers + - description: GMAC PHY mode control register + + interrupts: + maxItems: 1 + + interrupt-names: + const: macirq + + clocks: + items: + - description: Main GMAC clock + - description: Transmit clock + - description: Receive clock + - description: PTP reference clock + + clock-names: + items: + - const: stmmaceth + - const: tx + - const: rx + - const: ptp_ref + +required: + - clocks + - clock-names + +allOf: + - $ref: snps,dwmac.yaml# + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + bus { + #address-cells = <2>; + #size-cells = <2>; + + ethernet@4033c000 { + compatible = "nxp,s32g2-dwmac"; + reg = <0x0 0x4033c000 0x0 0x2000>, /* gmac IP */ + <0x0 0x4007c004 0x0 0x4>; /* GMAC_0_CTRL_STS */ + interrupt-parent = <&gic>; + interrupts = ; + interrupt-names = "macirq"; + snps,mtl-rx-config = <&mtl_rx_setup>; + snps,mtl-tx-config = <&mtl_tx_setup>; + clocks = <&clks 24>, <&clks 17>, <&clks 16>, <&clks 15>; + clock-names = "stmmaceth", "tx", "rx", "ptp_ref"; + phy-mode = "rgmii-id"; + phy-handle = <&phy0>; + + mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <5>; + }; + + mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <5>; + }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + phy0: ethernet-phy@0 { + reg = <0>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml b/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml index a12cda8aa764..cd09560e0aea 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml @@ -81,7 +81,7 @@ properties: List of phandles, each pointing to the power supply for the corresponding pairset named in 'pairset-names'. This property aligns with IEEE 802.3-2022, Section 33.2.3 and 145.2.4. - PSE Pinout Alternatives (as per IEEE 802.3-2022 Table 145\u20133) + PSE Pinout Alternatives (as per IEEE 802.3-2022 Table 145-3) |-----------|---------------|---------------|---------------|---------------| | Conductor | Alternative A | Alternative A | Alternative B | Alternative B | | | (MDI-X) | (MDI) | (X) | (S) | diff --git a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml index 0bcd593a7bd0..e7ee0d9efed8 100644 --- a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml @@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Ethernet ETHQOS device maintainers: - - Bhupesh Sharma + - Bjorn Andersson + - Konrad Dybcio description: dwmmac based Qualcomm ethernet devices which support Gigabit @@ -21,12 +22,12 @@ properties: oneOf: - items: - enum: - - qcom,qcs8300-ethqos - - const: qcom,sa8775p-ethqos + - qcom,qcs615-ethqos + - const: qcom,qcs404-ethqos - items: - enum: - - qcom,qcs615-ethqos - - const: qcom,sm8150-ethqos + - qcom,qcs8300-ethqos + - const: qcom,sa8775p-ethqos - enum: - qcom,qcs404-ethqos - qcom,sa8775p-ethqos diff --git a/Documentation/devicetree/bindings/net/qcom,ipa.yaml b/Documentation/devicetree/bindings/net/qcom,ipa.yaml index 53cae71d9957..1a46d80a66e8 100644 --- a/Documentation/devicetree/bindings/net/qcom,ipa.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ipa.yaml @@ -239,7 +239,7 @@ examples: qcom,gsi-loader = "self"; memory-region = <&ipa_fw_mem>; - firmware-name = "qcom/sc7180-trogdor/modem/modem.mdt"; + firmware-name = "qcom/sc7180-trogdor/modem/modem.mbn"; iommus = <&apps_smmu 0x440 0x0>, <&apps_smmu 0x442 0x0>; diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index eb1f3ae41ab9..91e75eb3f329 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -67,6 +67,7 @@ properties: - ingenic,x2000-mac - loongson,ls2k-dwmac - loongson,ls7a-dwmac + - nxp,s32g2-dwmac - qcom,qcs404-ethqos - qcom,sa8775p-ethqos - qcom,sc8280xp-ethqos diff --git a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml index bf23838fe6e8..85cea9966a27 100644 --- a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml @@ -154,56 +154,56 @@ examples: #include #include //Example 1 - ethernet0: ethernet@5800a000 { - compatible = "st,stm32mp1-dwmac", "snps,dwmac-4.20a"; - reg = <0x5800a000 0x2000>; - reg-names = "stmmaceth"; - interrupts = ; - interrupt-names = "macirq"; - clock-names = "stmmaceth", - "mac-clk-tx", - "mac-clk-rx", - "ethstp", - "eth-ck"; - clocks = <&rcc ETHMAC>, - <&rcc ETHTX>, - <&rcc ETHRX>, - <&rcc ETHSTP>, - <&rcc ETHCK_K>; - st,syscon = <&syscfg 0x4>; - snps,pbl = <2>; - snps,axi-config = <&stmmac_axi_config_0>; - snps,tso; - phy-mode = "rgmii"; - }; + ethernet0: ethernet@5800a000 { + compatible = "st,stm32mp1-dwmac", "snps,dwmac-4.20a"; + reg = <0x5800a000 0x2000>; + reg-names = "stmmaceth"; + interrupts = ; + interrupt-names = "macirq"; + clock-names = "stmmaceth", + "mac-clk-tx", + "mac-clk-rx", + "ethstp", + "eth-ck"; + clocks = <&rcc ETHMAC>, + <&rcc ETHTX>, + <&rcc ETHRX>, + <&rcc ETHSTP>, + <&rcc ETHCK_K>; + st,syscon = <&syscfg 0x4>; + snps,pbl = <2>; + snps,axi-config = <&stmmac_axi_config_0>; + snps,tso; + phy-mode = "rgmii"; + }; - | //Example 2 (MCU example) - ethernet1: ethernet@40028000 { - compatible = "st,stm32-dwmac", "snps,dwmac-3.50a"; - reg = <0x40028000 0x8000>; - reg-names = "stmmaceth"; - interrupts = <0 61 0>, <0 62 0>; - interrupt-names = "macirq", "eth_wake_irq"; - clock-names = "stmmaceth", "mac-clk-tx", "mac-clk-rx"; - clocks = <&rcc 0 25>, <&rcc 0 26>, <&rcc 0 27>; - st,syscon = <&syscfg 0x4>; - snps,pbl = <8>; - snps,mixed-burst; - phy-mode = "mii"; - }; + ethernet1: ethernet@40028000 { + compatible = "st,stm32-dwmac", "snps,dwmac-3.50a"; + reg = <0x40028000 0x8000>; + reg-names = "stmmaceth"; + interrupts = <0 61 0>, <0 62 0>; + interrupt-names = "macirq", "eth_wake_irq"; + clock-names = "stmmaceth", "mac-clk-tx", "mac-clk-rx"; + clocks = <&rcc 0 25>, <&rcc 0 26>, <&rcc 0 27>; + st,syscon = <&syscfg 0x4>; + snps,pbl = <8>; + snps,mixed-burst; + phy-mode = "mii"; + }; - | //Example 3 - ethernet2: ethernet@40027000 { - compatible = "st,stm32-dwmac", "snps,dwmac-4.10a"; - reg = <0x40028000 0x8000>; - reg-names = "stmmaceth"; - interrupts = <61>; - interrupt-names = "macirq"; - clock-names = "stmmaceth", "mac-clk-tx", "mac-clk-rx"; - clocks = <&rcc 62>, <&rcc 61>, <&rcc 60>; - st,syscon = <&syscfg 0x4>; - snps,pbl = <8>; - phy-mode = "mii"; - }; + ethernet2: ethernet@40027000 { + compatible = "st,stm32-dwmac", "snps,dwmac-4.10a"; + reg = <0x40028000 0x8000>; + reg-names = "stmmaceth"; + interrupts = <61>; + interrupt-names = "macirq"; + clock-names = "stmmaceth", "mac-clk-tx", "mac-clk-rx"; + clocks = <&rcc 62>, <&rcc 61>, <&rcc 60>; + st,syscon = <&syscfg 0x4>; + snps,pbl = <8>; + phy-mode = "mii"; + }; diff --git a/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml b/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml index 53604fab0b73..08119b6880ee 100644 --- a/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml +++ b/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml @@ -72,9 +72,9 @@ unevaluatedProperties: false examples: - | davinci_mdio: mdio@4a101000 { - compatible = "ti,davinci_mdio"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0x4a101000 0x1000>; - bus_freq = <1000000>; + compatible = "ti,davinci_mdio"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x4a101000 0x1000>; + bus_freq = <1000000>; }; diff --git a/Documentation/devicetree/bindings/net/ti,dp83822.yaml b/Documentation/devicetree/bindings/net/ti,dp83822.yaml index 784866ea392b..50c24248df26 100644 --- a/Documentation/devicetree/bindings/net/ti,dp83822.yaml +++ b/Documentation/devicetree/bindings/net/ti,dp83822.yaml @@ -96,6 +96,32 @@ properties: - master - slave + ti,gpio2-clk-out: + description: | + DP83822 PHY only. + The GPIO2 pin on the DP83822 can be configured as clock output. When + omitted, the PHY's default will be left as is. + + - 'mac-if': In MII mode the clock frequency is 25-MHz, in RMII Mode the + clock frequency is 50-MHz and in RGMII Mode the clock frequency is + 25-MHz. + - 'xi': XI clock(pass-through clock from XI pin). + - 'int-ref': Internal reference clock 25-MHz. + - 'rmii-master-mode-ref': RMII master mode reference clock 50-MHz. RMII + master mode reference clock is identical to MAC IF clock in RMII master + mode. + - 'free-running': Free running clock 125-MHz. + - 'recovered': Recovered clock is a 125-MHz recovered clock from a + connected link partner. + $ref: /schemas/types.yaml#/definitions/string + enum: + - mac-if + - xi + - int-ref + - rmii-master-mode-ref + - free-running + - recovered + required: - reg @@ -110,6 +136,7 @@ examples: reg = <0>; rx-internal-delay-ps = <1>; tx-internal-delay-ps = <1>; + ti,gpio2-clk-out = "xi"; }; }; diff --git a/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml b/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml index 02b6d32003cc..b11894fbaec4 100644 --- a/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml +++ b/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml @@ -302,16 +302,16 @@ examples: ti,fifo-depth = ; }; }; - }; - cpts@3d000 { - compatible = "ti,am65-cpts"; - reg = <0x0 0x3d000 0x0 0x400>; - clocks = <&k3_clks 18 2>; - clock-names = "cpts"; - interrupts-extended = <&gic500 GIC_SPI 858 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "cpts"; - ti,cpts-ext-ts-inputs = <4>; - ti,cpts-periodic-outputs = <2>; + cpts@3d000 { + compatible = "ti,am65-cpts"; + reg = <0x0 0x3d000 0x0 0x400>; + clocks = <&k3_clks 18 2>; + clock-names = "cpts"; + interrupts-extended = <&gic500 GIC_SPI 858 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "cpts"; + ti,cpts-ext-ts-inputs = <4>; + ti,cpts-periodic-outputs = <2>; + }; }; }; diff --git a/Documentation/devicetree/bindings/net/ti,k3-am654-cpts.yaml b/Documentation/devicetree/bindings/net/ti,k3-am654-cpts.yaml index 3888692275ad..3572749147fb 100644 --- a/Documentation/devicetree/bindings/net/ti,k3-am654-cpts.yaml +++ b/Documentation/devicetree/bindings/net/ti,k3-am654-cpts.yaml @@ -131,23 +131,23 @@ examples: #include cpts@310d0000 { - compatible = "ti,am65-cpts"; - reg = <0x310d0000 0x400>; - reg-names = "cpts"; - clocks = <&main_cpts_mux>; - clock-names = "cpts"; - interrupts-extended = <&k3_irq 163 0 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "cpts"; - ti,cpts-periodic-outputs = <6>; - ti,cpts-ext-ts-inputs = <8>; + compatible = "ti,am65-cpts"; + reg = <0x310d0000 0x400>; + reg-names = "cpts"; + clocks = <&main_cpts_mux>; + clock-names = "cpts"; + interrupts-extended = <&k3_irq 163 0 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "cpts"; + ti,cpts-periodic-outputs = <6>; + ti,cpts-ext-ts-inputs = <8>; - main_cpts_mux: refclk-mux { - #clock-cells = <0>; - clocks = <&k3_clks 118 5>, <&k3_clks 118 11>, - <&k3_clks 157 91>, <&k3_clks 157 77>, - <&k3_clks 157 102>, <&k3_clks 157 80>, - <&k3_clks 120 3>, <&k3_clks 121 3>; - assigned-clocks = <&main_cpts_mux>; - assigned-clock-parents = <&k3_clks 118 11>; - }; + main_cpts_mux: refclk-mux { + #clock-cells = <0>; + clocks = <&k3_clks 118 5>, <&k3_clks 118 11>, + <&k3_clks 157 91>, <&k3_clks 157 77>, + <&k3_clks 157 102>, <&k3_clks 157 80>, + <&k3_clks 120 3>, <&k3_clks 121 3>; + assigned-clocks = <&main_cpts_mux>; + assigned-clock-parents = <&k3_clks 118 11>; + }; }; diff --git a/Documentation/devicetree/bindings/net/wireless/marvell,sd8787.yaml b/Documentation/devicetree/bindings/net/wireless/marvell,sd8787.yaml index 1715b22e0dcf..930b700b73d0 100644 --- a/Documentation/devicetree/bindings/net/wireless/marvell,sd8787.yaml +++ b/Documentation/devicetree/bindings/net/wireless/marvell,sd8787.yaml @@ -79,15 +79,14 @@ examples: #include mmc { - #address-cells = <1>; - #size-cells = <0>; + #address-cells = <1>; + #size-cells = <0>; - wifi@1 { - compatible = "marvell,sd8897"; - reg = <1>; - interrupt-parent = <&pio>; - interrupts = <38 IRQ_TYPE_LEVEL_LOW>; - marvell,wakeup-pin = <3>; + wifi@1 { + compatible = "marvell,sd8897"; + reg = <1>; + interrupt-parent = <&pio>; + interrupts = <38 IRQ_TYPE_LEVEL_LOW>; + marvell,wakeup-pin = <3>; }; }; - diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml new file mode 100644 index 000000000000..cbfb559f6b69 --- /dev/null +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml @@ -0,0 +1,204 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/wireless/qcom,ath12k-wsi.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Technologies ath12k wireless devices (PCIe) with WSI interface + +maintainers: + - Jeff Johnson + - Kalle Valo + +description: | + Qualcomm Technologies IEEE 802.11be PCIe devices with WSI interface. + + The ath12k devices (QCN9274) feature WSI support. WSI stands for + WLAN Serial Interface. It is used for the exchange of specific + control information across radios based on the doorbell mechanism. + This WSI connection is essential to exchange control information + among these devices. + + The WSI interface includes TX and RX ports, which are used to connect + multiple WSI-supported devices together, forming a WSI group. + + Diagram to represent one WSI connection (one WSI group) among + three devices. + + +-------+ +-------+ +-------+ + | pcie1 | | pcie2 | | pcie3 | + | | | | | | + +----->| wsi |------->| wsi |------->| wsi |-----+ + | | grp 0 | | grp 0 | | grp 0 | | + | +-------+ +-------+ +-------+ | + +------------------------------------------------------+ + + Diagram to represent two WSI connections (two separate WSI groups) + among four devices. + + +-------+ +-------+ +-------+ +-------+ + | pcie0 | | pcie1 | | pcie2 | | pcie3 | + | | | | | | | | + +-->| wsi |--->| wsi |--+ +-->| wsi |--->| wsi |--+ + | | grp 0 | | grp 0 | | | | grp 1 | | grp 1 | | + | +-------+ +-------+ | | +-------+ +-------+ | + +---------------------------+ +---------------------------+ + +properties: + compatible: + enum: + - pci17cb,1109 # QCN9274 + + reg: + maxItems: 1 + + qcom,ath12k-calibration-variant: + $ref: /schemas/types.yaml#/definitions/string + description: + String to uniquely identify variant of the calibration data for designs + with colliding bus and device ids + + qcom,wsi-controller: + $ref: /schemas/types.yaml#/definitions/flag + description: + The WSI controller device in the WSI group aids (is capable) to + synchronize the Timing Synchronization Function (TSF) clock across + all devices in the WSI group. + + ports: + $ref: /schemas/graph.yaml#/properties/ports + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: + This is the TX port of WSI interface. It is attached to the RX + port of the next device in the WSI connection. + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: + This is the RX port of WSI interface. It is attached to the TX + port of the previous device in the WSI connection. + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + pcie { + #address-cells = <3>; + #size-cells = <2>; + + pcie@0 { + device_type = "pci"; + reg = <0x0 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + ranges; + + wifi@0 { + compatible = "pci17cb,1109"; + reg = <0x0 0x0 0x0 0x0 0x0>; + + qcom,ath12k-calibration-variant = "RDP433_1"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + wifi1_wsi_tx: endpoint { + remote-endpoint = <&wifi2_wsi_rx>; + }; + }; + + port@1 { + reg = <1>; + + wifi1_wsi_rx: endpoint { + remote-endpoint = <&wifi3_wsi_tx>; + }; + }; + }; + }; + }; + + pcie@1 { + device_type = "pci"; + reg = <0x0 0x0 0x1 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + ranges; + + wifi@0 { + compatible = "pci17cb,1109"; + reg = <0x0 0x0 0x0 0x0 0x0>; + + qcom,ath12k-calibration-variant = "RDP433_2"; + qcom,wsi-controller; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + wifi2_wsi_tx: endpoint { + remote-endpoint = <&wifi3_wsi_rx>; + }; + }; + + port@1 { + reg = <1>; + + wifi2_wsi_rx: endpoint { + remote-endpoint = <&wifi1_wsi_tx>; + }; + }; + }; + }; + }; + + pcie@2 { + device_type = "pci"; + reg = <0x0 0x0 0x2 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + ranges; + + wifi@0 { + compatible = "pci17cb,1109"; + reg = <0x0 0x0 0x0 0x0 0x0>; + + qcom,ath12k-calibration-variant = "RDP433_3"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + wifi3_wsi_tx: endpoint { + remote-endpoint = <&wifi1_wsi_rx>; + }; + }; + + port@1 { + reg = <1>; + + wifi3_wsi_rx: endpoint { + remote-endpoint = <&wifi2_wsi_tx>; + }; + }; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml index 80845c722ae4..d37f544ab8aa 100644 --- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml +++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml @@ -20,18 +20,22 @@ properties: - qcom,apq8064-qfprom - qcom,apq8084-qfprom - qcom,ipq5332-qfprom + - qcom,ipq5424-qfprom - qcom,ipq6018-qfprom - qcom,ipq8064-qfprom - qcom,ipq8074-qfprom - qcom,ipq9574-qfprom - qcom,msm8226-qfprom - qcom,msm8916-qfprom + - qcom,msm8917-qfprom - qcom,msm8974-qfprom - qcom,msm8976-qfprom - qcom,msm8996-qfprom - qcom,msm8998-qfprom - qcom,qcm2290-qfprom - qcom,qcs404-qfprom + - qcom,qcs615-qfprom + - qcom,qcs8300-qfprom - qcom,sc7180-qfprom - qcom,sc7280-qfprom - qcom,sc8280xp-qfprom diff --git a/Documentation/devicetree/bindings/nvmem/rmem.yaml b/Documentation/devicetree/bindings/nvmem/rmem.yaml index 1ec0d09bcafa..85f9f5de3906 100644 --- a/Documentation/devicetree/bindings/nvmem/rmem.yaml +++ b/Documentation/devicetree/bindings/nvmem/rmem.yaml @@ -16,6 +16,7 @@ properties: compatible: items: - enum: + - mobileye,eyeq5-bootloader-config - raspberrypi,bootloader-config - raspberrypi,bootloader-public-key - const: nvmem-rmem diff --git a/Documentation/devicetree/bindings/nvmem/sprd,sc2731-efuse.yaml b/Documentation/devicetree/bindings/nvmem/sprd,sc2731-efuse.yaml index dc25fe3d1841..8672bde24a9b 100644 --- a/Documentation/devicetree/bindings/nvmem/sprd,sc2731-efuse.yaml +++ b/Documentation/devicetree/bindings/nvmem/sprd,sc2731-efuse.yaml @@ -36,33 +36,4 @@ allOf: - $ref: nvmem-deprecated-cells.yaml# unevaluatedProperties: false - -examples: - - | - pmic { - #address-cells = <1>; - #size-cells = <0>; - - efuse@380 { - compatible = "sprd,sc2731-efuse"; - reg = <0x380>; - hwlocks = <&hwlock 12>; - #address-cells = <1>; - #size-cells = <1>; - - /* Data cells */ - fgu_calib: calib@6 { - reg = <0x6 0x2>; - bits = <0 9>; - }; - - adc_big_scale: calib@24 { - reg = <0x24 0x2>; - }; - - adc_small_scale: calib@26 { - reg = <0x26 0x2>; - }; - }; - }; ... diff --git a/Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml b/Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml index ec5e424bb3c8..75ab552f6ecd 100644 --- a/Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml +++ b/Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml @@ -22,6 +22,7 @@ allOf: properties: compatible: enum: + - allwinner,sun50i-a100-operating-points - allwinner,sun50i-h6-operating-points - allwinner,sun50i-h616-operating-points diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml index a8b34f58f8f4..cddbe21f99f2 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml @@ -17,11 +17,11 @@ description: properties: clocks: minItems: 3 - maxItems: 4 + maxItems: 5 clock-names: minItems: 3 - maxItems: 4 + maxItems: 5 num-lanes: const: 1 diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml index 84ca12e8b25b..0b3526de1d62 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml @@ -22,6 +22,7 @@ properties: - fsl,imx8mm-pcie-ep - fsl,imx8mq-pcie-ep - fsl,imx8mp-pcie-ep + - fsl,imx8q-pcie-ep - fsl,imx95-pcie-ep clocks: @@ -74,6 +75,20 @@ allOf: - const: dbi2 - const: atu + - if: + properties: + compatible: + enum: + - fsl,imx8q-pcie-ep + then: + properties: + reg: + maxItems: 2 + reg-names: + items: + - const: dbi + - const: addr_space + - if: properties: compatible: @@ -103,13 +118,21 @@ allOf: properties: clocks: minItems: 4 + maxItems: 4 clock-names: items: - const: pcie - const: pcie_bus - const: pcie_phy - const: pcie_aux - else: + + - if: + properties: + compatible: + enum: + - fsl,imx8mm-pcie-ep + - fsl,imx8mp-pcie-ep + then: properties: clocks: maxItems: 3 @@ -119,6 +142,20 @@ allOf: - const: pcie_bus - const: pcie_aux + - if: + properties: + compatible: + enum: + - fsl,imxq-pcie-ep + then: + properties: + clocks: + maxItems: 3 + clock-names: + items: + - const: dbi + - const: mstr + - const: slv unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml index 1e05c560d797..4c76cd3f98a9 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml @@ -40,10 +40,11 @@ properties: - description: PCIe PHY clock. - description: Additional required clock entry for imx6sx-pcie, imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep. + - description: PCIe reference clock. clock-names: minItems: 3 - maxItems: 4 + maxItems: 5 interrupts: items: @@ -127,7 +128,7 @@ allOf: then: properties: clocks: - minItems: 4 + maxItems: 4 clock-names: items: - const: pcie @@ -140,11 +141,10 @@ allOf: compatible: enum: - fsl,imx8mq-pcie - - fsl,imx95-pcie then: properties: clocks: - minItems: 4 + maxItems: 4 clock-names: items: - const: pcie @@ -200,6 +200,23 @@ allOf: - const: mstr - const: slv + - if: + properties: + compatible: + enum: + - fsl,imx95-pcie + then: + properties: + clocks: + maxItems: 5 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_phy + - const: pcie_aux + - const: ref + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/pci/layerscape-pcie-gen4.txt b/Documentation/devicetree/bindings/pci/layerscape-pcie-gen4.txt deleted file mode 100644 index b40fb5d15d3d..000000000000 --- a/Documentation/devicetree/bindings/pci/layerscape-pcie-gen4.txt +++ /dev/null @@ -1,52 +0,0 @@ -NXP Layerscape PCIe Gen4 controller - -This PCIe controller is based on the Mobiveil PCIe IP and thus inherits all -the common properties defined in mobiveil-pcie.txt. - -Required properties: -- compatible: should contain the platform identifier such as: - "fsl,lx2160a-pcie" -- reg: base addresses and lengths of the PCIe controller register blocks. - "csr_axi_slave": Bridge config registers - "config_axi_slave": PCIe controller registers -- interrupts: A list of interrupt outputs of the controller. Must contain an - entry for each entry in the interrupt-names property. -- interrupt-names: It could include the following entries: - "intr": The interrupt that is asserted for controller interrupts - "aer": Asserted for aer interrupt when chip support the aer interrupt with - none MSI/MSI-X/INTx mode,but there is interrupt line for aer. - "pme": Asserted for pme interrupt when chip support the pme interrupt with - none MSI/MSI-X/INTx mode,but there is interrupt line for pme. -- dma-coherent: Indicates that the hardware IP block can ensure the coherency - of the data transferred from/to the IP block. This can avoid the software - cache flush/invalid actions, and improve the performance significantly. -- msi-parent : See the generic MSI binding described in - Documentation/devicetree/bindings/interrupt-controller/msi.txt. - -Example: - - pcie@3400000 { - compatible = "fsl,lx2160a-pcie"; - reg = <0x00 0x03400000 0x0 0x00100000 /* controller registers */ - 0x80 0x00000000 0x0 0x00001000>; /* configuration space */ - reg-names = "csr_axi_slave", "config_axi_slave"; - interrupts = , /* AER interrupt */ - , /* PME interrupt */ - ; /* controller interrupt */ - interrupt-names = "aer", "pme", "intr"; - #address-cells = <3>; - #size-cells = <2>; - device_type = "pci"; - apio-wins = <8>; - ppio-wins = <8>; - dma-coherent; - bus-range = <0x0 0xff>; - msi-parent = <&its>; - ranges = <0x82000000 0x0 0x40000000 0x80 0x40000000 0x0 0x40000000>; - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 0 7>; - interrupt-map = <0000 0 0 1 &gic 0 0 GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>, - <0000 0 0 2 &gic 0 0 GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>, - <0000 0 0 3 &gic 0 0 GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>, - <0000 0 0 4 &gic 0 0 GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>; - }; diff --git a/Documentation/devicetree/bindings/pci/mbvl,gpex40-pcie.yaml b/Documentation/devicetree/bindings/pci/mbvl,gpex40-pcie.yaml new file mode 100644 index 000000000000..d286b77921e0 --- /dev/null +++ b/Documentation/devicetree/bindings/pci/mbvl,gpex40-pcie.yaml @@ -0,0 +1,173 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pci/mbvl,gpex40-pcie.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Mobiveil AXI PCIe Host Bridge + +maintainers: + - Frank Li + +description: + Mobiveil's GPEX 4.0 is a PCIe Gen4 host bridge IP. This configurable IP + has up to 8 outbound and inbound windows for address translation. + + NXP Layerscape PCIe Gen4 controller (Deprecated) base on Mobiveil's GPEX 4.0. + +properties: + compatible: + enum: + - fsl,lx2160a-pcie + - mbvl,gpex40-pcie + + reg: + items: + - description: PCIe controller registers + - description: Bridge config registers + - description: GPIO registers to control slot power + - description: MSI registers + minItems: 2 + + reg-names: + items: + - const: csr_axi_slave + - const: config_axi_slave + - const: gpio_slave + - const: apb_csr + minItems: 2 + + apio-wins: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + number of requested APIO outbound windows + 1. Config window + 2. Memory window + default: 2 + maximum: 256 + + ppio-wins: + $ref: /schemas/types.yaml#/definitions/uint32 + description: number of requested PPIO inbound windows + default: 1 + maximum: 256 + + interrupt-controller: true + + "#interrupt-cells": + const: 1 + + interrupts: + minItems: 1 + maxItems: 3 + + interrupt-names: + minItems: 1 + maxItems: 3 + + dma-coherent: true + + msi-parent: true + +required: + - compatible + - reg + - reg-names + +allOf: + - $ref: /schemas/pci/pci-host-bridge.yaml# + - if: + properties: + compatible: + enum: + - fsl,lx2160a-pcie + then: + properties: + reg: + maxItems: 2 + + reg-names: + maxItems: 2 + + interrupts: + minItems: 3 + + interrupt-names: + items: + - const: aer + - const: pme + - const: intr + else: + properties: + dma-coherent: false + msi-parent: false + interrupts: + maxItems: 1 + interrupt-names: false + +unevaluatedProperties: false + +examples: + - | + #include + + pcie@b0000000 { + compatible = "mbvl,gpex40-pcie"; + reg = <0xb0000000 0x00010000>, + <0xa0000000 0x00001000>, + <0xff000000 0x00200000>, + <0xb0010000 0x00001000>; + reg-names = "csr_axi_slave", + "config_axi_slave", + "gpio_slave", + "apb_csr"; + ranges = <0x83000000 0 0x00000000 0xa8000000 0 0x8000000>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + apio-wins = <2>; + ppio-wins = <1>; + bus-range = <0x00 0xff>; + interrupt-controller; + #interrupt-cells = <1>; + interrupt-parent = <&gic>; + interrupts = ; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 0 &pci_express 0>, + <0 0 0 1 &pci_express 1>, + <0 0 0 2 &pci_express 2>, + <0 0 0 3 &pci_express 3>; + }; + + - | + #include + + soc { + #address-cells = <2>; + #size-cells = <2>; + pcie@3400000 { + compatible = "fsl,lx2160a-pcie"; + reg = <0x00 0x03400000 0x0 0x00100000 /* controller registers */ + 0x80 0x00000000 0x0 0x00001000>; /* configuration space */ + reg-names = "csr_axi_slave", "config_axi_slave"; + ranges = <0x82000000 0x0 0x40000000 0x80 0x40000000 0x0 0x40000000>; + interrupts = , /* AER interrupt */ + , /* PME interrupt */ + ; /* controller interrupt */ + interrupt-names = "aer", "pme", "intr"; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + apio-wins = <8>; + ppio-wins = <8>; + dma-coherent; + bus-range = <0x00 0xff>; + msi-parent = <&its>; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0000 0 0 1 &gic 0 0 GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>, + <0000 0 0 2 &gic 0 0 GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>, + <0000 0 0 3 &gic 0 0 GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>, + <0000 0 0 4 &gic 0 0 GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>; + }; + }; diff --git a/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml b/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml index 2e1547569702..103574d18dbc 100644 --- a/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml +++ b/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml @@ -50,6 +50,8 @@ properties: items: pattern: '^fic[0-3]$' + dma-coherent: true + ranges: minItems: 1 maxItems: 3 diff --git a/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt b/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt deleted file mode 100644 index 64156993e052..000000000000 --- a/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt +++ /dev/null @@ -1,72 +0,0 @@ -* Mobiveil AXI PCIe Root Port Bridge DT description - -Mobiveil's GPEX 4.0 is a PCIe Gen4 root port bridge IP. This configurable IP -has up to 8 outbound and inbound windows for the address translation. - -Required properties: -- #address-cells: Address representation for root ports, set to <3> -- #size-cells: Size representation for root ports, set to <2> -- #interrupt-cells: specifies the number of cells needed to encode an - interrupt source. The value must be 1. -- compatible: Should contain "mbvl,gpex40-pcie" -- reg: Should contain PCIe registers location and length - Mandatory: - "config_axi_slave": PCIe controller registers - "csr_axi_slave" : Bridge config registers - Optional: - "gpio_slave" : GPIO registers to control slot power - "apb_csr" : MSI registers - -- device_type: must be "pci" -- apio-wins : number of requested apio outbound windows - default 2 outbound windows are configured - - 1. Config window - 2. Memory window -- ppio-wins : number of requested ppio inbound windows - default 1 inbound memory window is configured. -- bus-range: PCI bus numbers covered -- interrupt-controller: identifies the node as an interrupt controller -- #interrupt-cells: specifies the number of cells needed to encode an - interrupt source. The value must be 1. -- interrupts: The interrupt line of the PCIe controller - last cell of this field is set to 4 to - denote it as IRQ_TYPE_LEVEL_HIGH type interrupt. -- interrupt-map-mask, - interrupt-map: standard PCI properties to define the mapping of the - PCI interface to interrupt numbers. -- ranges: ranges for the PCI memory regions (I/O space region is not - supported by hardware) - Please refer to the standard PCI bus binding document for a more - detailed explanation - - -Example: -++++++++ - pcie0: pcie@a0000000 { - #address-cells = <3>; - #size-cells = <2>; - compatible = "mbvl,gpex40-pcie"; - reg = <0xa0000000 0x00001000>, - <0xb0000000 0x00010000>, - <0xff000000 0x00200000>, - <0xb0010000 0x00001000>; - reg-names = "config_axi_slave", - "csr_axi_slave", - "gpio_slave", - "apb_csr"; - device_type = "pci"; - apio-wins = <2>; - ppio-wins = <1>; - bus-range = <0x00000000 0x000000ff>; - interrupt-controller; - interrupt-parent = <&gic>; - #interrupt-cells = <1>; - interrupts = < 0 89 4 >; - interrupt-map-mask = <0 0 0 7>; - interrupt-map = <0 0 0 0 &pci_express 0>, - <0 0 0 1 &pci_express 1>, - <0 0 0 2 &pci_express 2>, - <0 0 0 3 &pci_express 3>; - ranges = < 0x83000000 0 0x00000000 0xa8000000 0 0x8000000>; - - }; diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml index 2b5498a35dcc..dbce671ba011 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml +++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml @@ -57,9 +57,10 @@ properties: interrupts: minItems: 8 - maxItems: 8 + maxItems: 9 interrupt-names: + minItems: 8 items: - const: msi0 - const: msi1 @@ -69,6 +70,7 @@ properties: - const: msi5 - const: msi6 - const: msi7 + - const: global resets: minItems: 1 @@ -139,9 +141,10 @@ examples: , , , - ; + , + ; interrupt-names = "msi0", "msi1", "msi2", "msi3", - "msi4", "msi5", "msi6", "msi7"; + "msi4", "msi5", "msi6", "msi7", "global"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; interrupt-map = <0 0 0 1 &intc 0 0 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml index bd87f6b49d68..7235d6554cfb 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml +++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml @@ -31,6 +31,10 @@ properties: - qcom,pcie-qcs404 - qcom,pcie-sdm845 - qcom,pcie-sdx55 + - items: + - enum: + - qcom,pcie-ipq5424 + - const: qcom,pcie-ipq9574 - items: - const: qcom,pcie-msm8998 - const: qcom,pcie-msm8996 diff --git a/Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml b/Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml index 989fb0fa2577..b63a759ec2d7 100644 --- a/Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml +++ b/Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml @@ -17,6 +17,7 @@ properties: enum: - xlnx,versal-cpm-host-1.00 - xlnx,versal-cpm5-host + - xlnx,versal-cpm5-host1 reg: items: diff --git a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml index d3cd7997879f..1b3de6678c08 100644 --- a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml +++ b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml @@ -13,6 +13,7 @@ properties: compatible: enum: - rockchip,rk3568-naneng-combphy + - rockchip,rk3576-naneng-combphy - rockchip,rk3588-naneng-combphy reg: diff --git a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml index 58ce2d91d28c..f60804687412 100644 --- a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml @@ -15,12 +15,21 @@ description: properties: compatible: - enum: - - qcom,ipq6018-qmp-pcie-phy - - qcom,ipq8074-qmp-gen3-pcie-phy - - qcom,ipq8074-qmp-pcie-phy - - qcom,ipq9574-qmp-gen3x1-pcie-phy - - qcom,ipq9574-qmp-gen3x2-pcie-phy + oneOf: + - enum: + - qcom,ipq6018-qmp-pcie-phy + - qcom,ipq8074-qmp-gen3-pcie-phy + - qcom,ipq8074-qmp-pcie-phy + - qcom,ipq9574-qmp-gen3x1-pcie-phy + - qcom,ipq9574-qmp-gen3x2-pcie-phy + - items: + - enum: + - qcom,ipq5424-qmp-gen3x1-pcie-phy + - const: qcom,ipq9574-qmp-gen3x1-pcie-phy + - items: + - enum: + - qcom,ipq5424-qmp-gen3x2-pcie-phy + - const: qcom,ipq9574-qmp-gen3x2-pcie-phy reg: items: diff --git a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml index 4aed4b5d65ec..39851ba9de43 100644 --- a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml @@ -18,6 +18,7 @@ properties: oneOf: - items: - enum: + - qcom,ipq5424-qusb2-phy - qcom,ipq6018-qusb2-phy - qcom,ipq8074-qusb2-phy - qcom,ipq9574-qusb2-phy diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml index 13fdf5f1beba..89391649e0b5 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml @@ -16,8 +16,10 @@ description: properties: compatible: enum: + - qcom,qcs615-qmp-gen3x1-pcie-phy - qcom,sa8775p-qmp-gen4x2-pcie-phy - qcom,sa8775p-qmp-gen4x4-pcie-phy + - qcom,sar2130p-qmp-gen3x2-pcie-phy - qcom,sc8180x-qmp-pcie-phy - qcom,sc8280xp-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x2-pcie-phy @@ -32,6 +34,7 @@ properties: - qcom,sm8250-qmp-gen3x2-pcie-phy - qcom,sm8250-qmp-modem-pcie-phy - qcom,sm8350-qmp-gen3x1-pcie-phy + - qcom,sm8350-qmp-gen3x2-pcie-phy - qcom,sm8450-qmp-gen3x1-pcie-phy - qcom,sm8450-qmp-gen4x2-pcie-phy - qcom,sm8550-qmp-gen3x2-pcie-phy @@ -139,6 +142,7 @@ allOf: compatible: contains: enum: + - qcom,sar2130p-qmp-gen3x2-pcie-phy - qcom,sc8180x-qmp-pcie-phy - qcom,sdm845-qhp-pcie-phy - qcom,sdm845-qmp-pcie-phy @@ -149,6 +153,7 @@ allOf: - qcom,sm8250-qmp-gen3x2-pcie-phy - qcom,sm8250-qmp-modem-pcie-phy - qcom,sm8350-qmp-gen3x1-pcie-phy + - qcom,sm8350-qmp-gen3x2-pcie-phy - qcom,sm8450-qmp-gen3x1-pcie-phy - qcom,sm8450-qmp-gen3x2-pcie-phy - qcom,sm8550-qmp-gen3x2-pcie-phy @@ -167,6 +172,7 @@ allOf: compatible: contains: enum: + - qcom,qcs615-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x2-pcie-phy - qcom,sc8280xp-qmp-gen3x4-pcie-phy diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml index baf5134ea3d8..a1b55168e050 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml @@ -16,6 +16,7 @@ description: properties: compatible: enum: + - qcom,ipq5424-qmp-usb3-phy - qcom,ipq6018-qmp-usb3-phy - qcom,ipq8074-qmp-usb3-phy - qcom,ipq9574-qmp-usb3-phy @@ -89,6 +90,7 @@ allOf: compatible: contains: enum: + - qcom,ipq5424-qmp-usb3-phy - qcom,ipq6018-qmp-usb3-phy - qcom,ipq8074-qmp-usb3-phy - qcom,ipq9574-qmp-usb3-phy diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml index 2d0d7e9e6431..358a6736a951 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml @@ -16,6 +16,7 @@ description: properties: compatible: enum: + - qcom,sar2130p-qmp-usb3-dp-phy - qcom,sc7180-qmp-usb3-dp-phy - qcom,sc7280-qmp-usb3-dp-phy - qcom,sc8180x-qmp-usb3-dp-phy @@ -127,6 +128,7 @@ allOf: properties: compatible: enum: + - qcom,sar2130p-qmp-usb3-dp-phy - qcom,sc8280xp-qmp-usb43dp-phy - qcom,sm6350-qmp-usb3-dp-phy - qcom,sm8550-qmp-usb3-dp-phy diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sun4i-a10-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/allwinner,sun4i-a10-pinctrl.yaml index 450240570314..990b78765427 100644 --- a/Documentation/devicetree/bindings/pinctrl/allwinner,sun4i-a10-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sun4i-a10-pinctrl.yaml @@ -44,6 +44,7 @@ properties: - allwinner,sun8i-r40-pinctrl - allwinner,sun8i-v3-pinctrl - allwinner,sun8i-v3s-pinctrl + - allwinner,sun8i-v853-pinctrl - allwinner,sun9i-a80-pinctrl - allwinner,sun9i-a80-r-pinctrl - allwinner,sun20i-d1-pinctrl @@ -179,6 +180,18 @@ allOf: minItems: 7 maxItems: 7 + - if: + properties: + compatible: + enum: + - allwinner,sun8i-v853-pinctrl + + then: + properties: + interrupts: + minItems: 8 + maxItems: 8 + - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/atmel,at91rm9200-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/atmel,at91rm9200-pinctrl.yaml index 1bb386b42039..a7ede29c1444 100644 --- a/Documentation/devicetree/bindings/pinctrl/atmel,at91rm9200-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/atmel,at91rm9200-pinctrl.yaml @@ -145,40 +145,40 @@ additionalProperties: examples: - | - #include - #include - #include + #include + #include + #include - pinctrl@fffff400 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "atmel,at91rm9200-pinctrl", "simple-mfd"; - ranges = <0xfffff400 0xfffff400 0x600>; + pinctrl@fffff400 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "atmel,at91rm9200-pinctrl", "simple-mfd"; + ranges = <0xfffff400 0xfffff400 0x600>; - atmel,mux-mask = < - /* A B */ - 0xffffffff 0xffc00c3b /* pioA */ - 0xffffffff 0x7fff3ccf /* pioB */ - 0xffffffff 0x007fffff /* pioC */ - >; + atmel,mux-mask = < + /* A B */ + 0xffffffff 0xffc00c3b /* pioA */ + 0xffffffff 0x7fff3ccf /* pioB */ + 0xffffffff 0x007fffff /* pioC */ + >; - dbgu { - pinctrl_dbgu: dbgu-0 { - atmel,pins = - ; - }; - }; + dbgu { + dbgu-0 { + atmel,pins = + ; + }; + }; - pioA: gpio@fffff400 { - compatible = "atmel,at91rm9200-gpio"; - reg = <0xfffff400 0x200>; - interrupts = <2 IRQ_TYPE_LEVEL_HIGH 1>; - #gpio-cells = <2>; - gpio-controller; - interrupt-controller; - #interrupt-cells = <2>; - clocks = <&pmc PMC_TYPE_PERIPHERAL 2>; - }; - }; + gpio@fffff400 { + compatible = "atmel,at91rm9200-gpio"; + reg = <0xfffff400 0x200>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH 1>; + #gpio-cells = <2>; + gpio-controller; + interrupt-controller; + #interrupt-cells = <2>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 2>; + }; + }; ... diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7988-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7988-pinctrl.yaml new file mode 100644 index 000000000000..26dfe7e7735a --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7988-pinctrl.yaml @@ -0,0 +1,575 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/mediatek,mt7988-pinctrl.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MediaTek MT7988 Pin Controller + +maintainers: + - Sean Wang + +description: + The MediaTek's MT7988 Pin controller is used to control SoC pins. + +properties: + compatible: + enum: + - mediatek,mt7988-pinctrl + + reg: + minItems: 7 + maxItems: 7 + + reg-names: + items: + - const: gpio + - const: iocfg_tr + - const: iocfg_br + - const: iocfg_rb + - const: iocfg_lb + - const: iocfg_tl + - const: eint + + gpio-controller: true + + "#gpio-cells": + const: 2 + + gpio-ranges: + minItems: 1 + maxItems: 5 + description: + GPIO valid number range. + + interrupt-controller: true + + interrupts: + maxItems: 1 + + "#interrupt-cells": + const: 2 + +allOf: + - $ref: pinctrl.yaml# + +required: + - compatible + - reg + - reg-names + - gpio-controller + - "#gpio-cells" + +patternProperties: + '-pins$': + type: object + additionalProperties: false + + properties: + mux: + type: object + additionalProperties: false + $ref: /schemas/pinctrl/pinmux-node.yaml + description: | + pinmux configuration nodes. + + The following table shows the effective values of "group", "function" + properties and chip pinout pins + + groups function pins (in pin#) + --------------------------------------------------------------------- + "tops_jtag0_0" "jtag" 0, 1, 2, 3, 4 + "wo0_jtag" "jtag" 50, 51, 52, 53, 54 + "wo1_jtag" "jtag" 50, 51, 52, 53, 54 + "wo2_jtag" "jtag" 50, 51, 52, 53, 54 + "jtag" "jtag" 58, 59, 60, 61, 62 + "tops_jtag0_1" "jtag" 58, 59, 60, 61, 62 + "int_usxgmii" "int_usxgmii" 2, 3 + "pwm0" "pwm" 57 + "pwm1" "pwm" 21 + "pwm2" "pwm" 80 + "pwm2_0" "pwm" 58 + "pwm3" "pwm" 81 + "pwm3_0" "pwm" 59 + "pwm4" "pwm" 82 + "pwm4_0" "pwm" 60 + "pwm5" "pwm" 83 + "pwm5_0" "pwm" 61 + "pwm6" "pwm" 69 + "pwm6_0" "pwm" 62 + "pwm7" "pwm" 70 + "pwm7_0" "pwm" 4 + "dfd" "dfd" 0, 1, 2, 3, 4 + "xfi_phy0_i2c0" "i2c" 0, 1 + "xfi_phy1_i2c0" "i2c" 0, 1 + "xfi_phy_pll_i2c0" "i2c" 3, 4 + "xfi_phy_pll_i2c1" "i2c" 3, 4 + "i2c0_0" "i2c" 5, 6 + "i2c1_sfp" "i2c" 5, 6 + "xfi_pextp_phy0_i2c" "i2c" 5, 6 + "xfi_pextp_phy1_i2c" "i2c" 5, 6 + "i2c0_1" "i2c" 15, 16 + "u30_phy_i2c0" "i2c" 15, 16 + "u32_phy_i2c0" "i2c" 15, 16 + "xfi_phy0_i2c1" "i2c" 15, 16 + "xfi_phy1_i2c1" "i2c" 15, 16 + "xfi_phy_pll_i2c2" "i2c" 15, 16 + "i2c1_0" "i2c" 17, 18 + "u30_phy_i2c1" "i2c" 17, 18 + "u32_phy_i2c1" "i2c" 17, 18 + "xfi_phy_pll_i2c3" "i2c" 17, 18 + "sgmii0_i2c" "i2c" 17, 18 + "sgmii1_i2c" "i2c" 17, 18 + "i2c1_2" "i2c" 69, 70 + "i2c2_0" "i2c" 69, 70 + "i2c2_1" "i2c" 71, 72 + "mdc_mdio0" "eth" 5, 6 + "2p5g_ext_mdio" "eth" 28, 29 + "gbe_ext_mdio" "eth" 30, 31 + "mdc_mdio1" "eth" 69, 70 + "pcie_wake_n0_0" "pcie" 7 + "pcie_clk_req_n0_0" "pcie" 8 + "pcie_wake_n3_0" "pcie" 9 + "pcie_clk_req_n3" "pcie" 10 + "pcie_clk_req_n0_1" "pcie" 10 + "pcie_p0_phy_i2c" "pcie" 7, 8 + "pcie_p1_phy_i2c" "pcie" 7, 8 + "pcie_p3_phy_i2c" "pcie" 9, 10 + "pcie_p2_phy_i2c" "pcie" 7, 8 + "ckm_phy_i2c" "pcie" 9, 10 + "pcie_wake_n0_1" "pcie" 13 + "pcie_wake_n3_1" "pcie" 14 + "pcie_2l_0_pereset" "pcie" 19 + "pcie_1l_1_pereset" "pcie" 20 + "pcie_clk_req_n2_1" "pcie" 63 + "pcie_2l_1_pereset" "pcie" 73 + "pcie_1l_0_pereset" "pcie" 74 + "pcie_wake_n1_0" "pcie" 75 + "pcie_clk_req_n1" "pcie" 76 + "pcie_wake_n2_0" "pcie" 77 + "pcie_clk_req_n2_0" "pcie" 78 + "pcie_wake_n2_1" "pcie" 79 + "pmic" "pmic" 11 + "watchdog" "watchdog" 12 + "spi0_wp_hold" "spi" 22, 23 + "spi0" "spi" 24, 25, 26, 27 + "spi1" "spi" 28, 29, 30, 31 + "spi2" "spi" 32, 33, 34, 35 + "spi2_wp_hold" "spi" 36, 37 + "snfi" "flash" 22, 23, 24, 25, 26, 27 + "emmc_45" "flash" 21, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37 + "sdcard" "flash" 32, 33, 34, 35, 36, 37 + "emmc_51" "flash" 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49 + "uart2" "uart" 0, 1, 2, 3 + "tops_uart0_0" "uart" 22, 23 + "uart2_0" "uart" 28, 29, 30, 31 + "uart1_0" "uart" 32, 33, 34, 35 + "uart2_1" "uart" 32, 33, 34, 35 + "net_wo0_uart_txd_0" "uart" 28 + "net_wo1_uart_txd_0" "uart" 29 + "net_wo2_uart_txd_0" "uart" 30 + "tops_uart1_0" "uart" 28, 29 + "tops_uart0_1" "uart" 30, 31 + "tops_uart1_1" "uart" 36, 37 + "uart0" "uart" 55, 56 + "tops_uart0_2" "uart" 55, 56 + "uart2_2" "uart" 50, 51, 52, 53 + "uart1_1" "uart" 58, 59, 60, 61 + "uart2_3" "uart" 58, 59, 60, 61 + "uart1_2" "uart" 80, 81, 82, 83 + "uart1_2_lite" "uart" 80, 81 + "tops_uart1_2" "uart" 80, 81 + "net_wo0_uart_txd_1" "uart" 80 + "net_wo1_uart_txd_1" "uart" 81 + "net_wo2_uart_txd_1" "uart" 82 + "udi" "udi" 32, 33, 34, 35, 36 + "i2s" "audio" 50, 51, 52, 53, 54 + "pcm" "audio" 50, 51, 52, 53 + "gbe0_led1" "led" 58 + "gbe1_led1" "led" 59 + "gbe2_led1" "led" 60 + "gbe3_led1" "led" 61 + "2p5gbe_led1" "led" 62 + "gbe0_led0" "led" 64 + "gbe1_led0" "led" 65 + "gbe2_led0" "led" 66 + "gbe3_led0" "led" 67 + "2p5gbe_led0" "led" 68 + "drv_vbus_p1" "usb" 63 + "drv_vbus" "usb" 79 + + properties: + function: + description: + A string containing the name of the function to mux to the group. + enum: [audio, dfd, eth, flash, i2c, int_usxgmii, jtag, led, pcie, pmic, pwm, spi, + uart, udi, usb, watchdog] + groups: + description: + An array of strings. Each string contains the name of a group. + + required: + - function + - groups + + allOf: + - if: + properties: + function: + const: audio + then: + properties: + groups: + enum: [i2s, pcm] + - if: + properties: + function: + const: jtag + then: + properties: + groups: + enum: [jtag, tops_jtag0_0, tops_jtag0_1, wo0_jtag, wo1_jtag, wo2_jtag] + - if: + properties: + function: + const: int_usxgmii + then: + properties: + groups: + const: int_usxgmii + - if: + properties: + function: + const: dfd + then: + properties: + groups: + const: dfd + - if: + properties: + function: + const: flash + then: + properties: + groups: + enum: [emmc_45, emmc_51, sdcard, snfi] + - if: + properties: + function: + const: eth + then: + properties: + groups: + enum: [2p5g_ext_mdio, gbe_ext_mdio, mdc_mdio0, mdc_mdio1] + - if: + properties: + function: + const: i2c + then: + properties: + groups: + enum: [xfi_phy0_i2c0, xfi_phy1_i2c0, xfi_phy_pll_i2c0, + xfi_phy_pll_i2c1, i2c0_0, i2c1_sfp, xfi_pextp_phy0_i2c, + xfi_pextp_phy1_i2c, i2c0_1, u30_phy_i2c0, u32_phy_i2c0, + xfi_phy0_i2c1, xfi_phy1_i2c1, xfi_phy_pll_i2c2, i2c1_0, + u30_phy_i2c1, u32_phy_i2c1, xfi_phy_pll_i2c3, sgmii0_i2c, + sgmii1_i2c, i2c1_2, i2c2_0, i2c2_1] + - if: + properties: + function: + const: led + then: + properties: + groups: + enum: [2p5gbe_led0, 2p5gbe_led1, gbe0_led0, gbe0_led1, gbe1_led0, gbe1_led1, + gbe2_led0, gbe2_led1, gbe3_led0, gbe3_led1, wf5g_led0, wf5g_led1] + - if: + properties: + function: + const: pcie + then: + properties: + groups: + items: + enum: [pcie_wake_n0_0, pcie_clk_req_n0_0, pcie_wake_n3_0, + pcie_clk_req_n3, pcie_p0_phy_i2c, pcie_p1_phy_i2c, + pcie_p3_phy_i2c, pcie_p2_phy_i2c, ckm_phy_i2c, + pcie_wake_n0_1, pcie_wake_n3_1, pcie_2l_0_pereset, + pcie_1l_1_pereset, pcie_clk_req_n2_1, pcie_2l_1_pereset, + pcie_1l_0_pereset, pcie_wake_n1_0, pcie_clk_req_n1, + pcie_wake_n2_0, pcie_clk_req_n2_0, pcie_wake_n2_1, + pcie_clk_req_n0_1] + maxItems: 3 + - if: + properties: + function: + const: pmic + then: + properties: + groups: + const: pmic + - if: + properties: + function: + const: pwm + then: + properties: + groups: + items: + enum: [pwm0, pwm1, pwm2, pwm2_0, pwm3, pwm3_0, pwm4, pwm4_0, pwm5, pwm5_0, + pwm6, pwm6_0, pwm7, pwm7_0] + maxItems: 2 + - if: + properties: + function: + const: spi + then: + properties: + groups: + items: + enum: [spi0, spi0_wp_hold, spi1, spi2, spi2_wp_hold] + maxItems: 2 + - if: + properties: + function: + const: uart + then: + properties: + groups: + items: + enum: [net_wo0_uart_txd_0, net_wo0_uart_txd_1, net_wo1_uart_txd_0, + net_wo1_uart_txd_1, net_wo2_uart_txd_0, net_wo2_uart_txd_1, + tops_uart0_0, tops_uart0_1, tops_uart0_2, tops_uart1_0, + tops_uart1_1, tops_uart1_2, uart0, uart1_0, uart1_1, uart1_2, + uart1_2_lite, uart2, uart2_0, uart2_1, uart2_3] + maxItems: 2 + - if: + properties: + function: + const: watchdog + then: + properties: + groups: + const: watchdog + - if: + properties: + function: + const: udi + then: + properties: + groups: + const: udi + - if: + properties: + function: + const: usb + then: + properties: + groups: + items: + enum: [drv_vbus, drv_vbus_p1] + maxItems: 1 + + patternProperties: + '^conf(-[-a-z]*)?$': + type: object + additionalProperties: false + description: + pinconf configuration nodes. + $ref: /schemas/pinctrl/pincfg-node.yaml + + properties: + pins: + description: + An array of strings. Each string contains the name of a pin. + items: + enum: [UART2_RXD, UART2_TXD, UART2_CTS, UART2_RTS, GPIO_A, SMI_0_MDC, + SMI_0_MDIO, PCIE30_2L_0_WAKE_N, PCIE30_2L_0_CLKREQ_N, + PCIE30_1L_1_WAKE_N, PCIE30_1L_1_CLKREQ_N, GPIO_P, WATCHDOG, + GPIO_RESET, GPIO_WPS, PMIC_I2C_SCL, PMIC_I2C_SDA, I2C_1_SCL, + I2C_1_SDA, PCIE30_2L_0_PRESET_N, PCIE30_1L_1_PRESET_N, PWMD1, + SPI0_WP, SPI0_HOLD, SPI0_CSB, SPI0_MISO, SPI0_MOSI, SPI0_CLK, + SPI1_CSB, SPI1_MISO, SPI1_MOSI, SPI1_CLK, SPI2_CLK, SPI2_MOSI, + SPI2_MISO, SPI2_CSB, SPI2_HOLD, SPI2_WP, EMMC_RSTB, EMMC_DSL, + EMMC_CK, EMMC_CMD, EMMC_DATA_7, EMMC_DATA_6, EMMC_DATA_5, + EMMC_DATA_4, EMMC_DATA_3, EMMC_DATA_2, EMMC_DATA_1, + EMMC_DATA_0, PCM_FS_I2S_LRCK, PCM_CLK_I2S_BCLK, + PCM_DRX_I2S_DIN, PCM_DTX_I2S_DOUT, PCM_MCK_I2S_MCLK, + UART0_RXD, UART0_TXD, PWMD0, JTAG_JTDI, JTAG_JTDO, JTAG_JTMS, + JTAG_JTCLK, JTAG_JTRST_N, USB_DRV_VBUS_P1, LED_A, LED_B, LED_C, + LED_D, LED_E, GPIO_B, GPIO_C, I2C_2_SCL, I2C_2_SDA, + PCIE30_2L_1_PRESET_N, PCIE30_1L_0_PRESET_N, + PCIE30_2L_1_WAKE_N, PCIE30_2L_1_CLKREQ_N, + PCIE30_1L_0_WAKE_N, PCIE30_1L_0_CLKREQ_N, USB_DRV_VBUS_P0, + UART1_RXD, UART1_TXD, UART1_CTS, UART1_RTS] + maxItems: 84 + + bias-disable: true + + bias-pull-up: + oneOf: + - type: boolean + description: normal pull up. + - enum: [100, 101, 102, 103] + description: + PUPD/R1/R0 pull down type. See MTK_PUPD_SET_R1R0 defines in + dt-bindings/pinctrl/mt65xx.h. + + bias-pull-down: + oneOf: + - type: boolean + description: normal pull down. + - enum: [100, 101, 102, 103] + description: + PUPD/R1/R0 pull down type. See MTK_PUPD_SET_R1R0 defines in + dt-bindings/pinctrl/mt65xx.h. + + input-enable: true + + input-disable: true + + output-enable: true + + output-low: true + + output-high: true + + input-schmitt-enable: true + + input-schmitt-disable: true + + drive-strength: + enum: [2, 4, 6, 8, 10, 12, 14, 16] + + mediatek,pull-up-adv: + description: | + Valid arguments for 'mediatek,pull-up-adv' are '0', '1', '2', '3' + Pull up settings for 2 pull resistors, R0 and R1. Valid arguments + are described as below: + 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. + 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. + 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. + 3: (R1, R0) = (1, 1) which means R1 enabled and R0 enabled. + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [0, 1, 2, 3] + + mediatek,pull-down-adv: + description: | + Valid arguments for 'mediatek,pull-up-adv' are '0', '1', '2', '3' + Pull down settings for 2 pull resistors, R0 and R1. Valid arguments + are described as below: + 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. + 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. + 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. + 3: (R1, R0) = (1, 1) which means R1 enabled and R0 enabled. + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [0, 1, 2, 3] + + required: + - pins + +additionalProperties: false + +examples: + - | + #include + #include + #include + + soc { + #address-cells = <2>; + #size-cells = <2>; + + pio: pinctrl@1001f000 { + compatible = "mediatek,mt7988-pinctrl"; + reg = <0 0x1001f000 0 0x1000>, + <0 0x11c10000 0 0x1000>, + <0 0x11d00000 0 0x1000>, + <0 0x11d20000 0 0x1000>, + <0 0x11e00000 0 0x1000>, + <0 0x11f00000 0 0x1000>, + <0 0x1000b000 0 0x1000>; + reg-names = "gpio", "iocfg_tr", + "iocfg_br", "iocfg_rb", + "iocfg_lb", "iocfg_tl", "eint"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pio 0 0 84>; + interrupt-controller; + interrupts = ; + interrupt-parent = <&gic>; + #interrupt-cells = <2>; + + i2c0_pins: i2c0-g0-pins { + mux { + function = "i2c"; + groups = "i2c0_1"; + }; + }; + + mdio0_pins: mdio0-pins { + mux { + function = "eth"; + groups = "mdc_mdio0"; + }; + + conf { + pins = "SMI_0_MDC", "SMI_0_MDIO"; + drive-strength = <8>; + }; + }; + + mmc0_pins_emmc_51: mmc0-emmc-51-pins { + mux { + function = "flash"; + groups = "emmc_51"; + }; + }; + + mmc0_pins_sdcard: mmc0-sdcard-pins { + mux { + function = "flash"; + groups = "sdcard"; + }; + }; + + pcie0_pins: pcie0-pins { + mux { + function = "pcie"; + groups = "pcie_2l_0_pereset", "pcie_clk_req_n0_0", + "pcie_wake_n0_0"; + }; + }; + + pcie1_pins: pcie1-pins { + mux { + function = "pcie"; + groups = "pcie_2l_1_pereset", "pcie_clk_req_n1", + "pcie_wake_n1_0"; + }; + }; + + pcie2_pins: pcie2-pins { + mux { + function = "pcie"; + groups = "pcie_1l_0_pereset", "pcie_clk_req_n2_0", + "pcie_wake_n2_0"; + }; + }; + + pcie3_pins: pcie3-pins { + mux { + function = "pcie"; + groups = "pcie_1l_1_pereset", "pcie_clk_req_n3", + "pcie_wake_n3_0"; + }; + }; + + uart0_pins: uart0-pins { + mux { + function = "uart"; + groups = "uart0"; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5424-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5424-tlmm.yaml index 5e64a232fc7a..df284d3645c1 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5424-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5424-tlmm.yaml @@ -79,8 +79,8 @@ $defs: qdss_cti_trig_out_b0, qdss_cti_trig_in_b1, qdss_cti_trig_out_b1, qdss_traceclk_a, qdss_tracectl_a, qdss_tracedata_a, qspi_clk, qspi_cs, qspi_data, resout, rx0, rx1, rx2, sdc_clk, sdc_cmd, - sdc_data, spi0, spi1, spi10, spi11, tsens_max, uart0, uart1, - wci_txd, wci_rxd, wsi_clk, wsi_data ] + sdc_data, spi0_cs, spi0_clk, spi0_miso, spi0_mosi, spi1, spi10, + spi11, tsens_max, uart0, uart1, wci_txd, wci_rxd, wsi_clk, wsi_data ] required: - pins diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8917-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8917-pinctrl.yaml new file mode 100644 index 000000000000..16d0c010e581 --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8917-pinctrl.yaml @@ -0,0 +1,160 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/qcom,msm8917-pinctrl.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm MSM8917 TLMM pin controller + +maintainers: + - Barnabas Czeman + +description: + Top Level Mode Multiplexer pin controller in Qualcomm MSM8917 SoC. + +properties: + compatible: + const: qcom,msm8917-pinctrl + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + gpio-reserved-ranges: + minItems: 1 + maxItems: 66 + + gpio-line-names: + maxItems: 134 + +patternProperties: + "-state$": + oneOf: + - $ref: "#/$defs/qcom-msm8917-tlmm-state" + - patternProperties: + "-pins$": + $ref: "#/$defs/qcom-msm8917-tlmm-state" + additionalProperties: false + +$defs: + qcom-msm8917-tlmm-state: + type: object + description: + Pinctrl node's client devices use subnodes for desired pin configuration. + Client device subnodes use below standard properties. + $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false + + properties: + pins: + description: + List of gpio pins affected by the properties specified in this + subnode. + items: + oneOf: + - pattern: "^gpio([0-9]|[1-9][0-9]|1[0-2][0-9]|13[0-3])$" + - enum: [ sdc1_clk, sdc1_cmd, sdc1_data, sdc1_rclk, sdc2_clk, + sdc2_cmd, sdc2_data, qdsd_clk, qdsd_cmd, qdsd_data0, + qdsd_data1, qdsd_data2, qdsd_data3 ] + minItems: 1 + maxItems: 16 + + function: + description: + Specify the alternative function to be configured for the specified + pins. + + enum: [ accel_int, adsp_ext, alsp_int, atest_bbrx0, atest_bbrx1, + atest_char, atest_char0, atest_char1, atest_char2, + atest_char3, atest_combodac_to_gpio_native, + atest_gpsadc_dtest0_native, atest_gpsadc_dtest1_native, + atest_tsens, atest_wlan0, atest_wlan1, audio_ref, + audio_reset, bimc_dte0, bimc_dte1, blsp6_spi, blsp8_spi, + blsp_i2c1, blsp_i2c2, blsp_i2c3, blsp_i2c4, blsp_i2c5, + blsp_i2c6, blsp_i2c7, blsp_i2c8, blsp_spi1, blsp_spi2, + blsp_spi3, blsp_spi4, blsp_spi5, blsp_spi6, blsp_spi7, + blsp_spi8, blsp_uart1, blsp_uart2, blsp_uart3, blsp_uart4, + blsp_uart5, blsp_uart6, blsp_uart7, blsp_uart8, cam0_ldo, + cam1_rst, cam1_standby, cam2_rst, cam2_standby, cam_mclk, + cci_async, cci_i2c, cci_timer0, cci_timer1, cdc_pdm0, + codec_int1, codec_int2, codec_mad, coex_uart, cri_trng, + cri_trng0, cri_trng1, dbg_out, dmic0_clk, dmic0_data, + ebi_cdc, ebi_ch0, ext_lpass, forced_usb, fp_gpio, fp_int, + gcc_gp1_clk_a, gcc_gp1_clk_b, gcc_gp2_clk_a, gcc_gp2_clk_b, + gcc_gp3_clk_a, gcc_gp3_clk_b, gcc_plltest, gcc_tlmm, gpio, + gsm0_tx, key_focus, key_snapshot, key_volp, ldo_en, + ldo_update, lpass_slimbus, lpass_slimbus0, lpass_slimbus1, + m_voc, mag_int, mdp_vsync, mipi_dsi0, modem_tsync, nav_pps, + nav_pps_in_a, nav_pps_in_b, nav_tsync, nfc_pwr, ov_ldo, + pa_indicator, pbs0, pbs1, pbs2, pri_mi2s, pri_mi2s_mclk_a, + pri_mi2s_mclk_b, pri_mi2s_ws, prng_rosc, + pwr_crypto_enabled_a, pwr_crypto_enabled_b, + pwr_modem_enabled_a, pwr_modem_enabled_b, pwr_nav_enabled_a, + pwr_nav_enabled_b, qdss_cti_trig_in_a0, qdss_cti_trig_in_a1, + qdss_cti_trig_in_b0, qdss_cti_trig_in_b1, + qdss_cti_trig_out_a0, qdss_cti_trig_out_a1, + qdss_cti_trig_out_b0, qdss_cti_trig_out_b1, qdss_traceclk_a, + qdss_traceclk_b, qdss_tracectl_a, qdss_tracectl_b, + qdss_tracedata_a, qdss_tracedata_b, sd_write, sdcard_det, + sec_mi2s, sec_mi2s_mclk_a, sec_mi2s_mclk_b, sensor_rst, + smb_int, ssbi_wtr1, ts_resout, ts_sample, uim1_clk, + uim1_data, uim1_present, uim1_reset, uim2_clk, uim2_data, + uim2_present, uim2_reset, uim_batt, us_emitter, us_euro, + wcss_bt, wcss_fm, wcss_wlan, wcss_wlan0, wcss_wlan1, + wcss_wlan2, webcam_rst, webcam_standby, wsa_io, wsa_irq ] + + required: + - pins + +allOf: + - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + #include + + tlmm: pinctrl@1000000 { + compatible = "qcom,msm8917-pinctrl"; + reg = <0x01000000 0x300000>; + interrupts = ; + gpio-controller; + gpio-ranges = <&tlmm 0 0 134>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + + blsp1-uart2-sleep-state { + pins = "gpio4", "gpio5"; + function = "gpio"; + + drive-strength = <2>; + bias-pull-down; + }; + + spi1-default-state { + spi-pins { + pins = "gpio0", "gpio1", "gpio3"; + function = "blsp_spi1"; + + drive-strength = <12>; + bias-disable; + }; + + cs-pins { + pins = "gpio2"; + function = "gpio"; + + drive-strength = <16>; + bias-disable; + output-high; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/realtek,rtd1315e-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/realtek,rtd1315e-pinctrl.yaml index fc6c65fea73b..90bd49d87d2e 100644 --- a/Documentation/devicetree/bindings/pinctrl/realtek,rtd1315e-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/realtek,rtd1315e-pinctrl.yaml @@ -159,30 +159,30 @@ additionalProperties: false examples: - | - pinctrl@4e000 { - compatible = "realtek,rtd1315e-pinctrl"; - reg = <0x4e000 0x130>; + pinctrl@4e000 { + compatible = "realtek,rtd1315e-pinctrl"; + reg = <0x4e000 0x130>; - emmc-hs200-pins { - pins = "emmc_clk", - "emmc_cmd", - "emmc_data_0", - "emmc_data_1", - "emmc_data_2", - "emmc_data_3", - "emmc_data_4", - "emmc_data_5", - "emmc_data_6", - "emmc_data_7"; - function = "emmc"; - realtek,drive-strength-p = <0x2>; - realtek,drive-strength-n = <0x2>; - }; + emmc-hs200-pins { + pins = "emmc_clk", + "emmc_cmd", + "emmc_data_0", + "emmc_data_1", + "emmc_data_2", + "emmc_data_3", + "emmc_data_4", + "emmc_data_5", + "emmc_data_6", + "emmc_data_7"; + function = "emmc"; + realtek,drive-strength-p = <0x2>; + realtek,drive-strength-n = <0x2>; + }; - i2c-0-pins { - pins = "gpio_12", - "gpio_13"; - function = "i2c0"; - drive-strength = <4>; - }; - }; + i2c-0-pins { + pins = "gpio_12", + "gpio_13"; + function = "i2c0"; + drive-strength = <4>; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/realtek,rtd1319d-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/realtek,rtd1319d-pinctrl.yaml index f07361d60acd..b6211c8544ca 100644 --- a/Documentation/devicetree/bindings/pinctrl/realtek,rtd1319d-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/realtek,rtd1319d-pinctrl.yaml @@ -158,30 +158,30 @@ additionalProperties: false examples: - | - pinctrl@4e000 { - compatible = "realtek,rtd1319d-pinctrl"; - reg = <0x4e000 0x130>; + pinctrl@4e000 { + compatible = "realtek,rtd1319d-pinctrl"; + reg = <0x4e000 0x130>; - emmc-hs200-pins { - pins = "emmc_clk", - "emmc_cmd", - "emmc_data_0", - "emmc_data_1", - "emmc_data_2", - "emmc_data_3", - "emmc_data_4", - "emmc_data_5", - "emmc_data_6", - "emmc_data_7"; - function = "emmc"; - realtek,drive-strength-p = <0x2>; - realtek,drive-strength-n = <0x2>; - }; + emmc-hs200-pins { + pins = "emmc_clk", + "emmc_cmd", + "emmc_data_0", + "emmc_data_1", + "emmc_data_2", + "emmc_data_3", + "emmc_data_4", + "emmc_data_5", + "emmc_data_6", + "emmc_data_7"; + function = "emmc"; + realtek,drive-strength-p = <0x2>; + realtek,drive-strength-n = <0x2>; + }; - i2c-0-pins { - pins = "gpio_12", - "gpio_13"; - function = "i2c0"; - drive-strength = <4>; - }; - }; + i2c-0-pins { + pins = "gpio_12", + "gpio_13"; + function = "i2c0"; + drive-strength = <4>; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/realtek,rtd1619b-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/realtek,rtd1619b-pinctrl.yaml index 671e4ec84624..e88bc649cc73 100644 --- a/Documentation/devicetree/bindings/pinctrl/realtek,rtd1619b-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/realtek,rtd1619b-pinctrl.yaml @@ -157,30 +157,30 @@ additionalProperties: false examples: - | - pinctrl@4e000 { - compatible = "realtek,rtd1619b-pinctrl"; - reg = <0x4e000 0x130>; + pinctrl@4e000 { + compatible = "realtek,rtd1619b-pinctrl"; + reg = <0x4e000 0x130>; - emmc-hs200-pins { - pins = "emmc_clk", - "emmc_cmd", - "emmc_data_0", - "emmc_data_1", - "emmc_data_2", - "emmc_data_3", - "emmc_data_4", - "emmc_data_5", - "emmc_data_6", - "emmc_data_7"; - function = "emmc"; - realtek,drive-strength-p = <0x2>; - realtek,drive-strength-n = <0x2>; - }; + emmc-hs200-pins { + pins = "emmc_clk", + "emmc_cmd", + "emmc_data_0", + "emmc_data_1", + "emmc_data_2", + "emmc_data_3", + "emmc_data_4", + "emmc_data_5", + "emmc_data_6", + "emmc_data_7"; + function = "emmc"; + realtek,drive-strength-p = <0x2>; + realtek,drive-strength-n = <0x2>; + }; - i2c-0-pins { - pins = "gpio_12", - "gpio_13"; - function = "i2c0"; - drive-strength = <4>; - }; - }; + i2c-0-pins { + pins = "gpio_12", + "gpio_13"; + function = "i2c0"; + drive-strength = <4>; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml index a1805b6e3f63..768bb3c2b456 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml @@ -26,6 +26,7 @@ properties: - renesas,r9a07g043-pinctrl # RZ/G2UL{Type-1,Type-2} and RZ/Five - renesas,r9a07g044-pinctrl # RZ/G2{L,LC} - renesas,r9a08g045-pinctrl # RZ/G3S + - renesas,r9a09g047-pinctrl # RZ/G3E - renesas,r9a09g057-pinctrl # RZ/V2H(P) - items: @@ -125,7 +126,7 @@ additionalProperties: drive-push-pull: true renesas,output-impedance: description: - Output impedance for pins on the RZ/V2H(P) SoC. The value provided by this + Output impedance for pins on the RZ/{G3E,V2H(P)} SoC. The value provided by this property corresponds to register bit values that can be set in the PFC_IOLH_mn register, which adjusts the drive strength value and is pin-dependent. $ref: /schemas/types.yaml#/definitions/uint32 @@ -142,7 +143,9 @@ allOf: properties: compatible: contains: - const: renesas,r9a09g057-pinctrl + enum: + - renesas,r9a09g047-pinctrl + - renesas,r9a09g057-pinctrl then: properties: resets: diff --git a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.yaml index 6a23d845f1f2..80a2b1934849 100644 --- a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.yaml @@ -44,6 +44,7 @@ properties: - rockchip,rk3328-pinctrl - rockchip,rk3368-pinctrl - rockchip,rk3399-pinctrl + - rockchip,rk3562-pinctrl - rockchip,rk3568-pinctrl - rockchip,rk3576-pinctrl - rockchip,rk3588-pinctrl diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,pinctrl-zynq.yaml b/Documentation/devicetree/bindings/pinctrl/xlnx,pinctrl-zynq.yaml index de6c10ba36c4..70548cb37ada 100644 --- a/Documentation/devicetree/bindings/pinctrl/xlnx,pinctrl-zynq.yaml +++ b/Documentation/devicetree/bindings/pinctrl/xlnx,pinctrl-zynq.yaml @@ -180,38 +180,31 @@ additionalProperties: false examples: - | #include - pinctrl0: pinctrl@700 { - compatible = "xlnx,pinctrl-zynq"; - reg = <0x700 0x200>; - syscon = <&slcr>; + pinctrl@700 { + compatible = "xlnx,pinctrl-zynq"; + reg = <0x700 0x200>; + syscon = <&slcr>; - pinctrl_uart1_default: uart1-default { - mux { - groups = "uart1_10_grp"; - function = "uart1"; - }; + uart1-default { + mux { + groups = "uart1_10_grp"; + function = "uart1"; + }; - conf { - groups = "uart1_10_grp"; - slew-rate = <0>; - power-source = ; - }; + conf { + groups = "uart1_10_grp"; + slew-rate = <0>; + power-source = ; + }; - conf-rx { - pins = "MIO49"; - bias-high-impedance; - }; + conf-rx { + pins = "MIO49"; + bias-high-impedance; + }; - conf-tx { - pins = "MIO48"; - bias-disable; - }; - }; + conf-tx { + pins = "MIO48"; + bias-disable; + }; + }; }; - - uart1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_uart1_default>; - }; - -... diff --git a/Documentation/devicetree/bindings/power/domain-idle-state.yaml b/Documentation/devicetree/bindings/power/domain-idle-state.yaml index ec1f6f669e50..4dd4f59bbbec 100644 --- a/Documentation/devicetree/bindings/power/domain-idle-state.yaml +++ b/Documentation/devicetree/bindings/power/domain-idle-state.yaml @@ -54,6 +54,11 @@ patternProperties: (i.e. idle states node with entry-method property is set to "psci") must specify this property. + idle-state-name: + $ref: /schemas/types.yaml#/definitions/string + description: + A string used as a descriptive name for the idle state. + required: - compatible - entry-latency-us diff --git a/Documentation/devicetree/bindings/power/raspberrypi,bcm2835-power.yaml b/Documentation/devicetree/bindings/power/raspberrypi,bcm2835-power.yaml new file mode 100644 index 000000000000..57579f70264c --- /dev/null +++ b/Documentation/devicetree/bindings/power/raspberrypi,bcm2835-power.yaml @@ -0,0 +1,42 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/power/raspberrypi,bcm2835-power.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Broadcom BCM2835 power domain + +maintainers: + - Alexander Aring + - Florian Fainelli + +description: + The Raspberry Pi power domain manages power for various subsystems + in the Raspberry Pi BCM2835 SoC. + +properties: + compatible: + enum: + - raspberrypi,bcm2835-power + + firmware: + $ref: /schemas/types.yaml#/definitions/phandle + description: Reference to the RPi firmware device node + + "#power-domain-cells": + const: 1 + +required: + - compatible + - firmware + - "#power-domain-cells" + +unevaluatedProperties: false + +examples: + - | + power-controller { + compatible = "raspberrypi,bcm2835-power"; + firmware = <&firmware>; + #power-domain-cells = <1>; + }; diff --git a/Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml b/Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml index 8c58e12cdb60..0735ceb7c103 100644 --- a/Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml +++ b/Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml @@ -22,6 +22,9 @@ properties: - enum: - atmel,sama5d2-shdwc - microchip,sam9x60-shdwc + - items: + - const: microchip,sam9x7-shdwc + - const: microchip,sam9x60-shdwc reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/power/supply/bq24190.yaml b/Documentation/devicetree/bindings/power/supply/bq24190.yaml index 131b7e57d22f..07adf88997b4 100644 --- a/Documentation/devicetree/bindings/power/supply/bq24190.yaml +++ b/Documentation/devicetree/bindings/power/supply/bq24190.yaml @@ -21,6 +21,7 @@ properties: - ti,bq24192i - ti,bq24196 - ti,bq24296 + - ti,bq24297 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/power/supply/gpio-charger.yaml b/Documentation/devicetree/bindings/power/supply/gpio-charger.yaml index 89f8e2bcb2d7..25826bfc289c 100644 --- a/Documentation/devicetree/bindings/power/supply/gpio-charger.yaml +++ b/Documentation/devicetree/bindings/power/supply/gpio-charger.yaml @@ -58,6 +58,10 @@ properties: charge-current-limit-gpios property. Bit 1 second to last GPIO and so on. + charge-current-limit-default-microamp: + description: Default charge current limit. Must be listed in + charge-current-limit-mapping. + required: - compatible @@ -72,6 +76,7 @@ anyOf: dependencies: charge-current-limit-gpios: [ charge-current-limit-mapping ] charge-current-limit-mapping: [ charge-current-limit-gpios ] + charge-current-limit-default-microamp: [charge-current-limit-mapping] additionalProperties: false @@ -91,4 +96,5 @@ examples: charge-current-limit-mapping = <2500000 0x00>, // 2.5 A => both GPIOs low <700000 0x01>, // 700 mA => GPIO A.12 high <0 0x02>; // 0 mA => GPIO A.11 high + charge-current-limit-default-microamp = <700000>; }; diff --git a/Documentation/devicetree/bindings/power/supply/ltc4162-l.yaml b/Documentation/devicetree/bindings/power/supply/ltc4162-l.yaml index 29d536541152..06595a953659 100644 --- a/Documentation/devicetree/bindings/power/supply/ltc4162-l.yaml +++ b/Documentation/devicetree/bindings/power/supply/ltc4162-l.yaml @@ -17,12 +17,18 @@ description: | panels, etc., and a rechargeable Lithium-Ion/Polymer battery. Specifications about the charger can be found at: + https://www.analog.com/en/products/ltc4162-l.html + https://www.analog.com/en/products/ltc4162-f.html https://www.analog.com/en/products/ltc4162-s.html + https://www.analog.com/en/products/ltc4015.html properties: compatible: enum: + - lltc,ltc4015 + - lltc,ltc4162-f - lltc,ltc4162-l + - lltc,ltc4162-s reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max17042.yaml b/Documentation/devicetree/bindings/power/supply/maxim,max17042.yaml index 085e2504d0dc..14242de7fc08 100644 --- a/Documentation/devicetree/bindings/power/supply/maxim,max17042.yaml +++ b/Documentation/devicetree/bindings/power/supply/maxim,max17042.yaml @@ -19,6 +19,7 @@ properties: - maxim,max17047 - maxim,max17050 - maxim,max17055 + - maxim,max77705-battery - maxim,max77849-battery reg: diff --git a/Documentation/devicetree/bindings/power/supply/st,stc3117.yaml b/Documentation/devicetree/bindings/power/supply/st,stc3117.yaml new file mode 100644 index 000000000000..e486131a27a9 --- /dev/null +++ b/Documentation/devicetree/bindings/power/supply/st,stc3117.yaml @@ -0,0 +1,74 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/power/supply/st,stc3117.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: STMicroelectronics STC3117 Fuel Gauge Unit Power Supply + +maintainers: + - Hardevsinh Palaniya + - Bhavin Sharma + +description: | + The STC3117 includes the STMicroelectronics OptimGauge algorithm. + It provides accurate battery state-of-charge (SOC) monitoring, tracks + battery parameter changes with operation conditions, temperature, + and aging, and allows the application to get a battery state-of-health + (SOH) indication. + + An alarm output signals low SOC or low voltage conditions and also + indicates fault conditions like a missing or swapped battery. + + Datasheet is available at + https://www.st.com/resource/en/datasheet/stc3117.pdf + +allOf: + - $ref: power-supply.yaml# + +properties: + compatible: + enum: + - st,stc3117 + + reg: + maxItems: 1 + + monitored-battery: + description: | + The fuel gauge uses the following battery properties: + - charge-full-design-microamp-hours + - voltage-min-design-microvolt + - voltage-max-design-microvolt + + shunt-resistor-micro-ohms: + description: Current sense resistor + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - monitored-battery + - shunt-resistor-micro-ohms + +unevaluatedProperties: false + +examples: + - | + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + battery@70 { + compatible = "st,stc3117"; + reg = <0x70>; + interrupt-parent = <&gpio0>; + interrupts = <31 IRQ_TYPE_LEVEL_LOW>; + monitored-battery = <&bat>; + shunt-resistor-micro-ohms = <10000>; + }; + }; diff --git a/Documentation/devicetree/bindings/pwm/adi,axi-pwmgen.yaml b/Documentation/devicetree/bindings/pwm/adi,axi-pwmgen.yaml index aa35209f74cf..45e112d0efb4 100644 --- a/Documentation/devicetree/bindings/pwm/adi,axi-pwmgen.yaml +++ b/Documentation/devicetree/bindings/pwm/adi,axi-pwmgen.yaml @@ -41,8 +41,8 @@ unevaluatedProperties: false examples: - | pwm@44b00000 { - compatible = "adi,axi-pwmgen-2.00.a"; - reg = <0x44b00000 0x1000>; - clocks = <&spi_clk>; - #pwm-cells = <3>; + compatible = "adi,axi-pwmgen-2.00.a"; + reg = <0x44b00000 0x1000>; + clocks = <&spi_clk>; + #pwm-cells = <3>; }; diff --git a/Documentation/devicetree/bindings/pwm/brcm,bcm7038-pwm.yaml b/Documentation/devicetree/bindings/pwm/brcm,bcm7038-pwm.yaml index 119de3d7f9dd..44548a9da158 100644 --- a/Documentation/devicetree/bindings/pwm/brcm,bcm7038-pwm.yaml +++ b/Documentation/devicetree/bindings/pwm/brcm,bcm7038-pwm.yaml @@ -35,8 +35,8 @@ additionalProperties: false examples: - | pwm: pwm@f0408000 { - compatible = "brcm,bcm7038-pwm"; - reg = <0xf0408000 0x28>; - #pwm-cells = <2>; - clocks = <&upg_fixed>; + compatible = "brcm,bcm7038-pwm"; + reg = <0xf0408000 0x28>; + #pwm-cells = <2>; + clocks = <&upg_fixed>; }; diff --git a/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.yaml b/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.yaml index e86c8053b366..fd785da5d3d7 100644 --- a/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.yaml +++ b/Documentation/devicetree/bindings/pwm/brcm,kona-pwm.yaml @@ -43,9 +43,9 @@ examples: #include pwm@3e01a000 { - compatible = "brcm,bcm11351-pwm", "brcm,kona-pwm"; - reg = <0x3e01a000 0xcc>; - clocks = <&slave_ccu BCM281XX_SLAVE_CCU_PWM>; - #pwm-cells = <3>; + compatible = "brcm,bcm11351-pwm", "brcm,kona-pwm"; + reg = <0x3e01a000 0xcc>; + clocks = <&slave_ccu BCM281XX_SLAVE_CCU_PWM>; + #pwm-cells = <3>; }; ... diff --git a/Documentation/devicetree/bindings/pwm/marvell,berlin-pwm.yaml b/Documentation/devicetree/bindings/pwm/marvell,berlin-pwm.yaml new file mode 100644 index 000000000000..091fec03df13 --- /dev/null +++ b/Documentation/devicetree/bindings/pwm/marvell,berlin-pwm.yaml @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pwm/marvell,berlin-pwm.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Berlin PWM controller + +maintainers: + - Jisheng Zhang + - Sebastian Hesselbarth + +properties: + compatible: + const: marvell,berlin-pwm + + reg: + maxItems: 1 + + "#pwm-cells": + const: 3 + + clocks: + maxItems: 1 + +required: + - compatible + - reg + - clocks + +allOf: + - $ref: pwm.yaml# + +unevaluatedProperties: false + +examples: + - | + pwm@f7f20000 { + compatible = "marvell,berlin-pwm"; + reg = <0xf7f20000 0x40>; + clocks = <&chip_clk 12>; + #pwm-cells = <3>; + }; + diff --git a/Documentation/devicetree/bindings/pwm/pwm-berlin.txt b/Documentation/devicetree/bindings/pwm/pwm-berlin.txt deleted file mode 100644 index f01e993a498a..000000000000 --- a/Documentation/devicetree/bindings/pwm/pwm-berlin.txt +++ /dev/null @@ -1,17 +0,0 @@ -Berlin PWM controller - -Required properties: -- compatible: should be "marvell,berlin-pwm" -- reg: physical base address and length of the controller's registers -- clocks: phandle to the input clock -- #pwm-cells: should be 3. See pwm.yaml in this directory for a description of - the cells format. - -Example: - -pwm: pwm@f7f20000 { - compatible = "marvell,berlin-pwm"; - reg = <0xf7f20000 0x40>; - clocks = <&chip_clk CLKID_CFG>; - #pwm-cells = <3>; -} diff --git a/Documentation/devicetree/bindings/pwm/pwm-sprd.txt b/Documentation/devicetree/bindings/pwm/pwm-sprd.txt deleted file mode 100644 index 87b206fd0618..000000000000 --- a/Documentation/devicetree/bindings/pwm/pwm-sprd.txt +++ /dev/null @@ -1,40 +0,0 @@ -Spreadtrum PWM controller - -Spreadtrum SoCs PWM controller provides 4 PWM channels. - -Required properties: -- compatible : Should be "sprd,ums512-pwm". -- reg: Physical base address and length of the controller's registers. -- clocks: The phandle and specifier referencing the controller's clocks. -- clock-names: Should contain following entries: - "pwmn": used to derive the functional clock for PWM channel n (n range: 0 ~ 3). - "enablen": for PWM channel n enable clock (n range: 0 ~ 3). -- #pwm-cells: Should be 2. See pwm.yaml in this directory for a description of - the cells format. - -Optional properties: -- assigned-clocks: Reference to the PWM clock entries. -- assigned-clock-parents: The phandle of the parent clock of PWM clock. - -Example: - pwms: pwm@32260000 { - compatible = "sprd,ums512-pwm"; - reg = <0 0x32260000 0 0x10000>; - clock-names = "pwm0", "enable0", - "pwm1", "enable1", - "pwm2", "enable2", - "pwm3", "enable3"; - clocks = <&aon_clk CLK_PWM0>, <&aonapb_gate CLK_PWM0_EB>, - <&aon_clk CLK_PWM1>, <&aonapb_gate CLK_PWM1_EB>, - <&aon_clk CLK_PWM2>, <&aonapb_gate CLK_PWM2_EB>, - <&aon_clk CLK_PWM3>, <&aonapb_gate CLK_PWM3_EB>; - assigned-clocks = <&aon_clk CLK_PWM0>, - <&aon_clk CLK_PWM1>, - <&aon_clk CLK_PWM2>, - <&aon_clk CLK_PWM3>; - assigned-clock-parents = <&ext_26m>, - <&ext_26m>, - <&ext_26m>, - <&ext_26m>; - #pwm-cells = <2>; - }; diff --git a/Documentation/devicetree/bindings/pwm/sprd,ums512-pwm.yaml b/Documentation/devicetree/bindings/pwm/sprd,ums512-pwm.yaml new file mode 100644 index 000000000000..c806b6768087 --- /dev/null +++ b/Documentation/devicetree/bindings/pwm/sprd,ums512-pwm.yaml @@ -0,0 +1,66 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pwm/sprd,ums512-pwm.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Spreadtrum/Unisoc UMS512 PWM Controller + +maintainers: + - Orson Zhai + - Baolin Wang + - Chunyan Zhang + +properties: + compatible: + const: sprd,ums512-pwm + + reg: + maxItems: 1 + + clocks: + maxItems: 8 + + clock-names: + items: + - const: pwm0 + - const: enable0 + - const: pwm1 + - const: enable1 + - const: pwm2 + - const: enable2 + - const: pwm3 + - const: enable3 + + '#pwm-cells': + const: 2 + +required: + - compatible + - reg + - clocks + - clock-names + +allOf: + - $ref: pwm.yaml# + +unevaluatedProperties: false + +examples: + - | + #include + + pwm@32260000 { + compatible = "sprd,ums512-pwm"; + reg = <0x32260000 0x10000>; + clocks = <&aon_clk CLK_PWM0>, <&aonapb_gate CLK_PWM0_EB>, + <&aon_clk CLK_PWM1>, <&aonapb_gate CLK_PWM1_EB>, + <&aon_clk CLK_PWM2>, <&aonapb_gate CLK_PWM2_EB>, + <&aon_clk CLK_PWM3>, <&aonapb_gate CLK_PWM3_EB>; + clock-names = "pwm0", "enable0", + "pwm1", "enable1", + "pwm2", "enable2", + "pwm3", "enable3"; + #pwm-cells = <2>; + }; +... diff --git a/Documentation/devicetree/bindings/regulator/mt6315-regulator.yaml b/Documentation/devicetree/bindings/regulator/mt6315-regulator.yaml index cd4aa27218a1..fa6743bb269d 100644 --- a/Documentation/devicetree/bindings/regulator/mt6315-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/mt6315-regulator.yaml @@ -35,10 +35,6 @@ properties: $ref: regulator.yaml# unevaluatedProperties: false - properties: - regulator-compatible: - pattern: "^vbuck[1-4]$" - additionalProperties: false required: @@ -56,7 +52,6 @@ examples: regulators { vbuck1 { - regulator-compatible = "vbuck1"; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; @@ -64,7 +59,6 @@ examples: }; vbuck3 { - regulator-compatible = "vbuck3"; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; diff --git a/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml b/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml index f8057bba747a..68709a7dc43f 100644 --- a/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml @@ -29,6 +29,7 @@ properties: - nxp,pca9450b - nxp,pca9450c - nxp,pca9451a + - nxp,pca9452 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/regulator/regulator.yaml b/Documentation/devicetree/bindings/regulator/regulator.yaml index 1ef380d1515e..77573bcb6b79 100644 --- a/Documentation/devicetree/bindings/regulator/regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/regulator.yaml @@ -34,6 +34,9 @@ properties: regulator-input-current-limit-microamp: description: maximum input current regulator allows + regulator-power-budget-milliwatt: + description: power budget of the regulator + regulator-always-on: description: boolean, regulator should never be disabled type: boolean diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sa8775p-pas.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sa8775p-pas.yaml index 7fe401a06805..a66007951d58 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,sa8775p-pas.yaml +++ b/Documentation/devicetree/bindings/remoteproc/qcom,sa8775p-pas.yaml @@ -15,12 +15,25 @@ description: properties: compatible: - enum: - - qcom,sa8775p-adsp-pas - - qcom,sa8775p-cdsp0-pas - - qcom,sa8775p-cdsp1-pas - - qcom,sa8775p-gpdsp0-pas - - qcom,sa8775p-gpdsp1-pas + oneOf: + - items: + - enum: + - qcom,qcs8300-adsp-pas + - const: qcom,sa8775p-adsp-pas + - items: + - enum: + - qcom,qcs8300-cdsp-pas + - const: qcom,sa8775p-cdsp0-pas + - items: + - enum: + - qcom,qcs8300-gpdsp-pas + - const: qcom,sa8775p-gpdsp0-pas + - enum: + - qcom,sa8775p-adsp-pas + - qcom,sa8775p-cdsp0-pas + - qcom,sa8775p-cdsp1-pas + - qcom,sa8775p-gpdsp0-pas + - qcom,sa8775p-gpdsp1-pas reg: maxItems: 1 @@ -63,8 +76,9 @@ allOf: - if: properties: compatible: - enum: - - qcom,sa8775p-adsp-pas + contains: + enum: + - qcom,sa8775p-adsp-pas then: properties: power-domains: @@ -79,9 +93,10 @@ allOf: - if: properties: compatible: - enum: - - qcom,sa8775p-cdsp0-pas - - qcom,sa8775p-cdsp1-pas + contains: + enum: + - qcom,sa8775p-cdsp0-pas + - qcom,sa8775p-cdsp1-pas then: properties: power-domains: @@ -98,9 +113,10 @@ allOf: - if: properties: compatible: - enum: - - qcom,sa8775p-gpdsp0-pas - - qcom,sa8775p-gpdsp1-pas + contains: + enum: + - qcom,sa8775p-gpdsp0-pas + - qcom,sa8775p-gpdsp1-pas then: properties: power-domains: diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sm6115-pas.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sm6115-pas.yaml index 758adb06c8dd..059cb87b4d6c 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,sm6115-pas.yaml +++ b/Documentation/devicetree/bindings/remoteproc/qcom,sm6115-pas.yaml @@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm SM6115 Peripheral Authentication Service maintainers: - - Bhupesh Sharma + - Bjorn Andersson + - Konrad Dybcio description: Qualcomm SM6115 SoC Peripheral Authentication Service loads and boots diff --git a/Documentation/devicetree/bindings/reset/st,stm32-rcc.txt b/Documentation/devicetree/bindings/reset/st,stm32-rcc.txt index 01db34375192..384035e8e60b 100644 --- a/Documentation/devicetree/bindings/reset/st,stm32-rcc.txt +++ b/Documentation/devicetree/bindings/reset/st,stm32-rcc.txt @@ -3,4 +3,4 @@ STMicroelectronics STM32 Peripheral Reset Controller The RCC IP is both a reset and a clock controller. -Please see Documentation/devicetree/bindings/clock/st,stm32-rcc.txt +Please see Documentation/devicetree/bindings/clock/st,stm32-rcc.yaml diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 8edc8261241a..2c72f148a74b 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -26,6 +26,18 @@ description: | allOf: - $ref: /schemas/cpu.yaml# - $ref: extensions.yaml + - if: + not: + properties: + compatible: + contains: + enum: + - thead,c906 + - thead,c910 + - thead,c920 + then: + properties: + thead,vlenb: false properties: compatible: @@ -46,6 +58,7 @@ properties: - sifive,u7 - sifive,u74 - sifive,u74-mc + - spacemit,x60 - thead,c906 - thead,c908 - thead,c910 @@ -95,6 +108,13 @@ properties: description: The blocksize in bytes for the Zicboz cache operations. + thead,vlenb: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + VLEN/8, the vector register length in bytes. This property is required on + thead systems where the vector register length is not identical on all harts, or + the vlenb CSR is not available. + # RISC-V has multiple properties for cache op block sizes as the sizes # differ between individual CBO extensions cache-op-block-size: false diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml index 9c7dd7e75e0c..a63b994e0763 100644 --- a/Documentation/devicetree/bindings/riscv/extensions.yaml +++ b/Documentation/devicetree/bindings/riscv/extensions.yaml @@ -621,6 +621,10 @@ properties: latency, as ratified in commit 56ed795 ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto. + # vendor extensions, each extension sorted alphanumerically under the + # vendor they belong to. Vendors are sorted alphanumerically as well. + + # Andes - const: xandespmu description: The Andes Technology performance monitor extension for counter overflow @@ -628,6 +632,12 @@ properties: Registers in the AX45MP datasheet. https://www.andestech.com/wp-content/uploads/AX45MP-1C-Rev.-5.0.0-Datasheet.pdf + # T-HEAD + - const: xtheadvector + description: + The T-HEAD specific 0.7.1 vector implementation as written in + https://github.com/T-head-Semi/thead-extension-spec/blob/95358cb2cca9489361c61d335e03d3134b14133f/xtheadvector.adoc. + allOf: # Zcb depends on Zca - if: diff --git a/Documentation/devicetree/bindings/riscv/spacemit.yaml b/Documentation/devicetree/bindings/riscv/spacemit.yaml new file mode 100644 index 000000000000..52e55077af1a --- /dev/null +++ b/Documentation/devicetree/bindings/riscv/spacemit.yaml @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/riscv/spacemit.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: SpacemiT SoC-based boards + +maintainers: + - Yangyu Chen + - Yixun Lan + +description: + SpacemiT SoC-based boards + +properties: + $nodename: + const: '/' + compatible: + oneOf: + - items: + - enum: + - bananapi,bpi-f3 + - const: spacemit,k1 + +additionalProperties: true + +... diff --git a/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml b/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml index a14b52178c4b..2599b847f406 100644 --- a/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml +++ b/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml @@ -14,9 +14,13 @@ maintainers: properties: compatible: - enum: - - fsl,imx1-rtc - - fsl,imx21-rtc + oneOf: + - const: fsl,imx1-rtc + - const: fsl,imx21-rtc + - items: + - enum: + - fsl,imx31-rtc + - const: fsl,imx21-rtc reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/serial/8250.yaml b/Documentation/devicetree/bindings/serial/8250.yaml index 692aa05500fd..0bde2379e864 100644 --- a/Documentation/devicetree/bindings/serial/8250.yaml +++ b/Documentation/devicetree/bindings/serial/8250.yaml @@ -111,7 +111,9 @@ properties: - mediatek,mt7623-btif - const: mediatek,mtk-btif - items: - - const: mrvl,mmp-uart + - enum: + - mrvl,mmp-uart + - spacemit,k1-uart - const: intel,xscale-uart - items: - enum: diff --git a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.yaml b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.yaml index 88871480018e..ab39b95dae40 100644 --- a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.yaml +++ b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.yaml @@ -23,6 +23,8 @@ properties: maxItems: 1 interrupts: + description: + When missing, device driver uses polling instead. maxItems: 1 clocks: @@ -76,7 +78,6 @@ properties: required: - compatible - reg - - interrupts allOf: - $ref: /schemas/spi/spi-peripheral-props.yaml# diff --git a/Documentation/devicetree/bindings/serial/renesas,scif.yaml b/Documentation/devicetree/bindings/serial/renesas,scif.yaml index 51d9fb0f4763..8e82999e6acb 100644 --- a/Documentation/devicetree/bindings/serial/renesas,scif.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,scif.yaml @@ -83,6 +83,11 @@ properties: - const: renesas,scif-r9a09g057 # RZ/V2H(P) + - items: + - enum: + - renesas,scif-r9a09g047 # RZ/G3E + - const: renesas,scif-r9a09g057 # RZ/V2H fallback + reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/soc/altera/altr,sys-mgr.yaml b/Documentation/devicetree/bindings/soc/altera/altr,sys-mgr.yaml new file mode 100644 index 000000000000..d56ff4c05ae5 --- /dev/null +++ b/Documentation/devicetree/bindings/soc/altera/altr,sys-mgr.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/soc/altera/altr,sys-mgr.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Altera SOCFPGA System Manager + +maintainers: + - Dinh Nguyen + +properties: + compatible: + oneOf: + - description: Cyclone5/Arria5/Arria10 + const: altr,sys-mgr + - description: Stratix10 SoC + items: + - const: altr,sys-mgr-s10 + - const: altr,sys-mgr + + reg: + maxItems: 1 + + cpu1-start-addr: + $ref: /schemas/types.yaml#/definitions/uint32 + description: CPU1 start address in hex + +required: + - compatible + - reg + +allOf: + - if: + properties: + compatible: + contains: + const: altr,sys-mgr-s10 + then: + properties: + cpu1-start-addr: false + +additionalProperties: false + +examples: + - | + sysmgr@ffd08000 { + compatible = "altr,sys-mgr"; + reg = <0xffd08000 0x1000>; + cpu1-start-addr = <0xffd080c4>; + }; diff --git a/Documentation/devicetree/bindings/soc/amlogic/amlogic,meson-gx-hhi-sysctrl.yaml b/Documentation/devicetree/bindings/soc/amlogic/amlogic,meson-gx-hhi-sysctrl.yaml index c6bce40946d4..3dc66f1de023 100644 --- a/Documentation/devicetree/bindings/soc/amlogic/amlogic,meson-gx-hhi-sysctrl.yaml +++ b/Documentation/devicetree/bindings/soc/amlogic/amlogic,meson-gx-hhi-sysctrl.yaml @@ -13,6 +13,7 @@ properties: compatible: items: - enum: + - amlogic,meson-hhi-sysctrl - amlogic,meson-gx-hhi-sysctrl - amlogic,meson-gx-ao-sysctrl - amlogic,meson-axg-hhi-sysctrl @@ -36,6 +37,19 @@ properties: type: object allOf: + - if: + properties: + compatible: + enum: + - amlogic,meson-hhi-sysctrl + then: + properties: + clock-controller: + $ref: /schemas/clock/amlogic,meson8-clkc.yaml# + + pinctrl: false + phy: false + - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/soc/bcm/raspberrypi,bcm2835-power.txt b/Documentation/devicetree/bindings/soc/bcm/raspberrypi,bcm2835-power.txt deleted file mode 100644 index 30942cf7992b..000000000000 --- a/Documentation/devicetree/bindings/soc/bcm/raspberrypi,bcm2835-power.txt +++ /dev/null @@ -1,47 +0,0 @@ -Raspberry Pi power domain driver - -Required properties: - -- compatible: Should be "raspberrypi,bcm2835-power". -- firmware: Reference to the RPi firmware device node. -- #power-domain-cells: Should be <1>, we providing multiple power domains. - -The valid defines for power domain are: - - RPI_POWER_DOMAIN_I2C0 - RPI_POWER_DOMAIN_I2C1 - RPI_POWER_DOMAIN_I2C2 - RPI_POWER_DOMAIN_VIDEO_SCALER - RPI_POWER_DOMAIN_VPU1 - RPI_POWER_DOMAIN_HDMI - RPI_POWER_DOMAIN_USB - RPI_POWER_DOMAIN_VEC - RPI_POWER_DOMAIN_JPEG - RPI_POWER_DOMAIN_H264 - RPI_POWER_DOMAIN_V3D - RPI_POWER_DOMAIN_ISP - RPI_POWER_DOMAIN_UNICAM0 - RPI_POWER_DOMAIN_UNICAM1 - RPI_POWER_DOMAIN_CCP2RX - RPI_POWER_DOMAIN_CSI2 - RPI_POWER_DOMAIN_CPI - RPI_POWER_DOMAIN_DSI0 - RPI_POWER_DOMAIN_DSI1 - RPI_POWER_DOMAIN_TRANSPOSER - RPI_POWER_DOMAIN_CCP2TX - RPI_POWER_DOMAIN_CDP - RPI_POWER_DOMAIN_ARM - -Example: - -power: power { - compatible = "raspberrypi,bcm2835-power"; - firmware = <&firmware>; - #power-domain-cells = <1>; -}; - -Example for using power domain: - -&usb { - power-domains = <&power RPI_POWER_DOMAIN_USB>; -}; diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,qman-portal.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,qman-portal.yaml index 17016184143f..e459fec02ba8 100644 --- a/Documentation/devicetree/bindings/soc/fsl/fsl,qman-portal.yaml +++ b/Documentation/devicetree/bindings/soc/fsl/fsl,qman-portal.yaml @@ -35,6 +35,7 @@ properties: fsl,liodn: $ref: /schemas/types.yaml#/definitions/uint32-array + maxItems: 2 description: See pamu.txt. Two LIODN(s). DQRR LIODN (DLIODN) and Frame LIODN (FLIODN) @@ -69,6 +70,7 @@ patternProperties: type: object properties: fsl,liodn: + $ref: /schemas/types.yaml#/definitions/uint32-array description: See pamu.txt, PAMU property used for static LIODN assignment fsl,iommu-parent: diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,aoss-qmp.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,aoss-qmp.yaml index e63f800c6caa..41fbbe059d80 100644 --- a/Documentation/devicetree/bindings/soc/qcom/qcom,aoss-qmp.yaml +++ b/Documentation/devicetree/bindings/soc/qcom/qcom,aoss-qmp.yaml @@ -25,6 +25,7 @@ properties: compatible: items: - enum: + - qcom,qcs615-aoss-qmp - qcom,qcs8300-aoss-qmp - qcom,qdu1000-aoss-qmp - qcom,sa8255p-aoss-qmp diff --git a/Documentation/devicetree/bindings/soc/renesas/renesas.yaml b/Documentation/devicetree/bindings/soc/renesas/renesas.yaml index b7acb65bdecd..225c0f07ae94 100644 --- a/Documentation/devicetree/bindings/soc/renesas/renesas.yaml +++ b/Documentation/devicetree/bindings/soc/renesas/renesas.yaml @@ -360,19 +360,21 @@ properties: - renesas,white-hawk-cpu # White Hawk CPU board (RTP8A779G0ASKB0FC0SA000) - const: renesas,r8a779g0 - - description: R-Car V4H (R8A779G2) - items: - - enum: - - renesas,white-hawk-single # White Hawk Single board (RTP8A779G2ASKB0F10SA001) - - const: renesas,r8a779g2 - - const: renesas,r8a779g0 - - items: - enum: - renesas,white-hawk-breakout # White Hawk BreakOut board (RTP8A779G0ASKB0SB0SA000) - const: renesas,white-hawk-cpu - const: renesas,r8a779g0 + - description: R-Car V4H (R8A779G[23]) + items: + - enum: + - renesas,white-hawk-single # White Hawk Single board (RTP8A779G[23]ASKB0F10SA001) + - enum: + - renesas,r8a779g2 # ES2.x + - renesas,r8a779g3 # ES3.x + - const: renesas,r8a779g0 + - description: R-Car V4M (R8A779H0) items: - enum: @@ -525,6 +527,23 @@ properties: - renesas,rzv2mevk2 # RZ/V2M Eval Board v2.0 - const: renesas,r9a09g011 + - description: RZ/G3E (R9A09G047) + items: + - enum: + - renesas,smarc2-evk # RZ SMARC Carrier-II EVK + - enum: + - renesas,rzg3e-smarcm # RZ/G3E SMARC Module (SoM) + - enum: + - renesas,r9a09g047e27 # Dual Cortex-A55 + Cortex-M33 (15mm BGA) + - renesas,r9a09g047e28 # Dual Cortex-A55 + Cortex-M33 (21mm BGA) + - renesas,r9a09g047e37 # Dual Cortex-A55 + Cortex-M33 + Ethos-U55 (15mm BGA) + - renesas,r9a09g047e38 # Dual Cortex-A55 + Cortex-M33 + Ethos-U55 (21mm BGA) + - renesas,r9a09g047e47 # Quad Cortex-A55 + Cortex-M33 (15mm BGA) + - renesas,r9a09g047e48 # Quad Cortex-A55 + Cortex-M33 (21mm BGA) + - renesas,r9a09g047e57 # Quad Cortex-A55 + Cortex-M33 + Ethos-U55 (15mm BGA) + - renesas,r9a09g047e58 # Quad Cortex-A55 + Cortex-M33 + Ethos-U55 (21mm BGA) + - const: renesas,r9a09g047 + - description: RZ/V2H(P) (R9A09G057) items: - enum: diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml index 7eca9e1ad6a3..61f38b68a4a3 100644 --- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml +++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml @@ -23,6 +23,7 @@ properties: - rockchip,rk3576-bigcore-grf - rockchip,rk3576-cci-grf - rockchip,rk3576-gpu-grf + - rockchip,rk3576-hdptxphy-grf - rockchip,rk3576-litcore-grf - rockchip,rk3576-npu-grf - rockchip,rk3576-php-grf diff --git a/Documentation/devicetree/bindings/soc/samsung/exynos-pmu.yaml b/Documentation/devicetree/bindings/soc/samsung/exynos-pmu.yaml index 6cdfe7e059a3..8e6d051d8c97 100644 --- a/Documentation/devicetree/bindings/soc/samsung/exynos-pmu.yaml +++ b/Documentation/devicetree/bindings/soc/samsung/exynos-pmu.yaml @@ -55,6 +55,7 @@ properties: - samsung,exynos7885-pmu - samsung,exynos8895-pmu - samsung,exynos9810-pmu + - samsung,exynos990-pmu - samsung,exynosautov9-pmu - samsung,exynosautov920-pmu - tesla,fsd-pmu diff --git a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml index f80fcbc3128b..5b046932fbc3 100644 --- a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml +++ b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml @@ -64,6 +64,7 @@ properties: samsung,mode: $ref: /schemas/types.yaml#/definitions/uint32 + enum: [0, 1, 2, 3] description: Selects USI function (which serial protocol to use). Refer to for valid USI mode values. diff --git a/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml b/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml index 3ca220582897..a75aef240629 100644 --- a/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml +++ b/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml @@ -21,6 +21,10 @@ properties: - samsung,exynos3-sysreg - samsung,exynos4-sysreg - samsung,exynos5-sysreg + - samsung,exynos8895-fsys0-sysreg + - samsung,exynos8895-fsys1-sysreg + - samsung,exynos8895-peric0-sysreg + - samsung,exynos8895-peric1-sysreg - samsung,exynosautov920-peric0-sysreg - samsung,exynosautov920-peric1-sysreg - tesla,fsd-cam-sysreg @@ -79,6 +83,10 @@ allOf: - samsung,exynos850-cmgp-sysreg - samsung,exynos850-peri-sysreg - samsung,exynos850-sysreg + - samsung,exynos8895-fsys0-sysreg + - samsung,exynos8895-fsys1-sysreg + - samsung,exynos8895-peric0-sysreg + - samsung,exynos8895-peric1-sysreg then: required: - clocks diff --git a/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml b/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml index 3cb1471cc6b6..927b3200e29e 100644 --- a/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml +++ b/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml @@ -92,6 +92,16 @@ properties: description: | This property is as per sci-pm-domain.txt. + clocks: + items: + - description: ICSSG_CORE Clock + - description: ICSSG_IEP Clock + - description: ICSSG_RGMII_MHZ_250 Clock + - description: ICSSG_RGMII_MHZ_50 Clock + - description: ICSSG_RGMII_MHZ_5 Clock + - description: ICSSG_UART Clock + - description: ICSSG_ICLK Clock + patternProperties: memories@[a-f0-9]+$: diff --git a/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu.txt b/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu.txt deleted file mode 100644 index 2417b13ba468..000000000000 --- a/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu.txt +++ /dev/null @@ -1,26 +0,0 @@ -LogicoreIP designed compatible with Xilinx ZYNQ family. -------------------------------------------------------- - -General concept ---------------- - -LogicoreIP design to provide the isolation between processing system -and programmable logic. Also provides the list of register set to configure -the frequency. - -Required properties: -- compatible: shall be one of: - "xlnx,vcu" - "xlnx,vcu-logicoreip-1.0" -- reg : The base offset and size of the VCU_PL_SLCR register space. -- clocks: phandle for aclk and pll_ref clocksource -- clock-names: The identification string, "aclk", is always required for - the axi clock. "pll_ref" is required for pll. -Example: - - xlnx_vcu: vcu@a0040000 { - compatible = "xlnx,vcu-logicoreip-1.0"; - reg = <0x0 0xa0040000 0x0 0x1000>; - clocks = <&si570_1>, <&clkc 71>; - clock-names = "pll_ref", "aclk"; - }; diff --git a/Documentation/devicetree/bindings/sound/adi,ssm2518.yaml b/Documentation/devicetree/bindings/sound/adi,ssm2518.yaml index f3f32540779c..f1beae84cad1 100644 --- a/Documentation/devicetree/bindings/sound/adi,ssm2518.yaml +++ b/Documentation/devicetree/bindings/sound/adi,ssm2518.yaml @@ -36,12 +36,14 @@ unevaluatedProperties: false examples: - | - i2c { - #address-cells = <1>; - #size-cells = <0>; - codec@34 { - compatible = "adi,ssm2518"; - reg = <0x34>; - gpios = <&gpio 5 0>; - }; - }; + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + codec@34 { + compatible = "adi,ssm2518"; + reg = <0x34>; + gpios = <&gpio 5 GPIO_ACTIVE_HIGH>; + }; + }; diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml index ebc9097f936a..ccae64ce3071 100644 --- a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml +++ b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml @@ -23,6 +23,7 @@ properties: - allwinner,sun8i-h3-codec - allwinner,sun8i-v3s-codec - allwinner,sun50i-h616-codec + - allwinner,suniv-f1c100s-codec reg: maxItems: 1 @@ -77,6 +78,7 @@ properties: - MIC1 - MIC2 - MIC3 + - MIC # Microphone Biases from the SoC - HBIAS @@ -87,6 +89,8 @@ properties: - Headset Mic - Line In - Line Out + - Right FM In + - Left FM In - Mic - Speaker @@ -270,6 +274,33 @@ allOf: - const: rx - const: tx + - if: + properties: + compatible: + enum: + - allwinner,suniv-f1c100s-codec + + then: + properties: + allwinner,audio-routing: + items: + enum: + - HP + - HPCOM + - LINEIN + - LINEOUT + - MIC + - HBIAS + - MBIAS + - Headphone + - Headset Mic + - Line In + - Line Out + - Right FM In + - Left FM In + - Mic + - Speaker + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/sound/awinic,aw88395.yaml b/Documentation/devicetree/bindings/sound/awinic,aw88395.yaml index 3b0b743e49c4..6676406bf2de 100644 --- a/Documentation/devicetree/bindings/sound/awinic,aw88395.yaml +++ b/Documentation/devicetree/bindings/sound/awinic,aw88395.yaml @@ -18,6 +18,7 @@ properties: compatible: enum: - awinic,aw88081 + - awinic,aw88083 - awinic,aw88261 - awinic,aw88395 - awinic,aw88399 @@ -58,6 +59,7 @@ allOf: contains: enum: - awinic,aw88081 + - awinic,aw88083 - awinic,aw88261 then: properties: diff --git a/Documentation/devicetree/bindings/sound/everest,es71x4.yaml b/Documentation/devicetree/bindings/sound/everest,es71x4.yaml index fd1b32812228..efe9f3fd3778 100644 --- a/Documentation/devicetree/bindings/sound/everest,es71x4.yaml +++ b/Documentation/devicetree/bindings/sound/everest,es71x4.yaml @@ -53,10 +53,10 @@ unevaluatedProperties: false examples: - | - codec { - compatible = "everest,es7134"; - #sound-dai-cells = <0>; - VDD-supply = <&vdd_supply>; - }; + codec { + compatible = "everest,es7134"; + #sound-dai-cells = <0>; + VDD-supply = <&vdd_supply>; + }; ... diff --git a/Documentation/devicetree/bindings/sound/everest,es7241.yaml b/Documentation/devicetree/bindings/sound/everest,es7241.yaml index f179af758730..e5cfb40f1ef2 100644 --- a/Documentation/devicetree/bindings/sound/everest,es7241.yaml +++ b/Documentation/devicetree/bindings/sound/everest,es7241.yaml @@ -54,14 +54,15 @@ unevaluatedProperties: false examples: - | - #include - codec { - compatible = "everest,es7241"; - #sound-dai-cells = <0>; - reset-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; - VDDP-supply = <&vddp_supply>; - VDDA-supply = <&vdda_supply>; - VDDD-supply = <&vddd_supply>; - }; + #include + + codec { + compatible = "everest,es7241"; + #sound-dai-cells = <0>; + reset-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; + VDDP-supply = <&vddp_supply>; + VDDA-supply = <&vdda_supply>; + VDDD-supply = <&vddd_supply>; + }; ... diff --git a/Documentation/devicetree/bindings/sound/fsl,easrc.yaml b/Documentation/devicetree/bindings/sound/fsl,easrc.yaml index 0782f3f9947f..c454110f4281 100644 --- a/Documentation/devicetree/bindings/sound/fsl,easrc.yaml +++ b/Documentation/devicetree/bindings/sound/fsl,easrc.yaml @@ -87,20 +87,20 @@ examples: #include easrc: easrc@300c0000 { - compatible = "fsl,imx8mn-easrc"; - reg = <0x300c0000 0x10000>; - interrupts = <0x0 122 0x4>; - clocks = <&clk IMX8MN_CLK_ASRC_ROOT>; - clock-names = "mem"; - dmas = <&sdma2 16 23 0> , <&sdma2 17 23 0>, - <&sdma2 18 23 0> , <&sdma2 19 23 0>, - <&sdma2 20 23 0> , <&sdma2 21 23 0>, - <&sdma2 22 23 0> , <&sdma2 23 23 0>; - dma-names = "ctx0_rx", "ctx0_tx", - "ctx1_rx", "ctx1_tx", - "ctx2_rx", "ctx2_tx", - "ctx3_rx", "ctx3_tx"; - firmware-name = "imx/easrc/easrc-imx8mn.bin"; - fsl,asrc-rate = <8000>; - fsl,asrc-format = <2>; + compatible = "fsl,imx8mn-easrc"; + reg = <0x300c0000 0x10000>; + interrupts = <0x0 122 0x4>; + clocks = <&clk IMX8MN_CLK_ASRC_ROOT>; + clock-names = "mem"; + dmas = <&sdma2 16 23 0> , <&sdma2 17 23 0>, + <&sdma2 18 23 0> , <&sdma2 19 23 0>, + <&sdma2 20 23 0> , <&sdma2 21 23 0>, + <&sdma2 22 23 0> , <&sdma2 23 23 0>; + dma-names = "ctx0_rx", "ctx0_tx", + "ctx1_rx", "ctx1_tx", + "ctx2_rx", "ctx2_tx", + "ctx3_rx", "ctx3_tx"; + firmware-name = "imx/easrc/easrc-imx8mn.bin"; + fsl,asrc-rate = <8000>; + fsl,asrc-format = <2>; }; diff --git a/Documentation/devicetree/bindings/sound/fsl,micfil.yaml b/Documentation/devicetree/bindings/sound/fsl,micfil.yaml index c1e9803fc113..c47b7a097490 100644 --- a/Documentation/devicetree/bindings/sound/fsl,micfil.yaml +++ b/Documentation/devicetree/bindings/sound/fsl,micfil.yaml @@ -25,6 +25,7 @@ properties: - fsl,imx8mm-micfil - fsl,imx8mp-micfil - fsl,imx93-micfil + - fsl,imx943-micfil reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/sound/fsl,mqs.yaml b/Documentation/devicetree/bindings/sound/fsl,mqs.yaml index 030ccc173130..8c22e8348b14 100644 --- a/Documentation/devicetree/bindings/sound/fsl,mqs.yaml +++ b/Documentation/devicetree/bindings/sound/fsl,mqs.yaml @@ -23,6 +23,8 @@ properties: - fsl,imx8qm-mqs - fsl,imx8qxp-mqs - fsl,imx93-mqs + - fsl,imx943-aonmix-mqs + - fsl,imx943-wakeupmix-mqs - fsl,imx95-aonmix-mqs - fsl,imx95-netcmix-mqs diff --git a/Documentation/devicetree/bindings/sound/fsl,xcvr.yaml b/Documentation/devicetree/bindings/sound/fsl,xcvr.yaml index 5e2801014221..f68d0e0ecfe5 100644 --- a/Documentation/devicetree/bindings/sound/fsl,xcvr.yaml +++ b/Documentation/devicetree/bindings/sound/fsl,xcvr.yaml @@ -140,21 +140,21 @@ examples: #include xcvr: xcvr@30cc0000 { - compatible = "fsl,imx8mp-xcvr"; - reg = <0x30cc0000 0x800>, - <0x30cc0800 0x400>, - <0x30cc0c00 0x080>, - <0x30cc0e00 0x080>; - reg-names = "ram", "regs", "rxfifo", "txfifo"; - interrupts = , - , - ; - clocks = <&audiomix_clk IMX8MP_CLK_AUDIOMIX_EARC_IPG>, - <&audiomix_clk IMX8MP_CLK_AUDIOMIX_EARC_PHY>, - <&audiomix_clk IMX8MP_CLK_AUDIOMIX_SPBA2_ROOT>, - <&audiomix_clk IMX8MP_CLK_AUDIOMIX_AUDPLL_ROOT>; - clock-names = "ipg", "phy", "spba", "pll_ipg"; - dmas = <&sdma2 30 2 0>, <&sdma2 31 2 0>; - dma-names = "rx", "tx"; - resets = <&audiomix_reset 0>; + compatible = "fsl,imx8mp-xcvr"; + reg = <0x30cc0000 0x800>, + <0x30cc0800 0x400>, + <0x30cc0c00 0x080>, + <0x30cc0e00 0x080>; + reg-names = "ram", "regs", "rxfifo", "txfifo"; + interrupts = , + , + ; + clocks = <&audiomix_clk IMX8MP_CLK_AUDIOMIX_EARC_IPG>, + <&audiomix_clk IMX8MP_CLK_AUDIOMIX_EARC_PHY>, + <&audiomix_clk IMX8MP_CLK_AUDIOMIX_SPBA2_ROOT>, + <&audiomix_clk IMX8MP_CLK_AUDIOMIX_AUDPLL_ROOT>; + clock-names = "ipg", "phy", "spba", "pll_ipg"; + dmas = <&sdma2 30 2 0>, <&sdma2 31 2 0>; + dma-names = "rx", "tx"; + resets = <&audiomix_reset 0>; }; diff --git a/Documentation/devicetree/bindings/sound/intel,keembay-i2s.yaml b/Documentation/devicetree/bindings/sound/intel,keembay-i2s.yaml index 76b6f2cf25df..dca617860938 100644 --- a/Documentation/devicetree/bindings/sound/intel,keembay-i2s.yaml +++ b/Documentation/devicetree/bindings/sound/intel,keembay-i2s.yaml @@ -72,19 +72,19 @@ unevaluatedProperties: false examples: - | - #include - #include - #define KEEM_BAY_PSS_AUX_I2S3 - #define KEEM_BAY_PSS_I2S3 - i2s3: i2s@20140000 { - compatible = "intel,keembay-i2s"; - #sound-dai-cells = <0>; - reg = <0x20140000 0x200>, /* I2S registers */ - <0x202a00a4 0x4>; /* I2S gen configuration */ - reg-names = "i2s-regs", "i2s_gen_cfg"; - interrupts = ; - clock-names = "osc", "apb_clk"; - clocks = <&scmi_clk KEEM_BAY_PSS_AUX_I2S3>, <&scmi_clk KEEM_BAY_PSS_I2S3>; - dmas = <&axi_dma0 29>, <&axi_dma0 33>; - dma-names = "tx", "rx"; - }; + #include + #include + #define KEEM_BAY_PSS_AUX_I2S3 + #define KEEM_BAY_PSS_I2S3 + i2s@20140000 { + compatible = "intel,keembay-i2s"; + #sound-dai-cells = <0>; + reg = <0x20140000 0x200>, /* I2S registers */ + <0x202a00a4 0x4>; /* I2S gen configuration */ + reg-names = "i2s-regs", "i2s_gen_cfg"; + interrupts = ; + clock-names = "osc", "apb_clk"; + clocks = <&scmi_clk KEEM_BAY_PSS_AUX_I2S3>, <&scmi_clk KEEM_BAY_PSS_I2S3>; + dmas = <&axi_dma0 29>, <&axi_dma0 33>; + dma-names = "tx", "rx"; + }; diff --git a/Documentation/devicetree/bindings/sound/mediatek,mt8188-mt6359.yaml b/Documentation/devicetree/bindings/sound/mediatek,mt8188-mt6359.yaml index ba482747f0e6..362e729b51b4 100644 --- a/Documentation/devicetree/bindings/sound/mediatek,mt8188-mt6359.yaml +++ b/Documentation/devicetree/bindings/sound/mediatek,mt8188-mt6359.yaml @@ -14,11 +14,15 @@ allOf: properties: compatible: - enum: - - mediatek,mt8188-es8326 - - mediatek,mt8188-mt6359-evb - - mediatek,mt8188-nau8825 - - mediatek,mt8188-rt5682s + oneOf: + - enum: + - mediatek,mt8188-es8326 + - mediatek,mt8188-mt6359-evb + - mediatek,mt8188-nau8825 + - mediatek,mt8188-rt5682s + - items: + - const: mediatek,mt8390-mt6359-evk + - const: mediatek,mt8188-mt6359-evb audio-routing: description: @@ -56,6 +60,8 @@ patternProperties: - ETDM2_OUT_BE - ETDM3_OUT_BE - PCM1_BE + - DL_SRC_BE + - UL_SRC_BE codec: description: Holds subnode which indicates codec dai. diff --git a/Documentation/devicetree/bindings/sound/neofidelity,ntp8918.yaml b/Documentation/devicetree/bindings/sound/neofidelity,ntp8918.yaml index 952768b35902..6946177e391a 100644 --- a/Documentation/devicetree/bindings/sound/neofidelity,ntp8918.yaml +++ b/Documentation/devicetree/bindings/sound/neofidelity,ntp8918.yaml @@ -55,16 +55,18 @@ unevaluatedProperties: false examples: - | - #include - i2c { - #address-cells = <1>; - #size-cells = <0>; - audio-codec@2a { - compatible = "neofidelity,ntp8918"; - #sound-dai-cells = <0>; - reg = <0x2a>; - clocks = <&clkc 150>, <&clkc 151>, <&clkc 152>; - clock-names = "wck", "scl", "bck"; - reset-gpios = <&gpio 5 GPIO_ACTIVE_LOW>; + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + audio-codec@2a { + compatible = "neofidelity,ntp8918"; + #sound-dai-cells = <0>; + reg = <0x2a>; + clocks = <&clkc 150>, <&clkc 151>, <&clkc 152>; + clock-names = "wck", "scl", "bck"; + reset-gpios = <&gpio 5 GPIO_ACTIVE_LOW>; + }; }; - }; diff --git a/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml b/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml index 13f09f1bc800..0a698798c22b 100644 --- a/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml +++ b/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml @@ -51,7 +51,7 @@ properties: description: Power supply for AVDD, providing 1.8V. cpvdd-supply: - description: Power supply for CPVDD, providing 3.5V. + description: Power supply for CPVDD, providing 1.8V. hp-detect-gpios: description: diff --git a/Documentation/devicetree/bindings/sound/realtek,rt5682.yaml b/Documentation/devicetree/bindings/sound/realtek,rt5682.yaml new file mode 100644 index 000000000000..39333ea05646 --- /dev/null +++ b/Documentation/devicetree/bindings/sound/realtek,rt5682.yaml @@ -0,0 +1,156 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/sound/realtek,rt5682.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Realtek rt5682 and rt5682i codecs + +maintainers: + - Bard Liao + +allOf: + - $ref: dai-common.yaml# + +properties: + compatible: + enum: + - realtek,rt5682 + - realtek,rt5682i + + reg: + maxItems: 1 + description: I2C address of the device. + + interrupts: + maxItems: 1 + description: The CODEC's interrupt output. + + realtek,dmic1-data-pin: + $ref: /schemas/types.yaml#/definitions/uint32 + enum: + - 0 # dmic1 data is not used + - 1 # using GPIO2 pin as dmic1 data pin + - 2 # using GPIO5 pin as dmic1 data pin + description: + Specify which GPIO pin be used as DMIC1 data pin. + + realtek,dmic1-clk-pin: + $ref: /schemas/types.yaml#/definitions/uint32 + enum: + - 0 # using GPIO1 pin as dmic1 clock pin + - 1 # using GPIO3 pin as dmic1 clock pin + description: + Specify which GPIO pin be used as DMIC1 clk pin. + + realtek,jd-src: + $ref: /schemas/types.yaml#/definitions/uint32 + enum: + - 0 # No JD is used + - 1 # using JD1 as JD source + description: + Specify which JD source be used. + + realtek,ldo1-en-gpios: + description: + The GPIO that controls the CODEC's LDO1_EN pin. + + realtek,btndet-delay: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + The debounce delay for push button. + The delay time is realtek,btndet-delay value multiple of 8.192 ms. + If absent, the default is 16. + + realtek,dmic-clk-rate-hz: + description: + Set the clock rate (hz) for the requirement of the particular DMIC. + + realtek,dmic-delay-ms: + description: + Set the delay time (ms) for the requirement of the particular DMIC. + + realtek,dmic-clk-driving-high: + type: boolean + description: + Set the high driving of the DMIC clock out. + + clocks: + items: + - description: phandle and clock specifier for codec MCLK. + + clock-names: + items: + - const: mclk + + "#clock-cells": + const: 1 + + clock-output-names: + minItems: 2 + maxItems: 2 + description: Name given for DAI word clock and bit clock outputs. + + "#sound-dai-cells": + const: 1 + + AVDD-supply: + description: Regulator supplying analog power through the AVDD pin. + + MICVDD-supply: + description: Regulator supplying power for the microphone bias through + the MICVDD pin. + + VBAT-supply: + description: Regulator supplying battery power through the VBAT pin. + + DBVDD-supply: + description: Regulator supplying I/O power through the DBVDD pin. + + LDO1-IN-supply: + description: Regulator supplying power to the digital core and charge + pump through the LDO1_IN pin. + +required: + - compatible + - reg + - AVDD-supply + - VBAT-supply + - MICVDD-supply + - DBVDD-supply + - LDO1-IN-supply + +unevaluatedProperties: false + +examples: + - | + #include + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + codec@1a { + compatible = "realtek,rt5682"; + reg = <0x1a>; + interrupts = <6 IRQ_TYPE_LEVEL_HIGH>; + realtek,ldo1-en-gpios = + <&gpio 2 GPIO_ACTIVE_HIGH>; + realtek,dmic1-data-pin = <1>; + realtek,dmic1-clk-pin = <1>; + realtek,jd-src = <1>; + + #clock-cells = <1>; + clock-output-names = "rt5682-dai-wclk", "rt5682-dai-bclk"; + + clocks = <&osc>; + clock-names = "mclk"; + + AVDD-supply = <&avdd_reg>; + VBAT-supply = <&vbat_reg>; + MICVDD-supply = <&micvdd_reg>; + DBVDD-supply = <&dbvdd_reg>; + LDO1-IN-supply = <&ldo1_in_reg>; + }; + }; diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml b/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml index 6d0d1514cd42..e8a2acb92646 100644 --- a/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml +++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml @@ -112,12 +112,6 @@ properties: description: List of necessary clock names. # details are defined below - post-init-providers: - description: At least if rsnd is using DPCM connection on Audio-Graph-Card2, - fw_devlink might doesn't have enough information to break the cycle. rsnd - driver will not be probed in such case. Same problem might occur with - Multi-CPU/Codec or Codec2Codec. - # ports is below port: $ref: audio-graph-port.yaml#/definitions/port-base diff --git a/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml b/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml index f4610eaed1e1..e4cdbf2202b9 100644 --- a/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml +++ b/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml @@ -19,6 +19,7 @@ properties: - renesas,r9a07g043-ssi # RZ/G2UL and RZ/Five - renesas,r9a07g044-ssi # RZ/G2{L,LC} - renesas,r9a07g054-ssi # RZ/V2L + - renesas,r9a08g045-ssi # RZ/G3S - const: renesas,rz-ssi reg: @@ -57,24 +58,6 @@ properties: dmas: minItems: 1 maxItems: 2 - description: - The first cell represents a phandle to dmac. - The second cell specifies the encoded MID/RID values of the SSI port - connected to the DMA client and the slave channel configuration - parameters. - bits[0:9] - Specifies MID/RID value of a SSI channel as below - MID/RID value of SSI rx0 = 0x256 - MID/RID value of SSI tx0 = 0x255 - MID/RID value of SSI rx1 = 0x25a - MID/RID value of SSI tx1 = 0x259 - MID/RID value of SSI rt2 = 0x25f - MID/RID value of SSI rx3 = 0x262 - MID/RID value of SSI tx3 = 0x261 - bit[10] - HIEN = 1, Detects a request in response to the rising edge - of the signal - bit[11] - LVL = 0, Detects based on the edge - bits[12:14] - AM = 2, Bus cycle mode - bit[15] - TM = 0, Single transfer mode dma-names: oneOf: diff --git a/Documentation/devicetree/bindings/sound/rt5682.txt b/Documentation/devicetree/bindings/sound/rt5682.txt deleted file mode 100644 index 5e1d08de18a5..000000000000 --- a/Documentation/devicetree/bindings/sound/rt5682.txt +++ /dev/null @@ -1,98 +0,0 @@ -RT5682 audio CODEC - -This device supports I2C only. - -Required properties: - -- compatible : "realtek,rt5682" or "realtek,rt5682i" - -- reg : The I2C address of the device. - -- AVDD-supply: phandle to the regulator supplying analog power through the - AVDD pin - -- MICVDD-supply: phandle to the regulator supplying power for the microphone - bias through the MICVDD pin. Either MICVDD or VBAT should be present. - -- VBAT-supply: phandle to the regulator supplying battery power through the - VBAT pin. Either MICVDD or VBAT should be present. - -- DBVDD-supply: phandle to the regulator supplying I/O power through the DBVDD - pin. - -- LDO1-IN-supply: phandle to the regulator supplying power to the digital core - and charge pump through the LDO1_IN pin. - -Optional properties: - -- interrupts : The CODEC's interrupt output. - -- realtek,dmic1-data-pin - 0: dmic1 is not used - 1: using GPIO2 pin as dmic1 data pin - 2: using GPIO5 pin as dmic1 data pin - -- realtek,dmic1-clk-pin - 0: using GPIO1 pin as dmic1 clock pin - 1: using GPIO3 pin as dmic1 clock pin - -- realtek,jd-src - 0: No JD is used - 1: using JD1 as JD source - -- realtek,ldo1-en-gpios : The GPIO that controls the CODEC's LDO1_EN pin. - -- realtek,btndet-delay - The debounce delay for push button. - The delay time is realtek,btndet-delay value multiple of 8.192 ms. - If absent, the default is 16. - -- #clock-cells : Should be set to '<1>', wclk and bclk sources provided. -- clock-output-names : Name given for DAI clocks output. - -- clocks : phandle and clock specifier for codec MCLK. -- clock-names : Clock name string for 'clocks' attribute, should be "mclk". - -- realtek,dmic-clk-rate-hz : Set the clock rate (hz) for the requirement of - the particular DMIC. - -- realtek,dmic-delay-ms : Set the delay time (ms) for the requirement of - the particular DMIC. - -- realtek,dmic-clk-driving-high : Set the high driving of the DMIC clock out. - -- #sound-dai-cells: Should be set to '<1>'. - -Pins on the device (for linking into audio routes) for RT5682: - - * DMIC L1 - * DMIC R1 - * IN1P - * HPOL - * HPOR - -Example: - -rt5682 { - compatible = "realtek,rt5682i"; - reg = <0x1a>; - interrupt-parent = <&gpio>; - interrupts = ; - realtek,ldo1-en-gpios = - <&gpio TEGRA_GPIO(R, 2) GPIO_ACTIVE_HIGH>; - realtek,dmic1-data-pin = <1>; - realtek,dmic1-clk-pin = <1>; - realtek,jd-src = <1>; - realtek,btndet-delay = <16>; - - #clock-cells = <1>; - clock-output-names = "rt5682-dai-wclk", "rt5682-dai-bclk"; - - clocks = <&osc>; - clock-names = "mclk"; - - AVDD-supply = <&avdd_reg>; - MICVDD-supply = <&micvdd_reg>; - DBVDD-supply = <&dbvdd_reg>; - LDO1-IN-supply = <&ldo1_in_reg>; -}; diff --git a/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml b/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml index 5aa00617291c..1f0e6787a746 100644 --- a/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml +++ b/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/sound/ti,pcm1681.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Texas Instruments PCM1681 8-channel PWM Processor +title: Texas Instruments PCM1681 8-channel Digital-to-Analog Converter maintainers: - Shenghao Ding diff --git a/Documentation/devicetree/bindings/sound/ti,pcm6240.yaml b/Documentation/devicetree/bindings/sound/ti,pcm6240.yaml index dd5b08e3d7a1..d89b4255b51c 100644 --- a/Documentation/devicetree/bindings/sound/ti,pcm6240.yaml +++ b/Documentation/devicetree/bindings/sound/ti,pcm6240.yaml @@ -159,19 +159,21 @@ additionalProperties: false examples: - | - #include - i2c { - /* example for two devices with interrupt support */ - #address-cells = <1>; - #size-cells = <0>; - pcm6240: audio-codec@48 { - compatible = "ti,pcm6240"; - reg = <0x48>, /* primary-device */ - <0x4b>; /* secondary-device */ - #sound-dai-cells = <0>; - reset-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>; - interrupt-parent = <&gpio1>; - interrupts = <15>; - }; - }; + #include + + i2c { + /* example for two devices with interrupt support */ + #address-cells = <1>; + #size-cells = <0>; + + audio-codec@48 { + compatible = "ti,pcm6240"; + reg = <0x48>, /* primary-device */ + <0x4b>; /* secondary-device */ + #sound-dai-cells = <0>; + reset-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&gpio1>; + interrupts = <15>; + }; + }; ... diff --git a/Documentation/devicetree/bindings/sound/ti,tas2562.yaml b/Documentation/devicetree/bindings/sound/ti,tas2562.yaml index 8bc3b0c7531e..3763ca16b91f 100644 --- a/Documentation/devicetree/bindings/sound/ti,tas2562.yaml +++ b/Documentation/devicetree/bindings/sound/ti,tas2562.yaml @@ -65,17 +65,19 @@ unevaluatedProperties: false examples: - | - #include - i2c { - #address-cells = <1>; - #size-cells = <0>; - codec: codec@4c { - compatible = "ti,tas2562"; - reg = <0x4c>; - #sound-dai-cells = <0>; - interrupt-parent = <&gpio1>; - interrupts = <14>; - shutdown-gpios = <&gpio1 15 0>; - ti,imon-slot-no = <0>; - }; - }; + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + codec@4c { + compatible = "ti,tas2562"; + reg = <0x4c>; + #sound-dai-cells = <0>; + interrupt-parent = <&gpio1>; + interrupts = <14>; + shutdown-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; + ti,imon-slot-no = <0>; + }; + }; diff --git a/Documentation/devicetree/bindings/sound/ti,tas2770.yaml b/Documentation/devicetree/bindings/sound/ti,tas2770.yaml index 362c2e6154f0..5e7aea43aced 100644 --- a/Documentation/devicetree/bindings/sound/ti,tas2770.yaml +++ b/Documentation/devicetree/bindings/sound/ti,tas2770.yaml @@ -69,19 +69,21 @@ unevaluatedProperties: false examples: - | - #include - i2c { - #address-cells = <1>; - #size-cells = <0>; - codec: codec@41 { - compatible = "ti,tas2770"; - reg = <0x41>; - #sound-dai-cells = <0>; - interrupt-parent = <&gpio1>; - interrupts = <14>; - reset-gpio = <&gpio1 15 0>; - shutdown-gpios = <&gpio1 14 0>; - ti,imon-slot-no = <0>; - ti,vmon-slot-no = <2>; - }; - }; + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + codec@41 { + compatible = "ti,tas2770"; + reg = <0x41>; + #sound-dai-cells = <0>; + interrupt-parent = <&gpio1>; + interrupts = <14>; + reset-gpio = <&gpio1 15 GPIO_ACTIVE_HIGH>; + shutdown-gpios = <&gpio1 14 GPIO_ACTIVE_HIGH>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + }; + }; diff --git a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml index 976238689249..5ea1cdc593b5 100644 --- a/Documentation/devicetree/bindings/sound/ti,tas2781.yaml +++ b/Documentation/devicetree/bindings/sound/ti,tas2781.yaml @@ -101,22 +101,24 @@ additionalProperties: false examples: - | - #include - i2c { - /* example with quad tas2781s, such as tablet or pad device */ - #address-cells = <1>; - #size-cells = <0>; - quad_tas2781: tas2781@38 { - compatible = "ti,tas2781"; - reg = <0x38>, /* Audio slot 0 */ - <0x3a>, /* Audio slot 1 */ - <0x39>, /* Audio slot 2 */ - <0x3b>; /* Audio slot 3 */ + #include - #sound-dai-cells = <0>; - reset-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>; - interrupt-parent = <&gpio1>; - interrupts = <15>; - }; - }; + i2c { + /* example with quad tas2781s, such as tablet or pad device */ + #address-cells = <1>; + #size-cells = <0>; + + audio-codec@38 { + compatible = "ti,tas2781"; + reg = <0x38>, /* Audio slot 0 */ + <0x3a>, /* Audio slot 1 */ + <0x39>, /* Audio slot 2 */ + <0x3b>; /* Audio slot 3 */ + + #sound-dai-cells = <0>; + reset-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&gpio1>; + interrupts = <15>; + }; + }; ... diff --git a/Documentation/devicetree/bindings/sound/ti,tas27xx.yaml b/Documentation/devicetree/bindings/sound/ti,tas27xx.yaml index 530bc3937847..5447482179c1 100644 --- a/Documentation/devicetree/bindings/sound/ti,tas27xx.yaml +++ b/Documentation/devicetree/bindings/sound/ti,tas27xx.yaml @@ -62,21 +62,23 @@ unevaluatedProperties: false examples: - | - #include - i2c { - #address-cells = <1>; - #size-cells = <0>; - codec: codec@38 { - compatible = "ti,tas2764"; - reg = <0x38>; - #sound-dai-cells = <0>; - interrupt-parent = <&gpio1>; - interrupts = <14>; - reset-gpios = <&gpio1 15 0>; - shutdown-gpios = <&gpio1 15 0>; - ti,imon-slot-no = <0>; - ti,vmon-slot-no = <2>; - }; - }; + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + codec@38 { + compatible = "ti,tas2764"; + reg = <0x38>; + #sound-dai-cells = <0>; + interrupt-parent = <&gpio1>; + interrupts = <14>; + reset-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; + shutdown-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + }; + }; ... diff --git a/Documentation/devicetree/bindings/sound/ti,tas57xx.yaml b/Documentation/devicetree/bindings/sound/ti,tas57xx.yaml index 2f917238db95..74f7d02b424b 100644 --- a/Documentation/devicetree/bindings/sound/ti,tas57xx.yaml +++ b/Documentation/devicetree/bindings/sound/ti,tas57xx.yaml @@ -112,22 +112,24 @@ unevaluatedProperties: false examples: - | - i2c { - #address-cells = <1>; - #size-cells = <0>; + #include - codec@2a { - compatible = "ti,tas5717"; - reg = <0x2a>; - #sound-dai-cells = <0>; - reset-gpios = <&gpio1 15 0>; - pdn-gpios = <&gpio1 15 0>; - AVDD-supply = <&avdd_supply>; - DVDD-supply = <&dvdd_supply>; - HPVDD-supply = <&hpvdd_supply>; - PVDD_AB-supply = <&pvdd_ab_supply>; - PVDD_CD-supply = <&pvdd_cd_supply>; - }; - }; + i2c { + #address-cells = <1>; + #size-cells = <0>; + + codec@2a { + compatible = "ti,tas5717"; + reg = <0x2a>; + #sound-dai-cells = <0>; + reset-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; + pdn-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; + AVDD-supply = <&avdd_supply>; + DVDD-supply = <&dvdd_supply>; + HPVDD-supply = <&hpvdd_supply>; + PVDD_AB-supply = <&pvdd_ab_supply>; + PVDD_CD-supply = <&pvdd_cd_supply>; + }; + }; ... diff --git a/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml b/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml index d48ecd6cd5ad..b6bc71d19286 100644 --- a/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml +++ b/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml @@ -68,6 +68,7 @@ properties: - items: - enum: - amd,pensando-elba-qspi + - amd,versal2-ospi - intel,lgm-qspi - intel,socfpga-qspi - mobileye,eyeq5-ospi diff --git a/Documentation/devicetree/bindings/spi/spi-controller.yaml b/Documentation/devicetree/bindings/spi/spi-controller.yaml index 093150c0cb87..82d051f7bd6e 100644 --- a/Documentation/devicetree/bindings/spi/spi-controller.yaml +++ b/Documentation/devicetree/bindings/spi/spi-controller.yaml @@ -69,6 +69,11 @@ properties: Should be generally avoided and be replaced by spi-cs-high + ACTIVE_HIGH. + The simplest way to obtain an active-high CS signal is to configure the + controller's cs-gpio property with the ACTIVE_HIGH flag and set the + peripheral's spi-cs-high property. See example below for a better + understanding. + fifo-depth: $ref: /schemas/types.yaml#/definitions/uint32 description: @@ -189,3 +194,23 @@ examples: stacked-memories = /bits/ 64 <0x10000000 0x10000000>; }; }; + + - | + #include + + spi@20204000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "brcm,bcm2835-spi"; + reg = <0x7e204000 0x1000>; + interrupts = <2 22>; + clocks = <&clk_spi>; + cs-gpios = <&gpio 8 GPIO_ACTIVE_HIGH>; + + display@0 { + compatible = "lg,lg4573"; + spi-max-frequency = <1000000>; + reg = <0>; + spi-cs-high; + }; + }; diff --git a/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml index d9322704f358..a7236f7db4ec 100644 --- a/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml +++ b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml @@ -47,7 +47,9 @@ properties: - const: allwinner,sun8i-v3s-system-control - const: allwinner,sun8i-h3-system-control - items: - - const: allwinner,sun50i-h6-system-control + - enum: + - allwinner,sun50i-a100-system-control + - allwinner,sun50i-h6-system-control - const: allwinner,sun50i-a64-system-control reg: diff --git a/Documentation/devicetree/bindings/sram/qcom,imem.yaml b/Documentation/devicetree/bindings/sram/qcom,imem.yaml index 9b06bcd01957..2711f90d9664 100644 --- a/Documentation/devicetree/bindings/sram/qcom,imem.yaml +++ b/Documentation/devicetree/bindings/sram/qcom,imem.yaml @@ -20,6 +20,7 @@ properties: - qcom,apq8064-imem - qcom,msm8226-imem - qcom,msm8974-imem + - qcom,msm8976-imem - qcom,qcs404-imem - qcom,qcs8300-imem - qcom,qdu1000-imem diff --git a/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml b/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml index ed5de0f92a9e..b9829bb22cc0 100644 --- a/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml +++ b/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml @@ -80,6 +80,7 @@ properties: - description: v2 of TSENS with combined interrupt items: - enum: + - qcom,ipq6018-tsens - qcom,ipq9574-tsens - const: qcom,ipq8074-tsens diff --git a/Documentation/devicetree/bindings/timer/fsl,imxgpt.yaml b/Documentation/devicetree/bindings/timer/fsl,imxgpt.yaml index e2607377cbae..9898dc7ea97b 100644 --- a/Documentation/devicetree/bindings/timer/fsl,imxgpt.yaml +++ b/Documentation/devicetree/bindings/timer/fsl,imxgpt.yaml @@ -21,6 +21,7 @@ properties: - items: - enum: - fsl,imx25-gpt + - fsl,imx35-gpt - fsl,imx50-gpt - fsl,imx51-gpt - fsl,imx53-gpt @@ -31,6 +32,7 @@ properties: - enum: - fsl,imx6sl-gpt - fsl,imx6sx-gpt + - fsl,imx7d-gpt - fsl,imx8mp-gpt - fsl,imxrt1050-gpt - fsl,imxrt1170-gpt @@ -38,7 +40,6 @@ properties: - items: - enum: - fsl,imx6ul-gpt - - fsl,imx7d-gpt - const: fsl,imx6sx-gpt reg: diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml index b42d43d2de48..76d83aea4e2b 100644 --- a/Documentation/devicetree/bindings/timer/sifive,clint.yaml +++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml @@ -31,6 +31,7 @@ properties: - enum: - canaan,k210-clint # Canaan Kendryte K210 - sifive,fu540-c000-clint # SiFive FU540 + - spacemit,k1-clint # SpacemiT K1 - starfive,jh7100-clint # StarFive JH7100 - starfive,jh7110-clint # StarFive JH7110 - starfive,jh8100-clint # StarFive JH8100 diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml index 88abb5c174f3..fadbd3c041c8 100644 --- a/Documentation/devicetree/bindings/trivial-devices.yaml +++ b/Documentation/devicetree/bindings/trivial-devices.yaml @@ -55,8 +55,6 @@ properties: - atmel,atsha204a # BPA-RS600: Power Supply - blutek,bpa-rs600 - # Bosch Sensortec pressure, temperature, humididty and VOC sensor - - bosch,bme680 # CM32181: Ambient Light Sensor - capella,cm32181 # CM3232: Ambient Light Sensor @@ -147,8 +145,12 @@ properties: - injoinic,ip5207 # Injoinic IP5209 2.4A Power Bank IC with I2C - injoinic,ip5209 + # Injoinic IP5306 2.1A Power Bank IC with I2C option + - injoinic,ip5306 # Inspur Power System power supply unit version 1 - inspur,ipsps1 + # Intel common redudant power supply crps185 + - intel,crps185 # Intersil ISL29028 Ambient Light and Proximity Sensor - isil,isl29028 # Intersil ISL29030 Ambient Light and Proximity Sensor diff --git a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml index cde334e3206b..a03fff5df5ef 100644 --- a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml +++ b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml @@ -26,6 +26,7 @@ properties: - qcom,msm8994-ufshc - qcom,msm8996-ufshc - qcom,msm8998-ufshc + - qcom,qcs615-ufshc - qcom,qcs8300-ufshc - qcom,sa8775p-ufshc - qcom,sc7180-ufshc @@ -243,6 +244,7 @@ allOf: compatible: contains: enum: + - qcom,qcs615-ufshc - qcom,sm6115-ufshc - qcom,sm6125-ufshc then: diff --git a/Documentation/devicetree/bindings/ufs/renesas,ufs.yaml b/Documentation/devicetree/bindings/ufs/renesas,ufs.yaml index f04f9f61fa9f..1949a15e73d2 100644 --- a/Documentation/devicetree/bindings/ufs/renesas,ufs.yaml +++ b/Documentation/devicetree/bindings/ufs/renesas,ufs.yaml @@ -50,12 +50,12 @@ examples: #include ufs: ufs@e686000 { - compatible = "renesas,r8a779f0-ufs"; - reg = <0xe6860000 0x100>; - interrupts = ; - clocks = <&cpg CPG_MOD 1514>, <&ufs30_clk>; - clock-names = "fck", "ref_clk"; - freq-table-hz = <200000000 200000000>, <38400000 38400000>; - power-domains = <&sysc R8A779F0_PD_ALWAYS_ON>; - resets = <&cpg 1514>; + compatible = "renesas,r8a779f0-ufs"; + reg = <0xe6860000 0x100>; + interrupts = ; + clocks = <&cpg CPG_MOD 1514>, <&ufs30_clk>; + clock-names = "fck", "ref_clk"; + freq-table-hz = <200000000 200000000>, <38400000 38400000>; + power-domains = <&sysc R8A779F0_PD_ALWAYS_ON>; + resets = <&cpg 1514>; }; diff --git a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml index 720879820f66..b4e744ebffd1 100644 --- a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml +++ b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml @@ -112,19 +112,19 @@ examples: #include ufs: ufs@15570000 { - compatible = "samsung,exynos7-ufs"; - reg = <0x15570000 0x100>, - <0x15570100 0x100>, - <0x15571000 0x200>, - <0x15572000 0x300>; - reg-names = "hci", "vs_hci", "unipro", "ufsp"; - interrupts = ; - clocks = <&clock_fsys1 ACLK_UFS20_LINK>, - <&clock_fsys1 SCLK_UFSUNIPRO20_USER>; - clock-names = "core_clk", "sclk_unipro_main"; - pinctrl-names = "default"; - pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>; - phys = <&ufs_phy>; - phy-names = "ufs-phy"; + compatible = "samsung,exynos7-ufs"; + reg = <0x15570000 0x100>, + <0x15570100 0x100>, + <0x15571000 0x200>, + <0x15572000 0x300>; + reg-names = "hci", "vs_hci", "unipro", "ufsp"; + interrupts = ; + clocks = <&clock_fsys1 ACLK_UFS20_LINK>, + <&clock_fsys1 SCLK_UFSUNIPRO20_USER>; + clock-names = "core_clk", "sclk_unipro_main"; + pinctrl-names = "default"; + pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>; + phys = <&ufs_phy>; + phy-names = "ufs-phy"; }; ... diff --git a/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml b/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml index a86bcd95100e..7f22f9c031b2 100644 --- a/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml +++ b/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml @@ -113,27 +113,27 @@ examples: - | #include vhub: usb-vhub@1e6a0000 { - compatible = "aspeed,ast2500-usb-vhub"; - reg = <0x1e6a0000 0x300>; - interrupts = <5>; - clocks = <&syscon ASPEED_CLK_GATE_USBPORT1CLK>; - aspeed,vhub-downstream-ports = <5>; - aspeed,vhub-generic-endpoints = <15>; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_usb2ad_default>; + compatible = "aspeed,ast2500-usb-vhub"; + reg = <0x1e6a0000 0x300>; + interrupts = <5>; + clocks = <&syscon ASPEED_CLK_GATE_USBPORT1CLK>; + aspeed,vhub-downstream-ports = <5>; + aspeed,vhub-generic-endpoints = <15>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usb2ad_default>; - vhub-vendor-id = <0x1d6b>; - vhub-product-id = <0x0107>; - vhub-device-revision = <0x0100>; - vhub-strings { - #address-cells = <1>; - #size-cells = <0>; + vhub-vendor-id = <0x1d6b>; + vhub-product-id = <0x0107>; + vhub-device-revision = <0x0100>; + vhub-strings { + #address-cells = <1>; + #size-cells = <0>; - string@409 { - reg = <0x409>; - manufacturer = "ASPEED"; - product = "USB Virtual Hub"; - serial-number = "0000"; - }; + string@409 { + reg = <0x409>; + manufacturer = "ASPEED"; + product = "USB Virtual Hub"; + serial-number = "0000"; }; + }; }; diff --git a/Documentation/devicetree/bindings/usb/brcm,bdc.yaml b/Documentation/devicetree/bindings/usb/brcm,bdc.yaml index 9e561fee98f1..f9375c69e86b 100644 --- a/Documentation/devicetree/bindings/usb/brcm,bdc.yaml +++ b/Documentation/devicetree/bindings/usb/brcm,bdc.yaml @@ -41,10 +41,10 @@ additionalProperties: false examples: - | - usb@f0b02000 { - compatible = "brcm,bdc-udc-v2"; - reg = <0xf0b02000 0xfc4>; - interrupts = <0x0 0x60 0x0>; - phys = <&usbphy_0 0x0>; - clocks = <&sw_usbd>; - }; + usb@f0b02000 { + compatible = "brcm,bdc-udc-v2"; + reg = <0xf0b02000 0xfc4>; + interrupts = <0x0 0x60 0x0>; + phys = <&usbphy_0 0x0>; + clocks = <&sw_usbd>; + }; diff --git a/Documentation/devicetree/bindings/usb/cypress,hx3.yaml b/Documentation/devicetree/bindings/usb/cypress,hx3.yaml index e44e88d993d0..1033b7a4b8f9 100644 --- a/Documentation/devicetree/bindings/usb/cypress,hx3.yaml +++ b/Documentation/devicetree/bindings/usb/cypress,hx3.yaml @@ -56,21 +56,21 @@ examples: /* 2.0 hub on port 1 */ hub_2_0: hub@1 { - compatible = "usb4b4,6504"; - reg = <1>; - peer-hub = <&hub_3_0>; - reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; - vdd-supply = <®_1v2_usb>; - vdd2-supply = <®_3v3_usb>; + compatible = "usb4b4,6504"; + reg = <1>; + peer-hub = <&hub_3_0>; + reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; + vdd-supply = <®_1v2_usb>; + vdd2-supply = <®_3v3_usb>; }; /* 3.0 hub on port 2 */ hub_3_0: hub@2 { - compatible = "usb4b4,6506"; - reg = <2>; - peer-hub = <&hub_2_0>; - reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; - vdd-supply = <®_1v2_usb>; - vdd2-supply = <®_3v3_usb>; + compatible = "usb4b4,6506"; + reg = <2>; + peer-hub = <&hub_2_0>; + reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; + vdd-supply = <®_1v2_usb>; + vdd2-supply = <®_3v3_usb>; }; }; diff --git a/Documentation/devicetree/bindings/usb/dwc2.yaml b/Documentation/devicetree/bindings/usb/dwc2.yaml index a5f2e3442a0e..e83d30a91b88 100644 --- a/Documentation/devicetree/bindings/usb/dwc2.yaml +++ b/Documentation/devicetree/bindings/usb/dwc2.yaml @@ -192,7 +192,7 @@ unevaluatedProperties: false examples: - | - usb@101c0000 { + usb@101c0000 { compatible = "rockchip,rk3066-usb", "snps,dwc2"; reg = <0x10180000 0x40000>; interrupts = <18>; @@ -200,6 +200,6 @@ examples: clock-names = "otg"; phys = <&usbphy>; phy-names = "usb2-phy"; - }; + }; ... diff --git a/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml b/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml index 8b25b9a01ced..e3a7df91f7f1 100644 --- a/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml +++ b/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml @@ -87,21 +87,21 @@ examples: #size-cells = <0>; typec-mux@42 { - compatible = "fcs,fsa4480"; - reg = <0x42>; + compatible = "fcs,fsa4480"; + reg = <0x42>; - interrupts-extended = <&tlmm 2 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&tlmm 2 IRQ_TYPE_LEVEL_LOW>; - vcc-supply = <&vreg_bob>; + vcc-supply = <&vreg_bob>; - mode-switch; - orientation-switch; + mode-switch; + orientation-switch; - port { - fsa4480_ept: endpoint { - remote-endpoint = <&typec_controller>; + port { + fsa4480_ept: endpoint { + remote-endpoint = <&typec_controller>; + }; }; - }; }; }; ... diff --git a/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml b/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml index 8a5f837eff94..e588514fab2d 100644 --- a/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml +++ b/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml @@ -20,6 +20,7 @@ properties: items: - enum: - nxp,cbdtu02043 + - onnn,fsusb42 - onnn,fsusb43l10x - pericom,pi3usb102 - ti,tmuxhs4212 diff --git a/Documentation/devicetree/bindings/usb/intel,keembay-dwc3.yaml b/Documentation/devicetree/bindings/usb/intel,keembay-dwc3.yaml index d3511f48cd55..1a75544a8c31 100644 --- a/Documentation/devicetree/bindings/usb/intel,keembay-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/intel,keembay-dwc3.yaml @@ -58,20 +58,20 @@ examples: #define KEEM_BAY_A53_AUX_USB_SUSPEND usb { - compatible = "intel,keembay-dwc3"; - clocks = <&scmi_clk KEEM_BAY_A53_AUX_USB>, - <&scmi_clk KEEM_BAY_A53_AUX_USB_REF>, - <&scmi_clk KEEM_BAY_A53_AUX_USB_ALT_REF>, - <&scmi_clk KEEM_BAY_A53_AUX_USB_SUSPEND>; - clock-names = "async_master", "ref", "alt_ref", "suspend"; - ranges; - #address-cells = <1>; - #size-cells = <1>; + compatible = "intel,keembay-dwc3"; + clocks = <&scmi_clk KEEM_BAY_A53_AUX_USB>, + <&scmi_clk KEEM_BAY_A53_AUX_USB_REF>, + <&scmi_clk KEEM_BAY_A53_AUX_USB_ALT_REF>, + <&scmi_clk KEEM_BAY_A53_AUX_USB_SUSPEND>; + clock-names = "async_master", "ref", "alt_ref", "suspend"; + ranges; + #address-cells = <1>; + #size-cells = <1>; - usb@34000000 { - compatible = "snps,dwc3"; - reg = <0x34000000 0x10000>; - interrupts = ; - dr_mode = "peripheral"; - }; + usb@34000000 { + compatible = "snps,dwc3"; + reg = <0x34000000 0x10000>; + interrupts = ; + dr_mode = "peripheral"; + }; }; diff --git a/Documentation/devicetree/bindings/usb/ite,it5205.yaml b/Documentation/devicetree/bindings/usb/ite,it5205.yaml index 36ec4251b5f2..889710733de5 100644 --- a/Documentation/devicetree/bindings/usb/ite,it5205.yaml +++ b/Documentation/devicetree/bindings/usb/ite,it5205.yaml @@ -54,19 +54,19 @@ examples: #size-cells = <0>; typec-mux@48 { - compatible = "ite,it5205"; - reg = <0x48>; + compatible = "ite,it5205"; + reg = <0x48>; - mode-switch; - orientation-switch; + mode-switch; + orientation-switch; - vcc-supply = <&mt6359_vibr_ldo_reg>; + vcc-supply = <&mt6359_vibr_ldo_reg>; - port { - it5205_usbss_sbu: endpoint { - remote-endpoint = <&typec_controller>; + port { + it5205_usbss_sbu: endpoint { + remote-endpoint = <&typec_controller>; + }; }; - }; }; }; ... diff --git a/Documentation/devicetree/bindings/usb/maxim,max33359.yaml b/Documentation/devicetree/bindings/usb/maxim,max33359.yaml index 20b62228371b..3de4dc40b791 100644 --- a/Documentation/devicetree/bindings/usb/maxim,max33359.yaml +++ b/Documentation/devicetree/bindings/usb/maxim,max33359.yaml @@ -13,8 +13,12 @@ description: Maxim TCPCI Type-C PD controller properties: compatible: - enum: - - maxim,max33359 + oneOf: + - enum: + - maxim,max33359 + - items: + - const: maxim,max77759-tcpci + - const: maxim,max33359 reg: maxItems: 1 @@ -70,6 +74,7 @@ examples: PDO_FIXED_DUAL_ROLE) PDO_FIXED(9000, 2000, 0)>; sink-bc12-completion-time-ms = <500>; + pd-revision = /bits/ 8 <0x03 0x01 0x01 0x08>; }; }; }; diff --git a/Documentation/devicetree/bindings/usb/maxim,max3420-udc.yaml b/Documentation/devicetree/bindings/usb/maxim,max3420-udc.yaml index 8e0f4ecc010d..6edb1fc5044e 100644 --- a/Documentation/devicetree/bindings/usb/maxim,max3420-udc.yaml +++ b/Documentation/devicetree/bindings/usb/maxim,max3420-udc.yaml @@ -50,18 +50,18 @@ additionalProperties: false examples: - | - #include - #include - spi { - #address-cells = <1>; - #size-cells = <0>; + #include + #include + spi { + #address-cells = <1>; + #size-cells = <0>; - udc@0 { - compatible = "maxim,max3420-udc"; - reg = <0>; - interrupt-parent = <&gpio>; - interrupts = <0 IRQ_TYPE_EDGE_FALLING>, <10 IRQ_TYPE_EDGE_BOTH>; - interrupt-names = "udc", "vbus"; - spi-max-frequency = <12500000>; - }; - }; + udc@0 { + compatible = "maxim,max3420-udc"; + reg = <0>; + interrupt-parent = <&gpio>; + interrupts = <0 IRQ_TYPE_EDGE_FALLING>, <10 IRQ_TYPE_EDGE_BOTH>; + interrupt-names = "udc", "vbus"; + spi-max-frequency = <12500000>; + }; + }; diff --git a/Documentation/devicetree/bindings/usb/nvidia,tegra210-xusb.yaml b/Documentation/devicetree/bindings/usb/nvidia,tegra210-xusb.yaml index 90296613b3a5..c0e313c70bba 100644 --- a/Documentation/devicetree/bindings/usb/nvidia,tegra210-xusb.yaml +++ b/Documentation/devicetree/bindings/usb/nvidia,tegra210-xusb.yaml @@ -189,7 +189,7 @@ examples: #size-cells = <0>; ethernet@1 { - compatible = "usb955,9ff"; - reg = <1>; + compatible = "usb955,9ff"; + reg = <1>; }; }; diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml index 935e204b607b..a2b3cf625e5b 100644 --- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml @@ -16,6 +16,7 @@ properties: - qcom,ipq4019-dwc3 - qcom,ipq5018-dwc3 - qcom,ipq5332-dwc3 + - qcom,ipq5424-dwc3 - qcom,ipq6018-dwc3 - qcom,ipq8064-dwc3 - qcom,ipq8074-dwc3 @@ -26,6 +27,7 @@ properties: - qcom,msm8998-dwc3 - qcom,qcm2290-dwc3 - qcom,qcs404-dwc3 + - qcom,qcs615-dwc3 - qcom,qcs8300-dwc3 - qcom,qdu1000-dwc3 - qcom,sa8775p-dwc3 @@ -341,6 +343,7 @@ allOf: contains: enum: - qcom,qcm2290-dwc3 + - qcom,qcs615-dwc3 - qcom,sar2130p-dwc3 - qcom,sc8180x-dwc3 - qcom,sc8180x-dwc3-mp @@ -453,8 +456,10 @@ allOf: then: properties: interrupts: + minItems: 3 maxItems: 4 interrupt-names: + minItems: 3 items: - const: pwr_event - const: dp_hs_phy_irq @@ -469,6 +474,7 @@ allOf: - qcom,ipq4019-dwc3 - qcom,ipq8064-dwc3 - qcom,msm8994-dwc3 + - qcom,qcs615-dwc3 - qcom,qcs8300-dwc3 - qcom,qdu1000-dwc3 - qcom,sa8775p-dwc3 diff --git a/Documentation/devicetree/bindings/usb/renesas,rzv2m-usb3drd.yaml b/Documentation/devicetree/bindings/usb/renesas,rzv2m-usb3drd.yaml index ff625600d9af..b87e139c29e5 100644 --- a/Documentation/devicetree/bindings/usb/renesas,rzv2m-usb3drd.yaml +++ b/Documentation/devicetree/bindings/usb/renesas,rzv2m-usb3drd.yaml @@ -104,26 +104,26 @@ examples: #size-cells = <1>; usb3host: usb@85060000 { - compatible = "renesas,r9a09g011-xhci", - "renesas,rzv2m-xhci"; - reg = <0x85060000 0x2000>; - interrupts = ; - clocks = <&cpg CPG_MOD R9A09G011_USB_ACLK_H>, - <&cpg CPG_MOD R9A09G011_USB_PCLK>; - clock-names = "axi", "reg"; - power-domains = <&cpg>; - resets = <&cpg R9A09G011_USB_ARESETN_H>; + compatible = "renesas,r9a09g011-xhci", + "renesas,rzv2m-xhci"; + reg = <0x85060000 0x2000>; + interrupts = ; + clocks = <&cpg CPG_MOD R9A09G011_USB_ACLK_H>, + <&cpg CPG_MOD R9A09G011_USB_PCLK>; + clock-names = "axi", "reg"; + power-domains = <&cpg>; + resets = <&cpg R9A09G011_USB_ARESETN_H>; }; usb3peri: usb3peri@85070000 { - compatible = "renesas,r9a09g011-usb3-peri", - "renesas,rzv2m-usb3-peri"; - reg = <0x85070000 0x400>; - interrupts = ; - clocks = <&cpg CPG_MOD R9A09G011_USB_ACLK_P>, - <&cpg CPG_MOD R9A09G011_USB_PCLK>; - clock-names = "axi", "reg"; - power-domains = <&cpg>; - resets = <&cpg R9A09G011_USB_ARESETN_P>; + compatible = "renesas,r9a09g011-usb3-peri", + "renesas,rzv2m-usb3-peri"; + reg = <0x85070000 0x400>; + interrupts = ; + clocks = <&cpg CPG_MOD R9A09G011_USB_ACLK_P>, + <&cpg CPG_MOD R9A09G011_USB_PCLK>; + clock-names = "axi", "reg"; + power-domains = <&cpg>; + resets = <&cpg R9A09G011_USB_ARESETN_P>; }; }; diff --git a/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml b/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml index b2b811a0ade8..4e56e4ffeaf2 100644 --- a/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml +++ b/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml @@ -132,19 +132,19 @@ examples: usb-role-switch; ports { - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; - usb3_hs_ep: endpoint { - remote-endpoint = <&hs_ep>; - }; + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + usb3_hs_ep: endpoint { + remote-endpoint = <&hs_ep>; }; - port@1 { - reg = <1>; - usb3_role_switch: endpoint { - remote-endpoint = <&hd3ss3220_out_ep>; - }; + }; + port@1 { + reg = <1>; + usb3_role_switch: endpoint { + remote-endpoint = <&hd3ss3220_out_ep>; }; + }; }; }; diff --git a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml index b23ef29bf794..980f325341d4 100644 --- a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml +++ b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml @@ -26,6 +26,7 @@ properties: - renesas,usbhs-r9a07g043 # RZ/G2UL and RZ/Five - renesas,usbhs-r9a07g044 # RZ/G2{L,LC} - renesas,usbhs-r9a07g054 # RZ/V2L + - renesas,usbhs-r9a08g045 # RZ/G3S - const: renesas,rzg2l-usbhs - items: @@ -130,6 +131,7 @@ allOf: - renesas,usbhs-r9a07g043 - renesas,usbhs-r9a07g044 - renesas,usbhs-r9a07g054 + - renesas,usbhs-r9a08g045 then: properties: interrupts: diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3-common.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3-common.yaml new file mode 100644 index 000000000000..c956053fd036 --- /dev/null +++ b/Documentation/devicetree/bindings/usb/snps,dwc3-common.yaml @@ -0,0 +1,415 @@ +# SPDX-License-Identifier: GPL-2.0 +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/usb/snps,dwc3-common.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Synopsys DesignWare USB3 Controller common properties + +maintainers: + - Felipe Balbi + +description: + Defines the properties of the DWC3 core as being embedded in either an + vendor-specific implementation or as a standalone component. + +allOf: + - $ref: usb-drd.yaml# + - if: + properties: + dr_mode: + const: peripheral + + required: + - dr_mode + then: + $ref: usb.yaml# + else: + $ref: usb-xhci.yaml# + +properties: + extcon: + maxItems: 1 + deprecated: true + + usb-phy: + minItems: 1 + items: + - description: USB2/HS PHY + - description: USB3/SS PHY + + phys: + minItems: 1 + maxItems: 19 + + phy-names: + minItems: 1 + maxItems: 19 + oneOf: + - items: + enum: [ usb2-phy, usb3-phy ] + - items: + pattern: "^usb(2-([0-9]|1[0-4])|3-[0-3])$" + + snps,usb2-lpm-disable: + description: Indicate if we don't want to enable USB2 HW LPM for host + mode. + type: boolean + + snps,usb3_lpm_capable: + description: Determines if platform is USB3 LPM capable + type: boolean + + snps,usb2-gadget-lpm-disable: + description: Indicate if we don't want to enable USB2 HW LPM for gadget + mode. + type: boolean + + snps,dis-start-transfer-quirk: + description: + When set, disable isoc START TRANSFER command failure SW work-around + for DWC_usb31 version 1.70a-ea06 and prior. + type: boolean + + snps,disable_scramble_quirk: + description: + True when SW should disable data scrambling. Only really useful for FPGA + builds. + type: boolean + + snps,has-lpm-erratum: + description: True when DWC3 was configured with LPM Erratum enabled + type: boolean + + snps,lpm-nyet-threshold: + description: LPM NYET threshold + $ref: /schemas/types.yaml#/definitions/uint8 + + snps,u2exit_lfps_quirk: + description: Set if we want to enable u2exit lfps quirk + type: boolean + + snps,u2ss_inp3_quirk: + description: Set if we enable P3 OK for U2/SS Inactive quirk + type: boolean + + snps,req_p1p2p3_quirk: + description: + When set, the core will always request for P1/P2/P3 transition sequence. + type: boolean + + snps,del_p1p2p3_quirk: + description: + When set core will delay P1/P2/P3 until a certain amount of 8B10B errors + occur. + type: boolean + + snps,del_phy_power_chg_quirk: + description: When set core will delay PHY power change from P0 to P1/P2/P3. + type: boolean + + snps,lfps_filter_quirk: + description: When set core will filter LFPS reception. + type: boolean + + snps,rx_detect_poll_quirk: + description: + when set core will disable a 400us delay to start Polling LFPS after + RX.Detect. + type: boolean + + snps,tx_de_emphasis_quirk: + description: When set core will set Tx de-emphasis value + type: boolean + + snps,tx_de_emphasis: + description: + The value driven to the PHY is controlled by the LTSSM during USB3 + Compliance mode. + $ref: /schemas/types.yaml#/definitions/uint8 + enum: + - 0 # -6dB de-emphasis + - 1 # -3.5dB de-emphasis + - 2 # No de-emphasis + + snps,dis_u3_susphy_quirk: + description: When set core will disable USB3 suspend phy + type: boolean + + snps,dis_u2_susphy_quirk: + description: When set core will disable USB2 suspend phy + type: boolean + + snps,dis_enblslpm_quirk: + description: + When set clears the enblslpm in GUSB2PHYCFG, disabling the suspend signal + to the PHY. + type: boolean + + snps,dis-u1-entry-quirk: + description: Set if link entering into U1 needs to be disabled + type: boolean + + snps,dis-u2-entry-quirk: + description: Set if link entering into U2 needs to be disabled + type: boolean + + snps,dis_rxdet_inp3_quirk: + description: + When set core will disable receiver detection in PHY P3 power state. + type: boolean + + snps,dis-u2-freeclk-exists-quirk: + description: + When set, clear the u2_freeclk_exists in GUSB2PHYCFG, specify that USB2 + PHY doesn't provide a free-running PHY clock. + type: boolean + + snps,dis-del-phy-power-chg-quirk: + description: + When set core will change PHY power from P0 to P1/P2/P3 without delay. + type: boolean + + snps,dis-tx-ipgap-linecheck-quirk: + description: When set, disable u2mac linestate check during HS transmit + type: boolean + + snps,parkmode-disable-ss-quirk: + description: + When set, all SuperSpeed bus instances in park mode are disabled. + type: boolean + + snps,parkmode-disable-hs-quirk: + description: + When set, all HighSpeed bus instances in park mode are disabled. + type: boolean + + snps,dis_metastability_quirk: + description: + When set, disable metastability workaround. CAUTION! Use only if you are + absolutely sure of it. + type: boolean + + snps,dis-split-quirk: + description: + When set, change the way URBs are handled by the driver. Needed to + avoid -EPROTO errors with usbhid on some devices (Hikey 970). + type: boolean + + snps,gfladj-refclk-lpm-sel-quirk: + description: + When set, run the SOF/ITP counter based on ref_clk. + type: boolean + + snps,resume-hs-terminations: + description: + Fix the issue of HS terminations CRC error on resume by enabling this + quirk. When set, all the termsel, xcvrsel, opmode becomes 0 during end + of resume. This option is to support certain legacy ULPI PHYs. + type: boolean + + snps,ulpi-ext-vbus-drv: + description: + Some ULPI USB PHY does not support internal VBUS supply, and driving + the CPEN pin, requires the configuration of the ulpi DRVVBUSEXTERNAL + bit. When set, the xhci host will configure the USB2 PHY drives VBUS + with an external supply. + type: boolean + + snps,is-utmi-l1-suspend: + description: + True when DWC3 asserts output signal utmi_l1_suspend_n, false when + asserts utmi_sleep_n. + type: boolean + + snps,hird-threshold: + description: HIRD threshold + $ref: /schemas/types.yaml#/definitions/uint8 + + snps,hsphy_interface: + description: + High-Speed PHY interface selection between UTMI+ and ULPI when the + DWC_USB3_HSPHY_INTERFACE has value 3. + $ref: /schemas/types.yaml#/definitions/string + enum: [utmi, ulpi] + + snps,quirk-frame-length-adjustment: + description: + Value for GFLADJ_30MHZ field of GFLADJ register for post-silicon frame + length adjustment when the fladj_30mhz_sdbnd signal is invalid or + incorrect. + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 0x3f + + snps,ref-clock-period-ns: + description: + Value for REFCLKPER field of GUCTL register for reference clock period in + nanoseconds, when the hardware set default does not match the actual + clock. + + This binding is deprecated. Instead, provide an appropriate reference clock. + minimum: 8 + maximum: 62 + deprecated: true + + snps,rx-thr-num-pkt: + description: + USB RX packet threshold count. In host mode, this field specifies + the space that must be available in the RX FIFO before the core can + start the corresponding USB RX transaction (burst). + In device mode, this field specifies the space that must be + available in the RX FIFO before the core can send ERDY for a + flow-controlled endpoint. It is only used for SuperSpeed. + The valid values for this field are from 1 to 15. (DWC3 SuperSpeed + USB 3.0 Controller Databook) + $ref: /schemas/types.yaml#/definitions/uint8 + minimum: 1 + maximum: 15 + + snps,rx-max-burst: + description: + Max USB RX burst size. In host mode, this field specifies the + Maximum Bulk IN burst the DWC_usb3 core can perform. When the system + bus is slower than the USB, RX FIFO can overrun during a long burst. + You can program a smaller value to this field to limit the RX burst + size that the core can perform. It only applies to SS Bulk, + Isochronous, and Interrupt IN endpoints in the host mode. + In device mode, this field specifies the NUMP value that is sent in + ERDY for an OUT endpoint. + The valid values for this field are from 1 to 16. (DWC3 SuperSpeed + USB 3.0 Controller Databook) + $ref: /schemas/types.yaml#/definitions/uint8 + minimum: 1 + maximum: 16 + + snps,tx-thr-num-pkt: + description: + USB TX packet threshold count. This field specifies the number of + packets that must be in the TXFIFO before the core can start + transmission for the corresponding USB transaction (burst). + This count is valid in both host and device modes. It is only used + for SuperSpeed operation. + Valid values are from 1 to 15. (DWC3 SuperSpeed USB 3.0 Controller + Databook) + $ref: /schemas/types.yaml#/definitions/uint8 + minimum: 1 + maximum: 15 + + snps,tx-max-burst: + description: + Max USB TX burst size. When the system bus is slower than the USB, + TX FIFO can underrun during a long burst. Program a smaller value + to this field to limit the TX burst size that the core can execute. + In Host mode, it only applies to SS Bulk, Isochronous, and Interrupt + OUT endpoints. This value is not used in device mode. + Valid values are from 1 to 16. (DWC3 SuperSpeed USB 3.0 Controller + Databook) + $ref: /schemas/types.yaml#/definitions/uint8 + minimum: 1 + maximum: 16 + + snps,rx-thr-num-pkt-prd: + description: + Periodic ESS RX packet threshold count (host mode only). Set this and + snps,rx-max-burst-prd to a valid, non-zero value 1-16 (DWC_usb31 + programming guide section 1.2.4) to enable periodic ESS RX threshold. + $ref: /schemas/types.yaml#/definitions/uint8 + minimum: 1 + maximum: 16 + + snps,rx-max-burst-prd: + description: + Max periodic ESS RX burst size (host mode only). Set this and + snps,rx-thr-num-pkt-prd to a valid, non-zero value 1-16 (DWC_usb31 + programming guide section 1.2.4) to enable periodic ESS RX threshold. + $ref: /schemas/types.yaml#/definitions/uint8 + minimum: 1 + maximum: 16 + + snps,tx-thr-num-pkt-prd: + description: + Periodic ESS TX packet threshold count (host mode only). Set this and + snps,tx-max-burst-prd to a valid, non-zero value 1-16 (DWC_usb31 + programming guide section 1.2.3) to enable periodic ESS TX threshold. + $ref: /schemas/types.yaml#/definitions/uint8 + minimum: 1 + maximum: 16 + + snps,tx-max-burst-prd: + description: + Max periodic ESS TX burst size (host mode only). Set this and + snps,tx-thr-num-pkt-prd to a valid, non-zero value 1-16 (DWC_usb31 + programming guide section 1.2.3) to enable periodic ESS TX threshold. + $ref: /schemas/types.yaml#/definitions/uint8 + minimum: 1 + maximum: 16 + + tx-fifo-resize: + description: Determines if the TX fifos can be dynamically resized depending + on the number of IN endpoints used and if bursting is supported. This + may help improve bandwidth on platforms with higher system latencies, as + increased fifo space allows for the controller to prefetch data into its + internal memory. + type: boolean + + tx-fifo-max-num: + description: Specifies the max number of packets the txfifo resizing logic + can account for when higher endpoint bursting is used. (bMaxBurst > 6) The + higher the number, the more fifo space the txfifo resizing logic will + allocate for that endpoint. + $ref: /schemas/types.yaml#/definitions/uint8 + minimum: 3 + + snps,incr-burst-type-adjustment: + description: + Value for INCR burst type of GSBUSCFG0 register, undefined length INCR + burst type enable and INCRx type. A single value means INCRX burst mode + enabled. If more than one value specified, undefined length INCR burst + type will be enabled with burst lengths utilized up to the maximum + of the values passed in this property. + $ref: /schemas/types.yaml#/definitions/uint32-array + minItems: 1 + maxItems: 8 + uniqueItems: true + items: + enum: [1, 4, 8, 16, 32, 64, 128, 256] + + num-hc-interrupters: + maximum: 8 + default: 1 + + port: + $ref: /schemas/graph.yaml#/properties/port + description: + This port is used with the 'usb-role-switch' property to connect the + dwc3 to type C connector. + + ports: + $ref: /schemas/graph.yaml#/properties/ports + description: + Those ports should be used with any connector to the data bus of this + controller using the OF graph bindings specified if the "usb-role-switch" + property is used. + + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: High Speed (HS) data bus. + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: Super Speed (SS) data bus. + + wakeup-source: + $ref: /schemas/types.yaml#/definitions/flag + description: + Enable USB remote wakeup. + +required: + - compatible + - reg + +additionalProperties: true +... + diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml index 1cd0ca90127d..4380bb6fa2f0 100644 --- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml @@ -15,18 +15,7 @@ description: compatible string. allOf: - - $ref: usb-drd.yaml# - - if: - properties: - dr_mode: - const: peripheral - - required: - - dr_mode - then: - $ref: usb.yaml# - else: - $ref: usb-xhci.yaml# + - $ref: snps,dwc3-common.yaml# properties: compatible: @@ -70,32 +59,9 @@ properties: dma-coherent: true - extcon: - maxItems: 1 - deprecated: true - iommus: maxItems: 1 - usb-phy: - minItems: 1 - items: - - description: USB2/HS PHY - - description: USB3/SS PHY - - phys: - minItems: 1 - maxItems: 19 - - phy-names: - minItems: 1 - maxItems: 19 - oneOf: - - items: - enum: [ usb2-phy, usb3-phy ] - - items: - pattern: "^usb(2-([0-9]|1[0-4])|3-[0-3])$" - power-domains: description: The DWC3 has 2 power-domains. The power management unit (PMU) and @@ -109,361 +75,6 @@ properties: resets: minItems: 1 - snps,usb2-lpm-disable: - description: Indicate if we don't want to enable USB2 HW LPM for host - mode. - type: boolean - - snps,usb3_lpm_capable: - description: Determines if platform is USB3 LPM capable - type: boolean - - snps,usb2-gadget-lpm-disable: - description: Indicate if we don't want to enable USB2 HW LPM for gadget - mode. - type: boolean - - snps,dis-start-transfer-quirk: - description: - When set, disable isoc START TRANSFER command failure SW work-around - for DWC_usb31 version 1.70a-ea06 and prior. - type: boolean - - snps,disable_scramble_quirk: - description: - True when SW should disable data scrambling. Only really useful for FPGA - builds. - type: boolean - - snps,has-lpm-erratum: - description: True when DWC3 was configured with LPM Erratum enabled - type: boolean - - snps,lpm-nyet-threshold: - description: LPM NYET threshold - $ref: /schemas/types.yaml#/definitions/uint8 - - snps,u2exit_lfps_quirk: - description: Set if we want to enable u2exit lfps quirk - type: boolean - - snps,u2ss_inp3_quirk: - description: Set if we enable P3 OK for U2/SS Inactive quirk - type: boolean - - snps,req_p1p2p3_quirk: - description: - When set, the core will always request for P1/P2/P3 transition sequence. - type: boolean - - snps,del_p1p2p3_quirk: - description: - When set core will delay P1/P2/P3 until a certain amount of 8B10B errors - occur. - type: boolean - - snps,del_phy_power_chg_quirk: - description: When set core will delay PHY power change from P0 to P1/P2/P3. - type: boolean - - snps,lfps_filter_quirk: - description: When set core will filter LFPS reception. - type: boolean - - snps,rx_detect_poll_quirk: - description: - when set core will disable a 400us delay to start Polling LFPS after - RX.Detect. - type: boolean - - snps,tx_de_emphasis_quirk: - description: When set core will set Tx de-emphasis value - type: boolean - - snps,tx_de_emphasis: - description: - The value driven to the PHY is controlled by the LTSSM during USB3 - Compliance mode. - $ref: /schemas/types.yaml#/definitions/uint8 - enum: - - 0 # -6dB de-emphasis - - 1 # -3.5dB de-emphasis - - 2 # No de-emphasis - - snps,dis_u3_susphy_quirk: - description: When set core will disable USB3 suspend phy - type: boolean - - snps,dis_u2_susphy_quirk: - description: When set core will disable USB2 suspend phy - type: boolean - - snps,dis_enblslpm_quirk: - description: - When set clears the enblslpm in GUSB2PHYCFG, disabling the suspend signal - to the PHY. - type: boolean - - snps,dis-u1-entry-quirk: - description: Set if link entering into U1 needs to be disabled - type: boolean - - snps,dis-u2-entry-quirk: - description: Set if link entering into U2 needs to be disabled - type: boolean - - snps,dis_rxdet_inp3_quirk: - description: - When set core will disable receiver detection in PHY P3 power state. - type: boolean - - snps,dis-u2-freeclk-exists-quirk: - description: - When set, clear the u2_freeclk_exists in GUSB2PHYCFG, specify that USB2 - PHY doesn't provide a free-running PHY clock. - type: boolean - - snps,dis-del-phy-power-chg-quirk: - description: - When set core will change PHY power from P0 to P1/P2/P3 without delay. - type: boolean - - snps,dis-tx-ipgap-linecheck-quirk: - description: When set, disable u2mac linestate check during HS transmit - type: boolean - - snps,parkmode-disable-ss-quirk: - description: - When set, all SuperSpeed bus instances in park mode are disabled. - type: boolean - - snps,parkmode-disable-hs-quirk: - description: - When set, all HighSpeed bus instances in park mode are disabled. - type: boolean - - snps,dis_metastability_quirk: - description: - When set, disable metastability workaround. CAUTION! Use only if you are - absolutely sure of it. - type: boolean - - snps,dis-split-quirk: - description: - When set, change the way URBs are handled by the driver. Needed to - avoid -EPROTO errors with usbhid on some devices (Hikey 970). - type: boolean - - snps,gfladj-refclk-lpm-sel-quirk: - description: - When set, run the SOF/ITP counter based on ref_clk. - type: boolean - - snps,resume-hs-terminations: - description: - Fix the issue of HS terminations CRC error on resume by enabling this - quirk. When set, all the termsel, xcvrsel, opmode becomes 0 during end - of resume. This option is to support certain legacy ULPI PHYs. - type: boolean - - snps,ulpi-ext-vbus-drv: - description: - Some ULPI USB PHY does not support internal VBUS supply, and driving - the CPEN pin, requires the configuration of the ulpi DRVVBUSEXTERNAL - bit. When set, the xhci host will configure the USB2 PHY drives VBUS - with an external supply. - type: boolean - - snps,is-utmi-l1-suspend: - description: - True when DWC3 asserts output signal utmi_l1_suspend_n, false when - asserts utmi_sleep_n. - type: boolean - - snps,hird-threshold: - description: HIRD threshold - $ref: /schemas/types.yaml#/definitions/uint8 - - snps,hsphy_interface: - description: - High-Speed PHY interface selection between UTMI+ and ULPI when the - DWC_USB3_HSPHY_INTERFACE has value 3. - $ref: /schemas/types.yaml#/definitions/string - enum: [utmi, ulpi] - - snps,quirk-frame-length-adjustment: - description: - Value for GFLADJ_30MHZ field of GFLADJ register for post-silicon frame - length adjustment when the fladj_30mhz_sdbnd signal is invalid or - incorrect. - $ref: /schemas/types.yaml#/definitions/uint32 - minimum: 0 - maximum: 0x3f - - snps,ref-clock-period-ns: - description: - Value for REFCLKPER field of GUCTL register for reference clock period in - nanoseconds, when the hardware set default does not match the actual - clock. - - This binding is deprecated. Instead, provide an appropriate reference clock. - minimum: 8 - maximum: 62 - deprecated: true - - snps,rx-thr-num-pkt: - description: - USB RX packet threshold count. In host mode, this field specifies - the space that must be available in the RX FIFO before the core can - start the corresponding USB RX transaction (burst). - In device mode, this field specifies the space that must be - available in the RX FIFO before the core can send ERDY for a - flow-controlled endpoint. It is only used for SuperSpeed. - The valid values for this field are from 1 to 15. (DWC3 SuperSpeed - USB 3.0 Controller Databook) - $ref: /schemas/types.yaml#/definitions/uint8 - minimum: 1 - maximum: 15 - - snps,rx-max-burst: - description: - Max USB RX burst size. In host mode, this field specifies the - Maximum Bulk IN burst the DWC_usb3 core can perform. When the system - bus is slower than the USB, RX FIFO can overrun during a long burst. - You can program a smaller value to this field to limit the RX burst - size that the core can perform. It only applies to SS Bulk, - Isochronous, and Interrupt IN endpoints in the host mode. - In device mode, this field specifies the NUMP value that is sent in - ERDY for an OUT endpoint. - The valid values for this field are from 1 to 16. (DWC3 SuperSpeed - USB 3.0 Controller Databook) - $ref: /schemas/types.yaml#/definitions/uint8 - minimum: 1 - maximum: 16 - - snps,tx-thr-num-pkt: - description: - USB TX packet threshold count. This field specifies the number of - packets that must be in the TXFIFO before the core can start - transmission for the corresponding USB transaction (burst). - This count is valid in both host and device modes. It is only used - for SuperSpeed operation. - Valid values are from 1 to 15. (DWC3 SuperSpeed USB 3.0 Controller - Databook) - $ref: /schemas/types.yaml#/definitions/uint8 - minimum: 1 - maximum: 15 - - snps,tx-max-burst: - description: - Max USB TX burst size. When the system bus is slower than the USB, - TX FIFO can underrun during a long burst. Program a smaller value - to this field to limit the TX burst size that the core can execute. - In Host mode, it only applies to SS Bulk, Isochronous, and Interrupt - OUT endpoints. This value is not used in device mode. - Valid values are from 1 to 16. (DWC3 SuperSpeed USB 3.0 Controller - Databook) - $ref: /schemas/types.yaml#/definitions/uint8 - minimum: 1 - maximum: 16 - - snps,rx-thr-num-pkt-prd: - description: - Periodic ESS RX packet threshold count (host mode only). Set this and - snps,rx-max-burst-prd to a valid, non-zero value 1-16 (DWC_usb31 - programming guide section 1.2.4) to enable periodic ESS RX threshold. - $ref: /schemas/types.yaml#/definitions/uint8 - minimum: 1 - maximum: 16 - - snps,rx-max-burst-prd: - description: - Max periodic ESS RX burst size (host mode only). Set this and - snps,rx-thr-num-pkt-prd to a valid, non-zero value 1-16 (DWC_usb31 - programming guide section 1.2.4) to enable periodic ESS RX threshold. - $ref: /schemas/types.yaml#/definitions/uint8 - minimum: 1 - maximum: 16 - - snps,tx-thr-num-pkt-prd: - description: - Periodic ESS TX packet threshold count (host mode only). Set this and - snps,tx-max-burst-prd to a valid, non-zero value 1-16 (DWC_usb31 - programming guide section 1.2.3) to enable periodic ESS TX threshold. - $ref: /schemas/types.yaml#/definitions/uint8 - minimum: 1 - maximum: 16 - - snps,tx-max-burst-prd: - description: - Max periodic ESS TX burst size (host mode only). Set this and - snps,tx-thr-num-pkt-prd to a valid, non-zero value 1-16 (DWC_usb31 - programming guide section 1.2.3) to enable periodic ESS TX threshold. - $ref: /schemas/types.yaml#/definitions/uint8 - minimum: 1 - maximum: 16 - - tx-fifo-resize: - description: Determines if the TX fifos can be dynamically resized depending - on the number of IN endpoints used and if bursting is supported. This - may help improve bandwidth on platforms with higher system latencies, as - increased fifo space allows for the controller to prefetch data into its - internal memory. - type: boolean - - tx-fifo-max-num: - description: Specifies the max number of packets the txfifo resizing logic - can account for when higher endpoint bursting is used. (bMaxBurst > 6) The - higher the number, the more fifo space the txfifo resizing logic will - allocate for that endpoint. - $ref: /schemas/types.yaml#/definitions/uint8 - minimum: 3 - - snps,incr-burst-type-adjustment: - description: - Value for INCR burst type of GSBUSCFG0 register, undefined length INCR - burst type enable and INCRx type. A single value means INCRX burst mode - enabled. If more than one value specified, undefined length INCR burst - type will be enabled with burst lengths utilized up to the maximum - of the values passed in this property. - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 1 - maxItems: 8 - uniqueItems: true - items: - enum: [1, 4, 8, 16, 32, 64, 128, 256] - - num-hc-interrupters: - maximum: 8 - default: 1 - - port: - $ref: /schemas/graph.yaml#/properties/port - description: - This port is used with the 'usb-role-switch' property to connect the - dwc3 to type C connector. - - ports: - $ref: /schemas/graph.yaml#/properties/ports - description: - Those ports should be used with any connector to the data bus of this - controller using the OF graph bindings specified if the "usb-role-switch" - property is used. - - properties: - port@0: - $ref: /schemas/graph.yaml#/properties/port - description: High Speed (HS) data bus. - - port@1: - $ref: /schemas/graph.yaml#/properties/port - description: Super Speed (SS) data bus. - - wakeup-source: - $ref: /schemas/types.yaml#/definitions/flag - description: - Enable USB remote wakeup. - unevaluatedProperties: false required: diff --git a/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml b/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml index 54c6586cb56d..bec1c8047bc0 100644 --- a/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml +++ b/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml @@ -56,26 +56,26 @@ examples: #size-cells = <0>; hd3ss3220@47 { - compatible = "ti,hd3ss3220"; - reg = <0x47>; - interrupt-parent = <&gpio6>; - interrupts = <3>; + compatible = "ti,hd3ss3220"; + reg = <0x47>; + interrupt-parent = <&gpio6>; + interrupts = <3>; - ports { - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; - hd3ss3220_in_ep: endpoint { - remote-endpoint = <&ss_ep>; - }; - }; - port@1 { - reg = <1>; - hd3ss3220_out_ep: endpoint { - remote-endpoint = <&usb3_role_switch>; - }; - }; + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + hd3ss3220_in_ep: endpoint { + remote-endpoint = <&ss_ep>; + }; }; + port@1 { + reg = <1>; + hd3ss3220_out_ep: endpoint { + remote-endpoint = <&usb3_role_switch>; + }; + }; + }; }; }; diff --git a/Documentation/devicetree/bindings/usb/ti,tusb73x0-pci.yaml b/Documentation/devicetree/bindings/usb/ti,tusb73x0-pci.yaml index ddda734f36fb..c4a91b3d6612 100644 --- a/Documentation/devicetree/bindings/usb/ti,tusb73x0-pci.yaml +++ b/Documentation/devicetree/bindings/usb/ti,tusb73x0-pci.yaml @@ -48,8 +48,8 @@ examples: device_type = "pci"; usb@0 { - compatible = "pci104c,8241"; - reg = <0x0 0x0 0x0 0x0 0x0>; - ti,pwron-active-high; + compatible = "pci104c,8241"; + reg = <0x0 0x0 0x0 0x0 0x0>; + ti,pwron-active-high; }; }; diff --git a/Documentation/devicetree/bindings/usb/ti,usb8020b.yaml b/Documentation/devicetree/bindings/usb/ti,usb8020b.yaml index 8ef117793e11..61217da8b2f3 100644 --- a/Documentation/devicetree/bindings/usb/ti,usb8020b.yaml +++ b/Documentation/devicetree/bindings/usb/ti,usb8020b.yaml @@ -51,19 +51,19 @@ examples: /* 2.0 hub on port 1 */ hub_2_0: hub@1 { - compatible = "usb451,8027"; - reg = <1>; - peer-hub = <&hub_3_0>; - reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>; - vdd-supply = <&usb_hub_fixed_3v3>; + compatible = "usb451,8027"; + reg = <1>; + peer-hub = <&hub_3_0>; + reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>; + vdd-supply = <&usb_hub_fixed_3v3>; }; /* 3.0 hub on port 2 */ hub_3_0: hub@2 { - compatible = "usb451,8025"; - reg = <2>; - peer-hub = <&hub_2_0>; - reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>; - vdd-supply = <&usb_hub_fixed_3v3>; + compatible = "usb451,8025"; + reg = <2>; + peer-hub = <&hub_2_0>; + reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>; + vdd-supply = <&usb_hub_fixed_3v3>; }; }; diff --git a/Documentation/devicetree/bindings/usb/ti,usb8041.yaml b/Documentation/devicetree/bindings/usb/ti,usb8041.yaml index c2e29bd61e11..bce730a5e237 100644 --- a/Documentation/devicetree/bindings/usb/ti,usb8041.yaml +++ b/Documentation/devicetree/bindings/usb/ti,usb8041.yaml @@ -51,17 +51,17 @@ examples: /* 2.0 hub on port 1 */ hub_2_0: hub@1 { - compatible = "usb451,8142"; - reg = <1>; - peer-hub = <&hub_3_0>; - reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; + compatible = "usb451,8142"; + reg = <1>; + peer-hub = <&hub_3_0>; + reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; }; /* 3.0 hub on port 2 */ hub_3_0: hub@2 { - compatible = "usb451,8140"; - reg = <2>; - peer-hub = <&hub_2_0>; - reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; + compatible = "usb451,8140"; + reg = <2>; + peer-hub = <&hub_2_0>; + reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; }; }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index da01616802c7..5079ca6ce1d1 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -218,6 +218,8 @@ patternProperties: description: Shenzhen BigTree Tech Co., LTD "^bitmain,.*": description: Bitmain Technologies + "^blaize,.*": + description: Blaize, Inc. "^blutek,.*": description: BluTek Power "^boe,.*": @@ -575,6 +577,8 @@ patternProperties: description: Gemtek Technology Co., Ltd. "^genesys,.*": description: Genesys Logic, Inc. + "^genexis,.*": + description: Genexis BV/AB "^geniatech,.*": description: Geniatech, Inc. "^giantec,.*": @@ -1204,6 +1208,8 @@ patternProperties: description: PulsedLight, Inc "^purism,.*": description: Purism, SPC + "^puya,.*": + description: Puya Semiconductor (Shanghai) Co., Ltd. "^qca,.*": description: Qualcomm Atheros, Inc. "^qcom,.*": @@ -1336,6 +1342,8 @@ patternProperties: description: Siemens AG "^sifive,.*": description: SiFive, Inc. + "^siflower,.*": + description: Shanghai Siflower Communication Co. "^sigma,.*": description: Sigma Designs, Inc. "^sii,.*": @@ -1524,6 +1532,8 @@ patternProperties: description: Topeet "^topic,.*": description: Topic Embedded Systems + "^topland,.*": + description: Topland Electronics (H.K) Co., Ltd. "^toppoly,.*": description: TPO (deprecated, use tpo) deprecated: true diff --git a/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml b/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml index 422becc6e1fa..fe6b3f9a3f8b 100644 --- a/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml +++ b/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml @@ -25,6 +25,8 @@ properties: reg: maxItems: 1 + vcc-supply: true + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml index 34896a39fa91..49e2b807db0b 100644 --- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml @@ -20,6 +20,7 @@ properties: - qcom,kpss-wdt-ipq4019 - qcom,apss-wdt-ipq5018 - qcom,apss-wdt-ipq5332 + - qcom,apss-wdt-ipq5424 - qcom,apss-wdt-ipq9574 - qcom,apss-wdt-msm8226 - qcom,apss-wdt-msm8974 diff --git a/Documentation/devicetree/of_unittest.rst b/Documentation/devicetree/of_unittest.rst index 8864b52d1195..a6c05962add3 100644 --- a/Documentation/devicetree/of_unittest.rst +++ b/Documentation/devicetree/of_unittest.rst @@ -50,15 +50,13 @@ from 'scripts/dtc/of_unittest_expect --help'. The Device Tree Source file (drivers/of/unittest-data/testcases.dts) contains the test data required for executing the unit tests automated in -drivers/of/unittest.c. Currently, following Device Tree Source Include files -(.dtsi) are included in testcases.dts:: +drivers/of/unittest.c. See the content of the folder:: - drivers/of/unittest-data/tests-interrupts.dtsi - drivers/of/unittest-data/tests-platform.dtsi - drivers/of/unittest-data/tests-phandle.dtsi - drivers/of/unittest-data/tests-match.dtsi + drivers/of/unittest-data/tests-*.dtsi -When the kernel is build with OF_SELFTEST enabled, then the following make +for the Device Tree Source Include files (.dtsi) included in testcases.dts. + +When the kernel is build with CONFIG_OF_UNITTEST enabled, then the following make rule:: $(obj)/%.dtb: $(src)/%.dts FORCE diff --git a/Documentation/driver-api/crypto/iaa/iaa-crypto.rst b/Documentation/driver-api/crypto/iaa/iaa-crypto.rst index bba40158dd5c..8e50b900d51c 100644 --- a/Documentation/driver-api/crypto/iaa/iaa-crypto.rst +++ b/Documentation/driver-api/crypto/iaa/iaa-crypto.rst @@ -272,7 +272,7 @@ The available attributes are: echo async_irq > /sys/bus/dsa/drivers/crypto/sync_mode Async mode without interrupts (caller must poll) can be enabled by - writing 'async' to it:: + writing 'async' to it (please see Caveat):: echo async > /sys/bus/dsa/drivers/crypto/sync_mode @@ -283,6 +283,13 @@ The available attributes are: The default mode is 'sync'. + Caveat: since the only mechanism that iaa_crypto currently implements + for async polling without interrupts is via the 'sync' mode as + described earlier, writing 'async' to + '/sys/bus/dsa/drivers/crypto/sync_mode' will internally enable the + 'sync' mode. This is to ensure correct iaa_crypto behavior until true + async polling without interrupts is enabled in iaa_crypto. + .. _iaa_default_config: IAA Default Configuration diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst index d594d0ea0e9d..d75728eb05f8 100644 --- a/Documentation/driver-api/driver-model/devres.rst +++ b/Documentation/driver-api/driver-model/devres.rst @@ -404,7 +404,6 @@ PHY devm_usb_get_phy() devm_usb_get_phy_by_node() devm_usb_get_phy_by_phandle() - devm_usb_put_phy() PINCTRL devm_pinctrl_get() diff --git a/Documentation/driver-api/extcon.rst b/Documentation/driver-api/extcon.rst new file mode 100644 index 000000000000..d3217b9cdcd5 --- /dev/null +++ b/Documentation/driver-api/extcon.rst @@ -0,0 +1,255 @@ +======================= +Extcon Device Subsystem +======================= + +Overview +======== + +The Extcon (External Connector) subsystem provides a unified framework for +managing external connectors in Linux systems. It allows drivers to report +the state of external connectors and provides a standardized interface for +userspace to query and monitor these states. + +Extcon is particularly useful in modern devices with multiple connectivity +options, such as smartphones, tablets, and laptops. It helps manage various +types of connectors, including: + +1. USB connectors (e.g., USB-C, micro-USB) +2. Charging ports (e.g., fast charging, wireless charging) +3. Audio jacks (e.g., 3.5mm headphone jack) +4. Video outputs (e.g., HDMI, DisplayPort) +5. Docking stations + +Real-world examples: + +1. Smartphone USB-C port: + A single USB-C port on a smartphone can serve multiple functions. Extcon + can manage the different states of this port, such as: + - USB data connection + - Charging (various types like fast charging, USB Power Delivery) + - Audio output (USB-C headphones) + - Video output (USB-C to HDMI adapter) + +2. Laptop docking station: + When a laptop is connected to a docking station, multiple connections are + made simultaneously. Extcon can handle the state changes for: + - Power delivery + - External displays + - USB hub connections + - Ethernet connectivity + +3. Wireless charging pad: + Extcon can manage the state of a wireless charging connection, allowing + the system to respond appropriately when a device is placed on or removed + from the charging pad. + +4. Smart TV HDMI ports: + In a smart TV, Extcon can manage multiple HDMI ports, detecting when + devices are connected or disconnected, and potentially identifying the + type of device (e.g., gaming console, set-top box, Blu-ray player). + +The Extcon framework simplifies the development of drivers for these complex +scenarios by providing a standardized way to report and query connector +states, handle mutually exclusive connections, and manage connector +properties. This allows for more robust and flexible handling of external +connections in modern devices. + +Key Components +============== + +extcon_dev +---------- + +The core structure representing an Extcon device:: + + struct extcon_dev { + const char *name; + const unsigned int *supported_cable; + const u32 *mutually_exclusive; + + /* Internal data */ + struct device dev; + unsigned int id; + struct raw_notifier_head nh_all; + struct raw_notifier_head *nh; + struct list_head entry; + int max_supported; + spinlock_t lock; + u32 state; + + /* Sysfs related */ + struct device_type extcon_dev_type; + struct extcon_cable *cables; + struct attribute_group attr_g_muex; + struct attribute **attrs_muex; + struct device_attribute *d_attrs_muex; + }; + +Key fields: + +- ``name``: Name of the Extcon device +- ``supported_cable``: Array of supported cable types +- ``mutually_exclusive``: Array defining mutually exclusive cable types + This field is crucial for enforcing hardware constraints. It's an array of + 32-bit unsigned integers, where each element represents a set of mutually + exclusive cable types. The array should be terminated with a 0. + + For example: + + :: + + static const u32 mutually_exclusive[] = { + BIT(0) | BIT(1), /* Cable 0 and 1 are mutually exclusive */ + BIT(2) | BIT(3) | BIT(4), /* Cables 2, 3, and 4 are mutually exclusive */ + 0 /* Terminator */ + }; + + In this example, cables 0 and 1 cannot be connected simultaneously, and + cables 2, 3, and 4 are also mutually exclusive. This is useful for + scenarios like a single port that can either be USB or HDMI, but not both + at the same time. + + The Extcon core uses this information to prevent invalid combinations of + cable states, ensuring that the reported states are always consistent + with the hardware capabilities. + +- ``state``: Current state of the device (bitmap of connected cables) + + +extcon_cable +------------ + +Represents an individual cable managed by an Extcon device:: + + struct extcon_cable { + struct extcon_dev *edev; + int cable_index; + struct attribute_group attr_g; + struct device_attribute attr_name; + struct device_attribute attr_state; + struct attribute *attrs[3]; + union extcon_property_value usb_propval[EXTCON_PROP_USB_CNT]; + union extcon_property_value chg_propval[EXTCON_PROP_CHG_CNT]; + union extcon_property_value jack_propval[EXTCON_PROP_JACK_CNT]; + union extcon_property_value disp_propval[EXTCON_PROP_DISP_CNT]; + DECLARE_BITMAP(usb_bits, EXTCON_PROP_USB_CNT); + DECLARE_BITMAP(chg_bits, EXTCON_PROP_CHG_CNT); + DECLARE_BITMAP(jack_bits, EXTCON_PROP_JACK_CNT); + DECLARE_BITMAP(disp_bits, EXTCON_PROP_DISP_CNT); + }; + +Core Functions +============== + +.. kernel-doc:: drivers/extcon/extcon.c + :identifiers: extcon_get_state + +.. kernel-doc:: drivers/extcon/extcon.c + :identifiers: extcon_set_state + +.. kernel-doc:: drivers/extcon/extcon.c + :identifiers: extcon_set_state_sync + +.. kernel-doc:: drivers/extcon/extcon.c + :identifiers: extcon_get_property + + +Sysfs Interface +=============== + +Extcon devices expose the following sysfs attributes: + +- ``name``: Name of the Extcon device +- ``state``: Current state of all supported cables +- ``cable.N/name``: Name of the Nth supported cable +- ``cable.N/state``: State of the Nth supported cable + +Usage Example +------------- + +.. code-block:: c + + #include + #include + #include + + struct my_extcon_data { + struct extcon_dev *edev; + struct device *dev; + }; + + static const unsigned int my_extcon_cable[] = { + EXTCON_USB, + EXTCON_USB_HOST, + EXTCON_NONE, + }; + + static int my_extcon_probe(struct platform_device *pdev) + { + struct my_extcon_data *data; + int ret; + + data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->dev = &pdev->dev; + + /* Initialize extcon device */ + data->edev = devm_extcon_dev_allocate(data->dev, my_extcon_cable); + if (IS_ERR(data->edev)) { + dev_err(data->dev, "Failed to allocate extcon device\n"); + return PTR_ERR(data->edev); + } + + /* Register extcon device */ + ret = devm_extcon_dev_register(data->dev, data->edev); + if (ret < 0) { + dev_err(data->dev, "Failed to register extcon device\n"); + return ret; + } + + platform_set_drvdata(pdev, data); + + /* Example: Set initial state */ + extcon_set_state_sync(data->edev, EXTCON_USB, true); + + dev_info(data->dev, "My extcon driver probed successfully\n"); + return 0; + } + + static int my_extcon_remove(struct platform_device *pdev) + { + struct my_extcon_data *data = platform_get_drvdata(pdev); + + /* Example: Clear state before removal */ + extcon_set_state_sync(data->edev, EXTCON_USB, false); + + dev_info(data->dev, "My extcon driver removed\n"); + return 0; + } + + static const struct of_device_id my_extcon_of_match[] = { + { .compatible = "my,extcon-device", }, + { }, + }; + MODULE_DEVICE_TABLE(of, my_extcon_of_match); + + static struct platform_driver my_extcon_driver = { + .driver = { + .name = "my-extcon-driver", + .of_match_table = my_extcon_of_match, + }, + .probe = my_extcon_probe, + .remove = my_extcon_remove, + }; + + module_platform_driver(my_extcon_driver); + +This example demonstrates: +--------------------------- + +- Defining supported cable types (USB and USB Host in this case). +- Allocating and registering an extcon device. +- Setting an initial state for a cable (USB connected in this example). +- Clearing the state when the driver is removed. diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index 7f83e05769b4..16e2c4ec3c01 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -86,6 +86,7 @@ Subsystem-specific APIs dmaengine/index dpll edac + extcon firmware/index fpga/index frame-buffer diff --git a/Documentation/driver-api/media/tx-rx.rst b/Documentation/driver-api/media/tx-rx.rst index dd09484df1d3..c71003f74b1c 100644 --- a/Documentation/driver-api/media/tx-rx.rst +++ b/Documentation/driver-api/media/tx-rx.rst @@ -50,7 +50,7 @@ The :ref:`V4L2_CID_LINK_FREQ ` control is used to tell the receiver the frequency of the bus (i.e. it is not the same as the symbol rate). ``.enable_streams()`` and ``.disable_streams()`` callbacks -^^^^^^^^^^^^^^^^^^^^^^^^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The struct v4l2_subdev_pad_ops->enable_streams() and struct v4l2_subdev_pad_ops->disable_streams() callbacks are used by the receiver driver @@ -79,14 +79,15 @@ where * - link_freq - The value of the ``V4L2_CID_LINK_FREQ`` integer64 menu item. * - nr_of_lanes - - Number of data lanes used on the CSI-2 link. This can - be obtained from the OF endpoint configuration. + - Number of data lanes used on the CSI-2 link. * - 2 - Data is transferred on both rising and falling edge of the signal. * - bits_per_sample - Number of bits per sample. * - k - - 16 for D-PHY and 7 for C-PHY + - 16 for D-PHY and 7 for C-PHY. + +Information on whether D-PHY or C-PHY is used, and the value of ``nr_of_lanes``, can be obtained from the OF endpoint configuration. .. note:: diff --git a/Documentation/driver-api/pps.rst b/Documentation/driver-api/pps.rst index 78dded03e5d8..71ad04c82d6c 100644 --- a/Documentation/driver-api/pps.rst +++ b/Documentation/driver-api/pps.rst @@ -202,6 +202,46 @@ Sometimes one needs to be able not only to catch PPS signals but to produce them also. For example, running a distributed simulation, which requires computers' clock to be synchronized very tightly. +To do so the class pps-gen has been added. PPS generators can be +registered in the kernel by defining a struct pps_gen_source_info as +follows:: + + static struct pps_gen_source_info pps_gen_dummy_info = { + .name = "dummy", + .use_system_clock = true, + .get_time = pps_gen_dummy_get_time, + .enable = pps_gen_dummy_enable, + }; + +Where the use_system_clock states if the generator uses the system +clock to generate its pulses, or they are from a peripheral device +clock. Method get_time() is used to query the time stored into the +generator clock, while the method enable() is used to enable or +disable the PPS pulse generation. + +Then calling the function pps_gen_register_source() in your +initialization routine as follows creates a new generator in the +system:: + + pps_gen = pps_gen_register_source(&pps_gen_dummy_info); + +Generators SYSFS support +------------------------ + +If the SYSFS filesystem is enabled in the kernel it provides a new class:: + + $ ls /sys/class/pps-gen/ + pps-gen0/ pps-gen1/ pps-gen2/ + +Every directory is the ID of a PPS generator defined in the system and +inside of it you find several files:: + + $ ls -F /sys/class/pps-gen/pps-gen0/ + dev enable name power/ subsystem@ system time uevent + +To enable the PPS signal generation you can use the command below:: + + $ echo 1 > /sys/class/pps-gen/pps-gen0/enable Parallel port generator ------------------------ diff --git a/Documentation/driver-api/scsi.rst b/Documentation/driver-api/scsi.rst index 273281474c09..bf2be96cc2d6 100644 --- a/Documentation/driver-api/scsi.rst +++ b/Documentation/driver-api/scsi.rst @@ -126,7 +126,7 @@ Manage scsi_dev_info_list, which tracks blacklisted and whitelisted devices. .. kernel-doc:: drivers/scsi/scsi_devinfo.c - :internal: + :export: drivers/scsi/scsi_ioctl.c ~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -162,7 +162,6 @@ statistics and to pass information directly to the lowlevel driver. I.E. plumbing to manage /proc/scsi/\* .. kernel-doc:: drivers/scsi/scsi_proc.c - :internal: drivers/scsi/scsi_netlink.c ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -193,7 +192,7 @@ else, sequentially scan LUNs up until some maximum is reached, or a LUN is seen that cannot have a device attached to it. .. kernel-doc:: drivers/scsi/scsi_scan.c - :internal: + :export: drivers/scsi/scsi_sysctl.c ~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/filesystems/bcachefs/CodingStyle.rst b/Documentation/filesystems/bcachefs/CodingStyle.rst index 01de555e21d8..b29562a6bf55 100644 --- a/Documentation/filesystems/bcachefs/CodingStyle.rst +++ b/Documentation/filesystems/bcachefs/CodingStyle.rst @@ -183,4 +183,4 @@ even better as a code comment. A good code comment is wonderful, but even better is the comment that didn't need to exist because the code was so straightforward as to be obvious; organized into small clean and tidy modules, with clear and descriptive names -for functions and variable, where every line of code has a clear purpose. +for functions and variables, where every line of code has a clear purpose. diff --git a/Documentation/filesystems/debugfs.rst b/Documentation/filesystems/debugfs.rst index dc35da8b8792..f7f977ffbf8d 100644 --- a/Documentation/filesystems/debugfs.rst +++ b/Documentation/filesystems/debugfs.rst @@ -211,18 +211,16 @@ seq_file content. There are a couple of other directory-oriented helper functions:: - struct dentry *debugfs_rename(struct dentry *old_dir, - struct dentry *old_dentry, - struct dentry *new_dir, - const char *new_name); + struct dentry *debugfs_change_name(struct dentry *dentry, + const char *fmt, ...); struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *target); -A call to debugfs_rename() will give a new name to an existing debugfs -file, possibly in a different directory. The new_name must not exist prior -to the call; the return value is old_dentry with updated information. +A call to debugfs_change_name() will give a new name to an existing debugfs +file, always in the same directory. The new_name must not exist prior +to the call; the return value is 0 on success and -E... on failuer. Symbolic links can be created with debugfs_create_symlink(). There is one important thing that all debugfs users must take into account: diff --git a/Documentation/filesystems/fiemap.rst b/Documentation/filesystems/fiemap.rst index 93fc96f760aa..23b3ed229e49 100644 --- a/Documentation/filesystems/fiemap.rst +++ b/Documentation/filesystems/fiemap.rst @@ -12,21 +12,10 @@ returns a list of extents. Request Basics -------------- -A fiemap request is encoded within struct fiemap:: - - struct fiemap { - __u64 fm_start; /* logical offset (inclusive) at - * which to start mapping (in) */ - __u64 fm_length; /* logical length of mapping which - * userspace cares about (in) */ - __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */ - __u32 fm_mapped_extents; /* number of extents that were - * mapped (out) */ - __u32 fm_extent_count; /* size of fm_extents array (in) */ - __u32 fm_reserved; - struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ - }; +A fiemap request is encoded within struct fiemap: +.. kernel-doc:: include/uapi/linux/fiemap.h + :identifiers: fiemap fm_start, and fm_length specify the logical range within the file which the process would like mappings for. Extents returned mirror @@ -60,6 +49,8 @@ FIEMAP_FLAG_XATTR If this flag is set, the extents returned will describe the inodes extended attribute lookup tree, instead of its data tree. +FIEMAP_FLAG_CACHE + This flag requests caching of the extents. Extent Mapping -------------- @@ -77,18 +68,10 @@ complete the requested range and will not have the FIEMAP_EXTENT_LAST flag set (see the next section on extent flags). Each extent is described by a single fiemap_extent structure as -returned in fm_extents:: +returned in fm_extents: - struct fiemap_extent { - __u64 fe_logical; /* logical offset in bytes for the start of - * the extent */ - __u64 fe_physical; /* physical offset in bytes for the start - * of the extent */ - __u64 fe_length; /* length in bytes for the extent */ - __u64 fe_reserved64[2]; - __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */ - __u32 fe_reserved[3]; - }; +.. kernel-doc:: include/uapi/linux/fiemap.h + :identifiers: fiemap_extent All offsets and lengths are in bytes and mirror those on disk. It is valid for an extents logical offset to start before the request or its logical @@ -175,6 +158,8 @@ FIEMAP_EXTENT_MERGED userspace would be highly inefficient, the kernel will try to merge most adjacent blocks into 'extents'. +FIEMAP_EXTENT_SHARED + This flag is set to request that space be shared with other files. VFS -> File System Implementation --------------------------------- @@ -191,14 +176,10 @@ each discovered extent:: u64 len); ->fiemap is passed struct fiemap_extent_info which describes the -fiemap request:: +fiemap request: - struct fiemap_extent_info { - unsigned int fi_flags; /* Flags as passed from user */ - unsigned int fi_extents_mapped; /* Number of mapped extents */ - unsigned int fi_extents_max; /* Size of fiemap_extent array */ - struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */ - }; +.. kernel-doc:: include/linux/fiemap.h + :identifiers: fiemap_extent_info It is intended that the file system should not need to access any of this structure directly. Filesystem handlers should be tolerant to signals and return diff --git a/Documentation/filesystems/fuse-io-uring.rst b/Documentation/filesystems/fuse-io-uring.rst new file mode 100644 index 000000000000..d73dd0dbd238 --- /dev/null +++ b/Documentation/filesystems/fuse-io-uring.rst @@ -0,0 +1,99 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================= +FUSE-over-io-uring design documentation +======================================= + +This documentation covers basic details how the fuse +kernel/userspace communication through io-uring is configured +and works. For generic details about FUSE see fuse.rst. + +This document also covers the current interface, which is +still in development and might change. + +Limitations +=========== +As of now not all requests types are supported through io-uring, userspace +is required to also handle requests through /dev/fuse after io-uring setup +is complete. Specifically notifications (initiated from the daemon side) +and interrupts. + +Fuse io-uring configuration +=========================== + +Fuse kernel requests are queued through the classical /dev/fuse +read/write interface - until io-uring setup is complete. + +In order to set up fuse-over-io-uring fuse-server (user-space) +needs to submit SQEs (opcode = IORING_OP_URING_CMD) to the /dev/fuse +connection file descriptor. Initial submit is with the sub command +FUSE_URING_REQ_REGISTER, which will just register entries to be +available in the kernel. + +Once at least one entry per queue is submitted, kernel starts +to enqueue to ring queues. +Note, every CPU core has its own fuse-io-uring queue. +Userspace handles the CQE/fuse-request and submits the result as +subcommand FUSE_URING_REQ_COMMIT_AND_FETCH - kernel completes +the requests and also marks the entry available again. If there are +pending requests waiting the request will be immediately submitted +to the daemon again. + +Initial SQE +-----------:: + + | | FUSE filesystem daemon + | | + | | >io_uring_submit() + | | IORING_OP_URING_CMD / + | | FUSE_URING_CMD_REGISTER + | | [wait cqe] + | | >io_uring_wait_cqe() or + | | >io_uring_submit_and_wait() + | | + | >fuse_uring_cmd() | + | >fuse_uring_register() | + + +Sending requests with CQEs +--------------------------:: + + | | FUSE filesystem daemon + | | [waiting for CQEs] + | "rm /mnt/fuse/file" | + | | + | >sys_unlink() | + | >fuse_unlink() | + | [allocate request] | + | >fuse_send_one() | + | ... | + | >fuse_uring_queue_fuse_req | + | [queue request on fg queue] | + | >fuse_uring_add_req_to_ring_ent() | + | ... | + | >fuse_uring_copy_to_ring() | + | >io_uring_cmd_done() | + | >request_wait_answer() | + | [sleep on req->waitq] | + | | [receives and handles CQE] + | | [submit result and fetch next] + | | >io_uring_submit() + | | IORING_OP_URING_CMD/ + | | FUSE_URING_CMD_COMMIT_AND_FETCH + | >fuse_uring_cmd() | + | >fuse_uring_commit_fetch() | + | >fuse_uring_commit() | + | >fuse_uring_copy_from_ring() | + | [ copy the result to the fuse req] | + | >fuse_uring_req_end() | + | >fuse_request_end() | + | [wake up req->waitq] | + | >fuse_uring_next_fuse_req | + | [wait or handle next req] | + | | + | [req->waitq woken up] | + | net pointers - (which are needed to find the per-cpu-refcount for the nfsd_serv). - - Details: - - - Embed nfs_uuid_t in nfs_client. nfs_uuid_t provides a list_head - that can be used to find the client. It does add the 16-byte - uuid_t to nfs_client so it is bigger than needed (given that - uuid_t is only used during the initial NFS client and server - LOCALIO handshake to determine if they are local to each other). - If that is really a problem we can find a fix. - - - When the nfs server confirms that the uuid_t is local, it moves - the nfs_uuid_t onto a per-net-ns list in NFSD's nfsd_net. - - - When each server's net-ns is shutting down - in a "pre_exit" - handler, all these nfs_uuid_t have their ->net cleared. There is - an rcu_synchronize() call between pre_exit() handlers and exit() - handlers so any caller that sees nfs_uuid_t ->net as not NULL can - safely manage the per-cpu-refcount for nfsd_serv. - - - The client's nfs_uuid_t is passed to nfsd_open_local_fh() so it - can safely dereference ->net in a private rcu_read_lock() section - to allow safe access to the associated nfsd_net and nfsd_serv. - -So LOCALIO required the introduction and use of NFSD's percpu_ref to -interlock nfsd_destroy_serv() and nfsd_open_local_fh(), to ensure each -nn->nfsd_serv is not destroyed while in use by nfsd_open_local_fh(), and +LOCALIO required the introduction and use of NFSD's percpu nfsd_net_ref +to interlock nfsd_shutdown_net() and nfsd_open_local_fh(), to ensure +each net-ns is not destroyed while in use by nfsd_open_local_fh(), and warrants a more detailed explanation: - nfsd_open_local_fh() uses nfsd_serv_try_get() before opening its + nfsd_open_local_fh() uses nfsd_net_try_get() before opening its nfsd_file handle and then the caller (NFS client) must drop the - reference for the nfsd_file and associated nn->nfsd_serv using - nfs_file_put_local() once it has completed its IO. + reference for the nfsd_file and associated net-ns using + nfsd_file_put_local() once it has completed its IO. This interlock working relies heavily on nfsd_open_local_fh() being afforded the ability to safely deal with the possibility that the NFSD's net-ns (and nfsd_net by association) may have been destroyed - by nfsd_destroy_serv() via nfsd_shutdown_net() -- which is only - possible given the nfs_uuid_t ->net pointer managemenet detailed - above. + by nfsd_destroy_serv() via nfsd_shutdown_net(). -All told, this elaborate interlock of the NFS client and server has been -verified to fix an easy to hit crash that would occur if an NFSD -instance running in a container, with a LOCALIO client mounted, is -shutdown. Upon restart of the container and associated NFSD the client -would go on to crash due to NULL pointer dereference that occurred due -to the LOCALIO client's attempting to nfsd_open_local_fh(), using -nn->nfsd_serv, without having a proper reference on nn->nfsd_serv. +This interlock of the NFS client and server has been verified to fix an +easy to hit crash that would occur if an NFSD instance running in a +container, with a LOCALIO client mounted, is shutdown. Upon restart of +the container and associated NFSD, the client would go on to crash due +to NULL pointer dereference that occurred due to the LOCALIO client's +attempting to nfsd_open_local_fh() without having a proper reference on +NFSD's net-ns. NFS Client issues IO instead of Server ====================================== @@ -306,10 +272,26 @@ is issuing IO to the underlying local filesystem that it is sharing with the NFS server. See: fs/nfs/localio.c:nfs_local_doio() and fs/nfs/localio.c:nfs_local_commit(). +With normal NFS that makes use of RPC to issue IO to the server, if an +application uses O_DIRECT the NFS client will bypass the pagecache but +the NFS server will not. The NFS server's use of buffered IO affords +applications to be less precise with their alignment when issuing IO to +the NFS client. But if all applications properly align their IO, LOCALIO +can be configured to use end-to-end O_DIRECT semantics from the NFS +client to the underlying local filesystem, that it is sharing with +the NFS server, by setting the 'localio_O_DIRECT_semantics' nfs module +parameter to Y, e.g.: + + echo Y > /sys/module/nfs/parameters/localio_O_DIRECT_semantics + +Once enabled, it will cause LOCALIO to use end-to-end O_DIRECT semantics +(but again, this may cause IO to fail if applications do not properly +align their IO). + Security ======== -Localio is only supported when UNIX-style authentication (AUTH_UNIX, aka +LOCALIO is only supported when UNIX-style authentication (AUTH_UNIX, aka AUTH_SYS) is used. Care is taken to ensure the same NFS security mechanisms are used @@ -324,6 +306,24 @@ client is afforded this same level of access (albeit in terms of the NFS protocol via SUNRPC). No other namespaces (user, mount, etc) have been altered or purposely extended from the server to the client. +Module Parameters +================= + +/sys/module/nfs/parameters/localio_enabled (bool) +controls if LOCALIO is enabled, defaults to Y. If client and server are +local but 'localio_enabled' is set to N then LOCALIO will not be used. + +/sys/module/nfs/parameters/localio_O_DIRECT_semantics (bool) +controls if O_DIRECT extends down to the underlying filesystem, defaults +to N. Application IO must be logical blocksize aligned, otherwise +O_DIRECT will fail. + +/sys/module/nfsv3/parameters/nfs3_localio_probe_throttle (uint) +controls if NFSv3 read and write IOs will trigger (re)enabling of +LOCALIO every N (nfs3_localio_probe_throttle) IOs, defaults to 0 +(disabled). Must be power-of-2, admin keeps all the pieces if they +misconfigure (too low a value or non-power-of-2). + Testing ======= diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst index 4c8387e1c880..6245b67ae9e0 100644 --- a/Documentation/filesystems/overlayfs.rst +++ b/Documentation/filesystems/overlayfs.rst @@ -156,7 +156,7 @@ A directory is made opaque by setting the xattr "trusted.overlay.opaque" to "y". Where the upper filesystem contains an opaque directory, any directory in the lower filesystem with the same name is ignored. -An opaque directory should not conntain any whiteouts, because they do not +An opaque directory should not contain any whiteouts, because they do not serve any purpose. A merge directory containing regular files with the xattr "trusted.overlay.whiteout", should be additionally marked by setting the xattr "trusted.overlay.opaque" to "x" on the merge directory itself. @@ -266,7 +266,7 @@ Non-directories Objects that are not directories (files, symlinks, device-special files etc.) are presented either from the upper or lower filesystem as appropriate. When a file in the lower filesystem is accessed in a way -the requires write-access, such as opening for write access, changing +that requires write-access, such as opening for write access, changing some metadata etc., the file is first copied from the lower filesystem to the upper filesystem (copy_up). Note that creating a hard-link also requires copy_up, though of course creation of a symlink does @@ -549,8 +549,8 @@ Nesting overlayfs mounts It is possible to use a lower directory that is stored on an overlayfs mount. For regular files this does not need any special care. However, files -that have overlayfs attributes, such as whiteouts or "overlay.*" xattrs will be -interpreted by the underlying overlayfs mount and stripped out. In order to +that have overlayfs attributes, such as whiteouts or "overlay.*" xattrs, will +be interpreted by the underlying overlayfs mount and stripped out. In order to allow the second overlayfs mount to see the attributes they must be escaped. Overlayfs specific xattrs are escaped by using a special prefix of diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 9ab2a3d6f2b4..1639e78e3146 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -313,7 +313,7 @@ done. **mandatory** -block truncatation on error exit from ->write_begin, and ->direct_IO +block truncation on error exit from ->write_begin, and ->direct_IO moved from generic methods (block_write_begin, cont_write_begin, nobh_write_begin, blockdev_direct_IO*) to callers. Take a look at ext2_write_failed and callers for an example. @@ -1141,3 +1141,19 @@ pointer are gone. set_blocksize() takes opened struct file instead of struct block_device now and it *must* be opened exclusive. + +--- + +** mandatory** + +->d_revalidate() gets two extra arguments - inode of parent directory and +name our dentry is expected to have. Both are stable (dir is pinned in +non-RCU case and will stay around during the call in RCU case, and name +is guaranteed to stay unchanging). Your instance doesn't have to use +either, but it often helps to avoid a lot of painful boilerplate. +Note that while name->name is stable and NUL-terminated, it may (and +often will) have name->name[name->len] equal to '/' rather than '\0' - +in normal case it points into the pathname being looked up. +NOTE: if you need something like full path from the root of filesystem, +you are still on your own - this assists with simple cases, but it's not +magic. diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 6a882c57a7e7..09f0aed5a08b 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -48,6 +48,7 @@ fixes/update part 1.1 Stefani Seibold June 9 2009 3.11 /proc//patch_state - Livepatch patch operation state 3.12 /proc//arch_status - Task architecture specific information 3.13 /proc//fd - List of symlinks to open files + 3.14 /proc//fd for fast access. ------------------------------------------------------- +3.14 /proc//ksm_merging_pages shows. + +ksm_process_profit +^^^^^^^^^^^^^^^^^^ + +The profit that KSM brings (Saved bytes). KSM can save memory by merging +identical pages, but also can consume additional memory, because it needs +to generate a number of rmap_items to save each scanned page's brief rmap +information. Some of these pages may be merged, but some may not be abled +to be merged after being checked several times, which are unprofitable +memory consumed. + +ksm_merge_any +^^^^^^^^^^^^^ + +It specifies whether the process's 'mm is added by prctl() into the +candidate list of KSM or not, and if KSM scanning is fully enabled at +process level. + +ksm_mergeable +^^^^^^^^^^^^^ + +It specifies whether any VMAs of the process''s mms are currently +applicable to KSM. + +More information about KSM can be found in +Documentation/admin-guide/mm/ksm.rst. + Chapter 4: Configuring procfs ============================= @@ -2261,7 +2331,7 @@ arguments are now protected against local eavesdroppers. hidepid=invisible or hidepid=2 means hidepid=1 plus all /proc// will be fully invisible to other users. It doesn't mean that it hides a fact whether a process with a specific pid value exists (it can be learned by other means, e.g. -by "kill -0 $PID"), but it hides process' uid and gid, which may be learned by +by "kill -0 $PID"), but it hides process's uid and gid, which may be learned by stat()'ing /proc// otherwise. It greatly complicates an intruder's task of gathering information about running processes, whether some daemon runs with elevated privileges, whether other user runs some sensitive program, whether diff --git a/Documentation/filesystems/squashfs.rst b/Documentation/filesystems/squashfs.rst index 4af8d6207509..45653b3228f9 100644 --- a/Documentation/filesystems/squashfs.rst +++ b/Documentation/filesystems/squashfs.rst @@ -6,7 +6,7 @@ Squashfs 4.0 Filesystem Squashfs is a compressed read-only filesystem for Linux. -It uses zlib, lz4, lzo, or xz compression to compress files, inodes and +It uses zlib, lz4, lzo, xz or zstd compression to compress files, inodes and directories. Inodes in the system are very small and all blocks are packed to minimise data overhead. Block sizes greater than 4K are supported up to a maximum of 1Mbytes (default block size 128K). @@ -16,8 +16,8 @@ use (i.e. in cases where a .tar.gz file may be used), and in constrained block device/memory systems (e.g. embedded systems) where low overhead is needed. -Mailing list: squashfs-devel@lists.sourceforge.net -Web site: www.squashfs.org +Mailing list (kernel code): linux-fsdevel@vger.kernel.org +Web site: github.com/plougher/squashfs-tools 1. Filesystem Features ---------------------- @@ -58,11 +58,9 @@ inodes have different sizes). As squashfs is a read-only filesystem, the mksquashfs program must be used to create populated squashfs filesystems. This and other squashfs utilities -can be obtained from http://www.squashfs.org. Usage instructions can be -obtained from this site also. - -The squashfs-tools development tree is now located on kernel.org - git://git.kernel.org/pub/scm/fs/squashfs/squashfs-tools.git +are very likely packaged by your linux distribution (called squashfs-tools). +The source code can be obtained from github.com/plougher/squashfs-tools. +Usage instructions can also be obtained from this site. 2.1 Mount options ----------------- diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 0b18af3f954e..31eea688609a 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -1251,7 +1251,8 @@ defined: .. code-block:: c struct dentry_operations { - int (*d_revalidate)(struct dentry *, unsigned int); + int (*d_revalidate)(struct inode *, const struct qstr *, + struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, @@ -1264,6 +1265,8 @@ defined: struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); + bool (*d_unalias_trylock)(const struct dentry *); + void (*d_unalias_unlock)(const struct dentry *); }; ``d_revalidate`` @@ -1427,6 +1430,25 @@ defined: For non-regular files, the 'dentry' argument is returned. +``d_unalias_trylock`` + if present, will be called by d_splice_alias() before moving a + preexisting attached alias. Returning false prevents __d_move(), + making d_splice_alias() fail with -ESTALE. + + Rationale: setting FS_RENAME_DOES_D_MOVE will prevent d_move() + and d_exchange() calls from the outside of filesystem methods; + however, it does not guarantee that attached dentries won't + be renamed or moved by d_splice_alias() finding a preexisting + alias for a directory inode. Normally we would not care; + however, something that wants to stabilize the entire path to + root over a blocking operation might need that. See 9p for one + (and hopefully only) example. + +``d_unalias_unlock`` + should be paired with ``d_unalias_trylock``; that one is called after + __d_move() call in __d_unalias(). + + Each dentry has a pointer to its parent dentry, as well as a hash list of child dentries. Child dentries are basically like files in a directory. diff --git a/Documentation/gpu/drm-compute.rst b/Documentation/gpu/drm-compute.rst new file mode 100644 index 000000000000..f90c3e63aa9e --- /dev/null +++ b/Documentation/gpu/drm-compute.rst @@ -0,0 +1,54 @@ +================================== +Long running workloads and compute +================================== + +Long running workloads (compute) are workloads that will not complete in 10 +seconds. (The time let the user wait before he reaches for the power button). +This means that other techniques need to be used to manage those workloads, +that cannot use fences. + +Some hardware may schedule compute jobs, and have no way to pre-empt them, or +have their memory swapped out from them. Or they simply want their workload +not to be preempted or swapped out at all. + +This means that it differs from what is described in driver-api/dma-buf.rst. + +As with normal compute jobs, dma-fence may not be used at all. In this case, +not even to force preemption. The driver with is simply forced to unmap a BO +from the long compute job's address space on unbind immediately, not even +waiting for the workload to complete. Effectively this terminates the workload +when there is no hardware support to recover. + +Since this is undesirable, there need to be mitigations to prevent a workload +from being terminated. There are several possible approach, all with their +advantages and drawbacks. + +The first approach you will likely try is to pin all buffers used by compute. +This guarantees that the job will run uninterrupted, but also allows a very +denial of service attack by pinning as much memory as possible, hogging the +all GPU memory, and possibly a huge chunk of CPU memory. + +A second approach that will work slightly better on its own is adding an option +not to evict when creating a new job (any kind). If all of userspace opts in +to this flag, it would prevent cooperating userspace from forced terminating +older compute jobs to start a new one. + +If job preemption and recoverable pagefaults are not available, those are the +only approaches possible. So even with those, you want a separate way of +controlling resources. The standard kernel way of doing so is cgroups. + +This creates a third option, using cgroups to prevent eviction. Both GPU and +driver-allocated CPU memory would be accounted to the correct cgroup, and +eviction would be made cgroup aware. This allows the GPU to be partitioned +into cgroups, that will allow jobs to run next to each other without +interference. + +The interface to the cgroup would be similar to the current CPU memory +interface, with similar semantics for min/low/high/max, if eviction can +be made cgroup aware. + +What should be noted is that each memory region (tiled memory for example) +should have its own accounting. + +The key is set to the regionid set by the driver, for example "tile0". +For the value of $card, we use drmGetUnique(). diff --git a/Documentation/gpu/drm-usage-stats.rst b/Documentation/gpu/drm-usage-stats.rst index 2717cb2a597e..b7fc106dad99 100644 --- a/Documentation/gpu/drm-usage-stats.rst +++ b/Documentation/gpu/drm-usage-stats.rst @@ -145,57 +145,57 @@ both. Memory ^^^^^^ -- drm-memory-: [KiB|MiB] - -Each possible memory type which can be used to store buffer objects by the -GPU in question shall be given a stable and unique name to be returned as the -string here. +Each possible memory type which can be used to store buffer objects by the GPU +in question shall be given a stable and unique name to be used as the "" +string. The region name "memory" is reserved to refer to normal system memory. -Value shall reflect the amount of storage currently consumed by the buffer +The value shall reflect the amount of storage currently consumed by the buffer objects belong to this client, in the respective memory region. Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB' indicating kibi- or mebi-bytes. -This key is deprecated and is an alias for drm-resident-. Only one of -the two should be present in the output. +- drm-total-: [KiB|MiB] + +The total size of all requested buffers, including both shared and private +memory. The backing store for the buffers does not need to be currently +instantiated to count under this category. To avoid double-counting, if a buffer +has multiple regions where it can be allocated to, the implementation should +consistently select a single region for accounting purposes. - drm-shared-: [KiB|MiB] -The total size of buffers that are shared with another file (e.g., have more -than a single handle). - -- drm-total-: [KiB|MiB] - -The total size of all created buffers including shared and private memory. The -backing store for the buffers does not have to be currently instantiated to be -counted under this category. +The total size of buffers that are shared with another file (i.e., have more +than one handle). The same requirement to avoid double-counting that applies to +drm-total- also applies here. - drm-resident-: [KiB|MiB] -The total size of buffers that are resident (have their backing store present or -instantiated) in the specified region. +The total size of buffers that are resident (i.e., have their backing store +present or instantiated) in the specified region. -This is an alias for drm-memory- and only one of the two should be -present in the output. +- drm-memory-: [KiB|MiB] + +This key is deprecated and is only printed by amdgpu; it is an alias for +drm-resident-. - drm-purgeable-: [KiB|MiB] -The total size of buffers that are purgeable. +The total size of buffers that are resident and purgeable. -For example drivers which implement a form of 'madvise' like functionality can -here count buffers which have instantiated backing store, but have been marked -with an equivalent of MADV_DONTNEED. +For example, drivers that implement functionality similar to 'madvise' can count +buffers that have instantiated backing stores but have been marked with an +equivalent of MADV_DONTNEED. - drm-active-: [KiB|MiB] The total size of buffers that are active on one or more engines. -One practical example of this can be presence of unsignaled fences in an GEM -buffer reservation object. Therefore the active category is a subset of -resident. +One practical example of this could be the presence of unsignaled fences in a +GEM buffer reservation object. Therefore, the active category is a subset of the +resident category. Implementation Details ====================== diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst index 37e383ccf73f..7dcb15850afd 100644 --- a/Documentation/gpu/index.rst +++ b/Documentation/gpu/index.rst @@ -13,6 +13,7 @@ GPU Driver Developer's Guide drm-usage-stats driver-uapi drm-client + drm-compute drivers backlight vga-switcheroo diff --git a/Documentation/gpu/zynqmp.rst b/Documentation/gpu/zynqmp.rst index f57bfa0ad6ec..1a6f9193de22 100644 --- a/Documentation/gpu/zynqmp.rst +++ b/Documentation/gpu/zynqmp.rst @@ -144,6 +144,4 @@ Internals .. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_dp.c -.. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_dpsub.c - .. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_kms.c diff --git a/Documentation/hid/index.rst b/Documentation/hid/index.rst index af02cf7cfa82..baf156b44b58 100644 --- a/Documentation/hid/index.rst +++ b/Documentation/hid/index.rst @@ -18,4 +18,5 @@ Human Interface Devices (HID) hid-alps intel-ish-hid + intel-thc-hid amd-sfh-hid diff --git a/Documentation/hid/intel-thc-hid.rst b/Documentation/hid/intel-thc-hid.rst new file mode 100644 index 000000000000..6c417205ac6a --- /dev/null +++ b/Documentation/hid/intel-thc-hid.rst @@ -0,0 +1,568 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================= +Intel Touch Host Controller (THC) +================================= + +Touch Host Controller is the name of the IP block in PCH that interface with Touch Devices (ex: +touchscreen, touchpad etc.). It is comprised of 3 key functional blocks: + +- A natively half-duplex Quad I/O capable SPI master +- Low latency I2C interface to support HIDI2C compliant devices +- A HW sequencer with RW DMA capability to system memory + +It has a single root space IOSF Primary interface that supports transactions to/from touch devices. +Host driver configures and controls the touch devices over THC interface. THC provides high +bandwidth DMA services to the touch driver and transfers the HID report to host system main memory. + +Hardware sequencer within the THC is responsible for transferring (via DMA) data from touch devices +into system memory. A ring buffer is used to avoid data loss due to asynchronous nature of data +consumption (by host) in relation to data production (by touch device via DMA). + +Unlike other common SPI/I2C controllers, THC handles the HID device data interrupt and reset +signals directly. + +1. Overview +=========== + +1.1 THC software/hardware stack +------------------------------- + +Below diagram illustrates the high-level architecture of THC software/hardware stack, which is fully +capable of supporting HIDSPI/HIDI2C protocol in Linux OS. + +:: + + ---------------------------------------------- + | +-----------------------------------+ | + | | Input Device | | + | +-----------------------------------+ | + | +-----------------------------------+ | + | | HID Multi-touch Driver | | + | +-----------------------------------+ | + | +-----------------------------------+ | + | | HID Core | | + | +-----------------------------------+ | + | +-----------------------------------+ | + | | THC QuickSPI/QuickI2C Driver | | + | +-----------------------------------+ | + | +-----------------------------------+ | + | | THC Hardware Driver | | + | +-----------------------------------+ | + | +----------------+ +----------------+ | + | SW | PCI Bus Driver | | ACPI Resource | | + | +----------------+ +----------------+ | + ---------------------------------------------- + ---------------------------------------------- + | +-----------------------------------+ | + | HW | PCI Bus | | + | +-----------------------------------+ | + | +-----------------------------------+ | + | | THC Controller | | + | +-----------------------------------+ | + | +-----------------------------------+ | + | | Touch IC | | + | +-----------------------------------+ | + ---------------------------------------------- + +Touch IC (TIC), also as known as the Touch devices (touchscreen or touchpad). The discrete analog +components that sense and transfer either discrete touch data or heatmap data in the form of HID +reports over the SPI/I2C bus to the THC Controller on the host. + +THC Host Controller, which is a PCI device HBA (host bus adapter), integrated into the PCH, that +serves as a bridge between the Touch ICs and the host. + +THC Hardware Driver, provides THC hardware operation APIs for above QuickSPI/QuickI2C driver, it +accesses THC MMIO registers to configure and control THC hardware. + +THC QuickSPI/QuickI2C driver, also as known as HIDSPI/HIDI2C driver, is registered as a HID +low-level driver that manages the THC Controller and implements HIDSPI/HIDI2C protocol. + + +1.2 THC hardware diagram +------------------------ +Below diagram shows THC hardware components:: + + --------------------------------- + | THC Controller | + | +---------------------------+ | + | | PCI Config Space | | + | +---------------------------+ | + | +---------------------------+ | + | + MMIO Registers | | + | +---------------------------+ | + +---------------+ | +------------+ +------------+ | + | System Memory +---+--+ DMA | | PIO | | + +---------------+ | +------------+ +------------+ | + | +---------------------------+ | + | | HW Sequencer | | + | +---------------------------+ | + | +------------+ +------------+ | + | | SPI/I2C | | GPIO | | + | | Controller | | Controller | | + | +------------+ +------------+ | + --------------------------------- + +As THC is exposed as a PCI devices, so it has standard PCI config space registers for PCI +enumeration and configuration. + +MMIO Registers, which provide registers access for driver to configure and control THC hardware, +the registers include several categories: Interrupt status and control, DMA configure, +PIO (Programmed I/O, defined in section 3.2) status and control, SPI bus configure, I2C subIP +status and control, reset status and control... + +THC provides two ways for driver to communicate with external Touch ICs: PIO and DMA. +PIO can let driver manually write/read data to/from Touch ICs, instead, THC DMA can +automatically write/read data without driver involved. + +HW Sequencer includes THC major logic, it gets instruction from MMIO registers to control +SPI bus and I2C bus to finish a bus data transaction, it also can automatically handle +Touch ICs interrupt and start DMA receive/send data from/to Touch ICs according to interrupt +type. That means THC HW Sequencer understands HIDSPI/HIDI2C transfer protocol, and handle +the communication without driver involved, what driver needs to do is just configure the THC +properly, and prepare the formatted data packet or handle received data packet. + +As THC supports HIDSPI/HIDI2C protocols, it has SPI controller and I2C subIP in it to expose +SPI bus and I2C bus. THC also integrates a GPIO controller to provide interrupt line support +and reset line support. + +2. THC Hardware Interface +========================= + +2.1 Host Interface +------------------ + +THC is exposed as "PCI Digitizer device" to the host. The PCI product and device IDs are +changed from different generations of processors. So the source code which enumerates drivers +needs to update from generation to generation. + + +2.2 Device Interface +-------------------- + +THC supports two types of bus for Touch IC connection: Enhanced SPI bus and I2C bus. + +2.2.1 SPI Port +~~~~~~~~~~~~~~ + +When PORT_TYPE = 00b in MMIO registers, THC uses SPI interfaces to communicate with external +Touch IC. THC enhanced SPI Bus supports different SPI modes: standard Single IO mode, +Dual IO mode and Quad IO mode. + +In Single IO mode, THC drives MOSI line to send data to Touch ICs, and receives data from Touch +ICs data from MISO line. In Dual IO mode, THC drivers MOSI and MISO both for data sending, and +also receives the data on both line. In Quad IO mode, there are other two lines (IO2 and IO3) +are added, THC drives MOSI (IO0), MISO (IO1), IO2 and IO3 at the same time for data sending, and +also receives the data on those 4 lines. Driver needs to configure THC in different mode by +setting different opcode. + +Beside IO mode, driver also needs to configure SPI bus speed. THC supports up to 42MHz SPI clock +on Intel Lunar Lake platform. + +For THC sending data to Touch IC, the data flow on SPI bus:: + + | --------------------THC sends---------------------------------| + <8Bits OPCode><24Bits Slave Address>........... + +For THC receiving data from Touch IC, the data flow on SPI bus:: + + | ---------THC Sends---------------||-----Touch IC sends--------| + <8Bits OPCode><24Bits Slave Address>........... + +2.2.2 I2C Port +~~~~~~~~~~~~~~ + +THC also integrates I2C controller in it, it's called I2C SubSystem. When PORT_TYPE = 01, THC +is configured to I2C mode. Comparing to SPI mode which can be configured through MMIO registers +directly, THC needs to use PIO read (by setting SubIP read opcode) to I2C subIP APB registers' +value and use PIO write (by setting SubIP write opcode) to do a write operation. + +2.2.3 GPIO interface +~~~~~~~~~~~~~~~~~~~~ + +THC also includes two GPIO pins, one for interrupt and the other for device reset control. + +Interrupt line can be configured to either level triggerred or edge triggerred by setting MMIO +Control register. + +Reset line is controlled by BIOS (or EFI) through ACPI _RST method, driver needs to call this +device ACPI _RST method to reset touch IC during initialization. + +3. High level concept +===================== + +3.1 Opcode +---------- + +Opcode (operation code) is used to tell THC or Touch IC what the operation will be, such as PIO +read or PIO write. + +When THC is configured to SPI mode, opcodes are used for determining the read/write IO mode. +There are some OPCode examples for SPI IO mode: + +======= ============================== +opcode Corresponding SPI command +======= ============================== +0x0B Read Single I/O +0x02 Write Single I/O +0xBB Read Dual I/O +0xB2 Write Dual I/O +0xEB Read Quad I/O +0xE2 Write Quad I/O +======= ============================== + +In general, different touch IC has different OPCode definition. According to HIDSPI +protocol whitepaper, those OPCodes are defined in device ACPI table, and driver needs to +query those information through OS ACPI APIs during driver initialization, then configures +THC MMIO OPCode registers with correct setting. + +When THC is working in I2C mode, opcodes are used to tell THC what's the next PIO type: +I2C SubIP APB register read, I2C SubIP APB register write, I2C touch IC device read, +I2C touch IC device write, I2C touch IC device write followed by read. + +Here are the THC pre-defined opcodes for I2C mode: + +======= =================================================== =========== +opcode Corresponding I2C command Address +======= =================================================== =========== +0x12 Read I2C SubIP APB internal registers 0h - FFh +0x13 Write I2C SubIP APB internal registers 0h - FFh +0x14 Read external Touch IC through I2C bus N/A +0x18 Write external Touch IC through I2C bus N/A +0x1C Write then read external Touch IC through I2C bus N/A +======= =================================================== =========== + +3.2 PIO +------- + +THC provides a programmed I/O (PIO) access interface for the driver to access the touch IC's +configuration registers, or access I2C subIP's configuration registers. To use PIO to perform +I/O operations, driver should pre-program PIO control registers and PIO data registers and kick +off the sequencing cycle. THC uses different PIO opcodes to distinguish different PIO +operations (PIO read/write/write followed by read). + +If there is a Sequencing Cycle In Progress and an attempt is made to program any of the control, +address, or data register the cycle is blocked and a sequence error will be encountered. + +A status bit indicates when the cycle has completed allowing the driver to know when read results +can be checked and/or when to initiate a new command. If enabled, the cycle done assertion can +interrupt driver with an interrupt. + +Because THC only has 16 FIFO registers for PIO, so all the data transfer through PIO shouldn't +exceed 64 bytes. + +As DMA needs max packet size for transferring configuration, and the max packet size information +always in HID device descriptor which needs THC driver to read it out from HID Device (Touch IC). +So PIO typical use case is, before DMA initialization, write RESET command (PIO write), read +RESET response (PIO read or PIO write followed by read), write Power ON command (PIO write), read +device descriptor (PIO read). + +For how to issue a PIO operation, here is the steps which driver needs follow: + +- Program read/write data size in THC_SS_BC. +- Program I/O target address in THC_SW_SEQ_DATA0_ADDR. +- If write, program the write data in THC_SW_SEQ_DATA0..THC_SW_SEQ_DATAn. +- Program the PIO opcode in THC_SS_CMD. +- Set TSSGO = 1 to start the PIO write sequence. +- If THC_SS_CD_IE = 1, SW will receives a MSI when the PIO is completed. +- If read, read out the data in THC_SW_SEQ_DATA0..THC_SW_SEQ_DATAn. + +3.3 DMA +------- + +THC has 4 DMA channels: Read DMA1, Read DMA2, Write DMA and Software DMA. + +3.3.1 Read DMA Channel +~~~~~~~~~~~~~~~~~~~~~~ + +THC has two Read DMA engines: 1st RxDMA (RxDMA1) and 2nd RxDMA (RxDMA2). RxDMA1 is reserved for +raw data mode. RxDMA2 is used for HID data mode and it is the RxDMA engine currently driver uses +for HID input report data retrieval. + +RxDMA's typical use case is auto receiving the data from Touch IC. Once RxDMA is enabled by +software, THC will start auto-handling receiving logic. + +For SPI mode, THC RxDMA sequence is: when Touch IC triggers a interrupt to THC, THC reads out +report header to identify what's the report type, and what's the report length, according to +above information, THC reads out report body to internal FIFO and start RxDMA coping the data +to system memory. After that, THC update interrupt cause register with report type, and update +RxDMA PRD table read pointer, then trigger a MSI interrupt to notify driver RxDMA finishing +data receiving. + +For I2C mode, THC RxDMA's behavior is a little bit different, because of HIDI2C protocol difference +with HIDSPI protocol, RxDMA only be used to receive input report. The sequence is, when Touch IC +triggers a interrupt to THC, THC first reads out 2 bytes from input report address to determine the +packet length, then use this packet length to start a DMA reading from input report address for +input report data. After that, THC update RxDMA PRD table read pointer, then trigger a MSI interrupt +to notify driver input report data is ready in system memory. + +All above sequence is hardware automatically handled, all driver needs to do is configure RxDMA and +waiting for interrupt ready then read out the data from system memory. + +3.3.2 Software DMA channel +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +THC supports a software triggerred RxDMA mode to read the touch data from touch IC. This SW RxDMA +is the 3rd THC RxDMA engine with the similar functionalities as the existing two RxDMAs, the only +difference is this SW RxDMA is triggerred by software, and RxDMA2 is triggerred by external Touch IC +interrupt. It gives a flexiblity to software driver to use RxDMA read Touch IC data in any time. + +Before software starts a SW RxDMA, it shall stop the 1st and 2nd RxDMA, clear PRD read/write pointer +and quiesce the device interrupt (THC_DEVINT_QUIESCE_HW_STS = 1), other operations are the same with +RxDMA. + +3.3.3 Write DMA Channel +~~~~~~~~~~~~~~~~~~~~~~~ + +THC has one write DMA engine, which can be used for sending data to Touch IC automatically. +According to HIDSPI and HIDI2C protocol, every time only one command can be sent to touch IC, and +before last command is completely handled, next command cannot be sent, THC write DMA engine only +supports single PRD table. + +What driver needs to do is, preparing PRD table and DMA buffer, then copy data to DMA buffer and +update PRD table with buffer address and buffer length, then start write DMA. THC will +automatically send the data to touch IC, and trigger a DMA completion interrupt once transferring +is done. + +3.4 PRD +------- + +Physical Region Descriptor (PRD) provides the memory mapping description for THC DMAs. + +3.4.1 PRD table and entry +~~~~~~~~~~~~~~~~~~~~~~~~~ + +In order to improve physical DMA memory usage, modern drivers trend to allocate a virtually +contiguous, but physically fragmented buffer of memory for each data buffer. Linux OS also +provide SGL (scatter gather list) APIs to support this usage. + +THC uses PRD table (physical region descriptor) to support the corresponding OS kernel +SGL that describes the virtual to physical buffer mapping. + +:: + + ------------------------ -------------- -------------- + | PRD table base address +----+ PRD table #1 +-----+ PRD Entry #1 | + ------------------------ -------------- -------------- + -------------- + | PRD Entry #2 | + -------------- + -------------- + | PRD Entry #n | + -------------- + +The read DMA engine supports multiple PRD tables held within a circular buffer that allow the THC +to support multiple data buffers from the Touch IC. This allows host SW to arm the Read DMA engine +with multiple buffers, allowing the Touch IC to send multiple data frames to the THC without SW +interaction. This capability is required when the CPU processes touch frames slower than the +Touch IC can send them. + +To simplify the design, SW assumes worst-case memory fragmentation. Therefore,each PRD table shall +contain the same number of PRD entries, allowing for a global register (per Touch IC) to hold the +number of PRD-entries per PRD table. + +SW allocates up to 128 PRD tables per Read DMA engine as specified in the THC_M_PRT_RPRD_CNTRL.PCD +register field. The number of PRD tables should equal the number of data buffers. + +Max OS memory fragmentation will be at a 4KB boundary, thus to address 1MB of virtually contiguous +memory 256 PRD entries are required for a single PRD Table. SW writes the number of PRD entries +for each PRD table in the THC_M_PRT_RPRD_CNTRL.PTEC register field. The PRD entry's length must be +multiple of 4KB except for the last entry in a PRD table. + +SW allocates all the data buffers and PRD tables only once at host initialization. + +3.4.2 PRD Write pointer and read pointer +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +As PRD tables are organized as a Circular Buffer (CB), a read pointer and a write pointer for a CB +are needed. + +DMA HW consumes the PRD tables in the CB, one PRD entry at a time until the EOP bit is found set +in a PRD entry. At this point HW increments the PRD read pointer. Thus, the read pointer points +to the PRD which the DMA engine is currently processing. This pointer rolls over once the circular +buffer's depth has been traversed with bit[7] the Rollover bit. E.g. if the DMA CB depth is equal +to 4 entries (0011b), then the read pointers will follow this pattern (HW is required to honor +this behavior): 00h 01h 02h 03h 80h 81h 82h 83h 00h 01h ... + +The write pointer is updated by SW. The write pointer points to location in the DMA CB, where the +next PRD table is going to be stored. SW needs to ensure that this pointer rolls over once the +circular buffer's depth has been traversed with Bit[7] as the rollover bit. E.g. if the DMA CB +depth is equal to 5 entries (0100b), then the write pointers will follow this pattern (SW is +required to honor this behavior): 00h 01h 02h 03h 04h 80h 81h 82h 83h 84h 00h 01h .. + +3.4.3 PRD descriptor structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Intel THC uses PRD entry descriptor for every PRD entry. Every PRD entry descriptor occupies +128 bits memories: + +=================== ======== =============================================== +struct field bit(s) description +=================== ======== =============================================== +dest_addr 53..0 destination memory address, as every entry + is 4KB, ignore lowest 10 bits of address. +reserved1 54..62 reserved +int_on_completion 63 completion interrupt enable bit, if this bit + set it means THC will trigger a completion + interrupt. This bit is set by SW driver. +len 87..64 how many bytes of data in this entry. +end_of_prd 88 end of PRD table bit, if this bit is set, + it means this entry is last entry in this PRD + table. This bit is set by SW driver. +hw_status 90..89 HW status bits +reserved2 127..91 reserved +=================== ======== =============================================== + +And one PRD table can include up to 256 PRD entries, as every entries is 4K bytes, so every +PRD table can describe 1M bytes memory. + +.. code-block:: c + + struct thc_prd_table { + struct thc_prd_entry entries[PRD_ENTRIES_NUM]; + }; + +In general, every PRD table means one HID touch data packet. Every DMA engine can support +up to 128 PRD tables (except write DMA, write DMA only has one PRD table). SW driver is responsible +to get max packet length from touch IC, and use this max packet length to create PRD entries for +each PRD table. + +4. HIDSPI support (QuickSPI) +============================ + +Intel THC is total compatible with HIDSPI protocol, THC HW sequenser can accelerate HIDSPI +protocol transferring. + +4.1 Reset Flow +-------------- + +- Call ACPI _RST method to reset Touch IC device. +- Read the reset response from TIC through PIO read. +- Issue a command to retrieve device descriptor from Touch IC through PIO write. +- Read the device descriptor from Touch IC through PIO read. +- If the device descriptor is valid, allocate DMA buffers and configure all DMA channels. +- Issue a command to retrieve report descriptor from Touch IC through DMA. + +4.2 Input Report Data Flow +-------------------------- + +Basic Flow: + +- Touch IC interrupts the THC Controller using an in-band THC interrupt. +- THC Sequencer reads the input report header by transmitting read approval as a signal + to the Touch IC to prepare for host to read from the device. +- THC Sequencer executes a Input Report Body Read operation corresponding to the value + reflected in “Input Report Length” field of the Input Report Header. +- THC DMA engine begins fetching data from the THC Sequencer and writes to host memory + at PRD entry 0 for the current CB PRD table entry. This process continues until the + THC Sequencer signals all data has been read or the THC DMA Read Engine reaches the + end of it's last PRD entry (or both). +- The THC Sequencer checks for the “Last Fragment Flag” bit in the Input Report Header. + If it is clear, the THC Sequencer enters an idle state. +- If the “Last Fragment Flag” bit is enabled the THC Sequencer enters End-of-Frame Processing. + +THC Sequencer End of Frame Processing: + +- THC DMA engine increments the read pointer of the Read PRD CB, sets EOF interrupt status + in RxDMA2 register (THC_M_PRT_READ_DMA_INT_STS_2). +- If THC EOF interrupt is enabled by the driver in the control register (THC_M_PRT_READ_DMA_CNTRL_2), + generates interrupt to software. + +Sequence of steps to read data from RX DMA buffer: + +- THC QuickSPI driver checks CB write Ptr and CB read Ptr to identify if any data frame in DMA + circular buffers. +- THC QuickSPI driver gets first unprocessed PRD table. +- THC QuickSPI driver scans all PRD entries in this PRD table to calculate the total frame size. +- THC QuickSPI driver copies all frame data out. +- THC QuickSPI driver checks the data type according to input report body, and calls related + callbacks to process the data. +- THC QuickSPI driver updates write Ptr. + +4.3 Output Report Data Flow +--------------------------- + +Generic Output Report Flow: + +- HID core calls raw_request callback with a request to THC QuickSPI driver. +- THC QuickSPI Driver converts request provided data into the output report packet and copies it + to THC's write DMA buffer. +- Start TxDMA to complete the write operation. + +5. HIDI2C support (QuickI2C) +============================ + +5.1 Reset Flow +-------------- + +- Read device descriptor from Touch IC device through PIO write followed by read. +- If the device descriptor is valid, allocate DMA buffers and configure all DMA channels. +- Use PIO or TxDMA to write a SET_POWER request to TIC's command register, and check if the + write operation is successfully completed. +- Use PIO or TxDMA to write a RESET request to TIC's command register. If the write operation + is successfully completed, wait for reset response from TIC. +- Use SWDMA to read report descriptor through TIC's report descriptor register. + +5.2 Input Report Data Flow +-------------------------- + +Basic Flow: + +- Touch IC asserts the interrupt indicating that it has an interrupt to send to HOST. + THC Sequencer issues a READ request over the I2C bus. The HIDI2C device returns the + first 2 bytes from the HIDI2C device which contains the length of the received data. +- THC Sequencer continues the Read operation as per the size of data indicated in the + length field. +- THC DMA engine begins fetching data from the THC Sequencer and writes to host memory + at PRD entry 0 for the current CB PRD table entry. THC writes 2Bytes for length field + plus the remaining data to RxDMA buffer. This process continues until the THC Sequencer + signals all data has been read or the THC DMA Read Engine reaches the end of it's last + PRD entry (or both). +- THC Sequencer enters End-of-Input Report Processing. +- If the device has no more input reports to send to the host, it de-asserts the interrupt + line. For any additional input reports, device keeps the interrupt line asserted and + steps 1 through 4 in the flow are repeated. + +THC Sequencer End of Input Report Processing: + +- THC DMA engine increments the read pointer of the Read PRD CB, sets EOF interrupt status + in RxDMA 2 register (THC_M_PRT_READ_DMA_INT_STS_2). +- If THC EOF interrupt is enabled by the driver in the control register + (THC_M_PRT_READ_DMA_CNTRL_2), generates interrupt to software. + +Sequence of steps to read data from RX DMA buffer: + +- THC QuickI2C driver checks CB write Ptr and CB read Ptr to identify if any data frame in DMA + circular buffers. +- THC QuickI2C driver gets first unprocessed PRD table. +- THC QuickI2C driver scans all PRD entries in this PRD table to calculate the total frame size. +- THC QuickI2C driver copies all frame data out. +- THC QuickI2C driver call hid_input_report to send the input report content to HID core, which + includes Report ID + Report Data Content (remove the length field from the original report + data). +- THC QuickI2C driver updates write Ptr. + +5.3 Output Report Data Flow +--------------------------- + +Generic Output Report Flow: + +- HID core call THC QuickI2C raw_request callback. +- THC QuickI2C uses PIO or TXDMA to write a SET_REPORT request to TIC's command register. Report + type in SET_REPORT should be set to Output. +- THC QuickI2C programs TxDMA buffer with TX Data to be written to TIC's data register. The first + 2 bytes should indicate the length of the report followed by the report contents including + Report ID. + +6. THC Debugging +================ + +To debug THC, event tracing mechanism is used. To enable debug logs:: + + echo 1 > /sys/kernel/debug/tracing/events/intel_thc/enable + cat /sys/kernel/debug/tracing/trace + +7. Reference +============ +- HIDSPI: https://download.microsoft.com/download/c/a/0/ca07aef3-3e10-4022-b1e9-c98cea99465d/HidSpiProtocolSpec.pdf +- HIDI2C: https://download.microsoft.com/download/7/d/d/7dd44bb7-2a7a-4505-ac1c-7227d3d96d5b/hid-over-i2c-protocol-spec-v1-0.docx diff --git a/Documentation/hwmon/adm1275.rst b/Documentation/hwmon/adm1275.rst index 467daf8ce3c5..57bd7a850558 100644 --- a/Documentation/hwmon/adm1275.rst +++ b/Documentation/hwmon/adm1275.rst @@ -19,6 +19,14 @@ Supported chips: Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1272.pdf + * Analog Devices ADM1273 + + Prefix: 'adm1273' + + Addresses scanned: - + + Datasheet: Not yet publicly available + * Analog Devices ADM1275 Prefix: 'adm1275' @@ -66,14 +74,14 @@ Description ----------- This driver supports hardware monitoring for Analog Devices ADM1075, ADM1272, -ADM1275, ADM1276, ADM1278, ADM1281, ADM1293, and ADM1294 Hot-Swap Controller and -Digital Power Monitors. +ADM1273, ADM1275, ADM1276, ADM1278, ADM1281, ADM1293, and ADM1294 Hot-Swap +Controller and Digital Power Monitors. -ADM1075, ADM1272, ADM1275, ADM1276, ADM1278, ADM1281, ADM1293, and ADM1294 are hot-swap -controllers that allow a circuit board to be removed from or inserted into -a live backplane. They also feature current and voltage readback via an -integrated 12 bit analog-to-digital converter (ADC), accessed using a -PMBus interface. +ADM1075, ADM1272, ADM1273, ADM1275, ADM1276, ADM1278, ADM1281, ADM1293, and +ADM1294 are hot-swap controllers that allow a circuit board to be removed from +or inserted into a live backplane. They also feature current and voltage +readback via an integrated 12 bit analog-to-digital converter (ADC), accessed +using a PMBus interface. The driver is a client driver to the core PMBus driver. Please see Documentation/hwmon/pmbus.rst for details on PMBus client drivers. @@ -141,7 +149,7 @@ power1_input_highest Highest observed input power. power1_reset_history Write any value to reset history. Power attributes are supported on ADM1075, ADM1272, - ADM1276, ADM1293, and ADM1294. + ADM1273, ADM1276, ADM1293, and ADM1294. temp1_input Chip temperature. temp1_max Maximum chip temperature. @@ -151,6 +159,6 @@ temp1_crit_alarm Critical temperature high alarm. temp1_highest Highest observed temperature. temp1_reset_history Write any value to reset history. - Temperature attributes are supported on ADM1272 and - ADM1278, and ADM1281. + Temperature attributes are supported on ADM1272, + ADM1273, ADM1278, and ADM1281. ======================= ======================================================= diff --git a/Documentation/hwmon/asus_ec_sensors.rst b/Documentation/hwmon/asus_ec_sensors.rst index ca38922f4ec5..739636cf7994 100644 --- a/Documentation/hwmon/asus_ec_sensors.rst +++ b/Documentation/hwmon/asus_ec_sensors.rst @@ -29,6 +29,7 @@ Supported boards: * ROG STRIX Z690-A GAMING WIFI D4 * ROG ZENITH II EXTREME * ROG ZENITH II EXTREME ALPHA + * TUF GAMING X670E PLUS Authors: - Eugene Shalygin diff --git a/Documentation/hwmon/crps.rst b/Documentation/hwmon/crps.rst new file mode 100644 index 000000000000..87380b496558 --- /dev/null +++ b/Documentation/hwmon/crps.rst @@ -0,0 +1,97 @@ +.. SPDX-License-Identifier: GPL-2.0-or-later + +Kernel driver crps +================== + +Supported chips: + + * Intel CRPS185 + + Prefix: 'crps185' + + Addresses scanned: - + + Datasheet: Only available under NDA. + +Authors: + Ninad Palsule + + +Description +----------- + +This driver implements support for Intel Common Redundant Power supply with +PMBus support. + +The driver is a client driver to the core PMBus driver. +Please see Documentation/hwmon/pmbus.rst for details on PMBus client drivers. + + +Usage Notes +----------- + +This driver does not auto-detect devices. You will have to instantiate the +devices explicitly. Please see Documentation/i2c/instantiating-devices.rst for +details. + + +Sysfs entries +------------- + +======================= ====================================================== +curr1_label "iin" +curr1_input Measured input current +curr1_max Maximum input current +curr1_max_alarm Input maximum current high alarm +curr1_crit Critial high input current +curr1_crit_alarm Input critical current high alarm +curr1_rated_max Maximum rated input current + +curr2_label "iout1" +curr2_input Measured output current +curr2_max Maximum output current +curr2_max_alarm Output maximum current high alarm +curr2_crit Critial high output current +curr2_crit_alarm Output critical current high alarm +curr2_rated_max Maximum rated output current + +in1_label "vin" +in1_input Measured input voltage +in1_crit Critical input over voltage +in1_crit_alarm Critical input over voltage alarm +in1_max Maximum input over voltage +in1_max_alarm Maximum input over voltage alarm +in1_rated_min Minimum rated input voltage +in1_rated_max Maximum rated input voltage + +in2_label "vout1" +in2_input Measured input voltage +in2_crit Critical input over voltage +in2_crit_alarm Critical input over voltage alarm +in2_lcrit Critical input under voltage fault +in2_lcrit_alarm Critical input under voltage fault alarm +in2_max Maximum input over voltage +in2_max_alarm Maximum input over voltage alarm +in2_min Minimum input under voltage warning +in2_min_alarm Minimum input under voltage warning alarm +in2_rated_min Minimum rated input voltage +in2_rated_max Maximum rated input voltage + +power1_label "pin" +power1_input Measured input power +power1_alarm Input power high alarm +power1_max Maximum input power +power1_rated_max Maximum rated input power + +temp[1-2]_input Measured temperature +temp[1-2]_crit Critical temperature +temp[1-2]_crit_alarm Critical temperature alarm +temp[1-2]_max Maximum temperature +temp[1-2]_max_alarm Maximum temperature alarm +temp[1-2]_rated_max Maximum rated temperature + +fan1_alarm Fan 1 warning. +fan1_fault Fan 1 fault. +fan1_input Fan 1 speed in RPM. +fan1_target Fan 1 target. +======================= ====================================================== diff --git a/Documentation/hwmon/hwmon-kernel-api.rst b/Documentation/hwmon/hwmon-kernel-api.rst index 8297acfa3a2d..e47fc757e63e 100644 --- a/Documentation/hwmon/hwmon-kernel-api.rst +++ b/Documentation/hwmon/hwmon-kernel-api.rst @@ -64,7 +64,8 @@ hwmon_device_register_with_info. All supported hwmon device registration functions only accept valid device names. Device names including invalid characters (whitespace, '*', or '-') -will be rejected. The 'name' parameter is mandatory. +will be rejected. If NULL is passed as name parameter, the hardware monitoring +device name will be derived from the parent device name. If the driver doesn't use a static device name (for example it uses dev_name()), and therefore cannot make sure the name only contains valid diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst index 55f1111594b2..874f8fd26325 100644 --- a/Documentation/hwmon/index.rst +++ b/Documentation/hwmon/index.rst @@ -58,6 +58,7 @@ Hardware Monitoring Kernel Drivers corsair-cpro corsair-psu cros_ec_hwmon + crps da9052 da9055 dell-smm-hwmon @@ -201,6 +202,7 @@ Hardware Monitoring Kernel Drivers pxe1610 pwm-fan q54sj108a2 + qnap-mcu-hwmon raspberrypi-hwmon sbrmi sbtsi_temp @@ -236,6 +238,7 @@ Hardware Monitoring Kernel Drivers tmp464 tmp513 tps23861 + tps25990 tps40422 tps53679 tps546d24 diff --git a/Documentation/hwmon/isl28022.rst b/Documentation/hwmon/isl28022.rst index 8d4422a2dacd..273ce5460135 100644 --- a/Documentation/hwmon/isl28022.rst +++ b/Documentation/hwmon/isl28022.rst @@ -33,7 +33,7 @@ details. The shunt value in micro-ohms, shunt voltage range and averaging can be set with device properties. -Please refer to the Documentation/devicetree/bindings/hwmon/isl,isl28022.yaml +Please refer to the Documentation/devicetree/bindings/hwmon/renesas,isl28022.yaml for bindings if the device tree is used. The driver supports only shunt and bus continuous ADC mode at 15bit resolution. @@ -48,6 +48,7 @@ The following attributes are supported. All attributes are read-only. ======================= ======================================================= in0_input bus voltage (milli Volt) +in1_input shunt voltage (milli Volt) curr1_input current (milli Ampere) power1_input power (micro Watt) diff --git a/Documentation/hwmon/lm75.rst b/Documentation/hwmon/lm75.rst index 6adab608dd05..c6a54bbca3c5 100644 --- a/Documentation/hwmon/lm75.rst +++ b/Documentation/hwmon/lm75.rst @@ -121,15 +121,17 @@ Supported chips: https://www.ti.com/product/TMP1075 - * NXP LM75B, PCT2075 + * NXP LM75B, P3T1755, PCT2075 - Prefix: 'lm75b', 'pct2075' + Prefix: 'lm75b', 'p3t1755', 'pct2075' Addresses scanned: none Datasheet: Publicly available at the NXP website - https://www.nxp.com/documents/data_sheet/LM75B.pdf + https://www.nxp.com/docs/en/data-sheet/LM75B.pdf + + https://www.nxp.com/docs/en/data-sheet/P3T1755.pdf https://www.nxp.com/docs/en/data-sheet/PCT2075.pdf diff --git a/Documentation/hwmon/max15301.rst b/Documentation/hwmon/max15301.rst index e3dc22fe1c6d..e2222e98304f 100644 --- a/Documentation/hwmon/max15301.rst +++ b/Documentation/hwmon/max15301.rst @@ -13,6 +13,14 @@ Supported chips: Datasheet: https://datasheets.maximintegrated.com/en/ds/MAX15301.pdf + * Maxim MAX15303 + + Prefix: 'max15303' + + Addresses scanned: - + + Datasheet: https://www.analog.com/media/en/technical-documentation/data-sheets/max15303.pdf + Author: Erik Rosen diff --git a/Documentation/hwmon/nct6683.rst b/Documentation/hwmon/nct6683.rst index 2a7a78eb1b46..8d4a20d99e59 100644 --- a/Documentation/hwmon/nct6683.rst +++ b/Documentation/hwmon/nct6683.rst @@ -55,14 +55,16 @@ Tested Boards and Firmware Versions The driver has been reported to work with the following boards and firmware versions. -=============== =============================================== -Board Firmware version -=============== =============================================== -Intel DH87RL NCT6683D EC firmware version 1.0 build 04/03/13 -Intel DH87MC NCT6683D EC firmware version 1.0 build 04/03/13 -Intel DB85FL NCT6683D EC firmware version 1.0 build 04/03/13 -ASRock X570 NCT6683D EC firmware version 1.0 build 06/28/19 -ASRock X670E NCT6686D EC firmware version 1.0 build 05/19/22 -MSI B550 NCT6687D EC firmware version 1.0 build 05/07/20 -MSI X670-P NCT6687D EC firmware version 0.0 build 09/27/22 -=============== =============================================== +=============================== =============================================== +Board Firmware version +=============================== =============================================== +Intel DH87RL NCT6683D EC firmware version 1.0 build 04/03/13 +Intel DH87MC NCT6683D EC firmware version 1.0 build 04/03/13 +Intel DB85FL NCT6683D EC firmware version 1.0 build 04/03/13 +ASRock X570 NCT6683D EC firmware version 1.0 build 06/28/19 +ASRock X670E NCT6686D EC firmware version 1.0 build 05/19/22 +ASRock B650 Steel Legend WiFi NCT6686D EC firmware version 1.0 build 11/09/23 +MSI B550 NCT6687D EC firmware version 1.0 build 05/07/20 +MSI X670-P NCT6687D EC firmware version 0.0 build 09/27/22 +MSI X870E NCT6687D EC firmware version 0.0 build 11/13/24 +=============================== =============================================== diff --git a/Documentation/hwmon/pmbus-core.rst b/Documentation/hwmon/pmbus-core.rst index 686a00265bf7..fdfb23773148 100644 --- a/Documentation/hwmon/pmbus-core.rst +++ b/Documentation/hwmon/pmbus-core.rst @@ -312,6 +312,10 @@ currently provides a flags field with four bits used:: #define PMBUS_USE_COEFFICIENTS_CMD BIT(5) + #define PMBUS_OP_PROTECTED BIT(6) + + #define PMBUS_VOUT_PROTECTED BIT(7) + struct pmbus_platform_data { u32 flags; /* Device specific flags */ @@ -373,3 +377,34 @@ PMBUS_USE_COEFFICIENTS_CMD When this flag is set the PMBus core driver will use the COEFFICIENTS register to initialize the coefficients for the direct mode format. + +PMBUS_OP_PROTECTED + +Set if the chip OPERATION command is protected and protection is not +determined by the standard WRITE_PROTECT command. + +PMBUS_VOUT_PROTECTED + +Set if the chip VOUT_COMMAND command is protected and protection is not +determined by the standard WRITE_PROTECT command. + +Module parameter +---------------- + +pmbus_core.wp: PMBus write protect forced mode + +PMBus may come up with a variety of write protection configuration. +'pmbus_core.wp' may be used if a particular write protection is necessary. +The ability to actually alter the protection may also depend on the chip +so the actual runtime write protection configuration may differ from +the requested one. pmbus_core currently support the following value: + +* 0: write protection removed. +* 1: Disable all writes except to the WRITE_PROTECT, OPERATION, + PAGE, ON_OFF_CONFIG and VOUT_COMMAND commands. +* 2: Disable all writes except to the WRITE_PROTECT, OPERATION and + PAGE commands. +* 3: Disable all writes except to the WRITE_PROTECT command. Note that + protection should include the PAGE register. This may be problematic + for multi-page chips, if the chips strictly follows the PMBus + specification, preventing the chip from changing the active page. diff --git a/Documentation/hwmon/qnap-mcu-hwmon.rst b/Documentation/hwmon/qnap-mcu-hwmon.rst new file mode 100644 index 000000000000..83407e3408f2 --- /dev/null +++ b/Documentation/hwmon/qnap-mcu-hwmon.rst @@ -0,0 +1,27 @@ +.. SPDX-License-Identifier: GPL-2.0-or-later + +Kernel driver qnap-mcu-hwmon +============================ + +This driver enables the use of the hardware monitoring and fan control +of the MCU used on some QNAP network attached storage devices. + +Author: Heiko Stuebner + +Description +----------- + +The driver implements a simple interface for driving the fan controlled by +setting its PWM output value and exposes the fan rpm and case-temperature +to user space through hwmon's sysfs interface. + +The fan rotation speed returned via the optional 'fan1_input' is calculated +inside the MCU device. + +The driver provides the following sensor accesses in sysfs: + +=============== ======= ======================================================= +fan1_input ro fan tachometer speed in RPM +pwm1 rw relative speed (0-255), 255=max. speed. +temp1_input ro Measured temperature in millicelsius +=============== ======= ======================================================= diff --git a/Documentation/hwmon/tps25990.rst b/Documentation/hwmon/tps25990.rst new file mode 100644 index 000000000000..04faec780d26 --- /dev/null +++ b/Documentation/hwmon/tps25990.rst @@ -0,0 +1,147 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Kernel driver tps25990 +====================== + +Supported chips: + + * TI TPS25990 + + Prefix: 'tps25990' + + * Datasheet + + Publicly available at Texas Instruments website: https://www.ti.com/lit/gpn/tps25990 + +Author: + + Jerome Brunet + +Description +----------- + +This driver implements support for TI TPS25990 eFuse. +This is an integrated, high-current circuit protection and power +management device with PMBUS interface + +Device compliant with: + +- PMBus rev 1.3 interface. + +Device supports direct format for reading input voltages, +output voltage, input current, input power and temperature. + +Due to the specificities of the chip, all history reset attributes +are tied together. Resetting the history of a sensor, resets the +history of all the sensors. + +The driver exports the following attributes via the 'sysfs' files +for input current: + +**curr1_average** + +**curr1_crit** + +**curr1_crit_alarm** + +**curr1_highest** + +**curr1_input** + +**curr1_label** + +**curr1_max** + +**curr1_max_alarm** + +**curr1_reset_history** + +The driver provides the following attributes for main input voltage: + +**in1_average** + +**in1_crit** + +**in1_crit_alarm** + +**in1_highest** + +**in1_input** + +**in1_label** + +**in1_lcrit** + +**in1_lcrit_alarm** + +**in1_lowest** + +**in1_max** + +**in1_max_alarm** + +**in1_min** + +**in1_min_alarm** + +**in1_reset_history** + +The driver provides the following attributes for auxiliary input voltage: + +**in2_input** + +**in2_label** + +The driver provides the following attributes for output voltage: + +**in3_average** + +**in3_input** + +**in3_label** + +**in3_lowest** + +**in3_min** + +**in3_min_alarm** + +**in3_reset_history** + +The driver provides the following attributes for input power: + +**power1_alarm** + +**power1_average** + +**power1_input** + +**power1_input_highest** + +**power1_label** + +**power1_max** + +**power1_reset_history** + +The driver provides the following attributes for temperature: + +**temp1_average** + +**temp1_crit** + +**temp1_crit_alarm** + +**temp1_highest** + +**temp1_input** + +**temp1_max** + +**temp1_max_alarm** + +**temp1_reset_history** + +The driver provides the following attributes for sampling: + +**samples** diff --git a/Documentation/iio/ad4695.rst b/Documentation/iio/ad4695.rst index 33ed29b7c98a..9ec8bf466c15 100644 --- a/Documentation/iio/ad4695.rst +++ b/Documentation/iio/ad4695.rst @@ -101,7 +101,7 @@ The macro comes from: .. code-block:: - #include + #include Pairing two INx pins ^^^^^^^^^^^^^^^^^^^^ diff --git a/Documentation/iio/adis16480.rst b/Documentation/iio/adis16480.rst index bc78fa04d958..4a2d40e0daa7 100644 --- a/Documentation/iio/adis16480.rst +++ b/Documentation/iio/adis16480.rst @@ -12,7 +12,10 @@ This driver supports Analog Device's IMUs on SPI bus. * `ADIS16375 `_ * `ADIS16480 `_ * `ADIS16485 `_ +* `ADIS16486 `_ +* `ADIS16487 `_ * `ADIS16488 `_ +* `ADIS16489 `_ * `ADIS16490 `_ * `ADIS16495 `_ * `ADIS16497 `_ diff --git a/Documentation/iio/index.rst b/Documentation/iio/index.rst index 074dbbf7ba0a..5710f5b9e958 100644 --- a/Documentation/iio/index.rst +++ b/Documentation/iio/index.rst @@ -29,3 +29,4 @@ Industrial I/O Kernel Drivers adxl380 bno055 ep93xx_adc + opt4060 diff --git a/Documentation/iio/opt4060.rst b/Documentation/iio/opt4060.rst new file mode 100644 index 000000000000..eb155089b6d2 --- /dev/null +++ b/Documentation/iio/opt4060.rst @@ -0,0 +1,61 @@ +============================== +OPT4060 driver +============================== + +1. Overview +============================= + +This driver supports the Texas Instrument RGBW high resolution color sensor over +I2C. +https://www.ti.com/lit/gpn/opt4060 + +The driver supports: +- Raw values for red, green, blue and clear. +- Illuminance values. +- Scaled color values for red, green and blue. +- IIO events for thresholds. +- IIO triggered buffer using both its own data ready trigger and triggers from +other drivers. + +2. Illuminance calculation +============================= + +Illuminance is calculated using the wide spectrum green channel. + +lux = GREEN_RAW x 2.15e-3 + +The value is accessed from: +/sys/bus/iio/devices/iio:deviceX/in_illuminance_input + +See section 8.4.5.2 in the data sheet for additional details. + +3. Color scale values +============================= + +The sensor has different sensitivity for the different color components and +compensating factors are exposed from the driver. + +The values are accessed from: +/sys/bus/iio/devices/iio:deviceX/in_intensity_red_scale +/sys/bus/iio/devices/iio:deviceX/in_intensity_green_scale +/sys/bus/iio/devices/iio:deviceX/in_intensity_blue_scale + +A userspace application can multiply the raw values with the scale values so +that for a particular test light source, typically white, the measurement +intensity is the same across the different color channels. This is calculated +in the following way: + +R = RED_RAW x SCALE_RED(2.4) +G = GREEN_RAW x SCALE_GREEN(1.0) +B = BLUE_RAW x SCALE_BLUE(1.3) + +The data sheet suggests using the scaled values to normalize the scaled R, G +and B values. This is useful to get a value for the ratio between colors +independent of light intensity. A userspace application can do this in the +following way: + +R_NORMALIZED = R / (R + G + B) +G_NORMALIZED = G / (R + G + B) +B_NORMALIZED = B / (R + G + B) + +See section 8.4.5.2 in the data sheet for additional details. diff --git a/Documentation/kbuild/gendwarfksyms.rst b/Documentation/kbuild/gendwarfksyms.rst new file mode 100644 index 000000000000..e4beaae7e456 --- /dev/null +++ b/Documentation/kbuild/gendwarfksyms.rst @@ -0,0 +1,308 @@ +======================= +DWARF module versioning +======================= + +1. Introduction +=============== + +When CONFIG_MODVERSIONS is enabled, symbol versions for modules +are typically calculated from preprocessed source code using the +**genksyms** tool. However, this is incompatible with languages such +as Rust, where the source code has insufficient information about +the resulting ABI. With CONFIG_GENDWARFKSYMS (and CONFIG_DEBUG_INFO) +selected, **gendwarfksyms** is used instead to calculate symbol versions +from the DWARF debugging information, which contains the necessary +details about the final module ABI. + +1.1. Usage +========== + +gendwarfksyms accepts a list of object files on the command line, and a +list of symbol names (one per line) in standard input:: + + Usage: gendwarfksyms [options] elf-object-file ... < symbol-list + + Options: + -d, --debug Print debugging information + --dump-dies Dump DWARF DIE contents + --dump-die-map Print debugging information about die_map changes + --dump-types Dump type strings + --dump-versions Dump expanded type strings used for symbol versions + -s, --stable Support kABI stability features + -T, --symtypes file Write a symtypes file + -h, --help Print this message + + +2. Type information availability +================================ + +While symbols are typically exported in the same translation unit (TU) +where they're defined, it's also perfectly fine for a TU to export +external symbols. For example, this is done when calculating symbol +versions for exports in stand-alone assembly code. + +To ensure the compiler emits the necessary DWARF type information in the +TU where symbols are actually exported, gendwarfksyms adds a pointer +to exported symbols in the `EXPORT_SYMBOL()` macro using the following +macro:: + + #define __GENDWARFKSYMS_EXPORT(sym) \ + static typeof(sym) *__gendwarfksyms_ptr_##sym __used \ + __section(".discard.gendwarfksyms") = &sym; + + +When a symbol pointer is found in DWARF, gendwarfksyms can use its +type for calculating symbol versions even if the symbol is defined +elsewhere. The name of the symbol pointer is expected to start with +`__gendwarfksyms_ptr_`, followed by the name of the exported symbol. + +3. Symtypes output format +========================= + +Similarly to genksyms, gendwarfksyms supports writing a symtypes +file for each processed object that contain types for exported +symbols and each referenced type that was used in calculating symbol +versions. These files can be useful when trying to determine what +exactly caused symbol versions to change between builds. To generate +symtypes files during a kernel build, set `KBUILD_SYMTYPES=1`. + +Matching the existing format, the first column of each line contains +either a type reference or a symbol name. Type references have a +one-letter prefix followed by "#" and the name of the type. Four +reference types are supported:: + + e# = enum + s# = struct + t# = typedef + u# = union + +Type names with spaces in them are wrapped in single quotes, e.g.:: + + s#'core::result::Result' + +The rest of the line contains a type string. Unlike with genksyms that +produces C-style type strings, gendwarfksyms uses the same simple parsed +DWARF format produced by **--dump-dies**, but with type references +instead of fully expanded strings. + +4. Maintaining a stable kABI +============================ + +Distribution maintainers often need the ability to make ABI compatible +changes to kernel data structures due to LTS updates or backports. Using +the traditional `#ifndef __GENKSYMS__` to hide these changes from symbol +versioning won't work when processing object files. To support this +use case, gendwarfksyms provides kABI stability features designed to +hide changes that won't affect the ABI when calculating versions. These +features are all gated behind the **--stable** command line flag and are +not used in the mainline kernel. To use stable features during a kernel +build, set `KBUILD_GENDWARFKSYMS_STABLE=1`. + +Examples for using these features are provided in the +**scripts/gendwarfksyms/examples** directory, including helper macros +for source code annotation. Note that as these features are only used to +transform the inputs for symbol versioning, the user is responsible for +ensuring that their changes actually won't break the ABI. + +4.1. kABI rules +=============== + +kABI rules allow distributions to fine-tune certain parts +of gendwarfksyms output and thus control how symbol +versions are calculated. These rules are defined in the +`.discard.gendwarfksyms.kabi_rules` section of the object file and +consist of simple null-terminated strings with the following structure:: + + version\0type\0target\0value\0 + +This string sequence is repeated as many times as needed to express all +the rules. The fields are as follows: + +- `version`: Ensures backward compatibility for future changes to the + structure. Currently expected to be "1". +- `type`: Indicates the type of rule being applied. +- `target`: Specifies the target of the rule, typically the fully + qualified name of the DWARF Debugging Information Entry (DIE). +- `value`: Provides rule-specific data. + +The following helper macro, for example, can be used to specify rules +in the source code:: + + #define __KABI_RULE(hint, target, value) \ + static const char __PASTE(__gendwarfksyms_rule_, \ + __COUNTER__)[] __used __aligned(1) \ + __section(".discard.gendwarfksyms.kabi_rules") = \ + "1\0" #hint "\0" #target "\0" #value + + +Currently, only the rules discussed in this section are supported, but +the format is extensible enough to allow further rules to be added as +need arises. + +4.1.1. Managing definition visibility +===================================== + +A declaration can change into a full definition when additional includes +are pulled into the translation unit. This changes the versions of any +symbol that references the type even if the ABI remains unchanged. As +it may not be possible to drop includes without breaking the build, the +`declonly` rule can be used to specify a type as declaration-only, even +if the debugging information contains the full definition. + +The rule fields are expected to be as follows: + +- `type`: "declonly" +- `target`: The fully qualified name of the target data structure + (as shown in **--dump-dies** output). +- `value`: This field is ignored. + +Using the `__KABI_RULE` macro, this rule can be defined as:: + + #define KABI_DECLONLY(fqn) __KABI_RULE(declonly, fqn, ) + +Example usage:: + + struct s { + /* definition */ + }; + + KABI_DECLONLY(s); + +4.1.2. Adding enumerators +========================= + +For enums, all enumerators and their values are included in calculating +symbol versions, which becomes a problem if we later need to add more +enumerators without changing symbol versions. The `enumerator_ignore` +rule allows us to hide named enumerators from the input. + +The rule fields are expected to be as follows: + +- `type`: "enumerator_ignore" +- `target`: The fully qualified name of the target enum + (as shown in **--dump-dies** output) and the name of the + enumerator field separated by a space. +- `value`: This field is ignored. + +Using the `__KABI_RULE` macro, this rule can be defined as:: + + #define KABI_ENUMERATOR_IGNORE(fqn, field) \ + __KABI_RULE(enumerator_ignore, fqn field, ) + +Example usage:: + + enum e { + A, B, C, D, + }; + + KABI_ENUMERATOR_IGNORE(e, B); + KABI_ENUMERATOR_IGNORE(e, C); + +If the enum additionally includes an end marker and new values must +be added in the middle, we may need to use the old value for the last +enumerator when calculating versions. The `enumerator_value` rule allows +us to override the value of an enumerator for version calculation: + +- `type`: "enumerator_value" +- `target`: The fully qualified name of the target enum + (as shown in **--dump-dies** output) and the name of the + enumerator field separated by a space. +- `value`: Integer value used for the field. + +Using the `__KABI_RULE` macro, this rule can be defined as:: + + #define KABI_ENUMERATOR_VALUE(fqn, field, value) \ + __KABI_RULE(enumerator_value, fqn field, value) + +Example usage:: + + enum e { + A, B, C, LAST, + }; + + KABI_ENUMERATOR_IGNORE(e, C); + KABI_ENUMERATOR_VALUE(e, LAST, 2); + +4.3. Adding structure members +============================= + +Perhaps the most common ABI compatible change is adding a member to a +kernel data structure. When changes to a structure are anticipated, +distribution maintainers can pre-emptively reserve space in the +structure and take it into use later without breaking the ABI. If +changes are needed to data structures without reserved space, existing +alignment holes can potentially be used instead. While kABI rules could +be added for these type of changes, using unions is typically a more +natural method. This section describes gendwarfksyms support for using +reserved space in data structures and hiding members that don't change +the ABI when calculating symbol versions. + +4.3.1. Reserving space and replacing members +============================================ + +Space is typically reserved for later use by appending integer types, or +arrays, to the end of the data structure, but any type can be used. Each +reserved member needs a unique name, but as the actual purpose is usually +not known at the time the space is reserved, for convenience, names that +start with `__kabi_` are left out when calculating symbol versions:: + + struct s { + long a; + long __kabi_reserved_0; /* reserved for future use */ + }; + +The reserved space can be taken into use by wrapping the member in a +union, which includes the original type and the replacement member:: + + struct s { + long a; + union { + long __kabi_reserved_0; /* original type */ + struct b b; /* replaced field */ + }; + }; + +If the `__kabi_` naming scheme was used when reserving space, the name +of the first member of the union must start with `__kabi_reserved`. This +ensures the original type is used when calculating versions, but the name +is again left out. The rest of the union is ignored. + +If we're replacing a member that doesn't follow this naming convention, +we also need to preserve the original name to avoid changing versions, +which we can do by changing the first union member's name to start with +`__kabi_renamed` followed by the original name. + +The examples include `KABI_(RESERVE|USE|REPLACE)*` macros that help +simplify the process and also ensure the replacement member is correctly +aligned and its size won't exceed the reserved space. + +4.3.2. Hiding members +===================== + +Predicting which structures will require changes during the support +timeframe isn't always possible, in which case one might have to resort +to placing new members into existing alignment holes:: + + struct s { + int a; + /* a 4-byte alignment hole */ + unsigned long b; + }; + + +While this won't change the size of the data structure, one needs to +be able to hide the added members from symbol versioning. Similarly +to reserved fields, this can be accomplished by wrapping the added +member to a union where one of the fields has a name starting with +`__kabi_ignored`:: + + struct s { + int a; + union { + char __kabi_ignored_0; + int n; + }; + unsigned long b; + }; + +With **--stable**, both versions produce the same symbol version. diff --git a/Documentation/kbuild/index.rst b/Documentation/kbuild/index.rst index cee2f99f734b..e82af05cd652 100644 --- a/Documentation/kbuild/index.rst +++ b/Documentation/kbuild/index.rst @@ -21,6 +21,7 @@ Kernel Build System reproducible-builds gcc-plugins llvm + gendwarfksyms .. only:: subproject and html diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst index 17c9f920f03d..3388a10f2dcc 100644 --- a/Documentation/kbuild/kbuild.rst +++ b/Documentation/kbuild/kbuild.rst @@ -91,6 +91,17 @@ HOSTRUSTFLAGS ------------- Additional flags to be passed to $(HOSTRUSTC) when building host programs. +PROCMACROLDFLAGS +---------------- +Flags to be passed when linking Rust proc macros. Since proc macros are loaded +by rustc at build time, they must be linked in a way that is compatible with +the rustc toolchain being used. + +For instance, it can be useful when rustc uses a different C library than +the one the user wants to use for host programs. + +If unset, it defaults to the flags passed when linking host programs. + HOSTLDFLAGS ----------- Additional flags to be passed when linking host programs. diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst index 101de236cd0c..a42f00d8cb90 100644 --- a/Documentation/kbuild/modules.rst +++ b/Documentation/kbuild/modules.rst @@ -423,6 +423,26 @@ Symbols From the Kernel (vmlinux + modules) 1) It lists all exported symbols from vmlinux and all modules. 2) It lists the CRC if CONFIG_MODVERSIONS is enabled. +Version Information Formats +--------------------------- + + Exported symbols have information stored in __ksymtab or __ksymtab_gpl + sections. Symbol names and namespaces are stored in __ksymtab_strings, + using a format similar to the string table used for ELF. If + CONFIG_MODVERSIONS is enabled, the CRCs corresponding to exported + symbols will be added to the __kcrctab or __kcrctab_gpl. + + If CONFIG_BASIC_MODVERSIONS is enabled (default with + CONFIG_MODVERSIONS), imported symbols will have their symbol name and + CRC stored in the __versions section of the importing module. This + mode only supports symbols of length up to 64 bytes. + + If CONFIG_EXTENDED_MODVERSIONS is enabled (required to enable both + CONFIG_MODVERSIONS and CONFIG_RUST at the same time), imported symbols + will have their symbol name recorded in the __version_ext_names + section as a series of concatenated, null-terminated strings. CRCs for + these symbols will be recorded in the __version_ext_crcs section. + Symbols and External Modules ---------------------------- diff --git a/Documentation/leds/index.rst b/Documentation/leds/index.rst index 3ade16c18328..0ab0a2128a11 100644 --- a/Documentation/leds/index.rst +++ b/Documentation/leds/index.rst @@ -28,4 +28,5 @@ LEDs leds-mlxcpld leds-mt6370-rgb leds-sc27xx + leds-st1202.rst leds-qcom-lpg diff --git a/Documentation/leds/leds-st1202.rst b/Documentation/leds/leds-st1202.rst new file mode 100644 index 000000000000..1a09fbfcedcf --- /dev/null +++ b/Documentation/leds/leds-st1202.rst @@ -0,0 +1,34 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================================ +Kernel driver for STMicroelectronics LED1202 +============================================ + +/sys/class/leds//hw_pattern +-------------------------------- + +Specify a hardware pattern for the ST1202 LED. The LED controller +implements 12 low-side current generators with independent dimming +control. Internal volatile memory allows the user to store up to 8 +different patterns. Each pattern is a particular output configuration +in terms of PWM duty-cycle and duration (ms). + +To be compatible with the hardware pattern format, maximum 8 tuples of +brightness (PWM) and duration must be written to hw_pattern. + +- Min pattern duration: 22 ms +- Max pattern duration: 5660 ms + +The format of the hardware pattern values should be: +"brightness duration brightness duration ..." + +/sys/class/leds//repeat +---------------------------- + +Specify a pattern repeat number, which is common for all channels. +Default is 1; negative numbers and 0 are invalid. + +This file will always return the originally written repeat number. + +When the 255 value is written to it, all patterns will repeat +indefinitely. diff --git a/Documentation/mm/damon/design.rst b/Documentation/mm/damon/design.rst index f9c50525bdbf..e28c6a1b40ae 100644 --- a/Documentation/mm/damon/design.rst +++ b/Documentation/mm/damon/design.rst @@ -203,6 +203,8 @@ This scheme, however, cannot preserve the quality of the output if the assumption is not guaranteed. +.. _damon_design_adaptive_regions_adjustment: + Adaptive Regions Adjustment ~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -264,6 +266,61 @@ tracepoints. For more details, please refer to the documentations for respectively. +.. _damon_design_monitoring_params_tuning_guide: + +Monitoring Parameters Tuning Guide +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +In short, set ``aggregation interval`` to capture meaningful amount of accesses +for the purpose. The amount of accesses can be measured using ``nr_accesses`` +and ``age`` of regions in the aggregated monitoring results snapshot. The +default value of the interval, ``100ms``, turns out to be too short in many +cases. Set ``sampling interval`` proportional to ``aggregation interval``. By +default, ``1/20`` is recommended as the ratio. + +``Aggregation interval`` should be set as the time interval that the workload +can make an amount of accesses for the monitoring purpose, within the interval. +If the interval is too short, only small number of accesses are captured. As a +result, the monitoring results look everything is samely accessed only rarely. +For many purposes, that would be useless. If it is too long, however, the time +to converge regions with the :ref:`regions adjustment mechanism +` can be too long, depending on the +time scale of the given purpose. This could happen if the workload is actually +making only rare accesses but the user thinks the amount of accesses for the +monitoring purpose too high. For such cases, the target amount of access to +capture per ``aggregation interval`` should carefully reconsidered. Also, note +that the captured amount of accesses is represented with not only +``nr_accesses``, but also ``age``. For example, even if every region on the +monitoring results show zero ``nr_accesses``, regions could still be +distinguished using ``age`` values as the recency information. + +Hence the optimum value of ``aggregation interval`` depends on the access +intensiveness of the workload. The user should tune the interval based on the +amount of access that captured on each aggregated snapshot of the monitoring +results. + +Note that the default value of the interval is 100 milliseconds, which is too +short in many cases, especially on large systems. + +``Sampling interval`` defines the resolution of each aggregation. If it is set +too large, monitoring results will look like every region was samely rarely +accessed, or samely frequently accessed. That is, regions become +undistinguishable based on access pattern, and therefore the results will be +useless in many use cases. If ``sampling interval`` is too small, it will not +degrade the resolution, but will increase the monitoring overhead. If it is +appropriate enough to provide a resolution of the monitoring results that +sufficient for the given purpose, it shouldn't be unnecessarily further +lowered. It is recommended to be set proportional to ``aggregation interval``. +By default, the ratio is set as ``1/20``, and it is still recommended. + +Refer to below documents for an example tuning based on the above guide. + +.. toctree:: + :maxdepth: 1 + + monitoring_intervals_tuning_example + + .. _damon_design_damos: Operation Schemes @@ -504,9 +561,34 @@ have a list of latency-critical processes. To let users optimize DAMOS schemes with such special knowledge, DAMOS provides a feature called DAMOS filters. The feature allows users to set an arbitrary -number of filters for each scheme. Each filter specifies the type of target -memory, and whether it should exclude the memory of the type (filter-out), or -all except the memory of the type (filter-in). +number of filters for each scheme. Each filter specifies + +- a type of memory (``type``), +- whether it is for the memory of the type or all except the type + (``matching``), and +- whether it is to allow (include) or reject (exclude) applying + the scheme's action to the memory (``allow``). + +When multiple filters are installed, each filter is evaluated in the installed +order. If a part of memory is matched to one of the filter, next filters are +ignored. If the memory passes through the filters evaluation stage because it +is not matched to any of the filters, applying the scheme's action to it is +allowed, same to the behavior when no filter exists. + +For example, let's assume 1) a filter for allowing anonymous pages and 2) +another filter for rejecting young pages are installed in the order. If a page +of a region that eligible to apply the scheme's action is an anonymous page, +the scheme's action will be applied to the page regardless of whether it is +young or not, since it matches with the first allow-filter. If the page is +not anonymous but young, the scheme's action will not be applied, since the +second reject-filter blocks it. If the page is neither anonymous nor young, +the page will pass through the filters evaluation stage since there is no +matching filter, and the action will be applied to the page. + +Note that the action can equally be applied to memory that either explicitly +filter-allowed or filters evaluation stage passed. It means that installing +allow-filters at the end of the list makes no practical change but only +filters-checking overhead. For efficient handling of filters, some types of filters are handled by the core layer, while others are handled by operations set. In the latter case, @@ -516,7 +598,7 @@ filter are not counted as the scheme has tried to the region. In contrast, if a memory regions is filtered by an operations set layer-handled filter, it is counted as the scheme has tried. This difference affects the statistics. -Below types of filters are currently supported. +Below ``type`` of filters are currently supported. - anonymous page - Applied to pages that containing data that not stored in files. @@ -539,6 +621,60 @@ To know how user-space can set the watermarks via :ref:`DAMON sysfs interface `, refer to :ref:`filters ` part of the documentation. +.. _damon_design_damos_stat: + +Statistics +~~~~~~~~~~ + +The statistics of DAMOS behaviors that designed to help monitoring, tuning and +debugging of DAMOS. + +DAMOS accounts below statistics for each scheme, from the beginning of the +scheme's execution. + +- ``nr_tried``: Total number of regions that the scheme is tried to be applied. +- ``sz_trtied``: Total size of regions that the scheme is tried to be applied. +- ``sz_ops_filter_passed``: Total bytes that passed operations set + layer-handled DAMOS filters. +- ``nr_applied``: Total number of regions that the scheme is applied. +- ``sz_applied``: Total size of regions that the scheme is applied. +- ``qt_exceeds``: Total number of times the quota of the scheme has exceeded. + +"A scheme is tried to be applied to a region" means DAMOS core logic determined +the region is eligible to apply the scheme's :ref:`action +`. The :ref:`access pattern +`, :ref:`quotas +`, :ref:`watermarks +`, and :ref:`filters +` that handled on core logic could affect this. +The core logic will only ask the underlying :ref:`operation set +` to do apply the action to the region, so whether the +action is really applied or not is unclear. That's why it is called "tried". + +"A scheme is applied to a region" means the :ref:`operation set +` has applied the action to at least a part of the +region. The :ref:`filters ` that handled by the +operation set, and the types of the :ref:`action ` +and the pages of the region can affect this. For example, if a filter is set +to exclude anonymous pages and the region has only anonymous pages, or if the +action is ``pageout`` while all pages of the region are unreclaimable, applying +the action to the region will fail. + +To know how user-space can read the stats via :ref:`DAMON sysfs interface +`, refer to :ref:s`stats ` part of the +documentation. + +Regions Walking +~~~~~~~~~~~~~~~ + +DAMOS feature allowing users access each region that a DAMOS action has just +applied. Using this feature, DAMON :ref:`API ` allows users +access full properties of the regions including the access monitoring results +and amount of the region's internal memory that passed the DAMOS filters. +:ref:`DAMON sysfs interface ` also allows users read the data +via special :ref:`files `. + +.. _damon_design_api: Application Programming Interface --------------------------------- @@ -573,15 +709,11 @@ General Purpose User Interface Modules DAMON modules that provide user space ABIs for general purpose DAMON usage in runtime. -DAMON user interface modules, namely 'DAMON sysfs interface' and 'DAMON debugfs -interface' are DAMON API user kernel modules that provide ABIs to the -user-space. Please note that DAMON debugfs interface is currently deprecated. - -Like many other ABIs, the modules create files on sysfs and debugfs, allow -users to specify their requests to and get the answers from DAMON by writing to -and reading from the files. As a response to such I/O, DAMON user interface -modules control DAMON and retrieve the results as user requested via the DAMON -API, and return the results to the user-space. +Like many other ABIs, the modules create files on pseudo file systems like +'sysfs', allow users to specify their requests to and get the answers from +DAMON by writing to and reading from the files. As a response to such I/O, +DAMON user interface modules control DAMON and retrieve the results as user +requested via the DAMON API, and return the results to the user-space. The ABIs are designed to be used for user space applications development, rather than human beings' fingers. Human users are recommended to use such @@ -590,8 +722,9 @@ Github (https://github.com/damonitor/damo), Pypi (https://pypistats.org/packages/damo), and Fedora (https://packages.fedoraproject.org/pkgs/python-damo/damo/). -Please refer to the ABI :doc:`document ` for -details of the interfaces. +Currently, one module for this type, namely 'DAMON sysfs interface' is +available. Please refer to the ABI :ref:`doc ` for details of +the interfaces. Special-Purpose Access-aware Kernel Modules @@ -599,8 +732,8 @@ Special-Purpose Access-aware Kernel Modules DAMON modules that provide user space ABI for specific purpose DAMON usage. -DAMON sysfs/debugfs user interfaces are for full control of all DAMON features -in runtime. For each special-purpose system-wide data access-aware system +DAMON user interface modules are for full control of all DAMON features in +runtime. For each special-purpose system-wide data access-aware system operations such as proactive reclamation or LRU lists balancing, the interfaces could be simplified by removing unnecessary knobs for the specific purpose, and extended for boot-time and even compile time control. Default values of DAMON diff --git a/Documentation/mm/damon/monitoring_intervals_tuning_example.rst b/Documentation/mm/damon/monitoring_intervals_tuning_example.rst new file mode 100644 index 000000000000..334a854efb40 --- /dev/null +++ b/Documentation/mm/damon/monitoring_intervals_tuning_example.rst @@ -0,0 +1,247 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================================= +DAMON Moniting Interval Parameters Tuning Example +================================================= + +DAMON's monitoring parameters need tuning based on given workload and the +monitoring purpose. There is a :ref:`tuning guide +` for that. This document +provides an example tuning based on the guide. + +Setup +===== + +For below example, DAMON of Linux kernel v6.11 and `damo +`_ (DAMON user-space tool) v2.5.9 was used to +monitor and visualize access patterns on the physical address space of a system +running a real-world server workload. + +5ms/100ms intervals: Too Short Interval +======================================= + +Let's start by capturing the access pattern snapshot on the physical address +space of the system using DAMON, with the default interval parameters (5 +milliseconds and 100 milliseconds for the sampling and the aggregation +intervals, respectively). Wait ten minutes between the start of DAMON and +the capturing of the snapshot, to show a meaningful time-wise access patterns. +:: + + # damo start + # sleep 600 + # damo record --snapshot 0 1 + # damo stop + +Then, list the DAMON-found regions of different access patterns, sorted by the +"access temperature". "Access temperature" is a metric representing the +access-hotness of a region. It is calculated as a weighted sum of the access +frequency and the age of the region. If the access frequency is 0 %, the +temperature is multipled by minus one. That is, if a region is not accessed, +it gets minus temperature and it gets lower as not accessed for longer time. +The sorting is in temperature-ascendint order, so the region at the top of the +list is the coldest, and the one at the bottom is the hottest one. :: + + # damo report access --sort_regions_by temperature + 0 addr 16.052 GiB size 5.985 GiB access 0 % age 5.900 s # coldest + 1 addr 22.037 GiB size 6.029 GiB access 0 % age 5.300 s + 2 addr 28.065 GiB size 6.045 GiB access 0 % age 5.200 s + 3 addr 10.069 GiB size 5.983 GiB access 0 % age 4.500 s + 4 addr 4.000 GiB size 6.069 GiB access 0 % age 4.400 s + 5 addr 62.008 GiB size 3.992 GiB access 0 % age 3.700 s + 6 addr 56.795 GiB size 5.213 GiB access 0 % age 3.300 s + 7 addr 39.393 GiB size 6.096 GiB access 0 % age 2.800 s + 8 addr 50.782 GiB size 6.012 GiB access 0 % age 2.800 s + 9 addr 34.111 GiB size 5.282 GiB access 0 % age 2.300 s + 10 addr 45.489 GiB size 5.293 GiB access 0 % age 1.800 s # hottest + total size: 62.000 GiB + +The list shows not seemingly hot regions, and only minimum access pattern +diversity. Every region has zero access frequency. The number of region is +10, which is the default ``min_nr_regions value``. Size of each region is also +nearly idential. We can suspect this is because “adaptive regions adjustment” +mechanism was not well working. As the guide suggested, we can get relative +hotness of regions using ``age`` as the recency information. That would be +better than nothing, but given the fact that the longest age is only about 6 +seconds while we waited about ten minuts, it is unclear how useful this will +be. + +The temperature ranges to total size of regions of each range histogram +visualization of the results also shows no interesting distribution pattern. :: + + # damo report access --style temperature-sz-hist + + [-,590,000,000, -,549,000,000) 5.985 GiB |********** | + [-,549,000,000, -,508,000,000) 12.074 GiB |********************| + [-,508,000,000, -,467,000,000) 0 B | | + [-,467,000,000, -,426,000,000) 12.052 GiB |********************| + [-,426,000,000, -,385,000,000) 0 B | | + [-,385,000,000, -,344,000,000) 3.992 GiB |******* | + [-,344,000,000, -,303,000,000) 5.213 GiB |********* | + [-,303,000,000, -,262,000,000) 12.109 GiB |********************| + [-,262,000,000, -,221,000,000) 5.282 GiB |********* | + [-,221,000,000, -,180,000,000) 0 B | | + [-,180,000,000, -,139,000,000) 5.293 GiB |********* | + total size: 62.000 GiB + +In short, the parameters provide poor quality monitoring results for hot +regions detection. According to the :ref:`guide +`, this is due to the too short +aggregation interval. + +100ms/2s intervals: Starts Showing Small Hot Regions +==================================================== + +Following the guide, increase the interval 20 times (100 milliseocnds and 2 +seconds for sampling and aggregation intervals, respectively). :: + + # damo start -s 100ms -a 2s + # sleep 600 + # damo record --snapshot 0 1 + # damo stop + # damo report access --sort_regions_by temperature + 0 addr 10.180 GiB size 6.117 GiB access 0 % age 7 m 8 s # coldest + 1 addr 49.275 GiB size 6.195 GiB access 0 % age 6 m 14 s + 2 addr 62.421 GiB size 3.579 GiB access 0 % age 6 m 4 s + 3 addr 40.154 GiB size 6.127 GiB access 0 % age 5 m 40 s + 4 addr 16.296 GiB size 6.182 GiB access 0 % age 5 m 32 s + 5 addr 34.254 GiB size 5.899 GiB access 0 % age 5 m 24 s + 6 addr 46.281 GiB size 2.995 GiB access 0 % age 5 m 20 s + 7 addr 28.420 GiB size 5.835 GiB access 0 % age 5 m 6 s + 8 addr 4.000 GiB size 6.180 GiB access 0 % age 4 m 16 s + 9 addr 22.478 GiB size 5.942 GiB access 0 % age 3 m 58 s + 10 addr 55.470 GiB size 915.645 MiB access 0 % age 3 m 6 s + 11 addr 56.364 GiB size 6.056 GiB access 0 % age 2 m 8 s + 12 addr 56.364 GiB size 4.000 KiB access 95 % age 16 s + 13 addr 49.275 GiB size 4.000 KiB access 100 % age 8 m 24 s # hottest + total size: 62.000 GiB + # damo report access --style temperature-sz-hist + + [-42,800,000,000, -33,479,999,000) 22.018 GiB |***************** | + [-33,479,999,000, -24,159,998,000) 27.090 GiB |********************| + [-24,159,998,000, -14,839,997,000) 6.836 GiB |****** | + [-14,839,997,000, -5,519,996,000) 6.056 GiB |***** | + [-5,519,996,000, 3,800,005,000) 4.000 KiB |* | + [3,800,005,000, 13,120,006,000) 0 B | | + [13,120,006,000, 22,440,007,000) 0 B | | + [22,440,007,000, 31,760,008,000) 0 B | | + [31,760,008,000, 41,080,009,000) 0 B | | + [41,080,009,000, 50,400,010,000) 0 B | | + [50,400,010,000, 59,720,011,000) 4.000 KiB |* | + total size: 62.000 GiB + +DAMON found two distinct 4 KiB regions that pretty hot. The regions are also +well aged. The hottest 4 KiB region was keeping the access frequency for about +8 minutes, and the coldest region was keeping no access for about 7 minutes. +The distribution on the histogram also looks like having a pattern. + +Especially, the finding of the 4 KiB regions among the 62 GiB total memory +shows DAMON’s adaptive regions adjustment is working as designed. + +Still the number of regions is close to the ``min_nr_regions``, and sizes of +cold regions are similar, though. Apparently it is improved, but it still has +rooms to improve. + +400ms/8s intervals: Pretty Improved Results +=========================================== + +Increase the intervals four times (400 milliseconds and 8 seconds +for sampling and aggregation intervals, respectively). :: + + # damo start -s 400ms -a 8s + # sleep 600 + # damo record --snapshot 0 1 + # damo stop + # damo report access --sort_regions_by temperature + 0 addr 64.492 GiB size 1.508 GiB access 0 % age 6 m 48 s # coldest + 1 addr 21.749 GiB size 5.674 GiB access 0 % age 6 m 8 s + 2 addr 27.422 GiB size 5.801 GiB access 0 % age 6 m + 3 addr 49.431 GiB size 8.675 GiB access 0 % age 5 m 28 s + 4 addr 33.223 GiB size 5.645 GiB access 0 % age 5 m 12 s + 5 addr 58.321 GiB size 6.170 GiB access 0 % age 5 m 4 s + [...] + 25 addr 6.615 GiB size 297.531 MiB access 15 % age 0 ns + 26 addr 9.513 GiB size 12.000 KiB access 20 % age 0 ns + 27 addr 9.511 GiB size 108.000 KiB access 25 % age 0 ns + 28 addr 9.513 GiB size 20.000 KiB access 25 % age 0 ns + 29 addr 9.511 GiB size 12.000 KiB access 30 % age 0 ns + 30 addr 9.520 GiB size 4.000 KiB access 40 % age 0 ns + [...] + 41 addr 9.520 GiB size 4.000 KiB access 80 % age 56 s + 42 addr 9.511 GiB size 12.000 KiB access 100 % age 6 m 16 s + 43 addr 58.321 GiB size 4.000 KiB access 100 % age 6 m 24 s + 44 addr 9.512 GiB size 4.000 KiB access 100 % age 6 m 48 s + 45 addr 58.106 GiB size 4.000 KiB access 100 % age 6 m 48 s # hottest + total size: 62.000 GiB + # damo report access --style temperature-sz-hist + + [-40,800,000,000, -32,639,999,000) 21.657 GiB |********************| + [-32,639,999,000, -24,479,998,000) 17.938 GiB |***************** | + [-24,479,998,000, -16,319,997,000) 16.885 GiB |**************** | + [-16,319,997,000, -8,159,996,000) 586.879 MiB |* | + [-8,159,996,000, 5,000) 4.946 GiB |***** | + [5,000, 8,160,006,000) 260.000 KiB |* | + [8,160,006,000, 16,320,007,000) 0 B | | + [16,320,007,000, 24,480,008,000) 0 B | | + [24,480,008,000, 32,640,009,000) 0 B | | + [32,640,009,000, 40,800,010,000) 16.000 KiB |* | + [40,800,010,000, 48,960,011,000) 8.000 KiB |* | + total size: 62.000 GiB + +The number of regions having different access patterns has significantly +increased. Size of each region is also more varied. Total size of non-zero +access frequency regions is also significantly increased. Maybe this is already +good enough to make some meaningful memory management efficieny changes. + +800ms/16s intervals: Another bias +================================= + +Further double the intervals (800 milliseconds and 16 seconds for sampling +and aggregation intervals, respectively). The results is more improved for the +hot regions detection, but starts looking degrading cold regions detection. :: + + # damo start -s 800ms -a 16s + # sleep 600 + # damo record --snapshot 0 1 + # damo stop + # damo report access --sort_regions_by temperature + 0 addr 64.781 GiB size 1.219 GiB access 0 % age 4 m 48 s + 1 addr 24.505 GiB size 2.475 GiB access 0 % age 4 m 16 s + 2 addr 26.980 GiB size 504.273 MiB access 0 % age 4 m + 3 addr 29.443 GiB size 2.462 GiB access 0 % age 4 m + 4 addr 37.264 GiB size 5.645 GiB access 0 % age 4 m + 5 addr 31.905 GiB size 5.359 GiB access 0 % age 3 m 44 s + [...] + 20 addr 8.711 GiB size 40.000 KiB access 5 % age 2 m 40 s + 21 addr 27.473 GiB size 1.970 GiB access 5 % age 4 m + 22 addr 48.185 GiB size 4.625 GiB access 5 % age 4 m + 23 addr 47.304 GiB size 902.117 MiB access 10 % age 4 m + 24 addr 8.711 GiB size 4.000 KiB access 100 % age 4 m + 25 addr 20.793 GiB size 3.713 GiB access 5 % age 4 m 16 s + 26 addr 8.773 GiB size 4.000 KiB access 100 % age 4 m 16 s + total size: 62.000 GiB + # damo report access --style temperature-sz-hist + + [-28,800,000,000, -23,359,999,000) 12.294 GiB |***************** | + [-23,359,999,000, -17,919,998,000) 9.753 GiB |************* | + [-17,919,998,000, -12,479,997,000) 15.131 GiB |********************| + [-12,479,997,000, -7,039,996,000) 0 B | | + [-7,039,996,000, -1,599,995,000) 7.506 GiB |********** | + [-1,599,995,000, 3,840,006,000) 6.127 GiB |********* | + [3,840,006,000, 9,280,007,000) 0 B | | + [9,280,007,000, 14,720,008,000) 136.000 KiB |* | + [14,720,008,000, 20,160,009,000) 40.000 KiB |* | + [20,160,009,000, 25,600,010,000) 11.188 GiB |*************** | + [25,600,010,000, 31,040,011,000) 4.000 KiB |* | + total size: 62.000 GiB + +It found more non-zero access frequency regions. The number of regions is still +much higher than the ``min_nr_regions``, but it is reduced from that of the +previous setup. And apparently the distribution seems bit biased to hot +regions. + +Conclusion +========== + +With the above experimental tuning results, we can conclude the theory and the +guide makes sense to at least this workload, and could be applied to similar +cases. diff --git a/Documentation/mm/physical_memory.rst b/Documentation/mm/physical_memory.rst index 531e73b003dd..71fd4a6acf42 100644 --- a/Documentation/mm/physical_memory.rst +++ b/Documentation/mm/physical_memory.rst @@ -33,7 +33,7 @@ The entire physical address space is partitioned into one or more blocks called zones which represent ranges within memory. These ranges are usually determined by architectural constraints for accessing the physical memory. The memory range within a node that corresponds to a particular zone is -described by a ``struct zone``, typedeffed to ``zone_t``. Each zone has +described by a ``struct zone``. Each zone has one of the types described below. * ``ZONE_DMA`` and ``ZONE_DMA32`` historically represented memory suitable for diff --git a/Documentation/mm/process_addrs.rst b/Documentation/mm/process_addrs.rst index e8618fbc62c9..81417fa2ed20 100644 --- a/Documentation/mm/process_addrs.rst +++ b/Documentation/mm/process_addrs.rst @@ -3,3 +3,857 @@ ================= Process Addresses ================= + +.. toctree:: + :maxdepth: 3 + + +Userland memory ranges are tracked by the kernel via Virtual Memory Areas or +'VMA's of type :c:struct:`!struct vm_area_struct`. + +Each VMA describes a virtually contiguous memory range with identical +attributes, each described by a :c:struct:`!struct vm_area_struct` +object. Userland access outside of VMAs is invalid except in the case where an +adjacent stack VMA could be extended to contain the accessed address. + +All VMAs are contained within one and only one virtual address space, described +by a :c:struct:`!struct mm_struct` object which is referenced by all tasks (that is, +threads) which share the virtual address space. We refer to this as the +:c:struct:`!mm`. + +Each mm object contains a maple tree data structure which describes all VMAs +within the virtual address space. + +.. note:: An exception to this is the 'gate' VMA which is provided by + architectures which use :c:struct:`!vsyscall` and is a global static + object which does not belong to any specific mm. + +------- +Locking +------- + +The kernel is designed to be highly scalable against concurrent read operations +on VMA **metadata** so a complicated set of locks are required to ensure memory +corruption does not occur. + +.. note:: Locking VMAs for their metadata does not have any impact on the memory + they describe nor the page tables that map them. + +Terminology +----------- + +* **mmap locks** - Each MM has a read/write semaphore :c:member:`!mmap_lock` + which locks at a process address space granularity which can be acquired via + :c:func:`!mmap_read_lock`, :c:func:`!mmap_write_lock` and variants. +* **VMA locks** - The VMA lock is at VMA granularity (of course) which behaves + as a read/write semaphore in practice. A VMA read lock is obtained via + :c:func:`!lock_vma_under_rcu` (and unlocked via :c:func:`!vma_end_read`) and a + write lock via :c:func:`!vma_start_write` (all VMA write locks are unlocked + automatically when the mmap write lock is released). To take a VMA write lock + you **must** have already acquired an :c:func:`!mmap_write_lock`. +* **rmap locks** - When trying to access VMAs through the reverse mapping via a + :c:struct:`!struct address_space` or :c:struct:`!struct anon_vma` object + (reachable from a folio via :c:member:`!folio->mapping`). VMAs must be stabilised via + :c:func:`!anon_vma_[try]lock_read` or :c:func:`!anon_vma_[try]lock_write` for + anonymous memory and :c:func:`!i_mmap_[try]lock_read` or + :c:func:`!i_mmap_[try]lock_write` for file-backed memory. We refer to these + locks as the reverse mapping locks, or 'rmap locks' for brevity. + +We discuss page table locks separately in the dedicated section below. + +The first thing **any** of these locks achieve is to **stabilise** the VMA +within the MM tree. That is, guaranteeing that the VMA object will not be +deleted from under you nor modified (except for some specific fields +described below). + +Stabilising a VMA also keeps the address space described by it around. + +Lock usage +---------- + +If you want to **read** VMA metadata fields or just keep the VMA stable, you +must do one of the following: + +* Obtain an mmap read lock at the MM granularity via :c:func:`!mmap_read_lock` (or a + suitable variant), unlocking it with a matching :c:func:`!mmap_read_unlock` when + you're done with the VMA, *or* +* Try to obtain a VMA read lock via :c:func:`!lock_vma_under_rcu`. This tries to + acquire the lock atomically so might fail, in which case fall-back logic is + required to instead obtain an mmap read lock if this returns :c:macro:`!NULL`, + *or* +* Acquire an rmap lock before traversing the locked interval tree (whether + anonymous or file-backed) to obtain the required VMA. + +If you want to **write** VMA metadata fields, then things vary depending on the +field (we explore each VMA field in detail below). For the majority you must: + +* Obtain an mmap write lock at the MM granularity via :c:func:`!mmap_write_lock` (or a + suitable variant), unlocking it with a matching :c:func:`!mmap_write_unlock` when + you're done with the VMA, *and* +* Obtain a VMA write lock via :c:func:`!vma_start_write` for each VMA you wish to + modify, which will be released automatically when :c:func:`!mmap_write_unlock` is + called. +* If you want to be able to write to **any** field, you must also hide the VMA + from the reverse mapping by obtaining an **rmap write lock**. + +VMA locks are special in that you must obtain an mmap **write** lock **first** +in order to obtain a VMA **write** lock. A VMA **read** lock however can be +obtained without any other lock (:c:func:`!lock_vma_under_rcu` will acquire then +release an RCU lock to lookup the VMA for you). + +This constrains the impact of writers on readers, as a writer can interact with +one VMA while a reader interacts with another simultaneously. + +.. note:: The primary users of VMA read locks are page fault handlers, which + means that without a VMA write lock, page faults will run concurrent with + whatever you are doing. + +Examining all valid lock states: + +.. table:: + + ========= ======== ========= ======= ===== =========== ========== + mmap lock VMA lock rmap lock Stable? Read? Write most? Write all? + ========= ======== ========= ======= ===== =========== ========== + \- \- \- N N N N + \- R \- Y Y N N + \- \- R/W Y Y N N + R/W \-/R \-/R/W Y Y N N + W W \-/R Y Y Y N + W W W Y Y Y Y + ========= ======== ========= ======= ===== =========== ========== + +.. warning:: While it's possible to obtain a VMA lock while holding an mmap read lock, + attempting to do the reverse is invalid as it can result in deadlock - if + another task already holds an mmap write lock and attempts to acquire a VMA + write lock that will deadlock on the VMA read lock. + +All of these locks behave as read/write semaphores in practice, so you can +obtain either a read or a write lock for each of these. + +.. note:: Generally speaking, a read/write semaphore is a class of lock which + permits concurrent readers. However a write lock can only be obtained + once all readers have left the critical region (and pending readers + made to wait). + + This renders read locks on a read/write semaphore concurrent with other + readers and write locks exclusive against all others holding the semaphore. + +VMA fields +^^^^^^^^^^ + +We can subdivide :c:struct:`!struct vm_area_struct` fields by their purpose, which makes it +easier to explore their locking characteristics: + +.. note:: We exclude VMA lock-specific fields here to avoid confusion, as these + are in effect an internal implementation detail. + +.. table:: Virtual layout fields + + ===================== ======================================== =========== + Field Description Write lock + ===================== ======================================== =========== + :c:member:`!vm_start` Inclusive start virtual address of range mmap write, + VMA describes. VMA write, + rmap write. + :c:member:`!vm_end` Exclusive end virtual address of range mmap write, + VMA describes. VMA write, + rmap write. + :c:member:`!vm_pgoff` Describes the page offset into the file, mmap write, + the original page offset within the VMA write, + virtual address space (prior to any rmap write. + :c:func:`!mremap`), or PFN if a PFN map + and the architecture does not support + :c:macro:`!CONFIG_ARCH_HAS_PTE_SPECIAL`. + ===================== ======================================== =========== + +These fields describes the size, start and end of the VMA, and as such cannot be +modified without first being hidden from the reverse mapping since these fields +are used to locate VMAs within the reverse mapping interval trees. + +.. table:: Core fields + + ============================ ======================================== ========================= + Field Description Write lock + ============================ ======================================== ========================= + :c:member:`!vm_mm` Containing mm_struct. None - written once on + initial map. + :c:member:`!vm_page_prot` Architecture-specific page table mmap write, VMA write. + protection bits determined from VMA + flags. + :c:member:`!vm_flags` Read-only access to VMA flags describing N/A + attributes of the VMA, in union with + private writable + :c:member:`!__vm_flags`. + :c:member:`!__vm_flags` Private, writable access to VMA flags mmap write, VMA write. + field, updated by + :c:func:`!vm_flags_*` functions. + :c:member:`!vm_file` If the VMA is file-backed, points to a None - written once on + struct file object describing the initial map. + underlying file, if anonymous then + :c:macro:`!NULL`. + :c:member:`!vm_ops` If the VMA is file-backed, then either None - Written once on + the driver or file-system provides a initial map by + :c:struct:`!struct vm_operations_struct` :c:func:`!f_ops->mmap()`. + object describing callbacks to be + invoked on VMA lifetime events. + :c:member:`!vm_private_data` A :c:member:`!void *` field for Handled by driver. + driver-specific metadata. + ============================ ======================================== ========================= + +These are the core fields which describe the MM the VMA belongs to and its attributes. + +.. table:: Config-specific fields + + ================================= ===================== ======================================== =============== + Field Configuration option Description Write lock + ================================= ===================== ======================================== =============== + :c:member:`!anon_name` CONFIG_ANON_VMA_NAME A field for storing a mmap write, + :c:struct:`!struct anon_vma_name` VMA write. + object providing a name for anonymous + mappings, or :c:macro:`!NULL` if none + is set or the VMA is file-backed. The + underlying object is reference counted + and can be shared across multiple VMAs + for scalability. + :c:member:`!swap_readahead_info` CONFIG_SWAP Metadata used by the swap mechanism mmap read, + to perform readahead. This field is swap-specific + accessed atomically. lock. + :c:member:`!vm_policy` CONFIG_NUMA :c:type:`!mempolicy` object which mmap write, + describes the NUMA behaviour of the VMA write. + VMA. The underlying object is reference + counted. + :c:member:`!numab_state` CONFIG_NUMA_BALANCING :c:type:`!vma_numab_state` object which mmap read, + describes the current state of numab-specific + NUMA balancing in relation to this VMA. lock. + Updated under mmap read lock by + :c:func:`!task_numa_work`. + :c:member:`!vm_userfaultfd_ctx` CONFIG_USERFAULTFD Userfaultfd context wrapper object of mmap write, + type :c:type:`!vm_userfaultfd_ctx`, VMA write. + either of zero size if userfaultfd is + disabled, or containing a pointer + to an underlying + :c:type:`!userfaultfd_ctx` object which + describes userfaultfd metadata. + ================================= ===================== ======================================== =============== + +These fields are present or not depending on whether the relevant kernel +configuration option is set. + +.. table:: Reverse mapping fields + + =================================== ========================================= ============================ + Field Description Write lock + =================================== ========================================= ============================ + :c:member:`!shared.rb` A red/black tree node used, if the mmap write, VMA write, + mapping is file-backed, to place the VMA i_mmap write. + in the + :c:member:`!struct address_space->i_mmap` + red/black interval tree. + :c:member:`!shared.rb_subtree_last` Metadata used for management of the mmap write, VMA write, + interval tree if the VMA is file-backed. i_mmap write. + :c:member:`!anon_vma_chain` List of pointers to both forked/CoW’d mmap read, anon_vma write. + :c:type:`!anon_vma` objects and + :c:member:`!vma->anon_vma` if it is + non-:c:macro:`!NULL`. + :c:member:`!anon_vma` :c:type:`!anon_vma` object used by When :c:macro:`NULL` and + anonymous folios mapped exclusively to setting non-:c:macro:`NULL`: + this VMA. Initially set by mmap read, page_table_lock. + :c:func:`!anon_vma_prepare` serialised + by the :c:macro:`!page_table_lock`. This When non-:c:macro:`NULL` and + is set as soon as any page is faulted in. setting :c:macro:`NULL`: + mmap write, VMA write, + anon_vma write. + =================================== ========================================= ============================ + +These fields are used to both place the VMA within the reverse mapping, and for +anonymous mappings, to be able to access both related :c:struct:`!struct anon_vma` objects +and the :c:struct:`!struct anon_vma` in which folios mapped exclusively to this VMA should +reside. + +.. note:: If a file-backed mapping is mapped with :c:macro:`!MAP_PRIVATE` set + then it can be in both the :c:type:`!anon_vma` and :c:type:`!i_mmap` + trees at the same time, so all of these fields might be utilised at + once. + +Page tables +----------- + +We won't speak exhaustively on the subject but broadly speaking, page tables map +virtual addresses to physical ones through a series of page tables, each of +which contain entries with physical addresses for the next page table level +(along with flags), and at the leaf level the physical addresses of the +underlying physical data pages or a special entry such as a swap entry, +migration entry or other special marker. Offsets into these pages are provided +by the virtual address itself. + +In Linux these are divided into five levels - PGD, P4D, PUD, PMD and PTE. Huge +pages might eliminate one or two of these levels, but when this is the case we +typically refer to the leaf level as the PTE level regardless. + +.. note:: In instances where the architecture supports fewer page tables than + five the kernel cleverly 'folds' page table levels, that is stubbing + out functions related to the skipped levels. This allows us to + conceptually act as if there were always five levels, even if the + compiler might, in practice, eliminate any code relating to missing + ones. + +There are four key operations typically performed on page tables: + +1. **Traversing** page tables - Simply reading page tables in order to traverse + them. This only requires that the VMA is kept stable, so a lock which + establishes this suffices for traversal (there are also lockless variants + which eliminate even this requirement, such as :c:func:`!gup_fast`). +2. **Installing** page table mappings - Whether creating a new mapping or + modifying an existing one in such a way as to change its identity. This + requires that the VMA is kept stable via an mmap or VMA lock (explicitly not + rmap locks). +3. **Zapping/unmapping** page table entries - This is what the kernel calls + clearing page table mappings at the leaf level only, whilst leaving all page + tables in place. This is a very common operation in the kernel performed on + file truncation, the :c:macro:`!MADV_DONTNEED` operation via + :c:func:`!madvise`, and others. This is performed by a number of functions + including :c:func:`!unmap_mapping_range` and :c:func:`!unmap_mapping_pages`. + The VMA need only be kept stable for this operation. +4. **Freeing** page tables - When finally the kernel removes page tables from a + userland process (typically via :c:func:`!free_pgtables`) extreme care must + be taken to ensure this is done safely, as this logic finally frees all page + tables in the specified range, ignoring existing leaf entries (it assumes the + caller has both zapped the range and prevented any further faults or + modifications within it). + +.. note:: Modifying mappings for reclaim or migration is performed under rmap + lock as it, like zapping, does not fundamentally modify the identity + of what is being mapped. + +**Traversing** and **zapping** ranges can be performed holding any one of the +locks described in the terminology section above - that is the mmap lock, the +VMA lock or either of the reverse mapping locks. + +That is - as long as you keep the relevant VMA **stable** - you are good to go +ahead and perform these operations on page tables (though internally, kernel +operations that perform writes also acquire internal page table locks to +serialise - see the page table implementation detail section for more details). + +When **installing** page table entries, the mmap or VMA lock must be held to +keep the VMA stable. We explore why this is in the page table locking details +section below. + +.. warning:: Page tables are normally only traversed in regions covered by VMAs. + If you want to traverse page tables in areas that might not be + covered by VMAs, heavier locking is required. + See :c:func:`!walk_page_range_novma` for details. + +**Freeing** page tables is an entirely internal memory management operation and +has special requirements (see the page freeing section below for more details). + +.. warning:: When **freeing** page tables, it must not be possible for VMAs + containing the ranges those page tables map to be accessible via + the reverse mapping. + + The :c:func:`!free_pgtables` function removes the relevant VMAs + from the reverse mappings, but no other VMAs can be permitted to be + accessible and span the specified range. + +Lock ordering +------------- + +As we have multiple locks across the kernel which may or may not be taken at the +same time as explicit mm or VMA locks, we have to be wary of lock inversion, and +the **order** in which locks are acquired and released becomes very important. + +.. note:: Lock inversion occurs when two threads need to acquire multiple locks, + but in doing so inadvertently cause a mutual deadlock. + + For example, consider thread 1 which holds lock A and tries to acquire lock B, + while thread 2 holds lock B and tries to acquire lock A. + + Both threads are now deadlocked on each other. However, had they attempted to + acquire locks in the same order, one would have waited for the other to + complete its work and no deadlock would have occurred. + +The opening comment in :c:macro:`!mm/rmap.c` describes in detail the required +ordering of locks within memory management code: + +.. code-block:: + + inode->i_rwsem (while writing or truncating, not reading or faulting) + mm->mmap_lock + mapping->invalidate_lock (in filemap_fault) + folio_lock + hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) + vma_start_write + mapping->i_mmap_rwsem + anon_vma->rwsem + mm->page_table_lock or pte_lock + swap_lock (in swap_duplicate, swap_info_get) + mmlist_lock (in mmput, drain_mmlist and others) + mapping->private_lock (in block_dirty_folio) + i_pages lock (widely used) + lruvec->lru_lock (in folio_lruvec_lock_irq) + inode->i_lock (in set_page_dirty's __mark_inode_dirty) + bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) + sb_lock (within inode_lock in fs/fs-writeback.c) + i_pages lock (widely used, in set_page_dirty, + in arch-dependent flush_dcache_mmap_lock, + within bdi.wb->list_lock in __sync_single_inode) + +There is also a file-system specific lock ordering comment located at the top of +:c:macro:`!mm/filemap.c`: + +.. code-block:: + + ->i_mmap_rwsem (truncate_pagecache) + ->private_lock (__free_pte->block_dirty_folio) + ->swap_lock (exclusive_swap_page, others) + ->i_pages lock + + ->i_rwsem + ->invalidate_lock (acquired by fs in truncate path) + ->i_mmap_rwsem (truncate->unmap_mapping_range) + + ->mmap_lock + ->i_mmap_rwsem + ->page_table_lock or pte_lock (various, mainly in memory.c) + ->i_pages lock (arch-dependent flush_dcache_mmap_lock) + + ->mmap_lock + ->invalidate_lock (filemap_fault) + ->lock_page (filemap_fault, access_process_vm) + + ->i_rwsem (generic_perform_write) + ->mmap_lock (fault_in_readable->do_page_fault) + + bdi->wb.list_lock + sb_lock (fs/fs-writeback.c) + ->i_pages lock (__sync_single_inode) + + ->i_mmap_rwsem + ->anon_vma.lock (vma_merge) + + ->anon_vma.lock + ->page_table_lock or pte_lock (anon_vma_prepare and various) + + ->page_table_lock or pte_lock + ->swap_lock (try_to_unmap_one) + ->private_lock (try_to_unmap_one) + ->i_pages lock (try_to_unmap_one) + ->lruvec->lru_lock (follow_page_mask->mark_page_accessed) + ->lruvec->lru_lock (check_pte_range->folio_isolate_lru) + ->private_lock (folio_remove_rmap_pte->set_page_dirty) + ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) + bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) + ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) + bdi.wb->list_lock (zap_pte_range->set_page_dirty) + ->inode->i_lock (zap_pte_range->set_page_dirty) + ->private_lock (zap_pte_range->block_dirty_folio) + +Please check the current state of these comments which may have changed since +the time of writing of this document. + +------------------------------ +Locking Implementation Details +------------------------------ + +.. warning:: Locking rules for PTE-level page tables are very different from + locking rules for page tables at other levels. + +Page table locking details +-------------------------- + +In addition to the locks described in the terminology section above, we have +additional locks dedicated to page tables: + +* **Higher level page table locks** - Higher level page tables, that is PGD, P4D + and PUD each make use of the process address space granularity + :c:member:`!mm->page_table_lock` lock when modified. + +* **Fine-grained page table locks** - PMDs and PTEs each have fine-grained locks + either kept within the folios describing the page tables or allocated + separated and pointed at by the folios if :c:macro:`!ALLOC_SPLIT_PTLOCKS` is + set. The PMD spin lock is obtained via :c:func:`!pmd_lock`, however PTEs are + mapped into higher memory (if a 32-bit system) and carefully locked via + :c:func:`!pte_offset_map_lock`. + +These locks represent the minimum required to interact with each page table +level, but there are further requirements. + +Importantly, note that on a **traversal** of page tables, sometimes no such +locks are taken. However, at the PTE level, at least concurrent page table +deletion must be prevented (using RCU) and the page table must be mapped into +high memory, see below. + +Whether care is taken on reading the page table entries depends on the +architecture, see the section on atomicity below. + +Locking rules +^^^^^^^^^^^^^ + +We establish basic locking rules when interacting with page tables: + +* When changing a page table entry the page table lock for that page table + **must** be held, except if you can safely assume nobody can access the page + tables concurrently (such as on invocation of :c:func:`!free_pgtables`). +* Reads from and writes to page table entries must be *appropriately* + atomic. See the section on atomicity below for details. +* Populating previously empty entries requires that the mmap or VMA locks are + held (read or write), doing so with only rmap locks would be dangerous (see + the warning below). +* As mentioned previously, zapping can be performed while simply keeping the VMA + stable, that is holding any one of the mmap, VMA or rmap locks. + +.. warning:: Populating previously empty entries is dangerous as, when unmapping + VMAs, :c:func:`!vms_clear_ptes` has a window of time between + zapping (via :c:func:`!unmap_vmas`) and freeing page tables (via + :c:func:`!free_pgtables`), where the VMA is still visible in the + rmap tree. :c:func:`!free_pgtables` assumes that the zap has + already been performed and removes PTEs unconditionally (along with + all other page tables in the freed range), so installing new PTE + entries could leak memory and also cause other unexpected and + dangerous behaviour. + +There are additional rules applicable when moving page tables, which we discuss +in the section on this topic below. + +PTE-level page tables are different from page tables at other levels, and there +are extra requirements for accessing them: + +* On 32-bit architectures, they may be in high memory (meaning they need to be + mapped into kernel memory to be accessible). +* When empty, they can be unlinked and RCU-freed while holding an mmap lock or + rmap lock for reading in combination with the PTE and PMD page table locks. + In particular, this happens in :c:func:`!retract_page_tables` when handling + :c:macro:`!MADV_COLLAPSE`. + So accessing PTE-level page tables requires at least holding an RCU read lock; + but that only suffices for readers that can tolerate racing with concurrent + page table updates such that an empty PTE is observed (in a page table that + has actually already been detached and marked for RCU freeing) while another + new page table has been installed in the same location and filled with + entries. Writers normally need to take the PTE lock and revalidate that the + PMD entry still refers to the same PTE-level page table. + If the writer does not care whether it is the same PTE-level page table, it + can take the PMD lock and revalidate that the contents of pmd entry still meet + the requirements. In particular, this also happens in :c:func:`!retract_page_tables` + when handling :c:macro:`!MADV_COLLAPSE`. + +To access PTE-level page tables, a helper like :c:func:`!pte_offset_map_lock` or +:c:func:`!pte_offset_map` can be used depending on stability requirements. +These map the page table into kernel memory if required, take the RCU lock, and +depending on variant, may also look up or acquire the PTE lock. +See the comment on :c:func:`!__pte_offset_map_lock`. + +Atomicity +^^^^^^^^^ + +Regardless of page table locks, the MMU hardware concurrently updates accessed +and dirty bits (perhaps more, depending on architecture). Additionally, page +table traversal operations in parallel (though holding the VMA stable) and +functionality like GUP-fast locklessly traverses (that is reads) page tables, +without even keeping the VMA stable at all. + +When performing a page table traversal and keeping the VMA stable, whether a +read must be performed once and only once or not depends on the architecture +(for instance x86-64 does not require any special precautions). + +If a write is being performed, or if a read informs whether a write takes place +(on an installation of a page table entry say, for instance in +:c:func:`!__pud_install`), special care must always be taken. In these cases we +can never assume that page table locks give us entirely exclusive access, and +must retrieve page table entries once and only once. + +If we are reading page table entries, then we need only ensure that the compiler +does not rearrange our loads. This is achieved via :c:func:`!pXXp_get` +functions - :c:func:`!pgdp_get`, :c:func:`!p4dp_get`, :c:func:`!pudp_get`, +:c:func:`!pmdp_get`, and :c:func:`!ptep_get`. + +Each of these uses :c:func:`!READ_ONCE` to guarantee that the compiler reads +the page table entry only once. + +However, if we wish to manipulate an existing page table entry and care about +the previously stored data, we must go further and use an hardware atomic +operation as, for example, in :c:func:`!ptep_get_and_clear`. + +Equally, operations that do not rely on the VMA being held stable, such as +GUP-fast (see :c:func:`!gup_fast` and its various page table level handlers like +:c:func:`!gup_fast_pte_range`), must very carefully interact with page table +entries, using functions such as :c:func:`!ptep_get_lockless` and equivalent for +higher level page table levels. + +Writes to page table entries must also be appropriately atomic, as established +by :c:func:`!set_pXX` functions - :c:func:`!set_pgd`, :c:func:`!set_p4d`, +:c:func:`!set_pud`, :c:func:`!set_pmd`, and :c:func:`!set_pte`. + +Equally functions which clear page table entries must be appropriately atomic, +as in :c:func:`!pXX_clear` functions - :c:func:`!pgd_clear`, +:c:func:`!p4d_clear`, :c:func:`!pud_clear`, :c:func:`!pmd_clear`, and +:c:func:`!pte_clear`. + +Page table installation +^^^^^^^^^^^^^^^^^^^^^^^ + +Page table installation is performed with the VMA held stable explicitly by an +mmap or VMA lock in read or write mode (see the warning in the locking rules +section for details as to why). + +When allocating a P4D, PUD or PMD and setting the relevant entry in the above +PGD, P4D or PUD, the :c:member:`!mm->page_table_lock` must be held. This is +acquired in :c:func:`!__p4d_alloc`, :c:func:`!__pud_alloc` and +:c:func:`!__pmd_alloc` respectively. + +.. note:: :c:func:`!__pmd_alloc` actually invokes :c:func:`!pud_lock` and + :c:func:`!pud_lockptr` in turn, however at the time of writing it ultimately + references the :c:member:`!mm->page_table_lock`. + +Allocating a PTE will either use the :c:member:`!mm->page_table_lock` or, if +:c:macro:`!USE_SPLIT_PMD_PTLOCKS` is defined, a lock embedded in the PMD +physical page metadata in the form of a :c:struct:`!struct ptdesc`, acquired by +:c:func:`!pmd_ptdesc` called from :c:func:`!pmd_lock` and ultimately +:c:func:`!__pte_alloc`. + +Finally, modifying the contents of the PTE requires special treatment, as the +PTE page table lock must be acquired whenever we want stable and exclusive +access to entries contained within a PTE, especially when we wish to modify +them. + +This is performed via :c:func:`!pte_offset_map_lock` which carefully checks to +ensure that the PTE hasn't changed from under us, ultimately invoking +:c:func:`!pte_lockptr` to obtain a spin lock at PTE granularity contained within +the :c:struct:`!struct ptdesc` associated with the physical PTE page. The lock +must be released via :c:func:`!pte_unmap_unlock`. + +.. note:: There are some variants on this, such as + :c:func:`!pte_offset_map_rw_nolock` when we know we hold the PTE stable but + for brevity we do not explore this. See the comment for + :c:func:`!__pte_offset_map_lock` for more details. + +When modifying data in ranges we typically only wish to allocate higher page +tables as necessary, using these locks to avoid races or overwriting anything, +and set/clear data at the PTE level as required (for instance when page faulting +or zapping). + +A typical pattern taken when traversing page table entries to install a new +mapping is to optimistically determine whether the page table entry in the table +above is empty, if so, only then acquiring the page table lock and checking +again to see if it was allocated underneath us. + +This allows for a traversal with page table locks only being taken when +required. An example of this is :c:func:`!__pud_alloc`. + +At the leaf page table, that is the PTE, we can't entirely rely on this pattern +as we have separate PMD and PTE locks and a THP collapse for instance might have +eliminated the PMD entry as well as the PTE from under us. + +This is why :c:func:`!__pte_offset_map_lock` locklessly retrieves the PMD entry +for the PTE, carefully checking it is as expected, before acquiring the +PTE-specific lock, and then *again* checking that the PMD entry is as expected. + +If a THP collapse (or similar) were to occur then the lock on both pages would +be acquired, so we can ensure this is prevented while the PTE lock is held. + +Installing entries this way ensures mutual exclusion on write. + +Page table freeing +^^^^^^^^^^^^^^^^^^ + +Tearing down page tables themselves is something that requires significant +care. There must be no way that page tables designated for removal can be +traversed or referenced by concurrent tasks. + +It is insufficient to simply hold an mmap write lock and VMA lock (which will +prevent racing faults, and rmap operations), as a file-backed mapping can be +truncated under the :c:struct:`!struct address_space->i_mmap_rwsem` alone. + +As a result, no VMA which can be accessed via the reverse mapping (either +through the :c:struct:`!struct anon_vma->rb_root` or the :c:member:`!struct +address_space->i_mmap` interval trees) can have its page tables torn down. + +The operation is typically performed via :c:func:`!free_pgtables`, which assumes +either the mmap write lock has been taken (as specified by its +:c:member:`!mm_wr_locked` parameter), or that the VMA is already unreachable. + +It carefully removes the VMA from all reverse mappings, however it's important +that no new ones overlap these or any route remain to permit access to addresses +within the range whose page tables are being torn down. + +Additionally, it assumes that a zap has already been performed and steps have +been taken to ensure that no further page table entries can be installed between +the zap and the invocation of :c:func:`!free_pgtables`. + +Since it is assumed that all such steps have been taken, page table entries are +cleared without page table locks (in the :c:func:`!pgd_clear`, :c:func:`!p4d_clear`, +:c:func:`!pud_clear`, and :c:func:`!pmd_clear` functions. + +.. note:: It is possible for leaf page tables to be torn down independent of + the page tables above it as is done by + :c:func:`!retract_page_tables`, which is performed under the i_mmap + read lock, PMD, and PTE page table locks, without this level of care. + +Page table moving +^^^^^^^^^^^^^^^^^ + +Some functions manipulate page table levels above PMD (that is PUD, P4D and PGD +page tables). Most notable of these is :c:func:`!mremap`, which is capable of +moving higher level page tables. + +In these instances, it is required that **all** locks are taken, that is +the mmap lock, the VMA lock and the relevant rmap locks. + +You can observe this in the :c:func:`!mremap` implementation in the functions +:c:func:`!take_rmap_locks` and :c:func:`!drop_rmap_locks` which perform the rmap +side of lock acquisition, invoked ultimately by :c:func:`!move_page_tables`. + +VMA lock internals +------------------ + +Overview +^^^^^^^^ + +VMA read locking is entirely optimistic - if the lock is contended or a competing +write has started, then we do not obtain a read lock. + +A VMA **read** lock is obtained by :c:func:`!lock_vma_under_rcu`, which first +calls :c:func:`!rcu_read_lock` to ensure that the VMA is looked up in an RCU +critical section, then attempts to VMA lock it via :c:func:`!vma_start_read`, +before releasing the RCU lock via :c:func:`!rcu_read_unlock`. + +VMA read locks hold the read lock on the :c:member:`!vma->vm_lock` semaphore for +their duration and the caller of :c:func:`!lock_vma_under_rcu` must release it +via :c:func:`!vma_end_read`. + +VMA **write** locks are acquired via :c:func:`!vma_start_write` in instances where a +VMA is about to be modified, unlike :c:func:`!vma_start_read` the lock is always +acquired. An mmap write lock **must** be held for the duration of the VMA write +lock, releasing or downgrading the mmap write lock also releases the VMA write +lock so there is no :c:func:`!vma_end_write` function. + +Note that a semaphore write lock is not held across a VMA lock. Rather, a +sequence number is used for serialisation, and the write semaphore is only +acquired at the point of write lock to update this. + +This ensures the semantics we require - VMA write locks provide exclusive write +access to the VMA. + +Implementation details +^^^^^^^^^^^^^^^^^^^^^^ + +The VMA lock mechanism is designed to be a lightweight means of avoiding the use +of the heavily contended mmap lock. It is implemented using a combination of a +read/write semaphore and sequence numbers belonging to the containing +:c:struct:`!struct mm_struct` and the VMA. + +Read locks are acquired via :c:func:`!vma_start_read`, which is an optimistic +operation, i.e. it tries to acquire a read lock but returns false if it is +unable to do so. At the end of the read operation, :c:func:`!vma_end_read` is +called to release the VMA read lock. + +Invoking :c:func:`!vma_start_read` requires that :c:func:`!rcu_read_lock` has +been called first, establishing that we are in an RCU critical section upon VMA +read lock acquisition. Once acquired, the RCU lock can be released as it is only +required for lookup. This is abstracted by :c:func:`!lock_vma_under_rcu` which +is the interface a user should use. + +Writing requires the mmap to be write-locked and the VMA lock to be acquired via +:c:func:`!vma_start_write`, however the write lock is released by the termination or +downgrade of the mmap write lock so no :c:func:`!vma_end_write` is required. + +All this is achieved by the use of per-mm and per-VMA sequence counts, which are +used in order to reduce complexity, especially for operations which write-lock +multiple VMAs at once. + +If the mm sequence count, :c:member:`!mm->mm_lock_seq` is equal to the VMA +sequence count :c:member:`!vma->vm_lock_seq` then the VMA is write-locked. If +they differ, then it is not. + +Each time the mmap write lock is released in :c:func:`!mmap_write_unlock` or +:c:func:`!mmap_write_downgrade`, :c:func:`!vma_end_write_all` is invoked which +also increments :c:member:`!mm->mm_lock_seq` via +:c:func:`!mm_lock_seqcount_end`. + +This way, we ensure that, regardless of the VMA's sequence number, a write lock +is never incorrectly indicated and that when we release an mmap write lock we +efficiently release **all** VMA write locks contained within the mmap at the +same time. + +Since the mmap write lock is exclusive against others who hold it, the automatic +release of any VMA locks on its release makes sense, as you would never want to +keep VMAs locked across entirely separate write operations. It also maintains +correct lock ordering. + +Each time a VMA read lock is acquired, we acquire a read lock on the +:c:member:`!vma->vm_lock` read/write semaphore and hold it, while checking that +the sequence count of the VMA does not match that of the mm. + +If it does, the read lock fails. If it does not, we hold the lock, excluding +writers, but permitting other readers, who will also obtain this lock under RCU. + +Importantly, maple tree operations performed in :c:func:`!lock_vma_under_rcu` +are also RCU safe, so the whole read lock operation is guaranteed to function +correctly. + +On the write side, we acquire a write lock on the :c:member:`!vma->vm_lock` +read/write semaphore, before setting the VMA's sequence number under this lock, +also simultaneously holding the mmap write lock. + +This way, if any read locks are in effect, :c:func:`!vma_start_write` will sleep +until these are finished and mutual exclusion is achieved. + +After setting the VMA's sequence number, the lock is released, avoiding +complexity with a long-term held write lock. + +This clever combination of a read/write semaphore and sequence count allows for +fast RCU-based per-VMA lock acquisition (especially on page fault, though +utilised elsewhere) with minimal complexity around lock ordering. + +mmap write lock downgrading +--------------------------- + +When an mmap write lock is held one has exclusive access to resources within the +mmap (with the usual caveats about requiring VMA write locks to avoid races with +tasks holding VMA read locks). + +It is then possible to **downgrade** from a write lock to a read lock via +:c:func:`!mmap_write_downgrade` which, similar to :c:func:`!mmap_write_unlock`, +implicitly terminates all VMA write locks via :c:func:`!vma_end_write_all`, but +importantly does not relinquish the mmap lock while downgrading, therefore +keeping the locked virtual address space stable. + +An interesting consequence of this is that downgraded locks are exclusive +against any other task possessing a downgraded lock (since a racing task would +have to acquire a write lock first to downgrade it, and the downgraded lock +prevents a new write lock from being obtained until the original lock is +released). + +For clarity, we map read (R)/downgraded write (D)/write (W) locks against one +another showing which locks exclude the others: + +.. list-table:: Lock exclusivity + :widths: 5 5 5 5 + :header-rows: 1 + :stub-columns: 1 + + * - + - R + - D + - W + * - R + - N + - N + - Y + * - D + - N + - Y + - Y + * - W + - Y + - Y + - Y + +Here a Y indicates the locks in the matching row/column are mutually exclusive, +and N indicates that they are not. + +Stack expansion +--------------- + +Stack expansion throws up additional complexities in that we cannot permit there +to be racing page faults, as a result we invoke :c:func:`!vma_start_write` to +prevent this in :c:func:`!expand_downwards` or :c:func:`!expand_upwards`. diff --git a/Documentation/mm/split_page_table_lock.rst b/Documentation/mm/split_page_table_lock.rst index 581446d4a4eb..8e1ceb0a6619 100644 --- a/Documentation/mm/split_page_table_lock.rst +++ b/Documentation/mm/split_page_table_lock.rst @@ -62,7 +62,7 @@ Support of split page table lock by an architecture =================================================== There's no need in special enabling of PTE split page table lock: everything -required is done by pagetable_pte_ctor() and pagetable_pte_dtor(), which +required is done by pagetable_pte_ctor() and pagetable_dtor(), which must be called on PTE table allocation / freeing. Make sure the architecture doesn't use slab allocator for page table @@ -73,7 +73,7 @@ PMD split lock only makes sense if you have more than two page table levels. PMD split lock enabling requires pagetable_pmd_ctor() call on PMD table -allocation and pagetable_pmd_dtor() on freeing. +allocation and pagetable_dtor() on freeing. Allocation usually happens in pmd_alloc_one(), freeing in pmd_free() and pmd_free_tlb(), but make sure you cover all PMD table allocation / freeing diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index 4f803eaac6d8..9660ffb1ed6a 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -106,6 +106,9 @@ properties: name-prefix: description: For enum the prefix of the values, optional. type: string + enum-cnt-name: + description: Name of the render-max counter enum entry. + type: string # End genetlink-c attribute-sets: diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index 8db0e22fa72c..16380e12cabe 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -117,6 +117,9 @@ properties: name-prefix: description: For enum the prefix of the values, optional. type: string + enum-cnt-name: + description: Name of the render-max counter enum entry. + type: string # End genetlink-c # Start genetlink-legacy members: diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index 914aa1c0a273..1b0772c8e333 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -221,7 +221,7 @@ properties: type: &attr-type description: The netlink attribute type enum: [ unused, pad, flag, binary, bitfield32, - u8, u16, u32, u64, s8, s16, s32, s64, + uint, sint, u8, u16, u32, u64, s8, s16, s32, s64, string, nest, indexed-array, nest-type-value, sub-message ] doc: diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 93369f0eb816..259cb211a338 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -5,6 +5,7 @@ name: ethtool protocol: genetlink-legacy doc: Partial family for Ethtool Netlink. +uapi-header: linux/ethtool_netlink_generated.h definitions: - @@ -12,43 +13,99 @@ definitions: enum-name: type: enum entries: [ vxlan, geneve, vxlan-gpe ] + enum-cnt-name: __ethtool-udp-tunnel-type-cnt + render-max: true - name: stringset type: enum entries: [] + header: linux/ethtool.h # skip rendering, no actual definition - name: header-flags type: flags - entries: [ compact-bitsets, omit-reply, stats ] + name-prefix: ethtool-flag- + doc: common ethtool header flags + entries: + - + name: compact-bitsets + doc: use compact bitsets in reply + - + name: omit-reply + doc: provide optional reply for SET or ACT requests + - + name: stats + doc: request statistics, if supported by the driver - name: module-fw-flash-status type: enum - entries: [ started, in_progress, completed, error ] + doc: plug-in module firmware flashing status + header: linux/ethtool.h + entries: + - + name: started + doc: The firmware flashing process has started. + - + name: in_progress + doc: The firmware flashing process is in progress. + - + name: completed + doc: The firmware flashing process was completed successfully. + - + name: error + doc: The firmware flashing process was stopped due to an error. - name: c33-pse-ext-state - enum-name: + doc: "groups of PSE extended states functions. IEEE 802.3-2022 33.2.4.4 Variables" type: enum name-prefix: ethtool-c33-pse-ext-state- + header: linux/ethtool.h entries: - - none - - error-condition - - mr-mps-valid - - mr-pse-enable - - option-detect-ted - - option-vport-lim - - ovld-detected - - power-not-available - - short-detected + - + name: none + doc: none + - + name: error-condition + doc: Group of error_condition states + - + name: mr-mps-valid + doc: Group of mr_mps_valid states + - + name: mr-pse-enable + doc: Group of mr_pse_enable states + - + name: option-detect-ted + doc: Group of option_detect_ted states + - + name: option-vport-lim + doc: Group of option_vport_lim states + - + name: ovld-detected + doc: Group of ovld_detected states + - + name: power-not-available + doc: Group of power_not_available states + - + name: short-detected + doc: Group of short_detected states - name: phy-upstream-type enum-name: type: enum entries: [ mac, phy ] + - + name: tcp-data-split + type: enum + entries: [ unknown, disabled, enabled ] attribute-sets: - name: header + attr-cnt-name: __ethtool-a-header-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: dev-index type: u32 @@ -65,7 +122,12 @@ attribute-sets: - name: bitset-bit + attr-cnt-name: __ethtool-a-bitset-bit-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: index type: u32 @@ -77,7 +139,12 @@ attribute-sets: type: flag - name: bitset-bits + attr-cnt-name: __ethtool-a-bitset-bits-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: bit type: nest @@ -85,7 +152,12 @@ attribute-sets: nested-attributes: bitset-bit - name: bitset + attr-cnt-name: __ethtool-a-bitset-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: nomask type: flag @@ -104,7 +176,12 @@ attribute-sets: type: binary - name: string + attr-cnt-name: __ethtool-a-string-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: index type: u32 @@ -113,7 +190,16 @@ attribute-sets: type: string - name: strings + attr-cnt-name: __ethtool-a-strings-cnt attributes: + - + name: unspec + type: unused + value: 0 + - + name: unspec + type: unused + value: 0 - name: string type: nest @@ -121,7 +207,12 @@ attribute-sets: nested-attributes: string - name: stringset + attr-cnt-name: __ethtool-a-stringset-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: id type: u32 @@ -135,7 +226,12 @@ attribute-sets: nested-attributes: strings - name: stringsets + attr-cnt-name: __ethtool-a-stringsets-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: stringset type: nest @@ -143,7 +239,12 @@ attribute-sets: nested-attributes: stringset - name: strset + attr-cnt-name: __ethtool-a-strset-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -158,7 +259,12 @@ attribute-sets: - name: privflags + attr-cnt-name: __ethtool-a-privflags-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -170,7 +276,12 @@ attribute-sets: - name: rings + attr-cnt-name: __ethtool-a-rings-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -205,6 +316,7 @@ attribute-sets: - name: tcp-data-split type: u8 + enum: tcp-data-split - name: cqe-size type: u32 @@ -220,34 +332,57 @@ attribute-sets: - name: tx-push-buf-len-max type: u32 + - + name: hds-thresh + type: u32 + - + name: hds-thresh-max + type: u32 - name: mm-stat + attr-cnt-name: __ethtool-a-mm-stat-cnt + doc: MAC Merge (802.3) attributes: + - + name: unspec + type: unused + value: 0 - name: pad type: pad - name: reassembly-errors + doc: aMACMergeFrameAssErrorCount type: u64 - name: smd-errors + doc: aMACMergeFrameSmdErrorCount type: u64 - name: reassembly-ok + doc: aMACMergeFrameAssOkCount type: u64 - name: rx-frag-count + doc: aMACMergeFragCountRx type: u64 - name: tx-frag-count + doc: aMACMergeFragCountTx type: u64 - name: hold-count + doc: aMACMergeHoldCount type: u64 - name: mm + attr-cnt-name: __ethtool-a-mm-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -285,7 +420,12 @@ attribute-sets: nested-attributes: mm-stat - name: linkinfo + attr-cnt-name: __ethtool-a-linkinfo-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -307,7 +447,12 @@ attribute-sets: type: u8 - name: linkmodes + attr-cnt-name: __ethtool-a-linkmodes-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -343,7 +488,12 @@ attribute-sets: type: u8 - name: linkstate + attr-cnt-name: __ethtool-a-linkstate-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -368,7 +518,12 @@ attribute-sets: type: u32 - name: debug + attr-cnt-name: __ethtool-a-debug-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -379,7 +534,12 @@ attribute-sets: nested-attributes: bitset - name: wol + attr-cnt-name: __ethtool-a-wol-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -393,7 +553,12 @@ attribute-sets: type: binary - name: features + attr-cnt-name: __ethtool-a-features-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -416,7 +581,12 @@ attribute-sets: nested-attributes: bitset - name: channels + attr-cnt-name: __ethtool-a-channels-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -448,7 +618,12 @@ attribute-sets: - name: irq-moderation + attr-cnt-name: __ethtool-a-irq-moderation-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: usec type: u32 @@ -460,7 +635,12 @@ attribute-sets: type: u32 - name: profile + attr-cnt-name: __ethtool-a-profile-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: irq-moderation type: nest @@ -468,7 +648,12 @@ attribute-sets: nested-attributes: irq-moderation - name: coalesce + attr-cnt-name: __ethtool-a-coalesce-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -565,7 +750,12 @@ attribute-sets: - name: pause-stat + attr-cnt-name: __ethtool-a-pause-stat-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: pad type: pad @@ -577,7 +767,12 @@ attribute-sets: type: u64 - name: pause + attr-cnt-name: __ethtool-a-pause-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -600,7 +795,12 @@ attribute-sets: type: u32 - name: eee + attr-cnt-name: __ethtool-a-eee-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -627,7 +827,12 @@ attribute-sets: type: u32 - name: ts-stat + attr-cnt-name: __ethtool-a-ts-stat-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: tx-pkts type: uint @@ -637,9 +842,31 @@ attribute-sets: - name: tx-err type: uint + - + name: tx-onestep-pkts-unconfirmed + type: uint + - + name: ts-hwtstamp-provider + attr-cnt-name: __ethtool-a-ts-hwtstamp-provider-cnt + attributes: + - + name: unspec + type: unused + value: 0 + - + name: index + type: u32 + - + name: qualifier + type: u32 - name: tsinfo + attr-cnt-name: __ethtool-a-tsinfo-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -663,21 +890,38 @@ attribute-sets: name: stats type: nest nested-attributes: ts-stat + - + name: hwtstamp-provider + type: nest + nested-attributes: ts-hwtstamp-provider - name: cable-result + attr-cnt-name: __ethtool-a-cable-result-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: pair + doc: ETHTOOL_A_CABLE_PAIR type: u8 - name: code + doc: ETHTOOL_A_CABLE_RESULT_CODE type: u8 - name: src + doc: ETHTOOL_A_CABLE_INF_SRC type: u32 - name: cable-fault-length + attr-cnt-name: __ethtool-a-cable-fault-length-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: pair type: u8 @@ -689,7 +933,12 @@ attribute-sets: type: u32 - name: cable-nest + attr-cnt-name: __ethtool-a-cable-nest-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: result type: nest @@ -700,20 +949,31 @@ attribute-sets: nested-attributes: cable-fault-length - name: cable-test + attr-cnt-name: __ethtool-a-cable-test-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest nested-attributes: header - name: cable-test-ntf + attr-cnt-name: __ethtool-a-cable-test-ntf-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest nested-attributes: header - name: status + doc: _STARTED/_COMPLETE type: u8 - name: nest @@ -721,7 +981,12 @@ attribute-sets: nested-attributes: cable-nest - name: cable-test-tdr-cfg + attr-cnt-name: __ethtool-a-cable-test-tdr-cfg-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: first type: u32 @@ -736,7 +1001,12 @@ attribute-sets: type: u8 - name: cable-test-tdr-ntf + attr-cnt-name: __ethtool-a-cable-test-tdr-ntf-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -750,7 +1020,12 @@ attribute-sets: nested-attributes: cable-nest - name: cable-test-tdr + attr-cnt-name: __ethtool-a-cable-test-tdr-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -761,7 +1036,12 @@ attribute-sets: nested-attributes: cable-test-tdr-cfg - name: tunnel-udp-entry + attr-cnt-name: __ethtool-a-tunnel-udp-entry-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: port type: u16 @@ -772,7 +1052,12 @@ attribute-sets: enum: udp-tunnel-type - name: tunnel-udp-table + attr-cnt-name: __ethtool-a-tunnel-udp-table-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: size type: u32 @@ -787,14 +1072,24 @@ attribute-sets: nested-attributes: tunnel-udp-entry - name: tunnel-udp + attr-cnt-name: __ethtool-a-tunnel-udp-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: table type: nest nested-attributes: tunnel-udp-table - name: tunnel-info + attr-cnt-name: __ethtool-a-tunnel-info-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -805,7 +1100,12 @@ attribute-sets: nested-attributes: tunnel-udp - name: fec-stat + attr-cnt-name: __ethtool-a-fec-stat-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: pad type: pad @@ -823,7 +1123,12 @@ attribute-sets: sub-type: u64 - name: fec + attr-cnt-name: __ethtool-a-fec-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -844,7 +1149,12 @@ attribute-sets: nested-attributes: fec-stat - name: module-eeprom + attr-cnt-name: __ethtool-a-module-eeprom-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -869,7 +1179,12 @@ attribute-sets: type: binary - name: stats-grp + attr-cnt-name: __ethtool-a-stats-grp-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: pad type: pad @@ -912,7 +1227,12 @@ attribute-sets: name: hist-val - name: stats + attr-cnt-name: __ethtool-a-stats-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: pad type: pad @@ -933,7 +1253,12 @@ attribute-sets: type: u32 - name: phc-vclocks + attr-cnt-name: __ethtool-a-phc-vclocks-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -947,7 +1272,12 @@ attribute-sets: sub-type: s32 - name: module + attr-cnt-name: __ethtool-a-module-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -960,7 +1290,13 @@ attribute-sets: type: u8 - name: c33-pse-pw-limit + attr-cnt-name: __ethtool-a-c33-pse-pw-limit-cnt + attr-max-name: __ethtool-a-c33-pse-pw-limit-max attributes: + - + name: unspec + type: unused + value: 0 - name: min type: u32 @@ -969,7 +1305,12 @@ attribute-sets: type: u32 - name: pse + attr-cnt-name: __ethtool-a-pse-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -1027,7 +1368,12 @@ attribute-sets: nested-attributes: c33-pse-pw-limit - name: rss + attr-cnt-name: __ethtool-a-rss-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -1053,7 +1399,12 @@ attribute-sets: type: u32 - name: plca + attr-cnt-name: __ethtool-a-plca-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -1084,7 +1435,12 @@ attribute-sets: type: u32 - name: module-fw-flash + attr-cnt-name: __ethtool-a-module-fw-flash-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -1110,7 +1466,12 @@ attribute-sets: type: uint - name: phy + attr-cnt-name: __ethtool-a-phy-cnt attributes: + - + name: unspec + type: unused + value: 0 - name: header type: nest @@ -1137,6 +1498,33 @@ attribute-sets: - name: downstream-sfp-name type: string + - + name: tsconfig + attr-cnt-name: __ethtool-a-tsconfig-cnt + attributes: + - + name: unspec + type: unused + value: 0 + - + name: header + type: nest + nested-attributes: header + - + name: hwtstamp-provider + type: nest + nested-attributes: ts-hwtstamp-provider + - + name: tx-types + type: nest + nested-attributes: bitset + - + name: rx-filters + type: nest + nested-attributes: bitset + - + name: hwtstamp-flags + type: u32 operations: enum-model: directional @@ -1398,6 +1786,8 @@ operations: - rx-push - tx-push-buf-len - tx-push-buf-len-max + - hds-thresh + - hds-thresh-max dump: *ring-get-op - name: rings-set @@ -1578,6 +1968,7 @@ operations: request: attributes: - header + - hwtstamp-provider reply: attributes: - header @@ -1586,6 +1977,7 @@ operations: - rx-filters - phc-index - stats + - hwtstamp-provider dump: *tsinfo-get-op - name: cable-test-act @@ -1960,3 +2352,32 @@ operations: name: phy-ntf doc: Notification for change in PHY devices. notify: phy-get + - + name: tsconfig-get + doc: Get hwtstamp config. + + attribute-set: tsconfig + + do: &tsconfig-get-op + request: + attributes: + - header + reply: + attributes: &tsconfig + - header + - hwtstamp-provider + - tx-types + - rx-filters + - hwtstamp-flags + dump: *tsconfig-get-op + - + name: tsconfig-set + doc: Set hwtstamp config. + + attribute-set: tsconfig + + do: + request: + attributes: *tsconfig + reply: + attributes: *tsconfig diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index dc190bf838fe..dfd017780d2f 100644 --- a/Documentation/netlink/specs/mptcp_pm.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -22,65 +22,67 @@ definitions: doc: unused event - name: created - doc: - token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport + doc: >- A new MPTCP connection has been created. It is the good time to allocate memory and send ADD_ADDR if needed. Depending on the traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. + Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, server-side. - name: established - doc: - token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport + doc: >- A MPTCP connection is established (can start new subflows). + Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, server-side. - name: closed - doc: - token + doc: >- A MPTCP connection has stopped. + Attribute: token. - name: announced value: 6 - doc: - token, rem_id, family, daddr4 | daddr6 [, dport] + doc: >- A new address has been announced by the peer. + Attributes: token, rem_id, family, daddr4 | daddr6 [, dport]. - name: removed - doc: - token, rem_id + doc: >- An address has been lost by the peer. + Attributes: token, rem_id. - name: sub-established value: 10 - doc: - token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, backup, if_idx [, error] + doc: >- A new subflow has been established. 'error' should not be set. + Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | + daddr6, sport, dport, backup, if_idx [, error]. - name: sub-closed - doc: - token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, backup, if_idx [, error] + doc: >- A subflow has been closed. An error (copy of sk_err) could be set if an error has been detected for this subflow. + Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | + daddr6, sport, dport, backup, if_idx [, error]. - name: sub-priority value: 13 - doc: - token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, backup, if_idx [, error] + doc: >- The priority of a subflow has changed. 'error' should not be set. + Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | + daddr6, sport, dport, backup, if_idx [, error]. - name: listener-created value: 15 - doc: - family, sport, saddr4 | saddr6 + doc: >- A new PM listener is created. + Attributes: family, sport, saddr4 | saddr6. - name: listener-closed - doc: - family, sport, saddr4 | saddr6 + doc: >- A PM listener is closed. + Attributes: family, sport, saddr4 | saddr6. attribute-sets: - @@ -306,8 +308,8 @@ operations: attributes: - addr - - name: flush-addrs - doc: flush addresses + name: flush-addrs + doc: Flush addresses attribute-set: endpoint dont-validate: [ strict ] flags: [ uns-admin-perm ] @@ -351,7 +353,7 @@ operations: - addr-remote - name: announce - doc: announce new sf + doc: Announce new address attribute-set: attr dont-validate: [ strict ] flags: [ uns-admin-perm ] @@ -362,7 +364,7 @@ operations: - token - name: remove - doc: announce removal + doc: Announce removal attribute-set: attr dont-validate: [ strict ] flags: [ uns-admin-perm ] @@ -373,7 +375,7 @@ operations: - loc-id - name: subflow-create - doc: todo + doc: Create subflow attribute-set: attr dont-validate: [ strict ] flags: [ uns-admin-perm ] @@ -385,7 +387,7 @@ operations: - addr-remote - name: subflow-destroy - doc: todo + doc: Destroy subflow attribute-set: attr dont-validate: [ strict ] flags: [ uns-admin-perm ] diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml index 9ffa13b77dcf..0d492500c7e5 100644 --- a/Documentation/netlink/specs/rt_link.yaml +++ b/Documentation/netlink/specs/rt_link.yaml @@ -1825,6 +1825,48 @@ attribute-sets: - name: erspan-hwid type: u16 + - + name: linkinfo-vti-attrs + name-prefix: ifla-vti- + attributes: + - + name: link + type: u32 + - + name: ikey + type: u32 + - + name: okey + type: u32 + - + name: local + type: binary + display-hint: ipv4 + - + name: remote + type: binary + display-hint: ipv4 + - + name: fwmark + type: u32 + - + name: linkinfo-vti6-attrs + subset-of: linkinfo-vti-attrs + attributes: + - + name: link + - + name: ikey + - + name: okey + - + name: local + display-hint: ipv6 + - + name: remote + display-hint: ipv6 + - + name: fwmark - name: linkinfo-geneve-attrs name-prefix: ifla-geneve- @@ -1941,6 +1983,42 @@ attribute-sets: - name: fwmark type: u32 + - + name: linkinfo-ip6tnl-attrs + subset-of: linkinfo-iptun-attrs + attributes: + - + name: link + - + name: local + display-hint: ipv6 + - + name: remote + display-hint: ipv6 + - + name: ttl + - + name: encap-limit + - + name: flowinfo + - + name: flags + # ip6tnl unlike ipip and sit has 32b flags + type: u32 + - + name: proto + - + name: encap-type + - + name: encap-flags + - + name: encap-sport + - + name: encap-dport + - + name: collect-metadata + - + name: fwmark - name: linkinfo-tun-attrs name-prefix: ifla-tun- @@ -2086,6 +2164,9 @@ attribute-sets: - name: mctp-net type: u32 + - + name: phys-binding + type: u8 - name: stats-attrs name-prefix: ifla-stats- @@ -2166,6 +2247,12 @@ attribute-sets: name: peer-scrub type: u32 enum: netkit-scrub + - + name: headroom + type: u16 + - + name: tailroom + type: u16 sub-messages: - @@ -2192,6 +2279,9 @@ sub-messages: - value: ipip attribute-set: linkinfo-iptun-attrs + - + value: ip6tnl + attribute-set: linkinfo-ip6tnl-attrs - value: sit attribute-set: linkinfo-iptun-attrs @@ -2204,6 +2294,12 @@ sub-messages: - value: vrf attribute-set: linkinfo-vrf-attrs + - + value: vti + attribute-set: linkinfo-vti-attrs + - + value: vti6 + attribute-set: linkinfo-vti6-attrs - value: netkit attribute-set: linkinfo-netkit-attrs diff --git a/Documentation/netlink/specs/rt_route.yaml b/Documentation/netlink/specs/rt_route.yaml index f4368be0caed..a674103e5bc4 100644 --- a/Documentation/netlink/specs/rt_route.yaml +++ b/Documentation/netlink/specs/rt_route.yaml @@ -177,6 +177,11 @@ attribute-sets: - name: rta-nh-id type: u32 + - + name: rta-flowlabel + type: u32 + byte-order: big-endian + display-hint: hex - name: rta-metrics attributes: @@ -260,6 +265,7 @@ operations: - rta-dport - rta-mark - rta-uid + - rta-flowlabel reply: value: 24 attributes: &all-route-attrs @@ -299,6 +305,7 @@ operations: - rta-sport - rta-dport - rta-nh-id + - rta-flowlabel dump: request: value: 26 diff --git a/Documentation/netlink/specs/rt_rule.yaml b/Documentation/netlink/specs/rt_rule.yaml index 03a8eef7952e..a9debac3058a 100644 --- a/Documentation/netlink/specs/rt_rule.yaml +++ b/Documentation/netlink/specs/rt_rule.yaml @@ -172,6 +172,16 @@ attribute-sets: - name: dscp type: u8 + - + name: flowlabel + type: u32 + byte-order: big-endian + display-hint: hex + - + name: flowlabel-mask + type: u32 + byte-order: big-endian + display-hint: hex operations: enum-model: directional @@ -203,6 +213,8 @@ operations: - sport-range - dport-range - dscp + - flowlabel + - flowlabel-mask - name: newrule-ntf doc: Notify a rule creation diff --git a/Documentation/networking/batman-adv.rst b/Documentation/networking/batman-adv.rst index 8a0dcb1894b4..44b9b5cc0e24 100644 --- a/Documentation/networking/batman-adv.rst +++ b/Documentation/networking/batman-adv.rst @@ -164,5 +164,5 @@ Mailing-list: You can also contact the Authors: -* Marek Lindner +* Marek Lindner * Simon Wunderlich diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index 7c8d22d68682..a4c1291d2561 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -1963,7 +1963,7 @@ obtain its hardware address from the first slave, which might not match the hardware address of the VLAN interfaces (which was ultimately copied from an earlier slave). -There are two methods to insure that the VLAN device operates +There are two methods to ensure that the VLAN device operates with the correct hardware address if all slaves are removed from a bond interface: @@ -2078,7 +2078,7 @@ as an unsolicited ARP reply (because ARP matches replies on an interface basis), and is discarded. The MII monitor is not affected by the state of the routing table. -The solution here is simply to insure that slaves do not have +The solution here is simply to ensure that slaves do not have routes of their own, and if for some reason they must, those routes do not supersede routes of their master. This should generally be the case, but unusual configurations or errant manual or automatic static @@ -2295,7 +2295,7 @@ active-backup: the switches have an ISL and play together well. If the network configuration is such that one switch is specifically a backup switch (e.g., has lower capacity, higher cost, etc), - then the primary option can be used to insure that the + then the primary option can be used to ensure that the preferred link is always used when it is available. broadcast: @@ -2322,7 +2322,7 @@ monitor can provide a higher level of reliability in detecting end to end connectivity failures (which may be caused by the failure of any individual component to pass traffic for any reason). Additionally, the ARP monitor should be configured with multiple targets (at least -one for each switch in the network). This will insure that, +one for each switch in the network). This will ensure that, regardless of which switch is active, the ARP monitor has a suitable target to query. diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst index 62519d38c58b..b018ce346392 100644 --- a/Documentation/networking/can.rst +++ b/Documentation/networking/can.rst @@ -699,10 +699,10 @@ RAW socket option CAN_RAW_JOIN_FILTERS The CAN_RAW socket can set multiple CAN identifier specific filters that lead to multiple filters in the af_can.c filter processing. These filters -are indenpendent from each other which leads to logical OR'ed filters when +are independent from each other which leads to logical OR'ed filters when applied (see :ref:`socketcan-rawfilter`). -This socket option joines the given CAN filters in the way that only CAN +This socket option joins the given CAN filters in the way that only CAN frames are passed to user space that matched *all* given CAN filters. The semantic for the applied filters is therefore changed to a logical AND. diff --git a/Documentation/networking/device_drivers/ethernet/intel/i40e.rst b/Documentation/networking/device_drivers/ethernet/intel/i40e.rst index 4fbaa1a2d674..53d9d5829d69 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/i40e.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/i40e.rst @@ -299,6 +299,18 @@ Use ethtool to view and set link-down-on-close, as follows:: ethtool --show-priv-flags ethX ethtool --set-priv-flags ethX link-down-on-close [on|off] +Setting the mdd-auto-reset-vf Private Flag +------------------------------------------ + +When the mdd-auto-reset-vf private flag is set to "on", the problematic VF will +be automatically reset if a malformed descriptor is detected. If the flag is +set to "off", the problematic VF will be disabled. + +Use ethtool to view and set mdd-auto-reset-vf, as follows:: + + ethtool --show-priv-flags ethX + ethtool --set-priv-flags ethX mdd-auto-reset-vf [on|off] + Viewing Link Messages --------------------- Link messages will not be displayed to the console if the distribution is diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index 456985407475..41618538fc70 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -53,6 +53,9 @@ parameters. * ``smfs`` Software managed flow steering. In SMFS mode, the HW steering entities are created and manage through the driver without firmware intervention. + * ``hmfs`` Hardware managed flow steering. In HMFS mode, the driver + is configuring steering rules directly to the HW using Work Queues with + a special new type of WQE (Work Queue Element). SMFS mode is faster and provides better rule insertion rate compared to default DMFS mode. diff --git a/Documentation/networking/diagnostic/twisted_pair_layer1_diagnostics.rst b/Documentation/networking/diagnostic/twisted_pair_layer1_diagnostics.rst index c9be5cc7e113..079e17effadf 100644 --- a/Documentation/networking/diagnostic/twisted_pair_layer1_diagnostics.rst +++ b/Documentation/networking/diagnostic/twisted_pair_layer1_diagnostics.rst @@ -713,17 +713,23 @@ driver supports reporting such events. - **Monitor Error Counters**: - - While some NIC drivers and PHYs provide error counters, there is no unified - set of PHY-specific counters across all hardware. Additionally, not all - PHYs provide useful information related to errors like CRC errors, frame - drops, or link flaps. Therefore, this step is dependent on the specific - hardware and driver support. + - Use `ethtool -S --all-groups` to retrieve standardized interface + statistics if the driver supports the unified interface: - - **Next Steps**: Use `ethtool -S ` to check if your driver - provides useful error counters. In some cases, counters may provide - information about errors like link flaps or physical layer problems (e.g., - excessive CRC errors), but results can vary significantly depending on the - PHY. + - **Command:** `ethtool -S --all-groups` + + - **Example Output (if supported)**: + + .. code-block:: bash + + phydev-RxFrames: 100391 + phydev-RxErrors: 0 + phydev-TxFrames: 9 + phydev-TxErrors: 0 + + - If the unified interface is not supported, use `ethtool -S ` to + retrieve MAC and PHY counters. Note that non-standardized PHY counter names + vary by driver and must be interpreted accordingly: - **Command:** `ethtool -S ` @@ -740,6 +746,17 @@ driver supports reporting such events. condition) or kernel log messages (e.g., link up/down events) to further diagnose the issue. + - **Compare Counters**: + + - Compare the egress and ingress frame counts reported by the PHY and MAC. + + - A small difference may occur due to sampling rate differences between the + MAC and PHY drivers, or if the PHY and MAC are not always fully + synchronized in their UP or DOWN states. + + - Significant discrepancies indicate potential issues in the data path + between the MAC and PHY. + When All Else Fails... ~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index b25926071ece..3770a2294509 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -237,6 +237,8 @@ Userspace to kernel: ``ETHTOOL_MSG_MM_SET`` set MAC merge layer parameters ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` flash transceiver module firmware ``ETHTOOL_MSG_PHY_GET`` get Ethernet PHY information + ``ETHTOOL_MSG_TSCONFIG_GET`` get hw timestamping configuration + ``ETHTOOL_MSG_TSCONFIG_SET`` set hw timestamping configuration ===================================== ================================= Kernel to userspace: @@ -286,6 +288,8 @@ Kernel to userspace: ``ETHTOOL_MSG_MODULE_FW_FLASH_NTF`` transceiver module flash updates ``ETHTOOL_MSG_PHY_GET_REPLY`` Ethernet PHY information ``ETHTOOL_MSG_PHY_NTF`` Ethernet PHY information change + ``ETHTOOL_MSG_TSCONFIG_GET_REPLY`` hw timestamping configuration + ``ETHTOOL_MSG_TSCONFIG_SET_REPLY`` new hw timestamping configuration ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -895,6 +899,10 @@ Kernel response contents: ``ETHTOOL_A_RINGS_RX_PUSH`` u8 flag of RX Push mode ``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN`` u32 size of TX push buffer ``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX`` u32 max size of TX push buffer + ``ETHTOOL_A_RINGS_HDS_THRESH`` u32 threshold of + header / data split + ``ETHTOOL_A_RINGS_HDS_THRESH_MAX`` u32 max threshold of + header / data split ======================================= ====== =========================== ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with @@ -937,10 +945,12 @@ Request contents: ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` u8 TCP header / data split ``ETHTOOL_A_RINGS_CQE_SIZE`` u32 Size of TX/RX CQE ``ETHTOOL_A_RINGS_TX_PUSH`` u8 flag of TX Push mode ``ETHTOOL_A_RINGS_RX_PUSH`` u8 flag of RX Push mode ``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN`` u32 size of TX push buffer + ``ETHTOOL_A_RINGS_HDS_THRESH`` u32 threshold of header / data split ==================================== ====== =========================== Kernel checks that requested ring sizes do not exceed limits reported by @@ -957,6 +967,10 @@ A bigger CQE can have more receive buffer pointers, and in turn the NIC can transfer a bigger frame from wire. Based on the NIC hardware, the overall completion queue size can be adjusted in the driver if CQE size is modified. +``ETHTOOL_A_RINGS_HDS_THRESH`` specifies the threshold value of +header / data split feature. If a received packet size is larger than this +threshold value, header and data will be split. + CHANNELS_GET ============ @@ -1245,9 +1259,10 @@ Gets timestamping information like ``ETHTOOL_GET_TS_INFO`` ioctl request. Request contents: - ===================================== ====== ========================== - ``ETHTOOL_A_TSINFO_HEADER`` nested request header - ===================================== ====== ========================== + ======================================== ====== ============================ + ``ETHTOOL_A_TSINFO_HEADER`` nested request header + ``ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER`` nested PTP hw clock provider + ======================================== ====== ============================ Kernel response contents: @@ -1266,11 +1281,17 @@ would be empty (no bit set). Additional hardware timestamping statistics response contents: - ===================================== ====== =================================== - ``ETHTOOL_A_TS_STAT_TX_PKTS`` uint Packets with Tx HW timestamps - ``ETHTOOL_A_TS_STAT_TX_LOST`` uint Tx HW timestamp not arrived count - ``ETHTOOL_A_TS_STAT_TX_ERR`` uint HW error request Tx timestamp count - ===================================== ====== =================================== + ================================================== ====== ===================== + ``ETHTOOL_A_TS_STAT_TX_PKTS`` uint Packets with Tx + HW timestamps + ``ETHTOOL_A_TS_STAT_TX_LOST`` uint Tx HW timestamp + not arrived count + ``ETHTOOL_A_TS_STAT_TX_ERR`` uint HW error request + Tx timestamp count + ``ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED`` uint Packets with one-step + HW TX timestamps with + unconfirmed delivery + ================================================== ====== ===================== CABLE_TEST ========== @@ -1611,6 +1632,7 @@ the ``ETHTOOL_A_STATS_GROUPS`` bitset. Currently defined values are: ETHTOOL_STATS_ETH_PHY eth-phy Basic IEEE 802.3 PHY statistics (30.3.2.1.*) ETHTOOL_STATS_ETH_CTRL eth-ctrl Basic IEEE 802.3 MAC Ctrl statistics (30.3.3.*) ETHTOOL_STATS_RMON rmon RMON (RFC 2819) statistics + ETHTOOL_STATS_PHY phy Additional PHY statistics, not defined by IEEE ====================== ======== =============================================== Each group should have a corresponding ``ETHTOOL_A_STATS_GRP`` in the reply. @@ -2243,6 +2265,75 @@ Kernel response contents: When ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` is PHY_UPSTREAM_PHY, the PHY's parent is another PHY. +TSCONFIG_GET +============ + +Retrieves the information about the current hardware timestamping source and +configuration. + +It is similar to the deprecated ``SIOCGHWTSTAMP`` ioctl request. + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_TSCONFIG_HEADER`` nested request header + ==================================== ====== ========================== + +Kernel response contents: + + ======================================== ====== ============================ + ``ETHTOOL_A_TSCONFIG_HEADER`` nested request header + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` nested PTP hw clock provider + ``ETHTOOL_A_TSCONFIG_TX_TYPES`` bitset hwtstamp Tx type + ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` bitset hwtstamp Rx filter + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` u32 hwtstamp flags + ======================================== ====== ============================ + +When set the ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` attribute identifies the +source of the hw timestamping provider. It is composed by +``ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX`` attribute which describe the index of +the PTP device and ``ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER`` which describe +the qualifier of the timestamp. + +When set the ``ETHTOOL_A_TSCONFIG_TX_TYPES``, ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` +and the ``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` attributes identify the Tx +type, the Rx filter and the flags configured for the current hw timestamping +provider. The attributes are propagated to the driver through the following +structure: + +.. kernel-doc:: include/linux/net_tstamp.h + :identifiers: kernel_hwtstamp_config + +TSCONFIG_SET +============ + +Set the information about the current hardware timestamping source and +configuration. + +It is similar to the deprecated ``SIOCSHWTSTAMP`` ioctl request. + +Request contents: + + ======================================== ====== ============================ + ``ETHTOOL_A_TSCONFIG_HEADER`` nested request header + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` nested PTP hw clock provider + ``ETHTOOL_A_TSCONFIG_TX_TYPES`` bitset hwtstamp Tx type + ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` bitset hwtstamp Rx filter + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` u32 hwtstamp flags + ======================================== ====== ============================ + +Kernel response contents: + + ======================================== ====== ============================ + ``ETHTOOL_A_TSCONFIG_HEADER`` nested request header + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` nested PTP hw clock provider + ``ETHTOOL_A_TSCONFIG_TX_TYPES`` bitset hwtstamp Tx type + ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` bitset hwtstamp Rx filter + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` u32 hwtstamp flags + ======================================== ====== ============================ + +For a description of each attribute, see ``TSCONFIG_GET``. + Request translation =================== @@ -2351,4 +2442,6 @@ are netlink only. n/a ``ETHTOOL_MSG_MM_SET`` n/a ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` n/a ``ETHTOOL_MSG_PHY_GET`` + ``SIOCGHWTSTAMP`` ``ETHTOOL_MSG_TSCONFIG_GET`` + ``SIOCSHWTSTAMP`` ``ETHTOOL_MSG_TSCONFIG_SET`` =================================== ===================================== diff --git a/Documentation/networking/ieee802154.rst b/Documentation/networking/ieee802154.rst index c652d383fe10..743c0a80e309 100644 --- a/Documentation/networking/ieee802154.rst +++ b/Documentation/networking/ieee802154.rst @@ -72,7 +72,8 @@ exports a management (e.g. MLME) and data API. possibly with some kinds of acceleration like automatic CRC computation and comparison, automagic ACK handling, address matching, etc. -Those types of devices require different approach to be hooked into Linux kernel. +Each type of device requires a different approach to be hooked into the Linux +kernel. HardMAC ------- @@ -81,10 +82,10 @@ See the header include/net/ieee802154_netdev.h. You have to implement Linux net_device, with .type = ARPHRD_IEEE802154. Data is exchanged with socket family code via plain sk_buffs. On skb reception skb->cb must contain additional info as described in the struct ieee802154_mac_cb. During packet transmission -the skb->cb is used to provide additional data to device's header_ops->create -function. Be aware that this data can be overridden later (when socket code -submits skb to qdisc), so if you need something from that cb later, you should -store info in the skb->data on your own. +the skb->cb is used to provide additional data to the device's +header_ops->create function. Be aware that this data can be overridden later +(when socket code submits skb to qdisc), so if you need something from that cb +later, you should store info in the skb->data on your own. To hook the MLME interface you have to populate the ml_priv field of your net_device with a pointer to struct ieee802154_mlme_ops instance. The fields @@ -94,8 +95,9 @@ All other fields are required. SoftMAC ------- -The MAC is the middle layer in the IEEE 802.15.4 Linux stack. This moment it -provides interface for drivers registration and management of slave interfaces. +The MAC is the middle layer in the IEEE 802.15.4 Linux stack. At the moment, it +provides an interface for driver registration and management of slave +interfaces. NOTE: Currently the only monitor device type is supported - it's IEEE 802.15.4 stack interface for network sniffers (e.g. WireShark). diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 46c178e564b3..058193ed2eeb 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -86,6 +86,7 @@ Contents: netdevices netfilter-sysctl netif-msg + netmem nexthop-group-resilient nf_conntrack-sysctl nf_flowtable diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index dcbb6f6caf6d..363b4950d542 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1000,6 +1000,20 @@ tcp_tw_reuse - INTEGER Default: 2 +tcp_tw_reuse_delay - UNSIGNED INTEGER + The delay in milliseconds before a TIME-WAIT socket can be reused by a + new connection, if TIME-WAIT socket reuse is enabled. The actual reuse + threshold is within [N, N+1] range, where N is the requested delay in + milliseconds, to ensure the delay interval is never shorter than the + configured value. + + This setting contains an assumption about the other TCP timestamp clock + tick interval. It should not be set to a value lower than the peer's + clock tick for PAWS (Protection Against Wrapped Sequence numbers) + mechanism work correctly for the reused connection. + + Default: 1000 (milliseconds) + tcp_window_scaling - BOOLEAN Enable window scaling as defined in RFC1323. diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index 95598c21fc8e..03e1d3610333 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -41,7 +41,7 @@ blackhole_timeout - INTEGER (seconds) MPTCP is re-enabled and will reset to the initial value when the blackhole issue goes away. - 0 to disable the blackhole detection. + 0 to disable the blackhole detection. This is a per-namespace sysctl. Default: 3600 @@ -108,3 +108,19 @@ stale_loss_cnt - INTEGER This is a per-namespace sysctl. Default: 4 + +syn_retrans_before_tcp_fallback - INTEGER + The number of SYN + MP_CAPABLE retransmissions before falling back to + TCP, i.e. dropping the MPTCP options. In other words, if all the packets + are dropped on the way, there will be: + + * The initial SYN with MPTCP support + * This number of SYN retransmitted with MPTCP support + * The next SYN retransmissions will be without MPTCP support + + 0 means the first retransmission will be done without MPTCP options. + >= 128 means that all SYN retransmissions will keep the MPTCP options. A + lower number might increase false-positive MPTCP blackholes detections. + This is a per-namespace sysctl. + + Default: 2 diff --git a/Documentation/networking/multi-pf-netdev.rst b/Documentation/networking/multi-pf-netdev.rst index 2cd25d81aaa7..2f5a5bb3ca9a 100644 --- a/Documentation/networking/multi-pf-netdev.rst +++ b/Documentation/networking/multi-pf-netdev.rst @@ -89,7 +89,7 @@ Observability ============= The relation between PF, irq, napi, and queue can be observed via netlink spec:: - $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump queue-get --json='{"ifindex": 13}' + $ ./tools/net/ynl/pyynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump queue-get --json='{"ifindex": 13}' [{'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'rx'}, {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'rx'}, {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'rx'}, @@ -101,7 +101,7 @@ The relation between PF, irq, napi, and queue can be observed via netlink spec:: {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'tx'}, {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'tx'}] - $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump napi-get --json='{"ifindex": 13}' + $ ./tools/net/ynl/pyynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump napi-get --json='{"ifindex": 13}' [{'id': 543, 'ifindex': 13, 'irq': 42}, {'id': 542, 'ifindex': 13, 'irq': 41}, {'id': 541, 'ifindex': 13, 'irq': 40}, diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst index 02720dd71a76..f970a2be271a 100644 --- a/Documentation/networking/napi.rst +++ b/Documentation/networking/napi.rst @@ -199,13 +199,13 @@ parameters mentioned above use hyphens instead of underscores: Per-NAPI configuration can be done programmatically in a user application or by using a script included in the kernel source tree: -``tools/net/ynl/cli.py``. +``tools/net/ynl/pyynl/cli.py``. For example, using the script: .. code-block:: bash - $ kernel-source/tools/net/ynl/cli.py \ + $ kernel-source/tools/net/ynl/pyynl/cli.py \ --spec Documentation/netlink/specs/netdev.yaml \ --do napi-set \ --json='{"id": 345, @@ -362,7 +362,7 @@ It is expected that ``irq-suspend-timeout`` will be set to a value much larger than ``gro_flush_timeout`` as ``irq-suspend-timeout`` should suspend IRQs for the duration of one userland processing cycle. -While it is not stricly necessary to use ``napi_defer_hard_irqs`` and +While it is not strictly necessary to use ``napi_defer_hard_irqs`` and ``gro_flush_timeout`` to use IRQ suspension, their use is strongly recommended. diff --git a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst index 629da6dc6d74..de0263302f16 100644 --- a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst +++ b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst @@ -79,6 +79,7 @@ u8 sysctl_tcp_retries1 u8 sysctl_tcp_retries2 u8 sysctl_tcp_orphan_retries u8 sysctl_tcp_tw_reuse timewait_sock_ops +unsigned_int sysctl_tcp_tw_reuse_delay timewait_sock_ops int sysctl_tcp_fin_timeout TCP_LAST_ACK/tcp_rcv_state_process unsigned_int sysctl_tcp_notsent_lowat read_mostly tcp_notsent_lowat/tcp_stream_memory_free u8 sysctl_tcp_sack tcp_syn_options diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index d55c2a22ec7a..94c4680fdf3e 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -124,7 +124,7 @@ To remove a target:: The interface exposes these parameters of a netconsole target to userspace: - ============== ================================= ============ + =============== ================================= ============ enabled Is this target currently enabled? (read-write) extended Extended mode enabled (read-write) release Prepend kernel release to message (read-write) @@ -135,7 +135,8 @@ The interface exposes these parameters of a netconsole target to userspace: remote_ip Remote agent's IP address (read-write) local_mac Local interface's MAC address (read-only) remote_mac Remote agent's MAC address (read-write) - ============== ================================= ============ + transmit_errors Number of packet send errors (read-only) + =============== ================================= ============ The "enabled" attribute is also used to control whether the parameters of a target can be updated or not -- you can modify the parameters of only diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst index 857c9784f87e..1d37038e9fbe 100644 --- a/Documentation/networking/netdevices.rst +++ b/Documentation/networking/netdevices.rst @@ -297,3 +297,13 @@ napi->poll: Context: softirq will be called with interrupts disabled by netconsole. + +NETDEV_INTERNAL symbol namespace +================================ + +Symbols exported as NETDEV_INTERNAL can only be used in networking +core and drivers which exclusively flow via the main networking list and trees. +Note that the inverse is not true, most symbols outside of NETDEV_INTERNAL +are not expected to be used by random code outside netdev either. +Symbols may lack the designation because they predate the namespaces, +or simply due to an oversight. diff --git a/Documentation/networking/netlink_spec/readme.txt b/Documentation/networking/netlink_spec/readme.txt index 6763f99d216c..030b44aca4e6 100644 --- a/Documentation/networking/netlink_spec/readme.txt +++ b/Documentation/networking/netlink_spec/readme.txt @@ -1,4 +1,4 @@ SPDX-License-Identifier: GPL-2.0 This file is populated during the build of the documentation (htmldocs) by the -tools/net/ynl/ynl-gen-rst.py script. +tools/net/ynl/pyynl/ynl_gen_rst.py script. diff --git a/Documentation/networking/netmem.rst b/Documentation/networking/netmem.rst new file mode 100644 index 000000000000..7de21ddb5412 --- /dev/null +++ b/Documentation/networking/netmem.rst @@ -0,0 +1,79 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================== +Netmem Support for Network Drivers +================================== + +This document outlines the requirements for network drivers to support netmem, +an abstract memory type that enables features like device memory TCP. By +supporting netmem, drivers can work with various underlying memory types +with little to no modification. + +Benefits of Netmem : + +* Flexibility: Netmem can be backed by different memory types (e.g., struct + page, DMA-buf), allowing drivers to support various use cases such as device + memory TCP. +* Future-proof: Drivers with netmem support are ready for upcoming + features that rely on it. +* Simplified Development: Drivers interact with a consistent API, + regardless of the underlying memory implementation. + +Driver Requirements +=================== + +1. The driver must support page_pool. + +2. The driver must support the tcp-data-split ethtool option. + +3. The driver must use the page_pool netmem APIs for payload memory. The netmem + APIs currently 1-to-1 correspond with page APIs. Conversion to netmem should + be achievable by switching the page APIs to netmem APIs and tracking memory + via netmem_refs in the driver rather than struct page * : + + - page_pool_alloc -> page_pool_alloc_netmem + - page_pool_get_dma_addr -> page_pool_get_dma_addr_netmem + - page_pool_put_page -> page_pool_put_netmem + + Not all page APIs have netmem equivalents at the moment. If your driver + relies on a missing netmem API, feel free to add and propose to netdev@, or + reach out to the maintainers and/or almasrymina@google.com for help adding + the netmem API. + +4. The driver must use the following PP_FLAGS: + + - PP_FLAG_DMA_MAP: netmem is not dma-mappable by the driver. The driver + must delegate the dma mapping to the page_pool, which knows when + dma-mapping is (or is not) appropriate. + - PP_FLAG_DMA_SYNC_DEV: netmem dma addr is not necessarily dma-syncable + by the driver. The driver must delegate the dma syncing to the page_pool, + which knows when dma-syncing is (or is not) appropriate. + - PP_FLAG_ALLOW_UNREADABLE_NETMEM. The driver must specify this flag iff + tcp-data-split is enabled. + +5. The driver must not assume the netmem is readable and/or backed by pages. + The netmem returned by the page_pool may be unreadable, in which case + netmem_address() will return NULL. The driver must correctly handle + unreadable netmem, i.e. don't attempt to handle its contents when + netmem_address() is NULL. + + Ideally, drivers should not have to check the underlying netmem type via + helpers like netmem_is_net_iov() or convert the netmem to any of its + underlying types via netmem_to_page() or netmem_to_net_iov(). In most cases, + netmem or page_pool helpers that abstract this complexity are provided + (and more can be added). + +6. The driver must use page_pool_dma_sync_netmem_for_cpu() in lieu of + dma_sync_single_range_for_cpu(). For some memory providers, dma_syncing for + CPU will be done by the page_pool, for others (particularly dmabuf memory + provider), dma syncing for CPU is the responsibility of the userspace using + dmabuf APIs. The driver must delegate the entire dma-syncing operation to + the page_pool which will do it correctly. + +7. Avoid implementing driver-specific recycling on top of the page_pool. Drivers + cannot hold onto a struct page to do their own recycling as the netmem may + not be backed by a struct page. However, you may hold onto a page_pool + reference with page_pool_fragment_netmem() or page_pool_ref_netmem() for + that purpose, but be mindful that some netmem types might have longer + circulation times, such as when userspace holds a reference in zerocopy + scenarios. diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index b37bfbfc7d79..61ef9da10e28 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -525,8 +525,8 @@ implicitly defined. ts[0] holds a software timestamp if set, ts[1] is again deprecated and ts[2] holds a hardware timestamp if set. -3. Hardware Timestamping configuration: SIOCSHWTSTAMP and SIOCGHWTSTAMP -======================================================================= +3. Hardware Timestamping configuration: ETHTOOL_MSG_TSCONFIG_SET/GET +==================================================================== Hardware time stamping must also be initialized for each device driver that is expected to do hardware time stamping. The parameter is defined in @@ -539,12 +539,14 @@ include/uapi/linux/net_tstamp.h as:: }; Desired behavior is passed into the kernel and to a specific device by -calling ioctl(SIOCSHWTSTAMP) with a pointer to a struct ifreq whose -ifr_data points to a struct hwtstamp_config. The tx_type and -rx_filter are hints to the driver what it is expected to do. If -the requested fine-grained filtering for incoming packets is not -supported, the driver may time stamp more than just the requested types -of packets. +calling the tsconfig netlink socket ``ETHTOOL_MSG_TSCONFIG_SET``. +The ``ETHTOOL_A_TSCONFIG_TX_TYPES``, ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` and +``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` netlink attributes are then used to set +the struct hwtstamp_config accordingly. + +The ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` netlink nested attribute is used +to select the source of the hardware time stamping. It is composed of an index +for the device source and a qualifier for the type of time stamping. Drivers are free to use a more permissive configuration than the requested configuration. It is expected that drivers should only implement directly the @@ -563,9 +565,16 @@ Only a processes with admin rights may change the configuration. User space is responsible to ensure that multiple processes don't interfere with each other and that the settings are reset. -Any process can read the actual configuration by passing this -structure to ioctl(SIOCGHWTSTAMP) in the same way. However, this has -not been implemented in all drivers. +Any process can read the actual configuration by requesting tsconfig netlink +socket ``ETHTOOL_MSG_TSCONFIG_GET``. + +The legacy configuration is the use of the ioctl(SIOCSHWTSTAMP) with a pointer +to a struct ifreq whose ifr_data points to a struct hwtstamp_config. +The tx_type and rx_filter are hints to the driver what it is expected to do. +If the requested fine-grained filtering for incoming packets is not +supported, the driver may time stamp more than just the requested types +of packets. ioctl(SIOCGHWTSTAMP) is used in the same way as the +ioctl(SIOCSHWTSTAMP). However, this has not been implemented in all drivers. :: @@ -610,9 +619,10 @@ not been implemented in all drivers. -------------------------------------------------------- A driver which supports hardware time stamping must support the -SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with -the actual values as described in the section on SIOCSHWTSTAMP. It -should also support SIOCGHWTSTAMP. +ndo_hwtstamp_set NDO or the legacy SIOCSHWTSTAMP ioctl and update the +supplied struct hwtstamp_config with the actual values as described in +the section on SIOCSHWTSTAMP. It should also support ndo_hwtstamp_get or +the legacy SIOCGHWTSTAMP. Time stamps for received packets must be stored in the skb. To get a pointer to the shared time stamp structure of the skb call skb_hwtstamps(). Then diff --git a/Documentation/networking/tls.rst b/Documentation/networking/tls.rst index 658ed3a71e1b..c7904a1bc167 100644 --- a/Documentation/networking/tls.rst +++ b/Documentation/networking/tls.rst @@ -200,6 +200,32 @@ received without a cmsg buffer set. recv will never return data from mixed types of TLS records. +TLS 1.3 Key Updates +------------------- + +In TLS 1.3, KeyUpdate handshake messages signal that the sender is +updating its TX key. Any message sent after a KeyUpdate will be +encrypted using the new key. The userspace library can pass the new +key to the kernel using the TLS_TX and TLS_RX socket options, as for +the initial keys. TLS version and cipher cannot be changed. + +To prevent attempting to decrypt incoming records using the wrong key, +decryption will be paused when a KeyUpdate message is received by the +kernel, until the new key has been provided using the TLS_RX socket +option. Any read occurring after the KeyUpdate has been read and +before the new key is provided will fail with EKEYEXPIRED. poll() will +not report any read events from the socket until the new key is +provided. There is no pausing on the transmit side. + +Userspace should make sure that the crypto_info provided has been set +properly. In particular, the kernel will not check for key/nonce +reuse. + +The number of successful and failed key updates is tracked in the +``TlsTxRekeyOk``, ``TlsRxRekeyOk``, ``TlsTxRekeyError``, +``TlsRxRekeyError`` statistics. The ``TlsRxRekeyReceived`` statistic +counts KeyUpdate handshake messages that have been received. + Integrating in to userspace TLS library --------------------------------------- @@ -286,3 +312,13 @@ TLS implementation exposes the following per-namespace statistics - ``TlsRxNoPadViolation`` - number of data RX records which had to be re-decrypted due to ``TLS_RX_EXPECT_NO_PAD`` mis-prediction. + +- ``TlsTxRekeyOk``, ``TlsRxRekeyOk`` - + number of successful rekeys on existing sessions for TX and RX + +- ``TlsTxRekeyError``, ``TlsRxRekeyError`` - + number of failed rekeys on existing sessions for TX and RX + +- ``TlsRxRekeyReceived`` - + number of received KeyUpdate handshake messages, requiring userspace + to provide a new RX key diff --git a/Documentation/networking/xfrm_device.rst b/Documentation/networking/xfrm_device.rst index bfea9d8579ed..66f6e9a9b59a 100644 --- a/Documentation/networking/xfrm_device.rst +++ b/Documentation/networking/xfrm_device.rst @@ -169,7 +169,8 @@ the stack in xfrm_input(). hand the packet to napi_gro_receive() as usual -In ESN mode, xdo_dev_state_advance_esn() is called from xfrm_replay_advance_esn(). +In ESN mode, xdo_dev_state_advance_esn() is called from +xfrm_replay_advance_esn() for RX, and xfrm_replay_overflow_offload_esn for TX. Driver will check packet seq number and update HW ESN state machine if needed. Packet offload mode: diff --git a/Documentation/nvme/index.rst b/Documentation/nvme/index.rst new file mode 100644 index 000000000000..13383c760cc7 --- /dev/null +++ b/Documentation/nvme/index.rst @@ -0,0 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============== +NVMe Subsystem +============== + +.. toctree:: + :maxdepth: 2 + :numbered: + + feature-and-quirk-policy + nvme-pci-endpoint-target diff --git a/Documentation/nvme/nvme-pci-endpoint-target.rst b/Documentation/nvme/nvme-pci-endpoint-target.rst new file mode 100644 index 000000000000..66e7b7d869b4 --- /dev/null +++ b/Documentation/nvme/nvme-pci-endpoint-target.rst @@ -0,0 +1,368 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================= +NVMe PCI Endpoint Function Target +================================= + +:Author: Damien Le Moal + +The NVMe PCI endpoint function target driver implements a NVMe PCIe controller +using a NVMe fabrics target controller configured with the PCI transport type. + +Overview +======== + +The NVMe PCI endpoint function target driver allows exposing a NVMe target +controller over a PCIe link, thus implementing an NVMe PCIe device similar to a +regular M.2 SSD. The target controller is created in the same manner as when +using NVMe over fabrics: the controller represents the interface to an NVMe +subsystem using a port. The port transfer type must be configured to be +"pci". The subsystem can be configured to have namespaces backed by regular +files or block devices, or can use NVMe passthrough to expose to the PCI host an +existing physical NVMe device or a NVMe fabrics host controller (e.g. a NVMe TCP +host controller). + +The NVMe PCI endpoint function target driver relies as much as possible on the +NVMe target core code to parse and execute NVMe commands submitted by the PCIe +host. However, using the PCI endpoint framework API and DMA API, the driver is +also responsible for managing all data transfers over the PCIe link. This +implies that the NVMe PCI endpoint function target driver implements several +NVMe data structure management and some NVMe command parsing. + +1) The driver manages retrieval of NVMe commands in submission queues using DMA + if supported, or MMIO otherwise. Each command retrieved is then executed + using a work item to maximize performance with the parallel execution of + multiple commands on different CPUs. The driver uses a work item to + constantly poll the doorbell of all submission queues to detect command + submissions from the PCIe host. + +2) The driver transfers completion queues entries of completed commands to the + PCIe host using MMIO copy of the entries in the host completion queue. + After posting completion entries in a completion queue, the driver uses the + PCI endpoint framework API to raise an interrupt to the host to signal the + commands completion. + +3) For any command that has a data buffer, the NVMe PCI endpoint target driver + parses the command PRPs or SGLs lists to create a list of PCI address + segments representing the mapping of the command data buffer on the host. + The command data buffer is transferred over the PCIe link using this list of + PCI address segments using DMA, if supported. If DMA is not supported, MMIO + is used, which results in poor performance. For write commands, the command + data buffer is transferred from the host into a local memory buffer before + executing the command using the target core code. For read commands, a local + memory buffer is allocated to execute the command and the content of that + buffer is transferred to the host once the command completes. + +Controller Capabilities +----------------------- + +The NVMe capabilities exposed to the PCIe host through the BAR 0 registers +are almost identical to the capabilities of the NVMe target controller +implemented by the target core code. There are some exceptions. + +1) The NVMe PCI endpoint target driver always sets the controller capability + CQR bit to request "Contiguous Queues Required". This is to facilitate the + mapping of a queue PCI address range to the local CPU address space. + +2) The doorbell stride (DSTRB) is always set to be 4B + +3) Since the PCI endpoint framework does not provide a way to handle PCI level + resets, the controller capability NSSR bit (NVM Subsystem Reset Supported) + is always cleared. + +4) The boot partition support (BPS), Persistent Memory Region Supported (PMRS) + and Controller Memory Buffer Supported (CMBS) capabilities are never + reported. + +Supported Features +------------------ + +The NVMe PCI endpoint target driver implements support for both PRPs and SGLs. +The driver also implements IRQ vector coalescing and submission queue +arbitration burst. + +The maximum number of queues and the maximum data transfer size (MDTS) are +configurable through configfs before starting the controller. To avoid issues +with excessive local memory usage for executing commands, MDTS defaults to 512 +KB and is limited to a maximum of 2 MB (arbitrary limit). + +Mimimum number of PCI Address Mapping Windows Required +------------------------------------------------------ + +Most PCI endpoint controllers provide a limited number of mapping windows for +mapping a PCI address range to local CPU memory addresses. The NVMe PCI +endpoint target controllers uses mapping windows for the following. + +1) One memory window for raising MSI or MSI-X interrupts +2) One memory window for MMIO transfers +3) One memory window for each completion queue + +Given the highly asynchronous nature of the NVMe PCI endpoint target driver +operation, the memory windows as described above will generally not be used +simultaneously, but that may happen. So a safe maximum number of completion +queues that can be supported is equal to the total number of memory mapping +windows of the PCI endpoint controller minus two. E.g. for an endpoint PCI +controller with 32 outbound memory windows available, up to 30 completion +queues can be safely operated without any risk of getting PCI address mapping +errors due to the lack of memory windows. + +Maximum Number of Queue Pairs +----------------------------- + +Upon binding of the NVMe PCI endpoint target driver to the PCI endpoint +controller, BAR 0 is allocated with enough space to accommodate the admin queue +and multiple I/O queues. The maximum of number of I/O queues pairs that can be +supported is limited by several factors. + +1) The NVMe target core code limits the maximum number of I/O queues to the + number of online CPUs. +2) The total number of queue pairs, including the admin queue, cannot exceed + the number of MSI-X or MSI vectors available. +3) The total number of completion queues must not exceed the total number of + PCI mapping windows minus 2 (see above). + +The NVMe endpoint function driver allows configuring the maximum number of +queue pairs through configfs. + +Limitations and NVMe Specification Non-Compliance +------------------------------------------------- + +Similar to the NVMe target core code, the NVMe PCI endpoint target driver does +not support multiple submission queues using the same completion queue. All +submission queues must specify a unique completion queue. + + +User Guide +========== + +This section describes the hardware requirements and how to setup an NVMe PCI +endpoint target device. + +Kernel Requirements +------------------- + +The kernel must be compiled with the configuration options CONFIG_PCI_ENDPOINT, +CONFIG_PCI_ENDPOINT_CONFIGFS, and CONFIG_NVME_TARGET_PCI_EPF enabled. +CONFIG_PCI, CONFIG_BLK_DEV_NVME and CONFIG_NVME_TARGET must also be enabled +(obviously). + +In addition to this, at least one PCI endpoint controller driver should be +available for the endpoint hardware used. + +To facilitate testing, enabling the null-blk driver (CONFIG_BLK_DEV_NULL_BLK) +is also recommended. With this, a simple setup using a null_blk block device +as a subsystem namespace can be used. + +Hardware Requirements +--------------------- + +To use the NVMe PCI endpoint target driver, at least one endpoint controller +device is required. + +To find the list of endpoint controller devices in the system:: + + # ls /sys/class/pci_epc/ + a40000000.pcie-ep + +If PCI_ENDPOINT_CONFIGFS is enabled:: + + # ls /sys/kernel/config/pci_ep/controllers + a40000000.pcie-ep + +The endpoint board must of course also be connected to a host with a PCI cable +with RX-TX signal swapped. If the host PCI slot used does not have +plug-and-play capabilities, the host should be powered off when the NVMe PCI +endpoint device is configured. + +NVMe Endpoint Device +-------------------- + +Creating an NVMe endpoint device is a two step process. First, an NVMe target +subsystem and port must be defined. Second, the NVMe PCI endpoint device must +be setup and bound to the subsystem and port created. + +Creating a NVMe Subsystem and Port +---------------------------------- + +Details about how to configure a NVMe target subsystem and port are outside the +scope of this document. The following only provides a simple example of a port +and subsystem with a single namespace backed by a null_blk device. + +First, make sure that configfs is enabled:: + + # mount -t configfs none /sys/kernel/config + +Next, create a null_blk device (default settings give a 250 GB device without +memory backing). The block device created will be /dev/nullb0 by default:: + + # modprobe null_blk + # ls /dev/nullb0 + /dev/nullb0 + +The NVMe PCI endpoint function target driver must be loaded:: + + # modprobe nvmet_pci_epf + # lsmod | grep nvmet + nvmet_pci_epf 32768 0 + nvmet 118784 1 nvmet_pci_epf + nvme_core 131072 2 nvmet_pci_epf,nvmet + +Now, create a subsystem and a port that we will use to create a PCI target +controller when setting up the NVMe PCI endpoint target device. In this +example, the port is created with a maximum of 4 I/O queue pairs:: + + # cd /sys/kernel/config/nvmet/subsystems + # mkdir nvmepf.0.nqn + # echo -n "Linux-pci-epf" > nvmepf.0.nqn/attr_model + # echo "0x1b96" > nvmepf.0.nqn/attr_vendor_id + # echo "0x1b96" > nvmepf.0.nqn/attr_subsys_vendor_id + # echo 1 > nvmepf.0.nqn/attr_allow_any_host + # echo 4 > nvmepf.0.nqn/attr_qid_max + +Next, create and enable the subsystem namespace using the null_blk block +device:: + + # mkdir nvmepf.0.nqn/namespaces/1 + # echo -n "/dev/nullb0" > nvmepf.0.nqn/namespaces/1/device_path + # echo 1 > "nvmepf.0.nqn/namespaces/1/enable" + +Finally, create the target port and link it to the subsystem:: + + # cd /sys/kernel/config/nvmet/ports + # mkdir 1 + # echo -n "pci" > 1/addr_trtype + # ln -s /sys/kernel/config/nvmet/subsystems/nvmepf.0.nqn \ + /sys/kernel/config/nvmet/ports/1/subsystems/nvmepf.0.nqn + +Creating a NVMe PCI Endpoint Device +----------------------------------- + +With the NVMe target subsystem and port ready for use, the NVMe PCI endpoint +device can now be created and enabled. The NVMe PCI endpoint target driver +should already be loaded (that is done automatically when the port is created):: + + # ls /sys/kernel/config/pci_ep/functions + nvmet_pci_epf + +Next, create function 0:: + + # cd /sys/kernel/config/pci_ep/functions/nvmet_pci_epf + # mkdir nvmepf.0 + # ls nvmepf.0/ + baseclass_code msix_interrupts secondary + cache_line_size nvme subclass_code + deviceid primary subsys_id + interrupt_pin progif_code subsys_vendor_id + msi_interrupts revid vendorid + +Configure the function using any device ID (the vendor ID for the device will +be automatically set to the same value as the NVMe target subsystem vendor +ID):: + + # cd /sys/kernel/config/pci_ep/functions/nvmet_pci_epf + # echo 0xBEEF > nvmepf.0/deviceid + # echo 32 > nvmepf.0/msix_interrupts + +If the PCI endpoint controller used does not support MSI-X, MSI can be +configured instead:: + + # echo 32 > nvmepf.0/msi_interrupts + +Next, let's bind our endpoint device with the target subsystem and port that we +created:: + + # echo 1 > nvmepf.0/nvme/portid + # echo "nvmepf.0.nqn" > nvmepf.0/nvme/subsysnqn + +The endpoint function can then be bound to the endpoint controller and the +controller started:: + + # cd /sys/kernel/config/pci_ep + # ln -s functions/nvmet_pci_epf/nvmepf.0 controllers/a40000000.pcie-ep/ + # echo 1 > controllers/a40000000.pcie-ep/start + +On the endpoint machine, kernel messages will show information as the NVMe +target device and endpoint device are created and connected. + +.. code-block:: text + + null_blk: disk nullb0 created + null_blk: module loaded + nvmet: adding nsid 1 to subsystem nvmepf.0.nqn + nvmet_pci_epf nvmet_pci_epf.0: PCI endpoint controller supports MSI-X, 32 vectors + nvmet: Created nvm controller 1 for subsystem nvmepf.0.nqn for NQN nqn.2014-08.org.nvmexpress:uuid:2ab90791-2246-4fbb-961d-4c3d5a5a0176. + nvmet_pci_epf nvmet_pci_epf.0: New PCI ctrl "nvmepf.0.nqn", 4 I/O queues, mdts 524288 B + +PCI Root-Complex Host +--------------------- + +Booting the PCI host will result in the initialization of the PCIe link (this +may be signaled by the PCI endpoint driver with a kernel message). A kernel +message on the endpoint will also signal when the host NVMe driver enables the +device controller:: + + nvmet_pci_epf nvmet_pci_epf.0: Enabling controller + +On the host side, the NVMe PCI endpoint function target device will is +discoverable as a PCI device, with the vendor ID and device ID as configured:: + + # lspci -n + 0000:01:00.0 0108: 1b96:beef + +An this device will be recognized as an NVMe device with a single namespace:: + + # lsblk + NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINTS + nvme0n1 259:0 0 250G 0 disk + +The NVMe endpoint block device can then be used as any other regular NVMe +namespace block device. The *nvme* command line utility can be used to get more +detailed information about the endpoint device:: + + # nvme id-ctrl /dev/nvme0 + NVME Identify Controller: + vid : 0x1b96 + ssvid : 0x1b96 + sn : 94993c85650ef7bcd625 + mn : Linux-pci-epf + fr : 6.13.0-r + rab : 6 + ieee : 000000 + cmic : 0xb + mdts : 7 + cntlid : 0x1 + ver : 0x20100 + ... + + +Endpoint Bindings +================= + +The NVMe PCI endpoint target driver uses the PCI endpoint configfs device +attributes as follows. + +================ =========================================================== +vendorid Ignored (the vendor id of the NVMe target subsystem is used) +deviceid Anything is OK (e.g. PCI_ANY_ID) +revid Do not care +progif_code Must be 0x02 (NVM Express) +baseclass_code Must be 0x01 (PCI_BASE_CLASS_STORAGE) +subclass_code Must be 0x08 (Non-Volatile Memory controller) +cache_line_size Do not care +subsys_vendor_id Ignored (the subsystem vendor id of the NVMe target subsystem + is used) +subsys_id Anything is OK (e.g. PCI_ANY_ID) +msi_interrupts At least equal to the number of queue pairs desired +msix_interrupts At least equal to the number of queue pairs desired +interrupt_pin Interrupt PIN to use if MSI and MSI-X are not supported +================ =========================================================== + +The NVMe PCI endpoint target function also has some specific configurable +fields defined in the *nvme* subdirectory of the function directory. These +fields are as follows. + +================ =========================================================== +mdts_kb Maximum data transfer size in KiB (default: 512) +portid The ID of the target port to use +subsysnqn The NQN of the target subsystem to use +================ =========================================================== diff --git a/Documentation/power/video.rst b/Documentation/power/video.rst index 337a2ba9f32f..8ab2458d1304 100644 --- a/Documentation/power/video.rst +++ b/Documentation/power/video.rst @@ -190,7 +190,7 @@ Toshiba Portege 3020CT s3_mode (3) Toshiba Satellite 4030CDT s3_mode (3) (S1 also works OK) Toshiba Satellite 4080XCDT s3_mode (3) (S1 also works OK) Toshiba Satellite 4090XCDT ??? [#f1]_ -Toshiba Satellite P10-554 s3_bios,s3_mode (4)[#f3]_ +Toshiba Satellite P10-554 s3_bios,s3_mode (4) [#f3]_ Toshiba M30 (2) xor X with nvidia driver using internal AGP Uniwill 244IIO ??? [#f1]_ =============================== =============================================== diff --git a/Documentation/process/5.Posting.rst b/Documentation/process/5.Posting.rst index b3eff03ea249..dbb763a8de90 100644 --- a/Documentation/process/5.Posting.rst +++ b/Documentation/process/5.Posting.rst @@ -261,6 +261,10 @@ The tags in common use are: can be used instead of Closes: if the patch fixes a part of the issue(s) being reported. + - A Suggested-by: tag indicates that the patch idea is suggested by the person + named and ensures credit to the person for the idea. This will, hopefully, + inspire them to help us again in the future. + - Cc: the named person received a copy of the patch and had the opportunity to comment on it. diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index 82b5e378eebf..a0beca805362 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -59,7 +59,6 @@ iptables 1.4.2 iptables -V openssl & libcrypto 1.0.0 openssl version bc 1.06.95 bc --version Sphinx\ [#f1]_ 2.4.4 sphinx-build --version -cpio any cpio --version GNU tar 1.28 tar --version gtags (optional) 6.6.5 gtags --version mkimage (optional) 2017.01 mkimage --version @@ -536,11 +535,6 @@ mcelog - -cpio ----- - -- - Networking ********** diff --git a/Documentation/process/debugging/driver_development_debugging_guide.rst b/Documentation/process/debugging/driver_development_debugging_guide.rst index aef204094205..46becda8764b 100644 --- a/Documentation/process/debugging/driver_development_debugging_guide.rst +++ b/Documentation/process/debugging/driver_development_debugging_guide.rst @@ -207,17 +207,29 @@ resources, that can cause performance disruptions or even OOM kills. device coredump --------------- -Prerequisite: ``#include `` +Prerequisite: ``CONFIG_DEV_COREDUMP`` & ``#include `` Provides the infrastructure for a driver to provide arbitrary data to userland. It is most often used in conjunction with udev or similar userland application to listen for kernel uevents, which indicate that the dump is ready. Udev has rules to copy that file somewhere for long-term storage and analysis, as by -default, the data for the dump is automatically cleaned up after 5 minutes. -That data is analyzed with driver-specific tools or GDB. +default, the data for the dump is automatically cleaned up after a default +5 minutes. That data is analyzed with driver-specific tools or GDB. + +A device coredump can be created with a vmalloc area, with read/free +methods, or as a scatter/gather list. You can find an example implementation at: `drivers/media/platform/qcom/venus/core.c -`__ +`__, +in the Bluetooth HCI layer, in several wireless drivers, and in several +DRM drivers. + +devcoredump interfaces +~~~~~~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/linux/devcoredump.h + +.. kernel-doc:: drivers/base/devcoredump.c **Copyright** ©2024 : Collabora diff --git a/Documentation/dev-tools/gdb-kernel-debugging.rst b/Documentation/process/debugging/gdb-kernel-debugging.rst similarity index 100% rename from Documentation/dev-tools/gdb-kernel-debugging.rst rename to Documentation/process/debugging/gdb-kernel-debugging.rst diff --git a/Documentation/process/debugging/index.rst b/Documentation/process/debugging/index.rst index f6e4a00dfee3..387d33d16f5e 100644 --- a/Documentation/process/debugging/index.rst +++ b/Documentation/process/debugging/index.rst @@ -11,6 +11,8 @@ general guides :maxdepth: 1 driver_development_debugging_guide + gdb-kernel-debugging + kgdb userspace_debugging_guide .. only:: subproject and html diff --git a/Documentation/dev-tools/kgdb.rst b/Documentation/process/debugging/kgdb.rst similarity index 96% rename from Documentation/dev-tools/kgdb.rst rename to Documentation/process/debugging/kgdb.rst index cb626a7a000c..b29b0aac2717 100644 --- a/Documentation/dev-tools/kgdb.rst +++ b/Documentation/process/debugging/kgdb.rst @@ -255,10 +255,10 @@ scenarios. .. note:: Kgdboc does not support interrupting the target via the gdb remote - protocol. You must manually send a :kbd:`SysRq-G` unless you have a proxy + protocol. You must manually send a `SysRq-G` unless you have a proxy that splits console output to a terminal program. A console proxy has a separate TCP port for the debugger and a separate TCP port for the - "human" console. The proxy can take care of sending the :kbd:`SysRq-G` + "human" console. The proxy can take care of sending the `SysRq-G` for you. When using kgdboc with no debugger proxy, you can end up connecting the @@ -267,9 +267,9 @@ have loaded kgdboc, a message should print on the console stating it is waiting for the debugger. In this case you disconnect your terminal program and then connect the debugger in its place. If you want to interrupt the target system and forcibly enter a debug session you have -to issue a :kbd:`Sysrq` sequence and then type the letter :kbd:`g`. Then you +to issue a `Sysrq` sequence and then type the letter `g`. Then you disconnect the terminal session and connect gdb. Your options if you -don't like this are to hack gdb to send the :kbd:`SysRq-G` for you as well as +don't like this are to hack gdb to send the `SysRq-G` for you as well as on the initial connect, or to use a debugger proxy that allows an unmodified gdb to do the debugging. @@ -401,7 +401,7 @@ This is a quick example of how to use kdb. 2. Enter the kernel debugger manually or by waiting for an oops or fault. There are several ways you can enter the kernel debugger - manually; all involve using the :kbd:`SysRq-G`, which means you must have + manually; all involve using the `SysRq-G`, which means you must have enabled ``CONFIG_MAGIC_SYSRQ=y`` in your kernel config. - When logged in as root or with a super user session you can run:: @@ -410,16 +410,16 @@ This is a quick example of how to use kdb. - Example using minicom 2.2 - Press: :kbd:`CTRL-A` :kbd:`f` :kbd:`g` + Press: `CTRL-A` `f` `g` - When you have telneted to a terminal server that supports sending a remote break - Press: :kbd:`CTRL-]` + Press: `CTRL-]` Type in: ``send break`` - Press: :kbd:`Enter` :kbd:`g` + Press: `Enter` `g` 3. From the kdb prompt you can run the ``help`` command to see a complete list of the commands that are available. @@ -460,7 +460,7 @@ This is a quick example of how to use kdb with a keyboard. 2. Enter the kernel debugger manually or by waiting for an oops or fault. There are several ways you can enter the kernel debugger - manually; all involve using the :kbd:`SysRq-G`, which means you must have + manually; all involve using the `SysRq-G`, which means you must have enabled ``CONFIG_MAGIC_SYSRQ=y`` in your kernel config. - When logged in as root or with a super user session you can run:: @@ -469,27 +469,27 @@ This is a quick example of how to use kdb with a keyboard. - Example using a laptop keyboard: - Press and hold down: :kbd:`Alt` + Press and hold down: `Alt` - Press and hold down: :kbd:`Fn` + Press and hold down: `Fn` - Press and release the key with the label: :kbd:`SysRq` + Press and release the key with the label: `SysRq` - Release: :kbd:`Fn` + Release: `Fn` - Press and release: :kbd:`g` + Press and release: `g` - Release: :kbd:`Alt` + Release: `Alt` - Example using a PS/2 101-key keyboard - Press and hold down: :kbd:`Alt` + Press and hold down: `Alt` - Press and release the key with the label: :kbd:`SysRq` + Press and release the key with the label: `SysRq` - Press and release: :kbd:`g` + Press and release: `g` - Release: :kbd:`Alt` + Release: `Alt` 3. Now type in a kdb command such as ``help``, ``dmesg``, ``bt`` or ``go`` to continue kernel execution. @@ -531,7 +531,7 @@ Connecting with gdb to a serial port In order to connect to gdb via kgdboc, the kernel must first be stopped. There are several ways to stop the kernel which include - using kgdbwait as a boot argument, via a :kbd:`SysRq-G`, or running the + using kgdbwait as a boot argument, via a `SysRq-G`, or running the kernel until it takes an exception where it waits for the debugger to attach. @@ -541,16 +541,16 @@ Connecting with gdb to a serial port - Example using minicom 2.2 - Press: :kbd:`CTRL-A` :kbd:`f` :kbd:`g` + Press: `CTRL-A` `f` `g` - When you have telneted to a terminal server that supports sending a remote break - Press: :kbd:`CTRL-]` + Press: `CTRL-]` Type in: ``send break`` - Press: :kbd:`Enter` :kbd:`g` + Press: `Enter` `g` 3. Connect from gdb @@ -578,7 +578,7 @@ Connecting with gdb to a serial port set debug remote 1 Remember if you continue in gdb, and need to "break in" again, you need -to issue an other :kbd:`SysRq-G`. It is easy to create a simple entry point by +to issue an other `SysRq-G`. It is easy to create a simple entry point by putting a breakpoint at ``sys_sync`` and then you can run ``sync`` from a shell or script to break into the debugger. @@ -612,7 +612,7 @@ or delete because kgdb will interpret that as part of the debug stream. .. note:: - Now you must kill gdb. Typically you press :kbd:`CTRL-Z` and issue + Now you must kill gdb. Typically you press `CTRL-Z` and issue the command:: kill -9 % diff --git a/Documentation/process/email-clients.rst b/Documentation/process/email-clients.rst index e6b9173a1845..84a2450bb6ec 100644 --- a/Documentation/process/email-clients.rst +++ b/Documentation/process/email-clients.rst @@ -86,7 +86,7 @@ In the :menuselection:`Sending Preferences` section: - :menuselection:`Strip Whitespace Before Sending` must be ``disabled`` When composing the message, the cursor should be placed where the patch -should appear, and then pressing :kbd:`CTRL-R` let you specify the patch file +should appear, and then pressing `CTRL-R` let you specify the patch file to insert into the message. Claws Mail (GUI) @@ -94,7 +94,7 @@ Claws Mail (GUI) Works. Some people use this successfully for patches. -To insert a patch use :menuselection:`Message-->Insert File` (:kbd:`CTRL-I`) +To insert a patch use :menuselection:`Message-->Insert File` (`CTRL-I`) or an external editor. If the inserted patch has to be edited in the Claws composition window @@ -108,11 +108,11 @@ Evolution (GUI) Some people use this successfully for patches. When composing mail select: Preformat - from :menuselection:`Format-->Paragraph Style-->Preformatted` (:kbd:`CTRL-7`) + from :menuselection:`Format-->Paragraph Style-->Preformatted` (`CTRL-7`) or the toolbar Then use: -:menuselection:`Insert-->Text File...` (:kbd:`ALT-N x`) +:menuselection:`Insert-->Text File...` (`ALT-N x`) to insert the patch. You can also ``diff -Nru old.c new.c | xclip``, select diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index 1ae71e31591c..e497729525d5 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -470,6 +470,52 @@ in a way which would break what would normally be considered uAPI. new ``netdevsim`` features must be accompanied by selftests under ``tools/testing/selftests/``. +Supported status for drivers +---------------------------- + +.. note: The following requirements apply only to Ethernet NIC drivers. + +Netdev defines additional requirements for drivers which want to acquire +the ``Supported`` status in the MAINTAINERS file. ``Supported`` drivers must +be running all upstream driver tests and reporting the results twice a day. +Drivers which do not comply with this requirement should use the ``Maintained`` +status. There is currently no difference in how ``Supported`` and ``Maintained`` +drivers are treated upstream. + +The exact rules a driver must follow to acquire the ``Supported`` status: + +1. Must run all tests under ``drivers/net`` and ``drivers/net/hw`` targets + of Linux selftests. Running and reporting private / internal tests is + also welcome, but upstream tests are a must. + +2. The minimum run frequency is once every 12 hours. Must test the + designated branch from the selected branch feed. Note that branches + are auto-constructed and exposed to intentional malicious patch posting, + so the test systems must be isolated. + +3. Drivers supporting multiple generations of devices must test at + least one device from each generation. A testbed manifest (exact + format TBD) should describe the device models tested. + +4. The tests must run reliably, if multiple branches are skipped or tests + are failing due to execution environment problems the ``Supported`` + status will be withdrawn. + +5. Test failures due to bugs either in the driver or the test itself, + or lack of support for the feature the test is targgeting are + *not* a basis for losing the ``Supported`` status. + +netdev CI will maintain an official page of supported devices, listing their +recent test results. + +The driver maintainer may arrange for someone else to run the test, +there is no requirement for the person listed as maintainer (or their +employer) to be responsible for running the tests. Collaboration between +vendors, hosting GH CI, other repos under linux-netdev, etc. is most welcome. + +See https://github.com/linux-netdev/nipa/wiki for more information about +netdev CI. Feel free to reach out to maintainers or the list with any questions. + Reviewer guidance ----------------- diff --git a/Documentation/process/maintainer-tip.rst b/Documentation/process/maintainer-tip.rst index e374b67b3277..41d5855700cd 100644 --- a/Documentation/process/maintainer-tip.rst +++ b/Documentation/process/maintainer-tip.rst @@ -270,7 +270,7 @@ Ordering of commit tags To have a uniform view of the commit tags, the tip maintainers use the following tag ordering scheme: - - Fixes: 12char-SHA1 ("sub/sys: Original subject line") + - Fixes: 12+char-SHA1 ("sub/sys: Original subject line") A Fixes tag should be added even for changes which do not need to be backported to stable kernels, i.e. when addressing a recently introduced diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst index 1518bd57adab..8fdc0ef3e604 100644 --- a/Documentation/process/submitting-patches.rst +++ b/Documentation/process/submitting-patches.rst @@ -143,10 +143,10 @@ also track such tags and take certain actions. Private bug trackers and invalid URLs are forbidden. If your patch fixes a bug in a specific commit, e.g. you found an issue using -``git bisect``, please use the 'Fixes:' tag with the first 12 characters of -the SHA-1 ID, and the one line summary. Do not split the tag across multiple -lines, tags are exempt from the "wrap at 75 columns" rule in order to simplify -parsing scripts. For example:: +``git bisect``, please use the 'Fixes:' tag with at least the first 12 +characters of the SHA-1 ID, and the one line summary. Do not split the tag +across multiple lines, tags are exempt from the "wrap at 75 columns" rule in +order to simplify parsing scripts. For example:: Fixes: 54a4f0239f2e ("KVM: MMU: make kvm_mmu_zap_page() return the number of pages it actually freed") @@ -463,21 +463,35 @@ If a person was not directly involved in the preparation or handling of a patch but wishes to signify and record their approval of it then they can ask to have an Acked-by: line added to the patch's changelog. -Acked-by: is often used by the maintainer of the affected code when that +Acked-by: is meant to be used by those responsible for or involved with the +affected code in one way or another. Most commonly, the maintainer when that maintainer neither contributed to nor forwarded the patch. +Acked-by: may also be used by other stakeholders, such as people with domain +knowledge (e.g. the original author of the code being modified), userspace-side +reviewers for a kernel uAPI patch or key users of a feature. Optionally, in +these cases, it can be useful to add a "# Suffix" to clarify its meaning:: + + Acked-by: The Stakeholder # As primary user + Acked-by: is not as formal as Signed-off-by:. It is a record that the acker has at least reviewed the patch and has indicated acceptance. Hence patch mergers will sometimes manually convert an acker's "yep, looks good to me" into an Acked-by: (but note that it is usually better to ask for an explicit ack). +Acked-by: is also less formal than Reviewed-by:. For instance, maintainers may +use it to signify that they are OK with a patch landing, but they may not have +reviewed it as thoroughly as if a Reviewed-by: was provided. Similarly, a key +user may not have carried out a technical review of the patch, yet they may be +satisfied with the general approach, the feature or the user-facing interface. + Acked-by: does not necessarily indicate acknowledgement of the entire patch. For example, if a patch affects multiple subsystems and has an Acked-by: from one subsystem maintainer then this usually indicates acknowledgement of just the part which affects that maintainer's code. Judgement should be used here. When in doubt people should refer to the original discussion in the mailing -list archives. +list archives. A "# Suffix" may also be used in this case to clarify. If a person has had the opportunity to comment on a patch, but has not provided such comments, you may optionally add a ``Cc:`` tag to the patch. @@ -600,6 +614,10 @@ process nor the requirement to Cc: stable@vger.kernel.org on all stable patch candidates. For more information, please read Documentation/process/stable-kernel-rules.rst. +Finally, while providing tags is welcome and typically very appreciated, please +note that signers (i.e. submitters and maintainers) may use their discretion in +applying offered tags. + .. _the_canonical_patch_format: The canonical patch format @@ -610,6 +628,9 @@ that, if you have your patches stored in a ``git`` repository, proper patch formatting can be had with ``git format-patch``. The tools cannot create the necessary text, though, so read the instructions below anyway. +Subject Line +^^^^^^^^^^^^ + The canonical patch subject line is:: Subject: [PATCH 001/123] subsystem: summary phrase @@ -683,6 +704,9 @@ Here are some good example Subjects:: Subject: [PATCH v2] sub/sys: Condensed patch summary Subject: [PATCH v2 M/N] sub/sys: Condensed patch summary +From Line +^^^^^^^^^ + The ``from`` line must be the very first line in the message body, and has the form: @@ -693,6 +717,9 @@ patch in the permanent changelog. If the ``from`` line is missing, then the ``From:`` line from the email header will be used to determine the patch author in the changelog. +Explanation Body +^^^^^^^^^^^^^^^^ + The explanation body will be committed to the permanent source changelog, so should make sense to a competent reader who has long since forgotten the immediate details of the discussion that might have led to @@ -708,6 +735,31 @@ _all_ of the compile failures; just enough that it is likely that someone searching for the patch can find it. As in the ``summary phrase``, it is important to be both succinct as well as descriptive. +.. _backtraces: + +Backtraces in commit messages +""""""""""""""""""""""""""""" + +Backtraces help document the call chain leading to a problem. However, +not all backtraces are helpful. For example, early boot call chains are +unique and obvious. Copying the full dmesg output verbatim, however, +adds distracting information like timestamps, module lists, register and +stack dumps. + +Therefore, the most useful backtraces should distill the relevant +information from the dump, which makes it easier to focus on the real +issue. Here is an example of a well-trimmed backtrace:: + + unchecked MSR access error: WRMSR to 0xd51 (tried to write 0x0000000000000064) + at rIP: 0xffffffffae059994 (native_write_msr+0x4/0x20) + Call Trace: + mba_wrmsr + update_domains + rdtgroup_mkdir + +Commentary +^^^^^^^^^^ + The ``---`` marker line serves the essential purpose of marking for patch handling tools where the changelog message ends. @@ -746,28 +798,6 @@ patch:: See more details on the proper patch format in the following references. -.. _backtraces: - -Backtraces in commit messages -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - -Backtraces help document the call chain leading to a problem. However, -not all backtraces are helpful. For example, early boot call chains are -unique and obvious. Copying the full dmesg output verbatim, however, -adds distracting information like timestamps, module lists, register and -stack dumps. - -Therefore, the most useful backtraces should distill the relevant -information from the dump, which makes it easier to focus on the real -issue. Here is an example of a well-trimmed backtrace:: - - unchecked MSR access error: WRMSR to 0xd51 (tried to write 0x0000000000000064) - at rIP: 0xffffffffae059994 (native_write_msr+0x4/0x20) - Call Trace: - mba_wrmsr - update_domains - rdtgroup_mkdir - .. _explicit_in_reply_to: Explicit In-Reply-To headers diff --git a/Documentation/scheduler/sched-deadline.rst b/Documentation/scheduler/sched-deadline.rst index 22838ed8e13a..a727827b8dd5 100644 --- a/Documentation/scheduler/sched-deadline.rst +++ b/Documentation/scheduler/sched-deadline.rst @@ -591,12 +591,13 @@ Deadline Task Scheduling The system wide settings are configured under the /proc virtual file system. - For now the -rt knobs are used for -deadline admission control and the - -deadline runtime is accounted against the -rt runtime. We realize that this - isn't entirely desirable; however, it is better to have a small interface for - now, and be able to change it easily later. The ideal situation (see 5.) is to - run -rt tasks from a -deadline server; in which case the -rt bandwidth is a - direct subset of dl_bw. + For now the -rt knobs are used for -deadline admission control and with + CONFIG_RT_GROUP_SCHED the -deadline runtime is accounted against the (root) + -rt runtime. With !CONFIG_RT_GROUP_SCHED the knob only serves for the -dl + admission control. We realize that this isn't entirely desirable; however, it + is better to have a small interface for now, and be able to change it easily + later. The ideal situation (see 5.) is to run -rt tasks from a -deadline + server; in which case the -rt bandwidth is a direct subset of dl_bw. This means that, for a root_domain comprising M CPUs, -deadline tasks can be created while the sum of their bandwidths stays below: diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 6cb8b676ce03..c4672d7df2f7 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -16,12 +16,12 @@ programs - the BPF scheduler. * The system integrity is maintained no matter what the BPF scheduler does. The default scheduling behavior is restored anytime an error is detected, a runnable task stalls, or on invoking the SysRq key sequence - :kbd:`SysRq-S`. + `SysRq-S`. * When the BPF scheduler triggers an error, debug information is dumped to aid debugging. The debug dump is passed to and printed out by the scheduler binary. The debug dump can also be accessed through the - `sched_ext_dump` tracepoint. The SysRq key sequence :kbd:`SysRq-D` + `sched_ext_dump` tracepoint. The SysRq key sequence `SysRq-D` triggers a debug dump. This doesn't terminate the BPF scheduler and can only be read through the tracepoint. @@ -59,7 +59,7 @@ set in ``ops->flags``, only tasks with the ``SCHED_EXT`` policy are scheduled by sched_ext, while tasks with ``SCHED_NORMAL``, ``SCHED_BATCH`` and ``SCHED_IDLE`` policies are scheduled by CFS. -Terminating the sched_ext scheduler program, triggering :kbd:`SysRq-S`, or +Terminating the sched_ext scheduler program, triggering `SysRq-S`, or detection of any internal error including stalled runnable tasks aborts the BPF scheduler and reverts all tasks back to CFS. @@ -242,9 +242,9 @@ The following briefly shows how a waking task is scheduled and executed. task was inserted directly from ``ops.select_cpu()``). ``ops.enqueue()`` can make one of the following decisions: - * Immediately insert the task into either the global or local DSQ by - calling ``scx_bpf_dsq_insert()`` with ``SCX_DSQ_GLOBAL`` or - ``SCX_DSQ_LOCAL``, respectively. + * Immediately insert the task into either the global or a local DSQ by + calling ``scx_bpf_dsq_insert()`` with one of the following options: + ``SCX_DSQ_GLOBAL``, ``SCX_DSQ_LOCAL``, or ``SCX_DSQ_LOCAL_ON | cpu``. * Immediately insert the task into a custom DSQ by calling ``scx_bpf_dsq_insert()`` with a DSQ ID which is smaller than 2^63. diff --git a/Documentation/scheduler/sched-rt-group.rst b/Documentation/scheduler/sched-rt-group.rst index d685609ed3d7..80b05a3009ea 100644 --- a/Documentation/scheduler/sched-rt-group.rst +++ b/Documentation/scheduler/sched-rt-group.rst @@ -92,10 +92,10 @@ The system wide settings are configured under the /proc virtual file system: /proc/sys/kernel/sched_rt_runtime_us: A global limit on how much time real-time scheduling may use. This is always less or equal to the period_us, as it denotes the time allocated from the - period_us for the real-time tasks. Even without CONFIG_RT_GROUP_SCHED enabled, - this will limit time reserved to real-time processes. With - CONFIG_RT_GROUP_SCHED=y it signifies the total bandwidth available to all - real-time groups. + period_us for the real-time tasks. Without CONFIG_RT_GROUP_SCHED enabled, + this only serves for admission control of deadline tasks. With + CONFIG_RT_GROUP_SCHED=y it also signifies the total bandwidth available to + all real-time groups. * Time is specified in us because the interface is s32. This gives an operating range from 1us to about 35 minutes. diff --git a/Documentation/scheduler/sched-stats.rst b/Documentation/scheduler/sched-stats.rst index 7c2b16c4729d..caea83d91c67 100644 --- a/Documentation/scheduler/sched-stats.rst +++ b/Documentation/scheduler/sched-stats.rst @@ -2,6 +2,12 @@ Scheduler Statistics ==================== +Version 17 of schedstats removed 'lb_imbalance' field as it has no +significance anymore and instead added more relevant fields namely +'lb_imbalance_load', 'lb_imbalance_util', 'lb_imbalance_task' and +'lb_imbalance_misfit'. The domain field prints the name of the +corresponding sched domain from this version onwards. + Version 16 of schedstats changed the order of definitions within 'enum cpu_idle_type', which changed the order of [CPU_MAX_IDLE_TYPES] columns in show_schedstat(). In particular the position of CPU_IDLE @@ -9,7 +15,9 @@ and __CPU_NOT_IDLE changed places. The size of the array is unchanged. Version 15 of schedstats dropped counters for some sched_yield: yld_exp_empty, yld_act_empty and yld_both_empty. Otherwise, it is -identical to version 14. +identical to version 14. Details are available at + + https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/scheduler/sched-stats.txt?id=1e1dbb259c79b Version 14 of schedstats includes support for sched_domains, which hit the mainline kernel in 2.6.20 although it is identical to the stats from version @@ -26,7 +34,14 @@ cpus on the machine, while domain0 is the most tightly focused domain, sometimes balancing only between pairs of cpus. At this time, there are no architectures which need more than three domain levels. The first field in the domain stats is a bit map indicating which cpus are affected -by that domain. +by that domain. Details are available at + + https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/sched-stats.txt?id=b762f3ffb797c + +The schedstat documentation is maintained version 10 onwards and is not +updated for version 11 and 12. The details for version 10 are available at + + https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/sched-stats.txt?id=1da177e4c3f4 These fields are counters, and only increment. Programs which make use of these will need to start with a baseline observation and then calculate @@ -71,88 +86,97 @@ Domain statistics ----------------- One of these is produced per domain for each cpu described. (Note that if CONFIG_SMP is not defined, *no* domains are utilized and these lines -will not appear in the output.) +will not appear in the output. is an extension to the domain field +that prints the name of the corresponding sched domain. It can appear in +schedstat version 17 and above, and requires CONFIG_SCHED_DEBUG.) -domain 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 +domain 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 The first field is a bit mask indicating what cpus this domain operates over. -The next 24 are a variety of sched_balance_rq() statistics in grouped into types -of idleness (idle, busy, and newly idle): +The next 33 are a variety of sched_balance_rq() statistics in grouped into types +of idleness (busy, idle and newly idle): 1) # of times in this domain sched_balance_rq() was called when the - cpu was idle - 2) # of times in this domain sched_balance_rq() checked but found - the load did not require balancing when the cpu was idle - 3) # of times in this domain sched_balance_rq() tried to move one or - more tasks and failed, when the cpu was idle - 4) sum of imbalances discovered (if any) with each call to - sched_balance_rq() in this domain when the cpu was idle - 5) # of times in this domain pull_task() was called when the cpu - was idle - 6) # of times in this domain pull_task() was called even though - the target task was cache-hot when idle - 7) # of times in this domain sched_balance_rq() was called but did - not find a busier queue while the cpu was idle - 8) # of times in this domain a busier queue was found while the - cpu was idle but no busier group was found - 9) # of times in this domain sched_balance_rq() was called when the cpu was busy - 10) # of times in this domain sched_balance_rq() checked but found the + 2) # of times in this domain sched_balance_rq() checked but found the load did not require balancing when busy - 11) # of times in this domain sched_balance_rq() tried to move one or + 3) # of times in this domain sched_balance_rq() tried to move one or more tasks and failed, when the cpu was busy - 12) sum of imbalances discovered (if any) with each call to - sched_balance_rq() in this domain when the cpu was busy - 13) # of times in this domain pull_task() was called when busy - 14) # of times in this domain pull_task() was called even though the + 4) Total imbalance in load when the cpu was busy + 5) Total imbalance in utilization when the cpu was busy + 6) Total imbalance in number of tasks when the cpu was busy + 7) Total imbalance due to misfit tasks when the cpu was busy + 8) # of times in this domain pull_task() was called when busy + 9) # of times in this domain pull_task() was called even though the target task was cache-hot when busy - 15) # of times in this domain sched_balance_rq() was called but did not + 10) # of times in this domain sched_balance_rq() was called but did not find a busier queue while the cpu was busy - 16) # of times in this domain a busier queue was found while the cpu + 11) # of times in this domain a busier queue was found while the cpu was busy but no busier group was found - 17) # of times in this domain sched_balance_rq() was called when the - cpu was just becoming idle - 18) # of times in this domain sched_balance_rq() checked but found the + 12) # of times in this domain sched_balance_rq() was called when the + cpu was idle + 13) # of times in this domain sched_balance_rq() checked but found + the load did not require balancing when the cpu was idle + 14) # of times in this domain sched_balance_rq() tried to move one or + more tasks and failed, when the cpu was idle + 15) Total imbalance in load when the cpu was idle + 16) Total imbalance in utilization when the cpu was idle + 17) Total imbalance in number of tasks when the cpu was idle + 18) Total imbalance due to misfit tasks when the cpu was idle + 19) # of times in this domain pull_task() was called when the cpu + was idle + 20) # of times in this domain pull_task() was called even though + the target task was cache-hot when idle + 21) # of times in this domain sched_balance_rq() was called but did + not find a busier queue while the cpu was idle + 22) # of times in this domain a busier queue was found while the + cpu was idle but no busier group was found + + 23) # of times in this domain sched_balance_rq() was called when the + was just becoming idle + 24) # of times in this domain sched_balance_rq() checked but found the load did not require balancing when the cpu was just becoming idle - 19) # of times in this domain sched_balance_rq() tried to move one or more + 25) # of times in this domain sched_balance_rq() tried to move one or more tasks and failed, when the cpu was just becoming idle - 20) sum of imbalances discovered (if any) with each call to - sched_balance_rq() in this domain when the cpu was just becoming idle - 21) # of times in this domain pull_task() was called when newly idle - 22) # of times in this domain pull_task() was called even though the + 26) Total imbalance in load when the cpu was just becoming idle + 27) Total imbalance in utilization when the cpu was just becoming idle + 28) Total imbalance in number of tasks when the cpu was just becoming idle + 29) Total imbalance due to misfit tasks when the cpu was just becoming idle + 30) # of times in this domain pull_task() was called when newly idle + 31) # of times in this domain pull_task() was called even though the target task was cache-hot when just becoming idle - 23) # of times in this domain sched_balance_rq() was called but did not + 32) # of times in this domain sched_balance_rq() was called but did not find a busier queue while the cpu was just becoming idle - 24) # of times in this domain a busier queue was found while the cpu + 33) # of times in this domain a busier queue was found while the cpu was just becoming idle but no busier group was found Next three are active_load_balance() statistics: - 25) # of times active_load_balance() was called - 26) # of times active_load_balance() tried to move a task and failed - 27) # of times active_load_balance() successfully moved a task + 34) # of times active_load_balance() was called + 35) # of times active_load_balance() tried to move a task and failed + 36) # of times active_load_balance() successfully moved a task Next three are sched_balance_exec() statistics: - 28) sbe_cnt is not used - 29) sbe_balanced is not used - 30) sbe_pushed is not used + 37) sbe_cnt is not used + 38) sbe_balanced is not used + 39) sbe_pushed is not used Next three are sched_balance_fork() statistics: - 31) sbf_cnt is not used - 32) sbf_balanced is not used - 33) sbf_pushed is not used + 40) sbf_cnt is not used + 41) sbf_balanced is not used + 42) sbf_pushed is not used Next three are try_to_wake_up() statistics: - 34) # of times in this domain try_to_wake_up() awoke a task that + 43) # of times in this domain try_to_wake_up() awoke a task that last ran on a different cpu in this domain - 35) # of times in this domain try_to_wake_up() moved a task to the + 44) # of times in this domain try_to_wake_up() moved a task to the waking cpu because it was cache-cold on its own cpu anyway - 36) # of times in this domain try_to_wake_up() started passive balancing + 45) # of times in this domain try_to_wake_up() started passive balancing /proc//schedstat --------------------- diff --git a/Documentation/scsi/scsi_eh.rst b/Documentation/scsi/scsi_eh.rst index 104d09e9af09..36cff176c5e6 100644 --- a/Documentation/scsi/scsi_eh.rst +++ b/Documentation/scsi/scsi_eh.rst @@ -54,13 +54,13 @@ invoking hostt->queuecommand() or the block layer will time it out. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ For all non-EH commands, scsi_done() is the completion callback. It -just calls blk_complete_request() to delete the block layer timer and -raise SCSI_SOFTIRQ +just calls blk_mq_complete_request() to delete the block layer timer and +raise BLOCK_SOFTIRQ. -SCSI_SOFTIRQ handler scsi_softirq calls scsi_decide_disposition() to -determine what to do with the command. scsi_decide_disposition() -looks at the scmd->result value and sense data to determine what to do -with the command. +The BLOCK_SOFTIRQ indirectly calls scsi_complete(), which calls +scsi_decide_disposition() to determine what to do with the command. +scsi_decide_disposition() looks at the scmd->result value and sense +data to determine what to do with the command. - SUCCESS @@ -110,7 +110,7 @@ The timeout handler is scsi_timeout(). When a timeout occurs, this function retry which failed), when retries are exceeded, or when the EH deadline is expired. In these cases Step #3 is taken. - 3. scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD) is invoked for the + 3. scsi_eh_scmd_add(scmd) is invoked for the command. See [1-4] for more information. 1.3 Asynchronous command aborts @@ -277,7 +277,6 @@ scmd->allowed. :ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd - - scsi_setup_cmd_retry() - move from local eh_work_q to local eh_done_q :LOCKING: none @@ -317,7 +316,7 @@ scmd->allowed. ``scsi_eh_get_sense`` This action is taken for each error-completed - (!SCSI_EH_CANCEL_CMD) commands without valid sense data. Most + command without valid sense data. Most SCSI transports/LLDDs automatically acquire sense data on command failures (autosense). Autosense is recommended for performance reasons and as sense information could get out of @@ -347,30 +346,6 @@ scmd->allowed. - otherwise No action. - 3. If !list_empty(&eh_work_q), invoke scsi_eh_abort_cmds(). - - ``scsi_eh_abort_cmds`` - - This action is taken for each timed out command when - no_async_abort is enabled in the host template. - hostt->eh_abort_handler() is invoked for each scmd. The - handler returns SUCCESS if it has succeeded to make LLDD and - all related hardware forget about the scmd. - - If a timedout scmd is successfully aborted and the sdev is - either offline or ready, scsi_eh_finish_cmd() is invoked for - the scmd. Otherwise, the scmd is left in eh_work_q for - higher-severity actions. - - Note that both offline and ready status mean that the sdev is - ready to process new scmds, where processing also implies - immediate failing; thus, if a sdev is in one of the two - states, no further recovery action is needed. - - Device readiness is tested using scsi_eh_tur() which issues - TEST_UNIT_READY command. Note that the scmd must have been - aborted successfully before reusing it for TEST_UNIT_READY. - 4. If !list_empty(&eh_work_q), invoke scsi_eh_ready_devs() ``scsi_eh_ready_devs`` @@ -384,7 +359,7 @@ scmd->allowed. For each sdev which has failed scmds with valid sense data of which scsi_check_sense()'s verdict is FAILED, - START_STOP_UNIT command is issued w/ start=1. Note that + START STOP UNIT command is issued w/ start=1. Note that as we explicitly choose error-completed scmds, it is known that lower layers have forgotten about the scmd and we can reuse it for STU. @@ -478,9 +453,6 @@ except for #1 must be implemented by eh_strategy_handler(). - shost->host_failed is zero. - - Each scmd is in such a state that scsi_setup_cmd_retry() on the - scmd doesn't make any difference. - - shost->eh_cmd_q is cleared. - Each scmd->eh_entry is cleared. diff --git a/Documentation/scsi/scsi_mid_low_api.rst b/Documentation/scsi/scsi_mid_low_api.rst index 2df29b92e196..3cd6dce98e74 100644 --- a/Documentation/scsi/scsi_mid_low_api.rst +++ b/Documentation/scsi/scsi_mid_low_api.rst @@ -101,7 +101,7 @@ supplied functions" below. Those functions in group b) are listed in a section entitled "Interface functions" below. Their function pointers are placed in the members of "struct scsi_host_template", an instance of which is passed to -scsi_host_alloc() [#]_. Those interface functions that the LLD does not +scsi_host_alloc(). Those interface functions that the LLD does not wish to supply should have NULL placed in the corresponding member of struct scsi_host_template. Defining an instance of struct scsi_host_template at file scope will cause NULL to be placed in function @@ -112,12 +112,9 @@ Those usages in group c) should be handled with care, especially in a that are shared with the mid level and other layers. All functions defined within an LLD and all data defined at file scope -should be static. For example the slave_alloc() function in an LLD +should be static. For example the sdev_init() function in an LLD called "xxx" could be defined as -``static int xxx_slave_alloc(struct scsi_device * sdev) { /* code */ }`` - -.. [#] the scsi_host_alloc() function is a replacement for the rather vaguely - named scsi_register() function in most situations. +``static int xxx_sdev_init(struct scsi_device * sdev) { /* code */ }`` Hotplug initialization model @@ -149,21 +146,21 @@ scsi devices of which only the first 2 respond:: scsi_add_host() ----> scsi_scan_host() -------+ | - slave_alloc() - slave_configure() --> scsi_change_queue_depth() + sdev_init() + sdev_configure() --> scsi_change_queue_depth() | - slave_alloc() - slave_configure() + sdev_init() + sdev_configure() | - slave_alloc() *** - slave_destroy() *** + sdev_init() *** + sdev_destroy() *** *** For scsi devices that the mid level tries to scan but do not - respond, a slave_alloc(), slave_destroy() pair is called. + respond, a sdev_init(), sdev_destroy() pair is called. If the LLD wants to adjust the default queue settings, it can invoke -scsi_change_queue_depth() in its slave_configure() routine. +scsi_change_queue_depth() in its sdev_configure() routine. When an HBA is being removed it could be as part of an orderly shutdown associated with the LLD module being unloaded (e.g. with the "rmmod" @@ -176,8 +173,8 @@ same:: ===----------------------=========-----------------===------ scsi_remove_host() ---------+ | - slave_destroy() - slave_destroy() + sdev_destroy() + sdev_destroy() scsi_host_put() It may be useful for a LLD to keep track of struct Scsi_Host instances @@ -202,8 +199,8 @@ An LLD can use this sequence to make the mid level aware of a SCSI device:: ===-------------------=========--------------------===------ scsi_add_device() ------+ | - slave_alloc() - slave_configure() [--> scsi_change_queue_depth()] + sdev_init() + sdev_configure() [--> scsi_change_queue_depth()] In a similar fashion, an LLD may become aware that a SCSI device has been removed (unplugged) or the connection to it has been interrupted. Some @@ -218,12 +215,12 @@ upper layers with this sequence:: ===----------------------=========-----------------===------ scsi_remove_device() -------+ | - slave_destroy() + sdev_destroy() It may be useful for an LLD to keep track of struct scsi_device instances -(a pointer is passed as the parameter to slave_alloc() and -slave_configure() callbacks). Such instances are "owned" by the mid-level. -struct scsi_device instances are freed after slave_destroy(). +(a pointer is passed as the parameter to sdev_init() and +sdev_configure() callbacks). Such instances are "owned" by the mid-level. +struct scsi_device instances are freed after sdev_destroy(). Reference Counting @@ -302,14 +299,12 @@ Summary: - scsi_host_alloc - return a new scsi_host instance whose refcount==1 - scsi_host_get - increments Scsi_Host instance's refcount - scsi_host_put - decrements Scsi_Host instance's refcount (free if 0) - - scsi_register - create and register a scsi host adapter instance. - scsi_remove_device - detach and remove a SCSI device - scsi_remove_host - detach and remove all SCSI devices owned by host - scsi_report_bus_reset - report scsi _bus_ reset observed - scsi_scan_host - scan SCSI bus - scsi_track_queue_full - track successive QUEUE_FULL events - scsi_unblock_requests - allow further commands to be queued to given host - - scsi_unregister - [calls scsi_host_put()] Details:: @@ -331,7 +326,7 @@ Details:: * bus scan when an HBA is added (i.e. scsi_scan_host()). So it * should only be called if the HBA becomes aware of a new scsi * device (lu) after scsi_scan_host() has completed. If successful - * this call can lead to slave_alloc() and slave_configure() callbacks + * this call can lead to sdev_init() and sdev_configure() callbacks * into the LLD. * * Defined in: drivers/scsi/scsi_scan.c @@ -374,8 +369,8 @@ Details:: * Might block: no * * Notes: Can be invoked any time on a SCSI device controlled by this - * LLD. [Specifically during and after slave_configure() and prior to - * slave_destroy().] Can safely be invoked from interrupt code. + * LLD. [Specifically during and after sdev_configure() and prior to + * sdev_destroy().] Can safely be invoked from interrupt code. * * Defined in: drivers/scsi/scsi.c [see source code for more notes] * @@ -474,27 +469,6 @@ Details:: void scsi_host_put(struct Scsi_Host *shost) - /** - * scsi_register - create and register a scsi host adapter instance. - * @sht: pointer to scsi host template - * @privsize: extra bytes to allocate in hostdata array (which is the - * last member of the returned Scsi_Host instance) - * - * Returns pointer to new Scsi_Host instance or NULL on failure - * - * Might block: yes - * - * Notes: When this call returns to the LLD, the SCSI bus scan on - * this host has _not_ yet been done. - * The hostdata array (by default zero length) is a per host scratch - * area for the LLD. - * - * Defined in: drivers/scsi/hosts.c . - **/ - struct Scsi_Host * scsi_register(struct scsi_host_template * sht, - int privsize) - - /** * scsi_remove_device - detach and remove a SCSI device * @sdev: a pointer to a scsi device instance @@ -506,7 +480,7 @@ Details:: * Notes: If an LLD becomes aware that a scsi device (lu) has * been removed but its host is still present then it can request * the removal of that scsi device. If successful this call will - * lead to the slave_destroy() callback being invoked. sdev is an + * lead to the sdev_destroy() callback being invoked. sdev is an * invalid pointer after this call. * * Defined in: drivers/scsi/scsi_sysfs.c . @@ -524,7 +498,7 @@ Details:: * * Notes: Should only be invoked if the "hotplug initialization * model" is being used. It should be called _prior_ to - * scsi_unregister(). + * calling scsi_host_put(). * * Defined in: drivers/scsi/hosts.c . **/ @@ -601,43 +575,24 @@ Details:: void scsi_unblock_requests(struct Scsi_Host * shost) - /** - * scsi_unregister - unregister and free memory used by host instance - * @shp: pointer to scsi host instance to unregister. - * - * Returns nothing - * - * Might block: no - * - * Notes: Should not be invoked if the "hotplug initialization - * model" is being used. Called internally by exit_this_scsi_driver() - * in the "passive initialization model". Hence a LLD has no need to - * call this function directly. - * - * Defined in: drivers/scsi/hosts.c . - **/ - void scsi_unregister(struct Scsi_Host * shp) - - - Interface Functions =================== Interface functions are supplied (defined) by LLDs and their function pointers are placed in an instance of struct scsi_host_template which -is passed to scsi_host_alloc() [or scsi_register() / init_this_scsi_driver()]. +is passed to scsi_host_alloc(). Some are mandatory. Interface functions should be declared static. The -accepted convention is that driver "xyz" will declare its slave_configure() +accepted convention is that driver "xyz" will declare its sdev_configure() function as:: - static int xyz_slave_configure(struct scsi_device * sdev); + static int xyz_sdev_configure(struct scsi_device * sdev); and so forth for all interface functions listed below. -A pointer to this function should be placed in the 'slave_configure' member +A pointer to this function should be placed in the 'sdev_configure' member of a "struct scsi_host_template" instance. A pointer to such an instance -should be passed to the mid level's scsi_host_alloc() [or scsi_register() / -init_this_scsi_driver()]. +should be passed to the mid level's scsi_host_alloc(). +. The interface functions are also described in the include/scsi/scsi_host.h file immediately above their definition point in "struct scsi_host_template". @@ -657,9 +612,9 @@ Summary: - ioctl - driver can respond to ioctls - proc_info - supports /proc/scsi/{driver_name}/{host_no} - queuecommand - queue scsi command, invoke 'done' on completion - - slave_alloc - prior to any commands being sent to a new device - - slave_configure - driver fine tuning for given device after attach - - slave_destroy - given device is about to be shut down + - sdev_init - prior to any commands being sent to a new device + - sdev_configure - driver fine tuning for given device after attach + - sdev_destroy - given device is about to be shut down Details:: @@ -728,11 +683,7 @@ Details:: * * Calling context: kernel thread * - * Notes: If 'no_async_abort' is defined this callback - * will be invoked from scsi_eh thread. No other commands - * will then be queued on current host during eh. - * Otherwise it will be called whenever scsi_timeout() - * is called due to a command timeout. + * Notes: This is called only for a command that has timed out. * * Optionally defined in: LLD **/ @@ -817,10 +768,6 @@ Details:: * The SCSI_IOCTL_PROBE_HOST ioctl yields the string returned by this * function (or struct Scsi_Host::name if this function is not * available). - * In a similar manner, init_this_scsi_driver() outputs to the console - * each host's "info" (or name) for the driver it is registering. - * Also if proc_info() is not supplied, the output of this function - * is used instead. * * Optionally defined in: LLD **/ @@ -960,7 +907,7 @@ Details:: /** - * slave_alloc - prior to any commands being sent to a new device + * sdev_init - prior to any commands being sent to a new device * (i.e. just prior to scan) this call is made * @sdp: pointer to new device (about to be scanned) * @@ -975,24 +922,24 @@ Details:: * prior to its initial scan. The corresponding scsi device may not * exist but the mid level is just about to scan for it (i.e. send * and INQUIRY command plus ...). If a device is found then - * slave_configure() will be called while if a device is not found - * slave_destroy() is called. + * sdev_configure() will be called while if a device is not found + * sdev_destroy() is called. * For more details see the include/scsi/scsi_host.h file. * * Optionally defined in: LLD **/ - int slave_alloc(struct scsi_device *sdp) + int sdev_init(struct scsi_device *sdp) /** - * slave_configure - driver fine tuning for given device just after it + * sdev_configure - driver fine tuning for given device just after it * has been first scanned (i.e. it responded to an * INQUIRY) * @sdp: device that has just been attached * * Returns 0 if ok. Any other return is assumed to be an error and * the device is taken offline. [offline devices will _not_ have - * slave_destroy() called on them so clean up resources.] + * sdev_destroy() called on them so clean up resources.] * * Locks: none * @@ -1004,11 +951,11 @@ Details:: * * Optionally defined in: LLD **/ - int slave_configure(struct scsi_device *sdp) + int sdev_configure(struct scsi_device *sdp) /** - * slave_destroy - given device is about to be shut down. All + * sdev_destroy - given device is about to be shut down. All * activity has ceased on this device. * @sdp: device that is about to be shut down * @@ -1023,12 +970,12 @@ Details:: * by this driver for given device should be freed now. No further * commands will be sent for this sdp instance. [However the device * could be re-attached in the future in which case a new instance - * of struct scsi_device would be supplied by future slave_alloc() - * and slave_configure() calls.] + * of struct scsi_device would be supplied by future sdev_init() + * and sdev_configure() calls.] * * Optionally defined in: LLD **/ - void slave_destroy(struct scsi_device *sdp) + void sdev_destroy(struct scsi_device *sdp) @@ -1039,7 +986,7 @@ struct scsi_host_template There is one "struct scsi_host_template" instance per LLD [#]_. It is typically initialized as a file scope static in a driver's header file. That way members that are not explicitly initialized will be set to 0 or NULL. -Member of interest: +Members of interest: name - name of driver (may contain spaces, please limit to @@ -1055,6 +1002,13 @@ Member of interest: - primary callback that the mid level uses to inject SCSI commands into an LLD. + vendor_id + - a unique value that identifies the vendor supplying + the LLD for the Scsi_Host. Used most often in validating + vendor-specific message requests. Value consists of an + identifier type and a vendor-specific value. + See scsi_netlink.h for a description of valid formats. + The structure is defined and commented in include/scsi/scsi_host.h .. [#] In extreme situations a single driver may have several instances @@ -1095,9 +1049,6 @@ of interest: - maximum number of commands that can be queued on devices controlled by the host. Overridden by LLD calls to scsi_change_queue_depth(). - no_async_abort - - 1=>Asynchronous aborts are not supported - - 0=>Timed-out commands will be aborted asynchronously hostt - pointer to driver's struct scsi_host_template from which this struct Scsi_Host instance was spawned @@ -1106,22 +1057,10 @@ of interest: transportt - pointer to driver's struct scsi_transport_template instance (if any). FC and SPI transports currently supported. - sh_list - - a double linked list of pointers to all struct Scsi_Host - instances (currently ordered by ascending host_no) - my_devices - - a double linked list of pointers to struct scsi_device - instances that belong to this host. hostdata[0] - area reserved for LLD at end of struct Scsi_Host. Size - is set by the second argument (named 'xtr_bytes') to - scsi_host_alloc() or scsi_register(). - vendor_id - - a unique value that identifies the vendor supplying - the LLD for the Scsi_Host. Used most often in validating - vendor-specific message requests. Value consists of an - identifier type and a vendor-specific value. - See scsi_netlink.h for a description of valid formats. + is set by the second argument (named 'privsize') to + scsi_host_alloc(). The scsi_host structure is defined in include/scsi/scsi_host.h @@ -1143,30 +1082,11 @@ Members of interest: cmnd - array containing SCSI command - cmnd_len + cmd_len - length (in bytes) of SCSI command sc_data_direction - direction of data transfer in data phase. See "enum dma_data_direction" in include/linux/dma-mapping.h - request_bufflen - - number of data bytes to transfer (0 if no data phase) - use_sg - - ==0 -> no scatter gather list, hence transfer data - to/from request_buffer - - >0 -> scatter gather list (actually an array) in - request_buffer with use_sg elements - request_buffer - - either contains data buffer or scatter gather list - depending on the setting of use_sg. Scatter gather - elements are defined by 'struct scatterlist' found - in include/linux/scatterlist.h . - done - - function pointer that should be invoked by LLD when the - SCSI command is completed (successfully or otherwise). - Should only be called by an LLD if the LLD has accepted - the command (i.e. queuecommand() returned or will return - 0). The LLD may invoke 'done' prior to queuecommand() - finishing. result - should be set by LLD prior to calling 'done'. A value of 0 implies a successfully completed command (and all @@ -1189,13 +1109,13 @@ Members of interest: device - pointer to scsi_device object that this command is associated with. - resid + resid_len (access by calling scsi_set_resid() / scsi_get_resid()) - an LLD should set this unsigned integer to the requested transfer length (i.e. 'request_bufflen') less the number - of bytes that are actually transferred. 'resid' is + of bytes that are actually transferred. 'resid_len' is preset to 0 so an LLD can ignore it if it cannot detect underruns (overruns should not be reported). An LLD - should set 'resid' prior to invoking 'done'. The most + should set 'resid_len' prior to invoking 'done'. The most interesting case is data transfers from a SCSI target device (e.g. READs) that underrun. underflow @@ -1204,10 +1124,10 @@ Members of interest: figure. Not many LLDs implement this check and some that do just output an error message to the log rather than report a DID_ERROR. Better for an LLD to implement - 'resid'. + 'resid_len'. -It is recommended that a LLD set 'resid' on data transfers from a SCSI -target device (e.g. READs). It is especially important that 'resid' is set +It is recommended that a LLD set 'resid_len' on data transfers from a SCSI +target device (e.g. READs). It is especially important that 'resid_len' is set when such data transfers have sense keys of MEDIUM ERROR and HARDWARE ERROR (and possibly RECOVERED ERROR). In these cases if a LLD is in doubt how much data has been received then the safest approach is to indicate no bytes have @@ -1217,7 +1137,7 @@ a LLD might use these helpers:: scsi_set_resid(SCpnt, scsi_bufflen(SCpnt)); where 'SCpnt' is a pointer to a scsi_cmnd object. To indicate only three 512 -bytes blocks has been received 'resid' could be set like this:: +bytes blocks have been received 'resid_len' could be set like this:: scsi_set_resid(SCpnt, scsi_bufflen(SCpnt) - (3 * 512)); diff --git a/Documentation/security/credentials.rst b/Documentation/security/credentials.rst index 357328d566c8..2aa0791bcefe 100644 --- a/Documentation/security/credentials.rst +++ b/Documentation/security/credentials.rst @@ -527,11 +527,6 @@ There are some functions to help manage credentials: This gets a reference on a live set of credentials, returning a pointer to that set of credentials. - - ``struct cred *get_new_cred(struct cred *cred);`` - - This gets a reference on a set of credentials that is under construction - and is thus still mutable, returning a pointer to that set of credentials. - Open File Credentials ===================== diff --git a/Documentation/sound/codecs/cs35l56.rst b/Documentation/sound/codecs/cs35l56.rst new file mode 100644 index 000000000000..98c6f6c74394 --- /dev/null +++ b/Documentation/sound/codecs/cs35l56.rst @@ -0,0 +1,292 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +===================================================================== +Audio drivers for Cirrus Logic CS35L54/56/57 Boosted Smart Amplifiers +===================================================================== +:Copyright: 2025 Cirrus Logic, Inc. and + Cirrus Logic International Semiconductor Ltd. + +Contact: patches@opensource.cirrus.com + +Summary +======= + +The high-level summary of this document is: + +**If you have a laptop that uses CS35L54/56/57 amplifiers but audio is not +working, DO NOT ATTEMPT TO USE FIRMWARE AND SETTINGS FROM ANOTHER LAPTOP, +EVEN IF THAT LAPTOP SEEMS SIMILAR.** + +The CS35L54/56/57 amplifiers must be correctly configured for the power +supply voltage, speaker impedance, maximum speaker voltage/current, and +other external hardware connections. + +The amplifiers feature advanced boost technology that increases the voltage +used to drive the speakers, while proprietary speaker protection algorithms +allow these boosted amplifiers to push the limits of the speakers without +causing damage. These **must** be configured correctly. + +Supported Cirrus Logic amplifiers +--------------------------------- + +The cs35l56 drivers support: + +* CS35L54 +* CS35L56 +* CS35L57 + +There are two drivers in the kernel + +*For systems using SoundWire*: sound/soc/codecs/cs35l56.c and associated files + +*For systems using HDA*: sound/pci/hda/cs35l56_hda.c + +Firmware +======== + +The amplifier is controlled and managed by firmware running on the internal +DSP. Firmware files are essential to enable the full capabilities of the +amplifier. + +Firmware is distributed in the linux-firmware repository: +https://gitlab.com/kernel-firmware/linux-firmware.git + +On most SoundWire systems the amplifier has a default minimum capability to +produce audio. However this will be + +* at low volume, to protect the speakers, since the speaker specifications + and power supply voltages are unknown. +* a mono mix of left and right channels. + +On some SoundWire systems that have both CS42L43 and CS35L56/57 the CS35L56/57 +receive their audio from the CS42L43 instead of directly from the host +SoundWire interface. These systems can be identified by the CS42L43 showing +in dmesg as a SoundWire device, but the CS35L56/57 as SPI. On these systems +the firmware is *mandatory* to enable receiving the audio from the CS42L43. + +On HDA systems the firmware is *mandatory* to enable HDA bridge mode. There +will not be any audio from the amplifiers without firmware. + +Cirrus Logic firmware files +--------------------------- + +Each amplifier requires two firmware files. One file has a .wmfw suffix, the +other has a .bin suffix. + +The firmware is customized by the OEM to match the hardware of each laptop, +and the firmware is specific to that laptop. Because of this, there are many +firmware files in linux-firmware for these amplifiers. Firmware files are +**not interchangeable between laptops**. + +Cirrus Logic submits files for known laptops to the upstream linux-firmware +repository. Providing Cirrus Logic is aware of a particular laptop and has +permission from the manufacturer to publish the firmware, it will be pushed +to linux-firmware. You may need to upgrade to a newer release of +linux-firmware to obtain the firmware for your laptop. + +**Important:** the Makefile for linux-firmware creates symlinks that are listed +in the WHENCE file. These symlinks are required for the CS35L56 driver to be +able to load the firmware. + +How do I know which firmware file I should have? +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +All firmware file names are qualified with a unique "system ID". On normal +x86 PCs with PCI audio this is the Vendor Subsystem ID (SSID) of the host +PCI audio interface. + +The SSID can be viewed using the lspci tool:: + + lspci -v -nn | grep -A2 -i audio + 0000:00:1f.3 Audio device [0403]: Intel Corporation Meteor Lake-P HD Audio Controller [8086:7e28] + Subsystem: Dell Meteor Lake-P HD Audio Controller [1028:0c63] + +In this example the SSID is 10280c63. + +The format of the firmware file names is: + + cs35lxx-b0-dsp1-misc-SSID[-spkidX]-ampN + +Where: + + * cs35lxx-b0 is the amplifier model and silicon revision. This information + is logged by the driver during initialization. + * SSID is the 8-digit hexadecimal SSID value. + * ampN is the amplifier number (for example amp1). This is the same as + the prefix on the ALSA control names except that it is always lower-case + in the file name. + * spkidX is an optional part, used for laptops that have firmware + configurations for different makes and models of internal speakers. + +Sound Open Firmware and ALSA topology files +------------------------------------------- + +All SoundWire systems will require a Sound Open Firmware (SOF) for the +host CPU audio DSP, together with an ALSA topology file (.tplg). + +The SOF firmware will usually be provided by the manufacturer of the host +CPU (i.e. Intel or AMD). The .tplg file is normally part of the SOF firmware +release. + +SOF binary builds are available from: https://github.com/thesofproject/sof-bin/releases + +The main SOF source is here: https://github.com/thesofproject + +ALSA-ucm configurations +----------------------- +Typically an appropriate ALSA-ucm configuration file is needed for +use-case managers and audio servers such as PipeWire. + +Configuration files are available from the alsa-ucm-conf repository: +https://git.alsa-project.org/?p=alsa-ucm-conf.git + +Kernel log messages +=================== + +SoundWire +--------- +A successful initialization will look like this (this will be repeated for +each amplifier):: + + [ 7.568374] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_P not found, using dummy regulator + [ 7.605208] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_IO not found, using dummy regulator + [ 7.605313] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_A not found, using dummy regulator + [ 7.939279] cs35l56 sdw:0:0:01fa:3556:01:0: Cirrus Logic CS35L56 Rev B0 OTP3 fw:3.4.4 (patched=0) + [ 7.947844] cs35l56 sdw:0:0:01fa:3556:01:0: Slave 4 state check1: UNATTACHED, status was 1 + [ 8.740280] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_B not found, using dummy regulator + [ 8.740552] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_AMP not found, using dummy regulator + [ 9.242164] cs35l56 sdw:0:0:01fa:3556:01:0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw: format 3 timestamp 0x66b2b872 + [ 9.242173] cs35l56 sdw:0:0:01fa:3556:01:0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw: Tue 05 Dec 2023 21:37:21 GMT Standard Time + [ 9.991709] cs35l56 sdw:0:0:01fa:3556:01:0: DSP1: Firmware: 1a00d6 vendor: 0x2 v3.11.23, 41 algorithms + [10.039098] cs35l56 sdw:0:0:01fa:3556:01:0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx-amp1.bin: v3.11.23 + [10.879235] cs35l56 sdw:0:0:01fa:3556:01:0: Slave 4 state check1: UNATTACHED, status was 1 + [11.401536] cs35l56 sdw:0:0:01fa:3556:01:0: Calibration applied + +HDA +--- +A successful initialization will look like this (this will be repeated for +each amplifier):: + + [ 6.306475] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: Cirrus Logic CS35L56 Rev B0 OTP3 fw:3.4.4 (patched=0) + [ 6.613892] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP system name: 'xxxxxxxx', amp name: 'AMP1' + [ 8.266660] snd_hda_codec_cs8409 ehdaudio0D0: bound i2c-CSC3556:00-cs35l56-hda.0 (ops cs35l56_hda_comp_ops [snd_hda_scodec_cs35l56]) + [ 8.287525] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw: format 3 timestamp 0x66b2b872 + [ 8.287528] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw: Tue 05 Dec 2023 21:37:21 GMT Standard Time + [ 9.984335] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP1: Firmware: 1a00d6 vendor: 0x2 v3.11.23, 41 algorithms + [10.085797] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx-amp1.bin: v3.11.23 + [10.655237] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: Calibration applied + +Important messages +~~~~~~~~~~~~~~~~~~ +Cirrus Logic CS35L56 Rev B0 OTP3 fw:3.4.4 (patched=0) + Shows that the driver has been able to read device ID registers from the + amplifier. + + * The actual amplifier type and silicon revision (CS35L56 B0 in this + example) is shown, as read from the amplifier identification registers. + * (patched=0) is normal, and indicates that the amplifier has been hard + reset and is running default ROM firmware. + * (patched=1) means that something has previously downloaded firmware + to the amplifier and the driver does not have control of the RESET + signal to be able to replace this preloaded firmware. This is normal + for systems where the BIOS downloads firmware to the amplifiers + before OS boot. + This status can also be seen if the cs35l56 kernel module is unloaded + and reloaded on a system where the driver does not have control of + RESET. SoundWire systems typically do not give the driver control of + RESET and only a BIOS (re)boot can reset the amplifiers. + +DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw + Shows that a .wmfw firmware file was found and downloaded. + +DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx-amp1.bin + Shows that a .bin firmware file was found and downloaded. + +Calibration applied + Factory calibration data in EFI was written to the amplifier. + +Error messages +============== +This section explains some of the error messages that the driver can log. + +Algorithm coefficient version %d.%d.%d but expected %d.%d.%d + The version of the .bin file content does not match the loaded firmware. + Caused by mismatched .wmfw and .bin file, or .bin file was found but + .wmfw was not. + +No %s for algorithm %x + The version of the .bin file content does not match the loaded firmware. + Caused by mismatched .wmfw and .bin file, or .bin file was found but + .wmfw was not. + +.bin file required but not found + HDA driver did not find a .bin file that matches this hardware. + +Calibration disabled due to missing firmware controls + Driver was not able to write EFI calibration data to firmware registers. + This typically means that either: + + * The driver did not find a suitable wmfw for this hardware, or + * The amplifier has already been patched with firmware by something + previously, and the driver does not have control of a hard RESET line + to be able to reset the amplifier and download the firmware files it + found. This situation is indicated by the device identification + string in the kernel log shows "(patched=1)" + +Failed to write calibration + Same meaning and cause as "Calibration disabled due to missing firmware + controls" + +Failed to read calibration data from EFI + Factory calibration data in EFI is missing, empty or corrupt. + This is most likely to be cause by accidentally deleting the file from + the EFI filesystem. + +No calibration for silicon ID + The factory calibration data in EFI does not match this hardware. + The most likely cause is that an amplifier has been replaced on the + motherboard without going through manufacturer calibration process to + generate calibration data for the new amplifier. + +Did not find any buses for CSCxxxx + Only on HDA systems. The HDA codec driver found an ACPI entry for + Cirrus Logic companion amps, but could not enumerate the ACPI entries for + the I2C/SPI buses. The most likely cause of this is that: + + * The relevant bus driver (I2C or SPI) is not part of the kernel. + * The HDA codec driver was built-in to the kernel but the I2C/SPI + bus driver is a module and so the HDA codec driver cannot call the + bus driver functions. + +init_completion timed out + The SoundWire bus controller (host end) did not enumerate the amplifier. + In other words, the ACPI says there is an amplifier but for some reason + it was not detected on the bus. + +No AF01 node + Indicates an error in ACPI. A SoundWire system should have a Device() + node named "AF01" but it was not found. + +Failed to get spk-id-gpios + ACPI says that the driver should request a GPIO but the driver was not + able to get that GPIO. The most likely cause is that the kernel does not + include the correct GPIO or PINCTRL driver for this system. + +Failed to read spk-id + ACPI says that the driver should request a GPIO but the driver was not + able to read that GPIO. + +Unexpected spk-id element count + AF01 contains more speaker ID GPIO entries than the driver supports + +Overtemp error + Amplifier overheat protection was triggered and the amplifier shut down + to protect itself. + +Amp short error + Amplifier detected a short-circuit on the speaker output pins and shut + down for protection. This would normally indicate a damaged speaker. + +Hibernate wake failed + The driver tried to wake the amplifier from its power-saving state but + did not see the expected responses from the amplifier. This can be caused + by using firmware that does not match the hardware. diff --git a/Documentation/sound/codecs/index.rst b/Documentation/sound/codecs/index.rst new file mode 100644 index 000000000000..2cb95d87bbef --- /dev/null +++ b/Documentation/sound/codecs/index.rst @@ -0,0 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Codec-Specific Information +========================== + +.. toctree:: + :maxdepth: 2 + + cs35l56 diff --git a/Documentation/sound/designs/midi-2.0.rst b/Documentation/sound/designs/midi-2.0.rst index 086487ca7ab1..71a343c93fe7 100644 --- a/Documentation/sound/designs/midi-2.0.rst +++ b/Documentation/sound/designs/midi-2.0.rst @@ -293,6 +293,17 @@ Rawmidi API Extensions status 0x05). When UMP core receives such a message, it updates the UMP EP info and the corresponding sequencer clients as well. +* The legacy rawmidi device number is found in the new `tied_device` + field of the rawmidi info. + On the other hand, the UMP rawmidi device number is found in + `tied_device` field of the legacy rawmidi info, too. + +* Each substream of the legacy rawmidi may be enabled / disabled + dynamically depending on the UMP FB state. + When the selected substream is inactive, it's indicated by the bit + 0x10 (`SNDRV_RAWMIDI_INFO_STREAM_INACTIVE`) in the `flags` field of + the legacy rawmidi info. + Control API Extensions ====================== @@ -377,6 +388,13 @@ Sequencer API Extensions announcement to the ALSA sequencer system port, similarly like the normal port change notification. +* There are two extended event types for notifying the UMP Endpoint and + Function Block changes via the system announcement port: + type 68 (`SNDRV_SEQ_EVENT_UMP_EP_CHANGE`) and type 69 + (`SNDRV_SEQ_EVENT_UMP_BLOCK_CHANGE`). They take the new type, + `snd_seq_ev_ump_notify` in the payload, indicating the client number + and the FB number that are changed. + MIDI2 USB Gadget Function Driver ================================ diff --git a/Documentation/sound/index.rst b/Documentation/sound/index.rst index c437f2a4bc85..51cd736f65b5 100644 --- a/Documentation/sound/index.rst +++ b/Documentation/sound/index.rst @@ -13,6 +13,7 @@ Sound Subsystem Documentation alsa-configuration hd-audio/index cards/index + codecs/index utimers .. only:: subproject and html diff --git a/Documentation/subsystem-apis.rst b/Documentation/subsystem-apis.rst index 74af50d2ef7f..b52ad5b969d4 100644 --- a/Documentation/subsystem-apis.rst +++ b/Documentation/subsystem-apis.rst @@ -60,6 +60,7 @@ Storage interfaces cdrom/index scsi/index target/index + nvme/index Other subsystems ---------------- diff --git a/Documentation/sunrpc/xdr/nfs4_1.x b/Documentation/sunrpc/xdr/nfs4_1.x new file mode 100644 index 000000000000..ca95150a3a29 --- /dev/null +++ b/Documentation/sunrpc/xdr/nfs4_1.x @@ -0,0 +1,186 @@ +/* + * Copyright (c) 2010 IETF Trust and the persons identified + * as the document authors. All rights reserved. + * + * The document authors are identified in RFC 3530 and + * RFC 5661. + * + * Redistribution and use in source and binary forms, with + * or without modification, are permitted provided that the + * following conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the + * following disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the + * following disclaimer in the documentation and/or other + * materials provided with the distribution. + * + * - Neither the name of Internet Society, IETF or IETF + * Trust, nor the names of specific contributors, may be + * used to endorse or promote products derived from this + * software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS + * AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO + * EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, + * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT + * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR + * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING + * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +pragma header nfs4; + +/* + * Basic typedefs for RFC 1832 data type definitions + */ +typedef hyper int64_t; +typedef unsigned int uint32_t; + +/* + * Basic data types + */ +typedef uint32_t bitmap4<>; + +/* + * Timeval + */ +struct nfstime4 { + int64_t seconds; + uint32_t nseconds; +}; + + +/* + * The following content was extracted from draft-ietf-nfsv4-delstid + */ + +typedef bool fattr4_offline; + + +const FATTR4_OFFLINE = 83; + + +struct open_arguments4 { + bitmap4 oa_share_access; + bitmap4 oa_share_deny; + bitmap4 oa_share_access_want; + bitmap4 oa_open_claim; + bitmap4 oa_create_mode; +}; + + +enum open_args_share_access4 { + OPEN_ARGS_SHARE_ACCESS_READ = 1, + OPEN_ARGS_SHARE_ACCESS_WRITE = 2, + OPEN_ARGS_SHARE_ACCESS_BOTH = 3 +}; + + +enum open_args_share_deny4 { + OPEN_ARGS_SHARE_DENY_NONE = 0, + OPEN_ARGS_SHARE_DENY_READ = 1, + OPEN_ARGS_SHARE_DENY_WRITE = 2, + OPEN_ARGS_SHARE_DENY_BOTH = 3 +}; + + +enum open_args_share_access_want4 { + OPEN_ARGS_SHARE_ACCESS_WANT_ANY_DELEG = 3, + OPEN_ARGS_SHARE_ACCESS_WANT_NO_DELEG = 4, + OPEN_ARGS_SHARE_ACCESS_WANT_CANCEL = 5, + OPEN_ARGS_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL + = 17, + OPEN_ARGS_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED + = 18, + OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 20, + OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 21 +}; + + +enum open_args_open_claim4 { + OPEN_ARGS_OPEN_CLAIM_NULL = 0, + OPEN_ARGS_OPEN_CLAIM_PREVIOUS = 1, + OPEN_ARGS_OPEN_CLAIM_DELEGATE_CUR = 2, + OPEN_ARGS_OPEN_CLAIM_DELEGATE_PREV = 3, + OPEN_ARGS_OPEN_CLAIM_FH = 4, + OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH = 5, + OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH = 6 +}; + + +enum open_args_createmode4 { + OPEN_ARGS_CREATEMODE_UNCHECKED4 = 0, + OPEN_ARGS_CREATE_MODE_GUARDED = 1, + OPEN_ARGS_CREATEMODE_EXCLUSIVE4 = 2, + OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1 = 3 +}; + + +typedef open_arguments4 fattr4_open_arguments; +pragma public fattr4_open_arguments; + + +%/* +% * Determine what OPEN supports. +% */ +const FATTR4_OPEN_ARGUMENTS = 86; + + + + +const OPEN4_RESULT_NO_OPEN_STATEID = 0x00000010; + + +/* + * attributes for the delegation times being + * cached and served by the "client" + */ +typedef nfstime4 fattr4_time_deleg_access; +typedef nfstime4 fattr4_time_deleg_modify; +pragma public fattr4_time_deleg_access; +pragma public fattr4_time_deleg_modify; + + +%/* +% * New RECOMMENDED Attribute for +% * delegation caching of times +% */ +const FATTR4_TIME_DELEG_ACCESS = 84; +const FATTR4_TIME_DELEG_MODIFY = 85; + + + +/* new flags for share_access field of OPEN4args */ +const OPEN4_SHARE_ACCESS_WANT_DELEG_MASK = 0xFF00; +const OPEN4_SHARE_ACCESS_WANT_NO_PREFERENCE = 0x0000; +const OPEN4_SHARE_ACCESS_WANT_READ_DELEG = 0x0100; +const OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG = 0x0200; +const OPEN4_SHARE_ACCESS_WANT_ANY_DELEG = 0x0300; +const OPEN4_SHARE_ACCESS_WANT_NO_DELEG = 0x0400; +const OPEN4_SHARE_ACCESS_WANT_CANCEL = 0x0500; + +const OPEN4_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL = 0x10000; +const OPEN4_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED = 0x20000; +const OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 0x100000; +const OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 0x200000; + +enum open_delegation_type4 { + OPEN_DELEGATE_NONE = 0, + OPEN_DELEGATE_READ = 1, + OPEN_DELEGATE_WRITE = 2, + OPEN_DELEGATE_NONE_EXT = 3, /* new to v4.1 */ + OPEN_DELEGATE_READ_ATTRS_DELEG = 4, + OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5 +}; diff --git a/Documentation/trace/events.rst b/Documentation/trace/events.rst index 759907c20e75..2d88a2acacc0 100644 --- a/Documentation/trace/events.rst +++ b/Documentation/trace/events.rst @@ -55,6 +55,30 @@ command:: # echo 'irq:*' > /sys/kernel/tracing/set_event +The set_event file may also be used to enable events associated to only +a specific module:: + + # echo ':mod:' > /sys/kernel/tracing/set_event + +Will enable all events in the module ````. If the module is not yet +loaded, the string will be saved and when a module is that matches ```` +is loaded, then it will apply the enabling of events then. + +The text before ``:mod:`` will be parsed to specify specific events that the +module creates:: + + # echo ':mod:' > /sys/kernel/tracing/set_event + +The above will enable any system or event that ```` matches. If +```` is ``"*"`` then it will match all events. + +To enable only a specific event within a system:: + + # echo '::mod:' > /sys/kernel/tracing/set_event + +If ```` is ``"*"`` then it will match all events within the system +for a given module. + 2.2 Via the 'enable' toggle --------------------------- diff --git a/Documentation/trace/fprobe.rst b/Documentation/trace/fprobe.rst index 196f52386aaa..71cd40472d36 100644 --- a/Documentation/trace/fprobe.rst +++ b/Documentation/trace/fprobe.rst @@ -9,9 +9,10 @@ Fprobe - Function entry/exit probe Introduction ============ -Fprobe is a function entry/exit probe mechanism based on ftrace. -Instead of using ftrace full feature, if you only want to attach callbacks -on function entry and exit, similar to the kprobes and kretprobes, you can +Fprobe is a function entry/exit probe based on the function-graph tracing +feature in ftrace. +Instead of tracing all functions, if you want to attach callbacks on specific +function entry and exit, similar to the kprobes and kretprobes, you can use fprobe. Compared with kprobes and kretprobes, fprobe gives faster instrumentation for multiple functions with single handler. This document describes how to use fprobe. @@ -91,12 +92,14 @@ The prototype of the entry/exit callback function are as follows: .. code-block:: c - int entry_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, void *entry_data); + int entry_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data); - void exit_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, void *entry_data); + void exit_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data); -Note that the @entry_ip is saved at function entry and passed to exit handler. -If the entry callback function returns !0, the corresponding exit callback will be cancelled. +Note that the @entry_ip is saved at function entry and passed to exit +handler. +If the entry callback function returns !0, the corresponding exit callback +will be cancelled. @fp This is the address of `fprobe` data structure related to this handler. @@ -112,12 +115,10 @@ If the entry callback function returns !0, the corresponding exit callback will This is the return address that the traced function will return to, somewhere in the caller. This can be used at both entry and exit. -@regs - This is the `pt_regs` data structure at the entry and exit. Note that - the instruction pointer of @regs may be different from the @entry_ip - in the entry_handler. If you need traced instruction pointer, you need - to use @entry_ip. On the other hand, in the exit_handler, the instruction - pointer of @regs is set to the current return address. +@fregs + This is the `ftrace_regs` data structure at the entry and exit. This + includes the function parameters, or the return values. So user can + access thos values via appropriate `ftrace_regs_*` APIs. @entry_data This is a local storage to share the data between entry and exit handlers. @@ -125,6 +126,17 @@ If the entry callback function returns !0, the corresponding exit callback will and `entry_data_size` field when registering the fprobe, the storage is allocated and passed to both `entry_handler` and `exit_handler`. +Entry data size and exit handlers on the same function +====================================================== + +Since the entry data is passed via per-task stack and it has limited size, +the entry data size per probe is limited to `15 * sizeof(long)`. You also need +to take care that the different fprobes are probing on the same function, this +limit becomes smaller. The entry data size is aligned to `sizeof(long)` and +each fprobe which has exit handler uses a `sizeof(long)` space on the stack, +you should keep the number of fprobes on the same function as small as +possible. + Share the callbacks with kprobes ================================ @@ -165,8 +177,8 @@ This counter counts up when; - fprobe fails to take ftrace_recursion lock. This usually means that a function which is traced by other ftrace users is called from the entry_handler. - - fprobe fails to setup the function exit because of the shortage of rethook - (the shadow stack for hooking the function return.) + - fprobe fails to setup the function exit because of failing to allocate the + data buffer from the per-task shadow stack. The `fprobe::nmissed` field counts up in both cases. Therefore, the former skips both of entry and exit callback and the latter skips the exit diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index 272464bb7c60..2b74f96d09d5 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -810,6 +810,12 @@ Here is the list of current tracers that may be configured. to draw a graph of function calls similar to C code source. + Note that the function graph calculates the timings of when the + function starts and returns internally and for each instance. If + there are two instances that run function graph tracer and traces + the same functions, the length of the timings may be slightly off as + each read the timestamp separately and not at the same time. + "blk" The block tracer. The tracer used by the blktrace user diff --git a/Documentation/trace/rv/runtime-verification.rst b/Documentation/trace/rv/runtime-verification.rst index dae78dfa7cdc..c700dde9259c 100644 --- a/Documentation/trace/rv/runtime-verification.rst +++ b/Documentation/trace/rv/runtime-verification.rst @@ -8,14 +8,14 @@ checking* and *theorem proving*) with a more practical approach for complex systems. Instead of relying on a fine-grained model of a system (e.g., a -re-implementation a instruction level), RV works by analyzing the trace of the +re-implementation at instruction level), RV works by analyzing the trace of the system's actual execution, comparing it against a formal specification of the system behavior. The main advantage is that RV can give precise information on the runtime behavior of the monitored system, without the pitfalls of developing models that require a re-implementation of the entire system in a modeling language. -Moreover, given an efficient monitoring method, it is possible execute an +Moreover, given an efficient monitoring method, it is possible to execute an *online* verification of a system, enabling the *reaction* for unexpected events, avoiding, for example, the propagation of a failure on safety-critical systems. diff --git a/Documentation/translations/it_IT/process/email-clients.rst b/Documentation/translations/it_IT/process/email-clients.rst index 97173746d8c9..9f8fe8abab4a 100644 --- a/Documentation/translations/it_IT/process/email-clients.rst +++ b/Documentation/translations/it_IT/process/email-clients.rst @@ -95,7 +95,7 @@ Nella sezione :menuselection:`Sending Preferences`: - :menuselection:`Strip Whitespace Before Sending` deve essere ``disabled`` Quando state scrivendo un messaggio, il cursore dev'essere posizionato -dove volete che la patch inizi, poi premendo :kbd:`CTRL-R` vi verrà chiesto +dove volete che la patch inizi, poi premendo `CTRL-R` vi verrà chiesto di selezionare il file patch da inserire nel messaggio. Claws Mail (GUI) @@ -104,7 +104,7 @@ Claws Mail (GUI) Funziona. Alcune persone riescono ad usarlo con successo per inviare le patch. Per inserire una patch usate :menuselection:`Messaggio-->Inserisci file` -(:kbd:`CTRL-I`) oppure un editor esterno. +(`CTRL-I`) oppure un editor esterno. Se la patch che avete inserito dev'essere modificata usando la finestra di scrittura di Claws, allora assicuratevi che l'"auto-interruzione" sia @@ -117,10 +117,10 @@ Alcune persone riescono ad usarlo con successo per inviare le patch. Quando state scrivendo una lettera selezionate: Preformattato da :menuselection:`Formato-->Stile del paragrafo-->Preformattato` - (:kbd:`CTRL-7`) o dalla barra degli strumenti + (`CTRL-7`) o dalla barra degli strumenti Poi per inserire la patch usate: -:menuselection:`Inserisci--> File di testo...` (:kbd:`ALT-N x`) +:menuselection:`Inserisci--> File di testo...` (`ALT-N x`) Potete anche eseguire ``diff -Nru old.c new.c | xclip``, selezionare :menuselection:`Preformattato`, e poi usare il tasto centrale del mouse. diff --git a/Documentation/translations/sp_SP/index.rst b/Documentation/translations/sp_SP/index.rst index aae7018b0d1a..2b50283e1608 100644 --- a/Documentation/translations/sp_SP/index.rst +++ b/Documentation/translations/sp_SP/index.rst @@ -7,7 +7,7 @@ Traducción al español \kerneldocCJKoff -:maintainer: Carlos Bilbao +:maintainer: Carlos Bilbao .. _sp_disclaimer: diff --git a/Documentation/translations/sp_SP/process/3.Early-stage.rst b/Documentation/translations/sp_SP/process/3.Early-stage.rst index 71cfb3fb0fda..bb3c630c7fd4 100644 --- a/Documentation/translations/sp_SP/process/3.Early-stage.rst +++ b/Documentation/translations/sp_SP/process/3.Early-stage.rst @@ -1,11 +1,241 @@ .. include:: ../disclaimer-sp.rst :Original: Documentation/process/3.Early-stage.rst +:Translator: Carlos Bilbao and Avadhut Naik .. _sp_development_early_stage: Planificación en etapa inicial ============================== -.. warning:: - TODO aún no traducido +Cuando uno se sienta a planear un proyecto de desarrollo del kernel Linux, +puede ser tentador lanzarse directamente a escribir código. Sin embargo, +como ocurre con cualquier proyecto significativo, gran parte del trabajo +que conduce al éxito es mejor realizarlo antes de escribir la primera línea +de código. Dedicar tiempo a la planificación y comunicación temprana puede +ahorrar mucho más tiempo en adelante. + +Especificar el problema +----------------------- + +Como en cualquier proyecto de ingeniería, una mejora exitosa del kernel +comienza con una descripción clara del problema a resolver. En algunos +casos, este paso es sencillo: cuando se necesita un driver para un hardware +específico, por ejemplo. En otros, sin embargo, es tentador confundir el +problema real con la solución propuesta, lo que puede generar dificultades. + +Consideremos un ejemplo: hace algunos años, los desarrolladores que +trabajaban con audio en Linux buscaban una forma de ejecutar aplicaciones +sin interrupciones u otros artefactos causados por la latencia excesiva en +el sistema. La solución a la que llegaron fue un módulo del kernel +destinado a integrarse en el marco del Módulo de Seguridad de Linux (LSM, +por sus siglas en inglés); este módulo podía configurarse para dar acceso a +aplicaciones específicas al planificador en tiempo real. Este módulo fue +implementado y enviado a la lista de correo del kernel de Linux, donde +inmediatamente encontró problemas. + +Para los desarrolladores de audio, este módulo de seguridad era suficiente +para resolver su problema inmediato. Sin embargo, para la comunidad más +amplia del kernel, se veía como un uso indebido del marco LSM (que no está +diseñado para otorgar privilegios a procesos que de otro modo no los +tendrían) y como un riesgo para la estabilidad del sistema. Sus soluciones +preferidas implicaban el acceso a la programación en tiempo real a través +del mecanismo de rlimit a corto plazo, y trabajo continuo para reducir la +latencia a largo plazo. + +La comunidad de audio, sin embargo, no podía ver más allá de la solución +particular que habían implementado; no estaban dispuestos a aceptar +alternativas. El desacuerdo resultante dejó a esos desarrolladores +desilusionados con todo el proceso de desarrollo del kernel; uno de ellos +volvió a una lista de audio y publicó esto (traducido): + + "Hay un buen número de desarrolladores muy competentes del kernel de Linux, pero tienden a ser opacados por una multitud de arrogantes necios. Intentar comunicar los requisitos de los usuarios a estas personas es una pérdida de tiempo. Son demasiado 'inteligentes' como para escuchar a simples mortales". + +Siendo el texto original: + + There are a number of very good Linux kernel developers, but they + tend to get outshouted by a large crowd of arrogant fools. Trying + to communicate user requirements to these people is a waste of + time. They are much too "intelligent" to listen to lesser mortals. + +(https://lwn.net/Articles/131776/). + +La realidad de la situación era diferente; los desarrolladores del kernel +estaban mucho más preocupados por la estabilidad del sistema, el +mantenimiento a largo plazo y encontrar la solución correcta al problema +que por un módulo específico. La moraleja de la historia es centrarse en el +problema, no en una solución específica, y discutirlo con la comunidad de +desarrollo antes de invertir en la creación de un cuerpo de código. + +Por lo tanto, al contemplar un proyecto de desarrollo del kernel, se deben +obtener respuestas a un conjunto corto de preguntas: + +- ¿Cuál es exactamente el problema que necesita ser resuelto? + +- ¿Quiénes son los usuarios afectados por este problema? ¿Qué casos de uso + debería abordar la solución? + +- ¿En qué aspectos el kernel actual no logra abordar ese problema? + +Solo entonces tiene sentido comenzar a considerar posibles soluciones. + +Discusión temprana +------------------ + +Al planificar un proyecto de desarrollo del kernel, tiene mucho sentido +realizar discusiones con la comunidad antes de lanzarse a la +implementación. La comunicación temprana puede ahorrar tiempo y problemas +de varias maneras: + +- Es posible que el problema ya esté siendo abordado por el kernel de + maneras que no haya comprendido. El kernel de Linux es grande y tiene + una serie de características y capacidades que no son inmediatamente + obvias. No todas las capacidades del kernel están documentadas tan bien + como uno quisiera, y es fácil pasar cosas por alto. El autor de este + texto ha visto la publicación de un driver completo que duplicaba uno + existente del que el nuevo autor no tenía conocimiento. El código que + reinventa ruedas existentes no solo es desperdicio; tampoco será aceptado + en el kernel principal. + +- Puede haber elementos de la solución propuesta que no serán aceptables + para su inclusión en el kernel principal. Es mejor descubrir problemas + como este antes de escribir el código. + +- Es completamente posible que otros desarrolladores ya hayan pensado en el + problema; pueden tener ideas para una mejor solución y estar dispuestos a + ayudar en la creación de esa solución. + +Años de experiencia con la comunidad de desarrollo del kernel han enseñado +una lección clara: el código del kernel que se diseña y desarrolla a +puertas cerradas invariablemente tiene problemas que solo se revelan cuando +el código se libera a la comunidad. A veces, estos problemas son graves, +requiriendo meses o años de esfuerzo antes de que el código pueda cumplir +con los estándares de la comunidad del kernel. Algunos ejemplos incluyen: + +- La pila de red Devicescape fue diseñada e implementada para sistemas de + un solo procesador. No pudo fusionarse en la rama principal hasta que se + hizo adecuada para sistemas multiprocesador. Adaptar el bloqueo y otros + aspectos en el código es una tarea difícil; como resultado, la fusión de + este código (ahora llamado mac80211) se retrasó más de un año. + +- El sistema de archivos Reiser4 incluía una serie de capacidades que, en + opinión de los desarrolladores principales del kernel, deberían haberse + implementado en la capa de sistemas de archivos virtuales. También + incluía funciones que no podían implementarse fácilmente sin exponer el + sistema a bloqueos causados por los usuarios. La revelación tardía de + estos problemas, y la negativa a abordar algunos de ellos, ha mantenido a + Reiser4 fuera del kernel principal. + +- El módulo de seguridad AppArmor hacía uso de estructuras de datos + internas del sistema de archivos virtual de maneras que se consideraban + inseguras y poco fiables. Esta preocupación (entre otras) mantuvo a + AppArmor fuera de la rama principal durante años. + +En cada uno de estos casos, se podría haber evitado mucho dolor y trabajo +adicional con algunas discusiones tempranas con los desarrolladores del +kernel. + +¿Con quién hablar? +------------------- + +Cuando los desarrolladores deciden hacer públicas sus ideas, la siguiente +pregunta será: ¿dónde empezar? La respuesta es encontrar la lista de correo +adecuada y el maintainer correcto. Para las listas de correo, la mejor +opción es buscar en el archivo MAINTAINERS un lugar relevante para +publicar. Si existe una lista de subsistema adecuada, es preferible +publicarla allí en lugar de en linux-kernel; es más probable que llegues a +desarrolladores con experiencia en el subsistema relevante y el ambiente +puede ser más propicio. + +Encontrar a los maintainers puede ser un poco más difícil. Nuevamente, el +archivo MAINTAINERS es el lugar para empezar. Sin embargo, ese archivo +tiende a no estar siempre actualizado, y no todos los subsistemas están +representados allí. La persona listada en el archivo MAINTAINERS puede, de +hecho, no ser la persona que está actuando en ese rol actualmente. Por lo +tanto, cuando haya dudas sobre a quién contactar, un truco útil es usar git +(y "git log" en particular) para ver quién está activo actualmente en el +subsistema de interés. Mira quién está escribiendo parches y quién, si +alguien, está adjuntando líneas de Signed-off-by a esos parches. Esas son +las personas que estarán mejor posicionadas para ayudar con un nuevo +proyecto de desarrollo. + +La tarea de encontrar al maintainer correcto es lo suficientemente +desafiante como para que los desarrolladores del kernel hayan añadido un +script para facilitar el proceso: + +:: + + .../scripts/get_maintainer.pl + +Este script devolverá los maintainers actuales de un archivo o directorio +dado cuando se le pase la opción "-f". Si se le pasa un parche en la línea +de comandos, listará a los maintainers que probablemente deberían recibir +copias del parche. Esta es la manera preferida (a diferencia de la opción +"-f") de obtener la lista de personas a las que hay que enviar las copias +de sus parches. Hay varias opciones que regulan cuán agresivamente +get_maintainer.pl buscará maintainers; por favor, ten cuidado al usar las +opciones más agresivas, ya que podrías terminar incluyendo desarrolladores +que no tienen ningún interés real en el código que estás modificando. + +Si todo lo demás falla, hablar con Andrew Morton puede ser una forma +efectiva de encontrar a un maintainer para un código específico. + +¿Cuándo publicar? +------------------ + +Si es posible, publicar sus planes en las primeras etapas solo puede ser +útil. Describa el problema que se está resolviendo y cualquier plan que se +haya hecho sobre cómo se llevará a cabo la implementación. Cualquier +información que puedas proporcionar puede ayudar a la comunidad de +desarrollo a ofrecer comentarios útiles sobre el proyecto. + +Una cosa desalentadora que puede suceder en esta etapa no es una reacción +hostil, sino, en cambio, poca o ninguna reacción en absoluto. La triste +realidad es que (1) los desarrolladores del kernel tienden a estar +ocupados, (2) no hay escasez de personas con grandes planes y poco código +(o incluso perspectivas de código) para respaldarlos, y (3) nadie está +obligado a revisar o comentar las ideas publicadas por otros. Además, los +diseños de alto nivel a menudo esconden problemas que solo se revelan +cuando alguien realmente intenta implementar esos diseños; por esa razón, +los desarrolladores del kernel prefieren ver el código. + +Si una publicación de solicitud de comentarios genera pocos comentarios, no +asuma que significa que no hay interés en el proyecto. Desafortunadamente, +tampoco puedes asumir que no hay problemas con tu idea. Lo mejor que puede +hacer en esta situación es seguir adelante, manteniendo informada a +comunidad a medida que avanza. + +Obtener respaldo oficial +------------------------ + +Si su trabajo se está realizando en un entorno corporativo — como ocurre +con la mayoría del trabajo en el kernel de Linux — es obvio que debe tener +permiso de los jefes debidamente autorizados antes de poder publicar los +planes o el código de su empresa en una lista de correo pública. La +publicación de código que no ha sido autorizado para su liberación bajo una +licencia compatible con la GPL puede ser especialmente problemática; cuanto +antes la gerencia y el personal legal de una empresa lleguen a un acuerdo +sobre la publicación de un proyecto de desarrollo del kernel, mejor será +para todos los involucrados. + +Algunos lectores pueden estar pensando en este momento que su trabajo en el +kernel está destinado a respaldar un producto que aún no ha sido reconocido +oficialmente. Revelar los planes de su empleador en una lista de correo +pública puede no ser una opción viable. En casos como este, vale la pena +considerar si realmente es necesario mantener el secreto; a menudo no hay +una necesidad real de mantener los planes de desarrollo en secreto. + +Dicho esto, también hay casos en los que una empresa legítimamente no puede +revelar sus planes al inicio del proceso de desarrollo. Las empresas con +desarrolladores experimentados en el kernel pueden optar por proceder de +manera abierta, bajo el supuesto de que podrán evitar problemas graves de +integración más adelante. Para las empresas sin ese tipo de experiencia +interna, la mejor opción suele ser contratar a un desarrollador externo +para que revise los planes bajo un acuerdo de confidencialidad (NDA). La +Linux Foundation opera un programa de NDA diseñado para ayudar en este tipo +de situaciones; se puede encontrar más información en: + + https://www.linuxfoundation.org/nda/ + +Este tipo de revisión suele ser suficiente para evitar problemas graves más +adelante sin necesidad de revelar públicamente el proyecto. diff --git a/Documentation/translations/sp_SP/process/4.Coding.rst b/Documentation/translations/sp_SP/process/4.Coding.rst index d9436e039b4b..7cc347c34354 100644 --- a/Documentation/translations/sp_SP/process/4.Coding.rst +++ b/Documentation/translations/sp_SP/process/4.Coding.rst @@ -1,11 +1,470 @@ .. include:: ../disclaimer-sp.rst :Original: Documentation/process/4.Coding.rst +:Translator: Carlos Bilbao and Avadhut Naik .. _sp_development_coding: Conseguir el código correcto ============================ -.. warning:: - TODO aún no traducido +Si bien hay mucho que decir a favor de un proceso de diseño sólido y +orientado a la comunidad, la prueba de cualquier proyecto de desarrollo del +kernel está en el código resultante. Es el código lo que será examinado por +otros desarrolladores y lo que será incluido (o no) en el árbol principal. +Por lo tanto, es la calidad de este código lo que determinará el éxito +final del proyecto. + +Esta sección examinará el proceso de programación. Comenzaremos observando +algunas de las maneras en que los desarrolladores del kernel pueden cometer +errores. Luego, el enfoque se dirigirá hacia hacer las cosas bien y las +herramientas que pueden ayudar en dicha búsqueda. + +Problemas +--------- + +Estilo de programación +********************** + +El kernel ha tenido durante mucho tiempo un estilo de programación +estándar, descrito en la documentación del kernel en +`Documentation/process/coding-style.rst`. Durante gran parte de ese tiempo, +las políticas descritas en ese archivo se tomaban como, en el mejor de los +casos, orientativas. Como resultado, hay una cantidad considerable de +código en el kernel que no cumple con las pautas de estilo de programación. +La presencia de ese código lleva a dos peligros independientes para los +desarrolladores del kernel. + +El primero de estos es creer que los estándares de programación del kernel +no importan y no se aplican. La realidad es que agregar nuevo código al +kernel es muy difícil si ese código no está escrito de acuerdo con el +estándar; muchos desarrolladores solicitarán que el código sea reformateado +antes de revisarlo. Una base de código tan grande como el kernel requiere +cierta uniformidad para que los desarrolladores puedan comprender +rápidamente cualquier parte de él. Así que ya no hay lugar para el código +con formato extraño. + +Ocasionalmente, el estilo de programación del kernel entrará en conflicto +con el estilo obligatorio de un empleador. En tales casos, el estilo del +kernel tendrá que prevalecer antes de que el código pueda ser fusionado. +Incluir código en el kernel significa renunciar a cierto grado de control +de varias maneras, incluida la forma en que se formatea el código. + +La otra trampa es asumir que el código que ya está en el kernel necesita +urgentemente correcciones de estilo de programación. Los desarrolladores +pueden comenzar a generar parches de reformateo como una forma de +familiarizarse con el proceso o como una forma de incluir su nombre en los +registros de cambios del kernel, o ambos. Pero las correcciones puramente +de estilo de programación son vistas como ruido por la comunidad de +desarrollo; tienden a recibir una recepción adversa. Por lo tanto, este +tipo de parche es mejor evitarlo. Es natural corregir el estilo de una +parte del código mientras se trabaja en él por otras razones, pero los +cambios de estilo de programación no deben hacerse por sí mismos. + +El documento de estilo de programación tampoco debe leerse como una ley +absoluta que nunca puede transgredirse. Si hay una buena razón para ir en +contra del estilo (una línea que se vuelve mucho menos legible si se divide +para ajustarse al límite de 80 columnas, por ejemplo), perfecto. + +Tenga en cuenta que también puedes usar la herramienta `clang-format` para +ayudarle con estas reglas, para reformatear rápidamente partes de su código +automáticamente y para revisar archivos completos a fin de detectar errores +de estilo de programación, errores tipográficos y posibles mejoras. También +es útil para ordenar `#includes`, alinear variables/macros, reformatear +texto y otras tareas similares. Consulte el archivo +`Documentation/dev-tools/clang-format.rst` para más detalles. + +Algunas configuraciones básicas del editor, como la indentación y los +finales de línea, se configurarán automáticamente si utilizas un editor +compatible con EditorConfig. Consulte el sitio web oficial de EditorConfig +para obtener más información: https://editorconfig.org/ + +Capas de abstracción +******************** + +Los profesores de ciencias de la computación enseñan a los estudiantes a +hacer un uso extensivo de capas de abstracción en nombre de la +flexibilidad y el ocultamiento de la información. Sin duda, el kernel hace +un uso extensivo de la abstracción; ningún proyecto que involucre varios +millones de líneas de código podría sobrevivir de otra manera. Pero la +experiencia ha demostrado que una abstracción excesiva o prematura puede +ser tan perjudicial como la optimización prematura. La abstracción debe +usarse en la medida necesaria y ya. + +A un nivel simple, considere una función que tiene un argumento que siempre +se pasa como cero por todos los que la invocan. Uno podría mantener ese +argumento por si alguien eventualmente necesita usar la flexibilidad +adicional que proporciona. Sin embargo, para entonces, es probable que el +código que implementa este argumento adicional se haya roto de alguna +manera sutil que nunca se notó, porque nunca se ha utilizado. O, cuando +surge la necesidad de flexibilidad adicional, no lo hace de una manera que +coincida con la expectativa temprana del programador. Los desarrolladores +del kernel rutinariamente enviarán parches para eliminar argumentos no +utilizados; en general, no deberían añadirse en primer lugar. + +Las capas de abstracción que ocultan el acceso al hardware, a menudo para +permitir que la mayor parte de un controlador se utilice con varios +sistemas operativos, son especialmente mal vistas. Dichas capas oscurecen +el código y pueden imponer una penalización en el rendimiento; no +pertenecen al kernel de Linux. + +Por otro lado, si se encuentra copiando cantidades significativas de código +de otro subsistema del kernel, es hora de preguntar si, de hecho, tendría +sentido extraer parte de ese código en una biblioteca separada o +implementar esa funcionalidad a un nivel superior. No tiene sentido +replicar el mismo código en todo el kernel. + +Uso de #ifdef y del preprocesador en general +******************************************** + +El preprocesador de C tiene una tentación poderosa para algunos +programadores de C, quienes lo ven como una forma de programar +eficientemente una gran cantidad de flexibilidad en un archivo fuente. Pero +el preprocesador no es C, y el uso intensivo de él da como resultado un +código mucho más difícil de leer para otros y más difícil de verificar por +el compilador para su corrección. El uso intensivo del preprocesador es +asi siempre un signo de un código que necesita algo de limpieza. + +La compilación condicional con `#ifdef` es, de hecho, una característica +poderosa, y se usa dentro del kernel. Pero hay poco deseo de ver código que +sté salpicado liberalmente con bloques `#ifdef`. Como regla general, el uso +de `#ifdef` debe limitarse a los archivos de encabezado siempre que sea +posible. El código condicionalmente compilado puede confinarse a funciones +que, si el código no va a estar presente, simplemente se convierten en +vacías. El compilador luego optimizará silenciosamente la llamada a la +función vacía. El resultado es un código mucho más limpio y fácil de +seguir. + +Las macros del preprocesador de C presentan varios peligros, incluida la +posible evaluación múltiple de expresiones con efectos secundarios y la +falta de seguridad de tipos. Si te sientes tentado a definir una macro, +considera crear una función en línea en su lugar. El código resultante será +el mismo, pero las funciones en línea son más fáciles de leer, no evalúan +sus argumentos varias veces y permiten que el compilador realice +comprobaciones de tipo en los argumentos y el valor de retorno. + +Funciones en línea +****************** + +Las funciones en línea presentan su propio peligro, sin embargo. Los +programadores pueden enamorarse de la eficiencia percibida al evitar una +llamada a función y llenar un archivo fuente con funciones en línea. Esas +funciones, sin embargo, pueden en realidad reducir el rendimiento. Dado que +su código se replica en cada sitio de llamada, terminan hinchando el tamaño +del kernel compilado. Eso, a su vez, crea presión en las cachés de memoria +del procesador, lo que puede ralentizar la ejecución de manera drástica +Las funciones en línea, como regla, deben ser bastante pequeñas y +relativamente raras. El costo de una llamada a función, después de todo, no +es tan alto; la creación de un gran número de funciones en línea es un +ejemplo clásico de optimización prematura. + +En general, los programadores del kernel ignoran los efectos de caché bajo +su propio riesgo. El clásico intercambio de tiempo/espacio que se enseña en +las clases de estructuras de datos iniciales a menudo no se aplica al +hardware contemporáneo. El espacio *es* tiempo, en el sentido de que un +programa más grande se ejecutará más lentamente que uno más compacto. + +Los compiladores más recientes toman un papel cada vez más activo al +decidir si una función dada debe realmente ser en línea o no. Por lo tanto, +la colocación liberal de palabras clave "inline" puede no solo ser +excesiva; también podría ser irrelevante. + +Bloqueo +******* + +En mayo de 2006, la pila de red "Devicescape" fue, con gran fanfarria, +lanzada bajo la licencia GPL y puesta a disposición para su inclusión en el +kernel principal. Esta donación fue una noticia bienvenida; el soporte para +redes inalámbricas en Linux se consideraba, en el mejor de los casos, +deficiente, y la pila de Devicescape ofrecía la promesa de solucionar esa +situación. Sin embargo, este código no fue incluido en el kernel principal +hasta junio de 2007 (versión 2.6.22). ¿Qué sucedió? + +Este código mostró varios signos de haber sido desarrollado a puertas +cerradas en una empresa. Pero un problema importante en particular fue que +no estaba diseñado para funcionar en sistemas multiprocesador. Antes de que +esta pila de red (ahora llamada mac80211) pudiera fusionarse, se tuvo que +implementar un esquema de bloqueo en ella. + +Hubo un tiempo en que se podía desarrollar código para el kernel de Linux +sin pensar en los problemas de concurrencia que presentan los sistemas +multiprocesador. Ahora, sin embargo, este documento se está escribiendo en +una computadora portátil con dos núcleos. Incluso en sistemas de un solo +procesador, el trabajo que se está realizando para mejorar la capacidad de +respuesta aumentará el nivel de concurrencia dentro del kernel. Los días en +que se podía escribir código para el kernel sin pensar en el bloqueo han +quedado atrás. + +Cualquier recurso (estructuras de datos, registros de hardware, etc.) que +pueda ser accedido concurrentemente por más de un hilo debe estar protegido +por un bloqueo. El nuevo código debe escribirse teniendo en cuenta este +requisito; implementar el bloqueo después de que el código ya ha sido +desarrollado es una tarea mucho más difícil. Los desarrolladores del kernel +deben tomarse el tiempo para comprender bien los primitivos de bloqueo +disponibles para elegir la herramienta adecuada para el trabajo. El código +que muestre una falta de atención a la concurrencia tendrá un camino +difícil para ser incluido en el kernel principal. + +Regresiones +*********** + +Un último peligro que vale la pena mencionar es el siguiente: puede ser +tentador realizar un cambio (que puede traer grandes mejoras) que cause un +problema para los usuarios existentes. Este tipo de cambio se llama una +"regresión", y las regresiones se han vuelto muy mal recibidas en el kernel +principal. Con pocas excepciones, los cambios que causan regresiones serán +revertidos si la regresión no se puede solucionar de manera oportuna. Es +mucho mejor evitar la regresión desde el principio. + +A menudo se argumenta que una regresión puede justificarse si hace que las +cosas funcionen para más personas de las que crea problemas. ¿Por qué no +hacer un cambio si trae nueva funcionalidad a diez sistemas por cada uno +que rompe? La mejor respuesta a esta pregunta fue expresada por Linus en +julio de 2007 (traducido): + +:: + + Entonces, no arreglamos errores introduciendo nuevos problemas. Eso + lleva a la locura, y nadie sabe si realmente se avanza. ¿Es dos pasos + adelante, uno atrás, o un paso adelante y dos atrás? + +(https://lwn.net/Articles/243460/). + +Un tipo de regresión especialmente mal recibido es cualquier tipo de cambio +en la ABI del espacio de usuario. Una vez que se ha exportado una interfaz +al espacio de usuario, debe ser soportada indefinidamente. Este hecho hace +que la creación de interfaces para el espacio de usuario sea +particularmente desafiante: dado que no pueden cambiarse de manera +incompatible, deben hacerse bien desde el principio. Por esta razón, +siempre se requiere una gran cantidad de reflexión, documentación clara y +una amplia revisión para las interfaces del espacio de usuario. + +Herramientas de verificación de código +************************************** + +Por ahora, al menos, escribir código libre de errores sigue siendo un ideal +que pocos de nosotros podemos alcanzar. Sin embargo, lo que podemos esperar +hacer es detectar y corregir tantos de esos errores como sea posible antes +de que nuestro código se integre en el kernel principal. Con ese fin, los +desarrolladores del kernel han reunido una impresionante variedad de +herramientas que pueden detectar una amplia variedad de problemas oscuros +de manera automatizada. Cualquier problema detectado por el ordenador es +un problema que no afectará a un usuario más adelante, por lo que es lógico +que las herramientas automatizadas se utilicen siempre que sea posible. + +El primer paso es simplemente prestar atención a las advertencias +producidas por el compilador. Las versiones contemporáneas de gcc pueden +detectar (y advertir sobre) una gran cantidad de errores potenciales. Con +bastante frecuencia, estas advertencias apuntan a problemas reales. El +código enviado para revisión no debería, por regla general, producir +ninguna advertencia del compilador. Al silenciar las advertencias, tenga +cuidado de comprender la causa real e intente evitar "correcciones" que +hagan desaparecer la advertencia sin abordar su causa. + +Tenga en cuenta que no todas las advertencias del compilador están +habilitadas de forma predeterminada. Compile el kernel con +"make KCFLAGS=-W" para obtener el conjunto completo. + +El kernel proporciona varias opciones de configuración que activan +funciones de depuración; la mayoría de estas se encuentran en el submenú +"kernel hacking". Varias de estas opciones deben estar activadas para +cualquier kernel utilizado para desarrollo o pruebas. En particular, +debería activar: + + - FRAME_WARN para obtener advertencias sobre marcos de pila más grandes + que una cantidad determinada. La salida generada puede ser extensa, pero + no es necesario preocuparse por las advertencias de otras partes del + kernel. + + - DEBUG_OBJECTS agregará código para rastrear la vida útil de varios + objetos creados por el kernel y advertir cuando se realicen cosas fuera + de orden. Si está agregando un subsistema que crea (y exporta) objetos + complejos propios, considere agregar soporte para la infraestructura de + depuración de objetos. + + - DEBUG_SLAB puede encontrar una variedad de errores en la asignación y + uso de memoria; debe usarse en la mayoría de los kernels de desarrollo. + + - DEBUG_SPINLOCK, DEBUG_ATOMIC_SLEEP y DEBUG_MUTEXES encontrarán una serie + de errores comunes de bloqueo. + +Hay bastantes otras opciones de depuración, algunas de las cuales se +discutirán más adelante. Algunas de ellas tienen un impacto significativo +en el rendimiento y no deben usarse todo el tiempo. Pero dedicar tiempo a +aprender las opciones disponibles probablemente será recompensado muchas +veces en poco tiempo. + +Una de las herramientas de depuración más pesadas es el verificador de +bloqueos, o "lockdep". Esta herramienta rastreará la adquisición y +liberación de cada bloqueo (spinlock o mutex) en el sistema, el orden en +que se adquieren los bloqueos en relación entre sí, el entorno actual de +interrupción, y más. Luego, puede asegurarse de que los bloqueos siempre se +adquieran en el mismo orden, que las mismas suposiciones de interrupción se +apliquen en todas las situaciones, y así sucesivamente. En otras palabras, +lockdep puede encontrar varios escenarios en los que el sistema podría, en +raras ocasiones, bloquearse. Este tipo de problema puede ser doloroso +(tanto para desarrolladores como para usuarios) en un sistema desplegado; +lockdep permite encontrarlos de manera automatizada con anticipación. El +código con cualquier tipo de bloqueo no trivial debe ejecutarse con lockdep +habilitado antes de ser enviado para su inclusión. + +Como programador diligente del kernel, sin duda alguna, verificará el +estado de retorno de cualquier operación (como una asignación de memoria) +que pueda fallar. Sin embargo, el hecho es que las rutas de recuperación de +fallos resultantes probablemente no hayan sido probadas en absoluto. El +código no probado tiende a ser código roto; podría tener mucha más +confianza en su código si todas esas rutas de manejo de errores se hubieran +ejercitado algunas veces. + +El kernel proporciona un marco de inyección de fallos que puede hacer +precisamente eso, especialmente donde están involucradas las asignaciones +de memoria. Con la inyección de fallos habilitada, un porcentaje +configurable de las asignaciones de memoria fallarán; estas fallas pueden +restringirse a un rango específico de código. Ejecutar con la inyección de +fallos habilitada permite al programador ver cómo responde el código cuando +las cosas van mal. Consulte +Documentation/fault-injection/fault-injection.rst para obtener más +información sobre cómo utilizar esta funcionalidad. + +Otros tipos de errores se pueden encontrar con la herramienta de análisis +estático "sparse". Con sparse, el programador puede recibir advertencias +sobre confusiones entre direcciones del espacio de usuario y del kernel, +mezcla de cantidades big-endian y little-endian, el paso de valores enteros +donde se espera un conjunto de banderas de bits, y así sucesivamente. +Sparse debe instalarse por separado (puede encontrarse en +https://sparse.wiki.kernel.org/index.php/Main_Page si su distribución no lo +empaqueta); luego, puede ejecutarse en el código agregando "C=1" a su +comando make. + +La herramienta "Coccinelle" (http://coccinelle.lip6.fr/) puede encontrar +una amplia variedad de posibles problemas de codificación; también puede +proponer correcciones para esos problemas. Bastantes "parches semánticos" +para el kernel se han empaquetado en el directorio scripts/coccinelle; +ejecutar "make coccicheck" ejecutará esos parches semánticos e informará +sobre cualquier problema encontrado. Consulte: +ref:`Documentation/dev-tools/coccinelle.rst ` para +obtener más información. + +Otros tipos de errores de portabilidad se encuentran mejor compilando su +código para otras arquitecturas. Si no tiene un sistema S/390 o una placa +de desarrollo Blackfin a mano, aún puede realizar el paso de compilación. +Un gran conjunto de compiladores cruzados para sistemas x86 se puede +encontrar en + + https://www.kernel.org/pub/tools/crosstool/ + +Muchos sistemas de compilación disponibles comercialmente también se pueden +utilizar para compilar código de kernel para una amplia gama de +arquitecturas. + +Los desarrolladores del kernel son afortunados: tienen acceso a una +variedad de herramientas de verificación de código de la que los +desarrolladores de la mayoría de los otros sistemas pueden estar celosos. +Pero todas esas herramientas no servirán de nada si no las usa. El +resultado final de ignorar estas herramientas es simple: alguien más puede +notificarle de un problema en su código a través de un "oportuno" +comentario en la lista de correo o, peor aún, el código problemático podría +ser eliminado. Es mucho más fácil usar estas herramientas en primer lugar. + +Documentación +************* + +La documentación a menudo ha sido más la excepción que la regla en el +desarrollo del kernel. Aun así, una documentación adecuada ayudará a +facilitar la integración de nuevo código en el kernel, hará la vida más +fácil a otros desarrolladores, y será útil para sus usuarios. En muchos +casos, la inclusión de documentación se ha vuelto esencialmente +obligatoria. + +La primera pieza de documentación para cualquier parche es su changelog +asociado. Las entradas de registro deben describir el problema que se está +esolviendo, la forma de la solución, las personas que trabajaron en el +parche, cualquier efecto relevante en el rendimiento, y cualquier otra cosa +que pueda ser necesaria para entender el parche. Asegúrese de que el +changelog diga *por qué* el parche vale la pena ser aplicado; un +sorprendente número de desarrolladores no proporciona esa información. + +Cualquier código que agregue una nueva interfaz para el espacio de usuario, +incluidos los nuevos archivos de sysfs o /proc, debe incluir documentación +de esa interfaz que permita a los desarrolladores del espacio de usuario +saber con qué están trabajando. Consulte `Documentation/ABI/README` para +una descripción de cómo debe formatearse esta documentación y qué +información debe proporcionarse. + +El archivo +:ref:`Documentation/admin-guide/kernel-parameters.rst ` +describe todos los parámetros de arranque del kernel. Cualquier parche que +agregue nuevos parámetros debe agregar las entradas correspondientes a este +archivo. + +Cualquier nueva opción de configuración debe ir acompañada de un texto de +ayuda que explique claramente las opciones y cuándo el usuario podría +querer seleccionarlas. + +La información de la API interna para muchos subsistemas está documentada +mediante comentarios especialmente formateados; estos comentarios pueden +extraerse y formatearse de diversas maneras mediante el script +"kernel-doc". Si está trabajando dentro de un subsistema que tiene +comentarios de kerneldoc, debe mantenerlos y agregarlos según corresponda +para las funciones disponibles externamente. Incluso en áreas que no han +sido tan documentadas, no hay ningún inconveniente en agregar comentarios +de kerneldoc para el futuro; de hecho, esta puede ser una actividad útil +para desarrolladores de kernel principiantes. El formato de estos +comentarios, junto con alguna información sobre cómo crear plantillas de +kerneldoc, se puede encontrar en +:ref:`Documentation/doc-guide/ `. + +Cualquiera que lea una cantidad significativa de código existente del +kernel notará que, a menudo, los comentarios son notables por su ausencia. +Una vez más, las expectativas para el nuevo código son más altas que en el +pasado; integrar código sin comentarios será más difícil. Dicho esto, hay +poco deseo de tener código excesivamente comentado. El código en sí debe +ser legible, con comentarios que expliquen los aspectos más sutiles. + +Ciertas cosas siempre deben comentarse. El uso de barreras de memoria debe +ir acompañado de una línea que explique por qué la barrera es necesaria. +Las reglas de bloqueo para las estructuras de datos generalmente necesitan +explicarse en algún lugar. Las estructuras de datos importantes en general +necesitan documentación completa. Las dependencias no obvias entre +fragmentos de código separados deben señalarse. Cualquier cosa que pueda +tentar a un maintainer de código a hacer una "limpieza" incorrecta necesita +un comentario que explique por qué se hace de esa manera. Y así +sucesivamente. + +Cambios en la API interna +************************* + +La interfaz binaria proporcionada por el kernel al espacio de usuario no se +puede romper, excepto en las circunstancias más graves. Las interfaces de +programación internas del kernel, en cambio, son altamente fluidas y pueden +cambiarse cuando surge la necesidad. Si usted se encuentra teniendo que +hacer un rodeo alrededor de una API del kernel, o simplemente no utilizando +una funcionalidad específica porque no cumple con sus necesidades, eso +puede ser una señal de que la API necesita cambiar. Como desarrollador del +kernel, usted está autorizado a hacer esos cambios. + +Hay, por supuesto, algunas condiciones. Los cambios en la API se pueden +hacer, pero necesitan estar bien justificados. Entonces, cualquier parche +que realice un cambio en la API interna debe ir acompañado de una +descripción de cuál es el cambio y por qué es necesario. Este tipo de +cambio también debe desglosarse en un parche separado, en lugar de estar +enterrado dentro de un parche más grande. + +La otra condición es que un desarrollador que cambia una API interna +generalmente está encargado de la tarea de corregir cualquier código dentro +del árbol del kernel que se vea afectado por el cambio. Para una función +ampliamente utilizada, este deber puede llevar a literalmente cientos o +miles de cambios, muchos de los cuales probablemente entren en conflicto +con el trabajo que otros desarrolladores están realizando. No hace falta +decir que esto puede ser un trabajo grande, por lo que es mejor asegurarse +de que la justificación sea sólida. Tenga en cuenta que la herramienta +Coccinelle puede ayudar con los cambios de API a gran escala. + +Cuando se realice un cambio incompatible en la API, siempre que sea +posible, se debe asegurar que el código que no ha sido actualizado sea +detectado por el compilador. Esto le ayudará a estar seguro de que ha +encontrado todos los usos en el árbol de esa interfaz. También alertará a +los desarrolladores de código fuera del árbol de que hay un cambio al que +necesitan responder. Apoyar el código fuera del árbol no es algo de lo que +los desarrolladores del kernel deban preocuparse, pero tampoco tenemos que +dificultarles la vida más de lo necesario. diff --git a/Documentation/translations/sp_SP/process/5.Posting.rst b/Documentation/translations/sp_SP/process/5.Posting.rst index 50a3bc5998a8..9e2ac9fdd63d 100644 --- a/Documentation/translations/sp_SP/process/5.Posting.rst +++ b/Documentation/translations/sp_SP/process/5.Posting.rst @@ -1,11 +1,391 @@ .. include:: ../disclaimer-sp.rst :Original: Documentation/process/5.Posting.rst +:Translator: Carlos Bilbao and Avadhut Naik .. _sp_development_posting: -Publicar parches -================ +Publicación de parches +====================== -.. warning:: - TODO aún no traducido +Tarde o temprano, llega el momento en que su trabajo esté listo para ser +presentado a la comunidad para su revisión y, eventualmente, su inclusión +en el kernel mainline. Como era de esperar, la comunidad de desarrollo del +kernel ha desarrollado un conjunto de convenciones y procedimientos que se +utilizan en la publicación de parches; seguirlos hará la vida mucho más +fácil para todos los involucrados. Este documento intentará cubrir estas +expectativas con un detalle razonable; también se puede encontrar más +información en los archivos. +:ref:`Documentation/translations/sp_SP/process/submitting-patches.rst ` +and :ref:`Documentation/translations/sp_SP/process/submit-checklist.rst ` + +Cuando publicar +--------------- + +Hay una tentación constante de evitar publicar parches antes de que +estén completamente “listos”. Para parches simples, eso no es un +problema. Sin embargo, si el trabajo que se está realizando es complejo, +hay mucho que ganar al obtener comentarios de la comunidad antes de que +se complete el trabajo. Por lo tanto, se debería considerar publicar +trabajo en progreso, o incluso poner a disposición un árbol de git para +que los desarrolladores interesados puedan ponerse al día con su trabajo +en cualquier momento. + +Al publicar código que aún no se considera listo para su inclusión, es +una buena idea decirlo en la propia publicación. Además, mencione +cualquier trabajo importante que aún falte por hacer y cualquier problema +conocido. Menos personas mirarán los parches que se sabe que están a +medias, pero aquellos que lo hagan vendrán con la idea de que pueden +ayudarlo a llevar el trabajo en la dirección correcta. + +Antes de crear parches +---------------------- + +Se deben hacer varias cosas antes de considerar enviar parches a la +comunidad de desarrollo. Estas incluyen: + + - Pruebe el código en la medida de lo posible. Utilice las herramientas + de depuración del kernel, asegúrese de que el kernel se compilará con + todas las combinaciones razonables de opciones de configuración, use + compiladores cruzados para compilar para diferentes arquitecturas, etc. + + - Asegúrese de que su código cumpla con las directrices de estilo de + codificación del kernel. + + - ¿Su cambio tiene implicaciones de rendimiento? Si es así, debe ejecutar + puntos de referencia que muestren cuál es el impacto (o beneficio) de + su cambio; se debe incluir un resumen de los resultados con el parche. + + - Asegúrese de que tiene derecho a publicar el código. Si este trabajo + se realizó para un empleador, es probable que el empleador tenga + derecho al trabajo y debe estar de acuerdo con su lanzamiento bajo la + GPL. + +Como regla general, pensar un poco más antes de publicar el código casi +siempre compensa el esfuerzo en poco tiempo. + +Preparación del parche +---------------------- + +La preparación de parches para su publicación puede ser una cantidad +sorprendente de trabajo, pero, una vez más, intentar ahorrar tiempo aquí +generalmente no es recomendable, ni siquiera a corto plazo. + +Los parches deben prepararse contra una versión específica del kernel. +Como regla general, un parche debe basarse en el mainline actual que se +encuentra en el árbol git de Linus. Al basarse en el mainline, comience +con un punto de lanzamiento bien conocido, una versión estable o -rc, en +lugar de bifurcarse fuera del mainline en un punto arbitrario. + +Puede ser necesario hacer revisiones contra -mm, linux-next o un árbol de +subsistemas para facilitar pruebas y revisiones más amplias. Dependiendo +del área de su parche y de lo que esté sucediendo en otros lugares, basar +un parche en estos otros árboles puede requerir una cantidad significativa +de trabajo para resolver conflictos y lidiar con los cambios de API. + +Solo los cambios más simples deben formatearse como un solo parche; todo +lo demás debe hacerse como una serie lógica de cambios. Dividir parches +es un poco un arte; algunos desarrolladores pasan mucho tiempo averiguando +cómo hacerlo de la manera que la comunidad espera. Sin embargo, hay +algunas reglas generales que pueden ayudar considerablemente: + + - La serie de parches que publique casi seguramente no será la serie de + cambios que se encuentran en su sistema de control de revisiones. En su + lugar, los cambios que ha realizado deben considerarse en su forma + final y luego dividirse de manera que tengan sentido. A los + desarrolladores les interesan los cambios discretos y autónomos, no el + camino que tomó para llegar a esos cambios. + + - Cada cambio lógicamente independiente debe formatearse como un parche + separado. Estos cambios pueden ser pequeños (“agregar un campo a esta + estructura”) o grandes (agregar un nuevo controlador significativo, + por ejemplo), pero deben ser conceptualmente pequeños y susceptibles + de una descripción de una línea. Cada parche debe hacer un cambio + especifico que pueda ser revisado por sí mismo y verificado para hacer + lo que dice que hace. + + - Para reafirmar la pauta anterior: no mezcle diferentes tipos de cambios + en el mismo parche. Si un solo parche corrige un error de seguridad + crítico, reorganiza algunas estructuras y reformatea el código, es muy + probable que se pase por alto y se pierda la solución importante. + + - Cada parche debe producir un kernel que se compile y funcione + correctamente; si su serie de parches se interrumpe en el medio, el + resultado debería seguir siendo un kernel funcional. La aplicación + parcial de una serie de parches es un escenario común cuando se + utiliza la herramienta “git bisect” para encontrar regresiones; si + el resultado es un kernel roto, hará la vida más difícil para los + desarrolladores y usuarios que participan en el noble trabajo de + rastrear problemas. + + - Sin embargo, no lo exagere. Un desarrollador una vez publicó un conjunto + de ediciones en un solo archivo como 500 parches separados – un acto + que no lo convirtió en la persona más popular en la lista de correo del + kernel. Un solo parche puede ser razonablemente grande si todavía + contiene un solo cambio *lógico*. + + - Puede ser tentador agregar una infraestructura completamente nueva con + una serie de parches, pero dejar esa infraestructura sin usar hasta el + parche final de la serie lo habilite todo. Esta tentación debe evitarse + si es posible; si esa serie agrega regresiones, bisection señalará el + ultimo parche como el que causó el problema, aunque el error real esté + en otra parte. Siempre que sea posible, un parche que agregue código + nuevo debe hacer que ese código se active de inmediato. + +Trabajar para crear la serie de parches perfecta puede ser un proceso +frustrante que lleva mucho tiempo y reflexión después de que el “trabajo +real” se ha hecho. Sin embargo, cuando se hace correctamente, es un tiempo +bien empleado. + +Formato de parches y registros de cambios +----------------------------------------- + +Así que ahora tiene una serie perfecta de parches para publicar, pero el +trabajo aún no se ha hecho. Cada parche necesita ser formateado en un +mensaje que comunique rápida y claramente su propósito al resto del +mundo. A tal fin, cada parche se compondrá de lo siguiente: + + - Una línea opcional “From” que nombra al autor del parche. Esta línea + solo es necesaria si pasa el parche de otra persona por correo + electrónico, pero nunca está de más agregarla en caso de duda. + + - Una descripción de una línea de lo que hace el parche. Este mensaje + debería ser suficiente para que un lector que lo vea sin otro contexto + pueda entender el alcance del parche; la línea aparecerá en los + registros de cambios de “forma corta”. Este mensaje generalmente se + formatea con el nombre del subsistema relevante primero, seguido del + propósito del parche. Por ejemplo: + + :: + + gpio: fix build on CONFIG_GPIO_SYSFS=n + + - Una línea en blanco seguida de una descripción detallada del contenido + del parche. Esta descripción puede ser tan larga como sea necesario; + debería decir qué hace el parche y por qué debe aplicarse al kernel. + + - Una o más líneas de etiquetas, con, como mínimo, una línea + Signed-off-by: del autor del parche. Las etiquetas se describirán con + más detalle a continuación. + +Los elementos de arriba, juntos, forman el registro de cambios para el +parche. Escribir buenos registros de cambios es un arte crucial, pero a +menudo descuidado; vale la pena pasar otro momento discutiendo este tema. +Al escribir un registro de cambios, debe recordar que muchas personas +diferentes leerán sus palabras. Estos incluyen a los maintainers y +revisores de subsistemas que necesitan decidir si el parche debe +incluirse, a los distribuidores y otros maintainers que intentan +determinar si un parche debe ser “backported” a otros kernels, a los +cazadores de errores que se preguntan si el parche es responsable de un +problema que están persiguiendo, a los usuarios que quieren saber cómo +ha cambiado el kernel, y más. Un buen registro de cambios transmite la +información necesaria a todas estas personas de la forma más directa y +concisa posible. + +Con ese fin, la línea de resumen debe describir los efectos y la +motivación del cambio, así como lo mejor posible dada la restricción de +una línea. La descripción detallada puede ampliar esos temas y +proporcionar cualquier información adicional necesaria. Si el parche +corrige un error, cita el commit que introdujo el error si es posible (y +por favor, proporcione tanto el ID del commit como el título al citar +commits). Si un problema está asociado con un registro específico o la +salida del compilador, incluya esa salida para ayudar a otros usuarios a +buscar una solución al mismo problema. Si el cambio está destinado a +apoyar otros cambios que llegarán en un parche posterior, dígalo. Si se +cambian las API internas, detalle esos cambios y cómo deben responder +otros desarrolladores. En general, cuanto más pueda ponerse en los zapatos +de todos los que leerán su registro de cambios, mejor será ese registro de +cambios (y el kernel en su conjunto). + +No hace falta decir que el registro de cambios debe ser el texto utilizado +al realizar el commit en un sistema de control de revisiones. Será seguido +por: + + - El parche, en el formato unificado de parche (“-u”). Usar la opción + “-p” en diff asociará los nombres de las funciones con los cambios, lo + que hará que el parche resultante sea más fácil de leer para otros. + +Debe evitar incluir cambios en archivos irrelevantes (los generados por +el proceso de compilación, por ejemplo, o los archivos de respaldo del +editor) en el parche. El archivo “dontdiff” en el directorio de +Documentation puede ayudar en este sentido; páselo a diff con la +opción “-X”. + +Las etiquetas ya mencionadas brevemente anteriormente proporcionan +información sobre cómo surgió el parche. Se describen en detalle en el +documento +:ref:`Documentation/translations/sp_SP/process/submitting-patches.rst `; +lo que sigue aquí es un breve resumen. + +Una etiqueta se usa para referirse a commits anteriores que introdujeron +problemas corregidos por el parche:: + + Fixes: 1f2e3d4c5b6a ("La primera línea del commit especificada por los primeros 12 caracteres de su ID SHA-1.") + +Otra etiqueta se utiliza para vincular páginas web con información +adicional o detalles, por ejemplo, una discusión previa que condujo al +parche o un documento con una especificación implementada por el parche:: + + Link: https://example.com/somewhere.html otras cosas opcionales + +Muchos maintainers, al aplicar un parche, también agregan esta etiqueta +para vincular a la última publicación de revisión pública del parche; a +menudo, eso se hace automáticamente mediante herramientas como b4 o git +hook como el que se describe en +'Documentation/maintainer/configure-git.rst'. + +Si la URL apunta a un informe de error público que está siendo corregido +por el parche, use la etiqueta “Closes:” (Cierra) en su lugar:: + + Closes: https://example.com/issues/1234 otras cosas opcionales + +Algunos rastreadores de errores tienen la capacidad de cerrar problemas +automáticamente cuando se aplica un commit con tal etiqueta. Algunos bots +que monitorean listas de correo también pueden rastrear dichas etiquetas +y realizar ciertas acciones. Los rastreadores de errores privados y las +URL no válidas están prohibidos. + +Otro tipo de etiqueta se utiliza para documentar quién estuvo involucrado +en el desarrollo del parche. Cada uno de estos utiliza este formato:: + + tag: Full Name otras cosas opcionales + +Las etiquetas de uso común son: + + - Signed-off-by: esta es una certificación del desarrollador de que él + o ella tiene el derecho de enviar el parche para su inclusión en el + kernel. Es un acuerdo con el Certificado de Origen del Desarrollador, + que se encuentra en + :ref:`Documentation/translations/sp_SP/process/submitting-patches.rst `. + El código sin la firma adecuada no se puede fusionar en el mainline. + + - Co-developed-by: indica que el parche fue co-creado por varios + desarrolladores; se utiliza para atribuir a los coautores (además del + autor atribuido por la etiqueta From:) cuando varias personas trabajan + en un solo parche. Cada Co-developed-by: debe ir seguido inmediatamente + por un Signedoff-by: del coautor asociado. Los detalles y ejemplos se + pueden encontrar en + :ref:`Documentation/translations/sp_SP/process/submitting-patches.rst `. + + - Acked-by: indica un acuerdo por parte de otro desarrollador (a menudo + un maintainer del código relevante) de que el parche es apropiado para + su inclusión en el kernel. + + - Tested-by: indica que la persona nombrada ha probado el parche y ha + encontrado que funciona. + + - Reviewed-by: el desarrollador nombrado ha revisado el parche para + verificar que sea correcto; consulte la declaración del revisor en + :ref:`Documentation/translations/sp_SP/process/submitting-patches.rst ` + para obtener más detalles. + + - Reported-by: nombra a un usuario que informó un problema que se + soluciona con este parche; esta etiqueta se utiliza para dar crédito + a las personas (a menudo infravalorada) que prueban nuestro código y + nos hacen saber cuándo las cosas no funcionan correctamente. Tenga en + cuenta que esta etiqueta debe ir seguida de una etiqueta Closes: que + apunte al informe, a menos que el informe no esté disponible en la + web. La etiqueta Link: se puede usar en lugar de Closes: si el parche + corrige una parte de los problemas reportados. + + - Cc: la persona nombrada recibió una copia del parche y tuvo la + oportunidad de comentar sobre él. + +Tenga cuidado al agregar etiquetas a sus parches, ya que solo Cc: es +apropiado para la adición sin el permiso explícito de la persona nombrada; +usar Reported-by: está casi bien en su mayoría, pero pida permiso si el +error fue reportado en privado. + +Envió del parche +---------------- + +Antes de enviar sus parches por correo, hay un par de cosas más de las +que debe ocuparse: + + - ¿Está seguro de que su correo no corromperá los parches? Los parches + con cambios gratuitos de espacio en blanco o ajuste de línea + realizados por el cliente de correo no se aplicarán en el otro + extremo, y a menudo, no se examinarán en detalle. Si tiene alguna + duda, envíese el parche por correo y convénzase de que parece + intacto. + + :ref:`Documentation/translations/sp_SP/process/email-clients.rst ` + tiene algunos consejos útiles sobre cómo hacer que clientes de correo + específicos funcionen para enviar parches. + + - ¿Está seguro de que su parche está libre de errores tontos? Siempre + debe ejecutar parches a través de scripts/checkpatch.pl y abordar las + quejas que surjan. Por favor, tenga en cuenta que checkpatch.pl, aunque + es la encarnación de una buena cantidad de pensamiento sobre cómo + deberían ser los parches del kernel, no es más inteligente que usted. + Si corregir una queja de checkpatch.pl empeoraría el código, no lo + haga. + +Los parches siempre deben enviarse como texto sin formato. Por favor, no +los envíe como archivos adjuntos; eso hace que sea mucho más difícil para +los revisores citar secciones del parche en sus respuestas. En su lugar, +simplemente coloca el parche directamente en su mensaje. + +Al enviar parches por correo, es importante enviar copias a cualquier +persona que pueda estar interesada en ellos. A diferencia de otros +proyectos, el kernel anima a la gente a equivocarse por el lado de enviar +demasiadas copias; no asuma que las personas relevantes verán su +publicación en las listas de correo. En particular, las copias deben +ir a: + + - El (los) maintainer(s) del (de los) subsistema(s) afectado(s). Como se + describió anteriormente, el archivo MAINTAINERS es el primer lugar para + buscar a estas personas. + + - Otros desarrolladores que han estado trabajando en la misma + área – especialmente aquellos que podrían estar trabajando allí ahora. + Usar git para ver quién más ha modificado los archivos en los que está + trabajando puede ser útil. + + - Si está respondiendo a un informe de error o a una solicitud de + función, copie también al autor. + + - Envié una copia a la lista de correo relevante o, si no se aplica nada + más, a la lista de linux-kernel. + + - Si está corrigiendo un error, piense si la corrección debe incluirse en + la próxima actualización estable. Si es así, stable@vger.kernel.org + debería obtener una copia del parche. También agregue un + "Cc: stable@vger.kernel.org" a las etiquetas dentro del parche; eso + hará que el equipo estable reciba una notificación cuando su solución + incluya en el mainline. + +Al seleccionar destinatarios para un parche, es bueno saber quién cree que +eventualmente aceptará el parche y lo fusionará. Aunque es posible enviar +parches directamente a Linus Torvalds y hacer que los fusione, las cosas +normalmente no se hacen de esa manera. Linus está ocupado y hay +maintainers de subsistemas que vigilan partes específicas del kernel. +Generalmente, querrá que ese maintainer fusione sus parches. Andrew Morton +es a menudo el objetivo del parche de último recurso si no hay un +maintainer obvio. + +Los parches necesitan buenas líneas de asunto. El formato canónico de una +línea de parche es algo así como: + +:: + + [PATCH nn/mm] subsys: descripción en una línea del parche + +donde “nn” es el número ordinal del parche, “”mm” es el número total de +parches en la serie, y “subsys” es el nombre del subsistema afectado. +Claramente, nn/mm se puede omitir para un parche único e independiente. + +Si tiene una serie significativa de parches, es costumbre enviar una +descripción introductoria como parte cero. Sin embargo, esta convención no +se sigue universalmente; si la utiliza, recuerde que la información en la +introducción no se incluye en los registros de cambios del kernel. Por lo +tanto, asegúrese de que los parches, en sí mismos, tengan información +completa del registro de cambios. + +En general, la segunda y las siguientes partes de un parche de varias +partes deben enviarse como una respuesta a la primera parte para que todas +se hilen juntas en el extremo receptor. Herramientas como git y quilt +tienen comandos para enviar por correo un conjunto de parches con el +subproceso adecuado. Sin embargo, si tiene una serie larga y está usando +git, por favor evite la opción –chain-reply-to para evitar crear un +anidamiento excepcionalmente profundo. diff --git a/Documentation/translations/sp_SP/process/6.Followthrough.rst b/Documentation/translations/sp_SP/process/6.Followthrough.rst index f0acf9082bb3..083898af46f5 100644 --- a/Documentation/translations/sp_SP/process/6.Followthrough.rst +++ b/Documentation/translations/sp_SP/process/6.Followthrough.rst @@ -1,11 +1,230 @@ .. include:: ../disclaimer-sp.rst :Original: Documentation/process/6.Followthrough.rst +:Translator: Carlos Bilbao and Avadhut Naik .. _sp_development_followthrough: Seguimiento =========== -.. warning:: - TODO aún no traducido +Llegados a este punto, ha seguido las directrices dadas hasta ahora, lo que +sumado a sus propias habilidades de ingeniería, ha resultado en una serie +de parches perfectos. Uno de los mayores errores que incluso los +desarrolladores de kernel experimentados pueden cometer es concluir que su +trabajo ya está hecho. En verdad, publicar parches indica una transición a +la siguiente etapa del proceso, con, posiblemente, bastante trabajo aún por +hacer. + +Es raro un parche que sea tan bueno en su primera publicación que no haya +espacio para la mejora. El proceso de desarrollo del kernel reconoce este +hecho y, como resultado, está muy orientado hacia la mejora del código +publicado. Y usted, como autor de ese código, se espera que trabaje con la +comunidad del kernel para asegurarse de que su código esté a la altura de +los estándares de calidad del kernel. No participar en este proceso es muy +probable que impida la inclusión de sus parches en la línea principal. + +Trabajando con revisores +------------------------ + +Un parche de cualquier importancia resultará en una serie de comentarios de +otros desarrolladores a medida que revisan el código. Trabajar con los +revisores puede ser, para muchos desarrolladores, la parte más intimidante +del proceso de desarrollo del kernel. Sin embargo, la vida puede ser mucho +más fácil si tiene en cuenta algunas cosas: + +- Si ha explicado bien su parche, los revisores entenderán su valor y por + qué se tomó la molestia de escribirlo. Pero ese valor no les impedirá + hacer una pregunta fundamental: ¿cómo será mantener un kernel con este + código en él cinco o diez años después? Muchos de los cambios que se le + pueden pedir que haga, desde ajustes de estilo de codificación hasta + reescrituras sustanciales, provienen de la comprensión de que Linux + seguirá existiendo y en desarrollo dentro de una década. + +- La revisión de código es un trabajo arduo y es una ocupación + relativamente ingrata; la gente recuerda quién escribió el código del + kernel, pero hay poca fama duradera para aquellos que lo revisaron. Así + que los revisores pueden ponerse de mal humor, especialmente cuando ven + los mismos errores repetirse una y otra vez. Si recibe una revisión que + parece enojada, insultante o abiertamente ofensiva, resista el impulso de + responder de la misma manera. La revisión de código se trata del código, + no de las personas, y los revisores de código no lo están atacando + personalmente. + +- De manera similar, los revisores de código no están tratando de promover + las agendas de sus empleadores a expensas de la suya. Los desarrolladores + del kernel a menudo esperan estar trabajando en el kernel dentro de + varios años, pero entienden que su empleador podría cambiar. + Verdaderamente, casi sin excepción, están trabajando hacia la creación + del mejor kernel posible; no están tratando de causar incomodidad a los + competidores de sus empleadores. + +- Esté preparado para solicitudes aparentemente ridículas de cambios en el + estilo de codificación y solicitudes para factorizar parte de su código + en partes compartidas del kernel. Una de las tareas que realizan los + maintainers es mantener las cosas con una apariencia uniforme. A veces, esto significa que el truco ingenioso en su driver para sortear un problema necesita convertirse en una característica generalizada del kernel lista para la próxima vez. + +En resumen, cuando los revisores le envían comentarios, necesita prestar +atención a las observaciones técnicas que están haciendo. No permita que su +forma de expresarse o su propio orgullo le impidan hacerlo. Cuando reciba +comentarios de revisión sobre un parche, tómese el tiempo para entender lo +que el revisor está tratando de decir. Si es posible, arregle las cosas que +el revisor le está pidiendo que corrija. Y responda al revisor: +agradézcales y describa cómo responderá a sus preguntas. + +Tenga en cuenta que no tiene que estar de acuerdo con cada cambio sugerido +por los revisores. Si cree que el revisor ha malinterpretado su código, +explique lo que realmente está sucediendo. Si tiene una objeción técnica a +un cambio sugerido, descríbalo y justifique su solución al problema. Si sus +explicaciones tienen sentido, el revisor las aceptará. Sin embargo, si su +explicación no resulta persuasiva, especialmente si otros comienzan a estar +de acuerdo con el revisor, tómese un tiempo para reflexionar nuevamente +sobre las cosas. Puede ser fácil quedar cegado por su propia solución a un +problema hasta el punto de no darse cuenta de que algo está +fundamentalmente mal o, quizás, ni siquiera está resolviendo el problema +correcto. + +Andrew Morton ha sugerido que cada comentario de revisión que no resulte en +un cambio de código debería resultar en un comentario adicional en el +código; eso puede ayudar a los revisores futuros a evitar las preguntas que +surgieron la primera vez. + +Un error fatal es ignorar los comentarios de revisión con la esperanza de +que desaparezcan. No desaparecerán. Si vuelve a publicar código sin haber +respondido a los comentarios que recibió la vez anterior, es probable que +descubra que sus parches no van a ninguna parte. + +Hablando de volver a publicar código: tenga en cuenta que los revisores no +recordarán todos los detalles del código que publicó la vez anterior. Así +que siempre es una buena idea recordarles sobre problemas planteados +anteriormente y cómo los manejó; el registro de cambios del parche es un +buen lugar para este tipo de información. Los revisores no deberían tener +que buscar en los archivos de la lista para familiarizarse con lo que se +dijo la última vez; si les ayuda a tener un buen comienzo, estarán de mejor +humor cuando revisiten su código. + +¿Qué sucede si ha intentado hacer todo bien y las cosas aún no van a +ninguna parte? La mayoría de los desacuerdos técnicos pueden resolverse +mediante discusión, pero hay momentos en los que alguien simplemente tiene +que tomar una decisión. Si realmente cree que esta decisión está en su +contra de manera incorrecta, siempre puede intentar apelar a una autoridad +superior. En el momento de escribir esto, esa autoridad superior tiende a +ser Andrew Morton. Andrew tiene un gran respeto en la comunidad de +desarrollo del kernel; a menudo puede desbloquear una situación que parece +estar irremediablemente bloqueada. Sin embargo, apelar a Andrew no debe +hacerse a la ligera, y no antes de que se hayan explorado todas las demás +alternativas. Y tenga en cuenta, por supuesto, que él puede no estar de +acuerdo con usted tampoco. + +¿Qué pasa después? +-------------------- + +Si un parche se considera algo bueno para agregar al kernel, y una vez que +se hayan resuelto la mayoría de los problemas de revisión, el siguiente +paso suele ser la entrada en el árbol del mantenedor de un subsistema. Cómo +funciona eso varía de un subsistema a otro; cada mantenedor tiene su propia +forma de hacer las cosas. En particular, puede haber más de un árbol, uno, +quizás, dedicado a los parches planificados para la próxima ventana de +fusión y otro para trabajos a más largo plazo. + +Para los parches que se aplican a áreas para las que no hay un árbol de +subsistema obvio (parches de gestión de memoria, por ejemplo), el árbol +predeterminado suele ser -mm. Los parches que afectan a múltiples +subsistemas también pueden terminar pasando por el árbol -mm. + +La inclusión en un árbol de subsistema puede dar mayor visibilidad a un +parche. Ahora, otros desarrolladores que trabajan con ese árbol recibirán +el parche por defecto. Los árboles de subsistemas típicamente alimentan +linux-next también, haciendo que su contenido sea visible para la comunidad +de desarrollo en su conjunto. En este punto, hay una buena probabilidad de +que reciba más comentarios de un nuevo conjunto de revisores; estos +comentarios necesitan ser respondidos como en la ronda anterior. + +Lo que también puede suceder en este punto, dependiendo de la naturaleza de +su parche, es que aparezcan conflictos con el trabajo que están realizando +otros. En el peor de los casos, conflictos pesados de parches pueden +resultar en que algunos trabajos se pongan en espera para que los parches +restantes puedan ser ajustados y fusionados. Otras veces, la resolución de +conflictos involucrará trabajar con otros desarrolladores y, posiblemente, +mover algunos parches entre árboles para asegurarse de que todo se aplique +sin problemas. Este trabajo puede ser un dolor, pero cuente sus +bendiciones: antes de la llegada del árbol linux-next, estos conflictos a +menudo solo surgían durante la ventana de fusión y tenían que ser abordados +de prisa. Ahora pueden resolverse con calma, antes de que se abra la +ventana de fusión (merge window). + +Algún día, si todo va bien, iniciará sesión y verá que su parche ha sido +incluido en el kernel principal. ¡Felicidades! Una vez que la celebración +termine (y se hayas agregado al archivo MAINTAINERS), vale la pena +recordar un pequeño hecho importante: el trabajo aún no está hecho. La +inclusión trae sus propios desafíos. + +Para empezar, la visibilidad de su parche ha aumentado una vez más. Puede +haber una nueva ronda de comentarios de desarrolladores que no estaban al +tanto del parche antes. Puede ser tentador ignorarlos, ya que ya no hay +cuestión de que su código sea fusionado. Sin embargo, resista esa +tentación; aún necesita ser receptivo a los desarrolladores que tienen +preguntas o sugerencias. + +Más importante aún, la inclusión en la línea principal pone su código en +manos de un grupo mucho más grande de probadores. Incluso si ha contribuido +un driver para hardware que aún no está disponible, se sorprenderá de +cuántas personas construirán su código en sus kernels. Y, por supuesto, +donde hay probadores, habrá informes de errores. + +El peor tipo de informes de errores son las regresiones. Si su parche causa +una regresión, encontrará un número incómodo de ojos sobre usted; las +regresiones pueden dar lugar a mucho malestar en la comunidad y pueden +hacer que algunos desarrolladores comiencen a preguntarse si su parche +realmente debería haber sido fusionado en primer lugar. Así que esté atento +a los comentarios sobre problemas y, si es posible, corrija los errores de +inmediato. + +Después de haber abordado cualquier regresión, puede haber otros errores +ordinarios que resolver. El período de estabilización es su mejor +oportunidad para corregir estos errores y garantizar que el debut de su +código en una versión del kernel principal sea lo más sólido posible. Así +que, por favor, responda a los informes de errores y solucione los +problemas si es posible. Para eso es el período de estabilización; puede +comenzar a crear parches nuevos y geniales una vez que se hayan resuelto +los problemas de los antiguos. + +Y no olvide que hay otros hitos que también pueden generar informes de +errores: la próxima versión estable del kernel principal, cuando +distribuidores prominentes adopten una versión del kernel que contenga su +parche, etc. Continuar respondiendo a estos informes es una cuestión de +orgullo básico en su trabajo. Sin embargo, si eso no es suficiente +motivación, también vale la pena considerar que la comunidad de desarrollo +recuerda a los desarrolladores que pierden interés en su código después de +que se fusiona. La próxima vez que publique un parche, lo evaluarán con la +suposición de que no estará disponible para mantenerlo después. + +Otras cosas que pueden suceder +------------------------------- + +Un día, puede que abra su cliente de correo y vea que alguien le ha enviado +un parche para su código. Esa es una de las ventajas de tener su código +disponible públicamente, después de todo. Si está de acuerdo con el parche, puede reenviarlo al maintainer del subsistema (asegúrese de incluir una +línea From: adecuada para que la atribución sea correcta, y añada su propia +firma), o enviar una respuesta Acked-by: y dejar que el autor original lo +envíe hacia arriba. + +Si no está de acuerdo con el parche, envíe una respuesta educada explicando +por qué. Si es posible, dígale al autor qué cambios deben hacerse para que +considere el parche aceptable. Existe una cierta resistencia a incluir +parches que son rechazados por el autor y el maintainer del código, pero +esto tiene un límite. Si se interpreta que bloque buen trabajo, esos +parches eventualmente lo eludirán y se incorporarán al kernel de todos +modos. En el kernel de Linux, nadie tiene poder de veto absoluto sobre +ningún código. Excepto quizás Linus. + +En muy raras ocasiones, puede encontrar algo completamente diferente: otro +desarrollador publica una solución distinta a su problema. En ese punto, es +probable que uno de los dos parches no se incluya, y "el mío fue el +primero" no se considera un argumento técnico convincente. Si el parche de +otra persona desplaza al suyo y se incorpora al kernel, realmente solo hay +una manera de responder: alegrarse de que su problema se haya resuelto y +continuar con su trabajo. Que su trabajo sea desplazado de esta manera +puede ser doloroso y desalentador, pero la comunidad recordará su reacción +mucho después de que hayan olvidado de quién era el parche que realmente se +incluyó. diff --git a/Documentation/translations/sp_SP/process/7.AdvancedTopics.rst b/Documentation/translations/sp_SP/process/7.AdvancedTopics.rst index 553759857339..42cb8b866e11 100644 --- a/Documentation/translations/sp_SP/process/7.AdvancedTopics.rst +++ b/Documentation/translations/sp_SP/process/7.AdvancedTopics.rst @@ -1,11 +1,214 @@ .. include:: ../disclaimer-sp.rst :Original: Documentation/process/7.AdvancedTopics.rst +:Translator: Carlos Bilbao and Avadhut Naik .. _sp_development_advancedtopics: Temas avanzados =============== -.. warning:: - TODO aún no traducido +Llegados a este punto, con suerte, tiene una idea de cómo funciona el +proceso de desarrollo. Sin embargo, ¡todavía hay más que aprender! Esta +sección cubrirá varios temas que pueden ser útiles para los desarrolladores +que desean convertirse en una parte regular del proceso de desarrollo del +kernel Linux. + +Gestionar parches con git +------------------------- + +El uso del control de versiones distribuido para el kernel comenzó a +principios de 2002 cuando Linus comenzó a jugar con la aplicación +propietaria BitKeeper. Aunque BitKeeper fue controvertido, el enfoque de +la gestión de versiones de software que incorporó ciertamente no lo fue. +El control de versiones distribuido permitió una aceleración inmediata +del proyecto de desarrollo del kernel. En los tiempos actuales, existen +varias alternativas gratuitas a BitKeeper. Para bien o para mal, el +proyecto del kernel ha optado por git como su herramienta preferida. + +Administrar parches con git puede hacer la vida mucho más fácil para el +desarrollador, especialmente a medida que crece el volumen de esos +parches. Git también tiene sus asperezas y representa ciertos peligros; +es una herramienta joven y poderosa que aún está siendo civilizada por +sus desarrolladores. Este documento no intentará enseñar al lector cómo +usar git; eso sería material suficiente para un documento extenso por +derecho propio. En su lugar, el enfoque aquí será cómo git encaja en el +proceso de desarrollo del kernel en particular. Los desarrolladores que +deseen ponerse al día con git encontrarán más información en: + + https://git-scm.com/ + + https://www.kernel.org/pub/software/scm/git/docs/user-manual.html + +y en varios tutoriales que se encuentran en la web. + +El primer orden del negocio es leer los sitios mencionados anteriormente +y comprender cómo funciona git antes de intentar usarlo para poner +parches a disposición de otros. Un desarrollador que usa git debe ser +capaz de obtener una copia del repositorio mainline, explorar el historial +de revisiones, hacer commits en el árbol, usar ramas, etcétera. También es +útil entender las herramientas de git para rescribir la historia (como +rebase). Git viene con su propia terminología y conceptos; un nuevo +usuario de git debe conocer las referencias, las ramas remotas, el índice, +las fusiones fast-forward, los pushes y pulls, las cabezas separadas, +etcétera. Todo puede ser un poco intimidante al principio, pero los +conceptos no son tan difíciles de entender con un poco de estudio. + +Usar git para generar parches para enviarlos por correo electrónico puede +ser un buen ejercicio mientras te pones al día. + +Cuando esté listo para comenzar a publicar árboles de git para que otros +los vean, necesitará por supuesto, un servidor del que se pueda extraer. +Configurar un servidor de este tipo con git-daemon es relativamente +sencillo si tiene un sistema accesible a Internet. De lo contrario, los +sitios de alojamiento público y gratuitos (GitHub, por ejemplo) están +comenzando a aparecer en la red. Los desarrolladores establecidos pueden +obtener una cuenta en kernel.org, pero no son fáciles de conseguir; ver +https://kernel.org/faq/ para más información. + +El flujo de trabajo normal de git implica el uso de muchas ramas. Cada +línea de desarrollo puede separarse en una “rama temática” separada y +mantenerse de forma independiente. Las ramas en git son baratas, no hay +razón para no hacer uso gratuito de ellas. Y, en cualquier caso, no debe +desarrollarse en ninguna rama de la que tenga la intención de pedir a +otros que hagan un pull. Las ramas disponibles públicamente deben crearse +con cuidado; fusione los parches de las ramas de desarrollo cuando estén +en forma completa y listos para usar – no antes. + +Git proporciona herramientas poderosas que permiten reescribir su historia +de desarrollo. Un parche inconveniente (uno que rompe la bisección, por +ejemplo, o que tiene algún otro tipo de error obvio) se puede corregir en +su lugar o hacer que desaparezca de la historia por completo. Una serie de +parches se puede reescribir como si se hubiera escrito sobre el mainline +de hoy, aunque haya estado trabajando en ella durante meses. Los cambios +se pueden transferir de manera transparente de una rama a otra. Y así +sucesivamente. El uso juicioso de la capacidad de git para revisar el +historial puede ayudar en la creación de conjuntos de parches limpios con +menos problemas. + +El uso excesivo de esta capacidad puede llevar a otros problemas más allá +de una simple obsesión por crear la historia perfecta del proyecto. +Reescribir la historia rescribirá los cambios contenidos en esa historia, +convirtiendo un árbol del kernel probado (con suerte) en uno no probado. +Pero más allá de eso, los desarrolladores no pueden colaborar fácilmente +si no tienen una vista compartida del historial del proyecto; si reescribe +la historia que otros desarrolladores han introducido en sus repositorios, +les hará la vida mucho más difícil a esos desarrolladores. Por lo tanto, +aquí se aplica una regla simple general: la historia que se ha exportado +a otros generalmente debe considerarse inmutable a partir de entonces. + +Por lo tanto, una vez que envié un conjunto de cambios a su servidor +disponible públicamente, esos cambios no deben reescribirse. Git +intentará hacer cumplir esta regla si intenta enviar cambios que no +resulten en un “fast-forward merge” (es decir, cambios que no comparten +el mismo historial). Es posible anular esta comprobación, y puede haber +ocasiones en las que sea necesario reescribir un árbol exportado. Mover +conjuntos de cambios entre árboles para evitar conflictos en linux-next +es un ejemplo. Pero tales acciones deberían ser raras. Esta es una de las +razones por las que el desarrollo debe hacerse en ramas privadas (que se +pueden reescribir si es necesario) y solo trasladarse a ramas públicas +cuando esté en un estado razonablemente avanzado. + +A medida que el mainline (u otro árbol en el que se basa un conjunto de +cambios) avanza, es tentador fusionarse con ese árbol para permanecer a +la vanguardia. Para una rama privada, la rebase puede ser una manera fácil +de mantenerse al día con otro árbol, pero la rebase no es una opción una +vez que el árbol se exporta al mundo. Una vez que eso sucede, se debe +realizar una fusión completa. Fusionar ocasionalmente tiene sentido, pero +las fusiones demasiado frecuentes pueden desordenar el historial +innecesariamente. La técnica sugerida en este caso es fusionar con poca +frecuencia y, por lo general, solo en puntos de lanzamiento específicos +(como una versión -rc del mainline). Si está nervioso por cambios +específicos, siempre puede realizar fusiones de prueba en una rama +privada. La herramienta git “rerere” puede ser útil en tales situaciones; +recuerda cómo se resolvieron los conflictos de fusión para que no tenga +que hacer el mismo trabajo dos veces. + +Una de las mayores quejas recurrentes sobre herramientas como git es la +siguiente: el movimiento masivo de parches de un repositorio a otro hace +que sea fácil deslizar cambios más aconsejados que pasan al mainline +debajo del radar de revisión. Los desarrolladores del kernel tienden a +descontentarse cuando ven que suceden ese tipo de cosas; poner un árbol +de git con parches no revisados o fuera de tema puede afectar su capacidad +para hacer que los árboles sean integrados en el futuro. Citando a Linus: + +:: + + Puede enviarme parches, pero para que yo acepte un parche de git de + su parte, necesito saber que usted sabe lo que está haciendo, y + necesito poder confiar en las cosas *sin* tener que revisar + manualmente cada cambio individual. + +(https://lwn.net/Articles/224135/). + +Para evitar este tipo de situación, asegúrese de que todos los parches +dentro de una rama determinada se adhieran estrictamente al tema asociado; +una rama de “correcciones de drivers” no debería hacer cambios en el +código central de gestión de memoria. Y, lo más importante, no utilice un +árbol git para eludir el proceso de revisión. Publique un resumen +ocasional del árbol en la lista relevante y, cuando sea el momento +adecuado, solicite que el árbol se incluya en linux-next. + +Si y cuando otros comiencen a enviar parches para su inclusión en su +árbol, no olvide revisarlos. Además, asegúrese de mantener la información +de autoría correcta; la herramienta git “am” hace lo mejor que puede es +este sentido, pero es posible que tenga que agregar una línea “From:” al +parche si ha sido reenviado a través de un tercero. + +Al solicitar un pull, proporcione toda la información relevante: dónde +está su árbol, qué rama se debe pull, y que cambios resultarán del pull. +El comando git request-pull puede ser útil en este sentido; formateará la +solicitud como otros desarrolladores esperan, y también comprobará para +asegurarse de que ha recordado enviar esos cambios al servidor público. + +Revisión de parches +------------------- + +Algunos lectores seguramente se opondrán a incluir esta sección con +“temas avanzados” porque incluso los desarrolladores principiantes del +kernel deberían revisar los parches. Es cierto que no hay mejor manera de +aprender a programar en el entorno del kernel que mirando el código +publicado por otros. Además, los revisores siempre escasean; al revisar +código, puede contribuir significativamente al proceso en su conjunto. + +Revisar el código puede ser una perspectiva intimidante, especialmente +para un nuevo desarrollador de kernel que puede sentirse nervioso al +cuestionar el código – en público – publicado por aquellos con más +experiencia. Sin embargo, incluso el código escrito por los desarrolladores +más experimentados se puede mejorar. Quizás el mejor consejo para los +revisores (todos los revisores) es este: expresar los comentarios de +revisión como preguntas en lugar de críticas. Preguntar “¿cómo se libera +el bloqueo en este camino?” siempre funcionará mejor que decir “el +bloqueo aquí es incorrecto”. + +Otra técnica que es útil en caso de desacuerdo es pedir a otros que +intervengan. Si una discusión llega a un punto muerto después de algunos +intercambios, solicite las opiniones de otros revisores o maintainers. A +menudo, aquellos que están de acuerdo con un revisor permanecen en +silencio a menos que se les invite a participar. La opinión de varias +personas tiene exponencialmente más peso. + +Diferentes desarrolladores revisarán el código desde diferentes puntos de +vista. Algunos se preocupan principalmente por el estilo de codificación +y si las líneas de código tienen espacios en blanco al final. Otros se +enfocarán principalmente en si el cambio implementado por el parche en su +totalidad es beneficioso para el kernel o no. Sin embargo, otros +comprobarán si hay bloqueos problemáticos, uso excesivo de la pila, +posibles problemas de seguridad, duplicación de código encontrado en +otras partes, documentación adecuada, efectos adversos en el rendimiento, +cambios en la ABI del espacio de usuario, etcétera. Todos los tipos de +revisión, si conducen a un mejor código en el kernel, son bienvenidos y +valen la pena. + +No hay ningún requisito estricto para usar etiquetas específicas como +``Reviewed-by``. De hecho, las revisiones en Inglés sencillo son más +informativas y alentadas incluso cuando se proporciona una etiqueta, por +ejemplo, “Revisé los aspectos A, B y C de esta propuesta y me parece +bien”. +¡Alguna forma de mensaje de revisión o respuesta es obviamente necesaria, +de lo contrario, los maintainers no sabrán que el revisor ha revisado el +parche en absoluto! + +Por último, pero no menos importante, la revisión de parches puede +convertirse en un proceso negativo, centrado en señalar problemas. ¡Por +favor, dé un cumplido de vez en cuando, especialmente a los principiantes! diff --git a/Documentation/translations/sp_SP/process/8.Conclusion.rst b/Documentation/translations/sp_SP/process/8.Conclusion.rst index dd181cb8ec9a..d311a23d53df 100644 --- a/Documentation/translations/sp_SP/process/8.Conclusion.rst +++ b/Documentation/translations/sp_SP/process/8.Conclusion.rst @@ -1,11 +1,82 @@ .. include:: ../disclaimer-sp.rst :Original: Documentation/process/8.Conclusion.rst +:Translator: Carlos Bilbao and Avadhut Naik .. _sp_development_conclusion: Para más información ==================== -.. warning:: - TODO aún no traducido +Hay numerosas fuentes de información sobre el desarrollo del kernel de +Linux y temas relacionados. La primera de ellas será el directorio de +Documentación (Documentation) que se encuentra en la distribución del +código fuente del kernel. Comience con el nivel superior +:ref:`Documentation/translations/sp_SP/process/howto.rst `; +también lea +:ref:`Documentation/translations/sp_SP/process/submitting-patches.rst `. +Muchas API internas del kernel están documentadas utilizando el mecanismo +de kerneldoc; “make htmldocs” o “make pdfdocs” se pueden usar para +generar esos documentos en formato HTML o PDF (aunque la versión de TeX +incluida en algunas distribuciones tiene límites internos y no procesa +los documentos correctamente). + +Varios sitios web discuten el desarrollo del kernel en todos los niveles +de detalle. A su autor le gustaría sugerir humildemente https://lwn.net/ +como fuente. La información sobre muchos temas específicos del kernel se +puede encontrar a través del índice del kernel de LWN en: + + https://lwn.net/Kernel/Index/ + +Más allá de eso, un recurso valioso para los desarrolladores del kernel +es: + + https://kernelnewbies.org/ + +Y, por supuesto, no se debe olvidar https://kernel.org/, la ubicación +definitiva para información de lanzamiento del kernel. + +Hay varios libros sobre el desarrollo del kernel: + + Linux Device Drivers, 3rd Edition (Jonathan Corbet, Alessandro + Rubini, and Greg Kroah-Hartman). En linea en + https://lwn.net/Kernel/LDD3/. + + Linux Kernel Development (Robert Love). + + Understanding the Linux Kernel (Daniel Bovet and Marco Cesati). + +Todos estos libros padecen un defecto común: suelen estar algo obsoletos +cuando llegan a las estanterías, y ya llevan un tiempo en las estanterías. +Aun así, hay bastante buena información que se puede encontrar allí. + +La documentación de git se puede encontrar en: + + https://www.kernel.org/pub/software/scm/git/docs/ + + https://www.kernel.org/pub/software/scm/git/docs/user-manual.html + +Conclusión +========== + +Felicitaciones a todos los que han logrado leer este extenso documento. +Con suerte, ha proporcionado una comprensión útil de cómo se desarrolla +el kernel Linux y cómo puede participar en ese proceso. + +Al final, lo que importa es la participación. Cualquier proyecto de +software de código abierto no es más que la suma de lo que sus +colaboradores aportan. El kernel Linux ha progresado tan rápido y tan como +lo ha hecho porque ha sido ayudado por un grupo impresionantemente grande +de desarrolladores, todos los cuales están trabajando para mejorarlo. El +kernel es un excelente ejemplo de lo que se puede lograr cuando miles de +personas trabajan juntas hacia un objetivo común. + +Sin embargo, el kernel siempre puede beneficiarse de una base de +desarrolladores más grande. Siempre hay más trabajo por hacer. Pero, lo +que es igual de importante, la mayoría de los demás participantes en el +ecosistema Linux pueden beneficiarse contribuyendo al kernel. Introducir +código en el mainline es la clave para una mayor calidad del código, +menores costes de mantenimiento y distribución, un mayor nivel de +influencia sobre la dirección del desarrollo del kernel y más. Es una +situación en la que todos los involucrados ganan. Encienda su editor y +únase a nosotros; será más que bienvenido. diff --git a/Documentation/translations/sp_SP/process/development-process.rst b/Documentation/translations/sp_SP/process/development-process.rst index 40d74086f22e..261bcdea3ffc 100644 --- a/Documentation/translations/sp_SP/process/development-process.rst +++ b/Documentation/translations/sp_SP/process/development-process.rst @@ -1,7 +1,7 @@ .. include:: ../disclaimer-sp.rst :Original: Documentation/process/development-process.rst -:Translator: Avadhut Naik +:Translator: Carlos Bilbao and Avadhut Naik .. _sp_development_process_main: @@ -9,14 +9,13 @@ Guía del proceso de desarrollo del kernel ========================================= El propósito de este documento es ayudar a los desarrolladores (y sus -gerentes) a trabajar con la comunidad de desarrollo con un mínimo de +jefes) a trabajar con la comunidad de desarrollo con el mínimo de frustración. Es un intento de documentar cómo funciona esta comunidad -de una manera accesible para aquellos que no están familiarizados -íntimamente con el desarrollo del kernel de Linux (o, de hecho, el -desarrollo de software libre en general). Si bien hay algo de material -técnico aquí, este es en gran medida una discusión orientada al proceso -que no requiere un conocimiento profundo de la programación del kernel -para entenderla. +de una manera accesible, para aquellos que no están familiarizados +íntimamente con el desarrollo del kernel Linux (o, de hecho, el desarrollo +de software libre en general). Si bien hay algo de material técnico aquí, +esto es en gran medida una discusión orientada al proceso que no requiere +un conocimiento profundo de la programación del kernel para entenderla. .. toctree:: :caption: Contenido @@ -25,3 +24,9 @@ para entenderla. 1.Intro 2.Process + 3.Early-stage + 4.Coding + 5.Posting + 6.Followthrough + 7.AdvancedTopics + 8.Conclusion diff --git a/Documentation/translations/sp_SP/process/email-clients.rst b/Documentation/translations/sp_SP/process/email-clients.rst index 55d5803daf41..f60b091ac9ca 100644 --- a/Documentation/translations/sp_SP/process/email-clients.rst +++ b/Documentation/translations/sp_SP/process/email-clients.rst @@ -96,7 +96,7 @@ En la sección :menuselection:`Sending Preferences`: - :menuselection:`Strip Whitespace Before Sending` debe estar ``disabled`` Al redactar el mensaje, el cursor debe colocarse donde el parche debería -aparecer, y luego presionando :kbd:`CTRL-R` se le permite especificar e +aparecer, y luego presionando `CTRL-R` se le permite especificar e archivo de parche a insertar en el mensaje. Claws Mail (GUI) @@ -104,7 +104,7 @@ Claws Mail (GUI) Funciona. Algunos usan esto con éxito para los parches. -Para insertar un parche haga :menuselection:`Message-->Insert File` (:kbd:`CTRL-I`) +Para insertar un parche haga :menuselection:`Message-->Insert File` (`CTRL-I`) o use un editor externo. Si el parche insertado debe editarse en la ventana de composición de Claws @@ -118,11 +118,11 @@ Evolution (GUI) Algunos usan esto con éxito para sus parches. Cuando escriba un correo seleccione: Preformat - desde :menuselection:`Format-->Paragraph Style-->Preformatted` (:kbd:`CTRL-7`) + desde :menuselection:`Format-->Paragraph Style-->Preformatted` (`CTRL-7`) o en la barra de herramientas Luego haga: -:menuselection:`Insert-->Text File...` (:kbd:`ALT-N x`) +:menuselection:`Insert-->Text File...` (`ALT-N x`) para insertar el parche. También puede hacer ``diff -Nru old.c new.c | xclip``, seleccione diff --git a/Documentation/translations/sp_SP/process/index.rst b/Documentation/translations/sp_SP/process/index.rst index adb2cc845928..cff972fe0084 100644 --- a/Documentation/translations/sp_SP/process/index.rst +++ b/Documentation/translations/sp_SP/process/index.rst @@ -10,6 +10,7 @@ .. toctree:: :maxdepth: 1 + development-process submitting-patches kernel-docs coding-style @@ -28,5 +29,4 @@ management-style submit-checklist howto - development-process maintainer-kvm-x86 diff --git a/Documentation/translations/zh_CN/admin-guide/bug-hunting.rst b/Documentation/translations/zh_CN/admin-guide/bug-hunting.rst index decb9b26d2f1..c3f6a83294dc 100644 --- a/Documentation/translations/zh_CN/admin-guide/bug-hunting.rst +++ b/Documentation/translations/zh_CN/admin-guide/bug-hunting.rst @@ -329,12 +329,3 @@ sysklogd发行版附带了一个补丁，它修改了 ``modules-2.0.0`` 包， Aug 29 09:51:01 blizard kernel: Call Trace: [oops:_oops_ioctl+48/80] [_sys_ioctl+254/272] [_system_call+82/128] Aug 29 09:51:01 blizard kernel: Code: c7 00 05 00 00 00 eb 08 90 90 90 90 90 90 90 90 89 ec 5d c3 ---------------------------------------------------------------------------- - -:: - - Dr. G.W. Wettstein Oncology Research Div. Computing Facility - Roger Maris Cancer Center INTERNET: greg@wind.rmcc.com - 820 4th St. N. - Fargo, ND 58122 - Phone: 701-234-7556 diff --git a/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst b/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst index 50f6f0b6bf11..9d7cb51be493 100644 --- a/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst +++ b/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst @@ -26,12 +26,7 @@ DAMON 为不同的用户提供了下面这些接口。 使用它，用户可以通过读取和写入特殊的sysfs文件来使用DAMON的主要功能。因此，你可以编写和使 用你个性化的DAMON sysfs包装程序，代替你读/写sysfs文件。 `DAMON用户空间工具 `_ 就是这种程序的一个例子 它同时支持虚拟和物理地址 - 空间的监测。注意，这个界面只提供简单的监测结果 :ref:`统计 `。对于详细的监测 - 结果，DAMON提供了一个:ref:`跟踪点 `。 -- *debugfs interface.* - :ref:`这 ` 几乎与:ref:`sysfs interface ` 接 - 口相同。这将在下一个LTS内核发布后被移除，所以用户应该转移到 - :ref:`sysfs interface `。 + 空间的监测。 - *内核空间编程接口。* :doc:`这 ` 这是为内核空间程序员准备的。使用它，用户可以通过为你编写内 核空间的DAMON应用程序，最灵活有效地利用DAMON的每一个功能。你甚至可以为各种地址空间扩展DAMON。 @@ -335,247 +330,6 @@ tried_regions// 请注意，我们强烈建议使用用户空间的工具，如 `damo `_ ， 而不是像上面那样手动读写文件。以上只是一个例子。 -debugfs接口 -=========== - -.. note:: - - DAMON debugfs接口将在下一个LTS内核发布后被移除，所以用户应该转移到 - :ref:`sysfs接口`。 - -DAMON导出了八个文件, ``attrs``, ``target_ids``, ``init_regions``, -``schemes``, ``monitor_on_DEPRECATED``, ``kdamond_pid``, ``mk_contexts`` 和 -``rm_contexts`` under its debugfs directory, ``/damon/``. - - -属性 ----- - -用户可以通过读取和写入 ``attrs`` 文件获得和设置 ``采样间隔`` 、 ``聚集间隔`` 、 ``更新间隔`` -以及监测目标区域的最小/最大数量。要详细了解监测属性，请参考 `:doc:/mm/damon/design` 。例如， -下面的命令将这些值设置为5ms、100ms、1000ms、10和1000，然后再次检查:: - - # cd /damon - # echo 5000 100000 1000000 10 1000 > attrs - # cat attrs - 5000 100000 1000000 10 1000 - - -目标ID ------- - -一些类型的地址空间支持多个监测目标。例如，虚拟内存地址空间的监测可以有多个进程作为监测目标。用户 -可以通过写入目标的相关id值来设置目标，并通过读取 ``target_ids`` 文件来获得当前目标的id。在监 -测虚拟地址空间的情况下，这些值应该是监测目标进程的pid。例如，下面的命令将pid为42和4242的进程设 -为监测目标，并再次检查:: - - # cd /damon - # echo 42 4242 > target_ids - # cat target_ids - 42 4242 - -用户还可以通过在文件中写入一个特殊的关键字 "paddr\n" 来监测系统的物理内存地址空间。因为物理地 -址空间监测不支持多个目标，读取文件会显示一个假值，即 ``42`` ，如下图所示:: - - # cd /damon - # echo paddr > target_ids - # cat target_ids - 42 - -请注意，设置目标ID并不启动监测。 - - -初始监测目标区域 ----------------- - -在虚拟地址空间监测的情况下，DAMON自动设置和更新监测的目标区域，这样就可以覆盖目标进程的整个 -内存映射。然而，用户可能希望将监测区域限制在特定的地址范围内，如堆、栈或特定的文件映射区域。 -或者，一些用户可以知道他们工作负载的初始访问模式，因此希望为“自适应区域调整”设置最佳初始区域。 - -相比之下，DAMON在物理内存监测的情况下不会自动设置和更新监测目标区域。因此，用户应该自己设置 -监测目标区域。 - -在这种情况下，用户可以通过在 ``init_regions`` 文件中写入适当的值，明确地设置他们想要的初 -始监测目标区域。输入应该是一个由三个整数组成的队列，用空格隔开，代表一个区域的形式如下:: - - - -目标idx应该是 ``target_ids`` 文件中目标的索引，从 ``0`` 开始，区域应该按照地址顺序传递。 -例如，下面的命令将设置几个地址范围， ``1-100`` 和 ``100-200`` 作为pid 42的初始监测目标 -区域，这是 ``target_ids`` 中的第一个（索引 ``0`` ），另外几个地址范围， ``20-40`` 和 -``50-100`` 作为pid 4242的地址，这是 ``target_ids`` 中的第二个（索引 ``1`` ）:: - - # cd /damon - # cat target_ids - 42 4242 - # echo "0 1 100 \ - 0 100 200 \ - 1 20 40 \ - 1 50 100" > init_regions - -请注意，这只是设置了初始的监测目标区域。在虚拟内存监测的情况下，DAMON会在一个 ``更新间隔`` -后自动更新区域的边界。因此，在这种情况下，如果用户不希望更新的话，应该把 ``更新间隔`` 设 -置得足够大。 - - -方案 ----- - -对于通常的基于DAMON的数据访问感知的内存管理优化，用户只是希望系统对特定访问模式的内存区域应用内 -存管理操作。DAMON从用户那里接收这种形式化的操作方案，并将这些方案应用到目标进程中。 - -用户可以通过读取和写入 ``scheme`` debugfs文件来获得和设置这些方案。读取该文件还可以显示每个 -方案的统计数据。在文件中，每一个方案都应该在每一行中以下列形式表示出来:: - - - -你可以通过简单地在文件中写入一个空字符串来禁用方案。 - -目标访问模式 -~~~~~~~~~~~~ - -``<目标访问模式>`` 是由三个范围构成的，形式如下:: - - min-size max-size min-acc max-acc min-age max-age - -具体来说，区域大小的字节数（ `min-size` 和 `max-size` ），访问频率的每聚合区间的监测访问次 -数（ `min-acc` 和 `max-acc` ），区域年龄的聚合区间数（ `min-age` 和 `max-age` ）都被指定。 -请注意，这些范围是封闭区间。 - -动作 -~~~~ - -```` 是一个预定义的内存管理动作的整数，DAMON将应用于具有目标访问模式的区域。支持 -的数字和它们的含义如下:: - - - 0: Call ``madvise()`` for the region with ``MADV_WILLNEED`` - - 1: Call ``madvise()`` for the region with ``MADV_COLD`` - - 2: Call ``madvise()`` for the region with ``MADV_PAGEOUT`` - - 3: Call ``madvise()`` for the region with ``MADV_HUGEPAGE`` - - 4: Call ``madvise()`` for the region with ``MADV_NOHUGEPAGE`` - - 5: Do nothing but count the statistics - -配额 -~~~~ - -每个 ``动作`` 的最佳 ``目标访问模式`` 取决于工作负载，所以不容易找到。更糟糕的是，将某个 -动作的方案设置得过于激进会导致严重的开销。为了避免这种开销，用户可以通过下面表格中的 ```` -来限制方案的时间和大小配额:: - - - -这使得DAMON在 ```` 毫秒内，尽量只用 ```` 毫秒的时间对 ``目标访 -问模式`` 的内存区域应用动作，并在 ```` 内只对最多字节的内存区域应 -用动作。将 ```` 和 ```` 都设置为零，可以禁用配额限制。 - -当预计超过配额限制时，DAMON会根据 ``目标访问模式`` 的大小、访问频率和年龄，对发现的内存 -区域进行优先排序。为了实现个性化的优先级，用户可以在 ``<优先级权重>`` 中设置这三个属性的 -权重，具体形式如下:: - - - -水位 -~~~~ - -有些方案需要根据系统特定指标的当前值来运行，如自由内存比率。对于这种情况，用户可以为该条 -件指定水位。:: - - - -```` 是一个预定义的整数，用于要检查的度量。支持的数字和它们的含义如下。 - - - 0: 忽视水位 - - 1: 系统空闲内存率 (千分比) - -每隔 ``<检查间隔>`` 微秒检查一次公制的值。 - -如果该值高于 ``<高标>`` 或低于 ``<低标>`` ，该方案被停用。如果该值低于 ``<中标>`` ， -该方案将被激活。 - -统计数据 -~~~~~~~~ - -它还统计每个方案被尝试应用的区域的总数量和字节数，每个方案被成功应用的区域的两个数量，以 -及超过配额限制的总数量。这些统计数据可用于在线分析或调整方案。 - -统计数据可以通过读取方案文件来显示。读取该文件将显示你在每一行中输入的每个 ``方案`` ， -统计的五个数字将被加在每一行的末尾。 - -例子 -~~~~ - -下面的命令应用了一个方案：”如果一个大小为[4KiB, 8KiB]的内存区域在[10, 20]的聚合时间 -间隔内显示出每一个聚合时间间隔[0, 5]的访问量，请分页出该区域。对于分页，每秒最多只能使 -用10ms，而且每秒分页不能超过1GiB。在这一限制下，首先分页出具有较长年龄的内存区域。另外， -每5秒钟检查一次系统的可用内存率，当可用内存率低于50%时开始监测和分页，但如果可用内存率 -大于60%，或低于30%，则停止监测“:: - - # cd /damon - # scheme="4096 8192 0 5 10 20 2" # target access pattern and action - # scheme+=" 10 $((1024*1024*1024)) 1000" # quotas - # scheme+=" 0 0 100" # prioritization weights - # scheme+=" 1 5000000 600 500 300" # watermarks - # echo "$scheme" > schemes - - -开关 ----- - -除非你明确地启动监测，否则如上所述的文件设置不会产生效果。你可以通过写入和读取 ``monitor_on_DEPRECATED`` -文件来启动、停止和检查监测的当前状态。写入 ``on`` 该文件可以启动对有属性的目标的监测。写入 -``off`` 该文件则停止这些目标。如果每个目标进程被终止，DAMON也会停止。下面的示例命令开启、关 -闭和检查DAMON的状态:: - - # cd /damon - # echo on > monitor_on_DEPRECATED - # echo off > monitor_on_DEPRECATED - # cat monitor_on_DEPRECATED - off - -请注意，当监测开启时，你不能写到上述的debugfs文件。如果你在DAMON运行时写到这些文件，将会返 -回一个错误代码，如 ``-EBUSY`` 。 - - -监测线程PID ------------ - -DAMON通过一个叫做kdamond的内核线程来进行请求监测。你可以通过读取 ``kdamond_pid`` 文件获 -得该线程的 ``pid`` 。当监测被 ``关闭`` 时，读取该文件不会返回任何信息:: - - # cd /damon - # cat monitor_on_DEPRECATED - off - # cat kdamond_pid - none - # echo on > monitor_on_DEPRECATED - # cat kdamond_pid - 18594 - - -使用多个监测线程 ----------------- - -每个监测上下文都会创建一个 ``kdamond`` 线程。你可以使用 ``mk_contexts`` 和 ``rm_contexts`` -文件为多个 ``kdamond`` 需要的用例创建和删除监测上下文。 - -将新上下文的名称写入 ``mk_contexts`` 文件，在 ``DAMON debugfs`` 目录上创建一个该名称的目录。 -该目录将有该上下文的 ``DAMON debugfs`` 文件:: - - # cd /damon - # ls foo - # ls: cannot access 'foo': No such file or directory - # echo foo > mk_contexts - # ls foo - # attrs init_regions kdamond_pid schemes target_ids - -如果不再需要上下文，你可以通过把上下文的名字放到 ``rm_contexts`` 文件中来删除它和相应的目录:: - - # echo foo > rm_contexts - # ls foo - # ls: cannot access 'foo': No such file or directory - -注意， ``mk_contexts`` 、 ``rm_contexts`` 和 ``monitor_on_DEPRECATED`` 文件只在根目录下。 - 监测结果的监测点 ================ diff --git a/Documentation/translations/zh_CN/admin-guide/sysrq.rst b/Documentation/translations/zh_CN/admin-guide/sysrq.rst index 8276d70f3b40..6b100acc4ed8 100644 --- a/Documentation/translations/zh_CN/admin-guide/sysrq.rst +++ b/Documentation/translations/zh_CN/admin-guide/sysrq.rst @@ -60,24 +60,24 @@ CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE 必须是以 16 进制数写入。 ~~~~~~~~~~~~~~~~~~~~~~~ 在 x86 架构上 - 你可以按下键盘组合键 :kbd:`ALT-SysRq-`。 + 你可以按下键盘组合键 `ALT-SysRq-`。 .. note:: 一些键盘可能没有标识 'SySRq' 键。'SySRq' 键也被当做 'Print Screen'键。 - 同时有些键盘无法处理同时按下这么多键，因此你可以先按下键盘 :kbd:`Alt` 键， - 然后按下键盘 :kbd:`SysRq` 键，再释放键盘 :kbd:`SysRq` 键，之后按下键盘上命令键 - :kbd:``，最后释放所有键。 + 同时有些键盘无法处理同时按下这么多键，因此你可以先按下键盘 `Alt` 键， + 然后按下键盘 `SysRq` 键，再释放键盘 `SysRq` 键，之后按下键盘上命令键 + ``，最后释放所有键。 在 SPARC 架构上 - 你可以按下键盘组合键 :kbd:`ALT-STOP-` 。 + 你可以按下键盘组合键 `ALT-STOP-` 。 在串行控制台（只针对 PC 类型的标准串口） 你可以发一个 ``BREAK`` ，然后在 5 秒内发送一个命令键， 发送 ``BREAK`` 两次将被翻译为一个正常的 BREAK 操作。 在 PowerPC 架构上 - 按下键盘组合键 :kbd:`ALT - Print Screen` （或者 :kbd:`F13`） - :kbd:`<命令键>` 。 - :kbd:`Print Screen` （或者 :kbd:`F13`） - :kbd:`<命令键>` 或许也能实现。 + 按下键盘组合键 `ALT - Print Screen` （或者 `F13`） - `<命令键>` 。 + `Print Screen` （或者 `F13`） - `<命令键>` 或许也能实现。 在其他架构上 如果你知道其他架构的组合键，请告诉我，我可以把它们添加到这部分。 @@ -87,7 +87,7 @@ CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE 必须是以 16 进制数写入。 echo t > /proc/sysrq-trigger -这个命令键 :kbd:`` 是区分大小写的。 +这个命令键 `` 是区分大小写的。 什么是命令键？ ~~~~~~~~~~~~~~ @@ -203,8 +203,8 @@ syslogd/klogd 进程是运行的，它们仍将被记录。） ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 这也会发生在我这，我发现轻敲键盘两侧的 shift、alt 和 control 键，然后再次敲击 -一个无效的 SysRq 键序列可以解决问题。（比如，像键盘组合键 :kbd:`alt-sysrq-z` ） -切换到另一个虚拟控制台（键盘操作 :kbd:`ALT+Fn` ），然后再切回来应该也有帮助。 +一个无效的 SysRq 键序列可以解决问题。（比如，像键盘组合键 `alt-sysrq-z` ） +切换到另一个虚拟控制台（键盘操作 `ALT+Fn` ），然后再切回来应该也有帮助。 我敲击了 SysRq 键，但像是什么都没发生，发生了什么错误？ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -259,7 +259,7 @@ SysRq 键的输出和所有其他控制台输出一样，受制于控制台日 文件的消费访问到。作为一个特例，来自 sysrq 命令的标题行将被传递给所有控制台 使用者，就好像当前日志级别是最大的一样。如果只发出标题头，则几乎可以肯定内核日志 级别太低。如果你需要控制台上的输出，那么你将需要临时提高控制台日志级别，通过使用 -键盘组合键 :kbd:`alt-sysrq-8` 或者:: +键盘组合键 `alt-sysrq-8` 或者:: echo 8 > /proc/sysrq-trigger diff --git a/Documentation/translations/zh_CN/devicetree/of_unittest.rst b/Documentation/translations/zh_CN/devicetree/of_unittest.rst index 11eb08ca8866..5c1a8e0cfd16 100644 --- a/Documentation/translations/zh_CN/devicetree/of_unittest.rst +++ b/Documentation/translations/zh_CN/devicetree/of_unittest.rst @@ -40,7 +40,7 @@ OF Selftest被设计用来测试提供给设备驱动开发者的接口（includ drivers/of/unittest-data/tests-phandle.dtsi drivers/of/unittest-data/tests-match.dtsi -当内核在启用OF_SELFTEST的情况下被构建时，那么下面的make规则:: +当内核在启用CONFIG_OF_UNITTEST的情况下被构建时，那么下面的make规则:: $(obj)/%.dtb: $(src)/%.dts FORCE $(call if_changed_dep, dtc) diff --git a/Documentation/translations/zh_CN/process/email-clients.rst b/Documentation/translations/zh_CN/process/email-clients.rst index a70393089df3..069c0460d20c 100644 --- a/Documentation/translations/zh_CN/process/email-clients.rst +++ b/Documentation/translations/zh_CN/process/email-clients.rst @@ -85,7 +85,7 @@ Alpine (TUI) - :menuselection:`Do Not Send Flowed Text` 必须开启 - :menuselection:`Strip Whitespace Before Sending` 必须关闭 -当写邮件时，光标应该放在补丁会出现的地方，然后按下 :kbd:`CTRL-R` 组合键，使指 +当写邮件时，光标应该放在补丁会出现的地方，然后按下 `CTRL-R` 组合键，使指 定的补丁文件嵌入到邮件中。 Claws Mail (GUI) @@ -93,7 +93,7 @@ Claws Mail (GUI) 可以用，有人用它成功地发过补丁。 -用 :menuselection:`Message-->Insert File` (:kbd:`CTRL-I`) 或外置编辑器插入补丁。 +用 :menuselection:`Message-->Insert File` (`CTRL-I`) 或外置编辑器插入补丁。 若要在Claws编辑窗口重修改插入的补丁，需关闭 :menuselection:`Configuration-->Preferences-->Compose-->Wrapping` @@ -105,11 +105,11 @@ Evolution (GUI) 一些开发者成功的使用它发送补丁。 撰写邮件时： -从 :menuselection:`格式-->段落样式-->预格式化` (:kbd:`CTRL-7`) +从 :menuselection:`格式-->段落样式-->预格式化` (`CTRL-7`) 或工具栏选择 :menuselection:`预格式化` ； 然后使用： -:menuselection:`插入-->文本文件...` (:kbd:`ALT-N x`) 插入补丁文件。 +:menuselection:`插入-->文本文件...` (`ALT-N x`) 插入补丁文件。 你还可以 ``diff -Nru old.c new.c | xclip`` ，选择 :menuselection:`预格式化` ， 然后使用鼠标中键进行粘帖。 diff --git a/Documentation/translations/zh_CN/security/IMA-templates.rst b/Documentation/translations/zh_CN/security/IMA-templates.rst new file mode 100644 index 000000000000..b391c9d03882 --- /dev/null +++ b/Documentation/translations/zh_CN/security/IMA-templates.rst @@ -0,0 +1,97 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: ../disclaimer-zh_CN.rst + +:Original: Documentation/security/IMA-templates.rst + +:翻译: + 赵硕 Shuo Zhao + +=============== +IMA模板管理机制 +=============== + + +介绍 +==== + +原始的 ``ima`` 模板是固定长度的，包含文件数据的哈希值和路径名。文件数据 +哈希值限制为20字节(md5/sha1)。路径名是一个以空字符终止的字符串，长度限 +制为255个字符内。 +为了克服这些限制并添加额外的文件元数据，通过定义额外的模板来扩展当前版本 +的IMA这是有必要的。例如，可能报告的信息包括索引节点的 UID/GID或索引节点 +及访问它进程的LSM标签。 + +然而，引入这个功能的主要问题是，每次定义一个新模板时，生成和显示度量列表 +的函数都需要包含处理新格式的代码，因此，这些函数的规模随着时间的推移会 +显著增长。 + +提出的解决方案通过将模板管理与其余IMA代码分离来解决这个问题。该解决方案 +的核心是定义两个新的数据结构：一个是模板描述符，用于确定度量列表中应包含 +哪些信息；另一个是模板字段，用于生成和显示给定类型的数据。 + +使用这些结构管理模板非常简单。为了支持一种新的数据类型，开发人员定义字段 +标识符，并实现两个函数，分别为init()和show()，用于生成和显示度量条目。 +定义一个新的模板描述符需要通过 ``ima_template_fmt`` 内核命令行参数指定 +模板格式(一个由 ``|`` 字符分隔的字段标识符字符串)。在启动时，IMA通过将格 +式转换从支持的模板字段集合中选取模板字段数组，来初始化所选的模板描述符。 + +在初始化步骤之后，IMA将调用 ``ima_alloc_init_template()`` (这是为新模板 +管理机制所打补丁中定义的新函数)，通过使用在内核配置选择的模板描述符或者新引 +入的 ``ima_template`` 和 ``ima_template_fmt`` 内核命令行参数，生成一个新 +的度量条目。在这一阶段，新架构的优势得以清晰展示：后一个函数将不会包含处理给 +定模板的特定代码，而是简单地调用与所选模板描述符关联的模板字段的 ``init()`` +方法，并将结果(指向已分配数据的指针和数据长度)存储在度量条目结构中。 + +相同的机制也用于显示度量条目。函数 ``ima[_ascii]_measurements_show()`` 会为 +每个条目检索用于生成该条目的模板描述符，并为模板字段结构数组中的每一项调用show() +方法。 + + + +支持的模板字段和描述符 +====================== + +下面是支持的模板字段列表 ``('': description)`` ，可以通过将其标识符 +添加到格式字符串中用于定义新的模板描述符(后续将添加对更多数据类型的支持): + + - 'd'：事件的摘要(即测量文件的摘要)，通过SHA1或MD5哈希算法计算； + - 'n'：事件的名称(即文件名)，大小至多255字节； + - 'd-ng'：事件的摘要，通过任意哈希算法计算(字段格式：:digest)； + - 'd-ngv2'：与d-ng相同，但以"ima"或"verity"摘要类型为前缀 + (字段格式：::digest)； + - 'd-modsig'：不含附加modsig的事件摘要； + - 'n-ng'：事件的名称，没有大小限制； + - 'sig'：文件签名，基于文件的/文件系统验证的摘要[1]，或EVM便携式签名， + 如果'security.ima'包含文件哈希； + - 'modsig'：附加的文件签名； + - 'buf'：用于生成哈希的缓冲区数据，没有大小限制； + - 'evmsig'：EVM便携式签名； + - 'iuid'：索引节点的UID； + - 'igid'：索引节点的GID； + - 'imode'：索引节点的模式； + - 'xattrnames'：xattr名称的列表(由``|``分隔)，仅当xattr存在时； + - 'xattrlengths'：xattr长度的列表(u32)，仅当xattr存在时； + - 'xattrvalues'：xattr值的列表； + + +下面是已定义的模板描述符列表： + + - "ima"：其格式是 ``d|n`` ； + - "ima-ng"(默认)：其格式是 ``d-ng|n-ng`` ； + - "ima-ngv2"：其格式是 ``d-ngv2|n-ng`` ； + - "ima-sig"：其格式是 ``d-ng|n-ng|sig`` ； + - "ima-sigv2"：其格式是 ``d-ngv2|n-ng|sig`` ； + - "ima-buf"：其格式是 ``d-ng|n-ng|buf`` ； + - "ima-modsig"：其格式是 ``d-ng|n-ng|sig|d-modsig|modsig`` ； + - "evm-sig"：其格式是 ``d-ng|n-ng|evmsig|xattrnames|xattrlengths|xattrvalues|iuid|igid|imode`` ； + + + +使用 +==== + +要指定用于生成度量条目的模板描述符，目前支持以下方法: + + - 从内核配置所支持模板描述符中选择一个模板描述符( ``ima-ng`` 是默认选择)； + - 通过 ``ima_template=`` 参数从内核命令行指定模板描述符名称； + - 通过内核命令行参数 ``ima_template_fmt=`` 注册一个具有自定义格式的新模板描述符。 diff --git a/Documentation/translations/zh_CN/security/digsig.rst b/Documentation/translations/zh_CN/security/digsig.rst new file mode 100644 index 000000000000..3e690b504ec5 --- /dev/null +++ b/Documentation/translations/zh_CN/security/digsig.rst @@ -0,0 +1,103 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: ../disclaimer-zh_CN.rst + +:Original: Documentation/security/digsig.rst + +:翻译: + 赵硕 Shuo Zhao + +=============== +数字签名验证API +=============== + +:作者: Dmitry Kasatkin +:日期: 2011.06.10 + + +.. 内容 + + 1.介绍 + 2.API + 3.用户空间工具 + + +介绍 +==== + +数字签名验证API提供了一种验证数字签名的方法。 +目前，数字签名被IMA/EVM完整性保护子系统使用。 + +数字签名验证是通过精简的GnuPG多精度整数(MPI)库的内核移植来实现的。 +该内核版本提供了内存分配错误处理，已根据内核编码风格进行重构，并修复 +了checkpatch.pl报告的错误和警告。 + +公钥和签名由头部和MPIs组成:: + + struct pubkey_hdr { + uint8_t version; /* 密钥格式版本 */ + time_t timestamp; /* 密钥时间戳，目前为0 */ + uint8_t algo; + uint8_t nmpi; + char mpi[0]; + } __packed; + + struct signature_hdr { + uint8_t version; /* 签名格式版本 */ + time_t timestamp; /* 签名时间戳 */ + uint8_t algo; + uint8_t hash; + uint8_t keyid[8]; + uint8_t nmpi; + char mpi[0]; + } __packed; + +keyid等同对整个密钥的内容进行SHA1哈希运算后的第12到19字节。 +签名头部用于生成签名的输入。这种方法确保了密钥或签名头部无法更改。 +它保护时间戳不被更改，并可以用于回滚保护。 + +API +=== + +目前API仅包含一个函数:: + + digsig_verify() - 使用公钥进行数字签名验证 + + /** + * digsig_verify() - 使用公钥进行数字签名验证 + * @keyring: 查找密钥的密钥环 + * @sig: 数字签名 + * @sigen: 签名的长度 + * @data: 数据 + * @datalen: 数据的长度 + * @return: 成功时返回0，失败时返回 -EINVAL + * + * 验证数据相对于数字签名的完整性。 + * 目前仅支持RSA算法。 + * 通常将内容的哈希值作为此函数的数据。 + * + */ + int digsig_verify(struct key *keyring, const char *sig, int siglen, + const char *data, int datalen); + +用户空间工具 +============ + +签名和密钥管理实用工具evm-utils提供了生成签名、加载密钥到内核密钥环中的功能。 +密钥可以是PEM格式，或转换为内核格式。 +当把密钥添加到内核密钥环时，keyid定义该密钥的名称：下面的示例中为5D2B05FC633EE3E8。 + +以下是keyctl实用工具的示例输出:: + + $ keyctl show + Session Keyring + -3 --alswrv 0 0 keyring: _ses + 603976250 --alswrv 0 -1 \_ keyring: _uid.0 + 817777377 --alswrv 0 0 \_ user: kmk + 891974900 --alswrv 0 0 \_ encrypted: evm-key + 170323636 --alswrv 0 0 \_ keyring: _module + 548221616 --alswrv 0 0 \_ keyring: _ima + 128198054 --alswrv 0 0 \_ keyring: _evm + + $ keyctl list 128198054 + 1 key in keyring: + 620789745: --alswrv 0 0 user: 5D2B05FC633EE3E8 diff --git a/Documentation/translations/zh_CN/security/index.rst b/Documentation/translations/zh_CN/security/index.rst new file mode 100644 index 000000000000..d8aacd1930d9 --- /dev/null +++ b/Documentation/translations/zh_CN/security/index.rst @@ -0,0 +1,34 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. include:: ../disclaimer-zh_CN.rst + +:Original: Documentation/security/index.rst + +:翻译: + + 赵岳辉 Yuehui Zhao + +======== +安全文档 +======== + +.. toctree:: + :maxdepth: 1 + + lsm + sak + siphash + digsig + landlock + +TODOLIST: +* credentials +* snp-tdx-threat-model +* IMA-templates +* keys/index +* lsm-development +* SCTP +* self-protection +* tpm/index +* secrets/index +* ipe diff --git a/Documentation/translations/zh_CN/security/landlock.rst b/Documentation/translations/zh_CN/security/landlock.rst new file mode 100644 index 000000000000..53b449b637b2 --- /dev/null +++ b/Documentation/translations/zh_CN/security/landlock.rst @@ -0,0 +1,123 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright ? 2017-2020 Micka?l Salaün +.. Copyright ? 2019-2020 ANSSI +.. include:: ../disclaimer-zh_CN.rst + +:Original: Documentation/security/landlock.rst + +:翻译: + + 毛玉贤 Yuxian Mao + +====================== +Landlock LSM: 内核文档 +====================== + +:作者: Mickaël Salaün +:日期: 2022年12月 + +Landlock的目标是创建有范围的访问控制（即沙箱机制）。为了增强整个 +系统的安全性，此功能应适用于任何进程，包括非特权进程。因为这些进 +程可能被攻击或植入后门（即不可信任的），所以从内核和其他进程的角 +度来看，Landlock的功能必须安全可用。因此，Landlock 的接口设计应当 +尽量减少可能的攻击点。 + +Landlock 旨在为非特权进程使用，同时遵循由其他访问控制机制（例如 DAC、LSM） +强制执行的系统安全策略。Landlock 规则不应与系统上强制执行的其他访问 +控制相冲突，而只能添加额外的限制。 + +任何用户都可以在其进程上强制执行Landlock规则集。这些规则集会以一种 +确保只能添加更多约束的方式与继承的规则集合并和评估。 + + +用户空间文档如下： +Documentation/userspace-api/landlock.rst. + +安全访问控制机制指导原则 +======================== + +* Landlock规则应侧重于对内核对象的访问控制，而非系统调用过滤（即 + 系统调用参数），后者是seccomp-bpf要侧重的。 +* 为了避免多种侧信道攻击（例如安全策略泄露、基于CPU的攻击），Landlock + 规则不应与用户空间进行程序化通信。 +* 内核访问检查不应降低未沙盒化进程的访问请求速度。 +* 与 Landlock 操作相关的计算（例如强制执行规则集）应仅影响请求这些 + 操作的进程。 +* 由沙盒化进程直接从内核中获得的资源（例如文件描述符）在被任何进程 + 使用时，都应保留其获取时的作用域访问权限。 + Cf. `文件描述符访问权限`_. + +设计选择 +======== + +inode访问权限 +------------- + +所有访问权限都与inode以及通过inode所访问到的内容相关。读取目录的 +内容并不意味着有权读取该目录中列出的 inode 所对应文件的内容。实际 +上，文件名是相对于其父目录而言的 ，一个 inode 可以通过多个文件名 +（通过硬链接）来引用。删除文件链接这一操作仅直接影响对应目录，而 +对被移除链接的inode并无影响。这就是“LANDLOCK_ACCESS_FS_REMOVE_FILE” +（文件系统移除文件访问权限）或“LANDLOCK_ACCESS_FS_REFER” （文件系 +统引用访问权限）不能与文件绑定，而只能与目录绑定的原因。 + +文件描述符访问权限 +------------------ + +在打开文件时，会检查访问权限并将其与文件描述符绑定。其基本原则是， +当在相同的 Landlock 域下执行时，等效的操作序列会产生相同的结果。 +以LANDLOCK_ACCESS_FS_TRUNCATE权限为例，如果相关的文件层次结构没有 +授予该访问权限，那么可能允许打开一个文件进行写操作，但不允许使用 +ftruncate调用截断由此产生的文件描述符。 +以下操作序列具有相同的语义，因此会产生相同的结果： + +* ``truncate(path);`` +* ``int fd = open(path, O_WRONLY); ftruncate(fd); close(fd);`` + +与文件访问模式类似（例如O_RDWR），即使文件描述符在进程之间传递 +（例如通过Unix域套接字），文件描述符中的Landlock访问权限也会被保留。 +这些访问权限即使在接收进程未被 Landlock 沙盒化的情况下也会被强制执行。 +事实上，这是为了保持整个系统访问控制的一致性，避免通过文件描述符传递 +而无意中绕过安全限制（即“混淆代理攻击”）。 + +测试 +==== + +用户空间的向后兼容性测试、ptrace 限制测试和文件系统支持测试可以在这里 +找到：tools/testing/selftests/landlock/ + +内核结构 +======== + +对象 +---- + +该API在以下内核代码中： + +security/landlock/object.h + +文件系统 +-------- + +该API在以下内核代码中： + +security/landlock/fs.h + +规则集和域 +---------- + +域是与一组主体（即任务凭证）关联的只读规则集。每次在任务上执行规则集时， +都会复制当前域，并在新域中导入规则集作为新的规则层。 事实上，一旦进入 +一个域，每条规则都与一个层级绑定。要授予对对象的访问权限，每一层中至少 +有一条规则必须允许对该对象执行请求操作。然后，任务只能过渡到一个新的域， +该新域是当前域的约束和任务提供的规则集的约束的交集。任务自行沙盒化时， +主体的定义是隐式的，这使得推理变得更加简单，并有助于避免陷阱。 + +该API在以下内核代码中： + +security/landlock/ruleset.h + +.. Links +.. _tools/testing/selftests/landlock/: + +https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/tools/testing/selftests/landlock/ diff --git a/Documentation/translations/zh_CN/security/lsm.rst b/Documentation/translations/zh_CN/security/lsm.rst new file mode 100644 index 000000000000..e0ec4c7831da --- /dev/null +++ b/Documentation/translations/zh_CN/security/lsm.rst @@ -0,0 +1,95 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: ../disclaimer-zh_CN.rst + +:Original: Documentation/security/lsm.rst + +:翻译: + + 赵岳辉 Yuehui Zhao + +================================ +Linux安全模块：Linux通用安全钩子 +================================ + +:作者: Stephen Smalley +:作者: Timothy Fraser +:作者: Chris Vance + +.. note:: + + 本文中描述的api已经过时了。 + +介绍 +==== + +在2001年3月，美国国家安全局（NSA）在2.5 Linux内核峰会上做了一个关于安全 +增强Linux（SELinux）的报告。SELinux是Linux内核中一种实现灵活且细粒度的非 +自主访问控制，最初作为自己特定的内核补丁实现。其他一些安全项目（例如RSBAC、 +Medusa）也为Linux内核开发了灵活的访问控制架构，并且多个项目为Linux开发了 +特定的访问控制模型（例如LIDS、DTE、SubDomain）。每个项目都开发并维护了自 +己的内核补丁，以支持其安全需求。 + +针对美国国家安全局的报告，Linus Torvalds发表了一系列言论，描述了一个他愿 +意考虑纳入主流Linux内核的安全框架。他描述了一个通用的框架，该框架将提供 +一组安全钩子来控制对内核对象的操作，同时在内核数据结构中提供一组不透明的 +安全域来维护安全属性。这个框架可以被可加载的内核模块用来实现任何所需的安 +全模型。Linus还提出了将Linux权能代码迁移到这样一个模块中的可能性。 + +Linux安全模块（LSM）项目是由WireX发起开发的这样一个框架。LSM是几个安全 +项目共同开发的成果，包括immununix、SELinux、SGI和Janus，以及包括 +Greg Kroah-Hartman和James Morris在内的几个人，来开发一个实现这一框架的 +Linux内核补丁。这项工作在2003年12月被纳入主流内核。此技术报告概述了该框 +架和权能安全模块的内容。 + +LSM框架 +======= + +LSM框架提供了一个通用的内核框架来支持安全模块。特别地，LSM框架主要关注 +支持访问控制模块，尽管未来的开发可能会解决其他安全需求，比如沙箱。就其 +本身而言，框架不提供任何额外的安全；它仅提供了支持安全模块的基础架构。 +LSM框架是可选的，要求开启 `CONFIG_SECURITY` 配置。权能逻辑作为一个安全 +模块被实现。该权能模块将在 `LSM权能模块`_ 一节中进一步讨论。 + +LSM框架在内核数据结构中包含安全域，并在内核代码的关键点调用钩子函数来 +管理这些安全域并执行访问控制。它还增加了注册安全模块的函数。接口 +/sys/kernel/security/lsm记录了一个以逗号分隔的安全模块列表，这些模块在 +系统中是激活的。 + +LSM安全域只是 ``void*`` 指针。数据被称为blob，这些数据可以由框架或使用 +它的各个安全模块进行管理。多个安全模块共同使用的安全blob通常由框架管理。 +对于进程和程序执行的安全信息，安全域包含在 :c:type: +`struct task_struct ` 和 :c:type: `struct cred ` 中。 +对于文件系统的安全信息，安全域包含在 :c:type: +`struct super_block ` 中。对于管道、文件和套接字的安全信息， +安全域包含在 :c:type: `struct inode ` 和 :c:type: `struct file ` +中。对于System V IPC的安全信息，安全域被添加到 :c:type: +`struct kern_ipc_perm ` 和 :c:type: `struct msg_msg ` +中；另外，:c:type: `struct msg_msg ` 、struct msg_queue和 +struct shmid_kernel的定义被移动到头文件中（ ``include/linux/msg.h`` 和 +``include/linux/shm.h`` 视情况而定），以允许安全模块使用这些定义。 + +对于数据包和网络设备的安全信息，安全域被添加到 :c:type: +`struct sk_buff ` 和 :c:type: `struct scm_cookie ` 中。 +与其他安全模块数据不同，这里使用的数据是一个32位整数。安全模块需要将这些值 +进行映射或关联到真正的安全属性。 + +LSM钩子被维护在链表中。每个钩子函数都维护一个链表，这些钩子按照CONFIG_LSM中 +指定的顺序被调用。每个钩子的详细文档都包含在 `security/security.c` 源文件中。 + +LSM框架提供了一种近似通用的安全模块堆栈。它定义了security_add_hooks()，每个安 +全模块向它传递一个 :c:type: `struct security_hooks_list ` +，该结构会被添加到链表中。LSM框架没有提供移除已注册钩子的机制。SELinux安全 +模块已经实现了一种移除自身的方法，然而该特性已被弃用。 + +这些钩子可以分为两大类：用于管理安全域的钩子和用于执行访问控制的钩子。 +第一类钩子的示例包括security_inode_alloc()和security_inode_free()，这些 +钩子用于为inode对象分配和释放安全结构。第二类钩子的示例是 +security_inode_permission()钩子，该钩子在访问inode时检查权限。 + +LSM权能模块 +=========== + +POSIX.1e 权能逻辑作为一个安全模块维护，存储在文件 ``security/commoncap.c`` +中。权能模块使用 :c:type: `lsm_info` 描述中的order域来标识它为第一个注册 +的安全模块。与其他模块不同，权能安全模块不使用通用的安全blob。其原因是历史 +性的，主要基于开销、复杂性和性能的考虑。 diff --git a/Documentation/translations/zh_CN/security/sak.rst b/Documentation/translations/zh_CN/security/sak.rst new file mode 100644 index 000000000000..574fe076201b --- /dev/null +++ b/Documentation/translations/zh_CN/security/sak.rst @@ -0,0 +1,86 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: ../disclaimer-zh_CN.rst + +:Original: Documentation/security/sak.rst + +:翻译: + + 张巍 zhangwei + +=========================== +Linux 安全注意键（SAK）处理 +=========================== + +:日期: 2001年3月18日 +:作者: Andrew Morton + +操作系统的安全注意键是一种安全工具，用于防止系统上存在特洛伊 +木马密码捕获程序。它提供了一种无法规避的方式，用于终止所有可 +能伪装成登录应用程序的程序。用户需要在登录系统之前输入这个安 +全键。 + +从键盘输入的方式生成安全注意键，Linux提供了两种相似但不同的 +方式。一种是按下ALT-SYSRQ-K组合键，但你不应该使用这种方式， +因为它只有在内核启用了SYSRQ支持的情况下才能使用。 + +正确生成SAK的方式是使用``loadkeys``来定义键序列。无论内核是否 +编译了sysrq支持，这种方式都能够正常工作。 + +当键盘处于原始模式时，SAK 能够正常工作。这意味着，一旦定义， +SAK 将终止正在运行的 X 服务器。如果系统处于运行级别 5，X 服 +务器将重新启动，这正是你希望发生的情况。 + +你应该使用什么键序列？ CTRL-ALT-DEL用于重启机器，CTRL-ALT- +BACKSPACE对X服务器有特殊作用。我们将选择CTRL-ALT-PAUSE。 + +在你的rc.sysinit（或rc.local）文件中，添加以下命令:: + + echo "Control Alt keycode 101 = SAK" | /bin/loadkeys + +就这样！只有超级用户才能重新编程SAK键。 + +.. note:: + + 1. Linux SAK据说并不是C2级安全性的系统所要求的"真正的SAK"。 + 该原因作者也不知道 + + 2. 在键盘输入的模式下，SAK会终止所有打开了/dev/console的应用 + 程序。 + + 但是不幸的是，这也包括一些你实际上不希望被终止的程序。原因是 + 这些程序错误的保持了/dev/console的打开状态。务必确保向你的 + Linux发行版提供商投诉这个问题。 + + 你可以用以下的命令来识别将被SAK终止的程序:: + + # ls -l /proc/[0-9]*/fd/* | grep console + l-wx------ 1 root root 64 Mar 18 00:46 /proc/579/fd/0 -> /dev/console + + 然后:: + + # ps aux|grep 579 + root 579 0.0 0.1 1088 436 ? S 00:43 0:00 gpm -t ps/2 + + 所以``gpm``会被SAK杀死。这应该gpm中的bug。它应该正在关闭标准输入， + 你可以通过查找initscript来启动gpm并更改它： + + 老的:: + + daemon gpm + + 新的:: + + daemon gpm < /dev/null + + Vixie cron似乎也有这个问题，并且需要采取相同的处理方式。 + + 此外，某个著名的Linux发行版在它的rc.sysinit和rc scripts的脚本中 + 包含了以下三行代码:: + + exec 3<&0 + exec 4>&1 + exec 5>&2 + + 这些代码会导致所有的守护进程将文件描述符3、4和5关联到/dev/console。 + 所以SAK会将他们所有都终止。一个简单的解决办法就是删掉这些代码，但是 + 这样做会导致系统管理应用程序出现异常 - 要对所有的情况进行充分测试。 diff --git a/Documentation/translations/zh_CN/security/siphash.rst b/Documentation/translations/zh_CN/security/siphash.rst new file mode 100644 index 000000000000..26dd8be699b3 --- /dev/null +++ b/Documentation/translations/zh_CN/security/siphash.rst @@ -0,0 +1,195 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: ../disclaimer-zh_CN.rst +:Original: Documentation/security/siphash.rst + +:翻译: + + 张巍 zhangwei + +===================================== +SipHash - 一种短输入伪随机函数（PRF） +===================================== + +：作者: Jason A.Donenfeld + +SipHash是一种加密安全的伪随机函数，即一种用于生成伪随机密钥的哈 +希函数，因为其在处理短输入时表现出色，因此得名。其由密码学家 +Daniel J. Bernstein和Jean-Philippe Aumasson设计。目的主要是替 +代其他哈希函数，例如：jhash，md5_transform，sha1_transform等。 + +SipHash采用一个完全由随机数生成的密钥，以及一个输入缓冲区或者 +多个输入整数，它输出一个与随机数难以区分的整数，你可以将它作 +为安全序列、安全cookies的一部分，或者对其进行掩码处理，以便在 +哈希表中使用。 + +生成密钥 +======== + +密钥应来源于加密安全的随机数生成，要么使用get random bytes +要么使用get random once:: + + siphash_key_t key; + get_random_bytes(&key, sizeof(key)); + +如果你的密钥来源不是这两个，那么你的做法是错的。 + +使用函数 +======== + +这个函数有两个变种，一种是接受整数列表，另一种是接受缓冲区:: + + u64 siphash(const void *data, size_t len, const siphash_key_t *key); + +和:: + + u64 siphash_1u64(u64, const siphash_key_t *key); + u64 siphash_2u64(u64, u64, const siphash_key_t *key); + u64 siphash_3u64(u64, u64, u64, const siphash_key_t *key); + u64 siphash_4u64(u64, u64, u64, u64, const siphash_key_t *key); + u64 siphash_1u32(u32, const siphash_key_t *key); + u64 siphash_2u32(u32, u32, const siphash_key_t *key); + u64 siphash_3u32(u32, u32, u32, const siphash_key_t *key); + u64 siphash_4u32(u32, u32, u32, u32, const siphash_key_t *key); + +如果向一个通用的hsiphash函数传递一个恒定长度的常量，他将 +在编译的时候将常量折叠，并自动选择一个优化后的函数。 + +哈希表键函数的用法:: + + struct some_hashtable { + DECLARE_HASHTABLE(hashtable, 8); + siphash_key_t key; + }; + + void init_hashtable(struct some_hashtable *table) + { + get_random_bytes(&table->key, sizeof(table->key)); + } + + static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input) + { + return &table->hashtable[siphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)]; + } + +然后，你可以像往常一样对返回的哈希存储桶进行迭代。 + +安全性 +====== + +SipHash有着非常高的安全性,因为其有128位的密钥。只要密钥是保密的， +即使攻击者看到多个输出，也无法猜测出函数的正确输出，因为2^128次 +方个输出是非常庞大的。 + +Linux实现了SipHash的“2-4”变体 + +Struct-passing陷阱 +================== + +通常情况下，XuY函数的输出长度不够大，因此你可能需要传递一个预填充 +的结构体给SipHash，在这样做时，务必确保结构体没有填充空隙，最简单 +的方法就是将结构体的成员按照大小降序的方式排序，并且使用offsetofend() +函数代替sizeof()来获取结构体大小，出于性能的考虑，如果可以的话，最 +好将结构体按右边界对齐，示例如下:: + + const struct { + struct in6_addr saddr; + u32 counter; + u16 dport; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .saddr = *(struct in6_addr *)saddr, + .counter = counter, + .dport = dport + }; + u64 h = siphash(&combined, offsetofend(typeof(combined), dport), &secret); + +资源 +==== + +如果你有兴趣了解更多信息，请阅读SipHash论文: +https://131002.net/siphash/siphash.pdf + +------------------------------------------------------------------------------- + +=========================================== +HalfSipHash 是 SipHash 的一个较不安全的变种 +=========================================== + +：作者: Jason A.Donenfeld + +如果你认为SipHash的速度不够快，无法满足你的需求，那么你可以 +使用HalfSipHash，这是一种令人担忧但是有用的选择。HalfSipHash +将SipHash的轮数从“2-4”降低到“1-3”，更令人担心的是，它使用一 +个容易被穷举攻击的64位密钥(输出为32位)，而不是SipHash的128位 +密钥，不过，这对于要求高性能“jhash”用户来说这是比较好的选择。 + +HalfSipHash是通过 "hsiphash" 系列函数提供的。 + +.. warning:: + 绝对不要在作为哈希表键函数之外使用hsiphash函数，只有在你 + 能完全能确定输出永远不会从内核传输出去的情况下才能使用， + 作为缓解哈希表泛洪拒绝服务攻击的一种手段，它仅在某些情况 + 下比jhash好用。 + +在64位的内核中，hsiphash函数实际上实现的是SipHash-1-3，这是一 +种减少轮数的SipHash变形，而不是HalfSipHash-1-3。这是因为在64位 +代码中SipHash-1-3的性能与HalfSipHash-1-3相当，甚至可能更快，请 +注意，这并不意味这在64位的内核中，hsihpash函数与siphash函数相 +同，也不意味着他们是安全的；hsihash函数仍然使用一种不太安全的 +减少轮数的算法，并将输出截断为32位。 + +生成哈希密钥 +============ + +密钥应始终来源于加密安全的随机数生成，要么使用get random bytes +要么使用get random once:: + + hsiphash_key_t key; + get_random_bytes(&key, sizeof(key)); + +如果你的钥匙来源不是这两个，那么你的做法是错的。 + +使用哈希函数 +============ + +这个函数有两种变体，一个是接受整数列表，另一种是接受缓冲区:: + + u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key); + +和:: + + u32 hsiphash_1u32(u32, const hsiphash_key_t *key); + u32 hsiphash_2u32(u32, u32, const hsiphash_key_t *key); + u32 hsiphash_3u32(u32, u32, u32, const hsiphash_key_t *key); + u32 hsiphash_4u32(u32, u32, u32, u32, const hsiphash_key_t *key); + +如果向一个通用的hsiphash函数传递一个恒定长度的常量，他将在编译 +的时候将常量折叠，并自动选择一个优化后的函数。 + +哈希表键函数的用法 +================== + +:: + + struct some_hashtable { + DECLARE_HASHTABLE(hashtable, 8); + hsiphash_key_t key; + }; + + void init_hashtable(struct some_hashtable *table) + { + get_random_bytes(&table->key, sizeof(table->key)); + } + + static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input) + { + return &table->hashtable[hsiphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)]; + } + +然后，你可以像往常一样对返回的哈希存储桶进行迭代。 + +性能 +==== + +hsiphash()大约比jhash()慢三倍，这是因为有许多替换，不过这些都不是问题， +因为哈希表查找不是瓶颈。而且，这些牺牲是为了hsiphash()的安全性和DoS抗 +性，这是值得的。 diff --git a/Documentation/translations/zh_CN/subsystem-apis.rst b/Documentation/translations/zh_CN/subsystem-apis.rst index 47780bb0772f..8b646c1010be 100644 --- a/Documentation/translations/zh_CN/subsystem-apis.rst +++ b/Documentation/translations/zh_CN/subsystem-apis.rst @@ -88,6 +88,7 @@ TODOList: cpu-freq/index iio/index virt/index + security/index PCI/index peci/index @@ -102,7 +103,6 @@ TODOList: * watchdog/index * hwmon/index * accel/index -* security/index * crypto/index * bpf/index * usb/index diff --git a/Documentation/translations/zh_TW/admin-guide/bug-hunting.rst b/Documentation/translations/zh_TW/admin-guide/bug-hunting.rst index c139ec99cab1..b25ecc44d735 100644 --- a/Documentation/translations/zh_TW/admin-guide/bug-hunting.rst +++ b/Documentation/translations/zh_TW/admin-guide/bug-hunting.rst @@ -332,13 +332,3 @@ sysklogd發行版附帶了一個補丁，它修改了 ``modules-2.0.0`` 包， Aug 29 09:51:01 blizard kernel: Call Trace: [oops:_oops_ioctl+48/80] [_sys_ioctl+254/272] [_system_call+82/128] Aug 29 09:51:01 blizard kernel: Code: c7 00 05 00 00 00 eb 08 90 90 90 90 90 90 90 90 89 ec 5d c3 ---------------------------------------------------------------------------- - -:: - - Dr. G.W. Wettstein Oncology Research Div. Computing Facility - Roger Maris Cancer Center INTERNET: greg@wind.rmcc.com - 820 4th St. N. - Fargo, ND 58122 - Phone: 701-234-7556 - diff --git a/Documentation/translations/zh_TW/admin-guide/mm/damon/usage.rst b/Documentation/translations/zh_TW/admin-guide/mm/damon/usage.rst index fbbbbad59ee4..d3fd4f850793 100644 --- a/Documentation/translations/zh_TW/admin-guide/mm/damon/usage.rst +++ b/Documentation/translations/zh_TW/admin-guide/mm/damon/usage.rst @@ -26,12 +26,7 @@ DAMON 爲不同的用戶提供了下面這些接口。 使用它，用戶可以通過讀取和寫入特殊的sysfs文件來使用DAMON的主要功能。因此，你可以編寫和使 用你個性化的DAMON sysfs包裝程序，代替你讀/寫sysfs文件。 `DAMON用戶空間工具 `_ 就是這種程序的一個例子 它同時支持虛擬和物理地址 - 空間的監測。注意，這個界面只提供簡單的監測結果 :ref:`統計 `。對於詳細的監測 - 結果，DAMON提供了一個:ref:`跟蹤點 `。 -- *debugfs interface.* - :ref:`這 ` 幾乎與:ref:`sysfs interface ` 接 - 口相同。這將在下一個LTS內核發佈後被移除，所以用戶應該轉移到 - :ref:`sysfs interface `。 + 空間的監測。 - *內核空間編程接口。* :doc:`這 ` 這是爲內核空間程序員準備的。使用它，用戶可以通過爲你編寫內 核空間的DAMON應用程序，最靈活有效地利用DAMON的每一個功能。你甚至可以爲各種地址空間擴展DAMON。 @@ -335,247 +330,6 @@ tried_regions// 請注意，我們強烈建議使用用戶空間的工具，如 `damo `_ ， 而不是像上面那樣手動讀寫文件。以上只是一個例子。 -debugfs接口 -=========== - -.. note:: - - DAMON debugfs接口將在下一個LTS內核發佈後被移除，所以用戶應該轉移到 - :ref:`sysfs接口`。 - -DAMON導出了八個文件, ``attrs``, ``target_ids``, ``init_regions``, -``schemes``, ``monitor_on_DEPRECATED``, ``kdamond_pid``, ``mk_contexts`` 和 -``rm_contexts`` under its debugfs directory, ``/damon/``. - - -屬性 ----- - -用戶可以通過讀取和寫入 ``attrs`` 文件獲得和設置 ``採樣間隔`` 、 ``聚集間隔`` 、 ``更新間隔`` -以及監測目標區域的最小/最大數量。要詳細瞭解監測屬性，請參考 `:doc:/mm/damon/design` 。例如， -下面的命令將這些值設置爲5ms、100ms、1000ms、10和1000，然後再次檢查:: - - # cd /damon - # echo 5000 100000 1000000 10 1000 > attrs - # cat attrs - 5000 100000 1000000 10 1000 - - -目標ID ------- - -一些類型的地址空間支持多個監測目標。例如，虛擬內存地址空間的監測可以有多個進程作爲監測目標。用戶 -可以通過寫入目標的相關id值來設置目標，並通過讀取 ``target_ids`` 文件來獲得當前目標的id。在監 -測虛擬地址空間的情況下，這些值應該是監測目標進程的pid。例如，下面的命令將pid爲42和4242的進程設 -爲監測目標，並再次檢查:: - - # cd /damon - # echo 42 4242 > target_ids - # cat target_ids - 42 4242 - -用戶還可以通過在文件中寫入一個特殊的關鍵字 "paddr\n" 來監測系統的物理內存地址空間。因爲物理地 -址空間監測不支持多個目標，讀取文件會顯示一個假值，即 ``42`` ，如下圖所示:: - - # cd /damon - # echo paddr > target_ids - # cat target_ids - 42 - -請注意，設置目標ID並不啓動監測。 - - -初始監測目標區域 ----------------- - -在虛擬地址空間監測的情況下，DAMON自動設置和更新監測的目標區域，這樣就可以覆蓋目標進程的整個 -內存映射。然而，用戶可能希望將監測區域限制在特定的地址範圍內，如堆、棧或特定的文件映射區域。 -或者，一些用戶可以知道他們工作負載的初始訪問模式，因此希望爲“自適應區域調整”設置最佳初始區域。 - -相比之下，DAMON在物理內存監測的情況下不會自動設置和更新監測目標區域。因此，用戶應該自己設置 -監測目標區域。 - -在這種情況下，用戶可以通過在 ``init_regions`` 文件中寫入適當的值，明確地設置他們想要的初 -始監測目標區域。輸入應該是一個由三個整數組成的隊列，用空格隔開，代表一個區域的形式如下:: - - - -目標idx應該是 ``target_ids`` 文件中目標的索引，從 ``0`` 開始，區域應該按照地址順序傳遞。 -例如，下面的命令將設置幾個地址範圍， ``1-100`` 和 ``100-200`` 作爲pid 42的初始監測目標 -區域，這是 ``target_ids`` 中的第一個（索引 ``0`` ），另外幾個地址範圍， ``20-40`` 和 -``50-100`` 作爲pid 4242的地址，這是 ``target_ids`` 中的第二個（索引 ``1`` ）:: - - # cd /damon - # cat target_ids - 42 4242 - # echo "0 1 100 \ - 0 100 200 \ - 1 20 40 \ - 1 50 100" > init_regions - -請注意，這只是設置了初始的監測目標區域。在虛擬內存監測的情況下，DAMON會在一個 ``更新間隔`` -後自動更新區域的邊界。因此，在這種情況下，如果用戶不希望更新的話，應該把 ``更新間隔`` 設 -置得足夠大。 - - -方案 ----- - -對於通常的基於DAMON的數據訪問感知的內存管理優化，用戶只是希望系統對特定訪問模式的內存區域應用內 -存管理操作。DAMON從用戶那裏接收這種形式化的操作方案，並將這些方案應用到目標進程中。 - -用戶可以通過讀取和寫入 ``scheme`` debugfs文件來獲得和設置這些方案。讀取該文件還可以顯示每個 -方案的統計數據。在文件中，每一個方案都應該在每一行中以下列形式表示出來:: - - - -你可以通過簡單地在文件中寫入一個空字符串來禁用方案。 - -目標訪問模式 -~~~~~~~~~~~~ - -``<目標訪問模式>`` 是由三個範圍構成的，形式如下:: - - min-size max-size min-acc max-acc min-age max-age - -具體來說，區域大小的字節數（ `min-size` 和 `max-size` ），訪問頻率的每聚合區間的監測訪問次 -數（ `min-acc` 和 `max-acc` ），區域年齡的聚合區間數（ `min-age` 和 `max-age` ）都被指定。 -請注意，這些範圍是封閉區間。 - -動作 -~~~~ - -```` 是一個預定義的內存管理動作的整數，DAMON將應用於具有目標訪問模式的區域。支持 -的數字和它們的含義如下:: - - - 0: Call ``madvise()`` for the region with ``MADV_WILLNEED`` - - 1: Call ``madvise()`` for the region with ``MADV_COLD`` - - 2: Call ``madvise()`` for the region with ``MADV_PAGEOUT`` - - 3: Call ``madvise()`` for the region with ``MADV_HUGEPAGE`` - - 4: Call ``madvise()`` for the region with ``MADV_NOHUGEPAGE`` - - 5: Do nothing but count the statistics - -配額 -~~~~ - -每個 ``動作`` 的最佳 ``目標訪問模式`` 取決於工作負載，所以不容易找到。更糟糕的是，將某個 -動作的方案設置得過於激進會導致嚴重的開銷。爲了避免這種開銷，用戶可以通過下面表格中的 ```` -來限制方案的時間和大小配額:: - - - -這使得DAMON在 ```` 毫秒內，儘量只用 ```` 毫秒的時間對 ``目標訪 -問模式`` 的內存區域應用動作，並在 ```` 內只對最多字節的內存區域應 -用動作。將 ```` 和 ```` 都設置爲零，可以禁用配額限制。 - -當預計超過配額限制時，DAMON會根據 ``目標訪問模式`` 的大小、訪問頻率和年齡，對發現的內存 -區域進行優先排序。爲了實現個性化的優先級，用戶可以在 ``<優先級權重>`` 中設置這三個屬性的 -權重，具體形式如下:: - - - -水位 -~~~~ - -有些方案需要根據系統特定指標的當前值來運行，如自由內存比率。對於這種情況，用戶可以爲該條 -件指定水位。:: - - - -```` 是一個預定義的整數，用於要檢查的度量。支持的數字和它們的含義如下。 - - - 0: 忽視水位 - - 1: 系統空閒內存率 (千分比) - -每隔 ``<檢查間隔>`` 微秒檢查一次公制的值。 - -如果該值高於 ``<高標>`` 或低於 ``<低標>`` ，該方案被停用。如果該值低於 ``<中標>`` ， -該方案將被激活。 - -統計數據 -~~~~~~~~ - -它還統計每個方案被嘗試應用的區域的總數量和字節數，每個方案被成功應用的區域的兩個數量，以 -及超過配額限制的總數量。這些統計數據可用於在線分析或調整方案。 - -統計數據可以通過讀取方案文件來顯示。讀取該文件將顯示你在每一行中輸入的每個 ``方案`` ， -統計的五個數字將被加在每一行的末尾。 - -例子 -~~~~ - -下面的命令應用了一個方案：”如果一個大小爲[4KiB, 8KiB]的內存區域在[10, 20]的聚合時間 -間隔內顯示出每一個聚合時間間隔[0, 5]的訪問量，請分頁出該區域。對於分頁，每秒最多隻能使 -用10ms，而且每秒分頁不能超過1GiB。在這一限制下，首先分頁出具有較長年齡的內存區域。另外， -每5秒鐘檢查一次系統的可用內存率，當可用內存率低於50%時開始監測和分頁，但如果可用內存率 -大於60%，或低於30%，則停止監測“:: - - # cd /damon - # scheme="4096 8192 0 5 10 20 2" # target access pattern and action - # scheme+=" 10 $((1024*1024*1024)) 1000" # quotas - # scheme+=" 0 0 100" # prioritization weights - # scheme+=" 1 5000000 600 500 300" # watermarks - # echo "$scheme" > schemes - - -開關 ----- - -除非你明確地啓動監測，否則如上所述的文件設置不會產生效果。你可以通過寫入和讀取 ``monitor_on_DEPRECATED`` -文件來啓動、停止和檢查監測的當前狀態。寫入 ``on`` 該文件可以啓動對有屬性的目標的監測。寫入 -``off`` 該文件則停止這些目標。如果每個目標進程被終止，DAMON也會停止。下面的示例命令開啓、關 -閉和檢查DAMON的狀態:: - - # cd /damon - # echo on > monitor_on_DEPRECATED - # echo off > monitor_on_DEPRECATED - # cat monitor_on_DEPRECATED - off - -請注意，當監測開啓時，你不能寫到上述的debugfs文件。如果你在DAMON運行時寫到這些文件，將會返 -回一個錯誤代碼，如 ``-EBUSY`` 。 - - -監測線程PID ------------ - -DAMON通過一個叫做kdamond的內核線程來進行請求監測。你可以通過讀取 ``kdamond_pid`` 文件獲 -得該線程的 ``pid`` 。當監測被 ``關閉`` 時，讀取該文件不會返回任何信息:: - - # cd /damon - # cat monitor_on_DEPRECATED - off - # cat kdamond_pid - none - # echo on > monitor_on_DEPRECATED - # cat kdamond_pid - 18594 - - -使用多個監測線程 ----------------- - -每個監測上下文都會創建一個 ``kdamond`` 線程。你可以使用 ``mk_contexts`` 和 ``rm_contexts`` -文件爲多個 ``kdamond`` 需要的用例創建和刪除監測上下文。 - -將新上下文的名稱寫入 ``mk_contexts`` 文件，在 ``DAMON debugfs`` 目錄上創建一個該名稱的目錄。 -該目錄將有該上下文的 ``DAMON debugfs`` 文件:: - - # cd /damon - # ls foo - # ls: cannot access 'foo': No such file or directory - # echo foo > mk_contexts - # ls foo - # attrs init_regions kdamond_pid schemes target_ids - -如果不再需要上下文，你可以通過把上下文的名字放到 ``rm_contexts`` 文件中來刪除它和相應的目錄:: - - # echo foo > rm_contexts - # ls foo - # ls: cannot access 'foo': No such file or directory - -注意， ``mk_contexts`` 、 ``rm_contexts`` 和 ``monitor_on_DEPRECATED`` 文件只在根目錄下。 - 監測結果的監測點 ================ diff --git a/Documentation/translations/zh_TW/admin-guide/sysrq.rst b/Documentation/translations/zh_TW/admin-guide/sysrq.rst index 4a08db00a495..4979e5d5405f 100644 --- a/Documentation/translations/zh_TW/admin-guide/sysrq.rst +++ b/Documentation/translations/zh_TW/admin-guide/sysrq.rst @@ -60,24 +60,24 @@ CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE 必須是以 16 進制數寫入。 ~~~~~~~~~~~~~~~~~~~~~~~ 在 x86 架構上 - 你可以按下鍵盤組合鍵 :kbd:`ALT-SysRq-`。 + 你可以按下鍵盤組合鍵 `ALT-SysRq-`。 .. note:: 一些鍵盤可能沒有標識 'SySRq' 鍵。'SySRq' 鍵也被當做 'Print Screen'鍵。 - 同時有些鍵盤無法處理同時按下這麼多鍵，因此你可以先按下鍵盤 :kbd:`Alt` 鍵， - 然後按下鍵盤 :kbd:`SysRq` 鍵，再釋放鍵盤 :kbd:`SysRq` 鍵，之後按下鍵盤上命令鍵 - :kbd:``，最後釋放所有鍵。 + 同時有些鍵盤無法處理同時按下這麼多鍵，因此你可以先按下鍵盤 `Alt` 鍵， + 然後按下鍵盤 `SysRq` 鍵，再釋放鍵盤 `SysRq` 鍵，之後按下鍵盤上命令鍵 + ``，最後釋放所有鍵。 在 SPARC 架構上 - 你可以按下鍵盤組合鍵 :kbd:`ALT-STOP-` 。 + 你可以按下鍵盤組合鍵 `ALT-STOP-` 。 在串行控制檯（只針對 PC 類型的標準串口） 你可以發一個 ``BREAK`` ，然後在 5 秒內發送一個命令鍵， 發送 ``BREAK`` 兩次將被翻譯爲一個正常的 BREAK 操作。 在 PowerPC 架構上 - 按下鍵盤組合鍵 :kbd:`ALT - Print Screen` （或者 :kbd:`F13`） - :kbd:`<命令鍵>` 。 - :kbd:`Print Screen` （或者 :kbd:`F13`） - :kbd:`<命令鍵>` 或許也能實現。 + 按下鍵盤組合鍵 `ALT - Print Screen` （或者 `F13`） - `<命令鍵>` 。 + `Print Screen` （或者 `F13`） - `<命令鍵>` 或許也能實現。 在其他架構上 如果你知道其他架構的組合鍵，請告訴我，我可以把它們添加到這部分。 @@ -87,7 +87,7 @@ CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE 必須是以 16 進制數寫入。 echo t > /proc/sysrq-trigger -這個命令鍵 :kbd:`` 是區分大小寫的。 +這個命令鍵 `` 是區分大小寫的。 什麼是命令鍵？ ~~~~~~~~~~~~~~ @@ -203,8 +203,8 @@ syslogd/klogd 進程是運行的，它們仍將被記錄。） ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 這也會發生在我這，我發現輕敲鍵盤兩側的 shift、alt 和 control 鍵，然後再次敲擊 -一個無效的 SysRq 鍵序列可以解決問題。（比如，像鍵盤組合鍵 :kbd:`alt-sysrq-z` ） -切換到另一個虛擬控制檯（鍵盤操作 :kbd:`ALT+Fn` ），然後再切回來應該也有幫助。 +一個無效的 SysRq 鍵序列可以解決問題。（比如，像鍵盤組合鍵 `alt-sysrq-z` ） +切換到另一個虛擬控制檯（鍵盤操作 `ALT+Fn` ），然後再切回來應該也有幫助。 我敲擊了 SysRq 鍵，但像是什麼都沒發生，發生了什麼錯誤？ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -259,7 +259,7 @@ SysRq 鍵的輸出和所有其他控制檯輸出一樣，受制於控制檯日 文件的消費訪問到。作爲一個特例，來自 sysrq 命令的標題行將被傳遞給所有控制檯 使用者，就好像當前日誌級別是最大的一樣。如果只發出標題頭，則幾乎可以肯定內核日誌 級別太低。如果你需要控制檯上的輸出，那麼你將需要臨時提高控制檯日誌級別，通過使用 -鍵盤組合鍵 :kbd:`alt-sysrq-8` 或者:: +鍵盤組合鍵 `alt-sysrq-8` 或者:: echo 8 > /proc/sysrq-trigger diff --git a/Documentation/translations/zh_TW/process/email-clients.rst b/Documentation/translations/zh_TW/process/email-clients.rst index a5ac9400a9f5..4543c447d797 100644 --- a/Documentation/translations/zh_TW/process/email-clients.rst +++ b/Documentation/translations/zh_TW/process/email-clients.rst @@ -86,7 +86,7 @@ Alpine (TUI) - :menuselection:`Do Not Send Flowed Text` 必須開啓 - :menuselection:`Strip Whitespace Before Sending` 必須關閉 -當寫郵件時，光標應該放在補丁會出現的地方，然後按下 :kbd:`CTRL-R` 組合鍵，使指 +當寫郵件時，光標應該放在補丁會出現的地方，然後按下 `CTRL-R` 組合鍵，使指 定的補丁文件嵌入到郵件中。 Claws Mail (GUI) @@ -94,7 +94,7 @@ Claws Mail (GUI) 可以用，有人用它成功地發過補丁。 -用 :menuselection:`Message-->Insert File` (:kbd:`CTRL-I`) 或外置編輯器插入補丁。 +用 :menuselection:`Message-->Insert File` (`CTRL-I`) 或外置編輯器插入補丁。 若要在Claws編輯窗口重修改插入的補丁，需關閉 :menuselection:`Configuration-->Preferences-->Compose-->Wrapping` @@ -106,11 +106,11 @@ Evolution (GUI) 一些開發者成功的使用它發送補丁。 撰寫郵件時： -從 :menuselection:`格式-->段落樣式-->預格式化` (:kbd:`CTRL-7`) +從 :menuselection:`格式-->段落樣式-->預格式化` (`CTRL-7`) 或工具欄選擇 :menuselection:`預格式化` ； 然後使用： -:menuselection:`插入-->文本文件...` (:kbd:`ALT-N x`) 插入補丁文件。 +:menuselection:`插入-->文本文件...` (`ALT-N x`) 插入補丁文件。 你還可以 ``diff -Nru old.c new.c | xclip`` ，選擇 :menuselection:`預格式化` ， 然後使用鼠標中鍵進行粘帖。 diff --git a/Documentation/usb/usbip_protocol.rst b/Documentation/usb/usbip_protocol.rst index adc158967cc6..3da1df3d94f5 100644 --- a/Documentation/usb/usbip_protocol.rst +++ b/Documentation/usb/usbip_protocol.rst @@ -285,17 +285,17 @@ OP_REP_IMPORT: +-----------+--------+------------+---------------------------------------------------+ | 0x138 | 2 | | bcdDevice | +-----------+--------+------------+---------------------------------------------------+ -| 0x139 | 1 | | bDeviceClass | +| 0x13A | 1 | | bDeviceClass | +-----------+--------+------------+---------------------------------------------------+ -| 0x13A | 1 | | bDeviceSubClass | +| 0x13B | 1 | | bDeviceSubClass | +-----------+--------+------------+---------------------------------------------------+ -| 0x13B | 1 | | bDeviceProtocol | +| 0x13C | 1 | | bDeviceProtocol | +-----------+--------+------------+---------------------------------------------------+ -| 0x13C | 1 | | bConfigurationValue | +| 0x13D | 1 | | bConfigurationValue | +-----------+--------+------------+---------------------------------------------------+ -| 0x13D | 1 | | bNumConfigurations | +| 0x13E | 1 | | bNumConfigurations | +-----------+--------+------------+---------------------------------------------------+ -| 0x13E | 1 | | bNumInterfaces | +| 0x13F | 1 | | bNumInterfaces | +-----------+--------+------------+---------------------------------------------------+ The following four commands have a common basic header called diff --git a/Documentation/userspace-api/check_exec.rst b/Documentation/userspace-api/check_exec.rst new file mode 100644 index 000000000000..05dfe3b56f71 --- /dev/null +++ b/Documentation/userspace-api/check_exec.rst @@ -0,0 +1,144 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright © 2024 Microsoft Corporation + +=================== +Executability check +=================== + +The ``AT_EXECVE_CHECK`` :manpage:`execveat(2)` flag, and the +``SECBIT_EXEC_RESTRICT_FILE`` and ``SECBIT_EXEC_DENY_INTERACTIVE`` securebits +are intended for script interpreters and dynamic linkers to enforce a +consistent execution security policy handled by the kernel. See the +`samples/check-exec/inc.c`_ example. + +Whether an interpreter should check these securebits or not depends on the +security risk of running malicious scripts with respect to the execution +environment, and whether the kernel can check if a script is trustworthy or +not. For instance, Python scripts running on a server can use arbitrary +syscalls and access arbitrary files. Such interpreters should then be +enlighten to use these securebits and let users define their security policy. +However, a JavaScript engine running in a web browser should already be +sandboxed and then should not be able to harm the user's environment. + +Script interpreters or dynamic linkers built for tailored execution environments +(e.g. hardened Linux distributions or hermetic container images) could use +``AT_EXECVE_CHECK`` without checking the related securebits if backward +compatibility is handled by something else (e.g. atomic update ensuring that +all legitimate libraries are allowed to be executed). It is then recommended +for script interpreters and dynamic linkers to check the securebits at run time +by default, but also to provide the ability for custom builds to behave like if +``SECBIT_EXEC_RESTRICT_FILE`` or ``SECBIT_EXEC_DENY_INTERACTIVE`` were always +set to 1 (i.e. always enforce restrictions). + +AT_EXECVE_CHECK +=============== + +Passing the ``AT_EXECVE_CHECK`` flag to :manpage:`execveat(2)` only performs a +check on a regular file and returns 0 if execution of this file would be +allowed, ignoring the file format and then the related interpreter dependencies +(e.g. ELF libraries, script's shebang). + +Programs should always perform this check to apply kernel-level checks against +files that are not directly executed by the kernel but passed to a user space +interpreter instead. All files that contain executable code, from the point of +view of the interpreter, should be checked. However the result of this check +should only be enforced according to ``SECBIT_EXEC_RESTRICT_FILE`` or +``SECBIT_EXEC_DENY_INTERACTIVE.``. + +The main purpose of this flag is to improve the security and consistency of an +execution environment to ensure that direct file execution (e.g. +``./script.sh``) and indirect file execution (e.g. ``sh script.sh``) lead to +the same result. For instance, this can be used to check if a file is +trustworthy according to the caller's environment. + +In a secure environment, libraries and any executable dependencies should also +be checked. For instance, dynamic linking should make sure that all libraries +are allowed for execution to avoid trivial bypass (e.g. using ``LD_PRELOAD``). +For such secure execution environment to make sense, only trusted code should +be executable, which also requires integrity guarantees. + +To avoid race conditions leading to time-of-check to time-of-use issues, +``AT_EXECVE_CHECK`` should be used with ``AT_EMPTY_PATH`` to check against a +file descriptor instead of a path. + +SECBIT_EXEC_RESTRICT_FILE and SECBIT_EXEC_DENY_INTERACTIVE +========================================================== + +When ``SECBIT_EXEC_RESTRICT_FILE`` is set, a process should only interpret or +execute a file if a call to :manpage:`execveat(2)` with the related file +descriptor and the ``AT_EXECVE_CHECK`` flag succeed. + +This secure bit may be set by user session managers, service managers, +container runtimes, sandboxer tools... Except for test environments, the +related ``SECBIT_EXEC_RESTRICT_FILE_LOCKED`` bit should also be set. + +Programs should only enforce consistent restrictions according to the +securebits but without relying on any other user-controlled configuration. +Indeed, the use case for these securebits is to only trust executable code +vetted by the system configuration (through the kernel), so we should be +careful to not let untrusted users control this configuration. + +However, script interpreters may still use user configuration such as +environment variables as long as it is not a way to disable the securebits +checks. For instance, the ``PATH`` and ``LD_PRELOAD`` variables can be set by +a script's caller. Changing these variables may lead to unintended code +executions, but only from vetted executable programs, which is OK. For this to +make sense, the system should provide a consistent security policy to avoid +arbitrary code execution e.g., by enforcing a write xor execute policy. + +When ``SECBIT_EXEC_DENY_INTERACTIVE`` is set, a process should never interpret +interactive user commands (e.g. scripts). However, if such commands are passed +through a file descriptor (e.g. stdin), its content should be interpreted if a +call to :manpage:`execveat(2)` with the related file descriptor and the +``AT_EXECVE_CHECK`` flag succeed. + +For instance, script interpreters called with a script snippet as argument +should always deny such execution if ``SECBIT_EXEC_DENY_INTERACTIVE`` is set. + +This secure bit may be set by user session managers, service managers, +container runtimes, sandboxer tools... Except for test environments, the +related ``SECBIT_EXEC_DENY_INTERACTIVE_LOCKED`` bit should also be set. + +Here is the expected behavior for a script interpreter according to combination +of any exec securebits: + +1. ``SECBIT_EXEC_RESTRICT_FILE=0`` and ``SECBIT_EXEC_DENY_INTERACTIVE=0`` + + Always interpret scripts, and allow arbitrary user commands (default). + + No threat, everyone and everything is trusted, but we can get ahead of + potential issues thanks to the call to :manpage:`execveat(2)` with + ``AT_EXECVE_CHECK`` which should always be performed but ignored by the + script interpreter. Indeed, this check is still important to enable systems + administrators to verify requests (e.g. with audit) and prepare for + migration to a secure mode. + +2. ``SECBIT_EXEC_RESTRICT_FILE=1`` and ``SECBIT_EXEC_DENY_INTERACTIVE=0`` + + Deny script interpretation if they are not executable, but allow + arbitrary user commands. + + The threat is (potential) malicious scripts run by trusted (and not fooled) + users. That can protect against unintended script executions (e.g. ``sh + /tmp/*.sh``). This makes sense for (semi-restricted) user sessions. + +3. ``SECBIT_EXEC_RESTRICT_FILE=0`` and ``SECBIT_EXEC_DENY_INTERACTIVE=1`` + + Always interpret scripts, but deny arbitrary user commands. + + This use case may be useful for secure services (i.e. without interactive + user session) where scripts' integrity is verified (e.g. with IMA/EVM or + dm-verity/IPE) but where access rights might not be ready yet. Indeed, + arbitrary interactive commands would be much more difficult to check. + +4. ``SECBIT_EXEC_RESTRICT_FILE=1`` and ``SECBIT_EXEC_DENY_INTERACTIVE=1`` + + Deny script interpretation if they are not executable, and also deny + any arbitrary user commands. + + The threat is malicious scripts run by untrusted users (but trusted code). + This makes sense for system services that may only execute trusted scripts. + +.. Links +.. _samples/check-exec/inc.c: + https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/samples/check-exec/inc.c diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 274cc7546efc..b1395d94b3fd 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -35,6 +35,7 @@ Security-related interfaces mfd_noexec spec_ctrl tee + check_exec Devices and I/O =============== @@ -63,6 +64,7 @@ Everything else vduse futex2 perf_ring_buffer + ntsync .. only:: subproject and html diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 243f1f1b554a..6d1465315df3 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -283,6 +283,7 @@ Code Seq# Include File Comments 'p' 80-9F linux/ppdev.h user-space parport 'p' A1-A5 linux/pps.h LinuxPPS +'p' B1-B3 linux/pps_gen.h LinuxPPS 'q' 00-1F linux/serio.h 'q' 80-FF linux/telephony.h Internet PhoneJACK, Internet LineJACK @@ -311,6 +312,7 @@ Code Seq# Include File Comments 'z' 10-4F drivers/s390/crypto/zcrypt_api.h conflict! '|' 00-7F linux/media.h +'|' 80-9F samples/ Any sample and example drivers 0x80 00-1F linux/fb.h 0x81 00-1F linux/vduse.h 0x89 00-06 arch/x86/include/asm/sockios.h diff --git a/Documentation/userspace-api/netlink/c-code-gen.rst b/Documentation/userspace-api/netlink/c-code-gen.rst index 89de42c13350..46415e6d646d 100644 --- a/Documentation/userspace-api/netlink/c-code-gen.rst +++ b/Documentation/userspace-api/netlink/c-code-gen.rst @@ -56,7 +56,9 @@ If ``name-prefix`` is specified it replaces the ``$family-$enum`` portion of the entry name. Boolean ``render-max`` controls creation of the max values -(which are enabled by default for attribute enums). +(which are enabled by default for attribute enums). These max +values are named ``__$pfx-MAX`` and ``$pfx-MAX``. The name +of the first value can be overridden via ``enum-cnt-name`` property. Attributes ========== diff --git a/Documentation/userspace-api/netlink/intro-specs.rst b/Documentation/userspace-api/netlink/intro-specs.rst index bada89699455..a4435ae4628d 100644 --- a/Documentation/userspace-api/netlink/intro-specs.rst +++ b/Documentation/userspace-api/netlink/intro-specs.rst @@ -15,7 +15,7 @@ developing Netlink related code. The tool is implemented in Python and can use a YAML specification to issue Netlink requests to the kernel. Only Generic Netlink is supported. -The tool is located at ``tools/net/ynl/cli.py``. It accepts +The tool is located at ``tools/net/ynl/pyynl/cli.py``. It accepts a handul of arguments, the most important ones are: - ``--spec`` - point to the spec file @@ -27,7 +27,7 @@ YAML specs can be found under ``Documentation/netlink/specs/``. Example use:: - $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/ethtool.yaml \ + $ ./tools/net/ynl/pyynl/cli.py --spec Documentation/netlink/specs/ethtool.yaml \ --do rings-get \ --json '{"header":{"dev-index": 18}}' {'header': {'dev-index': 18, 'dev-name': 'eni1np1'}, @@ -75,7 +75,7 @@ the two marker lines like above to a file, add that file to git, and run the regeneration tool. Grep the tree for ``YNL-GEN`` to see other examples. -The code generation itself is performed by ``tools/net/ynl/ynl-gen-c.py`` +The code generation itself is performed by ``tools/net/ynl/pyynl/ynl_gen_c.py`` but it takes a few arguments so calling it directly for each file quickly becomes tedious. @@ -84,7 +84,7 @@ YNL lib ``tools/net/ynl/lib/`` contains an implementation of a C library (based on libmnl) which integrates with code generated by -``tools/net/ynl/ynl-gen-c.py`` to create easy to use netlink wrappers. +``tools/net/ynl/pyynl/ynl_gen_c.py`` to create easy to use netlink wrappers. YNL basics ---------- diff --git a/Documentation/userspace-api/ntsync.rst b/Documentation/userspace-api/ntsync.rst new file mode 100644 index 000000000000..25e7c4aef968 --- /dev/null +++ b/Documentation/userspace-api/ntsync.rst @@ -0,0 +1,385 @@ +=================================== +NT synchronization primitive driver +=================================== + +This page documents the user-space API for the ntsync driver. + +ntsync is a support driver for emulation of NT synchronization +primitives by user-space NT emulators. It exists because implementation +in user-space, using existing tools, cannot match Windows performance +while offering accurate semantics. It is implemented entirely in +software, and does not drive any hardware device. + +This interface is meant as a compatibility tool only, and should not +be used for general synchronization. Instead use generic, versatile +interfaces such as futex(2) and poll(2). + +Synchronization primitives +========================== + +The ntsync driver exposes three types of synchronization primitives: +semaphores, mutexes, and events. + +A semaphore holds a single volatile 32-bit counter, and a static 32-bit +integer denoting the maximum value. It is considered signaled (that is, +can be acquired without contention, or will wake up a waiting thread) +when the counter is nonzero. The counter is decremented by one when a +wait is satisfied. Both the initial and maximum count are established +when the semaphore is created. + +A mutex holds a volatile 32-bit recursion count, and a volatile 32-bit +identifier denoting its owner. A mutex is considered signaled when its +owner is zero (indicating that it is not owned). The recursion count is +incremented when a wait is satisfied, and ownership is set to the given +identifier. + +A mutex also holds an internal flag denoting whether its previous owner +has died; such a mutex is said to be abandoned. Owner death is not +tracked automatically based on thread death, but rather must be +communicated using ``NTSYNC_IOC_MUTEX_KILL``. An abandoned mutex is +inherently considered unowned. + +Except for the "unowned" semantics of zero, the actual value of the +owner identifier is not interpreted by the ntsync driver at all. The +intended use is to store a thread identifier; however, the ntsync +driver does not actually validate that a calling thread provides +consistent or unique identifiers. + +An event is similar to a semaphore with a maximum count of one. It holds +a volatile boolean state denoting whether it is signaled or not. There +are two types of events, auto-reset and manual-reset. An auto-reset +event is designaled when a wait is satisfied; a manual-reset event is +not. The event type is specified when the event is created. + +Unless specified otherwise, all operations on an object are atomic and +totally ordered with respect to other operations on the same object. + +Objects are represented by files. When all file descriptors to an +object are closed, that object is deleted. + +Char device +=========== + +The ntsync driver creates a single char device /dev/ntsync. Each file +description opened on the device represents a unique instance intended +to back an individual NT virtual machine. Objects created by one ntsync +instance may only be used with other objects created by the same +instance. + +ioctl reference +=============== + +All operations on the device are done through ioctls. There are four +structures used in ioctl calls:: + + struct ntsync_sem_args { + __u32 count; + __u32 max; + }; + + struct ntsync_mutex_args { + __u32 owner; + __u32 count; + }; + + struct ntsync_event_args { + __u32 signaled; + __u32 manual; + }; + + struct ntsync_wait_args { + __u64 timeout; + __u64 objs; + __u32 count; + __u32 owner; + __u32 index; + __u32 alert; + __u32 flags; + __u32 pad; + }; + +Depending on the ioctl, members of the structure may be used as input, +output, or not at all. + +The ioctls on the device file are as follows: + +.. c:macro:: NTSYNC_IOC_CREATE_SEM + + Create a semaphore object. Takes a pointer to struct + :c:type:`ntsync_sem_args`, which is used as follows: + + .. list-table:: + + * - ``count`` + - Initial count of the semaphore. + * - ``max`` + - Maximum count of the semaphore. + + Fails with ``EINVAL`` if ``count`` is greater than ``max``. + On success, returns a file descriptor the created semaphore. + +.. c:macro:: NTSYNC_IOC_CREATE_MUTEX + + Create a mutex object. Takes a pointer to struct + :c:type:`ntsync_mutex_args`, which is used as follows: + + .. list-table:: + + * - ``count`` + - Initial recursion count of the mutex. + * - ``owner`` + - Initial owner of the mutex. + + If ``owner`` is nonzero and ``count`` is zero, or if ``owner`` is + zero and ``count`` is nonzero, the function fails with ``EINVAL``. + On success, returns a file descriptor the created mutex. + +.. c:macro:: NTSYNC_IOC_CREATE_EVENT + + Create an event object. Takes a pointer to struct + :c:type:`ntsync_event_args`, which is used as follows: + + .. list-table:: + + * - ``signaled`` + - If nonzero, the event is initially signaled, otherwise + nonsignaled. + * - ``manual`` + - If nonzero, the event is a manual-reset event, otherwise + auto-reset. + + On success, returns a file descriptor the created event. + +The ioctls on the individual objects are as follows: + +.. c:macro:: NTSYNC_IOC_SEM_POST + + Post to a semaphore object. Takes a pointer to a 32-bit integer, + which on input holds the count to be added to the semaphore, and on + output contains its previous count. + + If adding to the semaphore's current count would raise the latter + past the semaphore's maximum count, the ioctl fails with + ``EOVERFLOW`` and the semaphore is not affected. If raising the + semaphore's count causes it to become signaled, eligible threads + waiting on this semaphore will be woken and the semaphore's count + decremented appropriately. + +.. c:macro:: NTSYNC_IOC_MUTEX_UNLOCK + + Release a mutex object. Takes a pointer to struct + :c:type:`ntsync_mutex_args`, which is used as follows: + + .. list-table:: + + * - ``owner`` + - Specifies the owner trying to release this mutex. + * - ``count`` + - On output, contains the previous recursion count. + + If ``owner`` is zero, the ioctl fails with ``EINVAL``. If ``owner`` + is not the current owner of the mutex, the ioctl fails with + ``EPERM``. + + The mutex's count will be decremented by one. If decrementing the + mutex's count causes it to become zero, the mutex is marked as + unowned and signaled, and eligible threads waiting on it will be + woken as appropriate. + +.. c:macro:: NTSYNC_IOC_SET_EVENT + + Signal an event object. Takes a pointer to a 32-bit integer, which on + output contains the previous state of the event. + + Eligible threads will be woken, and auto-reset events will be + designaled appropriately. + +.. c:macro:: NTSYNC_IOC_RESET_EVENT + + Designal an event object. Takes a pointer to a 32-bit integer, which + on output contains the previous state of the event. + +.. c:macro:: NTSYNC_IOC_PULSE_EVENT + + Wake threads waiting on an event object while leaving it in an + unsignaled state. Takes a pointer to a 32-bit integer, which on + output contains the previous state of the event. + + A pulse operation can be thought of as a set followed by a reset, + performed as a single atomic operation. If two threads are waiting on + an auto-reset event which is pulsed, only one will be woken. If two + threads are waiting a manual-reset event which is pulsed, both will + be woken. However, in both cases, the event will be unsignaled + afterwards, and a simultaneous read operation will always report the + event as unsignaled. + +.. c:macro:: NTSYNC_IOC_READ_SEM + + Read the current state of a semaphore object. Takes a pointer to + struct :c:type:`ntsync_sem_args`, which is used as follows: + + .. list-table:: + + * - ``count`` + - On output, contains the current count of the semaphore. + * - ``max`` + - On output, contains the maximum count of the semaphore. + +.. c:macro:: NTSYNC_IOC_READ_MUTEX + + Read the current state of a mutex object. Takes a pointer to struct + :c:type:`ntsync_mutex_args`, which is used as follows: + + .. list-table:: + + * - ``owner`` + - On output, contains the current owner of the mutex, or zero + if the mutex is not currently owned. + * - ``count`` + - On output, contains the current recursion count of the mutex. + + If the mutex is marked as abandoned, the function fails with + ``EOWNERDEAD``. In this case, ``count`` and ``owner`` are set to + zero. + +.. c:macro:: NTSYNC_IOC_READ_EVENT + + Read the current state of an event object. Takes a pointer to struct + :c:type:`ntsync_event_args`, which is used as follows: + + .. list-table:: + + * - ``signaled`` + - On output, contains the current state of the event. + * - ``manual`` + - On output, contains 1 if the event is a manual-reset event, + and 0 otherwise. + +.. c:macro:: NTSYNC_IOC_KILL_OWNER + + Mark a mutex as unowned and abandoned if it is owned by the given + owner. Takes an input-only pointer to a 32-bit integer denoting the + owner. If the owner is zero, the ioctl fails with ``EINVAL``. If the + owner does not own the mutex, the function fails with ``EPERM``. + + Eligible threads waiting on the mutex will be woken as appropriate + (and such waits will fail with ``EOWNERDEAD``, as described below). + +.. c:macro:: NTSYNC_IOC_WAIT_ANY + + Poll on any of a list of objects, atomically acquiring at most one. + Takes a pointer to struct :c:type:`ntsync_wait_args`, which is + used as follows: + + .. list-table:: + + * - ``timeout`` + - Absolute timeout in nanoseconds. If ``NTSYNC_WAIT_REALTIME`` + is set, the timeout is measured against the REALTIME clock; + otherwise it is measured against the MONOTONIC clock. If the + timeout is equal to or earlier than the current time, the + function returns immediately without sleeping. If ``timeout`` + is U64_MAX, the function will sleep until an object is + signaled, and will not fail with ``ETIMEDOUT``. + * - ``objs`` + - Pointer to an array of ``count`` file descriptors + (specified as an integer so that the structure has the same + size regardless of architecture). If any object is + invalid, the function fails with ``EINVAL``. + * - ``count`` + - Number of objects specified in the ``objs`` array. + If greater than ``NTSYNC_MAX_WAIT_COUNT``, the function fails + with ``EINVAL``. + * - ``owner`` + - Mutex owner identifier. If any object in ``objs`` is a mutex, + the ioctl will attempt to acquire that mutex on behalf of + ``owner``. If ``owner`` is zero, the ioctl fails with + ``EINVAL``. + * - ``index`` + - On success, contains the index (into ``objs``) of the object + which was signaled. If ``alert`` was signaled instead, + this contains ``count``. + * - ``alert`` + - Optional event object file descriptor. If nonzero, this + specifies an "alert" event object which, if signaled, will + terminate the wait. If nonzero, the identifier must point to a + valid event. + * - ``flags`` + - Zero or more flags. Currently the only flag is + ``NTSYNC_WAIT_REALTIME``, which causes the timeout to be + measured against the REALTIME clock instead of MONOTONIC. + * - ``pad`` + - Unused, must be set to zero. + + This function attempts to acquire one of the given objects. If unable + to do so, it sleeps until an object becomes signaled, subsequently + acquiring it, or the timeout expires. In the latter case the ioctl + fails with ``ETIMEDOUT``. The function only acquires one object, even + if multiple objects are signaled. + + A semaphore is considered to be signaled if its count is nonzero, and + is acquired by decrementing its count by one. A mutex is considered + to be signaled if it is unowned or if its owner matches the ``owner`` + argument, and is acquired by incrementing its recursion count by one + and setting its owner to the ``owner`` argument. An auto-reset event + is acquired by designaling it; a manual-reset event is not affected + by acquisition. + + Acquisition is atomic and totally ordered with respect to other + operations on the same object. If two wait operations (with different + ``owner`` identifiers) are queued on the same mutex, only one is + signaled. If two wait operations are queued on the same semaphore, + and a value of one is posted to it, only one is signaled. + + If an abandoned mutex is acquired, the ioctl fails with + ``EOWNERDEAD``. Although this is a failure return, the function may + otherwise be considered successful. The mutex is marked as owned by + the given owner (with a recursion count of 1) and as no longer + abandoned, and ``index`` is still set to the index of the mutex. + + The ``alert`` argument is an "extra" event which can terminate the + wait, independently of all other objects. + + It is valid to pass the same object more than once, including by + passing the same event in the ``objs`` array and in ``alert``. If a + wakeup occurs due to that object being signaled, ``index`` is set to + the lowest index corresponding to that object. + + The function may fail with ``EINTR`` if a signal is received. + +.. c:macro:: NTSYNC_IOC_WAIT_ALL + + Poll on a list of objects, atomically acquiring all of them. Takes a + pointer to struct :c:type:`ntsync_wait_args`, which is used + identically to ``NTSYNC_IOC_WAIT_ANY``, except that ``index`` is + always filled with zero on success if not woken via alert. + + This function attempts to simultaneously acquire all of the given + objects. If unable to do so, it sleeps until all objects become + simultaneously signaled, subsequently acquiring them, or the timeout + expires. In the latter case the ioctl fails with ``ETIMEDOUT`` and no + objects are modified. + + Objects may become signaled and subsequently designaled (through + acquisition by other threads) while this thread is sleeping. Only + once all objects are simultaneously signaled does the ioctl acquire + them and return. The entire acquisition is atomic and totally ordered + with respect to other operations on any of the given objects. + + If an abandoned mutex is acquired, the ioctl fails with + ``EOWNERDEAD``. Similarly to ``NTSYNC_IOC_WAIT_ANY``, all objects are + nevertheless marked as acquired. Note that if multiple mutex objects + are specified, there is no way to know which were marked as + abandoned. + + As with "any" waits, the ``alert`` argument is an "extra" event which + can terminate the wait. Critically, however, an "all" wait will + succeed if all members in ``objs`` are signaled, *or* if ``alert`` is + signaled. In the latter case ``index`` will be set to ``count``. As + with "any" waits, if both conditions are filled, the former takes + priority, and objects in ``objs`` will be acquired. + + Unlike ``NTSYNC_IOC_WAIT_ANY``, it is not valid to pass the same + object more than once, nor is it valid to pass the same object in + ``objs`` and in ``alert``. If this is attempted, the function fails + with ``EINVAL``. diff --git a/Documentation/userspace-api/sysfs-platform_profile.rst b/Documentation/userspace-api/sysfs-platform_profile.rst index 4fccde2e4563..7f013356118a 100644 --- a/Documentation/userspace-api/sysfs-platform_profile.rst +++ b/Documentation/userspace-api/sysfs-platform_profile.rst @@ -40,3 +40,41 @@ added. Drivers which wish to introduce new profile names must: 1. Explain why the existing profile names cannot be used. 2. Add the new profile name, along with a clear description of the expected behaviour, to the sysfs-platform_profile ABI documentation. + +"Custom" profile support +======================== +The platform_profile class also supports profiles advertising a "custom" +profile. This is intended to be set by drivers when the setttings in the +driver have been modified in a way that a standard profile doesn't represent +the current state. + +Multiple driver support +======================= +When multiple drivers on a system advertise a platform profile handler, the +platform profile handler core will only advertise the profiles that are +common between all drivers to the ``/sys/firmware/acpi`` interfaces. + +This is to ensure there is no ambiguity on what the profile names mean when +all handlers don't support a profile. + +Individual drivers will register a 'platform_profile' class device that has +similar semantics as the ``/sys/firmware/acpi/platform_profile`` interface. + +To discover which driver is associated with a platform profile handler the +user can read the ``name`` attribute of the class device. + +To discover available profiles from the class interface the user can read the +``choices`` attribute. + +If a user wants to select a profile for a specific driver, they can do so +by writing to the ``profile`` attribute of the driver's class device. + +This will allow users to set different profiles for different drivers on the +same system. If the selected profile by individual drivers differs the +platform profile handler core will display the profile 'custom' to indicate +that the profiles are not the same. + +While the ``platform_profile`` attribute has the value ``custom``, writing a +common profile from ``platform_profile_choices`` to the platform_profile +attribute of the platform profile handler core will set the profile for all +drivers. diff --git a/Documentation/virt/hyperv/hibernation.rst b/Documentation/virt/hyperv/hibernation.rst new file mode 100644 index 000000000000..4ff27f4a317a --- /dev/null +++ b/Documentation/virt/hyperv/hibernation.rst @@ -0,0 +1,336 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Hibernating Guest VMs +===================== + +Background +---------- +Linux supports the ability to hibernate itself in order to save power. +Hibernation is sometimes called suspend-to-disk, as it writes a memory +image to disk and puts the hardware into the lowest possible power +state. Upon resume from hibernation, the hardware is restarted and the +memory image is restored from disk so that it can resume execution +where it left off. See the "Hibernation" section of +Documentation/admin-guide/pm/sleep-states.rst. + +Hibernation is usually done on devices with a single user, such as a +personal laptop. For example, the laptop goes into hibernation when +the cover is closed, and resumes when the cover is opened again. +Hibernation and resume happen on the same hardware, and Linux kernel +code orchestrating the hibernation steps assumes that the hardware +configuration is not changed while in the hibernated state. + +Hibernation can be initiated within Linux by writing "disk" to +/sys/power/state or by invoking the reboot system call with the +appropriate arguments. This functionality may be wrapped by user space +commands such "systemctl hibernate" that are run directly from a +command line or in response to events such as the laptop lid closing. + +Considerations for Guest VM Hibernation +--------------------------------------- +Linux guests on Hyper-V can also be hibernated, in which case the +hardware is the virtual hardware provided by Hyper-V to the guest VM. +Only the targeted guest VM is hibernated, while other guest VMs and +the underlying Hyper-V host continue to run normally. While the +underlying Windows Hyper-V and physical hardware on which it is +running might also be hibernated using hibernation functionality in +the Windows host, host hibernation and its impact on guest VMs is not +in scope for this documentation. + +Resuming a hibernated guest VM can be more challenging than with +physical hardware because VMs make it very easy to change the hardware +configuration between the hibernation and resume. Even when the resume +is done on the same VM that hibernated, the memory size might be +changed, or virtual NICs or SCSI controllers might be added or +removed. Virtual PCI devices assigned to the VM might be added or +removed. Most such changes cause the resume steps to fail, though +adding a new virtual NIC, SCSI controller, or vPCI device should work. + +Additional complexity can ensue because the disks of the hibernated VM +can be moved to another newly created VM that otherwise has the same +virtual hardware configuration. While it is desirable for resume from +hibernation to succeed after such a move, there are challenges. See +details on this scenario and its limitations in the "Resuming on a +Different VM" section below. + +Hyper-V also provides ways to move a VM from one Hyper-V host to +another. Hyper-V tries to ensure processor model and Hyper-V version +compatibility using VM Configuration Versions, and prevents moves to +a host that isn't compatible. Linux adapts to host and processor +differences by detecting them at boot time, but such detection is not +done when resuming execution in the hibernation image. If a VM is +hibernated on one host, then resumed on a host with a different processor +model or Hyper-V version, settings recorded in the hibernation image +may not match the new host. Because Linux does not detect such +mismatches when resuming the hibernation image, undefined behavior +and failures could result. + + +Enabling Guest VM Hibernation +----------------------------- +Hibernation of a Hyper-V guest VM is disabled by default because +hibernation is incompatible with memory hot-add, as provided by the +Hyper-V balloon driver. If hot-add is used and the VM hibernates, it +hibernates with more memory than it started with. But when the VM +resumes from hibernation, Hyper-V gives the VM only the originally +assigned memory, and the memory size mismatch causes resume to fail. + +To enable a Hyper-V VM for hibernation, the Hyper-V administrator must +enable the ACPI virtual S4 sleep state in the ACPI configuration that +Hyper-V provides to the guest VM. Such enablement is accomplished by +modifying a WMI property of the VM, the steps for which are outside +the scope of this documentation but are available on the web. +Enablement is treated as the indicator that the administrator +prioritizes Linux hibernation in the VM over hot-add, so the Hyper-V +balloon driver in Linux disables hot-add. Enablement is indicated if +the contents of /sys/power/disk contains "platform" as an option. The +enablement is also visible in /sys/bus/vmbus/hibernation. See function +hv_is_hibernation_supported(). + +Linux supports ACPI sleep states on x86, but not on arm64. So Linux +guest VM hibernation is not available on Hyper-V for arm64. + +Initiating Guest VM Hibernation +------------------------------- +Guest VMs can self-initiate hibernation using the standard Linux +methods of writing "disk" to /sys/power/state or the reboot system +call. As an additional layer, Linux guests on Hyper-V support the +"Shutdown" integration service, via which a Hyper-V administrator can +tell a Linux VM to hibernate using a command outside the VM. The +command generates a request to the Hyper-V shutdown driver in Linux, +which sends the uevent "EVENT=hibernate". See kernel functions +shutdown_onchannelcallback() and send_hibernate_uevent(). A udev rule +must be provided in the VM that handles this event and initiates +hibernation. + +Handling VMBus Devices During Hibernation & Resume +-------------------------------------------------- +The VMBus bus driver, and the individual VMBus device drivers, +implement suspend and resume functions that are called as part of the +Linux orchestration of hibernation and of resuming from hibernation. +The overall approach is to leave in place the data structures for the +primary VMBus channels and their associated Linux devices, such as +SCSI controllers and others, so that they are captured in the +hibernation image. This approach allows any state associated with the +device to be persisted across the hibernation/resume. When the VM +resumes, the devices are re-offered by Hyper-V and are connected to +the data structures that already exist in the resumed hibernation +image. + +VMBus devices are identified by class and instance GUID. (See section +"VMBus device creation/deletion" in +Documentation/virt/hyperv/vmbus.rst.) Upon resume from hibernation, +the resume functions expect that the devices offered by Hyper-V have +the same class/instance GUIDs as the devices present at the time of +hibernation. Having the same class/instance GUIDs allows the offered +devices to be matched to the primary VMBus channel data structures in +the memory of the now resumed hibernation image. If any devices are +offered that don't match primary VMBus channel data structures that +already exist, they are processed normally as newly added devices. If +primary VMBus channels that exist in the resumed hibernation image are +not matched with a device offered in the resumed VM, the resume +sequence waits for 10 seconds, then proceeds. But the unmatched device +is likely to cause errors in the resumed VM. + +When resuming existing primary VMBus channels, the newly offered +relids might be different because relids can change on each VM boot, +even if the VM configuration hasn't changed. The VMBus bus driver +resume function matches the class/instance GUIDs, and updates the +relids in case they have changed. + +VMBus sub-channels are not persisted in the hibernation image. Each +VMBus device driver's suspend function must close any sub-channels +prior to hibernation. Closing a sub-channel causes Hyper-V to send a +RESCIND_CHANNELOFFER message, which Linux processes by freeing the +channel data structures so that all vestiges of the sub-channel are +removed. By contrast, primary channels are marked closed and their +ring buffers are freed, but Hyper-V does not send a rescind message, +so the channel data structure continues to exist. Upon resume, the +device driver's resume function re-allocates the ring buffer and +re-opens the existing channel. It then communicates with Hyper-V to +re-open sub-channels from scratch. + +The Linux ends of Hyper-V sockets are forced closed at the time of +hibernation. The guest can't force closing the host end of the socket, +but any host-side actions on the host end will produce an error. + +VMBus devices use the same suspend function for the "freeze" and the +"poweroff" phases, and the same resume function for the "thaw" and +"restore" phases. See the "Entering Hibernation" section of +Documentation/driver-api/pm/devices.rst for the sequencing of the +phases. + +Detailed Hibernation Sequence +----------------------------- +1. The Linux power management (PM) subsystem prepares for + hibernation by freezing user space processes and allocating + memory to hold the hibernation image. +2. As part of the "freeze" phase, Linux PM calls the "suspend" + function for each VMBus device in turn. As described above, this + function removes sub-channels, and leaves the primary channel in + a closed state. +3. Linux PM calls the "suspend" function for the VMBus bus, which + closes any Hyper-V socket channels and unloads the top-level + VMBus connection with the Hyper-V host. +4. Linux PM disables non-boot CPUs, creates the hibernation image in + the previously allocated memory, then re-enables non-boot CPUs. + The hibernation image contains the memory data structures for the + closed primary channels, but no sub-channels. +5. As part of the "thaw" phase, Linux PM calls the "resume" function + for the VMBus bus, which re-establishes the top-level VMBus + connection and requests that Hyper-V re-offer the VMBus devices. + As offers are received for the primary channels, the relids are + updated as previously described. +6. Linux PM calls the "resume" function for each VMBus device. Each + device re-opens its primary channel, and communicates with Hyper-V + to re-establish sub-channels if appropriate. The sub-channels + are re-created as new channels since they were previously removed + entirely in Step 2. +7. With VMBus devices now working again, Linux PM writes the + hibernation image from memory to disk. +8. Linux PM repeats Steps 2 and 3 above as part of the "poweroff" + phase. VMBus channels are closed and the top-level VMBus + connection is unloaded. +9. Linux PM disables non-boot CPUs, and then enters ACPI sleep state + S4. Hibernation is now complete. + +Detailed Resume Sequence +------------------------ +1. The guest VM boots into a fresh Linux OS instance. During boot, + the top-level VMBus connection is established, and synthetic + devices are enabled. This happens via the normal paths that don't + involve hibernation. +2. Linux PM hibernation code reads swap space is to find and read + the hibernation image into memory. If there is no hibernation + image, then this boot becomes a normal boot. +3. If this is a resume from hibernation, the "freeze" phase is used + to shutdown VMBus devices and unload the top-level VMBus + connection in the running fresh OS instance, just like Steps 2 + and 3 in the hibernation sequence. +4. Linux PM disables non-boot CPUs, and transfers control to the + read-in hibernation image. In the now-running hibernation image, + non-boot CPUs are restarted. +5. As part of the "resume" phase, Linux PM repeats Steps 5 and 6 + from the hibernation sequence. The top-level VMBus connection is + re-established, and offers are received and matched to primary + channels in the image. Relids are updated. VMBus device resume + functions re-open primary channels and re-create sub-channels. +6. Linux PM exits the hibernation resume sequence and the VM is now + running normally from the hibernation image. + +Key-Value Pair (KVP) Pseudo-Device Anomalies +-------------------------------------------- +The VMBus KVP device behaves differently from other pseudo-devices +offered by Hyper-V. When the KVP primary channel is closed, Hyper-V +sends a rescind message, which causes all vestiges of the device to be +removed. But Hyper-V then re-offers the device, causing it to be newly +re-created. The removal and re-creation occurs during the "freeze" +phase of hibernation, so the hibernation image contains the re-created +KVP device. Similar behavior occurs during the "freeze" phase of the +resume sequence while still in the fresh OS instance. But in both +cases, the top-level VMBus connection is subsequently unloaded, which +causes the device to be discarded on the Hyper-V side. So no harm is +done and everything still works. + +Virtual PCI devices +------------------- +Virtual PCI devices are physical PCI devices that are mapped directly +into the VM's physical address space so the VM can interact directly +with the hardware. vPCI devices include those accessed via what Hyper-V +calls "Discrete Device Assignment" (DDA), as well as SR-IOV NIC +Virtual Functions (VF) devices. See Documentation/virt/hyperv/vpci.rst. + +Hyper-V DDA devices are offered to guest VMs after the top-level VMBus +connection is established, just like VMBus synthetic devices. They are +statically assigned to the VM, and their instance GUIDs don't change +unless the Hyper-V administrator makes changes to the configuration. +DDA devices are represented in Linux as virtual PCI devices that have +a VMBus identity as well as a PCI identity. Consequently, Linux guest +hibernation first handles DDA devices as VMBus devices in order to +manage the VMBus channel. But then they are also handled as PCI +devices using the hibernation functions implemented by their native +PCI driver. + +SR-IOV NIC VFs also have a VMBus identity as well as a PCI +identity, and overall are processed similarly to DDA devices. A +difference is that VFs are not offered to the VM during initial boot +of the VM. Instead, the VMBus synthetic NIC driver first starts +operating and communicates to Hyper-V that it is prepared to accept a +VF, and then the VF offer is made. However, the VMBus connection +might later be unloaded and then re-established without the VM being +rebooted, as happens in Steps 3 and 5 in the Detailed Hibernation +Sequence above and in the Detailed Resume Sequence. In such a case, +the VFs likely became part of the VM during initial boot, so when the +VMBus connection is re-established, the VFs are offered on the +re-established connection without intervention by the synthetic NIC driver. + +UIO Devices +----------- +A VMBus device can be exposed to user space using the Hyper-V UIO +driver (uio_hv_generic.c) so that a user space driver can control and +operate the device. However, the VMBus UIO driver does not support the +suspend and resume operations needed for hibernation. If a VMBus +device is configured to use the UIO driver, hibernating the VM fails +and Linux continues to run normally. The most common use of the Hyper-V +UIO driver is for DPDK networking, but there are other uses as well. + +Resuming on a Different VM +-------------------------- +This scenario occurs in the Azure public cloud in that a hibernated +customer VM only exists as saved configuration and disks -- the VM no +longer exists on any Hyper-V host. When the customer VM is resumed, a +new Hyper-V VM with identical configuration is created, likely on a +different Hyper-V host. That new Hyper-V VM becomes the resumed +customer VM, and the steps the Linux kernel takes to resume from the +hibernation image must work in that new VM. + +While the disks and their contents are preserved from the original VM, +the Hyper-V-provided VMBus instance GUIDs of the disk controllers and +other synthetic devices would typically be different. The difference +would cause the resume from hibernation to fail, so several things are +done to solve this problem: + +* For VMBus synthetic devices that support only a single instance, + Hyper-V always assigns the same instance GUIDs. For example, the + Hyper-V mouse, the shutdown pseudo-device, the time sync pseudo + device, etc., always have the same instance GUID, both for local + Hyper-V installs as well as in the Azure cloud. + +* VMBus synthetic SCSI controllers may have multiple instances in a + VM, and in the general case instance GUIDs vary from VM to VM. + However, Azure VMs always have exactly two synthetic SCSI + controllers, and Azure code overrides the normal Hyper-V behavior + so these controllers are always assigned the same two instance + GUIDs. Consequently, when a customer VM is resumed on a newly + created VM, the instance GUIDs match. But this guarantee does not + hold for local Hyper-V installs. + +* Similarly, VMBus synthetic NICs may have multiple instances in a + VM, and the instance GUIDs vary from VM to VM. Again, Azure code + overrides the normal Hyper-V behavior so that the instance GUID + of a synthetic NIC in a customer VM does not change, even if the + customer VM is deallocated or hibernated, and then re-constituted + on a newly created VM. As with SCSI controllers, this behavior + does not hold for local Hyper-V installs. + +* vPCI devices do not have the same instance GUIDs when resuming + from hibernation on a newly created VM. Consequently, Azure does + not support hibernation for VMs that have DDA devices such as + NVMe controllers or GPUs. For SR-IOV NIC VFs, Azure removes the + VF from the VM before it hibernates so that the hibernation image + does not contain a VF device. When the VM is resumed it + instantiates a new VF, rather than trying to match against a VF + that is present in the hibernation image. Because Azure must + remove any VFs before initiating hibernation, Azure VM + hibernation must be initiated externally from the Azure Portal or + Azure CLI, which in turn uses the Shutdown integration service to + tell Linux to do the hibernation. If hibernation is self-initiated + within the Azure VM, VFs remain in the hibernation image, and are + not resumed properly. + +In summary, Azure takes special actions to remove VFs and to ensure +that VMBus device instance GUIDs match on a new/different VM, allowing +hibernation to work for most general-purpose Azure VMs sizes. While +similar special actions could be taken when resuming on a different VM +on a local Hyper-V install, orchestrating such actions is not provided +out-of-the-box by local Hyper-V and so requires custom scripting. diff --git a/Documentation/virt/hyperv/index.rst b/Documentation/virt/hyperv/index.rst index 79bc4080329e..c84c40fd61c9 100644 --- a/Documentation/virt/hyperv/index.rst +++ b/Documentation/virt/hyperv/index.rst @@ -11,4 +11,5 @@ Hyper-V Enlightenments vmbus clocks vpci + hibernation coco diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 454c2aaa155e..0d1c3a820ce6 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1825,15 +1825,18 @@ emulate them efficiently. The fields in each entry are defined as follows: the values returned by the cpuid instruction for this function/index combination -The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned -as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC -support. Instead it is reported via:: +x2APIC (CPUID leaf 1, ecx[21) and TSC deadline timer (CPUID leaf 1, ecx[24]) +may be returned as true, but they depend on KVM_CREATE_IRQCHIP for in-kernel +emulation of the local APIC. TSC deadline timer support is also reported via:: ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER) if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the feature in userspace, then you can enable the feature for KVM_SET_CPUID2. +Enabling x2APIC in KVM_SET_CPUID2 requires KVM_CREATE_IRQCHIP as KVM doesn't +support forwarding x2APIC MSR accesses to userspace, i.e. KVM does not support +emulating x2APIC in userspace. 4.47 KVM_PPC_GET_PVINFO ----------------------- @@ -1914,6 +1917,9 @@ No flags are specified so far, the corresponding field must be set to zero. #define KVM_IRQ_ROUTING_HV_SINT 4 #define KVM_IRQ_ROUTING_XEN_EVTCHN 5 +On s390, adding a KVM_IRQ_ROUTING_S390_ADAPTER is rejected on ucontrol VMs with +error -EINVAL. + flags: - KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry @@ -5574,7 +5580,7 @@ KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA in guest physical address space. This attribute should be used in preference to KVM_XEN_ATTR_TYPE_SHARED_INFO as it avoids unnecessary invalidation of an internal cache when the page is - re-mapped in guest physcial address space. + re-mapped in guest physical address space. Setting the hva to zero will disable the shared_info page. @@ -7670,6 +7676,7 @@ branch to guests' 0x200 interrupt vector. :Architectures: x86 :Parameters: args[0] defines which exits are disabled :Returns: 0 on success, -EINVAL when args[0] contains invalid exits + or if any vCPUs have already been created Valid bits in args[0] are:: diff --git a/Documentation/virt/kvm/devices/s390_flic.rst b/Documentation/virt/kvm/devices/s390_flic.rst index ea96559ba501..b784f8016748 100644 --- a/Documentation/virt/kvm/devices/s390_flic.rst +++ b/Documentation/virt/kvm/devices/s390_flic.rst @@ -58,11 +58,15 @@ Groups: Enables async page faults for the guest. So in case of a major page fault the host is allowed to handle this async and continues the guest. + -EINVAL is returned when called on the FLIC of a ucontrol VM. + KVM_DEV_FLIC_APF_DISABLE_WAIT Disables async page faults for the guest and waits until already pending async page faults are done. This is necessary to trigger a completion interrupt for every init interrupt before migrating the interrupt list. + -EINVAL is returned when called on the FLIC of a ucontrol VM. + KVM_DEV_FLIC_ADAPTER_REGISTER Register an I/O adapter interrupt source. Takes a kvm_s390_io_adapter describing the adapter to register:: diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst index 31f14ec4a65b..31a9576c07af 100644 --- a/Documentation/virt/kvm/devices/vcpu.rst +++ b/Documentation/virt/kvm/devices/vcpu.rst @@ -142,8 +142,8 @@ the cpu field to the processor id. :Architectures: ARM64 -2.1. ATTRIBUTES: KVM_ARM_VCPU_TIMER_IRQ_VTIMER, KVM_ARM_VCPU_TIMER_IRQ_PTIMER ------------------------------------------------------------------------------ +2.1. ATTRIBUTES: KVM_ARM_VCPU_TIMER_IRQ_{VTIMER,PTIMER,HVTIMER,HPTIMER} +----------------------------------------------------------------------- :Parameters: in kvm_device_attr.addr the address for the timer interrupt is a pointer to an int @@ -159,10 +159,12 @@ A value describing the architected timer interrupt number when connected to an in-kernel virtual GIC. These must be a PPI (16 <= intid < 32). Setting the attribute overrides the default values (see below). -============================= ========================================== -KVM_ARM_VCPU_TIMER_IRQ_VTIMER The EL1 virtual timer intid (default: 27) -KVM_ARM_VCPU_TIMER_IRQ_PTIMER The EL1 physical timer intid (default: 30) -============================= ========================================== +============================== ========================================== +KVM_ARM_VCPU_TIMER_IRQ_VTIMER The EL1 virtual timer intid (default: 27) +KVM_ARM_VCPU_TIMER_IRQ_PTIMER The EL1 physical timer intid (default: 30) +KVM_ARM_VCPU_TIMER_IRQ_HVTIMER The EL2 virtual timer intid (default: 28) +KVM_ARM_VCPU_TIMER_IRQ_HPTIMER The EL2 physical timer intid (default: 26) +============================== ========================================== Setting the same PPI for different timers will prevent the VCPUs from running. Setting the interrupt number on a VCPU configures all VCPUs created at that diff --git a/Documentation/wmi/driver-development-guide.rst b/Documentation/wmi/driver-development-guide.rst index 676873c98680..f7e1089a0559 100644 --- a/Documentation/wmi/driver-development-guide.rst +++ b/Documentation/wmi/driver-development-guide.rst @@ -41,6 +41,10 @@ helps in understanding how the WMI device is supposed to work. The path of the A method associated with a given WMI device can be retrieved using the ``lswmi`` utility as mentioned above. +If you are attempting to port a driver to Linux and are working on a Windows +system, `WMIExplorer `_ can be useful +for inspecting available WMI methods and invoking them directly. + Basic WMI driver structure -------------------------- diff --git a/MAINTAINERS b/MAINTAINERS index 25c683a92162..d9e1f4b45062 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -185,6 +185,14 @@ W: http://www.adaptec.com/ F: Documentation/scsi/aacraid.rst F: drivers/scsi/aacraid/ +AAEON UPBOARD FPGA MFD DRIVER +M: Thomas Richard +S: Maintained +F: drivers/leds/leds-upboard.c +F: drivers/mfd/upboard-fpga.c +F: drivers/pinctrl/pinctrl-upboard.c +F: include/linux/mfd/upboard-fpga.h + AB8500 BATTERY AND CHARGER DRIVERS M: Linus Walleij F: Documentation/devicetree/bindings/power/supply/*ab8500* @@ -816,7 +824,7 @@ F: drivers/media/platform/sunxi/sun4i-csi/ ALLWINNER A31 CSI DRIVER M: Yong Deng -M: Paul Kocialkowski +M: Paul Kocialkowski L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media.git @@ -824,7 +832,7 @@ F: Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml F: drivers/media/platform/sunxi/sun6i-csi/ ALLWINNER A31 ISP DRIVER -M: Paul Kocialkowski +M: Paul Kocialkowski L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media.git @@ -833,7 +841,7 @@ F: drivers/staging/media/sunxi/sun6i-isp/ F: drivers/staging/media/sunxi/sun6i-isp/uapi/sun6i-isp-config.h ALLWINNER A31 MIPI CSI-2 BRIDGE DRIVER -M: Paul Kocialkowski +M: Paul Kocialkowski L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media.git @@ -876,7 +884,7 @@ F: drivers/thermal/sun8i_thermal.c ALLWINNER VPU DRIVER M: Maxime Ripard -M: Paul Kocialkowski +M: Paul Kocialkowski L: linux-media@vger.kernel.org S: Maintained F: drivers/staging/media/sunxi/cedrus/ @@ -949,10 +957,9 @@ AMAZON ETHERNET DRIVERS M: Shay Agroskin M: Arthur Kiyanovski R: David Arinzon -R: Noam Dagan R: Saeed Bishara L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/amazon/ena.rst F: drivers/net/ethernet/amazon/ @@ -980,6 +987,12 @@ L: linux-edac@vger.kernel.org S: Supported F: drivers/ras/amd/atl/* +AMD AE4DMA DRIVER +M: Basavaraj Natikar +L: dmaengine@vger.kernel.org +S: Supported +F: drivers/dma/amd/ae4dma/ + AMD AXI W1 DRIVER M: Kris Chaplin R: Thomas Delev @@ -1077,7 +1090,7 @@ F: drivers/video/fbdev/geode/ AMD HSMP DRIVER M: Naveen Krishna Chatradhi -R: Carlos Bilbao +R: Carlos Bilbao L: platform-driver-x86@vger.kernel.org S: Maintained F: Documentation/arch/x86/amd_hsmp.rst @@ -1121,11 +1134,19 @@ L: linux-i2c@vger.kernel.org S: Supported F: drivers/i2c/busses/i2c-amd-asf-plat.c +AMD NODE DRIVER +M: Mario Limonciello +M: Yazen Ghannam +L: linux-kernel@vger.kernel.org +S: Supported +F: arch/x86/include/asm/amd_node.h +F: arch/x86/kernel/amd_node.c + AMD PDS CORE DRIVER M: Shannon Nelson M: Brett Creeley L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/amd/pds_core.rst F: drivers/net/ethernet/amd/pds_core/ F: include/linux/pds/ @@ -1133,7 +1154,7 @@ F: include/linux/pds/ AMD PMC DRIVER M: Shyam Sundar S K L: platform-driver-x86@vger.kernel.org -S: Maintained +S: Supported F: drivers/platform/x86/amd/pmc/ AMD PMF DRIVER @@ -1164,8 +1185,8 @@ F: tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py AMD PTDMA DRIVER M: Basavaraj Natikar L: dmaengine@vger.kernel.org -S: Maintained -F: drivers/dma/ptdma/ +S: Supported +F: drivers/dma/amd/ptdma/ AMD QDMA DRIVER M: Nishad Saraf @@ -1208,7 +1229,7 @@ F: include/uapi/drm/amdxdna_accel.h AMD XGBE DRIVER M: "Shyam Sundar S K" L: netdev@vger.kernel.org -S: Supported +S: Maintained F: arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi F: drivers/net/ethernet/amd/xgbe/ @@ -1237,7 +1258,7 @@ S: Maintained F: Documentation/devicetree/bindings/rtc/amlogic,a4-rtc.yaml F: drivers/rtc/rtc-amlogic-a4.c -AMPHENOL CHIPCAP 2 HUMIDITY-TEMPERATURE IIO DRIVER +AMPHENOL CHIPCAP 2 DRIVER M: Javier Carrasco L: linux-hwmon@vger.kernel.org S: Maintained @@ -1303,7 +1324,7 @@ W: https://ez.analog.com/linux-software-drivers F: Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml F: Documentation/iio/ad4695.rst F: drivers/iio/adc/ad4695.c -F: include/dt-bindings/iio/adi,ad4695.h +F: include/dt-bindings/iio/adc/adi,ad4695.h ANALOG DEVICES INC AD7091R DRIVER M: Marcelo Schmitt @@ -1714,14 +1735,14 @@ F: drivers/edac/xgene_edac.c APPLIED MICRO (APM) X-GENE SOC ETHERNET (V2) DRIVER M: Iyappan Subramanian M: Keyur Chudgar -S: Supported +S: Maintained F: drivers/net/ethernet/apm/xgene-v2/ APPLIED MICRO (APM) X-GENE SOC ETHERNET DRIVER M: Iyappan Subramanian M: Keyur Chudgar M: Quan Nguyen -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/apm-xgene-enet.txt F: Documentation/devicetree/bindings/net/apm-xgene-mdio.txt F: drivers/net/ethernet/apm/xgene/ @@ -1759,7 +1780,7 @@ F: drivers/hwmon/aquacomputer_d5next.c AQUANTIA ETHERNET DRIVER (atlantic) M: Igor Russkikh L: netdev@vger.kernel.org -S: Supported +S: Maintained W: https://www.marvell.com/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst @@ -1768,7 +1789,7 @@ F: drivers/net/ethernet/aquantia/atlantic/ AQUANTIA ETHERNET DRIVER PTP SUBSYSTEM M: Egor Pomozov L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.aquantia.com F: drivers/net/ethernet/aquantia/atlantic/aq_ptp* @@ -1808,7 +1829,6 @@ F: include/uapi/linux/if_arcnet.h ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS) M: Arnd Bergmann -M: Olof Johansson L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: soc@lists.linux.dev S: Maintained @@ -1931,6 +1951,7 @@ ARM PMU PROFILING AND DEBUGGING M: Will Deacon M: Mark Rutland L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: linux-perf-users@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/arm/pmu.yaml F: Documentation/devicetree/bindings/perf/ @@ -2294,6 +2315,15 @@ F: arch/arm64/boot/dts/bitmain/ F: drivers/clk/clk-bm1880.c F: drivers/pinctrl/pinctrl-bm1880.c +ARM/BLAIZE ARCHITECTURE +M: James Cowgill +M: Matt Redfearn +M: Neil Jones +M: Nikolaos Pasaloukos +S: Maintained +F: Documentation/devicetree/bindings/arm/blaize.yaml +F: arch/arm64/boot/dts/blaize/ + ARM/CALXEDA HIGHBANK ARCHITECTURE M: Andre Przywara L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -2304,7 +2334,7 @@ F: arch/arm/mach-highbank/ ARM/CAVIUM THUNDER NETWORK DRIVER M: Sunil Goutham L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Supported +S: Maintained F: drivers/net/ethernet/cavium/thunder/ ARM/CIRRUS LOGIC BK3 MACHINE SUPPORT @@ -2702,7 +2732,6 @@ N: at91 N: atmel ARM/Microchip Sparx5 SoC support -M: Lars Povlsen M: Steen Hegelund M: Daniel Machon M: UNGLinuxDriver@microchip.com @@ -2841,12 +2870,19 @@ ARM/NXP S32G ARCHITECTURE R: Chester Lin R: Matthias Brugger R: Ghennadi Procopciuc -L: NXP S32 Linux Team +R: NXP S32 Linux Team L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm64/boot/dts/freescale/s32g*.dts* F: drivers/pinctrl/nxp/ +ARM/NXP S32G/S32R DWMAC ETHERNET DRIVER +M: Jan Petrous +L: NXP S32 Linux Team +S: Maintained +F: Documentation/devicetree/bindings/net/nxp,s32-dwmac.yaml +F: drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c + ARM/Orion SoC/Technologic Systems TS-78xx platform support M: Alexander Clouter L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -3034,6 +3070,7 @@ F: drivers/*/*s3c24* F: drivers/*/*s3c64xx* F: drivers/*/*s5pv210* F: drivers/clocksource/samsung_pwm_timer.c +F: drivers/mailbox/exynos-mailbox.c F: drivers/memory/samsung/ F: drivers/pwm/pwm-samsung.c F: drivers/soc/samsung/ @@ -3619,6 +3656,7 @@ F: drivers/phy/qualcomm/phy-ath79-usb.c ATHEROS ATH GENERIC UTILITIES M: Kalle Valo +M: Jeff Johnson L: linux-wireless@vger.kernel.org S: Supported F: drivers/net/wireless/ath/* @@ -3672,7 +3710,7 @@ F: include/uapi/linux/sonet.h ATMEL MACB ETHERNET DRIVER M: Nicolas Ferre M: Claudiu Beznea -S: Supported +S: Maintained F: drivers/net/ethernet/cadence/ ATMEL MAXTOUCH DRIVER @@ -3880,9 +3918,9 @@ S: Maintained F: drivers/platform/x86/barco-p50-gpio.c BATMAN ADVANCED -M: Marek Lindner +M: Marek Lindner M: Simon Wunderlich -M: Antonio Quartulli +M: Antonio Quartulli M: Sven Eckelmann L: b.a.t.m.a.n@lists.open-mesh.org (moderated for non-subscribers) S: Maintained @@ -4064,12 +4102,12 @@ S: Supported W: http://www.bluez.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next.git +F: Documentation/ABI/stable/sysfs-class-bluetooth F: include/net/bluetooth/ F: net/bluetooth/ BONDING DRIVER M: Jay Vosburgh -M: Andy Gospodarek L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/bonding.rst @@ -4142,7 +4180,6 @@ S: Odd Fixes F: drivers/net/ethernet/netronome/nfp/bpf/ BPF JIT for POWERPC (32-BIT AND 64-BIT) -M: Michael Ellerman M: Hari Bathini M: Christophe Leroy R: Naveen N Rao @@ -4402,7 +4439,7 @@ F: drivers/net/ethernet/broadcom/asp2/ BROADCOM B44 10/100 ETHERNET DRIVER M: Michael Chan L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/broadcom/b44.* BROADCOM B53/SF2 ETHERNET SWITCH DRIVER @@ -4586,7 +4623,7 @@ BROADCOM BNX2 GIGABIT ETHERNET DRIVER M: Rasesh Mody M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/broadcom/bnx2.* F: drivers/net/ethernet/broadcom/bnx2_* @@ -4610,13 +4647,14 @@ BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER M: Sudarsana Kalluru M: Manish Chopra L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/broadcom/bnx2x/ BROADCOM BNXT_EN 50 GIGABIT ETHERNET DRIVER M: Michael Chan +M: Pavan Chebbi L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/firmware/broadcom/tee_bnxt_fw.c F: drivers/net/ethernet/broadcom/bnxt/ F: include/linux/firmware/broadcom/tee_bnxt_fw.h @@ -4712,7 +4750,7 @@ M: Doug Berger M: Florian Fainelli R: Broadcom internal kernel review list L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/brcm,bcmgenet.yaml F: Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml F: drivers/net/ethernet/broadcom/genet/ @@ -4779,6 +4817,7 @@ F: drivers/scsi/mpi3mr/ BROADCOM NETXTREME-E ROCE DRIVER M: Selvin Xavier +M: Kalesh AP L: linux-rdma@vger.kernel.org S: Supported W: http://www.broadcom.com @@ -4864,7 +4903,7 @@ BROADCOM SYSTEMPORT ETHERNET DRIVER M: Florian Fainelli R: Broadcom internal kernel review list L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/brcm,systemport.yaml F: drivers/net/ethernet/broadcom/bcmsysport.* F: drivers/net/ethernet/broadcom/unimac.h @@ -4873,7 +4912,7 @@ BROADCOM TG3 GIGABIT ETHERNET DRIVER M: Pavan Chebbi M: Michael Chan L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/broadcom/tg3.* BROADCOM VK DRIVER @@ -4895,7 +4934,7 @@ M: Rasesh Mody M: Sudarsana Kalluru M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/brocade/bna/ BSG (block layer generic sg v4 driver) @@ -5022,7 +5061,7 @@ F: drivers/media/platform/cadence/cdns-csi2* CADENCE NAND DRIVER L: linux-mtd@lists.infradead.org S: Orphan -F: Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt +F: Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml F: drivers/mtd/nand/raw/cadence-nand-controller.c CADENCE USB3 DRD IP DRIVER @@ -5121,6 +5160,7 @@ F: include/uapi/linux/can/gw.h F: include/uapi/linux/can/isotp.h F: include/uapi/linux/can/raw.h F: net/can/ +F: net/sched/em_canid.c CAN-J1939 NETWORK LAYER M: Robin van der Gracht @@ -5160,6 +5200,7 @@ M: Serge Hallyn L: linux-security-module@vger.kernel.org S: Supported F: include/linux/capability.h +F: include/trace/events/capability.h F: include/uapi/linux/capability.h F: kernel/capability.c F: security/commoncap.c @@ -5332,6 +5373,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git F: drivers/char/ F: drivers/misc/ F: include/linux/miscdevice.h +F: samples/rust/rust_misc_device.rs X: drivers/char/agp/ X: drivers/char/hw_random/ X: drivers/char/ipmi/ @@ -5447,9 +5489,12 @@ F: include/linux/platform_data/cros_usbpd_notify.h CHROMEOS EC USB TYPE-C DRIVER M: Prashant Malani +M: Benson Leung +M: Abhishek Pandit-Subedi L: chrome-platform@lists.linux.dev S: Maintained F: drivers/platform/chrome/cros_ec_typec.* +F: drivers/platform/chrome/cros_typec_altmode.* F: drivers/platform/chrome/cros_typec_switch.c F: drivers/platform/chrome/cros_typec_vdm.* @@ -5465,6 +5510,13 @@ L: chrome-platform@lists.linux.dev S: Maintained F: drivers/watchdog/cros_ec_wdt.c +CHROMEOS UCSI DRIVER +M: Abhishek Pandit-Subedi +M: Łukasz Bartosik +L: chrome-platform@lists.linux.dev +S: Maintained +F: drivers/usb/typec/ucsi/cros_ec_ucsi.c + CHRONTEL CH7322 CEC DRIVER M: Joe Tessler L: linux-media@vger.kernel.org @@ -5480,6 +5532,7 @@ L: linux-sound@vger.kernel.org L: patches@opensource.cirrus.com S: Maintained F: Documentation/devicetree/bindings/sound/cirrus,cs* +F: Documentation/sound/codecs/cs* F: drivers/mfd/cs42l43* F: drivers/pinctrl/cirrus/pinctrl-cs42l43* F: drivers/spi/spi-cs42l43* @@ -5512,8 +5565,8 @@ L: patches@opensource.cirrus.com S: Supported W: https://github.com/CirrusLogic/linux-drivers/wiki T: git https://github.com/CirrusLogic/linux-drivers.git -F: drivers/firmware/cirrus/* -F: include/linux/firmware/cirrus/* +F: drivers/firmware/cirrus/ +F: include/linux/firmware/cirrus/ CIRRUS LOGIC EP93XX ETHERNET DRIVER M: Hartley Sweeten @@ -5583,7 +5636,7 @@ F: drivers/scsi/snic/ CISCO VIC ETHERNET NIC DRIVER M: Christian Benvenuti M: Satish Kharat -S: Supported +S: Maintained F: drivers/net/ethernet/cisco/enic/ CISCO VIC LOW LATENCY NIC DRIVER @@ -5804,7 +5857,7 @@ F: drivers/usb/atm/cxacru.c CONFIDENTIAL COMPUTING THREAT MODEL FOR X86 VIRTUALIZATION (SNP/TDX) M: Elena Reshetova -M: Carlos Bilbao +M: Carlos Bilbao S: Maintained F: Documentation/security/snp-tdx-threat-model.rst @@ -6069,12 +6122,30 @@ S: Maintained F: Documentation/filesystems/cramfs.rst F: fs/cramfs/ +CRC LIBRARY +M: Eric Biggers +R: Ard Biesheuvel +L: linux-crypto@vger.kernel.org +S: Maintained +T: git https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git crc-next +F: Documentation/staging/crc* +F: arch/*/lib/crc* +F: include/linux/crc* +F: lib/crc* + CREATIVE SB0540 M: Bastien Nocera L: linux-input@vger.kernel.org S: Maintained F: drivers/hid/hid-creative-sb0540.c +INTEL CRPS COMMON REDUNDANT PSU DRIVER +M: Ninad Palsule +L: linux-hwmon@vger.kernel.org +S: Maintained +F: Documentation/hwmon/crps.rst +F: drivers/hwmon/pmbus/crps.c + CRYPTO API M: Herbert Xu M: "David S. Miller" @@ -6181,7 +6252,7 @@ F: drivers/media/dvb-frontends/cxd2820r* CXGB3 ETHERNET DRIVER (CXGB3) M: Potnuri Bharat Teja L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/cxgb3/ @@ -6202,14 +6273,14 @@ F: drivers/crypto/chelsio CXGB4 ETHERNET DRIVER (CXGB4) M: Potnuri Bharat Teja L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/cxgb4/ CXGB4 INLINE CRYPTO DRIVER M: Ayush Sawal L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/inline_crypto/ @@ -6231,7 +6302,7 @@ F: include/uapi/rdma/cxgb4-abi.h CXGB4VF ETHERNET DRIVER (CXGB4VF) M: Potnuri Bharat Teja L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/cxgb4vf/ @@ -6239,8 +6310,8 @@ CXL (IBM Coherent Accelerator Processor Interface CAPI) DRIVER M: Frederic Barrat M: Andrew Donnellan L: linuxppc-dev@lists.ozlabs.org -S: Supported -F: Documentation/ABI/testing/sysfs-class-cxl +S: Obsolete +F: Documentation/ABI/obsolete/sysfs-class-cxl F: Documentation/arch/powerpc/cxl.rst F: arch/powerpc/platforms/powernv/pci-cxl.c F: drivers/misc/cxl/ @@ -6341,6 +6412,7 @@ F: Documentation/mm/damon/ F: include/linux/damon.h F: include/trace/events/damon.h F: mm/damon/ +F: samples/damon/ F: tools/testing/selftests/damon/ DAVICOM FAST ETHERNET (DMFE) NETWORK DRIVER @@ -6661,19 +6733,14 @@ L: linux-rtc@vger.kernel.org S: Maintained F: drivers/rtc/rtc-sd2405al.c -DH ELECTRONICS IMX6 DHCOM/DHCOR BOARD SUPPORT +DH ELECTRONICS DHSOM SOM AND BOARD SUPPORT M: Christoph Niedermaier -L: kernel@dh-electronics.com -S: Maintained -F: arch/arm/boot/dts/nxp/imx/imx6*-dhcom-* -F: arch/arm/boot/dts/nxp/imx/imx6*-dhcor-* - -DH ELECTRONICS STM32MP1 DHCOM/DHCOR BOARD SUPPORT M: Marek Vasut L: kernel@dh-electronics.com S: Maintained -F: arch/arm/boot/dts/st/stm32mp1*-dhcom-* -F: arch/arm/boot/dts/st/stm32mp1*-dhcor-* +N: dhcom +N: dhcor +N: dhsom DIALOG SEMICONDUCTOR DRIVERS M: Support Opensource @@ -7032,6 +7099,7 @@ F: include/linux/component.h DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS M: Greg Kroah-Hartman R: "Rafael J. Wysocki" +R: Danilo Krummrich S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git F: Documentation/core-api/kobject.rst @@ -7042,8 +7110,14 @@ F: include/linux/debugfs.h F: include/linux/fwnode.h F: include/linux/kobj* F: include/linux/property.h +F: include/linux/sysfs.h F: lib/kobj* F: rust/kernel/device.rs +F: rust/kernel/device_id.rs +F: rust/kernel/devres.rs +F: rust/kernel/driver.rs +F: rust/kernel/platform.rs +F: samples/rust/rust_driver_platform.rs DRIVERS FOR OMAP ADAPTIVE VOLTAGE SCALING (AVS) M: Nishanth Menon @@ -7081,7 +7155,8 @@ T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/sun4i/sun8i* DRM DRIVER FOR ARM PL111 CLCD -S: Orphan +M: Linus Walleij +S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/pl111/ @@ -7247,7 +7322,7 @@ F: Documentation/devicetree/bindings/display/panel/lg,sw43408.yaml F: drivers/gpu/drm/panel/panel-lg-sw43408.c DRM DRIVER FOR LOGICVC DISPLAY CONTROLLER -M: Paul Kocialkowski +M: Paul Kocialkowski S: Supported T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/logicvc/ @@ -7358,7 +7433,7 @@ F: drivers/gpu/drm/panel/panel-novatek-nt36672a.c DRM DRIVER FOR NVIDIA GEFORCE/QUADRO GPUS M: Karol Herbst M: Lyude Paul -M: Danilo Krummrich +M: Danilo Krummrich L: dri-devel@lists.freedesktop.org L: nouveau@lists.freedesktop.org S: Supported @@ -8408,7 +8483,7 @@ M: Ajit Khaparde M: Sriharsha Basavapatna M: Somnath Kotur L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.emulex.com F: drivers/net/ethernet/emulex/benet/ @@ -8465,7 +8540,7 @@ F: include/video/s1d13xxxfb.h EROFS FILE SYSTEM M: Gao Xiang M: Chao Yu -R: Yue Hu +R: Yue Hu R: Jeffle Xu R: Sandeep Dhavale L: linux-erofs@lists.ozlabs.org @@ -8563,8 +8638,8 @@ F: rust/kernel/net/phy.rs F: rust/kernel/net/phy/reg.rs EXEC & BINFMT API, ELF +M: Kees Cook R: Eric Biederman -R: Kees Cook L: linux-mm@kvack.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve @@ -8576,6 +8651,7 @@ F: fs/tests/binfmt_*_kunit.c F: fs/tests/exec_kunit.c F: include/linux/binfmts.h F: include/linux/elf.h +F: include/uapi/linux/auxvec.h F: include/uapi/linux/binfmts.h F: include/uapi/linux/elf.h F: tools/testing/selftests/exec/ @@ -8649,6 +8725,7 @@ L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/extcon.git F: Documentation/devicetree/bindings/extcon/ +F: Documentation/driver-api/extcon.rst F: Documentation/firmware-guide/acpi/extcon-intel-int3496.rst F: drivers/extcon/ F: include/linux/extcon.h @@ -8936,7 +9013,7 @@ F: include/linux/arm_ffa.h FIRMWARE LOADER (request_firmware) M: Luis Chamberlain M: Russ Weight -M: Danilo Krummrich +M: Danilo Krummrich L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/firmware_class/ @@ -8963,14 +9040,16 @@ L: linux-input@vger.kernel.org S: Maintained F: drivers/input/joystick/fsia6b.c -FOCUSRITE SCARLETT2 MIXER DRIVER (Scarlett Gen 2+ and Clarett) +FOCUSRITE CONTROL PROTOCOL/SCARLETT2 MIXER DRIVERS (Scarlett Gen 2+, Clarett, and Vocaster) M: Geoffrey D. Bennett L: linux-sound@vger.kernel.org S: Maintained -W: https://github.com/geoffreybennett/scarlett-gen2 -B: https://github.com/geoffreybennett/scarlett-gen2/issues -T: git https://github.com/geoffreybennett/scarlett-gen2.git +W: https://github.com/geoffreybennett/linux-fcp +B: https://github.com/geoffreybennett/linux-fcp/issues +T: git https://github.com/geoffreybennett/linux-fcp.git +F: include/uapi/sound/fcp.h F: include/uapi/sound/scarlett2.h +F: sound/usb/fcp.c F: sound/usb/mixer_scarlett2.c FORCEDETH GIGABIT ETHERNET DRIVER @@ -9447,7 +9526,7 @@ F: samples/ftrace FUNGIBLE ETHERNET DRIVERS M: Dimitris Michailidis L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/fungible/ FUSE: FILESYSTEM IN USERSPACE @@ -9562,6 +9641,13 @@ W: https://linuxtv.org T: git git://linuxtv.org/media.git F: drivers/media/radio/radio-gemtek* +GENDWARFKSYMS +M: Sami Tolvanen +L: linux-modules@vger.kernel.org +L: linux-kbuild@vger.kernel.org +S: Maintained +F: scripts/gendwarfksyms/ + GENERIC ARCHITECTURE TOPOLOGY M: Sudeep Holla L: linux-kernel@vger.kernel.org @@ -9752,7 +9838,7 @@ M: Jeroen de Borst M: Praveen Kaligineedi R: Shailend Chand L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/google/gve.rst F: drivers/net/ethernet/google @@ -9767,9 +9853,12 @@ F: drivers/firmware/google/ GOOGLE TENSOR SoC SUPPORT M: Peter Griffin +R: André Draszik +R: Tudor Ambarus L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org S: Maintained +C: irc://irc.oftc.net/pixel6-kernel-dev F: Documentation/devicetree/bindings/clock/google,gs101-clock.yaml F: arch/arm64/boot/dts/exynos/google/ F: drivers/clk/samsung/clk-gs101.c @@ -10044,7 +10133,8 @@ F: include/trace/events/handshake.h F: net/handshake/ HANTRO VPU CODEC DRIVER -M: Ezequiel Garcia +M: Nicolas Dufresne +M: Benjamin Gaignard M: Philipp Zabel L: linux-media@vger.kernel.org L: linux-rockchip@lists.infradead.org @@ -10292,7 +10382,6 @@ F: drivers/input/touchscreen/himax_hx83112b.c HIPPI M: Jes Sorensen -L: linux-hippi@sunsite.dk S: Maintained F: drivers/net/hippi/ F: include/linux/hippidevice.h @@ -10685,10 +10774,8 @@ F: Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml F: Documentation/networking/device_drivers/ethernet/microsoft/netvsc.rst F: Documentation/virt/hyperv F: arch/arm64/hyperv -F: arch/arm64/include/asm/hyperv-tlfs.h F: arch/arm64/include/asm/mshyperv.h F: arch/x86/hyperv -F: arch/x86/include/asm/hyperv-tlfs.h F: arch/x86/include/asm/mshyperv.h F: arch/x86/include/asm/trace/hyperv.h F: arch/x86/kernel/cpu/mshyperv.c @@ -10704,9 +10791,13 @@ F: drivers/pci/controller/pci-hyperv.c F: drivers/scsi/storvsc_drv.c F: drivers/uio/uio_hv_generic.c F: drivers/video/fbdev/hyperv_fb.c -F: include/asm-generic/hyperv-tlfs.h F: include/asm-generic/mshyperv.h F: include/clocksource/hyperv_timer.h +F: include/hyperv/hvgdk.h +F: include/hyperv/hvgdk_ext.h +F: include/hyperv/hvgdk_mini.h +F: include/hyperv/hvhdk.h +F: include/hyperv/hvhdk_mini.h F: include/linux/hyperv.h F: include/net/mana F: include/uapi/linux/hyperv.h @@ -10974,7 +11065,7 @@ M: Rick Lindsley R: Nick Child R: Thomas Falcon L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/ibm/ibmvnic.* IBM Power VFIO Support @@ -10985,7 +11076,7 @@ F: drivers/vfio/vfio_iommu_spapr_tce.c IBM Power Virtual Ethernet Device Driver M: Nick Child L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/ibm/ibmveth.* IBM Power Virtual FC Device Drivers @@ -11240,7 +11331,7 @@ S: Orphan F: drivers/video/fbdev/imsttfb.c INDEX OF FURTHER KERNEL DOCUMENTATION -M: Carlos Bilbao +M: Carlos Bilbao S: Maintained F: Documentation/process/kernel-docs.rst @@ -11454,9 +11545,8 @@ F: drivers/mfd/intel_pmc_bxt.c F: include/linux/mfd/intel_pmc_bxt.h INTEL C600 SERIES SAS CONTROLLER DRIVER -M: Artur Paszkiewicz L: linux-scsi@vger.kernel.org -S: Supported +S: Orphan T: git git://git.code.sf.net/p/intel-sas/isci F: drivers/scsi/isci/ @@ -11518,7 +11608,7 @@ INTEL ETHERNET DRIVERS M: Tony Nguyen M: Przemek Kitszel L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers) -S: Supported +S: Maintained W: https://www.intel.com/content/www/us/en/support.html Q: https://patchwork.ozlabs.org/project/intel-wired-lan/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue.git @@ -11887,6 +11977,12 @@ S: Maintained F: arch/x86/include/asm/intel_telemetry.h F: drivers/platform/x86/intel/telemetry/ +INTEL TOUCH HOST CONTROLLER (THC) DRIVER +M: Even Xu +M: Xinpeng Sun +S: Maintained +F: drivers/hid/intel-thc-hid/ + INTEL TPMI DRIVER M: Srinivas Pandruvada L: platform-driver-x86@vger.kernel.org @@ -12087,7 +12183,7 @@ F: include/uapi/linux/io_uring.h F: io_uring/ IPMI SUBSYSTEM -M: Corey Minyard +M: Corey Minyard L: openipmi-developer@lists.sourceforge.net (moderated for non-subscribers) S: Supported W: http://openipmi.sourceforge.net/ @@ -12399,6 +12495,13 @@ F: Documentation/kbuild/kconfig* F: scripts/Kconfig.include F: scripts/kconfig/ +KCORE +M: Omar Sandoval +L: linux-debuggers@vger.kernel.org +S: Maintained +F: fs/proc/kcore.c +F: include/linux/kcore.h + KCOV R: Dmitry Vyukov R: Andrey Konovalov @@ -12617,8 +12720,8 @@ F: arch/arm64/include/asm/kvm* F: arch/arm64/include/uapi/asm/kvm* F: arch/arm64/kvm/ F: include/kvm/arm_* -F: tools/testing/selftests/kvm/*/aarch64/ -F: tools/testing/selftests/kvm/aarch64/ +F: tools/testing/selftests/kvm/*/arm64/ +F: tools/testing/selftests/kvm/arm64/ KERNEL VIRTUAL MACHINE FOR LOONGARCH (KVM/LoongArch) M: Tianrui Zhao @@ -12644,7 +12747,7 @@ F: arch/mips/include/uapi/asm/kvm* F: arch/mips/kvm/ KERNEL VIRTUAL MACHINE FOR POWERPC (KVM/powerpc) -M: Michael Ellerman +M: Madhavan Srinivasan R: Nicholas Piggin L: linuxppc-dev@lists.ozlabs.org L: kvm@vger.kernel.org @@ -12689,8 +12792,8 @@ F: arch/s390/kvm/ F: arch/s390/mm/gmap.c F: drivers/s390/char/uvdevice.c F: tools/testing/selftests/drivers/s390x/uvdevice/ -F: tools/testing/selftests/kvm/*/s390x/ -F: tools/testing/selftests/kvm/s390x/ +F: tools/testing/selftests/kvm/*/s390/ +F: tools/testing/selftests/kvm/s390/ KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86) M: Sean Christopherson @@ -12707,8 +12810,8 @@ F: arch/x86/include/uapi/asm/svm.h F: arch/x86/include/uapi/asm/vmx.h F: arch/x86/kvm/ F: arch/x86/kvm/*/ -F: tools/testing/selftests/kvm/*/x86_64/ -F: tools/testing/selftests/kvm/x86_64/ +F: tools/testing/selftests/kvm/*/x86/ +F: tools/testing/selftests/kvm/x86/ KERNFS M: Greg Kroah-Hartman @@ -12823,7 +12926,7 @@ L: kgdb-bugreport@lists.sourceforge.net S: Maintained W: http://kgdb.wiki.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/kgdb.git -F: Documentation/dev-tools/kgdb.rst +F: Documentation/process/debugging/kgdb.rst F: drivers/misc/kgdbts.c F: drivers/tty/serial/kgdboc.c F: include/linux/kdb.h @@ -13126,7 +13229,7 @@ LIBETH COMMON ETHERNET LIBRARY M: Alexander Lobakin L: netdev@vger.kernel.org L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers) -S: Supported +S: Maintained T: git https://github.com/alobakin/linux.git F: drivers/net/ethernet/intel/libeth/ F: include/net/libeth/ @@ -13136,7 +13239,7 @@ LIBIE COMMON INTEL ETHERNET LIBRARY M: Alexander Lobakin L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers) L: netdev@vger.kernel.org -S: Supported +S: Maintained T: git https://github.com/alobakin/linux.git F: drivers/net/ethernet/intel/libie/ F: include/linux/net/intel/libie/ @@ -13223,11 +13326,11 @@ X: drivers/macintosh/adb-iop.c X: drivers/macintosh/via-macii.c LINUX FOR POWERPC (32-BIT AND 64-BIT) +M: Madhavan Srinivasan M: Michael Ellerman R: Nicholas Piggin R: Christophe Leroy R: Naveen N Rao -M: Madhavan Srinivasan L: linuxppc-dev@lists.ozlabs.org S: Supported W: https://github.com/linuxppc/wiki/wiki @@ -13313,7 +13416,7 @@ L: linux-kernel@vger.kernel.org L: linux-arch@vger.kernel.org L: lkmm@lists.linux.dev S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git rcu/dev F: Documentation/atomic_bitops.txt F: Documentation/atomic_t.txt F: Documentation/core-api/refcount-vs-atomic.rst @@ -13437,8 +13540,8 @@ LOCKING PRIMITIVES M: Peter Zijlstra M: Ingo Molnar M: Will Deacon +M: Boqun Feng (LOCKDEP & RUST) R: Waiman Long -R: Boqun Feng (LOCKDEP) L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core @@ -13452,6 +13555,11 @@ F: include/linux/seqlock.h F: include/linux/spinlock*.h F: kernel/locking/ F: lib/locking*.[ch] +F: rust/helpers/mutex.c +F: rust/helpers/spinlock.c +F: rust/kernel/sync/lock.rs +F: rust/kernel/sync/lock/ +F: rust/kernel/sync/locked_by.rs X: kernel/locking/locktorture.c LOGICAL DISK MANAGER SUPPORT (LDM, Windows 2000/XP/Vista Dynamic Disks) @@ -13556,6 +13664,12 @@ S: Maintained F: Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml F: drivers/thermal/loongson2_thermal.c +LOONGSON EDAC DRIVER +M: Zhao Qunqin +L: linux-edac@vger.kernel.org +S: Maintained +F: drivers/edac/loongson_edac.c + LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI) M: Sathya Prakash M: Sreekanth Reddy @@ -13939,7 +14053,7 @@ MARVELL OCTEON ENDPOINT DRIVER M: Veerasenareddy Burru M: Sathesh Edara L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/marvell/octeon_ep MARVELL OCTEON ENDPOINT VF DRIVER @@ -13948,7 +14062,7 @@ M: Sathesh Edara M: Shinas Rasheed M: Satananda Burla L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/marvell/octeon_ep_vf MARVELL OCTEONTX2 PHYSICAL FUNCTION DRIVER @@ -13956,8 +14070,9 @@ M: Sunil Goutham M: Geetha sowjanya M: Subbaraya Sundeep M: hariprasad +M: Bharat Bhushan L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/marvell/octeontx2/nic/ F: include/linux/soc/marvell/octeontx2/ @@ -13969,7 +14084,7 @@ M: Jerin Jacob M: hariprasad M: Subbaraya Sundeep L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst F: drivers/net/ethernet/marvell/octeontx2/af/ @@ -14509,6 +14624,14 @@ W: https://linuxtv.org T: git git://linuxtv.org/media.git F: drivers/media/dvb-frontends/stv6111* +MEDIA DRIVERS FOR STM32 - CSI +M: Alain Volmat +L: linux-media@vger.kernel.org +S: Supported +T: git git://linuxtv.org/media_tree.git +F: Documentation/devicetree/bindings/media/st,stm32mp25-csi.yaml +F: drivers/media/platform/st/stm32/stm32-csi.c + MEDIA DRIVERS FOR STM32 - DCMI / DCMIPP M: Hugues Fruchet M: Alain Volmat @@ -14578,7 +14701,6 @@ F: drivers/dma/mediatek/ MEDIATEK ETHERNET DRIVER M: Felix Fietkau M: Sean Wang -M: Mark Lee M: Lorenzo Bianconi L: netdev@vger.kernel.org S: Maintained @@ -14768,7 +14890,7 @@ F: drivers/memory/mtk-smi.c F: include/soc/mediatek/smi.h MEDIATEK SWITCH DRIVER -M: Arınç ÜNAL +M: Chester A. Unal M: Daniel Golle M: DENG Qingfang M: Sean Wang @@ -14858,7 +14980,7 @@ F: drivers/i2c/busses/i2c-mlxbf.c MELLANOX ETHERNET DRIVER (mlx4_en) M: Tariq Toukan L: netdev@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* @@ -14867,7 +14989,7 @@ MELLANOX ETHERNET DRIVER (mlx5e) M: Saeed Mahameed M: Tariq Toukan L: netdev@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* @@ -14875,7 +14997,7 @@ F: drivers/net/ethernet/mellanox/mlx5/core/en_* MELLANOX ETHERNET INNOVA DRIVERS R: Boris Pismenny L: netdev@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* @@ -14914,7 +15036,7 @@ MELLANOX MLX4 core VPI driver M: Tariq Toukan L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/ @@ -14936,7 +15058,7 @@ M: Leon Romanovsky M: Tariq Toukan L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/mellanox/ @@ -15084,7 +15206,15 @@ L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: mm/mlock.c F: mm/mmap.c +F: mm/mprotect.c +F: mm/mremap.c +F: mm/mseal.c +F: mm/vma.c +F: mm/vma.h +F: mm/vma_internal.h +F: tools/testing/vma/ MEMORY TECHNOLOGY DEVICES (MTD) M: Miquel Raynal @@ -15170,7 +15300,7 @@ META ETHERNET DRIVERS M: Alexander Duyck M: Jakub Kicinski R: kernel-team@meta.com -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/meta/ F: drivers/net/ethernet/meta/ @@ -16155,6 +16285,7 @@ F: drivers/scsi/sun3_scsi_vme.c NCSI LIBRARY M: Samuel Mendoza-Jonas +R: Paul Fertser S: Maintained F: net/ncsi/ @@ -16178,7 +16309,8 @@ M: Breno Leitao S: Maintained F: Documentation/networking/netconsole.rst F: drivers/net/netconsole.c -F: tools/testing/selftests/drivers/net/netcons_basic.sh +F: tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +F: tools/testing/selftests/drivers/net/netcons\* NETDEVSIM M: Jakub Kicinski @@ -16195,7 +16327,7 @@ F: net/sched/sch_netem.c NETERION 10GbE DRIVERS (s2io) M: Jon Mason L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/neterion/s2io.rst F: drivers/net/ethernet/neterion/ @@ -16294,7 +16426,7 @@ F: include/linux/inetdevice.h F: include/linux/netdev* F: include/linux/platform_data/wiznet.h F: include/uapi/linux/cn_proc.h -F: include/uapi/linux/ethtool_netlink.h +F: include/uapi/linux/ethtool_netlink* F: include/uapi/linux/if_* F: include/uapi/linux/net_shaper.h F: include/uapi/linux/netdev* @@ -16488,6 +16620,7 @@ F: tools/testing/selftests/net/mptcp/ NETWORKING [TCP] M: Eric Dumazet +M: Neal Cardwell L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/net_cachelines/tcp_sock.rst @@ -16520,7 +16653,7 @@ M: Manish Chopra M: Rahul Verma M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/qlogic/netxen/ NET_FAILOVER MODULE @@ -16616,8 +16749,8 @@ F: arch/nios2/ NITRO ENCLAVES (NE) M: Alexandru Ciobotaru +R: The AWS Nitro Enclaves Team L: linux-kernel@vger.kernel.org -L: The AWS Nitro Enclaves Team S: Supported W: https://aws.amazon.com/ec2/nitro/nitro-enclaves/ F: Documentation/virt/ne_overview.rst @@ -16628,8 +16761,8 @@ F: samples/nitro_enclaves/ NITRO SECURE MODULE (NSM) M: Alexander Graf +R: The AWS Nitro Enclaves Team L: linux-kernel@vger.kernel.org -L: The AWS Nitro Enclaves Team S: Supported W: https://aws.amazon.com/ec2/nitro/nitro-enclaves/ F: drivers/misc/nsm.c @@ -16725,6 +16858,15 @@ T: git https://github.com/Paragon-Software-Group/linux-ntfs3.git F: Documentation/filesystems/ntfs3.rst F: fs/ntfs3/ +NTSYNC SYNCHRONIZATION PRIMITIVE DRIVER +M: Elizabeth Figura +L: wine-devel@winehq.org +S: Supported +F: Documentation/userspace-api/ntsync.rst +F: drivers/misc/ntsync.c +F: include/uapi/linux/ntsync.h +F: tools/testing/selftests/drivers/ntsync/ + NUBUS SUBSYSTEM M: Finn Thain L: linux-m68k@lists.linux-m68k.org @@ -16806,6 +16948,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/srini/nvmem.git F: Documentation/ABI/stable/sysfs-bus-nvmem F: Documentation/devicetree/bindings/nvmem/ F: drivers/nvmem/ +F: include/dt-bindings/nvmem/ F: include/linux/nvmem-consumer.h F: include/linux/nvmem-provider.h @@ -17513,6 +17656,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git F: Documentation/ABI/testing/sysfs-firmware-ofw F: drivers/of/ F: include/linux/of*.h +F: rust/kernel/of.rs F: scripts/dtc/ F: tools/testing/selftests/dt/ K: of_overlay_notifier_ @@ -17652,6 +17796,7 @@ F: Documentation/core-api/packing.rst F: include/linux/packing.h F: lib/packing.c F: lib/packing_test.c +F: scripts/gen_packed_field_checks.c PADATA PARALLEL EXECUTION MECHANISM M: Steffen Klassert @@ -17918,7 +18063,7 @@ M: Karthikeyan Mitran M: Hou Zhiqiang L: linux-pci@vger.kernel.org S: Supported -F: Documentation/devicetree/bindings/pci/mobiveil-pcie.txt +F: Documentation/devicetree/bindings/pci/mbvl,gpex40-pcie.yaml F: drivers/pci/controller/mobiveil/pcie-mobiveil* PCI DRIVER FOR MVEBU (Marvell Armada 370 and Armada XP SOC support) @@ -17942,7 +18087,6 @@ M: Hou Zhiqiang L: linux-pci@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -F: Documentation/devicetree/bindings/pci/layerscape-pcie-gen4.txt F: drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c PCI DRIVER FOR PLDA PCIE IP @@ -18020,7 +18164,7 @@ F: Documentation/PCI/endpoint/* F: Documentation/misc-devices/pci-endpoint-test.rst F: drivers/misc/pci_endpoint_test.c F: drivers/pci/endpoint/ -F: tools/pci/ +F: tools/testing/selftests/pci_endpoint/ PCI ENHANCED ERROR HANDLING (EEH) FOR POWERPC M: Mahesh J Salgaonkar @@ -18113,6 +18257,8 @@ F: include/asm-generic/pci* F: include/linux/of_pci.h F: include/linux/pci* F: include/uapi/linux/pci* +F: rust/kernel/pci.rs +F: samples/rust/rust_driver_pci.rs PCIE BANDWIDTH CONTROLLER M: Ilpo Järvinen @@ -18296,7 +18442,7 @@ PENSANDO ETHERNET DRIVERS M: Shannon Nelson M: Brett Creeley L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/pensando/ionic.rst F: drivers/net/ethernet/pensando/ @@ -18441,8 +18587,8 @@ M: Fabio Estevam M: Shawn Guo M: Jacky Bai R: Pengutronix Kernel Team +R: NXP S32 Linux Team L: linux-gpio@vger.kernel.org -L: NXP S32 Linux Team S: Maintained F: Documentation/devicetree/bindings/pinctrl/fsl,* F: Documentation/devicetree/bindings/pinctrl/nxp,s32* @@ -18472,7 +18618,7 @@ F: Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml F: drivers/pinctrl/mediatek/ PIN CONTROLLER - MEDIATEK MIPS -M: Arınç ÜNAL +M: Chester A. Unal M: Sergio Paracuellos L: linux-mediatek@lists.infradead.org (moderated for non-subscribers) L: linux-mips@vger.kernel.org @@ -18726,11 +18872,13 @@ L: linuxpps@ml.enneenne.com (subscribers-only) S: Maintained W: http://wiki.enneenne.com/index.php/LinuxPPS_support F: Documentation/ABI/testing/sysfs-pps +F: Documentation/ABI/testing/sysfs-pps-gen F: Documentation/devicetree/bindings/pps/pps-gpio.yaml F: Documentation/driver-api/pps.rst F: drivers/pps/ F: include/linux/pps*.h F: include/uapi/linux/pps.h +F: include/uapi/linux/pps_gen.h PRESSURE STALL INFORMATION (PSI) M: Johannes Weiner @@ -19063,7 +19211,7 @@ F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER M: Manish Chopra L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/qlogic/qed/ F: drivers/net/ethernet/qlogic/qede/ F: include/linux/qed/ @@ -19091,7 +19239,7 @@ F: drivers/scsi/qla2xxx/ QLOGIC QLA3XXX NETWORK DRIVER M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/qlogic/qla3xxx.* QLOGIC QLA4XXX iSCSI DRIVER @@ -19107,7 +19255,7 @@ M: Shahed Shaikh M: Manish Chopra M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/qlogic/qlcnic/ QM1D1B0004 MEDIA DRIVER @@ -19122,6 +19270,15 @@ L: linux-media@vger.kernel.org S: Odd Fixes F: drivers/media/tuners/qm1d1c0042* +QNAP MCU DRIVER +M: Heiko Stuebner +S: Maintained +F: drivers/hwmon/qnap-mcu-hwmon.c +F: drivers/input/misc/qnap-mcu-input.c +F: drivers/leds/leds-qnap-mcu.c +F: drivers/mfd/qnap-mcu.c +F: include/linux/mfd/qnap-mcu.h + QNX4 FILESYSTEM M: Anders Larsen S: Maintained @@ -19296,7 +19453,7 @@ F: drivers/misc/fastrpc.c F: include/uapi/misc/fastrpc.h QUALCOMM HEXAGON ARCHITECTURE -M: Brian Cain +M: Brian Cain L: linux-hexagon@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/bcain/linux.git @@ -19516,7 +19673,7 @@ S: Maintained F: arch/mips/ralink RALINK MT7621 MIPS ARCHITECTURE -M: Arınç ÜNAL +M: Chester A. Unal M: Sergio Paracuellos L: linux-mips@vger.kernel.org S: Maintained @@ -19577,7 +19734,7 @@ F: drivers/ras/amd/fmpm.c RASPBERRY PI PISP BACK END M: Jacopo Mondi -L: Raspberry Pi Kernel Maintenance +R: Raspberry Pi Kernel Maintenance L: linux-media@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/media/raspberrypi,pispbe.yaml @@ -19617,7 +19774,7 @@ R: Mathieu Desnoyers R: Lai Jiangshan L: rcu@vger.kernel.org S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git rcu/dev F: tools/testing/selftests/rcutorture RDACM20 Camera Sensor @@ -19696,10 +19853,11 @@ R: Zqiang L: rcu@vger.kernel.org S: Supported W: http://www.rdrop.com/users/paulmck/RCU/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git rcu/dev F: Documentation/RCU/ F: include/linux/rcu* F: kernel/rcu/ +F: rust/kernel/sync/rcu.rs X: Documentation/RCU/torture.rst X: include/linux/srcu*.h X: kernel/rcu/srcu*.c @@ -19848,7 +20006,7 @@ M: Paul Barker M: Niklas Söderlund L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/renesas,etheravb.yaml F: drivers/net/ethernet/renesas/Kconfig F: drivers/net/ethernet/renesas/Makefile @@ -19868,7 +20026,7 @@ RENESAS ETHERNET TSN DRIVER M: Niklas Söderlund L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/renesas,ethertsn.yaml F: drivers/net/ethernet/renesas/rtsn.* @@ -20018,7 +20176,7 @@ RENESAS SUPERH ETHERNET DRIVER M: Niklas Söderlund L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/renesas,ether.yaml F: drivers/net/ethernet/renesas/Kconfig F: drivers/net/ethernet/renesas/Makefile @@ -20086,7 +20244,7 @@ F: net/rfkill/ RHASHTABLE M: Thomas Graf M: Herbert Xu -L: netdev@vger.kernel.org +L: linux-crypto@vger.kernel.org S: Maintained F: include/linux/rhashtable-types.h F: include/linux/rhashtable.h @@ -20193,6 +20351,15 @@ F: drivers/perf/riscv_pmu.c F: drivers/perf/riscv_pmu_legacy.c F: drivers/perf/riscv_pmu_sbi.c +RISC-V SPACEMIT SoC Support +M: Yixun Lan +L: linux-riscv@lists.infradead.org +S: Maintained +T: git https://github.com/spacemit-com/linux +F: arch/riscv/boot/dts/spacemit/ +N: spacemit +K: spacemit + RISC-V THEAD SoC SUPPORT M: Drew Fustini M: Guo Ren @@ -20303,6 +20470,11 @@ L: linux-serial@vger.kernel.org S: Odd Fixes F: drivers/tty/serial/rp2.* +ROHM BD79703 DAC +M: Matti Vaittinen +S: Supported +F: drivers/iio/dac/rohm-bd79703.c + ROHM BD99954 CHARGER IC M: Matti Vaittinen S: Supported @@ -20331,7 +20503,6 @@ ROHM BU270xx LIGHT SENSOR DRIVERs M: Matti Vaittinen L: linux-iio@vger.kernel.org S: Supported -F: drivers/iio/light/rohm-bu27008.c F: drivers/iio/light/rohm-bu27034.c ROHM MULTIFUNCTION BD9571MWV-M PMIC DEVICE DRIVERS @@ -20673,8 +20844,7 @@ F: arch/s390/include/uapi/asm/zcrypt.h F: drivers/s390/crypto/ S390 ZFCP DRIVER -M: Steffen Maier -M: Benjamin Block +M: Nihar Panda L: linux-s390@vger.kernel.org S: Supported F: drivers/s390/scsi/zfcp_* @@ -20729,6 +20899,15 @@ F: arch/arm64/boot/dts/exynos/exynos850* F: drivers/clk/samsung/clk-exynos850.c F: include/dt-bindings/clock/exynos850.h +SAMSUNG EXYNOS MAILBOX DRIVER +M: Tudor Ambarus +L: linux-kernel@vger.kernel.org +L: linux-samsung-soc@vger.kernel.org +S: Supported +F: Documentation/devicetree/bindings/mailbox/google,gs101-mbox.yaml +F: drivers/mailbox/exynos-mailbox.c +F: include/linux/mailbox/exynos-message.h + SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER M: Krzysztof Kozlowski L: linux-crypto@vger.kernel.org @@ -20861,7 +21040,7 @@ F: include/linux/platform_data/spi-s3c64xx.h SAMSUNG SXGBE DRIVERS M: Byungho An L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/samsung/sxgbe/ SAMSUNG THERMAL DRIVER @@ -20919,6 +21098,8 @@ F: kernel/sched/ SCHEDULER - SCHED_EXT R: Tejun Heo R: David Vernet +R: Andrea Righi +R: Changwoo Min L: linux-kernel@vger.kernel.org S: Maintained W: https://github.com/sched-ext/scx @@ -21253,6 +21434,7 @@ M: Srinivas Kandagatla L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/slimbus/ +F: Documentation/driver-api/slimbus.rst F: drivers/slimbus/ F: include/linux/slimbus.h @@ -21261,7 +21443,7 @@ M: Edward Cree M: Martin Habets L: netdev@vger.kernel.org L: linux-net-drivers@amd.com -S: Supported +S: Maintained F: Documentation/networking/devlink/sfc.rst F: drivers/net/ethernet/sfc/ @@ -21592,7 +21774,7 @@ R: Mathieu Desnoyers L: rcu@vger.kernel.org S: Supported W: http://www.rdrop.com/users/paulmck/RCU/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git rcu/dev F: include/linux/srcu*.h F: kernel/rcu/srcu*.c @@ -22003,6 +22185,7 @@ W: https://github.com/thesofproject/linux/ F: sound/soc/sof/ SOUND - GENERIC SOUND CARD (Simple-Audio-Card, Audio-Graph-Card) +M: Mark Brown M: Kuninori Morimoto S: Supported L: linux-sound@vger.kernel.org @@ -22032,7 +22215,7 @@ Q: http://patchwork.linuxtv.org/project/linux-media/list/ F: drivers/media/dvb-frontends/sp2* SPANISH DOCUMENTATION -M: Carlos Bilbao +M: Carlos Bilbao R: Avadhut Naik S: Maintained F: Documentation/translations/sp_SP/ @@ -22182,6 +22365,14 @@ T: git git://linuxtv.org/media.git F: Documentation/devicetree/bindings/media/i2c/st,st-mipid02.yaml F: drivers/media/i2c/st-mipid02.c +ST STC3117 FUEL GAUGE DRIVER +M: Hardevsinh Palaniya +M: Bhavin Sharma +L: linux-pm@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/power/supply/st,stc3117.yaml +F: drivers/power/supply/stc3117_fuel_gauge.c + ST STM32 FIREWALL M: Gatien Chevallier S: Maintained @@ -22326,7 +22517,6 @@ F: drivers/phy/starfive/phy-jh7110-dphy-rx.c STARFIVE JH7110 DPHY TX DRIVER M: Keith Zhao -M: Shengyang Chen S: Supported F: Documentation/devicetree/bindings/phy/starfive,jh7110-dphy-tx.yaml F: drivers/phy/starfive/phy-jh7110-dphy-tx.c @@ -22457,7 +22647,7 @@ F: arch/*/kernel/static_call.c F: include/linux/jump_label*.h F: include/linux/static_call*.h F: kernel/jump_label.c -F: kernel/static_call.c +F: kernel/static_call*.c STI AUDIO (ASoC) DRIVERS M: Arnaud Pouliquen @@ -22513,11 +22703,8 @@ F: Documentation/devicetree/bindings/phy/st,stm32mp25-combophy.yaml F: drivers/phy/st/phy-stm32-combophy.c STMMAC ETHERNET DRIVER -M: Alexandre Torgue -M: Jose Abreu L: netdev@vger.kernel.org -S: Supported -W: http://www.stlinux.com +S: Orphan F: Documentation/networking/device_drivers/ethernet/stmicro/ F: drivers/net/ethernet/stmicro/stmmac/ @@ -22745,13 +22932,12 @@ F: include/linux/platform_data/dma-dw.h SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER M: Jose Abreu L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/synopsys/ SYNOPSYS DESIGNWARE ETHERNET XPCS DRIVER -M: Jose Abreu L: netdev@vger.kernel.org -S: Supported +S: Orphan F: drivers/net/pcs/pcs-xpcs.c F: drivers/net/pcs/pcs-xpcs.h F: include/linux/pcs/pcs-xpcs.h @@ -23146,7 +23332,7 @@ F: drivers/phy/tegra/xusb* TEHUTI ETHERNET DRIVER M: Andy Gospodarek L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/tehuti/tehuti.* TEHUTI TN40XX ETHERNET DRIVER @@ -23232,6 +23418,8 @@ M: Jerome Brunet L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/hwmon/pmbus/ti,tps25990.yaml +F: Documentation/hwmon/tps25990.rst +F: drivers/hwmon/pmbus/tps25990.c TEXAS INSTRUMENTS TPS23861 PoE PSE DRIVER M: Robert Marko @@ -23249,6 +23437,13 @@ S: Supported F: Documentation/devicetree/bindings/iio/dac/ti,dac7612.yaml F: drivers/iio/dac/ti-dac7612.c +TEXAS INSTRUMENTS' LB8864 LED BACKLIGHT DRIVER +M: Alexander Sverdlin +L: linux-leds@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/leds/backlight/ti,lp8864.yaml +F: drivers/leds/leds-lp8864.c + TEXAS INSTRUMENTS' SYSTEM CONTROL INTERFACE (TISCI) PROTOCOL DRIVER M: Nishanth Menon M: Tero Kristo @@ -23556,6 +23751,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/ti/linux.git F: Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml F: drivers/pmdomain/ti/omap_prm.c F: drivers/soc/ti/* +F: include/linux/pruss_driver.h TI LM49xxx FAMILY ASoC CODEC DRIVERS M: M R Swami Reddy @@ -23659,7 +23855,6 @@ F: tools/testing/selftests/timers/ TIPC NETWORK LAYER M: Jon Maloy -M: Ying Xue L: netdev@vger.kernel.org (core kernel code) L: tipc-discussion@lists.sourceforge.net (user apps, general discussion) S: Maintained @@ -23721,7 +23916,7 @@ M: "Paul E. McKenney" M: Josh Triplett L: linux-kernel@vger.kernel.org S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git rcu/dev F: Documentation/RCU/torture.rst F: kernel/locking/locktorture.c F: kernel/rcu/rcuscale.c @@ -24265,7 +24460,8 @@ F: Documentation/devicetree/bindings/usb/nxp,isp1760.yaml F: drivers/usb/isp1760/* USB LAN78XX ETHERNET DRIVER -M: Woojung Huh +M: Thangaraj Samynathan +M: Rengarajan Sundararajan M: UNGLinuxDriver@microchip.com L: netdev@vger.kernel.org S: Maintained @@ -24450,7 +24646,11 @@ L: linux-media@vger.kernel.org S: Maintained W: http://www.ideasonboard.org/uvc/ T: git git://linuxtv.org/media.git +F: Documentation/userspace-api/media/drivers/uvcvideo.rst +F: Documentation/userspace-api/media/v4l/metafmt-uvc.rst +F: drivers/media/common/uvc.c F: drivers/media/usb/uvc/ +F: include/linux/usb/uvc.h F: include/uapi/linux/uvcvideo.h USB WEBCAM GADGET @@ -25035,21 +25235,6 @@ F: include/uapi/linux/vsockmon.h F: net/vmw_vsock/ F: tools/testing/vsock/ -VMA -M: Andrew Morton -M: Liam R. Howlett -M: Lorenzo Stoakes -R: Vlastimil Babka -R: Jann Horn -L: linux-mm@kvack.org -S: Maintained -W: https://www.linux-mm.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm -F: mm/vma.c -F: mm/vma.h -F: mm/vma_internal.h -F: tools/testing/vma/ - VMALLOC M: Andrew Morton R: Uladzislau Rezki @@ -25554,11 +25739,13 @@ F: arch/x86/entry/vdso/ XARRAY M: Matthew Wilcox L: linux-fsdevel@vger.kernel.org +L: linux-mm@kvack.org S: Supported F: Documentation/core-api/xarray.rst F: include/linux/idr.h F: include/linux/xarray.h F: lib/idr.c +F: lib/test_xarray.c F: lib/xarray.c F: tools/testing/radix-tree @@ -26038,7 +26225,7 @@ K: zstd ZSWAP COMPRESSED SWAP CACHING M: Johannes Weiner -M: Yosry Ahmed +M: Yosry Ahmed M: Nhat Pham R: Chengming Zhou L: linux-mm@kvack.org diff --git a/Makefile b/Makefile index e5b8a8832c0c..9e0d63d9d94b 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 -PATCHLEVEL = 13 +PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc1 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -497,6 +497,7 @@ KBUILD_HOSTRUSTFLAGS := $(rust_common_flags) -O -Cstrip=debuginfo \ -Zallow-features= $(HOSTRUSTFLAGS) KBUILD_HOSTLDFLAGS := $(HOST_LFS_LDFLAGS) $(HOSTLDFLAGS) KBUILD_HOSTLDLIBS := $(HOST_LFS_LIBS) $(HOSTLDLIBS) +KBUILD_PROCMACROLDFLAGS := $(or $(PROCMACROLDFLAGS),$(KBUILD_HOSTLDFLAGS)) # Make variables (CC, etc...) CPP = $(CC) -E @@ -621,7 +622,7 @@ export HOSTRUSTC KBUILD_HOSTRUSTFLAGS export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL export PERL PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD -export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE +export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS KBUILD_PROCMACROLDFLAGS LDFLAGS_MODULE export KBUILD_USERCFLAGS KBUILD_USERLDFLAGS export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS KBUILD_LDFLAGS @@ -1367,6 +1368,10 @@ PHONY += scripts_unifdef scripts_unifdef: scripts_basic $(Q)$(MAKE) $(build)=scripts scripts/unifdef +PHONY += scripts_gen_packed_field_checks +scripts_gen_packed_field_checks: scripts_basic + $(Q)$(MAKE) $(build)=scripts scripts/gen_packed_field_checks + # --------------------------------------------------------------------------- # Install @@ -1571,7 +1576,7 @@ MRPROPER_FILES += include/config include/generated \ certs/x509.genkey \ vmlinux-gdb.py \ rpmbuild \ - rust/libmacros.so + rust/libmacros.so rust/libmacros.dylib # clean - Delete most, but leave enough to build external modules # diff --git a/arch/Kconfig b/arch/Kconfig index 6682b2a53e34..b8a4ff365582 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1526,6 +1526,14 @@ config HAVE_ARCH_COMPILER_H linux/compiler-*.h in order to override macro definitions that those headers generally provide. +config HAVE_ARCH_LIBGCC_H + bool + help + An architecture can select this if it provides an + asm/libgcc.h header that should be included after + linux/libgcc.h in order to override macro definitions that + header generally provides. + config HAVE_ARCH_PREL32_RELOCATIONS bool help diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 302507bf9b5d..3df5f2dd4c0f 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -148,6 +148,8 @@ #define SCM_TS_OPT_ID 81 +#define SO_RCVPRIORITY 82 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/alpha/kernel/core_cia.c b/arch/alpha/kernel/core_cia.c index ca3d9c732b61..6e577228e175 100644 --- a/arch/alpha/kernel/core_cia.c +++ b/arch/alpha/kernel/core_cia.c @@ -331,10 +331,7 @@ cia_prepare_tbia_workaround(int window) long i; /* Use minimal 1K map. */ - ppte = memblock_alloc(CIA_BROKEN_TBIA_SIZE, 32768); - if (!ppte) - panic("%s: Failed to allocate %u bytes align=0x%x\n", - __func__, CIA_BROKEN_TBIA_SIZE, 32768); + ppte = memblock_alloc_or_panic(CIA_BROKEN_TBIA_SIZE, 32768); pte = (virt_to_phys(ppte) >> (PAGE_SHIFT - 1)) | 1; for (i = 0; i < CIA_BROKEN_TBIA_SIZE / sizeof(unsigned long); ++i) diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index b22248044bf0..b1bfbd11980d 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -81,10 +81,7 @@ mk_resource_name(int pe, int port, char *str) char *name; sprintf(tmp, "PCI %s PE %d PORT %d", str, pe, port); - name = memblock_alloc(strlen(tmp) + 1, SMP_CACHE_BYTES); - if (!name) - panic("%s: Failed to allocate %zu bytes\n", __func__, - strlen(tmp) + 1); + name = memblock_alloc_or_panic(strlen(tmp) + 1, SMP_CACHE_BYTES); strcpy(name, tmp); return name; @@ -119,10 +116,7 @@ alloc_io7(unsigned int pe) return NULL; } - io7 = memblock_alloc(sizeof(*io7), SMP_CACHE_BYTES); - if (!io7) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*io7)); + io7 = memblock_alloc_or_panic(sizeof(*io7), SMP_CACHE_BYTES); io7->pe = pe; raw_spin_lock_init(&io7->irq_lock); diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c index 4458eb7f44f0..8e9b4ac86b7e 100644 --- a/arch/alpha/kernel/pci.c +++ b/arch/alpha/kernel/pci.c @@ -391,10 +391,7 @@ alloc_pci_controller(void) { struct pci_controller *hose; - hose = memblock_alloc(sizeof(*hose), SMP_CACHE_BYTES); - if (!hose) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*hose)); + hose = memblock_alloc_or_panic(sizeof(*hose), SMP_CACHE_BYTES); *hose_tail = hose; hose_tail = &hose->next; @@ -405,13 +402,7 @@ alloc_pci_controller(void) struct resource * __init alloc_resource(void) { - void *ptr = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - - if (!ptr) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); - - return ptr; + return memblock_alloc_or_panic(sizeof(struct resource), SMP_CACHE_BYTES); } diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 7fcf3e9b7103..681f56089d9c 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -71,14 +71,8 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base, if (align < mem_size) align = mem_size; - arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES); - if (!arena) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*arena)); - arena->ptes = memblock_alloc(mem_size, align); - if (!arena->ptes) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, mem_size, align); + arena = memblock_alloc_or_panic(sizeof(*arena), SMP_CACHE_BYTES); + arena->ptes = memblock_alloc_or_panic(mem_size, align); spin_lock_init(&arena->lock); arena->hose = hose; diff --git a/arch/alpha/lib/fpreg.c b/arch/alpha/lib/fpreg.c index 9a238e7536ae..3d32165043f8 100644 --- a/arch/alpha/lib/fpreg.c +++ b/arch/alpha/lib/fpreg.c @@ -10,7 +10,6 @@ #include #include #include -#include #if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67) #define STT(reg,val) asm volatile ("ftoit $f"#reg",%0" : "=r"(val)); diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 4fe618446e4c..61c2198b1359 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -42,7 +42,7 @@ pgd_alloc(struct mm_struct *mm) { pgd_t *ret, *init; - ret = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + ret = __pgd_alloc(mm, 0); init = pgd_offset(&init_mm, 0UL); if (ret) { #ifdef CONFIG_ALPHA_LARGE_VMALLOC diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index ea5a1dcb133b..f27e6b90428e 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -6,6 +6,7 @@ config ARC def_bool y select ARC_TIMERS + select ARCH_HAS_CPU_CACHE_ALIASING select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DMA_PREP_COHERENT @@ -17,6 +18,7 @@ config ARC select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC select ARCH_32BIT_OFF_T select BUILDTIME_TABLE_SORT + select GENERIC_BUILTIN_DTB select CLONE_BACKWARDS select COMMON_CLK select DMA_DIRECT_REMAP @@ -24,7 +26,6 @@ config ARC # for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP select GENERIC_IRQ_SHOW select GENERIC_PCI_IOMAP - select GENERIC_PENDING_IRQ if SMP select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_IOREMAP @@ -550,11 +551,11 @@ config ARC_DBG_JUMP_LABEL part of static keys (jump labels) related code. endif -config ARC_BUILTIN_DTB_NAME +config BUILTIN_DTB_NAME string "Built in DTB" + default "nsim_700" help - Set the name of the DTB to embed in the vmlinux binary - Leaving it blank selects the "nsim_700" dtb. + Set the name of the DTB to embed in the vmlinux binary. endmenu # "ARC Architecture Configuration" diff --git a/arch/arc/Makefile b/arch/arc/Makefile index fb98478ed1ab..0c5e6e6314f2 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -82,9 +82,6 @@ KBUILD_CFLAGS += $(cflags-y) KBUILD_AFLAGS += $(KBUILD_CFLAGS) KBUILD_LDFLAGS += $(ldflags-y) -# w/o this dtb won't embed into kernel binary -core-y += arch/arc/boot/dts/ - core-y += arch/arc/plat-sim/ core-$(CONFIG_ARC_PLAT_TB10X) += arch/arc/plat-tb10x/ core-$(CONFIG_ARC_PLAT_AXS10X) += arch/arc/plat-axs10x/ diff --git a/arch/arc/boot/dts/Makefile b/arch/arc/boot/dts/Makefile index 48704dfdf75c..ee5664f0640d 100644 --- a/arch/arc/boot/dts/Makefile +++ b/arch/arc/boot/dts/Makefile @@ -1,13 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -# Built-in dtb -builtindtb-y := nsim_700 -ifneq ($(CONFIG_ARC_BUILTIN_DTB_NAME),) - builtindtb-y := $(CONFIG_ARC_BUILTIN_DTB_NAME) -endif - -obj-y += $(builtindtb-y).dtb.o -dtb-y := $(builtindtb-y).dtb +dtb-y := $(addsuffix .dtb, $(CONFIG_BUILTIN_DTB_NAME)) # for CONFIG_OF_ALL_DTBS test dtb- := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts)) diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index 319bbe270322..a7cd526dd7ca 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -23,7 +23,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS101=y CONFIG_ARC_CACHE_LINE_SHIFT=5 -CONFIG_ARC_BUILTIN_DTB_NAME="axs101" +CONFIG_BUILTIN_DTB_NAME="axs101" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 8c1f1a111a17..afa6a348f444 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -22,7 +22,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS103=y CONFIG_ISA_ARCV2=y -CONFIG_ARC_BUILTIN_DTB_NAME="axs103" +CONFIG_BUILTIN_DTB_NAME="axs103" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index 75cab9f25b5b..2bfa6371953c 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -22,7 +22,7 @@ CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS103=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y -CONFIG_ARC_BUILTIN_DTB_NAME="axs103_idu" +CONFIG_BUILTIN_DTB_NAME="axs103_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index 8c3ed5d6e6c3..3a1577112078 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -14,7 +14,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set -CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs" +CONFIG_BUILTIN_DTB_NAME="haps_hs" CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_COMPACTION is not set diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 6fc98c1b9b36..a3cf940b1f5b 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -16,7 +16,7 @@ CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SMP=y -CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs_idu" +CONFIG_BUILTIN_DTB_NAME="haps_hs_idu" CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 9e79154b5535..1558e8e87767 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -20,7 +20,7 @@ CONFIG_ISA_ARCV2=y CONFIG_SMP=y CONFIG_LINUX_LINK_BASE=0x90000000 CONFIG_LINUX_RAM_BASE=0x80000000 -CONFIG_ARC_BUILTIN_DTB_NAME="hsdk" +CONFIG_BUILTIN_DTB_NAME="hsdk" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 51092c39e360..f8b3235d9a65 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -17,7 +17,7 @@ CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_ISA_ARCOMPACT=y -CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700" +CONFIG_BUILTIN_DTB_NAME="nsim_700" CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 70c17bca4939..ee45dc0877fb 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -19,7 +19,7 @@ CONFIG_ISA_ARCOMPACT=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci" +CONFIG_BUILTIN_DTB_NAME="nsimosci" # CONFIG_COMPACTION is not set CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 59a3b6642fe7..e0a309970c20 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -19,7 +19,7 @@ CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set CONFIG_ISA_ARCV2=y -CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs" +CONFIG_BUILTIN_DTB_NAME="nsimosci_hs" # CONFIG_COMPACTION is not set CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 1419fc946a08..88325b8b49cf 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -16,7 +16,7 @@ CONFIG_MODULES=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y # CONFIG_ARC_TIMERS_64BIT is not set -CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu" +CONFIG_BUILTIN_DTB_NAME="nsimosci_hs_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 5aba3d850fa2..865fbc19ef03 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -26,7 +26,7 @@ CONFIG_MODULE_UNLOAD=y CONFIG_ARC_PLAT_TB10X=y CONFIG_ARC_CACHE_LINE_SHIFT=5 CONFIG_HZ=250 -CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk" +CONFIG_BUILTIN_DTB_NAME="abilis_tb100_dvk" CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index 50c343913825..03d9ac20baa9 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -13,7 +13,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS103=y CONFIG_ISA_ARCV2=y -CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38" +CONFIG_BUILTIN_DTB_NAME="vdk_hs38" CONFIG_PREEMPT=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 6d9e1d9f71d2..c09488992f13 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -15,7 +15,7 @@ CONFIG_AXS103=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y # CONFIG_ARC_TIMERS_64BIT is not set -CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp" +CONFIG_BUILTIN_DTB_NAME="vdk_hs38_smp" CONFIG_PREEMPT=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/arc/include/asm/cachetype.h b/arch/arc/include/asm/cachetype.h new file mode 100644 index 000000000000..acd3b6cb4bf5 --- /dev/null +++ b/arch/arc/include/asm/cachetype.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_ARC_CACHETYPE_H +#define __ASM_ARC_CACHETYPE_H + +#define cpu_dcache_is_aliasing() false +#define cpu_icache_is_aliasing() true + +#endif diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index 096b8ef58edb..dfae070fe8d5 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -53,19 +53,14 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte_ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *ret = (pgd_t *) __get_free_page(GFP_KERNEL); + pgd_t *ret = __pgd_alloc(mm, 0); if (ret) { int num, num2; - num = USER_PTRS_PER_PGD + USER_KERNEL_GUTTER / PGDIR_SIZE; - memzero(ret, num * sizeof(pgd_t)); + num = USER_PTRS_PER_PGD + USER_KERNEL_GUTTER / PGDIR_SIZE; num2 = VMALLOC_SIZE / PGDIR_SIZE; memcpy(ret + num, swapper_pg_dir + num, num2 * sizeof(pgd_t)); - - memzero(ret + num + num2, - (PTRS_PER_PGD - num - num2) * sizeof(pgd_t)); - } return ret; } diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 55373ca0d28b..cdd370ec9280 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -357,8 +357,6 @@ static void idu_cascade_isr(struct irq_desc *desc) static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq) { irq_set_chip_and_handler(virq, &idu_irq_chip, handle_level_irq); - irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); - return 0; } diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index d2f5ceaaed1b..3b2d8b1bd271 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -200,7 +200,6 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, struct callee_regs *cregs) { struct disasm_state state; - char buf[TASK_COMM_LEN]; /* handle user mode only and only if enabled by sysadmin */ if (!user_mode(regs) || !unaligned_enabled) @@ -212,11 +211,11 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, " performance significantly\n. To enable further" " logging of such instances, please \n" " echo 0 > /proc/sys/kernel/ignore-unaligned-usertrap\n", - get_task_comm(buf, current), task_pid_nr(current)); + current->comm, task_pid_nr(current)); } else { /* Add rate limiting if it gets down to it */ pr_warn("%s(%d): unaligned access to/from 0x%lx by PC: 0x%lx\n", - get_task_comm(buf, current), task_pid_nr(current), + current->comm, task_pid_nr(current), address, regs->ret); } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 202397be76d8..835b5f100e92 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -5,8 +5,11 @@ config ARM select ARCH_32BIT_OFF_T select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE if HAVE_KRETPROBES && FRAME_POINTER && !ARM_UNWIND select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CACHE_LINE_SIZE if OF select ARCH_HAS_CPU_CACHE_ALIASING select ARCH_HAS_CPU_FINALIZE_INIT if MMU + select ARCH_HAS_CRC32 if KERNEL_MODE_NEON + select ARCH_HAS_CRC_T10DIF if KERNEL_MODE_NEON select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DMA_ALLOC if MMU @@ -1751,5 +1754,3 @@ config ARCH_HIBERNATION_POSSIBLE default y if ARCH_SUSPEND_POSSIBLE endmenu - -source "arch/arm/Kconfig.assembler" diff --git a/arch/arm/Kconfig.assembler b/arch/arm/Kconfig.assembler deleted file mode 100644 index 5cb31aae1188..000000000000 --- a/arch/arm/Kconfig.assembler +++ /dev/null @@ -1,6 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -config AS_VFP_VMRS_FPINST - def_bool $(as-instr,.fpu vfpv2\nvmrs r0$(comma)FPINST) - help - Supported by binutils >= 2.24 and LLVM integrated assembler. diff --git a/arch/arm/boot/dts/allwinner/suniv-f1c100s-licheepi-nano.dts b/arch/arm/boot/dts/allwinner/suniv-f1c100s-licheepi-nano.dts index 43896723a994..472ded0aafcf 100644 --- a/arch/arm/boot/dts/allwinner/suniv-f1c100s-licheepi-nano.dts +++ b/arch/arm/boot/dts/allwinner/suniv-f1c100s-licheepi-nano.dts @@ -62,6 +62,14 @@ status = "okay"; }; +&codec { + allwinner,audio-routing = + "Headphone", "HP", + "Headphone", "HPCOM", + "MIC", "Mic"; + status = "okay"; +}; + &usb_otg { dr_mode = "otg"; status = "okay"; diff --git a/arch/arm/boot/dts/allwinner/suniv-f1c100s.dtsi b/arch/arm/boot/dts/allwinner/suniv-f1c100s.dtsi index 3c61d59ab5f8..e4b41bc93852 100644 --- a/arch/arm/boot/dts/allwinner/suniv-f1c100s.dtsi +++ b/arch/arm/boot/dts/allwinner/suniv-f1c100s.dtsi @@ -6,6 +6,7 @@ #include #include +#include / { #address-cells = <1>; @@ -159,6 +160,15 @@ status = "disabled"; }; + dma: dma-controller@1c02000 { + compatible = "allwinner,suniv-f1c100s-dma"; + reg = <0x01c02000 0x1000>; + interrupts = <18>; + clocks = <&ccu CLK_BUS_DMA>; + resets = <&ccu RST_BUS_DMA>; + #dma-cells = <2>; + }; + ccu: clock@1c20000 { compatible = "allwinner,suniv-f1c100s-ccu"; reg = <0x01c20000 0x400>; @@ -326,5 +336,19 @@ resets = <&ccu RST_BUS_UART2>; status = "disabled"; }; + + codec: codec@1c23c00 { + #sound-dai-cells = <0>; + compatible = "allwinner,suniv-f1c100s-codec"; + reg = <0x01c23c00 0x400>; + interrupts = <21>; + clocks = <&ccu CLK_BUS_CODEC>, <&ccu CLK_CODEC>; + clock-names = "apb", "codec"; + dmas = <&dma SUN4I_DMA_NORMAL 12>, + <&dma SUN4I_DMA_NORMAL 12>; + dma-names = "rx", "tx"; + resets = <&ccu RST_BUS_CODEC>; + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/amlogic/meson.dtsi b/arch/arm/boot/dts/amlogic/meson.dtsi index 8cb0fc78b2af..28ec2c821cdc 100644 --- a/arch/arm/boot/dts/amlogic/meson.dtsi +++ b/arch/arm/boot/dts/amlogic/meson.dtsi @@ -255,8 +255,6 @@ usb0: usb@c9040000 { compatible = "snps,dwc2"; - #address-cells = <1>; - #size-cells = <0>; reg = <0xc9040000 0x40000>; interrupts = ; phys = <&usb0_phy>; @@ -270,8 +268,6 @@ usb1: usb@c90c0000 { compatible = "snps,dwc2"; - #address-cells = <1>; - #size-cells = <0>; reg = <0xc90c0000 0x40000>; interrupts = ; phys = <&usb1_phy>; diff --git a/arch/arm/boot/dts/aspeed/Makefile b/arch/arm/boot/dts/aspeed/Makefile index c4f064e4b073..2e5f4833a073 100644 --- a/arch/arm/boot/dts/aspeed/Makefile +++ b/arch/arm/boot/dts/aspeed/Makefile @@ -6,6 +6,7 @@ dtb-$(CONFIG_ARCH_ASPEED) += \ aspeed-bmc-amd-daytonax.dtb \ aspeed-bmc-amd-ethanolx.dtb \ aspeed-bmc-ampere-mtjade.dtb \ + aspeed-bmc-ampere-mtjefferson.dtb \ aspeed-bmc-ampere-mtmitchell.dtb \ aspeed-bmc-arm-stardragon4800-rep2.dtb \ aspeed-bmc-asrock-e3c246d4i.dtb \ @@ -40,6 +41,7 @@ dtb-$(CONFIG_ARCH_ASPEED) += \ aspeed-bmc-ibm-rainier.dtb \ aspeed-bmc-ibm-rainier-1s4u.dtb \ aspeed-bmc-ibm-rainier-4u.dtb \ + aspeed-bmc-ibm-sbp1.dtb \ aspeed-bmc-ibm-system1.dtb \ aspeed-bmc-intel-s2600wf.dtb \ aspeed-bmc-inspur-fp5280g2.dtb \ diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-ampere-mtjefferson.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-ampere-mtjefferson.dts new file mode 100644 index 000000000000..c435359a4bd9 --- /dev/null +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-ampere-mtjefferson.dts @@ -0,0 +1,622 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2024 Ampere Computing LLC. + +/dts-v1/; + +#include "aspeed-g6.dtsi" +#include +#include + +/ { + model = "Ampere Mt. Jefferson BMC"; + compatible = "ampere,mtjefferson-bmc", "aspeed,ast2600"; + + aliases { + i2c20 = &i2c4_bus70_chn0; + i2c22 = &i2c4_bus70_chn2; + + /* + * I2C OCP alias port + */ + i2c30 = &ocpslot; + + /* + * I2C NVMe alias port + */ + i2c48 = &nvmeslot_0; + i2c49 = &nvmeslot_1; + i2c50 = &nvmeslot_2; + i2c51 = &nvmeslot_3; + i2c52 = &nvmeslot_4; + i2c53 = &nvmeslot_5; + i2c54 = &nvmeslot_6; + i2c55 = &nvmeslot_7; + i2c56 = &nvmeslot_8; + i2c57 = &nvmeslot_9; + i2c58 = &nvmeslot_10; + i2c59 = &nvmeslot_11; + }; + + chosen { + stdout-path = &uart5; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x80000000>; + }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + gfx_memory: framebuffer { + size = <0x01000000>; + alignment = <0x01000000>; + compatible = "shared-dma-pool"; + reusable; + }; + + video_engine_memory: video { + size = <0x04000000>; + alignment = <0x01000000>; + compatible = "shared-dma-pool"; + reusable; + }; + + vga_memory: region@bf000000 { + no-map; + compatible = "shared-dma-pool"; + reg = <0xbf000000 0x01000000>; /* 16M */ + }; + }; + + voltage_mon_reg: voltage-mon-regulator { + compatible = "regulator-fixed"; + regulator-name = "ltc2497_reg"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + leds { + compatible = "gpio-leds"; + led-bmc-ready { + gpios = <&gpio0 ASPEED_GPIO(W, 5) (GPIO_ACTIVE_HIGH | GPIO_TRANSITORY)>; + }; + + led-sw-heartbeat { + gpios = <&gpio0 ASPEED_GPIO(N, 3) GPIO_ACTIVE_HIGH>; + }; + + led-identify { + gpios = <&gpio0 ASPEED_GPIO(S, 3) GPIO_ACTIVE_HIGH>; + }; + + led-fault { + gpios = <&gpio0 ASPEED_GPIO(P, 4) GPIO_ACTIVE_HIGH>; + }; + }; + + iio-hwmon { + compatible = "iio-hwmon"; + io-channels = <&adc0 0>, <&adc0 1>, <&adc0 2>, + <&adc_i2c_2 0>, <&adc_i2c_2 1>, + <&adc_i2c_2 2>, <&adc_i2c_2 3>, + <&adc_i2c_2 4>, <&adc_i2c_2 5>, + <&adc_i2c_2 6>, <&adc_i2c_2 7>, + <&adc_i2c_2 8>, <&adc_i2c_2 9>, + <&adc_i2c_2 10>, <&adc_i2c_2 11>, + <&adc_i2c_2 12>, <&adc_i2c_2 13>, + <&adc_i2c_2 14>, <&adc_i2c_2 15>, + <&adc_i2c_0 0>, <&adc_i2c_0 1>, + <&adc_i2c_0 2>, <&adc_i2c_0 3>, + <&adc_i2c_0 4>, <&adc_i2c_0 5>, + <&adc_i2c_0 6>, <&adc_i2c_0 7>, + <&adc_i2c_0 8>, <&adc_i2c_0 9>, + <&adc_i2c_0 10>, <&adc_i2c_0 11>, + <&adc_i2c_0 12>; + }; +}; + +&mdio0 { + status = "okay"; + + ethphy0: ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0>; + }; +}; + +&mac0 { + status = "okay"; + + phy-mode = "rgmii"; + phy-handle = <ðphy0>; + + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_rgmii1_default>; +}; + +&mac3 { + status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_rmii4_default>; + use-ncsi; +}; + +&fmc { + status = "okay"; + flash@0 { + status = "okay"; + m25p,fast-read; + label = "bmc"; + spi-max-frequency = <50000000>; +#include "openbmc-flash-layout-64.dtsi" + }; + + flash@1 { + status = "okay"; + m25p,fast-read; + label = "alt-bmc"; + spi-max-frequency = <50000000>; +#include "openbmc-flash-layout-64-alt.dtsi" + }; +}; + +&spi1 { + status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi1_default>; + + flash@0 { + status = "okay"; + m25p,fast-read; + label = "pnor"; + spi-max-frequency = <20000000>; + }; +}; + +&uart1 { + status = "okay"; +}; + +&uart2 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c1 { + status = "okay"; +}; + +&i2c2 { + status = "okay"; +}; + +&i2c3 { + status = "okay"; + bus-frequency = <1000000>; + multi-master; + mctp-controller; + + mctp@10 { + compatible = "mctp-i2c-controller"; + reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; + }; +}; + +&i2c4 { + status = "okay"; + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + pagesize = <32>; + }; + + i2c-mux@70 { + compatible = "nxp,pca9545"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x70>; + i2c-mux-idle-disconnect; + + i2c4_bus70_chn0: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0>; + + eeprom@52 { + compatible = "atmel,24c256"; + reg = <0x52>; + pagesize = <32>; + }; + temperature-sensor@48 { + compatible = "ti,tmp75"; + reg = <0x48>; + }; + temperature-sensor@49 { + compatible = "ti,tmp75"; + reg = <0x49>; + }; + temperature-sensor@4a{ + compatible = "ti,tmp75"; + reg = <0x4a>; + }; + temperature-sensor@4b { + compatible = "ti,tmp464"; + reg = <0x4b>; + #address-cells = <1>; + #size-cells = <0>; + + channel@0 { + reg = <0x0>; + status = "disabled"; + }; + channel@1 { + reg = <0x1>; + status = "disabled"; + }; + channel@2 { + reg = <0x2>; + status = "disabled"; + }; + channel@3 { + reg = <0x3>; + status = "disabled"; + }; + channel@4 { + reg = <0x4>; + }; + }; + temperature-sensor@4d { + compatible = "ti,tmp75"; + reg = <0x4d>; + }; + temperature-sensor@4e { + compatible = "ti,tmp75"; + reg = <0x4e>; + }; + temperature-sensor@4f { + compatible = "ti,tmp75"; + reg = <0x4f>; + }; + temperature-sensor@28 { + compatible = "nuvoton,nct7802"; + reg = <0x28>; + + #address-cells = <1>; + #size-cells = <0>; + channel@1 { /* RTD1 */ + reg = <1>; + sensor-type = "temperature"; + temperature-mode = "thermistor"; + }; + }; + adc_i2c_0: adc@14 { + compatible = "lltc,ltc2497"; + reg = <0x14>; + vref-supply = <&voltage_mon_reg>; + #io-channel-cells = <1>; + }; + }; + + i2c4_bus70_chn2: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x2>; + + adc_i2c_2: adc@14 { + compatible = "lltc,ltc2497"; + reg = <0x14>; + vref-supply = <&voltage_mon_reg>; + #io-channel-cells = <1>; + }; + }; + }; +}; + +&i2c5 { + status = "okay"; + i2c-mux@70 { + compatible = "nxp,pca9548"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x70>; + i2c-mux-idle-disconnect; + + i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0>; + + i2c-mux@71 { + compatible = "nxp,pca9548"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x71>; + i2c-mux-idle-disconnect; + + nvmeslot_8: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0>; + }; + nvmeslot_9: i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x1>; + }; + nvmeslot_10: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x2>; + }; + nvmeslot_11: i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x3>; + }; + }; + + i2c-mux@72 { + compatible = "nxp,pca9548"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x72>; + i2c-mux-idle-disconnect; + + nvmeslot_4: i2c@4 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x4>; + }; + nvmeslot_5: i2c@5 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x5>; + }; + nvmeslot_6: i2c@6 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x6>; + }; + nvmeslot_7: i2c@7 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x7>; + }; + }; + + i2c-mux@74 { + compatible = "nxp,pca9548"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x74>; + i2c-mux-idle-disconnect; + + ocpslot: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0>; + + ocpslot_temp: temperature-sensor@1f { + compatible = "ti,tmp421"; + reg = <0x1f>; + #address-cells = <1>; + #size-cells = <0>; + + channel@0 { + reg = <0x0>; + status = "disabled"; + }; + channel@1 { + reg = <0x1>; + }; + }; + }; + + nvmeslot_0: i2c@4 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x4>; + }; + nvmeslot_1: i2c@5 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x5>; + }; + nvmeslot_2: i2c@6 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x6>; + }; + nvmeslot_3: i2c@7 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x7>; + }; + }; + }; + }; +}; + +&i2c6 { + status = "okay"; + + rtc@51 { + compatible = "nxp,pcf8563"; + reg = <0x51>; + }; +}; + +&i2c7 { + status = "okay"; + + temperature-sensor@4f { + compatible = "ti,tmp75"; + reg = <0x4f>; + }; +}; + +&i2c8 { + status = "okay"; + + fan-controller@5c { + compatible = "onnn,adt7462"; + reg = <0x5c>; + }; +}; + +&i2c9 { + status = "okay"; + + #address-cells = <1>; + #size-cells = <0>; + + eeprom@50 { + compatible = "atmel,24c02"; + reg = <0x50>; + }; + + eeprom@52 { + compatible = "atmel,24c02"; + reg = <0x52>; + }; + + temperature-sensor@18 { + compatible = "jedec,jc-42.4-temp"; + reg = <0x18>; + }; + + temperature-sensor@1a { + compatible = "jedec,jc-42.4-temp"; + reg = <0x1a>; + }; +}; + +&i2c10 { + status = "okay"; +}; + +&i2c11 { + status = "okay"; + ssif-bmc@10 { + compatible = "ssif-bmc"; + reg = <0x10>; + }; +}; + +&i2c14 { + status = "okay"; + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + pagesize = <32>; + }; + + bmc_ast2600_cpu: temperature-sensor@48 { + compatible = "ti,tmp75"; + reg = <0x48>; + }; +}; + +&i2c15 { + status = "okay"; + gpio_expander1: gpio-expander@22 { + compatible = "nxp,pca9535"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + gpio-line-names = + "presence-ocp1","presence-ocp2", + "","", + "","", + "","", + "","", + "","", + "","", + "",""; + }; +}; + +&adc0 { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_adc0_default &pinctrl_adc1_default + &pinctrl_adc2_default>; +}; + +&vhub { + status = "okay"; +}; + +&video { + status = "okay"; + memory-region = <&video_engine_memory>; +}; + +&gpio0 { + gpio-line-names = + /*A0-A7*/ "","","","","cpu-type-detect","i2c2-reset-n","i2c6-reset-n","i2c5-reset-n", + /*B0-B7*/ "","","","","host0-sysreset-n","host0-pmin-n","fru-rd-complete", + "chassis-id-sel", + /*C0-C7*/ "s0-vrd-fault-n","","bmc-debug-mode","","cpld-3v3-irq-n","","vrd-sel", + "spd-sel", + /*D0-D7*/ "presence-ps0","presence-ps1","hsc-12vmain-alt2-n","ext-high-temp-n", + "","","","", + /*E0-E7*/ "eth-phy-rst-n","eth-phy-int-n","","","","","","", + /*F0-F7*/ "s0-pcp-oc-warn-n","","power-chassis-control", + "cpu-bios-recover","s0-heartbeat","hs-scout-proc-hot","s0-vr-hot-n","", + /*G0-G7*/ "","","hsc-12vmain-alt1-n","","","bp-cpld-program-en","led-fp-sta-gr", + "led-fp-sta-amb", + /*H0-H7*/ "jtag-program-sel","jtag-cmpl2","wd-disable-n","power-chassis-good","","", + "","", + /*I0-I7*/ "","","","","","","power-button","rtc-battery-voltage-read-enable", + /*J0-J7*/ "","","","","","","","", + /*K0-K7*/ "","","","","","","","", + /*L0-L7*/ "","","","","reset-button","","","", + /*M0-M7*/ "nmi-n","s0-ddr-save","soc-spi-nor-access","presence-cpu0","s0-rtc-lock", + "","","", + /*N0-N7*/ "hpm-fw-recovery","hpm-stby-rst-n","jtag-sel-s0","led-sw-hb", + "jtag-dbgr-prsnt-n","","","", + /*O0-O7*/ "","","","","","","","", + /*P0-P7*/ "ps0-ac-loss-n","ps1-ac-loss-n","","","led-fault","user-mode","jtag-srst-n", + "led-bmc-hb", + /*Q0-Q7*/ "","","","","","","","", + /*R0-R7*/ "","","","","","","","", + /*S0-S7*/ "","","identify-button","led-identify","","spi-nor-access","host0-ready","", + /*T0-T7*/ "","","","","","","","", + /*U0-U7*/ "","","","","","","","", + /*V0-V7*/ "s0-hightemp-n","s0-fault-alert","s0-sys-auth-failure-n", + "host0-reboot-ack-n","s0-fw-boot-ok","host0-shd-req-n", + "host0-shd-ack-n","s0-overtemp-n", + /*W0-W7*/ "ocp-aux-pwren","ocp-main-pwren","ocp-pgood","", + "bmc-ok","bmc-ready","spi0-program-sel","spi0-backup-sel", + /*X0-X7*/ "","","","","","","","", + /*Y0-Y7*/ "","","","vrd-prg-en-n","","","","host0-special-boot", + /*Z0-Z7*/ "","ps0-pgood","ps1-pgood","","","","",""; + + ocp-aux-pwren-hog { + gpio-hog; + gpios = ; + output-high; + line-name = "ocp-aux-pwren"; + }; + +}; + +&gpio1 { + gpio-line-names = + /*18A0-18A7*/ "","","","","","","","", + /*18B0-18B7*/ "","","","","s0-soc-pgood","vga-ft-press-n","emmc-rst-n","s01-uart1-sel", + /*18C0-18C7*/ "uart1-mode0","uart1-mode1","uart2-mode0","uart2-mode1", + "","","","", + /*18D0-18D7*/ "","","","","","","","", + /*18E0-18E3*/ "","","",""; +}; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-ampere-mtmitchell.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-ampere-mtmitchell.dts index 0295f5adcfbc..2b336aa0146d 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-ampere-mtmitchell.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-ampere-mtmitchell.dts @@ -677,6 +677,12 @@ #size-cells = <0>; #gpio-cells = <2>; + gpio-line-names = + "ext-vref-sel","","presence-hdd-bp5-n","presence-hdd-bp6-n", + "","bmc-riser-en-n","bmc-ocp1-en-n","bmc-ocp0-en-n", + "","","","", + "","","",""; + bmc-ocp0-en-hog { gpio-hog; gpios = <7 GPIO_ACTIVE_LOW>; @@ -684,6 +690,16 @@ line-name = "bmc-ocp0-en-n"; }; }; + + fan-controller0@20 { + compatible = "maxim,max31790"; + reg = <0x20>; + }; + + fan-controller1@2f { + compatible = "maxim,max31790"; + reg = <0x2f>; + }; }; &i2c9 { @@ -958,7 +974,7 @@ "fan-fault","psu-fault", "","", "","", - "","", + "gpi0","gpi1", "","", "","", "","", diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-catalina.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-catalina.dts index 82835e96317d..c151984289bc 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-catalina.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-catalina.dts @@ -50,14 +50,14 @@ i2c45 = &i2c0mux5ch1; i2c46 = &i2c0mux5ch2; i2c47 = &i2c0mux5ch3; - i2c48 = &i2c30mux0ch0; - i2c49 = &i2c30mux0ch1; - i2c50 = &i2c30mux0ch2; - i2c51 = &i2c30mux0ch3; - i2c52 = &i2c30mux0ch4; - i2c53 = &i2c30mux0ch5; - i2c54 = &i2c30mux0ch6; - i2c55 = &i2c30mux0ch7; + i2c48 = &i2c5mux0ch0; + i2c49 = &i2c5mux0ch1; + i2c50 = &i2c5mux0ch2; + i2c51 = &i2c5mux0ch3; + i2c52 = &i2c5mux0ch4; + i2c53 = &i2c5mux0ch5; + i2c54 = &i2c5mux0ch6; + i2c55 = &i2c5mux0ch7; }; chosen { @@ -153,6 +153,13 @@ status = "okay"; }; +&mac2 { + status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ncsi3_default>; + use-ncsi; +}; + &mac3 { status = "okay"; pinctrl-names = "default"; @@ -185,6 +192,7 @@ reg = <0x71>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; i2c0mux0ch0: i2c@0 { #address-cells = <1>; @@ -213,6 +221,7 @@ reg = <0x72>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; i2c0mux1ch0: i2c@0 { #address-cells = <1>; @@ -242,79 +251,6 @@ #address-cells = <1>; #size-cells = <0>; reg = <2>; - i2c-mux@70 { - compatible = "nxp,pca9548"; - reg = <0x70>; - #address-cells = <1>; - #size-cells = <0>; - - i2c30mux0ch0: i2c@0 { - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; - }; - i2c30mux0ch1: i2c@1 { - #address-cells = <1>; - #size-cells = <0>; - reg = <1>; - }; - i2c30mux0ch2: i2c@2 { - #address-cells = <1>; - #size-cells = <0>; - reg = <2>; - }; - i2c30mux0ch3: i2c@3 { - #address-cells = <1>; - #size-cells = <0>; - reg = <3>; - }; - i2c30mux0ch4: i2c@4 { - #address-cells = <1>; - #size-cells = <0>; - reg = <4>; - }; - i2c30mux0ch5: i2c@5 { - #address-cells = <1>; - #size-cells = <0>; - reg = <5>; - }; - i2c30mux0ch6: i2c@6 { - #address-cells = <1>; - #size-cells = <0>; - reg = <6>; - // HDD FRU EEPROM - eeprom@52 { - compatible = "atmel,24c64"; - reg = <0x52>; - }; - }; - i2c30mux0ch7: i2c@7 { - #address-cells = <1>; - #size-cells = <0>; - reg = <7>; - - power-sensor@40 { - compatible = "ti,ina230"; - reg = <0x40>; - shunt-resistor = <2000>; - }; - power-sensor@41 { - compatible = "ti,ina230"; - reg = <0x41>; - shunt-resistor = <2000>; - }; - power-sensor@44 { - compatible = "ti,ina230"; - reg = <0x44>; - shunt-resistor = <2000>; - }; - power-sensor@45 { - compatible = "ti,ina230"; - reg = <0x45>; - shunt-resistor = <2000>; - }; - }; - }; }; i2c0mux1ch3: i2c@3 { #address-cells = <1>; @@ -328,6 +264,7 @@ reg = <0x73>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; i2c0mux2ch0: i2c@0 { #address-cells = <1>; @@ -356,6 +293,7 @@ reg = <0x75>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; i2c0mux3ch0: i2c@0 { #address-cells = <1>; @@ -384,6 +322,7 @@ reg = <0x76>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; i2c0mux4ch0: i2c@0 { #address-cells = <1>; @@ -426,6 +365,7 @@ reg = <0x77>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; i2c0mux5ch0: i2c@0 { #address-cells = <1>; @@ -512,12 +452,12 @@ power-monitor@42 { compatible = "lltc,ltc4287"; reg = <0x42>; - shunt-resistor-micro-ohms = <200>; + shunt-resistor-micro-ohms = <100>; }; power-monitor@43 { compatible = "lltc,ltc4287"; reg = <0x43>; - shunt-resistor-micro-ohms = <200>; + shunt-resistor-micro-ohms = <100>; }; }; i2c1mux0ch5: i2c@5 { @@ -593,8 +533,6 @@ reg = <0x20>; gpio-controller; #gpio-cells = <2>; - interrupt-parent = <&gpio0>; - interrupts = ; }; // Module 1 IOEXP @@ -603,8 +541,6 @@ reg = <0x21>; gpio-controller; #gpio-cells = <2>; - interrupt-parent = <&gpio0>; - interrupts = ; }; // HMC IOEXP @@ -613,8 +549,6 @@ reg = <0x27>; gpio-controller; #gpio-cells = <2>; - interrupt-parent = <&gpio0>; - interrupts = ; }; // Module 0 EEPROM @@ -640,6 +574,81 @@ &i2c5 { status = "okay"; + + i2c-mux@70 { + compatible = "nxp,pca9548"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + i2c-mux-idle-disconnect; + + i2c5mux0ch0: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + }; + i2c5mux0ch1: i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + }; + i2c5mux0ch2: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <2>; + }; + i2c5mux0ch3: i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <3>; + }; + i2c5mux0ch4: i2c@4 { + #address-cells = <1>; + #size-cells = <0>; + reg = <4>; + }; + i2c5mux0ch5: i2c@5 { + #address-cells = <1>; + #size-cells = <0>; + reg = <5>; + }; + i2c5mux0ch6: i2c@6 { + #address-cells = <1>; + #size-cells = <0>; + reg = <6>; + // HDD FRU EEPROM + eeprom@52 { + compatible = "atmel,24c64"; + reg = <0x52>; + }; + }; + i2c5mux0ch7: i2c@7 { + #address-cells = <1>; + #size-cells = <0>; + reg = <7>; + + power-sensor@40 { + compatible = "ti,ina230"; + reg = <0x40>; + shunt-resistor = <2000>; + }; + power-sensor@41 { + compatible = "ti,ina230"; + reg = <0x41>; + shunt-resistor = <2000>; + }; + power-sensor@44 { + compatible = "ti,ina230"; + reg = <0x44>; + shunt-resistor = <2000>; + }; + power-sensor@45 { + compatible = "ti,ina230"; + reg = <0x45>; + shunt-resistor = <2000>; + }; + }; + }; }; &i2c6 { @@ -834,9 +843,9 @@ }; // OCP NIC1 FRU EEPROM - eeprom@50 { + eeprom@52 { compatible = "atmel,24c64"; - reg = <0x50>; + reg = <0x52>; }; }; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-harma.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-harma.dts index cf3f807a38fe..9cb511a846e3 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-harma.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-harma.dts @@ -135,10 +135,6 @@ use-ncsi; }; -&rtc { - status = "okay"; -}; - &fmc { status = "okay"; @@ -397,12 +393,6 @@ reg = <0x31>; gpio-controller; #gpio-cells = <2>; - - gpio-line-names = - "","","","", - "","","presence-cmm","", - "","","","", - "","","",""; }; // PTTV FRU @@ -426,12 +416,6 @@ reg = <0x31>; gpio-controller; #gpio-cells = <2>; - - gpio-line-names = - "","","","", - "","","presence-cmm","", - "","","","", - "","","",""; }; // Aegis FRU @@ -506,6 +490,11 @@ #address-cells = <1>; #size-cells = <0>; reg = <3>; + + rtc@51 { + compatible = "nxp,pcf8563"; + reg = <0x51>; + }; }; }; }; @@ -565,7 +554,7 @@ /*B0-B7*/ "","","","", "bmc-spi-mux-select-0","led-identify","","", /*C0-C7*/ "reset-cause-platrst","","","","", - "cpu0-err-alert","","", + "power-hsc-good","power-chassis-good","", /*D0-D7*/ "","","sol-uart-select","","","","","", /*E0-E7*/ "","","","","","","","", /*F0-F7*/ "","","","","","","","", @@ -584,14 +573,16 @@ /*O0-O7*/ "","","","","","","","", /*P0-P7*/ "power-button","power-host-control", "reset-button","","led-power","","","", - /*Q0-Q7*/ "","","","","","power-chassis-control","","", + /*Q0-Q7*/ + "","","","", + "","power-chassis-control","","uart-switch-button", /*R0-R7*/ "","","","","","","","", /*S0-S7*/ "","","","","","","","", /*T0-T7*/ "","","","","","","","", /*U0-U7*/ "","","","","","","led-identify-gate","", /*V0-V7*/ "","","","", "rtc-battery-voltage-read-enable","", - "power-chassis-good","", + "","", /*W0-W7*/ "","","","","","","","", /*X0-X7*/ "","","","","","","","", /*Y0-Y7*/ "","","","","","","","", @@ -672,7 +663,7 @@ "presence-asic-modules-0","rt-cpu0-p1-force-enable", "presence-asic-modules-1","bios-debug-msg-disable", "","uart-control-buffer-select", - "","ac-control-n", + "presence-cmm","ac-control-n", /*G0-G3 line 96-103*/ "FM_CPU_CORETYPE2","", "FM_CPU_CORETYPE1","", @@ -684,7 +675,7 @@ "FM_BOARD_REV_ID2","", "FM_BOARD_REV_ID1","", /*H0-H3 line 112-119*/ - "FM_BOARD_REV_ID0","", + "FM_BOARD_REV_ID0","reset-control-cmos-clear", "","","","","","", /*H4-H7 line 120-127*/ "","", @@ -699,7 +690,7 @@ /*I4-I7 line 136-143*/ "","","","","","","","", /*J0-J3 line 144-151*/ - "","","","","","","","", + "","","power-card-enable","","","","","", /*J4-J7 line 152-159*/ "SLOT_ID_BCB_0","", "SLOT_ID_BCB_1","", @@ -715,9 +706,15 @@ "cpu0-thermtrip-alert","", "reset-cause-pcie","", /*L4-L7 line 184-191*/ - "pvdd11-ocp-alert","","","","","","","", + "pvdd11-ocp-alert","", + "power-fault-n","", + "asic0-card-type-detection0-n","", + "asic0-card-type-detection1-n","", /*M0-M3 line 192-199*/ - "","","","","","","","", + "asic0-card-type-detection2-n","", + "uart-switch-lsb","", + "uart-switch-msb","", + "","", /*M4-M7 line 200-207*/ "","","","","","","","", /*N0-N3 line 208-215*/ diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-minerva.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-minerva.dts index 41e2246cfbd1..ef96b17becb2 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-minerva.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-minerva.dts @@ -23,6 +23,32 @@ i2c19 = &imux19; i2c20 = &imux20; i2c21 = &imux21; + i2c22 = &imux22; + i2c23 = &imux23; + i2c24 = &imux24; + i2c25 = &imux25; + i2c26 = &imux26; + i2c27 = &imux27; + i2c28 = &imux28; + i2c29 = &imux29; + i2c30 = &imux30; + i2c31 = &imux31; + i2c32 = &imux32; + i2c33 = &imux33; + i2c34 = &imux34; + i2c35 = &imux35; + i2c36 = &imux36; + i2c37 = &imux37; + i2c38 = &imux38; + i2c39 = &imux39; + i2c40 = &imux40; + i2c41 = &imux41; + i2c42 = &imux42; + i2c43 = &imux43; + i2c44 = &imux44; + i2c45 = &imux45; + i2c46 = &imux46; + i2c47 = &imux47; spi1 = &spi_gpio; }; @@ -75,6 +101,11 @@ gpios = <&leds_gpio 10 GPIO_ACTIVE_LOW>; default-state = "off"; }; + + led-5 { + label = "bmc_ready_noled"; + gpios = <&sgpiom0 141 (GPIO_ACTIVE_HIGH|GPIO_TRANSITORY)>; + }; }; spi_gpio: spi { @@ -182,6 +213,63 @@ gpio-controller; #gpio-cells = <2>; }; + + gpio@11 { + compatible = "nxp,pca9555"; + reg = <0x11>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <238 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "PWRGD_P24V_SMPWROK", "P1V5_PWROK", + "P3V3_PWROK", "P5V_PWROK", + "P12V_SCM_PWROK", "P12V_PWROK", + "P24V_PWROK", "P48V_HSC_PWROK", + "ERR_GPIO_IRQ", "TMP75_ALERT_N", + "BMC_PWROK", "P12V_INA230_ALERT_N", + "P24V_INA230_ALERT_N","", + "P48V_HSC_ALERT_N", "P1V05_PWROK"; + }; + + gpio@12 { + compatible = "nxp,pca9555"; + reg = <0x12>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <240 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "P1V05_PWR_FAIL", "P1V5_PWR_FAIL", + "P24V_PWR_FAIL", "P24V_SM_PWR_FAIL", + "IRQ_NW0/1/2_N", "IRQ_NW3/4/5_N", + "RTC_INT_N_R", "ERR_GPIO_IRQ", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@13 { + compatible = "nxp,pca9555"; + reg = <0x13>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <242 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "", "", + "", "", + "", "", + "", "", + "RACKMON_A_1", "RACKMON_A_2", + "RACKMON_B_1", "RACKMON_B_2", + "", "", + "", ""; + }; }; &i2c1 { @@ -213,54 +301,8 @@ #size-cells = <0>; i2c-mux-idle-disconnect; - imux16: i2c@0 { - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; - - eeprom@50 { - compatible = "atmel,24c128"; - reg = <0x50>; - }; - - pwm@5e{ - compatible = "max31790"; - reg = <0x5e>; - #address-cells = <1>; - #size-cells = <0>; - }; - - power-sensor@40 { - compatible = "ti,ina238"; - reg = <0x40>; - shunt-resistor = <1000>; - }; - - power-sensor@41 { - compatible = "ti,ina238"; - reg = <0x41>; - shunt-resistor = <1000>; - }; - - power-sensor@44 { - compatible = "ti,ina238"; - reg = <0x44>; - shunt-resistor = <1000>; - }; - - power-sensor@45 { - compatible = "ti,ina238"; - reg = <0x45>; - shunt-resistor = <1000>; - }; - - temperature-sensor@4b { - compatible = "ti,tmp75"; - reg = <0x4b>; - }; - }; - - imux17: i2c@1 { + // FCB 1 + imux16: i2c@1 { #address-cells = <1>; #size-cells = <0>; reg = <1>; @@ -305,12 +347,88 @@ compatible = "ti,tmp75"; reg = <0x4b>; }; - }; - imux18: i2c@2 { + gpio@11 { + compatible = "nxp,pca9555"; + reg = <0x11>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <218 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "P48V_FAN1_PWRGD_R", "P48V_FAN2_PWRGD_R", + "P48V_FAN3_PWRGD_R", "P48V_FAN4_PWRGD_R", + "FCB_1_P48V_ZONE0_PWRGD_R", "FCB_1_P48V_ZONE1_PWRGD_R", + "FCB_1_PWRGD_P3V3_R", "", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@12 { + compatible = "nxp,pca9555"; + reg = <0x12>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <218 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "INA238_FAN1_ALERT_N", "INA238_FAN2_ALERT_N", + "INA238_FAN3_ALERT_N", "INA238_FAN4_ALERT_N", + "FCB_1_TMP75_ALERT_N", "", + "", "", + "FAN1_PRSNT", "FAN2_PRSNT", + "FAN3_PRSNT", "FAN4_PRSNT", + "", "", + "", ""; + }; + + gpio@13 { + compatible = "nxp,pca9555"; + reg = <0x13>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <218 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FAN1_IL_TACH_ALERT", "FAN1_OL_TACH_ALERT", + "FAN2_IL_TACH_ALERT", "FAN2_OL_TACH_ALERT", + "FAN3_IL_TACH_ALERT", "FAN3_OL_TACH_ALERT", + "FAN4_IL_TACH_ALERT", "FAN4_IL_TACH_ALERT", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@17 { + compatible = "nxp,pca9555"; + reg = <0x17>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <218 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FCB_1_P1V0_POWER_FAIL", "FCB_1_P1V8_POWER_FAIL", + "FCB_1_P48V_ZONE0_POWER_FAIL", "FAN1_POWER_FAIL", + "FAN2_POWER_FAIL", "FAN3_POWER_FAIL", + "FAN4_POWER_FAIL", "", + "", "", + "", "", + "", "", + "", ""; + }; + }; + // FCB 2 + imux17: i2c@0 { #address-cells = <1>; #size-cells = <0>; - reg = <2>; + reg = <0>; eeprom@50 { compatible = "atmel,24c128"; @@ -352,9 +470,85 @@ compatible = "ti,tmp75"; reg = <0x4b>; }; - }; - imux19: i2c@3 { + gpio@11 { + compatible = "nxp,pca9555"; + reg = <0x11>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <220 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "P48V_FAN5_PWRGD_R", "P48V_FAN6_PWRGD_R", + "P48V_FAN7_PWRGD_R", "P48V_FAN8_PWRGD_R", + "FCB_2_P48V_ZONE0_PWRGD_R", "FCB_2_P48V_ZONE1_PWRGD_R", + "FCB_2_PWRGD_P3V3_R", "", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@12 { + compatible = "nxp,pca9555"; + reg = <0x12>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <220 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "INA238_FAN5_ALERT_N", "INA238_FAN6_ALERT_N", + "INA238_FAN7_ALERT_N", "INA238_FAN8_ALERT_N", + "FCB_2_TMP75_ALERT_N", "", + "", "", + "FAN5_PRSNT", "FAN6_PRSNT", + "FAN7_PRSNT", "FAN8_PRSNT", + "", "", + "", ""; + }; + + gpio@13 { + compatible = "nxp,pca9555"; + reg = <0x13>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <220 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FAN5_IL_TACH_ALERT", "FAN5_OL_TACH_ALERT", + "FAN6_IL_TACH_ALERT", "FAN6_OL_TACH_ALERT", + "FAN7_IL_TACH_ALERT", "FAN7_OL_TACH_ALERT", + "FAN8_IL_TACH_ALERT", "FAN8_IL_TACH_ALERT", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@17 { + compatible = "nxp,pca9555"; + reg = <0x17>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <220 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FCB_2_P1V0_POWER_FAIL", "FCB_2_P1V8_POWER_FAIL", + "FCB_2_P48V_ZONE0_POWER_FAIL", "FAN5_POWER_FAIL", + "FAN6_POWER_FAIL", "FAN7_POWER_FAIL", + "FAN8_POWER_FAIL", "", + "", "", + "", "", + "", "", + "", ""; + }; + }; + // FCB 3 + imux18: i2c@3 { #address-cells = <1>; #size-cells = <0>; reg = <3>; @@ -399,9 +593,208 @@ compatible = "ti,tmp75"; reg = <0x4b>; }; - }; - imux20: i2c@5 { + gpio@11 { + compatible = "nxp,pca9555"; + reg = <0x11>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <230 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "P48V_FAN9_PWRGD_R", "P48V_FAN10_PWRGD_R", + "P48V_FAN11_PWRGD_R", "P48V_FAN12_PWRGD_R", + "FCB_3_P48V_ZONE0_PWRGD_R", "FCB_3_P48V_ZONE1_PWRGD_R", + "FCB_3_PWRGD_P3V3_R", "", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@12 { + compatible = "nxp,pca9555"; + reg = <0x12>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <230 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "INA238_FAN9_ALERT_N", "INA238_FAN10_ALERT_N", + "INA238_FAN11_ALERT_N", "INA238_FAN12_ALERT_N", + "FCB_3_TMP75_ALERT_N", "", + "", "", + "FAN9_PRSNT", "FAN10_PRSNT", + "FAN11_PRSNT", "FAN12_PRSNT", + "", "", + "", ""; + }; + + gpio@13 { + compatible = "nxp,pca9555"; + reg = <0x13>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <230 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FAN9_IL_TACH_ALERT", "FAN9_OL_TACH_ALERT", + "FAN10_IL_TACH_ALERT", "FAN10_OL_TACH_ALERT", + "FAN11_IL_TACH_ALERT", "FAN11_OL_TACH_ALERT", + "FAN12_IL_TACH_ALERT", "FAN12_IL_TACH_ALERT", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@17 { + compatible = "nxp,pca9555"; + reg = <0x17>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <230 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FCB_3_P1V0_POWER_FAIL", "FCB_3_P1V8_POWER_FAIL", + "FCB_3_P48V_ZONE0_POWER_FAIL", "FAN9_POWER_FAIL", + "FAN10_POWER_FAIL", "FAN11_POWER_FAIL", + "FAN12_POWER_FAIL", "", + "", "", + "", "", + "", "", + "", ""; + }; + }; + // FCB 4 + imux19: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <2>; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + pwm@5e{ + compatible = "max31790"; + reg = <0x5e>; + #address-cells = <1>; + #size-cells = <0>; + }; + + power-sensor@40 { + compatible = "ti,ina238"; + reg = <0x40>; + shunt-resistor = <1000>; + }; + + power-sensor@41 { + compatible = "ti,ina238"; + reg = <0x41>; + shunt-resistor = <1000>; + }; + + power-sensor@44 { + compatible = "ti,ina238"; + reg = <0x44>; + shunt-resistor = <1000>; + }; + + power-sensor@45 { + compatible = "ti,ina238"; + reg = <0x45>; + shunt-resistor = <1000>; + }; + + temperature-sensor@4b { + compatible = "ti,tmp75"; + reg = <0x4b>; + }; + + gpio@11 { + compatible = "nxp,pca9555"; + reg = <0x11>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <232 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "P48V_FAN13_PWRGD_R", "P48V_FAN14_PWRGD_R", + "P48V_FAN15_PWRGD_R", "P48V_FAN16_PWRGD_R", + "FCB_4_P48V_ZONE0_PWRGD_R", "FCB_4_P48V_ZONE1_PWRGD_R", + "FCB_4_PWRGD_P3V3_R", "", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@12 { + compatible = "nxp,pca9555"; + reg = <0x12>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <232 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "INA238_FAN13_ALERT_N", "INA238_FAN14_ALERT_N", + "INA238_FAN15_ALERT_N", "INA238_FAN16_ALERT_N", + "FCB_4_TMP75_ALERT_N", "", + "", "", + "FAN13_PRSNT", "FAN14_PRSNT", + "FAN15_PRSNT", "FAN16_PRSNT", + "", "", + "", ""; + }; + + gpio@13 { + compatible = "nxp,pca9555"; + reg = <0x13>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <232 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FAN13_IL_TACH_ALERT", "FAN13_OL_TACH_ALERT", + "FAN14_IL_TACH_ALERT", "FAN14_OL_TACH_ALERT", + "FAN15_IL_TACH_ALERT", "FAN15_OL_TACH_ALERT", + "FAN16_IL_TACH_ALERT", "FAN16_IL_TACH_ALERT", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@17 { + compatible = "nxp,pca9555"; + reg = <0x17>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <232 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FCB_4_P1V0_POWER_FAIL", "FCB_4_P1V8_POWER_FAIL", + "FCB_4_P48V_ZONE0_POWER_FAIL", "FAN13_POWER_FAIL", + "FAN14_POWER_FAIL", "FAN15_POWER_FAIL", + "FAN16_POWER_FAIL", "", + "", "", + "", "", + "", "", + "", ""; + }; + }; + // FCB 5 + imux20: i2c@4 { #address-cells = <1>; #size-cells = <0>; reg = <4>; @@ -445,9 +838,85 @@ compatible = "ti,tmp75"; reg = <0x4b>; }; - }; - imux21: i2c@4 { + gpio@11 { + compatible = "nxp,pca9555"; + reg = <0x11>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <254 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "P48V_FAN20_PWRGD_R", "P48V_FAN19_PWRGD_R", + "P48V_FAN18_PWRGD_R", "P48V_FAN17_PWRGD_R", + "FCB_5_P48V_ZONE0_PWRGD_R", "FCB_5_P48V_ZONE1_PWRGD_R", + "FCB_5_PWRGD_P3V3_R", "", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@12 { + compatible = "nxp,pca9555"; + reg = <0x12>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <254 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "INA238_FAN20_ALERT_N", "INA238_FAN19_ALERT_N", + "INA238_FAN18_ALERT_N", "INA238_FAN17_ALERT_N", + "FCB_5_TMP75_ALERT_N", "", + "", "", + "FAN20_PRSNT", "FAN19_PRSNT", + "FAN18_PRSNT", "FAN17_PRSNT", + "", "", + "", ""; + }; + + gpio@13 { + compatible = "nxp,pca9555"; + reg = <0x13>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <254 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FAN20_IL_TACH_ALERT", "FAN20_OL_TACH_ALERT", + "FAN19_IL_TACH_ALERT", "FAN19_OL_TACH_ALERT", + "FAN18_IL_TACH_ALERT", "FAN18_OL_TACH_ALERT", + "FAN17_IL_TACH_ALERT", "FAN17_OL_TACH_ALERT", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@17 { + compatible = "nxp,pca9555"; + reg = <0x17>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <254 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FCB_5_P1V0_POWER_FAIL", "FCB_5_P1V8_POWER_FAIL", + "FCB_5_P48V_ZONE0_POWER_FAIL", "FAN20_POWER_FAIL", + "FAN19_POWER_FAIL", "FAN18_POWER_FAIL", + "FAN17_POWER_FAIL", "", + "", "", + "", "", + "", "", + "", ""; + }; + }; + // FCB 6 + imux21: i2c@5 { #address-cells = <1>; #size-cells = <0>; reg = <5>; @@ -491,24 +960,316 @@ compatible = "ti,tmp75"; reg = <0x4b>; }; + + gpio@11 { + compatible = "nxp,pca9555"; + reg = <0x11>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <252 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "P48V_FAN24_PWRGD_R", "P48V_FAN23_PWRGD_R", + "P48V_FAN22_PWRGD_R", "P48V_FAN21_PWRGD_R", + "FCB_6_P48V_ZONE0_PWRGD_R", "FCB_6_P48V_ZONE1_PWRGD_R", + "FCB_6_PWRGD_P3V3_R", "", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@12 { + compatible = "nxp,pca9555"; + reg = <0x12>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <252 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "INA238_FAN24_ALERT_N", "INA238_FAN23_ALERT_N", + "INA238_FAN22_ALERT_N", "INA238_FAN21_ALERT_N", + "FCB_6_TMP75_ALERT_N", "", + "", "", + "FAN24_PRSNT", "FAN23_PRSNT", + "FAN22_PRSNT", "FAN21_PRSNT", + "", "", + "", ""; + }; + + gpio@13 { + compatible = "nxp,pca9555"; + reg = <0x13>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <252 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FAN24_IL_TACH_ALERT", "FAN24_OL_TACH_ALERT", + "FAN23_IL_TACH_ALERT", "FAN23_OL_TACH_ALERT", + "FAN22_IL_TACH_ALERT", "FAN22_OL_TACH_ALERT", + "FAN21_IL_TACH_ALERT", "FAN21_OL_TACH_ALERT", + "", "", + "", "", + "", "", + "", ""; + }; + + gpio@17 { + compatible = "nxp,pca9555"; + reg = <0x17>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&sgpiom0>; + interrupts = <252 IRQ_TYPE_LEVEL_LOW>; + + gpio-line-names = + "FCB_6_P1V0_POWER_FAIL", "FCB_6_P1V8_POWER_FAIL", + "FCB_6_P48V_ZONE0_POWER_FAIL", "FAN24_POWER_FAIL", + "FAN23_POWER_FAIL", "FAN22_POWER_FAIL", + "FAN21_POWER_FAIL", "", + "", "", + "", "", + "", "", + "", ""; + }; + }; + + imux22: i2c@6 { + #address-cells = <1>; + #size-cells = <0>; + reg = <6>; + }; + + imux23: i2c@7 { + #address-cells = <1>; + #size-cells = <0>; + reg = <7>; }; }; }; &i2c3 { status = "okay"; + + i2c-mux@72 { + compatible = "nxp,pca9545"; + reg = <0x72>; + #address-cells = <1>; + #size-cells = <0>; + + imux24: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux25: i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux26: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <2>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux27: i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <3>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + }; }; &i2c4 { status = "okay"; + + i2c-mux@72 { + compatible = "nxp,pca9545"; + reg = <0x72>; + #address-cells = <1>; + #size-cells = <0>; + + imux28: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux29: i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux30: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <2>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux31: i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <3>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + }; }; &i2c5 { status = "okay"; + + i2c-mux@72 { + compatible = "nxp,pca9545"; + reg = <0x72>; + #address-cells = <1>; + #size-cells = <0>; + + imux32: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux33: i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux34: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <2>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux35: i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <3>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + }; }; &i2c6 { status = "okay"; + + i2c-mux@72 { + compatible = "nxp,pca9545"; + reg = <0x72>; + #address-cells = <1>; + #size-cells = <0>; + + imux36: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux37: i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux38: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <2>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux39: i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <3>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + }; }; &i2c7 { @@ -531,14 +1292,111 @@ compatible = "nxp,pcf8563"; reg = <0x51>; }; + + rtc@68 { + compatible = "dallas,ds1339"; + reg = <0x68>; + }; }; &i2c12 { status = "okay"; + + i2c-mux@70 { + compatible = "nxp,pca9545"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + imux40: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux41: i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux42: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <2>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux43: i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <3>; + }; + }; }; &i2c13 { status = "okay"; + + i2c-mux@70 { + compatible = "nxp,pca9545"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + imux44: i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux45: i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux46: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <2>; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux47: i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <3>; + }; + }; }; &i2c14 { @@ -627,7 +1485,6 @@ gpio-line-names = /*"input pin","output pin"*/ /*A0 - A7*/ - "PRSNT_MTIA_BLADE0_N","PWREN_MTIA_BLADE0_EN_N", "PRSNT_MTIA_BLADE1_N","PWREN_MTIA_BLADE1_EN_N", "PRSNT_MTIA_BLADE2_N","PWREN_MTIA_BLADE2_EN_N", "PRSNT_MTIA_BLADE3_N","PWREN_MTIA_BLADE3_EN_N", @@ -635,8 +1492,8 @@ "PRSNT_MTIA_BLADE5_N","PWREN_MTIA_BLADE5_EN_N", "PRSNT_MTIA_BLADE6_N","PWREN_MTIA_BLADE6_EN_N", "PRSNT_MTIA_BLADE7_N","PWREN_MTIA_BLADE7_EN_N", - /*B0 - B7*/ "PRSNT_MTIA_BLADE8_N","PWREN_MTIA_BLADE8_EN_N", + /*B0 - B7*/ "PRSNT_MTIA_BLADE9_N","PWREN_MTIA_BLADE9_EN_N", "PRSNT_MTIA_BLADE10_N","PWREN_MTIA_BLADE10_EN_N", "PRSNT_MTIA_BLADE11_N","PWREN_MTIA_BLADE11_EN_N", @@ -644,80 +1501,80 @@ "PRSNT_MTIA_BLADE13_N","PWREN_MTIA_BLADE13_EN_N", "PRSNT_MTIA_BLADE14_N","PWREN_MTIA_BLADE14_EN_N", "PRSNT_MTIA_BLADE15_N","PWREN_MTIA_BLADE15_EN_N", + "PRSNT_MTIA_BLADE16_N","PWREN_MTIA_BLADE16_EN_N", /*C0 - C7*/ - "PRSNT_NW_BLADE0_N","PWREN_NW_BLADE0_EN_N", "PRSNT_NW_BLADE1_N","PWREN_NW_BLADE1_EN_N", "PRSNT_NW_BLADE2_N","PWREN_NW_BLADE2_EN_N", "PRSNT_NW_BLADE3_N","PWREN_NW_BLADE3_EN_N", "PRSNT_NW_BLADE4_N","PWREN_NW_BLADE4_EN_N", "PRSNT_NW_BLADE5_N","PWREN_NW_BLADE5_EN_N", - "PRSNT_FCB_TOP_0_N","PWREN_MTIA_BLADE0_HSC_EN_N", - "PRSNT_FCB_TOP_1_N","PWREN_MTIA_BLADE1_HSC_EN_N", + "PRSNT_NW_BLADE6_N","PWREN_NW_BLADE6_EN_N", + "PRSNT_FCB_1_N","PWREN_MTIA_BLADE1_HSC_EN_N", + "PRSNT_FCB_2_N","PWREN_MTIA_BLADE2_HSC_EN_N", /*D0 - D7*/ - "PRSNT_FCB_MIDDLE_0_N","PWREN_MTIA_BLADE2_HSC_EN_N", - "PRSNT_FCB_MIDDLE_1_N","PWREN_MTIA_BLADE3_HSC_EN_N", - "PRSNT_FCB_BOTTOM_1_N","PWREN_MTIA_BLADE4_HSC_EN_N", - "PRSNT_FCB_BOTTOM_0_N","PWREN_MTIA_BLADE5_HSC_EN_N", - "PWRGD_MTIA_BLADE0_PWROK_N","PWREN_MTIA_BLADE6_HSC_EN_N", + "PRSNT_FCB_3_N","PWREN_MTIA_BLADE3_HSC_EN_N", + "PRSNT_FCB_4_N","PWREN_MTIA_BLADE4_HSC_EN_N", + "PRSNT_FCB_6_N","PWREN_MTIA_BLADE5_HSC_EN_N", + "PRSNT_FCB_5_N","PWREN_MTIA_BLADE6_HSC_EN_N", "PWRGD_MTIA_BLADE1_PWROK_N","PWREN_MTIA_BLADE7_HSC_EN_N", "PWRGD_MTIA_BLADE2_PWROK_N","PWREN_MTIA_BLADE8_HSC_EN_N", "PWRGD_MTIA_BLADE3_PWROK_N","PWREN_MTIA_BLADE9_HSC_EN_N", - /*E0 - E7*/ "PWRGD_MTIA_BLADE4_PWROK_N","PWREN_MTIA_BLADE10_HSC_EN_N", + /*E0 - E7*/ "PWRGD_MTIA_BLADE5_PWROK_N","PWREN_MTIA_BLADE11_HSC_EN_N", "PWRGD_MTIA_BLADE6_PWROK_N","PWREN_MTIA_BLADE12_HSC_EN_N", "PWRGD_MTIA_BLADE7_PWROK_N","PWREN_MTIA_BLADE13_HSC_EN_N", "PWRGD_MTIA_BLADE8_PWROK_N","PWREN_MTIA_BLADE14_HSC_EN_N", "PWRGD_MTIA_BLADE9_PWROK_N","PWREN_MTIA_BLADE15_HSC_EN_N", - "PWRGD_MTIA_BLADE10_PWROK_N","PWREN_NW_BLADE0_HSC_EN_N", + "PWRGD_MTIA_BLADE10_PWROK_N","PWREN_MTIA_BLADE16_HSC_EN_N", "PWRGD_MTIA_BLADE11_PWROK_N","PWREN_NW_BLADE1_HSC_EN_N", - /*F0 - F7*/ "PWRGD_MTIA_BLADE12_PWROK_N","PWREN_NW_BLADE2_HSC_EN_N", + /*F0 - F7*/ "PWRGD_MTIA_BLADE13_PWROK_N","PWREN_NW_BLADE3_HSC_EN_N", "PWRGD_MTIA_BLADE14_PWROK_N","PWREN_NW_BLADE4_HSC_EN_N", "PWRGD_MTIA_BLADE15_PWROK_N","PWREN_NW_BLADE5_HSC_EN_N", - "PWRGD_NW_BLADE0_PWROK_N","PWREN_FCB_TOP_0_EN_N", - "PWRGD_NW_BLADE1_PWROK_N","PWREN_FCB_TOP_1_EN_N", - "PWRGD_NW_BLADE2_PWROK_N","PWREN_FCB_MIDDLE_0_EN_N", - "PWRGD_NW_BLADE3_PWROK_N","PWREN_FCB_MIDDLE_1_EN_N", + "PWRGD_MTIA_BLADE16_PWROK_N","PWREN_NW_BLADE6_HSC_EN_N", + "PWRGD_NW_BLADE1_PWROK_N","PWREN_SGPIO_FCB_2_EN_N", + "PWRGD_NW_BLADE2_PWROK_N","PWREN_SGPIO_FCB_1_EN_N", + "PWRGD_NW_BLADE3_PWROK_N","PWREN_SGPIO_FCB_4_EN_N", + "PWRGD_NW_BLADE4_PWROK_N","PWREN_SGPIO_FCB_3_EN_N", /*G0 - G7*/ - "PWRGD_NW_BLADE4_PWROK_N","PWREN_FCB_BOTTOM_1_EN_N", - "PWRGD_NW_BLADE5_PWROK_N","PWREN_FCB_BOTTOM_0_EN_N", - "PWRGD_FCB_TOP_0_PWROK_N","FM_CMM_AC_CYCLE_N", - "PWRGD_FCB_TOP_1_PWROK_N","MGMT_SFP_TX_DIS", - "PWRGD_FCB_MIDDLE_0_PWROK_N","FM_MDIO_SW_SEL", - "PWRGD_FCB_MIDDLE_1_PWROK_N","FM_P24V_SMPWR_EN", - "PWRGD_FCB_BOTTOM_1_PWROK_N","", - "PWRGD_FCB_BOTTOM_0_PWROK_N","", + "PWRGD_NW_BLADE5_PWROK_N","PWREN_SGPIO_FCB_5_EN_N", + "PWRGD_NW_BLADE6_PWROK_N","PWREN_SGPIO_FCB_6_EN_N", + "PWRGD_FCB_1","FM_BMC_RST_RTCRST_R", + "PWRGD_FCB_2","", + "PWRGD_FCB_3","FM_MDIO_SW_SEL", + "PWRGD_FCB_4","FM_P24V_SMPWR_EN", + "PWRGD_FCB_6","", + "PWRGD_FCB_5","", /*H0 - H7*/ - "LEAK_DETECT_MTIA_BLADE0_N","", "LEAK_DETECT_MTIA_BLADE1_N","", "LEAK_DETECT_MTIA_BLADE2_N","", "LEAK_DETECT_MTIA_BLADE3_N","", "LEAK_DETECT_MTIA_BLADE4_N","", "LEAK_DETECT_MTIA_BLADE5_N","", "LEAK_DETECT_MTIA_BLADE6_N","", - "LEAK_DETECT_MTIA_BLADE7_N","", + "LEAK_DETECT_MTIA_BLADE7_N","ERR_INJECT_CMM_PWR_FAIL_N", + "LEAK_DETECT_MTIA_BLADE8_N","", /*I0 - I7*/ - "LEAK_DETECT_MTIA_BLADE8_N","RST_I2CRST_FCB_BOTTOM_1_N", - "LEAK_DETECT_MTIA_BLADE9_N","RST_I2CRST_FCB_BOTTOM_0_N", - "LEAK_DETECT_MTIA_BLADE10_N","RST_I2CRST_FCB_MIDDLE_0_N", - "LEAK_DETECT_MTIA_BLADE11_N","RST_I2CRST_FCB_MIDDLE_1_N", - "LEAK_DETECT_MTIA_BLADE12_N","RST_I2CRST_FCB_TOP_0_N", - "LEAK_DETECT_MTIA_BLADE13_N","RST_I2CRST_FCB_TOP_1_N", - "LEAK_DETECT_MTIA_BLADE14_N","BMC_READY", - "LEAK_DETECT_MTIA_BLADE15_N","FM_88E6393X_BIN_UPDATE_EN_N", + "LEAK_DETECT_MTIA_BLADE9_N","RST_I2CRST_FCB_5_N", + "LEAK_DETECT_MTIA_BLADE10_N","RST_I2CRST_FCB_6_N", + "LEAK_DETECT_MTIA_BLADE11_N","RST_I2CRST_FCB_4_N", + "LEAK_DETECT_MTIA_BLADE12_N","RST_I2CRST_FCB_3_N", + "LEAK_DETECT_MTIA_BLADE13_N","RST_I2CRST_FCB_2_N", + "LEAK_DETECT_MTIA_BLADE14_N","RST_I2CRST_FCB_1_N", + "LEAK_DETECT_MTIA_BLADE15_N","BMC_READY", + "LEAK_DETECT_MTIA_BLADE16_N","FM_88E6393X_BIN_UPDATE_EN_N", /*J0 - J7*/ - "LEAK_DETECT_NW_BLADE0_N","WATER_VALVE_CLOSED_N", - "LEAK_DETECT_NW_BLADE1_N","", + "LEAK_DETECT_NW_BLADE1_N","WATER_VALVE_CLOSED_N", "LEAK_DETECT_NW_BLADE2_N","", "LEAK_DETECT_NW_BLADE3_N","", "LEAK_DETECT_NW_BLADE4_N","", "LEAK_DETECT_NW_BLADE5_N","", - "PWRGD_MTIA_BLADE0_HSC_PWROK_N","", + "LEAK_DETECT_NW_BLADE6_N","", "PWRGD_MTIA_BLADE1_HSC_PWROK_N","", - /*K0 - K7*/ "PWRGD_MTIA_BLADE2_HSC_PWROK_N","", + /*K0 - K7*/ "PWRGD_MTIA_BLADE3_HSC_PWROK_N","", "PWRGD_MTIA_BLADE4_HSC_PWROK_N","", "PWRGD_MTIA_BLADE5_HSC_PWROK_N","", @@ -725,49 +1582,50 @@ "PWRGD_MTIA_BLADE7_HSC_PWROK_N","", "PWRGD_MTIA_BLADE8_HSC_PWROK_N","", "PWRGD_MTIA_BLADE9_HSC_PWROK_N","", - /*L0 - L7*/ "PWRGD_MTIA_BLADE10_HSC_PWROK_N","", + /*L0 - L7*/ "PWRGD_MTIA_BLADE11_HSC_PWROK_N","", "PWRGD_MTIA_BLADE12_HSC_PWROK_N","", "PWRGD_MTIA_BLADE13_HSC_PWROK_N","", "PWRGD_MTIA_BLADE14_HSC_PWROK_N","", "PWRGD_MTIA_BLADE15_HSC_PWROK_N","", - "PWRGD_NW_BLADE0_HSC_PWROK_N","", + "PWRGD_MTIA_BLADE16_HSC_PWROK_N","", "PWRGD_NW_BLADE1_HSC_PWROK_N","", - /*M0 - M7*/ "PWRGD_NW_BLADE2_HSC_PWROK_N","", + /*M0 - M7*/ "PWRGD_NW_BLADE3_HSC_PWROK_N","", "PWRGD_NW_BLADE4_HSC_PWROK_N","", "PWRGD_NW_BLADE5_HSC_PWROK_N","", + "PWRGD_NW_BLADE6_HSC_PWROK_N","", "RPU_READY","", "IT_GEAR_RPU_LINK_N","", "IT_GEAR_LEAK","", "WATER_VALVE_CLOSED_N","", /*N0 - N7*/ - "VALVE_STS0","", - "VALVE_STS1","", - "PCA9555_IRQ0_N","", + "VALVE_STATUS_0","", + "VALVE_STATUS_1","", "PCA9555_IRQ1_N","", + "PCA9555_IRQ2_N","", "CR_TOGGLE_BOOT_N","", - "IRQ_FCB_TOP0_N","", - "IRQ_FCB_TOP1_N","", + "IRQ_FCB_1_N","", + "IRQ_FCB_2_N","", "CMM_CABLE_CARTRIDGE_PRSNT_BOT_N","", /*O0 - O7*/ "CMM_CABLE_CARTRIDGE_PRSNT_TOP_N","", "BOT_BCB_CABLE_PRSNT_N","", "TOP_BCB_CABLE_PRSNT_N","", - "IRQ_FCB_MID0_N","", - "IRQ_FCB_MID1_N","", + "IRQ_FCB_3_N","", + "IRQ_FCB_4_N","", "CHASSIS_LEAK0_DETECT_N","", "CHASSIS_LEAK1_DETECT_N","", - "VALVE_RMON_A_1","", + "PCA9555_IRQ3_N","", /*P0 - P7*/ - "VALVE_RMON_A_2","", - "VALVE_RMON_B_1","", - "VALVE_RMON_B_2","", + "PCA9555_IRQ4_N","", + "PCA9555_IRQ5_N","", + "CMM_AC_PWR_BTN_N","", "RPU_READY_SPARE","", "IT_GEAR_LEAK_SPARE","", "IT_GEAR_RPU_LINK_SPARE_N","", - "IRQ_FCB_BOT0_N","", - "IRQ_FCB_BOT0_N",""; + "IRQ_FCB_6_N","", + "IRQ_FCB_5_N",""; }; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-yosemite4.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-yosemite4.dts index 98477792aa00..29f224bccd63 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-yosemite4.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-yosemite4.dts @@ -17,6 +17,27 @@ serial6 = &uart7; serial7 = &uart8; serial8 = &uart9; + + i2c16 = &imux16; + i2c17 = &imux17; + i2c18 = &imux18; + i2c19 = &imux19; + i2c20 = &imux20; + i2c21 = &imux21; + i2c22 = &imux22; + i2c23 = &imux23; + i2c24 = &imux24; + i2c25 = &imux25; + i2c26 = &imux26; + i2c27 = &imux27; + i2c28 = &imux28; + i2c29 = &imux29; + i2c30 = &imux30; + i2c31 = &imux31; + i2c32 = &imux32; + i2c33 = &imux33; + i2c34 = &imux34; + i2c35 = &imux35; }; chosen { @@ -32,7 +53,25 @@ compatible = "iio-hwmon"; io-channels = <&adc0 0>, <&adc0 1>, <&adc0 2>, <&adc0 3>, <&adc0 4>, <&adc0 5>, <&adc0 6>, <&adc0 7>, - <&adc1 0>, <&adc1 1>; + <&adc1 0>, <&adc1 1>, <&adc1 7>; + }; + + spi { + compatible = "spi-gpio"; + #address-cells = <1>; + #size-cells = <0>; + + sck-gpios = <&gpio0 ASPEED_GPIO(X, 3) GPIO_ACTIVE_HIGH>; + mosi-gpios = <&gpio0 ASPEED_GPIO(X, 4) GPIO_ACTIVE_HIGH>; + miso-gpios = <&gpio0 ASPEED_GPIO(X, 5) GPIO_ACTIVE_HIGH>; + cs-gpios = <&gpio0 ASPEED_GPIO(X, 0) GPIO_ACTIVE_LOW>; + num-chipselects = <1>; + + tpm@0 { + compatible = "infineon,slb9670", "tcg,tpm_tis-spi"; + reg = <0>; + spi-max-frequency = <33000000>; + }; }; }; @@ -83,6 +122,13 @@ aspeed,ext-pulse-duration = <256>; }; +&wdt2 { + status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdtrst2_default>; + aspeed,reset-type = "system"; +}; + &mac2 { status = "okay"; pinctrl-names = "default"; @@ -105,15 +151,17 @@ status = "okay"; m25p,fast-read; label = "bmc"; - spi-rx-bus-width = <4>; + spi-tx-bus-width = <2>; + spi-rx-bus-width = <2>; spi-max-frequency = <50000000>; -#include "openbmc-flash-layout-64.dtsi" +#include "openbmc-flash-layout-128.dtsi" }; flash@1 { status = "okay"; m25p,fast-read; - label = "bmc2"; - spi-rx-bus-width = <4>; + label = "alt-bmc"; + spi-tx-bus-width = <2>; + spi-rx-bus-width = <2>; spi-max-frequency = <50000000>; }; }; @@ -129,9 +177,38 @@ reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; }; + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@24 { + compatible = "nxp,pca9506"; + reg = <0x24>; + gpio-controller; + #gpio-cells = <2>; + }; + power-sensor@40 { - compatible = "adi,adm1278"; + compatible = "adi,adm1281"; reg = <0x40>; + shunt-resistor-micro-ohms = <500>; }; }; @@ -146,9 +223,38 @@ reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; }; + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@24 { + compatible = "nxp,pca9506"; + reg = <0x24>; + gpio-controller; + #gpio-cells = <2>; + }; + power-sensor@40 { - compatible = "adi,adm1278"; + compatible = "adi,adm1281"; reg = <0x40>; + shunt-resistor-micro-ohms = <500>; }; }; @@ -163,9 +269,38 @@ reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; }; + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@24 { + compatible = "nxp,pca9506"; + reg = <0x24>; + gpio-controller; + #gpio-cells = <2>; + }; + power-sensor@40 { - compatible = "adi,adm1278"; + compatible = "adi,adm1281"; reg = <0x40>; + shunt-resistor-micro-ohms = <500>; }; }; @@ -180,9 +315,38 @@ reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; }; + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@24 { + compatible = "nxp,pca9506"; + reg = <0x24>; + gpio-controller; + #gpio-cells = <2>; + }; + power-sensor@40 { - compatible = "adi,adm1278"; + compatible = "adi,adm1281"; reg = <0x40>; + shunt-resistor-micro-ohms = <500>; }; }; @@ -197,9 +361,38 @@ reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; }; + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@24 { + compatible = "nxp,pca9506"; + reg = <0x24>; + gpio-controller; + #gpio-cells = <2>; + }; + power-sensor@40 { - compatible = "adi,adm1278"; + compatible = "adi,adm1281"; reg = <0x40>; + shunt-resistor-micro-ohms = <500>; }; }; @@ -214,9 +407,38 @@ reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; }; + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@24 { + compatible = "nxp,pca9506"; + reg = <0x24>; + gpio-controller; + #gpio-cells = <2>; + }; + power-sensor@40 { - compatible = "adi,adm1278"; + compatible = "adi,adm1281"; reg = <0x40>; + shunt-resistor-micro-ohms = <500>; }; }; @@ -231,9 +453,38 @@ reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; }; + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@24 { + compatible = "nxp,pca9506"; + reg = <0x24>; + gpio-controller; + #gpio-cells = <2>; + }; + power-sensor@40 { - compatible = "adi,adm1278"; + compatible = "adi,adm1281"; reg = <0x40>; + shunt-resistor-micro-ohms = <500>; }; }; @@ -248,48 +499,363 @@ reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; }; + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@24 { + compatible = "nxp,pca9506"; + reg = <0x24>; + gpio-controller; + #gpio-cells = <2>; + }; + power-sensor@40 { - compatible = "adi,adm1278"; + compatible = "adi,adm1281"; reg = <0x40>; + shunt-resistor-micro-ohms = <500>; }; }; &i2c8 { + #address-cells = <1>; + #size-cells = <0>; status = "okay"; bus-frequency = <400000>; i2c-mux@70 { compatible = "nxp,pca9544"; - idle-state = <0>; - i2c-mux-idle-disconnect; reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + i2c-mux-idle-disconnect; + + imux16: i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + gpio@49 { + compatible = "nxp,pca9537"; + reg = <0x49>; + gpio-controller; + #gpio-cells = <2>; + }; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + eeprom@51 { + compatible = "atmel,24c128"; + reg = <0x51>; + }; + + eeprom@54 { + compatible = "atmel,24c128"; + reg = <0x54>; + }; + }; + + imux17: i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + gpio@49 { + compatible = "nxp,pca9537"; + reg = <0x49>; + gpio-controller; + #gpio-cells = <2>; + }; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + eeprom@51 { + compatible = "atmel,24c128"; + reg = <0x51>; + }; + + eeprom@54 { + compatible = "atmel,24c128"; + reg = <0x54>; + }; + }; + + imux18: i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + gpio@49 { + compatible = "nxp,pca9537"; + reg = <0x49>; + gpio-controller; + #gpio-cells = <2>; + }; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + eeprom@51 { + compatible = "atmel,24c128"; + reg = <0x51>; + }; + + eeprom@54 { + compatible = "atmel,24c128"; + reg = <0x54>; + }; + }; + + imux19: i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + gpio@49 { + compatible = "nxp,pca9537"; + reg = <0x49>; + gpio-controller; + #gpio-cells = <2>; + }; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + eeprom@51 { + compatible = "atmel,24c128"; + reg = <0x51>; + }; + + eeprom@54 { + compatible = "atmel,24c128"; + reg = <0x54>; + }; + }; }; }; &i2c9 { + #address-cells = <1>; + #size-cells = <0>; status = "okay"; bus-frequency = <400000>; i2c-mux@71 { compatible = "nxp,pca9544"; - idle-state = <0>; - i2c-mux-idle-disconnect; reg = <0x71>; + #address-cells = <1>; + #size-cells = <0>; + i2c-mux-idle-disconnect; + + imux20: i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + gpio@49 { + compatible = "nxp,pca9537"; + reg = <0x49>; + gpio-controller; + #gpio-cells = <2>; + }; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + eeprom@51 { + compatible = "atmel,24c128"; + reg = <0x51>; + }; + + eeprom@54 { + compatible = "atmel,24c128"; + reg = <0x54>; + }; + }; + + imux21: i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + gpio@49 { + compatible = "nxp,pca9537"; + reg = <0x49>; + gpio-controller; + #gpio-cells = <2>; + }; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + eeprom@51 { + compatible = "atmel,24c128"; + reg = <0x51>; + }; + + eeprom@54 { + compatible = "atmel,24c128"; + reg = <0x54>; + }; + }; + + imux22: i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + gpio@49 { + compatible = "nxp,pca9537"; + reg = <0x49>; + gpio-controller; + #gpio-cells = <2>; + }; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + eeprom@51 { + compatible = "atmel,24c128"; + reg = <0x51>; + }; + + eeprom@54 { + compatible = "atmel,24c128"; + reg = <0x54>; + }; + }; + + imux23: i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + gpio@49 { + compatible = "nxp,pca9537"; + reg = <0x49>; + gpio-controller; + #gpio-cells = <2>; + }; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + eeprom@51 { + compatible = "atmel,24c128"; + reg = <0x51>; + }; + + eeprom@54 { + compatible = "atmel,24c128"; + reg = <0x54>; + }; + }; }; }; &i2c10 { + #address-cells = <1>; + #size-cells = <0>; status = "okay"; bus-frequency = <400000>; + i2c-mux@74 { + compatible = "nxp,pca9544"; + reg = <0x74>; + #address-cells = <1>; + #size-cells = <0>; + i2c-mux-idle-disconnect; + + imux28: i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + gpio@20 { + compatible = "nxp,pca9506"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@24 { + compatible = "nxp,pca9506"; + reg = <0x24>; + gpio-controller; + #gpio-cells = <2>; + gpio-line-names = "","","","", + "NIC0_MAIN_PWR_EN", + "NIC1_MAIN_PWR_EN", + "NIC2_MAIN_PWR_EN", + "NIC3_MAIN_PWR_EN", + "","","","","","","","", + "","","","","","","","", + "","","","","","","",""; + }; + }; + + imux29: i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; }; &i2c11 { status = "okay"; power-sensor@10 { - compatible = "adi, adm1272"; + compatible = "adi,adm1272"; reg = <0x10>; }; power-sensor@12 { - compatible = "adi, adm1272"; + compatible = "adi,adm1272"; reg = <0x12>; }; @@ -298,6 +864,20 @@ reg = <0x20>; gpio-controller; #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = <98 IRQ_TYPE_LEVEL_LOW>; + gpio-line-names = "P48V_OCP_GPIO1", "P48V_OCP_GPIO2", + "P48V_OCP_GPIO3", "FAN_BOARD_0_REVISION_0_R", + "FAN_BOARD_0_REVISION_1_R", + "FAN_BOARD_1_REVISION_0_R", + "FAN_BOARD_1_REVISION_1_R", "RST_MUX_R_N", + "RST_LED_CONTROL_FAN_BOARD_0_N", + "RST_LED_CONTROL_FAN_BOARD_1_N", + "RST_IOEXP_FAN_BOARD_0_N", + "RST_IOEXP_FAN_BOARD_1_N", + "PWRGD_LOAD_SWITCH_FAN_BOARD_0_R", + "PWRGD_LOAD_SWITCH_FAN_BOARD_1_R", + "", ""; }; gpio@21 { @@ -305,6 +885,19 @@ reg = <0x21>; gpio-controller; #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = <98 IRQ_TYPE_LEVEL_LOW>; + gpio-line-names = "HSC_OCP_SLOT_ODD_GPIO1", + "HSC_OCP_SLOT_ODD_GPIO2", + "HSC_OCP_SLOT_ODD_GPIO3", + "HSC_OCP_SLOT_EVEN_GPIO1", + "HSC_OCP_SLOT_EVEN_GPIO2", + "HSC_OCP_SLOT_EVEN_GPIO3", + "ADC_TYPE_0_R", "ADC_TYPE_1_R", + "MEDUSA_BOARD_REV_0", "MEDUSA_BOARD_REV_1", + "MEDUSA_BOARD_REV_2", "MEDUSA_BOARD_TYPE", + "DELTA_MODULE_TYPE", "P12V_HSC_TYPE", + "", ""; }; gpio@22 { @@ -312,6 +905,16 @@ reg = <0x22>; gpio-controller; #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = <98 IRQ_TYPE_LEVEL_LOW>; + gpio-line-names = "CARD_TYPE_SLOT1", "CARD_TYPE_SLOT2", + "CARD_TYPE_SLOT3", "CARD_TYPE_SLOT4", + "CARD_TYPE_SLOT5", "CARD_TYPE_SLOT6", + "CARD_TYPE_SLOT7", "CARD_TYPE_SLOT8", + "OC_P48V_HSC_0_N", "FLT_P48V_HSC_0_N", + "OC_P48V_HSC_1_N", "FLT_P48V_HSC_1_N", + "EN_P48V_AUX_0", "EN_P48V_AUX_1", + "PWRGD_P12V_AUX_0", "PWRGD_P12V_AUX_1"; }; gpio@23 { @@ -319,6 +922,16 @@ reg = <0x23>; gpio-controller; #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = <98 IRQ_TYPE_LEVEL_LOW>; + gpio-line-names = "HSC1_ALERT1_R_N", "HSC2_ALERT1_R_N", + "HSC3_ALERT1_R_N", "HSC4_ALERT1_R_N", + "HSC5_ALERT1_R_N", "HSC6_ALERT1_R_N", + "HSC7_ALERT1_R_N", "HSC8_ALERT1_R_N", + "HSC1_ALERT2_R_N", "HSC2_ALERT2_R_N", + "HSC3_ALERT2_R_N", "HSC4_ALERT2_R_N", + "HSC5_ALERT2_R_N", "HSC6_ALERT2_R_N", + "HSC7_ALERT2_R_N", "HSC8_ALERT2_R_N"; }; temperature-sensor@48 { @@ -331,39 +944,84 @@ reg = <0x49>; }; - temperature-sensor@4a { - compatible = "ti,tmp75"; - reg = <0x4a>; - }; - - temperature-sensor@4b { - compatible = "ti,tmp75"; - reg = <0x4b>; - }; - eeprom@54 { - compatible = "atmel,24c256"; + compatible = "atmel,24c128"; reg = <0x54>; }; }; &i2c12 { + #address-cells = <1>; + #size-cells = <0>; status = "okay"; bus-frequency = <400000>; - temperature-sensor@48 { - compatible = "ti,tmp75"; - reg = <0x48>; - }; + i2c-mux@70 { + compatible = "nxp,pca9544"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + i2c-mux-idle-disconnect; - eeprom@50 { - compatible = "atmel,24c128"; - reg = <0x50>; - }; + imux34: i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; - rtc@6f { - compatible = "nuvoton,nct3018y"; - reg = <0x6f>; + temperature-sensor@48 { + compatible = "ti,tmp75"; + reg = <0x48>; + }; + + eeprom@50 { + compatible = "atmel,24c128"; + reg = <0x50>; + }; + + eeprom@54 { + compatible = "atmel,24c64"; + reg = <0x54>; + }; + + rtc@6f { + compatible = "nuvoton,nct3018y"; + reg = <0x6f>; + }; + + gpio@20 { + compatible = "nxp,pca9506"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@21 { + compatible = "nxp,pca9506"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@22 { + compatible = "nxp,pca9506"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + gpio@23 { + compatible = "nxp,pca9506"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + }; + + imux35: i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; }; }; @@ -380,24 +1038,26 @@ }; &i2c14 { + #address-cells = <1>; + #size-cells = <0>; status = "okay"; bus-frequency = <400000>; adc@1d { compatible = "ti,adc128d818"; reg = <0x1d>; - ti,mode = /bits/ 8 <2>; + ti,mode = /bits/ 8 <1>; }; - adc@35 { + adc@36 { compatible = "ti,adc128d818"; - reg = <0x35>; - ti,mode = /bits/ 8 <2>; + reg = <0x36>; + ti,mode = /bits/ 8 <1>; }; adc@37 { compatible = "ti,adc128d818"; reg = <0x37>; - ti,mode = /bits/ 8 <2>; + ti,mode = /bits/ 8 <1>; }; power-sensor@40 { @@ -440,152 +1100,143 @@ reg = <0x51>; }; - i2c-mux@71 { - compatible = "nxp,pca9846"; + i2c-mux@73 { + compatible = "nxp,pca9544"; + reg = <0x73>; #address-cells = <1>; #size-cells = <0>; - - idle-state = <0>; i2c-mux-idle-disconnect; - reg = <0x71>; - i2c@0 { + imux32: i2c@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; - reg = <0>; - - adc@1f { - compatible = "ti,adc128d818"; - reg = <0x1f>; - ti,mode = /bits/ 8 <2>; - }; - - pwm@20{ - compatible = "max31790"; - reg = <0x20>; - #address-cells = <1>; - #size-cells = <0>; - }; - - gpio@22{ - compatible = "ti,tca6424"; - reg = <0x22>; - }; - - pwm@23{ - compatible = "max31790"; - reg = <0x23>; - #address-cells = <1>; - #size-cells = <0>; - }; - - adc@33 { - compatible = "maxim,max11615"; - reg = <0x33>; - }; - - eeprom@52 { - compatible = "atmel,24c128"; - reg = <0x52>; - }; - - gpio@61 { - compatible = "nxp,pca9552"; - reg = <0x61>; - #address-cells = <1>; - #size-cells = <0>; - gpio-controller; - #gpio-cells = <2>; + adc@35 { + compatible = "maxim,max11617"; + reg = <0x35>; }; }; - i2c@1 { + imux33: i2c@1 { + reg = <1>; #address-cells = <1>; #size-cells = <0>; - reg = <0>; - - adc@1f { - compatible = "ti,adc128d818"; - reg = <0x1f>; - ti,mode = /bits/ 8 <2>; - }; - - pwm@20{ - compatible = "max31790"; - reg = <0x20>; - #address-cells = <1>; - #size-cells = <0>; - }; - - gpio@22{ - compatible = "ti,tca6424"; - reg = <0x22>; - }; - - pwm@23{ - compatible = "max31790"; - reg = <0x23>; - #address-cells = <1>; - #size-cells = <0>; - }; - - adc@33 { - compatible = "maxim,max11615"; - reg = <0x33>; - }; - - eeprom@52 { - compatible = "atmel,24c128"; - reg = <0x52>; - }; - - gpio@61 { - compatible = "nxp,pca9552"; - reg = <0x61>; - #address-cells = <1>; - #size-cells = <0>; - gpio-controller; - #gpio-cells = <2>; + adc@35 { + compatible = "maxim,max11617"; + reg = <0x35>; }; }; }; - i2c-mux@73 { - compatible = "nxp,pca9544"; + i2c-mux@74 { + compatible = "nxp,pca9546"; + reg = <0x74>; #address-cells = <1>; #size-cells = <0>; - - idle-state = <0>; i2c-mux-idle-disconnect; - reg = <0x73>; - i2c@0 { + imux30: i2c@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; - reg = <0>; - adc@35 { - compatible = "maxim,max11617"; - reg = <0x35>; + adc@1f { + compatible = "ti,adc128d818"; + reg = <0x1f>; + ti,mode = /bits/ 8 <1>; + }; + + pwm@20{ + compatible = "maxim,max31790"; + reg = <0x20>; + }; + + gpio@22{ + compatible = "ti,tca6424"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + pwm@2f{ + compatible = "maxim,max31790"; + reg = <0x2f>; + }; + + adc@33 { + compatible = "maxim,max11615"; + reg = <0x33>; + }; + + eeprom@52 { + compatible = "atmel,24c128"; + reg = <0x52>; + }; + + gpio@61 { + compatible = "nxp,pca9552"; + reg = <0x61>; + #address-cells = <1>; + #size-cells = <0>; + gpio-controller; + #gpio-cells = <2>; }; }; - i2c@1 { + imux31: i2c@1 { + reg = <1>; #address-cells = <1>; #size-cells = <0>; - reg = <0>; - adc@35 { - compatible = "maxim,max11617"; - reg = <0x35>; + adc@1f { + compatible = "ti,adc128d818"; + reg = <0x1f>; + ti,mode = /bits/ 8 <1>; + }; + + pwm@20{ + compatible = "maxim,max31790"; + reg = <0x20>; + }; + + gpio@22{ + compatible = "ti,tca6424"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + + pwm@2f{ + compatible = "maxim,max31790"; + reg = <0x2f>; + }; + + adc@33 { + compatible = "maxim,max11615"; + reg = <0x33>; + }; + + eeprom@52 { + compatible = "atmel,24c128"; + reg = <0x52>; + }; + + gpio@61 { + compatible = "nxp,pca9552"; + reg = <0x61>; + #address-cells = <1>; + #size-cells = <0>; + gpio-controller; + #gpio-cells = <2>; }; }; }; }; &i2c15 { + #address-cells = <1>; + #size-cells = <0>; status = "okay"; - mctp-controller; multi-master; bus-frequency = <400000>; @@ -596,9 +1247,73 @@ i2c-mux@72 { compatible = "nxp,pca9544"; - idle-state = <0>; - i2c-mux-idle-disconnect; reg = <0x72>; + #address-cells = <1>; + #size-cells = <0>; + + imux24: i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + mctp-controller; + temperature-sensor@1f { + compatible = "ti,tmp421"; + reg = <0x1f>; + }; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux25: i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + mctp-controller; + temperature-sensor@1f { + compatible = "ti,tmp421"; + reg = <0x1f>; + }; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux26: i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + mctp-controller; + temperature-sensor@1f { + compatible = "ti,tmp421"; + reg = <0x1f>; + }; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; + + imux27: i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + mctp-controller; + temperature-sensor@1f { + compatible = "ti,tmp421"; + reg = <0x1f>; + }; + + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + }; }; }; @@ -612,10 +1327,10 @@ &adc1 { status = "okay"; - pinctrl-0 = <&pinctrl_adc8_default &pinctrl_adc9_default>; + pinctrl-0 = <&pinctrl_adc8_default &pinctrl_adc9_default + &pinctrl_adc15_default>; }; - &ehci0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-blueridge.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-blueridge.dts index dfe5cc3edb52..bc4c46235421 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-blueridge.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-blueridge.dts @@ -207,7 +207,8 @@ /*F0-F7*/ "","","rtc-battery-voltage-read-enable","reset-cause-pinhole","","", "factory-reset-toggle","", /*G0-G7*/ "","","","","","","","", - /*H0-H7*/ "","bmc-ingraham0","rear-enc-id0","rear-enc-fault0","","","","", + /*H0-H7*/ "","led-bmc-ingraham0","led-rear-enc-id0","led-rear-enc-fault0","","","", + "", /*I0-I7*/ "","","","","","","bmc-secure-boot","", /*J0-J7*/ "","","","","","","","", /*K0-K7*/ "","","","","","","","", @@ -215,7 +216,7 @@ /*M0-M7*/ "","","","","","","","", /*N0-N7*/ "","","","","","","","", /*O0-O7*/ "","","","usb-power","","","","", - /*P0-P7*/ "","","","","pcieslot-power","","","", + /*P0-P7*/ "","","","","led-pcieslot-power","","","", /*Q0-Q7*/ "cfam-reset","","regulator-standby-faulted","","","","","", /*R0-R7*/ "bmc-tpm-reset","power-chassis-control","power-chassis-good","","","","", "", @@ -739,7 +740,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "ddimm10"; @@ -747,7 +748,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "ddimm11"; @@ -755,7 +756,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "ddimm12"; @@ -763,7 +764,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "ddimm13"; @@ -771,7 +772,7 @@ type = ; }; - led@14 { + led@e { reg = <14>; default-state = "keep"; label = "ddimm14"; @@ -779,7 +780,7 @@ type = ; }; - led@15 { + led@f { reg = <15>; default-state = "keep"; label = "ddimm15"; @@ -876,7 +877,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "ddimm26"; @@ -884,7 +885,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "ddimm27"; @@ -892,7 +893,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "ddimm28"; @@ -900,7 +901,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "ddimm29"; @@ -908,7 +909,7 @@ type = ; }; - led@14 { + led@e { reg = <14>; default-state = "keep"; label = "ddimm30"; @@ -916,7 +917,7 @@ type = ; }; - led@15 { + led@f { reg = <15>; default-state = "keep"; label = "ddimm31"; @@ -1005,7 +1006,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "pcieslot7"; @@ -1013,7 +1014,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "pcieslot8"; @@ -1021,7 +1022,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "pcieslot9"; @@ -1029,7 +1030,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "pcieslot10"; @@ -1037,7 +1038,7 @@ type = ; }; - led@14 { + led@e { reg = <14>; default-state = "keep"; label = "pcieslot11"; @@ -1045,7 +1046,7 @@ type = ; }; - led@15 { + led@f { reg = <15>; default-state = "keep"; label = "tpm-wilson"; @@ -1231,8 +1232,9 @@ #gpio-cells = <2>; gpio-line-names = - "", "", "", "", "", "", "", "", - "", "", "", "", "", "", "power-config-full-load", ""; + "", "", "", "", "", "", "P10_DCM0_PRES", "P10_DCM1_PRES", + "", "", "", "", "PRESENT_VRM_DCM0_N", "PRESENT_VRM_DCM1_N", + "power-config-full-load", ""; }; led-controller@61 { diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-everest.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-everest.dts index 513077a1f4be..9961508ee872 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-everest.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-everest.dts @@ -353,6 +353,33 @@ "presence-base-op", ""; }; + + led-controller@63 { + compatible = "nxp,pca9552"; + reg = <0x63>; + #address-cells = <1>; + #size-cells = <0>; + gpio-controller; + #gpio-cells = <2>; + + gpio-line-names = + "presence-vrm-c12", + "presence-vrm-c13", + "presence-vrm-c15", + "presence-vrm-c16", + "presence-vrm-c17", + "presence-vrm-c18", + "presence-vrm-c20", + "presence-vrm-c21", + "presence-vrm-c54", + "presence-vrm-c55", + "presence-vrm-c57", + "presence-vrm-c58", + "presence-vrm-c59", + "presence-vrm-c60", + "presence-vrm-c62", + "presence-vrm-c63"; + }; }; &i2c1 { diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-fuji.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-fuji.dts index c24e464e5faa..9a43fc7bcebe 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-fuji.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-fuji.dts @@ -355,6 +355,33 @@ "presence-base-op", ""; }; + + led-controller@63 { + compatible = "nxp,pca9552"; + reg = <0x63>; + #address-cells = <1>; + #size-cells = <0>; + gpio-controller; + #gpio-cells = <2>; + + gpio-line-names = + "presence-vrm-c12", + "presence-vrm-c13", + "presence-vrm-c15", + "presence-vrm-c16", + "presence-vrm-c17", + "presence-vrm-c18", + "presence-vrm-c20", + "presence-vrm-c21", + "presence-vrm-c54", + "presence-vrm-c55", + "presence-vrm-c57", + "presence-vrm-c58", + "presence-vrm-c59", + "presence-vrm-c60", + "presence-vrm-c62", + "presence-vrm-c63"; + }; }; &i2c1 { @@ -949,7 +976,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "pcieslot-c10"; @@ -957,7 +984,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "pcieslot-c11"; @@ -1058,7 +1085,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "ddimm10"; @@ -1066,7 +1093,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "ddimm11"; @@ -1074,7 +1101,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "ddimm12"; @@ -1082,7 +1109,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "ddimm13"; @@ -1090,7 +1117,7 @@ type = ; }; - led@14 { + led@e { reg = <14>; default-state = "keep"; label = "ddimm14"; @@ -1098,7 +1125,7 @@ type = ; }; - led@15 { + led@f { reg = <15>; default-state = "keep"; label = "ddimm15"; @@ -1195,7 +1222,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "ddimm26"; @@ -1203,7 +1230,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "ddimm27"; @@ -1211,7 +1238,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "ddimm28"; @@ -1219,7 +1246,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "ddimm29"; @@ -1227,7 +1254,7 @@ type = ; }; - led@14 { + led@e { reg = <14>; default-state = "keep"; label = "ddimm30"; @@ -1235,7 +1262,7 @@ type = ; }; - led@15 { + led@f { reg = <15>; default-state = "keep"; label = "ddimm31"; @@ -1332,7 +1359,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "ddimm42"; @@ -1340,7 +1367,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "ddimm43"; @@ -1348,7 +1375,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "ddimm44"; @@ -1356,7 +1383,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "ddimm45"; @@ -1364,7 +1391,7 @@ type = ; }; - led@14 { + led@e { reg = <14>; default-state = "keep"; label = "ddimm46"; @@ -1372,7 +1399,7 @@ type = ; }; - led@15 { + led@f { reg = <15>; default-state = "keep"; label = "ddimm47"; @@ -1469,7 +1496,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "ddimm58"; @@ -1477,7 +1504,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "ddimm59"; @@ -1485,7 +1512,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "ddimm60"; @@ -1493,7 +1520,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "ddimm61"; @@ -1501,7 +1528,7 @@ type = ; }; - led@14 { + led@e { reg = <14>; default-state = "keep"; label = "ddimm62"; @@ -1509,7 +1536,7 @@ type = ; }; - led@15 { + led@f { reg = <15>; default-state = "keep"; label = "ddimm63"; @@ -1598,7 +1625,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "vrm6"; @@ -1606,7 +1633,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "vrm7"; @@ -1614,7 +1641,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "vrm12"; @@ -1622,7 +1649,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "vrm13"; @@ -1630,7 +1657,7 @@ type = ; }; - led@14 { + led@e { reg = <14>; default-state = "keep"; label = "vrm14"; @@ -1638,7 +1665,7 @@ type = ; }; - led@15 { + led@f { reg = <15>; default-state = "keep"; label = "vrm15"; @@ -1727,7 +1754,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "vrm2"; @@ -1735,7 +1762,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "vrm3"; @@ -1743,7 +1770,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "vrm8"; @@ -1751,7 +1778,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "vrm9"; @@ -1759,7 +1786,7 @@ type = ; }; - led@14 { + led@e { reg = <14>; default-state = "keep"; label = "vrm10"; @@ -1767,7 +1794,7 @@ type = ; }; - led@15 { + led@f { reg = <15>; default-state = "keep"; label = "vrm11"; @@ -2118,7 +2145,7 @@ type = ; }; - led@10 { + led@a { reg = <10>; default-state = "keep"; label = "fan0"; @@ -2126,7 +2153,7 @@ type = ; }; - led@11 { + led@b { reg = <11>; default-state = "keep"; label = "fan1"; @@ -2134,7 +2161,7 @@ type = ; }; - led@12 { + led@c { reg = <12>; default-state = "keep"; label = "fan2"; @@ -2142,7 +2169,7 @@ type = ; }; - led@13 { + led@d { reg = <13>; default-state = "keep"; label = "fan3"; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-rainier.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-rainier.dts index 0776b72c2199..638a2c1c7892 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-rainier.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-rainier.dts @@ -109,22 +109,22 @@ compatible = "gpio-leds"; /* BMC Card fault LED at the back */ - bmc-ingraham0 { + led-bmc-ingraham0 { gpios = <&gpio0 ASPEED_GPIO(H, 1) GPIO_ACTIVE_LOW>; }; /* Enclosure ID LED at the back */ - rear-enc-id0 { + led-rear-enc-id0 { gpios = <&gpio0 ASPEED_GPIO(H, 2) GPIO_ACTIVE_LOW>; }; /* Enclosure fault LED at the back */ - rear-enc-fault0 { + led-rear-enc-fault0 { gpios = <&gpio0 ASPEED_GPIO(H, 3) GPIO_ACTIVE_LOW>; }; /* PCIE slot power LED */ - pcieslot-power { + led-pcieslot-power { gpios = <&gpio0 ASPEED_GPIO(P, 4) GPIO_ACTIVE_LOW>; }; }; @@ -203,7 +203,7 @@ /*E0-E7*/ "","","","","","","","", /*F0-F7*/ "","","rtc-battery-voltage-read-enable","reset-cause-pinhole","","","factory-reset-toggle","", /*G0-G7*/ "","","","","","","","", - /*H0-H7*/ "","bmc-ingraham0","rear-enc-id0","rear-enc-fault0","","","","", + /*H0-H7*/ "","led-bmc-ingraham0","led-rear-enc-id0","led-rear-enc-fault0","","","","", /*I0-I7*/ "","","","","","","bmc-secure-boot","", /*J0-J7*/ "","","","","","","","", /*K0-K7*/ "","","","","","","","", @@ -211,7 +211,7 @@ /*M0-M7*/ "","","","","","","","", /*N0-N7*/ "","","","","","","","", /*O0-O7*/ "","","","usb-power","","","","", - /*P0-P7*/ "","","","","pcieslot-power","","","", + /*P0-P7*/ "","","","","led-pcieslot-power","","","", /*Q0-Q7*/ "cfam-reset","","regulator-standby-faulted","","","","","", /*R0-R7*/ "bmc-tpm-reset","power-chassis-control","power-chassis-good","","","","","", /*S0-S7*/ "presence-ps0","presence-ps1","presence-ps2","presence-ps3", @@ -1280,8 +1280,9 @@ #gpio-cells = <2>; gpio-line-names = - "", "", "", "", "", "", "", "", - "", "", "", "", "", "", "power-config-full-load", ""; + "", "", "", "", "", "", "P10_DCM0_PRES", "P10_DCM1_PRES", + "", "", "", "", "PRESENT_VRM_DCM0_N", "PRESENT_VRM_DCM1_N", + "power-config-full-load", ""; }; pca_pres2: pca9552@61 { diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-sbp1.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-sbp1.dts new file mode 100644 index 000000000000..8d98be3d5f2e --- /dev/null +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-sbp1.dts @@ -0,0 +1,6086 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright 2024 IBM Corp. +/dts-v1/; +#include +#include +#include +#include +#include +#include "aspeed-g6.dtsi" + +/ { + model = "IBM SBP1"; + compatible = "ibm,sbp1-bmc", "aspeed,ast2600"; + + chosen { + stdout-path = &uart1; + }; + + memory@80000000 { + reg = <0x80000000 0x20000000>; + device_type = "memory"; + }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + gfx_memory: framebuffer { + size = <0x01000000>; + alignment = <0x01000000>; + compatible = "shared-dma-pool"; + reusable; + }; + }; + + leds { + compatible = "gpio-leds"; + + led-power { + label = "LED_BMC_READY"; + gpios = <&gpio0 ASPEED_GPIO(H, 1) GPIO_ACTIVE_LOW>; + color = ; + default-state = "off"; + retain-state-suspended; + panic-indicator; + }; + + led-id-tpm { + label = "LED_ID_TPM"; + gpios = <&smb_pex_vr_ctrl 12 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-bat { + label = "LED_ID_BAT"; + gpios = <&smb_pex_vr_ctrl 16 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-mgmt-port2 { + label = "LED_ID_MGMT_PORT2"; + gpios = <&smb_pex_vr_ctrl 17 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-mgmt-port1 { + label = "LED_ID_MGMT_PORT1"; + gpios = <&smb_pex_vr_ctrl 18 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-nic1-port1 { + label = "LED_ID_NIC1_PORT1"; + gpios = <&smb_pex_vr_ctrl 22 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-nic1-port2 { + label = "LED_ID_NIC1_PORT2"; + gpios = <&smb_pex_vr_ctrl 23 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-nic2-port1 { + label = "LED_ID_NIC2_PORT1"; + gpios = <&smb_pex_vr_ctrl 24 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-nic2-port2 { + label = "LED_ID_NIC2_PORT2"; + gpios = <&smb_pex_vr_ctrl 25 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-m2-ssd2 { + label = "LED_ID_M2_SSD2"; + gpios = <&smb_pex_vr_ctrl 36 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-m2-ssd1 { + label = "LED_ID_M2_SSD1"; + gpios = <&smb_pex_vr_ctrl 37 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dwr-frnt-p { + label = "LED_ID_DWR_FRNT_P"; + gpios = <&smb_svc_pex_cpu3_led 37 GPIO_ACTIVE_HIGH>; + color = ; + + default-state = "on"; + retain-state-suspended; + retain-state-shutdown; + }; + + led-pwr-dwr-frnt { + label = "LED_PWR_DWR_FRNT"; + gpios = <&smb_svc_pex_cpu3_led 36 GPIO_ACTIVE_LOW>; + color = ; + + retain-state-suspended; + retain-state-shutdown; + }; + + led-pwr-dwr-back { + label = "LED_PWR_DWR_BACK"; + gpios = <&smb_pex_vr_ctrl 34 GPIO_ACTIVE_LOW>; + color = ; + + retain-state-suspended; + retain-state-shutdown; + }; + + led-id-dwr-back-p { + label = "LED_ID_DWR_BACK_P"; + gpios = <&smb_pex_vr_ctrl 35 GPIO_ACTIVE_HIGH>; + color = ; + + default-state = "on"; + retain-state-suspended; + retain-state-shutdown; + }; + + led-id-cpu0 { + label = "LED_ID_CPU0"; + gpios = <&smb_svc_pex_cpu0_led 39 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-cpu1 { + label = "LED_ID_CPU1"; + gpios = <&smb_svc_pex_cpu1_led 39 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-cpu2 { + label = "LED_ID_CPU2"; + gpios = <&smb_svc_pex_cpu2_led 39 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-cpu3 { + label = "LED_ID_CPU3"; + gpios = <&smb_svc_pex_cpu3_led 39 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0e2 { + label = "LED_ID_DIMM_C0E2"; + gpios = <&smb_svc_pex_cpu0_led 20 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0e1 { + label = "LED_ID_DIMM_C0E1"; + gpios = <&smb_svc_pex_cpu0_led 21 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0f2 { + label = "LED_ID_DIMM_C0F2"; + gpios = <&smb_svc_pex_cpu0_led 22 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0f1 { + label = "LED_ID_DIMM_C0F1"; + gpios = <&smb_svc_pex_cpu0_led 23 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0g2 { + label = "LED_ID_DIMM_C0G2"; + gpios = <&smb_svc_pex_cpu0_led 24 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0g1 { + label = "LED_ID_DIMM_C0G1"; + gpios = <&smb_svc_pex_cpu0_led 25 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0h2 { + label = "LED_ID_DIMM_C0H2"; + gpios = <&smb_svc_pex_cpu0_led 26 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0h1 { + label = "LED_ID_DIMM_C0H1"; + gpios = <&smb_svc_pex_cpu0_led 27 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0a2 { + label = "LED_ID_DIMM_C0A2"; + gpios = <&smb_svc_pex_cpu0_led 28 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0a1 { + label = "LED_ID_DIMM_C0A1"; + gpios = <&smb_svc_pex_cpu0_led 29 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0b2 { + label = "LED_ID_DIMM_C0B2"; + gpios = <&smb_svc_pex_cpu0_led 30 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0b1 { + label = "LED_ID_DIMM_C0B1"; + gpios = <&smb_svc_pex_cpu0_led 31 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0c2 { + label = "LED_ID_DIMM_C0C2"; + gpios = <&smb_svc_pex_cpu0_led 32 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0c1 { + label = "LED_ID_DIMM_C0C1"; + gpios = <&smb_svc_pex_cpu0_led 33 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0d2 { + label = "LED_ID_DIMM_C0D2"; + gpios = <&smb_svc_pex_cpu0_led 34 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c0d1 { + label = "LED_ID_DIMM_C0D1"; + gpios = <&smb_svc_pex_cpu0_led 35 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1e2 { + label = "LED_ID_DIMM_C1E2"; + gpios = <&smb_svc_pex_cpu1_led 20 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1e1 { + label = "LED_ID_DIMM_C1E1"; + gpios = <&smb_svc_pex_cpu1_led 21 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1f2 { + label = "LED_ID_DIMM_C1F2"; + gpios = <&smb_svc_pex_cpu1_led 22 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1f1 { + label = "LED_ID_DIMM_C1F1"; + gpios = <&smb_svc_pex_cpu1_led 23 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1g2 { + label = "LED_ID_DIMM_C1G2"; + gpios = <&smb_svc_pex_cpu1_led 24 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1g1 { + label = "LED_ID_DIMM_C1G1"; + gpios = <&smb_svc_pex_cpu1_led 25 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1h2 { + label = "LED_ID_DIMM_C1H2"; + gpios = <&smb_svc_pex_cpu1_led 26 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1h1 { + label = "LED_ID_DIMM_C1H1"; + gpios = <&smb_svc_pex_cpu1_led 27 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1a2 { + label = "LED_ID_DIMM_C1A2"; + gpios = <&smb_svc_pex_cpu1_led 28 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1a1 { + label = "LED_ID_DIMM_C1A1"; + gpios = <&smb_svc_pex_cpu1_led 29 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1b2 { + label = "LED_ID_DIMM_C1B2"; + gpios = <&smb_svc_pex_cpu1_led 30 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1b1 { + label = "LED_ID_DIMM_C1B1"; + gpios = <&smb_svc_pex_cpu1_led 31 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1c2 { + label = "LED_ID_DIMM_C1C2"; + gpios = <&smb_svc_pex_cpu1_led 32 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1c1 { + label = "LED_ID_DIMM_C1C1"; + gpios = <&smb_svc_pex_cpu1_led 33 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1d2 { + label = "LED_ID_DIMM_C1D2"; + gpios = <&smb_svc_pex_cpu1_led 34 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c1d1 { + label = "LED_ID_DIMM_C1D1"; + gpios = <&smb_svc_pex_cpu1_led 35 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2e2 { + label = "LED_ID_DIMM_C2E2"; + gpios = <&smb_svc_pex_cpu2_led 20 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2e1 { + label = "LED_ID_DIMM_C2E1"; + gpios = <&smb_svc_pex_cpu2_led 21 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2f2 { + label = "LED_ID_DIMM_C2F2"; + gpios = <&smb_svc_pex_cpu2_led 22 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2f1 { + label = "LED_ID_DIMM_C2F1"; + gpios = <&smb_svc_pex_cpu2_led 23 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2g2 { + label = "LED_ID_DIMM_C2G2"; + gpios = <&smb_svc_pex_cpu2_led 24 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2g1 { + label = "LED_ID_DIMM_C2G1"; + gpios = <&smb_svc_pex_cpu2_led 25 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2h2 { + label = "LED_ID_DIMM_C2H2"; + gpios = <&smb_svc_pex_cpu2_led 26 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2h1 { + label = "LED_ID_DIMM_C2H1"; + gpios = <&smb_svc_pex_cpu2_led 27 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2a2 { + label = "LED_ID_DIMM_C2A2"; + gpios = <&smb_svc_pex_cpu2_led 28 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2a1 { + label = "LED_ID_DIMM_C2A1"; + gpios = <&smb_svc_pex_cpu2_led 29 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2b2 { + label = "LED_ID_DIMM_C2B2"; + gpios = <&smb_svc_pex_cpu2_led 30 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2b1 { + label = "LED_ID_DIMM_C2B1"; + gpios = <&smb_svc_pex_cpu2_led 31 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2c2 { + label = "LED_ID_DIMM_C2C2"; + gpios = <&smb_svc_pex_cpu2_led 32 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2c1 { + label = "LED_ID_DIMM_C2C1"; + gpios = <&smb_svc_pex_cpu2_led 33 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2d2 { + label = "LED_ID_DIMM_C2D2"; + gpios = <&smb_svc_pex_cpu2_led 34 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c2d1 { + label = "LED_ID_DIMM_C2D1"; + gpios = <&smb_svc_pex_cpu2_led 35 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3e2 { + label = "LED_ID_DIMM_C3E2"; + gpios = <&smb_svc_pex_cpu3_led 20 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3e1 { + label = "LED_ID_DIMM_C3E1"; + gpios = <&smb_svc_pex_cpu3_led 21 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3f2 { + label = "LED_ID_DIMM_C3F2"; + gpios = <&smb_svc_pex_cpu3_led 22 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3f1 { + label = "LED_ID_DIMM_C3F1"; + gpios = <&smb_svc_pex_cpu3_led 23 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3g2 { + label = "LED_ID_DIMM_C3G2"; + gpios = <&smb_svc_pex_cpu3_led 24 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3g1 { + label = "LED_ID_DIMM_C3G1"; + gpios = <&smb_svc_pex_cpu3_led 25 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3h2 { + label = "LED_ID_DIMM_C3H2"; + gpios = <&smb_svc_pex_cpu3_led 26 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3h1 { + label = "LED_ID_DIMM_C3H1"; + gpios = <&smb_svc_pex_cpu3_led 27 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3a2 { + label = "LED_ID_DIMM_C3A2"; + gpios = <&smb_svc_pex_cpu3_led 28 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3a1 { + label = "LED_ID_DIMM_C3A1"; + gpios = <&smb_svc_pex_cpu3_led 29 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3b2 { + label = "LED_ID_DIMM_C3B2"; + gpios = <&smb_svc_pex_cpu3_led 30 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3b1 { + label = "LED_ID_DIMM_C3B1"; + gpios = <&smb_svc_pex_cpu3_led 31 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3c2 { + label = "LED_ID_DIMM_C3C2"; + gpios = <&smb_svc_pex_cpu3_led 32 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3c1 { + label = "LED_ID_DIMM_C3C1"; + gpios = <&smb_svc_pex_cpu3_led 33 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3d2 { + label = "LED_ID_DIMM_C3D2"; + gpios = <&smb_svc_pex_cpu3_led 34 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-c3d1 { + label = "LED_ID_DIMM_C3D1"; + gpios = <&smb_svc_pex_cpu3_led 35 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd01 { + label = "LED_ID_RSSD01"; + gpios = <&smb_svc_pex_rssd01_16 0 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd02 { + label = "LED_ID_RSSD02"; + gpios = <&smb_svc_pex_rssd01_16 1 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd03 { + label = "LED_ID_RSSD03"; + gpios = <&smb_svc_pex_rssd01_16 2 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd04 { + label = "LED_ID_RSSD04"; + gpios = <&smb_svc_pex_rssd01_16 3 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd05 { + label = "LED_ID_RSSD05"; + gpios = <&smb_svc_pex_rssd01_16 4 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd06 { + label = "LED_ID_RSSD06"; + gpios = <&smb_svc_pex_rssd01_16 5 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd07 { + label = "LED_ID_RSSD07"; + gpios = <&smb_svc_pex_rssd01_16 6 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd08 { + label = "LED_ID_RSSD08"; + gpios = <&smb_svc_pex_rssd01_16 7 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd09 { + label = "LED_ID_RSSD09"; + gpios = <&smb_svc_pex_rssd01_16 8 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd10 { + label = "LED_ID_RSSD10"; + gpios = <&smb_svc_pex_rssd01_16 9 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd11 { + label = "LED_ID_RSSD11"; + gpios = <&smb_svc_pex_rssd01_16 10 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd12 { + label = "LED_ID_RSSD12"; + gpios = <&smb_svc_pex_rssd01_16 11 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd13 { + label = "LED_ID_RSSD13"; + gpios = <&smb_svc_pex_rssd01_16 12 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd14 { + label = "LED_ID_RSSD14"; + gpios = <&smb_svc_pex_rssd01_16 13 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd15 { + label = "LED_ID_RSSD15"; + gpios = <&smb_svc_pex_rssd01_16 14 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd16 { + label = "LED_ID_RSSD16"; + gpios = <&smb_svc_pex_rssd01_16 15 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd17 { + label = "LED_ID_RSSD17"; + gpios = <&smb_svc_pex_rssd17_32 0 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd18 { + label = "LED_ID_RSSD18"; + gpios = <&smb_svc_pex_rssd17_32 1 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd19 { + label = "LED_ID_RSSD19"; + gpios = <&smb_svc_pex_rssd17_32 2 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd20 { + label = "LED_ID_RSSD20"; + gpios = <&smb_svc_pex_rssd17_32 3 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd21 { + label = "LED_ID_RSSD21"; + gpios = <&smb_svc_pex_rssd17_32 4 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd22 { + label = "LED_ID_RSSD22"; + gpios = <&smb_svc_pex_rssd17_32 5 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd23 { + label = "LED_ID_RSSD23"; + gpios = <&smb_svc_pex_rssd17_32 6 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd24 { + label = "LED_ID_RSSD24"; + gpios = <&smb_svc_pex_rssd17_32 7 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd25 { + label = "LED_ID_RSSD25"; + gpios = <&smb_svc_pex_rssd17_32 8 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd26 { + label = "LED_ID_RSSD26"; + gpios = <&smb_svc_pex_rssd17_32 9 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd27 { + label = "LED_ID_RSSD27"; + gpios = <&smb_svc_pex_rssd17_32 10 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd28 { + label = "LED_ID_RSSD28"; + gpios = <&smb_svc_pex_rssd17_32 11 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd29 { + label = "LED_ID_RSSD29"; + gpios = <&smb_svc_pex_rssd17_32 12 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd30 { + label = "LED_ID_RSSD30"; + gpios = <&smb_svc_pex_rssd17_32 13 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd31 { + label = "LED_ID_RSSD31"; + gpios = <&smb_svc_pex_rssd17_32 14 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-dimm-rssd32 { + label = "LED_ID_RSSD32"; + gpios = <&smb_svc_pex_rssd17_32 15 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm01 { + label = "LED_ID_FAN_ASM01"; + gpios = <&smb_svc_pex_rssd01_16 32 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm02 { + label = "LED_ID_FAN_ASM02"; + gpios = <&smb_svc_pex_rssd01_16 33 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm03 { + label = "LED_ID_FAN_ASM03"; + gpios = <&smb_svc_pex_rssd01_16 34 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm04 { + label = "LED_ID_FAN_ASM04"; + gpios = <&smb_svc_pex_rssd01_16 35 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm05 { + label = "LED_ID_FAN_ASM05"; + gpios = <&smb_svc_pex_rssd01_16 36 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm06 { + label = "LED_ID_FAN_ASM06"; + gpios = <&smb_svc_pex_rssd01_16 37 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm07 { + label = "LED_ID_FAN_ASM07"; + gpios = <&smb_svc_pex_rssd17_32 32 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm08 { + label = "LED_ID_FAN_ASM08"; + gpios = <&smb_svc_pex_rssd17_32 33 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm09 { + label = "LED_ID_FAN_ASM09"; + gpios = <&smb_svc_pex_rssd17_32 34 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm10 { + label = "LED_ID_FAN_ASM10"; + gpios = <&smb_svc_pex_rssd17_32 35 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm11 { + label = "LED_ID_FAN_ASM11"; + gpios = <&smb_svc_pex_rssd17_32 36 GPIO_ACTIVE_LOW>; + color = ; + }; + + led-id-fan-asm12 { + label = "LED_ID_FAN_ASM12"; + gpios = <&smb_svc_pex_rssd17_32 37 GPIO_ACTIVE_LOW>; + color = ; + }; + }; + + iio-hwmon { + compatible = "iio-hwmon"; + io-channels = <&p12v_vd 0>, <&p5v_aux_vd 0>, <&p5v_bmc_aux_vd 0>, <&p3v3_aux_vd 0>, + <&p3v3_bmc_aux_vd 0>, <&p1v8_bmc_aux_vd 0>, <&adc1 4>, <&adc0 2>, <&adc1 0>, + <&p2V5_aux_vd 0>, <&p3v3_rtc_vd 0>; + }; + + p12v_vd: voltage-divider1 { + compatible = "voltage-divider"; + io-channels = <&adc1 3>; + #io-channel-cells = <1>; + + /* + * Scale the system voltage by 1127/127 to fit the ADC range. + * Use small nominator to prevent integer overflow. + */ + output-ohms = <15>; + full-ohms = <133>; + }; + + p5v_aux_vd: voltage-divider2 { + compatible = "voltage-divider"; + io-channels = <&adc1 5>; + #io-channel-cells = <1>; + + /* + * Scale the system voltage by 1365/365 to fit the ADC range. + * Use small nominator to prevent integer overflow. + */ + output-ohms = <50>; + full-ohms = <187>; + }; + + p5v_bmc_aux_vd: voltage-divider3 { + compatible = "voltage-divider"; + io-channels = <&adc0 3>; + #io-channel-cells = <1>; + + /* + * Scale the system voltage by 1365/365 to fit the ADC range. + * Use small nominator to prevent integer overflow. + */ + output-ohms = <50>; + full-ohms = <187>; + }; + + p3v3_aux_vd: voltage-divider4 { + compatible = "voltage-divider"; + io-channels = <&adc1 2>; + #io-channel-cells = <1>; + + /* + * Scale the system voltage by 1698/698 to fit the ADC range. + * Use small nominator to prevent integer overflow. + */ + output-ohms = <14>; + full-ohms = <34>; + }; + + p3v3_bmc_aux_vd: voltage-divider5 { + compatible = "voltage-divider"; + io-channels = <&adc0 7>; + #io-channel-cells = <1>; + + /* + * Scale the system voltage by 1698/698 to fit the ADC range. + * Use small nominator to prevent integer overflow. + */ + output-ohms = <14>; + full-ohms = <34>; + }; + + p1v8_bmc_aux_vd: voltage-divider6 { + compatible = "voltage-divider"; + io-channels = <&adc0 6>; + #io-channel-cells = <1>; + + /* + * Scale the system voltage by 4000/3000 to fit the ADC range. + * Use small nominator to prevent integer overflow. + */ + output-ohms = <3>; + full-ohms = <4>; + }; + + p2V5_aux_vd: voltage-divider7 { + compatible = "voltage-divider"; + io-channels = <&adc1 1>; + #io-channel-cells = <1>; + + /* + * Scale the system voltage by 2100/1100 to fit the ADC range. + * Use small nominator to prevent integer overflow. + */ + output-ohms = <11>; + full-ohms = <21>; + }; + + p3v3_rtc_vd: voltage-divider8 { + compatible = "voltage-divider"; + io-channels = <&adc1 7>; + #io-channel-cells = <1>; + + /* + * Scale the system voltage by 231000/100000 to fit the ADC range. + * Use small nominator to prevent integer overflow. + */ + output-ohms = <100>; + full-ohms = <231>; + }; + + thermistor0: thermistor-0 { + compatible = "epcos,b57891s0103"; + pullup-uv = <3300000>; + pullup-ohm = <10000>; + pulldown-ohm = <0>; + io-channels = <&adc0 0>; + #thermal-sensor-cells = <0>; + }; + + thermistor1: thermistor-1 { + compatible = "epcos,b57891s0103"; + pullup-uv = <3300000>; + pullup-ohm = <10000>; + pulldown-ohm = <0>; + io-channels = <&adc0 1>; + #thermal-sensor-cells = <0>; + }; + + thermistor2: thermistor-2 { + compatible = "epcos,b57891s0103"; + pullup-uv = <3300000>; + pullup-ohm = <10000>; + pulldown-ohm = <0>; + io-channels = <&adc0 4>; + #thermal-sensor-cells = <0>; + }; + + thermistor3: thermistor-3 { + compatible = "epcos,b57891s0103"; + pullup-uv = <3300000>; + pullup-ohm = <10000>; + pulldown-ohm = <0>; + io-channels = <&adc0 5>; + #thermal-sensor-cells = <0>; + }; + + p12v: fixedregulator-p12v { + compatible = "regulator-fixed"; + regulator-name = "p12v"; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + regulator-always-on; + regulator-boot-on; + }; + + p3v3_bmc_aux: fixedregulator-p3v3-bmc-aux { + compatible = "regulator-fixed"; + regulator-name = "p3v3_bmc_aux"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + }; + + p1v8_bmc_aux: fixedregulator-p1v8-bmc-aux { + compatible = "regulator-fixed"; + regulator-name = "p1v8_bmc_aux"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + }; + + p1v2_bmc_aux: fixedregulator-p1v2-bmc-aux { + compatible = "regulator-fixed"; + regulator-name = "p1v2_bmc_aux"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-always-on; + regulator-boot-on; + }; + + p12v-a-consumer { + compatible = "regulator-output"; + vout-supply = <&p12v_a>; + }; + + p12v-b-consumer { + compatible = "regulator-output"; + vout-supply = <&p12v_b>; + }; + + p12v-c-consumer { + compatible = "regulator-output"; + vout-supply = <&p12v_c>; + }; + + p12v-d-consumer { + compatible = "regulator-output"; + vout-supply = <&p12v_d>; + }; + + pvccinfaon-cpu0-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccinfaon_cpu0>; + }; + + pvccfa-ehv-cpu0-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccfa_ehv_cpu0>; + }; + + pvnn-main-cpu0-consumer { + compatible = "regulator-output"; + vout-supply = <&pvnn_main_cpu0>; + }; + + pvccin-cpu0-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccin_cpu0>; + }; + + pvccfa-ehv-fivra-cpu0-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccfa_ehv_fivra_cpu0>; + }; + + pvccd-hv-cpu0-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccd_hv_cpu0>; + }; + + pvpp-hbm-cpu0-consumer { + compatible = "regulator-output"; + vout-supply = <&pvpp_hbm_cpu0>; + }; + + pvccinfaon-cpu1-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccinfaon_cpu1>; + }; + + pvccfa-ehv-cpu1-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccfa_ehv_cpu1>; + }; + + pvnn-main-cpu1-consumer { + compatible = "regulator-output"; + vout-supply = <&pvnn_main_cpu1>; + }; + + pvccin-cpu1-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccin_cpu1>; + }; + + pvccfa-ehv-fivra-cpu1-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccfa_ehv_fivra_cpu1>; + }; + + pvccd-hv-cpu1-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccd_hv_cpu1>; + }; + + pvpp-hbm-cpu1-consumer { + compatible = "regulator-output"; + vout-supply = <&pvpp_hbm_cpu1>; + }; + + pvccinfaon-cpu2-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccinfaon_cpu2>; + }; + + pvccfa-ehv-cpu2-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccfa_ehv_cpu2>; + }; + + pvnn-main-cpu2-consumer { + compatible = "regulator-output"; + vout-supply = <&pvnn_main_cpu2>; + }; + + pvccin-cpu2-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccin_cpu2>; + }; + + pvccfa-ehv-fivra-cpu2-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccfa_ehv_fivra_cpu2>; + }; + + pvccd-hv-cpu2-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccd_hv_cpu2>; + }; + + pvpp-hbm-cpu2-consumer { + compatible = "regulator-output"; + vout-supply = <&pvpp_hbm_cpu2>; + }; + + pvccinfaon-cpu3-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccinfaon_cpu3>; + }; + + pvccfa-ehv-cpu3-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccfa_ehv_cpu3>; + }; + + pvnn-main-cpu3-consumer { + compatible = "regulator-output"; + vout-supply = <&pvnn_main_cpu3>; + }; + + pvccin-cpu3-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccin_cpu3>; + }; + + pvccfa-ehv-fivra-cpu3-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccfa_ehv_fivra_cpu3>; + }; + + pvccd-hv-cpu3-consumer { + compatible = "regulator-output"; + vout-supply = <&pvccd_hv_cpu3>; + }; + + pvpp-hbm-cpu3-consumer { + compatible = "regulator-output"; + vout-supply = <&pvpp_hbm_cpu3>; + }; + + p1v05-pch-aux-consumer { + compatible = "regulator-output"; + vout-supply = <&p1v05_pch_aux>; + }; + + p1v8-pch-aux-consumer { + compatible = "regulator-output"; + vout-supply = <&p1v8_pch_aux>; + }; + + p3v3-pch-consumer { + compatible = "regulator-output"; + vout-supply = <&p3v3_pch>; + }; + + p5v-consumer { + compatible = "regulator-output"; + vout-supply = <&p5v>; + }; + + smb-m2-ssb-ssd2 { + compatible = "regulator-output"; + vout-supply = <&sw0_smb_m2_ssb_ssd2>; + }; + + smb-m2-ssb-ssd1 { + compatible = "regulator-output"; + vout-supply = <&sw0_smb_m2_ssb_ssd1>; + }; + + ssb-rssd01-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd01>; + }; + + ssb-rssd01-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd01>; + }; + + ssb-rssd02-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd02>; + }; + + ssb-rssd02-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd02>; + }; + + ssb-rssd03-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd03>; + }; + + ssb-rssd03-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd03>; + }; + + ssb-rssd04-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd04>; + }; + + ssb-rssd04-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd04>; + }; + + ssb-rssd05-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd05>; + }; + + ssb-rssd05-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd05>; + }; + + ssb-rssd06-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd06>; + }; + + ssb-rssd06-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd06>; + }; + + ssb-rssd07-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd07>; + }; + + ssb-rssd07-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd07>; + }; + + ssb-rssd08-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd08>; + }; + + ssb-rssd08-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd08>; + }; + + ssb-rssd09-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd09>; + }; + + ssb-rssd09-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd09>; + }; + + ssb-rssd10-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd10>; + }; + + ssb-rssd10-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd10>; + }; + + ssb-rssd11-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd11>; + }; + + ssb-rssd11-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd11>; + }; + + ssb-rssd12-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd12>; + }; + + ssb-rssd12-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd12>; + }; + + ssb-rssd13-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd13>; + }; + + ssb-rssd13-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd13>; + }; + + ssb-rssd14-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd14>; + }; + + ssb-rssd14-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd14>; + }; + + ssb-rssd15-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd15>; + }; + + ssb-rssd15-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd15>; + }; + + ssb-rssd16-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd16>; + }; + + ssb-rssd16-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd16>; + }; + + ssb-rssd17-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd17>; + }; + + ssb-rssd17-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd17>; + }; + + ssb-rssd18-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd18>; + }; + + ssb-rssd18-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd18>; + }; + + ssb-rssd19-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd19>; + }; + + ssb-rssd19-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd19>; + }; + + ssb-rssd20-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd20>; + }; + + ssb-rssd20-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd20>; + }; + + ssb-rssd21-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd21>; + }; + + ssb-rssd21-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd21>; + }; + + ssb-rssd22-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd22>; + }; + + ssb-rssd22-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd22>; + }; + + ssb-rssd23-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd23>; + }; + + ssb-rssd23-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd23>; + }; + + ssb-rssd24-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd24>; + }; + + ssb-rssd24-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd24>; + }; + + ssb-rssd25-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd25>; + }; + + ssb-rssd25-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd25>; + }; + + ssb-rssd26-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd26>; + }; + + ssb-rssd26-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd26>; + }; + + ssb-rssd27-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd27>; + }; + + ssb-rssd27-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd27>; + }; + + ssb-rssd28-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd28>; + }; + + ssb-rssd28-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd28>; + }; + + ssb-rssd29-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd29>; + }; + + ssb-rssd29-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd29>; + }; + + ssb-rssd30-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd30>; + }; + + ssb-rssd30-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd30>; + }; + + ssb-rssd31-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd31>; + }; + + ssb-rssd31-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd31>; + }; + + ssb-rssd32-sw0 { + compatible = "regulator-output"; + vout-supply = <&sw0_ssb_rssd32>; + }; + + ssb-rssd32-sw1 { + compatible = "regulator-output"; + vout-supply = <&sw1_ssb_rssd32>; + }; + + p3v3-nic-consumer { + compatible = "regulator-output"; + vout-supply = <&p3v3_nic>; + }; + + p1v8-nic-consumer { + compatible = "regulator-output"; + vout-supply = <&p1v8_nic>; + }; + + p1v2-nic-consumer { + compatible = "regulator-output"; + vout-supply = <&p1v2_nic>; + }; + + pvcore-nic1-consumer { + compatible = "regulator-output"; + vout-supply = <&pvcore_nic1>; + }; + + pvcore-nic2-consumer { + compatible = "regulator-output"; + vout-supply = <&pvcore_nic2>; + }; +}; + +&peci0 { + status = "okay"; +}; + +&vuart1 { + status = "okay"; +}; + +&lpc_snoop { + status = "okay"; + snoop-ports = <0x80>, <0x81>; +}; + +&fmc { + status = "okay"; + flash@0 { + status = "okay"; + m25p,fast-read; + label = "bmc"; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <4>; +#include "openbmc-flash-layout-64.dtsi" + }; + + flash@1 { + status = "okay"; + m25p,fast-read; + label = "alt-bmc"; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <4>; +#include "openbmc-flash-layout-64-alt.dtsi" + }; +}; + +&uart1 { + status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_txd1_default + &pinctrl_rxd1_default + &pinctrl_nrts1_default + &pinctrl_ndtr1_default + &pinctrl_ndsr1_default + &pinctrl_ncts1_default + &pinctrl_ndcd1_default + &pinctrl_nri1_default>; +}; + +&uart5 { + status = "disabled"; +}; + +&gpio1 { + status = "disabled"; +}; + +&video { + status = "okay"; +}; + +&vhub { + status = "okay"; +}; + +&pinctrl { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_vgahs_default &pinctrl_vgavs_default>; +}; + +&mdio2 { + status = "okay"; + + ethphy2: ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0>; + reset-gpios = <&gpio0 ASPEED_GPIO(V, 7) GPIO_ACTIVE_LOW>; + reset-assert-us = <10000>; + reset-deassert-us = <300>; + }; +}; + +&mdio3 { + status = "okay"; + + ethphy3: ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0>; + reset-gpios = <&gpio0 ASPEED_GPIO(G, 2) GPIO_ACTIVE_LOW>; + reset-assert-us = <10000>; + reset-deassert-us = <300>; + }; +}; + +&mac2 { + status = "okay"; + + phy-mode = "rgmii"; + phy-handle = <ðphy2>; + + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_rgmii3_default>; +}; + +&mac3 { + status = "okay"; + + phy-mode = "rgmii"; + phy-handle = <ðphy3>; + + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_rgmii4_default>; +}; + +&adc0 { + status = "okay"; + vref-supply = <&p1v8_bmc_aux>; + + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_adc0_default + &pinctrl_adc1_default + &pinctrl_adc2_default + &pinctrl_adc3_default + &pinctrl_adc4_default + &pinctrl_adc5_default + &pinctrl_adc6_default + &pinctrl_adc7_default>; +}; + +&adc1 { + status = "okay"; + vref-supply = <&p1v8_bmc_aux>; + aspeed,battery-sensing; + + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_adc8_default + &pinctrl_adc9_default + &pinctrl_adc10_default + &pinctrl_adc11_default + &pinctrl_adc12_default + &pinctrl_adc13_default + &pinctrl_adc15_default>; +}; + +&kcs3 { + status = "okay"; + aspeed,lpc-io-reg = <0xca2>; +}; + +&gpio0 { + status = "okay"; + gpio-line-names = + /* A0 - A7 */ + "", "", "", "", "", "", "", "", + /* B0 - B7 */ + "", "", "FM_ADR_TRIGGER_R_N", "RST_PLTRST_BUF_N", "BMC_TPM_RESET_N", "BMC_TPM_IRQ_N", + "PCH_TPM_RESET_N", "PCH_TPM_IRQ_N", + /* C0 - C7 */ + "", "", "", "", "", "", "", "", + /* D0 - D7 */ + "", "", "", "", "", "", "", "", + /* E0 - E7 */ + "", "", "", "", "", "", "", "", + /* F0 - F7 */ + "", "", "", "BMC_MUX_CPU1_RST_INT_N", "BMC_MUX_CPU2_RST_INT_N", "", "", "", + /* G0 - G7 */ + "FM_SSD_CLK_DRVR1_EN", "FM_CK440Q_DEV_EN", "BMC_MAC1_RESET_N", "FM_DB2000_DEV_EN", + "FM_CPU_RMCA_LVT3_N", "FM_CPU_CATERR_LVT3_N", "FM_DBP_PRESENT_N", "", + /* H0 - H7 */ + "SMB_SVC_PEX_RSSD17_32_INT", "LED_BMC_RDY", "RST_DBP_N", "", "", "", "", "", + /* I0 - I7 */ + "JTAG_MUX_MODE_SEL", "JTAG_MUX_TRANS_ENBL", "JTAG_MUX_LSP_SEL5", "JTAG_MUX_MSTR_SEL", + "JTAG_MUX_LSP_SEL3", "", "JTAG_MUX_ENBL_N", "JTAG_MUX_RST_N", + /* J0 - J7 */ + "", "", "", "", "", "", "", "", + /* K0 - K7 */ + "", "", "", "", "", "", "", "", + /* L0 - L7 */ + "", "", "", "", "RST_RTCRST_N", "RST_SRTCRST_N", "", "", + /* M0 - M7 */ + "BMC_UART1_CTS_N", "BMC_UART1_DCD_N", "BMC_UART1_DSR_N", "BMC_UART1_RI_N", + "BMC_UART1_DTR_N", "BMC_UART1_RTS_N", "", "", + /* N0 - N7 */ + "IRQ_BMC_PCH_NMI", "", "FM_PCH_BMC_THERMTRIP_N", "FM_BIOS_POST_CMPLT_N", "RST_PLTRST_N", + "FM_FLASH_SEC_OVRD", "FM_SMI_ACTIVE_N", "PWRGD_DBP", + /* O0 - O7 */ + "CATERR_CPU2_EN", "H_LVT1_THERMTRIP_N", "CATERR_CPU3_EN", "SMB_SVC_PEX_CPU0_LED_INT", + "H_LVT1_MEMTRIP_N", "", "CATERR_CPU1_EN", "FM_PCH_ADR_COMPLETE_N", + /* P0 - P7 */ + "PWRGD_SYS_PWROK", "PWRGD_PCH_PWROK", "BMC_MUX_CPU3_RST_INT_N", "BMC_MUX_SVC_RSSD_INT", + "FM_SLPS4_N", "IRQ_SML0_ALERT_N", "FM_SLPS3_N", "LED_BMC_HB", + /* Q0 - Q7 */ + "", "PEX_BMC_RST", "PEX_VR_CTRL_RST", "PEX_NIC_RST", "PEX_CPU0_LED_RST", "PEX_CPU1_LED_RST", + "PEX_CPU2_LED_RST", "PEX_CPU3_LED_RST", + /* R0 - R7 */ + "BMC_MUX_FANSSB_RSSD17_32_RST_INT_N", "BMC_MUX_FANPWM_RSSD01_16_RST_INT_N", + "BMC_MUX_SVC_VR_RST_INT_N", "BMC_MUX_NIC_RST_INT_N", "BMC_MUX_SVC_EXP_RST_INT_N", + "FM_CPU_ERR2_LVT3_N", "BMC_MUX_CPU0_RST_INT_N", "BMC_MUX_M2_RST_INT_N", + /* S0 - S7 */ + "SMB_SVC_PEX_RSSD01_16_INT", "RST_PCH_RSMRST_R_N", "", "", "BMC_ROT_FPGA_RESET_N", + "FM_SSD_CLK_DRVR0_EN", "", "", + /* T0 - T7 */ + "", "", "", "", "", "", "", "", + /* U0 - U7 */ + "", "", "", "", "", "", "", "", + /* V0 - V7 */ + "BMC_PEX_IRQ_INT", "RTC_BATT_TEST", "SMB_PEX_VR_CTRL_INT", "SMB_SVC_PEX_CPU3_LED_INT", + "PWRGD_CPUPWRGD", "SMB_SVC_PEX_CPU2_LED_INT", "SMB_SVC_PEX_CPU1_LED_INT", + "BMC_MAC0_RESET_N", + /* W0 - W7 */ + "", "", "", "", "", "", "", "", + /* X0 - X7 */ + "", "", "", "", "", "", "", "", + /* Y0 - Y7 */ + "FM_THROTTLE_N", "FM_PASSWORD_CLEAR_N", "H_LVT3_CATERR_DLY_N", "FM_CPU_OL_INT_R_N", "", "", + "", "", + /* Z0 - Z7 */ + "FM_CPU_ERR0_LVT3_N", "FM_CPU_ERR1_LVT3_N", "BMC_MUX_VR_PCH_CPU_RST_INT_N", + "JTAG_MUX_LSP_SEL1", "", "JTAG_MUX_LSP_SEL4", "JTAG_MUX_LSP_SEL2", ""; + + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_gpio0_unbiased_default>; +}; + +&pinctrl { + pinctrl_gpio0_unbiased_default: gpio_default { + pins = "AB15", "AD14", "R23", "A18", "AD24", "AD15", "AE14", "AC15", "U25", "AA24", + "V24", "W26", "AA23", "V26", "U24", "V25", "AE15", "C15", "F15"; + bias-disable; + }; +}; + +&i2c1 { + status = "okay"; + + bmc_mux_nic: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + reset-gpios = <&gpio0 ASPEED_GPIO(R, 3) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + smb_pex_nic: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + + interrupt-parent = <&smb_pex_vr_ctrl>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <2>; + + vdd-supply = <&p3v3_aux>; + reset-gpios = <&gpio0 ASPEED_GPIO(Q, 3) GPIO_ACTIVE_HIGH>; + + gpio-reserved-ranges = <19 1>, <22 6>, <30 6>, <38 2>; + + gpio-line-names = + /* GPORT0 */ + "IRQ_NIC2_OVT_WRNG", "FM_NIC2_ALLSTANDBY_N", "IRQ_NIC2_OVT_SHTDN", + "SMB_VR_PVCORE_NIC2_ALERT_N", "FM_NIC2_PERST1_N", + "SMB_NIC2_ALERT_N", "FM_NIC2_PERST3_N", "FM_NIC2_PERST2_N", + /* GPORT1 */ + "FM_NIC1_RST_N", "FM_NIC1_PERST0_N", "FM_NIC1_PERST2_N", + "FM_NIC1_PERST3_N", "SMB_NIC1_ALERT_N", "FM_NIC1_PERST1_N", + "SMB_VR_PVCORE_NIC1_ALERT_N", "IRQ_NIC1_OVT_SHTDN", + /* GPORT2 */ + "SMB_VR_P3V3_NIC_ALERT_N", "FM_NIC2_FLASH_PRSNT", + "FM_NIC1_FLASH_PRSNT", "", + /* GPORT3 */ + "FM_NIC2_PERST0_N", "FM_NIC2_RST_N", "", "", "", "", "", "", + /* GPORT4 */ + "FM_NIC1_ALLSTANDBY_N", "IRQ_NIC1_OVT_WRNG", "", "", "", "", "", "", + /* GPORT5 */ + "SMB_VR_P1V8_NIC_ALERT_N", "SMB_VR_P1V2_NIC_ALERT_N", "", ""; + + pinctrl-0 = <&U62160_pins>; + pinctrl-names = "default"; + U62160_pins: cfg-pins { + pins = "gp03", "gp16", "gp20", "gp50", "gp51"; + function = "gpio"; + input-enable; + bias-pull-up; + }; + }; + }; + + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + pvcore_nic2: ir38263-pvcore-nic2@40 { + compatible = "infineon,ir38263"; + reg = <0x40>; + + regulator-name = "pvcore_nic2"; + regulator-enable-ramp-delay = <2000>; + vin-supply = <&p12v>; + }; + }; + + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + pvcore_nic1: ir38263-pvcore-nic1@40 { + compatible = "infineon,ir38263"; + reg = <0x40>; + + regulator-name = "pvcore_nic1"; + regulator-enable-ramp-delay = <2000>; + vin-supply = <&p12v>; + }; + }; + + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + p3v3_nic: ir38263-p3v3-nic@40 { + compatible = "infineon,ir38263"; + reg = <0x40>; + + regulator-name = "p3v3_nic"; + regulator-enable-ramp-delay = <2000>; + vin-supply = <&p12v>; + }; + }; + + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + p1v2_nic: ir38263-p1v2-nic@40 { + compatible = "infineon,ir38263"; + reg = <0x40>; + + regulator-name = "p1v2_nic"; + regulator-enable-ramp-delay = <2000>; + vin-supply = <&p12v>; + }; + }; + + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + p1v8_nic: ir38263-p1v8-nic@40 { + compatible = "infineon,ir38263"; + reg = <0x40>; + + regulator-name = "p1v8_nic"; + regulator-enable-ramp-delay = <2000>; + vin-supply = <&p12v>; + }; + }; + }; +}; + +&i2c2 { + status = "okay"; +}; + +&i2c3 { + status = "okay"; + + i2cmux1: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio0 ASPEED_GPIO(R, 7) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + smb_m2_ssb_ssd1: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p3v3_aux>; + + interrupt-parent = <&smb_pex_vr_ctrl>; + interrupts = <30 IRQ_TYPE_LEVEL_LOW>; + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "m2_ssb_ssd1:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_smb_m2_ssb_ssd1: sw0 { + shunt-resistor-micro-ohms = <12000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <2800000>; + regulator-name = "p3v3_m2_ssd1"; + regulator-enable-ramp-delay = <10000>; + }; + }; + }; + }; + + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + smb_m2_ssb_ssd2: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + + interrupt-parent = <&smb_pex_vr_ctrl>; + interrupts = <39 IRQ_TYPE_LEVEL_LOW>; + vss1-supply = <&p3v3_aux>; + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "m2_ssb_ssd2:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_smb_m2_ssb_ssd2: sw0 { + shunt-resistor-micro-ohms = <12000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <2800000>; + regulator-name = "p3v3_m2_ssd2"; + regulator-enable-ramp-delay = <10000>; + }; + }; + }; + }; + + i2c@6 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@7 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; +}; + +&i2c4 { + status = "okay"; + multi-master; + bus-frequency = <1000000>; + + bmc-slave@10 { + compatible = "ipmb-dev"; + reg = <(0x10 | I2C_OWN_SLAVE_ADDRESS)>; + + i2c-protocol; + }; +}; + +&i2c5 { + status = "okay"; + + i2cmux2: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio0 ASPEED_GPIO(Z, 2) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + p1v05_pch_aux: ir38263-p1v05-pch-aux@40 { + compatible = "infineon,ir38263"; + reg = <0x40>; + + regulator-name = "p1v05_pch_aux"; + regulator-enable-ramp-delay = <2000>; + vin-supply = <&p12v>; + }; + }; + + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + p1v8_pch_aux: ir38060-p1v8-pch-aux@40 { + compatible = "infineon,ir38060"; + reg = <0x40>; + + regulator-name = "p1v8_pch_aux"; + regulator-enable-ramp-delay = <2000>; + vin-supply = <&p12v>; + }; + }; + + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; +}; + +&i2c14 { + status = "okay"; + + i2cmux13: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio0 ASPEED_GPIO(R, 6) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + smb_pex_cpu0_event: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + + interrupt-parent = <&smb_pex_vr_ctrl>; + interrupts = <10 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <2>; + + vdd-supply = <&p3v3_aux>; + reset-gpios = <&smb_svc_pex_cpu0_led 16 GPIO_ACTIVE_HIGH>; + + gpio-reserved-ranges = <14 2>, <21 1>, <25 3>, <33 1>; + + gpio-line-names = + /* GPORT0 */ + "PWRGD_CHD_CPU0", "PWRGD_CHC_CPU0", + "PWRGD_CHB_CPU0", "PWRGD_CHA_CPU0", + "PWRGD_CHE_CPU0", "PWRGD_CHF_CPU0", + "PWRGD_CHG_CPU0", "PWRGD_CHH_CPU0", + /* GPORT1 */ + "SMB_VR_PVPP_HBM_CPU0_ALERT_N", "SMB_VR_PVCCINFAON_CPU0_ALERT_N", + "SMB_VR_PVNN_MAIN_CPU0_ALERT_N", "SMB_VR_PVCCD_HV_CPU0_ALERT_N", + "SMB_VR_PVCCIN_CPU0_ALERT_N", "SEL_SMB_DIMM_CPU0", + "", "", + /* GPORT2 */ + "PWRGD_LVC3_CPU0_AB_DRAM_G", "PWRGD_LVC3_CPU0_CD_DRAM_G", + "PWRGD_LVC3_CPU0_EF_DRAM_G", "PWRGD_LVC3_CPU0_GH_DRAM_G", + /* GPORT3 */ + "FM_CPU0_DISABLE_COD_N", "", + "RST_LVC3_CPU0_RESET_N", "PWRGD_LVC3_CPU0_PWRGOOD", + "PWRGD_PLT_AUX_CPU0_LVT3", "", + "", "", + /* GPORT4 */ + "H_LVT3_CPU0_PROCHOT_N", "H_LVT3_CPU0_MEMHOT_IN_N", + "H_LVT3_CPU0_MEMHOT_OUT_N", "H_LVT3_CPU0_MEMTRIP_OUT_N", + "H_LVT3_CPU0_THERMTRIP_OUT_N", "", + "H_LVT3_CPU0_NMI", "FM_S3M_CPU0_CD_INIT_ERROR", + /* GPORT5 */ + "FM_CPU0_PKG_ID0", "FM_CPU0_PKG_ID1", + "FM_CPU0_PROC_ID0", "FM_CPU0_PROC_ID1"; + + pinctrl-0 = <&U62080_pins>; + pinctrl-names = "default"; + U62080_pins: cfg-pins { + pins = "gp10", "gp11", "gp12", "gp13", "gp14"; + function = "gpio"; + input-enable; + bias-pull-up; + }; + }; + }; + + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + pvccinfaon-pvccfa-cpu0@58 { + compatible = "mps,mp2971"; + reg = <0x58>; + interrupt-parent = <&smb_pex_cpu0_event>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvccinfaon_cpu0: vout0 { + regulator-name = "pvccinfaon_cpu0"; + regulator-enable-ramp-delay = <200>; + }; + pvccfa_ehv_cpu0: vout1 { + regulator-name = "pvccfa_ehv_cpu0"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + tda38640-pvnn-main-cpu0@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu0_event>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvnn_main_cpu0: vout { + regulator-name = "pvnn_main_cpu0"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + mp2973-pvccin-pvccfa-cpu0@58 { + compatible = "mps,mp2973"; + reg = <0x58>; + interrupt-parent = <&smb_pex_cpu0_event>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvccin_cpu0: vout0 { + regulator-name = "pvccin_cpu0"; + regulator-enable-ramp-delay = <200>; + }; + pvccfa_ehv_fivra_cpu0: vout1 { + regulator-name = "pvccfa_ehv_fivra_cpu0"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + tda38640-pvccd-hv-cpu0@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu0_event>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + infineon,en-pin-fixed-level; + + regulators { + pvccd_hv_cpu0: vout { + regulator-name = "pvccd_hv_cpu0"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + tda38640-pvpp-hbm-cpu0@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu0_event>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvpp_hbm_cpu0: vout { + regulator-name = "pvpp_hbm_cpu0"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; +}; + +&i2c7 { + status = "okay"; + + i2cmux4: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio0 ASPEED_GPIO(F, 3) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + smb_pex_cpu1_event: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + + interrupt-parent = <&smb_pex_vr_ctrl>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <2>; + + vdd-supply = <&p3v3_aux>; + reset-gpios = <&smb_svc_pex_cpu1_led 16 GPIO_ACTIVE_HIGH>; + + gpio-reserved-ranges = <14 2>, <21 1>, <25 3>, <33 1>; + + gpio-line-names = + /* GPORT0 */ + "PWRGD_CHD_CPU1", "PWRGD_CHC_CPU1", + "PWRGD_CHB_CPU1", "PWRGD_CHA_CPU1", + "PWRGD_CHE_CPU1", "PWRGD_CHF_CPU1", + "PWRGD_CHG_CPU1", "PWRGD_CHH_CPU1", + /* GPORT1 */ + "SMB_VR_PVPP_HBM_CPU1_ALERT_N", "SMB_VR_PVCCINFAON_CPU1_ALERT_N", + "SMB_VR_PVNN_MAIN_CPU1_ALERT_N", "SMB_VR_PVCCD_HV_CPU1_ALERT_N", + "SMB_VR_PVCCIN_CPU1_ALERT_N", "SEL_SMB_DIMM_CPU1", + "", "", + /* GPORT2 */ + "PWRGD_LVC3_CPU1_AB_DRAM_G", "PWRGD_LVC3_CPU1_CD_DRAM_G", + "PWRGD_LVC3_CPU1_EF_DRAM_G", "PWRGD_LVC3_CPU1_GH_DRAM_G", + /* GPORT3 */ + "FM_CPU1_DISABLE_COD_N", "", + "RST_LVC3_CPU1_RESET_N", "PWRGD_LVC3_CPU1_PWRGOOD", + "PWRGD_PLT_AUX_CPU1_LVT3", "", + "", "", + /* GPORT4 */ + "H_LVT3_CPU1_PROCHOT_N", "H_LVT3_CPU1_MEMHOT_IN_N", + "H_LVT3_CPU1_MEMHOT_OUT_N", "H_LVT3_CPU1_MEMTRIP_OUT_N", + "H_LVT3_CPU1_THERMTRIP_OUT_N", "", + "H_LVT3_CPU1_NMI", "FM_S3M_CPU1_CD_INIT_ERROR", + /* GPORT5 */ + "FM_CPU1_PKG_ID0", "FM_CPU1_PKG_ID1", + "FM_CPU1_PROC_ID0", "FM_CPU1_PROC_ID1"; + + pinctrl-0 = <&U62090_pins>; + pinctrl-names = "default"; + U62090_pins: cfg-pins { + pins = "gp10", "gp11", "gp12", "gp13", "gp14"; + function = "gpio"; + input-enable; + bias-pull-up; + }; + }; + }; + + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + pvccinfaon-pvccfa-cpu1@58 { + compatible = "mps,mp2971"; + reg = <0x58>; + interrupt-parent = <&smb_pex_cpu1_event>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvccinfaon_cpu1: vout0 { + regulator-name = "pvccinfaon_cpu1"; + regulator-enable-ramp-delay = <200>; + }; + pvccfa_ehv_cpu1: vout1 { + regulator-name = "pvccfa_ehv_cpu1"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + tda38640-pvnn-main-cpu1@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu1_event>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvnn_main_cpu1: vout { + regulator-name = "pvnn_main_cpu1"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + mp2973-pvccin-pvccfa-cpu1@58 { + compatible = "mps,mp2973"; + reg = <0x58>; + interrupt-parent = <&smb_pex_cpu1_event>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvccin_cpu1: vout0 { + regulator-name = "pvccin_cpu1"; + regulator-enable-ramp-delay = <200>; + }; + pvccfa_ehv_fivra_cpu1: vout1 { + regulator-name = "pvccfa_ehv_fivra_cpu1"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + tda38640-pvccd-hv-cpu1@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu1_event>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + infineon,en-pin-fixed-level; + + regulators { + pvccd_hv_cpu1: vout { + regulator-name = "pvccd_hv_cpu1"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + tda38640-pvpp-hbm-cpu1@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu1_event>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvpp_hbm_cpu1: vout { + regulator-name = "pvpp_hbm_cpu1"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; +}; + +&i2c6 { + status = "okay"; + + i2cmux3: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + smb_pex_cpu2_event: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + + interrupt-parent = <&smb_pex_vr_ctrl>; + interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <2>; + + vdd-supply = <&p3v3_aux>; + reset-gpios = <&smb_svc_pex_cpu2_led 16 GPIO_ACTIVE_HIGH>; + + gpio-reserved-ranges = <14 2>, <21 1>, <25 3>, <33 1>; + + gpio-line-names = + /* GPORT0 */ + "PWRGD_CHD_CPU2", "PWRGD_CHC_CPU2", + "PWRGD_CHB_CPU2", "PWRGD_CHA_CPU2", + "PWRGD_CHE_CPU2", "PWRGD_CHF_CPU2", + "PWRGD_CHG_CPU2", "PWRGD_CHH_CPU2", + /* GPORT1 */ + "SMB_VR_PVPP_HBM_CPU2_ALERT_N", "SMB_VR_PVCCINFAON_CPU2_ALERT_N", + "SMB_VR_PVNN_MAIN_CPU2_ALERT_N", "SMB_VR_PVCCD_HV_CPU2_ALERT_N", + "SMB_VR_PVCCIN_CPU2_ALERT_N", "SEL_SMB_DIMM_CPU2", + "", "", + /* GPORT2 */ + "PWRGD_LVC3_CPU2_AB_DRAM_G", "PWRGD_LVC3_CPU2_CD_DRAM_G", + "PWRGD_LVC3_CPU2_EF_DRAM_G", "PWRGD_LVC3_CPU2_GH_DRAM_G", + /* GPORT3 */ + "FM_CPU2_DISABLE_COD_N", "", + "RST_LVC3_CPU2_RESET_N", "PWRGD_LVC3_CPU2_PWRGOOD", + "PWRGD_PLT_AUX_CPU2_LVT3", "", + "", "", + /* GPORT4 */ + "H_LVT3_CPU2_PROCHOT_N", "H_LVT3_CPU2_MEMHOT_IN_N", + "H_LVT3_CPU2_MEMHOT_OUT_N", "H_LVT3_CPU2_MEMTRIP_OUT_N", + "H_LVT3_CPU2_THERMTRIP_OUT_N", "", + "H_LVT3_CPU2_NMI", "FM_S3M_CPU2_CD_INIT_ERROR", + /* GPORT5 */ + "FM_CPU2_PKG_ID0", "FM_CPU2_PKG_ID1", + "FM_CPU2_PROC_ID0", "FM_CPU2_PROC_ID1"; + + pinctrl-0 = <&U62100_pins>; + pinctrl-names = "default"; + U62100_pins: cfg-pins { + pins = "gp10", "gp11", "gp12", "gp13", "gp14"; + function = "gpio"; + input-enable; + bias-pull-up; + }; + }; + }; + + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + pvccinfaon-pvccfa-cpu2@58 { + compatible = "mps,mp2971"; + reg = <0x58>; + interrupt-parent = <&smb_pex_cpu2_event>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvccinfaon_cpu2: vout0 { + regulator-name = "pvccinfaon_cpu2"; + regulator-enable-ramp-delay = <200>; + }; + pvccfa_ehv_cpu2: vout1 { + regulator-name = "pvccfa_ehv_cpu2"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + tda38640-pvnn-main-cpu2@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu2_event>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvnn_main_cpu2: vout { + regulator-name = "pvnn_main_cpu2"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + mp2973-pvccin-pvccfa-cpu2@58 { + compatible = "mps,mp2973"; + reg = <0x58>; + interrupt-parent = <&smb_pex_cpu2_event>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvccin_cpu2: vout0 { + regulator-name = "pvccin_cpu2"; + regulator-enable-ramp-delay = <200>; + }; + pvccfa_ehv_fivra_cpu2: vout1 { + regulator-name = "pvccfa_ehv_fivra_cpu2"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + tda38640-pvccd-hv-cpu2@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu2_event>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + infineon,en-pin-fixed-level; + + regulators { + pvccd_hv_cpu2: vout { + regulator-name = "pvccd_hv_cpu2"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + tda38640-pvpp-hbm-cpu2@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu2_event>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvpp_hbm_cpu2: vout { + regulator-name = "pvpp_hbm_cpu2"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; +}; + +&i2c12 { + status = "okay"; + + i2cmux22: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio0 ASPEED_GPIO(P, 2) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + smb_pex_cpu3_event: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + + interrupt-parent = <&smb_pex_vr_ctrl>; + interrupts = <11 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <2>; + + vdd-supply = <&p3v3_aux>; + reset-gpios = <&smb_svc_pex_cpu3_led 16 GPIO_ACTIVE_HIGH>; + + gpio-reserved-ranges = <14 2>, <21 1>, <25 3>, <33 1>; + + gpio-line-names = + /* GPORT0 */ + "PWRGD_CHD_CPU3", "PWRGD_CHC_CPU3", + "PWRGD_CHB_CPU3", "PWRGD_CHA_CPU3", + "PWRGD_CHE_CPU3", "PWRGD_CHF_CPU3", + "PWRGD_CHG_CPU3", "PWRGD_CHH_CPU3", + /* GPORT1 */ + "SMB_VR_PVPP_HBM_CPU3_ALERT_N", "SMB_VR_PVCCINFAON_CPU3_ALERT_N", + "SMB_VR_PVNN_MAIN_CPU3_ALERT_N", "SMB_VR_PVCCD_HV_CPU3_ALERT_N", + "SMB_VR_PVCCIN_CPU3_ALERT_N", "SEL_SMB_DIMM_CPU3", + "", "", + /* GPORT2 */ + "PWRGD_LVC3_CPU3_AB_DRAM_G", "PWRGD_LVC3_CPU3_CD_DRAM_G", + "PWRGD_LVC3_CPU3_EF_DRAM_G", "PWRGD_LVC3_CPU3_GH_DRAM_G", + /* GPORT3 */ + "FM_CPU3_DISABLE_COD_N", "", + "RST_LVC3_CPU3_RESET_N", "PWRGD_LVC3_CPU3_PWRGOOD", + "PWRGD_PLT_AUX_CPU3_LVT3", "", + "", "", + /* GPORT4 */ + "H_LVT3_CPU3_PROCHOT_N", "H_LVT3_CPU3_MEMHOT_IN_N", + "H_LVT3_CPU3_MEMHOT_OUT_N", "H_LVT3_CPU3_MEMTRIP_OUT_N", + "H_LVT3_CPU3_THERMTRIP_OUT_N", "", + "H_LVT3_CPU3_NMI", "FM_S3M_CPU3_CD_INIT_ERROR", + /* GPORT5 */ + "FM_CPU3_PKG_ID0", "FM_CPU3_PKG_ID1", + "FM_CPU3_PROC_ID0", "FM_CPU3_PROC_ID1"; + + pinctrl-0 = <&U62110_pins>; + pinctrl-names = "default"; + U62110_pins: cfg-pins { + pins = "gp10", "gp11", "gp12", "gp13", "gp14"; + function = "gpio"; + input-enable; + bias-pull-up; + }; + }; + }; + + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + pvccinfaon-pvccfa-cpu3@58 { + compatible = "mps,mp2971"; + reg = <0x58>; + interrupt-parent = <&smb_pex_cpu3_event>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvccinfaon_cpu3: vout0 { + regulator-name = "pvccinfaon_cpu3"; + regulator-enable-ramp-delay = <200>; + }; + pvccfa_ehv_cpu3: vout1 { + regulator-name = "pvccfa_ehv_cpu3"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + tda38640-pvnn-main-cpu3@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu3_event>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvnn_main_cpu3: vout { + regulator-name = "pvnn_main_cpu3"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + mp2973-pvccin-pvccfa-cpu3@58 { + compatible = "mps,mp2973"; + reg = <0x58>; + interrupt-parent = <&smb_pex_cpu3_event>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvccin_cpu3: vout0 { + regulator-name = "pvccin_cpu3"; + regulator-enable-ramp-delay = <200>; + }; + pvccfa_ehv_fivra_cpu3: vout1 { + regulator-name = "pvccfa_ehv_fivra_cpu3"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + tda38640-pvccd-hv-cpu3@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu3_event>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + infineon,en-pin-fixed-level; + + regulators { + pvccd_hv_cpu3: vout { + regulator-name = "pvccd_hv_cpu3"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + tda38640-pvpp-hbm-cpu3@40 { + compatible = "infineon,tda38640"; + reg = <0x40>; + interrupt-parent = <&smb_pex_cpu3_event>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; + + regulators { + pvpp_hbm_cpu3: vout { + regulator-name = "pvpp_hbm_cpu3"; + regulator-enable-ramp-delay = <200>; + }; + }; + }; + }; + + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; +}; + +&i2c15 { + status = "okay"; + + i2cmux14: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio0 ASPEED_GPIO(R, 1) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux15: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 11 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux16: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 2 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux17: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 0 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux18: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 3 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux19: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 9 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + smb_pex_rssd17_32: pinctrl@20 { + compatible = "cypress,cy8c9560"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + + interrupt-parent = <&bmc_pex_irq>; + interrupts = <13 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <2>; + + vdd-supply = <&p3v3_aux>; + reset-gpios = <&bmc_pex_irq 19 GPIO_ACTIVE_HIGH>; + + gpio-reserved-ranges = <48 12>; + + gpio-line-names = + /* GPORT0 */ + "RSSD17_SMBRST_N", "RSSD18_SMBRST_N", + "RSSD19_SMBRST_N", "RSSD20_SMBRST_N", + "RSSD21_SMBRST_N", "RSSD22_SMBRST_N", + "RSSD23_SMBRST_N", "RSSD24_SMBRST_N", + /* GPORT1 */ + "RSSD25_SMBRST_N", "RSSD26_SMBRST_N", + "RSSD27_SMBRST_N", "RSSD28_SMBRST_N", + "RSSD29_SMBRST_N", "RSSD30_SMBRST_N", + "RSSD31_SMBRST_N", "RSSD32_SMBRST_N", + /* GPORT2 */ + "RSSD17_PWRDIS", "RSSD18_PWRDIS", + "RSSD19_PWRDIS", "RSSD20_PWRDIS", + /* GPORT3 */ + "RSSD21_PWRDIS", "RSSD22_PWRDIS", + "RSSD23_PWRDIS", "RSSD24_PWRDIS", + "RSSD25_PWRDIS", "RSSD26_PWRDIS", + "RSSD27_PWRDIS", "RSSD28_PWRDIS", + /* GPORT4 */ + "RSSD29_PWRDIS", "RSSD30_PWRDIS", + "RSSD31_PWRDIS", "RSSD32_PWRDIS", + "RSSD17_RESET_N", "RSSD18_RESET_N", + "RSSD19_RESET_N", "RSSD20_RESET_N", + /* GPORT5 */ + "RSSD21_RESET_N", "RSSD22_RESET_N", + "RSSD23_RESET_N", "RSSD24_RESET_N", + "RSSD25_RESET_N", "RSSD26_RESET_N", + "RSSD27_RESET_N", "RSSD28_RESET_N", + /* GPORT6 */ + "RSSD29_RESET_N", "RSSD30_RESET_N", + "RSSD31_RESET_N", "RSSD32_RESET_N", + "", "", + "", "", + /* GPORT7 */ + "", "", + "", "", + "", "", + "", ""; + }; + }; + + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux20: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 4 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + }; + + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux21: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 5 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + }; + }; +}; + +&i2c8 { + status = "okay"; + + i2cmux5: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio0 ASPEED_GPIO(R, 0) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux6: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 16 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux7: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 7 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux8: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 1 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux9: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 10 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux10: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 15 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + }; + }; + + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + smb_pex_rssd_01_16: pinctrl@20 { + compatible = "cypress,cy8c9560"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + + interrupt-parent = <&bmc_pex_irq>; + interrupts = <6 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <2>; + + vdd-supply = <&p3v3_aux>; + reset-gpios = <&bmc_pex_irq 18 GPIO_ACTIVE_HIGH>; + + gpio-reserved-ranges = <48 12>; + + gpio-line-names = + /* GPORT0 */ + "RSSD01_SMBRST_N", "RSSD02_SMBRST_N", + "RSSD03_SMBRST_N", "RSSD04_SMBRST_N", + "RSSD05_SMBRST_N", "RSSD06_SMBRST_N", + "RSSD07_SMBRST_N", "RSSD08_SMBRST_N", + /* GPORT1 */ + "RSSD09_SMBRST_N", "RSSD10_SMBRST_N", + "RSSD11_SMBRST_N", "RSSD12_SMBRST_N", + "RSSD13_SMBRST_N", "RSSD14_SMBRST_N", + "RSSD15_SMBRST_N", "RSSD16_SMBRST_N", + /* GPORT2 */ + "RSSD01_PWRDIS", "RSSD02_PWRDIS", + "RSSD03_PWRDIS", "RSSD04_PWRDIS", + /* GPORT3 */ + "RSSD05_PWRDIS", "RSSD06_PWRDIS", + "RSSD07_PWRDIS", "RSSD08_PWRDIS", + "RSSD09_PWRDIS", "RSSD10_PWRDIS", + "RSSD11_PWRDIS", "RSSD12_PWRDIS", + /* GPORT4 */ + "RSSD13_PWRDIS", "RSSD14_PWRDIS", + "RSSD15_PWRDIS", "RSSD16_PWRDIS", + "RSSD01_RESET_N", "RSSD02_RESET_N", + "RSSD03_RESET_N", "RSSD04_RESET_N", + /* GPORT5 */ + "RSSD05_RESET_N", "RSSD06_RESET_N", + "RSSD07_RESET_N", "RSSD08_RESET_N", + "RSSD09_RESET_N", "RSSD10_RESET_N", + "RSSD11_RESET_N", "RSSD12_RESET_N", + /* GPORT6 */ + "RSSD13_RESET_N", "RSSD14_RESET_N", + "RSSD15_RESET_N", "RSSD16_RESET_N", + "", "", + "", "", + /* GPORT7 */ + "", "", + "", "", + "", "", + "", ""; + }; + }; + + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux11: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 12 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + }; + + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + i2cmux12: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&bmc_pex_irq 14 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_aux>; + + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + }; + }; +}; + +&i2c13 { + status = "okay"; + + i2cmux23: mux@77 { + compatible = "maxim,max7357"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio0 ASPEED_GPIO(R, 4) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_bmc_aux>; + }; +}; + +&i2cmux23 { + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + smb_pex_vr_ctrl: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <2>; + vdd-supply = <&p3v3_bmc_aux>; + reset-gpios = <&gpio0 ASPEED_GPIO(Q, 2) GPIO_ACTIVE_HIGH>; + gpio-line-names = + /* GPORT0 */ + "BCM0_INPUT_DISABLE_N", "SMB_VR_P3V3_AUX_ALERT_N", + "SMB_PEX_CPU1_EVENT_INT", "SMB_PEX_CPU2_EVENT_INT", + "DPIC0_VOLTAGE_DETECTB_N", "DPIC0_VOLTAGE_DETECTA_N", + "DPIC1_VOLTAGE_DETECTA_N", "DPIC1_VOLTAGE_DETECTB_N", + /* GPORT1 */ + "SMB_PEX_NIC_INT", "SMB_VR_P1V05_PCH_AUX_ALERT_N", + "SMB_PEX_CPU0_EVENT_INT", "SMB_PEX_CPU3_EVENT_INT", + "LED_ID_TPM", "PLUG_DETECT_TPM", + "PLUG_DETECT_M2_SSD_CARRIER1", "RST_M2_SSD1_PERST_N", + /* GPORT2 */ + "LED_ID_BAT", "LED_ID_MGMT_PORT2", + "LED_ID_MGMT_PORT1", "SMB_VR_P5V_AUX_ALERT_N", + /* GPORT3 */ + "SMB_VR_AUX_SSB_ALERT_N", "BCM1_INPUT_DISABLE_N", + "LED_ID_NIC1_PORT1", "LED_ID_NIC1_PORT2", + "LED_ID_NIC2_PORT1", "LED_ID_NIC2_PORT2", + "RST_M2_SSD2_PERST_N", "PLUG_DETECT_M2_SSD2", + /* GPORT4 */ + "PLUG_DETECT_BAT", "PLUG_DETECT_M2_SSD1", + "M2_SSD1_SSB_ALERT_N", "BCM2_INPUT_DISABLE_N", + "SMB_VR_P1V8_PCH_AUX_ALERT_N", "BCM3_INPUT_DISABLE_N", + "LED_PWR_DWR_BACK", "LED_ID_DWR_BACK_P", + /* GPORT5 */ + "LED_ID_M2_SSD2", "LED_ID_M2_SSD1", + "PLUG_DETECT_M2_SSD_CARRIER2", "M2_SSD2_SSB_ALERT_N"; + + pinctrl-0 = <&U62120_input &U62120_input_pullup>; + pinctrl-names = "default"; + U62120_input: input-pins { + pins = "gp10"; + function = "gpio"; + input-enable; + bias-disable; + }; + U62120_input_pullup: input-pullup-pins { + pins = "gp01", "gp02", "gp03", "gp11", "gp12", "gp13", + "gp23", "gp30", "gp40", "gp42", "gp44", "gp53"; + function = "gpio"; + input-enable; + bias-pull-up; + }; + }; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + bmc_pex_irq: pinctrl@20 { + compatible = "cypress,cy8c9520"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <2>; + vdd-supply = <&p3v3_aux>; + reset-gpios = <&gpio0 ASPEED_GPIO(Q, 1) GPIO_ACTIVE_HIGH>; + gpio-line-names = + /* GPORT0 */ + "SMB_MUX_PWM_FANGRP2_RST_INT_N", "SMB_MUX_SSB_FANGRP2_RST_INT_N", + "SMB_MUX_PWM_FANGRP1_RST_INT_N", "SMB_MUX_SSB_RSSD01_08_RST_INT_N", + "SMB_MUX_RSSD01_08_RST_INT_N", "SMB_MUX_RSSD09_16_RST_INT_N", + "SMB_PEX_RSSD01_16_INT", "SMB_MUX_SSB_FANGRP1_RST_INT_N", + /* GPORT1 */ + "SMB_SVC_PEX_FAN_ALERT_INT", "SMB_MUX_SSB_RSSD09_16_RST_INT_N", + "SMB_MUX_SSB_RSSD17_24_RST_INT_N", "SMB_MUX_PWM_FANGRP0_RST_INT_N", + "SMB_MUX_RSSD17_24_RST_INT_N", "SMB_PEX_RSSD17_32_INT", + "SMB_MUX_RSSD25_32_RST_INT_N", "SMB_MUX_SSB_RSSD25_32_RST_INT_N", + /* GPORT2 */ + "SMB_MUX_SSB_FANGRP0_RST_INT_N", "PEX_FAN_ALERT_RST", + "PEX_RSSD01_16_RST", "PEX_RSSD17_32_RST"; + pinctrl-0 = <&U60000_pins>; + pinctrl-names = "default"; + U60000_pins: cfg-pins { + pins = "gp06", "gp10", "gp15"; + function = "gpio"; + input-enable; + bias-disable; + }; + }; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + i2cmux24: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + + vdd-supply = <&p3v3_bmc_aux>; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + eeprom@51 { + compatible = "atmel,24c32"; + reg = <0x51>; + pagesize = <32>; + vcc-supply = <&p3v3_bmc_aux>; + }; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + i2cmux25: mux@70 { + compatible = "maxim,max7357"; + reg = <0x70>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; +}; + +&i2cmux25 { + reset-gpios = <&gpio0 ASPEED_GPIO(R, 2) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + vdd-supply = <&p3v3_bmc_aux>; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + p5v_aux: ir38263-p5v-aux@40 { + compatible = "infineon,ir38263"; + reg = <0x40>; + + regulator-name = "p5v_aux"; + regulator-enable-ramp-delay = <2000>; + vin-supply = <&p12v>; + vbus-supply = <&p3v3_bmc_aux>; + regulator-always-on; + regulator-boot-on; + }; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + p3v3_aux: ir38263-p3v3-aux@40 { + compatible = "infineon,ir38263"; + reg = <0x40>; + + vin-supply = <&p12v>; + regulator-name = "p3v3_aux"; + /* + * 2msec for regulator + 18msec for board capacitance + * Note: Every IC has a PTC which slowly charges the bypass + * cap. + */ + regulator-enable-ramp-delay = <200000>; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + aux_ssb: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_pex_vr_ctrl>; + interrupts = <20 IRQ_TYPE_LEVEL_LOW>; + vss1-supply = <&p5v_aux>; + vss2-supply = <&p3v3_aux>; + regulators { + p5v: sw0 { + regulator-name = "p5v"; + shunt-resistor-micro-ohms = <12000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <100000>; + }; + p3v3_pch: sw1 { + regulator-name = "p3v3_pch"; + shunt-resistor-micro-ohms = <12000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <100000>; + }; + }; + }; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + pli1209bc_p12v_a: regulator@5f { + compatible = "vicor,pli1209bc"; + reg = <0x5f>; + regulators { + p12v_a: vout2 { + regulator-name = "bcm0"; + regulator-boot-on; + }; + }; + }; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + pli1209bc_p12v_b: regulator@5f { + compatible = "vicor,pli1209bc"; + reg = <0x5f>; + regulators { + p12v_b: vout2 { + regulator-name = "bcm1"; + regulator-boot-on; + }; + }; + }; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + pli1209bc_p12v_c: regulator@5f { + compatible = "vicor,pli1209bc"; + reg = <0x5f>; + regulators { + p12v_c: vout2 { + regulator-name = "bcm2"; + regulator-boot-on; + }; + }; + }; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + pli1209bc_p12v_d: regulator@5f { + compatible = "vicor,pli1209bc"; + reg = <0x5f>; + regulators { + p12v_d: vout2 { + regulator-name = "bcm3"; + regulator-boot-on; + }; + }; + }; + }; +}; + +&i2cmux24 { + + reset-gpios = <&gpio0 ASPEED_GPIO(P, 3) (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + + i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + smb_svc_pex_rssd01_16: pinctrl@20 { + compatible = "cypress,cy8c9560"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <2>; + vdd-supply = <&p3v3_bmc_aux>; + reset-gpios = <&smb_svc_pex_cpu0_led 17 GPIO_ACTIVE_HIGH>; + gpio-line-names = + /* GPORT0 */ + "LED_ID_RSSD01", "LED_ID_RSSD02", + "LED_ID_RSSD03", "LED_ID_RSSD04", + "LED_ID_RSSD05", "LED_ID_RSSD06", + "LED_ID_RSSD07", "LED_ID_RSSD08", + /* GPORT1 */ + "LED_ID_RSSD09", "LED_ID_RSSD10", + "LED_ID_RSSD11", "LED_ID_RSSD12", + "LED_ID_RSSD13", "LED_ID_RSSD14", + "LED_ID_RSSD15", "LED_ID_RSSD16", + /* GPORT2 */ + "RSSD01_PRESENT_N", "RSSD02_PRESENT_N", + "RSSD03_PRESENT_N", "RSSD04_PRESENT_N", + /* GPORT3 */ + "RSSD05_PRESENT_N", "RSSD06_PRESENT_N", + "RSSD07_PRESENT_N", "RSSD08_PRESENT_N", + "RSSD09_PRESENT_N", "RSSD10_PRESENT_N", + "RSSD11_PRESENT_N", "RSSD12_PRESENT_N", + /* GPORT4 */ + "RSSD13_PRESENT_N", "RSSD14_PRESENT_N", + "RSSD15_PRESENT_N", "RSSD16_PRESENT_N", + "LED_ID_FAN_ASM01", "LED_ID_FAN_ASM02", + "LED_ID_FAN_ASM03", "LED_ID_FAN_ASM04", + /* GPORT5 */ + "LED_ID_FAN_ASM05", "LED_ID_FAN_ASM06", + "PLUG_DETECT_FAN_ASM01", "PLUG_DETECT_FAN_ASM02", + "PLUG_DETECT_FAN_ASM03", "PLUG_DETECT_FAN_ASM04", + "PLUG_DETECT_FAN_ASM05", "PLUG_DETECT_FAN_ASM06", + /* GPORT6 */ + "SSB_RSSD01_ALERT_N", "SSB_RSSD02_ALERT_N", + "SSB_RSSD03_ALERT_N", "SSB_RSSD04_ALERT_N", + "SSB_RSSD05_ALERT_N", "SSB_RSSD06_ALERT_N", + "SSB_RSSD07_ALERT_N", "SSB_RSSD08_ALERT_N", + /* GPORT7 */ + "SSB_RSSD09_ALERT_N", "SSB_RSSD10_ALERT_N", + "SSB_RSSD11_ALERT_N", "SSB_RSSD12_ALERT_N", + "SSB_RSSD13_ALERT_N", "SSB_RSSD14_ALERT_N", + "SSB_RSSD15_ALERT_N", "SSB_RSSD16_ALERT_N"; + pinctrl-0 = <&U65200_pins>; + pinctrl-names = "default"; + U65200_pins: cfg-pins { + pins = "gp60", "gp61", "gp62", + "gp63", "gp64", "gp65", "gp66", + "gp67", "gp70", "gp71", "gp72", + "gp73", "gp74", "gp75", "gp76", "gp77"; + function = "gpio"; + input-enable; + bias-pull-up; + }; + }; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + smb_svc_pex_rssd17_32: pinctrl@20 { + compatible = "cypress,cy8c9560"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <2>; + vdd-supply = <&p3v3_bmc_aux>; + reset-gpios = <&smb_svc_pex_cpu1_led 17 GPIO_ACTIVE_HIGH>; + gpio-line-names = + /* GPORT0 */ + "LED_ID_RSSD17", "LED_ID_RSSD18", + "LED_ID_RSSD19", "LED_ID_RSSD20", + "LED_ID_RSSD21", "LED_ID_RSSD22", + "LED_ID_RSSD23", "LED_ID_RSSD24", + /* GPORT1 */ + "LED_ID_RSSD25", "LED_ID_RSSD26", + "LED_ID_RSSD27", "LED_ID_RSSD28", + "LED_ID_RSSD29", "LED_ID_RSSD30", + "LED_ID_RSSD31", "LED_ID_RSSD32", + /* GPORT2 */ + "RSSD17_PRESENT_N", "RSSD18_PRESENT_N", + "RSSD19_PRESENT_N", "RSSD20_PRESENT_N", + /* GPORT3 */ + "RSSD21_PRESENT_N", "RSSD22_PRESENT_N", + "RSSD23_PRESENT_N", "RSSD24_PRESENT_N", + "RSSD25_PRESENT_N", "RSSD26_PRESENT_N", + "RSSD27_PRESENT_N", "RSSD28_PRESENT_N", + /* GPORT4 */ + "RSSD29_PRESENT_N", "RSSD30_PRESENT_N", + "RSSD31_PRESENT_N", "RSSD32_PRESENT_N", + "LED_ID_FAN_ASM07", "LED_ID_FAN_ASM08", + "LED_ID_FAN_ASM09", "LED_ID_FAN_ASM10", + /* GPORT5 */ + "LED_ID_FAN_ASM11", "LED_ID_FAN_ASM12", + "PLUG_DETECT_FAN_ASM07", "PLUG_DETECT_FAN_ASM08", + "PLUG_DETECT_FAN_ASM09", "PLUG_DETECT_FAN_ASM10", + "PLUG_DETECT_FAN_ASM11", "PLUG_DETECT_FAN_ASM12", + /* GPORT6 */ + "SSB_RSSD17_ALERT_N", "SSB_RSSD18_ALERT_N", + "SSB_RSSD19_ALERT_N", "SSB_RSSD20_ALERT_N", + "SSB_RSSD21_ALERT_N", "SSB_RSSD22_ALERT_N", + "SSB_RSSD23_ALERT_N", "SSB_RSSD24_ALERT_N", + /* GPORT7 */ + "SSB_RSSD25_ALERT_N", "SSB_RSSD26_ALERT_N", + "SSB_RSSD27_ALERT_N", "SSB_RSSD28_ALERT_N", + "SSB_RSSD29_ALERT_N", "SSB_RSSD30_ALERT_N", + "SSB_RSSD31_ALERT_N", "SSB_RSSD32_ALERT_N"; + pinctrl-0 = <&U65300_pins>; + pinctrl-names = "default"; + U65300_pins: cfg-pins { + pins = "gp60", "gp61", "gp62", + "gp63", "gp64", "gp65", "gp66", + "gp67", "gp70", "gp71", "gp72", + "gp73", "gp74", "gp75", "gp76", + "gp77"; + function = "gpio"; + input-enable; + bias-pull-up; + }; + }; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + smb_svc_pex_cpu1_led: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <2>; + vdd-supply = <&p3v3_bmc_aux>; + reset-gpios = <&gpio0 ASPEED_GPIO(Q, 5) GPIO_ACTIVE_HIGH>; + gpio-reserved-ranges = <18 2>, <36 2>; + gpio-line-names = + /* GPORT0 */ + "PLUG_DETECT_DIMM_C1E2", "PLUG_DETECT_DIMM_C1E1", + "PLUG_DETECT_DIMM_C1F2", "PLUG_DETECT_DIMM_C1F1", + "PLUG_DETECT_DIMM_C1G2", "PLUG_DETECT_DIMM_C1G1", + "PLUG_DETECT_DIMM_C1H2", "PLUG_DETECT_DIMM_C1H1", + /* GPORT1 */ + "PLUG_DETECT_DIMM_C1D1", "PLUG_DETECT_DIMM_C1D2", + "PLUG_DETECT_DIMM_C1C1", "PLUG_DETECT_DIMM_C1C2", + "PLUG_DETECT_DIMM_C1B1", "PLUG_DETECT_DIMM_C1B2", + "PLUG_DETECT_DIMM_C1A1", "PLUG_DETECT_DIMM_C1A2", + /* GPORT2 */ + "PEX_CPU1_EVENT_RST", "SVC_PEX_RSSD17_32_RST", + "", "", + /* GPORT3 */ + "LED_ID_DIMM_C1E2", "LED_ID_DIMM_C1E1", + "LED_ID_DIMM_C1F2", "LED_ID_DIMM_C1F1", + "LED_ID_DIMM_C1G2", "LED_ID_DIMM_C1G1", + "LED_ID_DIMM_C1H2", "LED_ID_DIMM_C1H1", + /* GPORT4 */ + "LED_ID_DIMM_C1A2", "LED_ID_DIMM_C1A1", + "LED_ID_DIMM_C1B2", "LED_ID_DIMM_C1B1", + "LED_ID_DIMM_C1C2", "LED_ID_DIMM_C1C1", + "LED_ID_DIMM_C1D2", "LED_ID_DIMM_C1D1", + /* GPORT5 */ + "", "", + "FM_CPU1_SKTOCC_N", "LED_ID_CPU1"; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + smb_svc_pex_fan_alert: pinctrl@20 { + compatible = "cypress,cy8c9560"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&bmc_pex_irq>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <2>; + vdd-supply = <&p3v3_aux>; + reset-gpios = <&bmc_pex_irq 17 GPIO_ACTIVE_HIGH>; + gpio-reserved-ranges = <24 3>, <51 9>; + gpio-line-names = + /* GPORT0 */ + "FAN01_SSB_ALERT_N", "FAN02_SSB_ALERT_N", + "FAN03_SSB_ALERT_N", "FAN04_SSB_ALERT_N", + "FAN05_SSB_ALERT_N", "FAN06_SSB_ALERT_N", + "FAN07_SSB_ALERT_N", "FAN08_SSB_ALERT_N", + /* GPORT1 */ + "FAN09_SSB_ALERT_N", "FAN10_SSB_ALERT_N", + "FAN11_SSB_ALERT_N", "FAN12_SSB_ALERT_N", + "FAN13_SSB_ALERT_N", "FAN14_SSB_ALERT_N", + "FAN15_SSB_ALERT_N", "FAN16_SSB_ALERT_N", + /* GPORT2 */ + "FAN17_SSB_ALERT_N", "FAN18_SSB_ALERT_N", + "FAN19_SSB_ALERT_N", "FAN20_SSB_ALERT_N", + /* GPORT3 */ + "FAN21_SSB_ALERT_N", "FAN22_SSB_ALERT_N", + "FAN23_SSB_ALERT_N", "FAN24_SSB_ALERT_N", + "", "", + "", "FAN01_PWM_ALERT_N", + /* GPORT4 */ + "FAN02_PWM_ALERT_N", "FAN03_PWM_ALERT_N", + "FAN04_PWM_ALERT_N", "FAN05_PWM_ALERT_N", + "FAN06_PWM_ALERT_N", "FAN07_PWM_ALERT_N", + "FAN08_PWM_ALERT_N", "FAN09_PWM_ALERT_N", + /* GPORT5 */ + "FAN10_PWM_ALERT_N", "FAN11_PWM_ALERT_N", + "FAN12_PWM_ALERT_N", "FAN13_PWM_ALERT_N", + "FAN14_PWM_ALERT_N", "FAN15_PWM_ALERT_N", + "FAN16_PWM_ALERT_N", "FAN17_PWM_ALERT_N", + /* GPORT6 */ + "FAN18_PWM_ALERT_N", "FAN19_PWM_ALERT_N", + "FAN20_PWM_ALERT_N", "FAN21_PWM_ALERT_N", + "FAN22_PWM_ALERT_N", "FAN23_PWM_ALERT_N", + "FAN24_PWM_ALERT_N", "", + /* GPORT7 */ + "", "", + "", "", + "", "", + "", ""; + pinctrl-0 = <&U65600_pins>; + pinctrl-names = "default"; + U65600_pins: cfg-pins { + pins = "gp00", "gp01", "gp02", + "gp03", "gp04", "gp05", "gp06", + "gp07", "gp10", "gp11", "gp12", + "gp13", "gp14", "gp15", "gp16", + "gp17", "gp20", "gp21", "gp22", + "gp23", "gp30", "gp31", "gp32", + "gp33", "gp37", "gp40", "gp41", + "gp42", "gp43", "gp44", "gp45", + "gp46", "gp47", "gp50", "gp51", + "gp52", "gp53", "gp54", "gp55", + "gp56", "gp57", "gp60", "gp61", + "gp62", "gp63", "gp64", "gp65", + "gp66"; + function = "gpio"; + input-enable; + bias-pull-up; + }; + }; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + smb_svc_pex_cpu2_led: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <2>; + vdd-supply = <&p3v3_bmc_aux>; + reset-gpios = <&gpio0 ASPEED_GPIO(Q, 6) GPIO_ACTIVE_HIGH>; + gpio-reserved-ranges = <17 3>, <36 2>; + gpio-line-names = + /* GPORT0 */ + "PLUG_DETECT_DIMM_C2E2", "PLUG_DETECT_DIMM_C2E1", + "PLUG_DETECT_DIMM_C2F2", "PLUG_DETECT_DIMM_C2F1", + "PLUG_DETECT_DIMM_C2G2", "PLUG_DETECT_DIMM_C2G1", + "PLUG_DETECT_DIMM_C2H2", "PLUG_DETECT_DIMM_C2H1", + /* GPORT1 */ + "PLUG_DETECT_DIMM_C2D1", "PLUG_DETECT_DIMM_C2D2", + "PLUG_DETECT_DIMM_C2C1", "PLUG_DETECT_DIMM_C2C2", + "PLUG_DETECT_DIMM_C2B1", "PLUG_DETECT_DIMM_C2B2", + "PLUG_DETECT_DIMM_C2A1", "PLUG_DETECT_DIMM_C2A2", + /* GPORT2 */ + "PEX_CPU2_EVENT_RST", "", + "", "", + /* GPORT3 */ + "LED_ID_DIMM_C2E2", "LED_ID_DIMM_C2E1", + "LED_ID_DIMM_C2F2", "LED_ID_DIMM_C2F1", + "LED_ID_DIMM_C2G2", "LED_ID_DIMM_C2G1", + "LED_ID_DIMM_C2H2", "LED_ID_DIMM_C2H1", + /* GPORT4 */ + "LED_ID_DIMM_C2A2", "LED_ID_DIMM_C2A1", + "LED_ID_DIMM_C2B2", "LED_ID_DIMM_C2B1", + "LED_ID_DIMM_C2C2", "LED_ID_DIMM_C2C1", + "LED_ID_DIMM_C2D2", "LED_ID_DIMM_C2D1", + /* GPORT5 */ + "", "", + "FM_CPU2_SKTOCC_N", "LED_ID_CPU2"; + }; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + smb_svc_pex_cpu3_led: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <2>; + vdd-supply = <&p3v3_bmc_aux>; + reset-gpios = <&gpio0 ASPEED_GPIO(Q, 7) GPIO_ACTIVE_HIGH>; + gpio-reserved-ranges = <17 3>; + gpio-line-names = + /* GPORT0 */ + "PLUG_DETECT_DIMM_C3E2", "PLUG_DETECT_DIMM_C3E1", + "PLUG_DETECT_DIMM_C3F2", "PLUG_DETECT_DIMM_C3F1", + "PLUG_DETECT_DIMM_C3G2", "PLUG_DETECT_DIMM_C3G1", + "PLUG_DETECT_DIMM_C3H2", "PLUG_DETECT_DIMM_C3H1", + /* GPORT1 */ + "PLUG_DETECT_DIMM_C3D1", "PLUG_DETECT_DIMM_C3D2", + "PLUG_DETECT_DIMM_C3C1", "PLUG_DETECT_DIMM_C3C2", + "PLUG_DETECT_DIMM_C3B1", "PLUG_DETECT_DIMM_C3B2", + "PLUG_DETECT_DIMM_C3A1", "PLUG_DETECT_DIMM_C3A2", + /* GPORT2 */ + "PEX_CPU3_EVENT_RST", "", + "", "", + /* GPORT3 */ + "LED_ID_DIMM_C3E2", "LED_ID_DIMM_C3E1", + "LED_ID_DIMM_C3F2", "LED_ID_DIMM_C3F1", + "LED_ID_DIMM_C3G2", "LED_ID_DIMM_C3G1", + "LED_ID_DIMM_C3H2", "LED_ID_DIMM_C3H1", + /* GPORT4 */ + "LED_ID_DIMM_C3A2", "LED_ID_DIMM_C3A1", + "LED_ID_DIMM_C3B2", "LED_ID_DIMM_C3B1", + "LED_ID_DIMM_C3C2", "LED_ID_DIMM_C3C1", + "LED_ID_DIMM_C3D2", "LED_ID_DIMM_C3D1", + /* GPORT5 */ + "LED_PWR_DWR_FRNT", "LED_ID_DWR_FRNT_P", + "FM_CPU3_SKTOCC_N", "LED_ID_CPU3"; + }; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + smb_svc_pex_cpu0_led: pinctrl@20 { + compatible = "cypress,cy8c9540"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <2>; + vdd-supply = <&p3v3_bmc_aux>; + reset-gpios = <&gpio0 ASPEED_GPIO(Q, 4) GPIO_ACTIVE_HIGH>; + gpio-reserved-ranges = <18 2>, <36 2>; + gpio-line-names = + /* GPORT0 */ + "PLUG_DETECT_DIMM_C0E2", "PLUG_DETECT_DIMM_C0E1", + "PLUG_DETECT_DIMM_C0F2", "PLUG_DETECT_DIMM_C0F1", + "PLUG_DETECT_DIMM_C0G2", "PLUG_DETECT_DIMM_C0G1", + "PLUG_DETECT_DIMM_C0H2", "PLUG_DETECT_DIMM_C0H1", + /* GPORT1 */ + "PLUG_DETECT_DIMM_C0D1", "PLUG_DETECT_DIMM_C0D2", + "PLUG_DETECT_DIMM_C0C1", "PLUG_DETECT_DIMM_C0C2", + "PLUG_DETECT_DIMM_C0B1", "PLUG_DETECT_DIMM_C0B2", + "PLUG_DETECT_DIMM_C0A1", "PLUG_DETECT_DIMM_C0A2", + /* GPORT2 */ + "PEX_CPU0_EVENT_RST", "SVC_PEX_RSSD01_16_RST", + "", "", + /* GPORT3 */ + "LED_ID_DIMM_C0E2", "LED_ID_DIMM_C0E1", + "LED_ID_DIMM_C0F2", "LED_ID_DIMM_C0F1", + "LED_ID_DIMM_C0G2", "LED_ID_DIMM_C0G1", + "LED_ID_DIMM_C0H2", "LED_ID_DIMM_C0H1", + /* GPORT4 */ + "LED_ID_DIMM_C0A2", "LED_ID_DIMM_C0A1", + "LED_ID_DIMM_C0B2", "LED_ID_DIMM_C0B1", + "LED_ID_DIMM_C0C2", "LED_ID_DIMM_C0C1", + "LED_ID_DIMM_C0D2", "LED_ID_DIMM_C0D1", + /* GPORT5 */ + "", "", + "FM_CPU0_SKTOCC_N", "LED_ID_CPU0"; + }; + }; +}; + +&i2c9 { + status = "okay"; + + p1v2_bmc_aux_mon: pmic@60 { + compatible = "maxim,max8952"; + reg = <0x60>; + max8952,default-mode = <3>; + max8952,dvs-mode-microvolt = <1100000>, <1100000>, + <1100000>, <1100000>; + max8952,sync-freq = <0>; + max8952,ramp-speed = <0>; + regulator-always-on; + regulator-boot-on; + }; +}; + +&i2cmux8 { + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + fan10_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan10_ssb: sw0 { + regulator-name = "fan10_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + fan12_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan12_ssb: sw0 { + regulator-name = "fan12_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + fan14_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <13 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan14_ssb: sw0 { + regulator-name = "fan14_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + fan16_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <15 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan16_ssb: sw0 { + regulator-name = "fan16_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + fan18_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <17 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan18_ssb: sw0 { + regulator-name = "fan18_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + fan20_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <19 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan20_ssb: sw0 { + regulator-name = "fan20_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + fan22_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <21 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan22_ssb: sw0 { + regulator-name = "fan22_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + fan24_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <23 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan24_ssb: sw0 { + regulator-name = "fan24_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; +}; + +&i2cmux7 { + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + fan17_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <16 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan17_ssb: sw0 { + regulator-name = "fan17_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + fan19_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <18 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan19_ssb: sw0 { + regulator-name = "fan19_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + fan21_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <20 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan21_ssb: sw0 { + regulator-name = "fan21_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + fan23_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <22 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan23_ssb: sw0 { + regulator-name = "fan23_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + fan02_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan02_ssb: sw0 { + regulator-name = "fan02_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + fan04_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan04_ssb: sw0 { + regulator-name = "fan04_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + fan06_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <5 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan06_ssb: sw0 { + regulator-name = "fan06_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + fan08_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan08_ssb: sw0 { + regulator-name = "fan08_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; +}; + +&i2cmux6 { + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + fan01_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan01_ssb: sw0 { + regulator-name = "fan01_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + fan03_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan03_ssb: sw0 { + regulator-name = "fan03_supply"; + + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + fan05_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <4 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan05_ssb: sw0 { + regulator-name = "fan05_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + fan07_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <6 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan07_ssb: sw0 { + regulator-name = "fan07_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + fan09_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan09_ssb: sw0 { + regulator-name = "fan09_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + fan11_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan11_ssb: sw0 { + regulator-name = "fan11_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + fan13_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan13_ssb: sw0 { + regulator-name = "fan13_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + fan15_ssb: regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p12v>; + interrupt-parent = <&smb_svc_pex_fan_alert>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; + + regulators { + sw0_fan15_ssb: sw0 { + regulator-name = "fan15_supply"; + shunt-resistor-micro-ohms = <10000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <3400000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + + }; +}; + +&i2cmux9 { + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd19: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <46 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd19:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd19: sw0 { + regulator-name = "rssd19_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd19: sw1 { + regulator-name = "rssd19_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd18: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <45 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd18:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd18: sw0 { + regulator-name = "rssd18_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd18: sw1 { + regulator-name = "rssd18_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd17: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <44 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd17:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd17: sw0 { + regulator-name = "rssd17_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd17: sw1 { + regulator-name = "rssd17_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd20: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <47 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd20:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd20: sw0 { + regulator-name = "rssd20_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd20: sw1 { + regulator-name = "rssd20_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd21: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <48 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd21:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd21: sw0 { + regulator-name = "rssd21_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd21: sw1 { + regulator-name = "rssd21_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd22: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <49 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd22:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd22: sw0 { + regulator-name = "rssd22_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd22: sw1 { + regulator-name = "rssd22_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd24: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <51 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd24:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd24: sw0 { + regulator-name = "rssd24_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd24: sw1 { + regulator-name = "rssd24_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd23: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <50 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd23:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd23: sw0 { + regulator-name = "rssd23_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd23: sw1 { + regulator-name = "rssd23_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; +}; + +&i2cmux10 { + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd25: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <52 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd25:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd25: sw0 { + regulator-name = "rssd25_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd25: sw1 { + regulator-name = "rssd25_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd26: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <53 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd26:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd26: sw0 { + regulator-name = "rssd26_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd26: sw1 { + regulator-name = "rssd26_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd27: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <54 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd27:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd27: sw0 { + regulator-name = "rssd27_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd27: sw1 { + regulator-name = "rssd27_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd32: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <59 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd32:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd32: sw0 { + regulator-name = "rssd32_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd32: sw1 { + regulator-name = "rssd32_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd31: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <58 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd31:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd31: sw0 { + regulator-name = "rssd31_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd31: sw1 { + regulator-name = "rssd31_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd30: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <57 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd30:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd30: sw0 { + regulator-name = "rssd30_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd30: sw1 { + regulator-name = "rssd30_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd29: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <56 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd29:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd29: sw0 { + regulator-name = "rssd29_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd29: sw1 { + regulator-name = "rssd29_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd28: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd17_32>; + interrupts = <55 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd28:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd28: sw0 { + regulator-name = "rssd28_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd28: sw1 { + regulator-name = "rssd28_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; +}; + +&i2cmux18 { + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd03: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <46 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd03:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd03: sw0 { + regulator-name = "rssd03_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd03: sw1 { + regulator-name = "rssd03_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd02: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <45 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd02:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd02: sw0 { + regulator-name = "rssd02_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd02: sw1 { + regulator-name = "rssd02_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd01: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <44 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd01:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd01: sw0 { + regulator-name = "rssd01_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd01: sw1 { + regulator-name = "rssd01_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd04: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <47 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd04:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd04: sw0 { + regulator-name = "rssd04_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd04: sw1 { + regulator-name = "rssd04_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd05: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <48 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd05:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd05: sw0 { + regulator-name = "rssd05_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd05: sw1 { + regulator-name = "rssd05_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd08: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <51 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd08:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd08: sw0 { + regulator-name = "rssd08_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd08: sw1 { + regulator-name = "rssd08_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd07: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <50 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd07:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd07: sw0 { + regulator-name = "rssd07_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd07: sw1 { + regulator-name = "rssd07_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd06: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <49 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd06:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd06: sw0 { + regulator-name = "rssd06_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd06: sw1 { + regulator-name = "rssd06_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; +}; + +&i2cmux19 { + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd14: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <57 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd14:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd14: sw0 { + regulator-name = "rssd14_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd14: sw1 { + regulator-name = "rssd14_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd13: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <56 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd13:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd13: sw0 { + regulator-name = "rssd13_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd13: sw1 { + regulator-name = "rssd13_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd12: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <55 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd12:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd12: sw0 { + regulator-name = "rssd12_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd12: sw1 { + regulator-name = "rssd12_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd11: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <54 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd11:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd11: sw0 { + regulator-name = "rssd11_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd11: sw1 { + regulator-name = "rssd11_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@4 { + reg = <4>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd10: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <53 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd10:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd10: sw0 { + regulator-name = "rssd10_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd10: sw1 { + regulator-name = "rssd10_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@5 { + reg = <5>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd09: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <52 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd09:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd09: sw0 { + regulator-name = "rssd09_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd09: sw1 { + regulator-name = "rssd09_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@6 { + reg = <6>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd15: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <58 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd15:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd15: sw0 { + regulator-name = "rssd15_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd15: sw1 { + regulator-name = "rssd15_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; + i2c@7 { + reg = <7>; + #address-cells = <1>; + #size-cells = <0>; + + ssb_rssd16: regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + interrupt-parent = <&smb_svc_pex_rssd01_16>; + interrupts = <59 IRQ_TYPE_LEVEL_LOW>; + + vss1-supply = <&p3v3_aux>; + vss2-supply = <&p12v>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "rssd16:green:power"; + default-state = "off"; + }; + }; + + regulators { + sw0_ssb_rssd16: sw0 { + regulator-name = "rssd16_12v"; + shunt-resistor-micro-ohms = <9000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <4500000>; + regulator-enable-ramp-delay = <1000>; + }; + sw1_ssb_rssd16: sw1 { + regulator-name = "rssd16_3v3"; + shunt-resistor-micro-ohms = <100000>; + regulator-over-current-protection; + regulator-oc-protection-microamp = <410000>; + regulator-enable-ramp-delay = <1000>; + }; + }; + }; + }; +}; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-system1.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-system1.dts index f3efecc7eb8d..360b9ce3c850 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-system1.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-ibm-system1.dts @@ -370,17 +370,17 @@ /*K0-K7*/ "","","","","","","","", /*L0-L7*/ "","","","","","","","bmc-ready", /*M0-M7*/ "","","","","","","","", - /*N0-N7*/ "","","","","","","","", + /*N0-N7*/ "fpga-debug-enable","","","","","","","", /*O0-O7*/ "","","","","","","","", /*P0-P7*/ "","","","","","","","bmc-hb", - /*Q0-Q7*/ "","","","","","","","", + /*Q0-Q7*/ "","","","","","","pch-ready","", /*R0-R7*/ "","","","","","","","", /*S0-S7*/ "","","","","","","rear-enc-fault0","rear-enc-id0", /*T0-T7*/ "","","","","","","","", /*U0-U7*/ "","","","","","","","", /*V0-V7*/ "","rtc-battery-voltage-read-enable","","power-chassis-control","","","","", /*W0-W7*/ "","","","","","","","", - /*X0-X7*/ "","power-chassis-good","","","","","","", + /*X0-X7*/ "fpga-pgood","power-chassis-good","pch-pgood","","","","","", /*Y0-Y7*/ "","","","","","","","", /*Z0-Z7*/ "","","","","","","",""; }; @@ -398,6 +398,12 @@ clk-phase-mmc-hs200 = <180>, <180>; }; +&sgpiom0 { + status = "okay"; + ngpios = <128>; + bus-frequency = <1000000>; +}; + &ibt { status = "okay"; }; @@ -464,6 +470,15 @@ aspeed,lpc-interrupts = <11 IRQ_TYPE_LEVEL_LOW>; }; +&peci0 { + status = "okay"; +}; + +&lpc_snoop { + status = "okay"; + snoop-ports = <0x80>, <0x81>; +}; + &i2c0 { status = "okay"; @@ -666,22 +681,22 @@ status = "okay"; power-supply@58 { - compatible = "ibm,cffps"; + compatible = "intel,crps185"; reg = <0x58>; }; power-supply@59 { - compatible = "ibm,cffps"; + compatible = "intel,crps185"; reg = <0x59>; }; power-supply@5a { - compatible = "ibm,cffps"; + compatible = "intel,crps185"; reg = <0x5a>; }; power-supply@5b { - compatible = "ibm,cffps"; + compatible = "intel,crps185"; reg = <0x5b>; }; }; @@ -1007,6 +1022,7 @@ &i2c8 { status = "okay"; + bus-frequency = <400000>; i2c-mux@71 { compatible = "nxp,pca9548"; @@ -1468,6 +1484,7 @@ &i2c15 { status = "okay"; + bus-frequency = <400000>; i2c-mux@71 { compatible = "nxp,pca9548"; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-quanta-s6q.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-quanta-s6q.dts index 983853eedaef..fd361cf073c2 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-quanta-s6q.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-quanta-s6q.dts @@ -381,7 +381,7 @@ #size-cells = <0>; reg = <5>; - U190_fru@51 { + eeprom@51 { compatible = "atmel,24c128"; reg = <0x51>; pagesize = <32>; @@ -460,7 +460,7 @@ status = "okay"; /* MB FRU (U173) @ 0xA2 */ - mb_fru: mb_fru@51 { + mb_fru: eeprom@51 { compatible = "atmel,24c128"; reg = <0x51>; pagesize = <32>; @@ -472,7 +472,7 @@ reg = <0x4a>; }; - FP_U4_fru@52 { + eeprom@52 { compatible = "atmel,24c02"; reg = <0x52>; pagesize = <16>; @@ -593,7 +593,7 @@ status = "okay"; /* SCM FRU (U19) @ 0xA2 */ - scm_fru: scm_fru@51 { + scm_fru: eeprom@51 { compatible = "atmel,24c128"; reg = <0x51>; pagesize = <32>; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-vegman-rx20.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-vegman-rx20.dts index b8f0b08018a3..98f3e0437704 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-vegman-rx20.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-vegman-rx20.dts @@ -154,7 +154,7 @@ #address-cells = <1>; #size-cells = <0>; reg = <7>; - at24@50 { + eeprom@50 { compatible = "atmel,24c64"; reg = <0x50>; pagesize = <32>; @@ -196,7 +196,7 @@ #address-cells = <1>; #size-cells = <0>; reg = <7>; - at24@50 { + eeprom@50 { compatible = "atmel,24c64"; reg = <0x50>; pagesize = <32>; @@ -205,7 +205,7 @@ }; }; }; - at24@50 { + eeprom@50 { compatible = "atmel,24c64"; reg = <0x50>; pagesize = <32>; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-vegman.dtsi b/arch/arm/boot/dts/aspeed/aspeed-bmc-vegman.dtsi index 1a5b25b2ea29..16815eede710 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-vegman.dtsi +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-vegman.dtsi @@ -291,7 +291,7 @@ /* SMB_BMC_MGMT_LVC3 */ status = "okay"; - at24@50 { + eeprom@50 { compatible = "atmel,24c64"; reg = <0x50>; pagesize = <32>; diff --git a/arch/arm/boot/dts/broadcom/Makefile b/arch/arm/boot/dts/broadcom/Makefile index 5881bcc95eba..d23cf466127b 100644 --- a/arch/arm/boot/dts/broadcom/Makefile +++ b/arch/arm/boot/dts/broadcom/Makefile @@ -36,6 +36,7 @@ dtb-$(CONFIG_ARCH_BCM2835) += \ bcm2835-rpi-zero.dtb \ bcm2835-rpi-zero-w.dtb dtb-$(CONFIG_ARCH_BCMBCA) += \ + bcm6846-genexis-xg6846b.dtb \ bcm947622.dtb \ bcm963138.dtb \ bcm963138dvt.dtb \ diff --git a/arch/arm/boot/dts/broadcom/bcm53015-meraki-mr26.dts b/arch/arm/boot/dts/broadcom/bcm53015-meraki-mr26.dts index 0bf5106f7012..08abfdc63d18 100644 --- a/arch/arm/boot/dts/broadcom/bcm53015-meraki-mr26.dts +++ b/arch/arm/boot/dts/broadcom/bcm53015-meraki-mr26.dts @@ -59,6 +59,9 @@ &gmac0 { status = "okay"; + + nvmem-cells = <&macaddr_board_config_66>; + nvmem-cell-names = "mac-address"; }; &gmac1 { @@ -102,8 +105,25 @@ }; partition@800000 { + compatible = "linux,ubi"; label = "ubi"; reg = <0x800000 0x7780000>; + + volumes { + ubi-volume-board-config { + volname = "board-config"; + + nvmem-layout { + compatible = "fixed-layout"; + #address-cells = <1>; + #size-cells = <1>; + + macaddr_board_config_66: macaddr@66 { + reg = <0x66 0x6>; + }; + }; + }; + }; }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm53340-ubnt-unifi-switch8.dts b/arch/arm/boot/dts/broadcom/bcm53340-ubnt-unifi-switch8.dts index 975f854f652f..08cf1220b655 100644 --- a/arch/arm/boot/dts/broadcom/bcm53340-ubnt-unifi-switch8.dts +++ b/arch/arm/boot/dts/broadcom/bcm53340-ubnt-unifi-switch8.dts @@ -32,7 +32,6 @@ &qspi { status = "okay"; - bspi-sel = <0>; flash: flash@0 { compatible = "m25p80"; diff --git a/arch/arm/boot/dts/broadcom/bcm6846-genexis-xg6846b.dts b/arch/arm/boot/dts/broadcom/bcm6846-genexis-xg6846b.dts new file mode 100644 index 000000000000..a3616fb7b3a8 --- /dev/null +++ b/arch/arm/boot/dts/broadcom/bcm6846-genexis-xg6846b.dts @@ -0,0 +1,244 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright 2024 Linus Walleij + */ + +/dts-v1/; + +#include "bcm6846.dtsi" +#include +#include +#include + +/ { + model = "Genexis XG6846B Ethernet layer 2/3 router"; + compatible = "genexis,xg6846b", "brcm,bcm6846", "brcm,bcmbca"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + /* Micron D9PTK 256 MB RAM */ + memory@0 { + device_type = "memory"; + reg = <0x0 0x10000000>; + }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + secondary-boot@0 { + no-map; + reg = <0x00000000 0x00008000>; + }; + pmc3-firmware@8000 { + no-map; + reg = <0x00008000 0x00100000>; + }; + }; + + gpio-keys { + compatible = "gpio-keys-polled"; + poll-interval = <20000>; + + /* Called "canyon rescue button" in the vendor DTB */ + button-restart { + label = "Reset"; + linux,code = ; + gpios = <&gpio0 41 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&gpio0 { + status = "okay"; +}; + +&gpio1 { + status = "okay"; +}; + +&gpio2 { + status = "okay"; + /* Totally 79 GPIOs are available */ + ngpios = <15>; +}; + +&uart0 { + status = "okay"; +}; + +&leds { + status = "okay"; + brcm,serial-shift-bits = <16>; + + led@0 { + reg = <0>; + active-low; + function = "ext"; + color = ; + }; + + led@1 { + reg = <1>; + active-low; + function = "ext"; + color = ; + }; + + led@3 { + reg = <3>; + active-low; + function = LED_FUNCTION_WAN; + color = ; + }; + + led@4 { + reg = <4>; + active-low; + function = LED_FUNCTION_WAN; + color = ; + }; + + led@5 { + reg = <5>; + active-low; + function = LED_FUNCTION_POWER; + color = ; + }; + + led@6 { + reg = <6>; + active-low; + function = LED_FUNCTION_POWER; + color = ; + }; + + led@15 { + reg = <15>; + active-low; + function = LED_FUNCTION_USB; + color = ; + }; + + led@7 { + /* Activity 03 */ + reg = <7>; + active-low; + function = "lan1"; + color = ; + }; + + led@8 { + /* Activity 04 */ + reg = <8>; + active-low; + function = "lan1"; + color = ; + }; + + led@9 { + /* Activity 03 */ + reg = <9>; + active-low; + function = "lan2"; + color = ; + }; + + led@10 { + /* Activity 04 */ + reg = <10>; + active-low; + function = "lan2"; + color = ; + }; + + led@11 { + /* Activity 03 */ + reg = <11>; + active-low; + function = "lan3"; + color = ; + }; + + led@12 { + /* Activity 04 */ + reg = <12>; + active-low; + function = "lan3"; + color = ; + }; + + led@13 { + /* Activity 03 */ + reg = <13>; + active-low; + function = "lan4"; + color = ; + }; + + led@14 { + /* Activity 04 */ + reg = <14>; + active-low; + function = "lan4"; + color = ; + }; +}; + +&hsspi { + status = "okay"; +}; + +&nand_controller { + brcm,wp-not-connected; + status = "okay"; +}; + +&nandcs { + nand-on-flash-bbt; + brcm,nand-ecc-use-strap; + + /* Winbond W29N02GV, 256MB with 128KB erase blocks */ + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + loader@0 { + label = "loader"; + reg = <0x00000000 0x00400000>; + }; + image@400000 { + label = "image"; + reg = <0x00400000 0x0fb00000>; + }; + /* 0x00ff0000-0x00ffffff: bad block list */ + }; +}; + +&mdio { + status = "okay"; + + phy1: ethernet-phy@1 { + reg = <1>; + }; + phy2: ethernet-phy@2 { + reg = <2>; + }; + phy3: ethernet-phy@3 { + reg = <3>; + }; + phy4: ethernet-phy@4 { + reg = <4>; + }; + phy21: ethernet-phy@21 { + reg = <21>; + }; +}; diff --git a/arch/arm/boot/dts/broadcom/bcm6846.dtsi b/arch/arm/boot/dts/broadcom/bcm6846.dtsi index ee361cb00b7c..e0e06af3fe89 100644 --- a/arch/arm/boot/dts/broadcom/bcm6846.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm6846.dtsi @@ -99,6 +99,91 @@ #size-cells = <1>; ranges = <0 0xff800000 0x800000>; + watchdog@480 { + compatible = "brcm,bcm6345-wdt"; + reg = <0x480 0x10>; + }; + + /* GPIOs 0 .. 31 */ + gpio0: gpio@500 { + compatible = "brcm,bcm6345-gpio"; + reg = <0x500 0x04>, <0x520 0x04>; + reg-names = "dirout", "dat"; + gpio-controller; + #gpio-cells = <2>; + status = "disabled"; + }; + + /* GPIOs 32 .. 63 */ + gpio1: gpio@504 { + compatible = "brcm,bcm6345-gpio"; + reg = <0x504 0x04>, <0x524 0x04>; + reg-names = "dirout", "dat"; + gpio-controller; + #gpio-cells = <2>; + status = "disabled"; + }; + + /* GPIOs 64 .. 95 */ + gpio2: gpio@508 { + compatible = "brcm,bcm6345-gpio"; + reg = <0x508 0x04>, <0x528 0x04>; + reg-names = "dirout", "dat"; + gpio-controller; + #gpio-cells = <2>; + status = "disabled"; + }; + + /* GPIOs 96 .. 127 */ + gpio3: gpio@50c { + compatible = "brcm,bcm6345-gpio"; + reg = <0x50c 0x04>, <0x52c 0x04>; + reg-names = "dirout", "dat"; + gpio-controller; + #gpio-cells = <2>; + status = "disabled"; + }; + + /* GPIOs 128 .. 159 */ + gpio4: gpio@510 { + compatible = "brcm,bcm6345-gpio"; + reg = <0x510 0x04>, <0x530 0x04>; + reg-names = "dirout", "dat"; + gpio-controller; + #gpio-cells = <2>; + status = "disabled"; + }; + + /* GPIOs 160 .. 191 */ + gpio5: gpio@514 { + compatible = "brcm,bcm6345-gpio"; + reg = <0x514 0x04>, <0x534 0x04>; + reg-names = "dirout", "dat"; + gpio-controller; + #gpio-cells = <2>; + status = "disabled"; + }; + + /* GPIOs 192 .. 223 */ + gpio6: gpio@518 { + compatible = "brcm,bcm6345-gpio"; + reg = <0x518 0x04>, <0x538 0x04>; + reg-names = "dirout", "dat"; + gpio-controller; + #gpio-cells = <2>; + status = "disabled"; + }; + + /* GPIOs 224 .. 255 */ + gpio7: gpio@51c { + compatible = "brcm,bcm6345-gpio"; + reg = <0x51c 0x04>, <0x53c 0x04>; + reg-names = "dirout", "dat"; + gpio-controller; + #gpio-cells = <2>; + status = "disabled"; + }; + uart0: serial@640 { compatible = "brcm,bcm6345-uart"; reg = <0x640 0x1b>; @@ -108,6 +193,19 @@ status = "disabled"; }; + rng@b80 { + compatible = "brcm,iproc-rng200"; + reg = <0xb80 0x28>; + }; + + leds: led-controller@800 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "brcm,bcm63138-leds"; + reg = <0x800 0xdc>; + status = "disabled"; + }; + hsspi: spi@1000 { #address-cells = <1>; #size-cells = <0>; @@ -133,5 +231,27 @@ reg = <0>; }; }; + + mdio: mdio@2060 { + compatible = "brcm,bcm6846-mdio"; + reg = <0x02060 0x10>, <0x5a068 0x4>; + reg-names = "mdio", "mdio_indir_rw"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + pl081_dma: dma-controller@59000 { + compatible = "arm,pl081", "arm,primecell"; + // The magic B105F00D info is missing + arm,primecell-periphid = <0x00041081>; + reg = <0x59000 0x1000>; + interrupts = ; + memcpy-burst-size = <256>; + memcpy-bus-width = <32>; + clocks = <&periph_clk>; + clock-names = "apb_pclk"; + #dma-cells = <2>; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm953012hr.dts b/arch/arm/boot/dts/broadcom/bcm953012hr.dts index b070b69466bd..b728cd54715e 100644 --- a/arch/arm/boot/dts/broadcom/bcm953012hr.dts +++ b/arch/arm/boot/dts/broadcom/bcm953012hr.dts @@ -74,7 +74,6 @@ &spi_nor { status = "okay"; spi-max-frequency = <62500000>; - m25p,default-addr-width = <3>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/broadcom/bcm953012k.dts b/arch/arm/boot/dts/broadcom/bcm953012k.dts index f1e6bcaa1edd..27c0992f1855 100644 --- a/arch/arm/boot/dts/broadcom/bcm953012k.dts +++ b/arch/arm/boot/dts/broadcom/bcm953012k.dts @@ -84,7 +84,6 @@ &spi_nor { status = "okay"; spi-max-frequency = <62500000>; - m25p,default-addr-width = <3>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/broadcom/bcm958522er.dts b/arch/arm/boot/dts/broadcom/bcm958522er.dts index 15f023656df0..2f20f86bd31c 100644 --- a/arch/arm/boot/dts/broadcom/bcm958522er.dts +++ b/arch/arm/boot/dts/broadcom/bcm958522er.dts @@ -135,7 +135,6 @@ &qspi { status = "okay"; - bspi-sel = <0>; flash: flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/broadcom/bcm958525er.dts b/arch/arm/boot/dts/broadcom/bcm958525er.dts index 9b9c225a1fb3..980c03f74a19 100644 --- a/arch/arm/boot/dts/broadcom/bcm958525er.dts +++ b/arch/arm/boot/dts/broadcom/bcm958525er.dts @@ -135,7 +135,6 @@ &qspi { status = "okay"; - bspi-sel = <0>; flash: flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/broadcom/bcm958525xmc.dts b/arch/arm/boot/dts/broadcom/bcm958525xmc.dts index ca9311452739..440bb2d617f2 100644 --- a/arch/arm/boot/dts/broadcom/bcm958525xmc.dts +++ b/arch/arm/boot/dts/broadcom/bcm958525xmc.dts @@ -151,7 +151,6 @@ &qspi { status = "okay"; - bspi-sel = <0>; flash: flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/broadcom/bcm958622hr.dts b/arch/arm/boot/dts/broadcom/bcm958622hr.dts index 9db3c851451a..116f3a7c3bc6 100644 --- a/arch/arm/boot/dts/broadcom/bcm958622hr.dts +++ b/arch/arm/boot/dts/broadcom/bcm958622hr.dts @@ -139,7 +139,6 @@ &qspi { status = "okay"; - bspi-sel = <0>; flash: flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/broadcom/bcm958623hr.dts b/arch/arm/boot/dts/broadcom/bcm958623hr.dts index 32786e7c4e12..fc6ab73ecf56 100644 --- a/arch/arm/boot/dts/broadcom/bcm958623hr.dts +++ b/arch/arm/boot/dts/broadcom/bcm958623hr.dts @@ -143,7 +143,6 @@ &qspi { status = "okay"; - bspi-sel = <0>; flash: flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/broadcom/bcm958625hr.dts b/arch/arm/boot/dts/broadcom/bcm958625hr.dts index 74263d98de73..a9b6aa04d573 100644 --- a/arch/arm/boot/dts/broadcom/bcm958625hr.dts +++ b/arch/arm/boot/dts/broadcom/bcm958625hr.dts @@ -150,7 +150,6 @@ &qspi { status = "okay"; - bspi-sel = <0>; flash: flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/broadcom/bcm958625k.dts b/arch/arm/boot/dts/broadcom/bcm958625k.dts index 69ebc7a913a7..7996116fc923 100644 --- a/arch/arm/boot/dts/broadcom/bcm958625k.dts +++ b/arch/arm/boot/dts/broadcom/bcm958625k.dts @@ -154,7 +154,6 @@ &qspi { status = "okay"; - bspi-sel = <0>; flash: flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/broadcom/bcm988312hr.dts b/arch/arm/boot/dts/broadcom/bcm988312hr.dts index e96bc3f2d5cf..663a3f27b6e4 100644 --- a/arch/arm/boot/dts/broadcom/bcm988312hr.dts +++ b/arch/arm/boot/dts/broadcom/bcm988312hr.dts @@ -139,7 +139,6 @@ &qspi { status = "okay"; - bspi-sel = <0>; flash: flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_arria10.dtsi b/arch/arm/boot/dts/intel/socfpga/socfpga_arria10.dtsi index 6b6e77596ffa..b108265e9bde 100644 --- a/arch/arm/boot/dts/intel/socfpga/socfpga_arria10.dtsi +++ b/arch/arm/boot/dts/intel/socfpga/socfpga_arria10.dtsi @@ -440,7 +440,7 @@ clocks = <&l4_mp_clk>, <&peri_emac_ptp_clk>; clock-names = "stmmaceth", "ptp_ref"; resets = <&rst EMAC0_RESET>, <&rst EMAC0_OCP_RESET>; - reset-names = "stmmaceth", "ahb"; + reset-names = "stmmaceth", "stmmaceth-ocp"; snps,axi-config = <&socfpga_axi_setup>; status = "disabled"; }; @@ -460,7 +460,7 @@ clocks = <&l4_mp_clk>, <&peri_emac_ptp_clk>; clock-names = "stmmaceth", "ptp_ref"; resets = <&rst EMAC1_RESET>, <&rst EMAC1_OCP_RESET>; - reset-names = "stmmaceth", "ahb"; + reset-names = "stmmaceth", "stmmaceth-ocp"; snps,axi-config = <&socfpga_axi_setup>; status = "disabled"; }; @@ -480,7 +480,7 @@ clocks = <&l4_mp_clk>, <&peri_emac_ptp_clk>; clock-names = "stmmaceth", "ptp_ref"; resets = <&rst EMAC2_RESET>, <&rst EMAC2_OCP_RESET>; - reset-names = "stmmaceth", "ahb"; + reset-names = "stmmaceth", "stmmaceth-ocp"; snps,axi-config = <&socfpga_axi_setup>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_mcvevk.dts b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_mcvevk.dts index ceaec29770c6..c1e1264bcb09 100644 --- a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_mcvevk.dts +++ b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_mcvevk.dts @@ -50,8 +50,6 @@ stmpe1: stmpe811@41 { compatible = "st,stmpe811"; - #address-cells = <1>; - #size-cells = <0>; reg = <0x41>; id = <0>; blocks = <0x5>; diff --git a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_socdk.dts b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_socdk.dts index d37a982e8571..97622febc44e 100644 --- a/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_socdk.dts +++ b/arch/arm/boot/dts/intel/socfpga/socfpga_cyclone5_socdk.dts @@ -151,12 +151,6 @@ &spi0 { status = "okay"; - - spidev@0 { - compatible = "rohm,dh2228fv"; - reg = <0>; - spi-max-frequency = <1000000>; - }; }; &usb1 { diff --git a/arch/arm/boot/dts/marvell/mmp2-olpc-xo-1-75.dts b/arch/arm/boot/dts/marvell/mmp2-olpc-xo-1-75.dts index 55ea87870af3..86c425b72fa7 100644 --- a/arch/arm/boot/dts/marvell/mmp2-olpc-xo-1-75.dts +++ b/arch/arm/boot/dts/marvell/mmp2-olpc-xo-1-75.dts @@ -113,8 +113,8 @@ "Headphones", "HPOR", "MIC2", "Mic Jack"; widgets = "Headphone", "Headphones", "Microphone", "Mic Jack"; - hp-det-gpio = <&gpio 97 GPIO_ACTIVE_HIGH>; - mic-det-gpio = <&gpio 96 GPIO_ACTIVE_HIGH>; + hp-det-gpios = <&gpio 97 GPIO_ACTIVE_HIGH>; + mic-det-gpios = <&gpio 96 GPIO_ACTIVE_HIGH>; }; soc { diff --git a/arch/arm/boot/dts/mediatek/mt7623.dtsi b/arch/arm/boot/dts/mediatek/mt7623.dtsi index 814586abc297..fd7a89cc337d 100644 --- a/arch/arm/boot/dts/mediatek/mt7623.dtsi +++ b/arch/arm/boot/dts/mediatek/mt7623.dtsi @@ -308,7 +308,7 @@ clock-names = "spi", "wrap"; }; - cir: cir@10013000 { + cir: ir-receiver@10013000 { compatible = "mediatek,mt7623-cir"; reg = <0 0x10013000 0 0x1000>; interrupts = ; diff --git a/arch/arm/boot/dts/microchip/Makefile b/arch/arm/boot/dts/microchip/Makefile index 470fe46433a9..79cd38fdc7da 100644 --- a/arch/arm/boot/dts/microchip/Makefile +++ b/arch/arm/boot/dts/microchip/Makefile @@ -12,6 +12,7 @@ DTC_FLAGS_at91-sama5d2_xplained := -@ DTC_FLAGS_at91-sama5d3_eds := -@ DTC_FLAGS_at91-sama5d3_xplained := -@ DTC_FLAGS_at91-sama5d4_xplained := -@ +DTC_FLAGS_at91-sama7d65_curiosity := -@ DTC_FLAGS_at91-sama7g54_curiosity := -@ DTC_FLAGS_at91-sama7g5ek := -@ dtb-$(CONFIG_SOC_AT91RM9200) += \ @@ -90,6 +91,8 @@ dtb-$(CONFIG_SOC_SAM_V7) += \ at91-sama5d4_xplained.dtb \ at91-sama5d4ek.dtb \ at91-vinco.dtb +dtb-$(CONFIG_SOC_SAMA7D65) += \ + at91-sama7d65_curiosity.dtb dtb-$(CONFIG_SOC_SAMA7G5) += \ at91-sama7g54_curiosity.dtb \ at91-sama7g5ek.dtb diff --git a/arch/arm/boot/dts/microchip/at91-sam9x75_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sam9x75_curiosity.dts index 87b6ea97590b..1a6a909a5043 100644 --- a/arch/arm/boot/dts/microchip/at91-sam9x75_curiosity.dts +++ b/arch/arm/boot/dts/microchip/at91-sam9x75_curiosity.dts @@ -88,8 +88,6 @@ }; &i2c6 { - #address-cells = <1>; - #size-cells = <0>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_flx6_default>; i2c-analog-filter; @@ -200,6 +198,52 @@ }; }; +&flx7 { + atmel,flexcom-mode = ; + status = "okay"; +}; + +&i2c7 { + dmas = <0>, <0>; + i2c-analog-filter; + i2c-digital-filter; + i2c-digital-filter-width-ns = <35>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_flx7_default>; + status = "okay"; + + power-monitor@10 { + compatible = "microchip,pac1934"; + reg = <0x10>; + #address-cells = <1>; + #size-cells = <0>; + + channel@1 { + reg = <0x1>; + shunt-resistor-micro-ohms = <10000>; + label = "VDD3V3"; + }; + + channel@2 { + reg = <0x2>; + shunt-resistor-micro-ohms = <10000>; + label = "DCDC4"; + }; + + channel@3 { + reg = <0x3>; + shunt-resistor-micro-ohms = <10000>; + label = "VDDCORE"; + }; + + channel@4 { + reg = <0x4>; + shunt-resistor-micro-ohms = <10000>; + label = "VDDIODDR"; + }; + }; +}; + &i2s { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2s_default>; @@ -233,6 +277,12 @@ , ; }; + + pinctrl_flx7_default: flx7-default { + atmel,pins = + , + ; + }; }; gpio-keys { diff --git a/arch/arm/boot/dts/microchip/at91-sama5d27_wlsom1_ek.dts b/arch/arm/boot/dts/microchip/at91-sama5d27_wlsom1_ek.dts index 15239834d886..35a933eec573 100644 --- a/arch/arm/boot/dts/microchip/at91-sama5d27_wlsom1_ek.dts +++ b/arch/arm/boot/dts/microchip/at91-sama5d27_wlsom1_ek.dts @@ -197,6 +197,7 @@ &sdmmc0 { bus-width = <4>; + no-1-8-v; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_sdmmc0_default>; status = "okay"; diff --git a/arch/arm/boot/dts/microchip/at91-sama5d29_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sama5d29_curiosity.dts index b6684bf67d3e..7be215781549 100644 --- a/arch/arm/boot/dts/microchip/at91-sama5d29_curiosity.dts +++ b/arch/arm/boot/dts/microchip/at91-sama5d29_curiosity.dts @@ -514,6 +514,7 @@ &sdmmc0 { bus-width = <4>; + no-1-8-v; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_sdmmc0_default>; disable-wp; diff --git a/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts new file mode 100644 index 000000000000..0f86360fb733 --- /dev/null +++ b/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * at91-sama7d65_curiosity.dts - Device Tree file for SAMA7D65 Curiosity board + * + * Copyright (c) 2024 Microchip Technology Inc. and its subsidiaries + * + * Author: Romain Sioen + * + */ +/dts-v1/; +#include "sama7d65-pinfunc.h" +#include "sama7d65.dtsi" +#include +#include + +/ { + model = "Microchip SAMA7D65 Curiosity"; + compatible = "microchip,sama7d65-curiosity", "microchip,sama7d65", + "microchip,sama7d6", "microchip,sama7"; + + aliases { + serial0 = &uart6; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@60000000 { + device_type = "memory"; + reg = <0x60000000 0x40000000>; + }; +}; + +&flx6 { + atmel,flexcom-mode = ; + status = "okay"; +}; + +&uart6 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_uart6_default>; + status = "okay"; +}; + +&main_xtal { + clock-frequency = <24000000>; +}; + +&pioa { + pinctrl_sdmmc1_default: sdmmc1-default { + cmd-data { + pinmux = , + , + , + , + ; + slew-rate = <0>; + bias-disable; + }; + + ck-cd-rstn-vddsel { + pinmux = , + , + , + , + ; + slew-rate = <0>; + bias-disable; + }; + }; + + pinctrl_uart6_default: uart6-default { + pinmux = , + ; + bias-disable; + }; +}; + +&sdmmc1 { + bus-width = <4>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_sdmmc1_default>; + status = "okay"; +}; + +&slow_xtal { + clock-frequency = <32768>; +}; diff --git a/arch/arm/boot/dts/microchip/sam9x60.dtsi b/arch/arm/boot/dts/microchip/sam9x60.dtsi index 36944e18a329..b8b2c1ddf3f1 100644 --- a/arch/arm/boot/dts/microchip/sam9x60.dtsi +++ b/arch/arm/boot/dts/microchip/sam9x60.dtsi @@ -197,6 +197,8 @@ compatible = "microchip,sam9x60-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <13 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 13>; clock-names = "spi_clk"; dmas = <&dma0 @@ -268,6 +270,8 @@ compatible = "microchip,sam9x60-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <14 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 14>; clock-names = "spi_clk"; dmas = <&dma0 @@ -768,6 +772,8 @@ compatible = "microchip,sam9x60-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <5 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 5>; clock-names = "spi_clk"; dmas = <&dma0 @@ -839,6 +845,8 @@ compatible = "microchip,sam9x60-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <6 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 6>; clock-names = "spi_clk"; dmas = <&dma0 @@ -910,6 +918,8 @@ compatible = "microchip,sam9x60-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <7 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 7>; clock-names = "spi_clk"; dmas = <&dma0 @@ -981,6 +991,8 @@ compatible = "microchip,sam9x60-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <8 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 8>; clock-names = "spi_clk"; dmas = <&dma0 diff --git a/arch/arm/boot/dts/microchip/sam9x7.dtsi b/arch/arm/boot/dts/microchip/sam9x7.dtsi index beb1f34b38d3..b217a908f525 100644 --- a/arch/arm/boot/dts/microchip/sam9x7.dtsi +++ b/arch/arm/boot/dts/microchip/sam9x7.dtsi @@ -132,6 +132,8 @@ compatible = "microchip,sam9x7-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <13 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 13>; clock-names = "spi_clk"; dmas = <&dma0 @@ -151,6 +153,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <13 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 13>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -201,6 +205,8 @@ compatible = "microchip,sam9x7-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <14 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 14>; clock-names = "spi_clk"; dmas = <&dma0 @@ -220,6 +226,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <14 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 14>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -312,6 +320,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <32 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 32>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -362,6 +372,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <33 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 33>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -533,6 +545,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <9 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 9>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -583,6 +597,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <10 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 10>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -633,6 +649,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <11 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 11>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -683,6 +701,8 @@ compatible = "microchip,sam9x7-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <5 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 5>; clock-names = "spi_clk"; dmas = <&dma0 @@ -702,6 +722,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <5 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 5>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -752,6 +774,8 @@ compatible = "microchip,sam9x7-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <6 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 6>; clock-names = "spi_clk"; dmas = <&dma0 @@ -771,6 +795,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <6 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 6>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -821,6 +847,8 @@ compatible = "microchip,sam9x7-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <7 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 7>; clock-names = "spi_clk"; dmas = <&dma0 @@ -840,6 +868,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <7 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 7>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -890,6 +920,8 @@ compatible = "microchip,sam9x7-spi", "atmel,at91rm9200-spi"; reg = <0x400 0x200>; interrupts = <8 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 8>; clock-names = "spi_clk"; dmas = <&dma0 @@ -909,6 +941,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <8 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 8>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -984,6 +1018,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <15 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 15>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | @@ -1034,6 +1070,8 @@ compatible = "microchip,sam9x7-i2c", "microchip,sam9x60-i2c"; reg = <0x600 0x200>; interrupts = <16 IRQ_TYPE_LEVEL_HIGH 7>; + #address-cells = <1>; + #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 16>; dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | diff --git a/arch/arm/boot/dts/microchip/sama7d65-pinfunc.h b/arch/arm/boot/dts/microchip/sama7d65-pinfunc.h new file mode 100644 index 000000000000..c591f333cacb --- /dev/null +++ b/arch/arm/boot/dts/microchip/sama7d65-pinfunc.h @@ -0,0 +1,947 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */ +#define PINMUX_PIN(no, func, ioset) \ +(((no) & 0xffff) | (((func) & 0xf) << 16) | (((ioset) & 0xff) << 20)) + +#define PIN_PA0 0 +#define PIN_PA0__GPIO PINMUX_PIN(PIN_PA0, 0, 0) +#define PIN_PA0__SDMMC0_CK PINMUX_PIN(PIN_PA0, 1, 1) +#define PIN_PA0__FLEXCOM3_IO0 PINMUX_PIN(PIN_PA0, 2, 1) +#define PIN_PA0__NWER0 PINMUX_PIN(PIN_PA0, 3, 1) + +#define PIN_PA1 1 +#define PIN_PA1__GPIO PINMUX_PIN(PIN_PA1, 0, 0) +#define PIN_PA1__SDMMC0_CMD PINMUX_PIN(PIN_PA1, 1, 1) +#define PIN_PA1__FLEXCOM3_IO1 PINMUX_PIN(PIN_PA1, 2, 1) +#define PIN_PA1__A21 PINMUX_PIN(PIN_PA1, 3, 1) + +#define PIN_PA2 2 +#define PIN_PA2__GPIO PINMUX_PIN(PIN_PA2, 0, 0) +#define PIN_PA2__SDMMC0_RSTN PINMUX_PIN(PIN_PA2, 1, 1) +#define PIN_PA2__FLEXCOM3_IO2 PINMUX_PIN(PIN_PA2, 2, 1) +#define PIN_PA2__A22 PINMUX_PIN(PIN_PA2, 3, 1) + +#define PIN_PA3 3 +#define PIN_PA3__GPIO PINMUX_PIN(PIN_PA3, 0, 0) +#define PIN_PA3__SDMMC0_DAT0 PINMUX_PIN(PIN_PA3, 1, 1) +#define PIN_PA3__FLEXCOM3_IO3 PINMUX_PIN(PIN_PA3, 2, 1) +#define PIN_PA3__D0 PINMUX_PIN(PIN_PA3, 3, 1) + +#define PIN_PA4 4 +#define PIN_PA4__GPIO PINMUX_PIN(PIN_PA4, 0, 0) +#define PIN_PA4__SDMMC0_DAT1 PINMUX_PIN(PIN_PA4, 1, 1) +#define PIN_PA4__FLEXCOM3_IO4 PINMUX_PIN(PIN_PA4, 2, 1) +#define PIN_PA4__D1 PINMUX_PIN(PIN_PA4, 3, 1) + +#define PIN_PA5 5 +#define PIN_PA5__GPIO PINMUX_PIN(PIN_PA5, 0, 0) +#define PIN_PA5__SDMMC0_DAT4 PINMUX_PIN(PIN_PA5, 1, 1) +#define PIN_PA5__FLEXCOM2_IO0 PINMUX_PIN(PIN_PA5, 2, 3) +#define PIN_PA5__D4 PINMUX_PIN(PIN_PA5, 3, 1) +#define PIN_PA5__TCLK4 PINMUX_PIN(PIN_PA5, 6, 3) + +#define PIN_PA6 6 +#define PIN_PA6__GPIO PINMUX_PIN(PIN_PA6, 0, 0) +#define PIN_PA6__SDMMC0_DAT5 PINMUX_PIN(PIN_PA6, 1, 1) +#define PIN_PA6__FLEXCOM2_IO1 PINMUX_PIN(PIN_PA6, 2, 3) +#define PIN_PA6__D5 PINMUX_PIN(PIN_PA6, 3, 1) +#define PIN_PA6__TIOB4 PINMUX_PIN(PIN_PA6, 6, 3) + +#define PIN_PA7 7 +#define PIN_PA7__GPIO PINMUX_PIN(PIN_PA7, 0, 0) +#define PIN_PA7__SDMMC0_DAT6 PINMUX_PIN(PIN_PA7, 1, 1) +#define PIN_PA7__FLEXCOM2_IO2 PINMUX_PIN(PIN_PA7, 2, 3) +#define PIN_PA7__D6 PINMUX_PIN(PIN_PA7, 3, 1) +#define PIN_PA7__TIOA4 PINMUX_PIN(PIN_PA7, 6, 3) + +#define PIN_PA8 8 +#define PIN_PA8__GPIO PINMUX_PIN(PIN_PA8, 0, 0) +#define PIN_PA8__SDMMC0_DAT7 PINMUX_PIN(PIN_PA8, 1, 1) +#define PIN_PA8__FLEXCOM2_IO3 PINMUX_PIN(PIN_PA8, 2, 3) +#define PIN_PA8__D7 PINMUX_PIN(PIN_PA8, 3, 1) +#define PIN_PA8__TIOA5 PINMUX_PIN(PIN_PA8, 6, 3) + +#define PIN_PA9 9 +#define PIN_PA9__GPIO PINMUX_PIN(PIN_PA9, 0, 0) +#define PIN_PA9__SDMMC0_DAT2 PINMUX_PIN(PIN_PA9, 1, 1) +#define PIN_PA9__FLEXCOM0_IO2 PINMUX_PIN(PIN_PA9, 2, 1) +#define PIN_PA9__D2 PINMUX_PIN(PIN_PA9, 3, 1) +#define PIN_PA9__TIOB5 PINMUX_PIN(PIN_PA9, 6, 3) + +#define PIN_PA10 10 +#define PIN_PA10__GPIO PINMUX_PIN(PIN_PA10, 0, 0) +#define PIN_PA10__SDMMC0_DAT3 PINMUX_PIN(PIN_PA10, 1, 1) +#define PIN_PA10__FLEXCOM0_IO3 PINMUX_PIN(PIN_PA10, 2, 1) +#define PIN_PA10__D3 PINMUX_PIN(PIN_PA10, 3, 1) +#define PIN_PA10__TCLK5 PINMUX_PIN(PIN_PA10, 6, 3) + +#define PIN_PA11 11 +#define PIN_PA11__GPIO PINMUX_PIN(PIN_PA11, 0, 0) +#define PIN_PA11__SDMMC0_DS PINMUX_PIN(PIN_PA11, 1, 1) +#define PIN_PA11__FLEXCOM0_IO4 PINMUX_PIN(PIN_PA11, 2, 1) +#define PIN_PA11__NANDRDY PINMUX_PIN(PIN_PA11, 3, 1) +#define PIN_PA11__TIOB3 PINMUX_PIN(PIN_PA11, 6, 3) + +#define PIN_PA12 12 +#define PIN_PA12__GPIO PINMUX_PIN(PIN_PA12, 0, 0) +#define PIN_PA12__FLEXCOM0_IO0 PINMUX_PIN(PIN_PA12, 2, 1) +#define PIN_PA12__NRD PINMUX_PIN(PIN_PA12, 3, 1) +#define PIN_PA12__PCK0 PINMUX_PIN(PIN_PA12, 4, 1) +#define PIN_PA12__EXT_IRQ0 PINMUX_PIN(PIN_PA12, 5, 1) +#define PIN_PA12__TIOA3 PINMUX_PIN(PIN_PA12, 6, 3) + +#define PIN_PA13 13 +#define PIN_PA13__GPIO PINMUX_PIN(PIN_PA13, 0, 0) +#define PIN_PA13__FLEXCOM0_IO1 PINMUX_PIN(PIN_PA13, 2, 1) +#define PIN_PA13__NCS0 PINMUX_PIN(PIN_PA13, 3, 1) +#define PIN_PA13__PCK1 PINMUX_PIN(PIN_PA13, 4, 1) +#define PIN_PA13__TCLK3 PINMUX_PIN(PIN_PA13, 6, 3) + +#define PIN_PA14 14 +#define PIN_PA14__GPIO PINMUX_PIN(PIN_PA14, 0, 0) +#define PIN_PA14__FLEXCOM4_IO4 PINMUX_PIN(PIN_PA14, 1, 1) +#define PIN_PA14__SDMMC0_WP PINMUX_PIN(PIN_PA14, 2, 1) +#define PIN_PA14__FLEXCOM3_IO0 PINMUX_PIN(PIN_PA14, 3, 4) + +#define PIN_PA15 15 +#define PIN_PA15__GPIO PINMUX_PIN(PIN_PA15, 0, 0) +#define PIN_PA15__FLEXCOM4_IO3 PINMUX_PIN(PIN_PA15, 1, 1) +#define PIN_PA15__SDMMC0_1V8SEL PINMUX_PIN(PIN_PA15, 2, 1) +#define PIN_PA15__FLEXCOM3_IO1 PINMUX_PIN(PIN_PA15, 3, 4) + +#define PIN_PA16 16 +#define PIN_PA16__GPIO PINMUX_PIN(PIN_PA16, 0, 0) +#define PIN_PA16__FLEXCOM4_IO2 PINMUX_PIN(PIN_PA16, 1, 1) +#define PIN_PA16__SDMMCo_CD PINMUX_PIN(PIN_PA16, 2, 1) +#define PIN_PA16__PCK2 PINMUX_PIN(PIN_PA16, 4, 1) +#define PIN_PA16__EXT_IRQ1 PINMUX_PIN(PIN_PA16, 5, 1) + +#define PIN_PA17 17 +#define PIN_PA17__GPIO PINMUX_PIN(PIN_PA17, 0, 0) +#define PIN_PA17__FLEXCOM4_IO1 PINMUX_PIN(PIN_PA17, 1, 1) + +#define PIN_PA18 18 +#define PIN_PA18__GPIO PINMUX_PIN(PIN_PA18, 0, 0) +#define PIN_PA18__FLEXCOM4_IO0 PINMUX_PIN(PIN_PA18, 1, 1) + +#define PIN_PA19 19 +#define PIN_PA19__GPIO PINMUX_PIN(PIN_PA19, 0, 0) +#define PIN_PA19__TK0 PINMUX_PIN(PIN_PA19, 1, 1) +#define PIN_PA19__FLEXCOM4_IO5 PINMUX_PIN(PIN_PA19, 3, 1) +#define PIN_PA19__PWML0 PINMUX_PIN(PIN_PA19, 4, 3) + +#define PIN_PA20 20 +#define PIN_PA20__GPIO PINMUX_PIN(PIN_PA20, 0, 0) +#define PIN_PA20__TD0 PINMUX_PIN(PIN_PA20, 1, 1) +#define PIN_PA20__FLEXCOM3_IO4 PINMUX_PIN(PIN_PA20, 2, 2) +#define PIN_PA20__FLEXCOM4_IO6 PINMUX_PIN(PIN_PA20, 3, 1) +#define PIN_PA20__PWMH0 PINMUX_PIN(PIN_PA20, 4, 3) + +#define PIN_PA21 21 +#define PIN_PA21__GPIO PINMUX_PIN(PIN_PA21, 0, 0) +#define PIN_PA21__TF0 PINMUX_PIN(PIN_PA21, 1, 1) +#define PIN_PA21__FLEXCOM3_IO3 PINMUX_PIN(PIN_PA21, 2, 2) +#define PIN_PA21__PWML1 PINMUX_PIN(PIN_PA21, 4, 3) + +#define PIN_PA22 22 +#define PIN_PA22__GPIO PINMUX_PIN(PIN_PA22, 0, 0) +#define PIN_PA22__RD0 PINMUX_PIN(PIN_PA22, 1, 1) +#define PIN_PA22__FLEXCOM3_IO2 PINMUX_PIN(PIN_PA22, 2, 2) +#define PIN_PA22__PDMC0_DS1 PINMUX_PIN(PIN_PA22, 3, 1) +#define PIN_PA22__PWMH1 PINMUX_PIN(PIN_PA22, 4, 3) + +#define PIN_PA23 23 +#define PIN_PA23__GPIO PINMUX_PIN(PIN_PA23, 0, 0) +#define PIN_PA23__RK0 PINMUX_PIN(PIN_PA23, 1, 1) +#define PIN_PA23__FLEXCOM3_IO1 PINMUX_PIN(PIN_PA23, 2, 2) +#define PIN_PA23__PDMC0_CLK PINMUX_PIN(PIN_PA23, 3, 1) +#define PIN_PA23__PWML2 PINMUX_PIN(PIN_PA23, 4, 3) + +#define PIN_PA24 24 +#define PIN_PA24__GPIO PINMUX_PIN(PIN_PA24, 0, 0) +#define PIN_PA24__RF0 PINMUX_PIN(PIN_PA24, 1, 1) +#define PIN_PA24__FLEXCOM3_IO0 PINMUX_PIN(PIN_PA24, 2, 2) +#define PIN_PA24__PDMC0_DS0 PINMUX_PIN(PIN_PA24, 3, 1) +#define PIN_PA24__PWMH2 PINMUX_PIN(PIN_PA24, 4, 3) + +#define PIN_PA25 25 +#define PIN_PA25__GPIO PINMUX_PIN(PIN_PA25, 0, 0) +#define PIN_PA25__G0_TXCTL PINMUX_PIN(PIN_PA25, 1, 1) +#define PIN_PA25__FLEXCOM6_IO2 PINMUX_PIN(PIN_PA25, 2, 1) + +#define PIN_PA26 26 +#define PIN_PA26__GPIO PINMUX_PIN(PIN_PA26, 0, 0) +#define PIN_PA26__G0_TX0 PINMUX_PIN(PIN_PA26, 1, 1) +#define PIN_PA26__FLEXCOM6_IO3 PINMUX_PIN(PIN_PA26, 2, 1) + +#define PIN_PA27 27 +#define PIN_PA27__GPIO PINMUX_PIN(PIN_PA27, 0, 0) +#define PIN_PA27__G0_TX1 PINMUX_PIN(PIN_PA27, 1, 1) +#define PIN_PA27__FLEXCOM6_IO4 PINMUX_PIN(PIN_PA27, 2, 1) + +#define PIN_PA28 28 +#define PIN_PA28__GPIO PINMUX_PIN(PIN_PA28, 0, 0) +#define PIN_PA28__G0_RXCTL PINMUX_PIN(PIN_PA28, 1, 1) +#define PIN_PA28__FLEXCOM6_IO0 PINMUX_PIN(PIN_PA28, 2, 1) + +#define PIN_PA29 29 +#define PIN_PA29__GPIO PINMUX_PIN(PIN_PA29, 0, 0) +#define PIN_PA29__G0_RX0 PINMUX_PIN(PIN_PA29, 1, 1) +#define PIN_PA29__FLEXCOM6_IO1 PINMUX_PIN(PIN_PA29, 2, 1) + +#define PIN_PA30 30 +#define PIN_PA30__GPIO PINMUX_PIN(PIN_PA30, 0, 0) +#define PIN_PA30__G0_RX1 PINMUX_PIN(PIN_PA30, 1, 1) +#define PIN_PA30__FLEXCOM8_IO0 PINMUX_PIN(PIN_PA30, 2, 1) + +#define PIN_PA31 31 +#define PIN_PA31__GPIO PINMUX_PIN(PIN_PA31, 0, 0) +#define PIN_PA31__G0_MDC PINMUX_PIN(PIN_PA31, 1, 1) +#define PIN_PA31__FLEXCOM8_IO1 PINMUX_PIN(PIN_PA31, 2, 1) + +#define PIN_PB0 32 +#define PIN_PB0__GPIO PINMUX_PIN(PIN_PB0, 0, 0) +#define PIN_PB0__G0_MDIO PINMUX_PIN(PIN_PB0, 1, 1) +#define PIN_PB0__FLEXCOM8_IO3 PINMUX_PIN(PIN_PB0, 2, 2) + +#define PIN_PB1 33 +#define PIN_PB1__GPIO PINMUX_PIN(PIN_PB1, 0, 0) +#define PIN_PB1__G0_REFCK PINMUX_PIN(PIN_PB1, 1, 2) +#define PIN_PB1__FLEXCOM8_IO2 PINMUX_PIN(PIN_PB1, 2, 1) + +#define PIN_PB2 34 +#define PIN_PB2__GPIO PINMUX_PIN(PIN_PB2, 0, 0) +#define PIN_PB2__G0_RX2 PINMUX_PIN(PIN_PB2, 1, 1) +#define PIN_PB2__FLEXCOM8_IO4 PINMUX_PIN(PIN_PB2, 2, 1) +#define PIN_PB2__G0_RXER PINMUX_PIN(PIN_PB2, 3, 2) +#define PIN_PB2__RK0 PINMUX_PIN(PIN_PB2, 4, 2) + +#define PIN_PB3 35 +#define PIN_PB3__GPIO PINMUX_PIN(PIN_PB3, 0, 0) +#define PIN_PB3__G0_RXCK PINMUX_PIN(PIN_PB3, 1, 1) +#define PIN_PB3__FLEXCOM10_IO2 PINMUX_PIN(PIN_PB3, 2, 2) +#define PIN_PB3__TK0 PINMUX_PIN(PIN_PB3, 4, 2) + +#define PIN_PB4 36 +#define PIN_PB4__GPIO PINMUX_PIN(PIN_PB4, 0, 0) +#define PIN_PB4__G0_TX2 PINMUX_PIN(PIN_PB4, 1, 1) +#define PIN_PB4__FLEXCOM10_IO3 PINMUX_PIN(PIN_PB4, 2, 2) +#define PIN_PB4__TF0 PINMUX_PIN(PIN_PB4, 4, 2) + +#define PIN_PB5 37 +#define PIN_PB5__GPIO PINMUX_PIN(PIN_PB5, 0, 0) +#define PIN_PB5__G0_TX3 PINMUX_PIN(PIN_PB5, 1, 1) +#define PIN_PB5__FLEXCOM10_IO4 PINMUX_PIN(PIN_PB5, 2, 1) +#define PIN_PB5__TD0 PINMUX_PIN(PIN_PB5, 4, 2) + +#define PIN_PB6 38 +#define PIN_PB6__GPIO PINMUX_PIN(PIN_PB6, 0, 0) +#define PIN_PB6__G0_RX3 PINMUX_PIN(PIN_PB6, 1, 1) +#define PIN_PB6__FLEXCOM10_IO0 PINMUX_PIN(PIN_PB6, 2, 2) +#define PIN_PB6__RD0 PINMUX_PIN(PIN_PB6, 4, 2) + +#define PIN_PB7 39 +#define PIN_PB7__GPIO PINMUX_PIN(PIN_PB7, 0, 0) +#define PIN_PB7__G0_TSUCOMP PINMUX_PIN(PIN_PB7, 1, 1) +#define PIN_PB7__FLEXCOM10_IO1 PINMUX_PIN(PIN_PB7, 2, 2) +#define PIN_PB7__ADTRG PINMUX_PIN(PIN_PB7, 3, 1) +#define PIN_PB7__RF0 PINMUX_PIN(PIN_PB7, 4, 2) + +#define PIN_PB8 40 +#define PIN_PB8__GPIO PINMUX_PIN(PIN_PB8, 0, 0) +#define PIN_PB8__QSPI0_IO3 PINMUX_PIN(PIN_PB8, 1, 1) +#define PIN_PB8__PCK3 PINMUX_PIN(PIN_PB8, 2, 1) +#define PIN_PB8__FLEXCOM2_IO1 PINMUX_PIN(PIN_PB8, 4, 2) + +#define PIN_PB9 41 +#define PIN_PB9__GPIO PINMUX_PIN(PIN_PB9, 0, 0) +#define PIN_PB9__QSPI0_IO2 PINMUX_PIN(PIN_PB9, 1, 1) +#define PIN_PB9__FLEXCOM2_IO0 PINMUX_PIN(PIN_PB9, 4, 2) +#define PIN_PB9__PWMEXTRG0 PINMUX_PIN(PIN_PB9, 5, 1) + +#define PIN_PB10 42 +#define PIN_PB10__GPIO PINMUX_PIN(PIN_PB10, 0, 0) +#define PIN_PB10__QSPI0_IO1 PINMUX_PIN(PIN_PB10, 1, 1) +#define PIN_PB10__FLEXCOM2_IO4 PINMUX_PIN(PIN_PB10, 4, 2) +#define PIN_PB10__PWMEXTRG1 PINMUX_PIN(PIN_PB10, 5, 1) + +#define PIN_PB11 43 +#define PIN_PB11__GPIO PINMUX_PIN(PIN_PB11, 0, 0) +#define PIN_PB11__QSPI0_IO0 PINMUX_PIN(PIN_PB11, 1, 1) +#define PIN_PB11__FLEXCOM2_IO5 PINMUX_PIN(PIN_PB11, 4, 2) +#define PIN_PB11__PWML3 PINMUX_PIN(PIN_PB11, 5, 1) +#define PIN_PB11__TIOB3 PINMUX_PIN(PIN_PB11, 6, 2) + +#define PIN_PB12 44 +#define PIN_PB12__GPIO PINMUX_PIN(PIN_PB12, 0, 0) +#define PIN_PB12__QSPI0_CS PINMUX_PIN(PIN_PB12, 1, 1) +#define PIN_PB12__FLEXCOM2_IO3 PINMUX_PIN(PIN_PB12, 4, 2) +#define PIN_PB12__PWMFI1 PINMUX_PIN(PIN_PB12, 6, 1) +#define PIN_PB12__TIOA3 PINMUX_PIN(PIN_PB12, 6, 2) + +#define PIN_PB13 45 +#define PIN_PB13__GPIO PINMUX_PIN(PIN_PB13, 0, 0) +#define PIN_PB13__QSPI0_SCK PINMUX_PIN(PIN_PB13, 1, 1) +#define PIN_PB13__FLEXCOM2_IO2 PINMUX_PIN(PIN_PB13, 4, 2) +#define PIN_PB13__PWMFI0 PINMUX_PIN(PIN_PB13, 5, 1) +#define PIN_PB13__TCLK3 PINMUX_PIN(PIN_PB13, 6, 2) + +#define PIN_PB14 46 +#define PIN_PB14__GPIO PINMUX_PIN(PIN_PB14, 0, 0) +#define PIN_PB14__QSPI0_SCKN PINMUX_PIN(PIN_PB14, 1, 1) +#define PIN_PB14__QSPI1_SCK PINMUX_PIN(PIN_PB14, 2, 1) +#define PIN_PB14__I2SMCC0_CK PINMUX_PIN(PIN_PB14, 3, 3) +#define PIN_PB14__FLEXCOM10_IO5 PINMUX_PIN(PIN_PB14, 4, 1) +#define PIN_PB14__PWMH3 PINMUX_PIN(PIN_PB14, 5, 1) +#define PIN_PB14__FLEXCOM2_IO1 PINMUX_PIN(PIN_PB14, 7, 4) + +#define PIN_PB15 47 +#define PIN_PB15__GPIO PINMUX_PIN(PIN_PB15, 0, 0) +#define PIN_PB15__QSPI0_IO4 PINMUX_PIN(PIN_PB15, 1, 1) +#define PIN_PB15__QSPI1_IO0 PINMUX_PIN(PIN_PB15, 2, 1) +#define PIN_PB15__I2SMCC0_WS PINMUX_PIN(PIN_PB15, 3, 3) +#define PIN_PB15__FLEXCOM10_IO6 PINMUX_PIN(PIN_PB15, 4, 1) +#define PIN_PB15__PWML0 PINMUX_PIN(PIN_PB15, 5, 1) +#define PIN_PB15__TCLK4 PINMUX_PIN(PIN_PB15, 6, 2) +#define PIN_PB15__FLEXCOM2_IO0 PINMUX_PIN(PIN_PB15, 7, 4) + +#define PIN_PB16 48 +#define PIN_PB16__GPIO PINMUX_PIN(PIN_PB16, 0, 0) +#define PIN_PB16__QSPI0_IO5 PINMUX_PIN(PIN_PB16, 1, 1) +#define PIN_PB16__QSPI1_IO1 PINMUX_PIN(PIN_PB16, 2, 1) +#define PIN_PB16__I2SMCC0_DIN0 PINMUX_PIN(PIN_PB16, 3, 3) +#define PIN_PB16__FLEXCOM10_IO4 PINMUX_PIN(PIN_PB16, 4, 1) +#define PIN_PB16__PWMH0 PINMUX_PIN(PIN_PB16, 5, 1) +#define PIN_PB16__TIOB4 PINMUX_PIN(PIN_PB16, 6, 2) + +#define PIN_PB17 49 +#define PIN_PB17__GPIO PINMUX_PIN(PIN_PB17, 0, 0) +#define PIN_PB17__QSPI0_IO6 PINMUX_PIN(PIN_PB17, 1, 1) +#define PIN_PB17__QSPI1_IO2 PINMUX_PIN(PIN_PB17, 2, 1) +#define PIN_PB17__I2SMCC0_DOUT0 PINMUX_PIN(PIN_PB17, 3, 3) +#define PIN_PB17__FLEXCOM10_IO3 PINMUX_PIN(PIN_PB17, 4, 1) +#define PIN_PB17__PWML1 PINMUX_PIN(PIN_PB17, 5, 1) +#define PIN_PB17__TIOA4 PINMUX_PIN(PIN_PB17, 6, 2) + +#define PIN_PB18 50 +#define PIN_PB18__GPIO PINMUX_PIN(PIN_PB18, 0, 0) +#define PIN_PB18__QSPI0_IO7 PINMUX_PIN(PIN_PB18, 1, 1) +#define PIN_PB18__QSPI1_IO3 PINMUX_PIN(PIN_PB18, 2, 1) +#define PIN_PB18__I2SMCC0_MCK PINMUX_PIN(PIN_PB18, 3, 3) +#define PIN_PB18__FLEXCOM10_IO2 PINMUX_PIN(PIN_PB18, 4, 1) +#define PIN_PB18__PWMH1 PINMUX_PIN(PIN_PB18, 5, 1) +#define PIN_PB18__TIOA5 PINMUX_PIN(PIN_PB18, 6, 2) + +#define PIN_PB19 51 +#define PIN_PB19__GPIO PINMUX_PIN(PIN_PB19, 0, 0) +#define PIN_PB19__QSPI0_DQS PINMUX_PIN(PIN_PB19, 1, 1) +#define PIN_PB19__EXT_IRQ1 PINMUX_PIN(PIN_PB19, 2, 2) +#define PIN_PB19__PCK4 PINMUX_PIN(PIN_PB19, 3, 1) +#define PIN_PB19__FLEXCOM10_IO1 PINMUX_PIN(PIN_PB19, 4, 1) +#define PIN_PB19__PWML2 PINMUX_PIN(PIN_PB19, 5, 1) +#define PIN_PB19__TIOB5 PINMUX_PIN(PIN_PB19, 6, 2) + +#define PIN_PB20 52 +#define PIN_PB20__GPIO PINMUX_PIN(PIN_PB20, 0, 0) +#define PIN_PB20__QSPI0_INT PINMUX_PIN(PIN_PB20, 1, 1) +#define PIN_PB20__QSPI1_CS PINMUX_PIN(PIN_PB20, 2, 1) +#define PIN_PB20__FLEXCOM10_IO0 PINMUX_PIN(PIN_PB20, 4, 1) +#define PIN_PB20__PWMH2 PINMUX_PIN(PIN_PB20, 5, 1) +#define PIN_PB20__TCLK5 PINMUX_PIN(PIN_PB20, 6, 2) + +#define PIN_PB21 53 +#define PIN_PB21__GPIO PINMUX_PIN(PIN_PB21, 0, 0) +#define PIN_PB21__SDMMC1_RSTN PINMUX_PIN(PIN_PB21, 1, 1) +#define PIN_PB21__FLEXCOM6_IO4 PINMUX_PIN(PIN_PB21, 2, 2) +#define PIN_PB21__TIOB2 PINMUX_PIN(PIN_PB21, 3, 2) +#define PIN_PB21__ADTRG PINMUX_PIN(PIN_PB21, 4, 2) +#define PIN_PB21__EXT_IRQ0 PINMUX_PIN(PIN_PB21, 5, 2) + +#define PIN_PB22 54 +#define PIN_PB22__GPIO PINMUX_PIN(PIN_PB22, 0, 0) +#define PIN_PB22__SDMMC1_CMD PINMUX_PIN(PIN_PB22, 1, 1) +#define PIN_PB22__FLEXCOM6_IO3 PINMUX_PIN(PIN_PB22, 2, 2) +#define PIN_PB22__TCLK2 PINMUX_PIN(PIN_PB22, 3, 2) + +#define PIN_PB23 55 +#define PIN_PB23__GPIO PINMUX_PIN(PIN_PB23, 0, 0) +#define PIN_PB23__SDMMC1_CK PINMUX_PIN(PIN_PB23, 1, 1) +#define PIN_PB23__FLEXCOM6_IO2 PINMUX_PIN(PIN_PB23, 2, 2) +#define PIN_PB23__TIOA2 PINMUX_PIN(PIN_PB23, 3, 2) + +#define PIN_PB24 56 +#define PIN_PB24__GPIO PINMUX_PIN(PIN_PB24, 0, 0) +#define PIN_PB24__SDMMC1_DAT0 PINMUX_PIN(PIN_PB24, 1, 1) +#define PIN_PB24__FLEXCOM6_IO0 PINMUX_PIN(PIN_PB24, 2, 2) + +#define PIN_PB25 57 +#define PIN_PB25__GPIO PINMUX_PIN(PIN_PB25, 0, 0) +#define PIN_PB25__SDMMC1_DAT1 PINMUX_PIN(PIN_PB25, 1, 1) +#define PIN_PB25__FLEXCOM6_IO1 PINMUX_PIN(PIN_PB25, 2, 2) +#define PIN_PB25__TIOB2 PINMUX_PIN(PIN_PB25, 3, 1) + +#define PIN_PB26 58 +#define PIN_PB26__GPIO PINMUX_PIN(PIN_PB26, 0, 0) +#define PIN_PB26__SDMMC1_DAT2 PINMUX_PIN(PIN_PB26, 1, 1) +#define PIN_PB26__FLEXCOM8_IO0 PINMUX_PIN(PIN_PB26, 2, 3) +#define PIN_PB26__TCLK2 PINMUX_PIN(PIN_PB26, 3, 1) + +#define PIN_PB27 59 +#define PIN_PB27__GPIO PINMUX_PIN(PIN_PB27, 0, 0) +#define PIN_PB27__SDMMC1_DAT3 PINMUX_PIN(PIN_PB27, 1, 1) +#define PIN_PB27__FLEXCOM8_IO1 PINMUX_PIN(PIN_PB27, 2, 3) +#define PIN_PB27__TIOA2 PINMUX_PIN(PIN_PB27, 3, 1) + +#define PIN_PB28 60 +#define PIN_PB28__GPIO PINMUX_PIN(PIN_PB28, 0, 0) +#define PIN_PB28__SDMMC1_WP PINMUX_PIN(PIN_PB28, 1, 1) +#define PIN_PB28__FLEXCOM1_IO0 PINMUX_PIN(PIN_PB28, 3, 3) +#define PIN_PB28__D15 PINMUX_PIN(PIN_PB28, 5, 1) + +#define PIN_PB29 61 +#define PIN_PB29__GPIO PINMUX_PIN(PIN_PB29, 0, 0) +#define PIN_PB29__SDMMC1_CD PINMUX_PIN(PIN_PB29, 1, 1) +#define PIN_PB29__I2SMCC0_MCK PINMUX_PIN(PIN_PB29, 2, 1) +#define PIN_PB29__FLEXCOM1_IO1 PINMUX_PIN(PIN_PB29, 3, 3) +#define PIN_PB29__D14 PINMUX_PIN(PIN_PB29, 5, 2) + +#define PIN_PB30 62 +#define PIN_PB30__GPIO PINMUX_PIN(PIN_PB30, 0, 0) +#define PIN_PB30__SDMMC1_1V8SEL PINMUX_PIN(PIN_PB30, 1, 1) +#define PIN_PB30__I2SMCC1_MCK PINMUX_PIN(PIN_PB30, 2, 2) +#define PIN_PB30__FLEXCOM1_IO2 PINMUX_PIN(PIN_PB30, 3, 3) +#define PIN_PB30__TIOA1 PINMUX_PIN(PIN_PB30, 4, 1) +#define PIN_PB30__NCS1 PINMUX_PIN(PIN_PB30, 5, 1) + +#define PIN_PB31 63 +#define PIN_PB31__GPIO PINMUX_PIN(PIN_PB31, 0, 0) +#define PIN_PB31__PCK7 PINMUX_PIN(PIN_PB31, 1, 2) +#define PIN_PB31__I2SMCC1_DIN1 PINMUX_PIN(PIN_PB31, 2, 1) +#define PIN_PB31__FLEXCOM1_IO3 PINMUX_PIN(PIN_PB31, 3, 3) +#define PIN_PB31__TCLK1 PINMUX_PIN(PIN_PB31, 4, 1) +#define PIN_PB31__NWE PINMUX_PIN(PIN_PB31, 5, 2) + +#define PIN_PC0 64 +#define PIN_PC0__GPIO PINMUX_PIN(PIN_PC0, 0, 0) +#define PIN_PC0__PCK6 PINMUX_PIN(PIN_PC0, 1, 2) +#define PIN_PC0__I2SMCC1_DIN2 PINMUX_PIN(PIN_PC0, 2, 1) +#define PIN_PC0__FLEXCOM9_IO4 PINMUX_PIN(PIN_PC0, 3, 2) +#define PIN_PC0__TIOB1 PINMUX_PIN(PIN_PC0, 4, 1) +#define PIN_PC0__NWR1 PINMUX_PIN(PIN_PC0, 5, 1) + +#define PIN_PC1 65 +#define PIN_PC1__GPIO PINMUX_PIN(PIN_PC1, 0, 0) +#define PIN_PC1__PCK5 PINMUX_PIN(PIN_PC1, 1, 1) +#define PIN_PC1__FLEXCOM9_IO2 PINMUX_PIN(PIN_PC1, 3, 2) +#define PIN_PC1__SMCK PINMUX_PIN(PIN_PC1, 5, 1) + +#define PIN_PC2 66 +#define PIN_PC2__GPIO PINMUX_PIN(PIN_PC2, 0, 0) +#define PIN_PC2__EXT_IRQ0 PINMUX_PIN(PIN_PC2, 1, 3) +#define PIN_PC2__FLEXCOM9_IO3 PINMUX_PIN(PIN_PC2, 3, 2) +#define PIN_PC2__A11 PINMUX_PIN(PIN_PC2, 5, 1) + +#define PIN_PC3 67 +#define PIN_PC3__GPIO PINMUX_PIN(PIN_PC3, 0, 0) +#define PIN_PC3__SPDIF_RX PINMUX_PIN(PIN_PC3, 1, 2) +#define PIN_PC3__FLEXCOM9_IO0 PINMUX_PIN(PIN_PC3, 3, 2) +#define PIN_PC3__FLEXCOM0_IO4 PINMUX_PIN(PIN_PC3, 4, 2) +#define PIN_PC3__A10 PINMUX_PIN(PIN_PC3, 5, 1) + +#define PIN_PC4 68 +#define PIN_PC4__GPIO PINMUX_PIN(PIN_PC4, 0, 0) +#define PIN_PC4__SPDIF_TX PINMUX_PIN(PIN_PC4, 1, 2) +#define PIN_PC4__FLEXCOM9_IO1 PINMUX_PIN(PIN_PC4, 3, 2) +#define PIN_PC4__FLEXCOM0_IO3 PINMUX_PIN(PIN_PC4, 4, 2) +#define PIN_PC4__D0 PINMUX_PIN(PIN_PC4, 5, 2) + +#define PIN_PC5 69 +#define PIN_PC5__GPIO PINMUX_PIN(PIN_PC5, 0, 0) +#define PIN_PC5__I3CC_SDASPUE PINMUX_PIN(PIN_PC5, 1, 1) +#define PIN_PC5__I2SMCC1_DIN3 PINMUX_PIN(PIN_PC5, 2, 1) +#define PIN_PC5__FLEXCOM0_IO2 PINMUX_PIN(PIN_PC5, 4, 2) +#define PIN_PC5__D1 PINMUX_PIN(PIN_PC5, 5, 2) + +#define PIN_PC6 70 +#define PIN_PC6__GPIO PINMUX_PIN(PIN_PC6, 0, 0) +#define PIN_PC6__I3CC_SCL PINMUX_PIN(PIN_PC6, 1, 1) +#define PIN_PC6__FLEXCOM0_IO1 PINMUX_PIN(PIN_PC6, 4, 2) +#define PIN_PC6__D4 PINMUX_PIN(PIN_PC6, 5, 2) + +#define PIN_PC7 71 +#define PIN_PC7__GPIO PINMUX_PIN(PIN_PC7, 0, 0) +#define PIN_PC7__I3CC_SDA PINMUX_PIN(PIN_PC7, 1, 1) +#define PIN_PC7__FLEXCOM0_IO0 PINMUX_PIN(PIN_PC7, 4, 2) +#define PIN_PC7__D5 PINMUX_PIN(PIN_PC7, 5, 2) + +#define PIN_PC8 72 +#define PIN_PC8__GPIO PINMUX_PIN(PIN_PC8, 0, 0) +#define PIN_PC8__I2SMCC0_DIN1 PINMUX_PIN(PIN_PC8, 1, 1) +#define PIN_PC8__PDMC0_DS1 PINMUX_PIN(PIN_PC8, 2, 2) +#define PIN_PC8__I2SMCC1_DOUT1 PINMUX_PIN(PIN_PC8, 3, 1) +#define PIN_PC8__FLEXCOM9_IO0 PINMUX_PIN(PIN_PC8, 4, 1) +#define PIN_PC8__D6 PINMUX_PIN(PIN_PC8, 5, 2) + +#define PIN_PC9 73 +#define PIN_PC9__GPIO PINMUX_PIN(PIN_PC9, 0, 0) +#define PIN_PC9__I2SMCC0_DIN2 PINMUX_PIN(PIN_PC9, 1, 1) +#define PIN_PC9__PDMC0_CLK PINMUX_PIN(PIN_PC9, 2, 2) +#define PIN_PC9__I2SMCC1_DOUT2 PINMUX_PIN(PIN_PC9, 3, 1) +#define PIN_PC9__FLEXCOM9_IO1 PINMUX_PIN(PIN_PC9, 4, 1) +#define PIN_PC9__D7 PINMUX_PIN(PIN_PC9, 5, 2) + +#define PIN_PC10 74 +#define PIN_PC10__GPIO PINMUX_PIN(PIN_PC10, 0, 0) +#define PIN_PC10__I2SMCC0_DIN3 PINMUX_PIN(PIN_PC10, 1, 1) +#define PIN_PC10__PDMC0_DS0 PINMUX_PIN(PIN_PC10, 2, 2) +#define PIN_PC10__I2SMCC1_DOUT3 PINMUX_PIN(PIN_PC10, 3, 1) +#define PIN_PC10__FLEXCOM9_IO2 PINMUX_PIN(PIN_PC10, 4, 1) +#define PIN_PC10__D2 PINMUX_PIN(PIN_PC10, 5, 2) + +#define PIN_PC11 75 +#define PIN_PC11__GPIO PINMUX_PIN(PIN_PC11, 0, 0) +#define PIN_PC11__I2SMCC0_DOUT1 PINMUX_PIN(PIN_PC11, 1, 1) +#define PIN_PC11__PDMC1_DS0 PINMUX_PIN(PIN_PC11, 2, 1) +#define PIN_PC11__FLEXCOM9_IO3 PINMUX_PIN(PIN_PC11, 4, 1) +#define PIN_PC10__D3 PINMUX_PIN(PIN_PC10, 5, 2) + +#define PIN_PC12 76 +#define PIN_PC12__GPIO PINMUX_PIN(PIN_PC12, 0, 0) +#define PIN_PC12__I2SMCC0_DOUT2 PINMUX_PIN(PIN_PC12, 1, 1) +#define PIN_PC12__PDMC1_CLK PINMUX_PIN(PIN_PC12, 2, 1) +#define PIN_PC12__FLEXCOM9_IO4 PINMUX_PIN(PIN_PC12, 4, 1) +#define PIN_PC12__A9 PINMUX_PIN(PIN_PC12, 5, 1) + +#define PIN_PC13 77 +#define PIN_PC13__GPIO PINMUX_PIN(PIN_PC13, 0, 0) +#define PIN_PC13__I2SMCC0_DOUT3 PINMUX_PIN(PIN_PC13, 1, 1) +#define PIN_PC13__PDMC1_DS1 PINMUX_PIN(PIN_PC13, 2, 1) +#define PIN_PC13__A8 PINMUX_PIN(PIN_PC13, 5, 1) + +#define PIN_PC14 78 +#define PIN_PC14__GPIO PINMUX_PIN(PIN_PC14, 0, 0) +#define PIN_PC14__I2SMCC1_DIN0 PINMUX_PIN(PIN_PC14, 1, 1) +#define PIN_PC14__SPDIF_RX PINMUX_PIN(PIN_PC14, 2, 3) +#define PIN_PC14__FLEXCOM1_IO0 PINMUX_PIN(PIN_PC14, 3, 2) +#define PIN_PC14__A7 PINMUX_PIN(PIN_PC14, 5, 1) + +#define PIN_PC15 79 +#define PIN_PC15__GPIO PINMUX_PIN(PIN_PC15, 0, 0) +#define PIN_PC15__I2SMCC1_WS PINMUX_PIN(PIN_PC15, 1, 1) +#define PIN_PC15__PDMC1_DS1 PINMUX_PIN(PIN_PC15, 2, 2) +#define PIN_PC15__FLEXCOM1_IO1 PINMUX_PIN(PIN_PC15, 3, 2) +#define PIN_PC15__A6 PINMUX_PIN(PIN_PC15, 5, 1) + +#define PIN_PC16 80 +#define PIN_PC16__GPIO PINMUX_PIN(PIN_PC16, 0, 0) +#define PIN_PC16__I2SMCC1_CK PINMUX_PIN(PIN_PC16, 1, 1) +#define PIN_PC16__PDMC1_CLK PINMUX_PIN(PIN_PC16, 2, 2) +#define PIN_PC16__FLEXCOM1_IO2 PINMUX_PIN(PIN_PC16, 3, 2) +#define PIN_PC16__TIOA1 PINMUX_PIN(PIN_PC16, 4, 2) +#define PIN_PC16__A5 PINMUX_PIN(PIN_PC16, 5, 1) + +#define PIN_PC17 81 +#define PIN_PC17__GPIO PINMUX_PIN(PIN_PC17, 0, 0) +#define PIN_PC17__I2SMCC1_DOUT0 PINMUX_PIN(PIN_PC17, 1, 1) +#define PIN_PC17__PDMC1_DS0 PINMUX_PIN(PIN_PC17, 2, 2) +#define PIN_PC17__FLEXCOM1_IO3 PINMUX_PIN(PIN_PC17, 3, 2) +#define PIN_PC17__TCLK1 PINMUX_PIN(PIN_PC17, 4, 2) +#define PIN_PC17__A4 PINMUX_PIN(PIN_PC17, 5, 1) + +#define PIN_PC18 82 +#define PIN_PC18__GPIO PINMUX_PIN(PIN_PC18, 0, 0) +#define PIN_PC18__I2SMCC0_DIN0 PINMUX_PIN(PIN_PC18, 1, 1) +#define PIN_PC18__SPDIF_TX PINMUX_PIN(PIN_PC18, 2, 3) +#define PIN_PC18__FLEXCOM1_IO4 PINMUX_PIN(PIN_PC18, 3, 2) +#define PIN_PC18__TIOB1 PINMUX_PIN(PIN_PC18, 4, 2) +#define PIN_PC18__A3 PINMUX_PIN(PIN_PC18, 5, 1) + +#define PIN_PC19 83 +#define PIN_PC19__GPIO PINMUX_PIN(PIN_PC19, 0, 0) +#define PIN_PC19__I2SMCC0_WS PINMUX_PIN(PIN_PC19, 1, 1) +#define PIN_PC19__PCK6 PINMUX_PIN(PIN_PC19, 2, 1) +#define PIN_PC19__A2 PINMUX_PIN(PIN_PC19, 5, 1) + +#define PIN_PC20 84 +#define PIN_PC20__GPIO PINMUX_PIN(PIN_PC20, 0, 0) +#define PIN_PC20__I2SMCC0_DOUT0 PINMUX_PIN(PIN_PC20, 1, 1) +#define PIN_PC20__A1 PINMUX_PIN(PIN_PC20, 5, 1) + +#define PIN_PC21 85 +#define PIN_PC21__GPIO PINMUX_PIN(PIN_PC21, 0, 0) +#define PIN_PC21__I2SMCC0_CK PINMUX_PIN(PIN_PC21, 1, 1) +#define PIN_PC21__PCK7 PINMUX_PIN(PIN_PC21, 2, 1) +#define PIN_PC21__A0 PINMUX_PIN(PIN_PC21, 5, 1) + +#define PIN_PC22 86 +#define PIN_PC22__GPIO PINMUX_PIN(PIN_PC22, 0, 0) +#define PIN_PC22__NTRST PINMUX_PIN(PIN_PC22, 1, 1) +#define PIN_PC22__NWAIT PINMUX_PIN(PIN_PC22, 5, 1) + +#define PIN_PC23 87 +#define PIN_PC23__GPIO PINMUX_PIN(PIN_PC23, 0, 0) +#define PIN_PC23__TCK_SWCLK PINMUX_PIN(PIN_PC23, 1, 1) + +#define PIN_PC24 88 +#define PIN_PC24__GPIO PINMUX_PIN(PIN_PC24, 0, 0) +#define PIN_PC24__TMS_SWDIO PINMUX_PIN(PIN_PC24, 1, 1) + +#define PIN_PC25 89 +#define PIN_PC25__GPIO PINMUX_PIN(PIN_PC25, 0, 0) +#define PIN_PC25__TDI PINMUX_PIN(PIN_PC25, 1, 1) + +#define PIN_PC26 90 +#define PIN_PC26__GPIO PINMUX_PIN(PIN_PC26, 0, 0) +#define PIN_PC26__TDO PINMUX_PIN(PIN_PC26, 1, 1) +#define PIN_PC26__A15 PINMUX_PIN(PIN_PC26, 5, 1) + +#define PIN_PC27 91 +#define PIN_PC27__GPIO PINMUX_PIN(PIN_PC27, 0, 0) +#define PIN_PC27__SDMMC2_CMD PINMUX_PIN(PIN_PC27, 1, 1) +#define PIN_PC27__FLEXCOM8_IO0 PINMUX_PIN(PIN_PC27, 2, 2) +#define PIN_PC27__TD1 PINMUX_PIN(PIN_PC27, 4, 2) +#define PIN_PC27__D8 PINMUX_PIN(PIN_PC27, 5, 1) + +#define PIN_PC28 92 +#define PIN_PC28__GPIO PINMUX_PIN(PIN_PC28, 0, 0) +#define PIN_PC28__SDMMC2_CK PINMUX_PIN(PIN_PC28, 1, 1) +#define PIN_PC28__FLEXCOM8_IO1 PINMUX_PIN(PIN_PC28, 2, 2) +#define PIN_PC28__TF1 PINMUX_PIN(PIN_PC28, 4, 2) +#define PIN_PC28__D9 PINMUX_PIN(PIN_PC28, 5, 1) + +#define PIN_PC29 93 +#define PIN_PC29__GPIO PINMUX_PIN(PIN_PC29, 0, 0) +#define PIN_PC29__SDMMC2_DAT0 PINMUX_PIN(PIN_PC29, 1, 1) +#define PIN_PC29__FLEXCOM8_IO2 PINMUX_PIN(PIN_PC29, 2, 2) +#define PIN_PC29__TK1 PINMUX_PIN(PIN_PC29, 4, 2) +#define PIN_PC29__D10 PINMUX_PIN(PIN_PC29, 5, 1) +#define PIN_PC29__TCLK0 PINMUX_PIN(PIN_PC29, 6, 1) + +#define PIN_PC30 94 +#define PIN_PC30__GPIO PINMUX_PIN(PIN_PC30, 0, 0) +#define PIN_PC30__SDMMC2_DAT1 PINMUX_PIN(PIN_PC30, 1, 1) +#define PIN_PC30__FLEXCOM8_IO3 PINMUX_PIN(PIN_PC30, 2, 2) +#define PIN_PC30__RD1 PINMUX_PIN(PIN_PC30, 4, 2) +#define PIN_PC30__D11 PINMUX_PIN(PIN_PC30, 5, 1) +#define PIN_PC30__TIOA0 PINMUX_PIN(PIN_PC30, 6, 1) + +#define PIN_PC31 95 +#define PIN_PC31__GPIO PINMUX_PIN(PIN_PC31, 0, 0) +#define PIN_PC31__SDMMC2_DAT2 PINMUX_PIN(PIN_PC31, 1, 1) +#define PIN_PC31__FLEXCOM8_IO4 PINMUX_PIN(PIN_PC31, 2, 2) +#define PIN_PC31__PCK0 PINMUX_PIN(PIN_PC31, 3, 2) +#define PIN_PC31__RK1 PINMUX_PIN(PIN_PC31, 4, 2) +#define PIN_PC31__D12 PINMUX_PIN(PIN_PC31, 5, 1) +#define PIN_PC31__TIOB0 PINMUX_PIN(PIN_PC31, 6, 1) + +#define PIN_PD0 96 +#define PIN_PD0__GPIO PINMUX_PIN(PIN_PD0, 0, 0) +#define PIN_PD0__SDMMC2_DAT3 PINMUX_PIN(PIN_PD0, 1, 1) +#define PIN_PD0__PCK1 PINMUX_PIN(PIN_PD0, 3, 2) +#define PIN_PD0__RF1 PINMUX_PIN(PIN_PD0, 4, 2) +#define PIN_PD0__D13 PINMUX_PIN(PIN_PD0, 5, 1) + +#define PIN_PD1 97 +#define PIN_PD1__GPIO PINMUX_PIN(PIN_PD1, 0, 0) +#define PIN_PD1__SDMMC2_WP PINMUX_PIN(PIN_PD1, 1, 1) +#define PIN_PD1__FLEXCOM1_IO5 PINMUX_PIN(PIN_PD1, 2, 1) +#define PIN_PD1__LCDC_HSYNC PINMUX_PIN(PIN_PD1, 3, 2) +#define PIN_PD1__FLEXCOM3_IO0 PINMUX_PIN(PIN_PD1, 4, 3) + +#define PIN_PD2 98 +#define PIN_PD2__GPIO PINMUX_PIN(PIN_PD2, 0, 0) +#define PIN_PD2__SDMMC2_CD PINMUX_PIN(PIN_PD2, 1, 1) +#define PIN_PD2__FLEXCOM1_IO6 PINMUX_PIN(PIN_PD2, 2, 1) +#define PIN_PD2__LCDC_VSYNC PINMUX_PIN(PIN_PD2, 3, 2) +#define PIN_PD2__FLEXCOM3_IO1 PINMUX_PIN(PIN_PD2, 4, 3) + +#define PIN_PD3 99 +#define PIN_PD3__GPIO PINMUX_PIN(PIN_PD3, 0, 0) +#define PIN_PD3__SDMMC2_1V8SEL PINMUX_PIN(PIN_PD3, 1, 1) +#define PIN_PD3__FLEXCOM1_IO4 PINMUX_PIN(PIN_PD3, 2, 1) +#define PIN_PD3__TIOA0 PINMUX_PIN(PIN_PD3, 3, 2) +#define PIN_PD3__FLEXCOM3_IO2 PINMUX_PIN(PIN_PD3, 4, 3) +#define PIN_PD3__EXT_IRQ1 PINMUX_PIN(PIN_PD3, 5, 3) + +#define PIN_PD4 100 +#define PIN_PD4__GPIO PINMUX_PIN(PIN_PD4, 0, 0) +#define PIN_PD4__LCDC_HSYNC PINMUX_PIN(PIN_PD4, 1, 1) +#define PIN_PD4__FLEXCOM1_IO2 PINMUX_PIN(PIN_PD4, 2, 1) +#define PIN_PD4__TIOB0 PINMUX_PIN(PIN_PD4, 3, 2) +#define PIN_PD4__FLEXCOM7_IO1 PINMUX_PIN(PIN_PD4, 4, 3) + +#define PIN_PD5 101 +#define PIN_PD5__GPIO PINMUX_PIN(PIN_PD5, 0, 0) +#define PIN_PD5__LCDC_VSYNC PINMUX_PIN(PIN_PD5, 1, 1) +#define PIN_PD5__FLEXCOM1_IO3 PINMUX_PIN(PIN_PD5, 2, 1) +#define PIN_PD5__TCLK0 PINMUX_PIN(PIN_PD5, 3, 2) +#define PIN_PD5__FLEXCOM7_IO0 PINMUX_PIN(PIN_PD5, 4, 3) + +#define PIN_PD6 102 +#define PIN_PD6__GPIO PINMUX_PIN(PIN_PD6, 0, 0) +#define PIN_PD6__LCDC_PWM PINMUX_PIN(PIN_PD6, 1, 1) +#define PIN_PD6__FLEXCOM1_IO1 PINMUX_PIN(PIN_PD6, 2, 1) +#define PIN_PD6__FLEXCOM7_IO2 PINMUX_PIN(PIN_PD6, 4, 3) + +#define PIN_PD7 103 +#define PIN_PD7__GPIO PINMUX_PIN(PIN_PD7, 0, 0) +#define PIN_PD7__LCDC_DISP PINMUX_PIN(PIN_PD7, 1, 1) +#define PIN_PD7__FLEXCOM1_IO0 PINMUX_PIN(PIN_PD7, 2, 1) +#define PIN_PD7__FLEXCOM7_IO3 PINMUX_PIN(PIN_PD7, 4, 3) + +#define PIN_PD8 104 +#define PIN_PD8__GPIO PINMUX_PIN(PIN_PD8, 0, 0) +#define PIN_PD8__CANTX0 PINMUX_PIN(PIN_PD8, 1, 1) +#define PIN_PD8__FLEXCOM7_IO0 PINMUX_PIN(PIN_PD8, 2, 1) + +#define PIN_PD9 105 +#define PIN_PD9__GPIO PINMUX_PIN(PIN_PD9, 0, 0) +#define PIN_PD9__CANRX0 PINMUX_PIN(PIN_PD9, 1, 1) +#define PIN_PD9__FLEXCOM7_IO1 PINMUX_PIN(PIN_PD9, 2, 1) + +#define PIN_PD10 106 +#define PIN_PD10__GPIO PINMUX_PIN(PIN_PD10, 0, 0) +#define PIN_PD10__CANTX1 PINMUX_PIN(PIN_PD10, 1, 1) +#define PIN_PD10__FLEXCOM7_IO2 PINMUX_PIN(PIN_PD10, 2, 1) +#define PIN_PD10__TIOA1 PINMUX_PIN(PIN_PD10, 3, 3) + +#define PIN_PD11 107 +#define PIN_PD11__GPIO PINMUX_PIN(PIN_PD11, 0, 0) +#define PIN_PD11__CANRX1 PINMUX_PIN(PIN_PD11, 1, 1) +#define PIN_PD11__FLEXCOM7_IO3 PINMUX_PIN(PIN_PD11, 2, 1) +#define PIN_PD11__TCLK1 PINMUX_PIN(PIN_PD11, 3, 3) + +#define PIN_PD12 108 +#define PIN_PD12__GPIO PINMUX_PIN(PIN_PD12, 0, 0) +#define PIN_PD12__CANTX2 PINMUX_PIN(PIN_PD12, 1, 1) +#define PIN_PD12__FLEXCOM7_IO4 PINMUX_PIN(PIN_PD12, 2, 1) +#define PIN_PD12__TIOB1 PINMUX_PIN(PIN_PD12, 3, 3) +#define PIN_PD12__PCK2 PINMUX_PIN(PIN_PD12, 4, 2) +#define PIN_PD12__FLEXCOM3_IO3 PINMUX_PIN(PIN_PD12, 5, 3) + +#define PIN_PD13 109 +#define PIN_PD13__GPIO PINMUX_PIN(PIN_PD13, 0, 0) +#define PIN_PD13__CANRX2 PINMUX_PIN(PIN_PD13, 1, 1) +#define PIN_PD13__FLEXCOM5_IO4 PINMUX_PIN(PIN_PD13, 2, 1) +#define PIN_PD13__TIOA2 PINMUX_PIN(PIN_PD13, 3, 3) +#define PIN_PD13__PCK3 PINMUX_PIN(PIN_PD13, 4, 2) + +#define PIN_PD14 110 +#define PIN_PD14__GPIO PINMUX_PIN(PIN_PD14, 0, 0) +#define PIN_PD14__CANTX3 PINMUX_PIN(PIN_PD14, 1, 1) +#define PIN_PD14__FLEXCOM5_IO2 PINMUX_PIN(PIN_PD14, 2, 1) +#define PIN_PD14__TIOB2 PINMUX_PIN(PIN_PD14, 3, 3) + +#define PIN_PD15 111 +#define PIN_PD15__GPIO PINMUX_PIN(PIN_PD15, 0, 0) +#define PIN_PD15__CANRX3 PINMUX_PIN(PIN_PD15, 1, 1) +#define PIN_PD15__FLEXCOM5_IO3 PINMUX_PIN(PIN_PD15, 2, 1) +#define PIN_PD15__TCLK2 PINMUX_PIN(PIN_PD15, 3, 3) + +#define PIN_PD16 112 +#define PIN_PD16__GPIO PINMUX_PIN(PIN_PD16, 0, 0) +#define PIN_PD16__CANTX4 PINMUX_PIN(PIN_PD16, 1, 1) +#define PIN_PD16__FLEXCOM5_IO0 PINMUX_PIN(PIN_PD16, 2, 1) + +#define PIN_PD17 113 +#define PIN_PD17__GPIO PINMUX_PIN(PIN_PD17, 0, 0) +#define PIN_PD17__CANRX4 PINMUX_PIN(PIN_PD17, 1, 1) +#define PIN_PD17__FLEXCOM5_IO1 PINMUX_PIN(PIN_PD17, 2, 1) + +#define PIN_PD18 114 +#define PIN_PD18__GPIO PINMUX_PIN(PIN_PD18, 0, 0) +#define PIN_PD18__FLEXCOM6_IO0 PINMUX_PIN(PIN_PD18, 2, 4) +#define PIN_PD18__CANTX1 PINMUX_PIN(PIN_PD18, 3, 2) +#define PIN_PD18__PCK4 PINMUX_PIN(PIN_PD18, 4, 2) + +#define PIN_PD19 115 +#define PIN_PD19__GPIO PINMUX_PIN(PIN_PD19, 0, 0) +#define PIN_PD19__FLEXCOM6_IO1 PINMUX_PIN(PIN_PD19, 2, 4) +#define PIN_PD19__CANRX1 PINMUX_PIN(PIN_PD19, 3, 2) +#define PIN_PD19__PCK2 PINMUX_PIN(PIN_PD19, 4, 3) + +#define PIN_PD20 116 +#define PIN_PD20__GPIO PINMUX_PIN(PIN_PD20, 0, 0) +#define PIN_PD20__PFLEXCOM6_IO2 PINMUX_PIN(PIN_PD20, 2, 4) +#define PIN_PD20__I2SMCC1_MCK PINMUX_PIN(PIN_PD20, 3, 2) +#define PIN_PD20__PCK3 PINMUX_PIN(PIN_PD20, 4, 3) + +#define PIN_PD21 117 +#define PIN_PD21__GPIO PINMUX_PIN(PIN_PD21, 0, 0) +#define PIN_PD21__G1_TXCTL PINMUX_PIN(PIN_PD21, 1, 2) +#define PIN_PD21__FLEXCOM6_IO2 PINMUX_PIN(PIN_PD21, 2, 3) +#define PIN_PD21__TK1 PINMUX_PIN(PIN_PD21, 3, 1) + +#define PIN_PD22 118 +#define PIN_PD22__GPIO PINMUX_PIN(PIN_PD22, 0, 0) +#define PIN_PD22__G1_TX0 PINMUX_PIN(PIN_PD22, 1, 1) +#define PIN_PD22__FLEXCOM6_IO3 PINMUX_PIN(PIN_PD22, 2, 3) +#define PIN_PD22__TF1 PINMUX_PIN(PIN_PD22, 3, 1) + +#define PIN_PD23 119 +#define PIN_PD23__GPIO PINMUX_PIN(PIN_PD23, 0, 0) +#define PIN_PD23__G1_TX1 PINMUX_PIN(PIN_PD23, 1, 1) +#define PIN_PD23__FLEXCOM6_IO4 PINMUX_PIN(PIN_PD23, 2, 3) +#define PIN_PD23__TD1 PINMUX_PIN(PIN_PD23, 3, 1) + +#define PIN_PD24 120 +#define PIN_PD24__GPIO PINMUX_PIN(PIN_PD24, 0, 0) +#define PIN_PD24__G1_RXCTL PINMUX_PIN(PIN_PD24, 1, 1) +#define PIN_PD24__FLEXCOM6_IO0 PINMUX_PIN(PIN_PD24, 2, 3) +#define PIN_PD24__RD1 PINMUX_PIN(PIN_PD24, 3, 1) +#define PIN_PD24__PDMC0_DS1 PINMUX_PIN(PIN_PD24, 5, 3) + +#define PIN_PD25 121 +#define PIN_PD25__GPIO PINMUX_PIN(PIN_PD25, 0, 0) +#define PIN_PD25__G1_MDC PINMUX_PIN(PIN_PD25, 1, 1) +#define PIN_PD25__FLEXCOM6_IO1 PINMUX_PIN(PIN_PD25, 2, 3) +#define PIN_PD25__RK1 PINMUX_PIN(PIN_PD25, 3, 1) +#define PIN_PD25__PDMC0_CLK PINMUX_PIN(PIN_PD25, 5, 3) + +#define PIN_PD26 122 +#define PIN_PD26__GPIO PINMUX_PIN(PIN_PD26, 0, 0) +#define PIN_PD26__G1_MDIO PINMUX_PIN(PIN_PD26, 1, 1) +#define PIN_PD26__FLEXCOM7_IO4 PINMUX_PIN(PIN_PD26, 2, 2) +#define PIN_PD26__RF1 PINMUX_PIN(PIN_PD26, 3, 1) +#define PIN_PD26__I2SMCC1_DIN2 PINMUX_PIN(PIN_PD26, 4, 2) +#define PIN_PD26__PDMC0_DS0 PINMUX_PIN(PIN_PD26, 5, 3) + +#define PIN_PD27 123 +#define PIN_PD27__GPIO PINMUX_PIN(PIN_PD27, 0, 0) +#define PIN_PD27__G1_RX0 PINMUX_PIN(PIN_PD27, 1, 1) +#define PIN_PD27__FLEXCOM7_IO0 PINMUX_PIN(PIN_PD27, 2, 2) +#define PIN_PD27__SPDIF_RX PINMUX_PIN(PIN_PD27, 3, 1) +#define PIN_PD27__I2SMCC1_DIN3 PINMUX_PIN(PIN_PD27, 4, 2) + +#define PIN_PD28 124 +#define PIN_PD28__GPIO PINMUX_PIN(PIN_PD28, 0, 0) +#define PIN_PD28__G1_RX1 PINMUX_PIN(PIN_PD28, 1, 1) +#define PIN_PD28__FLEXCOM7_IO1 PINMUX_PIN(PIN_PD28, 2, 2) +#define PIN_PD28__SPDIF_TX PINMUX_PIN(PIN_PD28, 3, 1) +#define PIN_PD28__I2SMCC1_DIN1 PINMUX_PIN(PIN_PD28, 4, 2) + +#define PIN_PD29 125 +#define PIN_PD29__GPIO PINMUX_PIN(PIN_PD29, 0, 0) +#define PIN_PD29__G1_REFCK PINMUX_PIN(PIN_PD29, 1, 2) +#define PIN_PD29__FLEXCOM7_IO2 PINMUX_PIN(PIN_PD29, 2, 2) +#define PIN_PD29__I2SMCC1_DOUT3 PINMUX_PIN(PIN_PD29, 3, 2) + +#define PIN_PD30 126 +#define PIN_PD30__GPIO PINMUX_PIN(PIN_PD30, 0, 0) +#define PIN_PD30__G1_RX2 PINMUX_PIN(PIN_PD30, 1, 1) +#define PIN_PD30__FLEXCOM7_IO3 PINMUX_PIN(PIN_PD30, 2, 2) +#define PIN_PD30__I2SMCC1_DOUT1 PINMUX_PIN(PIN_PD30, 3, 2) +#define PIN_PD30__PDMC1_DS1 PINMUX_PIN(PIN_PD30, 4, 3) +#define PIN_PD30__G1_RXER PINMUX_PIN(PIN_PD30, 5, 2) + +#define PIN_PD31 127 +#define PIN_PD31__GPIO PINMUX_PIN(PIN_PD31, 0, 0) +#define PIN_PD31__G1_RX3 PINMUX_PIN(PIN_PD31, 1, 1) +#define PIN_PD31__FLEXCOM5_IO4 PINMUX_PIN(PIN_PD31, 2, 2) +#define PIN_PD31__I2SMCC1_DOUT2 PINMUX_PIN(PIN_PD31, 3, 3) +#define PIN_PD31__PDMC1_DS0 PINMUX_PIN(PIN_PD31, 4, 3) + +#define PIN_PE0 128 +#define PIN_PE0__GPIO PINMUX_PIN(PIN_PE0, 0, 0) +#define PIN_PE0__G1_TX2 PINMUX_PIN(PIN_PE0, 1, 1) +#define PIN_PE0__FLEXCOM5_IO2 PINMUX_PIN(PIN_PE0, 2, 2) +#define PIN_PE0__I2SMCC1_DIN0 PINMUX_PIN(PIN_PE0, 3, 2) +#define PIN_PE0__PDMC1_CLK PINMUX_PIN(PIN_PE0, 4, 3) + +#define PIN_PE1 129 +#define PIN_PE1__GPIO PINMUX_PIN(PIN_PE1, 0, 0) +#define PIN_PE1__G1_TX3 PINMUX_PIN(PIN_PE1, 1, 1) +#define PIN_PE1__FLEXCOM5_IO3 PINMUX_PIN(PIN_PE1, 2, 2) +#define PIN_PE1__I2SMCC1_WS PINMUX_PIN(PIN_PE1, 3, 2) +#define PIN_PE1__PDMC0_DS1 PINMUX_PIN(PIN_PE1, 4, 4) + +#define PIN_PE2 130 +#define PIN_PE2__GPIO PINMUX_PIN(PIN_PE2, 0, 0) +#define PIN_PE2__G1_RXCK PINMUX_PIN(PIN_PE2, 1, 1) +#define PIN_PE2__FLEXCOM5_IO1 PINMUX_PIN(PIN_PE2, 2, 2) +#define PIN_PE2__I2SMCC1_CK PINMUX_PIN(PIN_PE2, 3, 2) +#define PIN_PE2__PDMC0_CLK PINMUX_PIN(PIN_PE2, 4, 4) + +#define PIN_PE3 131 +#define PIN_PE3__GPIO PINMUX_PIN(PIN_PE3, 0, 0) +#define PIN_PE3__G1_TSUCOMP PINMUX_PIN(PIN_PE3, 1, 1) +#define PIN_PE3__FLEXCOM5_IO0 PINMUX_PIN(PIN_PE3, 2, 2) +#define PIN_PE3__I2SMCC1_DOUT0 PINMUX_PIN(PIN_PE3, 3, 2) +#define PIN_PE3__PDMC0_DS0 PINMUX_PIN(PIN_PE3, 4, 4) + +#define PIN_PE4 132 +#define PIN_PE4__GPIO PINMUX_PIN(PIN_PE4, 0, 0) +#define PIN_PE4__LCDC_DAT0 PINMUX_PIN(PIN_PE4, 1, 1) +#define PIN_PE4__FLEXCOM2_IO2 PINMUX_PIN(PIN_PE4, 2, 1) +#define PIN_PE4__PWML0 PINMUX_PIN(PIN_PE4, 3, 2) +#define PIN_PE4__TIOA3 PINMUX_PIN(PIN_PE4, 4, 1) +#define PIN_PE4__I2SMCC0_DIN1 PINMUX_PIN(PIN_PE4, 5, 2) + +#define PIN_PE5 133 +#define PIN_PE5__GPIO PINMUX_PIN(PIN_PE5, 0, 0) +#define PIN_PE5__LCDC_DAT1 PINMUX_PIN(PIN_PE5, 1, 1) +#define PIN_PE5__FLEXCOM2_IO3 PINMUX_PIN(PIN_PE5, 2, 1) +#define PIN_PE5__PWMH0 PINMUX_PIN(PIN_PE5, 3, 2) +#define PIN_PE5__TIOB3 PINMUX_PIN(PIN_PE5, 4, 1) +#define PIN_PE5__I2SMCC0_DIN2 PINMUX_PIN(PIN_PE5, 5, 2) + +#define PIN_PE6 134 +#define PIN_PE6__GPIO PINMUX_PIN(PIN_PE6, 0, 0) +#define PIN_PE6__LCDC_DAT2 PINMUX_PIN(PIN_PE6, 1, 1) +#define PIN_PE6__FLEXCOM2_IO4 PINMUX_PIN(PIN_PE6, 2, 1) +#define PIN_PE6__PWML1 PINMUX_PIN(PIN_PE6, 3, 2) +#define PIN_PE6__TCLK3 PINMUX_PIN(PIN_PE6, 4, 1) +#define PIN_PE6__I2SMCC0_DIN3 PINMUX_PIN(PIN_PE6, 5, 2) + +#define PIN_PE7 135 +#define PIN_PE7__GPIO PINMUX_PIN(PIN_PE7, 0, 0) +#define PIN_PE7__LCDC_DAT3 PINMUX_PIN(PIN_PE7, 1, 1) +#define PIN_PE7__FLEXCOM2_IO5 PINMUX_PIN(PIN_PE7, 2, 1) +#define PIN_PE7__PWMH1 PINMUX_PIN(PIN_PE7, 3, 2) +#define PIN_PE7__TIOA4 PINMUX_PIN(PIN_PE7, 4, 1) +#define PIN_PE7__I2SMCC0_DOUT1 PINMUX_PIN(PIN_PE7, 5, 2) + +#define PIN_PE8 136 +#define PIN_PE8__GPIO PINMUX_PIN(PIN_PE8, 0, 0) +#define PIN_PE8__LCDC_DAT4 PINMUX_PIN(PIN_PE8, 1, 1) +#define PIN_PE8__FLEXCOM2_IO0 PINMUX_PIN(PIN_PE8, 2, 1) +#define PIN_PE8__PWML2 PINMUX_PIN(PIN_PE8, 3, 2) +#define PIN_PE8__TIOB4 PINMUX_PIN(PIN_PE8, 4, 1) +#define PIN_PE8__I2SMCC0_CK PINMUX_PIN(PIN_PE8, 5, 2) + +#define PIN_PE9 137 +#define PIN_PE9__GPIO PINMUX_PIN(PIN_PE9, 0, 0) +#define PIN_PE9__LCDC_DAT5 PINMUX_PIN(PIN_PE9, 1, 1) +#define PIN_PE9__FLEXCOM2_IO1 PINMUX_PIN(PIN_PE9, 2, 1) +#define PIN_PE9__PWMH2 PINMUX_PIN(PIN_PE9, 3, 2) +#define PIN_PE9__TCLK4 PINMUX_PIN(PIN_PE9, 4, 1) +#define PIN_PE9__I2SMCC0_WS PINMUX_PIN(PIN_PE9, 5, 2) + +#define PIN_PE10 138 +#define PIN_PE10__GPIO PINMUX_PIN(PIN_PE10, 0, 0) +#define PIN_PE10__LCDC_DAT6 PINMUX_PIN(PIN_PE10, 1, 1) +#define PIN_PE10__FLEXCOM2_IO6 PINMUX_PIN(PIN_PE10, 2, 1) +#define PIN_PE10__PWML3 PINMUX_PIN(PIN_PE10, 3, 2) +#define PIN_PE10__TIOA5 PINMUX_PIN(PIN_PE10, 4, 1) +#define PIN_PE10__I2SMCC0_DOUT2 PINMUX_PIN(PIN_PE10, 5, 2) + +#define PIN_PE11 139 +#define PIN_PE11__GPIO PINMUX_PIN(PIN_PE11, 0, 0) +#define PIN_PE11__LCDC_DAT7 PINMUX_PIN(PIN_PE11, 1, 1) +#define PIN_PE11__PWMH3 PINMUX_PIN(PIN_PE11, 3, 2) +#define PIN_PE11__TIOB5 PINMUX_PIN(PIN_PE11, 4, 1) +#define PIN_PE11__I2SMCC0_DOUT3 PINMUX_PIN(PIN_PE11, 5, 2) + +#define PIN_PE12 140 +#define PIN_PE12__GPIO PINMUX_PIN(PIN_PE12, 0, 0) +#define PIN_PE12__LCDC_DEN PINMUX_PIN(PIN_PE12, 1, 1) +#define PIN_PE12__PCK3 PINMUX_PIN(PIN_PE12, 2, 4) +#define PIN_PE12__PWMEXTRG0 PINMUX_PIN(PIN_PE12, 3, 2) +#define PIN_PE12__TCLK5 PINMUX_PIN(PIN_PE12, 4, 1) +#define PIN_PE12__I2SMCC0_DIN0 PINMUX_PIN(PIN_PE12, 5, 2) + +#define PIN_PE13 141 +#define PIN_PE13__GPIO PINMUX_PIN(PIN_PE13, 0, 0) +#define PIN_PE13__LCDC_PCK PINMUX_PIN(PIN_PE13, 1, 1) +#define PIN_PE13__PCK4 PINMUX_PIN(PIN_PE13, 2, 3) +#define PIN_PE13__PWMEXTRG1 PINMUX_PIN(PIN_PE13, 3, 2) +#define PIN_PE13__I2SMCC0DOUT0 PINMUX_PIN(PIN_PE13, 5, 2) diff --git a/arch/arm/boot/dts/microchip/sama7d65.dtsi b/arch/arm/boot/dts/microchip/sama7d65.dtsi new file mode 100644 index 000000000000..854b30d15dcd --- /dev/null +++ b/arch/arm/boot/dts/microchip/sama7d65.dtsi @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * sama7d65.dtsi - Device Tree Include file for SAMA7D65 SoC + * + * Copyright (C) 2024 Microchip Technology Inc. and its subsidiaries + * + * Author: Ryan Wanner + * + */ + +#include +#include +#include +#include +#include + +/ { + model = "Microchip SAMA7D65 family SoC"; + compatible = "microchip,sama7d65"; + #address-cells = <1>; + #size-cells = <1>; + interrupt-parent = <&gic>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "arm,cortex-a7"; + reg = <0x0>; + device_type = "cpu"; + clocks = <&pmc PMC_TYPE_CORE PMC_CPUPLL>; + clock-names = "cpu"; + }; + }; + + clocks { + main_xtal: clock-mainxtal { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; + + slow_xtal: clock-slowxtal { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; + }; + + soc { + compatible = "simple-bus"; + ranges; + #address-cells = <1>; + #size-cells = <1>; + + pioa: pinctrl@e0014000 { + compatible = "microchip,sama7d65-pinctrl", "microchip,sama7g5-pinctrl"; + reg = <0xe0014000 0x800>; + interrupts = , + , + , + , + ; + clocks = <&pmc PMC_TYPE_PERIPHERAL 10>; + interrupt-controller; + #interrupt-cells = <2>; + gpio-controller; + #gpio-cells = <2>; + }; + + pmc: clock-controller@e0018000 { + compatible = "microchip,sama7d65-pmc", "syscon"; + reg = <0xe0018000 0x200>; + interrupts = ; + #clock-cells = <2>; + clocks = <&clk32k 1>, <&clk32k 0>, <&main_xtal>; + clock-names = "td_slck", "md_slck", "main_xtal"; + }; + + clk32k: clock-controller@e001d500 { + compatible = "microchip,sama7d65-sckc", "microchip,sam9x60-sckc"; + reg = <0xe001d500 0x4>; + clocks = <&slow_xtal>; + #clock-cells = <1>; + }; + + sdmmc1: mmc@e1208000 { + compatible = "microchip,sama7d65-sdhci", "microchip,sam9x60-sdhci"; + reg = <0xe1208000 0x400>; + interrupts = ; + clocks = <&pmc PMC_TYPE_PERIPHERAL 76>, <&pmc PMC_TYPE_GCK 76>; + clock-names = "hclock", "multclk"; + assigned-clocks = <&pmc PMC_TYPE_GCK 76>; + assigned-clock-rates = <200000000>; + assigned-clock-parents = <&pmc PMC_TYPE_CORE PMC_MCK1>; + status = "disabled"; + }; + + pit64b0: timer@e1800000 { + compatible = "microchip,sama7d65-pit64b", "microchip,sam9x60-pit64b"; + reg = <0xe1800000 0x100>; + interrupts = ; + clocks = <&pmc PMC_TYPE_PERIPHERAL 66>, <&pmc PMC_TYPE_GCK 66>; + clock-names = "pclk", "gclk"; + }; + + pit64b1: timer@e1804000 { + compatible = "microchip,sama7d65-pit64b", "microchip,sam9x60-pit64b"; + reg = <0xe1804000 0x100>; + interrupts = ; + clocks = <&pmc PMC_TYPE_PERIPHERAL 67>, <&pmc PMC_TYPE_GCK 67>; + clock-names = "pclk", "gclk"; + }; + + flx6: flexcom@e2020000 { + compatible = "microchip,sama7d65-flexcom", "atmel,sama5d2-flexcom"; + reg = <0xe2020000 0x200>; + ranges = <0x0 0xe2020000 0x800>; + #address-cells = <1>; + #size-cells = <1>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 40>; + status = "disabled"; + + uart6: serial@200 { + compatible = "microchip,sama7d65-usart", "atmel,at91sam9260-usart"; + reg = <0x200 0x200>; + interrupts = ; + clocks = <&pmc PMC_TYPE_PERIPHERAL 40>; + clock-names = "usart"; + atmel,usart-mode = ; + atmel,fifo-size = <16>; + status = "disabled"; + }; + }; + + gic: interrupt-controller@e8c11000 { + compatible = "arm,cortex-a7-gic"; + reg = <0xe8c11000 0x1000>, + <0xe8c12000 0x2000>; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + }; + }; +}; diff --git a/arch/arm/boot/dts/nuvoton/nuvoton-npcm730-gbs.dts b/arch/arm/boot/dts/nuvoton/nuvoton-npcm730-gbs.dts index 9f64c85e1c20..c3501786d600 100644 --- a/arch/arm/boot/dts/nuvoton/nuvoton-npcm730-gbs.dts +++ b/arch/arm/boot/dts/nuvoton/nuvoton-npcm730-gbs.dts @@ -661,7 +661,7 @@ clock-frequency = <100000>; status = "okay"; - mb_fru@50 { + eeprom@50 { compatible = "atmel,24c64"; reg = <0x50>; }; @@ -704,7 +704,7 @@ reg = <0x5d>; status = "okay"; }; - fan_fru@51 { + eeprom@51 { compatible = "atmel,24c64"; reg = <0x51>; }; @@ -714,7 +714,7 @@ #address-cells = <1>; #size-cells = <0>; reg = <3>; - hsbp_fru@52 { + eeprom@52 { compatible = "atmel,24c64"; reg = <0x52>; status = "okay"; diff --git a/arch/arm/boot/dts/nuvoton/nuvoton-npcm750-runbmc-olympus.dts b/arch/arm/boot/dts/nuvoton/nuvoton-npcm750-runbmc-olympus.dts index 087f4ac43187..f67ede148209 100644 --- a/arch/arm/boot/dts/nuvoton/nuvoton-npcm750-runbmc-olympus.dts +++ b/arch/arm/boot/dts/nuvoton/nuvoton-npcm750-runbmc-olympus.dts @@ -824,7 +824,7 @@ reg = <0x4a>; status = "okay"; }; - m24128_fru@51 { + eeprom@51 { compatible = "atmel,24c128"; reg = <0x51>; pagesize = <64>; diff --git a/arch/arm/boot/dts/nvidia/tegra124-nyan.dtsi b/arch/arm/boot/dts/nvidia/tegra124-nyan.dtsi index 8125c1b3e8d7..974c76f007db 100644 --- a/arch/arm/boot/dts/nvidia/tegra124-nyan.dtsi +++ b/arch/arm/boot/dts/nvidia/tegra124-nyan.dtsi @@ -716,6 +716,7 @@ regulator-name = "+5V_USB_HS"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; + regulator-boot-on; gpio = <&gpio TEGRA_GPIO(N, 4) GPIO_ACTIVE_HIGH>; enable-active-high; gpio-open-drain; @@ -727,6 +728,7 @@ regulator-name = "+5V_USB_SS"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; + regulator-boot-on; gpio = <&gpio TEGRA_GPIO(N, 5) GPIO_ACTIVE_HIGH>; enable-active-high; gpio-open-drain; diff --git a/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts b/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts index 7cd17b43b4b2..06545a6052f7 100644 --- a/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts +++ b/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts @@ -160,7 +160,7 @@ }; }; - mdio_gpio: mdio-gpio { + mdio_gpio: mdio { compatible = "virtual,mdio-gpio"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_swmdio>; diff --git a/arch/arm/boot/dts/nxp/imx/imx51-zii-scu2-mezz.dts b/arch/arm/boot/dts/nxp/imx/imx51-zii-scu2-mezz.dts index 625f9ac671ae..26eb7a9506e4 100644 --- a/arch/arm/boot/dts/nxp/imx/imx51-zii-scu2-mezz.dts +++ b/arch/arm/boot/dts/nxp/imx/imx51-zii-scu2-mezz.dts @@ -37,7 +37,7 @@ regulator-max-microvolt = <5000000>; }; - mdio_gpio: mdio-gpio { + mdio_gpio: mdio { compatible = "virtual,mdio-gpio"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_swmdio>; diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi index c1ae7c47b442..aa1adcc74019 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi @@ -94,7 +94,7 @@ mdio-gpio0 = &mdio0; }; - mdio0: mdio-gpio { + mdio0: mdio { compatible = "virtual,mdio-gpio"; gpios = <&gpio2 5 GPIO_ACTIVE_HIGH>, /* mdc */ <&gpio2 7 GPIO_ACTIVE_HIGH>; /* mdio */ diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi index 1c72da417011..dffab5aa8b9c 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi @@ -691,7 +691,7 @@ adv_7280: adv7280@21 { compatible = "adi,adv7280"; - adv,force-bt656-4; + adi,force-bt656-4; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_ipu1_csi0>; reg = <0x21>; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-sabresd.dtsi index dc8298f6db34..960e83f5e904 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-sabresd.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-sabresd.dtsi @@ -113,8 +113,8 @@ "DMICDAT", "DMIC"; mux-int-port = <2>; mux-ext-port = <3>; - hp-det-gpio = <&gpio7 8 GPIO_ACTIVE_LOW>; - mic-det-gpio = <&gpio1 9 GPIO_ACTIVE_LOW>; + hp-det-gpios = <&gpio7 8 GPIO_ACTIVE_LOW>; + mic-det-gpios = <&gpio1 9 GPIO_ACTIVE_LOW>; }; backlight_lvds: backlight-lvds { @@ -804,6 +804,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usbotg>; disable-over-current; + dr_mode = "otg"; status = "okay"; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi index d2200c9db25a..45bcfd7faf9d 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi @@ -711,8 +711,8 @@ reg_vdd3p0: regulator-3p0 { compatible = "fsl,anatop-regulator"; regulator-name = "vdd3p0"; - regulator-min-microvolt = <2800000>; - regulator-max-microvolt = <3150000>; + regulator-min-microvolt = <2625000>; + regulator-max-microvolt = <3400000>; regulator-always-on; anatop-reg-offset = <0x120>; anatop-vol-bit-shift = <8>; @@ -806,6 +806,7 @@ reg = <0x020c9000 0x1000>; interrupts = <0 44 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6QDL_CLK_USBPHY1>; + phy-3p0-supply = <®_vdd3p0>; fsl,anatop = <&anatop>; }; @@ -814,6 +815,7 @@ reg = <0x020ca000 0x1000>; interrupts = <0 45 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6QDL_CLK_USBPHY2>; + phy-3p0-supply = <®_vdd3p0>; fsl,anatop = <&anatop>; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6sl-evk.dts b/arch/arm/boot/dts/nxp/imx/imx6sl-evk.dts index 55cdfa7ea206..036705b783f4 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6sl-evk.dts +++ b/arch/arm/boot/dts/nxp/imx/imx6sl-evk.dts @@ -108,7 +108,7 @@ "IN3R", "AMIC"; mux-int-port = <2>; mux-ext-port = <3>; - hp-det-gpio = <&gpio4 19 GPIO_ACTIVE_LOW>; + hp-det-gpios = <&gpio4 19 GPIO_ACTIVE_LOW>; }; panel { diff --git a/arch/arm/boot/dts/nxp/imx/imx6sl.dtsi b/arch/arm/boot/dts/nxp/imx/imx6sl.dtsi index 941a2f185056..7381fb7f8912 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6sl.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6sl.dtsi @@ -546,8 +546,8 @@ reg_vdd3p0: regulator-3p0 { compatible = "fsl,anatop-regulator"; regulator-name = "vdd3p0"; - regulator-min-microvolt = <2800000>; - regulator-max-microvolt = <3150000>; + regulator-min-microvolt = <2625000>; + regulator-max-microvolt = <3400000>; regulator-always-on; anatop-reg-offset = <0x120>; anatop-vol-bit-shift = <8>; @@ -640,6 +640,7 @@ reg = <0x020c9000 0x1000>; interrupts = <0 44 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6SL_CLK_USBPHY1>; + phy-3p0-supply = <®_vdd3p0>; fsl,anatop = <&anatop>; }; @@ -648,6 +649,7 @@ reg = <0x020ca000 0x1000>; interrupts = <0 45 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6SL_CLK_USBPHY2>; + phy-3p0-supply = <®_vdd3p0>; fsl,anatop = <&anatop>; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6sll-evk.dts b/arch/arm/boot/dts/nxp/imx/imx6sll-evk.dts index 05d6827ea2af..814401486792 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6sll-evk.dts +++ b/arch/arm/boot/dts/nxp/imx/imx6sll-evk.dts @@ -157,7 +157,7 @@ "IN3R", "AMIC"; mux-int-port = <2>; mux-ext-port = <3>; - hp-det-gpio = <&gpio4 24 GPIO_ACTIVE_LOW>; + hp-det-gpios = <&gpio4 24 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6sx-sdb.dtsi b/arch/arm/boot/dts/nxp/imx/imx6sx-sdb.dtsi index 1beac42c1a27..67cf09e63a63 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6sx-sdb.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6sx-sdb.dtsi @@ -167,7 +167,7 @@ "IN3R", "AMIC"; mux-int-port = <2>; mux-ext-port = <6>; - hp-det-gpio = <&gpio1 17 GPIO_ACTIVE_LOW>; + hp-det-gpios = <&gpio1 17 GPIO_ACTIVE_LOW>; }; panel { diff --git a/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi b/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi index a9550f115f82..5132b575b001 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi @@ -637,8 +637,8 @@ reg_vdd3p0: regulator-3p0 { compatible = "fsl,anatop-regulator"; regulator-name = "vdd3p0"; - regulator-min-microvolt = <2800000>; - regulator-max-microvolt = <3150000>; + regulator-min-microvolt = <2625000>; + regulator-max-microvolt = <3400000>; regulator-always-on; anatop-reg-offset = <0x120>; anatop-vol-bit-shift = <8>; @@ -731,6 +731,7 @@ reg = <0x020c9000 0x1000>; interrupts = ; clocks = <&clks IMX6SX_CLK_USBPHY1>; + phy-3p0-supply = <®_vdd3p0>; fsl,anatop = <&anatop>; }; @@ -739,6 +740,7 @@ reg = <0x020ca000 0x1000>; interrupts = ; clocks = <&clks IMX6SX_CLK_USBPHY2>; + phy-3p0-supply = <®_vdd3p0>; fsl,anatop = <&anatop>; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi index b74ee8948a78..0e839bbfea08 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi @@ -68,7 +68,7 @@ audio-cpu = <&sai2>; audio-codec = <&codec>; audio-asrc = <&asrc>; - hp-det-gpio = <&gpio5 4 0>; + hp-det-gpios = <&gpio5 4 0>; audio-routing = "Headphone Jack", "HP_L", "Headphone Jack", "HP_R", diff --git a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi index e1c401f468e1..576a7df505d3 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi @@ -87,34 +87,6 @@ <&adc2 0>, <&adc2 1>, <&adc2 2>, <&adc2 3>; }; - reg_sd1_vmmc: regulator-sd1-vmmc { - compatible = "regulator-fixed"; - regulator-name = "VCC3V3_SD1"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - }; - - reg_fec1_pwdn: regulator-fec1-pwdn { - compatible = "regulator-fixed"; - regulator-name = "PWDN_FEC1"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - gpio = <&gpio1 9 GPIO_ACTIVE_HIGH>; - enable-active-high; - }; - - reg_fec2_pwdn: regulator-fec2-pwdn { - compatible = "regulator-fixed"; - regulator-name = "PWDN_FEC2"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - gpio = <&gpio2 31 GPIO_ACTIVE_HIGH>; - enable-active-high; - }; - reg_usb_otg1_vbus: regulator-usb-otg1-vbus { compatible = "regulator-fixed"; regulator-name = "VBUS_USBOTG1"; @@ -141,6 +113,7 @@ gpio = <&pca9555 12 GPIO_ACTIVE_HIGH>; enable-active-high; regulator-always-on; + vin-supply = <®_mba_5v>; }; reg_mpcie_3v3: regulator-mpcie-3v3 { @@ -151,6 +124,7 @@ gpio = <&pca9555 10 GPIO_ACTIVE_HIGH>; enable-active-high; regulator-always-on; + vin-supply = <®_mba_3v3>; }; reg_mba_12v0: regulator-mba-12v0 { @@ -162,13 +136,18 @@ enable-active-high; }; - reg_lvds_transmitter: regulator-lvds-transmitter { + reg_mba_5v: regulator-mba-5v { compatible = "regulator-fixed"; - regulator-name = "#SHTDN_LVDS"; + regulator-name = "VCC5V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + reg_mba_3v3: regulator-mba-3v3 { + compatible = "regulator-fixed"; + regulator-name = "VCC3V3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - gpio = <&pca9555 1 GPIO_ACTIVE_HIGH>; - enable-active-high; }; reg_vref_1v8: regulator-vref-1v8 { @@ -186,14 +165,7 @@ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; regulator-always-on; - }; - - reg_vcc_3v3: regulator-vcc-3v3 { - compatible = "regulator-fixed"; - regulator-name = "VCC3V3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; + vin-supply = <®_mba_3v3>; }; sound { @@ -239,7 +211,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet1>; phy-mode = "rgmii-id"; - phy-supply = <®_fec1_pwdn>; phy-handle = <ðphy1_0>; fsl,magic-packet; status = "okay"; @@ -260,6 +231,8 @@ reset-gpios = <&gpio7 15 GPIO_ACTIVE_LOW>; reset-assert-us = <1000>; reset-deassert-us = <500>; + interrupt-parent = <&gpio1>; + interrupts = <9 IRQ_TYPE_EDGE_FALLING>; }; }; }; @@ -318,7 +291,7 @@ lm75: temperature-sensor@49 { compatible = "national,lm75a"; reg = <0x49>; - vs-supply = <®_vcc_3v3>; + vs-supply = <®_mba_3v3>; }; }; @@ -351,7 +324,7 @@ interrupts = <12 IRQ_TYPE_EDGE_FALLING>; interrupt-controller; #interrupt-cells = <2>; - vcc-supply = <®_vcc_3v3>; + vcc-supply = <®_mba_3v3>; }; }; @@ -668,7 +641,7 @@ pinctrl-2 = <&pinctrl_usdhc1_200mhz>, <&pinctrl_usdhc1_gpio>; cd-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>; wp-gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>; - vmmc-supply = <®_sd1_vmmc>; + vmmc-supply = <®_mba_3v3>; bus-width = <4>; no-1-8-v; no-sdio; diff --git a/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi index 028961eb7108..aa8f65cd4adf 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi @@ -135,6 +135,7 @@ lm75a: temperature-sensor@48 { compatible = "national,lm75a"; reg = <0x48>; + vs-supply = <&vgen4_reg>; }; /* NXP SE97BTP with temperature sensor + eeprom, TQMa7x 02xx */ @@ -150,7 +151,6 @@ reg = <0x50>; pagesize = <32>; vcc-supply = <&vgen4_reg>; - status = "okay"; }; at24c02: eeprom@56 { @@ -158,7 +158,6 @@ reg = <0x56>; pagesize = <16>; vcc-supply = <&vgen4_reg>; - status = "okay"; }; ds1339: rtc@68 { diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-mba7.dts b/arch/arm/boot/dts/nxp/imx/imx7d-mba7.dts index 0443faa3dfae..e3ee16f1aaa9 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7d-mba7.dts +++ b/arch/arm/boot/dts/nxp/imx/imx7d-mba7.dts @@ -21,7 +21,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet2>; phy-mode = "rgmii-id"; - phy-supply = <®_fec2_pwdn>; phy-handle = <ðphy2_0>; fsl,magic-packet; status = "okay"; @@ -42,6 +41,8 @@ reset-gpios = <&gpio2 28 GPIO_ACTIVE_LOW>; reset-assert-us = <1000>; reset-deassert-us = <500>; + interrupt-parent = <&gpio2>; + interrupts = <31 IRQ_TYPE_EDGE_FALLING>; }; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-sdb.dts b/arch/arm/boot/dts/nxp/imx/imx7d-sdb.dts index f712537fca16..6cde84636900 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7d-sdb.dts +++ b/arch/arm/boot/dts/nxp/imx/imx7d-sdb.dts @@ -169,7 +169,7 @@ model = "wm8960-audio"; audio-cpu = <&sai1>; audio-codec = <&codec>; - hp-det-gpio = <&gpio2 28 GPIO_ACTIVE_HIGH>; + hp-det-gpios = <&gpio2 28 GPIO_ACTIVE_HIGH>; audio-routing = "Headphone Jack", "HP_L", "Headphone Jack", "HP_R", diff --git a/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi b/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi index dd714d235d5f..b0bad0d1ba36 100644 --- a/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi @@ -87,7 +87,7 @@ reg = <0x402c0000 0x4000>; interrupts = <110>; clocks = <&clks IMXRT1050_CLK_IPG_PDOF>, - <&clks IMXRT1050_CLK_OSC>, + <&clks IMXRT1050_CLK_AHB_PODF>, <&clks IMXRT1050_CLK_USDHC1>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi index d0f6120b665d..39530eb580ea 100644 --- a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi @@ -427,8 +427,9 @@ interrupt-names = "global", "doorbell"; - interconnects = <&system_noc MASTER_PCIE &mc_virt SLAVE_EBI_CH0>; - interconnect-names = "pcie-mem"; + interconnects = <&system_noc MASTER_PCIE &mc_virt SLAVE_EBI_CH0>, + <&mem_noc MASTER_AMPSS_M0 &system_noc SLAVE_PCIE_0>; + interconnect-names = "pcie-mem", "cpu-pcie"; resets = <&gcc GCC_PCIE_BCR>; reset-names = "core"; @@ -613,6 +614,8 @@ iommus = <&apps_smmu 0x1a0 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_hsphy>, <&usb_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; }; diff --git a/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi index 3bc67bb8c1eb..6b23ee676c9e 100644 --- a/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi @@ -335,6 +335,10 @@ ; interrupt-names = "global", "doorbell"; + interconnects = <&system_noc MASTER_PCIE_0 &mc_virt SLAVE_EBI1>, + <&mem_noc MASTER_APPSS_PROC &system_noc SLAVE_PCIE_0>; + interconnect-names = "pcie-mem", "cpu-pcie"; + resets = <&gcc GCC_PCIE_BCR>; reset-names = "core"; @@ -526,6 +530,8 @@ iommus = <&apps_smmu 0x1a0 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_hsphy>, <&usb_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; }; diff --git a/arch/arm/boot/dts/renesas/r7s72100.dtsi b/arch/arm/boot/dts/renesas/r7s72100.dtsi index b831bbc431ef..1a866dbaf5e9 100644 --- a/arch/arm/boot/dts/renesas/r7s72100.dtsi +++ b/arch/arm/boot/dts/renesas/r7s72100.dtsi @@ -238,6 +238,8 @@ ; interrupt-names = "error", "rx", "tx"; clocks = <&mstp10_clks R7S72100_CLK_SPI0>; + dmas = <&dmac 0x2d21>, <&dmac 0x2d22>; + dma-names = "tx", "rx"; power-domains = <&cpg_clocks>; num-cs = <1>; #address-cells = <1>; @@ -253,6 +255,8 @@ ; interrupt-names = "error", "rx", "tx"; clocks = <&mstp10_clks R7S72100_CLK_SPI1>; + dmas = <&dmac 0x2d25>, <&dmac 0x2d26>; + dma-names = "tx", "rx"; power-domains = <&cpg_clocks>; num-cs = <1>; #address-cells = <1>; @@ -268,6 +272,8 @@ ; interrupt-names = "error", "rx", "tx"; clocks = <&mstp10_clks R7S72100_CLK_SPI2>; + dmas = <&dmac 0x2d29>, <&dmac 0x2d2a>; + dma-names = "tx", "rx"; power-domains = <&cpg_clocks>; num-cs = <1>; #address-cells = <1>; @@ -283,6 +289,8 @@ ; interrupt-names = "error", "rx", "tx"; clocks = <&mstp10_clks R7S72100_CLK_SPI3>; + dmas = <&dmac 0x2d2d>, <&dmac 0x2d2e>; + dma-names = "tx", "rx"; power-domains = <&cpg_clocks>; num-cs = <1>; #address-cells = <1>; @@ -298,6 +306,8 @@ ; interrupt-names = "error", "rx", "tx"; clocks = <&mstp10_clks R7S72100_CLK_SPI4>; + dmas = <&dmac 0x2d31>, <&dmac 0x2d32>; + dma-names = "tx", "rx"; power-domains = <&cpg_clocks>; num-cs = <1>; #address-cells = <1>; diff --git a/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi b/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi index 9bc05961577d..70e3091062f9 100644 --- a/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi +++ b/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi @@ -300,12 +300,31 @@ regulator-max-microvolt = <2800000>; }; + earmic_bias_reg: voltage-regulator-6 { + compatible = "regulator-fixed"; + regulator-name = "EAR_MICBIAS_LDO_2.8V"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + gpio = <&gpm0 0 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + sound: sound { compatible = "samsung,midas-audio"; model = "TAB3"; mic-bias-supply = <&mic_bias_reg>; submic-bias-supply = <&submic_bias_reg>; + lineout-sel-gpios = <&gpj1 2 GPIO_ACTIVE_HIGH>; + + headset-mic-bias-supply = <&earmic_bias_reg>; + headset-detect-gpios = <&gpx0 4 GPIO_ACTIVE_LOW>; + headset-key-gpios = <&gpx3 6 GPIO_ACTIVE_LOW>; + samsung,headset-4pole-threshold-microvolt = <710 2000>; + samsung,headset-button-threshold-microvolt = <0 130 260>; + io-channel-names = "headset-detect"; + io-channels = <&adc 0>; + audio-routing = "HP", "HPOUT1L", "HP", "HPOUT1R", @@ -351,6 +370,11 @@ }; }; +&adc { + vdd-supply = <&ldo3_reg>; + status = "okay"; +}; + &bus_acp { devfreq = <&bus_dmc>; status = "okay"; @@ -511,12 +535,11 @@ wm1811: audio-codec@1a { compatible = "wlf,wm1811"; reg = <0x1a>; - clocks = <&pmu_system_controller 0>; - clock-names = "MCLK1"; + clocks = <&pmu_system_controller 0>, + <&s5m8767_osc S2MPS11_CLK_BT>; + clock-names = "MCLK1", "MCLK2"; interrupt-controller; #interrupt-cells = <2>; - interrupt-parent = <&gpx3>; - interrupts = <6 IRQ_TYPE_LEVEL_HIGH>; gpio-controller; #gpio-cells = <2>; diff --git a/arch/arm/boot/dts/st/Makefile b/arch/arm/boot/dts/st/Makefile index eab3a9bd435f..b7d5d305cbbe 100644 --- a/arch/arm/boot/dts/st/Makefile +++ b/arch/arm/boot/dts/st/Makefile @@ -39,6 +39,7 @@ dtb-$(CONFIG_ARCH_STM32) += \ stm32mp151c-mect1s.dtb \ stm32mp153c-dhcom-drc02.dtb \ stm32mp153c-dhcor-drc-compact.dtb \ + stm32mp153c-lxa-tac-gen3.dtb \ stm32mp153c-mecio1r1.dtb \ stm32mp157a-avenger96.dtb \ stm32mp157a-dhcor-avenger96.dtb \ diff --git a/arch/arm/boot/dts/st/stih410-b2260.dts b/arch/arm/boot/dts/st/stih410-b2260.dts index 240b62040000..736b1e059b0a 100644 --- a/arch/arm/boot/dts/st/stih410-b2260.dts +++ b/arch/arm/boot/dts/st/stih410-b2260.dts @@ -206,5 +206,9 @@ sata1: sata@9b28000 { status = "okay"; }; + + gpu: gpu@9f00000 { + status = "okay"; + }; }; }; diff --git a/arch/arm/boot/dts/st/stih410.dtsi b/arch/arm/boot/dts/st/stih410.dtsi index a69231854f78..d56343f44fda 100644 --- a/arch/arm/boot/dts/st/stih410.dtsi +++ b/arch/arm/boot/dts/st/stih410.dtsi @@ -285,5 +285,39 @@ resets = <&softreset STIH407_LPM_SOFTRESET>; hdmi-phandle = <&sti_hdmi>; }; + + gpu: gpu@9f00000 { + compatible = "st,stih410-mali", "arm,mali-400"; + reg = <0x9f00000 0x10000>; + /* LIMA driver needs 2 clocks, use the same for both */ + clocks = <&clk_s_c0_flexgen CLK_ICN_GPU>, + <&clk_s_c0_flexgen CLK_ICN_GPU>; + clock-names = "bus", "core"; + assigned-clocks = <&clk_s_c0_flexgen CLK_ICN_GPU>; + assigned-clock-rates = <400000000>; + resets = <&softreset STIH407_GPU_SOFTRESET>; + interrupts = , + , + , + , + , + , + , + , + , + ; + interrupt-names = "gp", + "gpmmu", + "pp0", + "ppmmu0", + "pp1", + "ppmmu1", + "pp2", + "ppmmu2", + "pp3", + "ppmmu3"; + + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/st/stm32mp131.dtsi b/arch/arm/boot/dts/st/stm32mp131.dtsi index e1a764d269d2..0019d12c3d3d 100644 --- a/arch/arm/boot/dts/st/stm32mp131.dtsi +++ b/arch/arm/boot/dts/st/stm32mp131.dtsi @@ -261,6 +261,11 @@ dma-names = "up"; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + timer@5 { compatible = "st,stm32h7-timer-trigger"; reg = <5>; @@ -281,6 +286,11 @@ dma-names = "up"; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + timer@6 { compatible = "st,stm32h7-timer-trigger"; reg = <6>; @@ -1196,6 +1206,11 @@ access-controllers = <&etzpc 23>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; @@ -1221,6 +1236,11 @@ access-controllers = <&etzpc 24>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; @@ -1246,6 +1266,11 @@ access-controllers = <&etzpc 25>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; @@ -1276,6 +1301,11 @@ access-controllers = <&etzpc 26>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; @@ -1304,6 +1334,11 @@ access-controllers = <&etzpc 27>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; @@ -1332,6 +1367,11 @@ access-controllers = <&etzpc 28>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; diff --git a/arch/arm/boot/dts/st/stm32mp135f-dk.dts b/arch/arm/boot/dts/st/stm32mp135f-dk.dts index 3a276589fef7..19a32f7d4d7d 100644 --- a/arch/arm/boot/dts/st/stm32mp135f-dk.dts +++ b/arch/arm/boot/dts/st/stm32mp135f-dk.dts @@ -440,6 +440,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { /* PWM output on pin 7 of the expansion connector (CN8.7) using TIM3_CH4 func */ pinctrl-0 = <&pwm3_pins_a>; @@ -456,6 +459,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { /* PWM output on pin 31 of the expansion connector (CN8.31) using TIM4_CH2 func */ pinctrl-0 = <&pwm4_pins_a>; @@ -472,6 +478,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { /* PWM output on pin 32 of the expansion connector (CN8.32) using TIM8_CH3 func */ pinctrl-0 = <&pwm8_pins_a>; @@ -486,6 +495,9 @@ &timers14 { status = "disabled"; + counter { + status = "okay"; + }; pwm { /* PWM output on pin 33 of the expansion connector (CN8.33) using TIM14_CH1 func */ pinctrl-0 = <&pwm14_pins_a>; diff --git a/arch/arm/boot/dts/st/stm32mp13xx-dhcor-som.dtsi b/arch/arm/boot/dts/st/stm32mp13xx-dhcor-som.dtsi index 5edbc790d1d2..6236ce2a6968 100644 --- a/arch/arm/boot/dts/st/stm32mp13xx-dhcor-som.dtsi +++ b/arch/arm/boot/dts/st/stm32mp13xx-dhcor-som.dtsi @@ -85,8 +85,8 @@ vddcpu: buck1 { /* VDD_CPU_1V2 */ regulator-name = "vddcpu"; - regulator-min-microvolt = <1250000>; - regulator-max-microvolt = <1250000>; + regulator-min-microvolt = <1350000>; + regulator-max-microvolt = <1350000>; regulator-always-on; regulator-initial-mode = <0>; regulator-over-current-protection; @@ -201,17 +201,17 @@ pagesize = <64>; }; - eeprom0wl: eeprom@58 { - compatible = "st,24256e-wl"; /* ST M24256E WL page of 0x50 */ - pagesize = <64>; - reg = <0x58>; - }; - rv3032: rtc@51 { compatible = "microcrystal,rv3032"; reg = <0x51>; interrupts-extended = <&gpioi 0 IRQ_TYPE_EDGE_FALLING>; }; + + eeprom0wl: eeprom@58 { + compatible = "st,24256e-wl"; /* ST M24256E WL page of 0x50 */ + pagesize = <64>; + reg = <0x58>; + }; }; &iwdg2 { diff --git a/arch/arm/boot/dts/st/stm32mp151.dtsi b/arch/arm/boot/dts/st/stm32mp151.dtsi index b28dc90926bd..b9a87fbe971d 100644 --- a/arch/arm/boot/dts/st/stm32mp151.dtsi +++ b/arch/arm/boot/dts/st/stm32mp151.dtsi @@ -129,7 +129,7 @@ reg = <0x4c001000 0x400>; st,proc-id = <0>; interrupts-extended = - <&exti 61 1>, + <&exti 61 IRQ_TYPE_LEVEL_HIGH>, <&intc GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "rx", "tx"; clocks = <&rcc IPCC>; @@ -578,6 +578,11 @@ access-controllers = <&etzpc 20>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + timer@5 { compatible = "st,stm32h7-timer-trigger"; reg = <5>; @@ -599,6 +604,11 @@ access-controllers = <&etzpc 21>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + timer@6 { compatible = "st,stm32h7-timer-trigger"; reg = <6>; @@ -618,6 +628,11 @@ access-controllers = <&etzpc 22>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; @@ -643,6 +658,11 @@ access-controllers = <&etzpc 23>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; @@ -668,6 +688,11 @@ access-controllers = <&etzpc 24>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; @@ -1116,6 +1141,11 @@ access-controllers = <&etzpc 54>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; @@ -1144,11 +1174,17 @@ access-controllers = <&etzpc 55>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; status = "disabled"; }; + timer@15 { compatible = "st,stm32h7-timer-trigger"; reg = <15>; @@ -1171,6 +1207,11 @@ access-controllers = <&etzpc 56>; status = "disabled"; + counter { + compatible = "st,stm32-timer-counter"; + status = "disabled"; + }; + pwm { compatible = "st,stm32-pwm"; #pwm-cells = <3>; diff --git a/arch/arm/boot/dts/st/stm32mp153c-lxa-tac-gen3.dts b/arch/arm/boot/dts/st/stm32mp153c-lxa-tac-gen3.dts new file mode 100644 index 000000000000..a40b0eae8da3 --- /dev/null +++ b/arch/arm/boot/dts/st/stm32mp153c-lxa-tac-gen3.dts @@ -0,0 +1,267 @@ +// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause) +/* + * Copyright (C) 2020 STMicroelectronics - All Rights Reserved + * Copyright (C) 2021 Rouven Czerwinski, Pengutronix + * Copyright (C) 2023, 2024 Leonard Göhrs, Pengutronix + */ + +/dts-v1/; + +#include "stm32mp153.dtsi" +#include "stm32mp15xc-lxa-tac.dtsi" + +/ { + model = "Linux Automation Test Automation Controller (TAC) Gen 3"; + compatible = "lxa,stm32mp153c-tac-gen3", "oct,stm32mp153x-osd32", "st,stm32mp153"; + + backlight: backlight { + compatible = "pwm-backlight"; + power-supply = <&v3v3>; + + brightness-levels = <0 31 63 95 127 159 191 223 255>; + default-brightness-level = <7>; + pwms = <&led_pwm 3 1000000 0>; + }; + + reg_iobus_12v: regulator-iobus-12v { + compatible = "regulator-fixed"; + vin-supply = <®_12v>; + gpio = <&gpioh 13 GPIO_ACTIVE_LOW>; + regulator-max-microvolt = <12000000>; + regulator-min-microvolt = <12000000>; + regulator-name = "12V_IOBUS"; + }; + + led-controller-1 { + compatible = "pwm-leds-multicolor"; + + multi-led { + color = ; + function = LED_FUNCTION_STATUS; + max-brightness = <65535>; + + led-red { + active-low; + color = ; + pwms = <&led_pwm 0 1000000 0>; + }; + + led-green { + active-low; + color = ; + pwms = <&led_pwm 2 1000000 0>; + }; + + led-blue { + active-low; + color = ; + pwms = <&led_pwm 1 1000000 0>; + }; + }; + }; + + led-controller-2 { + compatible = "gpio-leds"; + + led-5 { + label = "tac:green:iobus"; + gpios = <&gpiog 1 GPIO_ACTIVE_HIGH>; + }; + + led-6 { + label = "tac:green:can"; + gpios = <&gpiof 3 GPIO_ACTIVE_HIGH>; + }; + + led-7 { + label = "tac:green:out0"; + gpios = <&gpiob 8 GPIO_ACTIVE_HIGH>; + }; + + led-8 { + label = "tac:green:out1"; + gpios = <&gpiog 3 GPIO_ACTIVE_HIGH>; + }; + + led-9 { + label = "tac:green:uarttx"; + gpios = <&gpiod 3 GPIO_ACTIVE_HIGH>; + }; + + led-10 { + label = "tac:green:uartrx"; + gpios = <&gpiof 6 GPIO_ACTIVE_HIGH>; + }; + + led-11 { + label = "tac:green:usbh1"; + gpios = <&gpioc 8 GPIO_ACTIVE_HIGH>; + }; + + led-12 { + label = "tac:green:usbh2"; + gpios = <&gpiod 6 GPIO_ACTIVE_HIGH>; + }; + + led-13 { + label = "tac:green:usbh3"; + gpios = <&gpiob 9 GPIO_ACTIVE_HIGH>; + }; + + led-14 { + label = "tac:green:usbg"; + gpios = <&gpiod 14 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "usb-gadget"; + }; + + led-15 { + label = "tac:green:dutpwr"; + gpios = <&gpioa 15 GPIO_ACTIVE_HIGH>; + }; + }; +}; + +&adc { + pinctrl-names = "default"; + pinctrl-0 = <&board_adc1_ain_pins>; + vdd-supply = <&vdd>; + vdda-supply = <&vdda>; + vref-supply = <&vrefbuf>; + status = "okay"; + + adc1: adc@0 { + st,adc-channels = <2 5 9 10 13 14 15 18>; + st,min-sample-time-nsecs = <5000>; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + channel@2 { + reg = <2>; + label = "OUT_0_FB"; + }; + + channel@5 { + reg = <5>; + label = "IOBUS_CURR_FB"; + }; + + channel@9 { + reg = <9>; + label = "IOBUS_VOLT_FB"; + }; + + channel@10 { + reg = <10>; + label = "OUT_1_FB"; + }; + + channel@13 { + reg = <13>; + label = "HOST_CURR_FB"; + }; + + channel@14 { + reg = <14>; + label = "HOST_3_CURR_FB"; + }; + + channel@15 { + reg = <15>; + label = "HOST_1_CURR_FB"; + }; + + channel@18 { + reg = <18>; + label = "HOST_2_CURR_FB"; + }; + }; + + adc2: adc@100 { + st,adc-channels = <12>; + st,min-sample-time-nsecs = <500000>; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + channel@12 { + reg = <12>; + label = "TEMP_INTERNAL"; + }; + }; +}; + +&gpioa { + gpio-line-names = "", "", "", "", "", /* 0 */ + "ETH_GPIO1", "ETH_INT", "", "", "", /* 5 */ + "", "", "", "BOOTROM_LED", "ETH_LAB_LEDRP", /* 10 */ + ""; /* 15 */ +}; + +&gpioc { + gpio-line-names = "", "DUT_PWR_DISCH", "", "", "", /* 0 */ + "", "", "", "", "", /* 5 */ + "", ""; /* 10 */ +}; + +&gpioe { + gpio-line-names = "TP35", "", "", "", "CAN_1_120R", /* 0 */ + "", "", "USER_BTN2", "DUT_PWR_EN", "UART_TX_EN", /* 5 */ + "UART_RX_EN", "TP24", "", "TP25", "TP26", /* 10 */ + "TP27"; /* 15 */ +}; + +&gpiog { + gpio-line-names = "ETH_RESET", "", "", "", "", /* 0 */ + "IOBUS_FLT_FB", "", "USER_LED2", "ETH1_PPS_A", "CAN_0_120R", /* 5 */ + "POWER_ADC_RESET", "", "", "", "", /* 10 */ + ""; /* 15 */ +}; + +&m_can2 { + termination-gpios = <&gpioe 4 GPIO_ACTIVE_HIGH>; + termination-ohms = <120>; +}; + +&pinctrl { + board_adc1_ain_pins: board-adc1-ain-0 { + pins { + pinmux = , /* ADC1_INP2 */ + , /* ADC1_INP5 */ + , /* ADC1_INP9 */ + , /* ADC1_INP10 */ + , /* ADC1_INP13 */ + , /* ADC1_INP14 */ + , /* ADC1_INP15 */ + ; /* ADC1_INP18 */ + }; + }; +}; + +&spi2 { + adc@0 { + compatible = "ti,lmp92064"; + reg = <0>; + + reset-gpios = <&gpiog 10 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + shunt-resistor-micro-ohms = <15000>; + spi-max-frequency = <5000000>; + vdd-supply = <®_pb_3v3>; + vdig-supply = <®_pb_3v3>; + }; +}; + +&timers8 { + /* spare dmas for other usage */ + /delete-property/dmas; + /delete-property/dma-names; + + status = "okay"; + + led_pwm: pwm { + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&pwm8_pins_b>; + pinctrl-1 = <&pwm8_sleep_pins_b>; + status = "okay"; + }; +}; diff --git a/arch/arm/boot/dts/st/stm32mp157c-ev1.dts b/arch/arm/boot/dts/st/stm32mp157c-ev1.dts index 9eb9a1bf4f2c..8f99c30f1af1 100644 --- a/arch/arm/boot/dts/st/stm32mp157c-ev1.dts +++ b/arch/arm/boot/dts/st/stm32mp157c-ev1.dts @@ -306,6 +306,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { pinctrl-0 = <&pwm2_pins_a>; pinctrl-1 = <&pwm2_sleep_pins_a>; @@ -321,6 +324,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { pinctrl-0 = <&pwm8_pins_a>; pinctrl-1 = <&pwm8_sleep_pins_a>; @@ -336,6 +342,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { pinctrl-0 = <&pwm12_pins_a>; pinctrl-1 = <&pwm12_sleep_pins_a>; diff --git a/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen1.dts b/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen1.dts index 81f254fb88b0..e72e42eb0eb4 100644 --- a/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen1.dts +++ b/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen1.dts @@ -35,6 +35,76 @@ }; }; +&adc { + pinctrl-names = "default"; + pinctrl-0 = <&adc1_ain_pins_a>; + vdd-supply = <&vdd>; + vdda-supply = <&vdda>; + vref-supply = <&vrefbuf>; + status = "okay"; + + adc1: adc@0 { + st,adc-channels = <0 1 2 5 9 10 13 15>; + st,min-sample-time-nsecs = <5000>; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + channel@0 { + reg = <0>; + label = "HOST_2_CURR_FB"; + }; + + channel@1 { + reg = <1>; + label = "HOST_3_CURR_FB"; + }; + + channel@2 { + reg = <2>; + label = "OUT_0_FB"; + }; + + channel@5 { + reg = <5>; + label = "IOBUS_CURR_FB"; + }; + + channel@9 { + reg = <9>; + label = "IOBUS_VOLT_FB"; + }; + + channel@10 { + reg = <10>; + label = "OUT_1_FB"; + }; + + channel@13 { + reg = <13>; + label = "HOST_CURR_FB"; + }; + + channel@15 { + reg = <15>; + label = "HOST_1_CURR_FB"; + }; + }; + + adc2: adc@100 { + st,adc-channels = <12>; + st,min-sample-time-nsecs = <500000>; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + channel@12 { + reg = <12>; + label = "TEMP_INTERNAL"; + }; + }; +}; + &gpioa { gpio-line-names = "", "", "STACK_CS2", "", "STACK_CS3", /* 0 */ "ETH_GPIO1", "ETH_INT", "", "", "", /* 5 */ @@ -48,6 +118,20 @@ "", ""; /* 10 */ }; +&gpioe { + gpio-line-names = "TP35", "", "", "", "CAN_1_120R", /* 0 */ + "", "", "USER_BTN2", "TP48", "UART_TX_EN", /* 5 */ + "UART_RX_EN", "TP24", "", "TP25", "TP26", /* 10 */ + "TP27"; /* 15 */ +}; + +&gpiog { + gpio-line-names = "ETH_RESET", "", "", "", "", /* 0 */ + "IOBUS_FLT_FB", "", "USER_LED2", "ETH1_PPS_A", "CAN_0_120R", /* 5 */ + "TP49", "", "", "", "", /* 10 */ + ""; /* 15 */ +}; + &gpu { status = "disabled"; }; diff --git a/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen2.dts b/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen2.dts index 4cc177031661..2ae281725a48 100644 --- a/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen2.dts +++ b/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen2.dts @@ -121,6 +121,76 @@ }; }; +&adc { + pinctrl-names = "default"; + pinctrl-0 = <&adc1_ain_pins_a>; + vdd-supply = <&vdd>; + vdda-supply = <&vdda>; + vref-supply = <&vrefbuf>; + status = "okay"; + + adc1: adc@0 { + st,adc-channels = <0 1 2 5 9 10 13 15>; + st,min-sample-time-nsecs = <5000>; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + channel@0 { + reg = <0>; + label = "HOST_2_CURR_FB"; + }; + + channel@1 { + reg = <1>; + label = "HOST_3_CURR_FB"; + }; + + channel@2 { + reg = <2>; + label = "OUT_0_FB"; + }; + + channel@5 { + reg = <5>; + label = "IOBUS_CURR_FB"; + }; + + channel@9 { + reg = <9>; + label = "IOBUS_VOLT_FB"; + }; + + channel@10 { + reg = <10>; + label = "OUT_1_FB"; + }; + + channel@13 { + reg = <13>; + label = "HOST_CURR_FB"; + }; + + channel@15 { + reg = <15>; + label = "HOST_1_CURR_FB"; + }; + }; + + adc2: adc@100 { + st,adc-channels = <12>; + st,min-sample-time-nsecs = <500000>; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + channel@12 { + reg = <12>; + label = "TEMP_INTERNAL"; + }; + }; +}; + &gpioa { gpio-line-names = "", "", "DUT_PWR_EN", "", "STACK_CS3", /* 0 */ "ETH_GPIO1", "ETH_INT", "", "", "", /* 5 */ @@ -134,6 +204,20 @@ "", ""; /* 10 */ }; +&gpioe { + gpio-line-names = "TP35", "", "", "", "CAN_1_120R", /* 0 */ + "", "", "USER_BTN2", "TP48", "UART_TX_EN", /* 5 */ + "UART_RX_EN", "TP24", "", "TP25", "TP26", /* 10 */ + "TP27"; /* 15 */ +}; + +&gpiog { + gpio-line-names = "ETH_RESET", "", "", "", "", /* 0 */ + "IOBUS_FLT_FB", "", "USER_LED2", "ETH1_PPS_A", "CAN_0_120R", /* 5 */ + "TP49", "", "", "", "", /* 10 */ + ""; /* 15 */ +}; + &gpu { status = "disabled"; }; diff --git a/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi b/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi index c87fd96cbd91..be0c355d3105 100644 --- a/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi +++ b/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi @@ -16,12 +16,20 @@ / { aliases { + can0 = &m_can1; + can1 = &m_can2; ethernet0 = ðernet0; ethernet1 = &port_uplink; ethernet2 = &port_dut; + i2c0 = &i2c1; + i2c1 = &i2c4; + i2c2 = &i2c5; mmc1 = &sdmmc2; serial0 = &uart4; serial1 = &usart3; + spi0 = &spi2; + spi1 = &spi4; + spi2 = &spi5; }; chosen { @@ -142,76 +150,6 @@ baseboard_eeprom: &sip_eeprom { }; -&adc { - pinctrl-names = "default"; - pinctrl-0 = <&adc1_ain_pins_a>; - vdd-supply = <&vdd>; - vdda-supply = <&vdda>; - vref-supply = <&vrefbuf>; - status = "okay"; - - adc1: adc@0 { - st,adc-channels = <0 1 2 5 9 10 13 15>; - st,min-sample-time-nsecs = <5000>; - #address-cells = <1>; - #size-cells = <0>; - status = "okay"; - - channel@0 { - reg = <0>; - label = "HOST_2_CURR_FB"; - }; - - channel@1 { - reg = <1>; - label = "HOST_3_CURR_FB"; - }; - - channel@2 { - reg = <2>; - label = "OUT_0_FB"; - }; - - channel@5 { - reg = <5>; - label = "IOBUS_CURR_FB"; - }; - - channel@9 { - reg = <9>; - label = "IOBUS_VOLT_FB"; - }; - - channel@10 { - reg = <10>; - label = "OUT_1_FB"; - }; - - channel@13 { - reg = <13>; - label = "HOST_CURR_FB"; - }; - - channel@15 { - reg = <15>; - label = "HOST_1_CURR_FB"; - }; - }; - - adc2: adc@100 { - st,adc-channels = <12>; - st,min-sample-time-nsecs = <500000>; - #address-cells = <1>; - #size-cells = <0>; - status = "okay"; - - channel@12 { - reg = <12>; - label = "TEMP_INTERNAL"; - }; - }; -}; - &crc1 { status = "okay"; }; @@ -265,13 +203,6 @@ baseboard_eeprom: &sip_eeprom { "ETH_LAB_LEDRN"; /* 15 */ }; -&gpioe { - gpio-line-names = "TP35", "", "", "", "CAN_1_120R", /* 0 */ - "", "", "USER_BTN2", "TP48", "UART_TX_EN", /* 5 */ - "UART_RX_EN", "TP24", "", "TP25", "TP26", /* 10 */ - "TP27"; /* 15 */ -}; - &gpiof { gpio-line-names = "TP36", "TP37", "", "", "OLED_CS", /* 0 */ "", "", "", "", "", /* 5 */ @@ -279,13 +210,6 @@ baseboard_eeprom: &sip_eeprom { ""; /* 15 */ }; -&gpiog { - gpio-line-names = "ETH_RESET", "", "", "", "", /* 0 */ - "IOBUS_FLT_FB", "", "USER_LED2", "ETH1_PPS_A", "CAN_0_120R", /* 5 */ - "TP49", "", "", "", "", /* 10 */ - ""; /* 15 */ -}; - &gpioh { gpio-line-names = "", "", "OUT_1", "OUT_0", "OLED_RESET", /* 0 */ "", "", "", "", "", /* 5 */ @@ -379,10 +303,6 @@ baseboard_eeprom: &sip_eeprom { }; }; -&rtc { - status = "okay"; -}; - &sdmmc2 { pinctrl-names = "default", "opendrain", "sleep"; pinctrl-0 = <&sdmmc2_b4_pins_a &sdmmc2_d47_pins_b>; @@ -576,6 +496,10 @@ baseboard_eeprom: &sip_eeprom { vusb_d-supply = <&vdd_usb>; vusb_a-supply = <®18>; + g-rx-fifo-size = <512>; + g-np-tx-fifo-size = <32>; + g-tx-fifo-size = <128 128 64 16 16 16 16 16>; + dr_mode = "peripheral"; status = "okay"; diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-drc02.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-drc02.dtsi index bb4f8a0b937f..abe2dfe70636 100644 --- a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-drc02.dtsi +++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-drc02.dtsi @@ -6,18 +6,6 @@ #include #include -/ { - aliases { - serial0 = &uart4; - serial1 = &usart3; - serial2 = &uart8; - }; - - chosen { - stdout-path = "serial0:115200n8"; - }; -}; - &adc { status = "disabled"; }; diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-pdk2.dtsi index 171d7c7658fa..0fb4e55843b9 100644 --- a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-pdk2.dtsi @@ -7,16 +7,6 @@ #include / { - aliases { - serial0 = &uart4; - serial1 = &usart3; - serial2 = &uart8; - }; - - chosen { - stdout-path = "serial0:115200n8"; - }; - clk_ext_audio_codec: clock-codec { compatible = "fixed-clock"; #clock-cells = <0>; diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-picoitx.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-picoitx.dtsi index b5bc53accd6b..01c693cc0344 100644 --- a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-picoitx.dtsi +++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-picoitx.dtsi @@ -7,16 +7,6 @@ #include / { - aliases { - serial0 = &uart4; - serial1 = &usart3; - serial2 = &uart8; - }; - - chosen { - stdout-path = "serial0:115200n8"; - }; - led { compatible = "gpio-leds"; diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-som.dtsi index 74a11ccc5333..142d4a8731f8 100644 --- a/arch/arm/boot/dts/st/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/st/stm32mp15xx-dhcom-som.dtsi @@ -14,6 +14,13 @@ ethernet1 = &ksz8851; rtc0 = &hwrtc; rtc1 = &rtc; + serial0 = &uart4; + serial1 = &uart8; + serial2 = &usart3; + }; + + chosen { + stdout-path = "serial0:115200n8"; }; memory@c0000000 { diff --git a/arch/arm/boot/dts/st/stm32mp15xx-dkx.dtsi b/arch/arm/boot/dts/st/stm32mp15xx-dkx.dtsi index f7634c51efb2..a5511b1f0ce3 100644 --- a/arch/arm/boot/dts/st/stm32mp15xx-dkx.dtsi +++ b/arch/arm/boot/dts/st/stm32mp15xx-dkx.dtsi @@ -570,6 +570,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { pinctrl-0 = <&pwm1_pins_a>; pinctrl-1 = <&pwm1_sleep_pins_a>; @@ -585,6 +588,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { pinctrl-0 = <&pwm3_pins_a>; pinctrl-1 = <&pwm3_sleep_pins_a>; @@ -600,6 +606,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { pinctrl-0 = <&pwm4_pins_a &pwm4_pins_b>; pinctrl-1 = <&pwm4_sleep_pins_a &pwm4_sleep_pins_b>; @@ -615,6 +624,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { pinctrl-0 = <&pwm5_pins_a>; pinctrl-1 = <&pwm5_sleep_pins_a>; @@ -630,6 +642,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; timer@5 { status = "okay"; }; @@ -639,6 +654,9 @@ /delete-property/dmas; /delete-property/dma-names; status = "disabled"; + counter { + status = "okay"; + }; pwm { pinctrl-0 = <&pwm12_pins_a>; pinctrl-1 = <&pwm12_sleep_pins_a>; diff --git a/arch/arm/boot/dts/ti/omap/am437x-l4.dtsi b/arch/arm/boot/dts/ti/omap/am437x-l4.dtsi index 824b9415ebbe..fd4634f8c629 100644 --- a/arch/arm/boot/dts/ti/omap/am437x-l4.dtsi +++ b/arch/arm/boot/dts/ti/omap/am437x-l4.dtsi @@ -180,8 +180,7 @@ <0x9058 0x4>; reg-names = "rev", "sysc", "syss"; ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP | - SYSC_OMAP2_SOFTRESET | - SYSC_OMAP2_AUTOIDLE)>; + SYSC_OMAP2_SOFTRESET)>; ti,sysc-sidle = , , , @@ -698,8 +697,7 @@ <0x22058 0x4>; reg-names = "rev", "sysc", "syss"; ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP | - SYSC_OMAP2_SOFTRESET | - SYSC_OMAP2_AUTOIDLE)>; + SYSC_OMAP2_SOFTRESET)>; ti,sysc-sidle = , , , @@ -726,8 +724,7 @@ <0x24058 0x4>; reg-names = "rev", "sysc", "syss"; ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP | - SYSC_OMAP2_SOFTRESET | - SYSC_OMAP2_AUTOIDLE)>; + SYSC_OMAP2_SOFTRESET)>; ti,sysc-sidle = , , , @@ -1385,8 +1382,7 @@ <0xa6058 0x4>; reg-names = "rev", "sysc", "syss"; ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP | - SYSC_OMAP2_SOFTRESET | - SYSC_OMAP2_AUTOIDLE)>; + SYSC_OMAP2_SOFTRESET)>; ti,sysc-sidle = , , , @@ -1413,8 +1409,7 @@ <0xa8058 0x4>; reg-names = "rev", "sysc", "syss"; ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP | - SYSC_OMAP2_SOFTRESET | - SYSC_OMAP2_AUTOIDLE)>; + SYSC_OMAP2_SOFTRESET)>; ti,sysc-sidle = , , , @@ -1441,8 +1436,7 @@ <0xaa058 0x4>; reg-names = "rev", "sysc", "syss"; ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP | - SYSC_OMAP2_SOFTRESET | - SYSC_OMAP2_AUTOIDLE)>; + SYSC_OMAP2_SOFTRESET)>; ti,sysc-sidle = , , , diff --git a/arch/arm/boot/dts/ti/omap/dra7-l4.dtsi b/arch/arm/boot/dts/ti/omap/dra7-l4.dtsi index 6e67d99832ac..ba7fdaae9c6e 100644 --- a/arch/arm/boot/dts/ti/omap/dra7-l4.dtsi +++ b/arch/arm/boot/dts/ti/omap/dra7-l4.dtsi @@ -12,6 +12,7 @@ ranges = <0x00000000 0x4a000000 0x100000>, /* segment 0 */ <0x00100000 0x4a100000 0x100000>, /* segment 1 */ <0x00200000 0x4a200000 0x100000>; /* segment 2 */ + dma-ranges; segment@0 { /* 0x4a000000 */ compatible = "simple-pm-bus"; @@ -557,6 +558,7 @@ <0x0007e000 0x0017e000 0x001000>, /* ap 124 */ <0x00059000 0x00159000 0x001000>, /* ap 125 */ <0x0005a000 0x0015a000 0x001000>; /* ap 126 */ + dma-ranges; target-module@2000 { /* 0x4a102000, ap 27 3c.0 */ compatible = "ti,sysc"; diff --git a/arch/arm/boot/dts/ti/omap/omap3-gta04.dtsi b/arch/arm/boot/dts/ti/omap/omap3-gta04.dtsi index 2ee3ddd64020..1b18ed8c1f7a 100644 --- a/arch/arm/boot/dts/ti/omap/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/ti/omap/omap3-gta04.dtsi @@ -446,6 +446,7 @@ pinctrl-names = "default"; pinctrl-0 = < &hsusb2_2_pins + &mcspi3hog_pins >; hsusb2_2_pins: hsusb2-2-pins { @@ -459,6 +460,15 @@ >; }; + mcspi3hog_pins: mcspi3hog-pins { + pinctrl-single,pins = < + OMAP3630_CORE2_IOPAD(0x25dc, PIN_OUTPUT_PULLDOWN | MUX_MODE4) /* etk_d0 */ + OMAP3630_CORE2_IOPAD(0x25de, PIN_OUTPUT_PULLDOWN | MUX_MODE4) /* etk_d1 */ + OMAP3630_CORE2_IOPAD(0x25e0, PIN_OUTPUT_PULLDOWN | MUX_MODE4) /* etk_d2 */ + OMAP3630_CORE2_IOPAD(0x25e2, PIN_OUTPUT_PULLDOWN | MUX_MODE4) /* etk_d3 */ + >; + }; + spi_gpio_pins: spi-gpio-pinmux-pins { pinctrl-single,pins = < OMAP3630_CORE2_IOPAD(0x25d8, PIN_OUTPUT | MUX_MODE4) /* clk */ @@ -591,8 +601,10 @@ interrupts = <0 IRQ_TYPE_EDGE_FALLING>; /* GPIO_160 */ gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* GPIO_160 */ ti,x-plate-ohms = <600>; - touchscreen-size-x = <480>; - touchscreen-size-y = <640>; + touchscreen-size-x = <0xf00>; + touchscreen-size-y = <0xf00>; + touchscreen-min-x = <0x100>; + touchscreen-min-y = <0x100>; touchscreen-max-pressure = <1000>; touchscreen-fuzz-x = <3>; touchscreen-fuzz-y = <8>; diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c index 9a9aa53547a6..d1e82a318e3b 100644 --- a/arch/arm/common/bL_switcher.c +++ b/arch/arm/common/bL_switcher.c @@ -307,13 +307,11 @@ static struct task_struct *bL_switcher_thread_create(int cpu, void *arg) { struct task_struct *task; - task = kthread_create_on_node(bL_switcher_thread, arg, - cpu_to_node(cpu), "kswitcher_%d", cpu); - if (!IS_ERR(task)) { - kthread_bind(task, cpu); - wake_up_process(task); - } else + task = kthread_run_on_cpu(bL_switcher_thread, arg, + cpu, "kswitcher_%d"); + if (IS_ERR(task)) pr_err("%s failed for CPU %d\n", __func__, cpu); + return task; } diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0beecdde55f5..87841e5cafe2 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -230,6 +230,7 @@ CONFIG_RN5T618_POWER=m CONFIG_SENSORS_MC13783_ADC=y CONFIG_SENSORS_GPIO_FAN=y CONFIG_SENSORS_IIO_HWMON=y +CONFIG_SENSORS_JC42=m CONFIG_SENSORS_LM75=m CONFIG_SENSORS_PWM_FAN=y CONFIG_SENSORS_SY7636A=y @@ -323,6 +324,7 @@ CONFIG_SND_SOC_IMX_SGTL5000=y CONFIG_SND_SOC_FSL_ASOC_CARD=y CONFIG_SND_SOC_AC97_CODEC=y CONFIG_SND_SOC_CS42XX8_I2C=y +CONFIG_SND_SOC_SPDIF=y CONFIG_SND_SOC_TLV320AIC3X_I2C=y CONFIG_SND_SOC_WM8960=y CONFIG_SND_SOC_WM8962=y diff --git a/arch/arm/configs/milbeaut_m10v_defconfig b/arch/arm/configs/milbeaut_m10v_defconfig index f5eeac9c65c3..acd16204f8d7 100644 --- a/arch/arm/configs/milbeaut_m10v_defconfig +++ b/arch/arm/configs/milbeaut_m10v_defconfig @@ -107,7 +107,6 @@ CONFIG_CRYPTO_AES_ARM=m CONFIG_CRYPTO_AES_ARM_BS=m CONFIG_CRYPTO_AES_ARM_CE=m CONFIG_CRYPTO_CHACHA20_NEON=m -CONFIG_CRYPTO_CRC32_ARM_CE=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC_CCITT=m CONFIG_CRC_ITU_T=m diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 758276027dbc..37e3baa33b67 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -20,6 +20,7 @@ CONFIG_ARCH_AT91=y CONFIG_SOC_SAMA5D2=y CONFIG_SOC_SAMA5D3=y CONFIG_SOC_SAMA5D4=y +CONFIG_SOC_SAMA7D65=y CONFIG_SOC_SAMA7G5=y CONFIG_SOC_LAN966=y CONFIG_ARCH_BCM=y @@ -1306,7 +1307,6 @@ CONFIG_CRYPTO_AES_ARM=m CONFIG_CRYPTO_AES_ARM_BS=m CONFIG_CRYPTO_AES_ARM_CE=m CONFIG_CRYPTO_CHACHA20_NEON=m -CONFIG_CRYPTO_CRC32_ARM_CE=m CONFIG_CRYPTO_DEV_SUN4I_SS=m CONFIG_CRYPTO_DEV_FSL_CAAM=m CONFIG_CRYPTO_DEV_EXYNOS_RNG=m diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 3a166c2f02bd..6de45d7f6078 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -428,6 +428,7 @@ CONFIG_POWER_RESET_GPIO=y CONFIG_BATTERY_BQ27XXX=m CONFIG_CHARGER_ISP1704=m CONFIG_CHARGER_TWL4030=m +CONFIG_CHARGER_TWL6030=m CONFIG_CHARGER_BQ2415X=m CONFIG_CHARGER_BQ24190=m CONFIG_CHARGER_BQ24735=m diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index 38916ac4bce4..de0ac8f521d7 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -652,7 +652,6 @@ CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_SHA512=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig index 1a2e93c8ee71..ea7ddf640ba7 100644 --- a/arch/arm/configs/sama7_defconfig +++ b/arch/arm/configs/sama7_defconfig @@ -12,6 +12,7 @@ CONFIG_EXPERT=y # CONFIG_IO_URING is not set CONFIG_KALLSYMS_ALL=y CONFIG_ARCH_AT91=y +CONFIG_SOC_SAMA7D65=y CONFIG_SOC_SAMA7G5=y CONFIG_ATMEL_CLOCKSOURCE_TCB=y # CONFIG_CACHE_L2X0 is not set diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig index 0e380e450a62..fd28f3176c6b 100644 --- a/arch/arm/configs/shmobile_defconfig +++ b/arch/arm/configs/shmobile_defconfig @@ -192,6 +192,7 @@ CONFIG_DW_DMAC=y CONFIG_RZN1_DMAMUX=y CONFIG_RCAR_DMAC=y CONFIG_RENESAS_USB_DMAC=y +CONFIG_RZ_DMAC=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_ARCH_EMEV2=y CONFIG_ARCH_R8A7794=y diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig index 3baec075d1ef..77048b5e1ec4 100644 --- a/arch/arm/configs/stm32_defconfig +++ b/arch/arm/configs/stm32_defconfig @@ -6,23 +6,25 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_EXPERT=y # CONFIG_UID16 is not set +# CONFIG_POSIX_TIMERS is not set CONFIG_BASE_SMALL=y # CONFIG_FUTEX is not set # CONFIG_EPOLL is not set # CONFIG_SIGNALFD is not set # CONFIG_EVENTFD is not set # CONFIG_AIO is not set -# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IO_URING is not set +# CONFIG_ADVISE_SYSCALLS is not set # CONFIG_MMU is not set CONFIG_ARCH_STM32=y CONFIG_CPU_V7M_NUM_IRQ=240 CONFIG_SET_MEM_PARAM=y CONFIG_DRAM_BASE=0x90000000 -CONFIG_FLASH_MEM_BASE=0x08000000 -CONFIG_FLASH_SIZE=0x00200000 # CONFIG_ATAGS is not set CONFIG_XIP_KERNEL=y CONFIG_XIP_PHYS_ADDR=0x08008000 +# CONFIG_SUSPEND is not set +# CONFIG_GCC_PLUGINS is not set CONFIG_BINFMT_FLAT=y # CONFIG_COREDUMP is not set # CONFIG_VM_EVENT_COUNTERS is not set @@ -63,6 +65,7 @@ CONFIG_DMADEVICES=y CONFIG_STM32_DMA=y CONFIG_STM32_DMAMUX=y CONFIG_STM32_MDMA=y +# CONFIG_COMMON_CLK_STM32MP is not set CONFIG_IIO=y CONFIG_STM32_ADC_CORE=y CONFIG_STM32_ADC=y @@ -74,10 +77,7 @@ CONFIG_NLS=y CONFIG_CRC_ITU_T=y CONFIG_CRC7=y CONFIG_PRINTK_TIME=y -# CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_DEBUG_BUGVERBOSE is not set CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y # CONFIG_SLUB_DEBUG is not set -# CONFIG_SCHED_DEBUG is not set -CONFIG_CRYPTO=y diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig index 5ff49a5e9afc..32650c8431d9 100644 --- a/arch/arm/crypto/Kconfig +++ b/arch/arm/crypto/Kconfig @@ -222,30 +222,5 @@ config CRYPTO_CHACHA20_NEON Architecture: arm using: - NEON (Advanced SIMD) extensions -config CRYPTO_CRC32_ARM_CE - tristate "CRC32C and CRC32" - depends on KERNEL_MODE_NEON - depends on CRC32 - select CRYPTO_HASH - help - CRC32c CRC algorithm with the iSCSI polynomial (RFC 3385 and RFC 3720) - and CRC32 CRC algorithm (IEEE 802.3) - - Architecture: arm using: - - CRC and/or PMULL instructions - - Drivers: crc32-arm-ce and crc32c-arm-ce - -config CRYPTO_CRCT10DIF_ARM_CE - tristate "CRCT10DIF" - depends on KERNEL_MODE_NEON - depends on CRC_T10DIF - select CRYPTO_HASH - help - CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF) - - Architecture: arm using: - - PMULL (Polynomial Multiply Long) instructions - endmenu diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile index 13e62c7c25dc..3d0e23ff9e74 100644 --- a/arch/arm/crypto/Makefile +++ b/arch/arm/crypto/Makefile @@ -20,8 +20,6 @@ obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o -obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM_CE) += crct10dif-arm-ce.o -obj-$(CONFIG_CRYPTO_CRC32_ARM_CE) += crc32-arm-ce.o aes-arm-y := aes-cipher-core.o aes-cipher-glue.o aes-arm-bs-y := aes-neonbs-core.o aes-neonbs-glue.o @@ -37,8 +35,6 @@ sha1-arm-ce-y := sha1-ce-core.o sha1-ce-glue.o sha2-arm-ce-y := sha2-ce-core.o sha2-ce-glue.o aes-arm-ce-y := aes-ce-core.o aes-ce-glue.o ghash-arm-ce-y := ghash-ce-core.o ghash-ce-glue.o -crct10dif-arm-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o -crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o chacha-neon-y := chacha-scalar-core.o chacha-glue.o chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o poly1305-arm-y := poly1305-core.o poly1305-glue.o diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c deleted file mode 100644 index 20b4dff13e3a..000000000000 --- a/arch/arm/crypto/crc32-ce-glue.c +++ /dev/null @@ -1,247 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions instructions - * - * Copyright (C) 2016 Linaro Ltd - */ - -#include -#include -#include -#include -#include -#include - -#include -#include - -#include -#include -#include -#include - -#define PMULL_MIN_LEN 64L /* minimum size of buffer - * for crc32_pmull_le_16 */ -#define SCALE_F 16L /* size of NEON register */ - -asmlinkage u32 crc32_pmull_le(const u8 buf[], u32 len, u32 init_crc); -asmlinkage u32 crc32_armv8_le(u32 init_crc, const u8 buf[], u32 len); - -asmlinkage u32 crc32c_pmull_le(const u8 buf[], u32 len, u32 init_crc); -asmlinkage u32 crc32c_armv8_le(u32 init_crc, const u8 buf[], u32 len); - -static u32 (*fallback_crc32)(u32 init_crc, const u8 buf[], u32 len); -static u32 (*fallback_crc32c)(u32 init_crc, const u8 buf[], u32 len); - -static int crc32_cra_init(struct crypto_tfm *tfm) -{ - u32 *key = crypto_tfm_ctx(tfm); - - *key = 0; - return 0; -} - -static int crc32c_cra_init(struct crypto_tfm *tfm) -{ - u32 *key = crypto_tfm_ctx(tfm); - - *key = ~0; - return 0; -} - -static int crc32_setkey(struct crypto_shash *hash, const u8 *key, - unsigned int keylen) -{ - u32 *mctx = crypto_shash_ctx(hash); - - if (keylen != sizeof(u32)) - return -EINVAL; - *mctx = le32_to_cpup((__le32 *)key); - return 0; -} - -static int crc32_init(struct shash_desc *desc) -{ - u32 *mctx = crypto_shash_ctx(desc->tfm); - u32 *crc = shash_desc_ctx(desc); - - *crc = *mctx; - return 0; -} - -static int crc32_update(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - u32 *crc = shash_desc_ctx(desc); - - *crc = crc32_armv8_le(*crc, data, length); - return 0; -} - -static int crc32c_update(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - u32 *crc = shash_desc_ctx(desc); - - *crc = crc32c_armv8_le(*crc, data, length); - return 0; -} - -static int crc32_final(struct shash_desc *desc, u8 *out) -{ - u32 *crc = shash_desc_ctx(desc); - - put_unaligned_le32(*crc, out); - return 0; -} - -static int crc32c_final(struct shash_desc *desc, u8 *out) -{ - u32 *crc = shash_desc_ctx(desc); - - put_unaligned_le32(~*crc, out); - return 0; -} - -static int crc32_pmull_update(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - u32 *crc = shash_desc_ctx(desc); - unsigned int l; - - if (crypto_simd_usable()) { - if ((u32)data % SCALE_F) { - l = min_t(u32, length, SCALE_F - ((u32)data % SCALE_F)); - - *crc = fallback_crc32(*crc, data, l); - - data += l; - length -= l; - } - - if (length >= PMULL_MIN_LEN) { - l = round_down(length, SCALE_F); - - kernel_neon_begin(); - *crc = crc32_pmull_le(data, l, *crc); - kernel_neon_end(); - - data += l; - length -= l; - } - } - - if (length > 0) - *crc = fallback_crc32(*crc, data, length); - - return 0; -} - -static int crc32c_pmull_update(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - u32 *crc = shash_desc_ctx(desc); - unsigned int l; - - if (crypto_simd_usable()) { - if ((u32)data % SCALE_F) { - l = min_t(u32, length, SCALE_F - ((u32)data % SCALE_F)); - - *crc = fallback_crc32c(*crc, data, l); - - data += l; - length -= l; - } - - if (length >= PMULL_MIN_LEN) { - l = round_down(length, SCALE_F); - - kernel_neon_begin(); - *crc = crc32c_pmull_le(data, l, *crc); - kernel_neon_end(); - - data += l; - length -= l; - } - } - - if (length > 0) - *crc = fallback_crc32c(*crc, data, length); - - return 0; -} - -static struct shash_alg crc32_pmull_algs[] = { { - .setkey = crc32_setkey, - .init = crc32_init, - .update = crc32_update, - .final = crc32_final, - .descsize = sizeof(u32), - .digestsize = sizeof(u32), - - .base.cra_ctxsize = sizeof(u32), - .base.cra_init = crc32_cra_init, - .base.cra_name = "crc32", - .base.cra_driver_name = "crc32-arm-ce", - .base.cra_priority = 200, - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_blocksize = 1, - .base.cra_module = THIS_MODULE, -}, { - .setkey = crc32_setkey, - .init = crc32_init, - .update = crc32c_update, - .final = crc32c_final, - .descsize = sizeof(u32), - .digestsize = sizeof(u32), - - .base.cra_ctxsize = sizeof(u32), - .base.cra_init = crc32c_cra_init, - .base.cra_name = "crc32c", - .base.cra_driver_name = "crc32c-arm-ce", - .base.cra_priority = 200, - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_blocksize = 1, - .base.cra_module = THIS_MODULE, -} }; - -static int __init crc32_pmull_mod_init(void) -{ - if (elf_hwcap2 & HWCAP2_PMULL) { - crc32_pmull_algs[0].update = crc32_pmull_update; - crc32_pmull_algs[1].update = crc32c_pmull_update; - - if (elf_hwcap2 & HWCAP2_CRC32) { - fallback_crc32 = crc32_armv8_le; - fallback_crc32c = crc32c_armv8_le; - } else { - fallback_crc32 = crc32_le; - fallback_crc32c = __crc32c_le; - } - } else if (!(elf_hwcap2 & HWCAP2_CRC32)) { - return -ENODEV; - } - - return crypto_register_shashes(crc32_pmull_algs, - ARRAY_SIZE(crc32_pmull_algs)); -} - -static void __exit crc32_pmull_mod_exit(void) -{ - crypto_unregister_shashes(crc32_pmull_algs, - ARRAY_SIZE(crc32_pmull_algs)); -} - -static const struct cpu_feature __maybe_unused crc32_cpu_feature[] = { - { cpu_feature(CRC32) }, { cpu_feature(PMULL) }, { } -}; -MODULE_DEVICE_TABLE(cpu, crc32_cpu_feature); - -module_init(crc32_pmull_mod_init); -module_exit(crc32_pmull_mod_exit); - -MODULE_AUTHOR("Ard Biesheuvel "); -MODULE_DESCRIPTION("Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_CRYPTO("crc32"); -MODULE_ALIAS_CRYPTO("crc32c"); diff --git a/arch/arm/crypto/crct10dif-ce-glue.c b/arch/arm/crypto/crct10dif-ce-glue.c deleted file mode 100644 index a8b74523729e..000000000000 --- a/arch/arm/crypto/crct10dif-ce-glue.c +++ /dev/null @@ -1,124 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions instructions - * - * Copyright (C) 2016 Linaro Ltd - */ - -#include -#include -#include -#include -#include - -#include -#include - -#include -#include - -#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U - -asmlinkage u16 crc_t10dif_pmull64(u16 init_crc, const u8 *buf, size_t len); -asmlinkage void crc_t10dif_pmull8(u16 init_crc, const u8 *buf, size_t len, - u8 out[16]); - -static int crct10dif_init(struct shash_desc *desc) -{ - u16 *crc = shash_desc_ctx(desc); - - *crc = 0; - return 0; -} - -static int crct10dif_update_ce(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - u16 *crc = shash_desc_ctx(desc); - - if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) { - kernel_neon_begin(); - *crc = crc_t10dif_pmull64(*crc, data, length); - kernel_neon_end(); - } else { - *crc = crc_t10dif_generic(*crc, data, length); - } - - return 0; -} - -static int crct10dif_update_neon(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - u16 *crcp = shash_desc_ctx(desc); - u8 buf[16] __aligned(16); - u16 crc = *crcp; - - if (length > CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) { - kernel_neon_begin(); - crc_t10dif_pmull8(crc, data, length, buf); - kernel_neon_end(); - - crc = 0; - data = buf; - length = sizeof(buf); - } - - *crcp = crc_t10dif_generic(crc, data, length); - return 0; -} - -static int crct10dif_final(struct shash_desc *desc, u8 *out) -{ - u16 *crc = shash_desc_ctx(desc); - - *(u16 *)out = *crc; - return 0; -} - -static struct shash_alg algs[] = {{ - .digestsize = CRC_T10DIF_DIGEST_SIZE, - .init = crct10dif_init, - .update = crct10dif_update_neon, - .final = crct10dif_final, - .descsize = CRC_T10DIF_DIGEST_SIZE, - - .base.cra_name = "crct10dif", - .base.cra_driver_name = "crct10dif-arm-neon", - .base.cra_priority = 150, - .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE, - .base.cra_module = THIS_MODULE, -}, { - .digestsize = CRC_T10DIF_DIGEST_SIZE, - .init = crct10dif_init, - .update = crct10dif_update_ce, - .final = crct10dif_final, - .descsize = CRC_T10DIF_DIGEST_SIZE, - - .base.cra_name = "crct10dif", - .base.cra_driver_name = "crct10dif-arm-ce", - .base.cra_priority = 200, - .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE, - .base.cra_module = THIS_MODULE, -}}; - -static int __init crc_t10dif_mod_init(void) -{ - if (!(elf_hwcap & HWCAP_NEON)) - return -ENODEV; - - return crypto_register_shashes(algs, 1 + !!(elf_hwcap2 & HWCAP2_PMULL)); -} - -static void __exit crc_t10dif_mod_exit(void) -{ - crypto_unregister_shashes(algs, 1 + !!(elf_hwcap2 & HWCAP2_PMULL)); -} - -module_init(crc_t10dif_mod_init); -module_exit(crc_t10dif_mod_exit); - -MODULE_AUTHOR("Ard Biesheuvel "); -MODULE_DESCRIPTION("Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_CRYPTO("crct10dif"); diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h index e3ea34558ada..ecbc100d22a5 100644 --- a/arch/arm/include/asm/cache.h +++ b/arch/arm/include/asm/cache.h @@ -26,4 +26,10 @@ #define __read_mostly __section(".data..read_mostly") +#ifndef __ASSEMBLY__ +#ifdef CONFIG_ARCH_HAS_CACHE_LINE_SIZE +int cache_line_size(void); +#endif +#endif + #endif diff --git a/arch/arm/include/asm/cachetype.h b/arch/arm/include/asm/cachetype.h index b9dbe1d4c8fe..b01c59076b84 100644 --- a/arch/arm/include/asm/cachetype.h +++ b/arch/arm/include/asm/cachetype.h @@ -83,6 +83,14 @@ static inline unsigned int read_ccsidr(void) asm volatile("mrc p15, 1, %0, c0, c0, 0" : "=r" (val)); return val; } + +static inline unsigned int read_clidr(void) +{ + unsigned int val; + + asm volatile("mrc p15, 1, %0, c0, c0, 1" : "=r" (val)); + return val; +} #else /* CONFIG_CPU_V7M */ #include #include "asm/v7m.h" @@ -96,6 +104,11 @@ static inline unsigned int read_ccsidr(void) { return readl(BASEADDR_V7M_SCB + V7M_SCB_CCSIDR); } + +static inline unsigned int read_clidr(void) +{ + return readl(BASEADDR_V7M_SCB + V7M_SCB_CLIDR); +} #endif #endif diff --git a/arch/arm/include/asm/ecard.h b/arch/arm/include/asm/ecard.h index 4befe8d2ae19..7cbe001bf9cc 100644 --- a/arch/arm/include/asm/ecard.h +++ b/arch/arm/include/asm/ecard.h @@ -195,7 +195,7 @@ void __iomem *ecardm_iomap(struct expansion_card *ec, unsigned int res, unsigned long offset, unsigned long maxsize); #define ecardm_iounmap(__ec, __addr) devm_iounmap(&(__ec)->dev, __addr) -extern struct bus_type ecard_bus_type; +extern const struct bus_type ecard_bus_type; #define ECARD_DEV(_d) container_of((_d), struct expansion_card, dev) diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index f40d06ad5d2a..ea4fbe7b17f6 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -26,14 +26,7 @@ #else /* !CONFIG_MMU */ -#include #include - -static inline void __tlb_remove_table(void *_table) -{ - free_page_and_swap_cache((struct page *)_table); -} - #include static inline void @@ -41,8 +34,6 @@ __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { struct ptdesc *ptdesc = page_ptdesc(pte); - pagetable_pte_dtor(ptdesc); - #ifndef CONFIG_ARM_LPAE /* * With the classic ARM MMU, a pte page has two corresponding pmd @@ -61,7 +52,6 @@ __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) #ifdef CONFIG_ARM_LPAE struct ptdesc *ptdesc = virt_to_ptdesc(pmdp); - pagetable_pmd_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); #endif } diff --git a/arch/arm/include/asm/vfp.h b/arch/arm/include/asm/vfp.h index 157ea3426158..85ccc422d4d0 100644 --- a/arch/arm/include/asm/vfp.h +++ b/arch/arm/include/asm/vfp.h @@ -9,16 +9,6 @@ #ifndef __ASM_VFP_H #define __ASM_VFP_H -#ifndef CONFIG_AS_VFP_VMRS_FPINST -#define FPSID cr0 -#define FPSCR cr1 -#define MVFR1 cr6 -#define MVFR0 cr7 -#define FPEXC cr8 -#define FPINST cr9 -#define FPINST2 cr10 -#endif - /* FPSID bits */ #define FPSID_IMPLEMENTER_BIT (24) #define FPSID_IMPLEMENTER_MASK (0xff << FPSID_IMPLEMENTER_BIT) diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h index ba0d4cb5377e..e2e1d5a3727a 100644 --- a/arch/arm/include/asm/vfpmacros.h +++ b/arch/arm/include/asm/vfpmacros.h @@ -8,7 +8,6 @@ #include -#ifdef CONFIG_AS_VFP_VMRS_FPINST .macro VFPFMRX, rd, sysreg, cond vmrs\cond \rd, \sysreg .endm @@ -16,16 +15,6 @@ .macro VFPFMXR, sysreg, rd, cond vmsr\cond \sysreg, \rd .endm -#else - @ Macros to allow building with old toolkits (with no VFP support) - .macro VFPFMRX, rd, sysreg, cond - MRC\cond p10, 7, \rd, \sysreg, cr0, 0 @ FMRX \rd, \sysreg - .endm - - .macro VFPFMXR, sysreg, rd, cond - MCR\cond p10, 7, \rd, \sysreg, cr0, 0 @ FMXR \sysreg, \rd - .endm -#endif @ read all the working registers back into the VFP .macro VFPFLDMIA, base, tmp diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index aaae31b8c4a5..b3333d070390 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -40,6 +40,7 @@ obj-y += entry-armv.o endif obj-$(CONFIG_MMU) += bugs.o +obj-$(CONFIG_OF) += cacheinfo.o obj-$(CONFIG_CPU_IDLE) += cpuidle.o obj-$(CONFIG_ISA_DMA_API) += dma.o obj-$(CONFIG_FIQ) += fiq.o fiqasm.o diff --git a/arch/arm/kernel/cacheinfo.c b/arch/arm/kernel/cacheinfo.c new file mode 100644 index 000000000000..e1469b641780 --- /dev/null +++ b/arch/arm/kernel/cacheinfo.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ARM cacheinfo support + * + * Copyright (C) 2023 Linaro Ltd. + * Copyright (C) 2015 ARM Ltd. + * All Rights Reserved + */ + +#include +#include +#include + +#include +#include +#include + +/* Ctypen, bits[3(n - 1) + 2 : 3(n - 1)], for n = 1 to 7 */ +#define CLIDR_CTYPE_SHIFT(level) (3 * (level - 1)) +#define CLIDR_CTYPE_MASK(level) (7 << CLIDR_CTYPE_SHIFT(level)) +#define CLIDR_CTYPE(clidr, level) \ + (((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level)) + +#define MAX_CACHE_LEVEL 7 /* Max 7 level supported */ + +#define CTR_FORMAT_MASK GENMASK(31, 29) +#define CTR_FORMAT_ARMV6 0 +#define CTR_FORMAT_ARMV7 4 +#define CTR_CWG_MASK GENMASK(27, 24) +#define CTR_DSIZE_LEN_MASK GENMASK(13, 12) +#define CTR_ISIZE_LEN_MASK GENMASK(1, 0) + +/* Also valid for v7m */ +static inline int cache_line_size_cp15(void) +{ + u32 ctr = read_cpuid_cachetype(); + u32 format = FIELD_GET(CTR_FORMAT_MASK, ctr); + + if (format == CTR_FORMAT_ARMV7) { + u32 cwg = FIELD_GET(CTR_CWG_MASK, ctr); + + return cwg ? 4 << cwg : ARCH_DMA_MINALIGN; + } else if (WARN_ON_ONCE(format != CTR_FORMAT_ARMV6)) { + return ARCH_DMA_MINALIGN; + } + + return 8 << max(FIELD_GET(CTR_ISIZE_LEN_MASK, ctr), + FIELD_GET(CTR_DSIZE_LEN_MASK, ctr)); +} + +int cache_line_size(void) +{ + if (coherency_max_size != 0) + return coherency_max_size; + + /* CP15 is optional / implementation defined before ARMv6 */ + if (cpu_architecture() < CPU_ARCH_ARMv6) + return ARCH_DMA_MINALIGN; + + return cache_line_size_cp15(); +} +EXPORT_SYMBOL_GPL(cache_line_size); + +static inline enum cache_type get_cache_type(int level) +{ + u32 clidr; + + if (level > MAX_CACHE_LEVEL) + return CACHE_TYPE_NOCACHE; + + clidr = read_clidr(); + + return CLIDR_CTYPE(clidr, level); +} + +static void ci_leaf_init(struct cacheinfo *this_leaf, + enum cache_type type, unsigned int level) +{ + this_leaf->level = level; + this_leaf->type = type; +} + +static int detect_cache_level(unsigned int *level_p, unsigned int *leaves_p) +{ + unsigned int ctype, level, leaves; + u32 ctr, format; + + /* CLIDR is not present before ARMv7/v7m */ + if (cpu_architecture() < CPU_ARCH_ARMv7) + return -EOPNOTSUPP; + + /* Don't try reading CLIDR if CTR declares old format */ + ctr = read_cpuid_cachetype(); + format = FIELD_GET(CTR_FORMAT_MASK, ctr); + if (format != CTR_FORMAT_ARMV7) + return -EOPNOTSUPP; + + for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) { + ctype = get_cache_type(level); + if (ctype == CACHE_TYPE_NOCACHE) { + level--; + break; + } + /* Separate instruction and data caches */ + leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1; + } + + *level_p = level; + *leaves_p = leaves; + + return 0; +} + +int early_cache_level(unsigned int cpu) +{ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + + return detect_cache_level(&this_cpu_ci->num_levels, &this_cpu_ci->num_leaves); +} + +int init_cache_level(unsigned int cpu) +{ + unsigned int level, leaves; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + int fw_level; + int ret; + + ret = detect_cache_level(&level, &leaves); + if (ret) + return ret; + + fw_level = of_find_last_cache_level(cpu); + + if (level < fw_level) { + /* + * some external caches not specified in CLIDR_EL1 + * the information may be available in the device tree + * only unified external caches are considered here + */ + leaves += (fw_level - level); + level = fw_level; + } + + this_cpu_ci->num_levels = level; + this_cpu_ci->num_leaves = leaves; + return 0; +} + +int populate_cache_leaves(unsigned int cpu) +{ + unsigned int level, idx; + enum cache_type type; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cacheinfo *this_leaf = this_cpu_ci->info_list; + unsigned int arch = cpu_architecture(); + + /* CLIDR is not present before ARMv7/v7m */ + if (arch < CPU_ARCH_ARMv7) + return -EOPNOTSUPP; + + for (idx = 0, level = 1; level <= this_cpu_ci->num_levels && + idx < this_cpu_ci->num_leaves; idx++, level++) { + type = get_cache_type(level); + if (type == CACHE_TYPE_SEPARATE) { + ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level); + ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level); + } else { + ci_leaf_init(this_leaf++, type, level); + } + } + + return 0; +} diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c index 905b1b191546..db8be609fab2 100644 --- a/arch/arm/kernel/isa.c +++ b/arch/arm/kernel/isa.c @@ -16,7 +16,7 @@ static unsigned int isa_membase, isa_portbase, isa_portshift; -static struct ctl_table ctl_isa_vars[] = { +static const struct ctl_table ctl_isa_vars[] = { { .procname = "membase", .data = &isa_membase, diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 80ceb5bd2680..dd430477e7c1 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -127,29 +127,6 @@ void crash_smp_send_stop(void) cpus_stopped = 1; } -static void machine_kexec_mask_interrupts(void) -{ - unsigned int i; - struct irq_desc *desc; - - for_each_irq_desc(i, desc) { - struct irq_chip *chip; - - chip = irq_desc_get_chip(desc); - if (!chip) - continue; - - if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) - chip->irq_eoi(&desc->irq_data); - - if (chip->irq_mask) - chip->irq_mask(&desc->irq_data); - - if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) - chip->irq_disable(&desc->irq_data); - } -} - void machine_crash_shutdown(struct pt_regs *regs) { local_irq_disable(); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index e6a857bf0ce6..a41c93988d2c 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -880,10 +880,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) */ boot_alias_start = phys_to_idmap(start); if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) { - res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", - __func__, sizeof(*res)); + res = memblock_alloc_or_panic(sizeof(*res), SMP_CACHE_BYTES); res->name = "System RAM (boot alias)"; res->start = boot_alias_start; res->end = phys_to_idmap(res_end); @@ -891,10 +888,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) request_resource(&iomem_resource, res); } - res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*res)); + res = memblock_alloc_or_panic(sizeof(*res), SMP_CACHE_BYTES); res->name = "System RAM"; res->start = start; res->end = res_end; diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index 0ca5aae1bcc3..007874320937 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -45,3 +45,9 @@ ifeq ($(CONFIG_KERNEL_MODE_NEON),y) endif obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o + +obj-$(CONFIG_CRC32_ARCH) += crc32-arm.o +crc32-arm-y := crc32-glue.o crc32-core.o + +obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-arm.o +crc-t10dif-arm-y := crc-t10dif-glue.o crc-t10dif-core.o diff --git a/arch/arm/crypto/crct10dif-ce-core.S b/arch/arm/lib/crc-t10dif-core.S similarity index 100% rename from arch/arm/crypto/crct10dif-ce-core.S rename to arch/arm/lib/crc-t10dif-core.S diff --git a/arch/arm/lib/crc-t10dif-glue.c b/arch/arm/lib/crc-t10dif-glue.c new file mode 100644 index 000000000000..d24dee62670e --- /dev/null +++ b/arch/arm/lib/crc-t10dif-glue.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions instructions + * + * Copyright (C) 2016 Linaro Ltd + */ + +#include +#include +#include +#include +#include + +#include + +#include +#include + +static DEFINE_STATIC_KEY_FALSE(have_neon); +static DEFINE_STATIC_KEY_FALSE(have_pmull); + +#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U + +asmlinkage u16 crc_t10dif_pmull64(u16 init_crc, const u8 *buf, size_t len); +asmlinkage void crc_t10dif_pmull8(u16 init_crc, const u8 *buf, size_t len, + u8 out[16]); + +u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length) +{ + if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE) { + if (static_branch_likely(&have_pmull)) { + if (crypto_simd_usable()) { + kernel_neon_begin(); + crc = crc_t10dif_pmull64(crc, data, length); + kernel_neon_end(); + return crc; + } + } else if (length > CRC_T10DIF_PMULL_CHUNK_SIZE && + static_branch_likely(&have_neon) && + crypto_simd_usable()) { + u8 buf[16] __aligned(16); + + kernel_neon_begin(); + crc_t10dif_pmull8(crc, data, length, buf); + kernel_neon_end(); + + crc = 0; + data = buf; + length = sizeof(buf); + } + } + return crc_t10dif_generic(crc, data, length); +} +EXPORT_SYMBOL(crc_t10dif_arch); + +static int __init crc_t10dif_arm_init(void) +{ + if (elf_hwcap & HWCAP_NEON) { + static_branch_enable(&have_neon); + if (elf_hwcap2 & HWCAP2_PMULL) + static_branch_enable(&have_pmull); + } + return 0; +} +arch_initcall(crc_t10dif_arm_init); + +static void __exit crc_t10dif_arm_exit(void) +{ +} +module_exit(crc_t10dif_arm_exit); + +bool crc_t10dif_is_optimized(void) +{ + return static_key_enabled(&have_neon); +} +EXPORT_SYMBOL(crc_t10dif_is_optimized); + +MODULE_AUTHOR("Ard Biesheuvel "); +MODULE_DESCRIPTION("Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/arm/crypto/crc32-ce-core.S b/arch/arm/lib/crc32-core.S similarity index 98% rename from arch/arm/crypto/crc32-ce-core.S rename to arch/arm/lib/crc32-core.S index 88f9edf94e95..6f674f30c70b 100644 --- a/arch/arm/crypto/crc32-ce-core.S +++ b/arch/arm/lib/crc32-core.S @@ -48,7 +48,6 @@ */ #include -#include #include .text @@ -297,11 +296,11 @@ ARM_BE8(rev16 r3, r3 ) .endm .align 5 -SYM_TYPED_FUNC_START(crc32_armv8_le) +SYM_FUNC_START(crc32_armv8_le) __crc32 SYM_FUNC_END(crc32_armv8_le) .align 5 -SYM_TYPED_FUNC_START(crc32c_armv8_le) +SYM_FUNC_START(crc32c_armv8_le) __crc32 c SYM_FUNC_END(crc32c_armv8_le) diff --git a/arch/arm/lib/crc32-glue.c b/arch/arm/lib/crc32-glue.c new file mode 100644 index 000000000000..2c30ba3d80e6 --- /dev/null +++ b/arch/arm/lib/crc32-glue.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions instructions + * + * Copyright (C) 2016 Linaro Ltd + */ + +#include +#include +#include +#include +#include +#include + +#include + +#include +#include +#include + +static DEFINE_STATIC_KEY_FALSE(have_crc32); +static DEFINE_STATIC_KEY_FALSE(have_pmull); + +#define PMULL_MIN_LEN 64 /* min size of buffer for pmull functions */ + +asmlinkage u32 crc32_pmull_le(const u8 buf[], u32 len, u32 init_crc); +asmlinkage u32 crc32_armv8_le(u32 init_crc, const u8 buf[], u32 len); + +asmlinkage u32 crc32c_pmull_le(const u8 buf[], u32 len, u32 init_crc); +asmlinkage u32 crc32c_armv8_le(u32 init_crc, const u8 buf[], u32 len); + +static u32 crc32_le_scalar(u32 crc, const u8 *p, size_t len) +{ + if (static_branch_likely(&have_crc32)) + return crc32_armv8_le(crc, p, len); + return crc32_le_base(crc, p, len); +} + +u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) +{ + if (len >= PMULL_MIN_LEN + 15 && + static_branch_likely(&have_pmull) && crypto_simd_usable()) { + size_t n = -(uintptr_t)p & 15; + + /* align p to 16-byte boundary */ + if (n) { + crc = crc32_le_scalar(crc, p, n); + p += n; + len -= n; + } + n = round_down(len, 16); + kernel_neon_begin(); + crc = crc32_pmull_le(p, n, crc); + kernel_neon_end(); + p += n; + len -= n; + } + return crc32_le_scalar(crc, p, len); +} +EXPORT_SYMBOL(crc32_le_arch); + +static u32 crc32c_le_scalar(u32 crc, const u8 *p, size_t len) +{ + if (static_branch_likely(&have_crc32)) + return crc32c_armv8_le(crc, p, len); + return crc32c_le_base(crc, p, len); +} + +u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len) +{ + if (len >= PMULL_MIN_LEN + 15 && + static_branch_likely(&have_pmull) && crypto_simd_usable()) { + size_t n = -(uintptr_t)p & 15; + + /* align p to 16-byte boundary */ + if (n) { + crc = crc32c_le_scalar(crc, p, n); + p += n; + len -= n; + } + n = round_down(len, 16); + kernel_neon_begin(); + crc = crc32c_pmull_le(p, n, crc); + kernel_neon_end(); + p += n; + len -= n; + } + return crc32c_le_scalar(crc, p, len); +} +EXPORT_SYMBOL(crc32c_le_arch); + +u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) +{ + return crc32_be_base(crc, p, len); +} +EXPORT_SYMBOL(crc32_be_arch); + +static int __init crc32_arm_init(void) +{ + if (elf_hwcap2 & HWCAP2_CRC32) + static_branch_enable(&have_crc32); + if (elf_hwcap2 & HWCAP2_PMULL) + static_branch_enable(&have_pmull); + return 0; +} +arch_initcall(crc32_arm_init); + +static void __exit crc32_arm_exit(void) +{ +} +module_exit(crc32_arm_exit); + +u32 crc32_optimizations(void) +{ + if (elf_hwcap2 & (HWCAP2_CRC32 | HWCAP2_PMULL)) + return CRC32_LE_OPTIMIZATION | CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_AUTHOR("Ard Biesheuvel "); +MODULE_DESCRIPTION("Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig index 344f5305f69a..04bd91c72521 100644 --- a/arch/arm/mach-at91/Kconfig +++ b/arch/arm/mach-at91/Kconfig @@ -58,6 +58,17 @@ config SOC_SAMA5D4 help Select this if you are using one of Microchip's SAMA5D4 family SoC. +config SOC_SAMA7D65 + bool "SAMA7D65 family" + depends on ARCH_MULTI_V7 + select HAVE_AT91_GENERATED_CLK + select HAVE_AT91_SAM9X60_PLL + select HAVE_AT91_USB_CLK + select HAVE_AT91_UTMI + select SOC_SAMA7 + help + Select this if you are using one of Microchip's SAMA7D65 family SoC. + config SOC_SAMA7G5 bool "SAMA7G5 family" depends on ARCH_MULTI_V7 diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index b9b995f8a36e..05a1547642b6 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -598,7 +598,21 @@ static int at91_suspend_finish(unsigned long val) return 0; } -static void at91_pm_switch_ba_to_vbat(void) +/** + * at91_pm_switch_ba_to_auto() - Configure Backup Unit Power Switch + * to automatic/hardware mode. + * + * The Backup Unit Power Switch can be managed either by software or hardware. + * Enabling hardware mode allows the automatic transition of power between + * VDDANA (or VDDIN33) and VDDBU (or VBAT, respectively), based on the + * availability of these power sources. + * + * If the Backup Unit Power Switch is already in automatic mode, no action is + * required. If it is in software-controlled mode, it is switched to automatic + * mode to enhance safety and eliminate the need for toggling between power + * sources. + */ +static void at91_pm_switch_ba_to_auto(void) { unsigned int offset = offsetof(struct at91_pm_sfrbu_regs, pswbu); unsigned int val; @@ -609,24 +623,19 @@ static void at91_pm_switch_ba_to_vbat(void) val = readl(soc_pm.data.sfrbu + offset); - /* Already on VBAT. */ - if (!(val & soc_pm.sfrbu_regs.pswbu.state)) + /* Already on auto/hardware. */ + if (!(val & soc_pm.sfrbu_regs.pswbu.ctrl)) return; - val &= ~soc_pm.sfrbu_regs.pswbu.softsw; - val |= soc_pm.sfrbu_regs.pswbu.key | soc_pm.sfrbu_regs.pswbu.ctrl; + val &= ~soc_pm.sfrbu_regs.pswbu.ctrl; + val |= soc_pm.sfrbu_regs.pswbu.key; writel(val, soc_pm.data.sfrbu + offset); - - /* Wait for update. */ - val = readl(soc_pm.data.sfrbu + offset); - while (val & soc_pm.sfrbu_regs.pswbu.state) - val = readl(soc_pm.data.sfrbu + offset); } static void at91_pm_suspend(suspend_state_t state) { if (soc_pm.data.mode == AT91_PM_BACKUP) { - at91_pm_switch_ba_to_vbat(); + at91_pm_switch_ba_to_auto(); cpu_suspend(0, at91_suspend_finish); diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig index e4fe059cd861..dc47b2312127 100644 --- a/arch/arm/mach-imx/Kconfig +++ b/arch/arm/mach-imx/Kconfig @@ -6,6 +6,7 @@ menuconfig ARCH_MXC select CLKSRC_IMX_GPT select GENERIC_IRQ_CHIP select GPIOLIB + select PINCTRL select PM_OPP if PM select SOC_BUS select SRAM diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c index 3312ef93355d..a5bf5554800f 100644 --- a/arch/arm/mach-omap1/board-nokia770.c +++ b/arch/arm/mach-omap1/board-nokia770.c @@ -289,7 +289,7 @@ static struct gpiod_lookup_table nokia770_irq_gpio_table = { GPIO_LOOKUP("gpio-0-15", 15, "ads7846_irq", GPIO_ACTIVE_HIGH), /* GPIO used for retu IRQ */ - GPIO_LOOKUP("gpio-48-63", 15, "retu_irq", + GPIO_LOOKUP("gpio-48-63", 14, "retu_irq", GPIO_ACTIVE_HIGH), /* GPIO used for tahvo IRQ */ GPIO_LOOKUP("gpio-32-47", 8, "tahvo_irq", diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c index 2441d96b7144..a4785302b7ae 100644 --- a/arch/arm/mach-omap2/powerdomain.c +++ b/arch/arm/mach-omap2/powerdomain.c @@ -523,7 +523,7 @@ int pwrdm_get_mem_bank_count(struct powerdomain *pwrdm) * Set the powerdomain @pwrdm's next power state to @pwrst. The powerdomain * may not enter this state immediately if the preconditions for this state * have not been satisfied. Returns -EINVAL if the powerdomain pointer is - * null or if the power state is invalid for the powerdomin, or returns 0 + * null or if the power state is invalid for the powerdomain, or returns 0 * upon success. */ int pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst) diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c index 0c8d9000df5a..dd930e3a61a4 100644 --- a/arch/arm/mach-pxa/sharpsl_pm.c +++ b/arch/arm/mach-pxa/sharpsl_pm.c @@ -31,10 +31,10 @@ /* * Constants */ -#define SHARPSL_CHARGE_ON_TIME_INTERVAL (msecs_to_jiffies(1*60*1000)) /* 1 min */ -#define SHARPSL_CHARGE_FINISH_TIME (msecs_to_jiffies(10*60*1000)) /* 10 min */ -#define SHARPSL_BATCHK_TIME (msecs_to_jiffies(15*1000)) /* 15 sec */ -#define SHARPSL_BATCHK_TIME_SUSPEND (60*10) /* 10 min */ +#define SHARPSL_CHARGE_ON_TIME_INTERVAL (secs_to_jiffies(60)) +#define SHARPSL_CHARGE_FINISH_TIME (secs_to_jiffies(10*60)) +#define SHARPSL_BATCHK_TIME (secs_to_jiffies(15)) +#define SHARPSL_BATCHK_TIME_SUSPEND (60*10) /* 10 min */ #define SHARPSL_WAIT_CO_TIME 15 /* 15 sec */ #define SHARPSL_WAIT_DISCHARGE_ON 100 /* 100 msec */ diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index 9f7454b8efa7..2cde4c83b7f9 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -1124,7 +1124,7 @@ static int ecard_match(struct device *_dev, const struct device_driver *_drv) return ret; } -struct bus_type ecard_bus_type = { +const struct bus_type ecard_bus_type = { .name = "ecard", .dev_groups = ecard_dev_groups, .match = ecard_match, diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index f5b7a16c5803..f02f872ea8a9 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -726,13 +726,8 @@ EXPORT_SYMBOL(phys_mem_access_prot); static void __init *early_alloc(unsigned long sz) { - void *ptr = memblock_alloc(sz, sz); + return memblock_alloc_or_panic(sz, sz); - if (!ptr) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, sz, sz); - - return ptr; } static void *__init late_alloc(unsigned long sz) @@ -1027,10 +1022,7 @@ void __init iotable_init(struct map_desc *io_desc, int nr) if (!nr) return; - svm = memblock_alloc(sizeof(*svm) * nr, __alignof__(*svm)); - if (!svm) - panic("%s: Failed to allocate %zu bytes align=0x%zx\n", - __func__, sizeof(*svm) * nr, __alignof__(*svm)); + svm = memblock_alloc_or_panic(sizeof(*svm) * nr, __alignof__(*svm)); for (md = io_desc; nr; md++, nr--) { create_mapping(md); @@ -1052,10 +1044,7 @@ void __init vm_reserve_area_early(unsigned long addr, unsigned long size, struct vm_struct *vm; struct static_vm *svm; - svm = memblock_alloc(sizeof(*svm), __alignof__(*svm)); - if (!svm) - panic("%s: Failed to allocate %zu bytes align=0x%zx\n", - __func__, sizeof(*svm), __alignof__(*svm)); + svm = memblock_alloc_or_panic(sizeof(*svm), __alignof__(*svm)); vm = &svm->vm; vm->addr = (void *)addr; diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index c415f3859b20..1a8f6914ee59 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -162,10 +162,7 @@ void __init paging_init(const struct machine_desc *mdesc) mpu_setup(); /* allocate the zero page. */ - zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!zero_page) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + zero_page = (void *)memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); bootmem_init(); diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index f8e9bc58a84f..4eb81b7ed03a 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -17,11 +17,11 @@ #include "mm.h" #ifdef CONFIG_ARM_LPAE -#define __pgd_alloc() kmalloc_array(PTRS_PER_PGD, sizeof(pgd_t), GFP_KERNEL) -#define __pgd_free(pgd) kfree(pgd) +#define _pgd_alloc(mm) kmalloc_array(PTRS_PER_PGD, sizeof(pgd_t), GFP_KERNEL | __GFP_ZERO) +#define _pgd_free(mm, pgd) kfree(pgd) #else -#define __pgd_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL, 2) -#define __pgd_free(pgd) free_pages((unsigned long)pgd, 2) +#define _pgd_alloc(mm) __pgd_alloc(mm, 2) +#define _pgd_free(mm, pgd) __pgd_free(mm, pgd) #endif /* @@ -35,12 +35,10 @@ pgd_t *pgd_alloc(struct mm_struct *mm) pmd_t *new_pmd, *init_pmd; pte_t *new_pte, *init_pte; - new_pgd = __pgd_alloc(); + new_pgd = _pgd_alloc(mm); if (!new_pgd) goto no_pgd; - memset(new_pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t)); - /* * Copy over the kernel and IO PGD entries */ @@ -134,7 +132,7 @@ no_pmd: no_pud: p4d_free(mm, new_p4d); no_p4d: - __pgd_free(new_pgd); + _pgd_free(mm, new_pgd); no_pgd: return NULL; } @@ -207,5 +205,5 @@ no_pgd: p4d_free(mm, p4d); } #endif - __pgd_free(pgd_base); + _pgd_free(mm, pgd_base); } diff --git a/arch/arm/vfp/vfpinstr.h b/arch/arm/vfp/vfpinstr.h index 32090b0fb250..a2f0c47e0ce7 100644 --- a/arch/arm/vfp/vfpinstr.h +++ b/arch/arm/vfp/vfpinstr.h @@ -62,8 +62,6 @@ #define FPSCR_C (1 << 29) #define FPSCR_V (1 << 28) -#ifdef CONFIG_AS_VFP_VMRS_FPINST - #define fmrx(_vfp_) ({ \ u32 __v; \ asm volatile (".fpu vfpv2\n" \ @@ -78,26 +76,6 @@ : : "r" (_var_) : "cc"); \ }) -#else - -#define vfpreg(_vfp_) #_vfp_ - -#define fmrx(_vfp_) ({ \ - u32 __v; \ - asm volatile ("mrc p10, 7, %0, " vfpreg(_vfp_) "," \ - "cr0, 0 @ fmrx %0, " #_vfp_ \ - : "=r" (__v) : : "cc"); \ - __v; \ -}) - -#define fmxr(_vfp_, _var_) ({ \ - asm volatile ("mcr p10, 7, %0, " vfpreg(_vfp_) "," \ - "cr0, 0 @ fmxr " #_vfp_ ", %0" \ - : : "r" (_var_) : "cc"); \ -}) - -#endif - u32 vfp_single_cpdo(u32 inst, u32 fpscr); u32 vfp_single_cprt(u32 inst, u32 fpscr, struct pt_regs *regs); diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index d44867fc0c5e..7803d50b90f8 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -168,7 +168,7 @@ static void vfp_thread_copy(struct thread_info *thread) /* * When this function is called with the following 'cmd's, the following * is true while this function is being run: - * THREAD_NOFTIFY_SWTICH: + * THREAD_NOTIFY_SWITCH: * - the previously running thread will not be scheduled onto another CPU. * - the next thread to be run (v) will not be running on another CPU. * - thread->cpu is the local CPU number diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 100570a048c5..fcdd0ed3eca8 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -21,6 +21,8 @@ config ARM64 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_CC_PLATFORM + select ARCH_HAS_CRC32 + select ARCH_HAS_CRC_T10DIF if KERNEL_MODE_NEON select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE @@ -113,7 +115,7 @@ config ARM64 select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) select ARCH_WANT_LD_ORPHAN_WARN - select ARCH_WANTS_EXECMEM_LATE if EXECMEM + select ARCH_WANTS_EXECMEM_LATE select ARCH_WANTS_NO_INSTR select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES select ARCH_HAS_UBSAN @@ -149,6 +151,7 @@ config ARM64 select GENERIC_IDLE_POLL_SETUP select GENERIC_IOREMAP select GENERIC_IRQ_IPI + select GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL @@ -216,9 +219,11 @@ config ARM64 select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_GUP_FAST + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_ERROR_INJECTION + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_RETVAL select HAVE_GCC_PLUGINS @@ -1379,7 +1384,6 @@ config ARM64_VA_BITS_48 config ARM64_VA_BITS_52 bool "52-bit" - depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Enable 52-bit virtual addressing for userspace when explicitly requested via a hint to mmap(). The kernel will also use 52-bit @@ -1431,7 +1435,6 @@ config ARM64_PA_BITS_48 config ARM64_PA_BITS_52 bool "52-bit" depends on ARM64_64K_PAGES || ARM64_VA_BITS_52 - depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Enable support for a 52-bit physical address space, introduced as part of the ARMv8.2-LPA extension. @@ -1681,6 +1684,7 @@ config RODATA_FULL_DEFAULT_ENABLED config ARM64_SW_TTBR0_PAN bool "Emulate Privileged Access Never using TTBR0_EL1 switching" depends on !KCSAN + select ARM64_PAN help Enabling this option prevents the kernel from accessing user-space memory directly by pointing TTBR0_EL1 to a reserved @@ -1937,7 +1941,6 @@ config ARM64_RAS_EXTN config ARM64_CNP bool "Enable support for Common Not Private (CNP) translations" default y - depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Common Not Private (CNP) allows translation table entries to be shared between different PEs in the same inner shareable @@ -2132,7 +2135,7 @@ config ARM64_MTE depends on AS_HAS_ARMV8_5 depends on AS_HAS_LSE_ATOMICS # Required for tag checking in the uaccess routines - depends on ARM64_PAN + select ARM64_PAN select ARCH_HAS_SUBPAGE_FAULTS select ARCH_USES_HIGH_VMA_FLAGS select ARCH_USES_PG_ARCH_2 diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 370a9d2b6919..02f9248f7c84 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -101,6 +101,11 @@ config ARCH_BITMAIN help This enables support for the Bitmain SoC Family. +config ARCH_BLAIZE + bool "Blaize SoC Platforms" + help + This enables support for the Blaize SoC family + config ARCH_EXYNOS bool "Samsung Exynos SoC family" select COMMON_CLK_SAMSUNG @@ -135,8 +140,6 @@ config ARCH_K3 select SOC_TI select TI_MESSAGE_MANAGER select TI_SCI_PROTOCOL - select TI_SCI_INTR_IRQCHIP - select TI_SCI_INTA_IRQCHIP select TI_K3_SOCINFO help This enables support for Texas Instruments' K3 multicore SoC diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile index 21cd3a87f385..79b73a21ddc2 100644 --- a/arch/arm64/boot/dts/Makefile +++ b/arch/arm64/boot/dts/Makefile @@ -10,6 +10,7 @@ subdir-y += apm subdir-y += apple subdir-y += arm subdir-y += bitmain +subdir-y += blaize subdir-y += broadcom subdir-y += cavium subdir-y += exynos diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a100.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a100.dtsi index 29ac7716c7a5..a24adba201af 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a100.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a100.dtsi @@ -101,6 +101,39 @@ #size-cells = <1>; ranges = <0 0 0 0x3fffffff>; + syscon: syscon@3000000 { + compatible = "allwinner,sun50i-a100-system-control", + "allwinner,sun50i-a64-system-control"; + reg = <0x03000000 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + sram_a1: sram@20000 { + compatible = "mmio-sram"; + reg = <0x00020000 0x4000>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x00020000 0x4000>; + }; + + sram_c: sram@24000 { + compatible = "mmio-sram"; + reg = <0x024000 0x21000>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x024000 0x21000>; + }; + + sram_a2: sram@100000 { + compatible = "mmio-sram"; + reg = <0x0100000 0x14000>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x0100000 0x14000>; + }; + }; + ccu: clock@3001000 { compatible = "allwinner,sun50i-a100-ccu"; reg = <0x03001000 0x1000>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts index 379c2c8466f5..86d44349e095 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts @@ -390,6 +390,8 @@ &tcon0 { pinctrl-names = "default"; pinctrl-0 = <&lcd_rgb666_pins>; + assigned-clocks = <&ccu CLK_TCON0>; + assigned-clock-parents = <&ccu CLK_PLL_VIDEO0_2X>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-teres-i.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-teres-i.dts index b407e1dd08a7..ec055510af8b 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-teres-i.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-teres-i.dts @@ -369,6 +369,8 @@ &tcon0 { pinctrl-names = "default"; pinctrl-0 = <&lcd_rgb666_pins>; + assigned-clocks = <&ccu CLK_TCON0>; + assigned-clock-parents = <&ccu CLK_PLL_VIDEO0_2X>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index a5c3920e0f04..0fecf0abb204 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -445,6 +445,8 @@ clock-names = "ahb", "tcon-ch0"; clock-output-names = "tcon-data-clock"; #clock-cells = <0>; + assigned-clocks = <&ccu CLK_TCON0>; + assigned-clock-parents = <&ccu CLK_PLL_MIPI>; resets = <&ccu RST_BUS_TCON0>, <&ccu RST_BUS_LVDS>; reset-names = "lcd", "lvds"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h313-tanix-tx1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h313-tanix-tx1.dts index bafd3e803106..17e6aef67aaf 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h313-tanix-tx1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h313-tanix-tx1.dts @@ -6,6 +6,7 @@ /dts-v1/; #include "sun50i-h616.dtsi" +#include "sun50i-h616-cpu-opp.dtsi" #include #include diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_swvp.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_swvp.dts index 0d837d3e65a5..34ccf8138f7b 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_swvp.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_swvp.dts @@ -63,7 +63,6 @@ status = "okay"; phy-mode = "rgmii"; phy-addr = <0xffffffff>; - snps,max-mtu = <0x0>; }; &gmac1 { diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index 52d57773a77f..1736bd2e96e2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -178,9 +178,8 @@ vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; - brcmf: wifi@1 { + sdio: wifi@1 { reg = <1>; - compatible = "brcm,bcm4329-fmac"; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p230.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p230.dts index c1470416faad..7dffeb5931c9 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p230.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p230.dts @@ -102,8 +102,7 @@ }; &sd_emmc_a { - brcmf: wifi@1 { + sdio: wifi@1 { reg = <1>; - compatible = "brcm,bcm4329-fmac"; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p231.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p231.dts index 92c425d0259c..ff9145d49090 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p231.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p231.dts @@ -21,8 +21,7 @@ }; &sd_emmc_a { - brcmf: wifi@1 { + sdio: wifi@1 { reg = <1>; - compatible = "brcm,bcm4329-fmac"; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi index 7e7dc87ede2d..b52a830efcce 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi @@ -134,9 +134,8 @@ vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; - brcmf: wifi@1 { + sdio: wifi@1 { reg = <1>; - compatible = "brcm,bcm4329-fmac"; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts index d4858afa0e9c..feb31207773f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts @@ -72,8 +72,7 @@ }; &sd_emmc_a { - brcmf: wifi@1 { + sdio: wifi@1 { reg = <1>; - compatible = "brcm,bcm4329-fmac"; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-q201.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-q201.dts index d02b80d77378..6c8bec1853ac 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-q201.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-q201.dts @@ -21,8 +21,7 @@ }; &sd_emmc_a { - brcmf: wifi@1 { + sdio: wifi@1 { reg = <1>; - compatible = "brcm,bcm4329-fmac"; }; }; diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts index 19973ab4ea6b..9e10d7a6b5a2 100644 --- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts +++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts @@ -233,7 +233,7 @@ #interrupt-cells = <0x1>; compatible = "pci-host-ecam-generic"; device_type = "pci"; - bus-range = <0x0 0x1>; + bus-range = <0x0 0xff>; reg = <0x0 0x40000000 0x0 0x10000000>; ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>; interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/blaize/Makefile b/arch/arm64/boot/dts/blaize/Makefile new file mode 100644 index 000000000000..7e10b3199e6c --- /dev/null +++ b/arch/arm64/boot/dts/blaize/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0+ +dtb-$(CONFIG_ARCH_BLAIZE) += blaize-blzp1600-cb2.dtb diff --git a/arch/arm64/boot/dts/blaize/blaize-blzp1600-cb2.dts b/arch/arm64/boot/dts/blaize/blaize-blzp1600-cb2.dts new file mode 100644 index 000000000000..7e3cef2ed352 --- /dev/null +++ b/arch/arm64/boot/dts/blaize/blaize-blzp1600-cb2.dts @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2024 Blaize, Inc. All rights reserved. + */ + +/dts-v1/; + +#include "blaize-blzp1600-som.dtsi" + +/ { + model = "Blaize BLZP1600 SoM1600P CB2 Development Board"; + + compatible = "blaize,blzp1600-cb2", "blaize,blzp1600"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200"; + }; +}; + +&i2c0 { + clock-frequency = <100000>; + status = "okay"; +}; + +&i2c1 { + clock-frequency = <100000>; + status = "okay"; +}; + +&i2c3 { + clock-frequency = <100000>; + status = "okay"; + + gpio_expander: gpio@74 { + compatible = "ti,tca9539"; + reg = <0x74>; + gpio-controller; + #gpio-cells = <2>; + gpio-line-names = "RSP_PIN_7", /* GPIO_0 */ + "RSP_PIN_11", /* GPIO_1 */ + "RSP_PIN_13", /* GPIO_2 */ + "RSP_PIN_15", /* GPIO_3 */ + "RSP_PIN_27", /* GPIO_4 */ + "RSP_PIN_29", /* GPIO_5 */ + "RSP_PIN_31", /* GPIO_6 */ + "RSP_PIN_33", /* GPIO_7 */ + "RSP_PIN_37", /* GPIO_8 */ + "RSP_PIN_16", /* GPIO_9 */ + "RSP_PIN_18", /* GPIO_10 */ + "RSP_PIN_22", /* GPIO_11 */ + "RSP_PIN_28", /* GPIO_12 */ + "RSP_PIN_32", /* GPIO_13 */ + "RSP_PIN_36", /* GPIO_14 */ + "TP31"; /* GPIO_15 */ + }; + + gpio_expander_m2: gpio@75 { + compatible = "ti,tca9539"; + reg = <0x75>; + gpio-controller; + #gpio-cells = <2>; + gpio-line-names = "M2_W_DIS1_N", /* GPIO_0 */ + "M2_W_DIS2_N", /* GPIO_1 */ + "M2_UART_WAKE_N", /* GPIO_2 */ + "M2_COEX3", /* GPIO_3 */ + "M2_COEX_RXD", /* GPIO_4 */ + "M2_COEX_TXD", /* GPIO_5 */ + "M2_VENDOR_PIN40", /* GPIO_6 */ + "M2_VENDOR_PIN42", /* GPIO_7 */ + "M2_VENDOR_PIN38", /* GPIO_8 */ + "M2_SDIO_RST_N", /* GPIO_9 */ + "M2_SDIO_WAKE_N", /* GPIO_10 */ + "M2_PETN1", /* GPIO_11 */ + "M2_PERP1", /* GPIO_12 */ + "M2_PERN1", /* GPIO_13 */ + "UIM_SWP", /* GPIO_14 */ + "UART1_TO_RSP"; /* GPIO_15 */ + }; +}; diff --git a/arch/arm64/boot/dts/blaize/blaize-blzp1600-som.dtsi b/arch/arm64/boot/dts/blaize/blaize-blzp1600-som.dtsi new file mode 100644 index 000000000000..bfdff5953edd --- /dev/null +++ b/arch/arm64/boot/dts/blaize/blaize-blzp1600-som.dtsi @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2024 Blaize, Inc. All rights reserved. + */ + +#include "blaize-blzp1600.dtsi" + +/ { + memory@0 { + device_type = "memory"; + reg = <0x0 0x0 0x1 0x0>; + }; +}; + +/* i2c4 bus is available only on the SoM, not on the board */ +&i2c4 { + clock-frequency = <100000>; + status = "okay"; +}; + +&uart0 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/blaize/blaize-blzp1600.dtsi b/arch/arm64/boot/dts/blaize/blaize-blzp1600.dtsi new file mode 100644 index 000000000000..7d399e6a532f --- /dev/null +++ b/arch/arm64/boot/dts/blaize/blaize-blzp1600.dtsi @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2024 Blaize, Inc. All rights reserved. + */ + +/dts-v1/; + +#include +#include + +/ { + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "arm,cortex-a53"; + reg = <0x0 0x0>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&l2>; + }; + + cpu1: cpu@1 { + compatible = "arm,cortex-a53"; + reg = <0x0 0x1>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&l2>; + }; + + l2: l2-cache0 { + compatible = "cache"; + cache-level = <2>; + cache-unified; + }; + }; + + firmware { + scmi { + compatible = "arm,scmi-smc"; + arm,smc-id = <0x82002000>; + #address-cells = <1>; + #size-cells = <0>; + + shmem = <&scmi0_shm>; + + scmi_clk: protocol@14 { + reg = <0x14>; + #clock-cells = <1>; + }; + + scmi_rst: protocol@16 { + reg = <0x16>; + #reset-cells = <1>; + }; + }; + }; + + pmu { + compatible = "arm,cortex-a53-pmu"; + interrupts = , + ; + interrupt-affinity = <&cpu0>, <&cpu1>; + }; + + psci { + compatible = "arm,psci-1.0", "arm,psci-0.2"; + method = "smc"; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + /* SCMI reserved buffer space on DDR space */ + scmi0_shm: scmi-shmem@800 { + compatible = "arm,scmi-shmem"; + reg = <0x0 0x800 0x0 0x80>; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = /* Physical Secure PPI */ + , + /* Physical Non-Secure PPI */ + , + /* Hypervisor PPI */ + , + /* Virtual PPI */ + ; + }; + + soc@200000000 { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x0 0x2 0x0 0x850000>; + + gic: interrupt-controller@410000 { + compatible = "arm,gic-400"; + reg = <0x410000 0x20000>, + <0x420000 0x20000>, + <0x440000 0x20000>, + <0x460000 0x20000>; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + interrupts = ; + }; + + uart0: serial@4d0000 { + compatible = "ns16550a"; + reg = <0x4d0000 0x1000>; + clocks = <&scmi_clk 59>; + resets = <&scmi_rst 59>; + reg-shift = <2>; + interrupts = ; + status = "disabled"; + }; + + uart1: serial@4e0000 { + compatible = "ns16550a"; + reg = <0x4e0000 0x1000>; + clocks = <&scmi_clk 60>; + resets = <&scmi_rst 60>; + reg-shift = <2>; + interrupts = ; + status = "disabled"; + }; + + i2c0: i2c@4f0000 { + compatible = "snps,designware-i2c"; + reg = <0x4f0000 0x1000>; + interrupts = ; + clocks = <&scmi_clk 54>; + resets = <&scmi_rst 54>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c1: i2c@500000 { + compatible = "snps,designware-i2c"; + reg = <0x500000 0x1000>; + interrupts = ; + clocks = <&scmi_clk 55>; + resets = <&scmi_rst 55>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c2: i2c@510000 { + compatible = "snps,designware-i2c"; + reg = <0x510000 0x1000>; + interrupts = ; + clocks = <&scmi_clk 56>; + resets = <&scmi_rst 56>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c3: i2c@520000 { + compatible = "snps,designware-i2c"; + reg = <0x520000 0x1000>; + interrupts = ; + clocks = <&scmi_clk 57>; + resets = <&scmi_rst 57>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c4: i2c@530000 { + compatible = "snps,designware-i2c"; + reg = <0x530000 0x1000>; + interrupts = ; + clocks = <&scmi_clk 58>; + resets = <&scmi_rst 58>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + arm_cc712: crypto@550000 { + compatible = "arm,cryptocell-712-ree"; + reg = <0x550000 0x1000>; + interrupts = ; + clocks = <&scmi_clk 7>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/broadcom/Makefile b/arch/arm64/boot/dts/broadcom/Makefile index 92565e9781ad..3d0efb93b06d 100644 --- a/arch/arm64/boot/dts/broadcom/Makefile +++ b/arch/arm64/boot/dts/broadcom/Makefile @@ -7,6 +7,7 @@ dtb-$(CONFIG_ARCH_BCM2835) += bcm2711-rpi-400.dtb \ bcm2711-rpi-4-b.dtb \ bcm2711-rpi-cm4-io.dtb \ bcm2712-rpi-5-b.dtb \ + bcm2712-d-rpi-5-b.dtb \ bcm2837-rpi-3-a-plus.dtb \ bcm2837-rpi-3-b.dtb \ bcm2837-rpi-3-b-plus.dtb \ diff --git a/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts b/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts new file mode 100644 index 000000000000..7de24d60bcd1 --- /dev/null +++ b/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/dts-v1/; + +#include "bcm2712-rpi-5-b.dts" + +&gio_aon { + brcm,gpio-bank-widths = <15 6>; + + gpio-line-names = + "RP1_SDA", // AON_GPIO_00 + "RP1_SCL", // AON_GPIO_01 + "RP1_RUN", // AON_GPIO_02 + "SD_IOVDD_SEL", // AON_GPIO_03 + "SD_PWR_ON", // AON_GPIO_04 + "SD_CDET_N", // AON_GPIO_05 + "SD_FLG_N", // AON_GPIO_06 + "", // AON_GPIO_07 + "2712_WAKE", // AON_GPIO_08 + "2712_STAT_LED", // AON_GPIO_09 + "", // AON_GPIO_10 + "", // AON_GPIO_11 + "PMIC_INT", // AON_GPIO_12 + "UART_TX_FS", // AON_GPIO_13 + "UART_RX_FS", // AON_GPIO_14 + "", // AON_GPIO_15 + "", // AON_GPIO_16 + + // Pad bank0 out to 32 entries + "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", + + "HDMI0_SCL", // AON_SGPIO_00 + "HDMI0_SDA", // AON_SGPIO_01 + "HDMI1_SCL", // AON_SGPIO_02 + "HDMI1_SDA", // AON_SGPIO_03 + "PMIC_SCL", // AON_SGPIO_04 + "PMIC_SDA"; // AON_SGPIO_05 +}; diff --git a/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts b/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts index 2bdbb6780242..fbc56309660f 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts +++ b/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts @@ -62,3 +62,45 @@ sd-uhs-ddr50; sd-uhs-sdr104; }; + +&soc { + firmware: firmware { + compatible = "raspberrypi,bcm2835-firmware", "simple-mfd"; + #address-cells = <1>; + #size-cells = <1>; + + mboxes = <&mailbox>; + dma-ranges; + + firmware_clocks: clocks { + compatible = "raspberrypi,firmware-clocks"; + #clock-cells = <1>; + }; + + reset: reset { + compatible = "raspberrypi,firmware-reset"; + #reset-cells = <1>; + }; + }; + + power: power { + compatible = "raspberrypi,bcm2835-power"; + firmware = <&firmware>; + #power-domain-cells = <1>; + }; +}; + +&hvs { + clocks = <&firmware_clocks 4>, <&firmware_clocks 16>; + clock-names = "core", "disp"; +}; + +&hdmi0 { + clocks = <&firmware_clocks 13>, <&firmware_clocks 14>, <&dvp 0>, <&clk_27MHz>; + clock-names = "hdmi", "bvb", "audio", "cec"; +}; + +&hdmi1 { + clocks = <&firmware_clocks 13>, <&firmware_clocks 14>, <&dvp 1>, <&clk_27MHz>; + clock-names = "hdmi", "bvb", "audio", "cec"; +}; diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index 6e5a984c1d4e..689c82b7f596 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -67,7 +67,7 @@ l2_cache_l0: l2-cache-l0 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -91,7 +91,7 @@ l2_cache_l1: l2-cache-l1 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -115,7 +115,7 @@ l2_cache_l2: l2-cache-l2 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -139,7 +139,7 @@ l2_cache_l3: l2-cache-l3 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -221,11 +221,6 @@ #mbox-cells = <0>; }; - local_intc: interrupt-controller@7cd00000 { - compatible = "brcm,bcm2836-l1-intc"; - reg = <0x7cd00000 0x100>; - }; - uart10: serial@7d001000 { compatible = "arm,pl011", "arm,primecell"; reg = <0x7d001000 0x200>; @@ -265,6 +260,172 @@ interrupt-controller; #interrupt-cells = <3>; }; + + aon_intr: interrupt-controller@7d510600 { + compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc"; + reg = <0x7d510600 0x30>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <1>; + }; + + pixelvalve0: pixelvalve@7c410000 { + compatible = "brcm,bcm2712-pixelvalve0"; + reg = <0x7c410000 0x100>; + interrupts = ; + }; + + pixelvalve1: pixelvalve@7c411000 { + compatible = "brcm,bcm2712-pixelvalve1"; + reg = <0x7c411000 0x100>; + interrupts = ; + }; + + mop: mop@7c500000 { + compatible = "brcm,bcm2712-mop"; + reg = <0x7c500000 0x28>; + interrupt-parent = <&disp_intr>; + interrupts = <1>; + }; + + moplet: moplet@7c501000 { + compatible = "brcm,bcm2712-moplet"; + reg = <0x7c501000 0x20>; + interrupt-parent = <&disp_intr>; + interrupts = <0>; + }; + + disp_intr: interrupt-controller@7c502000 { + compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc"; + reg = <0x7c502000 0x30>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <1>; + }; + + dvp: clock@7c700000 { + compatible = "brcm,brcm2711-dvp"; + reg = <0x7c700000 0x10>; + clocks = <&clk_108MHz>; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + ddc0: i2c@7d508200 { + compatible = "brcm,brcmstb-i2c"; + reg = <0x7d508200 0x58>; + interrupt-parent = <&bsc_irq>; + interrupts = <1>; + clock-frequency = <97500>; + #address-cells = <1>; + #size-cells = <0>; + }; + + ddc1: i2c@7d508280 { + compatible = "brcm,brcmstb-i2c"; + reg = <0x7d508280 0x58>; + interrupt-parent = <&bsc_irq>; + interrupts = <2>; + clock-frequency = <97500>; + #address-cells = <1>; + #size-cells = <0>; + }; + + bsc_irq: interrupt-controller@7d508380 { + compatible = "brcm,bcm7271-l2-intc"; + reg = <0x7d508380 0x10>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <1>; + }; + + main_irq: interrupt-controller@7d508400 { + compatible = "brcm,bcm7271-l2-intc"; + reg = <0x7d508400 0x10>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <1>; + }; + + hdmi0: hdmi@7c701400 { + compatible = "brcm,bcm2712-hdmi0"; + reg = <0x7c701400 0x300>, + <0x7c701000 0x200>, + <0x7c701d00 0x300>, + <0x7c702000 0x80>, + <0x7c703800 0x200>, + <0x7c704000 0x800>, + <0x7c700100 0x80>, + <0x7d510800 0x100>, + <0x7c720000 0x100>; + reg-names = "hdmi", + "dvp", + "phy", + "rm", + "packet", + "metadata", + "csc", + "cec", + "hd"; + resets = <&dvp 1>; + interrupt-parent = <&aon_intr>; + interrupts = <1>, <2>, <3>, + <7>, <8>; + interrupt-names = "cec-tx", "cec-rx", "cec-low", + "hpd-connected", "hpd-removed"; + ddc = <&ddc0>; + }; + + hdmi1: hdmi@7c706400 { + compatible = "brcm,bcm2712-hdmi1"; + reg = <0x7c706400 0x300>, + <0x7c706000 0x200>, + <0x7c706d00 0x300>, + <0x7c707000 0x80>, + <0x7c708800 0x200>, + <0x7c709000 0x800>, + <0x7c700180 0x80>, + <0x7d511000 0x100>, + <0x7c720000 0x100>; + reg-names = "hdmi", + "dvp", + "phy", + "rm", + "packet", + "metadata", + "csc", + "cec", + "hd"; + resets = <&dvp 2>; + interrupt-parent = <&aon_intr>; + interrupts = <11>, <12>, <13>, + <14>, <15>; + interrupt-names = "cec-tx", "cec-rx", "cec-low", + "hpd-connected", "hpd-removed"; + ddc = <&ddc1>; + }; + }; + + axi: axi { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + + ranges = <0x00 0x00000000 0x00 0x00000000 0x10 0x00000000>, + <0x10 0x00000000 0x10 0x00000000 0x01 0x00000000>, + <0x14 0x00000000 0x14 0x00000000 0x04 0x00000000>, + <0x18 0x00000000 0x18 0x00000000 0x04 0x00000000>, + <0x1c 0x00000000 0x1c 0x00000000 0x04 0x00000000>; + + dma-ranges = <0x00 0x00000000 0x00 0x00000000 0x10 0x00000000>, + <0x10 0x00000000 0x10 0x00000000 0x01 0x00000000>, + <0x14 0x00000000 0x14 0x00000000 0x04 0x00000000>, + <0x18 0x00000000 0x18 0x00000000 0x04 0x00000000>, + <0x1c 0x00000000 0x1c 0x00000000 0x04 0x00000000>; + + vc4: gpu { + compatible = "brcm,bcm2712-vc6"; + }; }; timer { @@ -280,4 +441,26 @@ ; }; + + clk_27MHz: clk-27M { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <27000000>; + clock-output-names = "27MHz-clock"; + }; + + clk_108MHz: clk-108M { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <108000000>; + clock-output-names = "108MHz-clock"; + }; + + hvs: hvs@107c580000 { + compatible = "brcm,bcm2712-hvs"; + reg = <0x10 0x7c580000 0x0 0x1a000>; + interrupt-parent = <&disp_intr>; + interrupts = <2>, <9>, <16>; + interrupt-names = "ch0-eof", "ch1-eof", "ch2-eof"; + }; }; diff --git a/arch/arm64/boot/dts/broadcom/bcmbca/Makefile b/arch/arm64/boot/dts/broadcom/bcmbca/Makefile index 27741b71ba9e..9a8461d91c8c 100644 --- a/arch/arm64/boot/dts/broadcom/bcmbca/Makefile +++ b/arch/arm64/boot/dts/broadcom/bcmbca/Makefile @@ -2,6 +2,7 @@ dtb-$(CONFIG_ARCH_BCMBCA) += \ bcm4906-netgear-r8000p.dtb \ bcm4906-tplink-archer-c2300-v1.dtb \ + bcm4906-zyxel-ex3510b.dtb \ bcm4908-asus-gt-ac5300.dtb \ bcm4908-netgear-raxe500.dtb \ bcm94908.dtb \ diff --git a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4906-netgear-r8000p.dts b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4906-netgear-r8000p.dts index 999d93730240..a5f9ec92bd5e 100644 --- a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4906-netgear-r8000p.dts +++ b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4906-netgear-r8000p.dts @@ -144,16 +144,20 @@ #size-cells = <1>; partition@0 { - compatible = "nvmem-cells"; label = "cferom"; reg = <0x0 0x100000>; - #address-cells = <1>; #size-cells = <1>; ranges = <0 0x0 0x100000>; - base_mac_addr: mac@106a0 { - reg = <0x106a0 0x6>; + nvmem-layout { + compatible = "fixed-layout"; + #address-cells = <1>; + #size-cells = <1>; + + base_mac_addr: mac@106a0 { + reg = <0x106a0 0x6>; + }; }; }; diff --git a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4906-zyxel-ex3510b.dts b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4906-zyxel-ex3510b.dts new file mode 100644 index 000000000000..54e453bd09f7 --- /dev/null +++ b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4906-zyxel-ex3510b.dts @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0-or-later OR MIT + +#include +#include +#include + +#include "bcm4906.dtsi" + +/ { + compatible = "zyxel,ex3510b", "brcm,bcm4906", "brcm,bcm4908", "brcm,bcmbca"; + model = "Zyxel EX3510-B"; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x0 0x0 0x20000000>; + }; + + gpio-keys-polled { + compatible = "gpio-keys-polled"; + poll-interval = <100>; + + key-wps { + label = "WPS"; + linux,code = ; + gpios = <&gpio0 22 GPIO_ACTIVE_LOW>; + }; + + key-reset { + label = "Reset"; + linux,code = ; + gpios = <&gpio0 23 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&leds { + pinctrl-0 = <&pins_led_0_a>, <&pins_led_2_a>, <&pins_led_3_a>, + <&pins_led_4_a>, <&pins_led_10_a>, <&pins_led_12_a>, + <&pins_led_14_a>, <&pins_led_15_a>, <&pins_led_21_a>; + pinctrl-names = "default"; + + led@0 { + reg = <0x0>; + function = LED_FUNCTION_POWER; + color = ; + }; + + led@2 { + reg = <0x2>; + function = LED_FUNCTION_WAN_ONLINE; + color = ; + }; + + led@3 { + reg = <0x3>; + function = LED_FUNCTION_WAN_ONLINE; + color = ; + }; + + led@4 { + reg = <0x4>; + function = LED_FUNCTION_USB; + color = ; + trigger-sources = <&ohci_port1>, <&ohci_port2>, + <&ehci_port1>, <&ehci_port2>, + <&xhci_port1>, <&xhci_port2>; + linux,default-trigger = "usbport"; + }; + + led@a { + reg = <0xa>; + function = LED_FUNCTION_POWER; + color = ; + linux,default-trigger = "default-on"; + }; + + led@c { + reg = <0xc>; + function = LED_FUNCTION_LAN; + color = ; + active-low; + }; + + led@e { + reg = <0xe>; + function = LED_FUNCTION_WPS; + color = ; + active-low; + }; + + led@f { + reg = <0xf>; + function = LED_FUNCTION_WPS; + color = ; + active-low; + }; + + led@15 { + reg = <0x15>; + function = LED_FUNCTION_WAN; + color = ; + active-low; + }; +}; + +&enet { + nvmem-cells = <&base_mac_addr>; + nvmem-cell-names = "mac-address"; +}; + +&usb_phy { + brcm,ioc = <1>; + brcm,ipp = <1>; + status = "okay"; +}; + +&ehci { + status = "okay"; +}; + +&ohci { + status = "okay"; +}; + +&xhci { + status = "okay"; +}; + +&ports { + port@0 { + label = "lan1"; + }; + + port@1 { + label = "lan2"; + }; + + port@2 { + label = "lan3"; + }; + + port@3 { + label = "lan4"; + }; + + port@7 { + reg = <7>; + phy-mode = "internal"; + phy-handle = <&phy12>; + label = "wan"; + }; +}; + +&nand_controller { + status = "okay"; +}; + +&nandcs { + brcm,nand-oob-sector-size = <27>; + nand-ecc-strength = <8>; + nand-ecc-step-size = <512>; + nand-on-flash-bbt; + + #address-cells = <1>; + #size-cells = <0>; + + partitions { + compatible = "brcm,bcm4908-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + compatible = "nvmem-cells"; + label = "cferom"; + reg = <0x0 0x100000>; + read-only; + + #address-cells = <1>; + #size-cells = <1>; + + base_mac_addr: mac@106a0 { + reg = <0x106a0 0x6>; + }; + }; + + partition@100000 { + compatible = "brcm,bcm4908-firmware"; + reg = <0x100000 0x5f80000>; + }; + + partition@6080000 { + compatible = "brcm,bcm4908-firmware"; + reg = <0x6080000 0x5f80000>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi index 8b924812322c..613ba7ee43d6 100644 --- a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi @@ -30,7 +30,7 @@ compatible = "brcm,brahma-b53"; reg = <0x0>; enable-method = "spin-table"; - cpu-release-addr = <0x0 0xfff8>; + cpu-release-addr = <0x0 0xff8>; next-level-cache = <&l2>; }; @@ -39,7 +39,7 @@ compatible = "brcm,brahma-b53"; reg = <0x1>; enable-method = "spin-table"; - cpu-release-addr = <0x0 0xfff8>; + cpu-release-addr = <0x0 0xff8>; next-level-cache = <&l2>; }; @@ -48,7 +48,7 @@ compatible = "brcm,brahma-b53"; reg = <0x2>; enable-method = "spin-table"; - cpu-release-addr = <0x0 0xfff8>; + cpu-release-addr = <0x0 0xff8>; next-level-cache = <&l2>; }; @@ -57,7 +57,7 @@ compatible = "brcm,brahma-b53"; reg = <0x3>; enable-method = "spin-table"; - cpu-release-addr = <0x0 0xfff8>; + cpu-release-addr = <0x0 0xff8>; next-level-cache = <&l2>; }; @@ -68,6 +68,16 @@ }; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + cfe-stub@0 { + reg = <0x0 0x0 0x0 0x1000>; + }; + }; + axi@81000000 { compatible = "simple-bus"; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/northstar2/ns2-svk.dts index f43cfe66b6af..5939d342aec7 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2-svk.dts +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2-svk.dts @@ -137,7 +137,6 @@ spi-cpha; spi-cpol; pl022,interface = <0>; - pl022,slave-tx-disable = <0>; pl022,com-mode = <0>; pl022,rx-level-trig = <1>; pl022,tx-level-trig = <1>; @@ -200,7 +199,6 @@ }; &qspi { - bspi-sel = <0>; flash: flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2-xmc.dts b/arch/arm64/boot/dts/broadcom/northstar2/ns2-xmc.dts index c50df1d02797..0e134a94e142 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2-xmc.dts +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2-xmc.dts @@ -151,7 +151,6 @@ #size-cells = <1>; compatible = "m25p80"; spi-max-frequency = <62500000>; - m25p,default-addr-width = <3>; reg = <0x0 0x0>; partition@0 { diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi index cfd9fd23a1c2..5a4b81faff20 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi @@ -134,7 +134,6 @@ brcm,pcie-ob; brcm,pcie-ob-oarr-size; brcm,pcie-ob-axi-offset = <0x00000000>; - brcm,pcie-ob-window-size = <256>; status = "disabled"; @@ -165,7 +164,6 @@ brcm,pcie-ob; brcm,pcie-ob-oarr-size; brcm,pcie-ob-axi-offset = <0x30000000>; - brcm,pcie-ob-window-size = <256>; status = "disabled"; diff --git a/arch/arm64/boot/dts/exynos/Makefile b/arch/arm64/boot/dts/exynos/Makefile index 7a934499b235..f6f4bc650a94 100644 --- a/arch/arm64/boot/dts/exynos/Makefile +++ b/arch/arm64/boot/dts/exynos/Makefile @@ -8,6 +8,10 @@ dtb-$(CONFIG_ARCH_EXYNOS) += \ exynos7885-jackpotlte.dtb \ exynos850-e850-96.dtb \ exynos8895-dreamlte.dtb \ + exynos9810-starlte.dtb \ exynos990-c1s.dtb \ + exynos990-r8s.dtb \ + exynos990-x1s.dtb \ + exynos990-x1slte.dtb \ exynosautov9-sadk.dtb \ exynosautov920-sadk.dtb diff --git a/arch/arm64/boot/dts/exynos/exynos850-e850-96.dts b/arch/arm64/boot/dts/exynos/exynos850-e850-96.dts index f074df8982b3..7d70a32e75b2 100644 --- a/arch/arm64/boot/dts/exynos/exynos850-e850-96.dts +++ b/arch/arm64/boot/dts/exynos/exynos850-e850-96.dts @@ -45,17 +45,9 @@ }; }; - /* - * RAM: 4 GiB (eMCP): - * - 2 GiB at 0x80000000 - * - 2 GiB at 0x880000000 - * - * 0xbab00000..0xbfffffff: secure memory (85 MiB). - */ memory@80000000 { device_type = "memory"; - reg = <0x0 0x80000000 0x3ab00000>, - <0x0 0xc0000000 0x40000000>, + reg = <0x0 0x80000000 0x80000000>, <0x8 0x80000000 0x80000000>; }; @@ -146,6 +138,11 @@ #size-cells = <1>; ranges; + secure_mem: memory@bab00000 { + reg = <0x0 0xbab00000 0x5500000>; + no-map; + }; + ramoops@f0000000 { compatible = "ramoops"; reg = <0x0 0xf0000000 0x200000>; diff --git a/arch/arm64/boot/dts/exynos/exynos8895.dtsi b/arch/arm64/boot/dts/exynos/exynos8895.dtsi index 9f9ac5359879..36657abfc615 100644 --- a/arch/arm64/boot/dts/exynos/exynos8895.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos8895.dtsi @@ -38,7 +38,17 @@ <&cpu3>; }; - /* There's no PMU model for the Mongoose cores */ + mongoose-m2-pmu { + compatible = "samsung,mongoose-pmu"; + interrupts = , + , + , + ; + interrupt-affinity = <&cpu4>, + <&cpu5>, + <&cpu6>, + <&cpu7>; + }; cpus { #address-cells = <1>; @@ -218,6 +228,19 @@ "usi1", "usi2", "usi3"; }; + serial_0: serial@10430000 { + compatible = "samsung,exynos8895-uart"; + reg = <0x10430000 0x100>; + clocks = <&cmu_peric0 CLK_GOUT_PERIC0_UART_DBG_PCLK>, + <&cmu_peric0 CLK_GOUT_PERIC0_UART_DBG_EXT_UCLK>; + clock-names = "uart", "clk_uart_baud0"; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&uart0_bus>; + samsung,uart-fifosize = <256>; + status = "disabled"; + }; + pinctrl_peric0: pinctrl@104d0000 { compatible = "samsung,exynos8895-pinctrl"; reg = <0x104d0000 0x1000>; @@ -250,12 +273,69 @@ "usi10", "usi11", "usi12", "usi13"; }; + serial_1: serial@10830000 { + compatible = "samsung,exynos8895-uart"; + reg = <0x10830000 0x100>; + clocks = <&cmu_peric1 CLK_GOUT_PERIC1_UART_BT_PCLK>, + <&cmu_peric1 CLK_GOUT_PERIC1_UART_BT_EXT_UCLK>; + clock-names = "uart", "clk_uart_baud0"; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&uart1_bus>; + samsung,uart-fifosize = <256>; + status = "disabled"; + }; + pinctrl_peric1: pinctrl@10980000 { compatible = "samsung,exynos8895-pinctrl"; reg = <0x10980000 0x1000>; interrupts = ; }; + hsi2c_1: i2c@10990000 { + compatible = "samsung,exynos8895-hsi2c"; + reg = <0x10990000 0x1000>; + clocks = <&cmu_peric1 CLK_GOUT_PERIC1_HSI2C_CAM0_IPCLK>; + clock-names = "hsi2c"; + interrupts = ; + pinctrl-0 = <&hsi2c1_bus>; + pinctrl-names = "default"; + status = "disabled"; + }; + + hsi2c_2: i2c@109a0000 { + compatible = "samsung,exynos8895-hsi2c"; + reg = <0x109a0000 0x1000>; + clocks = <&cmu_peric1 CLK_GOUT_PERIC1_HSI2C_CAM1_IPCLK>; + clock-names = "hsi2c"; + interrupts = ; + pinctrl-0 = <&hsi2c2_bus>; + pinctrl-names = "default"; + status = "disabled"; + }; + + hsi2c_3: i2c@109b0000 { + compatible = "samsung,exynos8895-hsi2c"; + reg = <0x109b0000 0x1000>; + clocks = <&cmu_peric1 CLK_GOUT_PERIC1_HSI2C_CAM2_IPCLK>; + clock-names = "hsi2c"; + interrupts = ; + pinctrl-0 = <&hsi2c3_bus>; + pinctrl-names = "default"; + status = "disabled"; + }; + + hsi2c_4: i2c@109c0000 { + compatible = "samsung,exynos8895-hsi2c"; + reg = <0x109c0000 0x1000>; + clocks = <&cmu_peric1 CLK_GOUT_PERIC1_HSI2C_CAM3_IPCLK>; + clock-names = "hsi2c"; + interrupts = ; + pinctrl-0 = <&hsi2c4_bus>; + pinctrl-names = "default"; + status = "disabled"; + }; + spi_0: spi@109d0000 { compatible = "samsung,exynos8895-spi", "samsung,exynos850-spi"; diff --git a/arch/arm64/boot/dts/exynos/exynos9810-pinctrl.dtsi b/arch/arm64/boot/dts/exynos/exynos9810-pinctrl.dtsi new file mode 100644 index 000000000000..88091bf09e4e --- /dev/null +++ b/arch/arm64/boot/dts/exynos/exynos9810-pinctrl.dtsi @@ -0,0 +1,503 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Samsung's Exynos 9810 SoC pin-mux and pin-config device tree source + * + * Copyright (c) 2024 Markuss Broks + * Copyright (c) 2024 Maksym Holovach + */ + +#include "exynos-pinctrl.h" + +&pinctrl_alive { + etc1: etc1-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpa0: gpa0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + interrupt-parent = <&gic>; + interrupts = , + , + , + , + , + , + , + ; + #interrupt-cells = <2>; + }; + + gpa1: gpa1-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + interrupt-parent = <&gic>; + interrupts = , + , + , + , + , + , + , + ; + #interrupt-cells = <2>; + }; + + gpa2: gpa2-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + interrupt-parent = <&gic>; + interrupts = , + , + , + , + , + , + , + ; + #interrupt-cells = <2>; + }; + + gpa3: gpa3-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + interrupt-parent = <&gic>; + interrupts = , + , + , + , + , + , + , + ; + #interrupt-cells = <2>; + }; + + gpa4: gpa4-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpq0: gpq0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; +}; + +&pinctrl_aud { + gpb0: gpb0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpb1: gpb1-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpb2: gpb2-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; +}; + +&pinctrl_chub { + gph0: gph0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gph1: gph1-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; +}; + +&pinctrl_cmgp { + gpm0: gpm0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm1: gpm1-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm2: gpm2-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm3: gpm3-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm4: gpm4-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm5: gpm5-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm6: gpm6-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm7: gpm7-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm10: gpm10-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm11: gpm11-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm12: gpm12-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm13: gpm13-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm14: gpm14-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm15: gpm15-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm16: gpm16-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm17: gpm17-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm40: gpm40-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm41: gpm41-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm42: gpm42-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; + + gpm43: gpm43-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupts = ; + }; +}; + +&pinctrl_fsys0 { + gpf0: gpf0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; +}; + +&pinctrl_fsys1 { + gpf1: gpf1-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpf2: gpf2-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; +}; + +&pinctrl_peric0 { + gpg0: gpg0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpg1: gpg1-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpg2: gpg2-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpp0: gpp0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpp1: gpp1-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpp2: gpp2-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpp3: gpp3-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; +}; + +&pinctrl_peric1 { + gpc0: gpc0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpc1: gpc1-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpd0: gpd0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpg3: gpg3-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpp4: gpp4-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpp5: gpp5-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpp6: gpp6-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; +}; + +&pinctrl_vts { + gpt0: gpt0-gpio-bank { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; +}; diff --git a/arch/arm64/boot/dts/exynos/exynos9810-starlte.dts b/arch/arm64/boot/dts/exynos/exynos9810-starlte.dts new file mode 100644 index 000000000000..fc0ddfee4cd6 --- /dev/null +++ b/arch/arm64/boot/dts/exynos/exynos9810-starlte.dts @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Samsung Galaxy S9 (starlte/SM-G960F) device tree source + * + * Copyright (c) 2024 Markuss Broks + * Copyright (c) 2024 Maksym Holovach + */ + +/dts-v1/; +#include "exynos9810.dtsi" +#include +#include + +/ { + model = "Samsung Galaxy S9 (SM-G960F)"; + compatible = "samsung,starlte", "samsung,exynos9810"; + chassis-type = "handset"; + + chosen { + #address-cells = <2>; + #size-cells = <1>; + ranges; + + framebuffer@cc000000 { + compatible = "simple-framebuffer"; + reg = <0x0 0xcc000000 (1440 * 2960 * 4)>; + width = <1440>; + height = <2960>; + stride = <(1440 * 4)>; + format = "a8r8g8b8"; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-0 = <&key_power &key_voldown &key_volup &key_wink>; + pinctrl-names = "default"; + + power-key { + label = "Power"; + linux,code = ; + gpios = <&gpa2 4 GPIO_ACTIVE_LOW>; + wakeup-source; + }; + + voldown-key { + label = "Volume Down"; + linux,code = ; + gpios = <&gpa0 4 GPIO_ACTIVE_LOW>; + }; + + volup-key { + label = "Volume Up"; + linux,code = ; + gpios = <&gpa0 3 GPIO_ACTIVE_LOW>; + }; + + /* In stock firmware used for assistant. Map it as a camera button for now */ + wink-key { + label = "Camera"; + linux,code = ; + gpios = <&gpa0 6 GPIO_ACTIVE_LOW>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x3c800000>, + <0x0 0xc0000000 0x20000000>, + <0x0 0xe1900000 0x1e700000>, + <0x8 0x80000000 0x80000000>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <1>; + ranges; + + framebuffer@cc000000 { + reg = <0x0 0xcc000000 (1440 * 2960 * 4)>; + no-map; + }; + }; +}; + +&oscclk { + clock-frequency = <26000000>; +}; + +&pinctrl_alive { + key_power: key-power-pins { + samsung,pins = "gpa2-4"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; + + key_voldown: key-voldown-pins { + samsung,pins = "gpa0-4"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; + + key_volup: key-volup-pins { + samsung,pins = "gpa0-3"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; + + key_wink: key-wink-pins { + samsung,pins = "gpa0-6"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; +}; diff --git a/arch/arm64/boot/dts/exynos/exynos9810.dtsi b/arch/arm64/boot/dts/exynos/exynos9810.dtsi new file mode 100644 index 000000000000..01eba31f7ca3 --- /dev/null +++ b/arch/arm64/boot/dts/exynos/exynos9810.dtsi @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Samsung Exynos 9810 SoC device tree source + * + * Copyright (c) 2024 Markuss Broks + * Copyright (c) 2024 Maksym Holovach + */ + +#include + +/ { + compatible = "samsung,exynos9810"; + #address-cells = <2>; + #size-cells = <1>; + + interrupt-parent = <&gic>; + + aliases { + pinctrl0 = &pinctrl_alive; + pinctrl1 = &pinctrl_aud; + pinctrl2 = &pinctrl_chub; + pinctrl3 = &pinctrl_cmgp; + pinctrl4 = &pinctrl_fsys0; + pinctrl5 = &pinctrl_fsys1; + pinctrl6 = &pinctrl_peric0; + pinctrl7 = &pinctrl_peric1; + pinctrl8 = &pinctrl_vts; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + core1 { + cpu = <&cpu1>; + }; + core2 { + cpu = <&cpu2>; + }; + core3 { + cpu = <&cpu3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu4>; + }; + core1 { + cpu = <&cpu5>; + }; + core2 { + cpu = <&cpu6>; + }; + core3 { + cpu = <&cpu7>; + }; + }; + }; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0>; + enable-method = "psci"; + }; + + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x1>; + enable-method = "psci"; + }; + + cpu2: cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x2>; + enable-method = "psci"; + }; + + cpu3: cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x3>; + enable-method = "psci"; + }; + + cpu4: cpu@100 { + device_type = "cpu"; + compatible = "samsung,mongoose-m3"; + reg = <0x100>; + enable-method = "psci"; + }; + + cpu5: cpu@101 { + device_type = "cpu"; + compatible = "samsung,mongoose-m3"; + reg = <0x101>; + enable-method = "psci"; + }; + + cpu6: cpu@102 { + device_type = "cpu"; + compatible = "samsung,mongoose-m3"; + reg = <0x102>; + enable-method = "psci"; + }; + + cpu7: cpu@103 { + device_type = "cpu"; + compatible = "samsung,mongoose-m3"; + reg = <0x103>; + enable-method = "psci"; + }; + }; + + oscclk: osc-clock { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-output-names = "oscclk"; + }; + + pmu-a55 { + compatible = "arm,cortex-a55-pmu"; + interrupts = , + , + , + ; + interrupt-affinity = <&cpu0>, + <&cpu1>, + <&cpu2>, + <&cpu3>; + }; + + pmu-mongoose-m3 { + compatible = "samsung,mongoose-pmu"; + interrupts = , + , + , + ; + interrupt-affinity = <&cpu4>, + <&cpu5>, + <&cpu6>, + <&cpu7>; + }; + + psci { + compatible = "arm,psci"; + method = "smc"; + cpu_off = <0x84000002>; + cpu_on = <0xc4000003>; + cpu_suspend = <0xc4000001>; + }; + + soc: soc@0 { + compatible = "simple-bus"; + ranges = <0x0 0x0 0x0 0x20000000>; + + #address-cells = <1>; + #size-cells = <1>; + + chipid@10000000 { + compatible = "samsung,exynos9810-chipid", + "samsung,exynos850-chipid"; + reg = <0x10000000 0x100>; + }; + + gic: interrupt-controller@10101000 { + compatible = "arm,gic-400"; + reg = <0x10101000 0x1000>, + <0x10102000 0x1000>, + <0x10104000 0x2000>, + <0x10106000 0x2000>; + #interrupt-cells = <3>; + interrupt-controller; + interrupts = ; + #address-cells = <0>; + #size-cells = <1>; + }; + + pinctrl_peric0: pinctrl@10430000 { + compatible = "samsung,exynos9810-pinctrl"; + reg = <0x10430000 0x1000>; + interrupts = ; + }; + + pinctrl_peric1: pinctrl@10830000 { + compatible = "samsung,exynos9810-pinctrl"; + reg = <0x10830000 0x1000>; + interrupts = ; + }; + + pinctrl_fsys0: pinctrl@11050000 { + compatible = "samsung,exynos9810-pinctrl"; + reg = <0x11050000 0x1000>; + interrupts = ; + }; + + pinctrl_fsys1: pinctrl@11430000 { + compatible = "samsung,exynos9810-pinctrl"; + reg = <0x11430000 0x1000>; + interrupts = ; + }; + + pinctrl_vts: pinctrl@13880000 { + compatible = "samsung,exynos9810-pinctrl"; + reg = <0x13880000 0x1000>; + }; + + pinctrl_chub: pinctrl@13a80000 { + compatible = "samsung,exynos9810-pinctrl"; + reg = <0x13a80000 0x1000>; + interrupts = ; + }; + + pinctrl_alive: pinctrl@14050000 { + compatible = "samsung,exynos9810-pinctrl"; + reg = <0x14050000 0x1000>; + + wakeup-interrupt-controller { + compatible = "samsung,exynos9810-wakeup-eint", + "samsung,exynos850-wakeup-eint", + "samsung,exynos7-wakeup-eint"; + }; + }; + + pmu_system_controller: system-controller@14060000 { + compatible = "samsung,exynos9810-pmu", + "samsung,exynos7-pmu", "syscon"; + reg = <0x14060000 0x10000>; + }; + + pinctrl_cmgp: pinctrl@14220000 { + compatible = "samsung,exynos9810-pinctrl"; + reg = <0x14220000 0x1000>; + + wakeup-interrupt-controller { + compatible = "samsung,exynos9810-wakeup-eint", + "samsung,exynos850-wakeup-eint", + "samsung,exynos7-wakeup-eint"; + }; + }; + + pinctrl_aud: pinctrl@17c60000 { + compatible = "samsung,exynos9810-pinctrl"; + reg = <0x17c60000 0x1000>; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + /* Hypervisor Virtual Timer interrupt is not wired to GIC */ + interrupts = , + , + , + ; + /* + * Non-updatable, broken stock Samsung bootloader does not + * configure CNTFRQ_EL0 + */ + clock-frequency = <26000000>; + }; +}; + +#include "exynos9810-pinctrl.dtsi" +#include "arm/samsung/exynos-syscon-restart.dtsi" diff --git a/arch/arm64/boot/dts/exynos/exynos990-r8s.dts b/arch/arm64/boot/dts/exynos/exynos990-r8s.dts new file mode 100644 index 000000000000..6bae3c0ecc1c --- /dev/null +++ b/arch/arm64/boot/dts/exynos/exynos990-r8s.dts @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Samsung Galaxy S20 FE (r8s/SM-G780F) device tree source + * + * Copyright (c) 2024, Denzeel Oliva + */ + +/dts-v1/; +#include "exynos990.dtsi" +#include +#include +#include + +/ { + model = "Samsung Galaxy S20 FE"; + compatible = "samsung,r8s", "samsung,exynos990"; + + #address-cells = <2>; + #size-cells = <2>; + + chosen { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + framebuffer0: framebuffer@f1000000 { + compatible = "simple-framebuffer"; + reg = <0 0xf1000000 0 (1080 * 2400 * 4)>; + width = <1080>; + height = <2400>; + stride = <(1080 * 4)>; + format = "a8r8g8b8"; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x3ab00000>, + /* Memory hole */ + <0x0 0xc1200000 0x0 0x1ee00000>, + /* Memory hole */ + <0x0 0xe1900000 0x0 0x1e700000>, + /* Memory hole - last block */ + <0x8 0x80000000 0x0 0xc0000000>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + cont_splash_mem: framebuffer@f1000000 { + reg = <0 0xf1000000 0 0x13c6800>; + no-map; + }; + + abox_reserved: audio@f7fb0000 { + reg = <0 0xf7fb0000 0 0x2a50000>; + no-map; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-0 = <&key_power &key_voldown &key_volup>; + pinctrl-names = "default"; + + power-key { + label = "Power"; + linux,code = ; + gpios = <&gpa2 4 GPIO_ACTIVE_LOW>; + wakeup-source; + }; + + voldown-key { + label = "Volume Down"; + linux,code = ; + gpios = <&gpa0 4 GPIO_ACTIVE_LOW>; + }; + + volup-key { + label = "Volume Up"; + linux,code = ; + gpios = <&gpa0 3 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&oscclk { + clock-frequency = <26000000>; +}; + +&pinctrl_alive { + key_power: key-power-pins { + samsung,pins = "gpa2-4"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; + + key_voldown: key-voldown-pins { + samsung,pins = "gpa0-4"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; + + key_volup: key-volup-pins { + samsung,pins = "gpa0-3"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; +}; diff --git a/arch/arm64/boot/dts/exynos/exynos990-x1s-common.dtsi b/arch/arm64/boot/dts/exynos/exynos990-x1s-common.dtsi new file mode 100644 index 000000000000..55fa8e9e05db --- /dev/null +++ b/arch/arm64/boot/dts/exynos/exynos990-x1s-common.dtsi @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Samsung Galaxy S20 Series device tree source + * + * Copyright (c) 2024, Umer Uddin + */ + +/dts-v1/; +#include "exynos990.dtsi" +#include +#include +#include + +/ { + chosen { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + framebuffer0: framebuffer@f1000000 { + compatible = "simple-framebuffer"; + reg = <0 0xf1000000 0 (1440 * 3200 * 4)>; + width = <1440>; + height = <3200>; + stride = <(1440 * 4)>; + format = "a8r8g8b8"; + }; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + cont_splash_mem: framebuffer@f1000000 { + reg = <0 0xf1000000 0 0x1194000>; + no-map; + }; + + abox_reserved: audio@f7fb0000 { + reg = <0 0xf7fb0000 0 0x2a50000>; + no-map; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-0 = <&key_power &key_voldown &key_volup>; + pinctrl-names = "default"; + + power-key { + label = "Power"; + linux,code = ; + gpios = <&gpa2 4 GPIO_ACTIVE_LOW>; + wakeup-source; + }; + + voldown-key { + label = "Volume Down"; + linux,code = ; + gpios = <&gpa0 4 GPIO_ACTIVE_LOW>; + }; + + volup-key { + label = "Volume Up"; + linux,code = ; + gpios = <&gpa0 3 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&oscclk { + clock-frequency = <26000000>; +}; + +&pinctrl_alive { + key_power: key-power-pins { + samsung,pins = "gpa2-4"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; + + key_voldown: key-voldown-pins { + samsung,pins = "gpa0-4"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; + + key_volup: key-volup-pins { + samsung,pins = "gpa0-3"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; +}; diff --git a/arch/arm64/boot/dts/exynos/exynos990-x1s.dts b/arch/arm64/boot/dts/exynos/exynos990-x1s.dts new file mode 100644 index 000000000000..1ae881015e0c --- /dev/null +++ b/arch/arm64/boot/dts/exynos/exynos990-x1s.dts @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Samsung Galaxy S20 5G (x1s/SM-G981B) device tree source + * + * Copyright (c) 2024, Umer Uddin + */ + +/dts-v1/; +#include "exynos990-x1s-common.dtsi" + +/ { + #address-cells = <2>; + #size-cells = <2>; + + model = "Samsung Galaxy S20 5G"; + compatible = "samsung,x1s", "samsung,exynos990"; + + memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x3ab00000>, + /* Memory hole */ + <0x0 0xc1200000 0x0 0x1ee00000>, + /* Memory hole */ + <0x0 0xe1900000 0x0 0x1e700000>, + /* Memory hole */ + <0x8 0x80000000 0x2 0x7e800000>; + }; +}; diff --git a/arch/arm64/boot/dts/exynos/exynos990-x1slte.dts b/arch/arm64/boot/dts/exynos/exynos990-x1slte.dts new file mode 100644 index 000000000000..d3720996ba93 --- /dev/null +++ b/arch/arm64/boot/dts/exynos/exynos990-x1slte.dts @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Samsung Galaxy S20 (x1slte/SM-G980F) device tree source + * + * Copyright (c) 2024, Umer Uddin + */ + +/dts-v1/; +#include "exynos990-x1s-common.dtsi" + +/ { + #address-cells = <2>; + #size-cells = <2>; + + model = "Samsung Galaxy S20"; + compatible = "samsung,x1slte", "samsung,exynos990"; + + memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x3ab00000>, + /* Memory hole */ + <0x0 0xc1200000 0x0 0x1ee00000>, + /* Memory hole */ + <0x0 0xe1900000 0x0 0x1e700000>, + /* Memory hole */ + <0x8 0x80000000 0x1 0x7ec00000>; + }; +}; diff --git a/arch/arm64/boot/dts/exynos/exynos990.dtsi b/arch/arm64/boot/dts/exynos/exynos990.dtsi index c1986f00e443..9d017dbed952 100644 --- a/arch/arm64/boot/dts/exynos/exynos990.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos990.dtsi @@ -5,6 +5,7 @@ * Copyright (c) 2024, Igor Belwon */ +#include #include / { @@ -46,7 +47,14 @@ <&cpu5>; }; - /* There's no PMU model for cluster2, which are the Mongoose cores. */ + mongoose-m5-pmu { + compatible = "samsung,mongoose-pmu"; + interrupts = , + ; + + interrupt-affinity = <&cpu6>, + <&cpu7>; + }; cpus { #address-cells = <1>; @@ -199,6 +207,23 @@ interrupts = ; }; + cmu_hsi0: clock-controller@10a00000 { + compatible = "samsung,exynos990-cmu-hsi0"; + reg = <0x10a00000 0x8000>; + #clock-cells = <1>; + + clocks = <&oscclk>, + <&cmu_top CLK_DOUT_CMU_HSI0_BUS>, + <&cmu_top CLK_DOUT_CMU_HSI0_USB31DRD>, + <&cmu_top CLK_DOUT_CMU_HSI0_USBDP_DEBUG>, + <&cmu_top CLK_DOUT_CMU_HSI0_DPGTC>; + clock-names = "oscclk", + "bus", + "usb31drd", + "usbdp_debug", + "dpgtc"; + }; + pinctrl_hsi1: pinctrl@13040000 { compatible = "samsung,exynos990-pinctrl"; reg = <0x13040000 0x1000>; @@ -227,10 +252,33 @@ }; }; + pmu_system_controller: system-controller@15860000 { + compatible = "samsung,exynos990-pmu", + "samsung,exynos7-pmu", "syscon"; + reg = <0x15860000 0x10000>; + + reboot: syscon-reboot { + compatible = "syscon-reboot"; + regmap = <&pmu_system_controller>; + offset = <0x3a00>; /* SWRESET */ + mask = <0x2>; /* SWRESET_TRIGGER */ + value = <0x2>; + }; + }; + pinctrl_cmgp: pinctrl@15c30000 { compatible = "samsung,exynos990-pinctrl"; reg = <0x15c30000 0x1000>; }; + + cmu_top: clock-controller@1a330000 { + compatible = "samsung,exynos990-cmu-top"; + reg = <0x1a330000 0x8000>; + #clock-cells = <1>; + + clocks = <&oscclk>; + clock-names = "oscclk"; + }; }; timer { diff --git a/arch/arm64/boot/dts/exynos/exynosautov920.dtsi b/arch/arm64/boot/dts/exynos/exynosautov920.dtsi index c759134c909e..eb446cdc4ab6 100644 --- a/arch/arm64/boot/dts/exynos/exynosautov920.dtsi +++ b/arch/arm64/boot/dts/exynos/exynosautov920.dtsi @@ -183,6 +183,26 @@ "noc"; }; + watchdog_cl0: watchdog@10060000 { + compatible = "samsung,exynosautov920-wdt"; + reg = <0x10060000 0x100>; + interrupts = ; + clocks = <&xtcxo>, <&xtcxo>; + clock-names = "watchdog", "watchdog_src"; + samsung,syscon-phandle = <&pmu_system_controller>; + samsung,cluster-index = <0>; + }; + + watchdog_cl1: watchdog@10070000 { + compatible = "samsung,exynosautov920-wdt"; + reg = <0x10070000 0x100>; + interrupts = ; + clocks = <&xtcxo>, <&xtcxo>; + clock-names = "watchdog", "watchdog_src"; + samsung,syscon-phandle = <&pmu_system_controller>; + samsung,cluster-index = <1>; + }; + gic: interrupt-controller@10400000 { compatible = "arm,gic-v3"; #interrupt-cells = <3>; @@ -193,6 +213,69 @@ interrupts = ; }; + spdma0: dma-controller@10180000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x10180000 0x1000>; + interrupts = ; + clocks = <&cmu_misc CLK_MOUT_MISC_NOC_USER>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + }; + + spdma1: dma-controller@10190000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x10190000 0x1000>; + interrupts = ; + clocks = <&cmu_misc CLK_MOUT_MISC_NOC_USER>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + }; + + pdma0: dma-controller@101a0000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x101a0000 0x1000>; + interrupts = ; + clocks = <&cmu_misc CLK_MOUT_MISC_NOC_USER>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + }; + + pdma1: dma-controller@101b0000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x101b0000 0x1000>; + interrupts = ; + clocks = <&cmu_misc CLK_MOUT_MISC_NOC_USER>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + }; + + pdma2: dma-controller@101c0000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x101c0000 0x1000>; + interrupts = ; + clocks = <&cmu_misc CLK_MOUT_MISC_NOC_USER>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + }; + + pdma3: dma-controller@101d0000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x101d0000 0x1000>; + interrupts = ; + clocks = <&cmu_misc CLK_MOUT_MISC_NOC_USER>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + }; + + pdma4: dma-controller@101e0000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x101e0000 0x1000>; + interrupts = ; + clocks = <&cmu_misc CLK_MOUT_MISC_NOC_USER>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + }; + cmu_peric0: clock-controller@10800000 { compatible = "samsung,exynosautov920-cmu-peric0"; reg = <0x10800000 0x8000>; diff --git a/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts b/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts index 387fb779bd29..e58881c61d53 100644 --- a/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts +++ b/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts @@ -10,6 +10,7 @@ #include #include +#include #include "gs101-pinctrl.h" #include "gs101.dtsi" @@ -90,6 +91,89 @@ &hsi2c_12 { status = "okay"; /* TODO: add the devices once drivers exist */ + + usb-typec@25 { + compatible = "maxim,max77759-tcpci", "maxim,max33359"; + reg = <0x25>; + interrupts-extended = <&gpa8 2 IRQ_TYPE_LEVEL_LOW>; + pinctrl-0 = <&typec_int>; + pinctrl-names = "default"; + + connector { + compatible = "usb-c-connector"; + label = "USB-C"; + data-role = "dual"; + power-role = "dual"; + self-powered; + try-power-role = "sink"; + op-sink-microwatt = <2600000>; + slow-charger-loop; + /* + * max77759 operating in reverse boost mode (0xA) can + * source up to 1.5A while extboost can only do ~1A. + * Since extboost is the primary path, advertise 900mA. + */ + source-pdos = ; + sink-pdos = ; + sink-vdos = ; + sink-vdos-v1 = ; + /* + * Until bootloader is updated to set those two when + * console is enabled, we disable PD here. + */ + pd-disable; + typec-power-opmode = "default"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + usbc0_orien_sw: endpoint { + remote-endpoint = <&usbdrd31_phy_orien_switch>; + }; + }; + + port@1 { + reg = <1>; + + usbc0_role_sw: endpoint { + remote-endpoint = <&usbdrd31_dwc3_role_switch>; + }; + }; + }; + }; + }; }; &pinctrl_far_alive { @@ -106,6 +190,13 @@ samsung,pin-pud = ; samsung,pin-drv = ; }; + + typec_int: typec-int-pins { + samsung,pins = "gpa8-2"; + samsung,pin-function = ; + samsung,pin-pud = ; + samsung,pin-drv = ; + }; }; &pinctrl_gpio_alive { @@ -142,9 +233,16 @@ role-switch-default-mode = "peripheral"; maximum-speed = "super-speed-plus"; status = "okay"; + + port { + usbdrd31_dwc3_role_switch: endpoint { + remote-endpoint = <&usbc0_role_sw>; + }; + }; }; &usbdrd31_phy { + orientation-switch; /* TODO: Update these once PMIC is implemented */ pll-supply = <®_placeholder>; dvdd-usb20-supply = <®_placeholder>; @@ -153,6 +251,12 @@ vdda-usbdp-supply = <®_placeholder>; vddh-usbdp-supply = <®_placeholder>; status = "okay"; + + port { + usbdrd31_phy_orien_switch: endpoint { + remote-endpoint = <&usbc0_orien_sw>; + }; + }; }; &usi_uart { diff --git a/arch/arm64/boot/dts/exynos/google/gs101.dtsi b/arch/arm64/boot/dts/exynos/google/gs101.dtsi index 302c5beb224a..c5335dd59dfe 100644 --- a/arch/arm64/boot/dts/exynos/google/gs101.dtsi +++ b/arch/arm64/boot/dts/exynos/google/gs101.dtsi @@ -1267,7 +1267,7 @@ usbdrd31_phy: phy@11100000 { compatible = "google,gs101-usb31drd-phy"; - reg = <0x11100000 0x0100>, + reg = <0x11100000 0x0200>, <0x110f0000 0x0800>, <0x110e0000 0x2800>; reg-names = "phy", "pcs", "pma"; @@ -1302,6 +1302,9 @@ interrupts = ; phys = <&usbdrd31_phy 0>, <&usbdrd31_phy 1>; phy-names = "usb2-phy", "usb3-phy"; + snps,has-lpm-erratum; + snps,dis_u2_susphy_quirk; + snps,dis_u3_susphy_quirk; status = "disabled"; }; }; diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile index 42e6482a31cb..839432153cc7 100644 --- a/arch/arm64/boot/dts/freescale/Makefile +++ b/arch/arm64/boot/dts/freescale/Makefile @@ -165,6 +165,11 @@ imx8mn-tqma8mqnl-mba8mx-usbotg-dtbs += imx8mn-tqma8mqnl-mba8mx.dtb imx8mn-tqma8m dtb-$(CONFIG_ARCH_MXC) += imx8mn-tqma8mqnl-mba8mx-lvds-tm070jvhg33.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mn-tqma8mqnl-mba8mx-usbotg.dtb +dtb-$(CONFIG_ARCH_MXC) += imx8mp-aristainetos3-adpismarc.dtb +dtb-$(CONFIG_ARCH_MXC) += imx8mp-aristainetos3-helios.dtb +imx8mp-aristainetos3-helios-lvds-dtbs += imx8mp-aristainetos3-helios.dtb imx8mp-aristainetos3-helios-lvds.dtbo +dtb-$(CONFIG_ARCH_MXC) += imx8mp-aristainetos3-helios-lvds.dtb +dtb-$(CONFIG_ARCH_MXC) += imx8mp-aristainetos3-proton2s.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mp-beacon-kit.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mp-data-modul-edm-sbc.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mp-debix-model-a.dtb @@ -211,8 +216,16 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-wifi-ivy.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-wifi-mallow.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mp-verdin-wifi-yavia.dtb +imx8mp-evk-lvds0-imx-dlvds-hdmi-channel0-dtbs += imx8mp-evk.dtb imx8mp-evk-lvds0-imx-dlvds-hdmi-channel0.dtbo +imx8mp-evk-lvds0-imx-lvds-hdmi-dtbs += imx8mp-evk.dtb imx8mp-evk-lvds0-imx-lvds-hdmi.dtbo +imx8mp-evk-lvds1-imx-dlvds-hdmi-channel0-dtbs += imx8mp-evk.dtb imx8mp-evk-lvds1-imx-dlvds-hdmi-channel0.dtbo +imx8mp-evk-lvds1-imx-lvds-hdmi-dtbs += imx8mp-evk.dtb imx8mp-evk-lvds1-imx-lvds-hdmi.dtbo imx8mp-evk-mx8-dlvds-lcd1-dtbs += imx8mp-evk.dtb imx8mp-evk-mx8-dlvds-lcd1.dtbo imx8mp-evk-pcie-ep-dtbs += imx8mp-evk.dtb imx8mp-evk-pcie-ep.dtbo +dtb-$(CONFIG_ARCH_MXC) += imx8mp-evk-lvds0-imx-dlvds-hdmi-channel0.dtb +dtb-$(CONFIG_ARCH_MXC) += imx8mp-evk-lvds0-imx-lvds-hdmi.dtb +dtb-$(CONFIG_ARCH_MXC) += imx8mp-evk-lvds1-imx-dlvds-hdmi-channel0.dtb +dtb-$(CONFIG_ARCH_MXC) += imx8mp-evk-lvds1-imx-lvds-hdmi.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mp-evk-mx8-dlvds-lcd1.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mp-evk-pcie-ep.dtb diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi index a60ebb718789..c32a6947ae9c 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi @@ -165,7 +165,7 @@ audio_subsys: bus@59000000 { }; esai0: esai@59010000 { - compatible = "fsl,imx8qm-esai"; + compatible = "fsl,imx8qm-esai", "fsl,imx6ull-esai"; reg = <0x59010000 0x10000>; interrupts = ; clocks = <&esai0_lpcg IMX_LPCG_CLK_4>, diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phg.dts b/arch/arm64/boot/dts/freescale/imx8mm-phg.dts index 75bbedc6164c..a134b1833649 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-phg.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-phg.dts @@ -82,7 +82,7 @@ }; panel { - compatible = "panel-lvds"; + compatible = "auo,g084sn05", "panel-lvds"; width-mm = <170>; height-mm = <28>; data-mapping = "jeida-18"; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-display.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-display.dtsi index 7675583a6b67..98dec3c42060 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-display.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2-display.dtsi @@ -4,6 +4,34 @@ */ / { + chosen { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + framebuffer-panel0 { + compatible = "simple-framebuffer"; + clocks = <&clk IMX8MN_CLK_DISP_PIXEL_ROOT>, /* lcdif */ + <&clk IMX8MN_CLK_DISP_APB_ROOT>, + <&clk IMX8MN_CLK_DISP_AXI_ROOT>, + <&clk IMX8MN_VIDEO_PLL1>, + <&clk IMX8MN_CLK_DISP_AXI_ROOT>, /* pgc_dispmix */ + <&clk IMX8MN_CLK_DISP_APB_ROOT>, + <&clk IMX8MN_CLK_DISP_AXI>, + <&clk IMX8MN_CLK_DISP_APB>, + <&clk IMX8MN_SYS_PLL2_1000M>, + <&clk IMX8MN_SYS_PLL1_800M>, + <&clk IMX8MN_CLK_DSI_CORE>, /* mipi_disi */ + <&clk IMX8MN_CLK_DSI_PHY_REF>; + + power-domains = <&disp_blk_ctrl IMX8MN_DISPBLK_PD_LCDIF>, + <&disp_blk_ctrl IMX8MN_DISPBLK_PD_MIPI_DSI>; + dvdd-supply = <®_3v3_dvdd>; + avdd-supply = <®_v3v3_avdd>; + status = "disabled"; + }; + }; + backlight: backlight { compatible = "pwm-backlight"; pwms = <&pwm1 0 700000 0>; /* 700000 ns = 1337Hz */ diff --git a/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-adpismarc.dts b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-adpismarc.dts new file mode 100644 index 000000000000..6a688510dad9 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-adpismarc.dts @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright (C) 2024 Heiko Schocher + */ + +/dts-v1/; + +#include +#include +#include "imx8mp-aristainetos3a-som-v1.dtsi" + +&{/} { + model = "Aristainetos3 ADLink PI SMARC carrier"; + compatible = "abb,imx8mp-aristanetos3-adpismarc", + "abb,imx8mp-aristanetos3-som", + "fsl,imx8mp"; +}; + +&flexcan1 { + status = "okay"; +}; + +&i2c2 { + gpio8: pinctrl@3e { + compatible = "semtech,sx1509q"; + reg = <0x3e>; + + #gpio-cells = <2>; + #interrupt-cells = <2>; + semtech,probe-reset; + gpio-controller; + interrupt-controller; + interrupt-parent = <&gpio6>; + interrupts = <1 IRQ_TYPE_EDGE_FALLING>; + }; + +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-helios-lvds.dtso b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-helios-lvds.dtso new file mode 100644 index 000000000000..9d1f3b4ccc79 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-helios-lvds.dtso @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright (C) 2024 Heiko Schocher + */ +#include +#include +#include +#include + +/dts-v1/; +/plugin/; + +&{/} { + model = "Aristainetos3 helios carrier with LVDS"; + compatible = "abb,imx8mp-aristanetos3-helios", + "abb,imx8mp-aristanetos3-som", + "fsl,imx8mp"; + + panel_lvds: panel-lvds { + compatible = "lg,lb070wv8"; + power-supply = <®_vcc_disp>; + backlight = <&lvds_backlight>; + + port { + in_lvds0: endpoint { + remote-endpoint = <&ldb_lvds_ch0>; + }; + }; + }; + + reg_vcc_disp: regulator-disp { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_lcd0_vcc_en>; + compatible = "regulator-fixed"; + regulator-name = "disp_power_en_2v8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + gpio = <&gpio1 13 GPIO_ACTIVE_HIGH>; + enable-active-high; + regulator-boot-on; + regulator-always-on; + }; +}; + +&gpio3 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_gpio3_hog>; + + lvdssel-hog { + gpio-hog; + gpios = <23 GPIO_ACTIVE_HIGH>; + output-low; + line-name = "LVDSSEL"; + }; +}; + +&hdmi_blk_ctrl { + status = "disabled"; +}; + +&hdmi_pvi { + status = "disabled"; +}; + +&hdmi_tx { + status = "disabled"; +}; + +&hdmi_tx_phy { + status = "disabled"; +}; + +&irqsteer_hdmi { + status = "disabled"; +}; + +&ldb_lvds_ch0 { + remote-endpoint = <&in_lvds0>; +}; + +&lcdif1 { + status = "disabled"; +}; + +&lcdif2 { + status = "okay"; +}; + +&lcdif3 { + status = "disabled"; +}; + +&lvds_backlight { + status = "okay"; +}; + +&lvds_bridge { + /* IMX8MP_CLK_MEDIA_LDB = IMX8MP_CLK_MEDIA_DISP2_PIX * 7 */ + assigned-clock-rates = <232820000>; + status = "okay"; +}; + +&media_blk_ctrl { + /* + * currently it is not possible to let display clocks configure + * automatically, so we need to set them manually + */ + assigned-clock-rates = <500000000>, <200000000>, <0>, + /* IMX8MP_CLK_MEDIA_DISP2_PIX = pixelclk of lvds panel */ + <33260000>, <0>, + /* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_LDB * 2 */ + <465640000>; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-helios.dts b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-helios.dts new file mode 100644 index 000000000000..a4e649a8239b --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-helios.dts @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright (C) 2024 Heiko Schocher + */ + +/dts-v1/; + +#include +#include +#include "imx8mp-aristainetos3a-som-v1.dtsi" + +&{/} { + model = "Aristainetos3 helios carrier"; + compatible = "abb,imx8mp-aristanetos3-helios", + "abb,imx8mp-aristanetos3-som", + "fsl,imx8mp"; + + led-controller { + compatible = "gpio-leds"; + + led-0 { + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <20>; + gpios = <&pca6416 12 GPIO_ACTIVE_LOW>; + default-state = "off"; + }; + + led-1 { + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <20>; + gpios = <&pca6416 13 GPIO_ACTIVE_LOW>; + default-state = "off"; + }; + + led-2 { + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <20>; + gpios = <&pca6416 14 GPIO_ACTIVE_LOW>; + default-state = "off"; + }; + + led-3 { + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <20>; + gpios = <&pca6416 15 GPIO_ACTIVE_LOW>; + default-state = "off"; + }; + }; +}; + +ðphy1 { + status = "disabled"; +}; + +&fec { + status = "disabled"; +}; + +&i2c1 { + eeprom@57 { + compatible = "atmel,24c64"; + reg = <0x57>; + }; +}; + +&i2c3 { + pca6416: gpio@20 { + compatible = "ti,tca6416"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + gpio-line-names = "DIN0_CON", + "DIN1_CON", + "DIN2_CON", + "DIN3_CON", + "DIN4_CON", + "DIN5_CON", + "DIN6_CON", + "DIN7_CON", + "PM102_RES", + "COMx_RES", + "BPL_RES", + "PC_RES", + "LED_RED", + "LED_YELLOW", + "LED_GREEN", + "LED_BLUE"; + }; + + rtc@68 { + compatible = "st,m41t00"; + reg = <0x68>; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-proton2s.dts b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-proton2s.dts new file mode 100644 index 000000000000..2a736dbe96b4 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3-proton2s.dts @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright (C) 2024 Heiko Schocher + */ + +/dts-v1/; + +#include +#include +#include "imx8mp-aristainetos3a-som-v1.dtsi" + +&{/} { + model = "Aristainetos3 proton2s carrier"; + compatible = "abb,imx8mp-aristanetos3-proton2s", + "abb,imx8mp-aristanetos3-som", + "fsl,imx8mp"; + + watchdog { + /* MAX6371KA */ + compatible = "linux,wdt-gpio"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_watchdog_gpio>; + always-running; + gpios = <&gpio1 6 GPIO_ACTIVE_HIGH>; + hw_algo = "level"; + /* Reset triggers in 3..9 seconds */ + hw_margin_ms = <1500>; + }; +}; + +ðphy1 { + status = "disabled"; +}; + +&eqos { + max-speed = <100>; +}; + +&ecspi1{ + pinctrl-0 = <&pinctrl_ecspi1>; + cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>; +}; + +&fec { + status = "disabled"; +}; + +&gpio1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_gpio_proton2s>; + + gpio-line-names = + "", "", "", "", "", "", "", "POWER", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", ""; +}; + +&gpio6 { + gpio-line-names = + "RELAY0", "RELAY1", "RELAY2", "HEATER", + "FAN", "SPARE", "CLEAR", "FAULT", + "", "", "", "", "", "", "", "", ""; +}; + +&i2c2 { + tlc59108@40 { + compatible = "ti,tlc59108"; + reg = <0x40>; + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0x0>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <20>; + }; + + led@1 { + reg = <0x1>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <20>; + }; + + led@2 { + reg = <0x2>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <21>; + }; + + led@3 { + reg = <0x3>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <21>; + }; + + led@4 { + reg = <0x4>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <21>; + }; + + led@5 { + reg = <0x5>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <22>; + }; + + led@6 { + reg = <0x6>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <22>; + }; + + led@7 { + reg = <0x7>; + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <22>; + }; + }; + + rtc1: rtc@68 { + compatible = "dallas,ds1339"; + reg = <0x68>; + }; +}; + +&uart1 { + pinctrl-0 = <&pinctrl_uart1>; +}; + +&uart2 { + pinctrl-0 = <&pinctrl_uart2>; +}; + +&uart3 { + pinctrl-0 = <&pinctrl_uart3>; +}; + +&uart4 { + linux,rs485-enabled-at-boot-time; + rs485-rts-active-low; + rs485-rts-delay = <0 0>; + rts-gpios = <&gpio3 9 GPIO_ACTIVE_HIGH>; +}; + +&usdhc1 { + status = "disabled"; +}; + +&wdog1 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3a-som-v1.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3a-som-v1.dtsi new file mode 100644 index 000000000000..231e480acfd4 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3a-som-v1.dtsi @@ -0,0 +1,1107 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Heiko Schocher + */ + +#include +#include +#include +#include +#include "imx8mp.dtsi" + +/ { + model = "ADLINK LEC-iMX8MP-Q-N-4G-32G"; + compatible = "abb,imx8mp-aristanetos3-som", "fsl,imx8mp"; + + aliases { + ethernet0 = &eqos; + ethernet1 = &fec; + mmc0 = &usdhc3; /* eMMC */ + mmc1 = &usdhc2; /* MicroSD */ + }; + + chosen { + bootargs = "console=ttymxc1,115200 earlycon=ec_imx6q,0x30890000,115200"; + stdout-path = &uart2; + }; + + connector { + compatible = "usb-c-connector"; + label = "USB-C"; + + port { + usb_dr_connector: endpoint { + remote-endpoint = <&usb3_dwc>; + }; + }; + }; + + gpio-leds { + compatible = "gpio-leds"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_gpio_led>; + + led-0 { + function = LED_FUNCTION_STATUS; + color = ; + function-enumerator = <0>; + gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>; + default-state = "on"; + }; + }; + + lvds_backlight: backlight { + compatible = "pwm-backlight"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_lvds_bklt_en>; + pwms = <&pwm2 0 50000 0>; + enable-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>; + brightness-levels = <0 100>; + num-interpolated-steps = <100>; + default-brightness-level = <80>; + status = "disabled"; + }; + + memory@40000000 { + device_type = "memory"; + /* Memory size 512 MiB..8 GiB will be filled by U-Boot */ + reg = <0x0 0x40000000 0 0x08000000>; + }; + + pcie0_refclk: clock-pcie-ref { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <100000000>; + }; + + reg_can1_stby: regulator-can1-stby { + compatible = "regulator-fixed"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_flexcan1_reg>; + gpio = <&gpio5 5 GPIO_ACTIVE_HIGH>; + enable-active-high; + regulator-max-microvolt = <3300000>; + regulator-min-microvolt = <3300000>; + regulator-name = "can1-stby"; + }; + + reg_can2_stby: regulator-can2-stby { + compatible = "regulator-fixed"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_flexcan2_reg>; + enable-active-high; + gpio = <&gpio4 27 GPIO_ACTIVE_HIGH>; + regulator-max-microvolt = <3300000>; + regulator-min-microvolt = <3300000>; + regulator-name = "can2-stby"; + }; + + reg_dp83867_2v5: regulator-enet { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio7 15 GPIO_ACTIVE_HIGH>; + regulator-max-microvolt = <1800000>; + regulator-min-microvolt = <1800000>; + regulator-name = "enet_2v5"; + regulator-boot-on; + regulator-always-on; + }; + + reg_usb1_host_vbus: regulator-usb1-vbus { + compatible = "regulator-fixed"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usb1_vbus>; + enable-active-high; + gpio = <&gpio1 14 GPIO_ACTIVE_HIGH>; + regulator-max-microvolt = <5000000>; + regulator-min-microvolt = <5000000>; + regulator-name = "usb1_host_vbus"; + regulator-always-on; + }; + + reg_usdhc2_vmmc: regulator-usdhc2-vmmc { + compatible = "regulator-fixed"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usdhc2_vmmc>; + enable-active-high; + gpio = <&gpio2 19 GPIO_ACTIVE_HIGH>; /* SD2_RESET */ + regulator-max-microvolt = <3300000>; + regulator-min-microvolt = <3300000>; + regulator-name = "VDD_3V3_SD"; + off-on-delay-us = <12000>; + startup-delay-us = <100>; + vin-supply = <&buck4>; + }; +}; + +&A53_0 { + cpu-supply = <&buck2>; +}; + +&A53_1 { + cpu-supply = <&buck2>; +}; + +&A53_2 { + cpu-supply = <&buck2>; +}; + +&A53_3 { + cpu-supply = <&buck2>; +}; + +&clk { + clocks = <&osc_32k>, <&osc_24m>, <&clk_ext1>, <&clk_ext2>, + <&clk_ext3>, <&clk_ext4>; + clock-names = "osc_32k", "osc_24m", "clk_ext1", "clk_ext2", + "clk_ext3", "clk_ext4"; + assigned-clocks = <&clk IMX8MP_CLK_A53_SRC>, + <&clk IMX8MP_CLK_A53_CORE>, + <&clk IMX8MP_CLK_NOC>, + <&clk IMX8MP_CLK_NOC_IO>, + <&clk IMX8MP_CLK_GIC>, + <&clk IMX8MP_CLK_AUDIO_AHB>, + <&clk IMX8MP_CLK_AUDIO_AXI_SRC>, + <&clk IMX8MP_AUDIO_PLL1>, + <&clk IMX8MP_AUDIO_PLL2>, + <&clk IMX8MP_VIDEO_PLL1>; +}; + +&ecspi1{ + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ecspi1 &pinctrl_ecspi1_cs2>; + cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW &gpio1 6 GPIO_ACTIVE_LOW>; + status = "okay"; +}; + +&ecspi2 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ecspi2>; + cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>; + status = "okay"; +}; + +/* eth0 */ +&eqos { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_eqos_rgmii>; + phy-handle = <ðphy0>; + phy-mode = "rgmii-id"; + snps,force_thresh_dma_mode; + snps,mtl-tx-config = <&mtl_tx_setup>; + snps,mtl-rx-config = <&mtl_rx_setup>; + status = "okay"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + ethphy0: eqos-ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0>; + ti,rx-internal-delay = ; + ti,tx-internal-delay = ; + ti,fifo-depth = ; + ti,min-output-impedance; + ti,dp83867-rxctrl-strap-quirk; + interrupt-parent = <&gpio4>; + interrupts = <21 IRQ_TYPE_EDGE_FALLING>; + reset-gpios = <&gpio4 22 GPIO_ACTIVE_LOW>; + }; + }; + + mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <5>; + + queue0 { + snps,dcb-algorithm; + snps,priority = <0x1>; + }; + + queue1 { + snps,dcb-algorithm; + snps,priority = <0x2>; + }; + + queue2 { + snps,dcb-algorithm; + snps,priority = <0x4>; + }; + + queue3 { + snps,dcb-algorithm; + snps,priority = <0x8>; + }; + + queue4 { + snps,dcb-algorithm; + snps,priority = <0xf0>; + }; + }; + + mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <5>; + + queue0 { + snps,dcb-algorithm; + snps,priority = <0x1>; + snps,map-to-dma-channel = <0>; + }; + + queue1 { + snps,dcb-algorithm; + snps,priority = <0x2>; + snps,map-to-dma-channel = <1>; + }; + + queue2 { + snps,dcb-algorithm; + snps,priority = <0x4>; + snps,map-to-dma-channel = <2>; + }; + + queue3 { + snps,dcb-algorithm; + snps,priority = <0x8>; + snps,map-to-dma-channel = <3>; + }; + + queue4 { + snps,dcb-algorithm; + snps,priority = <0xf0>; + snps,map-to-dma-channel = <4>; + }; + }; +}; + +/* eth1 */ +&fec { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_fec_rgmii>; + phy-handle = <ðphy1>; + phy-mode = "rgmii-id"; + fsl,magic-packet; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + ethphy1: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + interrupt-parent = <&gpio4>; + interrupts = <3 IRQ_TYPE_EDGE_FALLING>; + reset-gpio = <&gpio4 2 GPIO_ACTIVE_LOW>; + ti,rx-internal-delay = ; + ti,tx-internal-delay = ; + ti,fifo-depth = ; + ti,min-output-impedance; + ti,dp83867-rxctrl-strap-quirk; + eee-broken-1000t; + }; + }; +}; + +&flexcan1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_flexcan1>; + xceiver-supply = <®_can1_stby>; + status = "disabled"; +}; + +&flexcan2 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_flexcan2>; + xceiver-supply = <®_can1_stby>; + status = "disabled"; +}; + +&hdmi_blk_ctrl { + status = "okay"; +}; + +&hdmi_pvi { + status = "okay"; +}; + +&hdmi_tx { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_hdmi>; + status = "okay"; +}; + +&hdmi_tx_phy { + status = "okay"; +}; + +&i2c1 { + clock-frequency = <100000>; + pinctrl-names = "default", "gpio"; + pinctrl-0 = <&pinctrl_i2c1>; + pinctrl-1 = <&pinctrl_i2c1_gpio>; + scl-gpios = <&gpio5 14 GPIO_ACTIVE_HIGH>; + sda-gpios = <&gpio5 15 GPIO_ACTIVE_HIGH>; + status = "okay"; + + pmic: pmic@25 { + compatible = "nxp,pca9450c"; + reg = <0x25>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pmic>; + interrupt-parent = <&gpio1>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; + + /* + * i.MX 8M Plus Data Sheet for Consumer Products + * 3.1.4 Operating ranges + * MIMX8ML8CVNKZAB + */ + regulators { + buck1: BUCK1 { /* VDD_SOC (dual-phase with BUCK3) */ + regulator-name = "buck1"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <2187500>; + regulator-ramp-delay = <3125>; + regulator-always-on; + regulator-boot-on; + }; + + buck2: BUCK2 { /* VDD_ARM */ + regulator-name = "buck2"; + nxp,dvs-run-voltage = <950000>; + nxp,dvs-standby-voltage = <850000>; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <2187500>; + regulator-ramp-delay = <3125>; + regulator-always-on; + regulator-boot-on; + }; + + buck4: BUCK4 { /* VDD_3V3 */ + regulator-name = "buck4"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + }; + + buck5: BUCK5 { /* VDD_1V8 */ + regulator-name = "buck5"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + regulator-boot-on; + }; + + buck6: BUCK6 { /* NVCC_DRAM_1V1 */ + regulator-name = "buck6"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + regulator-boot-on; + }; + + ldo1: LDO1 { /* NVCC_SNVS_1V8 */ + regulator-name = "ldo1"; + regulator-min-microvolt = <1600000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + }; + + ldo2: LDO2 { /* VDDA_1V8 */ + regulator-name = "ldo2"; + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <1150000>; + regulator-always-on; + regulator-boot-on; + }; + + ldo3: LDO3 { /* VDDA_1V8 */ + regulator-name = "ldo3"; + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + }; + + ldo4: LDO4 { /* PMIC_LDO4 */ + regulator-name = "ldo4"; + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + }; + + ldo5: LDO5 { /* NVCC_SD2 */ + regulator-name = "ldo5"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + }; + }; + }; +}; + +&i2c2 { + clock-frequency = <400000>; + pinctrl-names = "default", "gpio"; + pinctrl-0 = <&pinctrl_i2c2>; + pinctrl-1 = <&pinctrl_i2c2_gpio>; + scl-gpios = <&gpio5 16 GPIO_ACTIVE_HIGH>; + sda-gpios = <&gpio5 17 GPIO_ACTIVE_HIGH>; + status = "okay"; +}; + +&i2c3 { + clock-frequency = <100000>; + pinctrl-names = "default", "gpio"; + pinctrl-0 = <&pinctrl_i2c3>; + pinctrl-1 = <&pinctrl_i2c3_gpio>; + scl-gpios = <&gpio5 18 GPIO_ACTIVE_HIGH>; + sda-gpios = <&gpio5 19 GPIO_ACTIVE_HIGH>; + status = "okay"; +}; + +&i2c5 { + #address-cells = <1>; + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c5>; + status = "okay"; +}; + +&i2c6 { + clock-frequency = <100000>; + pinctrl-names = "default", "gpio"; + pinctrl-0 = <&pinctrl_i2c6>; + pinctrl-1 = <&pinctrl_i2c6_gpio>; + scl-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>; + sda-gpios = <&gpio3 20 GPIO_ACTIVE_HIGH>; + status = "okay"; + + /* TPM - ST33TPHF2XI2C U2301 */ + tpm: tpm@2e { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_tpm_irq>; + compatible = "st,st33ktpm2xi2c", "tcg,tpm-tis-i2c"; + reg = <0x2e>; + + label = "tpm"; + interrupt-parent = <&gpio3>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; + reset-gpios = <&gpio6 11 GPIO_ACTIVE_LOW>; + status = "okay"; + }; + + /* SX1509(0) U2605 */ + gpio6: pinctrl@3f { + compatible = "semtech,sx1509q"; + reg = <0x3f>; + #gpio-cells = <2>; + #interrupt-cells = <2>; + semtech,probe-reset; + gpio-controller; + interrupt-controller; + interrupt-parent = <&gpio1>; + interrupts = <12 IRQ_TYPE_EDGE_FALLING>; + }; + + /* RTC U2607 */ + rtc0: rtc@51 { + compatible = "nxp,pcf8563"; + reg = <0x51>; + #clock-cells = <0>; + }; + + /* SX1509(1) U2606 */ + gpio7: pinctrl@70 { + compatible = "semtech,sx1509q"; + reg = <0x70>; + #gpio-cells = <2>; + #interrupt-cells = <2>; + semtech,probe-reset; + gpio-controller; + interrupt-controller; + interrupt-parent = <&gpio4>; + interrupts = <19 IRQ_TYPE_EDGE_FALLING>; + + gpio6-cfg { + pins = "gpio6"; + output-high; + }; + + gpio7-cfg { + pins = "gpio7"; + output-high; + }; + }; +}; + +&irqsteer_hdmi { + status = "okay"; +}; + +&lcdif1 { + status = "disabled"; +}; + +&lcdif2 { + status = "disabled"; +}; + +/* HDMI */ +&lcdif3 { + status = "okay"; + +}; + +&lvds_bridge { + status = "disabled"; +}; + +&mipi_dsi { + status = "disabled"; +}; + +&pcie{ + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pcie>; + reset-gpio = <&gpio4 20 GPIO_ACTIVE_LOW>; + fsl,tx-deemph-gen1 = <0x1f>; + fsl,max-link-speed = <3>; + status = "okay"; +}; + +&pcie_phy{ + fsl,refclk-pad-mode = ; + clocks = <&pcie0_refclk>; + clock-names = "ref"; + status = "okay"; +}; + +&pwm1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pwm1>; + status = "okay"; +}; + +&pwm2 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pwm2>; + #pwm-cells = <3>; + status = "okay"; +}; + +&snvs_pwrkey { + status = "okay"; +}; + +&uart1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_uart1>; + status = "okay"; +}; + +&uart2 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_uart2>; + status = "okay"; +}; + +&uart3 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_uart3>; + status = "okay"; +}; + +&uart4 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_uart4>; + status = "okay"; +}; + +&usb3_phy0 { + status = "okay"; +}; + +&usb3_0 { + status = "okay"; +}; + +&usb_dwc3_0 { + adp-disable; + hnp-disable; + srp-disable; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "peripheral"; + status = "okay"; + + port { + usb3_dwc: endpoint { + remote-endpoint = <&usb_dr_connector>; + }; + }; +}; + +&usb3_phy1 { + status = "okay"; +}; + +&usb3_1 { + status = "okay"; +}; + +&usb_dwc3_1 { + dr_mode = "host"; + status = "okay"; +}; + +&usdhc1 { + pinctrl-names = "default", "state_100mhz", "state_200mhz"; + pinctrl-0 = <&pinctrl_usdhc1>; + pinctrl-1 = <&pinctrl_usdhc1_100mhz>; + pinctrl-2 = <&pinctrl_usdhc1_200mhz>; + bus-width = <4>; + non-removable; + status = "okay"; +}; + +/* SD slot */ +&usdhc2 { + pinctrl-names = "default", "state_100mhz", "state_200mhz"; + pinctrl-0 = <&pinctrl_usdhc2>, <&pinctrl_usdhc2_gpio>; + pinctrl-1 = <&pinctrl_usdhc2_100mhz>, <&pinctrl_usdhc2_gpio>; + pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>; + cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>; + vmmc-supply = <®_usdhc2_vmmc>; + bus-width = <4>; + status = "okay"; +}; + +/* eMMC */ +&usdhc3 { + pinctrl-names = "default", "state_100mhz", "state_200mhz"; + pinctrl-0 = <&pinctrl_usdhc3>; + pinctrl-1 = <&pinctrl_usdhc3_100mhz>; + pinctrl-2 = <&pinctrl_usdhc3_200mhz>; + vmmc-supply = <&buck4>; + vqmmc-supply = <&buck5>; + bus-width = <8>; + non-removable; + status = "okay"; +}; + +&wdog1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdog>; + fsl,ext-reset-output; + status = "okay"; +}; + +&iomuxc { + pinctrl_ecspi1: aristainetos3-ecspi1-grp { + fsl,pins = < + MX8MP_IOMUXC_ECSPI1_SCLK__ECSPI1_SCLK 0x82 + MX8MP_IOMUXC_ECSPI1_MOSI__ECSPI1_MOSI 0x82 + MX8MP_IOMUXC_ECSPI1_MISO__ECSPI1_MISO 0x82 + MX8MP_IOMUXC_ECSPI1_SS0__GPIO5_IO09 0x40000 + >; + }; + + pinctrl_ecspi1_cs2: aristainetos3-ecspi1-cs2-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO06__GPIO1_IO06 0x40000 + >; + }; + + pinctrl_ecspi2: aristainetos3-ecspi2-grp { + fsl,pins = < + MX8MP_IOMUXC_ECSPI2_SCLK__ECSPI2_SCLK 0x82 + MX8MP_IOMUXC_ECSPI2_MOSI__ECSPI2_MOSI 0x82 + MX8MP_IOMUXC_ECSPI2_MISO__ECSPI2_MISO 0x82 + MX8MP_IOMUXC_ECSPI2_SS0__GPIO5_IO13 0x40000 + >; + }; + + pinctrl_eqos_rgmii: aristainetos3-eqos-rgmii-grp { + fsl,pins = < + MX8MP_IOMUXC_ENET_MDC__ENET_QOS_MDC 0x3 + MX8MP_IOMUXC_ENET_MDIO__ENET_QOS_MDIO 0x3 + MX8MP_IOMUXC_ENET_RD0__ENET_QOS_RGMII_RD0 0x91 + MX8MP_IOMUXC_ENET_RD1__ENET_QOS_RGMII_RD1 0x91 + MX8MP_IOMUXC_ENET_RD2__ENET_QOS_RGMII_RD2 0x91 + MX8MP_IOMUXC_ENET_RD3__ENET_QOS_RGMII_RD3 0x91 + MX8MP_IOMUXC_ENET_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK 0x91 + MX8MP_IOMUXC_ENET_RX_CTL__ENET_QOS_RGMII_RX_CTL 0x91 + MX8MP_IOMUXC_ENET_TD0__ENET_QOS_RGMII_TD0 0x1f + MX8MP_IOMUXC_ENET_TD1__ENET_QOS_RGMII_TD1 0x1f + MX8MP_IOMUXC_ENET_TD2__ENET_QOS_RGMII_TD2 0x1f + MX8MP_IOMUXC_ENET_TD3__ENET_QOS_RGMII_TD3 0x1f + MX8MP_IOMUXC_ENET_TX_CTL__ENET_QOS_RGMII_TX_CTL 0x1f + MX8MP_IOMUXC_ENET_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK 0x1f + MX8MP_IOMUXC_SAI2_RXC__GPIO4_IO22 0x19 + >; + }; + + pinctrl_fec_rgmii: aristainetos3-fec-rgmii-grp { + fsl,pins = < + MX8MP_IOMUXC_SAI1_RXD2__ENET1_MDC 0x3 + MX8MP_IOMUXC_SAI1_RXD3__ENET1_MDIO 0x3 + MX8MP_IOMUXC_SAI1_RXD4__ENET1_RGMII_RD0 0x91 + MX8MP_IOMUXC_SAI1_RXD5__ENET1_RGMII_RD1 0x91 + MX8MP_IOMUXC_SAI1_RXD6__ENET1_RGMII_RD2 0x91 + MX8MP_IOMUXC_SAI1_RXD7__ENET1_RGMII_RD3 0x91 + MX8MP_IOMUXC_SAI1_TXC__ENET1_RGMII_RXC 0x91 + MX8MP_IOMUXC_SAI1_TXFS__ENET1_RGMII_RX_CTL 0x91 + MX8MP_IOMUXC_SAI1_TXD0__ENET1_RGMII_TD0 0x1f + MX8MP_IOMUXC_SAI1_TXD1__ENET1_RGMII_TD1 0x1f + MX8MP_IOMUXC_SAI1_TXD2__ENET1_RGMII_TD2 0x1f + MX8MP_IOMUXC_SAI1_TXD3__ENET1_RGMII_TD3 0x1f + MX8MP_IOMUXC_SAI1_TXD4__ENET1_RGMII_TX_CTL 0x1f + MX8MP_IOMUXC_SAI1_TXD5__ENET1_RGMII_TXC 0x1f + MX8MP_IOMUXC_SAI1_RXD0__GPIO4_IO02 0x19 + >; + }; + + pinctrl_flexcan1: aristainetos3-flexcan1-grp { + fsl,pins = < + MX8MP_IOMUXC_SPDIF_RX__CAN1_RX 0x154 + MX8MP_IOMUXC_SPDIF_TX__CAN1_TX 0x154 + >; + }; + + pinctrl_flexcan1_reg: aristainetos3-flexcan1-reg-grp { + fsl,pins = < + MX8MP_IOMUXC_SPDIF_EXT_CLK__GPIO5_IO05 0x154 + >; + }; + + pinctrl_flexcan2: aristainetos3-flexcan2-grp { + fsl,pins = < + MX8MP_IOMUXC_SAI5_MCLK__CAN2_RX 0x154 + MX8MP_IOMUXC_SAI5_RXD3__CAN2_TX 0x154 + >; + }; + + pinctrl_flexcan2_reg: aristainetos3-flexcan2-reg-grp { + fsl,pins = < + MX8MP_IOMUXC_SAI2_MCLK__GPIO4_IO27 0x154 + >; + }; + + pinctrl_gpio3_hog: aristainetos3-gpio3-hog-grp { + fsl,pins = < + MX8MP_IOMUXC_SAI5_RXD2__GPIO3_IO23 0xd6 + >; + }; + + pinctrl_gpio_led: aristainetos3-gpio-led-grp { + fsl,pins = < + MX8MP_IOMUXC_NAND_READY_B__GPIO3_IO16 0x19 + >; + }; + + pinctrl_gpio_proton2s: aristainetos3-gpio-proton2s-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO07__GPIO1_IO07 0x19 + >; + }; + + pinctrl_hdmi: aristainetos3-hdmi-grp { + fsl,pins = < + MX8MP_IOMUXC_HDMI_DDC_SCL__HDMIMIX_HDMI_SCL 0x400001c3 + MX8MP_IOMUXC_HDMI_DDC_SDA__HDMIMIX_HDMI_SDA 0x400001c3 + MX8MP_IOMUXC_HDMI_HPD__HDMIMIX_HDMI_HPD 0x40000019 + MX8MP_IOMUXC_HDMI_CEC__HDMIMIX_HDMI_CEC 0x40000019 + >; + }; + + pinctrl_i2c1: aristainetos3-i2c1-grp { + fsl,pins = < + MX8MP_IOMUXC_I2C1_SCL__I2C1_SCL 0x400001c3 + MX8MP_IOMUXC_I2C1_SDA__I2C1_SDA 0x400001c3 + >; + }; + + pinctrl_i2c1_gpio: aristainetos3-i2c1-gpio-grp { + fsl,pins = < + MX8MP_IOMUXC_I2C1_SCL__GPIO5_IO14 0x1c3 + MX8MP_IOMUXC_I2C1_SDA__GPIO5_IO15 0x1c3 + >; + }; + + pinctrl_i2c2: aristainetos3-i2c2-grp { + fsl,pins = < + MX8MP_IOMUXC_I2C2_SCL__I2C2_SCL 0x400001c3 + MX8MP_IOMUXC_I2C2_SDA__I2C2_SDA 0x400001c3 + >; + }; + + pinctrl_i2c2_gpio: aristainetos3-i2c2-gpio-grp { + fsl,pins = < + MX8MP_IOMUXC_I2C2_SCL__GPIO5_IO16 0x1c3 + MX8MP_IOMUXC_I2C2_SDA__GPIO5_IO17 0x1c3 + >; + }; + + pinctrl_i2c3: aristainetos3-i2c3-grp { + fsl,pins = < + MX8MP_IOMUXC_I2C3_SCL__I2C3_SCL 0x400001c3 + MX8MP_IOMUXC_I2C3_SDA__I2C3_SDA 0x400001c3 + >; + }; + + pinctrl_i2c3_gpio: aristainetos3-i2c3-gpio-grp { + fsl,pins = < + MX8MP_IOMUXC_I2C3_SCL__GPIO5_IO18 0x1c3 + MX8MP_IOMUXC_I2C3_SDA__GPIO5_IO19 0x1c3 + >; + }; + + pinctrl_i2c5: aristainetos3-i2c5-grp { + fsl,pins = < + MX8MP_IOMUXC_SAI5_RXD0__I2C5_SCL 0x400001c3 + MX8MP_IOMUXC_SAI5_MCLK__I2C5_SDA 0x400001c3 + >; + }; + + pinctrl_i2c6: aristainetos3-i2c6-grp { + fsl,pins = < + MX8MP_IOMUXC_SAI5_RXFS__I2C6_SCL 0x400001c3 + MX8MP_IOMUXC_SAI5_RXC__I2C6_SDA 0x400001c3 + >; + }; + + pinctrl_i2c6_gpio: aristainetos3-i2c6-gpio-grp { + fsl,pins = < + MX8MP_IOMUXC_SAI5_RXFS__GPIO3_IO19 0x1c3 + MX8MP_IOMUXC_SAI5_RXC__GPIO3_IO20 0x1c3 + >; + }; + + pinctrl_lcd0_vcc_en: aristainetos3-lcd0-vcc-en-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO13__GPIO1_IO13 0xd6 + >; + }; + + pinctrl_lvds_bklt_en: aristainetos3-lvds-bklt-en-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO10__GPIO1_IO10 0xd6 + >; + }; + + pinctrl_pcie: aristainetos3-pcie-grp { + fsl,pins = < + MX8MP_IOMUXC_I2C4_SCL__PCIE_CLKREQ_B 0x61 + MX8MP_IOMUXC_SAI1_MCLK__GPIO4_IO20 0x41 + >; + }; + + pinctrl_pmic: aristainetos3-pmic-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x41 + >; + }; + + pinctrl_pwm1: aristainetos3-pwm1-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO01__PWM1_OUT 0x116 + >; + }; + + pinctrl_pwm2: aristainetos3-pwm2-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO11__PWM2_OUT 0x116 + >; + }; + + pinctrl_tpm_irq: aristainetos3-tpm-irq-grp { + fsl,pins = < + MX8MP_IOMUXC_NAND_DQS__GPIO3_IO14 0xd6 + >; + }; + + pinctrl_uart1: aristainetos3-uart1-grp { + fsl,pins = < + MX8MP_IOMUXC_UART1_RXD__UART1_DCE_RX 0x140 + MX8MP_IOMUXC_UART1_TXD__UART1_DCE_TX 0x140 + >; + }; + + pinctrl_uart2: aristainetos3-uart2-grp { + fsl,pins = < + MX8MP_IOMUXC_UART2_RXD__UART2_DCE_RX 0x140 + MX8MP_IOMUXC_UART2_TXD__UART2_DCE_TX 0x140 + MX8MP_IOMUXC_SD1_DATA4__GPIO2_IO06 0x140 + MX8MP_IOMUXC_SD1_DATA5__UART2_DCE_CTS 0x140 + >; + }; + + pinctrl_uart3: aristainetos3-uart3-grp { + fsl,pins = < + MX8MP_IOMUXC_NAND_ALE__UART3_DCE_RX 0x140 + MX8MP_IOMUXC_NAND_CE0_B__UART3_DCE_TX 0x140 + >; + }; + + pinctrl_uart4: aristainetos3-uart4-grp { + fsl,pins = < + MX8MP_IOMUXC_UART4_RXD__UART4_DCE_RX 0x140 + MX8MP_IOMUXC_UART4_TXD__UART4_DCE_TX 0x140 + MX8MP_IOMUXC_NAND_DATA03__GPIO3_IO09 0x140 + MX8MP_IOMUXC_NAND_DATA02__UART4_DCE_CTS 0x140 + >; + }; + + pinctrl_usb1_vbus: aristainetos3-usb1-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO14__GPIO1_IO14 0x19 + >; + }; + + pinctrl_usdhc1: aristainetos3-usdhc1-grp { + fsl,pins = < + MX8MP_IOMUXC_SD1_CLK__USDHC1_CLK 0x190 + MX8MP_IOMUXC_SD1_CMD__USDHC1_CMD 0x1d0 + MX8MP_IOMUXC_SD1_DATA0__USDHC1_DATA0 0x1d0 + MX8MP_IOMUXC_SD1_DATA1__USDHC1_DATA1 0x1d0 + MX8MP_IOMUXC_SD1_DATA2__USDHC1_DATA2 0x1d0 + MX8MP_IOMUXC_SD1_DATA3__USDHC1_DATA3 0x1d0 + >; + }; + + pinctrl_usdhc1_100mhz: aristainetos3-usdhc1-100mhz-grp { + fsl,pins = < + MX8MP_IOMUXC_SD1_CLK__USDHC1_CLK 0x194 + MX8MP_IOMUXC_SD1_CMD__USDHC1_CMD 0x1d4 + MX8MP_IOMUXC_SD1_DATA0__USDHC1_DATA0 0x1d4 + MX8MP_IOMUXC_SD1_DATA1__USDHC1_DATA1 0x1d4 + MX8MP_IOMUXC_SD1_DATA2__USDHC1_DATA2 0x1d4 + MX8MP_IOMUXC_SD1_DATA3__USDHC1_DATA3 0x1d4 + >; + }; + + pinctrl_usdhc1_200mhz: aristainetos3-usdhc1-200mhz-grp { + fsl,pins = < + MX8MP_IOMUXC_SD1_CLK__USDHC1_CLK 0x196 + MX8MP_IOMUXC_SD1_CMD__USDHC1_CMD 0x1d6 + MX8MP_IOMUXC_SD1_DATA0__USDHC1_DATA0 0x1d6 + MX8MP_IOMUXC_SD1_DATA1__USDHC1_DATA1 0x1d6 + MX8MP_IOMUXC_SD1_DATA2__USDHC1_DATA2 0x1d6 + MX8MP_IOMUXC_SD1_DATA3__USDHC1_DATA3 0x1d6 + >; + }; + + pinctrl_usdhc2: aristainetos3-usdhc2-grp { + fsl,pins = < + MX8MP_IOMUXC_SD2_CLK__USDHC2_CLK 0x190 + MX8MP_IOMUXC_SD2_CMD__USDHC2_CMD 0x1d0 + MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0 0x1d0 + MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1 0x1d0 + MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2 0x1d0 + MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d0 + MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc1 + + >; + }; + + pinctrl_usdhc2_100mhz: aristainetos3-usdhc2-100mhz-grp { + fsl,pins = < + MX8MP_IOMUXC_SD2_CLK__USDHC2_CLK 0x194 + MX8MP_IOMUXC_SD2_CMD__USDHC2_CMD 0x1d4 + MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0 0x1d4 + MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1 0x1d4 + MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2 0x1d4 + MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d4 + MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc1 + >; + }; + + pinctrl_usdhc2_200mhz: aristainetos3-usdhc2-200mhz-grp { + fsl,pins = < + MX8MP_IOMUXC_SD2_CLK__USDHC2_CLK 0x196 + MX8MP_IOMUXC_SD2_CMD__USDHC2_CMD 0x1d6 + MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0 0x1d6 + MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1 0x1d6 + MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2 0x1d6 + MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d6 + MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc1 + >; + }; + + pinctrl_usdhc2_gpio: aristainetos3-usdhc2-gpio-grp { + fsl,pins = < + MX8MP_IOMUXC_SD2_CD_B__GPIO2_IO12 0x40000080 + >; + }; + + pinctrl_usdhc2_vmmc: aristainetos3-usdhc2-vmmc-grp { + fsl,pins = < + MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19 0x41 + >; + }; + + pinctrl_usdhc3: aristainetos3-usdhc3-grp { + fsl,pins = < + MX8MP_IOMUXC_NAND_WE_B__USDHC3_CLK 0x190 + MX8MP_IOMUXC_NAND_WP_B__USDHC3_CMD 0x1d0 + MX8MP_IOMUXC_NAND_DATA04__USDHC3_DATA0 0x1d0 + MX8MP_IOMUXC_NAND_DATA05__USDHC3_DATA1 0x1d0 + MX8MP_IOMUXC_NAND_DATA06__USDHC3_DATA2 0x1d0 + MX8MP_IOMUXC_NAND_DATA07__USDHC3_DATA3 0x1d0 + MX8MP_IOMUXC_NAND_RE_B__USDHC3_DATA4 0x1d0 + MX8MP_IOMUXC_NAND_CE2_B__USDHC3_DATA5 0x1d0 + MX8MP_IOMUXC_NAND_CE3_B__USDHC3_DATA6 0x1d0 + MX8MP_IOMUXC_NAND_CLE__USDHC3_DATA7 0x1d0 + MX8MP_IOMUXC_NAND_CE1_B__USDHC3_STROBE 0x190 + >; + }; + + pinctrl_usdhc3_100mhz: aristainetos3-usdhc3-100mhz-grp { + fsl,pins = < + MX8MP_IOMUXC_NAND_WE_B__USDHC3_CLK 0x194 + MX8MP_IOMUXC_NAND_WP_B__USDHC3_CMD 0x1d4 + MX8MP_IOMUXC_NAND_DATA04__USDHC3_DATA0 0x1d4 + MX8MP_IOMUXC_NAND_DATA05__USDHC3_DATA1 0x1d4 + MX8MP_IOMUXC_NAND_DATA06__USDHC3_DATA2 0x1d4 + MX8MP_IOMUXC_NAND_DATA07__USDHC3_DATA3 0x1d4 + MX8MP_IOMUXC_NAND_RE_B__USDHC3_DATA4 0x1d4 + MX8MP_IOMUXC_NAND_CE2_B__USDHC3_DATA5 0x1d4 + MX8MP_IOMUXC_NAND_CE3_B__USDHC3_DATA6 0x1d4 + MX8MP_IOMUXC_NAND_CLE__USDHC3_DATA7 0x1d4 + MX8MP_IOMUXC_NAND_CE1_B__USDHC3_STROBE 0x194 + >; + }; + + pinctrl_usdhc3_200mhz: aristainetos3-usdhc3-200mhz-grp { + fsl,pins = < + MX8MP_IOMUXC_NAND_WE_B__USDHC3_CLK 0x196 + MX8MP_IOMUXC_NAND_WP_B__USDHC3_CMD 0x1d6 + MX8MP_IOMUXC_NAND_DATA04__USDHC3_DATA0 0x1d6 + MX8MP_IOMUXC_NAND_DATA05__USDHC3_DATA1 0x1d6 + MX8MP_IOMUXC_NAND_DATA06__USDHC3_DATA2 0x1d6 + MX8MP_IOMUXC_NAND_DATA07__USDHC3_DATA3 0x1d6 + MX8MP_IOMUXC_NAND_RE_B__USDHC3_DATA4 0x1d6 + MX8MP_IOMUXC_NAND_CE2_B__USDHC3_DATA5 0x1d6 + MX8MP_IOMUXC_NAND_CE3_B__USDHC3_DATA6 0x1d6 + MX8MP_IOMUXC_NAND_CLE__USDHC3_DATA7 0x1d6 + MX8MP_IOMUXC_NAND_CE1_B__USDHC3_STROBE 0x196 + >; + }; + + pinctrl_watchdog_gpio: aristainetos3-wdog-gpio-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO06__GPIO1_IO06 0x19 + >; + }; + + pinctrl_wdog: aristainetos3-wdog-grp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO02__WDOG1_WDOG_B 0xc6 + >; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk-imx-lvds-hdmi-common.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-evk-imx-lvds-hdmi-common.dtsi new file mode 100644 index 000000000000..44b30e9b3fde --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk-imx-lvds-hdmi-common.dtsi @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright 2024 NXP + */ + +/dts-v1/; +/plugin/; + +&{/} { + lvds-hdmi-connector { + compatible = "hdmi-connector"; + label = "J2"; + type = "a"; + + port { + lvds2hdmi_connector_in: endpoint { + remote-endpoint = <&it6263_out>; + }; + }; + }; +}; + +&lcdif2 { + status = "okay"; +}; + +&lvds_bridge { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds0-imx-dlvds-hdmi-channel0.dtso b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds0-imx-dlvds-hdmi-channel0.dtso new file mode 100644 index 000000000000..4008d2fd36d6 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds0-imx-dlvds-hdmi-channel0.dtso @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright 2024 NXP + */ + +#include "imx8mp-evk-lvds0-imx-lvds-hdmi-common.dtsi" + +&it6263 { + ports { + port@0 { + reg = <0>; + dual-lvds-odd-pixels; + + it6263_lvds_link1: endpoint { + remote-endpoint = <&ldb_lvds_ch0>; + }; + }; + + port@1 { + reg = <1>; + dual-lvds-even-pixels; + + it6263_lvds_link2: endpoint { + remote-endpoint = <&ldb_lvds_ch1>; + }; + }; + }; +}; + +&lvds_bridge { + ports { + port@1 { + ldb_lvds_ch0: endpoint { + remote-endpoint = <&it6263_lvds_link1>; + }; + }; + + port@2 { + ldb_lvds_ch1: endpoint { + remote-endpoint = <&it6263_lvds_link2>; + }; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds0-imx-lvds-hdmi-common.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds0-imx-lvds-hdmi-common.dtsi new file mode 100644 index 000000000000..6eae7477abf8 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds0-imx-lvds-hdmi-common.dtsi @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright 2024 NXP + */ + +#include +#include "imx8mp-evk-imx-lvds-hdmi-common.dtsi" + +&i2c2 { + #address-cells = <1>; + #size-cells = <0>; + + it6263: hdmi@4c { + compatible = "ite,it6263"; + reg = <0x4c>; + data-mapping = "jeida-24"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_lvds_en>; + reset-gpios = <&gpio1 10 GPIO_ACTIVE_LOW>; + ivdd-supply = <®_buck5>; + ovdd-supply = <®_vext_3v3>; + txavcc18-supply = <®_buck5>; + txavcc33-supply = <®_vext_3v3>; + pvcc1-supply = <®_buck5>; + pvcc2-supply = <®_buck5>; + avcc-supply = <®_vext_3v3>; + anvdd-supply = <®_buck5>; + apvdd-supply = <®_buck5>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@2 { + reg = <2>; + + it6263_out: endpoint { + remote-endpoint = <&lvds2hdmi_connector_in>; + }; + }; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds0-imx-lvds-hdmi.dtso b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds0-imx-lvds-hdmi.dtso new file mode 100644 index 000000000000..9e11f261ad13 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds0-imx-lvds-hdmi.dtso @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright 2024 NXP + */ + +#include "imx8mp-evk-lvds0-imx-lvds-hdmi-common.dtsi" + +&it6263 { + ports { + port@0 { + reg = <0>; + + it6263_lvds_link1: endpoint { + remote-endpoint = <&ldb_lvds_ch0>; + }; + }; + }; +}; + +&lvds_bridge { + ports { + port@1 { + ldb_lvds_ch0: endpoint { + remote-endpoint = <&it6263_lvds_link1>; + }; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds1-imx-dlvds-hdmi-channel0.dtso b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds1-imx-dlvds-hdmi-channel0.dtso new file mode 100644 index 000000000000..af2e73e36a1b --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds1-imx-dlvds-hdmi-channel0.dtso @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright 2024 NXP + */ + +#include "imx8mp-evk-lvds1-imx-lvds-hdmi-common.dtsi" + +&it6263 { + ports { + port@0 { + reg = <0>; + dual-lvds-even-pixels; + + it6263_lvds_link1: endpoint { + remote-endpoint = <&ldb_lvds_ch1>; + }; + }; + + port@1 { + reg = <1>; + dual-lvds-odd-pixels; + + it6263_lvds_link2: endpoint { + remote-endpoint = <&ldb_lvds_ch0>; + }; + }; + }; +}; + +&lvds_bridge { + ports { + port@1 { + ldb_lvds_ch0: endpoint { + remote-endpoint = <&it6263_lvds_link2>; + }; + }; + + port@2 { + ldb_lvds_ch1: endpoint { + remote-endpoint = <&it6263_lvds_link1>; + }; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds1-imx-lvds-hdmi-common.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds1-imx-lvds-hdmi-common.dtsi new file mode 100644 index 000000000000..8cc9d361c2a4 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds1-imx-lvds-hdmi-common.dtsi @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright 2024 NXP + */ + +#include +#include "imx8mp-evk-imx-lvds-hdmi-common.dtsi" + +&i2c3 { + #address-cells = <1>; + #size-cells = <0>; + + it6263: hdmi@4c { + compatible = "ite,it6263"; + reg = <0x4c>; + data-mapping = "jeida-24"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_lvds_en>; + reset-gpios = <&gpio1 10 GPIO_ACTIVE_LOW>; + ivdd-supply = <®_buck5>; + ovdd-supply = <®_vext_3v3>; + txavcc18-supply = <®_buck5>; + txavcc33-supply = <®_vext_3v3>; + pvcc1-supply = <®_buck5>; + pvcc2-supply = <®_buck5>; + avcc-supply = <®_vext_3v3>; + anvdd-supply = <®_buck5>; + apvdd-supply = <®_buck5>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@2 { + reg = <2>; + + it6263_out: endpoint { + remote-endpoint = <&lvds2hdmi_connector_in>; + }; + }; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds1-imx-lvds-hdmi.dtso b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds1-imx-lvds-hdmi.dtso new file mode 100644 index 000000000000..527a893a71b2 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk-lvds1-imx-lvds-hdmi.dtso @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright 2024 NXP + */ + +#include "imx8mp-evk-lvds1-imx-lvds-hdmi-common.dtsi" + +&it6263 { + ports { + port@0 { + reg = <0>; + + it6263_lvds_link1: endpoint { + remote-endpoint = <&ldb_lvds_ch1>; + }; + }; + }; +}; + +&lvds_bridge { + ports { + port@2 { + ldb_lvds_ch1: endpoint { + remote-endpoint = <&it6263_lvds_link1>; + }; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts index d26930f1a9e9..68e12a752edd 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts @@ -938,6 +938,12 @@ >; }; + pinctrl_lvds_en: lvdsengrp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO10__GPIO1_IO10 0x1c0 + >; + }; + pinctrl_pcie0: pcie0grp { fsl,pins = < MX8MP_IOMUXC_I2C4_SCL__PCIE_CLKREQ_B 0x60 /* open drain, pull up */ diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts index 30962922b361..2c75da5f064f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts @@ -52,7 +52,7 @@ &lvds_bridge { /* IMX8MP_CLK_MEDIA_LDB = IMX8MP_CLK_MEDIA_DISP2_PIX * 7 */ - assigned-clock-rates = <482300000>; + assigned-clock-rates = <490000000>; status = "okay"; ports { @@ -70,10 +70,10 @@ */ assigned-clock-rates = <500000000>, <200000000>, <0>, /* IMX8MP_CLK_MEDIA_DISP2_PIX = pixelclk of lvds panel */ - <68900000>, + <70000000>, <500000000>, - /* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_LDB * 2 */ - <964600000>; + /* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_LDB */ + <490000000>; }; &pwm4 { diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts b/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts index b268ba7a0e12..9d8e7231b7c6 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts @@ -172,7 +172,7 @@ "Headphones", "HP_OUT", "Builtin Speaker", "Speaker Amp OUTR", "Speaker Amp INR", "LINE_OUT"; - simple-audio-card,hp-det-gpio = <&gpio3 20 GPIO_ACTIVE_HIGH>; + simple-audio-card,hp-det-gpios = <&gpio3 20 GPIO_ACTIVE_HIGH>; simple-audio-card,cpu { sound-dai = <&sai2>; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi index 1b39514d5c12..bb37a32ce461 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi @@ -241,7 +241,7 @@ "Headset Mic", "MICBIAS", "IN3R", "Headset Mic", "DMICDAT", "Digital Mic"; - simple-audio-card,hp-det-gpio = <&gpio3 9 GPIO_ACTIVE_HIGH>; + simple-audio-card,hp-det-gpios = <&gpio3 9 GPIO_ACTIVE_HIGH>; simple-audio-card,cpu { sound-dai = <&sai2>; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi index 0c960efd9b3d..c7bbba45f368 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi @@ -517,8 +517,6 @@ eeprom@a4 { compatible = "zii,rave-sp-eeprom"; reg = <0xa4 0x4000>; - #address-cells = <1>; - #size-cells = <1>; zii,eeprom-name = "main-eeprom"; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi index e24e639b98ee..c9b55f02497a 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi @@ -134,7 +134,7 @@ }; esai1: esai@59810000 { - compatible = "fsl,imx8qm-esai"; + compatible = "fsl,imx8qm-esai", "fsl,imx6ull-esai"; reg = <0x59810000 0x10000>; interrupts = ; clocks = <&esai1_lpcg IMX_LPCG_CLK_0>, diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts index 0e12dcd0d4d1..8491eb53120e 100644 --- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts @@ -595,6 +595,9 @@ }; &wdog3 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdog>; + fsl,ext-reset-output; status = "okay"; }; @@ -932,4 +935,9 @@ >; }; + pinctrl_wdog: wdoggrp { + fsl,pins = < + MX93_PAD_WDOG_ANY__WDOG1_WDOG_ANY 0x31e + >; + }; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-14x14-evk.dts b/arch/arm64/boot/dts/freescale/imx93-14x14-evk.dts index 236a44c1782a..f556b6569a68 100644 --- a/arch/arm64/boot/dts/freescale/imx93-14x14-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx93-14x14-evk.dts @@ -219,6 +219,89 @@ interrupt-parent = <&gpio3>; interrupts = <27 IRQ_TYPE_LEVEL_LOW>; }; + + pmic@25 { + compatible = "nxp,pca9452"; + reg = <0x25>; + interrupt-parent = <&pcal6524>; + interrupts = <11 IRQ_TYPE_EDGE_FALLING>; + + regulators { + buck1: BUCK1 { + regulator-name = "BUCK1"; + regulator-min-microvolt = <610000>; + regulator-max-microvolt = <950000>; + regulator-boot-on; + regulator-always-on; + regulator-ramp-delay = <3125>; + }; + + buck2: BUCK2 { + regulator-name = "BUCK2"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <670000>; + regulator-boot-on; + regulator-always-on; + regulator-ramp-delay = <3125>; + }; + + buck4: BUCK4{ + regulator-name = "BUCK4"; + regulator-min-microvolt = <1620000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + regulator-always-on; + }; + + buck5: BUCK5{ + regulator-name = "BUCK5"; + regulator-min-microvolt = <1620000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + regulator-always-on; + }; + + buck6: BUCK6 { + regulator-name = "BUCK6"; + regulator-min-microvolt = <1060000>; + regulator-max-microvolt = <1140000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo1: LDO1 { + regulator-name = "LDO1"; + regulator-min-microvolt = <1620000>; + regulator-max-microvolt = <1980000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo3: LDO3 { + regulator-name = "LDO3"; + regulator-min-microvolt = <1710000>; + regulator-max-microvolt = <1890000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo4: LDO4 { + regulator-name = "LDO4"; + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <840000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo5: LDO5 { + regulator-name = "LDO5"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + }; + }; }; &lpi2c3 { @@ -284,6 +367,9 @@ }; &wdog3 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdog>; + fsl,ext-reset-output; status = "okay"; }; @@ -465,4 +551,10 @@ MX93_PAD_SD2_VSELECT__USDHC2_VSELECT 0x51e >; }; + + pinctrl_wdog: wdoggrp { + fsl,pins = < + MX93_PAD_WDOG_ANY__WDOG1_WDOG_ANY 0x31e + >; + }; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-9x9-qsb.dts b/arch/arm64/boot/dts/freescale/imx93-9x9-qsb.dts index 20ec5b3c21f4..75e67115d52f 100644 --- a/arch/arm64/boot/dts/freescale/imx93-9x9-qsb.dts +++ b/arch/arm64/boot/dts/freescale/imx93-9x9-qsb.dts @@ -221,6 +221,11 @@ >; }; + p3t1085: temperature-sensor@48 { + compatible = "nxp,p3t1085"; + reg = <0x48>; + }; + ptn5110: tcpc@50 { compatible = "nxp,ptn5110", "tcpci"; reg = <0x50>; @@ -454,6 +459,9 @@ }; &wdog3 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdog>; + fsl,ext-reset-output; status = "okay"; }; @@ -641,4 +649,10 @@ MX93_PAD_SD2_VSELECT__USDHC2_VSELECT 0x51e >; }; + + pinctrl_wdog: wdoggrp { + fsl,pins = < + MX93_PAD_WDOG_ANY__WDOG1_WDOG_ANY 0x31e + >; + }; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts index 599df32976e2..8e939d716aac 100644 --- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts +++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts @@ -627,8 +627,8 @@ fsl,pins = < /* PD | FSEL_2 | DSE X4 */ MX93_PAD_ENET1_MDC__ENET_QOS_MDC 0x51e - /* SION | HYS | FSEL_2 | DSE X4 */ - MX93_PAD_ENET1_MDIO__ENET_QOS_MDIO 0x4000111e + /* SION | HYS | ODE | FSEL_2 | DSE X4 */ + MX93_PAD_ENET1_MDIO__ENET_QOS_MDIO 0x4000191e /* HYS | FSEL_0 | DSE no drive */ MX93_PAD_ENET1_RD0__ENET_QOS_RGMII_RD0 0x1000 MX93_PAD_ENET1_RD1__ENET_QOS_RGMII_RD1 0x1000 @@ -659,8 +659,8 @@ fsl,pins = < /* PD | FSEL_2 | DSE X4 */ MX93_PAD_ENET2_MDC__ENET1_MDC 0x51e - /* SION | HYS | FSEL_2 | DSE X4 */ - MX93_PAD_ENET2_MDIO__ENET1_MDIO 0x4000111e + /* SION | HYS | ODE | FSEL_2 | DSE X4 */ + MX93_PAD_ENET2_MDIO__ENET1_MDIO 0x4000191e /* HYS | FSEL_0 | DSE no drive */ MX93_PAD_ENET2_RD0__ENET1_RGMII_RD0 0x1000 MX93_PAD_ENET2_RD1__ENET1_RGMII_RD1 0x1000 diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts index 0b4b3bb866d0..2e953a05c590 100644 --- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts +++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts @@ -597,8 +597,8 @@ fsl,pins = < /* PD | FSEL_2 | DSE X4 */ MX93_PAD_ENET1_MDC__ENET_QOS_MDC 0x51e - /* SION | HYS | FSEL_2 | DSE X4 */ - MX93_PAD_ENET1_MDIO__ENET_QOS_MDIO 0x4000111e + /* SION | HYS | ODE | FSEL_2 | DSE X4 */ + MX93_PAD_ENET1_MDIO__ENET_QOS_MDIO 0x4000191e /* HYS | FSEL_0 | DSE no drive */ MX93_PAD_ENET1_RD0__ENET_QOS_RGMII_RD0 0x1000 MX93_PAD_ENET1_RD1__ENET_QOS_RGMII_RD1 0x1000 @@ -629,8 +629,8 @@ fsl,pins = < /* PD | FSEL_2 | DSE X4 */ MX93_PAD_ENET2_MDC__ENET1_MDC 0x51e - /* SION | HYS | FSEL_2 | DSE X4 */ - MX93_PAD_ENET2_MDIO__ENET1_MDIO 0x4000111e + /* SION | HYS | ODE | FSEL_2 | DSE X4 */ + MX93_PAD_ENET2_MDIO__ENET1_MDIO 0x4000191e /* HYS | FSEL_0 | DSE no drive */ MX93_PAD_ENET2_RD0__ENET1_RGMII_RD0 0x1000 MX93_PAD_ENET2_RD1__ENET1_RGMII_RD1 0x1000 diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi index 688488de8cd2..56766fdb0b1e 100644 --- a/arch/arm64/boot/dts/freescale/imx93.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93.dtsi @@ -925,7 +925,7 @@ reg-names = "ram", "regs", "rxfifo", "txfifo"; interrupts = , ; - clocks = <&clk IMX93_CLK_BUS_WAKEUP>, + clocks = <&clk IMX93_CLK_SPDIF_IPG>, <&clk IMX93_CLK_SPDIF_GATE>, <&clk IMX93_CLK_DUMMY>, <&clk IMX93_CLK_AUD_XCVR_GATE>; diff --git a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts index 6086cb7fa5a0..8bc066c3760c 100644 --- a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts @@ -22,6 +22,7 @@ compatible = "fsl,imx95-19x19-evk", "fsl,imx95"; aliases { + ethernet0 = &enetc_port0; gpio0 = &gpio1; gpio1 = &gpio2; gpio2 = &gpio3; @@ -193,6 +194,14 @@ }; }; +&enetc_port0 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_enetc0>; + phy-handle = <ðphy0>; + phy-mode = "rgmii-id"; + status = "okay"; +}; + &flexspi1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_flexspi1>; @@ -338,6 +347,25 @@ status = "okay"; }; +&netcmix_blk_ctrl { + status = "okay"; +}; + +&netc_blk_ctrl { + status = "okay"; +}; + +&netc_emdio { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_emdio>; + status = "okay"; + + ethphy0: ethernet-phy@1 { + reg = <1>; + realtek,clkout-disable; + }; +}; + &pcie0 { pinctrl-0 = <&pinctrl_pcie0>; pinctrl-names = "default"; @@ -429,6 +457,30 @@ }; &scmi_iomuxc { + pinctrl_emdio: emdiogrp{ + fsl,pins = < + IMX95_PAD_ENET1_MDC__NETCMIX_TOP_NETC_MDC 0x57e + IMX95_PAD_ENET1_MDIO__NETCMIX_TOP_NETC_MDIO 0x97e + >; + }; + + pinctrl_enetc0: enetc0grp { + fsl,pins = < + IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3 0x57e + IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2 0x57e + IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1 0x57e + IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0 0x57e + IMX95_PAD_ENET1_TX_CTL__NETCMIX_TOP_ETH0_RGMII_TX_CTL 0x57e + IMX95_PAD_ENET1_TXC__NETCMIX_TOP_ETH0_RGMII_TX_CLK 0x58e + IMX95_PAD_ENET1_RX_CTL__NETCMIX_TOP_ETH0_RGMII_RX_CTL 0x57e + IMX95_PAD_ENET1_RXC__NETCMIX_TOP_ETH0_RGMII_RX_CLK 0x58e + IMX95_PAD_ENET1_RD0__NETCMIX_TOP_ETH0_RGMII_RD0 0x57e + IMX95_PAD_ENET1_RD1__NETCMIX_TOP_ETH0_RGMII_RD1 0x57e + IMX95_PAD_ENET1_RD2__NETCMIX_TOP_ETH0_RGMII_RD2 0x57e + IMX95_PAD_ENET1_RD3__NETCMIX_TOP_ETH0_RGMII_RD3 0x57e + >; + }; + pinctrl_flexspi1: flexspi1grp { fsl,pins = < IMX95_PAD_XSPI1_SS0_B__FLEXSPI1_A_SS0_B 0x3fe diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index d10f62eacfe0..6b8470cb3461 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1673,7 +1673,7 @@ netcmix_blk_ctrl: syscon@4c810000 { compatible = "nxp,imx95-netcmix-blk-ctrl", "syscon"; - reg = <0x0 0x4c810000 0x0 0x10000>; + reg = <0x0 0x4c810000 0x0 0x8>; #clock-cells = <1>; clocks = <&scmi_clk IMX95_CLK_BUSNETCMIX>; assigned-clocks = <&scmi_clk IMX95_CLK_BUSNETCMIX>; @@ -1697,6 +1697,99 @@ status = "disabled"; }; + netc_blk_ctrl: system-controller@4cde0000 { + compatible = "nxp,imx95-netc-blk-ctrl"; + reg = <0x0 0x4cde0000 0x0 0x10000>, + <0x0 0x4cdf0000 0x0 0x10000>, + <0x0 0x4c81000c 0x0 0x18>; + reg-names = "ierb", "prb", "netcmix"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + power-domains = <&scmi_devpd IMX95_PD_NETC>; + assigned-clocks = <&scmi_clk IMX95_CLK_ENET>, + <&scmi_clk IMX95_CLK_ENETREF>; + assigned-clock-parents = <&scmi_clk IMX95_CLK_SYSPLL1_PFD2>, + <&scmi_clk IMX95_CLK_SYSPLL1_PFD0>; + assigned-clock-rates = <666666666>, <250000000>; + clocks = <&scmi_clk IMX95_CLK_ENET>; + clock-names = "ipg"; + status = "disabled"; + + netc_bus0: pcie@4ca00000 { + compatible = "pci-host-ecam-generic"; + reg = <0x0 0x4ca00000 0x0 0x100000>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + bus-range = <0x0 0x0>; + msi-map = <0x0 &its 0x60 0x1>, //ENETC0 PF + <0x10 &its 0x61 0x1>, //ENETC0 VF0 + <0x20 &its 0x62 0x1>, //ENETC0 VF1 + <0x40 &its 0x63 0x1>, //ENETC1 PF + <0x80 &its 0x64 0x1>, //ENETC2 PF + <0x90 &its 0x65 0x1>, //ENETC2 VF0 + <0xa0 &its 0x66 0x1>, //ENETC2 VF1 + <0xc0 &its 0x67 0x1>; //NETC Timer + /* ENETC0~2 and Timer BAR0 - non-prefetchable memory */ + ranges = <0x82000000 0x0 0x4cc00000 0x0 0x4cc00000 0x0 0xe0000 + /* Timer BAR2 - prefetchable memory */ + 0xc2000000 0x0 0x4cd00000 0x0 0x4cd00000 0x0 0x10000 + /* ENETC0~2: VF0-1 BAR0 - non-prefetchable memory */ + 0x82000000 0x0 0x4cd20000 0x0 0x4cd20000 0x0 0x60000 + /* ENETC0~2: VF0-1 BAR2 - prefetchable memory */ + 0xc2000000 0x0 0x4cd80000 0x0 0x4cd80000 0x0 0x60000>; + + enetc_port0: ethernet@0,0 { + compatible = "pci1131,e101"; + reg = <0x000000 0 0 0 0>; + clocks = <&scmi_clk IMX95_CLK_ENETREF>; + clock-names = "ref"; + status = "disabled"; + }; + + enetc_port1: ethernet@8,0 { + compatible = "pci1131,e101"; + reg = <0x004000 0 0 0 0>; + clocks = <&scmi_clk IMX95_CLK_ENETREF>; + clock-names = "ref"; + status = "disabled"; + }; + + enetc_port2: ethernet@10,0 { + compatible = "pci1131,e101"; + reg = <0x008000 0 0 0 0>; + status = "disabled"; + }; + + netc_timer: ethernet@18,0 { + reg = <0x00c000 0 0 0 0>; + status = "disabled"; + }; + }; + + netc_bus1: pcie@4cb00000 { + compatible = "pci-host-ecam-generic"; + reg = <0x0 0x4cb00000 0x0 0x100000>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + bus-range = <0x1 0x1>; + /* EMDIO BAR0 - non-prefetchable memory */ + ranges = <0x82000000 0x0 0x4cce0000 0x0 0x4cce0000 0x0 0x20000 + /* EMDIO BAR2 - prefetchable memory */ + 0xc2000000 0x0 0x4cd10000 0x0 0x4cd10000 0x0 0x10000>; + + netc_emdio: mdio@0,0 { + compatible = "pci1131,ee00"; + reg = <0x010000 0 0 0 0>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + }; + }; + ddr-pmu@4e090dc0 { compatible = "fsl,imx95-ddr-pmu", "fsl,imx93-ddr-pmu"; reg = <0x0 0x4e090dc0 0x0 0x200>; diff --git a/arch/arm64/boot/dts/hisilicon/hi6220.dtsi b/arch/arm64/boot/dts/hisilicon/hi6220.dtsi index a589954c29e2..f8b56d443850 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hi6220.dtsi @@ -727,8 +727,6 @@ compatible = "arm,pl022", "arm,primecell"; reg = <0x0 0xf7106000 0x0 0x1000>; interrupts = <0 50 4>; - bus-id = <0>; - enable-dma = <0>; clocks = <&sys_ctrl HI6220_SPI_CLK>, <&sys_ctrl HI6220_SPI_CLK>; clock-names = "sspclk", "apb_pclk"; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi index 2a5eeb21da47..1235ba5a9865 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi +++ b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi @@ -101,10 +101,13 @@ compatible = "arm,gic-400", "arm,cortex-a15-gic"; #interrupt-cells = <3>; interrupt-controller; + interrupt-parent = <&intc>; reg = <0x0 0xfffc1000 0x0 0x1000>, <0x0 0xfffc2000 0x0 0x2000>, <0x0 0xfffc4000 0x0 0x2000>, <0x0 0xfffc6000 0x0 0x2000>; + /* VGIC maintenance interrupt */ + interrupts = ; }; clocks { diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi index 1162978329c1..51c6e19e40b8 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi +++ b/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi @@ -222,6 +222,26 @@ status = "disabled"; }; + gpio0: gpio@ffc03200 { + compatible = "snps,dw-apb-gpio"; + reg = <0xffc03200 0x100>; + #address-cells = <1>; + #size-cells = <0>; + resets = <&rst GPIO0_RESET>; + status = "disabled"; + + porta: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + reg = <0>; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <24>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = ; + }; + }; + gpio1: gpio@10c03300 { compatible = "snps,dw-apb-gpio"; reg = <0x10c03300 0x100>; @@ -314,7 +334,7 @@ reg-io-width = <4>; num-cs = <4>; clocks = <&clkmgr AGILEX5_L4_MAIN_CLK>; - dmas = <&dmac0 2>, <&dmac0 3>; + dmas = <&dmac0 16>, <&dmac0 17>; dma-names = "tx", "rx"; status = "disabled"; @@ -331,6 +351,8 @@ reg-io-width = <4>; num-cs = <4>; clocks = <&clkmgr AGILEX5_L4_MAIN_CLK>; + dmas = <&dmac0 20>, <&dmac0 21>; + dma-names = "tx", "rx"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/marvell/armada-7040-db.dts b/arch/arm64/boot/dts/marvell/armada-7040-db.dts index 1e0ab35cc686..2b5e45d2c5a6 100644 --- a/arch/arm64/boot/dts/marvell/armada-7040-db.dts +++ b/arch/arm64/boot/dts/marvell/armada-7040-db.dts @@ -214,6 +214,7 @@ sata-port@1 { phys = <&cp0_comphy3 1>; + status = "okay"; }; }; diff --git a/arch/arm64/boot/dts/marvell/armada-7040-mochabin.dts b/arch/arm64/boot/dts/marvell/armada-7040-mochabin.dts index 7af949092b91..6bdc4f1e6939 100644 --- a/arch/arm64/boot/dts/marvell/armada-7040-mochabin.dts +++ b/arch/arm64/boot/dts/marvell/armada-7040-mochabin.dts @@ -433,11 +433,13 @@ /* 7 + 12 SATA connector (J24) */ sata-port@0 { phys = <&cp0_comphy2 0>; + status = "okay"; }; /* M.2-2250 B-key (J39) */ sata-port@1 { phys = <&cp0_comphy3 1>; + status = "okay"; }; }; diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts index 7005a32a6e1e..225a54ab688d 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts +++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts @@ -475,6 +475,7 @@ sata-port@1 { phys = <&cp1_comphy0 1>; + status = "okay"; }; }; diff --git a/arch/arm64/boot/dts/marvell/armada-8040-db.dts b/arch/arm64/boot/dts/marvell/armada-8040-db.dts index 2ec19d364e62..9d45e881a97d 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-db.dts +++ b/arch/arm64/boot/dts/marvell/armada-8040-db.dts @@ -145,9 +145,12 @@ sata-port@0 { phys = <&cp0_comphy1 0>; + status = "okay"; }; + sata-port@1 { phys = <&cp0_comphy3 1>; + status = "okay"; }; }; @@ -304,11 +307,9 @@ sata-port@0 { phys = <&cp1_comphy1 0>; - phy-names = "cp1-sata0-0-phy"; }; sata-port@1 { phys = <&cp1_comphy3 1>; - phy-names = "cp1-sata0-1-phy"; }; }; diff --git a/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dtsi b/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dtsi index e88ff5b179c8..0d4a5fd9503f 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dtsi @@ -245,6 +245,7 @@ /* CPM Lane 5 - U29 */ sata-port@1 { phys = <&cp0_comphy5 1>; + status = "okay"; }; }; @@ -344,13 +345,11 @@ /* CPS Lane 1 - U32 */ sata-port@0 { phys = <&cp1_comphy1 0>; - phy-names = "cp1-sata0-0-phy"; }; /* CPS Lane 3 - U31 */ sata-port@1 { phys = <&cp1_comphy3 1>; - phy-names = "cp1-sata0-1-phy"; }; }; diff --git a/arch/arm64/boot/dts/marvell/armada-8040-puzzle-m801.dts b/arch/arm64/boot/dts/marvell/armada-8040-puzzle-m801.dts index 3e5e0651ce68..9c25a88581e4 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-puzzle-m801.dts +++ b/arch/arm64/boot/dts/marvell/armada-8040-puzzle-m801.dts @@ -408,10 +408,12 @@ sata-port@0 { phys = <&cp0_comphy2 0>; + status = "okay"; }; sata-port@1 { phys = <&cp0_comphy5 1>; + status = "okay"; }; }; diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi index 7e595ac80043..161beec0b6b0 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi @@ -347,10 +347,12 @@ sata-port@0 { reg = <0>; + status = "disabled"; }; sata-port@1 { reg = <1>; + status = "disabled"; }; }; diff --git a/arch/arm64/boot/dts/marvell/cn9130-crb-B.dts b/arch/arm64/boot/dts/marvell/cn9130-crb-B.dts index 0904cb0309ae..34194745f79e 100644 --- a/arch/arm64/boot/dts/marvell/cn9130-crb-B.dts +++ b/arch/arm64/boot/dts/marvell/cn9130-crb-B.dts @@ -28,6 +28,7 @@ status = "okay"; /* Generic PHY, providing serdes lanes */ phys = <&cp0_comphy2 0>; + status = "okay"; }; }; diff --git a/arch/arm64/boot/dts/marvell/cn9131-cf-solidwan.dts b/arch/arm64/boot/dts/marvell/cn9131-cf-solidwan.dts index b1ea7dcaed17..47234d0858dd 100644 --- a/arch/arm64/boot/dts/marvell/cn9131-cf-solidwan.dts +++ b/arch/arm64/boot/dts/marvell/cn9131-cf-solidwan.dts @@ -435,7 +435,7 @@ managed = "in-band-status"; phy-mode = "sgmii"; phy = <&cp1_phy0>; - phys = <&cp0_comphy3 1>; + phys = <&cp1_comphy3 1>; status = "okay"; }; @@ -444,7 +444,7 @@ managed = "in-band-status"; phy-mode = "sgmii"; phy = <&cp1_phy1>; - phys = <&cp0_comphy5 2>; + phys = <&cp1_comphy5 2>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/marvell/cn9131-db.dtsi b/arch/arm64/boot/dts/marvell/cn9131-db.dtsi index ad7360c83048..626042fce7e2 100644 --- a/arch/arm64/boot/dts/marvell/cn9131-db.dtsi +++ b/arch/arm64/boot/dts/marvell/cn9131-db.dtsi @@ -127,6 +127,7 @@ sata-port@1 { /* Generic PHY, providing serdes lanes */ phys = <&cp1_comphy5 1>; + status = "okay"; }; }; diff --git a/arch/arm64/boot/dts/marvell/cn9132-db.dtsi b/arch/arm64/boot/dts/marvell/cn9132-db.dtsi index e753cfdac697..f91fc69905b8 100644 --- a/arch/arm64/boot/dts/marvell/cn9132-db.dtsi +++ b/arch/arm64/boot/dts/marvell/cn9132-db.dtsi @@ -175,6 +175,7 @@ sata-port@0 { /* Generic PHY, providing serdes lanes */ phys = <&cp2_comphy2 0>; + status = "okay"; }; }; diff --git a/arch/arm64/boot/dts/mediatek/Makefile b/arch/arm64/boot/dts/mediatek/Makefile index 8fd7b2bb7a15..b763b73788a4 100644 --- a/arch/arm64/boot/dts/mediatek/Makefile +++ b/arch/arm64/boot/dts/mediatek/Makefile @@ -17,10 +17,13 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-mini.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-emmc.dtbo dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-nand.dtbo dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-nor.dtbo +dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-sata.dtbo dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-sd.dtbo dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-rfb.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986b-rfb.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt7988a-bananapi-bpi-r4.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt7988a-bananapi-bpi-r4-emmc.dtbo +dtb-$(CONFIG_ARCH_MEDIATEK) += mt7988a-bananapi-bpi-r4-sd.dtbo dtb-$(CONFIG_ARCH_MEDIATEK) += mt8167-pumpkin.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8173-elm.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8173-elm-hana.dtb @@ -55,10 +58,15 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-kodama-sku32.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-krane-sku0.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-krane-sku176.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-pumpkin.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-chinchou-sku0.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-chinchou-sku1.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-chinchou-sku16.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-magneton-sku393216.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-magneton-sku393217.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-magneton-sku393218.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-rusty-sku196608.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-starmie-sku0.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-starmie-sku1.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-steelix-sku131072.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-steelix-sku131073.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-tentacool-sku327681.dtb @@ -69,10 +77,16 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-voltorb-sku589824.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-voltorb-sku589825.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-evb.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-evb.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-geralt-ciri-sku0.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-geralt-ciri-sku1.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-geralt-ciri-sku2.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-geralt-ciri-sku3.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-geralt-ciri-sku4.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-geralt-ciri-sku5.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-geralt-ciri-sku6.dtb +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-geralt-ciri-sku7.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8192-asurada-hayato-r1.dtb -dtb-$(CONFIG_ARCH_MEDIATEK) += mt8192-asurada-hayato-r5-sku2.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8192-asurada-spherion-r0.dtb -dtb-$(CONFIG_ARCH_MEDIATEK) += mt8192-asurada-spherion-r4.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8192-evb.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8195-cherry-dojo-r1.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8195-cherry-tomato-r1.dtb @@ -90,3 +104,4 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt8516-pumpkin.dtb # Device tree overlays support DTC_FLAGS_mt7986a-bananapi-bpi-r3 := -@ DTC_FLAGS_mt7986a-bananapi-bpi-r3-mini := -@ +DTC_FLAGS_mt7988a-bananapi-bpi-r4 := -@ diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts index c84c47c1352f..0449686bd06b 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts @@ -115,6 +115,7 @@ pinctrl-names = "default", "sleep"; pinctrl-0 = <ð_default>; pinctrl-1 = <ð_sleep>; + mediatek,mac-wol; status = "okay"; mdio { diff --git a/arch/arm64/boot/dts/mediatek/mt6359.dtsi b/arch/arm64/boot/dts/mediatek/mt6359.dtsi index 8e1b8c85c6ed..150ad84d5d2b 100644 --- a/arch/arm64/boot/dts/mediatek/mt6359.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt6359.dtsi @@ -8,6 +8,7 @@ compatible = "mediatek,mt6359"; interrupt-controller; #interrupt-cells = <2>; + #sound-dai-cells = <1>; pmic_adc: adc { compatible = "mediatek,mt6359-auxadc"; diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-sata.dtso b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-sata.dtso new file mode 100644 index 000000000000..f7dd52981977 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-sata.dtso @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2021 MediaTek Inc. + * Author: Frank Wunderlich + */ + +/dts-v1/; +/plugin/; + +#include + +&{/} { + compatible = "bananapi,bpi-r3", "mediatek,mt7986a"; + + reg_sata12v: regulator-sata12v { + compatible = "regulator-fixed"; + regulator-name = "sata12v"; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + gpio = <&pio 8 GPIO_ACTIVE_HIGH>; + enable-active-high; + regulator-always-on; + }; + + reg_sata5v: regulator-sata5v { + compatible = "regulator-fixed"; + regulator-name = "sata5v"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + vin-supply = <®_sata12v>; + }; + +}; diff --git a/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4-emmc.dtso b/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4-emmc.dtso new file mode 100644 index 000000000000..3e320b2f83d5 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4-emmc.dtso @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2021 MediaTek Inc. + * Author: Frank Wunderlich + */ + +/dts-v1/; +/plugin/; + +/ { + compatible = "bananapi,bpi-r4", "mediatek,mt7988a"; +}; + +&{/soc/mmc@11230000} { + pinctrl-names = "default", "state_uhs"; + pinctrl-0 = <&mmc0_pins_emmc_51>; + pinctrl-1 = <&mmc0_pins_emmc_51>; + bus-width = <8>; + max-frequency = <200000000>; + cap-mmc-highspeed; + mmc-hs200-1_8v; + mmc-hs400-1_8v; + hs400-ds-delay = <0x12814>; + vqmmc-supply = <®_1p8v>; + vmmc-supply = <®_3p3v>; + non-removable; + no-sd; + no-sdio; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; +}; + diff --git a/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4-sd.dtso b/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4-sd.dtso new file mode 100644 index 000000000000..663c6345dd31 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4-sd.dtso @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 MediaTek Inc. + * Author: Frank Wunderlich + */ + +/dts-v1/; +/plugin/; + +#include + +/ { + compatible = "bananapi,bpi-r4", "mediatek,mt7988a"; +}; + +&{/soc/mmc@11230000} { + pinctrl-names = "default", "state_uhs"; + pinctrl-0 = <&mmc0_pins_sdcard>; + pinctrl-1 = <&mmc0_pins_sdcard>; + cd-gpios = <&pio 12 GPIO_ACTIVE_LOW>; + bus-width = <4>; + max-frequency = <52000000>; + cap-sd-highspeed; + vmmc-supply = <®_3p3v>; + vqmmc-supply = <®_3p3v>; + no-mmc; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; +}; + diff --git a/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4.dts b/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4.dts index efc4ad0b08b8..6623112c24c7 100644 --- a/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4.dts +++ b/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4.dts @@ -2,10 +2,408 @@ /dts-v1/; +#include +#include + #include "mt7988a.dtsi" / { compatible = "bananapi,bpi-r4", "mediatek,mt7988a"; model = "Banana Pi BPI-R4"; chassis-type = "embedded"; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + reg_1p8v: regulator-1p8v { + compatible = "regulator-fixed"; + regulator-name = "fixed-1.8V"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + }; + + reg_3p3v: regulator-3p3v { + compatible = "regulator-fixed"; + regulator-name = "fixed-3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; +}; + +&cpu0 { + proc-supply = <&rt5190_buck3>; +}; + +&cpu1 { + proc-supply = <&rt5190_buck3>; +}; + +&cpu2 { + proc-supply = <&rt5190_buck3>; +}; + +&cpu3 { + proc-supply = <&rt5190_buck3>; +}; + +&cpu_thermal { + trips { + cpu_trip_hot: hot { + temperature = <120000>; + hysteresis = <2000>; + type = "hot"; + }; + + cpu_trip_active_high: active-high { + temperature = <115000>; + hysteresis = <2000>; + type = "active"; + }; + + cpu_trip_active_med: active-med { + temperature = <85000>; + hysteresis = <2000>; + type = "active"; + }; + + cpu_trip_active_low: active-low { + temperature = <40000>; + hysteresis = <2000>; + type = "active"; + }; + }; +}; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_pins>; + status = "okay"; + + rt5190a_64: rt5190a@64 { + compatible = "richtek,rt5190a"; + reg = <0x64>; + vin2-supply = <&rt5190_buck1>; + vin3-supply = <&rt5190_buck1>; + vin4-supply = <&rt5190_buck1>; + + regulators { + rt5190_buck1: buck1 { + regulator-name = "rt5190a-buck1"; + regulator-min-microvolt = <5090000>; + regulator-max-microvolt = <5090000>; + regulator-allowed-modes = + , ; + regulator-boot-on; + regulator-always-on; + }; + buck2 { + regulator-name = "vcore"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <1400000>; + regulator-boot-on; + regulator-always-on; + }; + rt5190_buck3: buck3 { + regulator-name = "vproc"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <1400000>; + regulator-boot-on; + }; + buck4 { + regulator-name = "rt5190a-buck4"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-allowed-modes = + , ; + regulator-boot-on; + regulator-always-on; + }; + ldo { + regulator-name = "rt5190a-ldo"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + }; + }; + }; +}; + +&i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_1_pins>; + status = "okay"; + + pca9545: i2c-mux@70 { + compatible = "nxp,pca9545"; + reg = <0x70>; + reset-gpios = <&pio 5 GPIO_ACTIVE_LOW>; + #address-cells = <1>; + #size-cells = <0>; + + i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + pcf8563: rtc@51 { + compatible = "nxp,pcf8563"; + reg = <0x51>; + #clock-cells = <0>; + }; + + eeprom@57 { + compatible = "atmel,24c02"; + reg = <0x57>; + size = <256>; + }; + + }; + + i2c_sfp1: i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + }; + + i2c_sfp2: i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <2>; + }; + }; +}; + +/* mPCIe SIM2 */ +&pcie0 { + status = "okay"; +}; + +/* mPCIe SIM3 */ +&pcie1 { + status = "okay"; +}; + +/* M.2 key-B SIM1 */ +&pcie2 { + status = "okay"; +}; + +/* M.2 key-M SSD */ +&pcie3 { + status = "okay"; +}; + +&pio { + mdio0_pins: mdio0-pins { + mux { + function = "eth"; + groups = "mdc_mdio0"; + }; + + conf { + pins = "SMI_0_MDC", "SMI_0_MDIO"; + drive-strength = <8>; + }; + }; + + i2c0_pins: i2c0-g0-pins { + mux { + function = "i2c"; + groups = "i2c0_1"; + }; + }; + + i2c1_pins: i2c1-g0-pins { + mux { + function = "i2c"; + groups = "i2c1_0"; + }; + }; + + i2c1_sfp_pins: i2c1-sfp-g0-pins { + mux { + function = "i2c"; + groups = "i2c1_sfp"; + }; + }; + + i2c2_0_pins: i2c2-g0-pins { + mux { + function = "i2c"; + groups = "i2c2_0"; + }; + }; + + i2c2_1_pins: i2c2-g1-pins { + mux { + function = "i2c"; + groups = "i2c2_1"; + }; + }; + + gbe0_led0_pins: gbe0-led0-pins { + mux { + function = "led"; + groups = "gbe0_led0"; + }; + }; + + gbe1_led0_pins: gbe1-led0-pins { + mux { + function = "led"; + groups = "gbe1_led0"; + }; + }; + + gbe2_led0_pins: gbe2-led0-pins { + mux { + function = "led"; + groups = "gbe2_led0"; + }; + }; + + gbe3_led0_pins: gbe3-led0-pins { + mux { + function = "led"; + groups = "gbe3_led0"; + }; + }; + + gbe0_led1_pins: gbe0-led1-pins { + mux { + function = "led"; + groups = "gbe0_led1"; + }; + }; + + gbe1_led1_pins: gbe1-led1-pins { + mux { + function = "led"; + groups = "gbe1_led1"; + }; + }; + + gbe2_led1_pins: gbe2-led1-pins { + mux { + function = "led"; + groups = "gbe2_led1"; + }; + }; + + gbe3_led1_pins: gbe3-led1-pins { + mux { + function = "led"; + groups = "gbe3_led1"; + }; + }; + + i2p5gbe_led0_pins: 2p5gbe-led0-pins { + mux { + function = "led"; + groups = "2p5gbe_led0"; + }; + }; + + i2p5gbe_led1_pins: 2p5gbe-led1-pins { + mux { + function = "led"; + groups = "2p5gbe_led1"; + }; + }; + + mmc0_pins_emmc_45: mmc0-emmc-45-pins { + mux { + function = "flash"; + groups = "emmc_45"; + }; + }; + + mmc0_pins_emmc_51: mmc0-emmc-51-pins { + mux { + function = "flash"; + groups = "emmc_51"; + }; + }; + + mmc0_pins_sdcard: mmc0-sdcard-pins { + mux { + function = "flash"; + groups = "sdcard"; + }; + }; + + uart0_pins: uart0-pins { + mux { + function = "uart"; + groups = "uart0"; + }; + }; + + snfi_pins: snfi-pins { + mux { + function = "flash"; + groups = "snfi"; + }; + }; + + spi0_pins: spi0-pins { + mux { + function = "spi"; + groups = "spi0"; + }; + }; + + spi0_flash_pins: spi0-flash-pins { + mux { + function = "spi"; + groups = "spi0", "spi0_wp_hold"; + }; + }; + + spi1_pins: spi1-pins { + mux { + function = "spi"; + groups = "spi1"; + }; + }; + + spi2_pins: spi2-pins { + mux { + function = "spi"; + groups = "spi2"; + }; + }; + + spi2_flash_pins: spi2-flash-pins { + mux { + function = "spi"; + groups = "spi2", "spi2_wp_hold"; + }; + }; +}; + +&pwm { + status = "okay"; +}; + +&serial0 { + status = "okay"; +}; + +&ssusb1 { + status = "okay"; +}; + +&tphy { + status = "okay"; +}; + +&watchdog { + status = "okay"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7988a.dtsi b/arch/arm64/boot/dts/mediatek/mt7988a.dtsi index c9649b815276..88b56a24efca 100644 --- a/arch/arm64/boot/dts/mediatek/mt7988a.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7988a.dtsi @@ -3,6 +3,8 @@ #include #include #include +#include +#include / { compatible = "mediatek,mt7988a"; @@ -14,32 +16,70 @@ #address-cells = <1>; #size-cells = <0>; - cpu@0 { + cpu0: cpu@0 { compatible = "arm,cortex-a73"; reg = <0x0>; device_type = "cpu"; enable-method = "psci"; + clocks = <&mcusys CLK_MCU_ARM_DIV_SEL>, + <&topckgen CLK_TOP_XTAL>; + clock-names = "cpu", "intermediate"; + operating-points-v2 = <&cluster0_opp>; }; - cpu@1 { + cpu1: cpu@1 { compatible = "arm,cortex-a73"; reg = <0x1>; device_type = "cpu"; enable-method = "psci"; + clocks = <&mcusys CLK_MCU_ARM_DIV_SEL>, + <&topckgen CLK_TOP_XTAL>; + clock-names = "cpu", "intermediate"; + operating-points-v2 = <&cluster0_opp>; }; - cpu@2 { + cpu2: cpu@2 { compatible = "arm,cortex-a73"; reg = <0x2>; device_type = "cpu"; enable-method = "psci"; + clocks = <&mcusys CLK_MCU_ARM_DIV_SEL>, + <&topckgen CLK_TOP_XTAL>; + clock-names = "cpu", "intermediate"; + operating-points-v2 = <&cluster0_opp>; }; - cpu@3 { + cpu3: cpu@3 { compatible = "arm,cortex-a73"; reg = <0x3>; device_type = "cpu"; enable-method = "psci"; + clocks = <&mcusys CLK_MCU_ARM_DIV_SEL>, + <&topckgen CLK_TOP_XTAL>; + clock-names = "cpu", "intermediate"; + operating-points-v2 = <&cluster0_opp>; + }; + + cluster0_opp: opp-table-0 { + compatible = "operating-points-v2"; + opp-shared; + + opp-800000000 { + opp-hz = /bits/ 64 <800000000>; + opp-microvolt = <850000>; + }; + opp-1100000000 { + opp-hz = /bits/ 64 <1100000000>; + opp-microvolt = <850000>; + }; + opp-1500000000 { + opp-hz = /bits/ 64 <1500000000>; + opp-microvolt = <850000>; + }; + opp-1800000000 { + opp-hz = /bits/ 64 <1800000000>; + opp-microvolt = <900000>; + }; }; }; @@ -61,6 +101,18 @@ method = "smc"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + /* 320 KiB reserved for ARM Trusted Firmware (BL31 and BL32) */ + secmon@43000000 { + reg = <0 0x43000000 0 0x50000>; + no-map; + }; + }; + soc { compatible = "simple-bus"; ranges; @@ -84,6 +136,7 @@ compatible = "mediatek,mt7988-infracfg", "syscon"; reg = <0 0x10001000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; topckgen: clock-controller@1001b000 { @@ -99,13 +152,66 @@ #reset-cells = <1>; }; - clock-controller@1001e000 { + apmixedsys: clock-controller@1001e000 { compatible = "mediatek,mt7988-apmixedsys"; reg = <0 0x1001e000 0 0x1000>; #clock-cells = <1>; }; - pwm@10048000 { + pio: pinctrl@1001f000 { + compatible = "mediatek,mt7988-pinctrl"; + reg = <0 0x1001f000 0 0x1000>, + <0 0x11c10000 0 0x1000>, + <0 0x11d00000 0 0x1000>, + <0 0x11d20000 0 0x1000>, + <0 0x11e00000 0 0x1000>, + <0 0x11f00000 0 0x1000>, + <0 0x1000b000 0 0x1000>; + reg-names = "gpio", "iocfg_tr", + "iocfg_br", "iocfg_rb", + "iocfg_lb", "iocfg_tl", "eint"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pio 0 0 84>; + interrupt-controller; + interrupts = ; + interrupt-parent = <&gic>; + #interrupt-cells = <2>; + + pcie0_pins: pcie0-pins { + mux { + function = "pcie"; + groups = "pcie_2l_0_pereset", "pcie_clk_req_n0_0", + "pcie_wake_n0_0"; + }; + }; + + pcie1_pins: pcie1-pins { + mux { + function = "pcie"; + groups = "pcie_2l_1_pereset", "pcie_clk_req_n1", + "pcie_wake_n1_0"; + }; + }; + + pcie2_pins: pcie2-pins { + mux { + function = "pcie"; + groups = "pcie_1l_0_pereset", "pcie_clk_req_n2_0", + "pcie_wake_n2_0"; + }; + }; + + pcie3_pins: pcie3-pins { + mux { + function = "pcie"; + groups = "pcie_1l_1_pereset", "pcie_clk_req_n3", + "pcie_wake_n3_0"; + }; + }; + }; + + pwm: pwm@10048000 { compatible = "mediatek,mt7988-pwm"; reg = <0 0x10048000 0 0x1000>; clocks = <&infracfg CLK_INFRA_66M_PWM_BCK>, @@ -124,7 +230,13 @@ status = "disabled"; }; - serial@11000000 { + mcusys: mcusys@100e0000 { + compatible = "mediatek,mt7988-mcusys", "syscon"; + reg = <0 0x100e0000 0 0x1000>; + #clock-cells = <1>; + }; + + serial0: serial@11000000 { compatible = "mediatek,mt7988-uart", "mediatek,mt6577-uart"; reg = <0 0x11000000 0 0x100>; interrupts = ; @@ -157,11 +269,12 @@ status = "disabled"; }; - i2c@11003000 { + i2c0: i2c@11003000 { compatible = "mediatek,mt7981-i2c"; reg = <0 0x11003000 0 0x1000>, <0 0x10217080 0 0x80>; interrupts = ; + clock-div = <1>; clocks = <&infracfg CLK_INFRA_I2C_BCK>, <&infracfg CLK_INFRA_66M_AP_DMA_BCK>; clock-names = "main", "dma"; @@ -170,11 +283,12 @@ status = "disabled"; }; - i2c@11004000 { + i2c1: i2c@11004000 { compatible = "mediatek,mt7981-i2c"; reg = <0 0x11004000 0 0x1000>, <0 0x10217100 0 0x80>; interrupts = ; + clock-div = <1>; clocks = <&infracfg CLK_INFRA_I2C_BCK>, <&infracfg CLK_INFRA_66M_AP_DMA_BCK>; clock-names = "main", "dma"; @@ -183,11 +297,12 @@ status = "disabled"; }; - i2c@11005000 { + i2c2: i2c@11005000 { compatible = "mediatek,mt7981-i2c"; reg = <0 0x11005000 0 0x1000>, <0 0x10217180 0 0x80>; interrupts = ; + clock-div = <1>; clocks = <&infracfg CLK_INFRA_I2C_BCK>, <&infracfg CLK_INFRA_66M_AP_DMA_BCK>; clock-names = "main", "dma"; @@ -196,6 +311,17 @@ status = "disabled"; }; + lvts: lvts@1100a000 { + compatible = "mediatek,mt7988-lvts-ap"; + #thermal-sensor-cells = <1>; + reg = <0 0x1100a000 0 0x1000>; + clocks = <&infracfg CLK_INFRA_26M_THERM_SYSTEM>; + interrupts = ; + resets = <&infracfg MT7988_INFRA_RST1_THERM_CTRL_SWRST>; + nvmem-cells = <&lvts_calibration>; + nvmem-cell-names = "lvts-calib-data-1"; + }; + usb@11190000 { compatible = "mediatek,mt7988-xhci", "mediatek,mtk-xhci"; reg = <0 0x11190000 0 0x2e00>, @@ -208,9 +334,10 @@ <&infracfg CLK_INFRA_133M_USB_HCK>, <&infracfg CLK_INFRA_USB_XHCI>; clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck"; + status = "disabled"; }; - usb@11200000 { + ssusb1: usb@11200000 { compatible = "mediatek,mt7988-xhci", "mediatek,mtk-xhci"; reg = <0 0x11200000 0 0x2e00>, <0 0x11203e00 0 0x0100>; @@ -222,6 +349,203 @@ <&infracfg CLK_INFRA_133M_USB_HCK_CK_P1>, <&infracfg CLK_INFRA_USB_XHCI_CK_P1>; clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck"; + phys = <&tphyu2port0 PHY_TYPE_USB2>, + <&tphyu3port0 PHY_TYPE_USB3>; + status = "disabled"; + }; + + mmc0: mmc@11230000 { + compatible = "mediatek,mt7988-mmc"; + reg = <0 0x11230000 0 0x1000>, + <0 0x11D60000 0 0x1000>; + interrupts = ; + clocks = <&infracfg CLK_INFRA_MSDC400>, + <&infracfg CLK_INFRA_MSDC2_HCK>, + <&infracfg CLK_INFRA_66M_MSDC_0_HCK>, + <&infracfg CLK_INFRA_133M_MSDC_0_HCK>; + assigned-clocks = <&topckgen CLK_TOP_EMMC_250M_SEL>, + <&topckgen CLK_TOP_EMMC_400M_SEL>; + assigned-clock-parents = <&topckgen CLK_TOP_NET1PLL_D5_D2>, + <&apmixedsys CLK_APMIXED_MSDCPLL>; + clock-names = "source", "hclk", "axi_cg", "ahb_cg"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + pcie2: pcie@11280000 { + compatible = "mediatek,mt7986-pcie", + "mediatek,mt8192-pcie"; + device_type = "pci"; + #address-cells = <3>; + #size-cells = <2>; + reg = <0 0x11280000 0 0x2000>; + reg-names = "pcie-mac"; + linux,pci-domain = <3>; + interrupts = ; + bus-range = <0x00 0xff>; + ranges = <0x81000000 0x00 0x20000000 0x00 + 0x20000000 0x00 0x00200000>, + <0x82000000 0x00 0x20200000 0x00 + 0x20200000 0x00 0x07e00000>; + clocks = <&infracfg CLK_INFRA_PCIE_PIPE_P2>, + <&infracfg CLK_INFRA_PCIE_GFMUX_TL_P2>, + <&infracfg CLK_INFRA_PCIE_PERI_26M_CK_P2>, + <&infracfg CLK_INFRA_133M_PCIE_CK_P2>; + clock-names = "pl_250m", "tl_26m", "peri_26m", + "top_133m"; + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_pins>; + status = "disabled"; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &pcie_intc2 0>, + <0 0 0 2 &pcie_intc2 1>, + <0 0 0 3 &pcie_intc2 2>, + <0 0 0 4 &pcie_intc2 3>; + pcie_intc2: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + pcie3: pcie@11290000 { + compatible = "mediatek,mt7986-pcie", + "mediatek,mt8192-pcie"; + device_type = "pci"; + #address-cells = <3>; + #size-cells = <2>; + reg = <0 0x11290000 0 0x2000>; + reg-names = "pcie-mac"; + linux,pci-domain = <2>; + interrupts = ; + bus-range = <0x00 0xff>; + ranges = <0x81000000 0x00 0x28000000 0x00 + 0x28000000 0x00 0x00200000>, + <0x82000000 0x00 0x28200000 0x00 + 0x28200000 0x00 0x07e00000>; + clocks = <&infracfg CLK_INFRA_PCIE_PIPE_P3>, + <&infracfg CLK_INFRA_PCIE_GFMUX_TL_P3>, + <&infracfg CLK_INFRA_PCIE_PERI_26M_CK_P3>, + <&infracfg CLK_INFRA_133M_PCIE_CK_P3>; + clock-names = "pl_250m", "tl_26m", "peri_26m", + "top_133m"; + pinctrl-names = "default"; + pinctrl-0 = <&pcie3_pins>; + status = "disabled"; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &pcie_intc3 0>, + <0 0 0 2 &pcie_intc3 1>, + <0 0 0 3 &pcie_intc3 2>, + <0 0 0 4 &pcie_intc3 3>; + pcie_intc3: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + pcie0: pcie@11300000 { + compatible = "mediatek,mt7986-pcie", + "mediatek,mt8192-pcie"; + device_type = "pci"; + #address-cells = <3>; + #size-cells = <2>; + reg = <0 0x11300000 0 0x2000>; + reg-names = "pcie-mac"; + linux,pci-domain = <0>; + interrupts = ; + bus-range = <0x00 0xff>; + ranges = <0x81000000 0x00 0x30000000 0x00 + 0x30000000 0x00 0x00200000>, + <0x82000000 0x00 0x30200000 0x00 + 0x30200000 0x00 0x07e00000>; + clocks = <&infracfg CLK_INFRA_PCIE_PIPE_P0>, + <&infracfg CLK_INFRA_PCIE_GFMUX_TL_P0>, + <&infracfg CLK_INFRA_PCIE_PERI_26M_CK_P0>, + <&infracfg CLK_INFRA_133M_PCIE_CK_P0>; + clock-names = "pl_250m", "tl_26m", "peri_26m", + "top_133m"; + pinctrl-names = "default"; + pinctrl-0 = <&pcie0_pins>; + status = "disabled"; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &pcie_intc0 0>, + <0 0 0 2 &pcie_intc0 1>, + <0 0 0 3 &pcie_intc0 2>, + <0 0 0 4 &pcie_intc0 3>; + pcie_intc0: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + pcie1: pcie@11310000 { + compatible = "mediatek,mt7986-pcie", + "mediatek,mt8192-pcie"; + device_type = "pci"; + #address-cells = <3>; + #size-cells = <2>; + reg = <0 0x11310000 0 0x2000>; + reg-names = "pcie-mac"; + linux,pci-domain = <1>; + interrupts = ; + bus-range = <0x00 0xff>; + ranges = <0x81000000 0x00 0x38000000 0x00 + 0x38000000 0x00 0x00200000>, + <0x82000000 0x00 0x38200000 0x00 + 0x38200000 0x00 0x07e00000>; + clocks = <&infracfg CLK_INFRA_PCIE_PIPE_P1>, + <&infracfg CLK_INFRA_PCIE_GFMUX_TL_P1>, + <&infracfg CLK_INFRA_PCIE_PERI_26M_CK_P1>, + <&infracfg CLK_INFRA_133M_PCIE_CK_P1>; + clock-names = "pl_250m", "tl_26m", "peri_26m", + "top_133m"; + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_pins>; + status = "disabled"; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &pcie_intc1 0>, + <0 0 0 2 &pcie_intc1 1>, + <0 0 0 3 &pcie_intc1 2>, + <0 0 0 4 &pcie_intc1 3>; + pcie_intc1: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + tphy: t-phy@11c50000 { + compatible = "mediatek,mt7986-tphy", + "mediatek,generic-tphy-v2"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + status = "disabled"; + + tphyu2port0: usb-phy@11c50000 { + reg = <0 0x11c50000 0 0x700>; + clocks = <&infracfg CLK_INFRA_USB_UTMI_CK_P1>; + clock-names = "ref"; + #phy-cells = <1>; + }; + + tphyu3port0: usb-phy@11c50700 { + reg = <0 0x11c50700 0 0x900>; + clocks = <&infracfg CLK_INFRA_USB_PIPE_CK_P1>; + clock-names = "ref"; + #phy-cells = <1>; + }; }; clock-controller@11f40000 { @@ -236,6 +560,10 @@ reg = <0 0x11f50000 0 0x1000>; #address-cells = <1>; #size-cells = <1>; + + lvts_calibration: calib@918 { + reg = <0x918 0x28>; + }; }; clock-controller@15000000 { @@ -253,6 +581,21 @@ }; }; + thermal-zones { + cpu_thermal: cpu-thermal { + polling-delay-passive = <1000>; + polling-delay = <1000>; + thermal-sensors = <&lvts 0>; + trips { + cpu_trip_crit: crit { + temperature = <125000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + }; + timer { compatible = "arm,armv8-timer"; interrupt-parent = <&gic>; diff --git a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi index eee64461421f..b5d4b5baf478 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi @@ -931,7 +931,7 @@ interrupt-controller; #interrupt-cells = <2>; - clock: mt6397clock { + clock: clocks { compatible = "mediatek,mt6397-clk"; #clock-cells = <1>; }; @@ -942,11 +942,10 @@ #gpio-cells = <2>; }; - regulator: mt6397regulator { + regulators { compatible = "mediatek,mt6397-regulator"; mt6397_vpca15_reg: buck_vpca15 { - regulator-compatible = "buck_vpca15"; regulator-name = "vpca15"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -956,7 +955,6 @@ }; mt6397_vpca7_reg: buck_vpca7 { - regulator-compatible = "buck_vpca7"; regulator-name = "vpca7"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -966,7 +964,6 @@ }; mt6397_vsramca15_reg: buck_vsramca15 { - regulator-compatible = "buck_vsramca15"; regulator-name = "vsramca15"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -975,7 +972,6 @@ }; mt6397_vsramca7_reg: buck_vsramca7 { - regulator-compatible = "buck_vsramca7"; regulator-name = "vsramca7"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -984,7 +980,6 @@ }; mt6397_vcore_reg: buck_vcore { - regulator-compatible = "buck_vcore"; regulator-name = "vcore"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -993,7 +988,6 @@ }; mt6397_vgpu_reg: buck_vgpu { - regulator-compatible = "buck_vgpu"; regulator-name = "vgpu"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -1002,7 +996,6 @@ }; mt6397_vdrm_reg: buck_vdrm { - regulator-compatible = "buck_vdrm"; regulator-name = "vdrm"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1400000>; @@ -1011,7 +1004,6 @@ }; mt6397_vio18_reg: buck_vio18 { - regulator-compatible = "buck_vio18"; regulator-name = "vio18"; regulator-min-microvolt = <1620000>; regulator-max-microvolt = <1980000>; @@ -1020,18 +1012,15 @@ }; mt6397_vtcxo_reg: ldo_vtcxo { - regulator-compatible = "ldo_vtcxo"; regulator-name = "vtcxo"; regulator-always-on; }; mt6397_va28_reg: ldo_va28 { - regulator-compatible = "ldo_va28"; regulator-name = "va28"; }; mt6397_vcama_reg: ldo_vcama { - regulator-compatible = "ldo_vcama"; regulator-name = "vcama"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -1039,18 +1028,15 @@ }; mt6397_vio28_reg: ldo_vio28 { - regulator-compatible = "ldo_vio28"; regulator-name = "vio28"; regulator-always-on; }; mt6397_vusb_reg: ldo_vusb { - regulator-compatible = "ldo_vusb"; regulator-name = "vusb"; }; mt6397_vmc_reg: ldo_vmc { - regulator-compatible = "ldo_vmc"; regulator-name = "vmc"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; @@ -1058,7 +1044,6 @@ }; mt6397_vmch_reg: ldo_vmch { - regulator-compatible = "ldo_vmch"; regulator-name = "vmch"; regulator-min-microvolt = <3000000>; regulator-max-microvolt = <3300000>; @@ -1066,7 +1051,6 @@ }; mt6397_vemc_3v3_reg: ldo_vemc3v3 { - regulator-compatible = "ldo_vemc3v3"; regulator-name = "vemc_3v3"; regulator-min-microvolt = <3000000>; regulator-max-microvolt = <3300000>; @@ -1074,7 +1058,6 @@ }; mt6397_vgp1_reg: ldo_vgp1 { - regulator-compatible = "ldo_vgp1"; regulator-name = "vcamd"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -1082,7 +1065,6 @@ }; mt6397_vgp2_reg: ldo_vgp2 { - regulator-compatible = "ldo_vgp2"; regulator-name = "vcamio"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; @@ -1090,7 +1072,6 @@ }; mt6397_vgp3_reg: ldo_vgp3 { - regulator-compatible = "ldo_vgp3"; regulator-name = "vcamaf"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -1098,7 +1079,6 @@ }; mt6397_vgp4_reg: ldo_vgp4 { - regulator-compatible = "ldo_vgp4"; regulator-name = "vgp4"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <3300000>; @@ -1106,7 +1086,6 @@ }; mt6397_vgp5_reg: ldo_vgp5 { - regulator-compatible = "ldo_vgp5"; regulator-name = "vgp5"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <3000000>; @@ -1114,7 +1093,6 @@ }; mt6397_vgp6_reg: ldo_vgp6 { - regulator-compatible = "ldo_vgp6"; regulator-name = "vgp6"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; @@ -1123,7 +1101,6 @@ }; mt6397_vibr_reg: ldo_vibr { - regulator-compatible = "ldo_vibr"; regulator-name = "vibr"; regulator-min-microvolt = <1300000>; regulator-max-microvolt = <3300000>; @@ -1131,7 +1108,7 @@ }; }; - rtc: mt6397rtc { + rtc: rtc { compatible = "mediatek,mt6397-rtc"; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts index bb4671c18e3b..9fffed0ef4bf 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts @@ -307,11 +307,10 @@ interrupt-controller; #interrupt-cells = <2>; - mt6397regulator: mt6397regulator { + regulators { compatible = "mediatek,mt6397-regulator"; mt6397_vpca15_reg: buck_vpca15 { - regulator-compatible = "buck_vpca15"; regulator-name = "vpca15"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -320,7 +319,6 @@ }; mt6397_vpca7_reg: buck_vpca7 { - regulator-compatible = "buck_vpca7"; regulator-name = "vpca7"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -329,7 +327,6 @@ }; mt6397_vsramca15_reg: buck_vsramca15 { - regulator-compatible = "buck_vsramca15"; regulator-name = "vsramca15"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -338,7 +335,6 @@ }; mt6397_vsramca7_reg: buck_vsramca7 { - regulator-compatible = "buck_vsramca7"; regulator-name = "vsramca7"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -347,7 +343,6 @@ }; mt6397_vcore_reg: buck_vcore { - regulator-compatible = "buck_vcore"; regulator-name = "vcore"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -356,7 +351,6 @@ }; mt6397_vgpu_reg: buck_vgpu { - regulator-compatible = "buck_vgpu"; regulator-name = "vgpu"; regulator-min-microvolt = < 700000>; regulator-max-microvolt = <1350000>; @@ -365,7 +359,6 @@ }; mt6397_vdrm_reg: buck_vdrm { - regulator-compatible = "buck_vdrm"; regulator-name = "vdrm"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1400000>; @@ -374,7 +367,6 @@ }; mt6397_vio18_reg: buck_vio18 { - regulator-compatible = "buck_vio18"; regulator-name = "vio18"; regulator-min-microvolt = <1620000>; regulator-max-microvolt = <1980000>; @@ -383,19 +375,16 @@ }; mt6397_vtcxo_reg: ldo_vtcxo { - regulator-compatible = "ldo_vtcxo"; regulator-name = "vtcxo"; regulator-always-on; }; mt6397_va28_reg: ldo_va28 { - regulator-compatible = "ldo_va28"; regulator-name = "va28"; regulator-always-on; }; mt6397_vcama_reg: ldo_vcama { - regulator-compatible = "ldo_vcama"; regulator-name = "vcama"; regulator-min-microvolt = <1500000>; regulator-max-microvolt = <2800000>; @@ -403,18 +392,15 @@ }; mt6397_vio28_reg: ldo_vio28 { - regulator-compatible = "ldo_vio28"; regulator-name = "vio28"; regulator-always-on; }; mt6397_vusb_reg: ldo_vusb { - regulator-compatible = "ldo_vusb"; regulator-name = "vusb"; }; mt6397_vmc_reg: ldo_vmc { - regulator-compatible = "ldo_vmc"; regulator-name = "vmc"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; @@ -422,7 +408,6 @@ }; mt6397_vmch_reg: ldo_vmch { - regulator-compatible = "ldo_vmch"; regulator-name = "vmch"; regulator-min-microvolt = <3000000>; regulator-max-microvolt = <3300000>; @@ -430,7 +415,6 @@ }; mt6397_vemc_3v3_reg: ldo_vemc3v3 { - regulator-compatible = "ldo_vemc3v3"; regulator-name = "vemc_3v3"; regulator-min-microvolt = <3000000>; regulator-max-microvolt = <3300000>; @@ -438,7 +422,6 @@ }; mt6397_vgp1_reg: ldo_vgp1 { - regulator-compatible = "ldo_vgp1"; regulator-name = "vcamd"; regulator-min-microvolt = <1220000>; regulator-max-microvolt = <3300000>; @@ -446,7 +429,6 @@ }; mt6397_vgp2_reg: ldo_vgp2 { - regulator-compatible = "ldo_vgp2"; regulator-name = "vcamio"; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <3300000>; @@ -454,7 +436,6 @@ }; mt6397_vgp3_reg: ldo_vgp3 { - regulator-compatible = "ldo_vgp3"; regulator-name = "vcamaf"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <3300000>; @@ -462,7 +443,6 @@ }; mt6397_vgp4_reg: ldo_vgp4 { - regulator-compatible = "ldo_vgp4"; regulator-name = "vgp4"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <3300000>; @@ -470,7 +450,6 @@ }; mt6397_vgp5_reg: ldo_vgp5 { - regulator-compatible = "ldo_vgp5"; regulator-name = "vgp5"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <3000000>; @@ -478,7 +457,6 @@ }; mt6397_vgp6_reg: ldo_vgp6 { - regulator-compatible = "ldo_vgp6"; regulator-name = "vgp6"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <3300000>; @@ -486,7 +464,6 @@ }; mt6397_vibr_reg: ldo_vibr { - regulator-compatible = "ldo_vibr"; regulator-name = "vibr"; regulator-min-microvolt = <1300000>; regulator-max-microvolt = <3300000>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts index 65860b33c01f..3935d83a047e 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts @@ -26,6 +26,10 @@ hid-descr-addr = <0x0001>; }; +&mt6358codec { + mediatek,dmic-mode = <1>; /* one-wire */ +}; + &qca_wifi { qcom,ath10k-calibration-variant = "GO_DAMU"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-kenzo.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-kenzo.dts index e8241587949b..561770fcf69e 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-kenzo.dts +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-kenzo.dts @@ -12,3 +12,18 @@ chassis-type = "laptop"; compatible = "google,juniper-sku17", "google,juniper", "mediatek,mt8183"; }; + +&i2c0 { + touchscreen@40 { + compatible = "hid-over-i2c"; + reg = <0x40>; + + pinctrl-names = "default"; + pinctrl-0 = <&touchscreen_pins>; + + interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>; + + post-power-on-delay-ms = <70>; + hid-descr-addr = <0x0001>; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-willow.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-willow.dtsi index 76d33540166f..c942e461a177 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-willow.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-willow.dtsi @@ -6,6 +6,21 @@ /dts-v1/; #include "mt8183-kukui-jacuzzi.dtsi" +&i2c0 { + touchscreen@40 { + compatible = "hid-over-i2c"; + reg = <0x40>; + + pinctrl-names = "default"; + pinctrl-0 = <&touchscreen_pins>; + + interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>; + + post-power-on-delay-ms = <70>; + hid-descr-addr = <0x0001>; + }; +}; + &i2c2 { trackpad@2c { compatible = "hid-over-i2c"; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi index 49e053b932e7..80888bd4ad82 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi @@ -39,8 +39,6 @@ pp3300_panel: pp3300-panel { compatible = "regulator-fixed"; regulator-name = "pp3300_panel"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; pinctrl-names = "default"; pinctrl-0 = <&pp3300_panel_pins>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi index 4b974bb781b1..e1495f1900a7 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi @@ -269,11 +269,6 @@ }; }; -&dpi0 { - /* TODO Re-enable after DP to Type-C port muxing can be described */ - status = "disabled"; -}; - &gic { mediatek,broken-save-restore-fw; }; @@ -944,13 +939,13 @@ }; &thermal_zones { - tboard1 { + tboard1-thermal { polling-delay = <1000>; /* milliseconds */ polling-delay-passive = <0>; /* milliseconds */ thermal-sensors = <&tboard_thermistor1>; }; - tboard2 { + tboard2-thermal { polling-delay = <1000>; /* milliseconds */ polling-delay-passive = <0>; /* milliseconds */ thermal-sensors = <&tboard_thermistor2>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts index 61a6f66914b8..dbdee604edab 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts +++ b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts @@ -522,10 +522,6 @@ status = "okay"; }; -&dsi0 { - status = "disabled"; -}; - &dpi0 { pinctrl-names = "default", "sleep"; pinctrl-0 = <&dpi_func_pins>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi index 1afeeb1155f5..0aa34e5bbaaa 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi @@ -1024,7 +1024,8 @@ }; keyboard: keyboard@10010000 { - compatible = "mediatek,mt6779-keypad"; + compatible = "mediatek,mt8183-keypad", + "mediatek,mt6779-keypad"; reg = <0 0x10010000 0 0x1000>; interrupts = ; clocks = <&clk26m>; @@ -1834,6 +1835,7 @@ resets = <&mmsys MT8183_MMSYS_SW0_RST_B_DISP_DSI0>; phys = <&mipi_tx0>; phy-names = "dphy"; + status = "disabled"; }; dpi0: dpi@14015000 { @@ -1845,6 +1847,7 @@ <&mmsys CLK_MM_DPI_MM>, <&apmixedsys CLK_APMIXED_TVDPLL>; clock-names = "pixel", "engine", "pll"; + status = "disabled"; port { dpi_out: endpoint { }; diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou-sku0.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou-sku0.dts new file mode 100644 index 000000000000..5d012bc4ff0d --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou-sku0.dts @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ + +/dts-v1/; +#include "mt8186-corsola-chinchou.dtsi" + +/ { + model = "Google chinchou CZ1104CM2A/CZ1204CM2A"; + compatible = "google,chinchou-sku0", "google,chinchou-sku2", + "google,chinchou-sku4", "google,chinchou-sku5", + "google,chinchou", "mediatek,mt8186"; +}; + +&gpio_keys { + status = "disabled"; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou-sku1.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou-sku1.dts new file mode 100644 index 000000000000..9d6e62af6944 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou-sku1.dts @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ + +/dts-v1/; +#include "mt8186-corsola-chinchou.dtsi" + +/ { + model = "Google chinchou CZ1104FM2A/CZ1204FM2A/CZ1104CM2A/CZ1204CM2A"; + compatible = "google,chinchou-sku1", "google,chinchou-sku3", + "google,chinchou-sku6", "google,chinchou-sku7", + "google,chinchou-sku17", "google,chinchou-sku20", + "google,chinchou-sku22", "google,chinchou-sku23", + "google,chinchou", "mediatek,mt8186"; +}; + +&gpio_keys { + status = "disabled"; +}; + +&i2c1 { + i2c-scl-internal-delay-ns = <10000>; + + touchscreen: touchscreen@41 { + compatible = "ilitek,ili2901"; + reg = <0x41>; + interrupts-extended = <&pio 12 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&touchscreen_pins>; + reset-gpios = <&pio 60 GPIO_ACTIVE_LOW>; + vccio-supply = <&pp1800_tchscr_report_disable>; + vcc33-supply = <&pp3300_z2>; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou-sku16.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou-sku16.dts new file mode 100644 index 000000000000..eb377de1fcde --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou-sku16.dts @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ + +/dts-v1/; +#include "mt8186-corsola-chinchou.dtsi" + +/ { + model = "Google chinchou CZ1104FM2A/CZ1204FM2A"; + compatible = "google,chinchou-sku16", "google,chinchou-sku18", + "google,chinchou-sku19", "google,chinchou-sku21", + "google,chinchou", "mediatek,mt8186"; +}; + +&i2c1 { + i2c-scl-internal-delay-ns = <10000>; + + touchscreen: touchscreen@41 { + compatible = "ilitek,ili2901"; + reg = <0x41>; + interrupts-extended = <&pio 12 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&touchscreen_pins>; + reset-gpios = <&pio 60 GPIO_ACTIVE_LOW>; + vccio-supply = <&pp1800_tchscr_report_disable>; + vcc33-supply = <&pp3300_z2>; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou.dtsi b/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou.dtsi new file mode 100644 index 000000000000..800792157021 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-chinchou.dtsi @@ -0,0 +1,321 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ + +/dts-v1/; +#include "mt8186-corsola.dtsi" + +/ { + /delete-node/ speaker-codec; + + pp1000_edpbrdg: regulator-pp1000-edpbrdg { + compatible = "regulator-fixed"; + regulator-name = "pp1000_edpbrdg"; + pinctrl-names = "default"; + pinctrl-0 = <&en_pp1000_edpbrdg>; + enable-active-high; + regulator-boot-on; + gpio = <&pio 29 GPIO_ACTIVE_HIGH>; + vin-supply = <&pp3300_z2>; + }; + + pp1800_edpbrdg_dx: regulator-pp1800-edpbrdg-dx { + compatible = "regulator-fixed"; + regulator-name = "pp1800_edpbrdg_dx"; + pinctrl-names = "default"; + pinctrl-0 = <&en_pp1800_edpbrdg>; + enable-active-high; + regulator-boot-on; + gpio = <&pio 30 GPIO_ACTIVE_HIGH>; + vin-supply = <&mt6366_vio18_reg>; + }; + + pp3300_edp_dx: regulator-pp3300-edp-dx { + compatible = "regulator-fixed"; + regulator-name = "pp3300_edp_dx"; + pinctrl-names = "default"; + pinctrl-0 = <&en_pp3300_edpbrdg>; + enable-active-high; + regulator-boot-on; + gpio = <&pio 31 GPIO_ACTIVE_HIGH>; + vin-supply = <&pp3300_z2>; + }; + + pp1800_tchscr_report_disable: regulator-pp1800-tchscr-report-disable { + compatible = "regulator-fixed"; + regulator-name = "pp1800_tchscr_report_disable"; + pinctrl-names = "default"; + regulator-boot-on; + pinctrl-0 = <&touch_pin_report>; + gpio = <&pio 37 GPIO_ACTIVE_LOW>; + }; +}; + +&dsi_out { + remote-endpoint = <&anx7625_in>; +}; + +&i2c0 { + clock-frequency = <400000>; + + anx_bridge: anx7625@58 { + compatible = "analogix,anx7625"; + reg = <0x58>; + pinctrl-names = "default"; + pinctrl-0 = <&anx7625_pins>; + enable-gpios = <&pio 96 GPIO_ACTIVE_HIGH>; + reset-gpios = <&pio 98 GPIO_ACTIVE_HIGH>; + vdd10-supply = <&pp1000_edpbrdg>; + vdd18-supply = <&pp1800_edpbrdg_dx>; + vdd33-supply = <&pp3300_edp_dx>; + analogix,lane0-swing = /bits/ 8 <0x70 0x30>; + analogix,lane1-swing = /bits/ 8 <0x70 0x30>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + anx7625_in: endpoint { + remote-endpoint = <&dsi_out>; + data-lanes = <0 1 2 3>; + }; + }; + + port@1 { + reg = <1>; + + anx7625_out: endpoint { + remote-endpoint = <&panel_in>; + }; + }; + }; + + aux-bus { + panel: panel { + compatible = "edp-panel"; + power-supply = <&pp3300_disp_x>; + backlight = <&backlight_lcd0>; + + port { + panel_in: endpoint { + remote-endpoint = <&anx7625_out>; + }; + }; + }; + }; + }; +}; + +&i2c2 { + /delete-node/ trackpad@15; + + touchpad@15 { + compatible = "hid-over-i2c"; + reg = <0x15>; + interrupts-extended = <&pio 11 IRQ_TYPE_LEVEL_LOW>; + post-power-on-delay-ms = <10>; + hid-descr-addr = <0x0001>; + vdd-supply = <&pp3300_s3>; + wakeup-source; + }; +}; + +&i2c5 { + clock-frequency = <400000>; + /delete-node/ codec@1a; + + rt5650: rt5650@1a { + compatible = "realtek,rt5650"; + reg = <0x1a>; + avdd-supply = <&mt6366_vio18_reg>; + cpvdd-supply = <&mt6366_vio18_reg>; + pinctrl-names = "default"; + pinctrl-0 = <&speaker_codec_pins_default>; + cbj-sleeve-gpios = <&pio 150 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&pio>; + interrupts = <17 IRQ_TYPE_EDGE_BOTH>; + #sound-dai-cells = <0>; + realtek,dmic1-data-pin = <2>; + realtek,jd-mode = <2>; + }; +}; + +&i2c_tunnel { + /delete-node/ sbs-battery@b; + + battery: sbs-battery@f { + compatible = "sbs,sbs-battery"; + reg = <0xf>; + sbs,i2c-retry-count = <2>; + sbs,poll-retry-count = <1>; + }; +}; + +&keyboard_controller { + keypad,num-columns = <15>; + + function-row-physmap = < + MATRIX_KEY(0x00, 0x02, 0) /* T1 */ + MATRIX_KEY(0x03, 0x02, 0) /* T2 */ + MATRIX_KEY(0x02, 0x02, 0) /* T3 */ + MATRIX_KEY(0x01, 0x02, 0) /* T4 */ + MATRIX_KEY(0x03, 0x04, 0) /* T5 */ + MATRIX_KEY(0x02, 0x04, 0) /* T6 */ + MATRIX_KEY(0x01, 0x04, 0) /* T7 */ + MATRIX_KEY(0x02, 0x09, 0) /* T8 */ + MATRIX_KEY(0x01, 0x09, 0) /* T9 */ + MATRIX_KEY(0x00, 0x04, 0) /* T10 */ + MATRIX_KEY(0x00, 0x01, 0) /* T11 */ + MATRIX_KEY(0x01, 0x05, 0) /* T12 */ + >; + + linux,keymap = < + CROS_STD_MAIN_KEYMAP + MATRIX_KEY(0x00, 0x02, KEY_BACK) /* T1 */ + MATRIX_KEY(0x03, 0x02, KEY_REFRESH) /* T2 */ + MATRIX_KEY(0x02, 0x02, KEY_ZOOM) /* T3 */ + MATRIX_KEY(0x01, 0x02, KEY_SCALE) /* T4 */ + MATRIX_KEY(0x03, 0x04, KEY_SYSRQ) /* T5 */ + MATRIX_KEY(0x02, 0x04, KEY_BRIGHTNESSDOWN) /* T6 */ + MATRIX_KEY(0x01, 0x04, KEY_BRIGHTNESSUP) /* T7 */ + MATRIX_KEY(0x02, 0x09, KEY_MUTE) /* T8 */ + MATRIX_KEY(0x01, 0x09, KEY_VOLUMEDOWN) /* T9 */ + MATRIX_KEY(0x00, 0x04, KEY_VOLUMEUP) /* T10 */ + MATRIX_KEY(0x00, 0x01, KEY_MICMUTE) /* T11 */ + MATRIX_KEY(0x01, 0x05, KEY_CONTROLPANEL) /* T12 */ + MATRIX_KEY(0x03, 0x05, KEY_PREVIOUSSONG) /* T13 */ + MATRIX_KEY(0x00, 0x09, KEY_PLAYPAUSE) /* T14 */ + MATRIX_KEY(0x00, 0x0b, KEY_NEXTSONG) /* T15 */ + MATRIX_KEY(0x03, 0x00, KEY_LEFTMETA) /* Search*/ + MATRIX_KEY(0x01, 0x0e, KEY_LEFTCTRL) /* Left Control*/ + MATRIX_KEY(0x06, 0x0d, KEY_LEFTALT) /* Left ALT*/ + MATRIX_KEY(0x03, 0x0e, KEY_RIGHTCTRL) /* Right Control*/ + MATRIX_KEY(0x06, 0x0a, KEY_BACKSLASH) /* BACKSLASH*/ + >; +}; + +&mmc1_pins_default { + pins-clk { + drive-strength = <8>; + }; + + pins-cmd-dat { + drive-strength = <8>; + }; +}; + +&mmc1_pins_uhs { + pins-clk { + drive-strength = <8>; + }; + + pins-cmd-dat { + drive-strength = <8>; + }; +}; + +&pen_insert { + wakeup-event-action = ; +}; + +&pio { + anx7625_pins: anx7625-pins { + pins-int { + pinmux = ; + input-enable; + bias-disable; + }; + + pins-reset { + pinmux = ; + output-low; + }; + + pins-power-en { + pinmux = ; + output-low; + }; + }; + + en_pp1000_edpbrdg: pp1000-edpbrdg-en-pins { + pins-vreg-en { + pinmux = ; + output-low; + }; + }; + + en_pp1800_edpbrdg: pp1800-edpbrdg-en-pins { + pins-vreg-en { + pinmux = ; + output-low; + }; + }; + + en_pp3300_edpbrdg: pp3300-edpbrdg-en-pins { + pins-vreg-en { + pinmux = ; + output-low; + }; + }; + + touch_pin_report: pin-report-pins { + pins-touch-en { + pinmux = ; + output-low; + }; + }; +}; + +&sound { + compatible = "mediatek,mt8186-mt6366-rt5650-sound"; + model = "mt8186_rt5650"; + mediatek,adsp = <&adsp>; + + audio-routing = + "Headphone", "HPOL", + "Headphone", "HPOR", + "IN1P", "Headset Mic", + "IN1N", "Headset Mic", + "Speakers", "SPOL", + "Speakers", "SPOR", + "HDMI1", "TX"; + + hs-playback-dai-link { + codec { + sound-dai = <&rt5650>; + }; + }; + + hs-capture-dai-link { + codec { + sound-dai = <&rt5650>; + }; + }; + + spk-share-dai-link { + }; + + spk-hdmi-playback-dai-link { + codec { + sound-dai = <&it6505dptx>; + }; + }; +}; + +&touchscreen_pins { + /delete-node/ pins-report-sw; +}; + +&wifi_enable_pin { + pins-wifi-enable { + pinmux = ; + }; +}; + +&wifi_pwrseq { + reset-gpios = <&pio 51 GPIO_ACTIVE_LOW>; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-starmie-sku0.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-starmie-sku0.dts new file mode 100644 index 000000000000..23e194579bf2 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-starmie-sku0.dts @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2023 Google LLC + */ + +/dts-v1/; +#include "mt8186-corsola-starmie.dtsi" + +/ { + model = "Google Starmie sku0 board"; + compatible = "google,starmie-sku0", "google,starmie-sku2", + "google,starmie-sku3", "google,starmie", + "mediatek,mt8186"; +}; + +&panel { + compatible = "starry,ili9882t"; +}; + +&i2c1 { + touchscreen: touchscreen@41 { + compatible = "ilitek,ili9882t"; + reg = <0x41>; + interrupts-extended = <&pio 12 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&touchscreen_pins>; + panel = <&panel>; + reset-gpios = <&pio 60 GPIO_ACTIVE_LOW>; + vccio-supply = <&mt6366_vio18_reg>; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-starmie-sku1.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-starmie-sku1.dts new file mode 100644 index 000000000000..214b972c9357 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-starmie-sku1.dts @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2023 Google LLC + */ + +/dts-v1/; +#include "mt8186-corsola-starmie.dtsi" + +/ { + model = "Google Starmie sku1 board"; + compatible = "google,starmie-sku1", "google,starmie-sku4", + "google,starmie", "mediatek,mt8186"; +}; + +&panel { + compatible = "starry,himax83102-j02", "himax,hx83102"; +}; + +&i2c1 { + touchscreen_himax: touchscreen@4f { + compatible = "hid-over-i2c"; + reg = <0x4f>; + interrupts-extended = <&pio 12 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&touchscreen_pins>; + vdd-supply = <&mt6366_vio18_reg>; + panel = <&panel>; + post-power-on-delay-ms = <450>; + hid-descr-addr = <0x0001>; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-starmie.dtsi b/arch/arm64/boot/dts/mediatek/mt8186-corsola-starmie.dtsi new file mode 100644 index 000000000000..5ea8bdc00e81 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-starmie.dtsi @@ -0,0 +1,472 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2023 Google LLC + */ + +/dts-v1/; +#include "mt8186-corsola.dtsi" + +/ { + en_pp6000_mipi_disp_150ma: en-pp6000-mipi-disp-150ma { + compatible = "regulator-fixed"; + regulator-name = "en_pp6000_mipi_disp_150ma"; + gpio = <&pio 154 GPIO_ACTIVE_HIGH>; + enable-active-high; + pinctrl-names = "default"; + pinctrl-0 = <&en_pp6000_mipi_disp_150ma_fixed_pins>; + }; + + /* + * Starmie does not have 3.3V display regulator. It is replaced + * with 6V module for enabling panel, re-using eDP GPIOs. + */ + /delete-node/ pp3300_disp_x; + en_pp6000_mipi_disp: en-regulator-pp6000-mipi-disp { + compatible = "regulator-fixed"; + pinctrl-names = "default"; + pinctrl-0 = <&edp_panel_fixed_pins>; + gpios = <&pio 153 GPIO_ACTIVE_HIGH>; + regulator-name = "en_pp6000_mipi_disp"; + enable-active-high; + regulator-enable-ramp-delay = <3000>; + vin-supply = <&pp3300_z2>; + }; + + tboard_thermistor1: thermal-sensor1 { + compatible = "generic-adc-thermal"; + #thermal-sensor-cells = <0>; + io-channels = <&auxadc 0>; + io-channel-names = "sensor-channel"; + temperature-lookup-table = < (-5000) 1492 + 0 1413 + 5000 1324 + 10000 1227 + 15000 1121 + 20000 1017 + 25000 900 + 30000 797 + 35000 698 + 40000 606 + 45000 522 + 50000 449 + 55000 383 + 60000 327 + 65000 278 + 70000 236 + 75000 201 + 80000 171 + 85000 145 + 90000 163 + 95000 124 + 100000 91 + 105000 78 + 110000 67 + 115000 58 + 120000 50 + 125000 44>; + }; + + tboard_thermistor2: thermal-sensor2 { + compatible = "generic-adc-thermal"; + #thermal-sensor-cells = <0>; + io-channels = <&auxadc 1>; + io-channel-names = "sensor-channel"; + temperature-lookup-table = < (-5000) 1492 + 0 1413 + 5000 1324 + 10000 1227 + 15000 1121 + 20000 1017 + 25000 900 + 30000 797 + 35000 698 + 40000 606 + 45000 522 + 50000 449 + 55000 383 + 60000 327 + 65000 278 + 70000 236 + 75000 201 + 80000 171 + 85000 145 + 90000 163 + 95000 124 + 100000 91 + 105000 78 + 110000 67 + 115000 58 + 120000 50 + 125000 44>; + }; +}; + +/* + * Starmie does not have EC keyboard. Remove default keyboard controller + * and replace it with the driver for side switches. + */ +/delete-node/ &keyboard_controller; + +&cros_ec { + cbas: cbas { + compatible = "google,cros-cbas"; + }; + + keyboard-controller { + compatible = "google,cros-ec-keyb-switches"; + }; +}; + +&dsi0 { + #address-cells = <1>; + #size-cells = <0>; + panel: panel@0 { + /* compatible will be set in board dts */ + reg = <0>; + enable-gpios = <&pio 98 0>; + pinctrl-names = "default"; + pinctrl-0 = <&panel_default_pins>; + avdd-supply = <&en_pp6000_mipi_disp>; + avee-supply = <&en_pp6000_mipi_disp_150ma>; + pp1800-supply = <&mt6366_vio18_reg>; + backlight = <&backlight_lcd0>; + rotation = <270>; + port { + panel_in: endpoint { + remote-endpoint = <&dsi_out>; + }; + }; + }; +}; + +&dsi_out { + remote-endpoint = <&panel_in>; +}; + +&i2c0 { + status = "disabled"; +}; + +&i2c2 { + status = "disabled"; +}; + +&i2c4 { + status = "disabled"; +}; + +&i2c5 { + clock-frequency = <400000>; +}; + +&mmc1_pins_default { + pins-clk { + drive-strength = <8>; + }; + + pins-cmd-dat { + drive-strength = <8>; + }; +}; + +&mmc1_pins_uhs { + pins-clk { + drive-strength = <8>; + }; + + pins-cmd-dat { + drive-strength = <8>; + }; +}; + +&pen_insert { + wakeup-event-action = ; +}; + +&pio { + /* 185 lines */ + gpio-line-names = "TP", + "TP", + "TP", + "I2S0_HP_DI", + "I2S3_DP_SPKR_DO", + "SAR_INT_ODL", + "BT_WAKE_AP_ODL", + "WIFI_INT_ODL", + "DPBRDG_INT_ODL", + "NC", + "EC_AP_HPD_OD", + "NC", + "TCHSCR_INT_1V8_ODL", + "EC_AP_INT_ODL", + "EC_IN_RW_ODL", + "GSC_AP_INT_ODL", + /* + * AP_FLASH_WP_L is crossystem ABI. Rev1 schematics + * call it AP_WP_ODL. + */ + "AP_FLASH_WP_L", + "HP_INT_ODL", + "PEN_EJECT_OD", + "NC", + "NC", + "UCAM_SEN_EN", + "NC", + "NC", + "NC", + "I2S2_DP_SPK_MCK", + "I2S2_DP_SPKR_BCK", + "I2S2_DP_SPKR_LRCK", + "NC", + "NC", + "NC", + "NC", + "UART_GSC_TX_AP_RX", + "UART_AP_TX_GSC_RX", + "UART_DBGCON_TX_ADSP_RX", + "UART_ADSP_TX_DBGCON_RX", + "NC", + "TCHSCR_REPORT_DISABLE", + "NC", + "EN_PP1800_DPBRDG", + "SPI_AP_CLK_EC", + "SPI_AP_CS_EC_L", + "SPI_AP_DO_EC_DI", + "SPI_AP_DI_EC_DO", + "SPI_AP_CLK_GSC", + "SPI_AP_CS_GSC_L", + "SPI_AP_DO_GSC_DI", + "SPI_AP_DI_GSC_DO", + "UART_DBGCON_TX_SCP_RX", + "UART_SCP_TX_DBGCON_RX", + "EN_PP1200_CAM_X", + "WLAN_MODULE_RST_L", + "NC", + "NC", + "NC", + "NC", + "I2S1_HP_DO", + "I2S1_HP_BCK", + "I2S1_HP_LRCK", + "I2S1_HP_MCK", + "TCHSCR_RST_1V8_L", + "SPI_AP_CLK_ROM", + "SPI_AP_CS_ROM_L", + "SPI_AP_DO_ROM_DI", + "SPI_AP_DI_ROM_DO", + "NC", + "NC", + "EMMC_STRB", + "EMMC_CLK", + "EMMC_CMD", + "EMMC_RST_L", + "EMMC_DATA0", + "EMMC_DATA1", + "EMMC_DATA2", + "EMMC_DATA3", + "EMMC_DATA4", + "EMMC_DATA5", + "EMMC_DATA6", + "EMMC_DATA7", + "AP_KPCOL0", + "NC", + "NC", + "NC", + "TP", + "SDIO_CLK", + "SDIO_CMD", + "SDIO_DATA0", + "SDIO_DATA1", + "SDIO_DATA2", + "SDIO_DATA3", + "NC", + "NC", + "NC", + "NC", + "NC", + "NC", + "NC", + "MIPI_BL_PWM_1V8", + "DISP_RST_1V8_L", + "MIPI_DPI_CLK", + "MIPI_DPI_VSYNC", + "MIPI_DPI_HSYNC", + "MIPI_DPI_DE", + "MIPI_DPI_D0", + "MIPI_DPI_D1", + "MIPI_DPI_D2", + "MIPI_DPI_D3", + "MIPI_DPI_D4", + "MIPI_DPI_D5", + "MIPI_DPI_D6", + "MIPI_DPI_DA7", + "MIPI_DPI_D8", + "MIPI_DPI_D9", + "MIPI_DPI_D10", + "MIPI_DPI_D11", + "PCM_BT_CLK", + "PCM_BT_SYNC", + "PCM_BT_DI", + "PCM_BT_DO", + "JTAG_TMS_TP", + "JTAG_TCK_TP", + "JTAG_TDI_TP", + "JTAG_TDO_TP", + "JTAG_TRSTN_TP", + "NC", + "NC", + "UCAM_DET_ODL", + "NC", + "NC", + "AP_I2C_TCHSCR_SCL_1V8", + "AP_I2C_TCHSCR_SDA_1V8", + "NC", + "NC", + "AP_I2C_DPBRDG_SCL_1V8", + "AP_I2C_DPBRDG_SDA_1V8", + "NC", + "NC", + "AP_I2C_AUD_SCL_1V8", + "AP_I2C_AUD_SDA_1V8", + "AP_I2C_DISP_SCL_1V8", + "AP_I2C_DISP_SDA_1V8", + "NC", + "NC", + "NC", + "NC", + "SCP_I2C_SENSOR_SCL_1V8", + "SCP_I2C_SENSOR_SDA_1V8", + "AP_EC_WARM_RST_REQ", + "AP_XHCI_INIT_DONE", + "USB3_HUB_RST_L", + "EN_SPKR", + "BEEP_ON", + "AP_DISP_BKLTEN", + "EN_PP6000_MIPI_DISP", + "EN_PP6000_MIPI_DISP_150MA", + "BT_KILL_1V8_L", + "WIFI_KILL_1V8_L", + "PWRAP_SPI0_CSN", + "PWRAP_SPI0_CK", + "PWRAP_SPI0_MO", + "PWRAP_SPI0_MI", + "SRCLKENA0", + "SRCLKENA1", + "SCP_VREQ_VAO", + "AP_RTC_CLK32K", + "AP_PMIC_WDTRST_L", + "AUD_CLK_MOSI", + "AUD_SYNC_MOSI", + "AUD_DAT_MOSI0", + "AUD_DAT_MOSI1", + "AUD_CLK_MISO", + "AUD_SYNC_MISO", + "AUD_DAT_MISO0", + "AUD_DAT_MISO1", + "NC", + "NC", + "NC", + "DPBRDG_RST_L", + "LTE_W_DISABLE_L", + "LTE_SAR_DETECT_L", + "EN_PP3300_LTE_X", + "LTE_PWR_OFF_L", + "LTE_RESET_L", + "TP", + "TP"; + + dpi_default_pins: dpi-default-pins { + pins-cmd-dat { + pinmux = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + drive-strength = <10>; + output-low; + }; + }; + + dpi_func_pins: dpi-func-pins { + pins-cmd-dat { + pinmux = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + drive-strength = <10>; + }; + }; + + en_pp6000_mipi_disp_150ma_fixed_pins: en_pp6000-mipi-disp-150ma-fixed-pins { + pins-en { + pinmux = ; + output-low; + }; + }; + + panel_default_pins: panel-default-pins { + pins-en { + pinmux = ; + output-low; + }; + }; +}; + +&usb_c1 { + status = "disabled"; +}; + +&thermal_zones { + tboard1-thermal { + polling-delay = <1000>; /* milliseconds */ + polling-delay-passive = <0>; /* milliseconds */ + thermal-sensors = <&tboard_thermistor1>; + }; + + tboard2-thermal { + polling-delay = <1000>; /* milliseconds */ + polling-delay-passive = <0>; /* milliseconds */ + thermal-sensors = <&tboard_thermistor2>; + }; +}; + +&wifi_pwrseq { + reset-gpios = <&pio 51 1>; +}; + +/* + * Battery on Starmie is using a different address than default. + * Remove old node to reuse "battery" alias. + */ +/delete-node/ &battery; +&i2c_tunnel { + battery: sbs-battery@f { + compatible = "sbs,sbs-battery"; + reg = <0xf>; + sbs,i2c-retry-count = <2>; + sbs,poll-retry-count = <1>; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi index cfcc7909dfe6..cebb134331fb 100644 --- a/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi @@ -424,6 +424,7 @@ ovdd-supply = <&mt6366_vsim2_reg>; pwr18-supply = <&pp1800_dpbrdg_dx>; reset-gpios = <&pio 177 GPIO_ACTIVE_LOW>; + extcon = <&usbc_extcon>; ports { #address-cells = <1>; @@ -1275,7 +1276,7 @@ interrupts-extended = <&pio 201 IRQ_TYPE_LEVEL_HIGH>; #interrupt-cells = <2>; - mt6366codec: codec { + mt6366codec: audio-codec { compatible = "mediatek,mt6366-sound", "mediatek,mt6358-sound"; Avdd-supply = <&mt6366_vaud28_reg>; mediatek,dmic-mode = <1>; /* one-wire */ @@ -1656,6 +1657,11 @@ try-power-role = "source"; }; }; + + usbc_extcon: extcon0 { + compatible = "google,extcon-usbc-cros-ec"; + google,usb-port-id = <0>; + }; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8186.dtsi b/arch/arm64/boot/dts/mediatek/mt8186.dtsi index d3c3c2a40adc..b91f88ffae0e 100644 --- a/arch/arm64/boot/dts/mediatek/mt8186.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8186.dtsi @@ -1577,6 +1577,8 @@ #address-cells = <2>; #size-cells = <2>; ranges; + wakeup-source; + mediatek,syscon-wakeup = <&pericfg 0x420 2>; status = "disabled"; usb_host0: usb@11200000 { @@ -1590,8 +1592,6 @@ <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_XHCI>; clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck"; interrupts = ; - mediatek,syscon-wakeup = <&pericfg 0x420 2>; - wakeup-source; status = "disabled"; }; }; @@ -1643,6 +1643,8 @@ #address-cells = <2>; #size-cells = <2>; ranges; + wakeup-source; + mediatek,syscon-wakeup = <&pericfg 0x424 2>; status = "disabled"; usb_host1: usb@11280000 { @@ -1656,8 +1658,6 @@ <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_XHCI>; clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck","xhci_ck"; interrupts = ; - mediatek,syscon-wakeup = <&pericfg 0x424 2>; - wakeup-source; status = "disabled"; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku0.dts b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku0.dts new file mode 100644 index 000000000000..79d6d12394b9 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku0.dts @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2023 Google LLC + */ +/dts-v1/; +#include "mt8188-geralt-ciri.dtsi" + +/ { + model = "Google Ciri sku0 board"; + compatible = "google,ciri-sku0", "google,ciri", "mediatek,mt8188"; +}; + +&dsi_panel { + compatible = "boe,nv110wum-l60", "himax,hx83102"; +}; + +&sound { + compatible = "mediatek,mt8188-rt5682s"; + model = "mt8188_m98390_5682"; + + audio-routing = + "ETDM1_OUT", "ETDM_SPK_PIN", + "ETDM2_OUT", "ETDM_HP_PIN", + "ETDM1_IN", "ETDM_SPK_PIN", + "ETDM2_IN", "ETDM_HP_PIN", + "ADDA Capture", "MTKAIF_PIN", + "Headphone Jack", "HPOL", + "Headphone Jack", "HPOR", + "IN1P", "Headset Mic", + "Left Spk", "Front Left BE_OUT", + "Right Spk", "Front Right BE_OUT"; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku1.dts b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku1.dts new file mode 100644 index 000000000000..ef5ea9d12b1d --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku1.dts @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2023 Google LLC + */ +/dts-v1/; +#include "mt8188-geralt-ciri.dtsi" + +/ { + model = "Google Ciri sku1 board"; + compatible = "google,ciri-sku1", "google,ciri", "mediatek,mt8188"; +}; + +&dsi_panel { + compatible = "ivo,t109nw41", "himax,hx83102"; +}; + +&i2c0 { + /delete-node/ audio-codec@1a; + + es8326: audio-codec@19 { + compatible = "everest,es8326"; + reg = <0x19>; + interrupts-extended = <&pio 108 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&audio_codec_pins>; + #sound-dai-cells = <0>; + everest,jack-pol = [0e]; + everest,interrupt-clk = [00]; + }; +}; + +&sound { + compatible = "mediatek,mt8188-es8326"; + model = "mt8188_m98390_8326"; + + audio-routing = + "ETDM1_OUT", "ETDM_SPK_PIN", + "ETDM2_OUT", "ETDM_HP_PIN", + "ETDM1_IN", "ETDM_SPK_PIN", + "ETDM2_IN", "ETDM_HP_PIN", + "ADDA Capture", "MTKAIF_PIN", + "Headphone Jack", "HPOL", + "Headphone Jack", "HPOR", + "MIC1", "Headset Mic", + "Left Spk", "Front Left BE_OUT", + "Right Spk", "Front Right BE_OUT"; + + dai-link-2 { + codec { + sound-dai = <&es8326>; + }; + }; + + dai-link-3 { + codec { + sound-dai = <&es8326>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku2.dts b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku2.dts new file mode 100644 index 000000000000..ef56786fc2be --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku2.dts @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ +/dts-v1/; +#include "mt8188-geralt-ciri.dtsi" + +/ { + model = "Google Ciri sku2 board"; + compatible = "google,ciri-sku2", "google,ciri", "mediatek,mt8188"; +}; + +&dsi_panel { + compatible = "boe,nv110wum-l60", "himax,hx83102"; +}; + +&i2c0 { + /delete-node/ audio-codec@1a; + + es8326: audio-codec@19 { + compatible = "everest,es8326"; + reg = <0x19>; + interrupts-extended = <&pio 108 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&audio_codec_pins>; + #sound-dai-cells = <0>; + everest,jack-pol = [0e]; + everest,interrupt-clk = [00]; + }; +}; + +&sound { + compatible = "mediatek,mt8188-es8326"; + model = "mt8188_m98390_8326"; + + audio-routing = + "ETDM1_OUT", "ETDM_SPK_PIN", + "ETDM2_OUT", "ETDM_HP_PIN", + "ETDM1_IN", "ETDM_SPK_PIN", + "ETDM2_IN", "ETDM_HP_PIN", + "ADDA Capture", "MTKAIF_PIN", + "Headphone Jack", "HPOL", + "Headphone Jack", "HPOR", + "MIC1", "Headset Mic", + "Left Spk", "Front Left BE_OUT", + "Right Spk", "Front Right BE_OUT"; + + dai-link-2 { + codec { + sound-dai = <&es8326>; + }; + }; + + dai-link-3 { + codec { + sound-dai = <&es8326>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku3.dts b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku3.dts new file mode 100644 index 000000000000..524f7f0064c1 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku3.dts @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ +/dts-v1/; +#include "mt8188-geralt-ciri.dtsi" + +/ { + model = "Google Ciri sku3 board"; + compatible = "google,ciri-sku3", "google,ciri", "mediatek,mt8188"; +}; + +&dsi_panel { + compatible = "ivo,t109nw41", "himax,hx83102"; +}; + +&sound { + compatible = "mediatek,mt8188-rt5682s"; + model = "mt8188_m98390_5682"; + + audio-routing = + "ETDM1_OUT", "ETDM_SPK_PIN", + "ETDM2_OUT", "ETDM_HP_PIN", + "ETDM1_IN", "ETDM_SPK_PIN", + "ETDM2_IN", "ETDM_HP_PIN", + "ADDA Capture", "MTKAIF_PIN", + "Headphone Jack", "HPOL", + "Headphone Jack", "HPOR", + "IN1P", "Headset Mic", + "Left Spk", "Front Left BE_OUT", + "Right Spk", "Front Right BE_OUT"; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku4.dts b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku4.dts new file mode 100644 index 000000000000..ea953d7e1543 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku4.dts @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ +/dts-v1/; +#include "mt8188-geralt-ciri.dtsi" + +/ { + model = "Google Ciri sku4 board (rev4)"; + compatible = "google,ciri-sku4", "google,ciri", "mediatek,mt8188"; +}; + +&dsi_panel { + compatible = "boe,nv110wum-l60", "himax,hx83102"; +}; + +&i2c0 { + /delete-node/ amplifier@38; + /delete-node/ amplifier@39; + + tas2563: amplifier@4f { + compatible = "ti,tas2563", "ti,tas2781"; + reg = <0x4f>, <0x4c>; /* left / right channel */ + reset-gpios = <&pio 118 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + }; +}; + +&sound { + compatible = "mediatek,mt8188-rt5682s"; + model = "mt8188_tas2563_5682"; + + audio-routing = + "ETDM1_OUT", "ETDM_SPK_PIN", + "ETDM2_OUT", "ETDM_HP_PIN", + "ETDM1_IN", "ETDM_SPK_PIN", + "ETDM2_IN", "ETDM_HP_PIN", + "ADDA Capture", "MTKAIF_PIN", + "Headphone Jack", "HPOL", + "Headphone Jack", "HPOR", + "IN1P", "Headset Mic"; + + dai-link-1 { + codec { + sound-dai = <&tas2563>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku5.dts b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku5.dts new file mode 100644 index 000000000000..bf87201ccf27 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku5.dts @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ +/dts-v1/; +#include "mt8188-geralt-ciri.dtsi" + +/ { + model = "Google Ciri sku5 board (rev4)"; + compatible = "google,ciri-sku5", "google,ciri", "mediatek,mt8188"; +}; + +&dsi_panel { + compatible = "ivo,t109nw41", "himax,hx83102"; +}; + +&i2c0 { + /delete-node/ audio-codec@1a; + /delete-node/ amplifier@38; + /delete-node/ amplifier@39; + + es8326: audio-codec@19 { + compatible = "everest,es8326"; + reg = <0x19>; + interrupts-extended = <&pio 108 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&audio_codec_pins>; + #sound-dai-cells = <0>; + everest,jack-pol = [0e]; + everest,interrupt-clk = [00]; + }; + + tas2563: amplifier@4f { + compatible = "ti,tas2563", "ti,tas2781"; + reg = <0x4f>, <0x4c>; /* left / right channel */ + reset-gpios = <&pio 118 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + }; +}; + +&sound { + compatible = "mediatek,mt8188-es8326"; + model = "mt8188_tas2563_8326"; + + audio-routing = + "ETDM1_OUT", "ETDM_SPK_PIN", + "ETDM2_OUT", "ETDM_HP_PIN", + "ETDM1_IN", "ETDM_SPK_PIN", + "ETDM2_IN", "ETDM_HP_PIN", + "ADDA Capture", "MTKAIF_PIN", + "Headphone Jack", "HPOL", + "Headphone Jack", "HPOR", + "MIC1", "Headset Mic"; + + dai-link-1 { + codec { + sound-dai = <&tas2563>; + }; + }; + + dai-link-2 { + codec { + sound-dai = <&es8326>; + }; + }; + + dai-link-3 { + codec { + sound-dai = <&es8326>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku6.dts b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku6.dts new file mode 100644 index 000000000000..17d7359dfb6a --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku6.dts @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ +/dts-v1/; +#include "mt8188-geralt-ciri.dtsi" + +/ { + model = "Google Ciri sku6 board (rev4)"; + compatible = "google,ciri-sku6", "google,ciri", "mediatek,mt8188"; +}; + +&dsi_panel { + compatible = "boe,nv110wum-l60", "himax,hx83102"; +}; + +&i2c0 { + /delete-node/ audio-codec@1a; + /delete-node/ amplifier@38; + /delete-node/ amplifier@39; + + es8326: audio-codec@19 { + compatible = "everest,es8326"; + reg = <0x19>; + interrupts-extended = <&pio 108 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&audio_codec_pins>; + #sound-dai-cells = <0>; + everest,jack-pol = [0e]; + everest,interrupt-clk = [00]; + }; + + tas2563: amplifier@4f { + compatible = "ti,tas2563", "ti,tas2781"; + reg = <0x4f>, <0x4c>; /* left / right channel */ + reset-gpios = <&pio 118 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + }; +}; + +&sound { + compatible = "mediatek,mt8188-es8326"; + model = "mt8188_tas2563_8326"; + + audio-routing = + "ETDM1_OUT", "ETDM_SPK_PIN", + "ETDM2_OUT", "ETDM_HP_PIN", + "ETDM1_IN", "ETDM_SPK_PIN", + "ETDM2_IN", "ETDM_HP_PIN", + "ADDA Capture", "MTKAIF_PIN", + "Headphone Jack", "HPOL", + "Headphone Jack", "HPOR", + "MIC1", "Headset Mic"; + + dai-link-1 { + codec { + sound-dai = <&tas2563>; + }; + }; + + dai-link-2 { + codec { + sound-dai = <&es8326>; + }; + }; + + dai-link-3 { + codec { + sound-dai = <&es8326>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku7.dts b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku7.dts new file mode 100644 index 000000000000..825015b452d5 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri-sku7.dts @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2024 Google LLC + */ +/dts-v1/; +#include "mt8188-geralt-ciri.dtsi" + +/ { + model = "Google Ciri sku7 board (rev4)"; + compatible = "google,ciri-sku7", "google,ciri", "mediatek,mt8188"; +}; + +&dsi_panel { + compatible = "ivo,t109nw41", "himax,hx83102"; +}; + +&i2c0 { + /delete-node/ amplifier@38; + /delete-node/ amplifier@39; + + tas2563: amplifier@4f { + compatible = "ti,tas2563", "ti,tas2781"; + reg = <0x4f>, <0x4c>; /* left / right channel */ + reset-gpios = <&pio 118 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + }; +}; + +&sound { + compatible = "mediatek,mt8188-rt5682s"; + model = "mt8188_tas2563_5682"; + + audio-routing = + "ETDM1_OUT", "ETDM_SPK_PIN", + "ETDM2_OUT", "ETDM_HP_PIN", + "ETDM1_IN", "ETDM_SPK_PIN", + "ETDM2_IN", "ETDM_HP_PIN", + "ADDA Capture", "MTKAIF_PIN", + "Headphone Jack", "HPOL", + "Headphone Jack", "HPOR", + "IN1P", "Headset Mic"; + + dai-link-1 { + codec { + sound-dai = <&tas2563>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri.dtsi b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri.dtsi new file mode 100644 index 000000000000..6815c435a57e --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt-ciri.dtsi @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright 2023 Google LLC + */ +/dts-v1/; +#include "mt8188-geralt.dtsi" + +&aud_etdm_hp_on { + pins-mclk { + pinmux = ; + }; +}; + +&aud_etdm_hp_off { + pins-mclk { + pinmux = ; + bias-pull-down; + input-enable; + }; +}; + +&i2c0 { + rt5682s: audio-codec@1a { + compatible = "realtek,rt5682s"; + reg = <0x1a>; + interrupts-extended = <&pio 108 IRQ_TYPE_EDGE_BOTH>; + pinctrl-names = "default"; + pinctrl-0 = <&audio_codec_pins>; + #sound-dai-cells = <1>; + + AVDD-supply = <&mt6359_vio18_ldo_reg>; + DBVDD-supply = <&mt6359_vio18_ldo_reg>; + LDO1-IN-supply = <&mt6359_vio18_ldo_reg>; + MICVDD-supply = <&pp3300_s3>; + realtek,jd-src = <1>; + }; + + max98390_38: amplifier@38 { + compatible = "maxim,max98390"; + reg = <0x38>; + sound-name-prefix = "Front Right"; + reset-gpios = <&pio 118 GPIO_ACTIVE_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&speaker_en>; + #sound-dai-cells = <0>; + }; + + max98390_39: amplifier@39 { + compatible = "maxim,max98390"; + reg = <0x39>; + sound-name-prefix = "Front Left"; + #sound-dai-cells = <0>; + }; +}; + +&i2c_tunnel { + /* + * The virtual battery I2C addr is 0xf on Ciri, so we describe it + * manually instead of including 'arm/cros-ec-sbs.dtsi'. + **/ + battery: sbs-battery@f { + compatible = "sbs,sbs-battery"; + reg = <0xf>; + sbs,i2c-retry-count = <2>; + sbs,poll-retry-count = <1>; + }; +}; + +&mipi_tx_config0 { + drive-strength-microamp = <5200>; +}; + +&mt6359_vm18_ldo_reg { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1900000>; + regulator-microvolt-offset = <100000>; +}; + +&sound { + dai-link-0 { + link-name = "ETDM1_IN_BE"; + dai-format = "i2s"; + mediatek,clk-provider = "cpu"; + }; + + dai-link-1 { + link-name = "ETDM1_OUT_BE"; + dai-format = "i2s"; + mediatek,clk-provider = "cpu"; + + codec { + sound-dai = <&max98390_38>, + <&max98390_39>; + }; + }; + + dai-link-2 { + link-name = "ETDM2_IN_BE"; + mediatek,clk-provider = "cpu"; + + codec { + sound-dai = <&rt5682s 0>; + }; + }; + + dai-link-3 { + link-name = "ETDM2_OUT_BE"; + mediatek,clk-provider = "cpu"; + + codec { + sound-dai = <&rt5682s 0>; + }; + }; + + dai-link-4 { + link-name = "DPTX_BE"; + + codec { + sound-dai = <&dp_tx>; + }; + }; +}; + +&pio { + gpio-line-names = + "GSC_AP_INT_ODL", + "AP_DISP_BKLTEN", + "", + "EN_PPVAR_MIPI_DISP", + "EN_PPVAR_MIPI_DISP_150MA", + "TCHSCR_RST_1V8_L", + "", + "", + "", + "", + "", + "I2S_SPKR_DATAOUT", + "EN_PP3300_WLAN_X", + "WIFI_KILL_1V8_L", + "BT_KILL_1V8_L", + "AP_FLASH_WP_L", /* ... is crossystem ABI. Rev1 schematics call it AP_WP_ODL. */ + "", + "", + "WCAM_PWDN_L", + "WCAM_RST_L", + "UCAM_PWDM_L", + "UCAM_RST_L", + "WCAM_24M_CLK", + "UCAM_24M_CLK", + "MT6319_INT", + "DISP_RST_1V8_L", + "DSIO_DSI_TE", + "", + "TP", + "MIPI_BL_PWM_1V8", + "", + "UART_AP_TX_GSC_RX", + "UART_GSC_TX_AP_RX", + "UART_SSPM_TX_DBGCON_RX", + "UART_DBGCON_TX_SSPM_RX", + "UART_ADSP_TX_DBGCON_RX", + "UART_DBGCON_TX_ADSP_RX", + "JTAG_AP_TMS", + "JTAG_AP_TCK", + "JTAG_AP_TDI", + "JTAG_AP_TDO", + "JTAG_AP_TRST", + "AP_KPCOL0", + "TP", + "", + "TP", + "EC_AP_HPD_OD", + "PCIE_WAKE_1V8_ODL", + "PCIE_RST_1V8_L", + "PCIE_CLKREQ_1V8_ODL", + "", + "", + "", + "", + "", + "AP_I2C_AUD_SCL_1V8", + "AP_I2C_AUD_SDA_1V8", + "AP_I2C_TPM_SCL_1V8", + "AP_I2C_TPM_SDA_1V8", + "AP_I2C_TCHSCR_SCL_1V8", + "AP_I2C_TCHSCR_SDA_1V8", + "AP_I2C_PMIC_SAR_SCL_1V8", + "AP_I2C_PMIC_SAR_SDA_1V8", + "AP_I2C_EC_HID_KB_SCL_1V8", + "AP_I2C_EC_HID_KB_SDA_1V8", + "AP_I2C_UCAM_SCL_1V8", + "AP_I2C_UCAM_SDA_1V8", + "AP_I2C_WCAM_SCL_1V8", + "AP_I2C_WCAM_SDA_1V8", + "SPI_AP_CS_EC_L", + "SPI_AP_CLK_EC", + "SPI_AP_DO_EC_DI", + "SPI_AP_DI_EC_DO", + "TP", + "TP", + "SPI_AP_CS_TCHSCR_L", + "SPI_AP_CLK_TCHSCR", + "SPI_AP_DO_TCHSCR_DI", + "SPI_AP_DI_TCHSCR_DO", + "TP", + "TP", + "TP", + "TP", + "", + "", + "", + "TP", + "", + "", + "", + "", + "", + "PWRAP_SPI_CS_L", + "PWRAP_SPI_CK", + "PWRAP_SPI_MOSI", + "PWRAP_SPI_MISO", + "SRCLKENA0", + "SRCLKENA1", + "SCP_VREQ_VAO", + "AP_RTC_CLK32K", + "AP_PMIC_WDTRST_L", + "AUD_CLK_MOSI", + "AUD_SYNC_MOSI", + "AUD_DAT_MOSI0", + "AUD_DAT_MOSI1", + "AUD_DAT_MISO0", + "AUD_DAT_MISO1", + "", + "HP_INT_ODL", + "SPKR_INT_ODL", + "I2S_HP_DATAIN", + "EN_SPKR", + "I2S_SPKR_MCLK", + "I2S_SPKR_BCLK", + "I2S_HP_MCLK", + "I2S_HP_BCLK", + "I2S_HP_LRCK", + "I2S_HP_DATAOUT", + "RST_SPKR_L", + "I2S_SPKR_LRCK", + "I2S_SPKR_DATAIN", + "", + "", + "", + "", + "SPI_AP_CLK_ROM", + "SPI_AP_CS_ROM_L", + "SPI_AP_DO_ROM_DI", + "SPI_AP_DI_ROM_DO", + "TP", + "TP", + "", + "", + "", + "", + "", + "", + "", + "", + "EN_PP2800A_UCAM_X", + "EN_PP1200_UCAM_X", + "EN_PP2800A_WCAM_X", + "EN_PP1100_WCAM_X", + "TCHSCR_INT_1V8_L", + "", + "MT7921_PMU_EN_1V8", + "", + "AP_EC_WARM_RST_REQ", + "EC_AP_HID_INT_ODL", + "EC_AP_INT_ODL", + "AP_XHCI_INIT_DONE", + "EMMC_DAT7", + "EMMC_DAT6", + "EMMC_DAT5", + "EMMC_DAT4", + "EMMC_RST_L", + "EMMC_CMD", + "EMMC_CLK", + "EMMC_DAT3", + "EMMC_DAT2", + "EMMC_DAT1", + "EMMC_DAT0", + "EMMC_DSL", + "", + "", + "", + "", + "", + "", + "", + "", + "USB3_HUB_RST_L", + "EC_AP_RSVD0_ODL", + "", + "", + "SPMI_SCL", + "SPMI_SDA"; + + audio_codec_pins: audio-codec-pins { + pins-hp-int-odl { + pinmux = ; + input-enable; + }; + }; + + speaker_en: speaker-en-pins { + pins-en-spkr { + pinmux = ; + }; + }; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi b/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi new file mode 100644 index 000000000000..b6abecbcfa81 --- /dev/null +++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi @@ -0,0 +1,1156 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2022 MediaTek Inc. + */ +/dts-v1/; +#include +#include "mt8188.dtsi" +#include "mt6359.dtsi" + +/ { + aliases { + i2c0 = &i2c0; + i2c1 = &i2c1; + i2c2 = &i2c2; + i2c3 = &i2c3; + i2c4 = &i2c4; + i2c5 = &i2c5; + i2c6 = &i2c6; + mmc0 = &mmc0; + serial0 = &uart0; + }; + + backlight_lcd0: backlight-lcd0 { + compatible = "pwm-backlight"; + brightness-levels = <0 1023>; + default-brightness-level = <576>; + enable-gpios = <&pio 1 GPIO_ACTIVE_HIGH>; + num-interpolated-steps = <1023>; + power-supply = <&ppvar_sys>; + pwms = <&disp_pwm0 0 500000>; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + dmic-codec { + compatible = "dmic-codec"; + num-channels = <2>; + wakeup-delay-ms = <100>; + }; + + memory@40000000 { + device_type = "memory"; + /* The size will be filled in by the bootloader */ + reg = <0 0x40000000 0 0>; + }; + + /* system wide LDO 1.8V power rail */ + pp1800_ldo_z1: regulator-pp1800-ldo-z1 { + compatible = "regulator-fixed"; + regulator-name = "pp1800_ldo_z1"; + /* controlled by PP3300_Z1 */ + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + vin-supply = <&pp3300_z1>; + }; + + /* separately switched 3.3V power rail */ + pp3300_s3: regulator-pp3300-s3 { + compatible = "regulator-fixed"; + regulator-name = "pp3300_s3"; + /* controlled by PMIC */ + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&pp3300_z1>; + }; + + /* system wide 3.3V power rail */ + pp3300_z1: regulator-pp3300-z1 { + compatible = "regulator-fixed"; + regulator-name = "pp3300_z1"; + /* controlled by PP3300_LDO_Z5 & EN_PWR_Z1 */ + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&ppvar_sys>; + }; + + pp3300_wlan: regulator-pp3300-wlan { + compatible = "regulator-fixed"; + regulator-name = "pp3300_wlan"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + enable-active-high; + gpio = <&pio 12 GPIO_ACTIVE_HIGH>; + pinctrl-0 = <&wlan_en>; + pinctrl-names = "default"; + vin-supply = <&pp3300_z1>; + }; + + /* system wide 4.2V power rail */ + pp4200_s5: regulator-pp4200-s5 { + compatible = "regulator-fixed"; + regulator-name = "pp4200_s5"; + /* controlled by EC */ + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <4200000>; + regulator-max-microvolt = <4200000>; + vin-supply = <&ppvar_sys>; + }; + + /* system wide 5.0V power rail */ + pp5000_z1: regulator-pp5000-z1 { + compatible = "regulator-fixed"; + regulator-name = "pp5000_z1"; + /* controlled by EC */ + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&ppvar_sys>; + }; + + pp5000_usb_vbus: regulator-pp5000-usb-vbus { + compatible = "regulator-fixed"; + regulator-name = "pp5000_usb_vbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + enable-active-high; + gpio = <&pio 150 GPIO_ACTIVE_HIGH>; + vin-supply = <&pp5000_z1>; + }; + + /* system wide semi-regulated power rail from battery or USB */ + ppvar_sys: regulator-ppvar-sys { + compatible = "regulator-fixed"; + regulator-name = "ppvar_sys"; + regulator-always-on; + regulator-boot-on; + }; + + ppvar_mipi_disp_avdd: regulator-ppvar-mipi-disp-avdd { + compatible = "regulator-fixed"; + regulator-name = "ppvar_mipi_disp_avdd"; + enable-active-high; + gpio = <&pio 3 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&mipi_disp_avdd_en>; + vin-supply = <&pp5000_z1>; + }; + + ppvar_mipi_disp_avee: regulator-ppvar-mipi-disp-avee { + compatible = "regulator-fixed"; + regulator-name = "ppvar_mipi_disp_avee"; + regulator-enable-ramp-delay = <10000>; + enable-active-high; + gpio = <&pio 4 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&mipi_disp_avee_en>; + vin-supply = <&pp5000_z1>; + }; + + reserved_memory: reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + apu_mem: memory@55000000 { + compatible = "shared-dma-pool"; + reg = <0 0x55000000 0 0x1400000>; + }; + + adsp_mem: memory@60000000 { + compatible = "shared-dma-pool"; + reg = <0 0x60000000 0 0xf00000>; + no-map; + }; + + afe_dma_mem: memory@60f00000 { + compatible = "shared-dma-pool"; + reg = <0 0x60f00000 0 0x100000>; + no-map; + }; + + adsp_dma_mem: memory@61000000 { + compatible = "shared-dma-pool"; + reg = <0 0x61000000 0 0x100000>; + no-map; + }; + }; +}; + +&adsp { + memory-region = <&adsp_dma_mem>, <&adsp_mem>; + pinctrl-names = "default"; + pinctrl-0 = <&adsp_uart_pins>; + status = "okay"; +}; + +&afe { + memory-region = <&afe_dma_mem>; + mediatek,etdm-out1-cowork-source = <0>; /* in1 */ + mediatek,etdm-in2-cowork-source = <3>; /* out2 */ + status = "okay"; +}; + +&auxadc { + status = "okay"; +}; + +&cam_vcore { + domain-supply = <&mt6359_vproc1_buck_reg>; +}; + +/* + * Geralt is the reference design and doesn't have target TDP. + * Ciri is (currently) the only device following Geralt, and its + * TDP target is 90 degrees. + **/ +&cpu_little0_alert0 { + temperature = <90000>; + hysteresis = <2000>; + type = "passive"; +}; + +&cpu_little1_alert0 { + temperature = <90000>; + hysteresis = <2000>; + type = "passive"; +}; + +&cpu_little2_alert0 { + temperature = <90000>; + hysteresis = <2000>; + type = "passive"; +}; + +&cpu_little3_alert0 { + temperature = <90000>; + hysteresis = <2000>; + type = "passive"; +}; + +&cpu_big0_alert0 { + temperature = <90000>; + hysteresis = <2000>; + type = "passive"; +}; + +&cpu_big1_alert0 { + temperature = <90000>; + hysteresis = <2000>; + type = "passive"; +}; + +&disp_dsi0 { + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + dsi_panel: panel@0 { + /* Compatible string for different panels can be found in each device dts */ + reg = <0>; + enable-gpios = <&pio 25 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&mipi_dsi_pins>; + + backlight = <&backlight_lcd0>; + avdd-supply = <&ppvar_mipi_disp_avdd>; + avee-supply = <&ppvar_mipi_disp_avee>; + pp1800-supply = <&mt6359_vm18_ldo_reg>; + rotation = <270>; + + status = "okay"; + + port { + dsi_panel_in: endpoint { + remote-endpoint = <&dsi_out>; + }; + }; + }; + + port { + dsi_out: endpoint { + remote-endpoint = <&dsi_panel_in>; + }; + }; +}; + +&disp_pwm0 { + pinctrl-names = "default"; + pinctrl-0 = <&disp_pwm0_pins>; + status = "okay"; +}; + +&disp_pwm1 { + pinctrl-names = "default"; + pinctrl-0 = <&disp_pwm1_pins>; +}; + +&dp_intf1 { + status = "okay"; + + port { + dp_intf1_out: endpoint { + remote-endpoint = <&dptx_in>; + }; + }; +}; + +&dp_tx { + pinctrl-names = "default"; + pinctrl-0 = <&dp_tx_hpd>; + #sound-dai-cells = <0>; + status = "okay"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dptx_in: endpoint { + remote-endpoint = <&dp_intf1_out>; + }; + }; + + port@1 { + reg = <1>; + dptx_out: endpoint { + data-lanes = <0 1 2 3>; + }; + }; + }; +}; + +&gpu { + mali-supply = <&mt6359_vproc2_buck_reg>; + status = "okay"; +}; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_pins>; + clock-frequency = <400000>; + status = "okay"; +}; + +&i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; + clock-frequency = <400000>; + status = "okay"; + + tpm@50 { + compatible = "google,cr50"; + reg = <0x50>; + interrupts-extended = <&pio 0 IRQ_TYPE_EDGE_RISING>; + pinctrl-names = "default"; + pinctrl-0 = <&gsc_int>; + }; +}; + +&i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; + clock-frequency = <400000>; + status = "okay"; +}; + +&i2c3 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins>; + clock-frequency = <400000>; + status = "okay"; +}; + +&i2c4 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c4_pins>; + clock-frequency = <400000>; + status = "okay"; +}; + +&i2c5 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c5_pins>; + clock-frequency = <400000>; + status = "okay"; +}; + +&i2c6 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c6_pins>; + clock-frequency = <400000>; + status = "okay"; +}; + +&mfg0 { + domain-supply = <&mt6359_vproc2_buck_reg>; +}; + +&mfg1 { + domain-supply = <&mt6359_vsram_others_ldo_reg>; +}; + +&mipi_tx_config0 { + status = "okay"; +}; + +&mmc0 { + bus-width = <8>; + cap-mmc-highspeed; + cap-mmc-hw-reset; + hs400-ds-delay = <0x1481b>; + max-frequency = <200000000>; + mmc-hs200-1_8v; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + no-sd; + no-sdio; + non-removable; + pinctrl-names = "default", "state_uhs"; + pinctrl-0 = <&mmc0_pins_default>; + pinctrl-1 = <&mmc0_pins_uhs>; + supports-cqe; + vmmc-supply = <&mt6359_vemc_1_ldo_reg>; + vqmmc-supply = <&mt6359_vufs_ldo_reg>; + status = "okay"; +}; + +&mt6359codec { + mediatek,dmic-mode = <1>; /* one-wire */ + mediatek,mic-type-0 = <2>; /* DMIC */ + mediatek,mic-type-2 = <2>; /* DMIC */ +}; + +&mt6359_vcore_buck_reg { + regulator-always-on; +}; + +&mt6359_vgpu11_buck_reg { + regulator-always-on; +}; + +&mt6359_vgpu11_sshub_buck_reg { + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <550000>; + regulator-always-on; +}; + +&mt6359_vio28_ldo_reg { + /delete-property/ regulator-always-on; +}; + +&mt6359_vm18_ldo_reg { + /delete-property/ regulator-always-on; +}; + +&mt6359_vmodem_buck_reg { + regulator-min-microvolt = <775000>; + regulator-max-microvolt = <775000>; +}; + +&mt6359_vpa_buck_reg { + regulator-max-microvolt = <3100000>; +}; + +&mt6359_vproc2_buck_reg { + /* + * Called "ppvar_dvdd_gpu" in the schematic. Renamed to + * "ppvar_dvdd_vgpu" here to match mtk-regulator-coupler requirements. + */ + regulator-name = "ppvar_dvdd_vgpu"; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <800000>; + regulator-coupled-with = <&mt6359_vsram_others_ldo_reg>; + regulator-coupled-max-spread = <6250>; +}; + +&mt6359_vpu_buck_reg { + regulator-always-on; +}; + +&mt6359_vrf12_ldo_reg { + regulator-always-on; +}; + +&mt6359_vsram_md_ldo_reg { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <800000>; +}; + +&mt6359_vsram_others_ldo_reg { + regulator-name = "pp0850_dvdd_sram_gpu"; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <800000>; + regulator-coupled-with = <&mt6359_vproc2_buck_reg>; + regulator-coupled-max-spread = <6250>; +}; + +&mt6359_vufs_ldo_reg { + regulator-always-on; +}; + +&nor_flash { + pinctrl-names = "default"; + pinctrl-0 = <&nor_pins>; + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <52000000>; + }; +}; + +&pcie { + pinctrl-names = "default"; + pinctrl-0 = <&pcie_pins>; + status = "okay"; +}; + +&pciephy { + status = "okay"; +}; + +&pio { + gpio-line-names = + "gsc_int", + "AP_DISP_BKLTEN", + "", + "EN_PPVAR_MIPI_DISP", + "EN_PPVAR_MIPI_DISP_150MA", + "TCHSCR_RST_1V8_L", + "TCHSRC_REPORT_DISABLE", + "", + "", + "", + "", + "I2S_SPKR_DATAOUT", + "EN_PP3300_WLAN_X", + "WIFI_KILL_1V8_L", + "BT_KILL_1V8_L", + "AP_FLASH_WP_L", /* ... is crossystem ABI. Rev1 schematics call it AP_WP_ODL. */ + "", + "EDP_HPD_1V8", + "WCAM_PWDN_L", + "WCAM_RST_L", + "UCAM_PWDM_L", + "UCAM_RST_L", + "WCAM_24M_CLK", + "UCAM_24M_CLK", + "MT6319_INT", + "DISP_RST_1V8_L", + "DSIO_DSI_TE", + "EN_PP3300_EDP_DISP_X", + "TP", + "MIPI_BL_PWM_1V8", + "EDP_BL_PWM_1V8", + "UART_AP_TX_GSC_RX", + "UART_GSC_TX_AP_RX", + "UART_SSPM_TX_DBGCON_RX", + "UART_DBGCON_TX_SSPM_RX", + "UART_ADSP_TX_DBGCON_RX", + "UART_DBGCON_TX_ADSP_RX", + "JTAG_AP_TMS", + "JTAG_AP_TCK", + "JTAG_AP_TDI", + "JTAG_AP_TDO", + "JTAG_AP_TRST", + "AP_KPCOL0", + "TP", + "BEEP_ON_OD", + "TP", + "EC_AP_HPD_OD", + "PCIE_WAKE_1V8_ODL", + "PCIE_RST_1V8_L", + "PCIE_CLKREQ_1V8_ODL", + "", + "", + "", + "", + "", + "AP_I2C_AUD_SCL_1V8", + "AP_I2C_AUD_SDA_1V8", + "AP_I2C_TPM_SCL_1V8", + "AP_I2C_TPM_SDA_1V8", + "AP_I2C_TCHSCR_SCL_1V8", + "AP_I2C_TCHSCR_SDA_1V8", + "AP_I2C_PMIC_SAR_SCL_1V8", + "AP_I2C_PMIC_SAR_SDA_1V8", + "AP_I2C_EC_HID_KB_SCL_1V8", + "AP_I2C_EC_HID_KB_SDA_1V8", + "AP_I2C_UCAM_SCL_1V8", + "AP_I2C_UCAM_SDA_1V8", + "AP_I2C_WCAM_SCL_1V8", + "AP_I2C_WCAM_SDA_1V8", + "SPI_AP_CS_EC_L", + "SPI_AP_CLK_EC", + "SPI_AP_DO_EC_DI", + "SPI_AP_DI_EC_DO", + "TP", + "TP", + "SPI_AP_CS_TCHSCR_L", + "SPI_AP_CLK_TCHSCR", + "SPI_AP_DO_TCHSCR_DI", + "SPI_AP_DI_TCHSCR_DO", + "TP", + "TP", + "TP", + "TP", + "", + "", + "", + "TP", + "", + "SAR_INT_ODL", + "", + "", + "", + "PWRAP_SPI_CS_L", + "PWRAP_SPI_CK", + "PWRAP_SPI_MOSI", + "PWRAP_SPI_MISO", + "SRCLKENA0", + "SRCLKENA1", + "SCP_VREQ_VAO", + "AP_RTC_CLK32K", + "AP_PMIC_WDTRST_L", + "AUD_CLK_MOSI", + "AUD_SYNC_MOSI", + "AUD_DAT_MOSI0", + "AUD_DAT_MOSI1", + "AUD_DAT_MISO0", + "AUD_DAT_MISO1", + "SD_CD_ODL", + "HP_INT_ODL", + "SPKR_INT_ODL", + "I2S_HP_DATAIN", + "EN_SPKR", + "I2S_SPKR_MCLK", + "I2S_SPKR_BCLK", + "I2S_HP_MCLK", + "I2S_HP_BCLK", + "I2S_HP_LRCK", + "I2S_HP_DATAOUT", + "RST_SPKR_L", + "I2S_SPKR_LRCK", + "I2S_SPKR_DATAIN", + "", + "", + "", + "", + "SPI_AP_CLK_ROM", + "SPI_AP_CS_ROM_L", + "SPI_AP_DO_ROM_DI", + "SPI_AP_DI_ROM_DO", + "TP", + "TP", + "", + "", + "", + "", + "", + "", + "", + "", + "EN_PP2800A_UCAM_X", + "EN_PP1200_UCAM_X", + "EN_PP2800A_WCAM_X", + "EN_PP1100_WCAM_X", + "TCHSCR_INT_1V8_L", + "EN_PP3300_MIPI_TCHSCR_X", + "MT7921_PMU_EN_1V8", + "EN_PP3300_EDP_TCHSCR_X", + "AP_EC_WARM_RST_REQ", + "EC_AP_HID_INT_ODL", + "EC_AP_INT_ODL", + "AP_XHCI_INIT_DONE", + "EMMC_DAT7", + "EMMC_DAT6", + "EMMC_DAT5", + "EMMC_DAT4", + "EMMC_RST_L", + "EMMC_CMD", + "EMMC_CLK", + "EMMC_DAT3", + "EMMC_DAT2", + "EMMC_DAT1", + "EMMC_DAT0", + "EMMC_DSL", + "SD_CMD", + "SD_CLK", + "SD_DAT0", + "SD_DAT1", + "SD_DAT2", + "SD_DAT3", + "", + "", + "USB3_HUB_RST_L", + "EC_AP_RSVD0_ODL", + "", + "", + "SPMI_SCL", + "SPMI_SDA"; + + adsp_uart_pins: adsp-uart-pins { + pins-bus { + pinmux = , + ; + }; + }; + + aud_etdm_hp_on: aud-etdm-hp-on-pins { + pins-bus { + pinmux = , + , + , + ; + }; + }; + + aud_etdm_hp_off: aud-etdm-hp-off-pins { + pins-bus { + pinmux = , + , + , + ; + bias-pull-down; + input-enable; + }; + }; + + aud_etdm_spk_on: aud-etdm-spk-on-pins { + pins-bus { + pinmux = , + , + , + ; + drive-strength = <8>; + }; + }; + + aud_etdm_spk_off: aud-etdm-spk-off-pins { + pins-bus { + pinmux = , + , + , + ; + bias-pull-down; + input-enable; + }; + }; + + aud_mtkaif_on: aud-mtkaif-on-pins { + pins-bus { + pinmux = , + , + , + , + , + ; + }; + }; + + aud_mtkaif_off: aud-mtkaif-off-pins { + pins-bus { + pinmux = , + , + , + , + , + ; + bias-pull-down; + input-enable; + }; + }; + + cros_ec_int: cros-ec-int-pins { + pins-ec-ap-int-odl { + pinmux = ; + input-enable; + }; + }; + + disp_pwm0_pins: disp-pwm0-pins { + pins-disp-pwm0 { + pinmux = ; + output-high; + }; + }; + + disp_pwm1_pins: disp-pwm1-pins { + pins-disp-pwm1 { + pinmux = ; + output-high; + }; + }; + + dp_tx_hpd: dp-tx-hpd-pins { + pins-dp-tx-hpd { + pinmux = ; + }; + }; + + gsc_int: gsc-int-pins { + pins-gsc-ap-int-odl { + pinmux = ; + input-enable; + }; + }; + + i2c0_pins: i2c0-pins { + pins-bus { + pinmux = , + ; + }; + }; + + i2c1_pins: i2c1-pins { + pins-bus { + pinmux = , + ; + }; + }; + + i2c2_pins: i2c2-pins { + pins-bus { + pinmux = , + ; + bias-disable; + drive-strength = <12>; + }; + }; + + i2c3_pins: i2c3-pins { + pins-bus { + pinmux = , + ; + }; + }; + + i2c4_pins: i2c4-pins { + pins-bus { + pinmux = , + ; + }; + }; + + i2c5_pins: i2c5-pins { + pins-bus { + pinmux = , + ; + }; + }; + + i2c6_pins: i2c6-pins { + pins-bus { + pinmux = , + ; + }; + }; + + mipi_disp_avdd_en: mipi-disp-avdd-en-pins { + pins-en-ppvar-mipi-disp { + pinmux = ; + output-low; + }; + }; + + mipi_disp_avee_en: mipi-disp-avee-en-pins { + pins-en-ppvar-mipi-disp-150ma { + pinmux = ; + output-low; + }; + }; + + mipi_dsi_pins: mipi-dsi-pins { + pins-bus { + pinmux = , + ; + output-low; + }; + }; + + mmc0_pins_default: mmc0-default-pins { + pins-bus { + pinmux = , + , + , + , + , + , + , + , + ; + input-enable; + drive-strength = <6>; + bias-pull-up = ; + }; + + pins-clk { + pinmux = ; + drive-strength = <6>; + bias-pull-down = ; + }; + + pins-rst { + pinmux = ; + drive-strength = <6>; + bias-pull-up = ; + }; + }; + + mmc0_pins_uhs: mmc0-uhs-pins { + pins-bus { + pinmux = , + , + , + , + , + , + , + , + ; + input-enable; + drive-strength = <8>; + bias-pull-up = ; + }; + + pins-clk { + pinmux = ; + drive-strength = <8>; + bias-pull-down = ; + }; + + pins-ds { + pinmux = ; + drive-strength = <8>; + bias-pull-down = ; + }; + + pins-rst { + pinmux = ; + drive-strength = <8>; + bias-pull-up = ; + }; + }; + + nor_pins: nor-default-pins { + pins-clk { + pinmux = , + , + ; + bias-pull-down; + }; + + pins-cs { + pinmux = ; + bias-pull-up; + }; + }; + + pcie_pins: pcie-default-pins { + pins-bus { + pinmux = , + , + ; + }; + }; + + spi0_pins: spi0-pins { + pins-bus { + pinmux = , + , + , + ; + bias-disable; + }; + }; + + spi1_pins_default: spi1-default-pins { + pins-bus { + pinmux = , + , + , + ; + bias-disable; + }; + }; + + spi1_pins_sleep: spi1-sleep-pins { + pins-bus { + pinmux = , + , + , + ; + bias-pull-down; + input-enable; + }; + }; + + spi2_pins: spi2-pins { + pins-bus { + pinmux = , + , + , + ; + bias-disable; + }; + }; + + uart0_pins: uart0-pins { + pins-bus { + pinmux = , + ; + bias-pull-up; + }; + }; + + wlan_en: wlan-en-pins { + pins-en-pp3300-wlan { + pinmux = ; + output-low; + }; + }; +}; + +&pmic { + interrupts-extended = <&pio 222 IRQ_TYPE_LEVEL_HIGH>; +}; + +&sound { + pinctrl-names = "aud_etdm_hp_on", "aud_etdm_hp_off", + "aud_etdm_spk_on", "aud_etdm_spk_off", + "aud_mtkaif_on", "aud_mtkaif_off"; + pinctrl-0 = <&aud_etdm_hp_on>; + pinctrl-1 = <&aud_etdm_hp_off>; + pinctrl-2 = <&aud_etdm_spk_on>; + pinctrl-3 = <&aud_etdm_spk_off>; + pinctrl-4 = <&aud_mtkaif_on>; + pinctrl-5 = <&aud_mtkaif_off>; + mediatek,adsp = <&adsp>; + /* The audio-routing is defined in each board dts */ + + status = "okay"; +}; + +&spi0 { + pinctrl-names = "default"; + pinctrl-0 = <&spi0_pins>; + status = "okay"; + + cros_ec: ec@0 { + compatible = "google,cros-ec-spi"; + reg = <0>; + interrupts-extended = <&pio 149 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&cros_ec_int>; + spi-max-frequency = <3000000>; + + i2c_tunnel: i2c-tunnel { + compatible = "google,cros-ec-i2c-tunnel"; + google,remote-bus = <1>; + #address-cells = <1>; + #size-cells = <0>; + }; + + cbas { + compatible = "google,cros-cbas"; + }; + }; +}; + +&spi1 { + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&spi1_pins_default>; + pinctrl-1 = <&spi1_pins_sleep>; + status = "okay"; +}; + +&spi2 { + pinctrl-names = "default"; + pinctrl-0 = <&spi2_pins>; + status = "okay"; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_pins>; + status = "okay"; +}; + +&u3phy0 { + status = "okay"; +}; + +&u3phy1 { + status = "okay"; +}; + +&u3phy2 { + status = "okay"; +}; + +/* USB detachable base */ +&xhci0 { + /* controlled by EC */ + vbus-supply = <&pp3300_z1>; + status = "okay"; +}; + +/* USB3 hub */ +&xhci1 { + vusb33-supply = <&pp3300_s3>; + vbus-supply = <&pp5000_usb_vbus>; + status = "okay"; +}; + +/* USB BT */ +&xhci2 { + /* no power supply since MT7921's power is controlled by PCIe */ + /* MT7921's USB BT has issues with USB2 LPM */ + usb2-lpm-disable; + status = "okay"; +}; + +#include + +&keyboard_controller { + function-row-physmap = < + MATRIX_KEY(0x00, 0x02, 0) /* T1 */ + MATRIX_KEY(0x03, 0x02, 0) /* T2 */ + MATRIX_KEY(0x02, 0x02, 0) /* T3 */ + MATRIX_KEY(0x01, 0x02, 0) /* T4 */ + MATRIX_KEY(0x03, 0x04, 0) /* T5 */ + MATRIX_KEY(0x02, 0x04, 0) /* T6 */ + MATRIX_KEY(0x01, 0x04, 0) /* T7 */ + MATRIX_KEY(0x02, 0x09, 0) /* T8 */ + MATRIX_KEY(0x01, 0x09, 0) /* T9 */ + MATRIX_KEY(0x00, 0x04, 0) /* T10 */ + >; + + linux,keymap = < + MATRIX_KEY(0x00, 0x02, KEY_BACK) + MATRIX_KEY(0x03, 0x02, KEY_REFRESH) + MATRIX_KEY(0x02, 0x02, KEY_ZOOM) + MATRIX_KEY(0x01, 0x02, KEY_SCALE) + MATRIX_KEY(0x03, 0x04, KEY_BRIGHTNESSDOWN) + MATRIX_KEY(0x02, 0x04, KEY_BRIGHTNESSUP) + MATRIX_KEY(0x01, 0x04, KEY_MICMUTE) + MATRIX_KEY(0x02, 0x09, KEY_MUTE) + MATRIX_KEY(0x01, 0x09, KEY_VOLUMEDOWN) + MATRIX_KEY(0x00, 0x04, KEY_VOLUMEUP) + CROS_STD_MAIN_KEYMAP + >; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8188.dtsi b/arch/arm64/boot/dts/mediatek/mt8188.dtsi index faccc7f16259..338120930b81 100644 --- a/arch/arm64/boot/dts/mediatek/mt8188.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8188.dtsi @@ -2125,6 +2125,11 @@ reg = <0x1ac 0x40>; }; + gpu_speedbin: gpu-speedbin@581 { + reg = <0x581 0x1>; + bits = <0 3>; + }; + socinfo-data1@7a0 { reg = <0x7a0 0x4>; }; @@ -2143,6 +2148,8 @@ , ; interrupt-names = "job", "mmu", "gpu"; + nvmem-cells = <&gpu_speedbin>; + nvmem-cell-names = "speed-bin"; operating-points-v2 = <&gpu_opp_table>; power-domains = <&spm MT8188_POWER_DOMAIN_MFG2>, <&spm MT8188_POWER_DOMAIN_MFG3>, @@ -2488,7 +2495,7 @@ }; ovl0: ovl@1c000000 { - compatible = "mediatek,mt8188-disp-ovl", "mediatek,mt8183-disp-ovl"; + compatible = "mediatek,mt8188-disp-ovl", "mediatek,mt8195-disp-ovl"; reg = <0 0x1c000000 0 0x1000>; clocks = <&vdosys0 CLK_VDO0_DISP_OVL0>; interrupts = ; diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada-hayato-r5-sku2.dts b/arch/arm64/boot/dts/mediatek/mt8192-asurada-hayato-r5-sku2.dts deleted file mode 100644 index cd86ad9ba28a..000000000000 --- a/arch/arm64/boot/dts/mediatek/mt8192-asurada-hayato-r5-sku2.dts +++ /dev/null @@ -1,65 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) -/* - * Copyright 2022 Google LLC - */ -/dts-v1/; -#include "mt8192-asurada.dtsi" - -/ { - model = "Google Hayato rev5"; - chassis-type = "convertible"; - compatible = "google,hayato-rev5-sku2", "google,hayato-sku2", - "google,hayato", "mediatek,mt8192"; -}; - -&keyboard_controller { - function-row-physmap = < - MATRIX_KEY(0x00, 0x02, 0) /* T1 */ - MATRIX_KEY(0x03, 0x02, 0) /* T2 */ - MATRIX_KEY(0x02, 0x02, 0) /* T3 */ - MATRIX_KEY(0x01, 0x02, 0) /* T4 */ - MATRIX_KEY(0x03, 0x04, 0) /* T5 */ - MATRIX_KEY(0x02, 0x04, 0) /* T6 */ - MATRIX_KEY(0x01, 0x04, 0) /* T7 */ - MATRIX_KEY(0x02, 0x09, 0) /* T8 */ - MATRIX_KEY(0x01, 0x09, 0) /* T9 */ - MATRIX_KEY(0x00, 0x04, 0) /* T10 */ - >; - linux,keymap = < - MATRIX_KEY(0x00, 0x02, KEY_BACK) - MATRIX_KEY(0x03, 0x02, KEY_FORWARD) - MATRIX_KEY(0x02, 0x02, KEY_REFRESH) - MATRIX_KEY(0x01, 0x02, KEY_FULL_SCREEN) - MATRIX_KEY(0x03, 0x04, KEY_SCALE) - MATRIX_KEY(0x02, 0x04, KEY_BRIGHTNESSDOWN) - MATRIX_KEY(0x01, 0x04, KEY_BRIGHTNESSUP) - MATRIX_KEY(0x02, 0x09, KEY_MUTE) - MATRIX_KEY(0x01, 0x09, KEY_VOLUMEDOWN) - MATRIX_KEY(0x00, 0x04, KEY_VOLUMEUP) - - CROS_STD_MAIN_KEYMAP - >; -}; - -&rt5682 { - compatible = "realtek,rt5682s"; -}; - -&sound { - compatible = "mediatek,mt8192_mt6359_rt1015p_rt5682s"; - - speaker-codecs { - sound-dai = <&rt1015p>; - }; - - headset-codec { - sound-dai = <&rt5682 0>; - }; -}; - -&touchscreen { - compatible = "hid-over-i2c"; - post-power-on-delay-ms = <10>; - hid-descr-addr = <0x0001>; - vdd-supply = <&pp3300_u>; -}; diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada-spherion-r4.dts b/arch/arm64/boot/dts/mediatek/mt8192-asurada-spherion-r4.dts deleted file mode 100644 index 5e9e598bab90..000000000000 --- a/arch/arm64/boot/dts/mediatek/mt8192-asurada-spherion-r4.dts +++ /dev/null @@ -1,78 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) -/* - * Copyright 2022 Google LLC - */ -/dts-v1/; -#include "mt8192-asurada.dtsi" -#include - -/ { - model = "Google Spherion (rev4)"; - chassis-type = "laptop"; - compatible = "google,spherion-rev4", "google,spherion", - "mediatek,mt8192"; - - pwmleds { - compatible = "pwm-leds"; - - led { - function = LED_FUNCTION_KBD_BACKLIGHT; - color = ; - pwms = <&cros_ec_pwm 0>; - max-brightness = <1023>; - }; - }; -}; - -&cros_ec_pwm { - status = "okay"; -}; - -&keyboard_controller { - function-row-physmap = < - MATRIX_KEY(0x00, 0x02, 0) /* T1 */ - MATRIX_KEY(0x03, 0x02, 0) /* T2 */ - MATRIX_KEY(0x02, 0x02, 0) /* T3 */ - MATRIX_KEY(0x01, 0x02, 0) /* T4 */ - MATRIX_KEY(0x03, 0x04, 0) /* T5 */ - MATRIX_KEY(0x02, 0x04, 0) /* T6 */ - MATRIX_KEY(0x01, 0x04, 0) /* T7 */ - MATRIX_KEY(0x02, 0x09, 0) /* T8 */ - MATRIX_KEY(0x01, 0x09, 0) /* T9 */ - MATRIX_KEY(0x00, 0x04, 0) /* T10 */ - >; - linux,keymap = < - MATRIX_KEY(0x00, 0x02, KEY_BACK) - MATRIX_KEY(0x03, 0x02, KEY_REFRESH) - MATRIX_KEY(0x02, 0x02, KEY_FULL_SCREEN) - MATRIX_KEY(0x01, 0x02, KEY_SCALE) - MATRIX_KEY(0x03, 0x04, KEY_SYSRQ) - MATRIX_KEY(0x02, 0x04, KEY_BRIGHTNESSDOWN) - MATRIX_KEY(0x01, 0x04, KEY_BRIGHTNESSUP) - MATRIX_KEY(0x02, 0x09, KEY_MUTE) - MATRIX_KEY(0x01, 0x09, KEY_VOLUMEDOWN) - MATRIX_KEY(0x00, 0x04, KEY_VOLUMEUP) - - CROS_STD_MAIN_KEYMAP - >; -}; - -&rt5682 { - compatible = "realtek,rt5682s"; -}; - -&sound { - compatible = "mediatek,mt8192_mt6359_rt1015p_rt5682s"; - - speaker-codecs { - sound-dai = <&rt1015p>; - }; - - headset-codec { - sound-dai = <&rt5682 0>; - }; -}; - -&touchscreen { - compatible = "elan,ekth3500"; -}; diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi index 8dda8b63765b..dd0d07fbe61a 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi @@ -1418,7 +1418,6 @@ regulators { mt6315_6_vbuck1: vbuck1 { - regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; @@ -1428,7 +1427,6 @@ }; mt6315_6_vbuck3: vbuck3 { - regulator-compatible = "vbuck3"; regulator-name = "Vlcpu"; regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; @@ -1445,7 +1443,6 @@ regulators { mt6315_7_vbuck1: vbuck1 { - regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; regulator-min-microvolt = <400000>; regulator-max-microvolt = <800000>; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi index 2c7b2223ee76..5056e07399e2 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi @@ -1285,7 +1285,6 @@ regulators { mt6315_6_vbuck1: vbuck1 { - regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; @@ -1303,7 +1302,6 @@ regulators { mt6315_7_vbuck1: vbuck1 { - regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts index 31d424b8fc7c..1f59b5786b81 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts @@ -109,6 +109,7 @@ pinctrl-names = "default", "sleep"; pinctrl-0 = <ð_default_pins>; pinctrl-1 = <ð_sleep_pins>; + mediatek,mac-wol; status = "okay"; mdio { @@ -137,7 +138,6 @@ richtek,vinovp-microvolt = <14500000>; otg_vbus_regulator: usb-otg-vbus-regulator { - regulator-compatible = "usb-otg-vbus"; regulator-name = "usb-otg-vbus"; regulator-min-microvolt = <4425000>; regulator-max-microvolt = <5825000>; @@ -149,7 +149,6 @@ LDO_VIN3-supply = <&mt6360_buck2>; mt6360_buck1: buck1 { - regulator-compatible = "BUCK1"; regulator-name = "mt6360,buck1"; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1300000>; @@ -160,7 +159,6 @@ }; mt6360_buck2: buck2 { - regulator-compatible = "BUCK2"; regulator-name = "mt6360,buck2"; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1300000>; @@ -171,7 +169,6 @@ }; mt6360_ldo1: ldo1 { - regulator-compatible = "LDO1"; regulator-name = "mt6360,ldo1"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <3600000>; @@ -180,7 +177,6 @@ }; mt6360_ldo2: ldo2 { - regulator-compatible = "LDO2"; regulator-name = "mt6360,ldo2"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <3600000>; @@ -189,7 +185,6 @@ }; mt6360_ldo3: ldo3 { - regulator-compatible = "LDO3"; regulator-name = "mt6360,ldo3"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <3600000>; @@ -198,7 +193,6 @@ }; mt6360_ldo5: ldo5 { - regulator-compatible = "LDO5"; regulator-name = "mt6360,ldo5"; regulator-min-microvolt = <2700000>; regulator-max-microvolt = <3600000>; @@ -207,7 +201,6 @@ }; mt6360_ldo6: ldo6 { - regulator-compatible = "LDO6"; regulator-name = "mt6360,ldo6"; regulator-min-microvolt = <500000>; regulator-max-microvolt = <2100000>; @@ -216,7 +209,6 @@ }; mt6360_ldo7: ldo7 { - regulator-compatible = "LDO7"; regulator-name = "mt6360,ldo7"; regulator-min-microvolt = <500000>; regulator-max-microvolt = <2100000>; diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index ade685ed2190..f013dbad9dc4 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -1611,9 +1611,6 @@ phy-names = "pcie-phy"; power-domains = <&spm MT8195_POWER_DOMAIN_PCIE_MAC_P1>; - resets = <&infracfg_ao MT8195_INFRA_RST2_PCIE_P1_SWRST>; - reset-names = "mac"; - #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie_intc1 0>, @@ -3138,7 +3135,7 @@ }; ovl0: ovl@1c000000 { - compatible = "mediatek,mt8195-disp-ovl", "mediatek,mt8183-disp-ovl"; + compatible = "mediatek,mt8195-disp-ovl"; reg = <0 0x1c000000 0 0x1000>; interrupts = ; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>; diff --git a/arch/arm64/boot/dts/mediatek/mt8365-evk.dts b/arch/arm64/boot/dts/mediatek/mt8365-evk.dts index 7d90112a7e27..44c61094c4d5 100644 --- a/arch/arm64/boot/dts/mediatek/mt8365-evk.dts +++ b/arch/arm64/boot/dts/mediatek/mt8365-evk.dts @@ -21,6 +21,7 @@ aliases { serial0 = &uart0; + ethernet = ðernet; }; chosen { diff --git a/arch/arm64/boot/dts/mediatek/mt8365.dtsi b/arch/arm64/boot/dts/mediatek/mt8365.dtsi index 9c91fe8ea0f9..2bf8c9d02b6e 100644 --- a/arch/arm64/boot/dts/mediatek/mt8365.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8365.dtsi @@ -449,7 +449,8 @@ }; keypad: keypad@10010000 { - compatible = "mediatek,mt6779-keypad"; + compatible = "mediatek,mt8365-keypad", + "mediatek,mt6779-keypad"; reg = <0 0x10010000 0 0x1000>; wakeup-source; interrupts = ; diff --git a/arch/arm64/boot/dts/mediatek/mt8390-genio-700-evk.dts b/arch/arm64/boot/dts/mediatek/mt8390-genio-700-evk.dts index 13f2e0e3fa8a..04e4a2f73799 100644 --- a/arch/arm64/boot/dts/mediatek/mt8390-genio-700-evk.dts +++ b/arch/arm64/boot/dts/mediatek/mt8390-genio-700-evk.dts @@ -93,6 +93,24 @@ compatible = "shared-dma-pool"; reg = <0 0x57000000 0 0x1400000>; /* 20 MB */ }; + + adsp_mem: memory@60000000 { + compatible = "shared-dma-pool"; + reg = <0 0x60000000 0 0xf00000>; + no-map; + }; + + afe_dma_mem: memory@60f00000 { + compatible = "shared-dma-pool"; + reg = <0 0x60f00000 0 0x100000>; + no-map; + }; + + adsp_dma_mem: memory@61000000 { + compatible = "shared-dma-pool"; + reg = <0 0x61000000 0 0x100000>; + no-map; + }; }; common_fixed_5v: regulator-0 { @@ -210,6 +228,16 @@ }; }; +&adsp { + memory-region = <&adsp_dma_mem>, <&adsp_mem>; + status = "okay"; +}; + +&afe { + memory-region = <&afe_dma_mem>; + status = "okay"; +}; + &gpu { mali-supply = <&mt6359_vproc2_buck_reg>; status = "okay"; @@ -932,6 +960,26 @@ status = "okay"; }; +&sound { + compatible = "mediatek,mt8390-mt6359-evk", "mediatek,mt8188-mt6359-evb"; + model = "mt8390-evk"; + pinctrl-names = "default"; + pinctrl-0 = <&audio_default_pins>; + audio-routing = + "Headphone", "Headphone L", + "Headphone", "Headphone R"; + mediatek,adsp = <&adsp>; + status = "okay"; + + dai-link-0 { + link-name = "DL_SRC_BE"; + + codec { + sound-dai = <&pmic 0>; + }; + }; +}; + &spi2 { pinctrl-0 = <&spi2_pins>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts index 5f16fb820580..5950194c9ccb 100644 --- a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts +++ b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts @@ -835,7 +835,6 @@ regulators { mt6315_6_vbuck1: vbuck1 { - regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1193750>; @@ -852,7 +851,6 @@ regulators { mt6315_7_vbuck1: vbuck1 { - regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; regulator-min-microvolt = <546000>; regulator-max-microvolt = <787000>; diff --git a/arch/arm64/boot/dts/mediatek/mt8395-kontron-3-5-sbc-i1200.dts b/arch/arm64/boot/dts/mediatek/mt8395-kontron-3-5-sbc-i1200.dts index e2e75b8ff918..4985b65925a9 100644 --- a/arch/arm64/boot/dts/mediatek/mt8395-kontron-3-5-sbc-i1200.dts +++ b/arch/arm64/boot/dts/mediatek/mt8395-kontron-3-5-sbc-i1200.dts @@ -271,6 +271,7 @@ pinctrl-names = "default", "sleep"; pinctrl-0 = <ð_default_pins>; pinctrl-1 = <ð_sleep_pins>; + mediatek,mac-wol; status = "okay"; mdio { diff --git a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts index 14ec970c4e49..41dc34837b02 100644 --- a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts +++ b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts @@ -812,7 +812,6 @@ regulators { mt6315_6_vbuck1: vbuck1 { - regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1193750>; @@ -829,7 +828,6 @@ regulators { mt6315_7_vbuck1: vbuck1 { - regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1193750>; diff --git a/arch/arm64/boot/dts/mediatek/mt8516.dtsi b/arch/arm64/boot/dts/mediatek/mt8516.dtsi index d0b03dc4d3f4..b5e753759465 100644 --- a/arch/arm64/boot/dts/mediatek/mt8516.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8516.dtsi @@ -144,10 +144,10 @@ #size-cells = <2>; ranges; - /* 128 KiB reserved for ARM Trusted Firmware (BL31) */ + /* 192 KiB reserved for ARM Trusted Firmware (BL31) */ bl31_secmon_reserved: secmon@43000000 { no-map; - reg = <0 0x43000000 0 0x20000>; + reg = <0 0x43000000 0 0x30000>; }; }; @@ -206,7 +206,7 @@ compatible = "mediatek,mt8516-wdt", "mediatek,mt6589-wdt"; reg = <0 0x10007000 0 0x1000>; - interrupts = ; + interrupts = ; #reset-cells = <1>; }; @@ -220,6 +220,17 @@ clock-names = "clk13m", "bus"; }; + keypad: keypad@10002000 { + compatible = "mediatek,mt8516-keypad", + "mediatek,mt6779-keypad"; + reg = <0 0x10002000 0 0x1000>; + wakeup-source; + interrupts = ; + clocks = <&clk26m>; + clock-names = "kpd"; + status = "disabled"; + }; + syscfg_pctl: syscfg-pctl@10005000 { compatible = "syscon"; reg = <0 0x10005000 0 0x1000>; @@ -268,7 +279,7 @@ interrupt-parent = <&gic>; interrupt-controller; reg = <0 0x10310000 0 0x1000>, - <0 0x10320000 0 0x1000>, + <0 0x1032f000 0 0x2000>, <0 0x10340000 0 0x2000>, <0 0x10360000 0 0x2000>; interrupts = , <0 0x11000180 0 0x80>; interrupts = ; + clock-div = <2>; clocks = <&topckgen CLK_TOP_I2C0>, <&topckgen CLK_TOP_APDMA>; clock-names = "main", "dma"; @@ -358,6 +370,7 @@ reg = <0 0x1100a000 0 0x90>, <0 0x11000200 0 0x80>; interrupts = ; + clock-div = <2>; clocks = <&topckgen CLK_TOP_I2C1>, <&topckgen CLK_TOP_APDMA>; clock-names = "main", "dma"; @@ -372,6 +385,7 @@ reg = <0 0x1100b000 0 0x90>, <0 0x11000280 0 0x80>; interrupts = ; + clock-div = <2>; clocks = <&topckgen CLK_TOP_I2C2>, <&topckgen CLK_TOP_APDMA>; clock-names = "main", "dma"; diff --git a/arch/arm64/boot/dts/mediatek/pumpkin-common.dtsi b/arch/arm64/boot/dts/mediatek/pumpkin-common.dtsi index ec8dfb3d1c6d..a356db5fcc5f 100644 --- a/arch/arm64/boot/dts/mediatek/pumpkin-common.dtsi +++ b/arch/arm64/boot/dts/mediatek/pumpkin-common.dtsi @@ -47,7 +47,6 @@ }; &i2c0 { - clock-div = <2>; pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins_a>; status = "okay"; @@ -156,7 +155,6 @@ }; &i2c2 { - clock-div = <2>; pinctrl-names = "default"; pinctrl-0 = <&i2c2_pins_a>; status = "okay"; diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi index 984c85eab41a..2601b43b2d8c 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi @@ -3815,7 +3815,7 @@ compatible = "nvidia,tegra234-sce-fabric"; reg = <0x0 0xb600000 0x0 0x40000>; interrupts = ; - status = "okay"; + status = "disabled"; }; rce-fabric@be00000 { @@ -3900,7 +3900,7 @@ assigned-clock-parents = <&bpmp TEGRA234_CLK_PLLP_OUT0>; resets = <&bpmp TEGRA234_RESET_SPI2>; reset-names = "spi"; - dmas = <&gpcdma 19>, <&gpcdma 19>; + dmas = <&gpcdma 16>, <&gpcdma 16>; dma-names = "rx", "tx"; dma-coherent; status = "disabled"; @@ -3995,7 +3995,7 @@ }; dce-fabric@de00000 { - compatible = "nvidia,tegra234-sce-fabric"; + compatible = "nvidia,tegra234-dce-fabric"; reg = <0x0 0xde00000 0x0 0x40000>; interrupts = ; status = "okay"; @@ -4018,6 +4018,8 @@ #redistributor-regions = <1>; #interrupt-cells = <3>; interrupt-controller; + + #address-cells = <0>; }; smmu_iso: iommu@10000000 { diff --git a/arch/arm64/boot/dts/qcom/Makefile b/arch/arm64/boot/dts/qcom/Makefile index 6ca8db4b8afe..140b0b2abfb5 100644 --- a/arch/arm64/boot/dts/qcom/Makefile +++ b/arch/arm64/boot/dts/qcom/Makefile @@ -3,6 +3,8 @@ dtb-$(CONFIG_ARCH_QCOM) += apq8016-sbc.dtb apq8016-sbc-usb-host-dtbs := apq8016-sbc.dtb apq8016-sbc-usb-host.dtbo +dtb-$(CONFIG_ARCH_QCOM) += sar2130p-qar2130p.dtb + dtb-$(CONFIG_ARCH_QCOM) += apq8016-sbc-usb-host.dtb dtb-$(CONFIG_ARCH_QCOM) += apq8016-sbc-d3-camera-mezzanine.dtb dtb-$(CONFIG_ARCH_QCOM) += apq8016-schneider-hmibsc.dtb @@ -16,6 +18,7 @@ dtb-$(CONFIG_ARCH_QCOM) += ipq5332-rdp441.dtb dtb-$(CONFIG_ARCH_QCOM) += ipq5332-rdp442.dtb dtb-$(CONFIG_ARCH_QCOM) += ipq5332-rdp468.dtb dtb-$(CONFIG_ARCH_QCOM) += ipq5332-rdp474.dtb +dtb-$(CONFIG_ARCH_QCOM) += ipq5424-rdp466.dtb dtb-$(CONFIG_ARCH_QCOM) += ipq6018-cp01-c1.dtb dtb-$(CONFIG_ARCH_QCOM) += ipq8074-hk01.dtb dtb-$(CONFIG_ARCH_QCOM) += ipq8074-hk10-c1.dtb @@ -59,6 +62,7 @@ dtb-$(CONFIG_ARCH_QCOM) += msm8916-wingtech-wt86518.dtb dtb-$(CONFIG_ARCH_QCOM) += msm8916-wingtech-wt86528.dtb dtb-$(CONFIG_ARCH_QCOM) += msm8916-wingtech-wt88047.dtb dtb-$(CONFIG_ARCH_QCOM) += msm8916-yiming-uz801v3.dtb +dtb-$(CONFIG_ARCH_QCOM) += msm8917-xiaomi-riva.dtb dtb-$(CONFIG_ARCH_QCOM) += msm8929-wingtech-wt82918hd.dtb dtb-$(CONFIG_ARCH_QCOM) += msm8939-huawei-kiwi.dtb dtb-$(CONFIG_ARCH_QCOM) += msm8939-longcheer-l9100.dtb @@ -110,7 +114,9 @@ dtb-$(CONFIG_ARCH_QCOM) += qcm6490-idp.dtb dtb-$(CONFIG_ARCH_QCOM) += qcm6490-shift-otter.dtb dtb-$(CONFIG_ARCH_QCOM) += qcs404-evb-1000.dtb dtb-$(CONFIG_ARCH_QCOM) += qcs404-evb-4000.dtb +dtb-$(CONFIG_ARCH_QCOM) += qcs615-ride.dtb dtb-$(CONFIG_ARCH_QCOM) += qcs6490-rb3gen2.dtb +dtb-$(CONFIG_ARCH_QCOM) += qcs8300-ride.dtb dtb-$(CONFIG_ARCH_QCOM) += qcs8550-aim300-aiot.dtb dtb-$(CONFIG_ARCH_QCOM) += qcs9100-ride.dtb dtb-$(CONFIG_ARCH_QCOM) += qcs9100-ride-r3.dtb @@ -195,8 +201,10 @@ dtb-$(CONFIG_ARCH_QCOM) += sc7280-crd-r3.dtb dtb-$(CONFIG_ARCH_QCOM) += sc8180x-lenovo-flex-5g.dtb dtb-$(CONFIG_ARCH_QCOM) += sc8180x-primus.dtb dtb-$(CONFIG_ARCH_QCOM) += sc8280xp-crd.dtb +dtb-$(CONFIG_ARCH_QCOM) += sc8280xp-huawei-gaokun3.dtb dtb-$(CONFIG_ARCH_QCOM) += sc8280xp-lenovo-thinkpad-x13s.dtb dtb-$(CONFIG_ARCH_QCOM) += sc8280xp-microsoft-arcata.dtb +dtb-$(CONFIG_ARCH_QCOM) += sc8280xp-microsoft-blackrock.dtb dtb-$(CONFIG_ARCH_QCOM) += sda660-inforce-ifc6560.dtb dtb-$(CONFIG_ARCH_QCOM) += sdm450-lenovo-tbx605f.dtb dtb-$(CONFIG_ARCH_QCOM) += sdm450-motorola-ali.dtb @@ -278,10 +286,14 @@ dtb-$(CONFIG_ARCH_QCOM) += sm8650-hdk-display-card.dtb dtb-$(CONFIG_ARCH_QCOM) += sm8650-hdk.dtb dtb-$(CONFIG_ARCH_QCOM) += sm8650-mtp.dtb dtb-$(CONFIG_ARCH_QCOM) += sm8650-qrd.dtb +dtb-$(CONFIG_ARCH_QCOM) += sm8750-mtp.dtb +dtb-$(CONFIG_ARCH_QCOM) += sm8750-qrd.dtb +dtb-$(CONFIG_ARCH_QCOM) += x1e001de-devkit.dtb dtb-$(CONFIG_ARCH_QCOM) += x1e78100-lenovo-thinkpad-t14s.dtb dtb-$(CONFIG_ARCH_QCOM) += x1e80100-asus-vivobook-s15.dtb dtb-$(CONFIG_ARCH_QCOM) += x1e80100-crd.dtb dtb-$(CONFIG_ARCH_QCOM) += x1e80100-dell-xps13-9345.dtb +dtb-$(CONFIG_ARCH_QCOM) += x1e80100-hp-omnibook-x14.dtb dtb-$(CONFIG_ARCH_QCOM) += x1e80100-lenovo-yoga-slim7x.dtb dtb-$(CONFIG_ARCH_QCOM) += x1e80100-microsoft-romulus13.dtb dtb-$(CONFIG_ARCH_QCOM) += x1e80100-microsoft-romulus15.dtb diff --git a/arch/arm64/boot/dts/qcom/ipq5332.dtsi b/arch/arm64/boot/dts/qcom/ipq5332.dtsi index d3c3e215a15c..ca3da95730bd 100644 --- a/arch/arm64/boot/dts/qcom/ipq5332.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq5332.dtsi @@ -180,7 +180,7 @@ }; rng: rng@e3000 { - compatible = "qcom,prng-ee"; + compatible = "qcom,ipq5332-trng", "qcom,trng"; reg = <0x000e3000 0x1000>; clocks = <&gcc GCC_PRNG_AHB_CLK>; clock-names = "core"; diff --git a/arch/arm64/boot/dts/qcom/ipq5424-rdp466.dts b/arch/arm64/boot/dts/qcom/ipq5424-rdp466.dts new file mode 100644 index 000000000000..b6e4bb3328b3 --- /dev/null +++ b/arch/arm64/boot/dts/qcom/ipq5424-rdp466.dts @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause +/* + * IPQ5424 RDP466 board device tree source + * + * Copyright (c) 2024 The Linux Foundation. All rights reserved. + */ + +/dts-v1/; + +#include "ipq5424.dtsi" + +/ { + model = "Qualcomm Technologies, Inc. IPQ5424 RDP466"; + compatible = "qcom,ipq5424-rdp466", "qcom,ipq5424"; + + aliases { + serial0 = &uart1; + }; + + vreg_misc_3p3: regulator-usb-3p3 { + compatible = "regulator-fixed"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + regulator-name = "usb_hs_vdda_3p3"; + }; + + vreg_misc_1p8: regulator-usb-1p8 { + compatible = "regulator-fixed"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + regulator-name = "vdda_1p8_usb"; + }; + + vreg_misc_0p925: regulator-usb-0p925 { + compatible = "regulator-fixed"; + regulator-min-microvolt = <925000>; + regulator-max-microvolt = <925000>; + regulator-boot-on; + regulator-always-on; + regulator-name = "vdd_core_usb"; + }; +}; + +&dwc_0 { + dr_mode = "host"; +}; + +&dwc_1 { + dr_mode = "host"; +}; + +&qusb_phy_0 { + vdd-supply = <&vreg_misc_0p925>; + vdda-pll-supply = <&vreg_misc_1p8>; + vdda-phy-dpdm-supply = <&vreg_misc_3p3>; + + status = "okay"; +}; + +&qusb_phy_1 { + vdd-supply = <&vreg_misc_0p925>; + vdda-pll-supply = <&vreg_misc_1p8>; + vdda-phy-dpdm-supply = <&vreg_misc_3p3>; + + status = "okay"; +}; + +&sleep_clk { + clock-frequency = <32000>; +}; + +&spi0 { + pinctrl-0 = <&spi0_default_state>; + pinctrl-names = "default"; + status = "okay"; + + flash@0 { + compatible = "micron,n25q128a11", "jedec,spi-nor"; + reg = <0>; + #address-cells = <1>; + #size-cells = <1>; + spi-max-frequency = <50000000>; + }; +}; + +&ssphy_0 { + vdda-pll-supply = <&vreg_misc_1p8>; + vdda-phy-supply = <&vreg_misc_0p925>; + + status = "okay"; +}; + +&tlmm { + spi0_default_state: spi0-default-state { + clk-pins { + pins = "gpio6"; + function = "spi0_clk"; + drive-strength = <8>; + bias-pull-down; + }; + + cs-pins { + pins = "gpio7"; + function = "spi0_cs"; + drive-strength = <8>; + bias-pull-up; + }; + + miso-pins { + pins = "gpio8"; + function = "spi0_miso"; + drive-strength = <8>; + bias-pull-down; + }; + + mosi-pins { + pins = "gpio9"; + function = "spi0_mosi"; + drive-strength = <8>; + bias-pull-down; + }; + }; + + sdc_default_state: sdc-default-state { + clk-pins { + pins = "gpio5"; + function = "sdc_clk"; + drive-strength = <8>; + bias-disable; + }; + + cmd-pins { + pins = "gpio4"; + function = "sdc_cmd"; + drive-strength = <8>; + bias-pull-up; + }; + + data-pins { + pins = "gpio0", "gpio1", "gpio2", "gpio3"; + function = "sdc_data"; + drive-strength = <8>; + bias-pull-up; + }; + }; +}; + +&uart1 { + pinctrl-0 = <&uart1_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&usb2 { + status = "okay"; +}; + +&usb3 { + status = "okay"; +}; + +&xo_board { + clock-frequency = <24000000>; +}; + diff --git a/arch/arm64/boot/dts/qcom/ipq5424.dtsi b/arch/arm64/boot/dts/qcom/ipq5424.dtsi new file mode 100644 index 000000000000..7034d378b1ef --- /dev/null +++ b/arch/arm64/boot/dts/qcom/ipq5424.dtsi @@ -0,0 +1,519 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* + * IPQ5424 device tree source + * + * Copyright (c) 2020-2021 The Linux Foundation. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include + +/ { + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&intc>; + + clocks { + sleep_clk: sleep-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; + + xo_board: xo-board-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; + }; + + cpus: cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0>; + enable-method = "psci"; + next-level-cache = <&l2_0>; + l2_0: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + + l3_0: l3-cache { + compatible = "cache"; + cache-level = <3>; + cache-unified; + }; + }; + }; + + cpu1: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + enable-method = "psci"; + reg = <0x100>; + next-level-cache = <&l2_100>; + + l2_100: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu2: cpu@200 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + enable-method = "psci"; + reg = <0x200>; + next-level-cache = <&l2_200>; + + l2_200: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu3: cpu@300 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + enable-method = "psci"; + reg = <0x300>; + next-level-cache = <&l2_300>; + + l2_300: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + }; + + firmware { + scm { + compatible = "qcom,scm-ipq5424", "qcom,scm"; + qcom,dload-mode = <&tcsr 0x25100>; + }; + }; + + memory@80000000 { + device_type = "memory"; + /* We expect the bootloader to fill in the size */ + reg = <0x0 0x80000000 0x0 0x0>; + }; + + pmu-a55 { + compatible = "arm,cortex-a55-pmu"; + interrupts = ; + }; + + pmu-dsu { + compatible = "arm,dsu-pmu"; + interrupts = ; + cpus = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>; + }; + + psci { + compatible = "arm,psci-1.0"; + method = "smc"; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + tz@8a600000 { + reg = <0x0 0x8a600000 0x0 0x200000>; + no-map; + }; + + smem@8a800000 { + compatible = "qcom,smem"; + reg = <0x0 0x8a800000 0x0 0x32000>; + no-map; + + hwlocks = <&tcsr_mutex 3>; + }; + }; + + soc@0 { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0 0 0 0 0x10 0>; + + rng: rng@4c3000 { + compatible = "qcom,ipq5424-trng", "qcom,trng"; + reg = <0 0x004c3000 0 0x1000>; + clocks = <&gcc GCC_PRNG_AHB_CLK>; + clock-names = "core"; + }; + + system-cache-controller@800000 { + compatible = "qcom,ipq5424-llcc"; + reg = <0 0x00800000 0 0x200000>; + reg-names = "llcc0_base"; + interrupts = ; + }; + + tlmm: pinctrl@1000000 { + compatible = "qcom,ipq5424-tlmm"; + reg = <0 0x01000000 0 0x300000>; + interrupts = ; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&tlmm 0 0 50>; + interrupt-controller; + #interrupt-cells = <2>; + + uart1_pins: uart1-state { + pins = "gpio43", "gpio44"; + function = "uart1"; + drive-strength = <8>; + bias-pull-up; + }; + }; + + gcc: clock-controller@1800000 { + compatible = "qcom,ipq5424-gcc"; + reg = <0 0x01800000 0 0x40000>; + clocks = <&xo_board>, + <&sleep_clk>, + <0>, + <0>, + <0>, + <0>, + <0>; + #clock-cells = <1>; + #reset-cells = <1>; + #interconnect-cells = <1>; + }; + + tcsr_mutex: hwlock@1905000 { + compatible = "qcom,tcsr-mutex"; + reg = <0 0x01905000 0 0x20000>; + #hwlock-cells = <1>; + }; + + tcsr: syscon@1937000 { + compatible = "qcom,tcsr-ipq5424", "syscon"; + reg = <0 0x01937000 0 0x2a000>; + }; + + qupv3: geniqup@1ac0000 { + compatible = "qcom,geni-se-qup"; + reg = <0 0x01ac0000 0 0x2000>; + ranges; + clocks = <&gcc GCC_QUPV3_AHB_MST_CLK>, + <&gcc GCC_QUPV3_AHB_SLV_CLK>; + clock-names = "m-ahb", "s-ahb"; + #address-cells = <2>; + #size-cells = <2>; + + uart1: serial@1a84000 { + compatible = "qcom,geni-debug-uart"; + reg = <0 0x01a84000 0 0x4000>; + clocks = <&gcc GCC_QUPV3_UART1_CLK>; + clock-names = "se"; + interrupts = ; + }; + + spi0: spi@1a90000 { + compatible = "qcom,geni-spi"; + reg = <0 0x01a90000 0 0x4000>; + clocks = <&gcc GCC_QUPV3_SPI0_CLK>; + clock-names = "se"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi1: spi@1a94000 { + compatible = "qcom,geni-spi"; + reg = <0 0x01a94000 0 0x4000>; + clocks = <&gcc GCC_QUPV3_SPI1_CLK>; + clock-names = "se"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + }; + + sdhc: mmc@7804000 { + compatible = "qcom,ipq5424-sdhci", "qcom,sdhci-msm-v5"; + reg = <0 0x07804000 0 0x1000>, <0 0x07805000 0 0x1000>; + reg-names = "hc", "cqhci"; + + interrupts = , + ; + interrupt-names = "hc_irq", "pwr_irq"; + + clocks = <&gcc GCC_SDCC1_AHB_CLK>, + <&gcc GCC_SDCC1_APPS_CLK>, + <&xo_board>; + clock-names = "iface", "core", "xo"; + + status = "disabled"; + }; + + intc: interrupt-controller@f200000 { + compatible = "arm,gic-v3"; + reg = <0 0xf200000 0 0x10000>, /* GICD */ + <0 0xf240000 0 0x80000>; /* GICR * 4 regions */ + #interrupt-cells = <0x3>; + interrupt-controller; + #redistributor-regions = <1>; + redistributor-stride = <0x0 0x20000>; + interrupts = ; + mbi-ranges = <672 128>; + msi-controller; + }; + + watchdog@f410000 { + compatible = "qcom,apss-wdt-ipq5424", "qcom,kpss-wdt"; + reg = <0 0x0f410000 0 0x1000>; + interrupts = ; + clocks = <&sleep_clk>; + }; + + qusb_phy_1: phy@71000 { + compatible = "qcom,ipq5424-qusb2-phy"; + reg = <0 0x00071000 0 0x180>; + #phy-cells = <0>; + + clocks = <&gcc GCC_USB1_PHY_CFG_AHB_CLK>, + <&xo_board>; + clock-names = "cfg_ahb", "ref"; + + resets = <&gcc GCC_QUSB2_1_PHY_BCR>; + status = "disabled"; + }; + + usb2: usb2@1e00000 { + compatible = "qcom,ipq5424-dwc3", "qcom,dwc3"; + reg = <0 0x01ef8800 0 0x400>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + clocks = <&gcc GCC_USB1_MASTER_CLK>, + <&gcc GCC_USB1_SLEEP_CLK>, + <&gcc GCC_USB1_MOCK_UTMI_CLK>, + <&gcc GCC_USB1_PHY_CFG_AHB_CLK>, + <&gcc GCC_CNOC_USB_CLK>; + + clock-names = "core", + "sleep", + "mock_utmi", + "iface", + "cfg_noc"; + + assigned-clocks = <&gcc GCC_USB1_MASTER_CLK>, + <&gcc GCC_USB1_MOCK_UTMI_CLK>; + assigned-clock-rates = <200000000>, + <24000000>; + + interrupts-extended = <&intc GIC_SPI 395 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 397 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 387 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 388 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "pwr_event", + "qusb2_phy", + "dm_hs_phy_irq", + "dp_hs_phy_irq"; + + resets = <&gcc GCC_USB1_BCR>; + qcom,select-utmi-as-pipe-clk; + status = "disabled"; + + dwc_1: usb@1e00000 { + compatible = "snps,dwc3"; + reg = <0 0x01e00000 0 0xe000>; + clocks = <&gcc GCC_USB1_MOCK_UTMI_CLK>; + clock-names = "ref"; + interrupts = ; + phys = <&qusb_phy_1>; + phy-names = "usb2-phy"; + tx-fifo-resize; + snps,is-utmi-l1-suspend; + snps,hird-threshold = /bits/ 8 <0x0>; + snps,dis_u2_susphy_quirk; + snps,dis_u3_susphy_quirk; + }; + }; + + qusb_phy_0: phy@7b000 { + compatible = "qcom,ipq5424-qusb2-phy"; + reg = <0 0x0007b000 0 0x180>; + #phy-cells = <0>; + + clocks = <&gcc GCC_USB0_PHY_CFG_AHB_CLK>, + <&xo_board>; + clock-names = "cfg_ahb", "ref"; + + resets = <&gcc GCC_QUSB2_0_PHY_BCR>; + status = "disabled"; + }; + + ssphy_0: phy@7d000 { + compatible = "qcom,ipq5424-qmp-usb3-phy"; + reg = <0 0x0007d000 0 0xa00>; + #phy-cells = <0>; + + clocks = <&gcc GCC_USB0_AUX_CLK>, + <&xo_board>, + <&gcc GCC_USB0_PHY_CFG_AHB_CLK>, + <&gcc GCC_USB0_PIPE_CLK>; + clock-names = "aux", + "ref", + "cfg_ahb", + "pipe"; + + resets = <&gcc GCC_USB0_PHY_BCR>, + <&gcc GCC_USB3PHY_0_PHY_BCR>; + reset-names = "phy", + "phy_phy"; + + #clock-cells = <0>; + clock-output-names = "usb0_pipe_clk"; + + status = "disabled"; + }; + + usb3: usb3@8a00000 { + compatible = "qcom,ipq5424-dwc3", "qcom,dwc3"; + reg = <0 0x08af8800 0 0x400>; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + clocks = <&gcc GCC_USB0_MASTER_CLK>, + <&gcc GCC_USB0_SLEEP_CLK>, + <&gcc GCC_USB0_MOCK_UTMI_CLK>, + <&gcc GCC_USB0_PHY_CFG_AHB_CLK>, + <&gcc GCC_CNOC_USB_CLK>; + + clock-names = "core", + "sleep", + "mock_utmi", + "iface", + "cfg_noc"; + + assigned-clocks = <&gcc GCC_USB0_MASTER_CLK>, + <&gcc GCC_USB0_MOCK_UTMI_CLK>; + assigned-clock-rates = <200000000>, + <24000000>; + + interrupts-extended = <&intc GIC_SPI 412 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 414 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 423 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "pwr_event", + "qusb2_phy", + "dm_hs_phy_irq", + "dp_hs_phy_irq"; + + resets = <&gcc GCC_USB_BCR>; + status = "disabled"; + + dwc_0: usb@8a00000 { + compatible = "snps,dwc3"; + reg = <0 0x08a00000 0 0xcd00>; + clocks = <&gcc GCC_USB0_MOCK_UTMI_CLK>; + clock-names = "ref"; + interrupts = ; + phys = <&qusb_phy_0>, <&ssphy_0>; + phy-names = "usb2-phy", "usb3-phy"; + tx-fifo-resize; + snps,is-utmi-l1-suspend; + snps,hird-threshold = /bits/ 8 <0x0>; + snps,dis_u2_susphy_quirk; + snps,dis_u3_susphy_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; + }; + }; + + timer@f420000 { + compatible = "arm,armv7-timer-mem"; + reg = <0 0xf420000 0 0x1000>; + ranges = <0 0 0 0x10000000>; + #address-cells = <1>; + #size-cells = <1>; + + frame@f421000 { + reg = <0xf421000 0x1000>, + <0xf422000 0x1000>; + interrupts = , + ; + frame-number = <0>; + }; + + frame@f423000 { + reg = <0xf423000 0x1000>; + interrupts = ; + frame-number = <1>; + status = "disabled"; + }; + + frame@f425000 { + reg = <0xf425000 0x1000>, + <0xf426000 0x1000>; + interrupts = ; + frame-number = <2>; + status = "disabled"; + }; + + frame@f427000 { + reg = <0xf427000 0x1000>; + interrupts = ; + frame-number = <3>; + status = "disabled"; + }; + + frame@f429000 { + reg = <0xf429000 0x1000>; + interrupts = ; + frame-number = <4>; + status = "disabled"; + }; + + frame@f42b000 { + reg = <0xf42b000 0x1000>; + interrupts = ; + frame-number = <5>; + status = "disabled"; + }; + + frame@f42d000 { + reg = <0xf42d000 0x1000>; + interrupts = ; + frame-number = <6>; + status = "disabled"; + }; + }; + + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + , + ; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi b/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi index 91e104b0f865..ae12f069f26f 100644 --- a/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq9574-rdp-common.dtsi @@ -3,7 +3,7 @@ * IPQ9574 RDP board common device tree source * * Copyright (c) 2020-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2023-2024, Qualcomm Innovation Center, Inc. All rights reserved. */ /dts-v1/; @@ -164,6 +164,26 @@ status = "okay"; }; +/* + * The bootstrap pins for the board select the XO clock frequency + * (48 MHZ or 96 MHZ used for different RDP type board). This setting + * automatically enables the right dividers, to ensure the reference + * clock output from WiFi to the CMN PLL is 48 MHZ. + */ +&ref_48mhz_clk { + clock-div = <1>; + clock-mult = <1>; +}; + +/* + * The frequency of xo_board_clk is fixed to 24 MHZ, which is routed + * from WiFi output clock 48 MHZ divided by 2. + */ &xo_board_clk { - clock-frequency = <24000000>; + clock-div = <2>; + clock-mult = <1>; +}; + +&xo_clk { + clock-frequency = <48000000>; }; diff --git a/arch/arm64/boot/dts/qcom/ipq9574-rdp433.dts b/arch/arm64/boot/dts/qcom/ipq9574-rdp433.dts index 1bb8d96c9a82..165ebbb59511 100644 --- a/arch/arm64/boot/dts/qcom/ipq9574-rdp433.dts +++ b/arch/arm64/boot/dts/qcom/ipq9574-rdp433.dts @@ -8,6 +8,7 @@ /dts-v1/; +#include #include "ipq9574-rdp-common.dtsi" / { @@ -15,6 +16,45 @@ compatible = "qcom,ipq9574-ap-al02-c7", "qcom,ipq9574"; }; +&pcie1_phy { + status = "okay"; +}; + +&pcie1 { + pinctrl-0 = <&pcie1_default>; + pinctrl-names = "default"; + + perst-gpios = <&tlmm 26 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 27 GPIO_ACTIVE_LOW>; + status = "okay"; +}; + +&pcie2_phy { + status = "okay"; +}; + +&pcie2 { + pinctrl-0 = <&pcie2_default>; + pinctrl-names = "default"; + + perst-gpios = <&tlmm 29 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 30 GPIO_ACTIVE_LOW>; + status = "okay"; +}; + +&pcie3_phy { + status = "okay"; +}; + +&pcie3 { + pinctrl-0 = <&pcie3_default>; + pinctrl-names = "default"; + + perst-gpios = <&tlmm 32 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 33 GPIO_ACTIVE_LOW>; + status = "okay"; +}; + &sdhc_1 { pinctrl-0 = <&sdc_default_state>; pinctrl-names = "default"; @@ -28,6 +68,79 @@ }; &tlmm { + + pcie1_default: pcie1-default-state { + clkreq-n-pins { + pins = "gpio25"; + function = "pcie1_clk"; + drive-strength = <6>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio26"; + function = "gpio"; + drive-strength = <8>; + bias-pull-down; + output-low; + }; + + wake-n-pins { + pins = "gpio27"; + function = "pcie1_wake"; + drive-strength = <6>; + bias-pull-up; + }; + }; + + pcie2_default: pcie2-default-state { + clkreq-n-pins { + pins = "gpio28"; + function = "pcie2_clk"; + drive-strength = <6>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio29"; + function = "gpio"; + drive-strength = <8>; + bias-pull-down; + output-low; + }; + + wake-n-pins { + pins = "gpio30"; + function = "pcie2_wake"; + drive-strength = <6>; + bias-pull-up; + }; + }; + + pcie3_default: pcie3-default-state { + clkreq-n-pins { + pins = "gpio31"; + function = "pcie3_clk"; + drive-strength = <6>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio32"; + function = "gpio"; + drive-strength = <8>; + bias-pull-up; + output-low; + }; + + wake-n-pins { + pins = "gpio33"; + function = "pcie3_wake"; + drive-strength = <6>; + bias-pull-up; + }; + }; + sdc_default_state: sdc-default-state { clk-pins { pins = "gpio5"; diff --git a/arch/arm64/boot/dts/qcom/ipq9574.dtsi b/arch/arm64/boot/dts/qcom/ipq9574.dtsi index d1fd35ebc4a2..942290028972 100644 --- a/arch/arm64/boot/dts/qcom/ipq9574.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq9574.dtsi @@ -3,10 +3,11 @@ * IPQ9574 SoC device tree source * * Copyright (c) 2020-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2023-2024, Qualcomm Innovation Center, Inc. All rights reserved. */ #include +#include #include #include #include @@ -19,12 +20,24 @@ #size-cells = <2>; clocks { + ref_48mhz_clk: ref-48mhz-clk { + compatible = "fixed-factor-clock"; + clocks = <&xo_clk>; + #clock-cells = <0>; + }; + sleep_clk: sleep-clk { compatible = "fixed-clock"; #clock-cells = <0>; }; xo_board_clk: xo-board-clk { + compatible = "fixed-factor-clock"; + clocks = <&ref_48mhz_clk>; + #clock-cells = <0>; + }; + + xo_clk: xo-clk { compatible = "fixed-clock"; #clock-cells = <0>; }; @@ -226,8 +239,54 @@ reg = <0x00060000 0x6000>; }; + pcie0_phy: phy@84000 { + compatible = "qcom,ipq9574-qmp-gen3x1-pcie-phy"; + reg = <0x00084000 0x1000>; + + clocks = <&gcc GCC_PCIE0_AUX_CLK>, + <&gcc GCC_PCIE0_AHB_CLK>, + <&gcc GCC_PCIE0_PIPE_CLK>; + clock-names = "aux", "cfg_ahb", "pipe"; + + assigned-clocks = <&gcc GCC_PCIE0_AUX_CLK>; + assigned-clock-rates = <20000000>; + + resets = <&gcc GCC_PCIE0_PHY_BCR>, + <&gcc GCC_PCIE0PHY_PHY_BCR>; + reset-names = "phy", "common"; + + #clock-cells = <0>; + clock-output-names = "gcc_pcie0_pipe_clk_src"; + + #phy-cells = <0>; + status = "disabled"; + }; + + pcie2_phy: phy@8c000 { + compatible = "qcom,ipq9574-qmp-gen3x2-pcie-phy"; + reg = <0x0008c000 0x2000>; + + clocks = <&gcc GCC_PCIE2_AUX_CLK>, + <&gcc GCC_PCIE2_AHB_CLK>, + <&gcc GCC_PCIE2_PIPE_CLK>; + clock-names = "aux", "cfg_ahb", "pipe"; + + assigned-clocks = <&gcc GCC_PCIE2_AUX_CLK>; + assigned-clock-rates = <20000000>; + + resets = <&gcc GCC_PCIE2_PHY_BCR>, + <&gcc GCC_PCIE2PHY_PHY_BCR>; + reset-names = "phy", "common"; + + #clock-cells = <0>; + clock-output-names = "gcc_pcie2_pipe_clk_src"; + + #phy-cells = <0>; + status = "disabled"; + }; + rng: rng@e3000 { - compatible = "qcom,prng-ee"; + compatible = "qcom,ipq9574-trng", "qcom,trng"; reg = <0x000e3000 0x1000>; clocks = <&gcc GCC_PRNG_AHB_CLK>; clock-names = "core"; @@ -243,6 +302,64 @@ status = "disabled"; }; + pcie3_phy: phy@f4000 { + compatible = "qcom,ipq9574-qmp-gen3x2-pcie-phy"; + reg = <0x000f4000 0x2000>; + + clocks = <&gcc GCC_PCIE3_AUX_CLK>, + <&gcc GCC_PCIE3_AHB_CLK>, + <&gcc GCC_PCIE3_PIPE_CLK>; + clock-names = "aux", "cfg_ahb", "pipe"; + + assigned-clocks = <&gcc GCC_PCIE3_AUX_CLK>; + assigned-clock-rates = <20000000>; + + resets = <&gcc GCC_PCIE3_PHY_BCR>, + <&gcc GCC_PCIE3PHY_PHY_BCR>; + reset-names = "phy", "common"; + + #clock-cells = <0>; + clock-output-names = "gcc_pcie3_pipe_clk_src"; + + #phy-cells = <0>; + status = "disabled"; + }; + + pcie1_phy: phy@fc000 { + compatible = "qcom,ipq9574-qmp-gen3x1-pcie-phy"; + reg = <0x000fc000 0x1000>; + + clocks = <&gcc GCC_PCIE1_AUX_CLK>, + <&gcc GCC_PCIE1_AHB_CLK>, + <&gcc GCC_PCIE1_PIPE_CLK>; + clock-names = "aux", "cfg_ahb", "pipe"; + + assigned-clocks = <&gcc GCC_PCIE1_AUX_CLK>; + assigned-clock-rates = <20000000>; + + resets = <&gcc GCC_PCIE1_PHY_BCR>, + <&gcc GCC_PCIE1PHY_PHY_BCR>; + reset-names = "phy", "common"; + + #clock-cells = <0>; + clock-output-names = "gcc_pcie1_pipe_clk_src"; + + #phy-cells = <0>; + status = "disabled"; + }; + + cmn_pll: clock-controller@9b000 { + compatible = "qcom,ipq9574-cmn-pll"; + reg = <0x0009b000 0x800>; + clocks = <&ref_48mhz_clk>, + <&gcc GCC_CMN_12GPLL_AHB_CLK>, + <&gcc GCC_CMN_12GPLL_SYS_CLK>; + clock-names = "ref", "ahb", "sys"; + #clock-cells = <1>; + assigned-clocks = <&cmn_pll CMN_PLL_CLK>; + assigned-clock-rates-u64 = /bits/ 64 <12000000000>; + }; + qfprom: efuse@a4000 { compatible = "qcom,ipq9574-qfprom", "qcom,qfprom"; reg = <0x000a4000 0x5a1>; @@ -309,10 +426,10 @@ clocks = <&xo_board_clk>, <&sleep_clk>, <0>, - <0>, - <0>, - <0>, - <0>, + <&pcie0_phy>, + <&pcie1_phy>, + <&pcie2_phy>, + <&pcie3_phy>, <0>; #clock-cells = <1>; #reset-cells = <1>; @@ -756,6 +873,326 @@ status = "disabled"; }; }; + + pcie1: pcie@10000000 { + compatible = "qcom,pcie-ipq9574"; + reg = <0x10000000 0xf1d>, + <0x10000f20 0xa8>, + <0x10001000 0x1000>, + <0x000f8000 0x4000>, + <0x10100000 0x1000>; + reg-names = "dbi", "elbi", "atu", "parf", "config"; + device_type = "pci"; + linux,pci-domain = <1>; + bus-range = <0x00 0xff>; + num-lanes = <1>; + #address-cells = <3>; + #size-cells = <2>; + + ranges = <0x01000000 0x0 0x00000000 0x10200000 0x0 0x100000>, + <0x02000000 0x0 0x10300000 0x10300000 0x0 0x7d00000>; + + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "msi0", + "msi1", + "msi2", + "msi3", + "msi4", + "msi5", + "msi6", + "msi7"; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc 0 0 35 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc 0 0 49 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc 0 0 84 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc 0 0 85 IRQ_TYPE_LEVEL_HIGH>; + + clocks = <&gcc GCC_PCIE1_AXI_M_CLK>, + <&gcc GCC_PCIE1_AXI_S_CLK>, + <&gcc GCC_PCIE1_AXI_S_BRIDGE_CLK>, + <&gcc GCC_PCIE1_RCHNG_CLK>, + <&gcc GCC_PCIE1_AHB_CLK>, + <&gcc GCC_PCIE1_AUX_CLK>; + clock-names = "axi_m", + "axi_s", + "axi_bridge", + "rchng", + "ahb", + "aux"; + + resets = <&gcc GCC_PCIE1_PIPE_ARES>, + <&gcc GCC_PCIE1_CORE_STICKY_ARES>, + <&gcc GCC_PCIE1_AXI_S_STICKY_ARES>, + <&gcc GCC_PCIE1_AXI_S_ARES>, + <&gcc GCC_PCIE1_AXI_M_STICKY_ARES>, + <&gcc GCC_PCIE1_AXI_M_ARES>, + <&gcc GCC_PCIE1_AUX_ARES>, + <&gcc GCC_PCIE1_AHB_ARES>; + reset-names = "pipe", + "sticky", + "axi_s_sticky", + "axi_s", + "axi_m_sticky", + "axi_m", + "aux", + "ahb"; + + phys = <&pcie1_phy>; + phy-names = "pciephy"; + interconnects = <&gcc MASTER_ANOC_PCIE1 &gcc SLAVE_ANOC_PCIE1>, + <&gcc MASTER_SNOC_PCIE1 &gcc SLAVE_SNOC_PCIE1>; + interconnect-names = "pcie-mem", "cpu-pcie"; + status = "disabled"; + }; + + pcie3: pcie@18000000 { + compatible = "qcom,pcie-ipq9574"; + reg = <0x18000000 0xf1d>, + <0x18000f20 0xa8>, + <0x18001000 0x1000>, + <0x000f0000 0x4000>, + <0x18100000 0x1000>; + reg-names = "dbi", "elbi", "atu", "parf", "config"; + device_type = "pci"; + linux,pci-domain = <3>; + bus-range = <0x00 0xff>; + num-lanes = <2>; + #address-cells = <3>; + #size-cells = <2>; + + ranges = <0x01000000 0x0 0x00000000 0x18200000 0x0 0x100000>, + <0x02000000 0x0 0x18300000 0x18300000 0x0 0x7d00000>; + + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "msi0", + "msi1", + "msi2", + "msi3", + "msi4", + "msi5", + "msi6", + "msi7"; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc 0 0 189 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc 0 0 190 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc 0 0 191 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc 0 0 192 IRQ_TYPE_LEVEL_HIGH>; + + clocks = <&gcc GCC_PCIE3_AXI_M_CLK>, + <&gcc GCC_PCIE3_AXI_S_CLK>, + <&gcc GCC_PCIE3_AXI_S_BRIDGE_CLK>, + <&gcc GCC_PCIE3_RCHNG_CLK>, + <&gcc GCC_PCIE3_AHB_CLK>, + <&gcc GCC_PCIE3_AUX_CLK>; + clock-names = "axi_m", + "axi_s", + "axi_bridge", + "rchng", + "ahb", + "aux"; + + resets = <&gcc GCC_PCIE3_PIPE_ARES>, + <&gcc GCC_PCIE3_CORE_STICKY_ARES>, + <&gcc GCC_PCIE3_AXI_S_STICKY_ARES>, + <&gcc GCC_PCIE3_AXI_S_ARES>, + <&gcc GCC_PCIE3_AXI_M_STICKY_ARES>, + <&gcc GCC_PCIE3_AXI_M_ARES>, + <&gcc GCC_PCIE3_AUX_ARES>, + <&gcc GCC_PCIE3_AHB_ARES>; + reset-names = "pipe", + "sticky", + "axi_s_sticky", + "axi_s", + "axi_m_sticky", + "axi_m", + "aux", + "ahb"; + + phys = <&pcie3_phy>; + phy-names = "pciephy"; + interconnects = <&gcc MASTER_ANOC_PCIE3 &gcc SLAVE_ANOC_PCIE3>, + <&gcc MASTER_SNOC_PCIE3 &gcc SLAVE_SNOC_PCIE3>; + interconnect-names = "pcie-mem", "cpu-pcie"; + status = "disabled"; + }; + + pcie2: pcie@20000000 { + compatible = "qcom,pcie-ipq9574"; + reg = <0x20000000 0xf1d>, + <0x20000f20 0xa8>, + <0x20001000 0x1000>, + <0x00088000 0x4000>, + <0x20100000 0x1000>; + reg-names = "dbi", "elbi", "atu", "parf", "config"; + device_type = "pci"; + linux,pci-domain = <2>; + bus-range = <0x00 0xff>; + num-lanes = <2>; + #address-cells = <3>; + #size-cells = <2>; + + ranges = <0x01000000 0x0 0x00000000 0x20200000 0x0 0x100000>, + <0x02000000 0x0 0x20300000 0x20300000 0x0 0x7d00000>; + + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "msi0", + "msi1", + "msi2", + "msi3", + "msi4", + "msi5", + "msi6", + "msi7"; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc 0 0 164 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc 0 0 165 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc 0 0 186 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc 0 0 187 IRQ_TYPE_LEVEL_HIGH>; + + clocks = <&gcc GCC_PCIE2_AXI_M_CLK>, + <&gcc GCC_PCIE2_AXI_S_CLK>, + <&gcc GCC_PCIE2_AXI_S_BRIDGE_CLK>, + <&gcc GCC_PCIE2_RCHNG_CLK>, + <&gcc GCC_PCIE2_AHB_CLK>, + <&gcc GCC_PCIE2_AUX_CLK>; + clock-names = "axi_m", + "axi_s", + "axi_bridge", + "rchng", + "ahb", + "aux"; + + resets = <&gcc GCC_PCIE2_PIPE_ARES>, + <&gcc GCC_PCIE2_CORE_STICKY_ARES>, + <&gcc GCC_PCIE2_AXI_S_STICKY_ARES>, + <&gcc GCC_PCIE2_AXI_S_ARES>, + <&gcc GCC_PCIE2_AXI_M_STICKY_ARES>, + <&gcc GCC_PCIE2_AXI_M_ARES>, + <&gcc GCC_PCIE2_AUX_ARES>, + <&gcc GCC_PCIE2_AHB_ARES>; + reset-names = "pipe", + "sticky", + "axi_s_sticky", + "axi_s", + "axi_m_sticky", + "axi_m", + "aux", + "ahb"; + + phys = <&pcie2_phy>; + phy-names = "pciephy"; + interconnects = <&gcc MASTER_ANOC_PCIE2 &gcc SLAVE_ANOC_PCIE2>, + <&gcc MASTER_SNOC_PCIE2 &gcc SLAVE_SNOC_PCIE2>; + interconnect-names = "pcie-mem", "cpu-pcie"; + status = "disabled"; + }; + + pcie0: pci@28000000 { + compatible = "qcom,pcie-ipq9574"; + reg = <0x28000000 0xf1d>, + <0x28000f20 0xa8>, + <0x28001000 0x1000>, + <0x00080000 0x4000>, + <0x28100000 0x1000>; + reg-names = "dbi", "elbi", "atu", "parf", "config"; + device_type = "pci"; + linux,pci-domain = <0>; + bus-range = <0x00 0xff>; + num-lanes = <1>; + #address-cells = <3>; + #size-cells = <2>; + + ranges = <0x01000000 0x0 0x00000000 0x28200000 0x0 0x100000>, + <0x02000000 0x0 0x28300000 0x28300000 0x0 0x7d00000>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "msi0", + "msi1", + "msi2", + "msi3", + "msi4", + "msi5", + "msi6", + "msi7"; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc 0 0 75 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc 0 0 78 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc 0 0 79 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc 0 0 83 IRQ_TYPE_LEVEL_HIGH>; + + clocks = <&gcc GCC_PCIE0_AXI_M_CLK>, + <&gcc GCC_PCIE0_AXI_S_CLK>, + <&gcc GCC_PCIE0_AXI_S_BRIDGE_CLK>, + <&gcc GCC_PCIE0_RCHNG_CLK>, + <&gcc GCC_PCIE0_AHB_CLK>, + <&gcc GCC_PCIE0_AUX_CLK>; + clock-names = "axi_m", + "axi_s", + "axi_bridge", + "rchng", + "ahb", + "aux"; + + resets = <&gcc GCC_PCIE0_PIPE_ARES>, + <&gcc GCC_PCIE0_CORE_STICKY_ARES>, + <&gcc GCC_PCIE0_AXI_S_STICKY_ARES>, + <&gcc GCC_PCIE0_AXI_S_ARES>, + <&gcc GCC_PCIE0_AXI_M_STICKY_ARES>, + <&gcc GCC_PCIE0_AXI_M_ARES>, + <&gcc GCC_PCIE0_AUX_ARES>, + <&gcc GCC_PCIE0_AHB_ARES>; + reset-names = "pipe", + "sticky", + "axi_s_sticky", + "axi_s", + "axi_m_sticky", + "axi_m", + "aux", + "ahb"; + + phys = <&pcie0_phy>; + phy-names = "pciephy"; + interconnects = <&gcc MASTER_ANOC_PCIE0 &gcc SLAVE_ANOC_PCIE0>, + <&gcc MASTER_SNOC_PCIE0 &gcc SLAVE_SNOC_PCIE0>; + interconnect-names = "pcie-mem", "cpu-pcie"; + status = "disabled"; + }; + }; thermal-zones { diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-serranove.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-serranove.dts index 5ce8f1350abc..caad1dead2e0 100644 --- a/arch/arm64/boot/dts/qcom/msm8916-samsung-serranove.dts +++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-serranove.dts @@ -321,6 +321,41 @@ status = "okay"; }; +&gpu { + status = "okay"; +}; + +&mdss { + status = "okay"; +}; + +&mdss_dsi0 { + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&mdss_default>; + pinctrl-1 = <&mdss_sleep>; + + panel@0 { + compatible = "samsung,s6e88a0-ams427ap24"; + reg = <0>; + + vdd3-supply = <&pm8916_l17>; + vci-supply = <&pm8916_l6>; + reset-gpios = <&tlmm 25 GPIO_ACTIVE_LOW>; + flip-horizontal; + + port { + panel_in: endpoint { + remote-endpoint = <&mdss_dsi0_out>; + }; + }; + }; +}; + +&mdss_dsi0_out { + data-lanes = <0 1>; + remote-endpoint = <&panel_in>; +}; + &mpss_mem { reg = <0x0 0x86800000 0x0 0x5a00000>; }; @@ -330,6 +365,13 @@ linux,code = ; }; +&pm8916_rpm_regulators { + pm8916_l17: l17 { + regulator-min-microvolt = <2850000>; + regulator-max-microvolt = <2850000>; + }; +}; + &pm8916_vib { status = "okay"; }; @@ -425,6 +467,22 @@ bias-disable; }; + mdss_default: mdss-default-state { + pins = "gpio25"; + function = "gpio"; + + drive-strength = <8>; + bias-disable; + }; + + mdss_sleep: mdss-sleep-state { + pins = "gpio25"; + function = "gpio"; + + drive-strength = <2>; + bias-pull-down; + }; + muic_i2c_default: muic-i2c-default-state { pins = "gpio105", "gpio106"; function = "gpio"; diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index 5e558bcc9d87..8f35c9af1878 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -125,7 +125,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <32768>; + clock-frequency = <32764>; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8917-xiaomi-riva.dts b/arch/arm64/boot/dts/qcom/msm8917-xiaomi-riva.dts new file mode 100644 index 000000000000..f1d22535fedd --- /dev/null +++ b/arch/arm64/boot/dts/qcom/msm8917-xiaomi-riva.dts @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023, Barnabas Czeman + */ + +/dts-v1/; + +#include +#include +#include "msm8917.dtsi" +#include "pm8937.dtsi" + +/delete-node/ &qseecom_mem; + +/ { + model = "Xiaomi Redmi 5A (riva)"; + compatible = "xiaomi,riva", "qcom,msm8917"; + chassis-type = "handset"; + + qcom,msm-id = ; + qcom,board-id = <0x1000b 2>, <0x2000b 2>; + + battery: battery { + compatible = "simple-battery"; + charge-full-design-microamp-hours = <3000000>; + energy-full-design-microwatt-hours = <11500000>; + constant-charge-current-max-microamp = <1000000>; + constant-charge-voltage-max-microvolt = <4400000>; + precharge-current-microamp = <256000>; + charge-term-current-microamp = <60000>; + voltage-min-design-microvolt = <3400000>; + }; + + chosen { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + stdout-path = "framebuffer0"; + + framebuffer0: framebuffer@90001000 { + compatible = "simple-framebuffer"; + reg = <0x0 0x90001000 0x0 (720 * 1280 * 3)>; + width = <720>; + height = <1280>; + stride = <(720 * 3)>; + format = "r8g8b8"; + + clocks = <&gcc GCC_MDSS_AHB_CLK>, + <&gcc GCC_MDSS_AXI_CLK>, + <&gcc GCC_MDSS_VSYNC_CLK>, + <&gcc GCC_MDSS_MDP_CLK>, + <&gcc GCC_MDSS_BYTE0_CLK>, + <&gcc GCC_MDSS_PCLK0_CLK>, + <&gcc GCC_MDSS_ESC0_CLK>; + power-domains = <&gcc MDSS_GDSC>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-0 = <&gpio_keys_default>; + pinctrl-names = "default"; + + key-volup { + label = "Volume Up"; + linux,code = ; + gpios = <&tlmm 91 GPIO_ACTIVE_LOW>; + debounce-interval = <15>; + }; + }; + + vph_pwr: regulator-vph-pwr { + compatible = "regulator-fixed"; + regulator-name = "vph_pwr"; + regulator-min-microvolt = <3700000>; + regulator-max-microvolt = <3700000>; + regulator-always-on; + regulator-boot-on; + }; + + reserved-memory { + qseecom_mem: qseecom@84a00000 { + reg = <0x0 0x84a00000 0x0 0x1900000>; + no-map; + }; + + framebuffer_mem: memory@90001000 { + reg = <0x0 0x90001000 0x0 (720 * 1280 * 3)>; + no-map; + }; + }; +}; + +&blsp1_i2c3 { + status = "okay"; + + touchscreen@38 { + compatible = "edt,edt-ft5306"; + reg = <0x38>; + interrupts-extended = <&tlmm 65 IRQ_TYPE_LEVEL_LOW>; + reset-gpios = <&tlmm 64 GPIO_ACTIVE_LOW>; + pinctrl-0 = <&tsp_int_rst_default>; + pinctrl-names = "default"; + vcc-supply = <&pm8937_l10>; + iovcc-supply = <&pm8937_l5>; + touchscreen-size-x = <720>; + touchscreen-size-y = <1280>; + }; +}; + +&blsp2_i2c1 { + status = "okay"; + + bq27426@55 { + compatible = "ti,bq27426"; + reg = <0x55>; + monitored-battery = <&battery>; + }; + + bq25601@6b{ + compatible = "ti,bq25601"; + reg = <0x6b>; + interrupts-extended = <&tlmm 61 IRQ_TYPE_EDGE_FALLING>; + pinctrl-0 = <&bq25601_int_default>; + pinctrl-names = "default"; + input-voltage-limit-microvolt = <4400000>; + input-current-limit-microamp = <1000000>; + monitored-battery = <&battery>; + }; +}; + +&pm8937_resin { + linux,code = ; + + status = "okay"; +}; + +&rpm_requests { + regulators-0 { + compatible = "qcom,rpm-pm8937-regulators"; + + vdd_s1-supply = <&vph_pwr>; + vdd_s2-supply = <&vph_pwr>; + vdd_s3-supply = <&vph_pwr>; + vdd_s4-supply = <&vph_pwr>; + + vdd_l1_l19-supply = <&pm8937_s3>; + vdd_l2_l23-supply = <&pm8937_s3>; + vdd_l3-supply = <&pm8937_s3>; + vdd_l4_l5_l6_l7_l16-supply = <&pm8937_s4>; + vdd_l8_l11_l12_l17_l22-supply = <&vph_pwr>; + vdd_l9_l10_l13_l14_l15_l18-supply = <&vph_pwr>; + + pm8937_s1: s1 { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1225000>; + }; + + pm8937_s3: s3 { + regulator-min-microvolt = <1300000>; + regulator-max-microvolt = <1300000>; + }; + + pm8937_s4: s4 { + regulator-min-microvolt = <2050000>; + regulator-max-microvolt = <2050000>; + }; + + pm8937_l2: l2 { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + }; + + pm8937_l5: l5 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + pm8937_l6: l6 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + pm8937_l7: l7 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + pm8937_l8: l8 { + regulator-min-microvolt = <2850000>; + regulator-max-microvolt = <2900000>; + }; + + pm8937_l9: l9 { + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3300000>; + }; + + pm8937_l10: l10 { + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <3000000>; + }; + + pm8937_l11: l11 { + regulator-min-microvolt = <2950000>; + regulator-max-microvolt = <2950000>; + regulator-allow-set-load; + regulator-system-load = <200000>; + }; + + pm8937_l12: l12 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2950000>; + }; + + pm8937_l13: l13 { + regulator-min-microvolt = <3075000>; + regulator-max-microvolt = <3075000>; + }; + + pm8937_l14: l14 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + }; + + pm8937_l15: l15 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + }; + + pm8937_l16: l16 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + pm8937_l17: l17 { + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2900000>; + }; + + pm8937_l19: l19 { + regulator-min-microvolt = <1225000>; + regulator-max-microvolt = <1350000>; + }; + + pm8937_l22: l22 { + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + }; + + pm8937_l23: l23 { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + }; + }; + +}; + +&sdhc_1 { + vmmc-supply = <&pm8937_l8>; + vqmmc-supply = <&pm8937_l5>; + + status = "okay"; +}; + +&sdhc_2 { + cd-gpios = <&tlmm 67 GPIO_ACTIVE_LOW>; + vmmc-supply = <&pm8937_l11>; + vqmmc-supply = <&pm8937_l12>; + pinctrl-0 = <&sdc2_default &sdc2_cd_default>; + pinctrl-1 = <&sdc2_sleep &sdc2_cd_default>; + pinctrl-names = "default", "sleep"; + + status = "okay"; +}; + +&sleep_clk { + clock-frequency = <32768>; +}; + +&tlmm { + bq25601_int_default: bq25601-int-default-state { + pins = "gpio61"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + + gpio_keys_default: gpio-keys-default-state { + pins = "gpio91"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + + sdc2_cd_default: sdc2-cd-default-state { + pins = "gpio67"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + tsp_int_rst_default: tsp-int-rst-default-state { + pins = "gpio64", "gpio65"; + function = "gpio"; + drive-strength = <8>; + bias-pull-up; + }; +}; + +&wcnss { + vddpx-supply = <&pm8937_l5>; + + status = "okay"; +}; + +&wcnss_iris { + compatible = "qcom,wcn3620"; + vddxo-supply = <&pm8937_l7>; + vddrfa-supply = <&pm8937_l19>; + vddpa-supply = <&pm8937_l9>; + vdddig-supply = <&pm8937_l5>; +}; + +&wcnss_mem { + status = "okay"; +}; + +&xo_board { + clock-frequency = <19200000>; +}; diff --git a/arch/arm64/boot/dts/qcom/msm8917.dtsi b/arch/arm64/boot/dts/qcom/msm8917.dtsi new file mode 100644 index 000000000000..7bf58dd0146e --- /dev/null +++ b/arch/arm64/boot/dts/qcom/msm8917.dtsi @@ -0,0 +1,1954 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include + +/ { + interrupt-parent = <&intc>; + + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + clocks { + sleep_clk: sleep-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; + + xo_board: xo-board { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@100 { + compatible = "arm,cortex-a53"; + reg = <0x100>; + device_type = "cpu"; + next-level-cache = <&l2_0>; + enable-method = "psci"; + clocks = <&apcs>; + operating-points-v2 = <&cpu_opp_table>; + #cooling-cells = <2>; + power-domains = <&cpu_pd0>; + power-domain-names = "psci"; + + l2_0: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + }; + }; + + cpu1: cpu@101 { + compatible = "arm,cortex-a53"; + reg = <0x101>; + device_type = "cpu"; + next-level-cache = <&l2_0>; + enable-method = "psci"; + clocks = <&apcs>; + operating-points-v2 = <&cpu_opp_table>; + #cooling-cells = <2>; + power-domains = <&cpu_pd1>; + power-domain-names = "psci"; + }; + + cpu2: cpu@102 { + compatible = "arm,cortex-a53"; + reg = <0x102>; + device_type = "cpu"; + next-level-cache = <&l2_0>; + enable-method = "psci"; + clocks = <&apcs>; + operating-points-v2 = <&cpu_opp_table>; + #cooling-cells = <2>; + power-domains = <&cpu_pd2>; + power-domain-names = "psci"; + }; + + cpu3: cpu@103 { + compatible = "arm,cortex-a53"; + reg = <0x103>; + device_type = "cpu"; + next-level-cache = <&l2_0>; + enable-method = "psci"; + clocks = <&apcs>; + operating-points-v2 = <&cpu_opp_table>; + #cooling-cells = <2>; + power-domains = <&cpu_pd3>; + power-domain-names = "psci"; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + }; + }; + + domain-idle-states { + cluster_sleep_0: cluster-sleep-0 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x41000053>; + entry-latency-us = <700>; + exit-latency-us = <1000>; + min-residency-us = <6500>; + }; + }; + + idle-states { + entry-method = "psci"; + + cpu_sleep_0: cpu-sleep-0 { + compatible = "arm,idle-state"; + idle-state-name = "standalone-power-collapse"; + arm,psci-suspend-param = <0x40000003>; + entry-latency-us = <125>; + exit-latency-us = <180>; + min-residency-us = <595>; + local-timer-stop; + }; + }; + + cpu_opp_table: opp-table-cpu { + compatible = "operating-points-v2"; + opp-shared; + + opp-960000000 { + opp-hz = /bits/ 64 <960000000>; + }; + + opp-1094400000 { + opp-hz = /bits/ 64 <1094400000>; + }; + + opp-1248000000 { + opp-hz = /bits/ 64 <1248000000>; + }; + + opp-1401600000 { + opp-hz = /bits/ 64 <1401600000>; + }; + }; + }; + + firmware { + scm: scm { + compatible = "qcom,scm-msm8916", "qcom,scm"; + clocks = <&gcc GCC_CRYPTO_CLK>, + <&gcc GCC_CRYPTO_AXI_CLK>, + <&gcc GCC_CRYPTO_AHB_CLK>; + clock-names = "core", "bus", "iface"; + #reset-cells = <1>; + + qcom,dload-mode = <&tcsr 0x6100>; + }; + }; + + memory@80000000 { + /* We expect the bootloader to fill in the reg */ + reg = <0 0x80000000 0 0>; + device_type = "memory"; + }; + + pmu { + compatible = "arm,cortex-a53-pmu"; + interrupts = ; + }; + + psci { + compatible = "arm,psci-1.0"; + method = "smc"; + + cluster_pd: power-domain-cluster { + #power-domain-cells = <0>; + domain-idle-states = <&cluster_sleep_0>; + }; + + cpu_pd0: power-domain-cpu0 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cpu_sleep_0>; + }; + + cpu_pd1: power-domain-cpu1 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cpu_sleep_0>; + }; + + cpu_pd2: power-domain-cpu2 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cpu_sleep_0>; + }; + + cpu_pd3: power-domain-cpu3 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cpu_sleep_0>; + }; + }; + + rpm: remoteproc { + compatible = "qcom,msm8917-rpm-proc", "qcom,rpm-proc"; + + smd-edge { + interrupts = ; + qcom,ipc = <&apcs 8 0>; + qcom,smd-edge = <15>; + + rpm_requests: rpm-requests { + compatible = "qcom,rpm-msm8917", "qcom,smd-rpm"; + qcom,smd-channels = "rpm_requests"; + + rpmcc: clock-controller { + compatible = "qcom,rpmcc-msm8917", "qcom,rpmcc"; + #clock-cells = <1>; + clocks = <&xo_board>; + clock-names = "xo"; + }; + + rpmpd: power-controller { + compatible = "qcom,msm8917-rpmpd"; + #power-domain-cells = <1>; + operating-points-v2 = <&rpmpd_opp_table>; + + rpmpd_opp_table: opp-table { + compatible = "operating-points-v2"; + + rpmpd_opp_ret: opp1 { + opp-level = ; + }; + + rpmpd_opp_ret_plus: opp2 { + opp-level = ; + }; + + rpmpd_opp_min_svs: opp3 { + opp-level = ; + }; + + rpmpd_opp_low_svs: opp4 { + opp-level = ; + }; + + rpmpd_opp_svs: opp5 { + opp-level = ; + }; + + rpmpd_opp_svs_plus: opp6 { + opp-level = ; + }; + + rpmpd_opp_nom: opp7 { + opp-level = ; + }; + + rpmpd_opp_nom_plus: opp8 { + opp-level = ; + }; + + rpmpd_opp_turbo: opp9 { + opp-level = ; + }; + }; + }; + }; + }; + }; + + reserved-memory { + ranges; + #address-cells = <2>; + #size-cells = <2>; + + qseecom_mem: qseecom@85b00000 { + reg = <0x0 0x85b00000 0x0 0x800000>; + no-map; + }; + + smem@86300000 { + compatible = "qcom,smem"; + reg = <0x0 0x86300000 0x0 0x100000>; + no-map; + + hwlocks = <&tcsr_mutex 3>; + qcom,rpm-msg-ram = <&rpm_msg_ram>; + }; + + reserved@86400000 { + reg = <0x0 0x86400000 0x0 0x400000>; + no-map; + }; + + rmtfs@92100000 { + compatible = "qcom,rmtfs-mem"; + reg = <0x0 0x92100000 0x0 0x180000>; + no-map; + + qcom,client-id = <1>; + }; + + adsp_mem: adsp { + size = <0x0 0x1100000>; + alignment = <0x0 0x100000>; + alloc-ranges = <0x0 0x86800000 0x0 0x8000000>; + no-map; + status = "disabled"; + }; + + mba_mem: mba { + size = <0x0 0x100000>; + alignment = <0x0 0x100000>; + alloc-ranges = <0x0 0x86800000 0x0 0x8000000>; + no-map; + status = "disabled"; + }; + + venus_mem: venus { + size = <0x0 0x400000>; + alignment = <0x0 0x100000>; + alloc-ranges = <0x0 0x86800000 0x0 0x8000000>; + no-map; + status = "disabled"; + }; + + wcnss_mem: wcnss { + size = <0x0 0x700000>; + alignment = <0x0 0x100000>; + alloc-ranges = <0x0 0x86800000 0x0 0x8000000>; + no-map; + status = "disabled"; + }; + }; + + smp2p-adsp { + compatible = "qcom,smp2p"; + qcom,smem = <443>, <429>; + + interrupts = ; + + mboxes = <&apcs 10>; + + qcom,local-pid = <0>; + qcom,remote-pid = <2>; + + adsp_smp2p_out: master-kernel { + qcom,entry-name = "master-kernel"; + + #qcom,smem-state-cells = <1>; + }; + + adsp_smp2p_in: slave-kernel { + qcom,entry-name = "slave-kernel"; + + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + smp2p-modem { + compatible = "qcom,smp2p"; + qcom,smem = <435>, <428>; + + interrupts = ; + + mboxes = <&apcs 14>; + + qcom,local-pid = <0>; + qcom,remote-pid = <1>; + + modem_smp2p_out: master-kernel { + qcom,entry-name = "master-kernel"; + + #qcom,smem-state-cells = <1>; + }; + + modem_smp2p_in: slave-kernel { + qcom,entry-name = "slave-kernel"; + + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + smp2p-wcnss { + compatible = "qcom,smp2p"; + qcom,smem = <451>, <431>; + + interrupts = ; + + mboxes = <&apcs 18>; + + qcom,local-pid = <0>; + qcom,remote-pid = <4>; + + wcnss_smp2p_out: master-kernel { + qcom,entry-name = "master-kernel"; + + #qcom,smem-state-cells = <1>; + }; + + wcnss_smp2p_in: slave-kernel { + qcom,entry-name = "slave-kernel"; + + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + smsm { + compatible = "qcom,smsm"; + + #address-cells = <1>; + #size-cells = <0>; + + mboxes = <0>, <&apcs 13>, <0>, <&apcs 19>; + + apps_smsm: apps@0 { + reg = <0>; + + #qcom,smem-state-cells = <1>; + }; + + hexagon_smsm: hexagon@1 { + reg = <1>; + interrupts = ; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + wcnss_smsm: wcnss@6 { + reg = <6>; + interrupts = ; + + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + soc: soc@0 { + compatible = "simple-bus"; + ranges = <0 0 0 0xffffffff>; + #address-cells = <1>; + #size-cells = <1>; + + rpm_msg_ram: sram@60000 { + compatible = "qcom,rpm-msg-ram"; + reg = <0x00060000 0x8000>; + }; + + usb_hs_phy: phy@6c000 { + compatible = "qcom,usb-hs-28nm-femtophy"; + reg = <0x0006c000 0x200>; + #phy-cells = <0>; + clocks = <&xo_board>, + <&gcc GCC_USB_HS_PHY_CFG_AHB_CLK>, + <&gcc GCC_USB2A_PHY_SLEEP_CLK>; + clock-names = "ref", "ahb", "sleep"; + resets = <&gcc GCC_QUSB2_PHY_BCR>, + <&gcc GCC_USB2_HS_PHY_ONLY_BCR>; + reset-names = "phy", "por"; + status = "disabled"; + }; + + qfprom: qfprom@a4000 { + compatible = "qcom,msm8917-qfprom", "qcom,qfprom"; + reg = <0x000a4000 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + + tsens_base1: base1@1d8 { + reg = <0x1d8 1>; + bits = <0 8>; + }; + + tsens_s5_p1: s5-p1@1d9 { + reg = <0x1d9 1>; + bits = <0 6>; + }; + + tsens_s5_p2: s5-p2@1d9 { + reg = <0x1d9 2>; + bits = <6 6>; + }; + + tsens_s6_p1: s6-p1@1da { + reg = <0x1da 2>; + bits = <4 6>; + }; + + tsens_s6_p2: s6-p2@1db { + reg = <0x1db 1>; + bits = <2 6>; + }; + + tsens_s7_p1: s7-p1@1dc { + reg = <0x1dc 1>; + bits = <0 6>; + }; + + tsens_s7_p2: s7-p2@1dc { + reg = <0x1dc 2>; + bits = <6 6>; + }; + + tsens_s8_p1: s8-p1@1dd { + reg = <0x1dd 2>; + bits = <4 6>; + }; + + tsens_s8_p2: s8-p2@1de { + reg = <0x1de 1>; + bits = <2 6>; + }; + + tsens_base2: base2@1df { + reg = <0x1df 1>; + bits = <0 8>; + }; + + tsens_mode: mode@210 { + reg = <0x210 1>; + bits = <0 3>; + }; + + tsens_s0_p1: s0-p1@210 { + reg = <0x210 2>; + bits = <3 6>; + }; + + tsens_s0_p2: s0-p2@211 { + reg = <0x211 1>; + bits = <1 6>; + }; + + tsens_s1_p1: s1-p1@211 { + reg = <0x211 2>; + bits = <7 6>; + }; + + tsens_s1_p2: s1-p2@212 { + reg = <0x212 2>; + bits = <5 6>; + }; + + tsens_s2_p1: s2-p1@213 { + reg = <0x213 2>; + bits = <3 6>; + }; + + tsens_s2_p2: s2-p2@214 { + reg = <0x214 1>; + bits = <1 6>; + }; + + tsens_s3_p1: s3-p1@214 { + reg = <0x214 2>; + bits = <7 6>; + }; + + tsens_s3_p2: s3-p2@215 { + reg = <0x215 2>; + bits = <5 6>; + }; + + tsens_s4_p1: s4-p1@216 { + reg = <0x216 2>; + bits = <3 6>; + }; + + tsens_s4_p2: s4-p2@217 { + reg = <0x217 1>; + bits = <1 6>; + }; + + tsens_s9_p1: s9-p1@230{ + reg = <0x230 1>; + bits = <0 6>; + }; + + tsens_s9_p2: s9-p2@230 { + reg = <0x230 2>; + bits = <6 6>; + }; + + tsens_s10_p1: s10-p1@231 { + reg = <0x231 2>; + bits = <4 6>; + }; + + tsens_s10_p2: s10-p2@232 { + reg = <0x232 1>; + bits = <2 6>; + }; + }; + + rng@e3000 { + compatible = "qcom,prng"; + reg = <0x000e3000 0x1000>; + clocks = <&gcc GCC_PRNG_AHB_CLK>; + clock-names = "core"; + }; + + tsens: thermal-sensor@4a9000 { + compatible = "qcom,msm8937-tsens", "qcom,tsens-v1"; + reg = <0x004a9000 0x1000>, + <0x004a8000 0x1000>; + interrupts = ; + interrupt-names = "uplow"; + nvmem-cells = <&tsens_mode>, + <&tsens_base1>, <&tsens_base2>, + <&tsens_s0_p1>, <&tsens_s0_p2>, + <&tsens_s1_p1>, <&tsens_s1_p2>, + <&tsens_s2_p1>, <&tsens_s2_p2>, + <&tsens_s3_p1>, <&tsens_s3_p2>, + <&tsens_s4_p1>, <&tsens_s4_p2>, + <&tsens_s5_p1>, <&tsens_s5_p2>, + <&tsens_s6_p1>, <&tsens_s6_p2>, + <&tsens_s7_p1>, <&tsens_s7_p2>, + <&tsens_s8_p1>, <&tsens_s8_p2>, + <&tsens_s9_p1>, <&tsens_s9_p2>, + <&tsens_s10_p1>, <&tsens_s10_p2>; + nvmem-cell-names = "mode", + "base1", "base2", + "s0_p1", "s0_p2", + "s1_p1", "s1_p2", + "s2_p1", "s2_p2", + "s3_p1", "s3_p2", + "s4_p1", "s4_p2", + "s5_p1", "s5_p2", + "s6_p1", "s6_p2", + "s7_p1", "s7_p2", + "s8_p1", "s8_p2", + "s9_p1", "s9_p2", + "s10_p1", "s10_p2"; + #qcom,sensors = <11>; + #thermal-sensor-cells = <1>; + }; + + restart@4ab000 { + compatible = "qcom,pshold"; + reg = <0x004ab000 0x4>; + }; + + tlmm: pinctrl@1000000 { + compatible = "qcom,msm8917-pinctrl"; + reg = <0x01000000 0x300000>; + interrupts = ; + gpio-controller; + gpio-ranges = <&tlmm 0 0 134>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + + blsp1_i2c2_default: blsp1-i2c2-default-state { + pins = "gpio6", "gpio7"; + function = "blsp_i2c2"; + drive-strength = <2>; + bias-disable; + }; + + blsp1_i2c2_sleep: blsp1-i2c2-sleep-state { + pins = "gpio6", "gpio7"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + blsp1_i2c3_default: blsp1-i2c3-default-state { + pins = "gpio10", "gpio11"; + function = "blsp_i2c3"; + drive-strength = <2>; + bias-disable; + }; + + blsp1_i2c3_sleep: blsp1-i2c3-sleep-state { + pins = "gpio10", "gpio11"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + blsp1_i2c4_default: blsp1-i2c4-default-state { + pins = "gpio14", "gpio15"; + function = "blsp_i2c4"; + drive-strength = <2>; + bias-disable; + }; + + blsp1_i2c4_sleep: blsp1-i2c4-sleep-state { + pins = "gpio14", "gpio15"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + blsp2_i2c1_default: blsp2-i2c1-default-state { + pins = "gpio18", "gpio19"; + function = "blsp_i2c5"; + drive-strength = <2>; + bias-disable; + }; + + blsp2_i2c1_sleep: blsp2-i2c1-sleep-state { + pins = "gpio18", "gpio19"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + blsp1_spi3_default: blsp1-spi3-default-state { + cs-pins { + pins = "gpio10"; + function = "blsp_spi3"; + drive-strength = <2>; + bias-disable; + }; + + spi-pins { + pins = "gpio8", "gpio9", "gpio11"; + function = "blsp_spi3"; + drive-strength = <12>; + bias-disable; + }; + }; + + blsp1_spi3_sleep: blsp1-spi3-sleep-state { + cs-pins { + pins = "gpio10"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + spi-pins { + pins = "gpio8", "gpio9", "gpio11"; + function = "gpio"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + blsp2_spi2_default: blsp2-spi2-default-state { + cs0-pins { + pins = "gpio47"; + function = "blsp_spi6"; + drive-strength = <16>; + bias-disable; + }; + + cs1-pins { + pins = "gpio22"; + function = "blsp_spi6"; + drive-strength = <16>; + bias-disable; + }; + + spi-pins { + pins = "gpio20", "gpio21", "gpio23"; + function = "blsp_spi6"; + drive-strength = <16>; + bias-disable; + }; + }; + + blsp2_spi2_sleep: blsp2-spi2-sleep-state { + cs0-pins { + pins = "gpio47"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + cs1-pins { + pins = "gpio22"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + spi-pins { + pins = "gpio20", "gpio21", "gpio23"; + function = "gpio"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + blsp1_uart1_default: blsp1-uart1-default-state { + pins = "gpio0", "gpio1", "gpio2", "gpio3"; + function = "blsp_uart1"; + drive-strength = <2>; + bias-disable; + }; + + blsp1_uart1_sleep: blsp1-uart1-sleep-state { + pins = "gpio0", "gpio1", "gpio2", "gpio3"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + blsp1_uart2_default: blsp1-uart2-default-state { + pins = "gpio4", "gpio5"; + function = "blsp_uart2"; + drive-strength = <2>; + bias-disable; + }; + + blsp1_uart2_sleep: blsp1-uart2-sleep-state { + pins = "gpio4", "gpio5"; + function = "gpio"; + drive-strength = <2>; + bias-pull-down; + }; + + sdc1_default: sdc1-default-state { + clk-pins { + pins = "sdc1_clk"; + bias-disable; + drive-strength = <16>; + }; + + cmd-pins { + pins = "sdc1_cmd"; + bias-pull-up; + drive-strength = <10>; + }; + + data-pins { + pins = "sdc1_data"; + bias-pull-up; + drive-strength = <10>; + }; + + rclk-pins { + pins = "sdc1_rclk"; + bias-pull-down; + }; + }; + + sdc1_sleep: sdc1-sleep-state { + clk-pins { + pins = "sdc1_clk"; + bias-disable; + drive-strength = <2>; + }; + + cmd-pins { + pins = "sdc1_cmd"; + bias-pull-up; + drive-strength = <2>; + }; + + data-pins { + pins = "sdc1_data"; + bias-pull-up; + drive-strength = <2>; + }; + + rclk-pins { + pins = "sdc1_rclk"; + bias-pull-down; + }; + }; + + sdc2_default: sdc2-default-state { + clk-pins { + pins = "sdc2_clk"; + bias-disable; + drive-strength = <16>; + }; + + cmd-pins { + pins = "sdc2_cmd"; + bias-pull-up; + drive-strength = <10>; + }; + + data-pins { + pins = "sdc2_data"; + bias-pull-up; + drive-strength = <10>; + }; + }; + + sdc2_sleep: sdc2-sleep-state { + clk-pins { + pins = "sdc2_clk"; + bias-disable; + drive-strength = <2>; + }; + + cmd-pins { + pins = "sdc2_cmd"; + bias-pull-up; + drive-strength = <2>; + }; + + data-pins { + pins = "sdc2_data"; + bias-pull-up; + drive-strength = <2>; + }; + }; + + wcnss_pin_a: wcnss-active-state { + wcss-wlan-pins { + pins = "gpio79", "gpio80"; + function = "wcss_wlan"; + drive-strength = <6>; + bias-pull-up; + + }; + + wcss-wlan0-pins { + pins = "gpio78"; + function = "wcss_wlan0"; + drive-strength = <6>; + bias-pull-up; + + }; + + wcss-wlan1-pins { + pins = "gpio77"; + function = "wcss_wlan1"; + drive-strength = <6>; + bias-pull-up; + + }; + + wcss-wlan2-pins { + pins = "gpio76"; + function = "wcss_wlan2"; + drive-strength = <6>; + bias-pull-up; + + }; + }; + }; + + gcc: clock-controller@1800000 { + compatible = "qcom,gcc-msm8917"; + reg = <0x01800000 0x80000>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + clocks = <&xo_board>, + <&sleep_clk>, + <&mdss_dsi0_phy 1>, + <&mdss_dsi0_phy 0>; + clock-names = "xo", + "sleep_clk", + "dsi0pll", + "dsi0pllbyte"; + }; + + tcsr_mutex: hwlock@1905000 { + compatible = "qcom,tcsr-mutex"; + reg = <0x01905000 0x20000>; + #hwlock-cells = <1>; + }; + + tcsr: syscon@1937000 { + compatible = "qcom,tcsr-msm8917", "syscon"; + reg = <0x01937000 0x30000>; + }; + + mdss: display-subsystem@1a00000 { + compatible = "qcom,mdss"; + reg = <0x01a00000 0x1000>, + <0x01ab0000 0x1040>; + reg-names = "mdss_phys", "vbif_phys"; + ranges; + + power-domains = <&gcc MDSS_GDSC>; + + clocks = <&gcc GCC_MDSS_AHB_CLK>, + <&gcc GCC_MDSS_AXI_CLK>, + <&gcc GCC_MDSS_VSYNC_CLK>; + clock-names = "iface", + "bus", + "vsync"; + + interrupts = ; + + interrupt-controller; + #interrupt-cells = <1>; + + #address-cells = <1>; + #size-cells = <1>; + + status = "disabled"; + + mdp: display-controller@1a01000 { + compatible = "qcom,msm8917-mdp5", "qcom,mdp5"; + reg = <0x01a01000 0x89000>; + reg-names = "mdp_phys"; + + interrupt-parent = <&mdss>; + interrupts = <0>; + + power-domains = <&gcc MDSS_GDSC>; + + clocks = <&gcc GCC_MDSS_AHB_CLK>, + <&gcc GCC_MDSS_AXI_CLK>, + <&gcc GCC_MDSS_MDP_CLK>, + <&gcc GCC_MDSS_VSYNC_CLK>; + clock-names = "iface", + "bus", + "core", + "vsync"; + + iommus = <&apps_iommu 0x15>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + mdp5_intf1_out: endpoint { + remote-endpoint = <&mdss_dsi0_in>; + }; + }; + }; + }; + + mdss_dsi0: dsi@1a94000 { + compatible = "qcom,mdss-dsi-ctrl"; + reg = <0x01a94000 0x300>; + reg-names = "dsi_ctrl"; + + interrupt-parent = <&mdss>; + interrupts = <4>; + + assigned-clocks = <&gcc BYTE0_CLK_SRC>, + <&gcc PCLK0_CLK_SRC>; + assigned-clock-parents = <&mdss_dsi0_phy 0>, + <&mdss_dsi0_phy 1>; + + clocks = <&gcc GCC_MDSS_MDP_CLK>, + <&gcc GCC_MDSS_AHB_CLK>, + <&gcc GCC_MDSS_AXI_CLK>, + <&gcc GCC_MDSS_BYTE0_CLK>, + <&gcc GCC_MDSS_PCLK0_CLK>, + <&gcc GCC_MDSS_ESC0_CLK>; + clock-names = "mdp_core", + "iface", + "bus", + "byte", + "pixel", + "core"; + phys = <&mdss_dsi0_phy>; + + operating-points-v2 = <&mdss_dsi0_opp_table>; + power-domains = <&rpmpd MSM8917_VDDCX>; + + #address-cells = <1>; + #size-cells = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + mdss_dsi0_in: endpoint { + remote-endpoint = <&mdp5_intf1_out>; + }; + }; + + port@1 { + reg = <1>; + + mdss_dsi0_out: endpoint { + }; + }; + }; + + mdss_dsi0_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-125000000 { + opp-hz = /bits/ 64 <125000000>; + required-opps = <&rpmpd_opp_svs>; + }; + + opp-187500000 { + opp-hz = /bits/ 64 <187500000>; + required-opps = <&rpmpd_opp_nom>; + }; + }; + }; + + mdss_dsi0_phy: phy@1a94a00 { + compatible = "qcom,dsi-phy-28nm-8937"; + reg = <0x01a94a00 0xd4>, + <0x01a94400 0x280>, + <0x01a94b80 0x30>; + reg-names = "dsi_pll", + "dsi_phy", + "dsi_phy_regulator"; + + #clock-cells = <1>; + #phy-cells = <0>; + + clocks = <&gcc GCC_MDSS_AHB_CLK>, + <&xo_board>; + clock-names = "iface", "ref"; + }; + }; + + apps_iommu: iommu@1e20000 { + compatible = "qcom,msm8917-iommu", "qcom,msm-iommu-v1"; + ranges = <0 0x01e20000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; + #iommu-cells = <1>; + + clocks = <&gcc GCC_SMMU_CFG_CLK>, + <&gcc GCC_APSS_TCU_CLK>; + clock-names = "iface", "bus"; + + qcom,iommu-secure-id = <17>; + + /* VFE */ + iommu-ctx@14000 { + compatible = "qcom,msm-iommu-v1-ns"; + reg = <0x14000 0x1000>; + interrupts = ; + }; + + /* MDP_0 */ + iommu-ctx@15000 { + compatible = "qcom,msm-iommu-v1-ns"; + reg = <0x15000 0x1000>; + interrupts = ; + }; + + /* VENUS_NS */ + iommu-ctx@16000 { + compatible = "qcom,msm-iommu-v1-ns"; + reg = <0x16000 0x1000>; + interrupts = ; + }; + }; + + gpu_iommu: iommu@1f08000 { + compatible = "qcom,msm8917-iommu", "qcom,msm-iommu-v1"; + ranges = <0 0x01f08000 0x10000>; + + #address-cells = <1>; + #size-cells = <1>; + #iommu-cells = <1>; + + clocks = <&gcc GCC_SMMU_CFG_CLK>, + <&gcc GCC_GFX_TCU_CLK>; + clock-names = "iface", "bus"; + qcom,iommu-secure-id = <18>; + + iommu-ctx@0 { + compatible = "qcom,msm-iommu-v2-ns"; + reg = <0 0x1000>; + interrupts = ; + }; + }; + + gpu: gpu@1c00000 { + compatible = "qcom,adreno-306.32", "qcom,adreno"; + reg = <0x01c00000 0x20000>; + reg-names = "kgsl_3d0_reg_memory"; + interrupts = ; + interrupt-names = "kgsl_3d0_irq"; + clock-names = "core", + "iface", + "mem_iface", + "alt_mem_iface", + "gfx3d"; + clocks = <&gcc GCC_OXILI_GFX3D_CLK>, + <&gcc GCC_OXILI_AHB_CLK>, + <&gcc GCC_BIMC_GFX_CLK>, + <&gcc GCC_BIMC_GPU_CLK>, + <&gcc GFX3D_CLK_SRC>; + power-domains = <&gcc OXILI_GX_GDSC>; + operating-points-v2 = <&gpu_opp_table>; + #cooling-cells = <2>; + + iommus = <&gpu_iommu 0>; + + status = "disabled"; + + gpu_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-19200000 { + opp-hz = /bits/ 64 <19200000>; + }; + + opp-270000000 { + opp-hz = /bits/ 64 <270000000>; + }; + + opp-400000000 { + opp-hz = /bits/ 64 <400000000>; + }; + + opp-484800000 { + opp-hz = /bits/ 64 <484800000>; + }; + + opp-523200000 { + opp-hz = /bits/ 64 <523200000>; + }; + + opp-598000000 { + opp-hz = /bits/ 64 <598000000>; + }; + }; + }; + + spmi_bus: spmi@200f000 { + compatible = "qcom,spmi-pmic-arb"; + reg = <0x0200f000 0x001000>, + <0x02400000 0x800000>, + <0x02c00000 0x800000>, + <0x03800000 0x200000>, + <0x0200a000 0x002100>; + reg-names = "core", + "chnls", + "obsrvr", + "intr", + "cnfg"; + interrupt-names = "periph_irq"; + interrupts = ; + qcom,ee = <0>; + qcom,channel = <0>; + #address-cells = <2>; + #size-cells = <0>; + interrupt-controller; + #interrupt-cells = <4>; + }; + + bam_dmux_dma: dma-controller@4044000 { + compatible = "qcom,bam-v1.7.0"; + reg = <0x04044000 0x19000>; + interrupts = ; + #dma-cells = <1>; + qcom,ee = <0>; + + num-channels = <6>; + qcom,num-ees = <1>; + qcom,powered-remotely; + + status = "disabled"; + }; + + sdhc_1: mmc@7824900 { + compatible = "qcom,sdhci-msm-v4"; + reg = <0x07824900 0x500>, + <0x07824000 0x800>; + reg-names = "hc", "core"; + + interrupts = , + ; + interrupt-names = "hc_irq", "pwr_irq"; + clocks = <&gcc GCC_SDCC1_AHB_CLK>, + <&gcc GCC_SDCC1_APPS_CLK>, + <&xo_board>; + clock-names = "iface", "core", "xo"; + pinctrl-0 = <&sdc1_default>; + pinctrl-1 = <&sdc1_sleep>; + pinctrl-names = "default", "sleep"; + power-domains = <&rpmpd MSM8917_VDDCX>; + mmc-hs200-1_8v; + mmc-hs400-1_8v; + mmc-ddr-1_8v; + bus-width = <8>; + non-removable; + status = "disabled"; + }; + + sdhc_2: mmc@7864900 { + compatible = "qcom,sdhci-msm-v4"; + reg = <0x07864900 0x500>, + <0x07864000 0x800>; + reg-names = "hc", "core"; + + interrupts = , + ; + interrupt-names = "hc_irq", "pwr_irq"; + clocks = <&gcc GCC_SDCC2_AHB_CLK>, + <&gcc GCC_SDCC2_APPS_CLK>, + <&xo_board>; + clock-names = "iface", "core", "xo"; + pinctrl-0 = <&sdc2_default>; + pinctrl-1 = <&sdc2_sleep>; + pinctrl-names = "default", "sleep"; + power-domains = <&rpmpd MSM8917_VDDCX>; + bus-width = <4>; + status = "disabled"; + }; + + blsp1_dma: dma-controller@7884000 { + compatible = "qcom,bam-v1.7.0"; + reg = <0x07884000 0x1f000>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "bam_clk"; + qcom,controlled-remotely; + #dma-cells = <1>; + num-channels = <12>; + qcom,num-ees = <4>; + qcom,ee = <0>; + }; + + blsp2_dma: dma-controller@7ac4000 { + compatible = "qcom,bam-v1.7.0"; + reg = <0x07ac4000 0x1d000>; + interrupts = ; + clocks = <&gcc GCC_BLSP2_AHB_CLK>; + clock-names = "bam_clk"; + qcom,controlled-remotely; + #dma-cells = <1>; + num-channels = <10>; + qcom,num-ees = <4>; + qcom,ee = <0>; + }; + + blsp1_uart1: serial@78af000 { + compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; + reg = <0x078af000 0x200>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_UART1_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp1_dma 0>, <&blsp1_dma 1>; + dma-names = "tx", "rx"; + pinctrl-0 = <&blsp1_uart1_default>; + pinctrl-1 = <&blsp1_uart1_sleep>; + pinctrl-names = "default", "sleep"; + status = "disabled"; + }; + + blsp1_uart2: serial@78b0000 { + compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; + reg = <0x078b0000 0x200>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_UART2_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp1_dma 2>, <&blsp1_dma 3>; + dma-names = "tx", "rx"; + pinctrl-0 = <&blsp1_uart2_default>; + pinctrl-1 = <&blsp1_uart2_sleep>; + pinctrl-names = "default", "sleep"; + status = "disabled"; + }; + + blsp1_i2c2: i2c@78b6000 { + compatible = "qcom,i2c-qup-v2.2.1"; + reg = <0x078b6000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP2_I2C_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp1_dma 6>, <&blsp1_dma 7>; + dma-names = "tx", "rx"; + pinctrl-0 = <&blsp1_i2c2_default>; + pinctrl-1 = <&blsp1_i2c2_sleep>; + pinctrl-names = "default", "sleep"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp1_i2c3: i2c@78b7000 { + compatible = "qcom,i2c-qup-v2.2.1"; + reg = <0x078b7000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP3_I2C_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp1_dma 8>, <&blsp1_dma 9>; + dma-names = "tx", "rx"; + pinctrl-0 = <&blsp1_i2c3_default>; + pinctrl-1 = <&blsp1_i2c3_sleep>; + pinctrl-names = "default", "sleep"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp1_spi3: spi@78b7000 { + compatible = "qcom,spi-qup-v2.2.1"; + reg = <0x078b7000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP3_SPI_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp1_dma 8>, <&blsp1_dma 9>; + dma-names = "tx", "rx"; + pinctrl-0 = <&blsp1_spi3_default>; + pinctrl-1 = <&blsp1_spi3_sleep>; + pinctrl-names = "default", "sleep"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp1_i2c4: i2c@78b8000 { + compatible = "qcom,i2c-qup-v2.2.1"; + reg = <0x078b8000 0x500>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP4_I2C_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp1_dma 10>, <&blsp1_dma 11>; + dma-names = "tx", "rx"; + pinctrl-0 = <&blsp1_i2c4_default>; + pinctrl-1 = <&blsp1_i2c4_sleep>; + pinctrl-names = "default", "sleep"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp2_i2c1: i2c@7af5000 { + compatible = "qcom,i2c-qup-v2.2.1"; + reg = <0x07af5000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP2_QUP1_I2C_APPS_CLK>, + <&gcc GCC_BLSP2_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp2_dma 4>, <&blsp2_dma 5>; + dma-names = "tx", "rx"; + pinctrl-0 = <&blsp2_i2c1_default>; + pinctrl-1 = <&blsp2_i2c1_sleep>; + pinctrl-names = "default", "sleep"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp2_spi2: spi@7af6000 { + compatible = "qcom,spi-qup-v2.2.1"; + reg = <0x07af6000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP2_QUP2_SPI_APPS_CLK>, + <&gcc GCC_BLSP2_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp2_dma 6>, <&blsp2_dma 7>; + dma-names = "tx", "rx"; + pinctrl-0 = <&blsp2_spi2_default>; + pinctrl-1 = <&blsp2_spi2_sleep>; + pinctrl-names = "default", "sleep"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + usb: usb@78db000 { + compatible = "qcom,ci-hdrc"; + reg = <0x078db000 0x200>, + <0x078db200 0x200>; + interrupts = , + ; + clocks = <&gcc GCC_USB_HS_AHB_CLK>, + <&gcc GCC_USB_HS_SYSTEM_CLK>; + clock-names = "iface", "core"; + assigned-clocks = <&gcc GCC_USB_HS_SYSTEM_CLK>; + assigned-clock-rates = <80000000>; + resets = <&gcc GCC_USB_HS_BCR>; + reset-names = "core"; + phy_type = "ulpi"; + dr_mode = "otg"; + hnp-disable; + srp-disable; + adp-disable; + ahb-burst-config = <0>; + phy-names = "usb-phy"; + phys = <&usb_hs_phy>; + status = "disabled"; + #reset-cells = <1>; + }; + + wcnss: remoteproc@a204000 { + compatible = "qcom,pronto-v3-pil", "qcom,pronto"; + reg = <0x0a204000 0x2000>, + <0x0a202000 0x1000>, + <0x0a21b000 0x3000>; + reg-names = "ccu", "dxe", "pmu"; + + memory-region = <&wcnss_mem>; + + interrupts-extended = <&intc GIC_SPI 149 IRQ_TYPE_EDGE_RISING>, + <&wcnss_smp2p_in 0 IRQ_TYPE_EDGE_RISING>, + <&wcnss_smp2p_in 1 IRQ_TYPE_EDGE_RISING>, + <&wcnss_smp2p_in 2 IRQ_TYPE_EDGE_RISING>, + <&wcnss_smp2p_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", "fatal", "ready", "handover", "stop-ack"; + + power-domains = <&rpmpd MSM8917_VDDCX>, + <&rpmpd MSM8917_VDDMX>; + power-domain-names = "cx", "mx"; + + qcom,smem-states = <&wcnss_smp2p_out 0>; + qcom,smem-state-names = "stop"; + + pinctrl-0 = <&wcnss_pin_a>; + pinctrl-names = "default"; + + status = "disabled"; + + wcnss_iris: iris { + clocks = <&rpmcc RPM_SMD_RF_CLK2>; + clock-names = "xo"; + }; + + smd-edge { + interrupts = ; + + mboxes = <&apcs 17>; + qcom,smd-edge = <6>; + qcom,remote-pid = <4>; + + label = "pronto"; + + wcnss_ctrl: wcnss { + compatible = "qcom,wcnss"; + qcom,smd-channels = "WCNSS_CTRL"; + + qcom,mmio = <&wcnss>; + + wcnss_bt: bluetooth { + compatible = "qcom,wcnss-bt"; + }; + + wcnss_wifi: wifi { + compatible = "qcom,wcnss-wlan"; + + interrupts = , + ; + interrupt-names = "tx", "rx"; + + qcom,smem-states = <&apps_smsm 10>, <&apps_smsm 9>; + qcom,smem-state-names = "tx-enable", + "tx-rings-empty"; + }; + }; + }; + }; + + intc: interrupt-controller@b000000 { + compatible = "qcom,msm-qgic2"; + reg = <0x0b000000 0x1000>, + <0x0b002000 0x1000>; + interrupt-controller; + #interrupt-cells = <3>; + }; + + apcs: mailbox@b011000 { + compatible = "qcom,msm8939-apcs-kpss-global", "syscon"; + reg = <0x0b011000 0x1000>; + #mbox-cells = <1>; + clocks = <&a53pll>, <&gcc GPLL0_EARLY>, <&rpmcc RPM_SMD_XO_CLK_SRC>; + clock-names = "pll", "aux", "ref"; + #clock-cells = <0>; + }; + + a53pll: clock@b016000 { + compatible = "qcom,msm8939-a53pll"; + reg = <0x0b016000 0x40>; + clocks = <&xo_board>; + clock-names = "xo"; + #clock-cells = <0>; + operating-points-v2 = <&pll_opp_table>; + + pll_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-960000000 { + opp-hz = /bits/ 64 <960000000>; + }; + + opp-1094400000 { + opp-hz = /bits/ 64 <1094400000>; + }; + + opp-1248000000 { + opp-hz = /bits/ 64 <1248000000>; + }; + + opp-1401600000 { + opp-hz = /bits/ 64 <1401600000>; + }; + }; + }; + + watchdog@b017000 { + compatible = "qcom,apss-wdt-qcs404", "qcom,kpss-wdt"; + reg = <0x0b017000 0x1000>; + clocks = <&sleep_clk>; + }; + + timer@b120000 { + compatible = "arm,armv7-timer-mem"; + reg = <0x0b120000 0x1000>; + ranges; + #address-cells = <1>; + #size-cells = <1>; + + frame@b121000 { + reg = <0x0b121000 0x1000>, + <0x0b122000 0x1000>; + frame-number = <0>; + interrupts = , + ; + }; + + frame@b123000 { + reg = <0x0b123000 0x1000>; + frame-number = <1>; + interrupts = ; + status = "disabled"; + }; + + frame@b124000 { + reg = <0x0b124000 0x1000>; + frame-number = <2>; + interrupts = ; + status = "disabled"; + }; + + frame@b125000 { + reg = <0x0b125000 0x1000>; + frame-number = <3>; + interrupts = ; + status = "disabled"; + }; + + frame@b126000 { + reg = <0x0b126000 0x1000>; + frame-number = <4>; + interrupts = ; + status = "disabled"; + }; + + frame@b127000 { + reg = <0x0b127000 0x1000>; + frame-number = <5>; + interrupts = ; + status = "disabled"; + }; + + frame@b128000 { + reg = <0x0b128000 0x1000>; + frame-number = <6>; + interrupts = ; + status = "disabled"; + }; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; + + thermal_zones: thermal-zones { + aoss-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 0>; + + trips { + aoss_alert0: trip-point0 { + temperature = <85000>; + hysteresis = <2000>; + type = "hot"; + }; + }; + }; + + camera-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 3>; + + trips { + camera_alert0: trip-point0 { + temperature = <85000>; + hysteresis = <2000>; + type = "hot"; + }; + }; + }; + + cpuss1-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 4>; + + cooling-maps { + map0 { + trip = <&cpuss1_alert0>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + cpuss1_alert0: trip-point0 { + temperature = <75000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpuss1_alert1: trip-point1 { + temperature = <85000>; + hysteresis = <2000>; + type = "hot"; + }; + + cpuss1_crit: cpuss1-crit { + temperature = <100000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + + cpu0-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 5>; + + cooling-maps { + map0 { + trip = <&cpu0_alert1>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + cpu0_alert0: trip-point0 { + temperature = <75000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu0_alert1: trip-point1 { + temperature = <85000>; + hysteresis = <2000>; + type = "hot"; + }; + + cpu0_crit: cpu-crit { + temperature = <100000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + + cpu1-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 6>; + + cooling-maps { + map0 { + trip = <&cpu1_alert1>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + cpu1_alert0: trip-point0 { + temperature = <75000>; + hysteresis = <2000>; + type = "hot"; + }; + + cpu1_alert1: trip-point1 { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu1_crit: cpu-crit { + temperature = <100000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + + cpu2-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 7>; + + cooling-maps { + map0 { + trip = <&cpu2_alert1>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + cpu2_alert0: trip-point0 { + temperature = <75000>; + hysteresis = <2000>; + type = "hot"; + }; + + cpu2_alert1: trip-point1 { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu2_crit: cpu-crit { + temperature = <100000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + + cpu3-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 8>; + + cooling-maps { + map0 { + trip = <&cpu3_alert1>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + cpu3_alert0: trip-point0 { + temperature = <75000>; + hysteresis = <2000>; + type = "hot"; + }; + + cpu3_alert1: trip-point1 { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu3_crit: cpu-crit { + temperature = <100000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + + gpu-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 9>; + + cooling-maps { + map0 { + trip = <&gpu_alert>; + cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + gpu_alert: trip-point0 { + temperature = <70000>; + hysteresis = <2000>; + type = "passive"; + }; + + gpu_crit: gpu-crit { + temperature = <90000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + + }; + + mdm-core-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 1>; + + trips { + mdm_core_alert0: trip-point0 { + temperature = <85000>; + hysteresis = <2000>; + type = "hot"; + }; + }; + }; + + q6-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens 2>; + + trips { + q6_alert0: trip-point0 { + temperature = <85000>; + hysteresis = <2000>; + type = "hot"; + }; + }; + }; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/msm8939.dtsi b/arch/arm64/boot/dts/qcom/msm8939.dtsi index 7a6f1eeaa3fc..7cd5660de1b3 100644 --- a/arch/arm64/boot/dts/qcom/msm8939.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8939.dtsi @@ -34,7 +34,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <32768>; + clock-frequency = <32764>; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts b/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts index 29e79ae0849d..1aca11daf83c 100644 --- a/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts +++ b/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts @@ -2,12 +2,13 @@ /* * Copyright (c) 2015, Huawei Inc. All rights reserved. * Copyright (c) 2016, The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2023, Petr Vorel + * Copyright (c) 2021-2024, Petr Vorel */ /dts-v1/; #include "msm8994.dtsi" +#include "pm8994.dtsi" / { model = "Huawei Nexus 6P"; @@ -46,6 +47,24 @@ no-map; }; }; + + gpio-keys { + compatible = "gpio-keys"; + autorepeat; + + button-vol-up { + label = "volume up"; + gpios = <&pm8994_gpios 3 GPIO_ACTIVE_LOW>; + linux,code = ; + wakeup-source; + debounce-interval = <15>; + }; + }; +}; + +&pm8994_resin { + linux,code = ; + status = "okay"; }; &blsp1_uart2 { diff --git a/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi b/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi index 10cd244dea4f..4c983b10dd92 100644 --- a/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi @@ -387,11 +387,6 @@ interrupts = <&tlmm 96 IRQ_TYPE_EDGE_FALLING>; - button_num = <8>; - touchpad_num = <0>; - wheel_num = <0>; - slider_num = <0>; - vcc-supply = <&vreg_l18a_2p85>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8994.dtsi b/arch/arm64/boot/dts/qcom/msm8994.dtsi index 1acb0f159511..b5cbdd620bb9 100644 --- a/arch/arm64/boot/dts/qcom/msm8994.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8994.dtsi @@ -34,7 +34,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <32768>; + clock-frequency = <32764>; clock-output-names = "sleep_clk"; }; }; @@ -437,6 +437,15 @@ #size-cells = <1>; ranges; + interrupts = , + , + , + ; + interrupt-names = "pwr_event", + "qusb2_phy", + "hs_phy_irq", + "ss_phy_irq"; + clocks = <&gcc GCC_USB30_MASTER_CLK>, <&gcc GCC_SYS_NOC_USB3_AXI_CLK>, <&gcc GCC_USB30_SLEEP_CLK>, diff --git a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts index f8e9d90afab0..dbad8f57f2fa 100644 --- a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts +++ b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts @@ -64,7 +64,7 @@ }; led@1 { - reg = <0>; + reg = <1>; chan-name = "button-backlight1"; led-cur = /bits/ 8 <0x32>; max-cur = /bits/ 8 <0xc8>; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index b379623c1b8a..4719e1fc70d2 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -3065,9 +3065,14 @@ #size-cells = <1>; ranges; - interrupts = , + interrupts = , + , + , ; - interrupt-names = "hs_phy_irq", "ss_phy_irq"; + interrupt-names = "pwr_event", + "qusb2_phy", + "hs_phy_irq", + "ss_phy_irq"; clocks = <&gcc GCC_SYS_NOC_USB3_AXI_CLK>, <&gcc GCC_USB30_MASTER_CLK>, diff --git a/arch/arm64/boot/dts/qcom/pm660l.dtsi b/arch/arm64/boot/dts/qcom/pm660l.dtsi index 0094e0ef058b..3f8b9eafe164 100644 --- a/arch/arm64/boot/dts/qcom/pm660l.dtsi +++ b/arch/arm64/boot/dts/qcom/pm660l.dtsi @@ -70,6 +70,12 @@ status = "disabled"; }; + pm660l_flash: led-controller@d300 { + compatible = "qcom,pm660l-flash-led", "qcom,spmi-flash-led"; + reg = <0xd300>; + status = "disabled"; + }; + pm660l_wled: leds@d800 { compatible = "qcom,pm660l-wled"; reg = <0xd800>, <0xd900>; diff --git a/arch/arm64/boot/dts/qcom/pm8150.dtsi b/arch/arm64/boot/dts/qcom/pm8150.dtsi index a74a7ff660d2..d2568686a098 100644 --- a/arch/arm64/boot/dts/qcom/pm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/pm8150.dtsi @@ -49,8 +49,6 @@ pon: pon@800 { compatible = "qcom,pm8998-pon"; reg = <0x0800>; - mode-bootloader = <0x2>; - mode-recovery = <0x1>; pon_pwrkey: pwrkey { compatible = "qcom,pm8941-pwrkey"; diff --git a/arch/arm64/boot/dts/qcom/pm8937.dtsi b/arch/arm64/boot/dts/qcom/pm8937.dtsi new file mode 100644 index 000000000000..42b3575b36ff --- /dev/null +++ b/arch/arm64/boot/dts/qcom/pm8937.dtsi @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2023, Dang Huynh + */ + +#include +#include +#include + +/ { + thermal-zones { + pm8937-thermal { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&pm8937_temp>; + + trips { + trip0 { + temperature = <105000>; + hysteresis = <0>; + type = "passive"; + }; + + trip1 { + temperature = <125000>; + hysteresis = <0>; + type = "hot"; + }; + + trip2 { + temperature = <145000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + }; +}; + +&spmi_bus { + pmic@0 { + compatible = "qcom,pm8937", "qcom,spmi-pmic"; + reg = <0x0 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pon@800 { + compatible = "qcom,pm8916-pon"; + reg = <0x800>; + mode-bootloader = <0x2>; + mode-recovery = <0x1>; + + pm8937_pwrkey: pwrkey { + compatible = "qcom,pm8941-pwrkey"; + interrupts = <0 0x8 0 IRQ_TYPE_EDGE_BOTH>; + debounce = <15625>; + bias-pull-up; + linux,code = ; + }; + + pm8937_resin: resin { + compatible = "qcom,pm8941-resin"; + interrupts = <0 0x8 1 IRQ_TYPE_EDGE_BOTH>; + debounce = <15625>; + bias-pull-up; + status = "disabled"; + }; + }; + + pm8937_gpios: gpio@c000 { + compatible = "qcom,pm8937-gpio", "qcom,spmi-gpio"; + reg = <0xc000>; + gpio-controller; + gpio-ranges = <&pm8937_gpios 0 0 8>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + pm8937_mpps: mpps@a000 { + compatible = "qcom,pm8937-mpp", "qcom,spmi-mpp"; + reg = <0xa000>; + gpio-controller; + gpio-ranges = <&pm8937_mpps 0 0 4>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + pm8937_temp: temp-alarm@2400 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0x2400>; + interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>; + io-channels = <&pm8937_vadc VADC_DIE_TEMP>; + io-channel-names = "thermal"; + #thermal-sensor-cells = <0>; + }; + + pm8937_vadc: adc@3100 { + compatible = "qcom,spmi-vadc"; + reg = <0x3100>; + interrupts = <0 0x31 0 IRQ_TYPE_EDGE_RISING>; + #address-cells = <1>; + #size-cells = <0>; + #io-channel-cells = <1>; + + channel@8 { + reg = ; + }; + + channel@9 { + reg = ; + }; + + channel@a { + reg = ; + }; + + channel@c { + reg = ; + }; + + channel@e { + reg = ; + }; + + channel@f { + reg = ; + }; + }; + + rtc@6000 { + compatible = "qcom,pm8941-rtc"; + reg = <0x6000>, <0x6100>; + reg-names = "rtc", "alarm"; + interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; + }; + }; + + pmic@1 { + compatible = "qcom,pm8937", "qcom,spmi-pmic"; + reg = <0x1 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pm8937_spmi_regulators: regulators { + compatible = "qcom,pm8937-regulators"; + }; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/pmd8028.dtsi b/arch/arm64/boot/dts/qcom/pmd8028.dtsi new file mode 100644 index 000000000000..a00913e28a4c --- /dev/null +++ b/arch/arm64/boot/dts/qcom/pmd8028.dtsi @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include + +/ { + thermal-zones { + pmd8028-thermal { + polling-delay-passive = <100>; + thermal-sensors = <&pmd8028_temp_alarm>; + + trips { + pmd8028_trip0: trip0 { + temperature = <95000>; + hysteresis = <0>; + type = "passive"; + }; + + pmd8028_trip1: trip1 { + temperature = <115000>; + hysteresis = <0>; + type = "hot"; + }; + + pmd8028_trip2: trip2 { + temperature = <145000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + }; +}; + +&spmi_bus { + pmd8028: pmic@4 { + compatible = "qcom,pmd8028", "qcom,spmi-pmic"; + reg = <0x4 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pmd8028_temp_alarm: temp-alarm@a00 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0xa00>; + interrupts = <0x4 0xa 0x0 IRQ_TYPE_EDGE_BOTH>; + #thermal-sensor-cells = <0>; + }; + + pmd8028_gpios: gpio@8800 { + compatible = "qcom,pmd8028-gpio", "qcom,spmi-gpio"; + reg = <0x8800>; + gpio-controller; + gpio-ranges = <&pmd8028_gpios 0 0 4>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/pmi8950.dtsi b/arch/arm64/boot/dts/qcom/pmi8950.dtsi index 4aff437263a2..3d3b1cd97cc3 100644 --- a/arch/arm64/boot/dts/qcom/pmi8950.dtsi +++ b/arch/arm64/boot/dts/qcom/pmi8950.dtsi @@ -84,6 +84,23 @@ #address-cells = <1>; #size-cells = <0>; + labibb { + compatible = "qcom,pmi8950-lab-ibb", + "qcom,pmi8998-lab-ibb"; + + ibb: ibb { + interrupts = <0x3 0xdc 0x2 IRQ_TYPE_EDGE_RISING>, + <0x3 0xdc 0x0 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sc-err", "ocp"; + }; + + lab: lab { + interrupts = <0x3 0xde 0x1 IRQ_TYPE_EDGE_RISING>, + <0x3 0xde 0x0 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sc-err", "ocp"; + }; + }; + pmi8950_pwm: pwm { compatible = "qcom,pmi8950-pwm"; #pwm-cells = <2>; diff --git a/arch/arm64/boot/dts/qcom/pmih0108.dtsi b/arch/arm64/boot/dts/qcom/pmih0108.dtsi new file mode 100644 index 000000000000..1c875995d881 --- /dev/null +++ b/arch/arm64/boot/dts/qcom/pmih0108.dtsi @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include + +/ { + thermal-zones { + pmih0108-thermal { + polling-delay-passive = <100>; + thermal-sensors = <&pmih0108_temp_alarm>; + + trips { + trip0 { + temperature = <95000>; + hysteresis = <0>; + type = "passive"; + }; + + trip1 { + temperature = <115000>; + hysteresis = <0>; + type = "hot"; + }; + + trip2 { + temperature = <145000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + }; +}; + +&spmi_bus { + pmih0108: pmic@7 { + compatible = "qcom,pmih0108", "qcom,spmi-pmic"; + reg = <0x7 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pmih0108_temp_alarm: temp-alarm@a00 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0xa00>; + interrupts = <0x7 0xa 0x0 IRQ_TYPE_EDGE_BOTH>; + #thermal-sensor-cells = <0>; + }; + + pmih0108_gpios: gpio@8800 { + compatible = "qcom,pmih0108-gpio", "qcom,spmi-gpio"; + reg = <0x8800>; + gpio-controller; + gpio-ranges = <&pmih0108_gpios 0 0 18>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + pmih0108_eusb2_repeater: phy@fd00 { + compatible = "qcom,pm8550b-eusb2-repeater"; + reg = <0xfd00>; + #phy-cells = <0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/pmk8350.dtsi b/arch/arm64/boot/dts/qcom/pmk8350.dtsi index f0ed15458dd7..565752af2204 100644 --- a/arch/arm64/boot/dts/qcom/pmk8350.dtsi +++ b/arch/arm64/boot/dts/qcom/pmk8350.dtsi @@ -76,6 +76,14 @@ status = "disabled"; }; + pmk8350_sdam_1: nvram@7000 { + compatible = "qcom,spmi-sdam"; + reg = <0x7000>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x7000 0x100>; + }; + pmk8350_sdam_2: nvram@7100 { compatible = "qcom,spmi-sdam"; reg = <0x7100>; @@ -89,6 +97,70 @@ }; }; + pmk8350_sdam_5: nvram@7400 { + compatible = "qcom,spmi-sdam"; + reg = <0x7400>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x7400 0x100>; + }; + + pmk8350_sdam_13: nvram@7c00 { + compatible = "qcom,spmi-sdam"; + reg = <0x7c00>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x7c00 0x100>; + }; + + pmk8350_sdam_14: nvram@7d00 { + compatible = "qcom,spmi-sdam"; + reg = <0x7d00>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x7d00 0x100>; + }; + + pmk8350_sdam_21: nvram@8400 { + compatible = "qcom,spmi-sdam"; + reg = <0x8400>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x8400 0x100>; + }; + + pmk8350_sdam_22: nvram@8500 { + compatible = "qcom,spmi-sdam"; + reg = <0x8500>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x8500 0x100>; + }; + + pmk8350_sdam_23: nvram@8600 { + compatible = "qcom,spmi-sdam"; + reg = <0x8600>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x8600 0x100>; + }; + + pmk8350_sdam_41: nvram@9800 { + compatible = "qcom,spmi-sdam"; + reg = <0x9800>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x9800 0x100>; + }; + + pmk8350_sdam_46: nvram@9d00 { + compatible = "qcom,spmi-sdam"; + reg = <0x9d00>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x9d00 0x100>; + }; + pmk8350_gpios: gpio@b000 { compatible = "qcom,pmk8350-gpio", "qcom,spmi-gpio"; reg = <0xb000>; diff --git a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts index fdc62f1b1c5a..769c66cb5d19 100644 --- a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts +++ b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts @@ -108,6 +108,36 @@ }; }; + vreg_afvdd_2p8: regulator-afvdd-2p8 { + compatible = "regulator-fixed"; + regulator-name = "AFVDD_2P8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + gpio = <&tlmm 68 GPIO_ACTIVE_HIGH>; + enable-active-high; + vin-supply = <&vreg_bob>; + }; + + vreg_ois_avdd0_1p8: regulator-ois-avdd0-1p8 { + compatible = "regulator-fixed"; + regulator-name = "OIS_AVDD0_1P8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + gpio = <&tlmm 157 GPIO_ACTIVE_HIGH>; + enable-active-high; + vin-supply = <&vreg_bob>; + }; + + vreg_ois_dvdd_1p1: regulator-ois-dvdd-1p1 { + compatible = "regulator-fixed"; + regulator-name = "OIS_DVDD_1P1"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + gpio = <&tlmm 97 GPIO_ACTIVE_HIGH>; + enable-active-high; + vin-supply = <&vreg_s8b>; + }; + reserved-memory { cont_splash_mem: cont-splash@e1000000 { reg = <0x0 0xe1000000 0x0 0x2300000>; @@ -134,36 +164,6 @@ }; }; - ois_avdd0_1p8: regulator-ois-avdd0-1p8 { - compatible = "regulator-fixed"; - regulator-name = "OIS_AVDD0_1P8"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - gpio = <&tlmm 157 GPIO_ACTIVE_HIGH>; - enable-active-high; - vin-supply = <&vreg_bob>; - }; - - ois_dvdd_1p1: regulator-ois-dvdd-1p1 { - compatible = "regulator-fixed"; - regulator-name = "OIS_DVDD_1P1"; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1100000>; - gpio = <&tlmm 97 GPIO_ACTIVE_HIGH>; - enable-active-high; - vin-supply = <&vreg_s8b>; - }; - - afvdd_2p8: regulator-afvdd-2p8 { - compatible = "regulator-fixed"; - regulator-name = "AFVDD_2P8"; - regulator-min-microvolt = <2800000>; - regulator-max-microvolt = <2800000>; - gpio = <&tlmm 68 GPIO_ACTIVE_HIGH>; - enable-active-high; - vin-supply = <&vreg_bob>; - }; - thermal-zones { camera-thermal { polling-delay-passive = <0>; @@ -556,6 +556,47 @@ }; }; +&cci0 { + status = "okay"; +}; + +&cci0_i2c0 { + /* IMX800 @ 1a */ + + eeprom@50 { + compatible = "puya,p24c256c", "atmel,24c256"; + reg = <0x50>; + vcc-supply = <&vreg_l6p>; + read-only; + }; +}; + +&cci0_i2c1 { + /* IMX858 @ 29 */ + + eeprom@54 { + compatible = "giantec,gt24p128f", "atmel,24c128"; + reg = <0x54>; + vcc-supply = <&vreg_l6p>; + read-only; + }; +}; + +&cci1 { + status = "okay"; +}; + +&cci1_i2c1 { + /* S5KJN1SQ03 @ 10 */ + + eeprom@51 { + compatible = "giantec,gt24p128f", "atmel,24c128"; + reg = <0x51>; + vcc-supply = <&vreg_l6p>; + read-only; + }; +}; + &dispcc { /* Disable for now so simple-framebuffer continues working */ status = "disabled"; diff --git a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts index c5fb153614e1..9209efcc49b5 100644 --- a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts +++ b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts @@ -258,6 +258,8 @@ regulator-name = "vreg_l6b_1p2"; regulator-min-microvolt = <1140000>; regulator-max-microvolt = <1260000>; + regulator-allow-set-load; + regulator-allowed-modes = ; regulator-initial-mode = ; }; @@ -265,6 +267,8 @@ regulator-name = "vreg_l7b_2p952"; regulator-min-microvolt = <2400000>; regulator-max-microvolt = <3544000>; + regulator-allow-set-load; + regulator-allowed-modes = ; regulator-initial-mode = ; }; @@ -279,6 +283,8 @@ regulator-name = "vreg_l9b_1p2"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1304000>; + regulator-allow-set-load; + regulator-allowed-modes = ; regulator-initial-mode = ; }; @@ -467,6 +473,8 @@ regulator-name = "vreg_l10c_0p88"; regulator-min-microvolt = <720000>; regulator-max-microvolt = <1050000>; + regulator-allow-set-load; + regulator-allowed-modes = ; regulator-initial-mode = ; }; diff --git a/arch/arm64/boot/dts/qcom/qcm6490-shift-otter.dts b/arch/arm64/boot/dts/qcom/qcm6490-shift-otter.dts index 4667e47a74bc..75930f957696 100644 --- a/arch/arm64/boot/dts/qcom/qcm6490-shift-otter.dts +++ b/arch/arm64/boot/dts/qcom/qcm6490-shift-otter.dts @@ -942,8 +942,6 @@ qcom,squelch-detector-bp = <(-2090)>; - orientation-switch; - status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/qcs404.dtsi b/arch/arm64/boot/dts/qcom/qcs404.dtsi index 215ba146207a..5a9df6b12305 100644 --- a/arch/arm64/boot/dts/qcom/qcs404.dtsi +++ b/arch/arm64/boot/dts/qcom/qcs404.dtsi @@ -28,7 +28,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <32768>; + clock-frequency = <32764>; }; }; @@ -694,6 +694,8 @@ snps,has-lpm-erratum; snps,hird-threshold = /bits/ 8 <0x10>; snps,usb3_lpm_capable; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; dr_mode = "otg"; }; }; @@ -731,6 +733,8 @@ snps,has-lpm-erratum; snps,hird-threshold = /bits/ 8 <0x10>; snps,usb3_lpm_capable; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; dr_mode = "peripheral"; }; }; diff --git a/arch/arm64/boot/dts/qcom/qcs615-ride.dts b/arch/arm64/boot/dts/qcom/qcs615-ride.dts new file mode 100644 index 000000000000..2b5aa3c66867 --- /dev/null +++ b/arch/arm64/boot/dts/qcom/qcs615-ride.dts @@ -0,0 +1,343 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ +/dts-v1/; + +#include +#include +#include +#include "qcs615.dtsi" +#include "pm8150.dtsi" +/ { + model = "Qualcomm Technologies, Inc. QCS615 Ride"; + compatible = "qcom,qcs615-ride", "qcom,qcs615"; + chassis-type = "embedded"; + + aliases { + mmc0 = &sdhc_1; + mmc1 = &sdhc_2; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + clocks { + sleep_clk: sleep-clk { + compatible = "fixed-clock"; + clock-frequency = <32000>; + #clock-cells = <0>; + }; + + xo_board_clk: xo-board-clk { + compatible = "fixed-clock"; + clock-frequency = <38400000>; + #clock-cells = <0>; + }; + }; + + regulator-usb2-vbus { + compatible = "regulator-fixed"; + regulator-name = "USB2_VBUS"; + gpio = <&pm8150_gpios 10 GPIO_ACTIVE_HIGH>; + pinctrl-0 = <&usb2_en>; + pinctrl-names = "default"; + enable-active-high; + regulator-always-on; + }; +}; + +&apps_rsc { + regulators-0 { + compatible = "qcom,pm8150-rpmh-regulators"; + qcom,pmic-id = "a"; + + vreg_s3a: smps3 { + regulator-name = "vreg_s3a"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <650000>; + regulator-initial-mode = ; + }; + + vreg_s4a: smps4 { + regulator-name = "vreg_s4a"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1829000>; + regulator-initial-mode = ; + }; + + vreg_s5a: smps5 { + regulator-name = "vreg_s5a"; + regulator-min-microvolt = <1896000>; + regulator-max-microvolt = <2040000>; + regulator-initial-mode = ; + }; + + vreg_s6a: smps6 { + regulator-name = "vreg_s6a"; + regulator-min-microvolt = <1304000>; + regulator-max-microvolt = <1404000>; + regulator-initial-mode = ; + }; + + vreg_l1a: ldo1 { + regulator-name = "vreg_l1a"; + regulator-min-microvolt = <488000>; + regulator-max-microvolt = <852000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2a: ldo2 { + regulator-name = "vreg_l2a"; + regulator-min-microvolt = <1650000>; + regulator-max-microvolt = <3100000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3a: ldo3 { + regulator-name = "vreg_l3a"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1248000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l5a: ldo5 { + regulator-name = "vreg_l5a"; + regulator-min-microvolt = <875000>; + regulator-max-microvolt = <975000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l7a: ldo7 { + regulator-name = "vreg_l7a"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1900000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l8a: ldo8 { + regulator-name = "vreg_l8a"; + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1350000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l10a: ldo10 { + regulator-name = "vreg_l10a"; + regulator-min-microvolt = <2950000>; + regulator-max-microvolt = <3312000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l11a: ldo11 { + regulator-name = "vreg_l11a"; + regulator-min-microvolt = <1232000>; + regulator-max-microvolt = <1260000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l12a: ldo12 { + regulator-name = "vreg_l12a"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1890000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l13a: ldo13 { + regulator-name = "vreg_l13a"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3230000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l15a: ldo15 { + regulator-name = "vreg_l15a"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1904000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l16a: ldo16 { + regulator-name = "vreg_l16a"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3312000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l17a: ldo17 { + regulator-name = "vreg_l17a"; + regulator-min-microvolt = <2950000>; + regulator-max-microvolt = <3312000>; + regulator-initial-mode = ; + }; + }; +}; + +&gcc { + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>; +}; + +&pm8150_gpios { + usb2_en: usb2-en-state { + pins = "gpio10"; + function = "normal"; + output-enable; + power-source = <0>; + }; +}; + +&pon_pwrkey { + status = "okay"; +}; + +&pon_resin { + linux,code = ; + + status = "okay"; +}; + +&qupv3_id_0 { + status = "okay"; +}; + +&rpmhcc { + clocks = <&xo_board_clk>; +}; + +&sdhc_1 { + pinctrl-0 = <&sdc1_state_on>; + pinctrl-1 = <&sdc1_state_off>; + pinctrl-names = "default", "sleep"; + + bus-width = <8>; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + vmmc-supply = <&vreg_l17a>; + vqmmc-supply = <&vreg_s4a>; + + non-removable; + no-sd; + no-sdio; + + status = "okay"; +}; + +&sdhc_2 { + pinctrl-0 = <&sdc2_state_on>; + pinctrl-1 = <&sdc2_state_off>; + pinctrl-names = "default", "sleep"; + + bus-width = <4>; + cd-gpios = <&tlmm 99 GPIO_ACTIVE_LOW>; + + vmmc-supply = <&vreg_l10a>; + vqmmc-supply = <&vreg_s4a>; + + status = "okay"; +}; + +&uart0 { + status = "okay"; +}; + +&usb_1_hsphy { + vdd-supply = <&vreg_l5a>; + vdda-pll-supply = <&vreg_l12a>; + vdda-phy-dpdm-supply = <&vreg_l13a>; + + status = "okay"; +}; + +&usb_qmpphy { + vdda-phy-supply = <&vreg_l5a>; + vdda-pll-supply = <&vreg_l12a>; + + status = "okay"; +}; + +&usb_1 { + status = "okay"; +}; + +&usb_1_dwc3 { + dr_mode = "peripheral"; +}; + +&usb_hsphy_2 { + vdd-supply = <&vreg_l5a>; + vdda-pll-supply = <&vreg_l12a>; + vdda-phy-dpdm-supply = <&vreg_l13a>; + + status = "okay"; +}; + +&usb_2 { + status = "okay"; +}; + +&usb_2_dwc3 { + dr_mode = "host"; +}; + +&ufs_mem_hc { + reset-gpios = <&tlmm 123 GPIO_ACTIVE_LOW>; + vcc-supply = <&vreg_l17a>; + vcc-max-microamp = <600000>; + vccq2-supply = <&vreg_s4a>; + vccq2-max-microamp = <600000>; + + status = "okay"; +}; + +&ufs_mem_phy { + vdda-phy-supply = <&vreg_l5a>; + vdda-pll-supply = <&vreg_l12a>; + + status = "okay"; +}; + +&watchdog { + clocks = <&sleep_clk>; +}; diff --git a/arch/arm64/boot/dts/qcom/qcs615.dtsi b/arch/arm64/boot/dts/qcom/qcs615.dtsi new file mode 100644 index 000000000000..f4abfad474ea --- /dev/null +++ b/arch/arm64/boot/dts/qcom/qcs615.dtsi @@ -0,0 +1,3670 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/ { + interrupt-parent = <&intc>; + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x0>; + enable-method = "psci"; + power-domains = <&cpu_pd0>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + next-level-cache = <&l2_0>; + #cooling-cells = <2>; + + l2_0: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu1: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x100>; + enable-method = "psci"; + power-domains = <&cpu_pd1>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + next-level-cache = <&l2_100>; + + l2_100: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu2: cpu@200 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x200>; + enable-method = "psci"; + power-domains = <&cpu_pd2>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + next-level-cache = <&l2_200>; + + l2_200: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu3: cpu@300 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x300>; + enable-method = "psci"; + power-domains = <&cpu_pd3>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + next-level-cache = <&l2_300>; + + l2_300: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu4: cpu@400 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x400>; + enable-method = "psci"; + power-domains = <&cpu_pd4>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + next-level-cache = <&l2_400>; + + l2_400: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu5: cpu@500 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x500>; + enable-method = "psci"; + power-domains = <&cpu_pd5>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + next-level-cache = <&l2_500>; + + l2_500: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu6: cpu@600 { + device_type = "cpu"; + compatible = "arm,cortex-a76"; + reg = <0x0 0x600>; + enable-method = "psci"; + power-domains = <&cpu_pd6>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1740>; + dynamic-power-coefficient = <404>; + next-level-cache = <&l2_600>; + #cooling-cells = <2>; + + l2_600: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu7: cpu@700 { + device_type = "cpu"; + compatible = "arm,cortex-a76"; + reg = <0x0 0x700>; + enable-method = "psci"; + power-domains = <&cpu_pd7>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1740>; + dynamic-power-coefficient = <404>; + next-level-cache = <&l2_700>; + + l2_700: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + + core4 { + cpu = <&cpu4>; + }; + + core5 { + cpu = <&cpu5>; + }; + + core6 { + cpu = <&cpu6>; + }; + + core7 { + cpu = <&cpu7>; + }; + }; + }; + + l3_0: l3-cache { + compatible = "cache"; + cache-level = <3>; + cache-unified; + }; + }; + + dummy_eud: dummy-sink { + compatible = "arm,coresight-dummy-sink"; + + in-ports { + port { + eud_in: endpoint { + remote-endpoint = <&replicator_swao_out1>; + }; + }; + }; + }; + + idle-states { + entry-method = "psci"; + + little_cpu_sleep_0: cpu-sleep-0-0 { + compatible = "arm,idle-state"; + idle-state-name = "silver-power-collapse"; + arm,psci-suspend-param = <0x40000003>; + entry-latency-us = <549>; + exit-latency-us = <901>; + min-residency-us = <1774>; + local-timer-stop; + }; + + little_cpu_sleep_1: cpu-sleep-0-1 { + compatible = "arm,idle-state"; + idle-state-name = "silver-rail-power-collapse"; + arm,psci-suspend-param = <0x40000004>; + entry-latency-us = <702>; + exit-latency-us = <915>; + min-residency-us = <4001>; + local-timer-stop; + }; + + big_cpu_sleep_0: cpu-sleep-1-0 { + compatible = "arm,idle-state"; + idle-state-name = "gold-power-collapse"; + arm,psci-suspend-param = <0x40000003>; + entry-latency-us = <523>; + exit-latency-us = <1244>; + min-residency-us = <2207>; + local-timer-stop; + }; + + big_cpu_sleep_1: cpu-sleep-1-1 { + compatible = "arm,idle-state"; + idle-state-name = "gold-rail-power-collapse"; + arm,psci-suspend-param = <0x40000004>; + entry-latency-us = <526>; + exit-latency-us = <1854>; + min-residency-us = <5555>; + local-timer-stop; + }; + }; + + domain-idle-states { + cluster_sleep_0: cluster-sleep-0 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x41000044>; + entry-latency-us = <2752>; + exit-latency-us = <3048>; + min-residency-us = <6118>; + }; + + cluster_sleep_1: cluster-sleep-1 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x41001344>; + entry-latency-us = <3263>; + exit-latency-us = <4562>; + min-residency-us = <8467>; + }; + + cluster_sleep_2: cluster-sleep-2 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x4100b344>; + entry-latency-us = <3638>; + exit-latency-us = <6562>; + min-residency-us = <9826>; + }; + }; + + memory@80000000 { + device_type = "memory"; + /* We expect the bootloader to fill in the size */ + reg = <0 0x80000000 0 0>; + }; + + firmware { + scm { + compatible = "qcom,scm-qcs615", "qcom,scm"; + qcom,dload-mode = <&tcsr 0x13000>; + }; + }; + + camnoc_virt: interconnect-0 { + compatible = "qcom,qcs615-camnoc-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + ipa_virt: interconnect-1 { + compatible = "qcom,qcs615-ipa-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + mc_virt: interconnect-2 { + compatible = "qcom,qcs615-mc-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + qup_opp_table: opp-table-qup { + compatible = "operating-points-v2"; + opp-shared; + + opp-75000000 { + opp-hz = /bits/ 64 <75000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-100000000 { + opp-hz = /bits/ 64 <100000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-128000000 { + opp-hz = /bits/ 64 <128000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + + psci { + compatible = "arm,psci-1.0"; + method = "smc"; + + cpu_pd0: power-domain-cpu0 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cpu_pd1: power-domain-cpu1 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cpu_pd2: power-domain-cpu2 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cpu_pd3: power-domain-cpu3 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cpu_pd4: power-domain-cpu4 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cpu_pd5: power-domain-cpu5 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cpu_pd6: power-domain-cpu6 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&big_cpu_sleep_0 &big_cpu_sleep_1>; + }; + + cpu_pd7: power-domain-cpu7 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&big_cpu_sleep_0 &big_cpu_sleep_1>; + }; + + cluster_pd: power-domain-cluster { + #power-domain-cells = <0>; + domain-idle-states = <&cluster_sleep_0 + &cluster_sleep_1 + &cluster_sleep_2>; + }; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + smem_region: smem@86000000 { + compatible = "qcom,smem"; + reg = <0x0 0x86000000 0x0 0x200000>; + no-map; + hwlocks = <&tcsr_mutex 3>; + }; + }; + + soc: soc@0 { + compatible = "simple-bus"; + ranges = <0 0 0 0 0x10 0>; + dma-ranges = <0 0 0 0 0x10 0>; + #address-cells = <2>; + #size-cells = <2>; + + gcc: clock-controller@100000 { + compatible = "qcom,qcs615-gcc"; + reg = <0 0x00100000 0 0x1f0000>; + + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + + qfprom: efuse@780000 { + compatible = "qcom,qcs615-qfprom", "qcom,qfprom"; + reg = <0x0 0x00780000 0x0 0x7000>; + #address-cells = <1>; + #size-cells = <1>; + + qusb2_hstx_trim: hstx-trim@1f8 { + reg = <0x1fb 0x1>; + bits = <1 4>; + }; + }; + + sdhc_1: mmc@7c4000 { + compatible = "qcom,qcs615-sdhci", "qcom,sdhci-msm-v5"; + reg = <0x0 0x007c4000 0x0 0x1000>, + <0x0 0x007c5000 0x0 0x1000>, + <0x0 0x007c8000 0x0 0x8000>; + reg-names = "hc", + "cqhci", + "ice"; + + interrupts = , + ; + interrupt-names = "hc_irq", + "pwr_irq"; + + clocks = <&gcc GCC_SDCC1_AHB_CLK>, + <&gcc GCC_SDCC1_APPS_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_SDCC1_ICE_CORE_CLK>; + clock-names = "iface", + "core", + "xo", + "ice"; + + resets = <&gcc GCC_SDCC1_BCR>; + + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&sdhc1_opp_table>; + iommus = <&apps_smmu 0x02c0 0x0>; + interconnects = <&aggre1_noc MASTER_SDCC_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_SDCC_1 QCOM_ICC_TAG_ACTIVE_ONLY>; + interconnect-names = "sdhc-ddr", + "cpu-sdhc"; + + qcom,dll-config = <0x000f642c>; + qcom,ddr-config = <0x80040868>; + supports-cqe; + dma-coherent; + + status = "disabled"; + + sdhc1_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-50000000 { + opp-hz = /bits/ 64 <50000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-100000000 { + opp-hz = /bits/ 64 <100000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-200000000 { + opp-hz = /bits/ 64 <200000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + + opp-384000000 { + opp-hz = /bits/ 64 <384000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; + + gpi_dma0: dma-controller@800000 { + compatible = "qcom,qcs615-gpi-dma", "qcom,sdm845-gpi-dma"; + reg = <0x0 0x800000 0x0 0x60000>; + #dma-cells = <3>; + interrupts = , + , + , + , + , + , + , + ; + dma-channels = <8>; + dma-channel-mask = <0xf>; + iommus = <&apps_smmu 0xd6 0x0>; + status = "disabled"; + }; + + qupv3_id_0: geniqup@8c0000 { + compatible = "qcom,geni-se-qup"; + reg = <0x0 0x008c0000 0x0 0x6000>; + ranges; + clocks = <&gcc GCC_QUPV3_WRAP_0_M_AHB_CLK>, + <&gcc GCC_QUPV3_WRAP_0_S_AHB_CLK>; + clock-names = "m-ahb", + "s-ahb"; + iommus = <&apps_smmu 0xc3 0x0>; + #address-cells = <2>; + #size-cells = <2>; + status = "disabled"; + + uart0: serial@880000 { + compatible = "qcom,geni-debug-uart"; + reg = <0x0 0x00880000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP0_S0_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_uart0_tx>, <&qup_uart0_rx>; + pinctrl-names = "default"; + interrupts = ; + interconnects = <&aggre1_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + status = "disabled"; + }; + + i2c1: i2c@884000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x884000 0x0 0x4000>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = ; + clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_i2c1_data_clk>; + pinctrl-names = "default"; + interconnects = <&aggre1_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + dmas = <&gpi_dma0 0 1 QCOM_GPI_I2C>, + <&gpi_dma0 1 1 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + + i2c2: i2c@888000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x888000 0x0 0x4000>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = ; + clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_i2c2_data_clk>; + pinctrl-names = "default"; + interconnects = <&aggre1_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + dmas = <&gpi_dma0 0 2 QCOM_GPI_I2C>, + <&gpi_dma0 1 2 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + + spi2: spi@888000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00888000 0x0 0x4000>; + interrupts = ; + clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_spi2_data_clk>, <&qup_spi2_cs>; + pinctrl-names = "default"; + interconnects = <&aggre1_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + dmas = <&gpi_dma0 0 2 QCOM_GPI_SPI>, + <&gpi_dma0 1 2 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + uart2: serial@888000 { + compatible = "qcom,geni-uart"; + reg = <0x0 0x00888000 0x0 0x4000>; + interrupts = ; + clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_uart2_cts>, <&qup_uart2_rts>, + <&qup_uart2_tx>, <&qup_uart2_rx>; + pinctrl-names = "default"; + interconnects = <&aggre1_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + status = "disabled"; + }; + + i2c3: i2c@88c000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x88c000 0x0 0x4000>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = ; + clocks = <&gcc GCC_QUPV3_WRAP0_S3_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_i2c3_data_clk>; + pinctrl-names = "default"; + interconnects = <&aggre1_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + dmas = <&gpi_dma0 0 3 QCOM_GPI_I2C>, + <&gpi_dma0 1 3 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + }; + + gpi_dma1: dma-controller@a00000 { + compatible = "qcom,qcs615-gpi-dma", "qcom,sdm845-gpi-dma"; + reg = <0x0 0xa00000 0x0 0x60000>; + #dma-cells = <3>; + interrupts = , + , + , + , + , + , + , + ; + dma-channels = <8>; + dma-channel-mask = <0xf>; + iommus = <&apps_smmu 0x376 0x0>; + status = "disabled"; + }; + + qupv3_id_1: geniqup@ac0000 { + compatible = "qcom,geni-se-qup"; + reg = <0x0 0xac0000 0x0 0x2000>; + ranges; + clocks = <&gcc GCC_QUPV3_WRAP_1_M_AHB_CLK>, + <&gcc GCC_QUPV3_WRAP_1_S_AHB_CLK>; + clock-names = "m-ahb", + "s-ahb"; + iommus = <&apps_smmu 0x363 0x0>; + #address-cells = <2>; + #size-cells = <2>; + status = "disabled"; + + i2c4: i2c@a80000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0xa80000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_i2c4_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 0 QCOM_GPI_I2C>, + <&gpi_dma1 1 0 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + + spi4: spi@a80000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0xa80000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_spi4_data_clk>, <&qup_spi4_cs>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table>; + dmas = <&gpi_dma1 0 0 QCOM_GPI_SPI>, + <&gpi_dma1 1 0 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + + uart4: serial@a80000 { + compatible = "qcom,geni-uart"; + reg = <0x0 0xa80000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_uart4_cts>, <&qup_uart4_rts>, + <&qup_uart4_tx>, <&qup_uart4_rx>; + pinctrl-names = "default"; + interrupts = ; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table>; + status = "disabled"; + }; + + i2c5: i2c@a84000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0xa84000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_i2c5_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 1 QCOM_GPI_I2C>, + <&gpi_dma1 1 1 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + + i2c6: i2c@a88000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0xa88000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_i2c6_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 2 QCOM_GPI_I2C>, + <&gpi_dma1 1 2 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + + spi6: spi@a88000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0xa88000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_spi6_data_clk>, <&qup_spi6_cs>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table>; + dmas = <&gpi_dma1 0 2 QCOM_GPI_SPI>, + <&gpi_dma1 1 2 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + + uart6: serial@a88000 { + compatible = "qcom,geni-uart"; + reg = <0x0 0xa88000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_uart6_cts>, <&qup_uart6_rts>, + <&qup_uart6_tx>, <&qup_uart6_rx>; + pinctrl-names = "default"; + interrupts = ; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table>; + status = "disabled"; + }; + + i2c7: i2c@a8c000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0xa8c000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_i2c7_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 3 QCOM_GPI_I2C>, + <&gpi_dma1 1 3 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + + spi7: spi@a8c000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0xa8c000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_spi7_data_clk>, <&qup_spi7_cs>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table>; + dmas = <&gpi_dma1 0 3 QCOM_GPI_SPI>, + <&gpi_dma1 1 3 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + status = "disabled"; + }; + + uart7: serial@a8c000 { + compatible = "qcom,geni-uart"; + reg = <0x0 0xa8c000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_uart7_cts>, <&qup_uart7_rts>, + <&qup_uart7_tx>, <&qup_uart7_rx>; + pinctrl-names = "default"; + interrupts = ; + interconnects = <&aggre1_noc MASTER_BLSP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table>; + status = "disabled"; + }; + }; + + config_noc: interconnect@1500000 { + reg = <0x0 0x01500000 0x0 0x5080>; + compatible = "qcom,qcs615-config-noc"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + system_noc: interconnect@1620000 { + reg = <0x0 0x01620000 0x0 0x1f300>; + compatible = "qcom,qcs615-system-noc"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + aggre1_noc: interconnect@1700000 { + reg = <0x0 0x01700000 0x0 0x3f200>; + compatible = "qcom,qcs615-aggre1-noc"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + mmss_noc: interconnect@1740000 { + reg = <0x0 0x01740000 0x0 0x1c100>; + compatible = "qcom,qcs615-mmss-noc"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + ufs_mem_hc: ufshc@1d84000 { + compatible = "qcom,qcs615-ufshc", "qcom,ufshc", "jedec,ufs-2.0"; + reg = <0x0 0x01d84000 0x0 0x3000>, + <0x0 0x01d90000 0x0 0x8000>; + reg-names = "std", + "ice"; + + interrupts = ; + + clocks = <&gcc GCC_UFS_PHY_AXI_CLK>, + <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>, + <&gcc GCC_UFS_PHY_AHB_CLK>, + <&gcc GCC_UFS_PHY_UNIPRO_CORE_CLK>, + <&gcc GCC_UFS_PHY_ICE_CORE_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>, + <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>; + clock-names = "core_clk", + "bus_aggr_clk", + "iface_clk", + "core_clk_unipro", + "core_clk_ice", + "ref_clk", + "tx_lane0_sync_clk", + "rx_lane0_sync_clk"; + + resets = <&gcc GCC_UFS_PHY_BCR>; + reset-names = "rst"; + + operating-points-v2 = <&ufs_opp_table>; + interconnects = <&aggre1_noc MASTER_UFS_MEM QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_UFS_MEM_CFG QCOM_ICC_TAG_ACTIVE_ONLY>; + interconnect-names = "ufs-ddr", + "cpu-ufs"; + + power-domains = <&gcc UFS_PHY_GDSC>; + + iommus = <&apps_smmu 0x300 0x0>; + dma-coherent; + + lanes-per-direction = <1>; + + phys = <&ufs_mem_phy>; + phy-names = "ufsphy"; + + #reset-cells = <1>; + + status = "disabled"; + + ufs_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-50000000 { + opp-hz = /bits/ 64 <50000000>, + /bits/ 64 <0>, + /bits/ 64 <0>, + /bits/ 64 <37500000>, + /bits/ 64 <75000000>, + /bits/ 64 <0>, + /bits/ 64 <0>, + /bits/ 64 <0>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-100000000 { + opp-hz = /bits/ 64 <100000000>, + /bits/ 64 <0>, + /bits/ 64 <0>, + /bits/ 64 <75000000>, + /bits/ 64 <150000000>, + /bits/ 64 <0>, + /bits/ 64 <0>, + /bits/ 64 <0>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-200000000 { + opp-hz = /bits/ 64 <200000000>, + /bits/ 64 <0>, + /bits/ 64 <0>, + /bits/ 64 <150000000>, + /bits/ 64 <300000000>, + /bits/ 64 <0>, + /bits/ 64 <0>, + /bits/ 64 <0>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; + + ufs_mem_phy: phy@1d87000 { + compatible = "qcom,qcs615-qmp-ufs-phy", "qcom,sm6115-qmp-ufs-phy"; + reg = <0x0 0x01d87000 0x0 0xe00>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_UFS_PHY_PHY_AUX_CLK>, + <&gcc GCC_UFS_MEM_CLKREF_CLK>; + clock-names = "ref", + "ref_aux", + "qref"; + + power-domains = <&gcc UFS_PHY_GDSC>; + + resets = <&ufs_mem_hc 0>; + reset-names = "ufsphy"; + + #clock-cells = <1>; + #phy-cells = <0>; + + status = "disabled"; + }; + + tcsr_mutex: hwlock@1f40000 { + compatible = "qcom,tcsr-mutex"; + reg = <0x0 0x01f40000 0x0 0x20000>; + #hwlock-cells = <1>; + }; + + tcsr: syscon@1fc0000 { + compatible = "qcom,qcs615-tcsr", "syscon"; + reg = <0x0 0x01fc0000 0x0 0x30000>; + }; + + tlmm: pinctrl@3100000 { + compatible = "qcom,qcs615-tlmm"; + reg = <0x0 0x03100000 0x0 0x300000>, + <0x0 0x03500000 0x0 0x300000>, + <0x0 0x03d00000 0x0 0x300000>; + reg-names = "east", + "west", + "south"; + interrupts = ; + gpio-ranges = <&tlmm 0 0 124>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + wakeup-parent = <&pdc>; + + qup_i2c1_data_clk: qup-i2c1-data-clk-state { + pins = "gpio4", "gpio5"; + function = "qup0"; + + }; + + qup_i2c2_data_clk: qup-i2c2-data-clk-state { + pins = "gpio0", "gpio1"; + function = "qup0"; + }; + + qup_i2c3_data_clk: qup-i2c3-data-clk-state { + pins = "gpio18", "gpio19"; + function = "qup0"; + }; + + qup_i2c4_data_clk: qup-i2c4-data-clk-state { + pins = "gpio20", "gpio21"; + function = "qup1"; + }; + + qup_i2c5_data_clk: qup-i2c5-data-clk-state { + pins = "gpio14", "gpio15"; + function = "qup1"; + }; + + qup_i2c6_data_clk: qup-i2c6-data-clk-state { + pins = "gpio6", "gpio7"; + function = "qup1"; + }; + + qup_i2c7_data_clk: qup-i2c7-data-clk-state { + pins = "gpio10", "gpio11"; + function = "qup1"; + }; + + qup_spi2_data_clk: qup-spi2-data-clk-state { + pins = "gpio0", "gpio1", "gpio2"; + function = "qup0"; + }; + + qup_spi2_cs: qup-spi2-cs-state { + pins = "gpio3"; + function = "qup0"; + }; + + qup_spi2_cs_gpio: qup-spi2-cs-gpio-state { + pins = "gpio3"; + function = "gpio"; + }; + + qup_spi4_data_clk: qup-spi4-data-clk-state { + pins = "gpio20", "gpio21", "gpio22"; + function = "qup1"; + }; + + qup_spi4_cs: qup-spi4-cs-state { + pins = "gpio23"; + function = "qup1"; + }; + + qup_spi4_cs_gpio: qup-spi4-cs-gpio-state { + pins = "gpio23"; + function = "gpio"; + }; + + qup_spi6_data_clk: qup-spi6-data-clk-state { + pins = "gpio6", "gpio7", "gpio8"; + function = "qup1"; + }; + + qup_spi6_cs: qup-spi6-cs-state { + pins = "gpio9"; + function = "qup1"; + }; + + qup_spi6_cs_gpio: qup-spi6-cs-gpio-state { + pins = "gpio9"; + function = "gpio"; + }; + + qup_spi7_data_clk: qup-spi7-data-clk-state { + pins = "gpio10", "gpio11", "gpio12"; + function = "qup1"; + }; + + qup_spi7_cs: qup-spi7-cs-state { + pins = "gpio13"; + function = "qup1"; + }; + + qup_spi7_cs_gpio: qup-spi7-cs-gpio-state { + pins = "gpio13"; + function = "gpio"; + }; + + qup_uart0_tx: qup-uart0-tx-state { + pins = "gpio16"; + function = "qup0"; + }; + + qup_uart0_rx: qup-uart0-rx-state { + pins = "gpio17"; + function = "qup0"; + }; + + qup_uart2_cts: qup-uart2-cts-state { + pins = "gpio0"; + function = "qup0"; + }; + + qup_uart2_rts: qup-uart2-rts-state { + pins = "gpio1"; + function = "qup0"; + }; + + qup_uart2_tx: qup-uart2-tx-state { + pins = "gpio2"; + function = "qup0"; + }; + + qup_uart2_rx: qup-uart2-rx-state { + pins = "gpio3"; + function = "qup0"; + }; + + qup_uart4_cts: qup-uart4-cts-state { + pins = "gpio20"; + function = "qup1"; + }; + + qup_uart4_rts: qup-uart4-rts-state { + pins = "gpio21"; + function = "qup1"; + }; + + qup_uart4_tx: qup-uart4-tx-state { + pins = "gpio22"; + function = "qup1"; + }; + + qup_uart4_rx: qup-uart4-rx-state { + pins = "gpio23"; + function = "qup1"; + }; + + qup_uart6_cts: qup-uart6-cts-state { + pins = "gpio6"; + function = "qup1"; + }; + + qup_uart6_rts: qup-uart6-rts-state { + pins = "gpio7"; + function = "qup1"; + }; + + qup_uart6_tx: qup-uart6-tx-state { + pins = "gpio8"; + function = "qup1"; + }; + + qup_uart6_rx: qup-uart6-rx-state { + pins = "gpio9"; + function = "qup1"; + }; + + qup_uart7_cts: qup-uart7-cts-state { + pins = "gpio10"; + function = "qup1"; + }; + + qup_uart7_rts: qup-uart7-rts-state { + pins = "gpio11"; + function = "qup1"; + }; + + qup_uart7_tx: qup-uart7-tx-state { + pins = "gpio12"; + function = "qup1"; + }; + + qup_uart7_rx: qup-uart7-rx-state { + pins = "gpio13"; + function = "qup1"; + }; + + sdc1_state_on: sdc1-on-state { + clk-pins { + pins = "sdc1_clk"; + bias-disable; + drive-strength = <16>; + }; + + cmd-pins { + pins = "sdc1_cmd"; + bias-pull-up; + drive-strength = <10>; + }; + + data-pins { + pins = "sdc1_data"; + bias-pull-up; + drive-strength = <10>; + }; + + rclk-pins { + pins = "sdc1_rclk"; + bias-pull-down; + }; + }; + + sdc1_state_off: sdc1-off-state { + clk-pins { + pins = "sdc1_clk"; + bias-disable; + drive-strength = <2>; + }; + + cmd-pins { + pins = "sdc1_cmd"; + bias-pull-up; + drive-strength = <2>; + }; + + data-pins { + pins = "sdc1_data"; + bias-pull-up; + drive-strength = <2>; + }; + + rclk-pins { + pins = "sdc1_rclk"; + bias-pull-down; + }; + }; + + sdc2_state_on: sdc2-on-state { + clk-pins { + pins = "sdc2_clk"; + bias-disable; + drive-strength = <16>; + }; + + cmd-pins { + pins = "sdc2_cmd"; + bias-pull-up; + drive-strength = <10>; + }; + + data-pins { + pins = "sdc2_data"; + bias-pull-up; + drive-strength = <10>; + }; + }; + + sdc2_state_off: sdc2-off-state { + clk-pins { + pins = "sdc2_clk"; + bias-disable; + drive-strength = <2>; + }; + + cmd-pins { + pins = "sdc2_cmd"; + bias-pull-up; + drive-strength = <2>; + }; + + data-pins { + pins = "sdc2_data"; + bias-pull-up; + drive-strength = <2>; + }; + }; + }; + + stm@6002000 { + compatible = "arm,coresight-stm", "arm,primecell"; + reg = <0x0 0x06002000 0x0 0x1000>, + <0x0 0x16280000 0x0 0x180000>; + reg-names = "stm-base", + "stm-stimulus-base"; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + out-ports { + port { + stm_out: endpoint { + remote-endpoint = <&funnel_in0_in7>; + }; + }; + }; + }; + + tpda@6004000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x06004000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + tpda_qdss_in0: endpoint { + remote-endpoint = <&tpdm_center_out>; + }; + }; + + port@4 { + reg = <4>; + + tpda_qdss_in4: endpoint { + remote-endpoint = <&funnel_monaq_out>; + }; + }; + + port@5 { + reg = <5>; + + tpda_qdss_in5: endpoint { + remote-endpoint = <&funnel_ddr_0_out>; + }; + }; + + port@6 { + reg = <6>; + + tpda_qdss_in6: endpoint { + remote-endpoint = <&funnel_turing_out>; + }; + }; + + port@7 { + reg = <7>; + + tpda_qdss_in7: endpoint { + remote-endpoint = <&tpdm_vsense_out>; + }; + }; + + port@8 { + reg = <8>; + + tpda_qdss_in8: endpoint { + remote-endpoint = <&tpdm_dcc_out>; + }; + }; + + port@9 { + reg = <9>; + + tpda_qdss_in9: endpoint { + remote-endpoint = <&tpdm_prng_out>; + }; + }; + + port@b { + reg = <11>; + + tpda_qdss_in11: endpoint { + remote-endpoint = <&tpdm_qm_out>; + }; + }; + + port@c { + reg = <12>; + + tpda_qdss_in12: endpoint { + remote-endpoint = <&tpdm_west_out>; + }; + }; + + port@d { + reg = <13>; + + tpda_qdss_in13: endpoint { + remote-endpoint = <&tpdm_pimem_out>; + }; + }; + }; + + out-ports { + port { + tpda_qdss_out: endpoint { + remote-endpoint = <&funnel_qatb_in>; + }; + }; + }; + }; + + funnel@6005000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x06005000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + funnel_qatb_in: endpoint { + remote-endpoint = <&tpda_qdss_out>; + }; + }; + }; + + out-ports { + port { + funnel_qatb_out: endpoint { + remote-endpoint = <&funnel_in0_in6>; + }; + }; + }; + }; + + cti@6010000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06010000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6011000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06011000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6012000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06012000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6013000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06013000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6014000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06014000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6015000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06015000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6016000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06016000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6017000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06017000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6018000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06018000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6019000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06019000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@601a000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x0601a000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@601b000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x0601b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@601c000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x0601c000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@601d000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x0601d000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@601e000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x0601e000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@601f000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x0601f000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + funnel@6041000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x06041000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@6 { + reg = <6>; + + funnel_in0_in6: endpoint { + remote-endpoint = <&funnel_qatb_out>; + }; + }; + + port@7 { + reg = <7>; + + funnel_in0_in7: endpoint { + remote-endpoint = <&stm_out>; + }; + }; + }; + + out-ports { + port { + funnel_in0_out: endpoint { + remote-endpoint = <&funnel_merg_in0>; + }; + }; + }; + }; + + funnel@6042000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x06042000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@3 { + reg = <3>; + + funnel_in1_in3: endpoint { + remote-endpoint = <&replicator_swao_out0>; + }; + }; + + port@4 { + reg = <4>; + + funnel_in1_in4: endpoint { + remote-endpoint = <&tpdm_wcss_out>; + }; + }; + + port@7 { + reg = <7>; + + funnel_in1_in7: endpoint { + remote-endpoint = <&funnel_apss_merg_out>; + }; + }; + }; + + out-ports { + port { + funnel_in1_out: endpoint { + remote-endpoint = <&funnel_merg_in1>; + }; + }; + }; + }; + + funnel@6045000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x06045000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + funnel_merg_in0: endpoint { + remote-endpoint = <&funnel_in0_out>; + }; + }; + + port@1 { + reg = <1>; + + funnel_merg_in1: endpoint { + remote-endpoint = <&funnel_in1_out>; + }; + }; + }; + + out-ports { + port { + funnel_merg_out: endpoint { + remote-endpoint = <&tmc_etf_in>; + }; + }; + }; + }; + + replicator@6046000 { + compatible = "arm,coresight-dynamic-replicator", "arm,primecell"; + reg = <0x0 0x06046000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + replicator0_in: endpoint { + remote-endpoint= <&tmc_etf_out>; + }; + }; + }; + + out-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@1 { + reg = <1>; + + replicator0_out1: endpoint { + remote-endpoint= <&replicator1_in>; + }; + }; + }; + }; + + tmc@6047000 { + compatible = "arm,coresight-tmc", "arm,primecell"; + reg = <0x0 0x06047000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tmc_etf_in: endpoint { + remote-endpoint = <&funnel_merg_out>; + }; + }; + }; + + out-ports { + port { + tmc_etf_out: endpoint { + remote-endpoint = <&replicator0_in>; + }; + }; + }; + }; + + replicator@604a000 { + compatible = "arm,coresight-dynamic-replicator", "arm,primecell"; + reg = <0x0 0x0604a000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + replicator1_in: endpoint { + remote-endpoint= <&replicator0_out1>; + }; + }; + }; + + out-ports { + port { + replicator1_out: endpoint { + remote-endpoint= <&funnel_swao_in6>; + }; + }; + }; + }; + + cti@683b000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x0683b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + tpdm@6840000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06840000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + tpdm_vsense_out: endpoint { + remote-endpoint = <&tpda_qdss_in7>; + }; + }; + }; + }; + + tpdm@684c000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x0684c000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + tpdm_prng_out: endpoint { + remote-endpoint = <&tpda_qdss_in9>; + }; + }; + }; + }; + + tpdm@6850000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06850000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + tpdm_pimem_out: endpoint { + remote-endpoint = <&tpda_qdss_in13>; + }; + }; + }; + }; + + tpdm@6860000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06860000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + tpdm_turing_out: endpoint { + remote-endpoint = <&funnel_turing_in>; + }; + }; + }; + }; + + funnel@6861000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x06861000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + funnel_turing_in: endpoint { + remote-endpoint = <&tpdm_turing_out>; + }; + }; + }; + + out-ports { + port { + funnel_turing_out: endpoint { + remote-endpoint = <&tpda_qdss_in6>; + }; + }; + }; + }; + + cti@6867000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06867000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + tpdm@6870000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06870000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + tpdm_dcc_out: endpoint { + remote-endpoint = <&tpda_qdss_in8>; + }; + }; + }; + }; + + tpdm@699c000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x0699c000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + tpdm_wcss_out: endpoint { + remote-endpoint = <&funnel_in1_in4>; + }; + }; + }; + }; + + tpdm@69c0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x069c0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + tpdm_monaq_out: endpoint { + remote-endpoint = <&funnel_monaq_in>; + }; + }; + }; + }; + + funnel@69c3000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x069c3000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + funnel_monaq_in: endpoint { + remote-endpoint = <&tpdm_monaq_out>; + }; + }; + }; + + out-ports { + port { + funnel_monaq_out: endpoint { + remote-endpoint = <&tpda_qdss_in4>; + }; + }; + }; + }; + + tpdm@69d0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x069d0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + tpdm_qm_out: endpoint { + remote-endpoint = <&tpda_qdss_in11>; + }; + }; + }; + }; + + tpdm@6a00000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06a00000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + tpdm_ddr_out: endpoint { + remote-endpoint = <&funnel_ddr_0_in>; + }; + }; + }; + }; + + cti@6a02000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06a02000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6a03000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06a03000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6a10000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06a10000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6a11000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06a11000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + funnel@6a05000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x06a05000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + funnel_ddr_0_in: endpoint { + remote-endpoint = <&tpdm_ddr_out>; + }; + }; + }; + + out-ports { + port { + funnel_ddr_0_out: endpoint { + remote-endpoint = <&tpda_qdss_in5>; + }; + }; + }; + }; + + tpda@6b01000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x06b01000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + tpda_swao_in0: endpoint { + remote-endpoint = <&tpdm_swao0_out>; + }; + }; + + port@1 { + reg = <1>; + + tpda_swao_in1: endpoint { + remote-endpoint = <&tpdm_swao1_out>; + }; + + }; + }; + + out-ports { + port { + tpda_swao_out: endpoint { + remote-endpoint = <&funnel_swao_in7>; + }; + }; + }; + }; + + tpdm@6b02000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06b02000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + tpdm_swao0_out: endpoint { + remote-endpoint = <&tpda_swao_in0>; + }; + }; + }; + }; + + tpdm@6b03000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06b03000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + tpdm_swao1_out: endpoint { + remote-endpoint = <&tpda_swao_in1>; + }; + }; + }; + }; + + cti@6b04000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06b04000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6b05000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06b05000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6b06000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06b06000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6b07000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06b07000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + funnel@6b08000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x06b08000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@6 { + reg = <6>; + + funnel_swao_in6: endpoint { + remote-endpoint= <&replicator1_out>; + }; + }; + + port@7 { + reg = <7>; + + funnel_swao_in7: endpoint { + remote-endpoint= <&tpda_swao_out>; + }; + }; + }; + + out-ports { + port { + funnel_swao_out: endpoint { + remote-endpoint = <&tmc_etf_swao_in>; + }; + }; + }; + }; + + tmc@6b09000 { + compatible = "arm,coresight-tmc", "arm,primecell"; + reg = <0x0 0x06b09000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tmc_etf_swao_in: endpoint { + remote-endpoint= <&funnel_swao_out>; + }; + }; + }; + + out-ports { + port { + tmc_etf_swao_out: endpoint { + remote-endpoint= <&replicator_swao_in>; + }; + }; + }; + }; + + replicator@6b0a000 { + compatible = "arm,coresight-dynamic-replicator", "arm,primecell"; + reg = <0x0 0x06b0a000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + replicator_swao_in: endpoint { + remote-endpoint = <&tmc_etf_swao_out>; + }; + }; + }; + + out-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + replicator_swao_out0: endpoint { + remote-endpoint = <&funnel_in1_in3>; + }; + }; + + port@1 { + reg = <1>; + + replicator_swao_out1: endpoint { + remote-endpoint = <&eud_in>; + }; + }; + }; + }; + + cti@6b21000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06b21000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + tpdm@6b48000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06b48000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + tpdm_west_out: endpoint { + remote-endpoint = <&tpda_qdss_in12>; + }; + }; + }; + }; + + cti@6c13000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06c13000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6c20000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06c20000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + status = "disabled"; + }; + + tpdm@6c28000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06c28000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + tpdm_center_out: endpoint { + remote-endpoint = <&tpda_qdss_in0>; + }; + }; + }; + }; + + cti@6c29000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06c29000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6c2a000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06c2a000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@7020000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x07020000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + etm@7040000 { + compatible = "arm,primecell"; + reg = <0x0 0x07040000 0x0 0x1000>; + cpu = <&cpu0>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm0_out: endpoint { + remote-endpoint = <&funnel_apss_in0>; + }; + }; + }; + }; + + cti@7120000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x07120000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + etm@7140000 { + compatible = "arm,primecell"; + reg = <0x0 0x07140000 0x0 0x1000>; + cpu = <&cpu1>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm1_out: endpoint { + remote-endpoint = <&funnel_apss_in1>; + }; + }; + }; + }; + + cti@7220000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x07220000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + etm@7240000 { + compatible = "arm,primecell"; + reg = <0x0 0x07240000 0x0 0x1000>; + cpu = <&cpu2>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm2_out: endpoint { + remote-endpoint = <&funnel_apss_in2>; + }; + }; + }; + }; + + cti@7320000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x07320000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + etm@7340000 { + compatible = "arm,primecell"; + reg = <0x0 0x07340000 0x0 0x1000>; + cpu = <&cpu3>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm3_out: endpoint { + remote-endpoint = <&funnel_apss_in3>; + }; + }; + }; + }; + + cti@7420000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x07420000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + etm@7440000 { + compatible = "arm,primecell"; + reg = <0x0 0x07440000 0x0 0x1000>; + cpu = <&cpu4>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm4_out: endpoint { + remote-endpoint = <&funnel_apss_in4>; + }; + }; + }; + }; + + cti@7520000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x07520000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + etm@7540000 { + compatible = "arm,primecell"; + reg = <0x0 0x07540000 0x0 0x1000>; + cpu = <&cpu5>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm5_out: endpoint { + remote-endpoint = <&funnel_apss_in5>; + }; + }; + }; + }; + + cti@7620000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x07620000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + etm@7640000 { + compatible = "arm,primecell"; + reg = <0x0 0x07640000 0x0 0x1000>; + cpu = <&cpu6>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm6_out: endpoint { + remote-endpoint = <&funnel_apss_in6>; + }; + }; + }; + }; + + cti@7720000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x07720000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + etm@7740000 { + compatible = "arm,primecell"; + reg = <0x0 0x07740000 0x0 0x1000>; + cpu = <&cpu7>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm7_out: endpoint { + remote-endpoint = <&funnel_apss_in7>; + }; + }; + }; + }; + + funnel@7800000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x07800000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + funnel_apss_in0: endpoint { + remote-endpoint = <&etm0_out>; + }; + }; + + port@1 { + reg = <1>; + + funnel_apss_in1: endpoint { + remote-endpoint = <&etm1_out>; + }; + }; + + port@2 { + reg = <2>; + + funnel_apss_in2: endpoint { + remote-endpoint = <&etm2_out>; + }; + }; + + port@3 { + reg = <3>; + + funnel_apss_in3: endpoint { + remote-endpoint = <&etm3_out>; + }; + }; + + port@4 { + reg = <4>; + + funnel_apss_in4: endpoint { + remote-endpoint = <&etm4_out>; + }; + }; + + port@5 { + reg = <5>; + + funnel_apss_in5: endpoint { + remote-endpoint = <&etm5_out>; + }; + }; + + port@6 { + reg = <6>; + + funnel_apss_in6: endpoint { + remote-endpoint = <&etm6_out>; + }; + }; + + port@7 { + reg = <7>; + + funnel_apss_in7: endpoint { + remote-endpoint = <&etm7_out>; + }; + }; + }; + + out-ports { + port { + funnel_apss_out: endpoint { + remote-endpoint = <&funnel_apss_merg_in0>; + }; + }; + }; + }; + + funnel@7810000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x07810000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + funnel_apss_merg_in0: endpoint { + remote-endpoint = <&funnel_apss_out>; + }; + }; + + port@2 { + reg = <2>; + + funnel_apss_merg_in2: endpoint { + remote-endpoint = <&tpda_olc_out>; + }; + }; + + port@3 { + reg = <3>; + + funnel_apss_merg_in3: endpoint { + remote-endpoint = <&tpda_llm_silver_out>; + }; + }; + + port@4 { + reg = <4>; + + funnel_apss_merg_in4: endpoint { + remote-endpoint = <&tpda_llm_gold_out>; + }; + }; + + port@5 { + reg = <5>; + + funnel_apss_merg_in5: endpoint { + remote-endpoint = <&tpda_apss_out>; + }; + }; + }; + + out-ports { + port { + funnel_apss_merg_out: endpoint { + remote-endpoint = <&funnel_in1_in7>; + }; + }; + }; + }; + + tpdm@7830000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x07830000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + tpdm_olc_out: endpoint { + remote-endpoint = <&tpda_olc_in>; + }; + }; + }; + }; + + tpda@7832000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x07832000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tpda_olc_in: endpoint { + remote-endpoint = <&tpdm_olc_out>; + }; + }; + }; + + out-ports { + port { + tpda_olc_out: endpoint { + remote-endpoint = <&funnel_apss_merg_in2>; + }; + }; + }; + }; + + tpdm@7860000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x07860000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + tpdm_apss_out: endpoint { + remote-endpoint = <&tpda_apss_in>; + }; + }; + }; + }; + + tpda@7862000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x07862000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tpda_apss_in: endpoint { + remote-endpoint = <&tpdm_apss_out>; + }; + }; + }; + + out-ports { + port { + tpda_apss_out: endpoint { + remote-endpoint = <&funnel_apss_merg_in5>; + }; + }; + }; + }; + + tpdm@78a0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x078a0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + tpdm_llm_silver_out: endpoint { + remote-endpoint = <&tpda_llm_silver_in>; + }; + }; + }; + }; + + tpdm@78b0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x078b0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + tpdm_llm_gold_out: endpoint { + remote-endpoint = <&tpda_llm_gold_in>; + }; + }; + }; + }; + + tpda@78c0000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x078c0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tpda_llm_silver_in: endpoint { + remote-endpoint = <&tpdm_llm_silver_out>; + }; + }; + }; + + out-ports { + port { + tpda_llm_silver_out: endpoint { + remote-endpoint = <&funnel_apss_merg_in3>; + }; + }; + }; + }; + + tpda@78d0000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x078d0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tpda_llm_gold_in: endpoint { + remote-endpoint = <&tpdm_llm_gold_out>; + }; + }; + }; + + out-ports { + port { + tpda_llm_gold_out: endpoint { + remote-endpoint = <&funnel_apss_merg_in4>; + }; + }; + }; + }; + + cti@78e0000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x078e0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@78f0000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x078f0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@7900000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x07900000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + pmu@90b6300 { + compatible = "qcom,qcs615-cpu-bwmon", "qcom,sdm845-bwmon"; + reg = <0x0 0x090b6300 0x0 0x600>; + interrupts = ; + interconnects = <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ACTIVE_ONLY>; + + operating-points-v2 = <&cpu_bwmon_opp_table>; + + cpu_bwmon_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-0 { + opp-peak-kBps = <12896000>; + }; + + opp-1 { + opp-peak-kBps = <14928000>; + }; + }; + }; + + pmu@90cd000 { + compatible = "qcom,qcs615-llcc-bwmon", "qcom,sc7280-llcc-bwmon"; + reg = <0x0 0x090cd000 0x0 0x1000>; + interrupts = ; + interconnects = <&mc_virt MASTER_LLCC QCOM_ICC_TAG_ACTIVE_ONLY + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ACTIVE_ONLY>; + + operating-points-v2 = <&llcc_bwmon_opp_table>; + + llcc_bwmon_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-0 { + opp-peak-kBps = <800000>; + }; + + opp-1 { + opp-peak-kBps = <1200000>; + }; + + opp-2 { + opp-peak-kBps = <1804800>; + }; + + opp-3 { + opp-peak-kBps = <2188800>; + }; + + opp-4 { + opp-peak-kBps = <2726400>; + }; + + opp-5 { + opp-peak-kBps = <3072000>; + }; + + opp-6 { + opp-peak-kBps = <4070400>; + }; + + opp-7 { + opp-peak-kBps = <5414400>; + }; + + opp-8 { + opp-peak-kBps = <6220800>; + }; + }; + }; + + sdhc_2: mmc@8804000 { + compatible = "qcom,qcs615-sdhci", "qcom,sdhci-msm-v5"; + reg = <0x0 0x08804000 0x0 0x1000>; + reg-names = "hc"; + + interrupts = , + ; + interrupt-names = "hc_irq", + "pwr_irq"; + + clocks = <&gcc GCC_SDCC2_AHB_CLK>, + <&gcc GCC_SDCC2_APPS_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", + "core", + "xo"; + + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&sdhc2_opp_table>; + iommus = <&apps_smmu 0x02a0 0x0>; + resets = <&gcc GCC_SDCC2_BCR>; + interconnects = <&aggre1_noc MASTER_SDCC_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_SDCC_2 QCOM_ICC_TAG_ACTIVE_ONLY>; + interconnect-names = "sdhc-ddr", + "cpu-sdhc"; + + qcom,dll-config = <0x0007642c>; + qcom,ddr-config = <0x80040868>; + dma-coherent; + + status = "disabled"; + + sdhc2_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-50000000 { + opp-hz = /bits/ 64 <50000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-100000000 { + opp-hz = /bits/ 64 <100000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-202000000 { + opp-hz = /bits/ 64 <202000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; + + dc_noc: interconnect@9160000 { + reg = <0x0 0x09160000 0x0 0x3200>; + compatible = "qcom,qcs615-dc-noc"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + llcc: system-cache-controller@9200000 { + compatible = "qcom,qcs615-llcc"; + reg = <0x0 0x09200000 0x0 0x50000>, + <0x0 0x09600000 0x0 0x50000>; + reg-names = "llcc0_base", + "llcc_broadcast_base"; + }; + + gem_noc: interconnect@9680000 { + reg = <0x0 0x09680000 0x0 0x3e200>; + compatible = "qcom,qcs615-gem-noc"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + pdc: interrupt-controller@b220000 { + compatible = "qcom,qcs615-pdc", "qcom,pdc"; + reg = <0x0 0x0b220000 0x0 0x30000>, + <0x0 0x17c000f0 0x0 0x64>; + qcom,pdc-ranges = <0 480 94>, <94 609 31>, <125 63 1>; + interrupt-parent = <&intc>; + #interrupt-cells = <2>; + interrupt-controller; + }; + + aoss_qmp: power-controller@c300000 { + compatible = "qcom,qcs615-aoss-qmp", "qcom,aoss-qmp"; + reg = <0x0 0x0c300000 0x0 0x400>; + interrupts = ; + mboxes = <&apss_shared 0>; + + #clock-cells = <0>; + #power-domain-cells = <1>; + }; + + sram@c3f0000 { + compatible = "qcom,rpmh-stats"; + reg = <0x0 0x0c3f0000 0x0 0x400>; + }; + + apps_smmu: iommu@15000000 { + compatible = "qcom,qcs615-smmu-500", "qcom,smmu-500", "arm,mmu-500"; + reg = <0x0 0x15000000 0x0 0x80000>; + #iommu-cells = <2>; + #global-interrupts = <1>; + dma-coherent; + + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + }; + + spmi_bus: spmi@c440000 { + compatible = "qcom,spmi-pmic-arb"; + reg = <0x0 0x0c440000 0x0 0x1100>, + <0x0 0x0c600000 0x0 0x2000000>, + <0x0 0x0e600000 0x0 0x100000>, + <0x0 0x0e700000 0x0 0xa0000>, + <0x0 0x0c40a000 0x0 0x26000>; + reg-names = "core", + "chnls", + "obsrvr", + "intr", + "cnfg"; + interrupts-extended = <&pdc 1 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "periph_irq"; + interrupt-controller; + #interrupt-cells = <4>; + #address-cells = <2>; + #size-cells = <0>; + cell-index = <0>; + qcom,channel = <0>; + qcom,ee = <0>; + }; + + intc: interrupt-controller@17a00000 { + compatible = "arm,gic-v3"; + reg = <0x0 0x17a00000 0x0 0x10000>, /* GICD */ + <0x0 0x17a60000 0x0 0x100000>; /* GICR * 8 */ + interrupts = ; + #interrupt-cells = <3>; + interrupt-controller; + #redistributor-regions = <1>; + redistributor-stride = <0x0 0x20000>; + }; + + apss_shared: mailbox@17c00000 { + compatible = "qcom,qcs615-apss-shared", + "qcom,sdm845-apss-shared"; + reg = <0x0 0x17c00000 0x0 0x1000>; + #mbox-cells = <1>; + }; + + watchdog: watchdog@17c10000 { + compatible = "qcom,apss-wdt-qcs615", "qcom,kpss-wdt"; + reg = <0x0 0x17c10000 0x0 0x1000>; + interrupts = ; + }; + + timer@17c20000 { + compatible = "arm,armv7-timer-mem"; + reg = <0x0 0x17c20000 0x0 0x1000>; + ranges = <0 0 0 0x20000000>; + #address-cells = <1>; + #size-cells = <1>; + + frame@17c21000 { + reg = <0x17c21000 0x1000>, + <0x17c22000 0x1000>; + frame-number = <0>; + interrupts = , + ; + }; + + frame@17c23000 { + reg = <0x17c23000 0x1000>; + frame-number = <1>; + interrupts = ; + status = "disabled"; + }; + + frame@17c25000 { + reg = <0x17c25000 0x1000>; + frame-number = <2>; + interrupts = ; + status = "disabled"; + }; + + frame@17c27000 { + reg = <0x17c27000 0x1000>; + frame-number = <3>; + interrupts = ; + status = "disabled"; + }; + + frame@17c29000 { + reg = <0x17c29000 0x1000>; + frame-number = <4>; + interrupts = ; + status = "disabled"; + }; + + frame@17c2b000 { + reg = <0x17c2b000 0x1000>; + frame-number = <5>; + interrupts = ; + status = "disabled"; + }; + + frame@17c2d000 { + reg = <0x17c2d000 0x1000>; + frame-number = <6>; + interrupts = ; + status = "disabled"; + }; + }; + + apps_rsc: rsc@18200000 { + compatible = "qcom,rpmh-rsc"; + reg = <0x0 0x18200000 0x0 0x10000>, + <0x0 0x18210000 0x0 0x10000>, + <0x0 0x18220000 0x0 0x10000>; + reg-names = "drv-0", + "drv-1", + "drv-2"; + + interrupts = , + , + ; + + qcom,drv-id = <2>; + qcom,tcs-offset = <0xd00>; + qcom,tcs-config = , + , + , + ; + + label = "apps_rsc"; + power-domains = <&cluster_pd>; + + apps_bcm_voter: bcm-voter { + compatible = "qcom,bcm-voter"; + }; + + rpmhcc: clock-controller { + compatible = "qcom,qcs615-rpmh-clk"; + clock-names = "xo"; + + #clock-cells = <1>; + }; + + rpmhpd: power-controller { + compatible = "qcom,qcs615-rpmhpd"; + #power-domain-cells = <1>; + operating-points-v2 = <&rpmhpd_opp_table>; + + rpmhpd_opp_table: opp-table { + compatible = "operating-points-v2"; + + rpmhpd_opp_ret: opp-0 { + opp-level = ; + }; + + rpmhpd_opp_min_svs: opp-1 { + opp-level = ; + }; + + rpmhpd_opp_low_svs: opp-2 { + opp-level = ; + }; + + rpmhpd_opp_svs: opp-3 { + opp-level = ; + }; + + rpmhpd_opp_svs_l1: opp-4 { + opp-level = ; + }; + + rpmhpd_opp_nom: opp-5 { + opp-level = ; + }; + + rpmhpd_opp_nom_l1: opp-6 { + opp-level = ; + }; + + rpmhpd_opp_nom_l2: opp-7 { + opp-level = ; + }; + + rpmhpd_opp_turbo: opp-8 { + opp-level = ; + }; + + rpmhpd_opp_turbo_l1: opp-9 { + opp-level = ; + }; + }; + }; + }; + + usb_1_hsphy: phy@88e2000 { + compatible = "qcom,qcs615-qusb2-phy"; + reg = <0x0 0x88e2000 0x0 0x180>; + + clocks = <&gcc GCC_AHB2PHY_WEST_CLK>, <&rpmhcc RPMH_CXO_CLK>; + clock-names = "cfg_ahb", "ref"; + + resets = <&gcc GCC_QUSB2PHY_PRIM_BCR>; + nvmem-cells = <&qusb2_hstx_trim>; + + #phy-cells = <0>; + + status = "disabled"; + }; + + usb_hsphy_2: phy@88e3000 { + compatible = "qcom,qcs615-qusb2-phy"; + reg = <0x0 0x088e3000 0x0 0x180>; + + clocks = <&gcc GCC_AHB2PHY_WEST_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "cfg_ahb", + "ref"; + + resets = <&gcc GCC_QUSB2PHY_SEC_BCR>; + + #phy-cells = <0>; + + status = "disabled"; + }; + + usb_qmpphy: phy@88e6000 { + compatible = "qcom,qcs615-qmp-usb3-phy"; + reg = <0x0 0x88e6000 0x0 0x1000>; + + clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, + <&gcc GCC_USB3_PRIM_CLKREF_CLK>, + <&gcc GCC_AHB2PHY_WEST_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; + clock-names = "aux", + "ref", + "cfg_ahb", + "pipe"; + + resets = <&gcc GCC_USB3_PHY_PRIM_SP0_BCR>, + <&gcc GCC_USB3PHY_PHY_PRIM_SP0_BCR>; + reset-names = "phy", "phy_phy"; + + qcom,tcsr-reg = <&tcsr 0xb244>; + + clock-output-names = "usb3_phy_pipe_clk_src"; + #clock-cells = <0>; + + #phy-cells = <0>; + + status = "disabled"; + }; + + usb_1: usb@a6f8800 { + compatible = "qcom,qcs615-dwc3", "qcom,dwc3"; + reg = <0x0 0x0a6f8800 0x0 0x400>; + + clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>, + <&gcc GCC_USB30_PRIM_MASTER_CLK>, + <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>, + <&gcc GCC_USB30_PRIM_SLEEP_CLK>, + <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>, + <&gcc GCC_USB3_PRIM_CLKREF_CLK>; + clock-names = "cfg_noc", + "core", + "iface", + "sleep", + "mock_utmi", + "xo"; + + assigned-clocks = <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>, + <&gcc GCC_USB30_PRIM_MASTER_CLK>; + assigned-clock-rates = <19200000>, <200000000>; + + interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>, + <&pdc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc 6 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "pwr_event", + "hs_phy_irq", + "dp_hs_phy_irq", + "dm_hs_phy_irq", + "ss_phy_irq"; + + power-domains = <&gcc USB30_PRIM_GDSC>; + required-opps = <&rpmhpd_opp_nom>; + + resets = <&gcc GCC_USB30_PRIM_BCR>; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + usb_1_dwc3: usb@a600000 { + compatible = "snps,dwc3"; + reg = <0x0 0x0a600000 0x0 0xcd00>; + + iommus = <&apps_smmu 0x140 0x0>; + interrupts = ; + + phys = <&usb_1_hsphy>, <&usb_qmpphy>; + phy-names = "usb2-phy", "usb3-phy"; + + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; + snps,dis_u2_susphy_quirk; + snps,dis_enblslpm_quirk; + snps,has-lpm-erratum; + snps,hird-threshold = /bits/ 8 <0x10>; + snps,usb3_lpm_capable; + }; + }; + + usb_2: usb@a8f8800 { + compatible = "qcom,qcs615-dwc3", "qcom,dwc3"; + reg = <0x0 0x0a8f8800 0x0 0x400>; + + clocks = <&gcc GCC_CFG_NOC_USB2_SEC_AXI_CLK>, + <&gcc GCC_USB20_SEC_MASTER_CLK>, + <&gcc GCC_AGGRE_USB2_SEC_AXI_CLK>, + <&gcc GCC_USB20_SEC_SLEEP_CLK>, + <&gcc GCC_USB20_SEC_MOCK_UTMI_CLK>, + <&gcc GCC_USB2_PRIM_CLKREF_CLK>; + clock-names = "cfg_noc", + "core", + "iface", + "sleep", + "mock_utmi", + "xo"; + + assigned-clocks = <&gcc GCC_USB20_SEC_MOCK_UTMI_CLK>, + <&gcc GCC_USB20_SEC_MASTER_CLK>; + assigned-clock-rates = <19200000>, <200000000>; + + interrupts-extended = <&intc GIC_SPI 663 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 662 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 11 IRQ_TYPE_EDGE_BOTH>, + <&pdc 10 IRQ_TYPE_EDGE_BOTH>; + interrupt-names = "pwr_event", + "hs_phy_irq", + "dp_hs_phy_irq", + "dm_hs_phy_irq"; + + power-domains = <&gcc USB20_SEC_GDSC>; + required-opps = <&rpmhpd_opp_nom>; + + resets = <&gcc GCC_USB20_SEC_BCR>; + + qcom,select-utmi-as-pipe-clk; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + usb_2_dwc3: usb@a800000 { + compatible = "snps,dwc3"; + reg = <0x0 0x0a800000 0x0 0xcd00>; + + iommus = <&apps_smmu 0xe0 0x0>; + interrupts = ; + + phys = <&usb_hsphy_2>; + phy-names = "usb2-phy"; + + snps,dis_u2_susphy_quirk; + snps,dis_enblslpm_quirk; + snps,has-lpm-erratum; + snps,hird-threshold = /bits/ 8 <0x10>; + + maximum-speed = "high-speed"; + }; + }; + }; + + arch_timer: timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts index 27695bd54220..7a36c90ad4ec 100644 --- a/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts +++ b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts @@ -9,6 +9,7 @@ #define PM7250B_SID 8 #define PM7250B_SID1 9 +#include #include #include #include "sc7280.dtsi" @@ -744,6 +745,46 @@ }; }; +&pm8350c_pwm { + nvmem = <&pmk8350_sdam_21>, + <&pmk8350_sdam_22>; + nvmem-names = "lpg_chan_sdam", + "lut_sdam"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "okay"; + + led@1 { + reg = <1>; + color = ; + function = LED_FUNCTION_INDICATOR; + function-enumerator = <3>; + linux,default-trigger = "none"; + default-state = "off"; + panic-indicator; + }; + + led@2 { + reg = <2>; + color = ; + function = LED_FUNCTION_INDICATOR; + function-enumerator = <2>; + linux,default-trigger = "none"; + default-state = "off"; + }; + + led@3 { + reg = <3>; + color = ; + function = LED_FUNCTION_INDICATOR; + function-enumerator = <1>; + linux,default-trigger = "none"; + default-state = "off"; + }; +}; + &pmk8350_rtc { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/qcs8300-ride.dts b/arch/arm64/boot/dts/qcom/qcs8300-ride.dts new file mode 100644 index 000000000000..b5c9f89b3435 --- /dev/null +++ b/arch/arm64/boot/dts/qcom/qcs8300-ride.dts @@ -0,0 +1,370 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +/dts-v1/; + +#include +#include + +#include "qcs8300.dtsi" +/ { + model = "Qualcomm Technologies, Inc. QCS8300 Ride"; + compatible = "qcom,qcs8300-ride", "qcom,qcs8300"; + chassis-type = "embedded"; + + aliases { + serial0 = &uart7; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; +}; + +&apps_rsc { + regulators-0 { + compatible = "qcom,pmm8654au-rpmh-regulators"; + qcom,pmic-id = "a"; + + vreg_s4a: smps4 { + regulator-name = "vreg_s4a"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_s9a: smps9 { + regulator-name = "vreg_s9a"; + regulator-min-microvolt = <1352000>; + regulator-max-microvolt = <1352000>; + regulator-initial-mode = ; + }; + + vreg_l3a: ldo3 { + regulator-name = "vreg_l3a"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l4a: ldo4 { + regulator-name = "vreg_l4a"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l5a: ldo5 { + regulator-name = "vreg_l5a"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l6a: ldo6 { + regulator-name = "vreg_l6a"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l7a: ldo7 { + regulator-name = "vreg_l7a"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l8a: ldo8 { + regulator-name = "vreg_l8a"; + regulator-min-microvolt = <2504000>; + regulator-max-microvolt = <2960000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l9a: ldo9 { + regulator-name = "vreg_l9a"; + regulator-min-microvolt = <2970000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-1 { + compatible = "qcom,pmm8654au-rpmh-regulators"; + qcom,pmic-id = "c"; + + vreg_s5c: smps5 { + regulator-name = "vreg_s5c"; + regulator-min-microvolt = <1104000>; + regulator-max-microvolt = <1104000>; + regulator-initial-mode = ; + }; + + vreg_l1c: ldo1 { + regulator-name = "vreg_l1c"; + regulator-min-microvolt = <300000>; + regulator-max-microvolt = <500000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2c: ldo2 { + regulator-name = "vreg_l2c"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <904000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l4c: ldo4 { + regulator-name = "vreg_l4c"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l6c: ldo6 { + regulator-name = "vreg_l6c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l7c: ldo7 { + regulator-name = "vreg_l7c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l8c: ldo8 { + regulator-name = "vreg_l8c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l9c: ldo9 { + regulator-name = "vreg_l9c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; +}; + +ðernet0 { + phy-mode = "2500base-x"; + phy-handle = <&phy0>; + + pinctrl-0 = <ðernet0_default>; + pinctrl-names = "default"; + + snps,mtl-rx-config = <&mtl_rx_setup>; + snps,mtl-tx-config = <&mtl_tx_setup>; + snps,ps-speed = <1000>; + + status = "okay"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + phy0: phy@8 { + compatible = "ethernet-phy-id31c3.1c33"; + reg = <0x8>; + device_type = "ethernet-phy"; + interrupts-extended = <&tlmm 4 IRQ_TYPE_EDGE_FALLING>; + reset-gpios = <&tlmm 31 GPIO_ACTIVE_LOW>; + reset-assert-us = <11000>; + reset-deassert-us = <70000>; + }; + }; + + mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <4>; + snps,rx-sched-sp; + + queue0 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x0>; + snps,route-up; + snps,priority = <0x1>; + }; + + queue1 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x1>; + snps,route-ptp; + }; + + queue2 { + snps,avb-algorithm; + snps,map-to-dma-channel = <0x2>; + snps,route-avcp; + }; + + queue3 { + snps,avb-algorithm; + snps,map-to-dma-channel = <0x3>; + snps,priority = <0xc>; + }; + }; + + mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <4>; + snps,tx-sched-sp; + + queue0 { + snps,dcb-algorithm; + }; + + queue1 { + snps,dcb-algorithm; + }; + + queue2 { + snps,avb-algorithm; + snps,send_slope = <0x1000>; + snps,idle_slope = <0x1000>; + snps,high_credit = <0x3e800>; + snps,low_credit = <0xffc18000>; + }; + + queue3 { + snps,avb-algorithm; + snps,send_slope = <0x1000>; + snps,idle_slope = <0x1000>; + snps,high_credit = <0x3e800>; + snps,low_credit = <0xffc18000>; + }; + }; +}; + +&qupv3_id_0 { + status = "okay"; +}; + +&remoteproc_adsp { + firmware-name = "qcom/qcs8300/adsp.mbn"; + status = "okay"; +}; + +&remoteproc_cdsp { + firmware-name = "qcom/qcs8300/cdsp0.mbn"; + status = "okay"; +}; + +&remoteproc_gpdsp { + firmware-name = "qcom/qcs8300/gpdsp0.mbn"; + status = "okay"; +}; + +&serdes0 { + phy-supply = <&vreg_l5a>; + status = "okay"; +}; + +&tlmm { + ethernet0_default: ethernet0-default-state { + ethernet0_mdc: ethernet0-mdc-pins { + pins = "gpio5"; + function = "emac0_mdc"; + drive-strength = <16>; + bias-pull-up; + }; + + ethernet0_mdio: ethernet0-mdio-pins { + pins = "gpio6"; + function = "emac0_mdio"; + drive-strength = <16>; + bias-pull-up; + }; + }; +}; + +&uart7 { + status = "okay"; +}; + +&ufs_mem_hc { + reset-gpios = <&tlmm 133 GPIO_ACTIVE_LOW>; + vcc-supply = <&vreg_l8a>; + vcc-max-microamp = <1100000>; + vccq-supply = <&vreg_l4c>; + vccq-max-microamp = <1200000>; + status = "okay"; +}; + +&ufs_mem_phy { + vdda-phy-supply = <&vreg_l4a>; + vdda-pll-supply = <&vreg_l5a>; + status = "okay"; +}; + +&usb_1_hsphy { + vdda-pll-supply = <&vreg_l7a>; + vdda18-supply = <&vreg_l7c>; + vdda33-supply = <&vreg_l9a>; + + status = "okay"; +}; + +&usb_qmpphy { + vdda-phy-supply = <&vreg_l7a>; + vdda-pll-supply = <&vreg_l5a>; + + status = "okay"; +}; + +&usb_1 { + status = "okay"; +}; + +&usb_1_dwc3 { + dr_mode = "peripheral"; +}; diff --git a/arch/arm64/boot/dts/qcom/qcs8300.dtsi b/arch/arm64/boot/dts/qcom/qcs8300.dtsi new file mode 100644 index 000000000000..4a057f7c0d9f --- /dev/null +++ b/arch/arm64/boot/dts/qcom/qcs8300.dtsi @@ -0,0 +1,3548 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/ { + interrupt-parent = <&intc>; + #address-cells = <2>; + #size-cells = <2>; + + clocks { + xo_board_clk: xo-board-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <38400000>; + }; + + sleep_clk: sleep-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <32000>; + }; + }; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a78c"; + reg = <0x0 0x0>; + enable-method = "psci"; + next-level-cache = <&l2_0>; + power-domains = <&cpu_pd0>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1946>; + dynamic-power-coefficient = <472>; + + l2_0: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu1: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a78c"; + reg = <0x0 0x100>; + enable-method = "psci"; + next-level-cache = <&l2_1>; + power-domains = <&cpu_pd1>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1946>; + dynamic-power-coefficient = <472>; + + l2_1: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu2: cpu@200 { + device_type = "cpu"; + compatible = "arm,cortex-a78c"; + reg = <0x0 0x200>; + enable-method = "psci"; + next-level-cache = <&l2_2>; + power-domains = <&cpu_pd2>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1946>; + dynamic-power-coefficient = <507>; + + l2_2: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu3: cpu@300 { + device_type = "cpu"; + compatible = "arm,cortex-a78c"; + reg = <0x0 0x300>; + enable-method = "psci"; + next-level-cache = <&l2_3>; + power-domains = <&cpu_pd3>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1946>; + dynamic-power-coefficient = <507>; + + l2_3: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu4: cpu@10000 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x10000>; + enable-method = "psci"; + next-level-cache = <&l2_4>; + power-domains = <&cpu_pd4>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + + l2_4: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_1>; + }; + }; + + cpu5: cpu@10100 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x10100>; + enable-method = "psci"; + next-level-cache = <&l2_5>; + power-domains = <&cpu_pd5>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + + l2_5: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_1>; + }; + }; + + cpu6: cpu@10200 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x10200>; + enable-method = "psci"; + next-level-cache = <&l2_6>; + power-domains = <&cpu_pd6>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + + l2_6: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_1>; + }; + }; + + cpu7: cpu@10300 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x10300>; + enable-method = "psci"; + next-level-cache = <&l2_7>; + power-domains = <&cpu_pd7>; + power-domain-names = "psci"; + capacity-dmips-mhz = <1024>; + dynamic-power-coefficient = <100>; + + l2_7: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_1>; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu4>; + }; + + core1 { + cpu = <&cpu5>; + }; + + core2 { + cpu = <&cpu6>; + }; + + core3 { + cpu = <&cpu7>; + }; + }; + }; + + l3_0: l3-cache-0 { + compatible = "cache"; + cache-level = <3>; + cache-unified; + }; + + l3_1: l3-cache-1 { + compatible = "cache"; + cache-level = <3>; + cache-unified; + }; + + idle-states { + entry-method = "psci"; + + little_cpu_sleep_0: cpu-sleep-0-0 { + compatible = "arm,idle-state"; + idle-state-name = "silver-power-collapse"; + arm,psci-suspend-param = <0x40000003>; + entry-latency-us = <449>; + exit-latency-us = <801>; + min-residency-us = <1574>; + local-timer-stop; + }; + + little_cpu_sleep_1: cpu-sleep-0-1 { + compatible = "arm,idle-state"; + idle-state-name = "silver-rail-power-collapse"; + arm,psci-suspend-param = <0x40000004>; + entry-latency-us = <602>; + exit-latency-us = <961>; + min-residency-us = <4288>; + local-timer-stop; + }; + + big_cpu_sleep_0: cpu-sleep-1-0 { + compatible = "arm,idle-state"; + idle-state-name = "gold-power-collapse"; + arm,psci-suspend-param = <0x40000003>; + entry-latency-us = <549>; + exit-latency-us = <901>; + min-residency-us = <1774>; + local-timer-stop; + }; + + big_cpu_sleep_1: cpu-sleep-1-1 { + compatible = "arm,idle-state"; + idle-state-name = "gold-rail-power-collapse"; + arm,psci-suspend-param = <0x40000004>; + entry-latency-us = <702>; + exit-latency-us = <1061>; + min-residency-us = <4488>; + local-timer-stop; + }; + }; + + domain-idle-states { + silver_cluster_sleep: cluster-sleep-0 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x41000044>; + entry-latency-us = <2552>; + exit-latency-us = <2848>; + min-residency-us = <5908>; + }; + + gold_cluster_sleep: cluster-sleep-1 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x41000044>; + entry-latency-us = <2752>; + exit-latency-us = <3048>; + min-residency-us = <6118>; + }; + + system_sleep: domain-sleep { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x42000144>; + entry-latency-us = <3263>; + exit-latency-us = <6562>; + min-residency-us = <9987>; + }; + }; + }; + + dummy_eud: dummy-sink { + compatible = "arm,coresight-dummy-sink"; + + in-ports { + port { + eud_in: endpoint { + remote-endpoint = <&swao_rep_out1>; + }; + }; + }; + }; + + firmware { + scm: scm { + compatible = "qcom,scm-qcs8300", "qcom,scm"; + qcom,dload-mode = <&tcsr 0x13000>; + }; + }; + + memory@80000000 { + device_type = "memory"; + /* We expect the bootloader to fill in the size */ + reg = <0x0 0x80000000 0x0 0x0>; + }; + + clk_virt: interconnect-0 { + compatible = "qcom,qcs8300-clk-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + mc_virt: interconnect-1 { + compatible = "qcom,qcs8300-mc-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + pmu-a55 { + compatible = "arm,cortex-a55-pmu"; + interrupts = ; + }; + + pmu-a78 { + compatible = "arm,cortex-a78-pmu"; + interrupts = ; + }; + + psci { + compatible = "arm,psci-1.0"; + method = "smc"; + + cpu_pd0: power-domain-cpu0 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd0>; + domain-idle-states = <&big_cpu_sleep_0 &big_cpu_sleep_1>; + }; + + cpu_pd1: power-domain-cpu1 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd0>; + domain-idle-states = <&big_cpu_sleep_0 &big_cpu_sleep_1>; + }; + + cpu_pd2: power-domain-cpu2 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd0>; + domain-idle-states = <&big_cpu_sleep_0 &big_cpu_sleep_1>; + }; + + cpu_pd3: power-domain-cpu3 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd0>; + domain-idle-states = <&big_cpu_sleep_0 &big_cpu_sleep_1>; + }; + + cpu_pd4: power-domain-cpu4 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd1>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cpu_pd5: power-domain-cpu5 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd1>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cpu_pd6: power-domain-cpu6 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd1>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cpu_pd7: power-domain-cpu7 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd1>; + domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; + }; + + cluster_pd0: power-domain-cluster0 { + #power-domain-cells = <0>; + power-domains = <&system_pd>; + domain-idle-states = <&gold_cluster_sleep>; + }; + + cluster_pd1: power-domain-cluster1 { + #power-domain-cells = <0>; + power-domains = <&system_pd>; + domain-idle-states = <&silver_cluster_sleep>; + }; + + system_pd: power-domain-system { + #power-domain-cells = <0>; + domain-idle-states = <&system_sleep>; + }; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + aop_image_mem: aop-image-region@90800000 { + reg = <0x0 0x90800000 0x0 0x60000>; + no-map; + }; + + aop_cmd_db_mem: aop-cmd-db-region@90860000 { + compatible = "qcom,cmd-db"; + reg = <0x0 0x90860000 0x0 0x20000>; + no-map; + }; + + smem_mem: smem@90900000 { + compatible = "qcom,smem"; + reg = <0x0 0x90900000 0x0 0x200000>; + no-map; + hwlocks = <&tcsr_mutex 3>; + }; + + lpass_machine_learning_mem: lpass-machine-learning-region@93b00000 { + reg = <0x0 0x93b00000 0x0 0xf00000>; + no-map; + }; + + adsp_rpc_remote_heap_mem: adsp-rpc-remote-heap-region@94a00000 { + reg = <0x0 0x94a00000 0x0 0x800000>; + no-map; + }; + + camera_mem: camera-region@95200000 { + reg = <0x0 0x95200000 0x0 0x500000>; + no-map; + }; + + adsp_mem: adsp-region@95c00000 { + no-map; + reg = <0x0 0x95c00000 0x0 0x1e00000>; + }; + + q6_adsp_dtb_mem: q6-adsp-dtb-region@97a00000 { + reg = <0x0 0x97a00000 0x0 0x80000>; + no-map; + }; + + q6_gpdsp_dtb_mem: q6-gpdsp-dtb-region@97a80000 { + reg = <0x0 0x97a80000 0x0 0x80000>; + no-map; + }; + + gpdsp_mem: gpdsp-region@97b00000 { + reg = <0x0 0x97b00000 0x0 0x1e00000>; + no-map; + }; + + q6_cdsp_dtb_mem: q6-cdsp-dtb-region@99900000 { + reg = <0x0 0x99900000 0x0 0x80000>; + no-map; + }; + + cdsp_mem: cdsp-region@99980000 { + reg = <0x0 0x99980000 0x0 0x1e00000>; + no-map; + }; + + gpu_microcode_mem: gpu-microcode-region@9b780000 { + reg = <0x0 0x9b780000 0x0 0x2000>; + no-map; + }; + + cvp_mem: cvp-region@9b782000 { + reg = <0x0 0x9b782000 0x0 0x700000>; + no-map; + }; + + video_mem: video-region@9be82000 { + reg = <0x0 0x9be82000 0x0 0x700000>; + no-map; + }; + }; + + smp2p-adsp { + compatible = "qcom,smp2p"; + interrupts-extended = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_SMP2P + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_SMP2P>; + + qcom,smem = <443>, <429>; + qcom,local-pid = <0>; + qcom,remote-pid = <2>; + + smp2p_adsp_in: slave-kernel { + qcom,entry-name = "slave-kernel"; + interrupt-controller; + #interrupt-cells = <2>; + }; + + smp2p_adsp_out: master-kernel { + qcom,entry-name = "master-kernel"; + #qcom,smem-state-cells = <1>; + }; + }; + + smp2p-cdsp { + compatible = "qcom,smp2p"; + interrupts-extended = <&ipcc IPCC_CLIENT_CDSP + IPCC_MPROC_SIGNAL_SMP2P + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_CDSP + IPCC_MPROC_SIGNAL_SMP2P>; + + qcom,smem = <94>, <432>; + qcom,local-pid = <0>; + qcom,remote-pid = <5>; + + smp2p_cdsp_in: slave-kernel { + qcom,entry-name = "slave-kernel"; + interrupt-controller; + #interrupt-cells = <2>; + }; + + smp2p_cdsp_out: master-kernel { + qcom,entry-name = "master-kernel"; + #qcom,smem-state-cells = <1>; + }; + }; + + smp2p-gpdsp { + compatible = "qcom,smp2p"; + interrupts-extended = <&ipcc IPCC_CLIENT_GPDSP0 + IPCC_MPROC_SIGNAL_SMP2P + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_GPDSP0 + IPCC_MPROC_SIGNAL_SMP2P>; + + qcom,smem = <617>, <616>; + qcom,local-pid = <0>; + qcom,remote-pid = <17>; + + smp2p_gpdsp_in: slave-kernel { + qcom,entry-name = "slave-kernel"; + interrupt-controller; + #interrupt-cells = <2>; + }; + + smp2p_gpdsp_out: master-kernel { + qcom,entry-name = "master-kernel"; + #qcom,smem-state-cells = <1>; + }; + }; + + soc: soc@0 { + compatible = "simple-bus"; + ranges = <0 0 0 0 0x10 0>; + #address-cells = <2>; + #size-cells = <2>; + + gcc: clock-controller@100000 { + compatible = "qcom,qcs8300-gcc"; + reg = <0x0 0x00100000 0x0 0xc7018>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&sleep_clk>, + <0>, + <0>, + <0>, + <0>, + <0>, + <0>, + <0>, + <0>; + }; + + ipcc: mailbox@408000 { + compatible = "qcom,qcs8300-ipcc", "qcom,ipcc"; + reg = <0x0 0x408000 0x0 0x1000>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <3>; + #mbox-cells = <2>; + }; + + qfprom: efuse@784000 { + compatible = "qcom,qcs8300-qfprom", "qcom,qfprom"; + reg = <0x0 0x00784000 0x0 0x1200>; + #address-cells = <1>; + #size-cells = <1>; + }; + + qupv3_id_0: geniqup@9c0000 { + compatible = "qcom,geni-se-qup"; + reg = <0x0 0x9c0000 0x0 0x2000>; + ranges; + clocks = <&gcc GCC_QUPV3_WRAP_0_M_AHB_CLK>, + <&gcc GCC_QUPV3_WRAP_0_S_AHB_CLK>; + clock-names = "m-ahb", + "s-ahb"; + #address-cells = <2>; + #size-cells = <2>; + status = "disabled"; + + uart7: serial@99c000 { + compatible = "qcom,geni-debug-uart"; + reg = <0x0 0x0099c000 0x0 0x4000>; + clocks = <&gcc GCC_QUPV3_WRAP0_S7_CLK>; + clock-names = "se"; + pinctrl-0 = <&qup_uart7_default>; + pinctrl-names = "default"; + interrupts = ; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_0 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + status = "disabled"; + }; + }; + + rng: rng@10d2000 { + compatible = "qcom,qcs8300-trng", "qcom,trng"; + reg = <0x0 0x010d2000 0x0 0x1000>; + }; + + config_noc: interconnect@14c0000 { + compatible = "qcom,qcs8300-config-noc"; + reg = <0x0 0x014c0000 0x0 0x13080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + system_noc: interconnect@1680000 { + compatible = "qcom,qcs8300-system-noc"; + reg = <0x0 0x01680000 0x0 0x15080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + aggre1_noc: interconnect@16c0000 { + compatible = "qcom,qcs8300-aggre1-noc"; + reg = <0x0 0x016c0000 0x0 0x17080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + aggre2_noc: interconnect@1700000 { + compatible = "qcom,qcs8300-aggre2-noc"; + reg = <0x0 0x01700000 0x0 0x1a080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + pcie_anoc: interconnect@1760000 { + compatible = "qcom,qcs8300-pcie-anoc"; + reg = <0x0 0x01760000 0x0 0xc080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + gpdsp_anoc: interconnect@1780000 { + compatible = "qcom,qcs8300-gpdsp-anoc"; + reg = <0x0 0x01780000 0x0 0xd080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + mmss_noc: interconnect@17a0000 { + compatible = "qcom,qcs8300-mmss-noc"; + reg = <0x0 0x017a0000 0x0 0x40000>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + ufs_mem_hc: ufs@1d84000 { + compatible = "qcom,qcs8300-ufshc", "qcom,ufshc", "jedec,ufs-2.0"; + reg = <0x0 0x01d84000 0x0 0x3000>; + interrupts = ; + phys = <&ufs_mem_phy>; + phy-names = "ufsphy"; + lanes-per-direction = <2>; + #reset-cells = <1>; + resets = <&gcc GCC_UFS_PHY_BCR>; + reset-names = "rst"; + + power-domains = <&gcc GCC_UFS_PHY_GDSC>; + required-opps = <&rpmhpd_opp_nom>; + + iommus = <&apps_smmu 0x100 0x0>; + dma-coherent; + + interconnects = <&aggre1_noc MASTER_UFS_MEM QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_UFS_MEM_CFG QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "ufs-ddr", + "cpu-ufs"; + + clocks = <&gcc GCC_UFS_PHY_AXI_CLK>, + <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>, + <&gcc GCC_UFS_PHY_AHB_CLK>, + <&gcc GCC_UFS_PHY_UNIPRO_CORE_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>, + <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>, + <&gcc GCC_UFS_PHY_RX_SYMBOL_1_CLK>; + clock-names = "core_clk", + "bus_aggr_clk", + "iface_clk", + "core_clk_unipro", + "ref_clk", + "tx_lane0_sync_clk", + "rx_lane0_sync_clk", + "rx_lane1_sync_clk"; + freq-table-hz = <75000000 300000000>, + <0 0>, + <0 0>, + <75000000 300000000>, + <0 0>, + <0 0>, + <0 0>, + <0 0>; + qcom,ice = <&ice>; + status = "disabled"; + }; + + ufs_mem_phy: phy@1d87000 { + compatible = "qcom,qcs8300-qmp-ufs-phy", "qcom,sa8775p-qmp-ufs-phy"; + reg = <0x0 0x01d87000 0x0 0xe10>; + /* + * Yes, GCC_EDP_REF_CLKREF_EN is correct in qref. It + * enables the CXO clock to eDP *and* UFS PHY. + */ + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_UFS_PHY_PHY_AUX_CLK>, + <&gcc GCC_EDP_REF_CLKREF_EN>; + clock-names = "ref", + "ref_aux", + "qref"; + power-domains = <&gcc GCC_UFS_PHY_GDSC>; + + resets = <&ufs_mem_hc 0>; + reset-names = "ufsphy"; + + #phy-cells = <0>; + status = "disabled"; + }; + + cryptobam: dma-controller@1dc4000 { + compatible = "qcom,bam-v1.7.4", "qcom,bam-v1.7.0"; + reg = <0x0 0x01dc4000 0x0 0x28000>; + interrupts = ; + #dma-cells = <1>; + qcom,ee = <0>; + qcom,controlled-remotely; + num-channels = <20>; + qcom,num-ees = <4>; + iommus = <&apps_smmu 0x480 0x00>, + <&apps_smmu 0x481 0x00>; + }; + + crypto: crypto@1dfa000 { + compatible = "qcom,qcs8300-qce", "qcom,qce"; + reg = <0x0 0x01dfa000 0x0 0x6000>; + dmas = <&cryptobam 4>, <&cryptobam 5>; + dma-names = "rx", "tx"; + iommus = <&apps_smmu 0x480 0x00>, + <&apps_smmu 0x481 0x00>; + interconnects = <&aggre2_noc MASTER_CRYPTO_CORE0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "memory"; + }; + + ice: crypto@1d88000 { + compatible = "qcom,qcs8300-inline-crypto-engine", + "qcom,inline-crypto-engine"; + reg = <0x0 0x01d88000 0x0 0x18000>; + clocks = <&gcc GCC_UFS_PHY_ICE_CORE_CLK>; + }; + + tcsr_mutex: hwlock@1f40000 { + compatible = "qcom,tcsr-mutex"; + reg = <0x0 0x01f40000 0x0 0x20000>; + #hwlock-cells = <1>; + }; + + tcsr: syscon@1fc0000 { + compatible = "qcom,qcs8300-tcsr", "syscon"; + reg = <0x0 0x1fc0000 0x0 0x30000>; + }; + + remoteproc_adsp: remoteproc@3000000 { + compatible = "qcom,qcs8300-adsp-pas", "qcom,sa8775p-adsp-pas"; + reg = <0x0 0x3000000 0x0 0x00100>; + + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", + "fatal", + "ready", + "handover", + "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + power-domains = <&rpmhpd RPMHPD_LCX>, + <&rpmhpd RPMHPD_LMX>; + power-domain-names = "lcx", + "lmx"; + + memory-region = <&adsp_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_adsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + remoteproc_adsp_glink: glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + label = "lpass"; + qcom,remote-pid = <2>; + + fastrpc { + compatible = "qcom,fastrpc"; + qcom,glink-channels = "fastrpcglink-apps-dsp"; + label = "adsp"; + memory-region = <&adsp_rpc_remote_heap_mem>; + qcom,vmids = ; + #address-cells = <1>; + #size-cells = <0>; + + compute-cb@3 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <3>; + iommus = <&apps_smmu 0x2003 0x0>; + dma-coherent; + }; + + compute-cb@4 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <4>; + iommus = <&apps_smmu 0x2004 0x0>; + dma-coherent; + }; + + compute-cb@5 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <5>; + iommus = <&apps_smmu 0x2005 0x0>; + dma-coherent; + }; + }; + }; + }; + + lpass_ag_noc: interconnect@3c40000 { + compatible = "qcom,qcs8300-lpass-ag-noc"; + reg = <0x0 0x03c40000 0x0 0x17200>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + stm@4002000 { + compatible = "arm,coresight-stm", "arm,primecell"; + reg = <0x0 0x04002000 0x0 0x1000>, + <0x0 0x16280000 0x0 0x180000>; + reg-names = "stm-base", + "stm-stimulus-base"; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + out-ports { + port { + stm_out: endpoint { + remote-endpoint = <&funnel0_in7>; + }; + }; + }; + }; + + tpda@4004000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x04004000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@1 { + reg = <1>; + + qdss_tpda_in1: endpoint { + remote-endpoint = <&qdss_tpdm1_out>; + }; + }; + }; + + out-ports { + port { + qdss_tpda_out: endpoint { + remote-endpoint = <&funnel0_in6>; + }; + }; + }; + }; + + tpdm@400f000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x0400f000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + qdss_tpdm1_out: endpoint { + remote-endpoint = <&qdss_tpda_in1>; + }; + }; + }; + }; + + funnel@4041000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04041000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@6 { + reg = <6>; + + funnel0_in6: endpoint { + remote-endpoint = <&qdss_tpda_out>; + }; + }; + + port@7 { + reg = <7>; + + funnel0_in7: endpoint { + remote-endpoint = <&stm_out>; + }; + }; + }; + + out-ports { + port { + funnel0_out: endpoint { + remote-endpoint = <&qdss_funnel_in0>; + }; + }; + }; + }; + + funnel@4042000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04042000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@4 { + reg = <4>; + + funnel1_in4: endpoint { + remote-endpoint = <&apss_funnel1_out>; + }; + }; + + port@5 { + reg = <5>; + + funnel1_in5: endpoint { + remote-endpoint = <&dlct0_funnel_out>; + }; + }; + + port@6 { + reg = <6>; + + funnel1_in6: endpoint { + remote-endpoint = <&dlmm_funnel_out>; + }; + }; + + port@7 { + reg = <7>; + + funnel1_in7: endpoint { + remote-endpoint = <&dlst_ch_funnel_out>; + }; + }; + }; + + out-ports { + port { + funnel1_out: endpoint { + remote-endpoint = <&qdss_funnel_in1>; + }; + }; + }; + }; + + funnel@4045000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04045000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + qdss_funnel_in0: endpoint { + remote-endpoint = <&funnel0_out>; + }; + }; + + port@1 { + reg = <1>; + + qdss_funnel_in1: endpoint { + remote-endpoint = <&funnel1_out>; + }; + }; + }; + + out-ports { + port { + qdss_funnel_out: endpoint { + remote-endpoint = <&aoss_funnel_in7>; + }; + }; + }; + }; + + tpdm@4841000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04841000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + prng_tpdm_out: endpoint { + remote-endpoint = <&dlct0_tpda_in19>; + }; + }; + }; + }; + + tpdm@4850000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04850000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + pimem_tpdm_out: endpoint { + remote-endpoint = <&dlct0_tpda_in25>; + }; + }; + }; + }; + + tpdm@4860000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04860000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + dlst_ch_tpdm0_out: endpoint { + remote-endpoint = <&dlst_ch_tpda_in8>; + }; + }; + }; + }; + + tpda@4864000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x04864000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@8 { + reg = <8>; + + dlst_ch_tpda_in8: endpoint { + remote-endpoint = <&dlst_ch_tpdm0_out>; + }; + }; + }; + + out-ports { + port { + dlst_ch_tpda_out: endpoint { + remote-endpoint = <&dlst_ch_funnel_in0>; + }; + }; + }; + }; + + funnel@4865000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04865000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + dlst_ch_funnel_in0: endpoint { + remote-endpoint = <&dlst_ch_tpda_out>; + }; + }; + + port@4 { + reg = <4>; + + dlst_ch_funnel_in4: endpoint { + remote-endpoint = <&dlst_funnel_out>; + }; + }; + + port@6 { + reg = <6>; + + dlst_ch_funnel_in6: endpoint { + remote-endpoint = <&gdsp_funnel_out>; + }; + }; + }; + + out-ports { + port { + dlst_ch_funnel_out: endpoint { + remote-endpoint = <&funnel1_in7>; + }; + }; + }; + }; + + tpdm@4980000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04980000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + turing2_tpdm_out: endpoint { + remote-endpoint = <&turing2_funnel_in0>; + }; + }; + }; + }; + + funnel@4983000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04983000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + turing2_funnel_in0: endpoint { + remote-endpoint = <&turing2_tpdm_out>; + }; + }; + }; + + out-ports { + port { + turing2_funnel_out0: endpoint { + remote-endpoint = <&gdsp_tpda_in5>; + }; + }; + }; + }; + + tpdm@4ac0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04ac0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + dlmm_tpdm0_out: endpoint { + remote-endpoint = <&dlmm_tpda_in27>; + }; + }; + }; + }; + + tpda@4ac4000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x04ac4000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@1b { + reg = <27>; + + dlmm_tpda_in27: endpoint { + remote-endpoint = <&dlmm_tpdm0_out>; + }; + }; + }; + + out-ports { + port { + dlmm_tpda_out: endpoint { + remote-endpoint = <&dlmm_funnel_in0>; + }; + }; + }; + }; + + funnel@4ac5000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04ac5000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + dlmm_funnel_in0: endpoint { + remote-endpoint = <&dlmm_tpda_out>; + }; + }; + }; + + out-ports { + port { + dlmm_funnel_out: endpoint { + remote-endpoint = <&funnel1_in6>; + }; + }; + }; + }; + + tpdm@4ad0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04ad0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + dlct0_tpdm0_out: endpoint { + remote-endpoint = <&dlct0_tpda_in26>; + }; + }; + }; + }; + + tpda@4ad3000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x04ad3000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@13 { + reg = <19>; + + dlct0_tpda_in19: endpoint { + remote-endpoint = <&prng_tpdm_out>; + }; + }; + + port@19 { + reg = <25>; + + dlct0_tpda_in25: endpoint { + remote-endpoint = <&pimem_tpdm_out>; + }; + }; + + port@1a { + reg = <26>; + + dlct0_tpda_in26: endpoint { + remote-endpoint = <&dlct0_tpdm0_out>; + }; + }; + }; + + out-ports { + port { + dlct0_tpda_out: endpoint { + remote-endpoint = <&dlct0_funnel_in0>; + }; + }; + }; + }; + + funnel@4ad4000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04ad4000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + dlct0_funnel_in0: endpoint { + remote-endpoint = <&dlct0_tpda_out>; + }; + }; + + port@4 { + reg = <4>; + + dlct0_funnel_in4: endpoint { + remote-endpoint = <&ddr_funnel5_out>; + }; + }; + }; + + out-ports { + port { + dlct0_funnel_out: endpoint { + remote-endpoint = <&funnel1_in5>; + }; + }; + }; + }; + + funnel@4b04000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04b04000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@6 { + reg = <6>; + + aoss_funnel_in6: endpoint { + remote-endpoint = <&aoss_tpda_out>; + }; + }; + + port@7 { + reg = <7>; + + aoss_funnel_in7: endpoint { + remote-endpoint = <&qdss_funnel_out>; + }; + }; + }; + + out-ports { + port { + aoss_funnel_out: endpoint { + remote-endpoint = <&etf0_in>; + }; + }; + }; + }; + + tmc_etf: tmc@4b05000 { + compatible = "arm,coresight-tmc", "arm,primecell"; + reg = <0x0 0x04b05000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + etf0_in: endpoint { + remote-endpoint = <&aoss_funnel_out>; + }; + }; + }; + + out-ports { + port { + etf0_out: endpoint { + remote-endpoint = <&swao_rep_in>; + }; + }; + }; + }; + + replicator@4b06000 { + compatible = "arm,coresight-dynamic-replicator", "arm,primecell"; + reg = <0x0 0x04b06000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + swao_rep_in: endpoint { + remote-endpoint = <&etf0_out>; + }; + }; + }; + + out-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@1 { + reg = <1>; + + swao_rep_out1: endpoint { + remote-endpoint = <&eud_in>; + }; + }; + }; + }; + + tpda@4b08000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x04b08000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + aoss_tpda_in0: endpoint { + remote-endpoint = <&aoss_tpdm0_out>; + }; + }; + + port@1 { + reg = <1>; + + aoss_tpda_in1: endpoint { + remote-endpoint = <&aoss_tpdm1_out>; + }; + }; + + port@2 { + reg = <2>; + + aoss_tpda_in2: endpoint { + remote-endpoint = <&aoss_tpdm2_out>; + }; + }; + + port@3 { + reg = <3>; + + aoss_tpda_in3: endpoint { + remote-endpoint = <&aoss_tpdm3_out>; + }; + }; + + port@4 { + reg = <4>; + + aoss_tpda_in4: endpoint { + remote-endpoint = <&aoss_tpdm4_out>; + }; + }; + }; + + out-ports { + port { + aoss_tpda_out: endpoint { + remote-endpoint = <&aoss_funnel_in6>; + }; + }; + }; + }; + + tpdm@4b09000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04b09000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm0_out: endpoint { + remote-endpoint = <&aoss_tpda_in0>; + }; + }; + }; + }; + + tpdm@4b0a000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04b0a000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm1_out: endpoint { + remote-endpoint = <&aoss_tpda_in1>; + }; + }; + }; + }; + + tpdm@4b0b000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04b0b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm2_out: endpoint { + remote-endpoint = <&aoss_tpda_in2>; + }; + }; + }; + }; + + tpdm@4b0c000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04b0c000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm3_out: endpoint { + remote-endpoint = <&aoss_tpda_in3>; + }; + }; + }; + }; + + tpdm@4b0d000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04b0d000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm4_out: endpoint { + remote-endpoint = <&aoss_tpda_in4>; + }; + }; + }; + }; + + cti@4b13000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x04b13000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + tpdm@4b80000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04b80000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + turing0_tpdm0_out: endpoint { + remote-endpoint = <&turing0_tpda_in0>; + }; + }; + }; + }; + + tpda@4b86000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x04b86000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + turing0_tpda_in0: endpoint { + remote-endpoint = <&turing0_tpdm0_out>; + }; + }; + }; + + out-ports { + port { + turing0_tpda_out: endpoint { + remote-endpoint = <&turing0_funnel_in0>; + }; + }; + }; + }; + + funnel@4b87000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04b87000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + turing0_funnel_in0: endpoint { + remote-endpoint = <&turing0_tpda_out>; + }; + }; + }; + + out-ports { + port { + turing0_funnel_out: endpoint { + remote-endpoint = <&gdsp_funnel_in4>; + }; + }; + }; + }; + + cti@4b8b000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x04b8b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + tpdm@4c40000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04c40000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + gdsp_tpdm0_out: endpoint { + remote-endpoint = <&gdsp_tpda_in8>; + }; + }; + }; + }; + + tpda@4c44000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x04c44000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@5 { + reg = <5>; + + gdsp_tpda_in5: endpoint { + remote-endpoint = <&turing2_funnel_out0>; + }; + }; + + port@8 { + reg = <8>; + + gdsp_tpda_in8: endpoint { + remote-endpoint = <&gdsp_tpdm0_out>; + }; + }; + }; + + out-ports { + port { + gdsp_tpda_out: endpoint { + remote-endpoint = <&gdsp_funnel_in0>; + }; + }; + }; + }; + + funnel@4c45000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04c45000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + gdsp_funnel_in0: endpoint { + remote-endpoint = <&gdsp_tpda_out>; + }; + }; + + port@4 { + reg = <4>; + + gdsp_funnel_in4: endpoint { + remote-endpoint = <&turing0_funnel_out>; + }; + }; + }; + + out-ports { + port { + gdsp_funnel_out: endpoint { + remote-endpoint = <&dlst_ch_funnel_in6>; + }; + }; + }; + }; + + tpdm@4c50000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04c50000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + dlst_tpdm0_out: endpoint { + remote-endpoint = <&dlst_tpda_in8>; + }; + }; + }; + }; + + tpda@4c54000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x04c54000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@8 { + reg = <8>; + + dlst_tpda_in8: endpoint { + remote-endpoint = <&dlst_tpdm0_out>; + }; + }; + }; + + out-ports { + port { + dlst_tpda_out: endpoint { + remote-endpoint = <&dlst_funnel_in0>; + }; + }; + }; + }; + + funnel@4c55000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04c55000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + dlst_funnel_in0: endpoint { + remote-endpoint = <&dlst_tpda_out>; + }; + }; + }; + + out-ports { + port { + dlst_funnel_out: endpoint { + remote-endpoint = <&dlst_ch_funnel_in4>; + }; + }; + }; + }; + + tpdm@4e00000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04e00000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + ddr_tpdm3_out: endpoint { + remote-endpoint = <&ddr_tpda_in4>; + }; + }; + }; + }; + + tpda@4e03000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x04e03000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + ddr_tpda_in0: endpoint { + remote-endpoint = <&ddr_funnel0_out0>; + }; + }; + + port@1 { + reg = <1>; + + ddr_tpda_in1: endpoint { + remote-endpoint = <&ddr_funnel1_out0>; + }; + }; + + port@4 { + reg = <4>; + + ddr_tpda_in4: endpoint { + remote-endpoint = <&ddr_tpdm3_out>; + }; + }; + }; + + out-ports { + port { + ddr_tpda_out: endpoint { + remote-endpoint = <&ddr_funnel5_in0>; + }; + }; + }; + }; + + funnel@4e04000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04e04000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + ddr_funnel5_in0: endpoint { + remote-endpoint = <&ddr_tpda_out>; + }; + }; + }; + + out-ports { + port { + ddr_funnel5_out: endpoint { + remote-endpoint = <&dlct0_funnel_in4>; + }; + }; + }; + }; + + tpdm@4e10000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04e10000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + ddr_tpdm0_out: endpoint { + remote-endpoint = <&ddr_funnel0_in0>; + }; + }; + }; + }; + + funnel@4e12000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04e12000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + ddr_funnel0_in0: endpoint { + remote-endpoint = <&ddr_tpdm0_out>; + }; + }; + }; + + out-ports { + port { + ddr_funnel0_out0: endpoint { + remote-endpoint = <&ddr_tpda_in0>; + }; + }; + }; + }; + + tpdm@4e20000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x04e20000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + ddr_tpdm1_out: endpoint { + remote-endpoint = <&ddr_funnel1_in0>; + }; + }; + }; + }; + + funnel@4e22000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x04e22000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + ddr_funnel1_in0: endpoint { + remote-endpoint = <&ddr_tpdm1_out>; + }; + }; + }; + + out-ports { + port { + ddr_funnel1_out0: endpoint { + remote-endpoint = <&ddr_tpda_in1>; + }; + }; + }; + }; + + etm@6040000 { + compatible = "arm,primecell"; + reg = <0x0 0x06040000 0x0 0x1000>; + cpu = <&cpu0>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm0_out: endpoint { + remote-endpoint = <&apss_funnel0_in0>; + }; + }; + }; + }; + + etm@6140000 { + compatible = "arm,primecell"; + reg = <0x0 0x06140000 0x0 0x1000>; + cpu = <&cpu1>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm1_out: endpoint { + remote-endpoint = <&apss_funnel0_in1>; + }; + }; + }; + }; + + etm@6240000 { + compatible = "arm,primecell"; + reg = <0x0 0x06240000 0x0 0x1000>; + cpu = <&cpu2>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm2_out: endpoint { + remote-endpoint = <&apss_funnel0_in2>; + }; + }; + }; + }; + + etm@6340000 { + compatible = "arm,primecell"; + reg = <0x0 0x06340000 0x0 0x1000>; + cpu = <&cpu3>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm3_out: endpoint { + remote-endpoint = <&apss_funnel0_in3>; + }; + }; + }; + }; + + etm@6440000 { + compatible = "arm,primecell"; + reg = <0x0 0x06440000 0x0 0x1000>; + cpu = <&cpu4>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm4_out: endpoint { + remote-endpoint = <&apss_funnel0_in4>; + }; + }; + }; + }; + + etm@6540000 { + compatible = "arm,primecell"; + reg = <0x0 0x06540000 0x0 0x1000>; + cpu = <&cpu5>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm5_out: endpoint { + remote-endpoint = <&apss_funnel0_in5>; + }; + }; + }; + }; + + etm@6640000 { + compatible = "arm,primecell"; + reg = <0x0 0x06640000 0x0 0x1000>; + cpu = <&cpu6>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm6_out: endpoint { + remote-endpoint = <&apss_funnel0_in6>; + }; + }; + }; + }; + + etm@6740000 { + compatible = "arm,primecell"; + reg = <0x0 0x06740000 0x0 0x1000>; + cpu = <&cpu7>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + arm,coresight-loses-context-with-cpu; + qcom,skip-power-up; + + out-ports { + port { + etm7_out: endpoint { + remote-endpoint = <&apss_funnel0_in7>; + }; + }; + }; + }; + + funnel@6800000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x06800000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + apss_funnel0_in0: endpoint { + remote-endpoint = <&etm0_out>; + }; + }; + + port@1 { + reg = <1>; + + apss_funnel0_in1: endpoint { + remote-endpoint = <&etm1_out>; + }; + }; + + port@2 { + reg = <2>; + + apss_funnel0_in2: endpoint { + remote-endpoint = <&etm2_out>; + }; + }; + + port@3 { + reg = <3>; + + apss_funnel0_in3: endpoint { + remote-endpoint = <&etm3_out>; + }; + }; + + port@4 { + reg = <4>; + + apss_funnel0_in4: endpoint { + remote-endpoint = <&etm4_out>; + }; + }; + + port@5 { + reg = <5>; + + apss_funnel0_in5: endpoint { + remote-endpoint = <&etm5_out>; + }; + }; + + port@6 { + reg = <6>; + + apss_funnel0_in6: endpoint { + remote-endpoint = <&etm6_out>; + }; + }; + + port@7 { + reg = <7>; + + apss_funnel0_in7: endpoint { + remote-endpoint = <&etm7_out>; + }; + }; + }; + + out-ports { + port { + apss_funnel0_out: endpoint { + remote-endpoint = <&apss_funnel1_in0>; + }; + }; + }; + }; + + funnel@6810000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x06810000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + apss_funnel1_in0: endpoint { + remote-endpoint = <&apss_funnel0_out>; + }; + }; + + port@3 { + reg = <3>; + + apss_funnel1_in3: endpoint { + remote-endpoint = <&apss_tpda_out>; + }; + }; + }; + + out-ports { + port { + apss_funnel1_out: endpoint { + remote-endpoint = <&funnel1_in4>; + }; + }; + }; + }; + + cti@682b000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x0682b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + tpdm@6860000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06860000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + apss_tpdm3_out: endpoint { + remote-endpoint = <&apss_tpda_in3>; + }; + }; + }; + }; + + tpdm@6861000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x06861000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + apss_tpdm4_out: endpoint { + remote-endpoint = <&apss_tpda_in4>; + }; + }; + }; + }; + + tpda@6863000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x06863000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + apss_tpda_in0: endpoint { + remote-endpoint = <&apss_tpdm0_out>; + }; + }; + + port@1 { + reg = <1>; + + apss_tpda_in1: endpoint { + remote-endpoint = <&apss_tpdm1_out>; + }; + }; + + port@2 { + reg = <2>; + + apss_tpda_in2: endpoint { + remote-endpoint = <&apss_tpdm2_out>; + }; + }; + + port@3 { + reg = <3>; + + apss_tpda_in3: endpoint { + remote-endpoint = <&apss_tpdm3_out>; + }; + }; + + port@4 { + reg = <4>; + + apss_tpda_in4: endpoint { + remote-endpoint = <&apss_tpdm4_out>; + }; + }; + }; + + out-ports { + port { + apss_tpda_out: endpoint { + remote-endpoint = <&apss_funnel1_in3>; + }; + }; + }; + }; + + tpdm@68a0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x068a0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + apss_tpdm1_out: endpoint { + remote-endpoint = <&apss_tpda_in1>; + }; + }; + }; + }; + + tpdm@68b0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x068b0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + apss_tpdm0_out: endpoint { + remote-endpoint = <&apss_tpda_in0>; + }; + }; + }; + }; + + tpdm@68c0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x068c0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + apss_tpdm2_out: endpoint { + remote-endpoint = <&apss_tpda_in2>; + }; + }; + }; + }; + + cti@68e0000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x068e0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@68f0000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x068f0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@6900000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x06900000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + usb_1_hsphy: phy@8904000 { + compatible = "qcom,qcs8300-usb-hs-phy", + "qcom,usb-snps-hs-7nm-phy"; + reg = <0x0 0x08904000 0x0 0x400>; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "ref"; + + resets = <&gcc GCC_USB2_PHY_PRIM_BCR>; + + #phy-cells = <0>; + + status = "disabled"; + }; + + usb_2_hsphy: phy@8906000 { + compatible = "qcom,qcs8300-usb-hs-phy", + "qcom,usb-snps-hs-7nm-phy"; + reg = <0x0 0x08906000 0x0 0x400>; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "ref"; + + resets = <&gcc GCC_USB2_PHY_SEC_BCR>; + + #phy-cells = <0>; + + status = "disabled"; + }; + + usb_qmpphy: phy@8907000 { + compatible = "qcom,qcs8300-qmp-usb3-uni-phy"; + reg = <0x0 0x08907000 0x0 0x2000>; + + clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, + <&gcc GCC_USB_CLKREF_EN>, + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; + clock-names = "aux", + "ref", + "com_aux", + "pipe"; + + resets = <&gcc GCC_USB3_PHY_PRIM_BCR>, + <&gcc GCC_USB3PHY_PHY_PRIM_BCR>; + reset-names = "phy", "phy_phy"; + + power-domains = <&gcc GCC_USB30_PRIM_GDSC>; + + #clock-cells = <0>; + clock-output-names = "usb3_prim_phy_pipe_clk_src"; + + #phy-cells = <0>; + + status = "disabled"; + }; + + serdes0: phy@8909000 { + compatible = "qcom,qcs8300-dwmac-sgmii-phy", "qcom,sa8775p-dwmac-sgmii-phy"; + reg = <0x0 0x08909000 0x0 0x00000e10>; + clocks = <&gcc GCC_SGMI_CLKREF_EN>; + clock-names = "sgmi_ref"; + #phy-cells = <0>; + status = "disabled"; + }; + + gpucc: clock-controller@3d90000 { + compatible = "qcom,qcs8300-gpucc"; + reg = <0x0 0x03d90000 0x0 0xa000>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_GPU_GPLL0_CLK_SRC>, + <&gcc GCC_GPU_GPLL0_DIV_CLK_SRC>; + clock-names = "bi_tcxo", + "gcc_gpu_gpll0_clk_src", + "gcc_gpu_gpll0_div_clk_src"; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + + pmu@9091000 { + compatible = "qcom,qcs8300-llcc-bwmon", "qcom,sc7280-llcc-bwmon"; + reg = <0x0 0x9091000 0x0 0x1000>; + + interrupts = ; + + interconnects = <&mc_virt MASTER_LLCC QCOM_ICC_TAG_ACTIVE_ONLY + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ACTIVE_ONLY>; + + operating-points-v2 = <&llcc_bwmon_opp_table>; + + llcc_bwmon_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-0 { + opp-peak-kBps = <762000>; + }; + + opp-1 { + opp-peak-kBps = <1720000>; + }; + + opp-2 { + opp-peak-kBps = <2086000>; + }; + + opp-3 { + opp-peak-kBps = <2601000>; + }; + + opp-4 { + opp-peak-kBps = <2929000>; + }; + + opp-5 { + opp-peak-kBps = <5931000>; + }; + + opp-6 { + opp-peak-kBps = <6515000>; + }; + + opp-7 { + opp-peak-kBps = <7984000>; + }; + + opp-8 { + opp-peak-kBps = <10437000>; + }; + + opp-9 { + opp-peak-kBps = <12195000>; + }; + }; + }; + + pmu@90b5400 { + compatible = "qcom,qcs8300-cpu-bwmon", "qcom,sdm845-bwmon"; + reg = <0x0 0x90b5400 0x0 0x600>; + interrupts = ; + interconnects = <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ACTIVE_ONLY>; + + operating-points-v2 = <&cpu_bwmon_opp_table>; + + cpu_bwmon_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-0 { + opp-peak-kBps = <9155000>; + }; + + opp-1 { + opp-peak-kBps = <12298000>; + }; + + opp-2 { + opp-peak-kBps = <14236000>; + }; + + opp-3 { + opp-peak-kBps = <16265000>; + }; + }; + }; + + pmu@90b6400 { + compatible = "qcom,qcs8300-cpu-bwmon", "qcom,sdm845-bwmon"; + reg = <0x0 0x90b6400 0x0 0x600>; + interrupts = ; + interconnects = <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ACTIVE_ONLY>; + + operating-points-v2 = <&cpu_bwmon_opp_table>; + }; + + dc_noc: interconnect@90e0000 { + compatible = "qcom,qcs8300-dc-noc"; + reg = <0x0 0x090e0000 0x0 0x5080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + gem_noc: interconnect@9100000 { + compatible = "qcom,qcs8300-gem-noc"; + reg = <0x0 0x9100000 0x0 0xf7080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + llcc: system-cache-controller@9200000 { + compatible = "qcom,qcs8300-llcc"; + reg = <0x0 0x09200000 0x0 0x80000>, + <0x0 0x09300000 0x0 0x80000>, + <0x0 0x09400000 0x0 0x80000>, + <0x0 0x09500000 0x0 0x80000>, + <0x0 0x09a00000 0x0 0x80000>; + reg-names = "llcc0_base", + "llcc1_base", + "llcc2_base", + "llcc3_base", + "llcc_broadcast_base"; + interrupts = ; + }; + + usb_1: usb@a6f8800 { + compatible = "qcom,qcs8300-dwc3", "qcom,dwc3"; + reg = <0x0 0x0a6f8800 0x0 0x400>; + + clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>, + <&gcc GCC_USB30_PRIM_MASTER_CLK>, + <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>, + <&gcc GCC_USB30_PRIM_SLEEP_CLK>, + <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>; + clock-names = "cfg_noc", + "core", + "iface", + "sleep", + "mock_utmi"; + + assigned-clocks = <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>, + <&gcc GCC_USB30_PRIM_MASTER_CLK>; + assigned-clock-rates = <19200000>, <200000000>; + + interrupts-extended = <&intc GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 261 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 14 IRQ_TYPE_EDGE_BOTH>, + <&pdc 15 IRQ_TYPE_EDGE_BOTH>, + <&pdc 12 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "pwr_event", + "hs_phy_irq", + "dp_hs_phy_irq", + "dm_hs_phy_irq", + "ss_phy_irq"; + + power-domains = <&gcc GCC_USB30_PRIM_GDSC>; + required-opps = <&rpmhpd_opp_nom>; + + resets = <&gcc GCC_USB30_PRIM_BCR>; + interconnects = <&aggre1_noc MASTER_USB3_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_USB3_0 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "usb-ddr", "apps-usb"; + + wakeup-source; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + usb_1_dwc3: usb@a600000 { + compatible = "snps,dwc3"; + reg = <0x0 0x0a600000 0x0 0xe000>; + interrupts = ; + iommus = <&apps_smmu 0x80 0x0>; + phys = <&usb_1_hsphy>, <&usb_qmpphy>; + phy-names = "usb2-phy", "usb3-phy"; + snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; + snps,dis_u2_susphy_quirk; + snps,dis_u3_susphy_quirk; + }; + }; + + usb_2: usb@a4f8800 { + compatible = "qcom,qcs8300-dwc3", "qcom,dwc3"; + reg = <0x0 0x0a4f8800 0x0 0x400>; + + clocks = <&gcc GCC_CFG_NOC_USB2_PRIM_AXI_CLK>, + <&gcc GCC_USB20_MASTER_CLK>, + <&gcc GCC_AGGRE_USB2_PRIM_AXI_CLK>, + <&gcc GCC_USB20_SLEEP_CLK>, + <&gcc GCC_USB20_MOCK_UTMI_CLK>; + clock-names = "cfg_noc", + "core", + "iface", + "sleep", + "mock_utmi"; + + assigned-clocks = <&gcc GCC_USB20_MOCK_UTMI_CLK>, + <&gcc GCC_USB20_MASTER_CLK>; + assigned-clock-rates = <19200000>, <120000000>; + + interrupts-extended = <&intc GIC_SPI 444 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 443 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 10 IRQ_TYPE_EDGE_BOTH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>; + interrupt-names = "pwr_event", + "hs_phy_irq", + "dp_hs_phy_irq", + "dm_hs_phy_irq"; + + power-domains = <&gcc GCC_USB20_PRIM_GDSC>; + required-opps = <&rpmhpd_opp_nom>; + + resets = <&gcc GCC_USB20_PRIM_BCR>; + + interconnects = <&aggre1_noc MASTER_USB2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_USB2 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "usb-ddr", "apps-usb"; + + qcom,select-utmi-as-pipe-clk; + wakeup-source; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + usb_2_dwc3: usb@a400000 { + compatible = "snps,dwc3"; + reg = <0x0 0x0a400000 0x0 0xe000>; + + interrupts = ; + iommus = <&apps_smmu 0x20 0x0>; + + phys = <&usb_2_hsphy>; + phy-names = "usb2-phy"; + maximum-speed = "high-speed"; + + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; + snps,dis_u2_susphy_quirk; + snps,dis_u3_susphy_quirk; + snps,dis_enblslpm_quirk; + }; + }; + + videocc: clock-controller@abf0000 { + compatible = "qcom,qcs8300-videocc"; + reg = <0x0 0x0abf0000 0x0 0x10000>; + clocks = <&gcc GCC_VIDEO_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>; + power-domains = <&rpmhpd RPMHPD_MMCX>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + + camcc: clock-controller@ade0000 { + compatible = "qcom,qcs8300-camcc"; + reg = <0x0 0x0ade0000 0x0 0x20000>; + clocks = <&gcc GCC_CAMERA_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>; + power-domains = <&rpmhpd RPMHPD_MMCX>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + + dispcc: clock-controller@af00000 { + compatible = "qcom,sa8775p-dispcc0"; + reg = <0x0 0x0af00000 0x0 0x20000>; + clocks = <&gcc GCC_DISP_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>, + <0>, <0>, <0>, <0>, + <0>, <0>, <0>, <0>; + power-domains = <&rpmhpd RPMHPD_MMCX>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + + pdc: interrupt-controller@b220000 { + compatible = "qcom,qcs8300-pdc", "qcom,pdc"; + reg = <0x0 0xb220000 0x0 0x30000>, + <0x0 0x17c000f0 0x0 0x64>; + interrupt-parent = <&intc>; + #interrupt-cells = <2>; + interrupt-controller; + qcom,pdc-ranges = <0 480 40>, + <40 140 14>, + <54 263 1>, + <55 306 4>, + <59 312 3>, + <62 374 2>, + <64 434 2>, + <66 438 2>, + <70 520 1>, + <73 523 1>, + <118 568 6>, + <124 609 3>, + <159 638 1>, + <160 720 3>, + <169 728 30>, + <199 416 2>, + <201 449 1>, + <202 89 1>, + <203 451 1>, + <204 462 1>, + <205 264 1>, + <206 579 1>, + <207 653 1>, + <208 656 1>, + <209 659 1>, + <210 122 1>, + <211 699 1>, + <212 705 1>, + <213 450 1>, + <214 643 2>, + <216 646 5>, + <221 390 5>, + <226 700 2>, + <228 440 1>, + <229 663 1>, + <230 524 2>, + <232 612 3>, + <235 723 5>; + }; + + aoss_qmp: power-management@c300000 { + compatible = "qcom,qcs8300-aoss-qmp", "qcom,aoss-qmp"; + reg = <0x0 0x0c300000 0x0 0x400>; + interrupts-extended = <&ipcc IPCC_CLIENT_AOP + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_AOP IPCC_MPROC_SIGNAL_GLINK_QMP>; + #clock-cells = <0>; + }; + + tlmm: pinctrl@f100000 { + compatible = "qcom,qcs8300-tlmm"; + reg = <0x0 0x0f100000 0x0 0x300000>; + interrupts = ; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&tlmm 0 0 134>; + interrupt-controller; + #interrupt-cells = <2>; + wakeup-parent = <&pdc>; + + qup_uart7_default: qup-uart7-state { + /* TX, RX */ + pins = "gpio43", "gpio44"; + function = "qup0_se7"; + }; + }; + + sram: sram@146d8000 { + compatible = "qcom,qcs8300-imem", "syscon", "simple-mfd"; + reg = <0x0 0x146d8000 0x0 0x1000>; + ranges = <0x0 0x0 0x146d8000 0x1000>; + + #address-cells = <1>; + #size-cells = <1>; + + pil-reloc@94c { + compatible = "qcom,pil-reloc-info"; + reg = <0x94c 0xc8>; + }; + }; + + apps_smmu: iommu@15000000 { + compatible = "qcom,qcs8300-smmu-500", "qcom,smmu-500", "arm,mmu-500"; + + reg = <0x0 0x15000000 0x0 0x100000>; + #iommu-cells = <2>; + #global-interrupts = <2>; + dma-coherent; + + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + }; + + intc: interrupt-controller@17a00000 { + compatible = "arm,gic-v3"; + reg = <0x0 0x17a00000 0x0 0x10000>, + <0x0 0x17a60000 0x0 0x100000>; + interrupts = ; + #interrupt-cells = <3>; + interrupt-controller; + #redistributor-regions = <1>; + redistributor-stride = <0x0 0x20000>; + }; + + watchdog@17c10000 { + compatible = "qcom,apss-wdt-qcs8300", "qcom,kpss-wdt"; + reg = <0x0 0x17c10000 0x0 0x1000>; + clocks = <&sleep_clk>; + interrupts = ; + }; + + timer@17c20000 { + compatible = "arm,armv7-timer-mem"; + reg = <0x0 0x17c20000 0x0 0x1000>; + ranges = <0x0 0x0 0x0 0x20000000>; + #address-cells = <1>; + #size-cells = <1>; + + frame@17c21000 { + reg = <0x17c21000 0x1000>, + <0x17c22000 0x1000>; + frame-number = <0>; + interrupts = , + ; + }; + + frame@17c23000 { + reg = <0x17c23000 0x1000>; + frame-number = <1>; + interrupts = ; + status = "disabled"; + }; + + frame@17c25000 { + reg = <0x17c25000 0x1000>; + frame-number = <2>; + interrupts = ; + status = "disabled"; + }; + + frame@17c27000 { + reg = <0x17c27000 0x1000>; + frame-number = <3>; + interrupts = ; + status = "disabled"; + }; + + frame@17c29000 { + reg = <0x17c29000 0x1000>; + frame-number = <4>; + interrupts = ; + status = "disabled"; + }; + + frame@17c2b000 { + reg = <0x17c2b000 0x1000>; + frame-number = <5>; + interrupts = ; + status = "disabled"; + }; + + frame@17c2d000 { + reg = <0x17c2d000 0x1000>; + frame-number = <6>; + interrupts = ; + status = "disabled"; + }; + }; + + apps_rsc: rsc@18200000 { + compatible = "qcom,rpmh-rsc"; + reg = <0x0 0x18200000 0x0 0x10000>, + <0x0 0x18210000 0x0 0x10000>, + <0x0 0x18220000 0x0 0x10000>; + reg-names = "drv-0", + "drv-1", + "drv-2"; + interrupts = , + , + ; + + power-domains = <&system_pd>; + label = "apps_rsc"; + + qcom,tcs-offset = <0xd00>; + qcom,drv-id = <2>; + qcom,tcs-config = , + , + , + ; + + apps_bcm_voter: bcm-voter { + compatible = "qcom,bcm-voter"; + }; + + rpmhcc: clock-controller { + compatible = "qcom,sa8775p-rpmh-clk"; + #clock-cells = <1>; + clocks = <&xo_board_clk>; + clock-names = "xo"; + }; + + rpmhpd: power-controller { + compatible = "qcom,qcs8300-rpmhpd"; + #power-domain-cells = <1>; + operating-points-v2 = <&rpmhpd_opp_table>; + + rpmhpd_opp_table: opp-table { + compatible = "operating-points-v2"; + + rpmhpd_opp_ret: opp-0 { + opp-level = ; + }; + + rpmhpd_opp_min_svs: opp-1 { + opp-level = ; + }; + + rpmhpd_opp_low_svs: opp-2 { + opp-level = ; + }; + + rpmhpd_opp_svs: opp-3 { + opp-level = ; + }; + + rpmhpd_opp_svs_l1: opp-4 { + opp-level = ; + }; + + rpmhpd_opp_nom: opp-5 { + opp-level = ; + }; + + rpmhpd_opp_nom_l1: opp-6 { + opp-level = ; + }; + + rpmhpd_opp_nom_l2: opp-7 { + opp-level = ; + }; + + rpmhpd_opp_turbo: opp-8 { + opp-level = ; + }; + + rpmhpd_opp_turbo_l1: opp-9 { + opp-level = ; + }; + }; + }; + }; + + remoteproc_gpdsp: remoteproc@20c00000 { + compatible = "qcom,qcs8300-gpdsp-pas", "qcom,sa8775p-gpdsp0-pas"; + reg = <0x0 0x20c00000 0x0 0x10000>; + + interrupts-extended = <&intc GIC_SPI 768 IRQ_TYPE_EDGE_RISING>, + <&smp2p_gpdsp_in 0 0>, + <&smp2p_gpdsp_in 1 0>, + <&smp2p_gpdsp_in 2 0>, + <&smp2p_gpdsp_in 3 0>; + interrupt-names = "wdog", + "fatal", + "ready", + "handover", + "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + power-domains = <&rpmhpd RPMHPD_CX>, + <&rpmhpd RPMHPD_MXC>; + power-domain-names = "cx", + "mxc"; + + interconnects = <&gpdsp_anoc MASTER_DSP0 QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_CLK_CTL QCOM_ICC_TAG_ALWAYS>; + + memory-region = <&gpdsp_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_gpdsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_GPDSP0 + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_GPDSP0 + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + label = "gpdsp"; + qcom,remote-pid = <17>; + }; + }; + + ethernet0: ethernet@23040000 { + compatible = "qcom,qcs8300-ethqos", "qcom,sa8775p-ethqos"; + reg = <0x0 0x23040000 0x0 0x00010000>, + <0x0 0x23056000 0x0 0x00000100>; + reg-names = "stmmaceth", "rgmii"; + + interrupts = , + ; + interrupt-names = "macirq", "sfty"; + + clocks = <&gcc GCC_EMAC0_AXI_CLK>, + <&gcc GCC_EMAC0_SLV_AHB_CLK>, + <&gcc GCC_EMAC0_PTP_CLK>, + <&gcc GCC_EMAC0_PHY_AUX_CLK>; + clock-names = "stmmaceth", + "pclk", + "ptp_ref", + "phyaux"; + power-domains = <&gcc GCC_EMAC0_GDSC>; + + phys = <&serdes0>; + phy-names = "serdes"; + + iommus = <&apps_smmu 0x120 0xf>; + dma-coherent; + + snps,tso; + snps,pbl = <32>; + rx-fifo-depth = <16384>; + tx-fifo-depth = <20480>; + + status = "disabled"; + }; + + nspa_noc: interconnect@260c0000 { + compatible = "qcom,qcs8300-nspa-noc"; + reg = <0x0 0x260c0000 0x0 0x16080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + remoteproc_cdsp: remoteproc@26300000 { + compatible = "qcom,qcs8300-cdsp-pas", "qcom,sa8775p-cdsp0-pas"; + reg = <0x0 0x26300000 0x0 0x10000>; + + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", + "fatal", + "ready", + "handover", + "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + power-domains = <&rpmhpd RPMHPD_CX>, + <&rpmhpd RPMHPD_MXC>, + <&rpmhpd RPMHPD_NSP0>; + + power-domain-names = "cx", + "mxc", + "nsp"; + + interconnects = <&nspa_noc MASTER_CDSP_PROC QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + + memory-region = <&cdsp_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_cdsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_CDSP + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_CDSP + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + label = "cdsp"; + qcom,remote-pid = <5>; + + fastrpc { + compatible = "qcom,fastrpc"; + qcom,glink-channels = "fastrpcglink-apps-dsp"; + label = "cdsp"; + #address-cells = <1>; + #size-cells = <0>; + + compute-cb@1 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <1>; + iommus = <&apps_smmu 0x19c1 0x0440>, + <&apps_smmu 0x1961 0x0400>; + dma-coherent; + }; + + compute-cb@2 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <2>; + iommus = <&apps_smmu 0x19c2 0x0440>, + <&apps_smmu 0x1962 0x0400>; + dma-coherent; + }; + + compute-cb@3 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <3>; + iommus = <&apps_smmu 0x19c3 0x0440>, + <&apps_smmu 0x1963 0x0400>; + dma-coherent; + }; + + compute-cb@4 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <4>; + iommus = <&apps_smmu 0x19c4 0x0440>, + <&apps_smmu 0x1964 0x0400>; + dma-coherent; + }; + }; + }; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/qcs8550-aim300.dtsi b/arch/arm64/boot/dts/qcom/qcs8550-aim300.dtsi index f6960e2d466a..e6ac529e6b72 100644 --- a/arch/arm64/boot/dts/qcom/qcs8550-aim300.dtsi +++ b/arch/arm64/boot/dts/qcom/qcs8550-aim300.dtsi @@ -367,7 +367,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &ufs_mem_hc { diff --git a/arch/arm64/boot/dts/qcom/qdu1000-idp.dts b/arch/arm64/boot/dts/qcom/qdu1000-idp.dts index e65305f8136c..d125fc77ae14 100644 --- a/arch/arm64/boot/dts/qcom/qdu1000-idp.dts +++ b/arch/arm64/boot/dts/qcom/qdu1000-idp.dts @@ -22,20 +22,6 @@ stdout-path = "serial0:115200n8"; }; - clocks { - xo_board: xo-board-clk { - compatible = "fixed-clock"; - clock-frequency = <19200000>; - #clock-cells = <0>; - }; - - sleep_clk: sleep-clk { - compatible = "fixed-clock"; - clock-frequency = <32000>; - #clock-cells = <0>; - }; - }; - ppvar_sys: ppvar-sys-regulator { compatible = "regulator-fixed"; regulator-name = "ppvar_sys"; @@ -239,6 +225,11 @@ }; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &qup_i2c1_data_clk { drive-strength = <2>; bias-pull-up; diff --git a/arch/arm64/boot/dts/qcom/qdu1000.dtsi b/arch/arm64/boot/dts/qcom/qdu1000.dtsi index 47c0dd31aaf2..f973aa8f7477 100644 --- a/arch/arm64/boot/dts/qcom/qdu1000.dtsi +++ b/arch/arm64/boot/dts/qcom/qdu1000.dtsi @@ -21,6 +21,20 @@ chosen: chosen { }; + clocks { + xo_board: xo-board-clk { + compatible = "fixed-clock"; + clock-frequency = <19200000>; + #clock-cells = <0>; + }; + + sleep_clk: sleep-clk { + compatible = "fixed-clock"; + clock-frequency = <32764>; + #clock-cells = <0>; + }; + }; + cpus { #address-cells = <2>; #size-cells = <0>; @@ -1009,6 +1023,8 @@ iommus = <&apps_smmu 0xc0 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy>; phy-names = "usb2-phy", diff --git a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts index a9540e92d3e6..52db18847803 100644 --- a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts +++ b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts @@ -6,6 +6,8 @@ /dts-v1/; #include +#include +#include #include #include "sm4250.dtsi" #include "pm6125.dtsi" @@ -103,6 +105,55 @@ }; }; + sound { + compatible = "qcom,qrb4210-rb2-sndcard"; + pinctrl-0 = <&lpi_i2s2_active>; + pinctrl-names = "default"; + model = "Qualcomm-RB2-WSA8815-Speakers-DMIC0"; + audio-routing = "MM_DL1", "MultiMedia1 Playback", + "MM_DL2", "MultiMedia2 Playback"; + + mm1-dai-link { + link-name = "MultiMedia1"; + + cpu { + sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA1>; + }; + }; + + mm2-dai-link { + link-name = "MultiMedia2"; + + cpu { + sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA2>; + }; + }; + + mm3-dai-link { + link-name = "MultiMedia3"; + + cpu { + sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA3>; + }; + }; + + hdmi-dai-link { + link-name = "HDMI Playback"; + + cpu { + sound-dai = <&q6afedai SECONDARY_MI2S_RX>; + }; + + platform { + sound-dai = <&q6routing>; + }; + + codec { + sound-dai = <<9611_codec 0>; + }; + }; + }; + vreg_hdmi_out_1p2: regulator-hdmi-out-1p2 { compatible = "regulator-fixed"; regulator-name = "VREG_HDMI_OUT_1P2"; @@ -318,6 +369,14 @@ status = "okay"; }; +/* SECONDARY I2S uses 1 I2S SD Line for audio on LT9611UXC HDMI Bridge */ +&q6afedai { + dai@20 { + reg = ; + qcom,sd-lines = <0>; + }; +}; + &qupv3_id_0 { status = "okay"; }; @@ -545,7 +604,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &tlmm { diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts index 52eef88e882c..7afa5acac3fc 100644 --- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts +++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts @@ -964,6 +964,11 @@ }; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &pon_pwrkey { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/qru1000-idp.dts b/arch/arm64/boot/dts/qcom/qru1000-idp.dts index 1c781d9e24cf..439f5c327dc4 100644 --- a/arch/arm64/boot/dts/qcom/qru1000-idp.dts +++ b/arch/arm64/boot/dts/qcom/qru1000-idp.dts @@ -22,20 +22,6 @@ stdout-path = "serial0:115200n8"; }; - clocks { - xo_board: xo-board-clk { - compatible = "fixed-clock"; - clock-frequency = <19200000>; - #clock-cells = <0>; - }; - - sleep_clk: sleep-clk { - compatible = "fixed-clock"; - clock-frequency = <32000>; - #clock-cells = <0>; - }; - }; - ppvar_sys: ppvar-sys-regulator { compatible = "regulator-fixed"; regulator-name = "ppvar_sys"; @@ -239,6 +225,11 @@ }; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &qup_i2c1_data_clk { drive-strength = <2>; bias-pull-up; diff --git a/arch/arm64/boot/dts/qcom/sa8775p-ride.dtsi b/arch/arm64/boot/dts/qcom/sa8775p-ride.dtsi index 3fc62e123689..175f8b1e3b2d 100644 --- a/arch/arm64/boot/dts/qcom/sa8775p-ride.dtsi +++ b/arch/arm64/boot/dts/qcom/sa8775p-ride.dtsi @@ -104,6 +104,30 @@ }; }; }; + + dp0-connector { + compatible = "dp-connector"; + label = "eDP0"; + type = "full-size"; + + port { + dp0_connector_in: endpoint { + remote-endpoint = <&mdss0_dp0_out>; + }; + }; + }; + + dp1-connector { + compatible = "dp-connector"; + label = "eDP1"; + type = "full-size"; + + port { + dp1_connector_in: endpoint { + remote-endpoint = <&mdss0_dp1_out>; + }; + }; + }; }; &apps_rsc { @@ -498,6 +522,50 @@ status = "okay"; }; +&mdss0 { + status = "okay"; +}; + +&mdss0_dp0 { + pinctrl-0 = <&dp0_hot_plug_det>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&mdss0_dp0_out { + data-lanes = <0 1 2 3>; + link-frequencies = /bits/ 64 <1620000000 2700000000 5400000000 8100000000>; + remote-endpoint = <&dp0_connector_in>; +}; + +&mdss0_dp0_phy { + vdda-phy-supply = <&vreg_l1c>; + vdda-pll-supply = <&vreg_l4a>; + + status = "okay"; +}; + +&mdss0_dp1 { + pinctrl-0 = <&dp1_hot_plug_det>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&mdss0_dp1_out { + data-lanes = <0 1 2 3>; + link-frequencies = /bits/ 64 <1620000000 2700000000 5400000000 8100000000>; + remote-endpoint = <&dp1_connector_in>; +}; + +&mdss0_dp1_phy { + vdda-phy-supply = <&vreg_l1c>; + vdda-pll-supply = <&vreg_l4a>; + + status = "okay"; +}; + &pmm8654au_0_gpios { gpio-line-names = "DS_EN", "POFF_COMPLETE", @@ -608,7 +676,7 @@ }; &sleep_clk { - clock-frequency = <32764>; + clock-frequency = <32000>; }; &spi16 { @@ -618,6 +686,18 @@ }; &tlmm { + dp0_hot_plug_det: dp0-hot-plug-det-state { + pins = "gpio101"; + function = "edp0_hot"; + bias-disable; + }; + + dp1_hot_plug_det: dp1-hot-plug-det-state { + pins = "gpio102"; + function = "edp1_hot"; + bias-disable; + }; + ethernet0_default: ethernet0-default-state { ethernet0_mdc: ethernet0-mdc-pins { pins = "gpio8"; diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi index 9f315a51a7c1..3394ae2d1300 100644 --- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi +++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -44,6 +45,8 @@ compatible = "qcom,kryo"; reg = <0x0 0x0>; enable-method = "psci"; + power-domains = <&cpu_pd0>; + power-domain-names = "psci"; qcom,freq-domain = <&cpufreq_hw 0>; next-level-cache = <&l2_0>; capacity-dmips-mhz = <1024>; @@ -66,6 +69,8 @@ compatible = "qcom,kryo"; reg = <0x0 0x100>; enable-method = "psci"; + power-domains = <&cpu_pd1>; + power-domain-names = "psci"; qcom,freq-domain = <&cpufreq_hw 0>; next-level-cache = <&l2_1>; capacity-dmips-mhz = <1024>; @@ -83,6 +88,8 @@ compatible = "qcom,kryo"; reg = <0x0 0x200>; enable-method = "psci"; + power-domains = <&cpu_pd2>; + power-domain-names = "psci"; qcom,freq-domain = <&cpufreq_hw 0>; next-level-cache = <&l2_2>; capacity-dmips-mhz = <1024>; @@ -100,6 +107,8 @@ compatible = "qcom,kryo"; reg = <0x0 0x300>; enable-method = "psci"; + power-domains = <&cpu_pd3>; + power-domain-names = "psci"; qcom,freq-domain = <&cpufreq_hw 0>; next-level-cache = <&l2_3>; capacity-dmips-mhz = <1024>; @@ -117,6 +126,8 @@ compatible = "qcom,kryo"; reg = <0x0 0x10000>; enable-method = "psci"; + power-domains = <&cpu_pd4>; + power-domain-names = "psci"; qcom,freq-domain = <&cpufreq_hw 1>; next-level-cache = <&l2_4>; capacity-dmips-mhz = <1024>; @@ -140,6 +151,8 @@ compatible = "qcom,kryo"; reg = <0x0 0x10100>; enable-method = "psci"; + power-domains = <&cpu_pd5>; + power-domain-names = "psci"; qcom,freq-domain = <&cpufreq_hw 1>; next-level-cache = <&l2_5>; capacity-dmips-mhz = <1024>; @@ -157,6 +170,8 @@ compatible = "qcom,kryo"; reg = <0x0 0x10200>; enable-method = "psci"; + power-domains = <&cpu_pd6>; + power-domain-names = "psci"; qcom,freq-domain = <&cpufreq_hw 1>; next-level-cache = <&l2_6>; capacity-dmips-mhz = <1024>; @@ -174,6 +189,8 @@ compatible = "qcom,kryo"; reg = <0x0 0x10300>; enable-method = "psci"; + power-domains = <&cpu_pd7>; + power-domain-names = "psci"; qcom,freq-domain = <&cpufreq_hw 1>; next-level-cache = <&l2_7>; capacity-dmips-mhz = <1024>; @@ -854,8 +871,8 @@ #mbox-cells = <2>; }; - gpi_dma2: qcom,gpi-dma@800000 { - compatible = "qcom,sm6350-gpi-dma"; + gpi_dma2: dma-controller@800000 { + compatible = "qcom,sa8775p-gpi-dma", "qcom,sm6350-gpi-dma"; reg = <0x0 0x00800000 0x0 0x60000>; #dma-cells = <3>; interrupts = , @@ -1345,8 +1362,8 @@ }; - gpi_dma0: qcom,gpi-dma@900000 { - compatible = "qcom,sm6350-gpi-dma"; + gpi_dma0: dma-controller@900000 { + compatible = "qcom,sa8775p-gpi-dma", "qcom,sm6350-gpi-dma"; reg = <0x0 0x00900000 0x0 0x60000>; #dma-cells = <3>; interrupts = , @@ -1770,8 +1787,8 @@ }; }; - gpi_dma1: qcom,gpi-dma@a00000 { - compatible = "qcom,sm6350-gpi-dma"; + gpi_dma1: dma-controller@a00000 { + compatible = "qcom,sa8775p-gpi-dma", "qcom,sm6350-gpi-dma"; reg = <0x0 0x00a00000 0x0 0x60000>; #dma-cells = <3>; interrupts = , @@ -2225,8 +2242,8 @@ }; }; - gpi_dma3: qcom,gpi-dma@b00000 { - compatible = "qcom,sm6350-gpi-dma"; + gpi_dma3: dma-controller@b00000 { + compatible = "qcom,sa8775p-gpi-dma", "qcom,sm6350-gpi-dma"; reg = <0x0 0x00b00000 0x0 0x58000>; #dma-cells = <3>; interrupts = , @@ -2440,6 +2457,7 @@ qcom,cmb-element-bits = <32>; qcom,cmb-msrs-num = <32>; + status = "disabled"; out-ports { port { @@ -3411,6 +3429,8 @@ iommus = <&apps_smmu 0x080 0x0>; phys = <&usb_0_hsphy>, <&usb_0_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; }; }; @@ -3500,6 +3520,8 @@ iommus = <&apps_smmu 0x0a0 0x0>; phys = <&usb_1_hsphy>, <&usb_1_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; }; }; @@ -3563,6 +3585,8 @@ iommus = <&apps_smmu 0x020 0x0>; phys = <&usb_2_hsphy>; phy-names = "usb2-phy"; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; }; }; @@ -3759,6 +3783,353 @@ interrupts = ; }; + videocc: clock-controller@abf0000 { + compatible = "qcom,sa8775p-videocc"; + reg = <0x0 0x0abf0000 0x0 0x10000>; + clocks = <&gcc GCC_VIDEO_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>; + power-domains = <&rpmhpd SA8775P_MMCX>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + + camcc: clock-controller@ade0000 { + compatible = "qcom,sa8775p-camcc"; + reg = <0x0 0x0ade0000 0x0 0x20000>; + clocks = <&gcc GCC_CAMERA_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>; + power-domains = <&rpmhpd SA8775P_MMCX>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + + mdss0: display-subsystem@ae00000 { + compatible = "qcom,sa8775p-mdss"; + reg = <0x0 0x0ae00000 0x0 0x1000>; + reg-names = "mdss"; + + /* same path used twice */ + interconnects = <&mmss_noc MASTER_MDP0 QCOM_ICC_TAG_ACTIVE_ONLY + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ACTIVE_ONLY>, + <&mmss_noc MASTER_MDP1 QCOM_ICC_TAG_ACTIVE_ONLY + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ACTIVE_ONLY>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ACTIVE_ONLY>; + interconnect-names = "mdp0-mem", + "mdp1-mem", + "cpu-cfg"; + + resets = <&dispcc0 MDSS_DISP_CC_MDSS_CORE_BCR>; + + power-domains = <&dispcc0 MDSS_DISP_CC_MDSS_CORE_GDSC>; + + clocks = <&dispcc0 MDSS_DISP_CC_MDSS_AHB_CLK>, + <&gcc GCC_DISP_HF_AXI_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_MDP_CLK>; + + interrupts = ; + interrupt-controller; + #interrupt-cells = <1>; + + iommus = <&apps_smmu 0x1000 0x402>; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + mdss0_mdp: display-controller@ae01000 { + compatible = "qcom,sa8775p-dpu"; + reg = <0x0 0x0ae01000 0x0 0x8f000>, + <0x0 0x0aeb0000 0x0 0x2008>; + reg-names = "mdp", "vbif"; + + clocks = <&gcc GCC_DISP_HF_AXI_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_AHB_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_MDP_LUT_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_MDP_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_VSYNC_CLK>; + clock-names = "bus", + "iface", + "lut", + "core", + "vsync"; + + assigned-clocks = <&dispcc0 MDSS_DISP_CC_MDSS_VSYNC_CLK>; + assigned-clock-rates = <19200000>; + + operating-points-v2 = <&mdss0_mdp_opp_table>; + power-domains = <&rpmhpd SA8775P_MMCX>; + + interrupt-parent = <&mdss0>; + interrupts = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + dpu_intf0_out: endpoint { + remote-endpoint = <&mdss0_dp0_in>; + }; + }; + + port@1 { + reg = <1>; + + dpu_intf4_out: endpoint { + remote-endpoint = <&mdss0_dp1_in>; + }; + }; + }; + + mdss0_mdp_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-375000000 { + opp-hz = /bits/ 64 <375000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + + opp-500000000 { + opp-hz = /bits/ 64 <500000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + + opp-575000000 { + opp-hz = /bits/ 64 <575000000>; + required-opps = <&rpmhpd_opp_turbo>; + }; + + opp-650000000 { + opp-hz = /bits/ 64 <650000000>; + required-opps = <&rpmhpd_opp_turbo_l1>; + }; + }; + }; + + mdss0_dp0_phy: phy@aec2a00 { + compatible = "qcom,sa8775p-edp-phy"; + + reg = <0x0 0x0aec2a00 0x0 0x200>, + <0x0 0x0aec2200 0x0 0xd0>, + <0x0 0x0aec2600 0x0 0xd0>, + <0x0 0x0aec2000 0x0 0x1c8>; + + clocks = <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_AUX_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_AHB_CLK>; + clock-names = "aux", + "cfg_ahb"; + + #clock-cells = <1>; + #phy-cells = <0>; + + status = "disabled"; + }; + + mdss0_dp1_phy: phy@aec5a00 { + compatible = "qcom,sa8775p-edp-phy"; + + reg = <0x0 0x0aec5a00 0x0 0x200>, + <0x0 0x0aec5200 0x0 0xd0>, + <0x0 0x0aec5600 0x0 0xd0>, + <0x0 0x0aec5000 0x0 0x1c8>; + + clocks = <&dispcc0 MDSS_DISP_CC_MDSS_DPTX1_AUX_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_AHB_CLK>; + clock-names = "aux", + "cfg_ahb"; + + #clock-cells = <1>; + #phy-cells = <0>; + + status = "disabled"; + }; + + mdss0_dp0: displayport-controller@af54000 { + compatible = "qcom,sa8775p-dp"; + + reg = <0x0 0x0af54000 0x0 0x104>, + <0x0 0x0af54200 0x0 0x0c0>, + <0x0 0x0af55000 0x0 0x770>, + <0x0 0x0af56000 0x0 0x09c>, + <0x0 0x0af57000 0x0 0x09c>; + + interrupt-parent = <&mdss0>; + interrupts = <12>; + + clocks = <&dispcc0 MDSS_DISP_CC_MDSS_AHB_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_AUX_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_LINK_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_LINK_INTF_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL0_CLK>; + clock-names = "core_iface", + "core_aux", + "ctrl_link", + "ctrl_link_iface", + "stream_pixel"; + assigned-clocks = <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_LINK_CLK_SRC>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL0_CLK_SRC>; + assigned-clock-parents = <&mdss0_dp0_phy 0>, <&mdss0_dp0_phy 1>; + phys = <&mdss0_dp0_phy>; + phy-names = "dp"; + + operating-points-v2 = <&dp_opp_table>; + power-domains = <&rpmhpd SA8775P_MMCX>; + + #sound-dai-cells = <0>; + + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + mdss0_dp0_in: endpoint { + remote-endpoint = <&dpu_intf0_out>; + }; + }; + + port@1 { + reg = <1>; + + mdss0_dp0_out: endpoint { }; + }; + }; + + dp_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-160000000 { + opp-hz = /bits/ 64 <160000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-270000000 { + opp-hz = /bits/ 64 <270000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-540000000 { + opp-hz = /bits/ 64 <540000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + + opp-810000000 { + opp-hz = /bits/ 64 <810000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; + + mdss0_dp1: displayport-controller@af5c000 { + compatible = "qcom,sa8775p-dp"; + + reg = <0x0 0x0af5c000 0x0 0x104>, + <0x0 0x0af5c200 0x0 0x0c0>, + <0x0 0x0af5d000 0x0 0x770>, + <0x0 0x0af5e000 0x0 0x09c>, + <0x0 0x0af5f000 0x0 0x09c>; + + interrupt-parent = <&mdss0>; + interrupts = <13>; + + clocks = <&dispcc0 MDSS_DISP_CC_MDSS_AHB_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX1_AUX_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX1_LINK_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX1_LINK_INTF_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX1_PIXEL0_CLK>; + clock-names = "core_iface", + "core_aux", + "ctrl_link", + "ctrl_link_iface", + "stream_pixel"; + assigned-clocks = <&dispcc0 MDSS_DISP_CC_MDSS_DPTX1_LINK_CLK_SRC>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX1_PIXEL0_CLK_SRC>; + assigned-clock-parents = <&mdss0_dp1_phy 0>, <&mdss0_dp1_phy 1>; + phys = <&mdss0_dp1_phy>; + phy-names = "dp"; + + operating-points-v2 = <&dp1_opp_table>; + power-domains = <&rpmhpd SA8775P_MMCX>; + + #sound-dai-cells = <0>; + + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + mdss0_dp1_in: endpoint { + remote-endpoint = <&dpu_intf4_out>; + }; + }; + + port@1 { + reg = <1>; + + mdss0_dp1_out: endpoint { }; + }; + }; + + dp1_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-160000000 { + opp-hz = /bits/ 64 <160000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-270000000 { + opp-hz = /bits/ 64 <270000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-540000000 { + opp-hz = /bits/ 64 <540000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + + opp-810000000 { + opp-hz = /bits/ 64 <810000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; + }; + + dispcc0: clock-controller@af00000 { + compatible = "qcom,sa8775p-dispcc0"; + reg = <0x0 0x0af00000 0x0 0x20000>; + clocks = <&gcc GCC_DISP_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>, + <&mdss0_dp0_phy 0>, <&mdss0_dp0_phy 1>, + <&mdss0_dp1_phy 0>, <&mdss0_dp1_phy 1>, + <0>, <0>, <0>, <0>; + power-domains = <&rpmhpd SA8775P_MMCX>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + pdc: interrupt-controller@b220000 { compatible = "qcom,sa8775p-pdc", "qcom,pdc"; reg = <0x0 0x0b220000 0x0 0x30000>, @@ -4381,6 +4752,22 @@ }; }; + dispcc1: clock-controller@22100000 { + compatible = "qcom,sa8775p-dispcc1"; + reg = <0x0 0x22100000 0x0 0x20000>; + clocks = <&gcc GCC_DISP_AHB_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>, + <0>, <0>, <0>, <0>, + <0>, <0>, <0>, <0>; + power-domains = <&rpmhpd SA8775P_MMCX>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + status = "disabled"; + }; + ethernet1: ethernet@23000000 { compatible = "qcom,sa8775p-ethqos"; reg = <0x0 0x23000000 0x0 0x10000>, @@ -6092,7 +6479,7 @@ <0x0 0x40000000 0x0 0xf20>, <0x0 0x40000f20 0x0 0xa8>, <0x0 0x40001000 0x0 0x4000>, - <0x0 0x40200000 0x0 0x100000>, + <0x0 0x40200000 0x0 0x1fe00000>, <0x0 0x01c03000 0x0 0x1000>, <0x0 0x40005000 0x0 0x2000>; reg-names = "parf", "dbi", "elbi", "atu", "addr_space", @@ -6250,7 +6637,7 @@ <0x0 0x60000000 0x0 0xf20>, <0x0 0x60000f20 0x0 0xa8>, <0x0 0x60001000 0x0 0x4000>, - <0x0 0x60200000 0x0 0x100000>, + <0x0 0x60200000 0x0 0x1fe00000>, <0x0 0x01c13000 0x0 0x1000>, <0x0 0x60005000 0x0 0x2000>; reg-names = "parf", "dbi", "elbi", "atu", "addr_space", diff --git a/arch/arm64/boot/dts/qcom/sar2130p-qar2130p.dts b/arch/arm64/boot/dts/qcom/sar2130p-qar2130p.dts new file mode 100644 index 000000000000..74778a5b19ba --- /dev/null +++ b/arch/arm64/boot/dts/qcom/sar2130p-qar2130p.dts @@ -0,0 +1,558 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024, Linaro Limited + */ + +/dts-v1/; + +#include +#include +#include "sar2130p.dtsi" +#include "pm8150.dtsi" + +/ { + model = "Qualcomm Snapdragon AR2 Gen1 Smart Viewer Development Kit"; + compatible = "qcom,qar2130p", "qcom,sar2130p"; + chassis-type = "embedded"; + + aliases { + serial0 = &uart11; + serial1 = &uart7; + i2c0 = &i2c8; + i2c1 = &i2c10; + mmc1 = &sdhc_1; + spi0 = &spi0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + vph_pwr: regulator-vph-pwr { + compatible = "regulator-fixed"; + regulator-name = "vph_pwr"; + regulator-min-microvolt = <3700000>; + regulator-max-microvolt = <3700000>; + regulator-always-on; + }; + + /* pm3003a on I2C0, should not be controlled */ + vreg_ext_1p3: regulator-ext-1p3 { + compatible = "regulator-fixed"; + regulator-name = "vph_ext_1p3"; + regulator-min-microvolt = <1300000>; + regulator-max-microvolt = <1300000>; + regulator-always-on; + vin-supply = <&vph_pwr>; + }; + + /* EBI rail, used as LDO input, can not be part of PMIC config */ + vreg_s10a_0p89: regulator-s10a-0p89 { + compatible = "regulator-fixed"; + regulator-name = "vph_s10a_0p89"; + regulator-min-microvolt = <890000>; + regulator-max-microvolt = <890000>; + regulator-always-on; + vin-supply = <&vph_pwr>; + }; + + thermal-zones { + sar2130p-thermal { + thermal-sensors = <&pm8150_adc_tm 1>; + + trips { + active-config0 { + temperature = <100000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + }; + + wifi-thermal { + thermal-sensors = <&pm8150_adc_tm 2>; + + trips { + active-config0 { + temperature = <52000>; + hysteresis = <4000>; + type = "passive"; + }; + }; + }; + + xo-thermal { + thermal-sensors = <&pm8150_adc_tm 0>; + + trips { + active-config0 { + temperature = <50000>; + hysteresis = <4000>; + type = "passive"; + }; + }; + }; + }; + + wcn7850-pmu { + compatible = "qcom,wcn7850-pmu"; + + pinctrl-0 = <&wlan_en_state>, <&bt_en_state>; + pinctrl-names = "default"; + + wlan-enable-gpios = <&tlmm 45 GPIO_ACTIVE_HIGH>; + bt-enable-gpios = <&tlmm 46 GPIO_ACTIVE_HIGH>; + + vdd-supply = <&vreg_s4a_0p95>; + vddio-supply = <&vreg_l15a_1p8>; + vddaon-supply = <&vreg_s4a_0p95>; + vdddig-supply = <&vreg_s4a_0p95>; + vddrfa1p2-supply = <&vreg_s4a_0p95>; + vddrfa1p8-supply = <&vreg_s5a_1p88>; + + regulators { + vreg_pmu_rfa_cmn: ldo0 { + regulator-name = "vreg_pmu_rfa_cmn"; + }; + + vreg_pmu_aon_0p59: ldo1 { + regulator-name = "vreg_pmu_aon_0p59"; + }; + + vreg_pmu_wlcx_0p8: ldo2 { + regulator-name = "vreg_pmu_wlcx_0p8"; + }; + + vreg_pmu_wlmx_0p85: ldo3 { + regulator-name = "vreg_pmu_wlmx_0p85"; + }; + + vreg_pmu_btcmx_0p85: ldo4 { + regulator-name = "vreg_pmu_btcmx_0p85"; + }; + + vreg_pmu_rfa_0p8: ldo5 { + regulator-name = "vreg_pmu_rfa_0p8"; + }; + + vreg_pmu_rfa_1p2: ldo6 { + regulator-name = "vreg_pmu_rfa_1p2"; + }; + + vreg_pmu_rfa_1p8: ldo7 { + regulator-name = "vreg_pmu_rfa_1p8"; + }; + + vreg_pmu_pcie_0p9: ldo8 { + regulator-name = "vreg_pmu_pcie_0p9"; + }; + + vreg_pmu_pcie_1p8: ldo9 { + regulator-name = "vreg_pmu_pcie_1p8"; + }; + }; + }; +}; + +&apps_rsc { + regulators-0 { + compatible = "qcom,pm8150-rpmh-regulators"; + qcom,pmic-id = "a"; + + vdd-s1-supply = <&vph_pwr>; + vdd-s2-supply = <&vph_pwr>; + vdd-s3-supply = <&vph_pwr>; + vdd-s4-supply = <&vph_pwr>; + vdd-s5-supply = <&vph_pwr>; + vdd-s6-supply = <&vph_pwr>; + vdd-s7-supply = <&vph_pwr>; + vdd-s8-supply = <&vph_pwr>; + vdd-s9-supply = <&vph_pwr>; + vdd-s10-supply = <&vph_pwr>; + vdd-l1-l8-l11-supply = <&vreg_s4a_0p95>; + vdd-l3-l4-l5-l18-supply = <&vreg_ext_1p3>; + vdd-l6-l9-supply = <&vreg_s10a_0p89>; + vdd-l7-l12-l14-l15-supply = <&vreg_s5a_1p88>; + + vreg_s4a_0p95: smps6 { + regulator-name = "vreg_s4a_0p95"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1170000>; + regulator-initial-mode = ; + }; + + vreg_s5a_1p88: smps5 { + regulator-name = "vreg_s5a_1p88"; + regulator-min-microvolt = <1856000>; + regulator-max-microvolt = <2040000>; + regulator-initial-mode = ; + }; + + vreg_l1a_0p91: ldo1 { + regulator-name = "vreg_l1a_0p91"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l2a_3p1: ldo2 { + regulator-name = "vreg_l2a_3p1"; + regulator-min-microvolt = <3080000>; + regulator-max-microvolt = <3544000>; + regulator-initial-mode = ; + }; + + vreg_l3a_1p2: ldo3 { + regulator-name = "vreg_l3a_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1304000>; + regulator-initial-mode = ; + }; + + /* ldo4 1.26 - system ? */ + + vreg_l5a_1p13: ldo5 { + regulator-name = "vreg_l5a_1p13"; + regulator-min-microvolt = <1128000>; + regulator-max-microvolt = <1170000>; + regulator-initial-mode = ; + }; + + vreg_l6a_0p6: ldo6 { + regulator-name = "vreg_l6a_0p6"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <650000>; + regulator-initial-mode = ; + }; + + vreg_l7a_1p8: ldo7 { + regulator-name = "vreg_l7a_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1950000>; + regulator-initial-mode = ; + }; + + vreg_l8a_0p88: ldo8 { + regulator-name = "vreg_l8a_0p88"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <950000>; + regulator-initial-mode = ; + }; + + /* ldo9 - LCX */ + + vreg_l10a_2p95: ldo10 { + regulator-name = "vreg_l10a_2p95"; + regulator-min-microvolt = <2952000>; + regulator-max-microvolt = <3544000>; + regulator-initial-mode = ; + }; + + /* ldo11 - LMX */ + + vreg_l12a_1p8: ldo12 { + regulator-name = "vreg_l12a_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1880000>; + regulator-initial-mode = ; + }; + + /* no ldo13 */ + + vreg_l14a_1p8: ldo14 { + regulator-name = "vreg_l14a_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1880000>; + regulator-initial-mode = ; + }; + + vreg_l15a_1p8: ldo15 { + regulator-name = "vreg_l15a_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + /* no ldo16 - system */ + + vreg_l17a_3p26: ldo17 { + regulator-name = "vreg_l17a_3p26"; + regulator-min-microvolt = <3200000>; + regulator-max-microvolt = <3544000>; + regulator-initial-mode = ; + }; + + vreg_l18a_1p2: ldo18 { + regulator-name = "vreg_l18a_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1304000>; + regulator-initial-mode = ; + }; + }; + +}; + +&gpi_dma0 { + status = "okay"; +}; + +&gpi_dma1 { + status = "okay"; +}; + +&gpu { + status = "okay"; +}; + +&gpu_zap_shader { + firmware-name = "qcom/sar2130p/a620_zap.mbn"; +}; + +&pon_pwrkey { + status = "okay"; +}; + +&pon_resin { + linux,code = ; + + status = "okay"; +}; + +&qupv3_id_0 { + status = "okay"; +}; + +&qupv3_id_1 { + status = "okay"; +}; + +&i2c4 { + clock-frequency = <400000>; + + status = "okay"; +}; + +&i2c8 { + clock-frequency = <400000>; + + status = "okay"; + + ptn3222: redriver@4f { + compatible = "nxp,ptn3222"; + reg = <0x4f>; + + reset-gpios = <&tlmm 99 GPIO_ACTIVE_LOW>; + + vdd3v3-supply = <&vreg_l2a_3p1>; + vdd1v8-supply = <&vreg_l15a_1p8>; + + #phy-cells = <0>; + }; +}; + +&i2c10 { + clock-frequency = <400000>; + + status = "okay"; +}; + +&pcie0 { + perst-gpios = <&tlmm 55 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 57 GPIO_ACTIVE_HIGH>; + + pinctrl-0 = <&pcie0_default_state>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&pcieport0 { + wifi@0 { + compatible = "pci17cb,1107"; + reg = <0x10000 0x0 0x0 0x0 0x0>; + + vddaon-supply = <&vreg_pmu_aon_0p59>; + vddwlcx-supply = <&vreg_pmu_wlcx_0p8>; + vddwlmx-supply = <&vreg_pmu_wlmx_0p85>; + vddrfacmn-supply = <&vreg_pmu_rfa_cmn>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p8-supply = <&vreg_pmu_rfa_1p8>; + vddpcie0p9-supply = <&vreg_pmu_pcie_0p9>; + vddpcie1p8-supply = <&vreg_pmu_pcie_1p8>; + }; +}; + +&pcie0_phy { + vdda-phy-supply = <&vreg_l8a_0p88>; + vdda-pll-supply = <&vreg_l3a_1p2>; + + status = "okay"; +}; + +&pm8150_adc { + channel@4c { + reg = ; + qcom,ratiometric; + qcom,hw-settle-time = <200>; + label = "xo_therm"; + }; + + channel@4d { + reg = ; + qcom,ratiometric; + qcom,hw-settle-time = <200>; + qcom,pre-scaling = <1 1>; + label = "skin_therm"; + }; + + channel@4e { + /* msm-5.10 uses ADC5_AMUX_THM2 / 0x0e, although there is a pullup */ + reg = ; + qcom,hw-settle-time = <200>; + qcom,pre-scaling = <1 1>; + label = "wifi_therm"; + }; +}; + +&pm8150_adc_tm { + status = "okay"; + + xo-therm@0 { + reg = <0>; + io-channels = <&pm8150_adc ADC5_XO_THERM_100K_PU>; + qcom,ratiometric; + qcom,hw-settle-time-us = <200>; + }; + + skin-therm@1 { + reg = <1>; + io-channels = <&pm8150_adc ADC5_AMUX_THM1_100K_PU>; + qcom,ratiometric; + qcom,hw-settle-time-us = <200>; + }; + + wifi-therm@2 { + reg = <2>; + /* msm-5.10 uses ADC5_AMUX_THM2, although there is a pullup */ + io-channels = <&pm8150_adc ADC5_AMUX_THM2_100K_PU>; + qcom,hw-settle-time-us = <200>; + }; +}; + +&remoteproc_adsp { + firmware-name = "qcom/sar2130p/adsp.mbn"; + + status = "okay"; +}; + +&sdhc_1 { + vmmc-supply = <&vreg_l10a_2p95>; + vqmmc-supply = <&vreg_l7a_1p8>; + + status = "okay"; +}; + +&tlmm { + bt_en_state: bt-enable-state { + pins = "gpio46"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + }; + + pcie0_default_state: pcie0-default-state { + perst-pins { + pins = "gpio55"; + function = "gpio"; + drive-strength = <2>; + bias-pull-down; + }; + + clkreq-pins { + pins = "gpio56"; + function = "pcie0_clkreqn"; + drive-strength = <2>; + bias-pull-up; + }; + + wake-pins { + pins = "gpio57"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + pcie1_default_state: pcie1-default-state { + perst-pins { + pins = "gpio58"; + function = "gpio"; + drive-strength = <2>; + bias-pull-down; + }; + + clkreq-pins { + pins = "gpio59"; + function = "pcie1_clkreqn"; + drive-strength = <2>; + bias-pull-up; + }; + + wake-pins { + pins = "gpio60"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + wlan_en_state: wlan-enable-state { + pins = "gpio45"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + }; +}; + +&uart7 { + status = "okay"; + + bluetooth { + compatible = "qcom,wcn7850-bt"; + + vddrfacmn-supply = <&vreg_pmu_rfa_cmn>; + vddaon-supply = <&vreg_pmu_aon_0p59>; + vddwlcx-supply = <&vreg_pmu_wlcx_0p8>; + vddwlmx-supply = <&vreg_pmu_wlmx_0p85>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p8-supply = <&vreg_pmu_rfa_1p8>; + + max-speed = <3200000>; + }; +}; + +&uart11 { + status = "okay"; +}; + +&usb_1 { + status = "okay"; +}; + +&usb_1_hsphy { + vdd-supply = <&vreg_l8a_0p88>; + vdda12-supply = <&vreg_l3a_1p2>; + + phys = <&ptn3222>; + + status = "okay"; +}; + +&usb_dp_qmpphy { + vdda-phy-supply = <&vreg_l3a_1p2>; + vdda-pll-supply = <&vreg_l1a_0p91>; + + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/qcom/sar2130p.dtsi b/arch/arm64/boot/dts/qcom/sar2130p.dtsi new file mode 100644 index 000000000000..dd832e6816be --- /dev/null +++ b/arch/arm64/boot/dts/qcom/sar2130p.dtsi @@ -0,0 +1,3123 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024, Linaro Limited + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/ { + interrupt-parent = <&intc>; + + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + clocks { + xo_board: xo-board { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <19200000>; + }; + + sleep_clk: sleep-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <32764>; + }; + }; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x0>; + clocks = <&cpufreq_hw 0>; + enable-method = "psci"; + next-level-cache = <&l2_0>; + qcom,freq-domain = <&cpufreq_hw 0>; + power-domains = <&cpu_pd0>; + power-domain-names = "psci"; + #cooling-cells = <2>; + + l2_0: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + + l3_0: l3-cache { + compatible = "cache"; + cache-level = <3>; + cache-unified; + }; + }; + }; + + cpu1: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x100>; + clocks = <&cpufreq_hw 0>; + enable-method = "psci"; + next-level-cache = <&l2_100>; + qcom,freq-domain = <&cpufreq_hw 0>; + power-domains = <&cpu_pd1>; + power-domain-names = "psci"; + #cooling-cells = <2>; + + l2_100: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu2: cpu@200 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x200>; + clocks = <&cpufreq_hw 0>; + enable-method = "psci"; + next-level-cache = <&l2_200>; + qcom,freq-domain = <&cpufreq_hw 0>; + power-domains = <&cpu_pd2>; + power-domain-names = "psci"; + #cooling-cells = <2>; + + l2_200: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu3: cpu@300 { + device_type = "cpu"; + compatible = "arm,cortex-a55"; + reg = <0x0 0x300>; + clocks = <&cpufreq_hw 0>; + enable-method = "psci"; + next-level-cache = <&l2_300>; + qcom,freq-domain = <&cpufreq_hw 0>; + power-domains = <&cpu_pd3>; + power-domain-names = "psci"; + #cooling-cells = <2>; + + l2_300: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + }; + }; + + idle-states { + entry-method = "psci"; + + cpu_sleep_0: cpu-sleep-0-0 { + compatible = "arm,idle-state"; + idle-state-name = "silver-power-collapse"; + arm,psci-suspend-param = <0x40000003>; + entry-latency-us = <549>; + exit-latency-us = <901>; + min-residency-us = <1774>; + local-timer-stop; + }; + + cpu_sleep_1: cpu-sleep-0-1 { + compatible = "arm,idle-state"; + idle-state-name = "silver-rail-power-collapse"; + arm,psci-suspend-param = <0x40000004>; + entry-latency-us = <702>; + exit-latency-us = <915>; + min-residency-us = <4001>; + local-timer-stop; + }; + }; + + domain-idle-states { + cluster_sleep_0: cluster-sleep-0 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x41000044>; + entry-latency-us = <2752>; + exit-latency-us = <3048>; + min-residency-us = <6118>; + }; + + cluster_sleep_1: cluster-sleep-1 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x41002344>; + entry-latency-us = <3263>; + exit-latency-us = <4562>; + min-residency-us = <8467>; + }; + + cluster_sleep_2: cluster-sleep-2 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x4100c344>; + entry-latency-us = <3638>; + exit-latency-us = <6562>; + min-residency-us = <9862>; + }; + }; + }; + + firmware { + scm: scm { + compatible = "qcom,scm-sar2130p", "qcom,scm"; + qcom,dload-mode = <&tcsr_mutex 0x13000>; + interconnects = <&system_noc MASTER_CRYPTO QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + }; + }; + + clk_virt: interconnect-0 { + compatible = "qcom,sar2130p-clk-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + mc_virt: interconnect-1 { + compatible = "qcom,sar2130p-mc-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + memory@80000000 { + device_type = "memory"; + /* We expect the bootloader to fill in the size */ + reg = <0x0 0x80000000 0x0 0x0>; + }; + + pmu { + compatible = "arm,armv8-pmuv3"; + interrupts = ; + }; + + psci { + compatible = "arm,psci-1.0"; + method = "smc"; + + cpu_pd0: power-domain-cpu0 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cpu_sleep_0>, <&cpu_sleep_1>; + }; + + cpu_pd1: power-domain-cpu1 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cpu_sleep_0>, <&cpu_sleep_1>; + }; + + cpu_pd2: power-domain-cpu2 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cpu_sleep_0>, <&cpu_sleep_1>; + }; + + cpu_pd3: power-domain-cpu3 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cpu_sleep_0>, <&cpu_sleep_1>; + }; + + cluster_pd: power-domain-cpu-cluster0 { + #power-domain-cells = <0>; + domain-idle-states = <&cluster_sleep_0>, <&cluster_sleep_1>, <&cluster_sleep_2>; + }; + }; + + reserved_memory: reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + hyp_mem: hyp@80000000 { + reg = <0x0 0x80000000 0x0 0x600000>; + no-map; + }; + + xbl_dt_log_mem: xbl-dt-log@80600000 { + reg = <0x0 0x80600000 0x0 0x40000>; + no-map; + }; + + xbl_ramdump_mem: xbl-ramdump@80640000 { + reg = <0x0 0x80640000 0x0 0x1c0000>; + no-map; + }; + + aop_image_mem: aop-image@80800000 { + reg = <0x0 0x80800000 0x0 0x60000>; + no-map; + }; + + aop_cmd_db_mem: aop-cmd-db@80860000 { + compatible = "qcom,cmd-db"; + reg = <0x0 0x80860000 0x0 0x20000>; + no-map; + }; + + aop_config_mem: aop-config@80880000 { + reg = <0x0 0x80880000 0x0 0x20000>; + no-map; + }; + + tme_crash_dump_mem: tme-crash-dump@808a0000 { + reg = <0x0 0x808a0000 0x0 0x40000>; + no-map; + }; + + tme_log_mem: tme-log@808e0000 { + reg = <0x0 0x808e0000 0x0 0x4000>; + no-map; + }; + + uefi_log_mem: uefi-log@808e4000 { + reg = <0x0 0x808e4000 0x0 0x10000>; + no-map; + }; + + secdata_apss_mem: secdata-apss@808ff000 { + reg = <0x0 0x808ff000 0x0 0x1000>; + no-map; + }; + + smem: smem@80900000 { + compatible = "qcom,smem"; + reg = <0x0 0x80900000 0x0 0x200000>; + hwlocks = <&tcsr_mutex 3>; + no-map; + }; + + cpucp_fw_mem: cpucp-fw@80b00000 { + reg = <0x0 0x80b00000 0x0 0x100000>; + no-map; + }; + + helios_ram_dump_mem: helios-ram-dump@80c00000 { + reg = <0x0 0x80c00000 0x0 0xe00000>; + no-map; + }; + + camera_mem: camera@84e00000 { + reg = <0x0 0x84e00000 0x0 0x800000>; + no-map; + }; + + video_mem: video@86f00000 { + reg = <0x0 0x86f00000 0x0 0x500000>; + no-map; + }; + + adsp_mem: adsp@87600000 { + reg = <0x0 0x87600000 0x0 0x1e00000>; + no-map; + }; + + cdsp_mem: cdsp@89400000 { + reg = <0x0 0x89400000 0x0 0xf00000>; + no-map; + }; + + ipa_fw_mem: ipa-fw@8a300000 { + reg = <0x0 0x8a300000 0x0 0x10000>; + no-map; + }; + + ipa_gsi_mem: ipa-gsi@8a3a0000 { + reg = <0x0 0x8a310000 0x0 0xa000>; + no-map; + }; + + gpu_micro_code_mem: gpu-micro-code@8a31a000 { + reg = <0x0 0x8a31a000 0x0 0x2000>; + no-map; + }; + + cvp_mem: cvp@8a400000 { + reg = <0x0 0x8a400000 0x0 0x700000>; + no-map; + }; + + xbl_sc_mem: xbl-sc@a6e00000 { + no-map; + reg = <0x0 0xa6e00000 0x0 0x40000>; + }; + + global_sync_mem: global-sync@a6f00000 { + no-map; + reg = <0x0 0xa6f00000 0x0 0x100000>; + }; + + tz_stat_mem: tz-stat@e8800000 { + no-map; + reg = <0x0 0xe8800000 0x0 0x100000>; + }; + + tags_mem: tags@e8900000 { + no-map; + reg = <0x0 0xe8900000 0x0 0x500000>; + }; + + qtee_mem: qtee@e8e00000 { + no-map; + reg = <0x0 0xe8e00000 0x0 0x500000>; + }; + + trusted_apps_mem: trusted-apps@e9300000 { + no-map; + reg = <0x0 0xe9300000 0x0 0xc00000>; + }; + }; + + smp2p-adsp { + compatible = "qcom,smp2p"; + qcom,smem = <443>, <429>; + interrupts-extended = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_SMP2P + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_SMP2P>; + + qcom,local-pid = <0>; + qcom,remote-pid = <2>; + + smp2p_adsp_out: master-kernel { + qcom,entry-name = "master-kernel"; + #qcom,smem-state-cells = <1>; + }; + + smp2p_adsp_in: slave-kernel { + qcom,entry-name = "slave-kernel"; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + smp2p-cdsp { + compatible = "qcom,smp2p"; + qcom,smem = <94>, <432>; + interrupts-extended = <&ipcc IPCC_CLIENT_CDSP + IPCC_MPROC_SIGNAL_SMP2P + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_CDSP + IPCC_MPROC_SIGNAL_SMP2P>; + + qcom,local-pid = <0>; + qcom,remote-pid = <5>; + + smp2p_cdsp_out: master-kernel { + qcom,entry-name = "master-kernel"; + #qcom,smem-state-cells = <1>; + }; + + smp2p_cdsp_in: slave-kernel { + qcom,entry-name = "slave-kernel"; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + soc: soc@0 { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0 0 0 0 0x10 0>; + dma-ranges = <0 0 0 0 0x10 0>; + + gcc: clock-controller@100000 { + compatible = "qcom,sar2130p-gcc"; + reg = <0x0 0x00100000 0x0 0x1f4200>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&sleep_clk>, + <&pcie0_phy>, + <&pcie1_phy>, + <&usb_dp_qmpphy QMP_USB43DP_USB3_PIPE_CLK>; + }; + + sdhc_1: mmc@7c4000 { + compatible = "qcom,sar2130p-sdhci", "qcom,sdhci-msm-v5"; + reg = <0x0 0x007c4000 0x0 0x1000>, + <0x0 0x007c5000 0x0 0x1000>; + reg-names = "hc", "cqhci"; + + iommus = <&apps_smmu 0x160 0x0>; + interrupts = , + ; + interrupt-names = "hc_irq", "pwr_irq"; + + clocks = <&gcc GCC_SDCC1_AHB_CLK>, + <&gcc GCC_SDCC1_APPS_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "core", "xo"; + interconnects = <&system_noc MASTER_SDCC_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_SDCC_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "sdhc-ddr","cpu-sdhc"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&sdhc1_opp_table>; + + pinctrl-0 = <&sdc1_default>; + pinctrl-1 = <&sdc1_sleep>; + pinctrl-names = "default", "sleep"; + + bus-width = <8>; + non-removable; + supports-cqe; + + mmc-ddr-1_8v; + mmc-hs200-1_8v; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + + status = "disabled"; + + sdhc1_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-100000000 { + opp-hz = /bits/ 64 <100000000>; + required-opps = <&rpmhpd_opp_low_svs>; + opp-peak-kBps = <500000 200000>; + opp-avg-kBps = <104000 0>; + }; + + opp-384000000 { + opp-hz = /bits/ 64 <384000000>; + required-opps = <&rpmhpd_opp_nom>; + opp-peak-kBps = <2500000 1000000>; + opp-avg-kBps = <400000 0>; + }; + }; + }; + + gpi_dma0: dma-controller@900000 { + compatible = "qcom,sar2130p-gpi-dma", "qcom,sm6350-gpi-dma"; + reg = <0x0 0x00900000 0x0 0x60000>; + interrupts = , + , + , + , + , + , + , + , + , + , + , + ; + #dma-cells = <3>; + dma-channels = <12>; + dma-channel-mask = <0x7e>; + iommus = <&apps_smmu 0x76 0x0>; + + status = "disabled"; + }; + + qupv3_id_0: geniqup@9c0000 { + compatible = "qcom,geni-se-qup"; + reg = <0x0 0x009c0000 0x0 0x2000>; + clock-names = "m-ahb", "s-ahb"; + clocks = <&gcc GCC_QUPV3_WRAP_0_M_AHB_CLK>, + <&gcc GCC_QUPV3_WRAP_0_S_AHB_CLK>; + iommus = <&apps_smmu 0x63 0x0>; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + i2c0: i2c@980000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00980000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S0_CLK>; + pinctrl-0 = <&qup_i2c0_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 0 QCOM_GPI_I2C>, + <&gpi_dma0 1 0 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi0: spi@980000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00980000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S0_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi0_data_clk>, <&qup_spi0_cs0>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 0 QCOM_GPI_SPI>, + <&gpi_dma0 1 0 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c1: i2c@984000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00984000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>; + pinctrl-0 = <&qup_i2c1_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 1 QCOM_GPI_I2C>, + <&gpi_dma0 1 1 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi1: spi@984000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00984000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi1_data_clk>, <&qup_spi1_cs>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 1 QCOM_GPI_SPI>, + <&gpi_dma0 1 1 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c2: i2c@988000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00988000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; + pinctrl-0 = <&qup_i2c2_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 2 QCOM_GPI_I2C>, + <&gpi_dma0 1 2 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi2: spi@988000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00988000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi2_data_clk>, <&qup_spi2_cs>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 2 QCOM_GPI_SPI>, + <&gpi_dma0 1 2 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + + i2c3: i2c@98c000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x0098c000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S3_CLK>; + pinctrl-0 = <&qup_i2c3_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 3 QCOM_GPI_I2C>, + <&gpi_dma0 1 3 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi3: spi@98c000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x0098c000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S3_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi3_data_clk>, <&qup_spi3_cs0>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 3 QCOM_GPI_SPI>, + <&gpi_dma0 1 3 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c4: i2c@990000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00990000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S4_CLK>; + pinctrl-0 = <&qup_i2c4_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 4 QCOM_GPI_I2C>, + <&gpi_dma0 1 4 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi4: spi@990000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00990000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S4_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi4_data_clk>, <&qup_spi4_cs0>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 4 QCOM_GPI_SPI>, + <&gpi_dma0 1 4 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c5: i2c@994000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00994000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S5_CLK>; + pinctrl-0 = <&qup_i2c5_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 5 QCOM_GPI_I2C>, + <&gpi_dma0 1 5 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi5: spi@994000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00994000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP0_S5_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi5_data_clk>, <&qup_spi5_cs>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma0 0 5 QCOM_GPI_SPI>, + <&gpi_dma0 1 5 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + }; + + gpi_dma1: dma-controller@a00000 { + compatible = "qcom,sar2130p-gpi-dma", "qcom,sm6350-gpi-dma"; + #dma-cells = <3>; + reg = <0x0 0x00a00000 0x0 0x60000>; + interrupts = , + , + , + , + , + , + , + , + , + , + , + ; + dma-channels = <12>; + dma-channel-mask = <0x7e>; + iommus = <&apps_smmu 0x16 0x0>; + + status = "disabled"; + }; + + qupv3_id_1: geniqup@ac0000 { + compatible = "qcom,geni-se-qup"; + reg = <0x0 0x00ac0000 0x0 0x6000>; + clock-names = "m-ahb", "s-ahb"; + clocks = <&gcc GCC_QUPV3_WRAP_1_M_AHB_CLK>, + <&gcc GCC_QUPV3_WRAP_1_S_AHB_CLK>; + iommus = <&apps_smmu 0x3 0x0>; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + i2c6: i2c@a80000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a80000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>; + pinctrl-0 = <&qup_i2c6_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 0 QCOM_GPI_I2C>, + <&gpi_dma1 1 0 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi6: spi@a80000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a80000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi6_data_clk>, <&qup_spi6_cs>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 0 QCOM_GPI_SPI>, + <&gpi_dma1 1 0 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c7: i2c@a84000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a84000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>; + pinctrl-0 = <&qup_i2c7_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 1 QCOM_GPI_I2C>, + <&gpi_dma1 1 1 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi7: spi@a84000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a84000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi7_data_clk>, <&qup_spi7_cs>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 1 QCOM_GPI_SPI>, + <&gpi_dma1 1 1 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + uart7: serial@a84000 { + compatible = "qcom,geni-uart"; + reg = <0x0 0x00a84000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>; + pinctrl-0 = <&qup_uart7_default>; + pinctrl-names = "default"; + interrupts = ; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config"; + + status = "disabled"; + }; + + i2c8: i2c@a88000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a88000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>; + pinctrl-0 = <&qup_i2c8_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 2 QCOM_GPI_I2C>, + <&gpi_dma1 1 2 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi8: spi@a88000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a88000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi8_data_clk>, <&qup_spi8_cs>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 2 QCOM_GPI_SPI>, + <&gpi_dma1 1 2 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c9: i2c@a8c000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a8c000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>; + pinctrl-0 = <&qup_i2c9_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 3 QCOM_GPI_I2C>, + <&gpi_dma1 1 3 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi9: spi@a8c000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a8c000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi9_data_clk>, <&qup_spi9_cs>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 3 QCOM_GPI_SPI>, + <&gpi_dma1 1 3 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c10: i2c@a90000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a90000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S4_CLK>; + pinctrl-0 = <&qup_i2c10_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 4 QCOM_GPI_I2C>, + <&gpi_dma1 1 4 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi10: spi@a90000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a90000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S4_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi10_data_clk>, <&qup_spi10_cs>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 4 QCOM_GPI_SPI>, + <&gpi_dma1 1 4 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c11: i2c@a94000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a94000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S5_CLK>; + pinctrl-0 = <&qup_i2c11_data_clk>; + pinctrl-names = "default"; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 5 QCOM_GPI_I2C>, + <&gpi_dma1 1 5 QCOM_GPI_I2C>; + dma-names = "tx", "rx"; + + status = "disabled"; + }; + + spi11: spi@a94000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a94000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S5_CLK>; + interrupts = ; + pinctrl-0 = <&qup_spi11_data_clk>, <&qup_spi11_cs>; + pinctrl-names = "default"; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_A2NOC_SNOC QCOM_ICC_TAG_ALWAYS + &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, + <&system_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", "qup-config", "qup-memory"; + dmas = <&gpi_dma1 0 5 QCOM_GPI_SPI>, + <&gpi_dma1 1 5 QCOM_GPI_SPI>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + uart11: serial@a94000 { + compatible = "qcom,geni-debug-uart"; + reg = <0x0 0x00a94000 0x0 0x4000>; + clock-names = "se"; + clocks = <&gcc GCC_QUPV3_WRAP1_S5_CLK>; + pinctrl-0 = <&qup_uart11_default>; + pinctrl-names = "default"; + interrupts = ; + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + status = "disabled"; + }; + }; + + config_noc: interconnect@1500000 { + compatible = "qcom,sar2130p-config-noc"; + reg = <0x0 0x01500000 0x0 0x10>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + system_noc: interconnect@1680000 { + compatible = "qcom,sar2130p-system-noc"; + reg = <0x0 0x01680000 0x0 0x29080>; + clocks = <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + pcie_noc: interconnect@16c0000 { + compatible = "qcom,sar2130p-pcie-anoc"; + reg = <0x0 0x016c0000 0x0 0xa080>; + clocks = <&gcc GCC_AGGRE_NOC_PCIE_1_AXI_CLK>, + <&gcc GCC_CFG_NOC_PCIE_ANOC_AHB_CLK>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + mmss_noc: interconnect@1740000 { + compatible = "qcom,sar2130p-mmss-noc"; + reg = <0x0 0x01740000 0x0 0x1f100>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + pcie0: pcie@1c00000 { + device_type = "pci"; + compatible = "qcom,sar2130p-pcie", "qcom,pcie-sm8550"; + reg = <0x0 0x01c00000 0x0 0x3000>, + <0x0 0x60000000 0x0 0xf1d>, + <0x0 0x60000f20 0x0 0xa8>, + <0x0 0x60001000 0x0 0x1000>, + <0x0 0x60100000 0x0 0x100000>, + <0x0 0x01c0c000 0x0 0x1000>; + reg-names = "parf", "dbi", "elbi", "atu", "config", "mhi"; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x0 0x60200000 0x0 0x100000>, + <0x02000000 0x0 0x60300000 0x0 0x60300000 0x0 0x3d00000>; + bus-range = <0x00 0xff>; + + dma-coherent; + + linux,pci-domain = <0>; + num-lanes = <2>; + + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "msi0", + "msi1", + "msi2", + "msi3", + "msi4", + "msi5", + "msi6", + "msi7"; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc 0 0 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ + <0 0 0 2 &intc 0 0 0 150 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ + <0 0 0 3 &intc 0 0 0 151 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ + <0 0 0 4 &intc 0 0 0 152 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ + + clocks = <&gcc GCC_PCIE_0_AUX_CLK>, + <&gcc GCC_PCIE_0_CFG_AHB_CLK>, + <&gcc GCC_PCIE_0_MSTR_AXI_CLK>, + <&gcc GCC_PCIE_0_SLV_AXI_CLK>, + <&gcc GCC_PCIE_0_SLV_Q2A_AXI_CLK>, + <&gcc GCC_DDRSS_PCIE_SF_CLK>, + <&gcc GCC_AGGRE_NOC_PCIE_1_AXI_CLK>; + clock-names = "aux", + "cfg", + "bus_master", + "bus_slave", + "slave_q2a", + "ddrss_sf_tbu", + "noc_aggr"; + + interconnects = <&pcie_noc MASTER_PCIE_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_PCIE_0 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "pcie-mem", "cpu-pcie"; + + iommu-map = <0x0 &apps_smmu 0x1c00 0x1>, + <0x100 &apps_smmu 0x1c01 0x1>; + + resets = <&gcc GCC_PCIE_0_BCR>; + reset-names = "pci"; + + power-domains = <&gcc PCIE_0_GDSC>; + + phys = <&pcie0_phy>; + phy-names = "pciephy"; + + status = "disabled"; + + pcieport0: pcie@0 { + device_type = "pci"; + reg = <0x0 0x0 0x0 0x0 0x0>; + bus-range = <0x01 0xff>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + }; + }; + + pcie0_phy: phy@1c06000 { + compatible = "qcom,sar2130p-qmp-gen3x2-pcie-phy"; + reg = <0x0 0x01c06000 0x0 0x2000>; + + clocks = <&gcc GCC_PCIE_0_AUX_CLK>, + <&gcc GCC_PCIE_0_CFG_AHB_CLK>, + <&tcsr TCSR_PCIE_0_CLKREF_EN>, + <&gcc GCC_PCIE_0_PHY_RCHNG_CLK>, + <&gcc GCC_PCIE_0_PIPE_CLK>; + clock-names = "aux", "cfg_ahb", "ref", "rchng", + "pipe"; + + resets = <&gcc GCC_PCIE_0_PHY_BCR>; + reset-names = "phy"; + + assigned-clocks = <&gcc GCC_PCIE_0_PHY_RCHNG_CLK>; + assigned-clock-rates = <100000000>; + + power-domains = <&gcc PCIE_0_PHY_GDSC>; + + #clock-cells = <0>; + clock-output-names = "pcie0_pipe_clk"; + + #phy-cells = <0>; + + status = "disabled"; + }; + + pcie1: pcie@1c08000 { + device_type = "pci"; + compatible = "qcom,sar2130p-pcie", "qcom,pcie-sm8550"; + reg = <0x0 0x01c08000 0x0 0x3000>, + <0x0 0x40000000 0x0 0xf1d>, + <0x0 0x40000f20 0x0 0xa8>, + <0x0 0x40001000 0x0 0x1000>, + <0x0 0x40100000 0x0 0x100000>, + <0x0 0x01c0b000 0x0 0x1000>; + reg-names = "parf", "dbi", "elbi", "atu", "config", "mhi"; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>, + <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>; + bus-range = <0x00 0xff>; + + dma-coherent; + + linux,pci-domain = <1>; + num-lanes = <2>; + + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "msi0", + "msi1", + "msi2", + "msi3", + "msi4", + "msi5", + "msi6", + "msi7"; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ + <0 0 0 2 &intc 0 0 0 435 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ + <0 0 0 3 &intc 0 0 0 438 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ + <0 0 0 4 &intc 0 0 0 439 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ + + clocks = <&gcc GCC_PCIE_1_AUX_CLK>, + <&gcc GCC_PCIE_1_CFG_AHB_CLK>, + <&gcc GCC_PCIE_1_MSTR_AXI_CLK>, + <&gcc GCC_PCIE_1_SLV_AXI_CLK>, + <&gcc GCC_PCIE_1_SLV_Q2A_AXI_CLK>, + <&gcc GCC_DDRSS_PCIE_SF_CLK>, + <&gcc GCC_AGGRE_NOC_PCIE_1_AXI_CLK>, + <&gcc GCC_CFG_NOC_PCIE_ANOC_AHB_CLK>, + <&gcc GCC_QMIP_PCIE_AHB_CLK>; + clock-names = "aux", + "cfg", + "bus_master", + "bus_slave", + "slave_q2a", + "ddrss_sf_tbu", + "noc_aggr", + "cnoc_sf_axi", + "qmip_pcie_ahb"; + + assigned-clocks = <&gcc GCC_PCIE_1_AUX_CLK>; + assigned-clock-rates = <19200000>; + + interconnects = <&pcie_noc MASTER_PCIE_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_PCIE_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "pcie-mem", "cpu-pcie"; + + iommu-map = <0x0 &apps_smmu 0x1e00 0x1>, + <0x100 &apps_smmu 0x1e01 0x1>; + + resets = <&gcc GCC_PCIE_1_BCR>, + <&gcc GCC_PCIE_1_LINK_DOWN_BCR>; + reset-names = "pci", "link_down"; + + power-domains = <&gcc PCIE_1_GDSC>; + + phys = <&pcie1_phy>; + phy-names = "pciephy"; + + status = "disabled"; + + pcie@0 { + device_type = "pci"; + reg = <0x0 0x0 0x0 0x0 0x0>; + bus-range = <0x01 0xff>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + }; + }; + + pcie1_phy: phy@1c0e000 { + compatible = "qcom,sar2130p-qmp-gen3x2-pcie-phy"; + reg = <0x0 0x01c0e000 0x0 0x2000>; + + clocks = <&gcc GCC_PCIE_1_AUX_CLK>, + <&gcc GCC_PCIE_1_CFG_AHB_CLK>, + <&tcsr TCSR_PCIE_1_CLKREF_EN>, + <&gcc GCC_PCIE_1_PHY_RCHNG_CLK>, + <&gcc GCC_PCIE_1_PIPE_CLK>; + clock-names = "aux", "cfg_ahb", "ref", "rchng", + "pipe"; + + resets = <&gcc GCC_PCIE_1_PHY_BCR>; + reset-names = "phy"; + + assigned-clocks = <&gcc GCC_PCIE_1_PHY_RCHNG_CLK>; + assigned-clock-rates = <100000000>; + + power-domains = <&gcc PCIE_1_PHY_GDSC>; + + #clock-cells = <0>; + clock-output-names = "pcie1_pipe_clk"; + + #phy-cells = <0>; + + status = "disabled"; + }; + + tcsr_mutex: hwlock@1f40000 { + compatible = "qcom,tcsr-mutex"; + reg = <0x0 0x01f40000 0x0 0x20000>; + + #hwlock-cells = <1>; + }; + + tcsr: clock-controller@1fc0000 { + compatible = "qcom,sar2130p-tcsr", "syscon"; + reg = <0x0 0x01fc0000 0x0 0x30000>; + clocks = <&rpmhcc RPMH_CXO_CLK>; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + remoteproc_adsp: remoteproc@3000000 { + compatible = "qcom,sar2130p-adsp-pas"; + reg = <0x0 0x03000000 0x0 0x10000>; + + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", "fatal", "ready", + "handover", "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + power-domains = <&rpmhpd RPMHPD_LCX>, + <&rpmhpd RPMHPD_LMX>; + power-domain-names = "lcx", "lmx"; + + memory-region = <&adsp_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_adsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + remoteproc_adsp_glink: glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + label = "lpass"; + qcom,remote-pid = <2>; + + gpr { + compatible = "qcom,gpr"; + qcom,glink-channels = "adsp_apps"; + qcom,domain = ; + qcom,intents = <512 20>; + #address-cells = <1>; + #size-cells = <0>; + + q6apm: service@1 { + compatible = "qcom,q6apm"; + reg = ; + #sound-dai-cells = <0>; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6apmdai: dais { + compatible = "qcom,q6apm-dais"; + iommus = <&apps_smmu 0x1801 0x0>; + }; + + q6apmbedai: bedais { + compatible = "qcom,q6apm-lpass-dais"; + #sound-dai-cells = <1>; + }; + }; + + q6prm: service@2 { + compatible = "qcom,q6prm"; + reg = ; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6prmcc: clock-controller { + compatible = "qcom,q6prm-lpass-clocks"; + #clock-cells = <2>; + }; + }; + }; + + fastrpc { + compatible = "qcom,fastrpc"; + qcom,glink-channels = "fastrpcglink-apps-dsp"; + label = "adsp"; + qcom,non-secure-domain; + #address-cells = <1>; + #size-cells = <0>; + + compute-cb@3 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <3>; + iommus = <&apps_smmu 0x1803 0x0>; + }; + + compute-cb@4 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <4>; + iommus = <&apps_smmu 0x1804 0x0>; + }; + + compute-cb@5 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <5>; + iommus = <&apps_smmu 0x1805 0x0>; + }; + + compute-cb@6 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <6>; + iommus = <&apps_smmu 0x1806 0x0>; + }; + }; + }; + }; + + gpu: gpu@3d00000 { + compatible = "qcom,adreno-621.0", "qcom,adreno"; + reg = <0x0 0x03d00000 0x0 0x40000>, + <0x0 0x03d9e000 0x0 0x2000>, + <0x0 0x03d61000 0x0 0x800>; + reg-names = "kgsl_3d0_reg_memory", + "cx_mem", + "cx_dbgc"; + + interrupts = ; + + iommus = <&adreno_smmu 0 0x401>; + + operating-points-v2 = <&gpu_opp_table>; + + qcom,gmu = <&gmu>; + + nvmem-cells = <&gpu_speed_bin>; + nvmem-cell-names = "speed_bin"; + #cooling-cells = <2>; + + status = "disabled"; + + gpu_zap_shader: zap-shader { + memory-region = <&gpu_micro_code_mem>; + }; + + gpu_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-843000000 { + opp-hz = /bits/ 64 <843000000>; + opp-level = ; + opp-supported-hw = <0x1>; + }; + + opp-780000000 { + opp-hz = /bits/ 64 <780000000>; + opp-level = ; + opp-supported-hw = <0x1>; + }; + + opp-644000000 { + opp-hz = /bits/ 64 <644000000>; + opp-level = ; + opp-supported-hw = <0x3>; + }; + + opp-570000000 { + opp-hz = /bits/ 64 <570000000>; + opp-level = ; + opp-supported-hw = <0x3>; + }; + + opp-450000000 { + opp-hz = /bits/ 64 <450000000>; + opp-level = ; + opp-supported-hw = <0x3>; + }; + + opp-320000000 { + opp-hz = /bits/ 64 <320000000>; + opp-level = ; + opp-supported-hw = <0x3>; + }; + + opp-235000000 { + opp-hz = /bits/ 64 <235000000>; + opp-level = ; + opp-supported-hw = <0x3>; + }; + }; + }; + + gmu: gmu@3d6a000 { + compatible = "qcom,adreno-gmu-621.0", "qcom,adreno-gmu"; + reg = <0x0 0x03d6a000 0x0 0x35000>, + <0x0 0x03de0000 0x0 0x10000>, + <0x0 0x0b290000 0x0 0x10000>; + reg-names = "gmu", "rscc", "gmu_pdc"; + + interrupts = , + ; + interrupt-names = "hfi", "gmu"; + + clocks = <&gpucc GPU_CC_AHB_CLK>, + <&gpucc GPU_CC_CX_GMU_CLK>, + <&gpucc GPU_CC_CXO_CLK>, + <&gcc GCC_DDRSS_GPU_AXI_CLK>, + <&gcc GCC_GPU_MEMNOC_GFX_CLK>, + <&gpucc GPU_CC_HUB_CX_INT_CLK>; + clock-names = "ahb", + "gmu", + "cxo", + "axi", + "memnoc", + "hub"; + + power-domains = <&gpucc GPU_CX_GDSC>, + <&gpucc GPU_GX_GDSC>; + power-domain-names = "cx", + "gx"; + + iommus = <&adreno_smmu 5 0x400>; + + qcom,qmp = <&aoss_qmp>; + + operating-points-v2 = <&gmu_opp_table>; + + gmu_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-220000000 { + opp-hz = /bits/ 64 <220000000>; + opp-level = ; + }; + + opp-550000000 { + opp-hz = /bits/ 64 <550000000>; + opp-level = ; + }; + }; + }; + + gpucc: clock-controller@3d90000 { + compatible = "qcom,sar2130p-gpucc"; + reg = <0x0 0x03d90000 0x0 0xa000>; + + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_GPU_GPLL0_CLK_SRC>, + <&gcc GCC_GPU_GPLL0_DIV_CLK_SRC>; + + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + + adreno_smmu: iommu@3da0000 { + compatible = "qcom,sar2130p-smmu-500", "qcom,adreno-smmu", + "qcom,smmu-500", "arm,mmu-500"; + reg = <0x0 0x03da0000 0x0 0x10000>; + #iommu-cells = <2>; + #global-interrupts = <1>; + interrupts = , + , + , + , + , + , + , + , + ; + + clocks = <&gpucc GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK>, + <&gcc GCC_GPU_MEMNOC_GFX_CLK>, + <&gcc GCC_GPU_SNOC_DVM_GFX_CLK>, + <&gpucc GPU_CC_AHB_CLK>; + clock-names = "hlos", + "bus", + "iface", + "ahb"; + power-domains = <&gpucc GPU_CX_GDSC>; + dma-coherent; + }; + + usb_1_hsphy: phy@88e3000 { + compatible = "qcom,sar2130p-snps-eusb2-phy", + "qcom,sm8550-snps-eusb2-phy"; + reg = <0x0 0x088e3000 0x0 0x154>; + #phy-cells = <0>; + + clocks = <&tcsr TCSR_USB2_CLKREF_EN>; + clock-names = "ref"; + + resets = <&gcc GCC_QUSB2PHY_PRIM_BCR>; + + status = "disabled"; + }; + + usb_dp_qmpphy: phy@88e8000 { + compatible = "qcom,sar2130p-qmp-usb3-dp-phy"; + reg = <0x0 0x088e8000 0x0 0x3000>; + + clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, + <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; + clock-names = "aux", "ref", "com_aux", "usb3_pipe"; + + power-domains = <&gcc USB3_PHY_GDSC>; + + resets = <&gcc GCC_USB3_PHY_PRIM_BCR>, + <&gcc GCC_USB3_DP_PHY_PRIM_BCR>; + reset-names = "phy", "common"; + + #clock-cells = <1>; + #phy-cells = <1>; + + orientation-switch; + + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + usb_dp_qmpphy_out: endpoint { + }; + }; + + port@1 { + reg = <1>; + + usb_dp_qmpphy_usb_ss_in: endpoint { + remote-endpoint = <&usb_1_dwc3_ss>; + }; + }; + + port@2 { + reg = <2>; + + usb_dp_qmpphy_dp_in: endpoint { + }; + }; + }; + }; + + usb_1: usb@a6f8800 { + compatible = "qcom,sar2130p-dwc3", "qcom,dwc3"; + reg = <0x0 0x0a6f8800 0x0 0x400>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>, + <&gcc GCC_USB30_PRIM_MASTER_CLK>, + <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>, + <&gcc GCC_USB30_PRIM_SLEEP_CLK>, + <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>, + <&tcsr TCSR_USB3_CLKREF_EN>; + clock-names = "cfg_noc", + "core", + "iface", + "sleep", + "mock_utmi", + "xo"; + + assigned-clocks = <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>, + <&gcc GCC_USB30_PRIM_MASTER_CLK>; + assigned-clock-rates = <19200000>, <200000000>; + + interrupts-extended = <&intc GIC_SPI 350 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 349 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 14 IRQ_TYPE_EDGE_BOTH>, + <&pdc 15 IRQ_TYPE_EDGE_BOTH>, + <&pdc 17 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "pwr_event", + "hs_phy_irq", + "dp_hs_phy_irq", + "dm_hs_phy_irq", + "ss_phy_irq"; + + power-domains = <&gcc USB30_PRIM_GDSC>; + required-opps = <&rpmhpd_opp_nom>; + + resets = <&gcc GCC_USB30_PRIM_BCR>; + + interconnects = <&system_noc MASTER_USB3_0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_USB3_0 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "usb-ddr", "apps-usb"; + + status = "disabled"; + + usb_1_dwc3: usb@a600000 { + compatible = "snps,dwc3"; + reg = <0x0 0x0a600000 0x0 0xcd00>; + interrupts = ; + iommus = <&apps_smmu 0x20 0x0>; + phys = <&usb_1_hsphy>, + <&usb_dp_qmpphy QMP_USB43DP_USB3_PHY>; + phy-names = "usb2-phy", "usb3-phy"; + + snps,has-lpm-erratum; + snps,hird-threshold = /bits/ 8 <0x0>; + snps,is-utmi-l1-suspend; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; + snps,dis_u2_susphy_quirk; + snps,dis_u3_susphy_quirk; + snps,parkmode-disable-ss-quirk; + + tx-fifo-resize; + dma-coherent; + usb-role-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + usb_1_dwc3_hs: endpoint { + }; + }; + + port@1 { + reg = <1>; + + usb_1_dwc3_ss: endpoint { + remote-endpoint = <&usb_dp_qmpphy_usb_ss_in>; + }; + }; + }; + }; + }; + + pdc: interrupt-controller@b220000 { + compatible = "qcom,sar2130p-pdc", "qcom,pdc"; + reg = <0x0 0x0b220000 0x0 0x30000>, <0x0 0x174000f0 0x0 0x64>; + qcom,pdc-ranges = <0 480 94>, + <94 609 31>, + <125 63 1>, + <126 716 12>; + #interrupt-cells = <2>; + interrupt-parent = <&intc>; + interrupt-controller; + }; + + aoss_qmp: power-management@c300000 { + compatible = "qcom,sar2130p-aoss-qmp", "qcom,aoss-qmp"; + reg = <0x0 0x0c300000 0x0 0x400>; + interrupt-parent = <&ipcc>; + interrupts-extended = <&ipcc IPCC_CLIENT_AOP IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_AOP IPCC_MPROC_SIGNAL_GLINK_QMP>; + + #clock-cells = <0>; + }; + + tsens0: thermal-sensor@c263000 { + compatible = "qcom,sar2130p-tsens", "qcom,tsens-v2"; + reg = <0x0 0x0c263000 0x0 0x1000>, /* TM */ + <0x0 0x0c222000 0x0 0x1000>; /* SROT */ + #qcom,sensors = <16>; + interrupts = , + ; + interrupt-names = "uplow", "critical"; + #thermal-sensor-cells = <1>; + }; + + sram@c3f0000 { + compatible = "qcom,rpmh-stats"; + reg = <0x0 0x0c3f0000 0x0 0x400>; + }; + + arbiter@c400000 { + compatible = "qcom,sar2130p-spmi-pmic-arb", + "qcom,x1e80100-spmi-pmic-arb"; + reg = <0x0 0x0c400000 0x0 0x3000>, + <0x0 0x0c500000 0x0 0x400000>, + <0x0 0x0c440000 0x0 0x80000>; + reg-names = "core", "chnls", "obsrvr"; + + qcom,ee = <0>; + qcom,channel = <0>; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + spmi_bus: spmi@c42d000 { + reg = <0x0 0x0c42d000 0x0 0x4000>, + <0x0 0x0c4c0000 0x0 0x10000>; + reg-names = "cnfg", "intr"; + + interrupt-names = "periph_irq"; + interrupts-extended = <&pdc 1 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <4>; + + #address-cells = <2>; + #size-cells = <0>; + }; + }; + + ipcc: mailbox@ed18000 { + compatible = "qcom,sar2130p-ipcc", "qcom,ipcc"; + reg = <0x0 0x0ed18000 0x0 0x1000>; + + interrupts = ; + interrupt-controller; + #interrupt-cells = <3>; + + #mbox-cells = <2>; + }; + + tlmm: pinctrl@f100000 { + compatible = "qcom,sar2130p-tlmm"; + reg = <0x0 0x0f100000 0x0 0x300000>; + interrupts = ; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + gpio-ranges = <&tlmm 0 0 156>; + wakeup-parent = <&pdc>; + + qup_i2c0_data_clk: qup-i2c0-data-clk-state { + /* SDA, SCL */ + pins = "gpio0", "gpio1"; + function = "qup0"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c1_data_clk: qup-i2c1-data-clk-state { + /* SDA, SCL */ + pins = "gpio2", "gpio3"; + function = "qup1"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c2_data_clk: qup-i2c2-data-clk-state { + /* SDA, SCL */ + pins = "gpio22", "gpio23"; + function = "qup2"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c3_data_clk: qup-i2c3-data-clk-state { + /* SDA, SCL */ + pins = "gpio16", "gpio17"; + function = "qup3"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c4_data_clk: qup-i2c4-data-clk-state { + /* SDA, SCL */ + pins = "gpio20", "gpio21"; + function = "qup4"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c5_data_clk: qup-i2c5-data-clk-state { + /* SDA, SCL */ + pins = "gpio95", "gpio96"; + function = "qup5"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c6_data_clk: qup-i2c6-data-clk-state { + /* SDA, SCL */ + pins = "gpio91", "gpio92"; + function = "qup6"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c7_data_clk: qup-i2c7-data-clk-state { + /* SDA, SCL */ + pins = "gpio8", "gpio9"; + function = "qup7"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c8_data_clk: qup-i2c8-data-clk-state { + /* SDA, SCL */ + pins = "gpio8", "gpio9"; + function = "qup8"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c9_data_clk: qup-i2c9-data-clk-state { + /* SDA, SCL */ + pins = "gpio109", "gpio110"; + function = "qup9"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c10_data_clk: qup-i2c10-data-clk-state { + /* SDA, SCL */ + pins = "gpio4", "gpio5"; + function = "qup10"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c11_data_clk: qup-i2c11-data-clk-state { + /* SDA, SCL */ + pins = "gpio28", "gpio30"; + function = "qup11"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_spi0_cs0: qup-spi0-cs0-state { + pins = "gpio3"; + function = "qup0"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi0_cs1: qup-spi0-cs1-state { + pins = "gpio93"; + function = "qup0"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi0_data_clk: qup-spi0-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio0", "gpio1", "gpio2"; + function = "qup0"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi1_cs: qup-spi1-cs-state { + pins = "gpio62"; + function = "qup1"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi1_data_clk: qup-spi1-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio2", "gpio3", "gpio61"; + function = "qup1"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi2_cs: qup-spi2-cs-state { + pins = "gpio13"; + function = "qup2"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi2_data_clk: qup-spi2-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio22", "gpio23", "gpio12"; + function = "qup2"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi3_cs0: qup-spi3-cs0-state { + pins = "gpio19"; + function = "qup3"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi3_cs1: qup-spi3-cs1-state { + pins = "gpio41"; + function = "qup3"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi3_data_clk: qup-spi3-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio16", "gpio17", "gpio18"; + function = "qup3"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi4_cs0: qup-spi4-cs0-state { + pins = "gpio23"; + function = "qup4"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi4_cs1: qup-spi4-cs1-state { + pins = "gpio94"; + function = "qup4"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi4_data_clk: qup-spi4-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio20", "gpio21", "gpio22"; + function = "qup4"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi5_cs: qup-spi5-cs-state { + pins = "gpio98"; + function = "qup5"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi5_data_clk: qup-spi5-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio95", "gpio96", "gpio97"; + function = "qup5"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi6_cs: qup-spi6-cs-state { + pins = "gpio63"; + function = "qup6"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi6_data_clk: qup-spi6-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio91", "gpio92", "gpio64"; + function = "qup6"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi7_cs: qup-spi7-cs-state { + pins = "gpio27"; + function = "qup7"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi7_data_clk: qup-spi7-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio24", "gpio25", "gpio26"; + function = "qup7"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi8_cs: qup-spi8-cs-state { + pins = "gpio11"; + function = "qup8"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi8_data_clk: qup-spi8-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio8", "gpio9", "gpio10"; + function = "qup8"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi9_cs: qup-spi9-cs-state { + pins = "gpio35"; + function = "qup9"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi9_data_clk: qup-spi9-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio109", "gpio110", "gpio34"; + function = "qup9"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi10_cs: qup-spi10-cs-state { + pins = "gpio7"; + function = "qup10"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi10_data_clk: qup-spi10-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio4", "gpio5", "gpio6"; + function = "qup10"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi11_cs: qup-spi11-cs-state { + pins = "gpio15"; + function = "qup11"; + drive-strength = <2>; + bias-disable; + }; + + qup_spi11_data_clk: qup-spi11-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio28", "gpio30", "gpio14"; + function = "qup11"; + drive-strength = <2>; + bias-disable; + }; + + qup_uart7_default: qup-uart7-default-state { + cts-pins { + pins = "gpio24"; + function = "qup7"; + drive-strength = <2>; + bias-disable; + }; + + rts-pins { + pins = "gpio25"; + function = "qup7"; + drive-strength = <2>; + bias-pull-down; + }; + + rx-pins { + pins = "gpio27"; + function = "qup7"; + drive-strength = <2>; + bias-pull-down; + }; + + tx-pins { + pins = "gpio26"; + function = "qup7"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + qup_uart11_default: qup-uart11-default-state { + pins = "gpio14", "gpio15"; + function = "qup11"; + drive-strength = <2>; + bias-disable; + }; + + sdc1_default: sdc1-default-state { + clk-pins { + pins = "sdc1_clk"; + drive-strength = <16>; + bias-disable; + }; + + cmd-pins { + pins = "sdc1_cmd"; + drive-strength = <10>; + bias-pull-up; + }; + + data-pins { + pins = "sdc1_data"; + drive-strength = <10>; + bias-pull-up; + }; + + rclk-pins { + pins = "sdc1_rclk"; + bias-pull-down; + }; + }; + + sdc1_sleep: sdc1-sleep-state { + clk-pins { + pins = "sdc1_clk"; + drive-strength = <2>; + bias-disable; + }; + + cmd-pins { + pins = "sdc1_cmd"; + drive-strength = <2>; + bias-pull-up; + }; + + data-pins { + pins = "sdc1_data"; + drive-strength = <2>; + bias-pull-up; + }; + + rclk-pins { + pins = "sdc1_rclk"; + bias-pull-down; + }; + }; + }; + + apps_smmu: iommu@15000000 { + compatible = "qcom,sar2130p-smmu-500", "qcom,smmu-500", "arm,mmu-500"; + reg = <0x0 0x15000000 0x0 0x100000>; + #iommu-cells = <2>; + #global-interrupts = <1>; + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + dma-coherent; + }; + + intc: interrupt-controller@17200000 { + compatible = "arm,gic-v3"; + #interrupt-cells = <3>; + interrupt-controller; + #redistributor-regions = <1>; + redistributor-stride = <0x0 0x20000>; + reg = <0x0 0x17200000 0x0 0x10000>, + <0x0 0x17260000 0x0 0x100000>; + interrupts = ; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + gic_its: msi-controller@17240000 { + compatible = "arm,gic-v3-its"; + reg = <0x0 0x17240000 0x0 0x20000>; + msi-controller; + #msi-cells = <1>; + }; + }; + + apps_rsc: rsc@17a00000 { + label = "apps_rsc"; + compatible = "qcom,rpmh-rsc"; + reg = <0x0 0x17a00000 0x0 0x10000>, + <0x0 0x17a10000 0x0 0x10000>, + <0x0 0x17a20000 0x0 0x10000>; + reg-names = "drv-0", "drv-1", "drv-2"; + interrupts = , + , + ; + qcom,tcs-offset = <0xd00>; + qcom,drv-id = <2>; + qcom,tcs-config = , , + , ; + power-domains = <&cluster_pd>; + + apps_bcm_voter: bcm-voter { + compatible = "qcom,bcm-voter"; + }; + + rpmhcc: clock-controller { + compatible = "qcom,sar2130p-rpmh-clk"; + #clock-cells = <1>; + clock-names = "xo"; + clocks = <&xo_board>; + }; + + rpmhpd: power-controller { + compatible = "qcom,sar2130p-rpmhpd"; + #power-domain-cells = <1>; + operating-points-v2 = <&rpmhpd_opp_table>; + + rpmhpd_opp_table: opp-table { + compatible = "operating-points-v2"; + + rpmhpd_opp_ret: opp1 { + opp-level = ; + }; + + rpmhpd_opp_min_svs: opp2 { + opp-level = ; + }; + + rpmhpd_opp_low_svs_d1: opp3 { + opp-level = ; + }; + + rpmhpd_opp_low_svs: opp4 { + opp-level = ; + }; + + rpmhpd_opp_svs: opp5 { + opp-level = ; + }; + + rpmhpd_opp_svs_l1: opp6 { + opp-level = ; + }; + + rpmhpd_opp_nom: opp7 { + opp-level = ; + }; + + rpmhpd_opp_turbo: opp8 { + opp-level = ; + }; + + rpmhpd_opp_turbo_l1: opp9 { + opp-level = ; + }; + }; + }; + }; + + cpufreq_hw: cpufreq@17d91000 { + compatible = "qcom,sar2130p-cpufreq-epss", "qcom,cpufreq-epss"; + reg = <0x0 0x17d91000 0x0 0x1000>; + reg-names = "freq-domain0"; + clocks = <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_GPLL0>; + clock-names = "xo", "alternate"; + interrupts = ; + interrupt-names = "dcvsh-irq-0"; + #freq-domain-cells = <1>; + #clock-cells = <1>; + }; + + gem_noc: interconnect@19100000 { + compatible = "qcom,sar2130p-gem-noc"; + reg = <0x0 0x19100000 0x0 0xa2080>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + /* + * Bootloader expects just cache-controller node instead of + * the typical system-cache-controller + */ + llcc: cache-controller@19200000 { + compatible = "qcom,sar2130p-llcc"; + reg = <0x0 0x19200000 0x0 0x80000>, + <0x0 0x19300000 0x0 0x80000>, + <0x0 0x19a00000 0x0 0x80000>, + <0x0 0x19c00000 0x0 0x80000>, + <0x0 0x19af0000 0x0 0x80000>, + <0x0 0x19cf0000 0x0 0x80000>; + reg-names = "llcc0_base", + "llcc1_base", + "llcc_broadcast_base", + "llcc_broadcast_and_base", + "llcc_scratchpad_broadcast_base", + "llcc_scratchpad_broadcast_and_base"; + interrupts = ; + }; + + qfprom: qfprom@221c8000 { + compatible = "qcom,sar2130p-qfprom", "qcom,qfprom"; + reg = <0x0 0x221c8000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + read-only; + + gpu_speed_bin: gpu-speed-bin@119 { + reg = <0x119 0x2>; + bits = <5 8>; + }; + }; + + nsp_noc: interconnect@320c0000 { + compatible = "qcom,sar2130p-nsp-noc"; + reg = <0x0 0x320c0000 0x0 0x10>; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + lpass_ag_noc: interconnect@3c40000 { + compatible = "qcom,sar2130p-lpass-ag-noc"; + reg = <0x0 0x3c40000 0x0 0x10>; + #interconnect-cells = <1>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + + interrupts = , + , + , + ; + }; + + thermal-zones { + aoss0-thermal { + thermal-sensors = <&tsens0 0>; + + trips { + trip-point0 { + temperature = <115000>; + hysteresis = <5000>; + type = "hot"; + }; + + aoss0-critical { + temperature = <125000>; + hysteresis = <0>; + type = "critical"; + }; + + }; + }; + + cpu0-thermal { + thermal-sensors = <&tsens0 1>; + + trips { + cpu0_alert0: trip-point0 { + temperature = <110000>; + hysteresis = <10000>; + type = "passive"; + }; + + cpu0_alert1: trip-point1 { + temperature = <115000>; + hysteresis = <5000>; + type = "passive"; + }; + + cpu0-critical { + temperature = <125000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&cpu0_alert0>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + + map1 { + trip = <&cpu0_alert1>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + }; + + cpu1-thermal { + thermal-sensors = <&tsens0 2>; + + trips { + cpu1_alert0: trip-point0 { + temperature = <110000>; + hysteresis = <10000>; + type = "passive"; + }; + + cpu1_alert1: trip-point1 { + temperature = <115000>; + hysteresis = <5000>; + type = "passive"; + }; + + cpu1-critical { + temperature = <125000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&cpu1_alert0>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + + map1 { + trip = <&cpu1_alert1>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + }; + + cpu2-thermal { + thermal-sensors = <&tsens0 3>; + + trips { + cpu2_alert0: trip-point0 { + temperature = <110000>; + hysteresis = <10000>; + type = "passive"; + }; + + cpu2_alert1: trip-point1 { + temperature = <115000>; + hysteresis = <5000>; + type = "passive"; + }; + + cpu2-critical { + temperature = <125000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&cpu2_alert0>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + + map1 { + trip = <&cpu2_alert1>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + }; + + cpu3-thermal { + thermal-sensors = <&tsens0 4>; + + trips { + cpu3_alert0: trip-point0 { + temperature = <110000>; + hysteresis = <10000>; + type = "passive"; + }; + + cpu3_alert1: rip-point1 { + temperature = <115000>; + hysteresis = <5000>; + type = "passive"; + }; + + cpu3-critical { + temperature = <125000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&cpu3_alert0>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + + map1 { + trip = <&cpu3_alert1>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + }; + + gpuss0-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens0 5>; + + cooling-maps { + map0 { + trip = <&gpu0_alert0>; + cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + gpu0_alert0: trip-point0 { + temperature = <85000>; + hysteresis = <1000>; + type = "passive"; + }; + + trip-point1 { + temperature = <90000>; + hysteresis = <1000>; + type = "hot"; + }; + + trip-point2 { + temperature = <115000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + }; + + gpuss1-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&tsens0 6>; + + cooling-maps { + map0 { + trip = <&gpu1_alert0>; + cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + gpu1_alert0: trip-point0 { + temperature = <85000>; + hysteresis = <1000>; + type = "passive"; + }; + + trip-point1 { + temperature = <90000>; + hysteresis = <1000>; + type = "hot"; + }; + + trip-point2 { + temperature = <115000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + }; + + nspss0-thermal { + thermal-sensors = <&tsens0 7>; + + trips { + trip-point0 { + temperature = <95000>; + hysteresis = <5000>; + type = "hot"; + }; + + trip-point1 { + temperature = <115000>; + hysteresis = <5000>; + type = "hot"; + }; + + nspss1-critical { + temperature = <125000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + }; + + nspss1-thermal { + thermal-sensors = <&tsens0 8>; + + trips { + trip-point0 { + temperature = <95000>; + hysteresis = <5000>; + type = "hot"; + }; + + trip-point1 { + temperature = <115000>; + hysteresis = <5000>; + type = "hot"; + }; + + nspss2-critical { + temperature = <125000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + }; + + nspss2-thermal { + thermal-sensors = <&tsens0 9>; + + trips { + trip-point0 { + temperature = <95000>; + hysteresis = <5000>; + type = "hot"; + }; + + trip-point1 { + temperature = <115000>; + hysteresis = <5000>; + type = "hot"; + }; + + nspss2-critical { + temperature = <125000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + }; + + video-thermal { + thermal-sensors = <&tsens0 10>; + + trips { + trip-point0 { + temperature = <115000>; + hysteresis = <5000>; + type = "hot"; + }; + + video-critical { + temperature = <125000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + + ddr-thermal { + thermal-sensors = <&tsens0 11>; + + trips { + trip-point0 { + temperature = <115000>; + hysteresis = <5000>; + type = "hot"; + }; + + ddr-critical { + temperature = <125000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + + camera0-thermal { + thermal-sensors = <&tsens0 12>; + + trips { + trip-point0 { + temperature = <115000>; + hysteresis = <5000>; + type = "hot"; + }; + + camera0-critical { + temperature = <125000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + + camera1-thermal { + thermal-sensors = <&tsens0 13>; + + trips { + trip-point0 { + temperature = <115000>; + hysteresis = <5000>; + type = "hot"; + }; + + camera1-critical { + temperature = <125000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + + mdmss-thermal { + thermal-sensors = <&tsens0 14>; + + trips { + trip-point0 { + temperature = <115000>; + hysteresis = <5000>; + type = "hot"; + }; + + mdmss-critical { + temperature = <125000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi index ac8d4589e3fb..f7300ffbb451 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi @@ -12,11 +12,11 @@ / { thermal-zones { - 5v-choke-thermal { + choke-5v-thermal { thermal-sensors = <&pm6150_adc_tm 1>; trips { - 5v-choke-crit { + choke-5v-crit { temperature = <125000>; hysteresis = <1000>; type = "critical"; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-quackingstick.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor-quackingstick.dtsi index 00229b1515e6..ff8996b4de4e 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-quackingstick.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-quackingstick.dtsi @@ -78,6 +78,7 @@ pinctrl-names = "default"; pinctrl-0 = <&lcd_rst>; avdd-supply = <&ppvar_lcd>; + avee-supply = <&ppvar_lcd>; pp1800-supply = <&v1p8_disp>; pp3300-supply = <&pp3300_dx_edp>; backlight = <&backlight>; diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index 76fe314d2ad5..87c432c12a24 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -580,55 +580,55 @@ compatible = "arm,psci-1.0"; method = "smc"; - cpu_pd0: cpu0 { + cpu_pd0: power-domain-cpu0 { #power-domain-cells = <0>; power-domains = <&cluster_pd>; domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; }; - cpu_pd1: cpu1 { + cpu_pd1: power-domain-cpu1 { #power-domain-cells = <0>; power-domains = <&cluster_pd>; domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; }; - cpu_pd2: cpu2 { + cpu_pd2: power-domain-cpu2 { #power-domain-cells = <0>; power-domains = <&cluster_pd>; domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; }; - cpu_pd3: cpu3 { + cpu_pd3: power-domain-cpu3 { #power-domain-cells = <0>; power-domains = <&cluster_pd>; domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; }; - cpu_pd4: cpu4 { + cpu_pd4: power-domain-cpu4 { #power-domain-cells = <0>; power-domains = <&cluster_pd>; domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; }; - cpu_pd5: cpu5 { + cpu_pd5: power-domain-cpu5 { #power-domain-cells = <0>; power-domains = <&cluster_pd>; domain-idle-states = <&little_cpu_sleep_0 &little_cpu_sleep_1>; }; - cpu_pd6: cpu6 { + cpu_pd6: power-domain-cpu6 { #power-domain-cells = <0>; power-domains = <&cluster_pd>; domain-idle-states = <&big_cpu_sleep_0 &big_cpu_sleep_1>; }; - cpu_pd7: cpu7 { + cpu_pd7: power-domain-cpu7 { #power-domain-cells = <0>; power-domains = <&cluster_pd>; domain-idle-states = <&big_cpu_sleep_0 &big_cpu_sleep_1>; }; - cluster_pd: cpu-cluster0 { + cluster_pd: power-domain-cluster { #power-domain-cells = <0>; domain-idle-states = <&cluster_sleep_pc &cluster_sleep_cx_ret @@ -3064,6 +3064,8 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,parkmode-disable-ss-quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; maximum-speed = "super-speed"; diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index 55db1c83ef55..0f2caf36910b 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -83,7 +83,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; - clock-frequency = <32000>; + clock-frequency = <32764>; #clock-cells = <0>; }; }; @@ -3715,6 +3715,8 @@ iommus = <&apps_smmu 0xa0 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_2_hsphy>; phy-names = "usb2-phy"; maximum-speed = "high-speed"; @@ -4244,6 +4246,8 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,parkmode-disable-ss-quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; maximum-speed = "super-speed"; diff --git a/arch/arm64/boot/dts/qcom/sc8180x-lenovo-flex-5g.dts b/arch/arm64/boot/dts/qcom/sc8180x-lenovo-flex-5g.dts index 62de4774c556..21c2d25a2945 100644 --- a/arch/arm64/boot/dts/qcom/sc8180x-lenovo-flex-5g.dts +++ b/arch/arm64/boot/dts/qcom/sc8180x-lenovo-flex-5g.dts @@ -681,10 +681,6 @@ status = "okay"; }; -&xo_board_clk { - clock-frequency = <38400000>; -}; - /* PINCTRL */ &pmc8180c_gpios { diff --git a/arch/arm64/boot/dts/qcom/sc8180x-primus.dts b/arch/arm64/boot/dts/qcom/sc8180x-primus.dts index 79b4d293ea1e..7a4bd6955470 100644 --- a/arch/arm64/boot/dts/qcom/sc8180x-primus.dts +++ b/arch/arm64/boot/dts/qcom/sc8180x-primus.dts @@ -773,10 +773,6 @@ status = "okay"; }; -&xo_board_clk { - clock-frequency = <38400000>; -}; - /* PINCTRL */ &pmc8180c_gpios { diff --git a/arch/arm64/boot/dts/qcom/sc8180x.dtsi b/arch/arm64/boot/dts/qcom/sc8180x.dtsi index 745a7d0b8381..28693a3bfc7f 100644 --- a/arch/arm64/boot/dts/qcom/sc8180x.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8180x.dtsi @@ -2762,6 +2762,8 @@ iommus = <&apps_smmu 0x60 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_mp_hsphy0>, <&usb_mp_qmpphy0>, <&usb_mp_hsphy1>, @@ -2825,6 +2827,8 @@ iommus = <&apps_smmu 0x140 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_prim_hsphy>, <&usb_prim_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; @@ -2902,6 +2906,8 @@ iommus = <&apps_smmu 0x160 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_sec_hsphy>, <&usb_sec_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts b/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts new file mode 100644 index 000000000000..09b95f89ee58 --- /dev/null +++ b/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts @@ -0,0 +1,1318 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2022, Linaro Limited + * + * Copyright (c) 2024, Tianyu Gao + * Copyright (c) 2024, Xuecong Chen + * + * Copyright (c) 2024, Pengyu Luo + */ + +/dts-v1/; + +#include +#include +#include +#include +#include +#include + +#include "sc8280xp.dtsi" +#include "sc8280xp-pmics.dtsi" + +/ { + chassis-type = "tablet"; + model = "Matebook E Go"; + compatible = "huawei,gaokun3", "qcom,sc8280xp"; + + aliases { + i2c4 = &i2c4; + serial1 = &uart2; + }; + + chosen { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + framebuffer0: framebuffer@c6200000 { + compatible = "simple-framebuffer"; + reg = <0x0 0xc6200000 0x0 0x02400000>; + width = <1600>; + height = <2560>; + stride = <(1600 * 4)>; + format = "a8r8g8b8"; + }; + }; + + wcd938x: audio-codec { + compatible = "qcom,wcd9380-codec"; + + pinctrl-0 = <&wcd_default>; + pinctrl-names = "default"; + + reset-gpios = <&tlmm 106 GPIO_ACTIVE_LOW>; + + vdd-buck-supply = <&vreg_s10b>; + vdd-rxtx-supply = <&vreg_s10b>; + vdd-io-supply = <&vreg_s10b>; + vdd-mic-bias-supply = <&vreg_bob>; + + qcom,micbias1-microvolt = <1800000>; + qcom,micbias2-microvolt = <1800000>; + qcom,micbias3-microvolt = <1800000>; + qcom,micbias4-microvolt = <1800000>; + qcom,mbhc-buttons-vthreshold-microvolt = <75000 150000 237000 500000 500000 500000 500000 500000>; + qcom,mbhc-headset-vthreshold-microvolt = <1700000>; + qcom,mbhc-headphone-vthreshold-microvolt = <50000>; + qcom,rx-device = <&wcd_rx>; + qcom,tx-device = <&wcd_tx>; + + #sound-dai-cells = <1>; + }; + + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-0 = <&mode_pin_active>, <&vol_up_n>; + pinctrl-names = "default"; + + key-vol-up { + label = "Volume Up"; + gpios = <&pmc8280_1_gpios 6 GPIO_ACTIVE_LOW>; + linux,code = ; + debounce-interval = <15>; + linux,can-disable; + wakeup-source; + }; + + switch-mode { + label = "Tablet Mode Switch"; + gpios = <&tlmm 26 GPIO_ACTIVE_HIGH>; + linux,input-type = ; + linux,code = ; + debounce-interval = <10>; + wakeup-source; + }; + }; + + vreg_misc_3p3: regulator-misc-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VCC3B"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&pmc8280_1_gpios 1 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&misc_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + regulator-always-on; + }; + + vreg_nvme: regulator-nvme { + compatible = "regulator-fixed"; + + regulator-name = "VCC3_SSD"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 135 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&nvme_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_vph_pwr: regulator-vph-pwr { + compatible = "regulator-fixed"; + + regulator-name = "VPH_VCC3R9"; + regulator-min-microvolt = <3900000>; + regulator-max-microvolt = <3900000>; + + regulator-always-on; + }; + + vreg_wlan: regulator-wlan { + compatible = "regulator-fixed"; + + regulator-name = "VCC_WLAN_3R9"; + regulator-min-microvolt = <3900000>; + regulator-max-microvolt = <3900000>; + + gpio = <&pmr735a_gpios 1 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&hastings_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + reserved-memory { + gpu_mem: gpu-mem@8bf00000 { + reg = <0 0x8bf00000 0 0x2000>; + no-map; + }; + + linux,cma { + compatible = "shared-dma-pool"; + size = <0x0 0x8000000>; + reusable; + linux,cma-default; + }; + }; + + thermal-zones { + skin-temp-thermal { + polling-delay-passive = <250>; + + thermal-sensors = <&pmk8280_adc_tm 5>; + + trips { + skin_temp_alert0: trip-point0 { + temperature = <55000>; + hysteresis = <1000>; + type = "passive"; + }; + + skin_temp_alert1: trip-point1 { + temperature = <58000>; + hysteresis = <1000>; + type = "passive"; + }; + + skin-temp-crit { + temperature = <73000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&skin_temp_alert0>; + cooling-device = <&cpu4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu5 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu6 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu7 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + + map1 { + trip = <&skin_temp_alert1>; + cooling-device = <&cpu4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu5 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu6 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu7 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + }; + }; + + wcn6855-pmu { + compatible = "qcom,wcn6855-pmu"; + + pinctrl-names = "default"; + pinctrl-0 = <&bt_default>, <&wlan_en>; + + wlan-enable-gpios = <&tlmm 134 GPIO_ACTIVE_HIGH>; + bt-enable-gpios = <&tlmm 133 GPIO_ACTIVE_HIGH>; + swctrl-gpios = <&tlmm 132 GPIO_ACTIVE_HIGH>; + + vddio-supply = <&vreg_s10b>; + vddaon-supply = <&vreg_s12b>; + vddpmu-supply = <&vreg_s12b>; + vddpmumx-supply = <&vreg_s12b>; + vddpmucx-supply = <&vreg_s12b>; + vddrfa0p95-supply = <&vreg_s12b>; + vddrfa1p3-supply = <&vreg_s11b>; + vddrfa1p9-supply = <&vreg_s1c>; + vddpcie1p3-supply = <&vreg_s11b>; + vddpcie1p9-supply = <&vreg_s1c>; + + regulators { + vreg_pmu_rfa_cmn_0p8: ldo0 { + regulator-name = "vreg_pmu_rfa_cmn_0p8"; + }; + + vreg_pmu_aon_0p8: ldo1 { + regulator-name = "vreg_pmu_aon_0p8"; + }; + + vreg_pmu_wlcx_0p8: ldo2 { + regulator-name = "vreg_pmu_wlcx_0p8"; + }; + + vreg_pmu_wlmx_0p8: ldo3 { + regulator-name = "vreg_pmu_wlmx_0p8"; + }; + + vreg_pmu_btcmx_0p8: ldo4 { + regulator-name = "vreg_pmu_btcmx_0p8"; + }; + + vreg_pmu_pcie_1p8: ldo5 { + regulator-name = "vreg_pmu_pcie_1p8"; + }; + + vreg_pmu_pcie_0p9: ldo6 { + regulator-name = "vreg_pmu_pcie_0p9"; + }; + + vreg_pmu_rfa_0p8: ldo7 { + regulator-name = "vreg_pmu_rfa_0p8"; + }; + + vreg_pmu_rfa_1p2: ldo8 { + regulator-name = "vreg_pmu_rfa_1p2"; + }; + + vreg_pmu_rfa_1p7: ldo9 { + regulator-name = "vreg_pmu_rfa_1p7"; + }; + }; + }; +}; + +&apps_rsc { + regulators-0 { + compatible = "qcom,pm8350-rpmh-regulators"; + qcom,pmic-id = "b"; + + vdd-l1-l4-supply = <&vreg_s12b>; + vdd-l2-l7-supply = <&vreg_bob>; + vdd-l3-l5-supply = <&vreg_s11b>; + vdd-l6-l9-l10-supply = <&vreg_s12b>; + vdd-l8-supply = <&vreg_s12b>; + + vreg_s10b: smps10 { + regulator-name = "vreg_s10b"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-always-on; + }; + + vreg_s11b: smps11 { + regulator-name = "vreg_s11b"; + regulator-min-microvolt = <1272000>; + regulator-max-microvolt = <1272000>; + regulator-initial-mode = ; + }; + + vreg_s12b: smps12 { + regulator-name = "vreg_s12b"; + regulator-min-microvolt = <984000>; + regulator-max-microvolt = <984000>; + regulator-initial-mode = ; + }; + + vreg_l1b: ldo1 { + regulator-name = "vreg_l1b"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2b: ldo2 { + regulator-name = "vreg_l2b"; + regulator-min-microvolt = <1904000>; + regulator-max-microvolt = <1904000>; + regulator-initial-mode = ; + }; + + vreg_l3b: ldo3 { + regulator-name = "vreg_l3b"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-boot-on; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l4b: ldo4 { + regulator-name = "vreg_l4b"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l5b: ldo5 { + regulator-name = "vreg_l5b"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l6b: ldo6 { + regulator-name = "vreg_l6b"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <880000>; + regulator-initial-mode = ; + regulator-boot-on; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l7b: ldo7 { + regulator-name = "vreg_l7b"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-boot-on; + }; + + vreg_l9b: ldo9 { + regulator-name = "vreg_l9b"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + }; + }; + + regulators-1 { + compatible = "qcom,pm8350c-rpmh-regulators"; + qcom,pmic-id = "c"; + + vdd-bob-supply = <&vreg_vph_pwr>; + vdd-l1-l12-supply = <&vreg_s1c>; + vdd-l2-l8-supply = <&vreg_s1c>; + vdd-l3-l4-l5-l7-l13-supply = <&vreg_bob>; + vdd-l6-l9-l11-supply = <&vreg_bob>; + vdd-l10-supply = <&vreg_s11b>; + + vreg_s1c: smps1 { + regulator-name = "vreg_s1c"; + regulator-min-microvolt = <1880000>; + regulator-max-microvolt = <1900000>; + regulator-initial-mode = ; + regulator-always-on; + }; + + vreg_l1c: ldo1 { + regulator-name = "vreg_l1c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2c: ldo2 { + regulator-name = "vreg_l2c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l8c: ldo8 { + regulator-name = "vreg_l8c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l12c: ldo12 { + regulator-name = "vreg_l12c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l13c: ldo13 { + regulator-name = "vreg_l13c"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_bob: bob { + regulator-name = "vreg_bob"; + regulator-min-microvolt = <3008000>; + regulator-max-microvolt = <3960000>; + regulator-initial-mode = ; + regulator-always-on; + }; + }; + + regulators-2 { + compatible = "qcom,pm8350-rpmh-regulators"; + qcom,pmic-id = "d"; + + vdd-l1-l4-supply = <&vreg_s11b>; + vdd-l2-l7-supply = <&vreg_bob>; + vdd-l3-l5-supply = <&vreg_s11b>; + vdd-l6-l9-l10-supply = <&vreg_s12b>; + vdd-l8-supply = <&vreg_s12b>; + + vreg_l2d: ldo2 { + regulator-name = "vreg_l2d"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3d: ldo3 { + regulator-name = "vreg_l3d"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l4d: ldo4 { + regulator-name = "vreg_l4d"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l6d: ldo6 { + regulator-name = "vreg_l6d"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <880000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l7d: ldo7 { + regulator-name = "vreg_l7d"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l8d: ldo8 { + regulator-name = "vreg_l8d"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l9d: ldo9 { + regulator-name = "vreg_l9d"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l10d: ldo10 { + regulator-name = "vreg_l10d"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; +}; + +&dispcc0 { + status = "okay"; +}; + +&gpu { + status = "okay"; + + zap-shader { + memory-region = <&gpu_mem>; + firmware-name = "qcom/sc8280xp/HUAWEI/gaokun3/qcdxkmsuc8280.mbn"; + }; +}; + +&i2c4 { + clock-frequency = <400000>; + + pinctrl-0 = <&i2c4_default>; + pinctrl-names = "default"; + + status = "okay"; + + touchscreen@4f { + compatible = "hid-over-i2c"; + reg = <0x4f>; + + hid-descr-addr = <0x1>; + interrupts-extended = <&tlmm 175 IRQ_TYPE_LEVEL_LOW>; + + vdd-supply = <&vreg_misc_3p3>; + vddl-supply = <&vreg_s10b>; + + pinctrl-0 = <&ts0_default>; + pinctrl-names = "default"; + }; + +}; + +&mdss0 { + status = "okay"; +}; + +&mdss0_dp0 { + status = "okay"; +}; + +&mdss0_dp0_out { + data-lanes = <0 1>; + remote-endpoint = <&usb_0_qmpphy_dp_in>; +}; + +&mdss0_dp1 { + status = "okay"; +}; + +&mdss0_dp1_out { + data-lanes = <0 1>; + remote-endpoint = <&usb_1_qmpphy_dp_in>; +}; + +&pcie2a { + perst-gpios = <&tlmm 143 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 145 GPIO_ACTIVE_LOW>; + + vddpe-3v3-supply = <&vreg_nvme>; + + pinctrl-0 = <&pcie2a_default>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&pcie2a_phy { + vdda-phy-supply = <&vreg_l6d>; + vdda-pll-supply = <&vreg_l4d>; + + status = "okay"; +}; + +&pcie4 { + max-link-speed = <2>; + + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; + + vddpe-3v3-supply = <&vreg_wlan>; + + pinctrl-0 = <&pcie4_default>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&pcie4_port0 { + wifi@0 { + compatible = "pci17cb,1103"; + reg = <0x10000 0x0 0x0 0x0 0x0>; + + vddrfacmn-supply = <&vreg_pmu_rfa_cmn_0p8>; + vddaon-supply = <&vreg_pmu_aon_0p8>; + vddwlcx-supply = <&vreg_pmu_wlcx_0p8>; + vddwlmx-supply = <&vreg_pmu_wlmx_0p8>; + vddpcie1p8-supply = <&vreg_pmu_pcie_1p8>; + vddpcie0p9-supply = <&vreg_pmu_pcie_0p9>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p8-supply = <&vreg_pmu_rfa_1p7>; + }; +}; + +&pcie4_phy { + vdda-phy-supply = <&vreg_l6d>; + vdda-pll-supply = <&vreg_l4d>; + + status = "okay"; +}; + +&pmk8280_adc_tm { + status = "okay"; + + sys-therm@0 { + reg = <0>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM1_100K_PU(1)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@1 { + reg = <1>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM2_100K_PU(1)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@2 { + reg = <2>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM3_100K_PU(1)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@3 { + reg = <3>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM4_100K_PU(1)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@4 { + reg = <4>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM1_100K_PU(3)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@5 { + reg = <5>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM2_100K_PU(3)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@6 { + reg = <6>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM3_100K_PU(3)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@7 { + reg = <7>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM4_100K_PU(3)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; +}; + +&pmk8280_pon_pwrkey { + status = "okay"; +}; + +&pmk8280_pon_resin { + status = "okay"; + linux,code = ; +}; + +&pmk8280_rtc { + nvmem-cells = <&rtc_offset>; + nvmem-cell-names = "offset"; + + status = "okay"; +}; + +&pmk8280_sdam_6 { + status = "okay"; + + rtc_offset: rtc-offset@bc { + reg = <0xbc 0x4>; + }; +}; + +&pmk8280_vadc { + channel@144 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm1"; + }; + + channel@145 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm2"; + }; + + channel@146 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm3"; + }; + + channel@147 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm4"; + }; + + channel@344 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm5"; + }; + + channel@345 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm6"; + }; + + channel@346 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm7"; + }; + + channel@347 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm8"; + }; +}; + +&qup0 { + status = "okay"; +}; + +&qup1 { + status = "okay"; +}; + +&qup2 { + status = "okay"; +}; + +&remoteproc_adsp { + firmware-name = "qcom/sc8280xp/HUAWEI/gaokun3/qcadsp8280.mbn"; + + status = "okay"; +}; + +&remoteproc_nsp0 { + firmware-name = "qcom/sc8280xp/HUAWEI/gaokun3/qccdsp8280.mbn"; + + status = "okay"; +}; + +&rxmacro { + status = "okay"; +}; + +&sound { + compatible = "qcom,sc8280xp-sndcard"; + model = "SC8280XP-HUAWEI-MATEBOOKEGO"; + audio-routing = "SpkrLeft IN", "WSA_SPK1 OUT", + "SpkrRight IN", "WSA_SPK2 OUT", + "IN1_HPHL", "HPHL_OUT", + "IN2_HPHR", "HPHR_OUT", + "AMIC2", "MIC BIAS2", + "VA DMIC0", "MIC BIAS1", + "VA DMIC1", "MIC BIAS1", + "VA DMIC2", "MIC BIAS3", + "VA DMIC0", "VA MIC BIAS1", + "VA DMIC1", "VA MIC BIAS1", + "VA DMIC2", "VA MIC BIAS3", + "TX SWR_ADC1", "ADC2_OUTPUT"; + + wcd-playback-dai-link { + link-name = "WCD Playback"; + + cpu { + sound-dai = <&q6apmbedai RX_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&wcd938x 0>, <&swr1 0>, <&rxmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wcd-capture-dai-link { + link-name = "WCD Capture"; + + cpu { + sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>; + }; + + codec { + sound-dai = <&wcd938x 1>, <&swr2 0>, <&txmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wsa-dai-link { + link-name = "WSA Playback"; + + cpu { + sound-dai = <&q6apmbedai WSA_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&left_spkr>, <&right_spkr>, <&swr0 0>, <&wsamacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + va-dai-link { + link-name = "VA Capture"; + + cpu { + sound-dai = <&q6apmbedai VA_CODEC_DMA_TX_0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + + codec { + sound-dai = <&vamacro 0>; + }; + }; +}; + +&swr0 { + status = "okay"; + + left_spkr: wsa8830-left@0,1 { + compatible = "sdw10217020200"; + reg = <0 1>; + pinctrl-0 = <&spkr_1_sd_n_default>; + pinctrl-names = "default"; + powerdown-gpios = <&tlmm 178 GPIO_ACTIVE_LOW>; + #thermal-sensor-cells = <0>; + sound-name-prefix = "SpkrLeft"; + #sound-dai-cells = <0>; + vdd-supply = <&vreg_s10b>; + }; + + right_spkr: wsa8830-right@0,2 { + compatible = "sdw10217020200"; + reg = <0 2>; + pinctrl-0 = <&spkr_2_sd_n_default>; + pinctrl-names = "default"; + powerdown-gpios = <&tlmm 179 GPIO_ACTIVE_LOW>; + #thermal-sensor-cells = <0>; + sound-name-prefix = "SpkrRight"; + #sound-dai-cells = <0>; + vdd-supply = <&vreg_s10b>; + }; +}; + +&swr1 { + status = "okay"; + + wcd_rx: wcd9380-rx@0,4 { + compatible = "sdw20217010d00"; + reg = <0 4>; + qcom,rx-port-mapping = <1 2 3 4 5>; + }; +}; + +&swr2 { + status = "okay"; + + wcd_tx: wcd9380-tx@0,3 { + compatible = "sdw20217010d00"; + reg = <0 3>; + qcom,tx-port-mapping = <1 1 2 3>; + }; +}; + +&txmacro { + status = "okay"; +}; + +&uart2 { + pinctrl-0 = <&uart2_default>; + pinctrl-names = "default"; + + status = "okay"; + + bluetooth { + compatible = "qcom,wcn6855-bt"; + + vddrfacmn-supply = <&vreg_pmu_rfa_cmn_0p8>; + vddaon-supply = <&vreg_pmu_aon_0p8>; + vddwlcx-supply = <&vreg_pmu_wlcx_0p8>; + vddwlmx-supply = <&vreg_pmu_wlmx_0p8>; + vddbtcmx-supply = <&vreg_pmu_btcmx_0p8>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p8-supply = <&vreg_pmu_rfa_1p7>; + + max-speed = <3200000>; + }; +}; + +&usb_0 { + status = "okay"; +}; + +&usb_0_dwc3 { + dr_mode = "host"; +}; + +&usb_0_hsphy { + vdda-pll-supply = <&vreg_l9d>; + vdda18-supply = <&vreg_l1c>; + vdda33-supply = <&vreg_l7d>; + + status = "okay"; +}; + +&usb_0_qmpphy { + vdda-phy-supply = <&vreg_l9d>; + vdda-pll-supply = <&vreg_l4d>; + + orientation-switch; + + status = "okay"; +}; + +&usb_0_qmpphy_dp_in { + remote-endpoint = <&mdss0_dp0_out>; +}; + +&usb_1 { + status = "okay"; +}; + +&usb_1_dwc3 { + dr_mode = "host"; +}; + +&usb_1_hsphy { + vdda-pll-supply = <&vreg_l4b>; + vdda18-supply = <&vreg_l1c>; + vdda33-supply = <&vreg_l13c>; + + status = "okay"; +}; + +&usb_1_qmpphy { + vdda-phy-supply = <&vreg_l4b>; + vdda-pll-supply = <&vreg_l3b>; + + orientation-switch; + + status = "okay"; +}; + +&usb_1_qmpphy_dp_in { + remote-endpoint = <&mdss0_dp1_out>; +}; + +&usb_2 { + status = "okay"; +}; + +&usb_2_hsphy0 { + vdda-pll-supply = <&vreg_l1b>; + vdda18-supply = <&vreg_l1c>; + vdda33-supply = <&vreg_l7d>; + + status = "okay"; +}; + +&usb_2_hsphy1 { + vdda-pll-supply = <&vreg_l8d>; + vdda18-supply = <&vreg_l1c>; + vdda33-supply = <&vreg_l7d>; + + status = "okay"; +}; + +&usb_2_hsphy2 { + vdda-pll-supply = <&vreg_l10d>; + vdda18-supply = <&vreg_l8c>; + vdda33-supply = <&vreg_l2d>; + + status = "okay"; +}; + +&usb_2_hsphy3 { + vdda-pll-supply = <&vreg_l10d>; + vdda18-supply = <&vreg_l8c>; + vdda33-supply = <&vreg_l2d>; + + status = "okay"; +}; + +&usb_2_qmpphy0 { + vdda-phy-supply = <&vreg_l1b>; + vdda-pll-supply = <&vreg_l4d>; + + status = "okay"; +}; + +&usb_2_qmpphy1 { + vdda-phy-supply = <&vreg_l8d>; + vdda-pll-supply = <&vreg_l4d>; + + status = "okay"; +}; + +&vamacro { + pinctrl-0 = <&dmic01_default>, <&dmic23_default>; + pinctrl-names = "default"; + + vdd-micb-supply = <&vreg_s10b>; + + qcom,dmic-sample-rate = <4800000>; + + status = "okay"; +}; + +&wsamacro { + status = "okay"; +}; + +&xo_board_clk { + clock-frequency = <38400000>; +}; + +/* PINCTRL */ + +&lpass_tlmm { + status = "okay"; +}; + +&pmc8280_1_gpios { + misc_3p3_reg_en: misc-3p3-reg-en-state { + pins = "gpio1"; + function = "normal"; + }; + + vol_up_n: vol-up-n-state { + pins = "gpio6"; + function = "normal"; + power-source = <1>; + input-enable; + bias-pull-up; + }; +}; + +&pmr735a_gpios { + hastings_reg_en: hastings-reg-en-state { + pins = "gpio1"; + function = "normal"; + }; +}; + +&tlmm { + + gpio-reserved-ranges = <70 2>, <74 6>, <83 4>, <125 2>, <128 2>, <154 4>; + + bt_default: bt-default-state { + hstp-bt-en-pins { + pins = "gpio133"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + }; + + hstp-sw-ctrl-pins { + pins = "gpio132"; + function = "gpio"; + bias-pull-down; + }; + }; + + i2c4_default: i2c4-default-state { + pins = "gpio171", "gpio172"; + function = "qup4"; + drive-strength = <16>; + bias-disable; + }; + + mode_pin_active: mode-pin-state { + pins = "gpio26"; + function = "gpio"; + bias-disable; + }; + + nvme_reg_en: nvme-reg-en-state { + pins = "gpio135"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + pcie2a_default: pcie2a-default-state { + clkreq-n-pins { + pins = "gpio142"; + function = "pcie2a_clkreq"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio143"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio145"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + pcie4_default: pcie4-default-state { + clkreq-n-pins { + pins = "gpio140"; + function = "pcie4_clkreq"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio141"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio139"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + spkr_1_sd_n_default: spkr-1-sd-n-default-state { + perst-n-pins { + pins = "gpio178"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + output-high; + }; + }; + + spkr_2_sd_n_default: spkr-2-sd-n-default-state { + perst-n-pins { + pins = "gpio179"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + output-high; + }; + }; + + ts0_default: ts0-default-state { + int-n-pins { + pins = "gpio175"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + reset-n-pins { + pins = "gpio99"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + output-high; + }; + }; + + uart2_default: uart2-default-state { + cts-pins { + pins = "gpio121"; + function = "qup2"; + bias-bus-hold; + }; + + rts-pins { + pins = "gpio122"; + function = "qup2"; + drive-strength = <2>; + bias-disable; + }; + + rx-pins { + pins = "gpio124"; + function = "qup2"; + bias-pull-up; + }; + + tx-pins { + pins = "gpio123"; + function = "qup2"; + drive-strength = <2>; + bias-disable; + }; + }; + + wcd_default: wcd-default-state { + reset-pins { + pins = "gpio106"; + function = "gpio"; + bias-disable; + }; + }; + + wlan_en: wlan-en-state { + pins = "gpio134"; + function = "gpio"; + drive-strength = <8>; + bias-pull-down; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-microsoft-blackrock.dts b/arch/arm64/boot/dts/qcom/sc8280xp-microsoft-blackrock.dts new file mode 100644 index 000000000000..fa9d94105052 --- /dev/null +++ b/arch/arm64/boot/dts/qcom/sc8280xp-microsoft-blackrock.dts @@ -0,0 +1,1325 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2022, Linaro Limited + * Copyright (c) 2023, Merck Hung + * Copyright (c) 2023, 2024 Jens Glathe + */ + +/dts-v1/; + +#include +#include +#include +#include +#include + +#include "sc8280xp.dtsi" +#include "sc8280xp-pmics.dtsi" + +/ { + model = "Windows Dev Kit 2023"; + compatible = "microsoft,blackrock", "qcom,sc8280xp"; + chassis-type = "desktop"; + + aliases { + i2c4 = &i2c4; + i2c21 = &i2c21; + serial1 = &uart2; + }; + + wcd938x: audio-codec { + compatible = "qcom,wcd9380-codec"; + + pinctrl-0 = <&wcd_default>; + pinctrl-names = "default"; + + reset-gpios = <&tlmm 106 GPIO_ACTIVE_LOW>; + + vdd-buck-supply = <&vreg_s10b>; + vdd-rxtx-supply = <&vreg_s10b>; + vdd-io-supply = <&vreg_s10b>; + vdd-mic-bias-supply = <&vreg_bob>; + + qcom,micbias1-microvolt = <1800000>; + qcom,micbias2-microvolt = <1800000>; + qcom,micbias3-microvolt = <1800000>; + qcom,micbias4-microvolt = <1800000>; + qcom,mbhc-buttons-vthreshold-microvolt = <75000 150000 237000 500000 500000 500000 500000 500000>; + qcom,mbhc-headset-vthreshold-microvolt = <1700000>; + qcom,mbhc-headphone-vthreshold-microvolt = <50000>; + qcom,rx-device = <&wcd_rx>; + qcom,tx-device = <&wcd_tx>; + + #sound-dai-cells = <1>; + }; + + dp3_connector: connector { + compatible = "dp-connector"; + label = "DP-3"; + type = "mini"; + + dp-pwr-supply = <&vreg_misc_3p3>; + + port { + dp1_connector_in: endpoint { + remote-endpoint = <&mdss0_dp2_phy_out>; + }; + }; + }; + + pmic-glink { + compatible = "qcom,sc8280xp-pmic-glink", "qcom,pmic-glink"; + + #address-cells = <1>; + #size-cells = <0>; + orientation-gpios = <&tlmm 166 GPIO_ACTIVE_HIGH>, + <&tlmm 49 GPIO_ACTIVE_HIGH>; + + /* Left-side rear port */ + connector@0 { + compatible = "usb-c-connector"; + reg = <0>; + power-role = "source"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + pmic_glink_con0_hs: endpoint { + remote-endpoint = <&usb_0_dwc3_hs>; + }; + }; + + port@1 { + reg = <1>; + + pmic_glink_con0_ss: endpoint { + remote-endpoint = <&usb_0_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_con0_sbu: endpoint { + remote-endpoint = <&usb0_sbu_mux>; + }; + }; + }; + }; + + /* Left-side front port */ + connector@1 { + compatible = "usb-c-connector"; + reg = <1>; + power-role = "source"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + pmic_glink_con1_hs: endpoint { + remote-endpoint = <&usb_1_dwc3_hs>; + }; + }; + + port@1 { + reg = <1>; + + pmic_glink_con1_ss: endpoint { + remote-endpoint = <&usb_1_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_con1_sbu: endpoint { + remote-endpoint = <&usb1_sbu_mux>; + }; + }; + }; + }; + }; + + vreg_misc_3p3: regulator-misc-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VCC3B"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&pmc8280_1_gpios 1 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&misc_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + regulator-always-on; + }; + + vreg_nvme: regulator-nvme { + compatible = "regulator-fixed"; + + regulator-name = "VCC3_SSD"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 135 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&nvme_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_vph_pwr: regulator-vph-pwr { + compatible = "regulator-fixed"; + + regulator-name = "VPH_VCC3R9"; + regulator-min-microvolt = <3900000>; + regulator-max-microvolt = <3900000>; + + regulator-always-on; + }; + + vreg_wlan: regulator-wlan { + compatible = "regulator-fixed"; + + regulator-name = "VCC_WLAN_3R9"; + regulator-min-microvolt = <3900000>; + regulator-max-microvolt = <3900000>; + + gpio = <&pmr735a_gpios 1 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&hastings_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_wwan: regulator-wwan { + compatible = "regulator-fixed"; + + regulator-name = "VCC3B_WAN"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&pmc8280_2_gpios 1 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&wwan_sw_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + reserved-memory { + gpu_mem: gpu-mem@8bf00000 { + reg = <0 0x8bf00000 0 0x2000>; + no-map; + }; + + linux,cma { + compatible = "shared-dma-pool"; + size = <0x0 0x8000000>; + reusable; + linux,cma-default; + }; + }; + + usb0-sbu-mux { + compatible = "pericom,pi3usb102", "gpio-sbu-mux"; + + enable-gpios = <&tlmm 101 GPIO_ACTIVE_LOW>; + select-gpios = <&tlmm 164 GPIO_ACTIVE_HIGH>; + + pinctrl-0 = <&usb0_sbu_default>; + pinctrl-names = "default"; + + mode-switch; + orientation-switch; + + port { + usb0_sbu_mux: endpoint { + remote-endpoint = <&pmic_glink_con0_sbu>; + }; + }; + }; + + usb1-sbu-mux { + compatible = "pericom,pi3usb102", "gpio-sbu-mux"; + + enable-gpios = <&tlmm 48 GPIO_ACTIVE_LOW>; + select-gpios = <&tlmm 47 GPIO_ACTIVE_HIGH>; + + pinctrl-0 = <&usb1_sbu_default>; + pinctrl-names = "default"; + + mode-switch; + orientation-switch; + + port { + usb1_sbu_mux: endpoint { + remote-endpoint = <&pmic_glink_con1_sbu>; + }; + }; + }; + + wcn6855-pmu { + compatible = "qcom,wcn6855-pmu"; + + pinctrl-0 = <&bt_default>, <&wlan_en>; + pinctrl-names = "default"; + + wlan-enable-gpios = <&tlmm 134 GPIO_ACTIVE_HIGH>; + bt-enable-gpios = <&tlmm 133 GPIO_ACTIVE_HIGH>; + swctrl-gpios = <&tlmm 132 GPIO_ACTIVE_HIGH>; + + vddio-supply = <&vreg_s10b>; + vddaon-supply = <&vreg_s12b>; + vddpmu-supply = <&vreg_s12b>; + vddpmumx-supply = <&vreg_s12b>; + vddpmucx-supply = <&vreg_s12b>; + vddrfa0p95-supply = <&vreg_s12b>; + vddrfa1p3-supply = <&vreg_s11b>; + vddrfa1p9-supply = <&vreg_s1c>; + vddpcie1p3-supply = <&vreg_s11b>; + vddpcie1p9-supply = <&vreg_s1c>; + + regulators { + vreg_pmu_rfa_cmn_0p8: ldo0 { + regulator-name = "vreg_pmu_rfa_cmn_0p8"; + }; + + vreg_pmu_aon_0p8: ldo1 { + regulator-name = "vreg_pmu_aon_0p8"; + }; + + vreg_pmu_wlcx_0p8: ldo2 { + regulator-name = "vreg_pmu_wlcx_0p8"; + }; + + vreg_pmu_wlmx_0p8: ldo3 { + regulator-name = "vreg_pmu_wlmx_0p8"; + }; + + vreg_pmu_btcmx_0p8: ldo4 { + regulator-name = "vreg_pmu_btcmx_0p8"; + }; + + vreg_pmu_pcie_1p8: ldo5 { + regulator-name = "vreg_pmu_pcie_1p8"; + }; + + vreg_pmu_pcie_0p9: ldo6 { + regulator-name = "vreg_pmu_pcie_0p9"; + }; + + vreg_pmu_rfa_0p8: ldo7 { + regulator-name = "vreg_pmu_rfa_0p8"; + }; + + vreg_pmu_rfa_1p2: ldo8 { + regulator-name = "vreg_pmu_rfa_1p2"; + }; + + vreg_pmu_rfa_1p7: ldo9 { + regulator-name = "vreg_pmu_rfa_1p7"; + }; + }; + }; +}; + +&apps_rsc { + regulators-0 { + compatible = "qcom,pm8350-rpmh-regulators"; + qcom,pmic-id = "b"; + + vdd-s10-supply = <&vreg_vph_pwr>; + vdd-s11-supply = <&vreg_vph_pwr>; + vdd-s12-supply = <&vreg_vph_pwr>; + vdd-l1-l4-supply = <&vreg_s12b>; + vdd-l2-l7-supply = <&vreg_bob>; + vdd-l3-l5-supply = <&vreg_s11b>; + vdd-l6-l9-l10-supply = <&vreg_s12b>; + vdd-l8-supply = <&vreg_s12b>; + + vreg_s10b: smps10 { + regulator-name = "vreg_s10b"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-always-on; + }; + + vreg_s11b: smps11 { + regulator-name = "vreg_s11b"; + regulator-min-microvolt = <1272000>; + regulator-max-microvolt = <1272000>; + regulator-initial-mode = ; + }; + + vreg_s12b: smps12 { + regulator-name = "vreg_s12b"; + regulator-min-microvolt = <984000>; + regulator-max-microvolt = <984000>; + regulator-initial-mode = ; + }; + + vreg_l1b: ldo1 { + regulator-name = "vreg_l1b"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + }; + + vreg_l3b: ldo3 { + regulator-name = "vreg_l3b"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-boot-on; + }; + + vreg_l4b: ldo4 { + regulator-name = "vreg_l4b"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + }; + + vreg_l6b: ldo6 { + regulator-name = "vreg_l6b"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <880000>; + regulator-initial-mode = ; + regulator-boot-on; + }; + }; + + regulators-1 { + compatible = "qcom,pm8350c-rpmh-regulators"; + qcom,pmic-id = "c"; + + vdd-bob-supply = <&vreg_vph_pwr>; + vdd-l1-l12-supply = <&vreg_s1c>; + vdd-l2-l8-supply = <&vreg_s1c>; + vdd-l3-l4-l5-l7-l13-supply = <&vreg_bob>; + vdd-l6-l9-l11-supply = <&vreg_bob>; + vdd-l10-supply = <&vreg_s11b>; + + vreg_s1c: smps1 { + regulator-name = "vreg_s1c"; + regulator-min-microvolt = <1880000>; + regulator-max-microvolt = <1900000>; + regulator-initial-mode = ; + regulator-always-on; + }; + + vreg_l1c: ldo1 { + regulator-name = "vreg_l1c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l6c: ldo6 { + regulator-name = "vreg_l6c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2960000>; + regulator-initial-mode = ; + }; + + vreg_l7c: ldo7 { + regulator-name = "vreg_l7c"; + regulator-min-microvolt = <2504000>; + regulator-max-microvolt = <2504000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l8c: ldo8 { + regulator-name = "vreg_l8c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l9c: ldo9 { + regulator-name = "vreg_l9c"; + regulator-min-microvolt = <2960000>; + regulator-max-microvolt = <2960000>; + regulator-initial-mode = ; + }; + + vreg_l12c: ldo12 { + regulator-name = "vreg_l12c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l13c: ldo13 { + regulator-name = "vreg_l13c"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + }; + + vreg_bob: bob { + regulator-name = "vreg_bob"; + regulator-min-microvolt = <3008000>; + regulator-max-microvolt = <3960000>; + regulator-initial-mode = ; + regulator-always-on; + }; + }; + + regulators-2 { + compatible = "qcom,pm8350-rpmh-regulators"; + qcom,pmic-id = "d"; + + vdd-l1-l4-supply = <&vreg_s11b>; + vdd-l2-l7-supply = <&vreg_bob>; + vdd-l3-l5-supply = <&vreg_s11b>; + vdd-l6-l9-l10-supply = <&vreg_s12b>; + vdd-l8-supply = <&vreg_s12b>; + + vreg_l2d: ldo2 { + regulator-name = "vreg_l2d"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + }; + + vreg_l3d: ldo3 { + regulator-name = "vreg_l3d"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l4d: ldo4 { + regulator-name = "vreg_l4d"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l6d: ldo6 { + regulator-name = "vreg_l6d"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <880000>; + regulator-initial-mode = ; + }; + + vreg_l7d: ldo7 { + regulator-name = "vreg_l7d"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + }; + + vreg_l8d: ldo8 { + regulator-name = "vreg_l8d"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + }; + + vreg_l9d: ldo9 { + regulator-name = "vreg_l9d"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + }; + + vreg_l10d: ldo10 { + regulator-name = "vreg_l10d"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + }; + }; +}; + +&dispcc0 { + status = "okay"; +}; + +&gpu { + status = "okay"; + + zap-shader { + memory-region = <&gpu_mem>; + firmware-name = "qcom/sc8280xp/microsoft/blackrock/qcdxkmsuc8280.mbn"; + }; +}; + +&mdss0 { + status = "okay"; +}; + +&mdss0_dp0 { + status = "okay"; +}; + +&mdss0_dp0_out { + data-lanes = <0 1>; + remote-endpoint = <&usb_0_qmpphy_dp_in>; +}; + +&mdss0_dp1 { + status = "okay"; +}; + +&mdss0_dp1_out { + data-lanes = <0 1>; + remote-endpoint = <&usb_1_qmpphy_dp_in>; +}; + +&mdss0_dp2 { + compatible = "qcom,sc8280xp-dp"; + + data-lanes = <0 1 2 3>; + + status = "okay"; + + ports { + port@1 { + reg = <1>; + mdss0_dp2_phy_out: endpoint { + remote-endpoint = <&dp1_connector_in>; + }; + }; + }; +}; + +&mdss0_dp2_phy { + compatible = "qcom,sc8280xp-dp-phy"; + + vdda-phy-supply = <&vreg_l3b>; + vdda-pll-supply = <&vreg_l6b>; + + status = "okay"; +}; + +&pcie2a { + perst-gpios = <&tlmm 143 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 145 GPIO_ACTIVE_LOW>; + + vddpe-3v3-supply = <&vreg_nvme>; + + pinctrl-0 = <&pcie2a_default>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&pcie2a_phy { + vdda-phy-supply = <&vreg_l4d>; + vdda-pll-supply = <&vreg_l6d>; + + status = "okay"; +}; + +&pcie4 { + max-link-speed = <2>; + + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; + + vddpe-3v3-supply = <&vreg_wlan>; + + pinctrl-0 = <&pcie4_default>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&pcie4_port0 { + wifi@0 { + compatible = "pci17cb,1103"; + reg = <0x10000 0x0 0x0 0x0 0x0>; + + vddrfacmn-supply = <&vreg_pmu_rfa_cmn_0p8>; + vddaon-supply = <&vreg_pmu_aon_0p8>; + vddwlcx-supply = <&vreg_pmu_wlcx_0p8>; + vddwlmx-supply = <&vreg_pmu_wlmx_0p8>; + vddpcie1p8-supply = <&vreg_pmu_pcie_1p8>; + vddpcie0p9-supply = <&vreg_pmu_pcie_0p9>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p8-supply = <&vreg_pmu_rfa_1p7>; + + qcom,ath11k-calibration-variant = "MS_Volterra"; + }; +}; + +&pcie4_phy { + vdda-phy-supply = <&vreg_l4d>; + vdda-pll-supply = <&vreg_l6d>; + + status = "okay"; +}; + +&pmc8280c_lpg { + status = "okay"; +}; + +&pmk8280_adc_tm { + status = "okay"; + + sys-therm@0 { + reg = <0>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM1_100K_PU(1)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@1 { + reg = <1>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM2_100K_PU(1)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@2 { + reg = <2>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM3_100K_PU(1)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@3 { + reg = <3>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM4_100K_PU(1)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@4 { + reg = <4>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM1_100K_PU(3)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@5 { + reg = <5>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM2_100K_PU(3)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@6 { + reg = <6>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM3_100K_PU(3)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; + + sys-therm@7 { + reg = <7>; + io-channels = <&pmk8280_vadc PM8350_ADC7_AMUX_THM4_100K_PU(3)>; + qcom,hw-settle-time-us = <200>; + qcom,avg-samples = <2>; + qcom,ratiometric; + }; +}; + +&pmk8280_pon_pwrkey { + status = "okay"; +}; + +&pmk8280_pon_resin { + status = "okay"; +}; + +&pmk8280_rtc { + nvmem-cells = <&rtc_offset>; + nvmem-cell-names = "offset"; + + status = "okay"; +}; + +&pmk8280_sdam_6 { + status = "okay"; + + rtc_offset: rtc-offset@bc { + reg = <0xbc 0x4>; + }; +}; + +&pmk8280_vadc { + channel@144 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm1"; + }; + + channel@145 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm2"; + }; + + channel@146 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm3"; + }; + + channel@147 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm4"; + }; + + channel@344 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm5"; + }; + + channel@345 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm6"; + }; + + channel@346 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm7"; + }; + + channel@347 { + reg = ; + qcom,hw-settle-time = <200>; + qcom,ratiometric; + label = "sys_therm8"; + }; +}; + +&qup0 { + status = "okay"; +}; + +&qup1 { + status = "okay"; +}; + +&qup2 { + status = "okay"; +}; + +&remoteproc_adsp { + firmware-name = "qcom/sc8280xp/microsoft/blackrock/qcadsp8280.mbn"; + + status = "okay"; +}; + +&remoteproc_nsp0 { + firmware-name = "qcom/sc8280xp/microsoft/blackrock/qccdsp8280.mbn"; + + status = "okay"; +}; + +&rxmacro { + status = "okay"; +}; + +&sound { + compatible = "qcom,sc8280xp-sndcard"; + model = "microsoft/blackrock"; + + wcd-playback-dai-link { + link-name = "WCD Playback"; + + cpu { + sound-dai = <&q6apmbedai RX_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&wcd938x 0>, <&swr1 0>, <&rxmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wcd-capture-dai-link { + link-name = "WCD Capture"; + + cpu { + sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>; + }; + + codec { + sound-dai = <&wcd938x 1>, <&swr2 0>, <&txmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wsa-dai-link { + link-name = "WSA Playback"; + + cpu { + sound-dai = <&q6apmbedai WSA_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&swr0 0>, <&wsamacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + va-dai-link { + link-name = "VA Capture"; + + cpu { + sound-dai = <&q6apmbedai VA_CODEC_DMA_TX_0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + + codec { + sound-dai = <&vamacro 0>; + }; + }; +}; + +&swr0 { + status = "okay"; +}; + +&swr1 { + status = "okay"; + + wcd_rx: wcd9380-rx@0,4 { + compatible = "sdw20217010d00"; + reg = <0 4>; + qcom,rx-port-mapping = <1 2 3 4 5>; + }; +}; + +&swr2 { + status = "okay"; + + wcd_tx: wcd9380-tx@0,3 { + compatible = "sdw20217010d00"; + reg = <0 3>; + qcom,tx-port-mapping = <1 1 2 3>; + }; +}; + +&txmacro { + status = "okay"; +}; + +&uart2 { + pinctrl-0 = <&uart2_default>; + pinctrl-names = "default"; + + status = "okay"; + + bluetooth { + compatible = "qcom,wcn6855-bt"; + + vddrfacmn-supply = <&vreg_pmu_rfa_cmn_0p8>; + vddaon-supply = <&vreg_pmu_aon_0p8>; + vddwlcx-supply = <&vreg_pmu_wlcx_0p8>; + vddwlmx-supply = <&vreg_pmu_wlmx_0p8>; + vddbtcmx-supply = <&vreg_pmu_btcmx_0p8>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p8-supply = <&vreg_pmu_rfa_1p7>; + + max-speed = <3200000>; + }; +}; + +&usb_0 { + status = "okay"; +}; + +&usb_0_dwc3 { + dr_mode = "host"; +}; + +&usb_0_dwc3_hs { + remote-endpoint = <&pmic_glink_con0_hs>; +}; + +&usb_0_hsphy { + vdda-pll-supply = <&vreg_l9d>; + vdda18-supply = <&vreg_l1c>; + vdda33-supply = <&vreg_l7d>; + + status = "okay"; +}; + +&usb_0_qmpphy { + vdda-phy-supply = <&vreg_l4d>; + vdda-pll-supply = <&vreg_l9d>; + + orientation-switch; + + status = "okay"; +}; + +&usb_0_qmpphy_dp_in { + remote-endpoint = <&mdss0_dp0_out>; +}; + +&usb_0_qmpphy_out { + remote-endpoint = <&pmic_glink_con0_ss>; +}; + +&usb_1 { + status = "okay"; +}; + +&usb_1_dwc3 { + dr_mode = "host"; +}; + +&usb_1_dwc3_hs { + remote-endpoint = <&pmic_glink_con1_hs>; +}; + +&usb_1_hsphy { + vdda-pll-supply = <&vreg_l4b>; + vdda18-supply = <&vreg_l1c>; + vdda33-supply = <&vreg_l13c>; + + status = "okay"; +}; + +&usb_1_qmpphy { + vdda-phy-supply = <&vreg_l3b>; + vdda-pll-supply = <&vreg_l4b>; + + orientation-switch; + + status = "okay"; +}; + +&usb_1_qmpphy_dp_in { + remote-endpoint = <&mdss0_dp1_out>; +}; + +&usb_1_qmpphy_out { + remote-endpoint = <&pmic_glink_con1_ss>; +}; + +&usb_2 { + pinctrl-0 = <&usb2_en_state>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&usb_2_dwc3 { + phys = <&usb_2_hsphy0>, <&usb_2_qmpphy0>; + phy-names = "usb2-0", "usb3-0"; +}; + +&usb_2_hsphy0 { + vdda-pll-supply = <&vreg_l1b>; + vdda18-supply = <&vreg_l1c>; + vdda33-supply = <&vreg_l7d>; + + status = "okay"; +}; + +&usb_2_qmpphy0 { + vdda-phy-supply = <&vreg_l1b>; + vdda-pll-supply = <&vreg_l4d>; + + status = "okay"; +}; + +&vamacro { + pinctrl-0 = <&dmic01_default>, <&dmic23_default>; + pinctrl-names = "default"; + + vdd-micb-supply = <&vreg_s10b>; + + qcom,dmic-sample-rate = <4800000>; + + status = "okay"; +}; + +&wsamacro { + status = "okay"; +}; + +&xo_board_clk { + clock-frequency = <38400000>; +}; + +/* PINCTRL */ + +&lpass_tlmm { + status = "okay"; +}; + +&pmc8280_1_gpios { + misc_3p3_reg_en: misc-3p3-reg-en-state { + pins = "gpio1"; + function = "normal"; + }; + + edp_bl_en: edp-bl-en-state { + pins = "gpio8"; + function = "normal"; + }; + + edp_bl_reg_en: edp-bl-reg-en-state { + pins = "gpio9"; + function = "normal"; + }; +}; + +&pmc8280_2_gpios { + wwan_sw_en: wwan-sw-en-state { + pins = "gpio1"; + function = "normal"; + }; +}; + +&pmc8280c_gpios { + edp_bl_pwm: edp-bl-pwm-state { + pins = "gpio8"; + function = "func1"; + }; +}; + +&pmr735a_gpios { + hastings_reg_en: hastings-reg-en-state { + pins = "gpio1"; + function = "normal"; + }; +}; + +&tlmm { + bt_default: bt-default-state { + hstp-bt-en-pins { + pins = "gpio133"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + }; + + hstp-sw-ctrl-pins { + pins = "gpio132"; + function = "gpio"; + bias-pull-down; + }; + }; + + nvme_reg_en: nvme-reg-en-state { + pins = "gpio135"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + pcie2a_default: pcie2a-default-state { + clkreq-n-pins { + pins = "gpio142"; + function = "pcie2a_clkreq"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio143"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio145"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + pcie3a_default: pcie3a-default-state { + clkreq-n-pins { + pins = "gpio150"; + function = "pcie3a_clkreq"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio151"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio148"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + pcie4_default: pcie4-default-state { + clkreq-n-pins { + pins = "gpio140"; + function = "pcie4_clkreq"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio141"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio139"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + uart2_default: uart2-default-state { + cts-pins { + pins = "gpio121"; + function = "qup2"; + bias-bus-hold; + }; + + rts-pins { + pins = "gpio122"; + function = "qup2"; + drive-strength = <2>; + bias-disable; + }; + + rx-pins { + pins = "gpio124"; + function = "qup2"; + bias-pull-up; + }; + + tx-pins { + pins = "gpio123"; + function = "qup2"; + drive-strength = <2>; + bias-disable; + }; + }; + + usb0_sbu_default: usb0-sbu-state { + oe-n-pins { + pins = "gpio101"; + function = "gpio"; + bias-disable; + drive-strength = <16>; + output-high; + }; + + sel-pins { + pins = "gpio164"; + function = "gpio"; + bias-disable; + drive-strength = <16>; + }; + }; + + usb1_sbu_default: usb1-sbu-state { + oe-n-pins { + pins = "gpio48"; + function = "gpio"; + bias-disable; + drive-strength = <16>; + output-high; + }; + + sel-pins { + pins = "gpio47"; + function = "gpio"; + bias-disable; + drive-strength = <16>; + }; + }; + + usb2_en_state: usb2-en-state { + /* TS3USB221A USB2.0 mux select */ + pins = "gpio24"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + output-low; + }; + + wcd_default: wcd-default-state { + reset-pins { + pins = "gpio106"; + function = "gpio"; + bias-disable; + }; + }; + + wlan_en: wlan-en-state { + pins = "gpio134"; + function = "gpio"; + drive-strength = <8>; + bias-pull-down; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index ef06d1ac084d..01501acb1790 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -2743,7 +2743,7 @@ remoteproc_adsp: remoteproc@3000000 { compatible = "qcom,sc8280xp-adsp-pas"; - reg = <0 0x03000000 0 0x100>; + reg = <0 0x03000000 0 0x10000>; interrupts-extended = <&intc GIC_SPI 162 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, @@ -3536,6 +3536,8 @@ "usb2-2", "usb2-3"; dr_mode = "host"; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; }; }; @@ -3593,6 +3595,8 @@ iommus = <&apps_smmu 0x820 0x0>; phys = <&usb_0_hsphy>, <&usb_0_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; ports { #address-cells = <1>; @@ -3670,6 +3674,8 @@ iommus = <&apps_smmu 0x860 0x0>; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; ports { #address-cells = <1>; @@ -3900,26 +3906,26 @@ "vfe3", "csid3"; - interrupts = , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - ; + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; interrupt-names = "csid1_lite", "vfe_lite1", "csiphy3", @@ -5254,7 +5260,7 @@ remoteproc_nsp0: remoteproc@1b300000 { compatible = "qcom,sc8280xp-nsp0-pas"; - reg = <0 0x1b300000 0 0x100>; + reg = <0 0x1b300000 0 0x10000>; interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp0_in 0 IRQ_TYPE_EDGE_RISING>, @@ -5385,7 +5391,7 @@ remoteproc_nsp1: remoteproc@21300000 { compatible = "qcom,sc8280xp-nsp1-pas"; - reg = <0 0x21300000 0 0x100>; + reg = <0 0x21300000 0 0x10000>; interrupts-extended = <&intc GIC_SPI 887 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp1_in 0 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sdm450-lenovo-tbx605f.dts b/arch/arm64/boot/dts/qcom/sdm450-lenovo-tbx605f.dts index c509bbfe5d3e..735a21df8cc9 100644 --- a/arch/arm64/boot/dts/qcom/sdm450-lenovo-tbx605f.dts +++ b/arch/arm64/boot/dts/qcom/sdm450-lenovo-tbx605f.dts @@ -46,6 +46,18 @@ }; }; + backlight: gpio-backlight { + compatible = "gpio-backlight"; + + gpios = <&tlmm 16 GPIO_ACTIVE_HIGH>; + + default-on; + + pinctrl-names = "default"; + pinctrl-0 = <&backlight_enable_active>; + pinctrl-1 = <&backlight_enable_sleep>; + }; + gpio-keys { compatible = "gpio-keys"; key-volume-up { @@ -63,6 +75,49 @@ }; }; +&mdss { + status = "okay"; +}; + +&mdss_dsi0 { + vdda-supply = <&pm8953_s3>; + vddio-supply = <&pm8953_l6>; + + status = "okay"; + + panel@0 { + compatible = "boe,tv101wum-ll2"; + reg = <0>; + + vsp-supply = <&lab>; + vsn-supply = <&ibb>; + reset-gpios = <&tlmm 61 GPIO_ACTIVE_LOW>; + + backlight = <&backlight>; + + pinctrl-names = "default"; + pinctrl-0 = <&panel_reset_active>; + pinctrl-1 = <&panel_reset_sleep>; + + port { + panel_in: endpoint { + remote-endpoint = <&mdss_dsi0_out>; + }; + }; + }; +}; + +&mdss_dsi0_out { + remote-endpoint = <&panel_in>; + data-lanes = <0 1 2 3>; +}; + +&mdss_dsi0_phy { + vcca-supply = <&pm8953_l3>; + + status = "okay"; +}; + &hsusb_phy { vdd-supply = <&pm8953_l3>; vdda-pll-supply = <&pm8953_l7>; @@ -90,6 +145,18 @@ }; }; +&ibb { + regulator-min-microvolt = <4600000>; + regulator-max-microvolt = <6000000>; + qcom,discharge-resistor-kohms = <32>; +}; + +&lab { + regulator-min-microvolt = <4600000>; + regulator-max-microvolt = <6000000>; + qcom,soft-start-us = <800>; +}; + &pm8953_resin { linux,code = ; status = "okay"; @@ -237,6 +304,36 @@ &tlmm { gpio-reserved-ranges = <0 4>, <135 4>; + backlight_enable_active: backlight-enable-active-state { + pins = "gpio16"; + function = "gpio"; + drive-strength = <8>; + bias-disable; + output-high; + }; + + backlight_enable_sleep: backlight-enable-sleep-state { + pins = "gpio16"; + function = "gpio"; + drive-strength = <2>; + bias-pull-down; + }; + + panel_reset_active: panel-reset-active-state { + pins = "gpio61"; + function = "gpio"; + drive-strength = <8>; + bias-disable; + output-high; + }; + + panel_reset_sleep: panel-reset-sleep-state { + pins = "gpio61"; + function = "gpio"; + drive-strength = <2>; + bias-pull-down; + }; + ts_int_active: ts-int-active-state { pins = "gpio65"; function = "gpio"; diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi index 19420cfdadf1..a2c079bac1a7 100644 --- a/arch/arm64/boot/dts/qcom/sdm630.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi @@ -1300,6 +1300,8 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,parkmode-disable-ss-quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&qusb2phy0>, <&usb3_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; @@ -1505,6 +1507,8 @@ interrupts = ; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; /* This is the HS-only host */ maximum-speed = "high-speed"; diff --git a/arch/arm64/boot/dts/qcom/sdm670-google-sargo.dts b/arch/arm64/boot/dts/qcom/sdm670-google-sargo.dts index 176b0119fe6d..74b5d9c68eb6 100644 --- a/arch/arm64/boot/dts/qcom/sdm670-google-sargo.dts +++ b/arch/arm64/boot/dts/qcom/sdm670-google-sargo.dts @@ -10,6 +10,7 @@ #include #include +#include #include #include #include "sdm670.dtsi" @@ -49,20 +50,6 @@ }; }; - clocks { - sleep_clk: sleep-clk { - compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <32764>; - }; - - xo_board: xo-board { - compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <38400000>; - }; - }; - gpio-keys { compatible = "gpio-keys"; autorepeat; @@ -407,6 +394,15 @@ status = "okay"; }; +&gpu { + status = "okay"; + + zap-shader { + memory-region = <&gpu_mem>; + firmware-name = "qcom/sdm670/sargo/a615_zap.mbn"; + }; +}; + &i2c9 { clock-frequency = <100000>; status = "okay"; @@ -482,6 +478,19 @@ status = "okay"; }; +&pm660l_flash { + status = "okay"; + + led-0 { + function = LED_FUNCTION_FLASH; + color = ; + led-sources = <1>, <2>; + led-max-microamp = <500000>; + flash-max-microamp = <1500000>; + flash-max-timeout-us = <1280000>; + }; +}; + &pm660l_gpios { vol_up_pin: vol-up-state { pins = "gpio7"; diff --git a/arch/arm64/boot/dts/qcom/sdm670.dtsi b/arch/arm64/boot/dts/qcom/sdm670.dtsi index c93dd06c0b7d..279e62ec5433 100644 --- a/arch/arm64/boot/dts/qcom/sdm670.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm670.dtsi @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -28,6 +29,20 @@ chosen { }; + clocks { + sleep_clk: sleep-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <32764>; + }; + + xo_board: xo-board { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <38400000>; + }; + }; + cpus { #address-cells = <2>; #size-cells = <0>; @@ -617,6 +632,11 @@ #address-cells = <1>; #size-cells = <1>; + gpu_speed_bin: gpu_speed_bin@1a2 { + reg = <0x1a2 0x2>; + bits = <5 8>; + }; + qusb2_hstx_trim: hstx-trim@1eb { reg = <0x1eb 0x1>; bits = <1 4>; @@ -1299,6 +1319,180 @@ }; }; + gpu: gpu@5000000 { + compatible = "qcom,adreno-615.0", "qcom,adreno"; + + reg = <0 0x05000000 0 0x40000>, <0 0x0509e000 0 0x10>; + reg-names = "kgsl_3d0_reg_memory", "cx_mem"; + + /* + * Look ma, no clocks! The GPU clocks and power are + * controlled entirely by the GMU + */ + + interrupts = ; + + iommus = <&adreno_smmu 0>; + + operating-points-v2 = <&gpu_opp_table>; + + qcom,gmu = <&gmu>; + + interconnects = <&mem_noc MASTER_GRAPHICS_3D 0 &mem_noc SLAVE_EBI_CH0 0>; + interconnect-names = "gfx-mem"; + + nvmem-cells = <&gpu_speed_bin>; + nvmem-cell-names = "speed_bin"; + + status = "disabled"; + + gpu_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-780000000 { + opp-hz = /bits/ 64 <780000000>; + opp-level = ; + opp-peak-kBps = <7216000>; + opp-supported-hw = <0x8>; + }; + + opp-750000000 { + opp-hz = /bits/ 64 <750000000>; + opp-level = ; + opp-peak-kBps = <7216000>; + opp-supported-hw = <0x8>; + }; + + opp-700000000 { + opp-hz = /bits/ 64 <700000000>; + opp-level = ; + opp-peak-kBps = <7216000>; + opp-supported-hw = <0x4>; + }; + + opp-650000000 { + opp-hz = /bits/ 64 <650000000>; + opp-level = ; + opp-peak-kBps = <7216000>; + opp-supported-hw = <0xc>; + }; + + opp-565000000 { + opp-hz = /bits/ 64 <565000000>; + opp-level = ; + opp-peak-kBps = <7216000>; + opp-supported-hw = <0xc>; + }; + + opp-504000000 { + opp-hz = /bits/ 64 <504000000>; + opp-level = ; + opp-peak-kBps = <7216000>; + opp-supported-hw = <0x2>; + }; + + opp-430000000 { + opp-hz = /bits/ 64 <430000000>; + opp-level = ; + opp-peak-kBps = <7216000>; + opp-supported-hw = <0xf>; + }; + + opp-355000000 { + opp-hz = /bits/ 64 <355000000>; + opp-level = ; + opp-peak-kBps = <6220000>; + opp-supported-hw = <0xf>; + }; + + opp-267000000 { + opp-hz = /bits/ 64 <267000000>; + opp-level = ; + opp-peak-kBps = <4068000>; + opp-supported-hw = <0xf>; + }; + + opp-180000000 { + opp-hz = /bits/ 64 <180000000>; + opp-level = ; + opp-peak-kBps = <1804000>; + opp-supported-hw = <0xf>; + }; + }; + }; + + adreno_smmu: iommu@5040000 { + compatible = "qcom,sdm670-smmu-v2", "qcom,adreno-smmu", "qcom,smmu-v2"; + reg = <0 0x05040000 0 0x10000>; + #iommu-cells = <1>; + #global-interrupts = <2>; + interrupts = , + , + , + , + , + , + , + , + , + ; + clocks = <&gcc GCC_GPU_MEMNOC_GFX_CLK>, + <&gcc GCC_GPU_CFG_AHB_CLK>; + clock-names = "bus", "iface"; + + power-domains = <&gpucc GPU_CX_GDSC>; + }; + + gmu: gmu@506a000 { + compatible = "qcom,adreno-gmu-615.0", "qcom,adreno-gmu"; + + reg = <0 0x0506a000 0 0x30000>, + <0 0x0b280000 0 0x10000>, + <0 0x0b480000 0 0x10000>; + reg-names = "gmu", "gmu_pdc", "gmu_pdc_seq"; + + interrupts = , + ; + interrupt-names = "hfi", "gmu"; + + clocks = <&gpucc GPU_CC_CX_GMU_CLK>, + <&gpucc GPU_CC_CXO_CLK>, + <&gcc GCC_DDRSS_GPU_AXI_CLK>, + <&gcc GCC_GPU_MEMNOC_GFX_CLK>; + clock-names = "gmu", "cxo", "axi", "memnoc"; + + power-domains = <&gpucc GPU_CX_GDSC>, + <&gpucc GPU_GX_GDSC>; + power-domain-names = "cx", "gx"; + + iommus = <&adreno_smmu 5>; + + operating-points-v2 = <&gmu_opp_table>; + + gmu_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-200000000 { + opp-hz = /bits/ 64 <200000000>; + opp-level = ; + }; + }; + }; + + gpucc: clock-controller@5090000 { + compatible = "qcom,sdm845-gpucc"; + reg = <0 0x05090000 0 0x9000>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_GPU_GPLL0_CLK_SRC>, + <&gcc GCC_GPU_GPLL0_DIV_CLK_SRC>; + clock-names = "bi_tcxo", + "gcc_gpu_gpll0_clk_src", + "gcc_gpu_gpll0_div_clk_src"; + }; + usb_1_hsphy: phy@88e2000 { compatible = "qcom,sdm670-qusb2-phy", "qcom,qusb2-v2-phy"; reg = <0 0x088e2000 0 0x400>; @@ -1400,6 +1594,16 @@ #interrupt-cells = <4>; }; + camcc: clock-controller@ad00000 { + compatible = "qcom,sdm670-camcc", "qcom,sdm845-camcc"; + reg = <0 0x0ad00000 0 0x10000>; + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "bi_tcxo"; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + mdss: display-subsystem@ae00000 { compatible = "qcom,sdm670-mdss"; reg = <0 0x0ae00000 0 0x1000>; diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c-navigation-mezzanine.dtso b/arch/arm64/boot/dts/qcom/sdm845-db845c-navigation-mezzanine.dtso index 0a87df806caf..59970082da45 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c-navigation-mezzanine.dtso +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c-navigation-mezzanine.dtso @@ -79,45 +79,3 @@ }; }; }; - -&cci_i2c1 { - #address-cells = <1>; - #size-cells = <0>; - - camera@60 { - compatible = "ovti,ov7251"; - - /* I2C address as per ov7251.txt linux documentation */ - reg = <0x60>; - - /* CAM3_RST_N */ - enable-gpios = <&tlmm 21 GPIO_ACTIVE_HIGH>; - pinctrl-names = "default"; - pinctrl-0 = <&cam3_default>; - - clocks = <&clock_camcc CAM_CC_MCLK3_CLK>; - clock-names = "xclk"; - clock-frequency = <24000000>; - - /* - * The &vreg_s4a_1p8 trace always powered on. - * - * The 2.8V vdda-supply regulator is enabled when the - * vreg_s4a_1p8 trace is pulled high. - * It too is represented by a fixed regulator. - * - * No 1.2V vddd-supply regulator is used. - */ - vdddo-supply = <&vreg_lvs1a_1p8>; - vdda-supply = <&cam3_avdd_2v8>; - - status = "disabled"; - - port { - ov7251_ep: endpoint { - data-lanes = <0 1>; -/* remote-endpoint = <&csiphy3_ep>; */ - }; - }; - }; -}; diff --git a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts index 486ce175e6bc..ddb82ecb0a92 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts @@ -452,7 +452,6 @@ irq-gpio = <&tlmm 125 GPIO_TRANSITORY>; touchscreen-size-x = <1080>; touchscreen-size-y = <2160>; - focaltech,max-touch-number = <5>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 1ed794638a7c..e0ce804bb1a3 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -4139,6 +4139,8 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,parkmode-disable-ss-quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; @@ -4215,6 +4217,8 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,parkmode-disable-ss-quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_2_hsphy>, <&usb_2_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; }; @@ -4326,16 +4330,16 @@ "vfe1", "vfe_lite"; - interrupts = , - , - , - , - , - , - , - , - , - ; + interrupts = , + , + , + , + , + , + , + , + , + ; interrupt-names = "csid0", "csid1", "csid2", diff --git a/arch/arm64/boot/dts/qcom/sdx75.dtsi b/arch/arm64/boot/dts/qcom/sdx75.dtsi index 5f7e59ecf1ca..b0a8a0fe5f39 100644 --- a/arch/arm64/boot/dts/qcom/sdx75.dtsi +++ b/arch/arm64/boot/dts/qcom/sdx75.dtsi @@ -34,7 +34,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; - clock-frequency = <32000>; + clock-frequency = <32764>; #clock-cells = <0>; }; }; @@ -893,7 +893,7 @@ remoteproc_mpss: remoteproc@4080000 { compatible = "qcom,sdx75-mpss-pas"; - reg = <0 0x04080000 0 0x4040>; + reg = <0 0x04080000 0 0x10000>; interrupts-extended = <&intc GIC_SPI 250 IRQ_TYPE_EDGE_RISING>, <&smp2p_modem_in 0 IRQ_TYPE_EDGE_RISING>, @@ -1037,6 +1037,8 @@ iommus = <&apps_smmu 0x80 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_hsphy>, <&usb_qmpphy>; phy-names = "usb2-phy", diff --git a/arch/arm64/boot/dts/qcom/sm4250.dtsi b/arch/arm64/boot/dts/qcom/sm4250.dtsi index a0ed61925e12..cd8c8e59976e 100644 --- a/arch/arm64/boot/dts/qcom/sm4250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm4250.dtsi @@ -36,3 +36,42 @@ &cpu7 { compatible = "qcom,kryo240"; }; + +&lpass_tlmm { + compatible = "qcom,sm4250-lpass-lpi-pinctrl"; + gpio-ranges = <&lpass_tlmm 0 0 27>; + + lpi_i2s2_active: lpi-i2s2-active-state { + sck-pins { + pins = "gpio10"; + function = "i2s2_clk"; + bias-disable; + drive-strength = <8>; + output-high; + }; + + ws-pins { + pins = "gpio11"; + function = "i2s2_ws"; + bias-disable; + drive-strength = <8>; + output-high; + }; + + data-pins { + pins = "gpio12"; + function = "i2s2_data"; + bias-disable; + drive-strength = <8>; + output-high; + }; + + ext-mclk1-pins { + pins = "gpio18"; + function = "ext_mclk1_a"; + bias-disable; + drive-strength = <16>; + output-high; + }; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/sm4450.dtsi b/arch/arm64/boot/dts/qcom/sm4450.dtsi index a0de5fe16faa..27453771aa68 100644 --- a/arch/arm64/boot/dts/qcom/sm4450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm4450.dtsi @@ -29,7 +29,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; - clock-frequency = <32000>; + clock-frequency = <32764>; #clock-cells = <0>; }; diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi index 9b23534c456b..94c081bf7a89 100644 --- a/arch/arm64/boot/dts/qcom/sm6115.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi @@ -14,6 +14,9 @@ #include #include #include +#include +#include +#include #include / { @@ -808,6 +811,20 @@ }; }; + lpass_tlmm: pinctrl@a7c0000 { + compatible = "qcom,sm6115-lpass-lpi-pinctrl"; + reg = <0x0 0x0a7c0000 0x0 0x20000>, + <0x0 0x0a950000 0x0 0x10000>; + + clocks = <&q6afecc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>; + clock-names = "audio"; + + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&lpass_tlmm 0 0 19>; + + }; + gcc: clock-controller@1400000 { compatible = "qcom,gcc-sm6115"; reg = <0x0 0x01400000 0x0 0x1f0000>; @@ -2027,7 +2044,7 @@ remoteproc_mpss: remoteproc@6080000 { compatible = "qcom,sm6115-mpss-pas"; - reg = <0x0 0x06080000 0x0 0x100>; + reg = <0x0 0x06080000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 307 IRQ_TYPE_EDGE_RISING>, <&modem_smp2p_in 0 IRQ_TYPE_EDGE_RISING>, @@ -2670,9 +2687,9 @@ }; }; - remoteproc_adsp: remoteproc@ab00000 { + remoteproc_adsp: remoteproc@a400000 { compatible = "qcom,sm6115-adsp-pas"; - reg = <0x0 0x0ab00000 0x0 0x100>; + reg = <0x0 0x0a400000 0x0 0x4040>; interrupts-extended = <&intc GIC_SPI 282 IRQ_TYPE_EDGE_RISING>, <&adsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>, @@ -2701,6 +2718,76 @@ qcom,remote-pid = <2>; mboxes = <&apcs_glb 8>; + apr { + compatible = "qcom,apr-v2"; + qcom,glink-channels = "apr_audio_svc"; + qcom,domain = ; + #address-cells = <1>; + #size-cells = <0>; + + service@3 { + reg = ; + compatible = "qcom,q6core"; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + }; + + q6afe: service@4 { + compatible = "qcom,q6afe"; + reg = ; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + q6afedai: dais { + compatible = "qcom,q6afe-dais"; + #address-cells = <1>; + #size-cells = <0>; + #sound-dai-cells = <1>; + }; + + q6afecc: clock-controller { + compatible = "qcom,q6afe-clocks"; + #clock-cells = <2>; + }; + }; + + q6asm: service@7 { + compatible = "qcom,q6asm"; + reg = ; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + q6asmdai: dais { + compatible = "qcom,q6asm-dais"; + #address-cells = <1>; + #size-cells = <0>; + #sound-dai-cells = <1>; + iommus = <&apps_smmu 0x1c1 0x0>; + + dai@0 { + reg = ; + }; + + dai@1 { + reg = ; + }; + + dai@2 { + reg = ; + }; + }; + }; + + q6adm: service@8 { + compatible = "qcom,q6adm"; + reg = ; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + q6routing: routing { + compatible = "qcom,q6adm-routing"; + #sound-dai-cells = <0>; + }; + }; + }; + fastrpc { compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; @@ -2744,7 +2831,7 @@ remoteproc_cdsp: remoteproc@b300000 { compatible = "qcom,sm6115-cdsp-pas"; - reg = <0x0 0x0b300000 0x0 0x100000>; + reg = <0x0 0x0b300000 0x0 0x4040>; interrupts-extended = <&intc GIC_SPI 265 IRQ_TYPE_EDGE_RISING>, <&cdsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm6125.dtsi b/arch/arm64/boot/dts/qcom/sm6125.dtsi index 17d528d63934..350d807a622f 100644 --- a/arch/arm64/boot/dts/qcom/sm6125.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6125.dtsi @@ -28,7 +28,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <32000>; + clock-frequency = <32764>; clock-output-names = "sleep_clk"; }; }; @@ -1209,6 +1209,8 @@ phy-names = "usb2-phy"; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; maximum-speed = "high-speed"; dr_mode = "peripheral"; }; diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi index 8d697280249f..00ad1d09a195 100644 --- a/arch/arm64/boot/dts/qcom/sm6350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi @@ -936,7 +936,7 @@ power-domains = <&rpmhpd SM6350_CX>; operating-points-v2 = <&qup_opp_table>; interconnects = <&clk_virt MASTER_QUP_CORE_0 0 &clk_virt SLAVE_QUP_CORE_0 0>, - <&aggre1_noc MASTER_QUP_0 0 &clk_virt SLAVE_EBI_CH0 0>; + <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_QUP_0 0>; interconnect-names = "qup-core", "qup-config"; status = "disabled"; }; @@ -1283,7 +1283,7 @@ adsp: remoteproc@3000000 { compatible = "qcom,sm6350-adsp-pas"; - reg = <0 0x03000000 0 0x100>; + reg = <0x0 0x03000000 0x0 0x10000>; interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, @@ -1503,7 +1503,7 @@ mpss: remoteproc@4080000 { compatible = "qcom,sm6350-mpss-pas"; - reg = <0x0 0x04080000 0x0 0x4040>; + reg = <0x0 0x04080000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_EDGE_RISING>, <&modem_smp2p_in 0 IRQ_TYPE_EDGE_RISING>, @@ -1924,6 +1924,8 @@ snps,has-lpm-erratum; snps,hird-threshold = /bits/ 8 <0x10>; snps,parkmode-disable-ss-quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; usb-role-switch; diff --git a/arch/arm64/boot/dts/qcom/sm6375.dtsi b/arch/arm64/boot/dts/qcom/sm6375.dtsi index e0b1c54e98c0..0faa3a40ff82 100644 --- a/arch/arm64/boot/dts/qcom/sm6375.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6375.dtsi @@ -29,7 +29,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; - clock-frequency = <32000>; + clock-frequency = <32764>; #clock-cells = <0>; }; }; @@ -1516,9 +1516,9 @@ #power-domain-cells = <1>; }; - remoteproc_mss: remoteproc@6000000 { + remoteproc_mss: remoteproc@6080000 { compatible = "qcom,sm6375-mpss-pas"; - reg = <0 0x06000000 0 0x4040>; + reg = <0x0 0x06080000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 307 IRQ_TYPE_EDGE_RISING>, <&smp2p_modem_in 0 IRQ_TYPE_EDGE_RISING>, @@ -1559,7 +1559,7 @@ remoteproc_adsp: remoteproc@a400000 { compatible = "qcom,sm6375-adsp-pas"; - reg = <0 0x0a400000 0 0x100>; + reg = <0 0x0a400000 0 0x10000>; interrupts-extended = <&intc GIC_SPI 282 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, @@ -1595,9 +1595,9 @@ }; }; - remoteproc_cdsp: remoteproc@b000000 { + remoteproc_cdsp: remoteproc@b300000 { compatible = "qcom,sm6375-cdsp-pas"; - reg = <0x0 0x0b000000 0x0 0x100000>; + reg = <0x0 0x0b300000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 265 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts b/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts index 2ee2561b57b1..52b16a4fdc43 100644 --- a/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts +++ b/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts @@ -32,7 +32,7 @@ chassis-type = "handset"; /* required for bootloader to select correct board */ - qcom,msm-id = <434 0x10000>, <459 0x10000>; + qcom,msm-id = <459 0x10000>; qcom,board-id = <8 32>; aliases { diff --git a/arch/arm64/boot/dts/qcom/sm8150-hdk.dts b/arch/arm64/boot/dts/qcom/sm8150-hdk.dts index bac08f00b303..6ea883b1edfa 100644 --- a/arch/arm64/boot/dts/qcom/sm8150-hdk.dts +++ b/arch/arm64/boot/dts/qcom/sm8150-hdk.dts @@ -578,6 +578,11 @@ }; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &pon_pwrkey { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8150-microsoft-surface-duo.dts b/arch/arm64/boot/dts/qcom/sm8150-microsoft-surface-duo.dts index b039773c4465..9a3d0ac6c423 100644 --- a/arch/arm64/boot/dts/qcom/sm8150-microsoft-surface-duo.dts +++ b/arch/arm64/boot/dts/qcom/sm8150-microsoft-surface-duo.dts @@ -376,8 +376,8 @@ pinctrl-0 = <&da7280_intr_default>; dlg,actuator-type = "LRA"; - dlg,dlg,const-op-mode = <1>; - dlg,dlg,periodic-op-mode = <1>; + dlg,const-op-mode = <1>; + dlg,periodic-op-mode = <1>; dlg,nom-microvolt = <2000000>; dlg,abs-max-microvolt = <2000000>; dlg,imax-microamp = <129000>; @@ -430,6 +430,11 @@ /* MAX34417 @ 0x1e */ }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &pon_pwrkey { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8150-mtp.dts b/arch/arm64/boot/dts/qcom/sm8150-mtp.dts index 256a1ba94945..2e1c7afe0aa7 100644 --- a/arch/arm64/boot/dts/qcom/sm8150-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8150-mtp.dts @@ -358,6 +358,11 @@ status = "okay"; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &pon_pwrkey { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8150-sony-xperia-kumano.dtsi b/arch/arm64/boot/dts/qcom/sm8150-sony-xperia-kumano.dtsi index ae0ca48b89a5..70fd6455518b 100644 --- a/arch/arm64/boot/dts/qcom/sm8150-sony-xperia-kumano.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150-sony-xperia-kumano.dtsi @@ -601,6 +601,11 @@ }; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &pon_pwrkey { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index cedae8d03a51..4dbda54b47a5 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -3658,6 +3658,8 @@ iommus = <&apps_smmu 0x140 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; @@ -3735,6 +3737,8 @@ iommus = <&apps_smmu 0x160 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_2_hsphy>, <&usb_2_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250-hdk.dts b/arch/arm64/boot/dts/qcom/sm8250-hdk.dts index 1bbb71e1a4fc..f5c193c6c5f9 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-hdk.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-hdk.dts @@ -373,6 +373,11 @@ status = "okay"; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &pon_pwrkey { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts index 21b2ca1def83..7f592bd30248 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts @@ -627,6 +627,11 @@ }; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &qupv3_id_0 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi index f6870d3f2886..d8289b2698f3 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi @@ -591,6 +591,11 @@ }; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &pon_pwrkey { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi index 3596dd328c31..813b009b7bd6 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi @@ -30,6 +30,10 @@ qcom,msm-id = ; /* SM8250 v2.1 */ qcom,board-id = <0x10008 0>; + aliases { + serial0 = &uart6; + }; + chosen { #address-cells = <2>; #size-cells = <2>; @@ -97,6 +101,67 @@ }; }; + qca6390-pmu { + compatible = "qcom,qca6390-pmu"; + + pinctrl-names = "default"; + pinctrl-0 = <&bt_en_state>, <&wlan_en_state>; + + vddaon-supply = <&vreg_s6a_0p95>; + vddpmu-supply = <&vreg_s6a_0p95>; + vddrfa0p95-supply = <&vreg_s6a_0p95>; + vddrfa1p3-supply = <&vreg_s8c_1p35>; + vddrfa1p9-supply = <&vreg_s5a_1p9>; + vddpcie1p3-supply = <&vreg_s8c_1p35>; + vddpcie1p9-supply = <&vreg_s5a_1p9>; + vddio-supply = <&vreg_s4a_1p8>; + + wlan-enable-gpios = <&tlmm 20 GPIO_ACTIVE_HIGH>; + bt-enable-gpios = <&tlmm 21 GPIO_ACTIVE_HIGH>; + + regulators { + vreg_pmu_rfa_cmn: ldo0 { + regulator-name = "vreg_pmu_rfa_cmn"; + }; + + vreg_pmu_aon_0p59: ldo1 { + regulator-name = "vreg_pmu_aon_0p59"; + }; + + vreg_pmu_wlcx_0p8: ldo2 { + regulator-name = "vreg_pmu_wlcx_0p8"; + }; + + vreg_pmu_wlmx_0p85: ldo3 { + regulator-name = "vreg_pmu_wlmx_0p85"; + }; + + vreg_pmu_btcmx_0p85: ldo4 { + regulator-name = "vreg_pmu_btcmx_0p85"; + }; + + vreg_pmu_rfa_0p8: ldo5 { + regulator-name = "vreg_pmu_rfa_0p8"; + }; + + vreg_pmu_rfa_1p2: ldo6 { + regulator-name = "vreg_pmu_rfa_1p2"; + }; + + vreg_pmu_rfa_1p7: ldo7 { + regulator-name = "vreg_pmu_rfa_1p7"; + }; + + vreg_pmu_pcie_0p9: ldo8 { + regulator-name = "vreg_pmu_pcie_0p9"; + }; + + vreg_pmu_pcie_1p8: ldo9 { + regulator-name = "vreg_pmu_pcie_1p8"; + }; + }; + }; + vph_pwr: vph-pwr-regulator { compatible = "regulator-fixed"; regulator-name = "vph_pwr"; @@ -619,6 +684,25 @@ status = "okay"; }; +&pcieport0 { + wifi@0 { + compatible = "pci17cb,1101"; + reg = <0x10000 0x0 0x0 0x0 0x0>; + + vddrfacmn-supply = <&vreg_pmu_rfa_cmn>; + vddaon-supply = <&vreg_pmu_aon_0p59>; + vddwlcx-supply = <&vreg_pmu_wlcx_0p8>; + vddwlmx-supply = <&vreg_pmu_wlmx_0p85>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p7-supply = <&vreg_pmu_rfa_1p7>; + vddpcie0p9-supply = <&vreg_pmu_pcie_0p9>; + vddpcie1p8-supply = <&vreg_pmu_pcie_1p8>; + + qcom,ath11k-calibration-variant = "Xiaomi_Pad_5Pro"; + }; +}; + &pm8150_gpios { vol_up_n: vol-up-n-state { pins = "gpio6"; @@ -673,6 +757,11 @@ status = "okay"; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &pon_pwrkey { status = "okay"; }; @@ -701,6 +790,37 @@ &tlmm { gpio-reserved-ranges = <40 4>; + + bt_en_state: bt-default-state { + pins = "gpio21"; + function = "gpio"; + drive-strength = <16>; + output-low; + bias-pull-up; + }; + + wlan_en_state: wlan-default-state { + pins = "gpio20"; + function = "gpio"; + drive-strength = <16>; + output-low; + bias-pull-up; + }; +}; + +&uart6 { + status = "okay"; + + bluetooth { + compatible = "qcom,qca6390-bt"; + + vddrfacmn-supply = <&vreg_pmu_rfa_cmn>; + vddaon-supply = <&vreg_pmu_aon_0p59>; + vddbtcmx-supply = <&vreg_pmu_btcmx_0p85>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p7-supply = <&vreg_pmu_rfa_1p7>; + }; }; &usb_1 { diff --git a/arch/arm64/boot/dts/qcom/sm8250-xiaomi-pipa.dts b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-pipa.dts index 86e1f7fd1c20..668078ea4f04 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-xiaomi-pipa.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-pipa.dts @@ -554,6 +554,11 @@ }; }; +&pon { + mode-bootloader = <0x2>; + mode-recovery = <0x1>; +}; + &pon_pwrkey { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index 48318ed1ce98..c2937b4d9f18 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -84,7 +84,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; - clock-frequency = <32768>; + clock-frequency = <32764>; #clock-cells = <0>; }; }; @@ -4207,6 +4207,8 @@ iommus = <&apps_smmu 0x0 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; @@ -4294,6 +4296,8 @@ iommus = <&apps_smmu 0x20 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_2_hsphy>, <&usb_2_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; }; @@ -4481,20 +4485,20 @@ "vfe_lite0", "vfe_lite1"; - interrupts = , - , - , - , - , - , - , - , - , - , - , - , - , - ; + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + ; interrupt-names = "csiphy0", "csiphy1", "csiphy2", diff --git a/arch/arm64/boot/dts/qcom/sm8350-hdk.dts b/arch/arm64/boot/dts/qcom/sm8350-hdk.dts index 796cbb58ef6e..f9de0e49fa24 100644 --- a/arch/arm64/boot/dts/qcom/sm8350-hdk.dts +++ b/arch/arm64/boot/dts/qcom/sm8350-hdk.dts @@ -925,3 +925,10 @@ }; }; }; + +&ipa { + qcom,gsi-loader = "self"; + memory-region = <&pil_ipa_fw_mem>; + status = "okay"; + firmware-name = "qcom/sm8350/ipa_fws.mbn"; +}; diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index 877905dfd861..69da30f35baa 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -42,7 +42,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; - clock-frequency = <32000>; + clock-frequency = <32764>; #clock-cells = <0>; }; }; @@ -1876,6 +1876,142 @@ reg = <0x0 0x1fc0000 0x0 0x30000>; }; + adsp: remoteproc@3000000 { + compatible = "qcom,sm8350-adsp-pas"; + reg = <0x0 0x03000000 0x0 0x10000>; + + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", "fatal", "ready", + "handover", "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + power-domains = <&rpmhpd RPMHPD_LCX>, + <&rpmhpd RPMHPD_LMX>; + power-domain-names = "lcx", "lmx"; + + memory-region = <&pil_adsp_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_adsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + label = "lpass"; + qcom,remote-pid = <2>; + + apr { + compatible = "qcom,apr-v2"; + qcom,glink-channels = "apr_audio_svc"; + qcom,domain = ; + #address-cells = <1>; + #size-cells = <0>; + + service@3 { + reg = ; + compatible = "qcom,q6core"; + qcom,protection-domain = "avs/audio", "msm/adsp/audio_pd"; + }; + + q6afe: service@4 { + compatible = "qcom,q6afe"; + reg = ; + qcom,protection-domain = "avs/audio", "msm/adsp/audio_pd"; + + q6afedai: dais { + compatible = "qcom,q6afe-dais"; + #address-cells = <1>; + #size-cells = <0>; + #sound-dai-cells = <1>; + }; + + q6afecc: clock-controller { + compatible = "qcom,q6afe-clocks"; + #clock-cells = <2>; + }; + }; + + q6asm: service@7 { + compatible = "qcom,q6asm"; + reg = ; + qcom,protection-domain = "avs/audio", "msm/adsp/audio_pd"; + + q6asmdai: dais { + compatible = "qcom,q6asm-dais"; + #address-cells = <1>; + #size-cells = <0>; + #sound-dai-cells = <1>; + iommus = <&apps_smmu 0x1801 0x0>; + + dai@0 { + reg = <0>; + }; + + dai@1 { + reg = <1>; + }; + + dai@2 { + reg = <2>; + }; + }; + }; + + q6adm: service@8 { + compatible = "qcom,q6adm"; + reg = ; + qcom,protection-domain = "avs/audio", "msm/adsp/audio_pd"; + + q6routing: routing { + compatible = "qcom,q6adm-routing"; + #sound-dai-cells = <0>; + }; + }; + }; + + fastrpc { + compatible = "qcom,fastrpc"; + qcom,glink-channels = "fastrpcglink-apps-dsp"; + label = "adsp"; + qcom,non-secure-domain; + #address-cells = <1>; + #size-cells = <0>; + + compute-cb@3 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <3>; + iommus = <&apps_smmu 0x1803 0x0>; + }; + + compute-cb@4 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <4>; + iommus = <&apps_smmu 0x1804 0x0>; + }; + + compute-cb@5 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <5>; + iommus = <&apps_smmu 0x1805 0x0>; + }; + }; + }; + }; + lpass_tlmm: pinctrl@33c0000 { compatible = "qcom,sm8350-lpass-lpi-pinctrl"; reg = <0 0x033c0000 0 0x20000>, @@ -2078,7 +2214,7 @@ mpss: remoteproc@4080000 { compatible = "qcom,sm8350-mpss-pas"; - reg = <0x0 0x04080000 0x0 0x4040>; + reg = <0x0 0x04080000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_EDGE_RISING>, <&smp2p_modem_in 0 IRQ_TYPE_EDGE_RISING>, @@ -2360,6 +2496,115 @@ qcom,bcm-voters = <&apps_bcm_voter>; }; + cdsp: remoteproc@a300000 { + compatible = "qcom,sm8350-cdsp-pas"; + reg = <0x0 0x0a300000 0x0 0x10000>; + + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", "fatal", "ready", + "handover", "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + power-domains = <&rpmhpd RPMHPD_CX>, + <&rpmhpd RPMHPD_MXC>; + power-domain-names = "cx", "mxc"; + + interconnects = <&compute_noc MASTER_CDSP_PROC 0 &mc_virt SLAVE_EBI1 0>; + + memory-region = <&pil_cdsp_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_cdsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_CDSP + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_CDSP + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + label = "cdsp"; + qcom,remote-pid = <5>; + + fastrpc { + compatible = "qcom,fastrpc"; + qcom,glink-channels = "fastrpcglink-apps-dsp"; + label = "cdsp"; + qcom,non-secure-domain; + #address-cells = <1>; + #size-cells = <0>; + + compute-cb@1 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <1>; + iommus = <&apps_smmu 0x2161 0x0400>, + <&apps_smmu 0x1181 0x0420>; + }; + + compute-cb@2 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <2>; + iommus = <&apps_smmu 0x2162 0x0400>, + <&apps_smmu 0x1182 0x0420>; + }; + + compute-cb@3 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <3>; + iommus = <&apps_smmu 0x2163 0x0400>, + <&apps_smmu 0x1183 0x0420>; + }; + + compute-cb@4 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <4>; + iommus = <&apps_smmu 0x2164 0x0400>, + <&apps_smmu 0x1184 0x0420>; + }; + + compute-cb@5 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <5>; + iommus = <&apps_smmu 0x2165 0x0400>, + <&apps_smmu 0x1185 0x0420>; + }; + + compute-cb@6 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <6>; + iommus = <&apps_smmu 0x2166 0x0400>, + <&apps_smmu 0x1186 0x0420>; + }; + + compute-cb@7 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <7>; + iommus = <&apps_smmu 0x2167 0x0400>, + <&apps_smmu 0x1187 0x0420>; + }; + + compute-cb@8 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <8>; + iommus = <&apps_smmu 0x2168 0x0400>, + <&apps_smmu 0x1188 0x0420>; + }; + + /* note: secure cb9 in downstream */ + }; + }; + }; + usb_1: usb@a6f8800 { compatible = "qcom,sm8350-dwc3", "qcom,dwc3"; reg = <0 0x0a6f8800 0 0x400>; @@ -2409,6 +2654,8 @@ iommus = <&apps_smmu 0x0 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; @@ -2485,6 +2732,8 @@ iommus = <&apps_smmu 0x20 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_2_hsphy>, <&usb_2_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; }; @@ -3285,142 +3534,6 @@ dma-coherent; }; - adsp: remoteproc@17300000 { - compatible = "qcom,sm8350-adsp-pas"; - reg = <0 0x17300000 0 0x100>; - - interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; - interrupt-names = "wdog", "fatal", "ready", - "handover", "stop-ack"; - - clocks = <&rpmhcc RPMH_CXO_CLK>; - clock-names = "xo"; - - power-domains = <&rpmhpd RPMHPD_LCX>, - <&rpmhpd RPMHPD_LMX>; - power-domain-names = "lcx", "lmx"; - - memory-region = <&pil_adsp_mem>; - - qcom,qmp = <&aoss_qmp>; - - qcom,smem-states = <&smp2p_adsp_out 0>; - qcom,smem-state-names = "stop"; - - status = "disabled"; - - glink-edge { - interrupts-extended = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP - IRQ_TYPE_EDGE_RISING>; - mboxes = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP>; - - label = "lpass"; - qcom,remote-pid = <2>; - - apr { - compatible = "qcom,apr-v2"; - qcom,glink-channels = "apr_audio_svc"; - qcom,domain = ; - #address-cells = <1>; - #size-cells = <0>; - - service@3 { - reg = ; - compatible = "qcom,q6core"; - qcom,protection-domain = "avs/audio", "msm/adsp/audio_pd"; - }; - - q6afe: service@4 { - compatible = "qcom,q6afe"; - reg = ; - qcom,protection-domain = "avs/audio", "msm/adsp/audio_pd"; - - q6afedai: dais { - compatible = "qcom,q6afe-dais"; - #address-cells = <1>; - #size-cells = <0>; - #sound-dai-cells = <1>; - }; - - q6afecc: clock-controller { - compatible = "qcom,q6afe-clocks"; - #clock-cells = <2>; - }; - }; - - q6asm: service@7 { - compatible = "qcom,q6asm"; - reg = ; - qcom,protection-domain = "avs/audio", "msm/adsp/audio_pd"; - - q6asmdai: dais { - compatible = "qcom,q6asm-dais"; - #address-cells = <1>; - #size-cells = <0>; - #sound-dai-cells = <1>; - iommus = <&apps_smmu 0x1801 0x0>; - - dai@0 { - reg = <0>; - }; - - dai@1 { - reg = <1>; - }; - - dai@2 { - reg = <2>; - }; - }; - }; - - q6adm: service@8 { - compatible = "qcom,q6adm"; - reg = ; - qcom,protection-domain = "avs/audio", "msm/adsp/audio_pd"; - - q6routing: routing { - compatible = "qcom,q6adm-routing"; - #sound-dai-cells = <0>; - }; - }; - }; - - fastrpc { - compatible = "qcom,fastrpc"; - qcom,glink-channels = "fastrpcglink-apps-dsp"; - label = "adsp"; - qcom,non-secure-domain; - #address-cells = <1>; - #size-cells = <0>; - - compute-cb@3 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <3>; - iommus = <&apps_smmu 0x1803 0x0>; - }; - - compute-cb@4 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <4>; - iommus = <&apps_smmu 0x1804 0x0>; - }; - - compute-cb@5 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <5>; - iommus = <&apps_smmu 0x1805 0x0>; - }; - }; - }; - }; - intc: interrupt-controller@17a00000 { compatible = "arm,gic-v3"; #interrupt-cells = <3>; @@ -3589,115 +3702,6 @@ #freq-domain-cells = <1>; #clock-cells = <1>; }; - - cdsp: remoteproc@98900000 { - compatible = "qcom,sm8350-cdsp-pas"; - reg = <0 0x98900000 0 0x1400000>; - - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, - <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, - <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>, - <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>, - <&smp2p_cdsp_in 3 IRQ_TYPE_EDGE_RISING>; - interrupt-names = "wdog", "fatal", "ready", - "handover", "stop-ack"; - - clocks = <&rpmhcc RPMH_CXO_CLK>; - clock-names = "xo"; - - power-domains = <&rpmhpd RPMHPD_CX>, - <&rpmhpd RPMHPD_MXC>; - power-domain-names = "cx", "mxc"; - - interconnects = <&compute_noc MASTER_CDSP_PROC 0 &mc_virt SLAVE_EBI1 0>; - - memory-region = <&pil_cdsp_mem>; - - qcom,qmp = <&aoss_qmp>; - - qcom,smem-states = <&smp2p_cdsp_out 0>; - qcom,smem-state-names = "stop"; - - status = "disabled"; - - glink-edge { - interrupts-extended = <&ipcc IPCC_CLIENT_CDSP - IPCC_MPROC_SIGNAL_GLINK_QMP - IRQ_TYPE_EDGE_RISING>; - mboxes = <&ipcc IPCC_CLIENT_CDSP - IPCC_MPROC_SIGNAL_GLINK_QMP>; - - label = "cdsp"; - qcom,remote-pid = <5>; - - fastrpc { - compatible = "qcom,fastrpc"; - qcom,glink-channels = "fastrpcglink-apps-dsp"; - label = "cdsp"; - qcom,non-secure-domain; - #address-cells = <1>; - #size-cells = <0>; - - compute-cb@1 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <1>; - iommus = <&apps_smmu 0x2161 0x0400>, - <&apps_smmu 0x1181 0x0420>; - }; - - compute-cb@2 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <2>; - iommus = <&apps_smmu 0x2162 0x0400>, - <&apps_smmu 0x1182 0x0420>; - }; - - compute-cb@3 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <3>; - iommus = <&apps_smmu 0x2163 0x0400>, - <&apps_smmu 0x1183 0x0420>; - }; - - compute-cb@4 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <4>; - iommus = <&apps_smmu 0x2164 0x0400>, - <&apps_smmu 0x1184 0x0420>; - }; - - compute-cb@5 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <5>; - iommus = <&apps_smmu 0x2165 0x0400>, - <&apps_smmu 0x1185 0x0420>; - }; - - compute-cb@6 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <6>; - iommus = <&apps_smmu 0x2166 0x0400>, - <&apps_smmu 0x1186 0x0420>; - }; - - compute-cb@7 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <7>; - iommus = <&apps_smmu 0x2167 0x0400>, - <&apps_smmu 0x1187 0x0420>; - }; - - compute-cb@8 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <8>; - iommus = <&apps_smmu 0x2168 0x0400>, - <&apps_smmu 0x1188 0x0420>; - }; - - /* note: secure cb9 in downstream */ - }; - }; - }; }; thermal_zones: thermal-zones { diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi index 53147aa6f7e4..9c809fc5fa45 100644 --- a/arch/arm64/boot/dts/qcom/sm8450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi @@ -43,7 +43,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <32000>; + clock-frequency = <32764>; }; }; @@ -287,6 +287,192 @@ }; }; + ete-0 { + compatible = "arm,embedded-trace-extension"; + cpu = <&cpu0>; + + out-ports { + port { + ete0_out_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_in_ete0>; + }; + }; + }; + }; + + ete-1 { + compatible = "arm,embedded-trace-extension"; + cpu = <&cpu1>; + + out-ports { + port { + ete1_out_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_in_ete1>; + }; + }; + }; + }; + + ete-2 { + compatible = "arm,embedded-trace-extension"; + cpu = <&cpu2>; + + out-ports { + port { + ete2_out_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_in_ete2>; + }; + }; + }; + }; + + ete-3 { + compatible = "arm,embedded-trace-extension"; + cpu = <&cpu3>; + + out-ports { + port { + ete3_out_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_in_ete3>; + }; + }; + }; + }; + + ete-4 { + compatible = "arm,embedded-trace-extension"; + cpu = <&cpu4>; + + out-ports { + port { + ete4_out_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_in_ete4>; + }; + }; + }; + }; + + ete-5 { + compatible = "arm,embedded-trace-extension"; + cpu = <&cpu5>; + + out-ports { + port { + ete5_out_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_in_ete5>; + }; + }; + }; + }; + + ete-6 { + compatible = "arm,embedded-trace-extension"; + cpu = <&cpu6>; + + out-ports { + port { + ete6_out_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_in_ete6>; + }; + }; + }; + }; + + ete-7 { + compatible = "arm,embedded-trace-extension"; + cpu = <&cpu7>; + + out-ports { + port { + ete7_out_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_in_ete7>; + }; + }; + }; + }; + + funnel-ete { + compatible = "arm,coresight-static-funnel"; + + out-ports { + port { + funnel_ete_out_funnel_apss: endpoint { + remote-endpoint = + <&funnel_apss_in_funnel_ete>; + }; + }; + }; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + funnel_ete_in_ete0: endpoint { + remote-endpoint = + <&ete0_out_funnel_ete>; + }; + }; + + port@1 { + reg = <1>; + funnel_ete_in_ete1: endpoint { + remote-endpoint = + <&ete1_out_funnel_ete>; + }; + }; + + port@2 { + reg = <2>; + funnel_ete_in_ete2: endpoint { + remote-endpoint = + <&ete2_out_funnel_ete>; + }; + }; + + port@3 { + reg = <3>; + funnel_ete_in_ete3: endpoint { + remote-endpoint = + <&ete3_out_funnel_ete>; + }; + }; + + port@4 { + reg = <4>; + funnel_ete_in_ete4: endpoint { + remote-endpoint = + <&ete4_out_funnel_ete>; + }; + }; + + port@5 { + reg = <5>; + funnel_ete_in_ete5: endpoint { + remote-endpoint = + <&ete5_out_funnel_ete>; + }; + }; + + port@6 { + reg = <6>; + funnel_ete_in_ete6: endpoint { + remote-endpoint = + <&ete6_out_funnel_ete>; + }; + }; + + port@7 { + reg = <7>; + funnel_ete_in_ete7: endpoint { + remote-endpoint = + <&ete7_out_funnel_ete>; + }; + }; + }; + }; + firmware { scm: scm { compatible = "qcom,scm-sm8450", "qcom,scm"; @@ -2496,6 +2682,112 @@ }; }; + remoteproc_adsp: remoteproc@3000000 { + compatible = "qcom,sm8450-adsp-pas"; + reg = <0x0 0x03000000 0x0 0x10000>; + + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", "fatal", "ready", + "handover", "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + power-domains = <&rpmhpd RPMHPD_LCX>, + <&rpmhpd RPMHPD_LMX>; + power-domain-names = "lcx", "lmx"; + + memory-region = <&adsp_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_adsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + remoteproc_adsp_glink: glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + label = "lpass"; + qcom,remote-pid = <2>; + + gpr { + compatible = "qcom,gpr"; + qcom,glink-channels = "adsp_apps"; + qcom,domain = ; + qcom,intents = <512 20>; + #address-cells = <1>; + #size-cells = <0>; + + q6apm: service@1 { + compatible = "qcom,q6apm"; + reg = ; + #sound-dai-cells = <0>; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6apmdai: dais { + compatible = "qcom,q6apm-dais"; + iommus = <&apps_smmu 0x1801 0x0>; + }; + + q6apmbedai: bedais { + compatible = "qcom,q6apm-lpass-dais"; + #sound-dai-cells = <1>; + }; + }; + + q6prm: service@2 { + compatible = "qcom,q6prm"; + reg = ; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6prmcc: clock-controller { + compatible = "qcom,q6prm-lpass-clocks"; + #clock-cells = <2>; + }; + }; + }; + + fastrpc { + compatible = "qcom,fastrpc"; + qcom,glink-channels = "fastrpcglink-apps-dsp"; + label = "adsp"; + qcom,non-secure-domain; + #address-cells = <1>; + #size-cells = <0>; + + compute-cb@3 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <3>; + iommus = <&apps_smmu 0x1803 0x0>; + }; + + compute-cb@4 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <4>; + iommus = <&apps_smmu 0x1804 0x0>; + }; + + compute-cb@5 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <5>; + iommus = <&apps_smmu 0x1805 0x0>; + }; + }; + }; + }; + wsa2macro: codec@31e0000 { compatible = "qcom,sm8450-lpass-wsa-macro"; reg = <0 0x031e0000 0 0x1000>; @@ -2692,115 +2984,9 @@ status = "disabled"; }; - remoteproc_adsp: remoteproc@30000000 { - compatible = "qcom,sm8450-adsp-pas"; - reg = <0 0x30000000 0 0x100>; - - interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; - interrupt-names = "wdog", "fatal", "ready", - "handover", "stop-ack"; - - clocks = <&rpmhcc RPMH_CXO_CLK>; - clock-names = "xo"; - - power-domains = <&rpmhpd RPMHPD_LCX>, - <&rpmhpd RPMHPD_LMX>; - power-domain-names = "lcx", "lmx"; - - memory-region = <&adsp_mem>; - - qcom,qmp = <&aoss_qmp>; - - qcom,smem-states = <&smp2p_adsp_out 0>; - qcom,smem-state-names = "stop"; - - status = "disabled"; - - remoteproc_adsp_glink: glink-edge { - interrupts-extended = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP - IRQ_TYPE_EDGE_RISING>; - mboxes = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP>; - - label = "lpass"; - qcom,remote-pid = <2>; - - gpr { - compatible = "qcom,gpr"; - qcom,glink-channels = "adsp_apps"; - qcom,domain = ; - qcom,intents = <512 20>; - #address-cells = <1>; - #size-cells = <0>; - - q6apm: service@1 { - compatible = "qcom,q6apm"; - reg = ; - #sound-dai-cells = <0>; - qcom,protection-domain = "avs/audio", - "msm/adsp/audio_pd"; - - q6apmdai: dais { - compatible = "qcom,q6apm-dais"; - iommus = <&apps_smmu 0x1801 0x0>; - }; - - q6apmbedai: bedais { - compatible = "qcom,q6apm-lpass-dais"; - #sound-dai-cells = <1>; - }; - }; - - q6prm: service@2 { - compatible = "qcom,q6prm"; - reg = ; - qcom,protection-domain = "avs/audio", - "msm/adsp/audio_pd"; - - q6prmcc: clock-controller { - compatible = "qcom,q6prm-lpass-clocks"; - #clock-cells = <2>; - }; - }; - }; - - fastrpc { - compatible = "qcom,fastrpc"; - qcom,glink-channels = "fastrpcglink-apps-dsp"; - label = "adsp"; - qcom,non-secure-domain; - #address-cells = <1>; - #size-cells = <0>; - - compute-cb@3 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <3>; - iommus = <&apps_smmu 0x1803 0x0>; - }; - - compute-cb@4 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <4>; - iommus = <&apps_smmu 0x1804 0x0>; - }; - - compute-cb@5 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <5>; - iommus = <&apps_smmu 0x1805 0x0>; - }; - }; - }; - }; - remoteproc_cdsp: remoteproc@32300000 { compatible = "qcom,sm8450-cdsp-pas"; - reg = <0 0x32300000 0 0x1400000>; + reg = <0 0x32300000 0 0x10000>; interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, @@ -2907,7 +3093,7 @@ remoteproc_mpss: remoteproc@4080000 { compatible = "qcom,sm8450-mpss-pas"; - reg = <0x0 0x04080000 0x0 0x4040>; + reg = <0x0 0x04080000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_EDGE_RISING>, <&smp2p_modem_in 0 IRQ_TYPE_EDGE_RISING>, @@ -4144,6 +4330,546 @@ }; }; + stm@10002000 { + compatible = "arm,coresight-stm", "arm,primecell"; + reg = <0x0 0x10002000 0x0 0x1000>, + <0x0 0x16280000 0x0 0x180000>; + reg-names = "stm-base", "stm-stimulus-base"; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + out-ports { + port { + stm_out_funnel_in0: endpoint { + remote-endpoint = + <&funnel_in0_in_stm>; + }; + }; + }; + }; + + funnel@10041000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10041000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@7 { + reg = <7>; + funnel_in0_in_stm: endpoint { + remote-endpoint = + <&stm_out_funnel_in0>; + }; + }; + }; + + out-ports { + port { + funnel_in0_out_funnel_qdss: endpoint { + remote-endpoint = + <&funnel_qdss_in_funnel_in0>; + }; + }; + }; + }; + + funnel@10042000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + + reg = <0x0 0x10042000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@4 { + reg = <4>; + funnel_in1_in_funnel_apss: endpoint { + remote-endpoint = + <&funnel_apss_out_funnel_in1>; + }; + }; + + port@6 { + reg = <6>; + funnel_in1_in_funnel_dl_center: endpoint { + remote-endpoint = + <&funnel_dl_center_out_funnel_in1>; + }; + }; + }; + + out-ports { + port { + funnel_in1_out_funnel_qdss: endpoint { + remote-endpoint = + <&funnel_qdss_in_funnel_in1>; + }; + }; + }; + }; + + funnel@10045000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10045000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + funnel_qdss_in_funnel_in0: endpoint { + remote-endpoint = + <&funnel_in0_out_funnel_qdss>; + }; + }; + + port@1 { + reg = <1>; + funnel_qdss_in_funnel_in1: endpoint { + remote-endpoint = + <&funnel_in1_out_funnel_qdss>; + }; + }; + }; + + out-ports { + port { + funnel_qdss_out_funnel_aoss: endpoint { + remote-endpoint = + <&funnel_aoss_in_funnel_qdss>; + }; + }; + }; + }; + + replicator@10046000 { + compatible = "arm,coresight-dynamic-replicator", "arm,primecell"; + reg = <0x0 0x10046000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + replicator_qdss_in_replicator_swao: endpoint { + remote-endpoint = + <&replicator_swao_out_replicator_qdss>; + }; + }; + }; + + out-ports { + + port { + replicator_qdss_out_replicator_etr: endpoint { + remote-endpoint = + <&replicator_etr_in_replicator_qdss>; + }; + }; + }; + }; + + tmc_etr: tmc@10048000 { + compatible = "arm,coresight-tmc", "arm,primecell"; + reg = <0x0 0x10048000 0x0 0x1000>; + + iommus = <&apps_smmu 0x0600 0>; + arm,buffer-size = <0x10000>; + + arm,scatter-gather; + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tmc_etr_in_replicator_etr: endpoint { + remote-endpoint = + <&replicator_etr_out_tmc_etr>; + }; + }; + }; + }; + + replicator@1004e000 { + compatible = "arm,coresight-dynamic-replicator", "arm,primecell"; + reg = <0x0 0x1004e000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + replicator_etr_in_replicator_qdss: endpoint { + remote-endpoint = + <&replicator_qdss_out_replicator_etr>; + }; + }; + }; + + out-ports { + + port { + + replicator_etr_out_tmc_etr: endpoint { + remote-endpoint = + <&tmc_etr_in_replicator_etr>; + }; + }; + }; + }; + + funnel@10b04000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + + reg = <0x0 0x10b04000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@6 { + reg = <6>; + funnel_aoss_in_tpda_aoss: endpoint { + remote-endpoint = + <&tpda_aoss_out_funnel_aoss>; + }; + }; + + port@7 { + reg = <7>; + funnel_aoss_in_funnel_qdss: endpoint { + remote-endpoint = + <&funnel_qdss_out_funnel_aoss>; + }; + }; + }; + + out-ports { + port { + funnel_aoss_out_tmc_etf: endpoint { + remote-endpoint = + <&tmc_etf_in_funnel_aoss>; + }; + }; + }; + }; + + tmc@10b05000 { + compatible = "arm,coresight-tmc", "arm,primecell"; + reg = <0x0 0x10b05000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tmc_etf_in_funnel_aoss: endpoint { + remote-endpoint = + <&funnel_aoss_out_tmc_etf>; + }; + }; + }; + + out-ports { + port { + tmc_etf_out_replicator_swao: endpoint { + remote-endpoint = + <&replicator_swao_in_tmc_etf>; + }; + }; + }; + }; + + replicator@10b06000 { + compatible = "arm,coresight-dynamic-replicator", "arm,primecell"; + reg = <0x0 0x10b06000 0x0 0x1000>; + + qcom,replicator-loses-context; + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + replicator_swao_in_tmc_etf: endpoint { + remote-endpoint = + <&tmc_etf_out_replicator_swao>; + }; + }; + }; + + out-ports { + + port { + replicator_swao_out_replicator_qdss: endpoint { + remote-endpoint = + <&replicator_qdss_in_replicator_swao>; + }; + }; + }; + }; + + tpda@10b08000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + + reg = <0x0 0x10b08000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + tpda_aoss_in_tpdm_swao_prio_0: endpoint { + remote-endpoint = + <&tpdm_swao_prio_0_out_tpda_aoss>; + }; + }; + + port@4 { + reg = <4>; + tpda_aoss_in_tpdm_swao: endpoint { + remote-endpoint = + <&tpdm_swao_out_tpda_aoss>; + }; + }; + }; + + out-ports { + + port { + tpda_aoss_out_funnel_aoss: endpoint { + remote-endpoint = + <&funnel_aoss_in_tpda_aoss>; + }; + }; + }; + }; + + tpdm@10b09000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10b09000 0x0 0x1000>; + + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + out-ports { + port { + tpdm_swao_prio_0_out_tpda_aoss: endpoint { + remote-endpoint = + <&tpda_aoss_in_tpdm_swao_prio_0>; + }; + }; + }; + }; + + tpdm@10b0d000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10b0d000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + out-ports { + port { + tpdm_swao_out_tpda_aoss: endpoint { + remote-endpoint = + <&tpda_aoss_in_tpdm_swao>; + }; + }; + }; + }; + + tpdm@10c28000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10c28000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + out-ports { + port { + tpdm_dlct_out_tpda_dl_center_26: endpoint { + remote-endpoint = + <&tpda_dl_center_26_in_tpdm_dlct>; + }; + }; + }; + }; + + tpdm@10c29000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10c29000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + out-ports { + port { + tpdm_ipcc_out_tpda_dl_center_27: endpoint { + remote-endpoint = + <&tpda_dl_center_27_in_tpdm_ipcc>; + }; + }; + }; + }; + + cti@10c2a000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x10c2a000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@10c2b000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x10c2b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + tpda@10c2e000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x10c2e000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + + #address-cells = <1>; + #size-cells = <0>; + + port@1a { + reg = <26>; + tpda_dl_center_26_in_tpdm_dlct: endpoint { + remote-endpoint = + <&tpdm_dlct_out_tpda_dl_center_26>; + }; + }; + + port@1b { + reg = <27>; + tpda_dl_center_27_in_tpdm_ipcc: endpoint { + remote-endpoint = + <&tpdm_ipcc_out_tpda_dl_center_27>; + }; + }; + }; + + out-ports { + + port { + tpda_dl_center_out_funnel_dl_center: endpoint { + remote-endpoint = + <&funnel_dl_center_in_tpda_dl_center>; + }; + }; + }; + }; + + funnel@10c2f000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10c2f000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + + port { + funnel_dl_center_in_tpda_dl_center: endpoint { + remote-endpoint = + <&tpda_dl_center_out_funnel_dl_center>; + }; + }; + }; + + out-ports { + port { + funnel_dl_center_out_funnel_in1: endpoint { + remote-endpoint = + <&funnel_in1_in_funnel_dl_center>; + }; + }; + }; + }; + + funnel@13810000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + + reg = <0x0 0x13810000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + + port { + funnel_apss_in_funnel_ete: endpoint { + remote-endpoint = + <&funnel_ete_out_funnel_apss>; + }; + }; + }; + + out-ports { + port { + funnel_apss_out_funnel_in1: endpoint { + remote-endpoint = + <&funnel_in1_in_funnel_apss>; + }; + }; + }; + }; + + cti@138e0000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x138e0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@138f0000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x138f0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + cti@13900000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x13900000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + sram@146aa000 { compatible = "qcom,sm8450-imem", "syscon", "simple-mfd"; reg = <0 0x146aa000 0 0x1000>; @@ -4672,6 +5398,8 @@ iommus = <&apps_smmu 0x0 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; diff --git a/arch/arm64/boot/dts/qcom/sm8550-hdk.dts b/arch/arm64/boot/dts/qcom/sm8550-hdk.dts index 01c921602605..29bc1ddfc7b2 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-hdk.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-hdk.dts @@ -1172,7 +1172,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &swr0 { diff --git a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts index ab447fc252f7..5648ab60ba4c 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts @@ -825,7 +825,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &swr0 { diff --git a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts index 6052dd922ec5..3a6cb2791304 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts @@ -1005,7 +1005,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &swr0 { diff --git a/arch/arm64/boot/dts/qcom/sm8550-samsung-q5q.dts b/arch/arm64/boot/dts/qcom/sm8550-samsung-q5q.dts index 3c5d8d26704f..e8383faac576 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-samsung-q5q.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-samsung-q5q.dts @@ -565,7 +565,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &tlmm { diff --git a/arch/arm64/boot/dts/qcom/sm8550-sony-xperia-yodo-pdx234.dts b/arch/arm64/boot/dts/qcom/sm8550-sony-xperia-yodo-pdx234.dts index 85d487ef80a0..d90dc7b37c4a 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-sony-xperia-yodo-pdx234.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-sony-xperia-yodo-pdx234.dts @@ -722,7 +722,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &tlmm { diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index e7774d32fb6d..eac8de4005d8 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -1734,7 +1735,8 @@ , , , - ; + , + ; interrupt-names = "msi0", "msi1", "msi2", @@ -1742,7 +1744,8 @@ "msi4", "msi5", "msi6", - "msi7"; + "msi7", + "global"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; interrupt-map = <0 0 0 1 &intc 0 0 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ @@ -1850,7 +1853,8 @@ , , , - ; + , + ; interrupt-names = "msi0", "msi1", "msi2", @@ -1858,7 +1862,8 @@ "msi4", "msi5", "msi6", - "msi7"; + "msi7", + "global"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ @@ -2114,6 +2119,10 @@ qcom,gmu = <&gmu>; #cooling-cells = <2>; + interconnects = <&gem_noc MASTER_GFX3D QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "gfx-mem"; + status = "disabled"; zap-shader { @@ -2127,41 +2136,49 @@ opp-680000000 { opp-hz = /bits/ 64 <680000000>; opp-level = ; + opp-peak-kBps = <16500000>; }; opp-615000000 { opp-hz = /bits/ 64 <615000000>; opp-level = ; + opp-peak-kBps = <12449218>; }; opp-550000000 { opp-hz = /bits/ 64 <550000000>; opp-level = ; + opp-peak-kBps = <10687500>; }; opp-475000000 { opp-hz = /bits/ 64 <475000000>; opp-level = ; + opp-peak-kBps = <6074218>; }; opp-401000000 { opp-hz = /bits/ 64 <401000000>; opp-level = ; + opp-peak-kBps = <6074218>; }; opp-348000000 { opp-hz = /bits/ 64 <348000000>; opp-level = ; + opp-peak-kBps = <6074218>; }; opp-295000000 { opp-hz = /bits/ 64 <295000000>; opp-level = ; + opp-peak-kBps = <6074218>; }; opp-220000000 { opp-hz = /bits/ 64 <220000000>; opp-level = ; + opp-peak-kBps = <2136718>; }; }; }; @@ -2314,7 +2331,7 @@ remoteproc_mpss: remoteproc@4080000 { compatible = "qcom,sm8550-mpss-pas"; - reg = <0x0 0x04080000 0x0 0x4040>; + reg = <0x0 0x04080000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_EDGE_RISING>, <&smp2p_modem_in 0 IRQ_TYPE_EDGE_RISING>, @@ -2354,6 +2371,137 @@ }; }; + remoteproc_adsp: remoteproc@6800000 { + compatible = "qcom,sm8550-adsp-pas"; + reg = <0x0 0x06800000 0x0 0x10000>; + + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", "fatal", "ready", + "handover", "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + power-domains = <&rpmhpd RPMHPD_LCX>, + <&rpmhpd RPMHPD_LMX>; + power-domain-names = "lcx", "lmx"; + + interconnects = <&lpass_lpicx_noc MASTER_LPASS_PROC 0 &mc_virt SLAVE_EBI1 0>; + + memory-region = <&adspslpi_mem>, <&q6_adsp_dtb_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_adsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + remoteproc_adsp_glink: glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + label = "lpass"; + qcom,remote-pid = <2>; + + fastrpc { + compatible = "qcom,fastrpc"; + qcom,glink-channels = "fastrpcglink-apps-dsp"; + label = "adsp"; + qcom,non-secure-domain; + #address-cells = <1>; + #size-cells = <0>; + + compute-cb@3 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <3>; + iommus = <&apps_smmu 0x1003 0x80>, + <&apps_smmu 0x1063 0x0>; + dma-coherent; + }; + + compute-cb@4 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <4>; + iommus = <&apps_smmu 0x1004 0x80>, + <&apps_smmu 0x1064 0x0>; + dma-coherent; + }; + + compute-cb@5 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <5>; + iommus = <&apps_smmu 0x1005 0x80>, + <&apps_smmu 0x1065 0x0>; + dma-coherent; + }; + + compute-cb@6 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <6>; + iommus = <&apps_smmu 0x1006 0x80>, + <&apps_smmu 0x1066 0x0>; + dma-coherent; + }; + + compute-cb@7 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <7>; + iommus = <&apps_smmu 0x1007 0x80>, + <&apps_smmu 0x1067 0x0>; + dma-coherent; + }; + }; + + gpr { + compatible = "qcom,gpr"; + qcom,glink-channels = "adsp_apps"; + qcom,domain = ; + qcom,intents = <512 20>; + #address-cells = <1>; + #size-cells = <0>; + + q6apm: service@1 { + compatible = "qcom,q6apm"; + reg = ; + #sound-dai-cells = <0>; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6apmdai: dais { + compatible = "qcom,q6apm-dais"; + iommus = <&apps_smmu 0x1001 0x80>, + <&apps_smmu 0x1061 0x0>; + }; + + q6apmbedai: bedais { + compatible = "qcom,q6apm-lpass-dais"; + #sound-dai-cells = <1>; + }; + }; + + q6prm: service@2 { + compatible = "qcom,q6prm"; + reg = ; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6prmcc: clock-controller { + compatible = "qcom,q6prm-lpass-clocks"; + #clock-cells = <2>; + }; + }; + }; + }; + }; + lpass_wsa2macro: codec@6aa0000 { compatible = "qcom,sm8550-lpass-wsa-macro"; reg = <0 0x06aa0000 0 0x1000>; @@ -2872,9 +3020,8 @@ power-domains = <&dispcc MDSS_GDSC>; - interconnects = <&mmss_noc MASTER_MDP 0 &gem_noc SLAVE_LLCC 0>, - <&mc_virt MASTER_LLCC 0 &mc_virt SLAVE_EBI1 0>; - interconnect-names = "mdp0-mem", "mdp1-mem"; + interconnects = <&mmss_noc MASTER_MDP 0 &mc_virt SLAVE_EBI1 0>; + interconnect-names = "mdp0-mem"; iommus = <&apps_smmu 0x1c00 0x2>; @@ -4576,137 +4723,6 @@ interrupts = ; }; - remoteproc_adsp: remoteproc@30000000 { - compatible = "qcom,sm8550-adsp-pas"; - reg = <0x0 0x30000000 0x0 0x100>; - - interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; - interrupt-names = "wdog", "fatal", "ready", - "handover", "stop-ack"; - - clocks = <&rpmhcc RPMH_CXO_CLK>; - clock-names = "xo"; - - power-domains = <&rpmhpd RPMHPD_LCX>, - <&rpmhpd RPMHPD_LMX>; - power-domain-names = "lcx", "lmx"; - - interconnects = <&lpass_lpicx_noc MASTER_LPASS_PROC 0 &mc_virt SLAVE_EBI1 0>; - - memory-region = <&adspslpi_mem>, <&q6_adsp_dtb_mem>; - - qcom,qmp = <&aoss_qmp>; - - qcom,smem-states = <&smp2p_adsp_out 0>; - qcom,smem-state-names = "stop"; - - status = "disabled"; - - remoteproc_adsp_glink: glink-edge { - interrupts-extended = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP - IRQ_TYPE_EDGE_RISING>; - mboxes = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP>; - - label = "lpass"; - qcom,remote-pid = <2>; - - fastrpc { - compatible = "qcom,fastrpc"; - qcom,glink-channels = "fastrpcglink-apps-dsp"; - label = "adsp"; - qcom,non-secure-domain; - #address-cells = <1>; - #size-cells = <0>; - - compute-cb@3 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <3>; - iommus = <&apps_smmu 0x1003 0x80>, - <&apps_smmu 0x1063 0x0>; - dma-coherent; - }; - - compute-cb@4 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <4>; - iommus = <&apps_smmu 0x1004 0x80>, - <&apps_smmu 0x1064 0x0>; - dma-coherent; - }; - - compute-cb@5 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <5>; - iommus = <&apps_smmu 0x1005 0x80>, - <&apps_smmu 0x1065 0x0>; - dma-coherent; - }; - - compute-cb@6 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <6>; - iommus = <&apps_smmu 0x1006 0x80>, - <&apps_smmu 0x1066 0x0>; - dma-coherent; - }; - - compute-cb@7 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <7>; - iommus = <&apps_smmu 0x1007 0x80>, - <&apps_smmu 0x1067 0x0>; - dma-coherent; - }; - }; - - gpr { - compatible = "qcom,gpr"; - qcom,glink-channels = "adsp_apps"; - qcom,domain = ; - qcom,intents = <512 20>; - #address-cells = <1>; - #size-cells = <0>; - - q6apm: service@1 { - compatible = "qcom,q6apm"; - reg = ; - #sound-dai-cells = <0>; - qcom,protection-domain = "avs/audio", - "msm/adsp/audio_pd"; - - q6apmdai: dais { - compatible = "qcom,q6apm-dais"; - iommus = <&apps_smmu 0x1001 0x80>, - <&apps_smmu 0x1061 0x0>; - }; - - q6apmbedai: bedais { - compatible = "qcom,q6apm-lpass-dais"; - #sound-dai-cells = <1>; - }; - }; - - q6prm: service@2 { - compatible = "qcom,q6prm"; - reg = ; - qcom,protection-domain = "avs/audio", - "msm/adsp/audio_pd"; - - q6prmcc: clock-controller { - compatible = "qcom,q6prm-lpass-clocks"; - #clock-cells = <2>; - }; - }; - }; - }; - }; - nsp_noc: interconnect@320c0000 { compatible = "qcom,sm8550-nsp-noc"; reg = <0 0x320c0000 0 0xe080>; @@ -4716,7 +4732,7 @@ remoteproc_cdsp: remoteproc@32300000 { compatible = "qcom,sm8550-cdsp-pas"; - reg = <0x0 0x32300000 0x0 0x1400000>; + reg = <0x0 0x32300000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm8650-hdk.dts b/arch/arm64/boot/dts/qcom/sm8650-hdk.dts index f00bdff4280a..d0912735b54e 100644 --- a/arch/arm64/boot/dts/qcom/sm8650-hdk.dts +++ b/arch/arm64/boot/dts/qcom/sm8650-hdk.dts @@ -1113,7 +1113,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &swr0 { diff --git a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts index 0db2cb03f252..76ef43c10f77 100644 --- a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts @@ -730,7 +730,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &swr0 { diff --git a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts index c5e8c3c2df91..71033fba21b5 100644 --- a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts +++ b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts @@ -1041,7 +1041,7 @@ }; &sleep_clk { - clock-frequency = <32000>; + clock-frequency = <32764>; }; &spi4 { diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index 25e47505adcb..86684cb9a932 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -365,6 +365,40 @@ }; }; + ete0 { + compatible = "arm,embedded-trace-extension"; + + cpu = <&cpu0>; + + out-ports { + port { + ete0_out_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_in_ete0>; + }; + }; + }; + }; + + funnel-ete { + compatible = "arm,coresight-static-funnel"; + + in-ports { + port { + funnel_ete_in_ete0: endpoint { + remote-endpoint = <&ete0_out_funnel_ete>; + }; + }; + }; + + out-ports { + port { + funnel_ete_out_funnel_apss: endpoint { + remote-endpoint = <&funnel_apss_in_funnel_ete>; + }; + }; + }; + }; + firmware { scm: scm { compatible = "qcom,scm-sm8650", "qcom,scm"; @@ -2233,7 +2267,8 @@ , , , - ; + , + ; interrupt-names = "msi0", "msi1", "msi2", @@ -2241,7 +2276,8 @@ "msi4", "msi5", "msi6", - "msi7"; + "msi7", + "global"; clocks = <&gcc GCC_PCIE_0_AUX_CLK>, <&gcc GCC_PCIE_0_CFG_AHB_CLK>, @@ -2365,7 +2401,8 @@ , , , - ; + , + ; interrupt-names = "msi0", "msi1", "msi2", @@ -2373,7 +2410,8 @@ "msi4", "msi5", "msi6", - "msi7"; + "msi7", + "global"; clocks = <&gcc GCC_PCIE_1_AUX_CLK>, <&gcc GCC_PCIE_1_CFG_AHB_CLK>, @@ -2636,6 +2674,10 @@ qcom,gmu = <&gmu>; #cooling-cells = <2>; + interconnects = <&gem_noc MASTER_GFX3D QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "gfx-mem"; + status = "disabled"; zap-shader { @@ -2649,56 +2691,67 @@ opp-231000000 { opp-hz = /bits/ 64 <231000000>; opp-level = ; + opp-peak-kBps = <2136718>; }; opp-310000000 { opp-hz = /bits/ 64 <310000000>; opp-level = ; + opp-peak-kBps = <2136718>; }; opp-366000000 { opp-hz = /bits/ 64 <366000000>; opp-level = ; + opp-peak-kBps = <6074218>; }; opp-422000000 { opp-hz = /bits/ 64 <422000000>; opp-level = ; + opp-peak-kBps = <8171875>; }; opp-500000000 { opp-hz = /bits/ 64 <500000000>; opp-level = ; + opp-peak-kBps = <8171875>; }; opp-578000000 { opp-hz = /bits/ 64 <578000000>; opp-level = ; + opp-peak-kBps = <8171875>; }; opp-629000000 { opp-hz = /bits/ 64 <629000000>; opp-level = ; + opp-peak-kBps = <10687500>; }; opp-680000000 { opp-hz = /bits/ 64 <680000000>; opp-level = ; + opp-peak-kBps = <12449218>; }; opp-720000000 { opp-hz = /bits/ 64 <720000000>; opp-level = ; + opp-peak-kBps = <12449218>; }; opp-770000000 { opp-hz = /bits/ 64 <770000000>; opp-level = ; + opp-peak-kBps = <12449218>; }; opp-834000000 { opp-hz = /bits/ 64 <834000000>; opp-level = ; + opp-peak-kBps = <14398437>; }; }; }; @@ -2853,7 +2906,7 @@ remoteproc_mpss: remoteproc@4080000 { compatible = "qcom,sm8650-mpss-pas"; - reg = <0 0x04080000 0 0x4040>; + reg = <0x0 0x04080000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_EDGE_RISING>, <&smp2p_modem_in 0 IRQ_TYPE_EDGE_RISING>, @@ -2904,6 +2957,154 @@ }; }; + remoteproc_adsp: remoteproc@6800000 { + compatible = "qcom,sm8650-adsp-pas"; + reg = <0x0 0x06800000 0x0 0x10000>; + + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", + "fatal", + "ready", + "handover", + "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + interconnects = <&lpass_lpicx_noc MASTER_LPASS_PROC QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + + power-domains = <&rpmhpd RPMHPD_LCX>, + <&rpmhpd RPMHPD_LMX>; + power-domain-names = "lcx", + "lmx"; + + memory-region = <&adspslpi_mem>, <&q6_adsp_dtb_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_adsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + remoteproc_adsp_glink: glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + + mboxes = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + qcom,remote-pid = <2>; + + label = "lpass"; + + fastrpc { + compatible = "qcom,fastrpc"; + + qcom,glink-channels = "fastrpcglink-apps-dsp"; + + label = "adsp"; + + qcom,non-secure-domain; + + #address-cells = <1>; + #size-cells = <0>; + + compute-cb@3 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <3>; + + iommus = <&apps_smmu 0x1003 0x80>, + <&apps_smmu 0x1043 0x20>; + dma-coherent; + }; + + compute-cb@4 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <4>; + + iommus = <&apps_smmu 0x1004 0x80>, + <&apps_smmu 0x1044 0x20>; + dma-coherent; + }; + + compute-cb@5 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <5>; + + iommus = <&apps_smmu 0x1005 0x80>, + <&apps_smmu 0x1045 0x20>; + dma-coherent; + }; + + compute-cb@6 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <6>; + + iommus = <&apps_smmu 0x1006 0x80>, + <&apps_smmu 0x1046 0x20>; + dma-coherent; + }; + + compute-cb@7 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <7>; + + iommus = <&apps_smmu 0x1007 0x40>, + <&apps_smmu 0x1067 0x0>, + <&apps_smmu 0x1087 0x0>; + dma-coherent; + }; + }; + + gpr { + compatible = "qcom,gpr"; + qcom,glink-channels = "adsp_apps"; + qcom,domain = ; + qcom,intents = <512 20>; + #address-cells = <1>; + #size-cells = <0>; + + q6apm: service@1 { + compatible = "qcom,q6apm"; + reg = ; + #sound-dai-cells = <0>; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6apmbedai: bedais { + compatible = "qcom,q6apm-lpass-dais"; + #sound-dai-cells = <1>; + }; + + q6apmdai: dais { + compatible = "qcom,q6apm-dais"; + iommus = <&apps_smmu 0x1001 0x80>, + <&apps_smmu 0x1061 0x0>; + }; + }; + + q6prm: service@2 { + compatible = "qcom,q6prm"; + reg = ; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6prmcc: clock-controller { + compatible = "qcom,q6prm-lpass-clocks"; + #clock-cells = <2>; + }; + }; + }; + }; + }; + lpass_wsa2macro: codec@6aa0000 { compatible = "qcom,sm8650-lpass-wsa-macro", "qcom,sm8550-lpass-wsa-macro"; reg = <0 0x06aa0000 0 0x1000>; @@ -3455,11 +3656,8 @@ resets = <&dispcc DISP_CC_MDSS_CORE_BCR>; interconnects = <&mmss_noc MASTER_MDP QCOM_ICC_TAG_ALWAYS - &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>, - <&mc_virt MASTER_LLCC QCOM_ICC_TAG_ALWAYS &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; - interconnect-names = "mdp0-mem", - "mdp1-mem"; + interconnect-names = "mdp0-mem"; power-domains = <&dispcc MDSS_GDSC>; @@ -4854,6 +5052,138 @@ }; }; + funnel@10042000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + + reg = <0x0 0x10042000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@4 { + reg = <4>; + + funnel_in1_in_funnel_apss: endpoint { + remote-endpoint = <&funnel_apss_out_funnel_in1>; + }; + }; + }; + + out-ports { + port { + funnel_in1_out_funnel_qdss: endpoint { + remote-endpoint = <&funnel_qdss_in_funnel_in1>; + }; + }; + }; + }; + + funnel@10045000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + + reg = <0x0 0x10045000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@1 { + reg = <1>; + + funnel_qdss_in_funnel_in1: endpoint { + remote-endpoint = <&funnel_in1_out_funnel_qdss>; + }; + }; + }; + + out-ports { + port { + funnel_qdss_out_funnel_aoss: endpoint { + remote-endpoint = <&funnel_aoss_in_funnel_qdss>; + }; + }; + }; + }; + + funnel@10b04000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + + reg = <0x0 0x10b04000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@7 { + reg = <7>; + + funnel_aoss_in_funnel_qdss: endpoint { + remote-endpoint = <&funnel_qdss_out_funnel_aoss>; + }; + }; + }; + + out-ports { + port { + funnel_aoss_out_tmc_etf: endpoint { + remote-endpoint = <&tmc_etf_in_funnel_aoss>; + }; + }; + }; + }; + + tmc@10b05000 { + compatible = "arm,coresight-tmc", "arm,primecell"; + + reg = <0x0 0x10b05000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tmc_etf_in_funnel_aoss: endpoint { + remote-endpoint = <&funnel_aoss_out_tmc_etf>; + }; + }; + }; + }; + + funnel@13810000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + + reg = <0x0 0x13810000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + funnel_apss_in_funnel_ete: endpoint { + remote-endpoint = <&funnel_ete_out_funnel_apss>; + }; + }; + }; + + out-ports { + port { + funnel_apss_out_funnel_in1: endpoint { + remote-endpoint = <&funnel_in1_in_funnel_apss>; + }; + }; + }; + }; + apps_smmu: iommu@15000000 { compatible = "qcom,sm8650-smmu-500", "qcom,smmu-500", "arm,mmu-500"; reg = <0 0x15000000 0 0x100000>; @@ -5322,154 +5652,6 @@ interrupts = ; }; - remoteproc_adsp: remoteproc@30000000 { - compatible = "qcom,sm8650-adsp-pas"; - reg = <0 0x30000000 0 0x100>; - - interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; - interrupt-names = "wdog", - "fatal", - "ready", - "handover", - "stop-ack"; - - clocks = <&rpmhcc RPMH_CXO_CLK>; - clock-names = "xo"; - - interconnects = <&lpass_lpicx_noc MASTER_LPASS_PROC QCOM_ICC_TAG_ALWAYS - &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; - - power-domains = <&rpmhpd RPMHPD_LCX>, - <&rpmhpd RPMHPD_LMX>; - power-domain-names = "lcx", - "lmx"; - - memory-region = <&adspslpi_mem>, <&q6_adsp_dtb_mem>; - - qcom,qmp = <&aoss_qmp>; - - qcom,smem-states = <&smp2p_adsp_out 0>; - qcom,smem-state-names = "stop"; - - status = "disabled"; - - remoteproc_adsp_glink: glink-edge { - interrupts-extended = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP - IRQ_TYPE_EDGE_RISING>; - - mboxes = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP>; - - qcom,remote-pid = <2>; - - label = "lpass"; - - fastrpc { - compatible = "qcom,fastrpc"; - - qcom,glink-channels = "fastrpcglink-apps-dsp"; - - label = "adsp"; - - qcom,non-secure-domain; - - #address-cells = <1>; - #size-cells = <0>; - - compute-cb@3 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <3>; - - iommus = <&apps_smmu 0x1003 0x80>, - <&apps_smmu 0x1043 0x20>; - dma-coherent; - }; - - compute-cb@4 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <4>; - - iommus = <&apps_smmu 0x1004 0x80>, - <&apps_smmu 0x1044 0x20>; - dma-coherent; - }; - - compute-cb@5 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <5>; - - iommus = <&apps_smmu 0x1005 0x80>, - <&apps_smmu 0x1045 0x20>; - dma-coherent; - }; - - compute-cb@6 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <6>; - - iommus = <&apps_smmu 0x1006 0x80>, - <&apps_smmu 0x1046 0x20>; - dma-coherent; - }; - - compute-cb@7 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <7>; - - iommus = <&apps_smmu 0x1007 0x40>, - <&apps_smmu 0x1067 0x0>, - <&apps_smmu 0x1087 0x0>; - dma-coherent; - }; - }; - - gpr { - compatible = "qcom,gpr"; - qcom,glink-channels = "adsp_apps"; - qcom,domain = ; - qcom,intents = <512 20>; - #address-cells = <1>; - #size-cells = <0>; - - q6apm: service@1 { - compatible = "qcom,q6apm"; - reg = ; - #sound-dai-cells = <0>; - qcom,protection-domain = "avs/audio", - "msm/adsp/audio_pd"; - - q6apmbedai: bedais { - compatible = "qcom,q6apm-lpass-dais"; - #sound-dai-cells = <1>; - }; - - q6apmdai: dais { - compatible = "qcom,q6apm-dais"; - iommus = <&apps_smmu 0x1001 0x80>, - <&apps_smmu 0x1061 0x0>; - }; - }; - - q6prm: service@2 { - compatible = "qcom,q6prm"; - reg = ; - qcom,protection-domain = "avs/audio", - "msm/adsp/audio_pd"; - - q6prmcc: clock-controller { - compatible = "qcom,q6prm-lpass-clocks"; - #clock-cells = <2>; - }; - }; - }; - }; - }; - nsp_noc: interconnect@320c0000 { compatible = "qcom,sm8650-nsp-noc"; reg = <0 0x320c0000 0 0xf080>; @@ -5481,7 +5663,7 @@ remoteproc_cdsp: remoteproc@32300000 { compatible = "qcom,sm8650-cdsp-pas"; - reg = <0 0x32300000 0 0x1400000>; + reg = <0x0 0x32300000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, @@ -5622,7 +5804,7 @@ /* note: secure cb9 in downstream */ - compute-cb@10 { + compute-cb@12 { compatible = "qcom,fastrpc-compute-cb"; reg = <12>; @@ -5632,7 +5814,7 @@ dma-coherent; }; - compute-cb@11 { + compute-cb@13 { compatible = "qcom,fastrpc-compute-cb"; reg = <13>; @@ -5642,7 +5824,7 @@ dma-coherent; }; - compute-cb@12 { + compute-cb@14 { compatible = "qcom,fastrpc-compute-cb"; reg = <14>; diff --git a/arch/arm64/boot/dts/qcom/sm8750-mtp.dts b/arch/arm64/boot/dts/qcom/sm8750-mtp.dts new file mode 100644 index 000000000000..9e3aacad7bda --- /dev/null +++ b/arch/arm64/boot/dts/qcom/sm8750-mtp.dts @@ -0,0 +1,794 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +/dts-v1/; + +#include +#include +#include +#include "sm8750.dtsi" +#include "pm8010.dtsi" +#include "pm8550.dtsi" +#define PMK8550VE_SID 8 +#include "pm8550ve.dtsi" +#include "pmd8028.dtsi" +#include "pmih0108.dtsi" +#include "pmk8550.dtsi" +#include "pmr735d_a.dtsi" +#include "sm8750-pmics.dtsi" + +/ { + model = "Qualcomm Technologies, Inc. SM8750 MTP"; + compatible = "qcom,sm8750-mtp", "qcom,sm8750"; + chassis-type = "handset"; + + + aliases { + serial0 = &uart7; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + clocks { + xo_board: xo-board { + compatible = "fixed-clock"; + clock-frequency = <76800000>; + #clock-cells = <0>; + }; + + sleep_clk: sleep-clk { + compatible = "fixed-clock"; + clock-frequency = <32000>; + #clock-cells = <0>; + }; + + bi_tcxo_div2: bi-tcxo-div2-clk { + compatible = "fixed-factor-clock"; + #clock-cells = <0>; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-mult = <1>; + clock-div = <2>; + }; + + bi_tcxo_ao_div2: bi-tcxo-ao-div2-clk { + compatible = "fixed-factor-clock"; + #clock-cells = <0>; + + clocks = <&rpmhcc RPMH_CXO_CLK_A>; + clock-mult = <1>; + clock-div = <2>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-0 = <&volume_up_n>; + pinctrl-names = "default"; + + key-volume-up { + label = "Volume Up"; + linux,code = ; + gpios = <&pm8550_gpios 6 GPIO_ACTIVE_LOW>; + debounce-interval = <15>; + linux,can-disable; + wakeup-source; + }; + }; + + vph_pwr: vph-pwr-regulator { + compatible = "regulator-fixed"; + + regulator-name = "vph_pwr"; + regulator-min-microvolt = <3700000>; + regulator-max-microvolt = <3700000>; + + regulator-always-on; + regulator-boot-on; + }; +}; + +&apps_rsc { + regulators-0 { + compatible = "qcom,pm8550-rpmh-regulators"; + + vdd-bob1-supply = <&vph_pwr>; + vdd-bob2-supply = <&vph_pwr>; + vdd-l1-l4-l10-supply = <&vreg_s3g_1p8>; + vdd-l2-l13-l14-supply = <&vreg_bob1>; + vdd-l3-supply = <&vreg_s7i_1p2>; + vdd-l5-l16-supply = <&vreg_bob1>; + vdd-l6-l7-supply = <&vreg_bob1>; + vdd-l8-l9-supply = <&vreg_bob1>; + vdd-l11-supply = <&vreg_s7i_1p2>; + vdd-l12-supply = <&vreg_s3g_1p8>; + vdd-l15-supply = <&vreg_s3g_1p8>; + vdd-l17-supply = <&vreg_bob2>; + + qcom,pmic-id = "b"; + + vreg_bob1: bob1 { + regulator-name = "vreg_bob1"; + regulator-min-microvolt = <3008000>; + regulator-max-microvolt = <4000000>; + regulator-initial-mode = ; + }; + + vreg_bob2: bob2 { + regulator-name = "vreg_bob2"; + regulator-min-microvolt = <2704000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + }; + + vreg_l1b_1p8: ldo1 { + regulator-name = "vreg_l1b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2b_3p0: ldo2 { + regulator-name = "vreg_l2b_3p0"; + regulator-min-microvolt = <3008000>; + regulator-max-microvolt = <3048000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l4b_1p8: ldo4 { + regulator-name = "vreg_l4b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l5b_3p1: ldo5 { + regulator-name = "vreg_l5b_3p1"; + regulator-min-microvolt = <3100000>; + regulator-max-microvolt = <3148000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l6b_1p8: ldo6 { + regulator-name = "vreg_l6b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l7b_1p8: ldo7 { + regulator-name = "vreg_l7b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + + }; + + vreg_l8b_1p8: ldo8 { + regulator-name = "vreg_l8b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l9b_2p9: ldo9 { + regulator-name = "vreg_l9b_2p9"; + regulator-min-microvolt = <2960000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l10b_1p8: ldo10 { + regulator-name = "vreg_l10b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l11b_1p0: ldo11 { + regulator-name = "vreg_l11b_1p0"; + regulator-min-microvolt = <1064000>; + regulator-max-microvolt = <1292000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l12b_1p8: ldo12 { + regulator-name = "vreg_l12b_1p8"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l13b_3p0: ldo13 { + regulator-name = "vreg_l13b_3p0"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3000000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l14b_3p2: ldo14 { + regulator-name = "vreg_l14b_3p2"; + regulator-min-microvolt = <3200000>; + regulator-max-microvolt = <3200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l15b_1p8: ldo15 { + regulator-name = "vreg_l15b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l16b_2p8: ldo16 { + regulator-name = "vreg_l16b_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l17b_2p5: ldo17 { + regulator-name = "vreg_l17b_2p5"; + regulator-min-microvolt = <2504000>; + regulator-max-microvolt = <2504000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-1 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s7i_1p2>; + vdd-l2-supply = <&vreg_s1d_0p97>; + vdd-l3-supply = <&vreg_s1d_0p97>; + vdd-s1-supply = <&vph_pwr>; + vdd-s3-supply = <&vph_pwr>; + vdd-s4-supply = <&vph_pwr>; + + qcom,pmic-id = "d"; + + vreg_s1d_0p97: smps1 { + regulator-name = "vreg_s1d_0p97"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + vreg_s3d_1p2: smps3 { + regulator-name = "vreg_s3d_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1300000>; + regulator-initial-mode = ; + }; + + vreg_s4d_0p85: smps4 { + regulator-name = "vreg_s4d_0p85"; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1036000>; + regulator-initial-mode = ; + }; + + vreg_l1d_1p2: ldo1 { + regulator-name = "vreg_l1d_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2d_0p88: ldo2 { + regulator-name = "vreg_l2d_0p88"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3d_0p88: ldo3 { + regulator-name = "vreg_l3d_0p88"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-2 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s1d_0p97>; + vdd-l2-supply = <&vreg_s7i_1p2>; + vdd-l3-supply = <&vreg_s3g_1p8>; + vdd-s5-supply = <&vph_pwr>; + + qcom,pmic-id = "f"; + + vreg_s5f_0p5: smps5 { + regulator-name = "vreg_s5f_0p5"; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1000000>; + regulator-initial-mode = ; + }; + + vreg_l1f_0p88: ldo1 { + regulator-name = "vreg_l1f_0p88"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2f_1p2: ldo2 { + regulator-name = "vreg_l2f_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3f_1p8: ldo3 { + regulator-name = "vreg_l3f_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + }; + + regulators-3 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s1d_0p97>; + vdd-l2-supply = <&vreg_s3g_1p8>; + vdd-l3-supply = <&vreg_s7i_1p2>; + vdd-s1-supply = <&vph_pwr>; + vdd-s3-supply = <&vph_pwr>; + + qcom,pmic-id = "g"; + + vreg_s1g_0p5: smps1 { + regulator-name = "vreg_s1g_0p5"; + regulator-min-microvolt = <300000>; + regulator-max-microvolt = <700000>; + regulator-initial-mode = ; + }; + + vreg_s3g_1p8: smps3 { + regulator-name = "vreg_s3g_1p8"; + regulator-min-microvolt = <1856000>; + regulator-max-microvolt = <2000000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_s4g_0p75: smps4 { + regulator-name = "vreg_s4g_0p75"; + regulator-min-microvolt = <300000>; + regulator-max-microvolt = <900000>; + regulator-initial-mode = ; + }; + + vreg_l1g_0p91: ldo1 { + regulator-name = "vreg_l1g_0p91"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <936000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2g_1p8: ldo2 { + regulator-name = "vreg_l2g_1p8"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1860000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3g_1p2: ldo3 { + regulator-name = "vreg_l3g_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1256000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-4 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s7i_1p2>; + vdd-l2-supply = <&vreg_s7i_1p2>; + vdd-l3-supply = <&vreg_s1d_0p97>; + vdd-s7-supply = <&vph_pwr>; + vdd-s8-supply = <&vph_pwr>; + + qcom,pmic-id = "i"; + + vreg_s7i_1p2: smps7 { + regulator-name = "vreg_s7i_1p2"; + regulator-min-microvolt = <1224000>; + regulator-max-microvolt = <1340000>; + regulator-initial-mode = ; + }; + + vreg_s8i_0p9: smps8 { + regulator-name = "vreg_s8i_0p9"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <972000>; + regulator-initial-mode = ; + }; + + vreg_l1i_1p2: ldo1 { + regulator-name = "vreg_l1i_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2i_1p2: ldo2 { + regulator-name = "vreg_l2i_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3i_0p88: ldo3 { + regulator-name = "vreg_l3i_0p88"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-5 { + compatible = "qcom,pm8550vs-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s1d_0p97>; + vdd-l2-supply = <&vreg_s7i_1p2>; + vdd-s2-supply = <&vph_pwr>; + vdd-s3-supply = <&vph_pwr>; + vdd-s4-supply = <&vph_pwr>; + + qcom,pmic-id = "j"; + + vreg_s2j_1p1: smps2 { + regulator-name = "vreg_s2j_1p1"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + vreg_s3j_1p1: smps3 { + regulator-name = "vreg_s3j_1p1"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + vreg_l1j_0p91: ldo1 { + regulator-name = "vreg_l1j_0p91"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2j_1p2: ldo2 { + regulator-name = "vreg_l2j_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-6 { + compatible = "qcom,pm8010-rpmh-regulators"; + qcom,pmic-id = "m"; + + vdd-l1-l2-supply = <&vreg_s7i_1p2>; + vdd-l3-l4-supply = <&vreg_bob2>; + vdd-l5-supply = <&vreg_s3g_1p8>; + vdd-l6-supply = <&vreg_bob1>; + vdd-l7-supply = <&vreg_bob1>; + + vreg_l1m_1p1: ldo1 { + regulator-name = "vreg_l1m_1p1"; + regulator-min-microvolt = <1104000>; + regulator-max-microvolt = <1104000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2m_1p056: ldo2 { + regulator-name = "vreg_l2m_1p056"; + regulator-min-microvolt = <1056000>; + regulator-max-microvolt = <1056000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3m_2p8: ldo3 { + regulator-name = "vreg_l3m_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l4m_2p8: ldo4 { + regulator-name = "vreg_l4m_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l5m_1p8: ldo5 { + regulator-name = "vreg_l5m_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l6m_2p8: ldo6 { + regulator-name = "vreg_l6m_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l7m_2p96: ldo7 { + regulator-name = "vreg_l7m_2p96"; + regulator-min-microvolt = <2960000>; + regulator-max-microvolt = <2960000>; + regulator-initial-mode = ; + }; + }; + + regulators-7 { + compatible = "qcom,pm8010-rpmh-regulators"; + qcom,pmic-id = "n"; + + vdd-l1-l2-supply = <&vreg_s7i_1p2>; + vdd-l3-l4-supply = <&vreg_s3g_1p8>; + vdd-l5-supply = <&vreg_bob2>; + vdd-l6-supply = <&vreg_bob2>; + vdd-l7-supply = <&vreg_bob1>; + + vreg_l1n_1p1: ldo1 { + regulator-name = "vreg_l1n_1p1"; + regulator-min-microvolt = <1104000>; + regulator-max-microvolt = <1104000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2n_1p1: ldo2 { + regulator-name = "vreg_l2n_1p1"; + regulator-min-microvolt = <1104000>; + regulator-max-microvolt = <1104000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3n_1p8: ldo3 { + regulator-name = "vreg_l3n_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l4n_1p8: ldo4 { + regulator-name = "vreg_l4n_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l5n_2p8: ldo5 { + regulator-name = "vreg_l5n_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l6n_2p8: ldo6 { + regulator-name = "vreg_l6n_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l7n_3p3: ldo7 { + regulator-name = "vreg_l7n_3p3"; + regulator-min-microvolt = <3304000>; + regulator-max-microvolt = <3304000>; + regulator-initial-mode = ; + }; + }; +}; + +&pm8550_flash { + status = "okay"; + + led-0 { + function = LED_FUNCTION_FLASH; + color = ; + led-sources = <1>, <4>; + led-max-microamp = <500000>; + flash-max-microamp = <2000000>; + flash-max-timeout-us = <1280000>; + function-enumerator = <0>; + }; + + led-1 { + function = LED_FUNCTION_FLASH; + color = ; + led-sources = <2>, <3>; + led-max-microamp = <500000>; + flash-max-microamp = <2000000>; + flash-max-timeout-us = <1280000>; + function-enumerator = <1>; + }; +}; + +&pm8550_gpios { + volume_up_n: volume-up-n-state { + pins = "gpio6"; + function = "normal"; + bias-pull-up; + input-enable; + power-source = <1>; + }; +}; + +&pm8550_pwm { + status = "okay"; + + multi-led { + color = ; + function = LED_FUNCTION_STATUS; + + #address-cells = <1>; + #size-cells = <0>; + + led@1 { + reg = <1>; + color = ; + }; + + led@2 { + reg = <2>; + color = ; + }; + + led@3 { + reg = <3>; + color = ; + }; + }; +}; + +&pon_pwrkey { + status = "okay"; +}; + +&pon_resin { + linux,code = ; + + status = "okay"; +}; + +&pmih0108_eusb2_repeater { + status = "okay"; + + vdd18-supply = <&vreg_l15b_1p8>; + vdd3-supply = <&vreg_l5b_3p1>; +}; + +&qupv3_1 { + status = "okay"; +}; + +&tlmm { + /* reserved for secure world */ + gpio-reserved-ranges = <36 4>, <74 1>; +}; + +&uart7 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/qcom/sm8750-pmics.dtsi b/arch/arm64/boot/dts/qcom/sm8750-pmics.dtsi new file mode 100644 index 000000000000..6eb8d78937c3 --- /dev/null +++ b/arch/arm64/boot/dts/qcom/sm8750-pmics.dtsi @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +/ { + thermal-zones { + pm8550ve-d-thermal { + polling-delay-passive = <100>; + + thermal-sensors = <&pm8550ve_d_temp_alarm>; + + trips { + trip0 { + temperature = <95000>; + hysteresis = <0>; + type = "passive"; + }; + + trip1 { + temperature = <115000>; + hysteresis = <0>; + type = "hot"; + }; + }; + }; + + pm8550ve-f-thermal { + polling-delay-passive = <100>; + + thermal-sensors = <&pm8550ve_f_temp_alarm>; + + trips { + trip0 { + temperature = <95000>; + hysteresis = <0>; + type = "passive"; + }; + + trip1 { + temperature = <115000>; + hysteresis = <0>; + type = "hot"; + }; + }; + }; + + pm8550ve-g-thermal { + polling-delay-passive = <100>; + + thermal-sensors = <&pm8550ve_g_temp_alarm>; + + trips { + trip0 { + temperature = <95000>; + hysteresis = <0>; + type = "passive"; + }; + + trip1 { + temperature = <115000>; + hysteresis = <0>; + type = "hot"; + }; + }; + }; + + pm8550vs-j-thermal { + polling-delay-passive = <100>; + + thermal-sensors = <&pm8550vs_j_temp_alarm>; + + trips { + trip0 { + temperature = <95000>; + hysteresis = <0>; + type = "passive"; + }; + + trip1 { + temperature = <115000>; + hysteresis = <0>; + type = "hot"; + }; + }; + }; + }; +}; + +&spmi_bus { + /* PM8550VE */ + pm8550ve_d: pmic@3 { + compatible = "qcom,pm8550ve", "qcom,spmi-pmic"; + reg = <0x3 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pm8550ve_d_temp_alarm: temp-alarm@a00 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0xa00>; + interrupts = <0x3 0xa 0x0 IRQ_TYPE_EDGE_BOTH>; + #thermal-sensor-cells = <0>; + }; + + pm8550ve_d_gpios: gpio@8800 { + compatible = "qcom,pm8550ve-gpio", "qcom,spmi-gpio"; + reg = <0x8800>; + gpio-controller; + gpio-ranges = <&pm8550ve_d_gpios 0 0 8>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + pm8550ve_f: pmic@5 { + compatible = "qcom,pm8550ve", "qcom,spmi-pmic"; + reg = <0x5 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pm8550ve_f_temp_alarm: temp-alarm@a00 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0xa00>; + interrupts = <0x5 0xa 0x0 IRQ_TYPE_EDGE_BOTH>; + #thermal-sensor-cells = <0>; + }; + + pm8550ve_f_gpios: gpio@8800 { + compatible = "qcom,pm8550ve-gpio", "qcom,spmi-gpio"; + reg = <0x8800>; + gpio-controller; + gpio-ranges = <&pm8550ve_f_gpios 0 0 6>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + pm8550ve_g: pmic@6 { + compatible = "qcom,pm8550ve", "qcom,spmi-pmic"; + reg = <0x6 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pm8550ve_g_temp_alarm: temp-alarm@a00 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0xa00>; + interrupts = <0x6 0xa 0x0 IRQ_TYPE_EDGE_BOTH>; + #thermal-sensor-cells = <0>; + }; + + pm8550ve_g_gpios: gpio@8800 { + compatible = "qcom,pm8550ve-gpio", "qcom,spmi-gpio"; + reg = <0x8800>; + gpio-controller; + gpio-ranges = <&pm8550ve_g_gpios 0 0 8>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + /* PM8550VS */ + pm8550vs_j: pmic@9 { + compatible = "qcom,pm8550vs", "qcom,spmi-pmic"; + reg = <0x9 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pm8550vs_j_temp_alarm: temp-alarm@a00 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0xa00>; + interrupts = <0x9 0xa 0x0 IRQ_TYPE_EDGE_BOTH>; + #thermal-sensor-cells = <0>; + }; + + pm8550vs_j_gpios: gpio@8800 { + compatible = "qcom,pm8550vs-gpio", "qcom,spmi-gpio"; + reg = <0x8800>; + gpio-controller; + gpio-ranges = <&pm8550vs_j_gpios 0 0 6>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/sm8750-qrd.dts b/arch/arm64/boot/dts/qcom/sm8750-qrd.dts new file mode 100644 index 000000000000..f77efab0aef9 --- /dev/null +++ b/arch/arm64/boot/dts/qcom/sm8750-qrd.dts @@ -0,0 +1,792 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +/dts-v1/; + +#include +#include +#include +#include "sm8750.dtsi" +#include "pm8010.dtsi" +#include "pm8550.dtsi" +#define PMK8550VE_SID 8 +#include "pm8550ve.dtsi" +#include "pmd8028.dtsi" +#include "pmih0108.dtsi" +#include "pmk8550.dtsi" +#include "pmr735d_a.dtsi" +#include "sm8750-pmics.dtsi" + +/ { + model = "Qualcomm Technologies, Inc. SM8750 QRD"; + compatible = "qcom,sm8750-qrd", "qcom,sm8750"; + chassis-type = "handset"; + + aliases { + serial0 = &uart7; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + clocks { + xo_board: xo-board { + compatible = "fixed-clock"; + clock-frequency = <76800000>; + #clock-cells = <0>; + }; + + sleep_clk: sleep-clk { + compatible = "fixed-clock"; + clock-frequency = <32000>; + #clock-cells = <0>; + }; + + bi_tcxo_div2: bi-tcxo-div2-clk { + compatible = "fixed-factor-clock"; + #clock-cells = <0>; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-mult = <1>; + clock-div = <2>; + }; + + bi_tcxo_ao_div2: bi-tcxo-ao-div2-clk { + compatible = "fixed-factor-clock"; + #clock-cells = <0>; + + clocks = <&rpmhcc RPMH_CXO_CLK_A>; + clock-mult = <1>; + clock-div = <2>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-0 = <&volume_up_n>; + pinctrl-names = "default"; + + key-volume-up { + label = "Volume Up"; + linux,code = ; + gpios = <&pm8550_gpios 6 GPIO_ACTIVE_LOW>; + debounce-interval = <15>; + linux,can-disable; + wakeup-source; + }; + }; + + vph_pwr: vph-pwr-regulator { + compatible = "regulator-fixed"; + + regulator-name = "vph_pwr"; + regulator-min-microvolt = <3700000>; + regulator-max-microvolt = <3700000>; + + regulator-always-on; + regulator-boot-on; + }; +}; + +&apps_rsc { + regulators-0 { + compatible = "qcom,pm8550-rpmh-regulators"; + + vdd-bob1-supply = <&vph_pwr>; + vdd-bob2-supply = <&vph_pwr>; + vdd-l1-l4-l10-supply = <&vreg_s3g_1p8>; + vdd-l2-l13-l14-supply = <&vreg_bob1>; + vdd-l3-supply = <&vreg_s7i_1p2>; + vdd-l5-l16-supply = <&vreg_bob1>; + vdd-l6-l7-supply = <&vreg_bob1>; + vdd-l8-l9-supply = <&vreg_bob1>; + vdd-l11-supply = <&vreg_s7i_1p2>; + vdd-l12-supply = <&vreg_s3g_1p8>; + vdd-l15-supply = <&vreg_s3g_1p8>; + vdd-l17-supply = <&vreg_bob2>; + + qcom,pmic-id = "b"; + + vreg_bob1: bob1 { + regulator-name = "vreg_bob1"; + regulator-min-microvolt = <3008000>; + regulator-max-microvolt = <4000000>; + regulator-initial-mode = ; + }; + + vreg_bob2: bob2 { + regulator-name = "vreg_bob2"; + regulator-min-microvolt = <2704000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + }; + + vreg_l1b_1p8: ldo1 { + regulator-name = "vreg_l1b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2b_3p0: ldo2 { + regulator-name = "vreg_l2b_3p0"; + regulator-min-microvolt = <3008000>; + regulator-max-microvolt = <3048000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l4b_1p8: ldo4 { + regulator-name = "vreg_l4b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l5b_3p1: ldo5 { + regulator-name = "vreg_l5b_3p1"; + regulator-min-microvolt = <3100000>; + regulator-max-microvolt = <3148000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l6b_1p8: ldo6 { + regulator-name = "vreg_l6b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l7b_1p8: ldo7 { + regulator-name = "vreg_l7b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l8b_1p8: ldo8 { + regulator-name = "vreg_l8b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l9b_2p9: ldo9 { + regulator-name = "vreg_l9b_2p9"; + regulator-min-microvolt = <2960000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l10b_1p8: ldo10 { + regulator-name = "vreg_l10b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l11b_1p0: ldo11 { + regulator-name = "vreg_l11b_1p0"; + regulator-min-microvolt = <1064000>; + regulator-max-microvolt = <1292000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l12b_1p8: ldo12 { + regulator-name = "vreg_l12b_1p8"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l13b_3p0: ldo13 { + regulator-name = "vreg_l13b_3p0"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3000000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l14b_3p2: ldo14 { + regulator-name = "vreg_l14b_3p2"; + regulator-min-microvolt = <3200000>; + regulator-max-microvolt = <3200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l15b_1p8: ldo15 { + regulator-name = "vreg_l15b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l16b_2p8: ldo16 { + regulator-name = "vreg_l16b_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l17b_2p5: ldo17 { + regulator-name = "vreg_l17b_2p5"; + regulator-min-microvolt = <2504000>; + regulator-max-microvolt = <2504000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-1 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s7i_1p2>; + vdd-l2-supply = <&vreg_s1d_0p97>; + vdd-l3-supply = <&vreg_s1d_0p97>; + vdd-s1-supply = <&vph_pwr>; + vdd-s3-supply = <&vph_pwr>; + vdd-s4-supply = <&vph_pwr>; + + qcom,pmic-id = "d"; + + vreg_s1d_0p97: smps1 { + regulator-name = "vreg_s1d_0p97"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + vreg_s3d_1p2: smps3 { + regulator-name = "vreg_s3d_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1300000>; + regulator-initial-mode = ; + }; + + vreg_s4d_0p85: smps4 { + regulator-name = "vreg_s4d_0p85"; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1036000>; + regulator-initial-mode = ; + }; + + vreg_l1d_1p2: ldo1 { + regulator-name = "vreg_l1d_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2d_0p88: ldo2 { + regulator-name = "vreg_l2d_0p88"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3d_0p88: ldo3 { + regulator-name = "vreg_l3d_0p88"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-2 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s1d_0p97>; + vdd-l2-supply = <&vreg_s7i_1p2>; + vdd-l3-supply = <&vreg_s3g_1p8>; + vdd-s5-supply = <&vph_pwr>; + + qcom,pmic-id = "f"; + + vreg_s5f_0p5: smps5 { + regulator-name = "vreg_s5f_0p5"; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1000000>; + regulator-initial-mode = ; + }; + + vreg_l1f_0p88: ldo1 { + regulator-name = "vreg_l1f_0p88"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2f_1p2: ldo2 { + regulator-name = "vreg_l2f_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3f_1p8: ldo3 { + regulator-name = "vreg_l3f_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + }; + + regulators-3 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s1d_0p97>; + vdd-l2-supply = <&vreg_s3g_1p8>; + vdd-l3-supply = <&vreg_s7i_1p2>; + vdd-s1-supply = <&vph_pwr>; + vdd-s3-supply = <&vph_pwr>; + + qcom,pmic-id = "g"; + + vreg_s1g_0p5: smps1 { + regulator-name = "vreg_s1g_0p5"; + regulator-min-microvolt = <300000>; + regulator-max-microvolt = <700000>; + regulator-initial-mode = ; + }; + + vreg_s3g_1p8: smps3 { + regulator-name = "vreg_s3g_1p8"; + regulator-min-microvolt = <1856000>; + regulator-max-microvolt = <2000000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_s4g_0p75: smps4 { + regulator-name = "vreg_s4g_0p75"; + regulator-min-microvolt = <300000>; + regulator-max-microvolt = <900000>; + regulator-initial-mode = ; + }; + + vreg_l1g_0p91: ldo1 { + regulator-name = "vreg_l1g_0p91"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <936000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2g_1p8: ldo2 { + regulator-name = "vreg_l2g_1p8"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1860000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3g_1p2: ldo3 { + regulator-name = "vreg_l3g_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1256000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-4 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s7i_1p2>; + vdd-l2-supply = <&vreg_s7i_1p2>; + vdd-l3-supply = <&vreg_s1d_0p97>; + vdd-s7-supply = <&vph_pwr>; + vdd-s8-supply = <&vph_pwr>; + + qcom,pmic-id = "i"; + + vreg_s7i_1p2: smps7 { + regulator-name = "vreg_s7i_1p2"; + regulator-min-microvolt = <1224000>; + regulator-max-microvolt = <1340000>; + regulator-initial-mode = ; + }; + + vreg_s8i_0p9: smps8 { + regulator-name = "vreg_s8i_0p9"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <972000>; + regulator-initial-mode = ; + }; + + vreg_l1i_1p2: ldo1 { + regulator-name = "vreg_l1i_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2i_1p2: ldo2 { + regulator-name = "vreg_l2i_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3i_0p88: ldo3 { + regulator-name = "vreg_l3i_0p88"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-5 { + compatible = "qcom,pm8550vs-rpmh-regulators"; + + vdd-l1-supply = <&vreg_s1d_0p97>; + vdd-l2-supply = <&vreg_s7i_1p2>; + vdd-s2-supply = <&vph_pwr>; + vdd-s3-supply = <&vph_pwr>; + + qcom,pmic-id = "j"; + + vreg_s2j_1p1: smps2 { + regulator-name = "vreg_s2j_1p1"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + vreg_s3j_1p1: smps3 { + regulator-name = "vreg_s3j_1p1"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + + vreg_l1j_0p91: ldo1 { + regulator-name = "vreg_l1j_0p91"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2j_1p2: ldo2 { + regulator-name = "vreg_l2j_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + }; + + regulators-6 { + compatible = "qcom,pm8010-rpmh-regulators"; + qcom,pmic-id = "m"; + + vdd-l1-l2-supply = <&vreg_s7i_1p2>; + vdd-l3-l4-supply = <&vreg_s3g_1p8>; + vdd-l5-supply = <&vreg_s3g_1p8>; + vdd-l6-supply = <&vreg_bob1>; + vdd-l7-supply = <&vreg_bob1>; + + vreg_l1m_1p1: ldo1 { + regulator-name = "vreg_l1m_1p1"; + regulator-min-microvolt = <1104000>; + regulator-max-microvolt = <1104000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2m_1p056: ldo2 { + regulator-name = "vreg_l2m_1p056"; + regulator-min-microvolt = <1056000>; + regulator-max-microvolt = <1056000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3m_2p8: ldo3 { + regulator-name = "vreg_l3m_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l4m_2p8: ldo4 { + regulator-name = "vreg_l4m_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l5m_1p8: ldo5 { + regulator-name = "vreg_l5m_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l6m_2p8: ldo6 { + regulator-name = "vreg_l6m_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l7m_2p96: ldo7 { + regulator-name = "vreg_l7m_2p96"; + regulator-min-microvolt = <2960000>; + regulator-max-microvolt = <2960000>; + regulator-initial-mode = ; + }; + }; + + regulators-7 { + compatible = "qcom,pm8010-rpmh-regulators"; + qcom,pmic-id = "n"; + + vdd-l1-l2-supply = <&vreg_s7i_1p2>; + vdd-l3-l4-supply = <&vreg_s7i_1p2>; + vdd-l5-supply = <&vreg_bob2>; + vdd-l6-supply = <&vreg_bob2>; + vdd-l7-supply = <&vreg_bob1>; + + vreg_l1n_1p1: ldo1 { + regulator-name = "vreg_l1n_1p1"; + regulator-min-microvolt = <1104000>; + regulator-max-microvolt = <1104000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l2n_1p1: ldo2 { + regulator-name = "vreg_l2n_1p1"; + regulator-min-microvolt = <1104000>; + regulator-max-microvolt = <1104000>; + regulator-initial-mode = ; + regulator-allow-set-load; + regulator-allowed-modes = ; + }; + + vreg_l3n_1p8: ldo3 { + regulator-name = "vreg_l3n_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l4n_1p8: ldo4 { + regulator-name = "vreg_l4n_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l5n_2p8: ldo5 { + regulator-name = "vreg_l5n_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l6n_2p8: ldo6 { + regulator-name = "vreg_l6n_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l7n_3p3: ldo7 { + regulator-name = "vreg_l7n_3p3"; + regulator-min-microvolt = <3304000>; + regulator-max-microvolt = <3304000>; + regulator-initial-mode = ; + }; + }; +}; + +&pm8550_flash { + status = "okay"; + + led-0 { + function = LED_FUNCTION_FLASH; + color = ; + led-sources = <1>, <4>; + led-max-microamp = <500000>; + flash-max-microamp = <2000000>; + flash-max-timeout-us = <1280000>; + function-enumerator = <0>; + }; + + led-1 { + function = LED_FUNCTION_FLASH; + color = ; + led-sources = <2>, <3>; + led-max-microamp = <500000>; + flash-max-microamp = <2000000>; + flash-max-timeout-us = <1280000>; + function-enumerator = <1>; + }; +}; + +&pm8550_gpios { + volume_up_n: volume-up-n-state { + pins = "gpio6"; + function = "normal"; + bias-pull-up; + input-enable; + power-source = <1>; + }; +}; + +&pm8550_pwm { + status = "okay"; + + multi-led { + color = ; + function = LED_FUNCTION_STATUS; + + #address-cells = <1>; + #size-cells = <0>; + + led@1 { + reg = <1>; + color = ; + }; + + led@2 { + reg = <2>; + color = ; + }; + + led@3 { + reg = <3>; + color = ; + }; + }; +}; + +&pon_pwrkey { + status = "okay"; +}; + +&pon_resin { + linux,code = ; + + status = "okay"; +}; + +&pmih0108_eusb2_repeater { + status = "okay"; + + vdd18-supply = <&vreg_l15b_1p8>; + vdd3-supply = <&vreg_l5b_3p1>; +}; + +&qupv3_1 { + status = "okay"; +}; + +&tlmm { + /* reserved for secure world */ + gpio-reserved-ranges = <36 4>, <74 1>; +}; + +&uart7 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/qcom/sm8750.dtsi b/arch/arm64/boot/dts/qcom/sm8750.dtsi new file mode 100644 index 000000000000..3bbd7d18598e --- /dev/null +++ b/arch/arm64/boot/dts/qcom/sm8750.dtsi @@ -0,0 +1,2907 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/ { + interrupt-parent = <&intc>; + + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "qcom,oryon"; + reg = <0x0 0x0>; + enable-method = "psci"; + next-level-cache = <&l2_0>; + power-domains = <&cpu_pd0>; + power-domain-names = "psci"; + + l2_0: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + }; + }; + + cpu1: cpu@100 { + device_type = "cpu"; + compatible = "qcom,oryon"; + reg = <0x0 0x100>; + enable-method = "psci"; + next-level-cache = <&l2_0>; + power-domains = <&cpu_pd1>; + power-domain-names = "psci"; + }; + + cpu2: cpu@200 { + device_type = "cpu"; + compatible = "qcom,oryon"; + reg = <0x0 0x200>; + enable-method = "psci"; + next-level-cache = <&l2_0>; + power-domains = <&cpu_pd2>; + power-domain-names = "psci"; + }; + + cpu3: cpu@300 { + device_type = "cpu"; + compatible = "qcom,oryon"; + reg = <0x0 0x300>; + enable-method = "psci"; + next-level-cache = <&l2_0>; + power-domains = <&cpu_pd3>; + power-domain-names = "psci"; + }; + + cpu4: cpu@400 { + device_type = "cpu"; + compatible = "qcom,oryon"; + reg = <0x0 0x400>; + enable-method = "psci"; + next-level-cache = <&l2_0>; + power-domains = <&cpu_pd4>; + power-domain-names = "psci"; + }; + + cpu5: cpu@500 { + device_type = "cpu"; + compatible = "qcom,oryon"; + reg = <0x0 0x500>; + enable-method = "psci"; + next-level-cache = <&l2_0>; + power-domains = <&cpu_pd5>; + power-domain-names = "psci"; + }; + + cpu6: cpu@10000 { + device_type = "cpu"; + compatible = "qcom,oryon"; + reg = <0x0 0x10000>; + enable-method = "psci"; + next-level-cache = <&L2_1>; + power-domains = <&cpu_pd6>; + power-domain-names = "psci"; + + L2_1: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + }; + }; + + cpu7: cpu@10100 { + device_type = "cpu"; + compatible = "qcom,oryon"; + reg = <0x0 0x10100>; + enable-method = "psci"; + next-level-cache = <&L2_1>; + power-domains = <&cpu_pd7>; + power-domain-names = "psci"; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + + core4 { + cpu = <&cpu4>; + }; + + core5 { + cpu = <&cpu5>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu6>; + }; + + core1 { + cpu = <&cpu7>; + }; + }; + }; + + idle-states { + entry-method = "psci"; + + cluster0_c4: cpu-sleep-0 { + compatible = "arm,idle-state"; + idle-state-name = "ret"; + arm,psci-suspend-param = <0x00000004>; + entry-latency-us = <93>; + exit-latency-us = <129>; + min-residency-us = <560>; + }; + + cluster1_c4: cpu-sleep-1 { + compatible = "arm,idle-state"; + idle-state-name = "ret"; + arm,psci-suspend-param = <0x00000004>; + entry-latency-us = <172>; + exit-latency-us = <130>; + min-residency-us = <686>; + }; + + }; + + domain-idle-states { + cluster_cl5: cluster-sleep-0 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x01000054>; + entry-latency-us = <2150>; + exit-latency-us = <1983>; + min-residency-us = <9144>; + }; + + domain_ss3: domain-sleep-0 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x0200c354>; + entry-latency-us = <2800>; + exit-latency-us = <4400>; + min-residency-us = <10150>; + }; + }; + }; + + firmware { + scm: scm { + compatible = "qcom,scm-sm8750", "qcom,scm"; + interconnects = <&aggre2_noc MASTER_CRYPTO QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + }; + }; + + clk_virt: interconnect-0 { + compatible = "qcom,sm8750-clk-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + mc_virt: interconnect-1 { + compatible = "qcom,sm8750-mc-virt"; + #interconnect-cells = <2>; + qcom,bcm-voters = <&apps_bcm_voter>; + }; + + memory@a0000000 { + device_type = "memory"; + /* We expect the bootloader to fill in the size */ + reg = <0x0 0xa0000000 0x0 0x0>; + }; + + pmu { + compatible = "arm,armv8-pmuv3"; + interrupts = ; + }; + + psci { + compatible = "arm,psci-1.0"; + method = "smc"; + + cpu_pd0: power-domain-cpu0 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cluster0_c4>; + }; + + cpu_pd1: power-domain-cpu1 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cluster0_c4>; + }; + + cpu_pd2: power-domain-cpu2 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cluster0_c4>; + }; + + cpu_pd3: power-domain-cpu3 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cluster0_c4>; + }; + + cpu_pd4: power-domain-cpu4 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cluster0_c4>; + }; + + cpu_pd5: power-domain-cpu5 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cluster0_c4>; + }; + + cpu_pd6: power-domain-cpu6 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cluster1_c4>; + }; + + cpu_pd7: power-domain-cpu7 { + #power-domain-cells = <0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&cluster1_c4>; + }; + + cluster_pd: power-domain-cluster { + #power-domain-cells = <0>; + domain-idle-states = <&cluster_cl5>; + power-domains = <&system_pd>; + }; + + system_pd: power-domain-system { + #power-domain-cells = <0>; + domain-idle-states = <&domain_ss3>; + }; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + gunyah_hyp_mem: gunyah-hyp@80000000 { + reg = <0x0 0x80000000 0x0 0xe00000>; + no-map; + }; + + cpusys_vm_mem: cpusys-vm-mem@80e00000 { + reg = <0x0 0x80e00000 0x0 0x40000>; + no-map; + }; + + cpucp_mem: cpucp@81200000 { + reg = <0x0 0x81200000 0x0 0x200000>; + no-map; + }; + + xbl_dtlog_mem: xbl-dtlog@81a00000 { + reg = <0x0 0x81a00000 0x0 0x40000>; + no-map; + }; + + aop_image_mem: aop-image@81c00000 { + reg = <0x0 0x81c00000 0x0 0x60000>; + no-map; + }; + + aop_cmd_db_mem: aop-cmd-db@81c60000 { + compatible = "qcom,cmd-db"; + reg = <0x0 0x81c60000 0x0 0x20000>; + no-map; + }; + + /* Merged aop_config, tme_crash_dump, tme_log and uefi_log regions */ + aop_tme_uefi_merged_mem: aop-tme-uefi-merged@81c80000 { + reg = <0x0 0x81c80000 0x0 0x74000>; + no-map; + }; + + /* Secdata region can be reused by apps */ + + smem_mem: smem@81d00000 { + compatible = "qcom,smem"; + reg = <0x0 0x81d00000 0x0 0x200000>; + hwlocks = <&tcsr_mutex 3>; + no-map; + }; + + pdp_ns_shared_mem: pdp-ns-shared@81f00000 { + reg = <0x0 0x81f00000 0x0 0x100000>; + no-map; + }; + + cpucp_scandump_mem: cpucp-scandump@82000000 { + reg = <0x0 0x82000000 0x0 0x380000>; + no-map; + }; + + adsp_mhi_mem: adsp-mhi@82380000 { + reg = <0x0 0x82380000 0x0 0x20000>; + no-map; + }; + + soccp_sdi_mem: soccp-sdi@823a0000 { + reg = <0x0 0x823a0000 0x0 0x40000>; + no-map; + }; + + pmic_minii_dump_mem: pmic-minii-dump@823e0000 { + reg = <0x0 0x823e0000 0x0 0x80000>; + no-map; + }; + + pvmfw_mem: pvmfw@824a0000 { + reg = <0x0 0x824a0000 0x0 0x100000>; + no-map; + }; + + global_sync_mem: global-sync@82600000 { + reg = <0x0 0x82600000 0x0 0x100000>; + no-map; + }; + + tz_stat_mem: tz-stat@82700000 { + reg = <0x0 0x82700000 0x0 0x100000>; + no-map; + }; + + qdss_mem: qdss@82800000 { + reg = <0x0 0x82800000 0x0 0x2000000>; + no-map; + }; + + dsm_partition_1_mem: dsm-partition-1@84a00000 { + reg = <0x0 0x84a00000 0x0 0x4900000>; + no-map; + }; + + dsm_partition_2_mem: dsm-partition-2@89300000 { + reg = <0x0 0x89300000 0x0 0xa80000>; + no-map; + }; + + mpss_mem: mpss@8ba00000 { + reg = <0x0 0x8ba00000 0x0 0xf600000>; + no-map; + }; + + q6_mpss_dtb_mem: q6-mpss-dtb@9b000000 { + reg = <0x0 0x9b000000 0x0 0x80000>; + no-map; + }; + + ipa_fw_mem: ipa-fw@9b080000 { + reg = <0x0 0x9b080000 0x0 0x10000>; + no-map; + }; + + ipa_gsi_mem: ipa-gsi@9b090000 { + reg = <0x0 0x9b090000 0x0 0xa000>; + no-map; + }; + + gpu_micro_code_mem: gpu-micro-code@9b09a000 { + reg = <0x0 0x9b09a000 0x0 0x2000>; + no-map; + }; + + spss_region_mem: spss@9b0a0000 { + reg = <0x0 0x9b0a0000 0x0 0x1e0000>; + no-map; + }; + + /* First part of the "SPU secure shared memory" region */ + spu_tz_shared_mem: spu-tz-shared@9b280000 { + reg = <0x0 0x9b280000 0x0 0x40000>; + no-map; + }; + + /* Second part of the "SPU secure shared memory" region */ + spu_modem_shared_mem: spu-modem-shared@9b2c0000 { + reg = <0x0 0x9b2c0000 0x0 0x40000>; + no-map; + }; + + camera_mem: camera@9b300000 { + reg = <0x0 0x9b300000 0x0 0x800000>; + no-map; + }; + + camera_2_mem: camera-2@9bb00000 { + reg = <0x0 0x9bb00000 0x0 0x800000>; + no-map; + }; + + video_mem: video@9c300000 { + reg = <0x0 0x9c300000 0x0 0x800000>; + no-map; + }; + + cvp_mem: cvp@9cb00000 { + reg = <0x0 0x9cb00000 0x0 0x700000>; + no-map; + }; + + cdsp_mem: cdsp@9d200000 { + reg = <0x0 0x9d200000 0x0 0x1900000>; + no-map; + }; + + q6_cdsp_dtb_mem: q6-cdsp-dtb@9eb00000 { + reg = <0x0 0x9eb00000 0x0 0x80000>; + no-map; + }; + + soccp_mem: soccp@9ec00000 { + reg = <0x0 0x9ec00000 0x0 0x180000>; + no-map; + }; + + q6_adsp_dtb_mem: q6-adsp-dtb@9ed80000 { + reg = <0x0 0x9ed80000 0x0 0x80000>; + no-map; + }; + + adspslpi_mem: adspslpi@9ee00000 { + reg = <0x0 0x9ee00000 0x0 0x3a80000>; + no-map; + }; + + xbl_ramdump_mem: xbl-ramdump@b8000000 { + reg = <0x0 0xb8000000 0x0 0x1c0000>; + no-map; + }; + + hwfence_shbuf: hwfence-shbuf@d4e23000 { + no-map; + reg = <0x0 0xd4e23000 0x0 0x2dd000>; + }; + + /* Merged tz_reserved, xbl_sc, and qtee regions */ + tz_merged_mem: tz-merged@d8000000 { + reg = <0x0 0xd8000000 0x0 0x600000>; + no-map; + }; + + trust_ui_vm_mem: trust-ui-vm@f3800000 { + reg = <0x0 0xf3800000 0x0 0x4400000>; + no-map; + }; + + oem_vm_mem: oem-vm@f7c00000 { + reg = <0x0 0xf7c00000 0x0 0x4c00000>; + no-map; + }; + + llcc_lpi_mem: llcc-lpi@ff800000 { + reg = <0x0 0xff800000 0x0 0x800000>; + no-map; + }; + }; + + soc: soc@0 { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <2>; + dma-ranges = <0 0 0 0 0x10 0>; + ranges = <0 0 0 0 0x10 0>; + + gcc: clock-controller@100000 { + compatible = "qcom,sm8750-gcc"; + reg = <0x0 0x00100000 0x0 0x1f4200>; + + clocks = <&bi_tcxo_div2>, + <0>, + <&sleep_clk>, + <0>, + <0>, + <0>, + <0>, + <0>; + + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + + gpi_dma2: dma-controller@800000 { + compatible = "qcom,sm8750-gpi-dma", "qcom,sm6350-gpi-dma"; + reg = <0x0 0x00800000 0x0 0x60000>; + + interrupts = , + , + , + , + , + , + , + , + , + , + , + ; + + dma-channels = <12>; + dma-channel-mask = <0x1e>; + #dma-cells = <3>; + + iommus = <&apps_smmu 0x436 0x0>; + + status = "disabled"; + }; + + qupv3_2: geniqup@8c0000 { + compatible = "qcom,geni-se-qup"; + reg = <0x0 0x008c0000 0x0 0x2000>; + + clocks = <&gcc GCC_QUPV3_WRAP_2_M_AHB_CLK>, + <&gcc GCC_QUPV3_WRAP_2_S_AHB_CLK>; + clock-names = "m-ahb", + "s-ahb"; + + iommus = <&apps_smmu 0x423 0x0>; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + i2c8: i2c@880000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00880000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S0_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 0 QCOM_GPI_I2C>, + <&gpi_dma2 1 0 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c8_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi8: spi@880000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00880000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S0_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 0 QCOM_GPI_SPI>, + <&gpi_dma2 1 0 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi8_data_clk>, <&qup_spi8_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c9: i2c@884000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00884000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S1_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 1 QCOM_GPI_I2C>, + <&gpi_dma2 1 1 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c9_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi9: spi@884000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00884000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S1_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 1 QCOM_GPI_SPI>, + <&gpi_dma2 1 1 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi9_data_clk>, <&qup_spi9_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c10: i2c@888000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00888000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S2_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 2 QCOM_GPI_I2C>, + <&gpi_dma2 1 2 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c10_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi10: spi@888000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00888000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S2_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 2 QCOM_GPI_SPI>, + <&gpi_dma2 1 2 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi10_data_clk>, <&qup_spi10_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c11: i2c@88c000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x0088c000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S3_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 3 QCOM_GPI_I2C>, + <&gpi_dma2 1 3 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c11_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi11: spi@88c000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x0088c000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S3_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 3 QCOM_GPI_SPI>, + <&gpi_dma2 1 3 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi11_data_clk>, <&qup_spi11_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c12: i2c@890000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00890000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S4_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 4 QCOM_GPI_I2C>, + <&gpi_dma2 1 4 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c12_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi12: spi@890000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00890000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S4_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 4 QCOM_GPI_SPI>, + <&gpi_dma2 1 4 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi12_data_clk>, <&qup_spi12_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c13: i2c@894000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00894000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S5_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 5 QCOM_GPI_I2C>, + <&gpi_dma2 1 5 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c13_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi13: spi@894000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00894000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S5_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 5 QCOM_GPI_SPI>, + <&gpi_dma2 1 5 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi13_data_clk>, <&qup_spi13_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + uart14: serial@898000 { + compatible = "qcom,geni-uart"; + reg = <0x0 0x00898000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S5_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&qup_uart14_default>; + pinctrl-names = "default"; + + status = "disabled"; + }; + + i2c15: i2c@89c000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x0089c000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S7_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 7 QCOM_GPI_I2C>, + <&gpi_dma2 1 7 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c15_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi15: spi@89c000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x0089c000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP2_S7_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>, + <&aggre2_noc MASTER_QUP_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma2 0 7 QCOM_GPI_SPI>, + <&gpi_dma2 1 7 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi15_data_clk>, <&qup_spi15_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + }; + + i2c_master_hub_0: geniqup@9c0000 { + compatible = "qcom,geni-se-i2c-master-hub"; + reg = <0x0 0x009c0000 0x0 0x2000>; + + clocks = <&gcc GCC_QUPV3_I2C_S_AHB_CLK>; + clock-names = "s-ahb"; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + i2c_hub_0: i2c@980000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x00980000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S0_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c0_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c_hub_1: i2c@984000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x00984000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S1_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c1_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c_hub_2: i2c@988000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x00988000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S2_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c2_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c_hub_3: i2c@98c000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x0098c000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S3_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c3_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c_hub_4: i2c@990000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x00990000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S4_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c4_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c_hub_5: i2c@994000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x00994000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S5_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c5_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c_hub_6: i2c@998000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x00998000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S6_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c6_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c_hub_7: i2c@99c000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x0099c000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S7_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c7_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c_hub_8: i2c@9a0000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x009a0000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S8_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c8_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c_hub_9: i2c@9a4000 { + compatible = "qcom,geni-i2c-master-hub"; + reg = <0x0 0x009a4000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_I2C_S9_CLK>, + <&gcc GCC_QUPV3_I2C_CORE_CLK>; + clock-names = "se", + "core"; + + interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_I2C QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + pinctrl-0 = <&hub_i2c9_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + }; + + gpi_dma1: dma-controller@a00000 { + compatible = "qcom,sm8750-gpi-dma", "qcom,sm6350-gpi-dma"; + reg = <0x0 0x00a00000 0x0 0x60000>; + + interrupts = , + , + , + , + , + , + , + , + , + , + , + ; + + dma-channels = <12>; + dma-channel-mask = <0x1e>; + #dma-cells = <3>; + + iommus = <&apps_smmu 0xb6 0x0>; + + status = "disabled"; + }; + + qupv3_1: geniqup@ac0000 { + compatible = "qcom,geni-se-qup"; + reg = <0x0 0x00ac0000 0x0 0x2000>; + + clocks = <&gcc GCC_QUPV3_WRAP_1_M_AHB_CLK>, + <&gcc GCC_QUPV3_WRAP_1_S_AHB_CLK>; + clock-names = "m-ahb", + "s-ahb"; + + iommus = <&apps_smmu 0xa3 0x0>; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + status = "disabled"; + + i2c0: i2c@a80000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a80000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 0 QCOM_GPI_I2C>, + <&gpi_dma1 1 0 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c0_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi0: spi@a80000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a80000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S0_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 0 QCOM_GPI_SPI>, + <&gpi_dma1 1 0 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi0_data_clk>, <&qup_spi0_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c1: i2c@a84000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a84000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 1 QCOM_GPI_I2C>, + <&gpi_dma1 1 1 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c1_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi1: spi@a84000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a84000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S1_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 1 QCOM_GPI_SPI>, + <&gpi_dma1 1 1 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi1_data_clk>, <&qup_spi1_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c2: i2c@a88000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a88000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 2 QCOM_GPI_I2C>, + <&gpi_dma1 1 2 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c2_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi2: spi@a88000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a88000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S2_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 2 QCOM_GPI_SPI>, + <&gpi_dma1 1 2 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi2_data_clk>, <&qup_spi2_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c3: i2c@a8c000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a8c000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 3 QCOM_GPI_I2C>, + <&gpi_dma1 1 3 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c3_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi3: spi@a8c000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a8c000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S3_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 3 QCOM_GPI_SPI>, + <&gpi_dma1 1 3 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi3_data_clk>, <&qup_spi3_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c4: i2c@a90000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a90000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S4_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 4 QCOM_GPI_I2C>, + <&gpi_dma1 1 4 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c4_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi4: spi@a90000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a90000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S4_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 4 QCOM_GPI_SPI>, + <&gpi_dma1 1 4 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi4_data_clk>, <&qup_spi4_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c5: i2c@a94000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a94000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S5_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 5 QCOM_GPI_I2C>, + <&gpi_dma1 1 5 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c5_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi5: spi@a94000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a94000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S5_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 5 QCOM_GPI_SPI>, + <&gpi_dma1 1 5 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi5_data_clk>, <&qup_spi5_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + i2c6: i2c@a98000 { + compatible = "qcom,geni-i2c"; + reg = <0x0 0x00a98000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S6_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 6 QCOM_GPI_I2C>, + <&gpi_dma1 1 6 QCOM_GPI_I2C>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_i2c6_data_clk>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + spi6: spi@a98000 { + compatible = "qcom,geni-spi"; + reg = <0x0 0x00a98000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S6_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>, + <&aggre1_noc MASTER_QUP_1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; + + dmas = <&gpi_dma1 0 6 QCOM_GPI_SPI>, + <&gpi_dma1 1 6 QCOM_GPI_SPI>; + dma-names = "tx", + "rx"; + + pinctrl-0 = <&qup_spi6_data_clk>, <&qup_spi6_cs>; + pinctrl-names = "default"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + + uart7: serial@a9c000 { + compatible = "qcom,geni-debug-uart"; + reg = <0x0 0x00a9c000 0x0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S7_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + + pinctrl-0 = <&qup_uart7_default>; + pinctrl-names = "default"; + + status = "disabled"; + }; + }; + + cnoc_main: interconnect@1500000 { + compatible = "qcom,sm8750-cnoc-main"; + reg = <0x0 0x01500000 0x0 0x16080>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + }; + + config_noc: interconnect@1600000 { + compatible = "qcom,sm8750-config-noc"; + reg = <0x0 0x01600000 0x0 0x6200>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + }; + + system_noc: interconnect@1680000 { + compatible = "qcom,sm8750-system-noc"; + reg = <0x0 0x01680000 0x0 0x1d080>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + }; + + pcie_noc: interconnect@16c0000 { + compatible = "qcom,sm8750-pcie-anoc"; + reg = <0x0 0x016c0000 0x0 0x11400>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + clocks = <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>, + <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>; + + }; + + aggre1_noc: interconnect@16e0000 { + compatible = "qcom,sm8750-aggre1-noc"; + reg = <0x0 0x016e0000 0x0 0x16400>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + clocks = <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>, + <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>; + + }; + + aggre2_noc: interconnect@1700000 { + compatible = "qcom,sm8750-aggre2-noc"; + reg = <0x0 0x01700000 0x0 0x1f400>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + clocks = <&rpmhcc RPMH_IPA_CLK>; + }; + + mmss_noc: interconnect@1780000 { + compatible = "qcom,sm8750-mmss-noc"; + reg = <0x0 0x01780000 0x0 0x5b800>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + }; + + tcsr_mutex: hwlock@1f40000 { + compatible = "qcom,tcsr-mutex"; + reg = <0x0 0x01f40000 0x0 0x20000>; + #hwlock-cells = <1>; + }; + + lpass_ag_noc: interconnect@7e40000 { + compatible = "qcom,sm8750-lpass-ag-noc"; + reg = <0x0 0x07e40000 0x0 0xe080>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + }; + + lpass_lpiaon_noc: interconnect@7400000 { + compatible = "qcom,sm8750-lpass-lpiaon-noc"; + reg = <0x0 0x07400000 0x0 0x19080>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + }; + + lpass_lpicx_noc: interconnect@7420000 { + compatible = "qcom,sm8750-lpass-lpicx-noc"; + reg = <0x0 0x07420000 0x0 0x44080>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + }; + + pdc: interrupt-controller@b220000 { + compatible = "qcom,sm8750-pdc", "qcom,pdc"; + reg = <0x0 0x0b220000 0x0 0x10000>, <0x0 0x164400f0 0x0 0x64>; + + qcom,pdc-ranges = <0 745 51>, <51 527 47>, + <98 609 32>, <130 717 12>, + <142 251 5>, <147 796 16>; + #interrupt-cells = <2>; + interrupt-parent = <&intc>; + interrupt-controller; + }; + + spmi_bus: spmi@c400000 { + compatible = "qcom,spmi-pmic-arb"; + reg = <0x0 0x0c400000 0x0 0x3000>, + <0x0 0x0c500000 0x0 0x400000>, + <0x0 0x0c440000 0x0 0x80000>, + <0x0 0x0c4c0000 0x0 0x10000>, + <0x0 0x0c42d000 0x0 0x4000>; + reg-names = "core", + "chnls", + "obsrvr", + "intr", + "cnfg"; + + interrupts-extended = <&pdc 1 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "periph_irq"; + + qcom,ee = <0>; + qcom,channel = <0>; + qcom,bus-id = <0>; + + interrupt-controller; + #interrupt-cells = <4>; + + #address-cells = <2>; + #size-cells = <0>; + }; + + tlmm: pinctrl@f100000 { + compatible = "qcom,sm8750-tlmm"; + reg = <0x0 0x0f100000 0x0 0x102000>; + + interrupts = ; + + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + gpio-ranges = <&tlmm 0 0 216>; + wakeup-parent = <&pdc>; + + hub_i2c0_data_clk: hub-i2c0-data-clk-state { + /* SDA, SCL */ + pins = "gpio64", "gpio65"; + function = "i2chub0_se0"; + drive-strength = <2>; + bias-pull-up; + }; + + hub_i2c1_data_clk: hub-i2c1-data-clk-state { + /* SDA, SCL */ + pins = "gpio66", "gpio67"; + function = "i2chub0_se1"; + drive-strength = <2>; + bias-pull-up; + }; + + hub_i2c2_data_clk: hub-i2c2-data-clk-state { + /* SDA, SCL */ + pins = "gpio68", "gpio69"; + function = "i2chub0_se2"; + drive-strength = <2>; + bias-pull-up; + }; + + hub_i2c3_data_clk: hub-i2c3-data-clk-state { + /* SDA, SCL */ + pins = "gpio70", "gpio71"; + function = "i2chub0_se3"; + drive-strength = <2>; + bias-pull-up; + }; + + hub_i2c4_data_clk: hub-i2c4-data-clk-state { + /* SDA, SCL */ + pins = "gpio72", "gpio73"; + function = "i2chub0_se4"; + drive-strength = <2>; + bias-pull-up; + }; + + hub_i2c5_data_clk: hub-i2c5-data-clk-state { + /* SDA, SCL */ + pins = "gpio74", "gpio75"; + function = "i2chub0_se5"; + drive-strength = <2>; + bias-pull-up; + }; + + hub_i2c6_data_clk: hub-i2c6-data-clk-state { + /* SDA, SCL */ + pins = "gpio76", "gpio77"; + function = "i2chub0_se6"; + drive-strength = <2>; + bias-pull-up; + }; + + hub_i2c7_data_clk: hub-i2c7-data-clk-state { + /* SDA, SCL */ + pins = "gpio82", "gpio83"; + function = "i2chub0_se7"; + drive-strength = <2>; + bias-pull-up; + }; + + hub_i2c8_data_clk: hub-i2c8-data-clk-state { + /* SDA, SCL */ + pins = "gpio206", "gpio207"; + function = "i2chub0_se8"; + drive-strength = <2>; + bias-pull-up; + }; + + hub_i2c9_data_clk: hub-i2c9-data-clk-state { + /* SDA, SCL */ + pins = "gpio80", "gpio81"; + function = "i2chub0_se9"; + drive-strength = <2>; + bias-pull-up; + }; + + pcie0_default_state: pcie0-default-state { + perst-pins { + pins = "gpio102"; + function = "gpio"; + drive-strength = <2>; + bias-pull-down; + }; + + clkreq-pins { + pins = "gpio103"; + function = "pcie0_clk_req_n"; + drive-strength = <2>; + bias-pull-up; + }; + + wake-pins { + pins = "gpio104"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + qup_i2c0_data_clk: qup-i2c0-data-clk-state { + /* SDA, SCL */ + pins = "gpio32", "gpio33"; + function = "qup1_se0"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c1_data_clk: qup-i2c1-data-clk-state { + /* SDA, SCL */ + pins = "gpio36", "gpio37"; + function = "qup1_se1"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c2_data_clk: qup-i2c2-data-clk-state { + /* SDA, SCL */ + pins = "gpio40", "gpio41"; + function = "qup1_se2"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c3_data_clk: qup-i2c3-data-clk-state { + /* SDA, SCL */ + pins = "gpio44", "gpio45"; + function = "qup1_se3"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c4_data_clk: qup-i2c4-data-clk-state { + /* SDA, SCL */ + pins = "gpio48", "gpio49"; + function = "qup1_se4"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c5_data_clk: qup-i2c5-data-clk-state { + /* SDA, SCL */ + pins = "gpio52", "gpio53"; + function = "qup1_se5"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c6_data_clk: qup-i2c6-data-clk-state { + /* SDA, SCL */ + pins = "gpio56", "gpio57"; + function = "qup1_se6"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c8_data_clk: qup-i2c8-data-clk-state { + /* SDA, SCL */ + pins = "gpio0", "gpio1"; + function = "qup2_se0"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c9_data_clk: qup-i2c9-data-clk-state { + /* SDA, SCL */ + pins = "gpio4", "gpio5"; + function = "qup2_se1"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c10_data_clk: qup-i2c10-data-clk-state { + /* SDA, SCL */ + pins = "gpio8", "gpio9"; + function = "qup2_se2"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c11_data_clk: qup-i2c11-data-clk-state { + /* SDA, SCL */ + pins = "gpio12", "gpio13"; + function = "qup2_se3"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c12_data_clk: qup-i2c12-data-clk-state { + /* SDA, SCL */ + pins = "gpio16", "gpio17"; + function = "qup2_se4"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c13_data_clk: qup-i2c13-data-clk-state { + /* SDA, SCL */ + pins = "gpio20", "gpio21"; + function = "qup2_se5"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_i2c15_data_clk: qup-i2c15-data-clk-state { + /* SDA, SCL */ + pins = "gpio28", "gpio29"; + function = "qup2_se7"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_spi0_cs: qup-spi0-cs-state { + pins = "gpio35"; + function = "qup1_se0"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi0_data_clk: qup-spi0-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio32", "gpio33", "gpio34"; + function = "qup1_se0"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi1_cs: qup-spi1-cs-state { + pins = "gpio39"; + function = "qup1_se1"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi1_data_clk: qup-spi1-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio36", "gpio37", "gpio38"; + function = "qup1_se1"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi2_cs: qup-spi2-cs-state { + pins = "gpio43"; + function = "qup1_se2"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi2_data_clk: qup-spi2-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio40", "gpio41", "gpio42"; + function = "qup1_se2"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi3_cs: qup-spi3-cs-state { + pins = "gpio47"; + function = "qup1_se3"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi3_data_clk: qup-spi3-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio44", "gpio45", "gpio46"; + function = "qup1_se3"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi4_cs: qup-spi4-cs-state { + pins = "gpio51"; + function = "qup1_se4"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi4_data_clk: qup-spi4-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio48", "gpio49", "gpio50"; + function = "qup1_se4"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi5_cs: qup-spi5-cs-state { + pins = "gpio55"; + function = "qup1_se5"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi5_data_clk: qup-spi5-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio52", "gpio53", "gpio54"; + function = "qup1_se5"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi6_cs: qup-spi6-cs-state { + pins = "gpio59"; + function = "qup1_se6"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi6_data_clk: qup-spi6-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio56", "gpio57", "gpio58"; + function = "qup1_se6"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi8_cs: qup-spi8-cs-state { + pins = "gpio3"; + function = "qup2_se0"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi8_data_clk: qup-spi8-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio0", "gpio1", "gpio2"; + function = "qup2_se0"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi9_cs: qup-spi9-cs-state { + pins = "gpio7"; + function = "qup2_se1"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi9_data_clk: qup-spi9-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio4", "gpio5", "gpio6"; + function = "qup2_se1"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi10_cs: qup-spi10-cs-state { + pins = "gpio11"; + function = "qup2_se2"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi10_data_clk: qup-spi10-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio8", "gpio9", "gpio10"; + function = "qup2_se2"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi11_cs: qup-spi11-cs-state { + pins = "gpio15"; + function = "qup2_se3"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi11_data_clk: qup-spi11-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio12", "gpio13", "gpio14"; + function = "qup2_se3"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi12_cs: qup-spi12-cs-state { + pins = "gpio19"; + function = "qup2_se4"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi12_data_clk: qup-spi12-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio16", "gpio17", "gpio18"; + function = "qup2_se4"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi13_cs: qup-spi13-cs-state { + pins = "gpio23"; + function = "qup2_se5"; + drive-strength = <6>; + bias-pull-up; + }; + + qup_spi13_data_clk: qup-spi13-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio20", "gpio21", "gpio22"; + function = "qup2_se5"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi15_cs: qup-spi15-cs-state { + pins = "gpio31"; + function = "qup2_se7"; + drive-strength = <6>; + bias-disable; + }; + + qup_spi15_data_clk: qup-spi15-data-clk-state { + /* MISO, MOSI, CLK */ + pins = "gpio28", "gpio29", "gpio30"; + function = "qup2_se7"; + drive-strength = <6>; + bias-disable; + }; + + qup_uart7_default: qup-uart7-default-state { + /* TX, RX */ + pins = "gpio62", "gpio63"; + function = "qup1_se7"; + drive-strength = <2>; + bias-disable; + }; + + qup_uart14_default: qup-uart14-default-state { + /* TX, RX */ + pins = "gpio26", "gpio27"; + function = "qup2_se6"; + drive-strength = <2>; + bias-pull-up; + }; + + qup_uart14_cts_rts: qup-uart14-cts-rts-state { + /* CTS, RTS */ + pins = "gpio24", "gpio25"; + function = "qup2_se6"; + drive-strength = <2>; + bias-pull-down; + }; + + sdc2_sleep: sdc2-sleep-state { + clk-pins { + pins = "sdc2_clk"; + drive-strength = <2>; + bias-disable; + }; + + cmd-pins { + pins = "sdc2_cmd"; + drive-strength = <2>; + bias-pull-up; + }; + + data-pins { + pins = "sdc2_data"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + sdc2_default: sdc2-default-state { + clk-pins { + pins = "sdc2_clk"; + drive-strength = <16>; + bias-disable; + }; + + cmd-pins { + pins = "sdc2_cmd"; + drive-strength = <10>; + bias-pull-up; + }; + + data-pins { + pins = "sdc2_data"; + drive-strength = <10>; + bias-pull-up; + }; + }; + }; + + tcsrcc: clock-controller@f204008 { + compatible = "qcom,sm8750-tcsr", "syscon"; + reg = <0x0 0x0f204008 0x0 0x3004>; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + + #clock-cells = <1>; + #reset-cells = <1>; + }; + + apps_smmu: iommu@15000000 { + compatible = "qcom,sm8750-smmu-500", "qcom,smmu-500", "arm,mmu-500"; + reg = <0x0 0x15000000 0x0 0x100000>; + + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + + #iommu-cells = <2>; + #global-interrupts = <1>; + + dma-coherent; + }; + + intc: interrupt-controller@16000000 { + compatible = "arm,gic-v3"; + reg = <0x0 0x16000000 0x0 0x10000>, + <0x0 0x16080000 0x0 0x200000>; + + interrupts = ; + + #interrupt-cells = <3>; + interrupt-controller; + + #redistributor-regions = <1>; + redistributor-stride = <0x0 0x40000>; + + #address-cells = <2>; + #size-cells = <2>; + ranges; + + gic_its: msi-controller@16040000 { + compatible = "arm,gic-v3-its"; + reg = <0x0 0x16040000 0x0 0x20000>; + + msi-controller; + #msi-cells = <1>; + }; + }; + + apps_rsc: rsc@16500000 { + compatible = "qcom,rpmh-rsc"; + reg = <0x0 0x16500000 0x0 0x10000>, + <0x0 0x16510000 0x0 0x10000>, + <0x0 0x16520000 0x0 0x10000>; + reg-names = "drv-0", + "drv-1", + "drv-2"; + + interrupts = , + , + ; + qcom,tcs-offset = <0xd00>; + qcom,drv-id = <2>; + qcom,tcs-config = , , + , ; + + label = "apps_rsc"; + + power-domains = <&system_pd>; + + apps_bcm_voter: bcm-voter { + compatible = "qcom,bcm-voter"; + }; + + rpmhcc: clock-controller { + compatible = "qcom,sm8750-rpmh-clk"; + + clocks = <&xo_board>; + clock-names = "xo"; + + #clock-cells = <1>; + }; + + rpmhpd: power-controller { + compatible = "qcom,sm8750-rpmhpd"; + + operating-points-v2 = <&rpmhpd_opp_table>; + + #power-domain-cells = <1>; + + rpmhpd_opp_table: opp-table { + compatible = "operating-points-v2"; + + rpmhpd_opp_ret: opp-16 { + opp-level = ; + }; + + rpmhpd_opp_min_svs: opp-48 { + opp-level = ; + }; + + rpmhpd_opp_low_svs_d3: opp-50 { + opp-level = ; + }; + + rpmhpd_opp_low_svs_d2: opp-52 { + opp-level = ; + }; + + rpmhpd_opp_low_svs_d1: opp-56 { + opp-level = ; + }; + + rpmhpd_opp_low_svs_d0: opp-60 { + opp-level = ; + }; + + rpmhpd_opp_low_svs: opp-64 { + opp-level = ; + }; + + rpmhpd_opp_low_svs_l1: opp-80 { + opp-level = ; + }; + + rpmhpd_opp_svs: opp-128 { + opp-level = ; + }; + + rpmhpd_opp_svs_l0: opp-144 { + opp-level = ; + }; + + rpmhpd_opp_svs_l1: opp-192 { + opp-level = ; + }; + + rpmhpd_opp_svs_l2: opp-224 { + opp-level = ; + }; + + rpmhpd_opp_nom: opp-256 { + opp-level = ; + }; + + rpmhpd_opp_nom_l1: opp-320 { + opp-level = ; + }; + + rpmhpd_opp_nom_l2: opp-336 { + opp-level = ; + }; + + rpmhpd_opp_turbo: opp-384 { + opp-level = ; + }; + + rpmhpd_opp_turbo_l1: opp-416 { + opp-level = ; + }; + + rpmhpd_opp_turbo_l2: opp-432 { + opp-level = ; + }; + + rpmhpd_opp_turbo_l3: opp-448 { + opp-level = ; + }; + + rpmhpd_opp_turbo_l4: opp-452 { + opp-level = ; + }; + + rpmhpd_opp_super_turbo_no_cpr: opp-480 { + opp-level = + ; + }; + }; + }; + }; + + timer@16800000 { + compatible = "arm,armv7-timer-mem"; + reg = <0x0 0x16800000 0x0 0x1000>; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0 0x20000000>; + + frame@16801000 { + reg = <0x0 0x16801000 0x1000>, + <0x0 0x16802000 0x1000>; + + interrupts = , + ; + + frame-number = <0>; + }; + + frame@16803000 { + reg = <0x0 0x16803000 0x1000>; + + interrupts = ; + + frame-number = <1>; + + status = "disabled"; + }; + + frame@16805000 { + reg = <0x0 0x16805000 0x1000>; + + interrupts = ; + + frame-number = <2>; + + status = "disabled"; + }; + + frame@16807000 { + reg = <0x0 0x16807000 0x1000>; + + interrupts = ; + + frame-number = <3>; + + status = "disabled"; + }; + + frame@16809000 { + reg = <0x0 0x16809000 0x1000>; + + interrupts = ; + + frame-number = <4>; + + status = "disabled"; + }; + + frame@1680b000 { + reg = <0x0 0x1680b000 0x1000>; + + interrupts = ; + + frame-number = <5>; + + status = "disabled"; + }; + + frame@1680d000 { + reg = <0x0 0x1680d000 0x1000>; + + interrupts = ; + + frame-number = <6>; + + status = "disabled"; + }; + }; + + gem_noc: interconnect@24100000 { + compatible = "qcom,sm8750-gem-noc"; + reg = <0x0 0x24100000 0x0 0x14b080>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + }; + + nsp_noc: interconnect@320c0000 { + compatible = "qcom,sm8750-nsp-noc"; + reg = <0x0 0x320c0000 0x0 0x13080>; + qcom,bcm-voters = <&apps_bcm_voter>; + #interconnect-cells = <2>; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + + interrupts = , + , + , + ; + }; +}; diff --git a/arch/arm64/boot/dts/qcom/x1e001de-devkit.dts b/arch/arm64/boot/dts/qcom/x1e001de-devkit.dts new file mode 100644 index 000000000000..5e3970b26e2f --- /dev/null +++ b/arch/arm64/boot/dts/qcom/x1e001de-devkit.dts @@ -0,0 +1,1371 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +/dts-v1/; + +#include +#include + +#include "x1e80100.dtsi" +#include "x1e80100-pmics.dtsi" + +/ { + model = "Qualcomm Technologies, Inc. X1E001DE Snapdragon Devkit for Windows"; + compatible = "qcom,x1e001de-devkit", "qcom,x1e001de", "qcom,x1e80100"; + + aliases { + serial0 = &uart21; + }; + + wcd938x: audio-codec { + compatible = "qcom,wcd9385-codec"; + + pinctrl-names = "default"; + pinctrl-0 = <&wcd_default>; + + qcom,micbias1-microvolt = <1800000>; + qcom,micbias2-microvolt = <1800000>; + qcom,micbias3-microvolt = <1800000>; + qcom,micbias4-microvolt = <1800000>; + qcom,mbhc-buttons-vthreshold-microvolt = <75000 150000 237000 500000 500000 500000 500000 500000>; + qcom,mbhc-headset-vthreshold-microvolt = <1700000>; + qcom,mbhc-headphone-vthreshold-microvolt = <50000>; + qcom,rx-device = <&wcd_rx>; + qcom,tx-device = <&wcd_tx>; + + reset-gpios = <&tlmm 191 GPIO_ACTIVE_LOW>; + + vdd-buck-supply = <&vreg_l15b_1p8>; + vdd-rxtx-supply = <&vreg_l15b_1p8>; + vdd-io-supply = <&vreg_l15b_1p8>; + vdd-mic-bias-supply = <&vreg_bob1>; + + #sound-dai-cells = <1>; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + pmic-glink { + compatible = "qcom,x1e80100-pmic-glink", + "qcom,sm8550-pmic-glink", + "qcom,pmic-glink"; + #address-cells = <1>; + #size-cells = <0>; + orientation-gpios = <&tlmm 121 GPIO_ACTIVE_HIGH>, + <&tlmm 123 GPIO_ACTIVE_HIGH>, + <&tlmm 125 GPIO_ACTIVE_HIGH>; + + /* Back panel port closer to the RJ45 connector */ + connector@0 { + compatible = "usb-c-connector"; + reg = <0>; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + pmic_glink_ss0_hs_in: endpoint { + remote-endpoint = <&usb_1_ss0_dwc3_hs>; + }; + }; + + port@1 { + reg = <1>; + + pmic_glink_ss0_ss_in: endpoint { + remote-endpoint = <&retimer_ss0_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_ss0_con_sbu_in: endpoint { + remote-endpoint = <&retimer_ss0_con_sbu_out>; + }; + }; + }; + }; + + /* Back panel port closer to the audio jack */ + connector@1 { + compatible = "usb-c-connector"; + reg = <1>; + power-role = "dual"; + data-role = "host"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + pmic_glink_ss1_hs_in: endpoint { + remote-endpoint = <&usb_1_ss1_dwc3_hs>; + }; + }; + + port@1 { + reg = <1>; + + pmic_glink_ss1_ss_in: endpoint { + remote-endpoint = <&retimer_ss1_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_ss1_con_sbu_in: endpoint { + remote-endpoint = <&retimer_ss1_con_sbu_out>; + }; + }; + }; + }; + + /* Front panel port */ + connector@2 { + compatible = "usb-c-connector"; + reg = <2>; + power-role = "dual"; + data-role = "host"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + pmic_glink_ss2_hs_in: endpoint { + remote-endpoint = <&usb_1_ss2_dwc3_hs>; + }; + }; + + port@1 { + reg = <1>; + + pmic_glink_ss2_ss_in: endpoint { + remote-endpoint = <&retimer_ss2_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_ss2_con_sbu_in: endpoint { + remote-endpoint = <&retimer_ss2_con_sbu_out>; + }; + }; + }; + }; + }; + + reserved-memory { + linux,cma { + compatible = "shared-dma-pool"; + size = <0x0 0x8000000>; + reusable; + linux,cma-default; + }; + }; + + sound { + compatible = "qcom,x1e80100-sndcard"; + model = "X1E001DE-DEVKIT"; + audio-routing = "IN1_HPHL", "HPHL_OUT", + "IN2_HPHR", "HPHR_OUT", + "AMIC2", "MIC BIAS2", + "TX SWR_INPUT1", "ADC2_OUTPUT"; + + wcd-playback-dai-link { + link-name = "WCD Playback"; + + cpu { + sound-dai = <&q6apmbedai RX_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&wcd938x 0>, <&swr1 0>, <&lpass_rxmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wcd-capture-dai-link { + link-name = "WCD Capture"; + + cpu { + sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>; + }; + + codec { + sound-dai = <&wcd938x 1>, <&swr2 1>, <&lpass_txmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + }; + + vreg_nvme: regulator-nvme { + compatible = "regulator-fixed"; + + regulator-name = "VREG_NVME_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 18 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-names = "default"; + pinctrl-0 = <&nvme_reg_en>; + + regulator-boot-on; + }; + + vreg_rtmr0_1p15: regulator-rtmr0-1p15 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_1P15"; + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; + + gpio = <&pmc8380_5_gpios 8 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&usb0_pwr_1p15_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr0_1p8: regulator-rtmr0-1p8 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_1P8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + gpio = <&pm8550ve_9_gpios 8 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&usb0_1p8_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr0_3p3: regulator-rtmr0-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&pm8550_gpios 11 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&usb0_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_1p15: regulator-rtmr1-1p15 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_1P15"; + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; + + gpio = <&tlmm 188 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr1_1p15_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_1p8: regulator-rtmr1-1p8 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_1P8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + gpio = <&tlmm 175 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr1_1p8_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_3p3: regulator-rtmr1-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 186 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr1_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr2_1p15: regulator-rtmr2-1p15 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR2_1P15"; + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; + + gpio = <&tlmm 189 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr2_1p15_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr2_1p8: regulator-rtmr2-1p8 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR2_1P8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + gpio = <&tlmm 126 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr2_1p8_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr2_3p3: regulator-rtmr2-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR2_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 187 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr2_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vph_pwr: regulator-vph-pwr { + compatible = "regulator-fixed"; + + regulator-name = "vph_pwr"; + regulator-min-microvolt = <3700000>; + regulator-max-microvolt = <3700000>; + + regulator-always-on; + regulator-boot-on; + }; + + vreg_wwan: regulator-wwan { + compatible = "regulator-fixed"; + + regulator-name = "SDX_VPH_PWR"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 221 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&wwan_sw_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; +}; + +&apps_rsc { + regulators-0 { + compatible = "qcom,pm8550-rpmh-regulators"; + qcom,pmic-id = "b"; + + vdd-bob1-supply = <&vph_pwr>; + vdd-bob2-supply = <&vph_pwr>; + vdd-l1-l4-l10-supply = <&vreg_s4c_1p8>; + vdd-l2-l13-l14-supply = <&vreg_bob1>; + vdd-l5-l16-supply = <&vreg_bob1>; + vdd-l6-l7-supply = <&vreg_bob2>; + vdd-l8-l9-supply = <&vreg_bob1>; + vdd-l12-supply = <&vreg_s5j_1p2>; + vdd-l15-supply = <&vreg_s4c_1p8>; + vdd-l17-supply = <&vreg_bob2>; + + vreg_bob1: bob1 { + regulator-name = "vreg_bob1"; + regulator-min-microvolt = <3008000>; + regulator-max-microvolt = <3960000>; + regulator-initial-mode = ; + }; + + vreg_bob2: bob2 { + regulator-name = "vreg_bob2"; + regulator-min-microvolt = <2504000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + }; + + vreg_l1b_1p8: ldo1 { + regulator-name = "vreg_l1b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l2b_3p0: ldo2 { + regulator-name = "vreg_l2b_3p0"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3100000>; + regulator-initial-mode = ; + }; + + vreg_l4b_1p8: ldo4 { + regulator-name = "vreg_l4b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l5b_3p0: ldo5 { + regulator-name = "vreg_l5b_3p0"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3000000>; + regulator-initial-mode = ; + }; + + vreg_l6b_1p8: ldo6 { + regulator-name = "vreg_l6b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2960000>; + regulator-initial-mode = ; + }; + + vreg_l7b_2p8: ldo7 { + regulator-name = "vreg_l7b_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l8b_3p0: ldo8 { + regulator-name = "vreg_l8b_3p0"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + }; + + vreg_l9b_2p9: ldo9 { + regulator-name = "vreg_l9b_2p9"; + regulator-min-microvolt = <2960000>; + regulator-max-microvolt = <2960000>; + regulator-initial-mode = ; + }; + + vreg_l10b_1p8: ldo10 { + regulator-name = "vreg_l10b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l12b_1p2: ldo12 { + regulator-name = "vreg_l12b_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l13b_3p0: ldo13 { + regulator-name = "vreg_l13b_3p0"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3100000>; + regulator-initial-mode = ; + }; + + vreg_l14b_3p0: ldo14 { + regulator-name = "vreg_l14b_3p0"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + }; + + vreg_l15b_1p8: ldo15 { + regulator-name = "vreg_l15b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l16b_2p9: ldo16 { + regulator-name = "vreg_l16b_2p9"; + regulator-min-microvolt = <2912000>; + regulator-max-microvolt = <2912000>; + regulator-initial-mode = ; + }; + + vreg_l17b_2p5: ldo17 { + regulator-name = "vreg_l17b_2p5"; + regulator-min-microvolt = <2504000>; + regulator-max-microvolt = <2504000>; + regulator-initial-mode = ; + }; + }; + + regulators-1 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + qcom,pmic-id = "c"; + + vdd-l1-supply = <&vreg_s5j_1p2>; + vdd-l2-supply = <&vreg_s1f_0p7>; + vdd-l3-supply = <&vreg_s1f_0p7>; + vdd-s4-supply = <&vph_pwr>; + + vreg_s4c_1p8: smps4 { + regulator-name = "vreg_s4c_1p8"; + regulator-min-microvolt = <1856000>; + regulator-max-microvolt = <2000000>; + regulator-initial-mode = ; + }; + + vreg_l1c_1p2: ldo1 { + regulator-name = "vreg_l1c_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l2c_0p8: ldo2 { + regulator-name = "vreg_l2c_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l3c_0p8: ldo3 { + regulator-name = "vreg_l3c_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + }; + + regulators-2 { + compatible = "qcom,pmc8380-rpmh-regulators"; + qcom,pmic-id = "d"; + + vdd-l1-supply = <&vreg_s1f_0p7>; + vdd-l2-supply = <&vreg_s1f_0p7>; + vdd-l3-supply = <&vreg_s4c_1p8>; + vdd-s1-supply = <&vph_pwr>; + + vreg_l1d_0p8: ldo1 { + regulator-name = "vreg_l1d_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l2d_0p9: ldo2 { + regulator-name = "vreg_l2d_0p9"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l3d_1p8: ldo3 { + regulator-name = "vreg_l3d_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + }; + + regulators-3 { + compatible = "qcom,pmc8380-rpmh-regulators"; + qcom,pmic-id = "e"; + + vdd-l2-supply = <&vreg_s1f_0p7>; + vdd-l3-supply = <&vreg_s5j_1p2>; + + vreg_l2e_0p8: ldo2 { + regulator-name = "vreg_l2e_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l3e_1p2: ldo3 { + regulator-name = "vreg_l3e_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + }; + + regulators-4 { + compatible = "qcom,pmc8380-rpmh-regulators"; + qcom,pmic-id = "f"; + + vdd-l1-supply = <&vreg_s5j_1p2>; + vdd-l2-supply = <&vreg_s5j_1p2>; + vdd-l3-supply = <&vreg_s5j_1p2>; + vdd-s1-supply = <&vph_pwr>; + + vreg_s1f_0p7: smps1 { + regulator-name = "vreg_s1f_0p7"; + regulator-min-microvolt = <700000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + vreg_l1f_1p0: ldo1 { + regulator-name = "vreg_l1f_1p0"; + regulator-min-microvolt = <1024000>; + regulator-max-microvolt = <1024000>; + regulator-initial-mode = ; + }; + + vreg_l2f_1p0: ldo2 { + regulator-name = "vreg_l2f_1p0"; + regulator-min-microvolt = <1024000>; + regulator-max-microvolt = <1024000>; + regulator-initial-mode = ; + }; + + vreg_l3f_1p0: ldo3 { + regulator-name = "vreg_l3f_1p0"; + regulator-min-microvolt = <1024000>; + regulator-max-microvolt = <1024000>; + regulator-initial-mode = ; + }; + }; + + regulators-6 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + qcom,pmic-id = "i"; + + vdd-l1-supply = <&vreg_s4c_1p8>; + vdd-l2-supply = <&vreg_s5j_1p2>; + vdd-l3-supply = <&vreg_s1f_0p7>; + vdd-s1-supply = <&vph_pwr>; + vdd-s2-supply = <&vph_pwr>; + + vreg_s1i_0p9: smps1 { + regulator-name = "vreg_s1i_0p9"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_s2i_1p0: smps2 { + regulator-name = "vreg_s2i_1p0"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + vreg_l1i_1p8: ldo1 { + regulator-name = "vreg_l1i_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l2i_1p2: ldo2 { + regulator-name = "vreg_l2i_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l3i_0p8: ldo3 { + regulator-name = "vreg_l3i_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + }; + + regulators-7 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + qcom,pmic-id = "j"; + + vdd-l1-supply = <&vreg_s1f_0p7>; + vdd-l2-supply = <&vreg_s5j_1p2>; + vdd-l3-supply = <&vreg_s1f_0p7>; + vdd-s5-supply = <&vph_pwr>; + + vreg_s5j_1p2: smps5 { + regulator-name = "vreg_s5j_1p2"; + regulator-min-microvolt = <1256000>; + regulator-max-microvolt = <1304000>; + regulator-initial-mode = ; + }; + + vreg_l1j_0p8: ldo1 { + regulator-name = "vreg_l1j_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l2j_1p2: ldo2 { + regulator-name = "vreg_l2j_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l3j_0p8: ldo3 { + regulator-name = "vreg_l3j_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + }; +}; + +&gpu { + status = "okay"; + + zap-shader { + firmware-name = "qcom/x1e80100/Thundercomm/DEVKIT/qcdxkmsuc8380.mbn"; + }; +}; + +&i2c1 { + clock-frequency = <400000>; + + status = "okay"; + + typec-mux@8 { + compatible = "parade,ps8830"; + reg = <0x08>; + + clocks = <&rpmhcc RPMH_RF_CLK5>; + clock-names = "xo"; + + vdd-supply = <&vreg_rtmr2_1p15>; + vdd33-supply = <&vreg_rtmr2_3p3>; + vdd33-cap-supply = <&vreg_rtmr2_3p3>; + vddar-supply = <&vreg_rtmr2_1p15>; + vddat-supply = <&vreg_rtmr2_1p15>; + vddio-supply = <&vreg_rtmr2_1p8>; + + reset-gpios = <&tlmm 185 GPIO_ACTIVE_HIGH>; + + orientation-switch; + retimer-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + retimer_ss2_ss_out: endpoint { + remote-endpoint = <&pmic_glink_ss2_ss_in>; + }; + }; + + port@1 { + reg = <1>; + + retimer_ss2_ss_in: endpoint { + remote-endpoint = <&usb_1_ss2_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + retimer_ss2_con_sbu_out: endpoint { + remote-endpoint = <&pmic_glink_ss2_con_sbu_in>; + }; + }; + }; + }; +}; + +&i2c3 { + clock-frequency = <400000>; + + status = "okay"; + + typec-mux@8 { + compatible = "parade,ps8830"; + reg = <0x08>; + + clocks = <&rpmhcc RPMH_RF_CLK3>; + clock-names = "xo"; + + vdd-supply = <&vreg_rtmr0_1p15>; + vdd33-supply = <&vreg_rtmr0_3p3>; + vdd33-cap-supply = <&vreg_rtmr0_3p3>; + vddar-supply = <&vreg_rtmr0_1p15>; + vddat-supply = <&vreg_rtmr0_1p15>; + vddio-supply = <&vreg_rtmr0_1p8>; + + reset-gpios = <&pm8550_gpios 10 GPIO_ACTIVE_HIGH>; + + retimer-switch; + orientation-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + retimer_ss0_ss_out: endpoint { + remote-endpoint = <&pmic_glink_ss0_ss_in>; + }; + }; + + port@1 { + reg = <1>; + + retimer_ss0_ss_in: endpoint { + remote-endpoint = <&usb_1_ss0_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + retimer_ss0_con_sbu_out: endpoint { + remote-endpoint = <&pmic_glink_ss0_con_sbu_in>; + }; + }; + }; + }; +}; + +&i2c7 { + clock-frequency = <400000>; + + status = "okay"; + + typec-mux@8 { + compatible = "parade,ps8830"; + reg = <0x8>; + + clocks = <&rpmhcc RPMH_RF_CLK4>; + clock-names = "xo"; + + vdd-supply = <&vreg_rtmr1_1p15>; + vdd33-supply = <&vreg_rtmr1_3p3>; + vdd33-cap-supply = <&vreg_rtmr1_3p3>; + vddar-supply = <&vreg_rtmr1_1p15>; + vddat-supply = <&vreg_rtmr1_1p15>; + vddio-supply = <&vreg_rtmr1_1p8>; + + reset-gpios = <&tlmm 176 GPIO_ACTIVE_HIGH>; + + retimer-switch; + orientation-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + retimer_ss1_ss_out: endpoint { + remote-endpoint = <&pmic_glink_ss1_ss_in>; + }; + }; + + port@1 { + reg = <1>; + + retimer_ss1_ss_in: endpoint { + remote-endpoint = <&usb_1_ss1_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + retimer_ss1_con_sbu_out: endpoint { + remote-endpoint = <&pmic_glink_ss1_con_sbu_in>; + }; + }; + }; + }; +}; + +&mdss { + status = "okay"; +}; + +&mdss_dp0 { + status = "okay"; +}; + +&mdss_dp0_out { + data-lanes = <0 1>; +}; + +&mdss_dp1 { + status = "okay"; +}; + +&mdss_dp1_out { + data-lanes = <0 1>; +}; + +&mdss_dp2 { + status = "okay"; +}; + +&mdss_dp2_out { + data-lanes = <0 1>; +}; + +&pcie4 { + perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&pcie4_default>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&pcie4_phy { + vdda-phy-supply = <&vreg_l3i_0p8>; + vdda-pll-supply = <&vreg_l3e_1p2>; + + status = "okay"; +}; + +&pcie5 { + perst-gpios = <&tlmm 149 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 151 GPIO_ACTIVE_LOW>; + + vddpe-3v3-supply = <&vreg_wwan>; + + pinctrl-0 = <&pcie5_default>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&pcie5_phy { + vdda-phy-supply = <&vreg_l3i_0p8>; + vdda-pll-supply = <&vreg_l3e_1p2>; + + status = "okay"; +}; + +&pcie6a { + perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>; + + vddpe-3v3-supply = <&vreg_nvme>; + + pinctrl-names = "default"; + pinctrl-0 = <&pcie6a_default>; + + status = "okay"; +}; + +&pcie6a_phy { + vdda-phy-supply = <&vreg_l1d_0p8>; + vdda-pll-supply = <&vreg_l2j_1p2>; + + status = "okay"; +}; + +&pm8550_gpios { + usb0_3p3_reg_en: usb0-3p3-reg-en-state { + pins = "gpio11"; + function = "normal"; + }; +}; + +&pmc8380_5_gpios { + usb0_pwr_1p15_en: usb0-pwr-1p15-en-state { + pins = "gpio8"; + function = "normal"; + }; +}; + +&pm8550ve_9_gpios { + usb0_1p8_reg_en: usb0-1p8-reg-en-state { + pins = "gpio8"; + function = "normal"; + }; +}; + +&qupv3_0 { + status = "okay"; +}; + +&qupv3_1 { + status = "okay"; +}; + +&qupv3_2 { + status = "okay"; +}; + +&remoteproc_adsp { + firmware-name = "qcom/x1e80100/Thundercomm/DEVKIT/qcadsp8380.mbn", + "qcom/x1e80100/Thundercomm/DEVKIT/adsp_dtbs.elf"; + + status = "okay"; +}; + +&remoteproc_cdsp { + firmware-name = "qcom/x1e80100/Thundercomm/DEVKIT/qccdsp8380.mbn", + "qcom/x1e80100/Thundercomm/DEVKIT/cdsp_dtbs.elf"; + + status = "okay"; +}; + +&sdhc_2 { + cd-gpios = <&tlmm 71 GPIO_ACTIVE_LOW>; + pinctrl-0 = <&sdc2_default &sdc2_card_det_n>; + pinctrl-1 = <&sdc2_sleep &sdc2_card_det_n>; + pinctrl-names = "default", "sleep"; + vmmc-supply = <&vreg_l9b_2p9>; + vqmmc-supply = <&vreg_l6b_1p8>; + bus-width = <4>; + no-sdio; + no-mmc; + status = "okay"; +}; + +&smb2360_0 { + status = "okay"; +}; + +&smb2360_0_eusb2_repeater { + vdd18-supply = <&vreg_l3d_1p8>; + vdd3-supply = <&vreg_l2b_3p0>; +}; + +&smb2360_1 { + status = "okay"; +}; + +&smb2360_1_eusb2_repeater { + vdd18-supply = <&vreg_l3d_1p8>; + vdd3-supply = <&vreg_l14b_3p0>; +}; + +&smb2360_2 { + status = "okay"; +}; + +&smb2360_2_eusb2_repeater { + vdd18-supply = <&vreg_l3d_1p8>; + vdd3-supply = <&vreg_l8b_3p0>; +}; + +&swr1 { + status = "okay"; + + /* WCD9385 RX */ + wcd_rx: codec@0,4 { + compatible = "sdw20217010d00"; + reg = <0 4>; + qcom,rx-port-mapping = <1 2 3 4 5>; + }; +}; + +&swr2 { + status = "okay"; + + /* WCD9385 TX */ + wcd_tx: codec@0,3 { + compatible = "sdw20217010d00"; + reg = <0 3>; + qcom,tx-port-mapping = <2 2 3 4>; + }; +}; + +&tlmm { + gpio-reserved-ranges = <44 4>; /* SPI (TPM) */ + + nvme_reg_en: nvme-reg-en-state { + pins = "gpio18"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + pcie4_default: pcie4-default-state { + clkreq-n-pins { + pins = "gpio147"; + function = "pcie4_clk"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio146"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio148"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + pcie5_default: pcie5-default-state { + clkreq-n-pins { + pins = "gpio150"; + function = "pcie5_clk"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio149"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio151"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + pcie6a_default: pcie6a-default-state { + clkreq-n-pins { + pins = "gpio153"; + function = "pcie6a_clk"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio152"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio154"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + rtmr1_1p15_reg_en: rtmr1-1p15-reg-en-state { + pins = "gpio188"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr1_1p8_reg_en: rtmr1-1p8-reg-en-state { + pins = "gpio175"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr1_3p3_reg_en: rtmr1-3p3-reg-en-state { + pins = "gpio186"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr2_1p15_reg_en: rtmr2-1p15-reg-en-state { + pins = "gpio189"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr2_1p8_reg_en: rtmr2-1p8-reg-en-state { + pins = "gpio126"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr2_3p3_reg_en: rtmr2-3p3-reg-en-state { + pins = "gpio187"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + sdc2_card_det_n: sdc2-card-det-state { + pins = "gpio71"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + + wcd_default: wcd-reset-n-active-state { + pins = "gpio191"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + output-low; + }; + + wwan_sw_en: wwan-sw-en-state { + pins = "gpio221"; + function = "gpio"; + drive-strength = <4>; + bias-disable; + }; +}; + +&uart21 { + compatible = "qcom,geni-debug-uart"; + status = "okay"; +}; + +&usb_1_ss0_hsphy { + vdd-supply = <&vreg_l3j_0p8>; + vdda12-supply = <&vreg_l2j_1p2>; + + phys = <&smb2360_0_eusb2_repeater>; + + status = "okay"; +}; + +&usb_1_ss0_qmpphy { + vdda-phy-supply = <&vreg_l2j_1p2>; + vdda-pll-supply = <&vreg_l1j_0p8>; + + status = "okay"; +}; + +&usb_1_ss0 { + status = "okay"; +}; + +&usb_1_ss0_dwc3 { + dr_mode = "otg"; + usb-role-switch; +}; + +&usb_1_ss0_dwc3_hs { + remote-endpoint = <&pmic_glink_ss0_hs_in>; +}; + +&usb_1_ss0_qmpphy_out { + remote-endpoint = <&retimer_ss0_ss_in>; +}; + +&usb_1_ss1_hsphy { + vdd-supply = <&vreg_l3j_0p8>; + vdda12-supply = <&vreg_l2j_1p2>; + + phys = <&smb2360_1_eusb2_repeater>; + + status = "okay"; +}; + +&usb_1_ss1_qmpphy { + vdda-phy-supply = <&vreg_l2j_1p2>; + vdda-pll-supply = <&vreg_l2d_0p9>; + + status = "okay"; +}; + +&usb_1_ss1 { + status = "okay"; +}; + +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + +&usb_1_ss1_dwc3_hs { + remote-endpoint = <&pmic_glink_ss1_hs_in>; +}; + +&usb_1_ss1_qmpphy_out { + remote-endpoint = <&retimer_ss1_ss_in>; +}; + +&usb_1_ss2_hsphy { + vdd-supply = <&vreg_l3j_0p8>; + vdda12-supply = <&vreg_l2j_1p2>; + + phys = <&smb2360_2_eusb2_repeater>; + + status = "okay"; +}; + +&usb_1_ss2_qmpphy { + vdda-phy-supply = <&vreg_l2j_1p2>; + vdda-pll-supply = <&vreg_l2d_0p9>; + + status = "okay"; +}; + +&usb_1_ss2 { + status = "okay"; +}; + +&usb_1_ss2_dwc3 { + dr_mode = "host"; +}; + +&usb_1_ss2_dwc3_hs { + remote-endpoint = <&pmic_glink_ss2_hs_in>; +}; + +&usb_1_ss2_qmpphy_out { + remote-endpoint = <&retimer_ss2_ss_in>; +}; diff --git a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts index 975550139e10..b2c2347f54fa 100644 --- a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts +++ b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts @@ -19,6 +19,32 @@ compatible = "lenovo,thinkpad-t14s", "qcom,x1e78100", "qcom,x1e80100"; chassis-type = "laptop"; + wcd938x: audio-codec { + compatible = "qcom,wcd9385-codec"; + + pinctrl-0 = <&wcd_default>; + pinctrl-names = "default"; + + qcom,micbias1-microvolt = <1800000>; + qcom,micbias2-microvolt = <1800000>; + qcom,micbias3-microvolt = <1800000>; + qcom,micbias4-microvolt = <1800000>; + qcom,mbhc-buttons-vthreshold-microvolt = <75000 150000 237000 500000 500000 500000 500000 500000>; + qcom,mbhc-headset-vthreshold-microvolt = <1700000>; + qcom,mbhc-headphone-vthreshold-microvolt = <50000>; + qcom,rx-device = <&wcd_rx>; + qcom,tx-device = <&wcd_tx>; + + reset-gpios = <&tlmm 191 GPIO_ACTIVE_LOW>; + + vdd-buck-supply = <&vreg_l15b_1p8>; + vdd-rxtx-supply = <&vreg_l15b_1p8>; + vdd-io-supply = <&vreg_l15b_1p8>; + vdd-mic-bias-supply = <&vreg_bob1>; + + #sound-dai-cells = <1>; + }; + gpio-keys { compatible = "gpio-keys"; @@ -153,6 +179,85 @@ regulator-always-on; regulator-boot-on; }; + + sound { + compatible = "qcom,x1e80100-sndcard"; + model = "X1E80100-LENOVO-Thinkpad-T14s"; + audio-routing = "SpkrLeft IN", "WSA WSA_SPK1 OUT", + "SpkrRight IN", "WSA WSA_SPK2 OUT", + "IN1_HPHL", "HPHL_OUT", + "IN2_HPHR", "HPHR_OUT", + "AMIC2", "MIC BIAS2", + "VA DMIC0", "MIC BIAS1", + "VA DMIC1", "MIC BIAS1", + "VA DMIC0", "VA MIC BIAS1", + "VA DMIC1", "VA MIC BIAS1", + "TX SWR_INPUT1", "ADC2_OUTPUT"; + + wcd-playback-dai-link { + link-name = "WCD Playback"; + + cpu { + sound-dai = <&q6apmbedai RX_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&wcd938x 0>, <&swr1 0>, <&lpass_rxmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wcd-capture-dai-link { + link-name = "WCD Capture"; + + cpu { + sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>; + }; + + codec { + sound-dai = <&wcd938x 1>, <&swr2 1>, <&lpass_txmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wsa-dai-link { + link-name = "WSA Playback"; + + cpu { + sound-dai = <&q6apmbedai WSA_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&left_spkr>, <&right_spkr>, <&swr0 0>, <&lpass_wsamacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + va-dai-link { + link-name = "VA Capture"; + + cpu { + sound-dai = <&q6apmbedai VA_CODEC_DMA_TX_0>; + }; + + codec { + sound-dai = <&lpass_vamacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + }; }; &apps_rsc { @@ -185,6 +290,13 @@ regulator-initial-mode = ; }; + vreg_l1b_1p8: ldo1 { + regulator-name = "vreg_l1b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + vreg_l2b_3p0: ldo2 { regulator-name = "vreg_l2b_3p0"; regulator-min-microvolt = <3072000>; @@ -495,6 +607,54 @@ }; }; +&i2c5 { + clock-frequency = <400000>; + + status = "okay"; + + eusb5_repeater: redriver@43 { + compatible = "nxp,ptn3222"; + reg = <0x43>; + #phy-cells = <0>; + + vdd3v3-supply = <&vreg_l13b_3p0>; + vdd1v8-supply = <&vreg_l4b_1p8>; + + reset-gpios = <&tlmm 7 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&eusb5_reset_n>; + pinctrl-names = "default"; + }; + + eusb3_repeater: redriver@47 { + compatible = "nxp,ptn3222"; + reg = <0x47>; + #phy-cells = <0>; + + vdd3v3-supply = <&vreg_l13b_3p0>; + vdd1v8-supply = <&vreg_l4b_1p8>; + + reset-gpios = <&tlmm 6 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&eusb3_reset_n>; + pinctrl-names = "default"; + }; + + eusb6_repeater: redriver@4f { + compatible = "nxp,ptn3222"; + reg = <0x4f>; + #phy-cells = <0>; + + vdd3v3-supply = <&vreg_l13b_3p0>; + vdd1v8-supply = <&vreg_l4b_1p8>; + + reset-gpios = <&tlmm 184 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&eusb6_reset_n>; + pinctrl-names = "default"; + }; +}; + &i2c8 { clock-frequency = <400000>; @@ -515,6 +675,24 @@ /* TODO: second-sourced touchscreen @ 0x41 */ }; +&lpass_tlmm { + spkr_01_sd_n_active: spkr-01-sd-n-active-state { + pins = "gpio12"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + output-low; + }; +}; + +&lpass_vamacro { + pinctrl-0 = <&dmic01_default>; + pinctrl-names = "default"; + + vdd-micb-supply = <&vreg_l1b_1p8>; + qcom,dmic-sample-rate = <4800000>; +}; + &mdss { status = "okay"; }; @@ -635,22 +813,107 @@ status = "okay"; }; +&smb2360_0 { + status = "okay"; +}; + &smb2360_0_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l2b_3p0>; }; +&smb2360_1 { + status = "okay"; +}; + &smb2360_1_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l14b_3p0>; }; +&swr0 { + status = "okay"; + + pinctrl-0 = <&wsa_swr_active>, <&spkr_01_sd_n_active>; + pinctrl-names = "default"; + + /* WSA8845, Left Speaker */ + left_spkr: speaker@0,0 { + compatible = "sdw20217020400"; + reg = <0 0>; + reset-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>; + #sound-dai-cells = <0>; + sound-name-prefix = "SpkrLeft"; + vdd-1p8-supply = <&vreg_l15b_1p8>; + vdd-io-supply = <&vreg_l12b_1p2>; + qcom,port-mapping = <1 2 3 7 10 13>; + }; + + /* WSA8845, Right Speaker */ + right_spkr: speaker@0,1 { + compatible = "sdw20217020400"; + reg = <0 1>; + reset-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>; + #sound-dai-cells = <0>; + sound-name-prefix = "SpkrRight"; + vdd-1p8-supply = <&vreg_l15b_1p8>; + vdd-io-supply = <&vreg_l12b_1p2>; + qcom,port-mapping = <4 5 6 7 11 13>; + }; +}; + +&swr1 { + status = "okay"; + + /* WCD9385 RX */ + wcd_rx: codec@0,4 { + compatible = "sdw20217010d00"; + reg = <0 4>; + qcom,rx-port-mapping = <1 2 3 4 5>; + }; +}; + +&swr2 { + status = "okay"; + + /* WCD9385 TX */ + wcd_tx: codec@0,3 { + compatible = "sdw20217010d00"; + reg = <0 3>; + qcom,tx-port-mapping = <2 2 3 4>; + }; +}; + &tlmm { gpio-reserved-ranges = <34 2>, /* Unused */ <44 4>, /* SPI (TPM) */ <72 2>, /* Secure EC I2C connection (?) */ <238 1>; /* UFS Reset */ + eusb3_reset_n: eusb3-reset-n-state { + pins = "gpio6"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + output-low; + }; + + eusb5_reset_n: eusb5-reset-n-state { + pins = "gpio7"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + output-low; + }; + + eusb6_reset_n: eusb6-reset-n-state { + pins = "gpio184"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + output-low; + }; + tpad_default: tpad-default-state { pins = "gpio3"; function = "gpio"; @@ -763,7 +1026,7 @@ }; &usb_1_ss0_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l1j_0p8>; status = "okay"; @@ -773,6 +1036,10 @@ status = "okay"; }; +&usb_1_ss0_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss0_dwc3_hs { remote-endpoint = <&pmic_glink_ss0_hs_in>; }; @@ -791,7 +1058,7 @@ }; &usb_1_ss1_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l2d_0p9>; status = "okay"; @@ -801,6 +1068,10 @@ status = "okay"; }; +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss1_dwc3_hs { remote-endpoint = <&pmic_glink_ss1_hs_in>; }; @@ -808,3 +1079,56 @@ &usb_1_ss1_qmpphy_out { remote-endpoint = <&pmic_glink_ss1_ss_in>; }; + +&usb_2 { + status = "okay"; +}; + +&usb_2_dwc3 { + dr_mode = "host"; +}; + +&usb_2_hsphy { + vdd-supply = <&vreg_l2e_0p8>; + vdda12-supply = <&vreg_l3e_1p2>; + + phys = <&eusb5_repeater>; + + status = "okay"; +}; + +&usb_mp { + status = "okay"; +}; + +&usb_mp_hsphy0 { + vdd-supply = <&vreg_l2e_0p8>; + vdda12-supply = <&vreg_l3e_1p2>; + + phys = <&eusb6_repeater>; + + status = "okay"; +}; + +&usb_mp_hsphy1 { + vdd-supply = <&vreg_l2e_0p8>; + vdda12-supply = <&vreg_l3e_1p2>; + + phys = <&eusb3_repeater>; + + status = "okay"; +}; + +&usb_mp_qmpphy0 { + vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-pll-supply = <&vreg_l3c_0p8>; + + status = "okay"; +}; + +&usb_mp_qmpphy1 { + vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-pll-supply = <&vreg_l3c_0p8>; + + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts b/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts index 8515c254e158..53781f9b13af 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts @@ -7,7 +7,9 @@ /dts-v1/; #include +#include #include +#include #include "x1e80100.dtsi" #include "x1e80100-pmics.dtsi" @@ -17,6 +19,20 @@ compatible = "asus,vivobook-s15", "qcom,x1e80100"; chassis-type = "laptop"; + gpio-keys { + compatible = "gpio-keys"; + pinctrl-0 = <&hall_int_n_default>; + pinctrl-names = "default"; + + switch-lid { + gpios = <&tlmm 92 GPIO_ACTIVE_LOW>; + linux,input-type = ; + linux,code = ; + wakeup-source; + wakeup-event-action = ; + }; + }; + pmic-glink { compatible = "qcom,x1e80100-pmic-glink", "qcom,sm8550-pmic-glink", @@ -328,6 +344,14 @@ }; }; +&gpu { + status = "okay"; + + zap-shader { + firmware-name = "qcom/x1e80100/ASUSTeK/vivobook-s15/qcdxkmsuc8380.mbn"; + }; +}; + &i2c0 { clock-frequency = <400000>; status = "okay"; @@ -399,9 +423,13 @@ aux-bus { panel { - compatible = "edp-panel"; + compatible = "samsung,atna56ac03", "samsung,atna33xc20"; + enable-gpios = <&pmc8380_3_gpios 4 GPIO_ACTIVE_HIGH>; power-supply = <&vreg_edp_3p3>; + pinctrl-0 = <&edp_bl_en>; + pinctrl-names = "default"; + port { edp_panel_in: endpoint { remote-endpoint = <&mdss_dp3_out>; @@ -467,6 +495,18 @@ status = "okay"; }; +&pmc8380_3_gpios { + edp_bl_en: edp-bl-en-state { + pins = "gpio4"; + function = "normal"; + power-source = <1>; /* 1.8 V */ + qcom,drive-strength = ; + bias-pull-down; + input-disable; + output-enable; + }; +}; + &qupv3_0 { status = "okay"; }; @@ -493,11 +533,19 @@ status = "okay"; }; +&smb2360_0 { + status = "okay"; +}; + &smb2360_0_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l2b_3p0>; }; +&smb2360_1 { + status = "okay"; +}; + &smb2360_1_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l14b_3p0>; @@ -515,6 +563,12 @@ bias-disable; }; + hall_int_n_default: hall-int-n-state { + pins = "gpio92"; + function = "gpio"; + bias-disable; + }; + kybd_default: kybd-default-state { pins = "gpio67"; function = "gpio"; @@ -591,7 +645,7 @@ }; &usb_1_ss0_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l1j_0p8>; status = "okay"; @@ -623,7 +677,7 @@ }; &usb_1_ss1_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l2d_0p9>; status = "okay"; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts index 39f9d9cdc10d..ff5b3472fafd 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts @@ -932,11 +932,19 @@ status = "okay"; }; +&smb2360_0 { + status = "okay"; +}; + &smb2360_0_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l2b_3p0>; }; +&smb2360_1 { + status = "okay"; +}; + &smb2360_1_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l14b_3p0>; @@ -1187,7 +1195,7 @@ }; &usb_1_ss0_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l1j_0p8>; status = "okay"; @@ -1197,6 +1205,10 @@ status = "okay"; }; +&usb_1_ss0_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss0_dwc3_hs { remote-endpoint = <&pmic_glink_ss0_hs_in>; }; @@ -1215,7 +1227,7 @@ }; &usb_1_ss1_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l2d_0p9>; status = "okay"; @@ -1225,6 +1237,10 @@ status = "okay"; }; +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss1_dwc3_hs { remote-endpoint = <&pmic_glink_ss1_hs_in>; }; @@ -1243,7 +1259,7 @@ }; &usb_1_ss2_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l2d_0p9>; status = "okay"; @@ -1253,6 +1269,10 @@ status = "okay"; }; +&usb_1_ss2_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss2_dwc3_hs { remote-endpoint = <&pmic_glink_ss2_hs_in>; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-dell-xps13-9345.dts b/arch/arm64/boot/dts/qcom/x1e80100-dell-xps13-9345.dts index 05624226faf9..86e87f03b0ec 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-dell-xps13-9345.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-dell-xps13-9345.dts @@ -89,7 +89,15 @@ reg = <1>; pmic_glink_ss0_ss_in: endpoint { - remote-endpoint = <&usb_1_ss0_qmpphy_out>; + remote-endpoint = <&retimer_ss0_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_ss0_con_sbu_in: endpoint { + remote-endpoint = <&retimer_ss0_con_sbu_out>; }; }; }; @@ -118,7 +126,15 @@ reg = <1>; pmic_glink_ss1_ss_in: endpoint { - remote-endpoint = <&usb_1_ss1_qmpphy_out>; + remote-endpoint = <&retimer_ss1_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_ss1_con_sbu_in: endpoint { + remote-endpoint = <&retimer_ss1_con_sbu_out>; }; }; }; @@ -166,6 +182,102 @@ regulator-boot-on; }; + vreg_rtmr0_1p15: regulator-rtmr0-1p15 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_1P15"; + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; + + gpio = <&pmc8380_5_gpios 8 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr0_1p15_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr0_1p8: regulator-rtmr0-1p8 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_1P8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + gpio = <&pm8550ve_9_gpios 8 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr0_1p8_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr0_3p3: regulator-rtmr0-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&pm8550_gpios 11 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr0_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_1p15: regulator-rtmr1-1p15 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_1P15"; + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; + + gpio = <&tlmm 188 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr1_1p15_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_1p8: regulator-rtmr1-1p8 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_1P8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + gpio = <&tlmm 175 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr1_1p8_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_3p3: regulator-rtmr1-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 186 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr1_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + vreg_vph_pwr: regulator-vph-pwr { compatible = "regulator-fixed"; @@ -492,9 +604,60 @@ &i2c3 { clock-frequency = <400000>; - status = "disabled"; - /* PS8830 Retimer @0x8 */ - /* Unknown device @0x9 */ + status = "okay"; + + /* Right-side USB Type-C port */ + typec-mux@8 { + compatible = "parade,ps8830"; + reg = <0x08>; + + clocks = <&rpmhcc RPMH_RF_CLK3>; + clock-names = "xo"; + + vdd-supply = <&vreg_rtmr0_1p15>; + vdd33-supply = <&vreg_rtmr0_3p3>; + vdd33-cap-supply = <&vreg_rtmr0_3p3>; + vddar-supply = <&vreg_rtmr0_1p15>; + vddat-supply = <&vreg_rtmr0_1p15>; + vddio-supply = <&vreg_rtmr0_1p8>; + + reset-gpios = <&pm8550_gpios 10 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&rtmr0_default>; + pinctrl-names = "default"; + + retimer-switch; + orientation-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + retimer_ss0_ss_out: endpoint { + remote-endpoint = <&pmic_glink_ss0_ss_in>; + }; + }; + + port@1 { + reg = <1>; + + retimer_ss0_ss_in: endpoint { + remote-endpoint = <&usb_1_ss0_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + retimer_ss0_con_sbu_out: endpoint { + remote-endpoint = <&pmic_glink_ss0_con_sbu_in>; + }; + }; + }; + }; }; &i2c5 { @@ -505,9 +668,61 @@ &i2c7 { clock-frequency = <400000>; - status = "disabled"; - /* PS8830 Retimer @0x8 */ - /* Unknown device @0x9 */ + status = "okay"; + + /* Left-side USB Type-C port */ + typec-mux@8 { + compatible = "parade,ps8830"; + reg = <0x8>; + + clocks = <&rpmhcc RPMH_RF_CLK4>; + clock-names = "xo"; + + vdd-supply = <&vreg_rtmr1_1p15>; + vdd33-supply = <&vreg_rtmr1_3p3>; + vdd33-cap-supply = <&vreg_rtmr1_3p3>; + vddar-supply = <&vreg_rtmr1_1p15>; + vddat-supply = <&vreg_rtmr1_1p15>; + vddio-supply = <&vreg_rtmr1_1p8>; + + reset-gpios = <&tlmm 176 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&rtmr1_default>; + pinctrl-names = "default"; + + retimer-switch; + orientation-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + retimer_ss1_ss_out: endpoint { + remote-endpoint = <&pmic_glink_ss1_ss_in>; + }; + }; + + port@1 { + reg = <1>; + + retimer_ss1_ss_in: endpoint { + remote-endpoint = <&usb_1_ss1_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + retimer_ss1_con_sbu_out: endpoint { + remote-endpoint = <&pmic_glink_ss1_con_sbu_in>; + }; + }; + + }; + }; }; &i2c8 { @@ -634,6 +849,36 @@ status = "okay"; }; +&pm8550_gpios { + rtmr0_default: rtmr0-reset-n-active-state { + pins = "gpio10"; + function = "normal"; + power-source = <1>; /* 1.8V */ + }; + + rtmr0_3p3_reg_en: rtmr0-3p3-reg-en-state { + pins = "gpio11"; + function = "normal"; + power-source = <1>; /* 1.8V */ + }; +}; + +&pmc8380_5_gpios { + rtmr0_1p15_reg_en: rtmr0-1p15-reg-en-state { + pins = "gpio8"; + function = "normal"; + power-source = <1>; /* 1.8V */ + }; +}; + +&pm8550ve_9_gpios { + rtmr0_1p8_reg_en: rtmr0-1p8-reg-en-state { + pins = "gpio8"; + function = "normal"; + power-source = <1>; /* 1.8V */ + }; +}; + &qupv3_0 { status = "okay"; }; @@ -660,11 +905,19 @@ status = "okay"; }; +&smb2360_0 { + status = "okay"; +}; + &smb2360_0_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l2b_3p0>; }; +&smb2360_1 { + status = "okay"; +}; + &smb2360_1_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l14b_3p0>; @@ -762,6 +1015,34 @@ }; }; + rtmr1_1p15_reg_en: rtmr1-1p15-reg-en-state { + pins = "gpio188"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr1_1p8_reg_en: rtmr1-1p8-reg-en-state { + pins = "gpio175"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr1_3p3_reg_en: rtmr1-3p3-reg-en-state { + pins = "gpio186"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr1_default: rtmr1-reset-n-active-state { + pins = "gpio176"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + tpad_default: tpad-default-state { disable-pins { pins = "gpio38"; @@ -820,7 +1101,7 @@ }; &usb_1_ss0_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l1j_0p9>; status = "okay"; @@ -839,7 +1120,7 @@ }; &usb_1_ss0_qmpphy_out { - remote-endpoint = <&pmic_glink_ss0_ss_in>; + remote-endpoint = <&retimer_ss0_ss_in>; }; &usb_1_ss1_hsphy { @@ -852,7 +1133,7 @@ }; &usb_1_ss1_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l2d_0p9>; status = "okay"; @@ -871,5 +1152,5 @@ }; &usb_1_ss1_qmpphy_out { - remote-endpoint = <&pmic_glink_ss1_ss_in>; + remote-endpoint = <&retimer_ss1_ss_in>; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-hp-omnibook-x14.dts b/arch/arm64/boot/dts/qcom/x1e80100-hp-omnibook-x14.dts new file mode 100644 index 000000000000..cd860a246c45 --- /dev/null +++ b/arch/arm64/boot/dts/qcom/x1e80100-hp-omnibook-x14.dts @@ -0,0 +1,1693 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2024, Xilin Wu + */ + +/dts-v1/; + +#include +#include +#include +#include +#include + +#include "x1e80100.dtsi" +#include "x1e80100-pmics.dtsi" + +/ { + model = "HP Omnibook X 14"; + compatible = "hp,omnibook-x14", "qcom,x1e80100"; + chassis-type = "laptop"; + + aliases { + serial0 = &uart21; + serial1 = &uart14; + }; + + wcd938x: audio-codec { + compatible = "qcom,wcd9385-codec"; + + pinctrl-names = "default"; + pinctrl-0 = <&wcd_default>; + + qcom,micbias1-microvolt = <1800000>; + qcom,micbias2-microvolt = <1800000>; + qcom,micbias3-microvolt = <1800000>; + qcom,micbias4-microvolt = <1800000>; + qcom,mbhc-buttons-vthreshold-microvolt = <75000 150000 237000 500000 500000 500000 500000 500000>; + qcom,mbhc-headset-vthreshold-microvolt = <1700000>; + qcom,mbhc-headphone-vthreshold-microvolt = <50000>; + qcom,rx-device = <&wcd_rx>; + qcom,tx-device = <&wcd_tx>; + + reset-gpios = <&tlmm 191 GPIO_ACTIVE_LOW>; + + vdd-buck-supply = <&vreg_l15b_1p8>; + vdd-rxtx-supply = <&vreg_l15b_1p8>; + vdd-io-supply = <&vreg_l15b_1p8>; + vdd-mic-bias-supply = <&vreg_bob1>; + + #sound-dai-cells = <1>; + }; + + backlight: backlight { + compatible = "pwm-backlight"; + pwms = <&pmk8550_pwm 0 5000000>; + + brightness-levels = <0 2048 4096 8192 16384 65535>; + num-interpolated-steps = <20>; + default-brightness-level = <80>; + + enable-gpios = <&pmc8380_3_gpios 4 GPIO_ACTIVE_HIGH>; + power-supply = <&vreg_edp_bl>; + + pinctrl-0 = <&edp_bl_en>, <&edp_bl_pwm>; + pinctrl-names = "default"; + }; + + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-0 = <&hall_int_n_default>; + pinctrl-names = "default"; + + switch-lid { + gpios = <&tlmm 92 GPIO_ACTIVE_LOW>; + linux,input-type = ; + linux,code = ; + wakeup-source; + wakeup-event-action = ; + }; + }; + + pmic-glink { + compatible = "qcom,x1e80100-pmic-glink", + "qcom,sm8550-pmic-glink", + "qcom,pmic-glink"; + orientation-gpios = <&tlmm 121 GPIO_ACTIVE_HIGH>, + <&tlmm 123 GPIO_ACTIVE_HIGH>; + #address-cells = <1>; + #size-cells = <0>; + + /* Left-side port, closer to the screen */ + connector@0 { + compatible = "usb-c-connector"; + reg = <0>; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + pmic_glink_ss0_hs_in: endpoint { + remote-endpoint = <&usb_1_ss0_dwc3_hs>; + }; + }; + + port@1 { + reg = <1>; + + pmic_glink_ss0_ss_in: endpoint { + remote-endpoint = <&retimer_ss0_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_ss0_con_sbu_in: endpoint { + remote-endpoint = <&retimer_ss0_con_sbu_out>; + }; + }; + }; + }; + + /* Left-side port, farther from the screen */ + connector@1 { + compatible = "usb-c-connector"; + reg = <1>; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + pmic_glink_ss1_hs_in: endpoint { + remote-endpoint = <&usb_1_ss1_dwc3_hs>; + }; + }; + + port@1 { + reg = <1>; + + pmic_glink_ss1_ss_in: endpoint { + remote-endpoint = <&retimer_ss1_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_ss1_con_sbu_in: endpoint { + remote-endpoint = <&retimer_ss1_con_sbu_out>; + }; + }; + }; + }; + }; + + reserved-memory { + linux,cma { + compatible = "shared-dma-pool"; + size = <0x0 0x8000000>; + reusable; + linux,cma-default; + }; + }; + + sound { + compatible = "qcom,x1e80100-sndcard"; + model = "X1E80100-HP-OMNIBOOK-X14"; + audio-routing = "SpkrLeft IN", "WSA WSA_SPK1 OUT", + "SpkrRight IN", "WSA WSA_SPK2 OUT", + "IN1_HPHL", "HPHL_OUT", + "IN2_HPHR", "HPHR_OUT", + "AMIC2", "MIC BIAS2", + "VA DMIC0", "MIC BIAS3", + "VA DMIC1", "MIC BIAS3", + "VA DMIC2", "MIC BIAS1", + "VA DMIC3", "MIC BIAS1", + "VA DMIC0", "VA MIC BIAS3", + "VA DMIC1", "VA MIC BIAS3", + "VA DMIC2", "VA MIC BIAS1", + "VA DMIC3", "VA MIC BIAS1", + "TX SWR_INPUT1", "ADC2_OUTPUT"; + + wcd-playback-dai-link { + link-name = "WCD Playback"; + + cpu { + sound-dai = <&q6apmbedai RX_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&wcd938x 0>, <&swr1 0>, <&lpass_rxmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wcd-capture-dai-link { + link-name = "WCD Capture"; + + cpu { + sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>; + }; + + codec { + sound-dai = <&wcd938x 1>, <&swr2 1>, <&lpass_txmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wsa-dai-link { + link-name = "WSA Playback"; + + cpu { + sound-dai = <&q6apmbedai WSA_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&left_spkr>, <&right_spkr>, <&swr0 0>, <&lpass_wsamacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + va-dai-link { + link-name = "VA Capture"; + + cpu { + sound-dai = <&q6apmbedai VA_CODEC_DMA_TX_0>; + }; + + codec { + sound-dai = <&lpass_vamacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + }; + + vreg_edp_3p3: regulator-edp-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_EDP_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 70 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&edp_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_edp_bl: regulator-edp-bl { + compatible = "regulator-fixed"; + + regulator-name = "VBL9"; + regulator-min-microvolt = <3600000>; + regulator-max-microvolt = <3600000>; + + gpio = <&pmc8380_3_gpios 10 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-names = "default"; + pinctrl-0 = <&edp_bl_reg_en>; + + regulator-boot-on; + }; + + vreg_misc_3p3: regulator-misc-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_MISC_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&pm8550ve_8_gpios 6 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-names = "default"; + pinctrl-0 = <&misc_3p3_reg_en>; + + regulator-boot-on; + regulator-always-on; + }; + + vreg_nvme: regulator-nvme { + compatible = "regulator-fixed"; + + regulator-name = "VREG_NVME_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 18 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&nvme_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr0_1p15: regulator-rtmr0-1p15 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_1P15"; + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; + + gpio = <&pmc8380_5_gpios 8 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&usb0_pwr_1p15_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr0_1p8: regulator-rtmr0-1p8 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_1P8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + gpio = <&pm8550ve_9_gpios 8 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&usb0_1p8_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr0_3p3: regulator-rtmr0-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&pm8550_gpios 11 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&usb0_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_1p15: regulator-rtmr1-1p15 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_1P15"; + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; + + gpio = <&tlmm 188 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&usb1_pwr_1p15_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_1p8: regulator-rtmr1-1p8 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_1P8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + gpio = <&tlmm 175 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&usb1_pwr_1p8_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_3p3: regulator-rtmr1-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 186 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&usb1_pwr_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_vph_pwr: regulator-vph-pwr { + compatible = "regulator-fixed"; + + regulator-name = "vreg_vph_pwr"; + regulator-min-microvolt = <3700000>; + regulator-max-microvolt = <3700000>; + + regulator-always-on; + regulator-boot-on; + }; + + vreg_wcn_3p3: regulator-wcn-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_WCN_3P3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 214 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&wcn_sw_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + /* + * TODO: These two regulators are actually part of the removable M.2 + * card and not the CRD mainboard. Need to describe this differently. + * Functionally it works correctly, because all we need to do is to + * turn on the actual 3.3V supply above. + */ + vreg_wcn_0p95: regulator-wcn-0p95 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_WCN_0P95"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <950000>; + + vin-supply = <&vreg_wcn_3p3>; + }; + + vreg_wcn_1p9: regulator-wcn-1p9 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_WCN_1P9"; + regulator-min-microvolt = <1900000>; + regulator-max-microvolt = <1900000>; + + vin-supply = <&vreg_wcn_3p3>; + }; + + wcn6855-pmu { + compatible = "qcom,wcn6855-pmu"; + + vddaon-supply = <&vreg_wcn_0p95>; + vddio-supply = <&vreg_wcn_1p9>; + vddpcie1p3-supply = <&vreg_wcn_1p9>; + vddpcie1p9-supply = <&vreg_wcn_1p9>; + vddpmu-supply = <&vreg_wcn_0p95>; + vddpmumx-supply = <&vreg_wcn_0p95>; + vddpmucx-supply = <&vreg_wcn_0p95>; + vddrfa0p95-supply = <&vreg_wcn_0p95>; + vddrfa1p3-supply = <&vreg_wcn_1p9>; + vddrfa1p9-supply = <&vreg_wcn_1p9>; + + wlan-enable-gpios = <&tlmm 117 GPIO_ACTIVE_HIGH>; + bt-enable-gpios = <&tlmm 116 GPIO_ACTIVE_HIGH>; + + pinctrl-0 = <&wcn_wlan_bt_en>; + pinctrl-names = "default"; + + regulators { + vreg_pmu_rfa_cmn_0p8: ldo0 { + regulator-name = "vreg_pmu_rfa_cmn_0p8"; + }; + + vreg_pmu_aon_0p8: ldo1 { + regulator-name = "vreg_pmu_aon_0p8"; + }; + + vreg_pmu_wlcx_0p8: ldo2 { + regulator-name = "vreg_pmu_wlcx_0p8"; + }; + + vreg_pmu_wlmx_0p8: ldo3 { + regulator-name = "vreg_pmu_wlmx_0p8"; + }; + + vreg_pmu_btcmx_0p8: ldo4 { + regulator-name = "vreg_pmu_btcmx_0p8"; + }; + + vreg_pmu_pcie_1p8: ldo5 { + regulator-name = "vreg_pmu_pcie_1p8"; + }; + + vreg_pmu_pcie_0p9: ldo6 { + regulator-name = "vreg_pmu_pcie_0p9"; + }; + + vreg_pmu_rfa_0p8: ldo7 { + regulator-name = "vreg_pmu_rfa_0p8"; + }; + + vreg_pmu_rfa_1p2: ldo8 { + regulator-name = "vreg_pmu_rfa_1p2"; + }; + + vreg_pmu_rfa_1p7: ldo9 { + regulator-name = "vreg_pmu_rfa_1p7"; + }; + }; + }; +}; + +&apps_rsc { + regulators-0 { + compatible = "qcom,pm8550-rpmh-regulators"; + qcom,pmic-id = "b"; + + vdd-bob1-supply = <&vreg_vph_pwr>; + vdd-bob2-supply = <&vreg_vph_pwr>; + vdd-l1-l4-l10-supply = <&vreg_s4c_1p8>; + vdd-l2-l13-l14-supply = <&vreg_bob1>; + vdd-l5-l16-supply = <&vreg_bob1>; + vdd-l6-l7-supply = <&vreg_bob2>; + vdd-l8-l9-supply = <&vreg_bob1>; + vdd-l12-supply = <&vreg_s5j_1p2>; + vdd-l15-supply = <&vreg_s4c_1p8>; + vdd-l17-supply = <&vreg_bob2>; + + vreg_bob1: bob1 { + regulator-name = "vreg_bob1"; + regulator-min-microvolt = <3008000>; + regulator-max-microvolt = <3960000>; + regulator-initial-mode = ; + }; + + vreg_bob2: bob2 { + regulator-name = "vreg_bob2"; + regulator-min-microvolt = <2504000>; + regulator-max-microvolt = <3008000>; + regulator-initial-mode = ; + }; + + vreg_l1b_1p8: ldo1 { + regulator-name = "vreg_l1b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l2b_3p0: ldo2 { + regulator-name = "vreg_l2b_3p0"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3100000>; + regulator-initial-mode = ; + }; + + vreg_l4b_1p8: ldo4 { + regulator-name = "vreg_l4b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l5b_3p0: ldo5 { + regulator-name = "vreg_l5b_3p0"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3000000>; + regulator-initial-mode = ; + }; + + vreg_l6b_1p8: ldo6 { + regulator-name = "vreg_l6b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2960000>; + regulator-initial-mode = ; + }; + + vreg_l7b_2p8: ldo7 { + regulator-name = "vreg_l7b_2p8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-initial-mode = ; + }; + + vreg_l8b_3p0: ldo8 { + regulator-name = "vreg_l8b_3p0"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + }; + + vreg_l9b_2p9: ldo9 { + regulator-name = "vreg_l9b_2p9"; + regulator-min-microvolt = <2960000>; + regulator-max-microvolt = <2960000>; + regulator-initial-mode = ; + }; + + vreg_l10b_1p8: ldo10 { + regulator-name = "vreg_l10b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l12b_1p2: ldo12 { + regulator-name = "vreg_l12b_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l13b_3p0: ldo13 { + regulator-name = "vreg_l13b_3p0"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3100000>; + regulator-initial-mode = ; + }; + + vreg_l14b_3p0: ldo14 { + regulator-name = "vreg_l14b_3p0"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + }; + + vreg_l15b_1p8: ldo15 { + regulator-name = "vreg_l15b_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l16b_2p9: ldo16 { + regulator-name = "vreg_l16b_2p9"; + regulator-min-microvolt = <2912000>; + regulator-max-microvolt = <2912000>; + regulator-initial-mode = ; + }; + + vreg_l17b_2p5: ldo17 { + regulator-name = "vreg_l17b_2p5"; + regulator-min-microvolt = <2504000>; + regulator-max-microvolt = <2504000>; + regulator-initial-mode = ; + }; + }; + + regulators-1 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + qcom,pmic-id = "c"; + + vdd-l1-supply = <&vreg_s5j_1p2>; + vdd-l2-supply = <&vreg_s1f_0p7>; + vdd-l3-supply = <&vreg_s1f_0p7>; + vdd-s4-supply = <&vreg_vph_pwr>; + + vreg_s4c_1p8: smps4 { + regulator-name = "vreg_s4c_1p8"; + regulator-min-microvolt = <1856000>; + regulator-max-microvolt = <2000000>; + regulator-initial-mode = ; + }; + + vreg_l1c_1p2: ldo1 { + regulator-name = "vreg_l1c_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l2c_0p8: ldo2 { + regulator-name = "vreg_l2c_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l3c_0p8: ldo3 { + regulator-name = "vreg_l3c_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + }; + + regulators-2 { + compatible = "qcom,pmc8380-rpmh-regulators"; + qcom,pmic-id = "d"; + + vdd-l1-supply = <&vreg_s1f_0p7>; + vdd-l2-supply = <&vreg_s1f_0p7>; + vdd-l3-supply = <&vreg_s4c_1p8>; + vdd-s1-supply = <&vreg_vph_pwr>; + + vreg_l1d_0p8: ldo1 { + regulator-name = "vreg_l1d_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l2d_0p9: ldo2 { + regulator-name = "vreg_l2d_0p9"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l3d_1p8: ldo3 { + regulator-name = "vreg_l3d_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + }; + + regulators-3 { + compatible = "qcom,pmc8380-rpmh-regulators"; + qcom,pmic-id = "e"; + + vdd-l2-supply = <&vreg_s1f_0p7>; + vdd-l3-supply = <&vreg_s5j_1p2>; + + vreg_l2e_0p8: ldo2 { + regulator-name = "vreg_l2e_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l3e_1p2: ldo3 { + regulator-name = "vreg_l3e_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + }; + + regulators-4 { + compatible = "qcom,pmc8380-rpmh-regulators"; + qcom,pmic-id = "f"; + + vdd-l1-supply = <&vreg_s5j_1p2>; + vdd-l2-supply = <&vreg_s5j_1p2>; + vdd-l3-supply = <&vreg_s5j_1p2>; + vdd-s1-supply = <&vreg_vph_pwr>; + + vreg_s1f_0p7: smps1 { + regulator-name = "vreg_s1f_0p7"; + regulator-min-microvolt = <700000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + vreg_l1f_1p0: ldo1 { + regulator-name = "vreg_l1f_1p0"; + regulator-min-microvolt = <1024000>; + regulator-max-microvolt = <1024000>; + regulator-initial-mode = ; + }; + + vreg_l2f_1p0: ldo2 { + regulator-name = "vreg_l2f_1p0"; + regulator-min-microvolt = <1024000>; + regulator-max-microvolt = <1024000>; + regulator-initial-mode = ; + }; + + vreg_l3f_1p0: ldo3 { + regulator-name = "vreg_l3f_1p0"; + regulator-min-microvolt = <1024000>; + regulator-max-microvolt = <1024000>; + regulator-initial-mode = ; + }; + }; + + regulators-6 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + qcom,pmic-id = "i"; + + vdd-l1-supply = <&vreg_s4c_1p8>; + vdd-l2-supply = <&vreg_s5j_1p2>; + vdd-l3-supply = <&vreg_s1f_0p7>; + vdd-s1-supply = <&vreg_vph_pwr>; + vdd-s2-supply = <&vreg_vph_pwr>; + + vreg_s1i_0p9: smps1 { + regulator-name = "vreg_s1i_0p9"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_s2i_1p0: smps2 { + regulator-name = "vreg_s2i_1p0"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1100000>; + regulator-initial-mode = ; + }; + + vreg_l1i_1p8: ldo1 { + regulator-name = "vreg_l1i_1p8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + + vreg_l2i_1p2: ldo2 { + regulator-name = "vreg_l2i_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l3i_0p8: ldo3 { + regulator-name = "vreg_l3i_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + }; + + regulators-7 { + compatible = "qcom,pm8550ve-rpmh-regulators"; + qcom,pmic-id = "j"; + + vdd-l1-supply = <&vreg_s1f_0p7>; + vdd-l2-supply = <&vreg_s5j_1p2>; + vdd-l3-supply = <&vreg_s1f_0p7>; + vdd-s5-supply = <&vreg_vph_pwr>; + + vreg_s5j_1p2: smps5 { + regulator-name = "vreg_s5j_1p2"; + regulator-min-microvolt = <1256000>; + regulator-max-microvolt = <1304000>; + regulator-initial-mode = ; + }; + + vreg_l1j_0p8: ldo1 { + regulator-name = "vreg_l1j_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + + vreg_l2j_1p2: ldo2 { + regulator-name = "vreg_l2j_1p2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-initial-mode = ; + }; + + vreg_l3j_0p8: ldo3 { + regulator-name = "vreg_l3j_0p8"; + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <920000>; + regulator-initial-mode = ; + }; + }; +}; + +&gpu { + status = "okay"; + + zap-shader { + firmware-name = "qcom/x1e80100/hp/omnibook-x14/qcdxkmsuc8380.mbn"; + }; +}; + +&i2c0 { + clock-frequency = <400000>; + + status = "okay"; + + keyboard@3a { + compatible = "hid-over-i2c"; + reg = <0x3a>; + + hid-descr-addr = <0x1>; + interrupts-extended = <&tlmm 67 IRQ_TYPE_LEVEL_LOW>; + + vdd-supply = <&vreg_misc_3p3>; + vddl-supply = <&vreg_l12b_1p2>; + + pinctrl-0 = <&kybd_default>; + pinctrl-names = "default"; + + wakeup-source; + }; + + touchpad@15 { + compatible = "hid-over-i2c"; + reg = <0x15>; + + hid-descr-addr = <0x1>; + interrupts-extended = <&tlmm 3 IRQ_TYPE_LEVEL_LOW>; + + vdd-supply = <&vreg_misc_3p3>; + vddl-supply = <&vreg_l12b_1p2>; + + pinctrl-0 = <&tpad_default>; + pinctrl-names = "default"; + + wakeup-source; + }; +}; + +&i2c1 { + clock-frequency = <400000>; + + status = "okay"; + + /* type-c PS8830 Retimer #2 0x8 */ + /* is active on Windows */ +}; + +&i2c3 { + clock-frequency = <400000>; + + status = "okay"; + + typec-mux@8 { + compatible = "parade,ps8830"; + reg = <0x08>; + + clocks = <&rpmhcc RPMH_RF_CLK3>; + + vdd-supply = <&vreg_rtmr0_1p15>; + vdd33-supply = <&vreg_rtmr0_3p3>; + vdd33-cap-supply = <&vreg_rtmr0_3p3>; + vddar-supply = <&vreg_rtmr0_1p15>; + vddat-supply = <&vreg_rtmr0_1p15>; + vddio-supply = <&vreg_rtmr0_1p8>; + + reset-gpios = <&pm8550_gpios 10 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&rtmr0_default>; + pinctrl-names = "default"; + + orientation-switch; + retimer-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + retimer_ss0_ss_out: endpoint { + remote-endpoint = <&pmic_glink_ss0_ss_in>; + }; + }; + + port@1 { + reg = <1>; + + retimer_ss0_ss_in: endpoint { + remote-endpoint = <&usb_1_ss0_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + retimer_ss0_con_sbu_out: endpoint { + remote-endpoint = <&pmic_glink_ss0_con_sbu_in>; + }; + }; + }; + }; +}; + +&i2c4 { + clock-frequency = <400000>; + + status = "okay"; + + /* is active on Windows */ +}; + +&i2c5 { + clock-frequency = <400000>; + status = "okay"; + + eusb3_repeater: redriver@47 { + compatible = "nxp,ptn3222"; + reg = <0x47>; + #phy-cells = <0>; + + vdd3v3-supply = <&vreg_l13b_3p0>; + vdd1v8-supply = <&vreg_l4b_1p8>; + + reset-gpios = <&tlmm 6 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&eusb3_reset_n>; + pinctrl-names = "default"; + + }; +}; + +&i2c7 { + clock-frequency = <400000>; + + status = "okay"; + + typec-mux@8 { + compatible = "parade,ps8830"; + reg = <0x8>; + + clocks = <&rpmhcc RPMH_RF_CLK4>; + + vdd-supply = <&vreg_rtmr1_1p15>; + vdd33-supply = <&vreg_rtmr1_3p3>; + vdd33-cap-supply = <&vreg_rtmr1_3p3>; + vddar-supply = <&vreg_rtmr1_1p15>; + vddat-supply = <&vreg_rtmr1_1p15>; + vddio-supply = <&vreg_rtmr1_1p8>; + + reset-gpios = <&tlmm 176 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&rtmr1_default>; + pinctrl-names = "default"; + + orientation-switch; + retimer-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + retimer_ss1_ss_out: endpoint { + remote-endpoint = <&pmic_glink_ss1_ss_in>; + }; + }; + + port@1 { + reg = <1>; + + retimer_ss1_ss_in: endpoint { + remote-endpoint = <&usb_1_ss1_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + retimer_ss1_con_sbu_out: endpoint { + remote-endpoint = <&pmic_glink_ss1_con_sbu_in>; + }; + }; + + }; + }; +}; + +&i2c8 { + clock-frequency = <400000>; + + status = "okay"; + + touchscreen@10 { + compatible = "hid-over-i2c"; + reg = <0x10>; + + hid-descr-addr = <0x1>; + interrupts-extended = <&tlmm 51 IRQ_TYPE_LEVEL_LOW>; + + vdd-supply = <&vreg_misc_3p3>; + vddl-supply = <&vreg_l15b_1p8>; + + pinctrl-0 = <&ts0_default>; + pinctrl-names = "default"; + }; +}; + +&i2c9 { + clock-frequency = <400000>; + + status = "okay"; + + /* is active on Windows */ +}; + +&lpass_tlmm { + spkr_01_sd_n_active: spkr-01-sd-n-active-state { + pins = "gpio12"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + output-low; + }; +}; + +&lpass_vamacro { + pinctrl-0 = <&dmic01_default>, <&dmic23_default>; + pinctrl-names = "default"; + + vdd-micb-supply = <&vreg_l1b_1p8>; + qcom,dmic-sample-rate = <4800000>; +}; + +&mdss { + status = "okay"; +}; + +&mdss_dp0 { + status = "okay"; +}; + +&mdss_dp0_out { + data-lanes = <0 1>; +}; + +&mdss_dp1 { + status = "okay"; +}; + +&mdss_dp1_out { + data-lanes = <0 1>; +}; + +&mdss_dp3 { + compatible = "qcom,x1e80100-dp"; + /delete-property/ #sound-dai-cells; + + status = "okay"; + + aux-bus { + panel { + compatible = "edp-panel"; + power-supply = <&vreg_edp_3p3>; + + backlight = <&backlight>; + + port { + edp_panel_in: endpoint { + remote-endpoint = <&mdss_dp3_out>; + }; + }; + }; + }; + + ports { + port@1 { + reg = <1>; + + mdss_dp3_out: endpoint { + data-lanes = <0 1 2 3>; + link-frequencies = /bits/ 64 <1620000000 2700000000 5400000000 8100000000>; + + remote-endpoint = <&edp_panel_in>; + }; + }; + }; +}; + +&mdss_dp3_phy { + vdda-phy-supply = <&vreg_l3j_0p8>; + vdda-pll-supply = <&vreg_l2j_1p2>; + + status = "okay"; +}; + +&pcie4 { + perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&pcie4_default>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&pcie4_phy { + vdda-phy-supply = <&vreg_l3i_0p8>; + vdda-pll-supply = <&vreg_l3e_1p2>; + + status = "okay"; +}; + +&pcie4_port0 { + wifi@0 { + compatible = "pci17cb,1107"; + reg = <0x10000 0x0 0x0 0x0 0x0>; + + vddaon-supply = <&vreg_pmu_aon_0p8>; + vddpcie0p9-supply = <&vreg_pmu_pcie_0p9>; + vddpcie1p8-supply = <&vreg_pmu_pcie_1p8>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p8-supply = <&vreg_pmu_rfa_1p7>; + vddrfacmn-supply = <&vreg_pmu_rfa_cmn_0p8>; + vddwlcx-supply = <&vreg_pmu_wlcx_0p8>; + vddwlmx-supply = <&vreg_pmu_wlmx_0p8>; + }; +}; + +&pcie6a { + perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>; + + vddpe-3v3-supply = <&vreg_nvme>; + + pinctrl-0 = <&pcie6a_default>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&pcie6a_phy { + vdda-phy-supply = <&vreg_l1d_0p8>; + vdda-pll-supply = <&vreg_l2j_1p2>; + + status = "okay"; +}; + +&pm8550_gpios { + rtmr0_default: rtmr0-reset-n-active-state { + pins = "gpio10"; + function = "normal"; + power-source = <1>; /* 1.8V */ + bias-disable; + input-disable; + output-enable; + }; + + usb0_3p3_reg_en: usb0-3p3-reg-en-state { + pins = "gpio11"; + function = "normal"; + power-source = <1>; /* 1.8V */ + bias-disable; + input-disable; + output-enable; + }; +}; + +&pm8550ve_8_gpios { + misc_3p3_reg_en: misc-3p3-reg-en-state { + pins = "gpio6"; + function = "normal"; + bias-disable; + drive-push-pull; + input-disable; + output-enable; + power-source = <1>; /* 1.8 V */ + qcom,drive-strength = ; + }; +}; + +&pm8550ve_9_gpios { + usb0_1p8_reg_en: usb0-1p8-reg-en-state { + pins = "gpio8"; + function = "normal"; + power-source = <1>; /* 1.8V */ + bias-disable; + input-disable; + output-enable; + }; +}; + +&pmc8380_3_gpios { + edp_bl_en: edp-bl-en-state { + pins = "gpio4"; + function = "normal"; + power-source = <1>; /* 1.8V */ + input-disable; + output-enable; + }; + + edp_bl_reg_en: edp-bl-reg-en-state { + pins = "gpio10"; + function = "normal"; + }; + +}; + +&pmk8550_gpios { + edp_bl_pwm: edp-bl-pwm-state { + pins = "gpio5"; + function = "func3"; + }; +}; + +&pmk8550_pwm { + status = "okay"; +}; + +&pmc8380_5_gpios { + usb0_pwr_1p15_reg_en: usb0-pwr-1p15-reg-en-state { + pins = "gpio8"; + function = "normal"; + power-source = <1>; /* 1.8V */ + bias-disable; + input-disable; + output-enable; + }; +}; + +&qupv3_0 { + status = "okay"; +}; + +&qupv3_1 { + status = "okay"; +}; + +&qupv3_2 { + status = "okay"; +}; + +&remoteproc_adsp { + firmware-name = "qcom/x1e80100/hp/omnibook-x14/qcadsp8380.mbn", + "qcom/x1e80100/hp/omnibook-x14/adsp_dtbs.elf"; + + status = "okay"; +}; + +&remoteproc_cdsp { + firmware-name = "qcom/x1e80100/hp/omnibook-x14/qccdsp8380.mbn", + "qcom/x1e80100/hp/omnibook-x14/cdsp_dtbs.elf"; + + status = "okay"; +}; + +&smb2360_0_eusb2_repeater { + vdd18-supply = <&vreg_l3d_1p8>; + vdd3-supply = <&vreg_l2b_3p0>; + + status = "okay"; +}; + +&smb2360_1_eusb2_repeater { + vdd18-supply = <&vreg_l3d_1p8>; + vdd3-supply = <&vreg_l14b_3p0>; + + status = "okay"; +}; + +&swr0 { + pinctrl-0 = <&wsa_swr_active>, <&spkr_01_sd_n_active>; + pinctrl-names = "default"; + + status = "okay"; + + /* WSA8845, Left Speaker */ + left_spkr: speaker@0,0 { + compatible = "sdw20217020400"; + reg = <0 0>; + reset-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>; + #sound-dai-cells = <0>; + sound-name-prefix = "SpkrLeft"; + vdd-1p8-supply = <&vreg_l15b_1p8>; + vdd-io-supply = <&vreg_l12b_1p2>; + qcom,port-mapping = <1 2 3 7 10 13>; + }; + + /* WSA8845, Right Speaker */ + right_spkr: speaker@0,1 { + compatible = "sdw20217020400"; + reg = <0 1>; + reset-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>; + #sound-dai-cells = <0>; + sound-name-prefix = "SpkrRight"; + vdd-1p8-supply = <&vreg_l15b_1p8>; + vdd-io-supply = <&vreg_l12b_1p2>; + qcom,port-mapping = <4 5 6 7 11 13>; + }; +}; + +&swr1 { + status = "okay"; + + /* WCD9385 RX */ + wcd_rx: codec@0,4 { + compatible = "sdw20217010d00"; + reg = <0 4>; + qcom,rx-port-mapping = <1 2 3 4 5>; + }; +}; + +&swr2 { + status = "okay"; + + /* WCD9385 TX */ + wcd_tx: codec@0,3 { + compatible = "sdw20217010d00"; + reg = <0 3>; + qcom,tx-port-mapping = <2 2 3 4>; + }; +}; + +&tlmm { + gpio-reserved-ranges = <34 2>, /* Unused */ + <44 4>, /* SPI (TPM) */ + <72 2>, /* Secure EC I2C connection (?) */ + <238 1>; /* UFS Reset */ + + bt_en_default: bt-en-sleep { + pins = "gpio116"; + function = "gpio"; + output-low; + bias-disable; + drive-strength = <16>; + }; + + edp_reg_en: edp-reg-en-state { + pins = "gpio70"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + }; + + eusb3_reset_n: eusb3-reset-n-state { + pins = "gpio6"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + output-low; + }; + + hall_int_n_default: hall-int-n-state { + pins = "gpio92"; + function = "gpio"; + bias-disable; + }; + + kybd_default: kybd-default-state { + pins = "gpio67"; + function = "gpio"; + bias-pull-up; + }; + + nvme_reg_en: nvme-reg-en-state { + pins = "gpio18"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + pcie4_default: pcie4-default-state { + clkreq-n-pins { + pins = "gpio147"; + function = "pcie4_clk"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio146"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio148"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + pcie6a_default: pcie6a-default-state { + clkreq-n-pins { + pins = "gpio153"; + function = "pcie6a_clk"; + drive-strength = <2>; + bias-pull-up; + }; + + perst-n-pins { + pins = "gpio152"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wake-n-pins { + pins = "gpio154"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + + rtmr1_default: rtmr1-reset-n-active-state { + pins = "gpio176"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + tpad_default: tpad-default-state { + pins = "gpio3"; + function = "gpio"; + bias-pull-up; + }; + + ts0_default: ts0-default-state { + int-n-pins { + pins = "gpio51"; + function = "gpio"; + bias-pull-up; + }; + + reset-n-pins { + pins = "gpio48"; + function = "gpio"; + output-high; + drive-strength = <16>; + }; + }; + + usb1_pwr_1p15_reg_en: usb1-pwr-1p15-reg-en-state { + pins = "gpio188"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + usb1_pwr_1p8_reg_en: usb1-pwr-1p8-reg-en-state { + pins = "gpio175"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + usb1_pwr_3p3_reg_en: usb1-pwr-3p3-reg-en-state { + pins = "gpio186"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wcd_default: wcd-reset-n-active-state { + pins = "gpio191"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + output-low; + }; + + wcn_sw_en: wcn-sw-en-state { + pins = "gpio214"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wcn_wlan_bt_en: wcn-wlan-bt-en-state { + pins = "gpio116", "gpio117"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; +}; + +&uart14 { + status = "okay"; + + bluetooth { + compatible = "qcom,wcn6855-bt"; + max-speed = <3200000>; + + vddrfacmn-supply = <&vreg_pmu_rfa_cmn_0p8>; + vddaon-supply = <&vreg_pmu_aon_0p8>; + vddwlcx-supply = <&vreg_pmu_wlcx_0p8>; + vddwlmx-supply = <&vreg_pmu_wlmx_0p8>; + vddbtcmx-supply = <&vreg_pmu_btcmx_0p8>; + vddrfa0p8-supply = <&vreg_pmu_rfa_0p8>; + vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>; + vddrfa1p8-supply = <&vreg_pmu_rfa_1p7>; + }; +}; + +&usb_1_ss0_hsphy { + vdd-supply = <&vreg_l3j_0p8>; + vdda12-supply = <&vreg_l2j_1p2>; + + phys = <&smb2360_0_eusb2_repeater>; + + status = "okay"; +}; + +&usb_1_ss0_qmpphy { + vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-pll-supply = <&vreg_l1j_0p8>; + + status = "okay"; +}; + +&usb_1_ss0 { + status = "okay"; +}; + +&usb_1_ss0_dwc3 { + dr_mode = "host"; +}; + +&usb_1_ss0_dwc3_hs { + remote-endpoint = <&pmic_glink_ss0_hs_in>; +}; + +&usb_1_ss0_qmpphy_out { + remote-endpoint = <&retimer_ss0_ss_in>; +}; + +&usb_1_ss1_hsphy { + vdd-supply = <&vreg_l3j_0p8>; + vdda12-supply = <&vreg_l2j_1p2>; + + phys = <&smb2360_1_eusb2_repeater>; + + status = "okay"; +}; + +&usb_1_ss1_qmpphy { + vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-pll-supply = <&vreg_l2d_0p9>; + + status = "okay"; +}; + +&usb_1_ss1 { + status = "okay"; +}; + +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + +&usb_1_ss1_dwc3_hs { + remote-endpoint = <&pmic_glink_ss1_hs_in>; +}; + +&usb_1_ss1_qmpphy_out { + remote-endpoint = <&retimer_ss1_ss_in>; +}; + +&usb_mp { + status = "okay"; +}; + +&usb_mp_dwc3 { + phys = <&usb_mp_hsphy0>, <&usb_mp_qmpphy0>; + phy-names = "usb2-0", "usb3-0"; +}; + +&usb_mp_hsphy0 { + vdd-supply = <&vreg_l2e_0p8>; + vdda12-supply = <&vreg_l3e_1p2>; + + phys = <&eusb3_repeater>; + + status = "okay"; +}; + +&usb_mp_qmpphy0 { + vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-pll-supply = <&vreg_l3c_0p8>; + + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts index ca5a808f2c7d..a3d53f2ba2c3 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts @@ -6,6 +6,7 @@ /dts-v1/; #include +#include #include #include "x1e80100.dtsi" @@ -23,6 +24,21 @@ stdout-path = "serial0:115200n8"; }; + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-0 = <&hall_int_n_default>; + pinctrl-names = "default"; + + switch-lid { + gpios = <&tlmm 92 GPIO_ACTIVE_LOW>; + linux,input-type = ; + linux,code = ; + wakeup-source; + wakeup-event-action = ; + }; + }; + pmic-glink { compatible = "qcom,x1e80100-pmic-glink", "qcom,sm8550-pmic-glink", @@ -717,11 +733,19 @@ status = "okay"; }; +&smb2360_0 { + status = "okay"; +}; + &smb2360_0_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l2b_3p0>; }; +&smb2360_1 { + status = "okay"; +}; + &smb2360_1_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l14b_3p0>; @@ -811,6 +835,28 @@ bias-disable; }; + hall_int_n_default: hall-int-n-state { + lid-n-pins { + pins = "gpio92"; + function = "gpio"; + bias-disable; + }; + + /* + * Pins 71 and 92 seem to be bridged together (pin 71 and 92 show the same + * events). By default, pin 71 is set as output-high, which blocks any + * event on pin 92. Output-disable on pin 71 is necessary to get events on + * pin 92. + * The purpose of pin 71 is not yet known; lid-pull is a supposition. + */ + lid-pull-n-pins { + pins = "gpio71"; + function = "gpio"; + bias-pull-up; + output-disable; + }; + }; + kybd_default: kybd-default-state { pins = "gpio67"; function = "gpio"; @@ -908,7 +954,7 @@ }; &usb_1_ss0_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l1j_0p8>; status = "okay"; @@ -940,7 +986,7 @@ }; &usb_1_ss1_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l2d_0p9>; status = "okay"; @@ -972,7 +1018,7 @@ }; &usb_1_ss2_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l2d_0p9>; status = "okay"; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi b/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi index 6835fdeef3ae..5867953c7356 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi @@ -22,6 +22,33 @@ i2c7 = &i2c7; }; + wcd938x: audio-codec { + compatible = "qcom,wcd9385-codec"; + + reset-gpios = <&tlmm 191 GPIO_ACTIVE_LOW>; + + qcom,micbias1-microvolt = <1800000>; + qcom,micbias2-microvolt = <1800000>; + qcom,micbias3-microvolt = <1800000>; + qcom,micbias4-microvolt = <1800000>; + qcom,mbhc-buttons-vthreshold-microvolt = <75000 150000 237000 500000 500000 500000 500000 500000>; + qcom,mbhc-headset-vthreshold-microvolt = <1700000>; + qcom,mbhc-headphone-vthreshold-microvolt = <50000>; + qcom,rx-device = <&wcd_rx>; + qcom,tx-device = <&wcd_tx>; + + + vdd-buck-supply = <&vreg_l15b>; + vdd-rxtx-supply = <&vreg_l15b>; + vdd-io-supply = <&vreg_l15b>; + vdd-mic-bias-supply = <&vreg_bob1>; + + pinctrl-0 = <&wcd_default>; + pinctrl-names = "default"; + + #sound-dai-cells = <1>; + }; + backlight: backlight { compatible = "pwm-backlight"; pwms = <&pmk8550_pwm 0 5000000>; @@ -97,7 +124,15 @@ reg = <1>; pmic_glink_ss0_ss_in: endpoint { - remote-endpoint = <&usb_1_ss0_qmpphy_out>; + remote-endpoint = <&retimer_ss0_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_ss0_con_sbu_in: endpoint { + remote-endpoint = <&retimer_ss0_con_sbu_out>; }; }; }; @@ -126,7 +161,15 @@ reg = <1>; pmic_glink_ss1_ss_in: endpoint { - remote-endpoint = <&usb_1_ss1_qmpphy_out>; + remote-endpoint = <&retimer_ss1_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + pmic_glink_ss1_con_sbu_in: endpoint { + remote-endpoint = <&retimer_ss1_con_sbu_out>; }; }; }; @@ -158,6 +201,109 @@ regulator-boot-on; }; + vreg_rtmr0_1p15: regulator-rtmr0-1p15 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_1P15"; + + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; + + gpio = <&pmc8380_5_gpios 8 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr0_1p15_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr0_1p8: regulator-rtmr0-1p8 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_1P8"; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + gpio = <&pm8550ve_9_gpios 8 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr0_1p8_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr0_3p3: regulator-rtmr0-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR0_3P3"; + + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&pm8550_gpios 11 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr0_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_1p15: regulator-rtmr1-1p15 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_1P15"; + + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; + + gpio = <&tlmm 188 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr1_1p15_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_1p8: regulator-rtmr1-1p8 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_1P8"; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + gpio = <&tlmm 175 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr1_1p8_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_rtmr1_3p3: regulator-rtmr1-3p3 { + compatible = "regulator-fixed"; + + regulator-name = "VREG_RTMR1_3P3"; + + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&tlmm 186 GPIO_ACTIVE_HIGH>; + enable-active-high; + + pinctrl-0 = <&rtmr1_3p3_reg_en>; + pinctrl-names = "default"; + + regulator-boot-on; + }; + + vreg_nvme: regulator-nvme { compatible = "regulator-fixed"; @@ -184,6 +330,86 @@ regulator-always-on; regulator-boot-on; }; + + sound { + compatible = "qcom,x1e80100-sndcard"; + model = "X1E80100-Romulus"; + audio-routing = "SpkrLeft IN", "WSA WSA_SPK1 OUT", + "SpkrRight IN", "WSA WSA_SPK2 OUT", + "IN1_HPHL", "HPHL_OUT", + "IN2_HPHR", "HPHR_OUT", + "AMIC2", "MIC BIAS2", + "VA DMIC0", "MIC BIAS3", + "VA DMIC1", "MIC BIAS3", + "VA DMIC0", "VA MIC BIAS3", + "VA DMIC1", "VA MIC BIAS3", + "TX SWR_INPUT1", "ADC2_OUTPUT"; + + va-dai-link { + link-name = "VA Capture"; + + cpu { + sound-dai = <&q6apmbedai VA_CODEC_DMA_TX_0>; + }; + + codec { + sound-dai = <&lpass_vamacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wcd-capture-dai-link { + link-name = "WCD Capture"; + + cpu { + sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>; + }; + + codec { + sound-dai = <&wcd938x 1>, <&swr2 1>, <&lpass_txmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wcd-playback-dai-link { + link-name = "WCD Playback"; + + cpu { + sound-dai = <&q6apmbedai RX_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&wcd938x 0>, <&swr1 0>, <&lpass_rxmacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + + wsa-dai-link { + link-name = "WSA Playback"; + + cpu { + sound-dai = <&q6apmbedai WSA_CODEC_DMA_RX_0>; + }; + + codec { + sound-dai = <&left_spkr>, <&right_spkr>, + <&swr0 0>, <&lpass_wsamacro 0>; + }; + + platform { + sound-dai = <&q6apm>; + }; + }; + }; }; &apps_rsc { @@ -558,7 +784,59 @@ status = "okay"; - /* PS8830 USB retimer @8 */ + /* Left-side rear port */ + typec-mux@8 { + compatible = "parade,ps8830"; + reg = <0x8>; + + reset-gpios = <&pm8550_gpios 10 GPIO_ACTIVE_LOW>; + + clocks = <&rpmhcc RPMH_RF_CLK3>; + clock-names = "xo"; + + vdd-supply = <&vreg_rtmr0_1p15>; + vdd33-supply = <&vreg_rtmr0_3p3>; + vdd33-cap-supply = <&vreg_rtmr0_3p3>; + vddar-supply = <&vreg_rtmr0_1p15>; + vddat-supply = <&vreg_rtmr0_1p15>; + vddio-supply = <&vreg_rtmr0_1p8>; + + pinctrl-0 = <&rtmr0_default>; + pinctrl-names = "default"; + + retimer-switch; + orientation-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + retimer_ss0_ss_out: endpoint { + remote-endpoint = <&pmic_glink_ss0_ss_in>; + }; + }; + + port@1 { + reg = <1>; + + retimer_ss0_ss_in: endpoint { + remote-endpoint = <&usb_1_ss0_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + retimer_ss0_con_sbu_out: endpoint { + remote-endpoint = <&pmic_glink_ss0_con_sbu_in>; + }; + }; + }; + }; + }; &i2c4 { @@ -592,7 +870,74 @@ status = "okay"; - /* PS8830 USB retimer @8 */ + /* Left-side front port */ + typec-mux@8 { + compatible = "parade,ps8830"; + reg = <0x8>; + + reset-gpios = <&tlmm 176 GPIO_ACTIVE_LOW>; + + clocks = <&rpmhcc RPMH_RF_CLK4>; + clock-names = "xo"; + + vdd-supply = <&vreg_rtmr1_1p15>; + vdd33-supply = <&vreg_rtmr1_3p3>; + vdd33-cap-supply = <&vreg_rtmr1_3p3>; + vddar-supply = <&vreg_rtmr1_1p15>; + vddat-supply = <&vreg_rtmr1_1p15>; + vddio-supply = <&vreg_rtmr1_1p8>; + + retimer-switch; + orientation-switch; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + retimer_ss1_ss_out: endpoint { + remote-endpoint = <&pmic_glink_ss1_ss_in>; + }; + }; + + port@1 { + reg = <1>; + + retimer_ss1_ss_in: endpoint { + remote-endpoint = <&usb_1_ss1_qmpphy_out>; + }; + }; + + port@2 { + reg = <2>; + + retimer_ss1_con_sbu_out: endpoint { + remote-endpoint = <&pmic_glink_ss1_con_sbu_in>; + }; + }; + }; + }; +}; + +&lpass_tlmm { + spkr_01_sd_n_active: spkr-01-sd-n-active-state { + pins = "gpio12"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + output-low; + }; +}; + +&lpass_vamacro { + qcom,dmic-sample-rate = <4800000>; + + vdd-micb-supply = <&vreg_l1b>; + + pinctrl-0 = <&dmic01_default>; + pinctrl-names = "default"; }; &mdss { @@ -641,6 +986,25 @@ status = "okay"; }; +&pcie3 { + perst-gpios = <&tlmm 143 GPIO_ACTIVE_LOW>; + wake-gpios = <&tlmm 145 GPIO_ACTIVE_HIGH>; + + pinctrl-0 = <&pcie3_default>; + pinctrl-names = "default"; + + /* The RTS5261 chip on the other side only does Gen1x1 anyway */ + max-link-speed = <1>; + status = "okay"; +}; + +&pcie3_phy { + vdda-phy-supply = <&vreg_l3c>; + vdda-pll-supply = <&vreg_l3e>; + + status = "okay"; +}; + &pcie4 { status = "okay"; }; @@ -671,6 +1035,28 @@ status = "okay"; }; +&pm8550_gpios { + rtmr0_default: rtmr0-reset-n-active-state { + pins = "gpio10"; + function = "normal"; + power-source = <1>; /* 1.8V */ + }; + + rtmr0_3p3_reg_en: rtmr0-3p3-reg-en-state { + pins = "gpio11"; + function = "normal"; + power-source = <1>; /* 1.8V */ + }; +}; + +&pm8550ve_9_gpios { + rtmr0_1p8_reg_en: rtmr0-1p8-reg-en-state { + pins = "gpio8"; + function = "normal"; + power-source = <1>; /* 1.8V */ + }; +}; + &pmc8380_3_gpios { edp_bl_en: edp-bl-en-state { pins = "gpio4"; @@ -681,6 +1067,14 @@ }; }; +&pmc8380_5_gpios { + rtmr0_1p15_reg_en: rtmr0-1p15-reg-en-state { + pins = "gpio8"; + function = "normal"; + power-source = <1>; /* 1.8V */ + }; +}; + &pmk8550_pwm { status = "okay"; }; @@ -706,23 +1100,31 @@ &remoteproc_adsp { firmware-name = "qcom/x1e80100/microsoft/Romulus/qcadsp8380.mbn", - "qcom/x1e80100/microsoft/Romulus/adsp_dtb.mbn"; + "qcom/x1e80100/microsoft/Romulus/adsp_dtbs.elf"; status = "okay"; }; &remoteproc_cdsp { firmware-name = "qcom/x1e80100/microsoft/Romulus/qccdsp8380.mbn", - "qcom/x1e80100/microsoft/Romulus/cdsp_dtb.mbn"; + "qcom/x1e80100/microsoft/Romulus/cdsp_dtbs.elf"; status = "okay"; }; +&smb2360_0 { + status = "okay"; +}; + &smb2360_0_eusb2_repeater { vdd18-supply = <&vreg_l3d>; vdd3-supply = <&vreg_l2b>; }; +&smb2360_1 { + status = "okay"; +}; + &smb2360_1_eusb2_repeater { vdd18-supply = <&vreg_l3d>; vdd3-supply = <&vreg_l14b>; @@ -737,6 +1139,59 @@ vdd3-supply = <&vreg_l8b>; }; +&swr0 { + pinctrl-0 = <&wsa_swr_active>, <&spkr_01_sd_n_active>; + pinctrl-names = "default"; + + status = "okay"; + + /* WSA8845, Left speaker */ + left_spkr: speaker@0,0 { + compatible = "sdw20217020400"; + reg = <0 0>; + reset-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>; + #sound-dai-cells = <0>; + sound-name-prefix = "SpkrLeft"; + vdd-1p8-supply = <&vreg_l15b>; + vdd-io-supply = <&vreg_l12b>; + qcom,port-mapping = <1 2 3 7 10 13>; + }; + + /* WSA8845, Right speaker */ + right_spkr: speaker@0,1 { + compatible = "sdw20217020400"; + reg = <0 1>; + reset-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>; + #sound-dai-cells = <0>; + sound-name-prefix = "SpkrRight"; + vdd-1p8-supply = <&vreg_l15b>; + vdd-io-supply = <&vreg_l12b>; + qcom,port-mapping = <4 5 6 7 11 13>; + }; +}; + +&swr1 { + status = "okay"; + + /* WCD9385 RX */ + wcd_rx: codec@0,4 { + compatible = "sdw20217010d00"; + reg = <0 4>; + qcom,rx-port-mapping = <1 2 3 4 5>; + }; +}; + +&swr2 { + status = "okay"; + + /* WCD9385 TX */ + wcd_tx: codec@0,3 { + compatible = "sdw20217010d00"; + reg = <0 3>; + qcom,tx-port-mapping = <2 2 3 4>; + }; +}; + &tlmm { gpio-reserved-ranges = <44 4>, /* SPI (TPM) */ <238 1>; /* UFS Reset */ @@ -767,6 +1222,29 @@ bias-disable; }; + pcie3_default: pcie3-default-state { + perst-n-pins { + pins = "gpio143"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + clkreq-n-pins { + pins = "gpio144"; + function = "pcie3_clk"; + drive-strength = <2>; + bias-pull-up; + }; + + wake-n-pins { + pins = "gpio145"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + }; + pcie6a_default: pcie6a-default-state { perst-n-pins { pins = "gpio152"; @@ -790,6 +1268,35 @@ }; }; + rtmr1_1p8_reg_en: rtmr1-1p8-reg-en-state { + pins = "gpio175"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr1_3p3_reg_en: rtmr1-3p3-reg-en-state { + pins = "gpio186"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + rtmr1_1p15_reg_en: rtmr1-1p15-reg-en-state { + pins = "gpio188"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + + wcd_default: wcd-reset-n-active-state { + pins = "gpio191"; + function = "gpio"; + drive-strength = <16>; + bias-disable; + output-low; + }; + cam_indicator_en: cam-indicator-en-state { pins = "gpio225"; function = "gpio"; @@ -823,7 +1330,7 @@ }; &usb_1_ss0_qmpphy { - vdda-phy-supply = <&vreg_l3e>; + vdda-phy-supply = <&vreg_l2j>; vdda-pll-supply = <&vreg_l1j>; status = "okay"; @@ -842,7 +1349,7 @@ }; &usb_1_ss0_qmpphy_out { - remote-endpoint = <&pmic_glink_ss0_ss_in>; + remote-endpoint = <&retimer_ss0_ss_in>; }; &usb_1_ss1_hsphy { @@ -855,7 +1362,7 @@ }; &usb_1_ss1_qmpphy { - vdda-phy-supply = <&vreg_l3e>; + vdda-phy-supply = <&vreg_l2j>; vdda-pll-supply = <&vreg_l2d>; status = "okay"; @@ -874,7 +1381,7 @@ }; &usb_1_ss1_qmpphy_out { - remote-endpoint = <&pmic_glink_ss1_ss_in>; + remote-endpoint = <&retimer_ss1_ss_in>; }; /* MP0 goes to the Surface Connector, MP1 goes to the USB-A port */ diff --git a/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi b/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi index 5b54ee79f048..d7a2a2b8fc6c 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi @@ -491,6 +491,8 @@ #address-cells = <1>; #size-cells = <0>; + status = "disabled"; + smb2360_0_eusb2_repeater: phy@fd00 { compatible = "qcom,smb2360-eusb2-repeater"; reg = <0xfd00>; @@ -504,6 +506,8 @@ #address-cells = <1>; #size-cells = <0>; + status = "disabled"; + smb2360_1_eusb2_repeater: phy@fd00 { compatible = "qcom,smb2360-eusb2-repeater"; reg = <0xfd00>; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts index 5ef030c60abe..ec594628304a 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts @@ -84,6 +84,14 @@ remote-endpoint = <&usb_1_ss0_qmpphy_out>; }; }; + + port@2 { + reg = <2>; + + pmic_glink_ss0_sbu: endpoint { + remote-endpoint = <&usb_1_ss0_sbu_mux>; + }; + }; }; }; @@ -112,6 +120,14 @@ remote-endpoint = <&usb_1_ss1_qmpphy_out>; }; }; + + port@2 { + reg = <2>; + + pmic_glink_ss1_sbu: endpoint { + remote-endpoint = <&usb_1_ss1_sbu_mux>; + }; + }; }; }; @@ -140,6 +156,14 @@ remote-endpoint = <&usb_1_ss2_qmpphy_out>; }; }; + + port@2 { + reg = <2>; + + pmic_glink_ss2_sbu: endpoint { + remote-endpoint = <&usb_1_ss2_sbu_mux>; + }; + }; }; }; }; @@ -256,6 +280,63 @@ regulator-boot-on; }; + + usb-1-ss0-sbu-mux { + compatible = "onnn,fsusb42", "gpio-sbu-mux"; + + enable-gpios = <&tlmm 168 GPIO_ACTIVE_LOW>; + select-gpios = <&tlmm 167 GPIO_ACTIVE_HIGH>; + + pinctrl-0 = <&usb_1_ss0_sbu_default>; + pinctrl-names = "default"; + + mode-switch; + orientation-switch; + + port { + usb_1_ss0_sbu_mux: endpoint { + remote-endpoint = <&pmic_glink_ss0_sbu>; + }; + }; + }; + + usb-1-ss1-sbu-mux { + compatible = "onnn,fsusb42", "gpio-sbu-mux"; + + enable-gpios = <&tlmm 179 GPIO_ACTIVE_LOW>; + select-gpios = <&tlmm 178 GPIO_ACTIVE_HIGH>; + + pinctrl-0 = <&usb_1_ss1_sbu_default>; + pinctrl-names = "default"; + + mode-switch; + orientation-switch; + + port { + usb_1_ss1_sbu_mux: endpoint { + remote-endpoint = <&pmic_glink_ss1_sbu>; + }; + }; + }; + + usb-1-ss2-sbu-mux { + compatible = "onnn,fsusb42", "gpio-sbu-mux"; + + enable-gpios = <&tlmm 171 GPIO_ACTIVE_LOW>; + select-gpios = <&tlmm 170 GPIO_ACTIVE_HIGH>; + + pinctrl-0 = <&usb_1_ss2_sbu_default>; + pinctrl-names = "default"; + + mode-switch; + orientation-switch; + + port { + usb_1_ss2_sbu_mux: endpoint { + remote-endpoint = <&pmic_glink_ss2_sbu>; + }; + }; + }; }; &apps_rsc { @@ -616,6 +697,40 @@ }; }; +&i2c5 { + clock-frequency = <400000>; + + status = "okay"; + + eusb3_repeater: redriver@47 { + compatible = "nxp,ptn3222"; + reg = <0x47>; + #phy-cells = <0>; + + vdd3v3-supply = <&vreg_l13b_3p0>; + vdd1v8-supply = <&vreg_l4b_1p8>; + + reset-gpios = <&tlmm 6 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&eusb3_reset_n>; + pinctrl-names = "default"; + }; + + eusb6_repeater: redriver@4f { + compatible = "nxp,ptn3222"; + reg = <0x4f>; + #phy-cells = <0>; + + vdd3v3-supply = <&vreg_l13b_3p0>; + vdd1v8-supply = <&vreg_l4b_1p8>; + + reset-gpios = <&tlmm 184 GPIO_ACTIVE_LOW>; + + pinctrl-0 = <&eusb6_reset_n>; + pinctrl-names = "default"; + }; +}; + &lpass_tlmm { spkr_01_sd_n_active: spkr-01-sd-n-active-state { pins = "gpio12"; @@ -630,6 +745,30 @@ status = "okay"; }; +&mdss_dp0 { + status = "okay"; +}; + +&mdss_dp0_out { + data-lanes = <0 1>; +}; + +&mdss_dp1 { + status = "okay"; +}; + +&mdss_dp1_out { + data-lanes = <0 1>; +}; + +&mdss_dp2 { + status = "okay"; +}; + +&mdss_dp2_out { + data-lanes = <0 1>; +}; + &mdss_dp3 { compatible = "qcom,x1e80100-dp"; /delete-property/ #sound-dai-cells; @@ -731,11 +870,32 @@ status = "okay"; }; +&smb2360_0 { + status = "okay"; +}; + +&sdhc_2 { + cd-gpios = <&tlmm 71 GPIO_ACTIVE_LOW>; + pinctrl-0 = <&sdc2_default &sdc2_card_det_n>; + pinctrl-1 = <&sdc2_sleep &sdc2_card_det_n>; + pinctrl-names = "default", "sleep"; + vmmc-supply = <&vreg_l9b_2p9>; + vqmmc-supply = <&vreg_l6b_1p8>; + bus-width = <4>; + no-sdio; + no-mmc; + status = "okay"; +}; + &smb2360_0_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l2b_3p0>; }; +&smb2360_1 { + status = "okay"; +}; + &smb2360_1_eusb2_repeater { vdd18-supply = <&vreg_l3d_1p8>; vdd3-supply = <&vreg_l14b_3p0>; @@ -819,6 +979,22 @@ bias-disable; }; + eusb3_reset_n: eusb3-reset-n-state { + pins = "gpio6"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + output-low; + }; + + eusb6_reset_n: eusb6-reset-n-state { + pins = "gpio184"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + output-low; + }; + nvme_reg_en: nvme-reg-en-state { pins = "gpio18"; function = "gpio"; @@ -872,6 +1048,86 @@ }; }; + sdc2_card_det_n: sdc2-card-det-state { + pins = "gpio71"; + function = "gpio"; + drive-strength = <2>; + bias-pull-up; + }; + + usb_1_ss0_sbu_default: usb-1-ss0-sbu-state { + mode-pins { + pins = "gpio166"; + function = "gpio"; + bias-disable; + drive-strength = <2>; + output-high; + }; + + oe-n-pins { + pins = "gpio168"; + function = "gpio"; + bias-disable; + drive-strength = <2>; + }; + + sel-pins { + pins = "gpio167"; + function = "gpio"; + bias-disable; + drive-strength = <2>; + }; + + }; + + usb_1_ss1_sbu_default: usb-1-ss1-sbu-state { + mode-pins { + pins = "gpio177"; + function = "gpio"; + bias-disable; + drive-strength = <2>; + output-high; + }; + + oe-n-pins { + pins = "gpio179"; + function = "gpio"; + bias-disable; + drive-strength = <2>; + }; + + sel-pins { + pins = "gpio178"; + function = "gpio"; + bias-disable; + drive-strength = <2>; + }; + }; + + usb_1_ss2_sbu_default: usb-1-ss2-sbu-state { + mode-pins { + pins = "gpio169"; + function = "gpio"; + bias-disable; + drive-strength = <2>; + output-high; + }; + + oe-n-pins { + pins = "gpio171"; + function = "gpio"; + bias-disable; + drive-strength = <2>; + }; + + sel-pins { + pins = "gpio170"; + function = "gpio"; + bias-disable; + drive-strength = <2>; + }; + }; + wcd_default: wcd-reset-n-active-state { pins = "gpio191"; function = "gpio"; @@ -896,7 +1152,7 @@ }; &usb_1_ss0_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l1j_0p8>; status = "okay"; @@ -928,7 +1184,7 @@ }; &usb_1_ss1_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l2d_0p9>; status = "okay"; @@ -960,7 +1216,7 @@ }; &usb_1_ss2_qmpphy { - vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-phy-supply = <&vreg_l2j_1p2>; vdda-pll-supply = <&vreg_l2d_0p9>; status = "okay"; @@ -981,3 +1237,39 @@ &usb_1_ss2_qmpphy_out { remote-endpoint = <&pmic_glink_ss2_ss_in>; }; + +&usb_mp { + status = "okay"; +}; + +&usb_mp_hsphy0 { + vdd-supply = <&vreg_l2e_0p8>; + vdda12-supply = <&vreg_l3e_1p2>; + + phys = <&eusb6_repeater>; + + status = "okay"; +}; + +&usb_mp_hsphy1 { + vdd-supply = <&vreg_l2e_0p8>; + vdda12-supply = <&vreg_l3e_1p2>; + + phys = <&eusb3_repeater>; + + status = "okay"; +}; + +&usb_mp_qmpphy0 { + vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-pll-supply = <&vreg_l3c_0p8>; + + status = "okay"; +}; + +&usb_mp_qmpphy1 { + vdda-phy-supply = <&vreg_l3e_1p2>; + vdda-pll-supply = <&vreg_l3c_0p8>; + + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index 88805629ed2b..4936fa5b98ff 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -38,7 +38,7 @@ sleep_clk: sleep-clk { compatible = "fixed-clock"; - clock-frequency = <32000>; + clock-frequency = <32764>; #clock-cells = <0>; }; @@ -303,6 +303,18 @@ }; }; + dummy-sink { + compatible = "arm,coresight-dummy-sink"; + + in-ports { + port { + eud_in: endpoint { + remote-endpoint = <&swao_rep_out1>; + }; + }; + }; + }; + firmware { scm: scm { compatible = "qcom,scm-x1e80100", "qcom,scm"; @@ -677,6 +689,34 @@ }; }; + qup_opp_table_100mhz: opp-table-qup100mhz { + compatible = "operating-points-v2"; + + opp-75000000 { + opp-hz = /bits/ 64 <75000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-100000000 { + opp-hz = /bits/ 64 <100000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + }; + + qup_opp_table_120mhz: opp-table-qup120mhz { + compatible = "operating-points-v2"; + + opp-75000000 { + opp-hz = /bits/ 64 <75000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-120000000 { + opp-hz = /bits/ 64 <120000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + }; + smp2p-adsp { compatible = "qcom,smp2p"; @@ -743,7 +783,7 @@ clocks = <&bi_tcxo_div2>, <&sleep_clk>, - <0>, + <&pcie3_phy>, <&pcie4_phy>, <&pcie5_phy>, <&pcie6a_phy>, @@ -831,6 +871,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma2 0 0 QCOM_GPI_I2C>, <&gpi_dma2 1 0 QCOM_GPI_I2C>; dma-names = "tx", @@ -864,6 +907,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_120mhz>; + dmas = <&gpi_dma2 0 0 QCOM_GPI_SPI>, <&gpi_dma2 1 0 QCOM_GPI_SPI>; dma-names = "tx", @@ -897,6 +943,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma2 0 1 QCOM_GPI_I2C>, <&gpi_dma2 1 1 QCOM_GPI_I2C>; dma-names = "tx", @@ -930,6 +979,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_120mhz>; + dmas = <&gpi_dma2 0 1 QCOM_GPI_SPI>, <&gpi_dma2 1 1 QCOM_GPI_SPI>; dma-names = "tx", @@ -963,6 +1015,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma2 0 2 QCOM_GPI_I2C>, <&gpi_dma2 1 2 QCOM_GPI_I2C>; dma-names = "tx", @@ -996,6 +1051,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma2 0 2 QCOM_GPI_SPI>, <&gpi_dma2 1 2 QCOM_GPI_SPI>; dma-names = "tx", @@ -1029,6 +1087,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma2 0 3 QCOM_GPI_I2C>, <&gpi_dma2 1 3 QCOM_GPI_I2C>; dma-names = "tx", @@ -1062,6 +1123,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma2 0 3 QCOM_GPI_SPI>, <&gpi_dma2 1 3 QCOM_GPI_SPI>; dma-names = "tx", @@ -1095,6 +1159,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma2 0 4 QCOM_GPI_I2C>, <&gpi_dma2 1 4 QCOM_GPI_I2C>; dma-names = "tx", @@ -1128,6 +1195,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma2 0 4 QCOM_GPI_SPI>, <&gpi_dma2 1 4 QCOM_GPI_SPI>; dma-names = "tx", @@ -1161,6 +1231,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma2 0 5 QCOM_GPI_I2C>, <&gpi_dma2 1 5 QCOM_GPI_I2C>; dma-names = "tx", @@ -1194,6 +1267,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma2 0 5 QCOM_GPI_SPI>, <&gpi_dma2 1 5 QCOM_GPI_SPI>; dma-names = "tx", @@ -1224,6 +1300,9 @@ interconnect-names = "qup-core", "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + pinctrl-0 = <&qup_uart21_default>; pinctrl-names = "default"; @@ -1249,6 +1328,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma2 0 6 QCOM_GPI_I2C>, <&gpi_dma2 1 6 QCOM_GPI_I2C>; dma-names = "tx", @@ -1282,6 +1364,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma2 0 6 QCOM_GPI_SPI>, <&gpi_dma2 1 6 QCOM_GPI_SPI>; dma-names = "tx", @@ -1315,6 +1400,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma2 0 7 QCOM_GPI_I2C>, <&gpi_dma2 1 7 QCOM_GPI_I2C>; dma-names = "tx", @@ -1348,6 +1436,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma2 0 7 QCOM_GPI_SPI>, <&gpi_dma2 1 7 QCOM_GPI_SPI>; dma-names = "tx", @@ -1425,6 +1516,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 0 QCOM_GPI_I2C>, <&gpi_dma1 1 0 QCOM_GPI_I2C>; dma-names = "tx", @@ -1458,6 +1552,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_120mhz>; + dmas = <&gpi_dma1 0 0 QCOM_GPI_SPI>, <&gpi_dma1 1 0 QCOM_GPI_SPI>; dma-names = "tx", @@ -1491,6 +1588,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 1 QCOM_GPI_I2C>, <&gpi_dma1 1 1 QCOM_GPI_I2C>; dma-names = "tx", @@ -1524,6 +1624,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_120mhz>; + dmas = <&gpi_dma1 0 1 QCOM_GPI_SPI>, <&gpi_dma1 1 1 QCOM_GPI_SPI>; dma-names = "tx", @@ -1557,6 +1660,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 2 QCOM_GPI_I2C>, <&gpi_dma1 1 2 QCOM_GPI_I2C>; dma-names = "tx", @@ -1590,6 +1696,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma1 0 2 QCOM_GPI_SPI>, <&gpi_dma1 1 2 QCOM_GPI_SPI>; dma-names = "tx", @@ -1623,6 +1732,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 3 QCOM_GPI_I2C>, <&gpi_dma1 1 3 QCOM_GPI_I2C>; dma-names = "tx", @@ -1656,6 +1768,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma1 0 3 QCOM_GPI_SPI>, <&gpi_dma1 1 3 QCOM_GPI_SPI>; dma-names = "tx", @@ -1689,6 +1804,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 4 QCOM_GPI_I2C>, <&gpi_dma1 1 4 QCOM_GPI_I2C>; dma-names = "tx", @@ -1722,6 +1840,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma1 0 4 QCOM_GPI_SPI>, <&gpi_dma1 1 4 QCOM_GPI_SPI>; dma-names = "tx", @@ -1755,6 +1876,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 5 QCOM_GPI_I2C>, <&gpi_dma1 1 5 QCOM_GPI_I2C>; dma-names = "tx", @@ -1788,6 +1912,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma1 0 5 QCOM_GPI_SPI>, <&gpi_dma1 1 5 QCOM_GPI_SPI>; dma-names = "tx", @@ -1821,6 +1948,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 6 QCOM_GPI_I2C>, <&gpi_dma1 1 6 QCOM_GPI_I2C>; dma-names = "tx", @@ -1854,6 +1984,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma1 0 6 QCOM_GPI_SPI>, <&gpi_dma1 1 6 QCOM_GPI_SPI>; dma-names = "tx", @@ -1868,6 +2001,31 @@ status = "disabled"; }; + uart14: serial@a98000 { + compatible = "qcom,geni-uart"; + reg = <0 0x00a98000 0 0x4000>; + + interrupts = ; + + clocks = <&gcc GCC_QUPV3_WRAP1_S6_CLK>; + clock-names = "se"; + + interconnects = <&clk_virt MASTER_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_1 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; + + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + + pinctrl-0 = <&qup_uart14_default>; + pinctrl-names = "default"; + + status = "disabled"; + }; + i2c15: i2c@a9c000 { compatible = "qcom,geni-i2c"; reg = <0 0x00a9c000 0 0x4000>; @@ -1887,6 +2045,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma1 0 7 QCOM_GPI_I2C>, <&gpi_dma1 1 7 QCOM_GPI_I2C>; dma-names = "tx", @@ -1920,6 +2081,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma1 0 7 QCOM_GPI_SPI>, <&gpi_dma1 1 7 QCOM_GPI_SPI>; dma-names = "tx", @@ -1996,6 +2160,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma0 0 0 QCOM_GPI_I2C>, <&gpi_dma0 1 0 QCOM_GPI_I2C>; dma-names = "tx", @@ -2029,6 +2196,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_120mhz>; + dmas = <&gpi_dma0 0 0 QCOM_GPI_SPI>, <&gpi_dma0 1 0 QCOM_GPI_SPI>; dma-names = "tx", @@ -2062,6 +2232,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma0 0 1 QCOM_GPI_I2C>, <&gpi_dma0 1 1 QCOM_GPI_I2C>; dma-names = "tx", @@ -2095,6 +2268,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_120mhz>; + dmas = <&gpi_dma0 0 1 QCOM_GPI_SPI>, <&gpi_dma0 1 1 QCOM_GPI_SPI>; dma-names = "tx", @@ -2128,6 +2304,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma0 0 2 QCOM_GPI_I2C>, <&gpi_dma0 1 2 QCOM_GPI_I2C>; dma-names = "tx", @@ -2158,6 +2337,9 @@ interconnect-names = "qup-core", "qup-config"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + pinctrl-0 = <&qup_uart2_default>; pinctrl-names = "default"; @@ -2183,6 +2365,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma0 0 2 QCOM_GPI_SPI>, <&gpi_dma0 1 2 QCOM_GPI_SPI>; dma-names = "tx", @@ -2216,6 +2401,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma0 0 3 QCOM_GPI_I2C>, <&gpi_dma0 1 3 QCOM_GPI_I2C>; dma-names = "tx", @@ -2249,6 +2437,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma0 0 3 QCOM_GPI_SPI>, <&gpi_dma0 1 3 QCOM_GPI_SPI>; dma-names = "tx", @@ -2282,6 +2473,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma0 0 4 QCOM_GPI_I2C>, <&gpi_dma0 1 4 QCOM_GPI_I2C>; dma-names = "tx", @@ -2315,6 +2509,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma0 0 4 QCOM_GPI_SPI>, <&gpi_dma0 1 4 QCOM_GPI_SPI>; dma-names = "tx", @@ -2348,6 +2545,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma0 0 5 QCOM_GPI_I2C>, <&gpi_dma0 1 5 QCOM_GPI_I2C>; dma-names = "tx", @@ -2381,6 +2581,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma0 0 5 QCOM_GPI_SPI>, <&gpi_dma0 1 5 QCOM_GPI_SPI>; dma-names = "tx", @@ -2414,6 +2617,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma0 0 6 QCOM_GPI_I2C>, <&gpi_dma0 1 6 QCOM_GPI_I2C>; dma-names = "tx", @@ -2447,6 +2653,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma0 0 6 QCOM_GPI_SPI>, <&gpi_dma0 1 6 QCOM_GPI_SPI>; dma-names = "tx", @@ -2480,6 +2689,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + required-opps = <&rpmhpd_opp_low_svs>; + dmas = <&gpi_dma0 0 7 QCOM_GPI_I2C>, <&gpi_dma0 1 7 QCOM_GPI_I2C>; dma-names = "tx", @@ -2513,6 +2725,9 @@ "qup-config", "qup-memory"; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&qup_opp_table_100mhz>; + dmas = <&gpi_dma0 0 7 QCOM_GPI_SPI>, <&gpi_dma0 1 7 QCOM_GPI_SPI>; dma-names = "tx", @@ -2906,6 +3121,208 @@ #interconnect-cells = <2>; }; + pcie3: pcie@1bd0000 { + device_type = "pci"; + compatible = "qcom,pcie-x1e80100"; + reg = <0x0 0x01bd0000 0x0 0x3000>, + <0x0 0x78000000 0x0 0xf1d>, + <0x0 0x78000f40 0x0 0xa8>, + <0x0 0x78001000 0x0 0x1000>, + <0x0 0x78100000 0x0 0x100000>, + <0x0 0x01bd3000 0x0 0x1000>; + reg-names = "parf", + "dbi", + "elbi", + "atu", + "config", + "mhi"; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x0 0x78200000 0x0 0x100000>, + <0x02000000 0x0 0x78300000 0x0 0x78300000 0x0 0x3d00000>, + <0x03000000 0x7 0x40000000 0x7 0x40000000 0x0 0x40000000>; + bus-range = <0x00 0xff>; + + dma-coherent; + + linux,pci-domain = <3>; + num-lanes = <8>; + + interrupts = , + , + , + , + , + , + , + , + ; + interrupt-names = "msi0", + "msi1", + "msi2", + "msi3", + "msi4", + "msi5", + "msi6", + "msi7", + "global"; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc 0 0 GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc 0 0 GIC_SPI 221 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc 0 0 GIC_SPI 237 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc 0 0 GIC_SPI 238 IRQ_TYPE_LEVEL_HIGH>; + + clocks = <&gcc GCC_PCIE_3_AUX_CLK>, + <&gcc GCC_PCIE_3_CFG_AHB_CLK>, + <&gcc GCC_PCIE_3_MSTR_AXI_CLK>, + <&gcc GCC_PCIE_3_SLV_AXI_CLK>, + <&gcc GCC_PCIE_3_SLV_Q2A_AXI_CLK>, + <&gcc GCC_CFG_NOC_PCIE_ANOC_NORTH_AHB_CLK>, + <&gcc GCC_CNOC_PCIE_NORTH_SF_AXI_CLK>; + clock-names = "aux", + "cfg", + "bus_master", + "bus_slave", + "slave_q2a", + "noc_aggr", + "cnoc_sf_axi"; + + assigned-clocks = <&gcc GCC_PCIE_3_AUX_CLK>; + assigned-clock-rates = <19200000>; + + interconnects = <&pcie_north_anoc MASTER_PCIE_3 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &cnoc_main SLAVE_PCIE_3 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "pcie-mem", + "cpu-pcie"; + + resets = <&gcc GCC_PCIE_3_BCR>, + <&gcc GCC_PCIE_3_LINK_DOWN_BCR>; + reset-names = "pci", + "link_down"; + + power-domains = <&gcc GCC_PCIE_3_GDSC>; + + phys = <&pcie3_phy>; + phy-names = "pciephy"; + + operating-points-v2 = <&pcie3_opp_table>; + + status = "disabled"; + + pcie3_opp_table: opp-table { + compatible = "operating-points-v2"; + + /* GEN 1 x1 */ + opp-2500000 { + opp-hz = /bits/ 64 <2500000>; + required-opps = <&rpmhpd_opp_low_svs>; + opp-peak-kBps = <250000 1>; + }; + + /* GEN 1 x2 and GEN 2 x1 */ + opp-5000000 { + opp-hz = /bits/ 64 <5000000>; + required-opps = <&rpmhpd_opp_low_svs>; + opp-peak-kBps = <500000 1>; + }; + + /* GEN 1 x4 and GEN 2 x2 */ + opp-10000000 { + opp-hz = /bits/ 64 <10000000>; + required-opps = <&rpmhpd_opp_low_svs>; + opp-peak-kBps = <1000000 1>; + }; + + /* GEN 1 x8 and GEN 2 x4 */ + opp-20000000 { + opp-hz = /bits/ 64 <20000000>; + required-opps = <&rpmhpd_opp_low_svs>; + opp-peak-kBps = <2000000 1>; + }; + + /* GEN 2 x8 */ + opp-40000000 { + opp-hz = /bits/ 64 <40000000>; + required-opps = <&rpmhpd_opp_low_svs>; + opp-peak-kBps = <4000000 1>; + }; + + /* GEN 3 x1 */ + opp-8000000 { + opp-hz = /bits/ 64 <8000000>; + required-opps = <&rpmhpd_opp_svs>; + opp-peak-kBps = <984500 1>; + }; + + /* GEN 3 x2 and GEN 4 x1 */ + opp-16000000 { + opp-hz = /bits/ 64 <16000000>; + required-opps = <&rpmhpd_opp_svs>; + opp-peak-kBps = <1969000 1>; + }; + + /* GEN 3 x4 and GEN 4 x2 */ + opp-32000000 { + opp-hz = /bits/ 64 <32000000>; + required-opps = <&rpmhpd_opp_svs>; + opp-peak-kBps = <3938000 1>; + }; + + /* GEN 3 x8 and GEN 4 x4 */ + opp-64000000 { + opp-hz = /bits/ 64 <64000000>; + required-opps = <&rpmhpd_opp_svs>; + opp-peak-kBps = <7876000 1>; + }; + + /* GEN 4 x8 */ + opp-128000000 { + opp-hz = /bits/ 64 <128000000>; + required-opps = <&rpmhpd_opp_svs>; + opp-peak-kBps = <15753000 1>; + }; + }; + }; + + pcie3_phy: phy@1be0000 { + compatible = "qcom,x1e80100-qmp-gen4x8-pcie-phy"; + reg = <0 0x01be0000 0 0x10000>; + + clocks = <&gcc GCC_PCIE_3_PHY_AUX_CLK>, + <&gcc GCC_PCIE_3_CFG_AHB_CLK>, + <&tcsr TCSR_PCIE_8L_CLKREF_EN>, + <&gcc GCC_PCIE_3_PHY_RCHNG_CLK>, + <&gcc GCC_PCIE_3_PIPE_CLK>, + <&gcc GCC_PCIE_3_PIPEDIV2_CLK>; + clock-names = "aux", + "cfg_ahb", + "ref", + "rchng", + "pipe", + "pipediv2"; + + resets = <&gcc GCC_PCIE_3_PHY_BCR>, + <&gcc GCC_PCIE_3_NOCSR_COM_PHY_BCR>; + reset-names = "phy", + "phy_nocsr"; + + assigned-clocks = <&gcc GCC_PCIE_3_PHY_RCHNG_CLK>; + assigned-clock-rates = <100000000>; + + power-domains = <&gcc GCC_PCIE_3_PHY_GDSC>; + + #clock-cells = <0>; + clock-output-names = "pcie3_pipe_clk"; + + #phy-cells = <0>; + + status = "disabled"; + }; + pcie6a: pci@1bf8000 { device_type = "pci"; compatible = "qcom,pcie-x1e80100"; @@ -2924,7 +3341,7 @@ #address-cells = <3>; #size-cells = <2>; ranges = <0x01000000 0x0 0x00000000 0x0 0x70200000 0x0 0x100000>, - <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x1d00000>; + <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x3d00000>; bus-range = <0x00 0xff>; dma-coherent; @@ -3518,6 +3935,143 @@ #interconnect-cells = <2>; }; + remoteproc_adsp: remoteproc@6800000 { + compatible = "qcom,x1e80100-adsp-pas"; + reg = <0x0 0x06800000 0x0 0x10000>; + + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "wdog", + "fatal", + "ready", + "handover", + "stop-ack"; + + clocks = <&rpmhcc RPMH_CXO_CLK>; + clock-names = "xo"; + + power-domains = <&rpmhpd RPMHPD_LCX>, + <&rpmhpd RPMHPD_LMX>; + power-domain-names = "lcx", + "lmx"; + + interconnects = <&lpass_lpicx_noc MASTER_LPASS_PROC QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; + + memory-region = <&adspslpi_mem>, + <&q6_adsp_dtb_mem>; + + qcom,qmp = <&aoss_qmp>; + + qcom,smem-states = <&smp2p_adsp_out 0>; + qcom,smem-state-names = "stop"; + + status = "disabled"; + + glink-edge { + interrupts-extended = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP + IRQ_TYPE_EDGE_RISING>; + mboxes = <&ipcc IPCC_CLIENT_LPASS + IPCC_MPROC_SIGNAL_GLINK_QMP>; + + label = "lpass"; + qcom,remote-pid = <2>; + + fastrpc { + compatible = "qcom,fastrpc"; + qcom,glink-channels = "fastrpcglink-apps-dsp"; + label = "adsp"; + qcom,non-secure-domain; + #address-cells = <1>; + #size-cells = <0>; + + compute-cb@3 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <3>; + iommus = <&apps_smmu 0x1003 0x80>, + <&apps_smmu 0x1063 0x0>; + dma-coherent; + }; + + compute-cb@4 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <4>; + iommus = <&apps_smmu 0x1004 0x80>, + <&apps_smmu 0x1064 0x0>; + dma-coherent; + }; + + compute-cb@5 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <5>; + iommus = <&apps_smmu 0x1005 0x80>, + <&apps_smmu 0x1065 0x0>; + dma-coherent; + }; + + compute-cb@6 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <6>; + iommus = <&apps_smmu 0x1006 0x80>, + <&apps_smmu 0x1066 0x0>; + dma-coherent; + }; + + compute-cb@7 { + compatible = "qcom,fastrpc-compute-cb"; + reg = <7>; + iommus = <&apps_smmu 0x1007 0x80>, + <&apps_smmu 0x1067 0x0>; + dma-coherent; + }; + }; + + gpr { + compatible = "qcom,gpr"; + qcom,glink-channels = "adsp_apps"; + qcom,domain = ; + qcom,intents = <512 20>; + #address-cells = <1>; + #size-cells = <0>; + + q6apm: service@1 { + compatible = "qcom,q6apm"; + reg = ; + #sound-dai-cells = <0>; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6apmbedai: bedais { + compatible = "qcom,q6apm-lpass-dais"; + #sound-dai-cells = <1>; + }; + + q6apmdai: dais { + compatible = "qcom,q6apm-dais"; + iommus = <&apps_smmu 0x1001 0x80>, + <&apps_smmu 0x1061 0x0>; + }; + }; + + q6prm: service@2 { + compatible = "qcom,q6prm"; + reg = ; + qcom,protection-domain = "avs/audio", + "msm/adsp/audio_pd"; + + q6prmcc: clock-controller { + compatible = "qcom,q6prm-lpass-clocks"; + #clock-cells = <2>; + }; + }; + }; + }; + }; + lpass_wsa2macro: codec@6aa0000 { compatible = "qcom,x1e80100-lpass-wsa-macro", "qcom,sm8550-lpass-wsa-macro"; reg = <0 0x06aa0000 0 0x1000>; @@ -3892,6 +4446,112 @@ #interconnect-cells = <2>; }; + sdhc_2: mmc@8804000 { + compatible = "qcom,x1e80100-sdhci", "qcom,sdhci-msm-v5"; + reg = <0 0x08804000 0 0x1000>; + + interrupts = , + ; + interrupt-names = "hc_irq", "pwr_irq"; + + clocks = <&gcc GCC_SDCC2_AHB_CLK>, + <&gcc GCC_SDCC2_APPS_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "core", "xo"; + iommus = <&apps_smmu 0x520 0>; + qcom,dll-config = <0x0007642c>; + qcom,ddr-config = <0x80040868>; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&sdhc2_opp_table>; + + interconnects = <&aggre2_noc MASTER_SDCC_2 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_SDCC_2 QCOM_ICC_TAG_ACTIVE_ONLY>; + interconnect-names = "sdhc-ddr", "cpu-sdhc"; + bus-width = <4>; + dma-coherent; + + status = "disabled"; + + sdhc2_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-19200000 { + opp-hz = /bits/ 64 <19200000>; + required-opps = <&rpmhpd_opp_min_svs>; + }; + + opp-50000000 { + opp-hz = /bits/ 64 <50000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-100000000 { + opp-hz = /bits/ 64 <100000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-202000000 { + opp-hz = /bits/ 64 <202000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + }; + }; + + sdhc_4: mmc@8844000 { + compatible = "qcom,x1e80100-sdhci", "qcom,sdhci-msm-v5"; + reg = <0 0x08844000 0 0x1000>; + + interrupts = , + ; + interrupt-names = "hc_irq", "pwr_irq"; + + clocks = <&gcc GCC_SDCC4_AHB_CLK>, + <&gcc GCC_SDCC4_APPS_CLK>, + <&rpmhcc RPMH_CXO_CLK>; + clock-names = "iface", "core", "xo"; + iommus = <&apps_smmu 0x160 0>; + qcom,dll-config = <0x0007642c>; + qcom,ddr-config = <0x80040868>; + power-domains = <&rpmhpd RPMHPD_CX>; + operating-points-v2 = <&sdhc4_opp_table>; + + interconnects = <&aggre2_noc MASTER_SDCC_4 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_SDCC_4 QCOM_ICC_TAG_ACTIVE_ONLY>; + interconnect-names = "sdhc-ddr", "cpu-sdhc"; + bus-width = <4>; + dma-coherent; + + status = "disabled"; + + sdhc4_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-19200000 { + opp-hz = /bits/ 64 <19200000>; + required-opps = <&rpmhpd_opp_min_svs>; + }; + + opp-50000000 { + opp-hz = /bits/ 64 <50000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-100000000 { + opp-hz = /bits/ 64 <100000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-202000000 { + opp-hz = /bits/ 64 <202000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + }; + }; + usb_2_hsphy: phy@88e0000 { compatible = "qcom,x1e80100-snps-eusb2-phy", "qcom,sm8550-snps-eusb2-phy"; @@ -4063,11 +4723,11 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,usb3_lpm_capable; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; @@ -4120,7 +4780,7 @@ <&gcc GCC_USB20_MASTER_CLK>; assigned-clock-rates = <19200000>, <200000000>; - interrupts-extended = <&intc GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 245 IRQ_TYPE_LEVEL_HIGH>, <&pdc 50 IRQ_TYPE_EDGE_BOTH>, <&pdc 49 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "pwr_event", @@ -4146,11 +4806,13 @@ usb_2_dwc3: usb@a200000 { compatible = "snps,dwc3"; reg = <0 0x0a200000 0 0xcd00>; - interrupts = ; + interrupts = ; iommus = <&apps_smmu 0x14e0 0x0>; phys = <&usb_2_hsphy>; phy-names = "usb2-phy"; maximum-speed = "high-speed"; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; ports { #address-cells = <1>; @@ -4247,6 +4909,8 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,usb3_lpm_capable; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; dma-coherent; }; @@ -4318,11 +4982,11 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,usb3_lpm_capable; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; @@ -4418,11 +5082,11 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,usb3_lpm_capable; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; @@ -5635,6 +6299,34 @@ }; }; + qup_uart14_default: qup-uart14-default-state { + cts-pins { + pins = "gpio56"; + function = "qup1_se6"; + bias-bus-hold; + }; + + rts-pins { + pins = "gpio57"; + function = "qup1_se6"; + drive-strength = <2>; + bias-disable; + }; + + tx-pins { + pins = "gpio58"; + function = "qup1_se6"; + drive-strength = <2>; + bias-disable; + }; + + rx-pins { + pins = "gpio59"; + function = "qup1_se6"; + bias-pull-up; + }; + }; + qup_uart21_default: qup-uart21-default-state { tx-pins { pins = "gpio86"; @@ -5650,6 +6342,1487 @@ bias-disable; }; }; + + sdc2_default: sdc2-default-state { + clk-pins { + pins = "sdc2_clk"; + drive-strength = <16>; + bias-disable; + }; + + cmd-pins { + pins = "sdc2_cmd"; + drive-strength = <10>; + bias-pull-up; + }; + + data-pins { + pins = "sdc2_data"; + drive-strength = <10>; + bias-pull-up; + }; + }; + + sdc2_sleep: sdc2-sleep-state { + clk-pins { + pins = "sdc2_clk"; + drive-strength = <2>; + bias-disable; + }; + + cmd-pins { + pins = "sdc2_cmd"; + drive-strength = <2>; + bias-pull-up; + }; + + data-pins { + pins = "sdc2_data"; + drive-strength = <2>; + bias-pull-up; + }; + }; + }; + + stm@10002000 { + compatible = "arm,coresight-stm", "arm,primecell"; + reg = <0x0 0x10002000 0x0 0x1000>, + <0x0 0x16280000 0x0 0x180000>; + reg-names = "stm-base", + "stm-stimulus-base"; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + out-ports { + port { + stm_out: endpoint { + remote-endpoint = <&funnel0_in7>; + }; + }; + }; + }; + + tpdm@10003000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10003000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + dcc_tpdm_out: endpoint { + remote-endpoint = <&qdss_tpda_in0>; + }; + }; + }; + }; + + tpda@10004000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x10004000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + qdss_tpda_in0: endpoint { + remote-endpoint = <&dcc_tpdm_out>; + }; + }; + + port@1 { + reg = <1>; + + qdss_tpda_in1: endpoint { + remote-endpoint = <&qdss_tpdm_out>; + }; + }; + }; + + out-ports { + port { + qdss_tpda_out: endpoint { + remote-endpoint = <&funnel0_in6>; + }; + }; + }; + }; + + tpdm@1000f000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x1000f000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + qdss_tpdm_out: endpoint { + remote-endpoint = <&qdss_tpda_in1>; + }; + }; + }; + }; + + funnel@10041000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10041000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@6 { + reg = <6>; + + funnel0_in6: endpoint { + remote-endpoint = <&qdss_tpda_out>; + }; + }; + + port@7 { + reg = <7>; + + funnel0_in7: endpoint { + remote-endpoint = <&stm_out>; + }; + }; + }; + + out-ports { + port { + funnel0_out: endpoint { + remote-endpoint = <&qdss_funnel_in0>; + }; + }; + }; + }; + + funnel@10042000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10042000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@2 { + reg = <2>; + + funnel1_in2: endpoint { + remote-endpoint = <&tmess_funnel_out>; + }; + }; + + port@5 { + reg = <5>; + + funnel1_in5: endpoint { + remote-endpoint = <&dlst_funnel_out>; + }; + }; + + port@6 { + reg = <6>; + + funnel1_in6: endpoint { + remote-endpoint = <&dlct1_funnel_out>; + }; + }; + }; + + out-ports { + port { + funnel1_out: endpoint { + remote-endpoint = <&qdss_funnel_in1>; + }; + }; + }; + }; + + funnel@10045000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10045000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + qdss_funnel_in0: endpoint { + remote-endpoint = <&funnel0_out>; + }; + }; + + port@1 { + reg = <1>; + + qdss_funnel_in1: endpoint { + remote-endpoint = <&funnel1_out>; + }; + }; + }; + + out-ports { + port { + qdss_funnel_out: endpoint { + remote-endpoint = <&aoss_funnel_in7>; + }; + }; + }; + }; + + tpdm@10800000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10800000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + mxa_tpdm_out: endpoint { + remote-endpoint = <&dlct2_tpda_in15>; + }; + }; + }; + }; + + tpdm@1082c000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x1082c000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + gcc_tpdm_out: endpoint { + remote-endpoint = <&dlct1_tpda_in21>; + }; + }; + }; + }; + + tpdm@10841000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10841000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + prng_tpdm_out: endpoint { + remote-endpoint = <&dlct1_tpda_in19>; + }; + }; + }; + }; + + tpdm@10844000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10844000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + lpass_cx_tpdm_out: endpoint { + remote-endpoint = <&lpass_cx_funnel_in0>; + }; + }; + }; + }; + + funnel@10846000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10846000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + lpass_cx_funnel_in0: endpoint { + remote-endpoint = <&lpass_cx_tpdm_out>; + }; + }; + }; + + out-ports { + port { + lpass_cx_funnel_out: endpoint { + remote-endpoint = <&dlct1_tpda_in4>; + }; + }; + }; + }; + + cti@1098b000 { + compatible = "arm,coresight-cti", "arm,primecell"; + reg = <0x0 0x1098b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + }; + + tpdm@109d0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x109d0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + qm_tpdm_out: endpoint { + remote-endpoint = <&dlct1_tpda_in20>; + }; + }; + }; + }; + + tpdm@10ac0000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10ac0000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + dlst_tpdm0_out: endpoint { + remote-endpoint = <&dlst_tpda_in8>; + }; + }; + }; + }; + + tpdm@10ac1000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10ac1000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + dlst_tpdm1_out: endpoint { + remote-endpoint = <&dlst_tpda_in9>; + }; + }; + }; + }; + + tpda@10ac4000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x10ac4000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@8 { + reg = <8>; + + dlst_tpda_in8: endpoint { + remote-endpoint = <&dlst_tpdm0_out>; + }; + }; + + port@9 { + reg = <9>; + + dlst_tpda_in9: endpoint { + remote-endpoint = <&dlst_tpdm1_out>; + }; + }; + }; + + out-ports { + port { + dlst_tpda_out: endpoint { + remote-endpoint = <&dlst_funnel_in0>; + }; + }; + }; + }; + + funnel@10ac5000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10ac5000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + dlst_funnel_in0: endpoint { + remote-endpoint = <&dlst_tpda_out>; + }; + }; + }; + + out-ports { + port { + dlst_funnel_out: endpoint { + remote-endpoint = <&funnel1_in5>; + }; + }; + }; + }; + + funnel@10b04000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10b04000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@3 { + reg = <3>; + + aoss_funnel_in3: endpoint { + remote-endpoint = <&ddr_lpi_funnel_out>; + }; + }; + + port@6 { + reg = <6>; + + aoss_funnel_in6: endpoint { + remote-endpoint = <&aoss_tpda_out>; + }; + }; + + port@7 { + reg = <7>; + + aoss_funnel_in7: endpoint { + remote-endpoint = <&qdss_funnel_out>; + }; + }; + }; + + out-ports { + port { + aoss_funnel_out: endpoint { + remote-endpoint = <&etf0_in>; + }; + }; + }; + }; + + etf0: tmc@10b05000 { + compatible = "arm,coresight-tmc", "arm,primecell"; + reg = <0x0 0x10b05000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + etf0_in: endpoint { + remote-endpoint = <&aoss_funnel_out>; + }; + }; + }; + + out-ports { + port { + etf0_out: endpoint { + remote-endpoint = <&swao_rep_in>; + }; + }; + }; + }; + + replicator@10b06000 { + compatible = "arm,coresight-dynamic-replicator", "arm,primecell"; + reg = <0x0 0x10b06000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + swao_rep_in: endpoint { + remote-endpoint = <&etf0_out>; + }; + }; + }; + + out-ports { + port { + swao_rep_out1: endpoint { + remote-endpoint = <&eud_in>; + }; + }; + }; + }; + + tpda@10b08000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x10b08000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + aoss_tpda_in0: endpoint { + remote-endpoint = <&aoss_tpdm0_out>; + }; + }; + + port@1 { + reg = <1>; + + aoss_tpda_in1: endpoint { + remote-endpoint = <&aoss_tpdm1_out>; + }; + }; + + port@2 { + reg = <2>; + + aoss_tpda_in2: endpoint { + remote-endpoint = <&aoss_tpdm2_out>; + }; + }; + + port@3 { + reg = <3>; + + aoss_tpda_in3: endpoint { + remote-endpoint = <&aoss_tpdm3_out>; + }; + }; + + port@4 { + reg = <4>; + + aoss_tpda_in4: endpoint { + remote-endpoint = <&aoss_tpdm4_out>; + }; + }; + }; + + out-ports { + port { + aoss_tpda_out: endpoint { + remote-endpoint = <&aoss_funnel_in6>; + }; + }; + }; + }; + + tpdm@10b09000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10b09000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm0_out: endpoint { + remote-endpoint = <&aoss_tpda_in0>; + }; + }; + }; + }; + + tpdm@10b0a000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10b0a000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm1_out: endpoint { + remote-endpoint = <&aoss_tpda_in1>; + }; + }; + }; + }; + + tpdm@10b0b000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10b0b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm2_out: endpoint { + remote-endpoint = <&aoss_tpda_in2>; + }; + }; + }; + }; + + tpdm@10b0c000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10b0c000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm3_out: endpoint { + remote-endpoint = <&aoss_tpda_in3>; + }; + }; + }; + }; + + tpdm@10b0d000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10b0d000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + aoss_tpdm4_out: endpoint { + remote-endpoint = <&aoss_tpda_in4>; + }; + }; + }; + }; + + tpdm@10b20000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10b20000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + lpicc_tpdm_out: endpoint { + remote-endpoint = <&ddr_lpi_tpda_in>; + }; + }; + }; + }; + + tpda@10b23000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x10b23000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + status = "disabled"; + + in-ports { + port { + ddr_lpi_tpda_in: endpoint { + remote-endpoint = <&lpicc_tpdm_out>; + }; + }; + }; + + out-ports { + port { + ddr_lpi_tpda_out: endpoint { + remote-endpoint = <&ddr_lpi_funnel_in0>; + }; + }; + }; + }; + + funnel@10b24000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10b24000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + status = "disabled"; + + in-ports { + port { + ddr_lpi_funnel_in0: endpoint { + remote-endpoint = <&ddr_lpi_tpda_out>; + }; + }; + }; + + out-ports { + port { + ddr_lpi_funnel_out: endpoint { + remote-endpoint = <&aoss_funnel_in3>; + }; + }; + }; + }; + + tpdm@10c08000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10c08000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + mm_tpdm_out: endpoint { + remote-endpoint = <&mm_funnel_in4>; + }; + }; + }; + }; + + funnel@10c0b000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10c0b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@4 { + reg = <4>; + + mm_funnel_in4: endpoint { + remote-endpoint = <&mm_tpdm_out>; + }; + }; + }; + + out-ports { + port { + mm_funnel_out: endpoint { + remote-endpoint = <&dlct2_tpda_in4>; + }; + }; + }; + }; + + tpdm@10c28000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10c28000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + + out-ports { + port { + dlct1_tpdm_out: endpoint { + remote-endpoint = <&dlct1_tpda_in26>; + }; + }; + }; + }; + + tpdm@10c29000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10c29000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + ipcc_tpdm_out: endpoint { + remote-endpoint = <&dlct1_tpda_in27>; + }; + }; + }; + }; + + tpda@10c2b000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x10c2b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@4 { + reg = <4>; + + dlct1_tpda_in4: endpoint { + remote-endpoint = <&lpass_cx_funnel_out>; + }; + }; + + port@13 { + reg = <19>; + + dlct1_tpda_in19: endpoint { + remote-endpoint = <&prng_tpdm_out>; + }; + }; + + port@14 { + reg = <20>; + + dlct1_tpda_in20: endpoint { + remote-endpoint = <&qm_tpdm_out>; + }; + }; + + port@15 { + reg = <21>; + + dlct1_tpda_in21: endpoint { + remote-endpoint = <&gcc_tpdm_out>; + }; + }; + + port@1a { + reg = <26>; + + dlct1_tpda_in26: endpoint { + remote-endpoint = <&dlct1_tpdm_out>; + }; + }; + + port@1b { + reg = <27>; + + dlct1_tpda_in27: endpoint { + remote-endpoint = <&ipcc_tpdm_out>; + }; + }; + }; + + out-ports { + port { + dlct1_tpda_out: endpoint { + remote-endpoint = <&dlct1_funnel_in0>; + }; + }; + }; + }; + + funnel@10c2c000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10c2c000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + dlct1_funnel_in0: endpoint { + remote-endpoint = <&dlct1_tpda_out>; + }; + }; + + port@4 { + reg = <4>; + + dlct1_funnel_in4: endpoint { + remote-endpoint = <&dlct2_funnel_out>; + }; + }; + + port@5 { + reg = <5>; + + dlct1_funnel_in5: endpoint { + remote-endpoint = <&ddr_funnel0_out>; + }; + }; + }; + + out-ports { + port { + dlct1_funnel_out: endpoint { + remote-endpoint = <&funnel1_in6>; + }; + }; + }; + }; + + tpdm@10c38000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10c38000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + dlct2_tpdm0_out: endpoint { + remote-endpoint = <&dlct2_tpda_in16>; + }; + }; + }; + }; + + tpdm@10c39000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10c39000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + dlct2_tpdm1_out: endpoint { + remote-endpoint = <&dlct2_tpda_in17>; + }; + }; + }; + }; + + tpda@10c3c000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x10c3c000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@4 { + reg = <4>; + + dlct2_tpda_in4: endpoint { + remote-endpoint = <&mm_funnel_out>; + }; + }; + + port@f { + reg = <15>; + + dlct2_tpda_in15: endpoint { + remote-endpoint = <&mxa_tpdm_out>; + }; + }; + + port@10 { + reg = <16>; + + dlct2_tpda_in16: endpoint { + remote-endpoint = <&dlct2_tpdm0_out>; + }; + }; + + port@11 { + reg = <17>; + + dlct2_tpda_in17: endpoint { + remote-endpoint = <&dlct2_tpdm1_out>; + }; + }; + }; + + out-ports { + port { + dlct2_tpda_out: endpoint { + remote-endpoint = <&dlct2_funnel_in0>; + }; + }; + }; + }; + + funnel@10c3d000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10c3d000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + dlct2_funnel_in0: endpoint { + remote-endpoint = <&dlct2_tpda_out>; + }; + }; + }; + + out-ports { + port { + dlct2_funnel_out: endpoint { + remote-endpoint = <&dlct1_funnel_in4>; + }; + }; + }; + }; + + tpdm@10cc1000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10cc1000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <64>; + qcom,cmb-msrs-num = <32>; + qcom,dsb-element-bits = <32>; + qcom,dsb-msrs-num = <32>; + status = "disabled"; + + out-ports { + port { + tmess_tpdm1_out: endpoint { + remote-endpoint = <&tmess_tpda_in2>; + }; + }; + }; + }; + + tpda@10cc4000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x10cc4000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@2 { + reg = <2>; + + tmess_tpda_in2: endpoint { + remote-endpoint = <&tmess_tpdm1_out>; + }; + }; + }; + + out-ports { + port { + tmess_tpda_out: endpoint { + remote-endpoint = <&tmess_funnel_in0>; + }; + }; + }; + }; + + funnel@10cc5000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10cc5000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + tmess_funnel_in0: endpoint { + remote-endpoint = <&tmess_tpda_out>; + }; + }; + }; + + out-ports { + port { + tmess_funnel_out: endpoint { + remote-endpoint = <&funnel1_in2>; + }; + }; + }; + }; + + funnel@10d04000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10d04000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@6 { + reg = <6>; + + ddr_funnel0_in6: endpoint { + remote-endpoint = <&ddr_funnel1_out>; + }; + }; + }; + + out-ports { + port { + ddr_funnel0_out: endpoint { + remote-endpoint = <&dlct1_funnel_in5>; + }; + }; + }; + }; + + tpdm@10d08000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10d08000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + llcc0_tpdm_out: endpoint { + remote-endpoint = <&llcc_tpda_in0>; + }; + }; + }; + }; + + tpdm@10d09000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10d09000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + llcc1_tpdm_out: endpoint { + remote-endpoint = <&llcc_tpda_in1>; + }; + }; + }; + }; + + tpdm@10d0a000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10d0a000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + llcc2_tpdm_out: endpoint { + remote-endpoint = <&llcc_tpda_in2>; + }; + }; + }; + }; + + tpdm@10d0b000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10d0b000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + llcc3_tpdm_out: endpoint { + remote-endpoint = <&llcc_tpda_in3>; + }; + }; + }; + }; + + tpdm@10d0c000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10d0c000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + llcc4_tpdm_out: endpoint { + remote-endpoint = <&llcc_tpda_in4>; + }; + }; + }; + }; + + tpdm@10d0d000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10d0d000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + llcc5_tpdm_out: endpoint { + remote-endpoint = <&llcc_tpda_in5>; + }; + }; + }; + }; + + tpdm@10d0e000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10d0e000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + llcc6_tpdm_out: endpoint { + remote-endpoint = <&llcc_tpda_in6>; + }; + }; + }; + }; + + tpdm@10d0f000 { + compatible = "qcom,coresight-tpdm", "arm,primecell"; + reg = <0x0 0x10d0f000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + qcom,cmb-element-bits = <32>; + qcom,cmb-msrs-num = <32>; + + out-ports { + port { + llcc7_tpdm_out: endpoint { + remote-endpoint = <&llcc_tpda_in7>; + }; + }; + }; + }; + + tpda@10d12000 { + compatible = "qcom,coresight-tpda", "arm,primecell"; + reg = <0x0 0x10d12000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + llcc_tpda_in0: endpoint { + remote-endpoint = <&llcc0_tpdm_out>; + }; + }; + + port@1 { + reg = <1>; + + llcc_tpda_in1: endpoint { + remote-endpoint = <&llcc1_tpdm_out>; + }; + }; + + port@2 { + reg = <2>; + + llcc_tpda_in2: endpoint { + remote-endpoint = <&llcc2_tpdm_out>; + }; + }; + + port@3 { + reg = <3>; + + llcc_tpda_in3: endpoint { + remote-endpoint = <&llcc3_tpdm_out>; + }; + }; + + port@4 { + reg = <4>; + + llcc_tpda_in4: endpoint { + remote-endpoint = <&llcc4_tpdm_out>; + }; + }; + + port@5 { + reg = <5>; + + llcc_tpda_in5: endpoint { + remote-endpoint = <&llcc5_tpdm_out>; + }; + }; + + port@6 { + reg = <6>; + + llcc_tpda_in6: endpoint { + remote-endpoint = <&llcc6_tpdm_out>; + }; + }; + + port@7 { + reg = <7>; + + llcc_tpda_in7: endpoint { + remote-endpoint = <&llcc7_tpdm_out>; + }; + }; + }; + + out-ports { + port { + llcc_tpda_out: endpoint { + remote-endpoint = <&ddr_funnel1_in0>; + }; + }; + }; + }; + + funnel@10d13000 { + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; + reg = <0x0 0x10d13000 0x0 0x1000>; + + clocks = <&aoss_qmp>; + clock-names = "apb_pclk"; + + in-ports { + port { + ddr_funnel1_in0: endpoint { + remote-endpoint = <&llcc_tpda_out>; + }; + }; + }; + + out-ports { + port { + ddr_funnel1_out: endpoint { + remote-endpoint = <&ddr_funnel0_in6>; + }; + }; + }; }; apps_smmu: iommu@15000000 { @@ -6117,146 +8290,9 @@ interrupts = ; }; - remoteproc_adsp: remoteproc@30000000 { - compatible = "qcom,x1e80100-adsp-pas"; - reg = <0 0x30000000 0 0x100>; - - interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; - interrupt-names = "wdog", - "fatal", - "ready", - "handover", - "stop-ack"; - - clocks = <&rpmhcc RPMH_CXO_CLK>; - clock-names = "xo"; - - power-domains = <&rpmhpd RPMHPD_LCX>, - <&rpmhpd RPMHPD_LMX>; - power-domain-names = "lcx", - "lmx"; - - interconnects = <&lpass_lpicx_noc MASTER_LPASS_PROC QCOM_ICC_TAG_ALWAYS - &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>; - - memory-region = <&adspslpi_mem>, - <&q6_adsp_dtb_mem>; - - qcom,qmp = <&aoss_qmp>; - - qcom,smem-states = <&smp2p_adsp_out 0>; - qcom,smem-state-names = "stop"; - - status = "disabled"; - - glink-edge { - interrupts-extended = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP - IRQ_TYPE_EDGE_RISING>; - mboxes = <&ipcc IPCC_CLIENT_LPASS - IPCC_MPROC_SIGNAL_GLINK_QMP>; - - label = "lpass"; - qcom,remote-pid = <2>; - - fastrpc { - compatible = "qcom,fastrpc"; - qcom,glink-channels = "fastrpcglink-apps-dsp"; - label = "adsp"; - qcom,non-secure-domain; - #address-cells = <1>; - #size-cells = <0>; - - compute-cb@3 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <3>; - iommus = <&apps_smmu 0x1003 0x80>, - <&apps_smmu 0x1063 0x0>; - dma-coherent; - }; - - compute-cb@4 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <4>; - iommus = <&apps_smmu 0x1004 0x80>, - <&apps_smmu 0x1064 0x0>; - dma-coherent; - }; - - compute-cb@5 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <5>; - iommus = <&apps_smmu 0x1005 0x80>, - <&apps_smmu 0x1065 0x0>; - dma-coherent; - }; - - compute-cb@6 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <6>; - iommus = <&apps_smmu 0x1006 0x80>, - <&apps_smmu 0x1066 0x0>; - dma-coherent; - }; - - compute-cb@7 { - compatible = "qcom,fastrpc-compute-cb"; - reg = <7>; - iommus = <&apps_smmu 0x1007 0x80>, - <&apps_smmu 0x1067 0x0>; - dma-coherent; - }; - }; - - gpr { - compatible = "qcom,gpr"; - qcom,glink-channels = "adsp_apps"; - qcom,domain = ; - qcom,intents = <512 20>; - #address-cells = <1>; - #size-cells = <0>; - - q6apm: service@1 { - compatible = "qcom,q6apm"; - reg = ; - #sound-dai-cells = <0>; - qcom,protection-domain = "avs/audio", - "msm/adsp/audio_pd"; - - q6apmbedai: bedais { - compatible = "qcom,q6apm-lpass-dais"; - #sound-dai-cells = <1>; - }; - - q6apmdai: dais { - compatible = "qcom,q6apm-dais"; - iommus = <&apps_smmu 0x1001 0x80>, - <&apps_smmu 0x1061 0x0>; - }; - }; - - q6prm: service@2 { - compatible = "qcom,q6prm"; - reg = ; - qcom,protection-domain = "avs/audio", - "msm/adsp/audio_pd"; - - q6prmcc: clock-controller { - compatible = "qcom,q6prm-lpass-clocks"; - #clock-cells = <2>; - }; - }; - }; - }; - }; - remoteproc_cdsp: remoteproc@32300000 { compatible = "qcom,x1e80100-cdsp-pas"; - reg = <0 0x32300000 0 0x1400000>; + reg = <0x0 0x32300000 0x0 0x10000>; interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/renesas/Makefile b/arch/arm64/boot/dts/renesas/Makefile index 97228a3cb99c..928635f2e76b 100644 --- a/arch/arm64/boot/dts/renesas/Makefile +++ b/arch/arm64/boot/dts/renesas/Makefile @@ -86,11 +86,17 @@ dtb-$(CONFIG_ARCH_R8A779F0) += r8a779f4-s4sk.dtb dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g0-white-hawk.dtb dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g0-white-hawk-cpu.dtb -dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g0-white-hawk-ard-audio-da7212.dtbo -r8a779g0-white-hawk-ard-audio-da7212-dtbs := r8a779g0-white-hawk.dtb r8a779g0-white-hawk-ard-audio-da7212.dtbo +dtb-$(CONFIG_ARCH_R8A779G0) += white-hawk-ard-audio-da7212.dtbo +r8a779g0-white-hawk-ard-audio-da7212-dtbs := r8a779g0-white-hawk.dtb white-hawk-ard-audio-da7212.dtbo dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g0-white-hawk-ard-audio-da7212.dtb dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g2-white-hawk-single.dtb +r8a779g2-white-hawk-single-ard-audio-da7212-dtbs := r8a779g2-white-hawk-single.dtb white-hawk-ard-audio-da7212.dtbo +dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g2-white-hawk-single-ard-audio-da7212.dtb + +dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g3-white-hawk-single.dtb +r8a779g3-white-hawk-single-ard-audio-da7212-dtbs := r8a779g3-white-hawk-single.dtb white-hawk-ard-audio-da7212.dtbo +dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g3-white-hawk-single-ard-audio-da7212.dtb dtb-$(CONFIG_ARCH_R8A779H0) += r8a779h0-gray-hawk-single.dtb @@ -140,6 +146,8 @@ dtb-$(CONFIG_ARCH_R9A08G045) += r9a08g045s33-smarc.dtb dtb-$(CONFIG_ARCH_R9A09G011) += r9a09g011-v2mevk2.dtb +dtb-$(CONFIG_ARCH_R9A09G047) += r9a09g047e57-smarc.dtb + dtb-$(CONFIG_ARCH_R9A09G057) += r9a09g057h44-rzv2h-evk.dtb dtb-$(CONFIG_ARCH_RCAR_GEN3) += draak-ebisu-panel-aa104xd12.dtbo diff --git a/arch/arm64/boot/dts/renesas/r8a779a0-falcon-ethernet.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0-falcon-ethernet.dtsi index e11bf9ace776..2a8537e13873 100644 --- a/arch/arm64/boot/dts/renesas/r8a779a0-falcon-ethernet.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779a0-falcon-ethernet.dtsi @@ -5,6 +5,121 @@ * Copyright (C) 2021 Glider bv */ +/ { + aliases { + ethernet1 = &avb1; + ethernet2 = &avb2; + ethernet3 = &avb3; + ethernet4 = &avb4; + ethernet5 = &avb5; + }; +}; + +&avb1 { + pinctrl-0 = <&avb1_pins>; + pinctrl-names = "default"; + phy-handle = <&avb1_phy>; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio5 15 GPIO_ACTIVE_LOW>; + reset-post-delay-us = <4000>; + + avb1_phy: ethernet-phy@7 { + compatible = "ethernet-phy-ieee802.3-c45"; + reg = <7>; + interrupts-extended = <&gpio5 16 IRQ_TYPE_LEVEL_LOW>; + }; + }; +}; + +&avb2 { + pinctrl-0 = <&avb2_pins>; + pinctrl-names = "default"; + phy-handle = <&avb2_phy>; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio6 15 GPIO_ACTIVE_LOW>; + reset-post-delay-us = <4000>; + + avb2_phy: ethernet-phy@7 { + compatible = "ethernet-phy-ieee802.3-c45"; + reg = <7>; + interrupts-extended = <&gpio6 16 IRQ_TYPE_LEVEL_LOW>; + }; + }; +}; + +&avb3 { + pinctrl-0 = <&avb3_pins>; + pinctrl-names = "default"; + phy-handle = <&avb3_phy>; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio7 15 GPIO_ACTIVE_LOW>; + reset-post-delay-us = <4000>; + + avb3_phy: ethernet-phy@7 { + compatible = "ethernet-phy-ieee802.3-c45"; + reg = <7>; + interrupts-extended = <&gpio7 16 IRQ_TYPE_LEVEL_LOW>; + }; + }; +}; + +&avb4 { + pinctrl-0 = <&avb4_pins>; + pinctrl-names = "default"; + phy-handle = <&avb4_phy>; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio8 15 GPIO_ACTIVE_LOW>; + reset-post-delay-us = <4000>; + + avb4_phy: ethernet-phy@7 { + compatible = "ethernet-phy-ieee802.3-c45"; + reg = <7>; + interrupts-extended = <&gpio8 16 IRQ_TYPE_LEVEL_LOW>; + }; + }; +}; + +&avb5 { + pinctrl-0 = <&avb5_pins>; + pinctrl-names = "default"; + phy-handle = <&avb5_phy>; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio9 15 GPIO_ACTIVE_LOW>; + reset-post-delay-us = <4000>; + + avb5_phy: ethernet-phy@7 { + compatible = "ethernet-phy-ieee802.3-c45"; + reg = <7>; + interrupts-extended = <&gpio9 16 IRQ_TYPE_LEVEL_LOW>; + }; + }; +}; + &i2c0 { eeprom@53 { compatible = "rohm,br24g01", "atmel,24c01"; @@ -13,3 +128,130 @@ pagesize = <8>; }; }; + +&pfc { + avb1_pins: avb1 { + mux { + groups = "avb1_link", "avb1_mdio", "avb1_rgmii", + "avb1_txcrefclk"; + function = "avb1"; + }; + + link { + groups = "avb1_link"; + bias-disable; + }; + + mdio { + groups = "avb1_mdio"; + drive-strength = <24>; + bias-disable; + }; + + rgmii { + groups = "avb1_rgmii"; + drive-strength = <24>; + bias-disable; + }; + }; + + avb2_pins: avb2 { + mux { + groups = "avb2_link", "avb2_mdio", "avb2_rgmii", + "avb2_txcrefclk"; + function = "avb2"; + }; + + link { + groups = "avb2_link"; + bias-disable; + }; + + mdio { + groups = "avb2_mdio"; + drive-strength = <24>; + bias-disable; + }; + + rgmii { + groups = "avb2_rgmii"; + drive-strength = <24>; + bias-disable; + }; + }; + + avb3_pins: avb3 { + mux { + groups = "avb3_link", "avb3_mdio", "avb3_rgmii", + "avb3_txcrefclk"; + function = "avb3"; + }; + + link { + groups = "avb3_link"; + bias-disable; + }; + + mdio { + groups = "avb3_mdio"; + drive-strength = <24>; + bias-disable; + }; + + rgmii { + groups = "avb3_rgmii"; + drive-strength = <24>; + bias-disable; + }; + }; + + avb4_pins: avb4 { + mux { + groups = "avb4_link", "avb4_mdio", "avb4_rgmii", + "avb4_txcrefclk"; + function = "avb4"; + }; + + link { + groups = "avb4_link"; + bias-disable; + }; + + mdio { + groups = "avb4_mdio"; + drive-strength = <24>; + bias-disable; + }; + + rgmii { + groups = "avb4_rgmii"; + drive-strength = <24>; + bias-disable; + }; + }; + + avb5_pins: avb5 { + mux { + groups = "avb5_link", "avb5_mdio", "avb5_rgmii", + "avb5_txcrefclk"; + function = "avb5"; + }; + + link { + groups = "avb5_link"; + bias-disable; + }; + + mdio { + groups = "avb5_mdio"; + drive-strength = <24>; + bias-disable; + }; + + rgmii { + groups = "avb5_rgmii"; + drive-strength = <24>; + bias-disable; + }; + }; +}; diff --git a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi index 7156b1a542e8..fe6d97859e4a 100644 --- a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi @@ -765,8 +765,6 @@ rx-internal-delay-ps = <0>; tx-internal-delay-ps = <0>; iommus = <&ipmmu_ds1 1>; - #address-cells = <1>; - #size-cells = <0>; status = "disabled"; }; @@ -814,8 +812,6 @@ rx-internal-delay-ps = <0>; tx-internal-delay-ps = <0>; iommus = <&ipmmu_ds1 2>; - #address-cells = <1>; - #size-cells = <0>; status = "disabled"; }; @@ -863,8 +859,6 @@ rx-internal-delay-ps = <0>; tx-internal-delay-ps = <0>; iommus = <&ipmmu_ds1 3>; - #address-cells = <1>; - #size-cells = <0>; status = "disabled"; }; @@ -912,8 +906,6 @@ rx-internal-delay-ps = <0>; tx-internal-delay-ps = <0>; iommus = <&ipmmu_ds1 4>; - #address-cells = <1>; - #size-cells = <0>; status = "disabled"; }; @@ -961,8 +953,6 @@ rx-internal-delay-ps = <0>; tx-internal-delay-ps = <0>; iommus = <&ipmmu_ds1 11>; - #address-cells = <1>; - #size-cells = <0>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi index 61c6b8022ffd..104f740d20d3 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi @@ -2453,6 +2453,46 @@ }; }; + fcpvx0: fcp@fedb0000 { + compatible = "renesas,fcpv"; + reg = <0 0xfedb0000 0 0x200>; + clocks = <&cpg CPG_MOD 1100>; + power-domains = <&sysc R8A779G0_PD_A3ISP0>; + resets = <&cpg 1100>; + iommus = <&ipmmu_vi1 24>; + }; + + fcpvx1: fcp@fedb8000 { + compatible = "renesas,fcpv"; + reg = <0 0xfedb8000 0 0x200>; + clocks = <&cpg CPG_MOD 1101>; + power-domains = <&sysc R8A779G0_PD_A3ISP1>; + resets = <&cpg 1101>; + iommus = <&ipmmu_vi1 25>; + }; + + vspx0: vsp@fedd0000 { + compatible = "renesas,vsp2"; + reg = <0 0xfedd0000 0 0x8000>; + interrupts = ; + clocks = <&cpg CPG_MOD 1028>; + power-domains = <&sysc R8A779G0_PD_A3ISP0>; + resets = <&cpg 1028>; + + renesas,fcp = <&fcpvx0>; + }; + + vspx1: vsp@fedd8000 { + compatible = "renesas,vsp2"; + reg = <0 0xfedd8000 0 0x8000>; + interrupts = ; + clocks = <&cpg CPG_MOD 1029>; + power-domains = <&sysc R8A779G0_PD_A3ISP1>; + resets = <&cpg 1029>; + + renesas,fcp = <&fcpvx1>; + }; + prr: chipid@fff00044 { compatible = "renesas,prr"; reg = <0 0xfff00044 0 4>; diff --git a/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts b/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts index 0062362b0ba0..48befde38937 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts +++ b/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts @@ -7,70 +7,10 @@ /dts-v1/; #include "r8a779g2.dtsi" -#include "white-hawk-cpu-common.dtsi" -#include "white-hawk-common.dtsi" +#include "white-hawk-single.dtsi" / { model = "Renesas White Hawk Single board based on r8a779g2"; compatible = "renesas,white-hawk-single", "renesas,r8a779g2", "renesas,r8a779g0"; }; - -&hscif0 { - uart-has-rtscts; -}; - -&hscif0_pins { - groups = "hscif0_data", "hscif0_ctrl"; - function = "hscif0"; -}; - -&pfc { - tsn0_pins: tsn0 { - mux { - groups = "tsn0_link", "tsn0_mdio", "tsn0_rgmii", - "tsn0_txcrefclk"; - function = "tsn0"; - }; - - link { - groups = "tsn0_link"; - bias-disable; - }; - - mdio { - groups = "tsn0_mdio"; - drive-strength = <24>; - bias-disable; - }; - - rgmii { - groups = "tsn0_rgmii"; - drive-strength = <24>; - bias-disable; - }; - }; -}; - -&tsn0 { - pinctrl-0 = <&tsn0_pins>; - pinctrl-names = "default"; - phy-mode = "rgmii"; - phy-handle = <&phy3>; - status = "okay"; - - mdio { - #address-cells = <1>; - #size-cells = <0>; - - reset-gpios = <&gpio1 23 GPIO_ACTIVE_LOW>; - reset-post-delay-us = <4000>; - - phy3: ethernet-phy@0 { - compatible = "ethernet-phy-id002b.0980", - "ethernet-phy-ieee802.3-c22"; - reg = <0>; - interrupts-extended = <&gpio4 3 IRQ_TYPE_LEVEL_LOW>; - }; - }; -}; diff --git a/arch/arm64/boot/dts/renesas/r8a779g3-white-hawk-single.dts b/arch/arm64/boot/dts/renesas/r8a779g3-white-hawk-single.dts new file mode 100644 index 000000000000..cd466d858854 --- /dev/null +++ b/arch/arm64/boot/dts/renesas/r8a779g3-white-hawk-single.dts @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the R-Car V4H ES3.0 White Hawk Single board + * + * Copyright (C) 2024 Glider bv + */ + +/dts-v1/; +#include "r8a779g3.dtsi" +#include "white-hawk-single.dtsi" + +/ { + model = "Renesas White Hawk Single board based on r8a779g3"; + compatible = "renesas,white-hawk-single", "renesas,r8a779g3", + "renesas,r8a779g0"; +}; diff --git a/arch/arm64/boot/dts/renesas/r8a779g3.dtsi b/arch/arm64/boot/dts/renesas/r8a779g3.dtsi new file mode 100644 index 000000000000..0295858a0260 --- /dev/null +++ b/arch/arm64/boot/dts/renesas/r8a779g3.dtsi @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the R-Car V4H (R8A779G3) SoC + * + * Copyright (C) 2024 Glider bv + */ + +#include "r8a779g0.dtsi" + +/ { + compatible = "renesas,r8a779g3", "renesas,r8a779g0"; +}; diff --git a/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts b/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts index 58eabcc7e0e0..18fd52f55de5 100644 --- a/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts +++ b/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts @@ -30,6 +30,7 @@ #include #include #include +#include #include "r8a779h0.dtsi" @@ -59,6 +60,12 @@ stdout-path = "serial0:921600n8"; }; + sn65dsi86_refclk: clk-x6 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <38400000>; + }; + keys { compatible = "gpio-keys"; @@ -132,22 +139,43 @@ #clock-cells = <0>; }; + mini-dp-con { + compatible = "dp-connector"; + label = "CN5"; + type = "mini"; + + port { + mini_dp_con_in: endpoint { + remote-endpoint = <&sn65dsi86_out0>; + }; + }; + }; + + reg_1p2v: regulator-1p2v { + compatible = "regulator-fixed"; + regulator-name = "fixed-1.2V"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-boot-on; + regulator-always-on; + }; + reg_1p8v: regulator-1p8v { - compatible = "regulator-fixed"; - regulator-name = "fixed-1.8V"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-boot-on; - regulator-always-on; + compatible = "regulator-fixed"; + regulator-name = "fixed-1.8V"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; }; reg_3p3v: regulator-3p3v { - compatible = "regulator-fixed"; - regulator-name = "fixed-3.3V"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; + compatible = "regulator-fixed"; + regulator-name = "fixed-3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; }; sound_mux: sound-mux { @@ -205,6 +233,65 @@ }; }; +&dsi0 { + status = "okay"; + + ports { + port@1 { + reg = <1>; + + dsi0_out: endpoint { + remote-endpoint = <&sn65dsi86_in0>; + data-lanes = <1 2 3 4>; + }; + }; + }; +}; + +&du { + status = "okay"; +}; + +&csi40 { + status = "okay"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + csi40_in: endpoint { + bus-type = ; + clock-lanes = <0>; + data-lanes = <1 2 3 4>; + remote-endpoint = <&max96724_out0>; + }; + }; + }; +}; + +&csi41 { + status = "okay"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + csi41_in: endpoint { + bus-type = ; + clock-lanes = <0>; + data-lanes = <1 2 3 4>; + remote-endpoint = <&max96724_out1>; + }; + }; + }; +}; + &extal_clk { clock-frequency = <16666666>; }; @@ -255,6 +342,20 @@ #interrupt-cells = <2>; }; + io_expander_b: gpio@21 { + compatible = "onnn,pca9654"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + io_expander_c: gpio@22 { + compatible = "onnn,pca9654"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; + eeprom@50 { compatible = "rohm,br24g01", "atmel,24c01"; label = "cpu-board"; @@ -284,6 +385,97 @@ }; }; +&i2c1 { + pinctrl-0 = <&i2c1_pins>; + pinctrl-names = "default"; + + status = "okay"; + clock-frequency = <400000>; + + bridge@2c { + pinctrl-0 = <&irq0_pins>; + pinctrl-names = "default"; + + compatible = "ti,sn65dsi86"; + reg = <0x2c>; + + clocks = <&sn65dsi86_refclk>; + clock-names = "refclk"; + + interrupts-extended = <&intc_ex 0 IRQ_TYPE_LEVEL_HIGH>; + + enable-gpios = <&gpio1 26 GPIO_ACTIVE_HIGH>; + + vccio-supply = <®_1p8v>; + vpll-supply = <®_1p8v>; + vcca-supply = <®_1p2v>; + vcc-supply = <®_1p2v>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + sn65dsi86_in0: endpoint { + remote-endpoint = <&dsi0_out>; + }; + }; + + port@1 { + reg = <1>; + + sn65dsi86_out0: endpoint { + remote-endpoint = <&mini_dp_con_in>; + }; + }; + }; + }; + + gmsl0: gmsl-deserializer@4e { + compatible = "maxim,max96724"; + reg = <0x4e>; + enable-gpios = <&io_expander_b 0 GPIO_ACTIVE_HIGH>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@4 { + reg = <4>; + max96724_out0: endpoint { + bus-type = ; + clock-lanes = <0>; + data-lanes = <1 2 3 4>; + remote-endpoint = <&csi40_in>; + }; + }; + }; + }; + + gmsl1: gmsl-deserializer@4f { + compatible = "maxim,max96724"; + reg = <0x4f>; + enable-gpios = <&io_expander_c 0 GPIO_ACTIVE_HIGH>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@4 { + reg = <4>; + max96724_out1: endpoint { + bus-type = ; + clock-lanes = <0>; + data-lanes = <1 2 3 4>; + remote-endpoint = <&csi41_in>; + }; + }; + }; + }; +}; + &i2c3 { pinctrl-0 = <&i2c3_pins>; pinctrl-names = "default"; @@ -307,6 +499,14 @@ }; }; +&isp0 { + status = "okay"; +}; + +&isp1 { + status = "okay"; +}; + &mmc0 { pinctrl-0 = <&mmc_pins>; pinctrl-1 = <&mmc_pins>; @@ -388,11 +588,21 @@ function = "i2c0"; }; + i2c1_pins: i2c1 { + groups = "i2c1"; + function = "i2c1"; + }; + i2c3_pins: i2c3 { groups = "i2c3"; function = "i2c3"; }; + irq0_pins: irq0_pins { + groups = "intc_ex_irq0_a"; + function = "intc_ex"; + }; + keys_pins: keys { pins = "GP_5_0", "GP_5_1", "GP_5_2"; bias-pull-up; @@ -494,3 +704,67 @@ &scif_clk2 { clock-frequency = <24000000>; }; + +&vin00 { + status = "okay"; +}; + +&vin01 { + status = "okay"; +}; + +&vin02 { + status = "okay"; +}; + +&vin03 { + status = "okay"; +}; + +&vin04 { + status = "okay"; +}; + +&vin05 { + status = "okay"; +}; + +&vin06 { + status = "okay"; +}; + +&vin07 { + status = "okay"; +}; + +&vin08 { + status = "okay"; +}; + +&vin09 { + status = "okay"; +}; + +&vin10 { + status = "okay"; +}; + +&vin11 { + status = "okay"; +}; + +&vin12 { + status = "okay"; +}; + +&vin13 { + status = "okay"; +}; + +&vin14 { + status = "okay"; +}; + +&vin15 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/renesas/r8a779h0.dtsi b/arch/arm64/boot/dts/renesas/r8a779h0.dtsi index facfff4b9cdc..d0c01c0fdda2 100644 --- a/arch/arm64/boot/dts/renesas/r8a779h0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779h0.dtsi @@ -1900,6 +1900,50 @@ }; }; + fcpvd0: fcp@fea10000 { + compatible = "renesas,fcpv"; + reg = <0 0xfea10000 0 0x200>; + clocks = <&cpg CPG_MOD 508>; + power-domains = <&sysc R8A779H0_PD_C4>; + resets = <&cpg 508>; + }; + + vspd0: vsp@fea20000 { + compatible = "renesas,vsp2"; + reg = <0 0xfea20000 0 0x8000>; + interrupts = ; + clocks = <&cpg CPG_MOD 830>; + power-domains = <&sysc R8A779H0_PD_C4>; + resets = <&cpg 830>; + renesas,fcp = <&fcpvd0>; + }; + + du: display@feb00000 { + compatible = "renesas,du-r8a779h0"; + reg = <0 0xfeb00000 0 0x40000>; + interrupts = ; + clocks = <&cpg CPG_MOD 411>; + clock-names = "du.0"; + power-domains = <&sysc R8A779H0_PD_C4>; + resets = <&cpg 411>; + reset-names = "du.0"; + renesas,vsps = <&vspd0 0>; + + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + du_out_dsi0: endpoint { + remote-endpoint = <&dsi0_in>; + }; + }; + }; + }; + isp0: isp@fed00000 { compatible = "renesas,r8a779h0-isp", "renesas,rcar-gen4-isp"; @@ -2068,6 +2112,35 @@ }; }; + dsi0: dsi-encoder@fed80000 { + compatible = "renesas,r8a779h0-dsi-csi2-tx"; + reg = <0 0xfed80000 0 0x10000>; + clocks = <&cpg CPG_MOD 415>, + <&cpg CPG_CORE R8A779H0_CLK_DSIEXT>, + <&cpg CPG_CORE R8A779H0_CLK_DSIREF>; + clock-names = "fck", "dsi", "pll"; + power-domains = <&sysc R8A779H0_PD_C4>; + resets = <&cpg 415>; + + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dsi0_in: endpoint { + remote-endpoint = <&du_out_dsi0>; + }; + }; + + port@1 { + reg = <1>; + }; + }; + }; + prr: chipid@fff00044 { compatible = "renesas,prr"; reg = <0 0xfff00044 0 4>; diff --git a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi index be8a0a768c65..a9b98db9ef95 100644 --- a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi @@ -14,6 +14,20 @@ #address-cells = <2>; #size-cells = <2>; + audio_clk1: audio1-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + /* This value must be overridden by boards that provide it. */ + clock-frequency = <0>; + }; + + audio_clk2: audio2-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + /* This value must be overridden by boards that provide it. */ + clock-frequency = <0>; + }; + cpus { #address-cells = <1>; #size-cells = <0>; @@ -73,6 +87,96 @@ status = "disabled"; }; + scif1: serial@1004bc00 { + compatible = "renesas,scif-r9a08g045", "renesas,scif-r9a07g044"; + reg = <0 0x1004bc00 0 0x400>; + interrupts = , + , + , + , + , + ; + interrupt-names = "eri", "rxi", "txi", + "bri", "dri", "tei"; + clocks = <&cpg CPG_MOD R9A08G045_SCIF1_CLK_PCK>; + clock-names = "fck"; + power-domains = <&cpg>; + resets = <&cpg R9A08G045_SCIF1_RST_SYSTEM_N>; + status = "disabled"; + }; + + scif2: serial@1004c000 { + compatible = "renesas,scif-r9a08g045", "renesas,scif-r9a07g044"; + reg = <0 0x1004c000 0 0x400>; + interrupts = , + , + , + , + , + ; + interrupt-names = "eri", "rxi", "txi", + "bri", "dri", "tei"; + clocks = <&cpg CPG_MOD R9A08G045_SCIF2_CLK_PCK>; + clock-names = "fck"; + power-domains = <&cpg>; + resets = <&cpg R9A08G045_SCIF2_RST_SYSTEM_N>; + status = "disabled"; + }; + + scif3: serial@1004c400 { + compatible = "renesas,scif-r9a08g045", "renesas,scif-r9a07g044"; + reg = <0 0x1004c400 0 0x400>; + interrupts = , + , + , + , + , + ; + interrupt-names = "eri", "rxi", "txi", + "bri", "dri", "tei"; + clocks = <&cpg CPG_MOD R9A08G045_SCIF3_CLK_PCK>; + clock-names = "fck"; + power-domains = <&cpg>; + resets = <&cpg R9A08G045_SCIF3_RST_SYSTEM_N>; + status = "disabled"; + }; + + scif4: serial@1004c800 { + compatible = "renesas,scif-r9a08g045", "renesas,scif-r9a07g044"; + reg = <0 0x1004c800 0 0x400>; + interrupts = , + , + , + , + , + ; + interrupt-names = "eri", "rxi", "txi", + "bri", "dri", "tei"; + clocks = <&cpg CPG_MOD R9A08G045_SCIF4_CLK_PCK>; + clock-names = "fck"; + power-domains = <&cpg>; + resets = <&cpg R9A08G045_SCIF4_RST_SYSTEM_N>; + status = "disabled"; + }; + + scif5: serial@1004e000 { + compatible = "renesas,scif-r9a08g045", "renesas,scif-r9a07g044"; + reg = <0 0x1004e000 0 0x400>; + interrupts = , + , + , + , + , + ; + interrupt-names = "eri", "rxi", "txi", + "bri", "dri", "tei"; + clocks = <&cpg CPG_MOD R9A08G045_SCIF5_CLK_PCK>; + clock-names = "fck"; + power-domains = <&cpg>; + resets = <&cpg R9A08G045_SCIF5_RST_SYSTEM_N>; + status = "disabled"; + }; + rtc: rtc@1004ec00 { compatible = "renesas,r9a08g045-rtca3", "renesas,rz-rtca3"; reg = <0 0x1004ec00 0 0x400>; @@ -87,6 +191,59 @@ status = "disabled"; }; + adc: adc@10058000 { + compatible = "renesas,r9a08g045-adc"; + reg = <0 0x10058000 0 0x1000>; + interrupts = ; + clocks = <&cpg CPG_MOD R9A08G045_ADC_ADCLK>, + <&cpg CPG_MOD R9A08G045_ADC_PCLK>; + clock-names = "adclk", "pclk"; + resets = <&cpg R9A08G045_ADC_PRESETN>, + <&cpg R9A08G045_ADC_ADRST_N>; + reset-names = "presetn", "adrst-n"; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + #io-channel-cells = <1>; + status = "disabled"; + + channel@0 { + reg = <0>; + }; + + channel@1 { + reg = <1>; + }; + + channel@2 { + reg = <2>; + }; + + channel@3 { + reg = <3>; + }; + + channel@4 { + reg = <4>; + }; + + channel@5 { + reg = <5>; + }; + + channel@6 { + reg = <6>; + }; + + channel@7 { + reg = <7>; + }; + + channel@8 { + reg = <8>; + }; + }; + vbattb: clock-controller@1005c000 { compatible = "renesas,r9a08g045-vbattb"; reg = <0 0x1005c000 0 0x1000>; @@ -187,6 +344,86 @@ status = "disabled"; }; + ssi0: ssi@100a8000 { + compatible = "renesas,r9a08g045-ssi", + "renesas,rz-ssi"; + reg = <0 0x100a8000 0 0x400>; + interrupts = , + , + ; + interrupt-names = "int_req", "dma_rx", "dma_tx"; + clocks = <&cpg CPG_MOD R9A08G045_SSI0_PCLK2>, + <&cpg CPG_MOD R9A08G045_SSI0_PCLK_SFR>, + <&audio_clk1>, <&audio_clk2>; + clock-names = "ssi", "ssi_sfr", "audio_clk1", "audio_clk2"; + resets = <&cpg R9A08G045_SSI0_RST_M2_REG>; + dmas = <&dmac 0x2665>, <&dmac 0x2666>; + dma-names = "tx", "rx"; + power-domains = <&cpg>; + #sound-dai-cells = <0>; + status = "disabled"; + }; + + ssi1: ssi@100a8400 { + compatible = "renesas,r9a08g045-ssi", + "renesas,rz-ssi"; + reg = <0 0x100a8400 0 0x400>; + interrupts = , + , + ; + interrupt-names = "int_req", "dma_rx", "dma_tx"; + clocks = <&cpg CPG_MOD R9A08G045_SSI1_PCLK2>, + <&cpg CPG_MOD R9A08G045_SSI1_PCLK_SFR>, + <&audio_clk1>, <&audio_clk2>; + clock-names = "ssi", "ssi_sfr", "audio_clk1", "audio_clk2"; + resets = <&cpg R9A08G045_SSI1_RST_M2_REG>; + dmas = <&dmac 0x2669>, <&dmac 0x266a>; + dma-names = "tx", "rx"; + power-domains = <&cpg>; + #sound-dai-cells = <0>; + status = "disabled"; + }; + + ssi2: ssi@100a8800 { + compatible = "renesas,r9a08g045-ssi", + "renesas,rz-ssi"; + reg = <0 0x100a8800 0 0x400>; + interrupts = , + , + ; + interrupt-names = "int_req", "dma_rx", "dma_tx"; + clocks = <&cpg CPG_MOD R9A08G045_SSI2_PCLK2>, + <&cpg CPG_MOD R9A08G045_SSI2_PCLK_SFR>, + <&audio_clk1>, <&audio_clk2>; + clock-names = "ssi", "ssi_sfr", "audio_clk1", "audio_clk2"; + resets = <&cpg R9A08G045_SSI2_RST_M2_REG>; + dmas = <&dmac 0x266d>, <&dmac 0x266e>; + dma-names = "tx", "rx"; + power-domains = <&cpg>; + #sound-dai-cells = <0>; + status = "disabled"; + }; + + ssi3: ssi@100a8c00 { + compatible = "renesas,r9a08g045-ssi", + "renesas,rz-ssi"; + reg = <0 0x100a8c00 0 0x400>; + interrupts = , + , + ; + interrupt-names = "int_req", "dma_rx", "dma_tx"; + clocks = <&cpg CPG_MOD R9A08G045_SSI3_PCLK2>, + <&cpg CPG_MOD R9A08G045_SSI3_PCLK_SFR>, + <&audio_clk1>, <&audio_clk2>; + clock-names = "ssi", "ssi_sfr", "audio_clk1", "audio_clk2"; + resets = <&cpg R9A08G045_SSI3_RST_M2_REG>; + dmas = <&dmac 0x2671>, <&dmac 0x2672>; + dma-names = "tx", "rx"; + power-domains = <&cpg>; + #sound-dai-cells = <0>; + status = "disabled"; + }; + cpg: clock-controller@11010000 { compatible = "renesas,r9a08g045-cpg"; reg = <0 0x11010000 0 0x10000>; diff --git a/arch/arm64/boot/dts/renesas/r9a09g047.dtsi b/arch/arm64/boot/dts/renesas/r9a09g047.dtsi new file mode 100644 index 000000000000..200e9ea89193 --- /dev/null +++ b/arch/arm64/boot/dts/renesas/r9a09g047.dtsi @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the RZ/G3E SoC + * + * Copyright (C) 2024 Renesas Electronics Corp. + */ + +#include +#include + +/ { + compatible = "renesas,r9a09g047"; + #address-cells = <2>; + #size-cells = <2>; + + audio_extal_clk: audio-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + /* This value must be overridden by the board */ + clock-frequency = <0>; + }; + + /* + * The default cluster table is based on the assumption that the PLLCA55 clock + * frequency is set to 1.7GHz. The PLLCA55 clock frequency can be set to + * 1.7/1.6/1.5/1.1 GHz based on the BOOTPLLCA_0/1 pins (and additionally can be + * clocked to 1.8GHz as well). The table below should be overridden in the board + * DTS based on the PLLCA55 clock frequency. + */ + cluster0_opp: opp-table-0 { + compatible = "operating-points-v2"; + + opp-1700000000 { + opp-hz = /bits/ 64 <1700000000>; + opp-microvolt = <900000>; + clock-latency-ns = <300000>; + }; + opp-850000000 { + opp-hz = /bits/ 64 <850000000>; + opp-microvolt = <800000>; + clock-latency-ns = <300000>; + }; + opp-425000000 { + opp-hz = /bits/ 64 <425000000>; + opp-microvolt = <800000>; + clock-latency-ns = <300000>; + }; + opp-212500000 { + opp-hz = /bits/ 64 <212500000>; + opp-microvolt = <800000>; + clock-latency-ns = <300000>; + opp-suspend; + }; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "arm,cortex-a55"; + reg = <0>; + device_type = "cpu"; + next-level-cache = <&L3_CA55>; + enable-method = "psci"; + clocks = <&cpg CPG_CORE R9A09G047_CA55_0_CORECLK0>; + operating-points-v2 = <&cluster0_opp>; + }; + + cpu1: cpu@100 { + compatible = "arm,cortex-a55"; + reg = <0x100>; + device_type = "cpu"; + next-level-cache = <&L3_CA55>; + enable-method = "psci"; + clocks = <&cpg CPG_CORE R9A09G047_CA55_0_CORECLK1>; + operating-points-v2 = <&cluster0_opp>; + }; + + cpu2: cpu@200 { + compatible = "arm,cortex-a55"; + reg = <0x200>; + device_type = "cpu"; + next-level-cache = <&L3_CA55>; + enable-method = "psci"; + clocks = <&cpg CPG_CORE R9A09G047_CA55_0_CORECLK2>; + operating-points-v2 = <&cluster0_opp>; + }; + + cpu3: cpu@300 { + compatible = "arm,cortex-a55"; + reg = <0x300>; + device_type = "cpu"; + next-level-cache = <&L3_CA55>; + enable-method = "psci"; + clocks = <&cpg CPG_CORE R9A09G047_CA55_0_CORECLK3>; + operating-points-v2 = <&cluster0_opp>; + }; + + L3_CA55: cache-controller-0 { + compatible = "cache"; + cache-unified; + cache-size = <0x100000>; + cache-level = <3>; + }; + }; + + psci { + compatible = "arm,psci-1.0", "arm,psci-0.2"; + method = "smc"; + }; + + qextal_clk: qextal-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + /* This value must be overridden by the board */ + clock-frequency = <0>; + }; + + rtxin_clk: rtxin-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + /* This value must be overridden by the board */ + clock-frequency = <0>; + }; + + soc: soc { + compatible = "simple-bus"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + pinctrl: pinctrl@10410000 { + compatible = "renesas,r9a09g047-pinctrl"; + reg = <0 0x10410000 0 0x10000>; + clocks = <&cpg CPG_CORE R9A09G047_IOTOP_0_SHCLK>; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl 0 0 232>; + #interrupt-cells = <2>; + interrupt-controller; + power-domains = <&cpg>; + resets = <&cpg 0xa5>, <&cpg 0xa6>; + }; + + cpg: clock-controller@10420000 { + compatible = "renesas,r9a09g047-cpg"; + reg = <0 0x10420000 0 0x10000>; + clocks = <&audio_extal_clk>, <&rtxin_clk>, <&qextal_clk>; + clock-names = "audio_extal", "rtxin", "qextal"; + #clock-cells = <2>; + #reset-cells = <1>; + #power-domain-cells = <0>; + }; + + scif0: serial@11c01400 { + compatible = "renesas,scif-r9a09g047", "renesas,scif-r9a09g057"; + reg = <0 0x11c01400 0 0x400>; + interrupts = , + , + , + , + , + , + , + , + ; + interrupt-names = "eri", "rxi", "txi", "bri", "dri", + "tei", "tei-dri", "rxi-edge", "txi-edge"; + clocks = <&cpg CPG_MOD 0x8f>; + clock-names = "fck"; + power-domains = <&cpg>; + resets = <&cpg 0x95>; + status = "disabled"; + }; + + i2c0: i2c@14400400 { + compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057"; + reg = <0 0x14400400 0 0x400>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "tei", "ri", "ti", "spi", "sti", + "naki", "ali", "tmoi"; + clocks = <&cpg CPG_MOD 0x94>; + resets = <&cpg 0x98>; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c1: i2c@14400800 { + compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057"; + reg = <0 0x14400800 0 0x400>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "tei", "ri", "ti", "spi", "sti", + "naki", "ali", "tmoi"; + clocks = <&cpg CPG_MOD 0x95>; + resets = <&cpg 0x99>; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c2: i2c@14400c00 { + compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057"; + reg = <0 0x14400c00 0 0x400>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "tei", "ri", "ti", "spi", "sti", + "naki", "ali", "tmoi"; + clocks = <&cpg CPG_MOD 0x96>; + resets = <&cpg 0x9a>; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c3: i2c@14401000 { + compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057"; + reg = <0 0x14401000 0 0x400>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "tei", "ri", "ti", "spi", "sti", + "naki", "ali", "tmoi"; + clocks = <&cpg CPG_MOD 0x97>; + resets = <&cpg 0x9b>; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c4: i2c@14401400 { + compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057"; + reg = <0 0x14401400 0 0x400>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "tei", "ri", "ti", "spi", "sti", + "naki", "ali", "tmoi"; + clocks = <&cpg CPG_MOD 0x98>; + resets = <&cpg 0x9c>; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c5: i2c@14401800 { + compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057"; + reg = <0 0x14401800 0 0x400>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "tei", "ri", "ti", "spi", "sti", + "naki", "ali", "tmoi"; + clocks = <&cpg CPG_MOD 0x99>; + resets = <&cpg 0x9d>; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c6: i2c@14401c00 { + compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057"; + reg = <0 0x14401c00 0 0x400>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "tei", "ri", "ti", "spi", "sti", + "naki", "ali", "tmoi"; + clocks = <&cpg CPG_MOD 0x9a>; + resets = <&cpg 0x9e>; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c7: i2c@14402000 { + compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057"; + reg = <0 0x14402000 0 0x400>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "tei", "ri", "ti", "spi", "sti", + "naki", "ali", "tmoi"; + clocks = <&cpg CPG_MOD 0x9b>; + resets = <&cpg 0x9f>; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c8: i2c@11c01000 { + compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057"; + reg = <0 0x11c01000 0 0x400>; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "tei", "ri", "ti", "spi", "sti", + "naki", "ali", "tmoi"; + clocks = <&cpg CPG_MOD 0x93>; + resets = <&cpg 0xa0>; + power-domains = <&cpg>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + gic: interrupt-controller@14900000 { + compatible = "arm,gic-v3"; + reg = <0x0 0x14900000 0 0x20000>, + <0x0 0x14940000 0 0x80000>; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + interrupts = ; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", "hyp-virt"; + }; +}; diff --git a/arch/arm64/boot/dts/renesas/r9a09g047e37.dtsi b/arch/arm64/boot/dts/renesas/r9a09g047e37.dtsi new file mode 100644 index 000000000000..e50d9159e832 --- /dev/null +++ b/arch/arm64/boot/dts/renesas/r9a09g047e37.dtsi @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the RZ/G3E R9A09G047E37 SoC specific parts + * + * Copyright (C) 2024 Renesas Electronics Corp. + */ + +/dts-v1/; +#include "r9a09g047.dtsi" + +/ { + compatible = "renesas,r9a09g047e37", "renesas,r9a09g047"; + + cpus { + /delete-node/ cpu@200; + /delete-node/ cpu@300; + }; +}; diff --git a/arch/arm64/boot/dts/renesas/r9a09g047e57-smarc.dts b/arch/arm64/boot/dts/renesas/r9a09g047e57-smarc.dts new file mode 100644 index 000000000000..c063d47e2952 --- /dev/null +++ b/arch/arm64/boot/dts/renesas/r9a09g047e57-smarc.dts @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the RZ/G3E SMARC EVK board + * + * Copyright (C) 2024 Renesas Electronics Corp. + */ + +/dts-v1/; + +#include +#include "r9a09g047e57.dtsi" +#include "rzg3e-smarc-som.dtsi" +#include "renesas-smarc2.dtsi" + +/ { + model = "Renesas SMARC EVK version 2 based on r9a09g047e57"; + compatible = "renesas,smarc2-evk", "renesas,rzg3e-smarcm", + "renesas,r9a09g047e57", "renesas,r9a09g047"; +}; + +&pinctrl { + scif_pins: scif { + pins = "SCIF_TXD", "SCIF_RXD"; + renesas,output-impedance = <1>; + }; +}; + +&scif0 { + pinctrl-0 = <&scif_pins>; + pinctrl-names = "default"; +}; diff --git a/arch/arm64/boot/dts/renesas/r9a09g047e57.dtsi b/arch/arm64/boot/dts/renesas/r9a09g047e57.dtsi new file mode 100644 index 000000000000..98a5faebd47a --- /dev/null +++ b/arch/arm64/boot/dts/renesas/r9a09g047e57.dtsi @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the RZ/G3E R9A09G047E57 SoC specific parts + * + * Copyright (C) 2024 Renesas Electronics Corp. + */ + +/dts-v1/; +#include "r9a09g047.dtsi" + +/ { + compatible = "renesas,r9a09g047e57", "renesas,r9a09g047"; +}; diff --git a/arch/arm64/boot/dts/renesas/r9a09g057h44-rzv2h-evk.dts b/arch/arm64/boot/dts/renesas/r9a09g057h44-rzv2h-evk.dts index 4703da8e9cff..0b705c987b6c 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g057h44-rzv2h-evk.dts +++ b/arch/arm64/boot/dts/renesas/r9a09g057h44-rzv2h-evk.dts @@ -7,7 +7,7 @@ /dts-v1/; -#include +#include #include #include "r9a09g057.dtsi" @@ -56,7 +56,7 @@ vqmmc_sdhi1: regulator-vccq-sdhi1 { compatible = "regulator-gpio"; regulator-name = "SDHI1 VccQ"; - gpios = <&pinctrl RZG2L_GPIO(10, 2) GPIO_ACTIVE_HIGH>; + gpios = <&pinctrl RZV2H_GPIO(A, 2) GPIO_ACTIVE_HIGH>; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; gpios-states = <0>; @@ -158,38 +158,38 @@ &pinctrl { i2c0_pins: i2c0 { - pinmux = , /* I2C0_SDA */ - ; /* I2C0_SCL */ + pinmux = , /* I2C0_SDA */ + ; /* I2C0_SCL */ }; i2c1_pins: i2c1 { - pinmux = , /* I2C1_SDA */ - ; /* I2C1_SCL */ + pinmux = , /* I2C1_SDA */ + ; /* I2C1_SCL */ }; i2c2_pins: i2c2 { - pinmux = , /* I2C2_SDA */ - ; /* I2C2_SCL */ + pinmux = , /* I2C2_SDA */ + ; /* I2C2_SCL */ }; i2c3_pins: i2c3 { - pinmux = , /* I2C3_SDA */ - ; /* I2C3_SCL */ + pinmux = , /* I2C3_SDA */ + ; /* I2C3_SCL */ }; i2c6_pins: i2c6 { - pinmux = , /* I2C6_SDA */ - ; /* I2C6_SCL */ + pinmux = , /* I2C6_SDA */ + ; /* I2C6_SCL */ }; i2c7_pins: i2c7 { - pinmux = , /* I2C7_SDA */ - ; /* I2C7_SCL */ + pinmux = , /* I2C7_SDA */ + ; /* I2C7_SCL */ }; i2c8_pins: i2c8 { - pinmux = , /* I2C8_SDA */ - ; /* I2C8_SCL */ + pinmux = , /* I2C8_SDA */ + ; /* I2C8_SCL */ }; scif_pins: scif { @@ -199,7 +199,7 @@ sd1-pwr-en-hog { gpio-hog; - gpios = ; + gpios = ; output-high; line-name = "sd1_pwr_en"; }; @@ -219,7 +219,7 @@ }; sd1_cd { - pinmux = ; /* SD1_CD */ + pinmux = ; /* SD1_CD */ }; }; }; diff --git a/arch/arm64/boot/dts/renesas/renesas-smarc2.dtsi b/arch/arm64/boot/dts/renesas/renesas-smarc2.dtsi new file mode 100644 index 000000000000..e378d55e6e9b --- /dev/null +++ b/arch/arm64/boot/dts/renesas/renesas-smarc2.dtsi @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the RZ SMARC Carrier-II Board. + * + * Copyright (C) 2024 Renesas Electronics Corp. + */ + +/ { + model = "Renesas RZ SMARC Carrier-II Board"; + compatible = "renesas,smarc2-evk"; + + chosen { + bootargs = "ignore_loglevel"; + stdout-path = "serial3:115200n8"; + }; + + aliases { + serial3 = &scif0; + }; +}; + +&scif0 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/renesas/rzg3e-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3e-smarc-som.dtsi new file mode 100644 index 000000000000..6b583ae2ac52 --- /dev/null +++ b/arch/arm64/boot/dts/renesas/rzg3e-smarc-som.dtsi @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the R9A09G047E57 SMARC SoM board. + * + * Copyright (C) 2024 Renesas Electronics Corp. + */ + +/ { + compatible = "renesas,rzg3e-smarcm", "renesas,r9a09g047e57", "renesas,r9a09g047"; + + memory@48000000 { + device_type = "memory"; + /* First 128MB is reserved for secure area. */ + reg = <0x0 0x48000000 0x0 0xf8000000>; + }; +}; + +&audio_extal_clk { + clock-frequency = <48000000>; +}; + +&qextal_clk { + clock-frequency = <24000000>; +}; + +&rtxin_clk { + clock-frequency = <32768>; +}; diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi index 2ed01d391554..ef12c1c462a7 100644 --- a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi @@ -43,11 +43,6 @@ #endif }; - chosen { - bootargs = "ignore_loglevel"; - stdout-path = "serial0:115200n8"; - }; - memory@48000000 { device_type = "memory"; /* First 128MB is reserved for secure area. */ @@ -63,7 +58,6 @@ enable-active-high; }; -#if SW_CONFIG2 == SW_ON vccq_sdhi0: regulator1 { compatible = "regulator-gpio"; regulator-name = "SDHI0 VccQ"; @@ -73,8 +67,8 @@ gpios-states = <1>; states = <3300000 1>, <1800000 0>; }; -#else - reg_1p8v: regulator1 { + + reg_1p8v: regulator2 { compatible = "regulator-fixed"; regulator-name = "fixed-1.8V"; regulator-min-microvolt = <1800000>; @@ -82,9 +76,17 @@ regulator-boot-on; regulator-always-on; }; -#endif - vcc_sdhi2: regulator2 { + reg_3p3v: regulator3 { + compatible = "regulator-fixed"; + regulator-name = "fixed-3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + vcc_sdhi2: regulator4 { compatible = "regulator-fixed"; regulator-name = "SDHI2 Vcc"; regulator-min-microvolt = <3300000>; @@ -92,6 +94,16 @@ gpios = <&pinctrl RZG2L_GPIO(8, 1) GPIO_ACTIVE_HIGH>; enable-active-high; }; + + x3_clk: x3-clock { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <24000000>; + }; +}; + +&adc { + status = "okay"; }; #if SW_CONFIG3 == SW_ON @@ -152,6 +164,30 @@ &i2c1 { status = "okay"; + + versa3: clock-generator@68 { + compatible = "renesas,5l35023"; + reg = <0x68>; + clocks = <&x3_clk>; + #clock-cells = <1>; + assigned-clocks = <&versa3 0>, + <&versa3 1>, + <&versa3 2>, + <&versa3 3>, + <&versa3 4>, + <&versa3 5>; + assigned-clock-rates = <24000000>, + <12288000>, + <11289600>, + <25000000>, + <100000000>, + <100000000>; + renesas,settings = [ + 80 00 11 19 4c 42 dc 2f 06 7d 20 1a 5f 1e f2 27 + 00 40 00 00 00 00 00 00 06 0c 19 02 3f f0 90 86 + a0 80 30 30 9c + ]; + }; }; #if SW_CONFIG2 == SW_ON diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi index 4509151344c4..81b4ffd1417d 100644 --- a/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi @@ -12,10 +12,15 @@ / { aliases { i2c0 = &i2c0; - serial0 = &scif0; + serial3 = &scif0; mmc1 = &sdhi1; }; + chosen { + bootargs = "ignore_loglevel"; + stdout-path = "serial3:115200n8"; + }; + keys { compatible = "gpio-keys"; @@ -44,6 +49,23 @@ }; }; + snd_rzg3s: sound { + compatible = "simple-audio-card"; + simple-audio-card,format = "i2s"; + simple-audio-card,bitclock-master = <&cpu_dai>; + simple-audio-card,frame-master = <&cpu_dai>; + simple-audio-card,mclk-fs = <256>; + + cpu_dai: simple-audio-card,cpu { + sound-dai = <&ssi3>; + }; + + codec_dai: simple-audio-card,codec { + sound-dai = <&da7212>; + clocks = <&versa3 1>; + }; + }; + vcc_sdhi1: regulator-vcc-sdhi1 { compatible = "regulator-fixed"; regulator-name = "SDHI1 Vcc"; @@ -64,13 +86,56 @@ }; }; +&audio_clk2 { + clock-frequency = <12288000>; +}; + &i2c0 { status = "okay"; clock-frequency = <1000000>; + + da7212: codec@1a { + compatible = "dlg,da7212"; + reg = <0x1a>; + + clocks = <&versa3 1>; + clock-names = "mclk"; + + #sound-dai-cells = <0>; + + dlg,micbias1-lvl = <2500>; + dlg,micbias2-lvl = <2500>; + dlg,dmic-data-sel = "lrise_rfall"; + dlg,dmic-samplephase = "between_clkedge"; + dlg,dmic-clkrate = <3000000>; + + VDDA-supply = <®_1p8v>; + VDDSP-supply = <®_3p3v>; + VDDMIC-supply = <®_3p3v>; + VDDIO-supply = <®_1p8v>; + }; +}; + +&i2c1 { + status = "okay"; + + clock-frequency = <400000>; + + power-monitor@44 { + compatible = "renesas,isl28022"; + reg = <0x44>; + shunt-resistor-micro-ohms = <8000>; + renesas,average-samples = <32>; + }; }; &pinctrl { + audio_clock_pins: audio-clock { + pins = "AUDIO_CLK1", "AUDIO_CLK2"; + input-enable; + }; + key-1-gpio-hog { gpio-hog; gpios = ; @@ -128,6 +193,13 @@ pinmux = ; /* SD1_CD */ }; }; + + ssi3_pins: ssi3 { + pinmux = , /* BCK */ + , /* RCK */ + , /* TXD */ + ; /* RXD */ + }; }; &scif0 { @@ -148,3 +220,12 @@ max-frequency = <125000000>; status = "okay"; }; + +&ssi3 { + clocks = <&cpg CPG_MOD R9A08G045_SSI3_PCLK2>, + <&cpg CPG_MOD R9A08G045_SSI3_PCLK_SFR>, + <&versa3 2>, <&audio_clk2>; + pinctrl-names = "default"; + pinctrl-0 = <&ssi3_pins>, <&audio_clock_pins>; + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi index 5c211ed83049..2a157d1efb3d 100644 --- a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi @@ -4,8 +4,24 @@ * * Copyright (C) 2017 Renesas Electronics Corp. * Copyright (C) 2017 Cogent Embedded, Inc. + * + * Sample Audio settings: + * + * > amixer set "DVC Out" 1% + * > amixer set "DVC In" 20% + * + * // if you use xxxx-mix+split.dtsi + * > amixer -D hw:1 set "pcm3168a DAC1" 50% + * > amixer -D hw:1 set "pcm3168a DAC2" 50% + * > amixer -D hw:1 set "pcm3168a DAC3" 50% + * > amixer -D hw:1 set "pcm3168a DAC4" 50% + * + * // else + * > amixer -D hw:1 set "DAC1" 50% + * > amixer -D hw:1 set "DAC2" 50% + * > amixer -D hw:1 set "DAC3" 50% + * > amixer -D hw:1 set "DAC4" 50% */ - / { aliases { serial1 = &hscif0; diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi index cb11abba7bef..0c58d816c375 100644 --- a/arch/arm64/boot/dts/renesas/ulcb.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi @@ -4,6 +4,11 @@ * * Copyright (C) 2016 Renesas Electronics Corp. * Copyright (C) 2016 Cogent Embedded, Inc. + * + * Sample Audio settings: + * + * > amixer set "DVC Out" 1% + * > amixer set "DVC In" 20% */ #include diff --git a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-ard-audio-da7212.dtso b/arch/arm64/boot/dts/renesas/white-hawk-ard-audio-da7212.dtso similarity index 96% rename from arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-ard-audio-da7212.dtso rename to arch/arm64/boot/dts/renesas/white-hawk-ard-audio-da7212.dtso index e6cf304c77ee..c27b9b3d4e5f 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-ard-audio-da7212.dtso +++ b/arch/arm64/boot/dts/renesas/white-hawk-ard-audio-da7212.dtso @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Device Tree Source for the White Hawk board with ARD-AUDIO-DA7212 Board + * Device Tree Source for White Hawk (Single) board with ARD-AUDIO-DA7212 board * * You can find and buy "ARD-AUDIO-DA7212" at Digi-Key * @@ -27,12 +27,12 @@ * +----------------------------+ * |Breakout board | * | | +---------------+ - * |CN34 (I2C CN) | |J1 | + * |CN(30)34 (I2C CN) | |J1 | * | I2C0_SCL pin3 |<----->| pin20 SCL | * | I2C0_SDA pin5 |<----->| pin18 SDA | * | | +---------------+ * | | +-----------------------+ - * |CN4 (Power) | |J7 | + * |CN(300)4 (Power) | |J7 | * | 3v3 (v) pin9 |<----->| pin4 / pin8 3.3v | * | GND (v) pin3 / pin4 |<----->| pin12 / pin14 GND | * +----------------------------+ +-----------------------+ diff --git a/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi index 3006b0a64f41..9017c4475a7c 100644 --- a/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi +++ b/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi @@ -21,6 +21,7 @@ bus-type = ; clock-lanes = <0>; data-lanes = <1 2 3>; + line-orders = <0 3 0>; remote-endpoint = <&max96712_out0>; }; }; @@ -41,6 +42,7 @@ bus-type = ; clock-lanes = <0>; data-lanes = <1 2 3>; + line-orders = <0 3 0>; remote-endpoint = <&max96712_out1>; }; }; diff --git a/arch/arm64/boot/dts/renesas/white-hawk-single.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-single.dtsi new file mode 100644 index 000000000000..20e8232f2f32 --- /dev/null +++ b/arch/arm64/boot/dts/renesas/white-hawk-single.dtsi @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the White Hawk Single board + * + * Copyright (C) 2023-2024 Glider bv + */ + +#include "white-hawk-cpu-common.dtsi" +#include "white-hawk-common.dtsi" + +/ { + model = "Renesas White Hawk Single board"; + compatible = "renesas,white-hawk-single"; +}; + +&hscif0 { + uart-has-rtscts; +}; + +&hscif0_pins { + groups = "hscif0_data", "hscif0_ctrl"; + function = "hscif0"; +}; + +&pfc { + tsn0_pins: tsn0 { + mux { + groups = "tsn0_link", "tsn0_mdio", "tsn0_rgmii", + "tsn0_txcrefclk"; + function = "tsn0"; + }; + + link { + groups = "tsn0_link"; + bias-disable; + }; + + mdio { + groups = "tsn0_mdio"; + drive-strength = <24>; + bias-disable; + }; + + rgmii { + groups = "tsn0_rgmii"; + drive-strength = <24>; + bias-disable; + }; + }; +}; + +&tsn0 { + pinctrl-0 = <&tsn0_pins>; + pinctrl-names = "default"; + phy-mode = "rgmii"; + phy-handle = <&phy3>; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio1 23 GPIO_ACTIVE_LOW>; + reset-post-delay-us = <4000>; + + phy3: ethernet-phy@0 { + compatible = "ethernet-phy-id002b.0980", + "ethernet-phy-ieee802.3-c22"; + reg = <0>; + interrupts-extended = <&gpio4 3 IRQ_TYPE_LEVEL_LOW>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/rockchip/Makefile b/arch/arm64/boot/dts/rockchip/Makefile index 86cc418a2255..def1222c1907 100644 --- a/arch/arm64/boot/dts/rockchip/Makefile +++ b/arch/arm64/boot/dts/rockchip/Makefile @@ -111,6 +111,8 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-box-demo.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-lckfb-tspi.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-lubancat-1.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-nanopi-r3s.dtb +dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-bigtreetech-cb2-manta.dtb +dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-bigtreetech-pi2.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-bpi-r2-pro.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-evb1-v10.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-fastrhino-r66s.dtb @@ -129,6 +131,8 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-wolfvision-pf5.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-wolfvision-pf5-display-vz.dtbo dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-wolfvision-pf5-io-expander.dtbo dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3576-armsom-sige5.dtb +dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3576-evb1-v10.dtb +dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3582-radxa-e52c.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-armsom-sige7.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-armsom-w3.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-coolpi-cm5-evb.dtb @@ -137,11 +141,14 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6a-io.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6a-wifi.dtbo dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6b-io.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-evb1-v10.dtb +dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-firefly-itx-3588j.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-friendlyelec-cm3588-nas.dtb +dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-h96-max-v58.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-jaguar.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-nanopc-t6.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-nanopc-t6-lts.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-ok3588-c.dtb +dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-orangepi-5-max.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-orangepi-5-plus.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-quartzpro64.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-rock-5-itx.dtb diff --git a/arch/arm64/boot/dts/rockchip/rk3308-rock-s0.dts b/arch/arm64/boot/dts/rockchip/rk3308-rock-s0.dts index bd6419a5c20a..8311af4c8689 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-rock-s0.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-rock-s0.dts @@ -74,6 +74,23 @@ vin-supply = <&vcc5v0_sys>; }; + /* + * HW revision prior to v1.2 must pull GPIO4_D6 low to access sdmmc. + * This is modeled as an always-on active low fixed regulator. + */ + vcc_sd: regulator-3v3-vcc-sd { + compatible = "regulator-fixed"; + gpios = <&gpio4 RK_PD6 GPIO_ACTIVE_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&sdmmc_2030>; + regulator-name = "vcc_sd"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_io>; + }; + vcc5v0_sys: regulator-5v0-vcc-sys { compatible = "regulator-fixed"; regulator-name = "vcc5v0_sys"; @@ -181,6 +198,12 @@ }; }; + sdmmc { + sdmmc_2030: sdmmc-2030 { + rockchip,pins = <4 RK_PD6 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + wifi { wifi_reg_on: wifi-reg-on { rockchip,pins = <0 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>; @@ -233,7 +256,7 @@ cap-mmc-highspeed; cap-sd-highspeed; disable-wp; - vmmc-supply = <&vcc_io>; + vmmc-supply = <&vcc_sd>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-a1.dts b/arch/arm64/boot/dts/rockchip/rk3328-a1.dts index 8dfeaf1f8eb0..f7c4578865c5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-a1.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-a1.dts @@ -110,7 +110,6 @@ phy-supply = <&vcc_io>; pinctrl-names = "default"; pinctrl-0 = <&rgmiim1_pins>; - snps,aal; snps,pbl = <0x4>; tx_delay = <0x26>; rx_delay = <0x11>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2.dtsi b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2.dtsi index 1715d311e1f2..691d17022afb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2.dtsi @@ -142,7 +142,6 @@ phy-supply = <&vcc_io_33>; pinctrl-0 = <&rgmiim1_pins>; pinctrl-names = "default"; - snps,aal; mdio { compatible = "snps,dwmac-mdio"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi index 82021ffb0a49..4f193704e5dc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi @@ -113,7 +113,6 @@ phy-supply = <&vcc_io>; pinctrl-0 = <&rgmiim1_pins>; pinctrl-names = "default"; - snps,aal; mdio { compatible = "snps,dwmac-mdio"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts index 425de197ddb8..6310b58de77f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts @@ -153,9 +153,6 @@ phy-supply = <&vcc_io>; pinctrl-names = "default"; pinctrl-0 = <&rgmiim1_pins>; - snps,aal; - snps,rxpbl = <0x4>; - snps,txpbl = <0x4>; tx_delay = <0x26>; rx_delay = <0x11>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index 745d3e996418..e550b6eeeff3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -144,7 +144,6 @@ phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&rgmiim1_pins>; - snps,force_thresh_dma_mode; snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 0597de415fe0..7d992c3c01ce 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -333,6 +333,7 @@ power-domain@RK3328_PD_HEVC { reg = ; + clocks = <&cru SCLK_VENC_CORE>; #power-domain-cells = <0>; }; power-domain@RK3328_PD_VIDEO { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index d12e661dfd99..995b30a7aae0 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -182,7 +182,7 @@ snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; tx_delay = <0x10>; - rx_delay = <0x10>; + rx_delay = <0x23>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2-manta.dts b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2-manta.dts new file mode 100644 index 000000000000..97415d099d88 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2-manta.dts @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) + +/dts-v1/; + +#include "rk3566-bigtreetech-cb2.dtsi" + +/ { + model = "BigTreeTech CB2"; + compatible = "bigtreetech,cb2-manta", "bigtreetech,cb2", "rockchip,rk3566"; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi new file mode 100644 index 000000000000..a48351471764 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi @@ -0,0 +1,904 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) + +/dts-v1/; + +#include +#include +#include +#include +#include +#include "rk3566.dtsi" + +/ { + aliases { + ethernet0 = &gmac1; + mmc0 = &sdhci; + mmc1 = &sdmmc0; + }; + + chosen: chosen { + stdout-path = "serial2:1500000n8"; + }; + + ext_cam_clk: clock-25000000-cam { + compatible = "fixed-clock"; + clock-frequency = <25000000>; + clock-output-names = "ext_cam_clk"; + #clock-cells = <0>; + }; + + can_mcp2515_osc: clock-8000000-mcp2515 { + compatible = "fixed-clock"; + clock-frequency = <8000000>; + #clock-cells = <0>; + }; + + hdmi-con { + compatible = "hdmi-connector"; + type = "a"; + + port { + hdmi_con_in: endpoint { + remote-endpoint = <&hdmi_out_con>; + }; + }; + }; + + leds: leds { + compatible = "gpio-leds"; + + led-0 { + color = ; + function = LED_FUNCTION_POWER; + gpios = <&gpio4 RK_PA1 GPIO_ACTIVE_LOW>; + linux,default-trigger = "default-on"; + pinctrl-names = "default"; + pinctrl-0 =<&blue_led>; + }; + + led-1 { + color = ; + function = LED_FUNCTION_HEARTBEAT; + gpios = <&gpio0 RK_PB7 GPIO_ACTIVE_LOW>; + linux,default-trigger = "heartbeat"; + pinctrl-names = "default"; + pinctrl-0 =<&heartbeat_led>; + }; + }; + + fan: pwm-fan { + compatible = "pwm-fan"; + #cooling-cells = <2>; + cooling-levels = <0 50 100 150 200 255>; + pwms = <&pwm7 0 50000 0>; + }; + + rk809-sound { + compatible = "simple-audio-card"; + simple-audio-card,format = "i2s"; + simple-audio-card,name = "Analog RK809"; + simple-audio-card,mclk-fs = <256>; + + simple-audio-card,cpu { + sound-dai = <&i2s1_8ch>; + }; + + simple-audio-card,codec { + sound-dai = <&rk809>; + }; + }; + + sdio_pwrseq: sdio-pwrseq { + compatible = "mmc-pwrseq-simple"; + clocks = <&rk809 1>; + clock-names = "ext_clock"; + pinctrl-names = "default"; + pinctrl-0 = <&wifi_enable_h>; + post-power-on-delay-ms = <200>; + reset-gpios = <&gpio0 RK_PD3 GPIO_ACTIVE_LOW>; + }; + + vbus: regulator-vbus { + compatible = "regulator-fixed"; + regulator-name = "vbus"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vcc12v_dcin: regulator-vcc12v-dcin { + compatible = "regulator-fixed"; + regulator-name = "vcc12v_dcin"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + }; + + vcc3v3_pcie: regulator-vcc3v3-pcie { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3_pcie"; + enable-active-high; + gpios = <&gpio0 RK_PB1 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie_drv>; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc12v_dcin>; + }; + + vcc3v3_sys: regulator-vcc3v3-sys { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3_sys"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vbus>; + }; + + vcc5v0_host: regulator-vcc5v0-host { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio0 RK_PB6 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&vcc5v0_host_en>; + regulator-name = "vcc5v0_host3"; + regulator-always-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vcc5v0_otg: regulator-vcc5v0-otg { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&vcc5v0_otg_en>; + regulator-name = "vcc5v0_otg3"; + regulator-always-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vcc5v0_sys: regulator-vcc5v0-sys { + compatible = "regulator-fixed"; + regulator-name = "vcc5v0_sys"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vbus>; + }; + + vcc5v0_usb: regulator-vcc5v0-usb { + compatible = "regulator-fixed"; + regulator-name = "vcc5v0_usb"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vbus>; + }; + + vcc5v0_usb2b: regulator-vcc5v0-usb2b { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&vcc5v0_usb2b_en>; + regulator-name = "vcc5v0_usb2b"; + regulator-always-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vcc5v0_usb2t: regulator-vcc5v0-usb2t { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio0 RK_PD5 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&vcc5v0_usb2t_en>; + regulator-name = "vcc5v0_usb2t"; + regulator-always-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vcc_5v: regulator-vcc-5v { + compatible = "regulator-fixed"; + regulator-name = "vcc_5v"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc12v_dcin>; + }; + + vcc_sd: regulator-vcc-sd { + compatible = "regulator-fixed"; + regulator-max-microvolt = <3300000>; + regulator-min-microvolt = <3300000>; + regulator-name = "vcc_sd"; + vin-supply = <&vcc3v3_sys>; + }; +}; + +&combphy1 { + status = "okay"; +}; + +&combphy2 { + status = "okay"; +}; + +&cpu0 { + cpu-supply = <&vdd_cpu>; +}; + +&cpu1 { + cpu-supply = <&vdd_cpu>; +}; + +&cpu2 { + cpu-supply = <&vdd_cpu>; +}; + +&cpu3 { + cpu-supply = <&vdd_cpu>; +}; + +&gmac1 { + assigned-clocks = <&cru SCLK_GMAC1_RX_TX>, <&cru SCLK_GMAC1>; + assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru CLK_MAC1_2TOP>; + assigned-clock-rates = <0>, <125000000>; + clock_in_out = "input"; + phy-handle = <&rgmii_phy0>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1m0_miim + &gmac1m0_tx_bus2 + &gmac1m0_rx_bus2 + &gmac1m0_rgmii_clk + &gmac1m0_clkinout + &gmac1m0_rgmii_bus>; + status = "okay"; +}; + +&mdio1 { + rgmii_phy0: phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reset-delay-us = <20000>; + reset-gpios = <&gpio0 RK_PC5 GPIO_ACTIVE_LOW>; + reset-post-delay-us = <100000>; + reg = <0x0>; + }; +}; + +&gpu { + mali-supply = <&vdd_gpu>; + status = "okay"; +}; + +&hdmi { + avdd-0v9-supply = <&vdda0v9_image>; + avdd-1v8-supply = <&vcca1v8_image>; + status = "okay"; +}; + +&hdmi_in { + hdmi_in_vp0: endpoint { + remote-endpoint = <&vp0_out_hdmi>; + }; +}; + +&hdmi_out { + hdmi_out_con: endpoint { + remote-endpoint = <&hdmi_con_in>; + }; +}; + +&hdmi_sound { + status = "okay"; +}; + +&i2c0 { + status = "okay"; + + vdd_cpu: regulator@1c { + compatible = "tcs,tcs4525"; + reg = <0x1c>; + regulator-name = "vdd_cpu"; + regulator-min-microvolt = <712500>; + regulator-max-microvolt = <1390000>; + regulator-initial-mode = <1>; + regulator-ramp-delay = <2300>; + regulator-boot-on; + regulator-always-on; + vin-supply = <&vcc5v0_sys>; + fcs,suspend-voltage-selector = <1>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + rk809: pmic@20 { + compatible = "rockchip,rk809"; + reg = <0x20>; + interrupt-parent = <&gpio0>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; + assigned-clocks = <&cru I2S1_MCLKOUT_TX>; + assigned-clock-parents = <&cru CLK_I2S1_8CH_TX>; + #clock-cells = <1>; + clock-names = "mclk"; + clocks = <&cru I2S1_MCLKOUT_TX>; + pinctrl-names = "default", "pmic-sleep", + "pmic-power-off", "pmic-reset"; + pinctrl-0 = <&pmic_int>, <&i2s1m0_mclk>; + #sound-dai-cells = <0>; + system-power-controller; + wakeup-source; + + vcc1-supply = <&vcc3v3_sys>; + vcc2-supply = <&vcc3v3_sys>; + vcc3-supply = <&vcc3v3_sys>; + vcc4-supply = <&vcc3v3_sys>; + vcc5-supply = <&vcc3v3_sys>; + vcc6-supply = <&vcc3v3_sys>; + vcc7-supply = <&vcc3v3_sys>; + vcc8-supply = <&vcc3v3_sys>; + vcc9-supply = <&vcc3v3_sys>; + + regulators { + vdd_logic: DCDC_REG1 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <6001>; + regulator-initial-mode = <0x2>; + regulator-name = "vdd_logic"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_gpu: DCDC_REG2 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <6001>; + regulator-initial-mode = <0x2>; + regulator-name = "vdd_gpu"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_ddr: DCDC_REG3 { + regulator-always-on; + regulator-boot-on; + regulator-initial-mode = <0x2>; + regulator-name = "vcc_ddr"; + + regulator-state-mem { + regulator-on-in-suspend; + }; + }; + + vdd_npu: DCDC_REG4 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <6001>; + regulator-initial-mode = <0x2>; + regulator-name = "vdd_npu"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdda0v9_image: LDO_REG1 { + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + regulator-name = "vdda0v9_image"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdda_0v9: LDO_REG2 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + regulator-name = "vdda_0v9"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdda0v9_pmu: LDO_REG3 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + regulator-name = "vdda0v9_pmu"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <900000>; + }; + }; + + vccio_acodec: LDO_REG4 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3000000>; + regulator-name = "vccio_acodec"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vccio_sd: LDO_REG5 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vccio_sd"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc3v3_pmu: LDO_REG6 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc3v3_pmu"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <3300000>; + }; + }; + + vcca_1v8: LDO_REG7 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcca_1v8"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcca1v8_pmu: LDO_REG8 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcca1v8_pmu"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vcca1v8_image: LDO_REG9 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcca1v8_image"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_1v8: DCDC_REG5 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcc_1v8"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_3v3: SWITCH_REG1 { + regulator-always-on; + regulator-boot-on; + regulator-name = "vcc_3v3"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc3v3_sd: SWITCH_REG2 { + regulator-always-on; + regulator-boot-on; + regulator-name = "vcc3v3_sd"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + }; + + codec { + rockchip,mic-in-differential; + }; + }; +}; + +&i2c2 { + pinctrl-0 = <&i2c2m1_xfer>; +}; + +&i2c3 { + status = "okay"; + + tft_tp: touchscreen@48 { + compatible = "ti,tsc2007"; + reg = <0x48>; + status = "okay"; + ti,x-plate-ohms = <660>; + ti,rt-thr = <3000>; + ti,fuzzx = <32>; + ti,fuzzy = <16>; + }; +}; + +&i2s0_8ch { + status = "okay"; +}; + +&i2s1_8ch { + pinctrl-names = "default"; + pinctrl-0 = <&i2s1m0_sclktx &i2s1m0_lrcktx &i2s1m0_sdi0 &i2s1m0_sdo0>; + rockchip,trcm-sync-tx-only; + status = "okay"; +}; + +&spi1 { + pinctrl-names = "default"; + pinctrl-0 = <&spi1m1_cs0 &spi1m1_pins>; + + can_mcp2515: can@0 { + compatible = "microchip,mcp2515"; + reg = <0x00>; + clocks = <&can_mcp2515_osc>; + interrupt-parent = <&gpio4>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&mcp2515_int_pin>; + spi-max-frequency = <10000000>; + vdd-supply = <&vcc3v3_sys>; + xceiver-supply = <&vcc3v3_sys>; + }; +}; + +&spi3 { + pinctrl-names = "default"; + pinctrl-0 = <&spi3m1_cs0 &spi3m1_pins>; +}; + +&pcie2x1 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie_reset_h>; + reset-gpios = <&gpio1 RK_PB2 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc3v3_pcie>; + status = "okay"; +}; + +&pinctrl { + bt { + bt_enable: bt-enable-h { + rockchip,pins = <2 RK_PB7 RK_FUNC_GPIO &pcfg_pull_down>; + }; + + bt_host_wake: bt-host-wake-l { + rockchip,pins = <2 RK_PC1 RK_FUNC_GPIO &pcfg_pull_down>; + }; + + bt_wake: bt-wake-l { + rockchip,pins = <2 RK_PC0 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + pcie { + pcie_drv: pcie-drv { + rockchip,pins = <4 RK_PB1 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + pcie_reset_h: pcie-reset-h { + rockchip,pins = <1 RK_PB2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + pmic { + pmic_int: pmic-int { + rockchip,pins = <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + + sdio-pwrseq { + wifi_enable_h: wifi-enable-h { + rockchip,pins = <0 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + wifi_host_wake: wifi-host-wake-l { + rockchip,pins = <2 RK_PB1 RK_FUNC_GPIO &pcfg_pull_down>; + }; + }; + + usb { + vcc5v0_host_en: vcc5v0-host-en { + rockchip,pins = <0 RK_PB6 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + vcc5v0_otg_en: vcc5v0-otg-en { + rockchip,pins = <0 RK_PB5 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + vcc5v0_usb2t_en: vcc5v0-usb2t-en { + rockchip,pins = <3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + vcc5v0_usb2b_en: vcc5v0-usb2b-en { + rockchip,pins = <4 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + work-led { + heartbeat_led: led-heartbeat { + rockchip,pins = <0 RK_PB7 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + blue_led: led-blue { + rockchip,pins = <4 RK_PA1 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + mcp2515 { + mcp2515_int_pin: mcp2515-int-pin { + rockchip,pins = <4 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; +}; + +&pmu_io_domains { + pmuio1-supply = <&vcc3v3_pmu>; + pmuio2-supply = <&vcc3v3_pmu>; + vccio1-supply = <&vcc_3v3>; + vccio2-supply = <&vcc_1v8>; + vccio3-supply = <&vccio_sd>; + vccio4-supply = <&vcc_1v8>; + vccio5-supply = <&vcc_3v3>; + vccio6-supply = <&vcc_3v3>; + vccio7-supply = <&vcc_3v3>; + status = "okay"; +}; + +&pwm0 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm0m1_pins>; +}; + +&pwm12 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm12m1_pins>; +}; + +&pwm13 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm13m1_pins>; +}; + +&pwm14 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm14m1_pins>; +}; + +&pwm15 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm15m1_pins>; +}; + +&saradc { + vref-supply = <&vcca_1v8>; + status = "okay"; +}; + +&sdhci { + bus-width = <8>; + max-frequency = <200000000>; + non-removable; + pinctrl-names = "default"; + pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd>; + status = "okay"; +}; + +&sdmmc0 { + max-frequency = <150000000>; + bus-width = <4>; + cap-mmc-highspeed; + cap-sd-highspeed; + disable-wp; + pinctrl-names = "default"; + pinctrl-0 = <&sdmmc0_bus4 &sdmmc0_clk &sdmmc0_cmd &sdmmc0_det>; + vmmc-supply = <&vcc_sd>; + vqmmc-supply = <&vccio_sd>; + status = "okay"; +}; + +&sdmmc1 { + /* WiFi & BT combo module AMPAK AP6256 */ + #address-cells = <1>; + #size-cells = <0>; + bus-width = <4>; + cap-sd-highspeed; + cap-sdio-irq; + disable-wp; + keep-power-in-suspend; + max-frequency = <150000000>; + mmc-pwrseq = <&sdio_pwrseq>; + non-removable; + pinctrl-names = "default"; + pinctrl-0 = <&sdmmc1_bus4 &sdmmc1_cmd &sdmmc1_clk>; + rockchip,default-sample-phase = <90>; + status = "okay"; + + sdio-wifi@1 { + compatible = "brcm,bcm4329-fmac"; + reg = <1>; + interrupt-parent = <&gpio2>; + interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "host-wake"; + pinctrl-names = "default"; + pinctrl-0 = <&wifi_host_wake>; + brcm,drive-strength = <10>; + }; +}; + +&sfc { + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; +}; + +&tsadc { + status = "okay"; +}; + +&uart1 { + dma-names = "tx","rx"; + pinctrl-names = "default"; + pinctrl-0 = <&uart1m0_xfer &uart1m0_ctsn &uart1m0_rtsn>; + uart-has-rtscts; + status = "okay"; + + bluetooth { + compatible = "brcm,bcm4345c5"; + clocks = <&rk809 1>; + clock-names = "lpo"; + device-wakeup-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>; + host-wakeup-gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>; + shutdown-gpios = <&gpio2 RK_PB7 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&bt_host_wake &bt_wake &bt_enable>; + vbat-supply = <&vcc3v3_sys>; + vddio-supply = <&vcca1v8_pmu>; + }; +}; + +&uart2 { + status = "okay"; +}; + +&uart5 { + pinctrl-names = "default"; + pinctrl-0 = <&uart5m1_xfer>; +}; + +&uart7 { + pinctrl-names = "default"; + pinctrl-0 = <&uart7m2_xfer>; +}; + +&usb2phy0 { + status = "okay"; +}; + +&usb2phy0_host { + phy-supply = <&vcc5v0_host>; + status = "okay"; +}; + +&usb2phy0_otg { + phy-supply = <&vcc5v0_otg>; + status = "okay"; +}; + +&usb2phy1 { + status = "okay"; +}; + +&usb2phy1_host { + phy-supply = <&vcc5v0_usb2t>; + status = "okay"; +}; + +&usb2phy1_otg { + phy-supply = <&vcc5v0_usb2b>; + status = "okay"; +}; + +&usb_host0_ehci { + status = "okay"; +}; + +&usb_host0_ohci { + status = "okay"; +}; + +&usb_host0_xhci { + dr_mode = "host"; + extcon = <&usb2phy0>; + status = "okay"; +}; + +&usb_host1_ehci { + status = "okay"; +}; + +&usb_host1_ohci { + status = "okay"; +}; + +&usb_host1_xhci { + status = "okay"; +}; + +&vop { + assigned-clocks = <&cru DCLK_VOP0>, <&cru DCLK_VOP1>; + assigned-clock-parents = <&pmucru PLL_HPLL>, <&cru PLL_VPLL>; + status = "okay"; +}; + +&vop_mmu { + status = "okay"; +}; + +&vp0 { + vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 { + reg = ; + remote-endpoint = <&hdmi_in_vp0>; + }; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-pi2.dts b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-pi2.dts new file mode 100644 index 000000000000..7cd444caa18b --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-pi2.dts @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) + +/dts-v1/; + +#include "rk3566-bigtreetech-cb2.dtsi" + +/ { + model = "BigTreeTech Pi 2"; + compatible = "bigtreetech,pi2", "rockchip,rk3566"; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-mecsbc.dts b/arch/arm64/boot/dts/rockchip/rk3568-mecsbc.dts index c491dc4d4947..b1f185a58902 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-mecsbc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-mecsbc.dts @@ -206,12 +206,6 @@ }; }; -&i2c2 { - status = "okay"; - pinctrl-names = "default"; - pinctrl-0 = <&i2c2m0_xfer>; -}; - &i2c3 { pinctrl-names = "default"; pinctrl-0 = <&i2c3m0_xfer>; @@ -357,6 +351,19 @@ status = "okay"; }; +&spi0 { + /* use hardware chipselect on cs0 (cs1 unconnected) */ + pinctrl-names = "default"; + pinctrl-0 = <&spi0m0_pins>, <&spi0m0_cs0>; + status = "okay"; + + fram@0 { + compatible = "fujitsu,mb85rs128ty"; + reg = <0>; + spi-max-frequency = <33000000>; + }; +}; + &tsadc { rockchip,hw-tshut-mode = <1>; rockchip,hw-tshut-polarity = <0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts index e601d9271ba8..7bd32d230ad2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts @@ -50,6 +50,7 @@ color = ; function = LED_FUNCTION_DISK; gpios = <&gpio1 RK_PD5 GPIO_ACTIVE_LOW>; + label = "hdd1:green:disk"; linux,default-trigger = "disk-activity"; pinctrl-names = "default"; pinctrl-0 = <&hdd1_led_pin>; @@ -59,6 +60,7 @@ color = ; function = LED_FUNCTION_DISK; gpios = <&gpio1 RK_PD6 GPIO_ACTIVE_LOW>; + label = "hdd2:green:disk"; linux,default-trigger = "disk-activity"; pinctrl-names = "default"; pinctrl-0 = <&hdd2_led_pin>; @@ -68,6 +70,7 @@ color = ; function = LED_FUNCTION_DISK; gpios = <&gpio1 RK_PD7 GPIO_ACTIVE_LOW>; + label = "hdd3:green:disk"; linux,default-trigger = "disk-activity"; pinctrl-names = "default"; pinctrl-0 = <&hdd3_led_pin>; @@ -77,6 +80,7 @@ color = ; function = LED_FUNCTION_DISK; gpios = <&gpio2 RK_PA0 GPIO_ACTIVE_LOW>; + label = "hdd4:green:disk"; linux,default-trigger = "disk-activity"; pinctrl-names = "default"; pinctrl-0 = <&hdd4_led_pin>; @@ -483,6 +487,54 @@ }; }; +/* + * The MCU can provide system temperature too, but only by polling and of + * course also cannot set trip points. So attach to the cpu thermal-zone + * instead to control the fan. + */ +&cpu_thermal { + trips { + case_fan0: case-fan0 { + hysteresis = <2000>; + temperature = <35000>; + type = "active"; + }; + + case_fan1: case-fan1 { + hysteresis = <2000>; + temperature = <45000>; + type = "active"; + }; + + case_fan2: case-fan2 { + hysteresis = <2000>; + temperature = <65000>; + type = "active"; + }; + }; + + cooling-maps { + /* + * Always provide some air movement, due to small case + * full of harddrives. + */ + map1 { + cooling-device = <&fan THERMAL_NO_LIMIT 1>; + trip = <&case_fan0>; + }; + + map2 { + cooling-device = <&fan 2 3>; + trip = <&case_fan1>; + }; + + map3 { + cooling-device = <&fan 4 THERMAL_NO_LIMIT>; + trip = <&case_fan2>; + }; + }; +}; + &pcie30phy { data-lanes = <1 2>; status = "okay"; @@ -582,6 +634,15 @@ */ &uart0 { status = "okay"; + + mcu { + compatible = "qnap,ts433-mcu"; + + fan: fan-0 { + #cooling-cells = <2>; + cooling-levels = <0 64 89 128 166 204 221 238>; + }; + }; }; /* diff --git a/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5.dts b/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5.dts index e8243c908542..bb33fabae16e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5.dts @@ -53,7 +53,7 @@ pdm_codec: pdm-codec { compatible = "dmic-codec"; - num-channels = <1>; + num-channels = <2>; #sound-dai-cells = <0>; }; @@ -167,6 +167,10 @@ }; }; +&hdmi_sound { + status = "okay"; +}; + &i2c0 { status = "okay"; @@ -414,6 +418,10 @@ pinctrl-0 = <&i2c4m1_xfer>; }; +&i2s0_8ch { + status = "okay"; +}; + &pdm { pinctrl-0 = <&pdmm0_clk &pdmm0_sdi0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3568.dtsi b/arch/arm64/boot/dts/rockchip/rk3568.dtsi index ecaefe208e3e..695cccbdab0f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3568.dtsi @@ -350,6 +350,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY0_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY0>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf0>; #phy-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi index 62be06f3b863..e55390629114 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi @@ -1681,6 +1681,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY1_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY1>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf1>; #phy-cells = <1>; @@ -1697,6 +1698,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY2_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY2>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf2>; #phy-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3576-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3576-evb1-v10.dts new file mode 100644 index 000000000000..782ca000a644 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3576-evb1-v10.dts @@ -0,0 +1,731 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright (c) 2024 Rockchip Electronics Co., Ltd. + * + */ + +/dts-v1/; + +#include +#include +#include +#include +#include "rk3576.dtsi" + +/ { + model = "Rockchip RK3576 EVB V10 Board"; + compatible = "rockchip,rk3576-evb1-v10", "rockchip,rk3576"; + + aliases { + ethernet0 = &gmac0; + ethernet1 = &gmac1; + }; + + chosen: chosen { + stdout-path = "serial0:1500000n8"; + }; + + adc_keys: adc-keys { + compatible = "adc-keys"; + io-channels = <&saradc 1>; + io-channel-names = "buttons"; + keyup-threshold-microvolt = <1800000>; + poll-interval = <100>; + + button-back { + label = "back"; + linux,code = ; + press-threshold-microvolt = <1235000>; + }; + + button-menu { + label = "menu"; + linux,code = ; + press-threshold-microvolt = <890000>; + }; + + button-vol-down { + label = "volume down"; + linux,code = ; + press-threshold-microvolt = <417000>; + }; + + button-vol-up { + label = "volume up"; + linux,code = ; + press-threshold-microvolt = <17000>; + }; + }; + + leds: leds { + compatible = "gpio-leds"; + + work_led: led-0 { + gpios = <&gpio0 RK_PB4 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "heartbeat"; + }; + }; + + vbus5v0_typec: regulator-vbus5v0-typec { + compatible = "regulator-fixed"; + regulator-name = "vbus5v0_typec"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + enable-active-high; + gpio = <&gpio0 RK_PD1 GPIO_ACTIVE_HIGH>; + vin-supply = <&vcc5v0_device>; + pinctrl-names = "default"; + pinctrl-0 = <&usb_otg0_pwren>; + }; + + vcc12v_dcin: regulator-vcc12v-dcin { + compatible = "regulator-fixed"; + regulator-name = "vcc12v_dcin"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + }; + + vcc1v2_ufs_vccq_s0: regulator-vcc1v2-ufs-vccq-s0 { + compatible = "regulator-fixed"; + regulator-name = "vcc1v2_ufs_vccq_s0"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + vin-supply = <&vcc_sys>; + }; + + vcc1v8_ufs_vccq2_s0: regulator-vcc1v8-ufs-vccq2-s0 { + compatible = "regulator-fixed"; + regulator-name = "vcc1v8_ufs_vccq2_s0"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + vin-supply = <&vcc_1v8_s3>; + }; + + vcc3v3_lcd_n: regulator-vcc3v3-lcd0-n { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3_lcd0_n"; + regulator-boot-on; + enable-active-high; + gpio = <&gpio0 RK_PC6 GPIO_ACTIVE_HIGH>; + vin-supply = <&vcc_3v3_s0>; + }; + + vcc3v3_pcie0: regulator-vcc3v3-pcie0 { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3_pcie1"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + enable-active-high; + gpios = <&gpio3 RK_PD4 GPIO_ACTIVE_HIGH>; + startup-delay-us = <5000>; + vin-supply = <&vcc12v_dcin>; + }; + + vcc3v3_rtc_s5: regulator-vcc3v3-rtc-s5 { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3_rtc_s5"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_sys>; + }; + + vcc5v0_device: regulator-vcc5v0-device { + compatible = "regulator-fixed"; + regulator-name = "vcc5v0_device"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc12v_dcin>; + }; + + vcc5v0_host: regulator-vcc5v0-host { + compatible = "regulator-fixed"; + regulator-name = "vcc5v0_host"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + enable-active-high; + gpio = <&gpio0 RK_PC7 GPIO_ACTIVE_HIGH>; + vin-supply = <&vcc5v0_device>; + pinctrl-names = "default"; + pinctrl-0 = <&usb_host_pwren>; + }; + + vcc_sys: regulator-vcc5v0-sys { + compatible = "regulator-fixed"; + regulator-name = "vcc_sys"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc12v_dcin>; + }; + + vcc_1v1_nldo_s3: regulator-vcc-1v1-nldo-s3 { + compatible = "regulator-fixed"; + regulator-name = "vcc_1v1_nldo_s3"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + vin-supply = <&vcc_sys>; + }; + + vcc_1v8_s0: regulator-vcc-1v8-s0 { + compatible = "regulator-fixed"; + regulator-name = "vcc_1v8_s0"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + vin-supply = <&vcc_1v8_s3>; + }; + + vcc_2v0_pldo_s3: regulator-vcc-2v0-pldo-s3 { + compatible = "regulator-fixed"; + regulator-name = "vcc_2v0_pldo_s3"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <2000000>; + regulator-max-microvolt = <2000000>; + vin-supply = <&vcc_sys>; + }; + + vcc_3v3_s0: regulator-vcc-3v3-s0 { + compatible = "regulator-fixed"; + regulator-name = "vcc_3v3_s0"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_3v3_s3>; + }; + + vcc_ufs_s0: regulator-vcc-ufs-s0 { + compatible = "regulator-fixed"; + regulator-name = "vcc_ufs_s0"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_sys>; + }; +}; + +&cpu_l0 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_b0 { + cpu-supply = <&vdd_cpu_big_s0>; +}; + +&combphy1_psu { + status = "okay"; +}; + +&gmac0 { + clock_in_out = "output"; + phy-mode = "rgmii-rxid"; + phy-handle = <&rgmii_phy0>; + pinctrl-names = "default"; + pinctrl-0 = <ð0m0_miim + ð0m0_tx_bus2 + ð0m0_rx_bus2 + ð0m0_rgmii_clk + ð0m0_rgmii_bus + ðm0_clk0_25m_out>; + snps,reset-gpio = <&gpio2 RK_PB5 GPIO_ACTIVE_LOW>; + snps,reset-active-low; + snps,reset-delays-us = <0 20000 100000>; + tx_delay = <0x21>; + status = "okay"; +}; + +&gmac1 { + clock_in_out = "output"; + phy-handle = <&rgmii_phy1>; + phy-mode = "rgmii-rxid"; + pinctrl-names = "default"; + pinctrl-0 = <ð1m0_miim + ð1m0_tx_bus2 + ð1m0_rx_bus2 + ð1m0_rgmii_clk + ð1m0_rgmii_bus + ðm0_clk1_25m_out>; + snps,reset-gpio = <&gpio3 RK_PA3 GPIO_ACTIVE_LOW>; + snps,reset-active-low; + snps,reset-delays-us = <0 20000 100000>; + tx_delay = <0x20>; + status = "okay"; +}; + +&i2c1 { + status = "okay"; + + rk806: pmic@23 { + compatible = "rockchip,rk806"; + reg = <0x23>; + interrupt-parent = <&gpio0>; + interrupts = <6 IRQ_TYPE_LEVEL_LOW>; + gpio-controller; + #gpio-cells = <2>; + pinctrl-names = "default"; + pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, + <&rk806_dvs2_null>, <&rk806_dvs3_null>; + system-power-controller; + + vcc1-supply = <&vcc_sys>; + vcc2-supply = <&vcc_sys>; + vcc3-supply = <&vcc_sys>; + vcc4-supply = <&vcc_sys>; + vcc5-supply = <&vcc_sys>; + vcc6-supply = <&vcc_sys>; + vcc7-supply = <&vcc_sys>; + vcc8-supply = <&vcc_sys>; + vcc9-supply = <&vcc_sys>; + vcc10-supply = <&vcc_sys>; + vcc11-supply = <&vcc_2v0_pldo_s3>; + vcc12-supply = <&vcc_sys>; + vcc13-supply = <&vcc_1v1_nldo_s3>; + vcc14-supply = <&vcc_1v1_nldo_s3>; + vcca-supply = <&vcc_sys>; + + rk806_dvs1_null: dvs1-null-pins { + pins = "gpio_pwrctrl1"; + function = "pin_fun0"; + }; + + rk806_dvs2_null: dvs2-null-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun0"; + }; + + rk806_dvs3_null: dvs3-null-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun0"; + }; + + rk806_dvs1_slp: dvs1-slp-pins { + pins = "gpio_pwrctrl1"; + function = "pin_fun1"; + }; + + rk806_dvs1_pwrdn: dvs1-pwrdn-pins { + pins = "gpio_pwrctrl1"; + function = "pin_fun2"; + }; + + rk806_dvs1_rst: dvs1-rst-pins { + pins = "gpio_pwrctrl1"; + function = "pin_fun3"; + }; + + rk806_dvs2_slp: dvs2-slp-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun1"; + }; + + rk806_dvs2_pwrdn: dvs2-pwrdn-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun2"; + }; + + rk806_dvs2_rst: dvs2-rst-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun3"; + }; + + rk806_dvs2_dvs: dvs2-dvs-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun4"; + }; + + rk806_dvs2_gpio: dvs2-gpio-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun5"; + }; + + rk806_dvs3_slp: dvs3-slp-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun1"; + }; + + rk806_dvs3_pwrdn: dvs3-pwrdn-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun2"; + }; + + rk806_dvs3_rst: dvs3-rst-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun3"; + }; + + rk806_dvs3_dvs: dvs3-dvs-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun4"; + }; + + rk806_dvs3_gpio: dvs3-gpio-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun5"; + }; + + regulators { + vdd_cpu_big_s0: dcdc-reg1 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + regulator-name = "vdd_cpu_big_s0"; + regulator-enable-ramp-delay = <400>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_npu_s0: dcdc-reg2 { + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + regulator-name = "vdd_npu_s0"; + regulator-enable-ramp-delay = <400>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_lit_s0: dcdc-reg3 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + regulator-name = "vdd_cpu_lit_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vcc_3v3_s3: dcdc-reg4 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc_3v3_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <3300000>; + }; + }; + + vdd_gpu_s0: dcdc-reg5 { + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <900000>; + regulator-ramp-delay = <12500>; + regulator-name = "vdd_gpu_s0"; + regulator-enable-ramp-delay = <400>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <850000>; + }; + }; + + vddq_ddr_s0: dcdc-reg6 { + regulator-always-on; + regulator-boot-on; + regulator-name = "vddq_ddr_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_logic_s0: dcdc-reg7 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <800000>; + regulator-name = "vdd_logic_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_1v8_s3: dcdc-reg8 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcc_1v8_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vdd2_ddr_s3: dcdc-reg9 { + regulator-always-on; + regulator-boot-on; + regulator-name = "vdd2_ddr_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + }; + }; + + vdd_ddr_s0: dcdc-reg10 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <1200000>; + regulator-name = "vdd_ddr_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcca_1v8_s0: pldo-reg1 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcca_1v8_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcca1v8_pldo2_s0: pldo-reg2 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcca1v8_pldo2_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdda_1v2_s0: pldo-reg3 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-name = "vdda_1v2_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcca_3v3_s0: pldo-reg4 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcca_3v3_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vccio_sd_s0: pldo-reg5 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vccio_sd_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcca1v8_pldo6_s3: pldo-reg6 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcca1v8_pldo6_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vdd_0v75_s3: nldo-reg1 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <750000>; + regulator-name = "vdd_0v75_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vdda_ddr_pll_s0: nldo-reg2 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + regulator-name = "vdda_ddr_pll_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdda0v75_hdmi_s0: nldo-reg3 { + regulator-boot-on; + regulator-min-microvolt = <837500>; + regulator-max-microvolt = <837500>; + regulator-name = "vdda0v75_hdmi_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdda_0v85_s0: nldo-reg4 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + regulator-name = "vdda_0v85_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdda_0v75_s0: nldo-reg5 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + regulator-name = "vdda_0v75_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + }; + }; +}; + +&mdio0 { + rgmii_phy0: phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0x1>; + clocks = <&cru REFCLKO25M_GMAC0_OUT>; + }; +}; + +&mdio1 { + rgmii_phy1: phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0x1>; + clocks = <&cru REFCLKO25M_GMAC1_OUT>; + }; +}; + +&pinctrl { + usb { + usb_host_pwren: usb-host-pwren { + rockchip,pins = <0 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + usb_otg0_pwren: usb-otg0-pwren { + rockchip,pins = <0 RK_PD1 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + usbc0_int: usbc0-int { + rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; +}; + +&sdmmc { + bus-width = <4>; + cap-mmc-highspeed; + cap-sd-highspeed; + disable-wp; + max-frequency = <200000000>; + no-sdio; + no-mmc; + sd-uhs-sdr104; + vqmmc-supply = <&vccio_sd_s0>; + status = "okay"; +}; + +&saradc { + vref-supply = <&vcca_1v8_s0>; + status = "okay"; +}; + +&u2phy0 { + status = "okay"; +}; + +&u2phy0_otg { + phy-supply = <&vbus5v0_typec>; + status = "okay"; +}; + +&u2phy1 { + status = "okay"; +}; + +&u2phy1_otg { + phy-supply = <&vcc5v0_host>; + status = "okay"; +}; + +&uart0 { + status = "okay"; +}; + +&usbdp_phy { + rockchip,dp-lane-mux = <2 3>; + status = "okay"; +}; + +&usb_drd0_dwc3 { + dr_mode = "host"; + status = "okay"; +}; + +&usb_drd1_dwc3 { + dr_mode = "host"; + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3576.dtsi b/arch/arm64/boot/dts/rockchip/rk3576.dtsi index 436232ffe4d1..4dde954043ef 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3576.dtsi @@ -445,6 +445,58 @@ #size-cells = <2>; ranges; + usb_drd0_dwc3: usb@23000000 { + compatible = "rockchip,rk3576-dwc3", "snps,dwc3"; + reg = <0x0 0x23000000 0x0 0x400000>; + clocks = <&cru CLK_REF_USB3OTG0>, + <&cru CLK_SUSPEND_USB3OTG0>, + <&cru ACLK_USB3OTG0>; + clock-names = "ref_clk", "suspend_clk", "bus_clk"; + interrupts = ; + power-domains = <&power RK3576_PD_USB>; + resets = <&cru SRST_A_USB3OTG0>; + dr_mode = "otg"; + phys = <&u2phy0_otg>, <&usbdp_phy PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + phy_type = "utmi_wide"; + snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; + snps,dis-u2-freeclk-exists-quirk; + snps,dis-del-phy-power-chg-quirk; + snps,dis-tx-ipgap-linecheck-quirk; + snps,parkmode-disable-hs-quirk; + snps,parkmode-disable-ss-quirk; + status = "disabled"; + }; + + usb_drd1_dwc3: usb@23400000 { + compatible = "rockchip,rk3576-dwc3", "snps,dwc3"; + reg = <0x0 0x23400000 0x0 0x400000>; + clocks = <&cru CLK_REF_USB3OTG1>, + <&cru CLK_SUSPEND_USB3OTG1>, + <&cru ACLK_USB3OTG1>; + clock-names = "ref_clk", "suspend_clk", "bus_clk"; + interrupts = ; + power-domains = <&power RK3576_PD_PHP>; + resets = <&cru SRST_A_USB3OTG1>; + dr_mode = "otg"; + phys = <&u2phy1_otg>, <&combphy1_psu PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + phy_type = "utmi_wide"; + snps,dis_enblslpm_quirk; + snps,dis-u1-entry-quirk; + snps,dis-u2-entry-quirk; + snps,dis-u2-freeclk-exists-quirk; + snps,dis-del-phy-power-chg-quirk; + snps,dis-tx-ipgap-linecheck-quirk; + snps,dis_rxdet_inp3_quirk; + snps,parkmode-disable-hs-quirk; + snps,parkmode-disable-ss-quirk; + dma-coherent; + status = "disabled"; + }; + sys_grf: syscon@2600a000 { compatible = "rockchip,rk3576-sys-grf", "syscon"; reg = <0x0 0x2600a000 0x0 0x2000>; @@ -515,6 +567,65 @@ reg = <0x0 0x2602c000 0x0 0x2000>; }; + usb2phy_grf: syscon@2602e000 { + compatible = "rockchip,rk3576-usb2phy-grf", "syscon", "simple-mfd"; + reg = <0x0 0x2602e000 0x0 0x4000>; + #address-cells = <1>; + #size-cells = <1>; + + u2phy0: usb2-phy@0 { + compatible = "rockchip,rk3576-usb2phy"; + reg = <0x0 0x10>; + resets = <&cru SRST_OTGPHY_0>, <&cru SRST_P_USBPHY_GRF_0>; + reset-names = "phy", "apb"; + clocks = <&cru CLK_PHY_REF_SRC>, + <&cru ACLK_MMU2>, + <&cru ACLK_SLV_MMU2>; + clock-names = "phyclk", "aclk", "aclk_slv"; + clock-output-names = "usb480m_phy0"; + #clock-cells = <0>; + status = "disabled"; + + u2phy0_otg: otg-port { + #phy-cells = <0>; + interrupts = , + , + ; + interrupt-names = "otg-bvalid", "otg-id", "linestate"; + status = "disabled"; + }; + }; + + u2phy1: usb2-phy@2000 { + compatible = "rockchip,rk3576-usb2phy"; + reg = <0x2000 0x10>; + resets = <&cru SRST_OTGPHY_1>, <&cru SRST_P_USBPHY_GRF_1>; + reset-names = "phy", "apb"; + clocks = <&cru CLK_PHY_REF_SRC>, + <&cru ACLK_MMU1>, + <&cru ACLK_SLV_MMU1>; + clock-names = "phyclk", "aclk", "aclk_slv"; + clock-output-names = "usb480m_phy1"; + #clock-cells = <0>; + status = "disabled"; + + u2phy1_otg: otg-port { + #phy-cells = <0>; + interrupts = , + , + ; + interrupt-names = "otg-bvalid", "otg-id", "linestate"; + status = "disabled"; + }; + }; + }; + + vo1_grf: syscon@26036000 { + compatible = "rockchip,rk3576-vo1-grf", "syscon"; + reg = <0x0 0x26036000 0x0 0x100>; + clocks = <&cru PCLK_VO1_ROOT>; + }; + sdgmac_grf: syscon@26038000 { compatible = "rockchip,rk3576-sdgmac-grf", "syscon"; reg = <0x0 0x26038000 0x0 0x1000>; @@ -1587,6 +1698,64 @@ status = "disabled"; }; + combphy0_ps: phy@2b050000 { + compatible = "rockchip,rk3576-naneng-combphy"; + reg = <0x0 0x2b050000 0x0 0x100>; + #phy-cells = <1>; + clocks = <&cru CLK_REF_PCIE0_PHY>, + <&cru PCLK_PCIE2_COMBOPHY0>, + <&cru PCLK_PCIE0>; + clock-names = "ref", "apb", "pipe"; + assigned-clocks = <&cru CLK_REF_PCIE0_PHY>; + assigned-clock-rates = <100000000>; + resets = <&cru SRST_PCIE0_PIPE_PHY>, + <&cru SRST_P_PCIE2_COMBOPHY0>; + reset-names = "phy", "apb"; + rockchip,pipe-grf = <&php_grf>; + rockchip,pipe-phy-grf = <&pipe_phy0_grf>; + status = "disabled"; + }; + + combphy1_psu: phy@2b060000 { + compatible = "rockchip,rk3576-naneng-combphy"; + reg = <0x0 0x2b060000 0x0 0x100>; + #phy-cells = <1>; + clocks = <&cru CLK_REF_PCIE1_PHY>, + <&cru PCLK_PCIE2_COMBOPHY1>, + <&cru PCLK_PCIE1>; + clock-names = "ref", "apb", "pipe"; + assigned-clocks = <&cru CLK_REF_PCIE1_PHY>; + assigned-clock-rates = <100000000>; + resets = <&cru SRST_PCIE1_PIPE_PHY>, + <&cru SRST_P_PCIE2_COMBOPHY1>; + reset-names = "phy", "apb"; + rockchip,pipe-grf = <&php_grf>; + rockchip,pipe-phy-grf = <&pipe_phy1_grf>; + status = "disabled"; + }; + + usbdp_phy: phy@2b010000 { + compatible = "rockchip,rk3576-usbdp-phy"; + reg = <0x0 0x2b010000 0x0 0x10000>; + #phy-cells = <1>; + clocks = <&cru CLK_PHY_REF_SRC >, + <&cru CLK_USBDP_COMBO_PHY_IMMORTAL>, + <&cru PCLK_USBDPPHY>, + <&u2phy0>; + clock-names = "refclk", "immortal", "pclk", "utmi"; + resets = <&cru SRST_USBDP_COMBO_PHY_INIT>, + <&cru SRST_USBDP_COMBO_PHY_CMN>, + <&cru SRST_USBDP_COMBO_PHY_LANE>, + <&cru SRST_USBDP_COMBO_PHY_PCS>, + <&cru SRST_P_USBDPPHY>; + reset-names = "init", "cmn", "lane", "pcs_apb", "pma_apb"; + rockchip,u2phy-grf = <&usb2phy_grf>; + rockchip,usb-grf = <&usb_grf>; + rockchip,usbdpphy-grf = <&usbdpphy_grf>; + rockchip,vo-grf = <&vo1_grf>; + status = "disabled"; + }; + sram: sram@3ff88000 { compatible = "mmio-sram"; reg = <0x0 0x3ff88000 0x0 0x78000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts b/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts new file mode 100644 index 000000000000..e04f21d8c831 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts @@ -0,0 +1,743 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright (c) 2024 Radxa Computer (Shenzhen) Co., Ltd. + */ + +/dts-v1/; + +#include +#include +#include +#include +#include +#include "rk3588s.dtsi" + +/ { + model = "Radxa E52C"; + compatible = "radxa,e52c", "rockchip,rk3582", "rockchip,rk3588s"; + + aliases { + mmc0 = &sdhci; + mmc1 = &sdmmc; + }; + + chosen { + stdout-path = "serial2:1500000n8"; + }; + + keys-0 { + compatible = "adc-keys"; + io-channels = <&saradc 0>; + io-channel-names = "buttons"; + keyup-threshold-microvolt = <18000>; + poll-interval = <100>; + + button-0 { + label = "Maskrom"; + linux,code = ; + press-threshold-microvolt = <0>; + }; + }; + + keys-1 { + compatible = "gpio-keys"; + pinctrl-names = "default"; + pinctrl-0 = <&btn_0>; + + button-1 { + label = "User"; + gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_LOW>; + linux,code = ; + wakeup-source; + }; + }; + + leds-0 { + compatible = "gpio-leds"; + pinctrl-names = "default"; + pinctrl-0 = <&led_0>; + + led-0 { + color = ; + default-state = "on"; + function = LED_FUNCTION_STATUS; + gpios = <&gpio3 RK_PC4 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "heartbeat"; + }; + }; + + leds-1 { + compatible = "pwm-leds"; + + led-1 { + color = ; + default-state = "on"; + function = LED_FUNCTION_LAN; + linux,default-trigger = "netdev"; + pwms = <&pwm14 0 1000000 PWM_POLARITY_INVERTED>; + max-brightness = <255>; + }; + + led-2 { + color = ; + default-state = "on"; + function = LED_FUNCTION_WAN; + linux,default-trigger = "netdev"; + pwms = <&pwm11 0 1000000 PWM_POLARITY_INVERTED>; + max-brightness = <255>; + }; + }; + + vcc_1v1_nldo_s3: regulator-1v1 { + compatible = "regulator-fixed"; + regulator-name = "vcc_1v1_nldo_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + vin-supply = <&vcc_sysin>; + }; + + vcc_3v3_pmu: regulator-3v3-0 { + compatible = "regulator-fixed"; + regulator-name = "vcc_3v3_pmu"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_3v3_s3>; + }; + + vcc_3v3_s0: regulator-3v3-1 { + compatible = "regulator-fixed"; + regulator-name = "vcc_3v3_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_3v3_s3>; + }; + + vcca: regulator-4v0 { + compatible = "regulator-fixed"; + regulator-name = "vcca"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <4000000>; + regulator-max-microvolt = <4000000>; + vin-supply = <&vcc_sysin>; + }; + + vcc5v0_usb_otg0: regulator-5v0-0 { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio0 RK_PD4 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&usb_otg_pwren_h>; + regulator-name = "vcc5v0_usb_otg0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc_sysin>; + }; + + vcc_5v0: regulator-5v0-1 { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&vcc_5v0_pwren_h>; + regulator-name = "vcc_5v0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc_sysin>; + }; + + vcc_sysin: regulator-5v0-2 { + compatible = "regulator-fixed"; + regulator-name = "vcc_sysin"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; +}; + +&combphy0_ps { + status = "okay"; +}; + +&combphy2_psu { + status = "okay"; +}; + +/* + * In the Rockchip RK3582 SoC, some CPU cores end up disabled + * and unused because they're marked in the efuses as defective. + * The disabling in the DT is performed by the boot loader. + */ +&cpu_b0 { + cpu-supply = <&vdd_cpu_big0_s0>; +}; + +&cpu_b1 { + cpu-supply = <&vdd_cpu_big0_s0>; +}; + +&cpu_b2 { + cpu-supply = <&vdd_cpu_big1_s0>; +}; + +&cpu_b3 { + cpu-supply = <&vdd_cpu_big1_s0>; +}; + +&cpu_l0 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l1 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l2 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l3 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0m2_xfer>; + status = "okay"; + + vdd_cpu_big0_s0: regulator@42 { + compatible = "rockchip,rk8602"; + reg = <0x42>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_cpu_big0_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc_sysin>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_big1_s0: regulator@43 { + compatible = "rockchip,rk8603", "rockchip,rk8602"; + reg = <0x43>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_cpu_big1_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc_sysin>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + eeprom@50 { + compatible = "belling,bl24c16a", "atmel,24c16"; + reg = <0x50>; + pagesize = <16>; + vcc-supply = <&vcc_3v3_pmu>; + }; +}; + +&i2c2 { + status = "okay"; + + vdd_npu_s0: regulator@42 { + compatible = "rockchip,rk8602"; + reg = <0x42>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_npu_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc_sysin>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; +}; + +&i2c5 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c5m2_xfer>; + status = "okay"; + + rtc@51 { + compatible = "haoyu,hym8563"; + reg = <0x51>; + #clock-cells = <0>; + clock-output-names = "rtcic_32kout"; + interrupt-parent = <&gpio0>; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&rtc_int_l>; + wakeup-source; + }; +}; + +&pcie2x1l1 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie20x1_1_perstn_m1>; + reset-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc_3v3_s3>; + status = "okay"; +}; + +&pcie2x1l2 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie20x1_2_perstn_m0>; + reset-gpios = <&gpio3 RK_PD1 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc_3v3_s3>; + status = "okay"; +}; + +&pinctrl { + keys { + btn_0: button-0 { + rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + leds { + led_0: led-0 { + rockchip,pins = <3 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + pcie { + pcie20x1_1_perstn_m1: pcie-1 { + rockchip,pins = <4 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + pcie20x1_2_perstn_m0: pcie-2 { + rockchip,pins = <3 RK_PD1 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + regulators { + vcc_5v0_pwren_h: regulator-5v0-1 { + rockchip,pins = <4 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + rtc { + rtc_int_l: rtc-0 { + rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + usb { + usb_otg_pwren_h: regulator-5v0-0 { + rockchip,pins = <0 RK_PD4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; +}; + +&pwm11 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm11m1_pins>; + status = "okay"; +}; + +&pwm14 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm14m1_pins>; + status = "okay"; +}; + +&saradc { + vref-supply = <&vcca_1v8_s0>; + status = "okay"; +}; + +&sdhci { + bus-width = <8>; + cap-mmc-highspeed; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + no-sd; + no-sdio; + non-removable; + vmmc-supply = <&vcc_3v3_s0>; + vqmmc-supply = <&vcc_1v8_s3>; + status = "okay"; +}; + +&sdmmc { + bus-width = <4>; + cap-mmc-highspeed; + cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; + disable-wp; + no-sdio; + sd-uhs-sdr104; + vmmc-supply = <&vcc_3v3_s3>; + vqmmc-supply = <&vccio_sd_s0>; + status = "okay"; +}; + +&spi2 { + status = "okay"; + assigned-clocks = <&cru CLK_SPI2>; + assigned-clock-rates = <200000000>; + num-cs = <1>; + pinctrl-names = "default"; + pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>; + + pmic@0 { + compatible = "rockchip,rk806"; + reg = <0>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio0>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, + <&rk806_dvs2_null>, <&rk806_dvs3_null>; + spi-max-frequency = <1000000>; + system-power-controller; + + vcc1-supply = <&vcc_sysin>; + vcc2-supply = <&vcc_sysin>; + vcc3-supply = <&vcc_sysin>; + vcc4-supply = <&vcc_sysin>; + vcc5-supply = <&vcc_sysin>; + vcc6-supply = <&vcc_sysin>; + vcc7-supply = <&vcc_sysin>; + vcc8-supply = <&vcc_sysin>; + vcc9-supply = <&vcc_sysin>; + vcc10-supply = <&vcc_sysin>; + vcc11-supply = <&vcc_2v0_pldo_s3>; + vcc12-supply = <&vcc_sysin>; + vcc13-supply = <&vcc_1v1_nldo_s3>; + vcc14-supply = <&vcc_1v1_nldo_s3>; + vcca-supply = <&vcca>; + + rk806_dvs1_null: dvs1-null-pins { + pins = "gpio_pwrctrl1"; + function = "pin_fun0"; + }; + + rk806_dvs2_null: dvs2-null-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun0"; + }; + + rk806_dvs3_null: dvs3-null-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun0"; + }; + + regulators { + vdd_gpu_s0: dcdc-reg1 { + regulator-name = "vdd_gpu_s0"; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <400>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_lit_s0: dcdc-reg2 { + regulator-name = "vdd_cpu_lit_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_logic_s0: dcdc-reg3 { + regulator-name = "vdd_logic_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <675000>; + regulator-max-microvolt = <750000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vdd_vdenc_s0: dcdc-reg4 { + regulator-name = "vdd_vdenc_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_ddr_s0: dcdc-reg5 { + regulator-name = "vdd_ddr_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <675000>; + regulator-max-microvolt = <900000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <850000>; + }; + }; + + vdd2_ddr_s3: dcdc-reg6 { + regulator-name = "vdd2_ddr_s3"; + regulator-always-on; + regulator-boot-on; + + regulator-state-mem { + regulator-on-in-suspend; + }; + }; + + vcc_2v0_pldo_s3: dcdc-reg7 { + regulator-name = "vcc_2v0_pldo_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <2000000>; + regulator-max-microvolt = <2000000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <2000000>; + }; + }; + + vcc_3v3_s3: dcdc-reg8 { + regulator-name = "vcc_3v3_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <3300000>; + }; + }; + + vddq_ddr_s0: dcdc-reg9 { + regulator-name = "vddq_ddr_s0"; + regulator-always-on; + regulator-boot-on; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_1v8_s3: dcdc-reg10 { + regulator-name = "vcc_1v8_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vcc_1v8_s0: pldo-reg1 { + regulator-name = "vcc_1v8_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vcca_1v8_s0: pldo-reg2 { + regulator-name = "vcca_1v8_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vdda_1v2_s0: pldo-reg3 { + regulator-name = "vdda_1v2_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcca_3v3_s0: pldo-reg4 { + regulator-name = "vcca_3v3_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <3300000>; + }; + }; + + vccio_sd_s0: pldo-reg5 { + regulator-name = "vccio_sd_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + pldo6_s3: pldo-reg6 { + regulator-name = "pldo6_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vdd_0v75_s3: nldo-reg1 { + regulator-name = "vdd_0v75_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vdda_ddr_pll_s0: nldo-reg2 { + regulator-name = "vdda_ddr_pll_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <850000>; + }; + }; + + vdda_0v75_s0: nldo-reg3 { + regulator-name = "vdda_0v75_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vdda_0v85_s0: nldo-reg4 { + regulator-name = "vdda_0v85_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_0v75_s0: nldo-reg5 { + regulator-name = "vdd_0v75_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + }; + }; +}; + +&tsadc { + status = "okay"; +}; + +&u2phy0 { + status = "okay"; +}; + +&u2phy0_otg { + phy-supply = <&vcc5v0_usb_otg0>; + status = "okay"; +}; + +&uart2 { + pinctrl-0 = <&uart2m0_xfer>; + status = "okay"; +}; + +&usb_host0_xhci { + dr_mode = "host"; + status = "okay"; +}; + +&usbdp_phy0 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi index a337f3fb8377..8cfa30837ce7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi @@ -555,7 +555,6 @@ ; interrupt-names = "eventq", "gerror", "priq", "cmdq-sync"; #iommu-cells = <1>; - status = "disabled"; }; mmu600_php: iommu@fcb00000 { @@ -1686,6 +1685,7 @@ linux,pci-domain = <3>; max-link-speed = <2>; msi-map = <0x3000 &its0 0x3000 0x1000>; + iommu-map = <0x3000 &mmu600_pcie 0x3000 0x1000>; num-lanes = <1>; phys = <&combphy2_psu PHY_TYPE_PCIE>; phy-names = "pcie-phy"; @@ -1737,6 +1737,7 @@ linux,pci-domain = <4>; max-link-speed = <2>; msi-map = <0x4000 &its0 0x4000 0x1000>; + iommu-map = <0x4000 &mmu600_pcie 0x4000 0x1000>; num-lanes = <1>; phys = <&combphy0_ps PHY_TYPE_PCIE>; phy-names = "pcie-phy"; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi index 05ae9bdcfbbd..7125790bbed2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi @@ -10,6 +10,15 @@ stdout-path = "serial2:1500000n8"; }; + /* Unnamed gated oscillator: 100MHz,3.3V,3225 */ + pcie30_port0_refclk: pcie30_port1_refclk: pcie-oscillator { + compatible = "gated-fixed-clock"; + #clock-cells = <0>; + clock-frequency = <100000000>; + clock-output-names = "pcie30_refclk"; + vdd-supply = <&vcc3v3_pi6c_05>; + }; + vcc3v3_pcie2x1l0: regulator-vcc3v3-pcie2x1l0 { compatible = "regulator-fixed"; regulator-name = "vcc3v3_pcie2x1l0"; @@ -19,26 +28,26 @@ vin-supply = <&vcc_3v3_s3>; }; - vcc3v3_pcie3x2: regulator-vcc3v3-pcie3x2 { + vcc3v3_bkey: regulator-vcc3v3-bkey { compatible = "regulator-fixed"; enable-active-high; gpios = <&gpio2 RK_PC4 GPIO_ACTIVE_HIGH>; /* PCIE_4G_PWEN */ pinctrl-names = "default"; - pinctrl-0 = <&pcie3x2_vcc3v3_en>; - regulator-name = "vcc3v3_pcie3x2"; + pinctrl-0 = <&pcie_4g_pwen>; + regulator-name = "vcc3v3_bkey"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; startup-delay-us = <5000>; vin-supply = <&vcc5v0_sys>; }; - vcc3v3_pcie3x4: regulator-vcc3v3-pcie3x4 { + vcc3v3_pcie30: vcc3v3_pi6c_05: regulator-vcc3v3-pi6c-05 { compatible = "regulator-fixed"; enable-active-high; gpios = <&gpio2 RK_PC5 GPIO_ACTIVE_HIGH>; /* PCIE30x4_PWREN_H */ pinctrl-names = "default"; - pinctrl-0 = <&pcie3x4_vcc3v3_en>; - regulator-name = "vcc3v3_pcie3x4"; + pinctrl-0 = <&pcie30x4_pwren_h>; + regulator-name = "vcc3v3_pcie30"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; startup-delay-us = <5000>; @@ -98,24 +107,52 @@ }; &pcie30phy { - status = "okay"; -}; - -/* B-Key and E-Key */ -&pcie3x2 { - pinctrl-names = "default"; - pinctrl-0 = <&pcie3x2_rst>; - reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>; /* PCIE30X4_PERSTn_M1_L */ - vpcie3v3-supply = <&vcc3v3_pcie3x2>; + data-lanes = <1 1 2 2>; + /* separate clock lines from the clock generator to phy and devices */ + rockchip,rx-common-refclk-mode = <0 0 0 0>; status = "okay"; }; /* M-Key */ -&pcie3x4 { +&pcie3x2 { + /* + * The board has a "pcie_refclk" oscillator that needs enabling, + * so add it to the list of clocks. + */ + clocks = <&cru ACLK_PCIE_2L_MSTR>, <&cru ACLK_PCIE_2L_SLV>, + <&cru ACLK_PCIE_2L_DBI>, <&cru PCLK_PCIE_2L>, + <&cru CLK_PCIE_AUX1>, <&cru CLK_PCIE2L_PIPE>, + <&pcie30_port1_refclk>; + clock-names = "aclk_mst", "aclk_slv", + "aclk_dbi", "pclk", + "aux", "pipe", + "ref"; + num-lanes = <2>; pinctrl-names = "default"; - pinctrl-0 = <&pcie3x4_rst>; + pinctrl-0 = <&pcie30x2_perstn_m1_l>; reset-gpios = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>; /* PCIE30X2_PERSTn_M1_L */ - vpcie3v3-supply = <&vcc3v3_pcie3x4>; + vpcie3v3-supply = <&vcc3v3_pcie30>; + status = "okay"; +}; + +/* B-Key and E-Key */ +&pcie3x4 { + /* + * The board has a "pcie_refclk" oscillator that needs enabling, + * so add it to the list of clocks. + */ + clocks = <&cru ACLK_PCIE_4L_MSTR>, <&cru ACLK_PCIE_4L_SLV>, + <&cru ACLK_PCIE_4L_DBI>, <&cru PCLK_PCIE_4L>, + <&cru CLK_PCIE_AUX0>, <&cru CLK_PCIE4L_PIPE>, + <&pcie30_port0_refclk>; + clock-names = "aclk_mst", "aclk_slv", + "aclk_dbi", "pclk", + "aux", "pipe", + "ref"; + pinctrl-names = "default"; + pinctrl-0 = <&pcie30x4_perstn_m1_l>; + reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>; /* PCIE30X4_PERSTn_M1_L */ + vpcie3v3-supply = <&vcc3v3_bkey>; status = "okay"; }; @@ -127,20 +164,20 @@ }; pcie3 { - pcie3x2_rst: pcie3x2-rst { - rockchip,pins = <4 RK_PB6 RK_FUNC_GPIO &pcfg_pull_none>; - }; - - pcie3x2_vcc3v3_en: pcie3x2-vcc3v3-en { - rockchip,pins = <2 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>; - }; - - pcie3x4_rst: pcie3x4-rst { + pcie30x2_perstn_m1_l: pcie30x2-perstn-m1-l { rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; }; - pcie3x4_vcc3v3_en: pcie3x4-vcc3v3-en { - rockchip,pins = <2 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>; + pcie_4g_pwen: pcie-4g-pwen { + rockchip,pins = <2 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>; + }; + + pcie30x4_perstn_m1_l: pcie30x4-perstn-m1-l { + rockchip,pins = <4 RK_PB6 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + pcie30x4_pwren_h: pcie30x4-pwren-h { + rockchip,pins = <2 RK_PC5 RK_FUNC_GPIO &pcfg_pull_down>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts index d6e464cdc536..ba49f0bbaac6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts @@ -206,6 +206,28 @@ pinctrl-0 = <&vcc3v3_pcie30_en>; }; + vcc3v3_pciewl_vbat: regulator-vcc3v3-pciewl-vbat { + compatible = "regulator-fixed"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "wlan-vbat"; + vin-supply = <&vcc_3v3_s0>; + }; + + vcc3v3_wlan: regulator-vcc3v3-wlan { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio3 RK_PB1 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&wifi_pwren>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "wlan-en"; + vin-supply = <&vcc3v3_pciewl_vbat>; + }; + vcc5v0_host: regulator-vcc5v0-host { compatible = "regulator-fixed"; regulator-name = "vcc5v0_host"; @@ -249,12 +271,26 @@ regulator-max-microvolt = <5000000>; vin-supply = <&vcc5v0_usbdcin>; }; + + vccio_wl: regulator-vccio-wl { + compatible = "regulator-fixed"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "wlan-vddio"; + vin-supply = <&vcc_1v8_s0>; + }; }; &combphy0_ps { status = "okay"; }; +&combphy1_ps { + status = "okay"; +}; + &combphy2_psu { status = "okay"; }; @@ -440,6 +476,30 @@ }; }; +&pcie2x1l0 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_0_rst>, <&pcie2_0_wake>, <&pcie2_0_clkreq>, <&wifi_host_wake_irq>; + reset-gpios = <&gpio4 RK_PA5 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc3v3_wlan>; + status = "okay"; + + pcie@0,0 { + reg = <0x200000 0 0 0 0>; + #address-cells = <3>; + #size-cells = <2>; + ranges; + device_type = "pci"; + bus-range = <0x20 0x2f>; + + wifi: wifi@0,0 { + compatible = "pci14e4,449d"; + reg = <0x210000 0 0 0 0>; + clocks = <&hym8563>; + clock-names = "lpo"; + }; + }; +}; + &pcie2x1l1 { reset-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; @@ -494,6 +554,18 @@ }; pcie2 { + pcie2_0_rst: pcie2-0-rst { + rockchip,pins = <4 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + pcie2_0_wake: pcie2-0-wake { + rockchip,pins = <4 RK_PA4 4 &pcfg_pull_none>; + }; + + pcie2_0_clkreq: pcie2-0-clkreq { + rockchip,pins = <4 RK_PA3 4 &pcfg_pull_none>; + }; + pcie2_1_rst: pcie2-1-rst { rockchip,pins = <4 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>; }; @@ -524,6 +596,16 @@ rockchip,pins = <3 RK_PB4 RK_FUNC_GPIO &pcfg_pull_up>; }; }; + + wlan { + wifi_host_wake_irq: wifi-host-wake-irq { + rockchip,pins = <3 RK_PA7 RK_FUNC_GPIO &pcfg_pull_down>; + }; + + wifi_pwren: wifi-pwren { + rockchip,pins = <3 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; }; &pwm2 { diff --git a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi index 0ce0934ec6b7..4a950907ea6f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi @@ -162,6 +162,7 @@ linux,pci-domain = <0>; max-link-speed = <3>; msi-map = <0x0000 &its1 0x0000 0x1000>; + iommu-map = <0x0000 &mmu600_pcie 0x0000 0x1000>; num-lanes = <4>; phys = <&pcie30phy>; phy-names = "pcie-phy"; @@ -212,6 +213,7 @@ interrupt-names = "sys", "pmc", "msg", "legacy", "err", "dma0", "dma1", "dma2", "dma3"; max-link-speed = <3>; + iommus = <&mmu600_pcie 0x0000>; num-lanes = <4>; phys = <&pcie30phy>; phy-names = "pcie-phy"; @@ -248,6 +250,7 @@ linux,pci-domain = <1>; max-link-speed = <3>; msi-map = <0x1000 &its1 0x1000 0x1000>; + iommu-map = <0x1000 &mmu600_pcie 0x1000 0x1000>; num-lanes = <2>; phys = <&pcie30phy>; phy-names = "pcie-phy"; @@ -297,6 +300,7 @@ linux,pci-domain = <2>; max-link-speed = <2>; msi-map = <0x2000 &its0 0x2000 0x1000>; + iommu-map = <0x2000 &mmu600_pcie 0x2000 0x1000>; num-lanes = <1>; phys = <&combphy1_ps PHY_TYPE_PCIE>; phy-names = "pcie-phy"; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-firefly-core-3588j.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-firefly-core-3588j.dtsi new file mode 100644 index 000000000000..42c523b553c9 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3588-firefly-core-3588j.dtsi @@ -0,0 +1,443 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) + +#include +#include + +#include "rk3588.dtsi" + +/ { + compatible = "firefly,core-3588j", "rockchip,rk3588"; + + aliases { + mmc0 = &sdhci; + }; +}; + +&cpu_b0 { + cpu-supply = <&vdd_cpu_big0_s0>; +}; + +&cpu_b1 { + cpu-supply = <&vdd_cpu_big0_s0>; +}; + +&cpu_b2 { + cpu-supply = <&vdd_cpu_big1_s0>; +}; + +&cpu_b3 { + cpu-supply = <&vdd_cpu_big1_s0>; +}; + +&cpu_l0 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l1 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l2 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l3 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0m2_xfer>; + status = "okay"; + + vdd_cpu_big0_s0: regulator@42 { + compatible = "rockchip,rk8602"; + reg = <0x42>; + fcs,suspend-voltage-selector = <1>; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <1050000>; + regulator-name = "vdd_cpu_big0_s0"; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc5v0_sys>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_big1_s0: regulator@43 { + compatible = "rockchip,rk8603", "rockchip,rk8602"; + reg = <0x43>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_cpu_big1_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc5v0_sys>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; +}; + +&i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1m2_xfer>; + status = "okay"; + + vdd_npu_s0: vdd_npu_mem_s0: regulator@42 { + compatible = "rockchip,rk8602"; + reg = <0x42>; + fcs,suspend-voltage-selector = <1>; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-name = "vdd_npu_s0"; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc5v0_sys>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; +}; + +&sdhci { + bus-width = <8>; + no-sdio; + no-sd; + non-removable; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + status = "okay"; +}; + +&spi2 { + assigned-clocks = <&cru CLK_SPI2>; + assigned-clock-rates = <200000000>; + num-cs = <1>; + pinctrl-names = "default"; + pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>; + status = "okay"; + + pmic@0 { + compatible = "rockchip,rk806"; + reg = <0x0>; + interrupt-parent = <&gpio0>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; + gpio-controller; + #gpio-cells = <2>; + pinctrl-names = "default"; + pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, + <&rk806_dvs2_null>, <&rk806_dvs3_null>; + spi-max-frequency = <1000000>; + system-power-controller; + + vcc1-supply = <&vcc5v0_sys>; + vcc2-supply = <&vcc5v0_sys>; + vcc3-supply = <&vcc5v0_sys>; + vcc4-supply = <&vcc5v0_sys>; + vcc5-supply = <&vcc5v0_sys>; + vcc6-supply = <&vcc5v0_sys>; + vcc7-supply = <&vcc5v0_sys>; + vcc8-supply = <&vcc5v0_sys>; + vcc9-supply = <&vcc5v0_sys>; + vcc10-supply = <&vcc5v0_sys>; + vcc11-supply = <&vcc_2v0_pldo_s3>; + vcc12-supply = <&vcc5v0_sys>; + vcc13-supply = <&vcc_1v1_nldo_s3>; + vcc14-supply = <&vcc_1v1_nldo_s3>; + vcca-supply = <&vcc5v0_sys>; + + rk806_dvs1_null: dvs1-null-pins { + pins = "gpio_pwrctrl1"; + function = "pin_fun0"; + }; + + rk806_dvs2_null: dvs2-null-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun0"; + }; + + rk806_dvs3_null: dvs3-null-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun0"; + }; + + regulators { + vdd_gpu_s0: vdd_gpu_mem_s0: dcdc-reg1 { + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + regulator-name = "vdd_gpu_s0"; + regulator-enable-ramp-delay = <400>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_lit_s0: vdd_cpu_lit_mem_s0: dcdc-reg2 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + regulator-name = "vdd_cpu_lit_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_log_s0: dcdc-reg3 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <675000>; + regulator-max-microvolt = <750000>; + regulator-ramp-delay = <12500>; + regulator-name = "vdd_log_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vdd_vdenc_s0: vdd_vdenc_mem_s0: dcdc-reg4 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + regulator-name = "vdd_vdenc_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_ddr_s0: dcdc-reg5 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <675000>; + regulator-max-microvolt = <900000>; + regulator-ramp-delay = <12500>; + regulator-name = "vdd_ddr_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <850000>; + }; + }; + + vdd2_ddr_s3: dcdc-reg6 { + regulator-always-on; + regulator-boot-on; + regulator-name = "vdd2_ddr_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + }; + }; + + vcc_2v0_pldo_s3: dcdc-reg7 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <2000000>; + regulator-max-microvolt = <2000000>; + regulator-name = "vdd_2v0_pldo_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <2000000>; + }; + }; + + vcc_3v3_s3: dcdc-reg8 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc_3v3_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <3300000>; + }; + }; + + vddq_ddr_s0: dcdc-reg9 { + regulator-always-on; + regulator-boot-on; + regulator-name = "vddq_ddr_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_1v8_s3: dcdc-reg10 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcc_1v8_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + avcc_1v8_s0: pldo-reg1 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "avcc_1v8_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_1v8_s0: pldo-reg2 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "vcc_1v8_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + avdd_1v2_s0: pldo-reg3 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-name = "avdd_1v2_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + avcc_3v3_s0: pldo-reg4 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "avcc_3v3_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vccio_sd_s0: pldo-reg5 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vccio_sd_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + pldo6_s3: pldo-reg6 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "pldo6_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vdd_0v75_s3: nldo-reg1 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + regulator-name = "vdd_0v75_s3"; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + avdd_ddr_pll_s0: nldo-reg2 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + regulator-name = "avdd_ddr_pll_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <850000>; + }; + }; + + avdd_0v75_s0: nldo-reg3 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + regulator-name = "avdd_0v75_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + avdd_0v85_s0: nldo-reg4 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + regulator-name = "avdd_0v85_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_0v75_s0: nldo-reg5 { + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + regulator-name = "vdd_0v75_s0"; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + }; + }; +}; + +/* rk3588 preferred debug out */ +&uart2 { + pinctrl-0 = <&uart2m0_xfer>; + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-firefly-itx-3588j.dts b/arch/arm64/boot/dts/rockchip/rk3588-firefly-itx-3588j.dts new file mode 100644 index 000000000000..2be5251d3e3b --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3588-firefly-itx-3588j.dts @@ -0,0 +1,702 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) + +/dts-v1/; + +#include +#include +#include +#include +#include +#include +#include "dt-bindings/usb/pd.h" + +#include "rk3588-firefly-core-3588j.dtsi" + +/ { + model = "Firefly ITX-3588J"; + compatible = "firefly,itx-3588j", "firefly,core-3588j", "rockchip,rk3588"; + + aliases { + ethernet0 = &gmac0; + ethernet1 = &gmac1; + }; + + chosen { + stdout-path = "serial2:1500000n8"; + }; + + /* + * there are also a "Reset" and "Mask ROM" button, but the needed + * settings are unknown at this time + */ + adc-keys-0 { + compatible = "adc-keys"; + io-channels = <&saradc 1>; + io-channel-names = "buttons"; + keyup-threshold-microvolt = <1800000>; + poll-interval = <100>; + + button-recovery { + label = "Recovery"; + linux,code = ; + press-threshold-microvolt = <2000>; + }; + }; + + analog-sound { + compatible = "simple-audio-card"; + pinctrl-0 = <&hp_detect>; + pinctrl-names = "default"; + simple-audio-card,aux-devs = <&_headphones>, <&_speaker>; + simple-audio-card,format = "i2s"; + simple-audio-card,hp-det-gpios = <&gpio1 RK_PC4 GPIO_ACTIVE_LOW>; + simple-audio-card,mclk-fs = <384>; + simple-audio-card,name = "rockchip_es8323"; + simple-audio-card,pin-switches = "Headphones", "Speaker"; + simple-audio-card,routing = + "Speaker Amplifier INL", "LOUT2", + "Speaker Amplifier INR", "ROUT2", + "Speaker", "Speaker Amplifier OUTL", + "Speaker", "Speaker Amplifier OUTR", + "Headphones Amplifier INL", "LOUT1", + "Headphones Amplifier INR", "ROUT1", + "Headphones", "Headphones Amplifier OUTL", + "Headphones", "Headphones Amplifier OUTR", + "LINPUT1", "Microphone Jack", + "RINPUT1", "Microphone Jack", + "LINPUT2", "Onboard Microphone", + "RINPUT2", "Onboard Microphone"; + simple-audio-card,widgets = + "Microphone", "Microphone Jack", + "Microphone", "Onboard Microphone", + "Headphone", "Headphones", + "Speaker", "Speaker"; + + simple-audio-card,cpu { + sound-dai = <&i2s0_8ch>; + }; + + simple-audio-card,codec { + sound-dai = <&es8323>; + system-clock-frequency = <12288000>; + }; + }; + + /* + * this does not seem to be a proper "amplifier" but is just + * a way to control the GPIO pins to switch on or off the given + * sound output device + */ + amp_headphones: headphones-audio-amplifier { + compatible = "simple-audio-amplifier"; + enable-gpios = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&headphone_amplifier_en>; + sound-name-prefix = "Headphones Amplifier"; + }; + + amp_speaker: speaker-audio-amplifier { + compatible = "simple-audio-amplifier"; + enable-gpios = <&gpio3 RK_PB2 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&speaker_amplifier_en>; + sound-name-prefix = "Speaker Amplifier"; + }; + + fan: pwm-fan { + compatible = "pwm-fan"; + #cooling-cells = <2>; + cooling-levels = <0 120 150 180 210 240 255>; + fan-supply = <&vcc12v_dcin>; + pwms = <&pwm15 0 50000 1>; + }; + + hdmi0-con { + compatible = "hdmi-connector"; + type = "a"; + + port { + hdmi0_con_in: endpoint { + remote-endpoint = <&hdmi0_out_con>; + }; + }; + }; + + leds { + compatible = "gpio-leds"; + + /* + * There is also a Power LED control @ RK_PB3 on + * GPIO1 but for some reason it doesn't seem to work right + */ + + user_led: led-1 { + gpios = <&pca9555 3 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "disk-activity"; + }; + }; + + pcie30_avdd0v75: regulator-pcie30-avdd0v75 { + compatible = "regulator-fixed"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + regulator-name = "pcie30_avdd0v75"; + vin-supply = <&avdd_0v75_s0>; + }; + + vbus5v0_typec_pwr_en: regulator-vbus5v0-typec-pwr-en { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&pca9555 12 GPIO_ACTIVE_HIGH>; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-name = "vbus5v0_typec_pwr_en"; + }; + + vcc12v_dcin: regulator-vcc12v-dcin { + compatible = "regulator-fixed"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + regulator-name = "vcc12v_dcin"; + }; + + vcc3v3_pcie30: regulator-vcc3v3-pcie30 { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio2 RK_PC5 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie3_vcc3v3_en>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc3v3_pcie30"; + startup-delay-us = <5000>; + vin-supply = <&vcc12v_dcin>; + }; + + vcc5v0_host: regulator-vcc5v0-host { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&pca9555 5 GPIO_ACTIVE_HIGH>; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-name = "vcc5v0_host"; + vin-supply = <&vcc5v0_usb>; + }; + + vcc5v0_host3: regulator-vcc5v0-host3 { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&pca9555 7 GPIO_ACTIVE_HIGH>; + regulator-name = "vcc5v0_host3"; + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc5v0_usb>; + }; + + vcc5v0_sys: regulator-vcc5v0-sys { + compatible = "regulator-fixed"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-name = "vcc5v0_sys"; + vin-supply = <&vcc12v_dcin>; + }; + + vcc5v0_usb: regulator-vcc5v0-usb { + compatible = "regulator-fixed"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-name = "vcc5v0_usb"; + vin-supply = <&vcc12v_dcin>; + }; + + vcc_1v1_nldo_s3: regulator-vcc-1v1-nldo-s3 { + compatible = "regulator-fixed"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + regulator-name = "vcc_1v1_nldo_s3"; + vin-supply = <&vcc5v0_sys>; + }; + + vcc_fan_pwr_en: regulator-vcc-fan-pwr-en { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&pca9555 11 GPIO_ACTIVE_HIGH>; + regulator-always-on; + regulator-boot-on; + regulator-name = "vcc_fan_pwr_en"; + }; + + vcc_hub_reset: regulator-vcc-hub-reset { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&pca9555 4 GPIO_ACTIVE_HIGH>; + regulator-always-on; + regulator-boot-on; + regulator-name = "vcc_hub_reset"; + }; + + vcc_hub3_reset: regulator-vcc-hub3-reset { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&pca9555 6 GPIO_ACTIVE_HIGH>; + regulator-always-on; + regulator-name = "vcc_hub3_reset"; + }; + + vcc_sata_pwr_en: regulator-vcc-sata-pwr-en { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&pca9555 10 GPIO_ACTIVE_HIGH>; + regulator-always-on; + regulator-boot-on; + regulator-name = "vcc_sata_pwr_en"; + }; +}; + +&avcc_1v8_s0 { + regulator-state-mem { + regulator-on-in-suspend; + }; +}; + +&combphy0_ps { + status = "okay"; +}; + +&combphy1_ps { + status = "okay"; +}; + +&combphy2_psu { + status = "okay"; +}; + +&gmac0 { + clock_in_out = "output"; + phy-handle = <&rgmii_phy0>; + phy-mode = "rgmii-rxid"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_miim + &gmac0_tx_bus2 + &gmac0_rx_bus2 + &gmac0_rgmii_clk + &gmac0_rgmii_bus>; + tx_delay = <0x45>; + rx_delay = <0x4a>; + status = "okay"; +}; + +&gmac1 { + clock_in_out = "output"; + phy-handle = <&rgmii_phy1>; + phy-mode = "rgmii-rxid"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1_miim + &gmac1_tx_bus2 + &gmac1_rx_bus2 + &gmac1_rgmii_clk + &gmac1_rgmii_bus>; + tx_delay = <0x42>; + rx_delay = <0x4f>; + status = "okay"; +}; + +&gpu { + mali-supply = <&vdd_gpu_s0>; + sram-supply = <&vdd_gpu_mem_s0>; + status = "okay"; +}; + +&hdmi0 { + status = "okay"; +}; + +&hdmi0_in { + hdmi0_in_vp0: endpoint { + remote-endpoint = <&vp0_out_hdmi0>; + }; +}; + +&hdmi0_out { + hdmi0_out_con: endpoint { + remote-endpoint = <&hdmi0_con_in>; + }; +}; + +&hdptxphy_hdmi0 { + status = "okay"; +}; + +&i2c3 { + status = "okay"; + + /* + * in the Firefly BSP source this was confusingly called an + * "ES8388" - it actually seems to be an ES8323 and the drivers + * for that work best + */ + es8323: audio-codec@11 { + compatible = "everest,es8323"; + reg = <0x11>; + assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; + assigned-clock-rates = <12288000>; + clocks = <&cru I2S0_8CH_MCLKOUT>; + clock-names = "mclk"; + #sound-dai-cells = <0>; + }; +}; + +&i2c6 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c6m0_xfer>; + status = "okay"; + + pca9555: gpio@21 { + compatible = "nxp,pca9555"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + }; + + usbc0: usb-typec@22 { + compatible = "fcs,fusb302"; + reg = <0x22>; + interrupt-parent = <&gpio0>; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&usbc0_int>; + vbus-supply = <&vbus5v0_typec_pwr_en>; + + usb_con: connector { + compatible = "usb-c-connector"; + label = "USB-C"; + data-role = "dual"; + op-sink-microwatt = <1000000>; + power-role = "dual"; + sink-pdos = + ; + source-pdos = + ; + try-power-role = "source"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + usbc0_orien_sw: endpoint { + remote-endpoint = <&usbdp_phy0_orientation_switch>; + }; + }; + + port@1 { + reg = <1>; + + usbc0_role_sw: endpoint { + remote-endpoint = <&dwc3_0_role_switch>; + }; + }; + + port@2 { + reg = <2>; + + dp_altmode_mux: endpoint { + remote-endpoint = <&usbdp_phy0_dp_altmode_mux>; + }; + }; + }; + }; + }; + + hym8563: rtc@51 { + compatible = "haoyu,hym8563"; + reg = <0x51>; + interrupt-parent = <&gpio0>; + interrupts = ; + #clock-cells = <0>; + clock-output-names = "hym8563"; + pinctrl-names = "default"; + pinctrl-0 = <&hym8563_int>; + wakeup-source; + }; +}; + +&i2s0_8ch { + pinctrl-names = "default"; + pinctrl-0 = <&i2s0_lrck + &i2s0_mclk + &i2s0_sclk + &i2s0_sdi0 + &i2s0_sdo0>; + status = "okay"; +}; + +&mdio0 { + rgmii_phy0: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0x1>; + }; +}; + +&mdio1 { + rgmii_phy1: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0x1>; + }; +}; + +&pcie2x1l0 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_0_rst>; + reset-gpios = <&gpio1 RK_PB4 GPIO_ACTIVE_HIGH>; + status = "okay"; +}; + +&pcie30phy { + status = "okay"; +}; + +&pcie3x4 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie3_rst>; + reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc3v3_pcie30>; + status = "okay"; +}; + +&pinctrl { + dp { + dp1_hpd: dp1-hpd { + rockchip,pins = <1 RK_PA4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + hym8563 { + hym8563_int: hym8563-int { + rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + + gpio-leds { + sys_led_pin: sys-led-pin { + rockchip,pins = + <1 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + pcie2 { + pcie2_0_rst: pcie2-0-rst { + rockchip,pins = <1 RK_PB4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + pcie3 { + pcie3_rst: pcie3-rst { + rockchip,pins = <4 RK_PB6 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + pcie3_vcc3v3_en: pcie3-vcc3v3-en { + rockchip,pins = <2 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + sound { + hp_detect: hp-detect { + rockchip,pins = <1 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + headphone_amplifier_en: headphone-amplifier-en { + rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + speaker_amplifier_en: speaker-amplifier-en { + rockchip,pins = <3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + usb { + usbc0_int: usbc0-int { + rockchip,pins = <0 RK_PD3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; +}; + +&pwm15 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm15m2_pins>; + status = "okay"; +}; + +&sata0 { + status = "okay"; +}; + +&sata1 { + status = "okay"; +}; + +&sata2 { + status = "okay"; +}; + +/* uart/232/485 */ +&uart0 { + pinctrl-0 = <&uart0m2_xfer>; + status = "okay"; +}; + +&uart1 { + pinctrl-0 = <&uart1m1_xfer>; + status = "okay"; +}; + +/* usb enable */ +&u2phy0 { + status = "okay"; +}; + +&u2phy0_otg { + status = "okay"; +}; + +&u2phy1 { + status = "okay"; +}; + +&u2phy1_otg { + phy-supply = <&vcc5v0_host>; + status = "okay"; +}; + +&u2phy2 { + status = "okay"; +}; + +&u2phy2_host { + phy-supply = <&vcc5v0_host>; + status = "okay"; +}; + +&u2phy3 { + status = "okay"; +}; + +&u2phy3_host { + phy-supply = <&vcc5v0_host>; + status = "okay"; +}; + +&usb_host0_ehci { + status = "okay"; +}; + +&usb_host0_ohci { + status = "okay"; +}; + +&usb_host1_ehci { + status = "okay"; +}; + +&usb_host1_ohci { + status = "okay"; +}; + +&usb_host0_xhci { + usb-role-switch; + dr_mode = "otg"; + status = "okay"; + + port { + #address-cells = <1>; + #size-cells = <0>; + + dwc3_0_role_switch: endpoint@0 { + reg = <0>; + remote-endpoint = <&usbc0_role_sw>; + }; + }; +}; + +&usb_host1_xhci { + dr_mode = "host"; + status = "okay"; +}; + +&usb_host2_xhci { + status = "okay"; +}; + +&usbdp_phy0 { + orientation-switch; + sbu1-dc-gpios = <&gpio4 RK_PA6 GPIO_ACTIVE_HIGH>; + sbu2-dc-gpios = <&gpio4 RK_PA7 GPIO_ACTIVE_HIGH>; + status = "okay"; + + port { + #address-cells = <1>; + #size-cells = <0>; + + usbdp_phy0_orientation_switch: endpoint@0 { + reg = <0>; + remote-endpoint = <&usbc0_orien_sw>; + }; + + usbdp_phy0_dp_altmode_mux: endpoint@1 { + reg = <1>; + remote-endpoint = <&dp_altmode_mux>; + }; + }; +}; + +&usbdp_phy1 { + rockchip,dp-lane-mux = <2 3>; + status = "okay"; +}; + +&vcc_1v8_s0 { + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; +}; + +/* for fan when deep sleep */ +&vdd_log_s0 { + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <750000>; + }; +}; + +/* display generator */ +&vop_mmu { + status = "okay"; +}; + +&vop { + status = "okay"; +}; + +&vp0 { + vp0_out_hdmi0: endpoint@ROCKCHIP_VOP2_EP_HDMI0 { + reg = ; + remote-endpoint = <&hdmi0_in_vp0>; + }; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-h96-max-v58.dts b/arch/arm64/boot/dts/rockchip/rk3588-h96-max-v58.dts new file mode 100644 index 000000000000..4791b77f3571 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3588-h96-max-v58.dts @@ -0,0 +1,802 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) + +/dts-v1/; + +#include +#include +#include +#include +#include "rk3588.dtsi" + +/ { + model = "H96 Max V58 TV Box"; + compatible = "haochuangyi,h96-max-v58", "rockchip,rk3588"; + + aliases { + ethernet0 = &gmac1; + mmc0 = &sdhci; + }; + + adc-keys { + compatible = "adc-keys"; + io-channels = <&saradc 1>; + io-channel-names = "buttons"; + keyup-threshold-microvolt = <1800000>; + poll-interval = <100>; + + button-function { + label = "Reset"; + linux,code = ; + press-threshold-microvolt = <1750>; + }; + }; + + chosen { + stdout-path = "serial2:1500000n8"; + }; + + hdmi0-con { + compatible = "hdmi-connector"; + type = "a"; + + port { + hdmi0_con_in: endpoint { + remote-endpoint = <&hdmi0_out_con>; + }; + }; + }; + + ir-receiver { + compatible = "gpio-ir-receiver"; + gpios = <&gpio0 RK_PD4 GPIO_ACTIVE_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&ir_receiver_pin>; + }; + + leds { + compatible = "gpio-leds"; + pinctrl-names = "default"; + pinctrl-0 = <&led_pins>; + + led { + color = ; + function = LED_FUNCTION_STATUS; + gpios = <&gpio3 RK_PD4 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "heartbeat"; + }; + }; + + vcc_1v1_nldo_s3: regulator-1v1 { + compatible = "regulator-fixed"; + regulator-name = "vcc_1v1_nldo_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + vin-supply = <&vcc5v0_sys>; + }; + + pcie_3v3: regulator-3v3-pcie { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio4 RK_PA1 GPIO_ACTIVE_HIGH>; + pinctrl-0 = <&pcie2_0_pow>; + pinctrl-names = "default"; + regulator-name = "pcie_3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc5v0_sys>; + }; + + wl_en_3v3: regulator-3v3-wlen { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>; + pinctrl-0 = <&wl_en>; + pinctrl-names = "default"; + /* + * Needs to be brought up before the PCIe driver is probed, + * otherwise detecting the WLAN module requires rescanning + * the bus, and even then it fails half of the time during + * firmware load + */ + regulator-always-on; + regulator-boot-on; + regulator-name = "wl_en_3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc5v0_sys>; + }; + + vcc5v0_host: regulator-5v0-host { + compatible = "regulator-fixed"; + regulator-name = "vcc5v0_host"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + enable-active-high; + gpios = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>; + pinctrl-0 = <&vcc5v0_host_en>; + pinctrl-names = "default"; + vin-supply = <&vcc5v0_sys>; + }; + + vcc5v0_otg: regulator-5v0-otg { + compatible = "regulator-fixed"; + regulator-name = "vcc5v0_otg"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + enable-active-high; + gpios = <&gpio4 RK_PA7 GPIO_ACTIVE_HIGH>; + pinctrl-0 = <&vcc5v0_otg_en>; + pinctrl-names = "default"; + vin-supply = <&vcc5v0_sys>; + }; + + vcc5v0_sys: regulator-5v0-sys { + compatible = "regulator-fixed"; + regulator-name = "vcc5v0_sys"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; +}; + +&combphy0_ps { + status = "okay"; +}; + +&combphy1_ps { + status = "okay"; +}; + +&combphy2_psu { + status = "okay"; +}; + +&cpu_b0 { + cpu-supply = <&vdd_cpu_big0_s0>; +}; + +&cpu_b1 { + cpu-supply = <&vdd_cpu_big0_s0>; +}; + +&cpu_b2 { + cpu-supply = <&vdd_cpu_big1_s0>; +}; + +&cpu_b3 { + cpu-supply = <&vdd_cpu_big1_s0>; +}; + +&cpu_l0 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l1 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l2 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l3 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&gpu { + mali-supply = <&vdd_gpu_s0>; + status = "okay"; +}; + +&hdmi0 { + status = "okay"; +}; + +&hdmi0_in { + hdmi0_in_vp0: endpoint { + remote-endpoint = <&vp0_out_hdmi0>; + }; +}; + +&hdmi0_out { + hdmi0_out_con: endpoint { + remote-endpoint = <&hdmi0_con_in>; + }; +}; + +&hdptxphy_hdmi0 { + status = "okay"; +}; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0m2_xfer>; + status = "okay"; + + vdd_cpu_big0_s0: regulator@42 { + compatible = "rockchip,rk8602"; + reg = <0x42>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_cpu_big0_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc5v0_sys>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_big1_s0: regulator@43 { + compatible = "rockchip,rk8603", "rockchip,rk8602"; + reg = <0x43>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_cpu_big1_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc5v0_sys>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; +}; + +&i2c6 { + status = "okay"; + + hym8563: rtc@51 { + compatible = "haoyu,hym8563"; + reg = <0x51>; + #clock-cells = <0>; + clock-output-names = "hym8563"; + pinctrl-names = "default"; + pinctrl-0 = <&hym8563_int>; + interrupt-parent = <&gpio0>; + interrupts = ; + wakeup-source; + }; +}; + +&gmac1 { + clock_in_out = "output"; + phy-handle = <&rgmii_phy1>; + phy-mode = "rgmii-id"; + pinctrl-0 = <&gmac1_miim + &gmac1_tx_bus2 + &gmac1_rx_bus2 + &gmac1_rgmii_clk + &gmac1_rgmii_bus>; + pinctrl-names = "default"; + status = "okay"; +}; + +&mdio1 { + rgmii_phy1: ethernet-phy@1 { + /* RTL8211F */ + compatible = "ethernet-phy-id001c.c916"; + reg = <0x1>; + pinctrl-names = "default"; + pinctrl-0 = <&rtl8211f_rst>; + reset-assert-us = <20000>; + reset-deassert-us = <100000>; + reset-gpios = <&gpio3 RK_PB7 GPIO_ACTIVE_LOW>; + }; +}; + +&pcie2x1l0 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_0_rst>; + reset-gpios = <&gpio4 RK_PA5 GPIO_ACTIVE_HIGH>; + status = "okay"; + + pcie@0,0 { + reg = <0x200000 0 0 0 0>; + #address-cells = <3>; + #size-cells = <2>; + ranges; + device_type = "pci"; + bus-range = <0x20 0x2f>; + + wifi: wifi@0,0 { + compatible = "pci14e4,449d"; + reg = <0x210000 0 0 0 0>; + clocks = <&hym8563>; + clock-names = "lpo"; + }; + }; +}; + +&pinctrl { + hym8563 { + hym8563_int: hym8563-int { + rockchip,pins = <0 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + ir-receiver { + ir_receiver_pin: ir-receiver-pin { + rockchip,pins = <0 RK_PD4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + leds { + led_pins: led-pins { + rockchip,pins = <3 RK_PD4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + pcie2 { + pcie2_0_rst: pcie2-0-rst { + rockchip,pins = <4 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + pcie2_0_pow: pcie2-0-pow { + rockchip,pins = <4 RK_PA1 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + rtl8211f { + rtl8211f_rst: rtl8211f-rst { + rockchip,pins = <3 RK_PB7 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + }; + + usb { + vcc5v0_host_en: vcc5v0-host-en { + rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + vcc5v0_otg_en: vcc5v0-otg-en { + rockchip,pins = <4 RK_PA7 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + wifibt { + wl_en: wl-en { + rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_up>; + }; + + wl_wake_host: wl-wake-host { + rockchip,pins = <0 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up>; + }; + + bt_en: bt-en { + rockchip,pins = <0 RK_PC6 RK_FUNC_GPIO &pcfg_pull_up>; + }; + + bt_wake: bt-wake { + rockchip,pins = <0 RK_PC5 RK_FUNC_GPIO &pcfg_pull_up>; + }; + + bt_wake_host: bt-wake-host { + rockchip,pins = <0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_down>; + }; + }; +}; + +&saradc { + vref-supply = <&avcc_1v8_s0>; + status = "okay"; +}; + +&sdhci { + bus-width = <8>; + no-sdio; + no-sd; + non-removable; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + status = "okay"; +}; + +&spi2 { + assigned-clocks = <&cru CLK_SPI2>; + assigned-clock-rates = <200000000>; + num-cs = <1>; + pinctrl-names = "default"; + pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>; + status = "okay"; + + pmic@0 { + compatible = "rockchip,rk806"; + reg = <0x0>; + interrupt-parent = <&gpio0>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, + <&rk806_dvs2_null>, <&rk806_dvs3_null>; + spi-max-frequency = <1000000>; + system-power-controller; + + vcc1-supply = <&vcc5v0_sys>; + vcc2-supply = <&vcc5v0_sys>; + vcc3-supply = <&vcc5v0_sys>; + vcc4-supply = <&vcc5v0_sys>; + vcc5-supply = <&vcc5v0_sys>; + vcc6-supply = <&vcc5v0_sys>; + vcc7-supply = <&vcc5v0_sys>; + vcc8-supply = <&vcc5v0_sys>; + vcc9-supply = <&vcc5v0_sys>; + vcc10-supply = <&vcc5v0_sys>; + vcc11-supply = <&vcc_2v0_pldo_s3>; + vcc12-supply = <&vcc5v0_sys>; + vcc13-supply = <&vcc_1v1_nldo_s3>; + vcc14-supply = <&vcc_1v1_nldo_s3>; + vcca-supply = <&vcc5v0_sys>; + + gpio-controller; + #gpio-cells = <2>; + + rk806_dvs1_null: dvs1-null-pins { + pins = "gpio_pwrctrl1"; + function = "pin_fun0"; + }; + + rk806_dvs2_null: dvs2-null-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun0"; + }; + + rk806_dvs3_null: dvs3-null-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun0"; + }; + + regulators { + vdd_gpu_s0: vdd_gpu_mem_s0: dcdc-reg1 { + regulator-name = "vdd_gpu_s0"; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <400>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_lit_s0: vdd_cpu_lit_mem_s0: dcdc-reg2 { + regulator-name = "vdd_cpu_lit_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_log_s0: dcdc-reg3 { + regulator-name = "vdd_log_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <675000>; + regulator-max-microvolt = <750000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vdd_vdenc_s0: vdd_vdenc_mem_s0: dcdc-reg4 { + regulator-name = "vdd_vdenc_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_ddr_s0: dcdc-reg5 { + regulator-name = "vdd_ddr_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <675000>; + regulator-max-microvolt = <900000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <850000>; + }; + }; + + vdd2_ddr_s3: dcdc-reg6 { + regulator-name = "vdd2_ddr_s3"; + regulator-always-on; + regulator-boot-on; + + regulator-state-mem { + regulator-on-in-suspend; + }; + }; + + vcc_2v0_pldo_s3: dcdc-reg7 { + regulator-name = "vdd_2v0_pldo_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <2000000>; + regulator-max-microvolt = <2000000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <2000000>; + }; + }; + + vcc_3v3_s3: dcdc-reg8 { + regulator-name = "vcc_3v3_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <3300000>; + }; + }; + + vddq_ddr_s0: dcdc-reg9 { + regulator-name = "vddq_ddr_s0"; + regulator-always-on; + regulator-boot-on; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_1v8_s3: dcdc-reg10 { + regulator-name = "vcc_1v8_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + avcc_1v8_s0: pldo-reg1 { + regulator-name = "avcc_1v8_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_1v8_s0: pldo-reg2 { + regulator-name = "vcc_1v8_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + avdd_1v2_s0: pldo-reg3 { + regulator-name = "avdd_1v2_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_3v3_s0: pldo-reg4 { + regulator-name = "vcc_3v3_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vccio_sd_s0: pldo-reg5 { + regulator-name = "vccio_sd_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + pldo6_s3: pldo-reg6 { + regulator-name = "pldo6_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vdd_0v75_s3: nldo-reg1 { + regulator-name = "vdd_0v75_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vdd_ddr_pll_s0: nldo-reg2 { + regulator-name = "vdd_ddr_pll_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <850000>; + }; + }; + + avdd_0v75_s0: nldo-reg3 { + regulator-name = "avdd_0v75_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_0v85_s0: nldo-reg4 { + regulator-name = "vdd_0v85_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_0v75_s0: nldo-reg5 { + regulator-name = "vdd_0v75_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + }; + }; +}; + +&tsadc { + status = "okay"; +}; + +&u2phy0 { + status = "okay"; +}; + +&u2phy0_otg { + phy-supply = <&vcc5v0_otg>; + status = "okay"; +}; + +&u2phy1 { + status = "okay"; +}; + +&u2phy1_otg { + phy-supply = <&vcc5v0_host>; + status = "okay"; +}; + +&uart2 { + pinctrl-0 = <&uart2m0_xfer>; + status = "okay"; +}; + +&uart9 { + pinctrl-0 = <&uart9m0_xfer &uart9m0_ctsn &uart9m0_rtsn>; + pinctrl-names = "default"; + uart-has-rtscts; + status = "okay"; + + bluetooth { + compatible = "brcm,bcm43438-bt"; + clocks = <&hym8563>; + clock-names = "lpo"; + device-wakeup-gpios = <&gpio0 RK_PC5 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&gpio0>; + interrupts = ; + pinctrl-0 = <&bt_en>, <&bt_wake_host>, <&bt_wake>; + pinctrl-names = "default"; + shutdown-gpios = <&gpio0 RK_PC6 GPIO_ACTIVE_HIGH>; + }; +}; + +&usbdp_phy0 { + status = "okay"; +}; + +&usbdp_phy1 { + status = "okay"; +}; + +&usb_host0_xhci { + dr_mode = "host"; + status = "okay"; +}; + +&usb_host1_xhci { + dr_mode = "host"; + status = "okay"; +}; + +&vop_mmu { + status = "okay"; +}; + +&vop { + status = "okay"; +}; + +&vp0 { + vp0_out_hdmi0: endpoint@ROCKCHIP_VOP2_EP_HDMI0 { + reg = ; + remote-endpoint = <&hdmi0_in_vp0>; + }; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-compact.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-compact.dtsi new file mode 100644 index 000000000000..87090cb98020 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-compact.dtsi @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) + +/dts-v1/; + +#include +#include +#include "rk3588-orangepi-5.dtsi" + +/ { + model = "Xunlong Orange Pi 5 Max"; + compatible = "xunlong,orangepi-5-max", "rockchip,rk3588"; + + vcc5v0_usb30_otg: vcc5v0-usb30-otg-regulator { + compatible = "regulator-fixed"; + enable-active-high; + /* USB_OTG_PWREN */ + gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&usb_otg_pwren>; + regulator-name = "vcc5v0_usb30_otg"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc5v0_sys>; + }; +}; + +&headphone_amp { + /* PHONE_CTL */ + enable-gpios = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>; +}; + +&analog_sound { + pinctrl-names = "default"; + pinctrl-0 = <&hp_detect>; + simple-audio-card,aux-devs = <&headphone_amp>; + simple-audio-card,hp-det-gpios = <&gpio3 RK_PD2 GPIO_ACTIVE_HIGH>; + + simple-audio-card,routing = + "Headphones", "LOUT1", + "Headphones", "ROUT1", + "LINPUT1", "Microphone Jack", + "RINPUT1", "Microphone Jack", + "LINPUT2", "Onboard Microphone", + "RINPUT2", "Onboard Microphone"; + simple-audio-card,widgets = + "Microphone", "Microphone Jack", + "Microphone", "Onboard Microphone", + "Headphone", "Headphones"; +}; + +&fan { + /* FAN_CTL_H */ + pwms = <&pwm9 0 50000 0>; +}; + +&hym8563 { + interrupt-parent = <&gpio0>; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&rtc_int_l>; +}; + +&led_blue_pwm { + /* PWM_LED1 */ + pwms = <&pwm4 0 25000 0>; + status = "okay"; +}; + +&led_green_pwm { + /* PWM_LED2 */ + pwms = <&pwm5 0 25000 0>; +}; + +/* phy2 */ +&pcie2x1l1 { + reset-gpios = <&gpio4 RK_PD4 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc3v3_pcie_eth>; + status = "okay"; +}; + +&pinctrl { + hym8563 { + rtc_int_l: hym8563-int { + rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + sound { + hp_detect: hp-detect { + rockchip,pins = <3 RK_PD2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + usb { + usb_host_pwren: usb-host-pwren { + rockchip,pins = <3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; +}; + +&pwm4 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm4m0_pins>; + status = "okay"; +}; + +&pwm5 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm5m1_pins>; + status = "okay"; +}; + +&pwm9 { + pinctrl-names = "default"; + pinctrl-0 = <&pwm9m2_pins>; + status = "okay"; +}; + +&sfc { + pinctrl-names = "default"; + pinctrl-0 = <&fspim2_pins>; +}; + +&u2phy0_otg { + phy-supply = <&vcc5v0_usb30_otg>; +}; + +&u2phy1_otg { + phy-supply = <&vcc5v0_usb20>; +}; + +&usb_host0_xhci { + dr_mode = "host"; +}; + +/* pcie eth. not a real regulator. 33VAUX */ +&vcc3v3_pcie_eth { + /* Ethernet_power_en */ + gpios = <&gpio0 RK_PD3 GPIO_ACTIVE_LOW>; +}; + +/* + * Represents the vcc5v0_usb20 and vcc5v0_usb30 in the schematic, + * both regulators share the same enable gpio + */ +&vcc5v0_usb20 { + /* USB_HOST_PWREN */ + gpios = <&gpio3 RK_PD5 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&usb_host_pwren>; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-max.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-max.dts new file mode 100644 index 000000000000..ce44549babf4 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-max.dts @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) + +/dts-v1/; + +#include +#include +#include +#include "rk3588-orangepi-5-compact.dtsi" + +/ { + model = "Xunlong Orange Pi 5 Max"; + compatible = "xunlong,orangepi-5-max", "rockchip,rk3588"; + + hdmi0-con { + compatible = "hdmi-connector"; + type = "a"; + + port { + hdmi0_con_in: endpoint { + remote-endpoint = <&hdmi0_out_con>; + }; + }; + }; +}; + +&hdmi0 { + status = "okay"; +}; + +&hdmi0_in { + hdmi0_in_vp0: endpoint { + remote-endpoint = <&vp0_out_hdmi0>; + }; +}; + +&hdmi0_out { + hdmi0_out_con: endpoint { + remote-endpoint = <&hdmi0_con_in>; + }; +}; + +&hdptxphy_hdmi0 { + status = "okay"; +}; + +&pinctrl { + + usb { + usb_otg_pwren: usb-otg-pwren { + rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; +}; + +&vp0 { + vp0_out_hdmi0: endpoint@ROCKCHIP_VOP2_EP_HDMI0 { + reg = ; + remote-endpoint = <&hdmi0_in_vp0>; + }; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts index 9f5a38b290bf..255e33c5dbdc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts @@ -6,86 +6,15 @@ /dts-v1/; #include -#include -#include #include #include #include -#include "rk3588.dtsi" +#include "rk3588-orangepi-5.dtsi" / { model = "Xunlong Orange Pi 5 Plus"; compatible = "xunlong,orangepi-5-plus", "rockchip,rk3588"; - aliases { - mmc0 = &sdhci; - mmc1 = &sdmmc; - }; - - chosen { - stdout-path = "serial2:1500000n8"; - }; - - adc-keys-0 { - compatible = "adc-keys"; - io-channels = <&saradc 0>; - io-channel-names = "buttons"; - keyup-threshold-microvolt = <1800000>; - poll-interval = <100>; - - button-maskrom { - label = "Mask Rom"; - linux,code = ; - press-threshold-microvolt = <2000>; - }; - }; - - adc-keys-1 { - compatible = "adc-keys"; - io-channels = <&saradc 1>; - io-channel-names = "buttons"; - keyup-threshold-microvolt = <1800000>; - poll-interval = <100>; - - button-recovery { - label = "Recovery"; - linux,code = ; - press-threshold-microvolt = <2000>; - }; - }; - - speaker_amp: speaker-audio-amplifier { - compatible = "simple-audio-amplifier"; - enable-gpios = <&gpio3 RK_PC0 GPIO_ACTIVE_HIGH>; - sound-name-prefix = "Speaker Amp"; - }; - - headphone_amp: headphones-audio-amplifier { - compatible = "simple-audio-amplifier"; - enable-gpios = <&gpio3 RK_PA7 GPIO_ACTIVE_HIGH>; - sound-name-prefix = "Headphones Amp"; - }; - - ir-receiver { - compatible = "gpio-ir-receiver"; - gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_LOW>; - pinctrl-names = "default"; - pinctrl-0 = <&ir_receiver_pin>; - }; - - gpio-leds { - compatible = "gpio-leds"; - pinctrl-names = "default"; - pinctrl-0 = <&blue_led_pin>; - - led { - color = ; - function = LED_FUNCTION_INDICATOR; - function-enumerator = <1>; - gpios = <&gpio3 RK_PA6 GPIO_ACTIVE_HIGH>; - }; - }; - hdmi0-con { compatible = "hdmi-connector"; type = "a"; @@ -97,24 +26,11 @@ }; }; - fan: pwm-fan { - compatible = "pwm-fan"; - cooling-levels = <0 70 75 80 100>; - fan-supply = <&vcc5v0_sys>; - pwms = <&pwm3 0 50000 0>; - #cooling-cells = <2>; - }; - - pwm-leds { - compatible = "pwm-leds"; - - led { - color = ; - function = LED_FUNCTION_INDICATOR; - function-enumerator = <2>; - max-brightness = <255>; - pwms = <&pwm2 0 25000 0>; - }; + ir-receiver { + compatible = "gpio-ir-receiver"; + gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&ir_receiver_pin>; }; rfkill { @@ -124,113 +40,63 @@ shutdown-gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>; }; - sound { - compatible = "simple-audio-card"; + vbus5v0_typec: regulator-vbus-typec { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; - pinctrl-0 = <&hp_detect>; - simple-audio-card,name = "Analog"; - simple-audio-card,aux-devs = <&speaker_amp>, <&headphone_amp>; - simple-audio-card,format = "i2s"; - simple-audio-card,mclk-fs = <256>; - simple-audio-card,hp-det-gpios = <&gpio1 RK_PD3 GPIO_ACTIVE_LOW>; - simple-audio-card,bitclock-master = <&daicpu>; - simple-audio-card,frame-master = <&daicpu>; - /*TODO: SARADC_IN3 is used as MIC detection / key input */ - - simple-audio-card,widgets = - "Microphone", "Onboard Microphone", - "Microphone", "Microphone Jack", - "Speaker", "Speaker", - "Headphone", "Headphones"; - - simple-audio-card,routing = - "Headphones", "LOUT1", - "Headphones", "ROUT1", - "Speaker", "LOUT2", - "Speaker", "ROUT2", - - "Headphones", "Headphones Amp OUTL", - "Headphones", "Headphones Amp OUTR", - "Headphones Amp INL", "LOUT1", - "Headphones Amp INR", "ROUT1", - - "Speaker", "Speaker Amp OUTL", - "Speaker", "Speaker Amp OUTR", - "Speaker Amp INL", "LOUT2", - "Speaker Amp INR", "ROUT2", - - /* single ended signal to LINPUT1 */ - "LINPUT1", "Microphone Jack", - "RINPUT1", "Microphone Jack", - /* differential signal */ - "LINPUT2", "Onboard Microphone", - "RINPUT2", "Onboard Microphone"; - - daicpu: simple-audio-card,cpu { - sound-dai = <&i2s0_8ch>; - system-clock-frequency = <12288000>; - }; - - daicodec: simple-audio-card,codec { - sound-dai = <&es8388>; - system-clock-frequency = <12288000>; - }; - }; - - vcc3v3_pcie30: regulator-vcc3v3-pcie30 { - compatible = "regulator-fixed"; - enable-active-high; - gpios = <&gpio2 RK_PB6 GPIO_ACTIVE_HIGH>; - regulator-name = "vcc3v3_pcie30"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - startup-delay-us = <5000>; - vin-supply = <&vcc5v0_sys>; - }; - - vcc3v3_pcie_eth: regulator-vcc3v3-pcie-eth { - compatible = "regulator-fixed"; - gpios = <&gpio3 RK_PB4 GPIO_ACTIVE_LOW>; - regulator-name = "vcc3v3_pcie_eth"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - startup-delay-us = <50000>; - vin-supply = <&vcc5v0_sys>; - }; - - vcc3v3_wf: regulator-vcc3v3-wf { - compatible = "regulator-fixed"; - enable-active-high; - gpios = <&gpio2 RK_PC5 GPIO_ACTIVE_HIGH>; - regulator-name = "vcc3v3_wf"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - startup-delay-us = <50000>; - vin-supply = <&vcc5v0_sys>; - }; - - vcc5v0_sys: regulator-vcc5v0-sys { - compatible = "regulator-fixed"; - regulator-name = "vcc5v0_sys"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - }; - - vcc5v0_usb20: regulator-vcc5v0-usb20 { - compatible = "regulator-fixed"; - enable-active-high; - gpio = <&gpio3 RK_PB7 GPIO_ACTIVE_HIGH>; - pinctrl-names = "default"; - pinctrl-0 = <&vcc5v0_usb20_en>; - regulator-name = "vcc5v0_usb20"; + pinctrl-0 = <&typec5v_pwren>; + regulator-name = "vbus5v0_typec"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; vin-supply = <&vcc5v0_sys>; }; }; +&speaker_amp { + enable-gpios = <&gpio3 RK_PC0 GPIO_ACTIVE_HIGH>; + status = "okay"; +}; + +&headphone_amp { + enable-gpios = <&gpio3 RK_PA7 GPIO_ACTIVE_HIGH>; +}; + +&analog_sound { + pinctrl-names = "default"; + pinctrl-0 = <&hp_detect>; + simple-audio-card,aux-devs = <&speaker_amp>, <&headphone_amp>; + simple-audio-card,hp-det-gpios = <&gpio1 RK_PD3 GPIO_ACTIVE_LOW>; + simple-audio-card,widgets = + "Microphone", "Onboard Microphone", + "Microphone", "Microphone Jack", + "Speaker", "Speaker", + "Headphone", "Headphones"; + + simple-audio-card,routing = + "Headphones", "LOUT1", + "Headphones", "ROUT1", + "Speaker", "LOUT2", + "Speaker", "ROUT2", + + "Headphones", "Headphones Amp OUTL", + "Headphones", "Headphones Amp OUTR", + "Headphones Amp INL", "LOUT1", + "Headphones Amp INR", "ROUT1", + + "Speaker", "Speaker Amp OUTL", + "Speaker", "Speaker Amp OUTR", + "Speaker Amp INL", "LOUT2", + "Speaker Amp INR", "ROUT2", + + /* single ended signal to LINPUT1 */ + "LINPUT1", "Microphone Jack", + "RINPUT1", "Microphone Jack", + /* differential signal */ + "LINPUT2", "Onboard Microphone", + "RINPUT2", "Onboard Microphone"; +}; + &combphy0_ps { status = "okay"; }; @@ -239,45 +105,8 @@ status = "okay"; }; -&combphy2_psu { - status = "okay"; -}; - -&cpu_b0 { - cpu-supply = <&vdd_cpu_big0_s0>; -}; - -&cpu_b1 { - cpu-supply = <&vdd_cpu_big0_s0>; -}; - -&cpu_b2 { - cpu-supply = <&vdd_cpu_big1_s0>; -}; - -&cpu_b3 { - cpu-supply = <&vdd_cpu_big1_s0>; -}; - -&cpu_l0 { - cpu-supply = <&vdd_cpu_lit_s0>; -}; - -&cpu_l1 { - cpu-supply = <&vdd_cpu_lit_s0>; -}; - -&cpu_l2 { - cpu-supply = <&vdd_cpu_lit_s0>; -}; - -&cpu_l3 { - cpu-supply = <&vdd_cpu_lit_s0>; -}; - -&gpu { - mali-supply = <&vdd_gpu_s0>; - status = "okay"; +&fan { + pwms = <&pwm3 0 50000 0>; }; &hdmi0 { @@ -300,128 +129,73 @@ status = "okay"; }; -&i2c0 { +&hym8563 { + interrupt-parent = <&gpio0>; + interrupts = ; pinctrl-names = "default"; - pinctrl-0 = <&i2c0m2_xfer>; - status = "okay"; - - vdd_cpu_big0_s0: regulator@42 { - compatible = "rockchip,rk8602"; - reg = <0x42>; - fcs,suspend-voltage-selector = <1>; - regulator-name = "vdd_cpu_big0_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <550000>; - regulator-max-microvolt = <1050000>; - regulator-ramp-delay = <2300>; - vin-supply = <&vcc5v0_sys>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - vdd_cpu_big1_s0: regulator@43 { - compatible = "rockchip,rk8603", "rockchip,rk8602"; - reg = <0x43>; - fcs,suspend-voltage-selector = <1>; - regulator-name = "vdd_cpu_big1_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <550000>; - regulator-max-microvolt = <1050000>; - regulator-ramp-delay = <2300>; - vin-supply = <&vcc5v0_sys>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; + pinctrl-0 = <&hym8563_int>; }; &i2c6 { - clock-frequency = <400000>; - status = "okay"; - - hym8563: rtc@51 { - compatible = "haoyu,hym8563"; - reg = <0x51>; + usbc0: usb-typec@22 { + compatible = "fcs,fusb302"; + reg = <0x22>; interrupt-parent = <&gpio0>; - interrupts = ; - #clock-cells = <0>; - clock-output-names = "hym8563"; + interrupts = ; pinctrl-names = "default"; - pinctrl-0 = <&hym8563_int>; - wakeup-source; + pinctrl-0 = <&usbc0_int>; + vbus-supply = <&vbus5v0_typec>; + status = "okay"; + + usb_con: connector { + compatible = "usb-c-connector"; + data-role = "dual"; + label = "USB-C"; + power-role = "dual"; + op-sink-microwatt = <10>; + source-pdos = ; + sink-pdos = ; + try-power-role = "source"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + usbc0_hs: endpoint { + remote-endpoint = <&usb_host0_xhci_drd_sw>; + }; + }; + + port@1 { + reg = <1>; + + usbc0_ss: endpoint { + remote-endpoint = <&usbdp_phy0_typec_ss>; + }; + }; + + port@2 { + reg = <2>; + + usbc0_sbu: endpoint { + remote-endpoint = <&usbdp_phy0_typec_sbu>; + }; + }; + }; + }; }; }; -&i2c7 { - status = "okay"; - - /* PLDO2 vcca 1.8V, BUCK8 gated by PLDO2 being enabled */ - es8388: audio-codec@11 { - compatible = "everest,es8388"; - reg = <0x11>; - clocks = <&cru I2S0_8CH_MCLKOUT>; - AVDD-supply = <&vcc_1v8_s0>; - DVDD-supply = <&vcc_1v8_s0>; - HPVDD-supply = <&vcc_3v3_s0>; - PVDD-supply = <&vcc_3v3_s0>; - assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; - assigned-clock-rates = <12288000>; - #sound-dai-cells = <0>; - }; -}; - -&i2s0_8ch { - pinctrl-names = "default"; - pinctrl-0 = <&i2s0_lrck - &i2s0_mclk - &i2s0_sclk - &i2s0_sdi0 - &i2s0_sdo0>; +&led_blue_gpio { + gpios = <&gpio3 RK_PA6 GPIO_ACTIVE_HIGH>; status = "okay"; }; -&i2s2_2ch { - pinctrl-names = "default"; - pinctrl-0 = <&i2s2m0_lrck - &i2s2m0_sclk - &i2s2m0_sdi - &i2s2m0_sdo>; - status = "okay"; -}; - -&package_thermal { - polling-delay = <1000>; - - cooling-maps { - map0 { - trip = <&package_fan0>; - cooling-device = <&fan THERMAL_NO_LIMIT 1>; - }; - - map1 { - trip = <&package_fan1>; - cooling-device = <&fan 2 THERMAL_NO_LIMIT>; - }; - }; - - trips { - package_fan0: package-fan0 { - temperature = <55000>; - hysteresis = <2000>; - type = "active"; - }; - - package_fan1: package-fan1 { - temperature = <65000>; - hysteresis = <2000>; - type = "active"; - }; - }; +&led_green_pwm { + pwms = <&pwm2 0 25000 0>; }; /* phy1 - M.KEY socket */ @@ -445,16 +219,6 @@ status = "okay"; }; -&pcie30phy { - status = "okay"; -}; - -&pcie3x4 { - reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>; - vpcie3v3-supply = <&vcc3v3_pcie30>; - status = "okay"; -}; - &pinctrl { hym8563 { hym8563_int: hym8563-int { @@ -485,6 +249,16 @@ rockchip,pins = <3 RK_PB7 RK_FUNC_GPIO &pcfg_pull_none>; }; }; + + usb-typec { + usbc0_int: usbc0-int { + rockchip,pins = <0 RK_PD3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + + typec5v_pwren: typec5v-pwren { + rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; }; &pwm2 { @@ -498,405 +272,17 @@ status = "okay"; }; -&saradc { - vref-supply = <&vcc_1v8_s0>; - status = "okay"; -}; - -&sdhci { - bus-width = <8>; - no-sdio; - no-sd; - non-removable; - max-frequency = <200000000>; - mmc-hs400-1_8v; - mmc-hs400-enhanced-strobe; - status = "okay"; -}; - -&sdmmc { - bus-width = <4>; - cap-sd-highspeed; - cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; - disable-wp; - max-frequency = <150000000>; - no-sdio; - no-mmc; - sd-uhs-sdr104; - vmmc-supply = <&vcc_3v3_s3>; - vqmmc-supply = <&vccio_sd_s0>; +&recovery_button { status = "okay"; }; &sfc { pinctrl-names = "default"; pinctrl-0 = <&fspim1_pins>; - status = "okay"; - - spi_flash: flash@0 { - compatible = "jedec,spi-nor"; - reg = <0x0>; - spi-max-frequency = <100000000>; - spi-rx-bus-width = <4>; - spi-tx-bus-width = <1>; - }; }; -&spi2 { - assigned-clocks = <&cru CLK_SPI2>; - assigned-clock-rates = <200000000>; - num-cs = <1>; - pinctrl-names = "default"; - pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>; - status = "okay"; - - pmic@0 { - compatible = "rockchip,rk806"; - reg = <0x0>; - interrupt-parent = <&gpio0>; - interrupts = <7 IRQ_TYPE_LEVEL_LOW>; - pinctrl-names = "default"; - pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, - <&rk806_dvs2_null>, <&rk806_dvs3_null>; - spi-max-frequency = <1000000>; - system-power-controller; - - vcc1-supply = <&vcc5v0_sys>; - vcc2-supply = <&vcc5v0_sys>; - vcc3-supply = <&vcc5v0_sys>; - vcc4-supply = <&vcc5v0_sys>; - vcc5-supply = <&vcc5v0_sys>; - vcc6-supply = <&vcc5v0_sys>; - vcc7-supply = <&vcc5v0_sys>; - vcc8-supply = <&vcc5v0_sys>; - vcc9-supply = <&vcc5v0_sys>; - vcc10-supply = <&vcc5v0_sys>; - vcc11-supply = <&vcc_2v0_pldo_s3>; - vcc12-supply = <&vcc5v0_sys>; - vcc13-supply = <&vdd2_ddr_s3>; - vcc14-supply = <&vdd2_ddr_s3>; - vcca-supply = <&vcc5v0_sys>; - - gpio-controller; - #gpio-cells = <2>; - - rk806_dvs1_null: dvs1-null-pins { - pins = "gpio_pwrctrl1"; - function = "pin_fun0"; - }; - - rk806_dvs2_null: dvs2-null-pins { - pins = "gpio_pwrctrl2"; - function = "pin_fun0"; - }; - - rk806_dvs3_null: dvs3-null-pins { - pins = "gpio_pwrctrl3"; - function = "pin_fun0"; - }; - - regulators { - vdd_gpu_s0: dcdc-reg1 { - regulator-name = "vdd_gpu_s0"; - regulator-boot-on; - regulator-enable-ramp-delay = <400>; - regulator-min-microvolt = <550000>; - regulator-max-microvolt = <950000>; - regulator-ramp-delay = <12500>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - vdd_cpu_lit_s0: dcdc-reg2 { - regulator-name = "vdd_cpu_lit_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <550000>; - regulator-max-microvolt = <950000>; - regulator-ramp-delay = <12500>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - vdd_log_s0: dcdc-reg3 { - regulator-name = "vdd_log_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <675000>; - regulator-max-microvolt = <825000>; - regulator-ramp-delay = <12500>; - - regulator-state-mem { - regulator-off-in-suspend; - regulator-suspend-microvolt = <750000>; - }; - }; - - vdd_vdenc_s0: dcdc-reg4 { - regulator-name = "vdd_vdenc_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <550000>; - regulator-max-microvolt = <825000>; - regulator-ramp-delay = <12500>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - vdd_ddr_s0: dcdc-reg5 { - regulator-name = "vdd_ddr_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <675000>; - regulator-max-microvolt = <900000>; - regulator-ramp-delay = <12500>; - - regulator-state-mem { - regulator-off-in-suspend; - regulator-suspend-microvolt = <850000>; - }; - }; - - vdd2_ddr_s3: dcdc-reg6 { - regulator-name = "vdd2_ddr_s3"; - regulator-always-on; - regulator-boot-on; - - regulator-state-mem { - regulator-on-in-suspend; - }; - }; - - vcc_2v0_pldo_s3: dcdc-reg7 { - regulator-name = "vdd_2v0_pldo_s3"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <2000000>; - regulator-max-microvolt = <2000000>; - regulator-ramp-delay = <12500>; - - regulator-state-mem { - regulator-on-in-suspend; - regulator-suspend-microvolt = <2000000>; - }; - }; - - vcc_3v3_s3: dcdc-reg8 { - regulator-name = "vcc_3v3_s3"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - - regulator-state-mem { - regulator-on-in-suspend; - regulator-suspend-microvolt = <3300000>; - }; - }; - - vddq_ddr_s0: dcdc-reg9 { - regulator-name = "vddq_ddr_s0"; - regulator-always-on; - regulator-boot-on; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - vcc_1v8_s3: dcdc-reg10 { - regulator-name = "vcc_1v8_s3"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - - regulator-state-mem { - regulator-on-in-suspend; - regulator-suspend-microvolt = <1800000>; - }; - }; - - avcc_1v8_s0: pldo-reg1 { - regulator-name = "avcc_1v8_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - - regulator-state-mem { - regulator-off-in-suspend; - regulator-suspend-microvolt = <1800000>; - }; - }; - - /* shorted to avcc_1v8_s0 on the board */ - vcc_1v8_s0: pldo-reg2 { - regulator-name = "vcc_1v8_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - - regulator-state-mem { - regulator-off-in-suspend; - regulator-suspend-microvolt = <1800000>; - }; - }; - - avdd_1v2_s0: pldo-reg3 { - regulator-name = "avdd_1v2_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <1200000>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - vcc_3v3_s0: pldo-reg4 { - regulator-name = "vcc_3v3_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-ramp-delay = <12500>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - vccio_sd_s0: pldo-reg5 { - regulator-name = "vccio_sd_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - regulator-ramp-delay = <12500>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - pldo6_s3: pldo-reg6 { - regulator-name = "pldo6_s3"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - - regulator-state-mem { - regulator-on-in-suspend; - regulator-suspend-microvolt = <1800000>; - }; - }; - - vdd_0v75_s3: nldo-reg1 { - regulator-name = "vdd_0v75_s3"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <750000>; - - regulator-state-mem { - regulator-on-in-suspend; - regulator-suspend-microvolt = <750000>; - }; - }; - - vdd_ddr_pll_s0: nldo-reg2 { - regulator-name = "vdd_ddr_pll_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <850000>; - regulator-max-microvolt = <850000>; - - regulator-state-mem { - regulator-off-in-suspend; - regulator-suspend-microvolt = <850000>; - }; - }; - - avdd_0v75_s0: nldo-reg3 { - regulator-name = "avdd_0v75_s0"; - regulator-always-on; - regulator-boot-on; - /* - * The schematic mentions that actual setting - * should be 0.8375V. RK3588 datasheet specifies - * maximum as 0.825V. So we set datasheet max - * here. - */ - regulator-min-microvolt = <825000>; - regulator-max-microvolt = <825000>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - vdd_0v85_s0: nldo-reg4 { - regulator-name = "vdd_0v85_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <850000>; - regulator-max-microvolt = <850000>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - - vdd_0v75_s0: nldo-reg5 { - regulator-name = "vdd_0v75_s0"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <750000>; - regulator-max-microvolt = <750000>; - - regulator-state-mem { - regulator-off-in-suspend; - }; - }; - }; - }; -}; - -&tsadc { - status = "okay"; -}; - -&u2phy2 { - status = "okay"; -}; - -&u2phy3 { - status = "okay"; -}; - -&u2phy2_host { - phy-supply = <&vcc5v0_usb20>; - status = "okay"; -}; - -&u2phy3_host { - phy-supply = <&vcc5v0_usb20>; - status = "okay"; -}; - -&uart2 { - pinctrl-0 = <&uart2m0_xfer>; - status = "okay"; +&u2phy1_otg { + phy-supply = <&vcc5v0_sys>; }; &uart9 { @@ -904,28 +290,50 @@ status = "okay"; }; -&usb_host0_ehci { +&usbdp_phy0 { + mode-switch; + orientation-switch; + sbu1-dc-gpios = <&gpio4 RK_PA6 GPIO_ACTIVE_HIGH>; + sbu2-dc-gpios = <&gpio4 RK_PA7 GPIO_ACTIVE_HIGH>; + + port { + #address-cells = <1>; + #size-cells = <0>; + + usbdp_phy0_typec_ss: endpoint@0 { + reg = <0>; + remote-endpoint = <&usbc0_ss>; + }; + + usbdp_phy0_typec_sbu: endpoint@1 { + reg = <1>; + remote-endpoint = <&usbc0_sbu>; + }; + }; +}; + +&usb_host0_xhci { + usb-role-switch; + + port { + usb_host0_xhci_drd_sw: endpoint { + remote-endpoint = <&usbc0_hs>; + }; + }; +}; + +&vcc3v3_pcie_eth { + gpios = <&gpio3 RK_PB4 GPIO_ACTIVE_LOW>; +}; + +&vcc3v3_wf { status = "okay"; }; -&usb_host0_ohci { - status = "okay"; -}; - -&usb_host1_ehci { - status = "okay"; -}; - -&usb_host1_ohci { - status = "okay"; -}; - -&vop_mmu { - status = "okay"; -}; - -&vop { - status = "okay"; +&vcc5v0_usb20 { + gpio = <&gpio3 RK_PB7 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&vcc5v0_usb20_en>; }; &vp0 { diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi new file mode 100644 index 000000000000..a98e804a0949 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi @@ -0,0 +1,805 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright (c) 2023 Ondřej Jirman + */ + +/dts-v1/; + +#include +#include +#include +#include +#include +#include "rk3588.dtsi" + +/ { + aliases { + mmc0 = &sdhci; + mmc1 = &sdmmc; + }; + + chosen { + stdout-path = "serial2:1500000n8"; + }; + + adc-keys-0 { + compatible = "adc-keys"; + io-channels = <&saradc 0>; + io-channel-names = "buttons"; + keyup-threshold-microvolt = <1800000>; + poll-interval = <100>; + + button-maskrom { + label = "Mask Rom"; + linux,code = ; + press-threshold-microvolt = <2000>; + }; + }; + + recovery_button: adc-keys-1 { + compatible = "adc-keys"; + io-channels = <&saradc 1>; + io-channel-names = "buttons"; + keyup-threshold-microvolt = <1800000>; + poll-interval = <100>; + status = "disabled"; + + button-recovery { + label = "Recovery"; + linux,code = ; + press-threshold-microvolt = <2000>; + }; + }; + + speaker_amp: speaker-audio-amplifier { + compatible = "simple-audio-amplifier"; + sound-name-prefix = "Speaker Amp"; + status = "disabled"; + }; + + headphone_amp: headphones-audio-amplifier { + compatible = "simple-audio-amplifier"; + sound-name-prefix = "Headphones Amp"; + }; + + gpio-leds { + compatible = "gpio-leds"; + + led_blue_gpio: led { + color = ; + function = LED_FUNCTION_INDICATOR; + function-enumerator = <1>; + status = "disabled"; + }; + }; + + fan: pwm-fan { + compatible = "pwm-fan"; + cooling-levels = <0 70 75 80 100>; + fan-supply = <&vcc5v0_sys>; + #cooling-cells = <2>; + }; + + pwm-leds { + compatible = "pwm-leds"; + + led_blue_pwm: led-1 { + color = ; + function = LED_FUNCTION_STATUS; + linux,default-trigger = "heartbeat"; + max-brightness = <255>; + status = "disabled"; + }; + + led_green_pwm: led-2 { + color = ; + function = LED_FUNCTION_INDICATOR; + function-enumerator = <2>; + max-brightness = <255>; + }; + }; + + rfkill { + compatible = "rfkill-gpio"; + label = "rfkill-pcie-wlan"; + radio-type = "wlan"; + shutdown-gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>; + }; + + analog_sound: sound { + compatible = "simple-audio-card"; + simple-audio-card,name = "Analog"; + simple-audio-card,format = "i2s"; + simple-audio-card,mclk-fs = <256>; + simple-audio-card,bitclock-master = <&daicpu>; + simple-audio-card,frame-master = <&daicpu>; + /*TODO: SARADC_IN3 is used as MIC detection / key input */ + + daicpu: simple-audio-card,cpu { + sound-dai = <&i2s0_8ch>; + system-clock-frequency = <12288000>; + }; + + daicodec: simple-audio-card,codec { + sound-dai = <&es8388>; + system-clock-frequency = <12288000>; + }; + }; + + vcc3v3_pcie30: regulator-vcc3v3-pcie30 { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio2 RK_PB6 GPIO_ACTIVE_HIGH>; + regulator-name = "vcc3v3_pcie30"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + startup-delay-us = <5000>; + vin-supply = <&vcc5v0_sys>; + }; + + vcc3v3_pcie_eth: regulator-vcc3v3-pcie-eth { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3_pcie_eth"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + startup-delay-us = <50000>; + vin-supply = <&vcc_3v3_s3>; + }; + + vcc3v3_wf: regulator-vcc3v3-wf { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio2 RK_PC5 GPIO_ACTIVE_HIGH>; + regulator-name = "vcc3v3_wf"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + startup-delay-us = <50000>; + vin-supply = <&vcc5v0_sys>; + status = "disabled"; + }; + + vcc5v0_sys: regulator-vcc5v0-sys { + compatible = "regulator-fixed"; + regulator-name = "vcc5v0_sys"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vcc5v0_usb20: regulator-vcc5v0-usb20 { + compatible = "regulator-fixed"; + enable-active-high; + regulator-name = "vcc5v0_usb20"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc5v0_sys>; + }; +}; + +&combphy2_psu { + status = "okay"; +}; + +&cpu_b0 { + cpu-supply = <&vdd_cpu_big0_s0>; +}; + +&cpu_b1 { + cpu-supply = <&vdd_cpu_big0_s0>; +}; + +&cpu_b2 { + cpu-supply = <&vdd_cpu_big1_s0>; +}; + +&cpu_b3 { + cpu-supply = <&vdd_cpu_big1_s0>; +}; + +&cpu_l0 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l1 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l2 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l3 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&gpu { + mali-supply = <&vdd_gpu_s0>; + status = "okay"; +}; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0m2_xfer>; + status = "okay"; + + vdd_cpu_big0_s0: regulator@42 { + compatible = "rockchip,rk8602"; + reg = <0x42>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_cpu_big0_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc5v0_sys>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_big1_s0: regulator@43 { + compatible = "rockchip,rk8603", "rockchip,rk8602"; + reg = <0x43>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_cpu_big1_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <2300>; + vin-supply = <&vcc5v0_sys>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; +}; + +&i2c6 { + clock-frequency = <400000>; + status = "okay"; + + hym8563: rtc@51 { + compatible = "haoyu,hym8563"; + reg = <0x51>; + #clock-cells = <0>; + clock-output-names = "hym8563"; + wakeup-source; + }; +}; + +&i2c7 { + status = "okay"; + + /* PLDO2 vcca 1.8V, BUCK8 gated by PLDO2 being enabled */ + es8388: audio-codec@11 { + compatible = "everest,es8388"; + reg = <0x11>; + clocks = <&cru I2S0_8CH_MCLKOUT>; + AVDD-supply = <&vcc_3v3_s0>; + DVDD-supply = <&vcc_1v8_s0>; + HPVDD-supply = <&vcc_3v3_s0>; + PVDD-supply = <&vcc_1v8_s0>; + assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; + assigned-clock-rates = <12288000>; + #sound-dai-cells = <0>; + }; +}; + +&i2s0_8ch { + pinctrl-names = "default"; + pinctrl-0 = <&i2s0_lrck + &i2s0_mclk + &i2s0_sclk + &i2s0_sdi0 + &i2s0_sdo0>; + status = "okay"; +}; + +&i2s2_2ch { + pinctrl-names = "default"; + pinctrl-0 = <&i2s2m0_lrck + &i2s2m0_sclk + &i2s2m0_sdi + &i2s2m0_sdo>; + status = "okay"; +}; + +&package_thermal { + polling-delay = <1000>; + + cooling-maps { + map0 { + trip = <&package_fan0>; + cooling-device = <&fan THERMAL_NO_LIMIT 1>; + }; + + map1 { + trip = <&package_fan1>; + cooling-device = <&fan 2 THERMAL_NO_LIMIT>; + }; + }; + + trips { + package_fan0: package-fan0 { + temperature = <55000>; + hysteresis = <2000>; + type = "active"; + }; + + package_fan1: package-fan1 { + temperature = <65000>; + hysteresis = <2000>; + type = "active"; + }; + }; +}; + +&pcie30phy { + status = "okay"; +}; + +&pcie3x4 { + reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc3v3_pcie30>; + status = "okay"; +}; + +&saradc { + vref-supply = <&vcc_1v8_s0>; + status = "okay"; +}; + +&sdhci { + bus-width = <8>; + no-sdio; + no-sd; + non-removable; + max-frequency = <200000000>; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + status = "okay"; +}; + +&sdmmc { + bus-width = <4>; + cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; + disable-wp; + max-frequency = <150000000>; + no-sdio; + no-mmc; + sd-uhs-sdr104; + vmmc-supply = <&vcc_3v3_s3>; + vqmmc-supply = <&vccio_sd_s0>; + status = "okay"; +}; + +&sfc { + status = "okay"; + + spi_flash: flash@0 { + compatible = "jedec,spi-nor"; + reg = <0x0>; + spi-max-frequency = <100000000>; + spi-rx-bus-width = <4>; + spi-tx-bus-width = <1>; + }; +}; + +&spi2 { + assigned-clocks = <&cru CLK_SPI2>; + assigned-clock-rates = <200000000>; + num-cs = <1>; + pinctrl-names = "default"; + pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>; + status = "okay"; + + pmic@0 { + compatible = "rockchip,rk806"; + reg = <0x0>; + interrupt-parent = <&gpio0>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, + <&rk806_dvs2_null>, <&rk806_dvs3_null>; + spi-max-frequency = <1000000>; + system-power-controller; + + vcc1-supply = <&vcc5v0_sys>; + vcc2-supply = <&vcc5v0_sys>; + vcc3-supply = <&vcc5v0_sys>; + vcc4-supply = <&vcc5v0_sys>; + vcc5-supply = <&vcc5v0_sys>; + vcc6-supply = <&vcc5v0_sys>; + vcc7-supply = <&vcc5v0_sys>; + vcc8-supply = <&vcc5v0_sys>; + vcc9-supply = <&vcc5v0_sys>; + vcc10-supply = <&vcc5v0_sys>; + vcc11-supply = <&vcc_2v0_pldo_s3>; + vcc12-supply = <&vcc5v0_sys>; + vcc13-supply = <&vdd2_ddr_s3>; + vcc14-supply = <&vdd2_ddr_s3>; + vcca-supply = <&vcc5v0_sys>; + + gpio-controller; + #gpio-cells = <2>; + + rk806_dvs1_null: dvs1-null-pins { + pins = "gpio_pwrctrl1"; + function = "pin_fun0"; + }; + + rk806_dvs2_null: dvs2-null-pins { + pins = "gpio_pwrctrl2"; + function = "pin_fun0"; + }; + + rk806_dvs3_null: dvs3-null-pins { + pins = "gpio_pwrctrl3"; + function = "pin_fun0"; + }; + + regulators { + vdd_gpu_s0: dcdc-reg1 { + regulator-name = "vdd_gpu_s0"; + regulator-boot-on; + regulator-enable-ramp-delay = <400>; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_lit_s0: dcdc-reg2 { + regulator-name = "vdd_cpu_lit_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <950000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_log_s0: dcdc-reg3 { + regulator-name = "vdd_log_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <675000>; + regulator-max-microvolt = <825000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vdd_vdenc_s0: dcdc-reg4 { + regulator-name = "vdd_vdenc_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <550000>; + regulator-max-microvolt = <825000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_ddr_s0: dcdc-reg5 { + regulator-name = "vdd_ddr_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <675000>; + regulator-max-microvolt = <900000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <850000>; + }; + }; + + vdd2_ddr_s3: dcdc-reg6 { + regulator-name = "vdd2_ddr_s3"; + regulator-always-on; + regulator-boot-on; + + regulator-state-mem { + regulator-on-in-suspend; + }; + }; + + vcc_2v0_pldo_s3: dcdc-reg7 { + regulator-name = "vdd_2v0_pldo_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <2000000>; + regulator-max-microvolt = <2000000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <2000000>; + }; + }; + + vcc_3v3_s3: dcdc-reg8 { + regulator-name = "vcc_3v3_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <3300000>; + }; + }; + + vddq_ddr_s0: dcdc-reg9 { + regulator-name = "vddq_ddr_s0"; + regulator-always-on; + regulator-boot-on; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_1v8_s3: dcdc-reg10 { + regulator-name = "vcc_1v8_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + avcc_1v8_s0: pldo-reg1 { + regulator-name = "avcc_1v8_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + /* shorted to avcc_1v8_s0 on the board */ + vcc_1v8_s0: pldo-reg2 { + regulator-name = "vcc_1v8_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + avdd_1v2_s0: pldo-reg3 { + regulator-name = "avdd_1v2_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_3v3_s0: pldo-reg4 { + regulator-name = "vcc_3v3_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vccio_sd_s0: pldo-reg5 { + regulator-name = "vccio_sd_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <12500>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + pldo6_s3: pldo-reg6 { + regulator-name = "pldo6_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vdd_0v75_s3: nldo-reg1 { + regulator-name = "vdd_0v75_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <750000>; + }; + }; + + vdd_ddr_pll_s0: nldo-reg2 { + regulator-name = "vdd_ddr_pll_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + + regulator-state-mem { + regulator-off-in-suspend; + regulator-suspend-microvolt = <850000>; + }; + }; + + avdd_0v75_s0: nldo-reg3 { + regulator-name = "avdd_0v75_s0"; + regulator-always-on; + regulator-boot-on; + /* + * The schematic mentions that actual setting + * should be 0.8375V. RK3588 datasheet specifies + * maximum as 0.825V. So we set datasheet max + * here. + */ + regulator-min-microvolt = <825000>; + regulator-max-microvolt = <825000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_0v85_s0: nldo-reg4 { + regulator-name = "vdd_0v85_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_0v75_s0: nldo-reg5 { + regulator-name = "vdd_0v75_s0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + }; + }; +}; + +&tsadc { + status = "okay"; +}; + +&u2phy0 { + status = "okay"; +}; + +&u2phy0_otg { + status = "okay"; +}; + +&u2phy1 { + status = "okay"; +}; + +&u2phy1_otg { + status = "okay"; +}; + +&u2phy2 { + status = "okay"; +}; + +&u2phy3 { + status = "okay"; +}; + +&u2phy2_host { + phy-supply = <&vcc5v0_usb20>; + status = "okay"; +}; + +&u2phy3_host { + phy-supply = <&vcc5v0_usb20>; + status = "okay"; +}; + +&uart2 { + pinctrl-0 = <&uart2m0_xfer>; + status = "okay"; +}; + +&usbdp_phy0 { + status = "okay"; +}; + +&usbdp_phy1 { + status = "okay"; +}; + +&usb_host0_ehci { + status = "okay"; +}; + +&usb_host0_ohci { + status = "okay"; +}; + +&usb_host0_xhci { + status = "okay"; +}; + +&usb_host1_ehci { + status = "okay"; +}; + +&usb_host1_ohci { + status = "okay"; +}; + +&usb_host1_xhci { + dr_mode = "host"; + status = "okay"; +}; + +&vop_mmu { + status = "okay"; +}; + +&vop { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts index c44d001da169..d597112f1d5b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts @@ -72,7 +72,7 @@ rfkill { compatible = "rfkill-gpio"; - label = "rfkill-pcie-wlan"; + label = "rfkill-m2-wlan"; radio-type = "wlan"; shutdown-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi index 76a6e8e517e9..d2eddea1840f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi @@ -434,6 +434,7 @@ &sdmmc { bus-width = <4>; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-mmc; @@ -774,6 +775,15 @@ status = "okay"; }; +&u2phy0 { + status = "okay"; +}; + +&u2phy0_otg { + phy-supply = <&vcc5v0_usb_otg0>; + status = "okay"; +}; + &u2phy2 { status = "okay"; }; @@ -796,6 +806,15 @@ status = "okay"; }; +&usb_host0_xhci { + dr_mode = "host"; + status = "okay"; +}; + +&usbdp_phy0 { + status = "okay"; +}; + &vop { status = "okay"; }; diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld11-global.dts b/arch/arm64/boot/dts/socionext/uniphier-ld11-global.dts index a251c4343548..de219570bbc9 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ld11-global.dts +++ b/arch/arm64/boot/dts/socionext/uniphier-ld11-global.dts @@ -61,7 +61,7 @@ &i2s_port4 &spdif_port0 &comp_spdif_port0>; - hp-det-gpio = <&gpio UNIPHIER_GPIO_IRQ(0) GPIO_ACTIVE_LOW>; + hp-det-gpios = <&gpio UNIPHIER_GPIO_IRQ(0) GPIO_ACTIVE_LOW>; }; spdif-out { diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20-global.dts b/arch/arm64/boot/dts/socionext/uniphier-ld20-global.dts index 79f6db2455c1..20e5fb724fae 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ld20-global.dts +++ b/arch/arm64/boot/dts/socionext/uniphier-ld20-global.dts @@ -61,7 +61,7 @@ &i2s_port4 &spdif_port0 &comp_spdif_port0>; - hp-det-gpio = <&gpio UNIPHIER_GPIO_IRQ(0) GPIO_ACTIVE_LOW>; + hp-det-gpios = <&gpio UNIPHIER_GPIO_IRQ(0) GPIO_ACTIVE_LOW>; }; spdif-out { diff --git a/arch/arm64/boot/dts/sprd/sc2731.dtsi b/arch/arm64/boot/dts/sprd/sc2731.dtsi index 12136e68dada..458685b82462 100644 --- a/arch/arm64/boot/dts/sprd/sc2731.dtsi +++ b/arch/arm64/boot/dts/sprd/sc2731.dtsi @@ -94,17 +94,17 @@ nvmem-cells = <&adc_big_scale>, <&adc_small_scale>; }; - fuel-gauge@a00 { + pmic_fgu: fuel-gauge@a00 { compatible = "sprd,sc2731-fgu"; reg = <0xa00>; - bat-detect-gpio = <&pmic_eic 9 GPIO_ACTIVE_HIGH>; + battery-detect-gpios = <&pmic_eic 9 GPIO_ACTIVE_HIGH>; io-channels = <&pmic_adc 3>, <&pmic_adc 6>; io-channel-names = "bat-temp", "charge-vol"; - monitored-battery = <&bat>; nvmem-cell-names = "fgu_calib"; nvmem-cells = <&fgu_calib>; interrupt-parent = <&sc2731_pmic>; interrupts = <4>; + status = "disabled"; }; vibrator@ec8 { diff --git a/arch/arm64/boot/dts/sprd/sc9863a.dtsi b/arch/arm64/boot/dts/sprd/sc9863a.dtsi index e5a2857721e2..e97000e560e7 100644 --- a/arch/arm64/boot/dts/sprd/sc9863a.dtsi +++ b/arch/arm64/boot/dts/sprd/sc9863a.dtsi @@ -163,18 +163,18 @@ ap_clk: clock-controller@21500000 { compatible = "sprd,sc9863a-ap-clk"; reg = <0 0x21500000 0 0x1000>; - clocks = <&ext_32k>, <&ext_26m>; - clock-names = "ext-32k", "ext-26m"; + clocks = <&ext_26m>, <&ext_32k>; + clock-names = "ext-26m", "ext-32k"; #clock-cells = <1>; }; aon_clk: clock-controller@402d0000 { compatible = "sprd,sc9863a-aon-clk"; reg = <0 0x402d0000 0 0x1000>; - clocks = <&ext_26m>, <&rco_100m>, - <&ext_32k>, <&ext_4m>; - clock-names = "ext-26m", "rco-100m", - "ext-32k", "ext-4m"; + clocks = <&ext_26m>, <&ext_32k>, + <&ext_4m>, <&rco_100m>; + clock-names = "ext-26m", "ext-32k", + "ext-4m", "rco-100m"; #clock-cells = <1>; }; @@ -288,7 +288,7 @@ }; }; - in-port { + in-ports { port { etf_little_in: endpoint { remote-endpoint = diff --git a/arch/arm64/boot/dts/sprd/sp9860g-1h10.dts b/arch/arm64/boot/dts/sprd/sp9860g-1h10.dts index 095b24a31313..b1fa817ece1e 100644 --- a/arch/arm64/boot/dts/sprd/sp9860g-1h10.dts +++ b/arch/arm64/boot/dts/sprd/sp9860g-1h10.dts @@ -71,8 +71,8 @@ compatible = "simple-battery"; charge-full-design-microamp-hours = <1900000>; charge-term-current-microamp = <120000>; - constant_charge_voltage_max_microvolt = <4350000>; - internal-resistance-micro-ohms = <250000>; + constant-charge-voltage-max-microvolt = <4350000>; + factory-internal-resistance-micro-ohms = <250000>; ocv-capacity-celsius = <20>; ocv-capacity-table-0 = <4185000 100>, <4113000 95>, <4066000 90>, <4022000 85>, <3983000 80>, <3949000 75>, @@ -84,6 +84,11 @@ }; }; +&pmic_fgu { + monitored-battery = <&bat>; + status = "okay"; +}; + &uart0 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/st/stm32mp251.dtsi b/arch/arm64/boot/dts/st/stm32mp251.dtsi index 6fe12e3bd7dd..f3c6cdfd7008 100644 --- a/arch/arm64/boot/dts/st/stm32mp251.dtsi +++ b/arch/arm64/boot/dts/st/stm32mp251.dtsi @@ -7,6 +7,7 @@ #include #include #include +#include / { #address-cells = <2>; @@ -237,6 +238,21 @@ #access-controller-cells = <1>; ranges; + i2s2: audio-controller@400b0000 { + compatible = "st,stm32mp25-i2s"; + reg = <0x400b0000 0x400>; + #sound-dai-cells = <0>; + interrupts = ; + clocks = <&rcc CK_BUS_SPI2>, <&rcc CK_KER_SPI2>; + clock-names = "pclk", "i2sclk"; + resets = <&rcc SPI2_R>; + dmas = <&hpdma 51 0x43 0x12>, + <&hpdma 52 0x43 0x21>; + dma-names = "rx", "tx"; + access-controllers = <&rifsc 23>; + status = "disabled"; + }; + spi2: spi@400b0000 { #address-cells = <1>; #size-cells = <0>; @@ -252,6 +268,21 @@ status = "disabled"; }; + i2s3: audio-controller@400c0000 { + compatible = "st,stm32mp25-i2s"; + reg = <0x400c0000 0x400>; + #sound-dai-cells = <0>; + interrupts = ; + clocks = <&rcc CK_BUS_SPI3>, <&rcc CK_KER_SPI3>; + clock-names = "pclk", "i2sclk"; + resets = <&rcc SPI3_R>; + dmas = <&hpdma 53 0x43 0x12>, + <&hpdma 54 0x43 0x21>; + dma-names = "rx", "tx"; + access-controllers = <&rifsc 24>; + status = "disabled"; + }; + spi3: spi@400c0000 { #address-cells = <1>; #size-cells = <0>; @@ -267,6 +298,20 @@ status = "disabled"; }; + spdifrx: audio-controller@400d0000 { + compatible = "st,stm32h7-spdifrx"; + #sound-dai-cells = <0>; + reg = <0x400d0000 0x400>; + clocks = <&rcc CK_KER_SPDIFRX>; + clock-names = "kclk"; + interrupts = ; + dmas = <&hpdma 71 0x43 0x212>, + <&hpdma 72 0x43 0x212>; + dma-names = "rx", "rx-ctrl"; + access-controllers = <&rifsc 30>; + status = "disabled"; + }; + usart2: serial@400e0000 { compatible = "st,stm32h7-uart"; reg = <0x400e0000 0x400>; @@ -439,6 +484,21 @@ status = "disabled"; }; + i2s1: audio-controller@40230000 { + compatible = "st,stm32mp25-i2s"; + reg = <0x40230000 0x400>; + #sound-dai-cells = <0>; + interrupts = ; + clocks = <&rcc CK_BUS_SPI1>, <&rcc CK_KER_SPI1>; + clock-names = "pclk", "i2sclk"; + resets = <&rcc SPI1_R>; + dmas = <&hpdma 49 0x43 0x12>, + <&hpdma 50 0x43 0x21>; + dma-names = "rx", "tx"; + access-controllers = <&rifsc 22>; + status = "disabled"; + }; + spi1: spi@40230000 { #address-cells = <1>; #size-cells = <0>; @@ -484,6 +544,108 @@ status = "disabled"; }; + sai1: sai@40290000 { + compatible = "st,stm32mp25-sai"; + reg = <0x40290000 0x4>, <0x4029a3f0 0x10>; + ranges = <0 0x40290000 0x400>; + #address-cells = <1>; + #size-cells = <1>; + clocks = <&rcc CK_BUS_SAI1>; + clock-names = "pclk"; + interrupts = ; + resets = <&rcc SAI1_R>; + access-controllers = <&rifsc 49>; + status = "disabled"; + + sai1a: audio-controller@40290004 { + compatible = "st,stm32-sai-sub-a"; + reg = <0x4 0x20>; + #sound-dai-cells = <0>; + clocks = <&rcc CK_KER_SAI1>; + clock-names = "sai_ck"; + dmas = <&hpdma 73 0x43 0x21>; + status = "disabled"; + }; + + sai1b: audio-controller@40290024 { + compatible = "st,stm32-sai-sub-b"; + reg = <0x24 0x20>; + #sound-dai-cells = <0>; + clocks = <&rcc CK_KER_SAI1>; + clock-names = "sai_ck"; + dmas = <&hpdma 74 0x43 0x12>; + status = "disabled"; + }; + }; + + sai2: sai@402a0000 { + compatible = "st,stm32mp25-sai"; + reg = <0x402a0000 0x4>, <0x402aa3f0 0x10>; + ranges = <0 0x402a0000 0x400>; + #address-cells = <1>; + #size-cells = <1>; + clocks = <&rcc CK_BUS_SAI2>; + clock-names = "pclk"; + interrupts = ; + resets = <&rcc SAI2_R>; + access-controllers = <&rifsc 50>; + status = "disabled"; + + sai2a: audio-controller@402a0004 { + compatible = "st,stm32-sai-sub-a"; + reg = <0x4 0x20>; + #sound-dai-cells = <0>; + clocks = <&rcc CK_KER_SAI2>; + clock-names = "sai_ck"; + dmas = <&hpdma 75 0x43 0x21>; + status = "disabled"; + }; + + sai2b: audio-controller@402a0024 { + compatible = "st,stm32-sai-sub-b"; + reg = <0x24 0x20>; + #sound-dai-cells = <0>; + clocks = <&rcc CK_KER_SAI2>; + clock-names = "sai_ck"; + dmas = <&hpdma 76 0x43 0x12>; + status = "disabled"; + }; + }; + + sai3: sai@402b0000 { + compatible = "st,stm32mp25-sai"; + reg = <0x402b0000 0x4>, <0x402ba3f0 0x10>; + ranges = <0 0x402b0000 0x400>; + #address-cells = <1>; + #size-cells = <1>; + clocks = <&rcc CK_BUS_SAI3>; + clock-names = "pclk"; + interrupts = ; + resets = <&rcc SAI3_R>; + access-controllers = <&rifsc 51>; + status = "disabled"; + + sai3a: audio-controller@402b0004 { + compatible = "st,stm32-sai-sub-a"; + reg = <0x4 0x20>; + #sound-dai-cells = <0>; + clocks = <&rcc CK_KER_SAI3>; + clock-names = "sai_ck"; + dmas = <&hpdma 77 0x43 0x21>; + status = "disabled"; + }; + + sai3b: audio-controller@502b0024 { + compatible = "st,stm32-sai-sub-b"; + reg = <0x24 0x20>; + #sound-dai-cells = <0>; + clocks = <&rcc CK_KER_SAI3>; + clock-names = "sai_ck"; + dmas = <&hpdma 78 0x43 0x12>; + status = "disabled"; + }; + }; + uart9: serial@402c0000 { compatible = "st,stm32h7-uart"; reg = <0x402c0000 0x400>; @@ -508,6 +670,40 @@ status = "disabled"; }; + sai4: sai@40340000 { + compatible = "st,stm32mp25-sai"; + reg = <0x40340000 0x4>, <0x4034a3f0 0x10>; + ranges = <0 0x40340000 0x400>; + #address-cells = <1>; + #size-cells = <1>; + clocks = <&rcc CK_BUS_SAI4>; + clock-names = "pclk"; + interrupts = ; + resets = <&rcc SAI4_R>; + access-controllers = <&rifsc 52>; + status = "disabled"; + + sai4a: audio-controller@40340004 { + compatible = "st,stm32-sai-sub-a"; + reg = <0x4 0x20>; + #sound-dai-cells = <0>; + clocks = <&rcc CK_KER_SAI4>; + clock-names = "sai_ck"; + dmas = <&hpdma 79 0x63 0x21>; + status = "disabled"; + }; + + sai4b: audio-controller@40340024 { + compatible = "st,stm32-sai-sub-b"; + reg = <0x24 0x20>; + #sound-dai-cells = <0>; + clocks = <&rcc CK_KER_SAI4>; + clock-names = "sai_ck"; + dmas = <&hpdma 80 0x43 0x12>; + status = "disabled"; + }; + }; + spi6: spi@40350000 { #address-cells = <1>; #size-cells = <0>; @@ -603,6 +799,44 @@ status = "disabled"; }; + csi: csi@48020000 { + compatible = "st,stm32mp25-csi"; + reg = <0x48020000 0x2000>; + interrupts = ; + resets = <&rcc CSI_R>; + clocks = <&rcc CK_KER_CSI>, <&rcc CK_KER_CSITXESC>, + <&rcc CK_KER_CSIPHY>; + clock-names = "pclk", "txesc", "csi2phy"; + access-controllers = <&rifsc 86>; + status = "disabled"; + }; + + dcmipp: dcmipp@48030000 { + compatible = "st,stm32mp25-dcmipp"; + reg = <0x48030000 0x1000>; + interrupts = ; + resets = <&rcc DCMIPP_R>; + clocks = <&rcc CK_BUS_DCMIPP>, <&rcc CK_KER_CSI>; + clock-names = "kclk", "mclk"; + access-controllers = <&rifsc 87>; + status = "disabled"; + }; + + combophy: phy@480c0000 { + compatible = "st,stm32mp25-combophy"; + reg = <0x480c0000 0x1000>; + #phy-cells = <1>; + clocks = <&rcc CK_BUS_USB3PCIEPHY>, <&rcc CK_KER_USB3PCIEPHY>; + clock-names = "apb", "ker"; + resets = <&rcc USB3PCIEPHY_R>; + reset-names = "phy"; + access-controllers = <&rifsc 67>; + power-domains = <&CLUSTER_PD>; + wakeup-source; + interrupts-extended = <&exti1 45 IRQ_TYPE_EDGE_FALLING>; + status = "disabled"; + }; + sdmmc1: mmc@48220000 { compatible = "st,stm32mp25-sdmmc2", "arm,pl18x", "arm,primecell"; arm,primecell-periphid = <0x00353180>; diff --git a/arch/arm64/boot/dts/st/stm32mp257f-ev1.dts b/arch/arm64/boot/dts/st/stm32mp257f-ev1.dts index 6f393b082789..1b88485a62a1 100644 --- a/arch/arm64/boot/dts/st/stm32mp257f-ev1.dts +++ b/arch/arm64/boot/dts/st/stm32mp257f-ev1.dts @@ -27,6 +27,44 @@ stdout-path = "serial0:115200n8"; }; + clocks { + clk_ext_camera: clk-ext-camera { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <24000000>; + }; + + pad_clk: pad-clk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <100000000>; + }; + }; + + imx335_2v9: regulator-2v9 { + compatible = "regulator-fixed"; + regulator-name = "imx335-avdd"; + regulator-min-microvolt = <2900000>; + regulator-max-microvolt = <2900000>; + regulator-always-on; + }; + + imx335_1v8: regulator-1v8 { + compatible = "regulator-fixed"; + regulator-name = "imx335-ovdd"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + }; + + imx335_1v2: regulator-1v2 { + compatible = "regulator-fixed"; + regulator-name = "imx335-dvdd"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-always-on; + }; + memory@80000000 { device_type = "memory"; reg = <0x0 0x80000000 0x1 0x0>; @@ -50,6 +88,46 @@ status = "okay"; }; +&combophy { + clocks = <&rcc CK_BUS_USB3PCIEPHY>, <&rcc CK_KER_USB3PCIEPHY>, <&pad_clk>; + clock-names = "apb", "ker", "pad"; + status = "okay"; +}; + +&csi { + vdd-supply = <&scmi_vddcore>; + vdda18-supply = <&scmi_v1v8>; + status = "okay"; + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + csi_sink: endpoint { + remote-endpoint = <&imx335_ep>; + data-lanes = <1 2>; + bus-type = <4>; + }; + }; + port@1 { + reg = <1>; + csi_source: endpoint { + remote-endpoint = <&dcmipp_0>; + }; + }; + }; +}; + +&dcmipp { + status = "okay"; + port { + dcmipp_0: endpoint { + remote-endpoint = <&csi_source>; + bus-type = <4>; + }; + }; +}; + ðernet2 { pinctrl-names = "default", "sleep"; pinctrl-0 = <ð2_rgmii_pins_a>; @@ -81,6 +159,25 @@ i2c-scl-falling-time-ns = <13>; clock-frequency = <400000>; status = "okay"; + + imx335: camera@1a { + compatible = "sony,imx335"; + reg = <0x1a>; + clocks = <&clk_ext_camera>; + avdd-supply = <&imx335_2v9>; + ovdd-supply = <&imx335_1v8>; + dvdd-supply = <&imx335_1v2>; + reset-gpios = <&gpioi 7 (GPIO_ACTIVE_LOW | GPIO_PUSH_PULL)>; + + port { + imx335_ep: endpoint { + remote-endpoint = <&csi_sink>; + clock-lanes = <0>; + data-lanes = <1 2>; + link-frequencies = /bits/ 64 <594000000>; + }; + }; + }; }; &i2c8 { diff --git a/arch/arm64/boot/dts/ti/Makefile b/arch/arm64/boot/dts/ti/Makefile index f71360f14f23..8a4bdf87e2d4 100644 --- a/arch/arm64/boot/dts/ti/Makefile +++ b/arch/arm64/boot/dts/ti/Makefile @@ -42,10 +42,6 @@ dtb-$(CONFIG_ARCH_K3) += k3-am62x-sk-csi2-imx219.dtbo dtb-$(CONFIG_ARCH_K3) += k3-am62x-sk-hdmi-audio.dtbo # Boards with AM64x SoC -k3-am642-hummingboard-t-pcie-dtbs := \ - k3-am642-hummingboard-t.dtb k3-am642-hummingboard-t-pcie.dtbo -k3-am642-hummingboard-t-usb3-dtbs := \ - k3-am642-hummingboard-t.dtb k3-am642-hummingboard-t-usb3.dtbo dtb-$(CONFIG_ARCH_K3) += k3-am642-evm.dtb dtb-$(CONFIG_ARCH_K3) += k3-am642-evm-icssg1-dualemac.dtbo dtb-$(CONFIG_ARCH_K3) += k3-am642-evm-icssg1-dualemac-mii.dtbo @@ -107,11 +103,13 @@ dtb-$(CONFIG_ARCH_K3) += k3-j721e-common-proc-board-infotainment.dtbo dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm.dtb dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm-gesi-exp-board.dtbo dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm-pcie0-ep.dtbo +dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm-pcie1-ep.dtbo dtb-$(CONFIG_ARCH_K3) += k3-j721e-sk.dtb dtb-$(CONFIG_ARCH_K3) += k3-j721e-sk-csi2-dual-imx219.dtbo # Boards with J721s2 SoC dtb-$(CONFIG_ARCH_K3) += k3-am68-sk-base-board.dtb +dtb-$(CONFIG_ARCH_K3) += k3-am68-sk-base-board-pcie1-ep.dtbo dtb-$(CONFIG_ARCH_K3) += k3-j721s2-common-proc-board.dtb dtb-$(CONFIG_ARCH_K3) += k3-j721s2-evm-gesi-exp-board.dtbo k3-j721s2-evm-dtbs := k3-j721s2-common-proc-board.dtb k3-j721s2-evm-gesi-exp-board.dtbo @@ -124,6 +122,7 @@ dtb-$(CONFIG_ARCH_K3) += k3-j722s-evm.dtb # Boards with J784s4 SoC dtb-$(CONFIG_ARCH_K3) += k3-am69-sk.dtb +dtb-$(CONFIG_ARCH_K3) += k3-am69-sk-pcie0-ep.dtbo dtb-$(CONFIG_ARCH_K3) += k3-j784s4-evm.dtb dtb-$(CONFIG_ARCH_K3) += k3-j784s4-evm-pcie0-pcie1-ep.dtbo dtb-$(CONFIG_ARCH_K3) += k3-j784s4-evm-quad-port-eth-exp1.dtbo @@ -192,14 +191,20 @@ k3-am642-tqma64xxl-mbax4xxl-wlan-dtbs := \ k3-am642-tqma64xxl-mbax4xxl.dtb k3-am64-tqma64xxl-mbax4xxl-wlan.dtbo k3-am68-sk-base-board-csi2-dual-imx219-dtbs := k3-am68-sk-base-board.dtb \ k3-j721e-sk-csi2-dual-imx219.dtbo +k3-am68-sk-base-board-pcie1-ep-dtbs := k3-am68-sk-base-board.dtb \ + k3-am68-sk-base-board-pcie1-ep.dtbo k3-am69-sk-csi2-dual-imx219-dtbs := k3-am69-sk.dtb \ k3-j721e-sk-csi2-dual-imx219.dtbo +k3-am69-sk-pcie0-ep-dtbs := k3-am69-sk.dtb \ + k3-am69-sk-pcie0-ep.dtbo k3-j7200-evm-pcie1-ep-dtbs := k3-j7200-common-proc-board.dtb \ k3-j7200-evm-pcie1-ep.dtbo k3-j721e-common-proc-board-infotainment-dtbs := k3-j721e-common-proc-board.dtb \ k3-j721e-common-proc-board-infotainment.dtbo k3-j721e-evm-pcie0-ep-dtbs := k3-j721e-common-proc-board.dtb \ k3-j721e-evm-pcie0-ep.dtbo +k3-j721e-evm-pcie1-ep-dtbs := k3-j721e-common-proc-board.dtb \ + k3-j721e-evm-pcie1-ep.dtbo k3-j721e-sk-csi2-dual-imx219-dtbs := k3-j721e-sk.dtb \ k3-j721e-sk-csi2-dual-imx219.dtbo k3-j721s2-evm-pcie1-ep-dtbs := k3-j721s2-common-proc-board.dtb \ @@ -229,10 +234,13 @@ dtb- += k3-am625-beagleplay-csi2-ov5640.dtb \ k3-am642-tqma64xxl-mbax4xxl-sdcard.dtb \ k3-am642-tqma64xxl-mbax4xxl-wlan.dtb \ k3-am68-sk-base-board-csi2-dual-imx219.dtb \ + k3-am68-sk-base-board-pcie1-ep.dtb \ k3-am69-sk-csi2-dual-imx219.dtb \ - k3-j7200-evm-pcie1-ep.dtbo \ + k3-am69-sk-pcie0-ep.dtb \ + k3-j7200-evm-pcie1-ep.dtb \ k3-j721e-common-proc-board-infotainment.dtb \ k3-j721e-evm-pcie0-ep.dtb \ + k3-j721e-evm-pcie1-ep.dtb \ k3-j721e-sk-csi2-dual-imx219.dtb \ k3-j721s2-evm-pcie1-ep.dtb \ k3-j784s4-evm-pcie0-pcie1-ep.dtb \ @@ -255,6 +263,7 @@ DTC_FLAGS_k3-am68-sk-base-board += -@ DTC_FLAGS_k3-am69-sk += -@ DTC_FLAGS_k3-j7200-common-proc-board += -@ DTC_FLAGS_k3-j721e-common-proc-board += -@ +DTC_FLAGS_k3-j721e-evm-pcie0-ep += -@ DTC_FLAGS_k3-j721e-sk += -@ DTC_FLAGS_k3-j721s2-common-proc-board += -@ DTC_FLAGS_k3-j784s4-evm += -@ diff --git a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi index 7cd727d10a5f..7d355aa73ea2 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi @@ -23,7 +23,6 @@ interrupt-controller; reg = <0x00 0x01800000 0x00 0x10000>, /* GICD */ <0x00 0x01880000 0x00 0xc0000>, /* GICR */ - <0x00 0x01880000 0x00 0xc0000>, /* GICR */ <0x01 0x00000000 0x00 0x2000>, /* GICC */ <0x01 0x00010000 0x00 0x1000>, /* GICH */ <0x01 0x00020000 0x00 0x2000>; /* GICV */ diff --git a/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi b/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi index 5952874fe429..2ef4cbaec789 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi @@ -95,6 +95,16 @@ regulator-boot-on; }; + vddshv_3v3: regulator-vddshv-3v3 { + compatible = "regulator-fixed"; + regulator-name = "VDDSHV0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vdd_3v3>; + regulator-always-on; + regulator-boot-on; + }; + leds { compatible = "gpio-leds"; pinctrl-names = "default"; @@ -313,6 +323,7 @@ compatible = "atmel,24c32"; pagesize = <32>; reg = <0x50>; + vcc-supply = <&vddshv_3v3>; }; i2c_som_rtc: rtc@52 { diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts index ee96f4f6deb0..75c80290b12a 100644 --- a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts +++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts @@ -610,7 +610,7 @@ reg = <1>; reset-gpios = <&main_gpio1 5 GPIO_ACTIVE_LOW>; reset-assert-us = <25>; - reset-deassert-us = <60000>; /* T2 */ + reset-deassert-us = <35>; }; }; diff --git a/arch/arm64/boot/dts/ti/k3-am625-sk.dts b/arch/arm64/boot/dts/ti/k3-am625-sk.dts index ae81ebb39d02..2fbfa3719345 100644 --- a/arch/arm64/boot/dts/ti/k3-am625-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am625-sk.dts @@ -219,13 +219,6 @@ }; }; -&mailbox0_cluster0 { - mbox_m4_0: mbox-m4-0 { - ti,mbox-rx = <0 0 0>; - ti,mbox-tx = <1 0 0>; - }; -}; - &fss { bootph-all; }; diff --git a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi index a93e2cd7b8c7..a1daba7b1fad 100644 --- a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi @@ -18,7 +18,6 @@ compatible = "arm,gic-v3"; reg = <0x00 0x01800000 0x00 0x10000>, /* GICD */ <0x00 0x01880000 0x00 0xc0000>, /* GICR */ - <0x00 0x01880000 0x00 0xc0000>, /* GICR */ <0x01 0x00000000 0x00 0x2000>, /* GICC */ <0x01 0x00010000 0x00 0x1000>, /* GICH */ <0x01 0x00020000 0x00 0x2000>; /* GICV */ diff --git a/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi index 0b1dd5390cd3..b2c8f5351743 100644 --- a/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi @@ -2,9 +2,11 @@ /* * Device Tree Source for AM62A SoC Family Wakeup Domain peripherals * - * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/ + * Copyright (C) 2022-2025 Texas Instruments Incorporated - https://www.ti.com/ */ +#include + &cbass_wakeup { wkup_conf: bus@43000000 { compatible = "simple-bus"; @@ -38,14 +40,34 @@ }; }; - wkup_uart0: serial@2b300000 { - compatible = "ti,am64-uart", "ti,am654-uart"; - reg = <0x00 0x2b300000 0x00 0x100>; - interrupts = ; + target-module@2b300050 { + compatible = "ti,sysc-omap2", "ti,sysc"; + reg = <0 0x2b300050 0 0x4>, + <0 0x2b300054 0 0x4>, + <0 0x2b300058 0 0x4>; + reg-names = "rev", "sysc", "syss"; + ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP | + SYSC_OMAP2_SOFTRESET | + SYSC_OMAP2_AUTOIDLE)>; + ti,sysc-sidle = , + , + , + ; + ti,syss-mask = <1>; + ti,no-reset-on-init; power-domains = <&k3_pds 114 TI_SCI_PD_EXCLUSIVE>; clocks = <&k3_clks 114 0>; - clock-names = "fclk"; - status = "disabled"; + clock-names = "fck"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0 0x2b300000 0x100000>; + + wkup_uart0: serial@0 { + compatible = "ti,am64-uart", "ti,am654-uart"; + reg = <0 0x100>; + interrupts = ; + status = "disabled"; + }; }; wkup_i2c0: i2c@2b200000 { diff --git a/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-main.dtsi index 41e1c24b1144..6e3beb5c2e01 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-main.dtsi @@ -651,6 +651,7 @@ interrupt-names = "host", "peripheral"; maximum-speed = "high-speed"; dr_mode = "otg"; + bootph-all; snps,usb2-gadget-lpm-disable; snps,usb2-lpm-disable; }; @@ -768,6 +769,7 @@ #mbox-cells = <1>; ti,mbox-num-users = <4>; ti,mbox-num-fifos = <16>; + status = "disabled"; }; mailbox0_cluster1: mailbox@29010000 { @@ -777,6 +779,7 @@ #mbox-cells = <1>; ti,mbox-num-users = <4>; ti,mbox-num-fifos = <16>; + status = "disabled"; }; mailbox0_cluster2: mailbox@29020000 { @@ -786,6 +789,7 @@ #mbox-cells = <1>; ti,mbox-num-users = <4>; ti,mbox-num-fifos = <16>; + status = "disabled"; }; mailbox0_cluster3: mailbox@29030000 { @@ -795,6 +799,7 @@ #mbox-cells = <1>; ti,mbox-num-users = <4>; ti,mbox-num-fifos = <16>; + status = "disabled"; }; ecap0: pwm@23100000 { diff --git a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts index 7f3dc39e12bc..ad71d2f27f53 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts @@ -621,6 +621,8 @@ }; &mailbox0_cluster0 { + status = "okay"; + mbox_r5_0: mbox-r5-0 { ti,mbox-rx = <0 0 0>; ti,mbox-tx = <1 0 0>; @@ -628,6 +630,8 @@ }; &mailbox0_cluster1 { + status = "okay"; + mbox_mcu_r5_0: mbox-mcu-r5-0 { ti,mbox-rx = <0 0 0>; ti,mbox-tx = <1 0 0>; diff --git a/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra.dtsi b/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra.dtsi index d364c247833f..922cad14c9f8 100644 --- a/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra.dtsi @@ -112,6 +112,25 @@ regulator-boot-on; }; + vcc_3v3_hdmi: regulator-vcc-3v3-hdmi { + compatible = "regulator-fixed"; + regulator-name = "VCC_3V3_HDMI"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_3v3_sw>; + regulator-always-on; + regulator-boot-on; + }; + + vcc_1v2_hdmi: regulator-vcc-1v2-hdmi { + compatible = "regulator-fixed"; + regulator-name = "HDMI_CVCC"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-always-on; + regulator-boot-on; + }; + vcc_3v3_mmc: regulator-vcc-3v3-mmc { compatible = "regulator-fixed"; regulator-name = "VCC_3V3_MMC"; @@ -367,6 +386,9 @@ pinctrl-names = "default"; pinctrl-0 = <&hdmi_int_pins_default>; + iovcc-supply = <&vcc_3v3_hdmi>; + cvcc12-supply = <&vcc_1v2_hdmi>; + ports { #address-cells = <1>; #size-cells = <0>; @@ -376,6 +398,7 @@ sii9022_in: endpoint { remote-endpoint = <&dpi1_out>; + bus-width = <16>; }; }; @@ -393,6 +416,7 @@ compatible = "atmel,24c02"; pagesize = <16>; reg = <0x51>; + vcc-supply = <&vcc_3v3_mmc>; }; }; diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi index 6957b3e44c82..2f129e8cd5b9 100644 --- a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi @@ -256,7 +256,7 @@ main_usb1_pins_default: main-usb1-default-pins { pinctrl-single,pins = < - AM62X_IOPAD(0x0258, PIN_OUTPUT, 0) /* (F18/E16) USB1_DRVVBUS */ + AM62X_IOPAD(0x0258, PIN_OUTPUT | PIN_DS_PULLUD_ENABLE | PIN_DS_PULL_UP, 0) /* (F18/E16) USB1_DRVVBUS */ >; }; @@ -315,6 +315,10 @@ }; }; +&cpsw_mac_syscon { + bootph-all; +}; + &wkup_uart0 { /* WKUP UART0 is used by DM firmware */ bootph-pre-ram; diff --git a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi index c66289a4362b..324eb44c258d 100644 --- a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi @@ -1227,6 +1227,15 @@ #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x00 0x30000000 0x80000>; + clocks = <&k3_clks 81 0>, /* icssg0_core_clk */ + <&k3_clks 81 3>, /* icssg0_iep_clk */ + <&k3_clks 81 16>, /* icssg0_rgmii_mhz_250_clk */ + <&k3_clks 81 17>, /* icssg0_rgmii_mhz_50_clk */ + <&k3_clks 81 18>, /* icssg0_rgmii_mhz_5_clk */ + <&k3_clks 81 19>, /* icssg0_uart_clk */ + <&k3_clks 81 20>; /* icssg0_iclk */ + assigned-clocks = <&k3_clks 81 0>; + assigned-clock-parents = <&k3_clks 81 2>; icssg0_mem: memories@0 { reg = <0x0 0x2000>, @@ -1252,7 +1261,7 @@ clocks = <&k3_clks 81 0>, /* icssg0_core_clk */ <&k3_clks 81 20>; /* icssg0_iclk */ assigned-clocks = <&icssg0_coreclk_mux>; - assigned-clock-parents = <&k3_clks 81 20>; + assigned-clock-parents = <&k3_clks 81 0>; }; icssg0_iepclk_mux: iepclk-mux@30 { @@ -1397,6 +1406,15 @@ #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x00 0x30080000 0x80000>; + clocks = <&k3_clks 82 0>, /* icssg1_core_clk */ + <&k3_clks 82 3>, /* icssg1_iep_clk */ + <&k3_clks 82 16>, /* icssg1_rgmii_mhz_250_clk */ + <&k3_clks 82 17>, /* icssg1_rgmii_mhz_50_clk */ + <&k3_clks 82 18>, /* icssg1_rgmii_mhz_5_clk */ + <&k3_clks 82 19>, /* icssg1_uart_clk */ + <&k3_clks 82 20>; /* icssg1_iclk */ + assigned-clocks = <&k3_clks 82 0>; + assigned-clock-parents = <&k3_clks 82 2>; icssg1_mem: memories@0 { reg = <0x0 0x2000>, @@ -1422,7 +1440,7 @@ clocks = <&k3_clks 82 0>, /* icssg1_core_clk */ <&k3_clks 82 20>; /* icssg1_iclk */ assigned-clocks = <&icssg1_coreclk_mux>; - assigned-clock-parents = <&k3_clks 82 20>; + assigned-clock-parents = <&k3_clks 82 0>; }; icssg1_iepclk_mux: iepclk-mux@30 { diff --git a/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-pcie.dtso b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-pcie.dts similarity index 78% rename from arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-pcie.dtso rename to arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-pcie.dts index bd9a5caf20da..023b2a6aaa56 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-pcie.dtso +++ b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-pcie.dts @@ -2,17 +2,19 @@ /* * Copyright (C) 2023 Josua Mayer * - * Overlay for SolidRun AM642 HummingBoard-T to enable PCI-E. + * DTS for SolidRun AM642 HummingBoard-T, + * running on Cortex A53, with PCI-E. + * */ -/dts-v1/; -/plugin/; - -#include -#include +#include "k3-am642-hummingboard-t.dts" #include "k3-serdes.h" +/ { + model = "SolidRun AM642 HummingBoard-T with PCI-E"; +}; + &pcie0_rc { pinctrl-names = "default"; pinctrl-0 = <&pcie0_default_pins>; diff --git a/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-usb3.dtso b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-usb3.dts similarity index 74% rename from arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-usb3.dtso rename to arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-usb3.dts index ffcc3bd3c7bc..ee9bd618f370 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-usb3.dtso +++ b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-usb3.dts @@ -2,16 +2,19 @@ /* * Copyright (C) 2023 Josua Mayer * - * Overlay for SolidRun AM642 HummingBoard-T to enable USB-3.1. + * DTS for SolidRun AM642 HummingBoard-T, + * running on Cortex A53, with USB-3.1 Gen 1. + * */ -/dts-v1/; -/plugin/; - -#include +#include "k3-am642-hummingboard-t.dts" #include "k3-serdes.h" +/ { + model = "SolidRun AM642 HummingBoard-T with USB-3.1 Gen 1"; +}; + &serdes0 { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts index e06a3b178b34..8f64d6272b1b 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts +++ b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts @@ -201,8 +201,6 @@ reset-gpios = <&main_gpio0 44 GPIO_ACTIVE_LOW>; reset-assert-us = <1000>; reset-deassert-us = <1000>; - ti,rx-fifo-depth = ; - ti,tx-fifo-depth = ; ti,rx-internal-delay = ; ti,clk-output-sel = ; }; @@ -230,8 +228,6 @@ reset-gpios = <&main_gpio1 47 GPIO_ACTIVE_LOW>; reset-assert-us = <1000>; reset-deassert-us = <1000>; - ti,rx-fifo-depth = ; - ti,tx-fifo-depth = ; ti,rx-internal-delay = ; ti,clk-output-sel = ; }; @@ -242,8 +238,6 @@ reset-gpios = <&main_gpio1 51 GPIO_ACTIVE_LOW>; reset-assert-us = <1000>; reset-deassert-us = <1000>; - ti,rx-fifo-depth = ; - ti,tx-fifo-depth = ; ti,rx-internal-delay = ; ti,clk-output-sel = ; }; diff --git a/arch/arm64/boot/dts/ti/k3-am67a-beagley-ai.dts b/arch/arm64/boot/dts/ti/k3-am67a-beagley-ai.dts index 44dfbdf89277..9be6bba28c26 100644 --- a/arch/arm64/boot/dts/ti/k3-am67a-beagley-ai.dts +++ b/arch/arm64/boot/dts/ti/k3-am67a-beagley-ai.dts @@ -50,11 +50,71 @@ no-map; }; + wkup_r5fss0_core0_dma_memory_region: r5f-dma-memory@a0000000 { + compatible = "shared-dma-pool"; + reg = <0x00 0xa0000000 0x00 0x100000>; + no-map; + }; + wkup_r5fss0_core0_memory_region: r5f-memory@a0100000 { compatible = "shared-dma-pool"; reg = <0x00 0xa0100000 0x00 0xf00000>; no-map; }; + + mcu_r5fss0_core0_dma_memory_region: mcu-r5fss-dma-memory-region@a1000000 { + compatible = "shared-dma-pool"; + reg = <0x00 0xa1000000 0x00 0x100000>; + no-map; + }; + + mcu_r5fss0_core0_memory_region: mcu-r5fss-memory-region@a1100000 { + compatible = "shared-dma-pool"; + reg = <0x00 0xa1100000 0x00 0xf00000>; + no-map; + }; + + main_r5fss0_core0_dma_memory_region: main-r5fss-dma-memory-region@a2000000 { + compatible = "shared-dma-pool"; + reg = <0x00 0xa2000000 0x00 0x100000>; + no-map; + }; + + main_r5fss0_core0_memory_region: main-r5fss-memory-region@a2100000 { + compatible = "shared-dma-pool"; + reg = <0x00 0xa2100000 0x00 0xf00000>; + no-map; + }; + + c7x_0_dma_memory_region: c7x-dma-memory@a3000000 { + compatible = "shared-dma-pool"; + reg = <0x00 0xa3000000 0x00 0x100000>; + no-map; + }; + + c7x_0_memory_region: c7x-memory@a3100000 { + compatible = "shared-dma-pool"; + reg = <0x00 0xa3100000 0x00 0xf00000>; + no-map; + }; + + c7x_1_dma_memory_region: c7x-dma-memory@a4000000 { + compatible = "shared-dma-pool"; + reg = <0x00 0xa4000000 0x00 0x100000>; + no-map; + }; + + c7x_1_memory_region: c7x-memory@a4100000 { + compatible = "shared-dma-pool"; + reg = <0x00 0xa4100000 0x00 0xf00000>; + no-map; + }; + + rtos_ipc_memory_region: ipc-memories@a5000000 { + reg = <0x00 0xa5000000 0x00 0x1c00000>; + alignment = <0x1000>; + no-map; + }; }; vsys_5v0: regulator-1 { @@ -391,3 +451,101 @@ ti,fails-without-test-cd; status = "okay"; }; + +&mailbox0_cluster0 { + status = "okay"; + + mbox_wkup_r5_0: mbox-wkup-r5-0 { + ti,mbox-rx = <0 0 0>; + ti,mbox-tx = <1 0 0>; + }; +}; + +&mailbox0_cluster1 { + status = "okay"; + + mbox_mcu_r5_0: mbox-mcu-r5-0 { + ti,mbox-rx = <0 0 0>; + ti,mbox-tx = <1 0 0>; + }; +}; + +&mailbox0_cluster2 { + status = "okay"; + + mbox_c7x_0: mbox-c7x-0 { + ti,mbox-rx = <0 0 0>; + ti,mbox-tx = <1 0 0>; + }; +}; + +&mailbox0_cluster3 { + status = "okay"; + + mbox_main_r5_0: mbox-main-r5-0 { + ti,mbox-rx = <0 0 0>; + ti,mbox-tx = <1 0 0>; + }; + + mbox_c7x_1: mbox-c7x-1 { + ti,mbox-rx = <2 0 0>; + ti,mbox-tx = <3 0 0>; + }; +}; + +/* Timers are used by Remoteproc firmware */ +&main_timer0 { + status = "reserved"; +}; + +&main_timer1 { + status = "reserved"; +}; + +&main_timer2 { + status = "reserved"; +}; + +&wkup_r5fss0 { + status = "okay"; +}; + +&wkup_r5fss0_core0 { + mboxes = <&mailbox0_cluster0 &mbox_wkup_r5_0>; + memory-region = <&wkup_r5fss0_core0_dma_memory_region>, + <&wkup_r5fss0_core0_memory_region>; +}; + +&mcu_r5fss0 { + status = "okay"; +}; + +&mcu_r5fss0_core0 { + mboxes = <&mailbox0_cluster1 &mbox_mcu_r5_0>; + memory-region = <&mcu_r5fss0_core0_dma_memory_region>, + <&mcu_r5fss0_core0_memory_region>; +}; + +&main_r5fss0 { + status = "okay"; +}; + +&main_r5fss0_core0 { + mboxes = <&mailbox0_cluster3 &mbox_main_r5_0>; + memory-region = <&main_r5fss0_core0_dma_memory_region>, + <&main_r5fss0_core0_memory_region>; +}; + +&c7x_0 { + mboxes = <&mailbox0_cluster2 &mbox_c7x_0>; + memory-region = <&c7x_0_dma_memory_region>, + <&c7x_0_memory_region>; + status = "okay"; +}; + +&c7x_1 { + mboxes = <&mailbox0_cluster3 &mbox_c7x_1>; + memory-region = <&c7x_1_dma_memory_region>, + <&c7x_1_memory_region>; + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/ti/k3-am68-sk-base-board-pcie1-ep.dtso b/arch/arm64/boot/dts/ti/k3-am68-sk-base-board-pcie1-ep.dtso new file mode 100644 index 000000000000..455736e378cc --- /dev/null +++ b/arch/arm64/boot/dts/ti/k3-am68-sk-base-board-pcie1-ep.dtso @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/** + * DT Overlay for enabling PCIE1 instance in Endpoint Configuration with the + * AM68-SK board. + * + * AM68-SK Board Product Link: https://www.ti.com/tool/SK-AM68 + * + * Copyright (C) 2024 Texas Instruments Incorporated - https://www.ti.com/ + */ + +/dts-v1/; +/plugin/; + +#include +#include + +#include "k3-pinctrl.h" + +/* + * Since Root Complex and Endpoint modes are mutually exclusive + * disable Root Complex mode. + */ +&pcie1_rc { + status = "disabled"; +}; + +&cbass_main { + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&gic500>; + + pcie1_ep: pcie-ep@2910000 { + compatible = "ti,j7200-pcie-ep", "ti,j721e-pcie-ep"; + reg = <0x00 0x02910000 0x00 0x1000>, + <0x00 0x02917000 0x00 0x400>, + <0x00 0x0d800000 0x00 0x00800000>, + <0x00 0x18000000 0x00 0x08000000>; + reg-names = "intd_cfg", "user_cfg", "reg", "mem"; + interrupt-names = "link_state"; + interrupts = ; + max-link-speed = <3>; + num-lanes = <2>; + power-domains = <&k3_pds 276 TI_SCI_PD_EXCLUSIVE>; + clocks = <&k3_clks 276 41>; + clock-names = "fck"; + max-functions = /bits/ 8 <6>; + max-virtual-functions = /bits/ 8 <4 4 4 4 0 0>; + dma-coherent; + phys = <&serdes0_pcie_link>; + phy-names = "pcie-phy"; + ti,syscon-pcie-ctrl = <&scm_conf 0x074>; + }; +}; diff --git a/arch/arm64/boot/dts/ti/k3-am69-sk-pcie0-ep.dtso b/arch/arm64/boot/dts/ti/k3-am69-sk-pcie0-ep.dtso new file mode 100644 index 000000000000..9a5bcf282a9e --- /dev/null +++ b/arch/arm64/boot/dts/ti/k3-am69-sk-pcie0-ep.dtso @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/** + * DT Overlay for enabling PCIE0 instances of PCIe in Endpoint Configuration + * on AM69-SK. + * + * AM69-SK Product Link: https://www.ti.com/tool/SK-AM69 + * + * Copyright (C) 2024 Texas Instruments Incorporated - https://www.ti.com/ + */ + +/dts-v1/; +/plugin/; + +#include +#include + +#include "k3-pinctrl.h" + +/* + * Since Root Complex and Endpoint modes are mutually exclusive + * disable Root Complex mode. + */ +&pcie0_rc { + status = "disabled"; +}; + +&cbass_main { + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&gic500>; + + pcie0_ep: pcie-ep@2900000 { + compatible = "ti,j784s4-pcie-ep"; + reg = <0x00 0x02900000 0x00 0x1000>, + <0x00 0x02907000 0x00 0x400>, + <0x00 0x0d000000 0x00 0x00800000>, + <0x00 0x10000000 0x00 0x08000000>; + reg-names = "intd_cfg", "user_cfg", "reg", "mem"; + interrupt-names = "link_state"; + interrupts = ; + max-link-speed = <3>; + num-lanes = <4>; + power-domains = <&k3_pds 332 TI_SCI_PD_EXCLUSIVE>; + clocks = <&k3_clks 332 0>; + clock-names = "fck"; + max-functions = /bits/ 8 <6>; + max-virtual-functions = /bits/ 8 <4 4 4 4 0 0>; + dma-coherent; + phys = <&serdes1_pcie_link>; + phy-names = "pcie-phy"; + ti,syscon-pcie-ctrl = <&pcie0_ctrl 0x0>; + }; +}; diff --git a/arch/arm64/boot/dts/ti/k3-am69-sk.dts b/arch/arm64/boot/dts/ti/k3-am69-sk.dts index 1e36965a1403..b85227052f97 100644 --- a/arch/arm64/boot/dts/ti/k3-am69-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am69-sk.dts @@ -484,6 +484,12 @@ >; }; + main_usbss0_pins_default: main-usbss0-default-pins { + pinctrl-single,pins = < + J784S4_IOPAD(0x0ec, PIN_OUTPUT, 6) /* (AN37) TIMER_IO1.USB0_DRVVBUS */ + >; + }; + }; &wkup_pmx0 { @@ -755,6 +761,7 @@ regulator-max-microvolt = <1100000>; regulator-boot-on; regulator-always-on; + bootph-all; }; bucka3: buck3 { @@ -763,6 +770,7 @@ regulator-max-microvolt = <850000>; regulator-boot-on; regulator-always-on; + bootph-all; }; bucka4: buck4 { @@ -771,6 +779,7 @@ regulator-max-microvolt = <1800000>; regulator-boot-on; regulator-always-on; + bootph-all; }; bucka5: buck5 { @@ -779,6 +788,7 @@ regulator-max-microvolt = <850000>; regulator-boot-on; regulator-always-on; + bootph-all; }; ldoa1: ldo1 { @@ -787,6 +797,7 @@ regulator-max-microvolt = <1800000>; regulator-boot-on; regulator-always-on; + bootph-all; }; ldoa2: ldo2 { @@ -795,6 +806,7 @@ regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; + bootph-all; }; ldoa3: ldo3 { @@ -803,6 +815,7 @@ regulator-max-microvolt = <800000>; regulator-boot-on; regulator-always-on; + bootph-all; }; ldoa4: ldo4 { @@ -811,6 +824,7 @@ regulator-max-microvolt = <1800000>; regulator-boot-on; regulator-always-on; + bootph-all; }; }; }; @@ -1299,6 +1313,14 @@ cdns,phy-type = ; resets = <&serdes_wiz0 1>, <&serdes_wiz0 2>, <&serdes_wiz0 3>; }; + + serdes0_usb_link: phy@3 { + reg = <3>; + cdns,num-lanes = <1>; + #phy-cells = <0>; + cdns,phy-type = ; + resets = <&serdes_wiz0 4>; + }; }; &serdes_wiz1 { @@ -1339,3 +1361,22 @@ phy-names = "pcie-phy"; num-lanes = <1>; }; + +&usb_serdes_mux { + idle-states = <0>; /* USB0 to SERDES0 */ +}; + +&usbss0 { + status = "okay"; + pinctrl-0 = <&main_usbss0_pins_default>; + pinctrl-names = "default"; + ti,vbus-divider; +}; + +&usb0 { + status = "okay"; + dr_mode = "otg"; + maximum-speed = "super-speed"; + phys = <&serdes0_usb_link>; + phy-names = "cdns3,usb3-phy"; +}; diff --git a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts index db43e7e10b76..f684ce6ad9ad 100644 --- a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts @@ -409,6 +409,10 @@ , ; }; +&mcu_spi1 { + mux-controls = <&spi1_linkdis 0>; +}; + &usb_serdes_mux { idle-states = <1>; /* USB0 to SERDES lane 3 */ bootph-all; diff --git a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi index 6a8453865874..56ab144fea07 100644 --- a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi @@ -184,6 +184,13 @@ reg = <0x4040 0x4>; #phy-cells = <1>; }; + + spi1_linkdis: mux-controller@4060 { + compatible = "reg-mux"; + reg = <0x4060 0x4>; + #mux-control-cells = <1>; + mux-reg-masks = <0x0 0x1>; + }; }; wkup_conf: bus@43000000 { diff --git a/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie1-ep.dtso b/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie1-ep.dtso new file mode 100644 index 000000000000..a8cccdcf3e3b --- /dev/null +++ b/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie1-ep.dtso @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/** + * DT Overlay for enabling PCIE1 instance in Endpoint Configuration with the + * J7 common processor board. + * + * J7 Common Processor Board Product Link: https://www.ti.com/tool/J721EXCPXEVM + * + * Copyright (C) 2024 Texas Instruments Incorporated - https://www.ti.com/ + */ + +/dts-v1/; +/plugin/; + +#include +#include + +#include "k3-pinctrl.h" + +/* + * Since Root Complex and Endpoint modes are mutually exclusive + * disable Root Complex mode. + */ +&pcie1_rc { + status = "disabled"; +}; + +&cbass_main { + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&gic500>; + + pcie1_ep: pcie-ep@2910000 { + compatible = "ti,j721e-pcie-ep"; + reg = <0x00 0x02910000 0x00 0x1000>, + <0x00 0x02917000 0x00 0x400>, + <0x00 0x0d800000 0x00 0x00800000>, + <0x00 0x18000000 0x00 0x08000000>; + reg-names = "intd_cfg", "user_cfg", "reg", "mem"; + interrupt-names = "link_state"; + interrupts = ; + max-link-speed = <3>; + num-lanes = <2>; + power-domains = <&k3_pds 240 TI_SCI_PD_EXCLUSIVE>; + clocks = <&k3_clks 240 1>; + clock-names = "fck"; + max-functions = /bits/ 8 <6>; + max-virtual-functions = /bits/ 8 <4 4 4 4 0 0>; + dma-coherent; + phys = <&serdes1_pcie_link>; + phy-names = "pcie-phy"; + ti,syscon-pcie-ctrl = <&scm_conf 0x4074>; + }; +}; diff --git a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts index a00f4a7d20d9..d184e9c1a0a5 100644 --- a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts +++ b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts @@ -359,6 +359,13 @@ J722S_IOPAD(0x00a0, PIN_OUTPUT, 1) /* (N24) GPMC0_WPn.AUDIO_EXT_REFCLK1 */ >; }; + + pmic_irq_pins_default: pmic-irq-default-pins { + pinctrl-single,pins = < + J722S_IOPAD(0x030, PIN_INPUT, 7) /* (K23) GPIO0_12 */ + >; + }; + }; &cpsw3g { @@ -406,6 +413,13 @@ &mcu_pmx0 { + mcu_i2c0_pins_default: mcu-i2c0-default-pins { + pinctrl-single,pins = < + J722S_MCU_IOPAD(0x048, PIN_INPUT, 0) /* (E11) MCU_I2C0_SDA */ + J722S_MCU_IOPAD(0x044, PIN_INPUT, 0) /* (B13) MCU_I2C0_SCL */ + >; + }; + mcu_mcan0_pins_default: mcu-mcan0-default-pins { pinctrl-single,pins = < J722S_MCU_IOPAD(0x038, PIN_INPUT, 0) /* (D8) MCU_MCAN0_RX */ @@ -459,6 +473,87 @@ clock-frequency = <400000>; status = "okay"; bootph-all; + + tps65224: pmic@48 { + compatible = "ti,tps65224-q1"; + reg = <0x48>; + pinctrl-names = "default"; + pinctrl-0 = <&pmic_irq_pins_default>; + interrupt-parent = <&main_gpio0>; + interrupts = <0 IRQ_TYPE_EDGE_FALLING>; + ti,primary-pmic; + + gpio-controller; + #gpio-cells = <2>; + + buck12-supply = <&vsys_io_3v3>; + buck3-supply = <&vsys_io_3v3>; + buck4-supply = <&vsys_io_3v3>; + + ldo1-supply = <&vsys_io_3v3>; + ldo2-supply = <&vsys_io_3v3>; + ldo3-supply = <&vsys_io_3v3>; + + regulators { + + buck1: buck1 { + regulator-name = "vcc1v8_io_buck1"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + bootph-all; + }; + + buck2: buck2 { + regulator-name = "vcc1v1_ddr_buck2"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + regulator-boot-on; + regulator-always-on; + }; + + buck3: buck3 { + regulator-name = "vcc0v85_ram_buck3"; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <850000>; + regulator-boot-on; + regulator-always-on; + }; + + buck4: buck4 { + regulator-name = "vcc0v75_ioret_buck4"; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <750000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo1: ldo1 { + regulator-name = "vdda1v8_pll_ldo1"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo2: ldo2 { + regulator-name = "dvdd3v3_ldo2"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo3: ldo3 { + regulator-name = "vdd1v85_phy_ldo3"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + }; + }; + }; }; &k3_clks { @@ -812,3 +907,10 @@ &mcu_gpio0 { status = "okay"; }; + +&mcu_i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&mcu_i2c0_pins_default>; + clock-frequency = <400000>; + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-evm-common.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-evm-common.dtsi index b2e2b9f507a9..2664f74a9c7a 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-evm-common.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-evm-common.dtsi @@ -635,6 +635,7 @@ regulator-max-microvolt = <1100000>; regulator-boot-on; regulator-always-on; + bootph-all; }; bucka3: buck3 { @@ -643,6 +644,7 @@ regulator-max-microvolt = <850000>; regulator-boot-on; regulator-always-on; + bootph-all; }; bucka4: buck4 { @@ -651,6 +653,7 @@ regulator-max-microvolt = <1800000>; regulator-boot-on; regulator-always-on; + bootph-all; }; bucka5: buck5 { @@ -659,6 +662,7 @@ regulator-max-microvolt = <850000>; regulator-boot-on; regulator-always-on; + bootph-all; }; ldoa1: ldo1 { @@ -667,6 +671,7 @@ regulator-max-microvolt = <1800000>; regulator-boot-on; regulator-always-on; + bootph-all; }; ldoa2: ldo2 { @@ -675,6 +680,7 @@ regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; + bootph-all; }; ldoa3: ldo3 { @@ -683,6 +689,7 @@ regulator-max-microvolt = <800000>; regulator-boot-on; regulator-always-on; + bootph-all; }; ldoa4: ldo4 { @@ -691,6 +698,7 @@ regulator-max-microvolt = <1800000>; regulator-boot-on; regulator-always-on; + bootph-all; }; }; }; diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi index 7721852c1f68..83bbf94b58d1 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi @@ -224,7 +224,7 @@ }; main_pmx0: pinctrl@11c000 { - compatible = "pinctrl-single"; + compatible = "ti,j7200-padconf", "pinctrl-single"; /* Proxy 0 addressing */ reg = <0x00 0x11c000 0x00 0x120>; #pinctrl-cells = <1>; @@ -234,7 +234,7 @@ /* TIMERIO pad input CTRLMMR_TIMER*_CTRL registers */ main_timerio_input: pinctrl@104200 { - compatible = "pinctrl-single"; + compatible = "ti,j7200-padconf", "pinctrl-single"; reg = <0x00 0x104200 0x00 0x50>; #pinctrl-cells = <1>; pinctrl-single,register-width = <32>; @@ -243,7 +243,7 @@ /* TIMERIO pad output CTCTRLMMR_TIMERIO*_CTRL registers */ main_timerio_output: pinctrl@104280 { - compatible = "pinctrl-single"; + compatible = "ti,j7200-padconf", "pinctrl-single"; reg = <0x00 0x104280 0x00 0x20>; #pinctrl-cells = <1>; pinctrl-single,register-width = <32>; @@ -2040,7 +2040,7 @@ #address-cells = <1>; #size-cells = <0>; power-domains = <&k3_pds 376 TI_SCI_PD_EXCLUSIVE>; - clocks = <&k3_clks 376 1>; + clocks = <&k3_clks 376 0>; status = "disabled"; }; @@ -2051,7 +2051,7 @@ #address-cells = <1>; #size-cells = <0>; power-domains = <&k3_pds 377 TI_SCI_PD_EXCLUSIVE>; - clocks = <&k3_clks 377 1>; + clocks = <&k3_clks 377 0>; status = "disabled"; }; @@ -2062,7 +2062,7 @@ #address-cells = <1>; #size-cells = <0>; power-domains = <&k3_pds 378 TI_SCI_PD_EXCLUSIVE>; - clocks = <&k3_clks 378 1>; + clocks = <&k3_clks 378 0>; status = "disabled"; }; @@ -2073,7 +2073,7 @@ #address-cells = <1>; #size-cells = <0>; power-domains = <&k3_pds 379 TI_SCI_PD_EXCLUSIVE>; - clocks = <&k3_clks 379 1>; + clocks = <&k3_clks 379 0>; status = "disabled"; }; @@ -2084,7 +2084,7 @@ #address-cells = <1>; #size-cells = <0>; power-domains = <&k3_pds 380 TI_SCI_PD_EXCLUSIVE>; - clocks = <&k3_clks 380 1>; + clocks = <&k3_clks 380 0>; status = "disabled"; }; @@ -2095,7 +2095,7 @@ #address-cells = <1>; #size-cells = <0>; power-domains = <&k3_pds 381 TI_SCI_PD_EXCLUSIVE>; - clocks = <&k3_clks 381 1>; + clocks = <&k3_clks 381 0>; status = "disabled"; }; @@ -2106,7 +2106,7 @@ #address-cells = <1>; #size-cells = <0>; power-domains = <&k3_pds 382 TI_SCI_PD_EXCLUSIVE>; - clocks = <&k3_clks 382 1>; + clocks = <&k3_clks 382 0>; status = "disabled"; }; @@ -2117,7 +2117,7 @@ #address-cells = <1>; #size-cells = <0>; power-domains = <&k3_pds 383 TI_SCI_PD_EXCLUSIVE>; - clocks = <&k3_clks 383 1>; + clocks = <&k3_clks 383 0>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-mcu-wakeup-common.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-mcu-wakeup-common.dtsi index 9638130caece..52e2965a3bf5 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-mcu-wakeup-common.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-mcu-wakeup-common.dtsi @@ -76,7 +76,7 @@ }; wkup_pmx0: pinctrl@4301c000 { - compatible = "pinctrl-single"; + compatible = "ti,j7200-padconf", "pinctrl-single"; /* Proxy 0 addressing */ reg = <0x00 0x4301c000 0x00 0x034>; #pinctrl-cells = <1>; @@ -85,7 +85,7 @@ }; wkup_pmx1: pinctrl@4301c038 { - compatible = "pinctrl-single"; + compatible = "ti,j7200-padconf", "pinctrl-single"; /* Proxy 0 addressing */ reg = <0x00 0x4301c038 0x00 0x02c>; #pinctrl-cells = <1>; @@ -94,7 +94,7 @@ }; wkup_pmx2: pinctrl@4301c068 { - compatible = "pinctrl-single"; + compatible = "ti,j7200-padconf", "pinctrl-single"; /* Proxy 0 addressing */ reg = <0x00 0x4301c068 0x00 0x120>; #pinctrl-cells = <1>; @@ -103,7 +103,7 @@ }; wkup_pmx3: pinctrl@4301c190 { - compatible = "pinctrl-single"; + compatible = "ti,j7200-padconf", "pinctrl-single"; /* Proxy 0 addressing */ reg = <0x00 0x4301c190 0x00 0x004>; #pinctrl-cells = <1>; @@ -125,7 +125,7 @@ /* MCU_TIMERIO pad input CTRLMMR_MCU_TIMER*_CTRL registers */ mcu_timerio_input: pinctrl@40f04200 { - compatible = "pinctrl-single"; + compatible = "ti,j7200-padconf", "pinctrl-single"; reg = <0x00 0x40f04200 0x00 0x28>; #pinctrl-cells = <1>; pinctrl-single,register-width = <32>; @@ -136,7 +136,7 @@ /* MCU_TIMERIO pad output CTRLMMR_MCU_TIMERIO*_CTRL registers */ mcu_timerio_output: pinctrl@40f04280 { - compatible = "pinctrl-single"; + compatible = "ti,j7200-padconf", "pinctrl-single"; reg = <0x00 0x40f04280 0x00 0x28>; #pinctrl-cells = <1>; pinctrl-single,register-width = <32>; diff --git a/arch/arm64/boot/dts/ti/k3-pinctrl.h b/arch/arm64/boot/dts/ti/k3-pinctrl.h index 22b8d73cfd32..cac7cccc1112 100644 --- a/arch/arm64/boot/dts/ti/k3-pinctrl.h +++ b/arch/arm64/boot/dts/ti/k3-pinctrl.h @@ -12,6 +12,12 @@ #define PULLTYPESEL_SHIFT (17) #define RXACTIVE_SHIFT (18) #define DEBOUNCE_SHIFT (11) +#define FORCE_DS_EN_SHIFT (15) +#define DS_EN_SHIFT (24) +#define DS_OUT_DIS_SHIFT (25) +#define DS_OUT_VAL_SHIFT (26) +#define DS_PULLUD_EN_SHIFT (27) +#define DS_PULLTYPE_SEL_SHIFT (28) #define PULL_DISABLE (1 << PULLUDEN_SHIFT) #define PULL_ENABLE (0 << PULLUDEN_SHIFT) @@ -38,6 +44,19 @@ #define PIN_DEBOUNCE_CONF5 (5 << DEBOUNCE_SHIFT) #define PIN_DEBOUNCE_CONF6 (6 << DEBOUNCE_SHIFT) +#define PIN_DS_FORCE_DISABLE (0 << FORCE_DS_EN_SHIFT) +#define PIN_DS_FORCE_ENABLE (1 << FORCE_DS_EN_SHIFT) +#define PIN_DS_IO_OVERRIDE_DISABLE (0 << DS_IO_OVERRIDE_EN_SHIFT) +#define PIN_DS_IO_OVERRIDE_ENABLE (1 << DS_IO_OVERRIDE_EN_SHIFT) +#define PIN_DS_OUT_ENABLE (0 << DS_OUT_DIS_SHIFT) +#define PIN_DS_OUT_DISABLE (1 << DS_OUT_DIS_SHIFT) +#define PIN_DS_OUT_VALUE_ZERO (0 << DS_OUT_VAL_SHIFT) +#define PIN_DS_OUT_VALUE_ONE (1 << DS_OUT_VAL_SHIFT) +#define PIN_DS_PULLUD_ENABLE (0 << DS_PULLUD_EN_SHIFT) +#define PIN_DS_PULLUD_DISABLE (1 << DS_PULLUD_EN_SHIFT) +#define PIN_DS_PULL_DOWN (0 << DS_PULLTYPE_SEL_SHIFT) +#define PIN_DS_PULL_UP (1 << DS_PULLTYPE_SEL_SHIFT) + /* Default mux configuration for gpio-ranges to use with pinctrl */ #define PIN_GPIO_RANGE_IOPAD (PIN_INPUT | 7) diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index c62831e61586..cb7da4415599 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -44,6 +44,7 @@ CONFIG_ARCH_BCM_IPROC=y CONFIG_ARCH_BCMBCA=y CONFIG_ARCH_BRCMSTB=y CONFIG_ARCH_BERLIN=y +CONFIG_ARCH_BLAIZE=y CONFIG_ARCH_EXYNOS=y CONFIG_ARCH_SPARX5=y CONFIG_ARCH_K3=y @@ -200,6 +201,7 @@ CONFIG_CFG80211=m CONFIG_MAC80211=m CONFIG_MAC80211_LEDS=y CONFIG_RFKILL=m +CONFIG_RFKILL_GPIO=m CONFIG_NET_9P=y CONFIG_NET_9P_VIRTIO=y CONFIG_NFC=m @@ -330,6 +332,7 @@ CONFIG_VIRTIO_NET=y CONFIG_MHI_NET=m CONFIG_NET_DSA_BCM_SF2=m CONFIG_NET_DSA_MSCC_FELIX=m +CONFIG_ENA_ETHERNET=m CONFIG_AMD_XGBE=y CONFIG_NET_XGENE=y CONFIG_ATL1C=m @@ -358,6 +361,8 @@ CONFIG_IGBVF=y CONFIG_MVNETA=y CONFIG_MVPP2=y CONFIG_SKY2=y +CONFIG_NET_VENDOR_MEDIATEK=y +CONFIG_NET_MEDIATEK_STAR_EMAC=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y @@ -373,6 +378,7 @@ CONFIG_SMSC911X=y CONFIG_SNI_AVE=y CONFIG_SNI_NETSEC=y CONFIG_STMMAC_ETH=m +CONFIG_DWMAC_MEDIATEK=m CONFIG_DWMAC_TEGRA=m CONFIG_TI_K3_AM65_CPSW_NUSS=y CONFIG_TI_ICSSG_PRUETH=m @@ -516,6 +522,7 @@ CONFIG_TCG_TIS_I2C_INFINEON=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MUX=y CONFIG_I2C_MUX_PCA954x=y +CONFIG_I2C_MUX_PINCTRL=m CONFIG_I2C_BCM2835=m CONFIG_I2C_CADENCE=m CONFIG_I2C_DESIGNWARE_CORE=y @@ -607,6 +614,8 @@ CONFIG_PINCTRL_MSM8996=y CONFIG_PINCTRL_MSM8998=y CONFIG_PINCTRL_QCM2290=y CONFIG_PINCTRL_QCS404=y +CONFIG_PINCTRL_QCS615=y +CONFIG_PINCTRL_QCS8300=y CONFIG_PINCTRL_QDF2XXX=y CONFIG_PINCTRL_QDU1000=y CONFIG_PINCTRL_SA8775P=y @@ -629,6 +638,7 @@ CONFIG_PINCTRL_SM8350=y CONFIG_PINCTRL_SM8450=y CONFIG_PINCTRL_SM8550=y CONFIG_PINCTRL_SM8650=y +CONFIG_PINCTRL_SM8750=y CONFIG_PINCTRL_X1E80100=y CONFIG_PINCTRL_QCOM_SPMI_PMIC=y CONFIG_PINCTRL_LPASS_LPI=m @@ -737,6 +747,7 @@ CONFIG_MESON_WATCHDOG=m CONFIG_ARM_SMC_WATCHDOG=y CONFIG_RENESAS_WDT=y CONFIG_RENESAS_RZG2LWDT=y +CONFIG_RENESAS_RZV2HWDT=y CONFIG_UNIPHIER_WATCHDOG=y CONFIG_PM8916_WATCHDOG=m CONFIG_BCM2835_WDT=y @@ -872,6 +883,7 @@ CONFIG_ROCKCHIP_VOP2=y CONFIG_ROCKCHIP_ANALOGIX_DP=y CONFIG_ROCKCHIP_CDN_DP=y CONFIG_ROCKCHIP_DW_HDMI=y +CONFIG_ROCKCHIP_DW_HDMI_QP=y CONFIG_ROCKCHIP_DW_MIPI_DSI=y CONFIG_ROCKCHIP_INNO_HDMI=y CONFIG_ROCKCHIP_LVDS=y @@ -900,6 +912,7 @@ CONFIG_DRM_PANEL_SITRONIX_ST7703=m CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA=m CONFIG_DRM_PANEL_VISIONOX_VTDR6130=m CONFIG_DRM_FSL_LDB=m +CONFIG_DRM_ITE_IT6263=m CONFIG_DRM_LONTIUM_LT8912B=m CONFIG_DRM_LONTIUM_LT9611=m CONFIG_DRM_LONTIUM_LT9611UXC=m @@ -965,6 +978,8 @@ CONFIG_SND_SOC_IMX_AUDMIX=m CONFIG_SND_SOC_MT8183=m CONFIG_SND_SOC_MT8183_MT6358_TS3A227E_MAX98357A=m CONFIG_SND_SOC_MT8183_DA7219_MAX98357A=m +CONFIG_SND_SOC_MT8188=m +CONFIG_SND_SOC_MT8188_MT6359=m CONFIG_SND_SOC_MT8192=m CONFIG_SND_SOC_MT8192_MT6359_RT1015_RT5682=m CONFIG_SND_SOC_MT8195=m @@ -993,6 +1008,7 @@ CONFIG_SND_SOC_RZ=m CONFIG_SND_SOC_SOF_TOPLEVEL=y CONFIG_SND_SOC_SOF_OF=y CONFIG_SND_SOC_SOF_MTK_TOPLEVEL=y +CONFIG_SND_SOC_SOF_MT8186=m CONFIG_SND_SOC_SOF_MT8195=m CONFIG_SND_SUN8I_CODEC=m CONFIG_SND_SUN8I_CODEC_ANALOG=m @@ -1120,6 +1136,7 @@ CONFIG_USB_MASS_STORAGE=m CONFIG_TYPEC=m CONFIG_TYPEC_TCPM=m CONFIG_TYPEC_TCPCI=m +CONFIG_TYPEC_TCPCI_MAXIM=m CONFIG_TYPEC_FUSB302=m CONFIG_TYPEC_QCOM_PMIC=m CONFIG_TYPEC_UCSI=m @@ -1310,6 +1327,7 @@ CONFIG_QCOM_CLK_SMD_RPM=y CONFIG_QCOM_CLK_RPMH=y CONFIG_IPQ_APSS_6018=y CONFIG_IPQ_APSS_5018=y +CONFIG_IPQ_CMN_PLL=m CONFIG_IPQ_GCC_5018=y CONFIG_IPQ_GCC_5332=y CONFIG_IPQ_GCC_6018=y @@ -1325,11 +1343,15 @@ CONFIG_MSM_MMCC_8998=m CONFIG_QCM_GCC_2290=y CONFIG_QCM_DISPCC_2290=m CONFIG_QCS_GCC_404=y +CONFIG_QCS_GCC_615=y +CONFIG_QCS_GCC_8300=y CONFIG_SC_CAMCC_7280=m +CONFIG_SA_CAMCC_8775P=m CONFIG_QDU_GCC_1000=y CONFIG_SC_CAMCC_8280XP=m CONFIG_SC_DISPCC_7280=m CONFIG_SC_DISPCC_8280XP=m +CONFIG_SA_DISPCC_8775P=m CONFIG_SA_GCC_8775P=y CONFIG_SA_GPUCC_8775P=m CONFIG_SC_GCC_7180=y @@ -1352,13 +1374,14 @@ CONFIG_SM_DISPCC_6115=m CONFIG_SM_DISPCC_8250=y CONFIG_SM_DISPCC_8450=m CONFIG_SM_DISPCC_8550=m -CONFIG_SM_DISPCC_8650=m +CONFIG_SM_DISPCC_8750=m CONFIG_SM_GCC_4450=y CONFIG_SM_GCC_6115=y CONFIG_SM_GCC_8350=y CONFIG_SM_GCC_8450=y CONFIG_SM_GCC_8550=y CONFIG_SM_GCC_8650=y +CONFIG_SM_GCC_8750=y CONFIG_SM_GPUCC_6115=m CONFIG_SM_GPUCC_8150=y CONFIG_SM_GPUCC_8250=y @@ -1368,6 +1391,8 @@ CONFIG_SM_GPUCC_8550=m CONFIG_SM_GPUCC_8650=m CONFIG_SM_TCSRCC_8550=y CONFIG_SM_TCSRCC_8650=y +CONFIG_SM_TCSRCC_8750=m +CONFIG_SA_VIDEOCC_8775P=m CONFIG_SM_VIDEOCC_8250=y CONFIG_QCOM_HFPLL=y CONFIG_CLK_GFM_LPASS_SM8250=m @@ -1400,6 +1425,7 @@ CONFIG_QCOM_Q6V5_PAS=m CONFIG_QCOM_SYSMON=m CONFIG_QCOM_WCNSS_PIL=m CONFIG_TI_K3_DSP_REMOTEPROC=m +CONFIG_TI_K3_M4_REMOTEPROC=m CONFIG_TI_K3_R5_REMOTEPROC=m CONFIG_RPMSG_CHAR=m CONFIG_RPMSG_CTRL=m @@ -1456,6 +1482,7 @@ CONFIG_ARCH_R9A07G044=y CONFIG_ARCH_R9A07G054=y CONFIG_ARCH_R9A08G045=y CONFIG_ARCH_R9A09G011=y +CONFIG_ARCH_R9A09G047=y CONFIG_ARCH_R9A09G057=y CONFIG_ROCKCHIP_IODOMAIN=y CONFIG_ARCH_TEGRA_132_SOC=y @@ -1632,6 +1659,8 @@ CONFIG_INTERCONNECT_QCOM_MSM8996=y CONFIG_INTERCONNECT_QCOM_OSM_L3=m CONFIG_INTERCONNECT_QCOM_QCM2290=y CONFIG_INTERCONNECT_QCOM_QCS404=m +CONFIG_INTERCONNECT_QCOM_QCS615=y +CONFIG_INTERCONNECT_QCOM_QCS8300=y CONFIG_INTERCONNECT_QCOM_QDU1000=y CONFIG_INTERCONNECT_QCOM_SA8775P=y CONFIG_INTERCONNECT_QCOM_SC7180=y @@ -1647,6 +1676,7 @@ CONFIG_INTERCONNECT_QCOM_SM8350=y CONFIG_INTERCONNECT_QCOM_SM8450=y CONFIG_INTERCONNECT_QCOM_SM8550=y CONFIG_INTERCONNECT_QCOM_SM8650=y +CONFIG_INTERCONNECT_QCOM_SM8750=y CONFIG_INTERCONNECT_QCOM_X1E80100=y CONFIG_COUNTER=m CONFIG_RZ_MTU3_CNT=m @@ -1698,7 +1728,6 @@ CONFIG_CRYPTO_SM3_ARM64_CE=m CONFIG_CRYPTO_AES_ARM64_CE_BLK=y CONFIG_CRYPTO_AES_ARM64_BS=m CONFIG_CRYPTO_AES_ARM64_CE_CCM=y -CONFIG_CRYPTO_CRCT10DIF_ARM64_CE=m CONFIG_CRYPTO_DEV_SUN8I_CE=m CONFIG_CRYPTO_DEV_FSL_CAAM=m CONFIG_CRYPTO_DEV_FSL_DPAA2_CAAM=m diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig index e7d9bd8e4709..5636ab83f22a 100644 --- a/arch/arm64/crypto/Kconfig +++ b/arch/arm64/crypto/Kconfig @@ -312,15 +312,5 @@ config CRYPTO_SM4_ARM64_CE_GCM - PMULL (Polynomial Multiply Long) instructions - NEON (Advanced SIMD) extensions -config CRYPTO_CRCT10DIF_ARM64_CE - tristate "CRCT10DIF (PMULL)" - depends on KERNEL_MODE_NEON && CRC_T10DIF - select CRYPTO_HASH - help - CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF) - - Architecture: arm64 using - - PMULL (Polynomial Multiply Long) instructions - endmenu diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index fbe64dce66e0..e7139c4768ce 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -44,9 +44,6 @@ ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o obj-$(CONFIG_CRYPTO_POLYVAL_ARM64_CE) += polyval-ce.o polyval-ce-y := polyval-ce-glue.o polyval-ce-core.o -obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM64_CE) += crct10dif-ce.o -crct10dif-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o - obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o aes-ce-cipher-y := aes-ce-core.o aes-ce-glue.o diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c deleted file mode 100644 index 08bcbd884395..000000000000 --- a/arch/arm64/crypto/crct10dif-ce-glue.c +++ /dev/null @@ -1,132 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions - * - * Copyright (C) 2016 - 2017 Linaro Ltd - */ - -#include -#include -#include -#include -#include -#include - -#include -#include - -#include -#include - -#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U - -asmlinkage void crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len, - u8 out[16]); -asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len); - -static int crct10dif_init(struct shash_desc *desc) -{ - u16 *crc = shash_desc_ctx(desc); - - *crc = 0; - return 0; -} - -static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - u16 *crcp = shash_desc_ctx(desc); - u16 crc = *crcp; - u8 buf[16]; - - if (length > CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) { - kernel_neon_begin(); - crc_t10dif_pmull_p8(crc, data, length, buf); - kernel_neon_end(); - - crc = 0; - data = buf; - length = sizeof(buf); - } - - *crcp = crc_t10dif_generic(crc, data, length); - return 0; -} - -static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - u16 *crc = shash_desc_ctx(desc); - - if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) { - kernel_neon_begin(); - *crc = crc_t10dif_pmull_p64(*crc, data, length); - kernel_neon_end(); - } else { - *crc = crc_t10dif_generic(*crc, data, length); - } - - return 0; -} - -static int crct10dif_final(struct shash_desc *desc, u8 *out) -{ - u16 *crc = shash_desc_ctx(desc); - - *(u16 *)out = *crc; - return 0; -} - -static struct shash_alg crc_t10dif_alg[] = {{ - .digestsize = CRC_T10DIF_DIGEST_SIZE, - .init = crct10dif_init, - .update = crct10dif_update_pmull_p8, - .final = crct10dif_final, - .descsize = CRC_T10DIF_DIGEST_SIZE, - - .base.cra_name = "crct10dif", - .base.cra_driver_name = "crct10dif-arm64-neon", - .base.cra_priority = 150, - .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE, - .base.cra_module = THIS_MODULE, -}, { - .digestsize = CRC_T10DIF_DIGEST_SIZE, - .init = crct10dif_init, - .update = crct10dif_update_pmull_p64, - .final = crct10dif_final, - .descsize = CRC_T10DIF_DIGEST_SIZE, - - .base.cra_name = "crct10dif", - .base.cra_driver_name = "crct10dif-arm64-ce", - .base.cra_priority = 200, - .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE, - .base.cra_module = THIS_MODULE, -}}; - -static int __init crc_t10dif_mod_init(void) -{ - if (cpu_have_named_feature(PMULL)) - return crypto_register_shashes(crc_t10dif_alg, - ARRAY_SIZE(crc_t10dif_alg)); - else - /* only register the first array element */ - return crypto_register_shash(crc_t10dif_alg); -} - -static void __exit crc_t10dif_mod_exit(void) -{ - if (cpu_have_named_feature(PMULL)) - crypto_unregister_shashes(crc_t10dif_alg, - ARRAY_SIZE(crc_t10dif_alg)); - else - crypto_unregister_shash(crc_t10dif_alg); -} - -module_cpu_feature_match(ASIMD, crc_t10dif_mod_init); -module_exit(crc_t10dif_mod_exit); - -MODULE_AUTHOR("Ard Biesheuvel "); -MODULE_DESCRIPTION("CRC-T10DIF using arm64 NEON and Crypto Extensions"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_CRYPTO("crct10dif"); -MODULE_ALIAS_CRYPTO("crct10dif-arm64-ce"); diff --git a/arch/arm64/hyperv/hv_core.c b/arch/arm64/hyperv/hv_core.c index f1ebc025e1df..69004f619c57 100644 --- a/arch/arm64/hyperv/hv_core.c +++ b/arch/arm64/hyperv/hv_core.c @@ -11,11 +11,10 @@ #include #include #include -#include #include #include #include -#include +#include #include /* diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c index b1a4de4eee29..fc49949b7df6 100644 --- a/arch/arm64/hyperv/mshyperv.c +++ b/arch/arm64/hyperv/mshyperv.c @@ -49,12 +49,12 @@ static int __init hyperv_init(void) hv_set_vpreg(HV_REGISTER_GUEST_OS_ID, guest_id); /* Get the features and hints from Hyper-V */ - hv_get_vpreg_128(HV_REGISTER_FEATURES, &result); + hv_get_vpreg_128(HV_REGISTER_PRIVILEGES_AND_FEATURES_INFO, &result); ms_hyperv.features = result.as32.a; ms_hyperv.priv_high = result.as32.b; ms_hyperv.misc_features = result.as32.c; - hv_get_vpreg_128(HV_REGISTER_ENLIGHTENMENTS, &result); + hv_get_vpreg_128(HV_REGISTER_FEATURES_INFO, &result); ms_hyperv.hints = result.as32.a; pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n", diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 4e350df9a02d..d2ff8f6c3231 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -8,6 +8,7 @@ syscall-y += unistd_32.h syscall-y += unistd_compat_32.h generic-y += early_ioremap.h +generic-y += fprobe.h generic-y += mcs_spinlock.h generic-y += mmzone.h generic-y += qrwlock.h diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 3d8d534a7a77..ad63457a05c5 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -343,6 +343,11 @@ alternative_cb_end // Narrow PARange to fit the PS field in TCR_ELx ubfx \tmp0, \tmp0, #ID_AA64MMFR0_EL1_PARANGE_SHIFT, #3 mov \tmp1, #ID_AA64MMFR0_EL1_PARANGE_MAX +#ifdef CONFIG_ARM64_LPA2 +alternative_if_not ARM64_HAS_VA52 + mov \tmp1, #ID_AA64MMFR0_EL1_PARANGE_48 +alternative_else_nop_endif +#endif cmp \tmp0, \tmp1 csel \tmp0, \tmp1, \tmp0, hi bfi \tcr, \tmp0, \pos, #3 diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index cbbf70e0f204..0b5ca6e0eb09 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -46,6 +46,8 @@ cpucap_is_possible(const unsigned int cap) return IS_ENABLED(CONFIG_ARM64_POE); case ARM64_HAS_GCS: return IS_ENABLED(CONFIG_ARM64_GCS); + case ARM64_HAFT: + return IS_ENABLED(CONFIG_ARM64_HAFT); case ARM64_UNMAP_KERNEL_AT_EL0: return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0); case ARM64_WORKAROUND_843419: diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 8b4e5a3cd24c..e0e4478f5fb5 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -671,6 +671,7 @@ static inline bool supports_clearbhb(int scope) } const struct cpumask *system_32bit_el0_cpumask(void); +const struct cpumask *fallback_32bit_el0_cpumask(void); DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); static inline bool system_supports_32bit_el0(void) @@ -852,8 +853,7 @@ static inline bool system_supports_gcs(void) static inline bool system_supports_haft(void) { - return IS_ENABLED(CONFIG_ARM64_HAFT) && - cpus_have_final_cap(ARM64_HAFT); + return cpus_have_final_cap(ARM64_HAFT); } static __always_inline bool system_supports_mpam(void) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 488f8e751349..6f3f4142e214 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -122,6 +122,7 @@ #define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 #define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804 #define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 +#define QCOM_CPU_PART_ORYON_X1 0x001 #define NVIDIA_CPU_PART_DENVER 0x003 #define NVIDIA_CPU_PART_CARMEL 0x004 @@ -198,6 +199,7 @@ #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD) #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER) +#define MIDR_QCOM_ORYON_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_ORYON_X1) #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER) #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 4ef52d7245bb..25e162651750 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -154,7 +154,7 @@ /* Coprocessor traps */ .macro __init_el2_cptr __check_hvhe .LnVHE_\@, x1 - mov x0, #CPACR_ELx_FPEN + mov x0, #CPACR_EL1_FPEN msr cpacr_el1, x0 b .Lskip_set_cptr_\@ .LnVHE_\@: @@ -332,7 +332,7 @@ // (h)VHE case mrs x0, cpacr_el1 // Disable SVE traps - orr x0, x0, #CPACR_ELx_ZEN + orr x0, x0, #CPACR_EL1_ZEN msr cpacr_el1, x0 b .Lskip_set_cptr_\@ @@ -353,7 +353,7 @@ // (h)VHE case mrs x0, cpacr_el1 // Disable SME traps - orr x0, x0, #CPACR_ELx_SMEN + orr x0, x0, #CPACR_EL1_SMEN msr cpacr_el1, x0 b .Lskip_set_cptr_sme_\@ diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 5ccff4de7f09..bfe3ce9df197 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -52,6 +52,8 @@ extern unsigned long ftrace_graph_call; extern void return_to_handler(void); unsigned long ftrace_call_adjust(unsigned long addr); +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip); +#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS #define HAVE_ARCH_FTRACE_REGS @@ -129,6 +131,38 @@ ftrace_override_function_with_return(struct ftrace_regs *fregs) arch_ftrace_regs(fregs)->pc = arch_ftrace_regs(fregs)->lr; } +static __always_inline unsigned long +ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->fp; +} + +static __always_inline unsigned long +ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->lr; +} + +static __always_inline struct pt_regs * +ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs) +{ + struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs); + + memcpy(regs->regs, afregs->regs, sizeof(afregs->regs)); + regs->sp = afregs->sp; + regs->pc = afregs->pc; + regs->regs[29] = afregs->fp; + regs->regs[30] = afregs->lr; + return regs; +} + +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->pc = arch_ftrace_regs(fregs)->pc; \ + (_regs)->regs[29] = arch_ftrace_regs(fregs)->fp; \ + (_regs)->sp = arch_ftrace_regs(fregs)->sp; \ + (_regs)->pstate = PSR_MODE_EL1h; \ + } while (0) + int ftrace_regs_query_register_offset(const char *name); int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); @@ -186,23 +220,6 @@ static inline bool arch_syscall_match_sym_name(const char *sym, #ifndef __ASSEMBLY__ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - /* x0 - x7 */ - unsigned long regs[8]; - - unsigned long fp; - unsigned long __unused; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->regs[0]; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->fp; -} void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer); diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 2b6c61c608e2..1c3f9617d54f 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -93,6 +93,21 @@ #define KERNEL_HWCAP_PACA __khwcap_feature(PACA) #define KERNEL_HWCAP_PACG __khwcap_feature(PACG) #define KERNEL_HWCAP_GCS __khwcap_feature(GCS) +#define KERNEL_HWCAP_CMPBR __khwcap_feature(CMPBR) +#define KERNEL_HWCAP_FPRCVT __khwcap_feature(FPRCVT) +#define KERNEL_HWCAP_F8MM8 __khwcap_feature(F8MM8) +#define KERNEL_HWCAP_F8MM4 __khwcap_feature(F8MM4) +#define KERNEL_HWCAP_SVE_F16MM __khwcap_feature(SVE_F16MM) +#define KERNEL_HWCAP_SVE_ELTPERM __khwcap_feature(SVE_ELTPERM) +#define KERNEL_HWCAP_SVE_AES2 __khwcap_feature(SVE_AES2) +#define KERNEL_HWCAP_SVE_BFSCALE __khwcap_feature(SVE_BFSCALE) +#define KERNEL_HWCAP_SVE2P2 __khwcap_feature(SVE2P2) +#define KERNEL_HWCAP_SME2P2 __khwcap_feature(SME2P2) +#define KERNEL_HWCAP_SME_SBITPERM __khwcap_feature(SME_SBITPERM) +#define KERNEL_HWCAP_SME_AES __khwcap_feature(SME_AES) +#define KERNEL_HWCAP_SME_SFEXPA __khwcap_feature(SME_SFEXPA) +#define KERNEL_HWCAP_SME_STMOP __khwcap_feature(SME_STMOP) +#define KERNEL_HWCAP_SME_SMOP4 __khwcap_feature(SME_SMOP4) #define __khwcap2_feature(x) (const_ilog2(HWCAP2_ ## x) + 64) #define KERNEL_HWCAP_DCPODP __khwcap2_feature(DCPODP) diff --git a/arch/arm64/include/asm/hyperv-tlfs.h b/arch/arm64/include/asm/hyperv-tlfs.h deleted file mode 100644 index bc30aadedfe9..000000000000 --- a/arch/arm64/include/asm/hyperv-tlfs.h +++ /dev/null @@ -1,71 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* - * This file contains definitions from the Hyper-V Hypervisor Top-Level - * Functional Specification (TLFS): - * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs - * - * Copyright (C) 2021, Microsoft, Inc. - * - * Author : Michael Kelley - */ - -#ifndef _ASM_HYPERV_TLFS_H -#define _ASM_HYPERV_TLFS_H - -#include - -/* - * All data structures defined in the TLFS that are shared between Hyper-V - * and a guest VM use Little Endian byte ordering. This matches the default - * byte ordering of Linux running on ARM64, so no special handling is required. - */ - -/* - * Group C Features. See the asm-generic version of hyperv-tlfs.h - * for a description of Feature Groups. - */ - -/* Crash MSRs available */ -#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(8) - -/* STIMER direct mode is available */ -#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(13) - -/* - * To support arch-generic code calling hv_set/get_register: - * - On x86, HV_MSR_ indicates an MSR accessed via rdmsrl/wrmsrl - * - On ARM, HV_MSR_ indicates a VP register accessed via hypercall - */ -#define HV_MSR_CRASH_P0 (HV_REGISTER_GUEST_CRASH_P0) -#define HV_MSR_CRASH_P1 (HV_REGISTER_GUEST_CRASH_P1) -#define HV_MSR_CRASH_P2 (HV_REGISTER_GUEST_CRASH_P2) -#define HV_MSR_CRASH_P3 (HV_REGISTER_GUEST_CRASH_P3) -#define HV_MSR_CRASH_P4 (HV_REGISTER_GUEST_CRASH_P4) -#define HV_MSR_CRASH_CTL (HV_REGISTER_GUEST_CRASH_CTL) - -#define HV_MSR_VP_INDEX (HV_REGISTER_VP_INDEX) -#define HV_MSR_TIME_REF_COUNT (HV_REGISTER_TIME_REF_COUNT) -#define HV_MSR_REFERENCE_TSC (HV_REGISTER_REFERENCE_TSC) - -#define HV_MSR_SINT0 (HV_REGISTER_SINT0) -#define HV_MSR_SCONTROL (HV_REGISTER_SCONTROL) -#define HV_MSR_SIEFP (HV_REGISTER_SIEFP) -#define HV_MSR_SIMP (HV_REGISTER_SIMP) -#define HV_MSR_EOM (HV_REGISTER_EOM) - -#define HV_MSR_STIMER0_CONFIG (HV_REGISTER_STIMER0_CONFIG) -#define HV_MSR_STIMER0_COUNT (HV_REGISTER_STIMER0_COUNT) - -union hv_msi_entry { - u64 as_uint64[2]; - struct { - u64 address; - u32 data; - u32 reserved; - } __packed; -}; - -#include - -#endif diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 3e0f0de1d2da..8d94a6c0ed5c 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -300,7 +300,7 @@ #define CPTR_EL2_TSM (1 << 12) #define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) #define CPTR_EL2_TZ (1 << 8) -#define CPTR_NVHE_EL2_RES1 0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */ +#define CPTR_NVHE_EL2_RES1 (BIT(13) | BIT(9) | GENMASK(7, 0)) #define CPTR_NVHE_EL2_RES0 (GENMASK(63, 32) | \ GENMASK(29, 21) | \ GENMASK(19, 14) | \ @@ -391,8 +391,6 @@ ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ ECN(BKPT32), ECN(VECTOR32), ECN(BRK64), ECN(ERET) -#define CPACR_EL1_TTA (1 << 28) - #define kvm_mode_names \ { PSR_MODE_EL0t, "EL0t" }, \ { PSR_MODE_EL1t, "EL1t" }, \ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index ca2590344313..bec227f9500a 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -53,8 +53,7 @@ enum __kvm_host_smccc_func { /* Hypercalls available only prior to pKVM finalisation */ /* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */ - __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1, - __KVM_HOST_SMCCC_FUNC___pkvm_init, + __KVM_HOST_SMCCC_FUNC___pkvm_init = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1, __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping, __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector, __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs, @@ -65,6 +64,12 @@ enum __kvm_host_smccc_func { /* Hypercalls available after pKVM finalisation */ __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp, __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp, + __KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest, + __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest, + __KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest, + __KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest, + __KVM_HOST_SMCCC_FUNC___pkvm_host_test_clear_young_guest, + __KVM_HOST_SMCCC_FUNC___pkvm_host_mkyoung_guest, __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc, __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run, __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context, @@ -79,6 +84,9 @@ enum __kvm_host_smccc_func { __KVM_HOST_SMCCC_FUNC___pkvm_init_vm, __KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu, __KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm, + __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load, + __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put, + __KVM_HOST_SMCCC_FUNC___pkvm_tlb_flush_vmid, }; #define DECLARE_KVM_VHE_SYM(sym) extern char sym[] @@ -247,8 +255,6 @@ extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu); extern u64 __vgic_v3_get_gic_config(void); extern void __vgic_v3_init_lrs(void); -extern u64 __kvm_get_mdcr_el2(void); - #define __KVM_EXTABLE(from, to) \ " .pushsection __kvm_ex_table, \"a\"\n" \ " .align 3\n" \ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index cf811009a33c..47f2cf408eed 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -184,29 +184,30 @@ static inline bool vcpu_is_el2(const struct kvm_vcpu *vcpu) return vcpu_is_el2_ctxt(&vcpu->arch.ctxt); } -static inline bool __vcpu_el2_e2h_is_set(const struct kvm_cpu_context *ctxt) -{ - return (!cpus_have_final_cap(ARM64_HAS_HCR_NV1) || - (ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H)); -} - static inline bool vcpu_el2_e2h_is_set(const struct kvm_vcpu *vcpu) { - return __vcpu_el2_e2h_is_set(&vcpu->arch.ctxt); -} - -static inline bool __vcpu_el2_tge_is_set(const struct kvm_cpu_context *ctxt) -{ - return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_TGE; + return (!cpus_have_final_cap(ARM64_HAS_HCR_NV1) || + (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_E2H)); } static inline bool vcpu_el2_tge_is_set(const struct kvm_vcpu *vcpu) { - return __vcpu_el2_tge_is_set(&vcpu->arch.ctxt); + return ctxt_sys_reg(&vcpu->arch.ctxt, HCR_EL2) & HCR_TGE; } -static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt) +static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu) { + bool e2h, tge; + u64 hcr; + + if (!vcpu_has_nv(vcpu)) + return false; + + hcr = __vcpu_sys_reg(vcpu, HCR_EL2); + + e2h = (hcr & HCR_E2H); + tge = (hcr & HCR_TGE); + /* * We are in a hypervisor context if the vcpu mode is EL2 or * E2H and TGE bits are set. The latter means we are in the user space @@ -215,14 +216,7 @@ static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt) * Note that the HCR_EL2.{E2H,TGE}={0,1} isn't really handled in the * rest of the KVM code, and will result in a misbehaving guest. */ - return vcpu_is_el2_ctxt(ctxt) || - (__vcpu_el2_e2h_is_set(ctxt) && __vcpu_el2_tge_is_set(ctxt)) || - __vcpu_el2_tge_is_set(ctxt); -} - -static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu) -{ - return vcpu_has_nv(vcpu) && __is_hyp_ctxt(&vcpu->arch.ctxt); + return vcpu_is_el2(vcpu) || (e2h && tge) || tge; } static inline bool vcpu_is_host_el0(const struct kvm_vcpu *vcpu) @@ -556,13 +550,13 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) ({ \ u64 cptr = 0; \ \ - if ((set) & CPACR_ELx_FPEN) \ + if ((set) & CPACR_EL1_FPEN) \ cptr |= CPTR_EL2_TFP; \ - if ((set) & CPACR_ELx_ZEN) \ + if ((set) & CPACR_EL1_ZEN) \ cptr |= CPTR_EL2_TZ; \ - if ((set) & CPACR_ELx_SMEN) \ + if ((set) & CPACR_EL1_SMEN) \ cptr |= CPTR_EL2_TSM; \ - if ((clr) & CPACR_ELx_TTA) \ + if ((clr) & CPACR_EL1_TTA) \ cptr |= CPTR_EL2_TTA; \ if ((clr) & CPTR_EL2_TAM) \ cptr |= CPTR_EL2_TAM; \ @@ -576,13 +570,13 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) ({ \ u64 cptr = 0; \ \ - if ((clr) & CPACR_ELx_FPEN) \ + if ((clr) & CPACR_EL1_FPEN) \ cptr |= CPTR_EL2_TFP; \ - if ((clr) & CPACR_ELx_ZEN) \ + if ((clr) & CPACR_EL1_ZEN) \ cptr |= CPTR_EL2_TZ; \ - if ((clr) & CPACR_ELx_SMEN) \ + if ((clr) & CPACR_EL1_SMEN) \ cptr |= CPTR_EL2_TSM; \ - if ((set) & CPACR_ELx_TTA) \ + if ((set) & CPACR_EL1_TTA) \ cptr |= CPTR_EL2_TTA; \ if ((set) & CPTR_EL2_TAM) \ cptr |= CPTR_EL2_TAM; \ @@ -595,13 +589,13 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) #define cpacr_clear_set(clr, set) \ do { \ BUILD_BUG_ON((set) & CPTR_VHE_EL2_RES0); \ - BUILD_BUG_ON((clr) & CPACR_ELx_E0POE); \ - __build_check_all_or_none((clr), CPACR_ELx_FPEN); \ - __build_check_all_or_none((set), CPACR_ELx_FPEN); \ - __build_check_all_or_none((clr), CPACR_ELx_ZEN); \ - __build_check_all_or_none((set), CPACR_ELx_ZEN); \ - __build_check_all_or_none((clr), CPACR_ELx_SMEN); \ - __build_check_all_or_none((set), CPACR_ELx_SMEN); \ + BUILD_BUG_ON((clr) & CPACR_EL1_E0POE); \ + __build_check_all_or_none((clr), CPACR_EL1_FPEN); \ + __build_check_all_or_none((set), CPACR_EL1_FPEN); \ + __build_check_all_or_none((clr), CPACR_EL1_ZEN); \ + __build_check_all_or_none((set), CPACR_EL1_ZEN); \ + __build_check_all_or_none((clr), CPACR_EL1_SMEN); \ + __build_check_all_or_none((set), CPACR_EL1_SMEN); \ \ if (has_vhe() || has_hvhe()) \ sysreg_clear_set(cpacr_el1, clr, set); \ @@ -619,40 +613,40 @@ static __always_inline void kvm_write_cptr_el2(u64 val) write_sysreg(val, cptr_el2); } -static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu) +/* Resets the value of cptr_el2 when returning to the host. */ +static __always_inline void __kvm_reset_cptr_el2(struct kvm *kvm) { u64 val; if (has_vhe()) { - val = (CPACR_ELx_FPEN | CPACR_EL1_ZEN_EL1EN); + val = (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN); if (cpus_have_final_cap(ARM64_SME)) val |= CPACR_EL1_SMEN_EL1EN; } else if (has_hvhe()) { - val = CPACR_ELx_FPEN; + val = CPACR_EL1_FPEN; - if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs()) - val |= CPACR_ELx_ZEN; + if (!kvm_has_sve(kvm) || !guest_owns_fp_regs()) + val |= CPACR_EL1_ZEN; if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_ELx_SMEN; + val |= CPACR_EL1_SMEN; } else { val = CPTR_NVHE_EL2_RES1; - if (vcpu_has_sve(vcpu) && guest_owns_fp_regs()) + if (kvm_has_sve(kvm) && guest_owns_fp_regs()) val |= CPTR_EL2_TZ; - if (cpus_have_final_cap(ARM64_SME)) - val &= ~CPTR_EL2_TSM; + if (!cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM; } - return val; -} - -static __always_inline void kvm_reset_cptr_el2(struct kvm_vcpu *vcpu) -{ - u64 val = kvm_get_reset_cptr_el2(vcpu); - kvm_write_cptr_el2(val); } +#ifdef __KVM_NVHE_HYPERVISOR__ +#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2(kern_hyp_va((v)->kvm)) +#else +#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2((v)->kvm) +#endif + /* * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE * format if E2H isn't set. @@ -685,7 +679,7 @@ static inline bool ____cptr_xen_trap_enabled(const struct kvm_vcpu *vcpu, #define __guest_hyp_cptr_xen_trap_enabled(vcpu, xen) \ (!vcpu_has_nv(vcpu) ? false : \ ____cptr_xen_trap_enabled(vcpu, \ - SYS_FIELD_GET(CPACR_ELx, xen, \ + SYS_FIELD_GET(CPACR_EL1, xen, \ vcpu_sanitised_cptr_el2(vcpu)))) static inline bool guest_hyp_fpsimd_traps_enabled(const struct kvm_vcpu *vcpu) @@ -697,9 +691,4 @@ static inline bool guest_hyp_sve_traps_enabled(const struct kvm_vcpu *vcpu) { return __guest_hyp_cptr_xen_trap_enabled(vcpu, ZEN); } - -static inline void kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) -{ - vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH); -} #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index e18e9244d17a..7cfa024de4e3 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -85,6 +85,7 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu); struct kvm_hyp_memcache { phys_addr_t head; unsigned long nr_pages; + struct pkvm_mapping *mapping; /* only used from EL1 */ }; static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc, @@ -331,6 +332,8 @@ struct kvm_arch { #define KVM_ARCH_FLAG_ID_REGS_INITIALIZED 7 /* Fine-Grained UNDEF initialised */ #define KVM_ARCH_FLAG_FGU_INITIALIZED 8 + /* SVE exposed to guest */ +#define KVM_ARCH_FLAG_GUEST_HAS_SVE 9 unsigned long flags; /* VM-wide vCPU feature set */ @@ -490,7 +493,6 @@ enum vcpu_sysreg { VBAR_EL2, /* Vector Base Address Register (EL2) */ RVBAR_EL2, /* Reset Vector Base Address Register */ CONTEXTIDR_EL2, /* Context ID Register (EL2) */ - CNTHCTL_EL2, /* Counter-timer Hypervisor Control register */ SP_EL2, /* EL2 Stack Pointer */ CNTHP_CTL_EL2, CNTHP_CVAL_EL2, @@ -501,6 +503,7 @@ enum vcpu_sysreg { MARKER(__SANITISED_REG_START__), TCR2_EL2, /* Extended Translation Control Register (EL2) */ MDCR_EL2, /* Monitor Debug Configuration Register (EL2) */ + CNTHCTL_EL2, /* Counter-timer Hypervisor Control register */ /* Any VNCR-capable reg goes after this point */ MARKER(__VNCR_START__), @@ -610,6 +613,14 @@ struct cpu_sve_state { * field. */ struct kvm_host_data { +#define KVM_HOST_DATA_FLAG_HAS_SPE 0 +#define KVM_HOST_DATA_FLAG_HAS_TRBE 1 +#define KVM_HOST_DATA_FLAG_HOST_SVE_ENABLED 2 +#define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED 3 +#define KVM_HOST_DATA_FLAG_TRBE_ENABLED 4 +#define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED 5 + unsigned long flags; + struct kvm_cpu_context host_ctxt; /* @@ -642,7 +653,7 @@ struct kvm_host_data { * host_debug_state contains the host registers which are * saved and restored during world switches. */ - struct { + struct { /* {Break,watch}point registers */ struct kvm_guest_debug_arch regs; /* Statistical profiling extension */ @@ -652,6 +663,16 @@ struct kvm_host_data { /* Values of trap registers for the host before guest entry. */ u64 mdcr_el2; } host_debug_state; + + /* Guest trace filter value */ + u64 trfcr_while_in_guest; + + /* Number of programmable event counters (PMCR_EL0.N) for this CPU */ + unsigned int nr_event_counters; + + /* Number of debug breakpoints/watchpoints for this CPU (minus 1) */ + unsigned int debug_brps; + unsigned int debug_wrps; }; struct kvm_host_psci_config { @@ -708,7 +729,6 @@ struct kvm_vcpu_arch { u64 hcr_el2; u64 hcrx_el2; u64 mdcr_el2; - u64 cptr_el2; /* Exception Information */ struct kvm_vcpu_fault_info fault; @@ -739,31 +759,22 @@ struct kvm_vcpu_arch { * * external_debug_state contains the debug values we want to debug the * guest. This is set via the KVM_SET_GUEST_DEBUG ioctl. - * - * debug_ptr points to the set of debug registers that should be loaded - * onto the hardware when running the guest. */ - struct kvm_guest_debug_arch *debug_ptr; struct kvm_guest_debug_arch vcpu_debug_state; struct kvm_guest_debug_arch external_debug_state; + u64 external_mdscr_el1; + + enum { + VCPU_DEBUG_FREE, + VCPU_DEBUG_HOST_OWNED, + VCPU_DEBUG_GUEST_OWNED, + } debug_owner; /* VGIC state */ struct vgic_cpu vgic_cpu; struct arch_timer_cpu timer_cpu; struct kvm_pmu pmu; - /* - * Guest registers we preserve during guest debugging. - * - * These shadow registers are updated by the kvm_handle_sys_reg - * trap handler if the guest accesses or updates them while we - * are using guest debug. - */ - struct { - u32 mdscr_el1; - bool pstate_ss; - } guest_debug_preserved; - /* vcpu power state */ struct kvm_mp_state mp_state; spinlock_t mp_state_lock; @@ -771,6 +782,9 @@ struct kvm_vcpu_arch { /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; + /* Pages to top-up the pKVM/EL2 guest pool */ + struct kvm_hyp_memcache pkvm_memcache; + /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; @@ -863,14 +877,10 @@ struct kvm_vcpu_arch { #define vcpu_set_flag(v, ...) __vcpu_set_flag((v), __VA_ARGS__) #define vcpu_clear_flag(v, ...) __vcpu_clear_flag((v), __VA_ARGS__) -/* SVE exposed to guest */ -#define GUEST_HAS_SVE __vcpu_single_flag(cflags, BIT(0)) +/* KVM_ARM_VCPU_INIT completed */ +#define VCPU_INITIALIZED __vcpu_single_flag(cflags, BIT(0)) /* SVE config completed */ #define VCPU_SVE_FINALIZED __vcpu_single_flag(cflags, BIT(1)) -/* PTRAUTH exposed to guest */ -#define GUEST_HAS_PTRAUTH __vcpu_single_flag(cflags, BIT(2)) -/* KVM_ARM_VCPU_INIT completed */ -#define VCPU_INITIALIZED __vcpu_single_flag(cflags, BIT(3)) /* Exception pending */ #define PENDING_EXCEPTION __vcpu_single_flag(iflags, BIT(0)) @@ -906,29 +916,21 @@ struct kvm_vcpu_arch { #define EXCEPT_AA64_EL2_IRQ __vcpu_except_flags(5) #define EXCEPT_AA64_EL2_FIQ __vcpu_except_flags(6) #define EXCEPT_AA64_EL2_SERR __vcpu_except_flags(7) -/* Guest debug is live */ -#define DEBUG_DIRTY __vcpu_single_flag(iflags, BIT(4)) -/* Save SPE context if active */ -#define DEBUG_STATE_SAVE_SPE __vcpu_single_flag(iflags, BIT(5)) -/* Save TRBE context if active */ -#define DEBUG_STATE_SAVE_TRBE __vcpu_single_flag(iflags, BIT(6)) -/* SVE enabled for host EL0 */ -#define HOST_SVE_ENABLED __vcpu_single_flag(sflags, BIT(0)) -/* SME enabled for EL0 */ -#define HOST_SME_ENABLED __vcpu_single_flag(sflags, BIT(1)) /* Physical CPU not in supported_cpus */ -#define ON_UNSUPPORTED_CPU __vcpu_single_flag(sflags, BIT(2)) +#define ON_UNSUPPORTED_CPU __vcpu_single_flag(sflags, BIT(0)) /* WFIT instruction trapped */ -#define IN_WFIT __vcpu_single_flag(sflags, BIT(3)) +#define IN_WFIT __vcpu_single_flag(sflags, BIT(1)) /* vcpu system registers loaded on physical CPU */ -#define SYSREGS_ON_CPU __vcpu_single_flag(sflags, BIT(4)) -/* Software step state is Active-pending */ -#define DBG_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(5)) +#define SYSREGS_ON_CPU __vcpu_single_flag(sflags, BIT(2)) +/* Software step state is Active-pending for external debug */ +#define HOST_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(3)) +/* Software step state is Active pending for guest debug */ +#define GUEST_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(4)) /* PMUSERENR for the guest EL0 is on physical CPU */ -#define PMUSERENR_ON_CPU __vcpu_single_flag(sflags, BIT(6)) +#define PMUSERENR_ON_CPU __vcpu_single_flag(sflags, BIT(5)) /* WFI instruction trapped */ -#define IN_WFI __vcpu_single_flag(sflags, BIT(7)) +#define IN_WFI __vcpu_single_flag(sflags, BIT(6)) /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ @@ -959,14 +961,21 @@ struct kvm_vcpu_arch { KVM_GUESTDBG_USE_HW | \ KVM_GUESTDBG_SINGLESTEP) -#define vcpu_has_sve(vcpu) (system_supports_sve() && \ - vcpu_get_flag(vcpu, GUEST_HAS_SVE)) +#define kvm_has_sve(kvm) (system_supports_sve() && \ + test_bit(KVM_ARCH_FLAG_GUEST_HAS_SVE, &(kvm)->arch.flags)) + +#ifdef __KVM_NVHE_HYPERVISOR__ +#define vcpu_has_sve(vcpu) kvm_has_sve(kern_hyp_va((vcpu)->kvm)) +#else +#define vcpu_has_sve(vcpu) kvm_has_sve((vcpu)->kvm) +#endif #ifdef CONFIG_ARM64_PTR_AUTH #define vcpu_has_ptrauth(vcpu) \ ((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) || \ cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) && \ - vcpu_get_flag(vcpu, GUEST_HAS_PTRAUTH)) + (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) || \ + vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC))) #else #define vcpu_has_ptrauth(vcpu) false #endif @@ -1307,6 +1316,13 @@ DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data); &this_cpu_ptr_hyp_sym(kvm_host_data)->f) #endif +#define host_data_test_flag(flag) \ + (test_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags))) +#define host_data_set_flag(flag) \ + set_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)) +#define host_data_clear_flag(flag) \ + clear_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)) + /* Check whether the FP regs are owned by the guest */ static inline bool guest_owns_fp_regs(void) { @@ -1332,15 +1348,22 @@ static inline bool kvm_system_needs_idmapped_vectors(void) static inline void kvm_arch_sync_events(struct kvm *kvm) {} -void kvm_arm_init_debug(void); -void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu); -void kvm_arm_setup_debug(struct kvm_vcpu *vcpu); -void kvm_arm_clear_debug(struct kvm_vcpu *vcpu); -void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu); +void kvm_init_host_debug_data(void); +void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu); +void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu); +void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu); +void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val); #define kvm_vcpu_os_lock_enabled(vcpu) \ (!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & OSLSR_EL1_OSLK)) +#define kvm_debug_regs_in_use(vcpu) \ + ((vcpu)->arch.debug_owner != VCPU_DEBUG_FREE) +#define kvm_host_owns_debug_regs(vcpu) \ + ((vcpu)->arch.debug_owner == VCPU_DEBUG_HOST_OWNED) +#define kvm_guest_owns_debug_regs(vcpu) \ + ((vcpu)->arch.debug_owner == VCPU_DEBUG_GUEST_OWNED) + int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, @@ -1367,14 +1390,13 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) return (!has_vhe() && attr->exclude_host); } -/* Flags for host debug state */ -void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu); -void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu); - #ifdef CONFIG_KVM void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u64 clr); bool kvm_set_pmuserenr(u64 val); +void kvm_enable_trbe(void); +void kvm_disable_trbe(void); +void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest); #else static inline void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u64 clr) {} @@ -1382,6 +1404,9 @@ static inline bool kvm_set_pmuserenr(u64 val) { return false; } +static inline void kvm_enable_trbe(void) {} +static inline void kvm_disable_trbe(void) {} +static inline void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest) {} #endif void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu); @@ -1422,6 +1447,7 @@ static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature) return test_bit(feature, ka->vcpu_features); } +#define kvm_vcpu_has_feature(k, f) __vcpu_has_feature(&(k)->arch, (f)) #define vcpu_has_feature(v, f) __vcpu_has_feature(&(v)->kvm->arch, (f)) #define kvm_vcpu_initialized(v) vcpu_get_flag(vcpu, VCPU_INITIALIZED) diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 66d93e320ec8..b98ac6aa631f 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -139,6 +139,8 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) #define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v)))) +extern u32 __hyp_va_bits; + /* * We currently support using a VM-specified IPA size. For backward * compatibility, the default IPA size is fixed to 40bits. @@ -353,6 +355,22 @@ static inline bool kvm_is_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu) return &kvm->arch.mmu != mmu; } +static inline void kvm_fault_lock(struct kvm *kvm) +{ + if (is_protected_kvm_enabled()) + write_lock(&kvm->mmu_lock); + else + read_lock(&kvm->mmu_lock); +} + +static inline void kvm_fault_unlock(struct kvm *kvm) +{ + if (is_protected_kvm_enabled()) + write_unlock(&kvm->mmu_lock); + else + read_unlock(&kvm->mmu_lock); +} + #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS void kvm_s2_ptdump_create_debugfs(struct kvm *kvm); #else diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index 233e65522716..56c4bcd35e2e 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -33,14 +33,14 @@ static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr) static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2) { - u64 cpacr_el1 = CPACR_ELx_RES1; + u64 cpacr_el1 = CPACR_EL1_RES1; if (cptr_el2 & CPTR_EL2_TTA) - cpacr_el1 |= CPACR_ELx_TTA; + cpacr_el1 |= CPACR_EL1_TTA; if (!(cptr_el2 & CPTR_EL2_TFP)) - cpacr_el1 |= CPACR_ELx_FPEN; + cpacr_el1 |= CPACR_EL1_FPEN; if (!(cptr_el2 & CPTR_EL2_TZ)) - cpacr_el1 |= CPACR_ELx_ZEN; + cpacr_el1 |= CPACR_EL1_ZEN; cpacr_el1 |= cptr_el2 & (CPTR_EL2_TCPAC | CPTR_EL2_TAM); @@ -64,6 +64,7 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0) } extern bool forward_smc_trap(struct kvm_vcpu *vcpu); +extern bool forward_debug_exception(struct kvm_vcpu *vcpu); extern void kvm_init_nested(struct kvm *kvm); extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu); extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu); @@ -186,7 +187,7 @@ static inline bool kvm_supported_tlbi_s1e2_op(struct kvm_vcpu *vpcu, u32 instr) return true; } -int kvm_init_nv_sysregs(struct kvm *kvm); +int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu); #ifdef CONFIG_ARM64_PTR_AUTH bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr); diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index aab04097b505..6b9d274052c7 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -412,15 +412,20 @@ static inline bool kvm_pgtable_walk_lock_held(void) * be used instead of block mappings. */ struct kvm_pgtable { - u32 ia_bits; - s8 start_level; - kvm_pteref_t pgd; - struct kvm_pgtable_mm_ops *mm_ops; + union { + struct rb_root pkvm_mappings; + struct { + u32 ia_bits; + s8 start_level; + kvm_pteref_t pgd; + struct kvm_pgtable_mm_ops *mm_ops; - /* Stage-2 only */ - struct kvm_s2_mmu *mmu; - enum kvm_pgtable_stage2_flags flags; - kvm_pgtable_force_pte_cb_t force_pte_cb; + /* Stage-2 only */ + enum kvm_pgtable_stage2_flags flags; + kvm_pgtable_force_pte_cb_t force_pte_cb; + }; + }; + struct kvm_s2_mmu *mmu; }; /** @@ -526,8 +531,11 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, enum kvm_pgtable_stage2_flags flags, kvm_pgtable_force_pte_cb_t force_pte_cb); -#define kvm_pgtable_stage2_init(pgt, mmu, mm_ops) \ - __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL) +static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, + struct kvm_pgtable_mm_ops *mm_ops) +{ + return __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL); +} /** * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table. @@ -669,13 +677,15 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size); * kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address to identify the page-table entry. + * @flags: Flags to control the page-table walk (ex. a shared walk) * * The offset of @addr within a page is ignored. * * If there is a valid, leaf page-table entry used to translate @addr, then * set the access flag in that entry. */ -void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr); +void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, + enum kvm_pgtable_walk_flags flags); /** * kvm_pgtable_stage2_test_clear_young() - Test and optionally clear the access @@ -705,6 +715,7 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address to identify the page-table entry. * @prot: Additional permissions to grant for the mapping. + * @flags: Flags to control the page-table walk (ex. a shared walk) * * The offset of @addr within a page is ignored. * @@ -717,7 +728,8 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, - enum kvm_pgtable_prot prot); + enum kvm_pgtable_prot prot, + enum kvm_pgtable_walk_flags flags); /** * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h index cd56acd9a842..eb65f12e81d9 100644 --- a/arch/arm64/include/asm/kvm_pkvm.h +++ b/arch/arm64/include/asm/kvm_pkvm.h @@ -20,6 +20,31 @@ int pkvm_init_host_vm(struct kvm *kvm); int pkvm_create_hyp_vm(struct kvm *kvm); void pkvm_destroy_hyp_vm(struct kvm *kvm); +/* + * This functions as an allow-list of protected VM capabilities. + * Features not explicitly allowed by this function are denied. + */ +static inline bool kvm_pvm_ext_allowed(long ext) +{ + switch (ext) { + case KVM_CAP_IRQCHIP: + case KVM_CAP_ARM_PSCI: + case KVM_CAP_ARM_PSCI_0_2: + case KVM_CAP_NR_VCPUS: + case KVM_CAP_MAX_VCPUS: + case KVM_CAP_MAX_VCPU_ID: + case KVM_CAP_MSI_DEVID: + case KVM_CAP_ARM_VM_IPA_SIZE: + case KVM_CAP_ARM_PMU_V3: + case KVM_CAP_ARM_SVE: + case KVM_CAP_ARM_PTRAUTH_ADDRESS: + case KVM_CAP_ARM_PTRAUTH_GENERIC: + return true; + default: + return false; + } +} + extern struct memblock_region kvm_nvhe_sym(hyp_memory)[]; extern unsigned int kvm_nvhe_sym(hyp_memblock_nr); @@ -137,4 +162,30 @@ static inline size_t pkvm_host_sve_state_size(void) SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl))); } +struct pkvm_mapping { + struct rb_node node; + u64 gfn; + u64 pfn; +}; + +int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, + struct kvm_pgtable_mm_ops *mm_ops); +void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); +int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, + enum kvm_pgtable_prot prot, void *mc, + enum kvm_pgtable_walk_flags flags); +int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size); +int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size); +int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size); +bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold); +int pkvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot, + enum kvm_pgtable_walk_flags flags); +void pkvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, + enum kvm_pgtable_walk_flags flags); +int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, + struct kvm_mmu_memory_cache *mc); +void pkvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level); +kvm_pte_t *pkvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level, + enum kvm_pgtable_prot prot, void *mc, + bool force_pte); #endif /* __ARM64_KVM_PKVM_H__ */ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 8b9f33cf561b..717829df294e 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -145,13 +145,16 @@ #define OVERFLOW_STACK_SIZE SZ_4K +#define NVHE_STACK_SHIFT PAGE_SHIFT +#define NVHE_STACK_SIZE (UL(1) << NVHE_STACK_SHIFT) + /* * With the minimum frame size of [x29, x30], exactly half the combined * sizes of the hyp and overflow stacks is the maximum size needed to * save the unwinded stacktrace; plus an additional entry to delimit the * end. */ -#define NVHE_STACKTRACE_SIZE ((OVERFLOW_STACK_SIZE + PAGE_SIZE) / 2 + sizeof(long)) +#define NVHE_STACKTRACE_SIZE ((OVERFLOW_STACK_SIZE + NVHE_STACK_SIZE) / 2 + sizeof(long)) /* * Alignment of kernel segments (e.g. .text, .data). diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 2ec96d91acc6..662471cfc536 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -109,8 +109,5 @@ static inline bool kaslr_requires_kpti(void) return true; } -#define INIT_MM_CONTEXT(name) \ - .pgd = swapper_pg_dir, - #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 48b3d9553b67..0dbe3b29049b 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -271,18 +271,26 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, } static inline const struct cpumask * -task_cpu_possible_mask(struct task_struct *p) +__task_cpu_possible_mask(struct task_struct *p, const struct cpumask *mask) { if (!static_branch_unlikely(&arm64_mismatched_32bit_el0)) - return cpu_possible_mask; + return mask; if (!is_compat_thread(task_thread_info(p))) - return cpu_possible_mask; + return mask; return system_32bit_el0_cpumask(); } + +static inline const struct cpumask * +task_cpu_possible_mask(struct task_struct *p) +{ + return __task_cpu_possible_mask(p, cpu_possible_mask); +} #define task_cpu_possible_mask task_cpu_possible_mask +const struct cpumask *task_cpu_fallback_mask(struct task_struct *p); + void verify_cpu_asid_bits(void); void post_ttbr_update_workaround(void); diff --git a/arch/arm64/include/asm/mshyperv.h b/arch/arm64/include/asm/mshyperv.h index a975e1a689dd..2e2f83bafcfb 100644 --- a/arch/arm64/include/asm/mshyperv.h +++ b/arch/arm64/include/asm/mshyperv.h @@ -6,9 +6,8 @@ * the ARM64 architecture. See include/asm-generic/mshyperv.h for * definitions are that architecture independent. * - * Definitions that are specified in the Hyper-V Top Level Functional - * Spec (TLFS) should not go in this file, but should instead go in - * hyperv-tlfs.h. + * Definitions that are derived from Hyper-V code or headers should not go in + * this file, but should instead go in the relevant files in include/hyperv. * * Copyright (C) 2021, Microsoft, Inc. * @@ -20,7 +19,7 @@ #include #include -#include +#include /* * Declare calls to get and set Hyper-V VP register values on ARM64, which diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index e75422864d1b..1b4509d3382c 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -85,24 +85,6 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, p4d_t *p4dp) __pgd_populate(pgdp, __pa(p4dp), pgdval); } -static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - gfp_t gfp = GFP_PGTABLE_USER; - - if (mm == &init_mm) - gfp = GFP_PGTABLE_KERNEL; - return (p4d_t *)get_zeroed_page(gfp); -} - -static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) -{ - if (!pgtable_l5_enabled()) - return; - BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); - free_page((unsigned long)p4d); -} - -#define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d) #else static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot) { diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index c78a988cca93..a9136cc551cc 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -222,12 +222,6 @@ */ #define S1_TABLE_AP (_AT(pmdval_t, 3) << 61) -/* - * Highest possible physical address supported. - */ -#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS) -#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1) - #define TTBR_CNP_BIT (UL(1) << 0) /* diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 9f9cf13bbd95..a95f1f77bb39 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -81,6 +81,7 @@ extern unsigned long prot_ns_shared; #define lpa2_is_enabled() false #define PTE_MAYBE_SHARED PTE_SHARED #define PMD_MAYBE_SHARED PMD_SECT_S +#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS) #else static inline bool __pure lpa2_is_enabled(void) { @@ -89,8 +90,14 @@ static inline bool __pure lpa2_is_enabled(void) #define PTE_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PTE_SHARED) #define PMD_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PMD_SECT_S) +#define PHYS_MASK_SHIFT (lpa2_is_enabled() ? CONFIG_ARM64_PA_BITS : 48) #endif +/* + * Highest possible physical address supported. + */ +#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1) + /* * If we have userspace only BTI we don't want to mark kernel pages * guarded even if the system does support BTI. diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 6986345b537a..0b2a2ad1b9e8 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -273,7 +273,7 @@ static inline pte_t pte_mknoncont(pte_t pte) return clear_pte_bit(pte, __pgprot(PTE_CONT)); } -static inline pte_t pte_mkpresent(pte_t pte) +static inline pte_t pte_mkvalid(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_VALID)); } @@ -896,7 +896,7 @@ static inline bool mm_pud_folded(const struct mm_struct *mm) pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) #define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) -#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) +#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & P4D_TABLE_BIT)) #define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) @@ -1023,7 +1023,7 @@ static inline bool mm_p4d_folded(const struct mm_struct *mm) pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) #define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) -#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) +#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & PGD_TABLE_BIT)) #define pgd_present(pgd) (!pgd_none(pgd)) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) @@ -1345,7 +1345,7 @@ static inline void ___ptep_set_wrprotect(struct mm_struct *mm, } /* - * __ptep_set_wrprotect - mark read-only while trasferring potential hardware + * __ptep_set_wrprotect - mark read-only while transferring potential hardware * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ static inline void __ptep_set_wrprotect(struct mm_struct *mm, diff --git a/arch/arm64/include/asm/rsi.h b/arch/arm64/include/asm/rsi.h index 188cbb9b23f5..b42aeac05340 100644 --- a/arch/arm64/include/asm/rsi.h +++ b/arch/arm64/include/asm/rsi.h @@ -10,6 +10,8 @@ #include #include +#define RSI_PDEV_NAME "arm-cca-dev" + DECLARE_STATIC_KEY_FALSE(rsi_present); void __init arm64_rsi_init(void); diff --git a/arch/arm64/include/asm/seccomp.h b/arch/arm64/include/asm/seccomp.h index b83975555314..bf6bf40bc5ab 100644 --- a/arch/arm64/include/asm/seccomp.h +++ b/arch/arm64/include/asm/seccomp.h @@ -23,7 +23,6 @@ #define SECCOMP_ARCH_NATIVE_NR NR_syscalls #define SECCOMP_ARCH_NATIVE_NAME "aarch64" #ifdef CONFIG_COMPAT -#include # define SECCOMP_ARCH_COMPAT AUDIT_ARCH_ARM # define SECCOMP_ARCH_COMPAT_NR __NR_compat32_syscalls # define SECCOMP_ARCH_COMPAT_NAME "arm" diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h index 8a8acc220371..84783efdc9d1 100644 --- a/arch/arm64/include/asm/sparsemem.h +++ b/arch/arm64/include/asm/sparsemem.h @@ -5,7 +5,10 @@ #ifndef __ASM_SPARSEMEM_H #define __ASM_SPARSEMEM_H -#define MAX_PHYSMEM_BITS CONFIG_ARM64_PA_BITS +#include + +#define MAX_PHYSMEM_BITS PHYS_MASK_SHIFT +#define MAX_POSSIBLE_PHYSMEM_BITS (52) /* * Section size must be at least 512MB for 64K base diff --git a/arch/arm64/include/asm/stacktrace/nvhe.h b/arch/arm64/include/asm/stacktrace/nvhe.h index 44759281d0d4..171f9edef49f 100644 --- a/arch/arm64/include/asm/stacktrace/nvhe.h +++ b/arch/arm64/include/asm/stacktrace/nvhe.h @@ -47,7 +47,7 @@ static inline void kvm_nvhe_unwind_init(struct unwind_state *state, DECLARE_KVM_NVHE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack); DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_stacktrace_info, kvm_stacktrace_info); -DECLARE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); +DECLARE_PER_CPU(unsigned long, kvm_arm_hyp_stack_base); void kvm_nvhe_dump_backtrace(unsigned long hyp_offset); diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index b8303a83c0bf..05ea5223d2d5 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -283,8 +283,6 @@ #define SYS_RGSR_EL1 sys_reg(3, 0, 1, 0, 5) #define SYS_GCR_EL1 sys_reg(3, 0, 1, 0, 6) -#define SYS_TRFCR_EL1 sys_reg(3, 0, 1, 2, 1) - #define SYS_TCR_EL1 sys_reg(3, 0, 2, 0, 2) #define SYS_APIAKEYLO_EL1 sys_reg(3, 0, 2, 1, 0) @@ -477,6 +475,7 @@ #define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0) #define SYS_CNTPCT_EL0 sys_reg(3, 3, 14, 0, 1) +#define SYS_CNTVCT_EL0 sys_reg(3, 3, 14, 0, 2) #define SYS_CNTPCTSS_EL0 sys_reg(3, 3, 14, 0, 5) #define SYS_CNTVCTSS_EL0 sys_reg(3, 3, 14, 0, 6) @@ -484,14 +483,17 @@ #define SYS_CNTP_CTL_EL0 sys_reg(3, 3, 14, 2, 1) #define SYS_CNTP_CVAL_EL0 sys_reg(3, 3, 14, 2, 2) +#define SYS_CNTV_TVAL_EL0 sys_reg(3, 3, 14, 3, 0) #define SYS_CNTV_CTL_EL0 sys_reg(3, 3, 14, 3, 1) #define SYS_CNTV_CVAL_EL0 sys_reg(3, 3, 14, 3, 2) #define SYS_AARCH32_CNTP_TVAL sys_reg(0, 0, 14, 2, 0) #define SYS_AARCH32_CNTP_CTL sys_reg(0, 0, 14, 2, 1) #define SYS_AARCH32_CNTPCT sys_reg(0, 0, 0, 14, 0) +#define SYS_AARCH32_CNTVCT sys_reg(0, 1, 0, 14, 0) #define SYS_AARCH32_CNTP_CVAL sys_reg(0, 2, 0, 14, 0) #define SYS_AARCH32_CNTPCTSS sys_reg(0, 8, 0, 14, 0) +#define SYS_AARCH32_CNTVCTSS sys_reg(0, 9, 0, 14, 0) #define __PMEV_op2(n) ((n) & 0x7) #define __CNTR_CRm(n) (0x8 | (((n) >> 3) & 0x3)) @@ -519,7 +521,6 @@ #define SYS_VTTBR_EL2 sys_reg(3, 4, 2, 1, 0) #define SYS_VTCR_EL2 sys_reg(3, 4, 2, 1, 2) -#define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) #define SYS_VNCR_EL2 sys_reg(3, 4, 2, 2, 0) #define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6) #define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0) @@ -983,15 +984,6 @@ /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */ #define SYS_MPIDR_SAFE_VAL (BIT(31)) -#define TRFCR_ELx_TS_SHIFT 5 -#define TRFCR_ELx_TS_MASK ((0x3UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_ELx_TS_VIRTUAL ((0x1UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_ELx_TS_GUEST_PHYSICAL ((0x2UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_ELx_TS_PHYSICAL ((0x3UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_EL2_CX BIT(3) -#define TRFCR_ELx_ExTRE BIT(1) -#define TRFCR_ELx_E0TRE BIT(0) - /* GIC Hypervisor interface registers */ /* ICH_MISR_EL2 bit definitions */ #define ICH_MISR_EOI (1 << 0) diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index a947c6e784ed..8d762607285c 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -9,12 +9,7 @@ #define __ASM_TLB_H #include -#include -static inline void __tlb_remove_table(void *_table) -{ - free_page_and_swap_cache((struct page *)_table); -} #define tlb_flush tlb_flush static void tlb_flush(struct mmu_gather *tlb); @@ -82,7 +77,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, { struct ptdesc *ptdesc = page_ptdesc(pte); - pagetable_pte_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } @@ -92,7 +86,6 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, { struct ptdesc *ptdesc = virt_to_ptdesc(pmdp); - pagetable_pmd_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } #endif @@ -106,7 +99,19 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, if (!pgtable_l4_enabled()) return; - pagetable_pud_dtor(ptdesc); + tlb_remove_ptdesc(tlb, ptdesc); +} +#endif + +#if CONFIG_PGTABLE_LEVELS > 4 +static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4dp, + unsigned long addr) +{ + struct ptdesc *ptdesc = virt_to_ptdesc(p4dp); + + if (!pgtable_l5_enabled()) + return; + tlb_remove_ptdesc(tlb, ptdesc); } #endif diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 48d46b768eae..705a7afa8e58 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -56,6 +56,21 @@ #define HWCAP_PACA (1 << 30) #define HWCAP_PACG (1UL << 31) #define HWCAP_GCS (1UL << 32) +#define HWCAP_CMPBR (1UL << 33) +#define HWCAP_FPRCVT (1UL << 34) +#define HWCAP_F8MM8 (1UL << 35) +#define HWCAP_F8MM4 (1UL << 36) +#define HWCAP_SVE_F16MM (1UL << 37) +#define HWCAP_SVE_ELTPERM (1UL << 38) +#define HWCAP_SVE_AES2 (1UL << 39) +#define HWCAP_SVE_BFSCALE (1UL << 40) +#define HWCAP_SVE2P2 (1UL << 41) +#define HWCAP_SME2P2 (1UL << 42) +#define HWCAP_SME_SBITPERM (1UL << 43) +#define HWCAP_SME_AES (1UL << 44) +#define HWCAP_SME_SFEXPA (1UL << 45) +#define HWCAP_SME_STMOP (1UL << 46) +#define HWCAP_SME_SMOP4 (1UL << 47) /* * HWCAP2 flags - for AT_HWCAP2 diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 66736ff04011..568bf858f319 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -43,9 +43,6 @@ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #define KVM_DIRTY_LOG_PAGE_OFFSET 64 -#define KVM_REG_SIZE(id) \ - (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) - struct kvm_regs { struct user_pt_regs regs; /* sp = sp_el0 */ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 29bf85dacffe..eb1a840e4110 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -179,18 +179,6 @@ int main(void) DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func)); #endif BLANK(); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - DEFINE(FGRET_REGS_X0, offsetof(struct fgraph_ret_regs, regs[0])); - DEFINE(FGRET_REGS_X1, offsetof(struct fgraph_ret_regs, regs[1])); - DEFINE(FGRET_REGS_X2, offsetof(struct fgraph_ret_regs, regs[2])); - DEFINE(FGRET_REGS_X3, offsetof(struct fgraph_ret_regs, regs[3])); - DEFINE(FGRET_REGS_X4, offsetof(struct fgraph_ret_regs, regs[4])); - DEFINE(FGRET_REGS_X5, offsetof(struct fgraph_ret_regs, regs[5])); - DEFINE(FGRET_REGS_X6, offsetof(struct fgraph_ret_regs, regs[6])); - DEFINE(FGRET_REGS_X7, offsetof(struct fgraph_ret_regs, regs[7])); - DEFINE(FGRET_REGS_FP, offsetof(struct fgraph_ret_regs, fp)); - DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs)); -#endif #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS DEFINE(FTRACE_OPS_DIRECT_CALL, offsetof(struct ftrace_ops, direct_call)); #endif diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index a78f247029ae..7ce555862895 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -786,6 +786,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE_LIST(erratum_ac03_cpu_38_list), }, #endif + { + .desc = "Broken CNTVOFF_EL2", + .capability = ARM64_WORKAROUND_QCOM_ORYON_CNTVOFF, + ERRATA_MIDR_RANGE_LIST(((const struct midr_range[]) { + MIDR_ALL_VERSIONS(MIDR_QCOM_ORYON_X1), + {} + })), + }, { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6ce71f444ed8..4eb7c6698ae4 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -75,6 +75,7 @@ #include #include #include +#include #include #include @@ -268,6 +269,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar3[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FPRCVT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FAMINMAX_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -317,6 +319,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F64MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F32MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F16MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_I8MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), @@ -329,6 +333,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BitPerm_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_EltPerm_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_AES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), @@ -373,6 +379,16 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SBitPerm_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_AES_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SFEXPA_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_STMOP_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMOP4_SHIFT, 1, 0), ARM64_FTR_END, }; @@ -381,6 +397,8 @@ static const struct arm64_ftr_bits ftr_id_aa64fpfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8FMA_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8MM8_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8MM4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E4M3_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E5M2_SHIFT, 1, 0), ARM64_FTR_END, @@ -1004,17 +1022,16 @@ static void init_cpu_ftr_reg(u32 sys_reg, u64 new) /* Override was valid */ ftr_new = tmp; str = "forced"; - } else if (ftr_ovr == tmp) { + } else { /* Override was the safe value */ str = "already set"; } - if (str) - pr_warn("%s[%d:%d]: %s to %llx\n", - reg->name, - ftrp->shift + ftrp->width - 1, - ftrp->shift, str, - tmp & (BIT(ftrp->width) - 1)); + pr_warn("%s[%d:%d]: %s to %llx\n", + reg->name, + ftrp->shift + ftrp->width - 1, + ftrp->shift, str, + tmp & (BIT(ftrp->width) - 1)); } else if ((ftr_mask & reg->override->val) == ftr_mask) { reg->override->val &= ~ftr_mask; pr_warn("%s[%d:%d]: impossible override, ignored\n", @@ -1167,12 +1184,6 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { unsigned long cpacr = cpacr_save_enable_kernel_sme(); - /* - * We mask out SMPS since even if the hardware - * supports priorities the kernel does not at present - * and we block access to them. - */ - info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; vec_init_vq_map(ARM64_VEC_SME); cpacr_restore(cpacr); @@ -1423,13 +1434,6 @@ void update_cpu_features(int cpu, id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { unsigned long cpacr = cpacr_save_enable_kernel_sme(); - /* - * We mask out SMPS since even if the hardware - * supports priorities the kernel does not at present - * and we block access to them. - */ - info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; - /* Probe vector lengths */ if (!system_capabilities_finalized()) vec_update_vq_map(ARM64_VEC_SME); @@ -1641,6 +1645,11 @@ const struct cpumask *system_32bit_el0_cpumask(void) return cpu_possible_mask; } +const struct cpumask *task_cpu_fallback_mask(struct task_struct *p) +{ + return __task_cpu_possible_mask(p, housekeeping_cpumask(HK_TYPE_TICK)); +} + static int __init parse_32bit_el0_param(char *str) { allow_mismatched_32bit_el0 = true; @@ -2376,8 +2385,8 @@ static void cpu_enable_mops(const struct arm64_cpu_capabilities *__unused) #ifdef CONFIG_ARM64_POE static void cpu_enable_poe(const struct arm64_cpu_capabilities *__unused) { - sysreg_clear_set(REG_TCR2_EL1, 0, TCR2_EL1x_E0POE); - sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_E0POE); + sysreg_clear_set(REG_TCR2_EL1, 0, TCR2_EL1_E0POE); + sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_E0POE); } #endif @@ -3022,6 +3031,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = match, \ } +#define HWCAP_CAP_MATCH_ID(match, reg, field, min_value, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + HWCAP_CPUID_MATCH(reg, field, min_value) \ + .matches = match, \ + } + #ifdef CONFIG_ARM64_PTR_AUTH static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { @@ -3050,6 +3066,13 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { }; #endif +#ifdef CONFIG_ARM64_SVE +static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope) +{ + return system_supports_sve() && has_user_cpuid_feature(cap, scope); +} +#endif + static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL), HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES), @@ -3092,19 +3115,24 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), - HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), - HWCAP_CAP(ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), - HWCAP_CAP(ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), - HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p2, CAP_HWCAP, KERNEL_HWCAP_SVE2P2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, AES2, CAP_HWCAP, KERNEL_HWCAP_SVE_AES2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, BFSCALE, CAP_HWCAP, KERNEL_HWCAP_SVE_BFSCALE), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F16MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_F16MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, EltPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_ELTPERM), #endif #ifdef CONFIG_ARM64_GCS HWCAP_CAP(ID_AA64PFR1_EL1, GCS, IMP, CAP_HWCAP, KERNEL_HWCAP_GCS), @@ -3124,6 +3152,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64MMFR0_EL1, ECV, IMP, CAP_HWCAP, KERNEL_HWCAP_ECV), HWCAP_CAP(ID_AA64MMFR1_EL1, AFP, IMP, CAP_HWCAP, KERNEL_HWCAP_AFP), HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC), + HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, CMPBR, CAP_HWCAP, KERNEL_HWCAP_CMPBR), HWCAP_CAP(ID_AA64ISAR2_EL1, RPRFM, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM), HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES), HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT), @@ -3133,6 +3162,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), + HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), @@ -3150,6 +3180,13 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM8), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM4), + HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM), + HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES), + HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA), + HWCAP_CAP(ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP), + HWCAP_CAP(ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4), #endif /* CONFIG_ARM64_SME */ HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT), HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), @@ -3478,7 +3515,7 @@ static void verify_hyp_capabilities(void) return; safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); - mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); /* Verify VMID bits */ @@ -3742,7 +3779,14 @@ static int enable_mismatched_32bit_el0(unsigned int cpu) static int lucky_winner = -1; struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu); - bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0); + bool cpu_32bit = false; + + if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) { + if (!housekeeping_cpu(cpu, HK_TYPE_TICK)) + pr_info("Treating adaptive-ticks CPU %u as 64-bit only\n", cpu); + else + cpu_32bit = true; + } if (cpu_32bit) { cpumask_set_cpu(cpu, cpu_32bit_el0_mask); diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index d79e88fccdfc..285d7d538342 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -145,6 +145,21 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_SF8DP4] = "smesf8dp4", [KERNEL_HWCAP_SME_SF8DP2] = "smesf8dp2", [KERNEL_HWCAP_POE] = "poe", + [KERNEL_HWCAP_CMPBR] = "cmpbr", + [KERNEL_HWCAP_FPRCVT] = "fprcvt", + [KERNEL_HWCAP_F8MM8] = "f8mm8", + [KERNEL_HWCAP_F8MM4] = "f8mm4", + [KERNEL_HWCAP_SVE_F16MM] = "svef16mm", + [KERNEL_HWCAP_SVE_ELTPERM] = "sveeltperm", + [KERNEL_HWCAP_SVE_AES2] = "sveaes2", + [KERNEL_HWCAP_SVE_BFSCALE] = "svebfscale", + [KERNEL_HWCAP_SVE2P2] = "sve2p2", + [KERNEL_HWCAP_SME2P2] = "sme2p2", + [KERNEL_HWCAP_SME_SBITPERM] = "smesbitperm", + [KERNEL_HWCAP_SME_AES] = "smeaes", + [KERNEL_HWCAP_SME_SFEXPA] = "smesfexpa", + [KERNEL_HWCAP_SME_STMOP] = "smestmop", + [KERNEL_HWCAP_SME_SMOP4] = "smesmop4", }; #ifdef CONFIG_COMPAT @@ -482,6 +497,16 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) if (id_aa64pfr0_mpam(info->reg_id_aa64pfr0)) info->reg_mpamidr = read_cpuid(MPAMIDR_EL1); + if (IS_ENABLED(CONFIG_ARM64_SME) && + id_aa64pfr1_sme(info->reg_id_aa64pfr1)) { + /* + * We mask out SMPS since even if the hardware + * supports priorities the kernel does not at present + * and we block access to them. + */ + info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; + } + cpuinfo_detect_icache_policy(info); } diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index f0c16640ef21..169ccf600066 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -329,24 +329,28 @@ SYM_FUNC_END(ftrace_stub_graph) * @fp is checked against the value passed by ftrace_graph_caller(). */ SYM_CODE_START(return_to_handler) - /* save return value regs */ - sub sp, sp, #FGRET_REGS_SIZE - stp x0, x1, [sp, #FGRET_REGS_X0] - stp x2, x3, [sp, #FGRET_REGS_X2] - stp x4, x5, [sp, #FGRET_REGS_X4] - stp x6, x7, [sp, #FGRET_REGS_X6] - str x29, [sp, #FGRET_REGS_FP] // parent's fp + /* Make room for ftrace_regs */ + sub sp, sp, #FREGS_SIZE + + /* Save return value regs */ + stp x0, x1, [sp, #FREGS_X0] + stp x2, x3, [sp, #FREGS_X2] + stp x4, x5, [sp, #FREGS_X4] + stp x6, x7, [sp, #FREGS_X6] + + /* Save the callsite's FP */ + str x29, [sp, #FREGS_FP] mov x0, sp - bl ftrace_return_to_handler // addr = ftrace_return_to_hander(regs); + bl ftrace_return_to_handler // addr = ftrace_return_to_hander(fregs); mov x30, x0 // restore the original return address - /* restore return value regs */ - ldp x0, x1, [sp, #FGRET_REGS_X0] - ldp x2, x3, [sp, #FGRET_REGS_X2] - ldp x4, x5, [sp, #FGRET_REGS_X4] - ldp x6, x7, [sp, #FGRET_REGS_X6] - add sp, sp, #FGRET_REGS_SIZE + /* Restore return value regs */ + ldp x0, x1, [sp, #FREGS_X0] + ldp x2, x3, [sp, #FREGS_X2] + ldp x4, x5, [sp, #FREGS_X4] + ldp x6, x7, [sp, #FREGS_X6] + add sp, sp, #FREGS_SIZE ret SYM_CODE_END(return_to_handler) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 8c4c1a2186cc..2b601d88762d 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -562,7 +562,7 @@ static int vec_proc_do_default_vl(const struct ctl_table *table, int write, return 0; } -static struct ctl_table sve_default_vl_table[] = { +static const struct ctl_table sve_default_vl_table[] = { { .procname = "sve_default_vector_length", .mode = 0644, @@ -585,7 +585,7 @@ static int __init sve_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL) -static struct ctl_table sme_default_vl_table[] = { +static const struct ctl_table sme_default_vl_table[] = { { .procname = "sme_default_vector_length", .mode = 0644, diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 245cb419ca24..d7c0d023dfe5 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -143,6 +143,69 @@ unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +/* Convert fentry_ip to the symbol address without kallsyms */ +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) +{ + u32 insn; + + /* + * When using patchable-function-entry without pre-function NOPS, ftrace + * entry is the address of the first NOP after the function entry point. + * + * The compiler has either generated: + * + * func+00: func: NOP // To be patched to MOV X9, LR + * func+04: NOP // To be patched to BL + * + * Or: + * + * func-04: BTI C + * func+00: func: NOP // To be patched to MOV X9, LR + * func+04: NOP // To be patched to BL + * + * The fentry_ip is the address of `BL ` which is at `func + 4` + * bytes in either case. + */ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return fentry_ip - AARCH64_INSN_SIZE; + + /* + * When using patchable-function-entry with pre-function NOPs, BTI is + * a bit different. + * + * func+00: func: NOP // To be patched to MOV X9, LR + * func+04: NOP // To be patched to BL + * + * Or: + * + * func+00: func: BTI C + * func+04: NOP // To be patched to MOV X9, LR + * func+08: NOP // To be patched to BL + * + * The fentry_ip is the address of `BL ` which is at either + * `func + 4` or `func + 8` depends on whether there is a BTI. + */ + + /* If there is no BTI, the func address should be one instruction before. */ + if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) + return fentry_ip - AARCH64_INSN_SIZE; + + /* We want to be extra safe in case entry ip is on the page edge, + * but otherwise we need to avoid get_kernel_nofault()'s overhead. + */ + if ((fentry_ip & ~PAGE_MASK) < AARCH64_INSN_SIZE * 2) { + if (get_kernel_nofault(insn, (u32 *)(fentry_ip - AARCH64_INSN_SIZE * 2))) + return 0; + } else { + insn = *(u32 *)(fentry_ip - AARCH64_INSN_SIZE * 2); + } + + if (aarch64_insn_is_bti(le32_to_cpu((__le32)insn))) + return fentry_ip - AARCH64_INSN_SIZE * 2; + + return fentry_ip - AARCH64_INSN_SIZE; +} + /* * Replace a single instruction, which may be a branch or NOP. * If @validate == true, a replaced instruction is checked against 'old'. @@ -481,7 +544,20 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - prepare_ftrace_return(ip, &arch_ftrace_regs(fregs)->lr, arch_ftrace_regs(fregs)->fp); + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long frame_pointer = arch_ftrace_regs(fregs)->fp; + unsigned long *parent = &arch_ftrace_regs(fregs)->lr; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; + + if (!function_graph_enter_regs(old, ip, frame_pointer, + (void *)frame_pointer, fregs)) { + *parent = return_hooker; + } } #else /* diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 8f5422ed1b75..ef3a69cc398e 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -105,6 +105,9 @@ KVM_NVHE_ALIAS(__hyp_stub_vectors); KVM_NVHE_ALIAS(vgic_v2_cpuif_trap); KVM_NVHE_ALIAS(vgic_v3_cpuif_trap); +/* Static key which is set if CNTVOFF_EL2 is unusable */ +KVM_NVHE_ALIAS(broken_cntvoff_key); + /* EL2 exception handling */ KVM_NVHE_ALIAS(__start___kvm_ex_table); KVM_NVHE_ALIAS(__stop___kvm_ex_table); diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 82e2203d86a3..6f121a0164a4 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -207,37 +207,6 @@ void machine_kexec(struct kimage *kimage) BUG(); /* Should never get here. */ } -static void machine_kexec_mask_interrupts(void) -{ - unsigned int i; - struct irq_desc *desc; - - for_each_irq_desc(i, desc) { - struct irq_chip *chip; - int ret; - - chip = irq_desc_get_chip(desc); - if (!chip) - continue; - - /* - * First try to remove the active state. If this - * fails, try to EOI the interrupt. - */ - ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); - - if (ret && irqd_irq_inprogress(&desc->irq_data) && - chip->irq_eoi) - chip->irq_eoi(&desc->irq_data); - - if (chip->irq_mask) - chip->irq_mask(&desc->irq_data); - - if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) - chip->irq_disable(&desc->irq_data); - } -} - /** * machine_crash_shutdown - shutdown non-crashing cpus and save registers */ diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c index 22159251eb3a..c6b185b885f7 100644 --- a/arch/arm64/kernel/pi/idreg-override.c +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -83,6 +83,15 @@ static bool __init mmfr2_varange_filter(u64 val) id_aa64mmfr0_override.val |= (ID_AA64MMFR0_EL1_TGRAN_LPA2 - 1) << ID_AA64MMFR0_EL1_TGRAN_SHIFT; id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_TGRAN_SHIFT; + + /* + * Override PARange to 48 bits - the override will just be + * ignored if the actual PARange is smaller, but this is + * unlikely to be the case for LPA2 capable silicon. + */ + id_aa64mmfr0_override.val |= + ID_AA64MMFR0_EL1_PARANGE_48 << ID_AA64MMFR0_EL1_PARANGE_SHIFT; + id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_PARANGE_SHIFT; } #endif return true; diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index f374a3e5a5fe..e57b043f324b 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -136,6 +136,12 @@ static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr) { u64 sctlr = read_sysreg(sctlr_el1); u64 tcr = read_sysreg(tcr_el1) | TCR_DS; + u64 mmfr0 = read_sysreg(id_aa64mmfr0_el1); + u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_EL1_PARANGE_SHIFT); + + tcr &= ~TCR_IPS_MASK; + tcr |= parange << TCR_IPS_SHIFT; asm(" msr sctlr_el1, %0 ;" " isb ;" diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 2968a33bb3bc..42faebb7b712 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -859,7 +859,7 @@ long get_tagged_addr_ctrl(struct task_struct *task) * disable it for tasks that already opted in to the relaxed ABI. */ -static struct ctl_table tagged_addr_sysctl_table[] = { +static const struct ctl_table tagged_addr_sysctl_table[] = { { .procname = "tagged_addr_disabled", .mode = 0644, diff --git a/arch/arm64/kernel/rsi.c b/arch/arm64/kernel/rsi.c index 3031f25c32ef..ce4778141ec7 100644 --- a/arch/arm64/kernel/rsi.c +++ b/arch/arm64/kernel/rsi.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -140,3 +141,17 @@ void __init arm64_rsi_init(void) static_branch_enable(&rsi_present); } +static struct platform_device rsi_dev = { + .name = RSI_PDEV_NAME, + .id = PLATFORM_DEVID_NONE +}; + +static int __init arm64_create_dummy_rsi_dev(void) +{ + if (is_realm_world() && + platform_device_register(&rsi_dev)) + pr_err("failed to register rsi platform device\n"); + return 0; +} + +arch_initcall(arm64_create_dummy_rsi_dev) diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 4f613e8e0745..85104587f849 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -223,9 +223,7 @@ static void __init request_standard_resources(void) num_standard_resources = memblock.memory.cnt; res_size = num_standard_resources * sizeof(*standard_resources); - standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES); - if (!standard_resources) - panic("%s: Failed to allocate %zu bytes\n", __func__, res_size); + standard_resources = memblock_alloc_or_panic(res_size, SMP_CACHE_BYTES); for_each_mem_region(region) { res = &standard_resources[i++]; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 37e24f1bd227..99ea26d400ff 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -36,15 +36,8 @@ #include #include -#ifdef CONFIG_ARM64_GCS #define GCS_SIGNAL_CAP(addr) (((unsigned long)addr) & GCS_CAP_ADDR_MASK) -static bool gcs_signal_cap_valid(u64 addr, u64 val) -{ - return val == GCS_SIGNAL_CAP(addr); -} -#endif - /* * Do a signal return; undo the signal stack. These are aligned to 128-bit. */ @@ -1062,8 +1055,7 @@ static int restore_sigframe(struct pt_regs *regs, #ifdef CONFIG_ARM64_GCS static int gcs_restore_signal(void) { - unsigned long __user *gcspr_el0; - u64 cap; + u64 gcspr_el0, cap; int ret; if (!system_supports_gcs()) @@ -1072,7 +1064,7 @@ static int gcs_restore_signal(void) if (!(current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE)) return 0; - gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0); + gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0); /* * Ensure that any changes to the GCS done via GCS operations @@ -1087,22 +1079,23 @@ static int gcs_restore_signal(void) * then faults will be generated on GCS operations - the main * concern is to protect GCS pages. */ - ret = copy_from_user(&cap, gcspr_el0, sizeof(cap)); + ret = copy_from_user(&cap, (unsigned long __user *)gcspr_el0, + sizeof(cap)); if (ret) return -EFAULT; /* * Check that the cap is the actual GCS before replacing it. */ - if (!gcs_signal_cap_valid((u64)gcspr_el0, cap)) + if (cap != GCS_SIGNAL_CAP(gcspr_el0)) return -EINVAL; /* Invalidate the token to prevent reuse */ - put_user_gcs(0, (__user void*)gcspr_el0, &ret); + put_user_gcs(0, (unsigned long __user *)gcspr_el0, &ret); if (ret != 0) return -EFAULT; - write_sysreg_s(gcspr_el0 + 1, SYS_GCSPR_EL0); + write_sysreg_s(gcspr_el0 + 8, SYS_GCSPR_EL0); return 0; } @@ -1421,7 +1414,7 @@ static int get_sigframe(struct rt_sigframe_user_layout *user, static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig) { - unsigned long __user *gcspr_el0; + u64 gcspr_el0; int ret = 0; if (!system_supports_gcs()) @@ -1434,18 +1427,20 @@ static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig) * We are entering a signal handler, current register state is * active. */ - gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0); + gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0); /* * Push a cap and the GCS entry for the trampoline onto the GCS. */ - put_user_gcs((unsigned long)sigtramp, gcspr_el0 - 2, &ret); - put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 1), gcspr_el0 - 1, &ret); + put_user_gcs((unsigned long)sigtramp, + (unsigned long __user *)(gcspr_el0 - 16), &ret); + put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 8), + (unsigned long __user *)(gcspr_el0 - 8), &ret); if (ret != 0) return ret; - gcspr_el0 -= 2; - write_sysreg_s((unsigned long)gcspr_el0, SYS_GCSPR_EL0); + gcspr_el0 -= 16; + write_sysreg_s(gcspr_el0, SYS_GCSPR_EL0); return 0; } diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 1215df590418..d3d243366536 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -30,6 +30,7 @@ static u32 host_vtimer_irq_flags; static u32 host_ptimer_irq_flags; static DEFINE_STATIC_KEY_FALSE(has_gic_active_state); +DEFINE_STATIC_KEY_FALSE(broken_cntvoff_key); static const u8 default_ppi[] = { [TIMER_PTIMER] = 30, @@ -101,21 +102,6 @@ u64 timer_get_cval(struct arch_timer_context *ctxt) } } -static u64 timer_get_offset(struct arch_timer_context *ctxt) -{ - u64 offset = 0; - - if (!ctxt) - return 0; - - if (ctxt->offset.vm_offset) - offset += *ctxt->offset.vm_offset; - if (ctxt->offset.vcpu_offset) - offset += *ctxt->offset.vcpu_offset; - - return offset; -} - static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl) { struct kvm_vcpu *vcpu = ctxt->vcpu; @@ -441,11 +427,30 @@ void kvm_timer_update_run(struct kvm_vcpu *vcpu) regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER; } +static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level) +{ + /* + * Paper over NV2 brokenness by publishing the interrupt status + * bit. This still results in a poor quality of emulation (guest + * writes will have no effect until the next exit). + * + * But hey, it's fast, right? + */ + if (is_hyp_ctxt(ctx->vcpu) && + (ctx == vcpu_vtimer(ctx->vcpu) || ctx == vcpu_ptimer(ctx->vcpu))) { + unsigned long val = timer_get_ctl(ctx); + __assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &val, level); + timer_set_ctl(ctx, val); + } +} + static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, struct arch_timer_context *timer_ctx) { int ret; + kvm_timer_update_status(timer_ctx, new_level); + timer_ctx->irq.level = new_level; trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx), timer_ctx->irq.level); @@ -471,6 +476,8 @@ static void timer_emulate(struct arch_timer_context *ctx) return; } + kvm_timer_update_status(ctx, should_fire); + /* * If the timer can fire now, we don't need to have a soft timer * scheduled for the future. If the timer cannot fire at all, @@ -513,7 +520,12 @@ static void timer_save_state(struct arch_timer_context *ctx) case TIMER_VTIMER: case TIMER_HVTIMER: timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL)); - timer_set_cval(ctx, read_sysreg_el0(SYS_CNTV_CVAL)); + cval = read_sysreg_el0(SYS_CNTV_CVAL); + + if (has_broken_cntvoff()) + cval -= timer_get_offset(ctx); + + timer_set_cval(ctx, cval); /* Disable the timer */ write_sysreg_el0(0, SYS_CNTV_CTL); @@ -618,8 +630,15 @@ static void timer_restore_state(struct arch_timer_context *ctx) case TIMER_VTIMER: case TIMER_HVTIMER: - set_cntvoff(timer_get_offset(ctx)); - write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL); + cval = timer_get_cval(ctx); + offset = timer_get_offset(ctx); + if (has_broken_cntvoff()) { + set_cntvoff(0); + cval += offset; + } else { + set_cntvoff(offset); + } + write_sysreg_el0(cval, SYS_CNTV_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL); break; @@ -762,7 +781,7 @@ static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu, static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map) { - bool tpt, tpc; + bool tvt, tpt, tvc, tpc, tvt02, tpt02; u64 clr, set; /* @@ -777,7 +796,29 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map) * within this function, reality kicks in and we start adding * traps based on emulation requirements. */ - tpt = tpc = false; + tvt = tpt = tvc = tpc = false; + tvt02 = tpt02 = false; + + /* + * NV2 badly breaks the timer semantics by redirecting accesses to + * the EL1 timer state to memory, so let's call ECV to the rescue if + * available: we trap all CNT{P,V}_{CTL,CVAL,TVAL}_EL0 accesses. + * + * The treatment slightly varies depending whether we run a nVHE or + * VHE guest: nVHE will use the _EL0 registers directly, while VHE + * will use the _EL02 accessors. This translates in different trap + * bits. + * + * None of the trapping is required when running in non-HYP context, + * unless required by the L1 hypervisor settings once we advertise + * ECV+NV in the guest, or that we need trapping for other reasons. + */ + if (cpus_have_final_cap(ARM64_HAS_ECV) && is_hyp_ctxt(vcpu)) { + if (vcpu_el2_e2h_is_set(vcpu)) + tvt02 = tpt02 = true; + else + tvt = tpt = true; + } /* * We have two possibility to deal with a physical offset: @@ -792,10 +833,21 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map) if (!has_cntpoff() && timer_get_offset(map->direct_ptimer)) tpt = tpc = true; + /* + * For the poor sods that could not correctly substract one value + * from another, trap the full virtual timer and counter. + */ + if (has_broken_cntvoff() && timer_get_offset(map->direct_vtimer)) + tvt = tvc = true; + /* * Apply the enable bits that the guest hypervisor has requested for * its own guest. We can only add traps that wouldn't have been set * above. + * Implementation choices: we do not support NV when E2H=0 in the + * guest, and we don't support configuration where E2H is writable + * by the guest (either FEAT_VHE or FEAT_E2H0 is implemented, but + * not both). This simplifies the handling of the EL1NV* bits. */ if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { u64 val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); @@ -806,6 +858,9 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map) tpt |= !(val & (CNTHCTL_EL1PCEN << 10)); tpc |= !(val & (CNTHCTL_EL1PCTEN << 10)); + + tpt02 |= (val & CNTHCTL_EL1NVPCT); + tvt02 |= (val & CNTHCTL_EL1NVVCT); } /* @@ -817,6 +872,10 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map) assign_clear_set_bit(tpt, CNTHCTL_EL1PCEN << 10, set, clr); assign_clear_set_bit(tpc, CNTHCTL_EL1PCTEN << 10, set, clr); + assign_clear_set_bit(tvt, CNTHCTL_EL1TVT, clr, set); + assign_clear_set_bit(tvc, CNTHCTL_EL1TVCT, clr, set); + assign_clear_set_bit(tvt02, CNTHCTL_EL1NVVCT, clr, set); + assign_clear_set_bit(tpt02, CNTHCTL_EL1NVPCT, clr, set); /* This only happens on VHE, so use the CNTHCTL_EL2 accessor. */ sysreg_clear_set(cnthctl_el2, clr, set); @@ -905,6 +964,54 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) kvm_timer_blocking(vcpu); } +void kvm_timer_sync_nested(struct kvm_vcpu *vcpu) +{ + /* + * When NV2 is on, guest hypervisors have their EL1 timer register + * accesses redirected to the VNCR page. Any guest action taken on + * the timer is postponed until the next exit, leading to a very + * poor quality of emulation. + * + * This is an unmitigated disaster, only papered over by FEAT_ECV, + * which allows trapping of the timer registers even with NV2. + * Still, this is still worse than FEAT_NV on its own. Meh. + */ + if (!vcpu_el2_e2h_is_set(vcpu)) { + if (cpus_have_final_cap(ARM64_HAS_ECV)) + return; + + /* + * A non-VHE guest hypervisor doesn't have any direct access + * to its timers: the EL2 registers trap (and the HW is + * fully emulated), while the EL0 registers access memory + * despite the access being notionally direct. Boo. + * + * We update the hardware timer registers with the + * latest value written by the guest to the VNCR page + * and let the hardware take care of the rest. + */ + write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CTL_EL0), SYS_CNTV_CTL); + write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0), SYS_CNTV_CVAL); + write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CTL_EL0), SYS_CNTP_CTL); + write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0), SYS_CNTP_CVAL); + } else { + /* + * For a VHE guest hypervisor, the EL2 state is directly + * stored in the host EL1 timers, while the emulated EL0 + * state is stored in the VNCR page. The latter could have + * been updated behind our back, and we must reset the + * emulation of the timers. + */ + struct timer_map map; + get_timer_map(vcpu, &map); + + soft_timer_cancel(&map.emul_vtimer->hrtimer); + soft_timer_cancel(&map.emul_ptimer->hrtimer); + timer_emulate(map.emul_vtimer); + timer_emulate(map.emul_ptimer); + } +} + /* * With a userspace irqchip we have to check if the guest de-asserted the * timer and if so, unmask the timer irq signal on the host interrupt @@ -1363,6 +1470,37 @@ static int kvm_irq_init(struct arch_timer_kvm_info *info) return 0; } +static void kvm_timer_handle_errata(void) +{ + u64 mmfr0, mmfr1, mmfr4; + + /* + * CNTVOFF_EL2 is broken on some implementations. For those, we trap + * all virtual timer/counter accesses, requiring FEAT_ECV. + * + * However, a hypervisor supporting nesting is likely to mitigate the + * erratum at L0, and not require other levels to mitigate it (which + * would otherwise be a terrible performance sink due to trap + * amplification). + * + * Given that the affected HW implements both FEAT_VHE and FEAT_E2H0, + * and that NV is likely not to (because of limitations of the + * architecture), only enable the workaround when FEAT_VHE and + * FEAT_E2H0 are both detected. Time will tell if this actually holds. + */ + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); + mmfr4 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR4_EL1); + if (SYS_FIELD_GET(ID_AA64MMFR1_EL1, VH, mmfr1) && + !SYS_FIELD_GET(ID_AA64MMFR4_EL1, E2H0, mmfr4) && + SYS_FIELD_GET(ID_AA64MMFR0_EL1, ECV, mmfr0) && + (has_vhe() || has_hvhe()) && + cpus_have_final_cap(ARM64_WORKAROUND_QCOM_ORYON_CNTVOFF)) { + static_branch_enable(&broken_cntvoff_key); + kvm_info("Broken CNTVOFF_EL2, trapping virtual timer\n"); + } +} + int __init kvm_timer_hyp_init(bool has_gic) { struct arch_timer_kvm_info *info; @@ -1431,6 +1569,7 @@ int __init kvm_timer_hyp_init(bool has_gic) goto out_free_vtimer_irq; } + kvm_timer_handle_errata(); return 0; out_free_ptimer_irq: diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a102c3aebdbc..646e806c6ca6 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -61,7 +61,7 @@ static enum kvm_wfx_trap_policy kvm_wfe_trap_policy __read_mostly = KVM_WFX_NOTR DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector); -DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); +DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_base); DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); DECLARE_KVM_NVHE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); @@ -80,31 +80,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } -/* - * This functions as an allow-list of protected VM capabilities. - * Features not explicitly allowed by this function are denied. - */ -static bool pkvm_ext_allowed(struct kvm *kvm, long ext) -{ - switch (ext) { - case KVM_CAP_IRQCHIP: - case KVM_CAP_ARM_PSCI: - case KVM_CAP_ARM_PSCI_0_2: - case KVM_CAP_NR_VCPUS: - case KVM_CAP_MAX_VCPUS: - case KVM_CAP_MAX_VCPU_ID: - case KVM_CAP_MSI_DEVID: - case KVM_CAP_ARM_VM_IPA_SIZE: - case KVM_CAP_ARM_PMU_V3: - case KVM_CAP_ARM_SVE: - case KVM_CAP_ARM_PTRAUTH_ADDRESS: - case KVM_CAP_ARM_PTRAUTH_GENERIC: - return true; - default: - return false; - } -} - int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -113,7 +88,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, if (cap->flags) return -EINVAL; - if (kvm_vm_is_protected(kvm) && !pkvm_ext_allowed(kvm, cap->cap)) + if (kvm_vm_is_protected(kvm) && !kvm_pvm_ext_allowed(cap->cap)) return -EINVAL; switch (cap->cap) { @@ -311,7 +286,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r; - if (kvm && kvm_vm_is_protected(kvm) && !pkvm_ext_allowed(kvm, ext)) + if (kvm && kvm_vm_is_protected(kvm) && !kvm_pvm_ext_allowed(ext)) return 0; switch (ext) { @@ -476,8 +451,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_pmu_vcpu_init(vcpu); - kvm_arm_reset_debug_ptr(vcpu); - kvm_arm_pvtime_vcpu_init(&vcpu->arch); vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; @@ -502,7 +475,10 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); + if (!is_protected_kvm_enabled()) + kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); + else + free_hyp_memcache(&vcpu->arch.pkvm_memcache); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); kvm_vgic_vcpu_destroy(vcpu); @@ -574,6 +550,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) struct kvm_s2_mmu *mmu; int *last_ran; + if (is_protected_kvm_enabled()) + goto nommu; + if (vcpu_has_nv(vcpu)) kvm_vcpu_load_hw_mmu(vcpu); @@ -594,10 +573,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) *last_ran = vcpu->vcpu_idx; } +nommu: vcpu->cpu = cpu; kvm_vgic_load(vcpu); kvm_timer_vcpu_load(vcpu); + kvm_vcpu_load_debug(vcpu); if (has_vhe()) kvm_vcpu_load_vhe(vcpu); kvm_arch_vcpu_load_fp(vcpu); @@ -617,7 +598,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu_set_pauth_traps(vcpu); - kvm_arch_vcpu_load_debug_state_flags(vcpu); + if (is_protected_kvm_enabled()) { + kvm_call_hyp_nvhe(__pkvm_vcpu_load, + vcpu->kvm->arch.pkvm.handle, + vcpu->vcpu_idx, vcpu->arch.hcr_el2); + kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, + &vcpu->arch.vgic_cpu.vgic_v3); + } if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus)) vcpu_set_on_unsupported_cpu(vcpu); @@ -625,7 +612,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { - kvm_arch_vcpu_put_debug_state_flags(vcpu); + if (is_protected_kvm_enabled()) { + kvm_call_hyp(__vgic_v3_save_vmcr_aprs, + &vcpu->arch.vgic_cpu.vgic_v3); + kvm_call_hyp_nvhe(__pkvm_vcpu_put); + } + + kvm_vcpu_put_debug(vcpu); kvm_arch_vcpu_put_fp(vcpu); if (has_vhe()) kvm_vcpu_put_vhe(vcpu); @@ -808,8 +801,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) kvm_init_mpidr_data(kvm); - kvm_arm_vcpu_init_debug(vcpu); - if (likely(irqchip_in_kernel(kvm))) { /* * Map the VGIC hardware resources before running a vcpu the @@ -1187,7 +1178,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) continue; } - kvm_arm_setup_debug(vcpu); kvm_arch_vcpu_ctxflush_fp(vcpu); /************************************************************** @@ -1204,8 +1194,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * Back from guest *************************************************************/ - kvm_arm_clear_debug(vcpu); - /* * We must sync the PMU state before the vgic state so * that the vgic can properly sample the updated state of the @@ -1228,6 +1216,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) if (unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_timer_sync_user(vcpu); + if (is_hyp_ctxt(vcpu)) + kvm_timer_sync_nested(vcpu); + kvm_arch_vcpu_ctxsync_fp(vcpu); /* @@ -1571,7 +1562,6 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, } vcpu_reset_hcr(vcpu); - vcpu->arch.cptr_el2 = kvm_get_reset_cptr_el2(vcpu); /* * Handle the "start in power-off" case. @@ -1990,8 +1980,7 @@ static int kvm_init_vector_slots(void) static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); - u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); - unsigned long tcr; + unsigned long tcr, ips; /* * Calculate the raw per-cpu offset without a translation from the @@ -2005,6 +1994,7 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) params->mair_el2 = read_sysreg(mair_el1); tcr = read_sysreg(tcr_el1); + ips = FIELD_GET(TCR_IPS_MASK, tcr); if (cpus_have_final_cap(ARM64_KVM_HVHE)) { tcr |= TCR_EPD1_MASK; } else { @@ -2014,8 +2004,8 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) tcr &= ~TCR_T0SZ_MASK; tcr |= TCR_T0SZ(hyp_va_bits); tcr &= ~TCR_EL2_PS_MASK; - tcr |= FIELD_PREP(TCR_EL2_PS_MASK, kvm_get_parange(mmfr0)); - if (kvm_lpa2_is_enabled()) + tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips); + if (lpa2_is_enabled()) tcr |= TCR_EL2_DS; params->tcr_el2 = tcr; @@ -2109,6 +2099,7 @@ static void cpu_set_hyp_vector(void) static void cpu_hyp_init_context(void) { kvm_init_host_cpu_context(host_data_ptr(host_ctxt)); + kvm_init_host_debug_data(); if (!is_kernel_in_hyp_mode()) cpu_init_hyp_mode(); @@ -2117,7 +2108,6 @@ static void cpu_hyp_init_context(void) static void cpu_hyp_init_features(void) { cpu_set_hyp_vector(); - kvm_arm_init_debug(); if (is_kernel_in_hyp_mode()) kvm_timer_init_vhe(); @@ -2339,7 +2329,7 @@ static void __init teardown_hyp_mode(void) free_hyp_pgds(); for_each_possible_cpu(cpu) { - free_page(per_cpu(kvm_arm_hyp_stack_page, cpu)); + free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT); free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order()); if (free_sve) { @@ -2527,15 +2517,15 @@ static int __init init_hyp_mode(void) * Allocate stack pages for Hypervisor-mode */ for_each_possible_cpu(cpu) { - unsigned long stack_page; + unsigned long stack_base; - stack_page = __get_free_page(GFP_KERNEL); - if (!stack_page) { + stack_base = __get_free_pages(GFP_KERNEL, NVHE_STACK_SHIFT - PAGE_SHIFT); + if (!stack_base) { err = -ENOMEM; goto out_err; } - per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page; + per_cpu(kvm_arm_hyp_stack_base, cpu) = stack_base; } /* @@ -2604,9 +2594,9 @@ static int __init init_hyp_mode(void) */ for_each_possible_cpu(cpu) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); - char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu); + char *stack_base = (char *)per_cpu(kvm_arm_hyp_stack_base, cpu); - err = create_hyp_stack(__pa(stack_page), ¶ms->stack_hyp_va); + err = create_hyp_stack(__pa(stack_base), ¶ms->stack_hyp_va); if (err) { kvm_err("Cannot map hyp stack\n"); goto out_err; @@ -2618,7 +2608,7 @@ static int __init init_hyp_mode(void) * __hyp_pa() won't do the right thing there, since the stack * has been mapped in the flexible private VA space. */ - params->stack_pa = __pa(stack_page); + params->stack_pa = __pa(stack_base); } for_each_possible_cpu(cpu) { diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 3d7eb395e33d..3a96c96816e9 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -111,7 +111,7 @@ static bool s1pie_enabled(struct kvm_vcpu *vcpu, enum trans_regime regime) return vcpu_read_sys_reg(vcpu, TCR2_EL2) & TCR2_EL2_PIE; case TR_EL10: return (__vcpu_sys_reg(vcpu, HCRX_EL2) & HCRX_EL2_TCR2En) && - (__vcpu_sys_reg(vcpu, TCR2_EL1) & TCR2_EL1x_PIE); + (__vcpu_sys_reg(vcpu, TCR2_EL1) & TCR2_EL1_PIE); default: BUG(); } @@ -140,8 +140,8 @@ static void compute_s1poe(struct kvm_vcpu *vcpu, struct s1_walk_info *wi) } val = __vcpu_sys_reg(vcpu, TCR2_EL1); - wi->poe = val & TCR2_EL1x_POE; - wi->e0poe = val & TCR2_EL1x_E0POE; + wi->poe = val & TCR2_EL1_POE; + wi->e0poe = val & TCR2_EL1_E0POE; } } diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index ce8886122ed3..0e4c805e7e89 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -3,7 +3,8 @@ * Debug and Guest Debug support * * Copyright (C) 2015 - Linaro Ltd - * Author: Alex Bennée + * Authors: Alex Bennée + * Oliver Upton */ #include @@ -14,72 +15,6 @@ #include #include -#include "trace.h" - -/* These are the bits of MDSCR_EL1 we may manipulate */ -#define MDSCR_EL1_DEBUG_MASK (DBG_MDSCR_SS | \ - DBG_MDSCR_KDE | \ - DBG_MDSCR_MDE) - -static DEFINE_PER_CPU(u64, mdcr_el2); - -/* - * save/restore_guest_debug_regs - * - * For some debug operations we need to tweak some guest registers. As - * a result we need to save the state of those registers before we - * make those modifications. - * - * Guest access to MDSCR_EL1 is trapped by the hypervisor and handled - * after we have restored the preserved value to the main context. - * - * When single-step is enabled by userspace, we tweak PSTATE.SS on every - * guest entry. Preserve PSTATE.SS so we can restore the original value - * for the vcpu after the single-step is disabled. - */ -static void save_guest_debug_regs(struct kvm_vcpu *vcpu) -{ - u64 val = vcpu_read_sys_reg(vcpu, MDSCR_EL1); - - vcpu->arch.guest_debug_preserved.mdscr_el1 = val; - - trace_kvm_arm_set_dreg32("Saved MDSCR_EL1", - vcpu->arch.guest_debug_preserved.mdscr_el1); - - vcpu->arch.guest_debug_preserved.pstate_ss = - (*vcpu_cpsr(vcpu) & DBG_SPSR_SS); -} - -static void restore_guest_debug_regs(struct kvm_vcpu *vcpu) -{ - u64 val = vcpu->arch.guest_debug_preserved.mdscr_el1; - - vcpu_write_sys_reg(vcpu, val, MDSCR_EL1); - - trace_kvm_arm_set_dreg32("Restored MDSCR_EL1", - vcpu_read_sys_reg(vcpu, MDSCR_EL1)); - - if (vcpu->arch.guest_debug_preserved.pstate_ss) - *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; - else - *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; -} - -/** - * kvm_arm_init_debug - grab what we need for debug - * - * Currently the sole task of this function is to retrieve the initial - * value of mdcr_el2 so we can preserve MDCR_EL2.HPMN which has - * presumably been set-up by some knowledgeable bootcode. - * - * It is called once per-cpu during CPU hyp initialisation. - */ - -void kvm_arm_init_debug(void) -{ - __this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2)); -} - /** * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value * @@ -95,11 +30,14 @@ void kvm_arm_init_debug(void) */ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) { + preempt_disable(); + /* * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK * to disable guest access to the profiling and trace buffers */ - vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; + vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN, + *host_data_ptr(nr_event_counters)); vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | MDCR_EL2_TTRF | @@ -113,233 +51,215 @@ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; /* - * Trap debug register access when one of the following is true: - * - Userspace is using the hardware to debug the guest - * (KVM_GUESTDBG_USE_HW is set). - * - The guest is not using debug (DEBUG_DIRTY clear). - * - The guest has enabled the OS Lock (debug exceptions are blocked). + * Trap debug registers if the guest doesn't have ownership of them. */ - if ((vcpu->guest_debug & KVM_GUESTDBG_USE_HW) || - !vcpu_get_flag(vcpu, DEBUG_DIRTY) || - kvm_vcpu_os_lock_enabled(vcpu)) + if (!kvm_guest_owns_debug_regs(vcpu)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; - trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); -} + /* Write MDCR_EL2 directly if we're already at EL2 */ + if (has_vhe()) + write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); -/** - * kvm_arm_vcpu_init_debug - setup vcpu debug traps - * - * @vcpu: the vcpu pointer - * - * Set vcpu initial mdcr_el2 value. - */ -void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - kvm_arm_setup_mdcr_el2(vcpu); preempt_enable(); } -/** - * kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state - * @vcpu: the vcpu pointer - */ - -void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) +void kvm_init_host_debug_data(void) { - vcpu->arch.debug_ptr = &vcpu->arch.vcpu_debug_state; -} + u64 dfr0 = read_sysreg(id_aa64dfr0_el1); -/** - * kvm_arm_setup_debug - set up debug related stuff - * - * @vcpu: the vcpu pointer - * - * This is called before each entry into the hypervisor to setup any - * debug related registers. - * - * Additionally, KVM only traps guest accesses to the debug registers if - * the guest is not actively using them (see the DEBUG_DIRTY - * flag on vcpu->arch.iflags). Since the guest must not interfere - * with the hardware state when debugging the guest, we must ensure that - * trapping is enabled whenever we are debugging the guest using the - * debug registers. - */ + if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0) + *host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N, + read_sysreg(pmcr_el0)); -void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) -{ - unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2; + *host_data_ptr(debug_brps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr0); + *host_data_ptr(debug_wrps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr0); - trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug); - - kvm_arm_setup_mdcr_el2(vcpu); - - /* Check if we need to use the debug registers. */ - if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { - /* Save guest debug state */ - save_guest_debug_regs(vcpu); - - /* - * Single Step (ARM ARM D2.12.3 The software step state - * machine) - * - * If we are doing Single Step we need to manipulate - * the guest's MDSCR_EL1.SS and PSTATE.SS. Once the - * step has occurred the hypervisor will trap the - * debug exception and we return to userspace. - * - * If the guest attempts to single step its userspace - * we would have to deal with a trapped exception - * while in the guest kernel. Because this would be - * hard to unwind we suppress the guest's ability to - * do so by masking MDSCR_EL.SS. - * - * This confuses guest debuggers which use - * single-step behind the scenes but everything - * returns to normal once the host is no longer - * debugging the system. - */ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - /* - * If the software step state at the last guest exit - * was Active-pending, we don't set DBG_SPSR_SS so - * that the state is maintained (to not run another - * single-step until the pending Software Step - * exception is taken). - */ - if (!vcpu_get_flag(vcpu, DBG_SS_ACTIVE_PENDING)) - *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; - else - *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; - - mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); - mdscr |= DBG_MDSCR_SS; - vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); - } else { - mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); - mdscr &= ~DBG_MDSCR_SS; - vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); - } - - trace_kvm_arm_set_dreg32("SPSR_EL2", *vcpu_cpsr(vcpu)); - - /* - * HW Breakpoints and watchpoints - * - * We simply switch the debug_ptr to point to our new - * external_debug_state which has been populated by the - * debug ioctl. The existing DEBUG_DIRTY mechanism ensures - * the registers are updated on the world switch. - */ - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { - /* Enable breakpoints/watchpoints */ - mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); - mdscr |= DBG_MDSCR_MDE; - vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); - - vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state; - vcpu_set_flag(vcpu, DEBUG_DIRTY); - - trace_kvm_arm_set_regset("BKPTS", get_num_brps(), - &vcpu->arch.debug_ptr->dbg_bcr[0], - &vcpu->arch.debug_ptr->dbg_bvr[0]); - - trace_kvm_arm_set_regset("WAPTS", get_num_wrps(), - &vcpu->arch.debug_ptr->dbg_wcr[0], - &vcpu->arch.debug_ptr->dbg_wvr[0]); - - /* - * The OS Lock blocks debug exceptions in all ELs when it is - * enabled. If the guest has enabled the OS Lock, constrain its - * effects to the guest. Emulate the behavior by clearing - * MDSCR_EL1.MDE. In so doing, we ensure that host debug - * exceptions are unaffected by guest configuration of the OS - * Lock. - */ - } else if (kvm_vcpu_os_lock_enabled(vcpu)) { - mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); - mdscr &= ~DBG_MDSCR_MDE; - vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); - } - } - - BUG_ON(!vcpu->guest_debug && - vcpu->arch.debug_ptr != &vcpu->arch.vcpu_debug_state); - - /* If KDE or MDE are set, perform a full save/restore cycle. */ - if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE)) - vcpu_set_flag(vcpu, DEBUG_DIRTY); - - /* Write mdcr_el2 changes since vcpu_load on VHE systems */ - if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2) - write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); - - trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1)); -} - -void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) -{ - trace_kvm_arm_clear_debug(vcpu->guest_debug); - - /* - * Restore the guest's debug registers if we were using them. - */ - if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)) - /* - * Mark the vcpu as ACTIVE_PENDING - * until Software Step exception is taken. - */ - vcpu_set_flag(vcpu, DBG_SS_ACTIVE_PENDING); - } - - restore_guest_debug_regs(vcpu); - - /* - * If we were using HW debug we need to restore the - * debug_ptr to the guest debug state. - */ - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { - kvm_arm_reset_debug_ptr(vcpu); - - trace_kvm_arm_set_regset("BKPTS", get_num_brps(), - &vcpu->arch.debug_ptr->dbg_bcr[0], - &vcpu->arch.debug_ptr->dbg_bvr[0]); - - trace_kvm_arm_set_regset("WAPTS", get_num_wrps(), - &vcpu->arch.debug_ptr->dbg_wcr[0], - &vcpu->arch.debug_ptr->dbg_wvr[0]); - } - } -} - -void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu) -{ - u64 dfr0; - - /* For VHE, there is nothing to do */ if (has_vhe()) return; - dfr0 = read_sysreg(id_aa64dfr0_el1); - /* - * If SPE is present on this CPU and is available at current EL, - * we may need to check if the host state needs to be saved. - */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && - !(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(PMBIDR_EL1_P_SHIFT))) - vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_SPE); + !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P)) + host_data_set_flag(HAS_SPE); - /* Check if we have TRBE implemented and available at the host */ - if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && - !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) - vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_TRBE); + if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceFilt_SHIFT)) { + /* Force disable trace in protected mode in case of no TRBE */ + if (is_protected_kvm_enabled()) + host_data_set_flag(EL1_TRACING_CONFIGURED); + + if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && + !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) + host_data_set_flag(HAS_TRBE); + } } -void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu) +/* + * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host + * has taken over MDSCR_EL1. + * + * - Userspace is single-stepping the guest, and MDSCR_EL1.SS is forced to 1. + * + * - Userspace is using the breakpoint/watchpoint registers to debug the + * guest, and MDSCR_EL1.MDE is forced to 1. + * + * - The guest has enabled the OS Lock, and KVM is forcing MDSCR_EL1.MDE to 0, + * masking all debug exceptions affected by the OS Lock. + */ +static void setup_external_mdscr(struct kvm_vcpu *vcpu) { - vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_SPE); - vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_TRBE); + /* + * Use the guest's MDSCR_EL1 as a starting point, since there are + * several other features controlled by MDSCR_EL1 that are not relevant + * to the host. + * + * Clear the bits that KVM may use which also satisfies emulation of + * the OS Lock as MDSCR_EL1.MDE is cleared. + */ + u64 mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1) & ~(MDSCR_EL1_SS | + MDSCR_EL1_MDE | + MDSCR_EL1_KDE); + + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + mdscr |= MDSCR_EL1_SS; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) + mdscr |= MDSCR_EL1_MDE | MDSCR_EL1_KDE; + + vcpu->arch.external_mdscr_el1 = mdscr; } + +void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) +{ + u64 mdscr; + + /* Must be called before kvm_vcpu_load_vhe() */ + KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm); + + /* + * Determine which of the possible debug states we're in: + * + * - VCPU_DEBUG_HOST_OWNED: KVM has taken ownership of the guest's + * breakpoint/watchpoint registers, or needs to use MDSCR_EL1 to do + * software step or emulate the effects of the OS Lock being enabled. + * + * - VCPU_DEBUG_GUEST_OWNED: The guest has debug exceptions enabled, and + * the breakpoint/watchpoint registers need to be loaded eagerly. + * + * - VCPU_DEBUG_FREE: Neither of the above apply, no breakpoint/watchpoint + * context needs to be loaded on the CPU. + */ + if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { + vcpu->arch.debug_owner = VCPU_DEBUG_HOST_OWNED; + setup_external_mdscr(vcpu); + + /* + * Steal the guest's single-step state machine if userspace wants + * single-step the guest. + */ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + if (*vcpu_cpsr(vcpu) & DBG_SPSR_SS) + vcpu_clear_flag(vcpu, GUEST_SS_ACTIVE_PENDING); + else + vcpu_set_flag(vcpu, GUEST_SS_ACTIVE_PENDING); + + if (!vcpu_get_flag(vcpu, HOST_SS_ACTIVE_PENDING)) + *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; + else + *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; + } + } else { + mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); + + if (mdscr & (MDSCR_EL1_KDE | MDSCR_EL1_MDE)) + vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; + else + vcpu->arch.debug_owner = VCPU_DEBUG_FREE; + } + + kvm_arm_setup_mdcr_el2(vcpu); +} + +void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu) +{ + if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) + return; + + /* + * Save the host's software step state and restore the guest's before + * potentially returning to userspace. + */ + if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)) + vcpu_set_flag(vcpu, HOST_SS_ACTIVE_PENDING); + else + vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING); + + if (vcpu_get_flag(vcpu, GUEST_SS_ACTIVE_PENDING)) + *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; + else + *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; +} + +/* + * Updates ownership of the debug registers after a trapped guest access to a + * breakpoint/watchpoint register. Host ownership of the debug registers is of + * strictly higher priority, and it is the responsibility of the VMM to emulate + * guest debug exceptions in this configuration. + */ +void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu) +{ + if (kvm_host_owns_debug_regs(vcpu)) + return; + + vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; + kvm_arm_setup_mdcr_el2(vcpu); +} + +void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val) +{ + if (val & OSLAR_EL1_OSLK) + __vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK; + else + __vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK; + + preempt_disable(); + kvm_arch_vcpu_put(vcpu); + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); +} + +void kvm_enable_trbe(void) +{ + if (has_vhe() || is_protected_kvm_enabled() || + WARN_ON_ONCE(preemptible())) + return; + + host_data_set_flag(TRBE_ENABLED); +} +EXPORT_SYMBOL_GPL(kvm_enable_trbe); + +void kvm_disable_trbe(void) +{ + if (has_vhe() || is_protected_kvm_enabled() || + WARN_ON_ONCE(preemptible())) + return; + + host_data_clear_flag(TRBE_ENABLED); +} +EXPORT_SYMBOL_GPL(kvm_disable_trbe); + +void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest) +{ + if (is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) + return; + + if (has_vhe()) { + write_sysreg_s(trfcr_while_in_guest, SYS_TRFCR_EL12); + return; + } + + *host_data_ptr(trfcr_while_in_guest) = trfcr_while_in_guest; + if (read_sysreg_s(SYS_TRFCR_EL1) != trfcr_while_in_guest) + host_data_set_flag(EL1_TRACING_CONFIGURED); + else + host_data_clear_flag(EL1_TRACING_CONFIGURED); +} +EXPORT_SYMBOL_GPL(kvm_tracing_set_el1_configuration); diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 1ffbfd1c3cf2..607d37bab70b 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -89,6 +89,9 @@ enum cgt_group_id { CGT_HCRX_EnFPM, CGT_HCRX_TCR2En, + CGT_CNTHCTL_EL1TVT, + CGT_CNTHCTL_EL1TVCT, + CGT_ICH_HCR_TC, CGT_ICH_HCR_TALL0, CGT_ICH_HCR_TALL1, @@ -124,6 +127,8 @@ enum cgt_group_id { __COMPLEX_CONDITIONS__, CGT_CNTHCTL_EL1PCTEN = __COMPLEX_CONDITIONS__, CGT_CNTHCTL_EL1PTEN, + CGT_CNTHCTL_EL1NVPCT, + CGT_CNTHCTL_EL1NVVCT, CGT_CPTR_TTA, CGT_MDCR_HPMN, @@ -393,6 +398,18 @@ static const struct trap_bits coarse_trap_bits[] = { .mask = HCRX_EL2_TCR2En, .behaviour = BEHAVE_FORWARD_RW, }, + [CGT_CNTHCTL_EL1TVT] = { + .index = CNTHCTL_EL2, + .value = CNTHCTL_EL1TVT, + .mask = CNTHCTL_EL1TVT, + .behaviour = BEHAVE_FORWARD_RW, + }, + [CGT_CNTHCTL_EL1TVCT] = { + .index = CNTHCTL_EL2, + .value = CNTHCTL_EL1TVCT, + .mask = CNTHCTL_EL1TVCT, + .behaviour = BEHAVE_FORWARD_READ, + }, [CGT_ICH_HCR_TC] = { .index = ICH_HCR_EL2, .value = ICH_HCR_TC, @@ -487,6 +504,32 @@ static enum trap_behaviour check_cnthctl_el1pten(struct kvm_vcpu *vcpu) return BEHAVE_FORWARD_RW; } +static bool is_nested_nv2_guest(struct kvm_vcpu *vcpu) +{ + u64 val; + + val = __vcpu_sys_reg(vcpu, HCR_EL2); + return ((val & (HCR_E2H | HCR_TGE | HCR_NV2 | HCR_NV1 | HCR_NV)) == (HCR_E2H | HCR_NV2 | HCR_NV)); +} + +static enum trap_behaviour check_cnthctl_el1nvpct(struct kvm_vcpu *vcpu) +{ + if (!is_nested_nv2_guest(vcpu) || + !(__vcpu_sys_reg(vcpu, CNTHCTL_EL2) & CNTHCTL_EL1NVPCT)) + return BEHAVE_HANDLE_LOCALLY; + + return BEHAVE_FORWARD_RW; +} + +static enum trap_behaviour check_cnthctl_el1nvvct(struct kvm_vcpu *vcpu) +{ + if (!is_nested_nv2_guest(vcpu) || + !(__vcpu_sys_reg(vcpu, CNTHCTL_EL2) & CNTHCTL_EL1NVVCT)) + return BEHAVE_HANDLE_LOCALLY; + + return BEHAVE_FORWARD_RW; +} + static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu) { u64 val = __vcpu_sys_reg(vcpu, CPTR_EL2); @@ -494,7 +537,7 @@ static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu) if (!vcpu_el2_e2h_is_set(vcpu)) val = translate_cptr_el2_to_cpacr_el1(val); - if (val & CPACR_ELx_TTA) + if (val & CPACR_EL1_TTA) return BEHAVE_FORWARD_RW; return BEHAVE_HANDLE_LOCALLY; @@ -534,6 +577,8 @@ static enum trap_behaviour check_mdcr_hpmn(struct kvm_vcpu *vcpu) static const complex_condition_check ccc[] = { CCC(CGT_CNTHCTL_EL1PCTEN, check_cnthctl_el1pcten), CCC(CGT_CNTHCTL_EL1PTEN, check_cnthctl_el1pten), + CCC(CGT_CNTHCTL_EL1NVPCT, check_cnthctl_el1nvpct), + CCC(CGT_CNTHCTL_EL1NVVCT, check_cnthctl_el1nvvct), CCC(CGT_CPTR_TTA, check_cptr_tta), CCC(CGT_MDCR_HPMN, check_mdcr_hpmn), }; @@ -850,11 +895,15 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = { SYS_CNTHP_CVAL_EL2, CGT_HCR_NV), SR_RANGE_TRAP(SYS_CNTHV_TVAL_EL2, SYS_CNTHV_CVAL_EL2, CGT_HCR_NV), - /* All _EL02, _EL12 registers */ + /* All _EL02, _EL12 registers up to CNTKCTL_EL12*/ SR_RANGE_TRAP(sys_reg(3, 5, 0, 0, 0), sys_reg(3, 5, 10, 15, 7), CGT_HCR_NV), SR_RANGE_TRAP(sys_reg(3, 5, 12, 0, 0), - sys_reg(3, 5, 14, 15, 7), CGT_HCR_NV), + sys_reg(3, 5, 14, 1, 0), CGT_HCR_NV), + SR_TRAP(SYS_CNTP_CTL_EL02, CGT_CNTHCTL_EL1NVPCT), + SR_TRAP(SYS_CNTP_CVAL_EL02, CGT_CNTHCTL_EL1NVPCT), + SR_TRAP(SYS_CNTV_CTL_EL02, CGT_CNTHCTL_EL1NVVCT), + SR_TRAP(SYS_CNTV_CVAL_EL02, CGT_CNTHCTL_EL1NVVCT), SR_TRAP(OP_AT_S1E2R, CGT_HCR_NV), SR_TRAP(OP_AT_S1E2W, CGT_HCR_NV), SR_TRAP(OP_AT_S12E1R, CGT_HCR_NV), @@ -1184,6 +1233,11 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = { SR_TRAP(SYS_CNTP_CTL_EL0, CGT_CNTHCTL_EL1PTEN), SR_TRAP(SYS_CNTPCT_EL0, CGT_CNTHCTL_EL1PCTEN), SR_TRAP(SYS_CNTPCTSS_EL0, CGT_CNTHCTL_EL1PCTEN), + SR_TRAP(SYS_CNTV_TVAL_EL0, CGT_CNTHCTL_EL1TVT), + SR_TRAP(SYS_CNTV_CVAL_EL0, CGT_CNTHCTL_EL1TVT), + SR_TRAP(SYS_CNTV_CTL_EL0, CGT_CNTHCTL_EL1TVT), + SR_TRAP(SYS_CNTVCT_EL0, CGT_CNTHCTL_EL1TVCT), + SR_TRAP(SYS_CNTVCTSS_EL0, CGT_CNTHCTL_EL1TVCT), SR_TRAP(SYS_FPMR, CGT_HCRX_EnFPM), /* * IMPDEF choice: @@ -2345,14 +2399,14 @@ inject: return true; } -static bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit) +static bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg, u64 control_bit) { bool control_bit_set; if (!vcpu_has_nv(vcpu)) return false; - control_bit_set = __vcpu_sys_reg(vcpu, HCR_EL2) & control_bit; + control_bit_set = __vcpu_sys_reg(vcpu, reg) & control_bit; if (!is_hyp_ctxt(vcpu) && control_bit_set) { kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu)); return true; @@ -2360,9 +2414,24 @@ static bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit) return false; } +static bool forward_hcr_traps(struct kvm_vcpu *vcpu, u64 control_bit) +{ + return __forward_traps(vcpu, HCR_EL2, control_bit); +} + bool forward_smc_trap(struct kvm_vcpu *vcpu) { - return forward_traps(vcpu, HCR_TSC); + return forward_hcr_traps(vcpu, HCR_TSC); +} + +static bool forward_mdcr_traps(struct kvm_vcpu *vcpu, u64 control_bit) +{ + return __forward_traps(vcpu, MDCR_EL2, control_bit); +} + +bool forward_debug_exception(struct kvm_vcpu *vcpu) +{ + return forward_mdcr_traps(vcpu, MDCR_EL2_TDE); } static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr) @@ -2406,7 +2475,7 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) * Forward this trap to the virtual EL2 if the virtual * HCR_EL2.NV bit is set and this is coming from !EL2. */ - if (forward_traps(vcpu, HCR_NV)) + if (forward_hcr_traps(vcpu, HCR_NV)) return; spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2); diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index ea5484ce1f3b..4d3d1a2eb157 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -65,14 +65,14 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) *host_data_ptr(fpsimd_state) = kern_hyp_va(¤t->thread.uw.fpsimd_state); *host_data_ptr(fpmr_ptr) = kern_hyp_va(¤t->thread.uw.fpmr); - vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); + host_data_clear_flag(HOST_SVE_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) - vcpu_set_flag(vcpu, HOST_SVE_ENABLED); + host_data_set_flag(HOST_SVE_ENABLED); if (system_supports_sme()) { - vcpu_clear_flag(vcpu, HOST_SME_ENABLED); + host_data_clear_flag(HOST_SME_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) - vcpu_set_flag(vcpu, HOST_SME_ENABLED); + host_data_set_flag(HOST_SME_ENABLED); /* * If PSTATE.SM is enabled then save any pending FP @@ -168,8 +168,8 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) */ if (has_vhe() && system_supports_sme()) { /* Also restore EL0 state seen on entry */ - if (vcpu_get_flag(vcpu, HOST_SME_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN); + if (host_data_test_flag(HOST_SME_ENABLED)) + sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN); else sysreg_clear_set(CPACR_EL1, CPACR_EL1_SMEN_EL0EN, @@ -227,7 +227,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) * for EL0. To avoid spurious traps, restore the trap state * seen by kvm_arch_vcpu_load_fp(): */ - if (vcpu_get_flag(vcpu, HOST_SVE_ENABLED)) + if (host_data_test_flag(HOST_SVE_ENABLED)) sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN); else sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 12dad841f2a5..2196979a24a3 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -917,31 +917,24 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - int ret = 0; - trace_kvm_set_guest_debug(vcpu, dbg->control); - if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) { - ret = -EINVAL; - goto out; - } + if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) + return -EINVAL; - if (dbg->control & KVM_GUESTDBG_ENABLE) { - vcpu->guest_debug = dbg->control; - - /* Hardware assisted Break and Watch points */ - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { - vcpu->arch.external_debug_state = dbg->arch; - } - - } else { - /* If not enabled clear all flags */ + if (!(dbg->control & KVM_GUESTDBG_ENABLE)) { vcpu->guest_debug = 0; - vcpu_clear_flag(vcpu, DBG_SS_ACTIVE_PENDING); + vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING); + return 0; } -out: - return ret; + vcpu->guest_debug = dbg->control; + + /* Hardware assisted Break and Watch points */ + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) + vcpu->arch.external_debug_state = dbg->arch; + + return 0; } int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index d7c2990e7c9e..512d152233ff 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -183,6 +183,9 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu) struct kvm_run *run = vcpu->run; u64 esr = kvm_vcpu_get_esr(vcpu); + if (!vcpu->guest_debug && forward_debug_exception(vcpu)) + return 1; + run->exit_reason = KVM_EXIT_DEBUG; run->debug.arch.hsr = lower_32_bits(esr); run->debug.arch.hsr_high = upper_32_bits(esr); @@ -193,7 +196,7 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu) run->debug.arch.far = vcpu->arch.fault.far_el2; break; case ESR_ELx_EC_SOFTSTP_LOW: - vcpu_clear_flag(vcpu, DBG_SS_ACTIVE_PENDING); + *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; break; } diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h index d00093699aaf..502a5b73ee70 100644 --- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h @@ -88,15 +88,26 @@ default: write_debug(ptr[0], reg, 0); \ } +static struct kvm_guest_debug_arch *__vcpu_debug_regs(struct kvm_vcpu *vcpu) +{ + switch (vcpu->arch.debug_owner) { + case VCPU_DEBUG_FREE: + WARN_ON_ONCE(1); + fallthrough; + case VCPU_DEBUG_GUEST_OWNED: + return &vcpu->arch.vcpu_debug_state; + case VCPU_DEBUG_HOST_OWNED: + return &vcpu->arch.external_debug_state; + } + + return NULL; +} + static void __debug_save_state(struct kvm_guest_debug_arch *dbg, struct kvm_cpu_context *ctxt) { - u64 aa64dfr0; - int brps, wrps; - - aa64dfr0 = read_sysreg(id_aa64dfr0_el1); - brps = (aa64dfr0 >> 12) & 0xf; - wrps = (aa64dfr0 >> 20) & 0xf; + int brps = *host_data_ptr(debug_brps); + int wrps = *host_data_ptr(debug_wrps); save_debug(dbg->dbg_bcr, dbgbcr, brps); save_debug(dbg->dbg_bvr, dbgbvr, brps); @@ -109,13 +120,8 @@ static void __debug_save_state(struct kvm_guest_debug_arch *dbg, static void __debug_restore_state(struct kvm_guest_debug_arch *dbg, struct kvm_cpu_context *ctxt) { - u64 aa64dfr0; - int brps, wrps; - - aa64dfr0 = read_sysreg(id_aa64dfr0_el1); - - brps = (aa64dfr0 >> 12) & 0xf; - wrps = (aa64dfr0 >> 20) & 0xf; + int brps = *host_data_ptr(debug_brps); + int wrps = *host_data_ptr(debug_wrps); restore_debug(dbg->dbg_bcr, dbgbcr, brps); restore_debug(dbg->dbg_bvr, dbgbvr, brps); @@ -132,13 +138,13 @@ static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu) struct kvm_guest_debug_arch *host_dbg; struct kvm_guest_debug_arch *guest_dbg; - if (!vcpu_get_flag(vcpu, DEBUG_DIRTY)) + if (!kvm_debug_regs_in_use(vcpu)) return; host_ctxt = host_data_ptr(host_ctxt); guest_ctxt = &vcpu->arch.ctxt; host_dbg = host_data_ptr(host_debug_state.regs); - guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr); + guest_dbg = __vcpu_debug_regs(vcpu); __debug_save_state(host_dbg, host_ctxt); __debug_restore_state(guest_dbg, guest_ctxt); @@ -151,18 +157,16 @@ static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu) struct kvm_guest_debug_arch *host_dbg; struct kvm_guest_debug_arch *guest_dbg; - if (!vcpu_get_flag(vcpu, DEBUG_DIRTY)) + if (!kvm_debug_regs_in_use(vcpu)) return; host_ctxt = host_data_ptr(host_ctxt); guest_ctxt = &vcpu->arch.ctxt; host_dbg = host_data_ptr(host_debug_state.regs); - guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr); + guest_dbg = __vcpu_debug_regs(vcpu); __debug_save_state(guest_dbg, guest_ctxt); __debug_restore_state(host_dbg, host_ctxt); - - vcpu_clear_flag(vcpu, DEBUG_DIRTY); } #endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */ diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 34f53707892d..f838a45665f2 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -419,9 +419,9 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) /* First disable enough traps to allow us to update the registers */ if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve())) - cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN); + cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN); else - cpacr_clear_set(0, CPACR_ELx_FPEN); + cpacr_clear_set(0, CPACR_EL1_FPEN); isb(); /* Write out the host state if it's in the registers */ @@ -501,7 +501,12 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu) return true; } -static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu) +static inline u64 compute_counter_value(struct arch_timer_context *ctxt) +{ + return arch_timer_read_cntpct_el0() - timer_get_offset(ctxt); +} + +static bool kvm_handle_cntxct(struct kvm_vcpu *vcpu) { struct arch_timer_context *ctxt; u32 sysreg; @@ -511,18 +516,19 @@ static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu) * We only get here for 64bit guests, 32bit guests will hit * the long and winding road all the way to the standard * handling. Yes, it sucks to be irrelevant. + * + * Also, we only deal with non-hypervisor context here (either + * an EL1 guest, or a non-HYP context of an EL2 guest). */ + if (is_hyp_ctxt(vcpu)) + return false; + sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); switch (sysreg) { case SYS_CNTPCT_EL0: case SYS_CNTPCTSS_EL0: if (vcpu_has_nv(vcpu)) { - if (is_hyp_ctxt(vcpu)) { - ctxt = vcpu_hptimer(vcpu); - break; - } - /* Check for guest hypervisor trapping */ val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); if (!vcpu_el2_e2h_is_set(vcpu)) @@ -534,16 +540,23 @@ static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu) ctxt = vcpu_ptimer(vcpu); break; + case SYS_CNTVCT_EL0: + case SYS_CNTVCTSS_EL0: + if (vcpu_has_nv(vcpu)) { + /* Check for guest hypervisor trapping */ + val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); + + if (val & CNTHCTL_EL1TVCT) + return false; + } + + ctxt = vcpu_vtimer(vcpu); + break; default: return false; } - val = arch_timer_read_cntpct_el0(); - - if (ctxt->offset.vm_offset) - val -= *kern_hyp_va(ctxt->offset.vm_offset); - if (ctxt->offset.vcpu_offset) - val -= *kern_hyp_va(ctxt->offset.vcpu_offset); + val = compute_counter_value(ctxt); vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val); __kvm_skip_instr(vcpu); @@ -588,7 +601,7 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) __vgic_v3_perform_cpuif_access(vcpu) == 1) return true; - if (kvm_hyp_handle_cntpct(vcpu)) + if (kvm_handle_cntxct(vcpu)) return true; return false; diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index a651c43ad679..76ff095c6b6e 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -18,9 +18,34 @@ static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt); +static inline struct kvm_vcpu *ctxt_to_vcpu(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt->__hyp_running_vcpu; + + if (!vcpu) + vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt); + + return vcpu; +} + +static inline bool ctxt_is_guest(struct kvm_cpu_context *ctxt) +{ + return host_data_ptr(host_ctxt) != ctxt; +} + +static inline u64 *ctxt_mdscr_el1(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt_to_vcpu(ctxt); + + if (ctxt_is_guest(ctxt) && kvm_host_owns_debug_regs(vcpu)) + return &vcpu->arch.external_mdscr_el1; + + return &ctxt_sys_reg(ctxt, MDSCR_EL1); +} + static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt) { - ctxt_sys_reg(ctxt, MDSCR_EL1) = read_sysreg(mdscr_el1); + *ctxt_mdscr_el1(ctxt) = read_sysreg(mdscr_el1); // POR_EL0 can affect uaccess, so must be saved/restored early. if (ctxt_has_s1poe(ctxt)) @@ -33,16 +58,6 @@ static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt) ctxt_sys_reg(ctxt, TPIDRRO_EL0) = read_sysreg(tpidrro_el0); } -static inline struct kvm_vcpu *ctxt_to_vcpu(struct kvm_cpu_context *ctxt) -{ - struct kvm_vcpu *vcpu = ctxt->__hyp_running_vcpu; - - if (!vcpu) - vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt); - - return vcpu; -} - static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt) { struct kvm_vcpu *vcpu = ctxt_to_vcpu(ctxt); @@ -139,7 +154,7 @@ static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) { - write_sysreg(ctxt_sys_reg(ctxt, MDSCR_EL1), mdscr_el1); + write_sysreg(*ctxt_mdscr_el1(ctxt), mdscr_el1); // POR_EL0 can affect uaccess, so must be saved/restored early. if (ctxt_has_s1poe(ctxt)) @@ -283,7 +298,7 @@ static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu) __vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2); __vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2); - if (has_vhe() || vcpu_get_flag(vcpu, DEBUG_DIRTY)) + if (has_vhe() || kvm_debug_regs_in_use(vcpu)) __vcpu_sys_reg(vcpu, DBGVCR32_EL2) = read_sysreg(dbgvcr32_el2); } @@ -300,7 +315,7 @@ static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu) write_sysreg(__vcpu_sys_reg(vcpu, DACR32_EL2), dacr32_el2); write_sysreg(__vcpu_sys_reg(vcpu, IFSR32_EL2), ifsr32_el2); - if (has_vhe() || vcpu_get_flag(vcpu, DEBUG_DIRTY)) + if (has_vhe() || kvm_debug_regs_in_use(vcpu)) write_sysreg(__vcpu_sys_reg(vcpu, DBGVCR32_EL2), dbgvcr32_el2); } diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h deleted file mode 100644 index f957890c7e38..000000000000 --- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h +++ /dev/null @@ -1,223 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2021 Google LLC - * Author: Fuad Tabba - */ - -#ifndef __ARM64_KVM_FIXED_CONFIG_H__ -#define __ARM64_KVM_FIXED_CONFIG_H__ - -#include - -/* - * This file contains definitions for features to be allowed or restricted for - * guest virtual machines, depending on the mode KVM is running in and on the - * type of guest that is running. - * - * The ALLOW masks represent a bitmask of feature fields that are allowed - * without any restrictions as long as they are supported by the system. - * - * The RESTRICT_UNSIGNED masks, if present, represent unsigned fields for - * features that are restricted to support at most the specified feature. - * - * If a feature field is not present in either, than it is not supported. - * - * The approach taken for protected VMs is to allow features that are: - * - Needed by common Linux distributions (e.g., floating point) - * - Trivial to support, e.g., supporting the feature does not introduce or - * require tracking of additional state in KVM - * - Cannot be trapped or prevent the guest from using anyway - */ - -/* - * Allow for protected VMs: - * - Floating-point and Advanced SIMD - * - Data Independent Timing - * - Spectre/Meltdown Mitigation - */ -#define PVM_ID_AA64PFR0_ALLOW (\ - ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_FP) | \ - ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AdvSIMD) | \ - ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_DIT) | \ - ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | \ - ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3) \ - ) - -/* - * Restrict to the following *unsigned* features for protected VMs: - * - AArch64 guests only (no support for AArch32 guests): - * AArch32 adds complexity in trap handling, emulation, condition codes, - * etc... - * - RAS (v1) - * Supported by KVM - */ -#define PVM_ID_AA64PFR0_RESTRICT_UNSIGNED (\ - SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL0, IMP) | \ - SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL1, IMP) | \ - SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL2, IMP) | \ - SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL3, IMP) | \ - SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, RAS, IMP) \ - ) - -/* - * Allow for protected VMs: - * - Branch Target Identification - * - Speculative Store Bypassing - */ -#define PVM_ID_AA64PFR1_ALLOW (\ - ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_BT) | \ - ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SSBS) \ - ) - -#define PVM_ID_AA64PFR2_ALLOW 0ULL - -/* - * Allow for protected VMs: - * - Mixed-endian - * - Distinction between Secure and Non-secure Memory - * - Mixed-endian at EL0 only - * - Non-context synchronizing exception entry and exit - */ -#define PVM_ID_AA64MMFR0_ALLOW (\ - ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_BIGEND) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_SNSMEM) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_BIGENDEL0) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_EXS) \ - ) - -/* - * Restrict to the following *unsigned* features for protected VMs: - * - 40-bit IPA - * - 16-bit ASID - */ -#define PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED (\ - FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_PARANGE), ID_AA64MMFR0_EL1_PARANGE_40) | \ - FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_ASIDBITS), ID_AA64MMFR0_EL1_ASIDBITS_16) \ - ) - -/* - * Allow for protected VMs: - * - Hardware translation table updates to Access flag and Dirty state - * - Number of VMID bits from CPU - * - Hierarchical Permission Disables - * - Privileged Access Never - * - SError interrupt exceptions from speculative reads - * - Enhanced Translation Synchronization - * - Control for cache maintenance permission - */ -#define PVM_ID_AA64MMFR1_ALLOW (\ - ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_VMIDBits) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HPDS) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_PAN) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_SpecSEI) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_ETS) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_CMOW) \ - ) - -/* - * Allow for protected VMs: - * - Common not Private translations - * - User Access Override - * - IESB bit in the SCTLR_ELx registers - * - Unaligned single-copy atomicity and atomic functions - * - ESR_ELx.EC value on an exception by read access to feature ID space - * - TTL field in address operations. - * - Break-before-make sequences when changing translation block size - * - E0PDx mechanism - */ -#define PVM_ID_AA64MMFR2_ALLOW (\ - ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_CnP) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_UAO) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_IESB) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_AT) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_IDS) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_TTL) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_BBM) | \ - ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_E0PD) \ - ) - -#define PVM_ID_AA64MMFR3_ALLOW (0ULL) - -/* - * No support for Scalable Vectors for protected VMs: - * Requires additional support from KVM, e.g., context-switching and - * trapping at EL2 - */ -#define PVM_ID_AA64ZFR0_ALLOW (0ULL) - -/* - * No support for debug, including breakpoints, and watchpoints for protected - * VMs: - * The Arm architecture mandates support for at least the Armv8 debug - * architecture, which would include at least 2 hardware breakpoints and - * watchpoints. Providing that support to protected guests adds - * considerable state and complexity. Therefore, the reserved value of 0 is - * used for debug-related fields. - */ -#define PVM_ID_AA64DFR0_ALLOW (0ULL) -#define PVM_ID_AA64DFR1_ALLOW (0ULL) - -/* - * No support for implementation defined features. - */ -#define PVM_ID_AA64AFR0_ALLOW (0ULL) -#define PVM_ID_AA64AFR1_ALLOW (0ULL) - -/* - * No restrictions on instructions implemented in AArch64. - */ -#define PVM_ID_AA64ISAR0_ALLOW (\ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_AES) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA1) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA2) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_CRC32) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RDM) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA3) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SM3) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SM4) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_DP) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_FHM) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_TS) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_TLB) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RNDR) \ - ) - -/* Restrict pointer authentication to the basic version. */ -#define PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED (\ - FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA), ID_AA64ISAR1_EL1_APA_PAuth) | \ - FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API), ID_AA64ISAR1_EL1_API_PAuth) \ - ) - -#define PVM_ID_AA64ISAR2_RESTRICT_UNSIGNED (\ - FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3), ID_AA64ISAR2_EL1_APA3_PAuth) \ - ) - -#define PVM_ID_AA64ISAR1_ALLOW (\ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_DPB) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_JSCVT) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_FCMA) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_LRCPC) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_FRINTTS) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_SB) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_SPECRES) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_BF16) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_DGH) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_I8MM) \ - ) - -#define PVM_ID_AA64ISAR2_ALLOW (\ - ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_ATS1A)| \ - ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3) | \ - ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_MOPS) \ - ) - -u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id); -bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code); -bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code); -int kvm_check_pvm_sysreg_table(void); - -#endif /* __ARM64_KVM_FIXED_CONFIG_H__ */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h index 97c527ef53c2..3766333bace9 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h +++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h @@ -7,7 +7,7 @@ #include #include -#define HYP_NO_ORDER USHRT_MAX +#define HYP_NO_ORDER ((u8)(~0)) struct hyp_pool { /* @@ -19,11 +19,11 @@ struct hyp_pool { struct list_head free_area[NR_PAGE_ORDERS]; phys_addr_t range_start; phys_addr_t range_end; - unsigned short max_order; + u8 max_order; }; /* Allocation */ -void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order); +void *hyp_alloc_pages(struct hyp_pool *pool, u8 order); void hyp_split_page(struct hyp_page *page); void hyp_get_page(struct hyp_pool *pool, void *addr); void hyp_put_page(struct hyp_pool *pool, void *addr); diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h index 0972faccc2af..978f38c386ee 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h @@ -11,40 +11,10 @@ #include #include #include +#include #include #include -/* - * SW bits 0-1 are reserved to track the memory ownership state of each page: - * 00: The page is owned exclusively by the page-table owner. - * 01: The page is owned by the page-table owner, but is shared - * with another entity. - * 10: The page is shared with, but not owned by the page-table owner. - * 11: Reserved for future use (lending). - */ -enum pkvm_page_state { - PKVM_PAGE_OWNED = 0ULL, - PKVM_PAGE_SHARED_OWNED = KVM_PGTABLE_PROT_SW0, - PKVM_PAGE_SHARED_BORROWED = KVM_PGTABLE_PROT_SW1, - __PKVM_PAGE_RESERVED = KVM_PGTABLE_PROT_SW0 | - KVM_PGTABLE_PROT_SW1, - - /* Meta-states which aren't encoded directly in the PTE's SW bits */ - PKVM_NOPAGE, -}; - -#define PKVM_PAGE_STATE_PROT_MASK (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1) -static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot, - enum pkvm_page_state state) -{ - return (prot & ~PKVM_PAGE_STATE_PROT_MASK) | state; -} - -static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot) -{ - return prot & PKVM_PAGE_STATE_PROT_MASK; -} - struct host_mmu { struct kvm_arch arch; struct kvm_pgtable pgt; @@ -69,6 +39,13 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages); int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages); int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages); int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages); +int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, + enum kvm_pgtable_prot prot); +int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm); +int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot); +int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm); +int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm); +int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu); bool addr_is_memory(phys_addr_t phys); int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot); diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h index ab205c4d6774..34233d586060 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h @@ -7,9 +7,47 @@ #include +/* + * Bits 0-1 are reserved to track the memory ownership state of each page: + * 00: The page is owned exclusively by the page-table owner. + * 01: The page is owned by the page-table owner, but is shared + * with another entity. + * 10: The page is shared with, but not owned by the page-table owner. + * 11: Reserved for future use (lending). + */ +enum pkvm_page_state { + PKVM_PAGE_OWNED = 0ULL, + PKVM_PAGE_SHARED_OWNED = BIT(0), + PKVM_PAGE_SHARED_BORROWED = BIT(1), + __PKVM_PAGE_RESERVED = BIT(0) | BIT(1), + + /* Meta-states which aren't encoded directly in the PTE's SW bits */ + PKVM_NOPAGE = BIT(2), +}; +#define PKVM_PAGE_META_STATES_MASK (~__PKVM_PAGE_RESERVED) + +#define PKVM_PAGE_STATE_PROT_MASK (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1) +static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot, + enum pkvm_page_state state) +{ + prot &= ~PKVM_PAGE_STATE_PROT_MASK; + prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state); + return prot; +} + +static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot) +{ + return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot); +} + struct hyp_page { - unsigned short refcount; - unsigned short order; + u16 refcount; + u8 order; + + /* Host (non-meta) state. Guarded by the host stage-2 lock. */ + enum pkvm_page_state host_state : 8; + + u32 host_share_guest_count; }; extern u64 __hyp_vmemmap; @@ -29,7 +67,13 @@ static inline phys_addr_t hyp_virt_to_phys(void *addr) #define hyp_phys_to_pfn(phys) ((phys) >> PAGE_SHIFT) #define hyp_pfn_to_phys(pfn) ((phys_addr_t)((pfn) << PAGE_SHIFT)) -#define hyp_phys_to_page(phys) (&hyp_vmemmap[hyp_phys_to_pfn(phys)]) + +static inline struct hyp_page *hyp_phys_to_page(phys_addr_t phys) +{ + BUILD_BUG_ON(sizeof(struct hyp_page) != sizeof(u64)); + return &hyp_vmemmap[hyp_phys_to_pfn(phys)]; +} + #define hyp_virt_to_page(virt) hyp_phys_to_page(__hyp_pa(virt)) #define hyp_virt_to_pfn(virt) hyp_phys_to_pfn(__hyp_pa(virt)) diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h index 24a9a8330d19..e42bf68c8848 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h @@ -20,6 +20,12 @@ struct pkvm_hyp_vcpu { /* Backpointer to the host's (untrusted) vCPU instance. */ struct kvm_vcpu *host_vcpu; + + /* + * If this hyp vCPU is loaded, then this is a backpointer to the + * per-cpu pointer tracking us. Otherwise, NULL if not loaded. + */ + struct pkvm_hyp_vcpu **loaded_hyp_vcpu; }; /* @@ -47,6 +53,8 @@ struct pkvm_hyp_vm { struct pkvm_hyp_vcpu *vcpus[]; }; +extern hyp_spinlock_t vm_table_lock; + static inline struct pkvm_hyp_vm * pkvm_hyp_vcpu_to_hyp_vm(struct pkvm_hyp_vcpu *hyp_vcpu) { @@ -58,6 +66,11 @@ static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu) return vcpu_is_protected(&hyp_vcpu->vcpu); } +static inline bool pkvm_hyp_vm_is_protected(struct pkvm_hyp_vm *hyp_vm) +{ + return kvm_vm_is_protected(&hyp_vm->kvm); +} + void pkvm_hyp_vm_table_init(void *tbl); int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva, @@ -69,5 +82,15 @@ int __pkvm_teardown_vm(pkvm_handle_t handle); struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, unsigned int vcpu_idx); void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu); +struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void); + +struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle); +struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle); +void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm); + +bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code); +bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code); +void kvm_init_pvm_id_regs(struct kvm_vcpu *vcpu); +int kvm_check_pvm_sysreg_table(void); #endif /* __ARM64_KVM_NVHE_PKVM_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c index 53efda0235cf..2f4a4f5036bb 100644 --- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c @@ -51,42 +51,55 @@ static void __debug_restore_spe(u64 pmscr_el1) write_sysreg_el1(pmscr_el1, SYS_PMSCR); } -static void __debug_save_trace(u64 *trfcr_el1) +static void __trace_do_switch(u64 *saved_trfcr, u64 new_trfcr) { - *trfcr_el1 = 0; - - /* Check if the TRBE is enabled */ - if (!(read_sysreg_s(SYS_TRBLIMITR_EL1) & TRBLIMITR_EL1_E)) - return; - /* - * Prohibit trace generation while we are in guest. - * Since access to TRFCR_EL1 is trapped, the guest can't - * modify the filtering set by the host. - */ - *trfcr_el1 = read_sysreg_el1(SYS_TRFCR); - write_sysreg_el1(0, SYS_TRFCR); - isb(); - /* Drain the trace buffer to memory */ - tsb_csync(); + *saved_trfcr = read_sysreg_el1(SYS_TRFCR); + write_sysreg_el1(new_trfcr, SYS_TRFCR); } -static void __debug_restore_trace(u64 trfcr_el1) +static bool __trace_needs_drain(void) { - if (!trfcr_el1) - return; + if (is_protected_kvm_enabled() && host_data_test_flag(HAS_TRBE)) + return read_sysreg_s(SYS_TRBLIMITR_EL1) & TRBLIMITR_EL1_E; - /* Restore trace filter controls */ - write_sysreg_el1(trfcr_el1, SYS_TRFCR); + return host_data_test_flag(TRBE_ENABLED); +} + +static bool __trace_needs_switch(void) +{ + return host_data_test_flag(TRBE_ENABLED) || + host_data_test_flag(EL1_TRACING_CONFIGURED); +} + +static void __trace_switch_to_guest(void) +{ + /* Unsupported with TRBE so disable */ + if (host_data_test_flag(TRBE_ENABLED)) + *host_data_ptr(trfcr_while_in_guest) = 0; + + __trace_do_switch(host_data_ptr(host_debug_state.trfcr_el1), + *host_data_ptr(trfcr_while_in_guest)); + + if (__trace_needs_drain()) { + isb(); + tsb_csync(); + } +} + +static void __trace_switch_to_host(void) +{ + __trace_do_switch(host_data_ptr(trfcr_while_in_guest), + *host_data_ptr(host_debug_state.trfcr_el1)); } void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu) { /* Disable and flush SPE data generation */ - if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE)) + if (host_data_test_flag(HAS_SPE)) __debug_save_spe(host_data_ptr(host_debug_state.pmscr_el1)); - /* Disable and flush Self-Hosted Trace generation */ - if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE)) - __debug_save_trace(host_data_ptr(host_debug_state.trfcr_el1)); + + if (__trace_needs_switch()) + __trace_switch_to_guest(); } void __debug_switch_to_guest(struct kvm_vcpu *vcpu) @@ -96,18 +109,13 @@ void __debug_switch_to_guest(struct kvm_vcpu *vcpu) void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu) { - if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE)) + if (host_data_test_flag(HAS_SPE)) __debug_restore_spe(*host_data_ptr(host_debug_state.pmscr_el1)); - if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE)) - __debug_restore_trace(*host_data_ptr(host_debug_state.trfcr_el1)); + if (__trace_needs_switch()) + __trace_switch_to_host(); } void __debug_switch_to_host(struct kvm_vcpu *vcpu) { __debug_switch_to_host_common(vcpu); } - -u64 __kvm_get_mdcr_el2(void) -{ - return read_sysreg(mdcr_el2); -} diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 3d610fc51f4d..58f0cb2298cc 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -188,12 +188,12 @@ SYM_FUNC_END(__host_hvc) /* * Test whether the SP has overflowed, without corrupting a GPR. - * nVHE hypervisor stacks are aligned so that the PAGE_SHIFT bit + * nVHE hypervisor stacks are aligned so that the NVHE_STACK_SHIFT bit * of SP should always be 1. */ add sp, sp, x0 // sp' = sp + x0 sub x0, sp, x0 // x0' = sp' - x0 = (sp + x0) - x0 = sp - tbz x0, #PAGE_SHIFT, .L__hyp_sp_overflow\@ + tbz x0, #NVHE_STACK_SHIFT, .L__hyp_sp_overflow\@ sub x0, sp, x0 // x0'' = sp' - x0' = (sp + x0) - sp = x0 sub sp, sp, x0 // sp'' = sp' - x0 = (sp + x0) - x0 = sp diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 6aa0b13d86e5..5c134520e180 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -68,7 +68,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) if (!guest_owns_fp_regs()) return; - cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN); + cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN); isb(); if (vcpu_has_sve(vcpu)) @@ -103,8 +103,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) /* Limit guest vector length to the maximum supported by the host. */ hyp_vcpu->vcpu.arch.sve_max_vl = min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl); - hyp_vcpu->vcpu.arch.hw_mmu = host_vcpu->arch.hw_mmu; - hyp_vcpu->vcpu.arch.mdcr_el2 = host_vcpu->arch.mdcr_el2; hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE); hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) & @@ -112,8 +110,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) hyp_vcpu->vcpu.arch.iflags = host_vcpu->arch.iflags; - hyp_vcpu->vcpu.arch.debug_ptr = kern_hyp_va(host_vcpu->arch.debug_ptr); - hyp_vcpu->vcpu.arch.vsesr_el2 = host_vcpu->arch.vsesr_el2; hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3 = host_vcpu->arch.vgic_cpu.vgic_v3; @@ -141,16 +137,46 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i]; } +static void handle___pkvm_vcpu_load(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(unsigned int, vcpu_idx, host_ctxt, 2); + DECLARE_REG(u64, hcr_el2, host_ctxt, 3); + struct pkvm_hyp_vcpu *hyp_vcpu; + + if (!is_protected_kvm_enabled()) + return; + + hyp_vcpu = pkvm_load_hyp_vcpu(handle, vcpu_idx); + if (!hyp_vcpu) + return; + + if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) { + /* Propagate WFx trapping flags */ + hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWE | HCR_TWI); + hyp_vcpu->vcpu.arch.hcr_el2 |= hcr_el2 & (HCR_TWE | HCR_TWI); + } +} + +static void handle___pkvm_vcpu_put(struct kvm_cpu_context *host_ctxt) +{ + struct pkvm_hyp_vcpu *hyp_vcpu; + + if (!is_protected_kvm_enabled()) + return; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (hyp_vcpu) + pkvm_put_hyp_vcpu(hyp_vcpu); +} + static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 1); int ret; - host_vcpu = kern_hyp_va(host_vcpu); - if (unlikely(is_protected_kvm_enabled())) { - struct pkvm_hyp_vcpu *hyp_vcpu; - struct kvm *host_kvm; + struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); /* * KVM (and pKVM) doesn't support SME guests for now, and @@ -163,9 +189,6 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) goto out; } - host_kvm = kern_hyp_va(host_vcpu->kvm); - hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle, - host_vcpu->vcpu_idx); if (!hyp_vcpu) { ret = -EINVAL; goto out; @@ -176,12 +199,141 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) ret = __kvm_vcpu_run(&hyp_vcpu->vcpu); sync_hyp_vcpu(hyp_vcpu); - pkvm_put_hyp_vcpu(hyp_vcpu); } else { /* The host is fully trusted, run its vCPU directly. */ - ret = __kvm_vcpu_run(host_vcpu); + ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu)); } +out: + cpu_reg(host_ctxt, 1) = ret; +} +static int pkvm_refill_memcache(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + return refill_memcache(&hyp_vcpu->vcpu.arch.pkvm_memcache, + host_vcpu->arch.pkvm_memcache.nr_pages, + &host_vcpu->arch.pkvm_memcache); +} + +static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, pfn, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3); + struct pkvm_hyp_vcpu *hyp_vcpu; + int ret = -EINVAL; + + if (!is_protected_kvm_enabled()) + goto out; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + goto out; + + ret = pkvm_refill_memcache(hyp_vcpu); + if (ret) + goto out; + + ret = __pkvm_host_share_guest(pfn, gfn, hyp_vcpu, prot); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + struct pkvm_hyp_vm *hyp_vm; + int ret = -EINVAL; + + if (!is_protected_kvm_enabled()) + goto out; + + hyp_vm = get_np_pkvm_hyp_vm(handle); + if (!hyp_vm) + goto out; + + ret = __pkvm_host_unshare_guest(gfn, hyp_vm); + put_pkvm_hyp_vm(hyp_vm); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_relax_perms_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, gfn, host_ctxt, 1); + DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 2); + struct pkvm_hyp_vcpu *hyp_vcpu; + int ret = -EINVAL; + + if (!is_protected_kvm_enabled()) + goto out; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + goto out; + + ret = __pkvm_host_relax_perms_guest(gfn, hyp_vcpu, prot); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + struct pkvm_hyp_vm *hyp_vm; + int ret = -EINVAL; + + if (!is_protected_kvm_enabled()) + goto out; + + hyp_vm = get_np_pkvm_hyp_vm(handle); + if (!hyp_vm) + goto out; + + ret = __pkvm_host_wrprotect_guest(gfn, hyp_vm); + put_pkvm_hyp_vm(hyp_vm); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + DECLARE_REG(bool, mkold, host_ctxt, 3); + struct pkvm_hyp_vm *hyp_vm; + int ret = -EINVAL; + + if (!is_protected_kvm_enabled()) + goto out; + + hyp_vm = get_np_pkvm_hyp_vm(handle); + if (!hyp_vm) + goto out; + + ret = __pkvm_host_test_clear_young_guest(gfn, mkold, hyp_vm); + put_pkvm_hyp_vm(hyp_vm); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_mkyoung_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, gfn, host_ctxt, 1); + struct pkvm_hyp_vcpu *hyp_vcpu; + int ret = -EINVAL; + + if (!is_protected_kvm_enabled()) + goto out; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + goto out; + + ret = __pkvm_host_mkyoung_guest(gfn, hyp_vcpu); out: cpu_reg(host_ctxt, 1) = ret; } @@ -233,6 +385,22 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt) __kvm_tlb_flush_vmid(kern_hyp_va(mmu)); } +static void handle___pkvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + struct pkvm_hyp_vm *hyp_vm; + + if (!is_protected_kvm_enabled()) + return; + + hyp_vm = get_np_pkvm_hyp_vm(handle); + if (!hyp_vm) + return; + + __kvm_tlb_flush_vmid(&hyp_vm->kvm.arch.mmu); + put_pkvm_hyp_vm(hyp_vm); +} + static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1); @@ -264,11 +432,6 @@ static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt) __vgic_v3_init_lrs(); } -static void handle___kvm_get_mdcr_el2(struct kvm_cpu_context *host_ctxt) -{ - cpu_reg(host_ctxt, 1) = __kvm_get_mdcr_el2(); -} - static void handle___vgic_v3_save_vmcr_aprs(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1); @@ -384,7 +547,6 @@ typedef void (*hcall_t)(struct kvm_cpu_context *); static const hcall_t host_hcall[] = { /* ___kvm_hyp_init */ - HANDLE_FUNC(__kvm_get_mdcr_el2), HANDLE_FUNC(__pkvm_init), HANDLE_FUNC(__pkvm_create_private_mapping), HANDLE_FUNC(__pkvm_cpu_set_vector), @@ -395,6 +557,12 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__pkvm_host_share_hyp), HANDLE_FUNC(__pkvm_host_unshare_hyp), + HANDLE_FUNC(__pkvm_host_share_guest), + HANDLE_FUNC(__pkvm_host_unshare_guest), + HANDLE_FUNC(__pkvm_host_relax_perms_guest), + HANDLE_FUNC(__pkvm_host_wrprotect_guest), + HANDLE_FUNC(__pkvm_host_test_clear_young_guest), + HANDLE_FUNC(__pkvm_host_mkyoung_guest), HANDLE_FUNC(__kvm_adjust_pc), HANDLE_FUNC(__kvm_vcpu_run), HANDLE_FUNC(__kvm_flush_vm_context), @@ -409,6 +577,9 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__pkvm_init_vm), HANDLE_FUNC(__pkvm_init_vcpu), HANDLE_FUNC(__pkvm_teardown_vm), + HANDLE_FUNC(__pkvm_vcpu_load), + HANDLE_FUNC(__pkvm_vcpu_put), + HANDLE_FUNC(__pkvm_tlb_flush_vmid), }; static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) @@ -481,7 +652,7 @@ void handle_trap(struct kvm_cpu_context *host_ctxt) handle_host_smc(host_ctxt); break; case ESR_ELx_EC_SVE: - cpacr_clear_set(0, CPACR_ELx_ZEN); + cpacr_clear_set(0, CPACR_EL1_ZEN); isb(); sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index caba3e4bd09e..7ad7b133b81a 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -201,8 +201,8 @@ static void *guest_s2_zalloc_page(void *mc) memset(addr, 0, PAGE_SIZE); p = hyp_virt_to_page(addr); - memset(p, 0, sizeof(*p)); p->refcount = 1; + p->order = 0; return addr; } @@ -268,6 +268,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd) void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc) { + struct hyp_page *page; void *addr; /* Dump all pgtable pages in the hyp_pool */ @@ -279,7 +280,9 @@ void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc) /* Drain the hyp_pool into the memcache */ addr = hyp_alloc_pages(&vm->pool, 0); while (addr) { - memset(hyp_virt_to_page(addr), 0, sizeof(struct hyp_page)); + page = hyp_virt_to_page(addr); + page->refcount = 0; + page->order = 0; push_hyp_memcache(mc, addr, hyp_virt_to_phys); WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(addr), 1)); addr = hyp_alloc_pages(&vm->pool, 0); @@ -382,19 +385,28 @@ bool addr_is_memory(phys_addr_t phys) return !!find_mem_range(phys, &range); } -static bool addr_is_allowed_memory(phys_addr_t phys) +static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range) +{ + return range->start <= addr && addr < range->end; +} + +static int check_range_allowed_memory(u64 start, u64 end) { struct memblock_region *reg; struct kvm_mem_range range; - reg = find_mem_range(phys, &range); + /* + * Callers can't check the state of a range that overlaps memory and + * MMIO regions, so ensure [start, end[ is in the same kvm_mem_range. + */ + reg = find_mem_range(start, &range); + if (!is_in_mem_range(end - 1, &range)) + return -EINVAL; - return reg && !(reg->flags & MEMBLOCK_NOMAP); -} + if (!reg || reg->flags & MEMBLOCK_NOMAP) + return -EPERM; -static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range) -{ - return range->start <= addr && addr < range->end; + return 0; } static bool range_is_memory(u64 start, u64 end) @@ -454,8 +466,10 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) if (kvm_pte_valid(pte)) return -EAGAIN; - if (pte) + if (pte) { + WARN_ON(addr_is_memory(addr) && hyp_phys_to_page(addr)->host_state != PKVM_NOPAGE); return -EPERM; + } do { u64 granule = kvm_granule_size(level); @@ -477,10 +491,33 @@ int host_stage2_idmap_locked(phys_addr_t addr, u64 size, return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot); } +static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_state state) +{ + phys_addr_t end = addr + size; + + for (; addr < end; addr += PAGE_SIZE) + hyp_phys_to_page(addr)->host_state = state; +} + int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id) { - return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt, - addr, size, &host_s2_pool, owner_id); + int ret; + + if (!addr_is_memory(addr)) + return -EPERM; + + ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt, + addr, size, &host_s2_pool, owner_id); + if (ret) + return ret; + + /* Don't forget to update the vmemmap tracking for the host */ + if (owner_id == PKVM_ID_HOST) + __host_update_page_state(addr, size, PKVM_PAGE_OWNED); + else + __host_update_page_state(addr, size, PKVM_NOPAGE); + + return 0; } static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot) @@ -546,39 +583,6 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt) BUG_ON(ret && ret != -EAGAIN); } -struct pkvm_mem_transition { - u64 nr_pages; - - struct { - enum pkvm_component_id id; - /* Address in the initiator's address space */ - u64 addr; - - union { - struct { - /* Address in the completer's address space */ - u64 completer_addr; - } host; - struct { - u64 completer_addr; - } hyp; - }; - } initiator; - - struct { - enum pkvm_component_id id; - } completer; -}; - -struct pkvm_mem_share { - const struct pkvm_mem_transition tx; - const enum kvm_pgtable_prot completer_prot; -}; - -struct pkvm_mem_donation { - const struct pkvm_mem_transition tx; -}; - struct check_walk_data { enum pkvm_page_state desired; enum pkvm_page_state (*get_page_state)(kvm_pte_t pte, u64 addr); @@ -604,115 +608,38 @@ static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size, return kvm_pgtable_walk(pgt, addr, size, &walker); } -static enum pkvm_page_state host_get_page_state(kvm_pte_t pte, u64 addr) -{ - if (!addr_is_allowed_memory(addr)) - return PKVM_NOPAGE; - - if (!kvm_pte_valid(pte) && pte) - return PKVM_NOPAGE; - - return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); -} - static int __host_check_page_state_range(u64 addr, u64 size, enum pkvm_page_state state) { - struct check_walk_data d = { - .desired = state, - .get_page_state = host_get_page_state, - }; + u64 end = addr + size; + int ret; + + ret = check_range_allowed_memory(addr, end); + if (ret) + return ret; hyp_assert_lock_held(&host_mmu.lock); - return check_page_state_range(&host_mmu.pgt, addr, size, &d); + for (; addr < end; addr += PAGE_SIZE) { + if (hyp_phys_to_page(addr)->host_state != state) + return -EPERM; + } + + return 0; } static int __host_set_page_state_range(u64 addr, u64 size, enum pkvm_page_state state) { - enum kvm_pgtable_prot prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, state); + if (hyp_phys_to_page(addr)->host_state == PKVM_NOPAGE) { + int ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT); - return host_stage2_idmap_locked(addr, size, prot); -} + if (ret) + return ret; + } -static int host_request_owned_transition(u64 *completer_addr, - const struct pkvm_mem_transition *tx) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - u64 addr = tx->initiator.addr; + __host_update_page_state(addr, size, state); - *completer_addr = tx->initiator.host.completer_addr; - return __host_check_page_state_range(addr, size, PKVM_PAGE_OWNED); -} - -static int host_request_unshare(u64 *completer_addr, - const struct pkvm_mem_transition *tx) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - u64 addr = tx->initiator.addr; - - *completer_addr = tx->initiator.host.completer_addr; - return __host_check_page_state_range(addr, size, PKVM_PAGE_SHARED_OWNED); -} - -static int host_initiate_share(u64 *completer_addr, - const struct pkvm_mem_transition *tx) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - u64 addr = tx->initiator.addr; - - *completer_addr = tx->initiator.host.completer_addr; - return __host_set_page_state_range(addr, size, PKVM_PAGE_SHARED_OWNED); -} - -static int host_initiate_unshare(u64 *completer_addr, - const struct pkvm_mem_transition *tx) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - u64 addr = tx->initiator.addr; - - *completer_addr = tx->initiator.host.completer_addr; - return __host_set_page_state_range(addr, size, PKVM_PAGE_OWNED); -} - -static int host_initiate_donation(u64 *completer_addr, - const struct pkvm_mem_transition *tx) -{ - u8 owner_id = tx->completer.id; - u64 size = tx->nr_pages * PAGE_SIZE; - - *completer_addr = tx->initiator.host.completer_addr; - return host_stage2_set_owner_locked(tx->initiator.addr, size, owner_id); -} - -static bool __host_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx) -{ - return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) || - tx->initiator.id != PKVM_ID_HYP); -} - -static int __host_ack_transition(u64 addr, const struct pkvm_mem_transition *tx, - enum pkvm_page_state state) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - - if (__host_ack_skip_pgtable_check(tx)) - return 0; - - return __host_check_page_state_range(addr, size, state); -} - -static int host_ack_donation(u64 addr, const struct pkvm_mem_transition *tx) -{ - return __host_ack_transition(addr, tx, PKVM_NOPAGE); -} - -static int host_complete_donation(u64 addr, const struct pkvm_mem_transition *tx) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - u8 host_id = tx->completer.id; - - return host_stage2_set_owner_locked(addr, size, host_id); + return 0; } static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte, u64 addr) @@ -735,387 +662,52 @@ static int __hyp_check_page_state_range(u64 addr, u64 size, return check_page_state_range(&pkvm_pgtable, addr, size, &d); } -static int hyp_request_donation(u64 *completer_addr, - const struct pkvm_mem_transition *tx) +static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr) { - u64 size = tx->nr_pages * PAGE_SIZE; - u64 addr = tx->initiator.addr; + if (!kvm_pte_valid(pte)) + return PKVM_NOPAGE; - *completer_addr = tx->initiator.hyp.completer_addr; - return __hyp_check_page_state_range(addr, size, PKVM_PAGE_OWNED); + return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); } -static int hyp_initiate_donation(u64 *completer_addr, - const struct pkvm_mem_transition *tx) +static int __guest_check_page_state_range(struct pkvm_hyp_vcpu *vcpu, u64 addr, + u64 size, enum pkvm_page_state state) { - u64 size = tx->nr_pages * PAGE_SIZE; - int ret; + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + struct check_walk_data d = { + .desired = state, + .get_page_state = guest_get_page_state, + }; - *completer_addr = tx->initiator.hyp.completer_addr; - ret = kvm_pgtable_hyp_unmap(&pkvm_pgtable, tx->initiator.addr, size); - return (ret != size) ? -EFAULT : 0; -} - -static bool __hyp_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx) -{ - return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) || - tx->initiator.id != PKVM_ID_HOST); -} - -static int hyp_ack_share(u64 addr, const struct pkvm_mem_transition *tx, - enum kvm_pgtable_prot perms) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - - if (perms != PAGE_HYP) - return -EPERM; - - if (__hyp_ack_skip_pgtable_check(tx)) - return 0; - - return __hyp_check_page_state_range(addr, size, PKVM_NOPAGE); -} - -static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - - if (tx->initiator.id == PKVM_ID_HOST && hyp_page_count((void *)addr)) - return -EBUSY; - - if (__hyp_ack_skip_pgtable_check(tx)) - return 0; - - return __hyp_check_page_state_range(addr, size, - PKVM_PAGE_SHARED_BORROWED); -} - -static int hyp_ack_donation(u64 addr, const struct pkvm_mem_transition *tx) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - - if (__hyp_ack_skip_pgtable_check(tx)) - return 0; - - return __hyp_check_page_state_range(addr, size, PKVM_NOPAGE); -} - -static int hyp_complete_share(u64 addr, const struct pkvm_mem_transition *tx, - enum kvm_pgtable_prot perms) -{ - void *start = (void *)addr, *end = start + (tx->nr_pages * PAGE_SIZE); - enum kvm_pgtable_prot prot; - - prot = pkvm_mkstate(perms, PKVM_PAGE_SHARED_BORROWED); - return pkvm_create_mappings_locked(start, end, prot); -} - -static int hyp_complete_unshare(u64 addr, const struct pkvm_mem_transition *tx) -{ - u64 size = tx->nr_pages * PAGE_SIZE; - int ret = kvm_pgtable_hyp_unmap(&pkvm_pgtable, addr, size); - - return (ret != size) ? -EFAULT : 0; -} - -static int hyp_complete_donation(u64 addr, - const struct pkvm_mem_transition *tx) -{ - void *start = (void *)addr, *end = start + (tx->nr_pages * PAGE_SIZE); - enum kvm_pgtable_prot prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED); - - return pkvm_create_mappings_locked(start, end, prot); -} - -static int check_share(struct pkvm_mem_share *share) -{ - const struct pkvm_mem_transition *tx = &share->tx; - u64 completer_addr; - int ret; - - switch (tx->initiator.id) { - case PKVM_ID_HOST: - ret = host_request_owned_transition(&completer_addr, tx); - break; - default: - ret = -EINVAL; - } - - if (ret) - return ret; - - switch (tx->completer.id) { - case PKVM_ID_HYP: - ret = hyp_ack_share(completer_addr, tx, share->completer_prot); - break; - case PKVM_ID_FFA: - /* - * We only check the host; the secure side will check the other - * end when we forward the FFA call. - */ - ret = 0; - break; - default: - ret = -EINVAL; - } - - return ret; -} - -static int __do_share(struct pkvm_mem_share *share) -{ - const struct pkvm_mem_transition *tx = &share->tx; - u64 completer_addr; - int ret; - - switch (tx->initiator.id) { - case PKVM_ID_HOST: - ret = host_initiate_share(&completer_addr, tx); - break; - default: - ret = -EINVAL; - } - - if (ret) - return ret; - - switch (tx->completer.id) { - case PKVM_ID_HYP: - ret = hyp_complete_share(completer_addr, tx, share->completer_prot); - break; - case PKVM_ID_FFA: - /* - * We're not responsible for any secure page-tables, so there's - * nothing to do here. - */ - ret = 0; - break; - default: - ret = -EINVAL; - } - - return ret; -} - -/* - * do_share(): - * - * The page owner grants access to another component with a given set - * of permissions. - * - * Initiator: OWNED => SHARED_OWNED - * Completer: NOPAGE => SHARED_BORROWED - */ -static int do_share(struct pkvm_mem_share *share) -{ - int ret; - - ret = check_share(share); - if (ret) - return ret; - - return WARN_ON(__do_share(share)); -} - -static int check_unshare(struct pkvm_mem_share *share) -{ - const struct pkvm_mem_transition *tx = &share->tx; - u64 completer_addr; - int ret; - - switch (tx->initiator.id) { - case PKVM_ID_HOST: - ret = host_request_unshare(&completer_addr, tx); - break; - default: - ret = -EINVAL; - } - - if (ret) - return ret; - - switch (tx->completer.id) { - case PKVM_ID_HYP: - ret = hyp_ack_unshare(completer_addr, tx); - break; - case PKVM_ID_FFA: - /* See check_share() */ - ret = 0; - break; - default: - ret = -EINVAL; - } - - return ret; -} - -static int __do_unshare(struct pkvm_mem_share *share) -{ - const struct pkvm_mem_transition *tx = &share->tx; - u64 completer_addr; - int ret; - - switch (tx->initiator.id) { - case PKVM_ID_HOST: - ret = host_initiate_unshare(&completer_addr, tx); - break; - default: - ret = -EINVAL; - } - - if (ret) - return ret; - - switch (tx->completer.id) { - case PKVM_ID_HYP: - ret = hyp_complete_unshare(completer_addr, tx); - break; - case PKVM_ID_FFA: - /* See __do_share() */ - ret = 0; - break; - default: - ret = -EINVAL; - } - - return ret; -} - -/* - * do_unshare(): - * - * The page owner revokes access from another component for a range of - * pages which were previously shared using do_share(). - * - * Initiator: SHARED_OWNED => OWNED - * Completer: SHARED_BORROWED => NOPAGE - */ -static int do_unshare(struct pkvm_mem_share *share) -{ - int ret; - - ret = check_unshare(share); - if (ret) - return ret; - - return WARN_ON(__do_unshare(share)); -} - -static int check_donation(struct pkvm_mem_donation *donation) -{ - const struct pkvm_mem_transition *tx = &donation->tx; - u64 completer_addr; - int ret; - - switch (tx->initiator.id) { - case PKVM_ID_HOST: - ret = host_request_owned_transition(&completer_addr, tx); - break; - case PKVM_ID_HYP: - ret = hyp_request_donation(&completer_addr, tx); - break; - default: - ret = -EINVAL; - } - - if (ret) - return ret; - - switch (tx->completer.id) { - case PKVM_ID_HOST: - ret = host_ack_donation(completer_addr, tx); - break; - case PKVM_ID_HYP: - ret = hyp_ack_donation(completer_addr, tx); - break; - default: - ret = -EINVAL; - } - - return ret; -} - -static int __do_donate(struct pkvm_mem_donation *donation) -{ - const struct pkvm_mem_transition *tx = &donation->tx; - u64 completer_addr; - int ret; - - switch (tx->initiator.id) { - case PKVM_ID_HOST: - ret = host_initiate_donation(&completer_addr, tx); - break; - case PKVM_ID_HYP: - ret = hyp_initiate_donation(&completer_addr, tx); - break; - default: - ret = -EINVAL; - } - - if (ret) - return ret; - - switch (tx->completer.id) { - case PKVM_ID_HOST: - ret = host_complete_donation(completer_addr, tx); - break; - case PKVM_ID_HYP: - ret = hyp_complete_donation(completer_addr, tx); - break; - default: - ret = -EINVAL; - } - - return ret; -} - -/* - * do_donate(): - * - * The page owner transfers ownership to another component, losing access - * as a consequence. - * - * Initiator: OWNED => NOPAGE - * Completer: NOPAGE => OWNED - */ -static int do_donate(struct pkvm_mem_donation *donation) -{ - int ret; - - ret = check_donation(donation); - if (ret) - return ret; - - return WARN_ON(__do_donate(donation)); + hyp_assert_lock_held(&vm->lock); + return check_page_state_range(&vm->pgt, addr, size, &d); } int __pkvm_host_share_hyp(u64 pfn) { + u64 phys = hyp_pfn_to_phys(pfn); + void *virt = __hyp_va(phys); + enum kvm_pgtable_prot prot; + u64 size = PAGE_SIZE; int ret; - u64 host_addr = hyp_pfn_to_phys(pfn); - u64 hyp_addr = (u64)__hyp_va(host_addr); - struct pkvm_mem_share share = { - .tx = { - .nr_pages = 1, - .initiator = { - .id = PKVM_ID_HOST, - .addr = host_addr, - .host = { - .completer_addr = hyp_addr, - }, - }, - .completer = { - .id = PKVM_ID_HYP, - }, - }, - .completer_prot = PAGE_HYP, - }; host_lock_component(); hyp_lock_component(); - ret = do_share(&share); + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); + if (ret) + goto unlock; + if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) { + ret = __hyp_check_page_state_range((u64)virt, size, PKVM_NOPAGE); + if (ret) + goto unlock; + } + prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED); + WARN_ON(pkvm_create_mappings_locked(virt, virt + size, prot)); + WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED)); + +unlock: hyp_unlock_component(); host_unlock_component(); @@ -1124,31 +716,29 @@ int __pkvm_host_share_hyp(u64 pfn) int __pkvm_host_unshare_hyp(u64 pfn) { + u64 phys = hyp_pfn_to_phys(pfn); + u64 virt = (u64)__hyp_va(phys); + u64 size = PAGE_SIZE; int ret; - u64 host_addr = hyp_pfn_to_phys(pfn); - u64 hyp_addr = (u64)__hyp_va(host_addr); - struct pkvm_mem_share share = { - .tx = { - .nr_pages = 1, - .initiator = { - .id = PKVM_ID_HOST, - .addr = host_addr, - .host = { - .completer_addr = hyp_addr, - }, - }, - .completer = { - .id = PKVM_ID_HYP, - }, - }, - .completer_prot = PAGE_HYP, - }; host_lock_component(); hyp_lock_component(); - ret = do_unshare(&share); + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); + if (ret) + goto unlock; + ret = __hyp_check_page_state_range(virt, size, PKVM_PAGE_SHARED_BORROWED); + if (ret) + goto unlock; + if (hyp_page_count((void *)virt)) { + ret = -EBUSY; + goto unlock; + } + WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size); + WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_OWNED)); + +unlock: hyp_unlock_component(); host_unlock_component(); @@ -1157,30 +747,29 @@ int __pkvm_host_unshare_hyp(u64 pfn) int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages) { + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE * nr_pages; + void *virt = __hyp_va(phys); + enum kvm_pgtable_prot prot; int ret; - u64 host_addr = hyp_pfn_to_phys(pfn); - u64 hyp_addr = (u64)__hyp_va(host_addr); - struct pkvm_mem_donation donation = { - .tx = { - .nr_pages = nr_pages, - .initiator = { - .id = PKVM_ID_HOST, - .addr = host_addr, - .host = { - .completer_addr = hyp_addr, - }, - }, - .completer = { - .id = PKVM_ID_HYP, - }, - }, - }; host_lock_component(); hyp_lock_component(); - ret = do_donate(&donation); + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); + if (ret) + goto unlock; + if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) { + ret = __hyp_check_page_state_range((u64)virt, size, PKVM_NOPAGE); + if (ret) + goto unlock; + } + prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED); + WARN_ON(pkvm_create_mappings_locked(virt, virt + size, prot)); + WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HYP)); + +unlock: hyp_unlock_component(); host_unlock_component(); @@ -1189,30 +778,27 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages) int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages) { + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE * nr_pages; + u64 virt = (u64)__hyp_va(phys); int ret; - u64 host_addr = hyp_pfn_to_phys(pfn); - u64 hyp_addr = (u64)__hyp_va(host_addr); - struct pkvm_mem_donation donation = { - .tx = { - .nr_pages = nr_pages, - .initiator = { - .id = PKVM_ID_HYP, - .addr = hyp_addr, - .hyp = { - .completer_addr = host_addr, - }, - }, - .completer = { - .id = PKVM_ID_HOST, - }, - }, - }; host_lock_component(); hyp_lock_component(); - ret = do_donate(&donation); + ret = __hyp_check_page_state_range(virt, size, PKVM_PAGE_OWNED); + if (ret) + goto unlock; + if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) { + ret = __host_check_page_state_range(phys, size, PKVM_NOPAGE); + if (ret) + goto unlock; + } + WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size); + WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HOST)); + +unlock: hyp_unlock_component(); host_unlock_component(); @@ -1266,22 +852,14 @@ void hyp_unpin_shared_mem(void *from, void *to) int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages) { + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE * nr_pages; int ret; - struct pkvm_mem_share share = { - .tx = { - .nr_pages = nr_pages, - .initiator = { - .id = PKVM_ID_HOST, - .addr = hyp_pfn_to_phys(pfn), - }, - .completer = { - .id = PKVM_ID_FFA, - }, - }, - }; host_lock_component(); - ret = do_share(&share); + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); + if (!ret) + ret = __host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); host_unlock_component(); return ret; @@ -1289,22 +867,213 @@ int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages) int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages) { + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE * nr_pages; int ret; - struct pkvm_mem_share share = { - .tx = { - .nr_pages = nr_pages, - .initiator = { - .id = PKVM_ID_HOST, - .addr = hyp_pfn_to_phys(pfn), - }, - .completer = { - .id = PKVM_ID_FFA, - }, - }, - }; host_lock_component(); - ret = do_unshare(&share); + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); + if (!ret) + ret = __host_set_page_state_range(phys, size, PKVM_PAGE_OWNED); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, + enum kvm_pgtable_prot prot) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 phys = hyp_pfn_to_phys(pfn); + u64 ipa = hyp_pfn_to_phys(gfn); + struct hyp_page *page; + int ret; + + if (prot & ~KVM_PGTABLE_PROT_RWX) + return -EINVAL; + + ret = check_range_allowed_memory(phys, phys + PAGE_SIZE); + if (ret) + return ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = __guest_check_page_state_range(vcpu, ipa, PAGE_SIZE, PKVM_NOPAGE); + if (ret) + goto unlock; + + page = hyp_phys_to_page(phys); + switch (page->host_state) { + case PKVM_PAGE_OWNED: + WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_OWNED)); + break; + case PKVM_PAGE_SHARED_OWNED: + if (page->host_share_guest_count) + break; + /* Only host to np-guest multi-sharing is tolerated */ + WARN_ON(1); + fallthrough; + default: + ret = -EPERM; + goto unlock; + } + + WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys, + pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED), + &vcpu->vcpu.arch.pkvm_memcache, 0)); + page->host_share_guest_count++; + +unlock: + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa) +{ + enum pkvm_page_state state; + struct hyp_page *page; + kvm_pte_t pte; + u64 phys; + s8 level; + int ret; + + ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level); + if (ret) + return ret; + if (level != KVM_PGTABLE_LAST_LEVEL) + return -E2BIG; + if (!kvm_pte_valid(pte)) + return -ENOENT; + + state = guest_get_page_state(pte, ipa); + if (state != PKVM_PAGE_SHARED_BORROWED) + return -EPERM; + + phys = kvm_pte_to_phys(pte); + ret = check_range_allowed_memory(phys, phys + PAGE_SIZE); + if (WARN_ON(ret)) + return ret; + + page = hyp_phys_to_page(phys); + if (page->host_state != PKVM_PAGE_SHARED_OWNED) + return -EPERM; + if (WARN_ON(!page->host_share_guest_count)) + return -EINVAL; + + *__phys = phys; + + return 0; +} + +int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *vm) +{ + u64 ipa = hyp_pfn_to_phys(gfn); + struct hyp_page *page; + u64 phys; + int ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = __check_host_shared_guest(vm, &phys, ipa); + if (ret) + goto unlock; + + ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, PAGE_SIZE); + if (ret) + goto unlock; + + page = hyp_phys_to_page(phys); + page->host_share_guest_count--; + if (!page->host_share_guest_count) + WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED)); + +unlock: + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 ipa = hyp_pfn_to_phys(gfn); + u64 phys; + int ret; + + if (prot & ~KVM_PGTABLE_PROT_RWX) + return -EINVAL; + + host_lock_component(); + guest_lock_component(vm); + + ret = __check_host_shared_guest(vm, &phys, ipa); + if (!ret) + ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0); + + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm) +{ + u64 ipa = hyp_pfn_to_phys(gfn); + u64 phys; + int ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = __check_host_shared_guest(vm, &phys, ipa); + if (!ret) + ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE); + + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm) +{ + u64 ipa = hyp_pfn_to_phys(gfn); + u64 phys; + int ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = __check_host_shared_guest(vm, &phys, ipa); + if (!ret) + ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold); + + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 ipa = hyp_pfn_to_phys(gfn); + u64 phys; + int ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = __check_host_shared_guest(vm, &phys, ipa); + if (!ret) + kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0); + + guest_unlock_component(vm); host_unlock_component(); return ret; diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index 8850b591d775..f41c7440b34b 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -360,10 +360,10 @@ int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr) prev_base = __io_map_base; /* - * Efficient stack verification using the PAGE_SHIFT bit implies + * Efficient stack verification using the NVHE_STACK_SHIFT bit implies * an alignment of our allocation on the order of the size. */ - size = PAGE_SIZE * 2; + size = NVHE_STACK_SIZE * 2; addr = ALIGN(__io_map_base, size); ret = __pkvm_alloc_private_va_range(addr, size); @@ -373,12 +373,12 @@ int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr) * at the higher address and leave the lower guard page * unbacked. * - * Any valid stack address now has the PAGE_SHIFT bit as 1 + * Any valid stack address now has the NVHE_STACK_SHIFT bit as 1 * and addresses corresponding to the guard page have the - * PAGE_SHIFT bit as 0 - this is used for overflow detection. + * NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection. */ - ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr + PAGE_SIZE, - PAGE_SIZE, phys, PAGE_HYP); + ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr + NVHE_STACK_SIZE, + NVHE_STACK_SIZE, phys, PAGE_HYP); if (ret) __io_map_base = prev_base; } diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c index e691290d3765..a1eb27a1a747 100644 --- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c +++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c @@ -32,7 +32,7 @@ u64 __hyp_vmemmap; */ static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool, struct hyp_page *p, - unsigned short order) + u8 order) { phys_addr_t addr = hyp_page_to_phys(p); @@ -51,7 +51,7 @@ static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool, /* Find a buddy page currently available for allocation */ static struct hyp_page *__find_buddy_avail(struct hyp_pool *pool, struct hyp_page *p, - unsigned short order) + u8 order) { struct hyp_page *buddy = __find_buddy_nocheck(pool, p, order); @@ -94,7 +94,7 @@ static void __hyp_attach_page(struct hyp_pool *pool, struct hyp_page *p) { phys_addr_t phys = hyp_page_to_phys(p); - unsigned short order = p->order; + u8 order = p->order; struct hyp_page *buddy; memset(hyp_page_to_virt(p), 0, PAGE_SIZE << p->order); @@ -129,7 +129,7 @@ insert: static struct hyp_page *__hyp_extract_page(struct hyp_pool *pool, struct hyp_page *p, - unsigned short order) + u8 order) { struct hyp_page *buddy; @@ -183,7 +183,7 @@ void hyp_get_page(struct hyp_pool *pool, void *addr) void hyp_split_page(struct hyp_page *p) { - unsigned short order = p->order; + u8 order = p->order; unsigned int i; p->order = 0; @@ -195,10 +195,10 @@ void hyp_split_page(struct hyp_page *p) } } -void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order) +void *hyp_alloc_pages(struct hyp_pool *pool, u8 order) { - unsigned short i = order; struct hyp_page *p; + u8 i = order; hyp_spin_lock(&pool->lock); diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 071993c16de8..3927fe52a3dd 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -9,7 +9,6 @@ #include -#include #include #include #include @@ -24,185 +23,10 @@ unsigned int kvm_arm_vmid_bits; unsigned int kvm_host_sve_max_vl; /* - * Set trap register values based on features in ID_AA64PFR0. + * The currently loaded hyp vCPU for each physical CPU. Used only when + * protected KVM is enabled, but for both protected and non-protected VMs. */ -static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu) -{ - const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR0_EL1); - u64 hcr_set = HCR_RW; - u64 hcr_clear = 0; - u64 cptr_set = 0; - u64 cptr_clear = 0; - - /* Protected KVM does not support AArch32 guests. */ - BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), - PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_EL1_EL0_IMP); - BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL1), - PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_EL1_EL1_IMP); - - /* - * Linux guests assume support for floating-point and Advanced SIMD. Do - * not change the trapping behavior for these from the KVM default. - */ - BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_FP), - PVM_ID_AA64PFR0_ALLOW)); - BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AdvSIMD), - PVM_ID_AA64PFR0_ALLOW)); - - if (has_hvhe()) - hcr_set |= HCR_E2H; - - /* Trap RAS unless all current versions are supported */ - if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_RAS), feature_ids) < - ID_AA64PFR0_EL1_RAS_V1P1) { - hcr_set |= HCR_TERR | HCR_TEA; - hcr_clear |= HCR_FIEN; - } - - /* Trap AMU */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AMU), feature_ids)) { - hcr_clear |= HCR_AMVOFFEN; - cptr_set |= CPTR_EL2_TAM; - } - - /* Trap SVE */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) { - if (has_hvhe()) - cptr_clear |= CPACR_ELx_ZEN; - else - cptr_set |= CPTR_EL2_TZ; - } - - vcpu->arch.hcr_el2 |= hcr_set; - vcpu->arch.hcr_el2 &= ~hcr_clear; - vcpu->arch.cptr_el2 |= cptr_set; - vcpu->arch.cptr_el2 &= ~cptr_clear; -} - -/* - * Set trap register values based on features in ID_AA64PFR1. - */ -static void pvm_init_traps_aa64pfr1(struct kvm_vcpu *vcpu) -{ - const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR1_EL1); - u64 hcr_set = 0; - u64 hcr_clear = 0; - - /* Memory Tagging: Trap and Treat as Untagged if not supported. */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE), feature_ids)) { - hcr_set |= HCR_TID5; - hcr_clear |= HCR_DCT | HCR_ATA; - } - - vcpu->arch.hcr_el2 |= hcr_set; - vcpu->arch.hcr_el2 &= ~hcr_clear; -} - -/* - * Set trap register values based on features in ID_AA64DFR0. - */ -static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu) -{ - const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64DFR0_EL1); - u64 mdcr_set = 0; - u64 mdcr_clear = 0; - u64 cptr_set = 0; - - /* Trap/constrain PMU */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), feature_ids)) { - mdcr_set |= MDCR_EL2_TPM | MDCR_EL2_TPMCR; - mdcr_clear |= MDCR_EL2_HPME | MDCR_EL2_MTPME | - MDCR_EL2_HPMN_MASK; - } - - /* Trap Debug */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), feature_ids)) - mdcr_set |= MDCR_EL2_TDRA | MDCR_EL2_TDA | MDCR_EL2_TDE; - - /* Trap OS Double Lock */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DoubleLock), feature_ids)) - mdcr_set |= MDCR_EL2_TDOSA; - - /* Trap SPE */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer), feature_ids)) { - mdcr_set |= MDCR_EL2_TPMS; - mdcr_clear |= MDCR_EL2_E2PB_MASK; - } - - /* Trap Trace Filter */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_TraceFilt), feature_ids)) - mdcr_set |= MDCR_EL2_TTRF; - - /* Trap Trace */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_TraceVer), feature_ids)) { - if (has_hvhe()) - cptr_set |= CPACR_EL1_TTA; - else - cptr_set |= CPTR_EL2_TTA; - } - - /* Trap External Trace */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids)) - mdcr_clear |= MDCR_EL2_E2TB_MASK; - - vcpu->arch.mdcr_el2 |= mdcr_set; - vcpu->arch.mdcr_el2 &= ~mdcr_clear; - vcpu->arch.cptr_el2 |= cptr_set; -} - -/* - * Set trap register values based on features in ID_AA64MMFR0. - */ -static void pvm_init_traps_aa64mmfr0(struct kvm_vcpu *vcpu) -{ - const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR0_EL1); - u64 mdcr_set = 0; - - /* Trap Debug Communications Channel registers */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_FGT), feature_ids)) - mdcr_set |= MDCR_EL2_TDCC; - - vcpu->arch.mdcr_el2 |= mdcr_set; -} - -/* - * Set trap register values based on features in ID_AA64MMFR1. - */ -static void pvm_init_traps_aa64mmfr1(struct kvm_vcpu *vcpu) -{ - const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR1_EL1); - u64 hcr_set = 0; - - /* Trap LOR */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_LO), feature_ids)) - hcr_set |= HCR_TLOR; - - vcpu->arch.hcr_el2 |= hcr_set; -} - -/* - * Set baseline trap register values. - */ -static void pvm_init_trap_regs(struct kvm_vcpu *vcpu) -{ - const u64 hcr_trap_feat_regs = HCR_TID3; - const u64 hcr_trap_impdef = HCR_TACR | HCR_TIDCP | HCR_TID1; - - /* - * Always trap: - * - Feature id registers: to control features exposed to guests - * - Implementation-defined features - */ - vcpu->arch.hcr_el2 |= hcr_trap_feat_regs | hcr_trap_impdef; - - /* Clear res0 and set res1 bits to trap potential new features. */ - vcpu->arch.hcr_el2 &= ~(HCR_RES0); - vcpu->arch.mdcr_el2 &= ~(MDCR_EL2_RES0); - if (!has_hvhe()) { - vcpu->arch.cptr_el2 |= CPTR_NVHE_EL2_RES1; - vcpu->arch.cptr_el2 &= ~(CPTR_NVHE_EL2_RES0); - } -} +static DEFINE_PER_CPU(struct pkvm_hyp_vcpu *, loaded_hyp_vcpu); static void pkvm_vcpu_reset_hcr(struct kvm_vcpu *vcpu) { @@ -229,27 +53,130 @@ static void pkvm_vcpu_reset_hcr(struct kvm_vcpu *vcpu) if (vcpu_has_ptrauth(vcpu)) vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK); + + if (kvm_has_mte(vcpu->kvm)) + vcpu->arch.hcr_el2 |= HCR_ATA; +} + +static void pvm_init_traps_hcr(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + u64 val = vcpu->arch.hcr_el2; + + /* No support for AArch32. */ + val |= HCR_RW; + + /* + * Always trap: + * - Feature id registers: to control features exposed to guests + * - Implementation-defined features + */ + val |= HCR_TACR | HCR_TIDCP | HCR_TID3 | HCR_TID1; + + if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) { + val |= HCR_TERR | HCR_TEA; + val &= ~(HCR_FIEN); + } + + if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, IMP)) + val &= ~(HCR_AMVOFFEN); + + if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, MTE, IMP)) { + val |= HCR_TID5; + val &= ~(HCR_DCT | HCR_ATA); + } + + if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP)) + val |= HCR_TLOR; + + vcpu->arch.hcr_el2 = val; +} + +static void pvm_init_traps_mdcr(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + u64 val = vcpu->arch.mdcr_el2; + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) { + val |= MDCR_EL2_TPM | MDCR_EL2_TPMCR; + val &= ~(MDCR_EL2_HPME | MDCR_EL2_MTPME | MDCR_EL2_HPMN_MASK); + } + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DebugVer, IMP)) + val |= MDCR_EL2_TDRA | MDCR_EL2_TDA; + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DoubleLock, IMP)) + val |= MDCR_EL2_TDOSA; + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP)) { + val |= MDCR_EL2_TPMS; + val &= ~MDCR_EL2_E2PB_MASK; + } + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP)) + val |= MDCR_EL2_TTRF; + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, ExtTrcBuff, IMP)) + val |= MDCR_EL2_E2TB_MASK; + + /* Trap Debug Communications Channel registers */ + if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, FGT, IMP)) + val |= MDCR_EL2_TDCC; + + vcpu->arch.mdcr_el2 = val; +} + +/* + * Check that cpu features that are neither trapped nor supported are not + * enabled for protected VMs. + */ +static int pkvm_check_pvm_cpu_features(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + /* Protected KVM does not support AArch32 guests. */ + if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL0, AARCH32) || + kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL1, AARCH32)) + return -EINVAL; + + /* + * Linux guests assume support for floating-point and Advanced SIMD. Do + * not change the trapping behavior for these from the KVM default. + */ + if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, FP, IMP) || + !kvm_has_feat(kvm, ID_AA64PFR0_EL1, AdvSIMD, IMP)) + return -EINVAL; + + /* No SME support in KVM right now. Check to catch if it changes. */ + if (kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP)) + return -EINVAL; + + return 0; } /* * Initialize trap register values in protected mode. */ -static void pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu) +static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu) { - vcpu->arch.cptr_el2 = kvm_get_reset_cptr_el2(vcpu); + struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu; + int ret; + vcpu->arch.mdcr_el2 = 0; pkvm_vcpu_reset_hcr(vcpu); - if ((!vcpu_is_protected(vcpu))) - return; + if ((!pkvm_hyp_vcpu_is_protected(hyp_vcpu))) + return 0; - pvm_init_trap_regs(vcpu); - pvm_init_traps_aa64pfr0(vcpu); - pvm_init_traps_aa64pfr1(vcpu); - pvm_init_traps_aa64dfr0(vcpu); - pvm_init_traps_aa64mmfr0(vcpu); - pvm_init_traps_aa64mmfr1(vcpu); + ret = pkvm_check_pvm_cpu_features(vcpu); + if (ret) + return ret; + + pvm_init_traps_hcr(vcpu); + pvm_init_traps_mdcr(vcpu); + + return 0; } /* @@ -270,10 +197,10 @@ static pkvm_handle_t idx_to_vm_handle(unsigned int idx) /* * Spinlock for protecting state related to the VM table. Protects writes - * to 'vm_table' and 'nr_table_entries' as well as reads and writes to - * 'last_hyp_vcpu_lookup'. + * to 'vm_table', 'nr_table_entries', and other per-vm state on initialization. + * Also protects reads and writes to 'last_hyp_vcpu_lookup'. */ -static DEFINE_HYP_SPINLOCK(vm_table_lock); +DEFINE_HYP_SPINLOCK(vm_table_lock); /* * The table of VM entries for protected VMs in hyp. @@ -306,15 +233,30 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, struct pkvm_hyp_vcpu *hyp_vcpu = NULL; struct pkvm_hyp_vm *hyp_vm; + /* Cannot load a new vcpu without putting the old one first. */ + if (__this_cpu_read(loaded_hyp_vcpu)) + return NULL; + hyp_spin_lock(&vm_table_lock); hyp_vm = get_vm_by_handle(handle); if (!hyp_vm || hyp_vm->nr_vcpus <= vcpu_idx) goto unlock; hyp_vcpu = hyp_vm->vcpus[vcpu_idx]; + + /* Ensure vcpu isn't loaded on more than one cpu simultaneously. */ + if (unlikely(hyp_vcpu->loaded_hyp_vcpu)) { + hyp_vcpu = NULL; + goto unlock; + } + + hyp_vcpu->loaded_hyp_vcpu = this_cpu_ptr(&loaded_hyp_vcpu); hyp_page_ref_inc(hyp_virt_to_page(hyp_vm)); unlock: hyp_spin_unlock(&vm_table_lock); + + if (hyp_vcpu) + __this_cpu_write(loaded_hyp_vcpu, hyp_vcpu); return hyp_vcpu; } @@ -323,17 +265,63 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu); hyp_spin_lock(&vm_table_lock); + hyp_vcpu->loaded_hyp_vcpu = NULL; + __this_cpu_write(loaded_hyp_vcpu, NULL); hyp_page_ref_dec(hyp_virt_to_page(hyp_vm)); hyp_spin_unlock(&vm_table_lock); } +struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void) +{ + return __this_cpu_read(loaded_hyp_vcpu); + +} + +struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle) +{ + struct pkvm_hyp_vm *hyp_vm; + + hyp_spin_lock(&vm_table_lock); + hyp_vm = get_vm_by_handle(handle); + if (hyp_vm) + hyp_page_ref_inc(hyp_virt_to_page(hyp_vm)); + hyp_spin_unlock(&vm_table_lock); + + return hyp_vm; +} + +void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm) +{ + hyp_spin_lock(&vm_table_lock); + hyp_page_ref_dec(hyp_virt_to_page(hyp_vm)); + hyp_spin_unlock(&vm_table_lock); +} + +struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle) +{ + struct pkvm_hyp_vm *hyp_vm = get_pkvm_hyp_vm(handle); + + if (hyp_vm && pkvm_hyp_vm_is_protected(hyp_vm)) { + put_pkvm_hyp_vm(hyp_vm); + hyp_vm = NULL; + } + + return hyp_vm; +} + static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struct kvm *host_kvm) { struct kvm *kvm = &hyp_vm->kvm; + unsigned long host_arch_flags = READ_ONCE(host_kvm->arch.flags); DECLARE_BITMAP(allowed_features, KVM_VCPU_MAX_FEATURES); + if (test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &host_kvm->arch.flags)) + set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags); + /* No restrictions for non-protected VMs. */ if (!kvm_vm_is_protected(kvm)) { + hyp_vm->kvm.arch.flags = host_arch_flags; + bitmap_copy(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features, KVM_VCPU_MAX_FEATURES); @@ -342,50 +330,26 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc bitmap_zero(allowed_features, KVM_VCPU_MAX_FEATURES); - /* - * For protected VMs, always allow: - * - CPU starting in poweroff state - * - PSCI v0.2 - */ - set_bit(KVM_ARM_VCPU_POWER_OFF, allowed_features); set_bit(KVM_ARM_VCPU_PSCI_0_2, allowed_features); - /* - * Check if remaining features are allowed: - * - Performance Monitoring - * - Scalable Vectors - * - Pointer Authentication - */ - if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), PVM_ID_AA64DFR0_ALLOW)) + if (kvm_pvm_ext_allowed(KVM_CAP_ARM_PMU_V3)) set_bit(KVM_ARM_VCPU_PMU_V3, allowed_features); - if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), PVM_ID_AA64PFR0_ALLOW)) - set_bit(KVM_ARM_VCPU_SVE, allowed_features); - - if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API), PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED) && - FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA), PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED)) + if (kvm_pvm_ext_allowed(KVM_CAP_ARM_PTRAUTH_ADDRESS)) set_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, allowed_features); - if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI), PVM_ID_AA64ISAR1_ALLOW) && - FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA), PVM_ID_AA64ISAR1_ALLOW)) + if (kvm_pvm_ext_allowed(KVM_CAP_ARM_PTRAUTH_GENERIC)) set_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, allowed_features); + if (kvm_pvm_ext_allowed(KVM_CAP_ARM_SVE)) { + set_bit(KVM_ARM_VCPU_SVE, allowed_features); + kvm->arch.flags |= host_arch_flags & BIT(KVM_ARCH_FLAG_GUEST_HAS_SVE); + } + bitmap_and(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features, allowed_features, KVM_VCPU_MAX_FEATURES); } -static void pkvm_vcpu_init_ptrauth(struct pkvm_hyp_vcpu *hyp_vcpu) -{ - struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu; - - if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) || - vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC)) { - kvm_vcpu_enable_ptrauth(vcpu); - } else { - vcpu_clear_flag(&hyp_vcpu->vcpu, GUEST_HAS_PTRAUTH); - } -} - static void unpin_host_vcpu(struct kvm_vcpu *host_vcpu) { if (host_vcpu) @@ -408,6 +372,7 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm, hyp_vm->kvm.created_vcpus = nr_vcpus; hyp_vm->kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr; hyp_vm->kvm.arch.pkvm.enabled = READ_ONCE(host_kvm->arch.pkvm.enabled); + hyp_vm->kvm.arch.flags = 0; pkvm_init_features_from_host(hyp_vm, host_kvm); } @@ -415,10 +380,8 @@ static void pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu * { struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu; - if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) { - vcpu_clear_flag(vcpu, GUEST_HAS_SVE); + if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) vcpu_clear_flag(vcpu, VCPU_SVE_FINALIZED); - } } static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, @@ -446,9 +409,14 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags); hyp_vcpu->vcpu.arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; + if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + kvm_init_pvm_id_regs(&hyp_vcpu->vcpu); + + ret = pkvm_vcpu_init_traps(hyp_vcpu); + if (ret) + goto done; + pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu); - pkvm_vcpu_init_ptrauth(hyp_vcpu); - pkvm_vcpu_init_traps(&hyp_vcpu->vcpu); done: if (ret) unpin_host_vcpu(host_vcpu); @@ -693,8 +661,6 @@ unlock: return ret; } - hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu); - return 0; } @@ -746,6 +712,14 @@ int __pkvm_teardown_vm(pkvm_handle_t handle) /* Push the metadata pages to the teardown memcache */ for (idx = 0; idx < hyp_vm->nr_vcpus; ++idx) { struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx]; + struct kvm_hyp_memcache *vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache; + + while (vcpu_mc->nr_pages) { + void *addr = pop_hyp_memcache(vcpu_mc, hyp_phys_to_virt); + + push_hyp_memcache(mc, addr, hyp_virt_to_phys); + unmap_donated_memory_noclear(addr, PAGE_SIZE); + } teardown_donated_memory(mc, hyp_vcpu, sizeof(*hyp_vcpu)); } diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index cbdd18cd3f98..d62bcb5634a2 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -12,7 +12,6 @@ #include #include -#include #include #include #include @@ -180,7 +179,6 @@ static void hpool_put_page(void *addr) static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { - enum kvm_pgtable_prot prot; enum pkvm_page_state state; phys_addr_t phys; @@ -203,16 +201,16 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx, case PKVM_PAGE_OWNED: return host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HYP); case PKVM_PAGE_SHARED_OWNED: - prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_BORROWED); + hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_BORROWED; break; case PKVM_PAGE_SHARED_BORROWED: - prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_OWNED); + hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_OWNED; break; default: return -EINVAL; } - return host_stage2_idmap_locked(phys, PAGE_SIZE, prot); + return 0; } static int fix_hyp_pgtable_refcnt_walker(const struct kvm_pgtable_visit_ctx *ctx, diff --git a/arch/arm64/kvm/hyp/nvhe/stacktrace.c b/arch/arm64/kvm/hyp/nvhe/stacktrace.c index ed6b58b19cfa..5b6eeab1a774 100644 --- a/arch/arm64/kvm/hyp/nvhe/stacktrace.c +++ b/arch/arm64/kvm/hyp/nvhe/stacktrace.c @@ -28,7 +28,7 @@ static void hyp_prepare_backtrace(unsigned long fp, unsigned long pc) struct kvm_nvhe_stacktrace_info *stacktrace_info = this_cpu_ptr(&kvm_stacktrace_info); struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params); - stacktrace_info->stack_base = (unsigned long)(params->stack_hyp_va - PAGE_SIZE); + stacktrace_info->stack_base = (unsigned long)(params->stack_hyp_va - NVHE_STACK_SIZE); stacktrace_info->overflow_stack_base = (unsigned long)this_cpu_ptr(overflow_stack); stacktrace_info->fp = fp; stacktrace_info->pc = pc; @@ -54,7 +54,7 @@ static struct stack_info stackinfo_get_hyp(void) { struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params); unsigned long high = params->stack_hyp_va; - unsigned long low = high - PAGE_SIZE; + unsigned long low = high - NVHE_STACK_SIZE; return (struct stack_info) { .low = low, diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index cc69106734ca..6c846d033d24 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -26,7 +26,6 @@ #include #include -#include #include /* Non-VHE specific context */ @@ -36,33 +35,46 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); -static void __activate_traps(struct kvm_vcpu *vcpu) +static void __activate_cptr_traps(struct kvm_vcpu *vcpu) { - u64 val; + u64 val = CPTR_EL2_TAM; /* Same bit irrespective of E2H */ - ___activate_traps(vcpu, vcpu->arch.hcr_el2); - __activate_traps_common(vcpu); + if (has_hvhe()) { + val |= CPACR_EL1_TTA; - val = vcpu->arch.cptr_el2; - val |= CPTR_EL2_TAM; /* Same bit irrespective of E2H */ - val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA; - if (cpus_have_final_cap(ARM64_SME)) { - if (has_hvhe()) - val &= ~CPACR_ELx_SMEN; - else - val |= CPTR_EL2_TSM; + if (guest_owns_fp_regs()) { + val |= CPACR_EL1_FPEN; + if (vcpu_has_sve(vcpu)) + val |= CPACR_EL1_ZEN; + } + } else { + val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1; + + /* + * Always trap SME since it's not supported in KVM. + * TSM is RES1 if SME isn't implemented. + */ + val |= CPTR_EL2_TSM; + + if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs()) + val |= CPTR_EL2_TZ; + + if (!guest_owns_fp_regs()) + val |= CPTR_EL2_TFP; } - if (!guest_owns_fp_regs()) { - if (has_hvhe()) - val &= ~(CPACR_ELx_FPEN | CPACR_ELx_ZEN); - else - val |= CPTR_EL2_TFP | CPTR_EL2_TZ; - + if (!guest_owns_fp_regs()) __activate_traps_fpsimd32(vcpu); - } kvm_write_cptr_el2(val); +} + +static void __activate_traps(struct kvm_vcpu *vcpu) +{ + ___activate_traps(vcpu, vcpu->arch.hcr_el2); + __activate_traps_common(vcpu); + __activate_cptr_traps(vcpu); + write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { @@ -192,7 +204,7 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) /* Re-enable SVE traps if not supported for the guest vcpu. */ if (!vcpu_has_sve(vcpu)) - cpacr_clear_set(CPACR_ELx_ZEN, 0); + cpacr_clear_set(CPACR_EL1_ZEN, 0); } else { __fpsimd_save_state(*host_data_ptr(fpsimd_state)); diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 2860548d4250..1ddd9ed3cbb3 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -11,7 +11,7 @@ #include -#include +#include #include "../../sys_regs.h" @@ -28,6 +28,221 @@ u64 id_aa64mmfr1_el1_sys_val; u64 id_aa64mmfr2_el1_sys_val; u64 id_aa64smfr0_el1_sys_val; +struct pvm_ftr_bits { + bool sign; + u8 shift; + u8 width; + u8 max_val; + bool (*vm_supported)(const struct kvm *kvm); +}; + +#define __MAX_FEAT_FUNC(id, fld, max, func, sgn) \ + { \ + .sign = sgn, \ + .shift = id##_##fld##_SHIFT, \ + .width = id##_##fld##_WIDTH, \ + .max_val = id##_##fld##_##max, \ + .vm_supported = func, \ + } + +#define MAX_FEAT_FUNC(id, fld, max, func) \ + __MAX_FEAT_FUNC(id, fld, max, func, id##_##fld##_SIGNED) + +#define MAX_FEAT(id, fld, max) \ + MAX_FEAT_FUNC(id, fld, max, NULL) + +#define MAX_FEAT_ENUM(id, fld, max) \ + __MAX_FEAT_FUNC(id, fld, max, NULL, false) + +#define FEAT_END { .width = 0, } + +static bool vm_has_ptrauth(const struct kvm *kvm) +{ + if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH)) + return false; + + return (cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) || + cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) && + kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC); +} + +static bool vm_has_sve(const struct kvm *kvm) +{ + return system_supports_sve() && kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_SVE); +} + +/* + * Definitions for features to be allowed or restricted for protected guests. + * + * Each field in the masks represents the highest supported value for the + * feature. If a feature field is not present, it is not supported. Moreover, + * these are used to generate the guest's view of the feature registers. + * + * The approach for protected VMs is to at least support features that are: + * - Needed by common Linux distributions (e.g., floating point) + * - Trivial to support, e.g., supporting the feature does not introduce or + * require tracking of additional state in KVM + * - Cannot be trapped or prevent the guest from using anyway + */ + +static const struct pvm_ftr_bits pvmid_aa64pfr0[] = { + MAX_FEAT(ID_AA64PFR0_EL1, EL0, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, EL1, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, EL2, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, EL3, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, FP, FP16), + MAX_FEAT(ID_AA64PFR0_EL1, AdvSIMD, FP16), + MAX_FEAT(ID_AA64PFR0_EL1, GIC, IMP), + MAX_FEAT_FUNC(ID_AA64PFR0_EL1, SVE, IMP, vm_has_sve), + MAX_FEAT(ID_AA64PFR0_EL1, RAS, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, DIT, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, CSV2, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, CSV3, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64pfr1[] = { + MAX_FEAT(ID_AA64PFR1_EL1, BT, IMP), + MAX_FEAT(ID_AA64PFR1_EL1, SSBS, SSBS2), + MAX_FEAT_ENUM(ID_AA64PFR1_EL1, MTE_frac, NI), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64mmfr0[] = { + MAX_FEAT_ENUM(ID_AA64MMFR0_EL1, PARANGE, 40), + MAX_FEAT_ENUM(ID_AA64MMFR0_EL1, ASIDBITS, 16), + MAX_FEAT(ID_AA64MMFR0_EL1, BIGEND, IMP), + MAX_FEAT(ID_AA64MMFR0_EL1, SNSMEM, IMP), + MAX_FEAT(ID_AA64MMFR0_EL1, BIGENDEL0, IMP), + MAX_FEAT(ID_AA64MMFR0_EL1, EXS, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64mmfr1[] = { + MAX_FEAT(ID_AA64MMFR1_EL1, HAFDBS, DBM), + MAX_FEAT_ENUM(ID_AA64MMFR1_EL1, VMIDBits, 16), + MAX_FEAT(ID_AA64MMFR1_EL1, HPDS, HPDS2), + MAX_FEAT(ID_AA64MMFR1_EL1, PAN, PAN3), + MAX_FEAT(ID_AA64MMFR1_EL1, SpecSEI, IMP), + MAX_FEAT(ID_AA64MMFR1_EL1, ETS, IMP), + MAX_FEAT(ID_AA64MMFR1_EL1, CMOW, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64mmfr2[] = { + MAX_FEAT(ID_AA64MMFR2_EL1, CnP, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, UAO, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, IESB, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, AT, IMP), + MAX_FEAT_ENUM(ID_AA64MMFR2_EL1, IDS, 0x18), + MAX_FEAT(ID_AA64MMFR2_EL1, TTL, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, BBM, 2), + MAX_FEAT(ID_AA64MMFR2_EL1, E0PD, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64isar1[] = { + MAX_FEAT(ID_AA64ISAR1_EL1, DPB, DPB2), + MAX_FEAT_FUNC(ID_AA64ISAR1_EL1, APA, PAuth, vm_has_ptrauth), + MAX_FEAT_FUNC(ID_AA64ISAR1_EL1, API, PAuth, vm_has_ptrauth), + MAX_FEAT(ID_AA64ISAR1_EL1, JSCVT, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, FCMA, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, LRCPC, LRCPC3), + MAX_FEAT(ID_AA64ISAR1_EL1, GPA, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, GPI, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, FRINTTS, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, SB, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX), + MAX_FEAT(ID_AA64ISAR1_EL1, BF16, EBF16), + MAX_FEAT(ID_AA64ISAR1_EL1, DGH, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, I8MM, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64isar2[] = { + MAX_FEAT_FUNC(ID_AA64ISAR2_EL1, GPA3, IMP, vm_has_ptrauth), + MAX_FEAT_FUNC(ID_AA64ISAR2_EL1, APA3, PAuth, vm_has_ptrauth), + MAX_FEAT(ID_AA64ISAR2_EL1, ATS1A, IMP), + FEAT_END +}; + +/* + * None of the features in ID_AA64DFR0_EL1 nor ID_AA64MMFR4_EL1 are supported. + * However, both have Not-Implemented values that are non-zero. Define them + * so they can be used when getting the value of these registers. + */ +#define ID_AA64DFR0_EL1_NONZERO_NI \ +( \ + SYS_FIELD_PREP_ENUM(ID_AA64DFR0_EL1, DoubleLock, NI) | \ + SYS_FIELD_PREP_ENUM(ID_AA64DFR0_EL1, MTPMU, NI) \ +) + +#define ID_AA64MMFR4_EL1_NONZERO_NI \ + SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, E2H0, NI) + +/* + * Returns the value of the feature registers based on the system register + * value, the vcpu support for the revelant features, and the additional + * restrictions for protected VMs. + */ +static u64 get_restricted_features(const struct kvm_vcpu *vcpu, + u64 sys_reg_val, + const struct pvm_ftr_bits restrictions[]) +{ + u64 val = 0UL; + int i; + + for (i = 0; restrictions[i].width != 0; i++) { + bool (*vm_supported)(const struct kvm *) = restrictions[i].vm_supported; + bool sign = restrictions[i].sign; + int shift = restrictions[i].shift; + int width = restrictions[i].width; + u64 min_signed = (1UL << width) - 1UL; + u64 sign_bit = 1UL << (width - 1); + u64 mask = GENMASK_ULL(width + shift - 1, shift); + u64 sys_val = (sys_reg_val & mask) >> shift; + u64 pvm_max = restrictions[i].max_val; + + if (vm_supported && !vm_supported(vcpu->kvm)) + val |= (sign ? min_signed : 0) << shift; + else if (sign && (sys_val >= sign_bit || pvm_max >= sign_bit)) + val |= max(sys_val, pvm_max) << shift; + else + val |= min(sys_val, pvm_max) << shift; + } + + return val; +} + +static u64 pvm_calc_id_reg(const struct kvm_vcpu *vcpu, u32 id) +{ + switch (id) { + case SYS_ID_AA64PFR0_EL1: + return get_restricted_features(vcpu, id_aa64pfr0_el1_sys_val, pvmid_aa64pfr0); + case SYS_ID_AA64PFR1_EL1: + return get_restricted_features(vcpu, id_aa64pfr1_el1_sys_val, pvmid_aa64pfr1); + case SYS_ID_AA64ISAR0_EL1: + return id_aa64isar0_el1_sys_val; + case SYS_ID_AA64ISAR1_EL1: + return get_restricted_features(vcpu, id_aa64isar1_el1_sys_val, pvmid_aa64isar1); + case SYS_ID_AA64ISAR2_EL1: + return get_restricted_features(vcpu, id_aa64isar2_el1_sys_val, pvmid_aa64isar2); + case SYS_ID_AA64MMFR0_EL1: + return get_restricted_features(vcpu, id_aa64mmfr0_el1_sys_val, pvmid_aa64mmfr0); + case SYS_ID_AA64MMFR1_EL1: + return get_restricted_features(vcpu, id_aa64mmfr1_el1_sys_val, pvmid_aa64mmfr1); + case SYS_ID_AA64MMFR2_EL1: + return get_restricted_features(vcpu, id_aa64mmfr2_el1_sys_val, pvmid_aa64mmfr2); + case SYS_ID_AA64DFR0_EL1: + return ID_AA64DFR0_EL1_NONZERO_NI; + case SYS_ID_AA64MMFR4_EL1: + return ID_AA64MMFR4_EL1_NONZERO_NI; + default: + /* Unhandled ID register, RAZ */ + return 0; + } +} + /* * Inject an unknown/undefined exception to an AArch64 guest while most of its * sysregs are live. @@ -49,201 +264,19 @@ static void inject_undef64(struct kvm_vcpu *vcpu) write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR); } -/* - * Returns the restricted features values of the feature register based on the - * limitations in restrict_fields. - * A feature id field value of 0b0000 does not impose any restrictions. - * Note: Use only for unsigned feature field values. - */ -static u64 get_restricted_features_unsigned(u64 sys_reg_val, - u64 restrict_fields) -{ - u64 value = 0UL; - u64 mask = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0); - - /* - * According to the Arm Architecture Reference Manual, feature fields - * use increasing values to indicate increases in functionality. - * Iterate over the restricted feature fields and calculate the minimum - * unsigned value between the one supported by the system, and what the - * value is being restricted to. - */ - while (sys_reg_val && restrict_fields) { - value |= min(sys_reg_val & mask, restrict_fields & mask); - sys_reg_val &= ~mask; - restrict_fields &= ~mask; - mask <<= ARM64_FEATURE_FIELD_BITS; - } - - return value; -} - -/* - * Functions that return the value of feature id registers for protected VMs - * based on allowed features, system features, and KVM support. - */ - -static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu) -{ - u64 set_mask = 0; - u64 allow_mask = PVM_ID_AA64PFR0_ALLOW; - - set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val, - PVM_ID_AA64PFR0_RESTRICT_UNSIGNED); - - return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask; -} - -static u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu) -{ - const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm); - u64 allow_mask = PVM_ID_AA64PFR1_ALLOW; - - if (!kvm_has_mte(kvm)) - allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE); - - return id_aa64pfr1_el1_sys_val & allow_mask; -} - -static u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu) -{ - /* - * No support for Scalable Vectors, therefore, hyp has no sanitized - * copy of the feature id register. - */ - BUILD_BUG_ON(PVM_ID_AA64ZFR0_ALLOW != 0ULL); - return 0; -} - -static u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu) -{ - /* - * No support for debug, including breakpoints, and watchpoints, - * therefore, pKVM has no sanitized copy of the feature id register. - */ - BUILD_BUG_ON(PVM_ID_AA64DFR0_ALLOW != 0ULL); - return 0; -} - -static u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu) -{ - /* - * No support for debug, therefore, hyp has no sanitized copy of the - * feature id register. - */ - BUILD_BUG_ON(PVM_ID_AA64DFR1_ALLOW != 0ULL); - return 0; -} - -static u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu) -{ - /* - * No support for implementation defined features, therefore, hyp has no - * sanitized copy of the feature id register. - */ - BUILD_BUG_ON(PVM_ID_AA64AFR0_ALLOW != 0ULL); - return 0; -} - -static u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu) -{ - /* - * No support for implementation defined features, therefore, hyp has no - * sanitized copy of the feature id register. - */ - BUILD_BUG_ON(PVM_ID_AA64AFR1_ALLOW != 0ULL); - return 0; -} - -static u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu) -{ - return id_aa64isar0_el1_sys_val & PVM_ID_AA64ISAR0_ALLOW; -} - -static u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu) -{ - u64 allow_mask = PVM_ID_AA64ISAR1_ALLOW; - - if (!vcpu_has_ptrauth(vcpu)) - allow_mask &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA) | - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API) | - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA) | - ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI)); - - return id_aa64isar1_el1_sys_val & allow_mask; -} - -static u64 get_pvm_id_aa64isar2(const struct kvm_vcpu *vcpu) -{ - u64 allow_mask = PVM_ID_AA64ISAR2_ALLOW; - - if (!vcpu_has_ptrauth(vcpu)) - allow_mask &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) | - ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3)); - - return id_aa64isar2_el1_sys_val & allow_mask; -} - -static u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu) -{ - u64 set_mask; - - set_mask = get_restricted_features_unsigned(id_aa64mmfr0_el1_sys_val, - PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED); - - return (id_aa64mmfr0_el1_sys_val & PVM_ID_AA64MMFR0_ALLOW) | set_mask; -} - -static u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu) -{ - return id_aa64mmfr1_el1_sys_val & PVM_ID_AA64MMFR1_ALLOW; -} - -static u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu) -{ - return id_aa64mmfr2_el1_sys_val & PVM_ID_AA64MMFR2_ALLOW; -} - -/* Read a sanitized cpufeature ID register by its encoding */ -u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id) -{ - switch (id) { - case SYS_ID_AA64PFR0_EL1: - return get_pvm_id_aa64pfr0(vcpu); - case SYS_ID_AA64PFR1_EL1: - return get_pvm_id_aa64pfr1(vcpu); - case SYS_ID_AA64ZFR0_EL1: - return get_pvm_id_aa64zfr0(vcpu); - case SYS_ID_AA64DFR0_EL1: - return get_pvm_id_aa64dfr0(vcpu); - case SYS_ID_AA64DFR1_EL1: - return get_pvm_id_aa64dfr1(vcpu); - case SYS_ID_AA64AFR0_EL1: - return get_pvm_id_aa64afr0(vcpu); - case SYS_ID_AA64AFR1_EL1: - return get_pvm_id_aa64afr1(vcpu); - case SYS_ID_AA64ISAR0_EL1: - return get_pvm_id_aa64isar0(vcpu); - case SYS_ID_AA64ISAR1_EL1: - return get_pvm_id_aa64isar1(vcpu); - case SYS_ID_AA64ISAR2_EL1: - return get_pvm_id_aa64isar2(vcpu); - case SYS_ID_AA64MMFR0_EL1: - return get_pvm_id_aa64mmfr0(vcpu); - case SYS_ID_AA64MMFR1_EL1: - return get_pvm_id_aa64mmfr1(vcpu); - case SYS_ID_AA64MMFR2_EL1: - return get_pvm_id_aa64mmfr2(vcpu); - default: - /* Unhandled ID register, RAZ */ - return 0; - } -} - static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r) { - return pvm_read_id_reg(vcpu, reg_to_encoding(r)); + struct kvm *kvm = vcpu->kvm; + u32 reg = reg_to_encoding(r); + + if (WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags))) + return 0; + + if (reg >= sys_reg(3, 0, 0, 1, 0) && reg <= sys_reg(3, 0, 0, 7, 7)) + return kvm->arch.id_regs[IDREG_IDX(reg)]; + + return 0; } /* Handler to RAZ/WI sysregs */ @@ -271,13 +304,6 @@ static bool pvm_access_id_aarch32(struct kvm_vcpu *vcpu, return false; } - /* - * No support for AArch32 guests, therefore, pKVM has no sanitized copy - * of AArch32 feature id registers. - */ - BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL1), - PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) > ID_AA64PFR0_EL1_EL1_IMP); - return pvm_access_raz_wi(vcpu, p, r); } @@ -448,6 +474,30 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = { /* Performance Monitoring Registers are restricted. */ }; +/* + * Initializes feature registers for protected vms. + */ +void kvm_init_pvm_id_regs(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_arch *ka = &kvm->arch; + u32 r; + + hyp_assert_lock_held(&vm_table_lock); + + if (test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags)) + return; + + /* + * Initialize only AArch64 id registers since AArch32 isn't supported + * for protected VMs. + */ + for (r = sys_reg(3, 0, 0, 4, 0); r <= sys_reg(3, 0, 0, 7, 7); r += sys_reg(0, 0, 0, 0, 1)) + ka->id_regs[IDREG_IDX(r)] = pvm_calc_id_reg(vcpu, r); + + set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags); +} + /* * Checks that the sysreg table is unique and in-order. * diff --git a/arch/arm64/kvm/hyp/nvhe/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c index 3aaab20ae5b4..ff176f4ce7de 100644 --- a/arch/arm64/kvm/hyp/nvhe/timer-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c @@ -22,15 +22,16 @@ void __kvm_timer_set_cntvoff(u64 cntvoff) */ void __timer_disable_traps(struct kvm_vcpu *vcpu) { - u64 val, shift = 0; + u64 set, clr, shift = 0; if (has_hvhe()) shift = 10; /* Allow physical timer/counter access for the host */ - val = read_sysreg(cnthctl_el2); - val |= (CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN) << shift; - write_sysreg(val, cnthctl_el2); + set = (CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN) << shift; + clr = CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT; + + sysreg_clear_set(cnthctl_el2, clr, set); } /* @@ -58,5 +59,12 @@ void __timer_enable_traps(struct kvm_vcpu *vcpu) set <<= 10; } + /* + * Trap the virtual counter/timer if we have a broken cntvoff + * implementation. + */ + if (has_broken_cntvoff()) + set |= CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT; + sysreg_clear_set(cnthctl_el2, clr, set); } diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 40bd55966540..df5cc74a7dd0 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -35,14 +35,6 @@ static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx) return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO); } -static bool kvm_phys_is_valid(u64 phys) -{ - u64 parange_max = kvm_get_parange_max(); - u8 shift = id_aa64mmfr0_parange_to_phys_shift(parange_max); - - return phys < BIT(shift); -} - static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys) { u64 granule = kvm_granule_size(ctx->level); @@ -53,7 +45,7 @@ static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, if (granule > (ctx->end - ctx->addr)) return false; - if (kvm_phys_is_valid(phys) && !IS_ALIGNED(phys, granule)) + if (!IS_ALIGNED(phys, granule)) return false; return IS_ALIGNED(ctx->addr, granule); @@ -587,6 +579,9 @@ struct stage2_map_data { /* Force mappings to page granularity */ bool force_pte; + + /* Walk should update owner_id only */ + bool annotation; }; u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) @@ -885,18 +880,7 @@ static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, { u64 phys = data->phys; - /* - * Stage-2 walks to update ownership data are communicated to the map - * walker using an invalid PA. Avoid offsetting an already invalid PA, - * which could overflow and make the address valid again. - */ - if (!kvm_phys_is_valid(phys)) - return phys; - - /* - * Otherwise, work out the correct PA based on how far the walk has - * gotten. - */ + /* Work out the correct PA based on how far the walk has gotten */ return phys + (ctx->addr - ctx->start); } @@ -908,6 +892,9 @@ static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL) return false; + if (data->annotation) + return true; + return kvm_block_mapping_supported(ctx, phys); } @@ -923,7 +910,7 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, if (!stage2_leaf_mapping_allowed(ctx, data)) return -E2BIG; - if (kvm_phys_is_valid(phys)) + if (!data->annotation) new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); else new = kvm_init_invalid_leaf_owner(data->owner_id); @@ -1085,11 +1072,11 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, { int ret; struct stage2_map_data map_data = { - .phys = KVM_PHYS_INVALID, .mmu = pgt->mmu, .memcache = mc, .owner_id = owner_id, .force_pte = true, + .annotation = true, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, @@ -1245,14 +1232,13 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) NULL, NULL, 0); } -void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr) +void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, + enum kvm_pgtable_walk_flags flags) { int ret; ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, - NULL, NULL, - KVM_PGTABLE_WALK_HANDLE_FAULT | - KVM_PGTABLE_WALK_SHARED); + NULL, NULL, flags); if (!ret) dsb(ishst); } @@ -1308,7 +1294,7 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, } int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, - enum kvm_pgtable_prot prot) + enum kvm_pgtable_prot prot, enum kvm_pgtable_walk_flags flags) { int ret; s8 level; @@ -1326,9 +1312,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, if (prot & KVM_PGTABLE_PROT_X) clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN; - ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, - KVM_PGTABLE_WALK_HANDLE_FAULT | - KVM_PGTABLE_WALK_SHARED); + ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, flags); if (!ret || ret == -EAGAIN) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level); return ret; diff --git a/arch/arm64/kvm/hyp/vhe/debug-sr.c b/arch/arm64/kvm/hyp/vhe/debug-sr.c index 289689b2682d..0100339b09e0 100644 --- a/arch/arm64/kvm/hyp/vhe/debug-sr.c +++ b/arch/arm64/kvm/hyp/vhe/debug-sr.c @@ -19,8 +19,3 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu) { __debug_switch_to_host_common(vcpu); } - -u64 __kvm_get_mdcr_el2(void) -{ - return read_sysreg(mdcr_el2); -} diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 80581b1c3995..b5b9dbaf1fdd 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -77,12 +77,12 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM * shift value for trapping the AMU accesses. */ - u64 val = CPACR_ELx_TTA | CPTR_EL2_TAM; + u64 val = CPACR_EL1_TTA | CPTR_EL2_TAM; if (guest_owns_fp_regs()) { - val |= CPACR_ELx_FPEN; + val |= CPACR_EL1_FPEN; if (vcpu_has_sve(vcpu)) - val |= CPACR_ELx_ZEN; + val |= CPACR_EL1_ZEN; } else { __activate_traps_fpsimd32(vcpu); } @@ -122,13 +122,13 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) * hypervisor has traps enabled to dispel any illusion of something more * complicated taking place. */ - if (!(SYS_FIELD_GET(CPACR_ELx, FPEN, cptr) & BIT(0))) - val &= ~CPACR_ELx_FPEN; - if (!(SYS_FIELD_GET(CPACR_ELx, ZEN, cptr) & BIT(0))) - val &= ~CPACR_ELx_ZEN; + if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0))) + val &= ~CPACR_EL1_FPEN; + if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0))) + val &= ~CPACR_EL1_ZEN; if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP)) - val |= cptr & CPACR_ELx_E0POE; + val |= cptr & CPACR_EL1_E0POE; val |= cptr & CPTR_EL2_TCPAC; @@ -256,6 +256,110 @@ void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu) host_data_ptr(host_ctxt)->__hyp_running_vcpu = NULL; } +static u64 compute_emulated_cntx_ctl_el0(struct kvm_vcpu *vcpu, + enum vcpu_sysreg reg) +{ + unsigned long ctl; + u64 cval, cnt; + bool stat; + + switch (reg) { + case CNTP_CTL_EL0: + cval = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + ctl = __vcpu_sys_reg(vcpu, CNTP_CTL_EL0); + cnt = compute_counter_value(vcpu_ptimer(vcpu)); + break; + case CNTV_CTL_EL0: + cval = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); + ctl = __vcpu_sys_reg(vcpu, CNTV_CTL_EL0); + cnt = compute_counter_value(vcpu_vtimer(vcpu)); + break; + default: + BUG(); + } + + stat = cval <= cnt; + __assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &ctl, stat); + + return ctl; +} + +static bool kvm_hyp_handle_timer(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u64 esr, val; + + /* + * Having FEAT_ECV allows for a better quality of timer emulation. + * However, this comes at a huge cost in terms of traps. Try and + * satisfy the reads from guest's hypervisor context without + * returning to the kernel if we can. + */ + if (!is_hyp_ctxt(vcpu)) + return false; + + esr = kvm_vcpu_get_esr(vcpu); + if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) != ESR_ELx_SYS64_ISS_DIR_READ) + return false; + + switch (esr_sys64_to_sysreg(esr)) { + case SYS_CNTP_CTL_EL02: + val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0); + break; + case SYS_CNTP_CTL_EL0: + if (vcpu_el2_e2h_is_set(vcpu)) + val = read_sysreg_el0(SYS_CNTP_CTL); + else + val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0); + break; + case SYS_CNTP_CVAL_EL02: + val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + break; + case SYS_CNTP_CVAL_EL0: + if (vcpu_el2_e2h_is_set(vcpu)) { + val = read_sysreg_el0(SYS_CNTP_CVAL); + + if (!has_cntpoff()) + val -= timer_get_offset(vcpu_hptimer(vcpu)); + } else { + val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + } + break; + case SYS_CNTPCT_EL0: + case SYS_CNTPCTSS_EL0: + val = compute_counter_value(vcpu_hptimer(vcpu)); + break; + case SYS_CNTV_CTL_EL02: + val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0); + break; + case SYS_CNTV_CTL_EL0: + if (vcpu_el2_e2h_is_set(vcpu)) + val = read_sysreg_el0(SYS_CNTV_CTL); + else + val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0); + break; + case SYS_CNTV_CVAL_EL02: + val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); + break; + case SYS_CNTV_CVAL_EL0: + if (vcpu_el2_e2h_is_set(vcpu)) + val = read_sysreg_el0(SYS_CNTV_CVAL); + else + val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); + break; + case SYS_CNTVCT_EL0: + case SYS_CNTVCTSS_EL0: + val = compute_counter_value(vcpu_hvtimer(vcpu)); + break; + default: + return false; + } + + vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val); + __kvm_skip_instr(vcpu); + + return true; +} + static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) { u64 esr = kvm_vcpu_get_esr(vcpu); @@ -409,6 +513,9 @@ static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code) if (kvm_hyp_handle_tlbi_el2(vcpu, exit_code)) return true; + if (kvm_hyp_handle_timer(vcpu, exit_code)) + return true; + if (kvm_hyp_handle_cpacr_el1(vcpu, exit_code)) return true; diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c index 5f78a39053a7..90b018e06f2c 100644 --- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c @@ -216,7 +216,7 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) __sysreg32_restore_state(vcpu); __sysreg_restore_user_state(guest_ctxt); - if (unlikely(__is_hyp_ctxt(guest_ctxt))) { + if (unlikely(is_hyp_ctxt(vcpu))) { __sysreg_restore_vel2_state(vcpu); } else { if (vcpu_has_nv(vcpu)) { @@ -260,7 +260,7 @@ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) host_ctxt = host_data_ptr(host_ctxt); - if (unlikely(__is_hyp_ctxt(guest_ctxt))) + if (unlikely(is_hyp_ctxt(vcpu))) __sysreg_save_vel2_state(vcpu); else __sysreg_save_el1_state(guest_ctxt); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c9d46ad57e52..1f55b0c7b11d 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -29,8 +30,12 @@ static unsigned long __ro_after_init hyp_idmap_start; static unsigned long __ro_after_init hyp_idmap_end; static phys_addr_t __ro_after_init hyp_idmap_vector; +u32 __ro_after_init __hyp_va_bits; + static unsigned long __ro_after_init io_map_base; +#define KVM_PGT_FN(fn) (!is_protected_kvm_enabled() ? fn : p ## fn) + static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end, phys_addr_t size) { @@ -147,7 +152,7 @@ static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr, return -EINVAL; next = __stage2_range_addr_end(addr, end, chunk_size); - ret = kvm_pgtable_stage2_split(pgt, addr, next - addr, cache); + ret = KVM_PGT_FN(kvm_pgtable_stage2_split)(pgt, addr, next - addr, cache); if (ret) break; } while (addr = next, addr != end); @@ -168,15 +173,23 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot) */ int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { - kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); + if (is_protected_kvm_enabled()) + kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle); + else + kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); return 0; } int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { - kvm_tlb_flush_vmid_range(&kvm->arch.mmu, - gfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT); + u64 size = nr_pages << PAGE_SHIFT; + u64 addr = gfn << PAGE_SHIFT; + + if (is_protected_kvm_enabled()) + kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle); + else + kvm_tlb_flush_vmid_range(&kvm->arch.mmu, addr, size); return 0; } @@ -225,7 +238,7 @@ static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head) void *pgtable = page_to_virt(page); s8 level = page_private(page); - kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level); + KVM_PGT_FN(kvm_pgtable_stage2_free_unlinked)(&kvm_s2_mm_ops, pgtable, level); } static void stage2_free_unlinked_table(void *addr, s8 level) @@ -324,7 +337,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON(size & ~PAGE_MASK); - WARN_ON(stage2_apply_range(mmu, start, end, kvm_pgtable_stage2_unmap, + WARN_ON(stage2_apply_range(mmu, start, end, KVM_PGT_FN(kvm_pgtable_stage2_unmap), may_block)); } @@ -336,7 +349,7 @@ void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { - stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_flush); + stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_flush)); } static void stage2_flush_memslot(struct kvm *kvm, @@ -704,10 +717,10 @@ int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr) mutex_lock(&kvm_hyp_pgd_mutex); /* - * Efficient stack verification using the PAGE_SHIFT bit implies + * Efficient stack verification using the NVHE_STACK_SHIFT bit implies * an alignment of our allocation on the order of the size. */ - size = PAGE_SIZE * 2; + size = NVHE_STACK_SIZE * 2; base = ALIGN_DOWN(io_map_base - size, size); ret = __hyp_alloc_private_va_range(base); @@ -724,12 +737,12 @@ int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr) * at the higher address and leave the lower guard page * unbacked. * - * Any valid stack address now has the PAGE_SHIFT bit as 1 + * Any valid stack address now has the NVHE_STACK_SHIFT bit as 1 * and addresses corresponding to the guard page have the - * PAGE_SHIFT bit as 0 - this is used for overflow detection. + * NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection. */ - ret = __create_hyp_mappings(base + PAGE_SIZE, PAGE_SIZE, phys_addr, - PAGE_HYP); + ret = __create_hyp_mappings(base + NVHE_STACK_SIZE, NVHE_STACK_SIZE, + phys_addr, PAGE_HYP); if (ret) kvm_err("Cannot map hyp stack\n"); @@ -942,10 +955,14 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t return -ENOMEM; mmu->arch = &kvm->arch; - err = kvm_pgtable_stage2_init(pgt, mmu, &kvm_s2_mm_ops); + err = KVM_PGT_FN(kvm_pgtable_stage2_init)(pgt, mmu, &kvm_s2_mm_ops); if (err) goto out_free_pgtable; + mmu->pgt = pgt; + if (is_protected_kvm_enabled()) + return 0; + mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran)); if (!mmu->last_vcpu_ran) { err = -ENOMEM; @@ -959,7 +976,6 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT; mmu->split_page_cache.gfp_zero = __GFP_ZERO; - mmu->pgt = pgt; mmu->pgd_phys = __pa(pgt->pgd); if (kvm_is_nested_s2_mmu(kvm, mmu)) @@ -968,7 +984,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t return 0; out_destroy_pgtable: - kvm_pgtable_stage2_destroy(pgt); + KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt); out_free_pgtable: kfree(pgt); return err; @@ -1065,7 +1081,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) write_unlock(&kvm->mmu_lock); if (pgt) { - kvm_pgtable_stage2_destroy(pgt); + KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt); kfree(pgt); } } @@ -1082,9 +1098,11 @@ static void *hyp_mc_alloc_fn(void *unused) void free_hyp_memcache(struct kvm_hyp_memcache *mc) { - if (is_protected_kvm_enabled()) - __free_hyp_memcache(mc, hyp_mc_free_fn, - kvm_host_va, NULL); + if (!is_protected_kvm_enabled()) + return; + + kfree(mc->mapping); + __free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, NULL); } int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) @@ -1092,6 +1110,12 @@ int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) if (!is_protected_kvm_enabled()) return 0; + if (!mc->mapping) { + mc->mapping = kzalloc(sizeof(struct pkvm_mapping), GFP_KERNEL_ACCOUNT); + if (!mc->mapping) + return -ENOMEM; + } + return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn, kvm_host_pa, NULL); } @@ -1130,8 +1154,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, break; write_lock(&kvm->mmu_lock); - ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot, - &cache, 0); + ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, addr, PAGE_SIZE, + pa, prot, &cache, 0); write_unlock(&kvm->mmu_lock); if (ret) break; @@ -1151,7 +1175,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, */ void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { - stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect); + stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_wrprotect)); } /** @@ -1442,9 +1466,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long mmu_seq; phys_addr_t ipa = fault_ipa; struct kvm *kvm = vcpu->kvm; - struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; struct vm_area_struct *vma; short vma_shift; + void *memcache; gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); @@ -1452,6 +1476,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt; struct page *page; + enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED; if (fault_is_perm) fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu); @@ -1471,8 +1496,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * and a write fault needs to collapse a block entry into a table. */ if (!fault_is_perm || (logging_active && write_fault)) { - ret = kvm_mmu_topup_memory_cache(memcache, - kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu)); + int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu); + + if (!is_protected_kvm_enabled()) { + memcache = &vcpu->arch.mmu_page_cache; + ret = kvm_mmu_topup_memory_cache(memcache, min_pages); + } else { + memcache = &vcpu->arch.pkvm_memcache; + ret = topup_hyp_memcache(memcache, min_pages); + } if (ret) return ret; } @@ -1493,7 +1525,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * logging_active is guaranteed to never be true for VM_PFNMAP * memslots. */ - if (logging_active) { + if (logging_active || is_protected_kvm_enabled()) { force_pte = true; vma_shift = PAGE_SHIFT; } else { @@ -1633,7 +1665,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, prot |= kvm_encode_nested_level(nested); } - read_lock(&kvm->mmu_lock); + kvm_fault_lock(kvm); pgt = vcpu->arch.hw_mmu->pgt; if (mmu_invalidate_retry(kvm, mmu_seq)) { ret = -EAGAIN; @@ -1695,18 +1727,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * PTE, which will be preserved. */ prot &= ~KVM_NV_GUEST_MAP_SZ; - ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); + ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, fault_ipa, prot, flags); } else { - ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, + ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, - memcache, - KVM_PGTABLE_WALK_HANDLE_FAULT | - KVM_PGTABLE_WALK_SHARED); + memcache, flags); } out_unlock: kvm_release_faultin_page(kvm, page, !!ret, writable); - read_unlock(&kvm->mmu_lock); + kvm_fault_unlock(kvm); /* Mark the page dirty only if the fault is handled successfully */ if (writable && !ret) @@ -1718,13 +1748,14 @@ out_unlock: /* Resolve the access fault by making the page young again. */ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { + enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED; struct kvm_s2_mmu *mmu; trace_kvm_access_fault(fault_ipa); read_lock(&vcpu->kvm->mmu_lock); mmu = vcpu->arch.hw_mmu; - kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa); + KVM_PGT_FN(kvm_pgtable_stage2_mkyoung)(mmu->pgt, fault_ipa, flags); read_unlock(&vcpu->kvm->mmu_lock); } @@ -1764,7 +1795,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) } /* Falls between the IPA range and the PARange? */ - if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) { + if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) { fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); if (is_iabt) @@ -1930,7 +1961,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (!kvm->arch.mmu.pgt) return false; - return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt, + return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, size, true); /* @@ -1946,7 +1977,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (!kvm->arch.mmu.pgt) return false; - return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt, + return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, size, false); } @@ -2056,6 +2087,7 @@ int __init kvm_mmu_init(u32 *hyp_va_bits) goto out_destroy_pgtable; io_map_base = hyp_idmap_start; + __hyp_va_bits = *hyp_va_bits; return 0; out_destroy_pgtable: diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 9b36218b48de..33d2ace68665 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -830,8 +830,10 @@ static void limit_nv_id_regs(struct kvm *kvm) NV_FTR(PFR0, RAS) | NV_FTR(PFR0, EL3) | NV_FTR(PFR0, EL2) | - NV_FTR(PFR0, EL1)); - /* 64bit EL1/EL2/EL3 only */ + NV_FTR(PFR0, EL1) | + NV_FTR(PFR0, EL0)); + /* 64bit only at any EL */ + val |= FIELD_PREP(NV_FTR(PFR0, EL0), 0b0001); val |= FIELD_PREP(NV_FTR(PFR0, EL1), 0b0001); val |= FIELD_PREP(NV_FTR(PFR0, EL2), 0b0001); val |= FIELD_PREP(NV_FTR(PFR0, EL3), 0b0001); @@ -963,14 +965,15 @@ static __always_inline void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, kvm->arch.sysreg_masks->mask[i].res1 = res1; } -int kvm_init_nv_sysregs(struct kvm *kvm) +int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; u64 res0, res1; lockdep_assert_held(&kvm->arch.config_lock); if (kvm->arch.sysreg_masks) - return 0; + goto out; kvm->arch.sysreg_masks = kzalloc(sizeof(*(kvm->arch.sysreg_masks)), GFP_KERNEL_ACCOUNT); @@ -1021,8 +1024,8 @@ int kvm_init_nv_sysregs(struct kvm *kvm) res0 |= HCR_NV2; if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, IMP)) res0 |= (HCR_AT | HCR_NV1 | HCR_NV); - if (!(__vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_ADDRESS) && - __vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_GENERIC))) + if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) && + kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC))) res0 |= (HCR_API | HCR_APK); if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TME, IMP)) res0 |= BIT(39); @@ -1078,8 +1081,8 @@ int kvm_init_nv_sysregs(struct kvm *kvm) /* HFG[RW]TR_EL2 */ res0 = res1 = 0; - if (!(__vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_ADDRESS) && - __vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_GENERIC))) + if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) && + kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC))) res0 |= (HFGxTR_EL2_APDAKey | HFGxTR_EL2_APDBKey | HFGxTR_EL2_APGAKey | HFGxTR_EL2_APIAKey | HFGxTR_EL2_APIBKey); @@ -1271,6 +1274,25 @@ int kvm_init_nv_sysregs(struct kvm *kvm) res0 |= MDCR_EL2_EnSTEPOP; set_sysreg_masks(kvm, MDCR_EL2, res0, res1); + /* CNTHCTL_EL2 */ + res0 = GENMASK(63, 20); + res1 = 0; + if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RME, IMP)) + res0 |= CNTHCTL_CNTPMASK | CNTHCTL_CNTVMASK; + if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, CNTPOFF)) { + res0 |= CNTHCTL_ECV; + if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, IMP)) + res0 |= (CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT | + CNTHCTL_EL1NVPCT | CNTHCTL_EL1NVVCT); + } + if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP)) + res0 |= GENMASK(11, 8); + set_sysreg_masks(kvm, CNTHCTL_EL2, res0, res1); + +out: + for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++) + (void)__vcpu_sys_reg(vcpu, sr); + return 0; } diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index 85117ea8f351..930b677eb9b0 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -268,3 +269,203 @@ static int __init finalize_pkvm(void) return ret; } device_initcall_sync(finalize_pkvm); + +static int cmp_mappings(struct rb_node *node, const struct rb_node *parent) +{ + struct pkvm_mapping *a = rb_entry(node, struct pkvm_mapping, node); + struct pkvm_mapping *b = rb_entry(parent, struct pkvm_mapping, node); + + if (a->gfn < b->gfn) + return -1; + if (a->gfn > b->gfn) + return 1; + return 0; +} + +static struct rb_node *find_first_mapping_node(struct rb_root *root, u64 gfn) +{ + struct rb_node *node = root->rb_node, *prev = NULL; + struct pkvm_mapping *mapping; + + while (node) { + mapping = rb_entry(node, struct pkvm_mapping, node); + if (mapping->gfn == gfn) + return node; + prev = node; + node = (gfn < mapping->gfn) ? node->rb_left : node->rb_right; + } + + return prev; +} + +/* + * __tmp is updated to rb_next(__tmp) *before* entering the body of the loop to allow freeing + * of __map inline. + */ +#define for_each_mapping_in_range_safe(__pgt, __start, __end, __map) \ + for (struct rb_node *__tmp = find_first_mapping_node(&(__pgt)->pkvm_mappings, \ + ((__start) >> PAGE_SHIFT)); \ + __tmp && ({ \ + __map = rb_entry(__tmp, struct pkvm_mapping, node); \ + __tmp = rb_next(__tmp); \ + true; \ + }); \ + ) \ + if (__map->gfn < ((__start) >> PAGE_SHIFT)) \ + continue; \ + else if (__map->gfn >= ((__end) >> PAGE_SHIFT)) \ + break; \ + else + +int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, + struct kvm_pgtable_mm_ops *mm_ops) +{ + pgt->pkvm_mappings = RB_ROOT; + pgt->mmu = mmu; + + return 0; +} + +void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) +{ + struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); + pkvm_handle_t handle = kvm->arch.pkvm.handle; + struct pkvm_mapping *mapping; + struct rb_node *node; + + if (!handle) + return; + + node = rb_first(&pgt->pkvm_mappings); + while (node) { + mapping = rb_entry(node, struct pkvm_mapping, node); + kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn); + node = rb_next(node); + rb_erase(&mapping->node, &pgt->pkvm_mappings); + kfree(mapping); + } +} + +int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, + u64 phys, enum kvm_pgtable_prot prot, + void *mc, enum kvm_pgtable_walk_flags flags) +{ + struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); + struct pkvm_mapping *mapping = NULL; + struct kvm_hyp_memcache *cache = mc; + u64 gfn = addr >> PAGE_SHIFT; + u64 pfn = phys >> PAGE_SHIFT; + int ret; + + if (size != PAGE_SIZE) + return -EINVAL; + + lockdep_assert_held_write(&kvm->mmu_lock); + ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, prot); + if (ret) { + /* Is the gfn already mapped due to a racing vCPU? */ + if (ret == -EPERM) + return -EAGAIN; + } + + swap(mapping, cache->mapping); + mapping->gfn = gfn; + mapping->pfn = pfn; + WARN_ON(rb_find_add(&mapping->node, &pgt->pkvm_mappings, cmp_mappings)); + + return ret; +} + +int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) +{ + struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); + pkvm_handle_t handle = kvm->arch.pkvm.handle; + struct pkvm_mapping *mapping; + int ret = 0; + + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) { + ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn); + if (WARN_ON(ret)) + break; + rb_erase(&mapping->node, &pgt->pkvm_mappings); + kfree(mapping); + } + + return ret; +} + +int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) +{ + struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); + pkvm_handle_t handle = kvm->arch.pkvm.handle; + struct pkvm_mapping *mapping; + int ret = 0; + + lockdep_assert_held(&kvm->mmu_lock); + for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) { + ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn); + if (WARN_ON(ret)) + break; + } + + return ret; +} + +int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size) +{ + struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); + struct pkvm_mapping *mapping; + + lockdep_assert_held(&kvm->mmu_lock); + for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) + __clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn), PAGE_SIZE); + + return 0; +} + +bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold) +{ + struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); + pkvm_handle_t handle = kvm->arch.pkvm.handle; + struct pkvm_mapping *mapping; + bool young = false; + + lockdep_assert_held(&kvm->mmu_lock); + for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) + young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn, + mkold); + + return young; +} + +int pkvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot, + enum kvm_pgtable_walk_flags flags) +{ + return kvm_call_hyp_nvhe(__pkvm_host_relax_perms_guest, addr >> PAGE_SHIFT, prot); +} + +void pkvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, + enum kvm_pgtable_walk_flags flags) +{ + WARN_ON(kvm_call_hyp_nvhe(__pkvm_host_mkyoung_guest, addr >> PAGE_SHIFT)); +} + +void pkvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level) +{ + WARN_ON_ONCE(1); +} + +kvm_pte_t *pkvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level, + enum kvm_pgtable_prot prot, void *mc, bool force_pte) +{ + WARN_ON_ONCE(1); + return NULL; +} + +int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, + struct kvm_mmu_memory_cache *mc) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 456102bc0b55..6c5950b9ceac 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -24,6 +24,7 @@ static DEFINE_MUTEX(arm_pmus_lock); static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc); static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc); +static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc); static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc) { @@ -327,48 +328,25 @@ u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu) return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX); } -/** - * kvm_pmu_enable_counter_mask - enable selected PMU counters - * @vcpu: The vcpu pointer - * @val: the value guest writes to PMCNTENSET register - * - * Call perf_event_enable to start counting the perf event - */ -void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +static void kvm_pmc_enable_perf_event(struct kvm_pmc *pmc) { - int i; - if (!kvm_vcpu_has_pmu(vcpu)) + if (!pmc->perf_event) { + kvm_pmu_create_perf_event(pmc); return; - - if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val) - return; - - for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { - struct kvm_pmc *pmc; - - if (!(val & BIT(i))) - continue; - - pmc = kvm_vcpu_idx_to_pmc(vcpu, i); - - if (!pmc->perf_event) { - kvm_pmu_create_perf_event(pmc); - } else { - perf_event_enable(pmc->perf_event); - if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) - kvm_debug("fail to enable perf event\n"); - } } + + perf_event_enable(pmc->perf_event); + if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) + kvm_debug("fail to enable perf event\n"); } -/** - * kvm_pmu_disable_counter_mask - disable selected PMU counters - * @vcpu: The vcpu pointer - * @val: the value guest writes to PMCNTENCLR register - * - * Call perf_event_disable to stop counting the perf event - */ -void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +static void kvm_pmc_disable_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) + perf_event_disable(pmc->perf_event); +} + +void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; @@ -376,16 +354,18 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) return; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { - struct kvm_pmc *pmc; + struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); if (!(val & BIT(i))) continue; - pmc = kvm_vcpu_idx_to_pmc(vcpu, i); - - if (pmc->perf_event) - perf_event_disable(pmc->perf_event); + if (kvm_pmu_counter_is_enabled(pmc)) + kvm_pmc_enable_perf_event(pmc); + else + kvm_pmc_disable_perf_event(pmc); } + + kvm_vcpu_pmu_restore_guest(vcpu); } /* @@ -626,27 +606,28 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) val &= ~ARMV8_PMU_PMCR_LP; + /* Request a reload of the PMU to enable/disable affected counters */ + if ((__vcpu_sys_reg(vcpu, PMCR_EL0) ^ val) & ARMV8_PMU_PMCR_E) + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); + /* The reset bits don't indicate any state, and shouldn't be saved. */ __vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P); - if (val & ARMV8_PMU_PMCR_E) { - kvm_pmu_enable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); - } else { - kvm_pmu_disable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); - } - if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { - unsigned long mask = kvm_pmu_accessible_counter_mask(vcpu); - mask &= ~BIT(ARMV8_PMU_CYCLE_IDX); + /* + * Unlike other PMU sysregs, the controls in PMCR_EL0 always apply + * to the 'guest' range of counters and never the 'hyp' range. + */ + unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) & + ~kvm_pmu_hyp_counter_mask(vcpu) & + ~BIT(ARMV8_PMU_CYCLE_IDX); + for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } - kvm_vcpu_pmu_restore_guest(vcpu); } static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) @@ -910,11 +891,11 @@ void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) { u64 mask = kvm_pmu_implemented_counter_mask(vcpu); - kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu)); - __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask; __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask; __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask; + + kvm_pmu_reprogram_counter_mask(vcpu, mask); } int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 470524b31951..803e11b0dc8f 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -85,7 +85,7 @@ static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) * KVM_REG_ARM64_SVE_VLS. Allocation is deferred until * kvm_arm_vcpu_finalize(), which freezes the configuration. */ - vcpu_set_flag(vcpu, GUEST_HAS_SVE); + set_bit(KVM_ARCH_FLAG_GUEST_HAS_SVE, &vcpu->kvm->arch.flags); } /* @@ -211,10 +211,6 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu) kvm_vcpu_reset_sve(vcpu); } - if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) || - vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC)) - kvm_vcpu_enable_ptrauth(vcpu); - if (vcpu_el1_is_32bit(vcpu)) pstate = VCPU_RESET_PSTATE_SVC; else if (vcpu_has_nv(vcpu)) diff --git a/arch/arm64/kvm/stacktrace.c b/arch/arm64/kvm/stacktrace.c index 3ace5b75813b..af5eec681127 100644 --- a/arch/arm64/kvm/stacktrace.c +++ b/arch/arm64/kvm/stacktrace.c @@ -19,6 +19,7 @@ #include #include +#include #include static struct stack_info stackinfo_get_overflow(void) @@ -50,7 +51,7 @@ static struct stack_info stackinfo_get_hyp(void) struct kvm_nvhe_stacktrace_info *stacktrace_info = this_cpu_ptr_nvhe_sym(kvm_stacktrace_info); unsigned long low = (unsigned long)stacktrace_info->stack_base; - unsigned long high = low + PAGE_SIZE; + unsigned long high = low + NVHE_STACK_SIZE; return (struct stack_info) { .low = low, @@ -60,8 +61,8 @@ static struct stack_info stackinfo_get_hyp(void) static struct stack_info stackinfo_get_hyp_kern_va(void) { - unsigned long low = (unsigned long)*this_cpu_ptr(&kvm_arm_hyp_stack_page); - unsigned long high = low + PAGE_SIZE; + unsigned long low = (unsigned long)*this_cpu_ptr(&kvm_arm_hyp_stack_base); + unsigned long high = low + NVHE_STACK_SIZE; return (struct stack_info) { .low = low, @@ -145,7 +146,7 @@ static void unwind(struct unwind_state *state, */ static bool kvm_nvhe_dump_backtrace_entry(void *arg, unsigned long where) { - unsigned long va_mask = GENMASK_ULL(vabits_actual - 1, 0); + unsigned long va_mask = GENMASK_ULL(__hyp_va_bits - 1, 0); unsigned long hyp_offset = (unsigned long)arg; /* Mask tags and convert to kern addr */ diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e2a5c2918d9e..f6cd1ea7fb55 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -570,17 +570,10 @@ static bool trap_oslar_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - u64 oslsr; - if (!p->is_write) return read_from_write_only(vcpu, p, r); - /* Forward the OSLK bit to OSLSR */ - oslsr = __vcpu_sys_reg(vcpu, OSLSR_EL1) & ~OSLSR_EL1_OSLK; - if (p->regval & OSLAR_EL1_OSLK) - oslsr |= OSLSR_EL1_OSLK; - - __vcpu_sys_reg(vcpu, OSLSR_EL1) = oslsr; + kvm_debug_handle_oslar(vcpu, p->regval); return true; } @@ -621,43 +614,13 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, } } -/* - * We want to avoid world-switching all the DBG registers all the - * time: - * - * - If we've touched any debug register, it is likely that we're - * going to touch more of them. It then makes sense to disable the - * traps and start doing the save/restore dance - * - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is - * then mandatory to save/restore the registers, as the guest - * depends on them. - * - * For this, we use a DIRTY bit, indicating the guest has modified the - * debug registers, used as follow: - * - * On guest entry: - * - If the dirty bit is set (because we're coming back from trapping), - * disable the traps, save host registers, restore guest registers. - * - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), - * set the dirty bit, disable the traps, save host registers, - * restore guest registers. - * - Otherwise, enable the traps - * - * On guest exit: - * - If the dirty bit is set, save guest registers, restore host - * registers and clear the dirty bit. This ensure that the host can - * now use the debug registers. - */ static bool trap_debug_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { access_rw(vcpu, p, r); - if (p->is_write) - vcpu_set_flag(vcpu, DEBUG_DIRTY); - - trace_trap_reg(__func__, r->reg, p->is_write, p->regval); + kvm_debug_set_guest_ownership(vcpu); return true; } @@ -666,9 +629,6 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu, * * A 32 bit write to a debug register leave top bits alone * A 32 bit read from a debug register only returns the bottom bits - * - * All writes will set the DEBUG_DIRTY flag to ensure the hyp code - * switches between host and guest values in future. */ static void reg_to_dbg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, @@ -683,8 +643,6 @@ static void reg_to_dbg(struct kvm_vcpu *vcpu, val &= ~mask; val |= (p->regval & (mask >> shift)) << shift; *dbg_reg = val; - - vcpu_set_flag(vcpu, DEBUG_DIRTY); } static void dbg_to_reg(struct kvm_vcpu *vcpu, @@ -698,152 +656,79 @@ static void dbg_to_reg(struct kvm_vcpu *vcpu, p->regval = (*dbg_reg & mask) >> shift; } -static bool trap_bvr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) +static u64 *demux_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; + struct kvm_guest_debug_arch *dbg = &vcpu->arch.vcpu_debug_state; + + switch (rd->Op2) { + case 0b100: + return &dbg->dbg_bvr[rd->CRm]; + case 0b101: + return &dbg->dbg_bcr[rd->CRm]; + case 0b110: + return &dbg->dbg_wvr[rd->CRm]; + case 0b111: + return &dbg->dbg_wcr[rd->CRm]; + default: + KVM_BUG_ON(1, vcpu->kvm); + return NULL; + } +} + +static bool trap_dbg_wb_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *rd) +{ + u64 *reg = demux_wb_reg(vcpu, rd); + + if (!reg) + return false; if (p->is_write) - reg_to_dbg(vcpu, p, rd, dbg_reg); + reg_to_dbg(vcpu, p, rd, reg); else - dbg_to_reg(vcpu, p, rd, dbg_reg); - - trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); + dbg_to_reg(vcpu, p, rd, reg); + kvm_debug_set_guest_ownership(vcpu); return true; } -static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, - u64 val) +static int set_dbg_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + u64 val) { - vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = val; + u64 *reg = demux_wb_reg(vcpu, rd); + + if (!reg) + return -EINVAL; + + *reg = val; return 0; } -static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, - u64 *val) +static int get_dbg_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + u64 *val) { - *val = vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; + u64 *reg = demux_wb_reg(vcpu, rd); + + if (!reg) + return -EINVAL; + + *val = *reg; return 0; } -static u64 reset_bvr(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) +static u64 reset_dbg_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = rd->val; - return rd->val; -} + u64 *reg = demux_wb_reg(vcpu, rd); -static bool trap_bcr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; + /* + * Bail early if we couldn't find storage for the register, the + * KVM_BUG_ON() in demux_wb_reg() will prevent this VM from ever + * being run. + */ + if (!reg) + return 0; - if (p->is_write) - reg_to_dbg(vcpu, p, rd, dbg_reg); - else - dbg_to_reg(vcpu, p, rd, dbg_reg); - - trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); - - return true; -} - -static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, - u64 val) -{ - vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = val; - return 0; -} - -static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, - u64 *val) -{ - *val = vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; - return 0; -} - -static u64 reset_bcr(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) -{ - vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = rd->val; - return rd->val; -} - -static bool trap_wvr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; - - if (p->is_write) - reg_to_dbg(vcpu, p, rd, dbg_reg); - else - dbg_to_reg(vcpu, p, rd, dbg_reg); - - trace_trap_reg(__func__, rd->CRm, p->is_write, - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]); - - return true; -} - -static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, - u64 val) -{ - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = val; - return 0; -} - -static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, - u64 *val) -{ - *val = vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; - return 0; -} - -static u64 reset_wvr(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) -{ - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = rd->val; - return rd->val; -} - -static bool trap_wcr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; - - if (p->is_write) - reg_to_dbg(vcpu, p, rd, dbg_reg); - else - dbg_to_reg(vcpu, p, rd, dbg_reg); - - trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); - - return true; -} - -static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, - u64 val) -{ - vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = val; - return 0; -} - -static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, - u64 *val) -{ - *val = vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; - return 0; -} - -static u64 reset_wcr(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) -{ - vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = rd->val; + *reg = rd->val; return rd->val; } @@ -1208,16 +1093,14 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, mask = kvm_pmu_accessible_counter_mask(vcpu); if (p->is_write) { val = p->regval & mask; - if (r->Op2 & 0x1) { + if (r->Op2 & 0x1) /* accessing PMCNTENSET_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val; - kvm_pmu_enable_counter_mask(vcpu, val); - kvm_vcpu_pmu_restore_guest(vcpu); - } else { + else /* accessing PMCNTENCLR_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val; - kvm_pmu_disable_counter_mask(vcpu, val); - } + + kvm_pmu_reprogram_counter_mask(vcpu, val); } else { p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); } @@ -1352,13 +1235,17 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ - trap_bvr, reset_bvr, 0, 0, get_bvr, set_bvr }, \ + trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0, \ + get_dbg_wb_reg, set_dbg_wb_reg }, \ { SYS_DESC(SYS_DBGBCRn_EL1(n)), \ - trap_bcr, reset_bcr, 0, 0, get_bcr, set_bcr }, \ + trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0, \ + get_dbg_wb_reg, set_dbg_wb_reg }, \ { SYS_DESC(SYS_DBGWVRn_EL1(n)), \ - trap_wvr, reset_wvr, 0, 0, get_wvr, set_wvr }, \ + trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0, \ + get_dbg_wb_reg, set_dbg_wb_reg }, \ { SYS_DESC(SYS_DBGWCRn_EL1(n)), \ - trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr } + trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0, \ + get_dbg_wb_reg, set_dbg_wb_reg } #define PMU_SYS_REG(name) \ SYS_DESC(SYS_##name), .reset = reset_pmu_reg, \ @@ -1412,26 +1299,146 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, switch (reg) { case SYS_CNTP_TVAL_EL0: + if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) + tmr = TIMER_HPTIMER; + else + tmr = TIMER_PTIMER; + treg = TIMER_REG_TVAL; + break; + + case SYS_CNTV_TVAL_EL0: + if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) + tmr = TIMER_HVTIMER; + else + tmr = TIMER_VTIMER; + treg = TIMER_REG_TVAL; + break; + case SYS_AARCH32_CNTP_TVAL: + case SYS_CNTP_TVAL_EL02: tmr = TIMER_PTIMER; treg = TIMER_REG_TVAL; break; + + case SYS_CNTV_TVAL_EL02: + tmr = TIMER_VTIMER; + treg = TIMER_REG_TVAL; + break; + + case SYS_CNTHP_TVAL_EL2: + tmr = TIMER_HPTIMER; + treg = TIMER_REG_TVAL; + break; + + case SYS_CNTHV_TVAL_EL2: + tmr = TIMER_HVTIMER; + treg = TIMER_REG_TVAL; + break; + case SYS_CNTP_CTL_EL0: + if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) + tmr = TIMER_HPTIMER; + else + tmr = TIMER_PTIMER; + treg = TIMER_REG_CTL; + break; + + case SYS_CNTV_CTL_EL0: + if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) + tmr = TIMER_HVTIMER; + else + tmr = TIMER_VTIMER; + treg = TIMER_REG_CTL; + break; + case SYS_AARCH32_CNTP_CTL: + case SYS_CNTP_CTL_EL02: tmr = TIMER_PTIMER; treg = TIMER_REG_CTL; break; + + case SYS_CNTV_CTL_EL02: + tmr = TIMER_VTIMER; + treg = TIMER_REG_CTL; + break; + + case SYS_CNTHP_CTL_EL2: + tmr = TIMER_HPTIMER; + treg = TIMER_REG_CTL; + break; + + case SYS_CNTHV_CTL_EL2: + tmr = TIMER_HVTIMER; + treg = TIMER_REG_CTL; + break; + case SYS_CNTP_CVAL_EL0: + if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) + tmr = TIMER_HPTIMER; + else + tmr = TIMER_PTIMER; + treg = TIMER_REG_CVAL; + break; + + case SYS_CNTV_CVAL_EL0: + if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) + tmr = TIMER_HVTIMER; + else + tmr = TIMER_VTIMER; + treg = TIMER_REG_CVAL; + break; + case SYS_AARCH32_CNTP_CVAL: + case SYS_CNTP_CVAL_EL02: tmr = TIMER_PTIMER; treg = TIMER_REG_CVAL; break; + + case SYS_CNTV_CVAL_EL02: + tmr = TIMER_VTIMER; + treg = TIMER_REG_CVAL; + break; + + case SYS_CNTHP_CVAL_EL2: + tmr = TIMER_HPTIMER; + treg = TIMER_REG_CVAL; + break; + + case SYS_CNTHV_CVAL_EL2: + tmr = TIMER_HVTIMER; + treg = TIMER_REG_CVAL; + break; + case SYS_CNTPCT_EL0: case SYS_CNTPCTSS_EL0: + if (is_hyp_ctxt(vcpu)) + tmr = TIMER_HPTIMER; + else + tmr = TIMER_PTIMER; + treg = TIMER_REG_CNT; + break; + case SYS_AARCH32_CNTPCT: + case SYS_AARCH32_CNTPCTSS: tmr = TIMER_PTIMER; treg = TIMER_REG_CNT; break; + + case SYS_CNTVCT_EL0: + case SYS_CNTVCTSS_EL0: + if (is_hyp_ctxt(vcpu)) + tmr = TIMER_HVTIMER; + else + tmr = TIMER_VTIMER; + treg = TIMER_REG_CNT; + break; + + case SYS_AARCH32_CNTVCT: + case SYS_AARCH32_CNTVCTSS: + tmr = TIMER_VTIMER; + treg = TIMER_REG_CNT; + break; + default: print_sys_reg_msg(p, "%s", "Unhandled trapped timer register"); return undef_access(vcpu, p, r); @@ -1601,9 +1608,13 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, if (!vcpu_has_ptrauth(vcpu)) val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) | ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3)); - if (!cpus_have_final_cap(ARM64_HAS_WFXT)) + if (!cpus_have_final_cap(ARM64_HAS_WFXT) || + has_broken_cntvoff()) val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_WFxT); break; + case SYS_ID_AA64ISAR3_EL1: + val &= ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_FAMINMAX; + break; case SYS_ID_AA64MMFR2_EL1: val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK; break; @@ -1806,6 +1817,9 @@ static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val) /* Hide SPE from guests */ val &= ~ID_AA64DFR0_EL1_PMSVer_MASK; + /* Hide BRBE from guests */ + val &= ~ID_AA64DFR0_EL1_BRBE_MASK; + return val; } @@ -2450,6 +2464,26 @@ static unsigned int s1pie_el2_visibility(const struct kvm_vcpu *vcpu, return __el2_visibility(vcpu, rd, s1pie_visibility); } +static bool access_mdcr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + u64 old = __vcpu_sys_reg(vcpu, MDCR_EL2); + + if (!access_rw(vcpu, p, r)) + return false; + + /* + * Request a reload of the PMU to enable/disable the counters affected + * by HPME. + */ + if ((old ^ __vcpu_sys_reg(vcpu, MDCR_EL2)) & MDCR_EL2_HPME) + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); + + return true; +} + + /* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 @@ -2608,7 +2642,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_WRITABLE(ID_AA64ISAR2_EL1, ~(ID_AA64ISAR2_EL1_RES0 | ID_AA64ISAR2_EL1_APA3 | ID_AA64ISAR2_EL1_GPA3)), - ID_UNALLOCATED(6,3), + ID_WRITABLE(ID_AA64ISAR3_EL1, (ID_AA64ISAR3_EL1_FPRCVT | + ID_AA64ISAR3_EL1_FAMINMAX)), ID_UNALLOCATED(6,4), ID_UNALLOCATED(6,5), ID_UNALLOCATED(6,6), @@ -2902,11 +2937,17 @@ static const struct sys_reg_desc sys_reg_descs[] = { AMU_AMEVTYPER1_EL0(15), { SYS_DESC(SYS_CNTPCT_EL0), access_arch_timer }, + { SYS_DESC(SYS_CNTVCT_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTPCTSS_EL0), access_arch_timer }, + { SYS_DESC(SYS_CNTVCTSS_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer }, + { SYS_DESC(SYS_CNTV_TVAL_EL0), access_arch_timer }, + { SYS_DESC(SYS_CNTV_CTL_EL0), access_arch_timer }, + { SYS_DESC(SYS_CNTV_CVAL_EL0), access_arch_timer }, + /* PMEVCNTRn_EL0 */ PMU_PMEVCNTR_EL0(0), PMU_PMEVCNTR_EL0(1), @@ -2983,7 +3024,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1), EL2_REG(ACTLR_EL2, access_rw, reset_val, 0), EL2_REG_VNCR(HCR_EL2, reset_hcr, 0), - EL2_REG(MDCR_EL2, access_rw, reset_val, 0), + EL2_REG(MDCR_EL2, access_mdcr, reset_val, 0), EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1), EL2_REG_VNCR(HSTR_EL2, reset_val, 0), EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0), @@ -3058,9 +3099,24 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG_VNCR(CNTVOFF_EL2, reset_val, 0), EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0), + { SYS_DESC(SYS_CNTHP_TVAL_EL2), access_arch_timer }, + EL2_REG(CNTHP_CTL_EL2, access_arch_timer, reset_val, 0), + EL2_REG(CNTHP_CVAL_EL2, access_arch_timer, reset_val, 0), + + { SYS_DESC(SYS_CNTHV_TVAL_EL2), access_arch_timer }, + EL2_REG(CNTHV_CTL_EL2, access_arch_timer, reset_val, 0), + EL2_REG(CNTHV_CVAL_EL2, access_arch_timer, reset_val, 0), { SYS_DESC(SYS_CNTKCTL_EL12), access_cntkctl_el12 }, + { SYS_DESC(SYS_CNTP_TVAL_EL02), access_arch_timer }, + { SYS_DESC(SYS_CNTP_CTL_EL02), access_arch_timer }, + { SYS_DESC(SYS_CNTP_CVAL_EL02), access_arch_timer }, + + { SYS_DESC(SYS_CNTV_TVAL_EL02), access_arch_timer }, + { SYS_DESC(SYS_CNTV_CTL_EL02), access_arch_timer }, + { SYS_DESC(SYS_CNTV_CVAL_EL02), access_arch_timer }, + EL2_REG(SP_EL2, NULL, reset_unknown, 0), }; @@ -3572,18 +3628,20 @@ static bool trap_dbgdidr(struct kvm_vcpu *vcpu, * None of the other registers share their location, so treat them as * if they were 64bit. */ -#define DBG_BCR_BVR_WCR_WVR(n) \ - /* DBGBVRn */ \ - { AA32(LO), Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_bvr, NULL, n }, \ - /* DBGBCRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_bcr, NULL, n }, \ - /* DBGWVRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_wvr, NULL, n }, \ - /* DBGWCRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_wcr, NULL, n } +#define DBG_BCR_BVR_WCR_WVR(n) \ + /* DBGBVRn */ \ + { AA32(LO), Op1( 0), CRn( 0), CRm((n)), Op2( 4), \ + trap_dbg_wb_reg, NULL, n }, \ + /* DBGBCRn */ \ + { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_dbg_wb_reg, NULL, n }, \ + /* DBGWVRn */ \ + { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_dbg_wb_reg, NULL, n }, \ + /* DBGWCRn */ \ + { Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_dbg_wb_reg, NULL, n } -#define DBGBXVR(n) \ - { AA32(HI), Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_bvr, NULL, n } +#define DBGBXVR(n) \ + { AA32(HI), Op1( 0), CRn( 1), CRm((n)), Op2( 1), \ + trap_dbg_wb_reg, NULL, n } /* * Trapped cp14 registers. We generally ignore most of the external @@ -3880,9 +3938,11 @@ static const struct sys_reg_desc cp15_64_regs[] = { { SYS_DESC(SYS_AARCH32_CNTPCT), access_arch_timer }, { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR1_EL1 }, { Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */ + { SYS_DESC(SYS_AARCH32_CNTVCT), access_arch_timer }, { Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */ { SYS_DESC(SYS_AARCH32_CNTP_CVAL), access_arch_timer }, { SYS_DESC(SYS_AARCH32_CNTPCTSS), access_arch_timer }, + { SYS_DESC(SYS_AARCH32_CNTVCTSS), access_arch_timer }, }; static bool check_sysreg_table(const struct sys_reg_desc *table, unsigned int n, @@ -4397,6 +4457,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) reset_vcpu_ftr_id_reg(vcpu, r); else r->reset(vcpu, r); + + if (r->reg >= __SANITISED_REG_START__ && r->reg < NR_SYS_REGS) + (void)__vcpu_sys_reg(vcpu, r->reg); } set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags); @@ -4973,6 +5036,14 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu) kvm->arch.fgu[HAFGRTR_GROUP] |= ~(HAFGRTR_EL2_RES0 | HAFGRTR_EL2_RES1); + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP)) { + kvm->arch.fgu[HDFGRTR_GROUP] |= (HDFGRTR_EL2_nBRBDATA | + HDFGRTR_EL2_nBRBCTL | + HDFGRTR_EL2_nBRBIDR); + kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_nBRBINJ | + HFGITR_EL2_nBRBIALL); + } + set_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags); out: mutex_unlock(&kvm->arch.config_lock); @@ -5000,7 +5071,7 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu) } if (vcpu_has_nv(vcpu)) { - int ret = kvm_init_nv_sysregs(kvm); + int ret = kvm_init_nv_sysregs(vcpu); if (ret) return ret; } diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h index 064a58c19f48..f85415db7713 100644 --- a/arch/arm64/kvm/trace_handle_exit.h +++ b/arch/arm64/kvm/trace_handle_exit.h @@ -46,38 +46,6 @@ TRACE_EVENT(kvm_hvc_arm64, __entry->vcpu_pc, __entry->r0, __entry->imm) ); -TRACE_EVENT(kvm_arm_setup_debug, - TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), - TP_ARGS(vcpu, guest_debug), - - TP_STRUCT__entry( - __field(struct kvm_vcpu *, vcpu) - __field(__u32, guest_debug) - ), - - TP_fast_assign( - __entry->vcpu = vcpu; - __entry->guest_debug = guest_debug; - ), - - TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) -); - -TRACE_EVENT(kvm_arm_clear_debug, - TP_PROTO(__u32 guest_debug), - TP_ARGS(guest_debug), - - TP_STRUCT__entry( - __field(__u32, guest_debug) - ), - - TP_fast_assign( - __entry->guest_debug = guest_debug; - ), - - TP_printk("flags: 0x%08x", __entry->guest_debug) -); - /* * The dreg32 name is a leftover from a distant past. This will really * output a 64bit value... @@ -99,49 +67,6 @@ TRACE_EVENT(kvm_arm_set_dreg32, TP_printk("%s: 0x%llx", __entry->name, __entry->value) ); -TRACE_DEFINE_SIZEOF(__u64); - -TRACE_EVENT(kvm_arm_set_regset, - TP_PROTO(const char *type, int len, __u64 *control, __u64 *value), - TP_ARGS(type, len, control, value), - TP_STRUCT__entry( - __field(const char *, name) - __field(int, len) - __array(u64, ctrls, 16) - __array(u64, values, 16) - ), - TP_fast_assign( - __entry->name = type; - __entry->len = len; - memcpy(__entry->ctrls, control, len << 3); - memcpy(__entry->values, value, len << 3); - ), - TP_printk("%d %s CTRL:%s VALUE:%s", __entry->len, __entry->name, - __print_array(__entry->ctrls, __entry->len, sizeof(__u64)), - __print_array(__entry->values, __entry->len, sizeof(__u64))) -); - -TRACE_EVENT(trap_reg, - TP_PROTO(const char *fn, int reg, bool is_write, u64 write_value), - TP_ARGS(fn, reg, is_write, write_value), - - TP_STRUCT__entry( - __field(const char *, fn) - __field(int, reg) - __field(bool, is_write) - __field(u64, write_value) - ), - - TP_fast_assign( - __entry->fn = fn; - __entry->reg = reg; - __entry->is_write = is_write; - __entry->write_value = write_value; - ), - - TP_printk("%s %s reg %d (0x%016llx)", __entry->fn, __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value) -); - TRACE_EVENT(kvm_handle_sys_reg, TP_PROTO(unsigned long hsr), TP_ARGS(hsr), diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index f267bc2486a1..d7233ab982d0 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -663,9 +664,9 @@ int vgic_v3_probe(const struct gic_kvm_info *info) if (info->has_v4) { kvm_vgic_global_state.has_gicv4 = gicv4_enable; kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable; - kvm_info("GICv4%s support %sabled\n", + kvm_info("GICv4%s support %s\n", kvm_vgic_global_state.has_gicv4_1 ? ".1" : "", - gicv4_enable ? "en" : "dis"); + str_enabled_disabled(gicv4_enable)); } kvm_vgic_global_state.vcpu_base = 0; @@ -734,7 +735,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if); + if (likely(!is_protected_kvm_enabled())) + kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if); if (has_vhe()) __vgic_v3_activate_traps(cpu_if); @@ -746,7 +748,8 @@ void vgic_v3_put(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if); + if (likely(!is_protected_kvm_enabled())) + kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if); WARN_ON(vgic_v4_put(vcpu)); if (has_vhe()) diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 8e882f479d98..4d49dff721a8 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -13,7 +13,11 @@ endif lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o -obj-$(CONFIG_CRC32) += crc32.o crc32-glue.o +obj-$(CONFIG_CRC32_ARCH) += crc32-arm64.o +crc32-arm64-y := crc32.o crc32-glue.o + +obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-arm64.o +crc-t10dif-arm64-y := crc-t10dif-glue.o crc-t10dif-core.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/lib/crc-t10dif-core.S similarity index 100% rename from arch/arm64/crypto/crct10dif-ce-core.S rename to arch/arm64/lib/crc-t10dif-core.S diff --git a/arch/arm64/lib/crc-t10dif-glue.c b/arch/arm64/lib/crc-t10dif-glue.c new file mode 100644 index 000000000000..dab7e3796232 --- /dev/null +++ b/arch/arm64/lib/crc-t10dif-glue.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions + * + * Copyright (C) 2016 - 2017 Linaro Ltd + */ + +#include +#include +#include +#include +#include +#include + +#include + +#include +#include + +static DEFINE_STATIC_KEY_FALSE(have_asimd); +static DEFINE_STATIC_KEY_FALSE(have_pmull); + +#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U + +asmlinkage void crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len, + u8 out[16]); +asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len); + +u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length) +{ + if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE) { + if (static_branch_likely(&have_pmull)) { + if (crypto_simd_usable()) { + kernel_neon_begin(); + crc = crc_t10dif_pmull_p64(crc, data, length); + kernel_neon_end(); + return crc; + } + } else if (length > CRC_T10DIF_PMULL_CHUNK_SIZE && + static_branch_likely(&have_asimd) && + crypto_simd_usable()) { + u8 buf[16]; + + kernel_neon_begin(); + crc_t10dif_pmull_p8(crc, data, length, buf); + kernel_neon_end(); + + crc = 0; + data = buf; + length = sizeof(buf); + } + } + return crc_t10dif_generic(crc, data, length); +} +EXPORT_SYMBOL(crc_t10dif_arch); + +static int __init crc_t10dif_arm64_init(void) +{ + if (cpu_have_named_feature(ASIMD)) { + static_branch_enable(&have_asimd); + if (cpu_have_named_feature(PMULL)) + static_branch_enable(&have_pmull); + } + return 0; +} +arch_initcall(crc_t10dif_arm64_init); + +static void __exit crc_t10dif_arm64_exit(void) +{ +} +module_exit(crc_t10dif_arm64_exit); + +bool crc_t10dif_is_optimized(void) +{ + return static_key_enabled(&have_asimd); +} +EXPORT_SYMBOL(crc_t10dif_is_optimized); + +MODULE_AUTHOR("Ard Biesheuvel "); +MODULE_DESCRIPTION("CRC-T10DIF using arm64 NEON and Crypto Extensions"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/arm64/lib/crc32-glue.c b/arch/arm64/lib/crc32-glue.c index 295ae3e6b997..15c4c9db573e 100644 --- a/arch/arm64/lib/crc32-glue.c +++ b/arch/arm64/lib/crc32-glue.c @@ -2,6 +2,7 @@ #include #include +#include #include #include @@ -21,7 +22,7 @@ asmlinkage u32 crc32_le_arm64_4way(u32 crc, unsigned char const *p, size_t len); asmlinkage u32 crc32c_le_arm64_4way(u32 crc, unsigned char const *p, size_t len); asmlinkage u32 crc32_be_arm64_4way(u32 crc, unsigned char const *p, size_t len); -u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) +u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len) { if (!alternative_has_cap_likely(ARM64_HAS_CRC32)) return crc32_le_base(crc, p, len); @@ -40,11 +41,12 @@ u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) return crc32_le_arm64(crc, p, len); } +EXPORT_SYMBOL(crc32_le_arch); -u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) +u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len) { if (!alternative_has_cap_likely(ARM64_HAS_CRC32)) - return __crc32c_le_base(crc, p, len); + return crc32c_le_base(crc, p, len); if (len >= min_len && cpu_have_named_feature(PMULL) && crypto_simd_usable()) { kernel_neon_begin(); @@ -60,8 +62,9 @@ u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) return crc32c_le_arm64(crc, p, len); } +EXPORT_SYMBOL(crc32c_le_arch); -u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) +u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len) { if (!alternative_has_cap_likely(ARM64_HAS_CRC32)) return crc32_be_base(crc, p, len); @@ -80,3 +83,17 @@ u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) return crc32_be_arm64(crc, p, len); } +EXPORT_SYMBOL(crc32_be_arch); + +u32 crc32_optimizations(void) +{ + if (alternative_has_cap_likely(ARM64_HAS_CRC32)) + return CRC32_LE_OPTIMIZATION | + CRC32_BE_OPTIMIZATION | + CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("arm64-optimized CRC32 functions"); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 3215adf48a1b..98a2a0e64e25 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -519,6 +519,18 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, static int __init hugetlbpage_init(void) { + /* + * HugeTLB pages are supported on maximum four page table + * levels (PUD, CONT PMD, PMD, CONT PTE) for a given base + * page size, corresponding to hugetlb_add_hstate() calls + * here. + * + * HUGE_MAX_HSTATE should at least match maximum supported + * HugeTLB page sizes on the platform. Any new addition to + * supported HugeTLB page sizes will also require changing + * HUGE_MAX_HSTATE as well. + */ + BUILD_BUG_ON(HUGE_MAX_HSTATE < 4); if (pud_sect_supported()) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index ccdef53872a0..9c0b8d9558fc 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -279,7 +279,12 @@ void __init arm64_memblock_init(void) if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern u16 memstart_offset_seed; - u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); + + /* + * Use the sanitised version of id_aa64mmfr0_el1 so that linear + * map randomization can be enabled by shrinking the IPA space. + */ + u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); int parange = cpuid_feature_extract_unsigned_field( mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); s64 range = linear_region_size - diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e2739b69e11b..b4df5bc5b1b8 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1169,7 +1169,8 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, unsigned long addr, unsigned long next) { vmemmap_verify((pte_t *)pmdp, node, addr, next); - return 1; + + return pmd_sect(READ_ONCE(*pmdp)); } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 0c501cabc238..8160cff35089 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -33,7 +33,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) gfp_t gfp = GFP_PGTABLE_USER; if (pgdir_is_page_size()) - return (pgd_t *)__get_free_page(gfp); + return __pgd_alloc(mm, 0); else return kmem_cache_alloc(pgd_cache, gfp); } @@ -41,7 +41,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) void pgd_free(struct mm_struct *mm, pgd_t *pgd) { if (pgdir_is_page_size()) - free_page((unsigned long)pgd); + __pgd_free(mm, pgd); else kmem_cache_free(pgd_cache, pgd); } diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index b8edc5765441..fb30c8804f87 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -501,7 +501,7 @@ alternative_else_nop_endif #ifdef CONFIG_ARM64_HAFT cmp x9, ID_AA64MMFR1_EL1_HAFDBS_HAFT b.lt 1f - orr tcr2, tcr2, TCR2_EL1x_HAFT + orr tcr2, tcr2, TCR2_EL1_HAFT #endif /* CONFIG_ARM64_HAFT */ 1: #endif /* CONFIG_ARM64_HW_AFDBM */ @@ -532,7 +532,8 @@ alternative_else_nop_endif #undef PTE_MAYBE_NG #undef PTE_MAYBE_SHARED - orr tcr2, tcr2, TCR2_EL1x_PIE + orr tcr2, tcr2, TCR2_EL1_PIE + msr REG_TCR2_EL1, x0 .Lskip_indirection: diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index 0f7b484cb2ff..19c67ed1a21f 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -57,7 +57,7 @@ static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr) */ BUG_ON(!pfn_valid(pte_pfn(pte))); - __set_pte(dst_ptep, pte_mkpresent(pte_mkwrite_novma(pte))); + __set_pte(dst_ptep, pte_mkvalid(pte_mkwrite_novma(pte))); } } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 66708b95493a..8446848edddb 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -267,6 +267,19 @@ static bool is_addsub_imm(u32 imm) return !(imm & ~0xfff) || !(imm & ~0xfff000); } +static inline void emit_a64_add_i(const bool is64, const int dst, const int src, + const int tmp, const s32 imm, struct jit_ctx *ctx) +{ + if (is_addsub_imm(imm)) { + emit(A64_ADD_I(is64, dst, src, imm), ctx); + } else if (is_addsub_imm(-imm)) { + emit(A64_SUB_I(is64, dst, src, -imm), ctx); + } else { + emit_a64_mov_i(is64, tmp, imm, ctx); + emit(A64_ADD(is64, dst, src, tmp), ctx); + } +} + /* * There are 3 types of AArch64 LDR/STR (immediate) instruction: * Post-index, Pre-index, Unsigned offset. @@ -648,16 +661,13 @@ static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) const s16 off = insn->off; u8 reg = dst; - if (off || arena) { - if (off) { - emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_ADD(1, tmp, tmp, dst), ctx); - reg = tmp; - } - if (arena) { - emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx); - reg = tmp; - } + if (off) { + emit_a64_add_i(1, tmp, reg, tmp, off, ctx); + reg = tmp; + } + if (arena) { + emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx); + reg = tmp; } switch (insn->imm) { @@ -723,7 +733,7 @@ static int emit_ll_sc_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) const s32 imm = insn->imm; const s16 off = insn->off; const bool isdw = BPF_SIZE(code) == BPF_DW; - u8 reg; + u8 reg = dst; s32 jmp_offset; if (BPF_MODE(code) == BPF_PROBE_ATOMIC) { @@ -732,11 +742,8 @@ static int emit_ll_sc_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) return -EINVAL; } - if (!off) { - reg = dst; - } else { - emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_ADD(1, tmp, tmp, dst), ctx); + if (off) { + emit_a64_add_i(1, tmp, reg, tmp, off, ctx); reg = tmp; } @@ -1146,14 +1153,7 @@ emit_bswap_uxt: /* dst = dst OP imm */ case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU64 | BPF_ADD | BPF_K: - if (is_addsub_imm(imm)) { - emit(A64_ADD_I(is64, dst, dst, imm), ctx); - } else if (is_addsub_imm(-imm)) { - emit(A64_SUB_I(is64, dst, dst, -imm), ctx); - } else { - emit_a64_mov_i(is64, tmp, imm, ctx); - emit(A64_ADD(is64, dst, dst, tmp), ctx); - } + emit_a64_add_i(is64, dst, dst, tmp, imm, ctx); break; case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU64 | BPF_SUB | BPF_K: diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index eb17f59e543c..1e65f2fb45bd 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -105,6 +105,7 @@ WORKAROUND_CLEAN_CACHE WORKAROUND_DEVICE_LOAD_ACQUIRE WORKAROUND_NVIDIA_CARMEL_CNP WORKAROUND_QCOM_FALKOR_E1003 +WORKAROUND_QCOM_ORYON_CNTVOFF WORKAROUND_REPEAT_TLBI WORKAROUND_SPECULATIVE_AT WORKAROUND_SPECULATIVE_SSBS diff --git a/arch/arm64/tools/gen-sysreg.awk b/arch/arm64/tools/gen-sysreg.awk index d1254a056114..1a2afc9fdd42 100755 --- a/arch/arm64/tools/gen-sysreg.awk +++ b/arch/arm64/tools/gen-sysreg.awk @@ -206,7 +206,7 @@ END { # Currently this is effectivey a comment, in future we may want to emit # defines for the fields. -/^Fields/ && block_current() == "Sysreg" { +(/^Fields/ || /^Mapping/) && block_current() == "Sysreg" { expect_fields(2) if (next_bit != 63) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index b081b54d6d22..762ee084b37c 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -24,8 +24,16 @@ # ... # EndEnum -# Alternatively if multiple registers share the same layout then -# a SysregFields block can be used to describe the shared layout +# For VHE aliases (*_EL12, *_EL02) of system registers, a Mapping +# entry describes the register the alias actually accesses: + +# Sysreg +# Mapping +# EndSysreg + +# Where multiple system regsiters are not VHE aliases but share a +# common layout, a SysregFields block can be used to describe the +# shared layout: # SysregFields # @@ -1010,7 +1018,12 @@ UnsignedEnum 35:32 FPMR 0b0000 NI 0b0001 IMP EndEnum -Res0 31:12 +Res0 31:20 +UnsignedEnum 19:16 UINJ + 0b0000 NI + 0b0001 IMP +EndEnum +Res0 15:12 UnsignedEnum 11:8 MTEFAR 0b0000 NI 0b0001 IMP @@ -1035,7 +1048,10 @@ UnsignedEnum 55:52 F32MM 0b0000 NI 0b0001 IMP EndEnum -Res0 51:48 +UnsignedEnum 51:48 F16MM + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 47:44 I8MM 0b0000 NI 0b0001 IMP @@ -1053,6 +1069,7 @@ Res0 31:28 UnsignedEnum 27:24 B16B16 0b0000 NI 0b0001 IMP + 0b0010 BFSCALE EndEnum UnsignedEnum 23:20 BF16 0b0000 NI @@ -1063,16 +1080,22 @@ UnsignedEnum 19:16 BitPerm 0b0000 NI 0b0001 IMP EndEnum -Res0 15:8 +UnsignedEnum 15:12 EltPerm + 0b0000 NI + 0b0001 IMP +EndEnum +Res0 11:8 UnsignedEnum 7:4 AES 0b0000 NI 0b0001 IMP 0b0010 PMULL128 + 0b0011 AES2 EndEnum UnsignedEnum 3:0 SVEver 0b0000 IMP 0b0001 SVE2 0b0010 SVE2p1 + 0b0011 SVE2p2 EndEnum EndSysreg @@ -1090,7 +1113,7 @@ UnsignedEnum 59:56 SMEver 0b0000 SME 0b0001 SME2 0b0010 SME2p1 - 0b0000 IMP + 0b0011 SME2p2 EndEnum UnsignedEnum 55:52 I16I64 0b0000 NI @@ -1154,7 +1177,29 @@ UnsignedEnum 28 SF8DP2 0b0 NI 0b1 IMP EndEnum -Res0 27:0 +Res0 27:26 +UnsignedEnum 25 SBitPerm + 0b0 NI + 0b1 IMP +EndEnum +UnsignedEnum 24 AES + 0b0 NI + 0b1 IMP +EndEnum +UnsignedEnum 23 SFEXPA + 0b0 NI + 0b1 IMP +EndEnum +Res0 22:17 +UnsignedEnum 16 STMOP + 0b0 NI + 0b1 IMP +EndEnum +Res0 15:1 +UnsignedEnum 0 SMOP4 + 0b0 NI + 0b1 IMP +EndEnum EndSysreg Sysreg ID_AA64FPFR0_EL1 3 0 0 4 7 @@ -1175,7 +1220,15 @@ UnsignedEnum 28 F8DP2 0b0 NI 0b1 IMP EndEnum -Res0 27:2 +UnsignedEnum 27 F8MM8 + 0b0 NI + 0b1 IMP +EndEnum +UnsignedEnum 26 F8MM4 + 0b0 NI + 0b1 IMP +EndEnum +Res0 25:2 UnsignedEnum 1 F8E4M3 0b0 NI 0b1 IMP @@ -1503,12 +1556,16 @@ EndEnum UnsignedEnum 55:52 CSSC 0b0000 NI 0b0001 IMP + 0b0010 CMPBR EndEnum UnsignedEnum 51:48 RPRFM 0b0000 NI 0b0001 IMP EndEnum -Res0 47:44 +UnsignedEnum 47:44 PCDPHINT + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 43:40 PRFMSLC 0b0000 NI 0b0001 IMP @@ -1561,7 +1618,23 @@ EndEnum EndSysreg Sysreg ID_AA64ISAR3_EL1 3 0 0 6 3 -Res0 63:16 +Res0 63:32 +UnsignedEnum 31:28 FPRCVT + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 27:24 LSUI + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 23:20 OCCMO + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 19:16 LSFE + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 15:12 PACM 0b0000 NI 0b0001 TRIVIAL_IMP @@ -1978,7 +2051,7 @@ Field 1 A Field 0 M EndSysreg -SysregFields CPACR_ELx +Sysreg CPACR_EL1 3 0 1 0 2 Res0 63:30 Field 29 E0POE Field 28 TTA @@ -1989,12 +2062,20 @@ Field 21:20 FPEN Res0 19:18 Field 17:16 ZEN Res0 15:0 -EndSysregFields - -Sysreg CPACR_EL1 3 0 1 0 2 -Fields CPACR_ELx EndSysreg +Sysreg TRFCR_EL1 3 0 1 2 1 +Res0 63:7 +UnsignedEnum 6:5 TS + 0b0001 VIRTUAL + 0b0010 GUEST_PHYSICAL + 0b0011 PHYSICAL +EndEnum +Res0 4:2 +Field 1 ExTRE +Field 0 E0TRE +EndSysregFields + Sysreg SMPRI_EL1 3 0 1 2 4 Res0 63:4 Field 3:0 PRIORITY @@ -2544,6 +2625,22 @@ Field 1 ICIALLU Field 0 ICIALLUIS EndSysreg +Sysreg TRFCR_EL2 3 4 1 2 1 +Res0 63:7 +UnsignedEnum 6:5 TS + 0b0000 USE_TRFCR_EL1_TS + 0b0001 VIRTUAL + 0b0010 GUEST_PHYSICAL + 0b0011 PHYSICAL +EndEnum +Res0 4 +Field 3 CX +Res0 2 +Field 1 E2TRE +Field 0 E0HTRE +EndSysreg + + Sysreg HDFGRTR_EL2 3 4 3 1 4 Field 63 PMBIDR_EL1 Field 62 nPMSNEVFR_EL1 @@ -2947,23 +3044,27 @@ Field 63:0 PhysicalOffset EndSysreg Sysreg CPACR_EL12 3 5 1 0 2 -Fields CPACR_ELx +Mapping CPACR_EL1 EndSysreg Sysreg ZCR_EL12 3 5 1 2 0 -Fields ZCR_ELx +Mapping ZCR_EL1 +EndSysreg + +Sysreg TRFCR_EL12 3 5 1 2 1 +Mapping TRFCR_EL1 EndSysreg Sysreg SMCR_EL12 3 5 1 2 6 -Fields SMCR_ELx +Mapping SMCR_EL1 EndSysreg Sysreg GCSCR_EL12 3 5 2 5 0 -Fields GCSCR_ELx +Mapping GCSCR_EL1 EndSysreg Sysreg GCSPR_EL12 3 5 2 5 1 -Fields GCSPR_ELx +Mapping GCSPR_EL1 EndSysreg Sysreg FAR_EL12 3 5 6 0 0 @@ -2975,7 +3076,7 @@ Fields MPAM1_ELx EndSysreg Sysreg CONTEXTIDR_EL12 3 5 13 0 1 -Fields CONTEXTIDR_ELx +Mapping CONTEXTIDR_EL1 EndSysreg SysregFields TTBRx_EL1 @@ -2992,7 +3093,7 @@ Sysreg TTBR1_EL1 3 0 2 0 1 Fields TTBRx_EL1 EndSysreg -SysregFields TCR2_EL1x +Sysreg TCR2_EL1 3 0 2 0 3 Res0 63:16 Field 15 DisCH1 Field 14 DisCH0 @@ -3006,14 +3107,10 @@ Field 3 POE Field 2 E0POE Field 1 PIE Field 0 PnCH -EndSysregFields - -Sysreg TCR2_EL1 3 0 2 0 3 -Fields TCR2_EL1x EndSysreg Sysreg TCR2_EL12 3 5 2 0 3 -Fields TCR2_EL1x +Mapping TCR2_EL1 EndSysreg Sysreg TCR2_EL2 3 4 2 0 3 @@ -3084,7 +3181,7 @@ Fields PIRx_ELx EndSysreg Sysreg PIRE0_EL12 3 5 10 2 2 -Fields PIRx_ELx +Mapping PIRE0_EL1 EndSysreg Sysreg PIRE0_EL2 3 4 10 2 2 @@ -3096,7 +3193,7 @@ Fields PIRx_ELx EndSysreg Sysreg PIR_EL12 3 5 10 2 3 -Fields PIRx_ELx +Mapping PIR_EL1 EndSysreg Sysreg PIR_EL2 3 4 10 2 3 @@ -3116,7 +3213,7 @@ Fields PIRx_ELx EndSysreg Sysreg POR_EL12 3 5 10 2 4 -Fields PIRx_ELx +Mapping POR_EL1 EndSysreg Sysreg S2POR_EL1 3 0 10 2 5 diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h index 9c84c9012e53..bf8400c28b5a 100644 --- a/arch/csky/include/asm/pgalloc.h +++ b/arch/csky/include/asm/pgalloc.h @@ -44,7 +44,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) pgd_t *ret; pgd_t *init; - ret = (pgd_t *) __get_free_page(GFP_KERNEL); + ret = __pgd_alloc(mm, 0); if (ret) { init = pgd_offset(&init_mm, 0UL); pgd_init((unsigned long *)ret); @@ -63,7 +63,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) #define __pte_free_tlb(tlb, pte, address) \ do { \ - pagetable_pte_dtor(page_ptdesc(pte)); \ + pagetable_dtor(page_ptdesc(pte)); \ tlb_remove_page_ptdesc(tlb, page_ptdesc(pte)); \ } while (0) diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 3eb51fbe804e..d987ba368ed6 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -20,7 +20,6 @@ config HEXAGON # select ARCH_HAS_CPU_IDLE_WAIT # select GPIOLIB # select HAVE_CLK - # select GENERIC_PENDING_IRQ if SMP select GENERIC_ATOMIC64 select HAVE_PERF_EVENTS # GENERIC_ALLOCATOR is used by dma_alloc_coherent() diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile index 92d005958dfb..ff172cbe5881 100644 --- a/arch/hexagon/Makefile +++ b/arch/hexagon/Makefile @@ -32,3 +32,9 @@ KBUILD_LDFLAGS += $(ldflags-y) TIR_NAME := r19 KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__ KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME) + +# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0 +# https://github.com/llvm/llvm-project/issues/99714 +ifneq ($(call clang-min-version, 190100),y) +KBUILD_CFLAGS += -mllvm -hexagon-cext=false +endif diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h index bf6cf5579cf4..9c58fb81f7fd 100644 --- a/arch/hexagon/include/asm/cmpxchg.h +++ b/arch/hexagon/include/asm/cmpxchg.h @@ -56,7 +56,7 @@ __arch_xchg(unsigned long x, volatile void *ptr, int size) __typeof__(ptr) __ptr = (ptr); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ - __typeof__(*(ptr)) __oldval = 0; \ + __typeof__(*(ptr)) __oldval = (__typeof__(*(ptr))) 0; \ \ asm volatile( \ "1: %0 = memw_locked(%1);\n" \ diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h index 55988625e6fb..1ee5f5f157ca 100644 --- a/arch/hexagon/include/asm/pgalloc.h +++ b/arch/hexagon/include/asm/pgalloc.h @@ -22,7 +22,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; - pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + pgd = __pgd_alloc(mm, 0); /* * There may be better ways to do this, but to ensure @@ -89,7 +89,7 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, #define __pte_free_tlb(tlb, pte, addr) \ do { \ - pagetable_pte_dtor((page_ptdesc(pte))); \ + pagetable_dtor((page_ptdesc(pte))); \ tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) diff --git a/arch/hexagon/include/asm/setup.h b/arch/hexagon/include/asm/setup.h new file mode 100644 index 000000000000..9f2749cd4052 --- /dev/null +++ b/arch/hexagon/include/asm/setup.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + */ + +#ifndef _ASM_HEXAGON_SETUP_H +#define _ASM_HEXAGON_SETUP_H + +#include +#include + +extern char external_cmdline_buffer; + +void __init setup_arch_memory(void); + +#endif diff --git a/arch/hexagon/include/uapi/asm/setup.h b/arch/hexagon/include/uapi/asm/setup.h index 8ce9428b1583..598f74f671f6 100644 --- a/arch/hexagon/include/uapi/asm/setup.h +++ b/arch/hexagon/include/uapi/asm/setup.h @@ -17,19 +17,9 @@ * 02110-1301, USA. */ -#ifndef _ASM_SETUP_H -#define _ASM_SETUP_H - -#ifdef __KERNEL__ -#include -#else -#define __init -#endif +#ifndef _UAPI_ASM_HEXAGON_SETUP_H +#define _UAPI_ASM_HEXAGON_SETUP_H #include -extern char external_cmdline_buffer; - -void __init setup_arch_memory(void); - #endif diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c index f0f207e2a694..6f851e1cd4ee 100644 --- a/arch/hexagon/kernel/time.c +++ b/arch/hexagon/kernel/time.c @@ -170,8 +170,7 @@ static void __init time_init_deferred(void) ce_dev->cpumask = cpu_all_mask; - if (!resource) - resource = rtos_timer_device.resource; + resource = rtos_timer_device.resource; /* ioremap here means this has to run later, after paging init */ rtos_timer = ioremap(resource->start, resource_size(resource)); diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c index 75e062722d28..e732aa01c2ff 100644 --- a/arch/hexagon/kernel/traps.c +++ b/arch/hexagon/kernel/traps.c @@ -135,7 +135,7 @@ static void do_show_stack(struct task_struct *task, unsigned long *fp, } /* Attempt to continue past exception. */ - if (0 == newfp) { + if (!newfp) { struct pt_regs *regs = (struct pt_regs *) (((void *)fp) + 8); @@ -195,8 +195,10 @@ int die(const char *str, struct pt_regs *regs, long err) printk(KERN_EMERG "Oops: %s[#%d]:\n", str, ++die.counter); if (notify_die(DIE_OOPS, str, regs, err, pt_cause(regs), SIGSEGV) == - NOTIFY_STOP) + NOTIFY_STOP) { + spin_unlock_irq(&die.lock); return 1; + } print_modules(); show_regs(regs); diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild index bfa21465d83a..beb8499dd8ed 100644 --- a/arch/loongarch/Kbuild +++ b/arch/loongarch/Kbuild @@ -4,7 +4,6 @@ obj-y += net/ obj-y += vdso/ obj-$(CONFIG_KVM) += kvm/ -obj-$(CONFIG_BUILTIN_DTB) += boot/dts/ # for cleaning subdir- += boot diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index dae3a9104ca6..2b8bd27a852f 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -15,6 +15,7 @@ config LOONGARCH select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CPU_FINALIZE_INIT + select ARCH_HAS_CRC32 select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_FAST_MULTIPLIER @@ -81,6 +82,7 @@ config LOONGARCH select BUILDTIME_TABLE_SORT select COMMON_CLK select CPU_PM + select EDAC_SUPPORT select EFI select GENERIC_CLOCKEVENTS select GENERIC_CMOS_UPDATE @@ -128,16 +130,18 @@ config LOONGARCH select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_FTRACE_REGS_HAVING_PT_REGS select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN select HAVE_EXIT_THREAD select HAVE_GUP_FAST + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS @@ -245,7 +249,7 @@ config MACH_LOONGSON64 def_bool 64BIT config FIX_EARLYCON_MEM - def_bool y + def_bool !ARCH_IOREMAP config PGTABLE_2LEVEL bool @@ -396,6 +400,7 @@ endchoice config BUILTIN_DTB bool "Enable built-in dtb in kernel" depends on OF + select GENERIC_BUILTIN_DTB help Some existing systems do not provide a canonical device tree to the kernel at boot time. Let's provide a device tree table in the diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile index 747d0c3f6389..15d5e14fe418 100644 --- a/arch/loongarch/boot/dts/Makefile +++ b/arch/loongarch/boot/dts/Makefile @@ -1,5 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only dtb-y = loongson-2k0500-ref.dtb loongson-2k1000-ref.dtb loongson-2k2000-ref.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME)) diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index 4dffc90192f7..73c77500ac46 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -113,7 +113,10 @@ CONFIG_ZBUD=y CONFIG_ZSMALLOC=m # CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y -CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y +# CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE is not set +CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO=y +# CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL is not set +# CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE is not set CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y @@ -1029,7 +1032,6 @@ CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_CHACHA20POLY1305=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_DEFLATE=m CONFIG_CRYPTO_LZO=m @@ -1040,7 +1042,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_CRC32_LOONGARCH=m CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_DMA_CMA=y CONFIG_DMA_NUMA_CMA=y diff --git a/arch/loongarch/crypto/Kconfig b/arch/loongarch/crypto/Kconfig index 200a6e8b43b1..a0270b3e5b30 100644 --- a/arch/loongarch/crypto/Kconfig +++ b/arch/loongarch/crypto/Kconfig @@ -2,13 +2,4 @@ menu "Accelerated Cryptographic Algorithms for CPU (loongarch)" -config CRYPTO_CRC32_LOONGARCH - tristate "CRC32c and CRC32" - select CRC32 - select CRYPTO_HASH - help - CRC32c and CRC32 CRC algorithms - - Architecture: LoongArch with CRC32 instructions - endmenu diff --git a/arch/loongarch/crypto/Makefile b/arch/loongarch/crypto/Makefile index d22613d27ce9..ba83755dde2b 100644 --- a/arch/loongarch/crypto/Makefile +++ b/arch/loongarch/crypto/Makefile @@ -2,5 +2,3 @@ # # Makefile for LoongArch crypto files.. # - -obj-$(CONFIG_CRYPTO_CRC32_LOONGARCH) += crc32-loongarch.o diff --git a/arch/loongarch/crypto/crc32-loongarch.c b/arch/loongarch/crypto/crc32-loongarch.c deleted file mode 100644 index b7d9782827f5..000000000000 --- a/arch/loongarch/crypto/crc32-loongarch.c +++ /dev/null @@ -1,300 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * crc32.c - CRC32 and CRC32C using LoongArch crc* instructions - * - * Module based on mips/crypto/crc32-mips.c - * - * Copyright (C) 2014 Linaro Ltd - * Copyright (C) 2018 MIPS Tech, LLC - * Copyright (C) 2020-2023 Loongson Technology Corporation Limited - */ - -#include -#include - -#include -#include - -#define _CRC32(crc, value, size, type) \ -do { \ - __asm__ __volatile__( \ - #type ".w." #size ".w" " %0, %1, %0\n\t"\ - : "+r" (crc) \ - : "r" (value) \ - : "memory"); \ -} while (0) - -#define CRC32(crc, value, size) _CRC32(crc, value, size, crc) -#define CRC32C(crc, value, size) _CRC32(crc, value, size, crcc) - -static u32 crc32_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) -{ - u32 crc = crc_; - - while (len >= sizeof(u64)) { - u64 value = get_unaligned_le64(p); - - CRC32(crc, value, d); - p += sizeof(u64); - len -= sizeof(u64); - } - - if (len & sizeof(u32)) { - u32 value = get_unaligned_le32(p); - - CRC32(crc, value, w); - p += sizeof(u32); - } - - if (len & sizeof(u16)) { - u16 value = get_unaligned_le16(p); - - CRC32(crc, value, h); - p += sizeof(u16); - } - - if (len & sizeof(u8)) { - u8 value = *p++; - - CRC32(crc, value, b); - } - - return crc; -} - -static u32 crc32c_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) -{ - u32 crc = crc_; - - while (len >= sizeof(u64)) { - u64 value = get_unaligned_le64(p); - - CRC32C(crc, value, d); - p += sizeof(u64); - len -= sizeof(u64); - } - - if (len & sizeof(u32)) { - u32 value = get_unaligned_le32(p); - - CRC32C(crc, value, w); - p += sizeof(u32); - } - - if (len & sizeof(u16)) { - u16 value = get_unaligned_le16(p); - - CRC32C(crc, value, h); - p += sizeof(u16); - } - - if (len & sizeof(u8)) { - u8 value = *p++; - - CRC32C(crc, value, b); - } - - return crc; -} - -#define CHKSUM_BLOCK_SIZE 1 -#define CHKSUM_DIGEST_SIZE 4 - -struct chksum_ctx { - u32 key; -}; - -struct chksum_desc_ctx { - u32 crc; -}; - -static int chksum_init(struct shash_desc *desc) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = mctx->key; - - return 0; -} - -/* - * Setting the seed allows arbitrary accumulators and flexible XOR policy - * If your algorithm starts with ~0, then XOR with ~0 before you set the seed. - */ -static int chksum_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(tfm); - - if (keylen != sizeof(mctx->key)) - return -EINVAL; - - mctx->key = get_unaligned_le32(key); - - return 0; -} - -static int chksum_update(struct shash_desc *desc, const u8 *data, unsigned int length) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = crc32_loongarch_hw(ctx->crc, data, length); - return 0; -} - -static int chksumc_update(struct shash_desc *desc, const u8 *data, unsigned int length) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = crc32c_loongarch_hw(ctx->crc, data, length); - return 0; -} - -static int chksum_final(struct shash_desc *desc, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - put_unaligned_le32(ctx->crc, out); - return 0; -} - -static int chksumc_final(struct shash_desc *desc, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - put_unaligned_le32(~ctx->crc, out); - return 0; -} - -static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out) -{ - put_unaligned_le32(crc32_loongarch_hw(crc, data, len), out); - return 0; -} - -static int __chksumc_finup(u32 crc, const u8 *data, unsigned int len, u8 *out) -{ - put_unaligned_le32(~crc32c_loongarch_hw(crc, data, len), out); - return 0; -} - -static int chksum_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - return __chksum_finup(ctx->crc, data, len, out); -} - -static int chksumc_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - return __chksumc_finup(ctx->crc, data, len, out); -} - -static int chksum_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); - - return __chksum_finup(mctx->key, data, length, out); -} - -static int chksumc_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); - - return __chksumc_finup(mctx->key, data, length, out); -} - -static int chksum_cra_init(struct crypto_tfm *tfm) -{ - struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); - - mctx->key = 0; - return 0; -} - -static int chksumc_cra_init(struct crypto_tfm *tfm) -{ - struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); - - mctx->key = ~0; - return 0; -} - -static struct shash_alg crc32_alg = { - .digestsize = CHKSUM_DIGEST_SIZE, - .setkey = chksum_setkey, - .init = chksum_init, - .update = chksum_update, - .final = chksum_final, - .finup = chksum_finup, - .digest = chksum_digest, - .descsize = sizeof(struct chksum_desc_ctx), - .base = { - .cra_name = "crc32", - .cra_driver_name = "crc32-loongarch", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct chksum_ctx), - .cra_module = THIS_MODULE, - .cra_init = chksum_cra_init, - } -}; - -static struct shash_alg crc32c_alg = { - .digestsize = CHKSUM_DIGEST_SIZE, - .setkey = chksum_setkey, - .init = chksum_init, - .update = chksumc_update, - .final = chksumc_final, - .finup = chksumc_finup, - .digest = chksumc_digest, - .descsize = sizeof(struct chksum_desc_ctx), - .base = { - .cra_name = "crc32c", - .cra_driver_name = "crc32c-loongarch", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct chksum_ctx), - .cra_module = THIS_MODULE, - .cra_init = chksumc_cra_init, - } -}; - -static int __init crc32_mod_init(void) -{ - int err; - - if (!cpu_has(CPU_FEATURE_CRC32)) - return 0; - - err = crypto_register_shash(&crc32_alg); - if (err) - return err; - - err = crypto_register_shash(&crc32c_alg); - if (err) - return err; - - return 0; -} - -static void __exit crc32_mod_exit(void) -{ - if (!cpu_has(CPU_FEATURE_CRC32)) - return; - - crypto_unregister_shash(&crc32_alg); - crypto_unregister_shash(&crc32c_alg); -} - -module_init(crc32_mod_init); -module_exit(crc32_mod_exit); - -MODULE_AUTHOR("Min Zhou "); -MODULE_AUTHOR("Huacai Chen "); -MODULE_DESCRIPTION("CRC32 and CRC32C using LoongArch crc* instructions"); -MODULE_LICENSE("GPL v2"); diff --git a/arch/loongarch/include/asm/bug.h b/arch/loongarch/include/asm/bug.h index 08388876ade4..f6f254f2c5db 100644 --- a/arch/loongarch/include/asm/bug.h +++ b/arch/loongarch/include/asm/bug.h @@ -4,6 +4,7 @@ #include #include +#include #ifndef CONFIG_DEBUG_BUGVERBOSE #define _BUGVERBOSE_LOCATION(file, line) @@ -33,25 +34,25 @@ #define ASM_BUG_FLAGS(flags) \ __BUG_ENTRY(flags) \ - break BRK_BUG + break BRK_BUG; #define ASM_BUG() ASM_BUG_FLAGS(0) -#define __BUG_FLAGS(flags) \ - asm_inline volatile (__stringify(ASM_BUG_FLAGS(flags))); +#define __BUG_FLAGS(flags, extra) \ + asm_inline volatile (__stringify(ASM_BUG_FLAGS(flags)) \ + extra); #define __WARN_FLAGS(flags) \ do { \ instrumentation_begin(); \ - __BUG_FLAGS(BUGFLAG_WARNING|(flags)); \ - annotate_reachable(); \ + __BUG_FLAGS(BUGFLAG_WARNING|(flags), ANNOTATE_REACHABLE(10001b));\ instrumentation_end(); \ } while (0) #define BUG() \ do { \ instrumentation_begin(); \ - __BUG_FLAGS(0); \ + __BUG_FLAGS(0, ""); \ unreachable(); \ } while (0) diff --git a/arch/loongarch/include/asm/cpu-info.h b/arch/loongarch/include/asm/cpu-info.h index 900589cb159d..35e0a230a484 100644 --- a/arch/loongarch/include/asm/cpu-info.h +++ b/arch/loongarch/include/asm/cpu-info.h @@ -57,6 +57,7 @@ struct cpuinfo_loongarch { int global_id; /* physical global thread number */ int vabits; /* Virtual Address size in bits */ int pabits; /* Physical Address size in bits */ + int timerbits; /* Width of arch timer in bits */ unsigned int ksave_mask; /* Usable KSave mask. */ unsigned int watch_dreg_count; /* Number data breakpoints */ unsigned int watch_ireg_count; /* Number instruction breakpoints */ diff --git a/arch/loongarch/include/asm/fprobe.h b/arch/loongarch/include/asm/fprobe.h new file mode 100644 index 000000000000..7af3b3126caf --- /dev/null +++ b/arch/loongarch/include/asm/fprobe.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_LOONGARCH_FPROBE_H +#define _ASM_LOONGARCH_FPROBE_H + +/* + * Explicitly undef ARCH_DEFINE_ENCODE_FPROBE_HEADER, because loongarch does not + * have enough number of fixed MSBs of the address of kernel objects for + * encoding the size of data in fprobe_header. Use 2-entries encoding instead. + */ +#undef ARCH_DEFINE_ENCODE_FPROBE_HEADER + +#endif /* _ASM_LOONGARCH_FPROBE_H */ diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index 8f13eaeaa325..6e0a99763a9a 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -57,6 +57,16 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) instruction_pointer_set(&arch_ftrace_regs(fregs)->regs, ip); } +#undef ftrace_regs_get_frame_pointer +#define ftrace_regs_get_frame_pointer(fregs) \ + (arch_ftrace_regs(fregs)->regs.regs[22]) + +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return *(unsigned long *)(arch_ftrace_regs(fregs)->regs.regs[1]); +} + #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); @@ -78,26 +88,4 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) #endif /* CONFIG_FUNCTION_TRACER */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - /* a0 - a1 */ - unsigned long regs[2]; - - unsigned long fp; - unsigned long __unused; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->regs[0]; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->fp; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_LOONGARCH_FTRACE_H */ diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h index d78330916bd1..13b2462f3d8c 100644 --- a/arch/loongarch/include/asm/hw_breakpoint.h +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -38,8 +38,8 @@ struct arch_hw_breakpoint { * Limits. * Changing these will require modifications to the register accessors. */ -#define LOONGARCH_MAX_BRP 8 -#define LOONGARCH_MAX_WRP 8 +#define LOONGARCH_MAX_BRP 14 +#define LOONGARCH_MAX_WRP 14 /* Virtual debug register bases. */ #define CSR_CFG_ADDR 0 diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index 7b8367c39da8..590982cd986e 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -162,6 +162,7 @@ enum emulation_result { #define LOONGARCH_PV_FEAT_UPDATED BIT_ULL(63) #define LOONGARCH_PV_FEAT_MASK (BIT(KVM_FEATURE_IPI) | \ BIT(KVM_FEATURE_STEAL_TIME) | \ + BIT(KVM_FEATURE_USER_HCALL) | \ BIT(KVM_FEATURE_VIRT_EXTIOI)) struct kvm_vcpu_arch { diff --git a/arch/loongarch/include/asm/kvm_para.h b/arch/loongarch/include/asm/kvm_para.h index c4e84227280d..3e4b397f423f 100644 --- a/arch/loongarch/include/asm/kvm_para.h +++ b/arch/loongarch/include/asm/kvm_para.h @@ -13,6 +13,7 @@ #define KVM_HCALL_CODE_SERVICE 0 #define KVM_HCALL_CODE_SWDBG 1 +#define KVM_HCALL_CODE_USER_SERVICE 2 #define KVM_HCALL_SERVICE HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_SERVICE) #define KVM_HCALL_FUNC_IPI 1 @@ -20,6 +21,8 @@ #define KVM_HCALL_SWDBG HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_SWDBG) +#define KVM_HCALL_USER_SERVICE HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_USER_SERVICE) + /* * LoongArch hypercall return code */ diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h index d7e8f7d50ee0..2c349f961bfb 100644 --- a/arch/loongarch/include/asm/kvm_vcpu.h +++ b/arch/loongarch/include/asm/kvm_vcpu.h @@ -43,6 +43,7 @@ int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst); int kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst); int kvm_complete_mmio_read(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_complete_iocsr_read(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_complete_user_service(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_emu_idle(struct kvm_vcpu *vcpu); int kvm_pending_timer(struct kvm_vcpu *vcpu); int kvm_handle_fault(struct kvm_vcpu *vcpu, int fault); diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 64ad277e096e..52651aa0e583 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -108,6 +108,12 @@ #define CPUCFG3_SPW_HG_HF BIT(11) #define CPUCFG3_RVA BIT(12) #define CPUCFG3_RVAMAX GENMASK(16, 13) +#define CPUCFG3_ALDORDER_CAP BIT(18) /* All address load ordered, capability */ +#define CPUCFG3_ASTORDER_CAP BIT(19) /* All address store ordered, capability */ +#define CPUCFG3_ALDORDER_STA BIT(20) /* All address load ordered, status */ +#define CPUCFG3_ASTORDER_STA BIT(21) /* All address store ordered, status */ +#define CPUCFG3_SLDORDER_CAP BIT(22) /* Same address load ordered, capability */ +#define CPUCFG3_SLDORDER_STA BIT(23) /* Same address load ordered, status */ #define LOONGARCH_CPUCFG4 0x4 #define CPUCFG4_CCFREQ GENMASK(31, 0) @@ -466,7 +472,6 @@ #define LOONGARCH_CSR_TCFG 0x41 /* Timer config */ #define CSR_TCFG_VAL_SHIFT 2 -#define CSR_TCFG_VAL_WIDTH 48 #define CSR_TCFG_VAL (_ULCAST_(0x3fffffffffff) << CSR_TCFG_VAL_SHIFT) #define CSR_TCFG_PERIOD_SHIFT 1 #define CSR_TCFG_PERIOD (_ULCAST_(0x1) << CSR_TCFG_PERIOD_SHIFT) @@ -566,6 +571,15 @@ /* Implement dependent */ #define LOONGARCH_CSR_IMPCTL1 0x80 /* Loongson config1 */ +#define CSR_LDSTORDER_SHIFT 28 +#define CSR_LDSTORDER_WIDTH 3 +#define CSR_LDSTORDER_MASK (_ULCAST_(0x7) << CSR_LDSTORDER_SHIFT) +#define CSR_LDSTORDER_NLD_NST (_ULCAST_(0x0) << CSR_LDSTORDER_SHIFT) /* 000 = No Load No Store */ +#define CSR_LDSTORDER_ALD_NST (_ULCAST_(0x1) << CSR_LDSTORDER_SHIFT) /* 001 = All Load No Store */ +#define CSR_LDSTORDER_SLD_NST (_ULCAST_(0x3) << CSR_LDSTORDER_SHIFT) /* 011 = Same Load No Store */ +#define CSR_LDSTORDER_NLD_AST (_ULCAST_(0x4) << CSR_LDSTORDER_SHIFT) /* 100 = No Load All Store */ +#define CSR_LDSTORDER_ALD_AST (_ULCAST_(0x5) << CSR_LDSTORDER_SHIFT) /* 101 = All Load All Store */ +#define CSR_LDSTORDER_SLD_AST (_ULCAST_(0x7) << CSR_LDSTORDER_SHIFT) /* 111 = Same Load All Store */ #define CSR_MISPEC_SHIFT 20 #define CSR_MISPEC_WIDTH 8 #define CSR_MISPEC (_ULCAST_(0xff) << CSR_MISPEC_SHIFT) @@ -959,6 +973,36 @@ #define LOONGARCH_CSR_DB7CTRL 0x34a /* data breakpoint 7 control */ #define LOONGARCH_CSR_DB7ASID 0x34b /* data breakpoint 7 asid */ +#define LOONGARCH_CSR_DB8ADDR 0x350 /* data breakpoint 8 address */ +#define LOONGARCH_CSR_DB8MASK 0x351 /* data breakpoint 8 mask */ +#define LOONGARCH_CSR_DB8CTRL 0x352 /* data breakpoint 8 control */ +#define LOONGARCH_CSR_DB8ASID 0x353 /* data breakpoint 8 asid */ + +#define LOONGARCH_CSR_DB9ADDR 0x358 /* data breakpoint 9 address */ +#define LOONGARCH_CSR_DB9MASK 0x359 /* data breakpoint 9 mask */ +#define LOONGARCH_CSR_DB9CTRL 0x35a /* data breakpoint 9 control */ +#define LOONGARCH_CSR_DB9ASID 0x35b /* data breakpoint 9 asid */ + +#define LOONGARCH_CSR_DB10ADDR 0x360 /* data breakpoint 10 address */ +#define LOONGARCH_CSR_DB10MASK 0x361 /* data breakpoint 10 mask */ +#define LOONGARCH_CSR_DB10CTRL 0x362 /* data breakpoint 10 control */ +#define LOONGARCH_CSR_DB10ASID 0x363 /* data breakpoint 10 asid */ + +#define LOONGARCH_CSR_DB11ADDR 0x368 /* data breakpoint 11 address */ +#define LOONGARCH_CSR_DB11MASK 0x369 /* data breakpoint 11 mask */ +#define LOONGARCH_CSR_DB11CTRL 0x36a /* data breakpoint 11 control */ +#define LOONGARCH_CSR_DB11ASID 0x36b /* data breakpoint 11 asid */ + +#define LOONGARCH_CSR_DB12ADDR 0x370 /* data breakpoint 12 address */ +#define LOONGARCH_CSR_DB12MASK 0x371 /* data breakpoint 12 mask */ +#define LOONGARCH_CSR_DB12CTRL 0x372 /* data breakpoint 12 control */ +#define LOONGARCH_CSR_DB12ASID 0x373 /* data breakpoint 12 asid */ + +#define LOONGARCH_CSR_DB13ADDR 0x378 /* data breakpoint 13 address */ +#define LOONGARCH_CSR_DB13MASK 0x379 /* data breakpoint 13 mask */ +#define LOONGARCH_CSR_DB13CTRL 0x37a /* data breakpoint 13 control */ +#define LOONGARCH_CSR_DB13ASID 0x37b /* data breakpoint 13 asid */ + #define LOONGARCH_CSR_FWPC 0x380 /* instruction breakpoint config */ #define LOONGARCH_CSR_FWPS 0x381 /* instruction breakpoint status */ @@ -1002,6 +1046,36 @@ #define LOONGARCH_CSR_IB7CTRL 0x3ca /* inst breakpoint 7 control */ #define LOONGARCH_CSR_IB7ASID 0x3cb /* inst breakpoint 7 asid */ +#define LOONGARCH_CSR_IB8ADDR 0x3d0 /* inst breakpoint 8 address */ +#define LOONGARCH_CSR_IB8MASK 0x3d1 /* inst breakpoint 8 mask */ +#define LOONGARCH_CSR_IB8CTRL 0x3d2 /* inst breakpoint 8 control */ +#define LOONGARCH_CSR_IB8ASID 0x3d3 /* inst breakpoint 8 asid */ + +#define LOONGARCH_CSR_IB9ADDR 0x3d8 /* inst breakpoint 9 address */ +#define LOONGARCH_CSR_IB9MASK 0x3d9 /* inst breakpoint 9 mask */ +#define LOONGARCH_CSR_IB9CTRL 0x3da /* inst breakpoint 9 control */ +#define LOONGARCH_CSR_IB9ASID 0x3db /* inst breakpoint 9 asid */ + +#define LOONGARCH_CSR_IB10ADDR 0x3e0 /* inst breakpoint 10 address */ +#define LOONGARCH_CSR_IB10MASK 0x3e1 /* inst breakpoint 10 mask */ +#define LOONGARCH_CSR_IB10CTRL 0x3e2 /* inst breakpoint 10 control */ +#define LOONGARCH_CSR_IB10ASID 0x3e3 /* inst breakpoint 10 asid */ + +#define LOONGARCH_CSR_IB11ADDR 0x3e8 /* inst breakpoint 11 address */ +#define LOONGARCH_CSR_IB11MASK 0x3e9 /* inst breakpoint 11 mask */ +#define LOONGARCH_CSR_IB11CTRL 0x3ea /* inst breakpoint 11 control */ +#define LOONGARCH_CSR_IB11ASID 0x3eb /* inst breakpoint 11 asid */ + +#define LOONGARCH_CSR_IB12ADDR 0x3f0 /* inst breakpoint 12 address */ +#define LOONGARCH_CSR_IB12MASK 0x3f1 /* inst breakpoint 12 mask */ +#define LOONGARCH_CSR_IB12CTRL 0x3f2 /* inst breakpoint 12 control */ +#define LOONGARCH_CSR_IB12ASID 0x3f3 /* inst breakpoint 12 asid */ + +#define LOONGARCH_CSR_IB13ADDR 0x3f8 /* inst breakpoint 13 address */ +#define LOONGARCH_CSR_IB13MASK 0x3f9 /* inst breakpoint 13 mask */ +#define LOONGARCH_CSR_IB13CTRL 0x3fa /* inst breakpoint 13 control */ +#define LOONGARCH_CSR_IB13ASID 0x3fb /* inst breakpoint 13 asid */ + #define LOONGARCH_CSR_DEBUG 0x500 /* debug config */ #define LOONGARCH_CSR_DERA 0x501 /* debug era */ #define LOONGARCH_CSR_DESAVE 0x502 /* debug save */ diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index a7b9c9e73593..7211dff8c969 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -57,7 +57,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) #define __pte_free_tlb(tlb, pte, address) \ do { \ - pagetable_pte_dtor(page_ptdesc(pte)); \ + pagetable_dtor(page_ptdesc(pte)); \ tlb_remove_page_ptdesc((tlb), page_ptdesc(pte)); \ } while (0) diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 82cd3a9f094b..45bfc65a0c9f 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -96,6 +96,13 @@ #define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL_SUC) +#define pgprot_nx pgprot_nx + +static inline pgprot_t pgprot_nx(pgprot_t _prot) +{ + return __pgprot(pgprot_val(_prot) | _PAGE_NO_EXEC); +} + #define pgprot_noncached pgprot_noncached static inline pgprot_t pgprot_noncached(pgprot_t _prot) diff --git a/arch/loongarch/include/uapi/asm/kvm_para.h b/arch/loongarch/include/uapi/asm/kvm_para.h index b0604aa9b4bb..76d802ef01ce 100644 --- a/arch/loongarch/include/uapi/asm/kvm_para.h +++ b/arch/loongarch/include/uapi/asm/kvm_para.h @@ -17,5 +17,6 @@ #define KVM_FEATURE_STEAL_TIME 2 /* BIT 24 - 31 are features configurable by user space vmm */ #define KVM_FEATURE_VIRT_EXTIOI 24 +#define KVM_FEATURE_USER_HCALL 25 #endif /* _UAPI_ASM_KVM_PARA_H */ diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h index ac915f841650..aafb3cd9e943 100644 --- a/arch/loongarch/include/uapi/asm/ptrace.h +++ b/arch/loongarch/include/uapi/asm/ptrace.h @@ -72,6 +72,16 @@ struct user_watch_state { } dbg_regs[8]; }; +struct user_watch_state_v2 { + uint64_t dbg_info; + struct { + uint64_t addr; + uint64_t mask; + uint32_t ctrl; + uint32_t pad; + } dbg_regs[14]; +}; + #define PTRACE_SYSEMU 0x1f #define PTRACE_SYSEMU_SINGLESTEP 0x20 diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index 9497968ee158..4853e8b04c6f 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -10,7 +10,7 @@ extra-y := vmlinux.lds obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \ traps.o irq.o idle.o process.o dma.o mem.o reset.o switch.o \ elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \ - alternative.o unwind.o + alternative.o kdebugfs.o unwind.o obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_EFI) += efi.o diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index 049c5c3e370c..8be1c38ad8eb 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -280,18 +280,6 @@ static void __used output_pbe_defines(void) } #endif -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static void __used output_fgraph_ret_regs_defines(void) -{ - COMMENT("LoongArch fgraph_ret_regs offsets."); - OFFSET(FGRET_REGS_A0, fgraph_ret_regs, regs[0]); - OFFSET(FGRET_REGS_A1, fgraph_ret_regs, regs[1]); - OFFSET(FGRET_REGS_FP, fgraph_ret_regs, fp); - DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs)); - BLANK(); -} -#endif - static void __used output_kvm_defines(void) { COMMENT("KVM/LoongArch Specific offsets."); diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c index c7988f757281..8e231b0d2cd6 100644 --- a/arch/loongarch/kernel/cacheinfo.c +++ b/arch/loongarch/kernel/cacheinfo.c @@ -51,6 +51,12 @@ static void cache_cpumap_setup(unsigned int cpu) continue; sib_leaf = sib_cpu_ci->info_list + index; + /* SMT cores share all caches */ + if (cpus_are_siblings(i, cpu)) { + cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map); + cpumask_set_cpu(i, &this_leaf->shared_cpu_map); + } + /* Node's cores share shared caches */ if (cache_leaves_are_shared(this_leaf, sib_leaf)) { cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map); cpumask_set_cpu(i, &this_leaf->shared_cpu_map); diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index cbce099037b2..fedaa67cde41 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -190,6 +190,7 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) set_cpu_asid_mask(c, asid_mask); config = read_csr_prcfg1(); + c->timerbits = (config & CSR_CONF1_TMRBITS) >> CSR_CONF1_TMRBITS_SHIFT; c->ksave_mask = GENMASK((config & CSR_CONF1_KSNUM) - 1, 0); c->ksave_mask &= ~(EXC_KSAVE_MASK | PERCPU_KSAVE_MASK | KVM_KSAVE_MASK); diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index 18056229e22e..25c9a4cfd5fa 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -243,8 +243,16 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, { struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs; unsigned long *parent = (unsigned long *)®s->regs[1]; + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long old; - prepare_ftrace_return(ip, (unsigned long *)parent); + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; + + if (!function_graph_enter_regs(old, ip, 0, parent, fregs)) + *parent = return_hooker; } #else static int ftrace_modify_graph_caller(bool enable) diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c index a6e4b605bfa8..c35f9bf38033 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -51,7 +51,13 @@ int hw_breakpoint_slots(int type) READ_WB_REG_CASE(OFF, 4, REG, T, VAL); \ READ_WB_REG_CASE(OFF, 5, REG, T, VAL); \ READ_WB_REG_CASE(OFF, 6, REG, T, VAL); \ - READ_WB_REG_CASE(OFF, 7, REG, T, VAL); + READ_WB_REG_CASE(OFF, 7, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 8, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 9, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 10, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 11, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 12, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 13, REG, T, VAL); #define GEN_WRITE_WB_REG_CASES(OFF, REG, T, VAL) \ WRITE_WB_REG_CASE(OFF, 0, REG, T, VAL); \ @@ -61,7 +67,13 @@ int hw_breakpoint_slots(int type) WRITE_WB_REG_CASE(OFF, 4, REG, T, VAL); \ WRITE_WB_REG_CASE(OFF, 5, REG, T, VAL); \ WRITE_WB_REG_CASE(OFF, 6, REG, T, VAL); \ - WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL); + WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 8, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 9, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 10, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 11, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 12, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 13, REG, T, VAL); static u64 read_wb_reg(int reg, int n, int t) { diff --git a/arch/loongarch/kernel/kdebugfs.c b/arch/loongarch/kernel/kdebugfs.c new file mode 100644 index 000000000000..80cf64772399 --- /dev/null +++ b/arch/loongarch/kernel/kdebugfs.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include + +struct dentry *arch_debugfs_dir; +EXPORT_SYMBOL(arch_debugfs_dir); + +static int sfb_state, tso_state; + +static void set_sfb_state(void *info) +{ + int val = *(int *)info << CSR_STFILL_SHIFT; + + csr_xchg32(val, CSR_STFILL, LOONGARCH_CSR_IMPCTL1); +} + +static ssize_t sfb_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + int s, state; + char str[32]; + + state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_STFILL) >> CSR_STFILL_SHIFT; + + s = snprintf(str, sizeof(str), "Boot State: %x\nCurrent State: %x\n", sfb_state, state); + + if (*ppos >= s) + return 0; + + s -= *ppos; + s = min_t(u32, s, count); + + if (copy_to_user(buf, &str[*ppos], s)) + return -EFAULT; + + *ppos += s; + + return s; +} + +static ssize_t sfb_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + int state; + + if (kstrtoint_from_user(buf, count, 10, &state)) + return -EFAULT; + + switch (state) { + case 0: case 1: + on_each_cpu(set_sfb_state, &state, 1); + break; + default: + return -EINVAL; + } + + return count; +} + +static const struct file_operations sfb_fops = { + .read = sfb_read, + .write = sfb_write, + .open = simple_open, + .llseek = default_llseek +}; + +#define LDSTORDER_NLD_NST 0x0 /* 000 = No Load No Store */ +#define LDSTORDER_ALD_NST 0x1 /* 001 = All Load No Store */ +#define LDSTORDER_SLD_NST 0x3 /* 011 = Same Load No Store */ +#define LDSTORDER_NLD_AST 0x4 /* 100 = No Load All Store */ +#define LDSTORDER_ALD_AST 0x5 /* 101 = All Load All Store */ +#define LDSTORDER_SLD_AST 0x7 /* 111 = Same Load All Store */ + +static char *tso_hints[] = { + "No Load No Store", + "All Load No Store", + "Invalid Config", + "Same Load No Store", + "No Load All Store", + "All Load All Store", + "Invalid Config", + "Same Load All Store" +}; + +static void set_tso_state(void *info) +{ + int val = *(int *)info << CSR_LDSTORDER_SHIFT; + + csr_xchg32(val, CSR_LDSTORDER_MASK, LOONGARCH_CSR_IMPCTL1); +} + +static ssize_t tso_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + int s, state; + char str[240]; + + state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_LDSTORDER_MASK) >> CSR_LDSTORDER_SHIFT; + + s = snprintf(str, sizeof(str), "Boot State: %d (%s)\n" + "Current State: %d (%s)\n\n" + "Available States:\n" + "0 (%s)\t" "1 (%s)\t" "3 (%s)\n" + "4 (%s)\t" "5 (%s)\t" "7 (%s)\n", + tso_state, tso_hints[tso_state], state, tso_hints[state], + tso_hints[0], tso_hints[1], tso_hints[3], tso_hints[4], tso_hints[5], tso_hints[7]); + + if (*ppos >= s) + return 0; + + s -= *ppos; + s = min_t(u32, s, count); + + if (copy_to_user(buf, &str[*ppos], s)) + return -EFAULT; + + *ppos += s; + + return s; +} + +static ssize_t tso_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + int state; + + if (kstrtoint_from_user(buf, count, 10, &state)) + return -EFAULT; + + switch (state) { + case 0: case 1: case 3: + case 4: case 5: case 7: + on_each_cpu(set_tso_state, &state, 1); + break; + default: + return -EINVAL; + } + + return count; +} + +static const struct file_operations tso_fops = { + .read = tso_read, + .write = tso_write, + .open = simple_open, + .llseek = default_llseek +}; + +static int __init arch_kdebugfs_init(void) +{ + unsigned int config = read_cpucfg(LOONGARCH_CPUCFG3); + + arch_debugfs_dir = debugfs_create_dir("loongarch", NULL); + + if (config & CPUCFG3_SFB) { + debugfs_create_file("sfb_state", S_IRUGO | S_IWUSR, + arch_debugfs_dir, &sfb_state, &sfb_fops); + sfb_state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_STFILL) >> CSR_STFILL_SHIFT; + } + + if (config & (CPUCFG3_ALDORDER_CAP | CPUCFG3_ASTORDER_CAP)) { + debugfs_create_file("tso_state", S_IRUGO | S_IWUSR, + arch_debugfs_dir, &tso_state, &tso_fops); + tso_state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_LDSTORDER_MASK) >> CSR_LDSTORDER_SHIFT; + } + + return 0; +} +postcore_initcall(arch_kdebugfs_init); diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S index 3015896016a0..b6850503e061 100644 --- a/arch/loongarch/kernel/mcount.S +++ b/arch/loongarch/kernel/mcount.S @@ -79,10 +79,11 @@ SYM_FUNC_START(ftrace_graph_caller) SYM_FUNC_END(ftrace_graph_caller) SYM_FUNC_START(return_to_handler) - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + /* Save return value regs */ + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler @@ -90,9 +91,11 @@ SYM_FUNC_START(return_to_handler) /* Restore the real parent address: a0 -> ra */ move ra, a0 - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + /* Restore return value regs */ + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE + jr ra SYM_FUNC_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S index 0c65cf09110c..d6b474ad1d5e 100644 --- a/arch/loongarch/kernel/mcount_dyn.S +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -140,19 +140,19 @@ SYM_CODE_END(ftrace_graph_caller) SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED /* Save return value regs */ - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler move ra, a0 /* Restore return value regs */ - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE jr ra SYM_CODE_END(return_to_handler) diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index 19dc6eff45cc..5e2402cfcab0 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -720,7 +720,7 @@ static int hw_break_set(struct task_struct *target, unsigned int note_type = regset->core_note_type; /* Resource info */ - offset = offsetof(struct user_watch_state, dbg_regs); + offset = offsetof(struct user_watch_state_v2, dbg_regs); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); /* (address, mask, ctrl) registers */ @@ -920,7 +920,7 @@ static const struct user_regset loongarch64_regsets[] = { #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { .core_note_type = NT_LOONGARCH_HW_BREAK, - .n = sizeof(struct user_watch_state) / sizeof(u32), + .n = sizeof(struct user_watch_state_v2) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, @@ -928,7 +928,7 @@ static const struct user_regset loongarch64_regsets[] = { }, [REGSET_HW_WATCH] = { .core_note_type = NT_LOONGARCH_HW_WATCH, - .n = sizeof(struct user_watch_state) / sizeof(u32), + .n = sizeof(struct user_watch_state_v2) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 56934fe58170..edcfdfcad7d2 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -431,7 +431,7 @@ static void __init resource_init(void) num_standard_resources = memblock.memory.cnt; res_size = num_standard_resources * sizeof(*standard_resources); - standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES); + standard_resources = memblock_alloc_or_panic(res_size, SMP_CACHE_BYTES); for_each_mem_region(region) { res = &standard_resources[i++]; diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S index 31dd8199b245..9c23cb7e432f 100644 --- a/arch/loongarch/kernel/switch.S +++ b/arch/loongarch/kernel/switch.S @@ -12,7 +12,7 @@ /* * task_struct *__switch_to(task_struct *prev, task_struct *next, - * struct thread_info *next_ti) + * struct thread_info *next_ti, void *sched_ra, void *sched_cfa) */ .align 5 SYM_FUNC_START(__switch_to) diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index a07d7eff4dc5..e2d3bfeb6366 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -132,7 +132,7 @@ int constant_clockevent_init(void) #else unsigned long min_delta = 1000; #endif - unsigned long max_delta = (1UL << 48) - 1; + unsigned long max_delta = GENMASK_ULL(boot_cpu_data.timerbits, 0); struct clock_event_device *cd; static int irq = 0, timer_irq_installed = 0; diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index c57b4134f3e8..2ec3106c0da3 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -597,17 +597,24 @@ int is_valid_bugaddr(unsigned long addr) static void bug_handler(struct pt_regs *regs) { + if (user_mode(regs)) { + force_sig(SIGTRAP); + return; + } + switch (report_bug(regs->csr_era, regs)) { case BUG_TRAP_TYPE_BUG: - case BUG_TRAP_TYPE_NONE: - die_if_kernel("Oops - BUG", regs); - force_sig(SIGTRAP); + die("Oops - BUG", regs); break; case BUG_TRAP_TYPE_WARN: /* Skip the BUG instruction and continue */ regs->csr_era += LOONGARCH_INSN_SIZE; break; + + default: + if (!fixup_exception(regs)) + die("Oops - BUG", regs); } } diff --git a/arch/loongarch/kernel/unaligned.c b/arch/loongarch/kernel/unaligned.c index 3abf163dda05..487be604b96a 100644 --- a/arch/loongarch/kernel/unaligned.c +++ b/arch/loongarch/kernel/unaligned.c @@ -482,14 +482,10 @@ sigbus: #ifdef CONFIG_DEBUG_FS static int __init debugfs_unaligned(void) { - struct dentry *d; - - d = debugfs_create_dir("loongarch", NULL); - debugfs_create_u32("unaligned_instructions_user", - S_IRUGO, d, &unaligned_instructions_user); + S_IRUGO, arch_debugfs_dir, &unaligned_instructions_user); debugfs_create_u32("unaligned_instructions_kernel", - S_IRUGO, d, &unaligned_instructions_kernel); + S_IRUGO, arch_debugfs_dir, &unaligned_instructions_kernel); return 0; } diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c index a7893bd01e73..c1e8ec5b941b 100644 --- a/arch/loongarch/kvm/exit.c +++ b/arch/loongarch/kvm/exit.c @@ -709,6 +709,14 @@ static int kvm_handle_write_fault(struct kvm_vcpu *vcpu) return kvm_handle_rdwr_fault(vcpu, true); } +int kvm_complete_user_service(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + update_pc(&vcpu->arch); + kvm_write_reg(vcpu, LOONGARCH_GPR_A0, run->hypercall.ret); + + return 0; +} + /** * kvm_handle_fpu_disabled() - Guest used fpu however it is disabled at host * @vcpu: Virtual CPU context. @@ -873,6 +881,28 @@ static int kvm_handle_hypercall(struct kvm_vcpu *vcpu) vcpu->stat.hypercall_exits++; kvm_handle_service(vcpu); break; + case KVM_HCALL_USER_SERVICE: + if (!kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_USER_HCALL)) { + kvm_write_reg(vcpu, LOONGARCH_GPR_A0, KVM_HCALL_INVALID_CODE); + break; + } + + vcpu->stat.hypercall_exits++; + vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; + vcpu->run->hypercall.nr = KVM_HCALL_USER_SERVICE; + vcpu->run->hypercall.args[0] = kvm_read_reg(vcpu, LOONGARCH_GPR_A0); + vcpu->run->hypercall.args[1] = kvm_read_reg(vcpu, LOONGARCH_GPR_A1); + vcpu->run->hypercall.args[2] = kvm_read_reg(vcpu, LOONGARCH_GPR_A2); + vcpu->run->hypercall.args[3] = kvm_read_reg(vcpu, LOONGARCH_GPR_A3); + vcpu->run->hypercall.args[4] = kvm_read_reg(vcpu, LOONGARCH_GPR_A4); + vcpu->run->hypercall.args[5] = kvm_read_reg(vcpu, LOONGARCH_GPR_A5); + vcpu->run->hypercall.flags = 0; + /* + * Set invalid return value by default, let user-mode VMM modify it. + */ + vcpu->run->hypercall.ret = KVM_HCALL_INVALID_CODE; + ret = RESUME_HOST; + break; case KVM_HCALL_SWDBG: /* KVM_HCALL_SWDBG only in effective when SW_BP is enabled */ if (vcpu->guest_debug & KVM_GUESTDBG_SW_BP_MASK) { diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 396fed2665a5..bf9268bf26d5 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -245,6 +245,24 @@ void kvm_check_vpid(struct kvm_vcpu *vcpu) trace_kvm_vpid_change(vcpu, vcpu->arch.vpid); vcpu->cpu = cpu; kvm_clear_request(KVM_REQ_TLB_FLUSH_GPA, vcpu); + + /* + * LLBCTL is a separated guest CSR register from host, a general + * exception ERET instruction clears the host LLBCTL register in + * host mode, and clears the guest LLBCTL register in guest mode. + * ERET in tlb refill exception does not clear LLBCTL register. + * + * When secondary mmu mapping is changed, guest OS does not know + * even if the content is changed after mapping is changed. + * + * Here clear WCLLB of the guest LLBCTL register when mapping is + * changed. Otherwise, if mmu mapping is changed while guest is + * executing LL/SC pair, LL loads with the old address and set + * the LLBCTL flag, SC checks the LLBCTL flag and will store the + * new address successfully since LLBCTL_WCLLB is on, even if + * memory with new address is changed on other VCPUs. + */ + set_gcsr_llbctl(CSR_LLBCTL_WCLLB); } /* Restore GSTAT(0x50).vpid */ diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index d18a4a270415..fb72095c8077 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -1732,9 +1732,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu->mmio_needed = 0; } - if (run->exit_reason == KVM_EXIT_LOONGARCH_IOCSR) { + switch (run->exit_reason) { + case KVM_EXIT_HYPERCALL: + kvm_complete_user_service(vcpu, run); + break; + case KVM_EXIT_LOONGARCH_IOCSR: if (!run->iocsr_io.is_write) kvm_complete_iocsr_read(vcpu, run); + break; } if (!vcpu->wants_to_run) diff --git a/arch/loongarch/lib/Makefile b/arch/loongarch/lib/Makefile index ccea3bbd4353..fae77809048b 100644 --- a/arch/loongarch/lib/Makefile +++ b/arch/loongarch/lib/Makefile @@ -11,3 +11,5 @@ obj-$(CONFIG_ARCH_SUPPORTS_INT128) += tishift.o obj-$(CONFIG_CPU_HAS_LSX) += xor_simd.o xor_simd_glue.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o + +obj-$(CONFIG_CRC32_ARCH) += crc32-loongarch.o diff --git a/arch/loongarch/lib/crc32-loongarch.c b/arch/loongarch/lib/crc32-loongarch.c new file mode 100644 index 000000000000..8af8113ecd9d --- /dev/null +++ b/arch/loongarch/lib/crc32-loongarch.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * CRC32 and CRC32C using LoongArch crc* instructions + * + * Module based on mips/crypto/crc32-mips.c + * + * Copyright (C) 2014 Linaro Ltd + * Copyright (C) 2018 MIPS Tech, LLC + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#include +#include +#include +#include + +#define _CRC32(crc, value, size, type) \ +do { \ + __asm__ __volatile__( \ + #type ".w." #size ".w" " %0, %1, %0\n\t"\ + : "+r" (crc) \ + : "r" (value) \ + : "memory"); \ +} while (0) + +#define CRC32(crc, value, size) _CRC32(crc, value, size, crc) +#define CRC32C(crc, value, size) _CRC32(crc, value, size, crcc) + +static DEFINE_STATIC_KEY_FALSE(have_crc32); + +u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) +{ + if (!static_branch_likely(&have_crc32)) + return crc32_le_base(crc, p, len); + + while (len >= sizeof(u64)) { + u64 value = get_unaligned_le64(p); + + CRC32(crc, value, d); + p += sizeof(u64); + len -= sizeof(u64); + } + + if (len & sizeof(u32)) { + u32 value = get_unaligned_le32(p); + + CRC32(crc, value, w); + p += sizeof(u32); + } + + if (len & sizeof(u16)) { + u16 value = get_unaligned_le16(p); + + CRC32(crc, value, h); + p += sizeof(u16); + } + + if (len & sizeof(u8)) { + u8 value = *p++; + + CRC32(crc, value, b); + } + + return crc; +} +EXPORT_SYMBOL(crc32_le_arch); + +u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len) +{ + if (!static_branch_likely(&have_crc32)) + return crc32c_le_base(crc, p, len); + + while (len >= sizeof(u64)) { + u64 value = get_unaligned_le64(p); + + CRC32C(crc, value, d); + p += sizeof(u64); + len -= sizeof(u64); + } + + if (len & sizeof(u32)) { + u32 value = get_unaligned_le32(p); + + CRC32C(crc, value, w); + p += sizeof(u32); + } + + if (len & sizeof(u16)) { + u16 value = get_unaligned_le16(p); + + CRC32C(crc, value, h); + p += sizeof(u16); + } + + if (len & sizeof(u8)) { + u8 value = *p++; + + CRC32C(crc, value, b); + } + + return crc; +} +EXPORT_SYMBOL(crc32c_le_arch); + +u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) +{ + return crc32_be_base(crc, p, len); +} +EXPORT_SYMBOL(crc32_be_arch); + +static int __init crc32_loongarch_init(void) +{ + if (cpu_has_crc32) + static_branch_enable(&have_crc32); + return 0; +} +arch_initcall(crc32_loongarch_init); + +static void __exit crc32_loongarch_exit(void) +{ +} +module_exit(crc32_loongarch_exit); + +u32 crc32_optimizations(void) +{ + if (static_key_enabled(&have_crc32)) + return CRC32_LE_OPTIMIZATION | CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_AUTHOR("Min Zhou "); +MODULE_AUTHOR("Huacai Chen "); +MODULE_DESCRIPTION("CRC32 and CRC32C using LoongArch crc* instructions"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index 188b52bbb254..ca5aa5f46a9f 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -174,9 +174,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr) pmd_t *pmd; if (p4d_none(p4dp_get(p4d))) { - pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pud) - panic("%s: Failed to allocate memory\n", __func__); + pud = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); p4d_populate(&init_mm, p4d, pud); #ifndef __PAGETABLE_PUD_FOLDED pud_init(pud); @@ -185,9 +183,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr) pud = pud_offset(p4d, addr); if (pud_none(pudp_get(pud))) { - pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pmd) - panic("%s: Failed to allocate memory\n", __func__); + pmd = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); pud_populate(&init_mm, pud, pmd); #ifndef __PAGETABLE_PMD_FOLDED pmd_init(pmd); @@ -198,10 +194,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr) if (!pmd_present(pmdp_get(pmd))) { pte_t *pte; - pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pte) - panic("%s: Failed to allocate memory\n", __func__); - + pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); pmd_populate_kernel(&init_mm, pmd, pte); kernel_pte_init(pte); } diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index 3fa69b23ff84..22a94bb3e6e8 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -23,11 +23,10 @@ EXPORT_SYMBOL(tlb_virt_to_page); pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *init, *ret = NULL; - struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); + pgd_t *init, *ret; - if (ptdesc) { - ret = (pgd_t *)ptdesc_address(ptdesc); + ret = __pgd_alloc(mm, 0); + if (ret) { init = pgd_offset(&init_mm, 0UL); pgd_init(ret); memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD, diff --git a/arch/loongarch/power/platform.c b/arch/loongarch/power/platform.c index 0909729dc2e1..5bbdb9fd76e5 100644 --- a/arch/loongarch/power/platform.c +++ b/arch/loongarch/power/platform.c @@ -17,7 +17,7 @@ void enable_gpe_wakeup(void) if (acpi_gbl_reduced_hardware) return; - acpi_enable_all_wakeup_gpes(); + acpi_hw_enable_all_wakeup_gpes(); } void enable_pci_wakeup(void) diff --git a/arch/loongarch/power/suspend_asm.S b/arch/loongarch/power/suspend_asm.S index 9fe28d5a0270..df0865df26fa 100644 --- a/arch/loongarch/power/suspend_asm.S +++ b/arch/loongarch/power/suspend_asm.S @@ -30,9 +30,6 @@ st.d $r29, sp, PT_R29 st.d $r30, sp, PT_R30 st.d $r31, sp, PT_R31 - - la.pcrel t0, acpi_saved_sp - st.d sp, t0, 0 .endm .macro SETUP_WAKEUP @@ -51,6 +48,7 @@ ld.d $r29, sp, PT_R29 ld.d $r30, sp, PT_R30 ld.d $r31, sp, PT_R31 + addi.d sp, sp, PT_SIZE .endm .text @@ -59,6 +57,10 @@ /* Sleep/wakeup code for Loongson-3 */ SYM_FUNC_START(loongarch_suspend_enter) SETUP_SLEEP + + la.pcrel t0, acpi_saved_sp + st.d sp, t0, 0 + bl __flush_cache_all /* Pass RA and SP to BIOS */ @@ -82,7 +84,7 @@ SYM_INNER_LABEL(loongarch_wakeup_start, SYM_L_GLOBAL) la.pcrel t0, acpi_saved_sp ld.d sp, t0, 0 + SETUP_WAKEUP - addi.d sp, sp, PT_SIZE jr ra SYM_FUNC_END(loongarch_suspend_enter) diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 7c4f7bcc89d7..b2ed0308c0ea 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -23,7 +23,9 @@ config M68K select GENERIC_LIB_ASHLDI3 select GENERIC_LIB_ASHRDI3 select GENERIC_LIB_LSHRDI3 + select GENERIC_LIB_MULDI3 select HAS_IOPORT if PCI || ISA || ATARI_ROM_ISA + select HAVE_ARCH_LIBGCC_H select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER select HAVE_ASM_MODVERSIONS diff --git a/arch/m68k/atari/nvram.c b/arch/m68k/atari/nvram.c index 7000d2443aa3..ededc31375c3 100644 --- a/arch/m68k/atari/nvram.c +++ b/arch/m68k/atari/nvram.c @@ -16,7 +16,9 @@ #include #include #include +#include #include + #include #include @@ -198,7 +200,7 @@ static void atari_nvram_proc_read(unsigned char *nvram, struct seq_file *seq, seq_printf(seq, "0x%02x (undefined)\n", nvram[1]); seq_printf(seq, "SCSI arbitration : %s\n", - (nvram[16] & 0x80) ? "on" : "off"); + str_on_off(nvram[16] & 0x80)); seq_puts(seq, "SCSI host ID : "); if (nvram[16] & 0x80) seq_printf(seq, "%d\n", nvram[16] & 7); @@ -236,7 +238,7 @@ static void atari_nvram_proc_read(unsigned char *nvram, struct seq_file *seq, vmode & 16 ? "VGA" : "TV", vmode & 32 ? "PAL" : "NTSC"); seq_printf(seq, " %soverscan, compat. mode %s%s\n", - vmode & 64 ? "" : "no ", vmode & 128 ? "on" : "off", + vmode & 64 ? "" : "no ", str_on_off(vmode & 128), vmode & 256 ? (vmode & 16 ? ", line doubling" : ", half screen") : ""); } diff --git a/arch/m68k/coldfire/m5441x.c b/arch/m68k/coldfire/m5441x.c index 405e9d5c832c..7a25cfc7ac07 100644 --- a/arch/m68k/coldfire/m5441x.c +++ b/arch/m68k/coldfire/m5441x.c @@ -33,14 +33,14 @@ DEFINE_CLK(0, "mcfuart.0", 24, MCF_BUSCLK); DEFINE_CLK(0, "mcfuart.1", 25, MCF_BUSCLK); DEFINE_CLK(0, "mcfuart.2", 26, MCF_BUSCLK); DEFINE_CLK(0, "mcfuart.3", 27, MCF_BUSCLK); -DEFINE_CLK(0, "mcftmr.0", 28, MCF_CLK); -DEFINE_CLK(0, "mcftmr.1", 29, MCF_CLK); -DEFINE_CLK(0, "mcftmr.2", 30, MCF_CLK); -DEFINE_CLK(0, "mcftmr.3", 31, MCF_CLK); -DEFINE_CLK(0, "mcfpit.0", 32, MCF_CLK); -DEFINE_CLK(0, "mcfpit.1", 33, MCF_CLK); -DEFINE_CLK(0, "mcfpit.2", 34, MCF_CLK); -DEFINE_CLK(0, "mcfpit.3", 35, MCF_CLK); +DEFINE_CLK(0, "mcftmr.0", 28, MCF_BUSCLK); +DEFINE_CLK(0, "mcftmr.1", 29, MCF_BUSCLK); +DEFINE_CLK(0, "mcftmr.2", 30, MCF_BUSCLK); +DEFINE_CLK(0, "mcftmr.3", 31, MCF_BUSCLK); +DEFINE_CLK(0, "mcfpit.0", 32, MCF_BUSCLK); +DEFINE_CLK(0, "mcfpit.1", 33, MCF_BUSCLK); +DEFINE_CLK(0, "mcfpit.2", 34, MCF_BUSCLK); +DEFINE_CLK(0, "mcfpit.3", 35, MCF_BUSCLK); DEFINE_CLK(0, "mcfeport.0", 37, MCF_CLK); DEFINE_CLK(0, "mcfadc.0", 38, MCF_CLK); DEFINE_CLK(0, "mcfdac.0", 39, MCF_CLK); @@ -167,8 +167,8 @@ static struct clk * const disable_clks[] __initconst = { &__clk_0_14, /* i2c.1 */ &__clk_0_22, /* i2c.0 */ &__clk_0_23, /* dspi.0 */ - &__clk_0_28, /* tmr.1 */ - &__clk_0_29, /* tmr.2 */ + &__clk_0_28, /* tmr.0 */ + &__clk_0_29, /* tmr.1 */ &__clk_0_30, /* tmr.2 */ &__clk_0_31, /* tmr.3 */ &__clk_0_32, /* pit.0 */ diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index c705247e7b5b..dbf2ea561c85 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -579,7 +579,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -589,7 +588,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -606,7 +604,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 6d62b9187a58..b0fd199cc0a4 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -536,7 +536,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -546,7 +545,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -563,7 +561,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index c3c644df852d..bb5b2d3b6c10 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -556,7 +556,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -566,7 +565,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -583,7 +581,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 20261f819691..8315a13bab73 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -528,7 +528,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -538,7 +537,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -555,7 +553,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index ce4fe93a0f70..350370657e5f 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -538,7 +538,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -548,7 +547,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -565,7 +563,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 040ae75f47c3..f942b4755702 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -555,7 +555,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -565,7 +564,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -582,7 +580,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 20d877cb4e30..b1eaad02efab 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -642,7 +642,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -652,7 +651,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -669,7 +667,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 5e1c8d0d3da5..6309a4442bb3 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -528,7 +528,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -538,7 +537,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -555,7 +553,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 5d1409e6a137..3feb0731f814 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -529,7 +529,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -539,7 +538,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -556,7 +554,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index e4c30e2b9bbb..ea04b1b0da7d 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -545,7 +545,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -555,7 +554,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -572,7 +570,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 980843a9ea1e..f52d9af92153 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -526,7 +526,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -536,7 +535,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -553,7 +551,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 38681cc6b598..f348447824da 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -526,7 +526,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m @@ -536,7 +535,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m @@ -553,7 +551,6 @@ CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m # CONFIG_CRYPTO_HW is not set CONFIG_PRIME_NUMBERS=m -CONFIG_CRC32_SELFTEST=m CONFIG_XZ_DEC_TEST=m CONFIG_GLOB_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set diff --git a/arch/m68k/include/asm/libgcc.h b/arch/m68k/include/asm/libgcc.h new file mode 100644 index 000000000000..27e17195bd7b --- /dev/null +++ b/arch/m68k/include/asm/libgcc.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_M68K_LIBGCC_H +#define __ASM_M68K_LIBGCC_H + +#ifndef CONFIG_CPU_HAS_NO_MULDIV64 +/* + * For those 68K CPUs that support 64bit multiply define umul_ppm() + * for the common muldi3 libgcc helper function (in lib/muldi3.c). + * CPUs that don't have it (like the original 68000 and ColdFire) + * will fallback to using the C-coded version of umul_ppmm(). + */ +#define umul_ppmm(w1, w0, u, v) \ + do { \ + unsigned long __u = (u), __v = (v); \ + unsigned long __w0, __w1; \ + \ + __asm__ ("mulu%.l %3,%1:%0" \ + : "=d" (__w0), \ + "=d" (__w1) \ + : "%0" (__u), \ + "dmi" (__v)); \ + \ + (w0) = __w0; (w1) = __w1; \ + } while (0) +#endif /* !CONFIG_CPU_HAS_NO_MULDIV64 */ + +#endif /* __ASM_M68K_LIBGCC_H */ diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index 302c5bf67179..4c648b51e7fd 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -37,7 +37,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pgtable, { struct ptdesc *ptdesc = virt_to_ptdesc(pgtable); - pagetable_pte_dtor(ptdesc); + pagetable_dtor(ptdesc); pagetable_free(ptdesc); } @@ -61,7 +61,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable) { struct ptdesc *ptdesc = virt_to_ptdesc(pgtable); - pagetable_pte_dtor(ptdesc); + pagetable_dtor(ptdesc); pagetable_free(ptdesc); } @@ -73,7 +73,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable) static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - pagetable_free(virt_to_ptdesc(pgd)); + pagetable_dtor_free(virt_to_ptdesc(pgd)); } static inline pgd_t *pgd_alloc(struct mm_struct *mm) @@ -84,6 +84,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) if (!ptdesc) return NULL; + pagetable_pgd_ctor(ptdesc); new_pgd = ptdesc_address(ptdesc); memcpy(new_pgd, swapper_pg_dir, PTRS_PER_PGD * sizeof(pgd_t)); diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h index 74a817d9387f..5abe7da8ac5a 100644 --- a/arch/m68k/include/asm/motorola_pgalloc.h +++ b/arch/m68k/include/asm/motorola_pgalloc.h @@ -9,9 +9,9 @@ extern void mmu_page_ctor(void *page); extern void mmu_page_dtor(void *page); enum m68k_table_types { - TABLE_PGD = 0, - TABLE_PMD = 0, /* same size as PGD */ - TABLE_PTE = 1, + TABLE_PGD, + TABLE_PMD, + TABLE_PTE, }; extern void init_pointer_table(void *table, int type); diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 4a137eecb6fe..f1ae4ed890db 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -19,7 +19,7 @@ extern const char bad_pmd_string[]; #define __pte_free_tlb(tlb, pte, addr) \ do { \ - pagetable_pte_dtor(page_ptdesc(pte)); \ + pagetable_dtor(page_ptdesc(pte)); \ tlb_remove_page_ptdesc((tlb), page_ptdesc(pte)); \ } while (0) @@ -43,7 +43,7 @@ static inline pgd_t * pgd_alloc(struct mm_struct *mm) { pgd_t *new_pgd; - new_pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL); + new_pgd = __pgd_alloc(mm, 0); memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE); memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT)); return new_pgd; diff --git a/arch/m68k/include/asm/vga.h b/arch/m68k/include/asm/vga.h index 4742e6bc3ab8..cdd414fa8710 100644 --- a/arch/m68k/include/asm/vga.h +++ b/arch/m68k/include/asm/vga.h @@ -9,7 +9,7 @@ */ #ifndef CONFIG_PCI -#include +#include #include /* @@ -29,9 +29,9 @@ #define inw_p(port) 0 #define outb_p(port, val) do { } while (0) #define outw(port, val) do { } while (0) -#define readb raw_inb -#define writeb raw_outb -#define writew raw_outw +#define readb __raw_readb +#define writeb __raw_writeb +#define writew __raw_writew #endif /* CONFIG_PCI */ #endif /* _ASM_M68K_VGA_H */ diff --git a/arch/m68k/lib/Makefile b/arch/m68k/lib/Makefile index 9158688e6cc6..15278a95259e 100644 --- a/arch/m68k/lib/Makefile +++ b/arch/m68k/lib/Makefile @@ -4,7 +4,7 @@ # Makefile for m68k-specific library files.. # -lib-y := muldi3.o memcpy.o memset.o memmove.o +lib-y := memcpy.o memset.o memmove.o lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_CPU_HAS_NO_MULDIV64) += mulsi3.o divsi3.o udivsi3.o diff --git a/arch/m68k/lib/muldi3.c b/arch/m68k/lib/muldi3.c deleted file mode 100644 index 5012a9b218c7..000000000000 --- a/arch/m68k/lib/muldi3.c +++ /dev/null @@ -1,97 +0,0 @@ -/* muldi3.c extracted from gcc-2.7.2.3/libgcc2.c and - gcc-2.7.2.3/longlong.h which is: */ -/* Copyright (C) 1989, 1992, 1993, 1994, 1995 Free Software Foundation, Inc. - -This file is part of GNU CC. - -GNU CC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 2, or (at your option) -any later version. - -GNU CC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. */ - -#include -#include -#include - -#ifdef CONFIG_CPU_HAS_NO_MULDIV64 - -#define SI_TYPE_SIZE 32 -#define __BITS4 (SI_TYPE_SIZE / 4) -#define __ll_B (1L << (SI_TYPE_SIZE / 2)) -#define __ll_lowpart(t) ((USItype) (t) % __ll_B) -#define __ll_highpart(t) ((USItype) (t) / __ll_B) - -#define umul_ppmm(w1, w0, u, v) \ - do { \ - USItype __x0, __x1, __x2, __x3; \ - USItype __ul, __vl, __uh, __vh; \ - \ - __ul = __ll_lowpart (u); \ - __uh = __ll_highpart (u); \ - __vl = __ll_lowpart (v); \ - __vh = __ll_highpart (v); \ - \ - __x0 = (USItype) __ul * __vl; \ - __x1 = (USItype) __ul * __vh; \ - __x2 = (USItype) __uh * __vl; \ - __x3 = (USItype) __uh * __vh; \ - \ - __x1 += __ll_highpart (__x0);/* this can't give carry */ \ - __x1 += __x2; /* but this indeed can */ \ - if (__x1 < __x2) /* did we get it? */ \ - __x3 += __ll_B; /* yes, add it in the proper pos. */ \ - \ - (w1) = __x3 + __ll_highpart (__x1); \ - (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0); \ - } while (0) - -#else - -#define umul_ppmm(w1, w0, u, v) \ - __asm__ ("mulu%.l %3,%1:%0" \ - : "=d" ((USItype)(w0)), \ - "=d" ((USItype)(w1)) \ - : "%0" ((USItype)(u)), \ - "dmi" ((USItype)(v))) - -#endif - -#define __umulsidi3(u, v) \ - ({DIunion __w; \ - umul_ppmm (__w.s.high, __w.s.low, u, v); \ - __w.ll; }) - -typedef int SItype __mode(SI); -typedef unsigned int USItype __mode(SI); -typedef int DItype __mode(DI); -typedef int word_type __mode(__word__); - -struct DIstruct {SItype high, low;}; - -typedef union -{ - struct DIstruct s; - DItype ll; -} DIunion; - -DItype -__muldi3 (DItype u, DItype v) -{ - DIunion w; - DIunion uu, vv; - - uu.ll = u; - vv.ll = v; - - w.ll = __umulsidi3 (uu.s.low, vv.s.low); - w.s.high += ((USItype) uu.s.low * (USItype) vv.s.high - + (USItype) uu.s.high * (USItype) vv.s.low); - - return w.ll; -} -EXPORT_SYMBOL(__muldi3); diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 1b47bec15832..8b11d0d545aa 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -68,10 +68,7 @@ void __init paging_init(void) high_memory = (void *) end_mem; - empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!empty_zero_page) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); max_zone_pfn[ZONE_DMA] = end_mem >> PAGE_SHIFT; free_area_init(max_zone_pfn); } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 9a6fa342e872..19a75029036c 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -42,20 +42,14 @@ void __init paging_init(void) unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; int i; - empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!empty_zero_page) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); pg_dir = swapper_pg_dir; memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir)); size = num_pages * sizeof(pte_t); size = (size + PAGE_SIZE) & ~(PAGE_SIZE-1); - next_pgtable = (unsigned long) memblock_alloc(size, PAGE_SIZE); - if (!next_pgtable) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, size, PAGE_SIZE); + next_pgtable = (unsigned long) memblock_alloc_or_panic(size, PAGE_SIZE); pg_dir += PAGE_OFFSET >> PGDIR_SHIFT; diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index c1761d309fc6..73651e093c4d 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -97,17 +97,19 @@ void mmu_page_dtor(void *page) typedef struct list_head ptable_desc; -static struct list_head ptable_list[2] = { +static struct list_head ptable_list[3] = { LIST_HEAD_INIT(ptable_list[0]), LIST_HEAD_INIT(ptable_list[1]), + LIST_HEAD_INIT(ptable_list[2]), }; #define PD_PTABLE(page) ((ptable_desc *)&(virt_to_page((void *)(page))->lru)) #define PD_PAGE(ptable) (list_entry(ptable, struct page, lru)) #define PD_MARKBITS(dp) (*(unsigned int *)&PD_PAGE(dp)->index) -static const int ptable_shift[2] = { - 7+2, /* PGD, PMD */ +static const int ptable_shift[3] = { + 7+2, /* PGD */ + 7+2, /* PMD */ 6+2, /* PTE */ }; @@ -156,12 +158,20 @@ void *get_pointer_table(int type) if (!(page = (void *)get_zeroed_page(GFP_KERNEL))) return NULL; - if (type == TABLE_PTE) { + switch (type) { + case TABLE_PTE: /* * m68k doesn't have SPLIT_PTE_PTLOCKS for not having * SMP. */ pagetable_pte_ctor(virt_to_ptdesc(page)); + break; + case TABLE_PMD: + pagetable_pmd_ctor(virt_to_ptdesc(page)); + break; + case TABLE_PGD: + pagetable_pgd_ctor(virt_to_ptdesc(page)); + break; } mmu_page_ctor(page); @@ -200,8 +210,7 @@ int free_pointer_table(void *table, int type) /* all tables in page are free, free page */ list_del(dp); mmu_page_dtor((void *)page); - if (type == TABLE_PTE) - pagetable_pte_dtor(virt_to_ptdesc((void *)page)); + pagetable_dtor(virt_to_ptdesc((void *)page)); free_page (page); return 1; } else if (ptable_list[type].next != dp) { @@ -491,10 +500,7 @@ void __init paging_init(void) * initialize the bad page table and bad page to point * to a couple of allocated pages */ - empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!empty_zero_page) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); /* * Set up SFC/DFC registers diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c index 494739c1783e..1ecf6bdd08bf 100644 --- a/arch/m68k/mm/sun3mmu.c +++ b/arch/m68k/mm/sun3mmu.c @@ -44,10 +44,7 @@ void __init paging_init(void) unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0, }; unsigned long size; - empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!empty_zero_page) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); address = PAGE_OFFSET; pg_dir = swapper_pg_dir; @@ -57,10 +54,7 @@ void __init paging_init(void) size = num_pages * sizeof(pte_t); size = (size + PAGE_SIZE) & ~(PAGE_SIZE-1); - next_pgtable = (unsigned long)memblock_alloc(size, PAGE_SIZE); - if (!next_pgtable) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, size, PAGE_SIZE); + next_pgtable = (unsigned long)memblock_alloc_or_panic(size, PAGE_SIZE); bootmem_end = (next_pgtable + size + PAGE_SIZE) & PAGE_MASK; /* Map whole memory from PAGE_OFFSET (0x0E000000) */ diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c index 6ebf52740ad7..225fc735e466 100644 --- a/arch/m68k/sun3/sun3dvma.c +++ b/arch/m68k/sun3/sun3dvma.c @@ -252,12 +252,8 @@ void __init dvma_init(void) list_add(&(hole->list), &hole_list); - iommu_use = memblock_alloc(IOMMU_TOTAL_ENTRIES * sizeof(unsigned long), + iommu_use = memblock_alloc_or_panic(IOMMU_TOTAL_ENTRIES * sizeof(unsigned long), SMP_CACHE_BYTES); - if (!iommu_use) - panic("%s: Failed to allocate %zu bytes\n", __func__, - IOMMU_TOTAL_ENTRIES * sizeof(unsigned long)); - dvma_unmap_iommu(DVMA_START, DVMA_SIZE); sun3_dvma_init(); diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h index 6c33b05f730f..084a8a0dc239 100644 --- a/arch/microblaze/include/asm/pgalloc.h +++ b/arch/microblaze/include/asm/pgalloc.h @@ -21,12 +21,7 @@ extern void __bad_pte(pmd_t *pmd); -static inline pgd_t *get_pgd(void) -{ - return (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, 0); -} - -#define pgd_alloc(mm) get_pgd() +#define pgd_alloc(mm) __pgd_alloc(mm, 0) extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 467b10f4361a..1924f2d83932 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -29,10 +29,12 @@ config MIPS select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WANT_LD_ORPHAN_WARN select BUILDTIME_TABLE_SORT + select BUILTIN_DTB_ALL if BUILTIN_DTB select CLONE_BACKWARDS select CPU_NO_EFFICIENT_FFS if (TARGET_ISA_REV < 1) select CPU_PM if CPU_IDLE || SUSPEND select GENERIC_ATOMIC64 if !64BIT + select GENERIC_BUILTIN_DTB if BUILTIN_DTB select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE select GENERIC_GETTIMEOFDAY @@ -1084,7 +1086,6 @@ config CSRC_IOASIC config CSRC_R4K select CLOCKSOURCE_WATCHDOG if CPU_FREQ - select HAVE_UNSTABLE_SCHED_CLOCK if SMP && 64BIT bool config CSRC_SB1250 @@ -1995,11 +1996,11 @@ config CPU_MIPSR5 config CPU_MIPSR6 bool default y if CPU_MIPS32_R6 || CPU_MIPS64_R6 + select ARCH_HAS_CRC32 select CPU_HAS_RIXI select CPU_HAS_DIEI if !CPU_DIEI_BROKEN select HAVE_ARCH_BITREVERSE select MIPS_ASID_BITS_VARIABLE - select MIPS_CRC_SUPPORT select MIPS_SPRAM config TARGET_ISA_REV @@ -2475,9 +2476,6 @@ config MIPS_ASID_BITS config MIPS_ASID_BITS_VARIABLE bool -config MIPS_CRC_SUPPORT - bool - # R4600 erratum. Due to the lack of errata information the exact # technical details aren't known. I've experimentally found that disabling # interrupts during indexed I-cache flushes seems to be sufficient to deal diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 5785a3d5ccfb..be8cb44a89fd 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -423,9 +423,6 @@ endif CLEAN_FILES += vmlinux.32 vmlinux.64 -# device-trees -core-y += arch/mips/boot/dts/ - archprepare: ifdef CONFIG_MIPS32_N32 @$(kecho) ' Checking missing-syscalls for N32' diff --git a/arch/mips/boot/dts/Makefile b/arch/mips/boot/dts/Makefile index e2476b12bb0c..ff468439a8c4 100644 --- a/arch/mips/boot/dts/Makefile +++ b/arch/mips/boot/dts/Makefile @@ -16,5 +16,3 @@ subdir-$(CONFIG_ATH79) += qca subdir-$(CONFIG_RALINK) += ralink subdir-$(CONFIG_MACH_REALTEK_RTL) += realtek subdir-$(CONFIG_FIT_IMAGE_FDT_XILFPGA) += xilfpga - -obj-$(CONFIG_BUILTIN_DTB) := $(addsuffix /, $(subdir-y)) diff --git a/arch/mips/boot/dts/brcm/Makefile b/arch/mips/boot/dts/brcm/Makefile index d85f446cc0ce..1798209697c6 100644 --- a/arch/mips/boot/dts/brcm/Makefile +++ b/arch/mips/boot/dts/brcm/Makefile @@ -33,5 +33,3 @@ dtb-$(CONFIG_DT_NONE) += \ bcm97420c.dtb \ bcm97425svmb.dtb \ bcm97435svmb.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/cavium-octeon/Makefile b/arch/mips/boot/dts/cavium-octeon/Makefile index 17aef35f311b..48085bca666c 100644 --- a/arch/mips/boot/dts/cavium-octeon/Makefile +++ b/arch/mips/boot/dts/cavium-octeon/Makefile @@ -1,4 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_CAVIUM_OCTEON_SOC) += octeon_3xxx.dtb octeon_68xx.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/ingenic/Makefile b/arch/mips/boot/dts/ingenic/Makefile index 54aa0c4e6091..6e674f1a3aa3 100644 --- a/arch/mips/boot/dts/ingenic/Makefile +++ b/arch/mips/boot/dts/ingenic/Makefile @@ -5,5 +5,3 @@ dtb-$(CONFIG_JZ4770_GCW0) += gcw0.dtb dtb-$(CONFIG_JZ4780_CI20) += ci20.dtb dtb-$(CONFIG_X1000_CU1000_NEO) += cu1000-neo.dtb dtb-$(CONFIG_X1830_CU1830_NEO) += cu1830-neo.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/lantiq/Makefile b/arch/mips/boot/dts/lantiq/Makefile index ae6e3e21ebeb..d8531b4653c0 100644 --- a/arch/mips/boot/dts/lantiq/Makefile +++ b/arch/mips/boot/dts/lantiq/Makefile @@ -1,4 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_DT_EASY50712) += danube_easy50712.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/loongson/Makefile b/arch/mips/boot/dts/loongson/Makefile index 5c6433e441ee..5e3ab984d70f 100644 --- a/arch/mips/boot/dts/loongson/Makefile +++ b/arch/mips/boot/dts/loongson/Makefile @@ -5,5 +5,3 @@ dtb-$(CONFIG_MACH_LOONGSON64) += loongson64c_4core_rs780e.dtb dtb-$(CONFIG_MACH_LOONGSON64) += loongson64c_8core_rs780e.dtb dtb-$(CONFIG_MACH_LOONGSON64) += loongson64g_4core_ls7a.dtb dtb-$(CONFIG_MACH_LOONGSON64) += loongson64v_4core_virtio.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/mobileye/eyeq5.dtsi b/arch/mips/boot/dts/mobileye/eyeq5.dtsi index 5d73e8320b8e..a84e6e720619 100644 --- a/arch/mips/boot/dts/mobileye/eyeq5.dtsi +++ b/arch/mips/boot/dts/mobileye/eyeq5.dtsi @@ -49,6 +49,28 @@ mhm_reserved_0: the-mhm-reserved-0@0 { reg = <0x8 0x00000000 0x0 0x0000800>; }; + + nvram@461fe00 { + compatible = "mobileye,eyeq5-bootloader-config", "nvmem-rmem"; + reg = <0x0 0x0461fe00 0x0 0x200>; + #address-cells = <1>; + #size-cells = <1>; + no-map; + + nvmem-layout { + compatible = "fixed-layout"; + #address-cells = <1>; + #size-cells = <1>; + + eth0_mac: mac@7c { + reg = <0x7c 0x6>; + }; + + eth1_mac: mac@82 { + reg = <0x82 0x6>; + }; + }; + }; }; aliases { diff --git a/arch/mips/boot/dts/mscc/Makefile b/arch/mips/boot/dts/mscc/Makefile index eeb6b7aae83b..566dbec3c7fb 100644 --- a/arch/mips/boot/dts/mscc/Makefile +++ b/arch/mips/boot/dts/mscc/Makefile @@ -8,6 +8,3 @@ dtb-$(CONFIG_SOC_VCOREIII) += \ ocelot_pcb123.dtb \ serval_pcb105.dtb \ serval_pcb106.dtb - - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/mti/Makefile b/arch/mips/boot/dts/mti/Makefile index b5f7426998b1..c1c7b27296dd 100644 --- a/arch/mips/boot/dts/mti/Makefile +++ b/arch/mips/boot/dts/mti/Makefile @@ -1,5 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_MIPS_MALTA) += malta.dtb dtb-$(CONFIG_LEGACY_BOARD_SEAD3) += sead3.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/pic32/Makefile b/arch/mips/boot/dts/pic32/Makefile index fb57f36324db..4069cda2370c 100644 --- a/arch/mips/boot/dts/pic32/Makefile +++ b/arch/mips/boot/dts/pic32/Makefile @@ -3,5 +3,3 @@ dtb-$(CONFIG_DTB_PIC32_MZDA_SK) += pic32mzda_sk.dtb dtb-$(CONFIG_DTB_PIC32_NONE) += \ pic32mzda_sk.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/ralink/Makefile b/arch/mips/boot/dts/ralink/Makefile index d27d7e8c700f..dc002152d843 100644 --- a/arch/mips/boot/dts/ralink/Makefile +++ b/arch/mips/boot/dts/ralink/Makefile @@ -10,5 +10,3 @@ dtb-$(CONFIG_SOC_MT7621) += \ mt7621-gnubee-gb-pc1.dtb \ mt7621-gnubee-gb-pc2.dtb \ mt7621-tplink-hc220-g5-v1.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig index e463a9acae03..f7c4b3529a2c 100644 --- a/arch/mips/configs/bigsur_defconfig +++ b/arch/mips/configs/bigsur_defconfig @@ -222,7 +222,6 @@ CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m diff --git a/arch/mips/configs/decstation_64_defconfig b/arch/mips/configs/decstation_64_defconfig index 92a1d0aea38c..da51b9731db0 100644 --- a/arch/mips/configs/decstation_64_defconfig +++ b/arch/mips/configs/decstation_64_defconfig @@ -177,10 +177,8 @@ CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_CMAC=m CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m CONFIG_CRYPTO_CRCT10DIF=m CONFIG_CRYPTO_MD4=m diff --git a/arch/mips/configs/decstation_defconfig b/arch/mips/configs/decstation_defconfig index db214fcebcbe..424e3f011fc2 100644 --- a/arch/mips/configs/decstation_defconfig +++ b/arch/mips/configs/decstation_defconfig @@ -172,10 +172,8 @@ CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_CMAC=m CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m CONFIG_CRYPTO_CRCT10DIF=m CONFIG_CRYPTO_MD4=m diff --git a/arch/mips/configs/decstation_r4k_defconfig b/arch/mips/configs/decstation_r4k_defconfig index 15b769e96d5b..cfc8bf791792 100644 --- a/arch/mips/configs/decstation_r4k_defconfig +++ b/arch/mips/configs/decstation_r4k_defconfig @@ -172,10 +172,8 @@ CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_CMAC=m CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m CONFIG_CRYPTO_CRCT10DIF=m CONFIG_CRYPTO_MD4=m diff --git a/arch/mips/configs/eyeq5_defconfig b/arch/mips/configs/eyeq5_defconfig index ae9a09b16e40..ff7af5dc6d9d 100644 --- a/arch/mips/configs/eyeq5_defconfig +++ b/arch/mips/configs/eyeq5_defconfig @@ -99,7 +99,6 @@ CONFIG_NFS_V4=y CONFIG_NFS_V4_1=y CONFIG_NFS_V4_2=y CONFIG_ROOT_NFS=y -CONFIG_CRYPTO_CRC32_MIPS=y CONFIG_FRAME_WARN=1024 CONFIG_DEBUG_FS=y # CONFIG_RCU_TRACE is not set diff --git a/arch/mips/configs/eyeq6_defconfig b/arch/mips/configs/eyeq6_defconfig index 6597d5e88b33..0afbb45a78e8 100644 --- a/arch/mips/configs/eyeq6_defconfig +++ b/arch/mips/configs/eyeq6_defconfig @@ -102,7 +102,6 @@ CONFIG_NFS_V4=y CONFIG_NFS_V4_1=y CONFIG_NFS_V4_2=y CONFIG_ROOT_NFS=y -CONFIG_CRYPTO_CRC32_MIPS=y CONFIG_FRAME_WARN=1024 CONFIG_DEBUG_FS=y # CONFIG_RCU_TRACE is not set diff --git a/arch/mips/configs/generic/32r6.config b/arch/mips/configs/generic/32r6.config index 1a5d5ea4ab2b..ca606e71f4d0 100644 --- a/arch/mips/configs/generic/32r6.config +++ b/arch/mips/configs/generic/32r6.config @@ -1,4 +1,2 @@ CONFIG_CPU_MIPS32_R6=y CONFIG_HIGHMEM=y - -CONFIG_CRYPTO_CRC32_MIPS=y diff --git a/arch/mips/configs/generic/64r6.config b/arch/mips/configs/generic/64r6.config index 63b4e95f303d..23a300914957 100644 --- a/arch/mips/configs/generic/64r6.config +++ b/arch/mips/configs/generic/64r6.config @@ -4,5 +4,4 @@ CONFIG_MIPS32_O32=y CONFIG_MIPS32_N32=y CONFIG_CPU_HAS_MSA=y -CONFIG_CRYPTO_CRC32_MIPS=y CONFIG_VIRTUALIZATION=y diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index 4714074c8bd7..b08a199767d1 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -305,7 +305,6 @@ CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA512=m diff --git a/arch/mips/configs/ip30_defconfig b/arch/mips/configs/ip30_defconfig index 178d61645cea..270181a7320a 100644 --- a/arch/mips/configs/ip30_defconfig +++ b/arch/mips/configs/ip30_defconfig @@ -176,7 +176,6 @@ CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_LZO=m diff --git a/arch/mips/crypto/Kconfig b/arch/mips/crypto/Kconfig index 9003a5c1e879..7decd40c4e20 100644 --- a/arch/mips/crypto/Kconfig +++ b/arch/mips/crypto/Kconfig @@ -2,15 +2,6 @@ menu "Accelerated Cryptographic Algorithms for CPU (mips)" -config CRYPTO_CRC32_MIPS - tristate "CRC32c and CRC32" - depends on MIPS_CRC_SUPPORT - select CRYPTO_HASH - help - CRC32c and CRC32 CRC algorithms - - Architecture: mips - config CRYPTO_POLY1305_MIPS tristate "Hash functions: Poly1305" depends on MIPS diff --git a/arch/mips/crypto/Makefile b/arch/mips/crypto/Makefile index 5e4105cccf9f..fddc88281412 100644 --- a/arch/mips/crypto/Makefile +++ b/arch/mips/crypto/Makefile @@ -3,8 +3,6 @@ # Makefile for MIPS crypto files.. # -obj-$(CONFIG_CRYPTO_CRC32_MIPS) += crc32-mips.o - obj-$(CONFIG_CRYPTO_CHACHA_MIPS) += chacha-mips.o chacha-mips-y := chacha-core.o chacha-glue.o AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots diff --git a/arch/mips/crypto/crc32-mips.c b/arch/mips/crypto/crc32-mips.c deleted file mode 100644 index 90eacf00cfc3..000000000000 --- a/arch/mips/crypto/crc32-mips.c +++ /dev/null @@ -1,354 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * crc32-mips.c - CRC32 and CRC32C using optional MIPSr6 instructions - * - * Module based on arm64/crypto/crc32-arm.c - * - * Copyright (C) 2014 Linaro Ltd - * Copyright (C) 2018 MIPS Tech, LLC - */ - -#include -#include -#include -#include -#include -#include -#include - -#include - -enum crc_op_size { - b, h, w, d, -}; - -enum crc_type { - crc32, - crc32c, -}; - -#ifndef TOOLCHAIN_SUPPORTS_CRC -#define _ASM_SET_CRC(OP, SZ, TYPE) \ -_ASM_MACRO_3R(OP, rt, rs, rt2, \ - ".ifnc \\rt, \\rt2\n\t" \ - ".error \"invalid operands \\\"" #OP " \\rt,\\rs,\\rt2\\\"\"\n\t" \ - ".endif\n\t" \ - _ASM_INSN_IF_MIPS(0x7c00000f | (__rt << 16) | (__rs << 21) | \ - ((SZ) << 6) | ((TYPE) << 8)) \ - _ASM_INSN32_IF_MM(0x00000030 | (__rs << 16) | (__rt << 21) | \ - ((SZ) << 14) | ((TYPE) << 3))) -#define _ASM_UNSET_CRC(op, SZ, TYPE) ".purgem " #op "\n\t" -#else /* !TOOLCHAIN_SUPPORTS_CRC */ -#define _ASM_SET_CRC(op, SZ, TYPE) ".set\tcrc\n\t" -#define _ASM_UNSET_CRC(op, SZ, TYPE) -#endif - -#define __CRC32(crc, value, op, SZ, TYPE) \ -do { \ - __asm__ __volatile__( \ - ".set push\n\t" \ - _ASM_SET_CRC(op, SZ, TYPE) \ - #op " %0, %1, %0\n\t" \ - _ASM_UNSET_CRC(op, SZ, TYPE) \ - ".set pop" \ - : "+r" (crc) \ - : "r" (value)); \ -} while (0) - -#define _CRC32_crc32b(crc, value) __CRC32(crc, value, crc32b, 0, 0) -#define _CRC32_crc32h(crc, value) __CRC32(crc, value, crc32h, 1, 0) -#define _CRC32_crc32w(crc, value) __CRC32(crc, value, crc32w, 2, 0) -#define _CRC32_crc32d(crc, value) __CRC32(crc, value, crc32d, 3, 0) -#define _CRC32_crc32cb(crc, value) __CRC32(crc, value, crc32cb, 0, 1) -#define _CRC32_crc32ch(crc, value) __CRC32(crc, value, crc32ch, 1, 1) -#define _CRC32_crc32cw(crc, value) __CRC32(crc, value, crc32cw, 2, 1) -#define _CRC32_crc32cd(crc, value) __CRC32(crc, value, crc32cd, 3, 1) - -#define _CRC32(crc, value, size, op) \ - _CRC32_##op##size(crc, value) - -#define CRC32(crc, value, size) \ - _CRC32(crc, value, size, crc32) - -#define CRC32C(crc, value, size) \ - _CRC32(crc, value, size, crc32c) - -static u32 crc32_mips_le_hw(u32 crc_, const u8 *p, unsigned int len) -{ - u32 crc = crc_; - - if (IS_ENABLED(CONFIG_64BIT)) { - for (; len >= sizeof(u64); p += sizeof(u64), len -= sizeof(u64)) { - u64 value = get_unaligned_le64(p); - - CRC32(crc, value, d); - } - - if (len & sizeof(u32)) { - u32 value = get_unaligned_le32(p); - - CRC32(crc, value, w); - p += sizeof(u32); - } - } else { - for (; len >= sizeof(u32); len -= sizeof(u32)) { - u32 value = get_unaligned_le32(p); - - CRC32(crc, value, w); - p += sizeof(u32); - } - } - - if (len & sizeof(u16)) { - u16 value = get_unaligned_le16(p); - - CRC32(crc, value, h); - p += sizeof(u16); - } - - if (len & sizeof(u8)) { - u8 value = *p++; - - CRC32(crc, value, b); - } - - return crc; -} - -static u32 crc32c_mips_le_hw(u32 crc_, const u8 *p, unsigned int len) -{ - u32 crc = crc_; - - if (IS_ENABLED(CONFIG_64BIT)) { - for (; len >= sizeof(u64); p += sizeof(u64), len -= sizeof(u64)) { - u64 value = get_unaligned_le64(p); - - CRC32C(crc, value, d); - } - - if (len & sizeof(u32)) { - u32 value = get_unaligned_le32(p); - - CRC32C(crc, value, w); - p += sizeof(u32); - } - } else { - for (; len >= sizeof(u32); len -= sizeof(u32)) { - u32 value = get_unaligned_le32(p); - - CRC32C(crc, value, w); - p += sizeof(u32); - } - } - - if (len & sizeof(u16)) { - u16 value = get_unaligned_le16(p); - - CRC32C(crc, value, h); - p += sizeof(u16); - } - - if (len & sizeof(u8)) { - u8 value = *p++; - - CRC32C(crc, value, b); - } - return crc; -} - -#define CHKSUM_BLOCK_SIZE 1 -#define CHKSUM_DIGEST_SIZE 4 - -struct chksum_ctx { - u32 key; -}; - -struct chksum_desc_ctx { - u32 crc; -}; - -static int chksum_init(struct shash_desc *desc) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = mctx->key; - - return 0; -} - -/* - * Setting the seed allows arbitrary accumulators and flexible XOR policy - * If your algorithm starts with ~0, then XOR with ~0 before you set - * the seed. - */ -static int chksum_setkey(struct crypto_shash *tfm, const u8 *key, - unsigned int keylen) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(tfm); - - if (keylen != sizeof(mctx->key)) - return -EINVAL; - mctx->key = get_unaligned_le32(key); - return 0; -} - -static int chksum_update(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = crc32_mips_le_hw(ctx->crc, data, length); - return 0; -} - -static int chksumc_update(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = crc32c_mips_le_hw(ctx->crc, data, length); - return 0; -} - -static int chksum_final(struct shash_desc *desc, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - put_unaligned_le32(ctx->crc, out); - return 0; -} - -static int chksumc_final(struct shash_desc *desc, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - put_unaligned_le32(~ctx->crc, out); - return 0; -} - -static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out) -{ - put_unaligned_le32(crc32_mips_le_hw(crc, data, len), out); - return 0; -} - -static int __chksumc_finup(u32 crc, const u8 *data, unsigned int len, u8 *out) -{ - put_unaligned_le32(~crc32c_mips_le_hw(crc, data, len), out); - return 0; -} - -static int chksum_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - return __chksum_finup(ctx->crc, data, len, out); -} - -static int chksumc_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - return __chksumc_finup(ctx->crc, data, len, out); -} - -static int chksum_digest(struct shash_desc *desc, const u8 *data, - unsigned int length, u8 *out) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); - - return __chksum_finup(mctx->key, data, length, out); -} - -static int chksumc_digest(struct shash_desc *desc, const u8 *data, - unsigned int length, u8 *out) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); - - return __chksumc_finup(mctx->key, data, length, out); -} - -static int chksum_cra_init(struct crypto_tfm *tfm) -{ - struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); - - mctx->key = ~0; - return 0; -} - -static struct shash_alg crc32_alg = { - .digestsize = CHKSUM_DIGEST_SIZE, - .setkey = chksum_setkey, - .init = chksum_init, - .update = chksum_update, - .final = chksum_final, - .finup = chksum_finup, - .digest = chksum_digest, - .descsize = sizeof(struct chksum_desc_ctx), - .base = { - .cra_name = "crc32", - .cra_driver_name = "crc32-mips-hw", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct chksum_ctx), - .cra_module = THIS_MODULE, - .cra_init = chksum_cra_init, - } -}; - -static struct shash_alg crc32c_alg = { - .digestsize = CHKSUM_DIGEST_SIZE, - .setkey = chksum_setkey, - .init = chksum_init, - .update = chksumc_update, - .final = chksumc_final, - .finup = chksumc_finup, - .digest = chksumc_digest, - .descsize = sizeof(struct chksum_desc_ctx), - .base = { - .cra_name = "crc32c", - .cra_driver_name = "crc32c-mips-hw", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct chksum_ctx), - .cra_module = THIS_MODULE, - .cra_init = chksum_cra_init, - } -}; - -static int __init crc32_mod_init(void) -{ - int err; - - err = crypto_register_shash(&crc32_alg); - - if (err) - return err; - - err = crypto_register_shash(&crc32c_alg); - - if (err) { - crypto_unregister_shash(&crc32_alg); - return err; - } - - return 0; -} - -static void __exit crc32_mod_exit(void) -{ - crypto_unregister_shash(&crc32_alg); - crypto_unregister_shash(&crc32c_alg); -} - -MODULE_AUTHOR("Marcin Nowakowski static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, @@ -49,14 +48,9 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) extern void pgd_init(void *addr); extern pgd_t *pgd_alloc(struct mm_struct *mm); -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - pagetable_free(virt_to_ptdesc(pgd)); -} - #define __pte_free_tlb(tlb, pte, address) \ do { \ - pagetable_pte_dtor(page_ptdesc(pte)); \ + pagetable_dtor(page_ptdesc(pte)); \ tlb_remove_page_ptdesc((tlb), page_ptdesc(pte)); \ } while (0) diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index d118d4731580..22fa8f19924a 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -159,6 +159,8 @@ #define SCM_TS_OPT_ID 81 +#define SO_RCVPRIORITY 82 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/kernel/cevt-bcm1480.c b/arch/mips/kernel/cevt-bcm1480.c index d39a2963b451..2a14dc4ee57e 100644 --- a/arch/mips/kernel/cevt-bcm1480.c +++ b/arch/mips/kernel/cevt-bcm1480.c @@ -103,7 +103,7 @@ void sb1480_clockevent_init(void) BUG_ON(cpu > 3); /* Only have 4 general purpose timers */ - sprintf(name, "bcm1480-counter-%d", cpu); + sprintf(name, "bcm1480-counter-%u", cpu); cd->name = name; cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 8c401e42301c..f39e85fd58fa 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -248,7 +248,7 @@ int ftrace_disable_ftrace_graph_caller(void) #define S_R_SP (0xafb0 << 16) /* s{d,w} R, offset(sp) */ #define OFFSET_MASK 0xffff /* stack offset range: 0 ~ PT_SIZE */ -unsigned long ftrace_get_parent_ra_addr(unsigned long self_ra, unsigned long +static unsigned long ftrace_get_parent_ra_addr(unsigned long self_ra, unsigned long old_parent_ra, unsigned long parent_ra_addr, unsigned long fp) { unsigned long sp, ip, tmp; diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index e3ff6179c99f..d99ed58b7043 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -60,6 +60,7 @@ .endm __HEAD + #ifndef CONFIG_NO_EXCEPT_FILL /* * Reserved space for exception handlers. diff --git a/arch/mips/kernel/mips-mt.c b/arch/mips/kernel/mips-mt.c index 37676a44fefb..2ef610650a9e 100644 --- a/arch/mips/kernel/mips-mt.c +++ b/arch/mips/kernel/mips-mt.c @@ -122,9 +122,8 @@ void mips_mt_set_cpuoptions(void) unsigned long ectlval; unsigned long itcblkgrn; - /* ErrCtl register is known as "ecc" to Linux */ - ectlval = read_c0_ecc(); - write_c0_ecc(ectlval | (0x1 << 26)); + ectlval = read_c0_errctl(); + write_c0_errctl(ectlval | (0x1 << 26)); ehb(); #define INDEX_0 (0x80000000) #define INDEX_8 (0x80000008) @@ -145,7 +144,7 @@ void mips_mt_set_cpuoptions(void) ehb(); /* Write out to ITU with CACHE op */ cache_op(Index_Store_Tag_D, INDEX_0); - write_c0_ecc(ectlval); + write_c0_errctl(ectlval); ehb(); printk("Mapped %ld ITC cells starting at 0x%08x\n", ((itcblkgrn & 0x7fe00000) >> 20), itc_base); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 12a1a4ffb602..fbfe0771317e 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -704,10 +704,7 @@ static void __init resource_init(void) for_each_mem_range(i, &start, &end) { struct resource *res; - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = memblock_alloc_or_panic(sizeof(struct resource), SMP_CACHE_BYTES); res->start = start; /* diff --git a/arch/mips/kernel/spram.c b/arch/mips/kernel/spram.c index 71c7e5e27567..dd31e3fffd24 100644 --- a/arch/mips/kernel/spram.c +++ b/arch/mips/kernel/spram.c @@ -26,10 +26,6 @@ #define ERRCTL_SPRAM (1 << 28) -/* errctl access */ -#define read_c0_errctl(x) read_c0_ecc(x) -#define write_c0_errctl(x) write_c0_ecc(x) - /* * Different semantics to the set_c0_* function built by __BUILD_SET_C0 */ diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index dc29bd9656b0..39e248d0ed59 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -1705,10 +1706,10 @@ static inline __init void parity_protection_init(void) l2parity &= l1parity; /* Probe L1 ECC support */ - cp0_ectl = read_c0_ecc(); - write_c0_ecc(cp0_ectl | ERRCTL_PE); + cp0_ectl = read_c0_errctl(); + write_c0_errctl(cp0_ectl | ERRCTL_PE); back_to_back_c0_hazard(); - cp0_ectl = read_c0_ecc(); + cp0_ectl = read_c0_errctl(); /* Probe L2 ECC support */ gcr_ectl = read_gcr_err_control(); @@ -1727,9 +1728,9 @@ static inline __init void parity_protection_init(void) cp0_ectl |= ERRCTL_PE; else cp0_ectl &= ~ERRCTL_PE; - write_c0_ecc(cp0_ectl); + write_c0_errctl(cp0_ectl); back_to_back_c0_hazard(); - WARN_ON(!!(read_c0_ecc() & ERRCTL_PE) != l1parity); + WARN_ON(!!(read_c0_errctl() & ERRCTL_PE) != l1parity); /* Configure L2 ECC checking */ if (l2parity) @@ -1741,8 +1742,8 @@ static inline __init void parity_protection_init(void) gcr_ectl &= CM_GCR_ERR_CONTROL_L2_ECC_EN; WARN_ON(!!gcr_ectl != l2parity); - pr_info("Cache parity protection %sabled\n", - l1parity ? "en" : "dis"); + pr_info("Cache parity protection %s\n", + str_enabled_disabled(l1parity)); return; } @@ -1761,18 +1762,18 @@ static inline __init void parity_protection_init(void) unsigned long errctl; unsigned int l1parity_present, l2parity_present; - errctl = read_c0_ecc(); + errctl = read_c0_errctl(); errctl &= ~(ERRCTL_PE|ERRCTL_L2P); /* probe L1 parity support */ - write_c0_ecc(errctl | ERRCTL_PE); + write_c0_errctl(errctl | ERRCTL_PE); back_to_back_c0_hazard(); - l1parity_present = (read_c0_ecc() & ERRCTL_PE); + l1parity_present = (read_c0_errctl() & ERRCTL_PE); /* probe L2 parity support */ - write_c0_ecc(errctl|ERRCTL_L2P); + write_c0_errctl(errctl|ERRCTL_L2P); back_to_back_c0_hazard(); - l2parity_present = (read_c0_ecc() & ERRCTL_L2P); + l2parity_present = (read_c0_errctl() & ERRCTL_L2P); if (l1parity_present && l2parity_present) { if (l1parity) @@ -1791,20 +1792,20 @@ static inline __init void parity_protection_init(void) printk(KERN_INFO "Writing ErrCtl register=%08lx\n", errctl); - write_c0_ecc(errctl); + write_c0_errctl(errctl); back_to_back_c0_hazard(); - errctl = read_c0_ecc(); + errctl = read_c0_errctl(); printk(KERN_INFO "Readback ErrCtl register=%08lx\n", errctl); if (l1parity_present) - printk(KERN_INFO "Cache parity protection %sabled\n", - (errctl & ERRCTL_PE) ? "en" : "dis"); + pr_info("Cache parity protection %s\n", + str_enabled_disabled(errctl & ERRCTL_PE)); if (l2parity_present) { if (l1parity_present && l1parity) errctl ^= ERRCTL_L2P; - printk(KERN_INFO "L2 cache parity protection %sabled\n", - (errctl & ERRCTL_L2P) ? "en" : "dis"); + pr_info("L2 cache parity protection %s\n", + str_enabled_disabled(errctl & ERRCTL_L2P)); } } break; @@ -1812,11 +1813,11 @@ static inline __init void parity_protection_init(void) case CPU_5KC: case CPU_5KE: case CPU_LOONGSON32: - write_c0_ecc(0x80000000); + write_c0_errctl(0x80000000); back_to_back_c0_hazard(); /* Set the PE bit (bit 31) in the c0_errctl register. */ - printk(KERN_INFO "Cache parity protection %sabled\n", - (read_c0_ecc() & 0x80000000) ? "en" : "dis"); + pr_info("Cache parity protection %s\n", + str_enabled_disabled(read_c0_errctl() & 0x80000000)); break; case CPU_20KC: case CPU_25KF: @@ -1887,8 +1888,8 @@ asmlinkage void do_ftlb(void) if ((cpu_has_mips_r2_r6) && (((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS) || ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_LOONGSON))) { - pr_err("FTLB error exception, cp0_ecc=0x%08x:\n", - read_c0_ecc()); + pr_err("FTLB error exception, cp0_errctl=0x%08x:\n", + read_c0_errctl()); pr_err("cp0_errorepc == %0*lx\n", field, read_c0_errorepc()); reg_val = read_c0_cacheerr(); pr_err("c0_cacheerr == %08x\n", reg_val); diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 4c8e3c0aa210..75c9d3618f58 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -97,11 +98,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) return -EINTR; if (IS_ENABLED(CONFIG_MIPS_FP_SUPPORT)) { + unsigned long unused; + /* Map delay slot emulation page */ - base = mmap_region(NULL, STACK_TOP, PAGE_SIZE, - VM_READ | VM_EXEC | - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, - 0, NULL); + base = do_mmap(NULL, STACK_TOP, PAGE_SIZE, PROT_READ | PROT_EXEC, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, 0, 0, &unused, + NULL); if (IS_ERR_VALUE(base)) { ret = base; goto out; diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile index 5d5b993cbc2b..9c024e6d5e54 100644 --- a/arch/mips/lib/Makefile +++ b/arch/mips/lib/Makefile @@ -14,5 +14,7 @@ lib-$(CONFIG_GENERIC_CSUM) := $(filter-out csum_partial.o, $(lib-y)) obj-$(CONFIG_CPU_GENERIC_DUMP_TLB) += dump_tlb.o obj-$(CONFIG_CPU_R3000) += r3k_dump_tlb.o +obj-$(CONFIG_CRC32_ARCH) += crc32-mips.o + # libgcc-style stuff needed in the kernel obj-y += bswapsi.o bswapdi.o multi3.o diff --git a/arch/mips/lib/crc32-mips.c b/arch/mips/lib/crc32-mips.c new file mode 100644 index 000000000000..083e5d693a16 --- /dev/null +++ b/arch/mips/lib/crc32-mips.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * crc32-mips.c - CRC32 and CRC32C using optional MIPSr6 instructions + * + * Module based on arm64/crypto/crc32-arm.c + * + * Copyright (C) 2014 Linaro Ltd + * Copyright (C) 2018 MIPS Tech, LLC + */ + +#include +#include +#include +#include +#include +#include +#include + +enum crc_op_size { + b, h, w, d, +}; + +enum crc_type { + crc32, + crc32c, +}; + +#ifndef TOOLCHAIN_SUPPORTS_CRC +#define _ASM_SET_CRC(OP, SZ, TYPE) \ +_ASM_MACRO_3R(OP, rt, rs, rt2, \ + ".ifnc \\rt, \\rt2\n\t" \ + ".error \"invalid operands \\\"" #OP " \\rt,\\rs,\\rt2\\\"\"\n\t" \ + ".endif\n\t" \ + _ASM_INSN_IF_MIPS(0x7c00000f | (__rt << 16) | (__rs << 21) | \ + ((SZ) << 6) | ((TYPE) << 8)) \ + _ASM_INSN32_IF_MM(0x00000030 | (__rs << 16) | (__rt << 21) | \ + ((SZ) << 14) | ((TYPE) << 3))) +#define _ASM_UNSET_CRC(op, SZ, TYPE) ".purgem " #op "\n\t" +#else /* !TOOLCHAIN_SUPPORTS_CRC */ +#define _ASM_SET_CRC(op, SZ, TYPE) ".set\tcrc\n\t" +#define _ASM_UNSET_CRC(op, SZ, TYPE) +#endif + +#define __CRC32(crc, value, op, SZ, TYPE) \ +do { \ + __asm__ __volatile__( \ + ".set push\n\t" \ + _ASM_SET_CRC(op, SZ, TYPE) \ + #op " %0, %1, %0\n\t" \ + _ASM_UNSET_CRC(op, SZ, TYPE) \ + ".set pop" \ + : "+r" (crc) \ + : "r" (value)); \ +} while (0) + +#define _CRC32_crc32b(crc, value) __CRC32(crc, value, crc32b, 0, 0) +#define _CRC32_crc32h(crc, value) __CRC32(crc, value, crc32h, 1, 0) +#define _CRC32_crc32w(crc, value) __CRC32(crc, value, crc32w, 2, 0) +#define _CRC32_crc32d(crc, value) __CRC32(crc, value, crc32d, 3, 0) +#define _CRC32_crc32cb(crc, value) __CRC32(crc, value, crc32cb, 0, 1) +#define _CRC32_crc32ch(crc, value) __CRC32(crc, value, crc32ch, 1, 1) +#define _CRC32_crc32cw(crc, value) __CRC32(crc, value, crc32cw, 2, 1) +#define _CRC32_crc32cd(crc, value) __CRC32(crc, value, crc32cd, 3, 1) + +#define _CRC32(crc, value, size, op) \ + _CRC32_##op##size(crc, value) + +#define CRC32(crc, value, size) \ + _CRC32(crc, value, size, crc32) + +#define CRC32C(crc, value, size) \ + _CRC32(crc, value, size, crc32c) + +static DEFINE_STATIC_KEY_FALSE(have_crc32); + +u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) +{ + if (!static_branch_likely(&have_crc32)) + return crc32_le_base(crc, p, len); + + if (IS_ENABLED(CONFIG_64BIT)) { + for (; len >= sizeof(u64); p += sizeof(u64), len -= sizeof(u64)) { + u64 value = get_unaligned_le64(p); + + CRC32(crc, value, d); + } + + if (len & sizeof(u32)) { + u32 value = get_unaligned_le32(p); + + CRC32(crc, value, w); + p += sizeof(u32); + } + } else { + for (; len >= sizeof(u32); len -= sizeof(u32)) { + u32 value = get_unaligned_le32(p); + + CRC32(crc, value, w); + p += sizeof(u32); + } + } + + if (len & sizeof(u16)) { + u16 value = get_unaligned_le16(p); + + CRC32(crc, value, h); + p += sizeof(u16); + } + + if (len & sizeof(u8)) { + u8 value = *p++; + + CRC32(crc, value, b); + } + + return crc; +} +EXPORT_SYMBOL(crc32_le_arch); + +u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len) +{ + if (!static_branch_likely(&have_crc32)) + return crc32c_le_base(crc, p, len); + + if (IS_ENABLED(CONFIG_64BIT)) { + for (; len >= sizeof(u64); p += sizeof(u64), len -= sizeof(u64)) { + u64 value = get_unaligned_le64(p); + + CRC32C(crc, value, d); + } + + if (len & sizeof(u32)) { + u32 value = get_unaligned_le32(p); + + CRC32C(crc, value, w); + p += sizeof(u32); + } + } else { + for (; len >= sizeof(u32); len -= sizeof(u32)) { + u32 value = get_unaligned_le32(p); + + CRC32C(crc, value, w); + p += sizeof(u32); + } + } + + if (len & sizeof(u16)) { + u16 value = get_unaligned_le16(p); + + CRC32C(crc, value, h); + p += sizeof(u16); + } + + if (len & sizeof(u8)) { + u8 value = *p++; + + CRC32C(crc, value, b); + } + return crc; +} +EXPORT_SYMBOL(crc32c_le_arch); + +u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) +{ + return crc32_be_base(crc, p, len); +} +EXPORT_SYMBOL(crc32_be_arch); + +static int __init crc32_mips_init(void) +{ + if (cpu_have_feature(cpu_feature(MIPS_CRC32))) + static_branch_enable(&have_crc32); + return 0; +} +arch_initcall(crc32_mips_init); + +static void __exit crc32_mips_exit(void) +{ +} +module_exit(crc32_mips_exit); + +u32 crc32_optimizations(void) +{ + if (static_key_enabled(&have_crc32)) + return CRC32_LE_OPTIMIZATION | CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_AUTHOR("Marcin Nowakowski name, strsep(&tmp_bios_vendor, "-"), einter->description, - einter->size, especial->special_name); } static struct kobj_attribute boardinfo_attr = __ATTR(boardinfo, 0444, diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c index 09ff05269861..be8d2ad10750 100644 --- a/arch/mips/loongson64/env.c +++ b/arch/mips/loongson64/env.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -162,7 +163,7 @@ void __init prom_lefi_init_env(void) dma_default_coherent = !eirq_source->dma_noncoherent; } - pr_info("Firmware: Coherent DMA: %s\n", dma_default_coherent ? "on" : "off"); + pr_info("Firmware: Coherent DMA: %s\n", str_on_off(dma_default_coherent)); loongson_sysconf.restart_addr = boot_p->reset_system.ResetWarm; loongson_sysconf.poweroff_addr = boot_p->reset_system.Shutdown; diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 265bc57819df..c89e70df43d8 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -1660,7 +1660,7 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; } - case 0x3: + case 0x7: if (MIPSInst_FUNC(ir) != pfetch_op) return SIGILL; diff --git a/arch/mips/mm/pgtable.c b/arch/mips/mm/pgtable.c index 1506e458040d..10835414819f 100644 --- a/arch/mips/mm/pgtable.c +++ b/arch/mips/mm/pgtable.c @@ -10,12 +10,10 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *init, *ret = NULL; - struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, - PGD_TABLE_ORDER); + pgd_t *init, *ret; - if (ptdesc) { - ret = ptdesc_address(ptdesc); + ret = __pgd_alloc(mm, PGD_TABLE_ORDER); + if (ret) { init = pgd_offset(&init_mm, 0UL); pgd_init(ret); memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD, diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c index ec2567f8efd8..66898fd182dc 100644 --- a/arch/mips/pci/pci-legacy.c +++ b/arch/mips/pci/pci-legacy.c @@ -29,6 +29,14 @@ static LIST_HEAD(controllers); static int pci_initialized; +unsigned long pci_address_to_pio(phys_addr_t address) +{ + if (address > IO_SPACE_LIMIT) + return (unsigned long)-1; + + return (unsigned long) address; +} + /* * We need to avoid collisions with `mirrored' VGA ports * and other strange ISA hardware, so we always want the diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index ce6bb8e74271..12a536b7bfbd 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -30,7 +30,7 @@ extern pgd_t *pgd_alloc(struct mm_struct *mm); #define __pte_free_tlb(tlb, pte, addr) \ do { \ - pagetable_pte_dtor(page_ptdesc(pte)); \ + pagetable_dtor(page_ptdesc(pte)); \ tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) diff --git a/arch/nios2/kernel/cpuinfo.c b/arch/nios2/kernel/cpuinfo.c index 338849c430a5..7b1e8f9128e9 100644 --- a/arch/nios2/kernel/cpuinfo.c +++ b/arch/nios2/kernel/cpuinfo.c @@ -143,11 +143,11 @@ static int show_cpuinfo(struct seq_file *m, void *v) " DIV:\t\t%s\n" " BMX:\t\t%s\n" " CDX:\t\t%s\n", - cpuinfo.has_mul ? "yes" : "no", - cpuinfo.has_mulx ? "yes" : "no", - cpuinfo.has_div ? "yes" : "no", - cpuinfo.has_bmx ? "yes" : "no", - cpuinfo.has_cdx ? "yes" : "no"); + str_yes_no(cpuinfo.has_mul), + str_yes_no(cpuinfo.has_mulx), + str_yes_no(cpuinfo.has_div), + str_yes_no(cpuinfo.has_bmx), + str_yes_no(cpuinfo.has_cdx)); seq_printf(m, "Icache:\t\t%ukB, line length: %u\n", diff --git a/arch/nios2/mm/pgtable.c b/arch/nios2/mm/pgtable.c index 7c76e8a7447a..6470ed378782 100644 --- a/arch/nios2/mm/pgtable.c +++ b/arch/nios2/mm/pgtable.c @@ -11,6 +11,7 @@ #include #include +#include /* pteaddr: * ptbase | vpn* | zero @@ -54,7 +55,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *ret, *init; - ret = (pgd_t *) __get_free_page(GFP_KERNEL); + ret = __pgd_alloc(mm, 0); if (ret) { init = pgd_offset(&init_mm, 0UL); pgd_init(ret); diff --git a/arch/openrisc/Kbuild b/arch/openrisc/Kbuild index b0b0f2b03f87..70bdb24ff204 100644 --- a/arch/openrisc/Kbuild +++ b/arch/openrisc/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 obj-y += lib/ kernel/ mm/ -obj-y += boot/dts/ # for cleaning subdir- += boot diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index 3279ef457c57..b38fee299bc4 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -10,6 +10,7 @@ config OPENRISC select ARCH_HAS_DMA_SET_UNCACHED select ARCH_HAS_DMA_CLEAR_UNCACHED select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select GENERIC_BUILTIN_DTB select COMMON_CLK select OF select OF_EARLY_FLATTREE @@ -26,6 +27,8 @@ config OPENRISC select HAVE_PCI select HAVE_UID16 select HAVE_PAGE_SIZE_8KB + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RSEQ select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS_BROADCAST select GENERIC_SMP_IDLE_THREAD @@ -92,7 +95,7 @@ config DCACHE_WRITETHROUGH If unsure say N here -config OPENRISC_BUILTIN_DTB +config BUILTIN_DTB_NAME string "Builtin DTB" default "" diff --git a/arch/openrisc/boot/dts/Makefile b/arch/openrisc/boot/dts/Makefile index 13db5a2aab52..3a66e0ef3985 100644 --- a/arch/openrisc/boot/dts/Makefile +++ b/arch/openrisc/boot/dts/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y += $(addsuffix .dtb.o, $(CONFIG_OPENRISC_BUILTIN_DTB)) +dtb-y += $(addsuffix .dtb, $(CONFIG_BUILTIN_DTB_NAME)) #DTC_FLAGS ?= -p 1024 diff --git a/arch/openrisc/configs/or1klitex_defconfig b/arch/openrisc/configs/or1klitex_defconfig index 466f31a091be..3e849d25838a 100644 --- a/arch/openrisc/configs/or1klitex_defconfig +++ b/arch/openrisc/configs/or1klitex_defconfig @@ -7,7 +7,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_SGETMASK_SYSCALL=y CONFIG_EXPERT=y -CONFIG_OPENRISC_BUILTIN_DTB="or1klitex" +CONFIG_BUILTIN_DTB_NAME="or1klitex" CONFIG_HZ_100=y CONFIG_OPENRISC_HAVE_SHADOW_GPRS=y CONFIG_NET=y diff --git a/arch/openrisc/configs/or1ksim_defconfig b/arch/openrisc/configs/or1ksim_defconfig index 0116e465238f..59fe33cefba2 100644 --- a/arch/openrisc/configs/or1ksim_defconfig +++ b/arch/openrisc/configs/or1ksim_defconfig @@ -14,7 +14,7 @@ CONFIG_SLUB=y CONFIG_SLUB_TINY=y CONFIG_MODULES=y # CONFIG_BLOCK is not set -CONFIG_OPENRISC_BUILTIN_DTB="or1ksim" +CONFIG_BUILTIN_DTB_NAME="or1ksim" CONFIG_HZ_100=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/openrisc/configs/simple_smp_defconfig b/arch/openrisc/configs/simple_smp_defconfig index b990cb6c9309..6008e824d31c 100644 --- a/arch/openrisc/configs/simple_smp_defconfig +++ b/arch/openrisc/configs/simple_smp_defconfig @@ -20,7 +20,7 @@ CONFIG_SLUB=y CONFIG_SLUB_TINY=y CONFIG_MODULES=y # CONFIG_BLOCK is not set -CONFIG_OPENRISC_BUILTIN_DTB="simple_smp" +CONFIG_BUILTIN_DTB_NAME="simple_smp" CONFIG_SMP=y CONFIG_HZ_100=y CONFIG_OPENRISC_HAVE_SHADOW_GPRS=y diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h index c6a73772a546..3372f4e6ab4b 100644 --- a/arch/openrisc/include/asm/pgalloc.h +++ b/arch/openrisc/include/asm/pgalloc.h @@ -41,15 +41,13 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, */ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *ret = (pgd_t *)__get_free_page(GFP_KERNEL); + pgd_t *ret = __pgd_alloc(mm, 0); - if (ret) { - memset(ret, 0, USER_PTRS_PER_PGD * sizeof(pgd_t)); + if (ret) memcpy(ret + USER_PTRS_PER_PGD, swapper_pg_dir + USER_PTRS_PER_PGD, (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); - } return ret; } @@ -68,7 +66,7 @@ extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm); #define __pte_free_tlb(tlb, pte, addr) \ do { \ - pagetable_pte_dtor(page_ptdesc(pte)); \ + pagetable_dtor(page_ptdesc(pte)); \ tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) diff --git a/arch/openrisc/include/asm/ptrace.h b/arch/openrisc/include/asm/ptrace.h index 1da3e66292e2..e5a282b67075 100644 --- a/arch/openrisc/include/asm/ptrace.h +++ b/arch/openrisc/include/asm/ptrace.h @@ -17,6 +17,7 @@ #include #include +#include /* * Make kernel PTrace/register structures opaque to userspace... userspace can @@ -42,6 +43,36 @@ struct pt_regs { /* Named registers */ long sr; /* Stored in place of r0 */ long sp; /* r1 */ + long gpr2; + long gpr3; + long gpr4; + long gpr5; + long gpr6; + long gpr7; + long gpr8; + long gpr9; + long gpr10; + long gpr11; + long gpr12; + long gpr13; + long gpr14; + long gpr15; + long gpr16; + long gpr17; + long gpr18; + long gpr19; + long gpr20; + long gpr21; + long gpr22; + long gpr23; + long gpr24; + long gpr25; + long gpr26; + long gpr27; + long gpr28; + long gpr29; + long gpr30; + long gpr31; }; struct { /* Old style */ @@ -66,16 +97,56 @@ struct pt_regs { /* TODO: Rename this to REDZONE because that's what it is */ #define STACK_FRAME_OVERHEAD 128 /* size of minimum stack frame */ -#define instruction_pointer(regs) ((regs)->pc) +#define MAX_REG_OFFSET offsetof(struct pt_regs, orig_gpr11) + +/* Helpers for working with the instruction pointer */ +static inline unsigned long instruction_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs->pc; +} +static inline void instruction_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->pc = val; +} + #define user_mode(regs) (((regs)->sr & SPR_SR_SM) == 0) #define user_stack_pointer(regs) ((unsigned long)(regs)->sp) #define profile_pc(regs) instruction_pointer(regs) +/* Valid only for Kernel mode traps. */ +static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs->sp; +} + static inline long regs_return_value(struct pt_regs *regs) { return regs->gpr[11]; } +extern int regs_query_register_offset(const char *name); +extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, + unsigned int n); + +/** + * regs_get_register() - get register value from its offset + * @regs: pt_regs from which register value is gotten + * @offset: offset of the register. + * + * regs_get_register returns the value of a register whose offset from @regs. + * The @offset is the offset of the register in struct pt_regs. + * If @offset is bigger than MAX_REG_OFFSET, this returns 0. + */ +static inline unsigned long regs_get_register(struct pt_regs *regs, + unsigned int offset) +{ + if (unlikely(offset > MAX_REG_OFFSET)) + return 0; + + return *(unsigned long *)((unsigned long)regs + offset); +} + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index ce6f2b08a35e..c7e90b09645e 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -714,6 +714,10 @@ _syscall_check_trace_leave: * interrupts that set NEED_RESCHED or SIGNALPENDING... really true? */ _syscall_check_work: +#ifdef CONFIG_DEBUG_RSEQ + l.jal rseq_syscall + l.ori r3,r1,0 +#endif /* Here we need to disable interrupts */ DISABLE_INTERRUPTS(r27,r29) TRACE_IRQS_OFF diff --git a/arch/openrisc/kernel/ptrace.c b/arch/openrisc/kernel/ptrace.c index 5091b18eab4c..8430570d0620 100644 --- a/arch/openrisc/kernel/ptrace.c +++ b/arch/openrisc/kernel/ptrace.c @@ -160,6 +160,102 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) * in exit.c or in signal.c. */ +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { + REG_OFFSET_NAME(sr), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(gpr2), + REG_OFFSET_NAME(gpr3), + REG_OFFSET_NAME(gpr4), + REG_OFFSET_NAME(gpr5), + REG_OFFSET_NAME(gpr6), + REG_OFFSET_NAME(gpr7), + REG_OFFSET_NAME(gpr8), + REG_OFFSET_NAME(gpr9), + REG_OFFSET_NAME(gpr10), + REG_OFFSET_NAME(gpr11), + REG_OFFSET_NAME(gpr12), + REG_OFFSET_NAME(gpr13), + REG_OFFSET_NAME(gpr14), + REG_OFFSET_NAME(gpr15), + REG_OFFSET_NAME(gpr16), + REG_OFFSET_NAME(gpr17), + REG_OFFSET_NAME(gpr18), + REG_OFFSET_NAME(gpr19), + REG_OFFSET_NAME(gpr20), + REG_OFFSET_NAME(gpr21), + REG_OFFSET_NAME(gpr22), + REG_OFFSET_NAME(gpr23), + REG_OFFSET_NAME(gpr24), + REG_OFFSET_NAME(gpr25), + REG_OFFSET_NAME(gpr26), + REG_OFFSET_NAME(gpr27), + REG_OFFSET_NAME(gpr28), + REG_OFFSET_NAME(gpr29), + REG_OFFSET_NAME(gpr30), + REG_OFFSET_NAME(gpr31), + REG_OFFSET_NAME(pc), + REG_OFFSET_NAME(orig_gpr11), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) +{ + return (addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} /* * Called by kernel/ptrace.c when detaching.. diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c index c7ab42e2cb7a..f70a13ee0593 100644 --- a/arch/openrisc/kernel/signal.c +++ b/arch/openrisc/kernel/signal.c @@ -244,6 +244,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) { int ret; + rseq_signal_deliver(ksig, regs); + ret = setup_rt_frame(ksig, sigmask_to_save(), regs); signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP)); diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index f59ea4c10b0f..8e63e86251ca 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -38,10 +38,7 @@ pte_t __ref *pte_alloc_one_kernel(struct mm_struct *mm) if (likely(mem_init_done)) { pte = (pte_t *)get_zeroed_page(GFP_KERNEL); } else { - pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pte) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); } return pte; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index aa6a3cad275d..fcc5973f7519 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -60,8 +60,8 @@ config PARISC select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HASH - select HAVE_ARCH_JUMP_LABEL - select HAVE_ARCH_JUMP_LABEL_RELATIVE + # select HAVE_ARCH_JUMP_LABEL + # select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KFENCE select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h index a63190af2f05..3143cf29ce27 100644 --- a/arch/parisc/include/asm/io.h +++ b/arch/parisc/include/asm/io.h @@ -135,12 +135,8 @@ static inline void gsc_writeq(unsigned long long val, unsigned long addr) #define pci_iounmap pci_iounmap -void memset_io(volatile void __iomem *addr, unsigned char val, int count); void memcpy_fromio(void *dst, const volatile void __iomem *src, int count); -void memcpy_toio(volatile void __iomem *dst, const void *src, int count); -#define memset_io memset_io #define memcpy_fromio memcpy_fromio -#define memcpy_toio memcpy_toio /* Port-space IO */ diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index e3e142b1c5c5..2ca74a56415c 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -11,27 +11,12 @@ #include #define __HAVE_ARCH_PMD_ALLOC_ONE -#define __HAVE_ARCH_PMD_FREE -#define __HAVE_ARCH_PGD_FREE #include /* Allocate the top level pgd (page directory) */ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *pgd; - - pgd = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_TABLE_ORDER); - if (unlikely(pgd == NULL)) - return NULL; - - memset(pgd, 0, PAGE_SIZE << PGD_TABLE_ORDER); - - return pgd; -} - -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_pages((unsigned long)pgd, PGD_TABLE_ORDER); + return __pgd_alloc(mm, PGD_TABLE_ORDER); } #if CONFIG_PGTABLE_LEVELS == 3 @@ -46,17 +31,19 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - pmd_t *pmd; + struct ptdesc *ptdesc; + gfp_t gfp = GFP_PGTABLE_USER; - pmd = (pmd_t *)__get_free_pages(GFP_PGTABLE_KERNEL, PMD_TABLE_ORDER); - if (likely(pmd)) - memset ((void *)pmd, 0, PAGE_SIZE << PMD_TABLE_ORDER); - return pmd; -} - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - free_pages((unsigned long)pmd, PMD_TABLE_ORDER); + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + ptdesc = pagetable_alloc(gfp, PMD_TABLE_ORDER); + if (!ptdesc) + return NULL; + if (!pagetable_pmd_ctor(ptdesc)) { + pagetable_free(ptdesc); + return NULL; + } + return ptdesc_address(ptdesc); } #endif diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index d268d69bfcd2..aa9cd4b951fe 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -140,6 +140,8 @@ #define SCM_TS_OPT_ID 0x404C +#define SO_RCVPRIORITY 0x404D + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index c1587aa35beb..1c366b0d3134 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -43,9 +43,7 @@ EXPORT_SYMBOL($global$); #endif #include -EXPORT_SYMBOL(memcpy_toio); EXPORT_SYMBOL(memcpy_fromio); -EXPORT_SYMBOL(memset_io); extern void $$divI(void); extern void $$divU(void); diff --git a/arch/parisc/kernel/vdso32/Makefile b/arch/parisc/kernel/vdso32/Makefile index 2b36d25ada6e..288f8b85978f 100644 --- a/arch/parisc/kernel/vdso32/Makefile +++ b/arch/parisc/kernel/vdso32/Makefile @@ -33,7 +33,7 @@ KBUILD_CFLAGS += -DBUILD_VDSO -DDISABLE_BRANCH_PROFILING VDSO_LIBGCC := $(shell $(CROSS32CC) -print-libgcc-file-name) obj-y += vdso32_wrapper.o -extra-y += vdso32.lds +targets += vdso32.lds CPPFLAGS_vdso32.lds += -P -C # -U$(ARCH) $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so FORCE diff --git a/arch/parisc/kernel/vdso64/Makefile b/arch/parisc/kernel/vdso64/Makefile index bd87bd6a6659..bc5d9553f311 100644 --- a/arch/parisc/kernel/vdso64/Makefile +++ b/arch/parisc/kernel/vdso64/Makefile @@ -32,7 +32,7 @@ KBUILD_CFLAGS += -DBUILD_VDSO -DDISABLE_BRANCH_PROFILING VDSO_LIBGCC := $(shell $(CC) -print-libgcc-file-name) obj-y += vdso64_wrapper.o -extra-y += vdso64.lds +targets += vdso64.lds CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so FORCE diff --git a/arch/parisc/lib/io.c b/arch/parisc/lib/io.c index 7c00496b47d4..7461366a65c9 100644 --- a/arch/parisc/lib/io.c +++ b/arch/parisc/lib/io.c @@ -12,32 +12,6 @@ #include #include -/* Copies a block of memory to a device in an efficient manner. - * Assumes the device can cope with 32-bit transfers. If it can't, - * don't use this function. - */ -void memcpy_toio(volatile void __iomem *dst, const void *src, int count) -{ - if (((unsigned long)dst & 3) != ((unsigned long)src & 3)) - goto bytecopy; - while ((unsigned long)dst & 3) { - writeb(*(char *)src, dst++); - src++; - count--; - } - while (count > 3) { - __raw_writel(*(u32 *)src, dst); - src += 4; - dst += 4; - count -= 4; - } - bytecopy: - while (count--) { - writeb(*(char *)src, dst++); - src++; - } -} - /* ** Copies a block of memory from a device in an efficient manner. ** Assumes the device can cope with 32-bit transfers. If it can't, @@ -99,27 +73,6 @@ void memcpy_fromio(void *dst, const volatile void __iomem *src, int count) } } -/* Sets a block of memory on a device to a given value. - * Assumes the device can cope with 32-bit transfers. If it can't, - * don't use this function. - */ -void memset_io(volatile void __iomem *addr, unsigned char val, int count) -{ - u32 val32 = (val << 24) | (val << 16) | (val << 8) | val; - while ((unsigned long)addr & 3) { - writeb(val, addr++); - count--; - } - while (count > 3) { - __raw_writel(val32, addr); - addr += 4; - count -= 4; - } - while (count--) { - writeb(val, addr++); - } -} - /* * Read COUNT 8-bit bytes from port PORT into memory starting at * SRC. diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 96970fa75e4a..61c0a2477072 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -377,10 +377,8 @@ static void __ref map_pages(unsigned long start_vaddr, #if CONFIG_PGTABLE_LEVELS == 3 if (pud_none(*pud)) { - pmd = memblock_alloc(PAGE_SIZE << PMD_TABLE_ORDER, + pmd = memblock_alloc_or_panic(PAGE_SIZE << PMD_TABLE_ORDER, PAGE_SIZE << PMD_TABLE_ORDER); - if (!pmd) - panic("pmd allocation failed.\n"); pud_populate(NULL, pud, pmd); } #endif @@ -388,9 +386,7 @@ static void __ref map_pages(unsigned long start_vaddr, pmd = pmd_offset(pud, vaddr); for (tmp1 = start_pmd; tmp1 < PTRS_PER_PMD; tmp1++, pmd++) { if (pmd_none(*pmd)) { - pg_table = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pg_table) - panic("page table allocation failed\n"); + pg_table = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); pmd_populate_kernel(NULL, pmd, pg_table); } @@ -648,9 +644,7 @@ static void __init pagetable_init(void) } #endif - empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!empty_zero_page) - panic("zero page allocation failed.\n"); + empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); } @@ -687,19 +681,15 @@ static void __init fixmap_init(void) #if CONFIG_PGTABLE_LEVELS == 3 if (pud_none(*pud)) { - pmd = memblock_alloc(PAGE_SIZE << PMD_TABLE_ORDER, + pmd = memblock_alloc_or_panic(PAGE_SIZE << PMD_TABLE_ORDER, PAGE_SIZE << PMD_TABLE_ORDER); - if (!pmd) - panic("fixmap: pmd allocation failed.\n"); pud_populate(NULL, pud, pmd); } #endif pmd = pmd_offset(pud, addr); do { - pte_t *pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pte) - panic("fixmap: pte allocation failed.\n"); + pte_t *pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); pmd_populate_kernel(&init_mm, pmd, pte); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a0ce777f9706..424f188e62d9 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -127,6 +127,8 @@ config PPC select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_HAS_COPY_MC if PPC64 + select ARCH_HAS_CRC32 if PPC64 && ALTIVEC + select ARCH_HAS_CRC_T10DIF if PPC64 && ALTIVEC select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE @@ -145,6 +147,7 @@ config PPC select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API + select ARCH_HAS_PREEMPT_LAZY select ARCH_HAS_PTE_DEVMAP if PPC_BOOK3S_64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64 @@ -240,6 +243,7 @@ config PPC select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_GUP_FAST + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_DESCRIPTORS if PPC64_ELF_ABI_V1 diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index 53f43a34e1a9..b33f0034990c 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -168,7 +168,6 @@ CONFIG_INFINIBAND_MTHCA=m CONFIG_INFINIBAND_IPOIB=m CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y CONFIG_EDAC=y -CONFIG_EDAC_CELL=y CONFIG_UIO=m CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 57ded82c2840..e8b3f67bf3f5 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -208,6 +208,7 @@ CONFIG_FB_ATY=y CONFIG_FB_ATY_CT=y CONFIG_FB_ATY_GX=y CONFIG_FB_3DFX=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index ee84ade7a033..6b6d7467fecf 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -320,8 +320,6 @@ CONFIG_XMON=y CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y -CONFIG_CRYPTO_CRC32C_VPMSUM=m -CONFIG_CRYPTO_CRCT10DIF_VPMSUM=m CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA1_PPC=m diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index f39c0d000c43..465eb96c755e 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -389,9 +389,6 @@ CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_LZO=m -CONFIG_CRYPTO_CRC32C_VPMSUM=m -CONFIG_CRYPTO_CRCT10DIF_VPMSUM=m -CONFIG_CRYPTO_VPMSUM_TESTER=m CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_AES_GCM_P10=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 4d77e17541e9..ca0c90e95837 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -716,6 +716,7 @@ CONFIG_FB_TRIDENT=m CONFIG_FB_SM501=m CONFIG_FB_IBM_GXT4500=y CONFIG_LCD_PLATFORM=m +CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig index 951a43726461..5b315e9756b3 100644 --- a/arch/powerpc/crypto/Kconfig +++ b/arch/powerpc/crypto/Kconfig @@ -13,39 +13,6 @@ config CRYPTO_CURVE25519_PPC64 Architecture: PowerPC64 - Little-endian -config CRYPTO_CRC32C_VPMSUM - tristate "CRC32c" - depends on PPC64 && ALTIVEC - select CRYPTO_HASH - select CRC32 - help - CRC32c CRC algorithm with the iSCSI polynomial (RFC 3385 and RFC 3720) - - Architecture: powerpc64 using - - AltiVec extensions - - Enable on POWER8 and newer processors for improved performance. - -config CRYPTO_CRCT10DIF_VPMSUM - tristate "CRC32T10DIF" - depends on PPC64 && ALTIVEC && CRC_T10DIF - select CRYPTO_HASH - help - CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF) - - Architecture: powerpc64 using - - AltiVec extensions - - Enable on POWER8 and newer processors for improved performance. - -config CRYPTO_VPMSUM_TESTER - tristate "CRC32c and CRC32T10DIF hardware acceleration tester" - depends on CRYPTO_CRCT10DIF_VPMSUM && CRYPTO_CRC32C_VPMSUM - help - Stress test for CRC32c and CRCT10DIF algorithms implemented with - powerpc64 AltiVec extensions (POWER8 vpmsum instructions). - Unless you are testing these algorithms, you don't need this. - config CRYPTO_MD5_PPC tristate "Digests: MD5" depends on PPC diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile index 59808592f0a1..9b38f4a7bc15 100644 --- a/arch/powerpc/crypto/Makefile +++ b/arch/powerpc/crypto/Makefile @@ -10,9 +10,6 @@ obj-$(CONFIG_CRYPTO_MD5_PPC) += md5-ppc.o obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o -obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o -obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o -obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o obj-$(CONFIG_CRYPTO_AES_GCM_P10) += aes-gcm-p10-crypto.o obj-$(CONFIG_CRYPTO_CHACHA20_P10) += chacha-p10-crypto.o obj-$(CONFIG_CRYPTO_POLY1305_P10) += poly1305-p10-crypto.o @@ -24,8 +21,6 @@ md5-ppc-y := md5-asm.o md5-glue.o sha1-powerpc-y := sha1-powerpc-asm.o sha1.o sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o -crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o -crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp10-ppc.o aesp10-ppc.o chacha-p10-crypto-y := chacha-p10-glue.o chacha-p10le-8x.o poly1305-p10-crypto-y := poly1305-p10-glue.o poly1305-p10le_64.o diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c index f37b3d13fc53..679f52794baf 100644 --- a/arch/powerpc/crypto/aes-gcm-p10-glue.c +++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c @@ -214,7 +214,6 @@ static int p10_aes_gcm_crypt(struct aead_request *req, u8 *riv, struct gcm_ctx *gctx = PTR_ALIGN((void *)databuf, PPC_ALIGN); u8 hashbuf[sizeof(struct Hash_ctx) + PPC_ALIGN]; struct Hash_ctx *hash = PTR_ALIGN((void *)hashbuf, PPC_ALIGN); - struct scatter_walk assoc_sg_walk; struct skcipher_walk walk; u8 *assocmem = NULL; u8 *assoc; @@ -234,8 +233,7 @@ static int p10_aes_gcm_crypt(struct aead_request *req, u8 *riv, /* Linearize assoc, if not already linear */ if (req->src->length >= assoclen && req->src->length) { - scatterwalk_start(&assoc_sg_walk, req->src); - assoc = scatterwalk_map(&assoc_sg_walk); + assoc = sg_virt(req->src); /* ppc64 is !HIGHMEM */ } else { gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? GFP_KERNEL : GFP_ATOMIC; @@ -253,10 +251,7 @@ static int p10_aes_gcm_crypt(struct aead_request *req, u8 *riv, gcmp10_init(gctx, iv, (unsigned char *) &ctx->enc_key, hash, assoc, assoclen); vsx_end(); - if (!assocmem) - scatterwalk_unmap(assoc); - else - kfree(assocmem); + kfree(assocmem); if (enc) ret = skcipher_walk_aead_encrypt(&walk, req, false); diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c deleted file mode 100644 index c61a874a3a5c..000000000000 --- a/arch/powerpc/crypto/crc-vpmsum_test.c +++ /dev/null @@ -1,133 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * CRC vpmsum tester - * Copyright 2017 Daniel Axtens, IBM Corporation. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static unsigned long iterations = 10000; - -#define MAX_CRC_LENGTH 65535 - - -static int __init crc_test_init(void) -{ - u16 crc16 = 0, verify16 = 0; - __le32 verify32le = 0; - unsigned char *data; - u32 verify32 = 0; - unsigned long i; - __le32 crc32; - int ret; - - struct crypto_shash *crct10dif_tfm; - struct crypto_shash *crc32c_tfm; - - if (!cpu_has_feature(CPU_FTR_ARCH_207S)) - return -ENODEV; - - data = kmalloc(MAX_CRC_LENGTH, GFP_KERNEL); - if (!data) - return -ENOMEM; - - crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0); - - if (IS_ERR(crct10dif_tfm)) { - pr_err("Error allocating crc-t10dif\n"); - goto free_buf; - } - - crc32c_tfm = crypto_alloc_shash("crc32c", 0, 0); - - if (IS_ERR(crc32c_tfm)) { - pr_err("Error allocating crc32c\n"); - goto free_16; - } - - do { - SHASH_DESC_ON_STACK(crct10dif_shash, crct10dif_tfm); - SHASH_DESC_ON_STACK(crc32c_shash, crc32c_tfm); - - crct10dif_shash->tfm = crct10dif_tfm; - ret = crypto_shash_init(crct10dif_shash); - - if (ret) { - pr_err("Error initing crc-t10dif\n"); - goto free_32; - } - - - crc32c_shash->tfm = crc32c_tfm; - ret = crypto_shash_init(crc32c_shash); - - if (ret) { - pr_err("Error initing crc32c\n"); - goto free_32; - } - - pr_info("crc-vpmsum_test begins, %lu iterations\n", iterations); - for (i=0; i"); -MODULE_DESCRIPTION("Vector polynomial multiply-sum CRC tester"); -MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c deleted file mode 100644 index 63760b7dbb76..000000000000 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ /dev/null @@ -1,173 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define CHKSUM_BLOCK_SIZE 1 -#define CHKSUM_DIGEST_SIZE 4 - -#define VMX_ALIGN 16 -#define VMX_ALIGN_MASK (VMX_ALIGN-1) - -#define VECTOR_BREAKPOINT 512 - -u32 __crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len); - -static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len) -{ - unsigned int prealign; - unsigned int tail; - - if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable()) - return __crc32c_le(crc, p, len); - - if ((unsigned long)p & VMX_ALIGN_MASK) { - prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK); - crc = __crc32c_le(crc, p, prealign); - len -= prealign; - p += prealign; - } - - if (len & ~VMX_ALIGN_MASK) { - preempt_disable(); - pagefault_disable(); - enable_kernel_altivec(); - crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK); - disable_kernel_altivec(); - pagefault_enable(); - preempt_enable(); - } - - tail = len & VMX_ALIGN_MASK; - if (tail) { - p += len & ~VMX_ALIGN_MASK; - crc = __crc32c_le(crc, p, tail); - } - - return crc; -} - -static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm) -{ - u32 *key = crypto_tfm_ctx(tfm); - - *key = ~0; - - return 0; -} - -/* - * Setting the seed allows arbitrary accumulators and flexible XOR policy - * If your algorithm starts with ~0, then XOR with ~0 before you set - * the seed. - */ -static int crc32c_vpmsum_setkey(struct crypto_shash *hash, const u8 *key, - unsigned int keylen) -{ - u32 *mctx = crypto_shash_ctx(hash); - - if (keylen != sizeof(u32)) - return -EINVAL; - *mctx = le32_to_cpup((__le32 *)key); - return 0; -} - -static int crc32c_vpmsum_init(struct shash_desc *desc) -{ - u32 *mctx = crypto_shash_ctx(desc->tfm); - u32 *crcp = shash_desc_ctx(desc); - - *crcp = *mctx; - - return 0; -} - -static int crc32c_vpmsum_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - u32 *crcp = shash_desc_ctx(desc); - - *crcp = crc32c_vpmsum(*crcp, data, len); - - return 0; -} - -static int __crc32c_vpmsum_finup(u32 *crcp, const u8 *data, unsigned int len, - u8 *out) -{ - *(__le32 *)out = ~cpu_to_le32(crc32c_vpmsum(*crcp, data, len)); - - return 0; -} - -static int crc32c_vpmsum_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32c_vpmsum_finup(shash_desc_ctx(desc), data, len, out); -} - -static int crc32c_vpmsum_final(struct shash_desc *desc, u8 *out) -{ - u32 *crcp = shash_desc_ctx(desc); - - *(__le32 *)out = ~cpu_to_le32p(crcp); - - return 0; -} - -static int crc32c_vpmsum_digest(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32c_vpmsum_finup(crypto_shash_ctx(desc->tfm), data, len, - out); -} - -static struct shash_alg alg = { - .setkey = crc32c_vpmsum_setkey, - .init = crc32c_vpmsum_init, - .update = crc32c_vpmsum_update, - .final = crc32c_vpmsum_final, - .finup = crc32c_vpmsum_finup, - .digest = crc32c_vpmsum_digest, - .descsize = sizeof(u32), - .digestsize = CHKSUM_DIGEST_SIZE, - .base = { - .cra_name = "crc32c", - .cra_driver_name = "crc32c-vpmsum", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(u32), - .cra_module = THIS_MODULE, - .cra_init = crc32c_vpmsum_cra_init, - } -}; - -static int __init crc32c_vpmsum_mod_init(void) -{ - if (!cpu_has_feature(CPU_FTR_ARCH_207S)) - return -ENODEV; - - return crypto_register_shash(&alg); -} - -static void __exit crc32c_vpmsum_mod_fini(void) -{ - crypto_unregister_shash(&alg); -} - -module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init); -module_exit(crc32c_vpmsum_mod_fini); - -MODULE_AUTHOR("Anton Blanchard "); -MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_CRYPTO("crc32c"); -MODULE_ALIAS_CRYPTO("crc32c-vpmsum"); diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index db481b336bca..82da7c7a1d12 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -43,6 +43,13 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return arch_ftrace_regs(fregs)->regs.msr ? &arch_ftrace_regs(fregs)->regs : NULL; } +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->result = 0; \ + (_regs)->nip = arch_ftrace_regs(fregs)->regs.nip; \ + (_regs)->gpr[1] = arch_ftrace_regs(fregs)->regs.gpr[1]; \ + asm volatile("mfmsr %0" : "=r" ((_regs)->msr)); \ + } while (0) + static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) @@ -50,6 +57,12 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, regs_set_return_ip(&arch_ftrace_regs(fregs)->regs, ip); } +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->regs.link; +} + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 18a3028ac3b6..dad2e7980f24 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -15,6 +15,15 @@ extern bool hugetlb_disabled; +static inline bool hugepages_supported(void) +{ + if (hugetlb_disabled) + return false; + + return HPAGE_SHIFT != 0; +} +#define hugepages_supported hugepages_supported + void __init hugetlbpage_init_defaultsize(void); int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 270ee93a0f7d..601e569303e1 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -61,7 +61,6 @@ struct pt_regs; extern void kexec_smp_wait(void); /* get and clear naca physid, wait for master to copy new code to 0 */ extern void default_machine_kexec(struct kimage *image); -extern void machine_kexec_mask_interrupts(void); void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_code_buffer, unsigned long start_address) __noreturn; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 6ebca2996f18..2785c7462ebf 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -103,6 +103,7 @@ void arch_setup_new_exec(void); #define TIF_PATCH_PENDING 6 /* pending live patching update */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SINGLESTEP 8 /* singlestepping active */ +#define TIF_NEED_RESCHED_LAZY 9 /* Scheduler driven lazy preemption */ #define TIF_SECCOMP 10 /* secure computing */ #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ #define TIF_NOERROR 12 /* Force successful syscall return */ @@ -122,6 +123,7 @@ void arch_setup_new_exec(void); #define _TIF_SYSCALL_TRACE (1< diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 1bee15c013e7..3af6c06af02f 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -1087,12 +1087,10 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char /* Count and allocate space for cpu features */ of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes, &nr_dt_cpu_features); - dt_cpu_features = memblock_alloc(sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, PAGE_SIZE); - if (!dt_cpu_features) - panic("%s: Failed to allocate %zu bytes align=0x%lx\n", - __func__, - sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, - PAGE_SIZE); + dt_cpu_features = + memblock_alloc_or_panic( + sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, + PAGE_SIZE); cpufeatures_setup_start(isa); diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 30b56c67fa61..e527cd3ef128 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -97,7 +97,7 @@ void power4_idle(void) /* * Register the sysctl to set/clear powersave_nap. */ -static struct ctl_table powersave_nap_ctl_table[] = { +static const struct ctl_table powersave_nap_ctl_table[] = { { .procname = "powersave-nap", .data = &powersave_nap, diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index af62ec974b97..8f4acc55407b 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -185,7 +185,7 @@ again: ti_flags = read_thread_flags(); while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) { local_irq_enable(); - if (ti_flags & _TIF_NEED_RESCHED) { + if (ti_flags & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) { schedule(); } else { /* @@ -396,7 +396,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) /* Returning to a kernel context with local irqs enabled. */ WARN_ON_ONCE(!(regs->msr & MSR_EE)); again: - if (IS_ENABLED(CONFIG_PREEMPT)) { + if (IS_ENABLED(CONFIG_PREEMPTION)) { /* Return to preemptible kernel context */ if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) { if (preempt_count() == 0) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 76381e14e800..0ebae6e4c19d 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -687,7 +687,7 @@ void iommu_table_clear(struct iommu_table *tbl) void iommu_table_reserve_pages(struct iommu_table *tbl, unsigned long res_start, unsigned long res_end) { - int i; + unsigned long i; WARN_ON_ONCE(res_end < res_start); /* diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 033cd00aa0fc..acb727f54e9d 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -27,32 +27,6 @@ .text -/* - * This returns the high 64 bits of the product of two 64-bit numbers. - */ -_GLOBAL(mulhdu) - cmpwi r6,0 - cmpwi cr1,r3,0 - mr r10,r4 - mulhwu r4,r4,r5 - beq 1f - mulhwu r0,r10,r6 - mullw r7,r10,r5 - addc r7,r0,r7 - addze r4,r4 -1: beqlr cr1 /* all done if high part of A is 0 */ - mullw r9,r3,r5 - mulhwu r10,r3,r5 - beq 2f - mullw r0,r3,r6 - mulhwu r8,r3,r6 - addc r7,r0,r7 - adde r4,r4,r8 - addze r10,r10 -2: addc r4,r4,r9 - addze r3,r10 - blr - /* * reloc_got2 runs through the .got2 section adding an offset * to each entry. diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 45dac7b46aa3..34a5aec4908f 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -369,6 +369,24 @@ static void dedotify_versions(struct modversion_info *vers, } } +/* Same as normal versions, remove a leading dot if present. */ +static void dedotify_ext_version_names(char *str_seq, unsigned long size) +{ + unsigned long out = 0; + unsigned long in; + char last = '\0'; + + for (in = 0; in < size; in++) { + /* Skip one leading dot */ + if (last == '\0' && str_seq[in] == '.') + in++; + last = str_seq[in]; + str_seq[out++] = last; + } + /* Zero the trailing portion of the names table for robustness */ + memset(&str_seq[out], 0, size - out); +} + /* * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC. * seem to be defined (value set later). @@ -438,10 +456,12 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, me->arch.toc_section = i; if (sechdrs[i].sh_addralign < 8) sechdrs[i].sh_addralign = 8; - } - else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0) + } else if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0) dedotify_versions((void *)hdr + sechdrs[i].sh_offset, sechdrs[i].sh_size); + else if (strcmp(secstrings + sechdrs[i].sh_name, "__version_ext_names") == 0) + dedotify_ext_version_names((void *)hdr + sechdrs[i].sh_offset, + sechdrs[i].sh_size); if (sechdrs[i].sh_type == SHT_SYMTAB) dedotify((void *)hdr + sechdrs[i].sh_offset, diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index ce0c8623e563..f8a3bd8cfae4 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -213,11 +213,8 @@ pci_create_OF_bus_map(void) struct property* of_prop; struct device_node *dn; - of_prop = memblock_alloc(sizeof(struct property) + 256, + of_prop = memblock_alloc_or_panic(sizeof(struct property) + 256, SMP_CACHE_BYTES); - if (!of_prop) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct property) + 256); dn = of_find_node_by_path("/"); if (dn) { memset(of_prop, -1, sizeof(struct property) + 256); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7b739b9a91ab..ef91f71e07c4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1960,8 +1960,8 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) * address of _start and the second entry is the TOC * value we need to use. */ - __get_user(entry, (unsigned long __user *)start); - __get_user(toc, (unsigned long __user *)start+1); + get_user(entry, (unsigned long __user *)start); + get_user(toc, (unsigned long __user *)start+1); /* Check whether the e_entry function descriptor entries * need to be relocated before we can use them. diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 8e776ba39497..57082fac4668 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2792,7 +2792,6 @@ static void __init flatten_device_tree(void) dt_struct_start, dt_struct_end); } -#ifdef CONFIG_PPC_CHRP /* * Pegasos and BriQ lacks the "ranges" property in the isa node * Pegasos needs decimal IRQ 14/15, not hexadecimal @@ -2843,11 +2842,7 @@ static void __init fixup_device_tree_chrp(void) } } } -#else -#define fixup_device_tree_chrp() -#endif -#if defined(CONFIG_PPC64) && defined(CONFIG_PPC_PMAC) static void __init fixup_device_tree_pmac64(void) { phandle u3, i2c, mpic; @@ -2887,11 +2882,7 @@ static void __init fixup_device_tree_pmac64(void) prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupt-parent", &parent, sizeof(parent)); } -#else -#define fixup_device_tree_pmac64() -#endif -#ifdef CONFIG_PPC_PMAC static void __init fixup_device_tree_pmac(void) { __be32 val = 1; @@ -2911,11 +2902,7 @@ static void __init fixup_device_tree_pmac(void) prom_setprop(node, NULL, "#size-cells", &val, sizeof(val)); } } -#else -static inline void fixup_device_tree_pmac(void) { } -#endif -#ifdef CONFIG_PPC_EFIKA /* * The MPC5200 FEC driver requires an phy-handle property to tell it how * to talk to the phy. If the phy-handle property is missing, then this @@ -3047,11 +3034,7 @@ static void __init fixup_device_tree_efika(void) /* Make sure ethernet phy-handle property exists */ fixup_device_tree_efika_add_phy(); } -#else -#define fixup_device_tree_efika() -#endif -#ifdef CONFIG_PPC_PASEMI_NEMO /* * CFE supplied on Nemo is broken in several ways, biggest * problem is that it reassigns ISA interrupts to unused mpic ints. @@ -3127,17 +3110,23 @@ static void __init fixup_device_tree_pasemi(void) prom_setprop(iob, name, "device_type", "isa", sizeof("isa")); } -#else /* !CONFIG_PPC_PASEMI_NEMO */ -static inline void fixup_device_tree_pasemi(void) { } -#endif static void __init fixup_device_tree(void) { - fixup_device_tree_chrp(); - fixup_device_tree_pmac(); - fixup_device_tree_pmac64(); - fixup_device_tree_efika(); - fixup_device_tree_pasemi(); + if (IS_ENABLED(CONFIG_PPC_CHRP)) + fixup_device_tree_chrp(); + + if (IS_ENABLED(CONFIG_PPC_PMAC)) + fixup_device_tree_pmac(); + + if (IS_ENABLED(CONFIG_PPC_PMAC) && IS_ENABLED(CONFIG_PPC64)) + fixup_device_tree_pmac64(); + + if (IS_ENABLED(CONFIG_PPC_EFIKA)) + fixup_device_tree_efika(); + + if (IS_ENABLED(CONFIG_PPC_PASEMI_NEMO)) + fixup_device_tree_pasemi(); } static void __init prom_find_boot_cpu(void) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 6fa179448c33..a08b0ede4e64 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -458,11 +458,8 @@ void __init smp_setup_cpu_maps(void) DBG("smp_setup_cpu_maps()\n"); - cpu_to_phys_id = memblock_alloc(nr_cpu_ids * sizeof(u32), + cpu_to_phys_id = memblock_alloc_or_panic(nr_cpu_ids * sizeof(u32), __alignof__(u32)); - if (!cpu_to_phys_id) - panic("%s: Failed to allocate %zu bytes align=0x%zx\n", - __func__, nr_cpu_ids * sizeof(u32), __alignof__(u32)); for_each_node_by_type(dn, "cpu") { const __be32 *intserv; @@ -834,8 +831,8 @@ static int __init check_cache_coherency(void) if (devtree_coherency != KERNEL_COHERENCY) { printk(KERN_ERR "kernel coherency:%s != device tree_coherency:%s\n", - KERNEL_COHERENCY ? "on" : "off", - devtree_coherency ? "on" : "off"); + str_on_off(KERNEL_COHERENCY), + str_on_off(devtree_coherency)); BUG(); } diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 75dbf3e0d9c4..5a1bf501fbe1 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -140,13 +140,7 @@ arch_initcall(ppc_init); static void *__init alloc_stack(void) { - void *ptr = memblock_alloc(THREAD_SIZE, THREAD_ALIGN); - - if (!ptr) - panic("cannot allocate %d bytes for stack at %pS\n", - THREAD_SIZE, (void *)_RET_IP_); - - return ptr; + return memblock_alloc_or_panic(THREAD_SIZE, THREAD_ALIGN); } void __init irqstack_early_init(void) diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 5ccd791761e8..2f776f137a89 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -658,7 +658,6 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { unsigned long sp = arch_ftrace_regs(fregs)->regs.gpr[1]; - int bit; if (unlikely(ftrace_graph_is_dead())) goto out; @@ -666,14 +665,9 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) - goto out; - - if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp)) + if (!function_graph_enter_regs(parent_ip, ip, 0, (unsigned long *)sp, fregs)) parent_ip = ppc_function_entry(return_to_handler); - ftrace_test_recursion_unlock(bit); out: arch_ftrace_regs(fregs)->regs.link = parent_ip; } diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c index 98787376eb87..ac35015f04c6 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.c +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -787,10 +787,10 @@ int ftrace_disable_ftrace_graph_caller(void) * in current thread info. Return the address we want to divert to. */ static unsigned long -__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) +__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp, + struct ftrace_regs *fregs) { unsigned long return_hooker; - int bit; if (unlikely(ftrace_graph_is_dead())) goto out; @@ -798,16 +798,11 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - bit = ftrace_test_recursion_trylock(ip, parent); - if (bit < 0) - goto out; - return_hooker = ppc_function_entry(return_to_handler); - if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp)) + if (!function_graph_enter_regs(parent, ip, 0, (unsigned long *)sp, fregs)) parent = return_hooker; - ftrace_test_recursion_unlock(bit); out: return parent; } @@ -816,13 +811,14 @@ out: void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip, arch_ftrace_regs(fregs)->regs.gpr[1]); + arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip, + arch_ftrace_regs(fregs)->regs.gpr[1], fregs); } #else unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) { - return __prepare_ftrace_return(parent, ip, sp); + return __prepare_ftrace_return(parent, ip, sp, NULL); } #endif #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32_wrapper.S index 10f92f265d51..20bca3548b44 100644 --- a/arch/powerpc/kernel/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32_wrapper.S @@ -2,7 +2,7 @@ #include #include - __PAGE_ALIGNED_DATA + .section ".data..ro_after_init", "aw" .globl vdso32_start, vdso32_end .balign PAGE_SIZE diff --git a/arch/powerpc/kernel/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64_wrapper.S index 839d1a61411d..1912936fa227 100644 --- a/arch/powerpc/kernel/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64_wrapper.S @@ -2,7 +2,7 @@ #include #include - __PAGE_ALIGNED_DATA + .section ".data..ro_after_init", "aw" .globl vdso64_start, vdso64_end .balign PAGE_SIZE diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index b8333a49ea5d..58a930a47422 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -22,28 +22,6 @@ #include #include -void machine_kexec_mask_interrupts(void) { - unsigned int i; - struct irq_desc *desc; - - for_each_irq_desc(i, desc) { - struct irq_chip *chip; - - chip = irq_desc_get_chip(desc); - if (!chip) - continue; - - if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) - chip->irq_eoi(&desc->irq_data); - - if (chip->irq_mask) - chip->irq_mask(&desc->irq_data); - - if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) - chip->irq_disable(&desc->irq_data); - } -} - #ifdef CONFIG_CRASH_DUMP void machine_crash_shutdown(struct pt_regs *regs) { diff --git a/arch/powerpc/kexec/core_32.c b/arch/powerpc/kexec/core_32.c index c95f96850c9e..deb28eb44f30 100644 --- a/arch/powerpc/kexec/core_32.c +++ b/arch/powerpc/kexec/core_32.c @@ -7,6 +7,7 @@ * Copyright (C) 2005 IBM Corporation. */ +#include #include #include #include diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 25429905ae90..86bff159c51e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4957,7 +4957,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, * states are synchronized from L0 to L1. L1 needs to inform L0 about * MER=1 only when there are pending external interrupts. * In the above if check, MER bit is set if there are pending - * external interrupts. Hence, explicity mask off MER bit + * external interrupts. Hence, explicitly mask off MER bit * here as otherwise it may generate spurious interrupts in L2 KVM * causing an endless loop, which results in L2 guest getting hung. */ diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 6d0d329cbb35..f9acf866c709 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -34,6 +34,8 @@ enum vcpu_ftr { #define E500_TLB_BITMAP (1 << 30) /* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 29) +/* entry is writable on the host */ +#define E500_TLB_WRITABLE (1 << 28) /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */ #define E500_TLB_MAS2_ATTR (0x7f) diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index e5a145b578a4..06caf8bbbe2b 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -45,11 +45,14 @@ static inline unsigned int tlb1_max_shadow_size(void) return host_tlb_params[1].entries - tlbcam_index - 1; } -static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode) +static inline u32 e500_shadow_mas3_attrib(u32 mas3, bool writable, int usermode) { /* Mask off reserved bits. */ mas3 &= MAS3_ATTRIB_MASK; + if (!writable) + mas3 &= ~(MAS3_UW|MAS3_SW); + #ifndef CONFIG_KVM_BOOKE_HV if (!usermode) { /* Guest is in supervisor mode, @@ -242,17 +245,18 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) return tlbe->mas7_3 & (MAS3_SW|MAS3_UW); } -static inline bool kvmppc_e500_ref_setup(struct tlbe_ref *ref, +static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, struct kvm_book3e_206_tlb_entry *gtlbe, - kvm_pfn_t pfn, unsigned int wimg) + kvm_pfn_t pfn, unsigned int wimg, + bool writable) { ref->pfn = pfn; ref->flags = E500_TLB_VALID; + if (writable) + ref->flags |= E500_TLB_WRITABLE; /* Use guest supplied MAS2_G and MAS2_E */ ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; - - return tlbe_is_writable(gtlbe); } static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) @@ -305,6 +309,7 @@ static void kvmppc_e500_setup_stlbe( { kvm_pfn_t pfn = ref->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; + bool writable = !!(ref->flags & E500_TLB_WRITABLE); BUG_ON(!(ref->flags & E500_TLB_VALID)); @@ -312,7 +317,7 @@ static void kvmppc_e500_setup_stlbe( stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | - e500_shadow_mas3_attrib(gtlbe->mas7_3, pr); + e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr); } static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, @@ -321,15 +326,14 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, struct tlbe_ref *ref) { struct kvm_memory_slot *slot; - unsigned long pfn = 0; /* silence GCC warning */ + unsigned int psize; + unsigned long pfn; struct page *page = NULL; unsigned long hva; - int pfnmap = 0; int tsize = BOOK3E_PAGESZ_4K; int ret = 0; unsigned long mmu_seq; struct kvm *kvm = vcpu_e500->vcpu.kvm; - unsigned long tsize_pages = 0; pte_t *ptep; unsigned int wimg = 0; pgd_t *pgdir; @@ -351,110 +355,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn); hva = gfn_to_hva_memslot(slot, gfn); - if (tlbsel == 1) { - struct vm_area_struct *vma; - mmap_read_lock(kvm->mm); - - vma = find_vma(kvm->mm, hva); - if (vma && hva >= vma->vm_start && - (vma->vm_flags & VM_PFNMAP)) { - /* - * This VMA is a physically contiguous region (e.g. - * /dev/mem) that bypasses normal Linux page - * management. Find the overlap between the - * vma and the memslot. - */ - - unsigned long start, end; - unsigned long slot_start, slot_end; - - pfnmap = 1; - - start = vma->vm_pgoff; - end = start + - vma_pages(vma); - - pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT); - - slot_start = pfn - (gfn - slot->base_gfn); - slot_end = slot_start + slot->npages; - - if (start < slot_start) - start = slot_start; - if (end > slot_end) - end = slot_end; - - tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> - MAS1_TSIZE_SHIFT; - - /* - * e500 doesn't implement the lowest tsize bit, - * or 1K pages. - */ - tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); - - /* - * Now find the largest tsize (up to what the guest - * requested) that will cover gfn, stay within the - * range, and for which gfn and pfn are mutually - * aligned. - */ - - for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { - unsigned long gfn_start, gfn_end; - tsize_pages = 1UL << (tsize - 2); - - gfn_start = gfn & ~(tsize_pages - 1); - gfn_end = gfn_start + tsize_pages; - - if (gfn_start + pfn - gfn < start) - continue; - if (gfn_end + pfn - gfn > end) - continue; - if ((gfn & (tsize_pages - 1)) != - (pfn & (tsize_pages - 1))) - continue; - - gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); - pfn &= ~(tsize_pages - 1); - break; - } - } else if (vma && hva >= vma->vm_start && - is_vm_hugetlb_page(vma)) { - unsigned long psize = vma_kernel_pagesize(vma); - - tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> - MAS1_TSIZE_SHIFT; - - /* - * Take the largest page size that satisfies both host - * and guest mapping - */ - tsize = min(__ilog2(psize) - 10, tsize); - - /* - * e500 doesn't implement the lowest tsize bit, - * or 1K pages. - */ - tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); - } - - mmap_read_unlock(kvm->mm); - } - - if (likely(!pfnmap)) { - tsize_pages = 1UL << (tsize + 10 - PAGE_SHIFT); - pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, NULL, &page); - if (is_error_noslot_pfn(pfn)) { - if (printk_ratelimit()) - pr_err("%s: real page not found for gfn %lx\n", - __func__, (long)gfn); - return -EINVAL; - } - - /* Align guest and physical address to page map boundaries */ - pfn &= ~(tsize_pages - 1); - gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); + pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &page); + if (is_error_noslot_pfn(pfn)) { + if (printk_ratelimit()) + pr_err("%s: real page not found for gfn %lx\n", + __func__, (long)gfn); + return -EINVAL; } spin_lock(&kvm->mmu_lock); @@ -472,14 +378,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, * can't run hence pfn won't change. */ local_irq_save(flags); - ptep = find_linux_pte(pgdir, hva, NULL, NULL); + ptep = find_linux_pte(pgdir, hva, NULL, &psize); if (ptep) { pte_t pte = READ_ONCE(*ptep); if (pte_present(pte)) { wimg = (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; - local_irq_restore(flags); } else { local_irq_restore(flags); pr_err_ratelimited("%s: pte not present: gfn %lx,pfn %lx\n", @@ -488,10 +393,72 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, goto out; } } - writable = kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg); + local_irq_restore(flags); + if (psize && tlbsel == 1) { + unsigned long psize_pages, tsize_pages; + unsigned long start, end; + unsigned long slot_start, slot_end; + + psize_pages = 1UL << (psize - PAGE_SHIFT); + start = pfn & ~(psize_pages - 1); + end = start + psize_pages; + + slot_start = pfn - (gfn - slot->base_gfn); + slot_end = slot_start + slot->npages; + + if (start < slot_start) + start = slot_start; + if (end > slot_end) + end = slot_end; + + tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> + MAS1_TSIZE_SHIFT; + + /* + * Any page size that doesn't satisfy the host mapping + * will fail the start and end tests. + */ + tsize = min(psize - PAGE_SHIFT + BOOK3E_PAGESZ_4K, tsize); + + /* + * e500 doesn't implement the lowest tsize bit, + * or 1K pages. + */ + tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); + + /* + * Now find the largest tsize (up to what the guest + * requested) that will cover gfn, stay within the + * range, and for which gfn and pfn are mutually + * aligned. + */ + + for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { + unsigned long gfn_start, gfn_end; + tsize_pages = 1UL << (tsize - 2); + + gfn_start = gfn & ~(tsize_pages - 1); + gfn_end = gfn_start + tsize_pages; + + if (gfn_start + pfn - gfn < start) + continue; + if (gfn_end + pfn - gfn > end) + continue; + if ((gfn & (tsize_pages - 1)) != + (pfn & (tsize_pages - 1))) + continue; + + gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); + pfn &= ~(tsize_pages - 1); + break; + } + } + + kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, ref, gvaddr, stlbe); + writable = tlbe_is_writable(stlbe); /* Clear i-cache for new pages */ kvmppc_mmu_flush_icache(pfn); diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index f14ecab674a3..dd8a4b52a0cc 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -78,4 +78,10 @@ CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec) # Enable CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include) +obj-$(CONFIG_CRC32_ARCH) += crc32-powerpc.o +crc32-powerpc-y := crc32-glue.o crc32c-vpmsum_asm.o + +obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-powerpc.o +crc-t10dif-powerpc-y := crc-t10dif-glue.o crct10dif-vpmsum_asm.o + obj-$(CONFIG_PPC64) += $(obj64-y) diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c b/arch/powerpc/lib/crc-t10dif-glue.c similarity index 50% rename from arch/powerpc/crypto/crct10dif-vpmsum_glue.c rename to arch/powerpc/lib/crc-t10dif-glue.c index 1dc8b6915178..730850dbc51d 100644 --- a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c +++ b/arch/powerpc/lib/crc-t10dif-glue.c @@ -7,7 +7,6 @@ */ #include -#include #include #include #include @@ -22,15 +21,18 @@ #define VECTOR_BREAKPOINT 64 +static DEFINE_STATIC_KEY_FALSE(have_vec_crypto); + u32 __crct10dif_vpmsum(u32 crc, unsigned char const *p, size_t len); -static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len) +u16 crc_t10dif_arch(u16 crci, const u8 *p, size_t len) { unsigned int prealign; unsigned int tail; u32 crc = crci; - if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable()) + if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || + !static_branch_likely(&have_vec_crypto) || !crypto_simd_usable()) return crc_t10dif_generic(crc, p, len); if ((unsigned long)p & VMX_ALIGN_MASK) { @@ -60,67 +62,28 @@ static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len) return crc & 0xffff; } +EXPORT_SYMBOL(crc_t10dif_arch); -static int crct10dif_vpmsum_init(struct shash_desc *desc) +static int __init crc_t10dif_powerpc_init(void) { - u16 *crc = shash_desc_ctx(desc); - - *crc = 0; + if (cpu_has_feature(CPU_FTR_ARCH_207S) && + (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO)) + static_branch_enable(&have_vec_crypto); return 0; } +arch_initcall(crc_t10dif_powerpc_init); -static int crct10dif_vpmsum_update(struct shash_desc *desc, const u8 *data, - unsigned int length) +static void __exit crc_t10dif_powerpc_exit(void) { - u16 *crc = shash_desc_ctx(desc); - - *crc = crct10dif_vpmsum(*crc, data, length); - - return 0; } +module_exit(crc_t10dif_powerpc_exit); - -static int crct10dif_vpmsum_final(struct shash_desc *desc, u8 *out) +bool crc_t10dif_is_optimized(void) { - u16 *crcp = shash_desc_ctx(desc); - - *(u16 *)out = *crcp; - return 0; + return static_key_enabled(&have_vec_crypto); } - -static struct shash_alg alg = { - .init = crct10dif_vpmsum_init, - .update = crct10dif_vpmsum_update, - .final = crct10dif_vpmsum_final, - .descsize = CRC_T10DIF_DIGEST_SIZE, - .digestsize = CRC_T10DIF_DIGEST_SIZE, - .base = { - .cra_name = "crct10dif", - .cra_driver_name = "crct10dif-vpmsum", - .cra_priority = 200, - .cra_blocksize = CRC_T10DIF_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -}; - -static int __init crct10dif_vpmsum_mod_init(void) -{ - if (!cpu_has_feature(CPU_FTR_ARCH_207S)) - return -ENODEV; - - return crypto_register_shash(&alg); -} - -static void __exit crct10dif_vpmsum_mod_fini(void) -{ - crypto_unregister_shash(&alg); -} - -module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crct10dif_vpmsum_mod_init); -module_exit(crct10dif_vpmsum_mod_fini); +EXPORT_SYMBOL(crc_t10dif_is_optimized); MODULE_AUTHOR("Daniel Axtens "); MODULE_DESCRIPTION("CRCT10DIF using vector polynomial multiply-sum instructions"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_CRYPTO("crct10dif"); -MODULE_ALIAS_CRYPTO("crct10dif-vpmsum"); diff --git a/arch/powerpc/lib/crc32-glue.c b/arch/powerpc/lib/crc32-glue.c new file mode 100644 index 000000000000..79cc954f499f --- /dev/null +++ b/arch/powerpc/lib/crc32-glue.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include +#include +#include + +#define VMX_ALIGN 16 +#define VMX_ALIGN_MASK (VMX_ALIGN-1) + +#define VECTOR_BREAKPOINT 512 + +static DEFINE_STATIC_KEY_FALSE(have_vec_crypto); + +u32 __crc32c_vpmsum(u32 crc, const u8 *p, size_t len); + +u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) +{ + return crc32_le_base(crc, p, len); +} +EXPORT_SYMBOL(crc32_le_arch); + +u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len) +{ + unsigned int prealign; + unsigned int tail; + + if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || + !static_branch_likely(&have_vec_crypto) || !crypto_simd_usable()) + return crc32c_le_base(crc, p, len); + + if ((unsigned long)p & VMX_ALIGN_MASK) { + prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK); + crc = crc32c_le_base(crc, p, prealign); + len -= prealign; + p += prealign; + } + + if (len & ~VMX_ALIGN_MASK) { + preempt_disable(); + pagefault_disable(); + enable_kernel_altivec(); + crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK); + disable_kernel_altivec(); + pagefault_enable(); + preempt_enable(); + } + + tail = len & VMX_ALIGN_MASK; + if (tail) { + p += len & ~VMX_ALIGN_MASK; + crc = crc32c_le_base(crc, p, tail); + } + + return crc; +} +EXPORT_SYMBOL(crc32c_le_arch); + +u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) +{ + return crc32_be_base(crc, p, len); +} +EXPORT_SYMBOL(crc32_be_arch); + +static int __init crc32_powerpc_init(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_207S) && + (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO)) + static_branch_enable(&have_vec_crypto); + return 0; +} +arch_initcall(crc32_powerpc_init); + +static void __exit crc32_powerpc_exit(void) +{ +} +module_exit(crc32_powerpc_exit); + +u32 crc32_optimizations(void) +{ + if (static_key_enabled(&have_vec_crypto)) + return CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_AUTHOR("Anton Blanchard "); +MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions"); +MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/lib/crc32-vpmsum_core.S similarity index 100% rename from arch/powerpc/crypto/crc32-vpmsum_core.S rename to arch/powerpc/lib/crc32-vpmsum_core.S diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/lib/crc32c-vpmsum_asm.S similarity index 100% rename from arch/powerpc/crypto/crc32c-vpmsum_asm.S rename to arch/powerpc/lib/crc32c-vpmsum_asm.S diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S b/arch/powerpc/lib/crct10dif-vpmsum_asm.S similarity index 100% rename from arch/powerpc/crypto/crct10dif-vpmsum_asm.S rename to arch/powerpc/lib/crct10dif-vpmsum_asm.S diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index d491da8d1838..58ed6bd613a6 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -45,7 +45,7 @@ int exit_vmx_usercopy(void) * set and we are preemptible. The hack here is to schedule a * decrementer to fire here and reschedule for us if necessary. */ - if (IS_ENABLED(CONFIG_PREEMPT) && need_resched()) + if (IS_ENABLED(CONFIG_PREEMPTION) && need_resched()) set_dec(1); return 0; } diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 6978344edcb4..be9c4106e22f 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -377,10 +377,7 @@ void __init MMU_init_hw(void) * Find some memory for the hash table. */ if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322); - Hash = memblock_alloc(Hash_size, Hash_size); - if (!Hash) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, Hash_size, Hash_size); + Hash = memblock_alloc_or_panic(Hash_size, Hash_size); _SDR1 = __pa(Hash) | SDR1_LOW_BITS; pr_info("Total memory = %lldMB; using %ldkB for hash table\n", diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index 1715b07c630c..4e1e45420bd4 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -253,7 +253,7 @@ static void pmd_frag_destroy(void *pmd_frag) count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ if (atomic_sub_and_test(PMD_FRAG_NR - count, &ptdesc->pt_frag_refcount)) { - pagetable_pmd_dtor(ptdesc); + pagetable_dtor(ptdesc); pagetable_free(ptdesc); } } diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 374542528080..ce64abea9e3e 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -330,11 +330,7 @@ void __init mmu_partition_table_init(void) unsigned long ptcr; /* Initialize the Partition Table with no entries */ - partition_tb = memblock_alloc(patb_size, patb_size); - if (!partition_tb) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, patb_size, patb_size); - + partition_tb = memblock_alloc_or_panic(patb_size, patb_size); ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12); set_ptcr_when_no_uv(ptcr); powernv_set_nmmu_ptcr(ptcr); @@ -477,7 +473,7 @@ void pmd_fragment_free(unsigned long *pmd) BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0); if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) { - pagetable_pmd_dtor(ptdesc); + pagetable_dtor(ptdesc); pagetable_free(ptdesc); } } diff --git a/arch/powerpc/mm/kasan/init_book3e_64.c b/arch/powerpc/mm/kasan/init_book3e_64.c index 43c03b84ff32..60c78aac0f63 100644 --- a/arch/powerpc/mm/kasan/init_book3e_64.c +++ b/arch/powerpc/mm/kasan/init_book3e_64.c @@ -40,19 +40,19 @@ static int __init kasan_map_kernel_page(unsigned long ea, unsigned long pa, pgpr pgdp = pgd_offset_k(ea); p4dp = p4d_offset(pgdp, ea); if (kasan_pud_table(*p4dp)) { - pudp = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); + pudp = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE); memcpy(pudp, kasan_early_shadow_pud, PUD_TABLE_SIZE); p4d_populate(&init_mm, p4dp, pudp); } pudp = pud_offset(p4dp, ea); if (kasan_pmd_table(*pudp)) { - pmdp = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); + pmdp = memblock_alloc_or_panic(PMD_TABLE_SIZE, PMD_TABLE_SIZE); memcpy(pmdp, kasan_early_shadow_pmd, PMD_TABLE_SIZE); pud_populate(&init_mm, pudp, pmdp); } pmdp = pmd_offset(pudp, ea); if (kasan_pte_table(*pmdp)) { - ptep = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); + ptep = memblock_alloc_or_panic(PTE_TABLE_SIZE, PTE_TABLE_SIZE); memcpy(ptep, kasan_early_shadow_pte, PTE_TABLE_SIZE); pmd_populate_kernel(&init_mm, pmdp, ptep); } @@ -74,7 +74,7 @@ static void __init kasan_init_phys_region(void *start, void *end) k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE); k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE); - va = memblock_alloc(k_end - k_start, PAGE_SIZE); + va = memblock_alloc_or_panic(k_end - k_start, PAGE_SIZE); for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE) kasan_map_kernel_page(k_cur, __pa(va), PAGE_KERNEL); } diff --git a/arch/powerpc/mm/kasan/init_book3s_64.c b/arch/powerpc/mm/kasan/init_book3s_64.c index 3fb5ce4f48f4..7d959544c077 100644 --- a/arch/powerpc/mm/kasan/init_book3s_64.c +++ b/arch/powerpc/mm/kasan/init_book3s_64.c @@ -32,7 +32,7 @@ static void __init kasan_init_phys_region(void *start, void *end) k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE); k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE); - va = memblock_alloc(k_end - k_start, PAGE_SIZE); + va = memblock_alloc_or_panic(k_end - k_start, PAGE_SIZE); for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE) map_kernel_page(k_cur, __pa(va), PAGE_KERNEL); } diff --git a/arch/powerpc/mm/nohash/mmu_context.c b/arch/powerpc/mm/nohash/mmu_context.c index 0b181da40ddb..a1a4e697251a 100644 --- a/arch/powerpc/mm/nohash/mmu_context.c +++ b/arch/powerpc/mm/nohash/mmu_context.c @@ -385,21 +385,11 @@ void __init mmu_context_init(void) /* * Allocate the maps used by context management */ - context_map = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES); - if (!context_map) - panic("%s: Failed to allocate %zu bytes\n", __func__, - CTX_MAP_SIZE); - context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1), + context_map = memblock_alloc_or_panic(CTX_MAP_SIZE, SMP_CACHE_BYTES); + context_mm = memblock_alloc_or_panic(sizeof(void *) * (LAST_CONTEXT + 1), SMP_CACHE_BYTES); - if (!context_mm) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(void *) * (LAST_CONTEXT + 1)); if (IS_ENABLED(CONFIG_SMP)) { - stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES); - if (!stale_map[boot_cpuid]) - panic("%s: Failed to allocate %zu bytes\n", __func__, - CTX_MAP_SIZE); - + stale_map[boot_cpuid] = memblock_alloc_or_panic(CTX_MAP_SIZE, SMP_CACHE_BYTES); cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE, "powerpc/mmu/ctx:prepare", mmu_ctx_cpu_prepare, mmu_ctx_cpu_dead); diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c index e89f64a0f24a..713268ccb1a0 100644 --- a/arch/powerpc/mm/pgtable-frag.c +++ b/arch/powerpc/mm/pgtable-frag.c @@ -25,7 +25,7 @@ void pte_frag_destroy(void *pte_frag) count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ if (atomic_sub_and_test(PTE_FRAG_NR - count, &ptdesc->pt_frag_refcount)) { - pagetable_pte_dtor(ptdesc); + pagetable_dtor(ptdesc); pagetable_free(ptdesc); } } @@ -111,7 +111,7 @@ static void pte_free_now(struct rcu_head *head) struct ptdesc *ptdesc; ptdesc = container_of(head, struct ptdesc, pt_rcu_head); - pagetable_pte_dtor(ptdesc); + pagetable_dtor(ptdesc); pagetable_free(ptdesc); } diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 787b22206386..15276068f657 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -50,13 +50,8 @@ notrace void __init early_ioremap_init(void) void __init *early_alloc_pgtable(unsigned long size) { - void *ptr = memblock_alloc(size, size); + return memblock_alloc_or_panic(size, size); - if (!ptr) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, size, size); - - return ptr; } pte_t __init *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va) diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c index b24d4102fbf6..1dc095ad48fc 100644 --- a/arch/powerpc/platforms/8xx/cpm1.c +++ b/arch/powerpc/platforms/8xx/cpm1.c @@ -45,7 +45,7 @@ #include #ifdef CONFIG_8xx_GPIO -#include +#include #endif #define CPM_MAP_SIZE (0x4000) @@ -376,7 +376,8 @@ int __init cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode) #ifdef CONFIG_8xx_GPIO struct cpm1_gpio16_chip { - struct of_mm_gpio_chip mm_gc; + struct gpio_chip gc; + void __iomem *regs; spinlock_t lock; /* shadowed data register to clear/set bits safely */ @@ -386,19 +387,17 @@ struct cpm1_gpio16_chip { int irq[16]; }; -static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc) +static void cpm1_gpio16_save_regs(struct cpm1_gpio16_chip *cpm1_gc) { - struct cpm1_gpio16_chip *cpm1_gc = - container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; cpm1_gc->cpdata = in_be16(&iop->dat); } static int cpm1_gpio16_get(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; u16 pin_mask; pin_mask = 1 << (15 - gpio); @@ -406,11 +405,9 @@ static int cpm1_gpio16_get(struct gpio_chip *gc, unsigned int gpio) return !!(in_be16(&iop->dat) & pin_mask); } -static void __cpm1_gpio16_set(struct of_mm_gpio_chip *mm_gc, u16 pin_mask, - int value) +static void __cpm1_gpio16_set(struct cpm1_gpio16_chip *cpm1_gc, u16 pin_mask, int value) { - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; if (value) cpm1_gc->cpdata |= pin_mask; @@ -422,38 +419,35 @@ static void __cpm1_gpio16_set(struct of_mm_gpio_chip *mm_gc, u16 pin_mask, static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); unsigned long flags; u16 pin_mask = 1 << (15 - gpio); spin_lock_irqsave(&cpm1_gc->lock, flags); - __cpm1_gpio16_set(mm_gc, pin_mask, value); + __cpm1_gpio16_set(cpm1_gc, pin_mask, value); spin_unlock_irqrestore(&cpm1_gc->lock, flags); } static int cpm1_gpio16_to_irq(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); return cpm1_gc->irq[gpio] ? : -ENXIO; } static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; unsigned long flags; u16 pin_mask = 1 << (15 - gpio); spin_lock_irqsave(&cpm1_gc->lock, flags); setbits16(&iop->dir, pin_mask); - __cpm1_gpio16_set(mm_gc, pin_mask, val); + __cpm1_gpio16_set(cpm1_gc, pin_mask, val); spin_unlock_irqrestore(&cpm1_gc->lock, flags); @@ -462,9 +456,8 @@ static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) static int cpm1_gpio16_dir_in(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; unsigned long flags; u16 pin_mask = 1 << (15 - gpio); @@ -481,11 +474,10 @@ int cpm1_gpiochip_add16(struct device *dev) { struct device_node *np = dev->of_node; struct cpm1_gpio16_chip *cpm1_gc; - struct of_mm_gpio_chip *mm_gc; struct gpio_chip *gc; u16 mask; - cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL); + cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL); if (!cpm1_gc) return -ENOMEM; @@ -499,10 +491,8 @@ int cpm1_gpiochip_add16(struct device *dev) cpm1_gc->irq[i] = irq_of_parse_and_map(np, j++); } - mm_gc = &cpm1_gc->mm_gc; - gc = &mm_gc->gc; - - mm_gc->save_regs = cpm1_gpio16_save_regs; + gc = &cpm1_gc->gc; + gc->base = -1; gc->ngpio = 16; gc->direction_input = cpm1_gpio16_dir_in; gc->direction_output = cpm1_gpio16_dir_out; @@ -512,30 +502,39 @@ int cpm1_gpiochip_add16(struct device *dev) gc->parent = dev; gc->owner = THIS_MODULE; - return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc); + gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np); + if (!gc->label) + return -ENOMEM; + + cpm1_gc->regs = devm_of_iomap(dev, np, 0, NULL); + if (IS_ERR(cpm1_gc->regs)) + return PTR_ERR(cpm1_gc->regs); + + cpm1_gpio16_save_regs(cpm1_gc); + + return devm_gpiochip_add_data(dev, gc, cpm1_gc); } struct cpm1_gpio32_chip { - struct of_mm_gpio_chip mm_gc; + struct gpio_chip gc; + void __iomem *regs; spinlock_t lock; /* shadowed data register to clear/set bits safely */ u32 cpdata; }; -static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc) +static void cpm1_gpio32_save_regs(struct cpm1_gpio32_chip *cpm1_gc) { - struct cpm1_gpio32_chip *cpm1_gc = - container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; cpm1_gc->cpdata = in_be32(&iop->dat); } static int cpm1_gpio32_get(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; u32 pin_mask; pin_mask = 1 << (31 - gpio); @@ -543,11 +542,9 @@ static int cpm1_gpio32_get(struct gpio_chip *gc, unsigned int gpio) return !!(in_be32(&iop->dat) & pin_mask); } -static void __cpm1_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask, - int value) +static void __cpm1_gpio32_set(struct cpm1_gpio32_chip *cpm1_gc, u32 pin_mask, int value) { - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; if (value) cpm1_gc->cpdata |= pin_mask; @@ -559,30 +556,28 @@ static void __cpm1_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask, static void cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc); unsigned long flags; u32 pin_mask = 1 << (31 - gpio); spin_lock_irqsave(&cpm1_gc->lock, flags); - __cpm1_gpio32_set(mm_gc, pin_mask, value); + __cpm1_gpio32_set(cpm1_gc, pin_mask, value); spin_unlock_irqrestore(&cpm1_gc->lock, flags); } static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; unsigned long flags; u32 pin_mask = 1 << (31 - gpio); spin_lock_irqsave(&cpm1_gc->lock, flags); setbits32(&iop->dir, pin_mask); - __cpm1_gpio32_set(mm_gc, pin_mask, val); + __cpm1_gpio32_set(cpm1_gc, pin_mask, val); spin_unlock_irqrestore(&cpm1_gc->lock, flags); @@ -591,9 +586,8 @@ static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) static int cpm1_gpio32_dir_in(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; unsigned long flags; u32 pin_mask = 1 << (31 - gpio); @@ -610,19 +604,16 @@ int cpm1_gpiochip_add32(struct device *dev) { struct device_node *np = dev->of_node; struct cpm1_gpio32_chip *cpm1_gc; - struct of_mm_gpio_chip *mm_gc; struct gpio_chip *gc; - cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL); + cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL); if (!cpm1_gc) return -ENOMEM; spin_lock_init(&cpm1_gc->lock); - mm_gc = &cpm1_gc->mm_gc; - gc = &mm_gc->gc; - - mm_gc->save_regs = cpm1_gpio32_save_regs; + gc = &cpm1_gc->gc; + gc->base = -1; gc->ngpio = 32; gc->direction_input = cpm1_gpio32_dir_in; gc->direction_output = cpm1_gpio32_dir_out; @@ -631,7 +622,17 @@ int cpm1_gpiochip_add32(struct device *dev) gc->parent = dev; gc->owner = THIS_MODULE; - return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc); + gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np); + if (!gc->label) + return -ENOMEM; + + cpm1_gc->regs = devm_of_iomap(dev, np, 0, NULL); + if (IS_ERR(cpm1_gc->regs)) + return PTR_ERR(cpm1_gc->regs); + + cpm1_gpio32_save_regs(cpm1_gc); + + return devm_gpiochip_add_data(dev, gc, cpm1_gc); } #endif /* CONFIG_8xx_GPIO */ diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index f381b177ea06..0b6365d85d11 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -464,7 +464,43 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } +/* + * During mmap() paste address, mapping VMA is saved in VAS window + * struct which is used to unmap during migration if the window is + * still open. But the user space can remove this mapping with + * munmap() before closing the window and the VMA address will + * be invalid. Set VAS window VMA to NULL in this function which + * is called before VMA free. + */ +static void vas_mmap_close(struct vm_area_struct *vma) +{ + struct file *fp = vma->vm_file; + struct coproc_instance *cp_inst = fp->private_data; + struct vas_window *txwin; + + /* Should not happen */ + if (!cp_inst || !cp_inst->txwin) { + pr_err("No attached VAS window for the paste address mmap\n"); + return; + } + + txwin = cp_inst->txwin; + /* + * task_ref.vma is set in coproc_mmap() during mmap paste + * address. So it has to be the same VMA that is getting freed. + */ + if (WARN_ON(txwin->task_ref.vma != vma)) { + pr_err("Invalid paste address mmaping\n"); + return; + } + + mutex_lock(&txwin->task_ref.mmap_mutex); + txwin->task_ref.vma = NULL; + mutex_unlock(&txwin->task_ref.mmap_mutex); +} + static const struct vm_operations_struct vas_vm_ops = { + .close = vas_mmap_close, .fault = vas_mmap_fault, }; diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c index fe2e0249cbc2..a112d26185a0 100644 --- a/arch/powerpc/platforms/powermac/nvram.c +++ b/arch/powerpc/platforms/powermac/nvram.c @@ -514,10 +514,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr) printk(KERN_ERR "nvram: no address\n"); return -EINVAL; } - nvram_image = memblock_alloc(NVRAM_SIZE, SMP_CACHE_BYTES); - if (!nvram_image) - panic("%s: Failed to allocate %u bytes\n", __func__, - NVRAM_SIZE); + nvram_image = memblock_alloc_or_panic(NVRAM_SIZE, SMP_CACHE_BYTES); nvram_data = ioremap(addr, NVRAM_SIZE*2); nvram_naddrs = 1; /* Make sure we get the correct case */ diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index 877720c64515..4ac9808e55a4 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -88,26 +88,6 @@ static void flush_dcache_range_chunked(unsigned long start, unsigned long stop, } } -static void memtrace_clear_range(unsigned long start_pfn, - unsigned long nr_pages) -{ - unsigned long pfn; - - /* As HIGHMEM does not apply, use clear_page() directly. */ - for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) { - if (IS_ALIGNED(pfn, PAGES_PER_SECTION)) - cond_resched(); - clear_page(__va(PFN_PHYS(pfn))); - } - /* - * Before we go ahead and use this range as cache inhibited range - * flush the cache. - */ - flush_dcache_range_chunked((unsigned long)pfn_to_kaddr(start_pfn), - (unsigned long)pfn_to_kaddr(start_pfn + nr_pages), - FLUSH_CHUNK_SIZE); -} - static u64 memtrace_alloc_node(u32 nid, u64 size) { const unsigned long nr_pages = PHYS_PFN(size); @@ -119,17 +99,18 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) * by alloc_contig_pages(). */ page = alloc_contig_pages(nr_pages, GFP_KERNEL | __GFP_THISNODE | - __GFP_NOWARN, nid, NULL); + __GFP_NOWARN | __GFP_ZERO, nid, NULL); if (!page) return 0; start_pfn = page_to_pfn(page); /* - * Clear the range while we still have a linear mapping. - * - * TODO: use __GFP_ZERO with alloc_contig_pages() once supported. + * Before we go ahead and use this range as cache inhibited range + * flush the cache. */ - memtrace_clear_range(start_pfn, nr_pages); + flush_dcache_range_chunked((unsigned long)pfn_to_kaddr(start_pfn), + (unsigned long)pfn_to_kaddr(start_pfn + nr_pages), + FLUSH_CHUNK_SIZE); /* * Set pages PageOffline(), to indicate that nobody (e.g., hibernation, diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 5d0f35bb917e..9ec265fcaff4 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -180,10 +180,7 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node, /* * Allocate a buffer to hold the MC recoverable ranges. */ - mc_recoverable_range = memblock_alloc(size, __alignof__(u64)); - if (!mc_recoverable_range) - panic("%s: Failed to allocate %u bytes align=0x%lx\n", - __func__, size, __alignof__(u64)); + mc_recoverable_range = memblock_alloc_or_panic(size, __alignof__(u64)); for (i = 0; i < mc_recoverable_range_len; i++) { mc_recoverable_range[i].start_addr = @@ -818,7 +815,7 @@ static int opal_add_one_export(struct kobject *parent, const char *export_name, sysfs_bin_attr_init(attr); attr->attr.name = name; attr->attr.mode = 0400; - attr->read = sysfs_bin_attr_simple_read; + attr->read_new = sysfs_bin_attr_simple_read; attr->private = __va(vals[0]); attr->size = vals[1]; diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 5144f11359f7..150c09b58ae8 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -115,10 +115,7 @@ static void __init prealloc(struct ps3_prealloc *p) if (!p->size) return; - p->address = memblock_alloc(p->size, p->align); - if (!p->address) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, p->size, p->align); + p->address = memblock_alloc_or_panic(p->size, p->align); printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size, p->address); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 1893f66371fa..b12ef382fec7 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -580,8 +580,10 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) switch(rets[0]) { case 0: - result = EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE; + result = EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED; break; case 1: result = EEH_STATE_RESET_ACTIVE | diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 534cd159e9ab..ae6f7a235d8b 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1650,7 +1650,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, dynamic_addr, dynamic_len, page_shift, NULL, &iommu_table_lpar_multi_ops); - iommu_init_table(newtbl, pci->phb->node, start, end); + iommu_init_table(newtbl, pci->phb->node, + start >> page_shift, end >> page_shift); pci->table_group->tables[default_win_removed ? 0 : 1] = newtbl; @@ -2065,7 +2066,9 @@ static long spapr_tce_create_table(struct iommu_table_group *table_group, int nu offset, 1UL << window_shift, IOMMU_PAGE_SHIFT_4K, NULL, &iommu_table_lpar_multi_ops); - iommu_init_table(tbl, pci->phb->node, start, end); + iommu_init_table(tbl, pci->phb->node, + start >> IOMMU_PAGE_SHIFT_4K, + end >> IOMMU_PAGE_SHIFT_4K); table_group->tables[0] = tbl; @@ -2136,7 +2139,7 @@ static long spapr_tce_create_table(struct iommu_table_group *table_group, int nu /* New table for using DDW instead of the default DMA window */ iommu_table_setparms_common(tbl, pci->phb->bus->number, create.liobn, win_addr, 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops); - iommu_init_table(tbl, pci->phb->node, start, end); + iommu_init_table(tbl, pci->phb->node, start >> page_shift, end >> page_shift); pci->table_group->tables[num] = tbl; set_iommu_table_base(&pdev->dev, tbl); @@ -2205,6 +2208,9 @@ static long spapr_tce_unset_window(struct iommu_table_group *table_group, int nu const char *win_name; int ret = -ENODEV; + if (!tbl) /* The table was never created OR window was never opened */ + return 0; + mutex_lock(&dma_win_init_mutex); if ((num == 0) && is_default_window_table(table_group, tbl)) diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 1798f0f14d58..62bd8e2d5d4c 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -53,7 +53,7 @@ struct update_props_workarea { static unsigned int nmi_wd_lpm_factor = 200; #ifdef CONFIG_SYSCTL -static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = { +static const struct ctl_table nmi_wd_lpm_factor_ctl_table[] = { { .procname = "nmi_wd_lpm_factor", .data = &nmi_wd_lpm_factor, diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f84ac9fbe203..f7c9271bda58 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -544,7 +544,7 @@ static int drc_pmem_query_health(struct papr_scm_priv *p) /* Jiffies offset for which the health data is assumed to be same */ cache_timeout = p->lasthealth_jiffies + - msecs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL * 1000); + secs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL); /* Fetch new health info is its older than MIN_HEALTH_QUERY_INTERVAL */ if (time_after(jiffies, cache_timeout)) diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index 0b6e37f3ffb8..456a4f64ae0a 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -124,10 +124,7 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count, if (bmp->bitmap_from_slab) bmp->bitmap = kzalloc(size, GFP_KERNEL); else { - bmp->bitmap = memblock_alloc(size, SMP_CACHE_BYTES); - if (!bmp->bitmap) - panic("%s: Failed to allocate %u bytes\n", __func__, - size); + bmp->bitmap = memblock_alloc_or_panic(size, SMP_CACHE_BYTES); /* the bitmap won't be freed from memblock allocator */ kmemleak_not_leak(bmp->bitmap); } diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index f4e841a36458..268859e4df87 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2623,9 +2623,9 @@ static void dump_one_paca(int cpu) printf("paca for cpu 0x%x @ %px:\n", cpu, p); - printf(" %-*s = %s\n", 25, "possible", cpu_possible(cpu) ? "yes" : "no"); - printf(" %-*s = %s\n", 25, "present", cpu_present(cpu) ? "yes" : "no"); - printf(" %-*s = %s\n", 25, "online", cpu_online(cpu) ? "yes" : "no"); + printf(" %-*s = %s\n", 25, "possible", str_yes_no(cpu_possible(cpu))); + printf(" %-*s = %s\n", 25, "present", str_yes_no(cpu_present(cpu))); + printf(" %-*s = %s\n", 25, "online", str_yes_no(cpu_online(cpu))); #define DUMP(paca, name, format) \ printf(" %-*s = "format"\t(0x%lx)\n", 25, #name, 18, paca->name, \ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d4a7ca0388c0..7612c52e9b1e 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -24,6 +24,7 @@ config RISCV select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CRC32 if RISCV_ISA_ZBC select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DEBUG_VM_PGTABLE @@ -146,9 +147,10 @@ config RISCV select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION select HAVE_EBPF_JIT if MMU select HAVE_GUP_FAST if MMU diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata index 2acc7d876e1f..e318119d570d 100644 --- a/arch/riscv/Kconfig.errata +++ b/arch/riscv/Kconfig.errata @@ -119,4 +119,15 @@ config ERRATA_THEAD_PMU If you don't know what to do here, say "Y". +config ERRATA_THEAD_GHOSTWRITE + bool "Apply T-Head Ghostwrite errata" + depends on ERRATA_THEAD && RISCV_ISA_XTHEADVECTOR + default y + help + The T-Head C9xx cores have a vulnerability in the xtheadvector + instruction set. When this errata is enabled, the CPUs will be probed + to determine if they are vulnerable and disable xtheadvector. + + If you don't know what to do here, say "Y". + endmenu # "CPU errata selection" diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index f51bb24bc84c..1916cf7ba450 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -24,6 +24,11 @@ config ARCH_SOPHGO help This enables support for Sophgo SoC platform hardware. +config ARCH_SPACEMIT + bool "SpacemiT SoCs" + help + This enables support for SpacemiT SoC platform hardware. + config ARCH_STARFIVE def_bool SOC_STARFIVE diff --git a/arch/riscv/Kconfig.vendor b/arch/riscv/Kconfig.vendor index 6f1cdd32ed29..b096548fe0ff 100644 --- a/arch/riscv/Kconfig.vendor +++ b/arch/riscv/Kconfig.vendor @@ -16,4 +16,30 @@ config RISCV_ISA_VENDOR_EXT_ANDES If you don't know what to do here, say Y. endmenu +menu "T-Head" +config RISCV_ISA_VENDOR_EXT_THEAD + bool "T-Head vendor extension support" + select RISCV_ISA_VENDOR_EXT + default y + help + Say N here to disable detection of and support for all T-Head vendor + extensions. Without this option enabled, T-Head vendor extensions will + not be detected at boot and their presence not reported to userspace. + + If you don't know what to do here, say Y. + +config RISCV_ISA_XTHEADVECTOR + bool "xtheadvector extension support" + depends on RISCV_ISA_VENDOR_EXT_THEAD + depends on RISCV_ISA_V + depends on FPU + default y + help + Say N here if you want to disable all xtheadvector related procedures + in the kernel. This will disable vector for any T-Head board that + contains xtheadvector rather than the standard vector. + + If you don't know what to do here, say Y. +endmenu + endmenu diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink index 829b9abc91f6..6b0580949b6a 100644 --- a/arch/riscv/Makefile.postlink +++ b/arch/riscv/Makefile.postlink @@ -10,6 +10,7 @@ __archpost: -include include/config/auto.conf include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib quiet_cmd_relocs_check = CHKREL $@ cmd_relocs_check = \ @@ -19,11 +20,6 @@ ifdef CONFIG_RELOCATABLE quiet_cmd_cp_vmlinux_relocs = CPREL vmlinux.relocs cmd_cp_vmlinux_relocs = cp vmlinux vmlinux.relocs -quiet_cmd_relocs_strip = STRIPREL $@ -cmd_relocs_strip = $(OBJCOPY) --remove-section='.rel.*' \ - --remove-section='.rel__*' \ - --remove-section='.rela.*' \ - --remove-section='.rela__*' $@ endif # `@true` prevents complaint when there is nothing to be done @@ -33,7 +29,7 @@ vmlinux: FORCE ifdef CONFIG_RELOCATABLE $(call if_changed,relocs_check) $(call if_changed,cp_vmlinux_relocs) - $(call if_changed,relocs_strip) + $(call if_changed,strip_relocs) endif clean: diff --git a/arch/riscv/boot/dts/Makefile b/arch/riscv/boot/dts/Makefile index fdae05bbf556..bff887d38abe 100644 --- a/arch/riscv/boot/dts/Makefile +++ b/arch/riscv/boot/dts/Makefile @@ -5,6 +5,7 @@ subdir-y += microchip subdir-y += renesas subdir-y += sifive subdir-y += sophgo +subdir-y += spacemit subdir-y += starfive subdir-y += thead diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi index 64c3c2e6cbe0..6367112e614a 100644 --- a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi @@ -27,7 +27,8 @@ riscv,isa = "rv64imafdc"; riscv,isa-base = "rv64i"; riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", - "zifencei", "zihpm"; + "zifencei", "zihpm", "xtheadvector"; + thead,vlenb = <128>; #cooling-cells = <2>; cpu0_intc: interrupt-controller { diff --git a/arch/riscv/boot/dts/spacemit/Makefile b/arch/riscv/boot/dts/spacemit/Makefile new file mode 100644 index 000000000000..ac617319a574 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_SPACEMIT) += k1-bananapi-f3.dtb diff --git a/arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts b/arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts new file mode 100644 index 000000000000..1d617b40a2d5 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen + */ + +#include "k1.dtsi" +#include "k1-pinctrl.dtsi" + +/ { + model = "Banana Pi BPI-F3"; + compatible = "bananapi,bpi-f3", "spacemit,k1"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0"; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_2_cfg>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi b/arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi new file mode 100644 index 000000000000..a8eac5517f85 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (c) 2024 Yixun Lan + */ + +#include + +#define K1_PADCONF(pin, func) (((pin) << 16) | (func)) + +&pinctrl { + uart0_2_cfg: uart0-2-cfg { + uart0-2-pins { + pinmux = , + ; + + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1.dtsi b/arch/riscv/boot/dts/spacemit/k1.dtsi new file mode 100644 index 000000000000..c670ebf8fa12 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1.dtsi @@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen + */ + +/dts-v1/; +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "SpacemiT K1"; + compatible = "spacemit,k1"; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <24000000>; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu_0>; + }; + core1 { + cpu = <&cpu_1>; + }; + core2 { + cpu = <&cpu_2>; + }; + core3 { + cpu = <&cpu_3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu_4>; + }; + core1 { + cpu = <&cpu_5>; + }; + core2 { + cpu = <&cpu_6>; + }; + core3 { + cpu = <&cpu_7>; + }; + }; + }; + + cpu_0: cpu@0 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <0>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_1: cpu@1 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <1>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_2: cpu@2 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <2>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_3: cpu@3 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <3>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_4: cpu@4 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <4>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu4_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_5: cpu@5 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <5>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu5_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_6: cpu@6 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <6>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu6_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_7: cpu@7 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <7>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu7_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cluster0_l2_cache: l2-cache0 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <524288>; + cache-sets = <512>; + cache-unified; + }; + + cluster1_l2_cache: l2-cache1 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <524288>; + cache-sets = <512>; + cache-unified; + }; + }; + + soc { + compatible = "simple-bus"; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + dma-noncoherent; + ranges; + + uart0: serial@d4017000 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017000 0x0 0x100>; + interrupts = <42>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart2: serial@d4017100 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017100 0x0 0x100>; + interrupts = <44>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart3: serial@d4017200 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017200 0x0 0x100>; + interrupts = <45>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart4: serial@d4017300 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017300 0x0 0x100>; + interrupts = <46>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart5: serial@d4017400 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017400 0x0 0x100>; + interrupts = <47>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart6: serial@d4017500 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017500 0x0 0x100>; + interrupts = <48>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart7: serial@d4017600 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017600 0x0 0x100>; + interrupts = <49>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart8: serial@d4017700 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017700 0x0 0x100>; + interrupts = <50>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart9: serial@d4017800 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017800 0x0 0x100>; + interrupts = <51>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + pinctrl: pinctrl@d401e000 { + compatible = "spacemit,k1-pinctrl"; + reg = <0x0 0xd401e000 0x0 0x400>; + }; + + plic: interrupt-controller@e0000000 { + compatible = "spacemit,k1-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xe0000000 0x0 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>, + <&cpu4_intc 11>, <&cpu4_intc 9>, + <&cpu5_intc 11>, <&cpu5_intc 9>, + <&cpu6_intc 11>, <&cpu6_intc 9>, + <&cpu7_intc 11>, <&cpu7_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + riscv,ndev = <159>; + }; + + clint: timer@e4000000 { + compatible = "spacemit,k1-clint", "sifive,clint0"; + reg = <0x0 0xe4000000 0x0 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>, + <&cpu2_intc 3>, <&cpu2_intc 7>, + <&cpu3_intc 3>, <&cpu3_intc 7>, + <&cpu4_intc 3>, <&cpu4_intc 7>, + <&cpu5_intc 3>, <&cpu5_intc 7>, + <&cpu6_intc 3>, <&cpu6_intc 7>, + <&cpu7_intc 3>, <&cpu7_intc 7>; + }; + + sec_uart1: serial@f0612000 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xf0612000 0x0 0x100>; + interrupts = <43>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "reserved"; /* for TEE usage */ + }; + }; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts b/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts index 0d248b671d4b..3bd62ab78523 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts +++ b/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts @@ -53,7 +53,23 @@ status = "okay"; }; +&sysgpio { + usb0_pins: usb0-0 { + vbus-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + &usb0 { - dr_mode = "peripheral"; + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; status = "okay"; }; diff --git a/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts index fe4a490ecc61..b764d4d92fd9 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts +++ b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts @@ -80,7 +80,23 @@ status = "okay"; }; +&sysgpio { + usb0_pins: usb0-0 { + vbus-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + &usb0 { - dr_mode = "peripheral"; + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; status = "okay"; }; diff --git a/arch/riscv/boot/dts/thead/th1520.dtsi b/arch/riscv/boot/dts/thead/th1520.dtsi index acfe030e803a..527336417765 100644 --- a/arch/riscv/boot/dts/thead/th1520.dtsi +++ b/arch/riscv/boot/dts/thead/th1520.dtsi @@ -599,6 +599,22 @@ status = "disabled"; }; + mbox_910t: mailbox@ffffc38000 { + compatible = "thead,th1520-mbox"; + reg = <0xff 0xffc38000 0x0 0x6000>, + <0xff 0xffc40000 0x0 0x6000>, + <0xff 0xffc4c000 0x0 0x2000>, + <0xff 0xffc54000 0x0 0x2000>; + reg-names = "local", "remote-icu0", "remote-icu1", "remote-icu2"; + clocks = <&clk CLK_MBOX0>, <&clk CLK_MBOX1>, <&clk CLK_MBOX2>, + <&clk CLK_MBOX3>; + clock-names = "clk-local", "clk-remote-icu0", "clk-remote-icu1", + "clk-remote-icu2"; + interrupt-parent = <&plic>; + interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; + #mbox-cells = <1>; + }; + gpio@fffff41000 { compatible = "snps,dw-apb-gpio"; reg = <0xff 0xfff41000 0x0 0x1000>; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index b4a37345703e..0f7dcbe3c45b 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -10,7 +10,6 @@ CONFIG_MEMCG=y CONFIG_BLK_CGROUP=y CONFIG_CGROUP_SCHED=y CONFIG_CFS_BANDWIDTH=y -CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y @@ -30,6 +29,7 @@ CONFIG_ARCH_MICROCHIP=y CONFIG_ARCH_RENESAS=y CONFIG_ARCH_SIFIVE=y CONFIG_ARCH_SOPHGO=y +CONFIG_ARCH_SPACEMIT=y CONFIG_SOC_STARFIVE=y CONFIG_ARCH_SUNXI=y CONFIG_ARCH_THEAD=y @@ -167,6 +167,7 @@ CONFIG_PINCTRL_SOPHGO_CV1800B=y CONFIG_PINCTRL_SOPHGO_CV1812H=y CONFIG_PINCTRL_SOPHGO_SG2000=y CONFIG_PINCTRL_SOPHGO_SG2002=y +CONFIG_PINCTRL_TH1520=y CONFIG_GPIO_DWAPB=y CONFIG_GPIO_SIFIVE=y CONFIG_POWER_RESET_GPIO_RESTART=y @@ -242,6 +243,7 @@ CONFIG_RTC_DRV_SUN6I=y CONFIG_DMADEVICES=y CONFIG_DMA_SUN6I=m CONFIG_DW_AXI_DMAC=y +CONFIG_DWMAC_THEAD=m CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index e24770a77932..0b942183f708 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -142,6 +143,31 @@ static bool errata_probe_pmu(unsigned int stage, return true; } +static bool errata_probe_ghostwrite(unsigned int stage, + unsigned long arch_id, unsigned long impid) +{ + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_GHOSTWRITE)) + return false; + + /* + * target-c9xx cores report arch_id and impid as 0 + * + * While ghostwrite may not affect all c9xx cores that implement + * xtheadvector, there is no futher granularity than c9xx. Assume + * vulnerable for this entire class of processors when xtheadvector is + * enabled. + */ + if (arch_id != 0 || impid != 0) + return false; + + if (stage != RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + ghostwrite_set_vulnerable(); + + return true; +} + static u32 thead_errata_probe(unsigned int stage, unsigned long archid, unsigned long impid) { @@ -155,6 +181,8 @@ static u32 thead_errata_probe(unsigned int stage, if (errata_probe_pmu(stage, archid, impid)) cpu_req_errata |= BIT(ERRATA_THEAD_PMU); + errata_probe_ghostwrite(stage, archid, impid); + return cpu_req_errata; } diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index de13d5a234f8..bd5fc9403295 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -4,6 +4,7 @@ syscall-y += syscall_table_64.h generic-y += early_ioremap.h generic-y += flat.h +generic-y += fprobe.h generic-y += kvm_para.h generic-y += mmzone.h generic-y += mcs_spinlock.h diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h index fae152ea0508..c6bd3d8354a9 100644 --- a/arch/riscv/include/asm/bitops.h +++ b/arch/riscv/include/asm/bitops.h @@ -228,7 +228,7 @@ legacy: * * This operation may be reordered on other architectures than x86. */ -static inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) +static __always_inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) { return __test_and_op_bit(or, __NOP, nr, addr); } @@ -240,7 +240,7 @@ static inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) * * This operation can be reordered on other architectures other than x86. */ -static inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) { return __test_and_op_bit(and, __NOT, nr, addr); } @@ -253,7 +253,7 @@ static inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) +static __always_inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) { return __test_and_op_bit(xor, __NOP, nr, addr); } @@ -270,7 +270,7 @@ static inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void arch_set_bit(int nr, volatile unsigned long *addr) +static __always_inline void arch_set_bit(int nr, volatile unsigned long *addr) { __op_bit(or, __NOP, nr, addr); } @@ -284,7 +284,7 @@ static inline void arch_set_bit(int nr, volatile unsigned long *addr) * on non x86 architectures, so if you are writing portable code, * make sure not to rely on its reordering guarantees. */ -static inline void arch_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline void arch_clear_bit(int nr, volatile unsigned long *addr) { __op_bit(and, __NOT, nr, addr); } @@ -298,7 +298,7 @@ static inline void arch_clear_bit(int nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void arch_change_bit(int nr, volatile unsigned long *addr) +static __always_inline void arch_change_bit(int nr, volatile unsigned long *addr) { __op_bit(xor, __NOP, nr, addr); } @@ -311,7 +311,7 @@ static inline void arch_change_bit(int nr, volatile unsigned long *addr) * This operation is atomic and provides acquire barrier semantics. * It can be used to implement bit locks. */ -static inline int arch_test_and_set_bit_lock( +static __always_inline int arch_test_and_set_bit_lock( unsigned long nr, volatile unsigned long *addr) { return __test_and_op_bit_ord(or, __NOP, nr, addr, .aq); @@ -324,7 +324,7 @@ static inline int arch_test_and_set_bit_lock( * * This operation is atomic and provides release barrier semantics. */ -static inline void arch_clear_bit_unlock( +static __always_inline void arch_clear_bit_unlock( unsigned long nr, volatile unsigned long *addr) { __op_bit_ord(and, __NOT, nr, addr, .rl); @@ -345,13 +345,13 @@ static inline void arch_clear_bit_unlock( * non-atomic property here: it's a lot more instructions and we still have to * provide release semantics anyway. */ -static inline void arch___clear_bit_unlock( +static __always_inline void arch___clear_bit_unlock( unsigned long nr, volatile unsigned long *addr) { arch_clear_bit_unlock(nr, addr); } -static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, +static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, volatile unsigned long *addr) { unsigned long res; diff --git a/arch/riscv/include/asm/bugs.h b/arch/riscv/include/asm/bugs.h new file mode 100644 index 000000000000..17ca0a947730 --- /dev/null +++ b/arch/riscv/include/asm/bugs.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Interface for managing mitigations for riscv vulnerabilities. + * + * Copyright (C) 2024 Rivos Inc. + */ + +#ifndef __ASM_BUGS_H +#define __ASM_BUGS_H + +/* Watch out, ordering is important here. */ +enum mitigation_state { + UNAFFECTED, + MITIGATED, + VULNERABLE, +}; + +void ghostwrite_set_vulnerable(void); +bool ghostwrite_enable_mitigation(void); +enum mitigation_state ghostwrite_get_state(void); + +#endif /* __ASM_BUGS_H */ diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 4bd054c54c21..569140d6e639 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -34,6 +34,8 @@ DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); /* Per-cpu ISA extensions. */ extern struct riscv_isainfo hart_isa[NR_CPUS]; +extern u32 thead_vlenb_of; + void __init riscv_user_isa_enable(void); #define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) { \ diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 37bdea65bbd8..6fed42e37705 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -30,6 +30,12 @@ #define SR_VS_CLEAN _AC(0x00000400, UL) #define SR_VS_DIRTY _AC(0x00000600, UL) +#define SR_VS_THEAD _AC(0x01800000, UL) /* xtheadvector Status */ +#define SR_VS_OFF_THEAD _AC(0x00000000, UL) +#define SR_VS_INITIAL_THEAD _AC(0x00800000, UL) +#define SR_VS_CLEAN_THEAD _AC(0x01000000, UL) +#define SR_VS_DIRTY_THEAD _AC(0x01800000, UL) + #define SR_XS _AC(0x00018000, UL) /* Extension Status */ #define SR_XS_OFF _AC(0x00000000, UL) #define SR_XS_INITIAL _AC(0x00008000, UL) @@ -315,6 +321,15 @@ #define CSR_STIMECMP 0x14D #define CSR_STIMECMPH 0x15D +/* xtheadvector symbolic CSR names */ +#define CSR_VXSAT 0x9 +#define CSR_VXRM 0xa + +/* xtheadvector CSR masks */ +#define CSR_VXRM_MASK 3 +#define CSR_VXRM_SHIFT 1 +#define CSR_VXSAT_MASK 1 + /* Supervisor-Level Window to Indirectly Accessed Registers (AIA) */ #define CSR_SISELECT 0x150 #define CSR_SIREG 0x151 diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index 7c8a71a526a3..6e426ed7919a 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -25,7 +25,8 @@ #ifdef CONFIG_ERRATA_THEAD #define ERRATA_THEAD_MAE 0 #define ERRATA_THEAD_PMU 1 -#define ERRATA_THEAD_NUMBER 2 +#define ERRATA_THEAD_GHOSTWRITE 2 +#define ERRATA_THEAD_NUMBER 3 #endif #ifdef __ASSEMBLY__ diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 3d66437a1029..c4721ce44ca4 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -168,6 +168,11 @@ static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct return arch_ftrace_regs(fregs)->sp; } +static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->s0; +} + static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n) { @@ -181,6 +186,11 @@ static __always_inline unsigned long ftrace_regs_get_return_value(const struct f return arch_ftrace_regs(fregs)->a0; } +static __always_inline unsigned long ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->ra; +} + static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs, unsigned long ret) { @@ -192,6 +202,20 @@ static __always_inline void ftrace_override_function_with_return(struct ftrace_r arch_ftrace_regs(fregs)->epc = arch_ftrace_regs(fregs)->ra; } +static __always_inline struct pt_regs * +ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs) +{ + struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs); + + memcpy(®s->a0, afregs->args, sizeof(afregs->args)); + regs->epc = afregs->epc; + regs->ra = afregs->ra; + regs->sp = afregs->sp; + regs->s0 = afregs->s0; + regs->t1 = afregs->t1; + return regs; +} + int ftrace_regs_query_register_offset(const char *name); void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, @@ -208,25 +232,4 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsi #endif /* CONFIG_DYNAMIC_FTRACE */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long a1; - unsigned long a0; - unsigned long s0; - unsigned long ra; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->a0; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->s0; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h index fc8130f995c1..72be100afa23 100644 --- a/arch/riscv/include/asm/futex.h +++ b/arch/riscv/include/asm/futex.h @@ -85,7 +85,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, __enable_user_access(); __asm__ __volatile__ ( - "1: lr.w.aqrl %[v],%[u] \n" + "1: lr.w %[v],%[u] \n" " bne %[v],%z[ov],3f \n" "2: sc.w.aqrl %[t],%z[nv],%[u] \n" " bnez %[t],1b \n" diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 1ce1df6d0ff3..dd624523981c 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* - * Copyright 2023 Rivos, Inc + * Copyright 2023-2024 Rivos, Inc */ #ifndef _ASM_HWPROBE_H @@ -8,7 +8,7 @@ #include -#define RISCV_HWPROBE_MAX_KEY 10 +#define RISCV_HWPROBE_MAX_KEY 11 static inline bool riscv_hwprobe_key_is_valid(__s64 key) { @@ -21,6 +21,7 @@ static inline bool hwprobe_key_is_bitmask(__s64 key) case RISCV_HWPROBE_KEY_BASE_BEHAVIOR: case RISCV_HWPROBE_KEY_IMA_EXT_0: case RISCV_HWPROBE_KEY_CPUPERF_0: + case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0: return true; } diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 35eab6e0f4ae..cc33e35cd628 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -87,6 +87,11 @@ struct kvm_vcpu_stat { u64 csr_exit_kernel; u64 signal_exits; u64 exits; + u64 instr_illegal_exits; + u64 load_misaligned_exits; + u64 store_misaligned_exits; + u64 load_access_exits; + u64 store_access_exits; }; struct kvm_arch_memory_slot { diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index b96705258cf9..4ed6203cdd30 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -85,6 +85,7 @@ extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor; diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 71aabc5c6713..125f5ecd9565 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -122,6 +122,7 @@ struct kernel_mapping { extern struct kernel_mapping kernel_map; extern phys_addr_t phys_ram_base; +extern unsigned long vmemmap_start_pfn; #define is_kernel_mapping(x) \ ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index f52264304f77..3e2aebea6312 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -12,16 +12,25 @@ #include #ifdef CONFIG_MMU -#define __HAVE_ARCH_PUD_ALLOC_ONE #define __HAVE_ARCH_PUD_FREE #include +/* + * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to + * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use + * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this + * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the + * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h + * for more details. + */ static inline void riscv_tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt) { - if (riscv_use_sbi_for_rfence()) + if (riscv_use_sbi_for_rfence()) { tlb_remove_ptdesc(tlb, pt); - else + } else { + pagetable_dtor(pt); tlb_remove_page_ptdesc(tlb, pt); + } } static inline void pmd_populate_kernel(struct mm_struct *mm, @@ -88,15 +97,6 @@ static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, } } -#define pud_alloc_one pud_alloc_one -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - if (pgtable_l4_enabled) - return __pud_alloc_one(mm, addr); - - return NULL; -} - #define pud_free pud_free static inline void pud_free(struct mm_struct *mm, pud_t *pud) { @@ -107,39 +107,8 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long addr) { - if (pgtable_l4_enabled) { - struct ptdesc *ptdesc = virt_to_ptdesc(pud); - - pagetable_pud_dtor(ptdesc); - riscv_tlb_remove_ptdesc(tlb, ptdesc); - } -} - -#define p4d_alloc_one p4d_alloc_one -static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - if (pgtable_l5_enabled) { - gfp_t gfp = GFP_PGTABLE_USER; - - if (mm == &init_mm) - gfp = GFP_PGTABLE_KERNEL; - return (p4d_t *)get_zeroed_page(gfp); - } - - return NULL; -} - -static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d) -{ - BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); - free_page((unsigned long)p4d); -} - -#define p4d_free p4d_free -static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) -{ - if (pgtable_l5_enabled) - __p4d_free(mm, p4d); + if (pgtable_l4_enabled) + riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud)); } static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, @@ -161,9 +130,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; - pgd = (pgd_t *)__get_free_page(GFP_KERNEL); + pgd = __pgd_alloc(mm, 0); if (likely(pgd != NULL)) { - memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t)); /* Copy kernel mappings */ sync_kernel_mappings(pgd); } @@ -175,10 +143,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { - struct ptdesc *ptdesc = virt_to_ptdesc(pmd); - - pagetable_pmd_dtor(ptdesc); - riscv_tlb_remove_ptdesc(tlb, ptdesc); + riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd)); } #endif /* __PAGETABLE_PMD_FOLDED */ @@ -186,10 +151,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { - struct ptdesc *ptdesc = page_ptdesc(pte); - - pagetable_pte_dtor(ptdesc); - riscv_tlb_remove_ptdesc(tlb, ptdesc); + riscv_tlb_remove_ptdesc(tlb, page_ptdesc(pte)); } #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index d4e99eef90ac..050fdc49b5ad 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -87,7 +87,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) +#define vmemmap ((struct page *)VMEMMAP_START - vmemmap_start_pfn) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 6c82318065cf..3d250824178b 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -159,6 +159,7 @@ struct riscv_pmu_snapshot_data { }; #define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0) +#define RISCV_PMU_PLAT_FW_EVENT_MASK GENMASK_ULL(61, 0) #define RISCV_PMU_RAW_EVENT_IDX 0x20000 #define RISCV_PLAT_FW_EVENT 0xFFFF diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h index e5121b89acea..52f11bfd0079 100644 --- a/arch/riscv/include/asm/spinlock.h +++ b/arch/riscv/include/asm/spinlock.h @@ -3,8 +3,11 @@ #ifndef __ASM_RISCV_SPINLOCK_H #define __ASM_RISCV_SPINLOCK_H -#ifdef CONFIG_RISCV_COMBO_SPINLOCKS +#ifdef CONFIG_QUEUED_SPINLOCKS #define _Q_PENDING_LOOPS (1 << 9) +#endif + +#ifdef CONFIG_RISCV_COMBO_SPINLOCKS #define __no_arch_spinlock_redefine #include diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 94e33216b2d9..0e71eb82f920 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -117,7 +117,7 @@ do { \ __set_prev_cpu(__prev->thread); \ if (has_fpu()) \ __switch_to_fpu(__prev, __next); \ - if (has_vector()) \ + if (has_vector() || has_xtheadvector()) \ __switch_to_vector(__prev, __next); \ if (switch_to_should_flush_icache(__next)) \ local_flush_icache_all(); \ diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h index 1f6c38420d8e..50b63b5c15bd 100644 --- a/arch/riscv/include/asm/tlb.h +++ b/arch/riscv/include/asm/tlb.h @@ -10,24 +10,6 @@ struct mmu_gather; static void tlb_flush(struct mmu_gather *tlb); -#ifdef CONFIG_MMU -#include - -/* - * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to - * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use - * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this - * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the - * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h - * for more details. - */ -static inline void __tlb_remove_table(void *table) -{ - free_page_and_swap_cache(table); -} - -#endif /* CONFIG_MMU */ - #define tlb_flush tlb_flush #include diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index c7c023afbacd..e8a83f55be2b 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -18,6 +18,27 @@ #include #include #include +#include +#include +#include + +#define __riscv_v_vstate_or(_val, TYPE) ({ \ + typeof(_val) _res = _val; \ + if (has_xtheadvector()) \ + _res = (_res & ~SR_VS_THEAD) | SR_VS_##TYPE##_THEAD; \ + else \ + _res = (_res & ~SR_VS) | SR_VS_##TYPE; \ + _res; \ +}) + +#define __riscv_v_vstate_check(_val, TYPE) ({ \ + bool _res; \ + if (has_xtheadvector()) \ + _res = ((_val) & SR_VS_THEAD) == SR_VS_##TYPE##_THEAD; \ + else \ + _res = ((_val) & SR_VS) == SR_VS_##TYPE; \ + _res; \ +}) extern unsigned long riscv_v_vsize; int riscv_v_setup_vsize(void); @@ -41,39 +62,62 @@ static __always_inline bool has_vector(void) return riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE32X); } +static __always_inline bool has_xtheadvector_no_alternatives(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_isa_vendor_extension_available(THEAD_VENDOR_ID, XTHEADVECTOR); + else + return false; +} + +static __always_inline bool has_xtheadvector(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_has_vendor_extension_unlikely(THEAD_VENDOR_ID, + RISCV_ISA_VENDOR_EXT_XTHEADVECTOR); + else + return false; +} + static inline void __riscv_v_vstate_clean(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_CLEAN; + regs->status = __riscv_v_vstate_or(regs->status, CLEAN); } static inline void __riscv_v_vstate_dirty(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_DIRTY; + regs->status = __riscv_v_vstate_or(regs->status, DIRTY); } static inline void riscv_v_vstate_off(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_OFF; + regs->status = __riscv_v_vstate_or(regs->status, OFF); } static inline void riscv_v_vstate_on(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_INITIAL; + regs->status = __riscv_v_vstate_or(regs->status, INITIAL); } static inline bool riscv_v_vstate_query(struct pt_regs *regs) { - return (regs->status & SR_VS) != 0; + return !__riscv_v_vstate_check(regs->status, OFF); } static __always_inline void riscv_v_enable(void) { - csr_set(CSR_SSTATUS, SR_VS); + if (has_xtheadvector()) + csr_set(CSR_SSTATUS, SR_VS_THEAD); + else + csr_set(CSR_SSTATUS, SR_VS); } static __always_inline void riscv_v_disable(void) { - csr_clear(CSR_SSTATUS, SR_VS); + if (has_xtheadvector()) + csr_clear(CSR_SSTATUS, SR_VS_THEAD); + else + csr_clear(CSR_SSTATUS, SR_VS); } static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) @@ -82,10 +126,36 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) "csrr %0, " __stringify(CSR_VSTART) "\n\t" "csrr %1, " __stringify(CSR_VTYPE) "\n\t" "csrr %2, " __stringify(CSR_VL) "\n\t" - "csrr %3, " __stringify(CSR_VCSR) "\n\t" - "csrr %4, " __stringify(CSR_VLENB) "\n\t" : "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl), - "=r" (dest->vcsr), "=r" (dest->vlenb) : :); + "=r" (dest->vcsr) : :); + + if (has_xtheadvector()) { + unsigned long status; + + /* + * CSR_VCSR is defined as + * [2:1] - vxrm[1:0] + * [0] - vxsat + * The earlier vector spec implemented by T-Head uses separate + * registers for the same bit-elements, so just combine those + * into the existing output field. + * + * Additionally T-Head cores need FS to be enabled when accessing + * the VXRM and VXSAT CSRs, otherwise ending in illegal instructions. + * Though the cores do not implement the VXRM and VXSAT fields in the + * FCSR CSR that vector-0.7.1 specifies. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + dest->vcsr = csr_read(CSR_VXSAT) | csr_read(CSR_VXRM) << CSR_VXRM_SHIFT; + + dest->vlenb = riscv_v_vsize / 32; + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + dest->vcsr = csr_read(CSR_VCSR); + dest->vlenb = csr_read(CSR_VLENB); + } } static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src) @@ -96,9 +166,25 @@ static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src "vsetvl x0, %2, %1\n\t" ".option pop\n\t" "csrw " __stringify(CSR_VSTART) ", %0\n\t" - "csrw " __stringify(CSR_VCSR) ", %3\n\t" - : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl), - "r" (src->vcsr) :); + : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl)); + + if (has_xtheadvector()) { + unsigned long status = csr_read(CSR_SSTATUS); + + /* + * Similar to __vstate_csr_save above, restore values for the + * separate VXRM and VXSAT CSRs from the vcsr variable. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + + csr_write(CSR_VXRM, (src->vcsr >> CSR_VXRM_SHIFT) & CSR_VXRM_MASK); + csr_write(CSR_VXSAT, src->vcsr & CSR_VXSAT_MASK); + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + csr_write(CSR_VCSR, src->vcsr); + } } static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, @@ -108,19 +194,33 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, riscv_v_enable(); __vstate_csr_save(save_to); - asm volatile ( - ".option push\n\t" - ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vse8.v v0, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl) : "r" (datap) : "memory"); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V0T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vse8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } riscv_v_disable(); } @@ -130,19 +230,33 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_ unsigned long vl; riscv_v_enable(); - asm volatile ( - ".option push\n\t" - ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vle8.v v0, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl) : "r" (datap) : "memory"); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V0T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vle8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } __vstate_csr_restore(restore_from); riscv_v_disable(); } @@ -152,33 +266,41 @@ static inline void __riscv_v_vstate_discard(void) unsigned long vl, vtype_inval = 1UL << (BITS_PER_LONG - 1); riscv_v_enable(); + if (has_xtheadvector()) + asm volatile (THEAD_VSETVLI_T4X0E8M8D1 : : : "t4"); + else + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + ".option pop\n\t": "=&r" (vl)); + asm volatile ( ".option push\n\t" ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" "vmv.v.i v0, -1\n\t" "vmv.v.i v8, -1\n\t" "vmv.v.i v16, -1\n\t" "vmv.v.i v24, -1\n\t" "vsetvl %0, x0, %1\n\t" ".option pop\n\t" - : "=&r" (vl) : "r" (vtype_inval) : "memory"); + : "=&r" (vl) : "r" (vtype_inval)); + riscv_v_disable(); } static inline void riscv_v_vstate_discard(struct pt_regs *regs) { - if ((regs->status & SR_VS) == SR_VS_OFF) - return; - - __riscv_v_vstate_discard(); - __riscv_v_vstate_dirty(regs); + if (riscv_v_vstate_query(regs)) { + __riscv_v_vstate_discard(); + __riscv_v_vstate_dirty(regs); + } } static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate, struct pt_regs *regs) { - if ((regs->status & SR_VS) == SR_VS_DIRTY) { + if (__riscv_v_vstate_check(regs->status, DIRTY)) { __riscv_v_vstate_save(vstate, vstate->datap); __riscv_v_vstate_clean(regs); } @@ -187,7 +309,7 @@ static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate, static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate, struct pt_regs *regs) { - if ((regs->status & SR_VS) != SR_VS_OFF) { + if (riscv_v_vstate_query(regs)) { __riscv_v_vstate_restore(vstate, vstate->datap); __riscv_v_vstate_clean(regs); } @@ -196,7 +318,7 @@ static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate, static inline void riscv_v_vstate_set_restore(struct task_struct *task, struct pt_regs *regs) { - if ((regs->status & SR_VS) != SR_VS_OFF) { + if (riscv_v_vstate_query(regs)) { set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE); riscv_v_vstate_on(regs); } @@ -270,6 +392,8 @@ struct pt_regs; static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; } static __always_inline bool has_vector(void) { return false; } static __always_inline bool insn_is_vector(u32 insn_buf) { return false; } +static __always_inline bool has_xtheadvector_no_alternatives(void) { return false; } +static __always_inline bool has_xtheadvector(void) { return false; } static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; } static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; } static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; } diff --git a/arch/riscv/include/asm/vendor_extensions/thead.h b/arch/riscv/include/asm/vendor_extensions/thead.h new file mode 100644 index 000000000000..e85c75b3b340 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H + +#include + +#include + +/* + * Extension keys must be strictly less than RISCV_ISA_VENDOR_EXT_MAX. + */ +#define RISCV_ISA_VENDOR_EXT_XTHEADVECTOR 0 + +extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead; + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void disable_xtheadvector(void); +#else +static inline void disable_xtheadvector(void) { } +#endif + +/* Extension specific helpers */ + +/* + * Vector 0.7.1 as used for example on T-Head Xuantie cores, uses an older + * encoding for vsetvli (ta, ma vs. d1), so provide an instruction for + * vsetvli t4, x0, e8, m8, d1 + */ +#define THEAD_VSETVLI_T4X0E8M8D1 ".long 0x00307ed7\n\t" + +/* + * While in theory, the vector-0.7.1 vsb.v and vlb.v result in the same + * encoding as the standard vse8.v and vle8.v, compilers seem to optimize + * the call resulting in a different encoding and then using a value for + * the "mop" field that is not part of vector-0.7.1 + * So encode specific variants for vstate_save and _restore. + */ +#define THEAD_VSB_V_V0T0 ".long 0x02028027\n\t" +#define THEAD_VSB_V_V8T0 ".long 0x02028427\n\t" +#define THEAD_VSB_V_V16T0 ".long 0x02028827\n\t" +#define THEAD_VSB_V_V24T0 ".long 0x02028c27\n\t" +#define THEAD_VLB_V_V0T0 ".long 0x012028007\n\t" +#define THEAD_VLB_V_V8T0 ".long 0x012028407\n\t" +#define THEAD_VLB_V_V16T0 ".long 0x012028807\n\t" +#define THEAD_VLB_V_V24T0 ".long 0x012028c07\n\t" + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h new file mode 100644 index 000000000000..65a9c5612466 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H + +#include + +#include + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus); +#else +static inline void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + pair->value = 0; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h new file mode 100644 index 000000000000..6b9293e984a9 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2024 Rivos, Inc + */ + +#ifndef _ASM_RISCV_SYS_HWPROBE_H +#define _ASM_RISCV_SYS_HWPROBE_H + +#include + +#define VENDOR_EXT_KEY(ext) \ + do { \ + if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_VENDOR_EXT_##ext)) \ + pair->value |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + else \ + missing |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + } while (false) + +/* + * Loop through and record extensions that 1) anyone has, and 2) anyone + * doesn't have. + * + * _extension_checks is an arbitrary C block to set the values of pair->value + * and missing. It should be filled with VENDOR_EXT_KEY expressions. + */ +#define VENDOR_EXTENSION_SUPPORTED(pair, cpus, per_hart_vendor_bitmap, _extension_checks) \ + do { \ + int cpu; \ + u64 missing = 0; \ + for_each_cpu(cpu, (cpus)) { \ + struct riscv_isavendorinfo *isainfo = &(per_hart_vendor_bitmap)[cpu]; \ + _extension_checks \ + } \ + (pair)->value &= ~missing; \ + } while (false) \ + +#endif /* _ASM_RISCV_SYS_HWPROBE_H */ diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h index 2f2bb0c84f9a..a5150cdf34d8 100644 --- a/arch/riscv/include/asm/vendorid_list.h +++ b/arch/riscv/include/asm/vendorid_list.h @@ -6,6 +6,7 @@ #define ASM_VENDOR_LIST_H #define ANDES_VENDOR_ID 0x31e +#define MICROCHIP_VENDOR_ID 0x029 #define SIFIVE_VENDOR_ID 0x489 #define THEAD_VENDOR_ID 0x5b7 diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 3af142b99f77..c3c1cc951cb9 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* - * Copyright 2023 Rivos, Inc + * Copyright 2023-2024 Rivos, Inc */ #ifndef _UAPI_ASM_HWPROBE_H @@ -94,6 +94,7 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW 2 #define RISCV_HWPROBE_MISALIGNED_VECTOR_FAST 3 #define RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED 4 +#define RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0 11 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ /* Flags */ diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index 3482c9a73d1b..f06bc5efcd79 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -179,6 +179,9 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_SSNPM, KVM_RISCV_ISA_EXT_SVADE, KVM_RISCV_ISA_EXT_SVADU, + KVM_RISCV_ISA_EXT_SVVPTC, + KVM_RISCV_ISA_EXT_ZABHA, + KVM_RISCV_ISA_EXT_ZICCRSE, KVM_RISCV_ISA_EXT_MAX, }; @@ -198,6 +201,7 @@ enum KVM_RISCV_SBI_EXT_ID { KVM_RISCV_SBI_EXT_VENDOR, KVM_RISCV_SBI_EXT_DBCN, KVM_RISCV_SBI_EXT_STA, + KVM_RISCV_SBI_EXT_SUSP, KVM_RISCV_SBI_EXT_MAX, }; @@ -211,9 +215,6 @@ struct kvm_riscv_sbi_sta { #define KVM_RISCV_TIMER_STATE_OFF 0 #define KVM_RISCV_TIMER_STATE_ON 1 -#define KVM_REG_SIZE(id) \ - (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) - /* If you need to interpret the index values, here is the key: */ #define KVM_REG_RISCV_TYPE_MASK 0x00000000FF000000 #define KVM_REG_RISCV_TYPE_SHIFT 24 diff --git a/arch/riscv/include/uapi/asm/vendor/thead.h b/arch/riscv/include/uapi/asm/vendor/thead.h new file mode 100644 index 000000000000..43790ebe5faf --- /dev/null +++ b/arch/riscv/include/uapi/asm/vendor/thead.h @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#define RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR (1 << 0) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 063d1faf5a53..8d186bfced45 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -123,3 +123,5 @@ obj-$(CONFIG_COMPAT) += compat_vdso/ obj-$(CONFIG_64BIT) += pi/ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o + +obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += bugs.o diff --git a/arch/riscv/kernel/bugs.c b/arch/riscv/kernel/bugs.c new file mode 100644 index 000000000000..3655fe7d678c --- /dev/null +++ b/arch/riscv/kernel/bugs.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Rivos Inc. + */ + +#include +#include +#include + +#include +#include + +static enum mitigation_state ghostwrite_state; + +void ghostwrite_set_vulnerable(void) +{ + ghostwrite_state = VULNERABLE; +} + +/* + * Vendor extension alternatives will use the value set at the time of boot + * alternative patching, thus this must be called before boot alternatives are + * patched (and after extension probing) to be effective. + * + * Returns true if mitgated, false otherwise. + */ +bool ghostwrite_enable_mitigation(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR) && + ghostwrite_state == VULNERABLE && !cpu_mitigations_off()) { + disable_xtheadvector(); + ghostwrite_state = MITIGATED; + return true; + } + + return false; +} + +enum mitigation_state ghostwrite_get_state(void) +{ + return ghostwrite_state; +} + +ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) { + switch (ghostwrite_state) { + case UNAFFECTED: + return sprintf(buf, "Not affected\n"); + case MITIGATED: + return sprintf(buf, "Mitigation: xtheadvector disabled\n"); + case VULNERABLE: + fallthrough; + default: + return sprintf(buf, "Vulnerable\n"); + } + } else { + return sprintf(buf, "Not affected\n"); + } +} diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index c0916ed318c2..c6ba750536c3 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -26,6 +27,7 @@ #include #include #include +#include #define NUM_ALPHA_EXTS ('z' - 'a' + 1) @@ -39,6 +41,8 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; /* Per-cpu ISA extensions. */ struct riscv_isainfo hart_isa[NR_CPUS]; +u32 thead_vlenb_of; + /** * riscv_isa_extension_base() - Get base extension word * @@ -791,9 +795,50 @@ static void __init riscv_fill_vendor_ext_list(int cpu) } } +static int has_thead_homogeneous_vlenb(void) +{ + int cpu; + u32 prev_vlenb = 0; + u32 vlenb; + + /* Ignore thead,vlenb property if xtheavector is not enabled in the kernel */ + if (!IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return 0; + + for_each_possible_cpu(cpu) { + struct device_node *cpu_node; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) { + pr_warn("Unable to find cpu node\n"); + return -ENOENT; + } + + if (of_property_read_u32(cpu_node, "thead,vlenb", &vlenb)) { + of_node_put(cpu_node); + + if (prev_vlenb) + return -ENOENT; + continue; + } + + if (prev_vlenb && vlenb != prev_vlenb) { + of_node_put(cpu_node); + return -ENOENT; + } + + prev_vlenb = vlenb; + of_node_put(cpu_node); + } + + thead_vlenb_of = vlenb; + return 0; +} + static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) { unsigned int cpu; + bool mitigated; for_each_possible_cpu(cpu) { unsigned long this_hwcap = 0; @@ -844,6 +889,17 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) riscv_fill_vendor_ext_list(cpu); } + /* + * Execute ghostwrite mitigation immediately after detecting extensions + * to disable xtheadvector if necessary. + */ + mitigated = ghostwrite_enable_mitigation(); + + if (!mitigated && has_xtheadvector_no_alternatives() && has_thead_homogeneous_vlenb() < 0) { + pr_warn("Unsupported heterogeneous vlenb detected, vector extension disabled.\n"); + disable_xtheadvector(); + } + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) return -ENOENT; @@ -896,7 +952,8 @@ void __init riscv_fill_hwcap(void) elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } - if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_ZVE32X)) { + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_ZVE32X) || + has_xtheadvector_no_alternatives()) { /* * This cannot fail when called on the boot hart */ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index c200d329d4bd..33a5a9f2a0d4 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -23,21 +23,21 @@ REG_S a0, TASK_TI_A0(tp) csrr a0, CSR_CAUSE /* Exclude IRQs */ - blt a0, zero, _new_vmalloc_restore_context_a0 + blt a0, zero, .Lnew_vmalloc_restore_context_a0 REG_S a1, TASK_TI_A1(tp) /* Only check new_vmalloc if we are in page/protection fault */ li a1, EXC_LOAD_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_STORE_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_INST_PAGE_FAULT - bne a0, a1, _new_vmalloc_restore_context_a1 + bne a0, a1, .Lnew_vmalloc_restore_context_a1 -_new_vmalloc_kernel_address: +.Lnew_vmalloc_kernel_address: /* Is it a kernel address? */ csrr a0, CSR_TVAL - bge a0, zero, _new_vmalloc_restore_context_a1 + bge a0, zero, .Lnew_vmalloc_restore_context_a1 /* Check if a new vmalloc mapping appeared that could explain the trap */ REG_S a2, TASK_TI_A2(tp) @@ -69,7 +69,7 @@ _new_vmalloc_kernel_address: /* Check the value of new_vmalloc for this cpu */ REG_L a2, 0(a0) and a2, a2, a1 - beq a2, zero, _new_vmalloc_restore_context + beq a2, zero, .Lnew_vmalloc_restore_context /* Atomically reset the current cpu bit in new_vmalloc */ amoxor.d a0, a1, (a0) @@ -83,11 +83,11 @@ _new_vmalloc_kernel_address: csrw CSR_SCRATCH, x0 sret -_new_vmalloc_restore_context: +.Lnew_vmalloc_restore_context: REG_L a2, TASK_TI_A2(tp) -_new_vmalloc_restore_context_a1: +.Lnew_vmalloc_restore_context_a1: REG_L a1, TASK_TI_A1(tp) -_new_vmalloc_restore_context_a0: +.Lnew_vmalloc_restore_context_a0: REG_L a0, TASK_TI_A0(tp) .endm @@ -278,6 +278,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception) #else sret #endif +SYM_INNER_LABEL(ret_from_exception_end, SYM_L_GLOBAL) SYM_CODE_END(ret_from_exception) ASM_NOKPROBE(ret_from_exception) diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 8cb9b211611d..3524db5e4fa0 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -214,7 +214,22 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - prepare_ftrace_return(&arch_ftrace_regs(fregs)->ra, ip, arch_ftrace_regs(fregs)->s0); + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long frame_pointer = arch_ftrace_regs(fregs)->s0; + unsigned long *parent = &arch_ftrace_regs(fregs)->ra; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + /* + * We don't suffer access faults, so no extra fault-recovery assembly + * is needed here. + */ + old = *parent; + + if (!function_graph_enter_regs(old, ip, frame_pointer, parent, fregs)) + *parent = return_hooker; } #else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ extern void ftrace_graph_call(void); diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c index 6afe80c7f03a..99972a48e86b 100644 --- a/arch/riscv/kernel/kernel_mode_vector.c +++ b/arch/riscv/kernel/kernel_mode_vector.c @@ -143,7 +143,7 @@ static int riscv_v_start_kernel_context(bool *is_nested) /* Transfer the ownership of V from user to kernel, then save */ riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY); - if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) { + if (__riscv_v_vstate_check(task_pt_regs(current)->status, DIRTY)) { uvstate = ¤t->thread.vstate; __riscv_v_vstate_save(uvstate, uvstate->datap); } @@ -160,7 +160,7 @@ asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs) return; depth = riscv_v_ctx_get_depth(); - if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY) + if (depth == 0 && __riscv_v_vstate_check(regs->status, DIRTY)) riscv_preempt_v_set_dirty(); riscv_v_ctx_depth_inc(); @@ -208,7 +208,7 @@ void kernel_vector_begin(void) { bool nested = false; - if (WARN_ON(!has_vector())) + if (WARN_ON(!(has_vector() || has_xtheadvector()))) return; BUG_ON(!may_use_simd()); @@ -236,7 +236,7 @@ EXPORT_SYMBOL_GPL(kernel_vector_begin); */ void kernel_vector_end(void) { - if (WARN_ON(!has_vector())) + if (WARN_ON(!(has_vector() || has_xtheadvector()))) return; riscv_v_disable(); diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index 3c830a6f7ef4..2306ce3e5f22 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -114,29 +114,6 @@ void machine_shutdown(void) #endif } -static void machine_kexec_mask_interrupts(void) -{ - unsigned int i; - struct irq_desc *desc; - - for_each_irq_desc(i, desc) { - struct irq_chip *chip; - - chip = irq_desc_get_chip(desc); - if (!chip) - continue; - - if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) - chip->irq_eoi(&desc->irq_data); - - if (chip->irq_mask) - chip->irq_mask(&desc->irq_data); - - if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) - chip->irq_disable(&desc->irq_data); - } -} - /* * machine_crash_shutdown - Prepare to kexec after a kernel crash * diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index 3a42f6287909..068168046e0e 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -12,6 +12,8 @@ #include #include +#define ABI_SIZE_ON_STACK 80 + .text .macro SAVE_ABI_STATE @@ -26,12 +28,12 @@ * register if a0 was not saved. */ .macro SAVE_RET_ABI_STATE - addi sp, sp, -4*SZREG - REG_S s0, 2*SZREG(sp) - REG_S ra, 3*SZREG(sp) - REG_S a0, 1*SZREG(sp) - REG_S a1, 0*SZREG(sp) - addi s0, sp, 4*SZREG + addi sp, sp, -ABI_SIZE_ON_STACK + REG_S ra, 1*SZREG(sp) + REG_S s0, 8*SZREG(sp) + REG_S a0, 10*SZREG(sp) + REG_S a1, 11*SZREG(sp) + addi s0, sp, ABI_SIZE_ON_STACK .endm .macro RESTORE_ABI_STATE @@ -41,11 +43,11 @@ .endm .macro RESTORE_RET_ABI_STATE - REG_L ra, 3*SZREG(sp) - REG_L s0, 2*SZREG(sp) - REG_L a0, 1*SZREG(sp) - REG_L a1, 0*SZREG(sp) - addi sp, sp, 4*SZREG + REG_L ra, 1*SZREG(sp) + REG_L s0, 8*SZREG(sp) + REG_L a0, 10*SZREG(sp) + REG_L a1, 11*SZREG(sp) + addi sp, sp, ABI_SIZE_ON_STACK .endm SYM_TYPED_FUNC_START(ftrace_stub) diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 1cd461f3d872..47d0ebeec93c 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -23,7 +23,7 @@ struct used_bucket { struct relocation_head { struct hlist_node node; - struct list_head *rel_entry; + struct list_head rel_entry; void *location; }; @@ -634,7 +634,7 @@ process_accumulated_relocations(struct module *me, location = rel_head_iter->location; list_for_each_entry_safe(rel_entry_iter, rel_entry_iter_tmp, - rel_head_iter->rel_entry, + &rel_head_iter->rel_entry, head) { curr_type = rel_entry_iter->type; reloc_handlers[curr_type].reloc_handler( @@ -704,16 +704,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, return -ENOMEM; } - rel_head->rel_entry = - kmalloc(sizeof(struct list_head), GFP_KERNEL); - - if (!rel_head->rel_entry) { - kfree(entry); - kfree(rel_head); - return -ENOMEM; - } - - INIT_LIST_HEAD(rel_head->rel_entry); + INIT_LIST_HEAD(&rel_head->rel_entry); rel_head->location = location; INIT_HLIST_NODE(&rel_head->node); if (!current_head->first) { @@ -722,7 +713,6 @@ static int add_relocation_to_accumulate(struct module *me, int type, if (!bucket) { kfree(entry); - kfree(rel_head->rel_entry); kfree(rel_head); return -ENOMEM; } @@ -735,7 +725,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, } /* Add relocation to head of discovered rel_head */ - list_add_tail(&entry->head, rel_head->rel_entry); + list_add_tail(&entry->head, &rel_head->rel_entry); return 0; } diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 380a0e8cecc0..c0738d6c6498 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -30,7 +30,7 @@ static void __kprobes arch_prepare_ss_slot(struct kprobe *p) p->ainsn.api.restore = (unsigned long)p->addr + len; patch_text_nosync(p->ainsn.api.insn, &p->opcode, len); - patch_text_nosync(p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); + patch_text_nosync((void *)p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); } static void __kprobes arch_prepare_simulate(struct kprobe *p) diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 58b6482c2bf6..7c244de77180 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -190,7 +190,7 @@ void flush_thread(void) void arch_release_task_struct(struct task_struct *tsk) { /* Free the vector context of datap. */ - if (has_vector()) + if (has_vector() || has_xtheadvector()) riscv_v_thread_free(tsk); } @@ -240,7 +240,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.s[0] = 0; } p->thread.riscv_v_flags = 0; - if (has_vector()) + if (has_vector() || has_xtheadvector()) riscv_v_thread_alloc(p); p->thread.ra = (unsigned long)ret_from_fork; p->thread.sp = (unsigned long)childregs; /* kernel sp */ @@ -364,7 +364,7 @@ static bool try_to_set_pmm(unsigned long value) * disable it for tasks that already opted in to the relaxed ABI. */ -static struct ctl_table tagged_addr_sysctl_table[] = { +static const struct ctl_table tagged_addr_sysctl_table[] = { { .procname = "tagged_addr_disabled", .mode = 0644, diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 45010e71df86..f1793630fc51 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -147,9 +147,7 @@ static void __init init_resources(void) res_idx = num_resources - 1; mem_res_sz = num_resources * sizeof(*mem_res); - mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); - if (!mem_res) - panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); + mem_res = memblock_alloc_or_panic(mem_res_sz, SMP_CACHE_BYTES); /* * Start by adding the reserved regions, if they overlap diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index dcd282419456..94e905eea1de 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -189,7 +189,7 @@ static long restore_sigcontext(struct pt_regs *regs, return 0; case RISCV_V_MAGIC: - if (!has_vector() || !riscv_v_vstate_query(regs) || + if (!(has_vector() || has_xtheadvector()) || !riscv_v_vstate_query(regs) || size != riscv_v_sc_size) return -EINVAL; @@ -211,7 +211,7 @@ static size_t get_rt_frame_size(bool cal_all) frame_size = sizeof(*frame); - if (has_vector()) { + if (has_vector() || has_xtheadvector()) { if (cal_all || riscv_v_vstate_query(task_pt_regs(current))) total_context_size += riscv_v_sc_size; } @@ -284,7 +284,7 @@ static long setup_sigcontext(struct rt_sigframe __user *frame, if (has_fpu()) err |= save_fp_state(regs, &sc->sc_fpregs); /* Save the vector state. */ - if (has_vector() && riscv_v_vstate_query(regs)) + if ((has_vector() || has_xtheadvector()) && riscv_v_vstate_query(regs)) err |= save_v_state(regs, (void __user **)&sc_ext_ptr); /* Write zero to fp-reserved space and check it on restore_sigcontext */ err |= __put_user(0, &sc->sc_extdesc.reserved); diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index c180a647a30e..d58b5e751286 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -43,6 +43,7 @@ enum ipi_message_type { unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = { [0 ... NR_CPUS-1] = INVALID_HARTID }; +EXPORT_SYMBOL_GPL(__cpuid_to_hartid_map); void __init smp_setup_processor_id(void) { diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 153a2db4c5fa..d4355c770c36 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -17,6 +17,7 @@ #ifdef CONFIG_FRAME_POINTER extern asmlinkage void handle_exception(void); +extern unsigned long ret_from_exception_end; static inline int fp_is_valid(unsigned long fp, unsigned long sp) { @@ -71,7 +72,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame->fp; pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, &frame->ra); - if (pc == (unsigned long)handle_exception) { + if (pc >= (unsigned long)handle_exception && + pc < (unsigned long)&ret_from_exception_end) { if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) break; diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index cb93adfffc48..bcd3b816306c 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -15,6 +15,7 @@ #include #include #include +#include #include @@ -286,6 +287,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, pair->value = riscv_timebase; break; + case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0: + hwprobe_isa_vendor_ext_thead_0(pair, cpus); + break; + /* * For forward compatibility, unknown keys don't fail the whole * call, but get their element key set to -1 and value set to 0 diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 51ebfd23e007..8ff8e8b36524 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -35,7 +35,7 @@ int show_unhandled_signals = 1; -static DEFINE_SPINLOCK(die_lock); +static DEFINE_RAW_SPINLOCK(die_lock); static int copy_code(struct pt_regs *regs, u16 *val, const u16 *insns) { @@ -81,7 +81,7 @@ void die(struct pt_regs *regs, const char *str) oops_enter(); - spin_lock_irqsave(&die_lock, flags); + raw_spin_lock_irqsave(&die_lock, flags); console_verbose(); bust_spinlocks(1); @@ -100,7 +100,7 @@ void die(struct pt_regs *regs, const char *str) bust_spinlocks(0); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irqrestore(&die_lock, flags); + raw_spin_unlock_irqrestore(&die_lock, flags); oops_exit(); if (in_interrupt()) diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c index 821818886fab..184f780c932d 100644 --- a/arch/riscv/kernel/vector.c +++ b/arch/riscv/kernel/vector.c @@ -33,7 +33,17 @@ int riscv_v_setup_vsize(void) { unsigned long this_vsize; - /* There are 32 vector registers with vlenb length. */ + /* + * There are 32 vector registers with vlenb length. + * + * If the thead,vlenb property was provided by the firmware, use that + * instead of probing the CSRs. + */ + if (thead_vlenb_of) { + riscv_v_vsize = thead_vlenb_of * 32; + return 0; + } + riscv_v_enable(); this_vsize = csr_read(CSR_VLENB) * 32; riscv_v_disable(); @@ -53,7 +63,7 @@ int riscv_v_setup_vsize(void) void __init riscv_v_setup_ctx_cache(void) { - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return; riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx", @@ -173,7 +183,7 @@ bool riscv_v_first_use_handler(struct pt_regs *regs) u32 __user *epc = (u32 __user *)regs->epc; u32 insn = (u32)regs->badaddr; - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return false; /* Do not handle if V is not supported, or disabled */ @@ -216,7 +226,7 @@ void riscv_v_vstate_ctrl_init(struct task_struct *tsk) bool inherit; int cur, next; - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return; next = riscv_v_ctrl_get_next(tsk); @@ -238,7 +248,7 @@ void riscv_v_vstate_ctrl_init(struct task_struct *tsk) long riscv_v_vstate_ctrl_get_current(void) { - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return -EINVAL; return current->thread.vstate_ctrl & PR_RISCV_V_VSTATE_CTRL_MASK; @@ -249,7 +259,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg) bool inherit; int cur, next; - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return -EINVAL; if (arg & ~PR_RISCV_V_VSTATE_CTRL_MASK) @@ -287,7 +297,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg) #ifdef CONFIG_SYSCTL -static struct ctl_table riscv_v_default_vstate_table[] = { +static const struct ctl_table riscv_v_default_vstate_table[] = { { .procname = "riscv_v_default_allow", .data = &riscv_v_implicit_uacc, @@ -299,7 +309,7 @@ static struct ctl_table riscv_v_default_vstate_table[] = { static int __init riscv_v_sysctl_init(void) { - if (has_vector()) + if (has_vector() || has_xtheadvector()) if (!register_sysctl("abi", riscv_v_default_vstate_table)) return -EINVAL; return 0; @@ -309,7 +319,7 @@ static int __init riscv_v_sysctl_init(void) static int __init riscv_v_sysctl_init(void) { return 0; } #endif /* ! CONFIG_SYSCTL */ -static int riscv_v_init(void) +static int __init riscv_v_init(void) { return riscv_v_sysctl_init(); } diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c index a8126d118341..a31ff84740eb 100644 --- a/arch/riscv/kernel/vendor_extensions.c +++ b/arch/riscv/kernel/vendor_extensions.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -14,6 +15,9 @@ struct riscv_isa_vendor_ext_data_list *riscv_isa_vendor_ext_list[] = { #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES &riscv_isa_vendor_ext_list_andes, #endif +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD + &riscv_isa_vendor_ext_list_thead, +#endif }; const size_t riscv_isa_vendor_ext_list_size = ARRAY_SIZE(riscv_isa_vendor_ext_list); @@ -41,6 +45,12 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig cpu_bmap = riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap; break; #endif + #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD + case THEAD_VENDOR_ID: + bmap = &riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap; + cpu_bmap = riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap; + break; + #endif default: return false; } diff --git a/arch/riscv/kernel/vendor_extensions/Makefile b/arch/riscv/kernel/vendor_extensions/Makefile index 6a61aed944f1..866414c81a9f 100644 --- a/arch/riscv/kernel/vendor_extensions/Makefile +++ b/arch/riscv/kernel/vendor_extensions/Makefile @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_ANDES) += andes.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD) += thead.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD) += thead_hwprobe.o diff --git a/arch/riscv/kernel/vendor_extensions/thead.c b/arch/riscv/kernel/vendor_extensions/thead.c new file mode 100644 index 000000000000..519dbf70710a --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/thead.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +#include +#include +#include + +/* All T-Head vendor extensions supported in Linux */ +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_thead[] = { + __RISCV_ISA_EXT_DATA(xtheadvector, RISCV_ISA_VENDOR_EXT_XTHEADVECTOR), +}; + +struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead = { + .ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_thead), + .ext_data = riscv_isa_vendor_ext_thead, +}; + +void disable_xtheadvector(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap[cpu].isa); + + clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap.isa); +} diff --git a/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c new file mode 100644 index 000000000000..2eba34011786 --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +#include +#include + +#include +#include + +void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus) +{ + VENDOR_EXTENSION_SUPPORTED(pair, cpus, + riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap, { + VENDOR_EXT_KEY(XTHEADVECTOR); + }); +} diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 0fb1840c3e0a..4e0bba91d284 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -30,6 +30,7 @@ kvm-y += vcpu_sbi_hsm.o kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_sbi_pmu.o kvm-y += vcpu_sbi_replace.o kvm-y += vcpu_sbi_sta.o +kvm-y += vcpu_sbi_system.o kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o kvm-y += vcpu_switch.o kvm-y += vcpu_timer.o diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index e048dcc6e65e..60d684c76c58 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -34,7 +34,12 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, csr_exit_user), STATS_DESC_COUNTER(VCPU, csr_exit_kernel), STATS_DESC_COUNTER(VCPU, signal_exits), - STATS_DESC_COUNTER(VCPU, exits) + STATS_DESC_COUNTER(VCPU, exits), + STATS_DESC_COUNTER(VCPU, instr_illegal_exits), + STATS_DESC_COUNTER(VCPU, load_misaligned_exits), + STATS_DESC_COUNTER(VCPU, store_misaligned_exits), + STATS_DESC_COUNTER(VCPU, load_access_exits), + STATS_DESC_COUNTER(VCPU, store_access_exits), }; const struct kvm_stats_header kvm_vcpu_stats_header = { diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index fa98e5c024b2..6e0c18412795 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -165,6 +165,17 @@ void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, vcpu->arch.guest_context.sstatus |= SR_SPP; } +static inline int vcpu_redirect(struct kvm_vcpu *vcpu, struct kvm_cpu_trap *trap) +{ + int ret = -EFAULT; + + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) { + kvm_riscv_vcpu_trap_redirect(vcpu, trap); + ret = 1; + } + return ret; +} + /* * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on * proper exit to userspace. @@ -183,14 +194,32 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, run->exit_reason = KVM_EXIT_UNKNOWN; switch (trap->scause) { case EXC_INST_ILLEGAL: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_ILLEGAL_INSN); + vcpu->stat.instr_illegal_exits++; + ret = vcpu_redirect(vcpu, trap); + break; case EXC_LOAD_MISALIGNED: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_MISALIGNED_LOAD); + vcpu->stat.load_misaligned_exits++; + ret = vcpu_redirect(vcpu, trap); + break; case EXC_STORE_MISALIGNED: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_MISALIGNED_STORE); + vcpu->stat.store_misaligned_exits++; + ret = vcpu_redirect(vcpu, trap); + break; case EXC_LOAD_ACCESS: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_ACCESS_LOAD); + vcpu->stat.load_access_exits++; + ret = vcpu_redirect(vcpu, trap); + break; case EXC_STORE_ACCESS: - if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) { - kvm_riscv_vcpu_trap_redirect(vcpu, trap); - ret = 1; - } + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_ACCESS_STORE); + vcpu->stat.store_access_exits++; + ret = vcpu_redirect(vcpu, trap); + break; + case EXC_INST_ACCESS: + ret = vcpu_redirect(vcpu, trap); break; case EXC_VIRTUAL_INST_FAULT: if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index 753f66c8b70a..f6d27b59c641 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -46,6 +46,8 @@ static const unsigned long kvm_isa_ext_arr[] = { KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), KVM_ISA_EXT_ARR(SVPBMT), + KVM_ISA_EXT_ARR(SVVPTC), + KVM_ISA_EXT_ARR(ZABHA), KVM_ISA_EXT_ARR(ZACAS), KVM_ISA_EXT_ARR(ZAWRS), KVM_ISA_EXT_ARR(ZBA), @@ -65,6 +67,7 @@ static const unsigned long kvm_isa_ext_arr[] = { KVM_ISA_EXT_ARR(ZFHMIN), KVM_ISA_EXT_ARR(ZICBOM), KVM_ISA_EXT_ARR(ZICBOZ), + KVM_ISA_EXT_ARR(ZICCRSE), KVM_ISA_EXT_ARR(ZICNTR), KVM_ISA_EXT_ARR(ZICOND), KVM_ISA_EXT_ARR(ZICSR), @@ -145,6 +148,8 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) case KVM_RISCV_ISA_EXT_SSTC: case KVM_RISCV_ISA_EXT_SVINVAL: case KVM_RISCV_ISA_EXT_SVNAPOT: + case KVM_RISCV_ISA_EXT_SVVPTC: + case KVM_RISCV_ISA_EXT_ZABHA: case KVM_RISCV_ISA_EXT_ZACAS: case KVM_RISCV_ISA_EXT_ZAWRS: case KVM_RISCV_ISA_EXT_ZBA: @@ -162,6 +167,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) case KVM_RISCV_ISA_EXT_ZFA: case KVM_RISCV_ISA_EXT_ZFH: case KVM_RISCV_ISA_EXT_ZFHMIN: + case KVM_RISCV_ISA_EXT_ZICCRSE: case KVM_RISCV_ISA_EXT_ZICNTR: case KVM_RISCV_ISA_EXT_ZICOND: case KVM_RISCV_ISA_EXT_ZICSR: diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 6e704ed86a83..d1c83a77735e 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -70,6 +70,10 @@ static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = { .ext_idx = KVM_RISCV_SBI_EXT_DBCN, .ext_ptr = &vcpu_sbi_ext_dbcn, }, + { + .ext_idx = KVM_RISCV_SBI_EXT_SUSP, + .ext_ptr = &vcpu_sbi_ext_susp, + }, { .ext_idx = KVM_RISCV_SBI_EXT_STA, .ext_ptr = &vcpu_sbi_ext_sta, diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c new file mode 100644 index 000000000000..5d55e08791fa --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_system.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024 Ventana Micro Systems Inc. + */ + +#include + +#include +#include + +static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_cpu_context *reset_cntx; + unsigned long funcid = cp->a6; + unsigned long hva, i; + struct kvm_vcpu *tmp; + + switch (funcid) { + case SBI_EXT_SUSP_SYSTEM_SUSPEND: + if (cp->a0 != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + + if (!(cp->sstatus & SR_SPP)) { + retdata->err_val = SBI_ERR_FAILURE; + return 0; + } + + hva = kvm_vcpu_gfn_to_hva_prot(vcpu, cp->a1 >> PAGE_SHIFT, NULL); + if (kvm_is_error_hva(hva)) { + retdata->err_val = SBI_ERR_INVALID_ADDRESS; + return 0; + } + + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (tmp == vcpu) + continue; + if (!kvm_riscv_vcpu_stopped(tmp)) { + retdata->err_val = SBI_ERR_DENIED; + return 0; + } + } + + spin_lock(&vcpu->arch.reset_cntx_lock); + reset_cntx = &vcpu->arch.guest_reset_context; + reset_cntx->sepc = cp->a1; + reset_cntx->a0 = vcpu->vcpu_id; + reset_cntx->a1 = cp->a2; + spin_unlock(&vcpu->arch.reset_cntx_lock); + + kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); + + /* userspace provides the suspend implementation */ + kvm_riscv_vcpu_sbi_forward(vcpu, run); + retdata->uexit = true; + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + break; + } + + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp = { + .extid_start = SBI_EXT_SUSP, + .extid_end = SBI_EXT_SUSP, + .default_disabled = true, + .handler = kvm_sbi_ext_susp_handler, +}; diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 8eec6b69a875..79368a895fee 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -15,8 +15,7 @@ endif lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o -lib-$(CONFIG_RISCV_ISA_ZBC) += crc32.o - +obj-$(CONFIG_CRC32_ARCH) += crc32-riscv.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_RISCV_ISA_V) += xor.o lib-$(CONFIG_RISCV_ISA_V) += riscv_v_helpers.o diff --git a/arch/riscv/lib/crc32.c b/arch/riscv/lib/crc32-riscv.c similarity index 91% rename from arch/riscv/lib/crc32.c rename to arch/riscv/lib/crc32-riscv.c index d7dc599af3ef..53d56ab422c7 100644 --- a/arch/riscv/lib/crc32.c +++ b/arch/riscv/lib/crc32-riscv.c @@ -14,6 +14,7 @@ #include #include #include +#include /* * Refer to https://www.corsix.org/content/barrett-reduction-polynomials for @@ -217,17 +218,19 @@ legacy: return crc_fb(crc, p, len); } -u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) +u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len) { return crc32_le_generic(crc, p, len, CRC32_POLY_LE, CRC32_POLY_QT_LE, crc32_le_base); } +EXPORT_SYMBOL(crc32_le_arch); -u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) +u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len) { return crc32_le_generic(crc, p, len, CRC32C_POLY_LE, - CRC32C_POLY_QT_LE, __crc32c_le_base); + CRC32C_POLY_QT_LE, crc32c_le_base); } +EXPORT_SYMBOL(crc32c_le_arch); static inline u32 crc32_be_unaligned(u32 crc, unsigned char const *p, size_t len) @@ -253,7 +256,7 @@ static inline u32 crc32_be_unaligned(u32 crc, unsigned char const *p, return crc; } -u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) +u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len) { size_t offset, head_len, tail_len; unsigned long const *p_ul; @@ -292,3 +295,17 @@ u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) legacy: return crc32_be_base(crc, p, len); } +EXPORT_SYMBOL(crc32_be_arch); + +u32 crc32_optimizations(void) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return CRC32_LE_OPTIMIZATION | + CRC32_BE_OPTIMIZATION | + CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Accelerated CRC32 implementation with Zbc extension"); diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index a9f2b4af8f3f..0194324a0c50 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -22,6 +22,57 @@ #include "../kernel/head.h" +static void show_pte(unsigned long addr) +{ + pgd_t *pgdp, pgd; + p4d_t *p4dp, p4d; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; + struct mm_struct *mm = current->mm; + + if (!mm) + mm = &init_mm; + + pr_alert("Current %s pgtable: %luK pagesize, %d-bit VAs, pgdp=0x%016llx\n", + current->comm, PAGE_SIZE / SZ_1K, VA_BITS, + mm == &init_mm ? (u64)__pa_symbol(mm->pgd) : virt_to_phys(mm->pgd)); + + pgdp = pgd_offset(mm, addr); + pgd = pgdp_get(pgdp); + pr_alert("[%016lx] pgd=%016lx", addr, pgd_val(pgd)); + if (pgd_none(pgd) || pgd_bad(pgd) || pgd_leaf(pgd)) + goto out; + + p4dp = p4d_offset(pgdp, addr); + p4d = p4dp_get(p4dp); + pr_cont(", p4d=%016lx", p4d_val(p4d)); + if (p4d_none(p4d) || p4d_bad(p4d) || p4d_leaf(p4d)) + goto out; + + pudp = pud_offset(p4dp, addr); + pud = pudp_get(pudp); + pr_cont(", pud=%016lx", pud_val(pud)); + if (pud_none(pud) || pud_bad(pud) || pud_leaf(pud)) + goto out; + + pmdp = pmd_offset(pudp, addr); + pmd = pmdp_get(pmdp); + pr_cont(", pmd=%016lx", pmd_val(pmd)); + if (pmd_none(pmd) || pmd_bad(pmd) || pmd_leaf(pmd)) + goto out; + + ptep = pte_offset_map(pmdp, addr); + if (!ptep) + goto out; + + pte = ptep_get(ptep); + pr_cont(", pte=%016lx", pte_val(pte)); + pte_unmap(ptep); +out: + pr_cont("\n"); +} + static void die_kernel_fault(const char *msg, unsigned long addr, struct pt_regs *regs) { @@ -31,6 +82,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, addr); bust_spinlocks(0); + show_pte(addr); die(regs, "Oops"); make_task_dead(SIGKILL); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index fc53ce748c80..15b2eda4c364 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include "../kernel/head.h" @@ -62,6 +63,13 @@ EXPORT_SYMBOL(pgtable_l5_enabled); phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define VMEMMAP_ADDR_ALIGN (1ULL << SECTION_SIZE_BITS) + +unsigned long vmemmap_start_pfn __ro_after_init; +EXPORT_SYMBOL(vmemmap_start_pfn); +#endif + unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); @@ -240,8 +248,12 @@ static void __init setup_bootmem(void) * Make sure we align the start of the memory on a PMD boundary so that * at worst, we map the linear mapping with PMD mappings. */ - if (!IS_ENABLED(CONFIG_XIP_KERNEL)) + if (!IS_ENABLED(CONFIG_XIP_KERNEL)) { phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif + } /* * In 64-bit, any use of __va/__pa before this point is wrong as we @@ -256,8 +268,12 @@ static void __init setup_bootmem(void) */ if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) { max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE; - memblock_cap_memory_range(phys_ram_base, - max_mapped_addr - phys_ram_base); + if (memblock_end_of_DRAM() > max_mapped_addr) { + memblock_cap_memory_range(phys_ram_base, + max_mapped_addr - phys_ram_base); + pr_warn("Physical memory overflows the linear mapping size: region above %pa removed", + &max_mapped_addr); + } } /* @@ -1101,6 +1117,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); phys_ram_base = CONFIG_PHYS_RAM_BASE; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); @@ -1558,7 +1577,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) return; } - pagetable_pte_dtor(ptdesc); + pagetable_dtor(ptdesc); if (PageReserved(page)) free_reserved_page(page); else @@ -1580,7 +1599,7 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemm } if (!is_vmemmap) - pagetable_pmd_dtor(ptdesc); + pagetable_dtor(ptdesc); if (PageReserved(page)) free_reserved_page(page); else diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index c301c8d291d2..41c635d6aca4 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -32,7 +32,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned pte_t *ptep, *p; if (pmd_none(pmdp_get(pmd))) { - p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); + p = memblock_alloc_or_panic(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -54,7 +54,7 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned unsigned long next; if (pud_none(pudp_get(pud))) { - p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); + p = memblock_alloc_or_panic(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -85,7 +85,7 @@ static void __init kasan_populate_pud(p4d_t *p4d, unsigned long next; if (p4d_none(p4dp_get(p4d))) { - p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); + p = memblock_alloc_or_panic(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -116,7 +116,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd, unsigned long next; if (pgd_none(pgdp_get(pgd))) { - p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE); + p = memblock_alloc_or_panic(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE); set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -385,7 +385,7 @@ static void __init kasan_shallow_populate_pud(p4d_t *p4d, next = pud_addr_end(vaddr, end); if (pud_none(pudp_get(pud_k))) { - p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; } @@ -405,7 +405,7 @@ static void __init kasan_shallow_populate_p4d(pgd_t *pgd, next = p4d_addr_end(vaddr, end); if (p4d_none(p4dp_get(p4d_k))) { - p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; } @@ -424,7 +424,7 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long next = pgd_addr_end(vaddr, end); if (pgd_none(pgdp_get(pgd_k))) { - p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 0077969170e8..9c9ec08d78c7 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -52,13 +52,19 @@ config KASAN_SHADOW_OFFSET depends on KASAN default 0x1C000000000000 -config GCC_ASM_FLAG_OUTPUT_BROKEN +config CC_ASM_FLAG_OUTPUT_BROKEN def_bool CC_IS_GCC && GCC_VERSION < 140200 help GCC versions before 14.2.0 may die with an internal compiler error in some configurations if flag output operands are used within inline assemblies. +config CC_HAS_ASM_AOR_FORMAT_FLAGS + def_bool !(CC_IS_CLANG && CLANG_VERSION < 190100) + help + Clang versions before 19.1.0 do not support A, + O, and R inline assembly format flags. + config S390 def_bool y # @@ -72,6 +78,8 @@ config S390 select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 + select ARCH_HAS_CPU_FINALIZE_INIT + select ARCH_HAS_CRC32 select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE @@ -183,16 +191,18 @@ config S390 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_FTRACE_REGS_HAVING_PT_REGS select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT if HAVE_MARCH_Z196_FEATURES select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_GUP_FAST select HAVE_FENTRY + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION - select HAVE_FUNCTION_GRAPH_RETVAL + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS @@ -233,6 +243,7 @@ config S390 select HAVE_VIRT_CPU_ACCOUNTING_IDLE select IOMMU_HELPER if PCI select IOMMU_SUPPORT if PCI + select KASAN_VMALLOC if KASAN select LOCK_MM_AND_FIND_VMA select MMU_GATHER_MERGE_VMAS select MMU_GATHER_NO_GATHER @@ -240,6 +251,7 @@ config S390 select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PCI select NEED_PER_CPU_EMBED_FIRST_CHUNK + select NEED_PROC_VMCORE_DEVICE_RAM if PROC_VMCORE select NEED_SG_DMA_LENGTH if PCI select OLD_SIGACTION select OLD_SIGSUSPEND3 @@ -255,6 +267,7 @@ config S390 select USER_STACKTRACE_SUPPORT select VDSO_GETRANDOM select VIRT_CPU_ACCOUNTING + select VMAP_STACK select ZONE_DMA # Note: keep the above list sorted alphabetically @@ -688,32 +701,6 @@ config MAX_PHYSMEM_BITS Increasing the number of bits also increases the kernel image size. By default 46 bits (64TB) are supported. -config CHECK_STACK - def_bool y - depends on !VMAP_STACK - prompt "Detect kernel stack overflow" - help - This option enables the compiler option -mstack-guard and - -mstack-size if they are available. If the compiler supports them - it will emit additional code to each function prolog to trigger - an illegal operation if the kernel stack is about to overflow. - - Say N if you are unsure. - -config STACK_GUARD - int "Size of the guard area (128-1024)" - range 128 1024 - depends on CHECK_STACK - default "256" - help - This allows you to specify the size of the guard area at the lower - end of the kernel stack. If the kernel stack points into the guard - area on function entry an illegal operation is triggered. The size - needs to be a power of 2. Please keep in mind that the size of an - interrupt frame is 184 bytes for 31 bit and 328 bytes on 64 bit. - The minimum size for the stack guard should be 256 for 31 bit and - 512 for 64 bit. - endmenu menu "I/O subsystem" diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 7fd57398221e..5fae311203c2 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -22,7 +22,7 @@ KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__ ifndef CONFIG_AS_IS_LLVM KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf)) endif -KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack +KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack -std=gnu11 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY KBUILD_CFLAGS_DECOMPRESSOR += -D__DECOMPRESSOR KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float -mbackchain @@ -72,15 +72,6 @@ cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y) KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y) -ifneq ($(call cc-option,-mstack-size=8192 -mstack-guard=128),) - CC_FLAGS_CHECK_STACK := -mstack-size=$(STACK_SIZE) - ifeq ($(call cc-option,-mstack-size=8192),) - CC_FLAGS_CHECK_STACK += -mstack-guard=$(CONFIG_STACK_GUARD) - endif - export CC_FLAGS_CHECK_STACK - cflags-$(CONFIG_CHECK_STACK) += $(CC_FLAGS_CHECK_STACK) -endif - ifdef CONFIG_EXPOLINE ifdef CONFIG_EXPOLINE_EXTERN CC_FLAGS_EXPOLINE := -mindirect-branch=thunk-extern diff --git a/arch/s390/Makefile.postlink b/arch/s390/Makefile.postlink index df82f5410769..1ae5478cd6ac 100644 --- a/arch/s390/Makefile.postlink +++ b/arch/s390/Makefile.postlink @@ -11,6 +11,7 @@ __archpost: -include include/config/auto.conf include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib CMD_RELOCS=arch/s390/tools/relocs OUT_RELOCS = arch/s390/boot @@ -19,11 +20,6 @@ quiet_cmd_relocs = RELOCS $(OUT_RELOCS)/relocs.S mkdir -p $(OUT_RELOCS); \ $(CMD_RELOCS) $@ > $(OUT_RELOCS)/relocs.S -quiet_cmd_strip_relocs = RSTRIP $@ - cmd_strip_relocs = \ - $(OBJCOPY) --remove-section='.rel.*' --remove-section='.rel__*' \ - --remove-section='.rela.*' --remove-section='.rela__*' $@ - vmlinux: FORCE $(call cmd,relocs) $(call cmd,strip_relocs) diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 91a30e017d65..dd7ba7587dd5 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -52,7 +52,7 @@ static int appldata_interval_handler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table_header *appldata_sysctl_header; -static struct ctl_table appldata_table[] = { +static const struct ctl_table appldata_table[] = { { .procname = "timer", .mode = S_IRUGO | S_IWUSR, diff --git a/arch/s390/boot/als.c b/arch/s390/boot/als.c index 11e0c3d5dbc8..79afb5fa7f1f 100644 --- a/arch/s390/boot/als.c +++ b/arch/s390/boot/als.c @@ -46,7 +46,7 @@ void print_missing_facilities(void) * z/VM adds a four character prefix. */ if (strlen(als_str) > 70) { - boot_printk("%s\n", als_str); + boot_emerg("%s\n", als_str); *als_str = '\0'; } u16_to_decimal(val_str, i * BITS_PER_LONG + j); @@ -54,7 +54,7 @@ void print_missing_facilities(void) first = 0; } } - boot_printk("%s\n", als_str); + boot_emerg("%s\n", als_str); } static void facility_mismatch(void) @@ -62,10 +62,10 @@ static void facility_mismatch(void) struct cpuid id; get_cpu_id(&id); - boot_printk("The Linux kernel requires more recent processor hardware\n"); - boot_printk("Detected machine-type number: %4x\n", id.machine); + boot_emerg("The Linux kernel requires more recent processor hardware\n"); + boot_emerg("Detected machine-type number: %4x\n", id.machine); print_missing_facilities(); - boot_printk("See Principles of Operations for facility bits\n"); + boot_emerg("See Principles of Operations for facility bits\n"); disabled_wait(); } diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 7521a9d75fa2..69f261566a64 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -8,12 +8,12 @@ #ifndef __ASSEMBLY__ +#include #include struct machine_info { unsigned char has_edat1 : 1; unsigned char has_edat2 : 1; - unsigned char has_nx : 1; }; struct vmlinux_info { @@ -48,13 +48,16 @@ void physmem_set_usable_limit(unsigned long limit); void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size); void physmem_free(enum reserved_range_type type); /* for continuous/multiple allocations per type */ -unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size, - unsigned long align); +unsigned long physmem_alloc_or_die(enum reserved_range_type type, unsigned long size, + unsigned long align); +unsigned long physmem_alloc(enum reserved_range_type type, unsigned long size, + unsigned long align, bool die_on_oom); /* for single allocations, 1 per type */ unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long size, unsigned long align, unsigned long min, unsigned long max, bool die_on_oom); unsigned long get_physmem_alloc_pos(void); +void dump_physmem_reserved(void); bool ipl_report_certs_intersects(unsigned long addr, unsigned long size, unsigned long *intersection_start); bool is_ipl_block_dump(void); @@ -70,12 +73,28 @@ void print_pgm_check_info(void); unsigned long randomize_within_range(unsigned long size, unsigned long align, unsigned long min, unsigned long max); void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned long asce_limit); -void __printf(1, 2) boot_printk(const char *fmt, ...); +int __printf(1, 2) boot_printk(const char *fmt, ...); void print_stacktrace(unsigned long sp); void error(char *m); int get_random(unsigned long limit, unsigned long *value); +void boot_rb_dump(void); + +#ifndef boot_fmt +#define boot_fmt(fmt) fmt +#endif + +#define boot_emerg(fmt, ...) boot_printk(KERN_EMERG boot_fmt(fmt), ##__VA_ARGS__) +#define boot_alert(fmt, ...) boot_printk(KERN_ALERT boot_fmt(fmt), ##__VA_ARGS__) +#define boot_crit(fmt, ...) boot_printk(KERN_CRIT boot_fmt(fmt), ##__VA_ARGS__) +#define boot_err(fmt, ...) boot_printk(KERN_ERR boot_fmt(fmt), ##__VA_ARGS__) +#define boot_warn(fmt, ...) boot_printk(KERN_WARNING boot_fmt(fmt), ##__VA_ARGS__) +#define boot_notice(fmt, ...) boot_printk(KERN_NOTICE boot_fmt(fmt), ##__VA_ARGS__) +#define boot_info(fmt, ...) boot_printk(KERN_INFO boot_fmt(fmt), ##__VA_ARGS__) +#define boot_debug(fmt, ...) boot_printk(KERN_DEBUG boot_fmt(fmt), ##__VA_ARGS__) extern struct machine_info machine; +extern int boot_console_loglevel; +extern bool boot_ignore_loglevel; /* Symbols defined by linker scripts */ extern const char kernel_version[]; diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c index f478e8e9cbda..03500b9d9fb9 100644 --- a/arch/s390/boot/decompressor.c +++ b/arch/s390/boot/decompressor.c @@ -9,6 +9,7 @@ #include #include +#include #include #include "decompressor.h" #include "boot.h" @@ -63,6 +64,15 @@ static unsigned long free_mem_end_ptr = (unsigned long) _end + BOOT_HEAP_SIZE; #include "../../../../lib/decompress_unzstd.c" #endif +static void decompress_error(char *m) +{ + if (bootdebug) + boot_rb_dump(); + boot_emerg("Decompression error: %s\n", m); + boot_emerg(" -- System halted\n"); + disabled_wait(); +} + unsigned long mem_safe_offset(void) { return ALIGN(free_mem_end_ptr, PAGE_SIZE); @@ -71,5 +81,5 @@ unsigned long mem_safe_offset(void) void deploy_kernel(void *output) { __decompress(_compressed_start, _compressed_end - _compressed_start, - NULL, NULL, output, vmlinux.image_size, NULL, error); + NULL, NULL, output, vmlinux.image_size, NULL, decompress_error); } diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 557462e62cd7..d3731f2983b7 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -215,7 +215,7 @@ static void check_cleared_facilities(void) for (i = 0; i < ARRAY_SIZE(als); i++) { if ((stfle_fac_list[i] & als[i]) != als[i]) { - boot_printk("Warning: The Linux kernel requires facilities cleared via command line option\n"); + boot_emerg("The Linux kernel requires facilities cleared via command line option\n"); print_missing_facilities(); break; } @@ -313,5 +313,23 @@ void parse_boot_command_line(void) #endif if (!strcmp(param, "relocate_lowcore") && test_facility(193)) relocate_lowcore = 1; + if (!strcmp(param, "earlyprintk")) + boot_earlyprintk = true; + if (!strcmp(param, "debug")) + boot_console_loglevel = CONSOLE_LOGLEVEL_DEBUG; + if (!strcmp(param, "bootdebug")) { + bootdebug = true; + if (val) + strncpy(bootdebug_filter, val, sizeof(bootdebug_filter) - 1); + } + if (!strcmp(param, "quiet")) + boot_console_loglevel = CONSOLE_LOGLEVEL_QUIET; + if (!strcmp(param, "ignore_loglevel")) + boot_ignore_loglevel = true; + if (!strcmp(param, "loglevel")) { + boot_console_loglevel = simple_strtoull(val, NULL, 10); + if (boot_console_loglevel < CONSOLE_LOGLEVEL_MIN) + boot_console_loglevel = CONSOLE_LOGLEVEL_MIN; + } } } diff --git a/arch/s390/boot/ipl_report.c b/arch/s390/boot/ipl_report.c index d00898852a88..f73cd757a5f7 100644 --- a/arch/s390/boot/ipl_report.c +++ b/arch/s390/boot/ipl_report.c @@ -30,7 +30,6 @@ static unsigned long get_cert_comp_list_size(void) { struct ipl_rb_certificate_entry *cert; struct ipl_rb_component_entry *comp; - size_t size; /* * Find the length for the IPL report boot data @@ -155,7 +154,7 @@ void save_ipl_cert_comp_list(void) return; size = get_cert_comp_list_size(); - early_ipl_comp_list_addr = physmem_alloc_top_down(RR_CERT_COMP_LIST, size, sizeof(int)); + early_ipl_comp_list_addr = physmem_alloc_or_die(RR_CERT_COMP_LIST, size, sizeof(int)); ipl_cert_list_addr = early_ipl_comp_list_addr + early_ipl_comp_list_size; copy_components_bootdata(); diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index f864d2bff775..941f4c9e27cc 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -32,7 +32,7 @@ struct prng_parm { static int check_prng(void) { if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG)) { - boot_printk("KASLR disabled: CPU has no PRNG\n"); + boot_warn("KASLR disabled: CPU has no PRNG\n"); return 0; } if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG)) @@ -168,7 +168,7 @@ static unsigned long iterate_valid_positions(unsigned long size, unsigned long a * cannot have chains. * * On the other hand, "dynamic" or "repetitive" allocations are done via - * physmem_alloc_top_down(). These allocations are tightly packed together + * physmem_alloc_or_die(). These allocations are tightly packed together * top down from the end of online memory. physmem_alloc_pos represents * current position where those allocations start. * diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c index 5abe59fb3bc0..633f11600aab 100644 --- a/arch/s390/boot/pgm_check_info.c +++ b/arch/s390/boot/pgm_check_info.c @@ -17,13 +17,14 @@ void print_stacktrace(unsigned long sp) (unsigned long)_stack_end }; bool first = true; - boot_printk("Call Trace:\n"); + boot_emerg("Call Trace:\n"); while (!(sp & 0x7) && on_stack(&boot_stack, sp, sizeof(struct stack_frame))) { struct stack_frame *sf = (struct stack_frame *)sp; - boot_printk(first ? "(sp:%016lx [<%016lx>] %pS)\n" : - " sp:%016lx [<%016lx>] %pS\n", - sp, sf->gprs[8], (void *)sf->gprs[8]); + if (first) + boot_emerg("(sp:%016lx [<%016lx>] %pS)\n", sp, sf->gprs[8], (void *)sf->gprs[8]); + else + boot_emerg(" sp:%016lx [<%016lx>] %pS\n", sp, sf->gprs[8], (void *)sf->gprs[8]); if (sf->back_chain <= sp) break; sp = sf->back_chain; @@ -36,30 +37,30 @@ void print_pgm_check_info(void) unsigned long *gpregs = (unsigned long *)get_lowcore()->gpregs_save_area; struct psw_bits *psw = &psw_bits(get_lowcore()->psw_save_area); - boot_printk("Linux version %s\n", kernel_version); + if (bootdebug) + boot_rb_dump(); + boot_emerg("Linux version %s\n", kernel_version); if (!is_prot_virt_guest() && early_command_line[0]) - boot_printk("Kernel command line: %s\n", early_command_line); - boot_printk("Kernel fault: interruption code %04x ilc:%x\n", - get_lowcore()->pgm_code, get_lowcore()->pgm_ilc >> 1); + boot_emerg("Kernel command line: %s\n", early_command_line); + boot_emerg("Kernel fault: interruption code %04x ilc:%d\n", + get_lowcore()->pgm_code, get_lowcore()->pgm_ilc >> 1); if (kaslr_enabled()) { - boot_printk("Kernel random base: %lx\n", __kaslr_offset); - boot_printk("Kernel random base phys: %lx\n", __kaslr_offset_phys); + boot_emerg("Kernel random base: %lx\n", __kaslr_offset); + boot_emerg("Kernel random base phys: %lx\n", __kaslr_offset_phys); } - boot_printk("PSW : %016lx %016lx (%pS)\n", - get_lowcore()->psw_save_area.mask, - get_lowcore()->psw_save_area.addr, - (void *)get_lowcore()->psw_save_area.addr); - boot_printk( - " R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x P:%x AS:%x CC:%x PM:%x RI:%x EA:%x\n", - psw->per, psw->dat, psw->io, psw->ext, psw->key, psw->mcheck, - psw->wait, psw->pstate, psw->as, psw->cc, psw->pm, psw->ri, - psw->eaba); - boot_printk("GPRS: %016lx %016lx %016lx %016lx\n", gpregs[0], gpregs[1], gpregs[2], gpregs[3]); - boot_printk(" %016lx %016lx %016lx %016lx\n", gpregs[4], gpregs[5], gpregs[6], gpregs[7]); - boot_printk(" %016lx %016lx %016lx %016lx\n", gpregs[8], gpregs[9], gpregs[10], gpregs[11]); - boot_printk(" %016lx %016lx %016lx %016lx\n", gpregs[12], gpregs[13], gpregs[14], gpregs[15]); + boot_emerg("PSW : %016lx %016lx (%pS)\n", + get_lowcore()->psw_save_area.mask, + get_lowcore()->psw_save_area.addr, + (void *)get_lowcore()->psw_save_area.addr); + boot_emerg(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x P:%x AS:%x CC:%x PM:%x RI:%x EA:%x\n", + psw->per, psw->dat, psw->io, psw->ext, psw->key, psw->mcheck, + psw->wait, psw->pstate, psw->as, psw->cc, psw->pm, psw->ri, psw->eaba); + boot_emerg("GPRS: %016lx %016lx %016lx %016lx\n", gpregs[0], gpregs[1], gpregs[2], gpregs[3]); + boot_emerg(" %016lx %016lx %016lx %016lx\n", gpregs[4], gpregs[5], gpregs[6], gpregs[7]); + boot_emerg(" %016lx %016lx %016lx %016lx\n", gpregs[8], gpregs[9], gpregs[10], gpregs[11]); + boot_emerg(" %016lx %016lx %016lx %016lx\n", gpregs[12], gpregs[13], gpregs[14], gpregs[15]); print_stacktrace(get_lowcore()->gpregs_save_area[15]); - boot_printk("Last Breaking-Event-Address:\n"); - boot_printk(" [<%016lx>] %pS\n", (unsigned long)get_lowcore()->pgm_last_break, - (void *)get_lowcore()->pgm_last_break); + boot_emerg("Last Breaking-Event-Address:\n"); + boot_emerg(" [<%016lx>] %pS\n", (unsigned long)get_lowcore()->pgm_last_break, + (void *)get_lowcore()->pgm_last_break); } diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c index 7617aa2d2f7e..aa096ef68e8c 100644 --- a/arch/s390/boot/physmem_info.c +++ b/arch/s390/boot/physmem_info.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define boot_fmt(fmt) "physmem: " fmt #include #include #include @@ -28,7 +29,7 @@ static struct physmem_range *__get_physmem_range_ptr(u32 n) return &physmem_info.online[n]; if (unlikely(!physmem_info.online_extended)) { physmem_info.online_extended = (struct physmem_range *)physmem_alloc_range( - RR_MEM_DETECT_EXTENDED, ENTRIES_EXTENDED_MAX, sizeof(long), 0, + RR_MEM_DETECT_EXT, ENTRIES_EXTENDED_MAX, sizeof(long), 0, physmem_alloc_pos, true); } return &physmem_info.online_extended[n - MEM_INLINED_ENTRIES]; @@ -207,11 +208,16 @@ unsigned long detect_max_physmem_end(void) max_physmem_end = search_mem_end(); physmem_info.info_source = MEM_DETECT_BIN_SEARCH; } + boot_debug("Max physical memory: 0x%016lx (info source: %s)\n", max_physmem_end, + get_physmem_info_source()); return max_physmem_end; } void detect_physmem_online_ranges(unsigned long max_physmem_end) { + unsigned long start, end; + int i; + if (!sclp_early_read_storage_info()) { physmem_info.info_source = MEM_DETECT_SCLP_STOR_INFO; } else if (physmem_info.info_source == MEM_DETECT_DIAG500_STOR_LIMIT) { @@ -226,12 +232,16 @@ void detect_physmem_online_ranges(unsigned long max_physmem_end) } else if (max_physmem_end) { add_physmem_online_range(0, max_physmem_end); } + boot_debug("Online memory ranges (info source: %s):\n", get_physmem_info_source()); + for_each_physmem_online_range(i, &start, &end) + boot_debug(" online [%d]: 0x%016lx-0x%016lx\n", i, start, end); } void physmem_set_usable_limit(unsigned long limit) { physmem_info.usable = limit; physmem_alloc_pos = limit; + boot_debug("Usable memory limit: 0x%016lx\n", limit); } static void die_oom(unsigned long size, unsigned long align, unsigned long min, unsigned long max) @@ -241,38 +251,47 @@ static void die_oom(unsigned long size, unsigned long align, unsigned long min, enum reserved_range_type t; int i; - boot_printk("Linux version %s\n", kernel_version); + boot_emerg("Linux version %s\n", kernel_version); if (!is_prot_virt_guest() && early_command_line[0]) - boot_printk("Kernel command line: %s\n", early_command_line); - boot_printk("Out of memory allocating %lx bytes %lx aligned in range %lx:%lx\n", - size, align, min, max); - boot_printk("Reserved memory ranges:\n"); + boot_emerg("Kernel command line: %s\n", early_command_line); + boot_emerg("Out of memory allocating %lu bytes 0x%lx aligned in range %lx:%lx\n", + size, align, min, max); + boot_emerg("Reserved memory ranges:\n"); for_each_physmem_reserved_range(t, range, &start, &end) { - boot_printk("%016lx %016lx %s\n", start, end, get_rr_type_name(t)); + boot_emerg("%016lx %016lx %s\n", start, end, get_rr_type_name(t)); total_reserved_mem += end - start; } - boot_printk("Usable online memory ranges (info source: %s [%x]):\n", - get_physmem_info_source(), physmem_info.info_source); + boot_emerg("Usable online memory ranges (info source: %s [%d]):\n", + get_physmem_info_source(), physmem_info.info_source); for_each_physmem_usable_range(i, &start, &end) { - boot_printk("%016lx %016lx\n", start, end); + boot_emerg("%016lx %016lx\n", start, end); total_mem += end - start; } - boot_printk("Usable online memory total: %lx Reserved: %lx Free: %lx\n", - total_mem, total_reserved_mem, - total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0); + boot_emerg("Usable online memory total: %lu Reserved: %lu Free: %lu\n", + total_mem, total_reserved_mem, + total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0); print_stacktrace(current_frame_address()); - boot_printk("\n\n -- System halted\n"); + boot_emerg(" -- System halted\n"); disabled_wait(); } -void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size) +static void _physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size) { physmem_info.reserved[type].start = addr; physmem_info.reserved[type].end = addr + size; } +void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size) +{ + _physmem_reserve(type, addr, size); + boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Reserve:", addr, addr + size, + get_rr_type_name(type)); +} + void physmem_free(enum reserved_range_type type) { + boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Free:", physmem_info.reserved[type].start, + physmem_info.reserved[type].end, get_rr_type_name(type)); physmem_info.reserved[type].start = 0; physmem_info.reserved[type].end = 0; } @@ -339,41 +358,73 @@ unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long s max = min(max, physmem_alloc_pos); addr = __physmem_alloc_range(size, align, min, max, 0, NULL, die_on_oom); if (addr) - physmem_reserve(type, addr, size); + _physmem_reserve(type, addr, size); + boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Alloc range:", addr, addr + size, + get_rr_type_name(type)); return addr; } -unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size, - unsigned long align) +unsigned long physmem_alloc(enum reserved_range_type type, unsigned long size, + unsigned long align, bool die_on_oom) { struct reserved_range *range = &physmem_info.reserved[type]; - struct reserved_range *new_range; + struct reserved_range *new_range = NULL; unsigned int ranges_left; unsigned long addr; addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos, physmem_alloc_ranges, - &ranges_left, true); + &ranges_left, die_on_oom); + if (!addr) + return 0; /* if not a consecutive allocation of the same type or first allocation */ if (range->start != addr + size) { if (range->end) { - physmem_alloc_pos = __physmem_alloc_range( - sizeof(struct reserved_range), 0, 0, physmem_alloc_pos, - physmem_alloc_ranges, &ranges_left, true); - new_range = (struct reserved_range *)physmem_alloc_pos; + addr = __physmem_alloc_range(sizeof(struct reserved_range), 0, 0, + physmem_alloc_pos, physmem_alloc_ranges, + &ranges_left, true); + new_range = (struct reserved_range *)addr; + addr = __physmem_alloc_range(size, align, 0, addr, ranges_left, + &ranges_left, die_on_oom); + if (!addr) + return 0; *new_range = *range; range->chain = new_range; - addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos, - ranges_left, &ranges_left, true); } range->end = addr + size; } + if (type != RR_VMEM) { + boot_debug("%-14s 0x%016lx-0x%016lx %-20s align 0x%lx split %d\n", "Alloc topdown:", + addr, addr + size, get_rr_type_name(type), align, !!new_range); + } range->start = addr; physmem_alloc_pos = addr; physmem_alloc_ranges = ranges_left; return addr; } +unsigned long physmem_alloc_or_die(enum reserved_range_type type, unsigned long size, + unsigned long align) +{ + return physmem_alloc(type, size, align, true); +} + unsigned long get_physmem_alloc_pos(void) { return physmem_alloc_pos; } + +void dump_physmem_reserved(void) +{ + struct reserved_range *range; + enum reserved_range_type t; + unsigned long start, end; + + boot_debug("Reserved memory ranges:\n"); + for_each_physmem_reserved_range(t, range, &start, &end) { + if (end) { + boot_debug("%-14s 0x%016lx-0x%016lx @%012lx chain %012lx\n", + get_rr_type_name(t), start, end, (unsigned long)range, + (unsigned long)range->chain); + } + } +} diff --git a/arch/s390/boot/printk.c b/arch/s390/boot/printk.c index 35f18f2b936e..b4c66fa667d5 100644 --- a/arch/s390/boot/printk.c +++ b/arch/s390/boot/printk.c @@ -5,21 +5,111 @@ #include #include #include +#include #include #include #include #include #include "boot.h" +int boot_console_loglevel = CONFIG_CONSOLE_LOGLEVEL_DEFAULT; +bool boot_ignore_loglevel; +char __bootdata(boot_rb)[PAGE_SIZE * 2]; +bool __bootdata(boot_earlyprintk); +size_t __bootdata(boot_rb_off); +char __bootdata(bootdebug_filter)[128]; +bool __bootdata(bootdebug); + +static void boot_rb_add(const char *str, size_t len) +{ + /* leave double '\0' in the end */ + size_t avail = sizeof(boot_rb) - boot_rb_off - 1; + + /* store strings separated by '\0' */ + if (len + 1 > avail) + boot_rb_off = 0; + strcpy(boot_rb + boot_rb_off, str); + boot_rb_off += len + 1; +} + +static void print_rb_entry(const char *str) +{ + sclp_early_printk(printk_skip_level(str)); +} + +static bool debug_messages_printed(void) +{ + return boot_earlyprintk && (boot_ignore_loglevel || boot_console_loglevel > LOGLEVEL_DEBUG); +} + +void boot_rb_dump(void) +{ + if (debug_messages_printed()) + return; + sclp_early_printk("Boot messages ring buffer:\n"); + boot_rb_foreach(print_rb_entry); +} + const char hex_asc[] = "0123456789abcdef"; static char *as_hex(char *dst, unsigned long val, int pad) { - char *p, *end = p = dst + max(pad, (int)__fls(val | 1) / 4 + 1); + char *p = dst + max(pad, (int)__fls(val | 1) / 4 + 1); - for (*p-- = 0; p >= dst; val >>= 4) + for (*p-- = '\0'; p >= dst; val >>= 4) *p-- = hex_asc[val & 0x0f]; - return end; + return dst; +} + +#define MAX_NUMLEN 21 +static char *as_dec(char *buf, unsigned long val, bool is_signed) +{ + bool negative = false; + char *p = buf + MAX_NUMLEN; + + if (is_signed && (long)val < 0) { + val = (val == LONG_MIN ? LONG_MIN : -(long)val); + negative = true; + } + + *--p = '\0'; + do { + *--p = '0' + (val % 10); + val /= 10; + } while (val); + + if (negative) + *--p = '-'; + return p; +} + +static ssize_t strpad(char *dst, size_t dst_size, const char *src, + int _pad, bool zero_pad, bool decimal) +{ + ssize_t len = strlen(src), pad = _pad; + char *p = dst; + + if (max(len, abs(pad)) >= dst_size) + return -E2BIG; + + if (pad > len) { + if (decimal && zero_pad && *src == '-') { + *p++ = '-'; + src++; + len--; + pad--; + } + memset(p, zero_pad ? '0' : ' ', pad - len); + p += pad - len; + } + memcpy(p, src, len); + p += len; + if (pad < 0 && -pad > len) { + memset(p, ' ', -pad - len); + p += -pad - len; + } + *p = '\0'; + return p - dst; } static char *symstart(char *p) @@ -58,35 +148,94 @@ static noinline char *findsym(unsigned long ip, unsigned short *off, unsigned sh return NULL; } -static noinline char *strsym(void *ip) +#define MAX_SYMLEN 64 +static noinline char *strsym(char *buf, void *ip) { - static char buf[64]; unsigned short off; unsigned short len; char *p; p = findsym((unsigned long)ip, &off, &len); if (p) { - strncpy(buf, p, sizeof(buf)); + strncpy(buf, p, MAX_SYMLEN); /* reserve 15 bytes for offset/len in symbol+0x1234/0x1234 */ - p = buf + strnlen(buf, sizeof(buf) - 15); + p = buf + strnlen(buf, MAX_SYMLEN - 15); strcpy(p, "+0x"); - p = as_hex(p + 3, off, 0); - strcpy(p, "/0x"); - as_hex(p + 3, len, 0); + as_hex(p + 3, off, 0); + strcat(p, "/0x"); + as_hex(p + strlen(p), len, 0); } else { as_hex(buf, (unsigned long)ip, 16); } return buf; } -void boot_printk(const char *fmt, ...) +static inline int printk_loglevel(const char *buf) +{ + if (buf[0] == KERN_SOH_ASCII && buf[1]) { + switch (buf[1]) { + case '0' ... '7': + return buf[1] - '0'; + } + } + return MESSAGE_LOGLEVEL_DEFAULT; +} + +static void boot_console_earlyprintk(const char *buf) +{ + int level = printk_loglevel(buf); + + /* always print emergency messages */ + if (level > LOGLEVEL_EMERG && !boot_earlyprintk) + return; + buf = printk_skip_level(buf); + /* print debug messages only when bootdebug is enabled */ + if (level == LOGLEVEL_DEBUG && (!bootdebug || !bootdebug_filter_match(skip_timestamp(buf)))) + return; + if (boot_ignore_loglevel || level < boot_console_loglevel) + sclp_early_printk(buf); +} + +static char *add_timestamp(char *buf) +{ +#ifdef CONFIG_PRINTK_TIME + union tod_clock *boot_clock = (union tod_clock *)&get_lowcore()->boot_clock; + unsigned long ns = tod_to_ns(get_tod_clock() - boot_clock->tod); + char ts[MAX_NUMLEN]; + + *buf++ = '['; + buf += strpad(buf, MAX_NUMLEN, as_dec(ts, ns / NSEC_PER_SEC, 0), 5, 0, 0); + *buf++ = '.'; + buf += strpad(buf, MAX_NUMLEN, as_dec(ts, (ns % NSEC_PER_SEC) / NSEC_PER_USEC, 0), 6, 1, 0); + *buf++ = ']'; + *buf++ = ' '; +#endif + return buf; +} + +#define va_arg_len_type(args, lenmod, typemod) \ + ((lenmod == 'l') ? va_arg(args, typemod long) : \ + (lenmod == 'h') ? (typemod short)va_arg(args, typemod int) : \ + (lenmod == 'H') ? (typemod char)va_arg(args, typemod int) : \ + (lenmod == 'z') ? va_arg(args, typemod long) : \ + va_arg(args, typemod int)) + +int boot_printk(const char *fmt, ...) { char buf[1024] = { 0 }; char *end = buf + sizeof(buf) - 1; /* make sure buf is 0 terminated */ - unsigned long pad; - char *p = buf; + bool zero_pad, decimal; + char *strval, *p = buf; + char valbuf[MAX(MAX_SYMLEN, MAX_NUMLEN)]; va_list args; + char lenmod; + ssize_t len; + int pad; + + *p++ = KERN_SOH_ASCII; + *p++ = printk_get_level(fmt) ?: '0' + MESSAGE_LOGLEVEL_DEFAULT; + p = add_timestamp(p); + fmt = printk_skip_level(fmt); va_start(args, fmt); for (; p < end && *fmt; fmt++) { @@ -94,31 +243,56 @@ void boot_printk(const char *fmt, ...) *p++ = *fmt; continue; } - pad = isdigit(*++fmt) ? simple_strtol(fmt, (char **)&fmt, 10) : 0; + if (*++fmt == '%') { + *p++ = '%'; + continue; + } + zero_pad = (*fmt == '0'); + pad = simple_strtol(fmt, (char **)&fmt, 10); + lenmod = (*fmt == 'h' || *fmt == 'l' || *fmt == 'z') ? *fmt++ : 0; + if (lenmod == 'h' && *fmt == 'h') { + lenmod = 'H'; + fmt++; + } + decimal = false; switch (*fmt) { case 's': - p = buf + strlcat(buf, va_arg(args, char *), sizeof(buf)); + if (lenmod) + goto out; + strval = va_arg(args, char *); + zero_pad = false; break; case 'p': - if (*++fmt != 'S') + if (*++fmt != 'S' || lenmod) goto out; - p = buf + strlcat(buf, strsym(va_arg(args, void *)), sizeof(buf)); + strval = strsym(valbuf, va_arg(args, void *)); + zero_pad = false; break; - case 'l': - if (*++fmt != 'x' || end - p <= max(sizeof(long) * 2, pad)) - goto out; - p = as_hex(p, va_arg(args, unsigned long), pad); + case 'd': + case 'i': + strval = as_dec(valbuf, va_arg_len_type(args, lenmod, signed), 1); + decimal = true; + break; + case 'u': + strval = as_dec(valbuf, va_arg_len_type(args, lenmod, unsigned), 0); break; case 'x': - if (end - p <= max(sizeof(int) * 2, pad)) - goto out; - p = as_hex(p, va_arg(args, unsigned int), pad); + strval = as_hex(valbuf, va_arg_len_type(args, lenmod, unsigned), 0); break; default: goto out; } + len = strpad(p, end - p, strval, pad, zero_pad, decimal); + if (len == -E2BIG) + break; + p += len; } out: va_end(args); - sclp_early_printk(buf); + len = strlen(buf); + if (len) { + boot_rb_add(buf, len); + boot_console_earlyprintk(buf); + } + return len; } diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index abe6e6c0ab98..885bd1dd2c82 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define boot_fmt(fmt) "startup: " fmt #include #include #include @@ -30,6 +31,9 @@ unsigned long __bootdata_preserved(vmemmap_size); unsigned long __bootdata_preserved(MODULES_VADDR); unsigned long __bootdata_preserved(MODULES_END); unsigned long __bootdata_preserved(max_mappable); +unsigned long __bootdata_preserved(page_noexec_mask); +unsigned long __bootdata_preserved(segment_noexec_mask); +unsigned long __bootdata_preserved(region_noexec_mask); int __bootdata_preserved(relocate_lowcore); u64 __bootdata_preserved(stfle_fac_list[16]); @@ -39,7 +43,8 @@ struct machine_info machine; void error(char *x) { - boot_printk("\n\n%s\n\n -- System halted", x); + boot_emerg("%s\n", x); + boot_emerg(" -- System halted\n"); disabled_wait(); } @@ -51,8 +56,14 @@ static void detect_facilities(void) } if (test_facility(78)) machine.has_edat2 = 1; - if (test_facility(130)) - machine.has_nx = 1; + page_noexec_mask = -1UL; + segment_noexec_mask = -1UL; + region_noexec_mask = -1UL; + if (!test_facility(130)) { + page_noexec_mask &= ~_PAGE_NOEXEC; + segment_noexec_mask &= ~_SEGMENT_ENTRY_NOEXEC; + region_noexec_mask &= ~_REGION_ENTRY_NOEXEC; + } } static int cmma_test_essa(void) @@ -134,7 +145,7 @@ static void rescue_initrd(unsigned long min, unsigned long max) return; old_addr = addr; physmem_free(RR_INITRD); - addr = physmem_alloc_top_down(RR_INITRD, size, 0); + addr = physmem_alloc_or_die(RR_INITRD, size, 0); memmove((void *)addr, (void *)old_addr, size); } @@ -213,12 +224,16 @@ static void setup_ident_map_size(unsigned long max_physmem_end) if (oldmem_data.start) { __kaslr_enabled = 0; ident_map_size = min(ident_map_size, oldmem_data.size); + boot_debug("kdump memory limit: 0x%016lx\n", oldmem_data.size); } else if (ipl_block_valid && is_ipl_block_dump()) { __kaslr_enabled = 0; - if (!sclp_early_get_hsa_size(&hsa_size) && hsa_size) + if (!sclp_early_get_hsa_size(&hsa_size) && hsa_size) { ident_map_size = min(ident_map_size, hsa_size); + boot_debug("Stand-alone dump limit: 0x%016lx\n", hsa_size); + } } #endif + boot_debug("Identity map size: 0x%016lx\n", ident_map_size); } #define FIXMAP_SIZE round_up(MEMCPY_REAL_SIZE + ABS_LOWCORE_MAP_SIZE, sizeof(struct lowcore)) @@ -234,6 +249,8 @@ static unsigned long get_vmem_size(unsigned long identity_size, vsize = round_up(SZ_2G + max_mappable, rte_size) + round_up(vmemmap_size, rte_size) + FIXMAP_SIZE + MODULES_LEN + KASLR_LEN; + if (IS_ENABLED(CONFIG_KMSAN)) + vsize += MODULES_LEN * 2; return size_add(vsize, vmalloc_size); } @@ -256,6 +273,7 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) BUILD_BUG_ON(!IS_ALIGNED(__NO_KASLR_START_KERNEL, THREAD_SIZE)); BUILD_BUG_ON(__NO_KASLR_END_KERNEL > _REGION1_SIZE); vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION3_SIZE); + boot_debug("vmem size estimated: 0x%016lx\n", vsize); if (IS_ENABLED(CONFIG_KASAN) || __NO_KASLR_END_KERNEL > _REGION2_SIZE || (vsize > _REGION2_SIZE && kaslr_enabled())) { asce_limit = _REGION1_SIZE; @@ -279,8 +297,10 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) * otherwise asce_limit and rte_size would have been adjusted. */ vmax = adjust_to_uv_max(asce_limit); + boot_debug("%d level paging 0x%016lx vmax\n", vmax == _REGION1_SIZE ? 4 : 3, vmax); #ifdef CONFIG_KASAN BUILD_BUG_ON(__NO_KASLR_END_KERNEL > KASAN_SHADOW_START); + boot_debug("KASAN shadow area: 0x%016lx-0x%016lx\n", KASAN_SHADOW_START, KASAN_SHADOW_END); /* force vmalloc and modules below kasan shadow */ vmax = min(vmax, KASAN_SHADOW_START); #endif @@ -294,19 +314,27 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) pos = 0; kernel_end = vmax - pos * THREAD_SIZE; kernel_start = round_down(kernel_end - kernel_size, THREAD_SIZE); + boot_debug("Randomization range: 0x%016lx-0x%016lx\n", vmax - kaslr_len, vmax); + boot_debug("kernel image: 0x%016lx-0x%016lx (kaslr)\n", kernel_start, + kernel_size + kernel_size); } else if (vmax < __NO_KASLR_END_KERNEL || vsize > __NO_KASLR_END_KERNEL) { kernel_start = round_down(vmax - kernel_size, THREAD_SIZE); - boot_printk("The kernel base address is forced to %lx\n", kernel_start); + boot_debug("kernel image: 0x%016lx-0x%016lx (constrained)\n", kernel_start, + kernel_start + kernel_size); } else { kernel_start = __NO_KASLR_START_KERNEL; + boot_debug("kernel image: 0x%016lx-0x%016lx (nokaslr)\n", kernel_start, + kernel_start + kernel_size); } __kaslr_offset = kernel_start; + boot_debug("__kaslr_offset: 0x%016lx\n", __kaslr_offset); MODULES_END = round_down(kernel_start, _SEGMENT_SIZE); MODULES_VADDR = MODULES_END - MODULES_LEN; VMALLOC_END = MODULES_VADDR; if (IS_ENABLED(CONFIG_KMSAN)) VMALLOC_END -= MODULES_LEN * 2; + boot_debug("modules area: 0x%016lx-0x%016lx\n", MODULES_VADDR, MODULES_END); /* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */ vsize = (VMALLOC_END - FIXMAP_SIZE) / 2; @@ -318,10 +346,15 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) VMALLOC_END -= vmalloc_size * 2; } VMALLOC_START = VMALLOC_END - vmalloc_size; + boot_debug("vmalloc area: 0x%016lx-0x%016lx\n", VMALLOC_START, VMALLOC_END); __memcpy_real_area = round_down(VMALLOC_START - MEMCPY_REAL_SIZE, PAGE_SIZE); + boot_debug("memcpy real area: 0x%016lx-0x%016lx\n", __memcpy_real_area, + __memcpy_real_area + MEMCPY_REAL_SIZE); __abs_lowcore = round_down(__memcpy_real_area - ABS_LOWCORE_MAP_SIZE, sizeof(struct lowcore)); + boot_debug("abs lowcore: 0x%016lx-0x%016lx\n", __abs_lowcore, + __abs_lowcore + ABS_LOWCORE_MAP_SIZE); /* split remaining virtual space between 1:1 mapping & vmemmap array */ pages = __abs_lowcore / (PAGE_SIZE + sizeof(struct page)); @@ -341,8 +374,11 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) BUILD_BUG_ON(MAX_DCSS_ADDR > (1UL << MAX_PHYSMEM_BITS)); max_mappable = max(ident_map_size, MAX_DCSS_ADDR); max_mappable = min(max_mappable, vmemmap_start); - if (IS_ENABLED(CONFIG_RANDOMIZE_IDENTITY_BASE)) - __identity_base = round_down(vmemmap_start - max_mappable, rte_size); +#ifdef CONFIG_RANDOMIZE_IDENTITY_BASE + __identity_base = round_down(vmemmap_start - max_mappable, rte_size); +#endif + boot_debug("identity map: 0x%016lx-0x%016lx\n", __identity_base, + __identity_base + ident_map_size); return asce_limit; } @@ -401,6 +437,10 @@ void startup_kernel(void) psw_t psw; setup_lpp(); + store_ipl_parmblock(); + uv_query_info(); + setup_boot_command_line(); + parse_boot_command_line(); /* * Non-randomized kernel physical start address must be _SEGMENT_SIZE @@ -420,12 +460,8 @@ void startup_kernel(void) oldmem_data.start = parmarea.oldmem_base; oldmem_data.size = parmarea.oldmem_size; - store_ipl_parmblock(); read_ipl_report(); - uv_query_info(); sclp_early_read_info(); - setup_boot_command_line(); - parse_boot_command_line(); detect_facilities(); cmma_init(); sanitize_prot_virt_host(); @@ -515,6 +551,7 @@ void startup_kernel(void) __kaslr_offset, __kaslr_offset_phys); kaslr_adjust_got(__kaslr_offset); setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit); + dump_physmem_reserved(); copy_bootdata(); __apply_alternatives((struct alt_instr *)_vmlinux_info.alt_instructions, (struct alt_instr *)_vmlinux_info.alt_instructions_end, @@ -531,5 +568,6 @@ void startup_kernel(void) */ psw.addr = __kaslr_offset + vmlinux.entry; psw.mask = PSW_KERNEL_BITS; + boot_debug("Starting kernel at: 0x%016lx\n", psw.addr); __load_psw(psw); } diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 145035f84a0e..cfca94a8eac4 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define boot_fmt(fmt) "vmem: " fmt #include #include #include @@ -13,6 +14,7 @@ #include "decompressor.h" #include "boot.h" +#define INVALID_PHYS_ADDR (~(phys_addr_t)0) struct ctlreg __bootdata_preserved(s390_invalid_asce); #ifdef CONFIG_PROC_FS @@ -31,12 +33,42 @@ enum populate_mode { POPULATE_IDENTITY, POPULATE_KERNEL, #ifdef CONFIG_KASAN + /* KASAN modes should be last and grouped together, see is_kasan_populate_mode() */ POPULATE_KASAN_MAP_SHADOW, POPULATE_KASAN_ZERO_SHADOW, POPULATE_KASAN_SHALLOW #endif }; +#define POPULATE_MODE_NAME(t) case POPULATE_ ## t: return #t +static inline const char *get_populate_mode_name(enum populate_mode t) +{ + switch (t) { + POPULATE_MODE_NAME(NONE); + POPULATE_MODE_NAME(DIRECT); + POPULATE_MODE_NAME(LOWCORE); + POPULATE_MODE_NAME(ABS_LOWCORE); + POPULATE_MODE_NAME(IDENTITY); + POPULATE_MODE_NAME(KERNEL); +#ifdef CONFIG_KASAN + POPULATE_MODE_NAME(KASAN_MAP_SHADOW); + POPULATE_MODE_NAME(KASAN_ZERO_SHADOW); + POPULATE_MODE_NAME(KASAN_SHALLOW); +#endif + default: + return "UNKNOWN"; + } +} + +static bool is_kasan_populate_mode(enum populate_mode mode) +{ +#ifdef CONFIG_KASAN + return mode >= POPULATE_KASAN_MAP_SHADOW; +#else + return false; +#endif +} + static void pgtable_populate(unsigned long addr, unsigned long end, enum populate_mode mode); #ifdef CONFIG_KASAN @@ -52,9 +84,12 @@ static pte_t pte_z; static inline void kasan_populate(unsigned long start, unsigned long end, enum populate_mode mode) { - start = PAGE_ALIGN_DOWN(__sha(start)); - end = PAGE_ALIGN(__sha(end)); - pgtable_populate(start, end, mode); + unsigned long sha_start = PAGE_ALIGN_DOWN(__sha(start)); + unsigned long sha_end = PAGE_ALIGN(__sha(end)); + + boot_debug("%-17s 0x%016lx-0x%016lx >> 0x%016lx-0x%016lx\n", get_populate_mode_name(mode), + start, end, sha_start, sha_end); + pgtable_populate(sha_start, sha_end, mode); } static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kernel_end) @@ -63,13 +98,10 @@ static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kern pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY); p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY); unsigned long memgap_start = 0; - unsigned long untracked_end; unsigned long start, end; int i; pte_z = __pte(__pa(kasan_early_shadow_page) | pgprot_val(PAGE_KERNEL_RO)); - if (!machine.has_nx) - pte_z = clear_pte_bit(pte_z, __pgprot(_PAGE_NOEXEC)); crst_table_init((unsigned long *)kasan_early_shadow_p4d, p4d_val(p4d_z)); crst_table_init((unsigned long *)kasan_early_shadow_pud, pud_val(pud_z)); crst_table_init((unsigned long *)kasan_early_shadow_pmd, pmd_val(pmd_z)); @@ -93,15 +125,10 @@ static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kern kasan_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KASAN_MAP_SHADOW); kasan_populate(0, (unsigned long)__identity_va(0), POPULATE_KASAN_ZERO_SHADOW); kasan_populate(AMODE31_START, AMODE31_END, POPULATE_KASAN_ZERO_SHADOW); - if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { - untracked_end = VMALLOC_START; - /* shallowly populate kasan shadow for vmalloc and modules */ - kasan_populate(VMALLOC_START, MODULES_END, POPULATE_KASAN_SHALLOW); - } else { - untracked_end = MODULES_VADDR; - } + /* shallowly populate kasan shadow for vmalloc and modules */ + kasan_populate(VMALLOC_START, MODULES_END, POPULATE_KASAN_SHALLOW); /* populate kasan shadow for untracked memory */ - kasan_populate((unsigned long)__identity_va(ident_map_size), untracked_end, + kasan_populate((unsigned long)__identity_va(ident_map_size), VMALLOC_START, POPULATE_KASAN_ZERO_SHADOW); kasan_populate(kernel_end, _REGION1_SIZE, POPULATE_KASAN_ZERO_SHADOW); } @@ -208,7 +235,7 @@ static void *boot_crst_alloc(unsigned long val) unsigned long size = PAGE_SIZE << CRST_ALLOC_ORDER; unsigned long *table; - table = (unsigned long *)physmem_alloc_top_down(RR_VMEM, size, size); + table = (unsigned long *)physmem_alloc_or_die(RR_VMEM, size, size); crst_table_init(table, val); __arch_set_page_dat(table, 1UL << CRST_ALLOC_ORDER); return table; @@ -224,7 +251,7 @@ static pte_t *boot_pte_alloc(void) * during POPULATE_KASAN_MAP_SHADOW when EDAT is off */ if (!pte_leftover) { - pte_leftover = (void *)physmem_alloc_top_down(RR_VMEM, PAGE_SIZE, PAGE_SIZE); + pte_leftover = (void *)physmem_alloc_or_die(RR_VMEM, PAGE_SIZE, PAGE_SIZE); pte = pte_leftover + _PAGE_TABLE_SIZE; __arch_set_page_dat(pte, 1); } else { @@ -236,11 +263,12 @@ static pte_t *boot_pte_alloc(void) return pte; } -static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_mode mode) +static unsigned long resolve_pa_may_alloc(unsigned long addr, unsigned long size, + enum populate_mode mode) { switch (mode) { case POPULATE_NONE: - return -1; + return INVALID_PHYS_ADDR; case POPULATE_DIRECT: return addr; case POPULATE_LOWCORE: @@ -253,38 +281,64 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m return __identity_pa(addr); #ifdef CONFIG_KASAN case POPULATE_KASAN_MAP_SHADOW: - addr = physmem_alloc_top_down(RR_VMEM, size, size); - memset((void *)addr, 0, size); - return addr; + /* Allow to fail large page allocations, this will fall back to 1mb/4k pages */ + addr = physmem_alloc(RR_VMEM, size, size, size == PAGE_SIZE); + if (addr) { + memset((void *)addr, 0, size); + return addr; + } + return INVALID_PHYS_ADDR; #endif default: - return -1; + return INVALID_PHYS_ADDR; } } -static bool large_allowed(enum populate_mode mode) +static bool large_page_mapping_allowed(enum populate_mode mode) { - return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY) || (mode == POPULATE_KERNEL); + switch (mode) { + case POPULATE_DIRECT: + case POPULATE_IDENTITY: + case POPULATE_KERNEL: +#ifdef CONFIG_KASAN + case POPULATE_KASAN_MAP_SHADOW: +#endif + return true; + default: + return false; + } } -static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end, - enum populate_mode mode) +static unsigned long try_get_large_pud_pa(pud_t *pu_dir, unsigned long addr, unsigned long end, + enum populate_mode mode) { - unsigned long size = end - addr; + unsigned long pa, size = end - addr; - return machine.has_edat2 && large_allowed(mode) && - IS_ALIGNED(addr, PUD_SIZE) && (size >= PUD_SIZE) && - IS_ALIGNED(_pa(addr, size, mode), PUD_SIZE); + if (!machine.has_edat2 || !large_page_mapping_allowed(mode) || + !IS_ALIGNED(addr, PUD_SIZE) || (size < PUD_SIZE)) + return INVALID_PHYS_ADDR; + + pa = resolve_pa_may_alloc(addr, size, mode); + if (!IS_ALIGNED(pa, PUD_SIZE)) + return INVALID_PHYS_ADDR; + + return pa; } -static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end, - enum populate_mode mode) +static unsigned long try_get_large_pmd_pa(pmd_t *pm_dir, unsigned long addr, unsigned long end, + enum populate_mode mode) { - unsigned long size = end - addr; + unsigned long pa, size = end - addr; - return machine.has_edat1 && large_allowed(mode) && - IS_ALIGNED(addr, PMD_SIZE) && (size >= PMD_SIZE) && - IS_ALIGNED(_pa(addr, size, mode), PMD_SIZE); + if (!machine.has_edat1 || !large_page_mapping_allowed(mode) || + !IS_ALIGNED(addr, PMD_SIZE) || (size < PMD_SIZE)) + return INVALID_PHYS_ADDR; + + pa = resolve_pa_may_alloc(addr, size, mode); + if (!IS_ALIGNED(pa, PMD_SIZE)) + return INVALID_PHYS_ADDR; + + return pa; } static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end, @@ -298,22 +352,20 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e if (pte_none(*pte)) { if (kasan_pte_populate_zero_shadow(pte, mode)) continue; - entry = __pte(_pa(addr, PAGE_SIZE, mode)); + entry = __pte(resolve_pa_may_alloc(addr, PAGE_SIZE, mode)); entry = set_pte_bit(entry, PAGE_KERNEL); - if (!machine.has_nx) - entry = clear_pte_bit(entry, __pgprot(_PAGE_NOEXEC)); set_pte(pte, entry); pages++; } } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_4K, pages); } static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long end, enum populate_mode mode) { - unsigned long next, pages = 0; + unsigned long pa, next, pages = 0; pmd_t *pmd, entry; pte_t *pte; @@ -323,11 +375,10 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e if (pmd_none(*pmd)) { if (kasan_pmd_populate_zero_shadow(pmd, addr, next, mode)) continue; - if (can_large_pmd(pmd, addr, next, mode)) { - entry = __pmd(_pa(addr, _SEGMENT_SIZE, mode)); + pa = try_get_large_pmd_pa(pmd, addr, next, mode); + if (pa != INVALID_PHYS_ADDR) { + entry = __pmd(pa); entry = set_pmd_bit(entry, SEGMENT_KERNEL); - if (!machine.has_nx) - entry = clear_pmd_bit(entry, __pgprot(_SEGMENT_ENTRY_NOEXEC)); set_pmd(pmd, entry); pages++; continue; @@ -339,14 +390,14 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e } pgtable_pte_populate(pmd, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_1M, pages); } static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long end, enum populate_mode mode) { - unsigned long next, pages = 0; + unsigned long pa, next, pages = 0; pud_t *pud, entry; pmd_t *pmd; @@ -356,11 +407,10 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e if (pud_none(*pud)) { if (kasan_pud_populate_zero_shadow(pud, addr, next, mode)) continue; - if (can_large_pud(pud, addr, next, mode)) { - entry = __pud(_pa(addr, _REGION3_SIZE, mode)); + pa = try_get_large_pud_pa(pud, addr, next, mode); + if (pa != INVALID_PHYS_ADDR) { + entry = __pud(pa); entry = set_pud_bit(entry, REGION3_KERNEL); - if (!machine.has_nx) - entry = clear_pud_bit(entry, __pgprot(_REGION_ENTRY_NOEXEC)); set_pud(pud, entry); pages++; continue; @@ -372,7 +422,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pgtable_pmd_populate(pud, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_2G, pages); } @@ -402,6 +452,13 @@ static void pgtable_populate(unsigned long addr, unsigned long end, enum populat pgd_t *pgd; p4d_t *p4d; + if (!is_kasan_populate_mode(mode)) { + boot_debug("%-17s 0x%016lx-0x%016lx -> 0x%016lx-0x%016lx\n", + get_populate_mode_name(mode), addr, end, + resolve_pa_may_alloc(addr, 0, mode), + resolve_pa_may_alloc(end - 1, 0, mode) + 1); + } + pgd = pgd_offset(&init_mm, addr); for (; addr < end; addr = next, pgd++) { next = pgd_addr_end(addr, end); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index d8d227ab82de..d6beec5292a0 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -770,7 +770,6 @@ CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_AEGIS128=m @@ -782,7 +781,6 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_CRC32=m @@ -795,7 +793,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_SHA1_S390=m CONFIG_CRYPTO_SHA256_S390=m @@ -818,7 +815,6 @@ CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CORDIC=m CONFIG_CRYPTO_LIB_CURVE25519=m CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m -CONFIG_CRC32_SELFTEST=y CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 6c2f2bb4fbf8..8cfbfb10bba8 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -756,7 +756,6 @@ CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_HCTR2=m -CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_AEGIS128=m @@ -768,7 +767,6 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SM3_GENERIC=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_CRC32=m @@ -782,7 +780,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_SHA1_S390=m CONFIG_CRYPTO_SHA256_S390=m diff --git a/arch/s390/configs/kasan.config b/arch/s390/configs/kasan.config index 84c2b551e992..cefbe2ba1228 100644 --- a/arch/s390/configs/kasan.config +++ b/arch/s390/configs/kasan.config @@ -1,4 +1,4 @@ # Help: Enable KASan for debugging CONFIG_KASAN=y CONFIG_KASAN_INLINE=y -CONFIG_KASAN_VMALLOC=y +CONFIG_KERNEL_IMAGE_BASE=0x7FFFE0000000 diff --git a/arch/s390/crypto/Kconfig b/arch/s390/crypto/Kconfig index d3eb3a233693..b760232537f1 100644 --- a/arch/s390/crypto/Kconfig +++ b/arch/s390/crypto/Kconfig @@ -2,18 +2,6 @@ menu "Accelerated Cryptographic Algorithms for CPU (s390)" -config CRYPTO_CRC32_S390 - tristate "CRC32c and CRC32" - depends on S390 - select CRYPTO_HASH - select CRC32 - help - CRC32c and CRC32 CRC algorithms - - Architecture: s390 - - It is available with IBM z13 or later. - config CRYPTO_SHA512_S390 tristate "Hash functions: SHA-384 and SHA-512" depends on S390 diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile index a0cb96937c3d..14dafadbcbed 100644 --- a/arch/s390/crypto/Makefile +++ b/arch/s390/crypto/Makefile @@ -14,9 +14,7 @@ obj-$(CONFIG_CRYPTO_PAES_S390) += paes_s390.o obj-$(CONFIG_CRYPTO_CHACHA_S390) += chacha_s390.o obj-$(CONFIG_S390_PRNG) += prng.o obj-$(CONFIG_CRYPTO_GHASH_S390) += ghash_s390.o -obj-$(CONFIG_CRYPTO_CRC32_S390) += crc32-vx_s390.o obj-$(CONFIG_CRYPTO_HMAC_S390) += hmac_s390.o obj-y += arch_random.o -crc32-vx_s390-y := crc32-vx.o crc32le-vx.o crc32be-vx.o chacha_s390-y := chacha-glue.o chacha-s390.o diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c deleted file mode 100644 index 89a10337e6ea..000000000000 --- a/arch/s390/crypto/crc32-vx.c +++ /dev/null @@ -1,306 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Crypto-API module for CRC-32 algorithms implemented with the - * z/Architecture Vector Extension Facility. - * - * Copyright IBM Corp. 2015 - * Author(s): Hendrik Brueckner - */ -#define KMSG_COMPONENT "crc32-vx" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt - -#include -#include -#include -#include -#include -#include "crc32-vx.h" - -#define CRC32_BLOCK_SIZE 1 -#define CRC32_DIGEST_SIZE 4 - -#define VX_MIN_LEN 64 -#define VX_ALIGNMENT 16L -#define VX_ALIGN_MASK (VX_ALIGNMENT - 1) - -struct crc_ctx { - u32 key; -}; - -struct crc_desc_ctx { - u32 crc; -}; - -/* - * DEFINE_CRC32_VX() - Define a CRC-32 function using the vector extension - * - * Creates a function to perform a particular CRC-32 computation. Depending - * on the message buffer, the hardware-accelerated or software implementation - * is used. Note that the message buffer is aligned to improve fetch - * operations of VECTOR LOAD MULTIPLE instructions. - * - */ -#define DEFINE_CRC32_VX(___fname, ___crc32_vx, ___crc32_sw) \ - static u32 __pure ___fname(u32 crc, \ - unsigned char const *data, size_t datalen) \ - { \ - unsigned long prealign, aligned, remaining; \ - DECLARE_KERNEL_FPU_ONSTACK16(vxstate); \ - \ - if (datalen < VX_MIN_LEN + VX_ALIGN_MASK) \ - return ___crc32_sw(crc, data, datalen); \ - \ - if ((unsigned long)data & VX_ALIGN_MASK) { \ - prealign = VX_ALIGNMENT - \ - ((unsigned long)data & VX_ALIGN_MASK); \ - datalen -= prealign; \ - crc = ___crc32_sw(crc, data, prealign); \ - data = (void *)((unsigned long)data + prealign); \ - } \ - \ - aligned = datalen & ~VX_ALIGN_MASK; \ - remaining = datalen & VX_ALIGN_MASK; \ - \ - kernel_fpu_begin(&vxstate, KERNEL_VXR_LOW); \ - crc = ___crc32_vx(crc, data, aligned); \ - kernel_fpu_end(&vxstate, KERNEL_VXR_LOW); \ - \ - if (remaining) \ - crc = ___crc32_sw(crc, data + aligned, remaining); \ - \ - return crc; \ - } - -DEFINE_CRC32_VX(crc32_le_vx, crc32_le_vgfm_16, crc32_le) -DEFINE_CRC32_VX(crc32_be_vx, crc32_be_vgfm_16, crc32_be) -DEFINE_CRC32_VX(crc32c_le_vx, crc32c_le_vgfm_16, __crc32c_le) - - -static int crc32_vx_cra_init_zero(struct crypto_tfm *tfm) -{ - struct crc_ctx *mctx = crypto_tfm_ctx(tfm); - - mctx->key = 0; - return 0; -} - -static int crc32_vx_cra_init_invert(struct crypto_tfm *tfm) -{ - struct crc_ctx *mctx = crypto_tfm_ctx(tfm); - - mctx->key = ~0; - return 0; -} - -static int crc32_vx_init(struct shash_desc *desc) -{ - struct crc_ctx *mctx = crypto_shash_ctx(desc->tfm); - struct crc_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = mctx->key; - return 0; -} - -static int crc32_vx_setkey(struct crypto_shash *tfm, const u8 *newkey, - unsigned int newkeylen) -{ - struct crc_ctx *mctx = crypto_shash_ctx(tfm); - - if (newkeylen != sizeof(mctx->key)) - return -EINVAL; - mctx->key = le32_to_cpu(*(__le32 *)newkey); - return 0; -} - -static int crc32be_vx_setkey(struct crypto_shash *tfm, const u8 *newkey, - unsigned int newkeylen) -{ - struct crc_ctx *mctx = crypto_shash_ctx(tfm); - - if (newkeylen != sizeof(mctx->key)) - return -EINVAL; - mctx->key = be32_to_cpu(*(__be32 *)newkey); - return 0; -} - -static int crc32le_vx_final(struct shash_desc *desc, u8 *out) -{ - struct crc_desc_ctx *ctx = shash_desc_ctx(desc); - - *(__le32 *)out = cpu_to_le32p(&ctx->crc); - return 0; -} - -static int crc32be_vx_final(struct shash_desc *desc, u8 *out) -{ - struct crc_desc_ctx *ctx = shash_desc_ctx(desc); - - *(__be32 *)out = cpu_to_be32p(&ctx->crc); - return 0; -} - -static int crc32c_vx_final(struct shash_desc *desc, u8 *out) -{ - struct crc_desc_ctx *ctx = shash_desc_ctx(desc); - - /* - * Perform a final XOR with 0xFFFFFFFF to be in sync - * with the generic crc32c shash implementation. - */ - *(__le32 *)out = ~cpu_to_le32p(&ctx->crc); - return 0; -} - -static int __crc32le_vx_finup(u32 *crc, const u8 *data, unsigned int len, - u8 *out) -{ - *(__le32 *)out = cpu_to_le32(crc32_le_vx(*crc, data, len)); - return 0; -} - -static int __crc32be_vx_finup(u32 *crc, const u8 *data, unsigned int len, - u8 *out) -{ - *(__be32 *)out = cpu_to_be32(crc32_be_vx(*crc, data, len)); - return 0; -} - -static int __crc32c_vx_finup(u32 *crc, const u8 *data, unsigned int len, - u8 *out) -{ - /* - * Perform a final XOR with 0xFFFFFFFF to be in sync - * with the generic crc32c shash implementation. - */ - *(__le32 *)out = ~cpu_to_le32(crc32c_le_vx(*crc, data, len)); - return 0; -} - - -#define CRC32_VX_FINUP(alg, func) \ - static int alg ## _vx_finup(struct shash_desc *desc, const u8 *data, \ - unsigned int datalen, u8 *out) \ - { \ - return __ ## alg ## _vx_finup(shash_desc_ctx(desc), \ - data, datalen, out); \ - } - -CRC32_VX_FINUP(crc32le, crc32_le_vx) -CRC32_VX_FINUP(crc32be, crc32_be_vx) -CRC32_VX_FINUP(crc32c, crc32c_le_vx) - -#define CRC32_VX_DIGEST(alg, func) \ - static int alg ## _vx_digest(struct shash_desc *desc, const u8 *data, \ - unsigned int len, u8 *out) \ - { \ - return __ ## alg ## _vx_finup(crypto_shash_ctx(desc->tfm), \ - data, len, out); \ - } - -CRC32_VX_DIGEST(crc32le, crc32_le_vx) -CRC32_VX_DIGEST(crc32be, crc32_be_vx) -CRC32_VX_DIGEST(crc32c, crc32c_le_vx) - -#define CRC32_VX_UPDATE(alg, func) \ - static int alg ## _vx_update(struct shash_desc *desc, const u8 *data, \ - unsigned int datalen) \ - { \ - struct crc_desc_ctx *ctx = shash_desc_ctx(desc); \ - ctx->crc = func(ctx->crc, data, datalen); \ - return 0; \ - } - -CRC32_VX_UPDATE(crc32le, crc32_le_vx) -CRC32_VX_UPDATE(crc32be, crc32_be_vx) -CRC32_VX_UPDATE(crc32c, crc32c_le_vx) - - -static struct shash_alg crc32_vx_algs[] = { - /* CRC-32 LE */ - { - .init = crc32_vx_init, - .setkey = crc32_vx_setkey, - .update = crc32le_vx_update, - .final = crc32le_vx_final, - .finup = crc32le_vx_finup, - .digest = crc32le_vx_digest, - .descsize = sizeof(struct crc_desc_ctx), - .digestsize = CRC32_DIGEST_SIZE, - .base = { - .cra_name = "crc32", - .cra_driver_name = "crc32-vx", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CRC32_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct crc_ctx), - .cra_module = THIS_MODULE, - .cra_init = crc32_vx_cra_init_zero, - }, - }, - /* CRC-32 BE */ - { - .init = crc32_vx_init, - .setkey = crc32be_vx_setkey, - .update = crc32be_vx_update, - .final = crc32be_vx_final, - .finup = crc32be_vx_finup, - .digest = crc32be_vx_digest, - .descsize = sizeof(struct crc_desc_ctx), - .digestsize = CRC32_DIGEST_SIZE, - .base = { - .cra_name = "crc32be", - .cra_driver_name = "crc32be-vx", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CRC32_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct crc_ctx), - .cra_module = THIS_MODULE, - .cra_init = crc32_vx_cra_init_zero, - }, - }, - /* CRC-32C LE */ - { - .init = crc32_vx_init, - .setkey = crc32_vx_setkey, - .update = crc32c_vx_update, - .final = crc32c_vx_final, - .finup = crc32c_vx_finup, - .digest = crc32c_vx_digest, - .descsize = sizeof(struct crc_desc_ctx), - .digestsize = CRC32_DIGEST_SIZE, - .base = { - .cra_name = "crc32c", - .cra_driver_name = "crc32c-vx", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CRC32_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct crc_ctx), - .cra_module = THIS_MODULE, - .cra_init = crc32_vx_cra_init_invert, - }, - }, -}; - - -static int __init crc_vx_mod_init(void) -{ - return crypto_register_shashes(crc32_vx_algs, - ARRAY_SIZE(crc32_vx_algs)); -} - -static void __exit crc_vx_mod_exit(void) -{ - crypto_unregister_shashes(crc32_vx_algs, ARRAY_SIZE(crc32_vx_algs)); -} - -module_cpu_feature_match(S390_CPU_FEATURE_VXRS, crc_vx_mod_init); -module_exit(crc_vx_mod_exit); - -MODULE_AUTHOR("Hendrik Brueckner "); -MODULE_DESCRIPTION("CRC-32 algorithms using z/Architecture Vector Extension Facility"); -MODULE_LICENSE("GPL"); - -MODULE_ALIAS_CRYPTO("crc32"); -MODULE_ALIAS_CRYPTO("crc32-vx"); -MODULE_ALIAS_CRYPTO("crc32c"); -MODULE_ALIAS_CRYPTO("crc32c-vx"); diff --git a/arch/s390/include/asm/abs_lowcore.h b/arch/s390/include/asm/abs_lowcore.h index d20df8c923fc..004d17ea05cf 100644 --- a/arch/s390/include/asm/abs_lowcore.h +++ b/arch/s390/include/asm/abs_lowcore.h @@ -2,7 +2,7 @@ #ifndef _ASM_S390_ABS_LOWCORE_H #define _ASM_S390_ABS_LOWCORE_H -#include +#include #include #define ABS_LOWCORE_MAP_SIZE (NR_CPUS * sizeof(struct lowcore)) @@ -25,7 +25,7 @@ static inline void put_abs_lowcore(struct lowcore *lc) put_cpu(); } -extern int __bootdata_preserved(relocate_lowcore); +extern int relocate_lowcore; static inline int have_relocated_lowcore(void) { diff --git a/arch/s390/include/asm/asm-extable.h b/arch/s390/include/asm/asm-extable.h index 4a6b0a8b6412..2e829c16fd8a 100644 --- a/arch/s390/include/asm/asm-extable.h +++ b/arch/s390/include/asm/asm-extable.h @@ -9,11 +9,11 @@ #define EX_TYPE_NONE 0 #define EX_TYPE_FIXUP 1 #define EX_TYPE_BPF 2 -#define EX_TYPE_UA_STORE 3 -#define EX_TYPE_UA_LOAD_MEM 4 +#define EX_TYPE_UA_FAULT 3 #define EX_TYPE_UA_LOAD_REG 5 #define EX_TYPE_UA_LOAD_REGPAIR 6 #define EX_TYPE_ZEROPAD 7 +#define EX_TYPE_FPC 8 #define EX_DATA_REG_ERR_SHIFT 0 #define EX_DATA_REG_ERR GENMASK(3, 0) @@ -69,11 +69,8 @@ #define EX_TABLE_AMODE31(_fault, _target) \ __EX_TABLE(.amode31.ex_table, _fault, _target, EX_TYPE_FIXUP, __stringify(%%r0), __stringify(%%r0), 0) -#define EX_TABLE_UA_STORE(_fault, _target, _regerr) \ - __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_STORE, _regerr, _regerr, 0) - -#define EX_TABLE_UA_LOAD_MEM(_fault, _target, _regerr, _regmem, _len) \ - __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_MEM, _regerr, _regmem, _len) +#define EX_TABLE_UA_FAULT(_fault, _target, _regerr) \ + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_FAULT, _regerr, _regerr, 0) #define EX_TABLE_UA_LOAD_REG(_fault, _target, _regerr, _regzero) \ __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_REG, _regerr, _regzero, 0) @@ -84,4 +81,7 @@ #define EX_TABLE_ZEROPAD(_fault, _target, _regdata, _regaddr) \ __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_ZEROPAD, _regdata, _regaddr, 0) +#define EX_TABLE_FPC(_fault, _target) \ + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_FPC, __stringify(%%r0), __stringify(%%r0), 0) + #endif /* __ASM_EXTABLE_H */ diff --git a/arch/s390/include/asm/asm.h b/arch/s390/include/asm/asm.h index ec011b94af2a..e9062b01e2a2 100644 --- a/arch/s390/include/asm/asm.h +++ b/arch/s390/include/asm/asm.h @@ -28,7 +28,7 @@ * [var] also contains the program mask. CC_TRANSFORM() moves the condition * code to the two least significant bits and sets all other bits to zero. */ -#if defined(__GCC_ASM_FLAG_OUTPUTS__) && !(IS_ENABLED(CONFIG_GCC_ASM_FLAG_OUTPUT_BROKEN)) +#if defined(__GCC_ASM_FLAG_OUTPUTS__) && !(IS_ENABLED(CONFIG_CC_ASM_FLAG_OUTPUT_BROKEN)) #define __HAVE_ASM_FLAG_OUTPUTS__ diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 6723fca64018..b36dd6a1d652 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -17,13 +17,13 @@ static __always_inline int arch_atomic_read(const atomic_t *v) { - return __atomic_read(v); + return __atomic_read(&v->counter); } #define arch_atomic_read arch_atomic_read static __always_inline void arch_atomic_set(atomic_t *v, int i) { - __atomic_set(v, i); + __atomic_set(&v->counter, i); } #define arch_atomic_set arch_atomic_set @@ -45,6 +45,36 @@ static __always_inline void arch_atomic_add(int i, atomic_t *v) } #define arch_atomic_add arch_atomic_add +static __always_inline void arch_atomic_inc(atomic_t *v) +{ + __atomic_add_const(1, &v->counter); +} +#define arch_atomic_inc arch_atomic_inc + +static __always_inline void arch_atomic_dec(atomic_t *v) +{ + __atomic_add_const(-1, &v->counter); +} +#define arch_atomic_dec arch_atomic_dec + +static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) +{ + return __atomic_add_and_test_barrier(-i, &v->counter); +} +#define arch_atomic_sub_and_test arch_atomic_sub_and_test + +static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) +{ + return __atomic_add_const_and_test_barrier(-1, &v->counter); +} +#define arch_atomic_dec_and_test arch_atomic_dec_and_test + +static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) +{ + return __atomic_add_const_and_test_barrier(1, &v->counter); +} +#define arch_atomic_inc_and_test arch_atomic_inc_and_test + #define arch_atomic_sub(_i, _v) arch_atomic_add(-(int)(_i), _v) #define arch_atomic_sub_return(_i, _v) arch_atomic_add_return(-(int)(_i), _v) #define arch_atomic_fetch_sub(_i, _v) arch_atomic_fetch_add(-(int)(_i), _v) @@ -94,13 +124,13 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n static __always_inline s64 arch_atomic64_read(const atomic64_t *v) { - return __atomic64_read(v); + return __atomic64_read((long *)&v->counter); } #define arch_atomic64_read arch_atomic64_read static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i) { - __atomic64_set(v, i); + __atomic64_set((long *)&v->counter, i); } #define arch_atomic64_set arch_atomic64_set @@ -122,6 +152,36 @@ static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) } #define arch_atomic64_add arch_atomic64_add +static __always_inline void arch_atomic64_inc(atomic64_t *v) +{ + __atomic64_add_const(1, (long *)&v->counter); +} +#define arch_atomic64_inc arch_atomic64_inc + +static __always_inline void arch_atomic64_dec(atomic64_t *v) +{ + __atomic64_add_const(-1, (long *)&v->counter); +} +#define arch_atomic64_dec arch_atomic64_dec + +static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + return __atomic64_add_and_test_barrier(-i, (long *)&v->counter); +} +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test + +static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v) +{ + return __atomic64_add_const_and_test_barrier(-1, (long *)&v->counter); +} +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test + +static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v) +{ + return __atomic64_add_const_and_test_barrier(1, (long *)&v->counter); +} +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test + static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new) { return arch_xchg(&v->counter, new); diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h index 1d6b2056fad8..585678bbcd7a 100644 --- a/arch/s390/include/asm/atomic_ops.h +++ b/arch/s390/include/asm/atomic_ops.h @@ -10,50 +10,51 @@ #include #include +#include -static __always_inline int __atomic_read(const atomic_t *v) +static __always_inline int __atomic_read(const int *ptr) { - int c; + int val; asm volatile( - " l %[c],%[counter]\n" - : [c] "=d" (c) : [counter] "R" (v->counter)); - return c; + " l %[val],%[ptr]\n" + : [val] "=d" (val) : [ptr] "R" (*ptr)); + return val; } -static __always_inline void __atomic_set(atomic_t *v, int i) +static __always_inline void __atomic_set(int *ptr, int val) { - if (__builtin_constant_p(i) && i >= S16_MIN && i <= S16_MAX) { + if (__builtin_constant_p(val) && val >= S16_MIN && val <= S16_MAX) { asm volatile( - " mvhi %[counter], %[i]\n" - : [counter] "=Q" (v->counter) : [i] "K" (i)); + " mvhi %[ptr],%[val]\n" + : [ptr] "=Q" (*ptr) : [val] "K" (val)); } else { asm volatile( - " st %[i],%[counter]\n" - : [counter] "=R" (v->counter) : [i] "d" (i)); + " st %[val],%[ptr]\n" + : [ptr] "=R" (*ptr) : [val] "d" (val)); } } -static __always_inline s64 __atomic64_read(const atomic64_t *v) +static __always_inline long __atomic64_read(const long *ptr) { - s64 c; + long val; asm volatile( - " lg %[c],%[counter]\n" - : [c] "=d" (c) : [counter] "RT" (v->counter)); - return c; + " lg %[val],%[ptr]\n" + : [val] "=d" (val) : [ptr] "RT" (*ptr)); + return val; } -static __always_inline void __atomic64_set(atomic64_t *v, s64 i) +static __always_inline void __atomic64_set(long *ptr, long val) { - if (__builtin_constant_p(i) && i >= S16_MIN && i <= S16_MAX) { + if (__builtin_constant_p(val) && val >= S16_MIN && val <= S16_MAX) { asm volatile( - " mvghi %[counter], %[i]\n" - : [counter] "=Q" (v->counter) : [i] "K" (i)); + " mvghi %[ptr],%[val]\n" + : [ptr] "=Q" (*ptr) : [val] "K" (val)); } else { asm volatile( - " stg %[i],%[counter]\n" - : [counter] "=RT" (v->counter) : [i] "d" (i)); + " stg %[val],%[ptr]\n" + : [ptr] "=RT" (*ptr) : [val] "d" (val)); } } @@ -73,7 +74,7 @@ static __always_inline op_type op_name(op_type val, op_type *ptr) \ } \ #define __ATOMIC_OPS(op_name, op_type, op_string) \ - __ATOMIC_OP(op_name, op_type, op_string, "\n") \ + __ATOMIC_OP(op_name, op_type, op_string, "") \ __ATOMIC_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n") __ATOMIC_OPS(__atomic_add, int, "laa") @@ -99,7 +100,7 @@ static __always_inline void op_name(op_type val, op_type *ptr) \ } #define __ATOMIC_CONST_OPS(op_name, op_type, op_string) \ - __ATOMIC_CONST_OP(op_name, op_type, op_string, "\n") \ + __ATOMIC_CONST_OP(op_name, op_type, op_string, "") \ __ATOMIC_CONST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n") __ATOMIC_CONST_OPS(__atomic_add_const, int, "asi") @@ -169,4 +170,76 @@ __ATOMIC64_OPS(__atomic64_xor, "xgr") #endif /* MARCH_HAS_Z196_FEATURES */ +#if defined(MARCH_HAS_Z196_FEATURES) && defined(__HAVE_ASM_FLAG_OUTPUTS__) + +#define __ATOMIC_TEST_OP(op_name, op_type, op_string, op_barrier) \ +static __always_inline bool op_name(op_type val, op_type *ptr) \ +{ \ + op_type tmp; \ + int cc; \ + \ + asm volatile( \ + op_string " %[tmp],%[val],%[ptr]\n" \ + op_barrier \ + : "=@cc" (cc), [tmp] "=d" (tmp), [ptr] "+QS" (*ptr) \ + : [val] "d" (val) \ + : "memory"); \ + return (cc == 0) || (cc == 2); \ +} \ + +#define __ATOMIC_TEST_OPS(op_name, op_type, op_string) \ + __ATOMIC_TEST_OP(op_name, op_type, op_string, "") \ + __ATOMIC_TEST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n") + +__ATOMIC_TEST_OPS(__atomic_add_and_test, int, "laal") +__ATOMIC_TEST_OPS(__atomic64_add_and_test, long, "laalg") + +#undef __ATOMIC_TEST_OPS +#undef __ATOMIC_TEST_OP + +#define __ATOMIC_CONST_TEST_OP(op_name, op_type, op_string, op_barrier) \ +static __always_inline bool op_name(op_type val, op_type *ptr) \ +{ \ + int cc; \ + \ + asm volatile( \ + op_string " %[ptr],%[val]\n" \ + op_barrier \ + : "=@cc" (cc), [ptr] "+QS" (*ptr) \ + : [val] "i" (val) \ + : "memory"); \ + return (cc == 0) || (cc == 2); \ +} + +#define __ATOMIC_CONST_TEST_OPS(op_name, op_type, op_string) \ + __ATOMIC_CONST_TEST_OP(op_name, op_type, op_string, "") \ + __ATOMIC_CONST_TEST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n") + +__ATOMIC_CONST_TEST_OPS(__atomic_add_const_and_test, int, "alsi") +__ATOMIC_CONST_TEST_OPS(__atomic64_add_const_and_test, long, "algsi") + +#undef __ATOMIC_CONST_TEST_OPS +#undef __ATOMIC_CONST_TEST_OP + +#else /* defined(MARCH_HAS_Z196_FEATURES) && defined(__HAVE_ASM_FLAG_OUTPUTS__) */ + +#define __ATOMIC_TEST_OP(op_name, op_func, op_type) \ +static __always_inline bool op_name(op_type val, op_type *ptr) \ +{ \ + return op_func(val, ptr) == -val; \ +} + +__ATOMIC_TEST_OP(__atomic_add_and_test, __atomic_add, int) +__ATOMIC_TEST_OP(__atomic_add_and_test_barrier, __atomic_add_barrier, int) +__ATOMIC_TEST_OP(__atomic_add_const_and_test, __atomic_add, int) +__ATOMIC_TEST_OP(__atomic_add_const_and_test_barrier, __atomic_add_barrier, int) +__ATOMIC_TEST_OP(__atomic64_add_and_test, __atomic64_add, long) +__ATOMIC_TEST_OP(__atomic64_add_and_test_barrier, __atomic64_add_barrier, long) +__ATOMIC_TEST_OP(__atomic64_add_const_and_test, __atomic64_add, long) +__ATOMIC_TEST_OP(__atomic64_add_const_and_test_barrier, __atomic64_add_barrier, long) + +#undef __ATOMIC_TEST_OP + +#endif /* defined(MARCH_HAS_Z196_FEATURES) && defined(__HAVE_ASM_FLAG_OUTPUTS__) */ + #endif /* __ARCH_S390_ATOMIC_OPS__ */ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 54a079cd39ed..d5125296ade2 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -36,184 +36,41 @@ #include #include #include -#include -#include +#include -#define __BITOPS_WORDS(bits) (((bits) + BITS_PER_LONG - 1) / BITS_PER_LONG) +#define arch___set_bit generic___set_bit +#define arch___clear_bit generic___clear_bit +#define arch___change_bit generic___change_bit +#define arch___test_and_set_bit generic___test_and_set_bit +#define arch___test_and_clear_bit generic___test_and_clear_bit +#define arch___test_and_change_bit generic___test_and_change_bit +#define arch_test_bit_acquire generic_test_bit_acquire -static inline unsigned long * -__bitops_word(unsigned long nr, const volatile unsigned long *ptr) +static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsigned long *ptr) { - unsigned long addr; +#ifdef __HAVE_ASM_FLAG_OUTPUTS__ + const volatile unsigned char *addr; + unsigned long mask; + int cc; - addr = (unsigned long)ptr + ((nr ^ (nr & (BITS_PER_LONG - 1))) >> 3); - return (unsigned long *)addr; + if (__builtin_constant_p(nr)) { + addr = (const volatile unsigned char *)ptr; + addr += (nr ^ (BITS_PER_LONG - BITS_PER_BYTE)) / BITS_PER_BYTE; + mask = 1UL << (nr & (BITS_PER_BYTE - 1)); + asm volatile( + " tm %[addr],%[mask]\n" + : "=@cc" (cc) + : [addr] "Q" (*addr), [mask] "I" (mask) + ); + return cc == 3; + } +#endif + return generic_test_bit(nr, ptr); } -static inline unsigned long __bitops_mask(unsigned long nr) -{ - return 1UL << (nr & (BITS_PER_LONG - 1)); -} - -static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - - __atomic64_or(mask, (long *)addr); -} - -static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - - __atomic64_and(~mask, (long *)addr); -} - -static __always_inline void arch_change_bit(unsigned long nr, - volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - - __atomic64_xor(mask, (long *)addr); -} - -static inline bool arch_test_and_set_bit(unsigned long nr, - volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = __atomic64_or_barrier(mask, (long *)addr); - return old & mask; -} - -static inline bool arch_test_and_clear_bit(unsigned long nr, - volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = __atomic64_and_barrier(~mask, (long *)addr); - return old & mask; -} - -static inline bool arch_test_and_change_bit(unsigned long nr, - volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = __atomic64_xor_barrier(mask, (long *)addr); - return old & mask; -} - -static __always_inline void -arch___set_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - - *p |= mask; -} - -static __always_inline void -arch___clear_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - - *p &= ~mask; -} - -static __always_inline void -arch___change_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - - *p ^= mask; -} - -static __always_inline bool -arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = *p; - *p |= mask; - return old & mask; -} - -static __always_inline bool -arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = *p; - *p &= ~mask; - return old & mask; -} - -static __always_inline bool -arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = *p; - *p ^= mask; - return old & mask; -} - -#define arch_test_bit generic_test_bit -#define arch_test_bit_acquire generic_test_bit_acquire - -static inline bool arch_test_and_set_bit_lock(unsigned long nr, - volatile unsigned long *ptr) -{ - if (arch_test_bit(nr, ptr)) - return true; - return arch_test_and_set_bit(nr, ptr); -} - -static inline void arch_clear_bit_unlock(unsigned long nr, - volatile unsigned long *ptr) -{ - smp_mb__before_atomic(); - arch_clear_bit(nr, ptr); -} - -static inline void arch___clear_bit_unlock(unsigned long nr, - volatile unsigned long *ptr) -{ - smp_mb(); - arch___clear_bit(nr, ptr); -} - -static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, - volatile unsigned long *ptr) -{ - unsigned long old; - - old = __atomic64_xor_barrier(mask, (long *)ptr); - return old & BIT(7); -} -#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte - -#include -#include -#include +#include +#include +#include /* * Functions which use MSB0 bit numbering. diff --git a/arch/s390/include/asm/boot_data.h b/arch/s390/include/asm/boot_data.h index f7eed27b3220..f55f8227058e 100644 --- a/arch/s390/include/asm/boot_data.h +++ b/arch/s390/include/asm/boot_data.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_S390_BOOT_DATA_H +#include #include #include @@ -15,4 +16,54 @@ extern unsigned long ipl_cert_list_size; extern unsigned long early_ipl_comp_list_addr; extern unsigned long early_ipl_comp_list_size; +extern char boot_rb[PAGE_SIZE * 2]; +extern bool boot_earlyprintk; +extern size_t boot_rb_off; +extern char bootdebug_filter[128]; +extern bool bootdebug; + +#define boot_rb_foreach(cb) \ + do { \ + size_t off = boot_rb_off + strlen(boot_rb + boot_rb_off) + 1; \ + size_t len; \ + for (; off < sizeof(boot_rb) && (len = strlen(boot_rb + off)); off += len + 1) \ + cb(boot_rb + off); \ + for (off = 0; off < boot_rb_off && (len = strlen(boot_rb + off)); off += len + 1) \ + cb(boot_rb + off); \ + } while (0) + +/* + * bootdebug_filter is a comma separated list of strings, + * where each string can be a prefix of the message. + */ +static inline bool bootdebug_filter_match(const char *buf) +{ + char *p = bootdebug_filter, *s; + char *end; + + if (!*p) + return true; + + end = p + strlen(p); + while (p < end) { + p = skip_spaces(p); + s = memscan(p, ',', end - p); + if (!strncmp(p, buf, s - p)) + return true; + p = s + 1; + } + return false; +} + +static inline const char *skip_timestamp(const char *buf) +{ +#ifdef CONFIG_PRINTK_TIME + const char *p = memchr(buf, ']', strlen(buf)); + + if (p && p[1] == ' ') + return p + 2; +#endif + return buf; +} + #endif /* _ASM_S390_BOOT_DATA_H */ diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 46f5c9660616..d86dea5900e7 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -25,7 +25,7 @@ static inline __wsum cksm(const void *buff, int len, __wsum sum) instrument_read(buff, len); kmsan_check_memory(buff, len); - asm volatile("\n" + asm volatile( "0: cksm %[sum],%[rp]\n" " jo 0b\n" : [sum] "+&d" (sum), [rp] "+&d" (rp.pair) : : "cc", "memory"); diff --git a/arch/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h index 638137d46c85..a03f64033760 100644 --- a/arch/s390/include/asm/css_chars.h +++ b/arch/s390/include/asm/css_chars.h @@ -25,7 +25,7 @@ struct css_general_char { u64 : 2; u64 : 3; - u64 aif_osa : 1; /* bit 67 */ + u64 aif_qdio : 1;/* bit 67 */ u64 : 12; u64 eadm_rf : 1; /* bit 80 */ u64 : 1; diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index a7f7bdc9e19c..6375276d94ea 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -85,6 +85,10 @@ int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view, int area, debug_entry_t *entry, char *out_buf, size_t out_buf_size); +#define DEBUG_SPRINTF_MAX_ARGS 10 +int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, + char *out_buf, size_t out_buf_size, + const char *inbuf); struct debug_view { char name[DEBUG_MAX_NAME_LEN]; debug_prolog_proc_t *prolog_proc; @@ -114,6 +118,9 @@ debug_info_t *debug_register_mode(const char *name, int pages, int nr_areas, int buf_size, umode_t mode, uid_t uid, gid_t gid); +ssize_t debug_dump(debug_info_t *id, struct debug_view *view, + char *buf, size_t buf_size, bool reverse); + void debug_unregister(debug_info_t *id); void debug_set_level(debug_info_t *id, int new_level); diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h index e1316e181230..5790630e31f0 100644 --- a/arch/s390/include/asm/diag.h +++ b/arch/s390/include/asm/diag.h @@ -36,8 +36,10 @@ enum diag_stat_enum { DIAG_STAT_X2FC, DIAG_STAT_X304, DIAG_STAT_X308, + DIAG_STAT_X310, DIAG_STAT_X318, DIAG_STAT_X320, + DIAG_STAT_X324, DIAG_STAT_X49C, DIAG_STAT_X500, NR_DIAG_STAT diff --git a/arch/s390/include/asm/ebcdic.h b/arch/s390/include/asm/ebcdic.h index efb50fc6866c..7164cb658435 100644 --- a/arch/s390/include/asm/ebcdic.h +++ b/arch/s390/include/asm/ebcdic.h @@ -22,18 +22,18 @@ extern __u8 _ebc_toupper[256]; /* EBCDIC -> uppercase */ static inline void codepage_convert(const __u8 *codepage, volatile char *addr, unsigned long nr) { - if (nr-- <= 0) + if (!nr--) return; asm volatile( - " bras 1,1f\n" - " tr 0(1,%0),0(%2)\n" - "0: tr 0(256,%0),0(%2)\n" + " j 2f\n" + "0: tr 0(1,%0),0(%2)\n" + "1: tr 0(256,%0),0(%2)\n" " la %0,256(%0)\n" - "1: ahi %1,-256\n" - " jnm 0b\n" - " ex %1,0(1)" + "2: aghi %1,-256\n" + " jnm 1b\n" + " exrl %1,0b" : "+&a" (addr), "+&a" (nr) - : "a" (codepage) : "cc", "memory", "1"); + : "a" (codepage) : "cc", "memory"); } #define ASCEBC(addr,nr) codepage_convert(_ascebc, addr, nr) diff --git a/arch/s390/include/asm/fprobe.h b/arch/s390/include/asm/fprobe.h new file mode 100644 index 000000000000..5ef600b372f4 --- /dev/null +++ b/arch/s390/include/asm/fprobe.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_S390_FPROBE_H +#define _ASM_S390_FPROBE_H + +#include + +#undef FPROBE_HEADER_MSB_PATTERN +#define FPROBE_HEADER_MSB_PATTERN 0 + +#endif /* _ASM_S390_FPROBE_H */ diff --git a/arch/s390/include/asm/fpu-insn.h b/arch/s390/include/asm/fpu-insn.h index c1e2e521d9af..f668bffd6dd3 100644 --- a/arch/s390/include/asm/fpu-insn.h +++ b/arch/s390/include/asm/fpu-insn.h @@ -100,19 +100,12 @@ static __always_inline void fpu_lfpc(unsigned int *fpc) */ static inline void fpu_lfpc_safe(unsigned int *fpc) { - u32 tmp; - instrument_read(fpc, sizeof(*fpc)); - asm volatile("\n" - "0: lfpc %[fpc]\n" - "1: nopr %%r7\n" - ".pushsection .fixup, \"ax\"\n" - "2: lghi %[tmp],0\n" - " sfpc %[tmp]\n" - " jg 1b\n" - ".popsection\n" - EX_TABLE(1b, 2b) - : [tmp] "=d" (tmp) + asm_inline volatile( + " lfpc %[fpc]\n" + "0: nopr %%r7\n" + EX_TABLE_FPC(0b, 0b) + : : [fpc] "Q" (*fpc) : "memory"); } @@ -183,21 +176,7 @@ static __always_inline void fpu_vgfmg(u8 v1, u8 v2, u8 v3) : "memory"); } -#ifdef CONFIG_CC_IS_CLANG - -static __always_inline void fpu_vl(u8 v1, const void *vxr) -{ - instrument_read(vxr, sizeof(__vector128)); - asm volatile("\n" - " la 1,%[vxr]\n" - " VL %[v1],0,,1\n" - : - : [vxr] "R" (*(__vector128 *)vxr), - [v1] "I" (v1) - : "memory", "1"); -} - -#else /* CONFIG_CC_IS_CLANG */ +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS static __always_inline void fpu_vl(u8 v1, const void *vxr) { @@ -209,7 +188,21 @@ static __always_inline void fpu_vl(u8 v1, const void *vxr) : "memory"); } -#endif /* CONFIG_CC_IS_CLANG */ +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ + +static __always_inline void fpu_vl(u8 v1, const void *vxr) +{ + instrument_read(vxr, sizeof(__vector128)); + asm volatile( + " la 1,%[vxr]\n" + " VL %[v1],0,,1\n" + : + : [vxr] "R" (*(__vector128 *)vxr), + [v1] "I" (v1) + : "memory", "1"); +} + +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vleib(u8 v, s16 val, u8 index) { @@ -238,25 +231,7 @@ static __always_inline u64 fpu_vlgvf(u8 v, u16 index) return val; } -#ifdef CONFIG_CC_IS_CLANG - -static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) -{ - unsigned int size; - - size = min(index + 1, sizeof(__vector128)); - instrument_read(vxr, size); - asm volatile("\n" - " la 1,%[vxr]\n" - " VLL %[v1],%[index],0,1\n" - : - : [vxr] "R" (*(u8 *)vxr), - [index] "d" (index), - [v1] "I" (v1) - : "memory", "1"); -} - -#else /* CONFIG_CC_IS_CLANG */ +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) { @@ -272,29 +247,27 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) : "memory"); } -#endif /* CONFIG_CC_IS_CLANG */ +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ -#ifdef CONFIG_CC_IS_CLANG +static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) +{ + unsigned int size; -#define fpu_vlm(_v1, _v3, _vxrs) \ -({ \ - unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128); \ - struct { \ - __vector128 _v[(_v3) - (_v1) + 1]; \ - } *_v = (void *)(_vxrs); \ - \ - instrument_read(_v, size); \ - asm volatile("\n" \ - " la 1,%[vxrs]\n" \ - " VLM %[v1],%[v3],0,1\n" \ - : \ - : [vxrs] "R" (*_v), \ - [v1] "I" (_v1), [v3] "I" (_v3) \ - : "memory", "1"); \ - (_v3) - (_v1) + 1; \ -}) + size = min(index + 1, sizeof(__vector128)); + instrument_read(vxr, size); + asm volatile( + " la 1,%[vxr]\n" + " VLL %[v1],%[index],0,1\n" + : + : [vxr] "R" (*(u8 *)vxr), + [index] "d" (index), + [v1] "I" (v1) + : "memory", "1"); +} -#else /* CONFIG_CC_IS_CLANG */ +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ + +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS #define fpu_vlm(_v1, _v3, _vxrs) \ ({ \ @@ -312,7 +285,27 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) (_v3) - (_v1) + 1; \ }) -#endif /* CONFIG_CC_IS_CLANG */ +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ + +#define fpu_vlm(_v1, _v3, _vxrs) \ +({ \ + unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128); \ + struct { \ + __vector128 _v[(_v3) - (_v1) + 1]; \ + } *_v = (void *)(_vxrs); \ + \ + instrument_read(_v, size); \ + asm volatile( \ + " la 1,%[vxrs]\n" \ + " VLM %[v1],%[v3],0,1\n" \ + : \ + : [vxrs] "R" (*_v), \ + [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory", "1"); \ + (_v3) - (_v1) + 1; \ +}) + +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vlr(u8 v1, u8 v2) { @@ -362,20 +355,7 @@ static __always_inline void fpu_vsrlb(u8 v1, u8 v2, u8 v3) : "memory"); } -#ifdef CONFIG_CC_IS_CLANG - -static __always_inline void fpu_vst(u8 v1, const void *vxr) -{ - instrument_write(vxr, sizeof(__vector128)); - asm volatile("\n" - " la 1,%[vxr]\n" - " VST %[v1],0,,1\n" - : [vxr] "=R" (*(__vector128 *)vxr) - : [v1] "I" (v1) - : "memory", "1"); -} - -#else /* CONFIG_CC_IS_CLANG */ +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS static __always_inline void fpu_vst(u8 v1, const void *vxr) { @@ -386,25 +366,22 @@ static __always_inline void fpu_vst(u8 v1, const void *vxr) : "memory"); } -#endif /* CONFIG_CC_IS_CLANG */ +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ -#ifdef CONFIG_CC_IS_CLANG - -static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) +static __always_inline void fpu_vst(u8 v1, const void *vxr) { - unsigned int size; - - size = min(index + 1, sizeof(__vector128)); - instrument_write(vxr, size); - asm volatile("\n" + instrument_write(vxr, sizeof(__vector128)); + asm volatile( " la 1,%[vxr]\n" - " VSTL %[v1],%[index],0,1\n" - : [vxr] "=R" (*(u8 *)vxr) - : [index] "d" (index), [v1] "I" (v1) + " VST %[v1],0,,1\n" + : [vxr] "=R" (*(__vector128 *)vxr) + : [v1] "I" (v1) : "memory", "1"); } -#else /* CONFIG_CC_IS_CLANG */ +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ + +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) { @@ -418,28 +395,25 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) : "memory"); } -#endif /* CONFIG_CC_IS_CLANG */ +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ -#ifdef CONFIG_CC_IS_CLANG +static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) +{ + unsigned int size; -#define fpu_vstm(_v1, _v3, _vxrs) \ -({ \ - unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128); \ - struct { \ - __vector128 _v[(_v3) - (_v1) + 1]; \ - } *_v = (void *)(_vxrs); \ - \ - instrument_write(_v, size); \ - asm volatile("\n" \ - " la 1,%[vxrs]\n" \ - " VSTM %[v1],%[v3],0,1\n" \ - : [vxrs] "=R" (*_v) \ - : [v1] "I" (_v1), [v3] "I" (_v3) \ - : "memory", "1"); \ - (_v3) - (_v1) + 1; \ -}) + size = min(index + 1, sizeof(__vector128)); + instrument_write(vxr, size); + asm volatile( + " la 1,%[vxr]\n" + " VSTL %[v1],%[index],0,1\n" + : [vxr] "=R" (*(u8 *)vxr) + : [index] "d" (index), [v1] "I" (v1) + : "memory", "1"); +} -#else /* CONFIG_CC_IS_CLANG */ +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ + +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS #define fpu_vstm(_v1, _v3, _vxrs) \ ({ \ @@ -456,7 +430,26 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) (_v3) - (_v1) + 1; \ }) -#endif /* CONFIG_CC_IS_CLANG */ +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ + +#define fpu_vstm(_v1, _v3, _vxrs) \ +({ \ + unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128); \ + struct { \ + __vector128 _v[(_v3) - (_v1) + 1]; \ + } *_v = (void *)(_vxrs); \ + \ + instrument_write(_v, size); \ + asm volatile( \ + " la 1,%[vxrs]\n" \ + " VSTM %[v1],%[v3],0,1\n" \ + : [vxrs] "=R" (*_v) \ + : [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory", "1"); \ + (_v3) - (_v1) + 1; \ +}) + +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vupllf(u8 v1, u8 v2) { diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index fc97d75dc752..185331e91f83 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -39,6 +39,7 @@ struct dyn_arch_ftrace { }; struct module; struct dyn_ftrace; +struct ftrace_ops; bool ftrace_need_init_nop(void); #define ftrace_need_init_nop ftrace_need_init_nop @@ -50,6 +51,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; } +#define ftrace_get_symaddr(fentry_ip) ((unsigned long)(fentry_ip)) #include @@ -62,23 +64,6 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return NULL; } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long gpr2; - unsigned long fp; -}; - -static __always_inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->gpr2; -} - -static __always_inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->fp; -} -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) @@ -86,6 +71,25 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, arch_ftrace_regs(fregs)->regs.psw.addr = ip; } +#undef ftrace_regs_get_frame_pointer +static __always_inline unsigned long +ftrace_regs_get_frame_pointer(struct ftrace_regs *fregs) +{ + return ftrace_regs_get_stack_pointer(fregs); +} + +static __always_inline unsigned long +ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->regs.gprs[14]; +} + +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->psw.mask = 0; \ + (_regs)->psw.addr = arch_ftrace_regs(fregs)->regs.psw.addr; \ + (_regs)->gprs[15] = arch_ftrace_regs(fregs)->regs.gprs[15]; \ + } while (0) + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* * When an ftrace registered caller is tracing a function that is @@ -126,6 +130,10 @@ static inline bool arch_syscall_match_sym_name(const char *sym, return !strcmp(sym + 7, name) || !strcmp(sym + 8, name); } +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#define ftrace_graph_func ftrace_graph_func + #endif /* __ASSEMBLY__ */ #ifdef CONFIG_FUNCTION_TRACER diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h index eaeaeb3ff0be..f5781794356b 100644 --- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -2,80 +2,95 @@ #ifndef _ASM_S390_FUTEX_H #define _ASM_S390_FUTEX_H +#include #include #include #include #include #include -#define __futex_atomic_op(insn, ret, oldval, newval, uaddr, oparg) \ - asm volatile( \ - " sacf 256\n" \ - "0: l %1,0(%6)\n" \ - "1:"insn \ - "2: cs %1,%2,0(%6)\n" \ - "3: jl 1b\n" \ - " lhi %0,0\n" \ - "4: sacf 768\n" \ - EX_TABLE(0b,4b) EX_TABLE(1b,4b) \ - EX_TABLE(2b,4b) EX_TABLE(3b,4b) \ - : "=d" (ret), "=&d" (oldval), "=&d" (newval), \ - "=m" (*uaddr) \ - : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \ - "m" (*uaddr) : "cc"); +#define FUTEX_OP_FUNC(name, insn) \ +static uaccess_kmsan_or_inline int \ +__futex_atomic_##name(int oparg, int *old, u32 __user *uaddr) \ +{ \ + int rc, new; \ + \ + instrument_copy_from_user_before(old, uaddr, sizeof(*old)); \ + asm_inline volatile( \ + " sacf 256\n" \ + "0: l %[old],%[uaddr]\n" \ + "1:"insn \ + "2: cs %[old],%[new],%[uaddr]\n" \ + "3: jl 1b\n" \ + " lhi %[rc],0\n" \ + "4: sacf 768\n" \ + EX_TABLE_UA_FAULT(0b, 4b, %[rc]) \ + EX_TABLE_UA_FAULT(1b, 4b, %[rc]) \ + EX_TABLE_UA_FAULT(2b, 4b, %[rc]) \ + EX_TABLE_UA_FAULT(3b, 4b, %[rc]) \ + : [rc] "=d" (rc), [old] "=&d" (*old), \ + [new] "=&d" (new), [uaddr] "+Q" (*uaddr) \ + : [oparg] "d" (oparg) \ + : "cc"); \ + if (!rc) \ + instrument_copy_from_user_after(old, uaddr, sizeof(*old), 0); \ + return rc; \ +} -static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, - u32 __user *uaddr) +FUTEX_OP_FUNC(set, "lr %[new],%[oparg]\n") +FUTEX_OP_FUNC(add, "lr %[new],%[old]\n ar %[new],%[oparg]\n") +FUTEX_OP_FUNC(or, "lr %[new],%[old]\n or %[new],%[oparg]\n") +FUTEX_OP_FUNC(and, "lr %[new],%[old]\n nr %[new],%[oparg]\n") +FUTEX_OP_FUNC(xor, "lr %[new],%[old]\n xr %[new],%[oparg]\n") + +static inline +int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int oldval = 0, newval, ret; + int old, rc; switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("lr %2,%5\n", - ret, oldval, newval, uaddr, oparg); + rc = __futex_atomic_set(oparg, &old, uaddr); break; case FUTEX_OP_ADD: - __futex_atomic_op("lr %2,%1\nar %2,%5\n", - ret, oldval, newval, uaddr, oparg); + rc = __futex_atomic_add(oparg, &old, uaddr); break; case FUTEX_OP_OR: - __futex_atomic_op("lr %2,%1\nor %2,%5\n", - ret, oldval, newval, uaddr, oparg); + rc = __futex_atomic_or(oparg, &old, uaddr); break; case FUTEX_OP_ANDN: - __futex_atomic_op("lr %2,%1\nnr %2,%5\n", - ret, oldval, newval, uaddr, oparg); + rc = __futex_atomic_and(~oparg, &old, uaddr); break; case FUTEX_OP_XOR: - __futex_atomic_op("lr %2,%1\nxr %2,%5\n", - ret, oldval, newval, uaddr, oparg); + rc = __futex_atomic_xor(oparg, &old, uaddr); break; default: - ret = -ENOSYS; + rc = -ENOSYS; } - - if (!ret) - *oval = oldval; - - return ret; + if (!rc) + *oval = old; + return rc; } -static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, - u32 oldval, u32 newval) +static uaccess_kmsan_or_inline +int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { - int ret; + int rc; - asm volatile( - " sacf 256\n" - "0: cs %1,%4,0(%5)\n" - "1: la %0,0\n" - "2: sacf 768\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) - : "=d" (ret), "+d" (oldval), "=m" (*uaddr) - : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr) + instrument_copy_from_user_before(uval, uaddr, sizeof(*uval)); + asm_inline volatile( + " sacf 256\n" + "0: cs %[old],%[new],%[uaddr]\n" + "1: lhi %[rc],0\n" + "2: sacf 768\n" + EX_TABLE_UA_FAULT(0b, 2b, %[rc]) + EX_TABLE_UA_FAULT(1b, 2b, %[rc]) + : [rc] "=d" (rc), [old] "+d" (oldval), [uaddr] "+Q" (*uaddr) + : [new] "d" (newval) : "cc", "memory"); *uval = oldval; - return ret; + instrument_copy_from_user_after(uval, uaddr, sizeof(*uval), 0); + return rc; } #endif /* _ASM_S390_FUTEX_H */ diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index a40664b236e9..7c52acaf9f82 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -20,12 +20,13 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz); void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); + pte_t *ptep, pte_t pte); + #define __HAVE_ARCH_HUGE_PTEP_GET -extern pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep); + #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR -extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep); +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); static inline void arch_clear_hugetlb_flags(struct folio *folio) { @@ -56,6 +57,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, pte_t pte, int dirty) { int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte); + if (changed) { huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); @@ -68,21 +70,10 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep); + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); } -#define __HAVE_ARCH_HUGE_PTE_NONE -static inline int huge_pte_none(pte_t pte) -{ - return pte_none(pte); -} - -#define __HAVE_ARCH_HUGE_PTE_NONE_MOSTLY -static inline int huge_pte_none_mostly(pte_t pte) -{ - return huge_pte_none(pte) || is_pte_marker(pte); -} - #define __HAVE_ARCH_HUGE_PTE_MKUFFD_WP static inline pte_t huge_pte_mkuffd_wp(pte_t pte) { diff --git a/arch/s390/include/asm/page-states.h b/arch/s390/include/asm/page-states.h index 08fcbd628120..794fdb21500a 100644 --- a/arch/s390/include/asm/page-states.h +++ b/arch/s390/include/asm/page-states.h @@ -7,7 +7,6 @@ #ifndef PAGE_STATES_H #define PAGE_STATES_H -#include #include #define ESSA_GET_STATE 0 @@ -21,7 +20,7 @@ #define ESSA_MAX ESSA_SET_STABLE_NODAT -extern int __bootdata_preserved(cmma_flag); +extern int cmma_flag; static __always_inline unsigned long essa(unsigned long paddr, unsigned char cmd) { diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 4f43cdd9835b..1ff145f7b52b 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -184,7 +184,11 @@ extern struct vm_layout vm_layout; #define __kaslr_offset vm_layout.kaslr_offset #define __kaslr_offset_phys vm_layout.kaslr_offset_phys +#ifdef CONFIG_RANDOMIZE_IDENTITY_BASE #define __identity_base vm_layout.identity_base +#else +#define __identity_base 0UL +#endif #define ident_map_size vm_layout.identity_size static inline unsigned long kaslr_offset(void) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 7b84ef6dc4b6..b19b6ed2ab53 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -53,29 +53,42 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address) { unsigned long *table = crst_table_alloc(mm); - if (table) - crst_table_init(table, _REGION2_ENTRY_EMPTY); + if (!table) + return NULL; + crst_table_init(table, _REGION2_ENTRY_EMPTY); + pagetable_p4d_ctor(virt_to_ptdesc(table)); + return (p4d_t *) table; } static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) { - if (!mm_p4d_folded(mm)) - crst_table_free(mm, (unsigned long *) p4d); + if (mm_p4d_folded(mm)) + return; + + pagetable_dtor(virt_to_ptdesc(p4d)); + crst_table_free(mm, (unsigned long *) p4d); } static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { unsigned long *table = crst_table_alloc(mm); - if (table) - crst_table_init(table, _REGION3_ENTRY_EMPTY); + + if (!table) + return NULL; + crst_table_init(table, _REGION3_ENTRY_EMPTY); + pagetable_pud_ctor(virt_to_ptdesc(table)); + return (pud_t *) table; } static inline void pud_free(struct mm_struct *mm, pud_t *pud) { - if (!mm_pud_folded(mm)) - crst_table_free(mm, (unsigned long *) pud); + if (mm_pud_folded(mm)) + return; + + pagetable_dtor(virt_to_ptdesc(pud)); + crst_table_free(mm, (unsigned long *) pud); } static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) @@ -96,7 +109,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { if (mm_pmd_folded(mm)) return; - pagetable_pmd_dtor(virt_to_ptdesc(pmd)); + pagetable_dtor(virt_to_ptdesc(pmd)); crst_table_free(mm, (unsigned long *) pmd); } @@ -117,11 +130,18 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - return (pgd_t *) crst_table_alloc(mm); + unsigned long *table = crst_table_alloc(mm); + + if (!table) + return NULL; + pagetable_pgd_ctor(virt_to_ptdesc(table)); + + return (pgd_t *) table; } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { + pagetable_dtor(virt_to_ptdesc(pgd)); crst_table_free(mm, (unsigned long *) pgd); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 48268095b0a3..a3b51056a177 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -35,7 +34,7 @@ enum { PG_DIRECT_MAP_MAX }; -extern atomic_long_t __bootdata_preserved(direct_pages_count[PG_DIRECT_MAP_MAX]); +extern atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX]; static inline void update_page_count(int level, long count) { @@ -85,14 +84,14 @@ extern unsigned long zero_page_mask; * happen without trampolines and in addition the placement within a * 2GB frame is branch prediction unit friendly. */ -extern unsigned long __bootdata_preserved(VMALLOC_START); -extern unsigned long __bootdata_preserved(VMALLOC_END); +extern unsigned long VMALLOC_START; +extern unsigned long VMALLOC_END; #define VMALLOC_DEFAULT_SIZE ((512UL << 30) - MODULES_LEN) -extern struct page *__bootdata_preserved(vmemmap); -extern unsigned long __bootdata_preserved(vmemmap_size); +extern struct page *vmemmap; +extern unsigned long vmemmap_size; -extern unsigned long __bootdata_preserved(MODULES_VADDR); -extern unsigned long __bootdata_preserved(MODULES_END); +extern unsigned long MODULES_VADDR; +extern unsigned long MODULES_END; #define MODULES_VADDR MODULES_VADDR #define MODULES_END MODULES_END #define MODULES_LEN (1UL << 31) @@ -125,6 +124,8 @@ static inline int is_module_addr(void *addr) #define KASLR_LEN 0UL #endif +void setup_protection_map(void); + /* * A 64 bit pagetable entry of S390 has following format: * | PFRA |0IPC| OS | @@ -443,98 +444,107 @@ static inline int is_module_addr(void *addr) /* * Page protection definitions. */ -#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_INVALID | _PAGE_PROTECT) -#define PAGE_RO __pgprot(_PAGE_PRESENT | _PAGE_READ | \ +#define __PAGE_NONE (_PAGE_PRESENT | _PAGE_INVALID | _PAGE_PROTECT) +#define __PAGE_RO (_PAGE_PRESENT | _PAGE_READ | \ _PAGE_NOEXEC | _PAGE_INVALID | _PAGE_PROTECT) -#define PAGE_RX __pgprot(_PAGE_PRESENT | _PAGE_READ | \ +#define __PAGE_RX (_PAGE_PRESENT | _PAGE_READ | \ _PAGE_INVALID | _PAGE_PROTECT) -#define PAGE_RW __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ +#define __PAGE_RW (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ _PAGE_NOEXEC | _PAGE_INVALID | _PAGE_PROTECT) -#define PAGE_RWX __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ +#define __PAGE_RWX (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ _PAGE_INVALID | _PAGE_PROTECT) - -#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ +#define __PAGE_SHARED (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ _PAGE_YOUNG | _PAGE_DIRTY | _PAGE_NOEXEC) -#define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ +#define __PAGE_KERNEL (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ _PAGE_YOUNG | _PAGE_DIRTY | _PAGE_NOEXEC) -#define PAGE_KERNEL_RO __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \ +#define __PAGE_KERNEL_RO (_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \ _PAGE_PROTECT | _PAGE_NOEXEC) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ - _PAGE_YOUNG | _PAGE_DIRTY) -/* - * On s390 the page table entry has an invalid bit and a read-only bit. - * Read permission implies execute permission and write permission - * implies read permission. - */ - /*xwr*/ +extern unsigned long page_noexec_mask; + +#define __pgprot_page_mask(x) __pgprot((x) & page_noexec_mask) + +#define PAGE_NONE __pgprot_page_mask(__PAGE_NONE) +#define PAGE_RO __pgprot_page_mask(__PAGE_RO) +#define PAGE_RX __pgprot_page_mask(__PAGE_RX) +#define PAGE_RW __pgprot_page_mask(__PAGE_RW) +#define PAGE_RWX __pgprot_page_mask(__PAGE_RWX) +#define PAGE_SHARED __pgprot_page_mask(__PAGE_SHARED) +#define PAGE_KERNEL __pgprot_page_mask(__PAGE_KERNEL) +#define PAGE_KERNEL_RO __pgprot_page_mask(__PAGE_KERNEL_RO) /* * Segment entry (large page) protection definitions. */ -#define SEGMENT_NONE __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_NONE (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_INVALID | \ _SEGMENT_ENTRY_PROTECT) -#define SEGMENT_RO __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_RO (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_PROTECT | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_NOEXEC) -#define SEGMENT_RX __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_RX (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_PROTECT | \ _SEGMENT_ENTRY_READ) -#define SEGMENT_RW __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_RW (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_WRITE | \ _SEGMENT_ENTRY_NOEXEC) -#define SEGMENT_RWX __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_RWX (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_WRITE) -#define SEGMENT_KERNEL __pgprot(_SEGMENT_ENTRY | \ +#define __SEGMENT_KERNEL (_SEGMENT_ENTRY | \ _SEGMENT_ENTRY_LARGE | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_WRITE | \ _SEGMENT_ENTRY_YOUNG | \ _SEGMENT_ENTRY_DIRTY | \ _SEGMENT_ENTRY_NOEXEC) -#define SEGMENT_KERNEL_RO __pgprot(_SEGMENT_ENTRY | \ +#define __SEGMENT_KERNEL_RO (_SEGMENT_ENTRY | \ _SEGMENT_ENTRY_LARGE | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_YOUNG | \ _SEGMENT_ENTRY_PROTECT | \ _SEGMENT_ENTRY_NOEXEC) -#define SEGMENT_KERNEL_EXEC __pgprot(_SEGMENT_ENTRY | \ - _SEGMENT_ENTRY_LARGE | \ - _SEGMENT_ENTRY_READ | \ - _SEGMENT_ENTRY_WRITE | \ - _SEGMENT_ENTRY_YOUNG | \ - _SEGMENT_ENTRY_DIRTY) + +extern unsigned long segment_noexec_mask; + +#define __pgprot_segment_mask(x) __pgprot((x) & segment_noexec_mask) + +#define SEGMENT_NONE __pgprot_segment_mask(__SEGMENT_NONE) +#define SEGMENT_RO __pgprot_segment_mask(__SEGMENT_RO) +#define SEGMENT_RX __pgprot_segment_mask(__SEGMENT_RX) +#define SEGMENT_RW __pgprot_segment_mask(__SEGMENT_RW) +#define SEGMENT_RWX __pgprot_segment_mask(__SEGMENT_RWX) +#define SEGMENT_KERNEL __pgprot_segment_mask(__SEGMENT_KERNEL) +#define SEGMENT_KERNEL_RO __pgprot_segment_mask(__SEGMENT_KERNEL_RO) /* * Region3 entry (large page) protection definitions. */ -#define REGION3_KERNEL __pgprot(_REGION_ENTRY_TYPE_R3 | \ +#define __REGION3_KERNEL (_REGION_ENTRY_TYPE_R3 | \ _REGION3_ENTRY_PRESENT | \ - _REGION3_ENTRY_LARGE | \ - _REGION3_ENTRY_READ | \ - _REGION3_ENTRY_WRITE | \ - _REGION3_ENTRY_YOUNG | \ + _REGION3_ENTRY_LARGE | \ + _REGION3_ENTRY_READ | \ + _REGION3_ENTRY_WRITE | \ + _REGION3_ENTRY_YOUNG | \ _REGION3_ENTRY_DIRTY | \ _REGION_ENTRY_NOEXEC) -#define REGION3_KERNEL_RO __pgprot(_REGION_ENTRY_TYPE_R3 | \ - _REGION3_ENTRY_PRESENT | \ - _REGION3_ENTRY_LARGE | \ - _REGION3_ENTRY_READ | \ - _REGION3_ENTRY_YOUNG | \ - _REGION_ENTRY_PROTECT | \ - _REGION_ENTRY_NOEXEC) -#define REGION3_KERNEL_EXEC __pgprot(_REGION_ENTRY_TYPE_R3 | \ +#define __REGION3_KERNEL_RO (_REGION_ENTRY_TYPE_R3 | \ _REGION3_ENTRY_PRESENT | \ - _REGION3_ENTRY_LARGE | \ - _REGION3_ENTRY_READ | \ - _REGION3_ENTRY_WRITE | \ - _REGION3_ENTRY_YOUNG | \ - _REGION3_ENTRY_DIRTY) + _REGION3_ENTRY_LARGE | \ + _REGION3_ENTRY_READ | \ + _REGION3_ENTRY_YOUNG | \ + _REGION_ENTRY_PROTECT | \ + _REGION_ENTRY_NOEXEC) + +extern unsigned long region_noexec_mask; + +#define __pgprot_region_mask(x) __pgprot((x) & region_noexec_mask) + +#define REGION3_KERNEL __pgprot_region_mask(__REGION3_KERNEL) +#define REGION3_KERNEL_RO __pgprot_region_mask(__REGION3_KERNEL_RO) static inline bool mm_p4d_folded(struct mm_struct *mm) { @@ -1435,8 +1445,6 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) pte_t __pte; __pte = __pte(physpage | pgprot_val(pgprot)); - if (!MACHINE_HAS_NX) - __pte = clear_pte_bit(__pte, __pgprot(_PAGE_NOEXEC)); return pte_mkyoung(__pte); } @@ -1804,8 +1812,6 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t entry) { - if (!MACHINE_HAS_NX) - entry = clear_pmd_bit(entry, __pgprot(_SEGMENT_ENTRY_NOEXEC)); set_pmd(pmdp, entry); } diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h index 51b68a43e195..7ef3bbec98b0 100644 --- a/arch/s390/include/asm/physmem_info.h +++ b/arch/s390/include/asm/physmem_info.h @@ -26,7 +26,7 @@ enum reserved_range_type { RR_AMODE31, RR_IPLREPORT, RR_CERT_COMP_LIST, - RR_MEM_DETECT_EXTENDED, + RR_MEM_DETECT_EXT, RR_VMEM, RR_MAX }; @@ -128,7 +128,7 @@ static inline const char *get_rr_type_name(enum reserved_range_type t) RR_TYPE_NAME(AMODE31); RR_TYPE_NAME(IPLREPORT); RR_TYPE_NAME(CERT_COMP_LIST); - RR_TYPE_NAME(MEM_DETECT_EXTENDED); + RR_TYPE_NAME(MEM_DETECT_EXT); RR_TYPE_NAME(VMEM); default: return "UNKNOWN"; diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h index 2c29bdf12127..6ccd033acfe5 100644 --- a/arch/s390/include/asm/preempt.h +++ b/arch/s390/include/asm/preempt.h @@ -8,12 +8,19 @@ #include #include -#ifdef MARCH_HAS_Z196_FEATURES - /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 + +/* + * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such + * that a decrement hitting 0 means we can and should reschedule. + */ #define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) +/* + * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users + * that think a non-zero value indicates we cannot preempt. + */ static __always_inline int preempt_count(void) { return READ_ONCE(get_lowcore()->preempt_count) & ~PREEMPT_NEED_RESCHED; @@ -29,6 +36,15 @@ static __always_inline void preempt_count_set(int pc) } while (!arch_try_cmpxchg(&get_lowcore()->preempt_count, &old, new)); } +/* + * We fold the NEED_RESCHED bit into the preempt count such that + * preempt_enable() can decrement and test for needing to reschedule with a + * short instruction sequence. + * + * We invert the actual bit, so that when the decrement hits 0 we know we both + * need to resched (the bit is cleared) and can resched (no preempt count). + */ + static __always_inline void set_preempt_need_resched(void) { __atomic_and(~PREEMPT_NEED_RESCHED, &get_lowcore()->preempt_count); @@ -64,67 +80,24 @@ static __always_inline void __preempt_count_sub(int val) __preempt_count_add(-val); } +/* + * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ static __always_inline bool __preempt_count_dec_and_test(void) { - return __atomic_add(-1, &get_lowcore()->preempt_count) == 1; + return __atomic_add_const_and_test(-1, &get_lowcore()->preempt_count); } +/* + * Returns true when we need to resched and can (barring IRQ state). + */ static __always_inline bool should_resched(int preempt_offset) { - return unlikely(READ_ONCE(get_lowcore()->preempt_count) == - preempt_offset); + return unlikely(READ_ONCE(get_lowcore()->preempt_count) == preempt_offset); } -#else /* MARCH_HAS_Z196_FEATURES */ - -#define PREEMPT_ENABLED (0) - -static __always_inline int preempt_count(void) -{ - return READ_ONCE(get_lowcore()->preempt_count); -} - -static __always_inline void preempt_count_set(int pc) -{ - get_lowcore()->preempt_count = pc; -} - -static __always_inline void set_preempt_need_resched(void) -{ -} - -static __always_inline void clear_preempt_need_resched(void) -{ -} - -static __always_inline bool test_preempt_need_resched(void) -{ - return false; -} - -static __always_inline void __preempt_count_add(int val) -{ - get_lowcore()->preempt_count += val; -} - -static __always_inline void __preempt_count_sub(int val) -{ - get_lowcore()->preempt_count -= val; -} - -static __always_inline bool __preempt_count_dec_and_test(void) -{ - return !--get_lowcore()->preempt_count && tif_need_resched(); -} - -static __always_inline bool should_resched(int preempt_offset) -{ - return unlikely(preempt_count() == preempt_offset && - tif_need_resched()); -} - -#endif /* MARCH_HAS_Z196_FEATURES */ - #define init_task_preempt_count(p) do { } while (0) /* Deferred to CPU bringup time */ #define init_idle_preempt_count(p, cpu) do { } while (0) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 8761fd01a9f0..4f8d5592c298 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -163,8 +163,7 @@ static __always_inline void __stackleak_poison(unsigned long erase_low, " la %[addr],256(%[addr])\n" " brctg %[tmp],0b\n" "1: stg %[poison],0(%[addr])\n" - " larl %[tmp],3f\n" - " ex %[count],0(%[tmp])\n" + " exrl %[count],3f\n" " j 4f\n" "2: stg %[poison],0(%[addr])\n" " j 4f\n" diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index eb00fa1771da..18f37dff03c9 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -16,6 +16,11 @@ /* 24 + 16 * SCLP_MAX_CORES */ #define EXT_SCCB_READ_CPU (3 * PAGE_SIZE) +#define SCLP_ERRNOTIFY_AQ_RESET 0 +#define SCLP_ERRNOTIFY_AQ_REPAIR 1 +#define SCLP_ERRNOTIFY_AQ_INFO_LOG 2 +#define SCLP_ERRNOTIFY_AQ_OPTICS_DATA 3 + #ifndef __ASSEMBLY__ #include #include @@ -87,8 +92,10 @@ struct sclp_info { unsigned char has_kss : 1; unsigned char has_diag204_bif : 1; unsigned char has_gisaf : 1; + unsigned char has_diag310 : 1; unsigned char has_diag318 : 1; unsigned char has_diag320 : 1; + unsigned char has_diag324 : 1; unsigned char has_sipl : 1; unsigned char has_sipl_eckd : 1; unsigned char has_dirq : 1; @@ -111,6 +118,34 @@ struct sclp_info { }; extern struct sclp_info sclp; +struct sccb_header { + u16 length; + u8 function_code; + u8 control_mask[3]; + u16 response_code; +} __packed; + +struct evbuf_header { + u16 length; + u8 type; + u8 flags; + u16 _reserved; +} __packed; + +struct err_notify_evbuf { + struct evbuf_header header; + u8 action; + u8 atype; + u32 fh; + u32 fid; + u8 data[]; +} __packed; + +struct err_notify_sccb { + struct sccb_header header; + struct err_notify_evbuf evbuf; +} __packed; + struct zpci_report_error_header { u8 version; /* Interface version byte */ u8 action; /* Action qualifier byte @@ -137,6 +172,7 @@ void sclp_early_printk(const char *s); void __sclp_early_printk(const char *s, unsigned int len); void sclp_emergency_printk(const char *s); +int sclp_init(void); int sclp_early_get_memsize(unsigned long *mem); int sclp_early_get_hsa_size(unsigned long *hsa_size); int _sclp_get_core_info(struct sclp_core_info *info); diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index e95b2c8081eb..72655fd2d867 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -22,7 +22,6 @@ * Pages used for the page tables is a different story. FIXME: more */ -void __tlb_remove_table(void *_table); static inline void tlb_flush(struct mmu_gather *tlb); static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, bool delay_rmap, int page_size); @@ -87,7 +86,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, tlb->cleared_pmds = 1; if (mm_alloc_pgste(tlb->mm)) gmap_unlink(tlb->mm, (unsigned long *)pte, address); - tlb_remove_ptdesc(tlb, pte); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pte)); } /* @@ -102,12 +101,11 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, { if (mm_pmd_folded(tlb->mm)) return; - pagetable_pmd_dtor(virt_to_ptdesc(pmd)); __tlb_adjust_range(tlb, address, PAGE_SIZE); tlb->mm->context.flush_mm = 1; tlb->freed_tables = 1; tlb->cleared_puds = 1; - tlb_remove_ptdesc(tlb, pmd); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd)); } /* @@ -125,7 +123,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, __tlb_adjust_range(tlb, address, PAGE_SIZE); tlb->mm->context.flush_mm = 1; tlb->freed_tables = 1; - tlb_remove_ptdesc(tlb, p4d); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d)); } /* @@ -140,11 +138,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, { if (mm_pud_folded(tlb->mm)) return; + __tlb_adjust_range(tlb, address, PAGE_SIZE); tlb->mm->context.flush_mm = 1; tlb->freed_tables = 1; tlb->cleared_p4ds = 1; - tlb_remove_ptdesc(tlb, pud); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud)); } - #endif /* _S390_TLB_H */ diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index a81f897a81ce..f5920163ee97 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -22,16 +22,117 @@ void debug_user_asce(int exit); -unsigned long __must_check -raw_copy_from_user(void *to, const void __user *from, unsigned long n); +union oac { + unsigned int val; + struct { + struct { + unsigned short key : 4; + unsigned short : 4; + unsigned short as : 2; + unsigned short : 4; + unsigned short k : 1; + unsigned short a : 1; + } oac1; + struct { + unsigned short key : 4; + unsigned short : 4; + unsigned short as : 2; + unsigned short : 4; + unsigned short k : 1; + unsigned short a : 1; + } oac2; + }; +}; -unsigned long __must_check -raw_copy_to_user(void __user *to, const void *from, unsigned long n); +static __always_inline __must_check unsigned long +raw_copy_from_user_key(void *to, const void __user *from, unsigned long size, unsigned long key) +{ + unsigned long rem; + union oac spec = { + .oac2.key = key, + .oac2.as = PSW_BITS_AS_SECONDARY, + .oac2.k = 1, + .oac2.a = 1, + }; -#ifndef CONFIG_KASAN -#define INLINE_COPY_FROM_USER -#define INLINE_COPY_TO_USER -#endif + asm_inline volatile( + " lr %%r0,%[spec]\n" + "0: mvcos 0(%[to]),0(%[from]),%[size]\n" + "1: jz 5f\n" + " algr %[size],%[val]\n" + " slgr %[from],%[val]\n" + " slgr %[to],%[val]\n" + " j 0b\n" + "2: la %[rem],4095(%[from])\n" /* rem = from + 4095 */ + " nr %[rem],%[val]\n" /* rem = (from + 4095) & -4096 */ + " slgr %[rem],%[from]\n" + " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ + " jnh 6f\n" + "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" + "4: slgr %[size],%[rem]\n" + " j 6f\n" + "5: lghi %[size],0\n" + "6:\n" + EX_TABLE(0b, 2b) + EX_TABLE(1b, 2b) + EX_TABLE(3b, 6b) + EX_TABLE(4b, 6b) + : [size] "+&a" (size), [from] "+&a" (from), [to] "+&a" (to), [rem] "=&a" (rem) + : [val] "a" (-4096UL), [spec] "d" (spec.val) + : "cc", "memory", "0"); + return size; +} + +static __always_inline __must_check unsigned long +raw_copy_from_user(void *to, const void __user *from, unsigned long n) +{ + return raw_copy_from_user_key(to, from, n, 0); +} + +static __always_inline __must_check unsigned long +raw_copy_to_user_key(void __user *to, const void *from, unsigned long size, unsigned long key) +{ + unsigned long rem; + union oac spec = { + .oac1.key = key, + .oac1.as = PSW_BITS_AS_SECONDARY, + .oac1.k = 1, + .oac1.a = 1, + }; + + asm_inline volatile( + " lr %%r0,%[spec]\n" + "0: mvcos 0(%[to]),0(%[from]),%[size]\n" + "1: jz 5f\n" + " algr %[size],%[val]\n" + " slgr %[to],%[val]\n" + " slgr %[from],%[val]\n" + " j 0b\n" + "2: la %[rem],4095(%[to])\n" /* rem = to + 4095 */ + " nr %[rem],%[val]\n" /* rem = (to + 4095) & -4096 */ + " slgr %[rem],%[to]\n" + " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ + " jnh 6f\n" + "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" + "4: slgr %[size],%[rem]\n" + " j 6f\n" + "5: lghi %[size],0\n" + "6:\n" + EX_TABLE(0b, 2b) + EX_TABLE(1b, 2b) + EX_TABLE(3b, 6b) + EX_TABLE(4b, 6b) + : [size] "+&a" (size), [to] "+&a" (to), [from] "+&a" (from), [rem] "=&a" (rem) + : [val] "a" (-4096UL), [spec] "d" (spec.val) + : "cc", "memory", "0"); + return size; +} + +static __always_inline __must_check unsigned long +raw_copy_to_user(void __user *to, const void *from, unsigned long n) +{ + return raw_copy_to_user_key(to, from, n, 0); +} unsigned long __must_check _copy_from_user_key(void *to, const void __user *from, unsigned long n, unsigned long key); @@ -55,63 +156,71 @@ copy_to_user_key(void __user *to, const void *from, unsigned long n, unsigned lo return n; } -union oac { - unsigned int val; - struct { - struct { - unsigned short key : 4; - unsigned short : 4; - unsigned short as : 2; - unsigned short : 4; - unsigned short k : 1; - unsigned short a : 1; - } oac1; - struct { - unsigned short key : 4; - unsigned short : 4; - unsigned short as : 2; - unsigned short : 4; - unsigned short k : 1; - unsigned short a : 1; - } oac2; - }; -}; - int __noreturn __put_user_bad(void); #ifdef CONFIG_KMSAN -#define get_put_user_noinstr_attributes \ - noinline __maybe_unused __no_sanitize_memory +#define uaccess_kmsan_or_inline noinline __maybe_unused __no_sanitize_memory #else -#define get_put_user_noinstr_attributes __always_inline +#define uaccess_kmsan_or_inline __always_inline #endif -#define DEFINE_PUT_USER(type) \ -static get_put_user_noinstr_attributes int \ +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +#define DEFINE_PUT_USER_NOINSTR(type) \ +static uaccess_kmsan_or_inline int \ +__put_user_##type##_noinstr(unsigned type __user *to, \ + unsigned type *from, \ + unsigned long size) \ +{ \ + asm goto( \ + " llilh %%r0,%[spec]\n" \ + "0: mvcos %[to],%[from],%[size]\n" \ + "1: nopr %%r7\n" \ + EX_TABLE(0b, %l[Efault]) \ + EX_TABLE(1b, %l[Efault]) \ + : [to] "+Q" (*to) \ + : [size] "d" (size), [from] "Q" (*from), \ + [spec] "I" (0x81) \ + : "cc", "0" \ + : Efault \ + ); \ + return 0; \ +Efault: \ + return -EFAULT; \ +} + +#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +#define DEFINE_PUT_USER_NOINSTR(type) \ +static uaccess_kmsan_or_inline int \ __put_user_##type##_noinstr(unsigned type __user *to, \ unsigned type *from, \ unsigned long size) \ { \ - union oac __oac_spec = { \ - .oac1.as = PSW_BITS_AS_SECONDARY, \ - .oac1.a = 1, \ - }; \ int rc; \ \ asm volatile( \ - " lr 0,%[spec]\n" \ - "0: mvcos %[_to],%[_from],%[_size]\n" \ - "1: xr %[rc],%[rc]\n" \ + " llilh %%r0,%[spec]\n" \ + "0: mvcos %[to],%[from],%[size]\n" \ + "1: lhi %[rc],0\n" \ "2:\n" \ - EX_TABLE_UA_STORE(0b, 2b, %[rc]) \ - EX_TABLE_UA_STORE(1b, 2b, %[rc]) \ - : [rc] "=&d" (rc), [_to] "+Q" (*(to)) \ - : [_size] "d" (size), [_from] "Q" (*(from)), \ - [spec] "d" (__oac_spec.val) \ + EX_TABLE_UA_FAULT(0b, 2b, %[rc]) \ + EX_TABLE_UA_FAULT(1b, 2b, %[rc]) \ + : [rc] "=d" (rc), [to] "+Q" (*to) \ + : [size] "d" (size), [from] "Q" (*from), \ + [spec] "I" (0x81) \ : "cc", "0"); \ return rc; \ -} \ - \ +} + +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +DEFINE_PUT_USER_NOINSTR(char); +DEFINE_PUT_USER_NOINSTR(short); +DEFINE_PUT_USER_NOINSTR(int); +DEFINE_PUT_USER_NOINSTR(long); + +#define DEFINE_PUT_USER(type) \ static __always_inline int \ __put_user_##type(unsigned type __user *to, unsigned type *from, \ unsigned long size) \ @@ -128,69 +237,111 @@ DEFINE_PUT_USER(short); DEFINE_PUT_USER(int); DEFINE_PUT_USER(long); -static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) -{ - int rc; +#define __put_user(x, ptr) \ +({ \ + __typeof__(*(ptr)) __x = (x); \ + int __prc; \ + \ + __chk_user_ptr(ptr); \ + switch (sizeof(*(ptr))) { \ + case 1: \ + __prc = __put_user_char((unsigned char __user *)(ptr), \ + (unsigned char *)&__x, \ + sizeof(*(ptr))); \ + break; \ + case 2: \ + __prc = __put_user_short((unsigned short __user *)(ptr),\ + (unsigned short *)&__x, \ + sizeof(*(ptr))); \ + break; \ + case 4: \ + __prc = __put_user_int((unsigned int __user *)(ptr), \ + (unsigned int *)&__x, \ + sizeof(*(ptr))); \ + break; \ + case 8: \ + __prc = __put_user_long((unsigned long __user *)(ptr), \ + (unsigned long *)&__x, \ + sizeof(*(ptr))); \ + break; \ + default: \ + __prc = __put_user_bad(); \ + break; \ + } \ + __builtin_expect(__prc, 0); \ +}) - switch (size) { - case 1: - rc = __put_user_char((unsigned char __user *)ptr, - (unsigned char *)x, - size); - break; - case 2: - rc = __put_user_short((unsigned short __user *)ptr, - (unsigned short *)x, - size); - break; - case 4: - rc = __put_user_int((unsigned int __user *)ptr, - (unsigned int *)x, - size); - break; - case 8: - rc = __put_user_long((unsigned long __user *)ptr, - (unsigned long *)x, - size); - break; - default: - __put_user_bad(); - break; - } - return rc; -} +#define put_user(x, ptr) \ +({ \ + might_fault(); \ + __put_user(x, ptr); \ +}) int __noreturn __get_user_bad(void); -#define DEFINE_GET_USER(type) \ -static get_put_user_noinstr_attributes int \ +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +#define DEFINE_GET_USER_NOINSTR(type) \ +static uaccess_kmsan_or_inline int \ __get_user_##type##_noinstr(unsigned type *to, \ - unsigned type __user *from, \ + const unsigned type __user *from, \ + unsigned long size) \ +{ \ + asm goto( \ + " lhi %%r0,%[spec]\n" \ + "0: mvcos %[to],%[from],%[size]\n" \ + "1: nopr %%r7\n" \ + EX_TABLE(0b, %l[Efault]) \ + EX_TABLE(1b, %l[Efault]) \ + : [to] "=Q" (*to) \ + : [size] "d" (size), [from] "Q" (*from), \ + [spec] "I" (0x81) \ + : "cc", "0" \ + : Efault \ + ); \ + return 0; \ +Efault: \ + *to = 0; \ + return -EFAULT; \ +} + +#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +#define DEFINE_GET_USER_NOINSTR(type) \ +static uaccess_kmsan_or_inline int \ +__get_user_##type##_noinstr(unsigned type *to, \ + const unsigned type __user *from, \ unsigned long size) \ { \ - union oac __oac_spec = { \ - .oac2.as = PSW_BITS_AS_SECONDARY, \ - .oac2.a = 1, \ - }; \ int rc; \ \ asm volatile( \ - " lr 0,%[spec]\n" \ - "0: mvcos 0(%[_to]),%[_from],%[_size]\n" \ - "1: xr %[rc],%[rc]\n" \ + " lhi %%r0,%[spec]\n" \ + "0: mvcos %[to],%[from],%[size]\n" \ + "1: lhi %[rc],0\n" \ "2:\n" \ - EX_TABLE_UA_LOAD_MEM(0b, 2b, %[rc], %[_to], %[_ksize]) \ - EX_TABLE_UA_LOAD_MEM(1b, 2b, %[rc], %[_to], %[_ksize]) \ - : [rc] "=&d" (rc), "=Q" (*(to)) \ - : [_size] "d" (size), [_from] "Q" (*(from)), \ - [spec] "d" (__oac_spec.val), [_to] "a" (to), \ - [_ksize] "K" (size) \ + EX_TABLE_UA_FAULT(0b, 2b, %[rc]) \ + EX_TABLE_UA_FAULT(1b, 2b, %[rc]) \ + : [rc] "=d" (rc), [to] "=Q" (*to) \ + : [size] "d" (size), [from] "Q" (*from), \ + [spec] "I" (0x81) \ : "cc", "0"); \ + if (likely(!rc)) \ + return 0; \ + *to = 0; \ return rc; \ -} \ - \ +} + +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +DEFINE_GET_USER_NOINSTR(char); +DEFINE_GET_USER_NOINSTR(short); +DEFINE_GET_USER_NOINSTR(int); +DEFINE_GET_USER_NOINSTR(long); + +#define DEFINE_GET_USER(type) \ static __always_inline int \ -__get_user_##type(unsigned type *to, unsigned type __user *from, \ +__get_user_##type(unsigned type *to, const unsigned type __user *from, \ unsigned long size) \ { \ int rc; \ @@ -205,107 +356,50 @@ DEFINE_GET_USER(short); DEFINE_GET_USER(int); DEFINE_GET_USER(long); -static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) -{ - int rc; - - switch (size) { - case 1: - rc = __get_user_char((unsigned char *)x, - (unsigned char __user *)ptr, - size); - break; - case 2: - rc = __get_user_short((unsigned short *)x, - (unsigned short __user *)ptr, - size); - break; - case 4: - rc = __get_user_int((unsigned int *)x, - (unsigned int __user *)ptr, - size); - break; - case 8: - rc = __get_user_long((unsigned long *)x, - (unsigned long __user *)ptr, - size); - break; - default: - __get_user_bad(); - break; - } - return rc; -} - -/* - * These are the main single-value transfer routines. They automatically - * use the right size if we just have the right pointer type. - */ -#define __put_user(x, ptr) \ -({ \ - __typeof__(*(ptr)) __x = (x); \ - int __pu_err = -EFAULT; \ - \ - __chk_user_ptr(ptr); \ - switch (sizeof(*(ptr))) { \ - case 1: \ - case 2: \ - case 4: \ - case 8: \ - __pu_err = __put_user_fn(&__x, ptr, sizeof(*(ptr))); \ - break; \ - default: \ - __put_user_bad(); \ - break; \ - } \ - __builtin_expect(__pu_err, 0); \ -}) - -#define put_user(x, ptr) \ -({ \ - might_fault(); \ - __put_user(x, ptr); \ -}) - #define __get_user(x, ptr) \ ({ \ - int __gu_err = -EFAULT; \ + const __user void *____guptr = (ptr); \ + int __grc; \ \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: { \ + const unsigned char __user *__guptr = ____guptr; \ unsigned char __x; \ \ - __gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr))); \ + __grc = __get_user_char(&__x, __guptr, sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *)&__x; \ break; \ }; \ case 2: { \ + const unsigned short __user *__guptr = ____guptr; \ unsigned short __x; \ \ - __gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr))); \ + __grc = __get_user_short(&__x, __guptr, sizeof(*(ptr)));\ (x) = *(__force __typeof__(*(ptr)) *)&__x; \ break; \ }; \ case 4: { \ + const unsigned int __user *__guptr = ____guptr; \ unsigned int __x; \ \ - __gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr))); \ + __grc = __get_user_int(&__x, __guptr, sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *)&__x; \ break; \ }; \ case 8: { \ + const unsigned long __user *__guptr = ____guptr; \ unsigned long __x; \ \ - __gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr))); \ + __grc = __get_user_long(&__x, __guptr, sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *)&__x; \ break; \ }; \ default: \ - __get_user_bad(); \ + __grc = __get_user_bad(); \ break; \ } \ - __builtin_expect(__gu_err, 0); \ + __builtin_expect(__grc, 0); \ }) #define get_user(x, ptr) \ @@ -341,108 +435,70 @@ static inline void *s390_kernel_write(void *dst, const void *src, size_t size) return __s390_kernel_write(dst, src, size); } -int __noreturn __put_kernel_bad(void); +void __noreturn __mvc_kernel_nofault_bad(void); -#define __put_kernel_asm(val, to, insn) \ -({ \ - int __rc; \ - \ - asm volatile( \ - "0: " insn " %[_val],%[_to]\n" \ - "1: xr %[rc],%[rc]\n" \ - "2:\n" \ - EX_TABLE_UA_STORE(0b, 2b, %[rc]) \ - EX_TABLE_UA_STORE(1b, 2b, %[rc]) \ - : [rc] "=d" (__rc), [_to] "+Q" (*(to)) \ - : [_val] "d" (val) \ - : "cc"); \ - __rc; \ -}) +#if defined(CONFIG_CC_HAS_ASM_GOTO_OUTPUT) && defined(CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS) -#define __put_kernel_nofault(dst, src, type, err_label) \ +#define __mvc_kernel_nofault(dst, src, type, err_label) \ do { \ - unsigned long __x = (unsigned long)(*((type *)(src))); \ - int __pk_err; \ + switch (sizeof(type)) { \ + case 1: \ + case 2: \ + case 4: \ + case 8: \ + asm goto( \ + "0: mvc %O[_dst](%[_len],%R[_dst]),%[_src]\n" \ + "1: nopr %%r7\n" \ + EX_TABLE(0b, %l[err_label]) \ + EX_TABLE(1b, %l[err_label]) \ + : [_dst] "=Q" (*(type *)dst) \ + : [_src] "Q" (*(type *)(src)), \ + [_len] "I" (sizeof(type)) \ + : \ + : err_label); \ + break; \ + default: \ + __mvc_kernel_nofault_bad(); \ + break; \ + } \ +} while (0) + +#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT) && CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ + +#define __mvc_kernel_nofault(dst, src, type, err_label) \ +do { \ + type *(__dst) = (type *)(dst); \ + int __rc; \ \ switch (sizeof(type)) { \ case 1: \ - __pk_err = __put_kernel_asm(__x, (type *)(dst), "stc"); \ - break; \ case 2: \ - __pk_err = __put_kernel_asm(__x, (type *)(dst), "sth"); \ - break; \ case 4: \ - __pk_err = __put_kernel_asm(__x, (type *)(dst), "st"); \ - break; \ case 8: \ - __pk_err = __put_kernel_asm(__x, (type *)(dst), "stg"); \ + asm_inline volatile( \ + "0: mvc 0(%[_len],%[_dst]),%[_src]\n" \ + "1: lhi %[_rc],0\n" \ + "2:\n" \ + EX_TABLE_UA_FAULT(0b, 2b, %[_rc]) \ + EX_TABLE_UA_FAULT(1b, 2b, %[_rc]) \ + : [_rc] "=d" (__rc), \ + "=m" (*__dst) \ + : [_src] "Q" (*(type *)(src)), \ + [_dst] "a" (__dst), \ + [_len] "I" (sizeof(type))); \ + if (__rc) \ + goto err_label; \ break; \ default: \ - __pk_err = __put_kernel_bad(); \ + __mvc_kernel_nofault_bad(); \ break; \ } \ - if (unlikely(__pk_err)) \ - goto err_label; \ } while (0) -int __noreturn __get_kernel_bad(void); +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT && CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ -#define __get_kernel_asm(val, from, insn) \ -({ \ - int __rc; \ - \ - asm volatile( \ - "0: " insn " %[_val],%[_from]\n" \ - "1: xr %[rc],%[rc]\n" \ - "2:\n" \ - EX_TABLE_UA_LOAD_REG(0b, 2b, %[rc], %[_val]) \ - EX_TABLE_UA_LOAD_REG(1b, 2b, %[rc], %[_val]) \ - : [rc] "=d" (__rc), [_val] "=d" (val) \ - : [_from] "Q" (*(from)) \ - : "cc"); \ - __rc; \ -}) - -#define __get_kernel_nofault(dst, src, type, err_label) \ -do { \ - int __gk_err; \ - \ - switch (sizeof(type)) { \ - case 1: { \ - unsigned char __x; \ - \ - __gk_err = __get_kernel_asm(__x, (type *)(src), "ic"); \ - *((type *)(dst)) = (type)__x; \ - break; \ - }; \ - case 2: { \ - unsigned short __x; \ - \ - __gk_err = __get_kernel_asm(__x, (type *)(src), "lh"); \ - *((type *)(dst)) = (type)__x; \ - break; \ - }; \ - case 4: { \ - unsigned int __x; \ - \ - __gk_err = __get_kernel_asm(__x, (type *)(src), "l"); \ - *((type *)(dst)) = (type)__x; \ - break; \ - }; \ - case 8: { \ - unsigned long __x; \ - \ - __gk_err = __get_kernel_asm(__x, (type *)(src), "lg"); \ - *((type *)(dst)) = (type)__x; \ - break; \ - }; \ - default: \ - __gk_err = __get_kernel_bad(); \ - break; \ - } \ - if (unlikely(__gk_err)) \ - goto err_label; \ -} while (0) +#define __get_kernel_nofault __mvc_kernel_nofault +#define __put_kernel_nofault __mvc_kernel_nofault void __cmpxchg_user_key_called_with_bad_pointer(void); diff --git a/arch/s390/include/uapi/asm/diag.h b/arch/s390/include/uapi/asm/diag.h new file mode 100644 index 000000000000..b7e6ccb4ff6e --- /dev/null +++ b/arch/s390/include/uapi/asm/diag.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Diag ioctls and its associated structures definitions. + * + * Copyright IBM Corp. 2024 + */ + +#ifndef __S390_UAPI_ASM_DIAG_H +#define __S390_UAPI_ASM_DIAG_H + +#include + +#define DIAG_MAGIC_STR 'D' + +struct diag324_pib { + __u64 address; + __u64 sequence; +}; + +struct diag310_memtop { + __u64 address; + __u64 nesting_lvl; +}; + +/* Diag ioctl definitions */ +#define DIAG324_GET_PIBBUF _IOWR(DIAG_MAGIC_STR, 0x77, struct diag324_pib) +#define DIAG324_GET_PIBLEN _IOR(DIAG_MAGIC_STR, 0x78, size_t) +#define DIAG310_GET_STRIDE _IOR(DIAG_MAGIC_STR, 0x79, size_t) +#define DIAG310_GET_MEMTOPLEN _IOWR(DIAG_MAGIC_STR, 0x7a, size_t) +#define DIAG310_GET_MEMTOPBUF _IOWR(DIAG_MAGIC_STR, 0x7b, struct diag310_memtop) + +#endif /* __S390_UAPI_ASM_DIAG_H */ diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 48caae8c7e10..db5f3a3faefb 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -38,12 +38,13 @@ CFLAGS_unwind_bc.o += -fno-optimize-sibling-calls obj-y := head64.o traps.o time.o process.o early.o setup.o idle.o vtime.o obj-y += processor.o syscall.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o -obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o cpufeature.o +obj-y += debug.o irq.o ipl.o dis.o vdso.o cpufeature.o obj-y += sysinfo.o lgr.o os_info.o ctlreg.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o obj-y += entry.o reipl.o kdebugfs.o alternative.o obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o obj-y += smp.o text_amode31.o stacktrace.o abs_lowcore.o facility.o uv.o wti.o +obj-y += diag/ extra-y += vmlinux.lds diff --git a/arch/s390/kernel/abs_lowcore.c b/arch/s390/kernel/abs_lowcore.c index 09cd24cbe74e..88f0b91d7a73 100644 --- a/arch/s390/kernel/abs_lowcore.c +++ b/arch/s390/kernel/abs_lowcore.c @@ -2,6 +2,7 @@ #include #include +#include unsigned long __bootdata_preserved(__abs_lowcore); int __bootdata_preserved(relocate_lowcore); diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 862a9140528e..36709112ae7a 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -175,12 +175,6 @@ int main(void) DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size)); DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line)); DEFINE(MAX_COMMAND_LINE_SIZE, PARMAREA + offsetof(struct parmarea, max_command_line_size)); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* function graph return value tracing */ - OFFSET(__FGRAPH_RET_GPR2, fgraph_ret_regs, gpr2); - OFFSET(__FGRAPH_RET_FP, fgraph_ret_regs, fp); - DEFINE(__FGRAPH_RET_SIZE, sizeof(struct fgraph_ret_regs)); -#endif OFFSET(__FTRACE_REGS_PT_REGS, __arch_ftrace_regs, regs); DEFINE(__FTRACE_REGS_SIZE, sizeof(struct __arch_ftrace_regs)); diff --git a/arch/s390/kernel/cpacf.c b/arch/s390/kernel/cpacf.c index c8575dbc890d..4b9b34f95d72 100644 --- a/arch/s390/kernel/cpacf.c +++ b/arch/s390/kernel/cpacf.c @@ -14,7 +14,7 @@ #define CPACF_QUERY(name, instruction) \ static ssize_t name##_query_raw_read(struct file *fp, \ struct kobject *kobj, \ - struct bin_attribute *attr, \ + const struct bin_attribute *attr, \ char *buf, loff_t offs, \ size_t count) \ { \ @@ -24,7 +24,7 @@ static ssize_t name##_query_raw_read(struct file *fp, \ return -EOPNOTSUPP; \ return memory_read_from_buffer(buf, count, &offs, &mask, sizeof(mask)); \ } \ -static BIN_ATTR_RO(name##_query_raw, sizeof(cpacf_mask_t)) +static const BIN_ATTR_RO(name##_query_raw, sizeof(cpacf_mask_t)) CPACF_QUERY(km, KM); CPACF_QUERY(kmc, KMC); @@ -40,20 +40,20 @@ CPACF_QUERY(prno, PRNO); CPACF_QUERY(kma, KMA); CPACF_QUERY(kdsa, KDSA); -#define CPACF_QAI(name, instruction) \ -static ssize_t name##_query_auth_info_raw_read( \ - struct file *fp, struct kobject *kobj, \ - struct bin_attribute *attr, char *buf, loff_t offs, \ - size_t count) \ -{ \ - cpacf_qai_t qai; \ - \ - if (!cpacf_qai(CPACF_##instruction, &qai)) \ - return -EOPNOTSUPP; \ - return memory_read_from_buffer(buf, count, &offs, &qai, \ - sizeof(qai)); \ -} \ -static BIN_ATTR_RO(name##_query_auth_info_raw, sizeof(cpacf_qai_t)) +#define CPACF_QAI(name, instruction) \ +static ssize_t name##_query_auth_info_raw_read( \ + struct file *fp, struct kobject *kobj, \ + const struct bin_attribute *attr, char *buf, loff_t offs, \ + size_t count) \ +{ \ + cpacf_qai_t qai; \ + \ + if (!cpacf_qai(CPACF_##instruction, &qai)) \ + return -EOPNOTSUPP; \ + return memory_read_from_buffer(buf, count, &offs, &qai, \ + sizeof(qai)); \ +} \ +static const BIN_ATTR_RO(name##_query_auth_info_raw, sizeof(cpacf_qai_t)) CPACF_QAI(km, KM); CPACF_QAI(kmc, KMC); @@ -69,7 +69,7 @@ CPACF_QAI(prno, PRNO); CPACF_QAI(kma, KMA); CPACF_QAI(kdsa, KDSA); -static struct bin_attribute *cpacf_attrs[] = { +static const struct bin_attribute *const cpacf_attrs[] = { &bin_attr_km_query_raw, &bin_attr_kmc_query_raw, &bin_attr_kimd_query_raw, @@ -101,7 +101,7 @@ static struct bin_attribute *cpacf_attrs[] = { static const struct attribute_group cpacf_attr_grp = { .name = "cpacf", - .bin_attrs = cpacf_attrs, + .bin_attrs_new = cpacf_attrs, }; static int __init cpacf_init(void) diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index cd0c93a8fb8b..276cb4c1e11b 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -63,9 +63,7 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu) { struct save_area *sa; - sa = memblock_alloc(sizeof(*sa), 8); - if (!sa) - return NULL; + sa = memblock_alloc_or_panic(sizeof(*sa), 8); if (is_boot_cpu) list_add(&sa->list, &dump_save_areas); @@ -508,6 +506,19 @@ static int get_mem_chunk_cnt(void) return cnt; } +static void fill_ptload(Elf64_Phdr *phdr, unsigned long paddr, + unsigned long vaddr, unsigned long size) +{ + phdr->p_type = PT_LOAD; + phdr->p_vaddr = vaddr; + phdr->p_offset = paddr; + phdr->p_paddr = paddr; + phdr->p_filesz = size; + phdr->p_memsz = size; + phdr->p_flags = PF_R | PF_W | PF_X; + phdr->p_align = PAGE_SIZE; +} + /* * Initialize ELF loads (new kernel) */ @@ -520,14 +531,8 @@ static void loads_init(Elf64_Phdr *phdr, bool os_info_has_vm) if (os_info_has_vm) old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE); for_each_physmem_range(idx, &oldmem_type, &start, &end) { - phdr->p_type = PT_LOAD; - phdr->p_vaddr = old_identity_base + start; - phdr->p_offset = start; - phdr->p_paddr = start; - phdr->p_filesz = end - start; - phdr->p_memsz = end - start; - phdr->p_flags = PF_R | PF_W | PF_X; - phdr->p_align = PAGE_SIZE; + fill_ptload(phdr, start, old_identity_base + start, + end - start); phdr++; } } @@ -537,6 +542,22 @@ static bool os_info_has_vm(void) return os_info_old_value(OS_INFO_KASLR_OFFSET); } +#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM +/* + * Fill PT_LOAD for a physical memory range owned by a device and detected by + * its device driver. + */ +void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr, + unsigned long long paddr, unsigned long long size) +{ + unsigned long old_identity_base = 0; + + if (os_info_has_vm()) + old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE); + fill_ptload(phdr, paddr, old_identity_base + paddr, size); +} +#endif + /* * Prepare PT_LOAD type program header for kernel image region */ diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index de19fd8a6a95..ce038e9205f7 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -94,9 +95,6 @@ static int debug_input_flush_fn(debug_info_t *id, struct debug_view *view, static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view, char *out_buf, size_t out_buf_size, const char *in_buf); -static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, - char *out_buf, size_t out_buf_size, - const char *inbuf); static void debug_areas_swap(debug_info_t *a, debug_info_t *b); static void debug_events_append(debug_info_t *dest, debug_info_t *src); @@ -354,7 +352,10 @@ static debug_info_t *debug_info_copy(debug_info_t *in, int mode) for (i = 0; i < in->nr_areas; i++) { for (j = 0; j < in->pages_per_area; j++) memcpy(rc->areas[i][j], in->areas[i][j], PAGE_SIZE); + rc->active_pages[i] = in->active_pages[i]; + rc->active_entries[i] = in->active_entries[i]; } + rc->active_area = in->active_area; out: spin_unlock_irqrestore(&in->lock, flags); return rc; @@ -422,11 +423,17 @@ out: return len; } -/* - * debug_next_entry: - * - goto next entry in p_info +/** + * debug_next_entry - Go to the next entry + * @p_info: Private info that is manipulated + * + * Sets the current position in @p_info to the next entry. If no further entry + * exists the current position is set to one after the end the return value + * indicates that no further entries exist. + * + * Return: True if there are more following entries, false otherwise */ -static inline int debug_next_entry(file_private_info_t *p_info) +static inline bool debug_next_entry(file_private_info_t *p_info) { debug_info_t *id; @@ -434,10 +441,10 @@ static inline int debug_next_entry(file_private_info_t *p_info) if (p_info->act_entry == DEBUG_PROLOG_ENTRY) { p_info->act_entry = 0; p_info->act_page = 0; - goto out; + return true; } if (!id->areas) - return 1; + return false; p_info->act_entry += id->entry_size; /* switch to next page, if we reached the end of the page */ if (p_info->act_entry > (PAGE_SIZE - id->entry_size)) { @@ -450,10 +457,87 @@ static inline int debug_next_entry(file_private_info_t *p_info) p_info->act_page = 0; } if (p_info->act_area >= id->nr_areas) - return 1; + return false; } -out: - return 0; + return true; +} + +/** + * debug_to_act_entry - Go to the currently active entry + * @p_info: Private info that is manipulated + * + * Sets the current position in @p_info to the currently active + * entry of @p_info->debug_info_snap + */ +static void debug_to_act_entry(file_private_info_t *p_info) +{ + debug_info_t *snap_id; + + snap_id = p_info->debug_info_snap; + p_info->act_area = snap_id->active_area; + p_info->act_page = snap_id->active_pages[snap_id->active_area]; + p_info->act_entry = snap_id->active_entries[snap_id->active_area]; +} + +/** + * debug_prev_entry - Go to the previous entry + * @p_info: Private info that is manipulated + * + * Sets the current position in @p_info to the previous entry. If no previous entry + * exists the current position is set left as DEBUG_PROLOG_ENTRY and the return value + * indicates that no previous entries exist. + * + * Return: True if there are more previous entries, false otherwise + */ + +static inline bool debug_prev_entry(file_private_info_t *p_info) +{ + debug_info_t *id; + + id = p_info->debug_info_snap; + if (p_info->act_entry == DEBUG_PROLOG_ENTRY) + debug_to_act_entry(p_info); + if (!id->areas) + return false; + p_info->act_entry -= id->entry_size; + /* switch to prev page, if we reached the beginning of the page */ + if (p_info->act_entry < 0) { + /* end of previous page */ + p_info->act_entry = rounddown(PAGE_SIZE, id->entry_size) - id->entry_size; + p_info->act_page--; + if (p_info->act_page < 0) { + /* previous area */ + p_info->act_area--; + p_info->act_page = id->pages_per_area - 1; + } + if (p_info->act_area < 0) + p_info->act_area = (id->nr_areas - 1) % id->nr_areas; + } + /* check full circle */ + if (id->active_area == p_info->act_area && + id->active_pages[id->active_area] == p_info->act_page && + id->active_entries[id->active_area] == p_info->act_entry) + return false; + return true; +} + +/** + * debug_move_entry - Go to next entry in either the forward or backward direction + * @p_info: Private info that is manipulated + * @reverse: If true go to the next entry in reverse i.e. previous + * + * Sets the current position in @p_info to the next (@reverse == false) or + * previous (@reverse == true) entry. + * + * Return: True if there are further entries in that direction, + * false otherwise. + */ +static bool debug_move_entry(file_private_info_t *p_info, bool reverse) +{ + if (reverse) + return debug_prev_entry(p_info); + else + return debug_next_entry(p_info); } /* @@ -495,7 +579,7 @@ static ssize_t debug_output(struct file *file, /* file descriptor */ } if (copy_size == formatted_line_residue) { entry_offset = 0; - if (debug_next_entry(p_info)) + if (!debug_next_entry(p_info)) goto out; } } @@ -530,6 +614,42 @@ static ssize_t debug_input(struct file *file, const char __user *user_buf, return rc; /* number of input characters */ } +static file_private_info_t *debug_file_private_alloc(debug_info_t *debug_info, + struct debug_view *view) +{ + debug_info_t *debug_info_snapshot; + file_private_info_t *p_info; + + /* + * Make snapshot of current debug areas to get it consistent. + * To copy all the areas is only needed, if we have a view which + * formats the debug areas. + */ + if (!view->format_proc && !view->header_proc) + debug_info_snapshot = debug_info_copy(debug_info, NO_AREAS); + else + debug_info_snapshot = debug_info_copy(debug_info, ALL_AREAS); + + if (!debug_info_snapshot) + return NULL; + p_info = kmalloc(sizeof(file_private_info_t), GFP_KERNEL); + if (!p_info) { + debug_info_free(debug_info_snapshot); + return NULL; + } + p_info->offset = 0; + p_info->debug_info_snap = debug_info_snapshot; + p_info->debug_info_org = debug_info; + p_info->view = view; + p_info->act_area = 0; + p_info->act_page = 0; + p_info->act_entry = DEBUG_PROLOG_ENTRY; + p_info->act_entry_offset = 0; + debug_info_get(debug_info); + + return p_info; +} + /* * debug_open: * - called for user open() @@ -538,7 +658,7 @@ static ssize_t debug_input(struct file *file, const char __user *user_buf, */ static int debug_open(struct inode *inode, struct file *file) { - debug_info_t *debug_info, *debug_info_snapshot; + debug_info_t *debug_info; file_private_info_t *p_info; int i, rc = 0; @@ -556,42 +676,26 @@ static int debug_open(struct inode *inode, struct file *file) goto out; found: - - /* Make snapshot of current debug areas to get it consistent. */ - /* To copy all the areas is only needed, if we have a view which */ - /* formats the debug areas. */ - - if (!debug_info->views[i]->format_proc && !debug_info->views[i]->header_proc) - debug_info_snapshot = debug_info_copy(debug_info, NO_AREAS); - else - debug_info_snapshot = debug_info_copy(debug_info, ALL_AREAS); - - if (!debug_info_snapshot) { - rc = -ENOMEM; - goto out; - } - p_info = kmalloc(sizeof(file_private_info_t), GFP_KERNEL); + p_info = debug_file_private_alloc(debug_info, debug_info->views[i]); if (!p_info) { - debug_info_free(debug_info_snapshot); rc = -ENOMEM; goto out; } - p_info->offset = 0; - p_info->debug_info_snap = debug_info_snapshot; - p_info->debug_info_org = debug_info; - p_info->view = debug_info->views[i]; - p_info->act_area = 0; - p_info->act_page = 0; - p_info->act_entry = DEBUG_PROLOG_ENTRY; - p_info->act_entry_offset = 0; file->private_data = p_info; - debug_info_get(debug_info); nonseekable_open(inode, file); out: mutex_unlock(&debug_mutex); return rc; } +static void debug_file_private_free(file_private_info_t *p_info) +{ + if (p_info->debug_info_snap) + debug_info_free(p_info->debug_info_snap); + debug_info_put(p_info->debug_info_org); + kfree(p_info); +} + /* * debug_close: * - called for user close() @@ -602,13 +706,59 @@ static int debug_close(struct inode *inode, struct file *file) file_private_info_t *p_info; p_info = (file_private_info_t *) file->private_data; - if (p_info->debug_info_snap) - debug_info_free(p_info->debug_info_snap); - debug_info_put(p_info->debug_info_org); - kfree(file->private_data); + debug_file_private_free(p_info); + file->private_data = NULL; return 0; /* success */ } +/** + * debug_dump - Get a textual representation of debug info, or as much as fits + * @id: Debug information to use + * @view: View with which to dump the debug information + * @buf: Buffer the textual debug data representation is written to + * @buf_size: Size of the buffer, including the trailing '\0' byte + * @reverse: Go backwards from the last written entry + * + * This function may be used whenever a textual representation of the debug + * information is required without using an s390dbf file. + * + * Note: It is the callers responsibility to supply a view that is compatible + * with the debug information data. + * + * Return: On success returns the number of bytes written to the buffer not + * including the trailing '\0' byte. If bug_size == 0 the function returns 0. + * On failure an error code less than 0 is returned. + */ +ssize_t debug_dump(debug_info_t *id, struct debug_view *view, + char *buf, size_t buf_size, bool reverse) +{ + file_private_info_t *p_info; + size_t size, offset = 0; + + /* Need space for '\0' byte */ + if (buf_size < 1) + return 0; + buf_size--; + + p_info = debug_file_private_alloc(id, view); + if (!p_info) + return -ENOMEM; + + /* There is always at least the DEBUG_PROLOG_ENTRY */ + do { + size = debug_format_entry(p_info); + size = min(size, buf_size - offset); + memcpy(buf + offset, p_info->temp_buf, size); + offset += size; + if (offset >= buf_size) + break; + } while (debug_move_entry(p_info, reverse)); + debug_file_private_free(p_info); + buf[offset] = '\0'; + + return offset; +} + /* Create debugfs entries and add to internal list. */ static void _debug_register(debug_info_t *id) { @@ -972,7 +1122,7 @@ static int s390dbf_procactive(const struct ctl_table *table, int write, return 0; } -static struct ctl_table s390dbf_table[] = { +static const struct ctl_table s390dbf_table[] = { { .procname = "debug_stoppable", .data = &debug_stoppable, @@ -1532,8 +1682,8 @@ EXPORT_SYMBOL(debug_dflt_header_fn); #define DEBUG_SPRINTF_MAX_ARGS 10 -static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, - char *out_buf, size_t out_buf_size, const char *inbuf) +int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, + char *out_buf, size_t out_buf_size, const char *inbuf) { debug_sprintf_entry_t *curr_event = (debug_sprintf_entry_t *)inbuf; int num_longs, num_used_args = 0, i, rc = 0; @@ -1570,6 +1720,7 @@ static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, out: return rc; } +EXPORT_SYMBOL(debug_sprintf_format_fn); /* * debug_init: diff --git a/arch/s390/kernel/diag/Makefile b/arch/s390/kernel/diag/Makefile new file mode 100644 index 000000000000..956aee6c4090 --- /dev/null +++ b/arch/s390/kernel/diag/Makefile @@ -0,0 +1 @@ +obj-y := diag_misc.o diag324.o diag.o diag310.o diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag/diag.c similarity index 98% rename from arch/s390/kernel/diag.c rename to arch/s390/kernel/diag/diag.c index cdd6e31344fa..e15b8dee3228 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag/diag.c @@ -17,7 +17,7 @@ #include #include #include -#include "entry.h" +#include "../entry.h" struct diag_stat { unsigned int counter[NR_DIAG_STAT]; @@ -51,8 +51,10 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = { [DIAG_STAT_X2FC] = { .code = 0x2fc, .name = "Guest Performance Data" }, [DIAG_STAT_X304] = { .code = 0x304, .name = "Partition-Resource Service" }, [DIAG_STAT_X308] = { .code = 0x308, .name = "List-Directed IPL" }, + [DIAG_STAT_X310] = { .code = 0x310, .name = "Memory Topology Information" }, [DIAG_STAT_X318] = { .code = 0x318, .name = "CP Name and Version Codes" }, [DIAG_STAT_X320] = { .code = 0x320, .name = "Certificate Store" }, + [DIAG_STAT_X324] = { .code = 0x324, .name = "Power Information Block" }, [DIAG_STAT_X49C] = { .code = 0x49c, .name = "Warning-Track Interruption" }, [DIAG_STAT_X500] = { .code = 0x500, .name = "Virtio Service" }, }; diff --git a/arch/s390/kernel/diag/diag310.c b/arch/s390/kernel/diag/diag310.c new file mode 100644 index 000000000000..d6a34454aa5a --- /dev/null +++ b/arch/s390/kernel/diag/diag310.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Request memory topology information via diag0x310. + * + * Copyright IBM Corp. 2025 + */ + +#include +#include +#include +#include +#include +#include +#include +#include "diag_ioctl.h" + +#define DIAG310_LEVELMIN 1 +#define DIAG310_LEVELMAX 6 + +enum diag310_sc { + DIAG310_SUBC_0 = 0, + DIAG310_SUBC_1 = 1, + DIAG310_SUBC_4 = 4, + DIAG310_SUBC_5 = 5 +}; + +enum diag310_retcode { + DIAG310_RET_SUCCESS = 0x0001, + DIAG310_RET_BUSY = 0x0101, + DIAG310_RET_OPNOTSUPP = 0x0102, + DIAG310_RET_SC4_INVAL = 0x0401, + DIAG310_RET_SC4_NODATA = 0x0402, + DIAG310_RET_SC5_INVAL = 0x0501, + DIAG310_RET_SC5_NODATA = 0x0502, + DIAG310_RET_SC5_ESIZE = 0x0503 +}; + +union diag310_response { + u64 response; + struct { + u64 result : 32; + u64 : 16; + u64 rc : 16; + }; +}; + +union diag310_req_subcode { + u64 subcode; + struct { + u64 : 48; + u64 st : 8; + u64 sc : 8; + }; +}; + +union diag310_req_size { + u64 size; + struct { + u64 page_count : 32; + u64 : 32; + }; +}; + +static inline unsigned long diag310(unsigned long subcode, unsigned long size, void *addr) +{ + union register_pair rp = { .even = (unsigned long)addr, .odd = size }; + + diag_stat_inc(DIAG_STAT_X310); + asm volatile("diag %[rp],%[subcode],0x310\n" + : [rp] "+d" (rp.pair) + : [subcode] "d" (subcode) + : "memory"); + return rp.odd; +} + +static int diag310_result_to_errno(unsigned int result) +{ + switch (result) { + case DIAG310_RET_BUSY: + return -EBUSY; + case DIAG310_RET_OPNOTSUPP: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +static int diag310_get_subcode_mask(unsigned long *mask) +{ + union diag310_response res; + + res.response = diag310(DIAG310_SUBC_0, 0, NULL); + if (res.rc != DIAG310_RET_SUCCESS) + return diag310_result_to_errno(res.rc); + *mask = res.response; + return 0; +} + +static int diag310_get_memtop_stride(unsigned long *stride) +{ + union diag310_response res; + + res.response = diag310(DIAG310_SUBC_1, 0, NULL); + if (res.rc != DIAG310_RET_SUCCESS) + return diag310_result_to_errno(res.rc); + *stride = res.result; + return 0; +} + +static int diag310_get_memtop_size(unsigned long *pages, unsigned long level) +{ + union diag310_req_subcode req = { .sc = DIAG310_SUBC_4, .st = level }; + union diag310_response res; + + res.response = diag310(req.subcode, 0, NULL); + switch (res.rc) { + case DIAG310_RET_SUCCESS: + *pages = res.result; + return 0; + case DIAG310_RET_SC4_NODATA: + return -ENODATA; + case DIAG310_RET_SC4_INVAL: + return -EINVAL; + default: + return diag310_result_to_errno(res.rc); + } +} + +static int diag310_store_topology_map(void *buf, unsigned long pages, unsigned long level) +{ + union diag310_req_subcode req_sc = { .sc = DIAG310_SUBC_5, .st = level }; + union diag310_req_size req_size = { .page_count = pages }; + union diag310_response res; + + res.response = diag310(req_sc.subcode, req_size.size, buf); + switch (res.rc) { + case DIAG310_RET_SUCCESS: + return 0; + case DIAG310_RET_SC5_NODATA: + return -ENODATA; + case DIAG310_RET_SC5_ESIZE: + return -EOVERFLOW; + case DIAG310_RET_SC5_INVAL: + return -EINVAL; + default: + return diag310_result_to_errno(res.rc); + } +} + +static int diag310_check_features(void) +{ + static int features_available; + unsigned long mask; + int rc; + + if (READ_ONCE(features_available)) + return 0; + if (!sclp.has_diag310) + return -EOPNOTSUPP; + rc = diag310_get_subcode_mask(&mask); + if (rc) + return rc; + if (!test_bit_inv(DIAG310_SUBC_1, &mask)) + return -EOPNOTSUPP; + if (!test_bit_inv(DIAG310_SUBC_4, &mask)) + return -EOPNOTSUPP; + if (!test_bit_inv(DIAG310_SUBC_5, &mask)) + return -EOPNOTSUPP; + WRITE_ONCE(features_available, 1); + return 0; +} + +static int memtop_get_stride_len(unsigned long *res) +{ + static unsigned long memtop_stride; + unsigned long stride; + int rc; + + stride = READ_ONCE(memtop_stride); + if (!stride) { + rc = diag310_get_memtop_stride(&stride); + if (rc) + return rc; + WRITE_ONCE(memtop_stride, stride); + } + *res = stride; + return 0; +} + +static int memtop_get_page_count(unsigned long *res, unsigned long level) +{ + static unsigned long memtop_pages[DIAG310_LEVELMAX]; + unsigned long pages; + int rc; + + if (level > DIAG310_LEVELMAX || level < DIAG310_LEVELMIN) + return -EINVAL; + pages = READ_ONCE(memtop_pages[level - 1]); + if (!pages) { + rc = diag310_get_memtop_size(&pages, level); + if (rc) + return rc; + WRITE_ONCE(memtop_pages[level - 1], pages); + } + *res = pages; + return 0; +} + +long diag310_memtop_stride(unsigned long arg) +{ + size_t __user *argp = (void __user *)arg; + unsigned long stride; + int rc; + + rc = diag310_check_features(); + if (rc) + return rc; + rc = memtop_get_stride_len(&stride); + if (rc) + return rc; + if (put_user(stride, argp)) + return -EFAULT; + return 0; +} + +long diag310_memtop_len(unsigned long arg) +{ + size_t __user *argp = (void __user *)arg; + unsigned long pages, level; + int rc; + + rc = diag310_check_features(); + if (rc) + return rc; + if (get_user(level, argp)) + return -EFAULT; + rc = memtop_get_page_count(&pages, level); + if (rc) + return rc; + if (put_user(pages * PAGE_SIZE, argp)) + return -EFAULT; + return 0; +} + +long diag310_memtop_buf(unsigned long arg) +{ + struct diag310_memtop __user *udata = (struct diag310_memtop __user *)arg; + unsigned long level, pages, data_size; + u64 address; + void *buf; + int rc; + + rc = diag310_check_features(); + if (rc) + return rc; + if (get_user(level, &udata->nesting_lvl)) + return -EFAULT; + if (get_user(address, &udata->address)) + return -EFAULT; + rc = memtop_get_page_count(&pages, level); + if (rc) + return rc; + data_size = pages * PAGE_SIZE; + buf = __vmalloc_node(data_size, PAGE_SIZE, GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT, + NUMA_NO_NODE, __builtin_return_address(0)); + if (!buf) + return -ENOMEM; + rc = diag310_store_topology_map(buf, pages, level); + if (rc) + goto out; + if (copy_to_user((void __user *)address, buf, data_size)) + rc = -EFAULT; +out: + vfree(buf); + return rc; +} diff --git a/arch/s390/kernel/diag/diag324.c b/arch/s390/kernel/diag/diag324.c new file mode 100644 index 000000000000..7fa4c0b7eb6c --- /dev/null +++ b/arch/s390/kernel/diag/diag324.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Request power readings for resources in a computing environment via + * diag 0x324. diag 0x324 stores the power readings in the power information + * block (pib). + * + * Copyright IBM Corp. 2024 + */ + +#define pr_fmt(fmt) "diag324: " fmt +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include "diag_ioctl.h" + +enum subcode { + DIAG324_SUBC_0 = 0, + DIAG324_SUBC_1 = 1, + DIAG324_SUBC_2 = 2, +}; + +enum retcode { + DIAG324_RET_SUCCESS = 0x0001, + DIAG324_RET_SUBC_NOTAVAIL = 0x0103, + DIAG324_RET_INSUFFICIENT_SIZE = 0x0104, + DIAG324_RET_READING_UNAVAILABLE = 0x0105, +}; + +union diag324_response { + u64 response; + struct { + u64 installed : 32; + u64 : 16; + u64 rc : 16; + } sc0; + struct { + u64 format : 16; + u64 : 16; + u64 pib_len : 16; + u64 rc : 16; + } sc1; + struct { + u64 : 48; + u64 rc : 16; + } sc2; +}; + +union diag324_request { + u64 request; + struct { + u64 : 32; + u64 allocated : 16; + u64 : 12; + u64 sc : 4; + } sc2; +}; + +struct pib { + u32 : 8; + u32 num : 8; + u32 len : 16; + u32 : 24; + u32 hlen : 8; + u64 : 64; + u64 intv; + u8 r[]; +} __packed; + +struct pibdata { + struct pib *pib; + ktime_t expire; + u64 sequence; + size_t len; + int rc; +}; + +static DEFINE_MUTEX(pibmutex); +static struct pibdata pibdata; + +#define PIBWORK_DELAY (5 * NSEC_PER_SEC) + +static void pibwork_handler(struct work_struct *work); +static DECLARE_DELAYED_WORK(pibwork, pibwork_handler); + +static unsigned long diag324(unsigned long subcode, void *addr) +{ + union register_pair rp = { .even = (unsigned long)addr }; + + diag_stat_inc(DIAG_STAT_X324); + asm volatile("diag %[rp],%[subcode],0x324\n" + : [rp] "+d" (rp.pair) + : [subcode] "d" (subcode) + : "memory"); + return rp.odd; +} + +static void pibwork_handler(struct work_struct *work) +{ + struct pibdata *data = &pibdata; + ktime_t timedout; + + mutex_lock(&pibmutex); + timedout = ktime_add_ns(data->expire, PIBWORK_DELAY); + if (ktime_before(ktime_get(), timedout)) { + mod_delayed_work(system_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY)); + goto out; + } + vfree(data->pib); + data->pib = NULL; +out: + mutex_unlock(&pibmutex); +} + +static void pib_update(struct pibdata *data) +{ + union diag324_request req = { .sc2.sc = DIAG324_SUBC_2, .sc2.allocated = data->len }; + union diag324_response res; + int rc; + + memset(data->pib, 0, data->len); + res.response = diag324(req.request, data->pib); + switch (res.sc2.rc) { + case DIAG324_RET_SUCCESS: + rc = 0; + break; + case DIAG324_RET_SUBC_NOTAVAIL: + rc = -ENOENT; + break; + case DIAG324_RET_INSUFFICIENT_SIZE: + rc = -EMSGSIZE; + break; + case DIAG324_RET_READING_UNAVAILABLE: + rc = -EBUSY; + break; + default: + rc = -EINVAL; + } + data->rc = rc; +} + +long diag324_pibbuf(unsigned long arg) +{ + struct diag324_pib __user *udata = (struct diag324_pib __user *)arg; + struct pibdata *data = &pibdata; + static bool first = true; + u64 address; + int rc; + + if (!data->len) + return -EOPNOTSUPP; + if (get_user(address, &udata->address)) + return -EFAULT; + mutex_lock(&pibmutex); + rc = -ENOMEM; + if (!data->pib) + data->pib = vmalloc(data->len); + if (!data->pib) + goto out; + if (first || ktime_after(ktime_get(), data->expire)) { + pib_update(data); + data->sequence++; + data->expire = ktime_add_ns(ktime_get(), tod_to_ns(data->pib->intv)); + mod_delayed_work(system_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY)); + first = false; + } + rc = data->rc; + if (rc != 0 && rc != -EBUSY) + goto out; + rc = copy_to_user((void __user *)address, data->pib, data->pib->len); + rc |= put_user(data->sequence, &udata->sequence); + if (rc) + rc = -EFAULT; +out: + mutex_unlock(&pibmutex); + return rc; +} + +long diag324_piblen(unsigned long arg) +{ + struct pibdata *data = &pibdata; + + if (!data->len) + return -EOPNOTSUPP; + if (put_user(data->len, (size_t __user *)arg)) + return -EFAULT; + return 0; +} + +static int __init diag324_init(void) +{ + union diag324_response res; + unsigned long installed; + + if (!sclp.has_diag324) + return -EOPNOTSUPP; + res.response = diag324(DIAG324_SUBC_0, NULL); + if (res.sc0.rc != DIAG324_RET_SUCCESS) + return -EOPNOTSUPP; + installed = res.response; + if (!test_bit_inv(DIAG324_SUBC_1, &installed)) + return -EOPNOTSUPP; + if (!test_bit_inv(DIAG324_SUBC_2, &installed)) + return -EOPNOTSUPP; + res.response = diag324(DIAG324_SUBC_1, NULL); + if (res.sc1.rc != DIAG324_RET_SUCCESS) + return -EOPNOTSUPP; + pibdata.len = res.sc1.pib_len; + return 0; +} +device_initcall(diag324_init); diff --git a/arch/s390/kernel/diag/diag_ioctl.h b/arch/s390/kernel/diag/diag_ioctl.h new file mode 100644 index 000000000000..7080be946785 --- /dev/null +++ b/arch/s390/kernel/diag/diag_ioctl.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _DIAG_IOCTL_H +#define _DIAG_IOCTL_H + +#include + +long diag324_pibbuf(unsigned long arg); +long diag324_piblen(unsigned long arg); + +long diag310_memtop_stride(unsigned long arg); +long diag310_memtop_len(unsigned long arg); +long diag310_memtop_buf(unsigned long arg); + +#endif /* _DIAG_IOCTL_H */ diff --git a/arch/s390/kernel/diag/diag_misc.c b/arch/s390/kernel/diag/diag_misc.c new file mode 100644 index 000000000000..efffe02ea02e --- /dev/null +++ b/arch/s390/kernel/diag/diag_misc.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide diagnose information via misc device /dev/diag. + * + * Copyright IBM Corp. 2024 + */ + +#include +#include +#include +#include +#include +#include + +#include +#include "diag_ioctl.h" + +static long diag_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + long rc; + + switch (cmd) { + case DIAG324_GET_PIBLEN: + rc = diag324_piblen(arg); + break; + case DIAG324_GET_PIBBUF: + rc = diag324_pibbuf(arg); + break; + case DIAG310_GET_STRIDE: + rc = diag310_memtop_stride(arg); + break; + case DIAG310_GET_MEMTOPLEN: + rc = diag310_memtop_len(arg); + break; + case DIAG310_GET_MEMTOPBUF: + rc = diag310_memtop_buf(arg); + break; + default: + rc = -ENOIOCTLCMD; + break; + } + return rc; +} + +static const struct file_operations fops = { + .owner = THIS_MODULE, + .open = nonseekable_open, + .unlocked_ioctl = diag_ioctl, +}; + +static struct miscdevice diagdev = { + .name = "diag", + .minor = MISC_DYNAMIC_MINOR, + .fops = &fops, + .mode = 0444, +}; + +static int diag_init(void) +{ + return misc_register(&diagdev); +} + +device_initcall(diag_init); diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 62f8f5a750a3..2fa25164df7d 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -50,6 +50,7 @@ decompressor_handled_param(facilities); decompressor_handled_param(nokaslr); decompressor_handled_param(cmma); decompressor_handled_param(relocate_lowcore); +decompressor_handled_param(bootdebug); #if IS_ENABLED(CONFIG_KVM) decompressor_handled_param(prot_virt); #endif @@ -58,7 +59,7 @@ static void __init kasan_early_init(void) { #ifdef CONFIG_KASAN init_task.kasan_depth = 0; - sclp_early_printk("KernelAddressSanitizer initialized\n"); + pr_info("KernelAddressSanitizer initialized\n"); #endif } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 960c08700cf6..4cc3408c4dac 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -52,16 +52,7 @@ _LPP_OFFSET = __LC_LPP ALT_FACILITY(193) .endm - .macro CHECK_STACK savearea, lowcore -#ifdef CONFIG_CHECK_STACK - tml %r15,THREAD_SIZE - CONFIG_STACK_GUARD - la %r14,\savearea(\lowcore) - jz stack_overflow -#endif - .endm - .macro CHECK_VMAP_STACK savearea, lowcore, oklabel -#ifdef CONFIG_VMAP_STACK lgr %r14,%r15 nill %r14,0x10000 - THREAD_SIZE oill %r14,STACK_INIT_OFFSET @@ -77,9 +68,6 @@ _LPP_OFFSET = __LC_LPP je \oklabel la %r14,\savearea(\lowcore) j stack_overflow -#else - j \oklabel -#endif .endm /* @@ -326,8 +314,7 @@ SYM_CODE_START(pgm_check_handler) jnz 2f # -> enabled, can't be a double fault tm __LC_PGM_ILC+3(%r13),0x80 # check for per exception jnz .Lpgm_svcper # -> single stepped svc -2: CHECK_STACK __LC_SAVE_AREA,%r13 - aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) +2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) # CHECK_VMAP_STACK branches to stack_overflow or 4f CHECK_VMAP_STACK __LC_SAVE_AREA,%r13,4f 3: lg %r15,__LC_KERNEL_STACK(%r13) @@ -394,8 +381,7 @@ SYM_CODE_START(\name) BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST SIEEXIT __SF_SIE_CONTROL(%r15),%r13 #endif -0: CHECK_STACK __LC_SAVE_AREA,%r13 - aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) +0: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: lctlg %c1,%c1,__LC_KERNEL_ASCE(%r13) lg %r15,__LC_KERNEL_STACK(%r13) @@ -603,7 +589,6 @@ SYM_CODE_END(early_pgm_check_handler) .section .kprobes.text, "ax" -#if defined(CONFIG_CHECK_STACK) || defined(CONFIG_VMAP_STACK) /* * The synchronous or the asynchronous stack overflowed. We are dead. * No need to properly save the registers, we are going to panic anyway. @@ -621,7 +606,6 @@ SYM_CODE_START(stack_overflow) lgr %r2,%r11 # pass pointer to pt_regs jg kernel_stack_overflow SYM_CODE_END(stack_overflow) -#endif .section .data, "aw" .balign 4 diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 21969520f947..a1f28879c87e 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -41,7 +41,6 @@ void do_restart(void *arg); void __init startup_init(void); void die(struct pt_regs *regs, const char *str); int setup_profiling_timer(unsigned int multiplier); -unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip); struct s390_mmap_arg_struct; struct fadvise64_64_args; diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 51439a71e392..63ba6306632e 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -261,43 +261,18 @@ void ftrace_arch_code_modify_post_process(void) } #ifdef CONFIG_FUNCTION_GRAPH_TRACER -/* - * Hook the return address and push it in the stack of return addresses - * in current thread info. - */ -unsigned long prepare_ftrace_return(unsigned long ra, unsigned long sp, - unsigned long ip) + +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) { + unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14]; + if (unlikely(ftrace_graph_is_dead())) - goto out; + return; if (unlikely(atomic_read(¤t->tracing_graph_pause))) - goto out; - ip -= MCOUNT_INSN_SIZE; - if (!function_graph_enter(ra, ip, 0, (void *) sp)) - ra = (unsigned long) return_to_handler; -out: - return ra; -} -NOKPROBE_SYMBOL(prepare_ftrace_return); - -/* - * Patch the kernel code at ftrace_graph_caller location. The instruction - * there is branch relative on condition. To enable the ftrace graph code - * block, we simply patch the mask field of the instruction to zero and - * turn the instruction into a nop. - * To disable the ftrace graph code the mask field will be patched to - * all ones, which turns the instruction into an unconditional branch. - */ -int ftrace_enable_ftrace_graph_caller(void) -{ - /* Expect brc 0xf,... */ - return ftrace_patch_branch_mask(ftrace_graph_caller, 0xa7f4, false); -} - -int ftrace_disable_ftrace_graph_caller(void) -{ - /* Expect brc 0x0,... */ - return ftrace_patch_branch_mask(ftrace_graph_caller, 0xa704, true); + return; + if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs)) + *parent = (unsigned long)&return_to_handler; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/s390/kernel/hiperdispatch.c b/arch/s390/kernel/hiperdispatch.c index 2a99a216ab62..7857a7e8e56c 100644 --- a/arch/s390/kernel/hiperdispatch.c +++ b/arch/s390/kernel/hiperdispatch.c @@ -292,7 +292,7 @@ static int hiperdispatch_ctl_handler(const struct ctl_table *ctl, int write, return 0; } -static struct ctl_table hiperdispatch_ctl_table[] = { +static const struct ctl_table hiperdispatch_ctl_table[] = { { .procname = "hiperdispatch", .mode = 0644, diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index edbb52ce3f1e..69be2309cde0 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -270,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ if (len >= sizeof(_value)) \ return -E2BIG; \ len = strscpy(_value, buf, sizeof(_value)); \ - if (len < 0) \ + if ((ssize_t)len < 0) \ return len; \ strim(_value); \ return len; \ @@ -280,58 +280,58 @@ static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ sys_##_prefix##_##_name##_show, \ sys_##_prefix##_##_name##_store) -#define IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \ -static ssize_t sys_##_prefix##_scp_data_show(struct file *filp, \ - struct kobject *kobj, \ - struct bin_attribute *attr, \ - char *buf, loff_t off, \ - size_t count) \ -{ \ - size_t size = _ipl_block.scp_data_len; \ - void *scp_data = _ipl_block.scp_data; \ - \ - return memory_read_from_buffer(buf, count, &off, \ - scp_data, size); \ +#define IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \ +static ssize_t sys_##_prefix##_scp_data_show(struct file *filp, \ + struct kobject *kobj, \ + const struct bin_attribute *attr, \ + char *buf, loff_t off, \ + size_t count) \ +{ \ + size_t size = _ipl_block.scp_data_len; \ + void *scp_data = _ipl_block.scp_data; \ + \ + return memory_read_from_buffer(buf, count, &off, \ + scp_data, size); \ } #define IPL_ATTR_SCP_DATA_STORE_FN(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len)\ -static ssize_t sys_##_prefix##_scp_data_store(struct file *filp, \ - struct kobject *kobj, \ - struct bin_attribute *attr, \ - char *buf, loff_t off, \ - size_t count) \ -{ \ - size_t scpdata_len = count; \ - size_t padding; \ - \ - if (off) \ - return -EINVAL; \ - \ - memcpy(_ipl_block.scp_data, buf, count); \ - if (scpdata_len % 8) { \ - padding = 8 - (scpdata_len % 8); \ - memset(_ipl_block.scp_data + scpdata_len, \ - 0, padding); \ - scpdata_len += padding; \ - } \ - \ - _ipl_block_hdr.len = _ipl_bp_len + scpdata_len; \ - _ipl_block.len = _ipl_bp0_len + scpdata_len; \ - _ipl_block.scp_data_len = scpdata_len; \ - \ - return count; \ +static ssize_t sys_##_prefix##_scp_data_store(struct file *filp, \ + struct kobject *kobj, \ + const struct bin_attribute *attr, \ + char *buf, loff_t off, \ + size_t count) \ +{ \ + size_t scpdata_len = count; \ + size_t padding; \ + \ + if (off) \ + return -EINVAL; \ + \ + memcpy(_ipl_block.scp_data, buf, count); \ + if (scpdata_len % 8) { \ + padding = 8 - (scpdata_len % 8); \ + memset(_ipl_block.scp_data + scpdata_len, \ + 0, padding); \ + scpdata_len += padding; \ + } \ + \ + _ipl_block_hdr.len = _ipl_bp_len + scpdata_len; \ + _ipl_block.len = _ipl_bp0_len + scpdata_len; \ + _ipl_block.scp_data_len = scpdata_len; \ + \ + return count; \ } #define DEFINE_IPL_ATTR_SCP_DATA_RO(_prefix, _ipl_block, _size) \ IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \ -static struct bin_attribute sys_##_prefix##_scp_data_attr = \ +static const struct bin_attribute sys_##_prefix##_scp_data_attr = \ __BIN_ATTR(scp_data, 0444, sys_##_prefix##_scp_data_show, \ NULL, _size) #define DEFINE_IPL_ATTR_SCP_DATA_RW(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len, _size)\ IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \ IPL_ATTR_SCP_DATA_STORE_FN(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len)\ -static struct bin_attribute sys_##_prefix##_scp_data_attr = \ +static const struct bin_attribute sys_##_prefix##_scp_data_attr = \ __BIN_ATTR(scp_data, 0644, sys_##_prefix##_scp_data_show, \ sys_##_prefix##_scp_data_store, _size) @@ -434,19 +434,19 @@ static struct kobj_attribute sys_ipl_device_attr = __ATTR(device, 0444, sys_ipl_device_show, NULL); static ssize_t sys_ipl_parameter_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { return memory_read_from_buffer(buf, count, &off, &ipl_block, ipl_block.hdr.len); } -static struct bin_attribute sys_ipl_parameter_attr = +static const struct bin_attribute sys_ipl_parameter_attr = __BIN_ATTR(binary_parameter, 0444, sys_ipl_parameter_read, NULL, PAGE_SIZE); DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_fcp, ipl_block.fcp, PAGE_SIZE); -static struct bin_attribute *ipl_fcp_bin_attrs[] = { +static const struct bin_attribute *const ipl_fcp_bin_attrs[] = { &sys_ipl_parameter_attr, &sys_ipl_fcp_scp_data_attr, NULL, @@ -454,7 +454,7 @@ static struct bin_attribute *ipl_fcp_bin_attrs[] = { DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_nvme, ipl_block.nvme, PAGE_SIZE); -static struct bin_attribute *ipl_nvme_bin_attrs[] = { +static const struct bin_attribute *const ipl_nvme_bin_attrs[] = { &sys_ipl_parameter_attr, &sys_ipl_nvme_scp_data_attr, NULL, @@ -462,7 +462,7 @@ static struct bin_attribute *ipl_nvme_bin_attrs[] = { DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_eckd, ipl_block.eckd, PAGE_SIZE); -static struct bin_attribute *ipl_eckd_bin_attrs[] = { +static const struct bin_attribute *const ipl_eckd_bin_attrs[] = { &sys_ipl_parameter_attr, &sys_ipl_eckd_scp_data_attr, NULL, @@ -593,9 +593,9 @@ static struct attribute *ipl_fcp_attrs[] = { NULL, }; -static struct attribute_group ipl_fcp_attr_group = { +static const struct attribute_group ipl_fcp_attr_group = { .attrs = ipl_fcp_attrs, - .bin_attrs = ipl_fcp_bin_attrs, + .bin_attrs_new = ipl_fcp_bin_attrs, }; static struct attribute *ipl_nvme_attrs[] = { @@ -607,9 +607,9 @@ static struct attribute *ipl_nvme_attrs[] = { NULL, }; -static struct attribute_group ipl_nvme_attr_group = { +static const struct attribute_group ipl_nvme_attr_group = { .attrs = ipl_nvme_attrs, - .bin_attrs = ipl_nvme_bin_attrs, + .bin_attrs_new = ipl_nvme_bin_attrs, }; static struct attribute *ipl_eckd_attrs[] = { @@ -620,9 +620,9 @@ static struct attribute *ipl_eckd_attrs[] = { NULL, }; -static struct attribute_group ipl_eckd_attr_group = { +static const struct attribute_group ipl_eckd_attr_group = { .attrs = ipl_eckd_attrs, - .bin_attrs = ipl_eckd_bin_attrs, + .bin_attrs_new = ipl_eckd_bin_attrs, }; /* CCW ipl device attributes */ @@ -640,11 +640,11 @@ static struct attribute *ipl_ccw_attrs_lpar[] = { NULL, }; -static struct attribute_group ipl_ccw_attr_group_vm = { +static const struct attribute_group ipl_ccw_attr_group_vm = { .attrs = ipl_ccw_attrs_vm, }; -static struct attribute_group ipl_ccw_attr_group_lpar = { +static const struct attribute_group ipl_ccw_attr_group_lpar = { .attrs = ipl_ccw_attrs_lpar }; @@ -655,7 +655,7 @@ static struct attribute *ipl_common_attrs[] = { NULL, }; -static struct attribute_group ipl_common_attr_group = { +static const struct attribute_group ipl_common_attr_group = { .attrs = ipl_common_attrs, }; @@ -808,7 +808,7 @@ DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_fcp, reipl_block_fcp->hdr, IPL_BP_FCP_LEN, IPL_BP0_FCP_LEN, DIAG308_SCPDATA_SIZE); -static struct bin_attribute *reipl_fcp_bin_attrs[] = { +static const struct bin_attribute *const reipl_fcp_bin_attrs[] = { &sys_reipl_fcp_scp_data_attr, NULL, }; @@ -917,9 +917,9 @@ static struct attribute *reipl_fcp_attrs[] = { NULL, }; -static struct attribute_group reipl_fcp_attr_group = { +static const struct attribute_group reipl_fcp_attr_group = { .attrs = reipl_fcp_attrs, - .bin_attrs = reipl_fcp_bin_attrs, + .bin_attrs_new = reipl_fcp_bin_attrs, }; static struct kobj_attribute sys_reipl_fcp_clear_attr = @@ -932,7 +932,7 @@ DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_nvme, reipl_block_nvme->hdr, IPL_BP_NVME_LEN, IPL_BP0_NVME_LEN, DIAG308_SCPDATA_SIZE); -static struct bin_attribute *reipl_nvme_bin_attrs[] = { +static const struct bin_attribute *const reipl_nvme_bin_attrs[] = { &sys_reipl_nvme_scp_data_attr, NULL, }; @@ -955,9 +955,9 @@ static struct attribute *reipl_nvme_attrs[] = { NULL, }; -static struct attribute_group reipl_nvme_attr_group = { +static const struct attribute_group reipl_nvme_attr_group = { .attrs = reipl_nvme_attrs, - .bin_attrs = reipl_nvme_bin_attrs + .bin_attrs_new = reipl_nvme_bin_attrs }; static ssize_t reipl_nvme_clear_show(struct kobject *kobj, @@ -1031,7 +1031,7 @@ DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_eckd, reipl_block_eckd->hdr, IPL_BP_ECKD_LEN, IPL_BP0_ECKD_LEN, DIAG308_SCPDATA_SIZE); -static struct bin_attribute *reipl_eckd_bin_attrs[] = { +static const struct bin_attribute *const reipl_eckd_bin_attrs[] = { &sys_reipl_eckd_scp_data_attr, NULL, }; @@ -1048,9 +1048,9 @@ static struct attribute *reipl_eckd_attrs[] = { NULL, }; -static struct attribute_group reipl_eckd_attr_group = { +static const struct attribute_group reipl_eckd_attr_group = { .attrs = reipl_eckd_attrs, - .bin_attrs = reipl_eckd_bin_attrs + .bin_attrs_new = reipl_eckd_bin_attrs }; static ssize_t reipl_eckd_clear_show(struct kobject *kobj, @@ -1587,15 +1587,15 @@ static struct attribute *dump_fcp_attrs[] = { NULL, }; -static struct bin_attribute *dump_fcp_bin_attrs[] = { +static const struct bin_attribute *const dump_fcp_bin_attrs[] = { &sys_dump_fcp_scp_data_attr, NULL, }; -static struct attribute_group dump_fcp_attr_group = { +static const struct attribute_group dump_fcp_attr_group = { .name = IPL_FCP_STR, .attrs = dump_fcp_attrs, - .bin_attrs = dump_fcp_bin_attrs, + .bin_attrs_new = dump_fcp_bin_attrs, }; /* NVME dump device attributes */ @@ -1621,15 +1621,15 @@ static struct attribute *dump_nvme_attrs[] = { NULL, }; -static struct bin_attribute *dump_nvme_bin_attrs[] = { +static const struct bin_attribute *const dump_nvme_bin_attrs[] = { &sys_dump_nvme_scp_data_attr, NULL, }; -static struct attribute_group dump_nvme_attr_group = { +static const struct attribute_group dump_nvme_attr_group = { .name = IPL_NVME_STR, .attrs = dump_nvme_attrs, - .bin_attrs = dump_nvme_bin_attrs, + .bin_attrs_new = dump_nvme_bin_attrs, }; /* ECKD dump device attributes */ @@ -1655,15 +1655,15 @@ static struct attribute *dump_eckd_attrs[] = { NULL, }; -static struct bin_attribute *dump_eckd_bin_attrs[] = { +static const struct bin_attribute *const dump_eckd_bin_attrs[] = { &sys_dump_eckd_scp_data_attr, NULL, }; -static struct attribute_group dump_eckd_attr_group = { +static const struct attribute_group dump_eckd_attr_group = { .name = IPL_ECKD_STR, .attrs = dump_eckd_attrs, - .bin_attrs = dump_eckd_bin_attrs, + .bin_attrs_new = dump_eckd_bin_attrs, }; /* CCW dump device attributes */ diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c index 6652e54cf3db..6d1ffca5f798 100644 --- a/arch/s390/kernel/lgr.c +++ b/arch/s390/kernel/lgr.c @@ -166,7 +166,7 @@ static struct timer_list lgr_timer; */ static void lgr_timer_set(void) { - mod_timer(&lgr_timer, jiffies + msecs_to_jiffies(LGR_TIMER_INTERVAL_SECS * MSEC_PER_SEC)); + mod_timer(&lgr_timer, jiffies + secs_to_jiffies(LGR_TIMER_INTERVAL_SECS)); } /* diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 7e267ef63a7f..1fec370fecf4 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -104,17 +104,6 @@ SYM_CODE_START(ftrace_common) lgr %r3,%r14 la %r5,STACK_FREGS(%r15) BASR_EX %r14,%r1 -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -# The j instruction gets runtime patched to a nop instruction. -# See ftrace_enable_ftrace_graph_caller. -SYM_INNER_LABEL(ftrace_graph_caller, SYM_L_GLOBAL) - j .Lftrace_graph_caller_end - lmg %r2,%r3,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15) - lg %r4,(STACK_FREGS_PTREGS_PSW+8)(%r15) - brasl %r14,prepare_ftrace_return - stg %r2,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15) -.Lftrace_graph_caller_end: -#endif lg %r0,(STACK_FREGS_PTREGS_PSW+8)(%r15) #ifdef MARCH_HAS_Z196_FEATURES ltg %r1,STACK_FREGS_PTREGS_ORIG_GPR2(%r15) @@ -134,14 +123,14 @@ SYM_CODE_END(ftrace_common) SYM_FUNC_START(return_to_handler) stmg %r2,%r5,32(%r15) lgr %r1,%r15 - aghi %r15,-(STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE) + # allocate ftrace_regs and stack frame for ftrace_return_to_handler + aghi %r15,-STACK_FRAME_SIZE_FREGS stg %r1,__SF_BACKCHAIN(%r15) - la %r3,STACK_FRAME_OVERHEAD(%r15) - stg %r1,__FGRAPH_RET_FP(%r3) - stg %r2,__FGRAPH_RET_GPR2(%r3) - lgr %r2,%r3 + stg %r2,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15) + stg %r1,(STACK_FREGS_PTREGS_GPRS+15*8)(%r15) + la %r2,STACK_FRAME_OVERHEAD(%r15) brasl %r14,ftrace_return_to_handler - aghi %r15,STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE + aghi %r15,STACK_FRAME_SIZE_FREGS lgr %r14,%r2 lmg %r2,%r5,32(%r15) BR_EX %r14 diff --git a/arch/s390/kernel/numa.c b/arch/s390/kernel/numa.c index ddc1448ea2e1..2fc40f97c0ad 100644 --- a/arch/s390/kernel/numa.c +++ b/arch/s390/kernel/numa.c @@ -21,12 +21,8 @@ void __init numa_setup(void) nodes_clear(node_possible_map); node_set(0, node_possible_map); node_set_online(0); - for (nid = 0; nid < MAX_NUMNODES; nid++) { - NODE_DATA(nid) = memblock_alloc(sizeof(pg_data_t), 8); - if (!NODE_DATA(nid)) - panic("%s: Failed to allocate %zu bytes align=0x%x\n", - __func__, sizeof(pg_data_t), 8); - } + for (nid = 0; nid < MAX_NUMNODES; nid++) + NODE_DATA(nid) = memblock_alloc_or_panic(sizeof(pg_data_t), 8); NODE_DATA(0)->node_spanned_pages = memblock_end_of_DRAM() >> PAGE_SHIFT; NODE_DATA(0)->node_id = 0; } diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 29080d6d5d8d..c2a468986212 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -18,6 +18,7 @@ #include #include #include +#include #include /* diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index b0bc68da6a11..33205dd410e4 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -981,7 +981,7 @@ static int cfdiag_push_sample(struct perf_event *event, if (event->attr.sample_type & PERF_SAMPLE_RAW) { raw.frag.size = cpuhw->usedss; raw.frag.data = cpuhw->stop; - perf_sample_save_raw_data(&data, &raw); + perf_sample_save_raw_data(&data, event, &raw); } overflow = perf_event_overflow(event, &data, ®s); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 1e99514fb7ae..5f60248cb468 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -981,7 +981,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu) cpuhw->flags &= ~PMU_F_ENABLED; } -/* perf_exclude_event() - Filter event +/* perf_event_exclude() - Filter event * @event: The perf event * @regs: pt_regs structure * @sde_regs: Sample-data-entry (sde) regs structure @@ -990,7 +990,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu) * * Return non-zero if the event shall be excluded. */ -static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs, +static int perf_event_exclude(struct perf_event *event, struct pt_regs *regs, struct perf_sf_sde_regs *sde_regs) { if (event->attr.exclude_user && user_mode(regs)) @@ -1073,7 +1073,7 @@ static int perf_push_sample(struct perf_event *event, data.tid_entry.pid = basic->hpp & LPP_PID_MASK; overflow = 0; - if (perf_exclude_event(event, ®s, sde_regs)) + if (perf_event_exclude(event, ®s, sde_regs)) goto out; if (perf_event_overflow(event, &data, ®s)) { overflow = 1; diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index fa7325454266..10725f5a6f0f 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -478,7 +478,7 @@ static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump, if (event->attr.sample_type & PERF_SAMPLE_RAW) { raw.frag.size = rawsize; raw.frag.data = cpump->save; - perf_sample_save_raw_data(&data, &raw); + perf_sample_save_raw_data(&data, event, &raw); } overflow = perf_event_overflow(event, &data, ®s); diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index 7f462bef1fc0..a8f0bad99cf0 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -503,7 +503,7 @@ static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump, if (event->attr.sample_type & PERF_SAMPLE_RAW) { raw.frag.size = rawsize; raw.frag.data = cpump->save; - perf_sample_save_raw_data(&data, &raw); + perf_sample_save_raw_data(&data, event, &raw); } overflow = perf_event_overflow(event, &data, ®s); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index a3fea683b227..d78bcfe707b5 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -157,18 +157,24 @@ u64 __bootdata_preserved(stfle_fac_list[16]); EXPORT_SYMBOL(stfle_fac_list); struct oldmem_data __bootdata_preserved(oldmem_data); -unsigned long VMALLOC_START; +char __bootdata(boot_rb)[PAGE_SIZE * 2]; +bool __bootdata(boot_earlyprintk); +size_t __bootdata(boot_rb_off); +char __bootdata(bootdebug_filter)[128]; +bool __bootdata(bootdebug); + +unsigned long __bootdata_preserved(VMALLOC_START); EXPORT_SYMBOL(VMALLOC_START); -unsigned long VMALLOC_END; +unsigned long __bootdata_preserved(VMALLOC_END); EXPORT_SYMBOL(VMALLOC_END); -struct page *vmemmap; +struct page *__bootdata_preserved(vmemmap); EXPORT_SYMBOL(vmemmap); -unsigned long vmemmap_size; +unsigned long __bootdata_preserved(vmemmap_size); -unsigned long MODULES_VADDR; -unsigned long MODULES_END; +unsigned long __bootdata_preserved(MODULES_VADDR); +unsigned long __bootdata_preserved(MODULES_END); /* An array with a pointer to the lowcore of every CPU. */ struct lowcore *lowcore_ptr[NR_CPUS]; @@ -359,36 +365,24 @@ void *restart_stack; unsigned long stack_alloc(void) { -#ifdef CONFIG_VMAP_STACK - void *ret; + void *stack; - ret = __vmalloc_node(THREAD_SIZE, THREAD_SIZE, THREADINFO_GFP, - NUMA_NO_NODE, __builtin_return_address(0)); - kmemleak_not_leak(ret); - return (unsigned long)ret; -#else - return __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER); -#endif + stack = __vmalloc_node(THREAD_SIZE, THREAD_SIZE, THREADINFO_GFP, + NUMA_NO_NODE, __builtin_return_address(0)); + kmemleak_not_leak(stack); + return (unsigned long)stack; } void stack_free(unsigned long stack) { -#ifdef CONFIG_VMAP_STACK - vfree((void *) stack); -#else - free_pages(stack, THREAD_SIZE_ORDER); -#endif + vfree((void *)stack); } static unsigned long __init stack_alloc_early(void) { unsigned long stack; - stack = (unsigned long)memblock_alloc(THREAD_SIZE, THREAD_SIZE); - if (!stack) { - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, THREAD_SIZE, THREAD_SIZE); - } + stack = (unsigned long)memblock_alloc_or_panic(THREAD_SIZE, THREAD_SIZE); return stack; } @@ -512,10 +506,7 @@ static void __init setup_resources(void) bss_resource.end = __pa_symbol(__bss_stop) - 1; for_each_mem_range(i, &start, &end) { - res = memblock_alloc(sizeof(*res), 8); - if (!res) - panic("%s: Failed to allocate %zu bytes align=0x%x\n", - __func__, sizeof(*res), 8); + res = memblock_alloc_or_panic(sizeof(*res), 8); res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; res->name = "System RAM"; @@ -534,10 +525,7 @@ static void __init setup_resources(void) std_res->start > res->end) continue; if (std_res->end > res->end) { - sub_res = memblock_alloc(sizeof(*sub_res), 8); - if (!sub_res) - panic("%s: Failed to allocate %zu bytes align=0x%x\n", - __func__, sizeof(*sub_res), 8); + sub_res = memblock_alloc_or_panic(sizeof(*sub_res), 8); *sub_res = *std_res; sub_res->end = res->end; std_res->start = res->end + 1; @@ -704,7 +692,7 @@ static void __init reserve_physmem_info(void) { unsigned long addr, size; - if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size)) + if (get_physmem_reserved(RR_MEM_DETECT_EXT, &addr, &size)) memblock_reserve(addr, size); } @@ -712,7 +700,7 @@ static void __init free_physmem_info(void) { unsigned long addr, size; - if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size)) + if (get_physmem_reserved(RR_MEM_DETECT_EXT, &addr, &size)) memblock_phys_free(addr, size); } @@ -742,7 +730,7 @@ static void __init reserve_lowcore(void) void *lowcore_end = lowcore_start + sizeof(struct lowcore); void *start, *end; - if ((void *)__identity_base < lowcore_end) { + if (absolute_pointer(__identity_base) < lowcore_end) { start = max(lowcore_start, (void *)__identity_base); end = min(lowcore_end, (void *)(__identity_base + ident_map_size)); memblock_reserve(__pa(start), __pa(end)); @@ -824,9 +812,7 @@ static void __init setup_randomness(void) { struct sysinfo_3_2_2 *vmms; - vmms = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!vmms) - panic("Failed to allocate memory for sysinfo structure\n"); + vmms = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count); memblock_free(vmms, PAGE_SIZE); @@ -885,6 +871,23 @@ static void __init log_component_list(void) } } +/* + * Print avoiding interpretation of % in buf and taking bootdebug option + * into consideration. + */ +static void __init print_rb_entry(const char *buf) +{ + char fmt[] = KERN_SOH "0boot: %s"; + int level = printk_get_level(buf); + + buf = skip_timestamp(printk_skip_level(buf)); + if (level == KERN_DEBUG[1] && (!bootdebug || !bootdebug_filter_match(buf))) + return; + + fmt[1] = level; + printk(fmt, buf); +} + /* * Setup function called from init/main.c just after the banner * was printed. @@ -904,6 +907,9 @@ void __init setup_arch(char **cmdline_p) pr_info("Linux is running natively in 64-bit mode\n"); else pr_info("Linux is running as a guest in 64-bit mode\n"); + /* Print decompressor messages if not already printed */ + if (!boot_earlyprintk) + boot_rb_foreach(print_rb_entry); if (have_relocated_lowcore()) pr_info("Lowcore relocated to 0x%px\n", get_lowcore()); @@ -979,6 +985,7 @@ void __init setup_arch(char **cmdline_p) if (test_facility(193)) static_branch_enable(&cpu_has_bear); + setup_protection_map(); /* * Create kernel page tables. */ @@ -1006,3 +1013,8 @@ void __init setup_arch(char **cmdline_p) /* Add system specific data to the random pool */ setup_randomness(); } + +void __init arch_cpu_finalize_init(void) +{ + sclp_init(); +} diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 822d8e6f8717..7b08399b0846 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -611,9 +611,7 @@ void __init smp_save_dump_ipl_cpu(void) if (!dump_available()) return; sa = save_area_alloc(true); - regs = memblock_alloc(512, 8); - if (!sa || !regs) - panic("could not allocate memory for boot CPU save area\n"); + regs = memblock_alloc_or_panic(512, 8); copy_oldmem_kernel(regs, __LC_FPREGS_SAVE_AREA, 512); save_area_add_regs(sa, regs); memblock_free(regs, 512); @@ -646,8 +644,6 @@ void __init smp_save_dump_secondary_cpus(void) SIGP_CC_NOT_OPERATIONAL) continue; sa = save_area_alloc(false); - if (!sa) - panic("could not allocate memory for save area\n"); __pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, __pa(page)); save_area_add_regs(sa, page); if (cpu_has_vx()) { @@ -792,10 +788,7 @@ void __init smp_detect_cpus(void) u16 address; /* Get CPU information */ - info = memblock_alloc(sizeof(*info), 8); - if (!info) - panic("%s: Failed to allocate %zu bytes align=0x%x\n", - __func__, sizeof(*info), 8); + info = memblock_alloc_or_panic(sizeof(*info), 8); smp_get_core_info(info, 1); /* Find boot CPU type */ if (sclp.has_core_type) { diff --git a/arch/s390/kernel/text_amode31.S b/arch/s390/kernel/text_amode31.S index c0a70efa2426..26f2981aa09e 100644 --- a/arch/s390/kernel/text_amode31.S +++ b/arch/s390/kernel/text_amode31.S @@ -18,8 +18,7 @@ * affects a few functions that are not performance-relevant. */ .macro BR_EX_AMODE31_r14 - larl %r1,0f - ex 0,0(%r1) + exrl 0,0f j . 0: br %r14 .endm diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 34a65c141ea0..e9f47c3a6197 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -662,12 +662,12 @@ static void stp_check_leap(void) if (ret < 0) pr_err("failed to set leap second flags\n"); /* arm Timer to clear leap second flags */ - mod_timer(&stp_timer, jiffies + msecs_to_jiffies(14400 * MSEC_PER_SEC)); + mod_timer(&stp_timer, jiffies + secs_to_jiffies(14400)); } else { /* The day the leap second is scheduled for hasn't been reached. Retry * in one hour. */ - mod_timer(&stp_timer, jiffies + msecs_to_jiffies(3600 * MSEC_PER_SEC)); + mod_timer(&stp_timer, jiffies + secs_to_jiffies(3600)); } } diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 4f9c301a705b..211cc8382e4a 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -371,7 +371,7 @@ static void set_topology_timer(void) if (atomic_add_unless(&topology_poll, -1, 0)) mod_timer(&topology_timer, jiffies + msecs_to_jiffies(100)); else - mod_timer(&topology_timer, jiffies + msecs_to_jiffies(60 * MSEC_PER_SEC)); + mod_timer(&topology_timer, jiffies + secs_to_jiffies(60)); } void topology_expect_change(void) @@ -548,14 +548,21 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info, nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i]; nr_masks = max(nr_masks, 1); for (i = 0; i < nr_masks; i++) { - mask->next = memblock_alloc(sizeof(*mask->next), 8); - if (!mask->next) - panic("%s: Failed to allocate %zu bytes align=0x%x\n", - __func__, sizeof(*mask->next), 8); + mask->next = memblock_alloc_or_panic(sizeof(*mask->next), 8); mask = mask->next; } } +static int __init detect_polarization(union topology_entry *tle) +{ + struct topology_core *tl_core; + + while (tle->nl) + tle = next_tle(tle); + tl_core = (struct topology_core *)tle; + return tl_core->pp != POLARIZATION_HRZ; +} + void __init topology_init_early(void) { struct sysinfo_15_1_x *info; @@ -569,12 +576,10 @@ void __init topology_init_early(void) } if (!MACHINE_HAS_TOPOLOGY) goto out; - tl_info = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!tl_info) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + tl_info = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); info = tl_info; store_topology(info); + cpu_management = detect_polarization(info->tle); pr_info("The CPU configuration topology of the machine is: %d %d %d %d %d %d / %d\n", info->mag[0], info->mag[1], info->mag[2], info->mag[3], info->mag[4], info->mag[5], info->mnest); @@ -662,7 +667,7 @@ static int polarization_ctl_handler(const struct ctl_table *ctl, int write, return set_polarization(polarization); } -static struct ctl_table topology_ctl_table[] = { +static const struct ctl_table topology_ctl_table[] = { { .procname = "topology", .mode = 0644, diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 37bb4b761229..ad206f2068d8 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -5,7 +5,7 @@ include $(srctree)/lib/vdso/Makefile obj-vdso64 = vdso_user_wrapper.o note.o vgetrandom-chacha.o obj-cvdso64 = vdso64_generic.o getcpu.o vgetrandom.o -VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) $(CC_FLAGS_CHECK_STACK) +VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) CFLAGS_REMOVE_getcpu.o = $(VDSO_CFLAGS_REMOVE) CFLAGS_REMOVE_vgetrandom.o = $(VDSO_CFLAGS_REMOVE) CFLAGS_REMOVE_vdso64_generic.o = $(VDSO_CFLAGS_REMOVE) diff --git a/arch/s390/kernel/vmcore_info.c b/arch/s390/kernel/vmcore_info.c index 23f7d7619a99..cc8933e04ff7 100644 --- a/arch/s390/kernel/vmcore_info.c +++ b/arch/s390/kernel/vmcore_info.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only #include -#include #include +#include +#include #include void arch_crash_save_vmcoreinfo(void) diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 377b9aaf8c92..ff1ddba96352 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -52,7 +52,6 @@ SECTIONS SOFTIRQENTRY_TEXT FTRACE_HOTPATCH_TRAMPOLINES_TEXT *(.text.*_indirect_*) - *(.fixup) *(.gnu.warning) . = ALIGN(PAGE_SIZE); _etext = .; /* End of text section */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index ea8dce299954..d4f031e086fc 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2678,9 +2678,13 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) kvm_s390_clear_float_irqs(dev->kvm); break; case KVM_DEV_FLIC_APF_ENABLE: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 1; break; case KVM_DEV_FLIC_APF_DISABLE_WAIT: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 0; /* * Make sure no async faults are in transition when @@ -2894,6 +2898,8 @@ int kvm_set_routing_entry(struct kvm *kvm, switch (ue->type) { /* we store the userspace addresses instead of the guest addresses */ case KVM_IRQ_ROUTING_S390_ADAPTER: + if (kvm_is_ucontrol(kvm)) + return -EINVAL; e->set = set_adapter_int; uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr); if (uaddr == -EFAULT) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 150b9387860a..a687695d8f68 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -854,7 +854,7 @@ unpin: static void unpin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, gpa_t gpa) { - hpa_t hpa = (hpa_t) vsie_page->scb_o; + hpa_t hpa = virt_to_phys(vsie_page->scb_o); if (hpa) unpin_guest_page(vcpu->kvm, gpa, hpa); diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index f43f897d3fc0..14bbfe50033c 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -24,3 +24,6 @@ obj-$(CONFIG_S390_MODULES_SANITY_TEST_HELPERS) += test_modules_helpers.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o obj-$(CONFIG_EXPOLINE_EXTERN) += expoline.o + +obj-$(CONFIG_CRC32_ARCH) += crc32-s390.o +crc32-s390-y := crc32-glue.o crc32le-vx.o crc32be-vx.o diff --git a/arch/s390/lib/crc32-glue.c b/arch/s390/lib/crc32-glue.c new file mode 100644 index 000000000000..137080e61f90 --- /dev/null +++ b/arch/s390/lib/crc32-glue.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * CRC-32 implemented with the z/Architecture Vector Extension Facility. + * + * Copyright IBM Corp. 2015 + * Author(s): Hendrik Brueckner + */ +#define KMSG_COMPONENT "crc32-vx" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include +#include +#include +#include +#include "crc32-vx.h" + +#define VX_MIN_LEN 64 +#define VX_ALIGNMENT 16L +#define VX_ALIGN_MASK (VX_ALIGNMENT - 1) + +static DEFINE_STATIC_KEY_FALSE(have_vxrs); + +/* + * DEFINE_CRC32_VX() - Define a CRC-32 function using the vector extension + * + * Creates a function to perform a particular CRC-32 computation. Depending + * on the message buffer, the hardware-accelerated or software implementation + * is used. Note that the message buffer is aligned to improve fetch + * operations of VECTOR LOAD MULTIPLE instructions. + */ +#define DEFINE_CRC32_VX(___fname, ___crc32_vx, ___crc32_sw) \ + u32 ___fname(u32 crc, const u8 *data, size_t datalen) \ + { \ + unsigned long prealign, aligned, remaining; \ + DECLARE_KERNEL_FPU_ONSTACK16(vxstate); \ + \ + if (datalen < VX_MIN_LEN + VX_ALIGN_MASK || \ + !static_branch_likely(&have_vxrs)) \ + return ___crc32_sw(crc, data, datalen); \ + \ + if ((unsigned long)data & VX_ALIGN_MASK) { \ + prealign = VX_ALIGNMENT - \ + ((unsigned long)data & VX_ALIGN_MASK); \ + datalen -= prealign; \ + crc = ___crc32_sw(crc, data, prealign); \ + data = (void *)((unsigned long)data + prealign); \ + } \ + \ + aligned = datalen & ~VX_ALIGN_MASK; \ + remaining = datalen & VX_ALIGN_MASK; \ + \ + kernel_fpu_begin(&vxstate, KERNEL_VXR_LOW); \ + crc = ___crc32_vx(crc, data, aligned); \ + kernel_fpu_end(&vxstate, KERNEL_VXR_LOW); \ + \ + if (remaining) \ + crc = ___crc32_sw(crc, data + aligned, remaining); \ + \ + return crc; \ + } \ + EXPORT_SYMBOL(___fname); + +DEFINE_CRC32_VX(crc32_le_arch, crc32_le_vgfm_16, crc32_le_base) +DEFINE_CRC32_VX(crc32_be_arch, crc32_be_vgfm_16, crc32_be_base) +DEFINE_CRC32_VX(crc32c_le_arch, crc32c_le_vgfm_16, crc32c_le_base) + +static int __init crc32_s390_init(void) +{ + if (cpu_have_feature(S390_CPU_FEATURE_VXRS)) + static_branch_enable(&have_vxrs); + return 0; +} +arch_initcall(crc32_s390_init); + +static void __exit crc32_s390_exit(void) +{ +} +module_exit(crc32_s390_exit); + +u32 crc32_optimizations(void) +{ + if (static_key_enabled(&have_vxrs)) + return CRC32_LE_OPTIMIZATION | + CRC32_BE_OPTIMIZATION | + CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_AUTHOR("Hendrik Brueckner "); +MODULE_DESCRIPTION("CRC-32 algorithms using z/Architecture Vector Extension Facility"); +MODULE_LICENSE("GPL"); diff --git a/arch/s390/crypto/crc32-vx.h b/arch/s390/lib/crc32-vx.h similarity index 100% rename from arch/s390/crypto/crc32-vx.h rename to arch/s390/lib/crc32-vx.h diff --git a/arch/s390/crypto/crc32be-vx.c b/arch/s390/lib/crc32be-vx.c similarity index 100% rename from arch/s390/crypto/crc32be-vx.c rename to arch/s390/lib/crc32be-vx.c diff --git a/arch/s390/crypto/crc32le-vx.c b/arch/s390/lib/crc32le-vx.c similarity index 100% rename from arch/s390/crypto/crc32le-vx.c rename to arch/s390/lib/crc32le-vx.c diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S index 08f60a42b9a6..d026debf250c 100644 --- a/arch/s390/lib/mem.S +++ b/arch/s390/lib/mem.S @@ -34,8 +34,7 @@ SYM_FUNC_START(__memmove) la %r3,256(%r3) brctg %r0,.Lmemmove_forward_loop .Lmemmove_forward_remainder: - larl %r5,.Lmemmove_mvc - ex %r4,0(%r5) + exrl %r4,.Lmemmove_mvc .Lmemmove_exit: BR_EX %r14 .Lmemmove_reverse: @@ -83,8 +82,7 @@ SYM_FUNC_START(__memset) la %r1,256(%r1) brctg %r3,.Lmemset_clear_loop .Lmemset_clear_remainder: - larl %r3,.Lmemset_xc - ex %r4,0(%r3) + exrl %r4,.Lmemset_xc .Lmemset_exit: BR_EX %r14 .Lmemset_fill: @@ -102,8 +100,7 @@ SYM_FUNC_START(__memset) brctg %r5,.Lmemset_fill_loop .Lmemset_fill_remainder: stc %r3,0(%r1) - larl %r5,.Lmemset_mvc - ex %r4,0(%r5) + exrl %r4,.Lmemset_mvc BR_EX %r14 .Lmemset_fill_exit: stc %r3,0(%r1) @@ -132,8 +129,7 @@ SYM_FUNC_START(__memcpy) lgr %r1,%r2 jnz .Lmemcpy_loop .Lmemcpy_remainder: - larl %r5,.Lmemcpy_mvc - ex %r4,0(%r5) + exrl %r4,.Lmemcpy_mvc .Lmemcpy_exit: BR_EX %r14 .Lmemcpy_loop: @@ -175,8 +171,7 @@ SYM_FUNC_START(__memset\bits) brctg %r5,.L__memset_loop\bits .L__memset_remainder\bits: \insn %r3,0(%r1) - larl %r5,.L__memset_mvc\bits - ex %r4,0(%r5) + exrl %r4,.L__memset_mvc\bits BR_EX %r14 .L__memset_store\bits: \insn %r3,0(%r2) diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index c7c269d5c491..f977b7c37efc 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -31,51 +31,6 @@ void debug_user_asce(int exit) } #endif /*CONFIG_DEBUG_ENTRY */ -static unsigned long raw_copy_from_user_key(void *to, const void __user *from, - unsigned long size, unsigned long key) -{ - unsigned long rem; - union oac spec = { - .oac2.key = key, - .oac2.as = PSW_BITS_AS_SECONDARY, - .oac2.k = 1, - .oac2.a = 1, - }; - - asm volatile( - " lr 0,%[spec]\n" - "0: mvcos 0(%[to]),0(%[from]),%[size]\n" - "1: jz 5f\n" - " algr %[size],%[val]\n" - " slgr %[from],%[val]\n" - " slgr %[to],%[val]\n" - " j 0b\n" - "2: la %[rem],4095(%[from])\n" /* rem = from + 4095 */ - " nr %[rem],%[val]\n" /* rem = (from + 4095) & -4096 */ - " slgr %[rem],%[from]\n" - " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ - " jnh 6f\n" - "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" - "4: slgr %[size],%[rem]\n" - " j 6f\n" - "5: slgr %[size],%[size]\n" - "6:\n" - EX_TABLE(0b, 2b) - EX_TABLE(1b, 2b) - EX_TABLE(3b, 6b) - EX_TABLE(4b, 6b) - : [size] "+&a" (size), [from] "+&a" (from), [to] "+&a" (to), [rem] "=&a" (rem) - : [val] "a" (-4096UL), [spec] "d" (spec.val) - : "cc", "memory", "0"); - return size; -} - -unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) -{ - return raw_copy_from_user_key(to, from, n, 0); -} -EXPORT_SYMBOL(raw_copy_from_user); - unsigned long _copy_from_user_key(void *to, const void __user *from, unsigned long n, unsigned long key) { @@ -93,51 +48,6 @@ unsigned long _copy_from_user_key(void *to, const void __user *from, } EXPORT_SYMBOL(_copy_from_user_key); -static unsigned long raw_copy_to_user_key(void __user *to, const void *from, - unsigned long size, unsigned long key) -{ - unsigned long rem; - union oac spec = { - .oac1.key = key, - .oac1.as = PSW_BITS_AS_SECONDARY, - .oac1.k = 1, - .oac1.a = 1, - }; - - asm volatile( - " lr 0,%[spec]\n" - "0: mvcos 0(%[to]),0(%[from]),%[size]\n" - "1: jz 5f\n" - " algr %[size],%[val]\n" - " slgr %[to],%[val]\n" - " slgr %[from],%[val]\n" - " j 0b\n" - "2: la %[rem],4095(%[to])\n" /* rem = to + 4095 */ - " nr %[rem],%[val]\n" /* rem = (to + 4095) & -4096 */ - " slgr %[rem],%[to]\n" - " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ - " jnh 6f\n" - "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" - "4: slgr %[size],%[rem]\n" - " j 6f\n" - "5: slgr %[size],%[size]\n" - "6:\n" - EX_TABLE(0b, 2b) - EX_TABLE(1b, 2b) - EX_TABLE(3b, 6b) - EX_TABLE(4b, 6b) - : [size] "+&a" (size), [to] "+&a" (to), [from] "+&a" (from), [rem] "=&a" (rem) - : [val] "a" (-4096UL), [spec] "d" (spec.val) - : "cc", "memory", "0"); - return size; -} - -unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n) -{ - return raw_copy_to_user_key(to, from, n, 0); -} -EXPORT_SYMBOL(raw_copy_to_user); - unsigned long _copy_to_user_key(void __user *to, const void *from, unsigned long n, unsigned long key) { diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c index fb924a8041dc..ce7bcf7c0032 100644 --- a/arch/s390/lib/xor.c +++ b/arch/s390/lib/xor.c @@ -15,7 +15,6 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2) { asm volatile( - " larl 1,2f\n" " aghi %0,-1\n" " jm 3f\n" " srlg 0,%0,8\n" @@ -25,12 +24,12 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1, " la %1,256(%1)\n" " la %2,256(%2)\n" " brctg 0,0b\n" - "1: ex %0,0(1)\n" + "1: exrl %0,2f\n" " j 3f\n" "2: xc 0(1,%1),0(%2)\n" "3:\n" : : "d" (bytes), "a" (p1), "a" (p2) - : "0", "1", "cc", "memory"); + : "0", "cc", "memory"); } static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, @@ -38,9 +37,8 @@ static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p3) { asm volatile( - " larl 1,2f\n" " aghi %0,-1\n" - " jm 3f\n" + " jm 4f\n" " srlg 0,%0,8\n" " ltgr 0,0\n" " jz 1f\n" @@ -50,14 +48,14 @@ static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, " la %2,256(%2)\n" " la %3,256(%3)\n" " brctg 0,0b\n" - "1: ex %0,0(1)\n" - " ex %0,6(1)\n" - " j 3f\n" + "1: exrl %0,2f\n" + " exrl %0,3f\n" + " j 4f\n" "2: xc 0(1,%1),0(%2)\n" - " xc 0(1,%1),0(%3)\n" - "3:\n" + "3: xc 0(1,%1),0(%3)\n" + "4:\n" : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3) - : : "0", "1", "cc", "memory"); + : : "0", "cc", "memory"); } static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1, @@ -66,9 +64,8 @@ static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p4) { asm volatile( - " larl 1,2f\n" " aghi %0,-1\n" - " jm 3f\n" + " jm 5f\n" " srlg 0,%0,8\n" " ltgr 0,0\n" " jz 1f\n" @@ -80,16 +77,16 @@ static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1, " la %3,256(%3)\n" " la %4,256(%4)\n" " brctg 0,0b\n" - "1: ex %0,0(1)\n" - " ex %0,6(1)\n" - " ex %0,12(1)\n" - " j 3f\n" + "1: exrl %0,2f\n" + " exrl %0,3f\n" + " exrl %0,4f\n" + " j 5f\n" "2: xc 0(1,%1),0(%2)\n" - " xc 0(1,%1),0(%3)\n" - " xc 0(1,%1),0(%4)\n" - "3:\n" + "3: xc 0(1,%1),0(%3)\n" + "4: xc 0(1,%1),0(%4)\n" + "5:\n" : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4) - : : "0", "1", "cc", "memory"); + : : "0", "cc", "memory"); } static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, @@ -101,7 +98,7 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, asm volatile( " larl 1,2f\n" " aghi %0,-1\n" - " jm 3f\n" + " jm 6f\n" " srlg 0,%0,8\n" " ltgr 0,0\n" " jz 1f\n" @@ -115,19 +112,19 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, " la %4,256(%4)\n" " la %5,256(%5)\n" " brctg 0,0b\n" - "1: ex %0,0(1)\n" - " ex %0,6(1)\n" - " ex %0,12(1)\n" - " ex %0,18(1)\n" - " j 3f\n" + "1: exrl %0,2f\n" + " exrl %0,3f\n" + " exrl %0,4f\n" + " exrl %0,5f\n" + " j 6f\n" "2: xc 0(1,%1),0(%2)\n" - " xc 0(1,%1),0(%3)\n" - " xc 0(1,%1),0(%4)\n" - " xc 0(1,%1),0(%5)\n" - "3:\n" + "3: xc 0(1,%1),0(%3)\n" + "4: xc 0(1,%1),0(%4)\n" + "5: xc 0(1,%1),0(%5)\n" + "6:\n" : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4), "+a" (p5) - : : "0", "1", "cc", "memory"); + : : "0", "cc", "memory"); } struct xor_block_template xor_block_xc = { diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index d01724a715d0..39f44b6256e0 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -204,7 +204,7 @@ static void cmm_set_timer(void) del_timer(&cmm_timer); return; } - mod_timer(&cmm_timer, jiffies + msecs_to_jiffies(cmm_timeout_seconds * MSEC_PER_SEC)); + mod_timer(&cmm_timer, jiffies + secs_to_jiffies(cmm_timeout_seconds)); } static void cmm_timer_fn(struct timer_list *unused) @@ -332,7 +332,7 @@ static int cmm_timeout_handler(const struct ctl_table *ctl, int write, return 0; } -static struct ctl_table cmm_table[] = { +static const struct ctl_table cmm_table[] = { { .procname = "cmm_pages", .mode = 0644, diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c index 0a0738a473af..a046be1715cf 100644 --- a/arch/s390/mm/extable.c +++ b/arch/s390/mm/extable.c @@ -7,6 +7,7 @@ #include #include #include +#include const struct exception_table_entry *s390_search_extables(unsigned long addr) { @@ -26,7 +27,7 @@ static bool ex_handler_fixup(const struct exception_table_entry *ex, struct pt_r return true; } -static bool ex_handler_ua_store(const struct exception_table_entry *ex, struct pt_regs *regs) +static bool ex_handler_ua_fault(const struct exception_table_entry *ex, struct pt_regs *regs) { unsigned int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data); @@ -35,18 +36,6 @@ static bool ex_handler_ua_store(const struct exception_table_entry *ex, struct p return true; } -static bool ex_handler_ua_load_mem(const struct exception_table_entry *ex, struct pt_regs *regs) -{ - unsigned int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data); - unsigned int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data); - size_t len = FIELD_GET(EX_DATA_LEN, ex->data); - - regs->gprs[reg_err] = -EFAULT; - memset((void *)regs->gprs[reg_addr], 0, len); - regs->psw.addr = extable_fixup(ex); - return true; -} - static bool ex_handler_ua_load_reg(const struct exception_table_entry *ex, bool pair, struct pt_regs *regs) { @@ -77,6 +66,13 @@ static bool ex_handler_zeropad(const struct exception_table_entry *ex, struct pt return true; } +static bool ex_handler_fpc(const struct exception_table_entry *ex, struct pt_regs *regs) +{ + fpu_sfpc(0); + regs->psw.addr = extable_fixup(ex); + return true; +} + bool fixup_exception(struct pt_regs *regs) { const struct exception_table_entry *ex; @@ -89,16 +85,16 @@ bool fixup_exception(struct pt_regs *regs) return ex_handler_fixup(ex, regs); case EX_TYPE_BPF: return ex_handler_bpf(ex, regs); - case EX_TYPE_UA_STORE: - return ex_handler_ua_store(ex, regs); - case EX_TYPE_UA_LOAD_MEM: - return ex_handler_ua_load_mem(ex, regs); + case EX_TYPE_UA_FAULT: + return ex_handler_ua_fault(ex, regs); case EX_TYPE_UA_LOAD_REG: return ex_handler_ua_load_reg(ex, false, regs); case EX_TYPE_UA_LOAD_REGPAIR: return ex_handler_ua_load_reg(ex, true, regs); case EX_TYPE_ZEROPAD: return ex_handler_zeropad(ex, regs); + case EX_TYPE_FPC: + return ex_handler_fpc(ex, regs); } panic("invalid exception table entry"); } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 7a96623a9d2e..f2298f7a3f21 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -56,6 +56,15 @@ pgd_t invalid_pg_dir[PTRS_PER_PGD] __section(".bss..invalid_pg_dir"); struct ctlreg __bootdata_preserved(s390_invalid_asce); +unsigned long __bootdata_preserved(page_noexec_mask); +EXPORT_SYMBOL(page_noexec_mask); + +unsigned long __bootdata_preserved(segment_noexec_mask); +EXPORT_SYMBOL(segment_noexec_mask); + +unsigned long __bootdata_preserved(region_noexec_mask); +EXPORT_SYMBOL(region_noexec_mask); + unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(zero_page_mask); diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 28a18c42ba99..44426e0f2944 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 33f3504be90b..76f376876e0d 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -196,22 +196,28 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) } } -static const pgprot_t protection_map[16] = { - [VM_NONE] = PAGE_NONE, - [VM_READ] = PAGE_RO, - [VM_WRITE] = PAGE_RO, - [VM_WRITE | VM_READ] = PAGE_RO, - [VM_EXEC] = PAGE_RX, - [VM_EXEC | VM_READ] = PAGE_RX, - [VM_EXEC | VM_WRITE] = PAGE_RX, - [VM_EXEC | VM_WRITE | VM_READ] = PAGE_RX, - [VM_SHARED] = PAGE_NONE, - [VM_SHARED | VM_READ] = PAGE_RO, - [VM_SHARED | VM_WRITE] = PAGE_RW, - [VM_SHARED | VM_WRITE | VM_READ] = PAGE_RW, - [VM_SHARED | VM_EXEC] = PAGE_RX, - [VM_SHARED | VM_EXEC | VM_READ] = PAGE_RX, - [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_RWX, - [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_RWX -}; +static pgprot_t protection_map[16] __ro_after_init; + +void __init setup_protection_map(void) +{ + pgprot_t *pm = protection_map; + + pm[VM_NONE] = PAGE_NONE; + pm[VM_READ] = PAGE_RO; + pm[VM_WRITE] = PAGE_RO; + pm[VM_WRITE | VM_READ] = PAGE_RO; + pm[VM_EXEC] = PAGE_RX; + pm[VM_EXEC | VM_READ] = PAGE_RX; + pm[VM_EXEC | VM_WRITE] = PAGE_RX; + pm[VM_EXEC | VM_WRITE | VM_READ] = PAGE_RX; + pm[VM_SHARED] = PAGE_NONE; + pm[VM_SHARED | VM_READ] = PAGE_RO; + pm[VM_SHARED | VM_WRITE] = PAGE_RW; + pm[VM_SHARED | VM_WRITE | VM_READ] = PAGE_RW; + pm[VM_SHARED | VM_EXEC] = PAGE_RX; + pm[VM_SHARED | VM_EXEC | VM_READ] = PAGE_RX; + pm[VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_RWX; + pm[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_RWX; +} + DECLARE_VM_GET_PAGE_PROT diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 8f56a21a077f..eae97fb61712 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -109,8 +109,6 @@ static int walk_pte_level(pmd_t *pmdp, unsigned long addr, unsigned long end, } else if (flags & SET_MEMORY_DEF) { new = __pte(pte_val(new) & PAGE_MASK); new = set_pte_bit(new, PAGE_KERNEL); - if (!MACHINE_HAS_NX) - new = clear_pte_bit(new, __pgprot(_PAGE_NOEXEC)); } pgt_set((unsigned long *)ptep, pte_val(new), addr, CRDTE_DTT_PAGE); ptep++; @@ -167,8 +165,6 @@ static void modify_pmd_page(pmd_t *pmdp, unsigned long addr, } else if (flags & SET_MEMORY_DEF) { new = __pmd(pmd_val(new) & PMD_MASK); new = set_pmd_bit(new, SEGMENT_KERNEL); - if (!MACHINE_HAS_NX) - new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_NOEXEC)); } pgt_set((unsigned long *)pmdp, pmd_val(new), addr, CRDTE_DTT_SEGMENT); } @@ -256,8 +252,6 @@ static void modify_pud_page(pud_t *pudp, unsigned long addr, } else if (flags & SET_MEMORY_DEF) { new = __pud(pud_val(new) & PUD_MASK); new = set_pud_bit(new, REGION3_KERNEL); - if (!MACHINE_HAS_NX) - new = clear_pud_bit(new, __pgprot(_REGION_ENTRY_NOEXEC)); } pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3); } diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 58696a0c4e4a..cd2fef79ad2c 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -21,7 +21,7 @@ int page_table_allocate_pgste = 0; EXPORT_SYMBOL(page_table_allocate_pgste); -static struct ctl_table page_table_sysctl[] = { +static const struct ctl_table page_table_sysctl[] = { { .procname = "allocate_pgste", .data = &page_table_allocate_pgste, @@ -88,12 +88,14 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end) if (unlikely(!p4d)) goto err_p4d; crst_table_init(p4d, _REGION2_ENTRY_EMPTY); + pagetable_p4d_ctor(virt_to_ptdesc(p4d)); } if (end > _REGION1_SIZE) { pgd = crst_table_alloc(mm); if (unlikely(!pgd)) goto err_pgd; crst_table_init(pgd, _REGION1_ENTRY_EMPTY); + pagetable_pgd_ctor(virt_to_ptdesc(pgd)); } spin_lock_bh(&mm->page_table_lock); @@ -130,6 +132,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end) return 0; err_pgd: + pagetable_dtor(virt_to_ptdesc(p4d)); crst_table_free(mm, p4d); err_p4d: return -ENOMEM; @@ -180,30 +183,11 @@ unsigned long *page_table_alloc(struct mm_struct *mm) return table; } -static void pagetable_pte_dtor_free(struct ptdesc *ptdesc) -{ - pagetable_pte_dtor(ptdesc); - pagetable_free(ptdesc); -} - void page_table_free(struct mm_struct *mm, unsigned long *table) { struct ptdesc *ptdesc = virt_to_ptdesc(table); - pagetable_pte_dtor_free(ptdesc); -} - -void __tlb_remove_table(void *table) -{ - struct ptdesc *ptdesc = virt_to_ptdesc(table); - struct page *page = ptdesc_page(ptdesc); - - if (compound_order(page) == CRST_ALLOC_ORDER) { - /* pmd, pud, or p4d */ - pagetable_free(ptdesc); - return; - } - pagetable_pte_dtor_free(ptdesc); + pagetable_dtor_free(ptdesc); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -211,7 +195,7 @@ static void pte_free_now(struct rcu_head *head) { struct ptdesc *ptdesc = container_of(head, struct ptdesc, pt_rcu_head); - pagetable_pte_dtor_free(ptdesc); + pagetable_dtor_free(ptdesc); } void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index cea5dba80468..f05e62e037c2 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -360,8 +360,6 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pgste_t pgste; struct mm_struct *mm = vma->vm_mm; - if (!MACHINE_HAS_NX) - pte = clear_pte_bit(pte, __pgprot(_PAGE_NOEXEC)); if (mm_has_pgste(mm)) { pgste = pgste_get(ptep); pgste_set_key(ptep, pgste, pte, mm); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 665b8228afeb..8ead999e340b 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -171,9 +171,6 @@ static int __ref modify_pte_table(pmd_t *pmd, unsigned long addr, pte_t *pte; prot = pgprot_val(PAGE_KERNEL); - if (!MACHINE_HAS_NX) - prot &= ~_PAGE_NOEXEC; - pte = pte_offset_kernel(pmd, addr); for (; addr < end; addr += PAGE_SIZE, pte++) { if (!add) { @@ -230,9 +227,6 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr, pte_t *pte; prot = pgprot_val(SEGMENT_KERNEL); - if (!MACHINE_HAS_NX) - prot &= ~_SEGMENT_ENTRY_NOEXEC; - pmd = pmd_offset(pud, addr); for (; addr < end; addr = next, pmd++) { next = pmd_addr_end(addr, end); @@ -324,8 +318,6 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, pmd_t *pmd; prot = pgprot_val(REGION3_KERNEL); - if (!MACHINE_HAS_NX) - prot &= ~_REGION_ENTRY_NOEXEC; pud = pud_offset(p4d, addr); for (; addr < end; addr = next, pud++) { next = pud_addr_end(addr, end); @@ -670,7 +662,7 @@ void __init vmem_map_init(void) if (!static_key_enabled(&cpu_has_bear)) set_memory_x(0, 1); if (debug_pagealloc_enabled()) - __set_memory_4k(__va(0), __va(0) + ident_map_size); + __set_memory_4k(__va(0), absolute_pointer(__va(0)) + ident_map_size); pr_info("Write protected kernel read-only data: %luk\n", (unsigned long)(__end_rodata - _stext) >> 10); } diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index 2c21f0394c9a..df73c5182990 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -5,6 +5,6 @@ obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_clp.o \ pci_event.o pci_debug.o pci_insn.o pci_mmio.o \ - pci_bus.o pci_kvm_hook.o + pci_bus.o pci_kvm_hook.o pci_report.o obj-$(CONFIG_PCI_IOV) += pci_iov.o obj-$(CONFIG_SYSFS) += pci_sysfs.o diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index d5ace00d10f0..857afbc4828f 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -171,7 +171,6 @@ void zpci_bus_scan_busses(void) static bool zpci_bus_is_multifunction_root(struct zpci_dev *zdev) { return !s390_pci_no_rid && zdev->rid_available && - zpci_is_device_configured(zdev) && !zdev->vfn; } diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 7f7b732b3f3e..7bd7721c1239 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -16,6 +16,7 @@ #include #include "pci_bus.h" +#include "pci_report.h" /* Content Code Description for PCI Function Error */ struct zpci_ccdf_err { @@ -169,6 +170,8 @@ static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev, static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) { pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + struct zpci_dev *zdev = to_zpci(pdev); + char *status_str = "success"; struct pci_driver *driver; /* @@ -186,29 +189,37 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) if (is_passed_through(pdev)) { pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n", pci_name(pdev)); + status_str = "failed (pass-through)"; goto out_unlock; } driver = to_pci_driver(pdev->dev.driver); if (!is_driver_supported(driver)) { - if (!driver) + if (!driver) { pr_info("%s: Cannot be recovered because no driver is bound to the device\n", pci_name(pdev)); - else + status_str = "failed (no driver)"; + } else { pr_info("%s: The %s driver bound to the device does not support error recovery\n", pci_name(pdev), driver->name); + status_str = "failed (no driver support)"; + } goto out_unlock; } ers_res = zpci_event_notify_error_detected(pdev, driver); - if (ers_result_indicates_abort(ers_res)) + if (ers_result_indicates_abort(ers_res)) { + status_str = "failed (abort on detection)"; goto out_unlock; + } if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) { ers_res = zpci_event_do_error_state_clear(pdev, driver); - if (ers_result_indicates_abort(ers_res)) + if (ers_result_indicates_abort(ers_res)) { + status_str = "failed (abort on MMIO enable)"; goto out_unlock; + } } if (ers_res == PCI_ERS_RESULT_NEED_RESET) @@ -217,6 +228,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) if (ers_res != PCI_ERS_RESULT_RECOVERED) { pr_err("%s: Automatic recovery failed; operator intervention is required\n", pci_name(pdev)); + status_str = "failed (driver can't recover)"; goto out_unlock; } @@ -225,6 +237,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) driver->err_handler->resume(pdev); out_unlock: pci_dev_unlock(pdev); + zpci_report_status(zdev, "recovery", status_str); return ers_res; } diff --git a/arch/s390/pci/pci_report.c b/arch/s390/pci/pci_report.c new file mode 100644 index 000000000000..1b494e5ecc4d --- /dev/null +++ b/arch/s390/pci/pci_report.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 2024 + * + * Author(s): + * Niklas Schnelle + * + */ + +#define KMSG_COMPONENT "zpci" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include +#include +#include + +#include +#include +#include + +#include "pci_report.h" + +#define ZPCI_ERR_LOG_ID_KERNEL_REPORT 0x4714 + +struct zpci_report_error_data { + u64 timestamp; + u64 err_log_id; + char log_data[]; +} __packed; + +#define ZPCI_REPORT_SIZE (PAGE_SIZE - sizeof(struct err_notify_sccb)) +#define ZPCI_REPORT_DATA_SIZE (ZPCI_REPORT_SIZE - sizeof(struct zpci_report_error_data)) + +struct zpci_report_error { + struct zpci_report_error_header header; + struct zpci_report_error_data data; +} __packed; + +static const char *zpci_state_str(pci_channel_state_t state) +{ + switch (state) { + case pci_channel_io_normal: + return "normal"; + case pci_channel_io_frozen: + return "frozen"; + case pci_channel_io_perm_failure: + return "permanent-failure"; + default: + return "invalid"; + }; +} + +static int debug_log_header_fn(debug_info_t *id, struct debug_view *view, + int area, debug_entry_t *entry, char *out_buf, + size_t out_buf_size) +{ + unsigned long sec, usec; + unsigned int level; + char *except_str; + int rc = 0; + + level = entry->level; + sec = entry->clock; + usec = do_div(sec, USEC_PER_SEC); + + if (entry->exception) + except_str = "*"; + else + except_str = "-"; + rc += scnprintf(out_buf, out_buf_size, "%011ld:%06lu %1u %1s %04u ", + sec, usec, level, except_str, + entry->cpu); + return rc; +} + +static int debug_prolog_header(debug_info_t *id, struct debug_view *view, + char *out_buf, size_t out_buf_size) +{ + return scnprintf(out_buf, out_buf_size, "sec:usec level except cpu msg\n"); +} + +static struct debug_view debug_log_view = { + "pci_msg_log", + &debug_prolog_header, + &debug_log_header_fn, + &debug_sprintf_format_fn, + NULL, + NULL +}; + +/** + * zpci_report_status - Report the status of operations on a PCI device + * @zdev: The PCI device for which to report status + * @operation: A string representing the operation reported + * @status: A string representing the status of the operation + * + * This function creates a human readable report about an operation such as + * PCI device recovery and forwards this to the platform using the SCLP Write + * Event Data mechanism. Besides the operation and status strings the report + * also contains additional information about the device deemed useful for + * debug such as the currently bound device driver, if any, and error state. + * Additionally a string representation of pci_debug_msg_id, or as much as fits, + * is also included. + * + * Return: 0 on success an error code < 0 otherwise. + */ +int zpci_report_status(struct zpci_dev *zdev, const char *operation, const char *status) +{ + struct zpci_report_error *report; + struct pci_driver *driver = NULL; + struct pci_dev *pdev = NULL; + char *buf, *end; + int ret; + + if (!zdev || !zdev->zbus) + return -ENODEV; + + /* Protected virtualization hosts get nothing from us */ + if (prot_virt_guest) + return -ENODATA; + + report = (void *)get_zeroed_page(GFP_KERNEL); + if (!report) + return -ENOMEM; + if (zdev->zbus->bus) + pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + if (pdev) + driver = to_pci_driver(pdev->dev.driver); + + buf = report->data.log_data; + end = report->data.log_data + ZPCI_REPORT_DATA_SIZE; + buf += scnprintf(buf, end - buf, "report: %s\n", operation); + buf += scnprintf(buf, end - buf, "status: %s\n", status); + buf += scnprintf(buf, end - buf, "state: %s\n", + (pdev) ? zpci_state_str(pdev->error_state) : "n/a"); + buf += scnprintf(buf, end - buf, "driver: %s\n", (driver) ? driver->name : "n/a"); + ret = debug_dump(pci_debug_msg_id, &debug_log_view, buf, end - buf, true); + if (ret < 0) + pr_err("Reading PCI debug messages failed with code %d\n", ret); + else + buf += ret; + + report->header.version = 1; + report->header.action = SCLP_ERRNOTIFY_AQ_INFO_LOG; + report->header.length = buf - (char *)&report->data; + report->data.timestamp = ktime_get_clocktai_seconds(); + report->data.err_log_id = ZPCI_ERR_LOG_ID_KERNEL_REPORT; + + ret = sclp_pci_report(&report->header, zdev->fh, zdev->fid); + if (ret) + pr_err("Reporting PCI status failed with code %d\n", ret); + else + pr_info("Reported PCI device status\n"); + + free_page((unsigned long)report); + + return ret; +} diff --git a/arch/s390/pci/pci_report.h b/arch/s390/pci/pci_report.h new file mode 100644 index 000000000000..e08003d51a97 --- /dev/null +++ b/arch/s390/pci/pci_report.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 2024 + * + * Author(s): + * Niklas Schnelle + * + */ +#ifndef __S390_PCI_REPORT_H +#define __S390_PCI_REPORT_H + +struct zpci_dev; + +int zpci_report_status(struct zpci_dev *zdev, const char *operation, const char *status); + +#endif /* __S390_PCI_REPORT_H */ diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index 5f46ad58dcd1..2de1ea6c3a8c 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -135,7 +135,7 @@ out: static DEVICE_ATTR_WO(recover); static ssize_t util_string_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -145,10 +145,10 @@ static ssize_t util_string_read(struct file *filp, struct kobject *kobj, return memory_read_from_buffer(buf, count, &off, zdev->util_str, sizeof(zdev->util_str)); } -static BIN_ATTR_RO(util_string, CLP_UTIL_STR_LEN); +static const BIN_ATTR_RO(util_string, CLP_UTIL_STR_LEN); static ssize_t report_error_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct zpci_report_error_header *report = (void *) buf; @@ -164,7 +164,7 @@ static ssize_t report_error_write(struct file *filp, struct kobject *kobj, return ret ? ret : count; } -static BIN_ATTR(report_error, S_IWUSR, NULL, report_error_write, PAGE_SIZE); +static const BIN_ATTR(report_error, S_IWUSR, NULL, report_error_write, PAGE_SIZE); static ssize_t uid_is_unique_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -203,7 +203,7 @@ const struct attribute_group zpci_ident_attr_group = { .is_visible = zpci_index_is_visible, }; -static struct bin_attribute *zpci_bin_attrs[] = { +static const struct bin_attribute *const zpci_bin_attrs[] = { &bin_attr_util_string, &bin_attr_report_error, NULL, @@ -227,7 +227,7 @@ static struct attribute *zpci_dev_attrs[] = { const struct attribute_group zpci_attr_group = { .attrs = zpci_dev_attrs, - .bin_attrs = zpci_bin_attrs, + .bin_attrs_new = zpci_bin_attrs, }; static struct attribute *pfip_attrs[] = { diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile index 24eccaa29337..bdcf2a3b6c41 100644 --- a/arch/s390/purgatory/Makefile +++ b/arch/s390/purgatory/Makefile @@ -13,7 +13,7 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE $(call if_changed_rule,as_o_S) -KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes +KBUILD_CFLAGS := -std=gnu11 -fno-strict-aliasing -Wall -Wstrict-prototypes KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c index a1bc02b29c81..7d76c417f83f 100644 --- a/arch/s390/tools/gen_opcode_table.c +++ b/arch/s390/tools/gen_opcode_table.c @@ -201,6 +201,17 @@ static int cmp_long_insn(const void *a, const void *b) return strcmp(((struct insn *)a)->name, ((struct insn *)b)->name); } +static void print_insn_name(const char *name) +{ + size_t i, len; + + len = strlen(name); + printf("{"); + for (i = 0; i < len; i++) + printf(" \'%c\',", name[i]); + printf(" }"); +} + static void print_long_insn(struct gen_opcode *desc) { struct insn *insn; @@ -223,7 +234,9 @@ static void print_long_insn(struct gen_opcode *desc) insn = &desc->insn[i]; if (insn->name_len < 6) continue; - printf("\t[LONG_INSN_%s] = \"%s\", \\\n", insn->upper, insn->name); + printf("\t[LONG_INSN_%s] = ", insn->upper); + print_insn_name(insn->name); + printf(", \\\n"); } printf("}\n\n"); } @@ -236,11 +249,13 @@ static void print_opcode(struct insn *insn, int nr) if (insn->type->byte != 0) opcode += 2; printf("\t[%4d] = { .opfrag = 0x%s, .format = INSTR_%s, ", nr, opcode, insn->format); - if (insn->name_len < 6) - printf(".name = \"%s\" ", insn->name); - else - printf(".offset = LONG_INSN_%s ", insn->upper); - printf("}, \\\n"); + if (insn->name_len < 6) { + printf(".name = "); + print_insn_name(insn->name); + } else { + printf(".offset = LONG_INSN_%s", insn->upper); + } + printf(" }, \\\n"); } static void add_to_group(struct gen_opcode *desc, struct insn *insn, int offset) diff --git a/arch/sh/Kbuild b/arch/sh/Kbuild index 056efec72c2a..0da6c6d6821a 100644 --- a/arch/sh/Kbuild +++ b/arch/sh/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y += kernel/ mm/ boards/ obj-$(CONFIG_SH_FPU_EMU) += math-emu/ -obj-$(CONFIG_USE_BUILTIN_DTB) += boot/dts/ obj-$(CONFIG_HD6446X_SERIES) += cchips/hd6446x/ diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 04ff5fb9242e..89185af7bcc9 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -648,10 +648,11 @@ endmenu menu "Boot options" -config USE_BUILTIN_DTB +config BUILTIN_DTB bool "Use builtin DTB" default n depends on SH_DEVICE_TREE + select GENERIC_BUILTIN_DTB help Link a device tree blob for particular hardware into the kernel, suppressing use of the DTB pointer provided by the bootloader. @@ -659,10 +660,10 @@ config USE_BUILTIN_DTB not capable of providing a DTB to the kernel, or for experimental hardware without stable device tree bindings. -config BUILTIN_DTB_SOURCE +config BUILTIN_DTB_NAME string "Source file for builtin DTB" default "" - depends on USE_BUILTIN_DTB + depends on BUILTIN_DTB help Base name (without suffix, relative to arch/sh/boot/dts) for the a DTS file that will be used to produce the DTB linked into the diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index 109bec4dad94..1af93be61b1f 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -80,8 +80,8 @@ config SH_7724_SOLUTION_ENGINE select SOLUTION_ENGINE depends on CPU_SUBTYPE_SH7724 select GPIOLIB - select SND_SOC_AK4642 if SND_SIMPLE_CARD select REGULATOR_FIXED_VOLTAGE if REGULATOR + imply SND_SOC_AK4642 if SND_SIMPLE_CARD help Select 7724 SolutionEngine if configuring for a Hitachi SH7724 evaluation board. @@ -259,8 +259,8 @@ config SH_ECOVEC bool "EcoVec" depends on CPU_SUBTYPE_SH7724 select GPIOLIB - select SND_SOC_DA7210 if SND_SIMPLE_CARD select REGULATOR_FIXED_VOLTAGE if REGULATOR + imply SND_SOC_DA7210 if SND_SIMPLE_CARD help Renesas "R0P7724LC0011/21RL (EcoVec)" support. diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile index 4a6dec9714a9..d109978a5eb9 100644 --- a/arch/sh/boot/dts/Makefile +++ b/arch/sh/boot/dts/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_USE_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE)) +obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME)) diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index 5d8577ab1591..96d938fdf224 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -34,7 +34,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, #define __pte_free_tlb(tlb, pte, addr) \ do { \ - pagetable_pte_dtor(page_ptdesc(pte)); \ + pagetable_dtor(page_ptdesc(pte)); \ tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index 4e6835de54cf..9022d8af9d68 100644 --- a/arch/sh/kernel/irq.c +++ b/arch/sh/kernel/irq.c @@ -43,9 +43,9 @@ int arch_show_interrupts(struct seq_file *p, int prec) { int j; - seq_printf(p, "%*s: ", prec, "NMI"); + seq_printf(p, "%*s:", prec, "NMI"); for_each_online_cpu(j) - seq_printf(p, "%10u ", per_cpu(irq_stat.__nmi_count, j)); + seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat.__nmi_count, j), 10); seq_printf(p, " Non-maskable interrupts\n"); seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index f2b6f16a46b8..039a51291002 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -249,7 +249,7 @@ void __ref sh_fdt_init(phys_addr_t dt_phys) /* Avoid calling an __init function on secondary cpus. */ if (done) return; -#ifdef CONFIG_USE_BUILTIN_DTB +#ifdef CONFIG_BUILTIN_DTB dt_virt = __dtb_start; #else dt_virt = phys_to_virt(dt_phys); @@ -323,7 +323,7 @@ void __init setup_arch(char **cmdline_p) sh_early_platform_driver_probe("earlyprintk", 1, 1); #ifdef CONFIG_OF_EARLY_FLATTREE -#ifdef CONFIG_USE_BUILTIN_DTB +#ifdef CONFIG_BUILTIN_DTB unflatten_and_copy_device_tree(); #else unflatten_device_tree(); diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 2a88b0c9e70f..289a2fecebef 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -137,10 +137,7 @@ static pmd_t * __init one_md_table_init(pud_t *pud) if (pud_none(*pud)) { pmd_t *pmd; - pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pmd) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + pmd = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); pud_populate(&init_mm, pud, pmd); BUG_ON(pmd != pmd_offset(pud, 0)); } @@ -153,10 +150,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) if (pmd_none(*pmd)) { pte_t *pte; - pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pte) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); + pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); pmd_populate_kernel(&init_mm, pmd, pte); BUG_ON(pte != pte_offset_kernel(pmd, 0)); } diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index dcfdb7f1dae9..0f88123925a4 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -110,6 +110,7 @@ config SPARC64 select HAVE_SETUP_PER_CPU_AREA select NEED_PER_CPU_EMBED_FIRST_CHUNK select NEED_PER_CPU_PAGE_FIRST_CHUNK + select ARCH_HAS_CRC32 config ARCH_PROC_KCORE_TEXT def_bool y diff --git a/arch/sparc/crypto/Kconfig b/arch/sparc/crypto/Kconfig index cfe5102b1c68..e858597de89d 100644 --- a/arch/sparc/crypto/Kconfig +++ b/arch/sparc/crypto/Kconfig @@ -16,16 +16,6 @@ config CRYPTO_DES_SPARC64 Architecture: sparc64 -config CRYPTO_CRC32C_SPARC64 - tristate "CRC32c" - depends on SPARC64 - select CRYPTO_HASH - select CRC32 - help - CRC32c CRC algorithm with the iSCSI polynomial (RFC 3385 and RFC 3720) - - Architecture: sparc64 - config CRYPTO_MD5_SPARC64 tristate "Digests: MD5" depends on SPARC64 diff --git a/arch/sparc/crypto/Makefile b/arch/sparc/crypto/Makefile index d257186c27d1..a2d7fca40cb4 100644 --- a/arch/sparc/crypto/Makefile +++ b/arch/sparc/crypto/Makefile @@ -12,8 +12,6 @@ obj-$(CONFIG_CRYPTO_AES_SPARC64) += aes-sparc64.o obj-$(CONFIG_CRYPTO_DES_SPARC64) += des-sparc64.o obj-$(CONFIG_CRYPTO_CAMELLIA_SPARC64) += camellia-sparc64.o -obj-$(CONFIG_CRYPTO_CRC32C_SPARC64) += crc32c-sparc64.o - sha1-sparc64-y := sha1_asm.o sha1_glue.o sha256-sparc64-y := sha256_asm.o sha256_glue.o sha512-sparc64-y := sha512_asm.o sha512_glue.o @@ -22,5 +20,3 @@ md5-sparc64-y := md5_asm.o md5_glue.o aes-sparc64-y := aes_asm.o aes_glue.o des-sparc64-y := des_asm.o des_glue.o camellia-sparc64-y := camellia_asm.o camellia_glue.o - -crc32c-sparc64-y := crc32c_asm.o crc32c_glue.o diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c deleted file mode 100644 index 913b9a09e885..000000000000 --- a/arch/sparc/crypto/crc32c_glue.c +++ /dev/null @@ -1,184 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* Glue code for CRC32C optimized for sparc64 crypto opcodes. - * - * This is based largely upon arch/x86/crypto/crc32c-intel.c - * - * Copyright (C) 2008 Intel Corporation - * Authors: Austin Zhang - * Kent Liu - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include - -#include - -#include -#include -#include - -#include "opcodes.h" - -/* - * Setting the seed allows arbitrary accumulators and flexible XOR policy - * If your algorithm starts with ~0, then XOR with ~0 before you set - * the seed. - */ -static int crc32c_sparc64_setkey(struct crypto_shash *hash, const u8 *key, - unsigned int keylen) -{ - u32 *mctx = crypto_shash_ctx(hash); - - if (keylen != sizeof(u32)) - return -EINVAL; - *mctx = get_unaligned_le32(key); - return 0; -} - -static int crc32c_sparc64_init(struct shash_desc *desc) -{ - u32 *mctx = crypto_shash_ctx(desc->tfm); - u32 *crcp = shash_desc_ctx(desc); - - *crcp = *mctx; - - return 0; -} - -extern void crc32c_sparc64(u32 *crcp, const u64 *data, unsigned int len); - -static u32 crc32c_compute(u32 crc, const u8 *data, unsigned int len) -{ - unsigned int n = -(uintptr_t)data & 7; - - if (n) { - /* Data isn't 8-byte aligned. Align it. */ - n = min(n, len); - crc = __crc32c_le(crc, data, n); - data += n; - len -= n; - } - n = len & ~7U; - if (n) { - crc32c_sparc64(&crc, (const u64 *)data, n); - data += n; - len -= n; - } - if (len) - crc = __crc32c_le(crc, data, len); - return crc; -} - -static int crc32c_sparc64_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - u32 *crcp = shash_desc_ctx(desc); - - *crcp = crc32c_compute(*crcp, data, len); - return 0; -} - -static int __crc32c_sparc64_finup(const u32 *crcp, const u8 *data, - unsigned int len, u8 *out) -{ - put_unaligned_le32(~crc32c_compute(*crcp, data, len), out); - return 0; -} - -static int crc32c_sparc64_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32c_sparc64_finup(shash_desc_ctx(desc), data, len, out); -} - -static int crc32c_sparc64_final(struct shash_desc *desc, u8 *out) -{ - u32 *crcp = shash_desc_ctx(desc); - - put_unaligned_le32(~*crcp, out); - return 0; -} - -static int crc32c_sparc64_digest(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32c_sparc64_finup(crypto_shash_ctx(desc->tfm), data, len, - out); -} - -static int crc32c_sparc64_cra_init(struct crypto_tfm *tfm) -{ - u32 *key = crypto_tfm_ctx(tfm); - - *key = ~0; - - return 0; -} - -#define CHKSUM_BLOCK_SIZE 1 -#define CHKSUM_DIGEST_SIZE 4 - -static struct shash_alg alg = { - .setkey = crc32c_sparc64_setkey, - .init = crc32c_sparc64_init, - .update = crc32c_sparc64_update, - .final = crc32c_sparc64_final, - .finup = crc32c_sparc64_finup, - .digest = crc32c_sparc64_digest, - .descsize = sizeof(u32), - .digestsize = CHKSUM_DIGEST_SIZE, - .base = { - .cra_name = "crc32c", - .cra_driver_name = "crc32c-sparc64", - .cra_priority = SPARC_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(u32), - .cra_module = THIS_MODULE, - .cra_init = crc32c_sparc64_cra_init, - } -}; - -static bool __init sparc64_has_crc32c_opcode(void) -{ - unsigned long cfr; - - if (!(sparc64_elf_hwcap & HWCAP_SPARC_CRYPTO)) - return false; - - __asm__ __volatile__("rd %%asr26, %0" : "=r" (cfr)); - if (!(cfr & CFR_CRC32C)) - return false; - - return true; -} - -static int __init crc32c_sparc64_mod_init(void) -{ - if (sparc64_has_crc32c_opcode()) { - pr_info("Using sparc64 crc32c opcode optimized CRC32C implementation\n"); - return crypto_register_shash(&alg); - } - pr_info("sparc64 crc32c opcode not available.\n"); - return -ENODEV; -} - -static void __exit crc32c_sparc64_mod_fini(void) -{ - crypto_unregister_shash(&alg); -} - -module_init(crc32c_sparc64_mod_init); -module_exit(crc32c_sparc64_mod_fini); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("CRC32c (Castagnoli), sparc64 crc32c opcode accelerated"); - -MODULE_ALIAS_CRYPTO("crc32c"); - -#include "crop_devid.c" diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h index 3037187482db..1a6e694418e3 100644 --- a/arch/sparc/include/asm/tlb_64.h +++ b/arch/sparc/include/asm/tlb_64.h @@ -33,6 +33,7 @@ void flush_tlb_pending(void); #define tlb_needs_table_invalidate() (false) #endif +#define __HAVE_ARCH_TLB_REMOVE_TABLE #include #endif /* _SPARC64_TLB_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 113cd9f353e3..5b464a568664 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -141,6 +141,8 @@ #define SCM_TS_OPT_ID 0x005a +#define SO_RCVPRIORITY 0x005b + #if !defined(__KERNEL__) diff --git a/arch/sparc/kernel/irq_32.c b/arch/sparc/kernel/irq_32.c index 8605dd710f3c..5210991429d5 100644 --- a/arch/sparc/kernel/irq_32.c +++ b/arch/sparc/kernel/irq_32.c @@ -199,18 +199,18 @@ int arch_show_interrupts(struct seq_file *p, int prec) int j; #ifdef CONFIG_SMP - seq_printf(p, "RES: "); + seq_printf(p, "RES:"); for_each_online_cpu(j) - seq_printf(p, "%10u ", cpu_data(j).irq_resched_count); + seq_put_decimal_ull_width(p, " ", cpu_data(j).irq_resched_count, 10); seq_printf(p, " IPI rescheduling interrupts\n"); - seq_printf(p, "CAL: "); + seq_printf(p, "CAL:"); for_each_online_cpu(j) - seq_printf(p, "%10u ", cpu_data(j).irq_call_count); + seq_put_decimal_ull_width(p, " ", cpu_data(j).irq_call_count, 10); seq_printf(p, " IPI function call interrupts\n"); #endif - seq_printf(p, "NMI: "); + seq_printf(p, "NMI:"); for_each_online_cpu(j) - seq_printf(p, "%10u ", cpu_data(j).counter); + seq_put_decimal_ull_width(p, " ", cpu_data(j).counter, 10); seq_printf(p, " Non-maskable interrupts\n"); return 0; } diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 01ee800efde3..ded463c82abd 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -145,9 +146,7 @@ static int hv_irq_version; */ static bool sun4v_cookie_only_virqs(void) { - if (hv_irq_version >= 3) - return true; - return false; + return hv_irq_version >= 3; } static void __init irq_init_hv(void) @@ -170,7 +169,7 @@ static void __init irq_init_hv(void) pr_info("SUN4V: Using IRQ API major %d, cookie only virqs %s\n", hv_irq_version, - sun4v_cookie_only_virqs() ? "enabled" : "disabled"); + str_enabled_disabled(sun4v_cookie_only_virqs())); } /* This function is for the timer interrupt.*/ @@ -304,9 +303,9 @@ int arch_show_interrupts(struct seq_file *p, int prec) { int j; - seq_printf(p, "NMI: "); + seq_printf(p, "NMI:"); for_each_online_cpu(j) - seq_printf(p, "%10u ", cpu_data(j).__nmi_count); + seq_put_decimal_ull_width(p, " ", cpu_data(j).__nmi_count, 10); seq_printf(p, " Non-maskable interrupts\n"); return 0; } diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 50a0927a84a6..ddac216a2aff 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -932,7 +932,7 @@ static void pci_bus_slot_names(struct device_node *node, struct pci_bus *bus) { const struct pci_slot_names { u32 slot_mask; - char names[0]; + char names[]; } *prop; const char *sp; int len, i; diff --git a/arch/sparc/kernel/pci_common.c b/arch/sparc/kernel/pci_common.c index 5eeec9ad6845..2576f4f31309 100644 --- a/arch/sparc/kernel/pci_common.c +++ b/arch/sparc/kernel/pci_common.c @@ -361,7 +361,7 @@ void pci_determine_mem_io_space(struct pci_pbm_info *pbm) int i, saw_mem, saw_io; int num_pbm_ranges; - /* Corresponding generic code in of_pci_get_host_bridge_resources() */ + /* Corresponds to generic devm_of_pci_get_host_bridge_resources() */ saw_mem = saw_io = 0; pbm_ranges = of_get_property(pbm->op->dev.of_node, "ranges", &i); diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c index 3df960c137f7..a67dd67f10c8 100644 --- a/arch/sparc/kernel/prom_32.c +++ b/arch/sparc/kernel/prom_32.c @@ -28,9 +28,7 @@ void * __init prom_early_alloc(unsigned long size) { void *ret; - ret = memblock_alloc(size, SMP_CACHE_BYTES); - if (!ret) - panic("%s: Failed to allocate %lu bytes\n", __func__, size); + ret = memblock_alloc_or_panic(size, SMP_CACHE_BYTES); prom_early_allocated += size; diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index 07933d75ac81..1a1a9d6b8f2e 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -419,13 +419,13 @@ struct vio_remove_node_data { u64 node; }; -static int vio_md_node_match(struct device *dev, void *arg) +static int vio_md_node_match(struct device *dev, const void *arg) { struct vio_dev *vdev = to_vio_dev(dev); - struct vio_remove_node_data *node_data; + const struct vio_remove_node_data *node_data; u64 node; - node_data = (struct vio_remove_node_data *)arg; + node_data = (const struct vio_remove_node_data *)arg; node = vio_vdev_node(node_data->hp, vdev); diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index ee5091dd67ed..5724d0f356eb 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -53,3 +53,5 @@ lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o obj-$(CONFIG_SPARC64) += iomap.o obj-$(CONFIG_SPARC32) += atomic32.o obj-$(CONFIG_SPARC64) += PeeCeeI.o +obj-$(CONFIG_CRC32_ARCH) += crc32-sparc.o +crc32-sparc-y := crc32_glue.o crc32c_asm.o diff --git a/arch/sparc/lib/crc32_glue.c b/arch/sparc/lib/crc32_glue.c new file mode 100644 index 000000000000..41076d2b1fd2 --- /dev/null +++ b/arch/sparc/lib/crc32_glue.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Glue code for CRC32C optimized for sparc64 crypto opcodes. + * + * This is based largely upon arch/x86/crypto/crc32c-intel.c + * + * Copyright (C) 2008 Intel Corporation + * Authors: Austin Zhang + * Kent Liu + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include + +static DEFINE_STATIC_KEY_FALSE(have_crc32c_opcode); + +u32 crc32_le_arch(u32 crc, const u8 *data, size_t len) +{ + return crc32_le_base(crc, data, len); +} +EXPORT_SYMBOL(crc32_le_arch); + +void crc32c_sparc64(u32 *crcp, const u64 *data, size_t len); + +u32 crc32c_le_arch(u32 crc, const u8 *data, size_t len) +{ + size_t n = -(uintptr_t)data & 7; + + if (!static_branch_likely(&have_crc32c_opcode)) + return crc32c_le_base(crc, data, len); + + if (n) { + /* Data isn't 8-byte aligned. Align it. */ + n = min(n, len); + crc = crc32c_le_base(crc, data, n); + data += n; + len -= n; + } + n = len & ~7U; + if (n) { + crc32c_sparc64(&crc, (const u64 *)data, n); + data += n; + len -= n; + } + if (len) + crc = crc32c_le_base(crc, data, len); + return crc; +} +EXPORT_SYMBOL(crc32c_le_arch); + +u32 crc32_be_arch(u32 crc, const u8 *data, size_t len) +{ + return crc32_be_base(crc, data, len); +} +EXPORT_SYMBOL(crc32_be_arch); + +static int __init crc32_sparc_init(void) +{ + unsigned long cfr; + + if (!(sparc64_elf_hwcap & HWCAP_SPARC_CRYPTO)) + return 0; + + __asm__ __volatile__("rd %%asr26, %0" : "=r" (cfr)); + if (!(cfr & CFR_CRC32C)) + return 0; + + static_branch_enable(&have_crc32c_opcode); + pr_info("Using sparc64 crc32c opcode optimized CRC32C implementation\n"); + return 0; +} +arch_initcall(crc32_sparc_init); + +static void __exit crc32_sparc_exit(void) +{ +} +module_exit(crc32_sparc_exit); + +u32 crc32_optimizations(void) +{ + if (static_key_enabled(&have_crc32c_opcode)) + return CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("CRC32c (Castagnoli), sparc64 crc32c opcode accelerated"); diff --git a/arch/sparc/crypto/crc32c_asm.S b/arch/sparc/lib/crc32c_asm.S similarity index 92% rename from arch/sparc/crypto/crc32c_asm.S rename to arch/sparc/lib/crc32c_asm.S index b8659a479242..ee454fa6aed6 100644 --- a/arch/sparc/crypto/crc32c_asm.S +++ b/arch/sparc/lib/crc32c_asm.S @@ -3,7 +3,7 @@ #include #include -#include "opcodes.h" +#include "../crypto/opcodes.h" ENTRY(crc32c_sparc64) /* %o0=crc32p, %o1=data_ptr, %o2=len */ diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 21f8cbbd0581..05882bca5b73 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2915,7 +2915,7 @@ static void __pte_free(pgtable_t pte) { struct ptdesc *ptdesc = virt_to_ptdesc(pte); - pagetable_pte_dtor(ptdesc); + pagetable_dtor(ptdesc); pagetable_free(ptdesc); } diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index 9df51a62333d..dd32711022f5 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -277,19 +277,13 @@ static void __init srmmu_nocache_init(void) bitmap_bits = srmmu_nocache_size >> SRMMU_NOCACHE_BITMAP_SHIFT; - srmmu_nocache_pool = memblock_alloc(srmmu_nocache_size, + srmmu_nocache_pool = memblock_alloc_or_panic(srmmu_nocache_size, SRMMU_NOCACHE_ALIGN_MAX); - if (!srmmu_nocache_pool) - panic("%s: Failed to allocate %lu bytes align=0x%x\n", - __func__, srmmu_nocache_size, SRMMU_NOCACHE_ALIGN_MAX); memset(srmmu_nocache_pool, 0, srmmu_nocache_size); srmmu_nocache_bitmap = - memblock_alloc(BITS_TO_LONGS(bitmap_bits) * sizeof(long), + memblock_alloc_or_panic(BITS_TO_LONGS(bitmap_bits) * sizeof(long), SMP_CACHE_BYTES); - if (!srmmu_nocache_bitmap) - panic("%s: Failed to allocate %zu bytes\n", __func__, - BITS_TO_LONGS(bitmap_bits) * sizeof(long)); bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits); srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE); @@ -372,7 +366,7 @@ void pte_free(struct mm_struct *mm, pgtable_t ptep) page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT); spin_lock(&mm->page_table_lock); if (page_ref_dec_return(page) == 1) - pagetable_pte_dtor(page_ptdesc(page)); + pagetable_dtor(page_ptdesc(page)); spin_unlock(&mm->page_table_lock); srmmu_free_nocache(ptep, SRMMU_PTE_TABLE_SIZE); @@ -452,9 +446,7 @@ static void __init sparc_context_init(int numctx) unsigned long size; size = numctx * sizeof(struct ctx_list); - ctx_list_pool = memblock_alloc(size, SMP_CACHE_BYTES); - if (!ctx_list_pool) - panic("%s: Failed to allocate %lu bytes\n", __func__, size); + ctx_list_pool = memblock_alloc_or_panic(size, SMP_CACHE_BYTES); for (ctx = 0; ctx < numctx; ctx++) { struct ctx_list *clist; diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 75d04fb4994a..d5a9c5aabaec 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -636,10 +636,7 @@ static int __init eth_setup(char *str) return 1; } - new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES); - if (!new) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*new)); + new = memblock_alloc_or_panic(sizeof(*new), SMP_CACHE_BYTES); INIT_LIST_HEAD(&new->list); new->index = n; diff --git a/arch/um/drivers/rtc_kern.c b/arch/um/drivers/rtc_kern.c index 134a58f93c85..9158c936c128 100644 --- a/arch/um/drivers/rtc_kern.c +++ b/arch/um/drivers/rtc_kern.c @@ -51,6 +51,7 @@ static int uml_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) static int uml_rtc_alarm_irq_enable(struct device *dev, unsigned int enable) { + struct timespec64 ts; unsigned long long secs; if (!enable && !uml_rtc_alarm_enabled) @@ -58,7 +59,8 @@ static int uml_rtc_alarm_irq_enable(struct device *dev, unsigned int enable) uml_rtc_alarm_enabled = enable; - secs = uml_rtc_alarm_time - ktime_get_real_seconds(); + read_persistent_clock64(&ts); + secs = uml_rtc_alarm_time - ts.tv_sec; if (time_travel_mode == TT_MODE_OFF) { if (!enable) { @@ -73,7 +75,8 @@ static int uml_rtc_alarm_irq_enable(struct device *dev, unsigned int enable) if (enable) time_travel_add_event_rel(¨_rtc_alarm_event, - secs * NSEC_PER_SEC); + secs * NSEC_PER_SEC - + ts.tv_nsec); } return 0; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 66c1a8835e36..0b1e61f72fb3 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -865,7 +865,6 @@ static int ubd_add(int n, char **error_out) ubd_dev->tag_set.ops = &ubd_mq_ops; ubd_dev->tag_set.queue_depth = 64; ubd_dev->tag_set.numa_node = NUMA_NO_NODE; - ubd_dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ubd_dev->tag_set.driver_data = ubd_dev; ubd_dev->tag_set.nr_hw_queues = 1; diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 64c09db392c1..85b129e2b70b 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1694,10 +1694,7 @@ static int __init vector_setup(char *str) str, error); return 1; } - new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES); - if (!new) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*new)); + new = memblock_alloc_or_panic(sizeof(*new), SMP_CACHE_BYTES); INIT_LIST_HEAD(&new->list); new->unit = n; new->arguments = str; diff --git a/arch/um/include/asm/fixmap.h b/arch/um/include/asm/fixmap.h deleted file mode 100644 index 2efac5827188..000000000000 --- a/arch/um/include/asm/fixmap.h +++ /dev/null @@ -1,56 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_FIXMAP_H -#define __UM_FIXMAP_H - -#include -#include -#include -#include - -/* - * Here we define all the compile-time 'special' virtual - * addresses. The point is to have a constant address at - * compile time, but to set the physical address only - * in the boot process. We allocate these special addresses - * from the end of virtual memory (0xfffff000) backwards. - * Also this lets us do fail-safe vmalloc(), we - * can guarantee that these special addresses and - * vmalloc()-ed addresses never overlap. - * - * these 'compile-time allocated' memory buffers are - * fixed-size 4k pages. (or larger if used with an increment - * highger than 1) use fixmap_set(idx,phys) to associate - * physical memory with fixmap indices. - * - * TLB entries of such buffers will not be flushed across - * task switches. - */ - -/* - * on UP currently we will have no trace of the fixmap mechanizm, - * no page table allocations, etc. This might change in the - * future, say framebuffers for the console driver(s) could be - * fix-mapped? - */ -enum fixed_addresses { - __end_of_fixed_addresses -}; - -extern void __set_fixmap (enum fixed_addresses idx, - unsigned long phys, pgprot_t flags); - -/* - * used by vmalloc.c. - * - * Leave one empty page between vmalloc'ed areas and - * the start of the fixmap, and leave one page empty - * at the top of mem.. - */ - -#define FIXADDR_TOP (TASK_SIZE - 2 * PAGE_SIZE) -#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) - -#include - -#endif diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 04fb4e6969a4..f0af23c3aeb2 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -27,7 +27,7 @@ extern pgd_t *pgd_alloc(struct mm_struct *); #define __pte_free_tlb(tlb, pte, address) \ do { \ - pagetable_pte_dtor(page_ptdesc(pte)); \ + pagetable_dtor(page_ptdesc(pte)); \ tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) @@ -35,7 +35,7 @@ do { \ #define __pmd_free_tlb(tlb, pmd, address) \ do { \ - pagetable_pmd_dtor(virt_to_ptdesc(pmd)); \ + pagetable_dtor(virt_to_ptdesc(pmd)); \ tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd)); \ } while (0) @@ -43,7 +43,7 @@ do { \ #define __pud_free_tlb(tlb, pud, address) \ do { \ - pagetable_pud_dtor(virt_to_ptdesc(pud)); \ + pagetable_dtor(virt_to_ptdesc(pud)); \ tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud)); \ } while (0) diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 0bd60afcc37d..5601ca98e8a6 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -8,7 +8,8 @@ #ifndef __UM_PGTABLE_H #define __UM_PGTABLE_H -#include +#include +#include #define _PAGE_PRESENT 0x001 #define _PAGE_NEEDSYNC 0x002 @@ -48,11 +49,9 @@ extern unsigned long end_iomem; #define VMALLOC_OFFSET (__va_space) #define VMALLOC_START ((end_iomem + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)) -#define PKMAP_BASE ((FIXADDR_START - LAST_PKMAP * PAGE_SIZE) & PMD_MASK) -#define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE) +#define VMALLOC_END (TASK_SIZE-2*PAGE_SIZE) #define MODULES_VADDR VMALLOC_START #define MODULES_END VMALLOC_END -#define MODULES_LEN (MODULES_VADDR - MODULES_END) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY) #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) diff --git a/arch/um/kernel/load_file.c b/arch/um/kernel/load_file.c index 5cecd0e291fb..cb9d178ab7d8 100644 --- a/arch/um/kernel/load_file.c +++ b/arch/um/kernel/load_file.c @@ -48,9 +48,7 @@ void *uml_load_file(const char *filename, unsigned long long *size) return NULL; } - area = memblock_alloc(*size, SMP_CACHE_BYTES); - if (!area) - panic("%s: Failed to allocate %llu bytes\n", __func__, *size); + area = memblock_alloc_or_panic(*size, SMP_CACHE_BYTES); if (__uml_load_file(filename, area, *size)) { memblock_free(area, *size); diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 53248ed04771..befed230aac2 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include @@ -74,6 +73,7 @@ void __init mem_init(void) kmalloc_ok = 1; } +#if IS_ENABLED(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) /* * Create a page table and place a pointer to it in a middle page * directory entry. @@ -152,7 +152,6 @@ static void __init fixrange_init(unsigned long start, unsigned long end, static void __init fixaddr_user_init( void) { -#ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA long size = FIXADDR_USER_END - FIXADDR_USER_START; pte_t *pte; phys_t p; @@ -174,13 +173,12 @@ static void __init fixaddr_user_init( void) pte = virt_to_kpte(vaddr); pte_set_val(*pte, p, PAGE_READONLY); } -#endif } +#endif void __init paging_init(void) { unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; - unsigned long vaddr; empty_zero_page = (unsigned long *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); @@ -191,14 +189,9 @@ void __init paging_init(void) max_zone_pfn[ZONE_NORMAL] = end_iomem >> PAGE_SHIFT; free_area_init(max_zone_pfn); - /* - * Fixed mappings, only the page table structure has to be - * created - mappings will be set by set_fixmap(): - */ - vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; - fixrange_init(vaddr, FIXADDR_TOP, swapper_pg_dir); - +#if IS_ENABLED(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) fixaddr_user_init(); +#endif } /* @@ -214,14 +207,13 @@ void free_initmem(void) pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL); + pgd_t *pgd = __pgd_alloc(mm, 0); - if (pgd) { - memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t)); + if (pgd) memcpy(pgd + USER_PTRS_PER_PGD, swapper_pg_dir + USER_PTRS_PER_PGD, (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); - } + return pgd; } diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 30bdc0a87dc8..e5a2d4d897e0 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -213,14 +213,6 @@ int __uml_cant_sleep(void) { /* Is in_interrupt() really needed? */ } -int user_context(unsigned long sp) -{ - unsigned long stack; - - stack = sp & (PAGE_MASK << CONFIG_KERNEL_STACK_ORDER); - return stack != (unsigned long) current_thread_info(); -} - extern exitcall_t __uml_exitcall_begin, __uml_exitcall_end; void do_uml_exitcalls(void) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 8037a967225d..79ea97d4797e 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -264,7 +264,7 @@ EXPORT_SYMBOL(end_iomem); #define MIN_VMALLOC (32 * 1024 * 1024) -static void parse_host_cpu_flags(char *line) +static void __init parse_host_cpu_flags(char *line) { int i; for (i = 0; i < 32*NCAPINTS; i++) { @@ -272,7 +272,8 @@ static void parse_host_cpu_flags(char *line) set_cpu_cap(&boot_cpu_data, i); } } -static void parse_cache_line(char *line) + +static void __init parse_cache_line(char *line) { long res; char *to_parse = strstr(line, ":"); @@ -288,7 +289,7 @@ static void parse_cache_line(char *line) } } -static unsigned long get_top_address(char **envp) +static unsigned long __init get_top_address(char **envp) { unsigned long top_addr = (unsigned long) &top_addr; int i; @@ -376,9 +377,8 @@ int __init linux_main(int argc, char **argv, char **envp) iomem_size = (iomem_size + PAGE_SIZE - 1) & PAGE_MASK; max_physmem = TASK_SIZE - uml_physmem - iomem_size - MIN_VMALLOC; - - if (physmem_size + iomem_size > max_physmem) { - physmem_size = max_physmem - iomem_size; + if (physmem_size > max_physmem) { + physmem_size = max_physmem; os_info("Physical memory size shrunk to %llu bytes\n", physmem_size); } diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c index 0afcdeb8995b..3c63ce19e3bf 100644 --- a/arch/um/os-Linux/main.c +++ b/arch/um/os-Linux/main.c @@ -19,13 +19,11 @@ #include #include "internal.h" -#define PGD_BOUND (4 * 1024 * 1024) #define STACKSIZE (8 * 1024 * 1024) -#define THREAD_NAME_LEN (256) long elf_aux_hwcap; -static void set_stklim(void) +static void __init set_stklim(void) { struct rlimit lim; @@ -48,7 +46,7 @@ static void last_ditch_exit(int sig) exit(1); } -static void install_fatal_handler(int sig) +static void __init install_fatal_handler(int sig) { struct sigaction action; @@ -73,7 +71,7 @@ static void install_fatal_handler(int sig) #define UML_LIB_PATH ":" OS_LIB_PATH "/uml" -static void setup_env_path(void) +static void __init setup_env_path(void) { char *new_path = NULL; char *old_path = NULL; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9d7bd0ae48c4..87198d957e2f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -76,6 +76,8 @@ config X86 select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CPU_PASID if IOMMU_SVA + select ARCH_HAS_CRC32 + select ARCH_HAS_CRC_T10DIF if X86_64 select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE @@ -83,7 +85,6 @@ config X86 select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN select ARCH_HAS_EARLY_DEBUG if KGDB select ARCH_HAS_ELF_RANDOMIZE - select ARCH_HAS_EXECMEM_ROX if X86_64 select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL @@ -225,6 +226,7 @@ config X86 select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_DYNAMIC_FTRACE_WITH_ARGS if X86_64 + select HAVE_FTRACE_REGS_HAVING_PT_REGS if X86_64 select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_SAMPLE_FTRACE_DIRECT if X86_64 select HAVE_SAMPLE_FTRACE_DIRECT_MULTI if X86_64 @@ -234,8 +236,9 @@ config X86 select HAVE_EXIT_THREAD select HAVE_GUP_FAST select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE + select HAVE_FTRACE_GRAPH_FUNC if HAVE_FUNCTION_GRAPH_TRACER select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS if HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_TRACER if X86_32 || (X86_64 && DYNAMIC_FTRACE) select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS @@ -322,6 +325,7 @@ config X86 select FUNCTION_ALIGNMENT_4B imply IMA_SECURE_AND_OR_TRUSTED_BOOT if EFI select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE + select ARCH_SUPPORTS_PT_RECLAIM if X86_64 config INSTRUCTION_DECODER def_bool y @@ -1189,7 +1193,7 @@ config X86_MCE_INTEL config X86_MCE_AMD def_bool y prompt "AMD MCE features" - depends on X86_MCE && X86_LOCAL_APIC && AMD_NB + depends on X86_MCE && X86_LOCAL_APIC help Additional support for AMD specific MCE features such as the DRAM Error Threshold. @@ -1559,6 +1563,7 @@ config AMD_MEM_ENCRYPT select ARCH_HAS_CC_PLATFORM select X86_MEM_ENCRYPT select UNACCEPTED_MEMORY + select CRYPTO_LIB_AESGCM help Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory @@ -3128,6 +3133,10 @@ config TS5500 endif # X86_32 config AMD_NB + def_bool y + depends on AMD_NODE + +config AMD_NODE def_bool y depends on CPU_SUP_AMD && PCI diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 74777a97e394..1eb4d23cdaae 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -97,7 +97,7 @@ config IOMMU_DEBUG code. When you use it make sure you have a big enough IOMMU/AGP aperture. Most of the options enabled by this can be set more finegrained using the iommu= command line - options. See Documentation/arch/x86/x86_64/boot-options.rst for more + options. See Documentation/admin-guide/kernel-parameters.txt for more details. config IOMMU_LEAK diff --git a/arch/x86/Makefile.postlink b/arch/x86/Makefile.postlink index fef2e977cc7d..8b8a68162c94 100644 --- a/arch/x86/Makefile.postlink +++ b/arch/x86/Makefile.postlink @@ -11,6 +11,7 @@ __archpost: -include include/config/auto.conf include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib CMD_RELOCS = arch/x86/tools/relocs OUT_RELOCS = arch/x86/boot/compressed @@ -20,11 +21,6 @@ quiet_cmd_relocs = RELOCS $(OUT_RELOCS)/$@.relocs $(CMD_RELOCS) $@ > $(OUT_RELOCS)/$@.relocs; \ $(CMD_RELOCS) --abs-relocs $@ -quiet_cmd_strip_relocs = RSTRIP $@ - cmd_strip_relocs = \ - $(OBJCOPY) --remove-section='.rel.*' --remove-section='.rel__*' \ - --remove-section='.rela.*' --remove-section='.rela__*' $@ - # `@true` prevents complaint when there is nothing to be done vmlinux: FORCE diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index f4d82379bf44..f03d59ea6e40 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -25,10 +25,6 @@ #include "efi.h" #include -#include -#include -#include -#include #include #include diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index cd44e120fe53..bb55934c1cee 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -401,7 +401,8 @@ finish: * by the guest kernel. As and when a new feature is implemented in the * guest kernel, a corresponding bit should be added to the mask. */ -#define SNP_FEATURES_PRESENT MSR_AMD64_SNP_DEBUG_SWAP +#define SNP_FEATURES_PRESENT (MSR_AMD64_SNP_DEBUG_SWAP | \ + MSR_AMD64_SNP_SECURE_TSC) u64 snp_get_unsupported_features(u64 status) { diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index 0f81f70aca82..9a0ddda3aa69 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -65,7 +65,6 @@ static __maybe_unused __always_inline bool amd_cc_platform_vtom(enum cc_attr att * up under SME the trampoline area cannot be encrypted, whereas under SEV * the trampoline area must be encrypted. */ - static bool noinstr amd_cc_platform_has(enum cc_attr attr) { #ifdef CONFIG_AMD_MEM_ENCRYPT @@ -97,6 +96,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_SEV_SNP: return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + case CC_ATTR_GUEST_SNP_SECURE_TSC: + return sev_status & MSR_AMD64_SNP_SECURE_TSC; + case CC_ATTR_HOST_SEV_SNP: return cc_flags.host_sev_snp; diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile index 4e375e7305ac..dcb06dc8b5ae 100644 --- a/arch/x86/coco/sev/Makefile +++ b/arch/x86/coco/sev/Makefile @@ -2,6 +2,10 @@ obj-y += core.o +# jump tables are emitted using absolute references in non-PIC code +# so they cannot be used in the early SEV startup code +CFLAGS_core.o += -fno-jump-tables + ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_core.o = -pg endif @@ -13,3 +17,6 @@ KCOV_INSTRUMENT_core.o := n # With some compiler versions the generated code results in boot hangs, caused # by several compilation units. To be safe, disable all instrumentation. KCSAN_SANITIZE := n + +# Clang 14 and older may fail to respect __no_sanitize_undefined when inlining +UBSAN_SANITIZE := n diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index c5b0148b8c0a..82492efc5d94 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -9,6 +9,8 @@ #define pr_fmt(fmt) "SEV: " fmt +#define DISABLE_BRANCH_PROFILING + #include /* For show_regs() */ #include #include @@ -25,6 +27,7 @@ #include #include #include +#include #include #include @@ -95,6 +98,15 @@ static u64 sev_hv_features __ro_after_init; /* Secrets page physical address from the CC blob */ static u64 secrets_pa __ro_after_init; +/* + * For Secure TSC guests, the BSP fetches TSC_INFO using SNP guest messaging and + * initializes snp_tsc_scale and snp_tsc_offset. These values are replicated + * across the APs VMSA fields (TSC_SCALE and TSC_OFFSET). + */ +static u64 snp_tsc_scale __ro_after_init; +static u64 snp_tsc_offset __ro_after_init; +static u64 snp_tsc_freq_khz __ro_after_init; + /* #VC handler runtime per-CPU data */ struct sev_es_runtime_data { struct ghcb ghcb_page; @@ -777,15 +789,10 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr, val = sev_es_rd_ghcb_msr(); - if (WARN(GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP, - "Wrong PSC response code: 0x%x\n", - (unsigned int)GHCB_RESP_CODE(val))) + if (GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) goto e_term; - if (WARN(GHCB_MSR_PSC_RESP_VAL(val), - "Failed to change page state to '%s' paddr 0x%lx error 0x%llx\n", - op == SNP_PAGE_STATE_PRIVATE ? "private" : "shared", - paddr, GHCB_MSR_PSC_RESP_VAL(val))) + if (GHCB_MSR_PSC_RESP_VAL(val)) goto e_term; /* Page validation must be performed after changing to private */ @@ -821,7 +828,7 @@ void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long padd early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_PRIVATE); } -void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, +void __head early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { /* @@ -1276,6 +1283,12 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) vmsa->vmpl = snp_vmpl; vmsa->sev_features = sev_status >> 2; + /* Populate AP's TSC scale/offset to get accurate TSC values. */ + if (cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) { + vmsa->tsc_scale = snp_tsc_scale; + vmsa->tsc_offset = snp_tsc_offset; + } + /* Switch the page over to a VMSA page now that it is initialized */ ret = snp_set_vmsa(vmsa, caa, apic_id, true); if (ret) { @@ -1418,6 +1431,41 @@ static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write) return ES_OK; } +/* + * TSC related accesses should not exit to the hypervisor when a guest is + * executing with Secure TSC enabled, so special handling is required for + * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ. + */ +static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write) +{ + u64 tsc; + + /* + * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled. + * Terminate the SNP guest when the interception is enabled. + */ + if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ) + return ES_VMM_ERROR; + + /* + * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC + * to return undefined values, so ignore all writes. + * + * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use + * the value returned by rdtsc_ordered(). + */ + if (write) { + WARN_ONCE(1, "TSC MSR writes are verboten!\n"); + return ES_OK; + } + + tsc = rdtsc_ordered(); + regs->ax = lower_32_bits(tsc); + regs->dx = upper_32_bits(tsc); + + return ES_OK; +} + static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; @@ -1427,8 +1475,18 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) /* Is it a WRMSR? */ write = ctxt->insn.opcode.bytes[1] == 0x30; - if (regs->cx == MSR_SVSM_CAA) + switch (regs->cx) { + case MSR_SVSM_CAA: return __vc_handle_msr_caa(regs, write); + case MSR_IA32_TSC: + case MSR_AMD64_GUEST_TSC_FREQ: + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + return __vc_handle_secure_tsc_msrs(regs, write); + else + break; + default: + break; + } ghcb_set_rcx(ghcb, regs->cx); if (write) { @@ -1572,9 +1630,7 @@ static void __init alloc_runtime_data(int cpu) struct svsm_ca *caa; /* Allocate the SVSM CA page if an SVSM is present */ - caa = memblock_alloc(sizeof(*caa), PAGE_SIZE); - if (!caa) - panic("Can't allocate SVSM CA page\n"); + caa = memblock_alloc_or_panic(sizeof(*caa), PAGE_SIZE); per_cpu(svsm_caa, cpu) = caa; per_cpu(svsm_caa_pa, cpu) = __pa(caa); @@ -2362,7 +2418,7 @@ static __head void svsm_setup(struct cc_blob_sev_info *cc_info) call.rcx = pa; ret = svsm_perform_call_protocol(&call); if (ret) - panic("Can't remap the SVSM CA, ret=%d, rax_out=0x%llx\n", ret, call.rax_out); + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CA_REMAP_FAIL); RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)pa; RIP_REL_REF(boot_svsm_caa_pa) = pa; @@ -2508,8 +2564,8 @@ int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, } EXPORT_SYMBOL_GPL(snp_issue_svsm_attest_req); -int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, - struct snp_guest_request_ioctl *rio) +static int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, + struct snp_guest_request_ioctl *rio) { struct ghcb_state state; struct es_em_ctxt ctxt; @@ -2571,7 +2627,6 @@ e_restore_irq: return ret; } -EXPORT_SYMBOL_GPL(snp_issue_guest_request); static struct platform_device sev_guest_device = { .name = "sev-guest", @@ -2580,15 +2635,9 @@ static struct platform_device sev_guest_device = { static int __init snp_init_platform_device(void) { - struct sev_guest_platform_data data; - if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return -ENODEV; - data.secrets_gpa = secrets_pa; - if (platform_device_add_data(&sev_guest_device, &data, sizeof(data))) - return -ENODEV; - if (platform_device_register(&sev_guest_device)) return -ENODEV; @@ -2667,3 +2716,581 @@ static int __init sev_sysfs_init(void) } arch_initcall(sev_sysfs_init); #endif // CONFIG_SYSFS + +static void free_shared_pages(void *buf, size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + int ret; + + if (!buf) + return; + + ret = set_memory_encrypted((unsigned long)buf, npages); + if (ret) { + WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); + return; + } + + __free_pages(virt_to_page(buf), get_order(sz)); +} + +static void *alloc_shared_pages(size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + struct page *page; + int ret; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz)); + if (!page) + return NULL; + + ret = set_memory_decrypted((unsigned long)page_address(page), npages); + if (ret) { + pr_err("failed to mark page shared, ret=%d\n", ret); + __free_pages(page, get_order(sz)); + return NULL; + } + + return page_address(page); +} + +static u8 *get_vmpck(int id, struct snp_secrets_page *secrets, u32 **seqno) +{ + u8 *key = NULL; + + switch (id) { + case 0: + *seqno = &secrets->os_area.msg_seqno_0; + key = secrets->vmpck0; + break; + case 1: + *seqno = &secrets->os_area.msg_seqno_1; + key = secrets->vmpck1; + break; + case 2: + *seqno = &secrets->os_area.msg_seqno_2; + key = secrets->vmpck2; + break; + case 3: + *seqno = &secrets->os_area.msg_seqno_3; + key = secrets->vmpck3; + break; + default: + break; + } + + return key; +} + +static struct aesgcm_ctx *snp_init_crypto(u8 *key, size_t keylen) +{ + struct aesgcm_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + if (aesgcm_expandkey(ctx, key, keylen, AUTHTAG_LEN)) { + pr_err("Crypto context initialization failed\n"); + kfree(ctx); + return NULL; + } + + return ctx; +} + +int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id) +{ + /* Adjust the default VMPCK key based on the executing VMPL level */ + if (vmpck_id == -1) + vmpck_id = snp_vmpl; + + mdesc->vmpck = get_vmpck(vmpck_id, mdesc->secrets, &mdesc->os_area_msg_seqno); + if (!mdesc->vmpck) { + pr_err("Invalid VMPCK%d communication key\n", vmpck_id); + return -EINVAL; + } + + /* Verify that VMPCK is not zero. */ + if (!memchr_inv(mdesc->vmpck, 0, VMPCK_KEY_LEN)) { + pr_err("Empty VMPCK%d communication key\n", vmpck_id); + return -EINVAL; + } + + mdesc->vmpck_id = vmpck_id; + + mdesc->ctx = snp_init_crypto(mdesc->vmpck, VMPCK_KEY_LEN); + if (!mdesc->ctx) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_GPL(snp_msg_init); + +struct snp_msg_desc *snp_msg_alloc(void) +{ + struct snp_msg_desc *mdesc; + void __iomem *mem; + + BUILD_BUG_ON(sizeof(struct snp_guest_msg) > PAGE_SIZE); + + mdesc = kzalloc(sizeof(struct snp_msg_desc), GFP_KERNEL); + if (!mdesc) + return ERR_PTR(-ENOMEM); + + mem = ioremap_encrypted(secrets_pa, PAGE_SIZE); + if (!mem) + goto e_free_mdesc; + + mdesc->secrets = (__force struct snp_secrets_page *)mem; + + /* Allocate the shared page used for the request and response message. */ + mdesc->request = alloc_shared_pages(sizeof(struct snp_guest_msg)); + if (!mdesc->request) + goto e_unmap; + + mdesc->response = alloc_shared_pages(sizeof(struct snp_guest_msg)); + if (!mdesc->response) + goto e_free_request; + + mdesc->certs_data = alloc_shared_pages(SEV_FW_BLOB_MAX_SIZE); + if (!mdesc->certs_data) + goto e_free_response; + + /* initial the input address for guest request */ + mdesc->input.req_gpa = __pa(mdesc->request); + mdesc->input.resp_gpa = __pa(mdesc->response); + mdesc->input.data_gpa = __pa(mdesc->certs_data); + + return mdesc; + +e_free_response: + free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); +e_free_request: + free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); +e_unmap: + iounmap(mem); +e_free_mdesc: + kfree(mdesc); + + return ERR_PTR(-ENOMEM); +} +EXPORT_SYMBOL_GPL(snp_msg_alloc); + +void snp_msg_free(struct snp_msg_desc *mdesc) +{ + if (!mdesc) + return; + + kfree(mdesc->ctx); + free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); + free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); + free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE); + iounmap((__force void __iomem *)mdesc->secrets); + + memset(mdesc, 0, sizeof(*mdesc)); + kfree(mdesc); +} +EXPORT_SYMBOL_GPL(snp_msg_free); + +/* Mutex to serialize the shared buffer access and command handling. */ +static DEFINE_MUTEX(snp_cmd_mutex); + +/* + * If an error is received from the host or AMD Secure Processor (ASP) there + * are two options. Either retry the exact same encrypted request or discontinue + * using the VMPCK. + * + * This is because in the current encryption scheme GHCB v2 uses AES-GCM to + * encrypt the requests. The IV for this scheme is the sequence number. GCM + * cannot tolerate IV reuse. + * + * The ASP FW v1.51 only increments the sequence numbers on a successful + * guest<->ASP back and forth and only accepts messages at its exact sequence + * number. + * + * So if the sequence number were to be reused the encryption scheme is + * vulnerable. If the sequence number were incremented for a fresh IV the ASP + * will reject the request. + */ +static void snp_disable_vmpck(struct snp_msg_desc *mdesc) +{ + pr_alert("Disabling VMPCK%d communication key to prevent IV reuse.\n", + mdesc->vmpck_id); + memzero_explicit(mdesc->vmpck, VMPCK_KEY_LEN); + mdesc->vmpck = NULL; +} + +static inline u64 __snp_get_msg_seqno(struct snp_msg_desc *mdesc) +{ + u64 count; + + lockdep_assert_held(&snp_cmd_mutex); + + /* Read the current message sequence counter from secrets pages */ + count = *mdesc->os_area_msg_seqno; + + return count + 1; +} + +/* Return a non-zero on success */ +static u64 snp_get_msg_seqno(struct snp_msg_desc *mdesc) +{ + u64 count = __snp_get_msg_seqno(mdesc); + + /* + * The message sequence counter for the SNP guest request is a 64-bit + * value but the version 2 of GHCB specification defines a 32-bit storage + * for it. If the counter exceeds the 32-bit value then return zero. + * The caller should check the return value, but if the caller happens to + * not check the value and use it, then the firmware treats zero as an + * invalid number and will fail the message request. + */ + if (count >= UINT_MAX) { + pr_err("request message sequence counter overflow\n"); + return 0; + } + + return count; +} + +static void snp_inc_msg_seqno(struct snp_msg_desc *mdesc) +{ + /* + * The counter is also incremented by the PSP, so increment it by 2 + * and save in secrets page. + */ + *mdesc->os_area_msg_seqno += 2; +} + +static int verify_and_dec_payload(struct snp_msg_desc *mdesc, struct snp_guest_req *req) +{ + struct snp_guest_msg *resp_msg = &mdesc->secret_response; + struct snp_guest_msg *req_msg = &mdesc->secret_request; + struct snp_guest_msg_hdr *req_msg_hdr = &req_msg->hdr; + struct snp_guest_msg_hdr *resp_msg_hdr = &resp_msg->hdr; + struct aesgcm_ctx *ctx = mdesc->ctx; + u8 iv[GCM_AES_IV_SIZE] = {}; + + pr_debug("response [seqno %lld type %d version %d sz %d]\n", + resp_msg_hdr->msg_seqno, resp_msg_hdr->msg_type, resp_msg_hdr->msg_version, + resp_msg_hdr->msg_sz); + + /* Copy response from shared memory to encrypted memory. */ + memcpy(resp_msg, mdesc->response, sizeof(*resp_msg)); + + /* Verify that the sequence counter is incremented by 1 */ + if (unlikely(resp_msg_hdr->msg_seqno != (req_msg_hdr->msg_seqno + 1))) + return -EBADMSG; + + /* Verify response message type and version number. */ + if (resp_msg_hdr->msg_type != (req_msg_hdr->msg_type + 1) || + resp_msg_hdr->msg_version != req_msg_hdr->msg_version) + return -EBADMSG; + + /* + * If the message size is greater than our buffer length then return + * an error. + */ + if (unlikely((resp_msg_hdr->msg_sz + ctx->authsize) > req->resp_sz)) + return -EBADMSG; + + /* Decrypt the payload */ + memcpy(iv, &resp_msg_hdr->msg_seqno, min(sizeof(iv), sizeof(resp_msg_hdr->msg_seqno))); + if (!aesgcm_decrypt(ctx, req->resp_buf, resp_msg->payload, resp_msg_hdr->msg_sz, + &resp_msg_hdr->algo, AAD_LEN, iv, resp_msg_hdr->authtag)) + return -EBADMSG; + + return 0; +} + +static int enc_payload(struct snp_msg_desc *mdesc, u64 seqno, struct snp_guest_req *req) +{ + struct snp_guest_msg *msg = &mdesc->secret_request; + struct snp_guest_msg_hdr *hdr = &msg->hdr; + struct aesgcm_ctx *ctx = mdesc->ctx; + u8 iv[GCM_AES_IV_SIZE] = {}; + + memset(msg, 0, sizeof(*msg)); + + hdr->algo = SNP_AEAD_AES_256_GCM; + hdr->hdr_version = MSG_HDR_VER; + hdr->hdr_sz = sizeof(*hdr); + hdr->msg_type = req->msg_type; + hdr->msg_version = req->msg_version; + hdr->msg_seqno = seqno; + hdr->msg_vmpck = req->vmpck_id; + hdr->msg_sz = req->req_sz; + + /* Verify the sequence number is non-zero */ + if (!hdr->msg_seqno) + return -ENOSR; + + pr_debug("request [seqno %lld type %d version %d sz %d]\n", + hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz); + + if (WARN_ON((req->req_sz + ctx->authsize) > sizeof(msg->payload))) + return -EBADMSG; + + memcpy(iv, &hdr->msg_seqno, min(sizeof(iv), sizeof(hdr->msg_seqno))); + aesgcm_encrypt(ctx, msg->payload, req->req_buf, req->req_sz, &hdr->algo, + AAD_LEN, iv, hdr->authtag); + + return 0; +} + +static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) +{ + unsigned long req_start = jiffies; + unsigned int override_npages = 0; + u64 override_err = 0; + int rc; + +retry_request: + /* + * Call firmware to process the request. In this function the encrypted + * message enters shared memory with the host. So after this call the + * sequence number must be incremented or the VMPCK must be deleted to + * prevent reuse of the IV. + */ + rc = snp_issue_guest_request(req, &mdesc->input, rio); + switch (rc) { + case -ENOSPC: + /* + * If the extended guest request fails due to having too + * small of a certificate data buffer, retry the same + * guest request without the extended data request in + * order to increment the sequence number and thus avoid + * IV reuse. + */ + override_npages = mdesc->input.data_npages; + req->exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + /* + * Override the error to inform callers the given extended + * request buffer size was too small and give the caller the + * required buffer size. + */ + override_err = SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN); + + /* + * If this call to the firmware succeeds, the sequence number can + * be incremented allowing for continued use of the VMPCK. If + * there is an error reflected in the return value, this value + * is checked further down and the result will be the deletion + * of the VMPCK and the error code being propagated back to the + * user as an ioctl() return code. + */ + goto retry_request; + + /* + * The host may return SNP_GUEST_VMM_ERR_BUSY if the request has been + * throttled. Retry in the driver to avoid returning and reusing the + * message sequence number on a different message. + */ + case -EAGAIN: + if (jiffies - req_start > SNP_REQ_MAX_RETRY_DURATION) { + rc = -ETIMEDOUT; + break; + } + schedule_timeout_killable(SNP_REQ_RETRY_DELAY); + goto retry_request; + } + + /* + * Increment the message sequence number. There is no harm in doing + * this now because decryption uses the value stored in the response + * structure and any failure will wipe the VMPCK, preventing further + * use anyway. + */ + snp_inc_msg_seqno(mdesc); + + if (override_err) { + rio->exitinfo2 = override_err; + + /* + * If an extended guest request was issued and the supplied certificate + * buffer was not large enough, a standard guest request was issued to + * prevent IV reuse. If the standard request was successful, return -EIO + * back to the caller as would have originally been returned. + */ + if (!rc && override_err == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) + rc = -EIO; + } + + if (override_npages) + mdesc->input.data_npages = override_npages; + + return rc; +} + +int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) +{ + u64 seqno; + int rc; + + guard(mutex)(&snp_cmd_mutex); + + /* Check if the VMPCK is not empty */ + if (!mdesc->vmpck || !memchr_inv(mdesc->vmpck, 0, VMPCK_KEY_LEN)) { + pr_err_ratelimited("VMPCK is disabled\n"); + return -ENOTTY; + } + + /* Get message sequence and verify that its a non-zero */ + seqno = snp_get_msg_seqno(mdesc); + if (!seqno) + return -EIO; + + /* Clear shared memory's response for the host to populate. */ + memset(mdesc->response, 0, sizeof(struct snp_guest_msg)); + + /* Encrypt the userspace provided payload in mdesc->secret_request. */ + rc = enc_payload(mdesc, seqno, req); + if (rc) + return rc; + + /* + * Write the fully encrypted request to the shared unencrypted + * request page. + */ + memcpy(mdesc->request, &mdesc->secret_request, sizeof(mdesc->secret_request)); + + rc = __handle_guest_request(mdesc, req, rio); + if (rc) { + if (rc == -EIO && + rio->exitinfo2 == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) + return rc; + + pr_alert("Detected error from ASP request. rc: %d, exitinfo2: 0x%llx\n", + rc, rio->exitinfo2); + + snp_disable_vmpck(mdesc); + return rc; + } + + rc = verify_and_dec_payload(mdesc, req); + if (rc) { + pr_alert("Detected unexpected decode failure from ASP. rc: %d\n", rc); + snp_disable_vmpck(mdesc); + return rc; + } + + return 0; +} +EXPORT_SYMBOL_GPL(snp_send_guest_request); + +static int __init snp_get_tsc_info(void) +{ + struct snp_guest_request_ioctl *rio; + struct snp_tsc_info_resp *tsc_resp; + struct snp_tsc_info_req *tsc_req; + struct snp_msg_desc *mdesc; + struct snp_guest_req *req; + int rc = -ENOMEM; + + tsc_req = kzalloc(sizeof(*tsc_req), GFP_KERNEL); + if (!tsc_req) + return rc; + + /* + * The intermediate response buffer is used while decrypting the + * response payload. Make sure that it has enough space to cover + * the authtag. + */ + tsc_resp = kzalloc(sizeof(*tsc_resp) + AUTHTAG_LEN, GFP_KERNEL); + if (!tsc_resp) + goto e_free_tsc_req; + + req = kzalloc(sizeof(*req), GFP_KERNEL); + if (!req) + goto e_free_tsc_resp; + + rio = kzalloc(sizeof(*rio), GFP_KERNEL); + if (!rio) + goto e_free_req; + + mdesc = snp_msg_alloc(); + if (IS_ERR_OR_NULL(mdesc)) + goto e_free_rio; + + rc = snp_msg_init(mdesc, snp_vmpl); + if (rc) + goto e_free_mdesc; + + req->msg_version = MSG_HDR_VER; + req->msg_type = SNP_MSG_TSC_INFO_REQ; + req->vmpck_id = snp_vmpl; + req->req_buf = tsc_req; + req->req_sz = sizeof(*tsc_req); + req->resp_buf = (void *)tsc_resp; + req->resp_sz = sizeof(*tsc_resp) + AUTHTAG_LEN; + req->exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + rc = snp_send_guest_request(mdesc, req, rio); + if (rc) + goto e_request; + + pr_debug("%s: response status 0x%x scale 0x%llx offset 0x%llx factor 0x%x\n", + __func__, tsc_resp->status, tsc_resp->tsc_scale, tsc_resp->tsc_offset, + tsc_resp->tsc_factor); + + if (!tsc_resp->status) { + snp_tsc_scale = tsc_resp->tsc_scale; + snp_tsc_offset = tsc_resp->tsc_offset; + } else { + pr_err("Failed to get TSC info, response status 0x%x\n", tsc_resp->status); + rc = -EIO; + } + +e_request: + /* The response buffer contains sensitive data, explicitly clear it. */ + memzero_explicit(tsc_resp, sizeof(*tsc_resp) + AUTHTAG_LEN); +e_free_mdesc: + snp_msg_free(mdesc); +e_free_rio: + kfree(rio); +e_free_req: + kfree(req); + e_free_tsc_resp: + kfree(tsc_resp); +e_free_tsc_req: + kfree(tsc_req); + + return rc; +} + +void __init snp_secure_tsc_prepare(void) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) + return; + + if (snp_get_tsc_info()) { + pr_alert("Unable to retrieve Secure TSC info from ASP\n"); + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECURE_TSC); + } + + pr_debug("SecureTSC enabled"); +} + +static unsigned long securetsc_get_tsc_khz(void) +{ + return snp_tsc_freq_khz; +} + +void __init snp_secure_tsc_init(void) +{ + unsigned long long tsc_freq_mhz; + + if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) + return; + + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); + rdmsrl(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz); + snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000); + + x86_platform.calibrate_cpu = securetsc_get_tsc_khz; + x86_platform.calibrate_tsc = securetsc_get_tsc_khz; +} diff --git a/arch/x86/coco/sev/shared.c b/arch/x86/coco/sev/shared.c index 71de53194089..2e4122f8aa6b 100644 --- a/arch/x86/coco/sev/shared.c +++ b/arch/x86/coco/sev/shared.c @@ -498,7 +498,7 @@ static const struct snp_cpuid_table *snp_cpuid_get_table(void) * * Return: XSAVE area size on success, 0 otherwise. */ -static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) +static u32 __head snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); u64 xfeatures_found = 0; @@ -576,8 +576,9 @@ static void snp_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpui sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV); } -static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, - struct cpuid_leaf *leaf) +static int __head +snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + struct cpuid_leaf *leaf) { struct cpuid_leaf leaf_hv = *leaf; @@ -1140,6 +1141,16 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, bool rdtscp = (exit_code == SVM_EXIT_RDTSCP); enum es_result ret; + /* + * The hypervisor should not be intercepting RDTSC/RDTSCP when Secure + * TSC is enabled. A #VC exception will be generated if the RDTSC/RDTSCP + * instructions are being intercepted. If this should occur and Secure + * TSC is enabled, guest execution should be terminated as the guest + * cannot rely on the TSC value provided by the hypervisor. + */ + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + return ES_VMM_ERROR; + ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0); if (ret != ES_OK) return ret; @@ -1243,7 +1254,7 @@ static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svs __pval_terminate(pfn, action, page_size, ret, svsm_ret); } -static void svsm_pval_4k_page(unsigned long paddr, bool validate) +static void __head svsm_pval_4k_page(unsigned long paddr, bool validate) { struct svsm_pvalidate_call *pc; struct svsm_call call = {}; @@ -1275,12 +1286,13 @@ static void svsm_pval_4k_page(unsigned long paddr, bool validate) ret = svsm_perform_call_protocol(&call); if (ret) - svsm_pval_terminate(pc, ret, call.rax_out); + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); native_local_irq_restore(flags); } -static void pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, bool validate) +static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, + bool validate) { int ret; @@ -1293,7 +1305,7 @@ static void pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, bool val } else { ret = pvalidate(vaddr, RMP_PG_SIZE_4K, validate); if (ret) - __pval_terminate(PHYS_PFN(paddr), validate, RMP_PG_SIZE_4K, ret, 0); + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); } } diff --git a/arch/x86/coco/tdx/Makefile b/arch/x86/coco/tdx/Makefile index 2c7dcbf1458b..b3c47d3700e2 100644 --- a/arch/x86/coco/tdx/Makefile +++ b/arch/x86/coco/tdx/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y += tdx.o tdx-shared.o tdcall.o +obj-y += debug.o tdcall.o tdx.o tdx-shared.o diff --git a/arch/x86/coco/tdx/debug.c b/arch/x86/coco/tdx/debug.c new file mode 100644 index 000000000000..cef847c8bb67 --- /dev/null +++ b/arch/x86/coco/tdx/debug.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 + +#undef pr_fmt +#define pr_fmt(fmt) "tdx: " fmt + +#include +#include +#include + +#define DEF_TDX_ATTR_NAME(_name) [TDX_ATTR_##_name##_BIT] = __stringify(_name) + +static __initdata const char *tdx_attributes[] = { + DEF_TDX_ATTR_NAME(DEBUG), + DEF_TDX_ATTR_NAME(HGS_PLUS_PROF), + DEF_TDX_ATTR_NAME(PERF_PROF), + DEF_TDX_ATTR_NAME(PMT_PROF), + DEF_TDX_ATTR_NAME(ICSSD), + DEF_TDX_ATTR_NAME(LASS), + DEF_TDX_ATTR_NAME(SEPT_VE_DISABLE), + DEF_TDX_ATTR_NAME(MIGRTABLE), + DEF_TDX_ATTR_NAME(PKS), + DEF_TDX_ATTR_NAME(KL), + DEF_TDX_ATTR_NAME(TPA), + DEF_TDX_ATTR_NAME(PERFMON), +}; + +#define DEF_TD_CTLS_NAME(_name) [TD_CTLS_##_name##_BIT] = __stringify(_name) + +static __initdata const char *tdcs_td_ctls[] = { + DEF_TD_CTLS_NAME(PENDING_VE_DISABLE), + DEF_TD_CTLS_NAME(ENUM_TOPOLOGY), + DEF_TD_CTLS_NAME(VIRT_CPUID2), + DEF_TD_CTLS_NAME(REDUCE_VE), + DEF_TD_CTLS_NAME(LOCK), +}; + +void __init tdx_dump_attributes(u64 td_attr) +{ + pr_info("Attributes:"); + + for (int i = 0; i < ARRAY_SIZE(tdx_attributes); i++) { + if (!tdx_attributes[i]) + continue; + if (td_attr & BIT(i)) + pr_cont(" %s", tdx_attributes[i]); + td_attr &= ~BIT(i); + } + + if (td_attr) + pr_cont(" unknown:%#llx", td_attr); + pr_cont("\n"); + +} + +void __init tdx_dump_td_ctls(u64 td_ctls) +{ + pr_info("TD_CTLS:"); + + for (int i = 0; i < ARRAY_SIZE(tdcs_td_ctls); i++) { + if (!tdcs_td_ctls[i]) + continue; + if (td_ctls & BIT(i)) + pr_cont(" %s", tdcs_td_ctls[i]); + td_ctls &= ~BIT(i); + } + if (td_ctls) + pr_cont(" unknown:%#llx", td_ctls); + pr_cont("\n"); +} diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 0d9b090b4880..32809a06dab4 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -32,9 +32,6 @@ #define VE_GET_PORT_NUM(e) ((e) >> 16) #define VE_IS_IO_STRING(e) ((e) & BIT(4)) -#define ATTR_DEBUG BIT(0) -#define ATTR_SEPT_VE_DISABLE BIT(28) - /* TDX Module call error codes */ #define TDCALL_RETURN_CODE(a) ((a) >> 32) #define TDCALL_INVALID_OPERAND 0xc0000100 @@ -200,14 +197,14 @@ static void __noreturn tdx_panic(const char *msg) * * TDX 1.0 does not allow the guest to disable SEPT #VE on its own. The VMM * controls if the guest will receive such #VE with TD attribute - * ATTR_SEPT_VE_DISABLE. + * TDX_ATTR_SEPT_VE_DISABLE. * * Newer TDX modules allow the guest to control if it wants to receive SEPT * violation #VEs. * * Check if the feature is available and disable SEPT #VE if possible. * - * If the TD is allowed to disable/enable SEPT #VEs, the ATTR_SEPT_VE_DISABLE + * If the TD is allowed to disable/enable SEPT #VEs, the TDX_ATTR_SEPT_VE_DISABLE * attribute is no longer reliable. It reflects the initial state of the * control for the TD, but it will not be updated if someone (e.g. bootloader) * changes it before the kernel starts. Kernel must check TDCS_TD_CTLS bit to @@ -216,14 +213,14 @@ static void __noreturn tdx_panic(const char *msg) static void disable_sept_ve(u64 td_attr) { const char *msg = "TD misconfiguration: SEPT #VE has to be disabled"; - bool debug = td_attr & ATTR_DEBUG; + bool debug = td_attr & TDX_ATTR_DEBUG; u64 config, controls; /* Is this TD allowed to disable SEPT #VE */ tdg_vm_rd(TDCS_CONFIG_FLAGS, &config); if (!(config & TDCS_CONFIG_FLEXIBLE_PENDING_VE)) { /* No SEPT #VE controls for the guest: check the attribute */ - if (td_attr & ATTR_SEPT_VE_DISABLE) + if (td_attr & TDX_ATTR_SEPT_VE_DISABLE) return; /* Relax SEPT_VE_DISABLE check for debug TD for backtraces */ @@ -274,6 +271,20 @@ static void enable_cpu_topology_enumeration(void) tdg_vm_wr(TDCS_TD_CTLS, TD_CTLS_ENUM_TOPOLOGY, TD_CTLS_ENUM_TOPOLOGY); } +static void reduce_unnecessary_ve(void) +{ + u64 err = tdg_vm_wr(TDCS_TD_CTLS, TD_CTLS_REDUCE_VE, TD_CTLS_REDUCE_VE); + + if (err == TDX_SUCCESS) + return; + + /* + * Enabling REDUCE_VE includes ENUM_TOPOLOGY. Only try to + * enable ENUM_TOPOLOGY if REDUCE_VE was not successful. + */ + enable_cpu_topology_enumeration(); +} + static void tdx_setup(u64 *cc_mask) { struct tdx_module_args args = {}; @@ -305,7 +316,8 @@ static void tdx_setup(u64 *cc_mask) tdg_vm_wr(TDCS_NOTIFY_ENABLES, 0, -1ULL); disable_sept_ve(td_attr); - enable_cpu_topology_enumeration(); + + reduce_unnecessary_ve(); } /* @@ -1025,6 +1037,20 @@ static void tdx_kexec_finish(void) } } +static __init void tdx_announce(void) +{ + struct tdx_module_args args = {}; + u64 controls; + + pr_info("Guest detected\n"); + + tdcall(TDG_VP_INFO, &args); + tdx_dump_attributes(args.rdx); + + tdg_vm_rd(TDCS_TD_CTLS, &controls); + tdx_dump_td_ctls(controls); +} + void __init tdx_early_init(void) { u64 cc_mask; @@ -1094,5 +1120,5 @@ void __init tdx_early_init(void) */ x86_cpuinit.parallel_bringup = false; - pr_info("Guest detected\n"); + tdx_announce(); } diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig index 3d2e38ba5240..4757bf922075 100644 --- a/arch/x86/crypto/Kconfig +++ b/arch/x86/crypto/Kconfig @@ -492,36 +492,4 @@ config CRYPTO_GHASH_CLMUL_NI_INTEL Architecture: x86_64 using: - CLMUL-NI (carry-less multiplication new instructions) -config CRYPTO_CRC32C_INTEL - tristate "CRC32c (SSE4.2/PCLMULQDQ)" - depends on X86 - select CRYPTO_HASH - help - CRC32c CRC algorithm with the iSCSI polynomial (RFC 3385 and RFC 3720) - - Architecture: x86 (32-bit and 64-bit) using: - - SSE4.2 (Streaming SIMD Extensions 4.2) CRC32 instruction - - PCLMULQDQ (carry-less multiplication) - -config CRYPTO_CRC32_PCLMUL - tristate "CRC32 (PCLMULQDQ)" - depends on X86 - select CRYPTO_HASH - select CRC32 - help - CRC32 CRC algorithm (IEEE 802.3) - - Architecture: x86 (32-bit and 64-bit) using: - - PCLMULQDQ (carry-less multiplication) - -config CRYPTO_CRCT10DIF_PCLMUL - tristate "CRCT10DIF (PCLMULQDQ)" - depends on X86 && 64BIT && CRC_T10DIF - select CRYPTO_HASH - help - CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF) - - Architecture: x86_64 using: - - PCLMULQDQ (carry-less multiplication) - endmenu diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 53b4a277809e..07b00bfca64b 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -75,16 +75,6 @@ ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o obj-$(CONFIG_CRYPTO_POLYVAL_CLMUL_NI) += polyval-clmulni.o polyval-clmulni-y := polyval-clmulni_asm.o polyval-clmulni_glue.o -obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o -crc32c-intel-y := crc32c-intel_glue.o -crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o - -obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o -crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o - -obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o -crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o - obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o targets += poly1305-x86_64-cryptogams.S diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index c19d8e3d96a3..01fa568dc5fc 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -240,7 +240,6 @@ static struct aead_alg crypto_aegis128_aesni_alg = { .cra_blocksize = 1, .cra_ctxsize = sizeof(struct aegis_ctx) + __alignof__(struct aegis_ctx), - .cra_alignmask = 0, .cra_priority = 400, .cra_name = "__aegis128", diff --git a/arch/x86/crypto/aes-gcm-avx10-x86_64.S b/arch/x86/crypto/aes-gcm-avx10-x86_64.S index 97e0ee515fc5..02ee11083d4f 100644 --- a/arch/x86/crypto/aes-gcm-avx10-x86_64.S +++ b/arch/x86/crypto/aes-gcm-avx10-x86_64.S @@ -88,7 +88,7 @@ // A shuffle mask that reflects the bytes of 16-byte blocks .Lbswap_mask: - .octa 0x000102030405060708090a0b0c0d0e0f + .octa 0x000102030405060708090a0b0c0d0e0f // This is the GHASH reducing polynomial without its constant term, i.e. // x^128 + x^7 + x^2 + x, represented using the backwards mapping @@ -384,8 +384,8 @@ vpshufd $0xd3, H_CUR_XMM, %xmm0 vpsrad $31, %xmm0, %xmm0 vpaddq H_CUR_XMM, H_CUR_XMM, H_CUR_XMM - vpand .Lgfpoly_and_internal_carrybit(%rip), %xmm0, %xmm0 - vpxor %xmm0, H_CUR_XMM, H_CUR_XMM + // H_CUR_XMM ^= xmm0 & gfpoly_and_internal_carrybit + vpternlogd $0x78, .Lgfpoly_and_internal_carrybit(%rip), %xmm0, H_CUR_XMM // Load the gfpoly constant. vbroadcasti32x4 .Lgfpoly(%rip), GFPOLY @@ -562,6 +562,32 @@ vpxord RNDKEY0, V3, V3 .endm +// Do the last AES round for four vectors of counter blocks V0-V3, XOR source +// data with the resulting keystream, and write the result to DST and +// GHASHDATA[0-3]. (Implementation differs slightly, but has the same effect.) +.macro _aesenclast_and_xor_4x + // XOR the source data with the last round key, saving the result in + // GHASHDATA[0-3]. This reduces latency by taking advantage of the + // property vaesenclast(key, a) ^ b == vaesenclast(key ^ b, a). + vpxord 0*VL(SRC), RNDKEYLAST, GHASHDATA0 + vpxord 1*VL(SRC), RNDKEYLAST, GHASHDATA1 + vpxord 2*VL(SRC), RNDKEYLAST, GHASHDATA2 + vpxord 3*VL(SRC), RNDKEYLAST, GHASHDATA3 + + // Do the last AES round. This handles the XOR with the source data + // too, as per the optimization described above. + vaesenclast GHASHDATA0, V0, GHASHDATA0 + vaesenclast GHASHDATA1, V1, GHASHDATA1 + vaesenclast GHASHDATA2, V2, GHASHDATA2 + vaesenclast GHASHDATA3, V3, GHASHDATA3 + + // Store the en/decrypted data to DST. + vmovdqu8 GHASHDATA0, 0*VL(DST) + vmovdqu8 GHASHDATA1, 1*VL(DST) + vmovdqu8 GHASHDATA2, 2*VL(DST) + vmovdqu8 GHASHDATA3, 3*VL(DST) +.endm + // void aes_gcm_{enc,dec}_update_##suffix(const struct aes_gcm_key_avx10 *key, // const u32 le_ctr[4], u8 ghash_acc[16], // const u8 *src, u8 *dst, int datalen); @@ -640,7 +666,7 @@ // LE_CTR contains the next set of little-endian counter blocks. .set LE_CTR, V12 - // RNDKEY0, RNDKEYLAST, and RNDKEY_M[9-5] contain cached AES round keys, + // RNDKEY0, RNDKEYLAST, and RNDKEY_M[9-1] contain cached AES round keys, // copied to all 128-bit lanes. RNDKEY0 is the zero-th round key, // RNDKEYLAST the last, and RNDKEY_M\i the one \i-th from the last. .set RNDKEY0, V13 @@ -650,15 +676,10 @@ .set RNDKEY_M7, V17 .set RNDKEY_M6, V18 .set RNDKEY_M5, V19 - - // RNDKEYLAST[0-3] temporarily store the last AES round key XOR'd with - // the corresponding block of source data. This is useful because - // vaesenclast(key, a) ^ b == vaesenclast(key ^ b, a), and key ^ b can - // be computed in parallel with the AES rounds. - .set RNDKEYLAST0, V20 - .set RNDKEYLAST1, V21 - .set RNDKEYLAST2, V22 - .set RNDKEYLAST3, V23 + .set RNDKEY_M4, V20 + .set RNDKEY_M3, V21 + .set RNDKEY_M2, V22 + .set RNDKEY_M1, V23 // GHASHTMP[0-2] are temporary variables used by _ghash_step_4x. These // cannot coincide with anything used for AES encryption, since for @@ -713,7 +734,7 @@ // Pre-subtracting 4*VL from DATALEN saves an instruction from the main // loop and also ensures that at least one write always occurs to // DATALEN, zero-extending it and allowing DATALEN64 to be used later. - sub $4*VL, DATALEN + add $-4*VL, DATALEN // shorter than 'sub 4*VL' when VL=32 jl .Lcrypt_loop_4x_done\@ // Load powers of the hash key. @@ -748,26 +769,15 @@ add $16, %rax cmp %rax, RNDKEYLAST_PTR jne 1b - vpxord 0*VL(SRC), RNDKEYLAST, RNDKEYLAST0 - vpxord 1*VL(SRC), RNDKEYLAST, RNDKEYLAST1 - vpxord 2*VL(SRC), RNDKEYLAST, RNDKEYLAST2 - vpxord 3*VL(SRC), RNDKEYLAST, RNDKEYLAST3 - vaesenclast RNDKEYLAST0, V0, GHASHDATA0 - vaesenclast RNDKEYLAST1, V1, GHASHDATA1 - vaesenclast RNDKEYLAST2, V2, GHASHDATA2 - vaesenclast RNDKEYLAST3, V3, GHASHDATA3 - vmovdqu8 GHASHDATA0, 0*VL(DST) - vmovdqu8 GHASHDATA1, 1*VL(DST) - vmovdqu8 GHASHDATA2, 2*VL(DST) - vmovdqu8 GHASHDATA3, 3*VL(DST) - add $4*VL, SRC - add $4*VL, DST - sub $4*VL, DATALEN + _aesenclast_and_xor_4x + sub $-4*VL, SRC // shorter than 'add 4*VL' when VL=32 + sub $-4*VL, DST + add $-4*VL, DATALEN jl .Lghash_last_ciphertext_4x\@ .endif // Cache as many additional AES round keys as possible. -.irp i, 9,8,7,6,5 +.irp i, 9,8,7,6,5,4,3,2,1 vbroadcasti32x4 -\i*16(RNDKEYLAST_PTR), RNDKEY_M\i .endr @@ -799,50 +809,17 @@ _vaesenc_4x RNDKEY 128: - // XOR the source data with the last round key, saving the result in - // RNDKEYLAST[0-3]. This reduces latency by taking advantage of the - // property vaesenclast(key, a) ^ b == vaesenclast(key ^ b, a). -.if \enc - vpxord 0*VL(SRC), RNDKEYLAST, RNDKEYLAST0 - vpxord 1*VL(SRC), RNDKEYLAST, RNDKEYLAST1 - vpxord 2*VL(SRC), RNDKEYLAST, RNDKEYLAST2 - vpxord 3*VL(SRC), RNDKEYLAST, RNDKEYLAST3 -.else - vpxord GHASHDATA0, RNDKEYLAST, RNDKEYLAST0 - vpxord GHASHDATA1, RNDKEYLAST, RNDKEYLAST1 - vpxord GHASHDATA2, RNDKEYLAST, RNDKEYLAST2 - vpxord GHASHDATA3, RNDKEYLAST, RNDKEYLAST3 -.endif - // Finish the AES encryption of the counter blocks in V0-V3, interleaved // with the GHASH update of the ciphertext blocks in GHASHDATA[0-3]. -.irp i, 9,8,7,6,5 +.irp i, 9,8,7,6,5,4,3,2,1 + _ghash_step_4x (9 - \i) _vaesenc_4x RNDKEY_M\i - _ghash_step_4x (9 - \i) -.endr -.irp i, 4,3,2,1 - vbroadcasti32x4 -\i*16(RNDKEYLAST_PTR), RNDKEY - _vaesenc_4x RNDKEY - _ghash_step_4x (9 - \i) .endr _ghash_step_4x 9 - - // Do the last AES round. This handles the XOR with the source data - // too, as per the optimization described above. - vaesenclast RNDKEYLAST0, V0, GHASHDATA0 - vaesenclast RNDKEYLAST1, V1, GHASHDATA1 - vaesenclast RNDKEYLAST2, V2, GHASHDATA2 - vaesenclast RNDKEYLAST3, V3, GHASHDATA3 - - // Store the en/decrypted data to DST. - vmovdqu8 GHASHDATA0, 0*VL(DST) - vmovdqu8 GHASHDATA1, 1*VL(DST) - vmovdqu8 GHASHDATA2, 2*VL(DST) - vmovdqu8 GHASHDATA3, 3*VL(DST) - - add $4*VL, SRC - add $4*VL, DST - sub $4*VL, DATALEN + _aesenclast_and_xor_4x + sub $-4*VL, SRC // shorter than 'add 4*VL' when VL=32 + sub $-4*VL, DST + add $-4*VL, DATALEN jge .Lcrypt_loop_4x\@ .if \enc @@ -856,7 +833,7 @@ .Lcrypt_loop_4x_done\@: // Undo the extra subtraction by 4*VL and check whether data remains. - add $4*VL, DATALEN + sub $-4*VL, DATALEN // shorter than 'add 4*VL' when VL=32 jz .Ldone\@ // The data length isn't a multiple of 4*VL. Process the remaining data @@ -940,7 +917,7 @@ // GHASH. However, any such blocks are all-zeroes, and the values that // they're multiplied with are also all-zeroes. Therefore they just add // 0 * 0 = 0 to the final GHASH result, which makes no difference. - vmovdqu8 (POWERS_PTR), H_POW1 + vmovdqu8 (POWERS_PTR), H_POW1 .if \enc vmovdqu8 V0, V1{%k1}{z} .endif diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S index 48f97b79f7a9..8a3e23fbcf85 100644 --- a/arch/x86/crypto/aes-xts-avx-x86_64.S +++ b/arch/x86/crypto/aes-xts-avx-x86_64.S @@ -80,22 +80,6 @@ .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 .text -// Function parameters -.set KEY, %rdi // Initially points to crypto_aes_ctx, then is - // advanced to point to 7th-from-last round key -.set SRC, %rsi // Pointer to next source data -.set DST, %rdx // Pointer to next destination data -.set LEN, %ecx // Remaining length in bytes -.set LEN8, %cl -.set LEN64, %rcx -.set TWEAK, %r8 // Pointer to next tweak - -// %rax holds the AES key length in bytes. -.set KEYLEN, %eax -.set KEYLEN64, %rax - -// %r9-r11 are available as temporaries. - .macro _define_Vi i .if VL == 16 .set V\i, %xmm\i @@ -112,41 +96,31 @@ // Define register aliases V0-V15, or V0-V31 if all 32 SIMD registers // are available, that map to the xmm, ymm, or zmm registers according // to the selected Vector Length (VL). - _define_Vi 0 - _define_Vi 1 - _define_Vi 2 - _define_Vi 3 - _define_Vi 4 - _define_Vi 5 - _define_Vi 6 - _define_Vi 7 - _define_Vi 8 - _define_Vi 9 - _define_Vi 10 - _define_Vi 11 - _define_Vi 12 - _define_Vi 13 - _define_Vi 14 - _define_Vi 15 +.irp i, 0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 + _define_Vi \i +.endr .if USE_AVX10 - _define_Vi 16 - _define_Vi 17 - _define_Vi 18 - _define_Vi 19 - _define_Vi 20 - _define_Vi 21 - _define_Vi 22 - _define_Vi 23 - _define_Vi 24 - _define_Vi 25 - _define_Vi 26 - _define_Vi 27 - _define_Vi 28 - _define_Vi 29 - _define_Vi 30 - _define_Vi 31 +.irp i, 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31 + _define_Vi \i +.endr .endif + // Function parameters + .set KEY, %rdi // Initially points to crypto_aes_ctx, then is + // advanced to point to 7th-from-last round key + .set SRC, %rsi // Pointer to next source data + .set DST, %rdx // Pointer to next destination data + .set LEN, %ecx // Remaining length in bytes + .set LEN8, %cl + .set LEN64, %rcx + .set TWEAK, %r8 // Pointer to next tweak + + // %rax holds the AES key length in bytes. + .set KEYLEN, %eax + .set KEYLEN64, %rax + + // %r9-r11 are available as temporaries. + // V0-V3 hold the data blocks during the main loop, or temporary values // otherwise. V4-V5 hold temporary values. @@ -214,6 +188,7 @@ .endm // Move a vector between memory and a register. +// The register operand must be in the first 16 vector registers. .macro _vmovdqu src, dst .if VL < 64 vmovdqu \src, \dst @@ -234,11 +209,12 @@ .endm // XOR two vectors together. +// Any register operands must be in the first 16 vector registers. .macro _vpxor src1, src2, dst -.if USE_AVX10 - vpxord \src1, \src2, \dst -.else +.if VL < 64 vpxor \src1, \src2, \dst +.else + vpxord \src1, \src2, \dst .endif .endm @@ -259,8 +235,12 @@ vpshufd $0x13, \src, \tmp vpaddq \src, \src, \dst vpsrad $31, \tmp, \tmp +.if USE_AVX10 + vpternlogd $0x78, GF_POLY_XMM, \tmp, \dst +.else vpand GF_POLY_XMM, \tmp, \tmp vpxor \tmp, \dst, \dst +.endif .endm // Given the XTS tweak(s) in the vector \src, compute the next vector of @@ -369,9 +349,14 @@ // Do one step in computing the next set of tweaks using the VPCLMULQDQ method // (the same method _next_tweakvec uses for VL > 16). This means multiplying -// each tweak by x^(4*VL/16) independently. Since 4*VL/16 is a multiple of 8 -// when VL > 16 (which it is here), the needed shift amounts are byte-aligned, -// which allows the use of vpsrldq and vpslldq to do 128-bit wide shifts. +// each tweak by x^(4*VL/16) independently. +// +// Since 4*VL/16 is a multiple of 8 when VL > 16 (which it is here), the needed +// shift amounts are byte-aligned, which allows the use of vpsrldq and vpslldq +// to do 128-bit wide shifts. The 128-bit left shift (vpslldq) saves +// instructions directly. The 128-bit right shift (vpsrldq) performs better +// than a 64-bit right shift on Intel CPUs in the context where it is used here, +// because it runs on a different execution port from the AES instructions. .macro _tweak_step_pclmul i .if \i == 0 vpsrldq $(128 - 4*VL/16) / 8, TWEAK0, NEXT_TWEAK0 @@ -406,7 +391,7 @@ // \i that include at least 0 through 19, then 1000 which signals the last step. // // This is used to interleave the computation of the next set of tweaks with the -// AES en/decryptions, which increases performance in some cases. +// AES en/decryptions, which increases performance in some cases. Clobbers V5. .macro _tweak_step i .if VL == 16 _tweak_step_mulx \i @@ -443,9 +428,10 @@ // the last round needs different instructions. // // An alternative approach would be to roll up all the round loops. We - // don't do that because it isn't compatible with caching the round keys - // in registers which we do when possible (see below), and also because - // it seems unwise to rely *too* heavily on the CPU's branch predictor. + // don't do that because (a) it isn't compatible with caching the round + // keys in registers which we do when possible (see below), (b) we + // interleave the AES rounds with the XTS tweak computation, and (c) it + // seems unwise to rely *too* heavily on the CPU's branch predictor. lea OFFS-16(KEY, KEYLEN64, 4), KEY // If all 32 SIMD registers are available, cache all the round keys. @@ -472,90 +458,94 @@ .endif .endm -// Do a single round of AES encryption (if \enc==1) or decryption (if \enc==0) -// on the block(s) in \data using the round key(s) in \key. The register length -// determines the number of AES blocks en/decrypted. -.macro _vaes enc, last, key, data +// Do a single non-last round of AES encryption (if \enc==1) or decryption (if +// \enc==0) on the block(s) in \data using the round key(s) in \key. The +// register length determines the number of AES blocks en/decrypted. +.macro _vaes enc, key, data .if \enc -.if \last - vaesenclast \key, \data, \data -.else vaesenc \key, \data, \data -.endif -.else -.if \last - vaesdeclast \key, \data, \data .else vaesdec \key, \data, \data .endif +.endm + +// Same as _vaes, but does the last round. +.macro _vaeslast enc, key, data +.if \enc + vaesenclast \key, \data, \data +.else + vaesdeclast \key, \data, \data .endif .endm -// Do a single round of AES en/decryption on the block(s) in \data, using the -// same key for all block(s). The round key is loaded from the appropriate -// register or memory location for round \i. May clobber V4. -.macro _vaes_1x enc, last, i, xmm_suffix, data +// Do a single non-last round of AES en/decryption on the block(s) in \data, +// using the same key for all block(s). The round key is loaded from the +// appropriate register or memory location for round \i. May clobber \tmp. +.macro _vaes_1x enc, i, xmm_suffix, data, tmp .if USE_AVX10 - _vaes \enc, \last, KEY\i\xmm_suffix, \data + _vaes \enc, KEY\i\xmm_suffix, \data .else .ifnb \xmm_suffix - _vaes \enc, \last, (\i-7)*16(KEY), \data + _vaes \enc, (\i-7)*16(KEY), \data .else - _vbroadcast128 (\i-7)*16(KEY), V4 - _vaes \enc, \last, V4, \data + _vbroadcast128 (\i-7)*16(KEY), \tmp + _vaes \enc, \tmp, \data .endif .endif .endm -// Do a single round of AES en/decryption on the blocks in registers V0-V3, -// using the same key for all blocks. The round key is loaded from the +// Do a single non-last round of AES en/decryption on the blocks in registers +// V0-V3, using the same key for all blocks. The round key is loaded from the // appropriate register or memory location for round \i. In addition, does two -// steps of the computation of the next set of tweaks. May clobber V4. -.macro _vaes_4x enc, last, i +// steps of the computation of the next set of tweaks. May clobber V4 and V5. +.macro _vaes_4x enc, i .if USE_AVX10 _tweak_step (2*(\i-5)) - _vaes \enc, \last, KEY\i, V0 - _vaes \enc, \last, KEY\i, V1 + _vaes \enc, KEY\i, V0 + _vaes \enc, KEY\i, V1 _tweak_step (2*(\i-5) + 1) - _vaes \enc, \last, KEY\i, V2 - _vaes \enc, \last, KEY\i, V3 + _vaes \enc, KEY\i, V2 + _vaes \enc, KEY\i, V3 .else _vbroadcast128 (\i-7)*16(KEY), V4 _tweak_step (2*(\i-5)) - _vaes \enc, \last, V4, V0 - _vaes \enc, \last, V4, V1 + _vaes \enc, V4, V0 + _vaes \enc, V4, V1 _tweak_step (2*(\i-5) + 1) - _vaes \enc, \last, V4, V2 - _vaes \enc, \last, V4, V3 + _vaes \enc, V4, V2 + _vaes \enc, V4, V3 .endif .endm // Do tweaked AES en/decryption (i.e., XOR with \tweak, then AES en/decrypt, // then XOR with \tweak again) of the block(s) in \data. To process a single // block, use xmm registers and set \xmm_suffix=_XMM. To process a vector of -// length VL, use V* registers and leave \xmm_suffix empty. May clobber V4. -.macro _aes_crypt enc, xmm_suffix, tweak, data +// length VL, use V* registers and leave \xmm_suffix empty. Clobbers \tmp. +.macro _aes_crypt enc, xmm_suffix, tweak, data, tmp _xor3 KEY0\xmm_suffix, \tweak, \data cmp $24, KEYLEN jl .Laes128\@ je .Laes192\@ - _vaes_1x \enc, 0, 1, \xmm_suffix, \data - _vaes_1x \enc, 0, 2, \xmm_suffix, \data + _vaes_1x \enc, 1, \xmm_suffix, \data, tmp=\tmp + _vaes_1x \enc, 2, \xmm_suffix, \data, tmp=\tmp .Laes192\@: - _vaes_1x \enc, 0, 3, \xmm_suffix, \data - _vaes_1x \enc, 0, 4, \xmm_suffix, \data + _vaes_1x \enc, 3, \xmm_suffix, \data, tmp=\tmp + _vaes_1x \enc, 4, \xmm_suffix, \data, tmp=\tmp .Laes128\@: - _vaes_1x \enc, 0, 5, \xmm_suffix, \data - _vaes_1x \enc, 0, 6, \xmm_suffix, \data - _vaes_1x \enc, 0, 7, \xmm_suffix, \data - _vaes_1x \enc, 0, 8, \xmm_suffix, \data - _vaes_1x \enc, 0, 9, \xmm_suffix, \data - _vaes_1x \enc, 0, 10, \xmm_suffix, \data - _vaes_1x \enc, 0, 11, \xmm_suffix, \data - _vaes_1x \enc, 0, 12, \xmm_suffix, \data - _vaes_1x \enc, 0, 13, \xmm_suffix, \data - _vaes_1x \enc, 1, 14, \xmm_suffix, \data - _vpxor \tweak, \data, \data +.irp i, 5,6,7,8,9,10,11,12,13 + _vaes_1x \enc, \i, \xmm_suffix, \data, tmp=\tmp +.endr +.if USE_AVX10 + vpxord KEY14\xmm_suffix, \tweak, \tmp +.else +.ifnb \xmm_suffix + vpxor 7*16(KEY), \tweak, \tmp +.else + _vbroadcast128 7*16(KEY), \tmp + vpxor \tweak, \tmp, \tmp +.endif +.endif + _vaeslast \enc, \tmp, \data .endm .macro _aes_xts_crypt enc @@ -581,7 +571,7 @@ // Compute the first set of tweaks TWEAK[0-3]. _compute_first_set_of_tweaks - sub $4*VL, LEN + add $-4*VL, LEN // shorter than 'sub 4*VL' when VL=32 jl .Lhandle_remainder\@ .Lmain_loop\@: @@ -589,10 +579,10 @@ // XOR each source block with its tweak and the zero-th round key. .if USE_AVX10 - vmovdqu8 0*VL(SRC), V0 - vmovdqu8 1*VL(SRC), V1 - vmovdqu8 2*VL(SRC), V2 - vmovdqu8 3*VL(SRC), V3 + _vmovdqu 0*VL(SRC), V0 + _vmovdqu 1*VL(SRC), V1 + _vmovdqu 2*VL(SRC), V2 + _vmovdqu 3*VL(SRC), V3 vpternlogd $0x96, TWEAK0, KEY0, V0 vpternlogd $0x96, TWEAK1, KEY0, V1 vpternlogd $0x96, TWEAK2, KEY0, V2 @@ -612,28 +602,43 @@ je .Laes192\@ // Do all the AES rounds on the data blocks, interleaved with // the computation of the next set of tweaks. - _vaes_4x \enc, 0, 1 - _vaes_4x \enc, 0, 2 + _vaes_4x \enc, 1 + _vaes_4x \enc, 2 .Laes192\@: - _vaes_4x \enc, 0, 3 - _vaes_4x \enc, 0, 4 + _vaes_4x \enc, 3 + _vaes_4x \enc, 4 .Laes128\@: - _vaes_4x \enc, 0, 5 - _vaes_4x \enc, 0, 6 - _vaes_4x \enc, 0, 7 - _vaes_4x \enc, 0, 8 - _vaes_4x \enc, 0, 9 - _vaes_4x \enc, 0, 10 - _vaes_4x \enc, 0, 11 - _vaes_4x \enc, 0, 12 - _vaes_4x \enc, 0, 13 - _vaes_4x \enc, 1, 14 - - // XOR in the tweaks again. - _vpxor TWEAK0, V0, V0 - _vpxor TWEAK1, V1, V1 - _vpxor TWEAK2, V2, V2 - _vpxor TWEAK3, V3, V3 +.irp i, 5,6,7,8,9,10,11,12,13 + _vaes_4x \enc, \i +.endr + // Do the last AES round, then XOR the results with the tweaks again. + // Reduce latency by doing the XOR before the vaesenclast, utilizing the + // property vaesenclast(key, a) ^ b == vaesenclast(key ^ b, a) + // (and likewise for vaesdeclast). +.if USE_AVX10 + _tweak_step 18 + _tweak_step 19 + vpxord TWEAK0, KEY14, V4 + vpxord TWEAK1, KEY14, V5 + _vaeslast \enc, V4, V0 + _vaeslast \enc, V5, V1 + vpxord TWEAK2, KEY14, V4 + vpxord TWEAK3, KEY14, V5 + _vaeslast \enc, V4, V2 + _vaeslast \enc, V5, V3 +.else + _vbroadcast128 7*16(KEY), V4 + _tweak_step 18 // uses V5 + _tweak_step 19 // uses V5 + vpxor TWEAK0, V4, V5 + _vaeslast \enc, V5, V0 + vpxor TWEAK1, V4, V5 + _vaeslast \enc, V5, V1 + vpxor TWEAK2, V4, V5 + vpxor TWEAK3, V4, V4 + _vaeslast \enc, V5, V2 + _vaeslast \enc, V4, V3 +.endif // Store the destination blocks. _vmovdqu V0, 0*VL(DST) @@ -644,9 +649,9 @@ // Finish computing the next set of tweaks. _tweak_step 1000 - add $4*VL, SRC - add $4*VL, DST - sub $4*VL, LEN + sub $-4*VL, SRC // shorter than 'add 4*VL' when VL=32 + sub $-4*VL, DST + add $-4*VL, LEN jge .Lmain_loop\@ // Check for the uncommon case where the data length isn't a multiple of @@ -670,7 +675,7 @@ jl .Lvec_at_a_time_done\@ .Lvec_at_a_time\@: _vmovdqu (SRC), V0 - _aes_crypt \enc, , TWEAK0, V0 + _aes_crypt \enc, , TWEAK0, V0, tmp=V1 _vmovdqu V0, (DST) _next_tweakvec TWEAK0, V0, V1, TWEAK0 add $VL, SRC @@ -687,7 +692,7 @@ jl .Lblock_at_a_time_done\@ .Lblock_at_a_time\@: vmovdqu (SRC), %xmm0 - _aes_crypt \enc, _XMM, TWEAK0_XMM, %xmm0 + _aes_crypt \enc, _XMM, TWEAK0_XMM, %xmm0, tmp=%xmm1 vmovdqu %xmm0, (DST) _next_tweak TWEAK0_XMM, %xmm0, TWEAK0_XMM add $16, SRC @@ -715,7 +720,7 @@ // Do it now by advancing the tweak and decrypting the last full block. _next_tweak TWEAK0_XMM, %xmm0, TWEAK1_XMM vmovdqu (SRC), %xmm0 - _aes_crypt \enc, _XMM, TWEAK1_XMM, %xmm0 + _aes_crypt \enc, _XMM, TWEAK1_XMM, %xmm0, tmp=%xmm1 .endif .if USE_AVX10 @@ -758,47 +763,49 @@ vpblendvb %xmm3, %xmm0, %xmm1, %xmm0 .endif // En/decrypt again and store the last full block. - _aes_crypt \enc, _XMM, TWEAK0_XMM, %xmm0 + _aes_crypt \enc, _XMM, TWEAK0_XMM, %xmm0, tmp=%xmm1 vmovdqu %xmm0, (DST) jmp .Ldone\@ .endm // void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key, // u8 iv[AES_BLOCK_SIZE]); +// +// Encrypt |iv| using the AES key |tweak_key| to get the first tweak. Assumes +// that the CPU supports AES-NI and AVX, but not necessarily VAES or AVX10. SYM_TYPED_FUNC_START(aes_xts_encrypt_iv) - vmovdqu (%rsi), %xmm0 - vpxor (%rdi), %xmm0, %xmm0 - movl 480(%rdi), %eax // AES key length - lea -16(%rdi, %rax, 4), %rdi - cmp $24, %eax + .set TWEAK_KEY, %rdi + .set IV, %rsi + .set KEYLEN, %eax + .set KEYLEN64, %rax + + vmovdqu (IV), %xmm0 + vpxor (TWEAK_KEY), %xmm0, %xmm0 + movl 480(TWEAK_KEY), KEYLEN + lea -16(TWEAK_KEY, KEYLEN64, 4), TWEAK_KEY + cmp $24, KEYLEN jl .Lencrypt_iv_aes128 je .Lencrypt_iv_aes192 - vaesenc -6*16(%rdi), %xmm0, %xmm0 - vaesenc -5*16(%rdi), %xmm0, %xmm0 + vaesenc -6*16(TWEAK_KEY), %xmm0, %xmm0 + vaesenc -5*16(TWEAK_KEY), %xmm0, %xmm0 .Lencrypt_iv_aes192: - vaesenc -4*16(%rdi), %xmm0, %xmm0 - vaesenc -3*16(%rdi), %xmm0, %xmm0 + vaesenc -4*16(TWEAK_KEY), %xmm0, %xmm0 + vaesenc -3*16(TWEAK_KEY), %xmm0, %xmm0 .Lencrypt_iv_aes128: - vaesenc -2*16(%rdi), %xmm0, %xmm0 - vaesenc -1*16(%rdi), %xmm0, %xmm0 - vaesenc 0*16(%rdi), %xmm0, %xmm0 - vaesenc 1*16(%rdi), %xmm0, %xmm0 - vaesenc 2*16(%rdi), %xmm0, %xmm0 - vaesenc 3*16(%rdi), %xmm0, %xmm0 - vaesenc 4*16(%rdi), %xmm0, %xmm0 - vaesenc 5*16(%rdi), %xmm0, %xmm0 - vaesenc 6*16(%rdi), %xmm0, %xmm0 - vaesenclast 7*16(%rdi), %xmm0, %xmm0 - vmovdqu %xmm0, (%rsi) +.irp i, -2,-1,0,1,2,3,4,5,6 + vaesenc \i*16(TWEAK_KEY), %xmm0, %xmm0 +.endr + vaesenclast 7*16(TWEAK_KEY), %xmm0, %xmm0 + vmovdqu %xmm0, (IV) RET SYM_FUNC_END(aes_xts_encrypt_iv) // Below are the actual AES-XTS encryption and decryption functions, // instantiated from the above macro. They all have the following prototype: // -// void (*xts_asm_func)(const struct crypto_aes_ctx *key, -// const u8 *src, u8 *dst, unsigned int len, -// u8 tweak[AES_BLOCK_SIZE]); +// void (*xts_crypt_func)(const struct crypto_aes_ctx *key, +// const u8 *src, u8 *dst, int len, +// u8 tweak[AES_BLOCK_SIZE]); // // |key| is the data key. |tweak| contains the next tweak; the encryption of // the original IV with the tweak key was already done. This function supports diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index fbf43482e1f5..11e95fc62636 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -505,7 +505,7 @@ static int xts_setkey_aesni(struct crypto_skcipher *tfm, const u8 *key, typedef void (*xts_encrypt_iv_func)(const struct crypto_aes_ctx *tweak_key, u8 iv[AES_BLOCK_SIZE]); typedef void (*xts_crypt_func)(const struct crypto_aes_ctx *key, - const u8 *src, u8 *dst, unsigned int len, + const u8 *src, u8 *dst, int len, u8 tweak[AES_BLOCK_SIZE]); /* This handles cases where the source and/or destination span pages. */ @@ -624,14 +624,14 @@ static void aesni_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key, } static void aesni_xts_encrypt(const struct crypto_aes_ctx *key, - const u8 *src, u8 *dst, unsigned int len, + const u8 *src, u8 *dst, int len, u8 tweak[AES_BLOCK_SIZE]) { aesni_xts_enc(key, dst, src, len, tweak); } static void aesni_xts_decrypt(const struct crypto_aes_ctx *key, - const u8 *src, u8 *dst, unsigned int len, + const u8 *src, u8 *dst, int len, u8 tweak[AES_BLOCK_SIZE]) { aesni_xts_dec(key, dst, src, len, tweak); @@ -790,10 +790,10 @@ asmlinkage void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key, \ asmlinkage void \ aes_xts_encrypt_##suffix(const struct crypto_aes_ctx *key, const u8 *src, \ - u8 *dst, unsigned int len, u8 tweak[AES_BLOCK_SIZE]); \ + u8 *dst, int len, u8 tweak[AES_BLOCK_SIZE]); \ asmlinkage void \ aes_xts_decrypt_##suffix(const struct crypto_aes_ctx *key, const u8 *src, \ - u8 *dst, unsigned int len, u8 tweak[AES_BLOCK_SIZE]); \ + u8 *dst, int len, u8 tweak[AES_BLOCK_SIZE]); \ \ static int xts_encrypt_##suffix(struct skcipher_request *req) \ { \ diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c index 552f2df0643f..26c5f2ee5d10 100644 --- a/arch/x86/crypto/blowfish_glue.c +++ b/arch/x86/crypto/blowfish_glue.c @@ -94,7 +94,6 @@ static struct crypto_alg bf_cipher_alg = { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = BF_BLOCK_SIZE, .cra_ctxsize = sizeof(struct bf_ctx), - .cra_alignmask = 0, .cra_module = THIS_MODULE, .cra_u = { .cipher = { diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c index f110708c8038..3bd37d664121 100644 --- a/arch/x86/crypto/camellia_glue.c +++ b/arch/x86/crypto/camellia_glue.c @@ -1313,7 +1313,6 @@ static struct crypto_alg camellia_cipher_alg = { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_ctx), - .cra_alignmask = 0, .cra_module = THIS_MODULE, .cra_u = { .cipher = { diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c deleted file mode 100644 index 9f5e342b9845..000000000000 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ /dev/null @@ -1,202 +0,0 @@ -/* GPL HEADER START - * - * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 only, - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License version 2 for more details (a copy is included - * in the LICENSE file that accompanied this code). - * - * You should have received a copy of the GNU General Public License - * version 2 along with this program; If not, see http://www.gnu.org/licenses - * - * Please visit http://www.xyratex.com/contact if you need additional - * information or have any questions. - * - * GPL HEADER END - */ - -/* - * Copyright 2012 Xyratex Technology Limited - * - * Wrappers for kernel crypto shash api to pclmulqdq crc32 implementation. - */ -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#define CHKSUM_BLOCK_SIZE 1 -#define CHKSUM_DIGEST_SIZE 4 - -#define PCLMUL_MIN_LEN 64L /* minimum size of buffer - * for crc32_pclmul_le_16 */ -#define SCALE_F 16L /* size of xmm register */ -#define SCALE_F_MASK (SCALE_F - 1) - -u32 crc32_pclmul_le_16(unsigned char const *buffer, size_t len, u32 crc32); - -static u32 __attribute__((pure)) - crc32_pclmul_le(u32 crc, unsigned char const *p, size_t len) -{ - unsigned int iquotient; - unsigned int iremainder; - unsigned int prealign; - - if (len < PCLMUL_MIN_LEN + SCALE_F_MASK || !crypto_simd_usable()) - return crc32_le(crc, p, len); - - if ((long)p & SCALE_F_MASK) { - /* align p to 16 byte */ - prealign = SCALE_F - ((long)p & SCALE_F_MASK); - - crc = crc32_le(crc, p, prealign); - len -= prealign; - p = (unsigned char *)(((unsigned long)p + SCALE_F_MASK) & - ~SCALE_F_MASK); - } - iquotient = len & (~SCALE_F_MASK); - iremainder = len & SCALE_F_MASK; - - kernel_fpu_begin(); - crc = crc32_pclmul_le_16(p, iquotient, crc); - kernel_fpu_end(); - - if (iremainder) - crc = crc32_le(crc, p + iquotient, iremainder); - - return crc; -} - -static int crc32_pclmul_cra_init(struct crypto_tfm *tfm) -{ - u32 *key = crypto_tfm_ctx(tfm); - - *key = 0; - - return 0; -} - -static int crc32_pclmul_setkey(struct crypto_shash *hash, const u8 *key, - unsigned int keylen) -{ - u32 *mctx = crypto_shash_ctx(hash); - - if (keylen != sizeof(u32)) - return -EINVAL; - *mctx = le32_to_cpup((__le32 *)key); - return 0; -} - -static int crc32_pclmul_init(struct shash_desc *desc) -{ - u32 *mctx = crypto_shash_ctx(desc->tfm); - u32 *crcp = shash_desc_ctx(desc); - - *crcp = *mctx; - - return 0; -} - -static int crc32_pclmul_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - u32 *crcp = shash_desc_ctx(desc); - - *crcp = crc32_pclmul_le(*crcp, data, len); - return 0; -} - -/* No final XOR 0xFFFFFFFF, like crc32_le */ -static int __crc32_pclmul_finup(u32 *crcp, const u8 *data, unsigned int len, - u8 *out) -{ - *(__le32 *)out = cpu_to_le32(crc32_pclmul_le(*crcp, data, len)); - return 0; -} - -static int crc32_pclmul_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32_pclmul_finup(shash_desc_ctx(desc), data, len, out); -} - -static int crc32_pclmul_final(struct shash_desc *desc, u8 *out) -{ - u32 *crcp = shash_desc_ctx(desc); - - *(__le32 *)out = cpu_to_le32p(crcp); - return 0; -} - -static int crc32_pclmul_digest(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32_pclmul_finup(crypto_shash_ctx(desc->tfm), data, len, - out); -} - -static struct shash_alg alg = { - .setkey = crc32_pclmul_setkey, - .init = crc32_pclmul_init, - .update = crc32_pclmul_update, - .final = crc32_pclmul_final, - .finup = crc32_pclmul_finup, - .digest = crc32_pclmul_digest, - .descsize = sizeof(u32), - .digestsize = CHKSUM_DIGEST_SIZE, - .base = { - .cra_name = "crc32", - .cra_driver_name = "crc32-pclmul", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(u32), - .cra_module = THIS_MODULE, - .cra_init = crc32_pclmul_cra_init, - } -}; - -static const struct x86_cpu_id crc32pclmul_cpu_id[] = { - X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, crc32pclmul_cpu_id); - - -static int __init crc32_pclmul_mod_init(void) -{ - - if (!x86_match_cpu(crc32pclmul_cpu_id)) { - pr_info("PCLMULQDQ-NI instructions are not detected.\n"); - return -ENODEV; - } - return crypto_register_shash(&alg); -} - -static void __exit crc32_pclmul_mod_fini(void) -{ - crypto_unregister_shash(&alg); -} - -module_init(crc32_pclmul_mod_init); -module_exit(crc32_pclmul_mod_fini); - -MODULE_AUTHOR("Alexander Boyko "); -MODULE_DESCRIPTION("CRC32 algorithm (IEEE 802.3) accelerated with PCLMULQDQ"); -MODULE_LICENSE("GPL"); - -MODULE_ALIAS_CRYPTO("crc32"); -MODULE_ALIAS_CRYPTO("crc32-pclmul"); diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c deleted file mode 100644 index 52c5d47ef5a1..000000000000 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ /dev/null @@ -1,250 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Using hardware provided CRC32 instruction to accelerate the CRC32 disposal. - * CRC32C polynomial:0x1EDC6F41(BE)/0x82F63B78(LE) - * CRC32 is a new instruction in Intel SSE4.2, the reference can be found at: - * http://www.intel.com/products/processor/manuals/ - * Intel(R) 64 and IA-32 Architectures Software Developer's Manual - * Volume 2A: Instruction Set Reference, A-M - * - * Copyright (C) 2008 Intel Corporation - * Authors: Austin Zhang - * Kent Liu - */ -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#define CHKSUM_BLOCK_SIZE 1 -#define CHKSUM_DIGEST_SIZE 4 - -#define SCALE_F sizeof(unsigned long) - -#ifdef CONFIG_X86_64 -#define CRC32_INST "crc32q %1, %q0" -#else -#define CRC32_INST "crc32l %1, %0" -#endif - -#ifdef CONFIG_X86_64 -/* - * use carryless multiply version of crc32c when buffer - * size is >= 512 to account - * for fpu state save/restore overhead. - */ -#define CRC32C_PCL_BREAKEVEN 512 - -asmlinkage unsigned int crc_pcl(const u8 *buffer, unsigned int len, - unsigned int crc_init); -#endif /* CONFIG_X86_64 */ - -static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length) -{ - while (length--) { - asm("crc32b %1, %0" - : "+r" (crc) : "rm" (*data)); - data++; - } - - return crc; -} - -static u32 __pure crc32c_intel_le_hw(u32 crc, unsigned char const *p, size_t len) -{ - unsigned int iquotient = len / SCALE_F; - unsigned int iremainder = len % SCALE_F; - unsigned long *ptmp = (unsigned long *)p; - - while (iquotient--) { - asm(CRC32_INST - : "+r" (crc) : "rm" (*ptmp)); - ptmp++; - } - - if (iremainder) - crc = crc32c_intel_le_hw_byte(crc, (unsigned char *)ptmp, - iremainder); - - return crc; -} - -/* - * Setting the seed allows arbitrary accumulators and flexible XOR policy - * If your algorithm starts with ~0, then XOR with ~0 before you set - * the seed. - */ -static int crc32c_intel_setkey(struct crypto_shash *hash, const u8 *key, - unsigned int keylen) -{ - u32 *mctx = crypto_shash_ctx(hash); - - if (keylen != sizeof(u32)) - return -EINVAL; - *mctx = le32_to_cpup((__le32 *)key); - return 0; -} - -static int crc32c_intel_init(struct shash_desc *desc) -{ - u32 *mctx = crypto_shash_ctx(desc->tfm); - u32 *crcp = shash_desc_ctx(desc); - - *crcp = *mctx; - - return 0; -} - -static int crc32c_intel_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - u32 *crcp = shash_desc_ctx(desc); - - *crcp = crc32c_intel_le_hw(*crcp, data, len); - return 0; -} - -static int __crc32c_intel_finup(u32 *crcp, const u8 *data, unsigned int len, - u8 *out) -{ - *(__le32 *)out = ~cpu_to_le32(crc32c_intel_le_hw(*crcp, data, len)); - return 0; -} - -static int crc32c_intel_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32c_intel_finup(shash_desc_ctx(desc), data, len, out); -} - -static int crc32c_intel_final(struct shash_desc *desc, u8 *out) -{ - u32 *crcp = shash_desc_ctx(desc); - - *(__le32 *)out = ~cpu_to_le32p(crcp); - return 0; -} - -static int crc32c_intel_digest(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32c_intel_finup(crypto_shash_ctx(desc->tfm), data, len, - out); -} - -static int crc32c_intel_cra_init(struct crypto_tfm *tfm) -{ - u32 *key = crypto_tfm_ctx(tfm); - - *key = ~0; - - return 0; -} - -#ifdef CONFIG_X86_64 -static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - u32 *crcp = shash_desc_ctx(desc); - - /* - * use faster PCL version if datasize is large enough to - * overcome kernel fpu state save/restore overhead - */ - if (len >= CRC32C_PCL_BREAKEVEN && crypto_simd_usable()) { - kernel_fpu_begin(); - *crcp = crc_pcl(data, len, *crcp); - kernel_fpu_end(); - } else - *crcp = crc32c_intel_le_hw(*crcp, data, len); - return 0; -} - -static int __crc32c_pcl_intel_finup(u32 *crcp, const u8 *data, unsigned int len, - u8 *out) -{ - if (len >= CRC32C_PCL_BREAKEVEN && crypto_simd_usable()) { - kernel_fpu_begin(); - *(__le32 *)out = ~cpu_to_le32(crc_pcl(data, len, *crcp)); - kernel_fpu_end(); - } else - *(__le32 *)out = - ~cpu_to_le32(crc32c_intel_le_hw(*crcp, data, len)); - return 0; -} - -static int crc32c_pcl_intel_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32c_pcl_intel_finup(shash_desc_ctx(desc), data, len, out); -} - -static int crc32c_pcl_intel_digest(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return __crc32c_pcl_intel_finup(crypto_shash_ctx(desc->tfm), data, len, - out); -} -#endif /* CONFIG_X86_64 */ - -static struct shash_alg alg = { - .setkey = crc32c_intel_setkey, - .init = crc32c_intel_init, - .update = crc32c_intel_update, - .final = crc32c_intel_final, - .finup = crc32c_intel_finup, - .digest = crc32c_intel_digest, - .descsize = sizeof(u32), - .digestsize = CHKSUM_DIGEST_SIZE, - .base = { - .cra_name = "crc32c", - .cra_driver_name = "crc32c-intel", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(u32), - .cra_module = THIS_MODULE, - .cra_init = crc32c_intel_cra_init, - } -}; - -static const struct x86_cpu_id crc32c_cpu_id[] = { - X86_MATCH_FEATURE(X86_FEATURE_XMM4_2, NULL), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, crc32c_cpu_id); - -static int __init crc32c_intel_mod_init(void) -{ - if (!x86_match_cpu(crc32c_cpu_id)) - return -ENODEV; -#ifdef CONFIG_X86_64 - if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) { - alg.update = crc32c_pcl_intel_update; - alg.finup = crc32c_pcl_intel_finup; - alg.digest = crc32c_pcl_intel_digest; - } -#endif - return crypto_register_shash(&alg); -} - -static void __exit crc32c_intel_mod_fini(void) -{ - crypto_unregister_shash(&alg); -} - -module_init(crc32c_intel_mod_init); -module_exit(crc32c_intel_mod_fini); - -MODULE_AUTHOR("Austin Zhang , Kent Liu "); -MODULE_DESCRIPTION("CRC32c (Castagnoli) optimization using Intel Hardware."); -MODULE_LICENSE("GPL"); - -MODULE_ALIAS_CRYPTO("crc32c"); -MODULE_ALIAS_CRYPTO("crc32c-intel"); diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c deleted file mode 100644 index 71291d5af9f4..000000000000 --- a/arch/x86/crypto/crct10dif-pclmul_glue.c +++ /dev/null @@ -1,143 +0,0 @@ -/* - * Cryptographic API. - * - * T10 Data Integrity Field CRC16 Crypto Transform using PCLMULQDQ Instructions - * - * Copyright (C) 2013 Intel Corporation - * Author: Tim Chen - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -asmlinkage u16 crc_t10dif_pcl(u16 init_crc, const u8 *buf, size_t len); - -struct chksum_desc_ctx { - __u16 crc; -}; - -static int chksum_init(struct shash_desc *desc) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = 0; - - return 0; -} - -static int chksum_update(struct shash_desc *desc, const u8 *data, - unsigned int length) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - if (length >= 16 && crypto_simd_usable()) { - kernel_fpu_begin(); - ctx->crc = crc_t10dif_pcl(ctx->crc, data, length); - kernel_fpu_end(); - } else - ctx->crc = crc_t10dif_generic(ctx->crc, data, length); - return 0; -} - -static int chksum_final(struct shash_desc *desc, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - *(__u16 *)out = ctx->crc; - return 0; -} - -static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out) -{ - if (len >= 16 && crypto_simd_usable()) { - kernel_fpu_begin(); - *(__u16 *)out = crc_t10dif_pcl(crc, data, len); - kernel_fpu_end(); - } else - *(__u16 *)out = crc_t10dif_generic(crc, data, len); - return 0; -} - -static int chksum_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - return __chksum_finup(ctx->crc, data, len, out); -} - -static int chksum_digest(struct shash_desc *desc, const u8 *data, - unsigned int length, u8 *out) -{ - return __chksum_finup(0, data, length, out); -} - -static struct shash_alg alg = { - .digestsize = CRC_T10DIF_DIGEST_SIZE, - .init = chksum_init, - .update = chksum_update, - .final = chksum_final, - .finup = chksum_finup, - .digest = chksum_digest, - .descsize = sizeof(struct chksum_desc_ctx), - .base = { - .cra_name = "crct10dif", - .cra_driver_name = "crct10dif-pclmul", - .cra_priority = 200, - .cra_blocksize = CRC_T10DIF_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -}; - -static const struct x86_cpu_id crct10dif_cpu_id[] = { - X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, crct10dif_cpu_id); - -static int __init crct10dif_intel_mod_init(void) -{ - if (!x86_match_cpu(crct10dif_cpu_id)) - return -ENODEV; - - return crypto_register_shash(&alg); -} - -static void __exit crct10dif_intel_mod_fini(void) -{ - crypto_unregister_shash(&alg); -} - -module_init(crct10dif_intel_mod_init); -module_exit(crct10dif_intel_mod_fini); - -MODULE_AUTHOR("Tim Chen "); -MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ."); -MODULE_LICENSE("GPL"); - -MODULE_ALIAS_CRYPTO("crct10dif"); -MODULE_ALIAS_CRYPTO("crct10dif-pclmul"); diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c index abb8b1fe123b..e88439d3828e 100644 --- a/arch/x86/crypto/des3_ede_glue.c +++ b/arch/x86/crypto/des3_ede_glue.c @@ -291,7 +291,6 @@ static struct crypto_alg des3_ede_cipher = { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = DES3_EDE_BLOCK_SIZE, .cra_ctxsize = sizeof(struct des3_ede_x86_ctx), - .cra_alignmask = 0, .cra_module = THIS_MODULE, .cra_u = { .cipher = { diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c index 0614beece279..4c67184dc573 100644 --- a/arch/x86/crypto/twofish_glue.c +++ b/arch/x86/crypto/twofish_glue.c @@ -68,7 +68,6 @@ static struct crypto_alg alg = { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = TF_BLOCK_SIZE, .cra_ctxsize = sizeof(struct twofish_ctx), - .cra_alignmask = 0, .cra_module = THIS_MODULE, .cra_u = { .cipher = { diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 1b5be07f8669..f52dbe0ad93c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -308,10 +308,9 @@ SYM_CODE_END(xen_error_entry) movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ .endif - call \cfunc - /* For some configurations \cfunc ends up being a noreturn. */ - REACHABLE + ANNOTATE_REACHABLE + call \cfunc jmp error_return .endm @@ -529,10 +528,10 @@ SYM_CODE_START(\asmsym) movq %rsp, %rdi /* pt_regs pointer into first argument */ movq ORIG_RAX(%rsp), %rsi /* get error code into 2nd argument*/ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ - call \cfunc /* For some configurations \cfunc ends up being a noreturn. */ - REACHABLE + ANNOTATE_REACHABLE + call \cfunc jmp paranoid_exit diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 76e4e74f35b5..f6d2d8aba643 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -57,7 +57,7 @@ __setup_param("vdso=", vdso_setup, vdso32_setup, 0); /* Register vsyscall32 into the ABI table */ #include -static struct ctl_table abi_table2[] = { +static const struct ctl_table abi_table2[] = { { .procname = "vsyscall32", .data = &vdso32_enabled, diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index b4a1a2576510..30d6ceb4c8ad 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -1001,8 +1001,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!x86_perf_event_set_period(event)) continue; - if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index e91970b01d62..e7a8b8758e08 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -31,6 +31,8 @@ static u32 ibs_caps; #define IBS_FETCH_CONFIG_MASK (IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT) #define IBS_OP_CONFIG_MASK IBS_OP_MAX_CNT +/* attr.config2 */ +#define IBS_SW_FILTER_MASK 1 /* * IBS states: @@ -290,6 +292,16 @@ static int perf_ibs_init(struct perf_event *event) if (has_branch_stack(event)) return -EOPNOTSUPP; + /* handle exclude_{user,kernel} in the IRQ handler */ + if (event->attr.exclude_host || event->attr.exclude_guest || + event->attr.exclude_idle) + return -EINVAL; + + if (!(event->attr.config2 & IBS_SW_FILTER_MASK) && + (event->attr.exclude_kernel || event->attr.exclude_user || + event->attr.exclude_hv)) + return -EINVAL; + ret = validate_group(event); if (ret) return ret; @@ -550,24 +562,14 @@ static struct attribute *attrs_empty[] = { NULL, }; -static struct attribute_group empty_format_group = { - .name = "format", - .attrs = attrs_empty, -}; - static struct attribute_group empty_caps_group = { .name = "caps", .attrs = attrs_empty, }; -static const struct attribute_group *empty_attr_groups[] = { - &empty_format_group, - &empty_caps_group, - NULL, -}; - PMU_FORMAT_ATTR(rand_en, "config:57"); PMU_FORMAT_ATTR(cnt_ctl, "config:19"); +PMU_FORMAT_ATTR(swfilt, "config2:0"); PMU_EVENT_ATTR_STRING(l3missonly, fetch_l3missonly, "config:59"); PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16"); PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1"); @@ -578,8 +580,9 @@ zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int return ibs_caps & IBS_CAPS_ZEN4 ? attr->mode : 0; } -static struct attribute *rand_en_attrs[] = { +static struct attribute *fetch_attrs[] = { &format_attr_rand_en.attr, + &format_attr_swfilt.attr, NULL, }; @@ -593,9 +596,9 @@ static struct attribute *zen4_ibs_extensions_attrs[] = { NULL, }; -static struct attribute_group group_rand_en = { +static struct attribute_group group_fetch_formats = { .name = "format", - .attrs = rand_en_attrs, + .attrs = fetch_attrs, }; static struct attribute_group group_fetch_l3missonly = { @@ -611,7 +614,7 @@ static struct attribute_group group_zen4_ibs_extensions = { }; static const struct attribute_group *fetch_attr_groups[] = { - &group_rand_en, + &group_fetch_formats, &empty_caps_group, NULL, }; @@ -628,6 +631,11 @@ cnt_ctl_is_visible(struct kobject *kobj, struct attribute *attr, int i) return ibs_caps & IBS_CAPS_OPCNT ? attr->mode : 0; } +static struct attribute *op_attrs[] = { + &format_attr_swfilt.attr, + NULL, +}; + static struct attribute *cnt_ctl_attrs[] = { &format_attr_cnt_ctl.attr, NULL, @@ -638,6 +646,11 @@ static struct attribute *op_l3missonly_attrs[] = { NULL, }; +static struct attribute_group group_op_formats = { + .name = "format", + .attrs = op_attrs, +}; + static struct attribute_group group_cnt_ctl = { .name = "format", .attrs = cnt_ctl_attrs, @@ -650,6 +663,12 @@ static struct attribute_group group_op_l3missonly = { .is_visible = zen4_ibs_extensions_is_visible, }; +static const struct attribute_group *op_attr_groups[] = { + &group_op_formats, + &empty_caps_group, + NULL, +}; + static const struct attribute_group *op_attr_update[] = { &group_cnt_ctl, &group_op_l3missonly, @@ -667,7 +686,6 @@ static struct perf_ibs perf_ibs_fetch = { .start = perf_ibs_start, .stop = perf_ibs_stop, .read = perf_ibs_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }, .msr = MSR_AMD64_IBSFETCHCTL, .config_mask = IBS_FETCH_CONFIG_MASK, @@ -691,7 +709,6 @@ static struct perf_ibs perf_ibs_op = { .start = perf_ibs_start, .stop = perf_ibs_stop, .read = perf_ibs_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, @@ -1111,6 +1128,12 @@ fail: regs.flags |= PERF_EFLAGS_EXACT; } + if ((event->attr.config2 & IBS_SW_FILTER_MASK) && + perf_exclude_event(event, ®s)) { + throttle = perf_event_account_interrupt(event); + goto out; + } + if (event->attr.sample_type & PERF_SAMPLE_RAW) { raw = (struct perf_raw_record){ .frag = { @@ -1118,7 +1141,7 @@ fail: .data = ibs_data.data, }, }; - perf_sample_save_raw_data(&data, &raw); + perf_sample_save_raw_data(&data, event, &raw); } if (perf_ibs == &perf_ibs_op) @@ -1129,8 +1152,7 @@ fail: * recorded as part of interrupt regs. Thus we need to use rip from * interrupt regs while unwinding call stack. */ - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) - perf_sample_save_callchain(&data, event, iregs); + perf_sample_save_callchain(&data, event, iregs); throttle = perf_event_overflow(event, &data, ®s); out: @@ -1228,7 +1250,7 @@ static __init int perf_ibs_op_init(void) if (ibs_caps & IBS_CAPS_ZEN4) perf_ibs_op.config_mask |= IBS_OP_L3MISSONLY; - perf_ibs_op.pmu.attr_groups = empty_attr_groups; + perf_ibs_op.pmu.attr_groups = op_attr_groups; perf_ibs_op.pmu.attr_update = op_attr_update; return perf_ibs_pmu_init(&perf_ibs_op, "ibs_op"); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index c75c482d4c52..8f218ac0d445 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1707,8 +1707,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs) perf_sample_data_init(&data, 0, event->hw.last_period); - if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2e1e26846050..7601196d1d18 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -429,6 +429,16 @@ static struct event_constraint intel_lnc_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_lnc_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0xfffffffffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0xfffffffffffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE), + INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), + INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0xf, FE), + INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), + EVENT_EXTRA_END +}; EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); @@ -2816,6 +2826,9 @@ static void intel_pmu_enable_fixed(struct perf_event *event) return; idx = INTEL_PMC_IDX_FIXED_SLOTS; + + if (event->attr.config1 & INTEL_TD_CFG_METRIC_CLEAR) + bits |= INTEL_FIXED_3_METRICS_CLEAR; } intel_set_masks(event, idx); @@ -4071,7 +4084,12 @@ static int intel_pmu_hw_config(struct perf_event *event) * is used in a metrics group, it too cannot support sampling. */ if (intel_pmu_has_cap(event, PERF_CAP_METRICS_IDX) && is_topdown_event(event)) { - if (event->attr.config1 || event->attr.config2) + /* The metrics_clear can only be set for the slots event */ + if (event->attr.config1 && + (!is_slots_event(event) || (event->attr.config1 & ~INTEL_TD_CFG_METRIC_CLEAR))) + return -EINVAL; + + if (event->attr.config2) return -EINVAL; /* @@ -4680,6 +4698,8 @@ PMU_FORMAT_ATTR(in_tx, "config:32" ); PMU_FORMAT_ATTR(in_tx_cp, "config:33" ); PMU_FORMAT_ATTR(eq, "config:36" ); /* v6 + */ +PMU_FORMAT_ATTR(metrics_clear, "config1:0"); /* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */ + static ssize_t umask2_show(struct device *dev, struct device_attribute *attr, char *page) @@ -4699,6 +4719,7 @@ static struct device_attribute format_attr_umask2 = static struct attribute *format_evtsel_ext_attrs[] = { &format_attr_umask2.attr, &format_attr_eq.attr, + &format_attr_metrics_clear.attr, NULL }; @@ -4723,6 +4744,13 @@ evtsel_ext_is_visible(struct kobject *kobj, struct attribute *attr, int i) if (i == 1) return (mask & ARCH_PERFMON_EVENTSEL_EQ) ? attr->mode : 0; + /* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */ + if (i == 2) { + union perf_capabilities intel_cap = hybrid(dev_get_drvdata(dev), intel_cap); + + return intel_cap.rdpmc_metrics_clear ? attr->mode : 0; + } + return 0; } @@ -5371,42 +5399,32 @@ static __init void intel_clovertown_quirk(void) x86_pmu.pebs_constraints = NULL; } -static const struct x86_cpu_desc isolation_ucodes[] = { - INTEL_CPU_DESC(INTEL_HASWELL, 3, 0x0000001f), - INTEL_CPU_DESC(INTEL_HASWELL_L, 1, 0x0000001e), - INTEL_CPU_DESC(INTEL_HASWELL_G, 1, 0x00000015), - INTEL_CPU_DESC(INTEL_HASWELL_X, 2, 0x00000037), - INTEL_CPU_DESC(INTEL_HASWELL_X, 4, 0x0000000a), - INTEL_CPU_DESC(INTEL_BROADWELL, 4, 0x00000023), - INTEL_CPU_DESC(INTEL_BROADWELL_G, 1, 0x00000014), - INTEL_CPU_DESC(INTEL_BROADWELL_D, 2, 0x00000010), - INTEL_CPU_DESC(INTEL_BROADWELL_D, 3, 0x07000009), - INTEL_CPU_DESC(INTEL_BROADWELL_D, 4, 0x0f000009), - INTEL_CPU_DESC(INTEL_BROADWELL_D, 5, 0x0e000002), - INTEL_CPU_DESC(INTEL_BROADWELL_X, 1, 0x0b000014), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 3, 0x00000021), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 4, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 5, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 6, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 7, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 11, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_L, 3, 0x0000007c), - INTEL_CPU_DESC(INTEL_SKYLAKE, 3, 0x0000007c), - INTEL_CPU_DESC(INTEL_KABYLAKE, 9, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE_L, 9, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE_L, 10, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE_L, 11, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE_L, 12, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE, 10, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE, 11, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE, 12, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE, 13, 0x0000004e), +static const struct x86_cpu_id isolation_ucodes[] = { + X86_MATCH_VFM_STEPS(INTEL_HASWELL, 3, 3, 0x0000001f), + X86_MATCH_VFM_STEPS(INTEL_HASWELL_L, 1, 1, 0x0000001e), + X86_MATCH_VFM_STEPS(INTEL_HASWELL_G, 1, 1, 0x00000015), + X86_MATCH_VFM_STEPS(INTEL_HASWELL_X, 2, 2, 0x00000037), + X86_MATCH_VFM_STEPS(INTEL_HASWELL_X, 4, 4, 0x0000000a), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL, 4, 4, 0x00000023), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_G, 1, 1, 0x00000014), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 2, 2, 0x00000010), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 3, 3, 0x07000009), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 4, 4, 0x0f000009), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 5, 5, 0x0e000002), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_X, 1, 1, 0x0b000014), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 3, 3, 0x00000021), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 4, 7, 0x00000000), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 11, 11, 0x00000000), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_L, 3, 3, 0x0000007c), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE, 3, 3, 0x0000007c), + X86_MATCH_VFM_STEPS(INTEL_KABYLAKE, 9, 13, 0x0000004e), + X86_MATCH_VFM_STEPS(INTEL_KABYLAKE_L, 9, 12, 0x0000004e), {} }; static void intel_check_pebs_isolation(void) { - x86_pmu.pebs_no_isolation = !x86_cpu_has_min_microcode_rev(isolation_ucodes); + x86_pmu.pebs_no_isolation = !x86_match_min_microcode_rev(isolation_ucodes); } static __init void intel_pebs_isolation_quirk(void) @@ -5416,16 +5434,16 @@ static __init void intel_pebs_isolation_quirk(void) intel_check_pebs_isolation(); } -static const struct x86_cpu_desc pebs_ucodes[] = { - INTEL_CPU_DESC(INTEL_SANDYBRIDGE, 7, 0x00000028), - INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X, 6, 0x00000618), - INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X, 7, 0x0000070c), +static const struct x86_cpu_id pebs_ucodes[] = { + X86_MATCH_VFM_STEPS(INTEL_SANDYBRIDGE, 7, 7, 0x00000028), + X86_MATCH_VFM_STEPS(INTEL_SANDYBRIDGE_X, 6, 6, 0x00000618), + X86_MATCH_VFM_STEPS(INTEL_SANDYBRIDGE_X, 7, 7, 0x0000070c), {} }; static bool intel_snb_pebs_broken(void) { - return !x86_cpu_has_min_microcode_rev(pebs_ucodes); + return !x86_match_min_microcode_rev(pebs_ucodes); } static void intel_snb_check_microcode(void) @@ -6422,7 +6440,7 @@ static __always_inline void intel_pmu_init_lnc(struct pmu *pmu) intel_pmu_init_glc(pmu); hybrid(pmu, event_constraints) = intel_lnc_event_constraints; hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints; - hybrid(pmu, extra_regs) = intel_rwc_extra_regs; + hybrid(pmu, extra_regs) = intel_lnc_extra_regs; } static __always_inline void intel_pmu_init_skt(struct pmu *pmu) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 1a4b326ca2ce..ba74e1198328 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1789,8 +1789,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, * previous PMI context or an (I)RET happened between the record and * PMI. */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) - perf_sample_save_callchain(data, event, iregs); + perf_sample_save_callchain(data, event, iregs); /* * We use the interrupt regs as a base because the PEBS record does not @@ -1889,8 +1888,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, if (x86_pmu.intel_cap.pebs_format >= 3) setup_pebs_time(event, data, pebs->tsc); - if (has_branch_stack(event)) - perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); } static void adaptive_pebs_save_regs(struct pt_regs *regs, @@ -1917,8 +1915,6 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs, } #define PEBS_LATENCY_MASK 0xffff -#define PEBS_CACHE_LATENCY_OFFSET 32 -#define PEBS_RETIRE_LATENCY_OFFSET 32 /* * With adaptive PEBS the layout depends on what fields are configured. @@ -1932,8 +1928,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_basic *basic = __pebs; void *next_record = basic + 1; - u64 sample_type; - u64 format_size; + u64 sample_type, format_group; struct pebs_meminfo *meminfo = NULL; struct pebs_gprs *gprs = NULL; struct x86_perf_regs *perf_regs; @@ -1945,7 +1940,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, perf_regs->xmm_regs = NULL; sample_type = event->attr.sample_type; - format_size = basic->format_size; + format_group = basic->format_group; perf_sample_data_init(data, 0, event->hw.last_period); data->period = event->hw.last_period; @@ -1957,8 +1952,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, * previous PMI context or an (I)RET happened between the record and * PMI. */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) - perf_sample_save_callchain(data, event, iregs); + perf_sample_save_callchain(data, event, iregs); *regs = *iregs; /* The ip in basic is EventingIP */ @@ -1967,7 +1961,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) { if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY) - data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK; + data->weight.var3_w = basic->retire_latency; else data->weight.var3_w = 0; } @@ -1977,12 +1971,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, * But PERF_SAMPLE_TRANSACTION needs gprs->ax. * Save the pointer here but process later. */ - if (format_size & PEBS_DATACFG_MEMINFO) { + if (format_group & PEBS_DATACFG_MEMINFO) { meminfo = next_record; next_record = meminfo + 1; } - if (format_size & PEBS_DATACFG_GP) { + if (format_group & PEBS_DATACFG_GP) { gprs = next_record; next_record = gprs + 1; @@ -1995,14 +1989,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, adaptive_pebs_save_regs(regs, gprs); } - if (format_size & PEBS_DATACFG_MEMINFO) { + if (format_group & PEBS_DATACFG_MEMINFO) { if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) { - u64 weight = meminfo->latency; + u64 latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ? + meminfo->cache_latency : meminfo->mem_latency; - if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) { - data->weight.var2_w = weight & PEBS_LATENCY_MASK; - weight >>= PEBS_CACHE_LATENCY_OFFSET; - } + if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) + data->weight.var2_w = meminfo->instr_latency; /* * Although meminfo::latency is defined as a u64, @@ -2010,12 +2003,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, * in practice on Ice Lake and earlier platforms. */ if (sample_type & PERF_SAMPLE_WEIGHT) { - data->weight.full = weight ?: + data->weight.full = latency ?: intel_get_tsx_weight(meminfo->tsx_tuning); } else { - data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?: + data->weight.var1_dw = (u32)latency ?: intel_get_tsx_weight(meminfo->tsx_tuning); } + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; } @@ -2036,16 +2030,16 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, } } - if (format_size & PEBS_DATACFG_XMMS) { + if (format_group & PEBS_DATACFG_XMMS) { struct pebs_xmm *xmm = next_record; next_record = xmm + 1; perf_regs->xmm_regs = xmm->xmm; } - if (format_size & PEBS_DATACFG_LBRS) { + if (format_group & PEBS_DATACFG_LBRS) { struct lbr_entry *lbr = next_record; - int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT) + int num_lbr = ((format_group >> PEBS_DATACFG_LBR_SHIFT) & 0xff) + 1; next_record = next_record + num_lbr * sizeof(struct lbr_entry); @@ -2055,11 +2049,11 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, } } - WARN_ONCE(next_record != __pebs + (format_size >> 48), - "PEBS record size %llu, expected %llu, config %llx\n", - format_size >> 48, + WARN_ONCE(next_record != __pebs + basic->format_size, + "PEBS record size %u, expected %llu, config %llx\n", + basic->format_size, (u64)(next_record - __pebs), - basic->format_size); + format_group); } static inline void * @@ -2170,46 +2164,33 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) return 0; } +typedef void (*setup_fn)(struct perf_event *, struct pt_regs *, void *, + struct perf_sample_data *, struct pt_regs *); + +static struct pt_regs dummy_iregs; + static __always_inline void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, + struct pt_regs *regs, struct perf_sample_data *data, - void *base, void *top, - int bit, int count, - void (*setup_sample)(struct perf_event *, - struct pt_regs *, - void *, - struct perf_sample_data *, - struct pt_regs *)) + void *at, + setup_fn setup_sample) +{ + setup_sample(event, iregs, at, data, regs); + perf_event_output(event, data, regs); +} + +static __always_inline void +__intel_pmu_pebs_last_event(struct perf_event *event, + struct pt_regs *iregs, + struct pt_regs *regs, + struct perf_sample_data *data, + void *at, + int count, + setup_fn setup_sample) { - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - struct x86_perf_regs perf_regs; - struct pt_regs *regs = &perf_regs.regs; - void *at = get_next_pebs_record_by_bit(base, top, bit); - static struct pt_regs dummy_iregs; - - if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { - /* - * Now, auto-reload is only enabled in fixed period mode. - * The reload value is always hwc->sample_period. - * May need to change it, if auto-reload is enabled in - * freq mode later. - */ - intel_pmu_save_and_restart_reload(event, count); - } else if (!intel_pmu_save_and_restart(event)) - return; - - if (!iregs) - iregs = &dummy_iregs; - - while (count > 1) { - setup_sample(event, iregs, at, data, regs); - perf_event_output(event, data, regs); - at += cpuc->pebs_record_size; - at = get_next_pebs_record_by_bit(at, top, bit); - count--; - } setup_sample(event, iregs, at, data, regs); if (iregs == &dummy_iregs) { @@ -2228,6 +2209,44 @@ __intel_pmu_pebs_event(struct perf_event *event, if (perf_event_overflow(event, data, regs)) x86_pmu_stop(event, 0); } + + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + /* + * Now, auto-reload is only enabled in fixed period mode. + * The reload value is always hwc->sample_period. + * May need to change it, if auto-reload is enabled in + * freq mode later. + */ + intel_pmu_save_and_restart_reload(event, count); + } else + intel_pmu_save_and_restart(event); +} + +static __always_inline void +__intel_pmu_pebs_events(struct perf_event *event, + struct pt_regs *iregs, + struct perf_sample_data *data, + void *base, void *top, + int bit, int count, + setup_fn setup_sample) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; + void *at = get_next_pebs_record_by_bit(base, top, bit); + int cnt = count; + + if (!iregs) + iregs = &dummy_iregs; + + while (cnt > 1) { + __intel_pmu_pebs_event(event, iregs, regs, data, at, setup_sample); + at += cpuc->pebs_record_size; + at = get_next_pebs_record_by_bit(at, top, bit); + cnt--; + } + + __intel_pmu_pebs_last_event(event, iregs, regs, data, at, count, setup_sample); } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data) @@ -2264,8 +2283,8 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_ return; } - __intel_pmu_pebs_event(event, iregs, data, at, top, 0, n, - setup_pebs_fixed_sample_data); + __intel_pmu_pebs_events(event, iregs, data, at, top, 0, n, + setup_pebs_fixed_sample_data); } static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size) @@ -2396,9 +2415,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d } if (counts[bit]) { - __intel_pmu_pebs_event(event, iregs, data, base, - top, bit, counts[bit], - setup_pebs_fixed_sample_data); + __intel_pmu_pebs_events(event, iregs, data, base, + top, bit, counts[bit], + setup_pebs_fixed_sample_data); } } } @@ -2406,8 +2425,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data) { short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS]; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; + struct pebs_basic *basic; struct perf_event *event; void *base, *at, *top; int bit; @@ -2429,30 +2452,41 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d return; } - for (at = base; at < top; at += cpuc->pebs_record_size) { + if (!iregs) + iregs = &dummy_iregs; + + /* Process all but the last event for each counter. */ + for (at = base; at < top; at += basic->format_size) { u64 pebs_status; - pebs_status = get_pebs_status(at) & cpuc->pebs_enabled; - pebs_status &= mask; + basic = at; + if (basic->format_size != cpuc->pebs_record_size) + continue; - for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) - counts[bit]++; + pebs_status = basic->applicable_counters & cpuc->pebs_enabled & mask; + for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) { + event = cpuc->events[bit]; + + if (WARN_ON_ONCE(!event) || + WARN_ON_ONCE(!event->attr.precise_ip)) + continue; + + if (counts[bit]++) { + __intel_pmu_pebs_event(event, iregs, regs, data, last[bit], + setup_pebs_adaptive_sample_data); + } + last[bit] = at; + } } for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) { - if (counts[bit] == 0) + if (!counts[bit]) continue; event = cpuc->events[bit]; - if (WARN_ON_ONCE(!event)) - continue; - if (WARN_ON_ONCE(!event->attr.precise_ip)) - continue; - - __intel_pmu_pebs_event(event, iregs, data, base, - top, bit, counts[bit], - setup_pebs_adaptive_sample_data); + __intel_pmu_pebs_last_event(event, iregs, regs, data, last[bit], + counts[bit], setup_pebs_adaptive_sample_data); } } @@ -2517,6 +2551,7 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; + case 6: case 5: x86_pmu.pebs_ept = 1; fallthrough; diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 4b0373bc8ab4..fa37565f6418 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -18,6 +18,7 @@ #include #include +#include #include #include #include @@ -201,10 +202,10 @@ static int __init pt_pmu_hw_init(void) * otherwise, zero for numerator stands for "not enumerated" * as per SDM */ - if (boot_cpu_data.cpuid_level >= CPUID_TSC_LEAF) { + if (boot_cpu_data.cpuid_level >= CPUID_LEAF_TSC) { u32 eax, ebx, ecx, edx; - cpuid(CPUID_TSC_LEAF, &eax, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_TSC, &eax, &ebx, &ecx, &edx); pt_pmu.tsc_art_num = ebx; pt_pmu.tsc_art_den = eax; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 7ee94fc6d7cb..2ac36250b656 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -37,9 +37,6 @@ struct topa_entry { u64 rsvd4 : 12; }; -/* TSC to Core Crystal Clock Ratio */ -#define CPUID_TSC_LEAF 0x15 - struct pt_pmu { struct pmu pmu; u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index d98fac567684..60b3078b7502 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -745,7 +745,7 @@ static int uncore_pmu_event_init(struct perf_event *event) pmu = uncore_event_to_pmu(event); /* no device found for this pmu */ - if (pmu->func_id < 0) + if (!pmu->registered) return -ENOENT; /* Sampling not supported yet */ @@ -992,7 +992,7 @@ static void uncore_types_exit(struct intel_uncore_type **types) uncore_type_exit(*types); } -static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) +static int __init uncore_type_init(struct intel_uncore_type *type) { struct intel_uncore_pmu *pmus; size_t size; @@ -1005,7 +1005,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) size = uncore_max_dies() * sizeof(struct intel_uncore_box *); for (i = 0; i < type->num_boxes; i++) { - pmus[i].func_id = setid ? i : -1; pmus[i].pmu_idx = i; pmus[i].type = type; pmus[i].boxes = kzalloc(size, GFP_KERNEL); @@ -1055,12 +1054,12 @@ err: } static int __init -uncore_types_init(struct intel_uncore_type **types, bool setid) +uncore_types_init(struct intel_uncore_type **types) { int ret; for (; *types; types++) { - ret = uncore_type_init(*types, setid); + ret = uncore_type_init(*types); if (ret) return ret; } @@ -1160,11 +1159,6 @@ static int uncore_pci_pmu_register(struct pci_dev *pdev, if (!box) return -ENOMEM; - if (pmu->func_id < 0) - pmu->func_id = pdev->devfn; - else - WARN_ON_ONCE(pmu->func_id != pdev->devfn); - atomic_inc(&box->refcnt); box->dieid = die; box->pci_dev = pdev; @@ -1410,7 +1404,7 @@ static int __init uncore_pci_init(void) goto err; } - ret = uncore_types_init(uncore_pci_uncores, false); + ret = uncore_types_init(uncore_pci_uncores); if (ret) goto errtype; @@ -1678,7 +1672,7 @@ static int __init uncore_cpu_init(void) { int ret; - ret = uncore_types_init(uncore_msr_uncores, true); + ret = uncore_types_init(uncore_msr_uncores); if (ret) goto err; @@ -1697,7 +1691,7 @@ static int __init uncore_mmio_init(void) struct intel_uncore_type **types = uncore_mmio_uncores; int ret; - ret = uncore_types_init(types, true); + ret = uncore_types_init(types); if (ret) goto err; @@ -1910,6 +1904,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &gnr_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &gnr_uncore_init), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, &gnr_uncore_init), {}, }; MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 79ff32e13dcc..3dcb88c0ecfa 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -125,7 +125,6 @@ struct intel_uncore_pmu { struct pmu pmu; char name[UNCORE_PMU_NAME_LEN]; int pmu_idx; - int func_id; bool registered; atomic_t activeboxes; cpumask_t cpu_mask; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 3934e1e4e3b1..edb7fd50efe0 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -910,7 +910,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event) pmu = uncore_event_to_pmu(event); /* no device found for this pmu */ - if (pmu->func_id < 0) + if (!pmu->registered) return -ENOENT; /* Sampling not supported yet */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index ca98744343b8..60973c209c0e 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -6684,17 +6684,8 @@ void spr_uncore_mmio_init(void) /* GNR uncore support */ #define UNCORE_GNR_NUM_UNCORE_TYPES 23 -#define UNCORE_GNR_TYPE_15 15 -#define UNCORE_GNR_B2UPI 18 -#define UNCORE_GNR_TYPE_21 21 -#define UNCORE_GNR_TYPE_22 22 int gnr_uncore_units_ignore[] = { - UNCORE_SPR_UPI, - UNCORE_GNR_TYPE_15, - UNCORE_GNR_B2UPI, - UNCORE_GNR_TYPE_21, - UNCORE_GNR_TYPE_22, UNCORE_IGNORE_END }; @@ -6703,6 +6694,31 @@ static struct intel_uncore_type gnr_uncore_ubox = { .attr_update = uncore_alias_groups, }; +static struct intel_uncore_type gnr_uncore_pciex8 = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "pciex8", +}; + +static struct intel_uncore_type gnr_uncore_pciex16 = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "pciex16", +}; + +static struct intel_uncore_type gnr_uncore_upi = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "upi", +}; + +static struct intel_uncore_type gnr_uncore_b2upi = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "b2upi", +}; + +static struct intel_uncore_type gnr_uncore_b2hot = { + .name = "b2hot", + .attr_update = uncore_alias_groups, +}; + static struct intel_uncore_type gnr_uncore_b2cmi = { SPR_UNCORE_PCI_COMMON_FORMAT(), .name = "b2cmi", @@ -6727,21 +6743,21 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = { &gnr_uncore_ubox, &spr_uncore_imc, NULL, + &gnr_uncore_upi, NULL, NULL, NULL, + &spr_uncore_cxlcm, + &spr_uncore_cxldp, NULL, - NULL, - NULL, - NULL, - NULL, + &gnr_uncore_b2hot, &gnr_uncore_b2cmi, &gnr_uncore_b2cxl, - NULL, + &gnr_uncore_b2upi, NULL, &gnr_uncore_mdf_sbo, - NULL, - NULL, + &gnr_uncore_pciex16, + &gnr_uncore_pciex8, }; static struct freerunning_counters gnr_iio_freerunning[] = { diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 82c6f45ce975..31c2771545a6 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -624,6 +624,7 @@ union perf_capabilities { u64 pebs_output_pt_available:1; u64 pebs_timing_info:1; u64 anythread_deprecated:1; + u64 rdpmc_metrics_clear:1; }; u64 capabilities; }; diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index a8defc813c36..d3bb3865c1b1 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -39,6 +39,10 @@ * event: rapl_energy_psys * perf code: 0x5 * + * core counter: consumption of a single physical core + * event: rapl_energy_core (power_core PMU) + * perf code: 0x1 + * * We manage those counters as free running (read-only). They may be * use simultaneously by other tools, such as turbostat. * @@ -70,18 +74,22 @@ MODULE_LICENSE("GPL"); /* * RAPL energy status counters */ -enum perf_rapl_events { +enum perf_rapl_pkg_events { PERF_RAPL_PP0 = 0, /* all cores */ PERF_RAPL_PKG, /* entire package */ PERF_RAPL_RAM, /* DRAM */ PERF_RAPL_PP1, /* gpu */ PERF_RAPL_PSYS, /* psys */ - PERF_RAPL_MAX, - NR_RAPL_DOMAINS = PERF_RAPL_MAX, + PERF_RAPL_PKG_EVENTS_MAX, + NR_RAPL_PKG_DOMAINS = PERF_RAPL_PKG_EVENTS_MAX, }; -static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { +#define PERF_RAPL_CORE 0 /* single core */ +#define PERF_RAPL_CORE_EVENTS_MAX 1 +#define NR_RAPL_CORE_DOMAINS PERF_RAPL_CORE_EVENTS_MAX + +static const char *const rapl_pkg_domain_names[NR_RAPL_PKG_DOMAINS] __initconst = { "pp0-core", "package", "dram", @@ -89,6 +97,8 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "psys", }; +static const char *const rapl_core_domain_name __initconst = "core"; + /* * event code: LSB 8 bits, passed in attr->config * any other bit is reserved @@ -112,7 +122,7 @@ static struct perf_pmu_events_attr event_attr_##v = { \ * considered as either pkg-scope or die-scope, and we are considering * them as die-scope. */ -#define rapl_pmu_is_pkg_scope() \ +#define rapl_pkg_pmu_is_pkg_scope() \ (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || \ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) @@ -129,7 +139,8 @@ struct rapl_pmu { struct rapl_pmus { struct pmu pmu; unsigned int nr_rapl_pmu; - struct rapl_pmu *pmus[] __counted_by(nr_rapl_pmu); + unsigned int cntr_mask; + struct rapl_pmu *rapl_pmu[] __counted_by(nr_rapl_pmu); }; enum rapl_unit_quirk { @@ -139,44 +150,43 @@ enum rapl_unit_quirk { }; struct rapl_model { - struct perf_msr *rapl_msrs; - unsigned long events; + struct perf_msr *rapl_pkg_msrs; + struct perf_msr *rapl_core_msrs; + unsigned long pkg_events; + unsigned long core_events; unsigned int msr_power_unit; enum rapl_unit_quirk unit_quirk; }; /* 1/2^hw_unit Joule */ -static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; -static struct rapl_pmus *rapl_pmus; -static unsigned int rapl_cntr_mask; +static int rapl_pkg_hw_unit[NR_RAPL_PKG_DOMAINS] __read_mostly; +static int rapl_core_hw_unit __read_mostly; +static struct rapl_pmus *rapl_pmus_pkg; +static struct rapl_pmus *rapl_pmus_core; static u64 rapl_timer_ms; -static struct perf_msr *rapl_msrs; +static struct rapl_model *rapl_model; /* - * Helper functions to get the correct topology macros according to the + * Helper function to get the correct topology id according to the * RAPL PMU scope. */ -static inline unsigned int get_rapl_pmu_idx(int cpu) +static inline unsigned int get_rapl_pmu_idx(int cpu, int scope) { - return rapl_pmu_is_pkg_scope() ? topology_logical_package_id(cpu) : - topology_logical_die_id(cpu); -} - -static inline const struct cpumask *get_rapl_pmu_cpumask(int cpu) -{ - return rapl_pmu_is_pkg_scope() ? topology_core_cpumask(cpu) : - topology_die_cpumask(cpu); -} - -static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) -{ - unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu); - /* - * The unsigned check also catches the '-1' return value for non - * existent mappings in the topology map. + * Returns unsigned int, which converts the '-1' return value + * (for non-existent mappings in topology map) to UINT_MAX, so + * the error check in the caller is simplified. */ - return rapl_pmu_idx < rapl_pmus->nr_rapl_pmu ? rapl_pmus->pmus[rapl_pmu_idx] : NULL; + switch (scope) { + case PERF_PMU_SCOPE_PKG: + return topology_logical_package_id(cpu); + case PERF_PMU_SCOPE_DIE: + return topology_logical_die_id(cpu); + case PERF_PMU_SCOPE_CORE: + return topology_logical_core_id(cpu); + default: + return -EINVAL; + } } static inline u64 rapl_read_counter(struct perf_event *event) @@ -186,19 +196,20 @@ static inline u64 rapl_read_counter(struct perf_event *event) return raw; } -static inline u64 rapl_scale(u64 v, int cfg) +static inline u64 rapl_scale(u64 v, struct perf_event *event) { - if (cfg > NR_RAPL_DOMAINS) { - pr_warn("Invalid domain %d, failed to scale data\n", cfg); - return v; - } + int hw_unit = rapl_pkg_hw_unit[event->hw.config - 1]; + + if (event->pmu->scope == PERF_PMU_SCOPE_CORE) + hw_unit = rapl_core_hw_unit; + /* * scale delta to smallest unit (1/2^32) * users must then scale back: count * 1/(1e9*2^32) to get Joules * or use ldexp(count, -32). * Watts = Joules/Time delta */ - return v << (32 - rapl_hw_unit[cfg - 1]); + return v << (32 - hw_unit); } static u64 rapl_event_update(struct perf_event *event) @@ -225,7 +236,7 @@ static u64 rapl_event_update(struct perf_event *event) delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - sdelta = rapl_scale(delta, event->hw.config); + sdelta = rapl_scale(delta, event); local64_add(sdelta, &event->count); @@ -240,34 +251,34 @@ static void rapl_start_hrtimer(struct rapl_pmu *pmu) static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) { - struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer); + struct rapl_pmu *rapl_pmu = container_of(hrtimer, struct rapl_pmu, hrtimer); struct perf_event *event; unsigned long flags; - if (!pmu->n_active) + if (!rapl_pmu->n_active) return HRTIMER_NORESTART; - raw_spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&rapl_pmu->lock, flags); - list_for_each_entry(event, &pmu->active_list, active_entry) + list_for_each_entry(event, &rapl_pmu->active_list, active_entry) rapl_event_update(event); - raw_spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); - hrtimer_forward_now(hrtimer, pmu->timer_interval); + hrtimer_forward_now(hrtimer, rapl_pmu->timer_interval); return HRTIMER_RESTART; } -static void rapl_hrtimer_init(struct rapl_pmu *pmu) +static void rapl_hrtimer_init(struct rapl_pmu *rapl_pmu) { - struct hrtimer *hr = &pmu->hrtimer; + struct hrtimer *hr = &rapl_pmu->hrtimer; hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hr->function = rapl_hrtimer_handle; } -static void __rapl_pmu_event_start(struct rapl_pmu *pmu, +static void __rapl_pmu_event_start(struct rapl_pmu *rapl_pmu, struct perf_event *event) { if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) @@ -275,39 +286,39 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu, event->hw.state = 0; - list_add_tail(&event->active_entry, &pmu->active_list); + list_add_tail(&event->active_entry, &rapl_pmu->active_list); local64_set(&event->hw.prev_count, rapl_read_counter(event)); - pmu->n_active++; - if (pmu->n_active == 1) - rapl_start_hrtimer(pmu); + rapl_pmu->n_active++; + if (rapl_pmu->n_active == 1) + rapl_start_hrtimer(rapl_pmu); } static void rapl_pmu_event_start(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = event->pmu_private; + struct rapl_pmu *rapl_pmu = event->pmu_private; unsigned long flags; - raw_spin_lock_irqsave(&pmu->lock, flags); - __rapl_pmu_event_start(pmu, event); - raw_spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_lock_irqsave(&rapl_pmu->lock, flags); + __rapl_pmu_event_start(rapl_pmu, event); + raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); } static void rapl_pmu_event_stop(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = event->pmu_private; + struct rapl_pmu *rapl_pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; - raw_spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&rapl_pmu->lock, flags); /* mark event as deactivated and stopped */ if (!(hwc->state & PERF_HES_STOPPED)) { - WARN_ON_ONCE(pmu->n_active <= 0); - pmu->n_active--; - if (pmu->n_active == 0) - hrtimer_cancel(&pmu->hrtimer); + WARN_ON_ONCE(rapl_pmu->n_active <= 0); + rapl_pmu->n_active--; + if (rapl_pmu->n_active == 0) + hrtimer_cancel(&rapl_pmu->hrtimer); list_del(&event->active_entry); @@ -325,23 +336,23 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode) hwc->state |= PERF_HES_UPTODATE; } - raw_spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); } static int rapl_pmu_event_add(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = event->pmu_private; + struct rapl_pmu *rapl_pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; - raw_spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&rapl_pmu->lock, flags); hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (mode & PERF_EF_START) - __rapl_pmu_event_start(pmu, event); + __rapl_pmu_event_start(rapl_pmu, event); - raw_spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); return 0; } @@ -354,12 +365,14 @@ static void rapl_pmu_event_del(struct perf_event *event, int flags) static int rapl_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config & RAPL_EVENT_MASK; - int bit, ret = 0; - struct rapl_pmu *pmu; + int bit, rapl_pmus_scope, ret = 0; + struct rapl_pmu *rapl_pmu; + unsigned int rapl_pmu_idx; + struct rapl_pmus *rapl_pmus; - /* only look at RAPL events */ - if (event->attr.type != rapl_pmus->pmu.type) - return -ENOENT; + /* unsupported modes and filters */ + if (event->attr.sample_period) /* no sampling */ + return -EINVAL; /* check only supported bits are set */ if (event->attr.config & ~RAPL_EVENT_MASK) @@ -368,26 +381,49 @@ static int rapl_pmu_event_init(struct perf_event *event) if (event->cpu < 0) return -EINVAL; - if (!cfg || cfg >= NR_RAPL_DOMAINS + 1) + rapl_pmus = container_of(event->pmu, struct rapl_pmus, pmu); + if (!rapl_pmus) return -EINVAL; + rapl_pmus_scope = rapl_pmus->pmu.scope; - cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1); - bit = cfg - 1; + if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) { + /* only look at RAPL package events */ + if (event->attr.type != rapl_pmus_pkg->pmu.type) + return -ENOENT; + + cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1); + if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) + return -EINVAL; + + bit = cfg - 1; + event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr; + } else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) { + /* only look at RAPL core events */ + if (event->attr.type != rapl_pmus_core->pmu.type) + return -ENOENT; + + cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1); + if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) + return -EINVAL; + + bit = cfg - 1; + event->hw.event_base = rapl_model->rapl_core_msrs[bit].msr; + } else + return -EINVAL; /* check event supported */ - if (!(rapl_cntr_mask & (1 << bit))) + if (!(rapl_pmus->cntr_mask & (1 << bit))) return -EINVAL; - /* unsupported modes and filters */ - if (event->attr.sample_period) /* no sampling */ + rapl_pmu_idx = get_rapl_pmu_idx(event->cpu, rapl_pmus_scope); + if (rapl_pmu_idx >= rapl_pmus->nr_rapl_pmu) return -EINVAL; - /* must be done before validate_group */ - pmu = cpu_to_rapl_pmu(event->cpu); - if (!pmu) + rapl_pmu = rapl_pmus->rapl_pmu[rapl_pmu_idx]; + if (!rapl_pmu) return -EINVAL; - event->pmu_private = pmu; - event->hw.event_base = rapl_msrs[bit].msr; + + event->pmu_private = rapl_pmu; event->hw.config = cfg; event->hw.idx = bit; @@ -404,12 +440,14 @@ RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05"); +RAPL_EVENT_ATTR_STR(energy-core, rapl_core, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules"); +RAPL_EVENT_ATTR_STR(energy-core.unit, rapl_core_unit, "Joules"); /* * we compute in 0.23 nJ increments regardless of MSR @@ -419,6 +457,7 @@ RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890 RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10"); +RAPL_EVENT_ATTR_STR(energy-core.scale, rapl_core_scale, "2.3283064365386962890625e-10"); /* * There are no default events, but we need to create @@ -451,6 +490,12 @@ static const struct attribute_group *rapl_attr_groups[] = { NULL, }; +static const struct attribute_group *rapl_core_attr_groups[] = { + &rapl_pmu_format_group, + &rapl_pmu_events_group, + NULL, +}; + static struct attribute *rapl_events_cores[] = { EVENT_PTR(rapl_cores), EVENT_PTR(rapl_cores_unit), @@ -511,6 +556,18 @@ static struct attribute_group rapl_events_psys_group = { .attrs = rapl_events_psys, }; +static struct attribute *rapl_events_core[] = { + EVENT_PTR(rapl_core), + EVENT_PTR(rapl_core_unit), + EVENT_PTR(rapl_core_scale), + NULL, +}; + +static struct attribute_group rapl_events_core_group = { + .name = "events", + .attrs = rapl_events_core, +}; + static bool test_msr(int idx, void *data) { return test_bit(idx, (unsigned long *) data); @@ -536,11 +593,11 @@ static struct perf_msr intel_rapl_spr_msrs[] = { }; /* - * Force to PERF_RAPL_MAX size due to: - * - perf_msr_probe(PERF_RAPL_MAX) + * Force to PERF_RAPL_PKG_EVENTS_MAX size due to: + * - perf_msr_probe(PERF_RAPL_PKG_EVENTS_MAX) * - want to use same event codes across both architectures */ -static struct perf_msr amd_rapl_msrs[] = { +static struct perf_msr amd_rapl_pkg_msrs[] = { [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, NULL, false, 0 }, [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, NULL, false, 0 }, @@ -548,18 +605,25 @@ static struct perf_msr amd_rapl_msrs[] = { [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, NULL, false, 0 }, }; -static int rapl_check_hw_unit(struct rapl_model *rm) +static struct perf_msr amd_rapl_core_msrs[] = { + [PERF_RAPL_CORE] = { MSR_AMD_CORE_ENERGY_STATUS, &rapl_events_core_group, + test_msr, false, RAPL_MSR_MASK }, +}; + +static int rapl_check_hw_unit(void) { u64 msr_rapl_power_unit_bits; int i; /* protect rdmsrl() to handle virtualization */ - if (rdmsrl_safe(rm->msr_power_unit, &msr_rapl_power_unit_bits)) + if (rdmsrl_safe(rapl_model->msr_power_unit, &msr_rapl_power_unit_bits)) return -1; - for (i = 0; i < NR_RAPL_DOMAINS; i++) - rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++) + rapl_pkg_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; - switch (rm->unit_quirk) { + rapl_core_hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + + switch (rapl_model->unit_quirk) { /* * DRAM domain on HSW server and KNL has fixed energy unit which can be * different than the unit from power unit MSR. See @@ -567,17 +631,16 @@ static int rapl_check_hw_unit(struct rapl_model *rm) * of 2. Datasheet, September 2014, Reference Number: 330784-001 " */ case RAPL_UNIT_QUIRK_INTEL_HSW: - rapl_hw_unit[PERF_RAPL_RAM] = 16; + rapl_pkg_hw_unit[PERF_RAPL_RAM] = 16; break; /* SPR uses a fixed energy unit for Psys domain. */ case RAPL_UNIT_QUIRK_INTEL_SPR: - rapl_hw_unit[PERF_RAPL_PSYS] = 0; + rapl_pkg_hw_unit[PERF_RAPL_PSYS] = 0; break; default: break; } - /* * Calculate the timer rate: * Use reference of 200W for scaling the timeout to avoid counter @@ -586,9 +649,9 @@ static int rapl_check_hw_unit(struct rapl_model *rm) * if hw unit is 32, then we use 2 ms 1/200/2 */ rapl_timer_ms = 2; - if (rapl_hw_unit[0] < 32) { + if (rapl_pkg_hw_unit[0] < 32) { rapl_timer_ms = (1000 / (2 * 100)); - rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1)); + rapl_timer_ms *= (1ULL << (32 - rapl_pkg_hw_unit[0] - 1)); } return 0; } @@ -596,24 +659,32 @@ static int rapl_check_hw_unit(struct rapl_model *rm) static void __init rapl_advertise(void) { int i; + int num_counters = hweight32(rapl_pmus_pkg->cntr_mask); + + if (rapl_pmus_core) + num_counters += hweight32(rapl_pmus_core->cntr_mask); pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n", - hweight32(rapl_cntr_mask), rapl_timer_ms); + num_counters, rapl_timer_ms); - for (i = 0; i < NR_RAPL_DOMAINS; i++) { - if (rapl_cntr_mask & (1 << i)) { + for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++) { + if (rapl_pmus_pkg->cntr_mask & (1 << i)) { pr_info("hw unit of domain %s 2^-%d Joules\n", - rapl_domain_names[i], rapl_hw_unit[i]); + rapl_pkg_domain_names[i], rapl_pkg_hw_unit[i]); } } + + if (rapl_pmus_core && (rapl_pmus_core->cntr_mask & (1 << PERF_RAPL_CORE))) + pr_info("hw unit of domain %s 2^-%d Joules\n", + rapl_core_domain_name, rapl_core_hw_unit); } -static void cleanup_rapl_pmus(void) +static void cleanup_rapl_pmus(struct rapl_pmus *rapl_pmus) { int i; for (i = 0; i < rapl_pmus->nr_rapl_pmu; i++) - kfree(rapl_pmus->pmus[i]); + kfree(rapl_pmus->rapl_pmu[i]); kfree(rapl_pmus); } @@ -626,46 +697,60 @@ static const struct attribute_group *rapl_attr_update[] = { NULL, }; -static int __init init_rapl_pmu(void) +static const struct attribute_group *rapl_core_attr_update[] = { + &rapl_events_core_group, + NULL, +}; + +static int __init init_rapl_pmu(struct rapl_pmus *rapl_pmus) { - struct rapl_pmu *pmu; + struct rapl_pmu *rapl_pmu; int idx; for (idx = 0; idx < rapl_pmus->nr_rapl_pmu; idx++) { - pmu = kzalloc(sizeof(*pmu), GFP_KERNEL); - if (!pmu) + rapl_pmu = kzalloc(sizeof(*rapl_pmu), GFP_KERNEL); + if (!rapl_pmu) goto free; - raw_spin_lock_init(&pmu->lock); - INIT_LIST_HEAD(&pmu->active_list); - pmu->pmu = &rapl_pmus->pmu; - pmu->timer_interval = ms_to_ktime(rapl_timer_ms); - rapl_hrtimer_init(pmu); + raw_spin_lock_init(&rapl_pmu->lock); + INIT_LIST_HEAD(&rapl_pmu->active_list); + rapl_pmu->pmu = &rapl_pmus->pmu; + rapl_pmu->timer_interval = ms_to_ktime(rapl_timer_ms); + rapl_hrtimer_init(rapl_pmu); - rapl_pmus->pmus[idx] = pmu; + rapl_pmus->rapl_pmu[idx] = rapl_pmu; } return 0; free: for (; idx > 0; idx--) - kfree(rapl_pmus->pmus[idx - 1]); + kfree(rapl_pmus->rapl_pmu[idx - 1]); return -ENOMEM; } -static int __init init_rapl_pmus(void) +static int __init init_rapl_pmus(struct rapl_pmus **rapl_pmus_ptr, int rapl_pmu_scope, + const struct attribute_group **rapl_attr_groups, + const struct attribute_group **rapl_attr_update) { int nr_rapl_pmu = topology_max_packages(); - int rapl_pmu_scope = PERF_PMU_SCOPE_PKG; + struct rapl_pmus *rapl_pmus; - if (!rapl_pmu_is_pkg_scope()) { - nr_rapl_pmu *= topology_max_dies_per_package(); - rapl_pmu_scope = PERF_PMU_SCOPE_DIE; - } + /* + * rapl_pmu_scope must be either PKG, DIE or CORE + */ + if (rapl_pmu_scope == PERF_PMU_SCOPE_DIE) + nr_rapl_pmu *= topology_max_dies_per_package(); + else if (rapl_pmu_scope == PERF_PMU_SCOPE_CORE) + nr_rapl_pmu *= topology_num_cores_per_package(); + else if (rapl_pmu_scope != PERF_PMU_SCOPE_PKG) + return -EINVAL; - rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL); + rapl_pmus = kzalloc(struct_size(rapl_pmus, rapl_pmu, nr_rapl_pmu), GFP_KERNEL); if (!rapl_pmus) return -ENOMEM; + *rapl_pmus_ptr = rapl_pmus; + rapl_pmus->nr_rapl_pmu = nr_rapl_pmu; rapl_pmus->pmu.attr_groups = rapl_attr_groups; rapl_pmus->pmu.attr_update = rapl_attr_update; @@ -680,75 +765,77 @@ static int __init init_rapl_pmus(void) rapl_pmus->pmu.module = THIS_MODULE; rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE; - return init_rapl_pmu(); + return init_rapl_pmu(rapl_pmus); } static struct rapl_model model_snb = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_snbep = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsw = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsx = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_knl = { - .events = BIT(PERF_RAPL_PKG) | + .pkg_events = BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_skl = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1) | BIT(PERF_RAPL_PSYS), .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_spr = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PSYS), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_SPR, .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_spr_msrs, + .rapl_pkg_msrs = intel_rapl_spr_msrs, }; static struct rapl_model model_amd_hygon = { - .events = BIT(PERF_RAPL_PKG), + .pkg_events = BIT(PERF_RAPL_PKG), + .core_events = BIT(PERF_RAPL_CORE), .msr_power_unit = MSR_AMD_RAPL_POWER_UNIT, - .rapl_msrs = amd_rapl_msrs, + .rapl_pkg_msrs = amd_rapl_pkg_msrs, + .rapl_core_msrs = amd_rapl_core_msrs, }; static const struct x86_cpu_id rapl_model_match[] __initconst = { @@ -804,45 +891,73 @@ MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); static int __init rapl_pmu_init(void) { const struct x86_cpu_id *id; - struct rapl_model *rm; + int rapl_pkg_pmu_scope = PERF_PMU_SCOPE_DIE; int ret; + if (rapl_pkg_pmu_is_pkg_scope()) + rapl_pkg_pmu_scope = PERF_PMU_SCOPE_PKG; + id = x86_match_cpu(rapl_model_match); if (!id) return -ENODEV; - rm = (struct rapl_model *) id->driver_data; + rapl_model = (struct rapl_model *) id->driver_data; - rapl_msrs = rm->rapl_msrs; - - rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX, - false, (void *) &rm->events); - - ret = rapl_check_hw_unit(rm); + ret = rapl_check_hw_unit(); if (ret) return ret; - ret = init_rapl_pmus(); + ret = init_rapl_pmus(&rapl_pmus_pkg, rapl_pkg_pmu_scope, rapl_attr_groups, + rapl_attr_update); if (ret) return ret; - ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); + rapl_pmus_pkg->cntr_mask = perf_msr_probe(rapl_model->rapl_pkg_msrs, + PERF_RAPL_PKG_EVENTS_MAX, false, + (void *) &rapl_model->pkg_events); + + ret = perf_pmu_register(&rapl_pmus_pkg->pmu, "power", -1); if (ret) goto out; + if (rapl_model->core_events) { + ret = init_rapl_pmus(&rapl_pmus_core, PERF_PMU_SCOPE_CORE, + rapl_core_attr_groups, + rapl_core_attr_update); + if (ret) { + pr_warn("power-core PMU initialization failed (%d)\n", ret); + goto core_init_failed; + } + + rapl_pmus_core->cntr_mask = perf_msr_probe(rapl_model->rapl_core_msrs, + PERF_RAPL_CORE_EVENTS_MAX, false, + (void *) &rapl_model->core_events); + + ret = perf_pmu_register(&rapl_pmus_core->pmu, "power_core", -1); + if (ret) { + pr_warn("power-core PMU registration failed (%d)\n", ret); + cleanup_rapl_pmus(rapl_pmus_core); + } + } + +core_init_failed: rapl_advertise(); return 0; out: pr_warn("Initialization failed (%d), disabled\n", ret); - cleanup_rapl_pmus(); + cleanup_rapl_pmus(rapl_pmus_pkg); return ret; } module_init(rapl_pmu_init); static void __exit intel_rapl_exit(void) { - perf_pmu_unregister(&rapl_pmus->pmu); - cleanup_rapl_pmus(); + if (rapl_pmus_core) { + perf_pmu_unregister(&rapl_pmus_core->pmu); + cleanup_rapl_pmus(rapl_pmus_core); + } + perf_pmu_unregister(&rapl_pmus_pkg->pmu); + cleanup_rapl_pmus(rapl_pmus_pkg); } module_exit(intel_rapl_exit); diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 0569f579338b..f022d5f64fb6 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 95eada2994e1..173005e6a95d 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include #include @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include @@ -416,24 +415,24 @@ static void __init hv_get_partition_id(void) static u8 __init get_vtl(void) { u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS; - struct hv_get_vp_registers_input *input; - struct hv_get_vp_registers_output *output; + struct hv_input_get_vp_registers *input; + struct hv_output_get_vp_registers *output; unsigned long flags; u64 ret; local_irq_save(flags); input = *this_cpu_ptr(hyperv_pcpu_input_arg); - output = (struct hv_get_vp_registers_output *)input; + output = *this_cpu_ptr(hyperv_pcpu_output_arg); - memset(input, 0, struct_size(input, element, 1)); - input->header.partitionid = HV_PARTITION_ID_SELF; - input->header.vpindex = HV_VP_INDEX_SELF; - input->header.inputvtl = 0; - input->element[0].name0 = HV_X64_REGISTER_VSM_VP_STATUS; + memset(input, 0, struct_size(input, names, 1)); + input->partition_id = HV_PARTITION_ID_SELF; + input->vp_index = HV_VP_INDEX_SELF; + input->input_vtl.as_uint8 = 0; + input->names[0] = HV_REGISTER_VSM_VP_STATUS; ret = hv_do_hypercall(control, input, output); if (hv_result_success(ret)) { - ret = output->as64.low & HV_X64_VTL_MASK; + ret = output->values[0].reg8 & HV_X64_VTL_MASK; } else { pr_err("Failed to get VTL(error: %lld) exiting...\n", ret); BUG(); @@ -473,7 +472,7 @@ void __init hyperv_init(void) if (hv_isolation_type_tdx()) hv_vp_assist_page = NULL; else - hv_vp_assist_page = kcalloc(num_possible_cpus(), + hv_vp_assist_page = kcalloc(nr_cpu_ids, sizeof(*hv_vp_assist_page), GFP_KERNEL); if (!hv_vp_assist_page) { diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c index 3fa1f2ee7b0d..ac4c834d4435 100644 --- a/arch/x86/hyperv/hv_proc.c +++ b/arch/x86/hyperv/hv_proc.c @@ -3,7 +3,6 @@ #include #include #include -#include #include #include #include @@ -177,7 +176,7 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) input->partition_id = partition_id; input->vp_index = vp_index; input->flags = flags; - input->subnode_type = HvSubnodeAny; + input->subnode_type = HV_SUBNODE_ANY; input->proximity_domain_info = hv_numa_node_to_pxm_info(node); status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL); local_irq_restore(irq_flags); diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 04775346369c..4e1b1e3b5658 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -189,7 +189,7 @@ static int hv_vtl_apicid_to_vp_id(u32 apic_id) input->partition_id = HV_PARTITION_ID_SELF; input->apic_ids[0] = apic_id; - output = (u32 *)input; + output = *this_cpu_ptr(hyperv_pcpu_output_arg); control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID; status = hv_do_hypercall(control, input, output); diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c index 3215a4a07408..64b921360b0f 100644 --- a/arch/x86/hyperv/irqdomain.c +++ b/arch/x86/hyperv/irqdomain.c @@ -304,7 +304,7 @@ static struct irq_chip hv_pci_msi_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = hv_irq_compose_msi_msg, .irq_set_affinity = msi_domain_set_affinity, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED, }; static struct msi_domain_ops pci_msi_domain_ops = { diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 60fc3ed72830..dd68d9ad9b22 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -7,7 +7,6 @@ */ #include -#include #include #include #include @@ -664,7 +663,7 @@ void __init hv_vtom_init(void) x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility; /* Set WB as the default cache mode. */ - mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); + guest_force_mtrr_state(NULL, 0, MTRR_TYPE_WRBACK); } #endif /* defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) */ diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 1cc113200ff5..cc8c3bd0e7c2 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -1,6 +1,5 @@ #define pr_fmt(fmt) "Hyper-V: " fmt -#include #include #include #include diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c index 9dc259fa322e..1083dc8646f9 100644 --- a/arch/x86/hyperv/nested.c +++ b/arch/x86/hyperv/nested.c @@ -11,7 +11,7 @@ #include -#include +#include #include #include diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 6c23d1661b17..58f4ddecc5fa 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -10,5 +10,6 @@ generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h generic-y += early_ioremap.h +generic-y += fprobe.h generic-y += mcs_spinlock.h generic-y += mmzone.h diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index dc03a647776d..e3903b731305 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -4,6 +4,7 @@ #include #include +#include #include #define ALT_FLAGS_SHIFT 16 @@ -54,16 +55,6 @@ #define LOCK_PREFIX "" #endif -/* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -#define ANNOTATE_IGNORE_ALTERNATIVE \ - "999:\n\t" \ - ".pushsection .discard.ignore_alts\n\t" \ - ".long 999b\n\t" \ - ".popsection\n\t" - /* * The patching flags are part of the upper bits of the @ft_flags parameter when * specifying them. The split is currently like this: @@ -310,17 +301,6 @@ void nop_func(void); .endm #endif -/* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -.macro ANNOTATE_IGNORE_ALTERNATIVE - .Lannotate_\@: - .pushsection .discard.ignore_alts - .long .Lannotate_\@ - .popsection -.endm - /* * Issue one struct alt_instr descriptor entry (need to put it into * the section .altinstructions, see below). This entry contains diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index d0caac26533f..4c4efb93045e 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -4,7 +4,7 @@ #include #include -#include +#include struct amd_nb_bus_dev_range { u8 bus; @@ -21,49 +21,16 @@ extern int amd_numa_init(void); extern int amd_get_subcaches(int); extern int amd_set_subcaches(int, unsigned long); -int __must_check amd_smn_read(u16 node, u32 address, u32 *value); -int __must_check amd_smn_write(u16 node, u32 address, u32 value); - struct amd_l3_cache { unsigned indices; u8 subcaches[4]; }; -struct threshold_block { - unsigned int block; /* Number within bank */ - unsigned int bank; /* MCA bank the block belongs to */ - unsigned int cpu; /* CPU which controls MCA bank */ - u32 address; /* MSR address for the block */ - u16 interrupt_enable; /* Enable/Disable APIC interrupt */ - bool interrupt_capable; /* Bank can generate an interrupt. */ - - u16 threshold_limit; /* - * Value upon which threshold - * interrupt is generated. - */ - - struct kobject kobj; /* sysfs object */ - struct list_head miscj; /* - * List of threshold blocks - * within a bank. - */ -}; - -struct threshold_bank { - struct kobject *kobj; - struct threshold_block *blocks; - - /* initialized to the number of CPUs on the node sharing this bank */ - refcount_t cpus; - unsigned int shared; -}; - struct amd_northbridge { struct pci_dev *root; struct pci_dev *misc; struct pci_dev *link; struct amd_l3_cache l3_cache; - struct threshold_bank *bank4; }; struct amd_northbridge_info { @@ -82,23 +49,6 @@ u16 amd_nb_num(void); bool amd_nb_has_feature(unsigned int feature); struct amd_northbridge *node_to_amd_nb(int node); -static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev) -{ - struct pci_dev *misc; - int i; - - for (i = 0; i != amd_nb_num(); i++) { - misc = node_to_amd_nb(i)->misc; - - if (pci_domain_nr(misc->bus) == pci_domain_nr(pdev->bus) && - PCI_SLOT(misc->devfn) == PCI_SLOT(pdev->devfn)) - return i; - } - - WARN(1, "Unable to find AMD Northbridge id for %s\n", pci_name(pdev)); - return 0; -} - static inline bool amd_gart_present(void) { if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) diff --git a/arch/x86/include/asm/amd_node.h b/arch/x86/include/asm/amd_node.h new file mode 100644 index 000000000000..113ad3e8ee40 --- /dev/null +++ b/arch/x86/include/asm/amd_node.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Node helper functions and common defines + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam + * + * Note: + * Items in this file may only be used in a single place. + * However, it's prudent to keep all AMD Node functionality + * in a unified place rather than spreading throughout the + * kernel. + */ + +#ifndef _ASM_X86_AMD_NODE_H_ +#define _ASM_X86_AMD_NODE_H_ + +#include + +#define MAX_AMD_NUM_NODES 8 +#define AMD_NODE0_PCI_SLOT 0x18 + +struct pci_dev *amd_node_get_func(u16 node, u8 func); +struct pci_dev *amd_node_get_root(u16 node); + +static inline u16 amd_num_nodes(void) +{ + return topology_amd_nodes_per_pkg() * topology_max_packages(); +} + +int __must_check amd_smn_read(u16 node, u32 address, u32 *value); +int __must_check amd_smn_write(u16 node, u32 address, u32 value); + +#endif /*_ASM_X86_AMD_NODE_H_*/ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 806649c7f23d..e85ac0c7c039 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -92,7 +92,7 @@ do { \ do { \ __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ANNOTATE_REACHABLE(1b)); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index e4121d9aa9e1..ba32e0f44cba 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -56,7 +56,6 @@ /* x86_cpu_id::flags */ #define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0) -#define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY @@ -208,6 +207,7 @@ VFM_MODEL(vfm), \ X86_STEPPING_ANY, X86_FEATURE_ANY, data) +#define __X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping * @vfm: Encoded 8-bits each for vendor, family, model @@ -218,12 +218,13 @@ * * feature is set to wildcard */ -#define X86_MATCH_VFM_STEPPINGS(vfm, steppings, data) \ - X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ - VFM_VENDOR(vfm), \ - VFM_FAMILY(vfm), \ - VFM_MODEL(vfm), \ - steppings, X86_FEATURE_ANY, data) +#define X86_MATCH_VFM_STEPS(vfm, min_step, max_step, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + __X86_STEPPINGS(min_step, max_step), \ + X86_FEATURE_ANY, data) /** * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature @@ -242,41 +243,7 @@ VFM_MODEL(vfm), \ X86_STEPPING_ANY, feature, data) -/* - * Match specific microcode revisions. - * - * vendor/family/model/stepping must be all set. - * - * Only checks against the boot CPU. When mixed-stepping configs are - * valid for a CPU model, add a quirk for every valid stepping and - * do the fine-tuning in the quirk handler. - */ - -struct x86_cpu_desc { - u8 x86_family; - u8 x86_vendor; - u8 x86_model; - u8 x86_stepping; - u32 x86_microcode_rev; -}; - -#define INTEL_CPU_DESC(vfm, stepping, revision) { \ - .x86_family = VFM_FAMILY(vfm), \ - .x86_vendor = VFM_VENDOR(vfm), \ - .x86_model = VFM_MODEL(vfm), \ - .x86_stepping = (stepping), \ - .x86_microcode_rev = (revision), \ -} - -#define AMD_CPU_DESC(fam, model, stepping, revision) { \ - .x86_family = (fam), \ - .x86_vendor = X86_VENDOR_AMD, \ - .x86_model = (model), \ - .x86_stepping = (stepping), \ - .x86_microcode_rev = (revision), \ -} - extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); -extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table); +extern bool x86_match_min_microcode_rev(const struct x86_cpu_id *table); #endif /* _ASM_X86_CPU_DEVICE_ID */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 0b9611da6c53..de1ad09fe8d7 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -132,11 +132,12 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; x86_this_cpu_test_bit(bit, cpu_info.x86_capability)) /* - * This macro is for detection of features which need kernel - * infrastructure to be used. It may *not* directly test the CPU - * itself. Use the cpu_has() family if you want true runtime - * testing of CPU features, like in hypervisor code where you are - * supporting a possible guest feature where host support for it + * This is the default CPU features testing macro to use in code. + * + * It is for detection of features which need kernel infrastructure to be + * used. It may *not* directly test the CPU itself. Use the cpu_has() family + * if you want true runtime testing of CPU features, like in hypervisor code + * where you are supporting a possible guest feature where host support for it * is not relevant. */ #define cpu_feature_enabled(bit) \ @@ -161,13 +162,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) /* - * Static testing of CPU features. Used the same as boot_cpu_has(). It - * statically patches the target code for additional performance. Use - * static_cpu_has() only in fast paths, where every cycle counts. Which - * means that the boot_cpu_has() variant is already fast enough for the - * majority of cases and you should stick to using it as it is generally - * only two instructions: a RIP-relative MOV and a TEST. - * * Do not use an "m" constraint for [cap_byte] here: gcc doesn't know * that this is only used on a fallback path and will sometimes cause * it to manifest the address of boot_cpu_data in a register, fouling diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 17b6590748c0..508c0dad116b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -83,8 +83,8 @@ #define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ #define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ #define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* P4 */ +/* Free ( 3*32+ 6) */ +/* Free ( 3*32+ 7) */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ #define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */ #define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */ @@ -443,15 +443,18 @@ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */ /* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ -#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */ -#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_SME (19*32+ 0) /* "sme" Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* "sev" Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ -#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */ -#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */ -#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* hardware-enforced cache coherency */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */ +#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */ +#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */ #define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ +#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ @@ -464,6 +467,7 @@ #define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ +#define X86_FEATURE_SRSO_USER_KERNEL_NO (20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */ /* * Extended auxiliary flags: Linux defined - for features scattered in various diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index 239b9ba5c398..b2b9b4ef3dae 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -21,6 +21,13 @@ enum cpuid_regs_idx { CPUID_EDX, }; +#define CPUID_LEAF_MWAIT 0x5 +#define CPUID_LEAF_DCA 0x9 +#define CPUID_LEAF_XSTATE 0x0d +#define CPUID_LEAF_TSC 0x15 +#define CPUID_LEAF_FREQ 0x16 +#define CPUID_LEAF_TILE 0x1d + #ifdef CONFIG_X86_32 bool have_cpuid_p(void); #else diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 521aad70e41b..f227a70ac91f 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -250,6 +250,9 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi64_argmap_allocate_pool(type, size, buffer) \ ((type), (size), efi64_zero_upper(buffer)) +#define __efi64_argmap_locate_handle_buffer(type, proto, key, num, buf) \ + ((type), (proto), (key), efi64_zero_upper(num), efi64_zero_upper(buf)) + #define __efi64_argmap_create_event(type, tpl, f, c, event) \ ((type), (tpl), (f), (c), efi64_zero_upper(event)) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index d4427b88ee12..7f39fe7980c5 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -12,10 +12,6 @@ /* Bit 63 of XCR0 is reserved for future expansion */ #define XFEATURE_MASK_EXTEND (~(XFEATURE_MASK_FPSSE | (1ULL << 63))) -#define XSTATE_CPUID 0x0000000d - -#define TILE_CPUID 0x0000001d - #define FXSAVE_SIZE 512 #define XSAVE_HDR_SIZE 64 diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 6e8cf0fa48fc..f9cb4d07df58 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -34,6 +34,27 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) +{ +#ifdef CONFIG_X86_KERNEL_IBT + u32 instr; + + /* We want to be extra safe in case entry ip is on the page edge, + * but otherwise we need to avoid get_kernel_nofault()'s overhead. + */ + if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) { + if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE))) + return fentry_ip; + } else { + instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE); + } + if (is_endbr(instr)) + fentry_ip -= ENDBR_INSN_SIZE; +#endif + return fentry_ip; +} +#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip) + #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS #include @@ -47,10 +68,23 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) return &arch_ftrace_regs(fregs)->regs; } +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->ip = arch_ftrace_regs(fregs)->regs.ip; \ + (_regs)->sp = arch_ftrace_regs(fregs)->regs.sp; \ + (_regs)->cs = __KERNEL_CS; \ + (_regs)->flags = 0; \ + } while (0) + #define ftrace_regs_set_instruction_pointer(fregs, _ip) \ do { arch_ftrace_regs(fregs)->regs.ip = (_ip); } while (0) +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return *(unsigned long *)ftrace_regs_get_stack_pointer(fregs); +} + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, @@ -134,24 +168,4 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) #endif /* !COMPILE_OFFSETS */ #endif /* !__ASSEMBLY__ */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long ax; - unsigned long dx; - unsigned long bp; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->ax; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->bp; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_X86_FTRACE_H */ diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index ab9f3dd87c80..ab0c78855ecb 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -84,7 +84,6 @@ extern int hpet_set_rtc_irq_bit(unsigned long bit_mask); extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec); extern int hpet_set_periodic_freq(unsigned long freq); -extern int hpet_rtc_dropped_irq(void); extern int hpet_rtc_timer_init(void); extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id); extern int hpet_register_irq_handler(rtc_irq_handler handler); diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h deleted file mode 100644 index 3787d26810c1..000000000000 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ /dev/null @@ -1,811 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* - * This file contains definitions from Hyper-V Hypervisor Top-Level Functional - * Specification (TLFS): - * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs - */ - -#ifndef _ASM_X86_HYPERV_TLFS_H -#define _ASM_X86_HYPERV_TLFS_H - -#include -#include -/* - * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent - * is set by CPUID(HvCpuIdFunctionVersionAndFeatures). - */ -#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 0x40000000 -#define HYPERV_CPUID_INTERFACE 0x40000001 -#define HYPERV_CPUID_VERSION 0x40000002 -#define HYPERV_CPUID_FEATURES 0x40000003 -#define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004 -#define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005 -#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES 0x40000007 -#define HYPERV_CPUID_NESTED_FEATURES 0x4000000A -#define HYPERV_CPUID_ISOLATION_CONFIG 0x4000000C - -#define HYPERV_CPUID_VIRT_STACK_INTERFACE 0x40000081 -#define HYPERV_VS_INTERFACE_EAX_SIGNATURE 0x31235356 /* "VS#1" */ - -#define HYPERV_CPUID_VIRT_STACK_PROPERTIES 0x40000082 -/* Support for the extended IOAPIC RTE format */ -#define HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE BIT(2) - -#define HYPERV_HYPERVISOR_PRESENT_BIT 0x80000000 -#define HYPERV_CPUID_MIN 0x40000005 -#define HYPERV_CPUID_MAX 0x4000ffff - -/* - * Group D Features. The bit assignments are custom to each architecture. - * On x86/x64 these are HYPERV_CPUID_FEATURES.EDX bits. - */ -/* The MWAIT instruction is available (per section MONITOR / MWAIT) */ -#define HV_X64_MWAIT_AVAILABLE BIT(0) -/* Guest debugging support is available */ -#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) -/* Performance Monitor support is available*/ -#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) -/* Support for physical CPU dynamic partitioning events is available*/ -#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) -/* - * Support for passing hypercall input parameter block via XMM - * registers is available - */ -#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) -/* Support for a virtual guest idle state is available */ -#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) -/* Frequency MSRs available */ -#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) -/* Crash MSR available */ -#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) -/* Support for debug MSRs available */ -#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) -/* Support for extended gva ranges for flush hypercalls available */ -#define HV_FEATURE_EXT_GVA_RANGES_FLUSH BIT(14) -/* - * Support for returning hypercall output block via XMM - * registers is available - */ -#define HV_X64_HYPERCALL_XMM_OUTPUT_AVAILABLE BIT(15) -/* stimer Direct Mode is available */ -#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) - -/* - * Implementation recommendations. Indicates which behaviors the hypervisor - * recommends the OS implement for optimal performance. - * These are HYPERV_CPUID_ENLIGHTMENT_INFO.EAX bits. - */ -/* - * Recommend using hypercall for address space switches rather - * than MOV to CR3 instruction - */ -#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) -/* Recommend using hypercall for local TLB flushes rather - * than INVLPG or MOV to CR3 instructions */ -#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) -/* - * Recommend using hypercall for remote TLB flushes rather - * than inter-processor interrupts - */ -#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) -/* - * Recommend using MSRs for accessing APIC registers - * EOI, ICR and TPR rather than their memory-mapped counterparts - */ -#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) -/* Recommend using the hypervisor-provided MSR to initiate a system RESET */ -#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) -/* - * Recommend using relaxed timing for this partition. If used, - * the VM should disable any watchdog timeouts that rely on the - * timely delivery of external interrupts - */ -#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) - -/* - * Recommend not using Auto End-Of-Interrupt feature - */ -#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) - -/* - * Recommend using cluster IPI hypercalls. - */ -#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) - -/* Recommend using the newer ExProcessorMasks interface */ -#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) - -/* Indicates that the hypervisor is nested within a Hyper-V partition. */ -#define HV_X64_HYPERV_NESTED BIT(12) - -/* Recommend using enlightened VMCS */ -#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) - -/* Use hypercalls for MMIO config space access */ -#define HV_X64_USE_MMIO_HYPERCALLS BIT(21) - -/* - * CPU management features identification. - * These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits. - */ -#define HV_X64_START_LOGICAL_PROCESSOR BIT(0) -#define HV_X64_CREATE_ROOT_VIRTUAL_PROCESSOR BIT(1) -#define HV_X64_PERFORMANCE_COUNTER_SYNC BIT(2) -#define HV_X64_RESERVED_IDENTITY_BIT BIT(31) - -/* - * Virtual processor will never share a physical core with another virtual - * processor, except for virtual processors that are reported as sibling SMT - * threads. - */ -#define HV_X64_NO_NONARCH_CORESHARING BIT(18) - -/* Nested features. These are HYPERV_CPUID_NESTED_FEATURES.EAX bits. */ -#define HV_X64_NESTED_DIRECT_FLUSH BIT(17) -#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) -#define HV_X64_NESTED_MSR_BITMAP BIT(19) - -/* Nested features #2. These are HYPERV_CPUID_NESTED_FEATURES.EBX bits. */ -#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL BIT(0) - -/* - * This is specific to AMD and specifies that enlightened TLB flush is - * supported. If guest opts in to this feature, ASID invalidations only - * flushes gva -> hpa mapping entries. To flush the TLB entries derived - * from NPT, hypercalls should be used (HvFlushGuestPhysicalAddressSpace - * or HvFlushGuestPhysicalAddressList). - */ -#define HV_X64_NESTED_ENLIGHTENED_TLB BIT(22) - -/* HYPERV_CPUID_ISOLATION_CONFIG.EAX bits. */ -#define HV_PARAVISOR_PRESENT BIT(0) - -/* HYPERV_CPUID_ISOLATION_CONFIG.EBX bits. */ -#define HV_ISOLATION_TYPE GENMASK(3, 0) -#define HV_SHARED_GPA_BOUNDARY_ACTIVE BIT(5) -#define HV_SHARED_GPA_BOUNDARY_BITS GENMASK(11, 6) - -enum hv_isolation_type { - HV_ISOLATION_TYPE_NONE = 0, - HV_ISOLATION_TYPE_VBS = 1, - HV_ISOLATION_TYPE_SNP = 2, - HV_ISOLATION_TYPE_TDX = 3 -}; - -/* Hyper-V specific model specific registers (MSRs) */ - -/* MSR used to identify the guest OS. */ -#define HV_X64_MSR_GUEST_OS_ID 0x40000000 - -/* MSR used to setup pages used to communicate with the hypervisor. */ -#define HV_X64_MSR_HYPERCALL 0x40000001 - -/* MSR used to provide vcpu index */ -#define HV_X64_MSR_VP_INDEX 0x40000002 - -/* MSR used to reset the guest OS. */ -#define HV_X64_MSR_RESET 0x40000003 - -/* MSR used to provide vcpu runtime in 100ns units */ -#define HV_X64_MSR_VP_RUNTIME 0x40000010 - -/* MSR used to read the per-partition time reference counter */ -#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 - -/* A partition's reference time stamp counter (TSC) page */ -#define HV_X64_MSR_REFERENCE_TSC 0x40000021 - -/* MSR used to retrieve the TSC frequency */ -#define HV_X64_MSR_TSC_FREQUENCY 0x40000022 - -/* MSR used to retrieve the local APIC timer frequency */ -#define HV_X64_MSR_APIC_FREQUENCY 0x40000023 - -/* Define the virtual APIC registers */ -#define HV_X64_MSR_EOI 0x40000070 -#define HV_X64_MSR_ICR 0x40000071 -#define HV_X64_MSR_TPR 0x40000072 -#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 - -/* Define synthetic interrupt controller model specific registers. */ -#define HV_X64_MSR_SCONTROL 0x40000080 -#define HV_X64_MSR_SVERSION 0x40000081 -#define HV_X64_MSR_SIEFP 0x40000082 -#define HV_X64_MSR_SIMP 0x40000083 -#define HV_X64_MSR_EOM 0x40000084 -#define HV_X64_MSR_SINT0 0x40000090 -#define HV_X64_MSR_SINT1 0x40000091 -#define HV_X64_MSR_SINT2 0x40000092 -#define HV_X64_MSR_SINT3 0x40000093 -#define HV_X64_MSR_SINT4 0x40000094 -#define HV_X64_MSR_SINT5 0x40000095 -#define HV_X64_MSR_SINT6 0x40000096 -#define HV_X64_MSR_SINT7 0x40000097 -#define HV_X64_MSR_SINT8 0x40000098 -#define HV_X64_MSR_SINT9 0x40000099 -#define HV_X64_MSR_SINT10 0x4000009A -#define HV_X64_MSR_SINT11 0x4000009B -#define HV_X64_MSR_SINT12 0x4000009C -#define HV_X64_MSR_SINT13 0x4000009D -#define HV_X64_MSR_SINT14 0x4000009E -#define HV_X64_MSR_SINT15 0x4000009F - -/* - * Define synthetic interrupt controller model specific registers for - * nested hypervisor. - */ -#define HV_X64_MSR_NESTED_SCONTROL 0x40001080 -#define HV_X64_MSR_NESTED_SVERSION 0x40001081 -#define HV_X64_MSR_NESTED_SIEFP 0x40001082 -#define HV_X64_MSR_NESTED_SIMP 0x40001083 -#define HV_X64_MSR_NESTED_EOM 0x40001084 -#define HV_X64_MSR_NESTED_SINT0 0x40001090 - -/* - * Synthetic Timer MSRs. Four timers per vcpu. - */ -#define HV_X64_MSR_STIMER0_CONFIG 0x400000B0 -#define HV_X64_MSR_STIMER0_COUNT 0x400000B1 -#define HV_X64_MSR_STIMER1_CONFIG 0x400000B2 -#define HV_X64_MSR_STIMER1_COUNT 0x400000B3 -#define HV_X64_MSR_STIMER2_CONFIG 0x400000B4 -#define HV_X64_MSR_STIMER2_COUNT 0x400000B5 -#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 -#define HV_X64_MSR_STIMER3_COUNT 0x400000B7 - -/* Hyper-V guest idle MSR */ -#define HV_X64_MSR_GUEST_IDLE 0x400000F0 - -/* Hyper-V guest crash notification MSR's */ -#define HV_X64_MSR_CRASH_P0 0x40000100 -#define HV_X64_MSR_CRASH_P1 0x40000101 -#define HV_X64_MSR_CRASH_P2 0x40000102 -#define HV_X64_MSR_CRASH_P3 0x40000103 -#define HV_X64_MSR_CRASH_P4 0x40000104 -#define HV_X64_MSR_CRASH_CTL 0x40000105 - -/* TSC emulation after migration */ -#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 -#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 -#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 - -/* TSC invariant control */ -#define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118 - -/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ -#define HV_EXPOSE_INVARIANT_TSC BIT_ULL(0) - -/* - * To support arch-generic code calling hv_set/get_register: - * - On x86, HV_MSR_ indicates an MSR accessed via rdmsrl/wrmsrl - * - On ARM, HV_MSR_ indicates a VP register accessed via hypercall - */ -#define HV_MSR_CRASH_P0 (HV_X64_MSR_CRASH_P0) -#define HV_MSR_CRASH_P1 (HV_X64_MSR_CRASH_P1) -#define HV_MSR_CRASH_P2 (HV_X64_MSR_CRASH_P2) -#define HV_MSR_CRASH_P3 (HV_X64_MSR_CRASH_P3) -#define HV_MSR_CRASH_P4 (HV_X64_MSR_CRASH_P4) -#define HV_MSR_CRASH_CTL (HV_X64_MSR_CRASH_CTL) - -#define HV_MSR_VP_INDEX (HV_X64_MSR_VP_INDEX) -#define HV_MSR_TIME_REF_COUNT (HV_X64_MSR_TIME_REF_COUNT) -#define HV_MSR_REFERENCE_TSC (HV_X64_MSR_REFERENCE_TSC) - -#define HV_MSR_SINT0 (HV_X64_MSR_SINT0) -#define HV_MSR_SVERSION (HV_X64_MSR_SVERSION) -#define HV_MSR_SCONTROL (HV_X64_MSR_SCONTROL) -#define HV_MSR_SIEFP (HV_X64_MSR_SIEFP) -#define HV_MSR_SIMP (HV_X64_MSR_SIMP) -#define HV_MSR_EOM (HV_X64_MSR_EOM) - -#define HV_MSR_NESTED_SCONTROL (HV_X64_MSR_NESTED_SCONTROL) -#define HV_MSR_NESTED_SVERSION (HV_X64_MSR_NESTED_SVERSION) -#define HV_MSR_NESTED_SIEFP (HV_X64_MSR_NESTED_SIEFP) -#define HV_MSR_NESTED_SIMP (HV_X64_MSR_NESTED_SIMP) -#define HV_MSR_NESTED_EOM (HV_X64_MSR_NESTED_EOM) -#define HV_MSR_NESTED_SINT0 (HV_X64_MSR_NESTED_SINT0) - -#define HV_MSR_STIMER0_CONFIG (HV_X64_MSR_STIMER0_CONFIG) -#define HV_MSR_STIMER0_COUNT (HV_X64_MSR_STIMER0_COUNT) - -/* - * Registers are only accessible via HVCALL_GET_VP_REGISTERS hvcall and - * there is not associated MSR address. - */ -#define HV_X64_REGISTER_VSM_VP_STATUS 0x000D0003 -#define HV_X64_VTL_MASK GENMASK(3, 0) - -/* Hyper-V memory host visibility */ -enum hv_mem_host_visibility { - VMBUS_PAGE_NOT_VISIBLE = 0, - VMBUS_PAGE_VISIBLE_READ_ONLY = 1, - VMBUS_PAGE_VISIBLE_READ_WRITE = 3 -}; - -/* HvCallModifySparseGpaPageHostVisibility hypercall */ -#define HV_MAX_MODIFY_GPA_REP_COUNT ((PAGE_SIZE / sizeof(u64)) - 2) -struct hv_gpa_range_for_visibility { - u64 partition_id; - u32 host_visibility:2; - u32 reserved0:30; - u32 reserved1; - u64 gpa_page_list[HV_MAX_MODIFY_GPA_REP_COUNT]; -} __packed; - -/* - * Declare the MSR used to setup pages used to communicate with the hypervisor. - */ -union hv_x64_msr_hypercall_contents { - u64 as_uint64; - struct { - u64 enable:1; - u64 reserved:11; - u64 guest_physical_address:52; - } __packed; -}; - -union hv_vp_assist_msr_contents { - u64 as_uint64; - struct { - u64 enable:1; - u64 reserved:11; - u64 pfn:52; - } __packed; -}; - -struct hv_reenlightenment_control { - __u64 vector:8; - __u64 reserved1:8; - __u64 enabled:1; - __u64 reserved2:15; - __u64 target_vp:32; -} __packed; - -struct hv_tsc_emulation_control { - __u64 enabled:1; - __u64 reserved:63; -} __packed; - -struct hv_tsc_emulation_status { - __u64 inprogress:1; - __u64 reserved:63; -} __packed; - -#define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 -#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12 -#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ - (~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1)) - -#define HV_X64_MSR_CRASH_PARAMS \ - (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) - -#define HV_IPI_LOW_VECTOR 0x10 -#define HV_IPI_HIGH_VECTOR 0xff - -#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 -#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 -#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ - (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) - -/* Hyper-V Enlightened VMCS version mask in nested features CPUID */ -#define HV_X64_ENLIGHTENED_VMCS_VERSION 0xff - -#define HV_X64_MSR_TSC_REFERENCE_ENABLE 0x00000001 -#define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT 12 - -/* Number of XMM registers used in hypercall input/output */ -#define HV_HYPERCALL_MAX_XMM_REGISTERS 6 - -struct hv_nested_enlightenments_control { - struct { - __u32 directhypercall:1; - __u32 reserved:31; - } features; - struct { - __u32 inter_partition_comm:1; - __u32 reserved:31; - } hypercallControls; -} __packed; - -/* Define virtual processor assist page structure. */ -struct hv_vp_assist_page { - __u32 apic_assist; - __u32 reserved1; - __u32 vtl_entry_reason; - __u32 vtl_reserved; - __u64 vtl_ret_x64rax; - __u64 vtl_ret_x64rcx; - struct hv_nested_enlightenments_control nested_control; - __u8 enlighten_vmentry; - __u8 reserved2[7]; - __u64 current_nested_vmcs; - __u8 synthetic_time_unhalted_timer_expired; - __u8 reserved3[7]; - __u8 virtualization_fault_information[40]; - __u8 reserved4[8]; - __u8 intercept_message[256]; - __u8 vtl_ret_actions[256]; -} __packed; - -struct hv_enlightened_vmcs { - u32 revision_id; - u32 abort; - - u16 host_es_selector; - u16 host_cs_selector; - u16 host_ss_selector; - u16 host_ds_selector; - u16 host_fs_selector; - u16 host_gs_selector; - u16 host_tr_selector; - - u16 padding16_1; - - u64 host_ia32_pat; - u64 host_ia32_efer; - - u64 host_cr0; - u64 host_cr3; - u64 host_cr4; - - u64 host_ia32_sysenter_esp; - u64 host_ia32_sysenter_eip; - u64 host_rip; - u32 host_ia32_sysenter_cs; - - u32 pin_based_vm_exec_control; - u32 vm_exit_controls; - u32 secondary_vm_exec_control; - - u64 io_bitmap_a; - u64 io_bitmap_b; - u64 msr_bitmap; - - u16 guest_es_selector; - u16 guest_cs_selector; - u16 guest_ss_selector; - u16 guest_ds_selector; - u16 guest_fs_selector; - u16 guest_gs_selector; - u16 guest_ldtr_selector; - u16 guest_tr_selector; - - u32 guest_es_limit; - u32 guest_cs_limit; - u32 guest_ss_limit; - u32 guest_ds_limit; - u32 guest_fs_limit; - u32 guest_gs_limit; - u32 guest_ldtr_limit; - u32 guest_tr_limit; - u32 guest_gdtr_limit; - u32 guest_idtr_limit; - - u32 guest_es_ar_bytes; - u32 guest_cs_ar_bytes; - u32 guest_ss_ar_bytes; - u32 guest_ds_ar_bytes; - u32 guest_fs_ar_bytes; - u32 guest_gs_ar_bytes; - u32 guest_ldtr_ar_bytes; - u32 guest_tr_ar_bytes; - - u64 guest_es_base; - u64 guest_cs_base; - u64 guest_ss_base; - u64 guest_ds_base; - u64 guest_fs_base; - u64 guest_gs_base; - u64 guest_ldtr_base; - u64 guest_tr_base; - u64 guest_gdtr_base; - u64 guest_idtr_base; - - u64 padding64_1[3]; - - u64 vm_exit_msr_store_addr; - u64 vm_exit_msr_load_addr; - u64 vm_entry_msr_load_addr; - - u64 cr3_target_value0; - u64 cr3_target_value1; - u64 cr3_target_value2; - u64 cr3_target_value3; - - u32 page_fault_error_code_mask; - u32 page_fault_error_code_match; - - u32 cr3_target_count; - u32 vm_exit_msr_store_count; - u32 vm_exit_msr_load_count; - u32 vm_entry_msr_load_count; - - u64 tsc_offset; - u64 virtual_apic_page_addr; - u64 vmcs_link_pointer; - - u64 guest_ia32_debugctl; - u64 guest_ia32_pat; - u64 guest_ia32_efer; - - u64 guest_pdptr0; - u64 guest_pdptr1; - u64 guest_pdptr2; - u64 guest_pdptr3; - - u64 guest_pending_dbg_exceptions; - u64 guest_sysenter_esp; - u64 guest_sysenter_eip; - - u32 guest_activity_state; - u32 guest_sysenter_cs; - - u64 cr0_guest_host_mask; - u64 cr4_guest_host_mask; - u64 cr0_read_shadow; - u64 cr4_read_shadow; - u64 guest_cr0; - u64 guest_cr3; - u64 guest_cr4; - u64 guest_dr7; - - u64 host_fs_base; - u64 host_gs_base; - u64 host_tr_base; - u64 host_gdtr_base; - u64 host_idtr_base; - u64 host_rsp; - - u64 ept_pointer; - - u16 virtual_processor_id; - u16 padding16_2[3]; - - u64 padding64_2[5]; - u64 guest_physical_address; - - u32 vm_instruction_error; - u32 vm_exit_reason; - u32 vm_exit_intr_info; - u32 vm_exit_intr_error_code; - u32 idt_vectoring_info_field; - u32 idt_vectoring_error_code; - u32 vm_exit_instruction_len; - u32 vmx_instruction_info; - - u64 exit_qualification; - u64 exit_io_instruction_ecx; - u64 exit_io_instruction_esi; - u64 exit_io_instruction_edi; - u64 exit_io_instruction_eip; - - u64 guest_linear_address; - u64 guest_rsp; - u64 guest_rflags; - - u32 guest_interruptibility_info; - u32 cpu_based_vm_exec_control; - u32 exception_bitmap; - u32 vm_entry_controls; - u32 vm_entry_intr_info_field; - u32 vm_entry_exception_error_code; - u32 vm_entry_instruction_len; - u32 tpr_threshold; - - u64 guest_rip; - - u32 hv_clean_fields; - u32 padding32_1; - u32 hv_synthetic_controls; - struct { - u32 nested_flush_hypercall:1; - u32 msr_bitmap:1; - u32 reserved:30; - } __packed hv_enlightenments_control; - u32 hv_vp_id; - u32 padding32_2; - u64 hv_vm_id; - u64 partition_assist_page; - u64 padding64_4[4]; - u64 guest_bndcfgs; - u64 guest_ia32_perf_global_ctrl; - u64 guest_ia32_s_cet; - u64 guest_ssp; - u64 guest_ia32_int_ssp_table_addr; - u64 guest_ia32_lbr_ctl; - u64 padding64_5[2]; - u64 xss_exit_bitmap; - u64 encls_exiting_bitmap; - u64 host_ia32_perf_global_ctrl; - u64 tsc_multiplier; - u64 host_ia32_s_cet; - u64 host_ssp; - u64 host_ia32_int_ssp_table_addr; - u64 padding64_6; -} __packed; - -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP BIT(1) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2 BIT(2) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1 BIT(3) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC BIT(4) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT BIT(5) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY BIT(6) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN BIT(7) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR BIT(8) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT BIT(9) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC BIT(10) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1 BIT(11) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2 BIT(12) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER BIT(13) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1 BIT(14) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL BIT(15) - -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF - -/* - * Note, Hyper-V isn't actually stealing bit 28 from Intel, just abusing it by - * pairing it with architecturally impossible exit reasons. Bit 28 is set only - * on SMI exits to a SMI transfer monitor (STM) and if and only if a MTF VM-Exit - * is pending. I.e. it will never be set by hardware for non-SMI exits (there - * are only three), nor will it ever be set unless the VMM is an STM. - */ -#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031 - -/* - * Hyper-V uses the software reserved 32 bytes in VMCB control area to expose - * SVM enlightenments to guests. - */ -struct hv_vmcb_enlightenments { - struct __packed hv_enlightenments_control { - u32 nested_flush_hypercall:1; - u32 msr_bitmap:1; - u32 enlightened_npt_tlb: 1; - u32 reserved:29; - } __packed hv_enlightenments_control; - u32 hv_vp_id; - u64 hv_vm_id; - u64 partition_assist_page; - u64 reserved; -} __packed; - -/* - * Hyper-V uses the software reserved clean bit in VMCB. - */ -#define HV_VMCB_NESTED_ENLIGHTENMENTS 31 - -/* Synthetic VM-Exit */ -#define HV_SVM_EXITCODE_ENL 0xf0000000 -#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1) - -struct hv_partition_assist_pg { - u32 tlb_lock_count; -}; - -enum hv_interrupt_type { - HV_X64_INTERRUPT_TYPE_FIXED = 0x0000, - HV_X64_INTERRUPT_TYPE_LOWESTPRIORITY = 0x0001, - HV_X64_INTERRUPT_TYPE_SMI = 0x0002, - HV_X64_INTERRUPT_TYPE_REMOTEREAD = 0x0003, - HV_X64_INTERRUPT_TYPE_NMI = 0x0004, - HV_X64_INTERRUPT_TYPE_INIT = 0x0005, - HV_X64_INTERRUPT_TYPE_SIPI = 0x0006, - HV_X64_INTERRUPT_TYPE_EXTINT = 0x0007, - HV_X64_INTERRUPT_TYPE_LOCALINT0 = 0x0008, - HV_X64_INTERRUPT_TYPE_LOCALINT1 = 0x0009, - HV_X64_INTERRUPT_TYPE_MAXIMUM = 0x000A, -}; - -union hv_msi_address_register { - u32 as_uint32; - struct { - u32 reserved1:2; - u32 destination_mode:1; - u32 redirection_hint:1; - u32 reserved2:8; - u32 destination_id:8; - u32 msi_base:12; - }; -} __packed; - -union hv_msi_data_register { - u32 as_uint32; - struct { - u32 vector:8; - u32 delivery_mode:3; - u32 reserved1:3; - u32 level_assert:1; - u32 trigger_mode:1; - u32 reserved2:16; - }; -} __packed; - -/* HvRetargetDeviceInterrupt hypercall */ -union hv_msi_entry { - u64 as_uint64; - struct { - union hv_msi_address_register address; - union hv_msi_data_register data; - } __packed; -}; - -struct hv_x64_segment_register { - u64 base; - u32 limit; - u16 selector; - union { - struct { - u16 segment_type : 4; - u16 non_system_segment : 1; - u16 descriptor_privilege_level : 2; - u16 present : 1; - u16 reserved : 4; - u16 available : 1; - u16 _long : 1; - u16 _default : 1; - u16 granularity : 1; - } __packed; - u16 attributes; - }; -} __packed; - -struct hv_x64_table_register { - u16 pad[3]; - u16 limit; - u64 base; -} __packed; - -struct hv_init_vp_context { - u64 rip; - u64 rsp; - u64 rflags; - - struct hv_x64_segment_register cs; - struct hv_x64_segment_register ds; - struct hv_x64_segment_register es; - struct hv_x64_segment_register fs; - struct hv_x64_segment_register gs; - struct hv_x64_segment_register ss; - struct hv_x64_segment_register tr; - struct hv_x64_segment_register ldtr; - - struct hv_x64_table_register idtr; - struct hv_x64_table_register gdtr; - - u64 efer; - u64 cr0; - u64 cr3; - u64 cr4; - u64 msr_cr_pat; -} __packed; - -union hv_input_vtl { - u8 as_uint8; - struct { - u8 target_vtl: 4; - u8 use_target_vtl: 1; - u8 reserved_z: 3; - }; -} __packed; - -struct hv_enable_vp_vtl { - u64 partition_id; - u32 vp_index; - union hv_input_vtl target_vtl; - u8 mbz0; - u16 mbz1; - struct hv_init_vp_context vp_context; -} __packed; - -struct hv_get_vp_from_apic_id_in { - u64 partition_id; - union hv_input_vtl target_vtl; - u8 res[7]; - u32 apic_ids[]; -} __packed; - -#include - -#endif diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 14d72727d7ee..0e82ebc5d1e1 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_INIT_H #define _ASM_X86_INIT_H -#define __head __section(".head.text") +#define __head __section(".head.text") __no_sanitize_undefined struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ diff --git a/arch/x86/include/asm/intel_punit_ipc.h b/arch/x86/include/asm/intel_punit_ipc.h index ce16da719596..1f9b5d225912 100644 --- a/arch/x86/include/asm/intel_punit_ipc.h +++ b/arch/x86/include/asm/intel_punit_ipc.h @@ -80,17 +80,10 @@ typedef enum { #if IS_ENABLED(CONFIG_INTEL_PUNIT_IPC) -int intel_punit_ipc_simple_command(int cmd, int para1, int para2); int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, u32 *in, u32 *out); #else -static inline int intel_punit_ipc_simple_command(int cmd, - int para1, int para2) -{ - return -ENODEV; -} - static inline int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, u32 *in, u32 *out) { diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index b71ad173f877..562a547c29a5 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -100,8 +100,8 @@ } #define ASM_CALL_ARG0 \ - "call %c[__func] \n" \ - ASM_REACHABLE + "1: call %c[__func] \n" \ + ANNOTATE_REACHABLE(1b) #define ASM_CALL_ARG1 \ "movq %[arg1], %%rdi \n" \ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index ae5482a2f0ca..8ad187462b68 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -8,14 +8,9 @@ # define PA_PGD 2 # define PA_SWAP_PAGE 3 # define PAGES_NR 4 -#else -# define PA_CONTROL_PAGE 0 -# define VA_CONTROL_PAGE 1 -# define PA_TABLE_PAGE 2 -# define PA_SWAP_PAGE 3 -# define PAGES_NR 4 #endif +# define KEXEC_CONTROL_PAGE_SIZE 4096 # define KEXEC_CONTROL_CODE_MAX_SIZE 2048 #ifndef __ASSEMBLY__ @@ -43,7 +38,6 @@ struct kimage; /* Maximum address we can use for the control code buffer */ # define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE -# define KEXEC_CONTROL_PAGE_SIZE 4096 /* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_386 @@ -58,11 +52,12 @@ struct kimage; /* Maximum address we can use for the control pages */ # define KEXEC_CONTROL_MEMORY_LIMIT (MAXMEM-1) -/* Allocate one page for the pdp and the second for the code */ -# define KEXEC_CONTROL_PAGE_SIZE (4096UL + 4096UL) - /* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_X86_64 + +extern unsigned long kexec_va_control_page; +extern unsigned long kexec_pa_table_page; +extern unsigned long kexec_pa_swap_page; #endif /* @@ -116,21 +111,21 @@ static inline void crash_setup_regs(struct pt_regs *newregs, } #ifdef CONFIG_X86_32 -asmlinkage unsigned long -relocate_kernel(unsigned long indirection_page, - unsigned long control_page, - unsigned long start_address, - unsigned int has_pae, - unsigned int preserve_context); +typedef asmlinkage unsigned long +relocate_kernel_fn(unsigned long indirection_page, + unsigned long control_page, + unsigned long start_address, + unsigned int has_pae, + unsigned int preserve_context); #else -unsigned long -relocate_kernel(unsigned long indirection_page, - unsigned long page_list, - unsigned long start_address, - unsigned int preserve_context, - unsigned int host_mem_enc_active); +typedef unsigned long +relocate_kernel_fn(unsigned long indirection_page, + unsigned long pa_control_page, + unsigned long start_address, + unsigned int preserve_context, + unsigned int host_mem_enc_active); #endif - +extern relocate_kernel_fn relocate_kernel; #define ARCH_HAS_KIMAGE_ARCH #ifdef CONFIG_X86_32 @@ -145,6 +140,19 @@ struct kimage_arch { }; #else struct kimage_arch { + /* + * This is a kimage control page, as it must not overlap with either + * source or destination address ranges. + */ + pgd_t *pgd; + /* + * The virtual mapping of the control code page itself is used only + * during the transition, while the current kernel's pages are all + * in place. Thus the intermediate page table pages used to map it + * are not control pages, but instead just normal pages obtained + * with get_zeroed_page(). And have to be tracked (below) so that + * they can be freed. + */ p4d_t *p4d; pud_t *pud; pmd_t *pmd; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 5aff7222e40f..c35550581da0 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -83,7 +83,6 @@ KVM_X86_OP(enable_nmi_window) KVM_X86_OP(enable_irq_window) KVM_X86_OP_OPTIONAL(update_cr8_intercept) KVM_X86_OP(refresh_apicv_exec_ctrl) -KVM_X86_OP_OPTIONAL(hwapic_irr_update) KVM_X86_OP_OPTIONAL(hwapic_isr_update) KVM_X86_OP_OPTIONAL(load_eoi_exitmap) KVM_X86_OP_OPTIONAL(set_virtual_apic_mode) @@ -94,12 +93,17 @@ KVM_X86_OP_OPTIONAL_RET0(set_tss_addr) KVM_X86_OP_OPTIONAL_RET0(set_identity_map_addr) KVM_X86_OP_OPTIONAL_RET0(get_mt_mask) KVM_X86_OP(load_mmu_pgd) +KVM_X86_OP_OPTIONAL(link_external_spt) +KVM_X86_OP_OPTIONAL(set_external_spte) +KVM_X86_OP_OPTIONAL(free_external_spt) +KVM_X86_OP_OPTIONAL(remove_external_spte) KVM_X86_OP(has_wbinvd_exit) KVM_X86_OP(get_l2_tsc_offset) KVM_X86_OP(get_l2_tsc_multiplier) KVM_X86_OP(write_tsc_offset) KVM_X86_OP(write_tsc_multiplier) KVM_X86_OP(get_exit_info) +KVM_X86_OP(get_entry_info) KVM_X86_OP(check_intercept) KVM_X86_OP(handle_exit_irqoff) KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e159e44a6a1b..b15cde0a9b5c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -24,9 +24,9 @@ #include #include #include -#include #include #include +#include #include #include @@ -36,8 +36,8 @@ #include #include #include -#include #include +#include #define __KVM_HAVE_ARCH_VCPU_DEBUGFS @@ -313,10 +313,11 @@ struct kvm_kernel_irq_routing_entry; * the number of unique SPs that can theoretically be created is 2^n, where n * is the number of bits that are used to compute the role. * - * But, even though there are 19 bits in the mask below, not all combinations + * But, even though there are 20 bits in the mask below, not all combinations * of modes and flags are possible: * - * - invalid shadow pages are not accounted, so the bits are effectively 18 + * - invalid shadow pages are not accounted, mirror pages are not shadowed, + * so the bits are effectively 18. * * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); * execonly and ad_disabled are only used for nested EPT which has @@ -349,7 +350,8 @@ union kvm_mmu_page_role { unsigned ad_disabled:1; unsigned guest_mode:1; unsigned passthrough:1; - unsigned :5; + unsigned is_mirror:1; + unsigned :4; /* * This is left at the top of the word so that @@ -457,6 +459,7 @@ struct kvm_mmu { int (*sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i); struct kvm_mmu_root_info root; + hpa_t mirror_root_hpa; union kvm_cpu_role cpu_role; union kvm_mmu_page_role root_role; @@ -739,6 +742,23 @@ struct kvm_queued_exception { bool has_payload; }; +/* + * Hardware-defined CPUID leafs that are either scattered by the kernel or are + * unknown to the kernel, but need to be directly used by KVM. Note, these + * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. + */ +enum kvm_only_cpuid_leafs { + CPUID_12_EAX = NCAPINTS, + CPUID_7_1_EDX, + CPUID_8000_0007_EDX, + CPUID_8000_0022_EAX, + CPUID_7_2_EDX, + CPUID_24_0_EBX, + NR_KVM_CPU_CAPS, + + NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -813,6 +833,11 @@ struct kvm_vcpu_arch { struct kvm_mmu_memory_cache mmu_shadow_page_cache; struct kvm_mmu_memory_cache mmu_shadowed_info_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; + /* + * This cache is to allocate external page table. E.g. private EPT used + * by the TDX module. + */ + struct kvm_mmu_memory_cache mmu_external_spt_cache; /* * QEMU userspace and the guest each have their own FPU state. @@ -854,27 +879,23 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; - struct kvm_hypervisor_cpuid kvm_cpuid; bool is_amd_compatible; /* - * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly - * when "struct kvm_vcpu_arch" is no longer defined in an - * arch/x86/include/asm header. The max is mostly arbitrary, i.e. - * can be increased as necessary. + * cpu_caps holds the effective guest capabilities, i.e. the features + * the vCPU is allowed to use. Typically, but not always, features can + * be used by the guest if and only if both KVM and userspace want to + * expose the feature to the guest. + * + * A common exception is for virtualization holes, i.e. when KVM can't + * prevent the guest from using a feature, in which case the vCPU "has" + * the feature regardless of what KVM or userspace desires. + * + * Note, features that don't require KVM involvement in any way are + * NOT enforced/sanitized by KVM, i.e. are taken verbatim from the + * guest CPUID provided by userspace. */ -#define KVM_MAX_NR_GOVERNED_FEATURES BITS_PER_LONG - - /* - * Track whether or not the guest is allowed to use features that are - * governed by KVM, where "governed" means KVM needs to manage state - * and/or explicitly enable the feature in hardware. Typically, but - * not always, governed features can be used by the guest if and only - * if both KVM and userspace want to expose the feature to the guest. - */ - struct { - DECLARE_BITMAP(enabled, KVM_MAX_NR_GOVERNED_FEATURES); - } governed_features; + u32 cpu_caps[NR_KVM_CPU_CAPS]; u64 reserved_gpa_bits; int maxphyaddr; @@ -1445,6 +1466,7 @@ struct kvm_arch { struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; struct vhost_task *nx_huge_page_recovery_thread; u64 nx_huge_page_last; + struct once nx_once; #ifdef CONFIG_X86_64 /* The number of TDP MMU pages across all roots. */ @@ -1536,6 +1558,8 @@ struct kvm_arch { */ #define SPLIT_DESC_CACHE_MIN_NR_OBJECTS (SPTE_ENT_PER_PAGE + 1) struct kvm_mmu_memory_cache split_desc_cache; + + gfn_t gfn_direct_bits; }; struct kvm_vm_stat { @@ -1734,8 +1758,7 @@ struct kvm_x86_ops { const unsigned long required_apicv_inhibits; bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); - void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); - void (*hwapic_isr_update)(int isr); + void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu); @@ -1749,6 +1772,21 @@ struct kvm_x86_ops { void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); + /* Update external mapping with page table link. */ + int (*link_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + void *external_spt); + /* Update the external page table from spte getting set. */ + int (*set_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + kvm_pfn_t pfn_for_gfn); + + /* Update external page tables for page table about to be freed. */ + int (*free_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + void *external_spt); + + /* Update external page table from spte getting removed, and flush TLB. */ + int (*remove_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + kvm_pfn_t pfn_for_gfn); + bool (*has_wbinvd_exit)(void); u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); @@ -1757,12 +1795,15 @@ struct kvm_x86_ops { void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu); /* - * Retrieve somewhat arbitrary exit information. Intended to + * Retrieve somewhat arbitrary exit/entry information. Intended to * be used only from within tracepoints or error paths. */ void (*get_exit_info)(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, u64 *info2, - u32 *exit_int_info, u32 *exit_int_info_err_code); + u32 *intr_info, u32 *error_code); + + void (*get_entry_info)(struct kvm_vcpu *vcpu, + u32 *intr_info, u32 *error_code); int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, @@ -2019,8 +2060,8 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); * VMware backdoor emulation handles select instructions * and reinjects the #GP for all other cases. * - * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which - * case the CR2/GPA value pass on the stack is valid. + * EMULTYPE_PF - Set when an intercepted #PF triggers the emulation, in which case + * the CR2/GPA value pass on the stack is valid. * * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility * state and inject single-step #DBs after skipping @@ -2055,6 +2096,11 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); #define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) #define EMULTYPE_WRITE_PF_TO_SP (1 << 8) +static inline bool kvm_can_emulate_event_vectoring(int emul_type) +{ + return !(emul_type & EMULTYPE_PF); +} + int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); @@ -2062,6 +2108,8 @@ void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, u8 ndata); void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); +void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa); + void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data); @@ -2181,12 +2229,6 @@ static inline void kvm_clear_apicv_inhibit(struct kvm *kvm, kvm_set_or_clear_apicv_inhibit(kvm, reason, false); } -unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, - unsigned long a0, unsigned long a1, - unsigned long a2, unsigned long a3, - int op_64_bit, int cpl); -int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); - int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4543cf2eb5e8..eb2db07ef39c 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -276,7 +276,7 @@ static inline void cmci_rediscover(void) {} static inline void cmci_recheck(void) {} #endif -int mce_available(struct cpuinfo_x86 *c); +bool mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); bool mce_is_correctable(struct mce *m); bool mce_usable_address(struct mce *m); @@ -296,7 +296,7 @@ enum mcp_flags { void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); -int mce_notify_irq(void); +bool mce_notify_irq(void); DECLARE_PER_CPU(struct mce, injectm); @@ -386,8 +386,6 @@ static inline bool amd_mce_is_memory_error(struct mce *m) { return false; }; static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { } #endif -static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); } - unsigned long copy_mc_fragile_handle_tail(char *to, char *from, unsigned len); #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index ce4677b8b735..3b496cdcb74b 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -37,6 +37,8 @@ typedef struct { */ atomic64_t tlb_gen; + unsigned long next_trim_cpumask; + #ifdef CONFIG_MODIFY_LDT_SYSCALL struct rw_semaphore ldt_usr_sem; struct ldt_struct *ldt; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 2886cb668d7f..795fdd53bd0a 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -151,6 +151,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); + mm->context.next_trim_cpumask = jiffies + HZ; #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5f0bc6a6d025..f91ab1e75f9f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -6,10 +6,9 @@ #include #include #include -#include #include #include -#include +#include /* * Hyper-V always provides a single IO-APIC at this MMIO address. diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3ae84c3b8e6d..9a71880eec07 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -608,6 +608,7 @@ #define MSR_AMD_PERF_CTL 0xc0010062 #define MSR_AMD_PERF_STATUS 0xc0010063 #define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 +#define MSR_AMD64_GUEST_TSC_FREQ 0xc0010134 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 @@ -644,6 +645,7 @@ #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ #define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e +#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 @@ -682,11 +684,12 @@ #define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) #define MSR_AMD64_SNP_RESV_BIT 18 #define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) - -#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f - #define MSR_AMD64_RMP_BASE 0xc0010132 #define MSR_AMD64_RMP_END 0xc0010133 +#define MSR_AMD64_RMP_CFG 0xc0010136 +#define MSR_AMD64_SEG_RMP_ENABLED_BIT 0 +#define MSR_AMD64_SEG_RMP_ENABLED BIT_ULL(MSR_AMD64_SEG_RMP_ENABLED_BIT) +#define MSR_AMD64_RMP_SEGMENT_SHIFT(x) (((x) & GENMASK_ULL(13, 8)) >> 8) #define MSR_SVSM_CAA 0xc001f000 diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 4218248083d9..c69e269937c5 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -58,8 +58,8 @@ struct mtrr_state_type { */ # ifdef CONFIG_MTRR void mtrr_bp_init(void); -void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, - mtrr_type def_type); +void guest_force_mtrr_state(struct mtrr_var_range *var, unsigned int num_var, + mtrr_type def_type); extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform); extern void mtrr_save_fixed_ranges(void *); extern void mtrr_save_state(void); @@ -75,9 +75,9 @@ void mtrr_disable(void); void mtrr_enable(void); void mtrr_generic_set_state(void); # else -static inline void mtrr_overwrite_state(struct mtrr_var_range *var, - unsigned int num_var, - mtrr_type def_type) +static inline void guest_force_mtrr_state(struct mtrr_var_range *var, + unsigned int num_var, + mtrr_type def_type) { } diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 920426d691ce..ce857ef54cf1 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -15,7 +15,6 @@ #define MWAIT_HINT2SUBSTATE(hint) ((hint) & MWAIT_CSTATE_MASK) #define MWAIT_C1_SUBSTATE_MASK 0xf0 -#define CPUID_MWAIT_LEAF 5 #define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1 #define CPUID5_ECX_INTERRUPT_BREAK 0x2 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 96b410b1d4e8..7e8bf78c03d5 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -179,18 +179,6 @@ #ifdef __ASSEMBLY__ -/* - * This should be used immediately before an indirect jump/call. It tells - * objtool the subsequent indirect jump/call is vouched safe for retpoline - * builds. - */ -.macro ANNOTATE_RETPOLINE_SAFE -.Lhere_\@: - .pushsection .discard.retpoline_safe - .long .Lhere_\@ - .popsection -.endm - /* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions * vs RETBleed validation. @@ -350,12 +338,6 @@ #else /* __ASSEMBLY__ */ -#define ANNOTATE_RETPOLINE_SAFE \ - "999:\n\t" \ - ".pushsection .discard.retpoline_safe\n\t" \ - ".long 999b\n\t" \ - ".popsection\n\t" - typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index d4eb9e1d61b8..041aff51eb50 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -180,13 +180,6 @@ static inline void halt(void) PVOP_VCALL0(irq.halt); } -extern noinstr void pv_native_wbinvd(void); - -static __always_inline void wbinvd(void) -{ - PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN); -} - static inline u64 paravirt_read_msr(unsigned msr) { return PVOP_CALL1(u64, cpu.read_msr, msr); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 8d4fbe1be489..fea56b04f436 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -86,8 +86,6 @@ struct pv_cpu_ops { void (*update_io_bitmap)(void); #endif - void (*wbinvd)(void); - /* cpuid emulation, mostly so that caps bits can be disabled */ void (*cpuid)(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index d95f902acc52..1ac79f361645 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -41,6 +41,7 @@ #define INTEL_FIXED_0_USER (1ULL << 1) #define INTEL_FIXED_0_ANYTHREAD (1ULL << 2) #define INTEL_FIXED_0_ENABLE_PMI (1ULL << 3) +#define INTEL_FIXED_3_METRICS_CLEAR (1ULL << 2) #define HSW_IN_TX (1ULL << 32) #define HSW_IN_TX_CHECKPOINTED (1ULL << 33) @@ -372,6 +373,9 @@ static inline bool use_fixed_pseudo_encoding(u64 code) #define INTEL_TD_METRIC_MAX INTEL_TD_METRIC_MEM_BOUND #define INTEL_TD_METRIC_NUM 8 +#define INTEL_TD_CFG_METRIC_CLEAR_BIT 0 +#define INTEL_TD_CFG_METRIC_CLEAR BIT_ULL(INTEL_TD_CFG_METRIC_CLEAR_BIT) + static inline bool is_metric_idx(int idx) { return (unsigned)(idx - INTEL_PMC_IDX_METRIC_BASE) < INTEL_TD_METRIC_NUM; @@ -422,7 +426,9 @@ static inline bool is_topdown_idx(int idx) */ struct pebs_basic { - u64 format_size; + u64 format_group:32, + retire_latency:16, + format_size:16; u64 ip; u64 applicable_counters; u64 tsc; @@ -431,7 +437,17 @@ struct pebs_basic { struct pebs_meminfo { u64 address; u64 aux; - u64 latency; + union { + /* pre Alder Lake */ + u64 mem_latency; + /* Alder Lake and later */ + struct { + u64 instr_latency:16; + u64 pad2:16; + u64 cache_latency:16; + u64 pad3:16; + }; + }; u64 tsx_tuning; }; diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index dcd836b59beb..dd4841231bb9 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -147,24 +147,6 @@ static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4 set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } -static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - gfp_t gfp = GFP_KERNEL_ACCOUNT; - - if (mm == &init_mm) - gfp &= ~__GFP_ACCOUNT; - return (p4d_t *)get_zeroed_page(gfp); -} - -static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) -{ - if (!pgtable_l5_enabled()) - return; - - BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); - free_page((unsigned long)p4d); -} - extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c0975815980c..c0cd10182e90 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -98,6 +98,7 @@ struct cpuinfo_topology { // Logical ID mappings u32 logical_pkg_id; u32 logical_die_id; + u32 logical_core_id; // AMD Node ID and Nodes per Package info u32 amd_node_id; @@ -230,6 +231,8 @@ static inline unsigned long long l1tf_pfn_limit(void) return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } +void init_cpu_devs(void); +void get_cpu_vendor(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 3fa87e5e11ab..30e8ee7006f9 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -5,6 +5,7 @@ #include #include +extern char __relocate_kernel_start[], __relocate_kernel_end[]; extern char __brk_base[], __brk_limit[]; extern char __end_rodata_aligned[]; diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 0667b2a88614..85f4fde3515c 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -49,7 +49,7 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); -extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); +extern unsigned long __startup_64(unsigned long p2v_offset, struct boot_params *bp); extern void startup_64_setup_gdt_idt(void); extern void early_setup_idt(void); extern void __init do_early_exception(struct pt_regs *regs, int trapnr); diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 50f5666938c0..dcbccdb280f9 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -206,6 +206,8 @@ struct snp_psc_desc { #define GHCB_TERM_NO_SVSM 7 /* SVSM is not advertised in the secrets page */ #define GHCB_TERM_SVSM_VMPL0 8 /* SVSM is present but has set VMPL to 0 */ #define GHCB_TERM_SVSM_CAA 9 /* SVSM is present but CAA is not page aligned */ +#define GHCB_TERM_SECURE_TSC 10 /* Secure TSC initialization failed */ +#define GHCB_TERM_SVSM_CA_REMAP_FAIL 11 /* SVSM is present but CA could not be remapped */ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 91f08af31078..5d9685f92e5c 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -14,6 +14,7 @@ #include #include #include +#include #define GHCB_PROTOCOL_MIN 1ULL #define GHCB_PROTOCOL_MAX 2ULL @@ -124,6 +125,9 @@ struct snp_req_data { #define AAD_LEN 48 #define MSG_HDR_VER 1 +#define SNP_REQ_MAX_RETRY_DURATION (60*HZ) +#define SNP_REQ_RETRY_DELAY (2*HZ) + /* See SNP spec SNP_GUEST_REQUEST section for the structure */ enum msg_type { SNP_MSG_TYPE_INVALID = 0, @@ -142,6 +146,9 @@ enum msg_type { SNP_MSG_VMRK_REQ, SNP_MSG_VMRK_RSP, + SNP_MSG_TSC_INFO_REQ = 17, + SNP_MSG_TSC_INFO_RSP, + SNP_MSG_TYPE_MAX }; @@ -170,9 +177,20 @@ struct snp_guest_msg { u8 payload[PAGE_SIZE - sizeof(struct snp_guest_msg_hdr)]; } __packed; -struct sev_guest_platform_data { - u64 secrets_gpa; -}; +#define SNP_TSC_INFO_REQ_SZ 128 + +struct snp_tsc_info_req { + u8 rsvd[SNP_TSC_INFO_REQ_SZ]; +} __packed; + +struct snp_tsc_info_resp { + u32 status; + u32 rsvd1; + u64 tsc_scale; + u64 tsc_offset; + u32 tsc_factor; + u8 rsvd2[100]; +} __packed; struct snp_guest_req { void *req_buf; @@ -253,6 +271,7 @@ struct snp_msg_desc { u32 *os_area_msg_seqno; u8 *vmpck; + int vmpck_id; }; /* @@ -445,8 +464,6 @@ void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); void __noreturn snp_abort(void); void snp_dmi_setup(void); -int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, - struct snp_guest_request_ioctl *rio); int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input); void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); @@ -458,6 +475,15 @@ void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot); void snp_kexec_finish(void); void snp_kexec_begin(void); +int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id); +struct snp_msg_desc *snp_msg_alloc(void); +void snp_msg_free(struct snp_msg_desc *mdesc); +int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio); + +void __init snp_secure_tsc_prepare(void); +void __init snp_secure_tsc_init(void); + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define snp_vmpl 0 @@ -480,11 +506,6 @@ static inline void snp_set_wakeup_secondary_cpu(void) { } static inline bool snp_init(struct boot_params *bp) { return false; } static inline void snp_abort(void) { } static inline void snp_dmi_setup(void) { } -static inline int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, - struct snp_guest_request_ioctl *rio) -{ - return -ENOTTY; -} static inline int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input) { return -ENOTTY; @@ -498,6 +519,13 @@ static inline int prepare_pte_enc(struct pte_enc_desc *d) { return 0; } static inline void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot) { } static inline void snp_kexec_finish(void) { } static inline void snp_kexec_begin(void) { } +static inline int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id) { return -1; } +static inline struct snp_msg_desc *snp_msg_alloc(void) { return NULL; } +static inline void snp_msg_free(struct snp_msg_desc *mdesc) { } +static inline int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) { return -ENODEV; } +static inline void __init snp_secure_tsc_prepare(void) { } +static inline void __init snp_secure_tsc_init(void) { } #endif /* CONFIG_AMD_MEM_ENCRYPT */ diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index 89f7fcade8ae..fcbbef484a78 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -19,6 +19,32 @@ #define TDG_VM_RD 7 #define TDG_VM_WR 8 +/* TDX attributes */ +#define TDX_ATTR_DEBUG_BIT 0 +#define TDX_ATTR_DEBUG BIT_ULL(TDX_ATTR_DEBUG_BIT) +#define TDX_ATTR_HGS_PLUS_PROF_BIT 4 +#define TDX_ATTR_HGS_PLUS_PROF BIT_ULL(TDX_ATTR_HGS_PLUS_PROF_BIT) +#define TDX_ATTR_PERF_PROF_BIT 5 +#define TDX_ATTR_PERF_PROF BIT_ULL(TDX_ATTR_PERF_PROF_BIT) +#define TDX_ATTR_PMT_PROF_BIT 6 +#define TDX_ATTR_PMT_PROF BIT_ULL(TDX_ATTR_PMT_PROF_BIT) +#define TDX_ATTR_ICSSD_BIT 16 +#define TDX_ATTR_ICSSD BIT_ULL(TDX_ATTR_ICSSD_BIT) +#define TDX_ATTR_LASS_BIT 27 +#define TDX_ATTR_LASS BIT_ULL(TDX_ATTR_LASS_BIT) +#define TDX_ATTR_SEPT_VE_DISABLE_BIT 28 +#define TDX_ATTR_SEPT_VE_DISABLE BIT_ULL(TDX_ATTR_SEPT_VE_DISABLE_BIT) +#define TDX_ATTR_MIGRTABLE_BIT 29 +#define TDX_ATTR_MIGRTABLE BIT_ULL(TDX_ATTR_MIGRTABLE_BIT) +#define TDX_ATTR_PKS_BIT 30 +#define TDX_ATTR_PKS BIT_ULL(TDX_ATTR_PKS_BIT) +#define TDX_ATTR_KL_BIT 31 +#define TDX_ATTR_KL BIT_ULL(TDX_ATTR_KL_BIT) +#define TDX_ATTR_TPA_BIT 62 +#define TDX_ATTR_TPA BIT_ULL(TDX_ATTR_TPA_BIT) +#define TDX_ATTR_PERFMON_BIT 63 +#define TDX_ATTR_PERFMON BIT_ULL(TDX_ATTR_PERFMON_BIT) + /* TDX TD-Scope Metadata. To be used by TDG.VM.WR and TDG.VM.RD */ #define TDCS_CONFIG_FLAGS 0x1110000300000016 #define TDCS_TD_CTLS 0x1110000300000017 @@ -29,8 +55,16 @@ #define TDCS_CONFIG_FLEXIBLE_PENDING_VE BIT_ULL(1) /* TDCS_TD_CTLS bits */ -#define TD_CTLS_PENDING_VE_DISABLE BIT_ULL(0) -#define TD_CTLS_ENUM_TOPOLOGY BIT_ULL(1) +#define TD_CTLS_PENDING_VE_DISABLE_BIT 0 +#define TD_CTLS_PENDING_VE_DISABLE BIT_ULL(TD_CTLS_PENDING_VE_DISABLE_BIT) +#define TD_CTLS_ENUM_TOPOLOGY_BIT 1 +#define TD_CTLS_ENUM_TOPOLOGY BIT_ULL(TD_CTLS_ENUM_TOPOLOGY_BIT) +#define TD_CTLS_VIRT_CPUID2_BIT 2 +#define TD_CTLS_VIRT_CPUID2 BIT_ULL(TD_CTLS_VIRT_CPUID2_BIT) +#define TD_CTLS_REDUCE_VE_BIT 3 +#define TD_CTLS_REDUCE_VE BIT_ULL(TD_CTLS_REDUCE_VE_BIT) +#define TD_CTLS_LOCK_BIT 63 +#define TD_CTLS_LOCK BIT_ULL(TD_CTLS_LOCK_BIT) /* TDX hypercall Leaf IDs */ #define TDVMCALL_MAP_GPA 0x10001 diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index bab490379c65..2de1e5a75c57 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -13,30 +13,26 @@ #include #include -/* "Raw" instruction opcodes */ -#define __ASM_CLAC ".byte 0x0f,0x01,0xca" -#define __ASM_STAC ".byte 0x0f,0x01,0xcb" - #ifdef __ASSEMBLY__ #define ASM_CLAC \ - ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP + ALTERNATIVE "", "clac", X86_FEATURE_SMAP #define ASM_STAC \ - ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP + ALTERNATIVE "", "stac", X86_FEATURE_SMAP #else /* __ASSEMBLY__ */ static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __ASM_CLAC, X86_FEATURE_SMAP); + alternative("", "clac", X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __ASM_STAC, X86_FEATURE_SMAP); + alternative("", "stac", X86_FEATURE_SMAP); } static __always_inline unsigned long smap_save(void) @@ -44,7 +40,7 @@ static __always_inline unsigned long smap_save(void) unsigned long flags; asm volatile ("# smap_save\n\t" - ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC "\n\t", + ALTERNATIVE("", "pushf; pop %0; " "clac" "\n\t", X86_FEATURE_SMAP) : "=rm" (flags) : : "memory", "cc"); @@ -61,9 +57,9 @@ static __always_inline void smap_restore(unsigned long flags) /* These macros can be used in asm() statements */ #define ASM_CLAC \ - ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP) + ALTERNATIVE("", "clac", X86_FEATURE_SMAP) #define ASM_STAC \ - ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) + ALTERNATIVE("", "stac", X86_FEATURE_SMAP) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index aec6e2d3aa1d..03e7c2d49559 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -115,7 +115,7 @@ static inline void wrpkru(u32 pkru) } #endif -static __always_inline void native_wbinvd(void) +static __always_inline void wbinvd(void) { asm volatile("wbinvd": : :"memory"); } @@ -167,12 +167,6 @@ static inline void __write_cr4(unsigned long x) { native_write_cr4(x); } - -static __always_inline void wbinvd(void) -{ - native_wbinvd(); -} - #endif /* CONFIG_PARAVIRT_XXL */ static __always_inline void clflush(volatile void *__p) @@ -217,7 +211,7 @@ fail: #define nop() asm volatile ("nop") -static inline void serialize(void) +static __always_inline void serialize(void) { /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 125c407e2abe..41502bd2afd6 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -65,4 +65,19 @@ extern bool __static_call_fixup(void *tramp, u8 op, void *dest); +extern void __static_call_update_early(void *tramp, void *func); + +#define static_call_update_early(name, _func) \ +({ \ + typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \ + if (static_call_initialized) { \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), __F);\ + } else { \ + WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \ + __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\ + __F); \ + } \ +}) + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 2b59b9951c90..e2fac21471f5 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -5,7 +5,7 @@ #include #include -#include +#include /* * 32-bit intercept words in the VMCB Control Area, starting @@ -417,7 +417,9 @@ struct sev_es_save_area { u8 reserved_0x298[80]; u32 pkru; u32 tsc_aux; - u8 reserved_0x2f0[24]; + u64 tsc_scale; + u64 tsc_offset; + u8 reserved_0x300[8]; u64 rcx; u64 rdx; u64 rbx; @@ -564,7 +566,7 @@ static inline void __unused_size_checks(void) BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x1c0); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x248); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x298); - BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x2f0); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x300); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x320); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x380); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x3f0); diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index ab7382f92aff..96bda43538ee 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -8,7 +8,7 @@ #include #ifdef CONFIG_X86_32 -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { asm volatile ( "pushfl\n\t" @@ -19,7 +19,7 @@ static inline void iret_to_self(void) : ASM_CALL_CONSTRAINT : : "memory"); } #else -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { unsigned int tmp; @@ -55,7 +55,7 @@ static inline void iret_to_self(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ -static inline void sync_core(void) +static __always_inline void sync_core(void) { /* * The SERIALIZE instruction is the most straightforward way to diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index eba178996d84..b4b16dafd55e 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -66,6 +66,9 @@ int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport); u64 tdx_hcall_get_quote(u8 *buf, size_t size); +void __init tdx_dump_attributes(u64 td_attr); +void __init tdx_dump_td_ctls(u64 td_ctls); + #else static inline void tdx_early_init(void) { }; diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 4d3c9d00d6b6..77f52bc1578a 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -20,22 +20,9 @@ static inline void tlb_flush(struct mmu_gather *tlb) flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables); } -/* - * While x86 architecture in general requires an IPI to perform TLB - * shootdown, enablement code for several hypervisors overrides - * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing - * a hypercall. To keep software pagetable walkers safe in this case we - * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment - * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h - * for more details. - */ -static inline void __tlb_remove_table(void *table) -{ - free_page_and_swap_cache(table); -} - static inline void invlpg(unsigned long addr) { asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); } + #endif /* _ASM_X86_TLB_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 69e79fff41b8..02fc2aa06e9e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -222,6 +222,7 @@ struct flush_tlb_info { unsigned int initiating_cpu; u8 stride_shift; u8 freed_tables; + u8 trim_cpumask; }; void flush_tlb_local(void); diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index fd41103ad342..ec134b719144 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -143,6 +143,7 @@ extern const struct cpumask *cpu_clustergroup_mask(int cpu); #define topology_logical_package_id(cpu) (cpu_data(cpu).topo.logical_pkg_id) #define topology_physical_package_id(cpu) (cpu_data(cpu).topo.pkg_id) #define topology_logical_die_id(cpu) (cpu_data(cpu).topo.logical_die_id) +#define topology_logical_core_id(cpu) (cpu_data(cpu).topo.logical_core_id) #define topology_die_id(cpu) (cpu_data(cpu).topo.die_id) #define topology_core_id(cpu) (cpu_data(cpu).topo.core_id) #define topology_ppin(cpu) (cpu_data(cpu).ppin) @@ -250,7 +251,7 @@ extern bool x86_topology_update; #include DECLARE_PER_CPU_READ_MOSTLY(int, sched_core_priority); -extern unsigned int __read_mostly sysctl_sched_itmt_enabled; +extern bool __read_mostly sysctl_sched_itmt_enabled; /* Interface to set priority of a cpu */ void sched_set_itmt_core_prio(int prio, int core_cpu); @@ -263,7 +264,7 @@ void sched_clear_itmt_support(void); #else /* CONFIG_SCHED_MC_PRIO */ -#define sysctl_sched_itmt_enabled 0 +#define sysctl_sched_itmt_enabled false static inline void sched_set_itmt_core_prio(int prio, int core_cpu) { } diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index b0a887209400..c52f0133425b 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -63,13 +63,13 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, */ static inline void __user *mask_user_address(const void __user *ptr) { - unsigned long mask; + void __user *ret; asm("cmp %1,%0\n\t" - "sbb %0,%0" - :"=r" (mask) - :"r" (ptr), - "0" (runtime_const_ptr(USER_PTR_MAX))); - return (__force void __user *)(mask | (__force unsigned long)ptr); + "cmova %1,%0" + :"=r" (ret) + :"r" (runtime_const_ptr(USER_PTR_MAX)), + "0" (ptr)); + return ret; } #define masked_user_access_begin(x) ({ \ __auto_type __masked_ptr = (x); \ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a2dd24947eb8..97771b9d33af 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -39,9 +39,11 @@ #include #include #include +#include #include +#include #include #include #include @@ -86,11 +88,20 @@ struct xen_dm_op_buf; * there aren't more than 5 arguments...) */ -extern struct { char _entry[32]; } hypercall_page[]; +void xen_hypercall_func(void); +DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); -#define __HYPERCALL "call hypercall_page+%c[offset]" -#define __HYPERCALL_ENTRY(x) \ - [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0])) +#ifdef MODULE +#define __ADDRESSABLE_xen_hypercall +#else +#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#endif + +#define __HYPERCALL \ + __ADDRESSABLE_xen_hypercall \ + "call __SCT__xen_hypercall" + +#define __HYPERCALL_ENTRY(x) "a" (x) #ifdef CONFIG_X86_32 #define __HYPERCALL_RETREG "eax" @@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_0ARG(); \ asm volatile (__HYPERCALL \ : __HYPERCALL_0PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER0); \ (type)__res; \ }) @@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_1ARG(a1); \ asm volatile (__HYPERCALL \ : __HYPERCALL_1PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER1); \ (type)__res; \ }) @@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_2ARG(a1, a2); \ asm volatile (__HYPERCALL \ : __HYPERCALL_2PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER2); \ (type)__res; \ }) @@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_3ARG(a1, a2, a3); \ asm volatile (__HYPERCALL \ : __HYPERCALL_3PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER3); \ (type)__res; \ }) @@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_4ARG(a1, a2, a3, a4); \ asm volatile (__HYPERCALL \ : __HYPERCALL_4PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER4); \ (type)__res; \ }) @@ -206,12 +217,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) - return -EINVAL; - - asm volatile(CALL_NOSPEC + asm volatile(__HYPERCALL : __HYPERCALL_5PARAM - : [thunk_target] "a" (&hypercall_page[call]) + : __HYPERCALL_ENTRY(call) : __HYPERCALL_CLOBBER5); return (long)__res; diff --git a/arch/x86/include/uapi/asm/amd_hsmp.h b/arch/x86/include/uapi/asm/amd_hsmp.h index 4a7cace06204..92d8f256d096 100644 --- a/arch/x86/include/uapi/asm/amd_hsmp.h +++ b/arch/x86/include/uapi/asm/amd_hsmp.h @@ -50,6 +50,12 @@ enum hsmp_message_ids { HSMP_GET_METRIC_TABLE_VER, /* 23h Get metrics table version */ HSMP_GET_METRIC_TABLE, /* 24h Get metrics table */ HSMP_GET_METRIC_TABLE_DRAM_ADDR,/* 25h Get metrics table dram address */ + HSMP_SET_XGMI_PSTATE_RANGE, /* 26h Set xGMI P-state range */ + HSMP_CPU_RAIL_ISO_FREQ_POLICY, /* 27h Get/Set Cpu Iso frequency policy */ + HSMP_DFC_ENABLE_CTRL, /* 28h Enable/Disable DF C-state */ + HSMP_GET_RAPL_UNITS = 0x30, /* 30h Get scaling factor for energy */ + HSMP_GET_RAPL_CORE_COUNTER, /* 31h Get core energy counter value */ + HSMP_GET_RAPL_PACKAGE_COUNTER, /* 32h Get package energy counter value */ HSMP_MSG_ID_MAX, }; @@ -65,6 +71,7 @@ enum hsmp_msg_type { HSMP_RSVD = -1, HSMP_SET = 0, HSMP_GET = 1, + HSMP_SET_GET = 2, }; enum hsmp_proto_versions { @@ -72,7 +79,8 @@ enum hsmp_proto_versions { HSMP_PROTO_VER3, HSMP_PROTO_VER4, HSMP_PROTO_VER5, - HSMP_PROTO_VER6 + HSMP_PROTO_VER6, + HSMP_PROTO_VER7 }; struct hsmp_msg_desc { @@ -300,7 +308,7 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] * HSMP_SET_POWER_MODE, num_args = 1, response_sz = 0 * input: args[0] = power efficiency mode[2:0] */ - {1, 0, HSMP_SET}, + {1, 1, HSMP_SET_GET}, /* * HSMP_SET_PSTATE_MAX_MIN, num_args = 1, response_sz = 0 @@ -325,6 +333,58 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] * output: args[1] = upper 32 bits of the address */ {0, 2, HSMP_GET}, + + /* + * HSMP_SET_XGMI_PSTATE_RANGE, num_args = 1, response_sz = 0 + * input: args[0] = min xGMI p-state[15:8] + max xGMI p-state[7:0] + */ + {1, 0, HSMP_SET}, + + /* + * HSMP_CPU_RAIL_ISO_FREQ_POLICY, num_args = 1, response_sz = 1 + * input: args[0] = set/get policy[31] + + * disable/enable independent control[0] + * output: args[0] = current policy[0] + */ + {1, 1, HSMP_SET_GET}, + + /* + * HSMP_DFC_ENABLE_CTRL, num_args = 1, response_sz = 1 + * input: args[0] = set/get policy[31] + enable/disable DFC[0] + * output: args[0] = current policy[0] + */ + {1, 1, HSMP_SET_GET}, + + /* RESERVED(0x29-0x2f) */ + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + + /* + * HSMP_GET_RAPL_UNITS, response_sz = 1 + * output: args[0] = tu value[19:16] + esu value[12:8] + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_RAPL_CORE_COUNTER, num_args = 1, response_sz = 1 + * input: args[0] = apic id[15:0] + * output: args[0] = lower 32 bits of energy + * output: args[1] = upper 32 bits of energy + */ + {1, 2, HSMP_GET}, + + /* + * HSMP_GET_RAPL_PACKAGE_COUNTER, num_args = 0, response_sz = 1 + * output: args[0] = lower 32 bits of energy + * output: args[1] = upper 32 bits of energy + */ + {0, 2, HSMP_GET}, + }; /* Metrics table (supported only with proto version 6) */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 88585c1de416..9e75da97bce0 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -925,5 +925,6 @@ struct kvm_hyperv_eventfd { #define KVM_X86_SEV_VM 2 #define KVM_X86_SEV_ES_VM 3 #define KVM_X86_SNP_VM 4 +#define KVM_X86_TDX_VM 5 #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f7918980667a..b43eb7e384eb 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -119,6 +119,7 @@ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_HPET_TIMER) += hpet.o obj-$(CONFIG_AMD_NB) += amd_nb.o +obj-$(CONFIG_AMD_NODE) += amd_node.o obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 3a44a9dc3fb7..dae6a73be40e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -226,6 +226,28 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) return 0; } +static int __init +acpi_check_lapic(union acpi_subtable_headers *header, const unsigned long end) +{ + struct acpi_madt_local_apic *processor = NULL; + + processor = (struct acpi_madt_local_apic *)header; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + /* Ignore invalid ID */ + if (processor->id == 0xff) + return 0; + + /* Ignore processors that can not be onlined */ + if (!acpi_is_processor_usable(processor->lapic_flags)) + return 0; + + has_lapic_cpus = true; + return 0; +} + static int __init acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) { @@ -257,7 +279,6 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) processor->processor_id, /* ACPI ID */ processor->lapic_flags & ACPI_MADT_ENABLED); - has_lapic_cpus = true; return 0; } @@ -911,11 +932,8 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) * the resource tree during the lateinit timeframe. */ #define HPET_RESOURCE_NAME_SIZE 9 - hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE, + hpet_res = memblock_alloc_or_panic(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE, SMP_CACHE_BYTES); - if (!hpet_res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE); hpet_res->name = (void *)&hpet_res[1]; hpet_res->flags = IORESOURCE_MEM; @@ -1029,6 +1047,8 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) static int __init acpi_parse_madt_lapic_entries(void) { int count, x2count = 0; + struct acpi_subtable_proc madt_proc[2]; + int ret; if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; @@ -1037,10 +1057,27 @@ static int __init acpi_parse_madt_lapic_entries(void) acpi_parse_sapic, MAX_LOCAL_APIC); if (!count) { - count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, - acpi_parse_lapic, MAX_LOCAL_APIC); - x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, - acpi_parse_x2apic, MAX_LOCAL_APIC); + /* Check if there are valid LAPIC entries */ + acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, acpi_check_lapic, MAX_LOCAL_APIC); + + /* + * Enumerate the APIC IDs in the order that they appear in the + * MADT, no matter LAPIC entry or x2APIC entry is used. + */ + memset(madt_proc, 0, sizeof(madt_proc)); + madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC; + madt_proc[0].handler = acpi_parse_lapic; + madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC; + madt_proc[1].handler = acpi_parse_x2apic; + ret = acpi_table_parse_entries_array(ACPI_SIG_MADT, + sizeof(struct acpi_table_madt), + madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC); + if (ret < 0) { + pr_err("Error parsing LAPIC/X2APIC entries\n"); + return ret; + } + count = madt_proc[0].count; + x2count = madt_proc[1].count; } if (!count && !x2count) { pr_err("No LAPIC entries present\n"); diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index f3ffd0a3a012..5854f0b8f0f1 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -13,6 +13,7 @@ #include #include +#include #include #include @@ -128,7 +129,7 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) unsigned int cstate_type; /* C-state type and not ACPI C-state type */ unsigned int num_cstate_subtype; - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &edx); /* Check whether this particular cx_type (in CST) is supported or not */ cstate_type = (((cx->address >> MWAIT_SUBSTATE_SIZE) & @@ -172,7 +173,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, struct cpuinfo_x86 *c = &cpu_data(cpu); long retval; - if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF) + if (!cpu_cstate_entry || c->cpuid_level < CPUID_LEAF_MWAIT) return -1; if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 243843e44e89..c71b575bf229 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1854,11 +1854,18 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm) return temp_state; } +__ro_after_init struct mm_struct *poking_mm; +__ro_after_init unsigned long poking_addr; + static inline void unuse_temporary_mm(temp_mm_state_t prev_state) { lockdep_assert_irqs_disabled(); + switch_mm_irqs_off(NULL, prev_state.mm, current); + /* Clear the cpumask, to indicate no TLB flushing is needed anywhere */ + cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(poking_mm)); + /* * Restore the breakpoints if they were disabled before the temporary mm * was loaded. @@ -1867,9 +1874,6 @@ static inline void unuse_temporary_mm(temp_mm_state_t prev_state) hw_breakpoint_restore(); } -__ro_after_init struct mm_struct *poking_mm; -__ro_after_init unsigned long poking_addr; - static void text_poke_memcpy(void *dst, const void *src, size_t len) { memcpy(dst, src, len); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 9fe9972d2071..11fac09e3a8c 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -15,66 +15,8 @@ #include #include -#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 -#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 -#define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 -#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630 -#define PCI_DEVICE_ID_AMD_17H_MA0H_ROOT 0x14b5 -#define PCI_DEVICE_ID_AMD_19H_M10H_ROOT 0x14a4 -#define PCI_DEVICE_ID_AMD_19H_M40H_ROOT 0x14b5 -#define PCI_DEVICE_ID_AMD_19H_M60H_ROOT 0x14d8 -#define PCI_DEVICE_ID_AMD_19H_M70H_ROOT 0x14e8 -#define PCI_DEVICE_ID_AMD_1AH_M00H_ROOT 0x153a -#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 -#define PCI_DEVICE_ID_AMD_1AH_M60H_ROOT 0x1122 -#define PCI_DEVICE_ID_AMD_MI200_ROOT 0x14bb -#define PCI_DEVICE_ID_AMD_MI300_ROOT 0x14f8 - -#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 -#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec -#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 -#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c -#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 -#define PCI_DEVICE_ID_AMD_17H_MA0H_DF_F4 0x1728 -#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 -#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F4 0x14b1 -#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d -#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e -#define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4 -#define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 -#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc -#define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4 -#define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4 0x16fc -#define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4 0x124c -#define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4 0x12bc -#define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4 -#define PCI_DEVICE_ID_AMD_MI300_DF_F4 0x152c - -/* Protect the PCI config register pairs used for SMN. */ -static DEFINE_MUTEX(smn_mutex); - static u32 *flush_words; -static const struct pci_device_id amd_root_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_MA0H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_ROOT) }, - {} -}; - -#define PCI_DEVICE_ID_AMD_CNB17H_F4 0x1704 - static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, @@ -84,70 +26,6 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_MA0H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F3) }, - {} -}; - -static const struct pci_device_id amd_nb_link_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_MA0H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F4) }, - {} -}; - -static const struct pci_device_id hygon_root_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_ROOT) }, - {} -}; - -static const struct pci_device_id hygon_nb_misc_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) }, - {} -}; - -static const struct pci_device_id hygon_nb_link_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F4) }, {} }; @@ -178,176 +56,37 @@ struct amd_northbridge *node_to_amd_nb(int node) } EXPORT_SYMBOL_GPL(node_to_amd_nb); -static struct pci_dev *next_northbridge(struct pci_dev *dev, - const struct pci_device_id *ids) -{ - do { - dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev); - if (!dev) - break; - } while (!pci_match_id(ids, dev)); - return dev; -} - -/* - * SMN accesses may fail in ways that are difficult to detect here in the called - * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do - * their own checking based on what behavior they expect. - * - * For SMN reads, the returned value may be zero if the register is Read-as-Zero. - * Or it may be a "PCI Error Response", e.g. all 0xFFs. The "PCI Error Response" - * can be checked here, and a proper error code can be returned. - * - * But the Read-as-Zero response cannot be verified here. A value of 0 may be - * correct in some cases, so callers must check that this correct is for the - * register/fields they need. - * - * For SMN writes, success can be determined through a "write and read back" - * However, this is not robust when done here. - * - * Possible issues: - * - * 1) Bits that are "Write-1-to-Clear". In this case, the read value should - * *not* match the write value. - * - * 2) Bits that are "Read-as-Zero"/"Writes-Ignored". This information cannot be - * known here. - * - * 3) Bits that are "Reserved / Set to 1". Ditto above. - * - * Callers of amd_smn_write() should do the "write and read back" check - * themselves, if needed. - * - * For #1, they can see if their target bits got cleared. - * - * For #2 and #3, they can check if their target bits got set as intended. - * - * This matches what is done for RDMSR/WRMSR. As long as there's no #GP, then - * the operation is considered a success, and the caller does their own - * checking. - */ -static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write) -{ - struct pci_dev *root; - int err = -ENODEV; - - if (node >= amd_northbridges.num) - goto out; - - root = node_to_amd_nb(node)->root; - if (!root) - goto out; - - mutex_lock(&smn_mutex); - - err = pci_write_config_dword(root, 0x60, address); - if (err) { - pr_warn("Error programming SMN address 0x%x.\n", address); - goto out_unlock; - } - - err = (write ? pci_write_config_dword(root, 0x64, *value) - : pci_read_config_dword(root, 0x64, value)); - -out_unlock: - mutex_unlock(&smn_mutex); - -out: - return err; -} - -int __must_check amd_smn_read(u16 node, u32 address, u32 *value) -{ - int err = __amd_smn_rw(node, address, value, false); - - if (PCI_POSSIBLE_ERROR(*value)) { - err = -ENODEV; - *value = 0; - } - - return err; -} -EXPORT_SYMBOL_GPL(amd_smn_read); - -int __must_check amd_smn_write(u16 node, u32 address, u32 value) -{ - return __amd_smn_rw(node, address, &value, true); -} -EXPORT_SYMBOL_GPL(amd_smn_write); - - static int amd_cache_northbridges(void) { - const struct pci_device_id *misc_ids = amd_nb_misc_ids; - const struct pci_device_id *link_ids = amd_nb_link_ids; - const struct pci_device_id *root_ids = amd_root_ids; - struct pci_dev *root, *misc, *link; struct amd_northbridge *nb; - u16 roots_per_misc = 0; - u16 misc_count = 0; - u16 root_count = 0; - u16 i, j; + u16 i; if (amd_northbridges.num) return 0; - if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { - root_ids = hygon_root_ids; - misc_ids = hygon_nb_misc_ids; - link_ids = hygon_nb_link_ids; - } + amd_northbridges.num = amd_num_nodes(); - misc = NULL; - while ((misc = next_northbridge(misc, misc_ids))) - misc_count++; - - if (!misc_count) - return -ENODEV; - - root = NULL; - while ((root = next_northbridge(root, root_ids))) - root_count++; - - if (root_count) { - roots_per_misc = root_count / misc_count; - - /* - * There should be _exactly_ N roots for each DF/SMN - * interface. - */ - if (!roots_per_misc || (root_count % roots_per_misc)) { - pr_info("Unsupported AMD DF/PCI configuration found\n"); - return -ENODEV; - } - } - - nb = kcalloc(misc_count, sizeof(struct amd_northbridge), GFP_KERNEL); + nb = kcalloc(amd_northbridges.num, sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) return -ENOMEM; amd_northbridges.nb = nb; - amd_northbridges.num = misc_count; - link = misc = root = NULL; for (i = 0; i < amd_northbridges.num; i++) { - node_to_amd_nb(i)->root = root = - next_northbridge(root, root_ids); - node_to_amd_nb(i)->misc = misc = - next_northbridge(misc, misc_ids); - node_to_amd_nb(i)->link = link = - next_northbridge(link, link_ids); + node_to_amd_nb(i)->root = amd_node_get_root(i); + node_to_amd_nb(i)->misc = amd_node_get_func(i, 3); /* - * If there are more PCI root devices than data fabric/ - * system management network interfaces, then the (N) - * PCI roots per DF/SMN interface are functionally the - * same (for DF/SMN access) and N-1 are redundant. N-1 - * PCI roots should be skipped per DF/SMN interface so - * the following DF/SMN interfaces get mapped to - * correct PCI roots. + * Each Northbridge must have a 'misc' device. + * If not, then uninitialize everything. */ - for (j = 1; j < roots_per_misc; j++) - root = next_northbridge(root, root_ids); + if (!node_to_amd_nb(i)->misc) { + amd_northbridges.num = 0; + kfree(nb); + return -ENODEV; + } + + node_to_amd_nb(i)->link = amd_node_get_func(i, 4); } if (amd_gart_present()) @@ -385,7 +124,6 @@ static int amd_cache_northbridges(void) */ bool __init early_is_amd_nb(u32 device) { - const struct pci_device_id *misc_ids = amd_nb_misc_ids; const struct pci_device_id *id; u32 vendor = device & 0xffff; @@ -393,11 +131,11 @@ bool __init early_is_amd_nb(u32 device) boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) return false; - if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) - misc_ids = hygon_nb_misc_ids; + if (cpu_feature_enabled(X86_FEATURE_ZEN)) + return false; device >>= 16; - for (id = misc_ids; id->vendor; id++) + for (id = amd_nb_misc_ids; id->vendor; id++) if (vendor == id->vendor && device == id->device) return true; return false; @@ -582,6 +320,10 @@ static __init void fix_erratum_688(void) static __init int init_amd_nbs(void) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return 0; + amd_cache_northbridges(); amd_cache_gart(); diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c new file mode 100644 index 000000000000..d2ec7fd555c5 --- /dev/null +++ b/arch/x86/kernel/amd_node.c @@ -0,0 +1,215 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Node helper functions and common defines + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam + */ + +#include + +/* + * AMD Nodes are a physical collection of I/O devices within an SoC. There can be one + * or more nodes per package. + * + * The nodes are software-visible through PCI config space. All nodes are enumerated + * on segment 0 bus 0. The device (slot) numbers range from 0x18 to 0x1F (maximum 8 + * nodes) with 0x18 corresponding to node 0, 0x19 to node 1, etc. Each node can be a + * multi-function device. + * + * On legacy systems, these node devices represent integrated Northbridge functionality. + * On Zen-based systems, these node devices represent Data Fabric functionality. + * + * See "Configuration Space Accesses" section in BKDGs or + * "Processor x86 Core" -> "Configuration Space" section in PPRs. + */ +struct pci_dev *amd_node_get_func(u16 node, u8 func) +{ + if (node >= MAX_AMD_NUM_NODES) + return NULL; + + return pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(AMD_NODE0_PCI_SLOT + node, func)); +} + +#define DF_BLK_INST_CNT 0x040 +#define DF_CFG_ADDR_CNTL_LEGACY 0x084 +#define DF_CFG_ADDR_CNTL_DF4 0xC04 + +#define DF_MAJOR_REVISION GENMASK(27, 24) + +static u16 get_cfg_addr_cntl_offset(struct pci_dev *df_f0) +{ + u32 reg; + + /* + * Revision fields added for DF4 and later. + * + * Major revision of '0' is found pre-DF4. Field is Read-as-Zero. + */ + if (pci_read_config_dword(df_f0, DF_BLK_INST_CNT, ®)) + return 0; + + if (reg & DF_MAJOR_REVISION) + return DF_CFG_ADDR_CNTL_DF4; + + return DF_CFG_ADDR_CNTL_LEGACY; +} + +struct pci_dev *amd_node_get_root(u16 node) +{ + struct pci_dev *root; + u16 cntl_off; + u8 bus; + + if (!cpu_feature_enabled(X86_FEATURE_ZEN)) + return NULL; + + /* + * D18F0xXXX [Config Address Control] (DF::CfgAddressCntl) + * Bits [7:0] (SecBusNum) holds the bus number of the root device for + * this Data Fabric instance. The segment, device, and function will be 0. + */ + struct pci_dev *df_f0 __free(pci_dev_put) = amd_node_get_func(node, 0); + if (!df_f0) + return NULL; + + cntl_off = get_cfg_addr_cntl_offset(df_f0); + if (!cntl_off) + return NULL; + + if (pci_read_config_byte(df_f0, cntl_off, &bus)) + return NULL; + + /* Grab the pointer for the actual root device instance. */ + root = pci_get_domain_bus_and_slot(0, bus, 0); + + pci_dbg(root, "is root for AMD node %u\n", node); + return root; +} + +static struct pci_dev **amd_roots; + +/* Protect the PCI config register pairs used for SMN. */ +static DEFINE_MUTEX(smn_mutex); + +#define SMN_INDEX_OFFSET 0x60 +#define SMN_DATA_OFFSET 0x64 + +/* + * SMN accesses may fail in ways that are difficult to detect here in the called + * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do + * their own checking based on what behavior they expect. + * + * For SMN reads, the returned value may be zero if the register is Read-as-Zero. + * Or it may be a "PCI Error Response", e.g. all 0xFFs. The "PCI Error Response" + * can be checked here, and a proper error code can be returned. + * + * But the Read-as-Zero response cannot be verified here. A value of 0 may be + * correct in some cases, so callers must check that this correct is for the + * register/fields they need. + * + * For SMN writes, success can be determined through a "write and read back" + * However, this is not robust when done here. + * + * Possible issues: + * + * 1) Bits that are "Write-1-to-Clear". In this case, the read value should + * *not* match the write value. + * + * 2) Bits that are "Read-as-Zero"/"Writes-Ignored". This information cannot be + * known here. + * + * 3) Bits that are "Reserved / Set to 1". Ditto above. + * + * Callers of amd_smn_write() should do the "write and read back" check + * themselves, if needed. + * + * For #1, they can see if their target bits got cleared. + * + * For #2 and #3, they can check if their target bits got set as intended. + * + * This matches what is done for RDMSR/WRMSR. As long as there's no #GP, then + * the operation is considered a success, and the caller does their own + * checking. + */ +static int __amd_smn_rw(u8 i_off, u8 d_off, u16 node, u32 address, u32 *value, bool write) +{ + struct pci_dev *root; + int err = -ENODEV; + + if (node >= amd_num_nodes()) + return err; + + root = amd_roots[node]; + if (!root) + return err; + + guard(mutex)(&smn_mutex); + + err = pci_write_config_dword(root, i_off, address); + if (err) { + pr_warn("Error programming SMN address 0x%x.\n", address); + return pcibios_err_to_errno(err); + } + + err = (write ? pci_write_config_dword(root, d_off, *value) + : pci_read_config_dword(root, d_off, value)); + + return pcibios_err_to_errno(err); +} + +int __must_check amd_smn_read(u16 node, u32 address, u32 *value) +{ + int err = __amd_smn_rw(SMN_INDEX_OFFSET, SMN_DATA_OFFSET, node, address, value, false); + + if (PCI_POSSIBLE_ERROR(*value)) { + err = -ENODEV; + *value = 0; + } + + return err; +} +EXPORT_SYMBOL_GPL(amd_smn_read); + +int __must_check amd_smn_write(u16 node, u32 address, u32 value) +{ + return __amd_smn_rw(SMN_INDEX_OFFSET, SMN_DATA_OFFSET, node, address, &value, true); +} +EXPORT_SYMBOL_GPL(amd_smn_write); + +static int amd_cache_roots(void) +{ + u16 node, num_nodes = amd_num_nodes(); + + amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL); + if (!amd_roots) + return -ENOMEM; + + for (node = 0; node < num_nodes; node++) + amd_roots[node] = amd_node_get_root(node); + + return 0; +} + +static int __init amd_smn_init(void) +{ + int err; + + if (!cpu_feature_enabled(X86_FEATURE_ZEN)) + return 0; + + guard(mutex)(&smn_mutex); + + if (amd_roots) + return 0; + + err = amd_cache_roots(); + if (err) + return err; + + return 0; +} + +fs_initcall(amd_smn_init); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c5fb28e6451a..e893dc6f11c1 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -509,19 +509,19 @@ static struct clock_event_device lapic_clockevent = { static DEFINE_PER_CPU(struct clock_event_device, lapic_events); static const struct x86_cpu_id deadline_match[] __initconst = { - X86_MATCH_VFM_STEPPINGS(INTEL_HASWELL_X, X86_STEPPINGS(0x2, 0x2), 0x3a), /* EP */ - X86_MATCH_VFM_STEPPINGS(INTEL_HASWELL_X, X86_STEPPINGS(0x4, 0x4), 0x0f), /* EX */ + X86_MATCH_VFM_STEPS(INTEL_HASWELL_X, 0x2, 0x2, 0x3a), /* EP */ + X86_MATCH_VFM_STEPS(INTEL_HASWELL_X, 0x4, 0x4, 0x0f), /* EX */ X86_MATCH_VFM(INTEL_BROADWELL_X, 0x0b000020), - X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x2, 0x2), 0x00000011), - X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x3, 0x3), 0x0700000e), - X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x4, 0x4), 0x0f00000c), - X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x5, 0x5), 0x0e000003), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 0x2, 0x2, 0x00000011), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 0x3, 0x3, 0x0700000e), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 0x4, 0x4, 0x0f00000c), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 0x5, 0x5, 0x0e000003), - X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x3, 0x3), 0x01000136), - X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x4, 0x4), 0x02000014), - X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x5, 0xf), 0), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 0x3, 0x3, 0x01000136), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 0x4, 0x4, 0x02000014), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 0x5, 0xf, 0), X86_MATCH_VFM(INTEL_HASWELL, 0x22), X86_MATCH_VFM(INTEL_HASWELL_L, 0x20), @@ -2582,19 +2582,12 @@ int apic_is_clustered_box(void) /* * APIC command line parameters */ -static int __init setup_disableapic(char *arg) +static int __init setup_nolapic(char *arg) { apic_is_disabled = true; setup_clear_cpu_cap(X86_FEATURE_APIC); return 0; } -early_param("disableapic", setup_disableapic); - -/* same as disableapic, for compatibility */ -static int __init setup_nolapic(char *arg) -{ - return setup_disableapic(arg); -} early_param("nolapic", setup_nolapic); static int __init parse_lapic_timer_c2_ok(char *arg) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1029ea4ac8ba..eebc360ed1bb 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1165,7 +1165,7 @@ static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) (entry.ir_index_15 << 15) | entry.ir_index_0_14, entry.ir_zero); } else { apic_dbg("%s, %s, D(%02X%02X), M(%1d)\n", buf, - entry.dest_mode_logical ? "logical " : "physic al", + entry.dest_mode_logical ? "logical " : "physical", entry.virt_destid_8_14, entry.destid_0_7, entry.delivery_mode); } } @@ -1861,7 +1861,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE | + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED | IRQCHIP_AFFINITY_PRE_STARTUP, }; @@ -2503,9 +2503,7 @@ static struct resource * __init ioapic_setup_resources(void) n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource); n *= nr_ioapics; - mem = memblock_alloc(n, SMP_CACHE_BYTES); - if (!mem) - panic("%s: Failed to allocate %lu bytes\n", __func__, n); + mem = memblock_alloc_or_panic(n, SMP_CACHE_BYTES); res = (void *)mem; mem += sizeof(struct resource) * nr_ioapics; @@ -2564,11 +2562,8 @@ void __init io_apic_init_mappings(void) #ifdef CONFIG_X86_32 fake_ioapic_page: #endif - ioapic_phys = (unsigned long)memblock_alloc(PAGE_SIZE, + ioapic_phys = (unsigned long)memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); - if (!ioapic_phys) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); ioapic_phys = __pa(ioapic_phys); } io_apic_set_fixmap(idx, ioapic_phys); diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 340769242dea..66bc5d3e79db 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -214,6 +214,7 @@ static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain, if (WARN_ON_ONCE(domain != real_parent)) return false; info->chip->irq_set_affinity = msi_set_affinity; + info->chip->flags |= IRQCHIP_MOVE_DEFERRED; break; case DOMAIN_BUS_DMAR: case DOMAIN_BUS_AMDVI: @@ -315,7 +316,7 @@ static struct irq_chip dmar_msi_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = dmar_msi_compose_msg, .irq_write_msi_msg = dmar_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE | + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED | IRQCHIP_AFFINITY_PRE_STARTUP, }; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 465647456753..8418a892d195 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -139,14 +139,15 @@ static bool skip_addr(void *dest) return true; #endif #ifdef CONFIG_KEXEC_CORE +# ifdef CONFIG_X86_64 + if (dest >= (void *)__relocate_kernel_start && + dest < (void *)__relocate_kernel_end) + return true; +# else if (dest >= (void *)relocate_kernel && dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE) return true; -#endif -#ifdef CONFIG_XEN - if (dest >= (void *)hypercall_page && - dest < (void*)hypercall_page + PAGE_SIZE) - return true; +# endif #endif return false; } diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c index d2c732a34e5d..303bf74d175b 100644 --- a/arch/x86/kernel/cet.c +++ b/arch/x86/kernel/cet.c @@ -81,6 +81,34 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code) static __ro_after_init bool ibt_fatal = true; +/* + * By definition, all missing-ENDBRANCH #CPs are a result of WFE && !ENDBR. + * + * For the kernel IBT no ENDBR selftest where #CPs are deliberately triggered, + * the WFE state of the interrupted context needs to be cleared to let execution + * continue. Otherwise when the CPU resumes from the instruction that just + * caused the previous #CP, another missing-ENDBRANCH #CP is raised and the CPU + * enters a dead loop. + * + * This is not a problem with IDT because it doesn't preserve WFE and IRET doesn't + * set WFE. But FRED provides space on the entry stack (in an expanded CS area) + * to save and restore the WFE state, thus the WFE state is no longer clobbered, + * so software must clear it. + */ +static void ibt_clear_fred_wfe(struct pt_regs *regs) +{ + /* + * No need to do any FRED checks. + * + * For IDT event delivery, the high-order 48 bits of CS are pushed + * as 0s into the stack, and later IRET ignores these bits. + * + * For FRED, a test to check if fred_cs.wfe is set would be dropped + * by compilers. + */ + regs->fred_cs.wfe = 0; +} + static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) { if ((error_code & CP_EC) != CP_ENDBR) { @@ -90,6 +118,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(regs->ip == (unsigned long)&ibt_selftest_noendbr)) { regs->ax = 0; + ibt_clear_fred_wfe(regs); return; } @@ -97,6 +126,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (!ibt_fatal) { printk(KERN_DEFAULT CUT_HERE); __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); + ibt_clear_fred_wfe(regs); return; } BUG(); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 79d2e17f6582..54194f5995de 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -355,10 +355,15 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c) /* * RMP table entry format is not architectural and is defined by the * per-processor PPR. Restrict SNP support on the known CPU models - * for which the RMP table entry format is currently defined for. + * for which the RMP table entry format is currently defined or for + * processors which support the architecturally defined RMPREAD + * instruction. */ if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && - c->x86 >= 0x19 && snp_probe_rmptable_info()) { + (cpu_feature_enabled(X86_FEATURE_ZEN3) || + cpu_feature_enabled(X86_FEATURE_ZEN4) || + cpu_feature_enabled(X86_FEATURE_RMPREAD)) && + snp_probe_rmptable_info()) { cc_platform_set(CC_ATTR_HOST_SEV_SNP); } else { setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); @@ -795,10 +800,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c) clear_rdrand_cpuid_bit(c); } -static const struct x86_cpu_desc erratum_1386_microcode[] = { - AMD_CPU_DESC(0x17, 0x1, 0x2, 0x0800126e), - AMD_CPU_DESC(0x17, 0x31, 0x0, 0x08301052), - {}, +static const struct x86_cpu_id erratum_1386_microcode[] = { + X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x01), 0x2, 0x2, 0x0800126e), + X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x31), 0x0, 0x0, 0x08301052), }; static void fix_erratum_1386(struct cpuinfo_x86 *c) @@ -814,7 +818,7 @@ static void fix_erratum_1386(struct cpuinfo_x86 *c) * Clear the feature flag only on microcode revisions which * don't have the fix. */ - if (x86_cpu_has_min_microcode_rev(erratum_1386_microcode)) + if (x86_match_min_microcode_rev(erratum_1386_microcode)) return; clear_cpu_cap(c, X86_FEATURE_XSAVES); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 47a01d4028f6..5a505aa65489 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2615,6 +2615,9 @@ static void __init srso_select_mitigation(void) break; case SRSO_CMD_SAFE_RET: + if (boot_cpu_has(X86_FEATURE_SRSO_USER_KERNEL_NO)) + goto ibpb_on_vmexit; + if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { /* * Enable the return thunk for generated code @@ -2658,6 +2661,7 @@ static void __init srso_select_mitigation(void) } break; +ibpb_on_vmexit: case SRSO_CMD_IBPB_ON_VMEXIT: if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c index 704e9241b964..6cba85c79d42 100644 --- a/arch/x86/kernel/cpu/bus_lock.c +++ b/arch/x86/kernel/cpu/bus_lock.c @@ -49,7 +49,7 @@ static unsigned int sysctl_sld_mitigate = 1; static DEFINE_SEMAPHORE(buslock_sem, 1); #ifdef CONFIG_PROC_SYSCTL -static struct ctl_table sld_sysctls[] = { +static const struct ctl_table sld_sysctls[] = { { .procname = "split_lock_mitigate", .data = &sysctl_sld_mitigate, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a5c28975c608..7cce91b19fb2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -29,6 +29,7 @@ #include #include +#include #include #include #include @@ -636,9 +637,9 @@ struct cpuid_dependent_feature { static const struct cpuid_dependent_feature cpuid_dependent_features[] = { - { X86_FEATURE_MWAIT, 0x00000005 }, - { X86_FEATURE_DCA, 0x00000009 }, - { X86_FEATURE_XSAVE, 0x0000000d }, + { X86_FEATURE_MWAIT, CPUID_LEAF_MWAIT }, + { X86_FEATURE_DCA, CPUID_LEAF_DCA }, + { X86_FEATURE_XSAVE, CPUID_LEAF_XSTATE }, { 0, 0 } }; @@ -867,7 +868,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -static void get_cpu_vendor(struct cpuinfo_x86 *c) +void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; int i; @@ -1201,8 +1202,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define VULNBL(vendor, family, model, blacklist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist) -#define VULNBL_INTEL_STEPPINGS(vfm, steppings, issues) \ - X86_MATCH_VFM_STEPPINGS(vfm, steppings, issues) +#define VULNBL_INTEL_STEPS(vfm, max_stepping, issues) \ + X86_MATCH_VFM_STEPS(vfm, X86_STEP_MIN, max_stepping, issues) #define VULNBL_AMD(family, blacklist) \ VULNBL(AMD, family, X86_MODEL_ANY, blacklist) @@ -1227,49 +1228,50 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { - VULNBL_INTEL_STEPPINGS(INTEL_IVYBRIDGE, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_HASWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_L, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_G, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_G, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), - VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE_L, X86_STEPPING_ANY, GDS), - VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE, X86_STEPPING_ANY, GDS), - VULNBL_INTEL_STEPPINGS(INTEL_LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(INTEL_ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE_L, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_HASWELL, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_HASWELL_L, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_HASWELL_G, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_HASWELL_X, X86_STEP_MAX, MMIO), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_D, X86_STEP_MAX, MMIO), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO), + VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS), + VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_ALDERLAKE, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_D, X86_STEP_MAX, MMIO | RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_D, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEP_MAX, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), VULNBL_AMD(0x19, SRSO), + VULNBL_AMD(0x1a, SRSO), {} }; @@ -1649,15 +1651,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) detect_nopl(); } -void __init early_cpu_init(void) +void __init init_cpu_devs(void) { const struct cpu_dev *const *cdev; int count = 0; -#ifdef CONFIG_PROCESSOR_SELECT - pr_info("KERNEL supported cpus:\n"); -#endif - for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { const struct cpu_dev *cpudev = *cdev; @@ -1665,20 +1663,30 @@ void __init early_cpu_init(void) break; cpu_devs[count] = cpudev; count++; + } +} + +void __init early_cpu_init(void) +{ +#ifdef CONFIG_PROCESSOR_SELECT + unsigned int i, j; + + pr_info("KERNEL supported cpus:\n"); +#endif + + init_cpu_devs(); #ifdef CONFIG_PROCESSOR_SELECT - { - unsigned int j; - - for (j = 0; j < 2; j++) { - if (!cpudev->c_ident[j]) - continue; - pr_info(" %s %s\n", cpudev->c_vendor, - cpudev->c_ident[j]); - } + for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) { + for (j = 0; j < 2; j++) { + if (!cpu_devs[i]->c_ident[j]) + continue; + pr_info(" %s %s\n", cpu_devs[i]->c_vendor, + cpu_devs[i]->c_ident[j]); } -#endif } +#endif + early_identify_cpu(&boot_cpu_data); } diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c index 10719aba6276..cacfd3f6abef 100644 --- a/arch/x86/kernel/cpu/debugfs.c +++ b/arch/x86/kernel/cpu/debugfs.c @@ -25,6 +25,7 @@ static int cpu_debug_show(struct seq_file *m, void *p) seq_printf(m, "cpu_type: %s\n", get_topology_cpu_type_name(c)); seq_printf(m, "logical_pkg_id: %u\n", c->topo.logical_pkg_id); seq_printf(m, "logical_die_id: %u\n", c->topo.logical_die_id); + seq_printf(m, "logical_core_id: %u\n", c->topo.logical_core_id); seq_printf(m, "llc_id: %u\n", c->topo.llc_id); seq_printf(m, "l2c_id: %u\n", c->topo.l2c_id); seq_printf(m, "amd_node_id: %u\n", c->topo.amd_node_id); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 8ded9f859a3a..3dce22f00dc3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -599,11 +599,6 @@ static void init_intel(struct cpuinfo_x86 *c) if (p) strcpy(c->x86_model_id, p); } - - if (c->x86 == 15) - set_cpu_cap(c, X86_FEATURE_P4); - if (c->x86 == 6) - set_cpu_cap(c, X86_FEATURE_P3); #endif /* Work around errata */ diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index 8e7de733320a..4f3c65429f82 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -6,7 +6,7 @@ #include /** - * x86_match_cpu - match current CPU again an array of x86_cpu_ids + * x86_match_cpu - match current CPU against an array of x86_cpu_ids * @match: Pointer to array of x86_cpu_ids. Last entry terminated with * {}. * @@ -56,33 +56,13 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) } EXPORT_SYMBOL(x86_match_cpu); -static const struct x86_cpu_desc * -x86_match_cpu_with_stepping(const struct x86_cpu_desc *match) +bool x86_match_min_microcode_rev(const struct x86_cpu_id *table) { - struct cpuinfo_x86 *c = &boot_cpu_data; - const struct x86_cpu_desc *m; + const struct x86_cpu_id *res = x86_match_cpu(table); - for (m = match; m->x86_family | m->x86_model; m++) { - if (c->x86_vendor != m->x86_vendor) - continue; - if (c->x86 != m->x86_family) - continue; - if (c->x86_model != m->x86_model) - continue; - if (c->x86_stepping != m->x86_stepping) - continue; - return m; - } - return NULL; -} - -bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table) -{ - const struct x86_cpu_desc *res = x86_match_cpu_with_stepping(table); - - if (!res || res->x86_microcode_rev > boot_cpu_data.microcode) + if (!res || res->driver_data > boot_cpu_data.microcode) return false; return true; } -EXPORT_SYMBOL_GPL(x86_cpu_has_min_microcode_rev); +EXPORT_SYMBOL_GPL(x86_match_min_microcode_rev); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 6ca80fff1fea..1075a90141da 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -4,8 +4,6 @@ * * Written by Jacob Shin - AMD, Inc. * Maintained by: Borislav Petkov - * - * All MC4_MISCi registers are shared between cores on a node. */ #include #include @@ -20,7 +18,6 @@ #include #include -#include #include #include #include @@ -221,6 +218,32 @@ static const struct smca_hwid smca_hwid_mcatypes[] = { #define MAX_MCATYPE_NAME_LEN 30 static char buf_mcatype[MAX_MCATYPE_NAME_LEN]; +struct threshold_block { + /* This block's number within its bank. */ + unsigned int block; + /* MCA bank number that contains this block. */ + unsigned int bank; + /* CPU which controls this block's MCA bank. */ + unsigned int cpu; + /* MCA_MISC MSR address for this block. */ + u32 address; + /* Enable/Disable APIC interrupt. */ + bool interrupt_enable; + /* Bank can generate an interrupt. */ + bool interrupt_capable; + /* Value upon which threshold interrupt is generated. */ + u16 threshold_limit; + /* sysfs object */ + struct kobject kobj; + /* List of threshold blocks within this block's MCA bank. */ + struct list_head miscj; +}; + +struct threshold_bank { + struct kobject *kobj; + struct threshold_block *blocks; +}; + static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); /* @@ -333,19 +356,6 @@ struct thresh_restart { u16 old_limit; }; -static inline bool is_shared_bank(int bank) -{ - /* - * Scalable MCA provides for only one core to have access to the MSRs of - * a shared bank. - */ - if (mce_flags.smca) - return false; - - /* Bank 4 is for northbridge reporting and is thus shared */ - return (bank == 4); -} - static const char *bank4_names(const struct threshold_block *b) { switch (b->address) { @@ -381,7 +391,7 @@ static bool lvt_interrupt_supported(unsigned int bank, u32 msr_high_bits) return msr_high_bits & BIT(28); } -static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) +static bool lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) { int msr = (hi & MASK_LVTOFF_HI) >> 20; @@ -389,7 +399,7 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt " "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu, b->bank, b->block, b->address, hi, lo); - return 0; + return false; } if (apic != msr) { @@ -399,15 +409,15 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) * was set is reserved. Return early here: */ if (mce_flags.smca) - return 0; + return false; pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d " "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu, apic, b->bank, b->block, b->address, hi, lo); - return 0; + return false; } - return 1; + return true; }; /* Reprogram MCx_MISC MSR behind this threshold bank. */ @@ -1198,35 +1208,10 @@ out_free: return err; } -static int __threshold_add_blocks(struct threshold_bank *b) -{ - struct list_head *head = &b->blocks->miscj; - struct threshold_block *pos = NULL; - struct threshold_block *tmp = NULL; - int err = 0; - - err = kobject_add(&b->blocks->kobj, b->kobj, b->blocks->kobj.name); - if (err) - return err; - - list_for_each_entry_safe(pos, tmp, head, miscj) { - - err = kobject_add(&pos->kobj, b->kobj, pos->kobj.name); - if (err) { - list_for_each_entry_safe_reverse(pos, tmp, head, miscj) - kobject_del(&pos->kobj); - - return err; - } - } - return err; -} - static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, unsigned int bank) { struct device *dev = this_cpu_read(mce_device); - struct amd_northbridge *nb = NULL; struct threshold_bank *b = NULL; const char *name = get_name(cpu, bank, NULL); int err = 0; @@ -1234,26 +1219,6 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, if (!dev) return -ENODEV; - if (is_shared_bank(bank)) { - nb = node_to_amd_nb(topology_amd_node_id(cpu)); - - /* threshold descriptor already initialized on this node? */ - if (nb && nb->bank4) { - /* yes, use it */ - b = nb->bank4; - err = kobject_add(b->kobj, &dev->kobj, name); - if (err) - goto out; - - bp[bank] = b; - refcount_inc(&b->cpus); - - err = __threshold_add_blocks(b); - - goto out; - } - } - b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL); if (!b) { err = -ENOMEM; @@ -1267,17 +1232,6 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, goto out_free; } - if (is_shared_bank(bank)) { - b->shared = 1; - refcount_set(&b->cpus, 1); - - /* nb is already initialized, see above */ - if (nb) { - WARN_ON(nb->bank4); - nb->bank4 = b; - } - } - err = allocate_threshold_blocks(cpu, b, bank, 0, mca_msr_reg(bank, MCA_MISC)); if (err) goto out_kobj; @@ -1310,40 +1264,11 @@ static void deallocate_threshold_blocks(struct threshold_bank *bank) kobject_put(&bank->blocks->kobj); } -static void __threshold_remove_blocks(struct threshold_bank *b) -{ - struct threshold_block *pos = NULL; - struct threshold_block *tmp = NULL; - - kobject_put(b->kobj); - - list_for_each_entry_safe(pos, tmp, &b->blocks->miscj, miscj) - kobject_put(b->kobj); -} - static void threshold_remove_bank(struct threshold_bank *bank) { - struct amd_northbridge *nb; - if (!bank->blocks) goto out_free; - if (!bank->shared) - goto out_dealloc; - - if (!refcount_dec_and_test(&bank->cpus)) { - __threshold_remove_blocks(bank); - return; - } else { - /* - * The last CPU on this node using the shared bank is going - * away, remove that bank now. - */ - nb = node_to_amd_nb(topology_amd_node_id(smp_processor_id())); - nb->bank4 = NULL; - } - -out_dealloc: deallocate_threshold_blocks(bank); out_free: diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 7fb5556a0b53..0dc00c9894c7 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -151,7 +151,7 @@ EXPORT_PER_CPU_SYMBOL_GPL(injectm); void mce_log(struct mce_hw_err *err) { - if (!mce_gen_pool_add(err)) + if (mce_gen_pool_add(err)) irq_work_queue(&mce_irq_work); } EXPORT_SYMBOL_GPL(mce_log); @@ -492,10 +492,10 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs } } -int mce_available(struct cpuinfo_x86 *c) +bool mce_available(struct cpuinfo_x86 *c) { if (mca_cfg.disabled) - return 0; + return false; return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA); } @@ -1778,7 +1778,7 @@ static void mce_timer_delete_all(void) * Can be called from interrupt context, but not from machine check/NMI * context. */ -int mce_notify_irq(void) +bool mce_notify_irq(void) { /* Not more than two messages every minute */ static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); @@ -1789,9 +1789,9 @@ int mce_notify_irq(void) if (__ratelimit(&ratelimit)) pr_info(HW_ERR "Machine check events logged\n"); - return 1; + return true; } - return 0; + return false; } EXPORT_SYMBOL_GPL(mce_notify_irq); @@ -1910,101 +1910,120 @@ static void __mcheck_cpu_check_banks(void) } } -/* Add per CPU specific workarounds here */ -static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) +static void apply_quirks_amd(struct cpuinfo_x86 *c) { struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); - struct mca_config *cfg = &mca_cfg; - - if (c->x86_vendor == X86_VENDOR_UNKNOWN) { - pr_info("unknown CPU type - not enabling MCE support\n"); - return -EOPNOTSUPP; - } /* This should be disabled by the BIOS, but isn't always */ - if (c->x86_vendor == X86_VENDOR_AMD) { - if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) { - /* - * disable GART TBL walk error reporting, which - * trips off incorrectly with the IOMMU & 3ware - * & Cerberus: - */ - clear_bit(10, (unsigned long *)&mce_banks[4].ctl); - } - if (c->x86 < 0x11 && cfg->bootlog < 0) { - /* - * Lots of broken BIOS around that don't clear them - * by default and leave crap in there. Don't log: - */ - cfg->bootlog = 0; - } + if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) { /* - * Various K7s with broken bank 0 around. Always disable - * by default. + * disable GART TBL walk error reporting, which + * trips off incorrectly with the IOMMU & 3ware + * & Cerberus: */ - if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0) - mce_banks[0].ctl = 0; - - /* - * overflow_recov is supported for F15h Models 00h-0fh - * even though we don't have a CPUID bit for it. - */ - if (c->x86 == 0x15 && c->x86_model <= 0xf) - mce_flags.overflow_recov = 1; - - if (c->x86 >= 0x17 && c->x86 <= 0x1A) - mce_flags.zen_ifu_quirk = 1; - + clear_bit(10, (unsigned long *)&mce_banks[4].ctl); } - if (c->x86_vendor == X86_VENDOR_INTEL) { + if (c->x86 < 0x11 && mca_cfg.bootlog < 0) { /* - * SDM documents that on family 6 bank 0 should not be written - * because it aliases to another special BIOS controlled - * register. - * But it's not aliased anymore on model 0x1a+ - * Don't ignore bank 0 completely because there could be a - * valid event later, merely don't write CTL0. + * Lots of broken BIOS around that don't clear them + * by default and leave crap in there. Don't log: */ - - if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0) - mce_banks[0].init = false; - - /* - * All newer Intel systems support MCE broadcasting. Enable - * synchronization with a one second timeout. - */ - if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) && - cfg->monarch_timeout < 0) - cfg->monarch_timeout = USEC_PER_SEC; - - /* - * There are also broken BIOSes on some Pentium M and - * earlier systems: - */ - if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0) - cfg->bootlog = 0; - - if (c->x86_vfm == INTEL_SANDYBRIDGE_X) - mce_flags.snb_ifu_quirk = 1; - - /* - * Skylake, Cascacde Lake and Cooper Lake require a quirk on - * rep movs. - */ - if (c->x86_vfm == INTEL_SKYLAKE_X) - mce_flags.skx_repmov_quirk = 1; + mca_cfg.bootlog = 0; } - if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { - /* - * All newer Zhaoxin CPUs support MCE broadcasting. Enable - * synchronization with a one second timeout. - */ - if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) { - if (cfg->monarch_timeout < 0) - cfg->monarch_timeout = USEC_PER_SEC; - } + /* + * Various K7s with broken bank 0 around. Always disable + * by default. + */ + if (c->x86 == 6 && this_cpu_read(mce_num_banks)) + mce_banks[0].ctl = 0; + + /* + * overflow_recov is supported for F15h Models 00h-0fh + * even though we don't have a CPUID bit for it. + */ + if (c->x86 == 0x15 && c->x86_model <= 0xf) + mce_flags.overflow_recov = 1; + + if (c->x86 >= 0x17 && c->x86 <= 0x1A) + mce_flags.zen_ifu_quirk = 1; +} + +static void apply_quirks_intel(struct cpuinfo_x86 *c) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + + /* Older CPUs (prior to family 6) don't need quirks. */ + if (c->x86_vfm < INTEL_PENTIUM_PRO) + return; + + /* + * SDM documents that on family 6 bank 0 should not be written + * because it aliases to another special BIOS controlled + * register. + * But it's not aliased anymore on model 0x1a+ + * Don't ignore bank 0 completely because there could be a + * valid event later, merely don't write CTL0. + */ + if (c->x86_vfm < INTEL_NEHALEM_EP && this_cpu_read(mce_num_banks)) + mce_banks[0].init = false; + + /* + * All newer Intel systems support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if (c->x86_vfm >= INTEL_CORE_YONAH && mca_cfg.monarch_timeout < 0) + mca_cfg.monarch_timeout = USEC_PER_SEC; + + /* + * There are also broken BIOSes on some Pentium M and + * earlier systems: + */ + if (c->x86_vfm < INTEL_CORE_YONAH && mca_cfg.bootlog < 0) + mca_cfg.bootlog = 0; + + if (c->x86_vfm == INTEL_SANDYBRIDGE_X) + mce_flags.snb_ifu_quirk = 1; + + /* + * Skylake, Cascacde Lake and Cooper Lake require a quirk on + * rep movs. + */ + if (c->x86_vfm == INTEL_SKYLAKE_X) + mce_flags.skx_repmov_quirk = 1; +} + +static void apply_quirks_zhaoxin(struct cpuinfo_x86 *c) +{ + /* + * All newer Zhaoxin CPUs support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (mca_cfg.monarch_timeout < 0) + mca_cfg.monarch_timeout = USEC_PER_SEC; + } +} + +/* Add per CPU specific workarounds here */ +static bool __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) +{ + struct mca_config *cfg = &mca_cfg; + + switch (c->x86_vendor) { + case X86_VENDOR_UNKNOWN: + pr_info("unknown CPU type - not enabling MCE support\n"); + return false; + case X86_VENDOR_AMD: + apply_quirks_amd(c); + break; + case X86_VENDOR_INTEL: + apply_quirks_intel(c); + break; + case X86_VENDOR_ZHAOXIN: + apply_quirks_zhaoxin(c); + break; } if (cfg->monarch_timeout < 0) @@ -2012,28 +2031,28 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (cfg->bootlog != 0) cfg->panic_timeout = 30; - return 0; + return true; } -static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) +static bool __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) { if (c->x86 != 5) - return 0; + return false; switch (c->x86_vendor) { case X86_VENDOR_INTEL: intel_p5_mcheck_init(c); mce_flags.p5 = 1; - return 1; + return true; case X86_VENDOR_CENTAUR: winchip_mcheck_init(c); mce_flags.winchip = 1; - return 1; + return true; default: - return 0; + return false; } - return 0; + return false; } /* @@ -2099,13 +2118,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_intel_feature_init(c); break; - case X86_VENDOR_AMD: { - mce_amd_feature_init(c); - break; - } - + case X86_VENDOR_AMD: case X86_VENDOR_HYGON: - mce_hygon_feature_init(c); + mce_amd_feature_init(c); break; case X86_VENDOR_CENTAUR: @@ -2279,12 +2294,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_cap_init(); - if (__mcheck_cpu_apply_quirks(c) < 0) { + if (!__mcheck_cpu_apply_quirks(c)) { mca_cfg.disabled = 1; return; } - if (mce_gen_pool_init()) { + if (!mce_gen_pool_init()) { mca_cfg.disabled = 1; pr_emerg("Couldn't allocate MCE records pool!\n"); return; diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c index d0be6dda0c14..3ca9c007a666 100644 --- a/arch/x86/kernel/cpu/mce/genpool.c +++ b/arch/x86/kernel/cpu/mce/genpool.c @@ -94,64 +94,63 @@ bool mce_gen_pool_empty(void) return llist_empty(&mce_event_llist); } -int mce_gen_pool_add(struct mce_hw_err *err) +bool mce_gen_pool_add(struct mce_hw_err *err) { struct mce_evt_llist *node; if (filter_mce(&err->m)) - return -EINVAL; + return false; if (!mce_evt_pool) - return -EINVAL; + return false; node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node)); if (!node) { pr_warn_ratelimited("MCE records pool full!\n"); - return -ENOMEM; + return false; } memcpy(&node->err, err, sizeof(*err)); llist_add(&node->llnode, &mce_event_llist); - return 0; + return true; } -static int mce_gen_pool_create(void) +static bool mce_gen_pool_create(void) { int mce_numrecords, mce_poolsz, order; struct gen_pool *gpool; - int ret = -ENOMEM; void *mce_pool; order = order_base_2(sizeof(struct mce_evt_llist)); gpool = gen_pool_create(order, -1); if (!gpool) - return ret; + return false; mce_numrecords = max(MCE_MIN_ENTRIES, num_possible_cpus() * MCE_PER_CPU); mce_poolsz = mce_numrecords * (1 << order); mce_pool = kmalloc(mce_poolsz, GFP_KERNEL); if (!mce_pool) { gen_pool_destroy(gpool); - return ret; + return false; } - ret = gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1); - if (ret) { + + if (gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1)) { gen_pool_destroy(gpool); kfree(mce_pool); - return ret; + return false; } mce_evt_pool = gpool; - return ret; + return true; } -int mce_gen_pool_init(void) +bool mce_gen_pool_init(void) { /* Just init mce_gen_pool once. */ if (mce_evt_pool) - return 0; + return true; return mce_gen_pool_create(); } diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index b3cd2c61b11d..f863df0ff42c 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -75,12 +75,12 @@ static u16 cmci_threshold[MAX_NR_BANKS]; */ #define CMCI_STORM_THRESHOLD 32749 -static int cmci_supported(int *banks) +static bool cmci_supported(int *banks) { u64 cap; if (mca_cfg.cmci_disabled || mca_cfg.ignore_ce) - return 0; + return false; /* * Vendor check is not strictly needed, but the initial @@ -89,10 +89,11 @@ static int cmci_supported(int *banks) */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) - return 0; + return false; if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) - return 0; + return false; + rdmsrl(MSR_IA32_MCG_CAP, cap); *banks = min_t(unsigned, MAX_NR_BANKS, cap & MCG_BANKCNT_MASK); return !!(cap & MCG_CMCI_P); diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 84f810598231..95a504ece43e 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -31,8 +31,8 @@ struct mce_evt_llist { void mce_gen_pool_process(struct work_struct *__unused); bool mce_gen_pool_empty(void); -int mce_gen_pool_add(struct mce_hw_err *err); -int mce_gen_pool_init(void); +bool mce_gen_pool_add(struct mce_hw_err *err); +bool mce_gen_pool_init(void); struct llist_node *mce_gen_pool_prepare_records(void); int mce_severity(struct mce *a, struct pt_regs *regs, char **msg, bool is_excp); diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c index 89e31e1e5c9c..f4a007616468 100644 --- a/arch/x86/kernel/cpu/mce/threshold.c +++ b/arch/x86/kernel/cpu/mce/threshold.c @@ -90,7 +90,7 @@ void cmci_storm_end(unsigned int bank) storm->banks[bank].in_storm_mode = false; /* If no banks left in storm mode, stop polling. */ - if (!this_cpu_dec_return(storm_desc.stormy_bank_count)) + if (!--storm->stormy_bank_count) mce_timer_kick(false); } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index fb5d0c67fbab..a5dac7f3c0a0 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -283,13 +283,13 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize) * exceed the per-family maximum). @sh_psize is the size read from the section * header. */ -static unsigned int __verify_patch_size(u32 sh_psize, size_t buf_size) +static bool __verify_patch_size(u32 sh_psize, size_t buf_size) { u8 family = x86_family(bsp_cpuid_1_eax); u32 max_size; if (family >= 0x15) - return min_t(u32, sh_psize, buf_size); + goto ret; #define F1XH_MPB_MAX_SIZE 2048 #define F14H_MPB_MAX_SIZE 1824 @@ -303,13 +303,15 @@ static unsigned int __verify_patch_size(u32 sh_psize, size_t buf_size) break; default: WARN(1, "%s: WTF family: 0x%x\n", __func__, family); - return 0; + return false; } - if (sh_psize > min_t(u32, buf_size, max_size)) - return 0; + if (sh_psize > max_size) + return false; - return sh_psize; +ret: + /* Working with the whole buffer so < is ok. */ + return sh_psize <= buf_size; } /* @@ -324,7 +326,6 @@ static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size) { u8 family = x86_family(bsp_cpuid_1_eax); struct microcode_header_amd *mc_hdr; - unsigned int ret; u32 sh_psize; u16 proc_id; u8 patch_fam; @@ -348,8 +349,7 @@ static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size) return -1; } - ret = __verify_patch_size(sh_psize, buf_size); - if (!ret) { + if (!__verify_patch_size(sh_psize, buf_size)) { pr_debug("Per-family patch size mismatch.\n"); return -1; } @@ -381,8 +381,8 @@ static bool mc_patch_matches(struct microcode_amd *mc, u16 eq_id) /* * This scans the ucode blob for the proper container as we can have multiple - * containers glued together. Returns the equivalence ID from the equivalence - * table or 0 if none found. + * containers glued together. + * * Returns the amount of bytes consumed while scanning. @desc contains all the * data we're going to use in later stages of the application. */ @@ -484,7 +484,7 @@ static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc) } } -static int __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize) +static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize) { unsigned long p_addr = (unsigned long)&mc->hdr.data_code; u32 rev, dummy; @@ -508,9 +508,9 @@ static int __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize) native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); if (rev != mc->hdr.patch_id) - return -1; + return false; - return 0; + return true; } /* @@ -528,13 +528,12 @@ static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size) { struct cont_desc desc = { 0 }; struct microcode_amd *mc; - bool ret = false; scan_containers(ucode, size, &desc); mc = desc.mc; if (!mc) - return ret; + return false; /* * Allow application of the same revision to pick up SMT-specific @@ -542,9 +541,9 @@ static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size) * up-to-date. */ if (old_rev > mc->hdr.patch_id) - return ret; + return false; - return !__apply_microcode_amd(mc, desc.psize); + return __apply_microcode_amd(mc, desc.psize); } static bool get_builtin_microcode(struct cpio_data *cp) @@ -569,14 +568,19 @@ static bool get_builtin_microcode(struct cpio_data *cp) return false; } -static void __init find_blobs_in_containers(struct cpio_data *ret) +static bool __init find_blobs_in_containers(struct cpio_data *ret) { struct cpio_data cp; + bool found; if (!get_builtin_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path); - *ret = cp; + found = cp.data && cp.size; + if (found) + *ret = cp; + + return found; } void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax) @@ -591,8 +595,7 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_ /* Needed in load_microcode_amd() */ ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax; - find_blobs_in_containers(&cp); - if (!(cp.data && cp.size)) + if (!find_blobs_in_containers(&cp)) return; if (early_apply_microcode(ed->old_rev, cp.data, cp.size)) @@ -612,8 +615,7 @@ static int __init save_microcode_in_initrd(void) if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) return 0; - find_blobs_in_containers(&cp); - if (!(cp.data && cp.size)) + if (!find_blobs_in_containers(&cp)) return -EINVAL; scan_containers(cp.data, cp.size, &desc); @@ -760,7 +762,7 @@ void reload_ucode_amd(unsigned int cpu) rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); if (rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc, p->size)) + if (__apply_microcode_amd(mc, p->size)) pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id); } } @@ -813,7 +815,7 @@ static enum ucode_state apply_microcode_amd(int cpu) goto out; } - if (__apply_microcode_amd(mc_amd, p->size)) { + if (!__apply_microcode_amd(mc_amd, p->size)) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); return UCODE_ERROR; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..f285757618fc 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include #include @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 7b29ebda024f..2fdfda2b60e4 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -423,7 +423,7 @@ void __init mtrr_copy_map(void) } /** - * mtrr_overwrite_state - set static MTRR state + * guest_force_mtrr_state - set static MTRR state for a guest * * Used to set MTRR state via different means (e.g. with data obtained from * a hypervisor). @@ -436,8 +436,8 @@ void __init mtrr_copy_map(void) * @num_var: length of the @var array * @def_type: default caching type */ -void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, - mtrr_type def_type) +void guest_force_mtrr_state(struct mtrr_var_range *var, unsigned int num_var, + mtrr_type def_type) { unsigned int i; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 989d368be04f..ecbda0341a8a 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -625,7 +625,7 @@ void mtrr_save_state(void) static int __init mtrr_init_finalize(void) { /* - * Map might exist if mtrr_overwrite_state() has been called or if + * Map might exist if guest_force_mtrr_state() has been called or if * mtrr_enabled() returns true. */ mtrr_copy_map(); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index b681c2e07dbf..3d1735ed8d1f 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -234,7 +234,9 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r) r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD; else r->membw.throttle_mode = THREAD_THROTTLE_MAX; - thread_throttle_mode_init(); + + resctrl_file_fflags_init("thread_throttle_mode", + RFTYPE_CTRL_INFO | RFTYPE_RES_MB); r->alloc_capable = true; @@ -961,6 +963,11 @@ static __init bool get_rdt_mon_resources(void) if (!rdt_mon_features) return false; + if (is_mbm_local_enabled()) + mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID; + else if (is_mbm_total_enabled()) + mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID; + return !rdt_get_mon_l3_config(r); } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 200d89a64027..536351159cc2 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -518,6 +518,76 @@ static int smp_mon_event_count(void *arg) return 0; } +ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + buf[nbytes - 1] = '\0'; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + rdt_last_cmd_clear(); + + if (!strcmp(buf, "mbm_local_bytes")) { + if (is_mbm_local_enabled()) + rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID; + else + ret = -EINVAL; + } else if (!strcmp(buf, "mbm_total_bytes")) { + if (is_mbm_total_enabled()) + rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID; + else + ret = -EINVAL; + } else { + ret = -EINVAL; + } + + if (ret) + rdt_last_cmd_printf("Unsupported event id '%s'\n", buf); + + rdtgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + if (rdtgrp) { + switch (rdtgrp->mba_mbps_event) { + case QOS_L3_MBM_LOCAL_EVENT_ID: + seq_puts(s, "mbm_local_bytes\n"); + break; + case QOS_L3_MBM_TOTAL_EVENT_ID: + seq_puts(s, "mbm_total_bytes\n"); + break; + default: + pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event); + ret = -EINVAL; + break; + } + } else { + ret = -ENOENT; + } + + rdtgroup_kn_unlock(of->kn); + + return ret; +} + void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, cpumask_t *cpumask, int evtid, int first) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 955999aecfca..20c898f09b7e 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -283,6 +283,7 @@ struct pseudo_lock_region { * monitor only or ctrl_mon group * @mon: mongroup related data * @mode: mode of resource group + * @mba_mbps_event: input monitoring event id when mba_sc is enabled * @plr: pseudo-locked region */ struct rdtgroup { @@ -295,6 +296,7 @@ struct rdtgroup { enum rdt_group_type type; struct mongroup mon; enum rdtgrp_mode mode; + enum resctrl_event_id mba_mbps_event; struct pseudo_lock_region *plr; }; @@ -508,6 +510,7 @@ extern struct mutex rdtgroup_mutex; extern struct rdt_hw_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; extern struct dentry *debugfs_resctrl; +extern enum resctrl_event_id mba_mbps_default_event; enum resctrl_res_level { RDT_RESOURCE_L3, @@ -607,6 +610,10 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); +ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of, + struct seq_file *s, void *v); bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d, unsigned long cbm, int closid, bool exclusive); unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d, @@ -647,10 +654,8 @@ void cqm_handle_limbo(struct work_struct *work); bool has_busy_rmid(struct rdt_mon_domain *d); void __check_limbo(struct rdt_mon_domain *d, bool force_free); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); -void __init thread_throttle_mode_init(void); -void __init mbm_config_rftype_init(const char *config); +void resctrl_file_fflags_init(const char *config, unsigned long fflags); void rdt_staged_configs_clear(void); bool closid_allocated(unsigned int closid); int resctrl_find_cleanest_closid(void); - #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 5fcb3d635d91..94a1d9780461 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -663,9 +663,12 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) */ static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) { - u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); - struct mbm_state *m = &rr->d->mbm_local[idx]; u64 cur_bw, bytes, cur_bytes; + struct mbm_state *m; + + m = get_mbm_state(rr->d, closid, rmid, rr->evtid); + if (WARN_ON_ONCE(!m)) + return; cur_bytes = rr->val; bytes = cur_bytes - m->prev_bw_bytes; @@ -752,20 +755,20 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; struct rdt_ctrl_domain *dom_mba; + enum resctrl_event_id evt_id; struct rdt_resource *r_mba; - u32 cur_bw, user_bw, idx; struct list_head *head; struct rdtgroup *entry; - - if (!is_mbm_local_enabled()) - return; + u32 cur_bw, user_bw; r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; + evt_id = rgrp->mba_mbps_event; closid = rgrp->closid; rmid = rgrp->mon.rmid; - idx = resctrl_arch_rmid_idx_encode(closid, rmid); - pmbm_data = &dom_mbm->mbm_local[idx]; + pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id); + if (WARN_ON_ONCE(!pmbm_data)) + return; dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba); if (!dom_mba) { @@ -784,7 +787,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) */ head = &rgrp->mon.crdtgrp_list; list_for_each_entry(entry, head, mon.crdtgrp_list) { - cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; + cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id); + if (WARN_ON_ONCE(!cmbm_data)) + return; cur_bw += cmbm_data->prev_bw; } @@ -813,54 +818,45 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); } -static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, - u32 closid, u32 rmid) +static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d, + u32 closid, u32 rmid, enum resctrl_event_id evtid) { struct rmid_read rr = {0}; rr.r = r; rr.d = d; + rr.evtid = evtid; + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + if (IS_ERR(rr.arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(rr.arch_mon_ctx)); + return; + } + + __mon_event_count(closid, rmid, &rr); /* - * This is protected from concurrent reads from user - * as both the user and we hold the global mutex. + * If the software controller is enabled, compute the + * bandwidth for this event id. */ - if (is_mbm_total_enabled()) { - rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; - rr.val = 0; - rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); - if (IS_ERR(rr.arch_mon_ctx)) { - pr_warn_ratelimited("Failed to allocate monitor context: %ld", - PTR_ERR(rr.arch_mon_ctx)); - return; - } + if (is_mba_sc(NULL)) + mbm_bw_count(closid, rmid, &rr); - __mon_event_count(closid, rmid, &rr); + resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); +} - resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); - } - if (is_mbm_local_enabled()) { - rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; - rr.val = 0; - rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); - if (IS_ERR(rr.arch_mon_ctx)) { - pr_warn_ratelimited("Failed to allocate monitor context: %ld", - PTR_ERR(rr.arch_mon_ctx)); - return; - } +static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, + u32 closid, u32 rmid) +{ + /* + * This is protected from concurrent reads from user as both + * the user and overflow handler hold the global mutex. + */ + if (is_mbm_total_enabled()) + mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID); - __mon_event_count(closid, rmid, &rr); - - /* - * Call the MBA software controller only for the - * control groups and when user has enabled - * the software controller explicitly. - */ - if (is_mba_sc(NULL)) - mbm_bw_count(closid, rmid, &rr); - - resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); - } + if (is_mbm_local_enabled()) + mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID); } /* @@ -1224,11 +1220,13 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { mbm_total_event.configurable = true; - mbm_config_rftype_init("mbm_total_bytes_config"); + resctrl_file_fflags_init("mbm_total_bytes_config", + RFTYPE_MON_INFO | RFTYPE_RES_CACHE); } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { mbm_local_event.configurable = true; - mbm_config_rftype_init("mbm_local_bytes_config"); + resctrl_file_fflags_init("mbm_local_bytes_config", + RFTYPE_MON_INFO | RFTYPE_RES_CACHE); } } diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 972e6b6b0481..42cc162f7fc9 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -459,7 +459,7 @@ static int pseudo_lock_fn(void *_rdtgrp) * increase likelihood that allocated cache portion will be filled * with associated memory. */ - native_wbinvd(); + wbinvd(); /* * Always called with interrupts enabled. By disabling interrupts @@ -1205,20 +1205,14 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) plr->cpu = cpu; if (sel == 1) - thread = kthread_create_on_node(measure_cycles_lat_fn, plr, - cpu_to_node(cpu), - "pseudo_lock_measure/%u", - cpu); + thread = kthread_run_on_cpu(measure_cycles_lat_fn, plr, + cpu, "pseudo_lock_measure/%u"); else if (sel == 2) - thread = kthread_create_on_node(measure_l2_residency, plr, - cpu_to_node(cpu), - "pseudo_lock_measure/%u", - cpu); + thread = kthread_run_on_cpu(measure_l2_residency, plr, + cpu, "pseudo_lock_measure/%u"); else if (sel == 3) - thread = kthread_create_on_node(measure_l3_residency, plr, - cpu_to_node(cpu), - "pseudo_lock_measure/%u", - cpu); + thread = kthread_run_on_cpu(measure_l3_residency, plr, + cpu, "pseudo_lock_measure/%u"); else goto out; @@ -1226,8 +1220,6 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) ret = PTR_ERR(thread); goto out; } - kthread_bind(thread, cpu); - wake_up_process(thread); ret = wait_event_interruptible(plr->lock_thread_wq, plr->thread_done == 1); @@ -1315,18 +1307,14 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) plr->thread_done = 0; - thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp, - cpu_to_node(plr->cpu), - "pseudo_lock/%u", plr->cpu); + thread = kthread_run_on_cpu(pseudo_lock_fn, rdtgrp, + plr->cpu, "pseudo_lock/%u"); if (IS_ERR(thread)) { ret = PTR_ERR(thread); rdt_last_cmd_printf("Locking thread returned error %d\n", ret); goto out_cstates; } - kthread_bind(thread, plr->cpu); - wake_up_process(thread); - ret = wait_event_interruptible(plr->lock_thread_wq, plr->thread_done == 1); if (ret < 0) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index d906a1cd8491..6419e04d8a7b 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -65,6 +65,15 @@ static void rdtgroup_destroy_root(void); struct dentry *debugfs_resctrl; +/* + * Memory bandwidth monitoring event to use for the default CTRL_MON group + * and each new CTRL_MON group created by the user. Only relevant when + * the filesystem is mounted with the "mba_MBps" option so it does not + * matter that it remains uninitialized on systems that do not support + * the "mba_MBps" option. + */ +enum resctrl_event_id mba_mbps_default_event; + static bool resctrl_debug; void rdt_last_cmd_clear(void) @@ -1941,6 +1950,13 @@ static struct rftype res_common_files[] = { .seq_show = rdtgroup_schemata_show, .fflags = RFTYPE_CTRL_BASE, }, + { + .name = "mba_MBps_event", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_mba_mbps_event_write, + .seq_show = rdtgroup_mba_mbps_event_show, + }, { .name = "mode", .mode = 0644, @@ -2020,24 +2036,13 @@ static struct rftype *rdtgroup_get_rftype_by_name(const char *name) return NULL; } -void __init thread_throttle_mode_init(void) -{ - struct rftype *rft; - - rft = rdtgroup_get_rftype_by_name("thread_throttle_mode"); - if (!rft) - return; - - rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB; -} - -void __init mbm_config_rftype_init(const char *config) +void resctrl_file_fflags_init(const char *config, unsigned long fflags) { struct rftype *rft; rft = rdtgroup_get_rftype_by_name(config); if (rft) - rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE; + rft->fflags = fflags; } /** @@ -2343,7 +2348,7 @@ static bool supports_mba_mbps(void) struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; - return (is_mbm_local_enabled() && + return (is_mbm_enabled() && r->alloc_capable && is_mba_linear() && r->ctrl_scope == rmbm->mon_scope); } @@ -2357,6 +2362,7 @@ static int set_mba_sc(bool mba_sc) struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; u32 num_closid = resctrl_arch_get_num_closid(r); struct rdt_ctrl_domain *d; + unsigned long fflags; int i; if (!supports_mba_mbps() || mba_sc == is_mba_sc(r)) @@ -2364,11 +2370,16 @@ static int set_mba_sc(bool mba_sc) r->membw.mba_sc = mba_sc; + rdtgroup_default.mba_mbps_event = mba_mbps_default_event; + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { for (i = 0; i < num_closid; i++) d->mbps_val[i] = MBA_MAX_MBPS; } + fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0; + resctrl_file_fflags_init("mba_MBps_event", fflags); + return 0; } @@ -2768,7 +2779,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx->enable_cdpl2 = true; return 0; case Opt_mba_mbps: - msg = "mba_MBps requires local MBM and linear scale MBA at L3 scope"; + msg = "mba_MBps requires MBM and linear scale MBA at L3 scope"; if (!supports_mba_mbps()) return invalfc(fc, msg); ctx->enable_mba_mbps = true; @@ -3622,6 +3633,8 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, rdt_last_cmd_puts("kernfs subdir error\n"); goto out_del_list; } + if (is_mba_sc(NULL)) + rdtgrp->mba_mbps_event = mba_mbps_default_event; } goto out_unlock; diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index b2e313ea17bf..01456236a6dd 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -428,7 +428,7 @@ void __init topology_apply_cmdline_limits_early(void) { unsigned int possible = nr_cpu_ids; - /* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' */ + /* 'maxcpus=0' 'nosmp' 'nolapic' */ if (!setup_max_cpus || apic_is_disabled) possible = 1; diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c index 8277c64f88db..b5a5e1411469 100644 --- a/arch/x86/kernel/cpu/topology_common.c +++ b/arch/x86/kernel/cpu/topology_common.c @@ -185,6 +185,7 @@ static void topo_set_ids(struct topo_scan *tscan, bool early) if (!early) { c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN); c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN); + c->topo.logical_core_id = topology_get_logical_id(apicid, TOPO_CORE_DOMAIN); } /* Package relative core ID */ diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 4893d30ce438..82b96ed9890a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1146,11 +1146,8 @@ void __init e820__reserve_resources(void) struct resource *res; u64 end; - res = memblock_alloc(sizeof(*res) * e820_table->nr_entries, + res = memblock_alloc_or_panic(sizeof(*res) * e820_table->nr_entries, SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*res) * e820_table->nr_entries); e820_res = res; for (i = 0; i < e820_table->nr_entries; i++) { diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 6bc1eb2a21bd..887b0b8e21e3 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -190,7 +190,8 @@ int ssp_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct cet_user_state *cetregs; - if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !ssp_active(target, regset)) return -ENODEV; sync_fpstate(fpu); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 22abb5ee0cf2..27417b685c1d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -20,6 +20,7 @@ #include #include +#include #include #include #include @@ -232,7 +233,7 @@ static void __init setup_xstate_cache(void) xmm_space); for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx); xstate_sizes[i] = eax; xstate_flags[i] = ecx; @@ -398,7 +399,7 @@ int xfeature_size(int xfeature_nr) u32 eax, ebx, ecx, edx; CHECK_XFEATURE(xfeature_nr); - cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, xfeature_nr, &eax, &ebx, &ecx, &edx); return eax; } @@ -441,9 +442,9 @@ static void __init __xstate_dump_leaves(void) * just in case there are some goodies up there */ for (i = 0; i < XFEATURE_MAX + 10; i++) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx); pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n", - XSTATE_CPUID, i, eax, ebx, ecx, edx); + CPUID_LEAF_XSTATE, i, eax, ebx, ecx, edx); } } @@ -484,7 +485,7 @@ static int __init check_xtile_data_against_struct(int size) * Check the maximum palette id: * eax: the highest numbered palette subleaf. */ - cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_TILE, 0, &max_palid, &ebx, &ecx, &edx); /* * Cross-check each tile size and find the maximum number of @@ -498,7 +499,7 @@ static int __init check_xtile_data_against_struct(int size) * eax[31:16]: bytes per title * ebx[31:16]: the max names (or max number of tiles) */ - cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx); + cpuid_count(CPUID_LEAF_TILE, palid, &eax, &ebx, &edx, &edx); tile_size = eax >> 16; max = ebx >> 16; @@ -633,7 +634,7 @@ static unsigned int __init get_compacted_size(void) * are no supervisor states, but XSAVEC still uses compacted * format. */ - cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx); return ebx; } @@ -674,7 +675,7 @@ static unsigned int __init get_xsave_size_user(void) * containing all the *user* state components * corresponding to bits currently set in XCR0. */ - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx); return ebx; } @@ -763,21 +764,16 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) return; } - if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { - WARN_ON_FPU(1); - return; - } - /* * Find user xstates supported by the processor. */ - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features = eax + ((u64)edx << 32); /* * Find supervisor xstates supported by the processor. */ - cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32); if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { diff --git a/arch/x86/kernel/fred.c b/arch/x86/kernel/fred.c index 8d32c3f48abc..5e2cd1004980 100644 --- a/arch/x86/kernel/fred.c +++ b/arch/x86/kernel/fred.c @@ -50,7 +50,13 @@ void cpu_init_fred_exceptions(void) FRED_CONFIG_ENTRYPOINT(asm_fred_entrypoint_user)); wrmsrl(MSR_IA32_FRED_STKLVLS, 0); - wrmsrl(MSR_IA32_FRED_RSP0, 0); + + /* + * Ater a CPU offline/online cycle, the FRED RSP0 MSR should be + * resynchronized with its per-CPU cache. + */ + wrmsrl(MSR_IA32_FRED_RSP0, __this_cpu_read(fred_rsp0)); + wrmsrl(MSR_IA32_FRED_RSP1, 0); wrmsrl(MSR_IA32_FRED_RSP2, 0); wrmsrl(MSR_IA32_FRED_RSP3, 0); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 4dd0ad6c94d6..166bc0ea3bdf 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -607,16 +607,8 @@ int ftrace_disable_ftrace_graph_caller(void) } #endif /* CONFIG_DYNAMIC_FTRACE && !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ -/* - * Hook the return address and push it in the stack of return addrs - * in current thread info. - */ -void prepare_ftrace_return(unsigned long ip, unsigned long *parent, - unsigned long frame_pointer) +static inline bool skip_ftrace_return(void) { - unsigned long return_hooker = (unsigned long)&return_to_handler; - int bit; - /* * When resuming from suspend-to-ram, this function can be indirectly * called from early CPU startup code while the CPU is in real mode, @@ -626,23 +618,31 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent, * This check isn't as accurate as virt_addr_valid(), but it should be * good enough for this purpose, and it's fast. */ - if (unlikely((long)__builtin_frame_address(0) >= 0)) - return; + if ((long)__builtin_frame_address(0) >= 0) + return true; - if (unlikely(ftrace_graph_is_dead())) - return; + if (ftrace_graph_is_dead()) + return true; - if (unlikely(atomic_read(¤t->tracing_graph_pause))) - return; + if (atomic_read(¤t->tracing_graph_pause)) + return true; + return false; +} - bit = ftrace_test_recursion_trylock(ip, *parent); - if (bit < 0) +/* + * Hook the return address and push it in the stack of return addrs + * in current thread info. + */ +void prepare_ftrace_return(unsigned long ip, unsigned long *parent, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + + if (unlikely(skip_ftrace_return())) return; if (!function_graph_enter(*parent, ip, frame_pointer, parent)) *parent = return_hooker; - - ftrace_test_recursion_unlock(bit); } #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS @@ -651,8 +651,15 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, { struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs; unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs); + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long *parent = (unsigned long *)stack; - prepare_ftrace_return(ip, (unsigned long *)stack, 0); + if (unlikely(skip_ftrace_return())) + return; + + + if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs)) + *parent = return_hooker; } #endif diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index 58d9ed50fe61..f4e0c3361234 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -187,14 +187,15 @@ SYM_CODE_END(ftrace_graph_caller) .globl return_to_handler return_to_handler: - pushl $0 - pushl %edx - pushl %eax + subl $(PTREGS_SIZE), %esp + movl $0, PT_EBP(%esp) + movl %edx, PT_EDX(%esp) + movl %eax, PT_EAX(%esp) movl %esp, %eax call ftrace_return_to_handler movl %eax, %ecx - popl %eax - popl %edx - addl $4, %esp # skip ebp + movl PT_EAX(%esp), %eax + movl PT_EDX(%esp), %edx + addl $(PTREGS_SIZE), %esp JMP_NOSPEC ecx #endif diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 214f30e9f0c0..d51647228596 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -348,21 +348,22 @@ STACK_FRAME_NON_STANDARD_FP(__fentry__) SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - subq $24, %rsp - /* Save the return values */ - movq %rax, (%rsp) - movq %rdx, 8(%rsp) - movq %rbp, 16(%rsp) + /* Save ftrace_regs for function exit context */ + subq $(FRAME_SIZE), %rsp + + movq %rax, RAX(%rsp) + movq %rdx, RDX(%rsp) + movq %rbp, RBP(%rsp) movq %rsp, %rdi call ftrace_return_to_handler movq %rax, %rdi - movq 8(%rsp), %rdx - movq (%rsp), %rax + movq RDX(%rsp), %rdx + movq RAX(%rsp), %rax - addq $24, %rsp + addq $(FRAME_SIZE), %rsp /* * Jump back to the old return address. This cannot be JMP_NOSPEC rdi * since IBT would demand that contain ENDBR, which simply isn't so for diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 4b9d4557fc94..22c9ba305ac1 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -91,9 +91,11 @@ static inline bool check_la57_support(void) return true; } -static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd) +static unsigned long __head sme_postprocess_startup(struct boot_params *bp, + pmdval_t *pmd, + unsigned long p2v_offset) { - unsigned long vaddr, vaddr_end; + unsigned long paddr, paddr_end; int i; /* Encrypt the kernel and related (if SME is active) */ @@ -106,10 +108,10 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv * attribute. */ if (sme_get_me_mask()) { - vaddr = (unsigned long)__start_bss_decrypted; - vaddr_end = (unsigned long)__end_bss_decrypted; + paddr = (unsigned long)&RIP_REL_REF(__start_bss_decrypted); + paddr_end = (unsigned long)&RIP_REL_REF(__end_bss_decrypted); - for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + for (; paddr < paddr_end; paddr += PMD_SIZE) { /* * On SNP, transition the page to shared in the RMP table so that * it is consistent with the page table attribute change. @@ -118,11 +120,11 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv * mapping (kernel .text). PVALIDATE, by way of * early_snp_set_memory_shared(), requires a valid virtual * address but the kernel is currently running off of the identity - * mapping so use __pa() to get a *currently* valid virtual address. + * mapping so use the PA to get a *currently* valid virtual address. */ - early_snp_set_memory_shared(__pa(vaddr), __pa(vaddr), PTRS_PER_PMD); + early_snp_set_memory_shared(paddr, paddr, PTRS_PER_PMD); - i = pmd_index(vaddr); + i = pmd_index(paddr - p2v_offset); pmd[i] -= sme_get_me_mask(); } } @@ -138,12 +140,15 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv * doesn't have to generate PC-relative relocations when accessing globals from * that function. Clang actually does not generate them, which leads to * boot-time crashes. To work around this problem, every global pointer must - * be accessed using RIP_REL_REF(). + * be accessed using RIP_REL_REF(). Kernel virtual addresses can be determined + * by subtracting p2v_offset from the RIP-relative address. */ -unsigned long __head __startup_64(unsigned long physaddr, +unsigned long __head __startup_64(unsigned long p2v_offset, struct boot_params *bp) { pmd_t (*early_pgts)[PTRS_PER_PMD] = RIP_REL_REF(early_dynamic_pgts); + unsigned long physaddr = (unsigned long)&RIP_REL_REF(_text); + unsigned long va_text, va_end; unsigned long pgtable_flags; unsigned long load_delta; pgdval_t *pgd; @@ -163,13 +168,16 @@ unsigned long __head __startup_64(unsigned long physaddr, * Compute the delta between the address I am compiled to run at * and the address I am actually running at. */ - load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map); + load_delta = __START_KERNEL_map + p2v_offset; RIP_REL_REF(phys_base) = load_delta; /* Is the address not 2M aligned? */ if (load_delta & ~PMD_MASK) for (;;); + va_text = physaddr - p2v_offset; + va_end = (unsigned long)&RIP_REL_REF(_end) - p2v_offset; + /* Include the SME encryption mask in the fixup value */ load_delta += sme_get_me_mask(); @@ -178,7 +186,7 @@ unsigned long __head __startup_64(unsigned long physaddr, pgd = &RIP_REL_REF(early_top_pgt)->pgd; pgd[pgd_index(__START_KERNEL_map)] += load_delta; - if (la57) { + if (IS_ENABLED(CONFIG_X86_5LEVEL) && la57) { p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt); p4d[MAX_PTRS_PER_P4D - 1] += load_delta; @@ -230,7 +238,7 @@ unsigned long __head __startup_64(unsigned long physaddr, pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; - for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { + for (i = 0; i < DIV_ROUND_UP(va_end - va_text, PMD_SIZE); i++) { int idx = i + (physaddr >> PMD_SHIFT); pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE; @@ -255,11 +263,11 @@ unsigned long __head __startup_64(unsigned long physaddr, pmd = &RIP_REL_REF(level2_kernel_pgt)->pmd; /* invalidate pages before the kernel image */ - for (i = 0; i < pmd_index((unsigned long)_text); i++) + for (i = 0; i < pmd_index(va_text); i++) pmd[i] &= ~_PAGE_PRESENT; /* fixup pages that are part of the kernel image */ - for (; i <= pmd_index((unsigned long)_end); i++) + for (; i <= pmd_index(va_end); i++) if (pmd[i] & _PAGE_PRESENT) pmd[i] += load_delta; @@ -267,7 +275,7 @@ unsigned long __head __startup_64(unsigned long physaddr, for (; i < PTRS_PER_PMD; i++) pmd[i] &= ~_PAGE_PRESENT; - return sme_postprocess_startup(bp, pmd); + return sme_postprocess_startup(bp, pmd, p2v_offset); } /* Wipe all early page tables except for the kernel symbol map */ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 56163e2124cf..31345e0ba006 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -94,13 +94,19 @@ SYM_CODE_START_NOALIGN(startup_64) /* Sanitize CPU configuration */ call verify_cpu + /* + * Derive the kernel's physical-to-virtual offset from the physical and + * virtual addresses of common_startup_64(). + */ + leaq common_startup_64(%rip), %rdi + subq .Lcommon_startup_64(%rip), %rdi + /* * Perform pagetable fixups. Additionally, if SME is active, encrypt * the kernel and retrieve the modifier (SME encryption mask if SME * is active) to be added to the initial pgdir entry that will be * programmed into CR3. */ - leaq _text(%rip), %rdi movq %r15, %rsi call __startup_64 @@ -128,11 +134,11 @@ SYM_CODE_START_NOALIGN(startup_64) /* Branch to the common startup code at its kernel virtual address */ ANNOTATE_RETPOLINE_SAFE - jmp *0f(%rip) + jmp *.Lcommon_startup_64(%rip) SYM_CODE_END(startup_64) __INITRODATA -0: .quad common_startup_64 +SYM_DATA_LOCAL(.Lcommon_startup_64, .quad common_startup_64) .text SYM_CODE_START(secondary_startup_64) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c96ae8fee95e..7f4b2966e15c 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -516,22 +517,14 @@ static int hpet_msi_init(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq, irq_hw_number_t hwirq, msi_alloc_info_t *arg) { - irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); irq_domain_set_info(domain, virq, arg->hwirq, info->chip, NULL, handle_edge_irq, arg->data, "edge"); return 0; } -static void hpet_msi_free(struct irq_domain *domain, - struct msi_domain_info *info, unsigned int virq) -{ - irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); -} - static struct msi_domain_ops hpet_msi_domain_ops = { .msi_init = hpet_msi_init, - .msi_free = hpet_msi_free, }; static struct msi_domain_info hpet_msi_domain_info = { @@ -927,10 +920,7 @@ static bool __init mwait_pc10_supported(void) if (!cpu_feature_enabled(X86_FEATURE_MWAIT)) return false; - if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) - return false; - - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &mwait_substates); return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) && (ecx & CPUID5_ECX_INTERRUPT_BREAK) && @@ -1392,12 +1382,6 @@ int hpet_set_periodic_freq(unsigned long freq) } EXPORT_SYMBOL_GPL(hpet_set_periodic_freq); -int hpet_rtc_dropped_irq(void) -{ - return is_hpet_enabled(); -} -EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq); - static void hpet_rtc_timer_reinit(void) { unsigned int delta; diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index 51b805c727fc..9cea1fc36c18 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -34,49 +35,38 @@ static bool __read_mostly sched_itmt_capable; * of higher turbo frequency for cpus supporting Intel Turbo Boost Max * Technology 3.0. * - * It can be set via /proc/sys/kernel/sched_itmt_enabled + * It can be set via /sys/kernel/debug/x86/sched_itmt_enabled */ -unsigned int __read_mostly sysctl_sched_itmt_enabled; +bool __read_mostly sysctl_sched_itmt_enabled; -static int sched_itmt_update_handler(const struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static ssize_t sched_itmt_enabled_write(struct file *filp, + const char __user *ubuf, + size_t cnt, loff_t *ppos) { - unsigned int old_sysctl; - int ret; + ssize_t result; + bool orig; - mutex_lock(&itmt_update_mutex); + guard(mutex)(&itmt_update_mutex); - if (!sched_itmt_capable) { - mutex_unlock(&itmt_update_mutex); - return -EINVAL; - } + orig = sysctl_sched_itmt_enabled; + result = debugfs_write_file_bool(filp, ubuf, cnt, ppos); - old_sysctl = sysctl_sched_itmt_enabled; - ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - - if (!ret && write && old_sysctl != sysctl_sched_itmt_enabled) { + if (sysctl_sched_itmt_enabled != orig) { x86_topology_update = true; rebuild_sched_domains(); } - mutex_unlock(&itmt_update_mutex); - - return ret; + return result; } -static struct ctl_table itmt_kern_table[] = { - { - .procname = "sched_itmt_enabled", - .data = &sysctl_sched_itmt_enabled, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_itmt_update_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, +static const struct file_operations dfs_sched_itmt_fops = { + .read = debugfs_read_file_bool, + .write = sched_itmt_enabled_write, + .open = simple_open, + .llseek = default_llseek, }; -static struct ctl_table_header *itmt_sysctl_header; +static struct dentry *dfs_sched_itmt; /** * sched_set_itmt_support() - Indicate platform supports ITMT @@ -97,16 +87,18 @@ static struct ctl_table_header *itmt_sysctl_header; */ int sched_set_itmt_support(void) { - mutex_lock(&itmt_update_mutex); + guard(mutex)(&itmt_update_mutex); - if (sched_itmt_capable) { - mutex_unlock(&itmt_update_mutex); + if (sched_itmt_capable) return 0; - } - itmt_sysctl_header = register_sysctl("kernel", itmt_kern_table); - if (!itmt_sysctl_header) { - mutex_unlock(&itmt_update_mutex); + dfs_sched_itmt = debugfs_create_file_unsafe("sched_itmt_enabled", + 0644, + arch_debugfs_dir, + &sysctl_sched_itmt_enabled, + &dfs_sched_itmt_fops); + if (IS_ERR_OR_NULL(dfs_sched_itmt)) { + dfs_sched_itmt = NULL; return -ENOMEM; } @@ -117,8 +109,6 @@ int sched_set_itmt_support(void) x86_topology_update = true; rebuild_sched_domains(); - mutex_unlock(&itmt_update_mutex); - return 0; } @@ -134,18 +124,15 @@ int sched_set_itmt_support(void) */ void sched_clear_itmt_support(void) { - mutex_lock(&itmt_update_mutex); + guard(mutex)(&itmt_update_mutex); - if (!sched_itmt_capable) { - mutex_unlock(&itmt_update_mutex); + if (!sched_itmt_capable) return; - } + sched_itmt_capable = false; - if (itmt_sysctl_header) { - unregister_sysctl_table(itmt_sysctl_header); - itmt_sysctl_header = NULL; - } + debugfs_remove(dfs_sched_itmt); + dfs_sched_itmt = NULL; if (sysctl_sched_itmt_enabled) { /* disable sched_itmt if we are no longer ITMT capable */ @@ -153,8 +140,6 @@ void sched_clear_itmt_support(void) x86_topology_update = true; rebuild_sched_domains(); } - - mutex_unlock(&itmt_update_mutex); } int arch_asym_cpu_priority(int cpu) diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 257892fcefa7..b68d4be9464e 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -28,19 +28,19 @@ static ssize_t version_show(struct kobject *kobj, static struct kobj_attribute boot_params_version_attr = __ATTR_RO(version); static ssize_t boot_params_data_read(struct file *fp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { memcpy(buf, (void *)&boot_params + off, count); return count; } -static struct bin_attribute boot_params_data_attr = { +static const struct bin_attribute boot_params_data_attr = { .attr = { .name = "data", .mode = S_IRUGO, }, - .read = boot_params_data_read, + .read_new = boot_params_data_read, .size = sizeof(boot_params), }; @@ -49,14 +49,14 @@ static struct attribute *boot_params_version_attrs[] = { NULL, }; -static struct bin_attribute *boot_params_data_attrs[] = { +static const struct bin_attribute *const boot_params_data_attrs[] = { &boot_params_data_attr, NULL, }; static const struct attribute_group boot_params_attr_group = { .attrs = boot_params_version_attrs, - .bin_attrs = boot_params_data_attrs, + .bin_attrs_new = boot_params_data_attrs, }; static int kobj_to_setup_data_nr(struct kobject *kobj, int *nr) @@ -172,7 +172,7 @@ static ssize_t type_show(struct kobject *kobj, static ssize_t setup_data_data_read(struct file *fp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -250,7 +250,7 @@ static struct bin_attribute data_attr __ro_after_init = { .name = "data", .mode = S_IRUGO, }, - .read = setup_data_data_read, + .read_new = setup_data_data_read, }; static struct attribute *setup_data_type_attrs[] = { @@ -258,14 +258,14 @@ static struct attribute *setup_data_type_attrs[] = { NULL, }; -static struct bin_attribute *setup_data_data_attrs[] = { +static const struct bin_attribute *const setup_data_data_attrs[] = { &data_attr, NULL, }; static const struct attribute_group setup_data_attr_group = { .attrs = setup_data_type_attrs, - .bin_attrs = setup_data_data_attrs, + .bin_attrs_new = setup_data_data_attrs, }; static int __init create_setup_data_node(struct kobject *parent, diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 21e9e4845354..7a422a6c5983 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -983,7 +983,7 @@ static void __init kvm_init_platform(void) x86_platform.apic_post_init = kvm_apic_init; /* Set WB as the default cache mode for SEV-SNP and TDX */ - mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); + guest_force_mtrr_state(NULL, 0, MTRR_TYPE_WRBACK); } #if defined(CONFIG_AMD_MEM_ENCRYPT) diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 1b373d79cedc..80265162aeff 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -160,15 +160,10 @@ void machine_kexec_cleanup(struct kimage *image) */ void machine_kexec(struct kimage *image) { + relocate_kernel_fn *relocate_kernel_ptr; unsigned long page_list[PAGES_NR]; void *control_page; int save_ftrace_enabled; - asmlinkage unsigned long - (*relocate_kernel_ptr)(unsigned long indirection_page, - unsigned long control_page, - unsigned long start_address, - unsigned int has_pae, - unsigned int preserve_context); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 9c9ac606893e..a68f5a0a9f37 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -146,7 +146,8 @@ static void free_transition_pgtable(struct kimage *image) image->arch.pte = NULL; } -static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) +static int init_transition_pgtable(struct kimage *image, pgd_t *pgd, + unsigned long control_page) { pgprot_t prot = PAGE_KERNEL_EXEC_NOENC; unsigned long vaddr, paddr; @@ -156,8 +157,13 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) pmd_t *pmd; pte_t *pte; - vaddr = (unsigned long)relocate_kernel; - paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE); + /* + * For the transition to the identity mapped page tables, the control + * code page also needs to be mapped at the virtual address it starts + * off running from. + */ + vaddr = (unsigned long)__va(control_page); + paddr = control_page; pgd += pgd_index(vaddr); if (!pgd_present(*pgd)) { p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); @@ -216,7 +222,7 @@ static void *alloc_pgt_page(void *data) return p; } -static int init_pgtable(struct kimage *image, unsigned long start_pgtable) +static int init_pgtable(struct kimage *image, unsigned long control_page) { struct x86_mapping_info info = { .alloc_pgt_page = alloc_pgt_page, @@ -225,12 +231,12 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) .kernpg_flag = _KERNPG_TABLE_NOENC, }; unsigned long mstart, mend; - pgd_t *level4p; int result; int i; - level4p = (pgd_t *)__va(start_pgtable); - clear_page(level4p); + image->arch.pgd = alloc_pgt_page(image); + if (!image->arch.pgd) + return -ENOMEM; if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { info.page_flag |= _PAGE_ENC; @@ -244,8 +250,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) mstart = pfn_mapped[i].start << PAGE_SHIFT; mend = pfn_mapped[i].end << PAGE_SHIFT; - result = kernel_ident_mapping_init(&info, - level4p, mstart, mend); + result = kernel_ident_mapping_init(&info, image->arch.pgd, + mstart, mend); if (result) return result; } @@ -260,8 +266,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz; - result = kernel_ident_mapping_init(&info, - level4p, mstart, mend); + result = kernel_ident_mapping_init(&info, image->arch.pgd, + mstart, mend); if (result) return result; @@ -271,15 +277,19 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) * Prepare EFI systab and ACPI tables for kexec kernel since they are * not covered by pfn_mapped. */ - result = map_efi_systab(&info, level4p); + result = map_efi_systab(&info, image->arch.pgd); if (result) return result; - result = map_acpi_tables(&info, level4p); + result = map_acpi_tables(&info, image->arch.pgd); if (result) return result; - return init_transition_pgtable(image, level4p); + /* + * This must be last because the intermediate page table pages it + * allocates will not be control pages and may overlap the image. + */ + return init_transition_pgtable(image, image->arch.pgd, control_page); } static void load_segments(void) @@ -296,22 +306,35 @@ static void load_segments(void) int machine_kexec_prepare(struct kimage *image) { - unsigned long start_pgtable; + void *control_page = page_address(image->control_code_page); + unsigned long reloc_start = (unsigned long)__relocate_kernel_start; + unsigned long reloc_end = (unsigned long)__relocate_kernel_end; int result; - /* Calculate the offsets */ - start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT; - /* Setup the identity mapped 64bit page table */ - result = init_pgtable(image, start_pgtable); + result = init_pgtable(image, __pa(control_page)); if (result) return result; + kexec_va_control_page = (unsigned long)control_page; + kexec_pa_table_page = (unsigned long)__pa(image->arch.pgd); + + if (image->type == KEXEC_TYPE_DEFAULT) + kexec_pa_swap_page = page_to_pfn(image->swap_page) << PAGE_SHIFT; + + __memcpy(control_page, __relocate_kernel_start, reloc_end - reloc_start); + + set_memory_rox((unsigned long)control_page, 1); return 0; } void machine_kexec_cleanup(struct kimage *image) { + void *control_page = page_address(image->control_code_page); + + set_memory_nx((unsigned long)control_page, 1); + set_memory_rw((unsigned long)control_page, 1); + free_transition_pgtable(image); } @@ -319,9 +342,10 @@ void machine_kexec_cleanup(struct kimage *image) * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -void machine_kexec(struct kimage *image) +void __nocfi machine_kexec(struct kimage *image) { - unsigned long page_list[PAGES_NR]; + unsigned long reloc_start = (unsigned long)__relocate_kernel_start; + relocate_kernel_fn *relocate_kernel_ptr; unsigned int host_mem_enc_active; int save_ftrace_enabled; void *control_page; @@ -357,17 +381,13 @@ void machine_kexec(struct kimage *image) #endif } - control_page = page_address(image->control_code_page) + PAGE_SIZE; - __memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE); + control_page = page_address(image->control_code_page); - page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page); - page_list[VA_CONTROL_PAGE] = (unsigned long)control_page; - page_list[PA_TABLE_PAGE] = - (unsigned long)__pa(page_address(image->control_code_page)); - - if (image->type == KEXEC_TYPE_DEFAULT) - page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) - << PAGE_SHIFT); + /* + * Allow for the possibility that relocate_kernel might not be at + * the very start of the page. + */ + relocate_kernel_ptr = control_page + (unsigned long)relocate_kernel - reloc_start; /* * The segment registers are funny things, they have both a @@ -388,11 +408,11 @@ void machine_kexec(struct kimage *image) native_gdt_invalidate(); /* now call it */ - image->start = relocate_kernel((unsigned long)image->head, - (unsigned long)page_list, - image->start, - image->preserve_context, - host_mem_enc_active); + image->start = relocate_kernel_ptr((unsigned long)image->head, + virt_to_phys(control_page), + image->start, + image->preserve_context, + host_mem_enc_active); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -573,8 +593,7 @@ static void kexec_mark_crashkres(bool protect) /* Don't touch the control code page used in crash_kexec().*/ control = PFN_PHYS(page_to_pfn(kexec_crash_image->control_code_page)); - /* Control code page is located in the 2nd page. */ - kexec_mark_range(crashk_res.start, control + PAGE_SIZE - 1, protect); + kexec_mark_range(crashk_res.start, control - 1, protect); control += KEXEC_CONTROL_PAGE_SIZE; kexec_mark_range(control, crashk_res.end, protect); } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index fec381533555..1ccaa3397a67 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -59,10 +59,20 @@ void __init native_pv_lock_init(void) static_branch_enable(&virt_spin_lock_key); } +#ifndef CONFIG_PT_RECLAIM static void native_tlb_remove_table(struct mmu_gather *tlb, void *table) { - tlb_remove_page(tlb, table); + struct ptdesc *ptdesc = (struct ptdesc *)table; + + pagetable_dtor(ptdesc); + tlb_remove_page(tlb, ptdesc_page(ptdesc)); } +#else +static void native_tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + tlb_remove_table(tlb, table); +} +#endif struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; @@ -116,11 +126,6 @@ static noinstr void pv_native_set_debugreg(int regno, unsigned long val) native_set_debugreg(regno, val); } -noinstr void pv_native_wbinvd(void) -{ - native_wbinvd(); -} - static noinstr void pv_native_safe_halt(void) { native_safe_halt(); @@ -148,7 +153,6 @@ struct paravirt_patch_template pv_ops = { .cpu.read_cr0 = native_read_cr0, .cpu.write_cr0 = native_write_cr0, .cpu.write_cr4 = native_write_cr4, - .cpu.wbinvd = pv_native_wbinvd, .cpu.read_msr = native_read_msr, .cpu.write_msr = native_write_msr, .cpu.read_msr_safe = native_read_msr_safe, diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index f323d83e40a7..6267363e0189 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -108,10 +108,6 @@ void __init pci_iommu_alloc(void) swiotlb_init(x86_swiotlb_enable, x86_swiotlb_flags); } -/* - * See for the iommu kernel - * parameter documentation. - */ static __init int iommu_setup(char *p) { iommu_merge = 1; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f63f8fd00a91..6da6769d7254 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -825,7 +826,7 @@ void __noreturn stop_this_cpu(void *dummy) * X86_FEATURE_SME due to cmdline options. */ if (c->extended_cpuid_level >= 0x8000001f && (cpuid_eax(0x8000001f) & BIT(0))) - native_wbinvd(); + wbinvd(); /* * This brings a cache line back and dirties it, but @@ -838,7 +839,7 @@ void __noreturn stop_this_cpu(void *dummy) #ifdef CONFIG_SMP if (smp_ops.stop_this_cpu) { smp_ops.stop_this_cpu(); - unreachable(); + BUG(); } #endif @@ -846,7 +847,7 @@ void __noreturn stop_this_cpu(void *dummy) /* * Use native_halt() so that memory contents don't change * (stack usage and variables) after possibly issuing the - * native_wbinvd() above. + * wbinvd() above. */ native_halt(); } @@ -877,7 +878,7 @@ static __init bool prefer_mwait_c1_over_halt(void) if (boot_cpu_has_bug(X86_BUG_MONITOR) || boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) return false; - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &edx); /* * If MWAIT extensions are not available, it is safe to use MWAIT diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 615922838c51..dc1dd3f3e67f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -883,7 +883,7 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) if (smp_ops.stop_this_cpu) { smp_ops.stop_this_cpu(); - unreachable(); + BUG(); } /* Assume hlt works */ diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 540443d699e3..b44d8863e57f 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -24,33 +24,30 @@ #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) /* - * control_page + KEXEC_CONTROL_CODE_MAX_SIZE - * ~ control_page + PAGE_SIZE are used as data storage and stack for - * jumping back + * The .text..relocate_kernel and .data..relocate_kernel sections are copied + * into the control page, and the remainder of the page is used as the stack. */ -#define DATA(offset) (KEXEC_CONTROL_CODE_MAX_SIZE+(offset)) + .section .data..relocate_kernel,"a"; /* Minimal CPU state */ -#define RSP DATA(0x0) -#define CR0 DATA(0x8) -#define CR3 DATA(0x10) -#define CR4 DATA(0x18) +SYM_DATA_LOCAL(saved_rsp, .quad 0) +SYM_DATA_LOCAL(saved_cr0, .quad 0) +SYM_DATA_LOCAL(saved_cr3, .quad 0) +SYM_DATA_LOCAL(saved_cr4, .quad 0) + /* other data */ +SYM_DATA(kexec_va_control_page, .quad 0) +SYM_DATA(kexec_pa_table_page, .quad 0) +SYM_DATA(kexec_pa_swap_page, .quad 0) +SYM_DATA_LOCAL(pa_backup_pages_map, .quad 0) -/* other data */ -#define CP_PA_TABLE_PAGE DATA(0x20) -#define CP_PA_SWAP_PAGE DATA(0x28) -#define CP_PA_BACKUP_PAGES_MAP DATA(0x30) - - .text - .align PAGE_SIZE + .section .text..relocate_kernel,"ax"; .code64 -SYM_CODE_START_NOALIGN(relocate_range) SYM_CODE_START_NOALIGN(relocate_kernel) UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR /* * %rdi indirection_page - * %rsi page_list + * %rsi pa_control_page * %rdx start address * %rcx preserve_context * %r8 host_mem_enc_active @@ -65,60 +62,57 @@ SYM_CODE_START_NOALIGN(relocate_kernel) pushq %r15 pushf - movq PTR(VA_CONTROL_PAGE)(%rsi), %r11 - movq %rsp, RSP(%r11) - movq %cr0, %rax - movq %rax, CR0(%r11) - movq %cr3, %rax - movq %rax, CR3(%r11) - movq %cr4, %rax - movq %rax, CR4(%r11) - - /* Save CR4. Required to enable the right paging mode later. */ - movq %rax, %r13 - /* zero out flags, and disable interrupts */ pushq $0 popfq - /* Save SME active flag */ - movq %r8, %r12 - - /* - * get physical address of control page now - * this is impossible after page table switch - */ - movq PTR(PA_CONTROL_PAGE)(%rsi), %r8 - - /* get physical address of page table now too */ - movq PTR(PA_TABLE_PAGE)(%rsi), %r9 - - /* get physical address of swap page now */ - movq PTR(PA_SWAP_PAGE)(%rsi), %r10 - - /* save some information for jumping back */ - movq %r9, CP_PA_TABLE_PAGE(%r11) - movq %r10, CP_PA_SWAP_PAGE(%r11) - movq %rdi, CP_PA_BACKUP_PAGES_MAP(%r11) - /* Switch to the identity mapped page tables */ + movq %cr3, %rax + movq kexec_pa_table_page(%rip), %r9 movq %r9, %cr3 + /* Leave CR4 in %r13 to enable the right paging mode later. */ + movq %cr4, %r13 + + /* Disable global pages immediately to ensure this mapping is RWX */ + movq %r13, %r12 + andq $~(X86_CR4_PGE), %r12 + movq %r12, %cr4 + + /* Save %rsp and CRs. */ + movq %r13, saved_cr4(%rip) + movq %rsp, saved_rsp(%rip) + movq %rax, saved_cr3(%rip) + movq %cr0, %rax + movq %rax, saved_cr0(%rip) + + /* save indirection list for jumping back */ + movq %rdi, pa_backup_pages_map(%rip) + + /* Save the preserve_context to %r11 as swap_pages clobbers %rcx. */ + movq %rcx, %r11 + /* setup a new stack at the end of the physical control page */ - lea PAGE_SIZE(%r8), %rsp + lea PAGE_SIZE(%rsi), %rsp /* jump to identity mapped page */ - addq $(identity_mapped - relocate_kernel), %r8 - pushq %r8 - ANNOTATE_UNRET_SAFE - ret - int3 +0: addq $identity_mapped - 0b, %rsi + subq $__relocate_kernel_start - 0b, %rsi + ANNOTATE_RETPOLINE_SAFE + jmp *%rsi SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) UNWIND_HINT_END_OF_STACK - /* set return address to 0 if not preserving context */ - pushq $0 + /* + * %rdi indirection page + * %rdx start address + * %r8 host_mem_enc_active + * %r9 page table page + * %r11 preserve_context + * %r13 original CR4 when relocate_kernel() was invoked + */ + /* store the start address on the stack */ pushq %rdx @@ -166,13 +160,11 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) * entries that will conflict with the now unencrypted memory * used by kexec. Flush the caches before copying the kernel. */ - testq %r12, %r12 + testq %r8, %r8 jz .Lsme_off wbinvd .Lsme_off: - /* Save the preserve_context to %r11 as swap_pages clobbers %rcx. */ - movq %rcx, %r11 call swap_pages /* @@ -184,13 +176,14 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) movq %cr3, %rax movq %rax, %cr3 + testq %r11, %r11 /* preserve_context */ + jnz .Lrelocate + /* * set all of the registers to known values * leave %rsp alone */ - testq %r11, %r11 - jnz .Lrelocate xorl %eax, %eax xorl %ebx, %ebx xorl %ecx, %ecx @@ -213,20 +206,34 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) .Lrelocate: popq %rdx + + /* Use the swap page for the callee's stack */ + movq kexec_pa_swap_page(%rip), %r10 leaq PAGE_SIZE(%r10), %rsp + + /* push the existing entry point onto the callee's stack */ + pushq %rdx + ANNOTATE_RETPOLINE_SAFE call *%rdx /* get the re-entry point of the peer system */ - movq 0(%rsp), %rbp - leaq relocate_kernel(%rip), %r8 - movq CP_PA_SWAP_PAGE(%r8), %r10 - movq CP_PA_BACKUP_PAGES_MAP(%r8), %rdi - movq CP_PA_TABLE_PAGE(%r8), %rax + popq %rbp + movq kexec_pa_swap_page(%rip), %r10 + movq pa_backup_pages_map(%rip), %rdi + movq kexec_pa_table_page(%rip), %rax movq %rax, %cr3 + + /* Find start (and end) of this physical mapping of control page */ + leaq (%rip), %r8 + ANNOTATE_NOENDBR + andq $PAGE_MASK, %r8 lea PAGE_SIZE(%r8), %rsp + movl $1, %r11d /* Ensure preserve_context flag is set */ call swap_pages - movq $virtual_mapped, %rax + movq kexec_va_control_page(%rip), %rax +0: addq $virtual_mapped - 0b, %rax + subq $__relocate_kernel_start - 0b, %rax pushq %rax ANNOTATE_UNRET_SAFE ret @@ -236,11 +243,11 @@ SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR // RET target, above - movq RSP(%r8), %rsp - movq CR4(%r8), %rax + movq saved_rsp(%rip), %rsp + movq saved_cr4(%rip), %rax movq %rax, %cr4 - movq CR3(%r8), %rax - movq CR0(%r8), %r8 + movq saved_cr3(%rip), %rax + movq saved_cr0(%rip), %r8 movq %rax, %cr3 movq %r8, %cr0 @@ -250,6 +257,7 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) lgdt saved_context_gdt_desc(%rax) #endif + /* relocate_kernel() returns the re-entry point for next time */ movq %rbp, %rax popf @@ -267,42 +275,49 @@ SYM_CODE_END(virtual_mapped) /* Do the copies */ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) UNWIND_HINT_END_OF_STACK + /* + * %rdi indirection page + * %r11 preserve_context + */ movq %rdi, %rcx /* Put the indirection_page in %rcx */ xorl %edi, %edi xorl %esi, %esi - jmp 1f + jmp .Lstart /* Should start with an indirection record */ -0: /* top, read another word for the indirection page */ +.Lloop: /* top, read another word for the indirection page */ movq (%rbx), %rcx addq $8, %rbx -1: +.Lstart: testb $0x1, %cl /* is it a destination page? */ - jz 2f + jz .Lnotdest movq %rcx, %rdi andq $0xfffffffffffff000, %rdi - jmp 0b -2: + jmp .Lloop +.Lnotdest: testb $0x2, %cl /* is it an indirection page? */ - jz 2f + jz .Lnotind movq %rcx, %rbx andq $0xfffffffffffff000, %rbx - jmp 0b -2: + jmp .Lloop +.Lnotind: testb $0x4, %cl /* is it the done indicator? */ - jz 2f - jmp 3f -2: + jz .Lnotdone + jmp .Ldone +.Lnotdone: testb $0x8, %cl /* is it the source indicator? */ - jz 0b /* Ignore it otherwise */ + jz .Lloop /* Ignore it otherwise */ movq %rcx, %rsi /* For ever source page do a copy */ andq $0xfffffffffffff000, %rsi movq %rdi, %rdx /* Save destination page to %rdx */ movq %rsi, %rax /* Save source page to %rax */ + testq %r11, %r11 /* Only actually swap for ::preserve_context */ + jz .Lnoswap + /* copy source page to swap page */ - movq %r10, %rdi + movq kexec_pa_swap_page(%rip), %rdi movl $512, %ecx rep ; movsq @@ -314,17 +329,15 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) /* copy swap page to destination page */ movq %rdx, %rdi - movq %r10, %rsi + movq kexec_pa_swap_page(%rip), %rsi +.Lnoswap: movl $512, %ecx rep ; movsq lea PAGE_SIZE(%rax), %rsi - jmp 0b -3: + jmp .Lloop +.Ldone: ANNOTATE_UNRET_SAFE ret int3 SYM_CODE_END(swap_pages) - - .skip KEXEC_CONTROL_CODE_MAX_SIZE - (. - relocate_kernel), 0xcc -SYM_CODE_END(relocate_range); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f1fea506e20f..cebee310e200 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -259,6 +259,7 @@ static void __init relocate_initrd(void) u64 ramdisk_image = get_ramdisk_image(); u64 ramdisk_size = get_ramdisk_size(); u64 area_size = PAGE_ALIGN(ramdisk_size); + int ret = 0; /* We need to move the initrd down into directly mapped mem */ u64 relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0, @@ -272,7 +273,9 @@ static void __init relocate_initrd(void) printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n", relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1); - copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size); + ret = copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size); + if (ret) + panic("Copy RAMDISK failed\n"); printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to" " [mem %#010llx-%#010llx]\n", diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index b5a8f0891135..c10850ae6f09 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -64,6 +64,7 @@ #include #include +#include #include #include #include @@ -482,12 +483,6 @@ static int x86_core_flags(void) return cpu_core_flags() | x86_sched_itmt_flags(); } #endif -#ifdef CONFIG_SCHED_SMT -static int x86_smt_flags(void) -{ - return cpu_smt_flags(); -} -#endif #ifdef CONFIG_SCHED_CLUSTER static int x86_cluster_flags(void) { @@ -495,15 +490,6 @@ static int x86_cluster_flags(void) } #endif -static int x86_die_flags(void) -{ - if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU) || - cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) - return x86_sched_itmt_flags(); - - return 0; -} - /* * Set if a package/die has multiple NUMA nodes inside. * AMD Magny-Cours, Intel Cluster-on-Die, and Intel @@ -519,7 +505,7 @@ static void __init build_sched_topology(void) #ifdef CONFIG_SCHED_SMT x86_topology[i++] = (struct sched_domain_topology_level){ - cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) + cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }; #endif #ifdef CONFIG_SCHED_CLUSTER @@ -539,7 +525,7 @@ static void __init build_sched_topology(void) */ if (!x86_has_numa_in_package) { x86_topology[i++] = (struct sched_domain_topology_level){ - cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(PKG) + cpu_cpu_mask, x86_sched_itmt_flags, SD_INIT_NAME(PKG) }; } @@ -1291,10 +1277,8 @@ static inline void mwait_play_dead(void) return; if (!this_cpu_has(X86_FEATURE_CLFLUSH)) return; - if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF) - return; - eax = CPUID_MWAIT_LEAF; + eax = CPUID_LEAF_MWAIT; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 4eefaac64c6c..9e51242ed125 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,6 +172,14 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); +noinstr void __static_call_update_early(void *tramp, void *func) +{ + BUG_ON(system_state != SYSTEM_BOOTING); + BUG_ON(static_call_initialized); + __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE); + sync_core(); +} + #ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 67aeaba4ba9c..34dec0b72ea8 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -16,6 +16,7 @@ #include #include +#include #include #include #include @@ -30,6 +31,7 @@ #include #include #include +#include unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -665,13 +667,13 @@ unsigned long native_calibrate_tsc(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; - if (boot_cpu_data.cpuid_level < 0x15) + if (boot_cpu_data.cpuid_level < CPUID_LEAF_TSC) return 0; eax_denominator = ebx_numerator = ecx_hz = edx = 0; /* CPUID 15H TSC/Crystal ratio, plus optionally Crystal Hz */ - cpuid(0x15, &eax_denominator, &ebx_numerator, &ecx_hz, &edx); + cpuid(CPUID_LEAF_TSC, &eax_denominator, &ebx_numerator, &ecx_hz, &edx); if (ebx_numerator == 0 || eax_denominator == 0) return 0; @@ -680,8 +682,8 @@ unsigned long native_calibrate_tsc(void) /* * Denverton SoCs don't report crystal clock, and also don't support - * CPUID.0x16 for the calculation below, so hardcode the 25MHz crystal - * clock. + * CPUID_LEAF_FREQ for the calculation below, so hardcode the 25MHz + * crystal clock. */ if (crystal_khz == 0 && boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT_D) @@ -700,10 +702,10 @@ unsigned long native_calibrate_tsc(void) * clock, but we can easily calculate it to a high degree of accuracy * by considering the crystal ratio and the CPU speed. */ - if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= 0x16) { + if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= CPUID_LEAF_FREQ) { unsigned int eax_base_mhz, ebx, ecx, edx; - cpuid(0x16, &eax_base_mhz, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_FREQ, &eax_base_mhz, &ebx, &ecx, &edx); crystal_khz = eax_base_mhz * 1000 * eax_denominator / ebx_numerator; } @@ -738,12 +740,12 @@ static unsigned long cpu_khz_from_cpuid(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; - if (boot_cpu_data.cpuid_level < 0x16) + if (boot_cpu_data.cpuid_level < CPUID_LEAF_FREQ) return 0; eax_base_mhz = ebx_max_mhz = ecx_bus_mhz = edx = 0; - cpuid(0x16, &eax_base_mhz, &ebx_max_mhz, &ecx_bus_mhz, &edx); + cpuid(CPUID_LEAF_FREQ, &eax_base_mhz, &ebx_max_mhz, &ecx_bus_mhz, &edx); return eax_base_mhz * 1000; } @@ -1067,10 +1069,8 @@ core_initcall(cpufreq_register_tsc_scaling); #endif /* CONFIG_CPU_FREQ */ -#define ART_CPUID_LEAF (0x15) #define ART_MIN_DENOMINATOR (1) - /* * If ART is present detect the numerator:denominator to convert to TSC */ @@ -1078,7 +1078,7 @@ static void __init detect_art(void) { unsigned int unused; - if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) + if (boot_cpu_data.cpuid_level < CPUID_LEAF_TSC) return; /* @@ -1091,7 +1091,7 @@ static void __init detect_art(void) tsc_async_resets) return; - cpuid(ART_CPUID_LEAF, &art_base_clk.denominator, + cpuid(CPUID_LEAF_TSC, &art_base_clk.denominator, &art_base_clk.numerator, &art_base_clk.freq_khz, &unused); art_base_clk.freq_khz /= KHZ; @@ -1515,6 +1515,9 @@ void __init tsc_early_init(void) /* Don't change UV TSC multi-chassis synchronization */ if (is_early_uv_system()) return; + + snp_secure_tsc_init(); + if (!determine_cpu_tsc_frequencies(true)) return; tsc_enable_sched_clock(); diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index e9e803a4d44c..e6cc84143f3e 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -246,9 +246,8 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) /* VM86_SCREEN_BITMAP had numerous bugs and appears to have no users. */ if (v.flags & VM86_SCREEN_BITMAP) { - char comm[TASK_COMM_LEN]; - - pr_info_once("vm86: '%s' uses VM86_SCREEN_BITMAP, which is no longer supported\n", get_task_comm(comm, current)); + pr_info_once("vm86: '%s' uses VM86_SCREEN_BITMAP, which is no longer supported\n", + current->comm); return -EINVAL; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index fab3ac9a4574..0deb4887d6e9 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -28,6 +28,7 @@ #include #include #include +#include #undef i386 /* in case the preprocessor is a 32bit one */ @@ -95,7 +96,19 @@ const_pcpu_hot = pcpu_hot; #define BSS_DECRYPTED #endif +#if defined(CONFIG_X86_64) && defined(CONFIG_KEXEC_CORE) +#define KEXEC_RELOCATE_KERNEL \ + . = ALIGN(0x100); \ + __relocate_kernel_start = .; \ + *(.text..relocate_kernel); \ + *(.data..relocate_kernel); \ + __relocate_kernel_end = .; +ASSERT(__relocate_kernel_end - __relocate_kernel_start <= KEXEC_CONTROL_CODE_MAX_SIZE, + "relocate_kernel code too large!") +#else +#define KEXEC_RELOCATE_KERNEL +#endif PHDRS { text PT_LOAD FLAGS(5); /* R_E */ data PT_LOAD FLAGS(6); /* RW_ */ @@ -121,19 +134,6 @@ SECTIONS .text : AT(ADDR(.text) - LOAD_OFFSET) { _text = .; _stext = .; - /* bootstrapping code */ - HEAD_TEXT - TEXT_TEXT - SCHED_TEXT - LOCK_TEXT - KPROBES_TEXT - SOFTIRQENTRY_TEXT -#ifdef CONFIG_MITIGATION_RETPOLINE - *(.text..__x86.indirect_thunk) - *(.text..__x86.return_thunk) -#endif - STATIC_CALL_TEXT - ALIGN_ENTRY_TEXT_BEGIN *(.text..__x86.rethunk_untrain) ENTRY_TEXT @@ -147,10 +147,26 @@ SECTIONS *(.text..__x86.rethunk_safe) #endif ALIGN_ENTRY_TEXT_END + + TEXT_TEXT + SCHED_TEXT + LOCK_TEXT + KPROBES_TEXT + SOFTIRQENTRY_TEXT +#ifdef CONFIG_MITIGATION_RETPOLINE + *(.text..__x86.indirect_thunk) + *(.text..__x86.return_thunk) +#endif + STATIC_CALL_TEXT *(.gnu.warning) } :text = 0xcccccccc + /* bootstrapping code */ + .head.text : AT(ADDR(.head.text) - LOAD_OFFSET) { + HEAD_TEXT + } :text = 0xcccccccc + /* End of text section, which should occupy whole number of pages */ _etext = .; . = ALIGN(PAGE_SIZE); @@ -181,6 +197,7 @@ SECTIONS DATA_DATA CONSTRUCTORS + KEXEC_RELOCATE_KERNEL /* rarely changed data like cpu maps */ READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES) @@ -519,14 +536,10 @@ INIT_PER_CPU(irq_stack_backing_store); * linker will never mark as relocatable. (Using just ABSOLUTE() is not * sufficient for that). */ -#ifdef CONFIG_XEN #ifdef CONFIG_XEN_PV xen_elfnote_entry_value = ABSOLUTE(xen_elfnote_entry) + ABSOLUTE(startup_xen); #endif -xen_elfnote_hypercall_page_value = - ABSOLUTE(xen_elfnote_hypercall_page) + ABSOLUTE(hypercall_page); -#endif #ifdef CONFIG_PVH xen_elfnote_phys32_entry_value = ABSOLUTE(xen_elfnote_phys32_entry) + ABSOLUTE(pvh_start_xen - LOAD_OFFSET); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index ae0b438a2c99..2cbb3874ad39 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -82,15 +82,6 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) return ret; } -#define F feature_bit - -/* Scattered Flag - For features that are scattered by cpufeatures.h. */ -#define SF(name) \ -({ \ - BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ - (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0); \ -}) - /* * Magic value used by KVM when querying userspace-provided CPUID entries and * doesn't care about the CPIUD index because the index of the function in @@ -100,8 +91,8 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) */ #define KVM_CPUID_INDEX_NOT_SIGNIFICANT -1ull -static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( - struct kvm_cpuid_entry2 *entries, int nent, u32 function, u64 index) +static struct kvm_cpuid_entry2 *cpuid_entry2_find(struct kvm_vcpu *vcpu, + u32 function, u64 index) { struct kvm_cpuid_entry2 *e; int i; @@ -118,8 +109,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( */ lockdep_assert_irqs_enabled(); - for (i = 0; i < nent; i++) { - e = &entries[i]; + for (i = 0; i < vcpu->arch.cpuid_nent; i++) { + e = &vcpu->arch.cpuid_entries[i]; if (e->function != function) continue; @@ -151,9 +142,27 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( return NULL; } -static int kvm_check_cpuid(struct kvm_vcpu *vcpu, - struct kvm_cpuid_entry2 *entries, - int nent) +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, + u32 function, u32 index) +{ + return cpuid_entry2_find(vcpu, function, index); +} +EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry_index); + +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function) +{ + return cpuid_entry2_find(vcpu, function, KVM_CPUID_INDEX_NOT_SIGNIFICANT); +} +EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); + +/* + * cpuid_entry2_find() and KVM_CPUID_INDEX_NOT_SIGNIFICANT should never be used + * directly outside of kvm_find_cpuid_entry() and kvm_find_cpuid_entry_index(). + */ +#undef KVM_CPUID_INDEX_NOT_SIGNIFICANT + +static int kvm_check_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; u64 xfeatures; @@ -162,8 +171,7 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu, * The existing code assumes virtual address is 48-bit or 57-bit in the * canonical address checks; exit if it is ever changed. */ - best = cpuid_entry2_find(entries, nent, 0x80000008, - KVM_CPUID_INDEX_NOT_SIGNIFICANT); + best = kvm_find_cpuid_entry(vcpu, 0x80000008); if (best) { int vaddr_bits = (best->eax & 0xff00) >> 8; @@ -175,7 +183,7 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu, * Exposing dynamic xfeatures to the guest requires additional * enabling in the FPU, e.g. to expand the guest XSAVE state size. */ - best = cpuid_entry2_find(entries, nent, 0xd, 0); + best = kvm_find_cpuid_entry_index(vcpu, 0xd, 0); if (!best) return 0; @@ -187,6 +195,8 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu, return fpu_enable_guest_xfd_features(&vcpu->arch.guest_fpu, xfeatures); } +static u32 kvm_apply_cpuid_pv_features_quirk(struct kvm_vcpu *vcpu); + /* Check whether the supplied CPUID data is equal to what is already set for the vCPU. */ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, int nent) @@ -194,6 +204,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 struct kvm_cpuid_entry2 *orig; int i; + /* + * Apply runtime CPUID updates to the incoming CPUID entries to avoid + * false positives due mismatches on KVM-owned feature flags. + * + * Note! @e2 and @nent track the _old_ CPUID entries! + */ + kvm_update_cpuid_runtime(vcpu); + kvm_apply_cpuid_pv_features_quirk(vcpu); + if (nent != vcpu->arch.cpuid_nent) return -EINVAL; @@ -210,15 +229,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 return 0; } -static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_entry2 *entries, - int nent, const char *sig) +static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, + const char *sig) { struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; u32 base; for_each_possible_hypervisor_cpuid_base(base) { - entry = cpuid_entry2_find(entries, nent, base, KVM_CPUID_INDEX_NOT_SIGNIFICANT); + entry = kvm_find_cpuid_entry(vcpu, base); if (entry) { u32 signature[3]; @@ -238,118 +257,90 @@ static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_e return cpuid; } -static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, - const char *sig) +static u32 kvm_apply_cpuid_pv_features_quirk(struct kvm_vcpu *vcpu) { - return __kvm_get_hypervisor_cpuid(vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent, sig); -} + struct kvm_hypervisor_cpuid kvm_cpuid; + struct kvm_cpuid_entry2 *best; -static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_cpuid_entry2 *entries, - int nent, u32 kvm_cpuid_base) -{ - return cpuid_entry2_find(entries, nent, kvm_cpuid_base | KVM_CPUID_FEATURES, - KVM_CPUID_INDEX_NOT_SIGNIFICANT); -} + kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); + if (!kvm_cpuid.base) + return 0; -static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) -{ - u32 base = vcpu->arch.kvm_cpuid.base; + best = kvm_find_cpuid_entry(vcpu, kvm_cpuid.base | KVM_CPUID_FEATURES); + if (!best) + return 0; - if (!base) - return NULL; + if (kvm_hlt_in_guest(vcpu->kvm)) + best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); - return __kvm_find_kvm_cpuid_features(vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent, base); -} - -void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best = kvm_find_kvm_cpuid_features(vcpu); - - /* - * save the feature bitmap to avoid cpuid lookup for every PV - * operation - */ - if (best) - vcpu->arch.pv_cpuid.features = best->eax; + return best->eax; } /* * Calculate guest's supported XCR0 taking into account guest CPUID data and * KVM's supported XCR0 (comprised of host's XCR0 and KVM_SUPPORTED_XCR0). */ -static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent) +static u64 cpuid_get_supported_xcr0(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - best = cpuid_entry2_find(entries, nent, 0xd, 0); + best = kvm_find_cpuid_entry_index(vcpu, 0xd, 0); if (!best) return 0; return (best->eax | ((u64)best->edx << 32)) & kvm_caps.supported_xcr0; } -static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, - int nent) +static __always_inline void kvm_update_feature_runtime(struct kvm_vcpu *vcpu, + struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature, + bool has_feature) { - struct kvm_cpuid_entry2 *best; - struct kvm_hypervisor_cpuid kvm_cpuid; - - best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); - if (best) { - /* Update OSXSAVE bit */ - if (boot_cpu_has(X86_FEATURE_XSAVE)) - cpuid_entry_change(best, X86_FEATURE_OSXSAVE, - kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)); - - cpuid_entry_change(best, X86_FEATURE_APIC, - vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE); - } - - best = cpuid_entry2_find(entries, nent, 7, 0); - if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7) - cpuid_entry_change(best, X86_FEATURE_OSPKE, - kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE)); - - best = cpuid_entry2_find(entries, nent, 0xD, 0); - if (best) - best->ebx = xstate_required_size(vcpu->arch.xcr0, false); - - best = cpuid_entry2_find(entries, nent, 0xD, 1); - if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) || - cpuid_entry_has(best, X86_FEATURE_XSAVEC))) - best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - - kvm_cpuid = __kvm_get_hypervisor_cpuid(entries, nent, KVM_SIGNATURE); - if (kvm_cpuid.base) { - best = __kvm_find_kvm_cpuid_features(entries, nent, kvm_cpuid.base); - if (kvm_hlt_in_guest(vcpu->kvm) && best) - best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); - } - - if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { - best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); - if (best) - cpuid_entry_change(best, X86_FEATURE_MWAIT, - vcpu->arch.ia32_misc_enable_msr & - MSR_IA32_MISC_ENABLE_MWAIT); - } + cpuid_entry_change(entry, x86_feature, has_feature); + guest_cpu_cap_change(vcpu, x86_feature, has_feature); } void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) { - __kvm_update_cpuid_runtime(vcpu, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1); + if (best) { + kvm_update_feature_runtime(vcpu, best, X86_FEATURE_OSXSAVE, + kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)); + + kvm_update_feature_runtime(vcpu, best, X86_FEATURE_APIC, + vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE); + + if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) + kvm_update_feature_runtime(vcpu, best, X86_FEATURE_MWAIT, + vcpu->arch.ia32_misc_enable_msr & + MSR_IA32_MISC_ENABLE_MWAIT); + } + + best = kvm_find_cpuid_entry_index(vcpu, 7, 0); + if (best) + kvm_update_feature_runtime(vcpu, best, X86_FEATURE_OSPKE, + kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE)); + + + best = kvm_find_cpuid_entry_index(vcpu, 0xD, 0); + if (best) + best->ebx = xstate_required_size(vcpu->arch.xcr0, false); + + best = kvm_find_cpuid_entry_index(vcpu, 0xD, 1); + if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) || + cpuid_entry_has(best, X86_FEATURE_XSAVEC))) + best->ebx = xstate_required_size(vcpu->arch.xcr0, true); } EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); -static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent) +static bool kvm_cpuid_has_hyperv(struct kvm_vcpu *vcpu) { #ifdef CONFIG_KVM_HYPERV struct kvm_cpuid_entry2 *entry; - entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE, - KVM_CPUID_INDEX_NOT_SIGNIFICANT); + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE); return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; #else return false; @@ -368,15 +359,71 @@ static bool guest_cpuid_is_amd_or_hygon(struct kvm_vcpu *vcpu) is_guest_vendor_hygon(entry->ebx, entry->ecx, entry->edx); } -static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) +/* + * This isn't truly "unsafe", but except for the cpu_caps initialization code, + * all register lookups should use __cpuid_entry_get_reg(), which provides + * compile-time validation of the input. + */ +static u32 cpuid_get_reg_unsafe(struct kvm_cpuid_entry2 *entry, u32 reg) +{ + switch (reg) { + case CPUID_EAX: + return entry->eax; + case CPUID_EBX: + return entry->ebx; + case CPUID_ECX: + return entry->ecx; + case CPUID_EDX: + return entry->edx; + default: + WARN_ON_ONCE(1); + return 0; + } +} + +static int cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, u32 func, + bool include_partially_emulated); + +void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; + struct kvm_cpuid_entry2 *entry; bool allow_gbpages; + int i; - BUILD_BUG_ON(KVM_NR_GOVERNED_FEATURES > KVM_MAX_NR_GOVERNED_FEATURES); - bitmap_zero(vcpu->arch.governed_features.enabled, - KVM_MAX_NR_GOVERNED_FEATURES); + memset(vcpu->arch.cpu_caps, 0, sizeof(vcpu->arch.cpu_caps)); + BUILD_BUG_ON(ARRAY_SIZE(reverse_cpuid) != NR_KVM_CPU_CAPS); + + /* + * Reset guest capabilities to userspace's guest CPUID definition, i.e. + * honor userspace's definition for features that don't require KVM or + * hardware management/support (or that KVM simply doesn't care about). + */ + for (i = 0; i < NR_KVM_CPU_CAPS; i++) { + const struct cpuid_reg cpuid = reverse_cpuid[i]; + struct kvm_cpuid_entry2 emulated; + + if (!cpuid.function) + continue; + + entry = kvm_find_cpuid_entry_index(vcpu, cpuid.function, cpuid.index); + if (!entry) + continue; + + cpuid_func_emulated(&emulated, cpuid.function, true); + + /* + * A vCPU has a feature if it's supported by KVM and is enabled + * in guest CPUID. Note, this includes features that are + * supported by KVM but aren't advertised to userspace! + */ + vcpu->arch.cpu_caps[i] = kvm_cpu_caps[i] | + cpuid_get_reg_unsafe(&emulated, cpuid.reg); + vcpu->arch.cpu_caps[i] &= cpuid_get_reg_unsafe(entry, cpuid.reg); + } + + kvm_update_cpuid_runtime(vcpu); /* * If TDP is enabled, let the guest use GBPAGES if they're supported in @@ -390,9 +437,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) * and can install smaller shadow pages if the host lacks 1GiB support. */ allow_gbpages = tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) : - guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES); - if (allow_gbpages) - kvm_governed_feature_set(vcpu, X86_FEATURE_GBPAGES); + guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES); + guest_cpu_cap_change(vcpu, X86_FEATURE_GBPAGES, allow_gbpages); best = kvm_find_cpuid_entry(vcpu, 1); if (best && apic) { @@ -404,21 +450,22 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - vcpu->arch.guest_supported_xcr0 = - cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); + vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu); - kvm_update_pv_runtime(vcpu); + vcpu->arch.pv_cpuid.features = kvm_apply_cpuid_pv_features_quirk(vcpu); vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); kvm_pmu_refresh(vcpu); - vcpu->arch.cr4_guest_rsvd_bits = - __cr4_reserved_bits(guest_cpuid_has, vcpu); - kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent)); +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_) | + __cr4_reserved_bits(guest_cpu_cap_has, vcpu); +#undef __kvm_cpu_cap_has + + kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu)); /* Invoke the vendor callback only after the above state is updated. */ kvm_x86_call(vcpu_after_set_cpuid)(vcpu); @@ -457,9 +504,25 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, int nent) { + u32 vcpu_caps[NR_KVM_CPU_CAPS]; int r; - __kvm_update_cpuid_runtime(vcpu, e2, nent); + /* + * Swap the existing (old) entries with the incoming (new) entries in + * order to massage the new entries, e.g. to account for dynamic bits + * that KVM controls, without clobbering the current guest CPUID, which + * KVM needs to preserve in order to unwind on failure. + * + * Similarly, save the vCPU's current cpu_caps so that the capabilities + * can be updated alongside the CPUID entries when performing runtime + * updates. Full initialization is done if and only if the vCPU hasn't + * run, i.e. only if userspace is potentially changing CPUID features. + */ + swap(vcpu->arch.cpuid_entries, e2); + swap(vcpu->arch.cpuid_nent, nent); + + memcpy(vcpu_caps, vcpu->arch.cpu_caps, sizeof(vcpu_caps)); + BUILD_BUG_ON(sizeof(vcpu_caps) != sizeof(vcpu->arch.cpu_caps)); /* * KVM does not correctly handle changing guest CPUID after KVM_RUN, as @@ -475,35 +538,36 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, if (kvm_vcpu_has_run(vcpu)) { r = kvm_cpuid_check_equal(vcpu, e2, nent); if (r) - return r; - - kvfree(e2); - return 0; + goto err; + goto success; } #ifdef CONFIG_KVM_HYPERV - if (kvm_cpuid_has_hyperv(e2, nent)) { + if (kvm_cpuid_has_hyperv(vcpu)) { r = kvm_hv_vcpu_init(vcpu); if (r) - return r; + goto err; } #endif - r = kvm_check_cpuid(vcpu, e2, nent); + r = kvm_check_cpuid(vcpu); if (r) - return r; + goto err; - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = nent; - - vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); #ifdef CONFIG_KVM_XEN vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); #endif kvm_vcpu_after_set_cpuid(vcpu); +success: + kvfree(e2); return 0; + +err: + memcpy(vcpu->arch.cpu_caps, vcpu_caps, sizeof(vcpu_caps)); + swap(vcpu->arch.cpuid_entries, e2); + swap(vcpu->arch.cpuid_nent, nent); + return r; } /* when an old userspace process fills a new kernel module */ @@ -590,107 +654,294 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, return 0; } -/* Mask kvm_cpu_caps for @leaf with the raw CPUID capabilities of this CPU. */ -static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf) +static __always_inline u32 raw_cpuid_get(struct cpuid_reg cpuid) { - const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32); struct kvm_cpuid_entry2 entry; + u32 base; - reverse_cpuid_check(leaf); + /* + * KVM only supports features defined by Intel (0x0), AMD (0x80000000), + * and Centaur (0xc0000000). WARN if a feature for new vendor base is + * defined, as this and other code would need to be updated. + */ + base = cpuid.function & 0xffff0000; + if (WARN_ON_ONCE(base && base != 0x80000000 && base != 0xc0000000)) + return 0; + + if (cpuid_eax(base) < cpuid.function) + return 0; cpuid_count(cpuid.function, cpuid.index, &entry.eax, &entry.ebx, &entry.ecx, &entry.edx); - kvm_cpu_caps[leaf] &= *__cpuid_entry_get_reg(&entry, cpuid.reg); + return *__cpuid_entry_get_reg(&entry, cpuid.reg); } -static __always_inline -void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask) -{ - /* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */ - BUILD_BUG_ON(leaf < NCAPINTS); +/* + * For kernel-defined leafs, mask KVM's supported feature set with the kernel's + * capabilities as well as raw CPUID. For KVM-defined leafs, consult only raw + * CPUID, as KVM is the one and only authority (in the kernel). + */ +#define kvm_cpu_cap_init(leaf, feature_initializers...) \ +do { \ + const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32); \ + const u32 __maybe_unused kvm_cpu_cap_init_in_progress = leaf; \ + const u32 *kernel_cpu_caps = boot_cpu_data.x86_capability; \ + u32 kvm_cpu_cap_passthrough = 0; \ + u32 kvm_cpu_cap_synthesized = 0; \ + u32 kvm_cpu_cap_emulated = 0; \ + u32 kvm_cpu_cap_features = 0; \ + \ + feature_initializers \ + \ + kvm_cpu_caps[leaf] = kvm_cpu_cap_features; \ + \ + if (leaf < NCAPINTS) \ + kvm_cpu_caps[leaf] &= kernel_cpu_caps[leaf]; \ + \ + kvm_cpu_caps[leaf] |= kvm_cpu_cap_passthrough; \ + kvm_cpu_caps[leaf] &= (raw_cpuid_get(cpuid) | \ + kvm_cpu_cap_synthesized); \ + kvm_cpu_caps[leaf] |= kvm_cpu_cap_emulated; \ +} while (0) - kvm_cpu_caps[leaf] = mask; +/* + * Assert that the feature bit being declared, e.g. via F(), is in the CPUID + * word that's being initialized. Exempt 0x8000_0001.EDX usage of 0x1.EDX + * features, as AMD duplicated many 0x1.EDX features into 0x8000_0001.EDX. + */ +#define KVM_VALIDATE_CPU_CAP_USAGE(name) \ +do { \ + u32 __leaf = __feature_leaf(X86_FEATURE_##name); \ + \ + BUILD_BUG_ON(__leaf != kvm_cpu_cap_init_in_progress); \ +} while (0) - __kvm_cpu_cap_mask(leaf); -} +#define F(name) \ +({ \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ + kvm_cpu_cap_features |= feature_bit(name); \ +}) -static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) -{ - /* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */ - BUILD_BUG_ON(leaf >= NCAPINTS); +/* Scattered Flag - For features that are scattered by cpufeatures.h. */ +#define SCATTERED_F(name) \ +({ \ + BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ + if (boot_cpu_has(X86_FEATURE_##name)) \ + F(name); \ +}) - kvm_cpu_caps[leaf] &= mask; +/* Features that KVM supports only on 64-bit kernels. */ +#define X86_64_F(name) \ +({ \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ + if (IS_ENABLED(CONFIG_X86_64)) \ + F(name); \ +}) - __kvm_cpu_cap_mask(leaf); -} +/* + * Emulated Feature - For features that KVM emulates in software irrespective + * of host CPU/kernel support. + */ +#define EMULATED_F(name) \ +({ \ + kvm_cpu_cap_emulated |= feature_bit(name); \ + F(name); \ +}) + +/* + * Synthesized Feature - For features that are synthesized into boot_cpu_data, + * i.e. may not be present in the raw CPUID, but can still be advertised to + * userspace. Primarily used for mitigation related feature flags. + */ +#define SYNTHESIZED_F(name) \ +({ \ + kvm_cpu_cap_synthesized |= feature_bit(name); \ + F(name); \ +}) + +/* + * Passthrough Feature - For features that KVM supports based purely on raw + * hardware CPUID, i.e. that KVM virtualizes even if the host kernel doesn't + * use the feature. Simply force set the feature in KVM's capabilities, raw + * CPUID support will be factored in by kvm_cpu_cap_mask(). + */ +#define PASSTHROUGH_F(name) \ +({ \ + kvm_cpu_cap_passthrough |= feature_bit(name); \ + F(name); \ +}) + +/* + * Aliased Features - For features in 0x8000_0001.EDX that are duplicates of + * identical 0x1.EDX features, and thus are aliased from 0x1 to 0x8000_0001. + */ +#define ALIASED_1_EDX_F(name) \ +({ \ + BUILD_BUG_ON(__feature_leaf(X86_FEATURE_##name) != CPUID_1_EDX); \ + BUILD_BUG_ON(kvm_cpu_cap_init_in_progress != CPUID_8000_0001_EDX); \ + kvm_cpu_cap_features |= feature_bit(name); \ +}) + +/* + * Vendor Features - For features that KVM supports, but are added in later + * because they require additional vendor enabling. + */ +#define VENDOR_F(name) \ +({ \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ +}) + +/* + * Runtime Features - For features that KVM dynamically sets/clears at runtime, + * e.g. when CR4 changes, but which are never advertised to userspace. + */ +#define RUNTIME_F(name) \ +({ \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ +}) + +/* + * Undefine the MSR bit macro to avoid token concatenation issues when + * processing X86_FEATURE_SPEC_CTRL_SSBD. + */ +#undef SPEC_CTRL_SSBD + +/* DS is defined by ptrace-abi.h on 32-bit builds. */ +#undef DS void kvm_set_cpu_caps(void) { -#ifdef CONFIG_X86_64 - unsigned int f_gbpages = F(GBPAGES); - unsigned int f_lm = F(LM); - unsigned int f_xfd = F(XFD); -#else - unsigned int f_gbpages = 0; - unsigned int f_lm = 0; - unsigned int f_xfd = 0; -#endif memset(kvm_cpu_caps, 0, sizeof(kvm_cpu_caps)); BUILD_BUG_ON(sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps)) > sizeof(boot_cpu_data.x86_capability)); - memcpy(&kvm_cpu_caps, &boot_cpu_data.x86_capability, - sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps))); - - kvm_cpu_cap_mask(CPUID_1_ECX, + kvm_cpu_cap_init(CPUID_1_ECX, + F(XMM3), + F(PCLMULQDQ), + VENDOR_F(DTES64), /* * NOTE: MONITOR (and MWAIT) are emulated as NOP, but *not* - * advertised to guests via CPUID! + * advertised to guests via CPUID! MWAIT is also technically a + * runtime flag thanks to IA32_MISC_ENABLES; mark it as such so + * that KVM is aware that it's a known, unadvertised flag. */ - F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | - 0 /* DS-CPL, VMX, SMX, EST */ | - 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | - F(FMA) | F(CX16) | 0 /* xTPR Update */ | F(PDCM) | - F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | - F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | - 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | - F(F16C) | F(RDRAND) - ); - /* KVM emulates x2apic in software irrespective of host support. */ - kvm_cpu_cap_set(X86_FEATURE_X2APIC); - - kvm_cpu_cap_mask(CPUID_1_EDX, - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) | - 0 /* Reserved, DS, ACPI */ | F(MMX) | - F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | - 0 /* HTT, TM, Reserved, PBE */ + RUNTIME_F(MWAIT), + /* DS-CPL */ + VENDOR_F(VMX), + /* SMX, EST */ + /* TM2 */ + F(SSSE3), + /* CNXT-ID */ + /* Reserved */ + F(FMA), + F(CX16), + /* xTPR Update */ + F(PDCM), + F(PCID), + /* Reserved, DCA */ + F(XMM4_1), + F(XMM4_2), + EMULATED_F(X2APIC), + F(MOVBE), + F(POPCNT), + EMULATED_F(TSC_DEADLINE_TIMER), + F(AES), + F(XSAVE), + RUNTIME_F(OSXSAVE), + F(AVX), + F(F16C), + F(RDRAND), + EMULATED_F(HYPERVISOR), ); - kvm_cpu_cap_mask(CPUID_7_0_EBX, - F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | - F(FDP_EXCPTN_ONLY) | F(SMEP) | F(BMI2) | F(ERMS) | F(INVPCID) | - F(RTM) | F(ZERO_FCS_FDS) | 0 /*MPX*/ | F(AVX512F) | - F(AVX512DQ) | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) | - F(CLFLUSHOPT) | F(CLWB) | 0 /*INTEL_PT*/ | F(AVX512PF) | - F(AVX512ER) | F(AVX512CD) | F(SHA_NI) | F(AVX512BW) | - F(AVX512VL)); + kvm_cpu_cap_init(CPUID_1_EDX, + F(FPU), + F(VME), + F(DE), + F(PSE), + F(TSC), + F(MSR), + F(PAE), + F(MCE), + F(CX8), + F(APIC), + /* Reserved */ + F(SEP), + F(MTRR), + F(PGE), + F(MCA), + F(CMOV), + F(PAT), + F(PSE36), + /* PSN */ + F(CLFLUSH), + /* Reserved */ + VENDOR_F(DS), + /* ACPI */ + F(MMX), + F(FXSR), + F(XMM), + F(XMM2), + F(SELFSNOOP), + /* HTT, TM, Reserved, PBE */ + ); - kvm_cpu_cap_mask(CPUID_7_ECX, - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | - F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | - F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | - F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ | - F(SGX_LC) | F(BUS_LOCK_DETECT) + kvm_cpu_cap_init(CPUID_7_0_EBX, + F(FSGSBASE), + EMULATED_F(TSC_ADJUST), + F(SGX), + F(BMI1), + F(HLE), + F(AVX2), + F(FDP_EXCPTN_ONLY), + F(SMEP), + F(BMI2), + F(ERMS), + F(INVPCID), + F(RTM), + F(ZERO_FCS_FDS), + VENDOR_F(MPX), + F(AVX512F), + F(AVX512DQ), + F(RDSEED), + F(ADX), + F(SMAP), + F(AVX512IFMA), + F(CLFLUSHOPT), + F(CLWB), + VENDOR_F(INTEL_PT), + F(AVX512PF), + F(AVX512ER), + F(AVX512CD), + F(SHA_NI), + F(AVX512BW), + F(AVX512VL), + ); + + kvm_cpu_cap_init(CPUID_7_ECX, + F(AVX512VBMI), + PASSTHROUGH_F(LA57), + F(PKU), + RUNTIME_F(OSPKE), + F(RDPID), + F(AVX512_VPOPCNTDQ), + F(UMIP), + F(AVX512_VBMI2), + F(GFNI), + F(VAES), + F(VPCLMULQDQ), + F(AVX512_VNNI), + F(AVX512_BITALG), + F(CLDEMOTE), + F(MOVDIRI), + F(MOVDIR64B), + VENDOR_F(WAITPKG), + F(SGX_LC), + F(BUS_LOCK_DETECT), ); - /* Set LA57 based on hardware capability. */ - if (cpuid_ecx(7) & F(LA57)) - kvm_cpu_cap_set(X86_FEATURE_LA57); /* * PKU not yet implemented for shadow paging and requires OSPKE @@ -699,18 +950,25 @@ void kvm_set_cpu_caps(void) if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) kvm_cpu_cap_clear(X86_FEATURE_PKU); - kvm_cpu_cap_mask(CPUID_7_EDX, - F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | - F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | - F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | - F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) | - F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) | F(FLUSH_L1D) + kvm_cpu_cap_init(CPUID_7_EDX, + F(AVX512_4VNNIW), + F(AVX512_4FMAPS), + F(SPEC_CTRL), + F(SPEC_CTRL_SSBD), + EMULATED_F(ARCH_CAPABILITIES), + F(INTEL_STIBP), + F(MD_CLEAR), + F(AVX512_VP2INTERSECT), + F(FSRM), + F(SERIALIZE), + F(TSXLDTRK), + F(AVX512_FP16), + F(AMX_TILE), + F(AMX_INT8), + F(AMX_BF16), + F(FLUSH_L1D), ); - /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ - kvm_cpu_cap_set(X86_FEATURE_TSC_ADJUST); - kvm_cpu_cap_set(X86_FEATURE_ARCH_CAPABILITIES); - if (boot_cpu_has(X86_FEATURE_AMD_IBPB_RET) && boot_cpu_has(X86_FEATURE_AMD_IBPB) && boot_cpu_has(X86_FEATURE_AMD_IBRS)) @@ -720,65 +978,133 @@ void kvm_set_cpu_caps(void) if (boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); - kvm_cpu_cap_mask(CPUID_7_1_EAX, - F(SHA512) | F(SM3) | F(SM4) | F(AVX_VNNI) | F(AVX512_BF16) | - F(CMPCCXADD) | F(FZRM) | F(FSRS) | F(FSRC) | F(AMX_FP16) | - F(AVX_IFMA) | F(LAM) + kvm_cpu_cap_init(CPUID_7_1_EAX, + F(SHA512), + F(SM3), + F(SM4), + F(AVX_VNNI), + F(AVX512_BF16), + F(CMPCCXADD), + F(FZRM), + F(FSRS), + F(FSRC), + F(AMX_FP16), + F(AVX_IFMA), + F(LAM), ); - kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, - F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(AMX_COMPLEX) | - F(AVX_VNNI_INT16) | F(PREFETCHITI) | F(AVX10) + kvm_cpu_cap_init(CPUID_7_1_EDX, + F(AVX_VNNI_INT8), + F(AVX_NE_CONVERT), + F(AMX_COMPLEX), + F(AVX_VNNI_INT16), + F(PREFETCHITI), + F(AVX10), ); - kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, - F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | - F(BHI_CTRL) | F(MCDT_NO) + kvm_cpu_cap_init(CPUID_7_2_EDX, + F(INTEL_PSFD), + F(IPRED_CTRL), + F(RRSBA_CTRL), + F(DDPD_U), + F(BHI_CTRL), + F(MCDT_NO), ); - kvm_cpu_cap_mask(CPUID_D_1_EAX, - F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd + kvm_cpu_cap_init(CPUID_D_1_EAX, + F(XSAVEOPT), + F(XSAVEC), + F(XGETBV1), + F(XSAVES), + X86_64_F(XFD), ); - kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX, - SF(SGX1) | SF(SGX2) | SF(SGX_EDECCSSA) + kvm_cpu_cap_init(CPUID_12_EAX, + SCATTERED_F(SGX1), + SCATTERED_F(SGX2), + SCATTERED_F(SGX_EDECCSSA), ); - kvm_cpu_cap_init_kvm_defined(CPUID_24_0_EBX, - F(AVX10_128) | F(AVX10_256) | F(AVX10_512) + kvm_cpu_cap_init(CPUID_24_0_EBX, + F(AVX10_128), + F(AVX10_256), + F(AVX10_512), ); - kvm_cpu_cap_mask(CPUID_8000_0001_ECX, - F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | - F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | - F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | - 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | - F(TOPOEXT) | 0 /* PERFCTR_CORE */ + kvm_cpu_cap_init(CPUID_8000_0001_ECX, + F(LAHF_LM), + F(CMP_LEGACY), + VENDOR_F(SVM), + /* ExtApicSpace */ + F(CR8_LEGACY), + F(ABM), + F(SSE4A), + F(MISALIGNSSE), + F(3DNOWPREFETCH), + F(OSVW), + /* IBS */ + F(XOP), + /* SKINIT, WDT, LWP */ + F(FMA4), + F(TBM), + F(TOPOEXT), + VENDOR_F(PERFCTR_CORE), ); - kvm_cpu_cap_mask(CPUID_8000_0001_EDX, - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* Reserved */ | - F(NX) | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | - F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) | - 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW) + kvm_cpu_cap_init(CPUID_8000_0001_EDX, + ALIASED_1_EDX_F(FPU), + ALIASED_1_EDX_F(VME), + ALIASED_1_EDX_F(DE), + ALIASED_1_EDX_F(PSE), + ALIASED_1_EDX_F(TSC), + ALIASED_1_EDX_F(MSR), + ALIASED_1_EDX_F(PAE), + ALIASED_1_EDX_F(MCE), + ALIASED_1_EDX_F(CX8), + ALIASED_1_EDX_F(APIC), + /* Reserved */ + F(SYSCALL), + ALIASED_1_EDX_F(MTRR), + ALIASED_1_EDX_F(PGE), + ALIASED_1_EDX_F(MCA), + ALIASED_1_EDX_F(CMOV), + ALIASED_1_EDX_F(PAT), + ALIASED_1_EDX_F(PSE36), + /* Reserved */ + F(NX), + /* Reserved */ + F(MMXEXT), + ALIASED_1_EDX_F(MMX), + ALIASED_1_EDX_F(FXSR), + F(FXSR_OPT), + X86_64_F(GBPAGES), + F(RDTSCP), + /* Reserved */ + X86_64_F(LM), + F(3DNOWEXT), + F(3DNOW), ); if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64)) kvm_cpu_cap_set(X86_FEATURE_GBPAGES); - kvm_cpu_cap_init_kvm_defined(CPUID_8000_0007_EDX, - SF(CONSTANT_TSC) + kvm_cpu_cap_init(CPUID_8000_0007_EDX, + SCATTERED_F(CONSTANT_TSC), ); - kvm_cpu_cap_mask(CPUID_8000_0008_EBX, - F(CLZERO) | F(XSAVEERPTR) | - F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | - F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) | - F(AMD_PSFD) | F(AMD_IBPB_RET) + kvm_cpu_cap_init(CPUID_8000_0008_EBX, + F(CLZERO), + F(XSAVEERPTR), + F(WBNOINVD), + F(AMD_IBPB), + F(AMD_IBRS), + F(AMD_SSBD), + F(VIRT_SSBD), + F(AMD_SSB_NO), + F(AMD_STIBP), + F(AMD_STIBP_ALWAYS_ON), + F(AMD_PSFD), + F(AMD_IBPB_RET), ); /* @@ -808,50 +1134,73 @@ void kvm_set_cpu_caps(void) !boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); - /* - * Hide all SVM features by default, SVM will set the cap bits for - * features it emulates and/or exposes for L1. - */ - kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0); - - kvm_cpu_cap_mask(CPUID_8000_001F_EAX, - 0 /* SME */ | 0 /* SEV */ | 0 /* VM_PAGE_FLUSH */ | 0 /* SEV_ES */ | - F(SME_COHERENT)); - - kvm_cpu_cap_mask(CPUID_8000_0021_EAX, - F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | - F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ | - F(WRMSR_XX_BASE_NS) + /* All SVM features required additional vendor module enabling. */ + kvm_cpu_cap_init(CPUID_8000_000A_EDX, + VENDOR_F(NPT), + VENDOR_F(VMCBCLEAN), + VENDOR_F(FLUSHBYASID), + VENDOR_F(NRIPS), + VENDOR_F(TSCRATEMSR), + VENDOR_F(V_VMSAVE_VMLOAD), + VENDOR_F(LBRV), + VENDOR_F(PAUSEFILTER), + VENDOR_F(PFTHRESHOLD), + VENDOR_F(VGIF), + VENDOR_F(VNMI), + VENDOR_F(SVME_ADDR_CHK), ); - kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB); - kvm_cpu_cap_check_and_set(X86_FEATURE_IBPB_BRTYPE); - kvm_cpu_cap_check_and_set(X86_FEATURE_SRSO_NO); + kvm_cpu_cap_init(CPUID_8000_001F_EAX, + VENDOR_F(SME), + VENDOR_F(SEV), + /* VM_PAGE_FLUSH */ + VENDOR_F(SEV_ES), + F(SME_COHERENT), + ); - kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, - F(PERFMON_V2) + kvm_cpu_cap_init(CPUID_8000_0021_EAX, + F(NO_NESTED_DATA_BP), + /* + * Synthesize "LFENCE is serializing" into the AMD-defined entry + * in KVM's supported CPUID, i.e. if the feature is reported as + * supported by the kernel. LFENCE_RDTSC was a Linux-defined + * synthetic feature long before AMD joined the bandwagon, e.g. + * LFENCE is serializing on most CPUs that support SSE2. On + * CPUs that don't support AMD's leaf, ANDing with the raw host + * CPUID will drop the flags, and reporting support in AMD's + * leaf can make it easier for userspace to detect the feature. + */ + SYNTHESIZED_F(LFENCE_RDTSC), + /* SmmPgCfgLock */ + F(NULL_SEL_CLR_BASE), + F(AUTOIBRS), + EMULATED_F(NO_SMM_CTL_MSR), + /* PrefetchCtlMsr */ + F(WRMSR_XX_BASE_NS), + SYNTHESIZED_F(SBPB), + SYNTHESIZED_F(IBPB_BRTYPE), + SYNTHESIZED_F(SRSO_NO), + SYNTHESIZED_F(SRSO_USER_KERNEL_NO), + ); + + kvm_cpu_cap_init(CPUID_8000_0022_EAX, + F(PERFMON_V2), ); - /* - * Synthesize "LFENCE is serializing" into the AMD-defined entry in - * KVM's supported CPUID if the feature is reported as supported by the - * kernel. LFENCE_RDTSC was a Linux-defined synthetic feature long - * before AMD joined the bandwagon, e.g. LFENCE is serializing on most - * CPUs that support SSE2. On CPUs that don't support AMD's leaf, - * kvm_cpu_cap_mask() will unfortunately drop the flag due to ANDing - * the mask with the raw host CPUID, and reporting support in AMD's - * leaf can make it easier for userspace to detect the feature. - */ - if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) - kvm_cpu_cap_set(X86_FEATURE_LFENCE_RDTSC); if (!static_cpu_has_bug(X86_BUG_NULL_SEG)) kvm_cpu_cap_set(X86_FEATURE_NULL_SEL_CLR_BASE); - kvm_cpu_cap_set(X86_FEATURE_NO_SMM_CTL_MSR); - kvm_cpu_cap_mask(CPUID_C000_0001_EDX, - F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | - F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | - F(PMM) | F(PMM_EN) + kvm_cpu_cap_init(CPUID_C000_0001_EDX, + F(XSTORE), + F(XSTORE_EN), + F(XCRYPT), + F(XCRYPT_EN), + F(ACE2), + F(ACE2_EN), + F(PHE), + F(PHE_EN), + F(PMM), + F(PMM_EN), ); /* @@ -871,6 +1220,16 @@ void kvm_set_cpu_caps(void) } EXPORT_SYMBOL_GPL(kvm_set_cpu_caps); +#undef F +#undef SCATTERED_F +#undef X86_64_F +#undef EMULATED_F +#undef SYNTHESIZED_F +#undef PASSTHROUGH_F +#undef ALIASED_1_EDX_F +#undef VENDOR_F +#undef RUNTIME_F + struct kvm_cpuid_array { struct kvm_cpuid_entry2 *entries; int maxnent; @@ -928,14 +1287,11 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, return entry; } -static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) +static int cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, u32 func, + bool include_partially_emulated) { - struct kvm_cpuid_entry2 *entry; + memset(entry, 0, sizeof(*entry)); - if (array->nent >= array->maxnent) - return -E2BIG; - - entry = &array->entries[array->nent]; entry->function = func; entry->index = 0; entry->flags = 0; @@ -943,23 +1299,37 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) switch (func) { case 0: entry->eax = 7; - ++array->nent; - break; + return 1; case 1: - entry->ecx = F(MOVBE); - ++array->nent; - break; + entry->ecx = feature_bit(MOVBE); + /* + * KVM allows userspace to enumerate MONITOR+MWAIT support to + * the guest, but the MWAIT feature flag is never advertised + * to userspace because MONITOR+MWAIT aren't virtualized by + * hardware, can't be faithfully emulated in software (KVM + * emulates them as NOPs), and allowing the guest to execute + * them natively requires enabling a per-VM capability. + */ + if (include_partially_emulated) + entry->ecx |= feature_bit(MWAIT); + return 1; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; entry->eax = 0; if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) - entry->ecx = F(RDPID); - ++array->nent; - break; + entry->ecx = feature_bit(RDPID); + return 1; default: - break; + return 0; } +} +static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) +{ + if (array->nent >= array->maxnent) + return -E2BIG; + + array->nent += cpuid_func_emulated(&array->entries[array->nent], func, false); return 0; } @@ -1103,7 +1473,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) goto out; cpuid_entry_override(entry, CPUID_D_1_EAX); - if (entry->eax & (F(XSAVES)|F(XSAVEC))) + if (entry->eax & (feature_bit(XSAVES) | feature_bit(XSAVEC))) entry->ebx = xstate_required_size(permitted_xcr0 | permitted_xss, true); else { @@ -1540,22 +1910,6 @@ out_free: return r; } -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, - u32 function, u32 index) -{ - return cpuid_entry2_find(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, - function, index); -} -EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry_index); - -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function) -{ - return cpuid_entry2_find(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, - function, KVM_CPUID_INDEX_NOT_SIGNIFICANT); -} -EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); - /* * Intel CPUID semantics treats any query for an out-of-range leaf as if the * highest basic leaf (i.e. CPUID.0H:EAX) were requested. AMD CPUID semantics @@ -1648,10 +2002,10 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u64 data; if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) && (data & TSX_CTRL_CPUID_CLEAR)) - *ebx &= ~(F(RTM) | F(HLE)); + *ebx &= ~(feature_bit(RTM) | feature_bit(HLE)); } else if (function == 0x80000007) { if (kvm_hv_invtsc_suppressed(vcpu)) - *edx &= ~SF(CONSTANT_TSC); + *edx &= ~feature_bit(CONSTANT_TSC); } } else { *eax = *ebx = *ecx = *edx = 0; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index f16a7b2c2adc..67d80aa72d50 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -10,8 +10,8 @@ extern u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; void kvm_set_cpu_caps(void); +void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu); -void kvm_update_pv_runtime(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, u32 function, u32 index); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, @@ -67,41 +67,40 @@ static __always_inline void cpuid_entry_override(struct kvm_cpuid_entry2 *entry, *reg = kvm_cpu_caps[leaf]; } -static __always_inline u32 *guest_cpuid_get_register(struct kvm_vcpu *vcpu, - unsigned int x86_feature) +static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature); struct kvm_cpuid_entry2 *entry; + u32 *reg; + + /* + * XSAVES is a special snowflake. Due to lack of a dedicated intercept + * on SVM, KVM must assume that XSAVES (and thus XRSTORS) is usable by + * the guest if the host supports XSAVES and *XSAVE* is exposed to the + * guest. Because the guest can execute XSAVES and XRSTORS, i.e. can + * indirectly consume XSS, KVM must ensure XSS is zeroed when running + * the guest, i.e. must set XSAVES in vCPU capabilities. But to reject + * direct XSS reads and writes (to minimize the virtualization hole and + * honor userspace's CPUID), KVM needs to check the raw guest CPUID, + * not KVM's view of guest capabilities. + * + * For all other features, guest capabilities are accurate. Expand + * this allowlist with extreme vigilance. + */ + BUILD_BUG_ON(x86_feature != X86_FEATURE_XSAVES); entry = kvm_find_cpuid_entry_index(vcpu, cpuid.function, cpuid.index); if (!entry) return NULL; - return __cpuid_entry_get_reg(entry, cpuid.reg); -} - -static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, - unsigned int x86_feature) -{ - u32 *reg; - - reg = guest_cpuid_get_register(vcpu, x86_feature); + reg = __cpuid_entry_get_reg(entry, cpuid.reg); if (!reg) return false; return *reg & __feature_bit(x86_feature); } -static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, - unsigned int x86_feature) -{ - u32 *reg; - - reg = guest_cpuid_get_register(vcpu, x86_feature); - if (reg) - *reg &= ~__feature_bit(x86_feature); -} - static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu) { return vcpu->arch.is_amd_compatible; @@ -150,21 +149,6 @@ static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) return x86_stepping(best->eax); } -static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) -{ - return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)); -} - -static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) -{ - return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB) || - guest_cpuid_has(vcpu, X86_FEATURE_SBPB)); -} - static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu) { return vcpu->arch.msr_platform_info & MSR_PLATFORM_INFO_CPUID_FAULT; @@ -180,7 +164,6 @@ static __always_inline void kvm_cpu_cap_clear(unsigned int x86_feature) { unsigned int x86_leaf = __feature_leaf(x86_feature); - reverse_cpuid_check(x86_leaf); kvm_cpu_caps[x86_leaf] &= ~__feature_bit(x86_feature); } @@ -188,7 +171,6 @@ static __always_inline void kvm_cpu_cap_set(unsigned int x86_feature) { unsigned int x86_leaf = __feature_leaf(x86_feature); - reverse_cpuid_check(x86_leaf); kvm_cpu_caps[x86_leaf] |= __feature_bit(x86_feature); } @@ -196,7 +178,6 @@ static __always_inline u32 kvm_cpu_cap_get(unsigned int x86_feature) { unsigned int x86_leaf = __feature_leaf(x86_feature); - reverse_cpuid_check(x86_leaf); return kvm_cpu_caps[x86_leaf] & __feature_bit(x86_feature); } @@ -220,58 +201,61 @@ static __always_inline bool guest_pv_has(struct kvm_vcpu *vcpu, return vcpu->arch.pv_cpuid.features & (1u << kvm_feature); } -enum kvm_governed_features { -#define KVM_GOVERNED_FEATURE(x) KVM_GOVERNED_##x, -#include "governed_features.h" - KVM_NR_GOVERNED_FEATURES -}; - -static __always_inline int kvm_governed_feature_index(unsigned int x86_feature) +static __always_inline void guest_cpu_cap_set(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - switch (x86_feature) { -#define KVM_GOVERNED_FEATURE(x) case x: return KVM_GOVERNED_##x; -#include "governed_features.h" - default: - return -1; - } + unsigned int x86_leaf = __feature_leaf(x86_feature); + + vcpu->arch.cpu_caps[x86_leaf] |= __feature_bit(x86_feature); } -static __always_inline bool kvm_is_governed_feature(unsigned int x86_feature) +static __always_inline void guest_cpu_cap_clear(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - return kvm_governed_feature_index(x86_feature) >= 0; + unsigned int x86_leaf = __feature_leaf(x86_feature); + + vcpu->arch.cpu_caps[x86_leaf] &= ~__feature_bit(x86_feature); } -static __always_inline void kvm_governed_feature_set(struct kvm_vcpu *vcpu, - unsigned int x86_feature) +static __always_inline void guest_cpu_cap_change(struct kvm_vcpu *vcpu, + unsigned int x86_feature, + bool guest_has_cap) { - BUILD_BUG_ON(!kvm_is_governed_feature(x86_feature)); - - __set_bit(kvm_governed_feature_index(x86_feature), - vcpu->arch.governed_features.enabled); + if (guest_has_cap) + guest_cpu_cap_set(vcpu, x86_feature); + else + guest_cpu_cap_clear(vcpu, x86_feature); } -static __always_inline void kvm_governed_feature_check_and_set(struct kvm_vcpu *vcpu, - unsigned int x86_feature) +static __always_inline bool guest_cpu_cap_has(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - if (kvm_cpu_cap_has(x86_feature) && guest_cpuid_has(vcpu, x86_feature)) - kvm_governed_feature_set(vcpu, x86_feature); -} + unsigned int x86_leaf = __feature_leaf(x86_feature); -static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu, - unsigned int x86_feature) -{ - BUILD_BUG_ON(!kvm_is_governed_feature(x86_feature)); - - return test_bit(kvm_governed_feature_index(x86_feature), - vcpu->arch.governed_features.enabled); + return vcpu->arch.cpu_caps[x86_leaf] & __feature_bit(x86_feature); } static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { - if (guest_can_use(vcpu, X86_FEATURE_LAM)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LAM)) cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57); return kvm_vcpu_is_legal_gpa(vcpu, cr3); } +static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_STIBP) || + guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBRS) || + guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_SSBD)); +} + +static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBPB) || + guest_cpu_cap_has(vcpu, X86_FEATURE_SBPB)); +} + #endif diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h deleted file mode 100644 index ad463b1ed4e4..000000000000 --- a/arch/x86/kvm/governed_features.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#if !defined(KVM_GOVERNED_FEATURE) || defined(KVM_GOVERNED_X86_FEATURE) -BUILD_BUG() -#endif - -#define KVM_GOVERNED_X86_FEATURE(x) KVM_GOVERNED_FEATURE(X86_FEATURE_##x) - -KVM_GOVERNED_X86_FEATURE(GBPAGES) -KVM_GOVERNED_X86_FEATURE(XSAVES) -KVM_GOVERNED_X86_FEATURE(VMX) -KVM_GOVERNED_X86_FEATURE(NRIPS) -KVM_GOVERNED_X86_FEATURE(TSCRATEMSR) -KVM_GOVERNED_X86_FEATURE(V_VMSAVE_VMLOAD) -KVM_GOVERNED_X86_FEATURE(LBRV) -KVM_GOVERNED_X86_FEATURE(PAUSEFILTER) -KVM_GOVERNED_X86_FEATURE(PFTHRESHOLD) -KVM_GOVERNED_X86_FEATURE(VGIF) -KVM_GOVERNED_X86_FEATURE(VNMI) -KVM_GOVERNED_X86_FEATURE(LAM) - -#undef KVM_GOVERNED_X86_FEATURE -#undef KVM_GOVERNED_FEATURE diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 4f0a94346d00..6a6dd5a84f22 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1352,7 +1352,7 @@ static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) return; if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) || - !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVEC)) return; pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. " diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index cd57a517d04a..d7ab8780ab9e 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -681,7 +681,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) pid_nr = pid_vnr(pid); put_pid(pid); - pit->worker = kthread_create_worker(0, "kvm-pit/%d", pid_nr); + pit->worker = kthread_run_worker(0, "kvm-pit/%d", pid_nr); if (IS_ERR(pit->worker)) goto fail_kthread; diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 10495fffb890..73072585e164 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -88,6 +88,8 @@ struct x86_instruction_info { #define X86EMUL_CMPXCHG_FAILED 4 /* cmpxchg did not see expected value */ #define X86EMUL_IO_NEEDED 5 /* IO is needed to complete emulation */ #define X86EMUL_INTERCEPTED 6 /* Intercepted by nested VMCB/VMCS */ +/* Emulation during event vectoring is unhandleable. */ +#define X86EMUL_UNHANDLEABLE_VECTORING 7 /* x86-specific emulation flags */ #define X86EMUL_F_WRITE BIT(0) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3c83951c619e..a009c94c26c2 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -598,7 +598,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu) * version first and level-triggered interrupts never get EOIed in * IOAPIC. */ - if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_X2APIC) && !ioapic_in_kernel(vcpu->kvm)) v |= APIC_LVR_DIRECTED_EOI; kvm_lapic_set_reg(apic, APIC_LVR, v); @@ -734,10 +734,7 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) { if (unlikely(apic->apicv_active)) { - /* need to update RVI */ kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); - kvm_x86_call(hwapic_irr_update)(apic->vcpu, - apic_find_highest_irr(apic)); } else { apic->irr_pending = false; kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); @@ -763,7 +760,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * just set SVI. */ if (unlikely(apic->apicv_active)) - kvm_x86_call(hwapic_isr_update)(vec); + kvm_x86_call(hwapic_isr_update)(apic->vcpu, vec); else { ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -808,7 +805,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * and must be left alone. */ if (unlikely(apic->apicv_active)) - kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic)); + kvm_x86_call(hwapic_isr_update)(apic->vcpu, apic_find_highest_isr(apic)); else { --apic->isr_count; BUG_ON(apic->isr_count < 0); @@ -816,6 +813,17 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) } } +void kvm_apic_update_hwapic_isr(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (WARN_ON_ONCE(!lapic_in_kernel(vcpu)) || !apic->apicv_active) + return; + + kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic)); +} +EXPORT_SYMBOL_GPL(kvm_apic_update_hwapic_isr); + int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) { /* This may race with setting of irr in __apic_accept_irq() and @@ -2357,7 +2365,7 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; - val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask); + val &= (apic_lvt_mask[LVT_TIMER] | apic->lapic_timer.timer_mode_mask); kvm_lapic_set_reg(apic, APIC_LVTT, val); apic_update_lvtt(apic); break; @@ -2634,7 +2642,7 @@ int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated) return 0; u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff | - (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); + (guest_cpu_cap_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); if ((value & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID) return 1; @@ -2805,8 +2813,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) apic_update_ppr(apic); if (apic->apicv_active) { kvm_x86_call(apicv_post_state_restore)(vcpu); - kvm_x86_call(hwapic_irr_update)(vcpu, -1); - kvm_x86_call(hwapic_isr_update)(-1); + kvm_x86_call(hwapic_isr_update)(vcpu, -1); } vcpu->arch.apic_arb_prio = 0; @@ -3121,9 +3128,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_apic_update_apicv(vcpu); if (apic->apicv_active) { kvm_x86_call(apicv_post_state_restore)(vcpu); - kvm_x86_call(hwapic_irr_update)(vcpu, - apic_find_highest_irr(apic)); - kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic)); + kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic)); } kvm_make_request(KVM_REQ_EVENT, vcpu); if (ioapic_in_kernel(vcpu->kvm)) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 24add38beaf0..1a8553ebdb42 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -118,6 +118,7 @@ void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high); int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated); int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); +void kvm_apic_update_hwapic_isr(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e9322358678b..050a0e229a4d 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -104,6 +104,15 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { + /* + * Checking root.hpa is sufficient even when KVM has mirror root. + * We can have either: + * (1) mirror_root_hpa = INVALID_PAGE, root.hpa = INVALID_PAGE + * (2) mirror_root_hpa = root, root.hpa = INVALID_PAGE + * (3) mirror_root_hpa = root1, root.hpa = root2 + * We don't ever have: + * mirror_root_hpa = INVALID_PAGE, root.hpa = root + */ if (likely(vcpu->arch.mmu->root.hpa != INVALID_PAGE)) return 0; @@ -126,7 +135,7 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu) static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu) { - if (!guest_can_use(vcpu, X86_FEATURE_LAM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LAM)) return 0; return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57); @@ -287,4 +296,26 @@ static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu, return gpa; return translate_nested_gpa(vcpu, gpa, access, exception); } + +static inline bool kvm_has_mirrored_tdp(const struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_TDX_VM; +} + +static inline gfn_t kvm_gfn_direct_bits(const struct kvm *kvm) +{ + return kvm->arch.gfn_direct_bits; +} + +static inline bool kvm_is_addr_direct(struct kvm *kvm, gpa_t gpa) +{ + gpa_t gpa_direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(kvm)); + + return !gpa_direct_bits || (gpa & gpa_direct_bits); +} + +static inline bool kvm_is_gfn_alias(struct kvm *kvm, gfn_t gfn) +{ + return gfn & kvm_gfn_direct_bits(kvm); +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 22e7ad235123..a45ae60e84ab 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -599,6 +599,12 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect) 1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM); if (r) return r; + if (kvm_has_mirrored_tdp(vcpu->kvm)) { + r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_external_spt_cache, + PT64_ROOT_MAX_LEVEL); + if (r) + return r; + } r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache, PT64_ROOT_MAX_LEVEL); if (r) @@ -618,6 +624,7 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadowed_info_cache); + kvm_mmu_free_memory_cache(&vcpu->arch.mmu_external_spt_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache); } @@ -3364,18 +3371,6 @@ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, return true; } -static bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) -{ - if (fault->exec) - return is_executable_pte(spte); - - if (fault->write) - return is_writable_pte(spte); - - /* Fault was on Read access */ - return spte & PT_PRESENT_MASK; -} - /* * Returns the last level spte pointer of the shadow page walk for the given * gpa, and sets *spte to the spte value. This spte may be non-preset. If no @@ -3668,8 +3663,13 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) unsigned i; int r; - if (tdp_mmu_enabled) - return kvm_tdp_mmu_alloc_root(vcpu); + if (tdp_mmu_enabled) { + if (kvm_has_mirrored_tdp(vcpu->kvm) && + !VALID_PAGE(mmu->mirror_root_hpa)) + kvm_tdp_mmu_alloc_root(vcpu, true); + kvm_tdp_mmu_alloc_root(vcpu, false); + return 0; + } write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); @@ -4391,8 +4391,12 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, unsigned int access) { struct kvm_memory_slot *slot = fault->slot; + struct kvm *kvm = vcpu->kvm; int ret; + if (KVM_BUG_ON(kvm_is_gfn_alias(kvm, fault->gfn), kvm)) + return -EFAULT; + /* * Note that the mmu_invalidate_seq also serves to detect a concurrent * change in attributes. is_page_fault_stale() will detect an @@ -4406,7 +4410,7 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, * Now that we have a snapshot of mmu_invalidate_seq we can check for a * private vs. shared mismatch. */ - if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + if (fault->is_private != kvm_mem_is_private(kvm, fault->gfn)) { kvm_mmu_prepare_memory_fault_exit(vcpu, fault); return -EFAULT; } @@ -4468,7 +4472,7 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held * to detect retry guarantees the worst case latency for the vCPU. */ - if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) + if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) return RET_PF_RETRY; ret = __kvm_mmu_faultin_pfn(vcpu, fault); @@ -4488,7 +4492,7 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, * overall cost of failing to detect the invalidation until after * mmu_lock is acquired. */ - if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) { + if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) { kvm_mmu_finish_page_fault(vcpu, fault, RET_PF_RETRY); return RET_PF_RETRY; } @@ -5034,7 +5038,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, __reset_rsvds_bits_mask(&context->guest_rsvd_check, vcpu->arch.reserved_gpa_bits, context->cpu_role.base.level, is_efer_nx(context), - guest_can_use(vcpu, X86_FEATURE_GBPAGES), + guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), guest_cpuid_is_amd_compatible(vcpu)); } @@ -5111,7 +5115,7 @@ static void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(), context->root_role.level, context->root_role.efer_nx, - guest_can_use(vcpu, X86_FEATURE_GBPAGES), + guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES), is_pse, is_amd); if (!shadow_me_mask) @@ -6107,8 +6111,16 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err else if (r == RET_PF_SPURIOUS) vcpu->stat.pf_spurious++; + /* + * None of handle_mmio_page_fault(), kvm_mmu_do_page_fault(), or + * kvm_mmu_write_protect_fault() return RET_PF_CONTINUE. + * kvm_mmu_do_page_fault() only uses RET_PF_CONTINUE internally to + * indicate continuing the page fault handling until to the final + * page table mapping phase. + */ + WARN_ON_ONCE(r == RET_PF_CONTINUE); if (r != RET_PF_EMULATE) - return 1; + return r; emulate: return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, @@ -6284,6 +6296,7 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->root.hpa = INVALID_PAGE; mmu->root.pgd = 0; + mmu->mirror_root_hpa = INVALID_PAGE; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; @@ -6453,8 +6466,13 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * write and in the same critical section as making the reload request, * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield. */ - if (tdp_mmu_enabled) - kvm_tdp_mmu_invalidate_all_roots(kvm); + if (tdp_mmu_enabled) { + /* + * External page tables don't support fast zapping, therefore + * their mirrors must be invalidated separately by the caller. + */ + kvm_tdp_mmu_invalidate_roots(kvm, KVM_DIRECT_ROOTS); + } /* * Notify all vcpus to reload its shadow page table and flush TLB. @@ -6479,7 +6497,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * lead to use-after-free. */ if (tdp_mmu_enabled) - kvm_tdp_mmu_zap_invalidated_roots(kvm); + kvm_tdp_mmu_zap_invalidated_roots(kvm, true); } void kvm_mmu_init_vm(struct kvm *kvm) @@ -7232,6 +7250,12 @@ out: void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); + if (tdp_mmu_enabled) { + read_lock(&vcpu->kvm->mmu_lock); + mmu_free_root_page(vcpu->kvm, &vcpu->arch.mmu->mirror_root_hpa, + NULL); + read_unlock(&vcpu->kvm->mmu_lock); + } free_mmu_pages(&vcpu->arch.root_mmu); free_mmu_pages(&vcpu->arch.guest_mmu); mmu_free_memory_caches(vcpu); @@ -7423,20 +7447,28 @@ static bool kvm_nx_huge_page_recovery_worker(void *data) return true; } -int kvm_mmu_post_init_vm(struct kvm *kvm) +static void kvm_mmu_start_lpage_recovery(struct once *once) { - if (nx_hugepage_mitigation_hard_disabled) - return 0; + struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once); + struct kvm *kvm = container_of(ka, struct kvm, arch); kvm->arch.nx_huge_page_last = get_jiffies_64(); kvm->arch.nx_huge_page_recovery_thread = vhost_task_create( kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill, kvm, "kvm-nx-lpage-recovery"); + if (kvm->arch.nx_huge_page_recovery_thread) + vhost_task_start(kvm->arch.nx_huge_page_recovery_thread); +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + if (nx_hugepage_mitigation_hard_disabled) + return 0; + + call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery); if (!kvm->arch.nx_huge_page_recovery_thread) return -ENOMEM; - - vhost_task_start(kvm->arch.nx_huge_page_recovery_thread); return 0; } @@ -7464,6 +7496,12 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) return false; + /* Unmap the old attribute page. */ + if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE) + range->attr_filter = KVM_FILTER_SHARED; + else + range->attr_filter = KVM_FILTER_PRIVATE; + return kvm_unmap_gfn_range(kvm, range); } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index b00abbe3f6cf..75f00598289d 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -6,6 +6,8 @@ #include #include +#include "mmu.h" + #ifdef CONFIG_KVM_PROVE_MMU #define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x) #else @@ -101,7 +103,22 @@ struct kvm_mmu_page { int root_count; refcount_t tdp_mmu_root_count; }; - unsigned int unsync_children; + union { + /* These two members aren't used for TDP MMU */ + struct { + unsigned int unsync_children; + /* + * Number of writes since the last time traversal + * visited this page. + */ + atomic_t write_flooding_count; + }; + /* + * Page table page of external PT. + * Passed to TDX module, not accessed by KVM. + */ + void *external_spt; + }; union { struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ tdp_ptep_t ptep; @@ -124,9 +141,6 @@ struct kvm_mmu_page { int clear_spte_count; #endif - /* Number of writes since the last time traversal visited this page. */ - atomic_t write_flooding_count; - #ifdef CONFIG_X86_64 /* Used for freeing the page asynchronously if it is a TDP MMU page. */ struct rcu_head rcu_head; @@ -145,6 +159,34 @@ static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) return kvm_mmu_role_as_id(sp->role); } +static inline bool is_mirror_sp(const struct kvm_mmu_page *sp) +{ + return sp->role.is_mirror; +} + +static inline void kvm_mmu_alloc_external_spt(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +{ + /* + * external_spt is allocated for TDX module to hold private EPT mappings, + * TDX module will initialize the page by itself. + * Therefore, KVM does not need to initialize or access external_spt. + * KVM only interacts with sp->spt for private EPT operations. + */ + sp->external_spt = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_external_spt_cache); +} + +static inline gfn_t kvm_gfn_root_bits(const struct kvm *kvm, const struct kvm_mmu_page *root) +{ + /* + * Since mirror SPs are used only for TDX, which maps private memory + * at its "natural" GFN, no mask needs to be applied to them - and, dually, + * we expect that the bits is only used for the shared PT. + */ + if (is_mirror_sp(root)) + return 0; + return kvm_gfn_direct_bits(kvm); +} + static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) { /* @@ -229,7 +271,12 @@ struct kvm_page_fault { */ u8 goal_level; - /* Shifted addr, or result of guest page table walk if addr is a gva. */ + /* + * Shifted addr, or result of guest page table walk if addr is a gva. In + * the case of VM where memslot's can be mapped at multiple GPA aliases + * (i.e. TDX), the gfn field does not contain the bit that selects between + * the aliases (i.e. the shared bit for TDX). + */ gfn_t gfn; /* The memslot containing gfn. May be NULL. */ @@ -268,9 +315,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); * tracepoints via TRACE_DEFINE_ENUM() in mmutrace.h * * Note, all values must be greater than or equal to zero so as not to encroach - * on -errno return values. Somewhat arbitrarily use '0' for CONTINUE, which - * will allow for efficient machine code when checking for CONTINUE, e.g. - * "TEST %rax, %rax, JNZ", as all "stop!" values are non-zero. + * on -errno return values. */ enum { RET_PF_CONTINUE = 0, @@ -282,6 +327,14 @@ enum { RET_PF_SPURIOUS, }; +/* + * Define RET_PF_CONTINUE as 0 to allow for + * - efficient machine code when checking for CONTINUE, e.g. + * "TEST %rax, %rax, JNZ", as all "stop!" values are non-zero, + * - kvm_mmu_do_page_fault() to return other RET_PF_* as a positive value. + */ +static_assert(RET_PF_CONTINUE == 0); + static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { @@ -317,10 +370,19 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int r; if (vcpu->arch.mmu->root_role.direct) { - fault.gfn = fault.addr >> PAGE_SHIFT; + /* + * Things like memslots don't understand the concept of a shared + * bit. Strip it so that the GFN can be used like normal, and the + * fault.addr can be used when the shared bit is needed. + */ + fault.gfn = gpa_to_gfn(fault.addr) & ~kvm_gfn_direct_bits(vcpu->kvm); fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn); } + /* + * With retpoline being active an indirect call is rather expensive, + * so do a direct call in the most common case. + */ if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && fault.is_tdp) r = kvm_tdp_page_fault(vcpu, &fault); else diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index f332b33bc817..59746854c0af 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -276,6 +276,11 @@ static inline struct kvm_mmu_page *root_to_sp(hpa_t root) return spte_to_child_sp(root); } +static inline bool is_mirror_sptep(tdp_ptep_t sptep) +{ + return is_mirror_sp(sptep_to_sp(rcu_dereference(sptep))); +} + static inline bool is_mmio_spte(struct kvm *kvm, u64 spte) { return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value && @@ -461,6 +466,23 @@ static inline bool is_mmu_writable_spte(u64 spte) return spte & shadow_mmu_writable_mask; } +/* + * Returns true if the access indicated by @fault is allowed by the existing + * SPTE protections. Note, the caller is responsible for checking that the + * SPTE is a shadow-present, leaf SPTE (either before or after). + */ +static inline bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) +{ + if (fault->exec) + return is_executable_pte(spte); + + if (fault->write) + return is_writable_pte(spte); + + /* Fault was on Read access */ + return spte & PT_PRESENT_MASK; +} + /* * If the MMU-writable flag is cleared, i.e. the SPTE is write-protected for * write-tracking, remote TLBs must be flushed, even if the SPTE was read-only, diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index 04c247bfe318..9e17bfa80901 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -12,7 +12,7 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter) { iter->sptep = iter->pt_path[iter->level - 1] + - SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level); + SPTE_INDEX((iter->gfn | iter->gfn_bits) << PAGE_SHIFT, iter->level); iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep); } @@ -37,15 +37,17 @@ void tdp_iter_restart(struct tdp_iter *iter) * rooted at root_pt, starting with the walk to translate next_last_level_gfn. */ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, - int min_level, gfn_t next_last_level_gfn) + int min_level, gfn_t next_last_level_gfn, gfn_t gfn_bits) { if (WARN_ON_ONCE(!root || (root->role.level < 1) || - (root->role.level > PT64_ROOT_MAX_LEVEL))) { + (root->role.level > PT64_ROOT_MAX_LEVEL) || + (gfn_bits && next_last_level_gfn >= gfn_bits))) { iter->valid = false; return; } iter->next_last_level_gfn = next_last_level_gfn; + iter->gfn_bits = gfn_bits; iter->root_level = root->role.level; iter->min_level = min_level; iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root->spt; @@ -113,7 +115,7 @@ static bool try_step_side(struct tdp_iter *iter) * Check if the iterator is already at the end of the current page * table. */ - if (SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level) == + if (SPTE_INDEX((iter->gfn | iter->gfn_bits) << PAGE_SHIFT, iter->level) == (SPTE_ENT_PER_PAGE - 1)) return false; diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index 2880fd392e0c..047b78333653 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -93,8 +93,10 @@ struct tdp_iter { tdp_ptep_t pt_path[PT64_ROOT_MAX_LEVEL]; /* A pointer to the current SPTE */ tdp_ptep_t sptep; - /* The lowest GFN mapped by the current SPTE */ + /* The lowest GFN (mask bits excluded) mapped by the current SPTE */ gfn_t gfn; + /* Mask applied to convert the GFN to the mapping GPA */ + gfn_t gfn_bits; /* The level of the root page given to the iterator */ int root_level; /* The lowest level the iterator should traverse to */ @@ -122,18 +124,23 @@ struct tdp_iter { * Iterates over every SPTE mapping the GFN range [start, end) in a * preorder traversal. */ -#define for_each_tdp_pte_min_level(iter, root, min_level, start, end) \ - for (tdp_iter_start(&iter, root, min_level, start); \ - iter.valid && iter.gfn < end; \ +#define for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, end) \ + for (tdp_iter_start(&iter, root, min_level, start, kvm_gfn_root_bits(kvm, root)); \ + iter.valid && iter.gfn < end; \ tdp_iter_next(&iter)) -#define for_each_tdp_pte(iter, root, start, end) \ - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) +#define for_each_tdp_pte_min_level_all(iter, root, min_level) \ + for (tdp_iter_start(&iter, root, min_level, 0, 0); \ + iter.valid && iter.gfn < tdp_mmu_max_gfn_exclusive(); \ + tdp_iter_next(&iter)) + +#define for_each_tdp_pte(iter, kvm, root, start, end) \ + for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_4K, start, end) tdp_ptep_t spte_to_child_pt(u64 pte, int level); void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, - int min_level, gfn_t next_last_level_gfn); + int min_level, gfn_t next_last_level_gfn, gfn_t gfn_bits); void tdp_iter_next(struct tdp_iter *iter); void tdp_iter_restart(struct tdp_iter *iter); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 4508d868f1cd..046b6ba31197 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -37,8 +37,8 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) * for zapping and thus puts the TDP MMU's reference to each root, i.e. * ultimately frees all roots. */ - kvm_tdp_mmu_invalidate_all_roots(kvm); - kvm_tdp_mmu_zap_invalidated_roots(kvm); + kvm_tdp_mmu_invalidate_roots(kvm, KVM_VALID_ROOTS); + kvm_tdp_mmu_zap_invalidated_roots(kvm, false); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); @@ -53,6 +53,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) static void tdp_mmu_free_sp(struct kvm_mmu_page *sp) { + free_page((unsigned long)sp->external_spt); free_page((unsigned long)sp->spt); kmem_cache_free(mmu_page_header_cache, sp); } @@ -91,19 +92,33 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback); } +static bool tdp_mmu_root_match(struct kvm_mmu_page *root, + enum kvm_tdp_mmu_root_types types) +{ + if (WARN_ON_ONCE(!(types & KVM_VALID_ROOTS))) + return false; + + if (root->role.invalid && !(types & KVM_INVALID_ROOTS)) + return false; + + if (likely(!is_mirror_sp(root))) + return types & KVM_DIRECT_ROOTS; + return types & KVM_MIRROR_ROOTS; +} + /* * Returns the next root after @prev_root (or the first root if @prev_root is - * NULL). A reference to the returned root is acquired, and the reference to - * @prev_root is released (the caller obviously must hold a reference to - * @prev_root if it's non-NULL). + * NULL) that matches with @types. A reference to the returned root is + * acquired, and the reference to @prev_root is released (the caller obviously + * must hold a reference to @prev_root if it's non-NULL). * - * If @only_valid is true, invalid roots are skipped. + * Roots that doesn't match with @types are skipped. * * Returns NULL if the end of tdp_mmu_roots was reached. */ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, struct kvm_mmu_page *prev_root, - bool only_valid) + enum kvm_tdp_mmu_root_types types) { struct kvm_mmu_page *next_root; @@ -124,7 +139,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, typeof(*next_root), link); while (next_root) { - if ((!only_valid || !next_root->role.invalid) && + if (tdp_mmu_root_match(next_root, types) && kvm_tdp_mmu_get_root(next_root)) break; @@ -149,20 +164,20 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * If shared is set, this function is operating under the MMU lock in read * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _types) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, _types); \ ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + _root = tdp_mmu_next_root(_kvm, _root, _types)) \ if (_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) { \ } else #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true) + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, KVM_VALID_ROOTS) #define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, false); \ + for (_root = tdp_mmu_next_root(_kvm, NULL, KVM_ALL_ROOTS); \ ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ - _root = tdp_mmu_next_root(_kvm, _root, false)) + _root = tdp_mmu_next_root(_kvm, _root, KVM_ALL_ROOTS)) /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -171,18 +186,15 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * Holding mmu_lock for write obviates the need for RCU protection as the list * is guaranteed to be stable. */ -#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _only_valid) \ +#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _types) \ list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) || \ - ((_only_valid) && (_root)->role.invalid))) { \ + !tdp_mmu_root_match((_root), (_types)))) { \ } else -#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root(_kvm, _root, _as_id, false) - #define for_each_valid_tdp_mmu_root(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root(_kvm, _root, _as_id, true) + __for_each_tdp_mmu_root(_kvm, _root, _as_id, KVM_VALID_ROOTS) static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu) { @@ -223,7 +235,7 @@ static void tdp_mmu_init_child_sp(struct kvm_mmu_page *child_sp, tdp_mmu_init_sp(child_sp, iter->sptep, iter->gfn, role); } -int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) +void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu, bool mirror) { struct kvm_mmu *mmu = vcpu->arch.mmu; union kvm_mmu_page_role role = mmu->root_role; @@ -231,6 +243,9 @@ int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; struct kvm_mmu_page *root; + if (mirror) + role.is_mirror = true; + /* * Check for an existing root before acquiring the pages lock to avoid * unnecessary serialization if multiple vCPUs are loading a new root. @@ -282,9 +297,12 @@ out_read_unlock: * and actually consuming the root if it's invalidated after dropping * mmu_lock, and the root can't be freed as this vCPU holds a reference. */ - mmu->root.hpa = __pa(root->spt); - mmu->root.pgd = 0; - return 0; + if (mirror) { + mmu->mirror_root_hpa = __pa(root->spt); + } else { + mmu->root.hpa = __pa(root->spt); + mmu->root.pgd = 0; + } } static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, @@ -322,6 +340,29 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } +static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte, + int level) +{ + kvm_pfn_t old_pfn = spte_to_pfn(old_spte); + int ret; + + /* + * External (TDX) SPTEs are limited to PG_LEVEL_4K, and external + * PTs are removed in a special order, involving free_external_spt(). + * But remove_external_spte() will be called on non-leaf PTEs via + * __tdp_mmu_zap_root(), so avoid the error the former would return + * in this case. + */ + if (!is_last_spte(old_spte, level)) + return; + + /* Zapping leaf spte is allowed only when write lock is held. */ + lockdep_assert_held_write(&kvm->mmu_lock); + /* Because write lock is held, operation should success. */ + ret = static_call(kvm_x86_remove_external_spte)(kvm, gfn, level, old_pfn); + KVM_BUG_ON(ret, kvm); +} + /** * handle_removed_pt() - handle a page table removed from the TDP structure * @@ -417,11 +458,81 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, old_spte, FROZEN_SPTE, level, shared); + + if (is_mirror_sp(sp)) { + KVM_BUG_ON(shared, kvm); + remove_external_spte(kvm, gfn, old_spte, level); + } + } + + if (is_mirror_sp(sp) && + WARN_ON(static_call(kvm_x86_free_external_spt)(kvm, base_gfn, sp->role.level, + sp->external_spt))) { + /* + * Failed to free page table page in mirror page table and + * there is nothing to do further. + * Intentionally leak the page to prevent the kernel from + * accessing the encrypted page. + */ + sp->external_spt = NULL; } call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); } +static void *get_external_spt(gfn_t gfn, u64 new_spte, int level) +{ + if (is_shadow_present_pte(new_spte) && !is_last_spte(new_spte, level)) { + struct kvm_mmu_page *sp = spte_to_child_sp(new_spte); + + WARN_ON_ONCE(sp->role.level + 1 != level); + WARN_ON_ONCE(sp->gfn != gfn); + return sp->external_spt; + } + + return NULL; +} + +static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sptep, + gfn_t gfn, u64 old_spte, + u64 new_spte, int level) +{ + bool was_present = is_shadow_present_pte(old_spte); + bool is_present = is_shadow_present_pte(new_spte); + bool is_leaf = is_present && is_last_spte(new_spte, level); + kvm_pfn_t new_pfn = spte_to_pfn(new_spte); + int ret = 0; + + KVM_BUG_ON(was_present, kvm); + + lockdep_assert_held(&kvm->mmu_lock); + /* + * We need to lock out other updates to the SPTE until the external + * page table has been modified. Use FROZEN_SPTE similar to + * the zapping case. + */ + if (!try_cmpxchg64(rcu_dereference(sptep), &old_spte, FROZEN_SPTE)) + return -EBUSY; + + /* + * Use different call to either set up middle level + * external page table, or leaf. + */ + if (is_leaf) { + ret = static_call(kvm_x86_set_external_spte)(kvm, gfn, level, new_pfn); + } else { + void *external_spt = get_external_spt(gfn, new_spte, level); + + KVM_BUG_ON(!external_spt, kvm); + ret = static_call(kvm_x86_link_external_spt)(kvm, gfn, level, external_spt); + } + if (ret) + __kvm_tdp_mmu_write_spte(sptep, old_spte); + else + __kvm_tdp_mmu_write_spte(sptep, new_spte); + return ret; +} + /** * handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance @@ -522,11 +633,10 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, handle_removed_pt(kvm, spte_to_child_pt(old_spte, level), shared); } -static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, +static inline int __must_check __tdp_mmu_set_spte_atomic(struct kvm *kvm, + struct tdp_iter *iter, u64 new_spte) { - u64 *sptep = rcu_dereference(iter->sptep); - /* * The caller is responsible for ensuring the old SPTE is not a FROZEN * SPTE. KVM should never attempt to zap or manipulate a FROZEN SPTE, @@ -535,15 +645,34 @@ static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, */ WARN_ON_ONCE(iter->yielded || is_frozen_spte(iter->old_spte)); - /* - * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and - * does not hold the mmu_lock. On failure, i.e. if a different logical - * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with - * the current value, so the caller operates on fresh data, e.g. if it - * retries tdp_mmu_set_spte_atomic() - */ - if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) - return -EBUSY; + if (is_mirror_sptep(iter->sptep) && !is_frozen_spte(new_spte)) { + int ret; + + /* + * Users of atomic zapping don't operate on mirror roots, + * so don't handle it and bug the VM if it's seen. + */ + if (KVM_BUG_ON(!is_shadow_present_pte(new_spte), kvm)) + return -EBUSY; + + ret = set_external_spte_present(kvm, iter->sptep, iter->gfn, + iter->old_spte, new_spte, iter->level); + if (ret) + return ret; + } else { + u64 *sptep = rcu_dereference(iter->sptep); + + /* + * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs + * and does not hold the mmu_lock. On failure, i.e. if a + * different logical CPU modified the SPTE, try_cmpxchg64() + * updates iter->old_spte with the current value, so the caller + * operates on fresh data, e.g. if it retries + * tdp_mmu_set_spte_atomic() + */ + if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) + return -EBUSY; + } return 0; } @@ -573,7 +702,7 @@ static inline int __must_check tdp_mmu_set_spte_atomic(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - ret = __tdp_mmu_set_spte_atomic(iter, new_spte); + ret = __tdp_mmu_set_spte_atomic(kvm, iter, new_spte); if (ret) return ret; @@ -613,6 +742,16 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); + + /* + * Users that do non-atomic setting of PTEs don't operate on mirror + * roots, so don't handle it and bug the VM if it's seen. + */ + if (is_mirror_sptep(sptep)) { + KVM_BUG_ON(is_shadow_present_pte(new_spte), kvm); + remove_external_spte(kvm, gfn, old_spte, level); + } + return old_spte; } @@ -625,18 +764,18 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter, iter->gfn, iter->level); } -#define tdp_root_for_each_pte(_iter, _root, _start, _end) \ - for_each_tdp_pte(_iter, _root, _start, _end) +#define tdp_root_for_each_pte(_iter, _kvm, _root, _start, _end) \ + for_each_tdp_pte(_iter, _kvm, _root, _start, _end) -#define tdp_root_for_each_leaf_pte(_iter, _root, _start, _end) \ - tdp_root_for_each_pte(_iter, _root, _start, _end) \ +#define tdp_root_for_each_leaf_pte(_iter, _kvm, _root, _start, _end) \ + tdp_root_for_each_pte(_iter, _kvm, _root, _start, _end) \ if (!is_shadow_present_pte(_iter.old_spte) || \ !is_last_spte(_iter.old_spte, _iter.level)) \ continue; \ else -#define tdp_mmu_for_each_pte(_iter, _mmu, _start, _end) \ - for_each_tdp_pte(_iter, root_to_sp(_mmu->root.hpa), _start, _end) +#define tdp_mmu_for_each_pte(_iter, _kvm, _root, _start, _end) \ + for_each_tdp_pte(_iter, _kvm, _root, _start, _end) static inline bool __must_check tdp_mmu_iter_need_resched(struct kvm *kvm, struct tdp_iter *iter) @@ -705,10 +844,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - gfn_t end = tdp_mmu_max_gfn_exclusive(); - gfn_t start = 0; - - for_each_tdp_pte_min_level(iter, root, zap_level, start, end) { + for_each_tdp_pte_min_level_all(iter, root, zap_level) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared)) continue; @@ -812,7 +948,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_4K, start, end) { if (can_yield && tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) { flush = false; @@ -863,19 +999,21 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) struct kvm_mmu_page *root; /* - * Zap all roots, including invalid roots, as all SPTEs must be dropped - * before returning to the caller. Zap directly even if the root is - * also being zapped by a worker. Walking zapped top-level SPTEs isn't - * all that expensive and mmu_lock is already held, which means the - * worker has yielded, i.e. flushing the work instead of zapping here - * isn't guaranteed to be any faster. + * Zap all direct roots, including invalid direct roots, as all direct + * SPTEs must be dropped before returning to the caller. For TDX, mirror + * roots don't need handling in response to the mmu notifier (the caller). + * + * Zap directly even if the root is also being zapped by a concurrent + * "fast zap". Walking zapped top-level SPTEs isn't all that expensive + * and mmu_lock is already held, which means the other thread has yielded. * * A TLB flush is unnecessary, KVM zaps everything if and only the VM * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ lockdep_assert_held_write(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root) + __for_each_tdp_mmu_root_yield_safe(kvm, root, -1, + KVM_DIRECT_ROOTS | KVM_INVALID_ROOTS) tdp_mmu_zap_root(kvm, root, false); } @@ -883,11 +1021,14 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * Zap all invalidated roots to ensure all SPTEs are dropped before the "fast * zap" completes. */ -void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) +void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared) { struct kvm_mmu_page *root; - read_lock(&kvm->mmu_lock); + if (shared) + read_lock(&kvm->mmu_lock); + else + write_lock(&kvm->mmu_lock); for_each_tdp_mmu_root_yield_safe(kvm, root) { if (!root->tdp_mmu_scheduled_root_to_zap) @@ -905,7 +1046,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * that may be zapped, as such entries are associated with the * ASID on both VMX and SVM. */ - tdp_mmu_zap_root(kvm, root, true); + tdp_mmu_zap_root(kvm, root, shared); /* * The referenced needs to be put *after* zapping the root, as @@ -915,7 +1056,10 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) kvm_tdp_mmu_put_root(kvm, root); } - read_unlock(&kvm->mmu_lock); + if (shared) + read_unlock(&kvm->mmu_lock); + else + write_unlock(&kvm->mmu_lock); } /* @@ -928,10 +1072,18 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. * See kvm_tdp_mmu_alloc_root(). */ -void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) +void kvm_tdp_mmu_invalidate_roots(struct kvm *kvm, + enum kvm_tdp_mmu_root_types root_types) { struct kvm_mmu_page *root; + /* + * Invalidating invalid roots doesn't make sense, prevent developers from + * having to think about it. + */ + if (WARN_ON_ONCE(root_types & KVM_INVALID_ROOTS)) + root_types &= ~KVM_INVALID_ROOTS; + /* * mmu_lock must be held for write to ensure that a root doesn't become * invalid while there are active readers (invalidating a root while @@ -953,6 +1105,9 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) * or get/put references to roots. */ list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { + if (!tdp_mmu_root_match(root, root_types)) + continue; + /* * Note, invalid roots can outlive a memslot update! Invalid * roots must be *zapped* before the memslot update completes, @@ -985,6 +1140,11 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, if (fault->prefetch && is_shadow_present_pte(iter->old_spte)) return RET_PF_SPURIOUS; + if (is_shadow_present_pte(iter->old_spte) && + is_access_allowed(fault, iter->old_spte) && + is_last_spte(iter->old_spte, iter->level)) + return RET_PF_SPURIOUS; + if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); else @@ -1063,7 +1223,7 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, */ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - struct kvm_mmu *mmu = vcpu->arch.mmu; + struct kvm_mmu_page *root = tdp_mmu_get_root_for_fault(vcpu, fault); struct kvm *kvm = vcpu->kvm; struct tdp_iter iter; struct kvm_mmu_page *sp; @@ -1075,7 +1235,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) rcu_read_lock(); - tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) { + tdp_mmu_for_each_pte(iter, kvm, root, fault->gfn, fault->gfn + 1) { int r; if (fault->nx_huge_page_workaround_enabled) @@ -1102,13 +1262,18 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) */ sp = tdp_mmu_alloc_sp(vcpu); tdp_mmu_init_child_sp(sp, &iter); + if (is_mirror_sp(sp)) + kvm_mmu_alloc_external_spt(vcpu, sp); sp->nx_huge_page_disallowed = fault->huge_page_disallowed; - if (is_shadow_present_pte(iter.old_spte)) + if (is_shadow_present_pte(iter.old_spte)) { + /* Don't support large page for mirrored roots (TDX) */ + KVM_BUG_ON(is_mirror_sptep(iter.sptep), vcpu->kvm); r = tdp_mmu_split_huge_page(kvm, &iter, sp, true); - else + } else { r = tdp_mmu_link_sp(kvm, &iter, sp, true); + } /* * Force the guest to retry if installing an upper level SPTE @@ -1143,12 +1308,16 @@ retry: return ret; } +/* Used by mmu notifier via kvm_unmap_gfn_range() */ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { + enum kvm_tdp_mmu_root_types types; struct kvm_mmu_page *root; - __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) + types = kvm_gfn_range_filter_to_root_types(kvm, range->attr_filter) | KVM_INVALID_ROOTS; + + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, types) flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, range->may_block, flush); @@ -1188,20 +1357,24 @@ static bool __kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool test_only) { + enum kvm_tdp_mmu_root_types types; struct kvm_mmu_page *root; struct tdp_iter iter; bool ret = false; + types = kvm_gfn_range_filter_to_root_types(kvm, range->attr_filter); + /* * Don't support rescheduling, none of the MMU notifiers that funnel * into this helper allow blocking; it'd be dead, wasteful code. Note, * this helper must NOT be used to unmap GFNs, as it processes only * valid roots! */ - for_each_valid_tdp_mmu_root(kvm, root, range->slot->as_id) { + WARN_ON(types & ~KVM_VALID_ROOTS); + __for_each_tdp_mmu_root(kvm, root, range->slot->as_id, types) { guard(rcu)(); - tdp_root_for_each_leaf_pte(iter, root, range->start, range->end) { + tdp_root_for_each_leaf_pte(iter, kvm, root, range->start, range->end) { if (!is_accessed_spte(iter.old_spte)) continue; @@ -1242,7 +1415,7 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL); - for_each_tdp_pte_min_level(iter, root, min_level, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; @@ -1361,7 +1534,7 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm, * level above the target level (e.g. splitting a 1GB to 512 2MB pages, * and then splitting each of those to 512 4KB pages). */ - for_each_tdp_pte_min_level(iter, root, target_level + 1, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, target_level + 1, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared)) continue; @@ -1459,7 +1632,7 @@ static void clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_pte(iter, root, start, end) { + tdp_root_for_each_pte(iter, kvm, root, start, end) { retry: if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) @@ -1507,7 +1680,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask), + tdp_root_for_each_leaf_pte(iter, kvm, root, gfn + __ffs(mask), gfn + BITS_PER_LONG) { if (!mask) break; @@ -1561,7 +1734,7 @@ static int tdp_mmu_make_huge_spte(struct kvm *kvm, gfn_t end = start + KVM_PAGES_PER_HPAGE(parent->level); struct tdp_iter iter; - tdp_root_for_each_leaf_pte(iter, root, start, end) { + tdp_root_for_each_leaf_pte(iter, kvm, root, start, end) { /* * Use the parent iterator when checking for forward progress so * that KVM doesn't get stuck continuously trying to yield (i.e. @@ -1595,7 +1768,7 @@ static void recover_huge_pages_range(struct kvm *kvm, rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_2M, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_2M, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) { flush = false; @@ -1676,7 +1849,7 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, min_level, gfn, gfn + 1) { + for_each_tdp_pte_min_level(iter, kvm, root, min_level, gfn, gfn + 1) { if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) continue; @@ -1724,14 +1897,14 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { + struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); struct tdp_iter iter; - struct kvm_mmu *mmu = vcpu->arch.mmu; gfn_t gfn = addr >> PAGE_SHIFT; int leaf = -1; *root_level = vcpu->arch.mmu->root_role.level; - tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { + tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) { leaf = iter.level; sptes[leaf] = iter.old_spte; } @@ -1753,11 +1926,12 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn, u64 *spte) { + /* Fast pf is not supported for mirrored roots */ + struct kvm_mmu_page *root = tdp_mmu_get_root(vcpu, KVM_DIRECT_ROOTS); struct tdp_iter iter; - struct kvm_mmu *mmu = vcpu->arch.mmu; tdp_ptep_t sptep = NULL; - tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { + tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) { *spte = iter.old_spte; sptep = iter.sptep; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index f03ca0dd13d9..52acf99d40a0 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -10,7 +10,7 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); -int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu); +void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu, bool private); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) { @@ -19,11 +19,56 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root); +enum kvm_tdp_mmu_root_types { + KVM_INVALID_ROOTS = BIT(0), + KVM_DIRECT_ROOTS = BIT(1), + KVM_MIRROR_ROOTS = BIT(2), + KVM_VALID_ROOTS = KVM_DIRECT_ROOTS | KVM_MIRROR_ROOTS, + KVM_ALL_ROOTS = KVM_VALID_ROOTS | KVM_INVALID_ROOTS, +}; + +static inline enum kvm_tdp_mmu_root_types kvm_gfn_range_filter_to_root_types(struct kvm *kvm, + enum kvm_gfn_range_filter process) +{ + enum kvm_tdp_mmu_root_types ret = 0; + + if (!kvm_has_mirrored_tdp(kvm)) + return KVM_DIRECT_ROOTS; + + if (process & KVM_FILTER_PRIVATE) + ret |= KVM_MIRROR_ROOTS; + if (process & KVM_FILTER_SHARED) + ret |= KVM_DIRECT_ROOTS; + + WARN_ON_ONCE(!ret); + + return ret; +} + +static inline struct kvm_mmu_page *tdp_mmu_get_root_for_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + if (unlikely(!kvm_is_addr_direct(vcpu->kvm, fault->addr))) + return root_to_sp(vcpu->arch.mmu->mirror_root_hpa); + + return root_to_sp(vcpu->arch.mmu->root.hpa); +} + +static inline struct kvm_mmu_page *tdp_mmu_get_root(struct kvm_vcpu *vcpu, + enum kvm_tdp_mmu_root_types type) +{ + if (unlikely(type == KVM_MIRROR_ROOTS)) + return root_to_sp(vcpu->arch.mmu->mirror_root_hpa); + + return root_to_sp(vcpu->arch.mmu->root.hpa); +} + bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); -void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); -void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm); +void kvm_tdp_mmu_invalidate_roots(struct kvm *kvm, + enum kvm_tdp_mmu_root_types root_types); +void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared); int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 47a46283c866..75e9cfc689f8 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -797,7 +797,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); kvm_pmu_call(init)(vcpu); - kvm_pmu_refresh(vcpu); } /* Release perf_events for vPMCs that have been unused for a full time slice. */ diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index e46220ece83c..fde0ae986003 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -6,23 +6,6 @@ #include #include -/* - * Hardware-defined CPUID leafs that are either scattered by the kernel or are - * unknown to the kernel, but need to be directly used by KVM. Note, these - * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. - */ -enum kvm_only_cpuid_leafs { - CPUID_12_EAX = NCAPINTS, - CPUID_7_1_EDX, - CPUID_8000_0007_EDX, - CPUID_8000_0022_EAX, - CPUID_7_2_EDX, - CPUID_24_0_EBX, - NR_KVM_CPU_CAPS, - - NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, -}; - /* * Define a KVM-only feature flag. * @@ -145,7 +128,10 @@ static __always_inline u32 __feature_translate(int x86_feature) static __always_inline u32 __feature_leaf(int x86_feature) { - return __feature_translate(x86_feature) / 32; + u32 x86_leaf = __feature_translate(x86_feature) / 32; + + reverse_cpuid_check(x86_leaf); + return x86_leaf; } /* @@ -168,7 +154,6 @@ static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned int x86_featu { unsigned int x86_leaf = __feature_leaf(x86_feature); - reverse_cpuid_check(x86_leaf); return reverse_cpuid[x86_leaf]; } diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index 85241c0c7f56..e0ab7df27b66 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -283,7 +283,7 @@ void enter_smm(struct kvm_vcpu *vcpu) memset(smram.bytes, 0, sizeof(smram.bytes)); #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) enter_smm_save_state_64(vcpu, &smram.smram64); else #endif @@ -353,7 +353,7 @@ void enter_smm(struct kvm_vcpu *vcpu) kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) if (kvm_x86_call(set_efer)(vcpu, 0)) goto error; #endif @@ -586,7 +586,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) * supports long mode. */ #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) { struct kvm_segment cs_desc; unsigned long cr4; @@ -609,7 +609,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) kvm_set_cr0(vcpu, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) { unsigned long cr4, efer; /* Clear CR4.PAE before clearing EFER.LME. */ @@ -634,7 +634,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) return X86EMUL_UNHANDLEABLE; #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) ret = rsm_load_state_64(ctxt, &smram.smram64); else #endif diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 4b74ea91f4e6..65fd245a9953 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -1199,6 +1199,12 @@ bool avic_hardware_setup(void) return false; } + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !boot_cpu_has(X86_FEATURE_HV_INUSE_WR_ALLOWED)) { + pr_warn("AVIC disabled: missing HvInUseWrAllowed on SNP-enabled system\n"); + return false; + } + if (boot_cpu_has(X86_FEATURE_AVIC)) { pr_info("AVIC enabled\n"); } else if (force_avic) { diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index b708bdf7eaff..d77b094d9a4d 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -111,7 +111,7 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) static bool nested_vmcb_needs_vls_intercept(struct vcpu_svm *svm) { - if (!guest_can_use(&svm->vcpu, X86_FEATURE_V_VMSAVE_VMLOAD)) + if (!guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_V_VMSAVE_VMLOAD)) return true; if (!nested_npt_enabled(svm)) @@ -594,7 +594,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 vmcb_mark_dirty(vmcb02, VMCB_DR); } - if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { /* * Reserved bits of DEBUGCTL are ignored. Be consistent with @@ -651,7 +651,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes. */ - if (guest_can_use(vcpu, X86_FEATURE_VGIF) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VGIF) && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK)) int_ctl_vmcb12_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK); else @@ -689,7 +689,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.tsc_offset = vcpu->arch.tsc_offset; - if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR) && svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) nested_svm_update_tsc_ratio_msr(vcpu); @@ -710,7 +710,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, * what a nrips=0 CPU would do (L1 is responsible for advancing RIP * prior to injecting the event). */ - if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS)) vmcb02->control.next_rip = svm->nested.ctl.next_rip; else if (boot_cpu_has(X86_FEATURE_NRIPS)) vmcb02->control.next_rip = vmcb12_rip; @@ -720,7 +720,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, svm->soft_int_injected = true; svm->soft_int_csbase = vmcb12_csbase; svm->soft_int_old_rip = vmcb12_rip; - if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS)) svm->soft_int_next_rip = svm->nested.ctl.next_rip; else svm->soft_int_next_rip = vmcb12_rip; @@ -728,18 +728,18 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.virt_ext = vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK; - if (guest_can_use(vcpu, X86_FEATURE_LBRV)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV)) vmcb02->control.virt_ext |= (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK); if (!nested_vmcb_needs_vls_intercept(svm)) vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; - if (guest_can_use(vcpu, X86_FEATURE_PAUSEFILTER)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_PAUSEFILTER)) pause_count12 = svm->nested.ctl.pause_filter_count; else pause_count12 = 0; - if (guest_can_use(vcpu, X86_FEATURE_PFTHRESHOLD)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_PFTHRESHOLD)) pause_thresh12 = svm->nested.ctl.pause_filter_thresh; else pause_thresh12 = 0; @@ -1026,7 +1026,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (vmcb12->control.exit_code != SVM_EXIT_ERR) nested_save_pending_event_to_vmcb12(svm, vmcb12); - if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS)) vmcb12->control.next_rip = vmcb02->control.next_rip; vmcb12->control.int_ctl = svm->nested.ctl.int_ctl; @@ -1065,7 +1065,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (!nested_exit_on_intr(svm)) kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); - if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { svm_copy_lbrs(vmcb12, vmcb02); svm_update_lbrv(vcpu); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 22d5a65b410c..288f7f2a46f2 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -46,7 +46,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, switch (msr) { case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: - if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE)) return NULL; /* * Each PMU counter has a pair of CTL and CTR MSRs. CTLn @@ -109,7 +109,7 @@ static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) case MSR_K7_EVNTSEL0 ... MSR_K7_PERFCTR3: return pmu->version > 0; case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: - return guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE); + return guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE); case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS: case MSR_AMD64_PERF_CNTR_GLOBAL_CTL: case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR: @@ -179,7 +179,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) union cpuid_0x80000022_ebx ebx; pmu->version = 1; - if (guest_cpuid_has(vcpu, X86_FEATURE_PERFMON_V2)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFMON_V2)) { pmu->version = 2; /* * Note, PERFMON_V2 is also in 0x80000022.0x0, i.e. the guest @@ -189,7 +189,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) x86_feature_cpuid(X86_FEATURE_PERFMON_V2).index); ebx.full = kvm_find_cpuid_entry_index(vcpu, 0x80000022, 0)->ebx; pmu->nr_arch_gp_counters = ebx.split.num_core_pmc; - } else if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) { + } else if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE)) { pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS_CORE; } else { pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 943bd074a5d3..a2a794c32050 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -3051,11 +3051,11 @@ out: min_sev_asid, max_sev_asid); if (boot_cpu_has(X86_FEATURE_SEV_ES)) pr_info("SEV-ES %s (ASIDs %u - %u)\n", - sev_es_supported ? "enabled" : "disabled", + str_enabled_disabled(sev_es_supported), min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1); if (boot_cpu_has(X86_FEATURE_SEV_SNP)) pr_info("SEV-SNP %s (ASIDs %u - %u)\n", - sev_snp_supported ? "enabled" : "disabled", + str_enabled_disabled(sev_snp_supported), min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1); sev_enabled = sev_supported; @@ -3627,13 +3627,20 @@ static int snp_begin_psc_msr(struct vcpu_svm *svm, u64 ghcb_msr) return 1; /* resume guest */ } - if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) { + if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) { set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR); return 1; /* resume guest */ } vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + /* + * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2) + * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that + * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting + * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU. + */ + vcpu->run->hypercall.ret = 0; vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = 1; vcpu->run->hypercall.args[2] = (op == SNP_PAGE_STATE_PRIVATE) @@ -3710,7 +3717,7 @@ static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc) bool huge; u64 gfn; - if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) { + if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) { snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC); return 1; } @@ -3797,6 +3804,13 @@ next_range: case VMGEXIT_PSC_OP_SHARED: vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + /* + * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2) + * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that + * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting + * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU. + */ + vcpu->run->hypercall.ret = 0; vcpu->run->hypercall.args[0] = gfn_to_gpa(gfn); vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = entry_start.operation == VMGEXIT_PSC_OP_PRIVATE @@ -3820,7 +3834,7 @@ next_range: goto next_range; } - unreachable(); + BUG(); } static int __sev_snp_update_protected_guest_state(struct kvm_vcpu *vcpu) @@ -4435,8 +4449,8 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { - bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + bool v_tsc_aux = guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID); set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); } @@ -4445,16 +4459,15 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if * the host/guest supports its use. * - * guest_can_use() checks a number of requirements on the host/guest to - * ensure that MSR_IA32_XSS is available, but it might report true even - * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host - * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better - * to further check that the guest CPUID actually supports - * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved - * guests will still get intercepted and caught in the normal - * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths. + * KVM treats the guest as being capable of using XSAVES even if XSAVES + * isn't enabled in guest CPUID as there is no intercept for XSAVES, + * i.e. the guest can use XSAVES/XRSTOR to read/write XSS if XSAVE is + * exposed to the guest and XSAVES is supported in hardware. Condition + * full XSS passthrough on the guest being able to use XSAVES *and* + * XSAVES being exposed to the guest so that KVM can at least honor + * guest CPUID for RDMSR and WRMSR. */ - if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1); else diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index dd15cc635655..7640a84e554a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -284,8 +285,6 @@ u32 svm_msrpm_offset(u32 msr) return MSR_INVALID; } -static void svm_flush_tlb_current(struct kvm_vcpu *vcpu); - static int get_npt_level(void) { #ifdef CONFIG_X86_64 @@ -1049,7 +1048,7 @@ void svm_update_lbrv(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK; bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) || - (is_guest_mode(vcpu) && guest_can_use(vcpu, X86_FEATURE_LBRV) && + (is_guest_mode(vcpu) && guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)); if (enable_lbrv == current_enable_lbrv) @@ -1187,14 +1186,14 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, */ if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) { if (!npt_enabled || - !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID)) + !guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_INVPCID)) svm_set_intercept(svm, INTERCEPT_INVPCID); else svm_clr_intercept(svm, INTERCEPT_INVPCID); } if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) { - if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP)) svm_clr_intercept(svm, INTERCEPT_RDTSCP); else svm_set_intercept(svm, INTERCEPT_RDTSCP); @@ -1921,9 +1920,6 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE; unsigned long old_cr4 = vcpu->arch.cr4; - if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) - svm_flush_tlb_current(vcpu); - vcpu->arch.cr4 = cr4; if (!npt_enabled) { cr4 |= X86_CR4_PAE; @@ -2864,7 +2860,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr_info->index) { case MSR_AMD64_TSC_RATIO: if (!msr_info->host_initiated && - !guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR)) return 1; msr_info->data = svm->tsc_ratio_msr; break; @@ -2940,7 +2936,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_VIRT_SSBD)) return 1; msr_info->data = svm->virt_spec_ctrl; @@ -3024,7 +3020,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) switch (ecx) { case MSR_AMD64_TSC_RATIO: - if (!guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) { + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR)) { if (!msr->host_initiated) return 1; @@ -3046,7 +3042,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->tsc_ratio_msr = data; - if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR) && is_guest_mode(vcpu)) nested_svm_update_tsc_ratio_msr(vcpu); @@ -3091,7 +3087,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_VIRT_SSBD)) return 1; if (data & ~SPEC_CTRL_SSBD) @@ -3201,15 +3197,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & ~supported_de_cfg) return 1; - /* - * Don't let the guest change the host-programmed value. The - * MSR is very model specific, i.e. contains multiple bits that - * are completely unknown to KVM, and the one bit known to KVM - * is simply a reflection of hardware capabilities. - */ - if (!msr->host_initiated && data != svm->msr_decfg) - return 1; - svm->msr_decfg = data; break; } @@ -3272,7 +3259,7 @@ static int invpcid_interception(struct kvm_vcpu *vcpu) unsigned long type; gva_t gva; - if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -3542,6 +3529,21 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, *error_code = 0; } +static void svm_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, + u32 *error_code) +{ + struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control; + + *intr_info = control->event_inj; + + if ((*intr_info & SVM_EXITINTINFO_VALID) && + (*intr_info & SVM_EXITINTINFO_VALID_ERR)) + *error_code = control->event_inj_err; + else + *error_code = 0; + +} + static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4401,27 +4403,17 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) * XSS on VM-Enter/VM-Exit. Failure to do so would effectively give * the guest read/write access to the host's XSS. */ - if (boot_cpu_has(X86_FEATURE_XSAVE) && - boot_cpu_has(X86_FEATURE_XSAVES) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVE)) - kvm_governed_feature_set(vcpu, X86_FEATURE_XSAVES); - - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_NRIPS); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_TSCRATEMSR); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LBRV); + guest_cpu_cap_change(vcpu, X86_FEATURE_XSAVES, + boot_cpu_has(X86_FEATURE_XSAVES) && + guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE)); /* * Intercept VMLOAD if the vCPU model is Intel in order to emulate that * VMLOAD drops bits 63:32 of SYSENTER (ignoring the fact that exposing * SVM on Intel is bonkers and extremely unlikely to work). */ - if (!guest_cpuid_is_intel_compatible(vcpu)) - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD); - - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PAUSEFILTER); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PFTHRESHOLD); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VGIF); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VNMI); + if (guest_cpuid_is_intel_compatible(vcpu)) + guest_cpu_cap_clear(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD); svm_recalc_instruction_intercepts(vcpu, svm); @@ -4431,7 +4423,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0, - !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); + !!guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); if (sev_guest(vcpu->kvm)) sev_vcpu_after_set_cpuid(svm); @@ -4682,7 +4674,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) * responsible for ensuring nested SVM and SMIs are mutually exclusive. */ - if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return 1; smram->smram64.svm_guest_flag = 1; @@ -4729,14 +4721,14 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) const struct kvm_smram_state_64 *smram64 = &smram->smram64; - if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return 0; /* Non-zero if SMI arrived while vCPU was in guest mode. */ if (!smram64->svm_guest_flag) return 0; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SVM)) return 1; if (!(smram64->efer & EFER_SVME)) @@ -4799,9 +4791,15 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) { + struct vcpu_svm *svm = to_svm(vcpu); bool smep, smap, is_user; u64 error_code; + /* Check that emulation is possible during event vectoring */ + if ((svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK) && + !kvm_can_emulate_event_vectoring(emul_type)) + return X86EMUL_UNHANDLEABLE_VECTORING; + /* Emulation is always possible when KVM has access to all guest state. */ if (!sev_guest(vcpu->kvm)) return X86EMUL_CONTINUE; @@ -4898,7 +4896,7 @@ static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * In addition, don't apply the erratum workaround if the #NPF occurred * while translating guest page tables (see below). */ - error_code = to_svm(vcpu)->vmcb->control.exit_info_1; + error_code = svm->vmcb->control.exit_info_1; if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK)) goto resume_guest; @@ -5086,6 +5084,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .required_apicv_inhibits = AVIC_REQUIRED_APICV_INHIBITS, .get_exit_info = svm_get_exit_info, + .get_entry_info = svm_get_entry_info, .vcpu_after_set_cpuid = svm_vcpu_after_set_cpuid, @@ -5337,7 +5336,7 @@ static __init int svm_hardware_setup(void) /* Force VM NPT level equal to the host's paging level */ kvm_configure_mmu(npt_enabled, get_npt_level(), get_npt_level(), PG_LEVEL_1G); - pr_info("Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); + pr_info("Nested Paging %s\n", str_enabled_disabled(npt_enabled)); /* Setup shadow_me_value and shadow_me_mask */ kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 43fa6a16eb19..9d7cdb8fbf87 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -358,39 +358,32 @@ static __always_inline struct kvm_sev_info *to_kvm_sev_info(struct kvm *kvm) return &to_kvm_svm(kvm)->sev_info; } +#ifdef CONFIG_KVM_AMD_SEV static __always_inline bool sev_guest(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return sev->active; -#else - return false; -#endif } - static __always_inline bool sev_es_guest(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return sev->es_active && !WARN_ON_ONCE(!sev->active); -#else - return false; -#endif } static __always_inline bool sev_snp_guest(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return (sev->vmsa_features & SVM_SEV_FEAT_SNP_ACTIVE) && !WARN_ON_ONCE(!sev_es_guest(kvm)); -#else - return false; -#endif } +#else +#define sev_guest(kvm) false +#define sev_es_guest(kvm) false +#define sev_snp_guest(kvm) false +#endif static inline bool ghcb_gpa_is_registered(struct vcpu_svm *svm, u64 val) { @@ -502,7 +495,7 @@ static inline bool svm_is_intercept(struct vcpu_svm *svm, int bit) static inline bool nested_vgif_enabled(struct vcpu_svm *svm) { - return guest_can_use(&svm->vcpu, X86_FEATURE_VGIF) && + return guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_VGIF) && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK); } @@ -554,7 +547,7 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm) static inline bool nested_vnmi_enabled(struct vcpu_svm *svm) { - return guest_can_use(&svm->vcpu, X86_FEATURE_VNMI) && + return guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_VNMI) && (svm->nested.ctl.int_ctl & V_NMI_ENABLE_MASK); } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index d3aeffd6ae75..0b844cb97978 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -22,15 +22,22 @@ TRACE_EVENT(kvm_entry, __field( unsigned int, vcpu_id ) __field( unsigned long, rip ) __field( bool, immediate_exit ) + __field( u32, intr_info ) + __field( u32, error_code ) ), TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; __entry->rip = kvm_rip_read(vcpu); __entry->immediate_exit = force_immediate_exit; + + kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info, + &__entry->error_code); ), - TP_printk("vcpu %u, rip 0x%lx%s", __entry->vcpu_id, __entry->rip, + TP_printk("vcpu %u, rip 0x%lx intr_info 0x%08x error_code 0x%08x%s", + __entry->vcpu_id, __entry->rip, + __entry->intr_info, __entry->error_code, __entry->immediate_exit ? "[immediate exit]" : "") ); @@ -308,12 +315,14 @@ TRACE_EVENT(name, \ __field( u32, intr_info ) \ __field( u32, error_code ) \ __field( unsigned int, vcpu_id ) \ + __field( u64, requests ) \ ), \ \ TP_fast_assign( \ __entry->guest_rip = kvm_rip_read(vcpu); \ __entry->isa = isa; \ __entry->vcpu_id = vcpu->vcpu_id; \ + __entry->requests = READ_ONCE(vcpu->requests); \ kvm_x86_call(get_exit_info)(vcpu, \ &__entry->exit_reason, \ &__entry->info1, \ @@ -323,11 +332,13 @@ TRACE_EVENT(name, \ ), \ \ TP_printk("vcpu %u reason %s%s%s rip 0x%lx info1 0x%016llx " \ - "info2 0x%016llx intr_info 0x%08x error_code 0x%08x", \ + "info2 0x%016llx intr_info 0x%08x error_code 0x%08x " \ + "requests 0x%016llx", \ __entry->vcpu_id, \ kvm_print_exit_reason(__entry->exit_reason, __entry->isa), \ __entry->guest_rip, __entry->info1, __entry->info2, \ - __entry->intr_info, __entry->error_code) \ + __entry->intr_info, __entry->error_code, \ + __entry->requests) \ ) /* diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index a87407412615..11a339009781 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -42,7 +42,7 @@ static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) return vmx->nested.hv_evmcs; } -static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) +static inline bool guest_cpu_cap_has_evmcs(struct kvm_vcpu *vcpu) { /* * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.h b/arch/x86/kvm/vmx/hyperv_evmcs.h index a543fccfc574..6536290f4274 100644 --- a/arch/x86/kvm/vmx/hyperv_evmcs.h +++ b/arch/x86/kvm/vmx/hyperv_evmcs.h @@ -6,7 +6,7 @@ #ifndef __KVM_X86_VMX_HYPERV_EVMCS_H #define __KVM_X86_VMX_HYPERV_EVMCS_H -#include +#include #include "capabilities.h" #include "vmcs12.h" diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 92d35cc6cd15..2427f918e763 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -100,7 +100,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .load_eoi_exitmap = vmx_load_eoi_exitmap, .apicv_pre_state_restore = vmx_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, - .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .sync_pir_to_irr = vmx_sync_pir_to_irr, .deliver_interrupt = vmx_deliver_interrupt, @@ -111,6 +110,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .get_mt_mask = vmx_get_mt_mask, .get_exit_info = vmx_get_exit_info, + .get_entry_info = vmx_get_entry_info, .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid, @@ -126,7 +126,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .check_intercept = vmx_check_intercept, .handle_exit_irqoff = vmx_handle_exit_irqoff, - .cpu_dirty_log_size = PML_ENTITY_NUM, + .cpu_dirty_log_size = PML_LOG_NR_ENTRIES, .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, .nested_ops = &vmx_nested_ops, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index aa78b6f38dfe..8a7af02d466e 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -257,7 +257,7 @@ static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr) * state. It is possible that the area will stay mapped as * vmx->nested.hv_evmcs but this shouldn't be a problem. */ - if (!guest_cpuid_has_evmcs(vcpu) || + if (!guest_cpu_cap_has_evmcs(vcpu) || !evmptr_is_valid(nested_get_evmptr(vcpu))) return false; @@ -2089,7 +2089,7 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( bool evmcs_gpa_changed = false; u64 evmcs_gpa; - if (likely(!guest_cpuid_has_evmcs(vcpu))) + if (likely(!guest_cpu_cap_has_evmcs(vcpu))) return EVMPTRLD_DISABLED; evmcs_gpa = nested_get_evmptr(vcpu); @@ -2992,7 +2992,7 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, return -EINVAL; #ifdef CONFIG_KVM_HYPERV - if (guest_cpuid_has_evmcs(vcpu)) + if (guest_cpu_cap_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); #endif @@ -3287,7 +3287,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) * L2 was running), map it here to make sure vmcs12 changes are * properly reflected. */ - if (guest_cpuid_has_evmcs(vcpu) && + if (guest_cpu_cap_has_evmcs(vcpu) && vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) { enum nested_evmptrld_status evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, false); @@ -3442,7 +3442,7 @@ static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) if (!nested_cpu_has_pml(vmcs12)) return 0; - if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) { + if (vmcs12->guest_pml_index >= PML_LOG_NR_ENTRIES) { vmx->nested.pml_full = true; return 1; } @@ -3481,14 +3481,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) return 1; } -static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu) -{ - u8 rvi = vmx_get_rvi(); - u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI); - - return ((rvi & 0xf0) > (vppr & 0xf0)); -} - static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); @@ -3508,7 +3500,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); enum vm_entry_failure_code entry_failure_code; - bool evaluate_pending_interrupts; union vmx_exit_reason exit_reason = { .basic = EXIT_REASON_INVALID_STATE, .failed_vmentry = 1, @@ -3527,13 +3518,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, kvm_service_local_tlb_flush_requests(vcpu); - evaluate_pending_interrupts = exec_controls_get(vmx) & - (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); - if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) - evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); - if (!evaluate_pending_interrupts) - evaluate_pending_interrupts |= kvm_apic_has_pending_init_or_sipi(vcpu); - if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); @@ -3616,9 +3600,13 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit - * unconditionally. + * unconditionally. Take care to pull data from vmcs01 as appropriate, + * e.g. when checking for interrupt windows, as vmcs02 is now loaded. */ - if (unlikely(evaluate_pending_interrupts)) + if ((__exec_controls_get(&vmx->vmcs01) & (CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING)) || + kvm_apic_has_pending_init_or_sipi(vcpu) || + kvm_apic_has_interrupt(vcpu)) kvm_make_request(KVM_REQ_EVENT, vcpu); /* @@ -3751,14 +3739,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (unlikely(status != NVMX_VMENTRY_SUCCESS)) goto vmentry_failed; - /* Emulate processing of posted interrupts on VM-Enter. */ - if (nested_cpu_has_posted_intr(vmcs12) && - kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) { - vmx->nested.pi_pending = true; - kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv); - } - /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; @@ -4220,13 +4200,25 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) */ bool block_nested_exceptions = vmx->nested.nested_run_pending; /* - * New events (not exceptions) are only recognized at instruction + * Events that don't require injection, i.e. that are virtualized by + * hardware, aren't blocked by a pending VM-Enter as KVM doesn't need + * to regain control in order to deliver the event, and hardware will + * handle event ordering, e.g. with respect to injected exceptions. + * + * But, new events (not exceptions) are only recognized at instruction * boundaries. If an event needs reinjection, then KVM is handling a - * VM-Exit that occurred _during_ instruction execution; new events are - * blocked until the instruction completes. + * VM-Exit that occurred _during_ instruction execution; new events, + * irrespective of whether or not they're injected, are blocked until + * the instruction completes. + */ + bool block_non_injected_events = kvm_event_needs_reinjection(vcpu); + /* + * Inject events are blocked by nested VM-Enter, as KVM is responsible + * for managing priority between concurrent events, i.e. KVM needs to + * wait until after VM-Enter completes to deliver injected events. */ bool block_nested_events = block_nested_exceptions || - kvm_event_needs_reinjection(vcpu); + block_non_injected_events; if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { @@ -4338,18 +4330,26 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) { int irq; - if (block_nested_events) - return -EBUSY; - if (!nested_exit_on_intr(vcpu)) + if (!nested_exit_on_intr(vcpu)) { + if (block_nested_events) + return -EBUSY; + goto no_vmexit; + } if (!nested_exit_intr_ack_set(vcpu)) { + if (block_nested_events) + return -EBUSY; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); return 0; } irq = kvm_cpu_get_extint(vcpu); if (irq != -1) { + if (block_nested_events) + return -EBUSY; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); return 0; @@ -4368,11 +4368,22 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) * and enabling posted interrupts requires ACK-on-exit. */ if (irq == vmx->nested.posted_intr_nv) { + /* + * Nested posted interrupts are delivered via RVI, i.e. + * aren't injected by KVM, and so can be queued even if + * manual event injection is disallowed. + */ + if (block_non_injected_events) + return -EBUSY; + vmx->nested.pi_pending = true; kvm_apic_clear_irr(vcpu, irq); goto no_vmexit; } + if (block_nested_events) + return -EBUSY; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); @@ -5015,7 +5026,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, * doesn't isolate different VMCSs, i.e. in this case, doesn't provide * separate modes for L2 vs L1. */ - if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL)) indirect_branch_prediction_barrier(); /* Update any VMCS fields that might have changed while L2 ran */ @@ -5050,6 +5061,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } + if (vmx->nested.update_vmcs01_hwapic_isr) { + vmx->nested.update_vmcs01_hwapic_isr = false; + kvm_apic_update_hwapic_isr(vcpu); + } + if ((vm_exit_reason != -1) && (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))) vmx->nested.need_vmcs12_to_shadow_sync = true; @@ -6279,7 +6295,7 @@ static bool nested_vmx_exit_handled_encls(struct kvm_vcpu *vcpu, { u32 encls_leaf; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SGX) || + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) || !nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENCLS_EXITING)) return false; @@ -6617,7 +6633,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, vmx = to_vmx(vcpu); vmcs12 = get_vmcs12(vcpu); - if (guest_can_use(vcpu, X86_FEATURE_VMX) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) && (vmx->nested.vmxon || vmx->nested.smm.vmxon)) { kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr; kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr; @@ -6758,7 +6774,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS) return -EINVAL; } else { - if (!guest_can_use(vcpu, X86_FEATURE_VMX)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return -EINVAL; if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa)) @@ -6792,7 +6808,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) && - (!guest_can_use(vcpu, X86_FEATURE_VMX) || + (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) || !vmx->nested.enlightened_vmcs_enabled)) return -EINVAL; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 9c9d4a336166..77012b2eca0e 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -110,7 +110,7 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, static inline u64 vcpu_get_perf_capabilities(struct kvm_vcpu *vcpu) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) return 0; return vcpu->arch.perf_capabilities; @@ -160,7 +160,7 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) ret = vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PEBS_FORMAT; break; case MSR_IA32_DS_AREA: - ret = guest_cpuid_has(vcpu, X86_FEATURE_DS); + ret = guest_cpu_cap_has(vcpu, X86_FEATURE_DS); break; case MSR_PEBS_DATA_CFG: perf_capabilities = vcpu_get_perf_capabilities(vcpu); diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 1715d2ab07be..ad9116a99bcc 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -2,7 +2,7 @@ #ifndef __KVM_X86_VMX_POSTED_INTR_H #define __KVM_X86_VMX_POSTED_INTR_H -#include +#include #include void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index b352a3ba7354..9961e07cf071 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -122,7 +122,7 @@ static int sgx_inject_fault(struct kvm_vcpu *vcpu, gva_t gva, int trapnr) * likely than a bad userspace address. */ if ((trapnr == PF_VECTOR || !boot_cpu_has(X86_FEATURE_SGX2)) && - guest_cpuid_has(vcpu, X86_FEATURE_SGX2)) { + guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2)) { memset(&ex, 0, sizeof(ex)); ex.vector = PF_VECTOR; ex.error_code = PFERR_PRESENT_MASK | PFERR_WRITE_MASK | @@ -365,7 +365,7 @@ static inline bool encls_leaf_enabled_in_guest(struct kvm_vcpu *vcpu, u32 leaf) return true; if (leaf >= EAUG && leaf <= EMODT) - return guest_cpuid_has(vcpu, X86_FEATURE_SGX2); + return guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2); return false; } @@ -381,8 +381,8 @@ int handle_encls(struct kvm_vcpu *vcpu) { u32 leaf = (u32)kvm_rax_read(vcpu); - if (!enable_sgx || !guest_cpuid_has(vcpu, X86_FEATURE_SGX) || - !guest_cpuid_has(vcpu, X86_FEATURE_SGX1)) { + if (!enable_sgx || !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) || + !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX1)) { kvm_queue_exception(vcpu, UD_VECTOR); } else if (!encls_leaf_enabled_in_guest(vcpu, leaf) || !sgx_enabled_in_guest_bios(vcpu) || !is_paging(vcpu)) { @@ -479,15 +479,15 @@ void vmx_write_encls_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (!cpu_has_vmx_encls_vmexit()) return; - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) && sgx_enabled_in_guest_bios(vcpu)) { - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX1)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX1)) { bitmap &= ~GENMASK_ULL(ETRACK, ECREATE); if (sgx_intercept_encls_ecreate(vcpu)) bitmap |= (1 << ECREATE); } - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX2)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2)) bitmap &= ~GENMASK_ULL(EMODT, EAUG); /* diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 893366e53732..f72835e85b6d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1636,7 +1636,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) * result in a #GP unless the same write also clears TraceEn. */ if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) && - ((vmx->pt_desc.guest.ctl ^ data) & ~RTIT_CTL_TRACEEN)) + (data & RTIT_CTL_TRACEEN) && + data != vmx->pt_desc.guest.ctl) return 1; /* @@ -1705,6 +1706,12 @@ int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, kvm_queue_exception(vcpu, UD_VECTOR); return X86EMUL_PROPAGATE_FAULT; } + + /* Check that emulation is possible during event vectoring */ + if ((to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && + !kvm_can_emulate_event_vectoring(emul_type)) + return X86EMUL_UNHANDLEABLE_VECTORING; + return X86EMUL_CONTINUE; } @@ -1908,8 +1915,8 @@ static void vmx_setup_uret_msrs(struct vcpu_vmx *vmx) vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); vmx_setup_uret_msr(vmx, MSR_TSC_AUX, - guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)); + guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDPID)); /* * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new @@ -2062,7 +2069,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; @@ -2078,13 +2085,13 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) return 1; msr_info->data = to_vmx(vcpu)->msr_ia32_sgxlepubkeyhash [msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0]; break; case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: - if (!guest_can_use(vcpu, X86_FEATURE_VMX)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) @@ -2097,7 +2104,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * sanity checking and refuse to boot. Filter all unsupported * features out. */ - if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) + if (!msr_info->host_initiated && guest_cpu_cap_has_evmcs(vcpu)) nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); #endif @@ -2167,7 +2174,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, u64 data) { #ifdef CONFIG_X86_64 - if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return (u32)data; #endif return (unsigned long)data; @@ -2178,7 +2185,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated u64 debugctl = 0; if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && - (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) + (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) && @@ -2282,7 +2289,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) || (data & MSR_IA32_BNDCFGS_RSVD)) @@ -2384,7 +2391,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * behavior, but it's close enough. */ if (!msr_info->host_initiated && - (!guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC) || + (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC) || ((vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED) && !(vmx->msr_ia32_feature_control & FEAT_CTL_SGX_LC_ENABLED)))) return 1; @@ -2394,7 +2401,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!msr_info->host_initiated) return 1; /* they are read-only */ - if (!guest_can_use(vcpu, X86_FEATURE_VMX)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: @@ -2468,9 +2475,9 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((data & PERF_CAP_PEBS_MASK) != (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK)) return 1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_DS)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DS)) return 1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_DTES64)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DTES64)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; @@ -4590,10 +4597,7 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, bool __enabled; \ \ if (cpu_has_vmx_##name()) { \ - if (kvm_is_governed_feature(X86_FEATURE_##feat_name)) \ - __enabled = guest_can_use(__vcpu, X86_FEATURE_##feat_name); \ - else \ - __enabled = guest_cpuid_has(__vcpu, X86_FEATURE_##feat_name); \ + __enabled = guest_cpu_cap_has(__vcpu, X86_FEATURE_##feat_name); \ vmx_adjust_secondary_exec_control(vmx, exec_control, SECONDARY_EXEC_##ctrl_name,\ __enabled, exiting); \ } \ @@ -4669,8 +4673,8 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) */ if (cpu_has_vmx_rdtscp()) { bool rdpid_or_rdtscp_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID); vmx_adjust_secondary_exec_control(vmx, &exec_control, SECONDARY_EXEC_ENABLE_RDTSCP, @@ -4820,7 +4824,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) if (enable_pml) { vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } vmx_write_encls_bitmap(&vmx->vcpu, NULL); @@ -5959,7 +5963,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) } operand; int gpr_index; - if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -6049,7 +6053,7 @@ static int handle_preemption_timer(struct kvm_vcpu *vcpu) /* * When nested=0, all VMX instruction VM Exits filter here. The handlers - * are overwritten by nested_vmx_setup() when nested=1. + * are overwritten by nested_vmx_hardware_setup() when nested=1. */ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) { @@ -6191,6 +6195,15 @@ void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, } } +void vmx_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code) +{ + *intr_info = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); + if (is_exception_with_error_code(*intr_info)) + *error_code = vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE); + else + *error_code = 0; +} + static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { if (vmx->pml_pg) { @@ -6202,32 +6215,40 @@ static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + u16 pml_idx, pml_tail_index; u64 *pml_buf; - u16 pml_idx; + int i; pml_idx = vmcs_read16(GUEST_PML_INDEX); /* Do nothing if PML buffer is empty */ - if (pml_idx == (PML_ENTITY_NUM - 1)) + if (pml_idx == PML_HEAD_INDEX) return; + /* + * PML index always points to the next available PML buffer entity + * unless PML log has just overflowed. + */ + pml_tail_index = (pml_idx >= PML_LOG_NR_ENTRIES) ? 0 : pml_idx + 1; - /* PML index always points to next available PML buffer entity */ - if (pml_idx >= PML_ENTITY_NUM) - pml_idx = 0; - else - pml_idx++; - + /* + * PML log is written backwards: the CPU first writes the entry 511 + * then the entry 510, and so on. + * + * Read the entries in the same order they were written, to ensure that + * the dirty ring is filled in the same order the CPU wrote them. + */ pml_buf = page_address(vmx->pml_pg); - for (; pml_idx < PML_ENTITY_NUM; pml_idx++) { + + for (i = PML_HEAD_INDEX; i >= pml_tail_index; i--) { u64 gpa; - gpa = pml_buf[pml_idx]; + gpa = pml_buf[i]; WARN_ON(gpa & (PAGE_SIZE - 1)); kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } static void vmx_dump_sel(char *name, uint32_t sel) @@ -6543,33 +6564,15 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - /* - * Note: - * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by - * delivery event since it indicates guest is accessing MMIO. - * The vm-exit can be triggered again after return to guest that - * will cause infinite loop. - */ if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason.basic != EXIT_REASON_EXCEPTION_NMI && exit_reason.basic != EXIT_REASON_EPT_VIOLATION && exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && exit_reason.basic != EXIT_REASON_TASK_SWITCH && - exit_reason.basic != EXIT_REASON_NOTIFY)) { - int ndata = 3; - - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.data[0] = vectoring_info; - vcpu->run->internal.data[1] = exit_reason.full; - vcpu->run->internal.data[2] = vmx_get_exit_qual(vcpu); - if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { - vcpu->run->internal.data[ndata++] = - vmcs_read64(GUEST_PHYSICAL_ADDRESS); - } - vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; - vcpu->run->internal.ndata = ndata; + exit_reason.basic != EXIT_REASON_NOTIFY && + exit_reason.basic != EXIT_REASON_EPT_MISCONFIG)) { + kvm_prepare_event_vectoring_exit(vcpu, INVALID_GPA); return 0; } @@ -6862,11 +6865,32 @@ void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) read_unlock(&vcpu->kvm->mmu_lock); } -void vmx_hwapic_isr_update(int max_isr) +void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { u16 status; u8 old; + /* + * If L2 is active, defer the SVI update until vmcs01 is loaded, as SVI + * is only relevant for if and only if Virtual Interrupt Delivery is + * enabled in vmcs12, and if VID is enabled then L2 EOIs affect L2's + * vAPIC, not L1's vAPIC. KVM must update vmcs01 on the next nested + * VM-Exit, otherwise L1 with run with a stale SVI. + */ + if (is_guest_mode(vcpu)) { + /* + * KVM is supposed to forward intercepted L2 EOIs to L1 if VID + * is enabled in vmcs12; as above, the EOIs affect L2's vAPIC. + * Note, userspace can stuff state while L2 is active; assert + * that VID is disabled if and only if the vCPU is in KVM_RUN + * to avoid false positives if userspace is setting APIC state. + */ + WARN_ON_ONCE(vcpu->wants_to_run && + nested_cpu_has_vid(get_vmcs12(vcpu))); + to_vmx(vcpu)->nested.update_vmcs01_hwapic_isr = true; + return; + } + if (max_isr == -1) max_isr = 0; @@ -6896,20 +6920,6 @@ static void vmx_set_rvi(int vector) } } -void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) -{ - /* - * When running L2, updating RVI is only relevant when - * vmcs12 virtual-interrupt-delivery enabled. - * However, it can be enabled only when L1 also - * intercepts external-interrupts and in that case - * we should not update vmcs02 RVI but instead intercept - * interrupt. Therefore, do nothing when running L2. - */ - if (!is_guest_mode(vcpu)) - vmx_set_rvi(max_irr); -} - int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7828,12 +7838,8 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) * to the guest. XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be * set if and only if XSAVE is supported. */ - if (boot_cpu_has(X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVE)) - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES); - - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VMX); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LAM); + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE)) + guest_cpu_cap_clear(vcpu, X86_FEATURE_XSAVES); vmx_setup_uret_msrs(vmx); @@ -7841,7 +7847,7 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmcs_set_secondary_exec_control(vmx, vmx_secondary_exec_control(vmx)); - if (guest_can_use(vcpu, X86_FEATURE_VMX)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; @@ -7850,25 +7856,25 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) ~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX); - if (guest_can_use(vcpu, X86_FEATURE_VMX)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) nested_vmx_cr_fixed1_bits_update(vcpu); if (boot_cpu_has(X86_FEATURE_INTEL_PT) && - guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) + guest_cpu_cap_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); if (boot_cpu_has(X86_FEATURE_RTM)) { struct vmx_uret_msr *msr; msr = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (msr) { - bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); + bool enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_RTM); vmx_set_guest_uret_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); } } if (kvm_cpu_cap_has(X86_FEATURE_XFD)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)); + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)); if (boot_cpu_has(X86_FEATURE_IBPB)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, @@ -7876,17 +7882,17 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, - !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); set_cr4_guest_host_mask(vmx); vmx_write_encls_bitmap(vcpu, NULL); - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_ENABLED; else vmx->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_SGX_ENABLED; - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_LC_ENABLED; else @@ -8597,7 +8603,7 @@ static void __vmx_exit(void) vmx_cleanup_l1d_flush(); } -static void vmx_exit(void) +static void __exit vmx_exit(void) { kvm_exit(); __vmx_exit(); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 43f573f6ca46..8b111ce1087c 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -176,6 +176,7 @@ struct nested_vmx { bool reload_vmcs01_apic_access_page; bool update_vmcs01_cpu_dirty_logging; bool update_vmcs01_apicv_status; + bool update_vmcs01_hwapic_isr; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to @@ -330,7 +331,10 @@ struct vcpu_vmx { bool ple_window_dirty; /* Support for PML */ -#define PML_ENTITY_NUM 512 +#define PML_LOG_NR_ENTRIES 512 + /* PML is written backwards: this is the first entry written by the CPU */ +#define PML_HEAD_INDEX (PML_LOG_NR_ENTRIES-1) + struct page *pml_pg; /* apic deadline value in host tsc */ diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h index bba24ed99ee6..cdf8cbb69209 100644 --- a/arch/x86/kvm/vmx/vmx_onhyperv.h +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -3,7 +3,7 @@ #ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__ #define __ARCH_X86_KVM_VMX_ONHYPERV_H__ -#include +#include #include #include diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index a55981c5216e..ce3295a67c04 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -47,8 +47,7 @@ bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu); void vmx_migrate_timers(struct kvm_vcpu *vcpu); void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu); -void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); -void vmx_hwapic_isr_update(int max_isr); +void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu); void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, int trig_mode, int vector); @@ -104,8 +103,11 @@ void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr); u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); + void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code); +void vmx_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code); + u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); void vmx_write_tsc_offset(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8160baf3838..6d4a6734b2d6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -119,8 +119,6 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; - #define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) #define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE @@ -1179,7 +1177,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.xcr0 != kvm_host.xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); - if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && vcpu->arch.ia32_xss != kvm_host.xss) wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } @@ -1188,7 +1186,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) vcpu->arch.pkru != vcpu->arch.host_pkru && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) - write_pkru(vcpu->arch.pkru); + wrpkru(vcpu->arch.pkru); } EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); @@ -1202,7 +1200,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) { vcpu->arch.pkru = rdpkru(); if (vcpu->arch.pkru != vcpu->arch.host_pkru) - write_pkru(vcpu->arch.host_pkru); + wrpkru(vcpu->arch.host_pkru); } if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { @@ -1210,7 +1208,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.xcr0 != kvm_host.xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, kvm_host.xcr0); - if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && vcpu->arch.ia32_xss != kvm_host.xss) wrmsrl(MSR_IA32_XSS, kvm_host.xss); } @@ -1283,18 +1281,6 @@ int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_xsetbv); -bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - if (cr4 & cr4_reserved_bits) - return false; - - if (cr4 & vcpu->arch.cr4_guest_rsvd_bits) - return false; - - return true; -} -EXPORT_SYMBOL_GPL(__kvm_is_valid_cr4); - static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { return __kvm_is_valid_cr4(vcpu, cr4) && @@ -1516,10 +1502,10 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) { u64 fixed = DR6_FIXED_1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_RTM)) fixed |= DR6_RTM; - if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) fixed |= DR6_BUS_LOCK; return fixed; } @@ -1695,20 +1681,20 @@ static int do_get_feature_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { - if (efer & EFER_AUTOIBRS && !guest_cpuid_has(vcpu, X86_FEATURE_AUTOIBRS)) + if (efer & EFER_AUTOIBRS && !guest_cpu_cap_has(vcpu, X86_FEATURE_AUTOIBRS)) return false; - if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT)) + if (efer & EFER_FFXSR && !guest_cpu_cap_has(vcpu, X86_FEATURE_FXSR_OPT)) return false; - if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + if (efer & EFER_SVME && !guest_cpu_cap_has(vcpu, X86_FEATURE_SVM)) return false; if (efer & (EFER_LME | EFER_LMA) && - !guest_cpuid_has(vcpu, X86_FEATURE_LM)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return false; - if (efer & EFER_NX && !guest_cpuid_has(vcpu, X86_FEATURE_NX)) + if (efer & EFER_NX && !guest_cpu_cap_has(vcpu, X86_FEATURE_NX)) return false; return true; @@ -1850,8 +1836,8 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, return 1; if (!host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) return 1; /* @@ -1908,8 +1894,8 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, return 1; if (!host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) return 1; break; } @@ -2095,7 +2081,7 @@ EXPORT_SYMBOL_GPL(kvm_handle_invalid_op); static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) { if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) && - !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MWAIT)) return kvm_handle_invalid_op(vcpu); pr_warn_once("%s instruction emulated as NOP!\n", insn); @@ -3767,13 +3753,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_ARCH_CAPABILITIES: if (!msr_info->host_initiated || - !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) return KVM_MSR_RET_UNSUPPORTED; vcpu->arch.arch_capabilities = data; break; case MSR_IA32_PERF_CAPABILITIES: if (!msr_info->host_initiated || - !guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) return KVM_MSR_RET_UNSUPPORTED; if (data & ~kvm_caps.supported_perf_cap) @@ -3797,11 +3783,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((!guest_has_pred_cmd_msr(vcpu))) return 1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBPB)) reserved_bits |= PRED_CMD_IBPB; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SBPB)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SBPB)) reserved_bits |= PRED_CMD_SBPB; } @@ -3822,7 +3808,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } case MSR_IA32_FLUSH_CMD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)) return 1; if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D) || (data & ~L1D_FLUSH)) @@ -3873,7 +3859,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_set_lapic_tscdeadline_msr(vcpu, data); break; case MSR_IA32_TSC_ADJUST: - if (guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSC_ADJUST)) { if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; adjust_tsc_offset_guest(vcpu, adj); @@ -3900,7 +3886,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) && ((old_val ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_XMM3)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XMM3)) return 1; vcpu->arch.ia32_misc_enable_msr = data; kvm_update_cpuid_runtime(vcpu); @@ -4077,12 +4063,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.length = data; break; case MSR_AMD64_OSVW_STATUS: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.status = data; break; @@ -4101,7 +4087,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) @@ -4111,7 +4097,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) @@ -4226,12 +4212,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.microcode_version; break; case MSR_IA32_ARCH_CAPABILITIES: - if (!guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.arch_capabilities; break; case MSR_IA32_PERF_CAPABILITIES: - if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.perf_capabilities; break; @@ -4432,12 +4418,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0xbe702111; break; case MSR_AMD64_OSVW_ID_LENGTH: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.length; break; case MSR_AMD64_OSVW_STATUS: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.status; break; @@ -4456,14 +4442,14 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.fpstate->xfd; break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.xfd_err; @@ -4545,6 +4531,20 @@ static inline bool kvm_can_mwait_in_guest(void) boot_cpu_has(X86_FEATURE_ARAT); } +static u64 kvm_get_allowed_disable_exits(void) +{ + u64 r = KVM_X86_DISABLE_EXITS_PAUSE; + + if (!mitigate_smt_rsb) { + r |= KVM_X86_DISABLE_EXITS_HLT | + KVM_X86_DISABLE_EXITS_CSTATE; + + if (kvm_can_mwait_in_guest()) + r |= KVM_X86_DISABLE_EXITS_MWAIT; + } + return r; +} + #ifdef CONFIG_KVM_HYPERV static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 __user *cpuid_arg) @@ -4687,15 +4687,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: - r = KVM_X86_DISABLE_EXITS_PAUSE; - - if (!mitigate_smt_rsb) { - r |= KVM_X86_DISABLE_EXITS_HLT | - KVM_X86_DISABLE_EXITS_CSTATE; - - if (kvm_can_mwait_in_guest()) - r |= KVM_X86_DISABLE_EXITS_MWAIT; - } + r = kvm_get_allowed_disable_exits(); break; case KVM_CAP_X86_SMM: if (!IS_ENABLED(CONFIG_KVM_SMM)) @@ -5822,9 +5814,6 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; - if (vcpu->arch.pv_cpuid.enforce) - kvm_update_pv_runtime(vcpu); - return 0; default: return -EINVAL; @@ -6542,30 +6531,32 @@ split_irqchip_unlock: break; case KVM_CAP_X86_DISABLE_EXITS: r = -EINVAL; - if (cap->args[0] & ~KVM_X86_DISABLE_VALID_EXITS) + if (cap->args[0] & ~kvm_get_allowed_disable_exits()) break; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) - kvm->arch.pause_in_guest = true; + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) + goto disable_exits_unlock; #define SMT_RSB_MSG "This processor is affected by the Cross-Thread Return Predictions vulnerability. " \ "KVM_CAP_X86_DISABLE_EXITS should only be used with SMT disabled or trusted guests." - if (!mitigate_smt_rsb) { - if (boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible() && - (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE)) - pr_warn_once(SMT_RSB_MSG); - - if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) && - kvm_can_mwait_in_guest()) - kvm->arch.mwait_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) - kvm->arch.hlt_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) - kvm->arch.cstate_in_guest = true; - } + if (!mitigate_smt_rsb && boot_cpu_has_bug(X86_BUG_SMT_RSB) && + cpu_smt_possible() && + (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE)) + pr_warn_once(SMT_RSB_MSG); + if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) + kvm->arch.pause_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) + kvm->arch.mwait_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) + kvm->arch.hlt_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) + kvm->arch.cstate_in_guest = true; r = 0; +disable_exits_unlock: + mutex_unlock(&kvm->lock); break; case KVM_CAP_MSR_PLATFORM_INFO: kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; @@ -8511,17 +8502,17 @@ static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) { - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); + return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); } static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) { - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); + return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); } static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt) { - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); + return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); } static bool emulator_guest_cpuid_is_intel_compatible(struct x86_emulate_ctxt *ctxt) @@ -8813,6 +8804,28 @@ void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_prepare_emulation_failure_exit); +void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa) +{ + u32 reason, intr_info, error_code; + struct kvm_run *run = vcpu->run; + u64 info1, info2; + int ndata = 0; + + kvm_x86_call(get_exit_info)(vcpu, &reason, &info1, &info2, + &intr_info, &error_code); + + run->internal.data[ndata++] = info2; + run->internal.data[ndata++] = reason; + run->internal.data[ndata++] = info1; + run->internal.data[ndata++] = gpa; + run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; + + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; + run->internal.ndata = ndata; +} +EXPORT_SYMBOL_GPL(kvm_prepare_event_vectoring_exit); + static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { struct kvm *kvm = vcpu->kvm; @@ -9085,6 +9098,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) return 1; + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) + return 1; + + if (r == X86EMUL_UNHANDLEABLE_VECTORING) { + kvm_prepare_event_vectoring_exit(vcpu, cr2_or_gpa); + return 0; + } + WARN_ON_ONCE(r != X86EMUL_UNHANDLEABLE); return handle_emulation_failure(vcpu, emulation_type); } @@ -9773,10 +9795,6 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) kvm_caps.supported_xss = 0; -#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) - cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); -#undef __kvm_cpu_cap_has - if (kvm_caps.has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that @@ -9976,20 +9994,22 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu) { u64 ret = vcpu->run->hypercall.ret; - if (!is_64_bit_mode(vcpu)) + if (!is_64_bit_hypercall(vcpu)) ret = (u32)ret; kvm_rax_write(vcpu, ret); - ++vcpu->stat.hypercalls; return kvm_skip_emulated_instruction(vcpu); } -unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, - unsigned long a0, unsigned long a1, - unsigned long a2, unsigned long a3, - int op_64_bit, int cpl) +int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, + unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + int op_64_bit, int cpl, + int (*complete_hypercall)(struct kvm_vcpu *)) { unsigned long ret; + ++vcpu->stat.hypercalls; + trace_kvm_hypercall(nr, a0, a1, a2, a3); if (!op_64_bit) { @@ -10041,7 +10061,7 @@ unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, u64 gpa = a0, npages = a1, attrs = a2; ret = -KVM_ENOSYS; - if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) + if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) break; if (!PAGE_ALIGNED(gpa) || !npages || @@ -10052,6 +10072,13 @@ unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + /* + * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2) + * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that + * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting + * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU. + */ + vcpu->run->hypercall.ret = 0; vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = attrs; @@ -10060,8 +10087,7 @@ unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, vcpu->run->hypercall.flags |= KVM_EXIT_HYPERCALL_LONG_MODE; WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ); - vcpu->arch.complete_userspace_io = complete_hypercall_exit; - /* stat is incremented on completion. */ + vcpu->arch.complete_userspace_io = complete_hypercall; return 0; } default: @@ -10070,41 +10096,23 @@ unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, } out: - ++vcpu->stat.hypercalls; - return ret; + vcpu->run->hypercall.ret = ret; + return 1; } -EXPORT_SYMBOL_GPL(__kvm_emulate_hypercall); +EXPORT_SYMBOL_GPL(____kvm_emulate_hypercall); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { - unsigned long nr, a0, a1, a2, a3, ret; - int op_64_bit; - int cpl; - if (kvm_xen_hypercall_enabled(vcpu->kvm)) return kvm_xen_hypercall(vcpu); if (kvm_hv_hypercall_enabled(vcpu)) return kvm_hv_hypercall(vcpu); - nr = kvm_rax_read(vcpu); - a0 = kvm_rbx_read(vcpu); - a1 = kvm_rcx_read(vcpu); - a2 = kvm_rdx_read(vcpu); - a3 = kvm_rsi_read(vcpu); - op_64_bit = is_64_bit_hypercall(vcpu); - cpl = kvm_x86_call(get_cpl)(vcpu); - - ret = __kvm_emulate_hypercall(vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl); - if (nr == KVM_HC_MAP_GPA_RANGE && !ret) - /* MAP_GPA tosses the request to the user space. */ - return 0; - - if (!op_64_bit) - ret = (u32)ret; - kvm_rax_write(vcpu, ret); - - return kvm_skip_emulated_instruction(vcpu); + return __kvm_emulate_hypercall(vcpu, rax, rbx, rcx, rdx, rsi, + is_64_bit_hypercall(vcpu), + kvm_x86_call(get_cpl)(vcpu), + complete_hypercall_exit); } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); @@ -11463,6 +11471,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; int r; + r = kvm_mmu_post_init_vm(vcpu->kvm); + if (r) + return r; + vcpu_load(vcpu); kvm_sigset_activate(vcpu); kvm_run->flags = 0; @@ -12276,9 +12288,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) goto free_emulate_ctxt; } - vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); - kvm_async_pf_hash_reset(vcpu); if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) { @@ -12301,6 +12310,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_xen_init_vcpu(vcpu); vcpu_load(vcpu); + kvm_vcpu_after_set_cpuid(vcpu); kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz); kvm_vcpu_reset(vcpu, false); kvm_init_mmu(vcpu); @@ -12724,6 +12734,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); + if (ignore_msrs && !report_ignored_msrs) { + pr_warn_once("Running KVM with ignore_msrs=1 and report_ignored_msrs=0 is not a\n" + "a supported configuration. Lying to the guest about the existence of MSRs\n" + "may cause the guest operating system to hang or produce errors. If a guest\n" + "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); + } + return 0; out_uninit_mmu: @@ -12735,7 +12752,8 @@ out: int kvm_arch_post_init_vm(struct kvm *kvm) { - return kvm_mmu_post_init_vm(kvm); + once_init(&kvm->arch.nx_once); + return 0; } static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) @@ -12793,7 +12811,8 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *slot; - /* Called with kvm->slots_lock held. */ + lockdep_assert_held(&kvm->slots_lock); + if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) return ERR_PTR_USR(-EINVAL); @@ -12826,7 +12845,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, m.guest_phys_addr = gpa; m.userspace_addr = hva; m.memory_size = size; - r = __kvm_set_memory_region(kvm, &m); + r = kvm_set_internal_memslot(kvm, &m); if (r < 0) return ERR_PTR_USR(r); } @@ -12927,7 +12946,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, /* * Clear out the previous array pointers for the KVM_MR_MOVE case. The - * old arrays will be freed by __kvm_set_memory_region() if installing + * old arrays will be freed by kvm_set_memory_region() if installing * the new memslot is successful. */ memset(&slot->arch, 0, sizeof(slot->arch)); @@ -13020,6 +13039,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) return -EINVAL; + if (kvm_is_gfn_alias(kvm, new->base_gfn + new->npages - 1)) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index ec623d23d13d..91e50a513100 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -550,7 +550,6 @@ static inline void kvm_machine_check(void) void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); int kvm_spec_ctrl_test_value(u64 value); -bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e); int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); @@ -577,6 +576,11 @@ enum kvm_msr_access { #define KVM_MSR_RET_UNSUPPORTED 2 #define KVM_MSR_RET_FILTERED 3 +static inline bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + return !(cr4 & vcpu->arch.cr4_guest_rsvd_bits); +} + #define __cr4_reserved_bits(__cpu_has, __c) \ ({ \ u64 __reserved_bits = CR4_RESERVED_BITS; \ @@ -612,4 +616,32 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port, void *data, unsigned int count, int in); +static inline bool user_exit_on_hypercall(struct kvm *kvm, unsigned long hc_nr) +{ + return kvm->arch.hypercall_exit_enabled & BIT(hc_nr); +} + +int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, + unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + int op_64_bit, int cpl, + int (*complete_hypercall)(struct kvm_vcpu *)); + +#define __kvm_emulate_hypercall(_vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl, complete_hypercall) \ +({ \ + int __ret; \ + \ + __ret = ____kvm_emulate_hypercall(_vcpu, \ + kvm_##nr##_read(_vcpu), kvm_##a0##_read(_vcpu), \ + kvm_##a1##_read(_vcpu), kvm_##a2##_read(_vcpu), \ + kvm_##a3##_read(_vcpu), op_64_bit, cpl, \ + complete_hypercall); \ + \ + if (__ret > 0) \ + __ret = complete_hypercall(_vcpu); \ + __ret; \ +}) + +int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); + #endif diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 98583a9dbab3..8a59c61624c2 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -38,6 +38,13 @@ lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_MITIGATION_RETPOLINE) += retpoline.o +obj-$(CONFIG_CRC32_ARCH) += crc32-x86.o +crc32-x86-y := crc32-glue.o crc32-pclmul.o +crc32-x86-$(CONFIG_64BIT) += crc32c-3way.o + +obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-x86.o +crc-t10dif-x86-y := crc-t10dif-glue.o crct10dif-pcl-asm_64.o + obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o obj-y += iomem.o diff --git a/arch/x86/lib/crc-t10dif-glue.c b/arch/x86/lib/crc-t10dif-glue.c new file mode 100644 index 000000000000..13f07ddc9122 --- /dev/null +++ b/arch/x86/lib/crc-t10dif-glue.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * CRC-T10DIF using PCLMULQDQ instructions + * + * Copyright 2024 Google LLC + */ + +#include +#include +#include +#include +#include + +static DEFINE_STATIC_KEY_FALSE(have_pclmulqdq); + +asmlinkage u16 crc_t10dif_pcl(u16 init_crc, const u8 *buf, size_t len); + +u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len) +{ + if (len >= 16 && + static_key_enabled(&have_pclmulqdq) && crypto_simd_usable()) { + kernel_fpu_begin(); + crc = crc_t10dif_pcl(crc, p, len); + kernel_fpu_end(); + return crc; + } + return crc_t10dif_generic(crc, p, len); +} +EXPORT_SYMBOL(crc_t10dif_arch); + +static int __init crc_t10dif_x86_init(void) +{ + if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) + static_branch_enable(&have_pclmulqdq); + return 0; +} +arch_initcall(crc_t10dif_x86_init); + +static void __exit crc_t10dif_x86_exit(void) +{ +} +module_exit(crc_t10dif_x86_exit); + +bool crc_t10dif_is_optimized(void) +{ + return static_key_enabled(&have_pclmulqdq); +} +EXPORT_SYMBOL(crc_t10dif_is_optimized); + +MODULE_DESCRIPTION("CRC-T10DIF using PCLMULQDQ instructions"); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/lib/crc32-glue.c b/arch/x86/lib/crc32-glue.c new file mode 100644 index 000000000000..2dd18a886ded --- /dev/null +++ b/arch/x86/lib/crc32-glue.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * x86-optimized CRC32 functions + * + * Copyright (C) 2008 Intel Corporation + * Copyright 2012 Xyratex Technology Limited + * Copyright 2024 Google LLC + */ + +#include +#include +#include +#include +#include +#include + +/* minimum size of buffer for crc32_pclmul_le_16 */ +#define CRC32_PCLMUL_MIN_LEN 64 + +static DEFINE_STATIC_KEY_FALSE(have_crc32); +static DEFINE_STATIC_KEY_FALSE(have_pclmulqdq); + +u32 crc32_pclmul_le_16(u32 crc, const u8 *buffer, size_t len); + +u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) +{ + if (len >= CRC32_PCLMUL_MIN_LEN + 15 && + static_branch_likely(&have_pclmulqdq) && crypto_simd_usable()) { + size_t n = -(uintptr_t)p & 15; + + /* align p to 16-byte boundary */ + if (n) { + crc = crc32_le_base(crc, p, n); + p += n; + len -= n; + } + n = round_down(len, 16); + kernel_fpu_begin(); + crc = crc32_pclmul_le_16(crc, p, n); + kernel_fpu_end(); + p += n; + len -= n; + } + if (len) + crc = crc32_le_base(crc, p, len); + return crc; +} +EXPORT_SYMBOL(crc32_le_arch); + +#ifdef CONFIG_X86_64 +#define CRC32_INST "crc32q %1, %q0" +#else +#define CRC32_INST "crc32l %1, %0" +#endif + +/* + * Use carryless multiply version of crc32c when buffer size is >= 512 to + * account for FPU state save/restore overhead. + */ +#define CRC32C_PCLMUL_BREAKEVEN 512 + +asmlinkage u32 crc32c_x86_3way(u32 crc, const u8 *buffer, size_t len); + +u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len) +{ + size_t num_longs; + + if (!static_branch_likely(&have_crc32)) + return crc32c_le_base(crc, p, len); + + if (IS_ENABLED(CONFIG_X86_64) && len >= CRC32C_PCLMUL_BREAKEVEN && + static_branch_likely(&have_pclmulqdq) && crypto_simd_usable()) { + kernel_fpu_begin(); + crc = crc32c_x86_3way(crc, p, len); + kernel_fpu_end(); + return crc; + } + + for (num_longs = len / sizeof(unsigned long); + num_longs != 0; num_longs--, p += sizeof(unsigned long)) + asm(CRC32_INST : "+r" (crc) : "rm" (*(unsigned long *)p)); + + for (len %= sizeof(unsigned long); len; len--, p++) + asm("crc32b %1, %0" : "+r" (crc) : "rm" (*p)); + + return crc; +} +EXPORT_SYMBOL(crc32c_le_arch); + +u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) +{ + return crc32_be_base(crc, p, len); +} +EXPORT_SYMBOL(crc32_be_arch); + +static int __init crc32_x86_init(void) +{ + if (boot_cpu_has(X86_FEATURE_XMM4_2)) + static_branch_enable(&have_crc32); + if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) + static_branch_enable(&have_pclmulqdq); + return 0; +} +arch_initcall(crc32_x86_init); + +static void __exit crc32_x86_exit(void) +{ +} +module_exit(crc32_x86_exit); + +u32 crc32_optimizations(void) +{ + u32 optimizations = 0; + + if (static_key_enabled(&have_crc32)) + optimizations |= CRC32C_OPTIMIZATION; + if (static_key_enabled(&have_pclmulqdq)) + optimizations |= CRC32_LE_OPTIMIZATION; + return optimizations; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_DESCRIPTION("x86-optimized CRC32 functions"); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/lib/crc32-pclmul.S similarity index 95% rename from arch/x86/crypto/crc32-pclmul_asm.S rename to arch/x86/lib/crc32-pclmul.S index 5d31137e2c7d..f9637789cac1 100644 --- a/arch/x86/crypto/crc32-pclmul_asm.S +++ b/arch/x86/lib/crc32-pclmul.S @@ -58,13 +58,13 @@ #define CONSTANT %xmm0 #ifdef __x86_64__ -#define BUF %rdi -#define LEN %rsi -#define CRC %edx +#define CRC %edi +#define BUF %rsi +#define LEN %rdx #else -#define BUF %eax -#define LEN %edx -#define CRC %ecx +#define CRC %eax +#define BUF %edx +#define LEN %ecx #endif @@ -72,12 +72,11 @@ .text /** * Calculate crc32 - * BUF - buffer (16 bytes aligned) - * LEN - sizeof buffer (16 bytes aligned), LEN should be grater than 63 * CRC - initial crc32 + * BUF - buffer (16 bytes aligned) + * LEN - sizeof buffer (16 bytes aligned), LEN should be greater than 63 * return %eax crc32 - * uint crc32_pclmul_le_16(unsigned char const *buffer, - * size_t len, uint crc32) + * u32 crc32_pclmul_le_16(u32 crc, const u8 *buffer, size_t len); */ SYM_FUNC_START(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */ diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/lib/crc32c-3way.S similarity index 92% rename from arch/x86/crypto/crc32c-pcl-intel-asm_64.S rename to arch/x86/lib/crc32c-3way.S index 752812bc4991..9b8770503bbc 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/lib/crc32c-3way.S @@ -52,15 +52,16 @@ # regular CRC code that does not interleave the CRC instructions. #define SMALL_SIZE 200 -# unsigned int crc_pcl(const u8 *buffer, unsigned int len, unsigned int crc_init); +# u32 crc32c_x86_3way(u32 crc, const u8 *buffer, size_t len); .text -SYM_FUNC_START(crc_pcl) -#define bufp %rdi -#define bufp_d %edi -#define len %esi -#define crc_init %edx -#define crc_init_q %rdx +SYM_FUNC_START(crc32c_x86_3way) +#define crc0 %edi +#define crc0_q %rdi +#define bufp %rsi +#define bufp_d %esi +#define len %rdx +#define len_dw %edx #define n_misaligned %ecx /* overlaps chunk_bytes! */ #define n_misaligned_q %rcx #define chunk_bytes %ecx /* overlaps n_misaligned! */ @@ -85,9 +86,9 @@ SYM_FUNC_START(crc_pcl) .Ldo_align: movq (bufp), %rax add n_misaligned_q, bufp - sub n_misaligned, len + sub n_misaligned_q, len .Lalign_loop: - crc32b %al, crc_init # compute crc32 of 1-byte + crc32b %al, crc0 # compute crc32 of 1-byte shr $8, %rax # get next byte dec n_misaligned jne .Lalign_loop @@ -102,7 +103,7 @@ SYM_FUNC_START(crc_pcl) .Lpartial_block: # Compute floor(len / 24) to get num qwords to process from each lane. - imul $2731, len, %eax # 2731 = ceil(2^16 / 24) + imul $2731, len_dw, %eax # 2731 = ceil(2^16 / 24) shr $16, %eax jmp .Lcrc_3lanes @@ -125,16 +126,16 @@ SYM_FUNC_START(crc_pcl) # Unroll the loop by a factor of 4 to reduce the overhead of the loop # bookkeeping instructions, which can compete with crc32q for the ALUs. .Lcrc_3lanes_4x_loop: - crc32q (bufp), crc_init_q + crc32q (bufp), crc0_q crc32q (bufp,chunk_bytes_q), crc1 crc32q (bufp,chunk_bytes_q,2), crc2 - crc32q 8(bufp), crc_init_q + crc32q 8(bufp), crc0_q crc32q 8(bufp,chunk_bytes_q), crc1 crc32q 8(bufp,chunk_bytes_q,2), crc2 - crc32q 16(bufp), crc_init_q + crc32q 16(bufp), crc0_q crc32q 16(bufp,chunk_bytes_q), crc1 crc32q 16(bufp,chunk_bytes_q,2), crc2 - crc32q 24(bufp), crc_init_q + crc32q 24(bufp), crc0_q crc32q 24(bufp,chunk_bytes_q), crc1 crc32q 24(bufp,chunk_bytes_q,2), crc2 add $32, bufp @@ -146,7 +147,7 @@ SYM_FUNC_START(crc_pcl) jz .Lcrc_3lanes_last_qword .Lcrc_3lanes_1x_loop: - crc32q (bufp), crc_init_q + crc32q (bufp), crc0_q crc32q (bufp,chunk_bytes_q), crc1 crc32q (bufp,chunk_bytes_q,2), crc2 add $8, bufp @@ -154,7 +155,7 @@ SYM_FUNC_START(crc_pcl) jnz .Lcrc_3lanes_1x_loop .Lcrc_3lanes_last_qword: - crc32q (bufp), crc_init_q + crc32q (bufp), crc0_q crc32q (bufp,chunk_bytes_q), crc1 # SKIP crc32q (bufp,chunk_bytes_q,2), crc2 ; Don't do this one yet @@ -165,9 +166,9 @@ SYM_FUNC_START(crc_pcl) lea (K_table-8)(%rip), %rax # first entry is for idx 1 pmovzxdq (%rax,chunk_bytes_q), %xmm0 # 2 consts: K1:K2 lea (chunk_bytes,chunk_bytes,2), %eax # chunk_bytes * 3 - sub %eax, len # len -= chunk_bytes * 3 + sub %rax, len # len -= chunk_bytes * 3 - movq crc_init_q, %xmm1 # CRC for block 1 + movq crc0_q, %xmm1 # CRC for block 1 pclmulqdq $0x00, %xmm0, %xmm1 # Multiply by K2 movq crc1, %xmm2 # CRC for block 2 @@ -176,8 +177,8 @@ SYM_FUNC_START(crc_pcl) pxor %xmm2,%xmm1 movq %xmm1, %rax xor (bufp,chunk_bytes_q,2), %rax - mov crc2, crc_init_q - crc32 %rax, crc_init_q + mov crc2, crc0_q + crc32 %rax, crc0_q lea 8(bufp,chunk_bytes_q,2), bufp ################################################################ @@ -193,34 +194,34 @@ SYM_FUNC_START(crc_pcl) ## 6) Process any remainder without interleaving: ####################################################################### .Lsmall: - test len, len + test len_dw, len_dw jz .Ldone - mov len, %eax + mov len_dw, %eax shr $3, %eax jz .Ldo_dword .Ldo_qwords: - crc32q (bufp), crc_init_q + crc32q (bufp), crc0_q add $8, bufp dec %eax jnz .Ldo_qwords .Ldo_dword: - test $4, len + test $4, len_dw jz .Ldo_word - crc32l (bufp), crc_init + crc32l (bufp), crc0 add $4, bufp .Ldo_word: - test $2, len + test $2, len_dw jz .Ldo_byte - crc32w (bufp), crc_init + crc32w (bufp), crc0 add $2, bufp .Ldo_byte: - test $1, len + test $1, len_dw jz .Ldone - crc32b (bufp), crc_init + crc32b (bufp), crc0 .Ldone: - mov crc_init, %eax + mov crc0, %eax RET -SYM_FUNC_END(crc_pcl) +SYM_FUNC_END(crc32c_x86_3way) .section .rodata, "a", @progbits ################################################################ diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/lib/crct10dif-pcl-asm_64.S similarity index 100% rename from arch/x86/crypto/crct10dif-pcl-asm_64.S rename to arch/x86/lib/crct10dif-pcl-asm_64.S diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 4357ec2a0bfc..89ecd57c9d42 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -44,9 +44,8 @@ .pushsection runtime_ptr_USER_PTR_MAX,"a" .long 1b - 8 - . .popsection - cmp %rax, %rdx - sbb %rdx, %rdx - or %rdx, %rax + cmp %rdx, %rax + cmova %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax jae .Lbad_get_user diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e6c469b323cc..296d294142c8 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -7,7 +7,6 @@ #include /* test_thread_flag(), ... */ #include /* task_stack_*(), ... */ #include /* oops_begin/end, ... */ -#include /* search_exception_tables */ #include /* max_low_pfn */ #include /* kfence_handle_page_fault */ #include /* NOKPROBE_SYMBOL, ... */ @@ -678,7 +677,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, ASM_CALL_ARG3, , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info)); - unreachable(); + BUG(); } #endif diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index c6d29f283001..62aa4d66a032 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1080,7 +1080,8 @@ struct execmem_info __init *execmem_arch_setup(void) start = MODULES_VADDR + offset; - if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX)) { + if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) && + cpu_feature_enabled(X86_FEATURE_PSE)) { pgprot = PAGE_KERNEL_ROX; flags = EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE; } else { diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 8d29163568a7..38ff7791a9c7 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -593,8 +593,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr, * Examine the physical address to determine if it is EFI data. Check * it against the boot params structure and EFI tables and memory types. */ -static bool memremap_is_efi_data(resource_size_t phys_addr, - unsigned long size) +static bool memremap_is_efi_data(resource_size_t phys_addr) { u64 paddr; @@ -632,71 +631,9 @@ static bool memremap_is_efi_data(resource_size_t phys_addr, * Examine the physical address to determine if it is boot data by checking * it against the boot params setup_data chain. */ -static bool memremap_is_setup_data(resource_size_t phys_addr, - unsigned long size) -{ - struct setup_indirect *indirect; - struct setup_data *data; - u64 paddr, paddr_next; - - paddr = boot_params.hdr.setup_data; - while (paddr) { - unsigned int len; - - if (phys_addr == paddr) - return true; - - data = memremap(paddr, sizeof(*data), - MEMREMAP_WB | MEMREMAP_DEC); - if (!data) { - pr_warn("failed to memremap setup_data entry\n"); - return false; - } - - paddr_next = data->next; - len = data->len; - - if ((phys_addr > paddr) && - (phys_addr < (paddr + sizeof(struct setup_data) + len))) { - memunmap(data); - return true; - } - - if (data->type == SETUP_INDIRECT) { - memunmap(data); - data = memremap(paddr, sizeof(*data) + len, - MEMREMAP_WB | MEMREMAP_DEC); - if (!data) { - pr_warn("failed to memremap indirect setup_data\n"); - return false; - } - - indirect = (struct setup_indirect *)data->data; - - if (indirect->type != SETUP_INDIRECT) { - paddr = indirect->addr; - len = indirect->len; - } - } - - memunmap(data); - - if ((phys_addr > paddr) && (phys_addr < (paddr + len))) - return true; - - paddr = paddr_next; - } - - return false; -} - -/* - * Examine the physical address to determine if it is boot data by checking - * it against the boot params setup_data chain (early boot version). - */ -static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, - unsigned long size) +static bool __ref __memremap_is_setup_data(resource_size_t phys_addr, bool early) { + unsigned int setup_data_sz = sizeof(struct setup_data); struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; @@ -708,29 +645,40 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, if (phys_addr == paddr) return true; - data = early_memremap_decrypted(paddr, sizeof(*data)); + if (early) + data = early_memremap_decrypted(paddr, setup_data_sz); + else + data = memremap(paddr, setup_data_sz, MEMREMAP_WB | MEMREMAP_DEC); if (!data) { - pr_warn("failed to early memremap setup_data entry\n"); + pr_warn("failed to remap setup_data entry\n"); return false; } - size = sizeof(*data); + size = setup_data_sz; paddr_next = data->next; len = data->len; if ((phys_addr > paddr) && - (phys_addr < (paddr + sizeof(struct setup_data) + len))) { - early_memunmap(data, sizeof(*data)); + (phys_addr < (paddr + setup_data_sz + len))) { + if (early) + early_memunmap(data, setup_data_sz); + else + memunmap(data); return true; } if (data->type == SETUP_INDIRECT) { size += len; - early_memunmap(data, sizeof(*data)); - data = early_memremap_decrypted(paddr, size); + if (early) { + early_memunmap(data, setup_data_sz); + data = early_memremap_decrypted(paddr, size); + } else { + memunmap(data); + data = memremap(paddr, size, MEMREMAP_WB | MEMREMAP_DEC); + } if (!data) { - pr_warn("failed to early memremap indirect setup_data\n"); + pr_warn("failed to remap indirect setup_data\n"); return false; } @@ -742,7 +690,10 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, } } - early_memunmap(data, size); + if (early) + early_memunmap(data, size); + else + memunmap(data); if ((phys_addr > paddr) && (phys_addr < (paddr + len))) return true; @@ -753,6 +704,16 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, return false; } +static bool memremap_is_setup_data(resource_size_t phys_addr) +{ + return __memremap_is_setup_data(phys_addr, false); +} + +static bool __init early_memremap_is_setup_data(resource_size_t phys_addr) +{ + return __memremap_is_setup_data(phys_addr, true); +} + /* * Architecture function to determine if RAM remap is allowed. By default, a * RAM remap will map the data as encrypted. Determine if a RAM remap should @@ -771,8 +732,8 @@ bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, return false; if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { - if (memremap_is_setup_data(phys_addr, size) || - memremap_is_efi_data(phys_addr, size)) + if (memremap_is_setup_data(phys_addr) || + memremap_is_efi_data(phys_addr)) return false; } @@ -797,8 +758,8 @@ pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, encrypted_prot = true; if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { - if (early_memremap_is_setup_data(phys_addr, size) || - memremap_is_efi_data(phys_addr, size)) + if (early_memremap_is_setup_data(phys_addr) || + memremap_is_efi_data(phys_addr)) encrypted_prot = false; } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 0a120d85d7bb..95bae74fdab2 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -94,6 +94,8 @@ void __init mem_encrypt_init(void) /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ swiotlb_update_mem_attributes(); + snp_secure_tsc_prepare(); + print_mem_encrypt_feature_info(); } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 774f9677458f..b56c5c073003 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -541,6 +541,9 @@ void __init sme_early_init(void) * kernel mapped. */ snp_update_svsm_ca(); + + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 95bc50a8541c..ef4514d64c05 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -32,8 +32,6 @@ #include #include #include -#include -#include #include "../mm_internal.h" diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 5745a354a241..1fef5ad32d5a 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -19,12 +19,23 @@ EXPORT_SYMBOL(physical_mask); #endif #ifndef CONFIG_PARAVIRT +#ifndef CONFIG_PT_RECLAIM static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) { - tlb_remove_page(tlb, table); + struct ptdesc *ptdesc = (struct ptdesc *)table; + + pagetable_dtor(ptdesc); + tlb_remove_page(tlb, ptdesc_page(ptdesc)); } -#endif +#else +static inline +void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + tlb_remove_table(tlb, table); +} +#endif /* !CONFIG_PT_RECLAIM */ +#endif /* !CONFIG_PARAVIRT */ gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM; @@ -52,15 +63,13 @@ early_param("userpte", setup_userpte); void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { - pagetable_pte_dtor(page_ptdesc(pte)); paravirt_release_pte(page_to_pfn(pte)); - paravirt_tlb_remove_table(tlb, pte); + paravirt_tlb_remove_table(tlb, page_ptdesc(pte)); } #if CONFIG_PGTABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { - struct ptdesc *ptdesc = virt_to_ptdesc(pmd); paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); /* * NOTE! For PAE, any changes to the top page-directory-pointer-table @@ -69,25 +78,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) #ifdef CONFIG_X86_PAE tlb->need_flush_all = 1; #endif - pagetable_pmd_dtor(ptdesc); - paravirt_tlb_remove_table(tlb, ptdesc_page(ptdesc)); + paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pmd)); } #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { - struct ptdesc *ptdesc = virt_to_ptdesc(pud); - - pagetable_pud_dtor(ptdesc); paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); - paravirt_tlb_remove_table(tlb, virt_to_page(pud)); + paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pud)); } #if CONFIG_PGTABLE_LEVELS > 4 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) { paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT); - paravirt_tlb_remove_table(tlb, virt_to_page(p4d)); + paravirt_tlb_remove_table(tlb, virt_to_ptdesc(p4d)); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ @@ -222,7 +227,7 @@ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) if (pmds[i]) { ptdesc = virt_to_ptdesc(pmds[i]); - pagetable_pmd_dtor(ptdesc); + pagetable_dtor(ptdesc); pagetable_free(ptdesc); mm_dec_nr_pmds(mm); } @@ -392,15 +397,14 @@ void __init pgtable_cache_init(void) SLAB_PANIC, NULL); } -static inline pgd_t *_pgd_alloc(void) +static inline pgd_t *_pgd_alloc(struct mm_struct *mm) { /* * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain. * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) - return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, - PGD_ALLOCATION_ORDER); + return __pgd_alloc(mm, PGD_ALLOCATION_ORDER); /* * Now PAE kernel is not running as a Xen domain. We can allocate @@ -409,24 +413,23 @@ static inline pgd_t *_pgd_alloc(void) return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER); } -static inline void _pgd_free(pgd_t *pgd) +static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) { if (!SHARED_KERNEL_PMD) - free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); + __pgd_free(mm, pgd); else kmem_cache_free(pgd_cache, pgd); } #else -static inline pgd_t *_pgd_alloc(void) +static inline pgd_t *_pgd_alloc(struct mm_struct *mm) { - return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, - PGD_ALLOCATION_ORDER); + return __pgd_alloc(mm, PGD_ALLOCATION_ORDER); } -static inline void _pgd_free(pgd_t *pgd) +static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) { - free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); + __pgd_free(mm, pgd); } #endif /* CONFIG_X86_PAE */ @@ -436,7 +439,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS]; pmd_t *pmds[MAX_PREALLOCATED_PMDS]; - pgd = _pgd_alloc(); + pgd = _pgd_alloc(mm); if (pgd == NULL) goto out; @@ -479,7 +482,7 @@ out_free_pmds: if (sizeof(pmds) != 0) free_pmds(mm, pmds, PREALLOCATED_PMDS); out_free_pgd: - _pgd_free(pgd); + _pgd_free(mm, pgd); out: return NULL; } @@ -489,7 +492,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) pgd_mop_up_pmds(mm, pgd); pgd_dtor(pgd); paravirt_pgd_free(mm, pgd); - _pgd_free(pgd); + _pgd_free(mm, pgd); } /* @@ -856,7 +859,7 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) free_page((unsigned long)pmd_sv); - pagetable_pmd_dtor(virt_to_ptdesc(pmd)); + pagetable_dtor(virt_to_ptdesc(pmd)); free_page((unsigned long)pmd); return 1; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index a2becb85bea7..6cf881a942bb 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -607,18 +607,15 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, cond_mitigation(tsk); /* - * Stop remote flushes for the previous mm. - * Skip kernel threads; we never send init_mm TLB flushing IPIs, - * but the bitmap manipulation can cause cache line contention. + * Leave this CPU in prev's mm_cpumask. Atomic writes to + * mm_cpumask can be expensive under contention. The CPU + * will be removed lazily at TLB flush time. */ - if (prev != &init_mm) { - VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, - mm_cpumask(prev))); - cpumask_clear_cpu(cpu, mm_cpumask(prev)); - } + VM_WARN_ON_ONCE(prev != &init_mm && !cpumask_test_cpu(cpu, + mm_cpumask(prev))); /* Start receiving IPIs and then read tlb_gen (and LAM below) */ - if (next != &init_mm) + if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next))) cpumask_set_cpu(cpu, mm_cpumask(next)); next_tlb_gen = atomic64_read(&next->context.tlb_gen); @@ -760,10 +757,13 @@ static void flush_tlb_func(void *info) if (!local) { inc_irq_stat(irq_tlb_count); count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + } - /* Can only happen on remote CPUs */ - if (f->mm && f->mm != loaded_mm) - return; + /* The CPU was left in the mm_cpumask of the target mm. Clear it. */ + if (f->mm && f->mm != loaded_mm) { + cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(f->mm)); + trace_tlb_flush(TLB_REMOTE_WRONG_CPU, 0); + return; } if (unlikely(loaded_mm == &init_mm)) @@ -893,9 +893,36 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu, void *data) +static bool should_flush_tlb(int cpu, void *data) { - return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); + struct flush_tlb_info *info = data; + + /* Lazy TLB will get flushed at the next context switch. */ + if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu)) + return false; + + /* No mm means kernel memory flush. */ + if (!info->mm) + return true; + + /* The target mm is loaded, and the CPU is not lazy. */ + if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm) + return true; + + /* In cpumask, but not the loaded mm? Periodically remove by flushing. */ + if (info->trim_cpumask) + return true; + + return false; +} + +static bool should_trim_cpumask(struct mm_struct *mm) +{ + if (time_after(jiffies, READ_ONCE(mm->context.next_trim_cpumask))) { + WRITE_ONCE(mm->context.next_trim_cpumask, jiffies + HZ); + return true; + } + return false; } DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); @@ -929,7 +956,7 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, if (info->freed_tables) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); else - on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func, (void *)info, 1, cpumask); } @@ -980,6 +1007,7 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm, info->freed_tables = freed_tables; info->new_tlb_gen = new_tlb_gen; info->initiating_cpu = smp_processor_id(); + info->trim_cpumask = 0; return info; } @@ -1022,6 +1050,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, * flush_tlb_func_local() directly in this case. */ if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) { + info->trim_cpumask = should_trim_cpumask(mm); flush_tlb_multi(mm_cpumask(mm), info); } else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) { lockdep_assert_irqs_enabled(); diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 0681ecfe3430..efefeb82ab61 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include @@ -828,7 +828,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma); #endif -#ifdef CONFIG_AMD_NB +#ifdef CONFIG_AMD_NODE #define AMD_15B8_RCC_DEV2_EPF0_STRAP2 0x10136008 #define AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK 0x00000080L @@ -1010,4 +1010,34 @@ DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_suspend); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_resume); DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_suspend); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_resume); + +/* + * Putting PCIe root ports on Ryzen SoCs with USB4 controllers into D3hot + * may cause problems when the system attempts wake up from s2idle. + * + * On the TUXEDO Sirius 16 Gen 1 with a specific old BIOS this manifests as + * a system hang. + */ +static const struct dmi_system_id quirk_tuxeo_rp_d3_dmi_table[] = { + { + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "APX958"), + DMI_EXACT_MATCH(DMI_BIOS_VERSION, "V1.00A00_20240108"), + }, + }, + {} +}; + +static void quirk_tuxeo_rp_d3(struct pci_dev *pdev) +{ + struct pci_dev *root_pdev; + + if (dmi_check_system(quirk_tuxeo_rp_d3_dmi_table)) { + root_pdev = pcie_find_root_port(pdev); + if (root_pdev) + root_pdev->dev_flags |= PCI_DEV_FLAGS_NO_D3; + } +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1502, quirk_tuxeo_rp_d3); #endif /* CONFIG_SUSPEND */ diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index a7ff189421c3..463b784499a8 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -54,13 +54,11 @@ #include static unsigned long efi_systab_phys __initdata; -static unsigned long uga_phys = EFI_INVALID_TABLE_ADDR; static unsigned long efi_runtime, efi_nr_tables; unsigned long efi_fw_vendor, efi_config_table; static const efi_config_table_type_t arch_tables[] __initconst = { - {UGA_IO_PROTOCOL_GUID, &uga_phys, "UGA" }, #ifdef CONFIG_X86_UV {UV_SYSTEM_TABLE_GUID, &uv_systab_phys, "UVsystab" }, #endif @@ -72,7 +70,6 @@ static const unsigned long * const efi_tables[] = { &efi.acpi20, &efi.smbios, &efi.smbios3, - &uga_phys, #ifdef CONFIG_X86_UV &uv_systab_phys, #endif @@ -891,13 +888,6 @@ bool efi_is_table_address(unsigned long phys_addr) return false; } -char *efi_systab_show_arch(char *str) -{ - if (uga_phys != EFI_INVALID_TABLE_ADDR) - str += sprintf(str, "UGA=0x%lx\n", uga_phys); - return str; -} - #define EFI_FIELD(var) efi_ ## var #define EFI_ATTR_SHOW(name) \ diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 846bf49f2508..553f330198f2 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -561,6 +561,11 @@ int __init efi_reuse_config(u64 tables, int nr_tables) if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) ((efi_config_table_64_t *)p)->table = data->smbios; + + /* Do not bother to play with mem attr table across kexec */ + if (!efi_guidcmp(guid, EFI_MEMORY_ATTRIBUTES_TABLE_GUID)) + ((efi_config_table_64_t *)p)->table = EFI_INVALID_TABLE_ADDR; + p += sz; } early_memunmap(tablep, nr_tables * sz); diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index 74ebd6882690..cf5dca2dbb91 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -136,11 +136,7 @@ void * __init prom_early_alloc(unsigned long size) * fast enough on the platforms we care about while minimizing * wasted bootmem) and hand off chunks of it to callers. */ - res = memblock_alloc(chunk_size, SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - chunk_size); - BUG_ON(!res); + res = memblock_alloc_or_panic(chunk_size, SMP_CACHE_BYTES); prom_early_allocated += chunk_size; memset(res, 0, chunk_size); free_mem = chunk_size; diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index a379501b7a69..4f200ac96ce0 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -92,8 +92,6 @@ static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq, if (ret >= 0) { if (info->uv.limit == UV_AFFINITY_CPU) irq_set_status_flags(virq, IRQ_NO_BALANCING); - else - irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); chip_data->pnode = uv_blade_to_pnode(info->uv.blade); chip_data->offset = info->uv.offset; @@ -113,7 +111,6 @@ static void uv_domain_free(struct irq_domain *domain, unsigned int virq, BUG_ON(nr_irqs != 1); kfree(irq_data->chip_data); - irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); irq_clear_status_flags(virq, IRQ_NO_BALANCING); irq_domain_free_irqs_top(domain, virq, nr_irqs); } diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 27441e5863b2..e937be979ec8 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -841,10 +841,10 @@ static int is_percpu_sym(ElfW(Sym) *sym, const char *symname) static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, const char *symname) { + int headtext = !strcmp(sec_name(sec->shdr.sh_info), ".head.text"); unsigned r_type = ELF64_R_TYPE(rel->r_info); ElfW(Addr) offset = rel->r_offset; int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname); - if (sym->st_shndx == SHN_UNDEF) return 0; @@ -900,6 +900,12 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, break; } + if (headtext) { + die("Absolute reference to symbol '%s' not permitted in .head.text\n", + symname); + break; + } + /* * Relocation offsets for 64 bit kernels are output * as 32 bits and sign extended back to 64 bits when diff --git a/arch/x86/um/asm/archparam.h b/arch/x86/um/asm/archparam.h deleted file mode 100644 index c17cf68dda0f..000000000000 --- a/arch/x86/um/asm/archparam.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com) - * Copyright 2003 PathScale, Inc. - * Licensed under the GPL - */ - -#ifndef __UM_ARCHPARAM_H -#define __UM_ARCHPARAM_H - -#ifdef CONFIG_X86_32 - -#ifdef CONFIG_X86_PAE -#define LAST_PKMAP 512 -#else -#define LAST_PKMAP 1024 -#endif - -#endif - -#endif diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h index 2dd4ca6713f8..8f7476ff6e95 100644 --- a/arch/x86/um/shared/sysdep/ptrace.h +++ b/arch/x86/um/shared/sysdep/ptrace.h @@ -74,8 +74,6 @@ struct uml_pt_regs { #define UPT_FAULTINFO(r) (&(r)->faultinfo) #define UPT_IS_USER(r) ((r)->is_user) -extern int user_context(unsigned long sp); - extern int arch_init_registers(int pid); #endif /* __SYSDEP_X86_PTRACE_H */ diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index 9a6a943d8e41..1dcc027ec77e 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -31,10 +32,29 @@ #include /* - * The RMP entry format is not architectural. The format is defined in PPR - * Family 19h Model 01h, Rev B1 processor. + * The RMP entry information as returned by the RMPREAD instruction. */ struct rmpentry { + u64 gpa; + u8 assigned :1, + rsvd1 :7; + u8 pagesize :1, + hpage_region_status :1, + rsvd2 :6; + u8 immutable :1, + rsvd3 :7; + u8 rsvd4; + u32 asid; +} __packed; + +/* + * The raw RMP entry format is not architectural. The format is defined in PPR + * Family 19h Model 01h, Rev B1 processor. This format represents the actual + * entry in the RMP table memory. The bitfield definitions are used for machines + * without the RMPREAD instruction (Zen3 and Zen4), otherwise the "hi" and "lo" + * fields are only used for dumping the raw data. + */ +struct rmpentry_raw { union { struct { u64 assigned : 1, @@ -58,12 +78,48 @@ struct rmpentry { */ #define RMPTABLE_CPU_BOOKKEEPING_SZ 0x4000 +/* + * For a non-segmented RMP table, use the maximum physical addressing as the + * segment size in order to always arrive at index 0 in the table. + */ +#define RMPTABLE_NON_SEGMENTED_SHIFT 52 + +struct rmp_segment_desc { + struct rmpentry_raw *rmp_entry; + u64 max_index; + u64 size; +}; + +/* + * Segmented RMP Table support. + * - The segment size is used for two purposes: + * - Identify the amount of memory covered by an RMP segment + * - Quickly locate an RMP segment table entry for a physical address + * + * - The RMP segment table contains pointers to an RMP table that covers + * a specific portion of memory. There can be up to 512 8-byte entries, + * one pages worth. + */ +#define RST_ENTRY_MAPPED_SIZE(x) ((x) & GENMASK_ULL(19, 0)) +#define RST_ENTRY_SEGMENT_BASE(x) ((x) & GENMASK_ULL(51, 20)) + +#define RST_SIZE SZ_4K +static struct rmp_segment_desc **rmp_segment_table __ro_after_init; +static unsigned int rst_max_index __ro_after_init = 512; + +static unsigned int rmp_segment_shift; +static u64 rmp_segment_size; +static u64 rmp_segment_mask; + +#define RST_ENTRY_INDEX(x) ((x) >> rmp_segment_shift) +#define RMP_ENTRY_INDEX(x) ((u64)(PHYS_PFN((x) & rmp_segment_mask))) + +static u64 rmp_cfg; + /* Mask to apply to a PFN to get the first PFN of a 2MB page */ #define PFN_PMD_MASK GENMASK_ULL(63, PMD_SHIFT - PAGE_SHIFT) static u64 probed_rmp_base, probed_rmp_size; -static struct rmpentry *rmptable __ro_after_init; -static u64 rmptable_max_pfn __ro_after_init; static LIST_HEAD(snp_leaked_pages_list); static DEFINE_SPINLOCK(snp_leaked_pages_list_lock); @@ -116,36 +172,6 @@ static __init void snp_enable(void *arg) __snp_enable(smp_processor_id()); } -#define RMP_ADDR_MASK GENMASK_ULL(51, 13) - -bool snp_probe_rmptable_info(void) -{ - u64 rmp_sz, rmp_base, rmp_end; - - rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); - rdmsrl(MSR_AMD64_RMP_END, rmp_end); - - if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) { - pr_err("Memory for the RMP table has not been reserved by BIOS\n"); - return false; - } - - if (rmp_base > rmp_end) { - pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end); - return false; - } - - rmp_sz = rmp_end - rmp_base + 1; - - probed_rmp_base = rmp_base; - probed_rmp_size = rmp_sz; - - pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n", - rmp_base, rmp_end); - - return true; -} - static void __init __snp_fixup_e820_tables(u64 pa) { if (IS_ALIGNED(pa, PMD_SIZE)) @@ -178,35 +204,176 @@ static void __init __snp_fixup_e820_tables(u64 pa) } } -void __init snp_fixup_e820_tables(void) +static void __init fixup_e820_tables_for_segmented_rmp(void) +{ + u64 pa, *rst, size, mapped_size; + unsigned int i; + + __snp_fixup_e820_tables(probed_rmp_base); + + pa = probed_rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ; + + __snp_fixup_e820_tables(pa + RST_SIZE); + + rst = early_memremap(pa, RST_SIZE); + if (!rst) + return; + + for (i = 0; i < rst_max_index; i++) { + pa = RST_ENTRY_SEGMENT_BASE(rst[i]); + mapped_size = RST_ENTRY_MAPPED_SIZE(rst[i]); + if (!mapped_size) + continue; + + __snp_fixup_e820_tables(pa); + + /* + * Mapped size in GB. Mapped size is allowed to exceed + * the segment coverage size, but gets reduced to the + * segment coverage size. + */ + mapped_size <<= 30; + if (mapped_size > rmp_segment_size) + mapped_size = rmp_segment_size; + + /* Calculate the RMP segment size (16 bytes/page mapped) */ + size = PHYS_PFN(mapped_size) << 4; + + __snp_fixup_e820_tables(pa + size); + } + + early_memunmap(rst, RST_SIZE); +} + +static void __init fixup_e820_tables_for_contiguous_rmp(void) { __snp_fixup_e820_tables(probed_rmp_base); __snp_fixup_e820_tables(probed_rmp_base + probed_rmp_size); } -/* - * Do the necessary preparations which are verified by the firmware as - * described in the SNP_INIT_EX firmware command description in the SNP - * firmware ABI spec. - */ -static int __init snp_rmptable_init(void) +void __init snp_fixup_e820_tables(void) { - u64 max_rmp_pfn, calc_rmp_sz, rmptable_size, rmp_end, val; - void *rmptable_start; + if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED) { + fixup_e820_tables_for_segmented_rmp(); + } else { + fixup_e820_tables_for_contiguous_rmp(); + } +} - if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) - return 0; +static bool __init clear_rmptable_bookkeeping(void) +{ + void *bk; - if (!amd_iommu_snp_en) - goto nosnp; + bk = memremap(probed_rmp_base, RMPTABLE_CPU_BOOKKEEPING_SZ, MEMREMAP_WB); + if (!bk) { + pr_err("Failed to map RMP bookkeeping area\n"); + return false; + } + + memset(bk, 0, RMPTABLE_CPU_BOOKKEEPING_SZ); + + memunmap(bk); + + return true; +} + +static bool __init alloc_rmp_segment_desc(u64 segment_pa, u64 segment_size, u64 pa) +{ + u64 rst_index, rmp_segment_size_max; + struct rmp_segment_desc *desc; + void *rmp_segment; + + /* Calculate the maximum size an RMP can be (16 bytes/page mapped) */ + rmp_segment_size_max = PHYS_PFN(rmp_segment_size) << 4; + + /* Validate the RMP segment size */ + if (segment_size > rmp_segment_size_max) { + pr_err("Invalid RMP size 0x%llx for configured segment size 0x%llx\n", + segment_size, rmp_segment_size_max); + return false; + } + + /* Validate the RMP segment table index */ + rst_index = RST_ENTRY_INDEX(pa); + if (rst_index >= rst_max_index) { + pr_err("Invalid RMP segment base address 0x%llx for configured segment size 0x%llx\n", + pa, rmp_segment_size); + return false; + } + + if (rmp_segment_table[rst_index]) { + pr_err("RMP segment descriptor already exists at index %llu\n", rst_index); + return false; + } + + rmp_segment = memremap(segment_pa, segment_size, MEMREMAP_WB); + if (!rmp_segment) { + pr_err("Failed to map RMP segment addr 0x%llx size 0x%llx\n", + segment_pa, segment_size); + return false; + } + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) { + memunmap(rmp_segment); + return false; + } + + desc->rmp_entry = rmp_segment; + desc->max_index = segment_size / sizeof(*desc->rmp_entry); + desc->size = segment_size; + + rmp_segment_table[rst_index] = desc; + + return true; +} + +static void __init free_rmp_segment_table(void) +{ + unsigned int i; + + for (i = 0; i < rst_max_index; i++) { + struct rmp_segment_desc *desc; + + desc = rmp_segment_table[i]; + if (!desc) + continue; + + memunmap(desc->rmp_entry); + + kfree(desc); + } + + free_page((unsigned long)rmp_segment_table); + + rmp_segment_table = NULL; +} + +/* Allocate the table used to index into the RMP segments */ +static bool __init alloc_rmp_segment_table(void) +{ + struct page *page; + + page = alloc_page(__GFP_ZERO); + if (!page) + return false; + + rmp_segment_table = page_address(page); + + return true; +} + +static bool __init setup_contiguous_rmptable(void) +{ + u64 max_rmp_pfn, calc_rmp_sz, rmptable_segment, rmptable_size, rmp_end; if (!probed_rmp_size) - goto nosnp; + return false; rmp_end = probed_rmp_base + probed_rmp_size - 1; /* - * Calculate the amount the memory that must be reserved by the BIOS to + * Calculate the amount of memory that must be reserved by the BIOS to * address the whole RAM, including the bookkeeping area. The RMP itself * must also be covered. */ @@ -218,15 +385,140 @@ static int __init snp_rmptable_init(void) if (calc_rmp_sz > probed_rmp_size) { pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n", calc_rmp_sz, probed_rmp_size); - goto nosnp; + return false; } - rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB); - if (!rmptable_start) { - pr_err("Failed to map RMP table\n"); - goto nosnp; + if (!alloc_rmp_segment_table()) + return false; + + /* Map only the RMP entries */ + rmptable_segment = probed_rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ; + rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ; + + if (!alloc_rmp_segment_desc(rmptable_segment, rmptable_size, 0)) { + free_rmp_segment_table(); + return false; } + return true; +} + +static bool __init setup_segmented_rmptable(void) +{ + u64 rst_pa, *rst, pa, ram_pa_end, ram_pa_max; + unsigned int i, max_index; + + if (!probed_rmp_base) + return false; + + if (!alloc_rmp_segment_table()) + return false; + + rst_pa = probed_rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ; + rst = memremap(rst_pa, RST_SIZE, MEMREMAP_WB); + if (!rst) { + pr_err("Failed to map RMP segment table addr 0x%llx\n", rst_pa); + goto e_free; + } + + pr_info("Segmented RMP using %lluGB segments\n", rmp_segment_size >> 30); + + ram_pa_max = max_pfn << PAGE_SHIFT; + + max_index = 0; + ram_pa_end = 0; + for (i = 0; i < rst_max_index; i++) { + u64 rmp_segment, rmp_size, mapped_size; + + mapped_size = RST_ENTRY_MAPPED_SIZE(rst[i]); + if (!mapped_size) + continue; + + max_index = i; + + /* + * Mapped size in GB. Mapped size is allowed to exceed the + * segment coverage size, but gets reduced to the segment + * coverage size. + */ + mapped_size <<= 30; + if (mapped_size > rmp_segment_size) { + pr_info("RMP segment %u mapped size (0x%llx) reduced to 0x%llx\n", + i, mapped_size, rmp_segment_size); + mapped_size = rmp_segment_size; + } + + rmp_segment = RST_ENTRY_SEGMENT_BASE(rst[i]); + + /* Calculate the RMP segment size (16 bytes/page mapped) */ + rmp_size = PHYS_PFN(mapped_size) << 4; + + pa = (u64)i << rmp_segment_shift; + + /* + * Some segments may be for MMIO mapped above system RAM. These + * segments are used for Trusted I/O. + */ + if (pa < ram_pa_max) + ram_pa_end = pa + mapped_size; + + if (!alloc_rmp_segment_desc(rmp_segment, rmp_size, pa)) + goto e_unmap; + + pr_info("RMP segment %u physical address [0x%llx - 0x%llx] covering [0x%llx - 0x%llx]\n", + i, rmp_segment, rmp_segment + rmp_size - 1, pa, pa + mapped_size - 1); + } + + if (ram_pa_max > ram_pa_end) { + pr_err("Segmented RMP does not cover full system RAM (expected 0x%llx got 0x%llx)\n", + ram_pa_max, ram_pa_end); + goto e_unmap; + } + + /* Adjust the maximum index based on the found segments */ + rst_max_index = max_index + 1; + + memunmap(rst); + + return true; + +e_unmap: + memunmap(rst); + +e_free: + free_rmp_segment_table(); + + return false; +} + +static bool __init setup_rmptable(void) +{ + if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED) { + return setup_segmented_rmptable(); + } else { + return setup_contiguous_rmptable(); + } +} + +/* + * Do the necessary preparations which are verified by the firmware as + * described in the SNP_INIT_EX firmware command description in the SNP + * firmware ABI spec. + */ +static int __init snp_rmptable_init(void) +{ + unsigned int i; + u64 val; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return 0; + + if (!amd_iommu_snp_en) + goto nosnp; + + if (!setup_rmptable()) + goto nosnp; + /* * Check if SEV-SNP is already enabled, this can happen in case of * kexec boot. @@ -235,7 +527,22 @@ static int __init snp_rmptable_init(void) if (val & MSR_AMD64_SYSCFG_SNP_EN) goto skip_enable; - memset(rmptable_start, 0, probed_rmp_size); + /* Zero out the RMP bookkeeping area */ + if (!clear_rmptable_bookkeeping()) { + free_rmp_segment_table(); + goto nosnp; + } + + /* Zero out the RMP entries */ + for (i = 0; i < rst_max_index; i++) { + struct rmp_segment_desc *desc; + + desc = rmp_segment_table[i]; + if (!desc) + continue; + + memset(desc->rmp_entry, 0, desc->size); + } /* Flush the caches to ensure that data is written before SNP is enabled. */ wbinvd_on_all_cpus(); @@ -246,12 +553,6 @@ static int __init snp_rmptable_init(void) on_each_cpu(snp_enable, NULL, 1); skip_enable: - rmptable_start += RMPTABLE_CPU_BOOKKEEPING_SZ; - rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ; - - rmptable = (struct rmpentry *)rmptable_start; - rmptable_max_pfn = rmptable_size / sizeof(struct rmpentry) - 1; - cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/rmptable_init:online", __snp_enable, NULL); /* @@ -272,48 +573,212 @@ nosnp: */ device_initcall(snp_rmptable_init); -static struct rmpentry *get_rmpentry(u64 pfn) +static void set_rmp_segment_info(unsigned int segment_shift) { - if (WARN_ON_ONCE(pfn > rmptable_max_pfn)) - return ERR_PTR(-EFAULT); - - return &rmptable[pfn]; + rmp_segment_shift = segment_shift; + rmp_segment_size = 1ULL << rmp_segment_shift; + rmp_segment_mask = rmp_segment_size - 1; } -static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level) -{ - struct rmpentry *large_entry, *entry; +#define RMP_ADDR_MASK GENMASK_ULL(51, 13) - if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) +static bool probe_contiguous_rmptable_info(void) +{ + u64 rmp_sz, rmp_base, rmp_end; + + rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); + rdmsrl(MSR_AMD64_RMP_END, rmp_end); + + if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) { + pr_err("Memory for the RMP table has not been reserved by BIOS\n"); + return false; + } + + if (rmp_base > rmp_end) { + pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end); + return false; + } + + rmp_sz = rmp_end - rmp_base + 1; + + /* Treat the contiguous RMP table as a single segment */ + rst_max_index = 1; + + set_rmp_segment_info(RMPTABLE_NON_SEGMENTED_SHIFT); + + probed_rmp_base = rmp_base; + probed_rmp_size = rmp_sz; + + pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n", + rmp_base, rmp_end); + + return true; +} + +static bool probe_segmented_rmptable_info(void) +{ + unsigned int eax, ebx, segment_shift, segment_shift_min, segment_shift_max; + u64 rmp_base, rmp_end; + + rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); + if (!(rmp_base & RMP_ADDR_MASK)) { + pr_err("Memory for the RMP table has not been reserved by BIOS\n"); + return false; + } + + rdmsrl(MSR_AMD64_RMP_END, rmp_end); + WARN_ONCE(rmp_end & RMP_ADDR_MASK, + "Segmented RMP enabled but RMP_END MSR is non-zero\n"); + + /* Obtain the min and max supported RMP segment size */ + eax = cpuid_eax(0x80000025); + segment_shift_min = eax & GENMASK(5, 0); + segment_shift_max = (eax & GENMASK(11, 6)) >> 6; + + /* Verify the segment size is within the supported limits */ + segment_shift = MSR_AMD64_RMP_SEGMENT_SHIFT(rmp_cfg); + if (segment_shift > segment_shift_max || segment_shift < segment_shift_min) { + pr_err("RMP segment size (%u) is not within advertised bounds (min=%u, max=%u)\n", + segment_shift, segment_shift_min, segment_shift_max); + return false; + } + + /* Override the max supported RST index if a hardware limit exists */ + ebx = cpuid_ebx(0x80000025); + if (ebx & BIT(10)) + rst_max_index = ebx & GENMASK(9, 0); + + set_rmp_segment_info(segment_shift); + + probed_rmp_base = rmp_base; + probed_rmp_size = 0; + + pr_info("Segmented RMP base table physical range [0x%016llx - 0x%016llx]\n", + rmp_base, rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ + RST_SIZE); + + return true; +} + +bool snp_probe_rmptable_info(void) +{ + if (cpu_feature_enabled(X86_FEATURE_SEGMENTED_RMP)) + rdmsrl(MSR_AMD64_RMP_CFG, rmp_cfg); + + if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED) + return probe_segmented_rmptable_info(); + else + return probe_contiguous_rmptable_info(); +} + +/* + * About the array_index_nospec() usage below: + * + * This function can get called by exported functions like + * snp_lookup_rmpentry(), which is used by the KVM #PF handler, among + * others, and since the @pfn passed in cannot always be trusted, + * speculation should be stopped as a protective measure. + */ +static struct rmpentry_raw *get_raw_rmpentry(u64 pfn) +{ + u64 paddr, rst_index, segment_index; + struct rmp_segment_desc *desc; + + if (!rmp_segment_table) return ERR_PTR(-ENODEV); - entry = get_rmpentry(pfn); - if (IS_ERR(entry)) - return entry; + paddr = pfn << PAGE_SHIFT; + + rst_index = RST_ENTRY_INDEX(paddr); + if (unlikely(rst_index >= rst_max_index)) + return ERR_PTR(-EFAULT); + + rst_index = array_index_nospec(rst_index, rst_max_index); + + desc = rmp_segment_table[rst_index]; + if (unlikely(!desc)) + return ERR_PTR(-EFAULT); + + segment_index = RMP_ENTRY_INDEX(paddr); + if (unlikely(segment_index >= desc->max_index)) + return ERR_PTR(-EFAULT); + + segment_index = array_index_nospec(segment_index, desc->max_index); + + return desc->rmp_entry + segment_index; +} + +static int get_rmpentry(u64 pfn, struct rmpentry *e) +{ + struct rmpentry_raw *e_raw; + + if (cpu_feature_enabled(X86_FEATURE_RMPREAD)) { + int ret; + + /* Binutils version 2.44 supports the RMPREAD mnemonic. */ + asm volatile(".byte 0xf2, 0x0f, 0x01, 0xfd" + : "=a" (ret) + : "a" (pfn << PAGE_SHIFT), "c" (e) + : "memory", "cc"); + + return ret; + } + + e_raw = get_raw_rmpentry(pfn); + if (IS_ERR(e_raw)) + return PTR_ERR(e_raw); + + /* + * Map the raw RMP table entry onto the RMPREAD output format. + * The 2MB region status indicator (hpage_region_status field) is not + * calculated, since the overhead could be significant and the field + * is not used. + */ + memset(e, 0, sizeof(*e)); + e->gpa = e_raw->gpa << PAGE_SHIFT; + e->asid = e_raw->asid; + e->assigned = e_raw->assigned; + e->pagesize = e_raw->pagesize; + e->immutable = e_raw->immutable; + + return 0; +} + +static int __snp_lookup_rmpentry(u64 pfn, struct rmpentry *e, int *level) +{ + struct rmpentry e_large; + int ret; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return -ENODEV; + + ret = get_rmpentry(pfn, e); + if (ret) + return ret; /* * Find the authoritative RMP entry for a PFN. This can be either a 4K * RMP entry or a special large RMP entry that is authoritative for a * whole 2M area. */ - large_entry = get_rmpentry(pfn & PFN_PMD_MASK); - if (IS_ERR(large_entry)) - return large_entry; + ret = get_rmpentry(pfn & PFN_PMD_MASK, &e_large); + if (ret) + return ret; - *level = RMP_TO_PG_LEVEL(large_entry->pagesize); + *level = RMP_TO_PG_LEVEL(e_large.pagesize); - return entry; + return 0; } int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { - struct rmpentry *e; + struct rmpentry e; + int ret; - e = __snp_lookup_rmpentry(pfn, level); - if (IS_ERR(e)) - return PTR_ERR(e); + ret = __snp_lookup_rmpentry(pfn, &e, level); + if (ret) + return ret; - *assigned = !!e->assigned; + *assigned = !!e.assigned; return 0; } EXPORT_SYMBOL_GPL(snp_lookup_rmpentry); @@ -326,20 +791,28 @@ EXPORT_SYMBOL_GPL(snp_lookup_rmpentry); */ static void dump_rmpentry(u64 pfn) { + struct rmpentry_raw *e_raw; u64 pfn_i, pfn_end; - struct rmpentry *e; - int level; + struct rmpentry e; + int level, ret; - e = __snp_lookup_rmpentry(pfn, &level); - if (IS_ERR(e)) { - pr_err("Failed to read RMP entry for PFN 0x%llx, error %ld\n", - pfn, PTR_ERR(e)); + ret = __snp_lookup_rmpentry(pfn, &e, &level); + if (ret) { + pr_err("Failed to read RMP entry for PFN 0x%llx, error %d\n", + pfn, ret); return; } - if (e->assigned) { + if (e.assigned) { + e_raw = get_raw_rmpentry(pfn); + if (IS_ERR(e_raw)) { + pr_err("Failed to read RMP contents for PFN 0x%llx, error %ld\n", + pfn, PTR_ERR(e_raw)); + return; + } + pr_info("PFN 0x%llx, RMP entry: [0x%016llx - 0x%016llx]\n", - pfn, e->lo, e->hi); + pfn, e_raw->lo, e_raw->hi); return; } @@ -358,16 +831,16 @@ static void dump_rmpentry(u64 pfn) pfn, pfn_i, pfn_end); while (pfn_i < pfn_end) { - e = __snp_lookup_rmpentry(pfn_i, &level); - if (IS_ERR(e)) { - pr_err("Error %ld reading RMP entry for PFN 0x%llx\n", - PTR_ERR(e), pfn_i); + e_raw = get_raw_rmpentry(pfn_i); + if (IS_ERR(e_raw)) { + pr_err("Error %ld reading RMP contents for PFN 0x%llx\n", + PTR_ERR(e_raw), pfn_i); pfn_i++; continue; } - if (e->lo || e->hi) - pr_info("PFN: 0x%llx, [0x%016llx - 0x%016llx]\n", pfn_i, e->lo, e->hi); + if (e_raw->lo || e_raw->hi) + pr_info("PFN: 0x%llx, [0x%016llx - 0x%016llx]\n", pfn_i, e_raw->lo, e_raw->hi); pfn_i++; } } diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c index 4e2b2e2ac9f9..7fdb37387886 100644 --- a/arch/x86/virt/vmx/tdx/tdx.c +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -270,57 +270,15 @@ static int read_sys_metadata_field(u64 field_id, u64 *data) return 0; } -static int read_sys_metadata_field16(u64 field_id, - int offset, - struct tdx_tdmr_sysinfo *ts) -{ - u16 *ts_member = ((void *)ts) + offset; - u64 tmp; - int ret; +#include "tdx_global_metadata.c" - if (WARN_ON_ONCE(MD_FIELD_ID_ELE_SIZE_CODE(field_id) != - MD_FIELD_ID_ELE_SIZE_16BIT)) +static int check_features(struct tdx_sys_info *sysinfo) +{ + u64 tdx_features0 = sysinfo->features.tdx_features0; + + if (!(tdx_features0 & TDX_FEATURES0_NO_RBP_MOD)) { + pr_err("frame pointer (RBP) clobber bug present, upgrade TDX module\n"); return -EINVAL; - - ret = read_sys_metadata_field(field_id, &tmp); - if (ret) - return ret; - - *ts_member = tmp; - - return 0; -} - -struct field_mapping { - u64 field_id; - int offset; -}; - -#define TD_SYSINFO_MAP(_field_id, _offset) \ - { .field_id = MD_FIELD_ID_##_field_id, \ - .offset = offsetof(struct tdx_tdmr_sysinfo, _offset) } - -/* Map TD_SYSINFO fields into 'struct tdx_tdmr_sysinfo': */ -static const struct field_mapping fields[] = { - TD_SYSINFO_MAP(MAX_TDMRS, max_tdmrs), - TD_SYSINFO_MAP(MAX_RESERVED_PER_TDMR, max_reserved_per_tdmr), - TD_SYSINFO_MAP(PAMT_4K_ENTRY_SIZE, pamt_entry_size[TDX_PS_4K]), - TD_SYSINFO_MAP(PAMT_2M_ENTRY_SIZE, pamt_entry_size[TDX_PS_2M]), - TD_SYSINFO_MAP(PAMT_1G_ENTRY_SIZE, pamt_entry_size[TDX_PS_1G]), -}; - -static int get_tdx_tdmr_sysinfo(struct tdx_tdmr_sysinfo *tdmr_sysinfo) -{ - int ret; - int i; - - /* Populate 'tdmr_sysinfo' fields using the mapping structure above: */ - for (i = 0; i < ARRAY_SIZE(fields); i++) { - ret = read_sys_metadata_field16(fields[i].field_id, - fields[i].offset, - tdmr_sysinfo); - if (ret) - return ret; } return 0; @@ -342,13 +300,13 @@ static int tdmr_size_single(u16 max_reserved_per_tdmr) } static int alloc_tdmr_list(struct tdmr_info_list *tdmr_list, - struct tdx_tdmr_sysinfo *tdmr_sysinfo) + struct tdx_sys_info_tdmr *sysinfo_tdmr) { size_t tdmr_sz, tdmr_array_sz; void *tdmr_array; - tdmr_sz = tdmr_size_single(tdmr_sysinfo->max_reserved_per_tdmr); - tdmr_array_sz = tdmr_sz * tdmr_sysinfo->max_tdmrs; + tdmr_sz = tdmr_size_single(sysinfo_tdmr->max_reserved_per_tdmr); + tdmr_array_sz = tdmr_sz * sysinfo_tdmr->max_tdmrs; /* * To keep things simple, allocate all TDMRs together. @@ -367,7 +325,7 @@ static int alloc_tdmr_list(struct tdmr_info_list *tdmr_list, * at a given index in the TDMR list. */ tdmr_list->tdmr_sz = tdmr_sz; - tdmr_list->max_tdmrs = tdmr_sysinfo->max_tdmrs; + tdmr_list->max_tdmrs = sysinfo_tdmr->max_tdmrs; tdmr_list->nr_consumed_tdmrs = 0; return 0; @@ -921,25 +879,29 @@ static int tdmrs_populate_rsvd_areas_all(struct tdmr_info_list *tdmr_list, /* * Construct a list of TDMRs on the preallocated space in @tdmr_list * to cover all TDX memory regions in @tmb_list based on the TDX module - * TDMR global information in @tdmr_sysinfo. + * TDMR global information in @sysinfo_tdmr. */ static int construct_tdmrs(struct list_head *tmb_list, struct tdmr_info_list *tdmr_list, - struct tdx_tdmr_sysinfo *tdmr_sysinfo) + struct tdx_sys_info_tdmr *sysinfo_tdmr) { + u16 pamt_entry_size[TDX_PS_NR] = { + sysinfo_tdmr->pamt_4k_entry_size, + sysinfo_tdmr->pamt_2m_entry_size, + sysinfo_tdmr->pamt_1g_entry_size, + }; int ret; ret = fill_out_tdmrs(tmb_list, tdmr_list); if (ret) return ret; - ret = tdmrs_set_up_pamt_all(tdmr_list, tmb_list, - tdmr_sysinfo->pamt_entry_size); + ret = tdmrs_set_up_pamt_all(tdmr_list, tmb_list, pamt_entry_size); if (ret) return ret; ret = tdmrs_populate_rsvd_areas_all(tdmr_list, tmb_list, - tdmr_sysinfo->max_reserved_per_tdmr); + sysinfo_tdmr->max_reserved_per_tdmr); if (ret) tdmrs_free_pamt_all(tdmr_list); @@ -1098,9 +1060,18 @@ static int init_tdmrs(struct tdmr_info_list *tdmr_list) static int init_tdx_module(void) { - struct tdx_tdmr_sysinfo tdmr_sysinfo; + struct tdx_sys_info sysinfo; int ret; + ret = get_tdx_sys_info(&sysinfo); + if (ret) + return ret; + + /* Check whether the kernel can support this module */ + ret = check_features(&sysinfo); + if (ret) + return ret; + /* * To keep things simple, assume that all TDX-protected memory * will come from the page allocator. Make sure all pages in the @@ -1117,17 +1088,13 @@ static int init_tdx_module(void) if (ret) goto out_put_tdxmem; - ret = get_tdx_tdmr_sysinfo(&tdmr_sysinfo); - if (ret) - goto err_free_tdxmem; - /* Allocate enough space for constructing TDMRs */ - ret = alloc_tdmr_list(&tdx_tdmr_list, &tdmr_sysinfo); + ret = alloc_tdmr_list(&tdx_tdmr_list, &sysinfo.tdmr); if (ret) goto err_free_tdxmem; /* Cover all TDX-usable memory regions in TDMRs */ - ret = construct_tdmrs(&tdx_memlist, &tdx_tdmr_list, &tdmr_sysinfo); + ret = construct_tdmrs(&tdx_memlist, &tdx_tdmr_list, &sysinfo.tdmr); if (ret) goto err_free_tdmrs; diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h index b701f69485d3..4e3d533cdd61 100644 --- a/arch/x86/virt/vmx/tdx/tdx.h +++ b/arch/x86/virt/vmx/tdx/tdx.h @@ -3,6 +3,7 @@ #define _X86_VIRT_TDX_H #include +#include "tdx_global_metadata.h" /* * This file contains both macros and data structures defined by the TDX @@ -26,35 +27,6 @@ #define PT_NDA 0x0 #define PT_RSVD 0x1 -/* - * Global scope metadata field ID. - * - * See Table "Global Scope Metadata", TDX module 1.5 ABI spec. - */ -#define MD_FIELD_ID_MAX_TDMRS 0x9100000100000008ULL -#define MD_FIELD_ID_MAX_RESERVED_PER_TDMR 0x9100000100000009ULL -#define MD_FIELD_ID_PAMT_4K_ENTRY_SIZE 0x9100000100000010ULL -#define MD_FIELD_ID_PAMT_2M_ENTRY_SIZE 0x9100000100000011ULL -#define MD_FIELD_ID_PAMT_1G_ENTRY_SIZE 0x9100000100000012ULL - -/* - * Sub-field definition of metadata field ID. - * - * See Table "MD_FIELD_ID (Metadata Field Identifier / Sequence Header) - * Definition", TDX module 1.5 ABI spec. - * - * - Bit 33:32: ELEMENT_SIZE_CODE -- size of a single element of metadata - * - * 0: 8 bits - * 1: 16 bits - * 2: 32 bits - * 3: 64 bits - */ -#define MD_FIELD_ID_ELE_SIZE_CODE(_field_id) \ - (((_field_id) & GENMASK_ULL(33, 32)) >> 32) - -#define MD_FIELD_ID_ELE_SIZE_16BIT 1 - struct tdmr_reserved_area { u64 offset; u64 size; @@ -80,6 +52,9 @@ struct tdmr_info { DECLARE_FLEX_ARRAY(struct tdmr_reserved_area, reserved_areas); } __packed __aligned(TDMR_INFO_ALIGNMENT); +/* Bit definitions of TDX_FEATURES0 metadata field */ +#define TDX_FEATURES0_NO_RBP_MOD BIT(18) + /* * Do not put any hardware-defined TDX structure representations below * this comment! @@ -99,13 +74,6 @@ struct tdx_memblock { int nid; }; -/* "TDMR info" part of "Global Scope Metadata" for constructing TDMRs */ -struct tdx_tdmr_sysinfo { - u16 max_tdmrs; - u16 max_reserved_per_tdmr; - u16 pamt_entry_size[TDX_PS_NR]; -}; - /* Warn if kernel has less than TDMR_NR_WARN TDMRs after allocation */ #define TDMR_NR_WARN 4 diff --git a/arch/x86/virt/vmx/tdx/tdx_global_metadata.c b/arch/x86/virt/vmx/tdx/tdx_global_metadata.c new file mode 100644 index 000000000000..8027a24d1c6e --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdx_global_metadata.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Automatically generated functions to read TDX global metadata. + * + * This file doesn't compile on its own as it lacks of inclusion + * of SEAMCALL wrapper primitive which reads global metadata. + * Include this file to other C file instead. + */ + +static int get_tdx_sys_info_features(struct tdx_sys_info_features *sysinfo_features) +{ + int ret = 0; + u64 val; + + if (!ret && !(ret = read_sys_metadata_field(0x0A00000300000008, &val))) + sysinfo_features->tdx_features0 = val; + + return ret; +} + +static int get_tdx_sys_info_tdmr(struct tdx_sys_info_tdmr *sysinfo_tdmr) +{ + int ret = 0; + u64 val; + + if (!ret && !(ret = read_sys_metadata_field(0x9100000100000008, &val))) + sysinfo_tdmr->max_tdmrs = val; + if (!ret && !(ret = read_sys_metadata_field(0x9100000100000009, &val))) + sysinfo_tdmr->max_reserved_per_tdmr = val; + if (!ret && !(ret = read_sys_metadata_field(0x9100000100000010, &val))) + sysinfo_tdmr->pamt_4k_entry_size = val; + if (!ret && !(ret = read_sys_metadata_field(0x9100000100000011, &val))) + sysinfo_tdmr->pamt_2m_entry_size = val; + if (!ret && !(ret = read_sys_metadata_field(0x9100000100000012, &val))) + sysinfo_tdmr->pamt_1g_entry_size = val; + + return ret; +} + +static int get_tdx_sys_info(struct tdx_sys_info *sysinfo) +{ + int ret = 0; + + ret = ret ?: get_tdx_sys_info_features(&sysinfo->features); + ret = ret ?: get_tdx_sys_info_tdmr(&sysinfo->tdmr); + + return ret; +} diff --git a/arch/x86/virt/vmx/tdx/tdx_global_metadata.h b/arch/x86/virt/vmx/tdx/tdx_global_metadata.h new file mode 100644 index 000000000000..6dd3c9695f59 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdx_global_metadata.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Automatically generated TDX global metadata structures. */ +#ifndef _X86_VIRT_TDX_AUTO_GENERATED_TDX_GLOBAL_METADATA_H +#define _X86_VIRT_TDX_AUTO_GENERATED_TDX_GLOBAL_METADATA_H + +#include + +struct tdx_sys_info_features { + u64 tdx_features0; +}; + +struct tdx_sys_info_tdmr { + u16 max_tdmrs; + u16 max_reserved_per_tdmr; + u16 pamt_4k_entry_size; + u16 pamt_2m_entry_size; + u16 pamt_1g_entry_size; +}; + +struct tdx_sys_info { + struct tdx_sys_info_features features; + struct tdx_sys_info_tdmr tdmr; +}; + +#endif diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 84e5adbd0925..43dcd8c7badc 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -2,6 +2,7 @@ #include #include +#include #include #include #include @@ -21,7 +22,8 @@ #include "xen-ops.h" -EXPORT_SYMBOL_GPL(hypercall_page); +DEFINE_STATIC_CALL(xen_hypercall, xen_hypercall_hvm); +EXPORT_STATIC_CALL_TRAMP(xen_hypercall); /* * Pointer to the xen_vcpu_info structure or @@ -68,6 +70,67 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; +static __ref void xen_get_vendor(void) +{ + init_cpu_devs(); + cpu_detect(&boot_cpu_data); + get_cpu_vendor(&boot_cpu_data); +} + +void xen_hypercall_setfunc(void) +{ + if (static_call_query(xen_hypercall) != xen_hypercall_hvm) + return; + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + static_call_update(xen_hypercall, xen_hypercall_amd); + else + static_call_update(xen_hypercall, xen_hypercall_intel); +} + +/* + * Evaluate processor vendor in order to select the correct hypercall + * function for HVM/PVH guests. + * Might be called very early in boot before vendor has been set by + * early_cpu_init(). + */ +noinstr void *__xen_hypercall_setfunc(void) +{ + void (*func)(void); + + /* + * Xen is supported only on CPUs with CPUID, so testing for + * X86_FEATURE_CPUID is a test for early_cpu_init() having been + * run. + * + * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty + * dependency chain: it is being called via the xen_hypercall static + * call when running as a PVH or HVM guest. Hypercalls need to be + * noinstr due to PV guests using hypercalls in noinstr code. So we + * can safely tag the function body as "instrumentation ok", since + * the PV guest requirement is not of interest here (xen_get_vendor() + * calls noinstr functions, and static_call_update_early() might do + * so, too). + */ + instrumentation_begin(); + + if (!boot_cpu_has(X86_FEATURE_CPUID)) + xen_get_vendor(); + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + func = xen_hypercall_amd; + else + func = xen_hypercall_intel; + + static_call_update_early(xen_hypercall, func); + + instrumentation_end(); + + return func; +} + static int xen_cpu_up_online(unsigned int cpu) { xen_init_lock_cpu(cpu); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 24d2957a4726..fe57ff85d004 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -106,15 +106,8 @@ static void __init init_hvm_pv_info(void) /* PVH set up hypercall page in xen_prepare_pvh(). */ if (xen_pvh_domain()) pv_info.name = "Xen PVH"; - else { - u64 pfn; - uint32_t msr; - + else pv_info.name = "Xen HVM"; - msr = cpuid_ebx(base + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - } xen_setup_features(); @@ -300,6 +293,10 @@ static uint32_t __init xen_platform_hvm(void) if (xen_pv_domain()) return 0; + /* Set correct hypercall function. */ + if (xen_domain) + xen_hypercall_setfunc(); + if (xen_pvh_domain() && nopv) { /* Guest booting via the Xen-PVH boot entry goes here */ pr_info("\"nopv\" parameter is ignored in PVH guest\n"); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index d6818c6cafda..5e57835e999d 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -49,6 +49,7 @@ #include #include +#include #include #include #include @@ -171,7 +172,7 @@ static void __init xen_set_mtrr_data(void) /* Only overwrite MTRR state if any MTRR could be got from Xen. */ if (reg) - mtrr_overwrite_state(var, reg, MTRR_TYPE_UNCACHABLE); + guest_force_mtrr_state(var, reg, MTRR_TYPE_UNCACHABLE); #endif } @@ -195,7 +196,7 @@ static void __init xen_pv_init_platform(void) if (xen_initial_domain()) xen_set_mtrr_data(); else - mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); + guest_force_mtrr_state(NULL, 0, MTRR_TYPE_WRBACK); /* Adjust nr_cpu_ids before "enumeration" happens */ xen_smp_count_cpus(); @@ -230,7 +231,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, or_ebx = smp_processor_id() << 24; break; - case CPUID_MWAIT_LEAF: + case CPUID_LEAF_MWAIT: /* Synthesize the values.. */ *ax = 0; *bx = 0; @@ -300,7 +301,7 @@ static bool __init xen_check_mwait(void) * ecx and edx. The hypercall provides only partial information. */ - ax = CPUID_MWAIT_LEAF; + ax = CPUID_LEAF_MWAIT; bx = 0; cx = 0; dx = 0; @@ -1161,8 +1162,6 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = { .write_cr4 = xen_write_cr4, - .wbinvd = pv_native_wbinvd, - .read_msr = xen_read_msr, .write_msr = xen_write_msr, @@ -1341,6 +1340,9 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) xen_domain_type = XEN_PV_DOMAIN; xen_start_flags = xen_start_info->flags; + /* Interrupts are guaranteed to be off initially. */ + early_boot_irqs_disabled = true; + static_call_update_early(xen_hypercall, xen_hypercall_pv); xen_setup_features(); @@ -1431,7 +1433,6 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); local_irq_disable(); - early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index bf68c329fc01..0e3d930bcb89 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -129,17 +129,10 @@ static void __init pvh_arch_setup(void) void __init xen_pvh_init(struct boot_params *boot_params) { - u32 msr; - u64 pfn; - xen_pvh = 1; xen_domain_type = XEN_HVM_DOMAIN; xen_start_flags = pvh_start_info.flags; - msr = cpuid_ebx(xen_cpuid_base() + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - x86_init.oem.arch_setup = pvh_arch_setup; x86_init.oem.banner = xen_banner; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 55a4996d0c04..2c70cd35e72c 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -781,6 +781,7 @@ void xen_mm_pin_all(void) { struct page *page; + spin_lock(&init_mm.page_table_lock); spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { @@ -791,6 +792,7 @@ void xen_mm_pin_all(void) } spin_unlock(&pgd_lock); + spin_unlock(&init_mm.page_table_lock); } static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page, @@ -887,6 +889,7 @@ void xen_mm_unpin_all(void) { struct page *page; + spin_lock(&init_mm.page_table_lock); spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { @@ -898,6 +901,7 @@ void xen_mm_unpin_all(void) } spin_unlock(&pgd_lock); + spin_unlock(&init_mm.page_table_lock); } static void xen_enter_mmap(struct mm_struct *mm) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b52d3e17e2c1..56914e21e303 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -178,13 +178,7 @@ static void p2m_init_identity(unsigned long *p2m, unsigned long pfn) static void * __ref alloc_p2m_page(void) { if (unlikely(!slab_is_available())) { - void *ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - - if (!ptr) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); - - return ptr; + return memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); } return (void *)__get_free_page(GFP_KERNEL); diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 83189cf5cdce..b518f36d1ca2 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,9 +20,32 @@ #include #include +#include #include <../entry/calling.h> .pushsection .noinstr.text, "ax" +/* + * PV hypercall interface to the hypervisor. + * + * Called via inline asm(), so better preserve %rcx and %r11. + * + * Input: + * %eax: hypercall number + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %rax + */ +SYM_FUNC_START(xen_hypercall_pv) + ANNOTATE_NOENDBR + push %rcx + push %r11 + UNWIND_HINT_SAVE + syscall + UNWIND_HINT_RESTORE + pop %r11 + pop %rcx + RET +SYM_FUNC_END(xen_hypercall_pv) + /* * Disabling events is simply a matter of making the event mask * non-zero. @@ -176,7 +199,6 @@ SYM_CODE_START(xen_early_idt_handler_array) SYM_CODE_END(xen_early_idt_handler_array) __FINIT -hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* * Xen64 iret frame: * @@ -186,17 +208,28 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * cs * rip <-- standard iret frame * - * flags + * flags <-- xen_iret must push from here on * - * rcx } - * r11 }<-- pushed by hypercall page - * rsp->rax } + * rcx + * r11 + * rsp->rax */ +.macro xen_hypercall_iret + pushq $0 /* Flags */ + push %rcx + push %r11 + push %rax + mov $__HYPERVISOR_iret, %eax + syscall /* Do the IRET. */ +#ifdef CONFIG_MITIGATION_SLS + int3 +#endif +.endm + SYM_CODE_START(xen_iret) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_iret) /* @@ -301,8 +334,7 @@ SYM_CODE_START(xen_entry_SYSENTER_compat) ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_entry_SYSENTER_compat) SYM_CODE_END(xen_entry_SYSCALL_compat) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 7f6c69dbb816..9252652afe59 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -6,9 +6,11 @@ #include #include +#include #include #include +#include #include #include #include @@ -20,28 +22,6 @@ #include #include -.pushsection .noinstr.text, "ax" - .balign PAGE_SIZE -SYM_CODE_START(hypercall_page) - .rept (PAGE_SIZE / 32) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - /* - * Xen will write the hypercall page, and sort out ENDBR. - */ - .skip 31, 0xcc - .endr - -#define HYPERCALL(n) \ - .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ - .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 -#include -#undef HYPERCALL -SYM_CODE_END(hypercall_page) -.popsection - #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) @@ -87,6 +67,87 @@ SYM_CODE_END(xen_cpu_bringup_again) #endif #endif + .pushsection .noinstr.text, "ax" +/* + * Xen hypercall interface to the hypervisor. + * + * Input: + * %eax: hypercall number + * 32-bit: + * %ebx, %ecx, %edx, %esi, %edi: args 1..5 for the hypercall + * 64-bit: + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %[er]ax + */ +SYM_FUNC_START(xen_hypercall_hvm) + ENDBR + FRAME_BEGIN + /* Save all relevant registers (caller save and arguments). */ +#ifdef CONFIG_X86_32 + push %eax + push %ebx + push %ecx + push %edx + push %esi + push %edi +#else + push %rax + push %rcx + push %rdx + push %rdi + push %rsi + push %r11 + push %r10 + push %r9 + push %r8 +#ifdef CONFIG_FRAME_POINTER + pushq $0 /* Dummy push for stack alignment. */ +#endif +#endif + /* Set the vendor specific function. */ + call __xen_hypercall_setfunc + /* Set ZF = 1 if AMD, Restore saved registers. */ +#ifdef CONFIG_X86_32 + lea xen_hypercall_amd, %ebx + cmp %eax, %ebx + pop %edi + pop %esi + pop %edx + pop %ecx + pop %ebx + pop %eax +#else + lea xen_hypercall_amd(%rip), %rbx + cmp %rax, %rbx +#ifdef CONFIG_FRAME_POINTER + pop %rax /* Dummy pop. */ +#endif + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %rsi + pop %rdi + pop %rdx + pop %rcx + pop %rax +#endif + /* Use correct hypercall function. */ + jz xen_hypercall_amd + jmp xen_hypercall_intel +SYM_FUNC_END(xen_hypercall_hvm) + +SYM_FUNC_START(xen_hypercall_amd) + vmmcall + RET +SYM_FUNC_END(xen_hypercall_amd) + +SYM_FUNC_START(xen_hypercall_intel) + vmcall + RET +SYM_FUNC_END(xen_hypercall_intel) + .popsection + ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6") ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0") @@ -116,8 +177,6 @@ SYM_CODE_END(xen_cpu_bringup_again) #else # define FEATURES_DOM0 0 #endif - ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .globl xen_elfnote_hypercall_page; - xen_elfnote_hypercall_page: _ASM_PTR xen_elfnote_hypercall_page_value - .) ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long FEATURES_PV | FEATURES_PVH | FEATURES_DOM0) ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index e1b782e823e6..63c13a2ccf55 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -326,4 +326,13 @@ static inline void xen_smp_intr_free_pv(unsigned int cpu) {} static inline void xen_smp_count_cpus(void) { } #endif /* CONFIG_SMP */ +#ifdef CONFIG_XEN_PV +void xen_hypercall_pv(void); +#endif +void xen_hypercall_hvm(void); +void xen_hypercall_amd(void); +void xen_hypercall_intel(void); +void xen_hypercall_setfunc(void); +void *__xen_hypercall_setfunc(void); + #endif /* XEN_OPS_H */ diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h index 7fc0f9126dd3..1919ee9c3dd6 100644 --- a/arch/xtensa/include/asm/pgalloc.h +++ b/arch/xtensa/include/asm/pgalloc.h @@ -29,7 +29,7 @@ static inline pgd_t* pgd_alloc(struct mm_struct *mm) { - return (pgd_t*) __get_free_page(GFP_KERNEL | __GFP_ZERO); + return __pgd_alloc(mm, 0); } static inline void ptes_clear(pte_t *ptep) diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 7ed1a2085bd7..47b5df86ab5c 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -160,9 +160,7 @@ struct thread_struct { struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK]; struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK]; #endif - /* Make structure 16 bytes aligned. */ - int align[0] __attribute__ ((aligned(16))); -}; +} __aligned(16); /* This decides where the kernel will search for a free chunk of vm * space during mmap's. diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index e51f2060e830..f72e280363be 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -55,7 +55,7 @@ extern int initrd_below_start_ok; #endif #ifdef CONFIG_USE_OF -void *dtb_start = __dtb_start; +static void *dtb_start __initdata = __dtb_start; #endif extern unsigned long loops_per_jiffy; diff --git a/arch/xtensa/mm/kasan_init.c b/arch/xtensa/mm/kasan_init.c index f00d122aa806..f39c4d83173a 100644 --- a/arch/xtensa/mm/kasan_init.c +++ b/arch/xtensa/mm/kasan_init.c @@ -39,11 +39,7 @@ static void __init populate(void *start, void *end) unsigned long i, j; unsigned long vaddr = (unsigned long)start; pmd_t *pmd = pmd_off_k(vaddr); - pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE); - - if (!pte) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, n_pages * sizeof(pte_t), PAGE_SIZE); + pte_t *pte = memblock_alloc_or_panic(n_pages * sizeof(pte_t), PAGE_SIZE); pr_debug("%s: %p - %p\n", __func__, start, end); diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index d6d2b533a574..6ed009318d24 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -75,7 +76,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector, if (offset > dev->size || dev->size - offset < nbytes) { pr_notice("Beyond-end %s (%ld %ld)\n", - write ? "write" : "read", offset, nbytes); + str_write_read(write), offset, nbytes); return; } diff --git a/block/Makefile b/block/Makefile index ddfd21c1a9ff..33748123710b 100644 --- a/block/Makefile +++ b/block/Makefile @@ -27,8 +27,6 @@ bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o -obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o -obj-$(CONFIG_BLK_MQ_VIRTIO) += blk-mq-virtio.o obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o obj-$(CONFIG_BLK_WBT) += blk-wbt.o obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o diff --git a/block/bdev.c b/block/bdev.c index 738e3c8457e7..9d73a8fbf7f9 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -155,8 +155,7 @@ int set_blocksize(struct file *file, int size) struct inode *inode = file->f_mapping->host; struct block_device *bdev = I_BDEV(inode); - /* Size must be a power of two, and between 512 and PAGE_SIZE */ - if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) + if (blk_validate_block_size(size)) return -EINVAL; /* Size cannot be smaller than the size supported by the device */ diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 95dd7b795935..167542201603 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -6844,16 +6844,24 @@ static struct bfq_queue *bfq_waker_bfqq(struct bfq_queue *bfqq) if (new_bfqq == waker_bfqq) { /* * If waker_bfqq is in the merge chain, and current - * is the only procress. + * is the only process, waker_bfqq can be freed. */ if (bfqq_process_refs(waker_bfqq) == 1) return NULL; - break; + + return waker_bfqq; } new_bfqq = new_bfqq->new_bfqq; } + /* + * If waker_bfqq is not in the merge chain, and it's procress reference + * is 0, waker_bfqq can be freed. + */ + if (bfqq_process_refs(waker_bfqq) == 0) + return NULL; + return waker_bfqq; } @@ -7614,7 +7622,7 @@ static ssize_t bfq_low_latency_store(struct elevator_queue *e, #define BFQ_ATTR(name) \ __ATTR(name, 0644, bfq_##name##_show, bfq_##name##_store) -static struct elv_fs_entry bfq_attrs[] = { +static const struct elv_fs_entry bfq_attrs[] = { BFQ_ATTR(fifo_expire_sync), BFQ_ATTR(fifo_expire_async), BFQ_ATTR(back_seek_max), diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 2a4bd6611692..5d81ad9a3d20 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -118,17 +118,18 @@ static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs, static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip) { - unsigned short nr_vecs = bip->bip_max_vcnt - 1; - struct bio_vec *copy = &bip->bip_vec[1]; - size_t bytes = bip->bip_iter.bi_size; - struct iov_iter iter; + unsigned short orig_nr_vecs = bip->bip_max_vcnt - 1; + struct bio_vec *orig_bvecs = &bip->bip_vec[1]; + struct bio_vec *bounce_bvec = &bip->bip_vec[0]; + size_t bytes = bounce_bvec->bv_len; + struct iov_iter orig_iter; int ret; - iov_iter_bvec(&iter, ITER_DEST, copy, nr_vecs, bytes); - ret = copy_to_iter(bvec_virt(bip->bip_vec), bytes, &iter); + iov_iter_bvec(&orig_iter, ITER_DEST, orig_bvecs, orig_nr_vecs, bytes); + ret = copy_to_iter(bvec_virt(bounce_bvec), bytes, &orig_iter); WARN_ON_ONCE(ret != bytes); - bio_integrity_unpin_bvec(copy, nr_vecs, true); + bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs, true); } /** @@ -301,16 +302,15 @@ static unsigned int bvec_from_pages(struct bio_vec *bvec, struct page **pages, return nr_bvecs; } -int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes) +int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); unsigned int align = blk_lim_dma_alignment_and_pad(&q->limits); struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages; struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec; + size_t offset, bytes = iter->count; unsigned int direction, nr_bvecs; - struct iov_iter iter; int ret, nr_vecs; - size_t offset; bool copy; if (bio_integrity(bio)) @@ -323,8 +323,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes) else direction = ITER_SOURCE; - iov_iter_ubuf(&iter, direction, ubuf, bytes); - nr_vecs = iov_iter_npages(&iter, BIO_MAX_VECS + 1); + nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS + 1); if (nr_vecs > BIO_MAX_VECS) return -E2BIG; if (nr_vecs > UIO_FASTIOV) { @@ -334,8 +333,8 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes) pages = NULL; } - copy = !iov_iter_is_aligned(&iter, align, align); - ret = iov_iter_extract_pages(&iter, &pages, bytes, nr_vecs, 0, &offset); + copy = !iov_iter_is_aligned(iter, align, align); + ret = iov_iter_extract_pages(iter, &pages, bytes, nr_vecs, 0, &offset); if (unlikely(ret < 0)) goto free_bvec; @@ -365,6 +364,55 @@ free_bvec: return ret; } +static void bio_uio_meta_to_bip(struct bio *bio, struct uio_meta *meta) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + + if (meta->flags & IO_INTEGRITY_CHK_GUARD) + bip->bip_flags |= BIP_CHECK_GUARD; + if (meta->flags & IO_INTEGRITY_CHK_APPTAG) + bip->bip_flags |= BIP_CHECK_APPTAG; + if (meta->flags & IO_INTEGRITY_CHK_REFTAG) + bip->bip_flags |= BIP_CHECK_REFTAG; + + bip->app_tag = meta->app_tag; +} + +int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta) +{ + struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); + unsigned int integrity_bytes; + int ret; + struct iov_iter it; + + if (!bi) + return -EINVAL; + /* + * original meta iterator can be bigger. + * process integrity info corresponding to current data buffer only. + */ + it = meta->iter; + integrity_bytes = bio_integrity_bytes(bi, bio_sectors(bio)); + if (it.count < integrity_bytes) + return -EINVAL; + + /* should fit into two bytes */ + BUILD_BUG_ON(IO_INTEGRITY_VALID_FLAGS >= (1 << 16)); + + if (meta->flags && (meta->flags & ~IO_INTEGRITY_VALID_FLAGS)) + return -EINVAL; + + it.count = integrity_bytes; + ret = bio_integrity_map_user(bio, &it); + if (!ret) { + bio_uio_meta_to_bip(bio, meta); + bip_set_seed(bio_integrity(bio), meta->seed); + iov_iter_advance(&meta->iter, integrity_bytes); + meta->seed += bio_integrity_intervals(bi, bio_sectors(bio)); + } + return ret; +} + /** * bio_integrity_prep - Prepare bio for integrity I/O * @bio: bio to prepare @@ -435,6 +483,11 @@ bool bio_integrity_prep(struct bio *bio) if (bi->csum_type == BLK_INTEGRITY_CSUM_IP) bip->bip_flags |= BIP_IP_CHECKSUM; + /* describe what tags to check in payload */ + if (bi->csum_type) + bip->bip_flags |= BIP_CHECK_GUARD; + if (bi->flags & BLK_INTEGRITY_REF_TAG) + bip->bip_flags |= BIP_CHECK_REFTAG; if (bio_integrity_add_page(bio, virt_to_page(buf), len, offset_in_page(buf)) < len) { printk(KERN_ERR "could not attach integrity payload\n"); @@ -559,7 +612,8 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, bip->bip_vec = bip_src->bip_vec; bip->bip_iter = bip_src->bip_iter; - bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY; + bip->bip_flags = bip_src->bip_flags & BIP_CLONE_FLAGS; + bip->app_tag = bip_src->app_tag; return 0; } diff --git a/block/bio.c b/block/bio.c index d5bdc31d88d3..f0c416e5931d 100644 --- a/block/bio.c +++ b/block/bio.c @@ -946,8 +946,11 @@ static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page, /* * Try to merge a page into a segment, while obeying the hardware segment - * size limit. This is not for normal read/write bios, but for passthrough - * or Zone Append operations that we can't split. + * size limit. + * + * This is kept around for the integrity metadata, which is still tries + * to build the initial bio to the hardware limit and doesn't have proper + * helpers to split. Hopefully this will go away soon. */ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, struct page *page, unsigned len, unsigned offset, @@ -964,106 +967,6 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, return bvec_try_merge_page(bv, page, len, offset, same_page); } -/** - * bio_add_hw_page - attempt to add a page to a bio with hw constraints - * @q: the target queue - * @bio: destination bio - * @page: page to add - * @len: vec entry length - * @offset: vec entry offset - * @max_sectors: maximum number of sectors that can be added - * @same_page: return if the segment has been merged inside the same page - * - * Add a page to a bio while respecting the hardware max_sectors, max_segment - * and gap limitations. - */ -int bio_add_hw_page(struct request_queue *q, struct bio *bio, - struct page *page, unsigned int len, unsigned int offset, - unsigned int max_sectors, bool *same_page) -{ - unsigned int max_size = max_sectors << SECTOR_SHIFT; - - if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) - return 0; - - len = min3(len, max_size, queue_max_segment_size(q)); - if (len > max_size - bio->bi_iter.bi_size) - return 0; - - if (bio->bi_vcnt > 0) { - struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; - - if (bvec_try_merge_hw_page(q, bv, page, len, offset, - same_page)) { - bio->bi_iter.bi_size += len; - return len; - } - - if (bio->bi_vcnt >= - min(bio->bi_max_vecs, queue_max_segments(q))) - return 0; - - /* - * If the queue doesn't support SG gaps and adding this segment - * would create a gap, disallow it. - */ - if (bvec_gap_to_prev(&q->limits, bv, offset)) - return 0; - } - - bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, offset); - bio->bi_vcnt++; - bio->bi_iter.bi_size += len; - return len; -} - -/** - * bio_add_hw_folio - attempt to add a folio to a bio with hw constraints - * @q: the target queue - * @bio: destination bio - * @folio: folio to add - * @len: vec entry length - * @offset: vec entry offset in the folio - * @max_sectors: maximum number of sectors that can be added - * @same_page: return if the segment has been merged inside the same folio - * - * Add a folio to a bio while respecting the hardware max_sectors, max_segment - * and gap limitations. - */ -int bio_add_hw_folio(struct request_queue *q, struct bio *bio, - struct folio *folio, size_t len, size_t offset, - unsigned int max_sectors, bool *same_page) -{ - if (len > UINT_MAX || offset > UINT_MAX) - return 0; - return bio_add_hw_page(q, bio, folio_page(folio, 0), len, offset, - max_sectors, same_page); -} - -/** - * bio_add_pc_page - attempt to add page to passthrough bio - * @q: the target queue - * @bio: destination bio - * @page: page to add - * @len: vec entry length - * @offset: vec entry offset - * - * Attempt to add a page to the bio_vec maplist. This can fail for a - * number of reasons, such as the bio being full or target block device - * limitations. The target block device must allow bio's up to PAGE_SIZE, - * so it is always possible to add a single page to an empty bio. - * - * This should only be used by passthrough bios. - */ -int bio_add_pc_page(struct request_queue *q, struct bio *bio, - struct page *page, unsigned int len, unsigned int offset) -{ - bool same_page = false; - return bio_add_hw_page(q, bio, page, len, offset, - queue_max_hw_sectors(q), &same_page); -} -EXPORT_SYMBOL(bio_add_pc_page); - /** * __bio_add_page - add page(s) to a bio in a new segment * @bio: destination bio @@ -1707,6 +1610,10 @@ EXPORT_SYMBOL(bio_split); */ void bio_trim(struct bio *bio, sector_t offset, sector_t size) { + /* We should never trim an atomic write */ + if (WARN_ON_ONCE(bio->bi_opf & REQ_ATOMIC && size)) + return; + if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS || offset + size > bio_sectors(bio))) return; diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h index 022527b0b043..703a16fe1404 100644 --- a/block/blk-cgroup-rwstat.h +++ b/block/blk-cgroup-rwstat.h @@ -52,7 +52,7 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, /** * blkg_rwstat_add - add a value to a blkg_rwstat * @rwstat: target blkg_rwstat - * @op: REQ_OP and flags + * @opf: REQ_OP and flags * @val: value to add * * Add @val to @rwstat. The counters are chosen according to @rw. The @@ -83,8 +83,9 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, /** * blkg_rwstat_read - read the current values of a blkg_rwstat * @rwstat: blkg_rwstat to read + * @result: where to put the current values * - * Read the current snapshot of @rwstat and return it in the aux counts. + * Read the current snapshot of @rwstat and return it in the @result counts. */ static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat, struct blkg_rwstat_sample *result) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 45a395862fbc..9ed93d91d754 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1138,6 +1138,7 @@ static void blkcg_fill_root_iostats(void) blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } + class_dev_iter_exit(&iter); } static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) @@ -1545,6 +1546,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) struct request_queue *q = disk->queue; struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; + unsigned int memflags; int ret; if (blkcg_policy_enabled(q, pol)) @@ -1559,7 +1561,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) return -EINVAL; if (queue_is_mq(q)) - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); @@ -1623,7 +1625,7 @@ retry: spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) @@ -1667,12 +1669,13 @@ void blkcg_deactivate_policy(struct gendisk *disk, { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; + unsigned int memflags; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); @@ -1696,7 +1699,7 @@ void blkcg_deactivate_policy(struct gendisk *disk, mutex_unlock(&q->blkcg_mutex); if (queue_is_mq(q)) - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index b9e3265c1eb3..2c4663bd993a 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -225,7 +225,9 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx); /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg - * @return: true if this bio needs to be submitted with the root blkg context. + * @bio: the target &bio + * + * Return: true if this bio needs to be submitted with the root blkg context. * * In order to avoid priority inversions we sometimes need to issue a bio as if * it were attached to the root blkg, and then backcharge to the actual owning @@ -245,7 +247,7 @@ static inline bool bio_issue_as_root_blkg(struct bio *bio) * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. - + * * Must be called in a RCU critical section. */ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, @@ -268,7 +270,7 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, } /** - * blkg_to_pdata - get policy private data + * blkg_to_pd - get policy private data * @blkg: blkg of interest * @pol: policy of interest * @@ -287,7 +289,7 @@ static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, } /** - * pdata_to_blkg - get blkg associated with policy private data + * pd_to_blkg - get blkg associated with policy private data * @pd: policy private data of interest * * @pd is policy private data. Determine the blkg it's associated with. diff --git a/block/blk-core.c b/block/blk-core.c index 666efe8fa202..d6c4fa3943b5 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -430,7 +430,6 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id) refcount_set(&q->refs, 1); mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); - mutex_init(&q->sysfs_dir_lock); mutex_init(&q->limits_lock); mutex_init(&q->rq_qos_mutex); spin_lock_init(&q->queue_lock); @@ -629,8 +628,14 @@ static void __submit_bio(struct bio *bio) blk_mq_submit_bio(bio); } else if (likely(bio_queue_enter(bio) == 0)) { struct gendisk *disk = bio->bi_bdev->bd_disk; - - disk->fops->submit_bio(bio); + + if ((bio->bi_opf & REQ_POLLED) && + !(disk->queue->limits.features & BLK_FEAT_POLL)) { + bio->bi_status = BLK_STS_NOTSUPP; + bio_endio(bio); + } else { + disk->fops->submit_bio(bio); + } blk_queue_exit(disk->queue); } @@ -805,12 +810,6 @@ void submit_bio_noacct(struct bio *bio) } } - if (!(q->limits.features & BLK_FEAT_POLL) && - (bio->bi_opf & REQ_POLLED)) { - bio_clear_polled(bio); - goto not_supported; - } - switch (bio_op(bio)) { case REQ_OP_READ: break; @@ -935,7 +934,7 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) return 0; q = bdev_get_queue(bdev); - if (cookie == BLK_QC_T_NONE || !(q->limits.features & BLK_FEAT_POLL)) + if (cookie == BLK_QC_T_NONE) return 0; blk_flush_plug(current->plug, false); @@ -956,7 +955,8 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) } else { struct gendisk *disk = q->disk; - if (disk && disk->fops->poll_bio) + if ((q->limits.features & BLK_FEAT_POLL) && disk && + disk->fops->poll_bio) ret = disk->fops->poll_bio(bio, iob, flags); } blk_queue_exit(q); diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c index c9eb4241e048..d479f5481b66 100644 --- a/block/blk-ia-ranges.c +++ b/block/blk-ia-ranges.c @@ -111,7 +111,6 @@ int disk_register_independent_access_ranges(struct gendisk *disk) struct request_queue *q = disk->queue; int i, ret; - lockdep_assert_held(&q->sysfs_dir_lock); lockdep_assert_held(&q->sysfs_lock); if (!iars) @@ -155,7 +154,6 @@ void disk_unregister_independent_access_ranges(struct gendisk *disk) struct blk_independent_access_ranges *iars = disk->ia_ranges; int i; - lockdep_assert_held(&q->sysfs_dir_lock); lockdep_assert_held(&q->sysfs_lock); if (!iars) @@ -289,7 +287,6 @@ void disk_set_independent_access_ranges(struct gendisk *disk, { struct request_queue *q = disk->queue; - mutex_lock(&q->sysfs_dir_lock); mutex_lock(&q->sysfs_lock); if (iars && !disk_check_ia_ranges(disk, iars)) { kfree(iars); @@ -313,6 +310,5 @@ void disk_set_independent_access_ranges(struct gendisk *disk, disk_register_independent_access_ranges(disk); unlock: mutex_unlock(&q->sysfs_lock); - mutex_unlock(&q->sysfs_dir_lock); } EXPORT_SYMBOL_GPL(disk_set_independent_access_ranges); diff --git a/block/blk-integrity.c b/block/blk-integrity.c index b180cac61a9d..a1678f0a9f81 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -115,8 +115,16 @@ EXPORT_SYMBOL(blk_rq_map_integrity_sg); int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, ssize_t bytes) { - int ret = bio_integrity_map_user(rq->bio, ubuf, bytes); + int ret; + struct iov_iter iter; + unsigned int direction; + if (op_is_write(req_op(rq))) + direction = ITER_DEST; + else + direction = ITER_SOURCE; + iov_iter_ubuf(&iter, direction, ubuf, bytes); + ret = bio_integrity_map_user(rq->bio, &iter); if (ret) return ret; @@ -218,9 +226,7 @@ static ssize_t flag_store(struct device *dev, const char *page, size_t count, else lim.integrity.flags |= flag; - blk_mq_freeze_queue(q); - err = queue_limits_commit_update(q, &lim); - blk_mq_unfreeze_queue(q); + err = queue_limits_commit_update_frozen(q, &lim); if (err) return err; return count; diff --git a/block/blk-iocost.c b/block/blk-iocost.c index a5894ec9696e..65a1d4427ccf 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -3224,6 +3224,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, u32 qos[NR_QOS_PARAMS]; bool enable, user; char *body, *p; + unsigned int memflags; int ret; blkg_conf_init(&ctx, input); @@ -3247,7 +3248,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, ioc = q_to_ioc(disk->queue); } - blk_mq_freeze_queue(disk->queue); + memflags = blk_mq_freeze_queue(disk->queue); blk_mq_quiesce_queue(disk->queue); spin_lock_irq(&ioc->lock); @@ -3347,7 +3348,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, wbt_enable_default(disk); blk_mq_unquiesce_queue(disk->queue); - blk_mq_unfreeze_queue(disk->queue); + blk_mq_unfreeze_queue(disk->queue, memflags); blkg_conf_exit(&ctx); return nbytes; @@ -3355,7 +3356,7 @@ einval: spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(disk->queue); - blk_mq_unfreeze_queue(disk->queue); + blk_mq_unfreeze_queue(disk->queue, memflags); ret = -EINVAL; err: @@ -3414,6 +3415,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, { struct blkg_conf_ctx ctx; struct request_queue *q; + unsigned int memflags; struct ioc *ioc; u64 u[NR_I_LCOEFS]; bool user; @@ -3441,7 +3443,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, ioc = q_to_ioc(q); } - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); spin_lock_irq(&ioc->lock); @@ -3493,7 +3495,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); blkg_conf_exit(&ctx); return nbytes; @@ -3502,7 +3504,7 @@ einval: spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); ret = -EINVAL; err: diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index ebb522788d97..42c1e0b9a68f 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -749,9 +749,11 @@ static void blkiolatency_enable_work_fn(struct work_struct *work) */ enabled = atomic_read(&blkiolat->enable_cnt); if (enabled != blkiolat->enabled) { - blk_mq_freeze_queue(blkiolat->rqos.disk->queue); + unsigned int memflags; + + memflags = blk_mq_freeze_queue(blkiolat->rqos.disk->queue); blkiolat->enabled = enabled; - blk_mq_unfreeze_queue(blkiolat->rqos.disk->queue); + blk_mq_unfreeze_queue(blkiolat->rqos.disk->queue, memflags); } } diff --git a/block/blk-map.c b/block/blk-map.c index 894009b2d881..d2f22744b3d1 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -189,7 +189,7 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, } } - if (bio_add_pc_page(rq->q, bio, page, bytes, offset) < bytes) { + if (bio_add_page(bio, page, bytes, offset) < bytes) { if (!map_data) __free_page(page); break; @@ -272,86 +272,27 @@ static struct bio *blk_rq_map_bio_alloc(struct request *rq, static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, gfp_t gfp_mask) { - iov_iter_extraction_t extraction_flags = 0; - unsigned int max_sectors = queue_max_hw_sectors(rq->q); unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS); struct bio *bio; int ret; - int j; if (!iov_iter_count(iter)) return -EINVAL; bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask); - if (bio == NULL) + if (!bio) return -ENOMEM; - - if (blk_queue_pci_p2pdma(rq->q)) - extraction_flags |= ITER_ALLOW_P2PDMA; - if (iov_iter_extract_will_pin(iter)) - bio_set_flag(bio, BIO_PAGE_PINNED); - - while (iov_iter_count(iter)) { - struct page *stack_pages[UIO_FASTIOV]; - struct page **pages = stack_pages; - ssize_t bytes; - size_t offs; - int npages; - - if (nr_vecs > ARRAY_SIZE(stack_pages)) - pages = NULL; - - bytes = iov_iter_extract_pages(iter, &pages, LONG_MAX, - nr_vecs, extraction_flags, &offs); - if (unlikely(bytes <= 0)) { - ret = bytes ? bytes : -EFAULT; - goto out_unmap; - } - - npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE); - - if (unlikely(offs & queue_dma_alignment(rq->q))) - j = 0; - else { - for (j = 0; j < npages; j++) { - struct page *page = pages[j]; - unsigned int n = PAGE_SIZE - offs; - bool same_page = false; - - if (n > bytes) - n = bytes; - - if (!bio_add_hw_page(rq->q, bio, page, n, offs, - max_sectors, &same_page)) - break; - - if (same_page) - bio_release_page(bio, page); - bytes -= n; - offs = 0; - } - } - /* - * release the pages we didn't map into the bio, if any - */ - while (j < npages) - bio_release_page(bio, pages[j++]); - if (pages != stack_pages) - kvfree(pages); - /* couldn't stuff something into bio? */ - if (bytes) { - iov_iter_revert(iter, bytes); - break; - } - } - + ret = bio_iov_iter_get_pages(bio, iter); + if (ret) + goto out_put; ret = blk_rq_append_bio(rq, bio); if (ret) - goto out_unmap; + goto out_release; return 0; - out_unmap: +out_release: bio_release_pages(bio, false); +out_put: blk_mq_map_bio_put(bio); return ret; } @@ -422,8 +363,7 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data, page = virt_to_page(data); else page = vmalloc_to_page(data); - if (bio_add_pc_page(q, bio, page, bytes, - offset) < bytes) { + if (bio_add_page(bio, page, bytes, offset) < bytes) { /* we don't support partial mappings */ bio_uninit(bio); kfree(bio); @@ -507,7 +447,7 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data, if (!reading) memcpy(page_address(page), p, bytes); - if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes) + if (bio_add_page(bio, page, bytes, 0) < bytes) break; len -= bytes; @@ -536,24 +476,33 @@ cleanup: */ int blk_rq_append_bio(struct request *rq, struct bio *bio) { - struct bvec_iter iter; - struct bio_vec bv; + const struct queue_limits *lim = &rq->q->limits; + unsigned int max_bytes = lim->max_hw_sectors << SECTOR_SHIFT; unsigned int nr_segs = 0; + int ret; - bio_for_each_bvec(bv, bio, iter) - nr_segs++; + /* check that the data layout matches the hardware restrictions */ + ret = bio_split_rw_at(bio, lim, &nr_segs, max_bytes); + if (ret) { + /* if we would have to split the bio, copy instead */ + if (ret > 0) + ret = -EREMOTEIO; + return ret; + } - if (!rq->bio) { - blk_rq_bio_prep(rq, bio, nr_segs); - } else { + if (rq->bio) { if (!ll_back_merge_fn(rq, bio, nr_segs)) return -EINVAL; rq->biotail->bi_next = bio; rq->biotail = bio; - rq->__data_len += (bio)->bi_iter.bi_size; + rq->__data_len += bio->bi_iter.bi_size; bio_crypt_free_ctx(bio); + return 0; } + rq->nr_phys_segments = nr_segs; + rq->bio = rq->biotail = bio; + rq->__data_len = bio->bi_iter.bi_size; return 0; } EXPORT_SYMBOL(blk_rq_append_bio); @@ -561,9 +510,7 @@ EXPORT_SYMBOL(blk_rq_append_bio); /* Prepare bio for passthrough IO given ITER_BVEC iter */ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter) { - const struct queue_limits *lim = &rq->q->limits; - unsigned int max_bytes = lim->max_hw_sectors << SECTOR_SHIFT; - unsigned int nsegs; + unsigned int max_bytes = rq->q->limits.max_hw_sectors << SECTOR_SHIFT; struct bio *bio; int ret; @@ -576,18 +523,10 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter) return -ENOMEM; bio_iov_bvec_set(bio, iter); - /* check that the data layout matches the hardware restrictions */ - ret = bio_split_rw_at(bio, lim, &nsegs, max_bytes); - if (ret) { - /* if we would have to split the bio, copy instead */ - if (ret > 0) - ret = -EREMOTEIO; + ret = blk_rq_append_bio(rq, bio); + if (ret) blk_mq_map_bio_put(bio); - return ret; - } - - blk_rq_bio_prep(rq, bio, nsegs); - return 0; + return ret; } /** @@ -644,8 +583,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, ret = bio_copy_user_iov(rq, map_data, &i, gfp_mask); else ret = bio_map_user_iov(rq, &i, gfp_mask); - if (ret) + if (ret) { + if (ret == -EREMOTEIO) + ret = -EINVAL; goto unmap_rq; + } if (!bio) bio = rq->bio; } while (iov_iter_count(&i)); diff --git a/block/blk-merge.c b/block/blk-merge.c index e01383c6e534..15cd231d560c 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -473,6 +473,63 @@ unsigned int blk_recalc_rq_segments(struct request *rq) return nr_phys_segs; } +struct phys_vec { + phys_addr_t paddr; + u32 len; +}; + +static bool blk_map_iter_next(struct request *req, + struct req_iterator *iter, struct phys_vec *vec) +{ + unsigned int max_size; + struct bio_vec bv; + + if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { + if (!iter->bio) + return false; + vec->paddr = bvec_phys(&req->special_vec); + vec->len = req->special_vec.bv_len; + iter->bio = NULL; + return true; + } + + if (!iter->iter.bi_size) + return false; + + bv = mp_bvec_iter_bvec(iter->bio->bi_io_vec, iter->iter); + vec->paddr = bvec_phys(&bv); + max_size = get_max_segment_size(&req->q->limits, vec->paddr, UINT_MAX); + bv.bv_len = min(bv.bv_len, max_size); + bio_advance_iter_single(iter->bio, &iter->iter, bv.bv_len); + + /* + * If we are entirely done with this bi_io_vec entry, check if the next + * one could be merged into it. This typically happens when moving to + * the next bio, but some callers also don't pack bvecs tight. + */ + while (!iter->iter.bi_size || !iter->iter.bi_bvec_done) { + struct bio_vec next; + + if (!iter->iter.bi_size) { + if (!iter->bio->bi_next) + break; + iter->bio = iter->bio->bi_next; + iter->iter = iter->bio->bi_iter; + } + + next = mp_bvec_iter_bvec(iter->bio->bi_io_vec, iter->iter); + if (bv.bv_len + next.bv_len > max_size || + !biovec_phys_mergeable(req->q, &bv, &next)) + break; + + bv.bv_len += next.bv_len; + bio_advance_iter_single(iter->bio, &iter->iter, next.bv_len); + } + + vec->len = bv.bv_len; + return true; +} + static inline struct scatterlist *blk_next_sg(struct scatterlist **sg, struct scatterlist *sglist) { @@ -490,120 +547,26 @@ static inline struct scatterlist *blk_next_sg(struct scatterlist **sg, return sg_next(*sg); } -static unsigned blk_bvec_map_sg(struct request_queue *q, - struct bio_vec *bvec, struct scatterlist *sglist, - struct scatterlist **sg) -{ - unsigned nbytes = bvec->bv_len; - unsigned nsegs = 0, total = 0; - - while (nbytes > 0) { - unsigned offset = bvec->bv_offset + total; - unsigned len = get_max_segment_size(&q->limits, - bvec_phys(bvec) + total, nbytes); - struct page *page = bvec->bv_page; - - /* - * Unfortunately a fair number of drivers barf on scatterlists - * that have an offset larger than PAGE_SIZE, despite other - * subsystems dealing with that invariant just fine. For now - * stick to the legacy format where we never present those from - * the block layer, but the code below should be removed once - * these offenders (mostly MMC/SD drivers) are fixed. - */ - page += (offset >> PAGE_SHIFT); - offset &= ~PAGE_MASK; - - *sg = blk_next_sg(sg, sglist); - sg_set_page(*sg, page, len, offset); - - total += len; - nbytes -= len; - nsegs++; - } - - return nsegs; -} - -static inline int __blk_bvec_map_sg(struct bio_vec bv, - struct scatterlist *sglist, struct scatterlist **sg) -{ - *sg = blk_next_sg(sg, sglist); - sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset); - return 1; -} - -/* only try to merge bvecs into one sg if they are from two bios */ -static inline bool -__blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec, - struct bio_vec *bvprv, struct scatterlist **sg) -{ - - int nbytes = bvec->bv_len; - - if (!*sg) - return false; - - if ((*sg)->length + nbytes > queue_max_segment_size(q)) - return false; - - if (!biovec_phys_mergeable(q, bvprv, bvec)) - return false; - - (*sg)->length += nbytes; - - return true; -} - -static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, - struct scatterlist *sglist, - struct scatterlist **sg) -{ - struct bio_vec bvec, bvprv = { NULL }; - struct bvec_iter iter; - int nsegs = 0; - bool new_bio = false; - - for_each_bio(bio) { - bio_for_each_bvec(bvec, bio, iter) { - /* - * Only try to merge bvecs from two bios given we - * have done bio internal merge when adding pages - * to bio - */ - if (new_bio && - __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg)) - goto next_bvec; - - if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE) - nsegs += __blk_bvec_map_sg(bvec, sglist, sg); - else - nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg); - next_bvec: - new_bio = false; - } - if (likely(bio->bi_iter.bi_size)) { - bvprv = bvec; - new_bio = true; - } - } - - return nsegs; -} - /* - * map a request to scatterlist, return number of sg entries setup. Caller - * must make sure sg can hold rq->nr_phys_segments entries + * Map a request to scatterlist, return number of sg entries setup. Caller + * must make sure sg can hold rq->nr_phys_segments entries. */ int __blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg) { + struct req_iterator iter = { + .bio = rq->bio, + .iter = rq->bio->bi_iter, + }; + struct phys_vec vec; int nsegs = 0; - if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) - nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg); - else if (rq->bio) - nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg); + while (blk_map_iter_next(rq, &iter, &vec)) { + *last_sg = blk_next_sg(last_sg, sglist); + sg_set_page(*last_sg, phys_to_page(vec.paddr), vec.len, + offset_in_page(vec.paddr)); + nsegs++; + } if (*last_sg) sg_mark_end(*last_sg); diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index 9638b25fd521..444798c5374f 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "blk.h" #include "blk-mq.h" @@ -54,3 +55,38 @@ int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index) return NUMA_NO_NODE; } + +/** + * blk_mq_map_hw_queues - Create CPU to hardware queue mapping + * @qmap: CPU to hardware queue map + * @dev: The device to map queues + * @offset: Queue offset to use for the device + * + * Create a CPU to hardware queue mapping in @qmap. The struct bus_type + * irq_get_affinity callback will be used to retrieve the affinity. + */ +void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, + struct device *dev, unsigned int offset) + +{ + const struct cpumask *mask; + unsigned int queue, cpu; + + if (!dev->bus->irq_get_affinity) + goto fallback; + + for (queue = 0; queue < qmap->nr_queues; queue++) { + mask = dev->bus->irq_get_affinity(dev, queue + offset); + if (!mask) + goto fallback; + + for_each_cpu(cpu, mask) + qmap->mq_map[cpu] = qmap->queue_offset + queue; + } + + return; + +fallback: + blk_mq_map_queues(qmap); +} +EXPORT_SYMBOL_GPL(blk_mq_map_hw_queues); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 5463697a8442..adf5f0697b6b 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -172,21 +172,13 @@ static int hctx_state_show(void *data, struct seq_file *m) return 0; } -#define BLK_TAG_ALLOC_NAME(name) [BLK_TAG_ALLOC_##name] = #name -static const char *const alloc_policy_name[] = { - BLK_TAG_ALLOC_NAME(FIFO), - BLK_TAG_ALLOC_NAME(RR), -}; -#undef BLK_TAG_ALLOC_NAME - #define HCTX_FLAG_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name static const char *const hctx_flag_name[] = { - HCTX_FLAG_NAME(SHOULD_MERGE), HCTX_FLAG_NAME(TAG_QUEUE_SHARED), HCTX_FLAG_NAME(STACKING), HCTX_FLAG_NAME(TAG_HCTX_SHARED), HCTX_FLAG_NAME(BLOCKING), - HCTX_FLAG_NAME(NO_SCHED), + HCTX_FLAG_NAME(TAG_RR), HCTX_FLAG_NAME(NO_SCHED_BY_DEFAULT), }; #undef HCTX_FLAG_NAME @@ -194,22 +186,11 @@ static const char *const hctx_flag_name[] = { static int hctx_flags_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; - const int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(hctx->flags); - BUILD_BUG_ON(ARRAY_SIZE(hctx_flag_name) != - BLK_MQ_F_ALLOC_POLICY_START_BIT); - BUILD_BUG_ON(ARRAY_SIZE(alloc_policy_name) != BLK_TAG_ALLOC_MAX); + BUILD_BUG_ON(ARRAY_SIZE(hctx_flag_name) != ilog2(BLK_MQ_F_MAX)); - seq_puts(m, "alloc_policy="); - if (alloc_policy < ARRAY_SIZE(alloc_policy_name) && - alloc_policy_name[alloc_policy]) - seq_puts(m, alloc_policy_name[alloc_policy]); - else - seq_printf(m, "%d", alloc_policy); - seq_puts(m, " "); - blk_flags_show(m, - hctx->flags ^ BLK_ALLOC_POLICY_TO_MQ_FLAG(alloc_policy), - hctx_flag_name, ARRAY_SIZE(hctx_flag_name)); + blk_flags_show(m, hctx->flags, hctx_flag_name, + ARRAY_SIZE(hctx_flag_name)); seq_puts(m, "\n"); return 0; } diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c deleted file mode 100644 index d47b5c73c9eb..000000000000 --- a/block/blk-mq-pci.c +++ /dev/null @@ -1,46 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2016 Christoph Hellwig. - */ -#include -#include -#include -#include -#include - -#include "blk-mq.h" - -/** - * blk_mq_pci_map_queues - provide a default queue mapping for PCI device - * @qmap: CPU to hardware queue map. - * @pdev: PCI device associated with @set. - * @offset: Offset to use for the pci irq vector - * - * This function assumes the PCI device @pdev has at least as many available - * interrupt vectors as @set has queues. It will then query the vector - * corresponding to each queue for it's affinity mask and built queue mapping - * that maps a queue to the CPUs that have irq affinity for the corresponding - * vector. - */ -void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, - int offset) -{ - const struct cpumask *mask; - unsigned int queue, cpu; - - for (queue = 0; queue < qmap->nr_queues; queue++) { - mask = pci_irq_get_affinity(pdev, queue + offset); - if (!mask) - goto fallback; - - for_each_cpu(cpu, mask) - qmap->mq_map[cpu] = qmap->queue_offset + queue; - } - - return; - -fallback: - WARN_ON_ONCE(qmap->nr_queues > 1); - blk_mq_clear_mq_map(qmap); -} -EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues); diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 451a2c1f1f32..7442ca27c2bf 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -351,8 +351,7 @@ bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, ctx = blk_mq_get_ctx(q); hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); type = hctx->type; - if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE) || - list_empty_careful(&ctx->rq_lists[type])) + if (list_empty_careful(&ctx->rq_lists[type])) goto out_put; /* default per sw-queue merge */ diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index cd5ea6eaa76b..3feeeccf8a99 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -223,30 +223,27 @@ int blk_mq_sysfs_register(struct gendisk *disk) unsigned long i, j; int ret; - lockdep_assert_held(&q->sysfs_dir_lock); - ret = kobject_add(q->mq_kobj, &disk_to_dev(disk)->kobj, "mq"); if (ret < 0) - goto out; + return ret; kobject_uevent(q->mq_kobj, KOBJ_ADD); + mutex_lock(&q->tag_set->tag_list_lock); queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); if (ret) - goto unreg; + goto out_unreg; } + mutex_unlock(&q->tag_set->tag_list_lock); + return 0; - q->mq_sysfs_init_done = true; - -out: - return ret; - -unreg: +out_unreg: queue_for_each_hw_ctx(q, hctx, j) { if (j < i) blk_mq_unregister_hctx(hctx); } + mutex_unlock(&q->tag_set->tag_list_lock); kobject_uevent(q->mq_kobj, KOBJ_REMOVE); kobject_del(q->mq_kobj); @@ -259,15 +256,13 @@ void blk_mq_sysfs_unregister(struct gendisk *disk) struct blk_mq_hw_ctx *hctx; unsigned long i; - lockdep_assert_held(&q->sysfs_dir_lock); - + mutex_lock(&q->tag_set->tag_list_lock); queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); + mutex_unlock(&q->tag_set->tag_list_lock); kobject_uevent(q->mq_kobj, KOBJ_REMOVE); kobject_del(q->mq_kobj); - - q->mq_sysfs_init_done = false; } void blk_mq_sysfs_unregister_hctxs(struct request_queue *q) @@ -275,9 +270,7 @@ void blk_mq_sysfs_unregister_hctxs(struct request_queue *q) struct blk_mq_hw_ctx *hctx; unsigned long i; - lockdep_assert_held(&q->sysfs_dir_lock); - - if (!q->mq_sysfs_init_done) + if (!blk_queue_registered(q)) return; queue_for_each_hw_ctx(q, hctx, i) @@ -290,10 +283,8 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) unsigned long i; int ret = 0; - lockdep_assert_held(&q->sysfs_dir_lock); - - if (!q->mq_sysfs_init_done) - return ret; + if (!blk_queue_registered(q)) + goto out; queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); @@ -301,5 +292,6 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) break; } +out: return ret; } diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 2cafcf11ee8b..b9f417d980b4 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -544,30 +544,11 @@ static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, node); } -int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, - struct sbitmap_queue *breserved_tags, - unsigned int queue_depth, unsigned int reserved, - int node, int alloc_policy) -{ - unsigned int depth = queue_depth - reserved; - bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; - - if (bt_alloc(bitmap_tags, depth, round_robin, node)) - return -ENOMEM; - if (bt_alloc(breserved_tags, reserved, round_robin, node)) - goto free_bitmap_tags; - - return 0; - -free_bitmap_tags: - sbitmap_queue_free(bitmap_tags); - return -ENOMEM; -} - struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, - unsigned int reserved_tags, - int node, int alloc_policy) + unsigned int reserved_tags, unsigned int flags, int node) { + unsigned int depth = total_tags - reserved_tags; + bool round_robin = flags & BLK_MQ_F_TAG_RR; struct blk_mq_tags *tags; if (total_tags > BLK_MQ_TAG_MAX) { @@ -582,14 +563,18 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; spin_lock_init(&tags->lock); + if (bt_alloc(&tags->bitmap_tags, depth, round_robin, node)) + goto out_free_tags; + if (bt_alloc(&tags->breserved_tags, reserved_tags, round_robin, node)) + goto out_free_bitmap_tags; - if (blk_mq_init_bitmaps(&tags->bitmap_tags, &tags->breserved_tags, - total_tags, reserved_tags, node, - alloc_policy) < 0) { - kfree(tags); - return NULL; - } return tags; + +out_free_bitmap_tags: + sbitmap_queue_free(&tags->bitmap_tags); +out_free_tags: + kfree(tags); + return NULL; } void blk_mq_free_tags(struct blk_mq_tags *tags) diff --git a/block/blk-mq-virtio.c b/block/blk-mq-virtio.c deleted file mode 100644 index 68d0945c0b08..000000000000 --- a/block/blk-mq-virtio.c +++ /dev/null @@ -1,46 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2016 Christoph Hellwig. - */ -#include -#include -#include -#include -#include "blk-mq.h" - -/** - * blk_mq_virtio_map_queues - provide a default queue mapping for virtio device - * @qmap: CPU to hardware queue map. - * @vdev: virtio device to provide a mapping for. - * @first_vec: first interrupt vectors to use for queues (usually 0) - * - * This function assumes the virtio device @vdev has at least as many available - * interrupt vectors as @set has queues. It will then query the vector - * corresponding to each queue for it's affinity mask and built queue mapping - * that maps a queue to the CPUs that have irq affinity for the corresponding - * vector. - */ -void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, - struct virtio_device *vdev, int first_vec) -{ - const struct cpumask *mask; - unsigned int queue, cpu; - - if (!vdev->config->get_vq_affinity) - goto fallback; - - for (queue = 0; queue < qmap->nr_queues; queue++) { - mask = vdev->config->get_vq_affinity(vdev, first_vec + queue); - if (!mask) - goto fallback; - - for_each_cpu(cpu, mask) - qmap->mq_map[cpu] = qmap->queue_offset + queue; - } - - return; - -fallback: - blk_mq_map_queues(qmap); -} -EXPORT_SYMBOL_GPL(blk_mq_virtio_map_queues); diff --git a/block/blk-mq.c b/block/blk-mq.c index 6b6111513986..40490ac88045 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -131,6 +131,10 @@ static bool blk_freeze_set_owner(struct request_queue *q, if (!q->mq_freeze_depth) { q->mq_freeze_owner = owner; q->mq_freeze_owner_depth = 1; + q->mq_freeze_disk_dead = !q->disk || + test_bit(GD_DEAD, &q->disk->state) || + !blk_queue_registered(q); + q->mq_freeze_queue_dying = blk_queue_dying(q); return true; } @@ -142,8 +146,6 @@ static bool blk_freeze_set_owner(struct request_queue *q, /* verify the last unfreeze in owner context */ static bool blk_unfreeze_check_owner(struct request_queue *q) { - if (!q->mq_freeze_owner) - return false; if (q->mq_freeze_owner != current) return false; if (--q->mq_freeze_owner_depth == 0) { @@ -189,7 +191,7 @@ bool __blk_freeze_queue_start(struct request_queue *q, void blk_freeze_queue_start(struct request_queue *q) { if (__blk_freeze_queue_start(q, current)) - blk_freeze_acquire_lock(q, false, false); + blk_freeze_acquire_lock(q); } EXPORT_SYMBOL_GPL(blk_freeze_queue_start); @@ -208,12 +210,12 @@ int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout); -void blk_mq_freeze_queue(struct request_queue *q) +void blk_mq_freeze_queue_nomemsave(struct request_queue *q) { blk_freeze_queue_start(q); blk_mq_freeze_queue_wait(q); } -EXPORT_SYMBOL_GPL(blk_mq_freeze_queue); +EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_nomemsave); bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic) { @@ -234,12 +236,12 @@ bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic) return unfreeze; } -void blk_mq_unfreeze_queue(struct request_queue *q) +void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q) { if (__blk_mq_unfreeze_queue(q, false)) - blk_unfreeze_release_lock(q, false, false); + blk_unfreeze_release_lock(q); } -EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); +EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_nomemrestore); /* * non_owner variant of blk_freeze_queue_start @@ -2656,8 +2658,10 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, if (bio->bi_opf & REQ_RAHEAD) rq->cmd_flags |= REQ_FAILFAST_MASK; + rq->bio = rq->biotail = bio; rq->__sector = bio->bi_iter.bi_sector; - blk_rq_bio_prep(rq, bio, nr_segs); + rq->__data_len = bio->bi_iter.bi_size; + rq->nr_phys_segments = nr_segs; if (bio_integrity(bio)) rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q, bio); @@ -2980,12 +2984,9 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, } rq = __blk_mq_alloc_requests(&data); - if (rq) - return rq; - rq_qos_cleanup(q, bio); - if (bio->bi_opf & REQ_NOWAIT) - bio_wouldblock_error(bio); - return NULL; + if (unlikely(!rq)) + rq_qos_cleanup(q, bio); + return rq; } /* @@ -3092,14 +3093,21 @@ void blk_mq_submit_bio(struct bio *bio) } /* - * Device reconfiguration may change logical block size, so alignment - * check has to be done with queue usage counter held + * Device reconfiguration may change logical block size or reduce the + * number of poll queues, so the checks for alignment and poll support + * have to be done with queue usage counter held. */ if (unlikely(bio_unaligned(bio, q))) { bio_io_error(bio); goto queue_exit; } + if ((bio->bi_opf & REQ_POLLED) && !blk_mq_can_poll(q)) { + bio->bi_status = BLK_STS_NOTSUPP; + bio_endio(bio); + goto queue_exit; + } + bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); if (!bio) goto queue_exit; @@ -3114,12 +3122,15 @@ void blk_mq_submit_bio(struct bio *bio) goto queue_exit; new_request: - if (!rq) { - rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); - if (unlikely(!rq)) - goto queue_exit; - } else { + if (rq) { blk_mq_use_cached_rq(rq, plug, bio); + } else { + rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); + if (unlikely(!rq)) { + if (bio->bi_opf & REQ_NOWAIT) + bio_wouldblock_error(bio); + goto queue_exit; + } } trace_block_getrq(bio); @@ -3472,8 +3483,7 @@ static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, if (node == NUMA_NO_NODE) node = set->numa_node; - tags = blk_mq_init_tags(nr_tags, reserved_tags, node, - BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags)); + tags = blk_mq_init_tags(nr_tags, reserved_tags, set->flags, node); if (!tags) return NULL; @@ -4213,13 +4223,14 @@ static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set, bool shared) { struct request_queue *q; + unsigned int memflags; lockdep_assert_held(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); queue_set_hctx_shared(q, shared); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } } @@ -4317,12 +4328,6 @@ void blk_mq_release(struct request_queue *q) blk_mq_sysfs_deinit(q); } -static bool blk_mq_can_poll(struct blk_mq_tag_set *set) -{ - return set->nr_maps > HCTX_TYPE_POLL && - set->map[HCTX_TYPE_POLL].nr_queues; -} - struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata) { @@ -4333,7 +4338,7 @@ struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, if (!lim) lim = &default_lim; lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT; - if (blk_mq_can_poll(set)) + if (set->nr_maps > HCTX_TYPE_POLL) lim->features |= BLK_FEAT_POLL; q = blk_alloc_queue(lim, set->numa_node); @@ -4412,6 +4417,15 @@ struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, } EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue); +/* + * Only hctx removed from cpuhp list can be reused + */ +static bool blk_mq_hctx_is_reusable(struct blk_mq_hw_ctx *hctx) +{ + return hlist_unhashed(&hctx->cpuhp_online) && + hlist_unhashed(&hctx->cpuhp_dead); +} + static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, int hctx_idx, int node) @@ -4421,7 +4435,7 @@ static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( /* reuse dead hctx first */ spin_lock(&q->unused_hctx_lock); list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) { - if (tmp->numa_node == node) { + if (tmp->numa_node == node && blk_mq_hctx_is_reusable(tmp)) { hctx = tmp; break; } @@ -4453,8 +4467,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, unsigned long i, j; /* protect against switching io scheduler */ - lockdep_assert_held(&q->sysfs_lock); - + mutex_lock(&q->sysfs_lock); for (i = 0; i < set->nr_hw_queues; i++) { int old_node; int node = blk_mq_get_hctx_node(set, i); @@ -4487,6 +4500,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); + mutex_unlock(&q->sysfs_lock); /* unregister cpuhp callbacks for exited hctxs */ blk_mq_remove_hw_queues_cpuhp(q); @@ -4518,14 +4532,10 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, xa_init(&q->hctx_table); - mutex_lock(&q->sysfs_lock); - blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; - mutex_unlock(&q->sysfs_lock); - INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); @@ -4544,7 +4554,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, return 0; err_hctxs: - mutex_unlock(&q->sysfs_lock); blk_mq_release(q); err_exit: q->mq_ops = NULL; @@ -4925,12 +4934,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head, return false; /* q->elevator needs protection from ->sysfs_lock */ - lockdep_assert_held(&q->sysfs_lock); + mutex_lock(&q->sysfs_lock); /* the check has to be done with holding sysfs_lock */ if (!q->elevator) { kfree(qe); - goto out; + goto unlock; } INIT_LIST_HEAD(&qe->node); @@ -4940,7 +4949,9 @@ static bool blk_mq_elv_switch_none(struct list_head *head, __elevator_get(qe->type); list_add(&qe->node, head); elevator_disable(q); -out: +unlock: + mutex_unlock(&q->sysfs_lock); + return true; } @@ -4969,9 +4980,11 @@ static void blk_mq_elv_switch_back(struct list_head *head, list_del(&qe->node); kfree(qe); + mutex_lock(&q->sysfs_lock); elevator_switch(q, t); /* drop the reference acquired in blk_mq_elv_switch_none */ elevator_put(t); + mutex_unlock(&q->sysfs_lock); } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, @@ -4980,6 +4993,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, struct request_queue *q; LIST_HEAD(head); int prev_nr_hw_queues = set->nr_hw_queues; + unsigned int memflags; int i; lockdep_assert_held(&set->tag_list_lock); @@ -4991,11 +5005,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; - list_for_each_entry(q, &set->tag_list, tag_set_list) { - mutex_lock(&q->sysfs_dir_lock); - mutex_lock(&q->sysfs_lock); - blk_mq_freeze_queue(q); - } + memflags = memalloc_noio_save(); + list_for_each_entry(q, &set->tag_list, tag_set_list) + blk_mq_freeze_queue_nomemsave(q); + /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done @@ -5016,8 +5029,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, fallback: blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { - struct queue_limits lim; - blk_mq_realloc_hw_ctxs(set, q); if (q->nr_hw_queues != set->nr_hw_queues) { @@ -5031,13 +5042,6 @@ fallback: set->nr_hw_queues = prev_nr_hw_queues; goto fallback; } - lim = queue_limits_start_update(q); - if (blk_mq_can_poll(set)) - lim.features |= BLK_FEAT_POLL; - else - lim.features &= ~BLK_FEAT_POLL; - if (queue_limits_commit_update(q, &lim) < 0) - pr_warn("updating the poll flag failed\n"); blk_mq_map_swqueue(q); } @@ -5051,11 +5055,9 @@ switch_back: list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_elv_switch_back(&head, q); - list_for_each_entry(q, &set->tag_list, tag_set_list) { - blk_mq_unfreeze_queue(q); - mutex_unlock(&q->sysfs_lock); - mutex_unlock(&q->sysfs_dir_lock); - } + list_for_each_entry(q, &set->tag_list, tag_set_list) + blk_mq_unfreeze_queue_nomemrestore(q); + memalloc_noio_restore(memflags); /* Free the excess tags when nr_hw_queues shrink. */ for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++) @@ -5100,9 +5102,9 @@ static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx, int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob, unsigned int flags) { - struct blk_mq_hw_ctx *hctx = xa_load(&q->hctx_table, cookie); - - return blk_hctx_poll(q, hctx, iob, flags); + if (!blk_mq_can_poll(q)) + return 0; + return blk_hctx_poll(q, xa_load(&q->hctx_table, cookie), iob, flags); } int blk_rq_poll(struct request *rq, struct io_comp_batch *iob, diff --git a/block/blk-mq.h b/block/blk-mq.h index 89a20fffa4b1..44979e92b79f 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -163,11 +163,8 @@ struct blk_mq_alloc_data { }; struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, - unsigned int reserved_tags, int node, int alloc_policy); + unsigned int reserved_tags, unsigned int flags, int node); void blk_mq_free_tags(struct blk_mq_tags *tags); -int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, - struct sbitmap_queue *breserved_tags, unsigned int queue_depth, - unsigned int reserved, int node, int alloc_policy); unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, @@ -451,4 +448,10 @@ do { \ #define blk_mq_run_dispatch_ops(q, dispatch_ops) \ __blk_mq_run_dispatch_ops(q, true, dispatch_ops) \ +static inline bool blk_mq_can_poll(struct request_queue *q) +{ + return (q->limits.features & BLK_FEAT_POLL) && + q->tag_set->map[HCTX_TYPE_POLL].nr_queues; +} + #endif diff --git a/block/blk-pm.c b/block/blk-pm.c index 42e842074715..8d3e052f91da 100644 --- a/block/blk-pm.c +++ b/block/blk-pm.c @@ -89,7 +89,7 @@ int blk_pre_runtime_suspend(struct request_queue *q) if (percpu_ref_is_zero(&q->q_usage_counter)) ret = 0; /* Switch q_usage_counter back to per-cpu mode. */ - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue_nomemrestore(q); if (ret < 0) { spin_lock_irq(&q->queue_lock); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index eb9618cd68ad..d4d4f4dc0e23 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -299,6 +299,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, const struct rq_qos_ops *ops) { struct request_queue *q = disk->queue; + unsigned int memflags; lockdep_assert_held(&q->rq_qos_mutex); @@ -310,14 +311,14 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, * No IO can be in-flight when adding rqos, so freeze queue, which * is fine since we only support rq_qos for blk-mq queue. */ - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); if (rq_qos_id(q, rqos->id)) goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); if (rqos->ops->debugfs_attrs) { mutex_lock(&q->debugfs_mutex); @@ -327,7 +328,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, return 0; ebusy: - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); return -EBUSY; } @@ -335,17 +336,18 @@ void rq_qos_del(struct rq_qos *rqos) { struct request_queue *q = rqos->disk->queue; struct rq_qos **cur; + unsigned int memflags; lockdep_assert_held(&q->rq_qos_mutex); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_rqos(rqos); diff --git a/block/blk-settings.c b/block/blk-settings.c index 8f09e33f41f6..c44dadc35e1e 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -175,6 +175,9 @@ static void blk_validate_atomic_write_limits(struct queue_limits *lim) { unsigned int boundary_sectors; + if (!(lim->features & BLK_FEAT_ATOMIC_WRITES)) + goto unsupported; + if (!lim->atomic_write_hw_max) goto unsupported; @@ -413,7 +416,8 @@ int blk_set_default_limits(struct queue_limits *lim) * @lim: limits to apply * * Apply the limits in @lim that were obtained from queue_limits_start_update() - * and updated by the caller to @q. + * and updated by the caller to @q. The caller must have frozen the queue or + * ensure that there are no outstanding I/Os by other means. * * Returns 0 if successful, else a negative error code. */ @@ -443,6 +447,31 @@ out_unlock: } EXPORT_SYMBOL_GPL(queue_limits_commit_update); +/** + * queue_limits_commit_update_frozen - commit an atomic update of queue limits + * @q: queue to update + * @lim: limits to apply + * + * Apply the limits in @lim that were obtained from queue_limits_start_update() + * and updated with the new values by the caller to @q. Freezes the queue + * before the update and unfreezes it after. + * + * Returns 0 if successful, else a negative error code. + */ +int queue_limits_commit_update_frozen(struct request_queue *q, + struct queue_limits *lim) +{ + unsigned int memflags; + int ret; + + memflags = blk_mq_freeze_queue(q); + ret = queue_limits_commit_update(q, lim); + blk_mq_unfreeze_queue(q, memflags); + + return ret; +} +EXPORT_SYMBOL_GPL(queue_limits_commit_update_frozen); + /** * queue_limits_set - apply queue limits to queue * @q: queue to update @@ -584,12 +613,15 @@ static bool blk_stack_atomic_writes_head(struct queue_limits *t, } static void blk_stack_atomic_writes_limits(struct queue_limits *t, - struct queue_limits *b) + struct queue_limits *b, sector_t start) { - if (!(t->features & BLK_FEAT_ATOMIC_WRITES_STACKED)) + if (!(b->features & BLK_FEAT_ATOMIC_WRITES)) goto unsupported; - if (!b->atomic_write_unit_min) + if (!b->atomic_write_hw_unit_min) + goto unsupported; + + if (!blk_atomic_write_start_sect_aligned(start, b)) goto unsupported; /* @@ -611,7 +643,6 @@ unsupported: t->atomic_write_hw_unit_max = 0; t->atomic_write_hw_unit_min = 0; t->atomic_write_hw_boundary = 0; - t->features &= ~BLK_FEAT_ATOMIC_WRITES_STACKED; } /** @@ -774,7 +805,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->zone_write_granularity = 0; t->max_zone_append_sectors = 0; } - blk_stack_atomic_writes_limits(t, b); + blk_stack_atomic_writes_limits(t, b, start); return ret; } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 64f70c713d2f..6f548a4376aa 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -24,6 +24,8 @@ struct queue_sysfs_entry { struct attribute attr; ssize_t (*show)(struct gendisk *disk, char *page); ssize_t (*store)(struct gendisk *disk, const char *page, size_t count); + int (*store_limit)(struct gendisk *disk, const char *page, + size_t count, struct queue_limits *lim); void (*load_module)(struct gendisk *disk, const char *page, size_t count); }; @@ -153,13 +155,11 @@ QUEUE_SYSFS_SHOW_CONST(discard_zeroes_data, 0) QUEUE_SYSFS_SHOW_CONST(write_same_max, 0) QUEUE_SYSFS_SHOW_CONST(poll_delay, -1) -static ssize_t queue_max_discard_sectors_store(struct gendisk *disk, - const char *page, size_t count) +static int queue_max_discard_sectors_store(struct gendisk *disk, + const char *page, size_t count, struct queue_limits *lim) { unsigned long max_discard_bytes; - struct queue_limits lim; ssize_t ret; - int err; ret = queue_var_store(&max_discard_bytes, page, count); if (ret < 0) @@ -171,38 +171,28 @@ static ssize_t queue_max_discard_sectors_store(struct gendisk *disk, if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX) return -EINVAL; - lim = queue_limits_start_update(disk->queue); - lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT; - err = queue_limits_commit_update(disk->queue, &lim); - if (err) - return err; - return ret; + lim->max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT; + return 0; } -static ssize_t -queue_max_sectors_store(struct gendisk *disk, const char *page, size_t count) +static int +queue_max_sectors_store(struct gendisk *disk, const char *page, size_t count, + struct queue_limits *lim) { unsigned long max_sectors_kb; - struct queue_limits lim; ssize_t ret; - int err; ret = queue_var_store(&max_sectors_kb, page, count); if (ret < 0) return ret; - lim = queue_limits_start_update(disk->queue); - lim.max_user_sectors = max_sectors_kb << 1; - err = queue_limits_commit_update(disk->queue, &lim); - if (err) - return err; - return ret; + lim->max_user_sectors = max_sectors_kb << 1; + return 0; } static ssize_t queue_feature_store(struct gendisk *disk, const char *page, - size_t count, blk_features_t feature) + size_t count, struct queue_limits *lim, blk_features_t feature) { - struct queue_limits lim; unsigned long val; ssize_t ret; @@ -210,15 +200,11 @@ static ssize_t queue_feature_store(struct gendisk *disk, const char *page, if (ret < 0) return ret; - lim = queue_limits_start_update(disk->queue); if (val) - lim.features |= feature; + lim->features |= feature; else - lim.features &= ~feature; - ret = queue_limits_commit_update(disk->queue, &lim); - if (ret) - return ret; - return count; + lim->features &= ~feature; + return 0; } #define QUEUE_SYSFS_FEATURE(_name, _feature) \ @@ -227,10 +213,10 @@ static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \ return sysfs_emit(page, "%u\n", \ !!(disk->queue->limits.features & _feature)); \ } \ -static ssize_t queue_##_name##_store(struct gendisk *disk, \ - const char *page, size_t count) \ +static int queue_##_name##_store(struct gendisk *disk, \ + const char *page, size_t count, struct queue_limits *lim) \ { \ - return queue_feature_store(disk, page, count, _feature); \ + return queue_feature_store(disk, page, count, lim, _feature); \ } QUEUE_SYSFS_FEATURE(rotational, BLK_FEAT_ROTATIONAL) @@ -245,10 +231,17 @@ static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \ !!(disk->queue->limits.features & _feature)); \ } -QUEUE_SYSFS_FEATURE_SHOW(poll, BLK_FEAT_POLL); QUEUE_SYSFS_FEATURE_SHOW(fua, BLK_FEAT_FUA); QUEUE_SYSFS_FEATURE_SHOW(dax, BLK_FEAT_DAX); +static ssize_t queue_poll_show(struct gendisk *disk, char *page) +{ + if (queue_is_mq(disk->queue)) + return sysfs_emit(page, "%u\n", blk_mq_can_poll(disk->queue)); + return sysfs_emit(page, "%u\n", + !!(disk->queue->limits.features & BLK_FEAT_POLL)); +} + static ssize_t queue_zoned_show(struct gendisk *disk, char *page) { if (blk_queue_is_zoned(disk->queue)) @@ -266,10 +259,9 @@ static ssize_t queue_iostats_passthrough_show(struct gendisk *disk, char *page) return queue_var_show(!!blk_queue_passthrough_stat(disk->queue), page); } -static ssize_t queue_iostats_passthrough_store(struct gendisk *disk, - const char *page, size_t count) +static int queue_iostats_passthrough_store(struct gendisk *disk, + const char *page, size_t count, struct queue_limits *lim) { - struct queue_limits lim; unsigned long ios; ssize_t ret; @@ -277,18 +269,13 @@ static ssize_t queue_iostats_passthrough_store(struct gendisk *disk, if (ret < 0) return ret; - lim = queue_limits_start_update(disk->queue); if (ios) - lim.flags |= BLK_FLAG_IOSTATS_PASSTHROUGH; + lim->flags |= BLK_FLAG_IOSTATS_PASSTHROUGH; else - lim.flags &= ~BLK_FLAG_IOSTATS_PASSTHROUGH; - - ret = queue_limits_commit_update(disk->queue, &lim); - if (ret) - return ret; - - return count; + lim->flags &= ~BLK_FLAG_IOSTATS_PASSTHROUGH; + return 0; } + static ssize_t queue_nomerges_show(struct gendisk *disk, char *page) { return queue_var_show((blk_queue_nomerges(disk->queue) << 1) | @@ -391,12 +378,10 @@ static ssize_t queue_wc_show(struct gendisk *disk, char *page) return sysfs_emit(page, "write through\n"); } -static ssize_t queue_wc_store(struct gendisk *disk, const char *page, - size_t count) +static int queue_wc_store(struct gendisk *disk, const char *page, + size_t count, struct queue_limits *lim) { - struct queue_limits lim; bool disable; - int err; if (!strncmp(page, "write back", 10)) { disable = false; @@ -407,15 +392,11 @@ static ssize_t queue_wc_store(struct gendisk *disk, const char *page, return -EINVAL; } - lim = queue_limits_start_update(disk->queue); if (disable) - lim.flags |= BLK_FLAG_WRITE_CACHE_DISABLED; + lim->flags |= BLK_FLAG_WRITE_CACHE_DISABLED; else - lim.flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED; - err = queue_limits_commit_update(disk->queue, &lim); - if (err) - return err; - return count; + lim->flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED; + return 0; } #define QUEUE_RO_ENTRY(_prefix, _name) \ @@ -431,6 +412,13 @@ static struct queue_sysfs_entry _prefix##_entry = { \ .store = _prefix##_store, \ }; +#define QUEUE_LIM_RW_ENTRY(_prefix, _name) \ +static struct queue_sysfs_entry _prefix##_entry = { \ + .attr = { .name = _name, .mode = 0644 }, \ + .show = _prefix##_show, \ + .store_limit = _prefix##_store, \ +} + #define QUEUE_RW_LOAD_MODULE_ENTRY(_prefix, _name) \ static struct queue_sysfs_entry _prefix##_entry = { \ .attr = { .name = _name, .mode = 0644 }, \ @@ -441,7 +429,7 @@ static struct queue_sysfs_entry _prefix##_entry = { \ QUEUE_RW_ENTRY(queue_requests, "nr_requests"); QUEUE_RW_ENTRY(queue_ra, "read_ahead_kb"); -QUEUE_RW_ENTRY(queue_max_sectors, "max_sectors_kb"); +QUEUE_LIM_RW_ENTRY(queue_max_sectors, "max_sectors_kb"); QUEUE_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb"); QUEUE_RO_ENTRY(queue_max_segments, "max_segments"); QUEUE_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments"); @@ -457,7 +445,7 @@ QUEUE_RO_ENTRY(queue_io_opt, "optimal_io_size"); QUEUE_RO_ENTRY(queue_max_discard_segments, "max_discard_segments"); QUEUE_RO_ENTRY(queue_discard_granularity, "discard_granularity"); QUEUE_RO_ENTRY(queue_max_hw_discard_sectors, "discard_max_hw_bytes"); -QUEUE_RW_ENTRY(queue_max_discard_sectors, "discard_max_bytes"); +QUEUE_LIM_RW_ENTRY(queue_max_discard_sectors, "discard_max_bytes"); QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data"); QUEUE_RO_ENTRY(queue_atomic_write_max_sectors, "atomic_write_max_bytes"); @@ -477,11 +465,11 @@ QUEUE_RO_ENTRY(queue_max_open_zones, "max_open_zones"); QUEUE_RO_ENTRY(queue_max_active_zones, "max_active_zones"); QUEUE_RW_ENTRY(queue_nomerges, "nomerges"); -QUEUE_RW_ENTRY(queue_iostats_passthrough, "iostats_passthrough"); +QUEUE_LIM_RW_ENTRY(queue_iostats_passthrough, "iostats_passthrough"); QUEUE_RW_ENTRY(queue_rq_affinity, "rq_affinity"); QUEUE_RW_ENTRY(queue_poll, "io_poll"); QUEUE_RW_ENTRY(queue_poll_delay, "io_poll_delay"); -QUEUE_RW_ENTRY(queue_wc, "write_cache"); +QUEUE_LIM_RW_ENTRY(queue_wc, "write_cache"); QUEUE_RO_ENTRY(queue_fua, "fua"); QUEUE_RO_ENTRY(queue_dax, "dax"); QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout"); @@ -494,10 +482,10 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = { .show = queue_logical_block_size_show, }; -QUEUE_RW_ENTRY(queue_rotational, "rotational"); -QUEUE_RW_ENTRY(queue_iostats, "iostats"); -QUEUE_RW_ENTRY(queue_add_random, "add_random"); -QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes"); +QUEUE_LIM_RW_ENTRY(queue_rotational, "rotational"); +QUEUE_LIM_RW_ENTRY(queue_iostats, "iostats"); +QUEUE_LIM_RW_ENTRY(queue_add_random, "add_random"); +QUEUE_LIM_RW_ENTRY(queue_stable_writes, "stable_writes"); #ifdef CONFIG_BLK_WBT static ssize_t queue_var_store64(s64 *var, const char *page) @@ -693,9 +681,10 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, struct queue_sysfs_entry *entry = to_queue(attr); struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; + unsigned int memflags; ssize_t res; - if (!entry->store) + if (!entry->store_limit && !entry->store) return -EIO; /* @@ -706,10 +695,25 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, if (entry->load_module) entry->load_module(disk, page, length); + if (entry->store_limit) { + struct queue_limits lim = queue_limits_start_update(q); + + res = entry->store_limit(disk, page, length, &lim); + if (res < 0) { + queue_limits_cancel_update(q); + return res; + } + + res = queue_limits_commit_update_frozen(q, &lim); + if (res) + return res; + return length; + } + mutex_lock(&q->sysfs_lock); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); res = entry->store(disk, page, length); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); mutex_unlock(&q->sysfs_lock); return res; } @@ -758,7 +762,6 @@ int blk_register_queue(struct gendisk *disk) struct request_queue *q = disk->queue; int ret; - mutex_lock(&q->sysfs_dir_lock); kobject_init(&disk->queue_kobj, &blk_queue_ktype); ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue"); if (ret < 0) @@ -799,7 +802,6 @@ int blk_register_queue(struct gendisk *disk) if (q->elevator) kobject_uevent(&q->elevator->kobj, KOBJ_ADD); mutex_unlock(&q->sysfs_lock); - mutex_unlock(&q->sysfs_dir_lock); /* * SCSI probing may synchronously create and destroy a lot of @@ -824,7 +826,6 @@ out_debugfs_remove: mutex_unlock(&q->sysfs_lock); out_put_queue_kobj: kobject_put(&disk->queue_kobj); - mutex_unlock(&q->sysfs_dir_lock); return ret; } @@ -855,7 +856,6 @@ void blk_unregister_queue(struct gendisk *disk) blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q); mutex_unlock(&q->sysfs_lock); - mutex_lock(&q->sysfs_dir_lock); /* * Remove the sysfs attributes before unregistering the queue data * structures that can be modified through sysfs. @@ -872,7 +872,6 @@ void blk_unregister_queue(struct gendisk *disk) /* Now that we've deleted all child objects, we can delete the queue. */ kobject_uevent(&disk->queue_kobj, KOBJ_REMOVE); kobject_del(&disk->queue_kobj); - mutex_unlock(&q->sysfs_dir_lock); blk_debugfs_remove(disk); } diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 82dbaefcfa3b..8d149aff9fd0 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1202,6 +1202,7 @@ static int blk_throtl_init(struct gendisk *disk) { struct request_queue *q = disk->queue; struct throtl_data *td; + unsigned int memflags; int ret; td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node); @@ -1215,7 +1216,7 @@ static int blk_throtl_init(struct gendisk *disk) * Freeze queue before activating policy, to synchronize with IO path, * which is protected by 'q_usage_counter'. */ - blk_mq_freeze_queue(disk->queue); + memflags = blk_mq_freeze_queue(disk->queue); blk_mq_quiesce_queue(disk->queue); q->td = td; @@ -1239,7 +1240,7 @@ static int blk_throtl_init(struct gendisk *disk) out: blk_mq_unquiesce_queue(disk->queue); - blk_mq_unfreeze_queue(disk->queue); + blk_mq_unfreeze_queue(disk->queue, memflags); return ret; } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 84da1eadff64..761ea662ddc3 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -11,12 +11,8 @@ */ #include -#include #include #include -#include -#include -#include #include #include #include @@ -463,6 +459,8 @@ static inline void disk_put_zone_wplug(struct blk_zone_wplug *zwplug) static inline bool disk_should_remove_zone_wplug(struct gendisk *disk, struct blk_zone_wplug *zwplug) { + lockdep_assert_held(&zwplug->lock); + /* If the zone write plug was already removed, we are done. */ if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) return false; @@ -584,6 +582,7 @@ static inline void blk_zone_wplug_bio_io_error(struct blk_zone_wplug *zwplug, bio_clear_flag(bio, BIO_ZONE_WRITE_PLUGGING); bio_io_error(bio); disk_put_zone_wplug(zwplug); + /* Drop the reference taken by disk_zone_wplug_add_bio(() */ blk_queue_exit(q); } @@ -895,10 +894,7 @@ void blk_zone_write_plug_init_request(struct request *req) break; } - /* - * Drop the extra reference on the queue usage we got when - * plugging the BIO and advance the write pointer offset. - */ + /* Drop the reference taken by disk_zone_wplug_add_bio(). */ blk_queue_exit(q); zwplug->wp_offset += bio_sectors(bio); @@ -917,6 +913,8 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug, { struct gendisk *disk = bio->bi_bdev->bd_disk; + lockdep_assert_held(&zwplug->lock); + /* * If we lost track of the zone write pointer due to a write error, * the user must either execute a report zones, reset the zone or finish @@ -1446,7 +1444,6 @@ static int disk_update_zone_resources(struct gendisk *disk, unsigned int nr_seq_zones, nr_conv_zones; unsigned int pool_size; struct queue_limits lim; - int ret; disk->nr_zones = args->nr_zones; disk->zone_capacity = args->zone_capacity; @@ -1497,11 +1494,7 @@ static int disk_update_zone_resources(struct gendisk *disk, } commit: - blk_mq_freeze_queue(q); - ret = queue_limits_commit_update(q, &lim); - blk_mq_unfreeze_queue(q); - - return ret; + return queue_limits_commit_update_frozen(q, &lim); } static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx, @@ -1724,9 +1717,10 @@ int blk_revalidate_disk_zones(struct gendisk *disk) else pr_warn("%s: failed to revalidate zones\n", disk->disk_name); if (ret) { - blk_mq_freeze_queue(q); + unsigned int memflags = blk_mq_freeze_queue(q); + disk_free_zone_resources(disk); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } return ret; @@ -1776,37 +1770,41 @@ int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, EXPORT_SYMBOL_GPL(blk_zone_issue_zeroout); #ifdef CONFIG_BLK_DEBUG_FS +static void queue_zone_wplug_show(struct blk_zone_wplug *zwplug, + struct seq_file *m) +{ + unsigned int zwp_wp_offset, zwp_flags; + unsigned int zwp_zone_no, zwp_ref; + unsigned int zwp_bio_list_size; + unsigned long flags; + + spin_lock_irqsave(&zwplug->lock, flags); + zwp_zone_no = zwplug->zone_no; + zwp_flags = zwplug->flags; + zwp_ref = refcount_read(&zwplug->ref); + zwp_wp_offset = zwplug->wp_offset; + zwp_bio_list_size = bio_list_size(&zwplug->bio_list); + spin_unlock_irqrestore(&zwplug->lock, flags); + + seq_printf(m, "%u 0x%x %u %u %u\n", zwp_zone_no, zwp_flags, zwp_ref, + zwp_wp_offset, zwp_bio_list_size); +} int queue_zone_wplugs_show(void *data, struct seq_file *m) { struct request_queue *q = data; struct gendisk *disk = q->disk; struct blk_zone_wplug *zwplug; - unsigned int zwp_wp_offset, zwp_flags; - unsigned int zwp_zone_no, zwp_ref; - unsigned int zwp_bio_list_size, i; - unsigned long flags; + unsigned int i; if (!disk->zone_wplugs_hash) return 0; rcu_read_lock(); - for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) { - hlist_for_each_entry_rcu(zwplug, - &disk->zone_wplugs_hash[i], node) { - spin_lock_irqsave(&zwplug->lock, flags); - zwp_zone_no = zwplug->zone_no; - zwp_flags = zwplug->flags; - zwp_ref = refcount_read(&zwplug->ref); - zwp_wp_offset = zwplug->wp_offset; - zwp_bio_list_size = bio_list_size(&zwplug->bio_list); - spin_unlock_irqrestore(&zwplug->lock, flags); - - seq_printf(m, "%u 0x%x %u %u %u\n", - zwp_zone_no, zwp_flags, zwp_ref, - zwp_wp_offset, zwp_bio_list_size); - } - } + for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) + hlist_for_each_entry_rcu(zwplug, &disk->zone_wplugs_hash[i], + node) + queue_zone_wplug_show(zwplug, m); rcu_read_unlock(); return 0; diff --git a/block/blk.h b/block/blk.h index 2c26abf505b8..90fa5f28ccab 100644 --- a/block/blk.h +++ b/block/blk.h @@ -13,6 +13,8 @@ struct elevator_type; +#define BLK_DEV_MAX_SECTORS (LLONG_MAX >> 9) + /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) @@ -556,14 +558,6 @@ void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors); struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, struct lock_class_key *lkclass); -int bio_add_hw_page(struct request_queue *q, struct bio *bio, - struct page *page, unsigned int len, unsigned int offset, - unsigned int max_sectors, bool *same_page); - -int bio_add_hw_folio(struct request_queue *q, struct bio *bio, - struct folio *folio, size_t len, size_t offset, - unsigned int max_sectors, bool *same_page); - /* * Clean up a page appropriately, where the page may be pinned, may have a * ref taken on it or neither. @@ -720,22 +714,29 @@ void blk_integrity_verify(struct bio *bio); void blk_integrity_prepare(struct request *rq); void blk_integrity_complete(struct request *rq, unsigned int nr_bytes); -static inline void blk_freeze_acquire_lock(struct request_queue *q, bool - disk_dead, bool queue_dying) +#ifdef CONFIG_LOCKDEP +static inline void blk_freeze_acquire_lock(struct request_queue *q) { - if (!disk_dead) + if (!q->mq_freeze_disk_dead) rwsem_acquire(&q->io_lockdep_map, 0, 1, _RET_IP_); - if (!queue_dying) + if (!q->mq_freeze_queue_dying) rwsem_acquire(&q->q_lockdep_map, 0, 1, _RET_IP_); } -static inline void blk_unfreeze_release_lock(struct request_queue *q, bool - disk_dead, bool queue_dying) +static inline void blk_unfreeze_release_lock(struct request_queue *q) { - if (!queue_dying) + if (!q->mq_freeze_queue_dying) rwsem_release(&q->q_lockdep_map, _RET_IP_); - if (!disk_dead) + if (!q->mq_freeze_disk_dead) rwsem_release(&q->io_lockdep_map, _RET_IP_); } +#else +static inline void blk_freeze_acquire_lock(struct request_queue *q) +{ +} +static inline void blk_unfreeze_release_lock(struct request_queue *q) +{ +} +#endif #endif /* BLK_INTERNAL_H */ diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 32da4a4429ce..93523d8f8195 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -381,7 +381,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, set->queue_depth = 128; set->numa_node = NUMA_NO_NODE; set->cmd_size = sizeof(struct bsg_job) + dd_job_size; - set->flags = BLK_MQ_F_NO_SCHED | BLK_MQ_F_BLOCKING; + set->flags = BLK_MQ_F_BLOCKING; if (blk_mq_alloc_tag_set(set)) goto out_tag_set; diff --git a/block/elevator.c b/block/elevator.c index 7c3ba80e5ff4..cd2ce4921601 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -405,12 +405,12 @@ struct request *elv_former_request(struct request_queue *q, struct request *rq) return NULL; } -#define to_elv(atr) container_of((atr), struct elv_fs_entry, attr) +#define to_elv(atr) container_of_const((atr), struct elv_fs_entry, attr) static ssize_t elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { - struct elv_fs_entry *entry = to_elv(attr); + const struct elv_fs_entry *entry = to_elv(attr); struct elevator_queue *e; ssize_t error; @@ -428,7 +428,7 @@ static ssize_t elv_attr_store(struct kobject *kobj, struct attribute *attr, const char *page, size_t length) { - struct elv_fs_entry *entry = to_elv(attr); + const struct elv_fs_entry *entry = to_elv(attr); struct elevator_queue *e; ssize_t error; @@ -461,7 +461,7 @@ int elv_register_queue(struct request_queue *q, bool uevent) error = kobject_add(&e->kobj, &q->disk->queue_kobj, "iosched"); if (!error) { - struct elv_fs_entry *attr = e->type->elevator_attrs; + const struct elv_fs_entry *attr = e->type->elevator_attrs; if (attr) { while (attr->attr.name) { if (sysfs_create_file(&e->kobj, &attr->attr)) @@ -547,14 +547,6 @@ void elv_unregister(struct elevator_type *e) } EXPORT_SYMBOL_GPL(elv_unregister); -static inline bool elv_support_iosched(struct request_queue *q) -{ - if (!queue_is_mq(q) || - (q->tag_set->flags & BLK_MQ_F_NO_SCHED)) - return false; - return true; -} - /* * For single queue devices, default to using mq-deadline. If we have multiple * queues or mq-deadline is not available, default to "none". @@ -578,11 +570,9 @@ static struct elevator_type *elevator_get_default(struct request_queue *q) void elevator_init_mq(struct request_queue *q) { struct elevator_type *e; + unsigned int memflags; int err; - if (!elv_support_iosched(q)) - return; - WARN_ON_ONCE(blk_queue_registered(q)); if (unlikely(q->elevator)) @@ -601,16 +591,13 @@ void elevator_init_mq(struct request_queue *q) * * Disk isn't added yet, so verifying queue lock only manually. */ - blk_freeze_queue_start_non_owner(q); - blk_freeze_acquire_lock(q, true, false); - blk_mq_freeze_queue_wait(q); + memflags = blk_mq_freeze_queue(q); blk_mq_cancel_work_sync(q); err = blk_mq_init_sched(q, e); - blk_unfreeze_release_lock(q, true, false); - blk_mq_unfreeze_queue_non_owner(q); + blk_mq_unfreeze_queue(q, memflags); if (err) { pr_warn("\"%s\" elevator initialization failed, " @@ -628,11 +615,12 @@ void elevator_init_mq(struct request_queue *q) */ int elevator_switch(struct request_queue *q, struct elevator_type *new_e) { + unsigned int memflags; int ret; lockdep_assert_held(&q->sysfs_lock); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); if (q->elevator) { @@ -653,7 +641,7 @@ int elevator_switch(struct request_queue *q, struct elevator_type *new_e) out_unfreeze: blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); if (ret) { pr_warn("elv: switch to \"%s\" failed, falling back to \"none\"\n", @@ -665,9 +653,11 @@ out_unfreeze: void elevator_disable(struct request_queue *q) { + unsigned int memflags; + lockdep_assert_held(&q->sysfs_lock); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); elv_unregister_queue(q); @@ -678,7 +668,7 @@ void elevator_disable(struct request_queue *q) blk_add_trace_msg(q, "elv switch: none"); blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } /* @@ -717,9 +707,6 @@ void elv_iosched_load_module(struct gendisk *disk, const char *buf, struct elevator_type *found; const char *name; - if (!elv_support_iosched(disk->queue)) - return; - strscpy(elevator_name, buf, sizeof(elevator_name)); name = strstrip(elevator_name); @@ -737,9 +724,6 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, char elevator_name[ELV_NAME_MAX]; int ret; - if (!elv_support_iosched(disk->queue)) - return count; - strscpy(elevator_name, buf, sizeof(elevator_name)); ret = elevator_change(disk->queue, strstrip(elevator_name)); if (!ret) @@ -754,9 +738,6 @@ ssize_t elv_iosched_show(struct gendisk *disk, char *name) struct elevator_type *cur = NULL, *e; int len = 0; - if (!elv_support_iosched(q)) - return sprintf(name, "none\n"); - if (!q->elevator) { len += sprintf(name+len, "[none] "); } else { diff --git a/block/elevator.h b/block/elevator.h index dbf357ef4fab..e526662c5dbb 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -71,7 +71,7 @@ struct elevator_type size_t icq_size; /* see iocontext.h */ size_t icq_align; /* ditto */ - struct elv_fs_entry *elevator_attrs; + const struct elv_fs_entry *elevator_attrs; const char *elevator_name; const char *elevator_alias; struct module *elevator_owner; diff --git a/block/fops.c b/block/fops.c index 13a67940d040..be9f1dbea9ce 100644 --- a/block/fops.c +++ b/block/fops.c @@ -54,6 +54,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct bio bio; ssize_t ret; + WARN_ON_ONCE(iocb->ki_flags & IOCB_HAS_METADATA); if (nr_pages <= DIO_INLINE_BIO_VECS) vecs = inline_vecs; else { @@ -124,12 +125,16 @@ static void blkdev_bio_end_io(struct bio *bio) { struct blkdev_dio *dio = bio->bi_private; bool should_dirty = dio->flags & DIO_SHOULD_DIRTY; + bool is_sync = dio->flags & DIO_IS_SYNC; if (bio->bi_status && !dio->bio.bi_status) dio->bio.bi_status = bio->bi_status; + if (!is_sync && (dio->iocb->ki_flags & IOCB_HAS_METADATA)) + bio_integrity_unmap_user(bio); + if (atomic_dec_and_test(&dio->ref)) { - if (!(dio->flags & DIO_IS_SYNC)) { + if (!is_sync) { struct kiocb *iocb = dio->iocb; ssize_t ret; @@ -221,14 +226,16 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * a retry of this from blocking context. */ if (unlikely(iov_iter_count(iter))) { - bio_release_pages(bio, false); - bio_clear_flag(bio, BIO_REFFED); - bio_put(bio); - blk_finish_plug(&plug); - return -EAGAIN; + ret = -EAGAIN; + goto fail; } bio->bi_opf |= REQ_NOWAIT; } + if (!is_sync && (iocb->ki_flags & IOCB_HAS_METADATA)) { + ret = bio_integrity_map_iter(bio, iocb->private); + if (unlikely(ret)) + goto fail; + } if (is_read) { if (dio->flags & DIO_SHOULD_DIRTY) @@ -269,6 +276,12 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, bio_put(&dio->bio); return ret; +fail: + bio_release_pages(bio, false); + bio_clear_flag(bio, BIO_REFFED); + bio_put(bio); + blk_finish_plug(&plug); + return ret; } static void blkdev_bio_end_io_async(struct bio *bio) @@ -286,6 +299,9 @@ static void blkdev_bio_end_io_async(struct bio *bio) ret = blk_status_to_errno(bio->bi_status); } + if (iocb->ki_flags & IOCB_HAS_METADATA) + bio_integrity_unmap_user(bio); + iocb->ki_complete(iocb, ret); if (dio->flags & DIO_SHOULD_DIRTY) { @@ -330,10 +346,8 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, bio_iov_bvec_set(bio, iter); } else { ret = bio_iov_iter_get_pages(bio, iter); - if (unlikely(ret)) { - bio_put(bio); - return ret; - } + if (unlikely(ret)) + goto out_bio_put; } dio->size = bio->bi_iter.bi_size; @@ -346,6 +360,13 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, task_io_account_write(bio->bi_iter.bi_size); } + if (iocb->ki_flags & IOCB_HAS_METADATA) { + ret = bio_integrity_map_iter(bio, iocb->private); + WRITE_ONCE(iocb->private, NULL); + if (unlikely(ret)) + goto out_bio_put; + } + if (iocb->ki_flags & IOCB_ATOMIC) bio->bi_opf |= REQ_ATOMIC; @@ -360,6 +381,10 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, submit_bio(bio); } return -EIOCBQUEUED; + +out_bio_put: + bio_put(bio); + return ret; } static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) @@ -758,11 +783,12 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) file_accessed(iocb->ki_filp); ret = blkdev_direct_IO(iocb, to); - if (ret >= 0) { + if (ret > 0) { iocb->ki_pos += ret; count -= ret; } - iov_iter_revert(to, count - iov_iter_count(to)); + if (ret != -EIOCBQUEUED) + iov_iter_revert(to, count - iov_iter_count(to)); if (ret < 0 || !count) goto reexpand; } diff --git a/block/genhd.c b/block/genhd.c index 79230c109fca..e9375e20d866 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -58,6 +58,13 @@ static DEFINE_IDA(ext_devt_ida); void set_capacity(struct gendisk *disk, sector_t sectors) { + if (sectors > BLK_DEV_MAX_SECTORS) { + pr_warn_once("%s: truncate capacity from %lld to %lld\n", + disk->disk_name, sectors, + BLK_DEV_MAX_SECTORS); + sectors = BLK_DEV_MAX_SECTORS; + } + bdev_set_nr_sectors(disk->part0, sectors); } EXPORT_SYMBOL(set_capacity); @@ -400,21 +407,26 @@ int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, struct device *ddev = disk_to_dev(disk); int ret; - /* Only makes sense for bio-based to set ->poll_bio */ - if (queue_is_mq(disk->queue) && disk->fops->poll_bio) + if (WARN_ON_ONCE(bdev_nr_sectors(disk->part0) > BLK_DEV_MAX_SECTORS)) return -EINVAL; - /* - * The disk queue should now be all set with enough information about - * the device for the elevator code to pick an adequate default - * elevator if one is needed, that is, for devices requesting queue - * registration. - */ - elevator_init_mq(disk->queue); + if (queue_is_mq(disk->queue)) { + /* + * ->submit_bio and ->poll_bio are bypassed for blk-mq drivers. + */ + if (disk->fops->submit_bio || disk->fops->poll_bio) + return -EINVAL; - /* Mark bdev as having a submit_bio, if needed */ - if (disk->fops->submit_bio) + /* + * Initialize the I/O scheduler code and pick a default one if + * needed. + */ + elevator_init_mq(disk->queue); + } else { + if (!disk->fops->submit_bio) + return -EINVAL; bdev_set_flag(disk->part0, BD_HAS_SUBMIT_BIO); + } /* * If the driver provides an explicit major number it also must provide @@ -661,7 +673,7 @@ void del_gendisk(struct gendisk *disk) struct request_queue *q = disk->queue; struct block_device *part; unsigned long idx; - bool start_drain, queue_dying; + bool start_drain; might_sleep(); @@ -690,9 +702,8 @@ void del_gendisk(struct gendisk *disk) */ mutex_lock(&disk->open_mutex); start_drain = __blk_mark_disk_dead(disk); - queue_dying = blk_queue_dying(q); if (start_drain) - blk_freeze_acquire_lock(q, true, queue_dying); + blk_freeze_acquire_lock(q); xa_for_each_start(&disk->part_tbl, idx, part, 1) drop_partition(part); mutex_unlock(&disk->open_mutex); @@ -748,7 +759,7 @@ void del_gendisk(struct gendisk *disk) blk_mq_exit_queue(q); if (start_drain) - blk_unfreeze_release_lock(q, true, queue_dying); + blk_unfreeze_release_lock(q); } EXPORT_SYMBOL(del_gendisk); @@ -798,7 +809,7 @@ static ssize_t disk_badblocks_store(struct device *dev, } #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD -void blk_request_module(dev_t devt) +static bool blk_probe_dev(dev_t devt) { unsigned int major = MAJOR(devt); struct blk_major_name **n; @@ -808,14 +819,26 @@ void blk_request_module(dev_t devt) if ((*n)->major == major && (*n)->probe) { (*n)->probe(devt); mutex_unlock(&major_names_lock); - return; + return true; } } mutex_unlock(&major_names_lock); + return false; +} - if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0) - /* Make old-style 2.4 aliases work */ - request_module("block-major-%d", MAJOR(devt)); +void blk_request_module(dev_t devt) +{ + int error; + + if (blk_probe_dev(devt)) + return; + + error = request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)); + /* Make old-style 2.4 aliases work */ + if (error > 0) + error = request_module("block-major-%d", MAJOR(devt)); + if (!error) + blk_probe_dev(devt); } #endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */ diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 4155594aefc6..dc31f2dfa414 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -889,7 +889,7 @@ KYBER_LAT_SHOW_STORE(KYBER_WRITE, write); #undef KYBER_LAT_SHOW_STORE #define KYBER_LAT_ATTR(op) __ATTR(op##_lat_nsec, 0644, kyber_##op##_lat_show, kyber_##op##_lat_store) -static struct elv_fs_entry kyber_sched_attrs[] = { +static const struct elv_fs_entry kyber_sched_attrs[] = { KYBER_LAT_ATTR(read), KYBER_LAT_ATTR(write), __ATTR_NULL diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 5528347b5fcf..754f6b7415cd 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -834,7 +834,7 @@ STORE_INT(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX); #define DD_ATTR(name) \ __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store) -static struct elv_fs_entry deadline_attrs[] = { +static const struct elv_fs_entry deadline_attrs[] = { DD_ATTR(read_expire), DD_ATTR(write_expire), DD_ATTR(writes_starved), diff --git a/block/partitions/ldm.h b/block/partitions/ldm.h index e259180c8914..aa3bd050d8cd 100644 --- a/block/partitions/ldm.h +++ b/block/partitions/ldm.h @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/** +/* * ldm - Part of the Linux-NTFS project. * * Copyright (C) 2001,2002 Richard Russon diff --git a/crypto/Kconfig b/crypto/Kconfig index 6b0bfbccac08..74ae5f52b784 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -684,14 +684,6 @@ config CRYPTO_HCTR2 See https://eprint.iacr.org/2021/1441 -config CRYPTO_KEYWRAP - tristate "KW (AES Key Wrap)" - select CRYPTO_SKCIPHER - select CRYPTO_MANAGER - help - KW (AES Key Wrap) authenticated encryption mode (NIST SP800-38F - and RFC3394) without padding. - config CRYPTO_LRW tristate "LRW (Liskov Rivest Wagner)" select CRYPTO_LIB_GF128MUL @@ -1029,16 +1021,6 @@ config CRYPTO_STREEBOG https://tc26.ru/upload/iblock/fed/feddbb4d26b685903faa2ba11aea43f6.pdf https://tools.ietf.org/html/rfc6986 -config CRYPTO_VMAC - tristate "VMAC" - select CRYPTO_HASH - select CRYPTO_MANAGER - help - VMAC is a message authentication algorithm designed for - very high speed on 64-bit architectures. - - See https://fastcrypto.org/vmac for further information. - config CRYPTO_WP512 tristate "Whirlpool" select CRYPTO_HASH @@ -1102,6 +1084,7 @@ config CRYPTO_CRC32 config CRYPTO_CRCT10DIF tristate "CRCT10DIF" select CRYPTO_HASH + select CRC_T10DIF help CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF) diff --git a/crypto/Makefile b/crypto/Makefile index 77abca715445..f67e853c4690 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -69,7 +69,6 @@ obj-$(CONFIG_CRYPTO_MANAGER2) += cryptomgr.o obj-$(CONFIG_CRYPTO_USER) += crypto_user.o obj-$(CONFIG_CRYPTO_CMAC) += cmac.o obj-$(CONFIG_CRYPTO_HMAC) += hmac.o -obj-$(CONFIG_CRYPTO_VMAC) += vmac.o obj-$(CONFIG_CRYPTO_XCBC) += xcbc.o obj-$(CONFIG_CRYPTO_NULL2) += crypto_null.o obj-$(CONFIG_CRYPTO_MD4) += md4.o @@ -95,7 +94,6 @@ obj-$(CONFIG_CRYPTO_XTS) += xts.o obj-$(CONFIG_CRYPTO_CTR) += ctr.o obj-$(CONFIG_CRYPTO_XCTR) += xctr.o obj-$(CONFIG_CRYPTO_HCTR2) += hctr2.o -obj-$(CONFIG_CRYPTO_KEYWRAP) += keywrap.o obj-$(CONFIG_CRYPTO_ADIANTUM) += adiantum.o obj-$(CONFIG_CRYPTO_NHPOLY1305) += nhpoly1305.o obj-$(CONFIG_CRYPTO_GCM) += gcm.o @@ -157,7 +155,8 @@ obj-$(CONFIG_CRYPTO_CRC32C) += crc32c_generic.o obj-$(CONFIG_CRYPTO_CRC32) += crc32_generic.o CFLAGS_crc32c_generic.o += -DARCH=$(ARCH) CFLAGS_crc32_generic.o += -DARCH=$(ARCH) -obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif_common.o crct10dif_generic.o +obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif_generic.o +CFLAGS_crct10dif_generic.o += -DARCH=$(ARCH) obj-$(CONFIG_CRYPTO_CRC64_ROCKSOFT) += crc64_rocksoft_generic.o obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o obj-$(CONFIG_CRYPTO_LZO) += lzo.o lzo-rle.o diff --git a/crypto/aegis128-core.c b/crypto/aegis128-core.c index 4fdb53435827..6cbff298722b 100644 --- a/crypto/aegis128-core.c +++ b/crypto/aegis128-core.c @@ -516,7 +516,6 @@ static struct aead_alg crypto_aegis128_alg_generic = { .base.cra_blocksize = 1, .base.cra_ctxsize = sizeof(struct aegis_ctx), - .base.cra_alignmask = 0, .base.cra_priority = 100, .base.cra_name = "aegis128", .base.cra_driver_name = "aegis128-generic", @@ -535,7 +534,6 @@ static struct aead_alg crypto_aegis128_alg_simd = { .base.cra_blocksize = 1, .base.cra_ctxsize = sizeof(struct aegis_ctx), - .base.cra_alignmask = 0, .base.cra_priority = 200, .base.cra_name = "aegis128", .base.cra_driver_name = "aegis128-simd", diff --git a/crypto/ahash.c b/crypto/ahash.c index bcd9de009a91..b08b89ec26ec 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -27,6 +27,93 @@ #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e +struct crypto_hash_walk { + char *data; + + unsigned int offset; + unsigned int flags; + + struct page *pg; + unsigned int entrylen; + + unsigned int total; + struct scatterlist *sg; +}; + +static int hash_walk_next(struct crypto_hash_walk *walk) +{ + unsigned int offset = walk->offset; + unsigned int nbytes = min(walk->entrylen, + ((unsigned int)(PAGE_SIZE)) - offset); + + walk->data = kmap_local_page(walk->pg); + walk->data += offset; + walk->entrylen -= nbytes; + return nbytes; +} + +static int hash_walk_new_entry(struct crypto_hash_walk *walk) +{ + struct scatterlist *sg; + + sg = walk->sg; + walk->offset = sg->offset; + walk->pg = sg_page(walk->sg) + (walk->offset >> PAGE_SHIFT); + walk->offset = offset_in_page(walk->offset); + walk->entrylen = sg->length; + + if (walk->entrylen > walk->total) + walk->entrylen = walk->total; + walk->total -= walk->entrylen; + + return hash_walk_next(walk); +} + +static int crypto_hash_walk_first(struct ahash_request *req, + struct crypto_hash_walk *walk) +{ + walk->total = req->nbytes; + + if (!walk->total) { + walk->entrylen = 0; + return 0; + } + + walk->sg = req->src; + walk->flags = req->base.flags; + + return hash_walk_new_entry(walk); +} + +static int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err) +{ + walk->data -= walk->offset; + + kunmap_local(walk->data); + crypto_yield(walk->flags); + + if (err) + return err; + + if (walk->entrylen) { + walk->offset = 0; + walk->pg++; + return hash_walk_next(walk); + } + + if (!walk->total) + return 0; + + walk->sg = sg_next(walk->sg); + + return hash_walk_new_entry(walk); +} + +static inline int crypto_hash_walk_last(struct crypto_hash_walk *walk) +{ + return !(walk->entrylen | walk->total); +} + /* * For an ahash tfm that is using an shash algorithm (instead of an ahash * algorithm), this returns the underlying shash tfm. @@ -137,77 +224,6 @@ static int crypto_init_ahash_using_shash(struct crypto_tfm *tfm) return 0; } -static int hash_walk_next(struct crypto_hash_walk *walk) -{ - unsigned int offset = walk->offset; - unsigned int nbytes = min(walk->entrylen, - ((unsigned int)(PAGE_SIZE)) - offset); - - walk->data = kmap_local_page(walk->pg); - walk->data += offset; - walk->entrylen -= nbytes; - return nbytes; -} - -static int hash_walk_new_entry(struct crypto_hash_walk *walk) -{ - struct scatterlist *sg; - - sg = walk->sg; - walk->offset = sg->offset; - walk->pg = sg_page(walk->sg) + (walk->offset >> PAGE_SHIFT); - walk->offset = offset_in_page(walk->offset); - walk->entrylen = sg->length; - - if (walk->entrylen > walk->total) - walk->entrylen = walk->total; - walk->total -= walk->entrylen; - - return hash_walk_next(walk); -} - -int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err) -{ - walk->data -= walk->offset; - - kunmap_local(walk->data); - crypto_yield(walk->flags); - - if (err) - return err; - - if (walk->entrylen) { - walk->offset = 0; - walk->pg++; - return hash_walk_next(walk); - } - - if (!walk->total) - return 0; - - walk->sg = sg_next(walk->sg); - - return hash_walk_new_entry(walk); -} -EXPORT_SYMBOL_GPL(crypto_hash_walk_done); - -int crypto_hash_walk_first(struct ahash_request *req, - struct crypto_hash_walk *walk) -{ - walk->total = req->nbytes; - - if (!walk->total) { - walk->entrylen = 0; - return 0; - } - - walk->sg = req->src; - walk->flags = req->base.flags; - - return hash_walk_new_entry(walk); -} -EXPORT_SYMBOL_GPL(crypto_hash_walk_first); - static int ahash_nosetkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen) { diff --git a/crypto/algapi.c b/crypto/algapi.c index 16f7c7a9d8ab..5318c214debb 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -407,6 +407,7 @@ EXPORT_SYMBOL_GPL(crypto_remove_final); int crypto_register_alg(struct crypto_alg *alg) { struct crypto_larval *larval; + bool test_started = false; LIST_HEAD(algs_to_put); int err; @@ -418,17 +419,19 @@ int crypto_register_alg(struct crypto_alg *alg) down_write(&crypto_alg_sem); larval = __crypto_register_alg(alg, &algs_to_put); if (!IS_ERR_OR_NULL(larval)) { - bool test_started = crypto_boot_test_finished(); - + test_started = crypto_boot_test_finished(); larval->test_started = test_started; - if (test_started) - crypto_schedule_test(larval); } up_write(&crypto_alg_sem); if (IS_ERR(larval)) return PTR_ERR(larval); - crypto_remove_final(&algs_to_put); + + if (test_started) + crypto_schedule_test(larval); + else + crypto_remove_final(&algs_to_put); + return 0; } EXPORT_SYMBOL_GPL(crypto_register_alg); @@ -642,10 +645,8 @@ int crypto_register_instance(struct crypto_template *tmpl, larval = __crypto_register_alg(&inst->alg, &algs_to_put); if (IS_ERR(larval)) goto unlock; - else if (larval) { + else if (larval) larval->test_started = true; - crypto_schedule_test(larval); - } hlist_add_head(&inst->list, &tmpl->instances); inst->tmpl = tmpl; @@ -655,7 +656,12 @@ unlock: if (IS_ERR(larval)) return PTR_ERR(larval); - crypto_remove_final(&algs_to_put); + + if (larval) + crypto_schedule_test(larval); + else + crypto_remove_final(&algs_to_put); + return 0; } EXPORT_SYMBOL_GPL(crypto_register_instance); @@ -1016,6 +1022,8 @@ static void __init crypto_start_tests(void) if (IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS)) return; + set_crypto_boot_test_finished(); + for (;;) { struct crypto_larval *larval = NULL; struct crypto_alg *q; @@ -1038,7 +1046,6 @@ static void __init crypto_start_tests(void) l->test_started = true; larval = l; - crypto_schedule_test(larval); break; } @@ -1046,9 +1053,9 @@ static void __init crypto_start_tests(void) if (!larval) break; - } - set_crypto_boot_test_finished(); + crypto_schedule_test(larval); + } } static int __init crypto_algapi_init(void) diff --git a/crypto/anubis.c b/crypto/anubis.c index 9f0cf61bbc6e..886e7c913688 100644 --- a/crypto/anubis.c +++ b/crypto/anubis.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #define ANUBIS_MIN_KEY_SIZE 16 @@ -463,7 +463,6 @@ static int anubis_setkey(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct anubis_ctx *ctx = crypto_tfm_ctx(tfm); - const __be32 *key = (const __be32 *)in_key; int N, R, i, r; u32 kappa[ANUBIS_MAX_N]; u32 inter[ANUBIS_MAX_N]; @@ -482,7 +481,7 @@ static int anubis_setkey(struct crypto_tfm *tfm, const u8 *in_key, /* * map cipher key to initial key state (mu): */ for (i = 0; i < N; i++) - kappa[i] = be32_to_cpu(key[i]); + kappa[i] = get_unaligned_be32(&in_key[4 * i]); /* * generate R + 1 round keys: @@ -570,10 +569,8 @@ static int anubis_setkey(struct crypto_tfm *tfm, const u8 *in_key, } static void anubis_crypt(u32 roundKey[ANUBIS_MAX_ROUNDS + 1][4], - u8 *ciphertext, const u8 *plaintext, const int R) + u8 *dst, const u8 *src, const int R) { - const __be32 *src = (const __be32 *)plaintext; - __be32 *dst = (__be32 *)ciphertext; int i, r; u32 state[4]; u32 inter[4]; @@ -583,7 +580,7 @@ static void anubis_crypt(u32 roundKey[ANUBIS_MAX_ROUNDS + 1][4], * and add initial round key (sigma[K^0]): */ for (i = 0; i < 4; i++) - state[i] = be32_to_cpu(src[i]) ^ roundKey[0][i]; + state[i] = get_unaligned_be32(&src[4 * i]) ^ roundKey[0][i]; /* * R - 1 full rounds: @@ -654,7 +651,7 @@ static void anubis_crypt(u32 roundKey[ANUBIS_MAX_ROUNDS + 1][4], */ for (i = 0; i < 4; i++) - dst[i] = cpu_to_be32(inter[i]); + put_unaligned_be32(inter[i], &dst[4 * i]); } static void anubis_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) @@ -675,7 +672,6 @@ static struct crypto_alg anubis_alg = { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = ANUBIS_BLOCK_SIZE, .cra_ctxsize = sizeof (struct anubis_ctx), - .cra_alignmask = 3, .cra_module = THIS_MODULE, .cra_u = { .cipher = { .cia_min_keysize = ANUBIS_MIN_KEY_SIZE, diff --git a/crypto/aria_generic.c b/crypto/aria_generic.c index d96dfc4fdde6..bd359d3313c2 100644 --- a/crypto/aria_generic.c +++ b/crypto/aria_generic.c @@ -15,6 +15,7 @@ */ #include +#include static const u32 key_rc[20] = { 0x517cc1b7, 0x27220a94, 0xfe13abe8, 0xfa9a6ee0, @@ -27,7 +28,6 @@ static const u32 key_rc[20] = { static void aria_set_encrypt_key(struct aria_ctx *ctx, const u8 *in_key, unsigned int key_len) { - const __be32 *key = (const __be32 *)in_key; u32 w0[4], w1[4], w2[4], w3[4]; u32 reg0, reg1, reg2, reg3; const u32 *ck; @@ -35,10 +35,10 @@ static void aria_set_encrypt_key(struct aria_ctx *ctx, const u8 *in_key, ck = &key_rc[(key_len - 16) / 2]; - w0[0] = be32_to_cpu(key[0]); - w0[1] = be32_to_cpu(key[1]); - w0[2] = be32_to_cpu(key[2]); - w0[3] = be32_to_cpu(key[3]); + w0[0] = get_unaligned_be32(&in_key[0]); + w0[1] = get_unaligned_be32(&in_key[4]); + w0[2] = get_unaligned_be32(&in_key[8]); + w0[3] = get_unaligned_be32(&in_key[12]); reg0 = w0[0] ^ ck[0]; reg1 = w0[1] ^ ck[1]; @@ -48,11 +48,11 @@ static void aria_set_encrypt_key(struct aria_ctx *ctx, const u8 *in_key, aria_subst_diff_odd(®0, ®1, ®2, ®3); if (key_len > 16) { - w1[0] = be32_to_cpu(key[4]); - w1[1] = be32_to_cpu(key[5]); + w1[0] = get_unaligned_be32(&in_key[16]); + w1[1] = get_unaligned_be32(&in_key[20]); if (key_len > 24) { - w1[2] = be32_to_cpu(key[6]); - w1[3] = be32_to_cpu(key[7]); + w1[2] = get_unaligned_be32(&in_key[24]); + w1[3] = get_unaligned_be32(&in_key[28]); } else { w1[2] = 0; w1[3] = 0; @@ -195,17 +195,15 @@ EXPORT_SYMBOL_GPL(aria_set_key); static void __aria_crypt(struct aria_ctx *ctx, u8 *out, const u8 *in, u32 key[][ARIA_RD_KEY_WORDS]) { - const __be32 *src = (const __be32 *)in; - __be32 *dst = (__be32 *)out; u32 reg0, reg1, reg2, reg3; int rounds, rkidx = 0; rounds = ctx->rounds; - reg0 = be32_to_cpu(src[0]); - reg1 = be32_to_cpu(src[1]); - reg2 = be32_to_cpu(src[2]); - reg3 = be32_to_cpu(src[3]); + reg0 = get_unaligned_be32(&in[0]); + reg1 = get_unaligned_be32(&in[4]); + reg2 = get_unaligned_be32(&in[8]); + reg3 = get_unaligned_be32(&in[12]); aria_add_round_key(key[rkidx], ®0, ®1, ®2, ®3); rkidx++; @@ -241,10 +239,10 @@ static void __aria_crypt(struct aria_ctx *ctx, u8 *out, const u8 *in, (u8)(s1[get_u8(reg3, 2)]), (u8)(s2[get_u8(reg3, 3)])); - dst[0] = cpu_to_be32(reg0); - dst[1] = cpu_to_be32(reg1); - dst[2] = cpu_to_be32(reg2); - dst[3] = cpu_to_be32(reg3); + put_unaligned_be32(reg0, &out[0]); + put_unaligned_be32(reg1, &out[4]); + put_unaligned_be32(reg2, &out[8]); + put_unaligned_be32(reg3, &out[12]); } void aria_encrypt(void *_ctx, u8 *out, const u8 *in) @@ -284,7 +282,6 @@ static struct crypto_alg aria_alg = { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = ARIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct aria_ctx), - .cra_alignmask = 3, .cra_module = THIS_MODULE, .cra_u = { .cipher = { diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c index 43af5fa510c0..ba2d9d1ea235 100644 --- a/crypto/asymmetric_keys/asymmetric_type.c +++ b/crypto/asymmetric_keys/asymmetric_type.c @@ -18,16 +18,6 @@ #include "asymmetric_keys.h" -const char *const key_being_used_for[NR__KEY_BEING_USED_FOR] = { - [VERIFYING_MODULE_SIGNATURE] = "mod sig", - [VERIFYING_FIRMWARE_SIGNATURE] = "firmware sig", - [VERIFYING_KEXEC_PE_SIGNATURE] = "kexec PE sig", - [VERIFYING_KEY_SIGNATURE] = "key sig", - [VERIFYING_KEY_SELF_SIGNATURE] = "key self sig", - [VERIFYING_UNSPECIFIED_SIGNATURE] = "unspec sig", -}; -EXPORT_SYMBOL_GPL(key_being_used_for); - static LIST_HEAD(asymmetric_key_parsers); static DECLARE_RWSEM(asymmetric_key_parsers_sem); diff --git a/crypto/crc32_generic.c b/crypto/crc32_generic.c index 6a55d206fab3..783a30b27398 100644 --- a/crypto/crc32_generic.c +++ b/crypto/crc32_generic.c @@ -157,15 +157,19 @@ static struct shash_alg algs[] = {{ .base.cra_init = crc32_cra_init, }}; +static int num_algs; + static int __init crc32_mod_init(void) { /* register the arch flavor only if it differs from the generic one */ - return crypto_register_shashes(algs, 1 + (&crc32_le != &crc32_le_base)); + num_algs = 1 + ((crc32_optimizations() & CRC32_LE_OPTIMIZATION) != 0); + + return crypto_register_shashes(algs, num_algs); } static void __exit crc32_mod_fini(void) { - crypto_unregister_shashes(algs, 1 + (&crc32_le != &crc32_le_base)); + crypto_unregister_shashes(algs, num_algs); } subsys_initcall(crc32_mod_init); diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c index 7c2357c30fdf..985da981d6e2 100644 --- a/crypto/crc32c_generic.c +++ b/crypto/crc32c_generic.c @@ -85,7 +85,7 @@ static int chksum_update(struct shash_desc *desc, const u8 *data, { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - ctx->crc = __crc32c_le_base(ctx->crc, data, length); + ctx->crc = crc32c_le_base(ctx->crc, data, length); return 0; } @@ -108,7 +108,7 @@ static int chksum_final(struct shash_desc *desc, u8 *out) static int __chksum_finup(u32 *crcp, const u8 *data, unsigned int len, u8 *out) { - put_unaligned_le32(~__crc32c_le_base(*crcp, data, len), out); + put_unaligned_le32(~crc32c_le_base(*crcp, data, len), out); return 0; } @@ -197,15 +197,19 @@ static struct shash_alg algs[] = {{ .base.cra_init = crc32c_cra_init, }}; +static int num_algs; + static int __init crc32c_mod_init(void) { /* register the arch flavor only if it differs from the generic one */ - return crypto_register_shashes(algs, 1 + (&__crc32c_le != &__crc32c_le_base)); + num_algs = 1 + ((crc32_optimizations() & CRC32C_OPTIMIZATION) != 0); + + return crypto_register_shashes(algs, num_algs); } static void __exit crc32c_mod_fini(void) { - crypto_unregister_shashes(algs, 1 + (&__crc32c_le != &__crc32c_le_base)); + crypto_unregister_shashes(algs, num_algs); } subsys_initcall(crc32c_mod_init); diff --git a/crypto/crct10dif_common.c b/crypto/crct10dif_common.c deleted file mode 100644 index b2fab366f518..000000000000 --- a/crypto/crct10dif_common.c +++ /dev/null @@ -1,82 +0,0 @@ -/* - * Cryptographic API. - * - * T10 Data Integrity Field CRC16 Crypto Transform - * - * Copyright (c) 2007 Oracle Corporation. All rights reserved. - * Written by Martin K. Petersen - * Copyright (C) 2013 Intel Corporation - * Author: Tim Chen - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - * - */ - -#include -#include -#include - -/* Table generated using the following polynomium: - * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1 - * gt: 0x8bb7 - */ -static const __u16 t10_dif_crc_table[256] = { - 0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B, - 0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6, - 0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6, - 0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B, - 0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1, - 0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C, - 0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C, - 0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781, - 0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8, - 0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255, - 0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925, - 0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698, - 0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472, - 0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF, - 0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF, - 0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02, - 0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA, - 0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067, - 0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17, - 0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA, - 0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640, - 0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD, - 0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D, - 0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30, - 0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759, - 0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4, - 0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394, - 0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29, - 0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3, - 0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E, - 0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E, - 0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3 -}; - -__u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len) -{ - unsigned int i; - - for (i = 0 ; i < len ; i++) - crc = (crc << 8) ^ t10_dif_crc_table[((crc >> 8) ^ buffer[i]) & 0xff]; - - return crc; -} -EXPORT_SYMBOL(crc_t10dif_generic); - -MODULE_DESCRIPTION("T10 DIF CRC calculation common code"); -MODULE_LICENSE("GPL"); diff --git a/crypto/crct10dif_generic.c b/crypto/crct10dif_generic.c index e843982073bb..259cb01932cb 100644 --- a/crypto/crct10dif_generic.c +++ b/crypto/crct10dif_generic.c @@ -57,6 +57,15 @@ static int chksum_update(struct shash_desc *desc, const u8 *data, return 0; } +static int chksum_update_arch(struct shash_desc *desc, const u8 *data, + unsigned int length) +{ + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + + ctx->crc = crc_t10dif_update(ctx->crc, data, length); + return 0; +} + static int chksum_final(struct shash_desc *desc, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); @@ -71,6 +80,13 @@ static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out) return 0; } +static int __chksum_finup_arch(__u16 crc, const u8 *data, unsigned int len, + u8 *out) +{ + *(__u16 *)out = crc_t10dif_update(crc, data, len); + return 0; +} + static int chksum_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { @@ -79,37 +95,67 @@ static int chksum_finup(struct shash_desc *desc, const u8 *data, return __chksum_finup(ctx->crc, data, len, out); } +static int chksum_finup_arch(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + + return __chksum_finup_arch(ctx->crc, data, len, out); +} + static int chksum_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) { return __chksum_finup(0, data, length, out); } -static struct shash_alg alg = { - .digestsize = CRC_T10DIF_DIGEST_SIZE, - .init = chksum_init, - .update = chksum_update, - .final = chksum_final, - .finup = chksum_finup, - .digest = chksum_digest, - .descsize = sizeof(struct chksum_desc_ctx), - .base = { - .cra_name = "crct10dif", - .cra_driver_name = "crct10dif-generic", - .cra_priority = 100, - .cra_blocksize = CRC_T10DIF_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -}; +static int chksum_digest_arch(struct shash_desc *desc, const u8 *data, + unsigned int length, u8 *out) +{ + return __chksum_finup_arch(0, data, length, out); +} + +static struct shash_alg algs[] = {{ + .digestsize = CRC_T10DIF_DIGEST_SIZE, + .init = chksum_init, + .update = chksum_update, + .final = chksum_final, + .finup = chksum_finup, + .digest = chksum_digest, + .descsize = sizeof(struct chksum_desc_ctx), + .base.cra_name = "crct10dif", + .base.cra_driver_name = "crct10dif-generic", + .base.cra_priority = 100, + .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE, + .base.cra_module = THIS_MODULE, +}, { + .digestsize = CRC_T10DIF_DIGEST_SIZE, + .init = chksum_init, + .update = chksum_update_arch, + .final = chksum_final, + .finup = chksum_finup_arch, + .digest = chksum_digest_arch, + .descsize = sizeof(struct chksum_desc_ctx), + .base.cra_name = "crct10dif", + .base.cra_driver_name = "crct10dif-" __stringify(ARCH), + .base.cra_priority = 150, + .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE, + .base.cra_module = THIS_MODULE, +}}; + +static int num_algs; static int __init crct10dif_mod_init(void) { - return crypto_register_shash(&alg); + /* register the arch flavor only if it differs from the generic one */ + num_algs = 1 + crc_t10dif_is_optimized(); + + return crypto_register_shashes(algs, num_algs); } static void __exit crct10dif_mod_fini(void) { - crypto_unregister_shash(&alg); + crypto_unregister_shashes(algs, num_algs); } subsys_initcall(crct10dif_mod_init); diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c index e60a0eb628e8..c7c16da5e649 100644 --- a/crypto/crypto_engine.c +++ b/crypto/crypto_engine.c @@ -517,7 +517,7 @@ struct crypto_engine *crypto_engine_alloc_init_and_set(struct device *dev, crypto_init_queue(&engine->queue, qlen); spin_lock_init(&engine->queue_lock); - engine->kworker = kthread_create_worker(0, "%s", engine->name); + engine->kworker = kthread_run_worker(0, "%s", engine->name); if (IS_ERR(engine->kworker)) { dev_err(dev, "failed to create crypto request pump task\n"); return NULL; diff --git a/crypto/fips.c b/crypto/fips.c index 8a784018ebfc..2fa3a9ee61a1 100644 --- a/crypto/fips.c +++ b/crypto/fips.c @@ -12,6 +12,7 @@ #include #include #include +#include #include int fips_enabled; @@ -24,8 +25,7 @@ EXPORT_SYMBOL_GPL(fips_fail_notif_chain); static int fips_enable(char *str) { fips_enabled = !!simple_strtol(str, NULL, 0); - printk(KERN_INFO "fips mode: %s\n", - fips_enabled ? "enabled" : "disabled"); + pr_info("fips mode: %s\n", str_enabled_disabled(fips_enabled)); return 1; } @@ -41,7 +41,7 @@ __setup("fips=", fips_enable); static char fips_name[] = FIPS_MODULE_NAME; static char fips_version[] = FIPS_MODULE_VERSION; -static struct ctl_table crypto_sysctl_table[] = { +static const struct ctl_table crypto_sysctl_table[] = { { .procname = "fips_enabled", .data = &fips_enabled, diff --git a/crypto/keywrap.c b/crypto/keywrap.c deleted file mode 100644 index 385ffdfd5a9b..000000000000 --- a/crypto/keywrap.c +++ /dev/null @@ -1,320 +0,0 @@ -/* - * Key Wrapping: RFC3394 / NIST SP800-38F - * - * Copyright (C) 2015, Stephan Mueller - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, and the entire permission notice in its entirety, - * including the disclaimer of warranties. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. The name of the author may not be used to endorse or promote - * products derived from this software without specific prior - * written permission. - * - * ALTERNATIVELY, this product may be distributed under the terms of - * the GNU General Public License, in which case the provisions of the GPL2 - * are required INSTEAD OF the above restrictions. (This clause is - * necessary due to a potential bad interaction between the GPL and - * the restrictions contained in a BSD-style copyright.) - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES - * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF - * WHICH ARE HEREBY DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT - * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE - * USE OF THIS SOFTWARE, EVEN IF NOT ADVISED OF THE POSSIBILITY OF SUCH - * DAMAGE. - */ - -/* - * Note for using key wrapping: - * - * * The result of the encryption operation is the ciphertext starting - * with the 2nd semiblock. The first semiblock is provided as the IV. - * The IV used to start the encryption operation is the default IV. - * - * * The input for the decryption is the first semiblock handed in as an - * IV. The ciphertext is the data starting with the 2nd semiblock. The - * return code of the decryption operation will be EBADMSG in case an - * integrity error occurs. - * - * To obtain the full result of an encryption as expected by SP800-38F, the - * caller must allocate a buffer of plaintext + 8 bytes: - * - * unsigned int datalen = ptlen + crypto_skcipher_ivsize(tfm); - * u8 data[datalen]; - * u8 *iv = data; - * u8 *pt = data + crypto_skcipher_ivsize(tfm); - * - * sg_init_one(&sg, pt, ptlen); - * skcipher_request_set_crypt(req, &sg, &sg, ptlen, iv); - * - * ==> After encryption, data now contains full KW result as per SP800-38F. - * - * In case of decryption, ciphertext now already has the expected length - * and must be segmented appropriately: - * - * unsigned int datalen = CTLEN; - * u8 data[datalen]; - * - * u8 *iv = data; - * u8 *ct = data + crypto_skcipher_ivsize(tfm); - * unsigned int ctlen = datalen - crypto_skcipher_ivsize(tfm); - * sg_init_one(&sg, ct, ctlen); - * skcipher_request_set_crypt(req, &sg, &sg, ctlen, iv); - * - * ==> After decryption (which hopefully does not return EBADMSG), the ct - * pointer now points to the plaintext of size ctlen. - * - * Note 2: KWP is not implemented as this would defy in-place operation. - * If somebody wants to wrap non-aligned data, he should simply pad - * the input with zeros to fill it up to the 8 byte boundary. - */ - -#include -#include -#include -#include -#include -#include - -struct crypto_kw_block { -#define SEMIBSIZE 8 - __be64 A; - __be64 R; -}; - -/* - * Fast forward the SGL to the "end" length minus SEMIBSIZE. - * The start in the SGL defined by the fast-forward is returned with - * the walk variable - */ -static void crypto_kw_scatterlist_ff(struct scatter_walk *walk, - struct scatterlist *sg, - unsigned int end) -{ - unsigned int skip = 0; - - /* The caller should only operate on full SEMIBLOCKs. */ - BUG_ON(end < SEMIBSIZE); - - skip = end - SEMIBSIZE; - while (sg) { - if (sg->length > skip) { - scatterwalk_start(walk, sg); - scatterwalk_advance(walk, skip); - break; - } - - skip -= sg->length; - sg = sg_next(sg); - } -} - -static int crypto_kw_decrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct crypto_cipher *cipher = skcipher_cipher_simple(tfm); - struct crypto_kw_block block; - struct scatterlist *src, *dst; - u64 t = 6 * ((req->cryptlen) >> 3); - unsigned int i; - int ret = 0; - - /* - * Require at least 2 semiblocks (note, the 3rd semiblock that is - * required by SP800-38F is the IV. - */ - if (req->cryptlen < (2 * SEMIBSIZE) || req->cryptlen % SEMIBSIZE) - return -EINVAL; - - /* Place the IV into block A */ - memcpy(&block.A, req->iv, SEMIBSIZE); - - /* - * src scatterlist is read-only. dst scatterlist is r/w. During the - * first loop, src points to req->src and dst to req->dst. For any - * subsequent round, the code operates on req->dst only. - */ - src = req->src; - dst = req->dst; - - for (i = 0; i < 6; i++) { - struct scatter_walk src_walk, dst_walk; - unsigned int nbytes = req->cryptlen; - - while (nbytes) { - /* move pointer by nbytes in the SGL */ - crypto_kw_scatterlist_ff(&src_walk, src, nbytes); - /* get the source block */ - scatterwalk_copychunks(&block.R, &src_walk, SEMIBSIZE, - false); - - /* perform KW operation: modify IV with counter */ - block.A ^= cpu_to_be64(t); - t--; - /* perform KW operation: decrypt block */ - crypto_cipher_decrypt_one(cipher, (u8 *)&block, - (u8 *)&block); - - /* move pointer by nbytes in the SGL */ - crypto_kw_scatterlist_ff(&dst_walk, dst, nbytes); - /* Copy block->R into place */ - scatterwalk_copychunks(&block.R, &dst_walk, SEMIBSIZE, - true); - - nbytes -= SEMIBSIZE; - } - - /* we now start to operate on the dst SGL only */ - src = req->dst; - dst = req->dst; - } - - /* Perform authentication check */ - if (block.A != cpu_to_be64(0xa6a6a6a6a6a6a6a6ULL)) - ret = -EBADMSG; - - memzero_explicit(&block, sizeof(struct crypto_kw_block)); - - return ret; -} - -static int crypto_kw_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct crypto_cipher *cipher = skcipher_cipher_simple(tfm); - struct crypto_kw_block block; - struct scatterlist *src, *dst; - u64 t = 1; - unsigned int i; - - /* - * Require at least 2 semiblocks (note, the 3rd semiblock that is - * required by SP800-38F is the IV that occupies the first semiblock. - * This means that the dst memory must be one semiblock larger than src. - * Also ensure that the given data is aligned to semiblock. - */ - if (req->cryptlen < (2 * SEMIBSIZE) || req->cryptlen % SEMIBSIZE) - return -EINVAL; - - /* - * Place the predefined IV into block A -- for encrypt, the caller - * does not need to provide an IV, but he needs to fetch the final IV. - */ - block.A = cpu_to_be64(0xa6a6a6a6a6a6a6a6ULL); - - /* - * src scatterlist is read-only. dst scatterlist is r/w. During the - * first loop, src points to req->src and dst to req->dst. For any - * subsequent round, the code operates on req->dst only. - */ - src = req->src; - dst = req->dst; - - for (i = 0; i < 6; i++) { - struct scatter_walk src_walk, dst_walk; - unsigned int nbytes = req->cryptlen; - - scatterwalk_start(&src_walk, src); - scatterwalk_start(&dst_walk, dst); - - while (nbytes) { - /* get the source block */ - scatterwalk_copychunks(&block.R, &src_walk, SEMIBSIZE, - false); - - /* perform KW operation: encrypt block */ - crypto_cipher_encrypt_one(cipher, (u8 *)&block, - (u8 *)&block); - /* perform KW operation: modify IV with counter */ - block.A ^= cpu_to_be64(t); - t++; - - /* Copy block->R into place */ - scatterwalk_copychunks(&block.R, &dst_walk, SEMIBSIZE, - true); - - nbytes -= SEMIBSIZE; - } - - /* we now start to operate on the dst SGL only */ - src = req->dst; - dst = req->dst; - } - - /* establish the IV for the caller to pick up */ - memcpy(req->iv, &block.A, SEMIBSIZE); - - memzero_explicit(&block, sizeof(struct crypto_kw_block)); - - return 0; -} - -static int crypto_kw_create(struct crypto_template *tmpl, struct rtattr **tb) -{ - struct skcipher_instance *inst; - struct crypto_alg *alg; - int err; - - inst = skcipher_alloc_instance_simple(tmpl, tb); - if (IS_ERR(inst)) - return PTR_ERR(inst); - - alg = skcipher_ialg_simple(inst); - - err = -EINVAL; - /* Section 5.1 requirement for KW */ - if (alg->cra_blocksize != sizeof(struct crypto_kw_block)) - goto out_free_inst; - - inst->alg.base.cra_blocksize = SEMIBSIZE; - inst->alg.base.cra_alignmask = 0; - inst->alg.ivsize = SEMIBSIZE; - - inst->alg.encrypt = crypto_kw_encrypt; - inst->alg.decrypt = crypto_kw_decrypt; - - err = skcipher_register_instance(tmpl, inst); - if (err) { -out_free_inst: - inst->free(inst); - } - - return err; -} - -static struct crypto_template crypto_kw_tmpl = { - .name = "kw", - .create = crypto_kw_create, - .module = THIS_MODULE, -}; - -static int __init crypto_kw_init(void) -{ - return crypto_register_template(&crypto_kw_tmpl); -} - -static void __exit crypto_kw_exit(void) -{ - crypto_unregister_template(&crypto_kw_tmpl); -} - -subsys_initcall(crypto_kw_init); -module_exit(crypto_kw_exit); - -MODULE_LICENSE("Dual BSD/GPL"); -MODULE_AUTHOR("Stephan Mueller "); -MODULE_DESCRIPTION("Key Wrapping (RFC3394 / NIST SP800-38F)"); -MODULE_ALIAS_CRYPTO("kw"); -MODULE_IMPORT_NS("CRYPTO_INTERNAL"); diff --git a/crypto/khazad.c b/crypto/khazad.c index 70cafe73f974..7ad338ca2c18 100644 --- a/crypto/khazad.c +++ b/crypto/khazad.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #define KHAZAD_KEY_SIZE 16 @@ -757,14 +757,12 @@ static int khazad_setkey(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct khazad_ctx *ctx = crypto_tfm_ctx(tfm); - const __be32 *key = (const __be32 *)in_key; int r; const u64 *S = T7; u64 K2, K1; - /* key is supposed to be 32-bit aligned */ - K2 = ((u64)be32_to_cpu(key[0]) << 32) | be32_to_cpu(key[1]); - K1 = ((u64)be32_to_cpu(key[2]) << 32) | be32_to_cpu(key[3]); + K2 = get_unaligned_be64(&in_key[0]); + K1 = get_unaligned_be64(&in_key[8]); /* setup the encrypt key */ for (r = 0; r <= KHAZAD_ROUNDS; r++) { @@ -800,14 +798,12 @@ static int khazad_setkey(struct crypto_tfm *tfm, const u8 *in_key, } static void khazad_crypt(const u64 roundKey[KHAZAD_ROUNDS + 1], - u8 *ciphertext, const u8 *plaintext) + u8 *dst, const u8 *src) { - const __be64 *src = (const __be64 *)plaintext; - __be64 *dst = (__be64 *)ciphertext; int r; u64 state; - state = be64_to_cpu(*src) ^ roundKey[0]; + state = get_unaligned_be64(src) ^ roundKey[0]; for (r = 1; r < KHAZAD_ROUNDS; r++) { state = T0[(int)(state >> 56) ] ^ @@ -831,7 +827,7 @@ static void khazad_crypt(const u64 roundKey[KHAZAD_ROUNDS + 1], (T7[(int)(state ) & 0xff] & 0x00000000000000ffULL) ^ roundKey[KHAZAD_ROUNDS]; - *dst = cpu_to_be64(state); + put_unaligned_be64(state, dst); } static void khazad_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) @@ -852,7 +848,6 @@ static struct crypto_alg khazad_alg = { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = KHAZAD_BLOCK_SIZE, .cra_ctxsize = sizeof (struct khazad_ctx), - .cra_alignmask = 7, .cra_module = THIS_MODULE, .cra_u = { .cipher = { .cia_min_keysize = KHAZAD_KEY_SIZE, diff --git a/crypto/proc.c b/crypto/proc.c index 56c7c78df297..522b27d90d29 100644 --- a/crypto/proc.c +++ b/crypto/proc.c @@ -47,13 +47,10 @@ static int c_show(struct seq_file *m, void *p) (alg->cra_flags & CRYPTO_ALG_TESTED) ? "passed" : "unknown"); seq_printf(m, "internal : %s\n", - (alg->cra_flags & CRYPTO_ALG_INTERNAL) ? - "yes" : "no"); - if (fips_enabled) { + str_yes_no(alg->cra_flags & CRYPTO_ALG_INTERNAL)); + if (fips_enabled) seq_printf(m, "fips : %s\n", - (alg->cra_flags & CRYPTO_ALG_FIPS_INTERNAL) ? - "no" : "yes"); - } + str_no_yes(alg->cra_flags & CRYPTO_ALG_FIPS_INTERNAL)); if (alg->cra_flags & CRYPTO_ALG_LARVAL) { seq_printf(m, "type : larval\n"); diff --git a/crypto/seed.c b/crypto/seed.c index d0506ade2a5f..d05d8ed909fa 100644 --- a/crypto/seed.c +++ b/crypto/seed.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #define SEED_NUM_KCONSTANTS 16 #define SEED_KEY_SIZE 16 @@ -329,13 +329,12 @@ static int seed_set_key(struct crypto_tfm *tfm, const u8 *in_key, { struct seed_ctx *ctx = crypto_tfm_ctx(tfm); u32 *keyout = ctx->keysched; - const __be32 *key = (const __be32 *)in_key; u32 i, t0, t1, x1, x2, x3, x4; - x1 = be32_to_cpu(key[0]); - x2 = be32_to_cpu(key[1]); - x3 = be32_to_cpu(key[2]); - x4 = be32_to_cpu(key[3]); + x1 = get_unaligned_be32(&in_key[0]); + x2 = get_unaligned_be32(&in_key[4]); + x3 = get_unaligned_be32(&in_key[8]); + x4 = get_unaligned_be32(&in_key[12]); for (i = 0; i < SEED_NUM_KCONSTANTS; i++) { t0 = x1 + x3 - KC[i]; @@ -364,15 +363,13 @@ static int seed_set_key(struct crypto_tfm *tfm, const u8 *in_key, static void seed_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { const struct seed_ctx *ctx = crypto_tfm_ctx(tfm); - const __be32 *src = (const __be32 *)in; - __be32 *dst = (__be32 *)out; u32 x1, x2, x3, x4, t0, t1; const u32 *ks = ctx->keysched; - x1 = be32_to_cpu(src[0]); - x2 = be32_to_cpu(src[1]); - x3 = be32_to_cpu(src[2]); - x4 = be32_to_cpu(src[3]); + x1 = get_unaligned_be32(&in[0]); + x2 = get_unaligned_be32(&in[4]); + x3 = get_unaligned_be32(&in[8]); + x4 = get_unaligned_be32(&in[12]); OP(x1, x2, x3, x4, 0); OP(x3, x4, x1, x2, 2); @@ -391,10 +388,10 @@ static void seed_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) OP(x1, x2, x3, x4, 28); OP(x3, x4, x1, x2, 30); - dst[0] = cpu_to_be32(x3); - dst[1] = cpu_to_be32(x4); - dst[2] = cpu_to_be32(x1); - dst[3] = cpu_to_be32(x2); + put_unaligned_be32(x3, &out[0]); + put_unaligned_be32(x4, &out[4]); + put_unaligned_be32(x1, &out[8]); + put_unaligned_be32(x2, &out[12]); } /* decrypt a block of text */ @@ -402,15 +399,13 @@ static void seed_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) static void seed_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { const struct seed_ctx *ctx = crypto_tfm_ctx(tfm); - const __be32 *src = (const __be32 *)in; - __be32 *dst = (__be32 *)out; u32 x1, x2, x3, x4, t0, t1; const u32 *ks = ctx->keysched; - x1 = be32_to_cpu(src[0]); - x2 = be32_to_cpu(src[1]); - x3 = be32_to_cpu(src[2]); - x4 = be32_to_cpu(src[3]); + x1 = get_unaligned_be32(&in[0]); + x2 = get_unaligned_be32(&in[4]); + x3 = get_unaligned_be32(&in[8]); + x4 = get_unaligned_be32(&in[12]); OP(x1, x2, x3, x4, 30); OP(x3, x4, x1, x2, 28); @@ -429,10 +424,10 @@ static void seed_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) OP(x1, x2, x3, x4, 2); OP(x3, x4, x1, x2, 0); - dst[0] = cpu_to_be32(x3); - dst[1] = cpu_to_be32(x4); - dst[2] = cpu_to_be32(x1); - dst[3] = cpu_to_be32(x2); + put_unaligned_be32(x3, &out[0]); + put_unaligned_be32(x4, &out[4]); + put_unaligned_be32(x1, &out[8]); + put_unaligned_be32(x2, &out[12]); } @@ -443,7 +438,6 @@ static struct crypto_alg seed_alg = { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = SEED_BLOCK_SIZE, .cra_ctxsize = sizeof(struct seed_ctx), - .cra_alignmask = 3, .cra_module = THIS_MODULE, .cra_u = { .cipher = { diff --git a/crypto/sig.c b/crypto/sig.c index 5e1f1f739da2..dfc7cae90802 100644 --- a/crypto/sig.c +++ b/crypto/sig.c @@ -15,8 +15,6 @@ #include "internal.h" -#define CRYPTO_ALG_TYPE_SIG_MASK 0x0000000e - static void crypto_sig_exit_tfm(struct crypto_tfm *tfm) { struct crypto_sig *sig = __crypto_sig_tfm(tfm); @@ -73,7 +71,7 @@ static const struct crypto_type crypto_sig_type = { .report = crypto_sig_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, - .maskset = CRYPTO_ALG_TYPE_SIG_MASK, + .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_SIG, .tfmsize = offsetof(struct crypto_sig, base), }; diff --git a/crypto/skcipher.c b/crypto/skcipher.c index f74e4d0d87a2..a9eb2dcf2898 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -29,19 +28,10 @@ #define CRYPTO_ALG_TYPE_SKCIPHER_MASK 0x0000000e enum { - SKCIPHER_WALK_PHYS = 1 << 0, - SKCIPHER_WALK_SLOW = 1 << 1, - SKCIPHER_WALK_COPY = 1 << 2, - SKCIPHER_WALK_DIFF = 1 << 3, - SKCIPHER_WALK_SLEEP = 1 << 4, -}; - -struct skcipher_walk_buffer { - struct list_head entry; - struct scatter_walk dst; - unsigned int len; - u8 *data; - u8 buffer[]; + SKCIPHER_WALK_SLOW = 1 << 0, + SKCIPHER_WALK_COPY = 1 << 1, + SKCIPHER_WALK_DIFF = 1 << 2, + SKCIPHER_WALK_SLEEP = 1 << 3, }; static const struct crypto_type crypto_skcipher_type; @@ -73,16 +63,6 @@ static inline gfp_t skcipher_walk_gfp(struct skcipher_walk *walk) return walk->flags & SKCIPHER_WALK_SLEEP ? GFP_KERNEL : GFP_ATOMIC; } -/* Get a spot of the specified length that does not straddle a page. - * The caller needs to ensure that there is enough space for this operation. - */ -static inline u8 *skcipher_get_spot(u8 *start, unsigned int len) -{ - u8 *end_page = (u8 *)(((unsigned long)(start + len - 1)) & PAGE_MASK); - - return max(start, end_page); -} - static inline struct skcipher_alg *__crypto_skcipher_alg( struct crypto_alg *alg) { @@ -91,30 +71,44 @@ static inline struct skcipher_alg *__crypto_skcipher_alg( static int skcipher_done_slow(struct skcipher_walk *walk, unsigned int bsize) { - u8 *addr; + u8 *addr = PTR_ALIGN(walk->buffer, walk->alignmask + 1); - addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1); - addr = skcipher_get_spot(addr, bsize); - scatterwalk_copychunks(addr, &walk->out, bsize, - (walk->flags & SKCIPHER_WALK_PHYS) ? 2 : 1); + scatterwalk_copychunks(addr, &walk->out, bsize, 1); return 0; } -int skcipher_walk_done(struct skcipher_walk *walk, int err) +/** + * skcipher_walk_done() - finish one step of a skcipher_walk + * @walk: the skcipher_walk + * @res: number of bytes *not* processed (>= 0) from walk->nbytes, + * or a -errno value to terminate the walk due to an error + * + * This function cleans up after one step of walking through the source and + * destination scatterlists, and advances to the next step if applicable. + * walk->nbytes is set to the number of bytes available in the next step, + * walk->total is set to the new total number of bytes remaining, and + * walk->{src,dst}.virt.addr is set to the next pair of data pointers. If there + * is no more data, or if an error occurred (i.e. -errno return), then + * walk->nbytes and walk->total are set to 0 and all resources owned by the + * skcipher_walk are freed. + * + * Return: 0 or a -errno value. If @res was a -errno value then it will be + * returned, but other errors may occur too. + */ +int skcipher_walk_done(struct skcipher_walk *walk, int res) { - unsigned int n = walk->nbytes; - unsigned int nbytes = 0; + unsigned int n = walk->nbytes; /* num bytes processed this step */ + unsigned int total = 0; /* new total remaining */ if (!n) goto finish; - if (likely(err >= 0)) { - n -= err; - nbytes = walk->total - n; + if (likely(res >= 0)) { + n -= res; /* subtract num bytes *not* processed */ + total = walk->total - n; } - if (likely(!(walk->flags & (SKCIPHER_WALK_PHYS | - SKCIPHER_WALK_SLOW | + if (likely(!(walk->flags & (SKCIPHER_WALK_SLOW | SKCIPHER_WALK_COPY | SKCIPHER_WALK_DIFF)))) { unmap_src: @@ -126,34 +120,36 @@ unmap_src: skcipher_map_dst(walk); memcpy(walk->dst.virt.addr, walk->page, n); skcipher_unmap_dst(walk); - } else if (unlikely(walk->flags & SKCIPHER_WALK_SLOW)) { - if (err > 0) { + } else { /* SKCIPHER_WALK_SLOW */ + if (res > 0) { /* * Didn't process all bytes. Either the algorithm is * broken, or this was the last step and it turned out * the message wasn't evenly divisible into blocks but * the algorithm requires it. */ - err = -EINVAL; - nbytes = 0; + res = -EINVAL; + total = 0; } else n = skcipher_done_slow(walk, n); } - if (err > 0) - err = 0; + if (res > 0) + res = 0; - walk->total = nbytes; + walk->total = total; walk->nbytes = 0; scatterwalk_advance(&walk->in, n); scatterwalk_advance(&walk->out, n); - scatterwalk_done(&walk->in, 0, nbytes); - scatterwalk_done(&walk->out, 1, nbytes); + scatterwalk_done(&walk->in, 0, total); + scatterwalk_done(&walk->out, 1, total); - if (nbytes) { - crypto_yield(walk->flags & SKCIPHER_WALK_SLEEP ? - CRYPTO_TFM_REQ_MAY_SLEEP : 0); + if (total) { + if (walk->flags & SKCIPHER_WALK_SLEEP) + cond_resched(); + walk->flags &= ~(SKCIPHER_WALK_SLOW | SKCIPHER_WALK_COPY | + SKCIPHER_WALK_DIFF); return skcipher_walk_next(walk); } @@ -162,9 +158,6 @@ finish: if (!((unsigned long)walk->buffer | (unsigned long)walk->page)) goto out; - if (walk->flags & SKCIPHER_WALK_PHYS) - goto out; - if (walk->iv != walk->oiv) memcpy(walk->oiv, walk->iv, walk->ivsize); if (walk->buffer != walk->page) @@ -173,104 +166,29 @@ finish: free_page((unsigned long)walk->page); out: - return err; + return res; } EXPORT_SYMBOL_GPL(skcipher_walk_done); -void skcipher_walk_complete(struct skcipher_walk *walk, int err) -{ - struct skcipher_walk_buffer *p, *tmp; - - list_for_each_entry_safe(p, tmp, &walk->buffers, entry) { - u8 *data; - - if (err) - goto done; - - data = p->data; - if (!data) { - data = PTR_ALIGN(&p->buffer[0], walk->alignmask + 1); - data = skcipher_get_spot(data, walk->stride); - } - - scatterwalk_copychunks(data, &p->dst, p->len, 1); - - if (offset_in_page(p->data) + p->len + walk->stride > - PAGE_SIZE) - free_page((unsigned long)p->data); - -done: - list_del(&p->entry); - kfree(p); - } - - if (!err && walk->iv != walk->oiv) - memcpy(walk->oiv, walk->iv, walk->ivsize); - if (walk->buffer != walk->page) - kfree(walk->buffer); - if (walk->page) - free_page((unsigned long)walk->page); -} -EXPORT_SYMBOL_GPL(skcipher_walk_complete); - -static void skcipher_queue_write(struct skcipher_walk *walk, - struct skcipher_walk_buffer *p) -{ - p->dst = walk->out; - list_add_tail(&p->entry, &walk->buffers); -} - static int skcipher_next_slow(struct skcipher_walk *walk, unsigned int bsize) { - bool phys = walk->flags & SKCIPHER_WALK_PHYS; unsigned alignmask = walk->alignmask; - struct skcipher_walk_buffer *p; - unsigned a; unsigned n; u8 *buffer; - void *v; - if (!phys) { - if (!walk->buffer) - walk->buffer = walk->page; - buffer = walk->buffer; - if (buffer) - goto ok; + if (!walk->buffer) + walk->buffer = walk->page; + buffer = walk->buffer; + if (!buffer) { + /* Min size for a buffer of bsize bytes aligned to alignmask */ + n = bsize + (alignmask & ~(crypto_tfm_ctx_alignment() - 1)); + + buffer = kzalloc(n, skcipher_walk_gfp(walk)); + if (!buffer) + return skcipher_walk_done(walk, -ENOMEM); + walk->buffer = buffer; } - - /* Start with the minimum alignment of kmalloc. */ - a = crypto_tfm_ctx_alignment() - 1; - n = bsize; - - if (phys) { - /* Calculate the minimum alignment of p->buffer. */ - a &= (sizeof(*p) ^ (sizeof(*p) - 1)) >> 1; - n += sizeof(*p); - } - - /* Minimum size to align p->buffer by alignmask. */ - n += alignmask & ~a; - - /* Minimum size to ensure p->buffer does not straddle a page. */ - n += (bsize - 1) & ~(alignmask | a); - - v = kzalloc(n, skcipher_walk_gfp(walk)); - if (!v) - return skcipher_walk_done(walk, -ENOMEM); - - if (phys) { - p = v; - p->len = bsize; - skcipher_queue_write(walk, p); - buffer = p->buffer; - } else { - walk->buffer = v; - buffer = v; - } - -ok: walk->dst.virt.addr = PTR_ALIGN(buffer, alignmask + 1); - walk->dst.virt.addr = skcipher_get_spot(walk->dst.virt.addr, bsize); walk->src.virt.addr = walk->dst.virt.addr; scatterwalk_copychunks(walk->src.virt.addr, &walk->in, bsize, 0); @@ -283,7 +201,6 @@ ok: static int skcipher_next_copy(struct skcipher_walk *walk) { - struct skcipher_walk_buffer *p; u8 *tmp = walk->page; skcipher_map_src(walk); @@ -292,24 +209,6 @@ static int skcipher_next_copy(struct skcipher_walk *walk) walk->src.virt.addr = tmp; walk->dst.virt.addr = tmp; - - if (!(walk->flags & SKCIPHER_WALK_PHYS)) - return 0; - - p = kmalloc(sizeof(*p), skcipher_walk_gfp(walk)); - if (!p) - return -ENOMEM; - - p->data = walk->page; - p->len = walk->nbytes; - skcipher_queue_write(walk, p); - - if (offset_in_page(walk->page) + walk->nbytes + walk->stride > - PAGE_SIZE) - walk->page = NULL; - else - walk->page += walk->nbytes; - return 0; } @@ -317,16 +216,10 @@ static int skcipher_next_fast(struct skcipher_walk *walk) { unsigned long diff; - walk->src.phys.page = scatterwalk_page(&walk->in); - walk->src.phys.offset = offset_in_page(walk->in.offset); - walk->dst.phys.page = scatterwalk_page(&walk->out); - walk->dst.phys.offset = offset_in_page(walk->out.offset); - - if (walk->flags & SKCIPHER_WALK_PHYS) - return 0; - - diff = walk->src.phys.offset - walk->dst.phys.offset; - diff |= walk->src.virt.page - walk->dst.virt.page; + diff = offset_in_page(walk->in.offset) - + offset_in_page(walk->out.offset); + diff |= (u8 *)scatterwalk_page(&walk->in) - + (u8 *)scatterwalk_page(&walk->out); skcipher_map_src(walk); walk->dst.virt.addr = walk->src.virt.addr; @@ -343,10 +236,6 @@ static int skcipher_walk_next(struct skcipher_walk *walk) { unsigned int bsize; unsigned int n; - int err; - - walk->flags &= ~(SKCIPHER_WALK_SLOW | SKCIPHER_WALK_COPY | - SKCIPHER_WALK_DIFF); n = walk->total; bsize = min(walk->stride, max(n, walk->blocksize)); @@ -358,9 +247,9 @@ static int skcipher_walk_next(struct skcipher_walk *walk) return skcipher_walk_done(walk, -EINVAL); slow_path: - err = skcipher_next_slow(walk, bsize); - goto set_phys_lowmem; + return skcipher_next_slow(walk, bsize); } + walk->nbytes = n; if (unlikely((walk->in.offset | walk->out.offset) & walk->alignmask)) { if (!walk->page) { @@ -370,58 +259,30 @@ slow_path: if (!walk->page) goto slow_path; } - - walk->nbytes = min_t(unsigned, n, - PAGE_SIZE - offset_in_page(walk->page)); walk->flags |= SKCIPHER_WALK_COPY; - err = skcipher_next_copy(walk); - goto set_phys_lowmem; + return skcipher_next_copy(walk); } - walk->nbytes = n; - return skcipher_next_fast(walk); - -set_phys_lowmem: - if (!err && (walk->flags & SKCIPHER_WALK_PHYS)) { - walk->src.phys.page = virt_to_page(walk->src.virt.addr); - walk->dst.phys.page = virt_to_page(walk->dst.virt.addr); - walk->src.phys.offset &= PAGE_SIZE - 1; - walk->dst.phys.offset &= PAGE_SIZE - 1; - } - return err; } static int skcipher_copy_iv(struct skcipher_walk *walk) { - unsigned a = crypto_tfm_ctx_alignment() - 1; unsigned alignmask = walk->alignmask; unsigned ivsize = walk->ivsize; - unsigned bs = walk->stride; - unsigned aligned_bs; + unsigned aligned_stride = ALIGN(walk->stride, alignmask + 1); unsigned size; u8 *iv; - aligned_bs = ALIGN(bs, alignmask + 1); - - /* Minimum size to align buffer by alignmask. */ - size = alignmask & ~a; - - if (walk->flags & SKCIPHER_WALK_PHYS) - size += ivsize; - else { - size += aligned_bs + ivsize; - - /* Minimum size to ensure buffer does not straddle a page. */ - size += (bs - 1) & ~(alignmask | a); - } + /* Min size for a buffer of stride + ivsize, aligned to alignmask */ + size = aligned_stride + ivsize + + (alignmask & ~(crypto_tfm_ctx_alignment() - 1)); walk->buffer = kmalloc(size, skcipher_walk_gfp(walk)); if (!walk->buffer) return -ENOMEM; - iv = PTR_ALIGN(walk->buffer, alignmask + 1); - iv = skcipher_get_spot(iv, bs) + aligned_bs; + iv = PTR_ALIGN(walk->buffer, alignmask + 1) + aligned_stride; walk->iv = memcpy(iv, walk->iv, walk->ivsize); return 0; @@ -444,16 +305,22 @@ static int skcipher_walk_first(struct skcipher_walk *walk) return skcipher_walk_next(walk); } -static int skcipher_walk_skcipher(struct skcipher_walk *walk, - struct skcipher_request *req) +int skcipher_walk_virt(struct skcipher_walk *walk, + struct skcipher_request *req, bool atomic) { - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct skcipher_alg *alg = crypto_skcipher_alg(tfm); + const struct skcipher_alg *alg = + crypto_skcipher_alg(crypto_skcipher_reqtfm(req)); + + might_sleep_if(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP); walk->total = req->cryptlen; walk->nbytes = 0; walk->iv = req->iv; walk->oiv = req->iv; + if ((req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) && !atomic) + walk->flags = SKCIPHER_WALK_SLEEP; + else + walk->flags = 0; if (unlikely(!walk->total)) return 0; @@ -461,13 +328,14 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk, scatterwalk_start(&walk->in, req->src); scatterwalk_start(&walk->out, req->dst); - walk->flags &= ~SKCIPHER_WALK_SLEEP; - walk->flags |= req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? - SKCIPHER_WALK_SLEEP : 0; - - walk->blocksize = crypto_skcipher_blocksize(tfm); - walk->ivsize = crypto_skcipher_ivsize(tfm); - walk->alignmask = crypto_skcipher_alignmask(tfm); + /* + * Accessing 'alg' directly generates better code than using the + * crypto_skcipher_blocksize() and similar helper functions here, as it + * prevents the algorithm pointer from being repeatedly reloaded. + */ + walk->blocksize = alg->base.cra_blocksize; + walk->ivsize = alg->co.ivsize; + walk->alignmask = alg->base.cra_alignmask; if (alg->co.base.cra_type != &crypto_skcipher_type) walk->stride = alg->co.chunksize; @@ -476,50 +344,24 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk, return skcipher_walk_first(walk); } - -int skcipher_walk_virt(struct skcipher_walk *walk, - struct skcipher_request *req, bool atomic) -{ - int err; - - might_sleep_if(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP); - - walk->flags &= ~SKCIPHER_WALK_PHYS; - - err = skcipher_walk_skcipher(walk, req); - - walk->flags &= atomic ? ~SKCIPHER_WALK_SLEEP : ~0; - - return err; -} EXPORT_SYMBOL_GPL(skcipher_walk_virt); -int skcipher_walk_async(struct skcipher_walk *walk, - struct skcipher_request *req) -{ - walk->flags |= SKCIPHER_WALK_PHYS; - - INIT_LIST_HEAD(&walk->buffers); - - return skcipher_walk_skcipher(walk, req); -} -EXPORT_SYMBOL_GPL(skcipher_walk_async); - static int skcipher_walk_aead_common(struct skcipher_walk *walk, struct aead_request *req, bool atomic) { - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - int err; + const struct aead_alg *alg = crypto_aead_alg(crypto_aead_reqtfm(req)); walk->nbytes = 0; walk->iv = req->iv; walk->oiv = req->iv; + if ((req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) && !atomic) + walk->flags = SKCIPHER_WALK_SLEEP; + else + walk->flags = 0; if (unlikely(!walk->total)) return 0; - walk->flags &= ~SKCIPHER_WALK_PHYS; - scatterwalk_start(&walk->in, req->src); scatterwalk_start(&walk->out, req->dst); @@ -529,22 +371,17 @@ static int skcipher_walk_aead_common(struct skcipher_walk *walk, scatterwalk_done(&walk->in, 0, walk->total); scatterwalk_done(&walk->out, 0, walk->total); - if (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) - walk->flags |= SKCIPHER_WALK_SLEEP; - else - walk->flags &= ~SKCIPHER_WALK_SLEEP; + /* + * Accessing 'alg' directly generates better code than using the + * crypto_aead_blocksize() and similar helper functions here, as it + * prevents the algorithm pointer from being repeatedly reloaded. + */ + walk->blocksize = alg->base.cra_blocksize; + walk->stride = alg->chunksize; + walk->ivsize = alg->ivsize; + walk->alignmask = alg->base.cra_alignmask; - walk->blocksize = crypto_aead_blocksize(tfm); - walk->stride = crypto_aead_chunksize(tfm); - walk->ivsize = crypto_aead_ivsize(tfm); - walk->alignmask = crypto_aead_alignmask(tfm); - - err = skcipher_walk_first(walk); - - if (atomic) - walk->flags &= ~SKCIPHER_WALK_SLEEP; - - return err; + return skcipher_walk_first(walk); } int skcipher_walk_aead_encrypt(struct skcipher_walk *walk, diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index e9e7dceb606e..e1a74cb2cfbe 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -1738,10 +1738,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) ret = min(ret, tcrypt_test("hmac(rmd160)")); break; - case 109: - ret = min(ret, tcrypt_test("vmac64(aes)")); - break; - case 111: ret = min(ret, tcrypt_test("hmac(sha3-224)")); break; diff --git a/crypto/tea.c b/crypto/tea.c index 896f863f3067..b315da8c89eb 100644 --- a/crypto/tea.c +++ b/crypto/tea.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #define TEA_KEY_SIZE 16 @@ -43,12 +43,11 @@ static int tea_setkey(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct tea_ctx *ctx = crypto_tfm_ctx(tfm); - const __le32 *key = (const __le32 *)in_key; - ctx->KEY[0] = le32_to_cpu(key[0]); - ctx->KEY[1] = le32_to_cpu(key[1]); - ctx->KEY[2] = le32_to_cpu(key[2]); - ctx->KEY[3] = le32_to_cpu(key[3]); + ctx->KEY[0] = get_unaligned_le32(&in_key[0]); + ctx->KEY[1] = get_unaligned_le32(&in_key[4]); + ctx->KEY[2] = get_unaligned_le32(&in_key[8]); + ctx->KEY[3] = get_unaligned_le32(&in_key[12]); return 0; @@ -59,11 +58,9 @@ static void tea_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) u32 y, z, n, sum = 0; u32 k0, k1, k2, k3; struct tea_ctx *ctx = crypto_tfm_ctx(tfm); - const __le32 *in = (const __le32 *)src; - __le32 *out = (__le32 *)dst; - y = le32_to_cpu(in[0]); - z = le32_to_cpu(in[1]); + y = get_unaligned_le32(&src[0]); + z = get_unaligned_le32(&src[4]); k0 = ctx->KEY[0]; k1 = ctx->KEY[1]; @@ -78,8 +75,8 @@ static void tea_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) z += ((y << 4) + k2) ^ (y + sum) ^ ((y >> 5) + k3); } - out[0] = cpu_to_le32(y); - out[1] = cpu_to_le32(z); + put_unaligned_le32(y, &dst[0]); + put_unaligned_le32(z, &dst[4]); } static void tea_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) @@ -87,11 +84,9 @@ static void tea_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) u32 y, z, n, sum; u32 k0, k1, k2, k3; struct tea_ctx *ctx = crypto_tfm_ctx(tfm); - const __le32 *in = (const __le32 *)src; - __le32 *out = (__le32 *)dst; - y = le32_to_cpu(in[0]); - z = le32_to_cpu(in[1]); + y = get_unaligned_le32(&src[0]); + z = get_unaligned_le32(&src[4]); k0 = ctx->KEY[0]; k1 = ctx->KEY[1]; @@ -108,20 +103,19 @@ static void tea_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) sum -= TEA_DELTA; } - out[0] = cpu_to_le32(y); - out[1] = cpu_to_le32(z); + put_unaligned_le32(y, &dst[0]); + put_unaligned_le32(z, &dst[4]); } static int xtea_setkey(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct xtea_ctx *ctx = crypto_tfm_ctx(tfm); - const __le32 *key = (const __le32 *)in_key; - ctx->KEY[0] = le32_to_cpu(key[0]); - ctx->KEY[1] = le32_to_cpu(key[1]); - ctx->KEY[2] = le32_to_cpu(key[2]); - ctx->KEY[3] = le32_to_cpu(key[3]); + ctx->KEY[0] = get_unaligned_le32(&in_key[0]); + ctx->KEY[1] = get_unaligned_le32(&in_key[4]); + ctx->KEY[2] = get_unaligned_le32(&in_key[8]); + ctx->KEY[3] = get_unaligned_le32(&in_key[12]); return 0; @@ -132,11 +126,9 @@ static void xtea_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) u32 y, z, sum = 0; u32 limit = XTEA_DELTA * XTEA_ROUNDS; struct xtea_ctx *ctx = crypto_tfm_ctx(tfm); - const __le32 *in = (const __le32 *)src; - __le32 *out = (__le32 *)dst; - y = le32_to_cpu(in[0]); - z = le32_to_cpu(in[1]); + y = get_unaligned_le32(&src[0]); + z = get_unaligned_le32(&src[4]); while (sum != limit) { y += ((z << 4 ^ z >> 5) + z) ^ (sum + ctx->KEY[sum&3]); @@ -144,19 +136,17 @@ static void xtea_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) z += ((y << 4 ^ y >> 5) + y) ^ (sum + ctx->KEY[sum>>11 &3]); } - out[0] = cpu_to_le32(y); - out[1] = cpu_to_le32(z); + put_unaligned_le32(y, &dst[0]); + put_unaligned_le32(z, &dst[4]); } static void xtea_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { u32 y, z, sum; struct tea_ctx *ctx = crypto_tfm_ctx(tfm); - const __le32 *in = (const __le32 *)src; - __le32 *out = (__le32 *)dst; - y = le32_to_cpu(in[0]); - z = le32_to_cpu(in[1]); + y = get_unaligned_le32(&src[0]); + z = get_unaligned_le32(&src[4]); sum = XTEA_DELTA * XTEA_ROUNDS; @@ -166,8 +156,8 @@ static void xtea_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) y -= ((z << 4 ^ z >> 5) + z) ^ (sum + ctx->KEY[sum & 3]); } - out[0] = cpu_to_le32(y); - out[1] = cpu_to_le32(z); + put_unaligned_le32(y, &dst[0]); + put_unaligned_le32(z, &dst[4]); } @@ -176,11 +166,9 @@ static void xeta_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) u32 y, z, sum = 0; u32 limit = XTEA_DELTA * XTEA_ROUNDS; struct xtea_ctx *ctx = crypto_tfm_ctx(tfm); - const __le32 *in = (const __le32 *)src; - __le32 *out = (__le32 *)dst; - y = le32_to_cpu(in[0]); - z = le32_to_cpu(in[1]); + y = get_unaligned_le32(&src[0]); + z = get_unaligned_le32(&src[4]); while (sum != limit) { y += (z << 4 ^ z >> 5) + (z ^ sum) + ctx->KEY[sum&3]; @@ -188,19 +176,17 @@ static void xeta_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) z += (y << 4 ^ y >> 5) + (y ^ sum) + ctx->KEY[sum>>11 &3]; } - out[0] = cpu_to_le32(y); - out[1] = cpu_to_le32(z); + put_unaligned_le32(y, &dst[0]); + put_unaligned_le32(z, &dst[4]); } static void xeta_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { u32 y, z, sum; struct tea_ctx *ctx = crypto_tfm_ctx(tfm); - const __le32 *in = (const __le32 *)src; - __le32 *out = (__le32 *)dst; - y = le32_to_cpu(in[0]); - z = le32_to_cpu(in[1]); + y = get_unaligned_le32(&src[0]); + z = get_unaligned_le32(&src[4]); sum = XTEA_DELTA * XTEA_ROUNDS; @@ -210,8 +196,8 @@ static void xeta_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) y -= (z << 4 ^ z >> 5) + (z ^ sum) + ctx->KEY[sum & 3]; } - out[0] = cpu_to_le32(y); - out[1] = cpu_to_le32(z); + put_unaligned_le32(y, &dst[0]); + put_unaligned_le32(z, &dst[4]); } static struct crypto_alg tea_algs[3] = { { @@ -220,7 +206,6 @@ static struct crypto_alg tea_algs[3] = { { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = TEA_BLOCK_SIZE, .cra_ctxsize = sizeof (struct tea_ctx), - .cra_alignmask = 3, .cra_module = THIS_MODULE, .cra_u = { .cipher = { .cia_min_keysize = TEA_KEY_SIZE, @@ -234,7 +219,6 @@ static struct crypto_alg tea_algs[3] = { { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = XTEA_BLOCK_SIZE, .cra_ctxsize = sizeof (struct xtea_ctx), - .cra_alignmask = 3, .cra_module = THIS_MODULE, .cra_u = { .cipher = { .cia_min_keysize = XTEA_KEY_SIZE, @@ -248,7 +232,6 @@ static struct crypto_alg tea_algs[3] = { { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = XTEA_BLOCK_SIZE, .cra_ctxsize = sizeof (struct xtea_ctx), - .cra_alignmask = 3, .cra_module = THIS_MODULE, .cra_u = { .cipher = { .cia_min_keysize = XTEA_KEY_SIZE, diff --git a/crypto/testmgr.c b/crypto/testmgr.c index 1f5f48ab18c7..e61490ba4095 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -2885,18 +2885,11 @@ static int test_skcipher_vec_cfg(int enc, const struct cipher_testvec *vec, if (ivsize) { if (WARN_ON(ivsize > MAX_IVLEN)) return -EINVAL; - if (vec->generates_iv && !enc) - memcpy(iv, vec->iv_out, ivsize); - else if (vec->iv) + if (vec->iv) memcpy(iv, vec->iv, ivsize); else memset(iv, 0, ivsize); } else { - if (vec->generates_iv) { - pr_err("alg: skcipher: %s has ivsize=0 but test vector %s generates IV!\n", - driver, vec_name); - return -EINVAL; - } iv = NULL; } @@ -3133,10 +3126,6 @@ static int test_skcipher_vs_generic_impl(const char *generic_driver, if (noextratests) return 0; - /* Keywrap isn't supported here yet as it handles its IV differently. */ - if (strncmp(algname, "kw(", 3) == 0) - return 0; - init_rnd_state(&rng); if (!generic_driver) { /* Use default naming convention? */ @@ -5408,13 +5397,6 @@ static const struct alg_test_desc alg_test_descs[] = { .alg = "jitterentropy_rng", .fips_allowed = 1, .test = alg_test_null, - }, { - .alg = "kw(aes)", - .test = alg_test_skcipher, - .fips_allowed = 1, - .suite = { - .cipher = __VECS(aes_kw_tv_template) - } }, { .alg = "lrw(aes)", .generic_driver = "lrw(ecb(aes-generic))", @@ -5749,12 +5731,6 @@ static const struct alg_test_desc alg_test_descs[] = { .suite = { .hash = __VECS(streebog512_tv_template) } - }, { - .alg = "vmac64(aes)", - .test = alg_test_hash, - .suite = { - .hash = __VECS(vmac64_aes_tv_template) - } }, { .alg = "wp256", .test = alg_test_hash, diff --git a/crypto/testmgr.h b/crypto/testmgr.h index 430d33d9ac13..d754ab997186 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -59,8 +59,6 @@ struct hash_testvec { * @wk: Does the test need CRYPTO_TFM_REQ_FORBID_WEAK_KEYS? * ( e.g. test needs to fail due to a weak key ) * @fips_skip: Skip the test vector in FIPS mode - * @generates_iv: Encryption should ignore the given IV, and output @iv_out. - * Decryption takes @iv_out. Needed for AES Keywrap ("kw(aes)"). * @setkey_error: Expected error from setkey() * @crypt_error: Expected error from encrypt() and decrypt() */ @@ -74,7 +72,6 @@ struct cipher_testvec { unsigned short klen; unsigned int len; bool fips_skip; - bool generates_iv; int setkey_error; int crypt_error; }; @@ -8561,159 +8558,6 @@ static const struct hash_testvec aes_xcbc128_tv_template[] = { } }; -static const char vmac64_string1[144] = { - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - '\x01', '\x01', '\x01', '\x01', '\x02', '\x03', '\x02', '\x02', - '\x02', '\x04', '\x01', '\x07', '\x04', '\x01', '\x04', '\x03', -}; - -static const char vmac64_string2[144] = { - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - 'a', 'b', 'c', -}; - -static const char vmac64_string3[144] = { - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - 'a', 'b', 'c', 'a', 'b', 'c', 'a', 'b', - 'c', 'a', 'b', 'c', 'a', 'b', 'c', 'a', - 'b', 'c', 'a', 'b', 'c', 'a', 'b', 'c', - 'a', 'b', 'c', 'a', 'b', 'c', 'a', 'b', - 'c', 'a', 'b', 'c', 'a', 'b', 'c', 'a', - 'b', 'c', 'a', 'b', 'c', 'a', 'b', 'c', -}; - -static const char vmac64_string4[33] = { - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - 'b', 'c', 'e', 'f', 'i', 'j', 'l', 'm', - 'o', 'p', 'r', 's', 't', 'u', 'w', 'x', - 'z', -}; - -static const char vmac64_string5[143] = { - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - 'r', 'm', 'b', 't', 'c', 'o', 'l', 'k', - ']', '%', '9', '2', '7', '!', 'A', -}; - -static const char vmac64_string6[145] = { - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', - 'p', 't', '*', '7', 'l', 'i', '!', '#', - 'w', '0', 'z', '/', '4', 'A', 'n', -}; - -static const struct hash_testvec vmac64_aes_tv_template[] = { - { /* draft-krovetz-vmac-01 test vector 1 */ - .key = "abcdefghijklmnop", - .ksize = 16, - .plaintext = "\0\0\0\0\0\0\0\0bcdefghi", - .psize = 16, - .digest = "\x25\x76\xbe\x1c\x56\xd8\xb8\x1b", - }, { /* draft-krovetz-vmac-01 test vector 2 */ - .key = "abcdefghijklmnop", - .ksize = 16, - .plaintext = "\0\0\0\0\0\0\0\0bcdefghiabc", - .psize = 19, - .digest = "\x2d\x37\x6c\xf5\xb1\x81\x3c\xe5", - }, { /* draft-krovetz-vmac-01 test vector 3 */ - .key = "abcdefghijklmnop", - .ksize = 16, - .plaintext = "\0\0\0\0\0\0\0\0bcdefghi" - "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc", - .psize = 64, - .digest = "\xe8\x42\x1f\x61\xd5\x73\xd2\x98", - }, { /* draft-krovetz-vmac-01 test vector 4 */ - .key = "abcdefghijklmnop", - .ksize = 16, - .plaintext = "\0\0\0\0\0\0\0\0bcdefghi" - "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc" - "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc" - "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc" - "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc" - "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc" - "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabc", - .psize = 316, - .digest = "\x44\x92\xdf\x6c\x5c\xac\x1b\xbe", - }, { - .key = "\x00\x01\x02\x03\x04\x05\x06\x07" - "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", - .ksize = 16, - .plaintext = "\x00\x00\x00\x00\x00\x00\x00\x00" - "\x00\x00\x00\x00\x00\x00\x00\x00", - .psize = 16, - .digest = "\x54\x7b\xa4\x77\x35\x80\x58\x07", - }, { - .key = "\x00\x01\x02\x03\x04\x05\x06\x07" - "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", - .ksize = 16, - .plaintext = vmac64_string1, - .psize = sizeof(vmac64_string1), - .digest = "\xa1\x8c\x68\xae\xd3\x3c\xf5\xce", - }, { - .key = "\x00\x01\x02\x03\x04\x05\x06\x07" - "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", - .ksize = 16, - .plaintext = vmac64_string2, - .psize = sizeof(vmac64_string2), - .digest = "\x2d\x14\xbd\x81\x73\xb0\x27\xc9", - }, { - .key = "\x00\x01\x02\x03\x04\x05\x06\x07" - "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", - .ksize = 16, - .plaintext = vmac64_string3, - .psize = sizeof(vmac64_string3), - .digest = "\x19\x0b\x47\x98\x8c\x95\x1a\x8d", - }, { - .key = "abcdefghijklmnop", - .ksize = 16, - .plaintext = "\x00\x00\x00\x00\x00\x00\x00\x00" - "\x00\x00\x00\x00\x00\x00\x00\x00", - .psize = 16, - .digest = "\x84\x8f\x55\x9e\x26\xa1\x89\x3b", - }, { - .key = "abcdefghijklmnop", - .ksize = 16, - .plaintext = vmac64_string1, - .psize = sizeof(vmac64_string1), - .digest = "\xc2\x74\x8d\xf6\xb0\xab\x5e\xab", - }, { - .key = "abcdefghijklmnop", - .ksize = 16, - .plaintext = vmac64_string2, - .psize = sizeof(vmac64_string2), - .digest = "\xdf\x09\x7b\x3d\x42\x68\x15\x11", - }, { - .key = "abcdefghijklmnop", - .ksize = 16, - .plaintext = vmac64_string3, - .psize = sizeof(vmac64_string3), - .digest = "\xd4\xfa\x8f\xed\xe1\x8f\x32\x8b", - }, { - .key = "a09b5cd!f#07K\x00\x00\x00", - .ksize = 16, - .plaintext = vmac64_string4, - .psize = sizeof(vmac64_string4), - .digest = "\x5f\xa1\x4e\x42\xea\x0f\xa5\xab", - }, { - .key = "a09b5cd!f#07K\x00\x00\x00", - .ksize = 16, - .plaintext = vmac64_string5, - .psize = sizeof(vmac64_string5), - .digest = "\x60\x67\xe8\x1d\xbc\x98\x31\x25", - }, { - .key = "a09b5cd!f#07K\x00\x00\x00", - .ksize = 16, - .plaintext = vmac64_string6, - .psize = sizeof(vmac64_string6), - .digest = "\x41\xeb\x65\x95\x47\x9b\xae\xc4", - }, -}; - /* * SHA384 HMAC test vectors from RFC4231 */ @@ -24348,42 +24192,6 @@ static const struct aead_testvec aegis128_tv_template[] = { }, }; -/* - * All key wrapping test vectors taken from - * http://csrc.nist.gov/groups/STM/cavp/documents/mac/kwtestvectors.zip - * - * Note: as documented in keywrap.c, the ivout for encryption is the first - * semiblock of the ciphertext from the test vector. For decryption, iv is - * the first semiblock of the ciphertext. - */ -static const struct cipher_testvec aes_kw_tv_template[] = { - { - .key = "\x75\x75\xda\x3a\x93\x60\x7c\xc2" - "\xbf\xd8\xce\xc7\xaa\xdf\xd9\xa6", - .klen = 16, - .ptext = "\x42\x13\x6d\x3c\x38\x4a\x3e\xea" - "\xc9\x5a\x06\x6f\xd2\x8f\xed\x3f", - .ctext = "\xf6\x85\x94\x81\x6f\x64\xca\xa3" - "\xf5\x6f\xab\xea\x25\x48\xf5\xfb", - .len = 16, - .iv_out = "\x03\x1f\x6b\xd7\xe6\x1e\x64\x3d", - .generates_iv = true, - }, { - .key = "\x80\xaa\x99\x73\x27\xa4\x80\x6b" - "\x6a\x7a\x41\xa5\x2b\x86\xc3\x71" - "\x03\x86\xf9\x32\x78\x6e\xf7\x96" - "\x76\xfa\xfb\x90\xb8\x26\x3c\x5f", - .klen = 32, - .ptext = "\x0a\x25\x6b\xa7\x5c\xfa\x03\xaa" - "\xa0\x2b\xa9\x42\x03\xf1\x5b\xaa", - .ctext = "\xd3\x3d\x3d\x97\x7b\xf0\xa9\x15" - "\x59\xf9\x9c\x8a\xcd\x29\x3d\x43", - .len = 16, - .iv_out = "\x42\x3c\x96\x0d\x8a\x2a\xc4\xc1", - .generates_iv = true, - }, -}; - /* * ANSI X9.31 Continuous Pseudo-Random Number Generator (AES mode) * test vectors, taken from Appendix B.2.9 and B.2.10: diff --git a/crypto/vmac.c b/crypto/vmac.c deleted file mode 100644 index 2ea384645ecf..000000000000 --- a/crypto/vmac.c +++ /dev/null @@ -1,696 +0,0 @@ -/* - * VMAC: Message Authentication Code using Universal Hashing - * - * Reference: https://tools.ietf.org/html/draft-krovetz-vmac-01 - * - * Copyright (c) 2009, Intel Corporation. - * Copyright (c) 2018, Google Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 Temple - * Place - Suite 330, Boston, MA 02111-1307 USA. - */ - -/* - * Derived from: - * VMAC and VHASH Implementation by Ted Krovetz (tdk@acm.org) and Wei Dai. - * This implementation is herby placed in the public domain. - * The authors offers no warranty. Use at your own risk. - * Last modified: 17 APR 08, 1700 PDT - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * User definable settings. - */ -#define VMAC_TAG_LEN 64 -#define VMAC_KEY_SIZE 128/* Must be 128, 192 or 256 */ -#define VMAC_KEY_LEN (VMAC_KEY_SIZE/8) -#define VMAC_NHBYTES 128/* Must 2^i for any 3 < i < 13 Standard = 128*/ -#define VMAC_NONCEBYTES 16 - -/* per-transform (per-key) context */ -struct vmac_tfm_ctx { - struct crypto_cipher *cipher; - u64 nhkey[(VMAC_NHBYTES/8)+2*(VMAC_TAG_LEN/64-1)]; - u64 polykey[2*VMAC_TAG_LEN/64]; - u64 l3key[2*VMAC_TAG_LEN/64]; -}; - -/* per-request context */ -struct vmac_desc_ctx { - union { - u8 partial[VMAC_NHBYTES]; /* partial block */ - __le64 partial_words[VMAC_NHBYTES / 8]; - }; - unsigned int partial_size; /* size of the partial block */ - bool first_block_processed; - u64 polytmp[2*VMAC_TAG_LEN/64]; /* running total of L2-hash */ - union { - u8 bytes[VMAC_NONCEBYTES]; - __be64 pads[VMAC_NONCEBYTES / 8]; - } nonce; - unsigned int nonce_size; /* nonce bytes filled so far */ -}; - -/* - * Constants and masks - */ -#define UINT64_C(x) x##ULL -static const u64 p64 = UINT64_C(0xfffffffffffffeff); /* 2^64 - 257 prime */ -static const u64 m62 = UINT64_C(0x3fffffffffffffff); /* 62-bit mask */ -static const u64 m63 = UINT64_C(0x7fffffffffffffff); /* 63-bit mask */ -static const u64 m64 = UINT64_C(0xffffffffffffffff); /* 64-bit mask */ -static const u64 mpoly = UINT64_C(0x1fffffff1fffffff); /* Poly key mask */ - -#define pe64_to_cpup le64_to_cpup /* Prefer little endian */ - -#ifdef __LITTLE_ENDIAN -#define INDEX_HIGH 1 -#define INDEX_LOW 0 -#else -#define INDEX_HIGH 0 -#define INDEX_LOW 1 -#endif - -/* - * The following routines are used in this implementation. They are - * written via macros to simulate zero-overhead call-by-reference. - * - * MUL64: 64x64->128-bit multiplication - * PMUL64: assumes top bits cleared on inputs - * ADD128: 128x128->128-bit addition - */ - -#define ADD128(rh, rl, ih, il) \ - do { \ - u64 _il = (il); \ - (rl) += (_il); \ - if ((rl) < (_il)) \ - (rh)++; \ - (rh) += (ih); \ - } while (0) - -#define MUL32(i1, i2) ((u64)(u32)(i1)*(u32)(i2)) - -#define PMUL64(rh, rl, i1, i2) /* Assumes m doesn't overflow */ \ - do { \ - u64 _i1 = (i1), _i2 = (i2); \ - u64 m = MUL32(_i1, _i2>>32) + MUL32(_i1>>32, _i2); \ - rh = MUL32(_i1>>32, _i2>>32); \ - rl = MUL32(_i1, _i2); \ - ADD128(rh, rl, (m >> 32), (m << 32)); \ - } while (0) - -#define MUL64(rh, rl, i1, i2) \ - do { \ - u64 _i1 = (i1), _i2 = (i2); \ - u64 m1 = MUL32(_i1, _i2>>32); \ - u64 m2 = MUL32(_i1>>32, _i2); \ - rh = MUL32(_i1>>32, _i2>>32); \ - rl = MUL32(_i1, _i2); \ - ADD128(rh, rl, (m1 >> 32), (m1 << 32)); \ - ADD128(rh, rl, (m2 >> 32), (m2 << 32)); \ - } while (0) - -/* - * For highest performance the L1 NH and L2 polynomial hashes should be - * carefully implemented to take advantage of one's target architecture. - * Here these two hash functions are defined multiple time; once for - * 64-bit architectures, once for 32-bit SSE2 architectures, and once - * for the rest (32-bit) architectures. - * For each, nh_16 *must* be defined (works on multiples of 16 bytes). - * Optionally, nh_vmac_nhbytes can be defined (for multiples of - * VMAC_NHBYTES), and nh_16_2 and nh_vmac_nhbytes_2 (versions that do two - * NH computations at once). - */ - -#ifdef CONFIG_64BIT - -#define nh_16(mp, kp, nw, rh, rl) \ - do { \ - int i; u64 th, tl; \ - rh = rl = 0; \ - for (i = 0; i < nw; i += 2) { \ - MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i], \ - pe64_to_cpup((mp)+i+1)+(kp)[i+1]); \ - ADD128(rh, rl, th, tl); \ - } \ - } while (0) - -#define nh_16_2(mp, kp, nw, rh, rl, rh1, rl1) \ - do { \ - int i; u64 th, tl; \ - rh1 = rl1 = rh = rl = 0; \ - for (i = 0; i < nw; i += 2) { \ - MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i], \ - pe64_to_cpup((mp)+i+1)+(kp)[i+1]); \ - ADD128(rh, rl, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i+2], \ - pe64_to_cpup((mp)+i+1)+(kp)[i+3]); \ - ADD128(rh1, rl1, th, tl); \ - } \ - } while (0) - -#if (VMAC_NHBYTES >= 64) /* These versions do 64-bytes of message at a time */ -#define nh_vmac_nhbytes(mp, kp, nw, rh, rl) \ - do { \ - int i; u64 th, tl; \ - rh = rl = 0; \ - for (i = 0; i < nw; i += 8) { \ - MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i], \ - pe64_to_cpup((mp)+i+1)+(kp)[i+1]); \ - ADD128(rh, rl, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i+2)+(kp)[i+2], \ - pe64_to_cpup((mp)+i+3)+(kp)[i+3]); \ - ADD128(rh, rl, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i+4)+(kp)[i+4], \ - pe64_to_cpup((mp)+i+5)+(kp)[i+5]); \ - ADD128(rh, rl, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i+6)+(kp)[i+6], \ - pe64_to_cpup((mp)+i+7)+(kp)[i+7]); \ - ADD128(rh, rl, th, tl); \ - } \ - } while (0) - -#define nh_vmac_nhbytes_2(mp, kp, nw, rh, rl, rh1, rl1) \ - do { \ - int i; u64 th, tl; \ - rh1 = rl1 = rh = rl = 0; \ - for (i = 0; i < nw; i += 8) { \ - MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i], \ - pe64_to_cpup((mp)+i+1)+(kp)[i+1]); \ - ADD128(rh, rl, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i)+(kp)[i+2], \ - pe64_to_cpup((mp)+i+1)+(kp)[i+3]); \ - ADD128(rh1, rl1, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i+2)+(kp)[i+2], \ - pe64_to_cpup((mp)+i+3)+(kp)[i+3]); \ - ADD128(rh, rl, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i+2)+(kp)[i+4], \ - pe64_to_cpup((mp)+i+3)+(kp)[i+5]); \ - ADD128(rh1, rl1, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i+4)+(kp)[i+4], \ - pe64_to_cpup((mp)+i+5)+(kp)[i+5]); \ - ADD128(rh, rl, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i+4)+(kp)[i+6], \ - pe64_to_cpup((mp)+i+5)+(kp)[i+7]); \ - ADD128(rh1, rl1, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i+6)+(kp)[i+6], \ - pe64_to_cpup((mp)+i+7)+(kp)[i+7]); \ - ADD128(rh, rl, th, tl); \ - MUL64(th, tl, pe64_to_cpup((mp)+i+6)+(kp)[i+8], \ - pe64_to_cpup((mp)+i+7)+(kp)[i+9]); \ - ADD128(rh1, rl1, th, tl); \ - } \ - } while (0) -#endif - -#define poly_step(ah, al, kh, kl, mh, ml) \ - do { \ - u64 t1h, t1l, t2h, t2l, t3h, t3l, z = 0; \ - /* compute ab*cd, put bd into result registers */ \ - PMUL64(t3h, t3l, al, kh); \ - PMUL64(t2h, t2l, ah, kl); \ - PMUL64(t1h, t1l, ah, 2*kh); \ - PMUL64(ah, al, al, kl); \ - /* add 2 * ac to result */ \ - ADD128(ah, al, t1h, t1l); \ - /* add together ad + bc */ \ - ADD128(t2h, t2l, t3h, t3l); \ - /* now (ah,al), (t2l,2*t2h) need summing */ \ - /* first add the high registers, carrying into t2h */ \ - ADD128(t2h, ah, z, t2l); \ - /* double t2h and add top bit of ah */ \ - t2h = 2 * t2h + (ah >> 63); \ - ah &= m63; \ - /* now add the low registers */ \ - ADD128(ah, al, mh, ml); \ - ADD128(ah, al, z, t2h); \ - } while (0) - -#else /* ! CONFIG_64BIT */ - -#ifndef nh_16 -#define nh_16(mp, kp, nw, rh, rl) \ - do { \ - u64 t1, t2, m1, m2, t; \ - int i; \ - rh = rl = t = 0; \ - for (i = 0; i < nw; i += 2) { \ - t1 = pe64_to_cpup(mp+i) + kp[i]; \ - t2 = pe64_to_cpup(mp+i+1) + kp[i+1]; \ - m2 = MUL32(t1 >> 32, t2); \ - m1 = MUL32(t1, t2 >> 32); \ - ADD128(rh, rl, MUL32(t1 >> 32, t2 >> 32), \ - MUL32(t1, t2)); \ - rh += (u64)(u32)(m1 >> 32) \ - + (u32)(m2 >> 32); \ - t += (u64)(u32)m1 + (u32)m2; \ - } \ - ADD128(rh, rl, (t >> 32), (t << 32)); \ - } while (0) -#endif - -static void poly_step_func(u64 *ahi, u64 *alo, - const u64 *kh, const u64 *kl, - const u64 *mh, const u64 *ml) -{ -#define a0 (*(((u32 *)alo)+INDEX_LOW)) -#define a1 (*(((u32 *)alo)+INDEX_HIGH)) -#define a2 (*(((u32 *)ahi)+INDEX_LOW)) -#define a3 (*(((u32 *)ahi)+INDEX_HIGH)) -#define k0 (*(((u32 *)kl)+INDEX_LOW)) -#define k1 (*(((u32 *)kl)+INDEX_HIGH)) -#define k2 (*(((u32 *)kh)+INDEX_LOW)) -#define k3 (*(((u32 *)kh)+INDEX_HIGH)) - - u64 p, q, t; - u32 t2; - - p = MUL32(a3, k3); - p += p; - p += *(u64 *)mh; - p += MUL32(a0, k2); - p += MUL32(a1, k1); - p += MUL32(a2, k0); - t = (u32)(p); - p >>= 32; - p += MUL32(a0, k3); - p += MUL32(a1, k2); - p += MUL32(a2, k1); - p += MUL32(a3, k0); - t |= ((u64)((u32)p & 0x7fffffff)) << 32; - p >>= 31; - p += (u64)(((u32 *)ml)[INDEX_LOW]); - p += MUL32(a0, k0); - q = MUL32(a1, k3); - q += MUL32(a2, k2); - q += MUL32(a3, k1); - q += q; - p += q; - t2 = (u32)(p); - p >>= 32; - p += (u64)(((u32 *)ml)[INDEX_HIGH]); - p += MUL32(a0, k1); - p += MUL32(a1, k0); - q = MUL32(a2, k3); - q += MUL32(a3, k2); - q += q; - p += q; - *(u64 *)(alo) = (p << 32) | t2; - p >>= 32; - *(u64 *)(ahi) = p + t; - -#undef a0 -#undef a1 -#undef a2 -#undef a3 -#undef k0 -#undef k1 -#undef k2 -#undef k3 -} - -#define poly_step(ah, al, kh, kl, mh, ml) \ - poly_step_func(&(ah), &(al), &(kh), &(kl), &(mh), &(ml)) - -#endif /* end of specialized NH and poly definitions */ - -/* At least nh_16 is defined. Defined others as needed here */ -#ifndef nh_16_2 -#define nh_16_2(mp, kp, nw, rh, rl, rh2, rl2) \ - do { \ - nh_16(mp, kp, nw, rh, rl); \ - nh_16(mp, ((kp)+2), nw, rh2, rl2); \ - } while (0) -#endif -#ifndef nh_vmac_nhbytes -#define nh_vmac_nhbytes(mp, kp, nw, rh, rl) \ - nh_16(mp, kp, nw, rh, rl) -#endif -#ifndef nh_vmac_nhbytes_2 -#define nh_vmac_nhbytes_2(mp, kp, nw, rh, rl, rh2, rl2) \ - do { \ - nh_vmac_nhbytes(mp, kp, nw, rh, rl); \ - nh_vmac_nhbytes(mp, ((kp)+2), nw, rh2, rl2); \ - } while (0) -#endif - -static u64 l3hash(u64 p1, u64 p2, u64 k1, u64 k2, u64 len) -{ - u64 rh, rl, t, z = 0; - - /* fully reduce (p1,p2)+(len,0) mod p127 */ - t = p1 >> 63; - p1 &= m63; - ADD128(p1, p2, len, t); - /* At this point, (p1,p2) is at most 2^127+(len<<64) */ - t = (p1 > m63) + ((p1 == m63) && (p2 == m64)); - ADD128(p1, p2, z, t); - p1 &= m63; - - /* compute (p1,p2)/(2^64-2^32) and (p1,p2)%(2^64-2^32) */ - t = p1 + (p2 >> 32); - t += (t >> 32); - t += (u32)t > 0xfffffffeu; - p1 += (t >> 32); - p2 += (p1 << 32); - - /* compute (p1+k1)%p64 and (p2+k2)%p64 */ - p1 += k1; - p1 += (0 - (p1 < k1)) & 257; - p2 += k2; - p2 += (0 - (p2 < k2)) & 257; - - /* compute (p1+k1)*(p2+k2)%p64 */ - MUL64(rh, rl, p1, p2); - t = rh >> 56; - ADD128(t, rl, z, rh); - rh <<= 8; - ADD128(t, rl, z, rh); - t += t << 8; - rl += t; - rl += (0 - (rl < t)) & 257; - rl += (0 - (rl > p64-1)) & 257; - return rl; -} - -/* L1 and L2-hash one or more VMAC_NHBYTES-byte blocks */ -static void vhash_blocks(const struct vmac_tfm_ctx *tctx, - struct vmac_desc_ctx *dctx, - const __le64 *mptr, unsigned int blocks) -{ - const u64 *kptr = tctx->nhkey; - const u64 pkh = tctx->polykey[0]; - const u64 pkl = tctx->polykey[1]; - u64 ch = dctx->polytmp[0]; - u64 cl = dctx->polytmp[1]; - u64 rh, rl; - - if (!dctx->first_block_processed) { - dctx->first_block_processed = true; - nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl); - rh &= m62; - ADD128(ch, cl, rh, rl); - mptr += (VMAC_NHBYTES/sizeof(u64)); - blocks--; - } - - while (blocks--) { - nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl); - rh &= m62; - poly_step(ch, cl, pkh, pkl, rh, rl); - mptr += (VMAC_NHBYTES/sizeof(u64)); - } - - dctx->polytmp[0] = ch; - dctx->polytmp[1] = cl; -} - -static int vmac_setkey(struct crypto_shash *tfm, - const u8 *key, unsigned int keylen) -{ - struct vmac_tfm_ctx *tctx = crypto_shash_ctx(tfm); - __be64 out[2]; - u8 in[16] = { 0 }; - unsigned int i; - int err; - - if (keylen != VMAC_KEY_LEN) - return -EINVAL; - - err = crypto_cipher_setkey(tctx->cipher, key, keylen); - if (err) - return err; - - /* Fill nh key */ - in[0] = 0x80; - for (i = 0; i < ARRAY_SIZE(tctx->nhkey); i += 2) { - crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in); - tctx->nhkey[i] = be64_to_cpu(out[0]); - tctx->nhkey[i+1] = be64_to_cpu(out[1]); - in[15]++; - } - - /* Fill poly key */ - in[0] = 0xC0; - in[15] = 0; - for (i = 0; i < ARRAY_SIZE(tctx->polykey); i += 2) { - crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in); - tctx->polykey[i] = be64_to_cpu(out[0]) & mpoly; - tctx->polykey[i+1] = be64_to_cpu(out[1]) & mpoly; - in[15]++; - } - - /* Fill ip key */ - in[0] = 0xE0; - in[15] = 0; - for (i = 0; i < ARRAY_SIZE(tctx->l3key); i += 2) { - do { - crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in); - tctx->l3key[i] = be64_to_cpu(out[0]); - tctx->l3key[i+1] = be64_to_cpu(out[1]); - in[15]++; - } while (tctx->l3key[i] >= p64 || tctx->l3key[i+1] >= p64); - } - - return 0; -} - -static int vmac_init(struct shash_desc *desc) -{ - const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); - struct vmac_desc_ctx *dctx = shash_desc_ctx(desc); - - dctx->partial_size = 0; - dctx->first_block_processed = false; - memcpy(dctx->polytmp, tctx->polykey, sizeof(dctx->polytmp)); - dctx->nonce_size = 0; - return 0; -} - -static int vmac_update(struct shash_desc *desc, const u8 *p, unsigned int len) -{ - const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); - struct vmac_desc_ctx *dctx = shash_desc_ctx(desc); - unsigned int n; - - /* Nonce is passed as first VMAC_NONCEBYTES bytes of data */ - if (dctx->nonce_size < VMAC_NONCEBYTES) { - n = min(len, VMAC_NONCEBYTES - dctx->nonce_size); - memcpy(&dctx->nonce.bytes[dctx->nonce_size], p, n); - dctx->nonce_size += n; - p += n; - len -= n; - } - - if (dctx->partial_size) { - n = min(len, VMAC_NHBYTES - dctx->partial_size); - memcpy(&dctx->partial[dctx->partial_size], p, n); - dctx->partial_size += n; - p += n; - len -= n; - if (dctx->partial_size == VMAC_NHBYTES) { - vhash_blocks(tctx, dctx, dctx->partial_words, 1); - dctx->partial_size = 0; - } - } - - if (len >= VMAC_NHBYTES) { - n = round_down(len, VMAC_NHBYTES); - /* TODO: 'p' may be misaligned here */ - vhash_blocks(tctx, dctx, (const __le64 *)p, n / VMAC_NHBYTES); - p += n; - len -= n; - } - - if (len) { - memcpy(dctx->partial, p, len); - dctx->partial_size = len; - } - - return 0; -} - -static u64 vhash_final(const struct vmac_tfm_ctx *tctx, - struct vmac_desc_ctx *dctx) -{ - unsigned int partial = dctx->partial_size; - u64 ch = dctx->polytmp[0]; - u64 cl = dctx->polytmp[1]; - - /* L1 and L2-hash the final block if needed */ - if (partial) { - /* Zero-pad to next 128-bit boundary */ - unsigned int n = round_up(partial, 16); - u64 rh, rl; - - memset(&dctx->partial[partial], 0, n - partial); - nh_16(dctx->partial_words, tctx->nhkey, n / 8, rh, rl); - rh &= m62; - if (dctx->first_block_processed) - poly_step(ch, cl, tctx->polykey[0], tctx->polykey[1], - rh, rl); - else - ADD128(ch, cl, rh, rl); - } - - /* L3-hash the 128-bit output of L2-hash */ - return l3hash(ch, cl, tctx->l3key[0], tctx->l3key[1], partial * 8); -} - -static int vmac_final(struct shash_desc *desc, u8 *out) -{ - const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); - struct vmac_desc_ctx *dctx = shash_desc_ctx(desc); - int index; - u64 hash, pad; - - if (dctx->nonce_size != VMAC_NONCEBYTES) - return -EINVAL; - - /* - * The VMAC specification requires a nonce at least 1 bit shorter than - * the block cipher's block length, so we actually only accept a 127-bit - * nonce. We define the unused bit to be the first one and require that - * it be 0, so the needed prepending of a 0 bit is implicit. - */ - if (dctx->nonce.bytes[0] & 0x80) - return -EINVAL; - - /* Finish calculating the VHASH of the message */ - hash = vhash_final(tctx, dctx); - - /* Generate pseudorandom pad by encrypting the nonce */ - BUILD_BUG_ON(VMAC_NONCEBYTES != 2 * (VMAC_TAG_LEN / 8)); - index = dctx->nonce.bytes[VMAC_NONCEBYTES - 1] & 1; - dctx->nonce.bytes[VMAC_NONCEBYTES - 1] &= ~1; - crypto_cipher_encrypt_one(tctx->cipher, dctx->nonce.bytes, - dctx->nonce.bytes); - pad = be64_to_cpu(dctx->nonce.pads[index]); - - /* The VMAC is the sum of VHASH and the pseudorandom pad */ - put_unaligned_be64(hash + pad, out); - return 0; -} - -static int vmac_init_tfm(struct crypto_tfm *tfm) -{ - struct crypto_instance *inst = crypto_tfm_alg_instance(tfm); - struct crypto_cipher_spawn *spawn = crypto_instance_ctx(inst); - struct vmac_tfm_ctx *tctx = crypto_tfm_ctx(tfm); - struct crypto_cipher *cipher; - - cipher = crypto_spawn_cipher(spawn); - if (IS_ERR(cipher)) - return PTR_ERR(cipher); - - tctx->cipher = cipher; - return 0; -} - -static void vmac_exit_tfm(struct crypto_tfm *tfm) -{ - struct vmac_tfm_ctx *tctx = crypto_tfm_ctx(tfm); - - crypto_free_cipher(tctx->cipher); -} - -static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb) -{ - struct shash_instance *inst; - struct crypto_cipher_spawn *spawn; - struct crypto_alg *alg; - u32 mask; - int err; - - err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SHASH, &mask); - if (err) - return err; - - inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); - if (!inst) - return -ENOMEM; - spawn = shash_instance_ctx(inst); - - err = crypto_grab_cipher(spawn, shash_crypto_instance(inst), - crypto_attr_alg_name(tb[1]), 0, mask); - if (err) - goto err_free_inst; - alg = crypto_spawn_cipher_alg(spawn); - - err = -EINVAL; - if (alg->cra_blocksize != VMAC_NONCEBYTES) - goto err_free_inst; - - err = crypto_inst_setname(shash_crypto_instance(inst), tmpl->name, alg); - if (err) - goto err_free_inst; - - inst->alg.base.cra_priority = alg->cra_priority; - inst->alg.base.cra_blocksize = alg->cra_blocksize; - - inst->alg.base.cra_ctxsize = sizeof(struct vmac_tfm_ctx); - inst->alg.base.cra_init = vmac_init_tfm; - inst->alg.base.cra_exit = vmac_exit_tfm; - - inst->alg.descsize = sizeof(struct vmac_desc_ctx); - inst->alg.digestsize = VMAC_TAG_LEN / 8; - inst->alg.init = vmac_init; - inst->alg.update = vmac_update; - inst->alg.final = vmac_final; - inst->alg.setkey = vmac_setkey; - - inst->free = shash_free_singlespawn_instance; - - err = shash_register_instance(tmpl, inst); - if (err) { -err_free_inst: - shash_free_singlespawn_instance(inst); - } - return err; -} - -static struct crypto_template vmac64_tmpl = { - .name = "vmac64", - .create = vmac_create, - .module = THIS_MODULE, -}; - -static int __init vmac_module_init(void) -{ - return crypto_register_template(&vmac64_tmpl); -} - -static void __exit vmac_module_exit(void) -{ - crypto_unregister_template(&vmac64_tmpl); -} - -subsys_initcall(vmac_module_init); -module_exit(vmac_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("VMAC hash algorithm"); -MODULE_ALIAS_CRYPTO("vmac64"); -MODULE_IMPORT_NS("CRYPTO_INTERNAL"); diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index 9facf45818f9..5f43db02b240 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -22,7 +22,7 @@ #include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" -bool force_cmdlist; +static bool force_cmdlist; module_param(force_cmdlist, bool, 0600); MODULE_PARM_DESC(force_cmdlist, "Force use command list (Default false)"); diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c index 8de8f3bd4987..5a058e565b01 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -25,7 +25,7 @@ #include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" -int aie2_max_col = XRS_MAX_COL; +static int aie2_max_col = XRS_MAX_COL; module_param(aie2_max_col, uint, 0600); MODULE_PARM_DESC(aie2_max_col, "Maximum column could be used"); @@ -380,9 +380,9 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) goto stop_psp; } - mbox_res.ringbuf_base = (u64)ndev->sram_base; + mbox_res.ringbuf_base = ndev->sram_base; mbox_res.ringbuf_size = pci_resource_len(pdev, xdna->dev_info->sram_bar); - mbox_res.mbox_base = (u64)ndev->mbox_base; + mbox_res.mbox_base = ndev->mbox_base; mbox_res.mbox_size = MBOX_SIZE(ndev); mbox_res.name = "xdna_mailbox"; ndev->mbox = xdnam_mailbox_create(&xdna->ddev, &mbox_res); diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h index cc159cadff9f..f2d95531ddc2 100644 --- a/drivers/accel/amdxdna/aie2_pci.h +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -269,7 +269,7 @@ int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size); -int aie2_query_status(struct amdxdna_dev_hdl *ndev, char *buf, u32 size, u32 *cols_filled); +int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf, u32 size, u32 *cols_filled); int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size, void *handle, int (*cb)(void*, const u32 *, size_t)); int aie2_config_cu(struct amdxdna_hwctx *hwctx); diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c index 1afc8079e3d1..814b16bb1953 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox.c +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c @@ -98,27 +98,27 @@ struct mailbox_msg { static void mailbox_reg_write(struct mailbox_channel *mb_chann, u32 mbox_reg, u32 data) { struct xdna_mailbox_res *mb_res = &mb_chann->mb->res; - u64 ringbuf_addr = mb_res->mbox_base + mbox_reg; + void __iomem *ringbuf_addr = mb_res->mbox_base + mbox_reg; - writel(data, (void *)ringbuf_addr); + writel(data, ringbuf_addr); } static u32 mailbox_reg_read(struct mailbox_channel *mb_chann, u32 mbox_reg) { struct xdna_mailbox_res *mb_res = &mb_chann->mb->res; - u64 ringbuf_addr = mb_res->mbox_base + mbox_reg; + void __iomem *ringbuf_addr = mb_res->mbox_base + mbox_reg; - return readl((void *)ringbuf_addr); + return readl(ringbuf_addr); } static int mailbox_reg_read_non_zero(struct mailbox_channel *mb_chann, u32 mbox_reg, u32 *val) { struct xdna_mailbox_res *mb_res = &mb_chann->mb->res; - u64 ringbuf_addr = mb_res->mbox_base + mbox_reg; + void __iomem *ringbuf_addr = mb_res->mbox_base + mbox_reg; int ret, value; /* Poll till value is not zero */ - ret = readx_poll_timeout(readl, (void *)ringbuf_addr, value, + ret = readx_poll_timeout(readl, ringbuf_addr, value, value, 1 /* us */, 100); if (ret < 0) return ret; @@ -200,10 +200,10 @@ static void mailbox_release_msg(struct mailbox_channel *mb_chann, static int mailbox_send_msg(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) { + void __iomem *write_addr; u32 ringbuf_size; u32 head, tail; u32 start_addr; - u64 write_addr; u32 tmp_tail; head = mailbox_get_headptr(mb_chann, CHAN_RES_X2I); @@ -221,14 +221,14 @@ mailbox_send_msg(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) if (tail >= head && tmp_tail > ringbuf_size - sizeof(u32)) { write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; - writel(TOMBSTONE, (void *)write_addr); + writel(TOMBSTONE, write_addr); /* tombstone is set. Write from the start of the ringbuf */ tail = 0; } write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; - memcpy_toio((void *)write_addr, &mb_msg->pkg, mb_msg->pkg_size); + memcpy_toio(write_addr, &mb_msg->pkg, mb_msg->pkg_size); mailbox_set_tailptr(mb_chann, tail + mb_msg->pkg_size); trace_mbox_set_tail(MAILBOX_NAME, mb_chann->msix_irq, @@ -275,11 +275,11 @@ mailbox_get_resp(struct mailbox_channel *mb_chann, struct xdna_msg_header *heade static int mailbox_get_msg(struct mailbox_channel *mb_chann) { struct xdna_msg_header header; + void __iomem *read_addr; u32 msg_size, rest; u32 ringbuf_size; u32 head, tail; u32 start_addr; - u64 read_addr; int ret; if (mailbox_reg_read_non_zero(mb_chann, mb_chann->res[CHAN_RES_I2X].mb_tail_ptr_reg, &tail)) @@ -302,7 +302,7 @@ static int mailbox_get_msg(struct mailbox_channel *mb_chann) /* Peek size of the message or TOMBSTONE */ read_addr = mb_chann->mb->res.ringbuf_base + start_addr + head; - header.total_size = readl((void *)read_addr); + header.total_size = readl(read_addr); /* size is TOMBSTONE, set next read from 0 */ if (header.total_size == TOMBSTONE) { if (head < tail) { @@ -328,7 +328,7 @@ static int mailbox_get_msg(struct mailbox_channel *mb_chann) rest = sizeof(header) - sizeof(u32); read_addr += sizeof(u32); - memcpy_fromio((u32 *)&header + 1, (void *)read_addr, rest); + memcpy_fromio((u32 *)&header + 1, read_addr, rest); read_addr += rest; ret = mailbox_get_resp(mb_chann, &header, (u32 *)read_addr); diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.h b/drivers/accel/amdxdna/amdxdna_mailbox.h index 6ab7f5424633..57954c303bdd 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox.h +++ b/drivers/accel/amdxdna/amdxdna_mailbox.h @@ -39,9 +39,9 @@ struct xdna_mailbox_msg { * @mbox_size: mailbox size */ struct xdna_mailbox_res { - u64 ringbuf_base; + void __iomem *ringbuf_base; size_t ringbuf_size; - u64 mbox_base; + void __iomem *mbox_base; size_t mbox_size; const char *name; }; diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index 194e44fc243d..97d4a032171f 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -61,7 +61,7 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) goto put_rpm; } - client->pid = pid_nr(filp->pid); + client->pid = pid_nr(rcu_access_pointer(filp->pid)); client->xdna = xdna; client->sva = iommu_sva_bind_device(xdna->ddev.dev, current->mm); diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c index e408af57e378..e4f6dac7d00f 100644 --- a/drivers/accel/amdxdna/npu1_regs.c +++ b/drivers/accel/amdxdna/npu1_regs.c @@ -62,7 +62,7 @@ const struct dpm_clk_freq npu1_dpm_clk_table[] = { { 0 } }; -const struct amdxdna_dev_priv npu1_dev_priv = { +static const struct amdxdna_dev_priv npu1_dev_priv = { .fw_path = "amdnpu/1502_00/npu.sbin", .protocol_major = 0x5, .protocol_minor = 0x7, diff --git a/drivers/accel/amdxdna/npu2_regs.c b/drivers/accel/amdxdna/npu2_regs.c index 286bd0d475e2..a081cac75ee0 100644 --- a/drivers/accel/amdxdna/npu2_regs.c +++ b/drivers/accel/amdxdna/npu2_regs.c @@ -61,7 +61,7 @@ #define NPU2_SMU_BAR_BASE MMNPU_APERTURE4_BASE #define NPU2_SRAM_BAR_BASE MMNPU_APERTURE1_BASE -const struct amdxdna_dev_priv npu2_dev_priv = { +static const struct amdxdna_dev_priv npu2_dev_priv = { .fw_path = "amdnpu/17f0_00/npu.sbin", .protocol_major = 0x6, .protocol_minor = 0x6, diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/amdxdna/npu4_regs.c index 00c52833ce89..9f2e33182ec6 100644 --- a/drivers/accel/amdxdna/npu4_regs.c +++ b/drivers/accel/amdxdna/npu4_regs.c @@ -82,7 +82,7 @@ const struct dpm_clk_freq npu4_dpm_clk_table[] = { { 0 } }; -const struct amdxdna_dev_priv npu4_dev_priv = { +static const struct amdxdna_dev_priv npu4_dev_priv = { .fw_path = "amdnpu/17f0_10/npu.sbin", .protocol_major = 0x6, .protocol_minor = 12, diff --git a/drivers/accel/amdxdna/npu5_regs.c b/drivers/accel/amdxdna/npu5_regs.c index 118849272f27..5f1cf83461c4 100644 --- a/drivers/accel/amdxdna/npu5_regs.c +++ b/drivers/accel/amdxdna/npu5_regs.c @@ -61,7 +61,7 @@ #define NPU5_SMU_BAR_BASE MMNPU_APERTURE4_BASE #define NPU5_SRAM_BAR_BASE MMNPU_APERTURE1_BASE -const struct amdxdna_dev_priv npu5_dev_priv = { +static const struct amdxdna_dev_priv npu5_dev_priv = { .fw_path = "amdnpu/17f0_11/npu.sbin", .protocol_major = 0x6, .protocol_minor = 12, diff --git a/drivers/accel/amdxdna/npu6_regs.c b/drivers/accel/amdxdna/npu6_regs.c index f46c760cefc7..94a7005685a7 100644 --- a/drivers/accel/amdxdna/npu6_regs.c +++ b/drivers/accel/amdxdna/npu6_regs.c @@ -61,7 +61,7 @@ #define NPU6_SMU_BAR_BASE MMNPU_APERTURE4_BASE #define NPU6_SRAM_BAR_BASE MMNPU_APERTURE1_BASE -const struct amdxdna_dev_priv npu6_dev_priv = { +static const struct amdxdna_dev_priv npu6_dev_priv = { .fw_path = "amdnpu/17f0_10/npu.sbin", .protocol_major = 0x6, .protocol_minor = 12, diff --git a/drivers/accel/habanalabs/common/context.c b/drivers/accel/habanalabs/common/context.c index b83141f58319..9f212b17611a 100644 --- a/drivers/accel/habanalabs/common/context.c +++ b/drivers/accel/habanalabs/common/context.c @@ -199,7 +199,6 @@ out_err: int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx) { - char task_comm[TASK_COMM_LEN]; int rc = 0, i; ctx->hdev = hdev; @@ -272,7 +271,7 @@ int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx) mutex_init(&ctx->ts_reg_lock); dev_dbg(hdev->dev, "create user context, comm=\"%s\", asid=%u\n", - get_task_comm(task_comm, current), ctx->asid); + current->comm, ctx->asid); } return 0; diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c index e0cf3b4343bb..30277ae410d4 100644 --- a/drivers/accel/habanalabs/common/device.c +++ b/drivers/accel/habanalabs/common/device.c @@ -817,7 +817,7 @@ static void device_hard_reset_pending(struct work_struct *work) } queue_delayed_work(hdev->reset_wq, &device_reset_work->reset_work, - msecs_to_jiffies(HL_PENDING_RESET_PER_SEC * 1000)); + secs_to_jiffies(HL_PENDING_RESET_PER_SEC)); } } diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c index 5409b2c656c8..596c52e8aa26 100644 --- a/drivers/accel/habanalabs/common/habanalabs_drv.c +++ b/drivers/accel/habanalabs/common/habanalabs_drv.c @@ -361,8 +361,7 @@ static void fixup_device_params_per_asic(struct hl_device *hdev, int timeout) * a different default timeout for Gaudi */ if (timeout == HL_DEFAULT_TIMEOUT_LOCKED) - hdev->timeout_jiffies = msecs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED * - MSEC_PER_SEC); + hdev->timeout_jiffies = secs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED); hdev->reset_upon_device_release = 0; break; diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c index 1dd6e23172ca..8729a0c57d78 100644 --- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c @@ -1279,13 +1279,10 @@ static long _hl_ioctl(struct hl_fpriv *hpriv, unsigned int cmd, unsigned long ar retcode = -EFAULT; out_err: - if (retcode) { - char task_comm[TASK_COMM_LEN]; - + if (retcode) dev_dbg_ratelimited(dev, "error in ioctl: pid=%d, comm=\"%s\", cmd=%#010x, nr=%#04x\n", - task_pid_nr(current), get_task_comm(task_comm, current), cmd, nr); - } + task_pid_nr(current), current->comm, cmd, nr); if (kdata != stack_kdata) kfree(kdata); @@ -1308,11 +1305,9 @@ long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg) if (nr == _IOC_NR(DRM_IOCTL_HL_INFO)) { ioctl = &hl_ioctls_control[nr - HL_COMMAND_START]; } else { - char task_comm[TASK_COMM_LEN]; - dev_dbg_ratelimited(hdev->dev_ctrl, "invalid ioctl: pid=%d, comm=\"%s\", cmd=%#010x, nr=%#04x\n", - task_pid_nr(current), get_task_comm(task_comm, current), cmd, nr); + task_pid_nr(current), current->comm, cmd, nr); return -ENOTTY; } diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index d8e97a760fbc..16178054e629 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -409,7 +409,7 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p) mutex_lock(&bo->lock); drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u", - bo, bo->ctx->id, bo->vpu_addr, bo->base.base.size, + bo, bo->ctx ? bo->ctx->id : 0, bo->vpu_addr, bo->base.base.size, bo->flags, kref_read(&bo->base.base.refcount)); if (bo->base.pages) diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c index 891967a95bc3..0af614dfb6f9 100644 --- a/drivers/accel/ivpu/ivpu_mmu_context.c +++ b/drivers/accel/ivpu/ivpu_mmu_context.c @@ -612,18 +612,22 @@ int ivpu_mmu_reserved_context_init(struct ivpu_device *vdev) if (!ivpu_mmu_ensure_pgd(vdev, &vdev->rctx.pgtable)) { ivpu_err(vdev, "Failed to allocate root page table for reserved context\n"); ret = -ENOMEM; - goto unlock; + goto err_ctx_fini; } ret = ivpu_mmu_cd_set(vdev, vdev->rctx.id, &vdev->rctx.pgtable); if (ret) { ivpu_err(vdev, "Failed to set context descriptor for reserved context\n"); - goto unlock; + goto err_ctx_fini; } -unlock: mutex_unlock(&vdev->rctx.lock); return ret; + +err_ctx_fini: + mutex_unlock(&vdev->rctx.lock); + ivpu_mmu_context_fini(vdev, &vdev->rctx); + return ret; } void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev) diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 6821051dfa3a..87d7411ae059 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -378,6 +378,7 @@ void ivpu_pm_init(struct ivpu_device *vdev) pm_runtime_use_autosuspend(dev); pm_runtime_set_autosuspend_delay(dev, delay); + pm_runtime_set_active(dev); ivpu_dbg(vdev, PM, "Autosuspend delay = %d\n", delay); } @@ -392,7 +393,6 @@ void ivpu_pm_enable(struct ivpu_device *vdev) { struct device *dev = vdev->drm.dev; - pm_runtime_set_active(dev); pm_runtime_allow(dev); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index d65cd08ba8e1..d81b55f5068c 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -135,10 +135,10 @@ config ACPI_REV_OVERRIDE_POSSIBLE config ACPI_EC bool "Embedded Controller" depends on HAS_IOPORT - default X86 + default X86 || LOONGARCH help This driver handles communication with the microcontroller - on many x86 laptops and other machines. + on many x86/LoongArch laptops and other machines. config ACPI_EC_DEBUGFS tristate "EC read/write access through /sys/kernel/debug/ec" diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index ca87a0939135..f7fb7205028d 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -251,6 +251,10 @@ static int __init extlog_init(void) } extlog_l1_hdr = acpi_os_map_iomem(l1_dirbase, l1_hdr_size); + if (!extlog_l1_hdr) { + rc = -ENOMEM; + goto err_release_l1_hdr; + } l1_head = (struct extlog_l1_head *)extlog_l1_hdr; l1_size = l1_head->total_len; l1_percpu_entry = l1_head->entries; @@ -268,6 +272,10 @@ static int __init extlog_init(void) goto err; } extlog_l1_addr = acpi_os_map_iomem(l1_dirbase, l1_size); + if (!extlog_l1_addr) { + rc = -ENOMEM; + goto err_release_l1_dir; + } l1_entry_base = (u64 *)((u8 *)extlog_l1_addr + l1_hdr_size); /* remap elog table */ @@ -279,6 +287,10 @@ static int __init extlog_init(void) goto err_release_l1_dir; } elog_addr = acpi_os_map_iomem(elog_base, elog_size); + if (!elog_addr) { + rc = -ENOMEM; + goto err_release_elog; + } rc = -ENOMEM; /* allocate buffer to save elog record */ @@ -300,6 +312,8 @@ err_release_l1_dir: if (extlog_l1_addr) acpi_os_unmap_iomem(extlog_l1_addr, l1_size); release_mem_region(l1_dirbase, l1_size); +err_release_l1_hdr: + release_mem_region(l1_dirbase, l1_hdr_size); err: pr_warn(FW_BUG "Extended error log disabled because of problems parsing f/w tables\n"); return rc; diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c index 4ec20fd56985..3fde4496f8a2 100644 --- a/drivers/acpi/acpi_pad.c +++ b/drivers/acpi/acpi_pad.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -46,10 +47,8 @@ static void power_saving_mwait_init(void) if (!boot_cpu_has(X86_FEATURE_MWAIT)) return; - if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) - return; - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &edx); if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) || !(ecx & CPUID5_ECX_INTERRUPT_BREAK)) diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 8274a17872ed..a972831dbd66 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -610,16 +610,28 @@ acpi_video_device_lcd_get_level_current(struct acpi_video_device *device, return 0; } +/** + * acpi_video_device_EDID() - Get EDID from ACPI _DDC + * @device: video output device (LCD, CRT, ..) + * @edid: address for returned EDID pointer + * @length: _DDC length to request (must be a multiple of 128) + * + * Get EDID from ACPI _DDC. On success, a pointer to the EDID data is written + * to the @edid address, and the length of the EDID is returned. The caller is + * responsible for freeing the edid pointer. + * + * Return the length of EDID (positive value) on success or error (negative + * value). + */ static int -acpi_video_device_EDID(struct acpi_video_device *device, - union acpi_object **edid, int length) +acpi_video_device_EDID(struct acpi_video_device *device, void **edid, int length) { - int status; + acpi_status status; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *obj; union acpi_object arg0 = { ACPI_TYPE_INTEGER }; struct acpi_object_list args = { 1, &arg0 }; - + int ret; *edid = NULL; @@ -636,16 +648,17 @@ acpi_video_device_EDID(struct acpi_video_device *device, obj = buffer.pointer; - if (obj && obj->type == ACPI_TYPE_BUFFER) - *edid = obj; - else { + if (obj && obj->type == ACPI_TYPE_BUFFER) { + *edid = kmemdup(obj->buffer.pointer, obj->buffer.length, GFP_KERNEL); + ret = *edid ? obj->buffer.length : -ENOMEM; + } else { acpi_handle_debug(device->dev->handle, "Invalid _DDC data for length %d\n", length); - status = -EFAULT; - kfree(obj); + ret = -EFAULT; } - return status; + kfree(obj); + return ret; } /* bus */ @@ -1435,9 +1448,7 @@ int acpi_video_get_edid(struct acpi_device *device, int type, int device_id, { struct acpi_video_bus *video; struct acpi_video_device *video_device; - union acpi_object *buffer = NULL; - acpi_status status; - int i, length; + int i, length, ret; if (!device || !acpi_driver_data(device)) return -EINVAL; @@ -1477,16 +1488,10 @@ int acpi_video_get_edid(struct acpi_device *device, int type, int device_id, } for (length = 512; length > 0; length -= 128) { - status = acpi_video_device_EDID(video_device, &buffer, - length); - if (ACPI_SUCCESS(status)) - break; + ret = acpi_video_device_EDID(video_device, edid, length); + if (ret > 0) + return ret; } - if (!length) - continue; - - *edid = buffer->buffer.pointer; - return length; } return -ENODEV; diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h index 79bbfe00d241..b8543a34caea 100644 --- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -103,8 +103,6 @@ acpi_hw_get_gpe_status(struct acpi_gpe_event_info *gpe_event_info, acpi_status acpi_hw_enable_all_runtime_gpes(void); -acpi_status acpi_hw_enable_all_wakeup_gpes(void); - u8 acpi_hw_check_all_gpes(acpi_handle gpe_skip_device, u32 gpe_skip_number); acpi_status diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 07789f0b59bc..b72772494655 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -173,8 +173,6 @@ static struct gen_pool *ghes_estatus_pool; static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE]; static atomic_t ghes_estatus_cache_alloced; -static int ghes_panic_timeout __read_mostly = 30; - static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx) { phys_addr_t paddr; @@ -983,14 +981,16 @@ static void __ghes_panic(struct ghes *ghes, struct acpi_hest_generic_status *estatus, u64 buf_paddr, enum fixed_addresses fixmap_idx) { + const char *msg = GHES_PFX "Fatal hardware error"; + __ghes_print_estatus(KERN_EMERG, ghes->generic, estatus); ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx); - /* reboot to log the error! */ if (!panic_timeout) - panic_timeout = ghes_panic_timeout; - panic("Fatal hardware error!"); + pr_emerg("%s but panic disabled\n", msg); + + panic(msg); } static int ghes_proc(struct ghes *ghes) diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 3d5342f8d7b3..6760330a8af5 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -717,7 +717,7 @@ static void battery_hook_unregister_unlocked(struct acpi_battery_hook *hook) } list_del_init(&hook->list); - pr_info("extension unregistered: %s\n", hook->name); + pr_info("hook unregistered: %s\n", hook->name); } void battery_hook_unregister(struct acpi_battery_hook *hook) @@ -751,18 +751,18 @@ void battery_hook_register(struct acpi_battery_hook *hook) if (hook->add_battery(battery->bat, hook)) { /* * If a add-battery returns non-zero, - * the registration of the extension has failed, + * the registration of the hook has failed, * and we will not add it to the list of loaded * hooks. */ - pr_err("extension failed to load: %s", hook->name); + pr_err("hook failed to load: %s", hook->name); battery_hook_unregister_unlocked(hook); goto end; } power_supply_changed(battery->bat); } - pr_info("new extension: %s\n", hook->name); + pr_info("new hook: %s\n", hook->name); end: mutex_unlock(&hook_mutex); } @@ -805,10 +805,10 @@ static void battery_hook_add_battery(struct acpi_battery *battery) list_for_each_entry_safe(hook_node, tmp, &battery_hook_list, list) { if (hook_node->add_battery(battery->bat, hook_node)) { /* - * The notification of the extensions has failed, to - * prevent further errors we will unload the extension. + * The notification of the hook has failed, to + * prevent further errors we will unload the hook. */ - pr_err("error in extension, unloading: %s", + pr_err("error in hook, unloading: %s", hook_node->name); battery_hook_unregister_unlocked(hook_node); } diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c index d1d9c9289087..35ece8e9f15d 100644 --- a/drivers/acpi/bgrt.c +++ b/drivers/acpi/bgrt.c @@ -29,7 +29,7 @@ BGRT_SHOW(type, image_type); BGRT_SHOW(xoffset, image_offset_x); BGRT_SHOW(yoffset, image_offset_y); -static BIN_ATTR_SIMPLE_RO(image); +static __ro_after_init BIN_ATTR_SIMPLE_RO(image); static struct attribute *bgrt_attributes[] = { &bgrt_attr_version.attr, @@ -40,14 +40,14 @@ static struct attribute *bgrt_attributes[] = { NULL, }; -static struct bin_attribute *bgrt_bin_attributes[] = { +static const struct bin_attribute *const bgrt_bin_attributes[] = { &bin_attr_image, NULL, }; static const struct attribute_group bgrt_attribute_group = { .attrs = bgrt_attributes, - .bin_attrs = bgrt_bin_attributes, + .bin_attrs_new = bgrt_bin_attributes, }; int __init acpi_parse_bgrt(struct acpi_table_header *table) diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c index 624fce67ce43..952216c67d58 100644 --- a/drivers/acpi/dptf/dptf_pch_fivr.c +++ b/drivers/acpi/dptf/dptf_pch_fivr.c @@ -152,6 +152,7 @@ static const struct acpi_device_id pch_fivr_device_ids[] = { {"INTC1064", 0}, {"INTC106B", 0}, {"INTC10A3", 0}, + {"INTC10D7", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, pch_fivr_device_ids); diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c index 3d3edd81b172..e8caf4106ff9 100644 --- a/drivers/acpi/dptf/dptf_power.c +++ b/drivers/acpi/dptf/dptf_power.c @@ -236,6 +236,8 @@ static const struct acpi_device_id int3407_device_ids[] = { {"INTC106D", 0}, {"INTC10A4", 0}, {"INTC10A5", 0}, + {"INTC10D8", 0}, + {"INTC10D9", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, int3407_device_ids); diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c index 014ada759954..aef7aca2161d 100644 --- a/drivers/acpi/dptf/int340x_thermal.c +++ b/drivers/acpi/dptf/int340x_thermal.c @@ -55,6 +55,12 @@ static const struct acpi_device_id int340x_thermal_device_ids[] = { {"INTC10A3"}, {"INTC10A4"}, {"INTC10A5"}, + {"INTC10D4"}, + {"INTC10D5"}, + {"INTC10D6"}, + {"INTC10D7"}, + {"INTC10D8"}, + {"INTC10D9"}, {""}, }; diff --git a/drivers/acpi/fan.h b/drivers/acpi/fan.h index db25a3898af7..488b51e2cb31 100644 --- a/drivers/acpi/fan.h +++ b/drivers/acpi/fan.h @@ -19,6 +19,7 @@ {"INTC1063", }, /* Fan for Meteor Lake generation */ \ {"INTC106A", }, /* Fan for Lunar Lake generation */ \ {"INTC10A2", }, /* Fan for Raptor Lake generation */ \ + {"INTC10D6", }, /* Fan for Panther Lake generation */ \ {"PNP0C0B", } /* Generic ACPI fan */ #define ACPI_FPS_NAME_LEN 20 diff --git a/drivers/acpi/fan_core.c b/drivers/acpi/fan_core.c index 3ea9cfcff46e..10016f52f4f4 100644 --- a/drivers/acpi/fan_core.c +++ b/drivers/acpi/fan_core.c @@ -371,19 +371,25 @@ static int acpi_fan_probe(struct platform_device *pdev) result = sysfs_create_link(&pdev->dev.kobj, &cdev->device.kobj, "thermal_cooling"); - if (result) + if (result) { dev_err(&pdev->dev, "Failed to create sysfs link 'thermal_cooling'\n"); + goto err_unregister; + } result = sysfs_create_link(&cdev->device.kobj, &pdev->dev.kobj, "device"); if (result) { dev_err(&pdev->dev, "Failed to create sysfs link 'device'\n"); - goto err_end; + goto err_remove_link; } return 0; +err_remove_link: + sysfs_remove_link(&pdev->dev.kobj, "thermal_cooling"); +err_unregister: + thermal_cooling_device_unregister(cdev); err_end: if (fan->acpi4) acpi_fan_delete_attributes(device); diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c index 92b658f92dc0..5b85989f96be 100644 --- a/drivers/acpi/mipi-disco-img.c +++ b/drivers/acpi/mipi-disco-img.c @@ -624,8 +624,7 @@ static void init_crs_csi2_swnodes(struct crs_csi2 *csi2) if (!fwnode_property_present(adev_fwnode, "rotation")) { struct acpi_pld_info *pld; - status = acpi_get_physical_device_location(handle, &pld); - if (ACPI_SUCCESS(status)) { + if (acpi_get_physical_device_location(handle, &pld)) { swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_ROTATION)] = PROPERTY_ENTRY_U32("rotation", pld->rotation * 45U); diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index 80a3481c0470..bfbb08b1e6af 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -442,9 +442,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header, return -EINVAL; } - pr_info("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n", - hmat_loc->flags, hmat_data_type(type), ipds, tpds, - hmat_loc->entry_base_unit); + pr_debug("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n", + hmat_loc->flags, hmat_data_type(type), ipds, tpds, + hmat_loc->entry_base_unit); inits = (u32 *)(hmat_loc + 1); targs = inits + ipds; @@ -455,9 +455,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header, value = hmat_normalize(entries[init * tpds + targ], hmat_loc->entry_base_unit, type); - pr_info(" Initiator-Target[%u-%u]:%u%s\n", - inits[init], targs[targ], value, - hmat_data_type_suffix(type)); + pr_debug(" Initiator-Target[%u-%u]:%u%s\n", + inits[init], targs[targ], value, + hmat_data_type_suffix(type)); hmat_update_target(targs[targ], inits[init], mem_hier, type, value); @@ -485,9 +485,9 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header, } attrs = cache->cache_attributes; - pr_info("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n", - cache->memory_PD, cache->cache_size, attrs, - cache->number_of_SMBIOShandles); + pr_debug("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n", + cache->memory_PD, cache->cache_size, attrs, + cache->number_of_SMBIOShandles); target = find_mem_target(cache->memory_PD); if (!target) @@ -546,9 +546,9 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade } if (hmat_revision == 1) - pr_info("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n", - p->reserved3, p->reserved4, p->flags, p->processor_PD, - p->memory_PD); + pr_debug("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n", + p->reserved3, p->reserved4, p->flags, p->processor_PD, + p->memory_PD); else pr_info("Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n", p->flags, p->processor_PD, p->memory_PD); diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index bec0dcd1f9c3..00ac0d7bb8c9 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -81,6 +81,101 @@ int acpi_map_pxm_to_node(int pxm) } EXPORT_SYMBOL(acpi_map_pxm_to_node); +#ifdef CONFIG_NUMA_EMU +/* + * Take max_nid - 1 fake-numa nodes into account in both + * pxm_to_node_map()/node_to_pxm_map[] tables. + */ +int __init fix_pxm_node_maps(int max_nid) +{ + static int pxm_to_node_map_copy[MAX_PXM_DOMAINS] __initdata + = { [0 ... MAX_PXM_DOMAINS - 1] = NUMA_NO_NODE }; + static int node_to_pxm_map_copy[MAX_NUMNODES] __initdata + = { [0 ... MAX_NUMNODES - 1] = PXM_INVAL }; + int i, j, index = -1, count = 0; + nodemask_t nodes_to_enable; + + if (numa_off) + return -1; + + /* no or incomplete node/PXM mapping set, nothing to do */ + if (srat_disabled()) + return 0; + + /* find fake nodes PXM mapping */ + for (i = 0; i < MAX_NUMNODES; i++) { + if (node_to_pxm_map[i] != PXM_INVAL) { + for (j = 0; j <= max_nid; j++) { + if ((emu_nid_to_phys[j] == i) && + WARN(node_to_pxm_map_copy[j] != PXM_INVAL, + "Node %d is already binded to PXM %d\n", + j, node_to_pxm_map_copy[j])) + return -1; + if (emu_nid_to_phys[j] == i) { + node_to_pxm_map_copy[j] = + node_to_pxm_map[i]; + if (j > index) + index = j; + count++; + } + } + } + } + if (index == -1) { + pr_debug("No node/PXM mapping has been set\n"); + /* nothing more to be done */ + return 0; + } + if (WARN(index != max_nid, "%d max nid when expected %d\n", + index, max_nid)) + return -1; + + nodes_clear(nodes_to_enable); + + /* map phys nodes not used for fake nodes */ + for (i = 0; i < MAX_NUMNODES; i++) { + if (node_to_pxm_map[i] != PXM_INVAL) { + for (j = 0; j <= max_nid; j++) + if (emu_nid_to_phys[j] == i) + break; + /* fake nodes PXM mapping has been done */ + if (j <= max_nid) + continue; + /* find first hole */ + for (j = 0; + j < MAX_NUMNODES && + node_to_pxm_map_copy[j] != PXM_INVAL; + j++) + ; + if (WARN(j == MAX_NUMNODES, + "Number of nodes exceeds MAX_NUMNODES\n")) + return -1; + node_to_pxm_map_copy[j] = node_to_pxm_map[i]; + node_set(j, nodes_to_enable); + count++; + } + } + + /* creating reverse mapping in pxm_to_node_map[] */ + for (i = 0; i < MAX_NUMNODES; i++) + if (node_to_pxm_map_copy[i] != PXM_INVAL && + pxm_to_node_map_copy[node_to_pxm_map_copy[i]] == NUMA_NO_NODE) + pxm_to_node_map_copy[node_to_pxm_map_copy[i]] = i; + + /* overwrite with new mapping */ + for (i = 0; i < MAX_NUMNODES; i++) { + node_to_pxm_map[i] = node_to_pxm_map_copy[i]; + pxm_to_node_map[i] = pxm_to_node_map_copy[i]; + } + + /* enable other nodes found in PXM for hotplug */ + nodes_or(numa_nodes_parsed, nodes_to_enable, numa_nodes_parsed); + + pr_debug("found %d total number of nodes\n", count); + return 0; +} +#endif + static void __init acpi_table_print_srat_entry(struct acpi_subtable_header *header) { diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index fed446aace42..5ff343096ece 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -607,7 +607,27 @@ acpi_status acpi_os_remove_interrupt_handler(u32 gsi, acpi_osd_handler handler) void acpi_os_sleep(u64 ms) { - msleep(ms); + u64 usec = ms * USEC_PER_MSEC, delta_us = 50; + + /* + * Use a hrtimer because the timer wheel timers are optimized for + * cancelation before they expire and this timer is not going to be + * canceled. + * + * Set the delta between the requested sleep time and the effective + * deadline to at least 50 us in case there is an opportunity for timer + * coalescing. + * + * Moreover, longer sleeps can be assumed to need somewhat less timer + * precision, so sacrifice some of it for making the timer a more likely + * candidate for coalescing by setting the delta to 1% of the sleep time + * if it is above 5 ms (this value is chosen so that the delta is a + * continuous function of the sleep time). + */ + if (ms > 5) + delta_us = (USEC_PER_MSEC / 100) * ms; + + usleep_range(usec, usec + delta_us); } void acpi_os_stall(u32 us) diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c index d2f7fd7743a1..fc92e43d0fe9 100644 --- a/drivers/acpi/platform_profile.c +++ b/drivers/acpi/platform_profile.c @@ -2,16 +2,28 @@ /* Platform profile sysfs interface */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include +#include #include #include #include #include -static struct platform_profile_handler *cur_profile; +#define to_pprof_handler(d) (container_of(d, struct platform_profile_handler, dev)) + static DEFINE_MUTEX(profile_lock); +struct platform_profile_handler { + const char *name; + struct device dev; + int minor; + unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; + const struct platform_profile_ops *ops; +}; + static const char * const profile_names[] = { [PLATFORM_PROFILE_LOW_POWER] = "low-power", [PLATFORM_PROFILE_COOL] = "cool", @@ -19,99 +31,373 @@ static const char * const profile_names[] = { [PLATFORM_PROFILE_BALANCED] = "balanced", [PLATFORM_PROFILE_BALANCED_PERFORMANCE] = "balanced-performance", [PLATFORM_PROFILE_PERFORMANCE] = "performance", + [PLATFORM_PROFILE_CUSTOM] = "custom", }; static_assert(ARRAY_SIZE(profile_names) == PLATFORM_PROFILE_LAST); -static ssize_t platform_profile_choices_show(struct device *dev, - struct device_attribute *attr, - char *buf) +static DEFINE_IDA(platform_profile_ida); + +/** + * _commmon_choices_show - Show the available profile choices + * @choices: The available profile choices + * @buf: The buffer to write to + * + * Return: The number of bytes written + */ +static ssize_t _commmon_choices_show(unsigned long *choices, char *buf) { - int len = 0; - int err, i; + int i, len = 0; - err = mutex_lock_interruptible(&profile_lock); - if (err) - return err; - - if (!cur_profile) { - mutex_unlock(&profile_lock); - return -ENODEV; - } - - for_each_set_bit(i, cur_profile->choices, PLATFORM_PROFILE_LAST) { + for_each_set_bit(i, choices, PLATFORM_PROFILE_LAST) { if (len == 0) len += sysfs_emit_at(buf, len, "%s", profile_names[i]); else len += sysfs_emit_at(buf, len, " %s", profile_names[i]); } len += sysfs_emit_at(buf, len, "\n"); - mutex_unlock(&profile_lock); + return len; } -static ssize_t platform_profile_show(struct device *dev, - struct device_attribute *attr, - char *buf) +/** + * _store_class_profile - Set the profile for a class device + * @dev: The class device + * @data: The profile to set + * + * Return: 0 on success, -errno on failure + */ +static int _store_class_profile(struct device *dev, void *data) { - enum platform_profile_option profile = PLATFORM_PROFILE_BALANCED; + struct platform_profile_handler *handler; + int *bit = (int *)data; + + lockdep_assert_held(&profile_lock); + handler = to_pprof_handler(dev); + if (!test_bit(*bit, handler->choices)) + return -EOPNOTSUPP; + + return handler->ops->profile_set(dev, *bit); +} + +/** + * _notify_class_profile - Notify the class device of a profile change + * @dev: The class device + * @data: Unused + * + * Return: 0 on success, -errno on failure + */ +static int _notify_class_profile(struct device *dev, void *data) +{ + struct platform_profile_handler *handler = to_pprof_handler(dev); + + lockdep_assert_held(&profile_lock); + sysfs_notify(&handler->dev.kobj, NULL, "profile"); + kobject_uevent(&handler->dev.kobj, KOBJ_CHANGE); + + return 0; +} + +/** + * get_class_profile - Show the current profile for a class device + * @dev: The class device + * @profile: The profile to return + * + * Return: 0 on success, -errno on failure + */ +static int get_class_profile(struct device *dev, + enum platform_profile_option *profile) +{ + struct platform_profile_handler *handler; + enum platform_profile_option val; int err; - err = mutex_lock_interruptible(&profile_lock); - if (err) + lockdep_assert_held(&profile_lock); + handler = to_pprof_handler(dev); + err = handler->ops->profile_get(dev, &val); + if (err) { + pr_err("Failed to get profile for handler %s\n", handler->name); return err; - - if (!cur_profile) { - mutex_unlock(&profile_lock); - return -ENODEV; } - err = cur_profile->profile_get(cur_profile, &profile); - mutex_unlock(&profile_lock); - if (err) - return err; + if (WARN_ON(val >= PLATFORM_PROFILE_LAST)) + return -EINVAL; + *profile = val; - /* Check that profile is valid index */ - if (WARN_ON((profile < 0) || (profile >= ARRAY_SIZE(profile_names)))) - return -EIO; + return 0; +} + +/** + * name_show - Show the name of the profile handler + * @dev: The device + * @attr: The attribute + * @buf: The buffer to write to + * + * Return: The number of bytes written + */ +static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct platform_profile_handler *handler = to_pprof_handler(dev); + + return sysfs_emit(buf, "%s\n", handler->name); +} +static DEVICE_ATTR_RO(name); + +/** + * choices_show - Show the available profile choices + * @dev: The device + * @attr: The attribute + * @buf: The buffer to write to + * + * Return: The number of bytes written + */ +static ssize_t choices_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct platform_profile_handler *handler = to_pprof_handler(dev); + + return _commmon_choices_show(handler->choices, buf); +} +static DEVICE_ATTR_RO(choices); + +/** + * profile_show - Show the current profile for a class device + * @dev: The device + * @attr: The attribute + * @buf: The buffer to write to + * + * Return: The number of bytes written + */ +static ssize_t profile_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + enum platform_profile_option profile = PLATFORM_PROFILE_LAST; + int err; + + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) { + err = get_class_profile(dev, &profile); + if (err) + return err; + } return sysfs_emit(buf, "%s\n", profile_names[profile]); } -static ssize_t platform_profile_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +/** + * profile_store - Set the profile for a class device + * @dev: The device + * @attr: The attribute + * @buf: The buffer to read from + * @count: The number of bytes to read + * + * Return: The number of bytes read + */ +static ssize_t profile_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { - int err, i; + int index, ret; - err = mutex_lock_interruptible(&profile_lock); + index = sysfs_match_string(profile_names, buf); + if (index < 0) + return -EINVAL; + + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) { + ret = _store_class_profile(dev, &index); + if (ret) + return ret; + } + + sysfs_notify(acpi_kobj, NULL, "platform_profile"); + + return count; +} +static DEVICE_ATTR_RW(profile); + +static struct attribute *profile_attrs[] = { + &dev_attr_name.attr, + &dev_attr_choices.attr, + &dev_attr_profile.attr, + NULL +}; +ATTRIBUTE_GROUPS(profile); + +static void pprof_device_release(struct device *dev) +{ + struct platform_profile_handler *pprof = to_pprof_handler(dev); + + kfree(pprof); +} + +static const struct class platform_profile_class = { + .name = "platform-profile", + .dev_groups = profile_groups, + .dev_release = pprof_device_release, +}; + +/** + * _aggregate_choices - Aggregate the available profile choices + * @dev: The device + * @data: The available profile choices + * + * Return: 0 on success, -errno on failure + */ +static int _aggregate_choices(struct device *dev, void *data) +{ + struct platform_profile_handler *handler; + unsigned long *aggregate = data; + + lockdep_assert_held(&profile_lock); + handler = to_pprof_handler(dev); + if (test_bit(PLATFORM_PROFILE_LAST, aggregate)) + bitmap_copy(aggregate, handler->choices, PLATFORM_PROFILE_LAST); + else + bitmap_and(aggregate, handler->choices, aggregate, PLATFORM_PROFILE_LAST); + + return 0; +} + +/** + * platform_profile_choices_show - Show the available profile choices for legacy sysfs interface + * @dev: The device + * @attr: The attribute + * @buf: The buffer to write to + * + * Return: The number of bytes written + */ +static ssize_t platform_profile_choices_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + unsigned long aggregate[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; + int err; + + set_bit(PLATFORM_PROFILE_LAST, aggregate); + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) { + err = class_for_each_device(&platform_profile_class, NULL, + aggregate, _aggregate_choices); + if (err) + return err; + } + + /* no profile handler registered any more */ + if (bitmap_empty(aggregate, PLATFORM_PROFILE_LAST)) + return -EINVAL; + + return _commmon_choices_show(aggregate, buf); +} + +/** + * _aggregate_profiles - Aggregate the profiles for legacy sysfs interface + * @dev: The device + * @data: The profile to return + * + * Return: 0 on success, -errno on failure + */ +static int _aggregate_profiles(struct device *dev, void *data) +{ + enum platform_profile_option *profile = data; + enum platform_profile_option val; + int err; + + err = get_class_profile(dev, &val); if (err) return err; - if (!cur_profile) { - mutex_unlock(&profile_lock); - return -ENODEV; + if (*profile != PLATFORM_PROFILE_LAST && *profile != val) + *profile = PLATFORM_PROFILE_CUSTOM; + else + *profile = val; + + return 0; +} + +/** + * _store_and_notify - Store and notify a class from legacy sysfs interface + * @dev: The device + * @data: The profile to return + * + * Return: 0 on success, -errno on failure + */ +static int _store_and_notify(struct device *dev, void *data) +{ + enum platform_profile_option *profile = data; + int err; + + err = _store_class_profile(dev, profile); + if (err) + return err; + return _notify_class_profile(dev, NULL); +} + +/** + * platform_profile_show - Show the current profile for legacy sysfs interface + * @dev: The device + * @attr: The attribute + * @buf: The buffer to write to + * + * Return: The number of bytes written + */ +static ssize_t platform_profile_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + enum platform_profile_option profile = PLATFORM_PROFILE_LAST; + int err; + + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) { + err = class_for_each_device(&platform_profile_class, NULL, + &profile, _aggregate_profiles); + if (err) + return err; } + /* no profile handler registered any more */ + if (profile == PLATFORM_PROFILE_LAST) + return -EINVAL; + + return sysfs_emit(buf, "%s\n", profile_names[profile]); +} + +/** + * platform_profile_store - Set the profile for legacy sysfs interface + * @dev: The device + * @attr: The attribute + * @buf: The buffer to read from + * @count: The number of bytes to read + * + * Return: The number of bytes read + */ +static ssize_t platform_profile_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; + int ret; + int i; + /* Scan for a matching profile */ i = sysfs_match_string(profile_names, buf); - if (i < 0) { - mutex_unlock(&profile_lock); + if (i < 0 || i == PLATFORM_PROFILE_CUSTOM) return -EINVAL; + set_bit(PLATFORM_PROFILE_LAST, choices); + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) { + ret = class_for_each_device(&platform_profile_class, NULL, + choices, _aggregate_choices); + if (ret) + return ret; + if (!test_bit(i, choices)) + return -EOPNOTSUPP; + + ret = class_for_each_device(&platform_profile_class, NULL, &i, + _store_and_notify); + if (ret) + return ret; } - /* Check that platform supports this profile choice */ - if (!test_bit(i, cur_profile->choices)) { - mutex_unlock(&profile_lock); - return -EOPNOTSUPP; - } + sysfs_notify(acpi_kobj, NULL, "platform_profile"); - err = cur_profile->profile_set(cur_profile, i); - if (!err) - sysfs_notify(acpi_kobj, NULL, "platform_profile"); - - mutex_unlock(&profile_lock); - if (err) - return err; return count; } @@ -124,98 +410,249 @@ static struct attribute *platform_profile_attrs[] = { NULL }; +static int profile_class_registered(struct device *dev, const void *data) +{ + return 1; +} + +static umode_t profile_class_is_visible(struct kobject *kobj, struct attribute *attr, int idx) +{ + if (!class_find_device(&platform_profile_class, NULL, NULL, profile_class_registered)) + return 0; + return attr->mode; +} + static const struct attribute_group platform_profile_group = { - .attrs = platform_profile_attrs + .attrs = platform_profile_attrs, + .is_visible = profile_class_is_visible, }; -void platform_profile_notify(void) +/** + * platform_profile_notify - Notify class device and legacy sysfs interface + * @dev: The class device + */ +void platform_profile_notify(struct device *dev) { - if (!cur_profile) - return; + scoped_cond_guard(mutex_intr, return, &profile_lock) { + _notify_class_profile(dev, NULL); + } sysfs_notify(acpi_kobj, NULL, "platform_profile"); } EXPORT_SYMBOL_GPL(platform_profile_notify); +/** + * platform_profile_cycle - Cycles profiles available on all registered class devices + * + * Return: 0 on success, -errno on failure + */ int platform_profile_cycle(void) { - enum platform_profile_option profile; - enum platform_profile_option next; + enum platform_profile_option next = PLATFORM_PROFILE_LAST; + enum platform_profile_option profile = PLATFORM_PROFILE_LAST; + unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; int err; - err = mutex_lock_interruptible(&profile_lock); - if (err) - return err; + set_bit(PLATFORM_PROFILE_LAST, choices); + scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) { + err = class_for_each_device(&platform_profile_class, NULL, + &profile, _aggregate_profiles); + if (err) + return err; - if (!cur_profile) { - mutex_unlock(&profile_lock); - return -ENODEV; + if (profile == PLATFORM_PROFILE_CUSTOM || + profile == PLATFORM_PROFILE_LAST) + return -EINVAL; + + err = class_for_each_device(&platform_profile_class, NULL, + choices, _aggregate_choices); + if (err) + return err; + + /* never iterate into a custom if all drivers supported it */ + clear_bit(PLATFORM_PROFILE_CUSTOM, choices); + + next = find_next_bit_wrap(choices, + PLATFORM_PROFILE_LAST, + profile + 1); + + err = class_for_each_device(&platform_profile_class, NULL, &next, + _store_and_notify); + + if (err) + return err; } - err = cur_profile->profile_get(cur_profile, &profile); - if (err) { - mutex_unlock(&profile_lock); - return err; - } + sysfs_notify(acpi_kobj, NULL, "platform_profile"); - next = find_next_bit_wrap(cur_profile->choices, PLATFORM_PROFILE_LAST, - profile + 1); - - if (WARN_ON(next == PLATFORM_PROFILE_LAST)) { - mutex_unlock(&profile_lock); - return -EINVAL; - } - - err = cur_profile->profile_set(cur_profile, next); - mutex_unlock(&profile_lock); - - if (!err) - sysfs_notify(acpi_kobj, NULL, "platform_profile"); - - return err; + return 0; } EXPORT_SYMBOL_GPL(platform_profile_cycle); -int platform_profile_register(struct platform_profile_handler *pprof) +/** + * platform_profile_register - Creates and registers a platform profile class device + * @dev: Parent device + * @name: Name of the class device + * @drvdata: Driver data that will be attached to the class device + * @ops: Platform profile's mandatory operations + * + * Return: pointer to the new class device on success, ERR_PTR on failure + */ +struct device *platform_profile_register(struct device *dev, const char *name, + void *drvdata, + const struct platform_profile_ops *ops) { + struct device *ppdev; + int minor; int err; - mutex_lock(&profile_lock); - /* We can only have one active profile */ - if (cur_profile) { - mutex_unlock(&profile_lock); - return -EEXIST; - } + /* Sanity check */ + if (WARN_ON_ONCE(!dev || !name || !ops || !ops->profile_get || + !ops->profile_set || !ops->probe)) + return ERR_PTR(-EINVAL); - /* Sanity check the profile handler field are set */ - if (!pprof || bitmap_empty(pprof->choices, PLATFORM_PROFILE_LAST) || - !pprof->profile_set || !pprof->profile_get) { - mutex_unlock(&profile_lock); - return -EINVAL; - } + struct platform_profile_handler *pprof __free(kfree) = kzalloc( + sizeof(*pprof), GFP_KERNEL); + if (!pprof) + return ERR_PTR(-ENOMEM); - err = sysfs_create_group(acpi_kobj, &platform_profile_group); + err = ops->probe(drvdata, pprof->choices); if (err) { - mutex_unlock(&profile_lock); - return err; + dev_err(dev, "platform_profile probe failed\n"); + return ERR_PTR(err); } - cur_profile = pprof; - mutex_unlock(&profile_lock); - return 0; + if (bitmap_empty(pprof->choices, PLATFORM_PROFILE_LAST)) { + dev_err(dev, "Failed to register platform_profile class device with empty choices\n"); + return ERR_PTR(-EINVAL); + } + + guard(mutex)(&profile_lock); + + /* create class interface for individual handler */ + minor = ida_alloc(&platform_profile_ida, GFP_KERNEL); + if (minor < 0) + return ERR_PTR(minor); + + pprof->name = name; + pprof->ops = ops; + pprof->minor = minor; + pprof->dev.class = &platform_profile_class; + pprof->dev.parent = dev; + dev_set_drvdata(&pprof->dev, drvdata); + dev_set_name(&pprof->dev, "platform-profile-%d", pprof->minor); + /* device_register() takes ownership of pprof/ppdev */ + ppdev = &no_free_ptr(pprof)->dev; + err = device_register(ppdev); + if (err) { + put_device(ppdev); + goto cleanup_ida; + } + + sysfs_notify(acpi_kobj, NULL, "platform_profile"); + + err = sysfs_update_group(acpi_kobj, &platform_profile_group); + if (err) + goto cleanup_cur; + + return ppdev; + +cleanup_cur: + device_unregister(ppdev); + +cleanup_ida: + ida_free(&platform_profile_ida, minor); + + return ERR_PTR(err); } EXPORT_SYMBOL_GPL(platform_profile_register); -int platform_profile_remove(void) +/** + * platform_profile_remove - Unregisters a platform profile class device + * @dev: Class device + * + * Return: 0 + */ +int platform_profile_remove(struct device *dev) { - sysfs_remove_group(acpi_kobj, &platform_profile_group); + struct platform_profile_handler *pprof = to_pprof_handler(dev); + int id; + guard(mutex)(&profile_lock); + + id = pprof->minor; + device_unregister(&pprof->dev); + ida_free(&platform_profile_ida, id); + + sysfs_notify(acpi_kobj, NULL, "platform_profile"); + + sysfs_update_group(acpi_kobj, &platform_profile_group); - mutex_lock(&profile_lock); - cur_profile = NULL; - mutex_unlock(&profile_lock); return 0; } EXPORT_SYMBOL_GPL(platform_profile_remove); +static void devm_platform_profile_release(struct device *dev, void *res) +{ + struct device **ppdev = res; + + platform_profile_remove(*ppdev); +} + +/** + * devm_platform_profile_register - Device managed version of platform_profile_register + * @dev: Parent device + * @name: Name of the class device + * @drvdata: Driver data that will be attached to the class device + * @ops: Platform profile's mandatory operations + * + * Return: pointer to the new class device on success, ERR_PTR on failure + */ +struct device *devm_platform_profile_register(struct device *dev, const char *name, + void *drvdata, + const struct platform_profile_ops *ops) +{ + struct device *ppdev; + struct device **dr; + + dr = devres_alloc(devm_platform_profile_release, sizeof(*dr), GFP_KERNEL); + if (!dr) + return ERR_PTR(-ENOMEM); + + ppdev = platform_profile_register(dev, name, drvdata, ops); + if (IS_ERR(ppdev)) { + devres_free(dr); + return ppdev; + } + + *dr = ppdev; + devres_add(dev, dr); + + return ppdev; +} +EXPORT_SYMBOL_GPL(devm_platform_profile_register); + +static int __init platform_profile_init(void) +{ + int err; + + err = class_register(&platform_profile_class); + if (err) + return err; + + err = sysfs_create_group(acpi_kobj, &platform_profile_group); + if (err) + class_unregister(&platform_profile_class); + + return err; +} + +static void __exit platform_profile_exit(void) +{ + sysfs_remove_group(acpi_kobj, &platform_profile_group); + class_unregister(&platform_profile_class); +} +module_init(platform_profile_init); +module_exit(platform_profile_exit); + MODULE_AUTHOR("Mark Pearson "); MODULE_DESCRIPTION("ACPI platform profile sysfs interface"); MODULE_LICENSE("GPL"); diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 80a52a4e66dd..98d93ed58315 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1492,7 +1492,7 @@ acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode) static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode) { if (!is_acpi_device_node(fwnode)) - return false; + return true; return acpi_device_is_present(to_acpi_device_node(fwnode)); } @@ -1656,6 +1656,7 @@ static int acpi_fwnode_irq_get(const struct fwnode_handle *fwnode, acpi_fwnode_device_dma_supported, \ .device_get_dma_attr = acpi_fwnode_device_get_dma_attr, \ .property_present = acpi_fwnode_property_present, \ + .property_read_bool = acpi_fwnode_property_present, \ .property_read_int_array = \ acpi_fwnode_property_read_int_array, \ .property_read_string_array = \ diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 821867de43be..90aaec923889 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -440,6 +440,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"), }, }, + { + /* Asus Vivobook X1504VAP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "X1504VAP"), + }, + }, { /* Asus Vivobook X1704VAP */ .matches = { @@ -646,6 +653,17 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = { DMI_MATCH(DMI_BOARD_NAME, "GMxHGxx"), }, }, + { + /* + * TongFang GM5HG0A in case of the SKIKK Vanaheim relabel the + * board-name is changed, so check OEM strings instead. Note + * OEM string matches are always exact matches. + * https://bugzilla.kernel.org/show_bug.cgi?id=219614 + */ + .matches = { + DMI_EXACT_MATCH(DMI_OEM_STRING, "GM5HG0A"), + }, + }, { } }; @@ -671,11 +689,11 @@ static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, for (i = 0; i < ARRAY_SIZE(override_table); i++) { const struct irq_override_cmp *entry = &override_table[i]; - if (dmi_check_system(entry->system) && - entry->irq == gsi && + if (entry->irq == gsi && entry->triggering == triggering && entry->polarity == polarity && - entry->shareable == shareable) + entry->shareable == shareable && + dmi_check_system(entry->system)) return entry->override; } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 74dcccdc6482..9f4efa8f75a6 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -723,10 +723,8 @@ int acpi_tie_acpi_dev(struct acpi_device *adev) static void acpi_store_pld_crc(struct acpi_device *adev) { struct acpi_pld_info *pld; - acpi_status status; - status = acpi_get_physical_device_location(adev->handle, &pld); - if (ACPI_FAILURE(status)) + if (!acpi_get_physical_device_location(adev->handle, &pld)) return; adev->pld_crc = crc32(~0, pld, sizeof(*pld)); @@ -1769,6 +1767,7 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device) {"CSC3557", }, {"INT33FE", }, {"INT3515", }, + {"TXNW2781", }, /* Non-conforming _HID for Cirrus Logic already released */ {"CLSA0100", }, {"CLSA0101", }, diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index 687524b50085..a48ebbf768f9 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -319,7 +319,7 @@ struct acpi_data_attr { }; static ssize_t acpi_table_show(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t offset, size_t count) { struct acpi_table_attr *table_attr = @@ -372,7 +372,7 @@ static int acpi_table_attr_init(struct kobject *tables_obj, } table_attr->attr.size = table_header->length; - table_attr->attr.read = acpi_table_show; + table_attr->attr.read_new = acpi_table_show; table_attr->attr.attr.name = table_attr->filename; table_attr->attr.attr.mode = 0400; @@ -412,7 +412,7 @@ acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context) } static ssize_t acpi_data_show(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t offset, size_t count) { struct acpi_data_attr *data_attr; @@ -495,7 +495,7 @@ static int acpi_table_data_init(struct acpi_table_header *th) if (!data_attr) return -ENOMEM; sysfs_attr_init(&data_attr->attr.attr); - data_attr->attr.read = acpi_data_show; + data_attr->attr.read_new = acpi_data_show; data_attr->attr.attr.mode = 0400; return acpi_data_objs[i].fn(th, data_attr); } diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 9e1b01c35070..2295abbecd14 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -56,7 +56,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) (struct acpi_madt_local_apic *)header; pr_debug("LAPIC (acpi_id[0x%02x] lapic_id[0x%02x] %s)\n", p->processor_id, p->id, - (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + str_enabled_disabled(p->lapic_flags & ACPI_MADT_ENABLED)); } break; @@ -66,7 +66,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) (struct acpi_madt_local_x2apic *)header; pr_debug("X2APIC (apic_id[0x%02x] uid[0x%02x] %s)\n", p->local_apic_id, p->uid, - (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + str_enabled_disabled(p->lapic_flags & ACPI_MADT_ENABLED)); } break; @@ -160,7 +160,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) (struct acpi_madt_local_sapic *)header; pr_debug("LSAPIC (acpi_id[0x%02x] lsapic_id[0x%02x] lsapic_eid[0x%02x] %s)\n", p->processor_id, p->id, p->eid, - (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + str_enabled_disabled(p->lapic_flags & ACPI_MADT_ENABLED)); } break; @@ -183,7 +183,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) pr_debug("GICC (acpi_id[0x%04x] address[%llx] MPIDR[0x%llx] %s)\n", p->uid, p->base_address, p->arm_mpidr, - (p->flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + str_enabled_disabled(p->flags & ACPI_MADT_ENABLED)); } break; @@ -218,7 +218,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) pr_debug("CORE PIC (processor_id[0x%02x] core_id[0x%02x] %s)\n", p->processor_id, p->core_id, - (p->flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + str_enabled_disabled(p->flags & ACPI_MADT_ENABLED)); } break; @@ -228,7 +228,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) pr_debug("RISC-V INTC (acpi_uid[0x%04x] hart_id[0x%llx] %s)\n", p->uid, p->hart_id, - (p->flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + str_enabled_disabled(p->flags & ACPI_MADT_ENABLED)); } break; diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 6de542d99518..526563a0d188 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -494,7 +494,7 @@ bool acpi_device_dep(acpi_handle target, acpi_handle match) } EXPORT_SYMBOL_GPL(acpi_device_dep); -acpi_status +bool acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld) { acpi_status status; @@ -502,9 +502,8 @@ acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld union acpi_object *output; status = acpi_evaluate_object(handle, "_PLD", NULL, &buffer); - if (ACPI_FAILURE(status)) - return status; + return false; output = buffer.pointer; @@ -523,7 +522,7 @@ acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld out: kfree(buffer.pointer); - return status; + return ACPI_SUCCESS(status); } EXPORT_SYMBOL(acpi_get_physical_device_location); diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index cb45ef5240da..068c1612660b 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -407,6 +407,19 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { .driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS | ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY), }, + { + /* Vexia Edu Atla 10 tablet 5V version */ + .matches = { + /* Having all 3 of these not set is somewhat unique */ + DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."), + DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."), + DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."), + /* Above strings are too generic, also match on BIOS date */ + DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"), + }, + .driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS | + ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY), + }, { /* Vexia Edu Atla 10 tablet 9V version */ .matches = { diff --git a/drivers/android/binder.c b/drivers/android/binder.c index ef353ca13c35..76052006bd87 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1971,7 +1971,7 @@ static bool binder_validate_fixup(struct binder_proc *proc, * struct binder_task_work_cb - for deferred close * * @twork: callback_head for task work - * @fd: fd to close + * @file: file to close * * Structure to pass task work to be handled after * returning from binder_ioctl() via task_work_add(). @@ -3017,8 +3017,7 @@ static void binder_transaction(struct binder_proc *proc, struct binder_context *context = proc->context; int t_debug_id = atomic_inc_return(&binder_last_id); ktime_t t_start_time = ktime_get(); - char *secctx = NULL; - u32 secctx_sz = 0; + struct lsm_context lsmctx = { }; struct list_head sgc_head; struct list_head pf_head; const void __user *user_buffer = (const void __user *) @@ -3297,8 +3296,8 @@ static void binder_transaction(struct binder_proc *proc, size_t added_size; security_cred_getsecid(proc->cred, &secid); - ret = security_secid_to_secctx(secid, &secctx, &secctx_sz); - if (ret) { + ret = security_secid_to_secctx(secid, &lsmctx); + if (ret < 0) { binder_txn_error("%d:%d failed to get security context\n", thread->pid, proc->pid); return_error = BR_FAILED_REPLY; @@ -3306,7 +3305,7 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_get_secctx_failed; } - added_size = ALIGN(secctx_sz, sizeof(u64)); + added_size = ALIGN(lsmctx.len, sizeof(u64)); extra_buffers_size += added_size; if (extra_buffers_size < added_size) { binder_txn_error("%d:%d integer overflow of extra_buffers_size\n", @@ -3340,23 +3339,23 @@ static void binder_transaction(struct binder_proc *proc, t->buffer = NULL; goto err_binder_alloc_buf_failed; } - if (secctx) { + if (lsmctx.context) { int err; size_t buf_offset = ALIGN(tr->data_size, sizeof(void *)) + ALIGN(tr->offsets_size, sizeof(void *)) + ALIGN(extra_buffers_size, sizeof(void *)) - - ALIGN(secctx_sz, sizeof(u64)); + ALIGN(lsmctx.len, sizeof(u64)); t->security_ctx = t->buffer->user_data + buf_offset; err = binder_alloc_copy_to_buffer(&target_proc->alloc, t->buffer, buf_offset, - secctx, secctx_sz); + lsmctx.context, lsmctx.len); if (err) { t->security_ctx = 0; WARN_ON(1); } - security_release_secctx(secctx, secctx_sz); - secctx = NULL; + security_release_secctx(&lsmctx); + lsmctx.context = NULL; } t->buffer->debug_id = t->debug_id; t->buffer->transaction = t; @@ -3400,7 +3399,7 @@ static void binder_transaction(struct binder_proc *proc, off_end_offset = off_start_offset + tr->offsets_size; sg_buf_offset = ALIGN(off_end_offset, sizeof(void *)); sg_buf_end_offset = sg_buf_offset + extra_buffers_size - - ALIGN(secctx_sz, sizeof(u64)); + ALIGN(lsmctx.len, sizeof(u64)); off_min = 0; for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { @@ -3779,8 +3778,8 @@ err_copy_data_failed: binder_alloc_free_buf(&target_proc->alloc, t->buffer); err_binder_alloc_buf_failed: err_bad_extra_size: - if (secctx) - security_release_secctx(secctx, secctx_sz); + if (lsmctx.context) + security_release_secctx(&lsmctx); err_get_secctx_failed: kfree(tcomplete); binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE); @@ -3801,13 +3800,13 @@ err_invalid_target_handle: } binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, - "%d:%d transaction %s to %d:%d failed %d/%d/%d, size %lld-%lld line %d\n", + "%d:%d transaction %s to %d:%d failed %d/%d/%d, code %u size %lld-%lld line %d\n", proc->pid, thread->pid, reply ? "reply" : (tr->flags & TF_ONE_WAY ? "async" : "call"), target_proc ? target_proc->pid : 0, target_thread ? target_thread->pid : 0, t_debug_id, return_error, return_error_param, - (u64)tr->data_size, (u64)tr->offsets_size, + tr->code, (u64)tr->data_size, (u64)tr->offsets_size, return_error_line); if (target_thread) @@ -6374,7 +6373,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m, seq_printf(m, " node %d", buffer->target_node->debug_id); seq_printf(m, " size %zd:%zd offset %lx\n", buffer->data_size, buffer->offsets_size, - proc->alloc.buffer - buffer->user_data); + proc->alloc.vm_start - buffer->user_data); } static void print_binder_work_ilocked(struct seq_file *m, @@ -6928,6 +6927,11 @@ const struct binder_debugfs_entry binder_debugfs_entries[] = { {} /* terminator */ }; +void binder_add_device(struct binder_device *device) +{ + hlist_add_head(&device->hlist, &binder_devices); +} + static int __init init_binder_device(const char *name) { int ret; diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index a738e7745865..fcfaf1b899c8 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -61,7 +61,7 @@ static size_t binder_alloc_buffer_size(struct binder_alloc *alloc, struct binder_buffer *buffer) { if (list_is_last(&buffer->entry, &alloc->buffers)) - return alloc->buffer + alloc->buffer_size - buffer->user_data; + return alloc->vm_start + alloc->buffer_size - buffer->user_data; return binder_buffer_next(buffer)->user_data - buffer->user_data; } @@ -169,32 +169,33 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc, { struct binder_buffer *buffer; - spin_lock(&alloc->lock); + mutex_lock(&alloc->mutex); buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr); - spin_unlock(&alloc->lock); + mutex_unlock(&alloc->mutex); return buffer; } static inline void -binder_set_installed_page(struct binder_lru_page *lru_page, +binder_set_installed_page(struct binder_alloc *alloc, + unsigned long index, struct page *page) { /* Pairs with acquire in binder_get_installed_page() */ - smp_store_release(&lru_page->page_ptr, page); + smp_store_release(&alloc->pages[index], page); } static inline struct page * -binder_get_installed_page(struct binder_lru_page *lru_page) +binder_get_installed_page(struct binder_alloc *alloc, unsigned long index) { /* Pairs with release in binder_set_installed_page() */ - return smp_load_acquire(&lru_page->page_ptr); + return smp_load_acquire(&alloc->pages[index]); } static void binder_lru_freelist_add(struct binder_alloc *alloc, unsigned long start, unsigned long end) { - struct binder_lru_page *page; unsigned long page_addr; + struct page *page; trace_binder_update_page_range(alloc, false, start, end); @@ -202,65 +203,159 @@ static void binder_lru_freelist_add(struct binder_alloc *alloc, size_t index; int ret; - index = (page_addr - alloc->buffer) / PAGE_SIZE; - page = &alloc->pages[index]; - - if (!binder_get_installed_page(page)) + index = (page_addr - alloc->vm_start) / PAGE_SIZE; + page = binder_get_installed_page(alloc, index); + if (!page) continue; trace_binder_free_lru_start(alloc, index); - ret = list_lru_add_obj(&binder_freelist, &page->lru); + ret = list_lru_add(&binder_freelist, + page_to_lru(page), + page_to_nid(page), + NULL); WARN_ON(!ret); trace_binder_free_lru_end(alloc, index); } } +static inline +void binder_alloc_set_mapped(struct binder_alloc *alloc, bool state) +{ + /* pairs with smp_load_acquire in binder_alloc_is_mapped() */ + smp_store_release(&alloc->mapped, state); +} + +static inline bool binder_alloc_is_mapped(struct binder_alloc *alloc) +{ + /* pairs with smp_store_release in binder_alloc_set_mapped() */ + return smp_load_acquire(&alloc->mapped); +} + +static struct page *binder_page_lookup(struct binder_alloc *alloc, + unsigned long addr) +{ + struct mm_struct *mm = alloc->mm; + struct page *page; + long npages = 0; + + /* + * Find an existing page in the remote mm. If missing, + * don't attempt to fault-in just propagate an error. + */ + mmap_read_lock(mm); + if (binder_alloc_is_mapped(alloc)) + npages = get_user_pages_remote(mm, addr, 1, FOLL_NOFAULT, + &page, NULL); + mmap_read_unlock(mm); + + return npages > 0 ? page : NULL; +} + +static int binder_page_insert(struct binder_alloc *alloc, + unsigned long addr, + struct page *page) +{ + struct mm_struct *mm = alloc->mm; + struct vm_area_struct *vma; + int ret = -ESRCH; + + /* attempt per-vma lock first */ + vma = lock_vma_under_rcu(mm, addr); + if (vma) { + if (binder_alloc_is_mapped(alloc)) + ret = vm_insert_page(vma, addr, page); + vma_end_read(vma); + return ret; + } + + /* fall back to mmap_lock */ + mmap_read_lock(mm); + vma = vma_lookup(mm, addr); + if (vma && binder_alloc_is_mapped(alloc)) + ret = vm_insert_page(vma, addr, page); + mmap_read_unlock(mm); + + return ret; +} + +static struct page *binder_page_alloc(struct binder_alloc *alloc, + unsigned long index) +{ + struct binder_shrinker_mdata *mdata; + struct page *page; + + page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); + if (!page) + return NULL; + + /* allocate and install shrinker metadata under page->private */ + mdata = kzalloc(sizeof(*mdata), GFP_KERNEL); + if (!mdata) { + __free_page(page); + return NULL; + } + + mdata->alloc = alloc; + mdata->page_index = index; + INIT_LIST_HEAD(&mdata->lru); + set_page_private(page, (unsigned long)mdata); + + return page; +} + +static void binder_free_page(struct page *page) +{ + kfree((struct binder_shrinker_mdata *)page_private(page)); + __free_page(page); +} + static int binder_install_single_page(struct binder_alloc *alloc, - struct binder_lru_page *lru_page, + unsigned long index, unsigned long addr) { struct page *page; - int ret = 0; + int ret; if (!mmget_not_zero(alloc->mm)) return -ESRCH; - /* - * Protected with mmap_sem in write mode as multiple tasks - * might race to install the same page. - */ - mmap_write_lock(alloc->mm); - if (binder_get_installed_page(lru_page)) - goto out; - - if (!alloc->vma) { - pr_err("%d: %s failed, no vma\n", alloc->pid, __func__); - ret = -ESRCH; - goto out; - } - - page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); + page = binder_page_alloc(alloc, index); if (!page) { - pr_err("%d: failed to allocate page\n", alloc->pid); ret = -ENOMEM; goto out; } - ret = vm_insert_page(alloc->vma, addr, page); - if (ret) { + ret = binder_page_insert(alloc, addr, page); + switch (ret) { + case -EBUSY: + /* + * EBUSY is ok. Someone installed the pte first but the + * alloc->pages[index] has not been updated yet. Discard + * our page and look up the one already installed. + */ + ret = 0; + binder_free_page(page); + page = binder_page_lookup(alloc, addr); + if (!page) { + pr_err("%d: failed to find page at offset %lx\n", + alloc->pid, addr - alloc->vm_start); + ret = -ESRCH; + break; + } + fallthrough; + case 0: + /* Mark page installation complete and safe to use */ + binder_set_installed_page(alloc, index, page); + break; + default: + binder_free_page(page); pr_err("%d: %s failed to insert page at offset %lx with %d\n", - alloc->pid, __func__, addr - alloc->buffer, ret); - __free_page(page); - ret = -ENOMEM; - goto out; + alloc->pid, __func__, addr - alloc->vm_start, ret); + break; } - - /* Mark page installation complete and safe to use */ - binder_set_installed_page(lru_page, page); out: - mmap_write_unlock(alloc->mm); mmput_async(alloc->mm); return ret; } @@ -269,7 +364,6 @@ static int binder_install_buffer_pages(struct binder_alloc *alloc, struct binder_buffer *buffer, size_t size) { - struct binder_lru_page *page; unsigned long start, final; unsigned long page_addr; @@ -280,15 +374,13 @@ static int binder_install_buffer_pages(struct binder_alloc *alloc, unsigned long index; int ret; - index = (page_addr - alloc->buffer) / PAGE_SIZE; - page = &alloc->pages[index]; - - if (binder_get_installed_page(page)) + index = (page_addr - alloc->vm_start) / PAGE_SIZE; + if (binder_get_installed_page(alloc, index)) continue; trace_binder_alloc_page_start(alloc, index); - ret = binder_install_single_page(alloc, page, page_addr); + ret = binder_install_single_page(alloc, index, page_addr); if (ret) return ret; @@ -302,8 +394,8 @@ static int binder_install_buffer_pages(struct binder_alloc *alloc, static void binder_lru_freelist_del(struct binder_alloc *alloc, unsigned long start, unsigned long end) { - struct binder_lru_page *page; unsigned long page_addr; + struct page *page; trace_binder_update_page_range(alloc, true, start, end); @@ -311,13 +403,16 @@ static void binder_lru_freelist_del(struct binder_alloc *alloc, unsigned long index; bool on_lru; - index = (page_addr - alloc->buffer) / PAGE_SIZE; - page = &alloc->pages[index]; + index = (page_addr - alloc->vm_start) / PAGE_SIZE; + page = binder_get_installed_page(alloc, index); - if (page->page_ptr) { + if (page) { trace_binder_alloc_lru_start(alloc, index); - on_lru = list_lru_del_obj(&binder_freelist, &page->lru); + on_lru = list_lru_del(&binder_freelist, + page_to_lru(page), + page_to_nid(page), + NULL); WARN_ON(!on_lru); trace_binder_alloc_lru_end(alloc, index); @@ -329,20 +424,6 @@ static void binder_lru_freelist_del(struct binder_alloc *alloc, } } -static inline void binder_alloc_set_vma(struct binder_alloc *alloc, - struct vm_area_struct *vma) -{ - /* pairs with smp_load_acquire in binder_alloc_get_vma() */ - smp_store_release(&alloc->vma, vma); -} - -static inline struct vm_area_struct *binder_alloc_get_vma( - struct binder_alloc *alloc) -{ - /* pairs with smp_store_release in binder_alloc_set_vma() */ - return smp_load_acquire(&alloc->vma); -} - static void debug_no_space_locked(struct binder_alloc *alloc) { size_t largest_alloc_size = 0; @@ -576,7 +657,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, int ret; /* Check binder_alloc is fully initialized */ - if (!binder_alloc_get_vma(alloc)) { + if (!binder_alloc_is_mapped(alloc)) { binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%d: binder_alloc_buf, no vma\n", alloc->pid); @@ -597,10 +678,10 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, if (!next) return ERR_PTR(-ENOMEM); - spin_lock(&alloc->lock); + mutex_lock(&alloc->mutex); buffer = binder_alloc_new_buf_locked(alloc, next, size, is_async); if (IS_ERR(buffer)) { - spin_unlock(&alloc->lock); + mutex_unlock(&alloc->mutex); goto out; } @@ -608,7 +689,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, buffer->offsets_size = offsets_size; buffer->extra_buffers_size = extra_buffers_size; buffer->pid = current->tgid; - spin_unlock(&alloc->lock); + mutex_unlock(&alloc->mutex); ret = binder_install_buffer_pages(alloc, buffer, size); if (ret) { @@ -674,8 +755,8 @@ static void binder_free_buf_locked(struct binder_alloc *alloc, BUG_ON(buffer->free); BUG_ON(size > buffer_size); BUG_ON(buffer->transaction != NULL); - BUG_ON(buffer->user_data < alloc->buffer); - BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size); + BUG_ON(buffer->user_data < alloc->vm_start); + BUG_ON(buffer->user_data > alloc->vm_start + alloc->buffer_size); if (buffer->async_transaction) { alloc->free_async_space += buffer_size; @@ -734,14 +815,13 @@ static struct page *binder_alloc_get_page(struct binder_alloc *alloc, pgoff_t *pgoffp) { binder_size_t buffer_space_offset = buffer_offset + - (buffer->user_data - alloc->buffer); + (buffer->user_data - alloc->vm_start); pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK; size_t index = buffer_space_offset >> PAGE_SHIFT; - struct binder_lru_page *lru_page; - lru_page = &alloc->pages[index]; *pgoffp = pgoff; - return lru_page->page_ptr; + + return alloc->pages[index]; } /** @@ -785,17 +865,17 @@ void binder_alloc_free_buf(struct binder_alloc *alloc, * We could eliminate the call to binder_alloc_clear_buf() * from binder_alloc_deferred_release() by moving this to * binder_free_buf_locked(). However, that could - * increase contention for the alloc->lock if clear_on_free - * is used frequently for large buffers. This lock is not + * increase contention for the alloc mutex if clear_on_free + * is used frequently for large buffers. The mutex is not * needed for correctness here. */ if (buffer->clear_on_free) { binder_alloc_clear_buf(alloc, buffer); buffer->clear_on_free = false; } - spin_lock(&alloc->lock); + mutex_lock(&alloc->mutex); binder_free_buf_locked(alloc, buffer); - spin_unlock(&alloc->lock); + mutex_unlock(&alloc->mutex); } /** @@ -816,7 +896,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, { struct binder_buffer *buffer; const char *failure_string; - int ret, i; + int ret; if (unlikely(vma->vm_mm != alloc->mm)) { ret = -EINVAL; @@ -834,22 +914,17 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, SZ_4M); mutex_unlock(&binder_alloc_mmap_lock); - alloc->buffer = vma->vm_start; + alloc->vm_start = vma->vm_start; alloc->pages = kvcalloc(alloc->buffer_size / PAGE_SIZE, sizeof(alloc->pages[0]), GFP_KERNEL); - if (alloc->pages == NULL) { + if (!alloc->pages) { ret = -ENOMEM; failure_string = "alloc page array"; goto err_alloc_pages_failed; } - for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { - alloc->pages[i].alloc = alloc; - INIT_LIST_HEAD(&alloc->pages[i].lru); - } - buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); if (!buffer) { ret = -ENOMEM; @@ -857,14 +932,14 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, goto err_alloc_buf_struct_failed; } - buffer->user_data = alloc->buffer; + buffer->user_data = alloc->vm_start; list_add(&buffer->entry, &alloc->buffers); buffer->free = 1; binder_insert_free_buffer(alloc, buffer); alloc->free_async_space = alloc->buffer_size / 2; /* Signal binder_alloc is fully initialized */ - binder_alloc_set_vma(alloc, vma); + binder_alloc_set_mapped(alloc, true); return 0; @@ -872,7 +947,7 @@ err_alloc_buf_struct_failed: kvfree(alloc->pages); alloc->pages = NULL; err_alloc_pages_failed: - alloc->buffer = 0; + alloc->vm_start = 0; mutex_lock(&binder_alloc_mmap_lock); alloc->buffer_size = 0; err_already_mapped: @@ -893,8 +968,8 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) struct binder_buffer *buffer; buffers = 0; - spin_lock(&alloc->lock); - BUG_ON(alloc->vma); + mutex_lock(&alloc->mutex); + BUG_ON(alloc->mapped); while ((n = rb_first(&alloc->allocated_buffers))) { buffer = rb_entry(n, struct binder_buffer, rb_node); @@ -925,22 +1000,26 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) int i; for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { + struct page *page; bool on_lru; - if (!alloc->pages[i].page_ptr) + page = binder_get_installed_page(alloc, i); + if (!page) continue; - on_lru = list_lru_del_obj(&binder_freelist, - &alloc->pages[i].lru); + on_lru = list_lru_del(&binder_freelist, + page_to_lru(page), + page_to_nid(page), + NULL); binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, "%s: %d: page %d %s\n", __func__, alloc->pid, i, on_lru ? "on lru" : "active"); - __free_page(alloc->pages[i].page_ptr); + binder_free_page(page); page_count++; } } - spin_unlock(&alloc->lock); + mutex_unlock(&alloc->mutex); kvfree(alloc->pages); if (alloc->mm) mmdrop(alloc->mm); @@ -964,17 +1043,17 @@ void binder_alloc_print_allocated(struct seq_file *m, struct binder_buffer *buffer; struct rb_node *n; - spin_lock(&alloc->lock); + mutex_lock(&alloc->mutex); for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) { buffer = rb_entry(n, struct binder_buffer, rb_node); seq_printf(m, " buffer %d: %lx size %zd:%zd:%zd %s\n", buffer->debug_id, - buffer->user_data - alloc->buffer, + buffer->user_data - alloc->vm_start, buffer->data_size, buffer->offsets_size, buffer->extra_buffers_size, buffer->transaction ? "active" : "delivered"); } - spin_unlock(&alloc->lock); + mutex_unlock(&alloc->mutex); } /** @@ -985,29 +1064,29 @@ void binder_alloc_print_allocated(struct seq_file *m, void binder_alloc_print_pages(struct seq_file *m, struct binder_alloc *alloc) { - struct binder_lru_page *page; + struct page *page; int i; int active = 0; int lru = 0; int free = 0; - spin_lock(&alloc->lock); + mutex_lock(&alloc->mutex); /* * Make sure the binder_alloc is fully initialized, otherwise we might * read inconsistent state. */ - if (binder_alloc_get_vma(alloc) != NULL) { + if (binder_alloc_is_mapped(alloc)) { for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { - page = &alloc->pages[i]; - if (!page->page_ptr) + page = binder_get_installed_page(alloc, i); + if (!page) free++; - else if (list_empty(&page->lru)) + else if (list_empty(page_to_lru(page))) active++; else lru++; } } - spin_unlock(&alloc->lock); + mutex_unlock(&alloc->mutex); seq_printf(m, " pages: %d:%d:%d\n", active, lru, free); seq_printf(m, " pages high watermark: %zu\n", alloc->pages_high); } @@ -1023,10 +1102,10 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) struct rb_node *n; int count = 0; - spin_lock(&alloc->lock); + mutex_lock(&alloc->mutex); for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n)) count++; - spin_unlock(&alloc->lock); + mutex_unlock(&alloc->mutex); return count; } @@ -1036,12 +1115,12 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) * @alloc: binder_alloc for this proc * * Called from binder_vma_close() when releasing address space. - * Clears alloc->vma to prevent new incoming transactions from + * Clears alloc->mapped to prevent new incoming transactions from * allocating more buffers. */ void binder_alloc_vma_close(struct binder_alloc *alloc) { - binder_alloc_set_vma(alloc, NULL); + binder_alloc_set_mapped(alloc, false); } /** @@ -1058,39 +1137,50 @@ enum lru_status binder_alloc_free_page(struct list_head *item, void *cb_arg) __must_hold(&lru->lock) { - struct binder_lru_page *page = container_of(item, typeof(*page), lru); - struct binder_alloc *alloc = page->alloc; + struct binder_shrinker_mdata *mdata = container_of(item, typeof(*mdata), lru); + struct binder_alloc *alloc = mdata->alloc; struct mm_struct *mm = alloc->mm; struct vm_area_struct *vma; struct page *page_to_free; unsigned long page_addr; + int mm_locked = 0; size_t index; if (!mmget_not_zero(mm)) goto err_mmget; - if (!mmap_read_trylock(mm)) - goto err_mmap_read_lock_failed; - if (!spin_trylock(&alloc->lock)) - goto err_get_alloc_lock_failed; - if (!page->page_ptr) - goto err_page_already_freed; - index = page - alloc->pages; - page_addr = alloc->buffer + index * PAGE_SIZE; + index = mdata->page_index; + page_addr = alloc->vm_start + index * PAGE_SIZE; - vma = vma_lookup(mm, page_addr); - if (vma && vma != binder_alloc_get_vma(alloc)) + /* attempt per-vma lock first */ + vma = lock_vma_under_rcu(mm, page_addr); + if (!vma) { + /* fall back to mmap_lock */ + if (!mmap_read_trylock(mm)) + goto err_mmap_read_lock_failed; + mm_locked = 1; + vma = vma_lookup(mm, page_addr); + } + + if (!mutex_trylock(&alloc->mutex)) + goto err_get_alloc_mutex_failed; + + /* + * Since a binder_alloc can only be mapped once, we ensure + * the vma corresponds to this mapping by checking whether + * the binder_alloc is still mapped. + */ + if (vma && !binder_alloc_is_mapped(alloc)) goto err_invalid_vma; trace_binder_unmap_kernel_start(alloc, index); - page_to_free = page->page_ptr; - page->page_ptr = NULL; + page_to_free = alloc->pages[index]; + binder_set_installed_page(alloc, index, NULL); trace_binder_unmap_kernel_end(alloc, index); list_lru_isolate(lru, item); - spin_unlock(&alloc->lock); spin_unlock(&lru->lock); if (vma) { @@ -1101,17 +1191,23 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_user_end(alloc, index); } - mmap_read_unlock(mm); + mutex_unlock(&alloc->mutex); + if (mm_locked) + mmap_read_unlock(mm); + else + vma_end_read(vma); mmput_async(mm); - __free_page(page_to_free); + binder_free_page(page_to_free); return LRU_REMOVED_RETRY; err_invalid_vma: -err_page_already_freed: - spin_unlock(&alloc->lock); -err_get_alloc_lock_failed: - mmap_read_unlock(mm); + mutex_unlock(&alloc->mutex); +err_get_alloc_mutex_failed: + if (mm_locked) + mmap_read_unlock(mm); + else + vma_end_read(vma); err_mmap_read_lock_failed: mmput_async(mm); err_mmget: @@ -1145,7 +1241,7 @@ void binder_alloc_init(struct binder_alloc *alloc) alloc->pid = current->group_leader->pid; alloc->mm = current->mm; mmgrab(alloc->mm); - spin_lock_init(&alloc->lock); + mutex_init(&alloc->mutex); INIT_LIST_HEAD(&alloc->buffers); } diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index c02c8ebcb466..feecd7414241 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include #include @@ -59,34 +59,43 @@ struct binder_buffer { }; /** - * struct binder_lru_page - page object used for binder shrinker - * @page_ptr: pointer to physical page in mmap'd space - * @lru: entry in binder_freelist - * @alloc: binder_alloc for a proc + * struct binder_shrinker_mdata - binder metadata used to reclaim pages + * @lru: LRU entry in binder_freelist + * @alloc: binder_alloc owning the page to reclaim + * @page_index: offset in @alloc->pages[] into the page to reclaim */ -struct binder_lru_page { +struct binder_shrinker_mdata { struct list_head lru; - struct page *page_ptr; struct binder_alloc *alloc; + unsigned long page_index; }; +static inline struct list_head *page_to_lru(struct page *p) +{ + struct binder_shrinker_mdata *mdata; + + mdata = (struct binder_shrinker_mdata *)page_private(p); + + return &mdata->lru; +} + /** * struct binder_alloc - per-binder proc state for binder allocator - * @lock: protects binder_alloc fields - * @vma: vm_area_struct passed to mmap_handler - * (invariant after mmap) + * @mutex: protects binder_alloc fields * @mm: copy of task->mm (invariant after open) - * @buffer: base of per-proc address space mapped via mmap + * @vm_start: base of per-proc address space mapped via mmap * @buffers: list of all buffers for this proc * @free_buffers: rb tree of buffers available for allocation * sorted by size * @allocated_buffers: rb tree of allocated buffers sorted by address * @free_async_space: VA space available for async buffers. This is * initialized at mmap time to 1/2 the full VA space - * @pages: array of binder_lru_page + * @pages: array of struct page * * @buffer_size: size of address space specified via mmap * @pid: pid for associated binder_proc (invariant after init) * @pages_high: high watermark of offset in @pages + * @mapped: whether the vm area is mapped, each binder instance is + * allowed a single mapping throughout its lifetime * @oneway_spam_detected: %true if oneway spam detection fired, clear that * flag once the async buffer has returned to a healthy state * @@ -96,18 +105,18 @@ struct binder_lru_page { * struct binder_buffer objects used to track the user buffers */ struct binder_alloc { - spinlock_t lock; - struct vm_area_struct *vma; + struct mutex mutex; struct mm_struct *mm; - unsigned long buffer; + unsigned long vm_start; struct list_head buffers; struct rb_root free_buffers; struct rb_root allocated_buffers; size_t free_async_space; - struct binder_lru_page *pages; + struct page **pages; size_t buffer_size; int pid; size_t pages_high; + bool mapped; bool oneway_spam_detected; }; @@ -153,9 +162,9 @@ binder_alloc_get_free_async_space(struct binder_alloc *alloc) { size_t free_async_space; - spin_lock(&alloc->lock); + mutex_lock(&alloc->mutex); free_async_space = alloc->free_async_space; - spin_unlock(&alloc->lock); + mutex_unlock(&alloc->mutex); return free_async_space; } diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c index 81442fe20a69..c88735c54848 100644 --- a/drivers/android/binder_alloc_selftest.c +++ b/drivers/android/binder_alloc_selftest.c @@ -104,11 +104,11 @@ static bool check_buffer_pages_allocated(struct binder_alloc *alloc, end = PAGE_ALIGN(buffer->user_data + size); page_addr = buffer->user_data; for (; page_addr < end; page_addr += PAGE_SIZE) { - page_index = (page_addr - alloc->buffer) / PAGE_SIZE; - if (!alloc->pages[page_index].page_ptr || - !list_empty(&alloc->pages[page_index].lru)) { + page_index = (page_addr - alloc->vm_start) / PAGE_SIZE; + if (!alloc->pages[page_index] || + !list_empty(page_to_lru(alloc->pages[page_index]))) { pr_err("expect alloc but is %s at page index %d\n", - alloc->pages[page_index].page_ptr ? + alloc->pages[page_index] ? "lru" : "free", page_index); return false; } @@ -148,10 +148,10 @@ static void binder_selftest_free_buf(struct binder_alloc *alloc, * if binder shrinker ran during binder_alloc_free_buf * calls above. */ - if (list_empty(&alloc->pages[i].lru)) { + if (list_empty(page_to_lru(alloc->pages[i]))) { pr_err_size_seq(sizes, seq); pr_err("expect lru but is %s at page index %d\n", - alloc->pages[i].page_ptr ? "alloc" : "free", i); + alloc->pages[i] ? "alloc" : "free", i); binder_selftest_failures++; } } @@ -168,9 +168,9 @@ static void binder_selftest_free_page(struct binder_alloc *alloc) } for (i = 0; i < (alloc->buffer_size / PAGE_SIZE); i++) { - if (alloc->pages[i].page_ptr) { + if (alloc->pages[i]) { pr_err("expect free but is %s at page index %d\n", - list_empty(&alloc->pages[i].lru) ? + list_empty(page_to_lru(alloc->pages[i])) ? "alloc" : "lru", i); binder_selftest_failures++; } @@ -291,7 +291,7 @@ void binder_selftest_alloc(struct binder_alloc *alloc) if (!binder_selftest_run) return; mutex_lock(&binder_selftest_lock); - if (!binder_selftest_run || !alloc->vma) + if (!binder_selftest_run || !alloc->mapped) goto done; pr_info("STARTED\n"); binder_selftest_alloc_offset(alloc, end_offset, 0); diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index f8d6be682f23..e4eb8357989c 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -25,8 +25,7 @@ struct binder_context { /** * struct binder_device - information about a binder device node - * @hlist: list of binder devices (only used for devices requested via - * CONFIG_ANDROID_BINDER_DEVICES) + * @hlist: list of binder devices * @miscdev: information about a binder character device node * @context: binder context information * @binderfs_inode: This is the inode of the root dentry of the super block @@ -582,4 +581,12 @@ struct binder_object { }; }; +/** + * Add a binder device to binder_devices + * @device: the new binder device to add to the global list + * + * Not reentrant as the list is not protected by any locks + */ +void binder_add_device(struct binder_device *device); + #endif /* _LINUX_BINDER_INTERNAL_H */ diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h index fe38c6fc65d0..16de1b9e72f7 100644 --- a/drivers/android/binder_trace.h +++ b/drivers/android/binder_trace.h @@ -328,7 +328,7 @@ TRACE_EVENT(binder_update_page_range, TP_fast_assign( __entry->proc = alloc->pid; __entry->allocate = allocate; - __entry->offset = start - alloc->buffer; + __entry->offset = start - alloc->vm_start; __entry->size = end - start; ), TP_printk("proc=%d allocate=%d offset=%zu size=%zu", diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index ad1fa7abc323..bc6bae76ccaf 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -207,6 +207,8 @@ static int binderfs_binder_device_create(struct inode *ref_inode, fsnotify_create(root->d_inode, dentry); inode_unlock(d_inode(root)); + binder_add_device(device); + return 0; err: diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 8d27c567be1c..f813dbdc2346 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1987,7 +1987,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (ahci_init_msi(pdev, n_ports, hpriv) < 0) { /* legacy intx interrupts */ - pci_intx(pdev, 1); + pcim_intx(pdev, 1); } hpriv->irq = pci_irq_vector(pdev, 0); diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 8f40f75ba08c..8e895ae45c86 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -328,7 +328,7 @@ struct ahci_port_priv { struct ahci_host_priv { /* Input fields */ unsigned int flags; /* AHCI_HFLAG_* */ - u32 mask_port_map; /* mask out particular bits */ + u32 mask_port_map; /* Mask of valid ports */ void __iomem * mmio; /* bus-independent mem map */ u32 cap; /* cap to use */ @@ -379,6 +379,17 @@ struct ahci_host_priv { int port); }; +/* + * Return true if a port should be ignored because it is excluded from + * the host port map. + */ +static inline bool ahci_ignore_port(struct ahci_host_priv *hpriv, + unsigned int portid) +{ + return portid >= hpriv->nports || + !(hpriv->mask_port_map & (1 << portid)); +} + extern int ahci_ignore_sss; extern const struct attribute_group *ahci_shost_groups[]; @@ -396,8 +407,8 @@ extern const struct attribute_group *ahci_sdev_groups[]; .shost_groups = ahci_shost_groups, \ .sdev_groups = ahci_sdev_groups, \ .change_queue_depth = ata_scsi_change_queue_depth, \ - .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .device_configure = ata_scsi_device_configure + .tag_alloc_policy_rr = true, \ + .sdev_configure = ata_scsi_sdev_configure extern struct ata_port_operations ahci_ops; extern struct ata_port_operations ahci_platform_ops; diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index ef569eae4ce4..29be74fedcf0 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -288,6 +288,9 @@ static unsigned int brcm_ahci_read_id(struct ata_device *dev, /* Re-initialize and calibrate the PHY */ for (i = 0; i < hpriv->nports; i++) { + if (ahci_ignore_port(hpriv, i)) + continue; + rc = phy_init(hpriv->phys[i]); if (rc) goto disable_phys; diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c index 1ec35778903d..2d6a08c23d6a 100644 --- a/drivers/ata/ahci_ceva.c +++ b/drivers/ata/ahci_ceva.c @@ -206,6 +206,9 @@ static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv) goto disable_clks; for (i = 0; i < hpriv->nports; i++) { + if (ahci_ignore_port(hpriv, i)) + continue; + rc = phy_init(hpriv->phys[i]); if (rc) goto disable_rsts; @@ -215,6 +218,9 @@ static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv) ahci_platform_deassert_rsts(hpriv); for (i = 0; i < hpriv->nports; i++) { + if (ahci_ignore_port(hpriv, i)) + continue; + rc = phy_power_on(hpriv->phys[i]); if (rc) { phy_exit(hpriv->phys[i]); diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c index 6b9b4a1dfa15..4336c8a6e208 100644 --- a/drivers/ata/ahci_st.c +++ b/drivers/ata/ahci_st.c @@ -176,7 +176,6 @@ static int st_ahci_probe(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP static int st_ahci_suspend(struct device *dev) { struct ata_host *host = dev_get_drvdata(dev); @@ -221,9 +220,8 @@ static int st_ahci_resume(struct device *dev) return ahci_platform_resume_host(dev); } -#endif -static SIMPLE_DEV_PM_OPS(st_ahci_pm_ops, st_ahci_suspend, st_ahci_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(st_ahci_pm_ops, st_ahci_suspend, st_ahci_resume); static const struct of_device_id st_ahci_match[] = { { .compatible = "st,ahci", }, @@ -234,7 +232,7 @@ MODULE_DEVICE_TABLE(of, st_ahci_match); static struct platform_driver st_ahci_driver = { .driver = { .name = DRV_NAME, - .pm = &st_ahci_pm_ops, + .pm = pm_sleep_ptr(&st_ahci_pm_ops), .of_match_table = st_ahci_match, }, .probe = st_ahci_probe, diff --git a/drivers/ata/ata_generic.c b/drivers/ata/ata_generic.c index 2f57ec00ab82..e70b6c089cf1 100644 --- a/drivers/ata/ata_generic.c +++ b/drivers/ata/ata_generic.c @@ -209,7 +209,7 @@ static int ata_generic_init_one(struct pci_dev *dev, const struct pci_device_id return ata_pci_bmdma_init_one(dev, ppi, &generic_sht, (void *)id, 0); } -static struct pci_device_id ata_generic[] = { +static const struct pci_device_id ata_generic[] = { { PCI_DEVICE(PCI_VENDOR_ID_PCTECH, PCI_DEVICE_ID_PCTECH_SAMURAI_IDE), }, { PCI_DEVICE(PCI_VENDOR_ID_HOLTEK, PCI_DEVICE_ID_HOLTEK_6565), }, { PCI_DEVICE(PCI_VENDOR_ID_UMC, PCI_DEVICE_ID_UMC_UM8673F), }, diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 093b940bc953..d441246fa357 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -1725,7 +1725,7 @@ static int piix_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) * message-signalled interrupts currently). */ if (port_flags & PIIX_FLAG_CHECKINTR) - pci_intx(pdev, 1); + pcim_intx(pdev, 1); if (piix_check_450nx_errata(pdev)) { /* This writes into the master table but it does not diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 7a8064520a35..53b2c7719dc5 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -49,6 +49,9 @@ int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) int rc, i; for (i = 0; i < hpriv->nports; i++) { + if (ahci_ignore_port(hpriv, i)) + continue; + rc = phy_init(hpriv->phys[i]); if (rc) goto disable_phys; @@ -70,6 +73,9 @@ int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) disable_phys: while (--i >= 0) { + if (ahci_ignore_port(hpriv, i)) + continue; + phy_power_off(hpriv->phys[i]); phy_exit(hpriv->phys[i]); } @@ -88,6 +94,9 @@ void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) int i; for (i = 0; i < hpriv->nports; i++) { + if (ahci_ignore_port(hpriv, i)) + continue; + phy_power_off(hpriv->phys[i]); phy_exit(hpriv->phys[i]); } @@ -432,6 +441,20 @@ static int ahci_platform_get_firmware(struct ahci_host_priv *hpriv, return 0; } +static u32 ahci_platform_find_max_port_id(struct device *dev) +{ + u32 max_port = 0; + + for_each_child_of_node_scoped(dev->of_node, child) { + u32 port; + + if (!of_property_read_u32(child, "reg", &port)) + max_port = max(max_port, port); + } + + return max_port; +} + /** * ahci_platform_get_resources - Get platform resources * @pdev: platform device to get resources for @@ -458,6 +481,7 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev, struct device *dev = &pdev->dev; struct ahci_host_priv *hpriv; u32 mask_port_map = 0; + u32 max_port; if (!devres_open_group(dev, NULL, GFP_KERNEL)) return ERR_PTR(-ENOMEM); @@ -549,15 +573,17 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev, goto err_out; } + /* find maximum port id for allocating structures */ + max_port = ahci_platform_find_max_port_id(dev); /* - * If no sub-node was found, we still need to set nports to - * one in order to be able to use the + * Set nports according to maximum port id. Clamp at + * AHCI_MAX_PORTS, warning message for invalid port id + * is generated later. + * When DT has no sub-nodes max_port is 0, nports is 1, + * in order to be able to use the * ahci_platform_[en|dis]able_[phys|regulators] functions. */ - if (child_nodes) - hpriv->nports = child_nodes; - else - hpriv->nports = 1; + hpriv->nports = min(AHCI_MAX_PORTS, max_port + 1); hpriv->phys = devm_kcalloc(dev, hpriv->nports, sizeof(*hpriv->phys), GFP_KERNEL); if (!hpriv->phys) { @@ -625,6 +651,8 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev, * If no sub-node was found, keep this for device tree * compatibility */ + hpriv->mask_port_map |= BIT(0); + rc = ahci_platform_get_phy(hpriv, 0, dev, dev->of_node); if (rc) goto err_out; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index c085dd81ebe7..63ec2f218431 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4143,6 +4143,10 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = { { "Samsung SSD 860*", NULL, ATA_QUIRK_NO_NCQ_TRIM | ATA_QUIRK_ZERO_AFTER_TRIM | ATA_QUIRK_NO_NCQ_ON_ATI }, + { "Samsung SSD 870 QVO*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM | + ATA_QUIRK_NO_NCQ_ON_ATI | + ATA_QUIRK_NOLPM }, { "Samsung SSD 870*", NULL, ATA_QUIRK_NO_NCQ_TRIM | ATA_QUIRK_ZERO_AFTER_TRIM | ATA_QUIRK_NO_NCQ_ON_ATI }, diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 9c76fb1ad2ec..ba300cc0a3a3 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -1313,7 +1313,7 @@ int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth) EXPORT_SYMBOL_GPL(ata_scsi_change_queue_depth); /** - * ata_sas_device_configure - Default device_configure routine for libata + * ata_sas_sdev_configure - Default sdev_configure routine for libata * devices * @sdev: SCSI device to configure * @lim: queue limits @@ -1323,14 +1323,14 @@ EXPORT_SYMBOL_GPL(ata_scsi_change_queue_depth); * Zero. */ -int ata_sas_device_configure(struct scsi_device *sdev, struct queue_limits *lim, - struct ata_port *ap) +int ata_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim, + struct ata_port *ap) { ata_scsi_sdev_config(sdev); return ata_scsi_dev_config(sdev, lim, ap->link.device); } -EXPORT_SYMBOL_GPL(ata_sas_device_configure); +EXPORT_SYMBOL_GPL(ata_sas_sdev_configure); /** * ata_sas_queuecmd - Issue SCSI cdb to libata-managed device diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 2ce5befd2242..2796c0da8257 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1133,7 +1133,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct queue_limits *lim, } /** - * ata_scsi_slave_alloc - Early setup of SCSI device + * ata_scsi_sdev_init - Early setup of SCSI device * @sdev: SCSI device to examine * * This is called from scsi_alloc_sdev() when the scsi device @@ -1143,7 +1143,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct queue_limits *lim, * Defined by SCSI layer. We don't really care. */ -int ata_scsi_slave_alloc(struct scsi_device *sdev) +int ata_scsi_sdev_init(struct scsi_device *sdev) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct device_link *link; @@ -1166,10 +1166,10 @@ int ata_scsi_slave_alloc(struct scsi_device *sdev) return 0; } -EXPORT_SYMBOL_GPL(ata_scsi_slave_alloc); +EXPORT_SYMBOL_GPL(ata_scsi_sdev_init); /** - * ata_scsi_device_configure - Set SCSI device attributes + * ata_scsi_sdev_configure - Set SCSI device attributes * @sdev: SCSI device to examine * @lim: queue limits * @@ -1181,8 +1181,7 @@ EXPORT_SYMBOL_GPL(ata_scsi_slave_alloc); * Defined by SCSI layer. We don't really care. */ -int ata_scsi_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +int ata_scsi_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct ata_device *dev = __ata_scsi_find_dev(ap, sdev); @@ -1192,10 +1191,10 @@ int ata_scsi_device_configure(struct scsi_device *sdev, return 0; } -EXPORT_SYMBOL_GPL(ata_scsi_device_configure); +EXPORT_SYMBOL_GPL(ata_scsi_sdev_configure); /** - * ata_scsi_slave_destroy - SCSI device is about to be destroyed + * ata_scsi_sdev_destroy - SCSI device is about to be destroyed * @sdev: SCSI device to be destroyed * * @sdev is about to be destroyed for hot/warm unplugging. If @@ -1208,7 +1207,7 @@ EXPORT_SYMBOL_GPL(ata_scsi_device_configure); * LOCKING: * Defined by SCSI layer. We don't really care. */ -void ata_scsi_slave_destroy(struct scsi_device *sdev) +void ata_scsi_sdev_destroy(struct scsi_device *sdev) { struct ata_port *ap = ata_shost_to_port(sdev->host); unsigned long flags; @@ -1228,7 +1227,7 @@ void ata_scsi_slave_destroy(struct scsi_device *sdev) kfree(sdev->dma_drain_buf); } -EXPORT_SYMBOL_GPL(ata_scsi_slave_destroy); +EXPORT_SYMBOL_GPL(ata_scsi_sdev_destroy); /** * ata_scsi_start_stop_xlat - Translate SCSI START STOP UNIT command diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 67f277e1c3bf..5a46c066abc3 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -601,7 +601,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct page *page; - unsigned int offset; + unsigned int offset, count; if (!qc->cursg) { qc->curbytes = qc->nbytes; @@ -617,25 +617,27 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) page = nth_page(page, (offset >> PAGE_SHIFT)); offset %= PAGE_SIZE; - trace_ata_sff_pio_transfer_data(qc, offset, qc->sect_size); + /* don't overrun current sg */ + count = min(qc->cursg->length - qc->cursg_ofs, qc->sect_size); + + trace_ata_sff_pio_transfer_data(qc, offset, count); /* * Split the transfer when it splits a page boundary. Note that the * split still has to be dword aligned like all ATA data transfers. */ WARN_ON_ONCE(offset % 4); - if (offset + qc->sect_size > PAGE_SIZE) { + if (offset + count > PAGE_SIZE) { unsigned int split_len = PAGE_SIZE - offset; ata_pio_xfer(qc, page, offset, split_len); - ata_pio_xfer(qc, nth_page(page, 1), 0, - qc->sect_size - split_len); + ata_pio_xfer(qc, nth_page(page, 1), 0, count - split_len); } else { - ata_pio_xfer(qc, page, offset, qc->sect_size); + ata_pio_xfer(qc, page, offset, count); } - qc->curbytes += qc->sect_size; - qc->cursg_ofs += qc->sect_size; + qc->curbytes += count; + qc->cursg_ofs += count; if (qc->cursg_ofs == qc->cursg->length) { qc->cursg = sg_next(qc->cursg); diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c index aaef5924f636..308f86f9e2f0 100644 --- a/drivers/ata/pata_atp867x.c +++ b/drivers/ata/pata_atp867x.c @@ -525,7 +525,7 @@ static int atp867x_reinit_one(struct pci_dev *pdev) } #endif -static struct pci_device_id atp867x_pci_tbl[] = { +static const struct pci_device_id atp867x_pci_tbl[] = { { PCI_VDEVICE(ARTOP, PCI_DEVICE_ID_ARTOP_ATP867A), 0 }, { PCI_VDEVICE(ARTOP, PCI_DEVICE_ID_ARTOP_ATP867B), 0 }, { }, diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index f2f36e55a1f4..fbf5f07ea357 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -812,8 +812,8 @@ static void pata_macio_reset_hw(struct pata_macio_priv *priv, int resume) /* Hook the standard slave config to fixup some HW related alignment * restrictions */ -static int pata_macio_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int pata_macio_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct pata_macio_priv *priv = ap->private_data; @@ -822,7 +822,7 @@ static int pata_macio_device_configure(struct scsi_device *sdev, int rc; /* First call original */ - rc = ata_scsi_device_configure(sdev, lim); + rc = ata_scsi_sdev_configure(sdev, lim); if (rc) return rc; @@ -932,10 +932,10 @@ static const struct scsi_host_template pata_macio_sht = { /* We may not need that strict one */ .dma_boundary = ATA_DMA_BOUNDARY, .max_segment_size = PATA_MACIO_MAX_SEGMENT_SIZE, - .device_configure = pata_macio_device_configure, + .sdev_configure = pata_macio_sdev_configure, .sdev_groups = ata_common_sdev_groups, .can_queue = ATA_DEF_QUEUE, - .tag_alloc_policy = BLK_TAG_ALLOC_RR, + .tag_alloc_policy_rr = true, }; static struct ata_port_operations pata_macio_ops = { diff --git a/drivers/ata/pata_piccolo.c b/drivers/ata/pata_piccolo.c index ced906bf56be..beb53bd990be 100644 --- a/drivers/ata/pata_piccolo.c +++ b/drivers/ata/pata_piccolo.c @@ -97,7 +97,7 @@ static int ata_tosh_init_one(struct pci_dev *dev, const struct pci_device_id *id return ata_pci_bmdma_init_one(dev, ppi, &tosh_sht, NULL, 0); } -static struct pci_device_id ata_tosh[] = { +static const struct pci_device_id ata_tosh[] = { { PCI_DEVICE(PCI_VENDOR_ID_TOSHIBA,PCI_DEVICE_ID_TOSHIBA_PICCOLO_1), }, { PCI_DEVICE(PCI_VENDOR_ID_TOSHIBA,PCI_DEVICE_ID_TOSHIBA_PICCOLO_2), }, { PCI_DEVICE(PCI_VENDOR_ID_TOSHIBA,PCI_DEVICE_ID_TOSHIBA_PICCOLO_3), }, diff --git a/drivers/ata/pata_rdc.c b/drivers/ata/pata_rdc.c index 0a9689862f71..09792aac7f9d 100644 --- a/drivers/ata/pata_rdc.c +++ b/drivers/ata/pata_rdc.c @@ -340,7 +340,7 @@ static int rdc_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return rc; host->private_data = hpriv; - pci_intx(pdev, 1); + pcim_intx(pdev, 1); host->flags |= ATA_HOST_PARALLEL_SCAN; diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c index d040799bf9cb..530ee26b3012 100644 --- a/drivers/ata/sata_gemini.c +++ b/drivers/ata/sata_gemini.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -27,8 +26,6 @@ * @muxmode: the current muxing mode * @ide_pins: if the device is using the plain IDE interface pins * @sata_bridge: if the device enables the SATA bridge - * @sata0_reset: SATA0 reset handler - * @sata1_reset: SATA1 reset handler * @sata0_pclk: SATA0 PCLK handler * @sata1_pclk: SATA1 PCLK handler */ @@ -38,8 +35,6 @@ struct sata_gemini { enum gemini_muxmode muxmode; bool ide_pins; bool sata_bridge; - struct reset_control *sata0_reset; - struct reset_control *sata1_reset; struct clk *sata0_pclk; struct clk *sata1_pclk; }; @@ -224,18 +219,6 @@ void gemini_sata_stop_bridge(struct sata_gemini *sg, unsigned int bridge) } EXPORT_SYMBOL(gemini_sata_stop_bridge); -int gemini_sata_reset_bridge(struct sata_gemini *sg, - unsigned int bridge) -{ - if (bridge == 0) - reset_control_reset(sg->sata0_reset); - else - reset_control_reset(sg->sata1_reset); - msleep(10); - return gemini_sata_setup_bridge(sg, bridge); -} -EXPORT_SYMBOL(gemini_sata_reset_bridge); - static int gemini_sata_bridge_init(struct sata_gemini *sg) { struct device *dev = sg->dev; @@ -265,21 +248,6 @@ static int gemini_sata_bridge_init(struct sata_gemini *sg) return ret; } - sg->sata0_reset = devm_reset_control_get_exclusive(dev, "sata0"); - if (IS_ERR(sg->sata0_reset)) { - dev_err(dev, "no SATA0 reset controller\n"); - clk_disable_unprepare(sg->sata1_pclk); - clk_disable_unprepare(sg->sata0_pclk); - return PTR_ERR(sg->sata0_reset); - } - sg->sata1_reset = devm_reset_control_get_exclusive(dev, "sata1"); - if (IS_ERR(sg->sata1_reset)) { - dev_err(dev, "no SATA1 reset controller\n"); - clk_disable_unprepare(sg->sata1_pclk); - clk_disable_unprepare(sg->sata0_pclk); - return PTR_ERR(sg->sata1_reset); - } - sata_id = readl(sg->base + GEMINI_SATA_ID); sata_phy_id = readl(sg->base + GEMINI_SATA_PHY_ID); sg->sata_bridge = true; diff --git a/drivers/ata/sata_gemini.h b/drivers/ata/sata_gemini.h index 6f6e691d6007..b6e4a5c86e01 100644 --- a/drivers/ata/sata_gemini.h +++ b/drivers/ata/sata_gemini.h @@ -17,6 +17,5 @@ bool gemini_sata_bridge_enabled(struct sata_gemini *sg, bool is_ata1); enum gemini_muxmode gemini_sata_get_muxmode(struct sata_gemini *sg); int gemini_sata_start_bridge(struct sata_gemini *sg, unsigned int bridge); void gemini_sata_stop_bridge(struct sata_gemini *sg, unsigned int bridge); -int gemini_sata_reset_bridge(struct sata_gemini *sg, unsigned int bridge); #endif diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index b8f363370e1a..bcbf96867f89 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -672,8 +672,8 @@ static const struct scsi_host_template mv6_sht = { .dma_boundary = MV_DMA_BOUNDARY, .sdev_groups = ata_ncq_sdev_groups, .change_queue_depth = ata_scsi_change_queue_depth, - .tag_alloc_policy = BLK_TAG_ALLOC_RR, - .device_configure = ata_scsi_device_configure + .tag_alloc_policy_rr = true, + .sdev_configure = ata_scsi_sdev_configure }; static struct ata_port_operations mv5_ops = { diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 36d99043ef50..f36e2915ccf1 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -296,8 +296,8 @@ static void nv_nf2_freeze(struct ata_port *ap); static void nv_nf2_thaw(struct ata_port *ap); static void nv_ck804_freeze(struct ata_port *ap); static void nv_ck804_thaw(struct ata_port *ap); -static int nv_adma_device_configure(struct scsi_device *sdev, - struct queue_limits *lim); +static int nv_adma_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim); static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc); static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc); static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc); @@ -319,8 +319,8 @@ static void nv_adma_tf_read(struct ata_port *ap, struct ata_taskfile *tf); static void nv_mcp55_thaw(struct ata_port *ap); static void nv_mcp55_freeze(struct ata_port *ap); static void nv_swncq_error_handler(struct ata_port *ap); -static int nv_swncq_device_configure(struct scsi_device *sdev, - struct queue_limits *lim); +static int nv_swncq_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim); static int nv_swncq_port_start(struct ata_port *ap); static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc); static void nv_swncq_fill_sg(struct ata_queued_cmd *qc); @@ -382,10 +382,10 @@ static const struct scsi_host_template nv_adma_sht = { .can_queue = NV_ADMA_MAX_CPBS, .sg_tablesize = NV_ADMA_SGTBL_TOTAL_LEN, .dma_boundary = NV_ADMA_DMA_BOUNDARY, - .device_configure = nv_adma_device_configure, + .sdev_configure = nv_adma_sdev_configure, .sdev_groups = ata_ncq_sdev_groups, .change_queue_depth = ata_scsi_change_queue_depth, - .tag_alloc_policy = BLK_TAG_ALLOC_RR, + .tag_alloc_policy_rr = true, }; static const struct scsi_host_template nv_swncq_sht = { @@ -393,10 +393,10 @@ static const struct scsi_host_template nv_swncq_sht = { .can_queue = ATA_MAX_QUEUE - 1, .sg_tablesize = LIBATA_MAX_PRD, .dma_boundary = ATA_DMA_BOUNDARY, - .device_configure = nv_swncq_device_configure, + .sdev_configure = nv_swncq_sdev_configure, .sdev_groups = ata_ncq_sdev_groups, .change_queue_depth = ata_scsi_change_queue_depth, - .tag_alloc_policy = BLK_TAG_ALLOC_RR, + .tag_alloc_policy_rr = true, }; /* @@ -663,8 +663,8 @@ static void nv_adma_mode(struct ata_port *ap) pp->flags &= ~NV_ADMA_PORT_REGISTER_MODE; } -static int nv_adma_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int nv_adma_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct nv_adma_port_priv *pp = ap->private_data; @@ -676,7 +676,7 @@ static int nv_adma_device_configure(struct scsi_device *sdev, int adma_enable; u32 current_reg, new_reg, config_mask; - rc = ata_scsi_device_configure(sdev, lim); + rc = ata_scsi_sdev_configure(sdev, lim); if (sdev->id >= ATA_MAX_DEVICES || sdev->channel || sdev->lun) /* Not a proper libata device, ignore */ @@ -1871,8 +1871,8 @@ static void nv_swncq_host_init(struct ata_host *host) writel(~0x0, mmio + NV_INT_STATUS_MCP55); } -static int nv_swncq_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int nv_swncq_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct pci_dev *pdev = to_pci_dev(ap->host->dev); @@ -1882,7 +1882,7 @@ static int nv_swncq_device_configure(struct scsi_device *sdev, u8 check_maxtor = 0; unsigned char model_num[ATA_ID_PROD_LEN + 1]; - rc = ata_scsi_device_configure(sdev, lim); + rc = ata_scsi_sdev_configure(sdev, lim); if (sdev->id >= ATA_MAX_DEVICES || sdev->channel || sdev->lun) /* Not a proper libata device, ignore */ return rc; diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index 72c03cbdaff4..87f4cde6a686 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -378,10 +378,9 @@ static const struct scsi_host_template sil24_sht = { .can_queue = SIL24_MAX_CMDS, .sg_tablesize = SIL24_MAX_SGE, .dma_boundary = ATA_DMA_BOUNDARY, - .tag_alloc_policy = BLK_TAG_ALLOC_FIFO, .sdev_groups = ata_ncq_sdev_groups, .change_queue_depth = ata_scsi_change_queue_depth, - .device_configure = ata_scsi_device_configure + .sdev_configure = ata_scsi_sdev_configure }; static struct ata_port_operations sil24_ops = { @@ -1317,7 +1316,7 @@ static int sil24_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (sata_sil24_msi && !pci_enable_msi(pdev)) { dev_info(&pdev->dev, "Using MSI\n"); - pci_intx(pdev, 0); + pcim_intx(pdev, 0); } pci_set_master(pdev); diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c index ef8724986de3..b8b6d9eff3b8 100644 --- a/drivers/ata/sata_sis.c +++ b/drivers/ata/sata_sis.c @@ -290,7 +290,7 @@ static int sis_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_set_master(pdev); - pci_intx(pdev, 1); + pcim_intx(pdev, 1); return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt, IRQF_SHARED, &sis_sht); } diff --git a/drivers/ata/sata_uli.c b/drivers/ata/sata_uli.c index 60ea45926cd1..52894ff49dcb 100644 --- a/drivers/ata/sata_uli.c +++ b/drivers/ata/sata_uli.c @@ -221,7 +221,7 @@ static int uli_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_set_master(pdev); - pci_intx(pdev, 1); + pcim_intx(pdev, 1); return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt, IRQF_SHARED, &uli_sht); } diff --git a/drivers/ata/sata_vsc.c b/drivers/ata/sata_vsc.c index d39b87537168..a53a2dfc1e17 100644 --- a/drivers/ata/sata_vsc.c +++ b/drivers/ata/sata_vsc.c @@ -384,7 +384,7 @@ static int vsc_sata_init_one(struct pci_dev *pdev, pci_write_config_byte(pdev, PCI_CACHE_LINE_SIZE, 0x80); if (pci_enable_msi(pdev) == 0) - pci_intx(pdev, 0); + pcim_intx(pdev, 0); /* * Config offset 0x98 is "Extended Control and Status Register 0" diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig index 21545ffba065..8934e6ad5772 100644 --- a/drivers/auxdisplay/Kconfig +++ b/drivers/auxdisplay/Kconfig @@ -489,7 +489,7 @@ config IMG_ASCII_LCD config HT16K33 tristate "Holtek Ht16K33 LED controller with keyscan" - depends on FB && I2C && INPUT + depends on FB && I2C && INPUT && BACKLIGHT_CLASS_DEVICE select FB_SYSMEM_HELPERS select INPUT_MATRIXKMAP select FB_BACKLIGHT diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c index a802678a6f74..32e1863ef4b2 100644 --- a/drivers/auxdisplay/img-ascii-lcd.c +++ b/drivers/auxdisplay/img-ascii-lcd.c @@ -36,7 +36,6 @@ struct img_ascii_lcd_config { * @base: the base address of the LCD registers * @regmap: the regmap through which LCD registers are accessed * @offset: the offset within regmap to the start of the LCD registers - * @cfg: pointer to the LCD model configuration */ struct img_ascii_lcd_ctx { struct linedisp linedisp; @@ -45,7 +44,6 @@ struct img_ascii_lcd_ctx { struct regmap *regmap; }; u32 offset; - const struct img_ascii_lcd_config *cfg; }; /* @@ -71,7 +69,7 @@ static void boston_update(struct linedisp *linedisp) #endif } -static struct img_ascii_lcd_config boston_config = { +static const struct img_ascii_lcd_config boston_config = { .num_chars = 8, .ops = { .update = boston_update, @@ -100,7 +98,7 @@ static void malta_update(struct linedisp *linedisp) pr_err_ratelimited("Failed to update LCD display: %d\n", err); } -static struct img_ascii_lcd_config malta_config = { +static const struct img_ascii_lcd_config malta_config = { .num_chars = 8, .external_regmap = true, .ops = { @@ -202,7 +200,7 @@ static void sead3_update(struct linedisp *linedisp) pr_err_ratelimited("Failed to update LCD display: %d\n", err); } -static struct img_ascii_lcd_config sead3_config = { +static const struct img_ascii_lcd_config sead3_config = { .num_chars = 16, .external_regmap = true, .ops = { diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 657c93c38b0d..6b9e65a42cd2 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -354,7 +354,7 @@ static struct device *next_device(struct klist_iter *i) * count in the supplied callback. */ int bus_for_each_dev(const struct bus_type *bus, struct device *start, - void *data, int (*fn)(struct device *, void *)) + void *data, device_iter_t fn) { struct subsys_private *sp = bus_to_subsys(bus); struct klist_iter i; @@ -402,9 +402,12 @@ struct device *bus_find_device(const struct bus_type *bus, klist_iter_init_node(&sp->klist_devices, &i, (start ? &start->p->knode_bus : NULL)); - while ((dev = next_device(&i))) - if (match(dev, data) && get_device(dev)) + while ((dev = next_device(&i))) { + if (match(dev, data)) { + get_device(dev); break; + } + } klist_iter_exit(&i); subsys_put(sp); return dev; diff --git a/drivers/base/class.c b/drivers/base/class.c index 582b5a02a5c4..2526c57d924e 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -323,8 +323,12 @@ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, struct subsys_private *sp = class_to_subsys(class); struct klist_node *start_knode = NULL; - if (!sp) + memset(iter, 0, sizeof(*iter)); + if (!sp) { + pr_crit("%s: class %p was not registered yet\n", + __func__, class); return; + } if (start) start_knode = &start->p->knode_class; @@ -351,6 +355,9 @@ struct device *class_dev_iter_next(struct class_dev_iter *iter) struct klist_node *knode; struct device *dev; + if (!iter->sp) + return NULL; + while (1) { knode = klist_next(&iter->ki); if (!knode) @@ -395,7 +402,7 @@ EXPORT_SYMBOL_GPL(class_dev_iter_exit); * code. There's no locking restriction. */ int class_for_each_device(const struct class *class, const struct device *start, - void *data, int (*fn)(struct device *, void *)) + void *data, device_iter_t fn) { struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; @@ -594,30 +601,10 @@ EXPORT_SYMBOL_GPL(class_compat_unregister); * a bus device * @cls: the compatibility class * @dev: the target bus device - * @device_link: an optional device to which a "device" link should be created */ -int class_compat_create_link(struct class_compat *cls, struct device *dev, - struct device *device_link) +int class_compat_create_link(struct class_compat *cls, struct device *dev) { - int error; - - error = sysfs_create_link(cls->kobj, &dev->kobj, dev_name(dev)); - if (error) - return error; - - /* - * Optionally add a "device" link (typically to the parent), as a - * class device would have one and we want to provide as much - * backwards compatibility as possible. - */ - if (device_link) { - error = sysfs_create_link(&dev->kobj, &device_link->kobj, - "device"); - if (error) - sysfs_remove_link(cls->kobj, dev_name(dev)); - } - - return error; + return sysfs_create_link(cls->kobj, &dev->kobj, dev_name(dev)); } EXPORT_SYMBOL_GPL(class_compat_create_link); @@ -626,14 +613,9 @@ EXPORT_SYMBOL_GPL(class_compat_create_link); * a bus device * @cls: the compatibility class * @dev: the target bus device - * @device_link: an optional device to which a "device" link was previously - * created */ -void class_compat_remove_link(struct class_compat *cls, struct device *dev, - struct device *device_link) +void class_compat_remove_link(struct class_compat *cls, struct device *dev) { - if (device_link) - sysfs_remove_link(&dev->kobj, "device"); sysfs_remove_link(cls->kobj, dev_name(dev)); } EXPORT_SYMBOL_GPL(class_compat_remove_link); diff --git a/drivers/base/core.c b/drivers/base/core.c index 94865c9d8adc..5a1f05198114 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3980,7 +3980,7 @@ const char *device_get_devnode(const struct device *dev, * other than 0, we break out and return that value. */ int device_for_each_child(struct device *parent, void *data, - int (*fn)(struct device *dev, void *data)) + device_iter_t fn) { struct klist_iter i; struct device *child; @@ -4010,7 +4010,7 @@ EXPORT_SYMBOL_GPL(device_for_each_child); * other than 0, we break out and return that value. */ int device_for_each_child_reverse(struct device *parent, void *data, - int (*fn)(struct device *dev, void *data)) + device_iter_t fn) { struct klist_iter i; struct device *child; @@ -4043,14 +4043,14 @@ EXPORT_SYMBOL_GPL(device_for_each_child_reverse); * device_for_each_child_reverse_from(); */ int device_for_each_child_reverse_from(struct device *parent, - struct device *from, const void *data, - int (*fn)(struct device *, const void *)) + struct device *from, void *data, + device_iter_t fn) { struct klist_iter i; struct device *child; int error = 0; - if (!parent->p) + if (!parent || !parent->p) return 0; klist_iter_init_node(&parent->p->klist_children, &i, @@ -4079,8 +4079,8 @@ EXPORT_SYMBOL_GPL(device_for_each_child_reverse_from); * * NOTE: you will need to drop the reference with put_device() after use. */ -struct device *device_find_child(struct device *parent, void *data, - int (*match)(struct device *dev, void *data)) +struct device *device_find_child(struct device *parent, const void *data, + device_match_t match) { struct klist_iter i; struct device *child; @@ -4089,62 +4089,17 @@ struct device *device_find_child(struct device *parent, void *data, return NULL; klist_iter_init(&parent->p->klist_children, &i); - while ((child = next_device(&i))) - if (match(child, data) && get_device(child)) + while ((child = next_device(&i))) { + if (match(child, data)) { + get_device(child); break; + } + } klist_iter_exit(&i); return child; } EXPORT_SYMBOL_GPL(device_find_child); -/** - * device_find_child_by_name - device iterator for locating a child device. - * @parent: parent struct device - * @name: name of the child device - * - * This is similar to the device_find_child() function above, but it - * returns a reference to a device that has the name @name. - * - * NOTE: you will need to drop the reference with put_device() after use. - */ -struct device *device_find_child_by_name(struct device *parent, - const char *name) -{ - struct klist_iter i; - struct device *child; - - if (!parent) - return NULL; - - klist_iter_init(&parent->p->klist_children, &i); - while ((child = next_device(&i))) - if (sysfs_streq(dev_name(child), name) && get_device(child)) - break; - klist_iter_exit(&i); - return child; -} -EXPORT_SYMBOL_GPL(device_find_child_by_name); - -static int match_any(struct device *dev, void *unused) -{ - return 1; -} - -/** - * device_find_any_child - device iterator for locating a child device, if any. - * @parent: parent struct device - * - * This is similar to the device_find_child() function above, but it - * returns a reference to a child device, if any. - * - * NOTE: you will need to drop the reference with put_device() after use. - */ -struct device *device_find_any_child(struct device *parent) -{ - return device_find_child(parent, NULL, match_any); -} -EXPORT_SYMBOL_GPL(device_find_any_child); - int __init devices_init(void) { devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL); @@ -5244,15 +5199,21 @@ int device_match_name(struct device *dev, const void *name) } EXPORT_SYMBOL_GPL(device_match_name); +int device_match_type(struct device *dev, const void *type) +{ + return dev->type == type; +} +EXPORT_SYMBOL_GPL(device_match_type); + int device_match_of_node(struct device *dev, const void *np) { - return dev->of_node == np; + return np && dev->of_node == np; } EXPORT_SYMBOL_GPL(device_match_of_node); int device_match_fwnode(struct device *dev, const void *fwnode) { - return dev_fwnode(dev) == fwnode; + return fwnode && dev_fwnode(dev) == fwnode; } EXPORT_SYMBOL_GPL(device_match_fwnode); @@ -5264,13 +5225,13 @@ EXPORT_SYMBOL_GPL(device_match_devt); int device_match_acpi_dev(struct device *dev, const void *adev) { - return ACPI_COMPANION(dev) == adev; + return adev && ACPI_COMPANION(dev) == adev; } EXPORT_SYMBOL(device_match_acpi_dev); int device_match_acpi_handle(struct device *dev, const void *handle) { - return ACPI_HANDLE(dev) == handle; + return handle && ACPI_HANDLE(dev) == handle; } EXPORT_SYMBOL(device_match_acpi_handle); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index fdaa24bb641a..a7e511849875 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -599,6 +599,7 @@ CPU_SHOW_VULN_FALLBACK(retbleed); CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); CPU_SHOW_VULN_FALLBACK(gds); CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); +CPU_SHOW_VULN_FALLBACK(ghostwrite); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -614,6 +615,7 @@ static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); +static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -630,6 +632,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_spec_rstack_overflow.attr, &dev_attr_gather_data_sampling.attr, &dev_attr_reg_file_data_sampling.attr, + &dev_attr_ghostwrite.attr, NULL }; diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c index c795edad1b96..64840e5d5fcc 100644 --- a/drivers/base/devcoredump.c +++ b/drivers/base/devcoredump.c @@ -106,7 +106,7 @@ static void devcd_del(struct work_struct *wk) } static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t offset, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -116,7 +116,7 @@ static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj, } static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t offset, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -132,19 +132,15 @@ static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute devcd_attr_data = { - .attr = { .name = "data", .mode = S_IRUSR | S_IWUSR, }, - .size = 0, - .read = devcd_data_read, - .write = devcd_data_write, -}; +static const struct bin_attribute devcd_attr_data = + __BIN_ATTR(data, 0600, devcd_data_read, devcd_data_write, 0); -static struct bin_attribute *devcd_dev_bin_attrs[] = { +static const struct bin_attribute *const devcd_dev_bin_attrs[] = { &devcd_attr_data, NULL, }; static const struct attribute_group devcd_dev_group = { - .bin_attrs = devcd_dev_bin_attrs, + .bin_attrs_new = devcd_dev_bin_attrs, }; static const struct attribute_group *devcd_dev_groups[] = { @@ -186,9 +182,9 @@ static ssize_t disabled_show(const struct class *class, const struct class_attri * mutex_lock(&devcd->mutex); * * - * In the above diagram, It looks like disabled_store() would be racing with parallely + * In the above diagram, it looks like disabled_store() would be racing with parallelly * running devcd_del() and result in memory abort while acquiring devcd->mutex which - * is called after kfree of devcd memory after dropping its last reference with + * is called after kfree of devcd memory after dropping its last reference with * put_device(). However, this will not happens as fn(dev, data) runs * with its own reference to device via klist_node so it is not its last reference. * so, above situation would not occur. @@ -285,6 +281,8 @@ static void devcd_free_sgtable(void *data) * @offset: start copy from @offset@ bytes from the head of the data * in the given scatterlist * @data_len: the length of the data in the sg_table + * + * Returns: the number of bytes copied */ static ssize_t devcd_read_from_sgtable(char *buffer, loff_t offset, size_t buf_len, void *data, diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 2152eec0c135..93e7779ef21e 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -750,25 +750,38 @@ int __devm_add_action(struct device *dev, void (*action)(void *), void *data, co EXPORT_SYMBOL_GPL(__devm_add_action); /** - * devm_remove_action() - removes previously added custom action + * devm_remove_action_nowarn() - removes previously added custom action * @dev: Device that owns the action * @action: Function implementing the action * @data: Pointer to data passed to @action implementation * * Removes instance of @action previously added by devm_add_action(). * Both action and data should match one of the existing entries. + * + * In contrast to devm_remove_action(), this function does not WARN() if no + * entry could have been found. + * + * This should only be used if the action is contained in an object with + * independent lifetime management, e.g. the Devres rust abstraction. + * + * Causing the warning from regular driver code most likely indicates an abuse + * of the devres API. + * + * Returns: 0 on success, -ENOENT if no entry could have been found. */ -void devm_remove_action(struct device *dev, void (*action)(void *), void *data) +int devm_remove_action_nowarn(struct device *dev, + void (*action)(void *), + void *data) { struct action_devres devres = { .data = data, .action = action, }; - WARN_ON(devres_destroy(dev, devm_action_release, devm_action_match, - &devres)); + return devres_destroy(dev, devm_action_release, devm_action_match, + &devres); } -EXPORT_SYMBOL_GPL(devm_remove_action); +EXPORT_SYMBOL_GPL(devm_remove_action_nowarn); /** * devm_release_action() - release previously added custom action diff --git a/drivers/base/driver.c b/drivers/base/driver.c index b4eb5b89c4ee..8ab010ddf709 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -115,7 +115,7 @@ EXPORT_SYMBOL_GPL(driver_set_override); * Iterate over the @drv's list of devices calling @fn for each one. */ int driver_for_each_device(struct device_driver *drv, struct device *start, - void *data, int (*fn)(struct device *, void *)) + void *data, device_iter_t fn) { struct klist_iter i; struct device *dev; @@ -160,9 +160,12 @@ struct device *driver_find_device(const struct device_driver *drv, klist_iter_init_node(&drv->p->klist_devices, &i, (start ? &start->p->knode_driver : NULL)); - while ((dev = next_device(&i))) - if (match(dev, data) && get_device(dev)) + while ((dev = next_device(&i))) { + if (match(dev, data)) { + get_device(dev); break; + } + } klist_iter_exit(&i); return dev; } diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c index ddb70e29eb42..c8afc501a8a4 100644 --- a/drivers/base/firmware_loader/fallback_table.c +++ b/drivers/base/firmware_loader/fallback_table.c @@ -25,7 +25,7 @@ struct firmware_fallback_config fw_fallback_config = { EXPORT_SYMBOL_NS_GPL(fw_fallback_config, "FIRMWARE_LOADER_PRIVATE"); #ifdef CONFIG_SYSCTL -static struct ctl_table firmware_config_table[] = { +static const struct ctl_table firmware_config_table[] = { { .procname = "force_sysfs_fallback", .data = &fw_fallback_config.force_sysfs_fallback, diff --git a/drivers/base/firmware_loader/sysfs.c b/drivers/base/firmware_loader/sysfs.c index c9c93b47d9a5..d254ceb56d84 100644 --- a/drivers/base/firmware_loader/sysfs.c +++ b/drivers/base/firmware_loader/sysfs.c @@ -259,7 +259,7 @@ static void firmware_rw(struct fw_priv *fw_priv, char *buffer, } static ssize_t firmware_data_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t offset, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -316,7 +316,7 @@ static int fw_realloc_pages(struct fw_sysfs *fw_sysfs, int min_size) * the driver as a firmware image. **/ static ssize_t firmware_data_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t offset, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -356,11 +356,11 @@ out: return retval; } -static struct bin_attribute firmware_attr_data = { +static const struct bin_attribute firmware_attr_data = { .attr = { .name = "data", .mode = 0644 }, .size = 0, - .read = firmware_data_read, - .write = firmware_data_write, + .read_new = firmware_data_read, + .write_new = firmware_data_write, }; static struct attribute *fw_dev_attrs[] = { @@ -374,14 +374,14 @@ static struct attribute *fw_dev_attrs[] = { NULL }; -static struct bin_attribute *fw_dev_bin_attrs[] = { +static const struct bin_attribute *const fw_dev_bin_attrs[] = { &firmware_attr_data, NULL }; static const struct attribute_group fw_dev_attr_group = { .attrs = fw_dev_attrs, - .bin_attrs = fw_dev_bin_attrs, + .bin_attrs_new = fw_dev_bin_attrs, #ifdef CONFIG_FW_UPLOAD .is_visible = fw_upload_is_visible, #endif diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 67858eeb92ed..348c5dbbfa68 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -512,7 +512,7 @@ static ssize_t auto_online_blocks_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", - online_type_to_str[mhp_default_online_type]); + online_type_to_str[mhp_get_default_online_type()]); } static ssize_t auto_online_blocks_store(struct device *dev, @@ -524,7 +524,7 @@ static ssize_t auto_online_blocks_store(struct device *dev, if (online_type < 0) return -EINVAL; - mhp_default_online_type = online_type; + mhp_set_default_online_type(online_type); return count; } diff --git a/drivers/base/physical_location.c b/drivers/base/physical_location.c index 951819e71b4a..5db06e825c94 100644 --- a/drivers/base/physical_location.c +++ b/drivers/base/physical_location.c @@ -13,13 +13,11 @@ bool dev_add_physical_location(struct device *dev) { struct acpi_pld_info *pld; - acpi_status status; if (!has_acpi_companion(dev)) return false; - status = acpi_get_physical_device_location(ACPI_HANDLE(dev), &pld); - if (ACPI_FAILURE(status)) + if (!acpi_get_physical_device_location(ACPI_HANDLE(dev), &pld)) return false; dev->physical_location = diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 4a67e83300e1..d497d448e4b2 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -496,6 +496,7 @@ struct dpm_watchdog { struct device *dev; struct task_struct *tsk; struct timer_list timer; + bool fatal; }; #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \ @@ -512,11 +513,23 @@ struct dpm_watchdog { static void dpm_watchdog_handler(struct timer_list *t) { struct dpm_watchdog *wd = from_timer(wd, t, timer); + struct timer_list *timer = &wd->timer; + unsigned int time_left; - dev_emerg(wd->dev, "**** DPM device timeout ****\n"); - show_stack(wd->tsk, NULL, KERN_EMERG); - panic("%s %s: unrecoverable failure\n", - dev_driver_string(wd->dev), dev_name(wd->dev)); + if (wd->fatal) { + dev_emerg(wd->dev, "**** DPM device timeout ****\n"); + show_stack(wd->tsk, NULL, KERN_EMERG); + panic("%s %s: unrecoverable failure\n", + dev_driver_string(wd->dev), dev_name(wd->dev)); + } + + time_left = CONFIG_DPM_WATCHDOG_TIMEOUT - CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; + dev_warn(wd->dev, "**** DPM device timeout after %u seconds; %u seconds until panic ****\n", + CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT, time_left); + show_stack(wd->tsk, NULL, KERN_WARNING); + + wd->fatal = true; + mod_timer(timer, jiffies + HZ * time_left); } /** @@ -530,10 +543,11 @@ static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev) wd->dev = dev; wd->tsk = current; + wd->fatal = CONFIG_DPM_WATCHDOG_TIMEOUT == CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; timer_setup_on_stack(timer, dpm_watchdog_handler, 0); /* use same timeout value for both suspend and resume */ - timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_TIMEOUT; + timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; add_timer(timer); } @@ -642,13 +656,15 @@ static void device_resume_noirq(struct device *dev, pm_message_t state, bool asy * so change its status accordingly. * * Otherwise, the device is going to be resumed, so set its PM-runtime - * status to "active", but do that only if DPM_FLAG_SMART_SUSPEND is set - * to avoid confusing drivers that don't use it. + * status to "active" unless its power.set_active flag is clear, in + * which case it is not necessary to update its PM-runtime status. */ - if (skip_resume) + if (skip_resume) { pm_runtime_set_suspended(dev); - else if (dev_pm_skip_suspend(dev)) + } else if (dev->power.set_active) { pm_runtime_set_active(dev); + dev->power.set_active = false; + } if (dev->pm_domain) { info = "noirq power domain "; @@ -914,7 +930,7 @@ static void device_resume(struct device *dev, pm_message_t state, bool async) goto Complete; if (dev->power.direct_complete) { - /* Match the pm_runtime_disable() in __device_suspend(). */ + /* Match the pm_runtime_disable() in device_suspend(). */ pm_runtime_enable(dev); goto Complete; } @@ -1175,18 +1191,24 @@ static pm_message_t resume_event(pm_message_t sleep_state) return PMSG_ON; } -static void dpm_superior_set_must_resume(struct device *dev) +static void dpm_superior_set_must_resume(struct device *dev, bool set_active) { struct device_link *link; int idx; - if (dev->parent) + if (dev->parent) { dev->parent->power.must_resume = true; + if (set_active) + dev->parent->power.set_active = true; + } idx = device_links_read_lock(); - list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) + list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) { link->supplier->power.must_resume = true; + if (set_active) + link->supplier->power.set_active = true; + } device_links_read_unlock(idx); } @@ -1264,8 +1286,11 @@ Skip: dev->power.may_skip_resume)) dev->power.must_resume = true; - if (dev->power.must_resume) - dpm_superior_set_must_resume(dev); + if (dev->power.must_resume) { + dev->power.set_active = dev->power.set_active || + dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND); + dpm_superior_set_must_resume(dev, dev->power.set_active); + } Complete: complete_all(&dev->power.completion); diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index f8163b559bf9..f84018125b46 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -6,7 +6,6 @@ #include #include #include -#include #include #include #include "power.h" diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 5a5a9e978e85..8aa28c08b289 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -103,6 +103,32 @@ void dev_pm_clear_wake_irq(struct device *dev) } EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq); +static void devm_pm_clear_wake_irq(void *dev) +{ + dev_pm_clear_wake_irq(dev); +} + +/** + * devm_pm_set_wake_irq - device-managed variant of dev_pm_set_wake_irq + * @dev: Device entry + * @irq: Device IO interrupt + * + * + * Attach a device IO interrupt as a wake IRQ, same with dev_pm_set_wake_irq, + * but the device will be auto clear wake capability on driver detach. + */ +int devm_pm_set_wake_irq(struct device *dev, int irq) +{ + int ret; + + ret = dev_pm_set_wake_irq(dev, irq); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, devm_pm_clear_wake_irq, dev); +} +EXPORT_SYMBOL_GPL(devm_pm_set_wake_irq); + /** * handle_threaded_wake_irq - Handler for dedicated wake-up interrupts * @irq: Device specific dedicated wake-up interrupt diff --git a/drivers/base/property.c b/drivers/base/property.c index 837d77e3af2b..c1392743df9c 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -70,6 +70,44 @@ bool fwnode_property_present(const struct fwnode_handle *fwnode, } EXPORT_SYMBOL_GPL(fwnode_property_present); +/** + * device_property_read_bool - Return the value for a boolean property of a device + * @dev: Device whose property is being checked + * @propname: Name of the property + * + * Return if property @propname is true or false in the device firmware description. + * + * Return: true if property @propname is present. Otherwise, returns false. + */ +bool device_property_read_bool(const struct device *dev, const char *propname) +{ + return fwnode_property_read_bool(dev_fwnode(dev), propname); +} +EXPORT_SYMBOL_GPL(device_property_read_bool); + +/** + * fwnode_property_read_bool - Return the value for a boolean property of a firmware node + * @fwnode: Firmware node whose property to check + * @propname: Name of the property + * + * Return if property @propname is true or false in the firmware description. + */ +bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, + const char *propname) +{ + bool ret; + + if (IS_ERR_OR_NULL(fwnode)) + return false; + + ret = fwnode_call_bool_op(fwnode, property_read_bool, propname); + if (ret) + return ret; + + return fwnode_call_bool_op(fwnode->secondary, property_read_bool, propname); +} +EXPORT_SYMBOL_GPL(fwnode_property_read_bool); + /** * device_property_read_u8_array - return a u8 array property of a device * @dev: Device to get the property of diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c index 23da7b31d715..2319c30283a6 100644 --- a/drivers/base/regmap/regcache-maple.c +++ b/drivers/base/regmap/regcache-maple.c @@ -73,8 +73,7 @@ static int regcache_maple_write(struct regmap *map, unsigned int reg, rcu_read_unlock(); - entry = kmalloc((last - index + 1) * sizeof(unsigned long), - map->alloc_flags); + entry = kmalloc_array(last - index + 1, sizeof(*entry), map->alloc_flags); if (!entry) return -ENOMEM; @@ -204,7 +203,7 @@ static int regcache_maple_sync_block(struct regmap *map, unsigned long *entry, * overheads. */ if (max - min > 1 && regmap_can_raw_write(map)) { - buf = kmalloc(val_bytes * (max - min), map->alloc_flags); + buf = kmalloc_array(max - min, val_bytes, map->alloc_flags); if (!buf) { ret = -ENOMEM; goto out; @@ -320,7 +319,7 @@ static int regcache_maple_insert_block(struct regmap *map, int first, unsigned long *entry; int i, ret; - entry = kcalloc(last - first + 1, sizeof(unsigned long), map->alloc_flags); + entry = kmalloc_array(last - first + 1, sizeof(*entry), map->alloc_flags); if (!entry) return -ENOMEM; diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index 188438186589..a9d17f316e55 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -275,18 +275,16 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, pos = (reg - base_reg) / map->reg_stride; offset = (rbnode->base_reg - base_reg) / map->reg_stride; - blk = krealloc(rbnode->block, - blklen * map->cache_word_size, - map->alloc_flags); + blk = krealloc_array(rbnode->block, blklen, map->cache_word_size, map->alloc_flags); if (!blk) return -ENOMEM; rbnode->block = blk; if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) { - present = krealloc(rbnode->cache_present, - BITS_TO_LONGS(blklen) * sizeof(*present), - map->alloc_flags); + present = krealloc_array(rbnode->cache_present, + BITS_TO_LONGS(blklen), sizeof(*present), + map->alloc_flags); if (!present) return -ENOMEM; diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index d3659ba3cc11..b1f8508c3966 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -154,7 +154,7 @@ int regcache_init(struct regmap *map, const struct regmap_config *config) map->num_reg_defaults = config->num_reg_defaults; map->num_reg_defaults_raw = config->num_reg_defaults_raw; map->reg_defaults_raw = config->reg_defaults_raw; - map->cache_word_size = DIV_ROUND_UP(config->val_bits, 8); + map->cache_word_size = BITS_TO_BYTES(config->val_bits); map->cache_size_raw = map->cache_word_size * config->num_reg_defaults_raw; map->cache = NULL; diff --git a/drivers/base/regmap/regmap-sdw-mbq.c b/drivers/base/regmap/regmap-sdw-mbq.c index c99eada83780..86644bbd0710 100644 --- a/drivers/base/regmap/regmap-sdw-mbq.c +++ b/drivers/base/regmap/regmap-sdw-mbq.c @@ -1,45 +1,187 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright(c) 2020 Intel Corporation. +#include +#include #include #include +#include #include #include #include #include +#include #include "internal.h" +struct regmap_mbq_context { + struct device *dev; + + struct regmap_sdw_mbq_cfg cfg; + + int val_size; + bool (*readable_reg)(struct device *dev, unsigned int reg); +}; + +static int regmap_sdw_mbq_size(struct regmap_mbq_context *ctx, unsigned int reg) +{ + int size = ctx->val_size; + + if (ctx->cfg.mbq_size) { + size = ctx->cfg.mbq_size(ctx->dev, reg); + if (!size || size > ctx->val_size) + return -EINVAL; + } + + return size; +} + +static bool regmap_sdw_mbq_deferrable(struct regmap_mbq_context *ctx, unsigned int reg) +{ + if (ctx->cfg.deferrable) + return ctx->cfg.deferrable(ctx->dev, reg); + + return false; +} + +static int regmap_sdw_mbq_poll_busy(struct sdw_slave *slave, unsigned int reg, + struct regmap_mbq_context *ctx) +{ + struct device *dev = &slave->dev; + int val, ret = 0; + + dev_dbg(dev, "Deferring transaction for 0x%x\n", reg); + + reg = SDW_SDCA_CTL(SDW_SDCA_CTL_FUNC(reg), 0, + SDCA_CTL_ENTITY_0_FUNCTION_STATUS, 0); + + if (ctx->readable_reg(dev, reg)) { + ret = read_poll_timeout(sdw_read_no_pm, val, + val < 0 || !(val & SDCA_CTL_ENTITY_0_FUNCTION_BUSY), + ctx->cfg.timeout_us, ctx->cfg.retry_us, + false, slave, reg); + if (val < 0) + return val; + if (ret) + dev_err(dev, "Function busy timed out 0x%x: %d\n", reg, val); + } else { + fsleep(ctx->cfg.timeout_us); + } + + return ret; +} + +static int regmap_sdw_mbq_write_impl(struct sdw_slave *slave, + unsigned int reg, unsigned int val, + int mbq_size, bool deferrable) +{ + int shift = mbq_size * BITS_PER_BYTE; + int ret; + + while (--mbq_size > 0) { + shift -= BITS_PER_BYTE; + + ret = sdw_write_no_pm(slave, SDW_SDCA_MBQ_CTL(reg), + (val >> shift) & 0xff); + if (ret < 0) + return ret; + } + + ret = sdw_write_no_pm(slave, reg, val & 0xff); + if (deferrable && ret == -ENODATA) + return -EAGAIN; + + return ret; +} + static int regmap_sdw_mbq_write(void *context, unsigned int reg, unsigned int val) { - struct device *dev = context; + struct regmap_mbq_context *ctx = context; + struct device *dev = ctx->dev; struct sdw_slave *slave = dev_to_sdw_dev(dev); + bool deferrable = regmap_sdw_mbq_deferrable(ctx, reg); + int mbq_size = regmap_sdw_mbq_size(ctx, reg); int ret; - ret = sdw_write_no_pm(slave, SDW_SDCA_MBQ_CTL(reg), (val >> 8) & 0xff); - if (ret < 0) - return ret; + if (mbq_size < 0) + return mbq_size; - return sdw_write_no_pm(slave, reg, val & 0xff); + /* + * Technically the spec does allow a device to set itself to busy for + * internal reasons, but since it doesn't provide any information on + * how to handle timeouts in that case, for now the code will only + * process a single wait/timeout on function busy and a single retry + * of the transaction. + */ + ret = regmap_sdw_mbq_write_impl(slave, reg, val, mbq_size, deferrable); + if (ret == -EAGAIN) { + ret = regmap_sdw_mbq_poll_busy(slave, reg, ctx); + if (ret) + return ret; + + ret = regmap_sdw_mbq_write_impl(slave, reg, val, mbq_size, false); + } + + return ret; +} + +static int regmap_sdw_mbq_read_impl(struct sdw_slave *slave, + unsigned int reg, unsigned int *val, + int mbq_size, bool deferrable) +{ + int shift = BITS_PER_BYTE; + int read; + + read = sdw_read_no_pm(slave, reg); + if (read < 0) { + if (deferrable && read == -ENODATA) + return -EAGAIN; + + return read; + } + + *val = read; + + while (--mbq_size > 0) { + read = sdw_read_no_pm(slave, SDW_SDCA_MBQ_CTL(reg)); + if (read < 0) + return read; + + *val |= read << shift; + shift += BITS_PER_BYTE; + } + + return 0; } static int regmap_sdw_mbq_read(void *context, unsigned int reg, unsigned int *val) { - struct device *dev = context; + struct regmap_mbq_context *ctx = context; + struct device *dev = ctx->dev; struct sdw_slave *slave = dev_to_sdw_dev(dev); - int read0; - int read1; + bool deferrable = regmap_sdw_mbq_deferrable(ctx, reg); + int mbq_size = regmap_sdw_mbq_size(ctx, reg); + int ret; - read0 = sdw_read_no_pm(slave, reg); - if (read0 < 0) - return read0; + if (mbq_size < 0) + return mbq_size; - read1 = sdw_read_no_pm(slave, SDW_SDCA_MBQ_CTL(reg)); - if (read1 < 0) - return read1; + /* + * Technically the spec does allow a device to set itself to busy for + * internal reasons, but since it doesn't provide any information on + * how to handle timeouts in that case, for now the code will only + * process a single wait/timeout on function busy and a single retry + * of the transaction. + */ + ret = regmap_sdw_mbq_read_impl(slave, reg, val, mbq_size, deferrable); + if (ret == -EAGAIN) { + ret = regmap_sdw_mbq_poll_busy(slave, reg, ctx); + if (ret) + return ret; - *val = (read1 << 8) | read0; + ret = regmap_sdw_mbq_read_impl(slave, reg, val, mbq_size, false); + } - return 0; + return ret; } static const struct regmap_bus regmap_sdw_mbq = { @@ -51,8 +193,7 @@ static const struct regmap_bus regmap_sdw_mbq = { static int regmap_sdw_mbq_config_check(const struct regmap_config *config) { - /* MBQ-based controls are only 16-bits for now */ - if (config->val_bits != 16) + if (config->val_bits > (sizeof(unsigned int) * BITS_PER_BYTE)) return -ENOTSUPP; /* Registers are 32 bits wide */ @@ -65,35 +206,69 @@ static int regmap_sdw_mbq_config_check(const struct regmap_config *config) return 0; } +static struct regmap_mbq_context * +regmap_sdw_mbq_gen_context(struct device *dev, + const struct regmap_config *config, + const struct regmap_sdw_mbq_cfg *mbq_config) +{ + struct regmap_mbq_context *ctx; + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return ERR_PTR(-ENOMEM); + + ctx->dev = dev; + + if (mbq_config) + ctx->cfg = *mbq_config; + + ctx->val_size = config->val_bits / BITS_PER_BYTE; + ctx->readable_reg = config->readable_reg; + + return ctx; +} + struct regmap *__regmap_init_sdw_mbq(struct sdw_slave *sdw, const struct regmap_config *config, + const struct regmap_sdw_mbq_cfg *mbq_config, struct lock_class_key *lock_key, const char *lock_name) { + struct regmap_mbq_context *ctx; int ret; ret = regmap_sdw_mbq_config_check(config); if (ret) return ERR_PTR(ret); - return __regmap_init(&sdw->dev, ®map_sdw_mbq, - &sdw->dev, config, lock_key, lock_name); + ctx = regmap_sdw_mbq_gen_context(&sdw->dev, config, mbq_config); + if (IS_ERR(ctx)) + return ERR_CAST(ctx); + + return __regmap_init(&sdw->dev, ®map_sdw_mbq, ctx, + config, lock_key, lock_name); } EXPORT_SYMBOL_GPL(__regmap_init_sdw_mbq); struct regmap *__devm_regmap_init_sdw_mbq(struct sdw_slave *sdw, const struct regmap_config *config, + const struct regmap_sdw_mbq_cfg *mbq_config, struct lock_class_key *lock_key, const char *lock_name) { + struct regmap_mbq_context *ctx; int ret; ret = regmap_sdw_mbq_config_check(config); if (ret) return ERR_PTR(ret); - return __devm_regmap_init(&sdw->dev, ®map_sdw_mbq, - &sdw->dev, config, lock_key, lock_name); + ctx = regmap_sdw_mbq_gen_context(&sdw->dev, config, mbq_config); + if (IS_ERR(ctx)) + return ERR_CAST(ctx); + + return __devm_regmap_init(&sdw->dev, ®map_sdw_mbq, ctx, + config, lock_key, lock_name); } EXPORT_SYMBOL_GPL(__devm_regmap_init_sdw_mbq); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 5962ea1230a1..f2843f814675 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -769,14 +769,13 @@ struct regmap *__regmap_init(struct device *dev, map->alloc_flags = GFP_KERNEL; map->reg_base = config->reg_base; + map->reg_shift = config->pad_bits % 8; - map->format.reg_bytes = DIV_ROUND_UP(config->reg_bits, 8); map->format.pad_bytes = config->pad_bits / 8; map->format.reg_shift = config->reg_shift; - map->format.val_bytes = DIV_ROUND_UP(config->val_bits, 8); - map->format.buf_size = DIV_ROUND_UP(config->reg_bits + - config->val_bits + config->pad_bits, 8); - map->reg_shift = config->pad_bits % 8; + map->format.reg_bytes = BITS_TO_BYTES(config->reg_bits); + map->format.val_bytes = BITS_TO_BYTES(config->val_bits); + map->format.buf_size = BITS_TO_BYTES(config->reg_bits + config->val_bits + config->pad_bits); if (config->reg_stride) map->reg_stride = config->reg_stride; else @@ -3116,7 +3115,7 @@ int regmap_fields_read(struct regmap_field *field, unsigned int id, EXPORT_SYMBOL_GPL(regmap_fields_read); static int _regmap_bulk_read(struct regmap *map, unsigned int reg, - unsigned int *regs, void *val, size_t val_count) + const unsigned int *regs, void *val, size_t val_count) { u32 *u32 = val; u16 *u16 = val; @@ -3210,7 +3209,7 @@ EXPORT_SYMBOL_GPL(regmap_bulk_read); * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ -int regmap_multi_reg_read(struct regmap *map, unsigned int *regs, void *val, +int regmap_multi_reg_read(struct regmap *map, const unsigned int *regs, void *val, size_t val_count) { if (val_count == 0) diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index eb6eb25b343b..b1726a3515f6 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -677,6 +677,7 @@ static const struct fwnode_operations software_node_ops = { .get = software_node_get, .put = software_node_put, .property_present = software_node_property_present, + .property_read_bool = software_node_property_present, .property_read_int_array = software_node_read_int_array, .property_read_string_array = software_node_read_string_array, .get_name = software_node_get_name, diff --git a/drivers/base/test/Kconfig b/drivers/base/test/Kconfig index 5c7fac80611c..2756870615cc 100644 --- a/drivers/base/test/Kconfig +++ b/drivers/base/test/Kconfig @@ -12,6 +12,7 @@ config TEST_ASYNC_DRIVER_PROBE config DM_KUNIT_TEST tristate "KUnit Tests for the device model" if !KUNIT_ALL_TESTS depends on KUNIT + default KUNIT_ALL_TESTS config DRIVER_PE_KUNIT_TEST tristate "KUnit Tests for property entry API" if !KUNIT_ALL_TESTS diff --git a/drivers/base/test/platform-device-test.c b/drivers/base/test/platform-device-test.c index ea05b8785743..6355a2231b74 100644 --- a/drivers/base/test/platform-device-test.c +++ b/drivers/base/test/platform-device-test.c @@ -1,8 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include +#include +#include #include #define DEVICE_NAME "test" @@ -217,7 +220,43 @@ static struct kunit_suite platform_device_devm_test_suite = { .test_cases = platform_device_devm_tests, }; -kunit_test_suite(platform_device_devm_test_suite); +static void platform_device_find_by_null_test(struct kunit *test) +{ + struct platform_device *pdev; + int ret; + + pdev = kunit_platform_device_alloc(test, DEVICE_NAME, PLATFORM_DEVID_NONE); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev); + + ret = kunit_platform_device_add(test, pdev); + KUNIT_ASSERT_EQ(test, ret, 0); + + KUNIT_EXPECT_PTR_EQ(test, of_find_device_by_node(NULL), NULL); + + KUNIT_EXPECT_PTR_EQ(test, bus_find_device_by_of_node(&platform_bus_type, NULL), NULL); + KUNIT_EXPECT_PTR_EQ(test, bus_find_device_by_fwnode(&platform_bus_type, NULL), NULL); + KUNIT_EXPECT_PTR_EQ(test, bus_find_device_by_acpi_dev(&platform_bus_type, NULL), NULL); + + KUNIT_EXPECT_FALSE(test, device_match_of_node(&pdev->dev, NULL)); + KUNIT_EXPECT_FALSE(test, device_match_fwnode(&pdev->dev, NULL)); + KUNIT_EXPECT_FALSE(test, device_match_acpi_dev(&pdev->dev, NULL)); + KUNIT_EXPECT_FALSE(test, device_match_acpi_handle(&pdev->dev, NULL)); +} + +static struct kunit_case platform_device_match_tests[] = { + KUNIT_CASE(platform_device_find_by_null_test), + {} +}; + +static struct kunit_suite platform_device_match_test_suite = { + .name = "platform-device-match", + .test_cases = platform_device_match_tests, +}; + +kunit_test_suites( + &platform_device_devm_test_suite, + &platform_device_match_test_suite, +); MODULE_DESCRIPTION("Test module for platform devices"); MODULE_AUTHOR("Maxime Ripard "); diff --git a/drivers/base/topology.c b/drivers/base/topology.c index cf160dd2c27b..b962da263eee 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -27,9 +27,17 @@ static ssize_t name##_read(struct file *file, struct kobject *kobj, \ loff_t off, size_t count) \ { \ struct device *dev = kobj_to_dev(kobj); \ + cpumask_var_t mask; \ + ssize_t n; \ \ - return cpumap_print_bitmask_to_buf(buf, topology_##mask(dev->id), \ - off, count); \ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) \ + return -ENOMEM; \ + \ + cpumask_copy(mask, topology_##mask(dev->id)); \ + n = cpumap_print_bitmask_to_buf(buf, mask, off, count); \ + free_cpumask_var(mask); \ + \ + return n; \ } \ \ static ssize_t name##_list_read(struct file *file, struct kobject *kobj, \ @@ -37,9 +45,17 @@ static ssize_t name##_list_read(struct file *file, struct kobject *kobj, \ loff_t off, size_t count) \ { \ struct device *dev = kobj_to_dev(kobj); \ + cpumask_var_t mask; \ + ssize_t n; \ \ - return cpumap_print_list_to_buf(buf, topology_##mask(dev->id), \ - off, count); \ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) \ + return -ENOMEM; \ + \ + cpumask_copy(mask, topology_##mask(dev->id)); \ + n = cpumap_print_list_to_buf(buf, mask, off, count); \ + free_cpumask_var(mask); \ + \ + return n; \ } define_id_show_func(physical_package_id, "%d"); diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 49ced65bef4c..9edd4468f755 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1819,7 +1819,6 @@ static int fd_alloc_drive(int drive) unit[drive].tag_set.nr_maps = 1; unit[drive].tag_set.queue_depth = 2; unit[drive].tag_set.numa_node = NUMA_NO_NODE; - unit[drive].tag_set.flags = BLK_MQ_F_SHOULD_MERGE; if (blk_mq_alloc_tag_set(&unit[drive].tag_set)) goto out_cleanup_trackbuf; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 2028795ec61c..00b74a845328 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -368,7 +368,6 @@ aoeblk_gdalloc(void *vp) set->nr_hw_queues = 1; set->queue_depth = 128; set->numa_node = NUMA_NO_NODE; - set->flags = BLK_MQ_F_SHOULD_MERGE; err = blk_mq_alloc_tag_set(set); if (err) { pr_err("aoe: cannot allocate tag set for %ld.%d\n", diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index 3523dd82d7a0..4db7f6ce8ade 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -226,10 +226,11 @@ aoedev_downdev(struct aoedev *d) /* fast fail all pending I/O */ if (d->blkq) { /* UP is cleared, freeze+quiesce to insure all are errored */ - blk_mq_freeze_queue(d->blkq); + unsigned int memflags = blk_mq_freeze_queue(d->blkq); + blk_mq_quiesce_queue(d->blkq); blk_mq_unquiesce_queue(d->blkq); - blk_mq_unfreeze_queue(d->blkq); + blk_mq_unfreeze_queue(d->blkq, memflags); } if (d->gd) diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 4ba98c6654be..a81ade622a01 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -746,6 +746,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) unsigned char *p; int sect, nsect; unsigned long flags; + unsigned int memflags; int ret; if (type) { @@ -758,7 +759,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) } q = unit[drive].disk[type]->queue; - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); local_irq_save(flags); @@ -817,7 +818,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) ret = FormatError ? -EIO : 0; out: blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); return ret; } @@ -2088,7 +2089,6 @@ static int __init atari_floppy_init (void) unit[i].tag_set.nr_maps = 1; unit[i].tag_set.queue_depth = 2; unit[i].tag_set.numa_node = NUMA_NO_NODE; - unit[i].tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ret = blk_mq_alloc_tag_set(&unit[i].tag_set); if (ret) goto err; diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 3affb538b989..abf0486f0d4f 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4596,7 +4596,6 @@ static int __init do_floppy_init(void) tag_sets[drive].nr_maps = 1; tag_sets[drive].queue_depth = 2; tag_sets[drive].numa_node = NUMA_NO_NODE; - tag_sets[drive].flags = BLK_MQ_F_SHOULD_MERGE; err = blk_mq_alloc_tag_set(&tag_sets[drive]); if (err) goto out_put_disk; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 8f6761c27c68..c05fe27a96b6 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -68,7 +68,6 @@ struct loop_device { struct list_head idle_worker_list; struct rb_root worker_tree; struct timer_list timer; - bool use_dio; bool sysfs_inited; struct request_queue *lo_queue; @@ -182,41 +181,44 @@ static bool lo_bdev_can_use_dio(struct loop_device *lo, return true; } -static void __loop_update_dio(struct loop_device *lo, bool dio) +static bool lo_can_use_dio(struct loop_device *lo) { - struct file *file = lo->lo_backing_file; - struct inode *inode = file->f_mapping->host; - struct block_device *backing_bdev = NULL; - bool use_dio; + struct inode *inode = lo->lo_backing_file->f_mapping->host; + + if (!(lo->lo_backing_file->f_mode & FMODE_CAN_ODIRECT)) + return false; if (S_ISBLK(inode->i_mode)) - backing_bdev = I_BDEV(inode); - else if (inode->i_sb->s_bdev) - backing_bdev = inode->i_sb->s_bdev; + return lo_bdev_can_use_dio(lo, I_BDEV(inode)); + if (inode->i_sb->s_bdev) + return lo_bdev_can_use_dio(lo, inode->i_sb->s_bdev); + return true; +} - use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) && - (!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev)); +/* + * Direct I/O can be enabled either by using an O_DIRECT file descriptor, or by + * passing in the LO_FLAGS_DIRECT_IO flag from userspace. It will be silently + * disabled when the device block size is too small or the offset is unaligned. + * + * loop_get_status will always report the effective LO_FLAGS_DIRECT_IO flag and + * not the originally passed in one. + */ +static inline void loop_update_dio(struct loop_device *lo) +{ + bool dio_in_use = lo->lo_flags & LO_FLAGS_DIRECT_IO; - if (lo->use_dio == use_dio) - return; + lockdep_assert_held(&lo->lo_mutex); + WARN_ON_ONCE(lo->lo_state == Lo_bound && + lo->lo_queue->mq_freeze_depth == 0); - /* flush dirty pages before changing direct IO */ - vfs_fsync(file, 0); - - /* - * The flag of LO_FLAGS_DIRECT_IO is handled similarly with - * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup - * will get updated by ioctl(LOOP_GET_STATUS) - */ - if (lo->lo_state == Lo_bound) - blk_mq_freeze_queue(lo->lo_queue); - lo->use_dio = use_dio; - if (use_dio) + if (lo->lo_backing_file->f_flags & O_DIRECT) lo->lo_flags |= LO_FLAGS_DIRECT_IO; - else + if ((lo->lo_flags & LO_FLAGS_DIRECT_IO) && !lo_can_use_dio(lo)) lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; - if (lo->lo_state == Lo_bound) - blk_mq_unfreeze_queue(lo->lo_queue); + + /* flush dirty pages before starting to issue direct I/O */ + if ((lo->lo_flags & LO_FLAGS_DIRECT_IO) && !dio_in_use) + vfs_fsync(lo->lo_backing_file, 0); } /** @@ -311,6 +313,13 @@ static void loop_clear_limits(struct loop_device *lo, int mode) lim.discard_granularity = 0; } + /* + * XXX: this updates the queue limits without freezing the queue, which + * is against the locking protocol and dangerous. But we can't just + * freeze the queue as we're inside the ->queue_rq method here. So this + * should move out into a workqueue unless we get the file operations to + * advertise if they support specific fallocate operations. + */ queue_limits_commit_update(lo->lo_queue, &lim); } @@ -520,12 +529,6 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) } } -static inline void loop_update_dio(struct loop_device *lo) -{ - __loop_update_dio(lo, (lo->lo_backing_file->f_flags & O_DIRECT) | - lo->use_dio); -} - static void loop_reread_partitions(struct loop_device *lo) { int rc; @@ -583,6 +586,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, { struct file *file = fget(arg); struct file *old_file; + unsigned int memflags; int error; bool partscan; bool is_loop; @@ -620,14 +624,14 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, /* and ... switch */ disk_force_media_change(lo->lo_disk); - blk_mq_freeze_queue(lo->lo_queue); + memflags = blk_mq_freeze_queue(lo->lo_queue); mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); lo->lo_backing_file = file; lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping); mapping_set_gfp_mask(file->f_mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); loop_update_dio(lo); - blk_mq_unfreeze_queue(lo->lo_queue); + blk_mq_unfreeze_queue(lo->lo_queue, memflags); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; loop_global_unlock(lo, is_loop); @@ -964,7 +968,6 @@ loop_set_status_from_info(struct loop_device *lo, memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); lo->lo_file_name[LO_NAME_SIZE-1] = 0; - lo->lo_flags = info->lo_flags; return 0; } @@ -977,12 +980,12 @@ static unsigned int loop_default_blocksize(struct loop_device *lo, return SECTOR_SIZE; } -static int loop_reconfigure_limits(struct loop_device *lo, unsigned int bsize) +static void loop_update_limits(struct loop_device *lo, struct queue_limits *lim, + unsigned int bsize) { struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct block_device *backing_bdev = NULL; - struct queue_limits lim; u32 granularity = 0, max_discard_sectors = 0; if (S_ISBLK(inode->i_mode)) @@ -995,22 +998,20 @@ static int loop_reconfigure_limits(struct loop_device *lo, unsigned int bsize) loop_get_discard_config(lo, &granularity, &max_discard_sectors); - lim = queue_limits_start_update(lo->lo_queue); - lim.logical_block_size = bsize; - lim.physical_block_size = bsize; - lim.io_min = bsize; - lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL); + lim->logical_block_size = bsize; + lim->physical_block_size = bsize; + lim->io_min = bsize; + lim->features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL); if (file->f_op->fsync && !(lo->lo_flags & LO_FLAGS_READ_ONLY)) - lim.features |= BLK_FEAT_WRITE_CACHE; + lim->features |= BLK_FEAT_WRITE_CACHE; if (backing_bdev && !bdev_nonrot(backing_bdev)) - lim.features |= BLK_FEAT_ROTATIONAL; - lim.max_hw_discard_sectors = max_discard_sectors; - lim.max_write_zeroes_sectors = max_discard_sectors; + lim->features |= BLK_FEAT_ROTATIONAL; + lim->max_hw_discard_sectors = max_discard_sectors; + lim->max_write_zeroes_sectors = max_discard_sectors; if (max_discard_sectors) - lim.discard_granularity = granularity; + lim->discard_granularity = granularity; else - lim.discard_granularity = 0; - return queue_limits_commit_update(lo->lo_queue, &lim); + lim->discard_granularity = 0; } static int loop_configure(struct loop_device *lo, blk_mode_t mode, @@ -1019,6 +1020,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, { struct file *file = fget(config->fd); struct address_space *mapping; + struct queue_limits lim; int error; loff_t size; bool partscan; @@ -1063,6 +1065,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, error = loop_set_status_from_info(lo, &config->info); if (error) goto out_unlock; + lo->lo_flags = config->info.lo_flags; if (!(file->f_mode & FMODE_WRITE) || !(mode & BLK_OPEN_WRITE) || !file->f_op->write_iter) @@ -1084,13 +1087,15 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, disk_force_media_change(lo->lo_disk); set_disk_ro(lo->lo_disk, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); - lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO; lo->lo_device = bdev; lo->lo_backing_file = file; lo->old_gfp_mask = mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); - error = loop_reconfigure_limits(lo, config->block_size); + lim = queue_limits_start_update(lo->lo_queue); + loop_update_limits(lo, &lim, config->block_size); + /* No need to freeze the queue as the device isn't bound yet. */ + error = queue_limits_commit_update(lo->lo_queue, &lim); if (error) goto out_unlock; @@ -1150,7 +1155,12 @@ static void __loop_clr_fd(struct loop_device *lo) lo->lo_sizelimit = 0; memset(lo->lo_file_name, 0, LO_NAME_SIZE); - /* reset the block size to the default */ + /* + * Reset the block size to the default. + * + * No queue freezing needed because this is called from the final + * ->release call only, so there can't be any outstanding I/O. + */ lim = queue_limits_start_update(lo->lo_queue); lim.logical_block_size = SECTOR_SIZE; lim.physical_block_size = SECTOR_SIZE; @@ -1244,9 +1254,9 @@ static int loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { int err; - int prev_lo_flags; bool partscan = false; bool size_changed = false; + unsigned int memflags; err = mutex_lock_killable(&lo->lo_mutex); if (err) @@ -1263,21 +1273,18 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) invalidate_bdev(lo->lo_device); } - /* I/O need to be drained during transfer transition */ - blk_mq_freeze_queue(lo->lo_queue); - - prev_lo_flags = lo->lo_flags; + /* I/O needs to be drained before changing lo_offset or lo_sizelimit */ + memflags = blk_mq_freeze_queue(lo->lo_queue); err = loop_set_status_from_info(lo, info); if (err) goto out_unfreeze; - /* Mask out flags that can't be set using LOOP_SET_STATUS. */ - lo->lo_flags &= LOOP_SET_STATUS_SETTABLE_FLAGS; - /* For those flags, use the previous values instead */ - lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_SETTABLE_FLAGS; - /* For flags that can't be cleared, use previous values too */ - lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_CLEARABLE_FLAGS; + partscan = !(lo->lo_flags & LO_FLAGS_PARTSCAN) && + (info->lo_flags & LO_FLAGS_PARTSCAN); + + lo->lo_flags &= ~LOOP_SET_STATUS_CLEARABLE_FLAGS; + lo->lo_flags |= (info->lo_flags & LOOP_SET_STATUS_SETTABLE_FLAGS); if (size_changed) { loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit, @@ -1285,17 +1292,13 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) loop_set_size(lo, new_size); } - /* update dio if lo_offset or transfer is changed */ - __loop_update_dio(lo, lo->use_dio); + /* update the direct I/O flag if lo_offset changed */ + loop_update_dio(lo); out_unfreeze: - blk_mq_unfreeze_queue(lo->lo_queue); - - if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) && - !(prev_lo_flags & LO_FLAGS_PARTSCAN)) { + blk_mq_unfreeze_queue(lo->lo_queue, memflags); + if (partscan) clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); - partscan = true; - } out_unlock: mutex_unlock(&lo->lo_mutex); if (partscan) @@ -1444,20 +1447,34 @@ static int loop_set_capacity(struct loop_device *lo) static int loop_set_dio(struct loop_device *lo, unsigned long arg) { - int error = -ENXIO; - if (lo->lo_state != Lo_bound) - goto out; + bool use_dio = !!arg; + unsigned int memflags; - __loop_update_dio(lo, !!arg); - if (lo->use_dio == !!arg) + if (lo->lo_state != Lo_bound) + return -ENXIO; + if (use_dio == !!(lo->lo_flags & LO_FLAGS_DIRECT_IO)) return 0; - error = -EINVAL; - out: - return error; + + if (use_dio) { + if (!lo_can_use_dio(lo)) + return -EINVAL; + /* flush dirty pages before starting to use direct I/O */ + vfs_fsync(lo->lo_backing_file, 0); + } + + memflags = blk_mq_freeze_queue(lo->lo_queue); + if (use_dio) + lo->lo_flags |= LO_FLAGS_DIRECT_IO; + else + lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; + blk_mq_unfreeze_queue(lo->lo_queue, memflags); + return 0; } static int loop_set_block_size(struct loop_device *lo, unsigned long arg) { + struct queue_limits lim; + unsigned int memflags; int err = 0; if (lo->lo_state != Lo_bound) @@ -1469,10 +1486,13 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) sync_blockdev(lo->lo_device); invalidate_bdev(lo->lo_device); - blk_mq_freeze_queue(lo->lo_queue); - err = loop_reconfigure_limits(lo, arg); + lim = queue_limits_start_update(lo->lo_queue); + loop_update_limits(lo, &lim, arg); + + memflags = blk_mq_freeze_queue(lo->lo_queue); + err = queue_limits_commit_update(lo->lo_queue, &lim); loop_update_dio(lo); - blk_mq_unfreeze_queue(lo->lo_queue); + blk_mq_unfreeze_queue(lo->lo_queue, memflags); return err; } @@ -1854,7 +1874,7 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, cmd->use_aio = false; break; default: - cmd->use_aio = lo->use_dio; + cmd->use_aio = lo->lo_flags & LO_FLAGS_DIRECT_IO; break; } @@ -2023,8 +2043,7 @@ static int loop_add(int i) lo->tag_set.queue_depth = hw_queue_depth; lo->tag_set.numa_node = NUMA_NO_NODE; lo->tag_set.cmd_size = sizeof(struct loop_cmd); - lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING | - BLK_MQ_F_NO_SCHED_BY_DEFAULT; + lo->tag_set.flags = BLK_MQ_F_STACKING | BLK_MQ_F_NO_SCHED_BY_DEFAULT; lo->tag_set.driver_data = lo; err = blk_mq_alloc_tag_set(&lo->tag_set); diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 43701b7b10a7..95361099a2dc 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3416,7 +3416,6 @@ static int mtip_block_initialize(struct driver_data *dd) dd->tags.reserved_tags = 1; dd->tags.cmd_size = sizeof(struct mtip_cmd); dd->tags.numa_node = dd->numa_node; - dd->tags.flags = BLK_MQ_F_SHOULD_MERGE; dd->tags.driver_data = dd; dd->tags.timeout = MTIP_NCQ_CMD_TIMEOUT_MS; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index b852050d8a96..7bdc7eb808ea 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -62,6 +62,7 @@ struct nbd_sock { bool dead; int fallback_index; int cookie; + struct work_struct work; }; struct recv_thread_args { @@ -141,6 +142,9 @@ struct nbd_device { */ #define NBD_CMD_INFLIGHT 2 +/* Just part of request header or data payload is sent successfully */ +#define NBD_CMD_PARTIAL_SEND 3 + struct nbd_cmd { struct nbd_device *nbd; struct mutex lock; @@ -327,8 +331,7 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock, nsock->sent = 0; } -static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize, - loff_t blksize) +static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { struct queue_limits lim; int error; @@ -368,7 +371,7 @@ static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize, lim.logical_block_size = blksize; lim.physical_block_size = blksize; - error = queue_limits_commit_update(nbd->disk->queue, &lim); + error = queue_limits_commit_update_frozen(nbd->disk->queue, &lim); if (error) return error; @@ -379,18 +382,6 @@ static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize, return 0; } -static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, - loff_t blksize) -{ - int error; - - blk_mq_freeze_queue(nbd->disk->queue); - error = __nbd_set_size(nbd, bytesize, blksize); - blk_mq_unfreeze_queue(nbd->disk->queue); - - return error; -} - static void nbd_complete_rq(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); @@ -466,6 +457,12 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) if (!mutex_trylock(&cmd->lock)) return BLK_EH_RESET_TIMER; + /* partial send is handled in nbd_sock's work function */ + if (test_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags)) { + mutex_unlock(&cmd->lock); + return BLK_EH_RESET_TIMER; + } + if (!test_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { mutex_unlock(&cmd->lock); return BLK_EH_DONE; @@ -614,6 +611,30 @@ static inline int was_interrupted(int result) return result == -ERESTARTSYS || result == -EINTR; } +/* + * We've already sent header or part of data payload, have no choice but + * to set pending and schedule it in work. + * + * And we have to return BLK_STS_OK to block core, otherwise this same + * request may be re-dispatched with different tag, but our header has + * been sent out with old tag, and this way does confuse reply handling. + */ +static void nbd_sched_pending_work(struct nbd_device *nbd, + struct nbd_sock *nsock, + struct nbd_cmd *cmd, int sent) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + + /* pending work should be scheduled only once */ + WARN_ON_ONCE(test_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags)); + + nsock->pending = req; + nsock->sent = sent; + set_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags); + refcount_inc(&nbd->config_refs); + schedule_work(&nsock->work); +} + /* * Returns BLK_STS_RESOURCE if the caller should retry after a delay. * Returns BLK_STS_IOERR if sending failed. @@ -699,8 +720,8 @@ static blk_status_t nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, * completely done. */ if (sent) { - nsock->pending = req; - nsock->sent = sent; + nbd_sched_pending_work(nbd, nsock, cmd, sent); + return BLK_STS_OK; } set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; @@ -737,14 +758,8 @@ send_pages: result = sock_xmit(nbd, index, 1, &from, flags, &sent); if (result < 0) { if (was_interrupted(result)) { - /* We've already sent the header, we - * have no choice but to set pending and - * return BUSY. - */ - nsock->pending = req; - nsock->sent = sent; - set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return BLK_STS_RESOURCE; + nbd_sched_pending_work(nbd, nsock, cmd, sent); + return BLK_STS_OK; } dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", @@ -770,6 +785,14 @@ out: return BLK_STS_OK; requeue: + /* + * Can't requeue in case we are dealing with partial send + * + * We must run from pending work function. + * */ + if (test_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags)) + return BLK_STS_OK; + /* retry on a different socket */ dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); @@ -778,6 +801,44 @@ requeue: return BLK_STS_OK; } +/* handle partial sending */ +static void nbd_pending_cmd_work(struct work_struct *work) +{ + struct nbd_sock *nsock = container_of(work, struct nbd_sock, work); + struct request *req = nsock->pending; + struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); + struct nbd_device *nbd = cmd->nbd; + unsigned long deadline = READ_ONCE(req->deadline); + unsigned int wait_ms = 2; + + mutex_lock(&cmd->lock); + + WARN_ON_ONCE(test_bit(NBD_CMD_REQUEUED, &cmd->flags)); + if (WARN_ON_ONCE(!test_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags))) + goto out; + + mutex_lock(&nsock->tx_lock); + while (true) { + nbd_send_cmd(nbd, cmd, cmd->index); + if (!nsock->pending) + break; + + /* don't bother timeout handler for partial sending */ + if (READ_ONCE(jiffies) + msecs_to_jiffies(wait_ms) >= deadline) { + cmd->status = BLK_STS_IOERR; + blk_mq_complete_request(req); + break; + } + msleep(wait_ms); + wait_ms *= 2; + } + mutex_unlock(&nsock->tx_lock); + clear_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags); +out: + mutex_unlock(&cmd->lock); + nbd_config_put(nbd); +} + static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock, struct nbd_reply *reply) { @@ -1173,6 +1234,7 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, struct socket *sock; struct nbd_sock **socks; struct nbd_sock *nsock; + unsigned int memflags; int err; /* Arg will be cast to int, check it to avoid overflow */ @@ -1186,7 +1248,7 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, * We need to make sure we don't get any errant requests while we're * reallocating the ->socks array. */ - blk_mq_freeze_queue(nbd->disk->queue); + memflags = blk_mq_freeze_queue(nbd->disk->queue); if (!netlink && !nbd->task_setup && !test_bit(NBD_RT_BOUND, &config->runtime_flags)) @@ -1224,14 +1286,15 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, nsock->pending = NULL; nsock->sent = 0; nsock->cookie = 0; + INIT_WORK(&nsock->work, nbd_pending_cmd_work); socks[config->num_connections++] = nsock; atomic_inc(&config->live_connections); - blk_mq_unfreeze_queue(nbd->disk->queue); + blk_mq_unfreeze_queue(nbd->disk->queue, memflags); return 0; put_socket: - blk_mq_unfreeze_queue(nbd->disk->queue); + blk_mq_unfreeze_queue(nbd->disk->queue, memflags); sockfd_put(sock); return err; } @@ -1841,8 +1904,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) nbd->tag_set.queue_depth = 128; nbd->tag_set.numa_node = NUMA_NO_NODE; nbd->tag_set.cmd_size = sizeof(struct nbd_cmd); - nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | - BLK_MQ_F_BLOCKING; + nbd->tag_set.flags = BLK_MQ_F_BLOCKING; nbd->tag_set.driver_data = nbd; INIT_WORK(&nbd->remove_work, nbd_dev_remove_work); nbd->backend = NULL; @@ -2180,6 +2242,7 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) flush_workqueue(nbd->recv_workq); nbd_clear_que(nbd); nbd->task_setup = NULL; + clear_bit(NBD_RT_BOUND, &nbd->config->runtime_flags); mutex_unlock(&nbd->config_lock); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 3c3d8d200abb..d94ef37480bd 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -266,6 +266,10 @@ static bool g_zone_full; module_param_named(zone_full, g_zone_full, bool, S_IRUGO); MODULE_PARM_DESC(zone_full, "Initialize the sequential write required zones of a zoned device to be full. Default: false"); +static bool g_rotational; +module_param_named(rotational, g_rotational, bool, S_IRUGO); +MODULE_PARM_DESC(rotational, "Set the rotational feature for the device. Default: false"); + static struct nullb_device *null_alloc_dev(void); static void null_free_dev(struct nullb_device *dev); static void null_del_dev(struct nullb *nullb); @@ -468,6 +472,7 @@ NULLB_DEVICE_ATTR(no_sched, bool, NULL); NULLB_DEVICE_ATTR(shared_tags, bool, NULL); NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL); NULLB_DEVICE_ATTR(fua, bool, NULL); +NULLB_DEVICE_ATTR(rotational, bool, NULL); static ssize_t nullb_device_power_show(struct config_item *item, char *page) { @@ -621,6 +626,7 @@ static struct configfs_attribute *nullb_device_attrs[] = { &nullb_device_attr_shared_tags, &nullb_device_attr_shared_tag_bitmap, &nullb_device_attr_fua, + &nullb_device_attr_rotational, NULL, }; @@ -706,7 +712,8 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page) "shared_tags,size,submit_queues,use_per_node_hctx," "virt_boundary,zoned,zone_capacity,zone_max_active," "zone_max_open,zone_nr_conv,zone_offline,zone_readonly," - "zone_size,zone_append_max_sectors,zone_full\n"); + "zone_size,zone_append_max_sectors,zone_full," + "rotational\n"); } CONFIGFS_ATTR_RO(memb_group_, features); @@ -793,6 +800,7 @@ static struct nullb_device *null_alloc_dev(void) dev->shared_tags = g_shared_tags; dev->shared_tag_bitmap = g_shared_tag_bitmap; dev->fua = g_fua; + dev->rotational = g_rotational; return dev; } @@ -899,7 +907,7 @@ static struct nullb_page *null_radix_tree_insert(struct nullb *nullb, u64 idx, if (radix_tree_insert(root, idx, t_page)) { null_free_page(t_page); t_page = radix_tree_lookup(root, idx); - WARN_ON(!t_page || t_page->page->index != idx); + WARN_ON(!t_page || t_page->page->private != idx); } else if (is_cache) nullb->dev->curr_cache += PAGE_SIZE; @@ -922,7 +930,7 @@ static void null_free_device_storage(struct nullb_device *dev, bool is_cache) (void **)t_pages, pos, FREE_BATCH); for (i = 0; i < nr_pages; i++) { - pos = t_pages[i]->page->index; + pos = t_pages[i]->page->private; ret = radix_tree_delete_item(root, pos, t_pages[i]); WARN_ON(ret != t_pages[i]); null_free_page(ret); @@ -948,7 +956,7 @@ static struct nullb_page *__null_lookup_page(struct nullb *nullb, root = is_cache ? &nullb->dev->cache : &nullb->dev->data; t_page = radix_tree_lookup(root, idx); - WARN_ON(t_page && t_page->page->index != idx); + WARN_ON(t_page && t_page->page->private != idx); if (t_page && (for_write || test_bit(sector_bit, t_page->bitmap))) return t_page; @@ -991,7 +999,7 @@ static struct nullb_page *null_insert_page(struct nullb *nullb, spin_lock_irq(&nullb->lock); idx = sector >> PAGE_SECTORS_SHIFT; - t_page->page->index = idx; + t_page->page->private = idx; t_page = null_radix_tree_insert(nullb, idx, t_page, !ignore_cache); radix_tree_preload_end(); @@ -1011,7 +1019,7 @@ static int null_flush_cache_page(struct nullb *nullb, struct nullb_page *c_page) struct nullb_page *t_page, *ret; void *dst, *src; - idx = c_page->page->index; + idx = c_page->page->private; t_page = null_insert_page(nullb, idx << PAGE_SECTORS_SHIFT, true); @@ -1070,7 +1078,7 @@ again: * avoid race, we don't allow page free */ for (i = 0; i < nr_pages; i++) { - nullb->cache_flush_pos = c_pages[i]->page->index; + nullb->cache_flush_pos = c_pages[i]->page->private; /* * We found the page which is being flushed to disk by other * threads @@ -1783,9 +1791,8 @@ static int null_init_global_tag_set(void) tag_set.nr_hw_queues = g_submit_queues; tag_set.queue_depth = g_hw_queue_depth; tag_set.numa_node = g_home_node; - tag_set.flags = BLK_MQ_F_SHOULD_MERGE; if (g_no_sched) - tag_set.flags |= BLK_MQ_F_NO_SCHED; + tag_set.flags |= BLK_MQ_F_NO_SCHED_BY_DEFAULT; if (g_shared_tag_bitmap) tag_set.flags |= BLK_MQ_F_TAG_HCTX_SHARED; if (g_blocking) @@ -1809,9 +1816,8 @@ static int null_setup_tagset(struct nullb *nullb) nullb->tag_set->nr_hw_queues = nullb->dev->submit_queues; nullb->tag_set->queue_depth = nullb->dev->hw_queue_depth; nullb->tag_set->numa_node = nullb->dev->home_node; - nullb->tag_set->flags = BLK_MQ_F_SHOULD_MERGE; if (nullb->dev->no_sched) - nullb->tag_set->flags |= BLK_MQ_F_NO_SCHED; + nullb->tag_set->flags |= BLK_MQ_F_NO_SCHED_BY_DEFAULT; if (nullb->dev->shared_tag_bitmap) nullb->tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED; if (nullb->dev->blocking) @@ -1938,6 +1944,9 @@ static int null_add_dev(struct nullb_device *dev) lim.features |= BLK_FEAT_FUA; } + if (dev->rotational) + lim.features |= BLK_FEAT_ROTATIONAL; + nullb->disk = blk_mq_alloc_disk(nullb->tag_set, &lim, nullb); if (IS_ERR(nullb->disk)) { rv = PTR_ERR(nullb->disk); diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index a7bb32f73ec3..6f9fe6171087 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -107,6 +107,7 @@ struct nullb_device { bool shared_tags; /* share tag set between devices for blk-mq */ bool shared_tag_bitmap; /* use hostwide shared tags */ bool fua; /* Support FUA */ + bool rotational; /* Fake rotational device */ }; struct nullb { diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index ff45ed766469..dc9e4a14b885 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -384,9 +384,9 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) unsigned int devidx; struct queue_limits lim = { .logical_block_size = dev->blk_size, - .max_hw_sectors = dev->bounce_size >> 9, + .max_hw_sectors = BOUNCE_SIZE >> 9, .max_segments = -1, - .max_segment_size = dev->bounce_size, + .max_segment_size = BOUNCE_SIZE, .dma_alignment = dev->blk_size - 1, .features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL, @@ -434,8 +434,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) ps3disk_identify(dev); - error = blk_mq_alloc_sq_tag_set(&priv->tag_set, &ps3disk_mq_ops, 1, - BLK_MQ_F_SHOULD_MERGE); + error = blk_mq_alloc_sq_tag_set(&priv->tag_set, &ps3disk_mq_ops, 1, 0); if (error) goto fail_teardown; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index ac421dbeeb11..faafd7ff43d6 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4964,7 +4964,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) rbd_dev->tag_set.ops = &rbd_mq_ops; rbd_dev->tag_set.queue_depth = rbd_dev->opts->queue_depth; rbd_dev->tag_set.numa_node = NUMA_NO_NODE; - rbd_dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; rbd_dev->tag_set.nr_hw_queues = num_present_cpus(); rbd_dev->tag_set.cmd_size = sizeof(struct rbd_img_request); @@ -7282,9 +7281,10 @@ static ssize_t do_rbd_remove(const char *buf, size_t count) * Prevent new IO from being queued and wait for existing * IO to complete/fail. */ - blk_mq_freeze_queue(rbd_dev->disk->queue); + unsigned int memflags = blk_mq_freeze_queue(rbd_dev->disk->queue); + blk_mark_disk_dead(rbd_dev->disk); - blk_mq_unfreeze_queue(rbd_dev->disk->queue); + blk_mq_unfreeze_queue(rbd_dev->disk->queue, memflags); } del_gendisk(rbd_dev->disk); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index c34695d2eea7..82467ecde7ec 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1209,8 +1209,7 @@ static int setup_mq_tags(struct rnbd_clt_session *sess) tag_set->ops = &rnbd_mq_ops; tag_set->queue_depth = sess->queue_depth; tag_set->numa_node = NUMA_NO_NODE; - tag_set->flags = BLK_MQ_F_SHOULD_MERGE | - BLK_MQ_F_TAG_QUEUE_SHARED; + tag_set->flags = BLK_MQ_F_TAG_QUEUE_SHARED; tag_set->cmd_size = sizeof(struct rnbd_iu) + RNBD_RDMA_SGL_SIZE; /* for HCTX_TYPE_DEFAULT, HCTX_TYPE_READ, HCTX_TYPE_POLL */ diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 08ce6d96d04c..2ee6e9bd4e28 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -167,7 +167,7 @@ static int process_rdma(struct rnbd_srv_session *srv_sess, bio->bi_iter.bi_sector = le64_to_cpu(msg->sector); prio = srv_sess->ver < RNBD_PROTO_VER_MAJOR || usrlen < sizeof(*msg) ? 0 : le16_to_cpu(msg->prio); - bio_set_prio(bio, prio); + bio->bi_ioprio = prio; submit_bio(bio); diff --git a/drivers/block/rnull.rs b/drivers/block/rnull.rs index 9cca05dcf772..ddf3629d8894 100644 --- a/drivers/block/rnull.rs +++ b/drivers/block/rnull.rs @@ -32,25 +32,31 @@ module! { license: "GPL v2", } +#[pin_data] struct NullBlkModule { - _disk: Pin>>>, + #[pin] + _disk: Mutex>, } -impl kernel::Module for NullBlkModule { - fn init(_module: &'static ThisModule) -> Result { +impl kernel::InPlaceModule for NullBlkModule { + fn init(_module: &'static ThisModule) -> impl PinInit { pr_info!("Rust null_blk loaded\n"); - let tagset = Arc::pin_init(TagSet::new(1, 256, 1), flags::GFP_KERNEL)?; - let disk = gen_disk::GenDiskBuilder::new() - .capacity_sectors(4096 << 11) - .logical_block_size(4096)? - .physical_block_size(4096)? - .rotational(false) - .build(format_args!("rnullb{}", 0), tagset)?; + // Use a immediately-called closure as a stable `try` block + let disk = /* try */ (|| { + let tagset = Arc::pin_init(TagSet::new(1, 256, 1), flags::GFP_KERNEL)?; - let disk = KBox::pin_init(new_mutex!(disk, "nullb:disk"), flags::GFP_KERNEL)?; + gen_disk::GenDiskBuilder::new() + .capacity_sectors(4096 << 11) + .logical_block_size(4096)? + .physical_block_size(4096)? + .rotational(false) + .build(format_args!("rnullb{}", 0), tagset) + })(); - Ok(Self { _disk: disk }) + try_pin_init!(Self { + _disk <- new_mutex!(disk?, "nullb:disk"), + }) } } diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 2d38331ee667..33b3bc99d532 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -829,7 +829,7 @@ static int probe_disk(struct vdc_port *port) } err = blk_mq_alloc_sq_tag_set(&port->tag_set, &vdc_mq_ops, - VDC_TX_RING_SIZE, BLK_MQ_F_SHOULD_MERGE); + VDC_TX_RING_SIZE, 0); if (err) return err; @@ -918,12 +918,12 @@ struct vdc_check_port_data { char *type; }; -static int vdc_device_probed(struct device *dev, void *arg) +static int vdc_device_probed(struct device *dev, const void *arg) { struct vio_dev *vdev = to_vio_dev(dev); - struct vdc_check_port_data *port_data; + const struct vdc_check_port_data *port_data; - port_data = (struct vdc_check_port_data *)arg; + port_data = (const struct vdc_check_port_data *)arg; if ((vdev->dev_no == port_data->dev_no) && (!(strcmp((char *)&vdev->type, port_data->type))) && @@ -1113,6 +1113,7 @@ static void vdc_requeue_inflight(struct vdc_port *port) static void vdc_queue_drain(struct vdc_port *port) { struct request_queue *q = port->disk->queue; + unsigned int memflags; /* * Mark the queue as draining, then freeze/quiesce to ensure @@ -1121,12 +1122,12 @@ static void vdc_queue_drain(struct vdc_port *port) port->drain = 1; spin_unlock_irq(&port->vio.lock); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); spin_lock_irq(&port->vio.lock); port->drain = 0; - blk_mq_unquiesce_queue(q); + blk_mq_unquiesce_queue(q, memflags); blk_mq_unfreeze_queue(q); } diff --git a/drivers/block/swim.c b/drivers/block/swim.c index be4ac58afe41..eda33c5eb5e2 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -818,7 +818,7 @@ static int swim_floppy_init(struct swim_priv *swd) for (drive = 0; drive < swd->floppy_count; drive++) { err = blk_mq_alloc_sq_tag_set(&swd->unit[drive].tag_set, - &swim_mq_ops, 2, BLK_MQ_F_SHOULD_MERGE); + &swim_mq_ops, 2, 0); if (err) goto exit_put_disks; diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 90be1017f7bf..3aedcb5add61 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -840,6 +840,7 @@ static int grab_drive(struct floppy_state *fs, enum swim_state state, static void release_drive(struct floppy_state *fs) { struct request_queue *q = disks[fs->index]->queue; + unsigned int memflags; unsigned long flags; swim3_dbg("%s", "-> release drive\n"); @@ -848,10 +849,10 @@ static void release_drive(struct floppy_state *fs) fs->state = idle; spin_unlock_irqrestore(&swim3_lock, flags); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } static int fd_eject(struct floppy_state *fs) @@ -1208,8 +1209,7 @@ static int swim3_attach(struct macio_dev *mdev, fs = &floppy_states[floppy_count]; memset(fs, 0, sizeof(*fs)); - rc = blk_mq_alloc_sq_tag_set(&fs->tag_set, &swim3_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); + rc = blk_mq_alloc_sq_tag_set(&fs->tag_set, &swim3_mq_ops, 2, 0); if (rc) goto out_unregister; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index d4aed12dd436..529085181f35 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1618,6 +1618,21 @@ static void ublk_unquiesce_dev(struct ublk_device *ub) blk_mq_kick_requeue_list(ub->ub_disk->queue); } +static struct gendisk *ublk_detach_disk(struct ublk_device *ub) +{ + struct gendisk *disk; + + /* Sync with ublk_abort_queue() by holding the lock */ + spin_lock(&ub->lock); + disk = ub->ub_disk; + ub->dev_info.state = UBLK_S_DEV_DEAD; + ub->dev_info.ublksrv_pid = -1; + ub->ub_disk = NULL; + spin_unlock(&ub->lock); + + return disk; +} + static void ublk_stop_dev(struct ublk_device *ub) { struct gendisk *disk; @@ -1631,14 +1646,7 @@ static void ublk_stop_dev(struct ublk_device *ub) ublk_unquiesce_dev(ub); } del_gendisk(ub->ub_disk); - - /* Sync with ublk_abort_queue() by holding the lock */ - spin_lock(&ub->lock); - disk = ub->ub_disk; - ub->dev_info.state = UBLK_S_DEV_DEAD; - ub->dev_info.ublksrv_pid = -1; - ub->ub_disk = NULL; - spin_unlock(&ub->lock); + disk = ublk_detach_disk(ub); put_disk(disk); unlock: mutex_unlock(&ub->mutex); @@ -2205,7 +2213,6 @@ static int ublk_add_tag_set(struct ublk_device *ub) ub->tag_set.queue_depth = ub->dev_info.queue_depth; ub->tag_set.numa_node = NUMA_NO_NODE; ub->tag_set.cmd_size = sizeof(struct ublk_rq_data); - ub->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ub->tag_set.driver_data = ub; return blk_mq_alloc_tag_set(&ub->tag_set); } @@ -2336,7 +2343,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) out_put_cdev: if (ret) { - ub->dev_info.state = UBLK_S_DEV_DEAD; + ublk_detach_disk(ub); ublk_put_device(ub); } if (ret) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 3efe378f1386..6a61ec35f426 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include @@ -1106,9 +1105,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr, lim.features |= BLK_FEAT_WRITE_CACHE; else lim.features &= ~BLK_FEAT_WRITE_CACHE; - blk_mq_freeze_queue(disk->queue); - i = queue_limits_commit_update(disk->queue, &lim); - blk_mq_unfreeze_queue(disk->queue); + i = queue_limits_commit_update_frozen(disk->queue, &lim); if (i) return i; return count; @@ -1181,7 +1178,8 @@ static void virtblk_map_queues(struct blk_mq_tag_set *set) if (i == HCTX_TYPE_POLL) blk_mq_map_queues(&set->map[i]); else - blk_mq_virtio_map_queues(&set->map[i], vblk->vdev, 0); + blk_mq_map_hw_queues(&set->map[i], + &vblk->vdev->dev, 0); } } @@ -1481,7 +1479,6 @@ static int virtblk_probe(struct virtio_device *vdev) vblk->tag_set.ops = &virtio_mq_ops; vblk->tag_set.queue_depth = queue_depth; vblk->tag_set.numa_node = NUMA_NO_NODE; - vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; vblk->tag_set.cmd_size = sizeof(struct virtblk_req) + sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT; @@ -1582,16 +1579,16 @@ static void virtblk_remove(struct virtio_device *vdev) put_disk(vblk->disk); } -#ifdef CONFIG_PM_SLEEP -static int virtblk_freeze(struct virtio_device *vdev) +static int virtblk_freeze_priv(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; struct request_queue *q = vblk->disk->queue; + unsigned int memflags; /* Ensure no requests in virtqueues before deleting vqs. */ - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue_nowait(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); /* Ensure we don't receive any more interrupts */ virtio_reset_device(vdev); @@ -1605,7 +1602,7 @@ static int virtblk_freeze(struct virtio_device *vdev) return 0; } -static int virtblk_restore(struct virtio_device *vdev) +static int virtblk_restore_priv(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; int ret; @@ -1619,8 +1616,29 @@ static int virtblk_restore(struct virtio_device *vdev) return 0; } + +#ifdef CONFIG_PM_SLEEP +static int virtblk_freeze(struct virtio_device *vdev) +{ + return virtblk_freeze_priv(vdev); +} + +static int virtblk_restore(struct virtio_device *vdev) +{ + return virtblk_restore_priv(vdev); +} #endif +static int virtblk_reset_prepare(struct virtio_device *vdev) +{ + return virtblk_freeze_priv(vdev); +} + +static int virtblk_reset_done(struct virtio_device *vdev) +{ + return virtblk_restore_priv(vdev); +} + static const struct virtio_device_id id_table[] = { { VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID }, { 0 }, @@ -1656,6 +1674,8 @@ static struct virtio_driver virtio_blk = { .freeze = virtblk_freeze, .restore = virtblk_restore, #endif + .reset_prepare = virtblk_reset_prepare, + .reset_done = virtblk_reset_done, }; static int __init virtio_blk_init(void) diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 838064593f62..a7c2b04ab943 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -544,7 +544,7 @@ static void print_stats(struct xen_blkif_ring *ring) ring->st_rd_req, ring->st_wr_req, ring->st_f_req, ring->st_ds_req, ring->persistent_gnt_c, max_pgrants); - ring->st_print = jiffies + msecs_to_jiffies(10 * 1000); + ring->st_print = jiffies + secs_to_jiffies(10); ring->st_rd_req = 0; ring->st_wr_req = 0; ring->st_oo_req = 0; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 59ce113b882a..edcd08a9dcef 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1131,7 +1131,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, } else info->tag_set.queue_depth = BLK_RING_SIZE(info); info->tag_set.numa_node = NUMA_NO_NODE; - info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; info->tag_set.cmd_size = sizeof(struct blkif_req); info->tag_set.driver_data = info; diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index 4b7219be1bb8..8c1c7f4211eb 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -354,7 +354,6 @@ static int __init z2_init(void) tag_set.nr_maps = 1; tag_set.queue_depth = 16; tag_set.numa_node = NUMA_NO_NODE; - tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ret = blk_mq_alloc_tag_set(&tag_set); if (ret) goto out_unregister_blkdev; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 3dee026988dc..9f5020b077c5 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -55,8 +55,8 @@ static size_t huge_class_size; static const struct block_device_operations zram_devops; static void zram_free_page(struct zram *zram, size_t index); -static int zram_read_page(struct zram *zram, struct page *page, u32 index, - struct bio *parent); +static int zram_read_from_zspool(struct zram *zram, struct page *page, + u32 index); static int zram_slot_trylock(struct zram *zram, u32 index) { @@ -112,17 +112,6 @@ static void zram_clear_flag(struct zram *zram, u32 index, zram->table[index].flags &= ~BIT(flag); } -static inline void zram_set_element(struct zram *zram, u32 index, - unsigned long element) -{ - zram->table[index].element = element; -} - -static unsigned long zram_get_element(struct zram *zram, u32 index) -{ - return zram->table[index].element; -} - static size_t zram_get_obj_size(struct zram *zram, u32 index) { return zram->table[index].flags & (BIT(ZRAM_FLAG_SHIFT) - 1); @@ -143,6 +132,27 @@ static inline bool zram_allocated(struct zram *zram, u32 index) zram_test_flag(zram, index, ZRAM_WB); } +static inline void update_used_max(struct zram *zram, const unsigned long pages) +{ + unsigned long cur_max = atomic_long_read(&zram->stats.max_used_pages); + + do { + if (cur_max >= pages) + return; + } while (!atomic_long_try_cmpxchg(&zram->stats.max_used_pages, + &cur_max, pages)); +} + +static bool zram_can_store_page(struct zram *zram) +{ + unsigned long alloced_pages; + + alloced_pages = zs_get_total_pages(zram->mem_pool); + update_used_max(zram, alloced_pages); + + return !zram->limit_pages || alloced_pages <= zram->limit_pages; +} + #if PAGE_SIZE != 4096 static inline bool is_partial_io(struct bio_vec *bvec) { @@ -277,18 +287,6 @@ static struct zram_pp_slot *select_pp_slot(struct zram_pp_ctl *ctl) } #endif -static inline void update_used_max(struct zram *zram, - const unsigned long pages) -{ - unsigned long cur_max = atomic_long_read(&zram->stats.max_used_pages); - - do { - if (cur_max >= pages) - return; - } while (!atomic_long_try_cmpxchg(&zram->stats.max_used_pages, - &cur_max, pages)); -} - static inline void zram_fill_page(void *ptr, unsigned long len, unsigned long value) { @@ -614,6 +612,12 @@ static ssize_t backing_dev_store(struct device *dev, } nr_pages = i_size_read(inode) >> PAGE_SHIFT; + /* Refuse to use zero sized device (also prevents self reference) */ + if (!nr_pages) { + err = -EINVAL; + goto out; + } + bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long); bitmap = kvzalloc(bitmap_sz, GFP_KERNEL); if (!bitmap) { @@ -827,13 +831,10 @@ static ssize_t writeback_store(struct device *dev, */ if (!zram_test_flag(zram, index, ZRAM_PP_SLOT)) goto next; + if (zram_read_from_zspool(zram, page, index)) + goto next; zram_slot_unlock(zram, index); - if (zram_read_page(zram, page, index, NULL)) { - release_pp_slot(zram, pps); - continue; - } - bio_init(&bio, zram->bdev, &bio_vec, 1, REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); @@ -873,7 +874,7 @@ static ssize_t writeback_store(struct device *dev, zram_free_page(zram, index); zram_set_flag(zram, index, ZRAM_WB); - zram_set_element(zram, index, blk_idx); + zram_set_handle(zram, index, blk_idx); blk_idx = 0; atomic64_inc(&zram->stats.pages_stored); spin_lock(&zram->wb_limit_lock); @@ -883,6 +884,8 @@ static ssize_t writeback_store(struct device *dev, next: zram_slot_unlock(zram, index); release_pp_slot(zram, pps); + + cond_resched(); } if (blk_idx) @@ -1438,12 +1441,16 @@ static void zram_meta_free(struct zram *zram, u64 disksize) size_t num_pages = disksize >> PAGE_SHIFT; size_t index; + if (!zram->table) + return; + /* Free all pages that are still in this zram device */ for (index = 0; index < num_pages; index++) zram_free_page(zram, index); zs_destroy_pool(zram->mem_pool); vfree(zram->table); + zram->table = NULL; } static bool zram_meta_alloc(struct zram *zram, u64 disksize) @@ -1458,6 +1465,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) zram->mem_pool = zs_create_pool(zram->disk->disk_name); if (!zram->mem_pool) { vfree(zram->table); + zram->table = NULL; return false; } @@ -1494,7 +1502,7 @@ static void zram_free_page(struct zram *zram, size_t index) if (zram_test_flag(zram, index, ZRAM_WB)) { zram_clear_flag(zram, index, ZRAM_WB); - free_block_bdev(zram, zram_get_element(zram, index)); + free_block_bdev(zram, zram_get_handle(zram, index)); goto out; } @@ -1522,6 +1530,56 @@ out: zram_set_obj_size(zram, index, 0); } +static int read_same_filled_page(struct zram *zram, struct page *page, + u32 index) +{ + void *mem; + + mem = kmap_local_page(page); + zram_fill_page(mem, PAGE_SIZE, zram_get_handle(zram, index)); + kunmap_local(mem); + return 0; +} + +static int read_incompressible_page(struct zram *zram, struct page *page, + u32 index) +{ + unsigned long handle; + void *src, *dst; + + handle = zram_get_handle(zram, index); + src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); + dst = kmap_local_page(page); + copy_page(dst, src); + kunmap_local(dst); + zs_unmap_object(zram->mem_pool, handle); + + return 0; +} + +static int read_compressed_page(struct zram *zram, struct page *page, u32 index) +{ + struct zcomp_strm *zstrm; + unsigned long handle; + unsigned int size; + void *src, *dst; + int ret, prio; + + handle = zram_get_handle(zram, index); + size = zram_get_obj_size(zram, index); + prio = zram_get_priority(zram, index); + + zstrm = zcomp_stream_get(zram->comps[prio]); + src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); + dst = kmap_local_page(page); + ret = zcomp_decompress(zram->comps[prio], zstrm, src, size, dst); + kunmap_local(dst); + zs_unmap_object(zram->mem_pool, handle); + zcomp_stream_put(zram->comps[prio]); + + return ret; +} + /* * Reads (decompresses if needed) a page from zspool (zsmalloc). * Corresponding ZRAM slot should be locked. @@ -1529,47 +1587,14 @@ out: static int zram_read_from_zspool(struct zram *zram, struct page *page, u32 index) { - struct zcomp_strm *zstrm; - unsigned long handle; - unsigned int size; - void *src, *dst; - u32 prio; - int ret; + if (zram_test_flag(zram, index, ZRAM_SAME) || + !zram_get_handle(zram, index)) + return read_same_filled_page(zram, page, index); - handle = zram_get_handle(zram, index); - if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) { - unsigned long value; - void *mem; - - value = handle ? zram_get_element(zram, index) : 0; - mem = kmap_local_page(page); - zram_fill_page(mem, PAGE_SIZE, value); - kunmap_local(mem); - return 0; - } - - size = zram_get_obj_size(zram, index); - - if (size != PAGE_SIZE) { - prio = zram_get_priority(zram, index); - zstrm = zcomp_stream_get(zram->comps[prio]); - } - - src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); - if (size == PAGE_SIZE) { - dst = kmap_local_page(page); - copy_page(dst, src); - kunmap_local(dst); - ret = 0; - } else { - dst = kmap_local_page(page); - ret = zcomp_decompress(zram->comps[prio], zstrm, - src, size, dst); - kunmap_local(dst); - zcomp_stream_put(zram->comps[prio]); - } - zs_unmap_object(zram->mem_pool, handle); - return ret; + if (!zram_test_flag(zram, index, ZRAM_HUGE)) + return read_compressed_page(zram, page, index); + else + return read_incompressible_page(zram, page, index); } static int zram_read_page(struct zram *zram, struct page *page, u32 index, @@ -1589,7 +1614,7 @@ static int zram_read_page(struct zram *zram, struct page *page, u32 index, */ zram_slot_unlock(zram, index); - ret = read_from_bdev(zram, page, zram_get_element(zram, index), + ret = read_from_bdev(zram, page, zram_get_handle(zram, index), parent); } @@ -1627,33 +1652,88 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, return zram_read_page(zram, bvec->bv_page, index, bio); } +static int write_same_filled_page(struct zram *zram, unsigned long fill, + u32 index) +{ + zram_slot_lock(zram, index); + zram_set_flag(zram, index, ZRAM_SAME); + zram_set_handle(zram, index, fill); + zram_slot_unlock(zram, index); + + atomic64_inc(&zram->stats.same_pages); + atomic64_inc(&zram->stats.pages_stored); + + return 0; +} + +static int write_incompressible_page(struct zram *zram, struct page *page, + u32 index) +{ + unsigned long handle; + void *src, *dst; + + /* + * This function is called from preemptible context so we don't need + * to do optimistic and fallback to pessimistic handle allocation, + * like we do for compressible pages. + */ + handle = zs_malloc(zram->mem_pool, PAGE_SIZE, + GFP_NOIO | __GFP_HIGHMEM | __GFP_MOVABLE); + if (IS_ERR_VALUE(handle)) + return PTR_ERR((void *)handle); + + if (!zram_can_store_page(zram)) { + zs_free(zram->mem_pool, handle); + return -ENOMEM; + } + + dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO); + src = kmap_local_page(page); + memcpy(dst, src, PAGE_SIZE); + kunmap_local(src); + zs_unmap_object(zram->mem_pool, handle); + + zram_slot_lock(zram, index); + zram_set_flag(zram, index, ZRAM_HUGE); + zram_set_handle(zram, index, handle); + zram_set_obj_size(zram, index, PAGE_SIZE); + zram_slot_unlock(zram, index); + + atomic64_add(PAGE_SIZE, &zram->stats.compr_data_size); + atomic64_inc(&zram->stats.huge_pages); + atomic64_inc(&zram->stats.huge_pages_since); + atomic64_inc(&zram->stats.pages_stored); + + return 0; +} + static int zram_write_page(struct zram *zram, struct page *page, u32 index) { int ret = 0; - unsigned long alloced_pages; unsigned long handle = -ENOMEM; unsigned int comp_len = 0; - void *src, *dst, *mem; + void *dst, *mem; struct zcomp_strm *zstrm; unsigned long element = 0; - enum zram_pageflags flags = 0; + bool same_filled; + + /* First, free memory allocated to this slot (if any) */ + zram_slot_lock(zram, index); + zram_free_page(zram, index); + zram_slot_unlock(zram, index); mem = kmap_local_page(page); - if (page_same_filled(mem, &element)) { - kunmap_local(mem); - /* Free memory associated with this sector now. */ - flags = ZRAM_SAME; - atomic64_inc(&zram->stats.same_pages); - goto out; - } + same_filled = page_same_filled(mem, &element); kunmap_local(mem); + if (same_filled) + return write_same_filled_page(zram, element, index); compress_again: zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]); - src = kmap_local_page(page); + mem = kmap_local_page(page); ret = zcomp_compress(zram->comps[ZRAM_PRIMARY_COMP], zstrm, - src, &comp_len); - kunmap_local(src); + mem, &comp_len); + kunmap_local(mem); if (unlikely(ret)) { zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]); @@ -1662,8 +1742,11 @@ compress_again: return ret; } - if (comp_len >= huge_class_size) - comp_len = PAGE_SIZE; + if (comp_len >= huge_class_size) { + zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]); + return write_incompressible_page(zram, page, index); + } + /* * handle allocation has 2 paths: * a) fast path is executed with preemption disabled (for @@ -1679,35 +1762,23 @@ compress_again: */ if (IS_ERR_VALUE(handle)) handle = zs_malloc(zram->mem_pool, comp_len, - __GFP_KSWAPD_RECLAIM | - __GFP_NOWARN | - __GFP_HIGHMEM | - __GFP_MOVABLE); + __GFP_KSWAPD_RECLAIM | + __GFP_NOWARN | + __GFP_HIGHMEM | + __GFP_MOVABLE); if (IS_ERR_VALUE(handle)) { zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]); atomic64_inc(&zram->stats.writestall); handle = zs_malloc(zram->mem_pool, comp_len, - GFP_NOIO | __GFP_HIGHMEM | - __GFP_MOVABLE); + GFP_NOIO | __GFP_HIGHMEM | + __GFP_MOVABLE); if (IS_ERR_VALUE(handle)) return PTR_ERR((void *)handle); - if (comp_len != PAGE_SIZE) - goto compress_again; - /* - * If the page is not compressible, you need to acquire the - * lock and execute the code below. The zcomp_stream_get() - * call is needed to disable the cpu hotplug and grab the - * zstrm buffer back. It is necessary that the dereferencing - * of the zstrm variable below occurs correctly. - */ - zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]); + goto compress_again; } - alloced_pages = zs_get_total_pages(zram->mem_pool); - update_used_max(zram, alloced_pages); - - if (zram->limit_pages && alloced_pages > zram->limit_pages) { + if (!zram_can_store_page(zram)) { zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]); zs_free(zram->mem_pool, handle); return -ENOMEM; @@ -1715,41 +1786,19 @@ compress_again: dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO); - src = zstrm->buffer; - if (comp_len == PAGE_SIZE) - src = kmap_local_page(page); - memcpy(dst, src, comp_len); - if (comp_len == PAGE_SIZE) - kunmap_local(src); - + memcpy(dst, zstrm->buffer, comp_len); zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]); zs_unmap_object(zram->mem_pool, handle); - atomic64_add(comp_len, &zram->stats.compr_data_size); -out: - /* - * Free memory associated with this sector - * before overwriting unused sectors. - */ + zram_slot_lock(zram, index); - zram_free_page(zram, index); - - if (comp_len == PAGE_SIZE) { - zram_set_flag(zram, index, ZRAM_HUGE); - atomic64_inc(&zram->stats.huge_pages); - atomic64_inc(&zram->stats.huge_pages_since); - } - - if (flags) { - zram_set_flag(zram, index, flags); - zram_set_element(zram, index, element); - } else { - zram_set_handle(zram, index, handle); - zram_set_obj_size(zram, index, comp_len); - } + zram_set_handle(zram, index, handle); + zram_set_obj_size(zram, index, comp_len); zram_slot_unlock(zram, index); /* Update stats */ atomic64_inc(&zram->stats.pages_stored); + atomic64_add(comp_len, &zram->stats.compr_data_size); + return ret; } @@ -2320,11 +2369,6 @@ static void zram_reset_device(struct zram *zram) zram->limit_pages = 0; - if (!init_done(zram)) { - up_write(&zram->init_lock); - return; - } - set_capacity_and_notify(zram->disk, 0); part_stat_set_all(zram->disk->part0, 0); diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 134be414e210..db78d7c01b9a 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -62,10 +62,7 @@ enum zram_pageflags { /* Allocated for each disk page */ struct zram_table_entry { - union { - unsigned long handle; - unsigned long element; - }; + unsigned long handle; unsigned int flags; spinlock_t lock; #ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index a1153ada74d2..0a60660fc8ce 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -553,6 +553,9 @@ static const char *btbcm_get_board_name(struct device *dev) /* get rid of any '/' in the compatible string */ board_type = devm_kstrdup(dev, tmp, GFP_KERNEL); + if (!board_type) + return NULL; + strreplace(board_type, '/', '-'); return board_type; diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index d496cf2c3411..d2540b28bc7a 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -506,13 +507,13 @@ int btintel_version_info_tlv(struct hci_dev *hdev, bt_dev_info(hdev, "Device revision is %u", version->dev_rev_id); bt_dev_info(hdev, "Secure boot is %s", - version->secure_boot ? "enabled" : "disabled"); + str_enabled_disabled(version->secure_boot)); bt_dev_info(hdev, "OTP lock is %s", - version->otp_lock ? "enabled" : "disabled"); + str_enabled_disabled(version->otp_lock)); bt_dev_info(hdev, "API lock is %s", - version->api_lock ? "enabled" : "disabled"); + str_enabled_disabled(version->api_lock)); bt_dev_info(hdev, "Debug lock is %s", - version->debug_lock ? "enabled" : "disabled"); + str_enabled_disabled(version->debug_lock)); bt_dev_info(hdev, "Minimum firmware build %u week %u %u", version->min_fw_build_nn, version->min_fw_build_cw, 2000 + version->min_fw_build_yy); @@ -927,16 +928,16 @@ int btintel_read_boot_params(struct hci_dev *hdev, le16_to_cpu(params->dev_revid)); bt_dev_info(hdev, "Secure boot is %s", - params->secure_boot ? "enabled" : "disabled"); + str_enabled_disabled(params->secure_boot)); bt_dev_info(hdev, "OTP lock is %s", - params->otp_lock ? "enabled" : "disabled"); + str_enabled_disabled(params->otp_lock)); bt_dev_info(hdev, "API lock is %s", - params->api_lock ? "enabled" : "disabled"); + str_enabled_disabled(params->api_lock)); bt_dev_info(hdev, "Debug lock is %s", - params->debug_lock ? "enabled" : "disabled"); + str_enabled_disabled(params->debug_lock)); bt_dev_info(hdev, "Minimum firmware build %u week %u %u", params->min_fw_build_nn, params->min_fw_build_cw, diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index 18f34998a120..e26b07a9387d 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -88,7 +89,7 @@ int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb) else adapter->psmode = 0; BT_DBG("PS Mode:%s", - (adapter->psmode) ? "Enable" : "Disable"); + str_enable_disable(adapter->psmode)); } else { BT_DBG("PS Mode command failed"); } diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 7fd9d5ddce02..68846c5bd4f7 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -1329,7 +1329,6 @@ int btmtk_usb_setup(struct hci_dev *hdev) fwname = FIRMWARE_MT7668; break; case 0x7922: - case 0x7961: case 0x7925: /* Reset the device to ensure it's in the initial state before * downloading the firmware to ensure. @@ -1337,7 +1336,8 @@ int btmtk_usb_setup(struct hci_dev *hdev) if (!test_bit(BTMTK_FIRMWARE_LOADED, &btmtk_data->flags)) btmtk_usb_subsys_reset(hdev, dev_id); - + fallthrough; + case 0x7961: btmtk_fw_get_filename(fw_bin_name, sizeof(fw_bin_name), dev_id, fw_version, fw_flavor); @@ -1472,10 +1472,15 @@ EXPORT_SYMBOL_GPL(btmtk_usb_setup); int btmtk_usb_shutdown(struct hci_dev *hdev) { + struct btmtk_data *data = hci_get_priv(hdev); struct btmtk_hci_wmt_params wmt_params; u8 param = 0; int err; + err = usb_autopm_get_interface(data->intf); + if (err < 0) + return err; + /* Disable the device */ wmt_params.op = BTMTK_WMT_FUNC_CTRL; wmt_params.flag = 0; @@ -1486,9 +1491,11 @@ int btmtk_usb_shutdown(struct hci_dev *hdev) err = btmtk_usb_hci_wmt_sync(hdev, &wmt_params); if (err < 0) { bt_dev_err(hdev, "Failed to send wmt func ctrl (%d)", err); + usb_autopm_put_interface(data->intf); return err; } + usb_autopm_put_interface(data->intf); return 0; } EXPORT_SYMBOL_GPL(btmtk_usb_shutdown); diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index a1dfcfe43d3a..bd5464bde174 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -1249,7 +1249,7 @@ static int btmtksdio_send_frame(struct hci_dev *hdev, struct sk_buff *skb) return 0; } -static void btmtksdio_cmd_timeout(struct hci_dev *hdev) +static void btmtksdio_reset(struct hci_dev *hdev) { struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); u32 status; @@ -1360,7 +1360,7 @@ static int btmtksdio_probe(struct sdio_func *func, hdev->open = btmtksdio_open; hdev->close = btmtksdio_close; - hdev->cmd_timeout = btmtksdio_cmd_timeout; + hdev->reset = btmtksdio_reset; hdev->flush = btmtksdio_flush; hdev->setup = btmtksdio_setup; hdev->shutdown = btmtksdio_shutdown; diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 569f5b7d6e46..aa5ec1d444a9 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1386,7 +1386,7 @@ static void btnxpuart_tx_work(struct work_struct *work) skb_pull(skb, len); if (skb->len > 0) { skb_queue_head(&nxpdev->txq, skb); - break; + continue; } switch (hci_skb_pkt_type(skb)) { diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index dfbbac92242a..cdf09d9a9ad2 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -272,6 +272,39 @@ int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) } EXPORT_SYMBOL_GPL(qca_send_pre_shutdown_cmd); +static bool qca_filename_has_extension(const char *filename) +{ + const char *suffix = strrchr(filename, '.'); + + /* File extensions require a dot, but not as the first or last character */ + if (!suffix || suffix == filename || *(suffix + 1) == '\0') + return 0; + + /* Avoid matching directories with names that look like files with extensions */ + return !strchr(suffix, '/'); +} + +static bool qca_get_alt_nvm_file(char *filename, size_t max_size) +{ + char fwname[64]; + const char *suffix; + + /* nvm file name has an extension, replace with .bin */ + if (qca_filename_has_extension(filename)) { + suffix = strrchr(filename, '.'); + strscpy(fwname, filename, suffix - filename + 1); + snprintf(fwname + (suffix - filename), + sizeof(fwname) - (suffix - filename), ".bin"); + /* If nvm file is already the default one, return false to skip the retry. */ + if (strcmp(fwname, filename) == 0) + return false; + + snprintf(filename, max_size, "%s", fwname); + return true; + } + return false; +} + static int qca_tlv_check_data(struct hci_dev *hdev, struct qca_fw_config *config, u8 *fw_data, size_t fw_size, @@ -564,6 +597,19 @@ static int qca_download_firmware(struct hci_dev *hdev, config->fwname, ret); return ret; } + } + /* If the board-specific file is missing, try loading the default + * one, unless that was attempted already. + */ + else if (config->type == TLV_TYPE_NVM && + qca_get_alt_nvm_file(config->fwname, sizeof(config->fwname))) { + bt_dev_info(hdev, "QCA Downloading %s", config->fwname); + ret = request_firmware(&fw, config->fwname, &hdev->dev); + if (ret) { + bt_dev_err(hdev, "QCA Failed to request file: %s (%d)", + config->fwname, ret); + return ret; + } } else { bt_dev_err(hdev, "QCA Failed to request file: %s (%d)", config->fwname, ret); @@ -700,39 +746,43 @@ static int qca_check_bdaddr(struct hci_dev *hdev, const struct qca_fw_config *co return 0; } -static void qca_generate_hsp_nvm_name(char *fwname, size_t max_size, +static void qca_get_nvm_name_by_board(char *fwname, size_t max_size, + const char *stem, enum qca_btsoc_type soc_type, struct qca_btsoc_version ver, u8 rom_ver, u16 bid) { const char *variant; + const char *prefix; - /* hsp gf chip */ - if ((le32_to_cpu(ver.soc_id) & QCA_HSP_GF_SOC_MASK) == QCA_HSP_GF_SOC_ID) - variant = "g"; - else - variant = ""; + /* Set the default value to variant and prefix */ + variant = ""; + prefix = "b"; - if (bid == 0x0) - snprintf(fwname, max_size, "qca/hpnv%02x%s.bin", rom_ver, variant); - else - snprintf(fwname, max_size, "qca/hpnv%02x%s.%x", rom_ver, variant, bid); -} + if (soc_type == QCA_QCA2066) + prefix = ""; -static inline void qca_get_nvm_name_generic(struct qca_fw_config *cfg, - const char *stem, u8 rom_ver, u16 bid) -{ - if (bid == 0x0) - snprintf(cfg->fwname, sizeof(cfg->fwname), "qca/%snv%02x.bin", stem, rom_ver); - else if (bid & 0xff00) - snprintf(cfg->fwname, sizeof(cfg->fwname), - "qca/%snv%02x.b%x", stem, rom_ver, bid); - else - snprintf(cfg->fwname, sizeof(cfg->fwname), - "qca/%snv%02x.b%02x", stem, rom_ver, bid); + if (soc_type == QCA_WCN6855 || soc_type == QCA_QCA2066) { + /* If the chip is manufactured by GlobalFoundries */ + if ((le32_to_cpu(ver.soc_id) & QCA_HSP_GF_SOC_MASK) == QCA_HSP_GF_SOC_ID) + variant = "g"; + } + + if (rom_ver != 0) { + if (bid == 0x0 || bid == 0xffff) + snprintf(fwname, max_size, "qca/%s%02x%s.bin", stem, rom_ver, variant); + else + snprintf(fwname, max_size, "qca/%s%02x%s.%s%02x", stem, rom_ver, + variant, prefix, bid); + } else { + if (bid == 0x0 || bid == 0xffff) + snprintf(fwname, max_size, "qca/%s%s.bin", stem, variant); + else + snprintf(fwname, max_size, "qca/%s%s.%s%02x", stem, variant, prefix, bid); + } } int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, enum qca_btsoc_type soc_type, struct qca_btsoc_version ver, - const char *firmware_name) + const char *firmware_name, const char *rampatch_name) { struct qca_fw_config config = {}; int err; @@ -761,44 +811,48 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, /* Download rampatch file */ config.type = TLV_TYPE_PATCH; - switch (soc_type) { - case QCA_WCN3990: - case QCA_WCN3991: - case QCA_WCN3998: - snprintf(config.fwname, sizeof(config.fwname), - "qca/crbtfw%02x.tlv", rom_ver); - break; - case QCA_WCN3988: - snprintf(config.fwname, sizeof(config.fwname), - "qca/apbtfw%02x.tlv", rom_ver); - break; - case QCA_QCA2066: - snprintf(config.fwname, sizeof(config.fwname), - "qca/hpbtfw%02x.tlv", rom_ver); - break; - case QCA_QCA6390: - snprintf(config.fwname, sizeof(config.fwname), - "qca/htbtfw%02x.tlv", rom_ver); - break; - case QCA_WCN6750: - /* Choose mbn file by default.If mbn file is not found - * then choose tlv file - */ - config.type = ELF_TYPE_PATCH; - snprintf(config.fwname, sizeof(config.fwname), - "qca/msbtfw%02x.mbn", rom_ver); - break; - case QCA_WCN6855: - snprintf(config.fwname, sizeof(config.fwname), - "qca/hpbtfw%02x.tlv", rom_ver); - break; - case QCA_WCN7850: - snprintf(config.fwname, sizeof(config.fwname), - "qca/hmtbtfw%02x.tlv", rom_ver); - break; - default: - snprintf(config.fwname, sizeof(config.fwname), - "qca/rampatch_%08x.bin", soc_ver); + if (rampatch_name) { + snprintf(config.fwname, sizeof(config.fwname), "qca/%s", rampatch_name); + } else { + switch (soc_type) { + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + snprintf(config.fwname, sizeof(config.fwname), + "qca/crbtfw%02x.tlv", rom_ver); + break; + case QCA_WCN3988: + snprintf(config.fwname, sizeof(config.fwname), + "qca/apbtfw%02x.tlv", rom_ver); + break; + case QCA_QCA2066: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hpbtfw%02x.tlv", rom_ver); + break; + case QCA_QCA6390: + snprintf(config.fwname, sizeof(config.fwname), + "qca/htbtfw%02x.tlv", rom_ver); + break; + case QCA_WCN6750: + /* Choose mbn file by default.If mbn file is not found + * then choose tlv file + */ + config.type = ELF_TYPE_PATCH; + snprintf(config.fwname, sizeof(config.fwname), + "qca/msbtfw%02x.mbn", rom_ver); + break; + case QCA_WCN6855: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hpbtfw%02x.tlv", rom_ver); + break; + case QCA_WCN7850: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hmtbtfw%02x.tlv", rom_ver); + break; + default: + snprintf(config.fwname, sizeof(config.fwname), + "qca/rampatch_%08x.bin", soc_ver); + } } err = qca_download_firmware(hdev, &config, soc_type, rom_ver); @@ -816,8 +870,14 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, /* Download NVM configuration */ config.type = TLV_TYPE_NVM; if (firmware_name) { - snprintf(config.fwname, sizeof(config.fwname), - "qca/%s", firmware_name); + /* The firmware name has an extension, use it directly */ + if (qca_filename_has_extension(firmware_name)) { + snprintf(config.fwname, sizeof(config.fwname), "qca/%s", firmware_name); + } else { + qca_read_fw_board_id(hdev, &boardid); + qca_get_nvm_name_by_board(config.fwname, sizeof(config.fwname), + firmware_name, soc_type, ver, 0, boardid); + } } else { switch (soc_type) { case QCA_WCN3990: @@ -836,8 +896,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, "qca/apnv%02x.bin", rom_ver); break; case QCA_QCA2066: - qca_generate_hsp_nvm_name(config.fwname, - sizeof(config.fwname), ver, rom_ver, boardid); + qca_get_nvm_name_by_board(config.fwname, + sizeof(config.fwname), "hpnv", soc_type, ver, + rom_ver, boardid); break; case QCA_QCA6390: snprintf(config.fwname, sizeof(config.fwname), @@ -848,13 +909,14 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, "qca/msnv%02x.bin", rom_ver); break; case QCA_WCN6855: - snprintf(config.fwname, sizeof(config.fwname), - "qca/hpnv%02x.bin", rom_ver); + qca_read_fw_board_id(hdev, &boardid); + qca_get_nvm_name_by_board(config.fwname, sizeof(config.fwname), + "hpnv", soc_type, ver, rom_ver, boardid); break; case QCA_WCN7850: - qca_get_nvm_name_generic(&config, "hmt", rom_ver, boardid); + qca_get_nvm_name_by_board(config.fwname, sizeof(config.fwname), + "hmtnv", soc_type, ver, rom_ver, boardid); break; - default: snprintf(config.fwname, sizeof(config.fwname), "qca/nvm_%08x.bin", soc_ver); diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index bb5207d7a8c7..9d28c8800225 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -161,7 +161,7 @@ enum qca_btsoc_type { int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr); int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, enum qca_btsoc_type soc_type, struct qca_btsoc_version ver, - const char *firmware_name); + const char *firmware_name, const char *rampatch_name); int qca_read_soc_version(struct hci_dev *hdev, struct qca_btsoc_version *ver, enum qca_btsoc_type); int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr); @@ -176,7 +176,8 @@ static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdad static inline int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, enum qca_btsoc_type soc_type, struct qca_btsoc_version ver, - const char *firmware_name) + const char *firmware_name, + const char *rampatch_name) { return -EOPNOTSUPP; } diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 83025f457ca0..d3eba0d4a57d 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1351,12 +1351,14 @@ int btrtl_setup_realtek(struct hci_dev *hdev) btrtl_set_quirks(hdev, btrtl_dev); - hci_set_hw_info(hdev, + if (btrtl_dev->ic_info) { + hci_set_hw_info(hdev, "RTL lmp_subver=%u hci_rev=%u hci_ver=%u hci_bus=%u", btrtl_dev->ic_info->lmp_subver, btrtl_dev->ic_info->hci_rev, btrtl_dev->ic_info->hci_ver, btrtl_dev->ic_info->hci_bus); + } btrtl_free(btrtl_dev); return ret; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 279fe6c115fa..90966dfbd278 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -377,6 +377,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3623), .driver_info = BTUSB_QCA_WCN6855 | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x2c7c, 0x0130), .driver_info = BTUSB_QCA_WCN6855 | + BTUSB_WIDEBAND_SPEECH }, /* Broadcom BCM2035 */ { USB_DEVICE(0x0a5c, 0x2009), .driver_info = BTUSB_BCM92035 }, @@ -481,6 +483,9 @@ static const struct usb_device_id quirks_table[] = { { USB_DEVICE(0x13d3, 0x3549), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + /* Realtek 8851BE Bluetooth devices */ + { USB_DEVICE(0x13d3, 0x3600), .driver_info = BTUSB_REALTEK }, + /* Realtek 8852AE Bluetooth devices */ { USB_DEVICE(0x0bda, 0x2852), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, @@ -600,6 +605,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3567), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3576), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3578), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3583), .driver_info = BTUSB_MEDIATEK | @@ -610,6 +617,8 @@ static const struct usb_device_id quirks_table[] = { /* MediaTek MT7922 Bluetooth devices */ { USB_DEVICE(0x13d3, 0x3585), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3610), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH }, /* MediaTek MT7922A Bluetooth devices */ { USB_DEVICE(0x0489, 0xe0d8), .driver_info = BTUSB_MEDIATEK | @@ -674,6 +683,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3608), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3628), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH }, /* Additional Realtek 8723AE Bluetooth devices */ { USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK }, @@ -879,7 +890,6 @@ struct btusb_data { int (*disconnect)(struct hci_dev *hdev); int oob_wake_irq; /* irq for out-of-band wake-on-bt */ - unsigned cmd_timeout_cnt; struct qca_dump_info qca_dump; }; @@ -889,11 +899,6 @@ static void btusb_reset(struct hci_dev *hdev) struct btusb_data *data; int err; - if (hdev->reset) { - hdev->reset(hdev); - return; - } - data = hci_get_drvdata(hdev); /* This is not an unbalanced PM reference since the device will reset */ err = usb_autopm_get_interface(data->intf); @@ -906,15 +911,12 @@ static void btusb_reset(struct hci_dev *hdev) usb_queue_reset_device(data->intf); } -static void btusb_intel_cmd_timeout(struct hci_dev *hdev) +static void btusb_intel_reset(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); struct gpio_desc *reset_gpio = data->reset_gpio; struct btintel_data *intel_data = hci_get_priv(hdev); - if (++data->cmd_timeout_cnt < 5) - return; - if (intel_data->acpi_reset_method) { if (test_and_set_bit(INTEL_ACPI_RESET_ACTIVE, intel_data->flags)) { bt_dev_err(hdev, "acpi: last reset failed ? Not resetting again"); @@ -987,7 +989,7 @@ static inline void btusb_rtl_alloc_devcoredump(struct hci_dev *hdev, } } -static void btusb_rtl_cmd_timeout(struct hci_dev *hdev) +static void btusb_rtl_reset(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); struct gpio_desc *reset_gpio = data->reset_gpio; @@ -997,9 +999,6 @@ static void btusb_rtl_cmd_timeout(struct hci_dev *hdev) btusb_rtl_alloc_devcoredump(hdev, &hdr, NULL, 0); - if (++data->cmd_timeout_cnt < 5) - return; - if (!reset_gpio) { btusb_reset(hdev); return; @@ -1034,19 +1033,16 @@ static void btusb_rtl_hw_error(struct hci_dev *hdev, u8 code) btusb_rtl_alloc_devcoredump(hdev, &hdr, NULL, 0); } -static void btusb_qca_cmd_timeout(struct hci_dev *hdev) +static void btusb_qca_reset(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); struct gpio_desc *reset_gpio = data->reset_gpio; if (test_bit(BTUSB_HW_SSR_ACTIVE, &data->flags)) { - bt_dev_info(hdev, "Ramdump in progress, defer cmd_timeout"); + bt_dev_info(hdev, "Ramdump in progress, defer reset"); return; } - if (++data->cmd_timeout_cnt < 5) - return; - if (reset_gpio) { bt_dev_err(hdev, "Reset qca device via bt_en gpio"); @@ -2638,8 +2634,15 @@ static void btusb_mtk_claim_iso_intf(struct btusb_data *data) struct btmtk_data *btmtk_data = hci_get_priv(data->hdev); int err; + /* + * The function usb_driver_claim_interface() is documented to need + * locks held if it's not called from a probe routine. The code here + * is called from the hci_power_on workqueue, so grab the lock. + */ + device_lock(&btmtk_data->isopkt_intf->dev); err = usb_driver_claim_interface(&btusb_driver, btmtk_data->isopkt_intf, data); + device_unlock(&btmtk_data->isopkt_intf->dev); if (err < 0) { btmtk_data->isopkt_intf = NULL; bt_dev_err(data->hdev, "Failed to claim iso interface"); @@ -3645,6 +3648,32 @@ static const struct file_operations force_poll_sync_fops = { .llseek = default_llseek, }; +static ssize_t isoc_alt_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct btusb_data *data = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%d\n", data->isoc_altsetting); +} + +static ssize_t isoc_alt_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct btusb_data *data = dev_get_drvdata(dev); + int alt; + int ret; + + if (kstrtoint(buf, 10, &alt)) + return -EINVAL; + + ret = btusb_switch_alt_setting(data->hdev, alt); + return ret < 0 ? ret : count; +} + +static DEVICE_ATTR_RW(isoc_alt); + static int btusb_probe(struct usb_interface *intf, const struct usb_device_id *id) { @@ -3841,7 +3870,7 @@ static int btusb_probe(struct usb_interface *intf, /* Transport specific configuration */ hdev->send = btusb_send_frame_intel; - hdev->cmd_timeout = btusb_intel_cmd_timeout; + hdev->reset = btusb_intel_reset; if (id->driver_info & BTUSB_INTEL_NO_WBS_SUPPORT) btintel_set_flag(hdev, INTEL_ROM_LEGACY_NO_WBS_SUPPORT); @@ -3861,7 +3890,7 @@ static int btusb_probe(struct usb_interface *intf, hdev->setup = btusb_mtk_setup; hdev->shutdown = btusb_mtk_shutdown; hdev->manufacturer = 70; - hdev->cmd_timeout = btmtk_reset_sync; + hdev->reset = btmtk_reset_sync; hdev->set_bdaddr = btmtk_set_bdaddr; hdev->send = btusb_send_frame_mtk; set_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &hdev->quirks); @@ -3893,7 +3922,7 @@ static int btusb_probe(struct usb_interface *intf, data->setup_on_usb = btusb_setup_qca; hdev->shutdown = btusb_shutdown_qca; hdev->set_bdaddr = btusb_set_bdaddr_ath3012; - hdev->cmd_timeout = btusb_qca_cmd_timeout; + hdev->reset = btusb_qca_reset; set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); btusb_check_needs_reset_resume(intf); } @@ -3907,7 +3936,7 @@ static int btusb_probe(struct usb_interface *intf, data->setup_on_usb = btusb_setup_qca; hdev->shutdown = btusb_shutdown_qca; hdev->set_bdaddr = btusb_set_bdaddr_wcn6855; - hdev->cmd_timeout = btusb_qca_cmd_timeout; + hdev->reset = btusb_qca_reset; set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); hci_set_msft_opcode(hdev, 0xFD70); } @@ -3926,7 +3955,7 @@ static int btusb_probe(struct usb_interface *intf, btrtl_set_driver_name(hdev, btusb_driver.name); hdev->setup = btusb_setup_realtek; hdev->shutdown = btrtl_shutdown_realtek; - hdev->cmd_timeout = btusb_rtl_cmd_timeout; + hdev->reset = btusb_rtl_reset; hdev->hw_error = btusb_rtl_hw_error; /* Realtek devices need to set remote wakeup on auto-suspend */ @@ -4008,6 +4037,10 @@ static int btusb_probe(struct usb_interface *intf, data->isoc, data); if (err < 0) goto out_free_dev; + + err = device_create_file(&intf->dev, &dev_attr_isoc_alt); + if (err) + goto out_free_dev; } if (IS_ENABLED(CONFIG_BT_HCIBTUSB_BCM) && data->diag) { @@ -4054,8 +4087,10 @@ static void btusb_disconnect(struct usb_interface *intf) hdev = data->hdev; usb_set_intfdata(data->intf, NULL); - if (data->isoc) + if (data->isoc) { + device_remove_file(&intf->dev, &dev_attr_isoc_alt); usb_set_intfdata(data->isoc, NULL); + } if (data->diag) usb_set_intfdata(data->diag, NULL); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 37129e6cb0eb..0ac2168f1dc4 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -228,7 +229,7 @@ struct qca_serdev { u32 init_speed; u32 oper_speed; bool bdaddr_property_broken; - const char *firmware_name; + const char *firmware_name[2]; }; static int qca_regulator_enable(struct qca_serdev *qcadev); @@ -258,7 +259,18 @@ static const char *qca_get_firmware_name(struct hci_uart *hu) if (hu->serdev) { struct qca_serdev *qsd = serdev_device_get_drvdata(hu->serdev); - return qsd->firmware_name; + return qsd->firmware_name[0]; + } else { + return NULL; + } +} + +static const char *qca_get_rampatch_name(struct hci_uart *hu) +{ + if (hu->serdev) { + struct qca_serdev *qsd = serdev_device_get_drvdata(hu->serdev); + + return qsd->firmware_name[1]; } else { return NULL; } @@ -332,8 +344,8 @@ static void serial_clock_vote(unsigned long vote, struct hci_uart *hu) else __serial_clock_off(hu->tty); - BT_DBG("Vote serial clock %s(%s)", new_vote ? "true" : "false", - vote ? "true" : "false"); + BT_DBG("Vote serial clock %s(%s)", str_true_false(new_vote), + str_true_false(vote)); diff = jiffies_to_msecs(jiffies - qca->vote_last_jif); @@ -1638,7 +1650,7 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code) clear_bit(QCA_HW_ERROR_EVENT, &qca->flags); } -static void qca_cmd_timeout(struct hci_dev *hdev) +static void qca_reset(struct hci_dev *hdev) { struct hci_uart *hu = hci_get_drvdata(hdev); struct qca_data *qca = hu->priv; @@ -1855,6 +1867,7 @@ static int qca_setup(struct hci_uart *hu) unsigned int retries = 0; enum qca_btsoc_type soc_type = qca_soc_type(hu); const char *firmware_name = qca_get_firmware_name(hu); + const char *rampatch_name = qca_get_rampatch_name(hu); int ret; struct qca_btsoc_version ver; struct qca_serdev *qcadev; @@ -1963,12 +1976,12 @@ retry: /* Setup patch / NVM configurations */ ret = qca_uart_setup(hdev, qca_baudrate, soc_type, ver, - firmware_name); + firmware_name, rampatch_name); if (!ret) { clear_bit(QCA_IBS_DISABLED, &qca->flags); qca_debugfs_init(hdev); hu->hdev->hw_error = qca_hw_error; - hu->hdev->cmd_timeout = qca_cmd_timeout; + hu->hdev->reset = qca_reset; if (hu->serdev) { if (device_can_wakeup(hu->serdev->ctrl->dev.parent)) hu->hdev->wakeup = qca_wakeup; @@ -2202,7 +2215,7 @@ static int qca_power_off(struct hci_dev *hdev) enum qca_btsoc_type soc_type = qca_soc_type(hu); hu->hdev->hw_error = NULL; - hu->hdev->cmd_timeout = NULL; + hu->hdev->reset = NULL; del_timer_sync(&qca->wake_retrans_timer); del_timer_sync(&qca->tx_idle_timer); @@ -2309,8 +2322,8 @@ static int qca_serdev_probe(struct serdev_device *serdev) qcadev->serdev_hu.serdev = serdev; data = device_get_match_data(&serdev->dev); serdev_device_set_drvdata(serdev, qcadev); - device_property_read_string(&serdev->dev, "firmware-name", - &qcadev->firmware_name); + device_property_read_string_array(&serdev->dev, "firmware-name", + qcadev->firmware_name, ARRAY_SIZE(qcadev->firmware_name)); device_property_read_u32(&serdev->dev, "max-speed", &qcadev->oper_speed); if (!qcadev->oper_speed) diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c index 4b68c84ef485..52053f7c6d9a 100644 --- a/drivers/bus/fsl-mc/dprc-driver.c +++ b/drivers/bus/fsl-mc/dprc-driver.c @@ -22,8 +22,8 @@ struct fsl_mc_child_objs { struct fsl_mc_obj_desc *child_array; }; -static bool fsl_mc_device_match(struct fsl_mc_device *mc_dev, - struct fsl_mc_obj_desc *obj_desc) +static bool fsl_mc_device_match(const struct fsl_mc_device *mc_dev, + const struct fsl_mc_obj_desc *obj_desc) { return mc_dev->obj_desc.id == obj_desc->id && strcmp(mc_dev->obj_desc.type, obj_desc->type) == 0; @@ -112,9 +112,9 @@ void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev, } EXPORT_SYMBOL_GPL(dprc_remove_devices); -static int __fsl_mc_device_match(struct device *dev, void *data) +static int __fsl_mc_device_match(struct device *dev, const void *data) { - struct fsl_mc_obj_desc *obj_desc = data; + const struct fsl_mc_obj_desc *obj_desc = data; struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); return fsl_mc_device_match(mc_dev, obj_desc); diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 2916d1333649..d1f3d327ddd1 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -320,90 +320,90 @@ const struct bus_type fsl_mc_bus_type = { }; EXPORT_SYMBOL_GPL(fsl_mc_bus_type); -struct device_type fsl_mc_bus_dprc_type = { +const struct device_type fsl_mc_bus_dprc_type = { .name = "fsl_mc_bus_dprc" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dprc_type); -struct device_type fsl_mc_bus_dpni_type = { +const struct device_type fsl_mc_bus_dpni_type = { .name = "fsl_mc_bus_dpni" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpni_type); -struct device_type fsl_mc_bus_dpio_type = { +const struct device_type fsl_mc_bus_dpio_type = { .name = "fsl_mc_bus_dpio" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpio_type); -struct device_type fsl_mc_bus_dpsw_type = { +const struct device_type fsl_mc_bus_dpsw_type = { .name = "fsl_mc_bus_dpsw" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpsw_type); -struct device_type fsl_mc_bus_dpbp_type = { +const struct device_type fsl_mc_bus_dpbp_type = { .name = "fsl_mc_bus_dpbp" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpbp_type); -struct device_type fsl_mc_bus_dpcon_type = { +const struct device_type fsl_mc_bus_dpcon_type = { .name = "fsl_mc_bus_dpcon" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpcon_type); -struct device_type fsl_mc_bus_dpmcp_type = { +const struct device_type fsl_mc_bus_dpmcp_type = { .name = "fsl_mc_bus_dpmcp" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpmcp_type); -struct device_type fsl_mc_bus_dpmac_type = { +const struct device_type fsl_mc_bus_dpmac_type = { .name = "fsl_mc_bus_dpmac" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpmac_type); -struct device_type fsl_mc_bus_dprtc_type = { +const struct device_type fsl_mc_bus_dprtc_type = { .name = "fsl_mc_bus_dprtc" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dprtc_type); -struct device_type fsl_mc_bus_dpseci_type = { +const struct device_type fsl_mc_bus_dpseci_type = { .name = "fsl_mc_bus_dpseci" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpseci_type); -struct device_type fsl_mc_bus_dpdmux_type = { +const struct device_type fsl_mc_bus_dpdmux_type = { .name = "fsl_mc_bus_dpdmux" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdmux_type); -struct device_type fsl_mc_bus_dpdcei_type = { +const struct device_type fsl_mc_bus_dpdcei_type = { .name = "fsl_mc_bus_dpdcei" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdcei_type); -struct device_type fsl_mc_bus_dpaiop_type = { +const struct device_type fsl_mc_bus_dpaiop_type = { .name = "fsl_mc_bus_dpaiop" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpaiop_type); -struct device_type fsl_mc_bus_dpci_type = { +const struct device_type fsl_mc_bus_dpci_type = { .name = "fsl_mc_bus_dpci" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpci_type); -struct device_type fsl_mc_bus_dpdmai_type = { +const struct device_type fsl_mc_bus_dpdmai_type = { .name = "fsl_mc_bus_dpdmai" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdmai_type); -struct device_type fsl_mc_bus_dpdbg_type = { +const struct device_type fsl_mc_bus_dpdbg_type = { .name = "fsl_mc_bus_dpdbg" }; EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdbg_type); -static struct device_type *fsl_mc_get_device_type(const char *type) +static const struct device_type *fsl_mc_get_device_type(const char *type) { static const struct { - struct device_type *dev_type; + const struct device_type *dev_type; const char *type; } dev_types[] = { { &fsl_mc_bus_dprc_type, "dprc" }, diff --git a/drivers/bus/mhi/host/boot.c b/drivers/bus/mhi/host/boot.c index e8c92972f9df..9dcc7184817d 100644 --- a/drivers/bus/mhi/host/boot.c +++ b/drivers/bus/mhi/host/boot.c @@ -357,6 +357,7 @@ error_alloc_segment: for (--i, --mhi_buf; i >= 0; i--, mhi_buf--) dma_free_coherent(mhi_cntrl->cntrl_dev, mhi_buf->len, mhi_buf->buf, mhi_buf->dma_addr); + kfree(img_info->mhi_buf); error_alloc_mhi_buf: kfree(img_info); diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index 07645ce2119a..c41119b9079f 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -245,6 +245,58 @@ struct mhi_pci_dev_info { .channel = ch_num, \ } +static const struct mhi_channel_config mhi_qcom_qdu100_channels[] = { + MHI_CHANNEL_CONFIG_UL(0, "LOOPBACK", 32, 2), + MHI_CHANNEL_CONFIG_DL(1, "LOOPBACK", 32, 2), + MHI_CHANNEL_CONFIG_UL_SBL(2, "SAHARA", 128, 1), + MHI_CHANNEL_CONFIG_DL_SBL(3, "SAHARA", 128, 1), + MHI_CHANNEL_CONFIG_UL(4, "DIAG", 64, 3), + MHI_CHANNEL_CONFIG_DL(5, "DIAG", 64, 3), + MHI_CHANNEL_CONFIG_UL(9, "QDSS", 64, 3), + MHI_CHANNEL_CONFIG_UL(14, "NMEA", 32, 4), + MHI_CHANNEL_CONFIG_DL(15, "NMEA", 32, 4), + MHI_CHANNEL_CONFIG_UL(16, "CSM_CTRL", 32, 4), + MHI_CHANNEL_CONFIG_DL(17, "CSM_CTRL", 32, 4), + MHI_CHANNEL_CONFIG_UL(40, "MHI_PHC", 32, 4), + MHI_CHANNEL_CONFIG_DL(41, "MHI_PHC", 32, 4), + MHI_CHANNEL_CONFIG_UL(46, "IP_SW0", 256, 5), + MHI_CHANNEL_CONFIG_DL(47, "IP_SW0", 256, 5), +}; + +static struct mhi_event_config mhi_qcom_qdu100_events[] = { + /* first ring is control+data ring */ + MHI_EVENT_CONFIG_CTRL(0, 64), + /* SAHARA dedicated event ring */ + MHI_EVENT_CONFIG_SW_DATA(1, 256), + /* Software channels dedicated event ring */ + MHI_EVENT_CONFIG_SW_DATA(2, 64), + MHI_EVENT_CONFIG_SW_DATA(3, 256), + MHI_EVENT_CONFIG_SW_DATA(4, 256), + /* Software IP channels dedicated event ring */ + MHI_EVENT_CONFIG_SW_DATA(5, 512), + MHI_EVENT_CONFIG_SW_DATA(6, 512), + MHI_EVENT_CONFIG_SW_DATA(7, 512), +}; + +static const struct mhi_controller_config mhi_qcom_qdu100_config = { + .max_channels = 128, + .timeout_ms = 120000, + .num_channels = ARRAY_SIZE(mhi_qcom_qdu100_channels), + .ch_cfg = mhi_qcom_qdu100_channels, + .num_events = ARRAY_SIZE(mhi_qcom_qdu100_events), + .event_cfg = mhi_qcom_qdu100_events, +}; + +static const struct mhi_pci_dev_info mhi_qcom_qdu100_info = { + .name = "qcom-qdu100", + .fw = "qcom/qdu100/xbl_s.melf", + .edl_trigger = true, + .config = &mhi_qcom_qdu100_config, + .bar_num = MHI_PCI_DEFAULT_BAR_NUM, + .dma_data_width = 32, + .sideband_wake = false, +}; + static const struct mhi_channel_config modem_qcom_v1_mhi_channels[] = { MHI_CHANNEL_CONFIG_UL(4, "DIAG", 16, 1), MHI_CHANNEL_CONFIG_DL(5, "DIAG", 16, 1), @@ -742,6 +794,9 @@ static const struct pci_device_id mhi_pci_id_table[] = { .driver_data = (kernel_ulong_t) &mhi_qcom_sdx65_info }, { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0309), .driver_data = (kernel_ulong_t) &mhi_qcom_sdx75_info }, + /* QDU100, x100-DU */ + { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0601), + .driver_data = (kernel_ulong_t) &mhi_qcom_qdu100_info }, { PCI_DEVICE(PCI_VENDOR_ID_QUECTEL, 0x1001), /* EM120R-GL (sdx24) */ .driver_data = (kernel_ulong_t) &mhi_quectel_em1xx_info }, { PCI_DEVICE(PCI_VENDOR_ID_QUECTEL, 0x1002), /* EM160R-GL (sdx24) */ @@ -917,7 +972,7 @@ static int mhi_pci_claim(struct mhi_controller *mhi_cntrl, return err; } - mhi_cntrl->regs = pcim_iomap_region(pdev, 1 << bar_num, pci_name(pdev)); + mhi_cntrl->regs = pcim_iomap_region(pdev, bar_num, pci_name(pdev)); if (IS_ERR(mhi_cntrl->regs)) { err = PTR_ERR(mhi_cntrl->regs); dev_err(&pdev->dev, "failed to map pci region: %d\n", err); @@ -949,7 +1004,7 @@ static int mhi_pci_get_irqs(struct mhi_controller *mhi_cntrl, */ mhi_cntrl->nr_irqs = 1 + mhi_cntrl_config->num_events; - nr_vectors = pci_alloc_irq_vectors(pdev, 1, mhi_cntrl->nr_irqs, PCI_IRQ_MSI); + nr_vectors = pci_alloc_irq_vectors(pdev, 1, mhi_cntrl->nr_irqs, PCI_IRQ_MSIX | PCI_IRQ_MSI); if (nr_vectors < 0) { dev_err(&pdev->dev, "Error allocating MSI vectors %d\n", nr_vectors); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 6a99a459b80b..b163e043c687 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -1106,7 +1106,7 @@ int open_for_data(struct cdrom_device_info *cdi) } } - cd_dbg(CD_OPEN, "all seems well, opening the devicen"); + cd_dbg(CD_OPEN, "all seems well, opening the device\n"); /* all seems well, we can open the device */ ret = cdo->open(cdi, 0); /* open for data */ @@ -3612,7 +3612,7 @@ static int cdrom_sysctl_handler(const struct ctl_table *ctl, int write, } /* Place files in /proc/sys/dev/cdrom */ -static struct ctl_table cdrom_table[] = { +static const struct ctl_table cdrom_table[] = { { .procname = "info", .data = &cdrom_sysctl_settings.info, diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 64b097e830d4..85aceab5eac6 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -777,7 +777,7 @@ static int probe_gdrom(struct platform_device *devptr) probe_gdrom_setupcd(); err = blk_mq_alloc_sq_tag_set(&gd.tag_set, &gdrom_mq_ops, 1, - BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); + BLK_MQ_F_BLOCKING); if (err) goto probe_fail_free_cd_info; diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c index 76eac3653b1c..c573ed2ee71a 100644 --- a/drivers/cdx/cdx.c +++ b/drivers/cdx/cdx.c @@ -338,7 +338,10 @@ static void cdx_shutdown(struct device *dev) { struct cdx_driver *cdx_drv = to_cdx_driver(dev->driver); struct cdx_device *cdx_dev = to_cdx_device(dev); + struct cdx_controller *cdx = cdx_dev->cdx; + if (cdx_dev->is_bus && cdx_dev->enabled && cdx->ops->bus_disable) + cdx->ops->bus_disable(cdx, cdx_dev->bus_num); if (cdx_drv && cdx_drv->shutdown) cdx_drv->shutdown(cdx_dev); } diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 48fe96ab4649..e110857824fc 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -724,7 +724,7 @@ static int hpet_is_known(struct hpet_data *hdp) return 0; } -static struct ctl_table hpet_table[] = { +static const struct ctl_table hpet_table[] = { { .procname = "max-user-freq", .data = &hpet_max_freq, diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c index 7296127181ec..ee2bdc7ed0da 100644 --- a/drivers/char/ipmi/ipmb_dev_int.c +++ b/drivers/char/ipmi/ipmb_dev_int.c @@ -321,6 +321,9 @@ static int ipmb_probe(struct i2c_client *client) ipmb_dev->miscdev.name = devm_kasprintf(&client->dev, GFP_KERNEL, "%s%d", "ipmb-", client->adapter->nr); + if (!ipmb_dev->miscdev.name) + return -ENOMEM; + ipmb_dev->miscdev.fops = &ipmb_fops; ipmb_dev->miscdev.parent = &client->dev; ret = misc_register(&ipmb_dev->miscdev); @@ -355,11 +358,13 @@ static const struct i2c_device_id ipmb_id[] = { }; MODULE_DEVICE_TABLE(i2c, ipmb_id); +#ifdef CONFIG_ACPI static const struct acpi_device_id acpi_ipmb_id[] = { { "IPMB0001", 0 }, {}, }; MODULE_DEVICE_TABLE(acpi, acpi_ipmb_id); +#endif static struct i2c_driver ipmb_driver = { .driver = { diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c index 332082e02ea5..e6ba35b71f10 100644 --- a/drivers/char/ipmi/ipmi_devintf.c +++ b/drivers/char/ipmi/ipmi_devintf.c @@ -122,12 +122,9 @@ out: static int ipmi_release(struct inode *inode, struct file *file) { struct ipmi_file_private *priv = file->private_data; - int rv; struct ipmi_recv_msg *msg, *next; - rv = ipmi_destroy_user(priv->user); - if (rv) - return rv; + ipmi_destroy_user(priv->user); list_for_each_entry_safe(msg, next, &priv->recv_msgs, link) ipmi_free_recv_msg(msg); diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index e12b531f5c2f..1e5313748f8b 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -1398,13 +1398,11 @@ static void _ipmi_destroy_user(struct ipmi_user *user) module_put(owner); } -int ipmi_destroy_user(struct ipmi_user *user) +void ipmi_destroy_user(struct ipmi_user *user) { _ipmi_destroy_user(user); kref_put(&user->refcount, free_user); - - return 0; } EXPORT_SYMBOL(ipmi_destroy_user); diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c index 941d2dcc8c9d..e63c316d8aaa 100644 --- a/drivers/char/ipmi/ipmi_poweroff.c +++ b/drivers/char/ipmi/ipmi_poweroff.c @@ -650,7 +650,7 @@ static struct ipmi_smi_watcher smi_watcher = { #ifdef CONFIG_PROC_FS #include -static struct ctl_table ipmi_table[] = { +static const struct ctl_table ipmi_table[] = { { .procname = "poweroff_powercycle", .data = &poweroff_powercycle, .maxlen = sizeof(poweroff_powercycle), @@ -699,8 +699,6 @@ static int __init ipmi_poweroff_init(void) #ifdef MODULE static void __exit ipmi_poweroff_cleanup(void) { - int rv; - #ifdef CONFIG_PROC_FS unregister_sysctl_table(ipmi_table_header); #endif @@ -708,9 +706,7 @@ static void __exit ipmi_poweroff_cleanup(void) ipmi_smi_watcher_unregister(&smi_watcher); if (ready) { - rv = ipmi_destroy_user(ipmi_user); - if (rv) - pr_err("could not cleanup the IPMI user: 0x%x\n", rv); + ipmi_destroy_user(ipmi_user); pm_power_off = old_poweroff_func; } } diff --git a/drivers/char/ipmi/ipmi_si_pci.c b/drivers/char/ipmi/ipmi_si_pci.c index b83d55685b22..8c0ea637aba0 100644 --- a/drivers/char/ipmi/ipmi_si_pci.c +++ b/drivers/char/ipmi/ipmi_si_pci.c @@ -118,7 +118,7 @@ static int ipmi_pci_probe(struct pci_dev *pdev, if (io.irq) io.irq_setup = ipmi_std_irq_setup; - dev_info(&pdev->dev, "%pR regsize %d spacing %d irq %d\n", + dev_info(&pdev->dev, "%pR regsize %u spacing %u irq %d\n", &pdev->resource[0], io.regsize, io.regspacing, io.irq); return ipmi_si_add_smi(&io); diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 335eea80054e..f1875b2bebbc 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -1064,7 +1064,6 @@ static void ipmi_register_watchdog(int ipmi_intf) static void ipmi_unregister_watchdog(int ipmi_intf) { - int rv; struct ipmi_user *loc_user = watchdog_user; if (!loc_user) @@ -1089,9 +1088,7 @@ static void ipmi_unregister_watchdog(int ipmi_intf) mutex_lock(&ipmi_watchdog_mutex); /* Disconnect from IPMI. */ - rv = ipmi_destroy_user(loc_user); - if (rv) - pr_warn("error unlinking from IPMI: %d\n", rv); + ipmi_destroy_user(loc_user); /* If it comes back, restart it properly. */ ipmi_start_timer_on_heartbeat = 1; diff --git a/drivers/char/ipmi/ssif_bmc.c b/drivers/char/ipmi/ssif_bmc.c index a14fafc583d4..310f17dd9511 100644 --- a/drivers/char/ipmi/ssif_bmc.c +++ b/drivers/char/ipmi/ssif_bmc.c @@ -292,7 +292,6 @@ static void complete_response(struct ssif_bmc_ctx *ssif_bmc) ssif_bmc->nbytes_processed = 0; ssif_bmc->remain_len = 0; ssif_bmc->busy = false; - memset(&ssif_bmc->part_buf, 0, sizeof(struct ssif_part_buffer)); wake_up_all(&ssif_bmc->wait_queue); } @@ -744,9 +743,11 @@ static void on_stop_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) ssif_bmc->aborting = true; } } else if (ssif_bmc->state == SSIF_RES_SENDING) { - if (ssif_bmc->is_singlepart_read || ssif_bmc->block_num == 0xFF) + if (ssif_bmc->is_singlepart_read || ssif_bmc->block_num == 0xFF) { + memset(&ssif_bmc->part_buf, 0, sizeof(struct ssif_part_buffer)); /* Invalidate response buffer to denote it is sent */ complete_response(ssif_bmc); + } ssif_bmc->state = SSIF_READY; } diff --git a/drivers/char/misc.c b/drivers/char/misc.c index 541edc26ec89..2cf595d2e10b 100644 --- a/drivers/char/misc.c +++ b/drivers/char/misc.c @@ -63,16 +63,30 @@ static DEFINE_MUTEX(misc_mtx); #define DYNAMIC_MINORS 128 /* like dynamic majors */ static DEFINE_IDA(misc_minors_ida); -static int misc_minor_alloc(void) +static int misc_minor_alloc(int minor) { - int ret; + int ret = 0; - ret = ida_alloc_max(&misc_minors_ida, DYNAMIC_MINORS - 1, GFP_KERNEL); - if (ret >= 0) { - ret = DYNAMIC_MINORS - ret - 1; + if (minor == MISC_DYNAMIC_MINOR) { + /* allocate free id */ + ret = ida_alloc_max(&misc_minors_ida, DYNAMIC_MINORS - 1, GFP_KERNEL); + if (ret >= 0) { + ret = DYNAMIC_MINORS - ret - 1; + } else { + ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1, + MINORMASK, GFP_KERNEL); + } } else { - ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1, - MINORMASK, GFP_KERNEL); + /* specific minor, check if it is in dynamic or misc dynamic range */ + if (minor < DYNAMIC_MINORS) { + minor = DYNAMIC_MINORS - minor - 1; + ret = ida_alloc_range(&misc_minors_ida, minor, minor, GFP_KERNEL); + } else if (minor > MISC_DYNAMIC_MINOR) { + ret = ida_alloc_range(&misc_minors_ida, minor, minor, GFP_KERNEL); + } else { + /* case of non-dynamic minors, no need to allocate id */ + ret = 0; + } } return ret; } @@ -219,7 +233,7 @@ int misc_register(struct miscdevice *misc) mutex_lock(&misc_mtx); if (is_dynamic) { - int i = misc_minor_alloc(); + int i = misc_minor_alloc(misc->minor); if (i < 0) { err = -EBUSY; @@ -228,6 +242,7 @@ int misc_register(struct miscdevice *misc) misc->minor = i; } else { struct miscdevice *c; + int i; list_for_each_entry(c, &misc_list, list) { if (c->minor == misc->minor) { @@ -235,6 +250,12 @@ int misc_register(struct miscdevice *misc) goto out; } } + + i = misc_minor_alloc(misc->minor); + if (i < 0) { + err = -EBUSY; + goto out; + } } dev = MKDEV(MISC_MAJOR, misc->minor); diff --git a/drivers/char/random.c b/drivers/char/random.c index 23ee76bbb4aa..2581186fa61b 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1665,7 +1665,7 @@ static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf, return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } -static struct ctl_table random_table[] = { +static const struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c index 69533d0bfb51..cf02ec646f46 100644 --- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -63,6 +63,11 @@ static bool tpm_is_tpm2_log(void *bios_event_log, u64 len) return n == 0; } +static void tpm_bios_log_free(void *data) +{ + kvfree(data); +} + /* read binary bios log */ int tpm_read_log_acpi(struct tpm_chip *chip) { @@ -136,7 +141,7 @@ int tpm_read_log_acpi(struct tpm_chip *chip) } /* malloc EventLog space */ - log->bios_event_log = devm_kmalloc(&chip->dev, len, GFP_KERNEL); + log->bios_event_log = kvmalloc(len, GFP_KERNEL); if (!log->bios_event_log) return -ENOMEM; @@ -161,10 +166,16 @@ int tpm_read_log_acpi(struct tpm_chip *chip) goto err; } + ret = devm_add_action(&chip->dev, tpm_bios_log_free, log->bios_event_log); + if (ret) { + log->bios_event_log = NULL; + goto err; + } + return format; err: - devm_kfree(&chip->dev, log->bios_event_log); + tpm_bios_log_free(log->bios_event_log); log->bios_event_log = NULL; return ret; } diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index c62b208b42f1..24442485e73e 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -883,9 +883,9 @@ static int pipe_to_sg(struct pipe_inode_info *pipe, struct pipe_buffer *buf, if (len + offset > PAGE_SIZE) len = PAGE_SIZE - offset; - src = kmap_atomic(buf->page); + src = kmap_local_page(buf->page); memcpy(page_address(page) + offset, src + buf->offset, len); - kunmap_atomic(src); + kunmap_local(src); sg_set_page(&(sgl->sg[sgl->n]), page, len, offset); } diff --git a/drivers/clk/analogbits/wrpll-cln28hpc.c b/drivers/clk/analogbits/wrpll-cln28hpc.c index 65d422a588e1..9d178afc73bd 100644 --- a/drivers/clk/analogbits/wrpll-cln28hpc.c +++ b/drivers/clk/analogbits/wrpll-cln28hpc.c @@ -292,7 +292,7 @@ int wrpll_configure_for_rate(struct wrpll_cfg *c, u32 target_rate, vco = vco_pre * f; } - delta = abs(target_rate - vco); + delta = abs(target_vco_rate - vco); if (delta < best_delta) { best_delta = delta; best_r = r; diff --git a/drivers/clk/at91/Makefile b/drivers/clk/at91/Makefile index 8e3684ba2c74..9128a06b860d 100644 --- a/drivers/clk/at91/Makefile +++ b/drivers/clk/at91/Makefile @@ -24,4 +24,5 @@ obj-$(CONFIG_SOC_SAM9X7) += sam9x7.o obj-$(CONFIG_SOC_SAMA5D3) += sama5d3.o dt-compat.o obj-$(CONFIG_SOC_SAMA5D4) += sama5d4.o dt-compat.o obj-$(CONFIG_SOC_SAMA5D2) += sama5d2.o dt-compat.o +obj-$(CONFIG_SOC_SAMA7D65) += sama7d65.o obj-$(CONFIG_SOC_SAMA7G5) += sama7g5.o diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c index 15c46489ba85..7a544e429d34 100644 --- a/drivers/clk/at91/clk-master.c +++ b/drivers/clk/at91/clk-master.c @@ -20,7 +20,7 @@ #define PMC_MCR_CSS_SHIFT (16) -#define MASTER_MAX_ID 4 +#define MASTER_MAX_ID 9 #define to_clk_master(hw) container_of(hw, struct clk_master, hw) diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c index fda041102224..cefd9948e103 100644 --- a/drivers/clk/at91/clk-sam9x60-pll.c +++ b/drivers/clk/at91/clk-sam9x60-pll.c @@ -23,7 +23,7 @@ #define UPLL_DIV 2 #define PLL_MUL_MAX (FIELD_GET(PMC_PLL_CTRL1_MUL_MSK, UINT_MAX) + 1) -#define PLL_MAX_ID 7 +#define PLL_MAX_ID 9 struct sam9x60_pll_core { struct regmap *regmap; diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c index 5aa9c1f1c886..acf780a81589 100644 --- a/drivers/clk/at91/pmc.c +++ b/drivers/clk/at91/pmc.c @@ -151,6 +151,7 @@ static struct syscore_ops pmc_syscore_ops = { static const struct of_device_id pmc_dt_ids[] = { { .compatible = "atmel,sama5d2-pmc" }, { .compatible = "microchip,sama7g5-pmc", }, + { .compatible = "microchip,sama7d65-pmc", }, { /* sentinel */ } }; diff --git a/drivers/clk/at91/sama7d65.c b/drivers/clk/at91/sama7d65.c new file mode 100644 index 000000000000..a5d40df8b2f2 --- /dev/null +++ b/drivers/clk/at91/sama7d65.c @@ -0,0 +1,1375 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SAMA7D65 PMC code. + * + * Copyright (C) 2024 Microchip Technology Inc. and its subsidiaries + * + * Author: Ryan Wanner + */ +#include +#include +#include +#include + +#include + +#include "pmc.h" + +static DEFINE_SPINLOCK(pmc_pll_lock); +static DEFINE_SPINLOCK(pmc_mck0_lock); +static DEFINE_SPINLOCK(pmc_mckX_lock); + +#define PMC_INDEX_MAX 25 + +/* + * PLL clocks identifiers + * @PLL_ID_CPU: CPU PLL identifier + * @PLL_ID_SYS: System PLL identifier + * @PLL_ID_DDR: DDR PLL identifier + * @PLL_ID_GPU: Graphics subsystem PLL identifier + * @PLL_ID_BAUD: Baud PLL identifier + * @PLL_ID_AUDIO: Audio PLL identifier + * @PLL_ID_ETH: Ethernet PLL identifier + * @PLL_ID_LVDS: LVDS PLL identifier + * @PLL_ID_USB: USB PLL identifier + */ +enum pll_ids { + PLL_ID_CPU, + PLL_ID_SYS, + PLL_ID_DDR, + PLL_ID_GPU, + PLL_ID_BAUD, + PLL_ID_AUDIO, + PLL_ID_ETH, + PLL_ID_LVDS, + PLL_ID_USB, + PLL_ID_MAX +}; + +/* + * PLL component identifier + * @PLL_COMPID_FRAC: Fractional PLL component identifier + * @PLL_COMPID_DIV0: 1st PLL divider component identifier + * @PLL_COMPID_DIV1: 2nd PLL divider component identifier + */ +enum pll_component_id { + PLL_COMPID_FRAC, + PLL_COMPID_DIV0, + PLL_COMPID_DIV1, + PLL_COMPID_MAX +}; + +/* + * PLL type identifiers + * @PLL_TYPE_FRAC: fractional PLL identifier + * @PLL_TYPE_DIV: divider PLL identifier + */ +enum pll_type { + PLL_TYPE_FRAC, + PLL_TYPE_DIV +}; + +/* Layout for fractional PLLs. */ +static const struct clk_pll_layout pll_layout_frac = { + .mul_mask = GENMASK(31, 24), + .frac_mask = GENMASK(21, 0), + .mul_shift = 24, + .frac_shift = 0, +}; + +/* Layout for DIVPMC dividers. */ +static const struct clk_pll_layout pll_layout_divpmc = { + .div_mask = GENMASK(7, 0), + .endiv_mask = BIT(29), + .div_shift = 0, + .endiv_shift = 29, +}; + +/* Layout for DIVIO dividers. */ +static const struct clk_pll_layout pll_layout_divio = { + .div_mask = GENMASK(19, 12), + .endiv_mask = BIT(30), + .div_shift = 12, + .endiv_shift = 30, +}; + +/* + * CPU PLL output range. + * Notice: The upper limit has been setup to 1000000002 due to hardware + * block which cannot output exactly 1GHz. + */ +static const struct clk_range cpu_pll_outputs[] = { + { .min = 2343750, .max = 1000000002 }, +}; + +/* PLL output range. */ +static const struct clk_range pll_outputs[] = { + { .min = 2343750, .max = 1200000000 }, +}; + +/* + * Min: fCOREPLLCK = 600 MHz, PMC_PLL_CTRL0.DIVPMC = 255 + * Max: fCOREPLLCK = 800 MHz, PMC_PLL_CTRL0.DIVPMC = 0 + */ +static const struct clk_range lvdspll_outputs[] = { + { .min = 16406250, .max = 800000000 }, +}; + +static const struct clk_range upll_outputs[] = { + { .min = 480000000, .max = 480000000 }, +}; + +/* Fractional PLL core output range. */ +static const struct clk_range core_outputs[] = { + { .min = 600000000, .max = 1200000000 }, +}; + +static const struct clk_range lvdspll_core_outputs[] = { + { .min = 600000000, .max = 1200000000 }, +}; + +static const struct clk_range upll_core_outputs[] = { + { .min = 600000000, .max = 1200000000 }, +}; + +/* CPU PLL characteristics. */ +static const struct clk_pll_characteristics cpu_pll_characteristics = { + .input = { .min = 12000000, .max = 50000000 }, + .num_output = ARRAY_SIZE(cpu_pll_outputs), + .output = cpu_pll_outputs, + .core_output = core_outputs, +}; + +/* PLL characteristics. */ +static const struct clk_pll_characteristics pll_characteristics = { + .input = { .min = 12000000, .max = 50000000 }, + .num_output = ARRAY_SIZE(pll_outputs), + .output = pll_outputs, + .core_output = core_outputs, +}; + +static const struct clk_pll_characteristics lvdspll_characteristics = { + .input = { .min = 12000000, .max = 50000000 }, + .num_output = ARRAY_SIZE(lvdspll_outputs), + .output = lvdspll_outputs, + .core_output = lvdspll_core_outputs, +}; + +static const struct clk_pll_characteristics upll_characteristics = { + .input = { .min = 20000000, .max = 50000000 }, + .num_output = ARRAY_SIZE(upll_outputs), + .output = upll_outputs, + .core_output = upll_core_outputs, + .upll = true, +}; + +/* + * SAMA7D65 PLL possible parents + * @SAMA7D65_PLL_PARENT_MAINCK: MAINCK is PLL a parent + * @SAMA7D65_PLL_PARENT_MAIN_XTAL: MAIN XTAL is a PLL parent + * @SAMA7D65_PLL_PARENT_FRACCK: Frac PLL is a PLL parent (for PLL dividers) + */ +enum sama7d65_pll_parent { + SAMA7D65_PLL_PARENT_MAINCK, + SAMA7D65_PLL_PARENT_MAIN_XTAL, + SAMA7D65_PLL_PARENT_FRACCK +}; + +/* + * PLL clocks description + * @n: clock name + * @l: clock layout + * @c: clock characteristics + * @hw: pointer to clk_hw + * @t: clock type + * @f: clock flags + * @p: clock parent + * @eid: export index in sama7d65->chws[] array + * @safe_div: intermediate divider need to be set on PRE_RATE_CHANGE + * notification + */ +static struct sama7d65_pll { + const char *n; + const struct clk_pll_layout *l; + const struct clk_pll_characteristics *c; + struct clk_hw *hw; + unsigned long f; + enum sama7d65_pll_parent p; + u8 t; + u8 eid; + u8 safe_div; +} sama7d65_plls[][PLL_COMPID_MAX] = { + [PLL_ID_CPU] = { + [PLL_COMPID_FRAC] = { + .n = "cpupll_fracck", + .p = SAMA7D65_PLL_PARENT_MAINCK, + .l = &pll_layout_frac, + .c = &cpu_pll_characteristics, + .t = PLL_TYPE_FRAC, + /* + * This feeds cpupll_divpmcck which feeds CPU. It should + * not be disabled. + */ + .f = CLK_IS_CRITICAL, + }, + + [PLL_COMPID_DIV0] = { + .n = "cpupll_divpmcck", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divpmc, + .c = &cpu_pll_characteristics, + .t = PLL_TYPE_DIV, + /* This feeds CPU. It should not be disabled. */ + .f = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, + .eid = PMC_CPUPLL, + /* + * Safe div=15 should be safe even for switching b/w 1GHz and + * 90MHz (frac pll might go up to 1.2GHz). + */ + .safe_div = 15, + }, + }, + + [PLL_ID_SYS] = { + [PLL_COMPID_FRAC] = { + .n = "syspll_fracck", + .p = SAMA7D65_PLL_PARENT_MAINCK, + .l = &pll_layout_frac, + .c = &pll_characteristics, + .t = PLL_TYPE_FRAC, + /* + * This feeds syspll_divpmcck which may feed critical parts + * of the systems like timers. Therefore it should not be + * disabled. + */ + .f = CLK_IS_CRITICAL | CLK_SET_RATE_GATE, + }, + + [PLL_COMPID_DIV0] = { + .n = "syspll_divpmcck", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divpmc, + .c = &pll_characteristics, + .t = PLL_TYPE_DIV, + /* + * This may feed critical parts of the systems like timers. + * Therefore it should not be disabled. + */ + .f = CLK_IS_CRITICAL | CLK_SET_RATE_GATE, + .eid = PMC_SYSPLL, + }, + }, + + [PLL_ID_DDR] = { + [PLL_COMPID_FRAC] = { + .n = "ddrpll_fracck", + .p = SAMA7D65_PLL_PARENT_MAINCK, + .l = &pll_layout_frac, + .c = &pll_characteristics, + .t = PLL_TYPE_FRAC, + /* + * This feeds ddrpll_divpmcck which feeds DDR. It should not + * be disabled. + */ + .f = CLK_IS_CRITICAL | CLK_SET_RATE_GATE, + }, + + [PLL_COMPID_DIV0] = { + .n = "ddrpll_divpmcck", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divpmc, + .c = &pll_characteristics, + .t = PLL_TYPE_DIV, + /* This feeds DDR. It should not be disabled. */ + .f = CLK_IS_CRITICAL | CLK_SET_RATE_GATE, + }, + }, + + [PLL_ID_GPU] = { + [PLL_COMPID_FRAC] = { + .n = "gpupll_fracck", + .p = SAMA7D65_PLL_PARENT_MAINCK, + .l = &pll_layout_frac, + .c = &pll_characteristics, + .t = PLL_TYPE_FRAC, + .f = CLK_SET_RATE_GATE, + }, + + [PLL_COMPID_DIV0] = { + .n = "gpupll_divpmcck", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divpmc, + .c = &pll_characteristics, + .t = PLL_TYPE_DIV, + .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE | + CLK_SET_RATE_PARENT, + }, + }, + + [PLL_ID_BAUD] = { + [PLL_COMPID_FRAC] = { + .n = "baudpll_fracck", + .p = SAMA7D65_PLL_PARENT_MAINCK, + .l = &pll_layout_frac, + .c = &pll_characteristics, + .t = PLL_TYPE_FRAC, + .f = CLK_SET_RATE_GATE, + }, + + [PLL_COMPID_DIV0] = { + .n = "baudpll_divpmcck", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divpmc, + .c = &pll_characteristics, + .t = PLL_TYPE_DIV, + .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE | + CLK_SET_RATE_PARENT, + .eid = PMC_BAUDPLL, + }, + }, + + [PLL_ID_AUDIO] = { + [PLL_COMPID_FRAC] = { + .n = "audiopll_fracck", + .p = SAMA7D65_PLL_PARENT_MAIN_XTAL, + .l = &pll_layout_frac, + .c = &pll_characteristics, + .t = PLL_TYPE_FRAC, + .f = CLK_SET_RATE_GATE, + }, + + [PLL_COMPID_DIV0] = { + .n = "audiopll_divpmcck", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divpmc, + .c = &pll_characteristics, + .t = PLL_TYPE_DIV, + .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE | + CLK_SET_RATE_PARENT, + .eid = PMC_AUDIOPMCPLL, + }, + + [PLL_COMPID_DIV1] = { + .n = "audiopll_diviock", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divio, + .c = &pll_characteristics, + .t = PLL_TYPE_DIV, + .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE | + CLK_SET_RATE_PARENT, + .eid = PMC_AUDIOIOPLL, + }, + }, + + [PLL_ID_ETH] = { + [PLL_COMPID_FRAC] = { + .n = "ethpll_fracck", + .p = SAMA7D65_PLL_PARENT_MAIN_XTAL, + .l = &pll_layout_frac, + .c = &pll_characteristics, + .t = PLL_TYPE_FRAC, + .f = CLK_SET_RATE_GATE, + }, + + [PLL_COMPID_DIV0] = { + .n = "ethpll_divpmcck", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divpmc, + .c = &pll_characteristics, + .t = PLL_TYPE_DIV, + .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE | + CLK_SET_RATE_PARENT, + .eid = PMC_ETHPLL, + }, + }, + + [PLL_ID_LVDS] = { + [PLL_COMPID_FRAC] = { + .n = "lvdspll_fracck", + .p = SAMA7D65_PLL_PARENT_MAIN_XTAL, + .l = &pll_layout_frac, + .c = &lvdspll_characteristics, + .t = PLL_TYPE_FRAC, + .f = CLK_SET_RATE_GATE, + }, + + [PLL_COMPID_DIV0] = { + .n = "lvdspll_divpmcck", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divpmc, + .c = &lvdspll_characteristics, + .t = PLL_TYPE_DIV, + .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE | + CLK_SET_RATE_PARENT, + .eid = PMC_LVDSPLL, + }, + }, + + [PLL_ID_USB] = { + [PLL_COMPID_FRAC] = { + .n = "usbpll_fracck", + .p = SAMA7D65_PLL_PARENT_MAIN_XTAL, + .l = &pll_layout_frac, + .c = &upll_characteristics, + .t = PLL_TYPE_FRAC, + .f = CLK_SET_RATE_GATE, + }, + + [PLL_COMPID_DIV0] = { + .n = "usbpll_divpmcck", + .p = SAMA7D65_PLL_PARENT_FRACCK, + .l = &pll_layout_divpmc, + .c = &upll_characteristics, + .t = PLL_TYPE_DIV, + .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE | + CLK_SET_RATE_PARENT, + .eid = PMC_UTMI, + }, + }, +}; + +/* Used to create an array entry identifying a PLL by its components. */ +#define PLL_IDS_TO_ARR_ENTRY(_id, _comp) { PLL_ID_##_id, PLL_COMPID_##_comp} + +/* + * Master clock (MCK[0..9]) description + * @n: clock name + * @ep_chg_chg_id: index in parents array that specifies the changeable + * @ep: extra parents names array (entry formed by PLL components + * identifiers (see enum pll_component_id)) + * @hw: pointer to clk_hw + * parent + * @ep_count: extra parents count + * @ep_mux_table: mux table for extra parents + * @id: clock id + * @eid: export index in sama7d65->chws[] array + * @c: true if clock is critical and cannot be disabled + */ +static struct { + const char *n; + struct { + int pll_id; + int pll_compid; + } ep[4]; + struct clk_hw *hw; + int ep_chg_id; + u8 ep_count; + u8 ep_mux_table[4]; + u8 id; + u8 eid; + u8 c; +} sama7d65_mckx[] = { + { .n = "mck0", }, /* Dummy entry for MCK0 to store hw in probe. */ + { .n = "mck1", + .id = 1, + .ep = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), }, + .ep_mux_table = { 5, }, + .ep_count = 1, + .ep_chg_id = INT_MIN, + .eid = PMC_MCK1, + .c = 1, }, + + { .n = "mck2", + .id = 2, + .ep = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), PLL_IDS_TO_ARR_ENTRY(DDR, DIV0), }, + .ep_mux_table = { 5, 6, }, + .ep_count = 2, + .ep_chg_id = INT_MIN, + .c = 1, }, + + { .n = "mck3", + .id = 3, + .ep = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), PLL_IDS_TO_ARR_ENTRY(DDR, DIV0), }, + .ep_mux_table = { 5, 6, }, + .ep_count = 2, + .ep_chg_id = INT_MIN, + .eid = PMC_MCK3, + .c = 1, }, + + { .n = "mck4", + .id = 4, + .ep = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), }, + .ep_mux_table = { 5, }, + .ep_count = 1, + .ep_chg_id = INT_MIN, + .c = 1, }, + + { .n = "mck5", + .id = 5, + .ep = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), }, + .ep_mux_table = { 5, }, + .ep_count = 1, + .ep_chg_id = INT_MIN, + .eid = PMC_MCK5, + .c = 1, }, + + { .n = "mck6", + .id = 6, + .ep = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), }, + .ep_mux_table = { 5, }, + .ep_chg_id = INT_MIN, + .ep_count = 1, + .c = 1, }, + + { .n = "mck7", + .id = 7, + .ep = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), }, + .ep_mux_table = { 5, }, + .ep_chg_id = INT_MIN, + .ep_count = 1, }, + + { .n = "mck8", + .id = 8, + .ep = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), }, + .ep_mux_table = { 5, }, + .ep_chg_id = INT_MIN, + .ep_count = 1, }, + + { .n = "mck9", + .id = 9, + .ep = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), }, + .ep_mux_table = { 5, }, + .ep_chg_id = INT_MIN, + .ep_count = 1, }, +}; + +/* + * System clock description + * @n: clock name + * @p: clock parent name + * @id: clock id + */ +static const struct { + const char *n; + const char *p; + u8 id; +} sama7d65_systemck[] = { + { .n = "uhpck", .p = "usbck", .id = 6 }, + { .n = "pck0", .p = "prog0", .id = 8, }, + { .n = "pck1", .p = "prog1", .id = 9, }, + { .n = "pck2", .p = "prog2", .id = 10, }, + { .n = "pck3", .p = "prog3", .id = 11, }, + { .n = "pck4", .p = "prog4", .id = 12, }, + { .n = "pck5", .p = "prog5", .id = 13, }, + { .n = "pck6", .p = "prog6", .id = 14, }, + { .n = "pck7", .p = "prog7", .id = 15, }, +}; + +/* Mux table for programmable clocks. */ +static u32 sama7d65_prog_mux_table[] = { 0, 1, 2, 5, 7, 8, 9, 10, 12 }; + +/* + * Peripheral clock parent hw identifier (used to index in sama7d65_mckx[]) + * @PCK_PARENT_HW_MCK0: pck parent hw identifier is MCK0 + * @PCK_PARENT_HW_MCK1: pck parent hw identifier is MCK1 + * @PCK_PARENT_HW_MCK2: pck parent hw identifier is MCK2 + * @PCK_PARENT_HW_MCK3: pck parent hw identifier is MCK3 + * @PCK_PARENT_HW_MCK4: pck parent hw identifier is MCK4 + * @PCK_PARENT_HW_MCK5: pck parent hw identifier is MCK5 + * @PCK_PARENT_HW_MCK6: pck parent hw identifier is MCK6 + * @PCK_PARENT_HW_MCK7: pck parent hw identifier is MCK7 + * @PCK_PARENT_HW_MCK8: pck parent hw identifier is MCK8 + * @PCK_PARENT_HW_MCK9: pck parent hw identifier is MCK9 + * @PCK_PARENT_HW_MAX: max identifier + */ +enum sama7d65_pck_parent_hw_id { + PCK_PARENT_HW_MCK0, + PCK_PARENT_HW_MCK1, + PCK_PARENT_HW_MCK2, + PCK_PARENT_HW_MCK3, + PCK_PARENT_HW_MCK4, + PCK_PARENT_HW_MCK5, + PCK_PARENT_HW_MCK6, + PCK_PARENT_HW_MCK7, + PCK_PARENT_HW_MCK8, + PCK_PARENT_HW_MCK9, + PCK_PARENT_HW_MAX +}; + +/* + * Peripheral clock description + * @n: clock name + * @p: clock parent hw id + * @r: clock range values + * @id: clock id + * @chgp: index in parent array of the changeable parent + */ +static struct { + const char *n; + enum sama7d65_pck_parent_hw_id p; + struct clk_range r; + u8 chgp; + u8 id; +} sama7d65_periphck[] = { + { .n = "pioA_clk", .p = PCK_PARENT_HW_MCK0, .id = 10, }, + { .n = "securam_clk", .p = PCK_PARENT_HW_MCK0, .id = 17, }, + { .n = "sfr_clk", .p = PCK_PARENT_HW_MCK7, .id = 18, }, + { .n = "hsmc_clk", .p = PCK_PARENT_HW_MCK5, .id = 20, }, + { .n = "xdmac0_clk", .p = PCK_PARENT_HW_MCK6, .id = 21, }, + { .n = "xdmac1_clk", .p = PCK_PARENT_HW_MCK6, .id = 22, }, + { .n = "xdmac2_clk", .p = PCK_PARENT_HW_MCK1, .id = 23, }, + { .n = "acc_clk", .p = PCK_PARENT_HW_MCK7, .id = 24, }, + { .n = "aes_clk", .p = PCK_PARENT_HW_MCK6, .id = 26, }, + { .n = "tzaesbasc_clk", .p = PCK_PARENT_HW_MCK8, .id = 27, }, + { .n = "asrc_clk", .p = PCK_PARENT_HW_MCK9, .id = 29, .r = { .max = 200000000, }, }, + { .n = "cpkcc_clk", .p = PCK_PARENT_HW_MCK0, .id = 30, }, + { .n = "eic_clk", .p = PCK_PARENT_HW_MCK7, .id = 33, }, + { .n = "flex0_clk", .p = PCK_PARENT_HW_MCK7, .id = 34, }, + { .n = "flex1_clk", .p = PCK_PARENT_HW_MCK7, .id = 35, }, + { .n = "flex2_clk", .p = PCK_PARENT_HW_MCK7, .id = 36, }, + { .n = "flex3_clk", .p = PCK_PARENT_HW_MCK7, .id = 37, }, + { .n = "flex4_clk", .p = PCK_PARENT_HW_MCK8, .id = 38, }, + { .n = "flex5_clk", .p = PCK_PARENT_HW_MCK8, .id = 39, }, + { .n = "flex6_clk", .p = PCK_PARENT_HW_MCK8, .id = 40, }, + { .n = "flex7_clk", .p = PCK_PARENT_HW_MCK8, .id = 41, }, + { .n = "flex8_clk", .p = PCK_PARENT_HW_MCK9, .id = 42, }, + { .n = "flex9_clk", .p = PCK_PARENT_HW_MCK9, .id = 43, }, + { .n = "flex10_clk", .p = PCK_PARENT_HW_MCK9, .id = 44, }, + { .n = "gmac0_clk", .p = PCK_PARENT_HW_MCK6, .id = 46, }, + { .n = "gmac1_clk", .p = PCK_PARENT_HW_MCK6, .id = 47, }, + { .n = "gmac0_tsu_clk", .p = PCK_PARENT_HW_MCK1, .id = 49, }, + { .n = "gmac1_tsu_clk", .p = PCK_PARENT_HW_MCK1, .id = 50, }, + { .n = "icm_clk", .p = PCK_PARENT_HW_MCK5, .id = 53, }, + { .n = "i2smcc0_clk", .p = PCK_PARENT_HW_MCK9, .id = 54, .r = { .max = 200000000, }, }, + { .n = "i2smcc1_clk", .p = PCK_PARENT_HW_MCK9, .id = 55, .r = { .max = 200000000, }, }, + { .n = "lcd_clk", .p = PCK_PARENT_HW_MCK3, .id = 56, }, + { .n = "matrix_clk", .p = PCK_PARENT_HW_MCK5, .id = 57, }, + { .n = "mcan0_clk", .p = PCK_PARENT_HW_MCK5, .id = 58, .r = { .max = 200000000, }, }, + { .n = "mcan1_clk", .p = PCK_PARENT_HW_MCK5, .id = 59, .r = { .max = 200000000, }, }, + { .n = "mcan2_clk", .p = PCK_PARENT_HW_MCK5, .id = 60, .r = { .max = 200000000, }, }, + { .n = "mcan3_clk", .p = PCK_PARENT_HW_MCK5, .id = 61, .r = { .max = 200000000, }, }, + { .n = "mcan4_clk", .p = PCK_PARENT_HW_MCK5, .id = 62, .r = { .max = 200000000, }, }, + { .n = "pdmc0_clk", .p = PCK_PARENT_HW_MCK9, .id = 64, .r = { .max = 200000000, }, }, + { .n = "pdmc1_clk", .p = PCK_PARENT_HW_MCK9, .id = 65, .r = { .max = 200000000, }, }, + { .n = "pit64b0_clk", .p = PCK_PARENT_HW_MCK7, .id = 66, }, + { .n = "pit64b1_clk", .p = PCK_PARENT_HW_MCK7, .id = 67, }, + { .n = "pit64b2_clk", .p = PCK_PARENT_HW_MCK7, .id = 68, }, + { .n = "pit64b3_clk", .p = PCK_PARENT_HW_MCK8, .id = 69, }, + { .n = "pit64b4_clk", .p = PCK_PARENT_HW_MCK8, .id = 70, }, + { .n = "pit64b5_clk", .p = PCK_PARENT_HW_MCK8, .id = 71, }, + { .n = "pwm_clk", .p = PCK_PARENT_HW_MCK7, .id = 72, }, + { .n = "qspi0_clk", .p = PCK_PARENT_HW_MCK5, .id = 73, }, + { .n = "qspi1_clk", .p = PCK_PARENT_HW_MCK5, .id = 74, }, + { .n = "sdmmc0_clk", .p = PCK_PARENT_HW_MCK1, .id = 75, }, + { .n = "sdmmc1_clk", .p = PCK_PARENT_HW_MCK1, .id = 76, }, + { .n = "sdmmc2_clk", .p = PCK_PARENT_HW_MCK1, .id = 77, }, + { .n = "sha_clk", .p = PCK_PARENT_HW_MCK6, .id = 78, }, + { .n = "spdifrx_clk", .p = PCK_PARENT_HW_MCK9, .id = 79, .r = { .max = 200000000, }, }, + { .n = "spdiftx_clk", .p = PCK_PARENT_HW_MCK9, .id = 80, .r = { .max = 200000000, }, }, + { .n = "ssc0_clk", .p = PCK_PARENT_HW_MCK7, .id = 81, .r = { .max = 200000000, }, }, + { .n = "ssc1_clk", .p = PCK_PARENT_HW_MCK8, .id = 82, .r = { .max = 200000000, }, }, + { .n = "tcb0_ch0_clk", .p = PCK_PARENT_HW_MCK8, .id = 83, .r = { .max = 200000000, }, }, + { .n = "tcb0_ch1_clk", .p = PCK_PARENT_HW_MCK8, .id = 84, .r = { .max = 200000000, }, }, + { .n = "tcb0_ch2_clk", .p = PCK_PARENT_HW_MCK8, .id = 85, .r = { .max = 200000000, }, }, + { .n = "tcb1_ch0_clk", .p = PCK_PARENT_HW_MCK5, .id = 86, .r = { .max = 200000000, }, }, + { .n = "tcb1_ch1_clk", .p = PCK_PARENT_HW_MCK5, .id = 87, .r = { .max = 200000000, }, }, + { .n = "tcb1_ch2_clk", .p = PCK_PARENT_HW_MCK5, .id = 88, .r = { .max = 200000000, }, }, + { .n = "tcpca_clk", .p = PCK_PARENT_HW_MCK5, .id = 89, }, + { .n = "tcpcb_clk", .p = PCK_PARENT_HW_MCK5, .id = 90, }, + { .n = "tdes_clk", .p = PCK_PARENT_HW_MCK6, .id = 91, }, + { .n = "trng_clk", .p = PCK_PARENT_HW_MCK6, .id = 92, }, + { .n = "udphsa_clk", .p = PCK_PARENT_HW_MCK5, .id = 99, }, + { .n = "udphsb_clk", .p = PCK_PARENT_HW_MCK5, .id = 100, }, + { .n = "uhphs_clk", .p = PCK_PARENT_HW_MCK5, .id = 101, }, + { .n = "dsi_clk", .p = PCK_PARENT_HW_MCK3, .id = 103, }, + { .n = "lvdsc_clk", .p = PCK_PARENT_HW_MCK3, .id = 104, }, +}; + +/* + * Generic clock description + * @n: clock name + * @pp: PLL parents (entry formed by PLL components identifiers + * (see enum pll_component_id)) + * @pp_mux_table: PLL parents mux table + * @r: clock output range + * @pp_chg_id: id in parent array of changeable PLL parent + * @pp_count: PLL parents count + * @id: clock id + */ +static const struct { + const char *n; + struct { + int pll_id; + int pll_compid; + } pp[8]; + const char pp_mux_table[8]; + struct clk_range r; + int pp_chg_id; + u8 pp_count; + u8 id; +} sama7d65_gck[] = { + { .n = "adc_gclk", + .id = 25, + .r = { .max = 100000000, }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), }, + .pp_mux_table = { 8, 9, }, + .pp_count = 2, + .pp_chg_id = INT_MIN, }, + + { .n = "asrc_gclk", + .id = 29, + .r = { .max = 200000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), }, + .pp_mux_table = { 9, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex0_gclk", + .id = 34, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = {8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex1_gclk", + .id = 35, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = {8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex2_gclk", + .id = 36, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = {8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex3_gclk", + .id = 37, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = {8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex4_gclk", + .id = 38, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = { 8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex5_gclk", + .id = 39, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = { 8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex6_gclk", + .id = 40, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = { 8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex7_gclk", + .id = 41, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = { 8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex8_gclk", + .id = 42, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = { 8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex9_gclk", + .id = 43, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = { 8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "flex10_gclk", + .id = 44, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = { 8, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "gmac0_gclk", + .id = 46, + .r = { .max = 125000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 10, }, + .pp_count = 1, + .pp_chg_id = 4, }, + + { .n = "gmac1_gclk", + .id = 47, + .r = { .max = 125000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 10, }, + .pp_count = 1, + .pp_chg_id = 4, }, + + { .n = "gmac0_tsu_gclk", + .id = 49, + .r = { .max = 400000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = {10, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "gmac1_tsu_gclk", + .id = 50, + .r = { .max = 400000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 10, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "i2smcc0_gclk", + .id = 54, + .r = { .max = 100000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), }, + .pp_mux_table = { 9, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "i2smcc1_gclk", + .id = 55, + .r = { .max = 100000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), }, + .pp_mux_table = { 9, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "lcdc_gclk", + .id = 56, + .r = { .max = 90000000 }, + .pp_count = 0, + .pp_chg_id = INT_MIN, + }, + + { .n = "mcan0_gclk", + .id = 58, + .r = { .max = 80000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(USB, DIV0), }, + .pp_mux_table = { 12 }, + .pp_count = 1, + .pp_chg_id = 4, }, + + { .n = "mcan1_gclk", + .id = 59, + .r = { .max = 80000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(USB, DIV0), }, + .pp_mux_table = { 12 }, + .pp_count = 1, + .pp_chg_id = 4, }, + + { .n = "mcan2_gclk", + .id = 60, + .r = { .max = 80000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(USB, DIV0), }, + .pp_mux_table = { 12 }, + .pp_count = 1, + .pp_chg_id = 4, }, + + { .n = "mcan3_gclk", + .id = 61, + .r = { .max = 80000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(USB, DIV0), }, + .pp_mux_table = { 12 }, + .pp_count = 1, + .pp_chg_id = 4, }, + + { .n = "mcan4_gclk", + .id = 62, + .r = { .max = 80000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(USB, DIV0), }, + .pp_mux_table = { 12 }, + .pp_count = 1, + .pp_chg_id = 4, }, + + { .n = "pdmc0_gclk", + .id = 64, + .r = { .max = 80000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), }, + .pp_mux_table = { 9 }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "pdmc1_gclk", + .id = 65, + .r = { .max = 80000000, }, + .pp = { PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), }, + .pp_mux_table = { 9, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "pit64b0_gclk", + .id = 66, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), + PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 8, 9, 10, }, + .pp_count = 3, + .pp_chg_id = INT_MIN, }, + + { .n = "pit64b1_gclk", + .id = 67, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), + PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 8, 9, 10, }, + .pp_count = 3, + .pp_chg_id = INT_MIN, }, + + { .n = "pit64b2_gclk", + .id = 68, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), + PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 8, 9, 10, }, + .pp_count = 3, + .pp_chg_id = INT_MIN, }, + + { .n = "pit64b3_gclk", + .id = 69, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), + PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = {8, 9, 10, }, + .pp_count = 3, + .pp_chg_id = INT_MIN, }, + + { .n = "pit64b4_gclk", + .id = 70, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), + PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = {8, 9, 10, }, + .pp_count = 3, + .pp_chg_id = INT_MIN, }, + + { .n = "pit64b5_gclk", + .id = 71, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), + PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = {8, 9, 10, }, + .pp_count = 3, + .pp_chg_id = INT_MIN, }, + + { .n = "qspi0_gclk", + .id = 73, + .r = { .max = 400000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = { 5, 8, }, + .pp_count = 2, + .pp_chg_id = INT_MIN, }, + + { .n = "qspi1_gclk", + .id = 74, + .r = { .max = 266000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), }, + .pp_mux_table = { 5, 8, }, + .pp_count = 2, + .pp_chg_id = INT_MIN, }, + + { .n = "sdmmc0_gclk", + .id = 75, + .r = { .max = 208000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 8, 10, }, + .pp_count = 2, + .pp_chg_id = 4, }, + + { .n = "sdmmc1_gclk", + .id = 76, + .r = { .max = 208000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 8, 10, }, + .pp_count = 2, + .pp_chg_id = 4, }, + + { .n = "sdmmc2_gclk", + .id = 77, + .r = { .max = 208000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 8, 10 }, + .pp_count = 2, + .pp_chg_id = 4, }, + + { .n = "spdifrx_gclk", + .id = 79, + .r = { .max = 150000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), }, + .pp_mux_table = { 9, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "spdiftx_gclk", + .id = 80, + .r = { .max = 25000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), }, + .pp_mux_table = { 9, }, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "tcb0_ch0_gclk", + .id = 83, + .r = { .max = 34000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), + PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 8, 9, 10, }, + .pp_count = 3, + .pp_chg_id = INT_MIN, }, + + { .n = "tcb1_ch0_gclk", + .id = 86, + .r = { .max = 67000000 }, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), + PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = { 8, 9, 10, }, + .pp_count = 3, + .pp_chg_id = INT_MIN, }, + + { .n = "DSI_gclk", + .id = 103, + .r = {.max = 27000000}, + .pp = { PLL_IDS_TO_ARR_ENTRY(SYS, DIV0), }, + .pp_mux_table = {5}, + .pp_count = 1, + .pp_chg_id = INT_MIN, }, + + { .n = "I3CC_gclk", + .id = 105, + .r = {.max = 125000000}, + .pp = { PLL_IDS_TO_ARR_ENTRY(BAUD, DIV0), PLL_IDS_TO_ARR_ENTRY(AUDIO, DIV0), + PLL_IDS_TO_ARR_ENTRY(ETH, DIV0), }, + .pp_mux_table = {8, 9, 10, }, + .pp_count = 3, + .pp_chg_id = INT_MIN, }, +}; + +/* MCK0 characteristics. */ +static const struct clk_master_characteristics mck0_characteristics = { + .output = { .min = 32768, .max = 200000000 }, + .divisors = { 1, 2, 4, 3, 5 }, + .have_div3_pres = 1, +}; + +/* MCK0 layout. */ +static const struct clk_master_layout mck0_layout = { + .mask = 0x773, + .pres_shift = 4, + .offset = 0x28, +}; + +/* Programmable clock layout. */ +static const struct clk_programmable_layout programmable_layout = { + .pres_mask = 0xff, + .pres_shift = 8, + .css_mask = 0x1f, + .have_slck_mck = 0, + .is_pres_direct = 1, +}; + +/* Peripheral clock layout. */ +static const struct clk_pcr_layout sama7d65_pcr_layout = { + .offset = 0x88, + .cmd = BIT(31), + .gckcss_mask = GENMASK(12, 8), + .pid_mask = GENMASK(6, 0), +}; + +static void __init sama7d65_pmc_setup(struct device_node *np) +{ + const char *main_xtal_name = "main_xtal"; + struct pmc_data *sama7d65_pmc; + const char *parent_names[11]; + void **alloc_mem = NULL; + int alloc_mem_size = 0; + struct regmap *regmap; + struct clk_hw *hw, *main_rc_hw, *main_osc_hw, *main_xtal_hw; + struct clk_hw *td_slck_hw, *md_slck_hw; + static struct clk_parent_data parent_data; + struct clk_hw *parent_hws[10]; + bool bypass; + int i, j; + + td_slck_hw = __clk_get_hw(of_clk_get_by_name(np, "td_slck")); + md_slck_hw = __clk_get_hw(of_clk_get_by_name(np, "md_slck")); + main_xtal_hw = __clk_get_hw(of_clk_get_by_name(np, main_xtal_name)); + + if (!td_slck_hw || !md_slck_hw || !main_xtal_hw) + return; + + regmap = device_node_to_regmap(np); + if (IS_ERR(regmap)) + return; + + sama7d65_pmc = pmc_data_allocate(PMC_INDEX_MAX, + nck(sama7d65_systemck), + nck(sama7d65_periphck), + nck(sama7d65_gck), 8); + if (!sama7d65_pmc) + return; + + alloc_mem = kmalloc(sizeof(void *) * + (ARRAY_SIZE(sama7d65_mckx) + ARRAY_SIZE(sama7d65_gck)), + GFP_KERNEL); + if (!alloc_mem) + goto err_free; + + main_rc_hw = at91_clk_register_main_rc_osc(regmap, "main_rc_osc", 12000000, + 50000000); + if (IS_ERR(main_rc_hw)) + goto err_free; + + bypass = of_property_read_bool(np, "atmel,osc-bypass"); + + parent_data.name = main_xtal_name; + parent_data.fw_name = main_xtal_name; + main_osc_hw = at91_clk_register_main_osc(regmap, "main_osc", NULL, + &parent_data, bypass); + if (IS_ERR(main_osc_hw)) + goto err_free; + + parent_hws[0] = main_rc_hw; + parent_hws[1] = main_osc_hw; + hw = at91_clk_register_sam9x5_main(regmap, "mainck", NULL, parent_hws, 2); + if (IS_ERR(hw)) + goto err_free; + + sama7d65_pmc->chws[PMC_MAIN] = hw; + + for (i = 0; i < PLL_ID_MAX; i++) { + for (j = 0; j < PLL_COMPID_MAX; j++) { + struct clk_hw *parent_hw; + + if (!sama7d65_plls[i][j].n) + continue; + + switch (sama7d65_plls[i][j].t) { + case PLL_TYPE_FRAC: + switch (sama7d65_plls[i][j].p) { + case SAMA7D65_PLL_PARENT_MAINCK: + parent_hw = sama7d65_pmc->chws[PMC_MAIN]; + break; + case SAMA7D65_PLL_PARENT_MAIN_XTAL: + parent_hw = main_xtal_hw; + break; + default: + /* Should not happen. */ + parent_hw = NULL; + break; + } + + hw = sam9x60_clk_register_frac_pll(regmap, + &pmc_pll_lock, sama7d65_plls[i][j].n, + NULL, parent_hw, i, + sama7d65_plls[i][j].c, + sama7d65_plls[i][j].l, + sama7d65_plls[i][j].f); + break; + + case PLL_TYPE_DIV: + hw = sam9x60_clk_register_div_pll(regmap, + &pmc_pll_lock, sama7d65_plls[i][j].n, + NULL, sama7d65_plls[i][0].hw, i, + sama7d65_plls[i][j].c, + sama7d65_plls[i][j].l, + sama7d65_plls[i][j].f, + sama7d65_plls[i][j].safe_div); + break; + + default: + continue; + } + + if (IS_ERR(hw)) + goto err_free; + + sama7d65_plls[i][j].hw = hw; + if (sama7d65_plls[i][j].eid) + sama7d65_pmc->chws[sama7d65_plls[i][j].eid] = hw; + } + } + + hw = at91_clk_register_master_div(regmap, "mck0", NULL, + sama7d65_plls[PLL_ID_CPU][1].hw, + &mck0_layout, &mck0_characteristics, + &pmc_mck0_lock, CLK_GET_RATE_NOCACHE, 5); + if (IS_ERR(hw)) + goto err_free; + + sama7d65_pmc->chws[PMC_MCK] = hw; + sama7d65_mckx[PCK_PARENT_HW_MCK0].hw = hw; + + parent_hws[0] = md_slck_hw; + parent_hws[1] = td_slck_hw; + parent_hws[2] = sama7d65_pmc->chws[PMC_MAIN]; + for (i = PCK_PARENT_HW_MCK1; i < ARRAY_SIZE(sama7d65_mckx); i++) { + u8 num_parents = 3 + sama7d65_mckx[i].ep_count; + struct clk_hw *tmp_parent_hws[8]; + u32 *mux_table; + + mux_table = kmalloc_array(num_parents, sizeof(*mux_table), + GFP_KERNEL); + if (!mux_table) + goto err_free; + + alloc_mem[alloc_mem_size++] = mux_table; + + PMC_INIT_TABLE(mux_table, 3); + PMC_FILL_TABLE(&mux_table[3], sama7d65_mckx[i].ep_mux_table, + sama7d65_mckx[i].ep_count); + for (j = 0; j < sama7d65_mckx[i].ep_count; j++) { + u8 pll_id = sama7d65_mckx[i].ep[j].pll_id; + u8 pll_compid = sama7d65_mckx[i].ep[j].pll_compid; + + tmp_parent_hws[j] = sama7d65_plls[pll_id][pll_compid].hw; + } + PMC_FILL_TABLE(&parent_hws[3], tmp_parent_hws, + sama7d65_mckx[i].ep_count); + + hw = at91_clk_sama7g5_register_master(regmap, sama7d65_mckx[i].n, + num_parents, NULL, parent_hws, + mux_table, &pmc_mckX_lock, + sama7d65_mckx[i].id, + sama7d65_mckx[i].c, + sama7d65_mckx[i].ep_chg_id); + + if (IS_ERR(hw)) + goto err_free; + + sama7d65_mckx[i].hw = hw; + if (sama7d65_mckx[i].eid) + sama7d65_pmc->chws[sama7d65_mckx[i].eid] = hw; + } + + parent_names[0] = "syspll_divpmcck"; + parent_names[1] = "usbpll_divpmcck"; + parent_names[2] = "main_osc"; + hw = sam9x60_clk_register_usb(regmap, "usbck", parent_names, 3); + if (IS_ERR(hw)) + goto err_free; + + parent_hws[0] = md_slck_hw; + parent_hws[1] = td_slck_hw; + parent_hws[2] = sama7d65_pmc->chws[PMC_MAIN]; + parent_hws[3] = sama7d65_plls[PLL_ID_SYS][PLL_COMPID_DIV0].hw; + parent_hws[4] = sama7d65_plls[PLL_ID_DDR][PLL_COMPID_DIV0].hw; + parent_hws[5] = sama7d65_plls[PLL_ID_GPU][PLL_COMPID_DIV0].hw; + parent_hws[6] = sama7d65_plls[PLL_ID_BAUD][PLL_COMPID_DIV0].hw; + parent_hws[7] = sama7d65_plls[PLL_ID_AUDIO][PLL_COMPID_DIV0].hw; + parent_hws[8] = sama7d65_plls[PLL_ID_ETH][PLL_COMPID_DIV0].hw; + + for (i = 0; i < 8; i++) { + char name[6]; + + snprintf(name, sizeof(name), "prog%d", i); + + hw = at91_clk_register_programmable(regmap, name, NULL, parent_hws, + 9, i, + &programmable_layout, + sama7d65_prog_mux_table); + if (IS_ERR(hw)) + goto err_free; + + sama7d65_pmc->pchws[i] = hw; + } + + for (i = 0; i < ARRAY_SIZE(sama7d65_systemck); i++) { + hw = at91_clk_register_system(regmap, sama7d65_systemck[i].n, + sama7d65_systemck[i].p, NULL, + sama7d65_systemck[i].id, 0); + if (IS_ERR(hw)) + goto err_free; + + sama7d65_pmc->shws[sama7d65_systemck[i].id] = hw; + } + + for (i = 0; i < ARRAY_SIZE(sama7d65_periphck); i++) { + hw = at91_clk_register_sam9x5_peripheral(regmap, &pmc_pcr_lock, + &sama7d65_pcr_layout, + sama7d65_periphck[i].n, + NULL, + sama7d65_mckx[sama7d65_periphck[i].p].hw, + sama7d65_periphck[i].id, + &sama7d65_periphck[i].r, + sama7d65_periphck[i].chgp ? 0 : + INT_MIN, 0); + if (IS_ERR(hw)) + goto err_free; + + sama7d65_pmc->phws[sama7d65_periphck[i].id] = hw; + } + + parent_hws[0] = md_slck_hw; + parent_hws[1] = td_slck_hw; + parent_hws[2] = sama7d65_pmc->chws[PMC_MAIN]; + parent_hws[3] = sama7d65_pmc->chws[PMC_MCK1]; + for (i = 0; i < ARRAY_SIZE(sama7d65_gck); i++) { + u8 num_parents = 4 + sama7d65_gck[i].pp_count; + struct clk_hw *tmp_parent_hws[8]; + u32 *mux_table; + + mux_table = kmalloc_array(num_parents, sizeof(*mux_table), + GFP_KERNEL); + if (!mux_table) + goto err_free; + + alloc_mem[alloc_mem_size++] = mux_table; + + PMC_INIT_TABLE(mux_table, 4); + PMC_FILL_TABLE(&mux_table[4], sama7d65_gck[i].pp_mux_table, + sama7d65_gck[i].pp_count); + for (j = 0; j < sama7d65_gck[i].pp_count; j++) { + u8 pll_id = sama7d65_gck[i].pp[j].pll_id; + u8 pll_compid = sama7d65_gck[i].pp[j].pll_compid; + + tmp_parent_hws[j] = sama7d65_plls[pll_id][pll_compid].hw; + } + PMC_FILL_TABLE(&parent_hws[4], tmp_parent_hws, + sama7d65_gck[i].pp_count); + + hw = at91_clk_register_generated(regmap, &pmc_pcr_lock, + &sama7d65_pcr_layout, + sama7d65_gck[i].n, NULL, + parent_hws, mux_table, + num_parents, + sama7d65_gck[i].id, + &sama7d65_gck[i].r, + sama7d65_gck[i].pp_chg_id); + if (IS_ERR(hw)) + goto err_free; + + sama7d65_pmc->ghws[sama7d65_gck[i].id] = hw; + } + + of_clk_add_hw_provider(np, of_clk_hw_pmc_get, sama7d65_pmc); + kfree(alloc_mem); + + return; + +err_free: + if (alloc_mem) { + for (i = 0; i < alloc_mem_size; i++) + kfree(alloc_mem[i]); + kfree(alloc_mem); + } + + kfree(sama7d65_pmc); +} + +/* Some clks are used for a clocksource */ +CLK_OF_DECLARE(sama7d65_pmc, "microchip,sama7d65-pmc", sama7d65_pmc_setup); diff --git a/drivers/clk/at91/sckc.c b/drivers/clk/at91/sckc.c index 7741d8f3dbee..021d1b412af4 100644 --- a/drivers/clk/at91/sckc.c +++ b/drivers/clk/at91/sckc.c @@ -12,6 +12,8 @@ #include #include +#include + #define SLOW_CLOCK_FREQ 32768 #define SLOWCK_SW_CYCLES 5 #define SLOWCK_SW_TIME_USEC ((SLOWCK_SW_CYCLES * USEC_PER_SEC) / \ @@ -470,7 +472,7 @@ static void __init of_sam9x60_sckc_setup(struct device_node *np) { void __iomem *regbase = of_iomap(np, 0); struct clk_hw_onecell_data *clk_data; - struct clk_hw *slow_rc, *slow_osc; + struct clk_hw *slow_rc, *slow_osc, *hw; const char *xtal_name; const struct clk_hw *parent_hws[2]; static struct clk_parent_data parent_data = { @@ -506,19 +508,19 @@ static void __init of_sam9x60_sckc_setup(struct device_node *np) /* MD_SLCK and TD_SLCK. */ clk_data->num = 2; - clk_data->hws[0] = clk_hw_register_fixed_rate_parent_hw(NULL, "md_slck", - slow_rc, - 0, 32768); - if (IS_ERR(clk_data->hws[0])) + hw = clk_hw_register_fixed_rate_parent_hw(NULL, "md_slck", slow_rc, + 0, 32768); + if (IS_ERR(hw)) goto clk_data_free; + clk_data->hws[SCKC_MD_SLCK] = hw; parent_hws[0] = slow_rc; parent_hws[1] = slow_osc; - clk_data->hws[1] = at91_clk_register_sam9x5_slow(regbase, "td_slck", - parent_hws, 2, - &at91sam9x60_bits); - if (IS_ERR(clk_data->hws[1])) + hw = at91_clk_register_sam9x5_slow(regbase, "td_slck", parent_hws, + 2, &at91sam9x60_bits); + if (IS_ERR(hw)) goto unregister_md_slck; + clk_data->hws[SCKC_TD_SLCK] = hw; ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data); if (WARN_ON(ret)) @@ -527,9 +529,9 @@ static void __init of_sam9x60_sckc_setup(struct device_node *np) return; unregister_td_slck: - at91_clk_unregister_sam9x5_slow(clk_data->hws[1]); + at91_clk_unregister_sam9x5_slow(clk_data->hws[SCKC_TD_SLCK]); unregister_md_slck: - clk_hw_unregister(clk_data->hws[0]); + clk_hw_unregister(clk_data->hws[SCKC_MD_SLCK]); clk_data_free: kfree(clk_data); unregister_slow_osc: diff --git a/drivers/clk/bcm/clk-kona.c b/drivers/clk/bcm/clk-kona.c index ec5749e301ba..2b0ea882f1e4 100644 --- a/drivers/clk/bcm/clk-kona.c +++ b/drivers/clk/bcm/clk-kona.c @@ -10,6 +10,7 @@ #include #include #include +#include /* * "Policies" affect the frequencies of bus clocks provided by a @@ -502,7 +503,7 @@ static int clk_gate(struct ccu_data *ccu, const char *name, return 0; pr_err("%s: failed to %s gate for %s\n", __func__, - enable ? "enable" : "disable", name); + str_enable_disable(enable), name); return -EIO; } diff --git a/drivers/clk/bcm/clk-raspberrypi.c b/drivers/clk/bcm/clk-raspberrypi.c index a18a8768feb4..0e1fe3759530 100644 --- a/drivers/clk/bcm/clk-raspberrypi.c +++ b/drivers/clk/bcm/clk-raspberrypi.c @@ -34,6 +34,7 @@ static char *rpi_firmware_clk_names[] = { [RPI_FIRMWARE_M2MC_CLK_ID] = "m2mc", [RPI_FIRMWARE_PIXEL_BVB_CLK_ID] = "pixel-bvb", [RPI_FIRMWARE_VEC_CLK_ID] = "vec", + [RPI_FIRMWARE_DISP_CLK_ID] = "disp", }; #define RPI_FIRMWARE_STATE_ENABLE_BIT BIT(0) @@ -56,6 +57,12 @@ struct raspberrypi_clk_data { struct raspberrypi_clk *rpi; }; +static inline +const struct raspberrypi_clk_data *clk_hw_to_data(const struct clk_hw *hw) +{ + return container_of(hw, struct raspberrypi_clk_data, hw); +} + struct raspberrypi_clk_variant { bool export; char *clkdev; @@ -111,18 +118,31 @@ raspberrypi_clk_variants[RPI_FIRMWARE_NUM_CLK_ID] = { }, [RPI_FIRMWARE_V3D_CLK_ID] = { .export = true, + .minimize = true, }, [RPI_FIRMWARE_PIXEL_CLK_ID] = { .export = true, + .minimize = true, }, [RPI_FIRMWARE_HEVC_CLK_ID] = { .export = true, + .minimize = true, + }, + [RPI_FIRMWARE_ISP_CLK_ID] = { + .export = true, + .minimize = true, }, [RPI_FIRMWARE_PIXEL_BVB_CLK_ID] = { .export = true, + .minimize = true, }, [RPI_FIRMWARE_VEC_CLK_ID] = { .export = true, + .minimize = true, + }, + [RPI_FIRMWARE_DISP_CLK_ID] = { + .export = true, + .minimize = true, }, }; @@ -153,7 +173,6 @@ static int raspberrypi_clock_property(struct rpi_firmware *firmware, struct raspberrypi_firmware_prop msg = { .id = cpu_to_le32(data->id), .val = cpu_to_le32(*val), - .disable_turbo = cpu_to_le32(1), }; int ret; @@ -168,8 +187,7 @@ static int raspberrypi_clock_property(struct rpi_firmware *firmware, static int raspberrypi_fw_is_prepared(struct clk_hw *hw) { - struct raspberrypi_clk_data *data = - container_of(hw, struct raspberrypi_clk_data, hw); + const struct raspberrypi_clk_data *data = clk_hw_to_data(hw); struct raspberrypi_clk *rpi = data->rpi; u32 val = 0; int ret; @@ -186,8 +204,7 @@ static int raspberrypi_fw_is_prepared(struct clk_hw *hw) static unsigned long raspberrypi_fw_get_rate(struct clk_hw *hw, unsigned long parent_rate) { - struct raspberrypi_clk_data *data = - container_of(hw, struct raspberrypi_clk_data, hw); + const struct raspberrypi_clk_data *data = clk_hw_to_data(hw); struct raspberrypi_clk *rpi = data->rpi; u32 val = 0; int ret; @@ -203,8 +220,7 @@ static unsigned long raspberrypi_fw_get_rate(struct clk_hw *hw, static int raspberrypi_fw_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { - struct raspberrypi_clk_data *data = - container_of(hw, struct raspberrypi_clk_data, hw); + const struct raspberrypi_clk_data *data = clk_hw_to_data(hw); struct raspberrypi_clk *rpi = data->rpi; u32 _rate = rate; int ret; @@ -221,8 +237,7 @@ static int raspberrypi_fw_set_rate(struct clk_hw *hw, unsigned long rate, static int raspberrypi_fw_dumb_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { - struct raspberrypi_clk_data *data = - container_of(hw, struct raspberrypi_clk_data, hw); + const struct raspberrypi_clk_data *data = clk_hw_to_data(hw); struct raspberrypi_clk_variant *variant = data->variant; /* diff --git a/drivers/clk/clk-en7523.c b/drivers/clk/clk-en7523.c index 495c0d607c7d..15bbdeb60b8e 100644 --- a/drivers/clk/clk-en7523.c +++ b/drivers/clk/clk-en7523.c @@ -75,6 +75,7 @@ struct en_rst_data { }; struct en_clk_soc_data { + u32 num_clocks; const struct clk_ops pcie_ops; int (*hw_init)(struct platform_device *pdev, struct clk_hw_onecell_data *clk_data); @@ -90,6 +91,7 @@ static const u32 emi7581_base[] = { 540000000, 480000000, 400000000, 300000000 } static const u32 bus7581_base[] = { 600000000, 540000000 }; static const u32 npu7581_base[] = { 800000000, 750000000, 720000000, 600000000 }; static const u32 crypto_base[] = { 540000000, 480000000 }; +static const u32 emmc7581_base[] = { 200000000, 150000000 }; static const struct en_clk_desc en7523_base_clks[] = { { @@ -280,6 +282,15 @@ static const struct en_clk_desc en7581_base_clks[] = { .base_shift = 0, .base_values = crypto_base, .n_base_values = ARRAY_SIZE(crypto_base), + }, { + .id = EN7581_CLK_EMMC, + .name = "emmc", + + .base_reg = REG_CRYPTO_CLKSRC2, + .base_bits = 1, + .base_shift = 12, + .base_values = emmc7581_base, + .n_base_values = ARRAY_SIZE(emmc7581_base), } }; @@ -478,7 +489,6 @@ static int en7581_pci_enable(struct clk_hw *hw) REG_PCI_CONTROL_PERSTOUT; val = readl(np_base + REG_PCI_CONTROL); writel(val | mask, np_base + REG_PCI_CONTROL); - msleep(250); return 0; } @@ -504,8 +514,6 @@ static void en7523_register_clocks(struct device *dev, struct clk_hw_onecell_dat u32 rate; int i; - clk_data->num = EN7523_NUM_CLOCKS; - for (i = 0; i < ARRAY_SIZE(en7523_base_clks); i++) { const struct en_clk_desc *desc = &en7523_base_clks[i]; u32 reg = desc->div_reg ? desc->div_reg : desc->base_reg; @@ -587,8 +595,6 @@ static void en7581_register_clocks(struct device *dev, struct clk_hw_onecell_dat hw = en7523_register_pcie_clk(dev, base); clk_data->hws[EN7523_CLK_PCIE] = hw; - - clk_data->num = EN7523_NUM_CLOCKS; } static int en7523_reset_update(struct reset_controller_dev *rcdev, @@ -702,13 +708,15 @@ static int en7523_clk_probe(struct platform_device *pdev) struct clk_hw_onecell_data *clk_data; int r; + soc_data = device_get_match_data(&pdev->dev); + clk_data = devm_kzalloc(&pdev->dev, - struct_size(clk_data, hws, EN7523_NUM_CLOCKS), + struct_size(clk_data, hws, soc_data->num_clocks), GFP_KERNEL); if (!clk_data) return -ENOMEM; - soc_data = device_get_match_data(&pdev->dev); + clk_data->num = soc_data->num_clocks; r = soc_data->hw_init(pdev, clk_data); if (r) return r; @@ -717,6 +725,7 @@ static int en7523_clk_probe(struct platform_device *pdev) } static const struct en_clk_soc_data en7523_data = { + .num_clocks = ARRAY_SIZE(en7523_base_clks) + 1, .pcie_ops = { .is_enabled = en7523_pci_is_enabled, .prepare = en7523_pci_prepare, @@ -726,6 +735,8 @@ static const struct en_clk_soc_data en7523_data = { }; static const struct en_clk_soc_data en7581_data = { + /* We increment num_clocks by 1 to account for additional PCIe clock */ + .num_clocks = ARRAY_SIZE(en7581_base_clks) + 1, .pcie_ops = { .is_enabled = en7581_pci_is_enabled, .enable = en7581_pci_enable, diff --git a/drivers/clk/clk-ep93xx.c b/drivers/clk/clk-ep93xx.c index f888aed79b11..4bd8d6ecf6a2 100644 --- a/drivers/clk/clk-ep93xx.c +++ b/drivers/clk/clk-ep93xx.c @@ -586,9 +586,9 @@ static unsigned long calc_pll_rate(u64 rate, u32 config_word) static int ep93xx_plls_init(struct ep93xx_clk_priv *priv) { - const char fclk_divisors[] = { 1, 2, 4, 8, 16, 1, 1, 1 }; - const char hclk_divisors[] = { 1, 2, 4, 5, 6, 8, 16, 32 }; - const char pclk_divisors[] = { 1, 2, 4, 8 }; + static const char fclk_divisors[] = { 1, 2, 4, 8, 16, 1, 1, 1 }; + static const char hclk_divisors[] = { 1, 2, 4, 5, 6, 8, 16, 32 }; + static const char pclk_divisors[] = { 1, 2, 4, 8 }; struct clk_parent_data xtali = { .index = 0 }; unsigned int clk_f_div, clk_h_div, clk_p_div; unsigned long clk_pll1_rate, clk_pll2_rate; diff --git a/drivers/clk/clk-lmk04832.c b/drivers/clk/clk-lmk04832.c index c997e7491996..2bcf422f0b04 100644 --- a/drivers/clk/clk-lmk04832.c +++ b/drivers/clk/clk-lmk04832.c @@ -375,7 +375,7 @@ static unsigned long lmk04832_vco_recalc_rate(struct clk_hw *hw, unsigned long prate) { struct lmk04832 *lmk = container_of(hw, struct lmk04832, vco); - const unsigned int pll2_p[] = {8, 2, 2, 3, 4, 5, 6, 7}; + static const unsigned int pll2_p[] = {8, 2, 2, 3, 4, 5, 6, 7}; unsigned int pll2_n, p, pll2_r; unsigned int pll2_misc; unsigned long vco_rate; @@ -637,7 +637,7 @@ static int lmk04832_register_vco(struct lmk04832 *lmk) static int lmk04832_clkout_set_ddly(struct lmk04832 *lmk, int id) { - const int dclk_div_adj[] = {0, 0, -2, -2, 0, 3, -1, 0}; + static const int dclk_div_adj[] = {0, 0, -2, -2, 0, 3, -1, 0}; unsigned int sclkx_y_ddly = 10; unsigned int dclkx_y_ddly; unsigned int dclkx_y_div; diff --git a/drivers/clk/clk-loongson2.c b/drivers/clk/clk-loongson2.c index 7082b4309c6f..27e632edd484 100644 --- a/drivers/clk/clk-loongson2.c +++ b/drivers/clk/clk-loongson2.c @@ -294,7 +294,7 @@ static int loongson2_clk_probe(struct platform_device *pdev) return -EINVAL; for (p = data; p->name; p++) - clks_num++; + clks_num = max(clks_num, p->id + 1); clp = devm_kzalloc(dev, struct_size(clp, clk_data.hws, clks_num), GFP_KERNEL); @@ -309,6 +309,9 @@ static int loongson2_clk_probe(struct platform_device *pdev) clp->clk_data.num = clks_num; clp->dev = dev; + /* Avoid returning NULL for unused id */ + memset_p((void **)clp->clk_data.hws, ERR_PTR(-ENOENT), clks_num); + for (i = 0; i < clks_num; i++) { p = &data[i]; switch (p->type) { @@ -335,8 +338,8 @@ static int loongson2_clk_probe(struct platform_device *pdev) &clp->clk_lock); break; case CLK_TYPE_FIXED: - hw = clk_hw_register_fixed_rate_parent_data(dev, p->name, pdata, - 0, p->fixed_rate); + hw = devm_clk_hw_register_fixed_rate_parent_data(dev, p->name, pdata, + 0, p->fixed_rate); break; default: return dev_err_probe(dev, -EINVAL, "Invalid clk type\n"); diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c index 06245681dac7..fc0aeb4247f2 100644 --- a/drivers/clk/clk-nomadik.c +++ b/drivers/clk/clk-nomadik.c @@ -17,6 +17,7 @@ #include #include #include +#include #include /* @@ -116,9 +117,9 @@ static void __init nomadik_src_init(void) val = readl(src_base + SRC_XTALCR); pr_info("SXTALO is %s\n", - (val & SRC_XTALCR_SXTALDIS) ? "disabled" : "enabled"); + str_disabled_enabled(val & SRC_XTALCR_SXTALDIS)); pr_info("MXTAL is %s\n", - (val & SRC_XTALCR_MXTALSTAT) ? "enabled" : "disabled"); + str_enabled_disabled(val & SRC_XTALCR_MXTALSTAT)); if (of_property_read_bool(np, "disable-sxtalo")) { /* The machine uses an external oscillator circuit */ val |= SRC_XTALCR_SXTALDIS; diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c index 07c13ebe327d..f476883bc93b 100644 --- a/drivers/clk/clk-stm32f4.c +++ b/drivers/clk/clk-stm32f4.c @@ -5,6 +5,7 @@ * Inspired by clk-asm9260.c . */ +#include #include #include #include @@ -34,11 +35,20 @@ #define STM32F4_RCC_APB2ENR 0x44 #define STM32F4_RCC_BDCR 0x70 #define STM32F4_RCC_CSR 0x74 +#define STM32F4_RCC_SSCGR 0x80 #define STM32F4_RCC_PLLI2SCFGR 0x84 #define STM32F4_RCC_PLLSAICFGR 0x88 #define STM32F4_RCC_DCKCFGR 0x8c #define STM32F7_RCC_DCKCFGR2 0x90 +#define STM32F4_RCC_PLLCFGR_N_MASK GENMASK(14, 6) + +#define STM32F4_RCC_SSCGR_SSCGEN BIT(31) +#define STM32F4_RCC_SSCGR_SPREADSEL BIT(30) +#define STM32F4_RCC_SSCGR_RESERVED_MASK GENMASK(29, 28) +#define STM32F4_RCC_SSCGR_INCSTEP_MASK GENMASK(27, 13) +#define STM32F4_RCC_SSCGR_MODPER_MASK GENMASK(12, 0) + #define NONE -1 #define NO_IDX NONE #define NO_MUX NONE @@ -364,6 +374,16 @@ static const struct stm32f4_gate_data stm32f769_gates[] __initconst = { { STM32F4_RCC_APB2ENR, 30, "mdio", "apb2_div" }, }; +enum stm32f4_pll_ssc_mod_type { + STM32F4_PLL_SSC_CENTER_SPREAD, + STM32F4_PLL_SSC_DOWN_SPREAD, +}; + +static const char * const stm32f4_ssc_mod_methods[] __initconst = { + [STM32F4_PLL_SSC_DOWN_SPREAD] = "down-spread", + [STM32F4_PLL_SSC_CENTER_SPREAD] = "center-spread", +}; + /* * This bitmask tells us which bit offsets (0..192) on STM32F4[23]xxx * have gate bits associated with them. Its combined hweight is 71. @@ -509,6 +529,12 @@ static const struct clk_div_table pll_divr_table[] = { { 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 }, { 7, 7 }, { 0 } }; +struct stm32f4_pll_ssc { + unsigned int mod_freq; + unsigned int mod_depth; + enum stm32f4_pll_ssc_mod_type mod_type; +}; + struct stm32f4_pll { spinlock_t *lock; struct clk_gate gate; @@ -516,6 +542,8 @@ struct stm32f4_pll { u8 bit_rdy_idx; u8 status; u8 n_start; + bool ssc_enable; + struct stm32f4_pll_ssc ssc_conf; }; #define to_stm32f4_pll(_gate) container_of(_gate, struct stm32f4_pll, gate) @@ -538,6 +566,7 @@ struct stm32f4_vco_data { u8 offset; u8 bit_idx; u8 bit_rdy_idx; + bool sscg; }; static const struct stm32f4_vco_data vco_data[] = { @@ -632,9 +661,11 @@ static unsigned long stm32f4_pll_recalc(struct clk_hw *hw, { struct clk_gate *gate = to_clk_gate(hw); struct stm32f4_pll *pll = to_stm32f4_pll(gate); + unsigned long val; unsigned long n; - n = (readl(base + pll->offset) >> 6) & 0x1ff; + val = readl(base + pll->offset); + n = FIELD_GET(STM32F4_RCC_PLLCFGR_N_MASK, val); return parent_rate * n; } @@ -656,6 +687,32 @@ static long stm32f4_pll_round_rate(struct clk_hw *hw, unsigned long rate, return *prate * n; } +static void stm32f4_pll_set_ssc(struct clk_hw *hw, unsigned long parent_rate, + unsigned int ndiv) +{ + struct clk_gate *gate = to_clk_gate(hw); + struct stm32f4_pll *pll = to_stm32f4_pll(gate); + struct stm32f4_pll_ssc *ssc = &pll->ssc_conf; + u32 modeper, incstep; + u32 sscgr; + + sscgr = readl(base + STM32F4_RCC_SSCGR); + /* reserved field must be kept at reset value */ + sscgr &= STM32F4_RCC_SSCGR_RESERVED_MASK; + + modeper = DIV_ROUND_CLOSEST(parent_rate, 4 * ssc->mod_freq); + incstep = DIV_ROUND_CLOSEST(((1 << 15) - 1) * ssc->mod_depth * ndiv, + 5 * 10000 * modeper); + sscgr |= STM32F4_RCC_SSCGR_SSCGEN | + FIELD_PREP(STM32F4_RCC_SSCGR_INCSTEP_MASK, incstep) | + FIELD_PREP(STM32F4_RCC_SSCGR_MODPER_MASK, modeper); + + if (ssc->mod_type) + sscgr |= STM32F4_RCC_SSCGR_SPREADSEL; + + writel(sscgr, base + STM32F4_RCC_SSCGR); +} + static int stm32f4_pll_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { @@ -673,9 +730,13 @@ static int stm32f4_pll_set_rate(struct clk_hw *hw, unsigned long rate, n = rate / parent_rate; - val = readl(base + pll->offset) & ~(0x1ff << 6); + val = readl(base + pll->offset) & ~STM32F4_RCC_PLLCFGR_N_MASK; + val |= FIELD_PREP(STM32F4_RCC_PLLCFGR_N_MASK, n); - writel(val | ((n & 0x1ff) << 6), base + pll->offset); + writel(val, base + pll->offset); + + if (pll->ssc_enable) + stm32f4_pll_set_ssc(hw, parent_rate, n); if (pll_state) stm32f4_pll_enable(hw); @@ -782,6 +843,84 @@ static struct clk_hw *clk_register_pll_div(const char *name, return hw; } +static int __init stm32f4_pll_init_ssc(struct clk_hw *hw, + const struct stm32f4_pll_ssc *conf) +{ + struct clk_gate *gate = to_clk_gate(hw); + struct stm32f4_pll *pll = to_stm32f4_pll(gate); + struct clk_hw *parent; + unsigned long parent_rate; + int pll_state; + unsigned long n, val; + + parent = clk_hw_get_parent(hw); + if (!parent) { + pr_err("%s: failed to get clock parent\n", __func__); + return -ENODEV; + } + + parent_rate = clk_hw_get_rate(parent); + + pll->ssc_enable = true; + memcpy(&pll->ssc_conf, conf, sizeof(pll->ssc_conf)); + + pll_state = stm32f4_pll_is_enabled(hw); + + if (pll_state) + stm32f4_pll_disable(hw); + + val = readl(base + pll->offset); + n = FIELD_GET(STM32F4_RCC_PLLCFGR_N_MASK, val); + + pr_debug("%s: pll: %s, parent: %s, parent-rate: %lu, n: %lu\n", + __func__, clk_hw_get_name(hw), clk_hw_get_name(parent), + parent_rate, n); + + stm32f4_pll_set_ssc(hw, parent_rate, n); + + if (pll_state) + stm32f4_pll_enable(hw); + + return 0; +} + +static int __init stm32f4_pll_ssc_parse_dt(struct device_node *np, + struct stm32f4_pll_ssc *conf) +{ + int ret; + const char *s; + + if (!conf) + return -EINVAL; + + ret = of_property_read_u32(np, "st,ssc-modfreq-hz", &conf->mod_freq); + if (ret) + return ret; + + ret = of_property_read_u32(np, "st,ssc-moddepth-permyriad", + &conf->mod_depth); + if (ret) { + pr_err("%pOF: missing st,ssc-moddepth-permyriad\n", np); + return ret; + } + + ret = fwnode_property_match_property_string(of_fwnode_handle(np), + "st,ssc-modmethod", + stm32f4_ssc_mod_methods, + ARRAY_SIZE(stm32f4_ssc_mod_methods)); + if (ret < 0) { + pr_err("%pOF: failed to get st,ssc-modmethod\n", np); + return ret; + } + + conf->mod_type = ret; + + pr_debug("%pOF: SSCG settings: mod_freq: %d, mod_depth: %d mod_method: %s [%d]\n", + np, conf->mod_freq, conf->mod_depth, s, conf->mod_type); + + return 0; +} + static struct clk_hw *stm32f4_rcc_register_pll(const char *pllsrc, const struct stm32f4_pll_data *data, spinlock_t *lock) { @@ -1689,7 +1828,8 @@ static void __init stm32f4_rcc_init(struct device_node *np) const struct of_device_id *match; const struct stm32f4_clk_data *data; unsigned long pllm; - struct clk_hw *pll_src_hw; + struct clk_hw *pll_src_hw, *pll_vco_hw; + struct stm32f4_pll_ssc ssc_conf; base = of_iomap(np, 0); if (!base) { @@ -1748,8 +1888,8 @@ static void __init stm32f4_rcc_init(struct device_node *np) clk_hw_register_fixed_factor(NULL, "vco_in", pll_src, 0, 1, pllm); - stm32f4_rcc_register_pll("vco_in", &data->pll_data[0], - &stm32f4_clk_lock); + pll_vco_hw = stm32f4_rcc_register_pll("vco_in", &data->pll_data[0], + &stm32f4_clk_lock); clks[PLL_VCO_I2S] = stm32f4_rcc_register_pll("vco_in", &data->pll_data[1], &stm32f4_clk_lock); @@ -1894,6 +2034,9 @@ static void __init stm32f4_rcc_init(struct device_node *np) of_clk_add_hw_provider(np, stm32f4_rcc_lookup_clk, NULL); + if (!stm32f4_pll_ssc_parse_dt(np, &ssc_conf)) + stm32f4_pll_init_ssc(pll_vco_hw, &ssc_conf); + return; fail: kfree(clks); diff --git a/drivers/clk/clk-versaclock3.c b/drivers/clk/clk-versaclock3.c index 76d7ea1964c3..9fe27dace111 100644 --- a/drivers/clk/clk-versaclock3.c +++ b/drivers/clk/clk-versaclock3.c @@ -78,9 +78,6 @@ #define VC3_PLL1_VCO_MIN 300000000UL #define VC3_PLL1_VCO_MAX 600000000UL -#define VC3_PLL2_VCO_MIN 400000000UL -#define VC3_PLL2_VCO_MAX 1200000000UL - #define VC3_PLL3_VCO_MIN 300000000UL #define VC3_PLL3_VCO_MAX 800000000UL @@ -147,9 +144,13 @@ struct vc3_pfd_data { u8 mdiv2_bitmsk; }; +struct vc3_vco { + unsigned long min; + unsigned long max; +}; + struct vc3_pll_data { - unsigned long vco_min; - unsigned long vco_max; + struct vc3_vco vco; u8 num; u8 int_div_msb_offs; u8 int_div_lsb_offs; @@ -166,12 +167,17 @@ struct vc3_div_data { struct vc3_hw_data { struct clk_hw hw; struct regmap *regmap; - const void *data; + void *data; u32 div_int; u32 div_frc; }; +struct vc3_hw_cfg { + struct vc3_vco pll2_vco; + u32 se2_clk_sel_msk; +}; + static const struct clk_div_table div1_divs[] = { { .val = 0, .div = 1, }, { .val = 1, .div = 4, }, { .val = 2, .div = 5, }, { .val = 3, .div = 6, }, @@ -386,10 +392,10 @@ static long vc3_pll_round_rate(struct clk_hw *hw, unsigned long rate, const struct vc3_pll_data *pll = vc3->data; u64 div_frc; - if (rate < pll->vco_min) - rate = pll->vco_min; - if (rate > pll->vco_max) - rate = pll->vco_max; + if (rate < pll->vco.min) + rate = pll->vco.min; + if (rate > pll->vco.max) + rate = pll->vco.max; vc3->div_int = rate / *parent_rate; @@ -680,8 +686,10 @@ static struct vc3_hw_data clk_pll[] = { .num = VC3_PLL1, .int_div_msb_offs = VC3_PLL1_LOOP_FILTER_N_DIV_MSB, .int_div_lsb_offs = VC3_PLL1_VCO_N_DIVIDER, - .vco_min = VC3_PLL1_VCO_MIN, - .vco_max = VC3_PLL1_VCO_MAX + .vco = { + .min = VC3_PLL1_VCO_MIN, + .max = VC3_PLL1_VCO_MAX + } }, .hw.init = &(struct clk_init_data) { .name = "pll1", @@ -698,8 +706,6 @@ static struct vc3_hw_data clk_pll[] = { .num = VC3_PLL2, .int_div_msb_offs = VC3_PLL2_FB_INT_DIV_MSB, .int_div_lsb_offs = VC3_PLL2_FB_INT_DIV_LSB, - .vco_min = VC3_PLL2_VCO_MIN, - .vco_max = VC3_PLL2_VCO_MAX }, .hw.init = &(struct clk_init_data) { .name = "pll2", @@ -716,8 +722,10 @@ static struct vc3_hw_data clk_pll[] = { .num = VC3_PLL3, .int_div_msb_offs = VC3_PLL3_LOOP_FILTER_N_DIV_MSB, .int_div_lsb_offs = VC3_PLL3_N_DIVIDER, - .vco_min = VC3_PLL3_VCO_MIN, - .vco_max = VC3_PLL3_VCO_MAX + .vco = { + .min = VC3_PLL3_VCO_MIN, + .max = VC3_PLL3_VCO_MAX + } }, .hw.init = &(struct clk_init_data) { .name = "pll3", @@ -901,7 +909,6 @@ static struct vc3_hw_data clk_mux[] = { [VC3_SE2_MUX] = { .data = &(struct vc3_clk_data) { .offs = VC3_SE2_CTRL_REG0, - .bitmsk = VC3_SE2_CTRL_REG0_SE2_CLK_SEL }, .hw.init = &(struct clk_init_data) { .name = "se2_mux", @@ -982,6 +989,7 @@ static int vc3_probe(struct i2c_client *client) { struct device *dev = &client->dev; u8 settings[NUM_CONFIG_REGISTERS]; + const struct vc3_hw_cfg *data; struct regmap *regmap; const char *name; int ret, i; @@ -1029,9 +1037,16 @@ static int vc3_probe(struct i2c_client *client) clk_pfd[i].hw.init->name); } + data = i2c_get_match_data(client); + /* Register pll's */ for (i = 0; i < ARRAY_SIZE(clk_pll); i++) { clk_pll[i].regmap = regmap; + if (i == VC3_PLL2) { + struct vc3_pll_data *pll_data = clk_pll[i].data; + + pll_data->vco = data->pll2_vco; + } ret = devm_clk_hw_register(dev, &clk_pll[i].hw); if (ret) return dev_err_probe(dev, ret, "%s failed\n", @@ -1059,6 +1074,11 @@ static int vc3_probe(struct i2c_client *client) /* Register clk muxes */ for (i = 0; i < ARRAY_SIZE(clk_mux); i++) { clk_mux[i].regmap = regmap; + if (i == VC3_SE2_MUX) { + struct vc3_clk_data *clk_data = clk_mux[i].data; + + clk_data->bitmsk = data->se2_clk_sel_msk; + } ret = devm_clk_hw_register(dev, &clk_mux[i].hw); if (ret) return dev_err_probe(dev, ret, "%s failed\n", @@ -1108,8 +1128,19 @@ static int vc3_probe(struct i2c_client *client) return ret; } +static const struct vc3_hw_cfg vc3_5p = { + .pll2_vco = { .min = 400000000UL, .max = 1200000000UL }, + .se2_clk_sel_msk = BIT(6), +}; + +static const struct vc3_hw_cfg vc3_5l = { + .pll2_vco = { .min = 30000000UL, .max = 130000000UL }, + .se2_clk_sel_msk = BIT(0), +}; + static const struct of_device_id dev_ids[] = { - { .compatible = "renesas,5p35023" }, + { .compatible = "renesas,5p35023", .data = &vc3_5p }, + { .compatible = "renesas,5l35023", .data = &vc3_5l }, { /* Sentinel */ } }; MODULE_DEVICE_TABLE(of, dev_ids); diff --git a/drivers/clk/clk-xgene.c b/drivers/clk/clk-xgene.c index 0c3d0cee98c8..96946a8e2854 100644 --- a/drivers/clk/clk-xgene.c +++ b/drivers/clk/clk-xgene.c @@ -7,6 +7,7 @@ */ #include #include +#include #include #include #include @@ -520,8 +521,7 @@ static int xgene_clk_is_enabled(struct clk_hw *hw) data = xgene_clk_read(pclk->param.csr_reg + pclk->param.reg_clk_offset); pr_debug("%s clock is %s\n", clk_hw_get_name(hw), - data & pclk->param.reg_clk_mask ? "enabled" : - "disabled"); + str_enabled_disabled(data & pclk->param.reg_clk_mask)); } else { return 1; } diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 9b45fa005030..cf7720b9172f 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -5385,8 +5385,10 @@ const char *of_clk_get_parent_name(const struct device_node *np, int index) count++; } /* We went off the end of 'clock-indices' without finding it */ - if (of_property_present(clkspec.np, "clock-indices") && !found) + if (of_property_present(clkspec.np, "clock-indices") && !found) { + of_node_put(clkspec.np); return NULL; + } if (of_property_read_string_index(clkspec.np, "clock-output-names", index, diff --git a/drivers/clk/davinci/pll.c b/drivers/clk/davinci/pll.c index 5bbbb3a66477..82727b1fc67a 100644 --- a/drivers/clk/davinci/pll.c +++ b/drivers/clk/davinci/pll.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -840,27 +839,6 @@ int of_davinci_pll_init(struct device *dev, struct device_node *node, return 0; } -static struct davinci_pll_platform_data *davinci_pll_get_pdata(struct device *dev) -{ - struct davinci_pll_platform_data *pdata = dev_get_platdata(dev); - - /* - * Platform data is optional, so allocate a new struct if one was not - * provided. For device tree, this will always be the case. - */ - if (!pdata) - pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) - return NULL; - - /* for device tree, we need to fill in the struct */ - if (dev->of_node) - pdata->cfgchip = - syscon_regmap_lookup_by_compatible("ti,da830-cfgchip"); - - return pdata; -} - /* needed in early boot for clocksource/clockevent */ #ifdef CONFIG_ARCH_DAVINCI_DA850 CLK_OF_DECLARE(da850_pll0, "ti,da850-pll0", of_da850_pll0_init); @@ -890,8 +868,8 @@ typedef int (*davinci_pll_init)(struct device *dev, void __iomem *base, static int davinci_pll_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct davinci_pll_platform_data *pdata; davinci_pll_init pll_init = NULL; + struct regmap *cfgchip; void __iomem *base; pll_init = device_get_match_data(dev); @@ -903,17 +881,13 @@ static int davinci_pll_probe(struct platform_device *pdev) return -EINVAL; } - pdata = davinci_pll_get_pdata(dev); - if (!pdata) { - dev_err(dev, "missing platform data\n"); - return -EINVAL; - } + cfgchip = syscon_regmap_lookup_by_compatible("ti,da830-cfgchip"); base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) return PTR_ERR(base); - return pll_init(dev, base, pdata->cfgchip); + return pll_init(dev, base, cfgchip); } static struct platform_driver davinci_pll_driver = { diff --git a/drivers/clk/imx/clk-imx8mp-audiomix.c b/drivers/clk/imx/clk-imx8mp-audiomix.c index b2cb157703c5..c409fc7e0618 100644 --- a/drivers/clk/imx/clk-imx8mp-audiomix.c +++ b/drivers/clk/imx/clk-imx8mp-audiomix.c @@ -278,7 +278,8 @@ static int clk_imx8mp_audiomix_reset_controller_register(struct device *dev, #else /* !CONFIG_RESET_CONTROLLER */ -static int clk_imx8mp_audiomix_reset_controller_register(struct clk_imx8mp_audiomix_priv *priv) +static int clk_imx8mp_audiomix_reset_controller_register(struct device *dev, + struct clk_imx8mp_audiomix_priv *priv) { return 0; } diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 516dbd170c8a..fb18f507f121 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -399,8 +399,9 @@ static const char * const imx8mp_dram_core_sels[] = {"dram_pll_out", "dram_alt_r static const char * const imx8mp_clkout_sels[] = {"audio_pll1_out", "audio_pll2_out", "video_pll1_out", "dummy", "dummy", "gpu_pll_out", "vpu_pll_out", - "arm_pll_out", "sys_pll1", "sys_pll2", "sys_pll3", - "dummy", "dummy", "osc_24m", "dummy", "osc_32k"}; + "arm_pll_out", "sys_pll1_out", "sys_pll2_out", + "sys_pll3_out", "dummy", "dummy", "osc_24m", + "dummy", "osc_32k"}; static struct clk_hw **hws; static struct clk_hw_onecell_data *clk_hw_data; diff --git a/drivers/clk/imx/clk-imx93.c b/drivers/clk/imx/clk-imx93.c index 58a516dd385b..c5f358a75f30 100644 --- a/drivers/clk/imx/clk-imx93.c +++ b/drivers/clk/imx/clk-imx93.c @@ -15,7 +15,7 @@ #include "clk.h" -#define IMX93_CLK_END 207 +#define IMX93_CLK_END 208 #define PLAT_IMX93 BIT(0) #define PLAT_IMX91 BIT(1) @@ -38,6 +38,7 @@ static u32 share_count_sai2; static u32 share_count_sai3; static u32 share_count_mub; static u32 share_count_pdm; +static u32 share_count_spdif; static const char * const a55_core_sels[] = {"a55_alt", "arm_pll"}; static const char *parent_names[MAX_SEL][4] = { @@ -70,8 +71,8 @@ static const struct imx93_clk_root { { IMX93_CLK_WAKEUP_AXI, "wakeup_axi_root", 0x0380, FAST_SEL, CLK_IS_CRITICAL }, { IMX93_CLK_SWO_TRACE, "swo_trace_root", 0x0400, LOW_SPEED_IO_SEL, }, { IMX93_CLK_M33_SYSTICK, "m33_systick_root", 0x0480, LOW_SPEED_IO_SEL, 0, PLAT_IMX93, }, - { IMX93_CLK_FLEXIO1, "flexio1_root", 0x0500, LOW_SPEED_IO_SEL, }, - { IMX93_CLK_FLEXIO2, "flexio2_root", 0x0580, LOW_SPEED_IO_SEL, }, + { IMX93_CLK_FLEXIO1, "flexio1_root", 0x0500, LOW_SPEED_IO_SEL, 0, PLAT_IMX93, }, + { IMX93_CLK_FLEXIO2, "flexio2_root", 0x0580, LOW_SPEED_IO_SEL, 0, PLAT_IMX93, }, { IMX93_CLK_LPTMR1, "lptmr1_root", 0x0700, LOW_SPEED_IO_SEL, }, { IMX93_CLK_LPTMR2, "lptmr2_root", 0x0780, LOW_SPEED_IO_SEL, }, { IMX93_CLK_TPM2, "tpm2_root", 0x0880, TPM_SEL, }, @@ -177,10 +178,10 @@ static const struct imx93_clk_ccgr { { IMX93_CLK_WDOG5_GATE, "wdog5", "osc_24m", 0x8400, }, { IMX93_CLK_SEMA1_GATE, "sema1", "bus_aon_root", 0x8440, }, { IMX93_CLK_SEMA2_GATE, "sema2", "bus_wakeup_root", 0x8480, }, - { IMX93_CLK_MU1_A_GATE, "mu1_a", "bus_aon_root", 0x84c0, CLK_IGNORE_UNUSED }, - { IMX93_CLK_MU2_A_GATE, "mu2_a", "bus_wakeup_root", 0x84c0, CLK_IGNORE_UNUSED }, - { IMX93_CLK_MU1_B_GATE, "mu1_b", "bus_aon_root", 0x8500, 0, &share_count_mub }, - { IMX93_CLK_MU2_B_GATE, "mu2_b", "bus_wakeup_root", 0x8500, 0, &share_count_mub }, + { IMX93_CLK_MU1_A_GATE, "mu1_a", "bus_aon_root", 0x84c0, CLK_IGNORE_UNUSED, NULL, PLAT_IMX93 }, + { IMX93_CLK_MU2_A_GATE, "mu2_a", "bus_wakeup_root", 0x84c0, CLK_IGNORE_UNUSED, NULL, PLAT_IMX93 }, + { IMX93_CLK_MU1_B_GATE, "mu1_b", "bus_aon_root", 0x8500, 0, &share_count_mub, PLAT_IMX93 }, + { IMX93_CLK_MU2_B_GATE, "mu2_b", "bus_wakeup_root", 0x8500, 0, &share_count_mub, PLAT_IMX93 }, { IMX93_CLK_EDMA1_GATE, "edma1", "m33_root", 0x8540, }, { IMX93_CLK_EDMA2_GATE, "edma2", "wakeup_axi_root", 0x8580, }, { IMX93_CLK_FLEXSPI1_GATE, "flexspi1", "flexspi1_root", 0x8640, }, @@ -188,8 +189,8 @@ static const struct imx93_clk_ccgr { { IMX93_CLK_GPIO2_GATE, "gpio2", "bus_wakeup_root", 0x88c0, }, { IMX93_CLK_GPIO3_GATE, "gpio3", "bus_wakeup_root", 0x8900, }, { IMX93_CLK_GPIO4_GATE, "gpio4", "bus_wakeup_root", 0x8940, }, - { IMX93_CLK_FLEXIO1_GATE, "flexio1", "flexio1_root", 0x8980, }, - { IMX93_CLK_FLEXIO2_GATE, "flexio2", "flexio2_root", 0x89c0, }, + { IMX93_CLK_FLEXIO1_GATE, "flexio1", "flexio1_root", 0x8980, 0, NULL, PLAT_IMX93}, + { IMX93_CLK_FLEXIO2_GATE, "flexio2", "flexio2_root", 0x89c0, 0, NULL, PLAT_IMX93}, { IMX93_CLK_LPIT1_GATE, "lpit1", "bus_aon_root", 0x8a00, }, { IMX93_CLK_LPIT2_GATE, "lpit2", "bus_wakeup_root", 0x8a40, }, { IMX93_CLK_LPTMR1_GATE, "lptmr1", "lptmr1_root", 0x8a80, }, @@ -238,10 +239,10 @@ static const struct imx93_clk_ccgr { { IMX93_CLK_SAI3_GATE, "sai3", "sai3_root", 0x94c0, 0, &share_count_sai3}, { IMX93_CLK_SAI3_IPG, "sai3_ipg_clk", "bus_wakeup_root", 0x94c0, 0, &share_count_sai3}, { IMX93_CLK_MIPI_CSI_GATE, "mipi_csi", "media_apb_root", 0x9580, }, - { IMX93_CLK_MIPI_DSI_GATE, "mipi_dsi", "media_apb_root", 0x95c0, }, - { IMX93_CLK_LVDS_GATE, "lvds", "media_ldb_root", 0x9600, }, + { IMX93_CLK_MIPI_DSI_GATE, "mipi_dsi", "media_apb_root", 0x95c0, 0, NULL, PLAT_IMX93 }, + { IMX93_CLK_LVDS_GATE, "lvds", "media_ldb_root", 0x9600, 0, NULL, PLAT_IMX93 }, { IMX93_CLK_LCDIF_GATE, "lcdif", "media_apb_root", 0x9640, }, - { IMX93_CLK_PXP_GATE, "pxp", "media_apb_root", 0x9680, }, + { IMX93_CLK_PXP_GATE, "pxp", "media_apb_root", 0x9680, 0, NULL, PLAT_IMX93 }, { IMX93_CLK_ISI_GATE, "isi", "media_apb_root", 0x96c0, }, { IMX93_CLK_NIC_MEDIA_GATE, "nic_media", "media_axi_root", 0x9700, }, { IMX93_CLK_USB_CONTROLLER_GATE, "usb_controller", "hsio_root", 0x9a00, }, @@ -252,12 +253,13 @@ static const struct imx93_clk_ccgr { { IMX93_CLK_MQS1_GATE, "mqs1", "sai1_root", 0x9b00, }, { IMX93_CLK_MQS2_GATE, "mqs2", "sai3_root", 0x9b40, }, { IMX93_CLK_AUD_XCVR_GATE, "aud_xcvr", "audio_xcvr_root", 0x9b80, }, - { IMX93_CLK_SPDIF_GATE, "spdif", "spdif_root", 0x9c00, }, + { IMX93_CLK_SPDIF_IPG, "spdif_ipg_clk", "bus_wakeup_root", 0x9c00, 0, &share_count_spdif}, + { IMX93_CLK_SPDIF_GATE, "spdif", "spdif_root", 0x9c00, 0, &share_count_spdif}, { IMX93_CLK_HSIO_32K_GATE, "hsio_32k", "osc_32k", 0x9dc0, }, { IMX93_CLK_ENET1_GATE, "enet1", "wakeup_axi_root", 0x9e00, 0, NULL, PLAT_IMX93, }, { IMX93_CLK_ENET_QOS_GATE, "enet_qos", "wakeup_axi_root", 0x9e40, 0, NULL, PLAT_IMX93, }, - { IMX91_CLK_ENET2_REGULAR_GATE, "enet2_regular", "wakeup_axi_root", 0x9e00, 0, NULL, PLAT_IMX91, }, - { IMX91_CLK_ENET1_QOS_TSN_GATE, "enet1_qos_tsn", "wakeup_axi_root", 0x9e40, 0, NULL, PLAT_IMX91, }, + { IMX91_CLK_ENET2_REGULAR_GATE, "enet2_regular", "wakeup_axi_root", 0x9e00, 0, NULL, PLAT_IMX91, }, + { IMX91_CLK_ENET1_QOS_TSN_GATE, "enet1_qos_tsn", "wakeup_axi_root", 0x9e40, 0, NULL, PLAT_IMX91, }, /* Critical because clk accessed during CPU idle */ { IMX93_CLK_SYS_CNT_GATE, "sys_cnt", "osc_24m", 0x9e80, CLK_IS_CRITICAL}, { IMX93_CLK_TSTMR1_GATE, "tstmr1", "bus_aon_root", 0x9ec0, }, diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c index d63564dbb12c..f290981ea13b 100644 --- a/drivers/clk/imx/clk-pll14xx.c +++ b/drivers/clk/imx/clk-pll14xx.c @@ -56,7 +56,9 @@ static const struct imx_pll14xx_rate_table imx_pll1416x_tbl[] = { PLL_1416X_RATE(700000000U, 350, 3, 2), PLL_1416X_RATE(640000000U, 320, 3, 2), PLL_1416X_RATE(600000000U, 300, 3, 2), + PLL_1416X_RATE(416000000U, 208, 3, 2), PLL_1416X_RATE(320000000U, 160, 3, 2), + PLL_1416X_RATE(208000000U, 208, 3, 3), }; static const struct imx_pll14xx_rate_table imx_pll1443x_tbl[] = { diff --git a/drivers/clk/mediatek/clk-mt2701-aud.c b/drivers/clk/mediatek/clk-mt2701-aud.c index 425c69cfb105..e103121cf58e 100644 --- a/drivers/clk/mediatek/clk-mt2701-aud.c +++ b/drivers/clk/mediatek/clk-mt2701-aud.c @@ -55,10 +55,16 @@ static const struct mtk_gate audio_clks[] = { GATE_DUMMY(CLK_DUMMY, "aud_dummy"), /* AUDIO0 */ GATE_AUDIO0(CLK_AUD_AFE, "audio_afe", "aud_intbus_sel", 2), + GATE_DUMMY(CLK_AUD_LRCK_DETECT, "audio_lrck_detect_dummy"), + GATE_DUMMY(CLK_AUD_I2S, "audio_i2c_dummy"), + GATE_DUMMY(CLK_AUD_APLL_TUNER, "audio_apll_tuner_dummy"), GATE_AUDIO0(CLK_AUD_HDMI, "audio_hdmi", "audpll_sel", 20), GATE_AUDIO0(CLK_AUD_SPDF, "audio_spdf", "audpll_sel", 21), GATE_AUDIO0(CLK_AUD_SPDF2, "audio_spdf2", "audpll_sel", 22), GATE_AUDIO0(CLK_AUD_APLL, "audio_apll", "audpll_sel", 23), + GATE_DUMMY(CLK_AUD_TML, "audio_tml_dummy"), + GATE_DUMMY(CLK_AUD_AHB_IDLE_EXT, "audio_ahb_idle_ext_dummy"), + GATE_DUMMY(CLK_AUD_AHB_IDLE_INT, "audio_ahb_idle_int_dummy"), /* AUDIO1 */ GATE_AUDIO1(CLK_AUD_I2SIN1, "audio_i2sin1", "aud_mux1_sel", 0), GATE_AUDIO1(CLK_AUD_I2SIN2, "audio_i2sin2", "aud_mux1_sel", 1), @@ -76,10 +82,12 @@ static const struct mtk_gate audio_clks[] = { GATE_AUDIO1(CLK_AUD_ASRCI2, "audio_asrci2", "asm_h_sel", 13), GATE_AUDIO1(CLK_AUD_ASRCO1, "audio_asrco1", "asm_h_sel", 14), GATE_AUDIO1(CLK_AUD_ASRCO2, "audio_asrco2", "asm_h_sel", 15), + GATE_DUMMY(CLK_AUD_HDMIRX, "audio_hdmirx_dummy"), GATE_AUDIO1(CLK_AUD_INTDIR, "audio_intdir", "intdir_sel", 20), GATE_AUDIO1(CLK_AUD_A1SYS, "audio_a1sys", "aud_mux1_sel", 21), GATE_AUDIO1(CLK_AUD_A2SYS, "audio_a2sys", "aud_mux2_sel", 22), GATE_AUDIO1(CLK_AUD_AFE_CONN, "audio_afe_conn", "aud_mux1_sel", 23), + GATE_DUMMY(CLK_AUD_AFE_PCMIF, "audio_afe_pcmif_dummy"), GATE_AUDIO1(CLK_AUD_AFE_MRGIF, "audio_afe_mrgif", "aud_mux1_sel", 25), /* AUDIO2 */ GATE_AUDIO2(CLK_AUD_MMIF_UL1, "audio_ul1", "aud_mux1_sel", 0), @@ -100,6 +108,8 @@ static const struct mtk_gate audio_clks[] = { GATE_AUDIO2(CLK_AUD_MMIF_AWB2, "audio_awb2", "aud_mux1_sel", 15), GATE_AUDIO2(CLK_AUD_MMIF_DAI, "audio_dai", "aud_mux1_sel", 16), /* AUDIO3 */ + GATE_DUMMY(CLK_AUD_DMIC1, "audio_dmic1_dummy"), + GATE_DUMMY(CLK_AUD_DMIC2, "audio_dmic2_dummy"), GATE_AUDIO3(CLK_AUD_ASRCI3, "audio_asrci3", "asm_h_sel", 2), GATE_AUDIO3(CLK_AUD_ASRCI4, "audio_asrci4", "asm_h_sel", 3), GATE_AUDIO3(CLK_AUD_ASRCI5, "audio_asrci5", "asm_h_sel", 4), diff --git a/drivers/clk/mediatek/clk-mt2701-bdp.c b/drivers/clk/mediatek/clk-mt2701-bdp.c index 5da3eabffd3e..f11c7a4fa37b 100644 --- a/drivers/clk/mediatek/clk-mt2701-bdp.c +++ b/drivers/clk/mediatek/clk-mt2701-bdp.c @@ -31,6 +31,7 @@ static const struct mtk_gate_regs bdp1_cg_regs = { GATE_MTK(_id, _name, _parent, &bdp1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate bdp_clks[] = { + GATE_DUMMY(CLK_DUMMY, "bdp_dummy"), GATE_BDP0(CLK_BDP_BRG_BA, "brg_baclk", "mm_sel", 0), GATE_BDP0(CLK_BDP_BRG_DRAM, "brg_dram", "mm_sel", 1), GATE_BDP0(CLK_BDP_LARB_DRAM, "larb_dram", "mm_sel", 2), diff --git a/drivers/clk/mediatek/clk-mt2701-img.c b/drivers/clk/mediatek/clk-mt2701-img.c index 875594bc9dcb..c158e54c4652 100644 --- a/drivers/clk/mediatek/clk-mt2701-img.c +++ b/drivers/clk/mediatek/clk-mt2701-img.c @@ -22,6 +22,7 @@ static const struct mtk_gate_regs img_cg_regs = { GATE_MTK(_id, _name, _parent, &img_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate img_clks[] = { + GATE_DUMMY(CLK_DUMMY, "img_dummy"), GATE_IMG(CLK_IMG_SMI_COMM, "img_smi_comm", "mm_sel", 0), GATE_IMG(CLK_IMG_RESZ, "img_resz", "mm_sel", 1), GATE_IMG(CLK_IMG_JPGDEC_SMI, "img_jpgdec_smi", "mm_sel", 5), diff --git a/drivers/clk/mediatek/clk-mt2701-mm.c b/drivers/clk/mediatek/clk-mt2701-mm.c index bc68fa718878..474d87d62e83 100644 --- a/drivers/clk/mediatek/clk-mt2701-mm.c +++ b/drivers/clk/mediatek/clk-mt2701-mm.c @@ -31,6 +31,7 @@ static const struct mtk_gate_regs disp1_cg_regs = { GATE_MTK(_id, _name, _parent, &disp1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate mm_clks[] = { + GATE_DUMMY(CLK_DUMMY, "mm_dummy"), GATE_DISP0(CLK_MM_SMI_COMMON, "mm_smi_comm", "mm_sel", 0), GATE_DISP0(CLK_MM_SMI_LARB0, "mm_smi_larb0", "mm_sel", 1), GATE_DISP0(CLK_MM_CMDQ, "mm_cmdq", "mm_sel", 2), diff --git a/drivers/clk/mediatek/clk-mt2701-vdec.c b/drivers/clk/mediatek/clk-mt2701-vdec.c index 94db86f8d0a4..5299d92f3aba 100644 --- a/drivers/clk/mediatek/clk-mt2701-vdec.c +++ b/drivers/clk/mediatek/clk-mt2701-vdec.c @@ -31,6 +31,7 @@ static const struct mtk_gate_regs vdec1_cg_regs = { GATE_MTK(_id, _name, _parent, &vdec1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate vdec_clks[] = { + GATE_DUMMY(CLK_DUMMY, "vdec_dummy"), GATE_VDEC0(CLK_VDEC_CKGEN, "vdec_cken", "vdec_sel", 0), GATE_VDEC1(CLK_VDEC_LARB, "vdec_larb_cken", "mm_sel", 0), }; diff --git a/drivers/clk/mmp/clk-pxa1908-apbc.c b/drivers/clk/mmp/clk-pxa1908-apbc.c index b93d08466198..3fd7b5e644f3 100644 --- a/drivers/clk/mmp/clk-pxa1908-apbc.c +++ b/drivers/clk/mmp/clk-pxa1908-apbc.c @@ -96,8 +96,8 @@ static int pxa1908_apbc_probe(struct platform_device *pdev) struct pxa1908_clk_unit *pxa_unit; pxa_unit = devm_kzalloc(&pdev->dev, sizeof(*pxa_unit), GFP_KERNEL); - if (IS_ERR(pxa_unit)) - return PTR_ERR(pxa_unit); + if (!pxa_unit) + return -ENOMEM; pxa_unit->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pxa_unit->base)) diff --git a/drivers/clk/mmp/clk-pxa1908-apbcp.c b/drivers/clk/mmp/clk-pxa1908-apbcp.c index 08f3845cbb1b..f638d7e89b47 100644 --- a/drivers/clk/mmp/clk-pxa1908-apbcp.c +++ b/drivers/clk/mmp/clk-pxa1908-apbcp.c @@ -48,8 +48,8 @@ static int pxa1908_apbcp_probe(struct platform_device *pdev) struct pxa1908_clk_unit *pxa_unit; pxa_unit = devm_kzalloc(&pdev->dev, sizeof(*pxa_unit), GFP_KERNEL); - if (IS_ERR(pxa_unit)) - return PTR_ERR(pxa_unit); + if (!pxa_unit) + return -ENOMEM; pxa_unit->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pxa_unit->base)) diff --git a/drivers/clk/mmp/clk-pxa1908-mpmu.c b/drivers/clk/mmp/clk-pxa1908-mpmu.c index e3337bacaadd..90b4b2488574 100644 --- a/drivers/clk/mmp/clk-pxa1908-mpmu.c +++ b/drivers/clk/mmp/clk-pxa1908-mpmu.c @@ -78,8 +78,8 @@ static int pxa1908_mpmu_probe(struct platform_device *pdev) struct pxa1908_clk_unit *pxa_unit; pxa_unit = devm_kzalloc(&pdev->dev, sizeof(*pxa_unit), GFP_KERNEL); - if (IS_ERR(pxa_unit)) - return PTR_ERR(pxa_unit); + if (!pxa_unit) + return -ENOMEM; pxa_unit->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pxa_unit->base)) diff --git a/drivers/clk/mmp/pwr-island.c b/drivers/clk/mmp/pwr-island.c index edaa2433a472..eaf5d2c5e593 100644 --- a/drivers/clk/mmp/pwr-island.c +++ b/drivers/clk/mmp/pwr-island.c @@ -106,10 +106,10 @@ struct generic_pm_domain *mmp_pm_domain_register(const char *name, pm_domain->flags = flags; pm_domain->lock = lock; - pm_genpd_init(&pm_domain->genpd, NULL, true); pm_domain->genpd.name = name; pm_domain->genpd.power_on = mmp_pm_domain_power_on; pm_domain->genpd.power_off = mmp_pm_domain_power_off; + pm_genpd_init(&pm_domain->genpd, NULL, true); return &pm_domain->genpd; } diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index ef89d686cbc4..69bbf62ba3cd 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -64,6 +64,15 @@ config CLK_X1E80100_TCSRCC Support for the TCSR clock controller on X1E80100 devices. Say Y if you want to use peripheral devices such as SD/UFS. +config CLK_X1P42100_GPUCC + tristate "X1P42100 Graphics Clock Controller" + depends on ARM64 || COMPILE_TEST + select CLK_X1E80100_GCC + help + Support for the graphics clock controller on X1P42100 devices. + Say Y if you want to support graphics controller devices and + functionality such as 3D graphics. + config CLK_QCM2290_GPUCC tristate "QCM2290 Graphics Clock Controller" depends on ARM64 || COMPILE_TEST @@ -190,6 +199,15 @@ config IPQ_APSS_6018 Say Y if you want to support CPU frequency scaling on ipq based devices. +config IPQ_CMN_PLL + tristate "IPQ CMN PLL Clock Controller" + help + Support for CMN PLL clock controller on IPQ platform. The + CMN PLL consumes the AHB/SYS clocks from GCC and supplies + the output clocks to the networking hardware and GCC blocks. + Say Y or M if you want to support CMN PLL clock on the IPQ + based devices. + config IPQ_GCC_4019 tristate "IPQ4019 Global Clock Controller" help @@ -495,6 +513,15 @@ config QCS_GCC_8300 Say Y if you want to use peripheral devices such as UART, SPI, I2C, USB, SD/UFS, PCIe etc. +config QCS_GCC_615 + tristate "QCS615 Global Clock Controller" + depends on ARM64 || COMPILE_TEST + select QCOM_GDSC + help + Support for the global clock controller on QCS615 devices. + Say Y if you want to use multimedia devices or peripheral + devices such as UART, SPI, I2C, USB, SD/eMMC, PCIe etc. + config SC_CAMCC_7180 tristate "SC7180 Camera Clock Controller" depends on ARM64 || COMPILE_TEST @@ -1022,6 +1049,17 @@ config SM_DISPCC_8550 Say Y if you want to support display devices and functionality such as splash screen. +config SM_DISPCC_8750 + tristate "SM8750 Display Clock Controller" + depends on ARM64 || COMPILE_TEST + depends on SM_GCC_8750 + select QCOM_GDSC + help + Support for the display clock controller on Qualcomm Technologies, Inc + SM8750 devices. + Say Y if you want to support display devices and functionality such as + splash screen. + config SM_GCC_4450 tristate "SM4450 Global Clock Controller" depends on ARM64 || COMPILE_TEST @@ -1079,6 +1117,7 @@ config SM_GCC_7150 config SM_GCC_8150 tristate "SM8150 Global Clock Controller" depends on ARM64 || COMPILE_TEST + select QCOM_GDSC help Support for the global clock controller on SM8150 devices. Say Y if you want to use peripheral devices such as UART, @@ -1130,6 +1169,15 @@ config SM_GCC_8650 Say Y if you want to use peripheral devices such as UART, SPI, I2C, USB, SD/UFS, PCIe etc. +config SM_GCC_8750 + tristate "SM8750 Global Clock Controller" + depends on ARM64 || COMPILE_TEST + select QCOM_GDSC + help + Support for the global clock controller on SM8750 devices. + Say Y if you want to use peripheral devices such as UART, + SPI, I2C, USB, SD/UFS, PCIe etc. + config SM_GPUCC_4450 tristate "SM4450 Graphics Clock Controller" depends on ARM64 || COMPILE_TEST @@ -1230,6 +1278,15 @@ config SM_GPUCC_8650 Say Y if you want to support graphics controller devices and functionality such as 3D graphics. +config SM_LPASSCC_6115 + tristate "SM6115 Low Power Audio Subsystem (LPASS) Clock Controller" + depends on ARM64 || COMPILE_TEST + select SM_GCC_6115 + help + Support for the LPASS clock controller on SM6115 devices. + Say Y if you want to toggle LPASS-adjacent resets within + this clock controller to reset the LPASS subsystem. + config SM_TCSRCC_8550 tristate "SM8550 TCSR Clock Controller" depends on ARM64 || COMPILE_TEST @@ -1246,6 +1303,14 @@ config SM_TCSRCC_8650 Support for the TCSR clock controller on SM8650 devices. Say Y if you want to use peripheral devices such as SD/UFS. +config SM_TCSRCC_8750 + tristate "SM8750 TCSR Clock Controller" + depends on ARM64 || COMPILE_TEST + select QCOM_GDSC + help + Support for the TCSR clock controller on SM8750 devices. + Say Y if you want to use peripheral devices such as UFS/USB/PCIe. + config SA_VIDEOCC_8775P tristate "SA8775P Video Clock Controller" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index b09dbdc210eb..0db2f98bcb3e 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -26,9 +26,11 @@ obj-$(CONFIG_CLK_X1E80100_DISPCC) += dispcc-x1e80100.o obj-$(CONFIG_CLK_X1E80100_GCC) += gcc-x1e80100.o obj-$(CONFIG_CLK_X1E80100_GPUCC) += gpucc-x1e80100.o obj-$(CONFIG_CLK_X1E80100_TCSRCC) += tcsrcc-x1e80100.o +obj-$(CONFIG_CLK_X1P42100_GPUCC) += gpucc-x1p42100.o obj-$(CONFIG_CLK_QCM2290_GPUCC) += gpucc-qcm2290.o obj-$(CONFIG_IPQ_APSS_PLL) += apss-ipq-pll.o obj-$(CONFIG_IPQ_APSS_6018) += apss-ipq6018.o +obj-$(CONFIG_IPQ_CMN_PLL) += ipq-cmn-pll.o obj-$(CONFIG_IPQ_GCC_4019) += gcc-ipq4019.o obj-$(CONFIG_IPQ_GCC_5018) += gcc-ipq5018.o obj-$(CONFIG_IPQ_GCC_5332) += gcc-ipq5332.o @@ -71,6 +73,7 @@ obj-$(CONFIG_QCOM_CLK_SMD_RPM) += clk-smd-rpm.o obj-$(CONFIG_QCM_GCC_2290) += gcc-qcm2290.o obj-$(CONFIG_QCM_DISPCC_2290) += dispcc-qcm2290.o obj-$(CONFIG_QCS_GCC_404) += gcc-qcs404.o +obj-$(CONFIG_QCS_GCC_615) += gcc-qcs615.o obj-$(CONFIG_QCS_GCC_8300) += gcc-qcs8300.o obj-$(CONFIG_QCS_Q6SSTOP_404) += q6sstop-qcs404.o obj-$(CONFIG_QCS_TURING_404) += turingcc-qcs404.o @@ -131,6 +134,7 @@ obj-$(CONFIG_SM_DISPCC_7150) += dispcc-sm7150.o obj-$(CONFIG_SM_DISPCC_8250) += dispcc-sm8250.o obj-$(CONFIG_SM_DISPCC_8450) += dispcc-sm8450.o obj-$(CONFIG_SM_DISPCC_8550) += dispcc-sm8550.o +obj-$(CONFIG_SM_DISPCC_8750) += dispcc-sm8750.o obj-$(CONFIG_SM_GCC_4450) += gcc-sm4450.o obj-$(CONFIG_SM_GCC_6115) += gcc-sm6115.o obj-$(CONFIG_SM_GCC_6125) += gcc-sm6125.o @@ -143,6 +147,7 @@ obj-$(CONFIG_SM_GCC_8350) += gcc-sm8350.o obj-$(CONFIG_SM_GCC_8450) += gcc-sm8450.o obj-$(CONFIG_SM_GCC_8550) += gcc-sm8550.o obj-$(CONFIG_SM_GCC_8650) += gcc-sm8650.o +obj-$(CONFIG_SM_GCC_8750) += gcc-sm8750.o obj-$(CONFIG_SM_GPUCC_4450) += gpucc-sm4450.o obj-$(CONFIG_SM_GPUCC_6115) += gpucc-sm6115.o obj-$(CONFIG_SM_GPUCC_6125) += gpucc-sm6125.o @@ -154,8 +159,10 @@ obj-$(CONFIG_SM_GPUCC_8350) += gpucc-sm8350.o obj-$(CONFIG_SM_GPUCC_8450) += gpucc-sm8450.o obj-$(CONFIG_SM_GPUCC_8550) += gpucc-sm8550.o obj-$(CONFIG_SM_GPUCC_8650) += gpucc-sm8650.o +obj-$(CONFIG_SM_LPASSCC_6115) += lpasscc-sm6115.o obj-$(CONFIG_SM_TCSRCC_8550) += tcsrcc-sm8550.o obj-$(CONFIG_SM_TCSRCC_8650) += tcsrcc-sm8650.o +obj-$(CONFIG_SM_TCSRCC_8750) += tcsrcc-sm8750.o obj-$(CONFIG_SM_VIDEOCC_7150) += videocc-sm7150.o obj-$(CONFIG_SM_VIDEOCC_8150) += videocc-sm8150.o obj-$(CONFIG_SM_VIDEOCC_8250) += videocc-sm8250.o diff --git a/drivers/clk/qcom/apss-ipq-pll.c b/drivers/clk/qcom/apss-ipq-pll.c index e8632db2c542..d6c1aea7e9e1 100644 --- a/drivers/clk/qcom/apss-ipq-pll.c +++ b/drivers/clk/qcom/apss-ipq-pll.c @@ -73,20 +73,19 @@ static const struct alpha_pll_config ipq5018_pll_config = { .main_output_mask = BIT(0), .aux_output_mask = BIT(1), .early_output_mask = BIT(3), - .alpha_en_mask = BIT(24), .status_val = 0x3, .status_mask = GENMASK(10, 8), .lock_det = BIT(2), .test_ctl_hi_val = 0x00400003, }; +/* 1.080 GHz configuration */ static const struct alpha_pll_config ipq5332_pll_config = { .l = 0x2d, .config_ctl_val = 0x4001075b, .main_output_mask = BIT(0), .aux_output_mask = BIT(1), .early_output_mask = BIT(3), - .alpha_en_mask = BIT(24), .status_val = 0x3, .status_mask = GENMASK(10, 8), .lock_det = BIT(2), diff --git a/drivers/clk/qcom/camcc-x1e80100.c b/drivers/clk/qcom/camcc-x1e80100.c index 85e76c7712ad..b73524ae64b1 100644 --- a/drivers/clk/qcom/camcc-x1e80100.c +++ b/drivers/clk/qcom/camcc-x1e80100.c @@ -2212,6 +2212,8 @@ static struct clk_branch cam_cc_sfe_0_fast_ahb_clk = { }, }; +static struct gdsc cam_cc_titan_top_gdsc; + static struct gdsc cam_cc_bps_gdsc = { .gdscr = 0x10004, .en_rest_wait_val = 0x2, @@ -2221,6 +2223,7 @@ static struct gdsc cam_cc_bps_gdsc = { .name = "cam_cc_bps_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -2233,6 +2236,7 @@ static struct gdsc cam_cc_ife_0_gdsc = { .name = "cam_cc_ife_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -2245,6 +2249,7 @@ static struct gdsc cam_cc_ife_1_gdsc = { .name = "cam_cc_ife_1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -2257,6 +2262,7 @@ static struct gdsc cam_cc_ipe_0_gdsc = { .name = "cam_cc_ipe_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -2269,6 +2275,7 @@ static struct gdsc cam_cc_sfe_0_gdsc = { .name = "cam_cc_sfe_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index b8351f8c0b84..9a65d14acf71 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -58,6 +58,7 @@ #define PLL_TEST_CTL_U(p) ((p)->offset + (p)->regs[PLL_OFF_TEST_CTL_U]) #define PLL_TEST_CTL_U1(p) ((p)->offset + (p)->regs[PLL_OFF_TEST_CTL_U1]) #define PLL_TEST_CTL_U2(p) ((p)->offset + (p)->regs[PLL_OFF_TEST_CTL_U2]) +#define PLL_TEST_CTL_U3(p) ((p)->offset + (p)->regs[PLL_OFF_TEST_CTL_U3]) #define PLL_STATUS(p) ((p)->offset + (p)->regs[PLL_OFF_STATUS]) #define PLL_OPMODE(p) ((p)->offset + (p)->regs[PLL_OFF_OPMODE]) #define PLL_FRAC(p) ((p)->offset + (p)->regs[PLL_OFF_FRAC]) @@ -197,6 +198,37 @@ const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = { [PLL_OFF_TEST_CTL_U1] = 0x34, [PLL_OFF_TEST_CTL_U2] = 0x38, }, + [CLK_ALPHA_PLL_TYPE_PONGO_ELU] = { + [PLL_OFF_OPMODE] = 0x04, + [PLL_OFF_STATE] = 0x08, + [PLL_OFF_STATUS] = 0x0c, + [PLL_OFF_L_VAL] = 0x10, + [PLL_OFF_USER_CTL] = 0x14, + [PLL_OFF_USER_CTL_U] = 0x18, + [PLL_OFF_CONFIG_CTL] = 0x1c, + [PLL_OFF_CONFIG_CTL_U] = 0x20, + [PLL_OFF_CONFIG_CTL_U1] = 0x24, + [PLL_OFF_CONFIG_CTL_U2] = 0x28, + [PLL_OFF_TEST_CTL] = 0x2c, + [PLL_OFF_TEST_CTL_U] = 0x30, + [PLL_OFF_TEST_CTL_U1] = 0x34, + [PLL_OFF_TEST_CTL_U2] = 0x38, + [PLL_OFF_TEST_CTL_U3] = 0x3c, + }, + [CLK_ALPHA_PLL_TYPE_TAYCAN_ELU] = { + [PLL_OFF_OPMODE] = 0x04, + [PLL_OFF_STATE] = 0x08, + [PLL_OFF_STATUS] = 0x0c, + [PLL_OFF_L_VAL] = 0x10, + [PLL_OFF_ALPHA_VAL] = 0x14, + [PLL_OFF_USER_CTL] = 0x18, + [PLL_OFF_USER_CTL_U] = 0x1c, + [PLL_OFF_CONFIG_CTL] = 0x20, + [PLL_OFF_CONFIG_CTL_U] = 0x24, + [PLL_OFF_CONFIG_CTL_U1] = 0x28, + [PLL_OFF_TEST_CTL] = 0x2c, + [PLL_OFF_TEST_CTL_U] = 0x30, + }, [CLK_ALPHA_PLL_TYPE_RIVIAN_EVO] = { [PLL_OFF_OPMODE] = 0x04, [PLL_OFF_STATUS] = 0x0c, @@ -323,6 +355,12 @@ EXPORT_SYMBOL_GPL(clk_alpha_pll_regs); #define LUCID_EVO_PLL_CAL_L_VAL_SHIFT 16 #define LUCID_OLE_PLL_RINGOSC_CAL_L_VAL_SHIFT 24 +/* PONGO ELU PLL specific setting and offsets */ +#define PONGO_PLL_OUT_MASK GENMASK(1, 0) +#define PONGO_PLL_L_VAL_MASK GENMASK(11, 0) +#define PONGO_XO_PRESENT BIT(10) +#define PONGO_CLOCK_SELECT BIT(12) + /* ZONDA PLL specific */ #define ZONDA_PLL_OUT_MASK 0xf #define ZONDA_STAY_IN_CFA BIT(16) @@ -352,7 +390,8 @@ static int wait_for_pll(struct clk_alpha_pll *pll, u32 mask, bool inverse, if (ret) return ret; - for (count = 200; count > 0; count--) { + /* Pongo PLLs using a 32KHz reference can take upwards of 1500us to lock. */ + for (count = 1500; count > 0; count--) { ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val); if (ret) return ret; @@ -432,6 +471,8 @@ void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, mask |= config->pre_div_mask; mask |= config->post_div_mask; mask |= config->vco_mask; + mask |= config->alpha_en_mask; + mask |= config->alpha_mode_mask; regmap_update_bits(regmap, PLL_USER_CTL(pll), mask, val); @@ -2494,6 +2535,144 @@ const struct clk_ops clk_alpha_pll_reset_lucid_evo_ops = { }; EXPORT_SYMBOL_GPL(clk_alpha_pll_reset_lucid_evo_ops); +static int alpha_pll_pongo_elu_prepare(struct clk_hw *hw) +{ + struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); + struct regmap *regmap = pll->clkr.regmap; + int ret; + + /* Enable PLL intially to one-time calibrate against XO. */ + regmap_write(regmap, PLL_OPMODE(pll), PLL_RUN); + regmap_update_bits(regmap, PLL_MODE(pll), PLL_RESET_N, PLL_RESET_N); + regmap_update_bits(regmap, PLL_MODE(pll), PONGO_XO_PRESENT, PONGO_XO_PRESENT); + + /* Set regmap for wait_for_pll() */ + pll->clkr.regmap = regmap; + ret = wait_for_pll_enable_lock(pll); + if (ret) { + /* Reverse calibration - disable PLL output */ + regmap_update_bits(regmap, PLL_MODE(pll), PLL_OUTCTRL, 0); + return ret; + } + + /* Disable PLL after one-time calibration. */ + regmap_write(regmap, PLL_OPMODE(pll), PLL_STANDBY); + + /* Select internally generated clock. */ + regmap_update_bits(regmap, PLL_MODE(pll), PONGO_CLOCK_SELECT, + PONGO_CLOCK_SELECT); + + return 0; +} + +static int alpha_pll_pongo_elu_enable(struct clk_hw *hw) +{ + struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); + struct regmap *regmap = pll->clkr.regmap; + int ret; + + /* Check if PLL is already enabled */ + if (trion_pll_is_enabled(pll, regmap)) + return 0; + + ret = regmap_update_bits(regmap, PLL_MODE(pll), PLL_RESET_N, PLL_RESET_N); + if (ret) + return ret; + + /* Set operation mode to RUN */ + regmap_write(regmap, PLL_OPMODE(pll), PLL_RUN); + + ret = wait_for_pll_enable_lock(pll); + if (ret) + return ret; + + /* Enable the global PLL outputs */ + ret = regmap_update_bits(regmap, PLL_MODE(pll), PLL_OUTCTRL, PLL_OUTCTRL); + if (ret) + return ret; + + /* Ensure that the write above goes through before returning. */ + mb(); + + return ret; +} + +static void alpha_pll_pongo_elu_disable(struct clk_hw *hw) +{ + struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); + struct regmap *regmap = pll->clkr.regmap; + int ret; + + /* Disable the global PLL output */ + ret = regmap_update_bits(regmap, PLL_MODE(pll), PLL_OUTCTRL, 0); + if (ret) + return; + + /* Place the PLL mode in STANDBY */ + regmap_write(regmap, PLL_OPMODE(pll), PLL_STANDBY); +} + +static unsigned long alpha_pll_pongo_elu_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); + struct regmap *regmap = pll->clkr.regmap; + u32 l; + + if (regmap_read(regmap, PLL_L_VAL(pll), &l)) + return 0; + + l &= PONGO_PLL_L_VAL_MASK; + + return alpha_pll_calc_rate(parent_rate, l, 0, pll_alpha_width(pll)); +} + +const struct clk_ops clk_alpha_pll_pongo_elu_ops = { + .prepare = alpha_pll_pongo_elu_prepare, + .enable = alpha_pll_pongo_elu_enable, + .disable = alpha_pll_pongo_elu_disable, + .recalc_rate = alpha_pll_pongo_elu_recalc_rate, +}; +EXPORT_SYMBOL_GPL(clk_alpha_pll_pongo_elu_ops); + +void clk_pongo_elu_pll_configure(struct clk_alpha_pll *pll, + struct regmap *regmap, + const struct alpha_pll_config *config) +{ + u32 val; + + regmap_update_bits(regmap, PLL_USER_CTL(pll), PONGO_PLL_OUT_MASK, + PONGO_PLL_OUT_MASK); + + if (trion_pll_is_enabled(pll, regmap)) + return; + + if (regmap_read(regmap, PLL_L_VAL(pll), &val)) + return; + val &= PONGO_PLL_L_VAL_MASK; + if (val) + return; + + clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l); + clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL(pll), config->config_ctl_val); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U(pll), config->config_ctl_hi_val); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U1(pll), config->config_ctl_hi1_val); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U2(pll), config->config_ctl_hi2_val); + clk_alpha_pll_write_config(regmap, PLL_USER_CTL(pll), + config->user_ctl_val | PONGO_PLL_OUT_MASK); + clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U(pll), config->user_ctl_hi_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL(pll), config->test_ctl_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U(pll), config->test_ctl_hi_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U1(pll), config->test_ctl_hi1_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U2(pll), config->test_ctl_hi2_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U3(pll), config->test_ctl_hi3_val); + + /* Disable PLL output */ + regmap_update_bits(regmap, PLL_MODE(pll), PLL_OUTCTRL, 0); +} +EXPORT_SYMBOL_GPL(clk_pongo_elu_pll_configure); + void clk_rivian_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, const struct alpha_pll_config *config) { diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h index c6d1b8429f95..79aca8525262 100644 --- a/drivers/clk/qcom/clk-alpha-pll.h +++ b/drivers/clk/qcom/clk-alpha-pll.h @@ -27,6 +27,8 @@ enum { CLK_ALPHA_PLL_TYPE_ZONDA_OLE, CLK_ALPHA_PLL_TYPE_LUCID_EVO, CLK_ALPHA_PLL_TYPE_LUCID_OLE, + CLK_ALPHA_PLL_TYPE_PONGO_ELU, + CLK_ALPHA_PLL_TYPE_TAYCAN_ELU, CLK_ALPHA_PLL_TYPE_RIVIAN_EVO, CLK_ALPHA_PLL_TYPE_DEFAULT_EVO, CLK_ALPHA_PLL_TYPE_BRAMMO_EVO, @@ -52,6 +54,7 @@ enum { PLL_OFF_TEST_CTL_U, PLL_OFF_TEST_CTL_U1, PLL_OFF_TEST_CTL_U2, + PLL_OFF_TEST_CTL_U3, PLL_OFF_STATE, PLL_OFF_STATUS, PLL_OFF_OPMODE, @@ -137,6 +140,7 @@ struct alpha_pll_config { u32 test_ctl_hi_mask; u32 test_ctl_hi1_val; u32 test_ctl_hi2_val; + u32 test_ctl_hi3_val; u32 main_output_mask; u32 aux_output_mask; u32 aux2_output_mask; @@ -185,13 +189,17 @@ extern const struct clk_ops clk_alpha_pll_zonda_ops; #define clk_alpha_pll_zonda_ole_ops clk_alpha_pll_zonda_ops extern const struct clk_ops clk_alpha_pll_lucid_evo_ops; +#define clk_alpha_pll_taycan_elu_ops clk_alpha_pll_lucid_evo_ops extern const struct clk_ops clk_alpha_pll_reset_lucid_evo_ops; #define clk_alpha_pll_reset_lucid_ole_ops clk_alpha_pll_reset_lucid_evo_ops extern const struct clk_ops clk_alpha_pll_fixed_lucid_evo_ops; #define clk_alpha_pll_fixed_lucid_ole_ops clk_alpha_pll_fixed_lucid_evo_ops +#define clk_alpha_pll_fixed_taycan_elu_ops clk_alpha_pll_fixed_lucid_evo_ops extern const struct clk_ops clk_alpha_pll_postdiv_lucid_evo_ops; #define clk_alpha_pll_postdiv_lucid_ole_ops clk_alpha_pll_postdiv_lucid_evo_ops +#define clk_alpha_pll_postdiv_taycan_elu_ops clk_alpha_pll_postdiv_lucid_evo_ops +extern const struct clk_ops clk_alpha_pll_pongo_elu_ops; extern const struct clk_ops clk_alpha_pll_rivian_evo_ops; #define clk_alpha_pll_postdiv_rivian_evo_ops clk_alpha_pll_postdiv_fabia_ops @@ -218,6 +226,11 @@ void clk_lucid_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regma const struct alpha_pll_config *config); void clk_lucid_ole_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, const struct alpha_pll_config *config); +void clk_pongo_elu_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, + const struct alpha_pll_config *config); +#define clk_taycan_elu_pll_configure(pll, regmap, config) \ + clk_lucid_evo_pll_configure(pll, regmap, config) + void clk_rivian_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, const struct alpha_pll_config *config); void clk_stromer_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, diff --git a/drivers/clk/qcom/clk-rcg.c b/drivers/clk/qcom/clk-rcg.c index 88845baa7f84..987141c91fe0 100644 --- a/drivers/clk/qcom/clk-rcg.c +++ b/drivers/clk/qcom/clk-rcg.c @@ -597,6 +597,7 @@ struct frac_entry { }; static const struct frac_entry pixel_table[] = { + { 1, 1 }, { 1, 2 }, { 1, 3 }, { 3, 16 }, diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h index 80f1f4fcd52a..4fbdf4880d03 100644 --- a/drivers/clk/qcom/clk-rcg.h +++ b/drivers/clk/qcom/clk-rcg.h @@ -189,6 +189,7 @@ struct clk_rcg2_gfx3d { container_of(to_clk_rcg2(_hw), struct clk_rcg2_gfx3d, rcg) extern const struct clk_ops clk_rcg2_ops; +extern const struct clk_ops clk_rcg2_gp_ops; extern const struct clk_ops clk_rcg2_floor_ops; extern const struct clk_ops clk_rcg2_fm_ops; extern const struct clk_ops clk_rcg2_mux_closest_ops; diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index bf6406f5279a..8001fd9faf9d 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -8,11 +8,13 @@ #include #include #include +#include #include #include #include #include #include +#include #include #include @@ -32,6 +34,7 @@ #define CFG_REG 0x4 #define CFG_SRC_DIV_SHIFT 0 +#define CFG_SRC_DIV_LENGTH 8 #define CFG_SRC_SEL_SHIFT 8 #define CFG_SRC_SEL_MASK (0x7 << CFG_SRC_SEL_SHIFT) #define CFG_MODE_SHIFT 12 @@ -148,12 +151,32 @@ static int clk_rcg2_set_parent(struct clk_hw *hw, u8 index) return update_config(rcg); } -/* - * Calculate m/n:d rate +/** + * convert_to_reg_val() - Convert divisor values to hardware values. + * + * @f: Frequency table with pure m/n/pre_div parameters. + */ +static void convert_to_reg_val(struct freq_tbl *f) +{ + f->pre_div *= 2; + f->pre_div -= 1; +} + +/** + * calc_rate() - Calculate rate based on m/n:d values + * + * @rate: Parent rate. + * @m: Multiplier. + * @n: Divisor. + * @mode: Use zero to ignore m/n calculation. + * @hid_div: Pre divisor register value. Pre divisor value + * relates to hid_div as pre_div = (hid_div + 1) / 2. + * + * Return calculated rate according to formula: * * parent_rate m * rate = ----------- x --- - * hid_div n + * pre_div n */ static unsigned long calc_rate(unsigned long rate, u32 m, u32 n, u32 mode, u32 hid_div) @@ -393,16 +416,110 @@ static int clk_rcg2_fm_determine_rate(struct clk_hw *hw, return _freq_tbl_fm_determine_rate(hw, rcg->freq_multi_tbl, req); } -static int __clk_rcg2_configure(struct clk_rcg2 *rcg, const struct freq_tbl *f, - u32 *_cfg) +/** + * clk_rcg2_split_div() - Split multiplier that doesn't fit in n neither in pre_div. + * + * @multiplier: Multiplier to split between n and pre_div. + * @pre_div: Pointer to pre divisor value. + * @n: Pointer to n divisor value. + * @pre_div_max: Pre divisor maximum value. + */ +static inline void clk_rcg2_split_div(int multiplier, unsigned int *pre_div, + u16 *n, unsigned int pre_div_max) +{ + *n = mult_frac(multiplier * *n, *pre_div, pre_div_max); + *pre_div = pre_div_max; +} + +static void clk_rcg2_calc_mnd(u64 parent_rate, u64 rate, struct freq_tbl *f, + unsigned int mnd_max, unsigned int pre_div_max) +{ + int i = 2; + unsigned int pre_div = 1; + unsigned long rates_gcd, scaled_parent_rate; + u16 m, n = 1, n_candidate = 1, n_max; + + rates_gcd = gcd(parent_rate, rate); + m = div64_u64(rate, rates_gcd); + scaled_parent_rate = div64_u64(parent_rate, rates_gcd); + while (scaled_parent_rate > (mnd_max + m) * pre_div_max) { + // we're exceeding divisor's range, trying lower scale. + if (m > 1) { + m--; + scaled_parent_rate = mult_frac(scaled_parent_rate, m, (m + 1)); + } else { + // cannot lower scale, just set max divisor values. + f->n = mnd_max + m; + f->pre_div = pre_div_max; + f->m = m; + return; + } + } + + n_max = m + mnd_max; + + while (scaled_parent_rate > 1) { + while (scaled_parent_rate % i == 0) { + n_candidate *= i; + if (n_candidate < n_max) + n = n_candidate; + else if (pre_div * i < pre_div_max) + pre_div *= i; + else + clk_rcg2_split_div(i, &pre_div, &n, pre_div_max); + + scaled_parent_rate /= i; + } + i++; + } + + f->m = m; + f->n = n; + f->pre_div = pre_div > 1 ? pre_div : 0; +} + +static int clk_rcg2_determine_gp_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + struct clk_rcg2 *rcg = to_clk_rcg2(hw); + struct freq_tbl f_tbl = {}, *f = &f_tbl; + int mnd_max = BIT(rcg->mnd_width) - 1; + int hid_max = BIT(rcg->hid_width) - 1; + struct clk_hw *parent; + u64 parent_rate; + + parent = clk_hw_get_parent(hw); + parent_rate = clk_get_rate(parent->clk); + if (!parent_rate) + return -EINVAL; + + clk_rcg2_calc_mnd(parent_rate, req->rate, f, mnd_max, hid_max / 2); + convert_to_reg_val(f); + req->rate = calc_rate(parent_rate, f->m, f->n, f->n, f->pre_div); + + return 0; +} + +static int __clk_rcg2_configure_parent(struct clk_rcg2 *rcg, u8 src, u32 *_cfg) { - u32 cfg, mask, d_val, not2d_val, n_minus_m; struct clk_hw *hw = &rcg->clkr.hw; - int ret, index = qcom_find_src_index(hw, rcg->parent_map, f->src); + int index = qcom_find_src_index(hw, rcg->parent_map, src); if (index < 0) return index; + *_cfg &= ~CFG_SRC_SEL_MASK; + *_cfg |= rcg->parent_map[index].cfg << CFG_SRC_SEL_SHIFT; + + return 0; +} + +static int __clk_rcg2_configure_mnd(struct clk_rcg2 *rcg, const struct freq_tbl *f, + u32 *_cfg) +{ + u32 cfg, mask, d_val, not2d_val, n_minus_m; + int ret; + if (rcg->mnd_width && f->n) { mask = BIT(rcg->mnd_width) - 1; ret = regmap_update_bits(rcg->clkr.regmap, @@ -431,9 +548,8 @@ static int __clk_rcg2_configure(struct clk_rcg2 *rcg, const struct freq_tbl *f, } mask = BIT(rcg->hid_width) - 1; - mask |= CFG_SRC_SEL_MASK | CFG_MODE_MASK | CFG_HW_CLK_CTRL_MASK; + mask |= CFG_MODE_MASK | CFG_HW_CLK_CTRL_MASK; cfg = f->pre_div << CFG_SRC_DIV_SHIFT; - cfg |= rcg->parent_map[index].cfg << CFG_SRC_SEL_SHIFT; if (rcg->mnd_width && f->n && (f->m != f->n)) cfg |= CFG_MODE_DUAL_EDGE; if (rcg->hw_clk_ctrl) @@ -445,6 +561,22 @@ static int __clk_rcg2_configure(struct clk_rcg2 *rcg, const struct freq_tbl *f, return 0; } +static int __clk_rcg2_configure(struct clk_rcg2 *rcg, const struct freq_tbl *f, + u32 *_cfg) +{ + int ret; + + ret = __clk_rcg2_configure_parent(rcg, f->src, _cfg); + if (ret) + return ret; + + ret = __clk_rcg2_configure_mnd(rcg, f, _cfg); + if (ret) + return ret; + + return 0; +} + static int clk_rcg2_configure(struct clk_rcg2 *rcg, const struct freq_tbl *f) { u32 cfg; @@ -465,6 +597,26 @@ static int clk_rcg2_configure(struct clk_rcg2 *rcg, const struct freq_tbl *f) return update_config(rcg); } +static int clk_rcg2_configure_gp(struct clk_rcg2 *rcg, const struct freq_tbl *f) +{ + u32 cfg; + int ret; + + ret = regmap_read(rcg->clkr.regmap, RCG_CFG_OFFSET(rcg), &cfg); + if (ret) + return ret; + + ret = __clk_rcg2_configure_mnd(rcg, f, &cfg); + if (ret) + return ret; + + ret = regmap_write(rcg->clkr.regmap, RCG_CFG_OFFSET(rcg), cfg); + if (ret) + return ret; + + return update_config(rcg); +} + static int __clk_rcg2_set_rate(struct clk_hw *hw, unsigned long rate, enum freq_policy policy) { @@ -518,6 +670,22 @@ static int clk_rcg2_set_rate(struct clk_hw *hw, unsigned long rate, return __clk_rcg2_set_rate(hw, rate, CEIL); } +static int clk_rcg2_set_gp_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct clk_rcg2 *rcg = to_clk_rcg2(hw); + int mnd_max = BIT(rcg->mnd_width) - 1; + int hid_max = BIT(rcg->hid_width) - 1; + struct freq_tbl f_tbl = {}, *f = &f_tbl; + int ret; + + clk_rcg2_calc_mnd(parent_rate, rate, f, mnd_max, hid_max / 2); + convert_to_reg_val(f); + ret = clk_rcg2_configure_gp(rcg, f); + + return ret; +} + static int clk_rcg2_set_floor_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { @@ -645,6 +813,18 @@ const struct clk_ops clk_rcg2_ops = { }; EXPORT_SYMBOL_GPL(clk_rcg2_ops); +const struct clk_ops clk_rcg2_gp_ops = { + .is_enabled = clk_rcg2_is_enabled, + .get_parent = clk_rcg2_get_parent, + .set_parent = clk_rcg2_set_parent, + .recalc_rate = clk_rcg2_recalc_rate, + .determine_rate = clk_rcg2_determine_gp_rate, + .set_rate = clk_rcg2_set_gp_rate, + .get_duty_cycle = clk_rcg2_get_duty_cycle, + .set_duty_cycle = clk_rcg2_set_duty_cycle, +}; +EXPORT_SYMBOL_GPL(clk_rcg2_gp_ops); + const struct clk_ops clk_rcg2_floor_ops = { .is_enabled = clk_rcg2_is_enabled, .get_parent = clk_rcg2_get_parent, diff --git a/drivers/clk/qcom/clk-rpm.c b/drivers/clk/qcom/clk-rpm.c index 9da034f8f2ff..ccc112c21667 100644 --- a/drivers/clk/qcom/clk-rpm.c +++ b/drivers/clk/qcom/clk-rpm.c @@ -4,6 +4,7 @@ * Copyright (c) 2014, The Linux Foundation. All rights reserved. */ +#include #include #include #include @@ -224,10 +225,10 @@ static void clk_rpm_unprepare(struct clk_hw *hw) unsigned long active_rate, sleep_rate; int ret; - mutex_lock(&rpm_clk_lock); + guard(mutex)(&rpm_clk_lock); if (!r->rate) - goto out; + return; /* Take peer clock's rate into account only if it's enabled. */ if (peer->enabled) @@ -237,17 +238,14 @@ static void clk_rpm_unprepare(struct clk_hw *hw) active_rate = r->branch ? !!peer_rate : peer_rate; ret = clk_rpm_set_rate_active(r, active_rate); if (ret) - goto out; + return; sleep_rate = r->branch ? !!peer_sleep_rate : peer_sleep_rate; ret = clk_rpm_set_rate_sleep(r, sleep_rate); if (ret) - goto out; + return; r->enabled = false; - -out: - mutex_unlock(&rpm_clk_lock); } static int clk_rpm_xo_prepare(struct clk_hw *hw) @@ -324,12 +322,12 @@ static int clk_rpm_set_rate(struct clk_hw *hw, unsigned long active_rate, sleep_rate; unsigned long this_rate = 0, this_sleep_rate = 0; unsigned long peer_rate = 0, peer_sleep_rate = 0; - int ret = 0; + int ret; - mutex_lock(&rpm_clk_lock); + guard(mutex)(&rpm_clk_lock); if (!r->enabled) - goto out; + return 0; to_active_sleep(r, rate, &this_rate, &this_sleep_rate); @@ -341,19 +339,16 @@ static int clk_rpm_set_rate(struct clk_hw *hw, active_rate = max(this_rate, peer_rate); ret = clk_rpm_set_rate_active(r, active_rate); if (ret) - goto out; + return ret; sleep_rate = max(this_sleep_rate, peer_sleep_rate); ret = clk_rpm_set_rate_sleep(r, sleep_rate); if (ret) - goto out; + return ret; r->rate = rate; -out: - mutex_unlock(&rpm_clk_lock); - - return ret; + return 0; } static long clk_rpm_round_rate(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c index eefc322ce367..c7675930fde1 100644 --- a/drivers/clk/qcom/clk-rpmh.c +++ b/drivers/clk/qcom/clk-rpmh.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -206,7 +207,7 @@ static int clk_rpmh_aggregate_state_send_command(struct clk_rpmh *c, c->state = c->valid_state_mask; WARN(1, "clk: %s failed to %s\n", c->res_name, - enable ? "enable" : "disable"); + str_enable_disable(enable)); return ret; } @@ -329,7 +330,7 @@ static unsigned long clk_rpmh_bcm_recalc_rate(struct clk_hw *hw, { struct clk_rpmh *c = to_clk_rpmh(hw); - return c->aggr_state * c->unit; + return (unsigned long)c->aggr_state * c->unit; } static const struct clk_ops clk_rpmh_bcm_ops = { @@ -368,6 +369,8 @@ DEFINE_CLK_RPMH_VRM(rf_clk2, _d, "rfclkd2", 1); DEFINE_CLK_RPMH_VRM(rf_clk3, _d, "rfclkd3", 1); DEFINE_CLK_RPMH_VRM(rf_clk4, _d, "rfclkd4", 1); +DEFINE_CLK_RPMH_VRM(rf_clk3, _a2, "rfclka3", 2); + DEFINE_CLK_RPMH_VRM(clk1, _a1, "clka1", 1); DEFINE_CLK_RPMH_VRM(clk2, _a1, "clka2", 1); DEFINE_CLK_RPMH_VRM(clk3, _a1, "clka3", 1); @@ -807,6 +810,45 @@ static const struct clk_rpmh_desc clk_rpmh_x1e80100 = { .num_clks = ARRAY_SIZE(x1e80100_rpmh_clocks), }; +static struct clk_hw *qcs615_rpmh_clocks[] = { + [RPMH_CXO_CLK] = &clk_rpmh_bi_tcxo_div2.hw, + [RPMH_CXO_CLK_A] = &clk_rpmh_bi_tcxo_div2_ao.hw, + [RPMH_LN_BB_CLK2] = &clk_rpmh_ln_bb_clk2_a2.hw, + [RPMH_LN_BB_CLK2_A] = &clk_rpmh_ln_bb_clk2_a2_ao.hw, + [RPMH_LN_BB_CLK3] = &clk_rpmh_ln_bb_clk3_a2.hw, + [RPMH_LN_BB_CLK3_A] = &clk_rpmh_ln_bb_clk3_a2_ao.hw, + [RPMH_RF_CLK1] = &clk_rpmh_rf_clk1_a.hw, + [RPMH_RF_CLK1_A] = &clk_rpmh_rf_clk1_a_ao.hw, + [RPMH_RF_CLK2] = &clk_rpmh_rf_clk2_a.hw, + [RPMH_RF_CLK2_A] = &clk_rpmh_rf_clk2_a_ao.hw, +}; + +static const struct clk_rpmh_desc clk_rpmh_qcs615 = { + .clks = qcs615_rpmh_clocks, + .num_clks = ARRAY_SIZE(qcs615_rpmh_clocks), +}; + +static struct clk_hw *sm8750_rpmh_clocks[] = { + [RPMH_CXO_CLK] = &clk_rpmh_bi_tcxo_div2.hw, + [RPMH_CXO_CLK_A] = &clk_rpmh_bi_tcxo_div2_ao.hw, + [RPMH_LN_BB_CLK1] = &clk_rpmh_clk6_a2.hw, + [RPMH_LN_BB_CLK1_A] = &clk_rpmh_clk6_a2_ao.hw, + [RPMH_LN_BB_CLK3] = &clk_rpmh_clk8_a2.hw, + [RPMH_LN_BB_CLK3_A] = &clk_rpmh_clk8_a2_ao.hw, + [RPMH_RF_CLK1] = &clk_rpmh_rf_clk1_a.hw, + [RPMH_RF_CLK1_A] = &clk_rpmh_rf_clk1_a_ao.hw, + [RPMH_RF_CLK2] = &clk_rpmh_rf_clk2_a.hw, + [RPMH_RF_CLK2_A] = &clk_rpmh_rf_clk2_a_ao.hw, + [RPMH_RF_CLK3] = &clk_rpmh_rf_clk3_a2.hw, + [RPMH_RF_CLK3_A] = &clk_rpmh_rf_clk3_a2_ao.hw, + [RPMH_IPA_CLK] = &clk_rpmh_ipa.hw, +}; + +static const struct clk_rpmh_desc clk_rpmh_sm8750 = { + .clks = sm8750_rpmh_clocks, + .num_clks = ARRAY_SIZE(sm8750_rpmh_clocks), +}; + static struct clk_hw *of_clk_rpmh_hw_get(struct of_phandle_args *clkspec, void *data) { @@ -890,10 +932,12 @@ static int clk_rpmh_probe(struct platform_device *pdev) } static const struct of_device_id clk_rpmh_match_table[] = { + { .compatible = "qcom,qcs615-rpmh-clk", .data = &clk_rpmh_qcs615}, { .compatible = "qcom,qdu1000-rpmh-clk", .data = &clk_rpmh_qdu1000}, { .compatible = "qcom,sa8775p-rpmh-clk", .data = &clk_rpmh_sa8775p}, { .compatible = "qcom,sar2130p-rpmh-clk", .data = &clk_rpmh_sar2130p}, { .compatible = "qcom,sc7180-rpmh-clk", .data = &clk_rpmh_sc7180}, + { .compatible = "qcom,sc7280-rpmh-clk", .data = &clk_rpmh_sc7280}, { .compatible = "qcom,sc8180x-rpmh-clk", .data = &clk_rpmh_sc8180x}, { .compatible = "qcom,sc8280xp-rpmh-clk", .data = &clk_rpmh_sc8280xp}, { .compatible = "qcom,sdm845-rpmh-clk", .data = &clk_rpmh_sdm845}, @@ -909,7 +953,7 @@ static const struct of_device_id clk_rpmh_match_table[] = { { .compatible = "qcom,sm8450-rpmh-clk", .data = &clk_rpmh_sm8450}, { .compatible = "qcom,sm8550-rpmh-clk", .data = &clk_rpmh_sm8550}, { .compatible = "qcom,sm8650-rpmh-clk", .data = &clk_rpmh_sm8650}, - { .compatible = "qcom,sc7280-rpmh-clk", .data = &clk_rpmh_sc7280}, + { .compatible = "qcom,sm8750-rpmh-clk", .data = &clk_rpmh_sm8750}, { .compatible = "qcom,x1e80100-rpmh-clk", .data = &clk_rpmh_x1e80100}, { } }; diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 45c5255bcd11..29ef08a9d50b 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -4,6 +4,7 @@ * Copyright (c) 2014, The Linux Foundation. All rights reserved. */ +#include #include #include #include @@ -309,10 +310,10 @@ static void clk_smd_rpm_unprepare(struct clk_hw *hw) unsigned long active_rate, sleep_rate; int ret; - mutex_lock(&rpm_smd_clk_lock); + guard(mutex)(&rpm_smd_clk_lock); if (!r->rate) - goto out; + return; /* Take peer clock's rate into account only if it's enabled. */ if (peer->enabled) @@ -322,17 +323,14 @@ static void clk_smd_rpm_unprepare(struct clk_hw *hw) active_rate = r->branch ? !!peer_rate : peer_rate; ret = clk_smd_rpm_set_rate_active(r, active_rate); if (ret) - goto out; + return; sleep_rate = r->branch ? !!peer_sleep_rate : peer_sleep_rate; ret = clk_smd_rpm_set_rate_sleep(r, sleep_rate); if (ret) - goto out; + return; r->enabled = false; - -out: - mutex_unlock(&rpm_smd_clk_lock); } static int clk_smd_rpm_set_rate(struct clk_hw *hw, unsigned long rate, @@ -345,10 +343,10 @@ static int clk_smd_rpm_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long peer_rate = 0, peer_sleep_rate = 0; int ret = 0; - mutex_lock(&rpm_smd_clk_lock); + guard(mutex)(&rpm_smd_clk_lock); if (!r->enabled) - goto out; + return 0; to_active_sleep(r, rate, &this_rate, &this_sleep_rate); @@ -360,19 +358,16 @@ static int clk_smd_rpm_set_rate(struct clk_hw *hw, unsigned long rate, active_rate = max(this_rate, peer_rate); ret = clk_smd_rpm_set_rate_active(r, active_rate); if (ret) - goto out; + return ret; sleep_rate = max(this_sleep_rate, peer_sleep_rate); ret = clk_smd_rpm_set_rate_sleep(r, sleep_rate); if (ret) - goto out; + return ret; r->rate = rate; -out: - mutex_unlock(&rpm_smd_clk_lock); - - return ret; + return 0; } static long clk_smd_rpm_round_rate(struct clk_hw *hw, unsigned long rate, @@ -700,6 +695,60 @@ static const struct rpm_smd_clk_desc rpm_clk_msm8936 = { .num_icc_clks = ARRAY_SIZE(bimc_pcnoc_snoc_smmnoc_icc_clks), }; +static struct clk_smd_rpm *msm8937_clks[] = { + [RPM_SMD_XO_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo, + [RPM_SMD_XO_A_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo_a, + [RPM_SMD_QDSS_CLK] = &clk_smd_rpm_qdss_clk, + [RPM_SMD_QDSS_A_CLK] = &clk_smd_rpm_qdss_a_clk, + [RPM_SMD_BB_CLK1] = &clk_smd_rpm_bb_clk1, + [RPM_SMD_BB_CLK1_A] = &clk_smd_rpm_bb_clk1_a, + [RPM_SMD_BB_CLK2] = &clk_smd_rpm_bb_clk2, + [RPM_SMD_BB_CLK2_A] = &clk_smd_rpm_bb_clk2_a, + [RPM_SMD_RF_CLK2] = &clk_smd_rpm_rf_clk2, + [RPM_SMD_RF_CLK2_A] = &clk_smd_rpm_rf_clk2_a, + [RPM_SMD_DIV_CLK2] = &clk_smd_rpm_div_clk2, + [RPM_SMD_DIV_A_CLK2] = &clk_smd_rpm_div_clk2_a, + [RPM_SMD_BB_CLK1_PIN] = &clk_smd_rpm_bb_clk1_pin, + [RPM_SMD_BB_CLK1_A_PIN] = &clk_smd_rpm_bb_clk1_a_pin, + [RPM_SMD_BB_CLK2_PIN] = &clk_smd_rpm_bb_clk2_pin, + [RPM_SMD_BB_CLK2_A_PIN] = &clk_smd_rpm_bb_clk2_a_pin, +}; + +static const struct rpm_smd_clk_desc rpm_clk_msm8937 = { + .clks = msm8937_clks, + .num_clks = ARRAY_SIZE(msm8937_clks), + .icc_clks = bimc_pcnoc_snoc_smmnoc_icc_clks, + .num_icc_clks = ARRAY_SIZE(bimc_pcnoc_snoc_smmnoc_icc_clks), +}; + +static struct clk_smd_rpm *msm8940_clks[] = { + [RPM_SMD_XO_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo, + [RPM_SMD_XO_A_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo_a, + [RPM_SMD_IPA_CLK] = &clk_smd_rpm_ipa_clk, + [RPM_SMD_IPA_A_CLK] = &clk_smd_rpm_ipa_a_clk, + [RPM_SMD_QDSS_CLK] = &clk_smd_rpm_qdss_clk, + [RPM_SMD_QDSS_A_CLK] = &clk_smd_rpm_qdss_a_clk, + [RPM_SMD_BB_CLK1] = &clk_smd_rpm_bb_clk1, + [RPM_SMD_BB_CLK1_A] = &clk_smd_rpm_bb_clk1_a, + [RPM_SMD_BB_CLK2] = &clk_smd_rpm_bb_clk2, + [RPM_SMD_BB_CLK2_A] = &clk_smd_rpm_bb_clk2_a, + [RPM_SMD_RF_CLK2] = &clk_smd_rpm_rf_clk2, + [RPM_SMD_RF_CLK2_A] = &clk_smd_rpm_rf_clk2_a, + [RPM_SMD_DIV_CLK2] = &clk_smd_rpm_div_clk2, + [RPM_SMD_DIV_A_CLK2] = &clk_smd_rpm_div_clk2_a, + [RPM_SMD_BB_CLK1_PIN] = &clk_smd_rpm_bb_clk1_pin, + [RPM_SMD_BB_CLK1_A_PIN] = &clk_smd_rpm_bb_clk1_a_pin, + [RPM_SMD_BB_CLK2_PIN] = &clk_smd_rpm_bb_clk2_pin, + [RPM_SMD_BB_CLK2_A_PIN] = &clk_smd_rpm_bb_clk2_a_pin, +}; + +static const struct rpm_smd_clk_desc rpm_clk_msm8940 = { + .clks = msm8940_clks, + .num_clks = ARRAY_SIZE(msm8940_clks), + .icc_clks = bimc_pcnoc_snoc_smmnoc_icc_clks, + .num_icc_clks = ARRAY_SIZE(bimc_pcnoc_snoc_smmnoc_icc_clks), +}; + static struct clk_smd_rpm *msm8974_clks[] = { [RPM_SMD_XO_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo, [RPM_SMD_XO_A_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo_a, @@ -1216,6 +1265,8 @@ static const struct of_device_id rpm_smd_clk_match_table[] = { { .compatible = "qcom,rpmcc-msm8916", .data = &rpm_clk_msm8916 }, { .compatible = "qcom,rpmcc-msm8917", .data = &rpm_clk_msm8917 }, { .compatible = "qcom,rpmcc-msm8936", .data = &rpm_clk_msm8936 }, + { .compatible = "qcom,rpmcc-msm8937", .data = &rpm_clk_msm8937 }, + { .compatible = "qcom,rpmcc-msm8940", .data = &rpm_clk_msm8940 }, { .compatible = "qcom,rpmcc-msm8953", .data = &rpm_clk_msm8953 }, { .compatible = "qcom,rpmcc-msm8974", .data = &rpm_clk_msm8974 }, { .compatible = "qcom,rpmcc-msm8976", .data = &rpm_clk_msm8976 }, diff --git a/drivers/clk/qcom/clk-spmi-pmic-div.c b/drivers/clk/qcom/clk-spmi-pmic-div.c index f394031eb0e5..41a0a4f3b4fb 100644 --- a/drivers/clk/qcom/clk-spmi-pmic-div.c +++ b/drivers/clk/qcom/clk-spmi-pmic-div.c @@ -3,6 +3,7 @@ */ #include +#include #include #include #include @@ -140,30 +141,26 @@ static int clk_spmi_pmic_div_set_rate(struct clk_hw *hw, unsigned long rate, { struct clkdiv *clkdiv = to_clkdiv(hw); unsigned int div_factor = div_to_div_factor(parent_rate / rate); - unsigned long flags; bool enabled; int ret; - spin_lock_irqsave(&clkdiv->lock, flags); + guard(spinlock_irqsave)(&clkdiv->lock); + enabled = is_spmi_pmic_clkdiv_enabled(clkdiv); if (enabled) { ret = spmi_pmic_clkdiv_set_enable_state(clkdiv, false); if (ret) - goto unlock; + return ret; } ret = regmap_update_bits(clkdiv->regmap, clkdiv->base + REG_DIV_CTL1, DIV_CTL1_DIV_FACTOR_MASK, div_factor); if (ret) - goto unlock; + return ret; if (enabled) ret = __spmi_pmic_clkdiv_set_enable_state(clkdiv, true, div_factor); - -unlock: - spin_unlock_irqrestore(&clkdiv->lock, flags); - return ret; } diff --git a/drivers/clk/qcom/dispcc-qcm2290.c b/drivers/clk/qcom/dispcc-qcm2290.c index 449ffea2295d..d7bb1399e102 100644 --- a/drivers/clk/qcom/dispcc-qcm2290.c +++ b/drivers/clk/qcom/dispcc-qcm2290.c @@ -40,8 +40,6 @@ static const struct pll_vco spark_vco[] = { /* 768MHz configuration */ static const struct alpha_pll_config disp_cc_pll0_config = { .l = 0x28, - .alpha = 0x0, - .alpha_en_mask = BIT(24), .vco_val = 0x2 << 20, .vco_mask = GENMASK(21, 20), .main_output_mask = BIT(0), diff --git a/drivers/clk/qcom/dispcc-sm6115.c b/drivers/clk/qcom/dispcc-sm6115.c index 939887f82ecc..2b236d52b29f 100644 --- a/drivers/clk/qcom/dispcc-sm6115.c +++ b/drivers/clk/qcom/dispcc-sm6115.c @@ -48,8 +48,6 @@ static const struct pll_vco spark_vco[] = { /* 768MHz configuration */ static const struct alpha_pll_config disp_cc_pll0_config = { .l = 0x28, - .alpha = 0x0, - .alpha_en_mask = BIT(24), .vco_val = 0x2 << 20, .vco_mask = GENMASK(21, 20), .main_output_mask = BIT(0), diff --git a/drivers/clk/qcom/dispcc-sm6350.c b/drivers/clk/qcom/dispcc-sm6350.c index 50facb36701a..2bc6b5f99f57 100644 --- a/drivers/clk/qcom/dispcc-sm6350.c +++ b/drivers/clk/qcom/dispcc-sm6350.c @@ -187,13 +187,12 @@ static struct clk_rcg2 disp_cc_mdss_dp_aux_clk_src = { .cmd_rcgr = 0x1144, .mnd_width = 0, .hid_width = 5, + .parent_map = disp_cc_parent_map_6, .freq_tbl = ftbl_disp_cc_mdss_dp_aux_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "disp_cc_mdss_dp_aux_clk_src", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "bi_tcxo", - }, - .num_parents = 1, + .parent_data = disp_cc_parent_data_6, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_6), .ops = &clk_rcg2_ops, }, }; diff --git a/drivers/clk/qcom/dispcc-sm8750.c b/drivers/clk/qcom/dispcc-sm8750.c new file mode 100644 index 000000000000..0358dff91da5 --- /dev/null +++ b/drivers/clk/qcom/dispcc-sm8750.c @@ -0,0 +1,1963 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2023-2024, Linaro Ltd. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "common.h" +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-pll.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "reset.h" +#include "gdsc.h" + +/* Need to match the order of clocks in DT binding */ +enum { + DT_BI_TCXO, + DT_BI_TCXO_AO, + DT_AHB_CLK, + DT_SLEEP_CLK, + + DT_DSI0_PHY_PLL_OUT_BYTECLK, + DT_DSI0_PHY_PLL_OUT_DSICLK, + DT_DSI1_PHY_PLL_OUT_BYTECLK, + DT_DSI1_PHY_PLL_OUT_DSICLK, + + DT_DP0_PHY_PLL_LINK_CLK, + DT_DP0_PHY_PLL_VCO_DIV_CLK, + DT_DP1_PHY_PLL_LINK_CLK, + DT_DP1_PHY_PLL_VCO_DIV_CLK, + DT_DP2_PHY_PLL_LINK_CLK, + DT_DP2_PHY_PLL_VCO_DIV_CLK, + DT_DP3_PHY_PLL_LINK_CLK, + DT_DP3_PHY_PLL_VCO_DIV_CLK, +}; + +#define DISP_CC_MISC_CMD 0xF000 + +enum { + P_BI_TCXO, + P_DISP_CC_PLL0_OUT_MAIN, + P_DISP_CC_PLL1_OUT_EVEN, + P_DISP_CC_PLL1_OUT_MAIN, + P_DISP_CC_PLL2_OUT_MAIN, + P_DP0_PHY_PLL_LINK_CLK, + P_DP0_PHY_PLL_VCO_DIV_CLK, + P_DP1_PHY_PLL_LINK_CLK, + P_DP1_PHY_PLL_VCO_DIV_CLK, + P_DP2_PHY_PLL_LINK_CLK, + P_DP2_PHY_PLL_VCO_DIV_CLK, + P_DP3_PHY_PLL_LINK_CLK, + P_DP3_PHY_PLL_VCO_DIV_CLK, + P_DSI0_PHY_PLL_OUT_BYTECLK, + P_DSI0_PHY_PLL_OUT_DSICLK, + P_DSI1_PHY_PLL_OUT_BYTECLK, + P_DSI1_PHY_PLL_OUT_DSICLK, + P_SLEEP_CLK, +}; + +static const struct pll_vco pongo_elu_vco[] = { + { 38400000, 38400000, 0 }, +}; + +static const struct pll_vco taycan_elu_vco[] = { + { 249600000, 2500000000, 0 }, +}; + +static struct alpha_pll_config disp_cc_pll0_config = { + .l = 0xd, + .alpha = 0x6492, + .config_ctl_val = 0x19660387, + .config_ctl_hi_val = 0x098060a0, + .config_ctl_hi1_val = 0xb416cb20, + .user_ctl_val = 0x00000000, + .user_ctl_hi_val = 0x00000002, +}; + +static struct clk_alpha_pll disp_cc_pll0 = { + .offset = 0x0, + .vco_table = taycan_elu_vco, + .num_vco = ARRAY_SIZE(taycan_elu_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TAYCAN_ELU], + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_pll0", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_taycan_elu_ops, + }, + }, +}; + +static struct alpha_pll_config disp_cc_pll1_config = { + .l = 0x1f, + .alpha = 0x4000, + .config_ctl_val = 0x19660387, + .config_ctl_hi_val = 0x098060a0, + .config_ctl_hi1_val = 0xb416cb20, + .user_ctl_val = 0x00000000, + .user_ctl_hi_val = 0x00000002, +}; + +static struct clk_alpha_pll disp_cc_pll1 = { + .offset = 0x1000, + .vco_table = taycan_elu_vco, + .num_vco = ARRAY_SIZE(taycan_elu_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TAYCAN_ELU], + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_pll1", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_taycan_elu_ops, + }, + }, +}; + +static const struct alpha_pll_config disp_cc_pll2_config = { + .l = 0x493, + .alpha = 0x0, + .config_ctl_val = 0x60000f68, + .config_ctl_hi_val = 0x0001c808, + .config_ctl_hi1_val = 0x00000000, + .config_ctl_hi2_val = 0x040082f4, + .test_ctl_val = 0x00008000, + .test_ctl_hi_val = 0x0080c496, + .test_ctl_hi1_val = 0x40100180, + .test_ctl_hi2_val = 0x441001bc, + .test_ctl_hi3_val = 0x002003d8, + .user_ctl_val = 0x00000400, + .user_ctl_hi_val = 0x00e50302, +}; + +static struct clk_alpha_pll disp_cc_pll2 = { + .offset = 0x2000, + .vco_table = pongo_elu_vco, + .num_vco = ARRAY_SIZE(pongo_elu_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_PONGO_ELU], + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_pll2", + .parent_data = &(const struct clk_parent_data) { + .index = DT_SLEEP_CLK, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_pongo_elu_ops, + }, + }, +}; + +static const struct parent_map disp_cc_parent_map_0[] = { + { P_BI_TCXO, 0 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_0[] = { + { .index = DT_BI_TCXO }, +}; + +static const struct clk_parent_data disp_cc_parent_data_0_ao[] = { + { .index = DT_BI_TCXO_AO }, +}; + +static const struct parent_map disp_cc_parent_map_1[] = { + { P_BI_TCXO, 0 }, + { P_DSI0_PHY_PLL_OUT_DSICLK, 1 }, + { P_DSI0_PHY_PLL_OUT_BYTECLK, 2 }, + { P_DSI1_PHY_PLL_OUT_DSICLK, 3 }, + { P_DSI1_PHY_PLL_OUT_BYTECLK, 4 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_1[] = { + { .index = DT_BI_TCXO }, + { .index = DT_DSI0_PHY_PLL_OUT_DSICLK }, + { .index = DT_DSI0_PHY_PLL_OUT_BYTECLK }, + { .index = DT_DSI1_PHY_PLL_OUT_DSICLK }, + { .index = DT_DSI1_PHY_PLL_OUT_BYTECLK }, +}; + +static const struct parent_map disp_cc_parent_map_2[] = { + { P_BI_TCXO, 0 }, + { P_DP3_PHY_PLL_VCO_DIV_CLK, 3 }, + { P_DP1_PHY_PLL_VCO_DIV_CLK, 4 }, + { P_DP2_PHY_PLL_VCO_DIV_CLK, 6 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_2[] = { + { .index = DT_BI_TCXO }, + { .index = DT_DP3_PHY_PLL_VCO_DIV_CLK }, + { .index = DT_DP1_PHY_PLL_VCO_DIV_CLK }, + { .index = DT_DP2_PHY_PLL_VCO_DIV_CLK }, +}; + +static const struct parent_map disp_cc_parent_map_3[] = { + { P_BI_TCXO, 0 }, + { P_DP1_PHY_PLL_LINK_CLK, 2 }, + { P_DP2_PHY_PLL_LINK_CLK, 3 }, + { P_DP3_PHY_PLL_LINK_CLK, 4 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_3[] = { + { .index = DT_BI_TCXO }, + { .index = DT_DP1_PHY_PLL_LINK_CLK }, + { .index = DT_DP2_PHY_PLL_LINK_CLK }, + { .index = DT_DP3_PHY_PLL_LINK_CLK }, +}; + +static const struct parent_map disp_cc_parent_map_4[] = { + { P_BI_TCXO, 0 }, + { P_DSI0_PHY_PLL_OUT_DSICLK, 1 }, + { P_DISP_CC_PLL2_OUT_MAIN, 2 }, + { P_DSI1_PHY_PLL_OUT_DSICLK, 3 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_4[] = { + { .index = DT_BI_TCXO }, + { .index = DT_DSI0_PHY_PLL_OUT_DSICLK }, + { .hw = &disp_cc_pll2.clkr.hw }, + { .index = DT_DSI1_PHY_PLL_OUT_DSICLK }, +}; + +static const struct parent_map disp_cc_parent_map_5[] = { + { P_BI_TCXO, 0 }, + { P_DP0_PHY_PLL_LINK_CLK, 1 }, + { P_DP0_PHY_PLL_VCO_DIV_CLK, 2 }, + { P_DP3_PHY_PLL_VCO_DIV_CLK, 3 }, + { P_DP1_PHY_PLL_VCO_DIV_CLK, 4 }, + { P_DP2_PHY_PLL_VCO_DIV_CLK, 6 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_5[] = { + { .index = DT_BI_TCXO }, + { .index = DT_DP0_PHY_PLL_LINK_CLK }, + { .index = DT_DP0_PHY_PLL_VCO_DIV_CLK }, + { .index = DT_DP3_PHY_PLL_VCO_DIV_CLK }, + { .index = DT_DP1_PHY_PLL_VCO_DIV_CLK }, + { .index = DT_DP2_PHY_PLL_VCO_DIV_CLK }, +}; + +static const struct parent_map disp_cc_parent_map_6[] = { + { P_BI_TCXO, 0 }, + { P_DSI0_PHY_PLL_OUT_BYTECLK, 2 }, + { P_DSI1_PHY_PLL_OUT_BYTECLK, 4 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_6[] = { + { .index = DT_BI_TCXO }, + { .index = DT_DSI0_PHY_PLL_OUT_BYTECLK }, + { .index = DT_DSI1_PHY_PLL_OUT_BYTECLK }, +}; + +static const struct parent_map disp_cc_parent_map_7[] = { + { P_BI_TCXO, 0 }, + { P_DISP_CC_PLL1_OUT_MAIN, 4 }, + { P_DISP_CC_PLL1_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_7[] = { + { .index = DT_BI_TCXO }, + { .hw = &disp_cc_pll1.clkr.hw }, + { .hw = &disp_cc_pll1.clkr.hw }, +}; + +static const struct parent_map disp_cc_parent_map_8[] = { + { P_BI_TCXO, 0 }, + { P_DP0_PHY_PLL_LINK_CLK, 1 }, + { P_DP1_PHY_PLL_LINK_CLK, 2 }, + { P_DP2_PHY_PLL_LINK_CLK, 3 }, + { P_DP3_PHY_PLL_LINK_CLK, 4 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_8[] = { + { .index = DT_BI_TCXO }, + { .index = DT_DP0_PHY_PLL_LINK_CLK }, + { .index = DT_DP1_PHY_PLL_LINK_CLK }, + { .index = DT_DP2_PHY_PLL_LINK_CLK }, + { .index = DT_DP3_PHY_PLL_LINK_CLK }, +}; + +static const struct parent_map disp_cc_parent_map_9[] = { + { P_BI_TCXO, 0 }, + { P_DISP_CC_PLL0_OUT_MAIN, 1 }, + { P_DISP_CC_PLL1_OUT_MAIN, 4 }, + { P_DISP_CC_PLL1_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_9[] = { + { .index = DT_BI_TCXO }, + { .hw = &disp_cc_pll0.clkr.hw }, + { .hw = &disp_cc_pll1.clkr.hw }, + { .hw = &disp_cc_pll1.clkr.hw }, +}; + +static const struct parent_map disp_cc_parent_map_10[] = { + { P_BI_TCXO, 0 }, + { P_DISP_CC_PLL2_OUT_MAIN, 2 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_10[] = { + { .index = DT_BI_TCXO }, + { .hw = &disp_cc_pll2.clkr.hw }, +}; + +static const struct parent_map disp_cc_parent_map_11[] = { + { P_SLEEP_CLK, 0 }, +}; + +static const struct clk_parent_data disp_cc_parent_data_11[] = { + { .index = DT_SLEEP_CLK }, +}; + +static const struct freq_tbl ftbl_disp_cc_esync0_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 disp_cc_esync0_clk_src = { + .cmd_rcgr = 0x80c0, + .mnd_width = 16, + .hid_width = 5, + .parent_map = disp_cc_parent_map_4, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_esync0_clk_src", + .parent_data = disp_cc_parent_data_4, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_4), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_byte2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_esync1_clk_src = { + .cmd_rcgr = 0x80d8, + .mnd_width = 16, + .hid_width = 5, + .parent_map = disp_cc_parent_map_4, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_esync1_clk_src", + .parent_data = disp_cc_parent_data_4, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_4), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_byte2_ops, + }, +}; + +static const struct freq_tbl ftbl_disp_cc_mdss_ahb_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(37500000, P_DISP_CC_PLL1_OUT_MAIN, 16, 0, 0), + F(75000000, P_DISP_CC_PLL1_OUT_MAIN, 8, 0, 0), + { } +}; + +static struct clk_rcg2 disp_cc_mdss_ahb_clk_src = { + .cmd_rcgr = 0x8360, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_7, + .freq_tbl = ftbl_disp_cc_mdss_ahb_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_ahb_clk_src", + .parent_data = disp_cc_parent_data_7, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_7), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_byte0_clk_src = { + .cmd_rcgr = 0x8180, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_1, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_byte0_clk_src", + .parent_data = disp_cc_parent_data_1, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_byte2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_byte1_clk_src = { + .cmd_rcgr = 0x819c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_1, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_byte1_clk_src", + .parent_data = disp_cc_parent_data_1, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_byte2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx0_aux_clk_src = { + .cmd_rcgr = 0x8234, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_0, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_aux_clk_src", + .parent_data = disp_cc_parent_data_0, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx0_link_clk_src = { + .cmd_rcgr = 0x81e8, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_8, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_link_clk_src", + .parent_data = disp_cc_parent_data_8, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_8), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_byte2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx0_pixel0_clk_src = { + .cmd_rcgr = 0x8204, + .mnd_width = 16, + .hid_width = 5, + .parent_map = disp_cc_parent_map_5, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_pixel0_clk_src", + .parent_data = disp_cc_parent_data_5, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_5), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_dp_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx0_pixel1_clk_src = { + .cmd_rcgr = 0x821c, + .mnd_width = 16, + .hid_width = 5, + .parent_map = disp_cc_parent_map_5, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_pixel1_clk_src", + .parent_data = disp_cc_parent_data_5, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_5), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_dp_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx1_aux_clk_src = { + .cmd_rcgr = 0x8298, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_0, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_aux_clk_src", + .parent_data = disp_cc_parent_data_0, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx1_link_clk_src = { + .cmd_rcgr = 0x827c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_3, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_link_clk_src", + .parent_data = disp_cc_parent_data_3, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_byte2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx1_pixel0_clk_src = { + .cmd_rcgr = 0x824c, + .mnd_width = 16, + .hid_width = 5, + .parent_map = disp_cc_parent_map_2, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_pixel0_clk_src", + .parent_data = disp_cc_parent_data_2, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_2), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_dp_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx1_pixel1_clk_src = { + .cmd_rcgr = 0x8264, + .mnd_width = 16, + .hid_width = 5, + .parent_map = disp_cc_parent_map_2, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_pixel1_clk_src", + .parent_data = disp_cc_parent_data_2, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_2), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_dp_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx2_aux_clk_src = { + .cmd_rcgr = 0x82fc, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_0, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_aux_clk_src", + .parent_data = disp_cc_parent_data_0, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx2_link_clk_src = { + .cmd_rcgr = 0x82b0, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_3, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_link_clk_src", + .parent_data = disp_cc_parent_data_3, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_byte2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx2_pixel0_clk_src = { + .cmd_rcgr = 0x82cc, + .mnd_width = 16, + .hid_width = 5, + .parent_map = disp_cc_parent_map_2, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_pixel0_clk_src", + .parent_data = disp_cc_parent_data_2, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_2), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_dp_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx2_pixel1_clk_src = { + .cmd_rcgr = 0x82e4, + .mnd_width = 16, + .hid_width = 5, + .parent_map = disp_cc_parent_map_2, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_pixel1_clk_src", + .parent_data = disp_cc_parent_data_2, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_2), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_dp_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx3_aux_clk_src = { + .cmd_rcgr = 0x8348, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_0, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx3_aux_clk_src", + .parent_data = disp_cc_parent_data_0, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx3_link_clk_src = { + .cmd_rcgr = 0x832c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_3, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx3_link_clk_src", + .parent_data = disp_cc_parent_data_3, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_byte2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_dptx3_pixel0_clk_src = { + .cmd_rcgr = 0x8314, + .mnd_width = 16, + .hid_width = 5, + .parent_map = disp_cc_parent_map_2, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx3_pixel0_clk_src", + .parent_data = disp_cc_parent_data_2, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_2), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_dp_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_esc0_clk_src = { + .cmd_rcgr = 0x81b8, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_6, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_esc0_clk_src", + .parent_data = disp_cc_parent_data_6, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_6), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_esc1_clk_src = { + .cmd_rcgr = 0x81d0, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_6, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_esc1_clk_src", + .parent_data = disp_cc_parent_data_6, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_6), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_disp_cc_mdss_mdp_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(85714286, P_DISP_CC_PLL0_OUT_MAIN, 3, 0, 0), + F(100000000, P_DISP_CC_PLL0_OUT_MAIN, 3, 0, 0), + F(156000000, P_DISP_CC_PLL0_OUT_MAIN, 3, 0, 0), + F(207000000, P_DISP_CC_PLL0_OUT_MAIN, 3, 0, 0), + F(337000000, P_DISP_CC_PLL0_OUT_MAIN, 3, 0, 0), + F(417000000, P_DISP_CC_PLL0_OUT_MAIN, 3, 0, 0), + F(532000000, P_DISP_CC_PLL0_OUT_MAIN, 3, 0, 0), + F(575000000, P_DISP_CC_PLL0_OUT_MAIN, 3, 0, 0), + { } +}; + +static struct clk_rcg2 disp_cc_mdss_mdp_clk_src = { + .cmd_rcgr = 0x8150, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_9, + .freq_tbl = ftbl_disp_cc_mdss_mdp_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_mdp_clk_src", + .parent_data = disp_cc_parent_data_9, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_9), + .flags = CLK_SET_RATE_PARENT, + /* + * TODO: Downstream does not manage the clock directly, but + * places votes via new hardware block called "cesta". + * It is not clear whether such approach should be taken instead + * of manual control. + */ + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_pclk0_clk_src = { + .cmd_rcgr = 0x8108, + .mnd_width = 8, + .hid_width = 5, + .parent_map = disp_cc_parent_map_1, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_pclk0_clk_src", + .parent_data = disp_cc_parent_data_1, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_pixel_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_pclk1_clk_src = { + .cmd_rcgr = 0x8120, + .mnd_width = 8, + .hid_width = 5, + .parent_map = disp_cc_parent_map_1, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_pclk1_clk_src", + .parent_data = disp_cc_parent_data_1, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_pixel_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_pclk2_clk_src = { + .cmd_rcgr = 0x8138, + .mnd_width = 8, + .hid_width = 5, + .parent_map = disp_cc_parent_map_1, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_pclk2_clk_src", + .parent_data = disp_cc_parent_data_1, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_pixel_ops, + }, +}; + +static struct clk_rcg2 disp_cc_mdss_vsync_clk_src = { + .cmd_rcgr = 0x8168, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_0, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_vsync_clk_src", + .parent_data = disp_cc_parent_data_0, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_disp_cc_osc_clk_src[] = { + F(38400000, P_DISP_CC_PLL2_OUT_MAIN, 1, 0, 0), + { } +}; + +static struct clk_rcg2 disp_cc_osc_clk_src = { + .cmd_rcgr = 0x80f0, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_10, + .freq_tbl = ftbl_disp_cc_osc_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_osc_clk_src", + .parent_data = disp_cc_parent_data_10, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_10), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_disp_cc_sleep_clk_src[] = { + F(32000, P_SLEEP_CLK, 1, 0, 0), + { } +}; + +static struct clk_rcg2 disp_cc_sleep_clk_src = { + .cmd_rcgr = 0xe064, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_11, + .freq_tbl = ftbl_disp_cc_sleep_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_sleep_clk_src", + .parent_data = disp_cc_parent_data_11, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_11), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 disp_cc_xo_clk_src = { + .cmd_rcgr = 0xe044, + .mnd_width = 0, + .hid_width = 5, + .parent_map = disp_cc_parent_map_0, + .freq_tbl = ftbl_disp_cc_esync0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_xo_clk_src", + .parent_data = disp_cc_parent_data_0_ao, + .num_parents = ARRAY_SIZE(disp_cc_parent_data_0_ao), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_regmap_div disp_cc_mdss_byte0_div_clk_src = { + .reg = 0x8198, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_byte0_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_byte0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ops, + }, +}; + +static struct clk_regmap_div disp_cc_mdss_byte1_div_clk_src = { + .reg = 0x81b4, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_byte1_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_byte1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ops, + }, +}; + +static struct clk_regmap_div disp_cc_mdss_dptx0_link_div_clk_src = { + .reg = 0x8200, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_link_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx0_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_regmap_div disp_cc_mdss_dptx1_link_div_clk_src = { + .reg = 0x8294, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_link_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx1_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_regmap_div disp_cc_mdss_dptx2_link_div_clk_src = { + .reg = 0x82c8, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_link_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx2_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_regmap_div disp_cc_mdss_dptx3_link_div_clk_src = { + .reg = 0x8344, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx3_link_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx3_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_branch disp_cc_esync0_clk = { + .halt_reg = 0x80b8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x80b8, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_esync0_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_esync0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_esync1_clk = { + .halt_reg = 0x80bc, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x80bc, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_esync1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_esync1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_accu_shift_clk = { + .halt_reg = 0xe060, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xe060, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_accu_shift_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_xo_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_ahb1_clk = { + .halt_reg = 0xa028, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xa028, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_ahb1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_ahb_clk = { + .halt_reg = 0x80b0, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x80b0, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_byte0_clk = { + .halt_reg = 0x8034, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8034, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_byte0_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_byte0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_byte0_intf_clk = { + .halt_reg = 0x8038, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8038, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_byte0_intf_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_byte0_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_byte1_clk = { + .halt_reg = 0x803c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x803c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_byte1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_byte1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_byte1_intf_clk = { + .halt_reg = 0x8040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8040, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_byte1_intf_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_byte1_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx0_aux_clk = { + .halt_reg = 0x8064, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8064, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx0_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx0_crypto_clk = { + .halt_reg = 0x8058, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8058, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_crypto_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx0_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx0_link_clk = { + .halt_reg = 0x804c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x804c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_link_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx0_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx0_link_intf_clk = { + .halt_reg = 0x8054, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8054, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_link_intf_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx0_link_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx0_pixel0_clk = { + .halt_reg = 0x805c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x805c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_pixel0_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx0_pixel0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx0_pixel1_clk = { + .halt_reg = 0x8060, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8060, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_pixel1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx0_pixel1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx0_usb_router_link_intf_clk = { + .halt_reg = 0x8050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8050, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx0_usb_router_link_intf_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx0_link_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx1_aux_clk = { + .halt_reg = 0x8080, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8080, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx1_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx1_crypto_clk = { + .halt_reg = 0x807c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x807c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_crypto_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx1_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx1_link_clk = { + .halt_reg = 0x8070, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8070, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_link_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx1_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx1_link_intf_clk = { + .halt_reg = 0x8078, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8078, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_link_intf_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx1_link_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx1_pixel0_clk = { + .halt_reg = 0x8068, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8068, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_pixel0_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx1_pixel0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx1_pixel1_clk = { + .halt_reg = 0x806c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x806c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_pixel1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx1_pixel1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx1_usb_router_link_intf_clk = { + .halt_reg = 0x8074, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8074, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx1_usb_router_link_intf_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx1_link_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx2_aux_clk = { + .halt_reg = 0x8098, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8098, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx2_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx2_crypto_clk = { + .halt_reg = 0x8094, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8094, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_crypto_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx2_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx2_link_clk = { + .halt_reg = 0x808c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x808c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_link_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx2_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx2_link_intf_clk = { + .halt_reg = 0x8090, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8090, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_link_intf_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx2_link_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx2_pixel0_clk = { + .halt_reg = 0x8084, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8084, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_pixel0_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx2_pixel0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx2_pixel1_clk = { + .halt_reg = 0x8088, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8088, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx2_pixel1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx2_pixel1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx3_aux_clk = { + .halt_reg = 0x80a8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x80a8, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx3_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx3_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx3_crypto_clk = { + .halt_reg = 0x80ac, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x80ac, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx3_crypto_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx3_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx3_link_clk = { + .halt_reg = 0x80a0, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x80a0, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx3_link_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx3_link_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx3_link_intf_clk = { + .halt_reg = 0x80a4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x80a4, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx3_link_intf_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx3_link_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_dptx3_pixel0_clk = { + .halt_reg = 0x809c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x809c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_dptx3_pixel0_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_dptx3_pixel0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_esc0_clk = { + .halt_reg = 0x8044, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8044, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_esc0_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_esc0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_esc1_clk = { + .halt_reg = 0x8048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8048, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_esc1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_esc1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_mdp1_clk = { + .halt_reg = 0xa004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xa004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_mdp1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_mdp_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_mdp_clk = { + .halt_reg = 0x8010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_mdp_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_mdp_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_mdp_lut1_clk = { + .halt_reg = 0xa014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xa014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_mdp_lut1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_mdp_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_mdp_lut_clk = { + .halt_reg = 0x8020, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x8020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_mdp_lut_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_mdp_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_non_gdsc_ahb_clk = { + .halt_reg = 0xc004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xc004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_non_gdsc_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_pclk0_clk = { + .halt_reg = 0x8004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_pclk0_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_pclk0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_pclk1_clk = { + .halt_reg = 0x8008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_pclk1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_pclk1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_pclk2_clk = { + .halt_reg = 0x800c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x800c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_pclk2_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_pclk2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_vsync1_clk = { + .halt_reg = 0xa024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xa024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_vsync1_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_vsync_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_mdss_vsync_clk = { + .halt_reg = 0x8030, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8030, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_mdss_vsync_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_mdss_vsync_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch disp_cc_osc_clk = { + .halt_reg = 0x80b4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x80b4, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "disp_cc_osc_clk", + .parent_hws = (const struct clk_hw*[]) { + &disp_cc_osc_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct gdsc mdss_gdsc = { + .gdscr = 0x9000, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, + .pd = { + .name = "mdss_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR | HW_CTRL | RETAIN_FF_ENABLE, +}; + +static struct gdsc mdss_int2_gdsc = { + .gdscr = 0xb000, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, + .pd = { + .name = "mdss_int2_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR | HW_CTRL | RETAIN_FF_ENABLE, +}; + +static struct clk_regmap *disp_cc_sm8750_clocks[] = { + [DISP_CC_ESYNC0_CLK] = &disp_cc_esync0_clk.clkr, + [DISP_CC_ESYNC0_CLK_SRC] = &disp_cc_esync0_clk_src.clkr, + [DISP_CC_ESYNC1_CLK] = &disp_cc_esync1_clk.clkr, + [DISP_CC_ESYNC1_CLK_SRC] = &disp_cc_esync1_clk_src.clkr, + [DISP_CC_MDSS_ACCU_SHIFT_CLK] = &disp_cc_mdss_accu_shift_clk.clkr, + [DISP_CC_MDSS_AHB1_CLK] = &disp_cc_mdss_ahb1_clk.clkr, + [DISP_CC_MDSS_AHB_CLK] = &disp_cc_mdss_ahb_clk.clkr, + [DISP_CC_MDSS_AHB_CLK_SRC] = &disp_cc_mdss_ahb_clk_src.clkr, + [DISP_CC_MDSS_BYTE0_CLK] = &disp_cc_mdss_byte0_clk.clkr, + [DISP_CC_MDSS_BYTE0_CLK_SRC] = &disp_cc_mdss_byte0_clk_src.clkr, + [DISP_CC_MDSS_BYTE0_DIV_CLK_SRC] = &disp_cc_mdss_byte0_div_clk_src.clkr, + [DISP_CC_MDSS_BYTE0_INTF_CLK] = &disp_cc_mdss_byte0_intf_clk.clkr, + [DISP_CC_MDSS_BYTE1_CLK] = &disp_cc_mdss_byte1_clk.clkr, + [DISP_CC_MDSS_BYTE1_CLK_SRC] = &disp_cc_mdss_byte1_clk_src.clkr, + [DISP_CC_MDSS_BYTE1_DIV_CLK_SRC] = &disp_cc_mdss_byte1_div_clk_src.clkr, + [DISP_CC_MDSS_BYTE1_INTF_CLK] = &disp_cc_mdss_byte1_intf_clk.clkr, + [DISP_CC_MDSS_DPTX0_AUX_CLK] = &disp_cc_mdss_dptx0_aux_clk.clkr, + [DISP_CC_MDSS_DPTX0_AUX_CLK_SRC] = &disp_cc_mdss_dptx0_aux_clk_src.clkr, + [DISP_CC_MDSS_DPTX0_CRYPTO_CLK] = &disp_cc_mdss_dptx0_crypto_clk.clkr, + [DISP_CC_MDSS_DPTX0_LINK_CLK] = &disp_cc_mdss_dptx0_link_clk.clkr, + [DISP_CC_MDSS_DPTX0_LINK_CLK_SRC] = &disp_cc_mdss_dptx0_link_clk_src.clkr, + [DISP_CC_MDSS_DPTX0_LINK_DIV_CLK_SRC] = &disp_cc_mdss_dptx0_link_div_clk_src.clkr, + [DISP_CC_MDSS_DPTX0_LINK_INTF_CLK] = &disp_cc_mdss_dptx0_link_intf_clk.clkr, + [DISP_CC_MDSS_DPTX0_PIXEL0_CLK] = &disp_cc_mdss_dptx0_pixel0_clk.clkr, + [DISP_CC_MDSS_DPTX0_PIXEL0_CLK_SRC] = &disp_cc_mdss_dptx0_pixel0_clk_src.clkr, + [DISP_CC_MDSS_DPTX0_PIXEL1_CLK] = &disp_cc_mdss_dptx0_pixel1_clk.clkr, + [DISP_CC_MDSS_DPTX0_PIXEL1_CLK_SRC] = &disp_cc_mdss_dptx0_pixel1_clk_src.clkr, + [DISP_CC_MDSS_DPTX0_USB_ROUTER_LINK_INTF_CLK] = + &disp_cc_mdss_dptx0_usb_router_link_intf_clk.clkr, + [DISP_CC_MDSS_DPTX1_AUX_CLK] = &disp_cc_mdss_dptx1_aux_clk.clkr, + [DISP_CC_MDSS_DPTX1_AUX_CLK_SRC] = &disp_cc_mdss_dptx1_aux_clk_src.clkr, + [DISP_CC_MDSS_DPTX1_CRYPTO_CLK] = &disp_cc_mdss_dptx1_crypto_clk.clkr, + [DISP_CC_MDSS_DPTX1_LINK_CLK] = &disp_cc_mdss_dptx1_link_clk.clkr, + [DISP_CC_MDSS_DPTX1_LINK_CLK_SRC] = &disp_cc_mdss_dptx1_link_clk_src.clkr, + [DISP_CC_MDSS_DPTX1_LINK_DIV_CLK_SRC] = &disp_cc_mdss_dptx1_link_div_clk_src.clkr, + [DISP_CC_MDSS_DPTX1_LINK_INTF_CLK] = &disp_cc_mdss_dptx1_link_intf_clk.clkr, + [DISP_CC_MDSS_DPTX1_PIXEL0_CLK] = &disp_cc_mdss_dptx1_pixel0_clk.clkr, + [DISP_CC_MDSS_DPTX1_PIXEL0_CLK_SRC] = &disp_cc_mdss_dptx1_pixel0_clk_src.clkr, + [DISP_CC_MDSS_DPTX1_PIXEL1_CLK] = &disp_cc_mdss_dptx1_pixel1_clk.clkr, + [DISP_CC_MDSS_DPTX1_PIXEL1_CLK_SRC] = &disp_cc_mdss_dptx1_pixel1_clk_src.clkr, + [DISP_CC_MDSS_DPTX1_USB_ROUTER_LINK_INTF_CLK] = + &disp_cc_mdss_dptx1_usb_router_link_intf_clk.clkr, + [DISP_CC_MDSS_DPTX2_AUX_CLK] = &disp_cc_mdss_dptx2_aux_clk.clkr, + [DISP_CC_MDSS_DPTX2_AUX_CLK_SRC] = &disp_cc_mdss_dptx2_aux_clk_src.clkr, + [DISP_CC_MDSS_DPTX2_CRYPTO_CLK] = &disp_cc_mdss_dptx2_crypto_clk.clkr, + [DISP_CC_MDSS_DPTX2_LINK_CLK] = &disp_cc_mdss_dptx2_link_clk.clkr, + [DISP_CC_MDSS_DPTX2_LINK_CLK_SRC] = &disp_cc_mdss_dptx2_link_clk_src.clkr, + [DISP_CC_MDSS_DPTX2_LINK_DIV_CLK_SRC] = &disp_cc_mdss_dptx2_link_div_clk_src.clkr, + [DISP_CC_MDSS_DPTX2_LINK_INTF_CLK] = &disp_cc_mdss_dptx2_link_intf_clk.clkr, + [DISP_CC_MDSS_DPTX2_PIXEL0_CLK] = &disp_cc_mdss_dptx2_pixel0_clk.clkr, + [DISP_CC_MDSS_DPTX2_PIXEL0_CLK_SRC] = &disp_cc_mdss_dptx2_pixel0_clk_src.clkr, + [DISP_CC_MDSS_DPTX2_PIXEL1_CLK] = &disp_cc_mdss_dptx2_pixel1_clk.clkr, + [DISP_CC_MDSS_DPTX2_PIXEL1_CLK_SRC] = &disp_cc_mdss_dptx2_pixel1_clk_src.clkr, + [DISP_CC_MDSS_DPTX3_AUX_CLK] = &disp_cc_mdss_dptx3_aux_clk.clkr, + [DISP_CC_MDSS_DPTX3_AUX_CLK_SRC] = &disp_cc_mdss_dptx3_aux_clk_src.clkr, + [DISP_CC_MDSS_DPTX3_CRYPTO_CLK] = &disp_cc_mdss_dptx3_crypto_clk.clkr, + [DISP_CC_MDSS_DPTX3_LINK_CLK] = &disp_cc_mdss_dptx3_link_clk.clkr, + [DISP_CC_MDSS_DPTX3_LINK_CLK_SRC] = &disp_cc_mdss_dptx3_link_clk_src.clkr, + [DISP_CC_MDSS_DPTX3_LINK_DIV_CLK_SRC] = &disp_cc_mdss_dptx3_link_div_clk_src.clkr, + [DISP_CC_MDSS_DPTX3_LINK_INTF_CLK] = &disp_cc_mdss_dptx3_link_intf_clk.clkr, + [DISP_CC_MDSS_DPTX3_PIXEL0_CLK] = &disp_cc_mdss_dptx3_pixel0_clk.clkr, + [DISP_CC_MDSS_DPTX3_PIXEL0_CLK_SRC] = &disp_cc_mdss_dptx3_pixel0_clk_src.clkr, + [DISP_CC_MDSS_ESC0_CLK] = &disp_cc_mdss_esc0_clk.clkr, + [DISP_CC_MDSS_ESC0_CLK_SRC] = &disp_cc_mdss_esc0_clk_src.clkr, + [DISP_CC_MDSS_ESC1_CLK] = &disp_cc_mdss_esc1_clk.clkr, + [DISP_CC_MDSS_ESC1_CLK_SRC] = &disp_cc_mdss_esc1_clk_src.clkr, + [DISP_CC_MDSS_MDP1_CLK] = &disp_cc_mdss_mdp1_clk.clkr, + [DISP_CC_MDSS_MDP_CLK] = &disp_cc_mdss_mdp_clk.clkr, + [DISP_CC_MDSS_MDP_CLK_SRC] = &disp_cc_mdss_mdp_clk_src.clkr, + [DISP_CC_MDSS_MDP_LUT1_CLK] = &disp_cc_mdss_mdp_lut1_clk.clkr, + [DISP_CC_MDSS_MDP_LUT_CLK] = &disp_cc_mdss_mdp_lut_clk.clkr, + [DISP_CC_MDSS_NON_GDSC_AHB_CLK] = &disp_cc_mdss_non_gdsc_ahb_clk.clkr, + [DISP_CC_MDSS_PCLK0_CLK] = &disp_cc_mdss_pclk0_clk.clkr, + [DISP_CC_MDSS_PCLK0_CLK_SRC] = &disp_cc_mdss_pclk0_clk_src.clkr, + [DISP_CC_MDSS_PCLK1_CLK] = &disp_cc_mdss_pclk1_clk.clkr, + [DISP_CC_MDSS_PCLK1_CLK_SRC] = &disp_cc_mdss_pclk1_clk_src.clkr, + [DISP_CC_MDSS_PCLK2_CLK] = &disp_cc_mdss_pclk2_clk.clkr, + [DISP_CC_MDSS_PCLK2_CLK_SRC] = &disp_cc_mdss_pclk2_clk_src.clkr, + [DISP_CC_MDSS_VSYNC1_CLK] = &disp_cc_mdss_vsync1_clk.clkr, + [DISP_CC_MDSS_VSYNC_CLK] = &disp_cc_mdss_vsync_clk.clkr, + [DISP_CC_MDSS_VSYNC_CLK_SRC] = &disp_cc_mdss_vsync_clk_src.clkr, + [DISP_CC_OSC_CLK] = &disp_cc_osc_clk.clkr, + [DISP_CC_OSC_CLK_SRC] = &disp_cc_osc_clk_src.clkr, + [DISP_CC_PLL0] = &disp_cc_pll0.clkr, + [DISP_CC_PLL1] = &disp_cc_pll1.clkr, + [DISP_CC_PLL2] = &disp_cc_pll2.clkr, + [DISP_CC_SLEEP_CLK_SRC] = &disp_cc_sleep_clk_src.clkr, + [DISP_CC_XO_CLK_SRC] = &disp_cc_xo_clk_src.clkr, +}; + +static const struct qcom_reset_map disp_cc_sm8750_resets[] = { + [DISP_CC_MDSS_CORE_BCR] = { 0x8000 }, + [DISP_CC_MDSS_CORE_INT2_BCR] = { 0xa000 }, + [DISP_CC_MDSS_RSCC_BCR] = { 0xc000 }, +}; + +static struct gdsc *disp_cc_sm8750_gdscs[] = { + [MDSS_GDSC] = &mdss_gdsc, + [MDSS_INT2_GDSC] = &mdss_int2_gdsc, +}; + +static const struct regmap_config disp_cc_sm8750_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x11014, + .fast_io = true, +}; + +static struct qcom_cc_desc disp_cc_sm8750_desc = { + .config = &disp_cc_sm8750_regmap_config, + .clks = disp_cc_sm8750_clocks, + .num_clks = ARRAY_SIZE(disp_cc_sm8750_clocks), + .resets = disp_cc_sm8750_resets, + .num_resets = ARRAY_SIZE(disp_cc_sm8750_resets), + .gdscs = disp_cc_sm8750_gdscs, + .num_gdscs = ARRAY_SIZE(disp_cc_sm8750_gdscs), +}; + +static const struct of_device_id disp_cc_sm8750_match_table[] = { + { .compatible = "qcom,sm8750-dispcc" }, + { } +}; +MODULE_DEVICE_TABLE(of, disp_cc_sm8750_match_table); + +static int disp_cc_sm8750_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + int ret; + + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return ret; + + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) + return ret; + + regmap = qcom_cc_map(pdev, &disp_cc_sm8750_desc); + if (IS_ERR(regmap)) { + ret = PTR_ERR(regmap); + goto err_put_rpm; + } + + clk_taycan_elu_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config); + clk_taycan_elu_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config); + clk_pongo_elu_pll_configure(&disp_cc_pll2, regmap, &disp_cc_pll2_config); + + /* Enable clock gating for MDP clocks */ + regmap_update_bits(regmap, DISP_CC_MISC_CMD, 0x10, 0x10); + + /* Keep some clocks always-on */ + qcom_branch_set_clk_en(regmap, 0xe07c); /* DISP_CC_SLEEP_CLK */ + qcom_branch_set_clk_en(regmap, 0xe05c); /* DISP_CC_XO_CLK */ + qcom_branch_set_clk_en(regmap, 0xc00c); /* DISP_CC_MDSS_RSCC_AHB_CLK */ + qcom_branch_set_clk_en(regmap, 0xc008); /* DISP_CC_MDSS_RSCC_VSYNC_CLK */ + + ret = qcom_cc_really_probe(&pdev->dev, &disp_cc_sm8750_desc, regmap); + if (ret) + goto err_put_rpm; + + pm_runtime_put(&pdev->dev); + + return 0; + +err_put_rpm: + pm_runtime_put_sync(&pdev->dev); + + return ret; +} + +static struct platform_driver disp_cc_sm8750_driver = { + .probe = disp_cc_sm8750_probe, + .driver = { + .name = "disp_cc-sm8750", + .of_match_table = disp_cc_sm8750_match_table, + }, +}; + +module_platform_driver(disp_cc_sm8750_driver); + +MODULE_DESCRIPTION("QTI DISPCC SM8750 Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/qcom/gcc-ipq5424.c b/drivers/clk/qcom/gcc-ipq5424.c index 88a7d5b2e751..d5b218b76e29 100644 --- a/drivers/clk/qcom/gcc-ipq5424.c +++ b/drivers/clk/qcom/gcc-ipq5424.c @@ -5,6 +5,7 @@ */ #include +#include #include #include #include @@ -12,6 +13,7 @@ #include #include +#include #include #include "clk-alpha-pll.h" @@ -325,6 +327,24 @@ static struct clk_rcg2 gcc_xo_clk_src = { }, }; +static struct clk_branch gcc_xo_clk = { + .halt_reg = 0x34018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x34018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_xo_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_xo_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + static struct clk_fixed_factor gcc_xo_div4_clk_src = { .mult = 1, .div = 4, @@ -1097,24 +1117,6 @@ static struct clk_branch gcc_adss_pwm_clk = { }, }; -static struct clk_branch gcc_apss_dbg_clk = { - .halt_reg = 0x2402c, - .halt_check = BRANCH_HALT_VOTED, - .clkr = { - .enable_reg = 0x2402c, - .enable_mask = BIT(0), - .hw.init = &(const struct clk_init_data) { - .name = "gcc_apss_dbg_clk", - .parent_hws = (const struct clk_hw*[]) { - &gcc_qdss_dap_sync_clk_src.hw - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, - .ops = &clk_branch2_ops, - }, - }, -}; - static struct clk_branch gcc_cnoc_pcie0_1lane_s_clk = { .halt_reg = 0x31088, .halt_check = BRANCH_HALT, @@ -2785,7 +2787,6 @@ static struct clk_branch gcc_pcie3_rchng_clk = { static struct clk_regmap *gcc_ipq5424_clocks[] = { [GCC_ADSS_PWM_CLK] = &gcc_adss_pwm_clk.clkr, [GCC_ADSS_PWM_CLK_SRC] = &gcc_adss_pwm_clk_src.clkr, - [GCC_APSS_DBG_CLK] = &gcc_apss_dbg_clk.clkr, [GCC_CNOC_PCIE0_1LANE_S_CLK] = &gcc_cnoc_pcie0_1lane_s_clk.clkr, [GCC_CNOC_PCIE1_1LANE_S_CLK] = &gcc_cnoc_pcie1_1lane_s_clk.clkr, [GCC_CNOC_PCIE2_2LANE_S_CLK] = &gcc_cnoc_pcie2_2lane_s_clk.clkr, @@ -2920,6 +2921,7 @@ static struct clk_regmap *gcc_ipq5424_clocks[] = { [GCC_QPIC_CLK_SRC] = &gcc_qpic_clk_src.clkr, [GCC_QPIC_AHB_CLK] = &gcc_qpic_ahb_clk.clkr, [GCC_XO_CLK_SRC] = &gcc_xo_clk_src.clkr, + [GCC_XO_CLK] = &gcc_xo_clk.clkr, [GCC_QDSS_DAP_CLK] = &gcc_qdss_dap_clk.clkr, [GCC_QDSS_AT_CLK] = &gcc_qdss_at_clk.clkr, [GPLL0] = &gpll0.clkr, @@ -3230,6 +3232,20 @@ static const struct qcom_reset_map gcc_ipq5424_resets[] = { [GCC_QUSB2_1_PHY_BCR] = { 0x3C030, 0 }, }; +#define IPQ_APPS_ID 5424 /* some unique value */ + +static const struct qcom_icc_hws_data icc_ipq5424_hws[] = { + { MASTER_ANOC_PCIE0, SLAVE_ANOC_PCIE0, GCC_ANOC_PCIE0_1LANE_M_CLK }, + { MASTER_CNOC_PCIE0, SLAVE_CNOC_PCIE0, GCC_CNOC_PCIE0_1LANE_S_CLK }, + { MASTER_ANOC_PCIE1, SLAVE_ANOC_PCIE1, GCC_ANOC_PCIE1_1LANE_M_CLK }, + { MASTER_CNOC_PCIE1, SLAVE_CNOC_PCIE1, GCC_CNOC_PCIE1_1LANE_S_CLK }, + { MASTER_ANOC_PCIE2, SLAVE_ANOC_PCIE2, GCC_ANOC_PCIE2_2LANE_M_CLK }, + { MASTER_CNOC_PCIE2, SLAVE_CNOC_PCIE2, GCC_CNOC_PCIE2_2LANE_S_CLK }, + { MASTER_ANOC_PCIE3, SLAVE_ANOC_PCIE3, GCC_ANOC_PCIE3_2LANE_M_CLK }, + { MASTER_CNOC_PCIE3, SLAVE_CNOC_PCIE3, GCC_CNOC_PCIE3_2LANE_S_CLK }, + { MASTER_CNOC_USB, SLAVE_CNOC_USB, GCC_CNOC_USB_CLK }, +}; + static const struct of_device_id gcc_ipq5424_match_table[] = { { .compatible = "qcom,ipq5424-gcc" }, { } @@ -3260,6 +3276,8 @@ static const struct qcom_cc_desc gcc_ipq5424_desc = { .num_resets = ARRAY_SIZE(gcc_ipq5424_resets), .clk_hws = gcc_ipq5424_hws, .num_clk_hws = ARRAY_SIZE(gcc_ipq5424_hws), + .icc_hws = icc_ipq5424_hws, + .num_icc_hws = ARRAY_SIZE(icc_ipq5424_hws), }; static int gcc_ipq5424_probe(struct platform_device *pdev) @@ -3272,6 +3290,7 @@ static struct platform_driver gcc_ipq5424_driver = { .driver = { .name = "qcom,gcc-ipq5424", .of_match_table = gcc_ipq5424_match_table, + .sync_state = icc_sync_state, }, }; diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c index ab0f7fc665a9..d861191b0c85 100644 --- a/drivers/clk/qcom/gcc-ipq6018.c +++ b/drivers/clk/qcom/gcc-ipq6018.c @@ -4194,10 +4194,9 @@ static const struct alpha_pll_config ubi32_pll_config = { .test_ctl_hi_val = 0x4000, }; +/* 1200 MHz configuration */ static const struct alpha_pll_config nss_crypto_pll_config = { .l = 0x32, - .alpha = 0x0, - .alpha_hi = 0x0, .config_ctl_val = 0x4001055b, .main_output_mask = BIT(0), .pre_div_val = 0x0, @@ -4206,7 +4205,6 @@ static const struct alpha_pll_config nss_crypto_pll_config = { .post_div_mask = GENMASK(11, 8), .vco_mask = GENMASK(21, 20), .vco_val = 0x0, - .alpha_en_mask = BIT(24), }; static struct clk_hw *gcc_ipq6018_hws[] = { diff --git a/drivers/clk/qcom/gcc-mdm9607.c b/drivers/clk/qcom/gcc-mdm9607.c index 6e6068b168e6..07f1b78d737a 100644 --- a/drivers/clk/qcom/gcc-mdm9607.c +++ b/drivers/clk/qcom/gcc-mdm9607.c @@ -535,7 +535,7 @@ static struct clk_rcg2 blsp1_uart5_apps_clk_src = { }; static struct clk_rcg2 blsp1_uart6_apps_clk_src = { - .cmd_rcgr = 0x6044, + .cmd_rcgr = 0x7044, .mnd_width = 16, .hid_width = 5, .parent_map = gcc_xo_gpll0_map, diff --git a/drivers/clk/qcom/gcc-qcs615.c b/drivers/clk/qcom/gcc-qcs615.c new file mode 100644 index 000000000000..9695446bc2a3 --- /dev/null +++ b/drivers/clk/qcom/gcc-qcs615.c @@ -0,0 +1,3034 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "common.h" +#include "gdsc.h" +#include "reset.h" + +enum { + DT_BI_TCXO, + DT_BI_TCXO_AO, + DT_SLEEP_CLK, +}; + +enum { + P_BI_TCXO, + P_GPLL0_OUT_AUX2_DIV, + P_GPLL0_OUT_MAIN, + P_GPLL3_OUT_MAIN, + P_GPLL3_OUT_MAIN_DIV, + P_GPLL4_OUT_MAIN, + P_GPLL6_OUT_MAIN, + P_GPLL7_OUT_MAIN, + P_GPLL8_OUT_MAIN, + P_SLEEP_CLK, +}; + +static struct clk_alpha_pll gpll0 = { + .offset = 0x0, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpll0", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +/* Fixed divider clock of GPLL0 instead of PLL normal postdiv */ +static struct clk_fixed_factor gpll0_out_aux2_div = { + .mult = 1, + .div = 2, + .hw.init = &(struct clk_init_data) { + .name = "gpll0_out_aux2_div", + .parent_data = &(const struct clk_parent_data) { + .hw = &gpll0.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_alpha_pll gpll3 = { + .offset = 0x3000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(3), + .hw.init = &(const struct clk_init_data) { + .name = "gpll3", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +/* Fixed divider clock of GPLL3 instead of PLL normal postdiv */ +static struct clk_fixed_factor gpll3_out_aux2_div = { + .mult = 1, + .div = 2, + .hw.init = &(struct clk_init_data) { + .name = "gpll3_out_aux2_div", + .parent_data = &(const struct clk_parent_data) { + .hw = &gpll3.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_alpha_pll gpll4 = { + .offset = 0x76000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(4), + .hw.init = &(const struct clk_init_data) { + .name = "gpll4", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static struct clk_alpha_pll gpll6 = { + .offset = 0x13000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(6), + .hw.init = &(const struct clk_init_data) { + .name = "gpll6", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct clk_div_table post_div_table_gpll6_out_main[] = { + { 0x1, 2 }, + { } +}; + +static struct clk_alpha_pll_postdiv gpll6_out_main = { + .offset = 0x13000, + .post_div_shift = 8, + .post_div_table = post_div_table_gpll6_out_main, + .num_post_div = ARRAY_SIZE(post_div_table_gpll6_out_main), + .width = 4, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gpll6_out_main", + .parent_hws = (const struct clk_hw*[]) { + &gpll6.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_ops, + }, +}; + +static struct clk_alpha_pll gpll7 = { + .offset = 0x1a000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(7), + .hw.init = &(const struct clk_init_data) { + .name = "gpll7", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static struct clk_alpha_pll gpll8 = { + .offset = 0x1b000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(8), + .hw.init = &(const struct clk_init_data) { + .name = "gpll8", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct clk_div_table post_div_table_gpll8_out_main[] = { + { 0x1, 2 }, + { } +}; + +static struct clk_alpha_pll_postdiv gpll8_out_main = { + .offset = 0x1b000, + .post_div_shift = 8, + .post_div_table = post_div_table_gpll8_out_main, + .num_post_div = ARRAY_SIZE(post_div_table_gpll8_out_main), + .width = 4, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gpll8_out_main", + .parent_hws = (const struct clk_hw*[]) { + &gpll8.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_ops, + }, +}; + +static const struct parent_map gcc_parent_map_0[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL0_OUT_AUX2_DIV, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_0[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_aux2_div.hw }, +}; + +static const struct clk_parent_data gcc_parent_data_0_ao[] = { + { .index = DT_BI_TCXO_AO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_1[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL6_OUT_MAIN, 2 }, + { P_GPLL0_OUT_AUX2_DIV, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_1[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll6_out_main.clkr.hw }, + { .hw = &gpll0_out_aux2_div.hw }, +}; + +static const struct parent_map gcc_parent_map_2[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_SLEEP_CLK, 5 }, + { P_GPLL0_OUT_AUX2_DIV, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_2[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .index = DT_SLEEP_CLK }, + { .hw = &gpll0_out_aux2_div.hw }, +}; + +static const struct parent_map gcc_parent_map_3[] = { + { P_BI_TCXO, 0 }, + { P_SLEEP_CLK, 5 }, +}; + +static const struct clk_parent_data gcc_parent_data_3[] = { + { .index = DT_BI_TCXO }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_parent_map_4[] = { + { P_BI_TCXO, 0 }, +}; + +static const struct clk_parent_data gcc_parent_data_4[] = { + { .index = DT_BI_TCXO }, +}; + +static const struct parent_map gcc_parent_map_5[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL7_OUT_MAIN, 3 }, + { P_GPLL4_OUT_MAIN, 5 }, + { P_GPLL0_OUT_AUX2_DIV, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_5[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll7.clkr.hw }, + { .hw = &gpll4.clkr.hw }, + { .hw = &gpll0_out_aux2_div.hw }, +}; + +static const struct parent_map gcc_parent_map_6[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL7_OUT_MAIN, 3 }, + { P_GPLL0_OUT_AUX2_DIV, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_6[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll7.clkr.hw }, + { .hw = &gpll0_out_aux2_div.hw }, +}; + +static const struct parent_map gcc_parent_map_7[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL3_OUT_MAIN_DIV, 4 }, + { P_GPLL0_OUT_AUX2_DIV, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_7[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll3_out_aux2_div.hw }, + { .hw = &gpll0_out_aux2_div.hw }, +}; + +static const struct parent_map gcc_parent_map_8[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL8_OUT_MAIN, 2 }, + { P_GPLL4_OUT_MAIN, 5 }, + { P_GPLL0_OUT_AUX2_DIV, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_8[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll8_out_main.clkr.hw }, + { .hw = &gpll4.clkr.hw }, + { .hw = &gpll0_out_aux2_div.hw }, +}; + +static const struct parent_map gcc_parent_map_9[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL3_OUT_MAIN, 4 }, +}; + +static const struct clk_parent_data gcc_parent_data_9[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll3.clkr.hw }, +}; + +static const struct freq_tbl ftbl_gcc_cpuss_ahb_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_cpuss_ahb_clk_src = { + .cmd_rcgr = 0x48014, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_cpuss_ahb_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_cpuss_ahb_clk_src", + .parent_data = gcc_parent_data_0_ao, + .num_parents = ARRAY_SIZE(gcc_parent_data_0_ao), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_emac_ptp_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(50000000, P_GPLL0_OUT_AUX2_DIV, 6, 0, 0), + F(75000000, P_GPLL0_OUT_AUX2_DIV, 4, 0, 0), + F(125000000, P_GPLL7_OUT_MAIN, 4, 0, 0), + F(250000000, P_GPLL7_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_emac_ptp_clk_src = { + .cmd_rcgr = 0x6038, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_5, + .freq_tbl = ftbl_gcc_emac_ptp_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_emac_ptp_clk_src", + .parent_data = gcc_parent_data_5, + .num_parents = ARRAY_SIZE(gcc_parent_data_5), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_emac_rgmii_clk_src[] = { + F(2500000, P_BI_TCXO, 1, 25, 192), + F(5000000, P_BI_TCXO, 1, 25, 96), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(25000000, P_GPLL0_OUT_AUX2_DIV, 12, 0, 0), + F(50000000, P_GPLL0_OUT_AUX2_DIV, 6, 0, 0), + F(75000000, P_GPLL0_OUT_AUX2_DIV, 4, 0, 0), + F(125000000, P_GPLL7_OUT_MAIN, 4, 0, 0), + F(250000000, P_GPLL7_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_emac_rgmii_clk_src = { + .cmd_rcgr = 0x601c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_6, + .freq_tbl = ftbl_gcc_emac_rgmii_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_emac_rgmii_clk_src", + .parent_data = gcc_parent_data_6, + .num_parents = ARRAY_SIZE(gcc_parent_data_6), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_gp1_clk_src[] = { + F(25000000, P_GPLL0_OUT_AUX2_DIV, 12, 0, 0), + F(50000000, P_GPLL0_OUT_AUX2_DIV, 6, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_gp1_clk_src = { + .cmd_rcgr = 0x64004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_gp1_clk_src", + .parent_data = gcc_parent_data_2, + .num_parents = ARRAY_SIZE(gcc_parent_data_2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_gp2_clk_src = { + .cmd_rcgr = 0x65004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_gp2_clk_src", + .parent_data = gcc_parent_data_2, + .num_parents = ARRAY_SIZE(gcc_parent_data_2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_gp3_clk_src = { + .cmd_rcgr = 0x66004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_gp3_clk_src", + .parent_data = gcc_parent_data_2, + .num_parents = ARRAY_SIZE(gcc_parent_data_2), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcie_0_aux_clk_src[] = { + F(9600000, P_BI_TCXO, 2, 0, 0), + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcie_0_aux_clk_src = { + .cmd_rcgr = 0x6b02c, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_aux_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcie_phy_refgen_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcie_phy_refgen_clk_src = { + .cmd_rcgr = 0x6f014, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_phy_refgen_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_phy_refgen_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pdm2_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(60000000, P_GPLL0_OUT_MAIN, 10, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pdm2_clk_src = { + .cmd_rcgr = 0x33010, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pdm2_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pdm2_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_qspi_core_clk_src[] = { + F(60000000, P_GPLL0_OUT_AUX2_DIV, 5, 0, 0), + F(133250000, P_GPLL3_OUT_MAIN_DIV, 4, 0, 0), + F(266500000, P_GPLL3_OUT_MAIN_DIV, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_qspi_core_clk_src = { + .cmd_rcgr = 0x4b008, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_7, + .freq_tbl = ftbl_gcc_qspi_core_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qspi_core_clk_src", + .parent_data = gcc_parent_data_7, + .num_parents = ARRAY_SIZE(gcc_parent_data_7), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_qupv3_wrap0_s0_clk_src[] = { + F(7372800, P_GPLL0_OUT_AUX2_DIV, 1, 384, 15625), + F(14745600, P_GPLL0_OUT_AUX2_DIV, 1, 768, 15625), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(29491200, P_GPLL0_OUT_AUX2_DIV, 1, 1536, 15625), + F(32000000, P_GPLL0_OUT_AUX2_DIV, 1, 8, 75), + F(48000000, P_GPLL0_OUT_AUX2_DIV, 1, 4, 25), + F(64000000, P_GPLL0_OUT_AUX2_DIV, 1, 16, 75), + F(75000000, P_GPLL0_OUT_AUX2_DIV, 4, 0, 0), + F(80000000, P_GPLL0_OUT_AUX2_DIV, 1, 4, 15), + F(96000000, P_GPLL0_OUT_AUX2_DIV, 1, 8, 25), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), + F(102400000, P_GPLL0_OUT_AUX2_DIV, 1, 128, 375), + F(112000000, P_GPLL0_OUT_AUX2_DIV, 1, 28, 75), + F(117964800, P_GPLL0_OUT_AUX2_DIV, 1, 6144, 15625), + F(120000000, P_GPLL0_OUT_AUX2_DIV, 2.5, 0, 0), + F(128000000, P_GPLL6_OUT_MAIN, 3, 0, 0), + { } +}; + +static struct clk_init_data gcc_qupv3_wrap0_s0_clk_src_init = { + .name = "gcc_qupv3_wrap0_s0_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s0_clk_src = { + .cmd_rcgr = 0x17148, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s0_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s1_clk_src_init = { + .name = "gcc_qupv3_wrap0_s1_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s1_clk_src = { + .cmd_rcgr = 0x17278, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s1_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s2_clk_src_init = { + .name = "gcc_qupv3_wrap0_s2_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s2_clk_src = { + .cmd_rcgr = 0x173a8, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s2_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s3_clk_src_init = { + .name = "gcc_qupv3_wrap0_s3_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s3_clk_src = { + .cmd_rcgr = 0x174d8, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s3_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s4_clk_src_init = { + .name = "gcc_qupv3_wrap0_s4_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s4_clk_src = { + .cmd_rcgr = 0x17608, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s4_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s5_clk_src_init = { + .name = "gcc_qupv3_wrap0_s5_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s5_clk_src = { + .cmd_rcgr = 0x17738, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s5_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s0_clk_src_init = { + .name = "gcc_qupv3_wrap1_s0_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s0_clk_src = { + .cmd_rcgr = 0x18148, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s0_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s1_clk_src_init = { + .name = "gcc_qupv3_wrap1_s1_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s1_clk_src = { + .cmd_rcgr = 0x18278, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s1_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s2_clk_src_init = { + .name = "gcc_qupv3_wrap1_s2_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s2_clk_src = { + .cmd_rcgr = 0x183a8, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s2_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s3_clk_src_init = { + .name = "gcc_qupv3_wrap1_s3_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s3_clk_src = { + .cmd_rcgr = 0x184d8, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s3_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s4_clk_src_init = { + .name = "gcc_qupv3_wrap1_s4_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s4_clk_src = { + .cmd_rcgr = 0x18608, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s4_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s5_clk_src_init = { + .name = "gcc_qupv3_wrap1_s5_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s5_clk_src = { + .cmd_rcgr = 0x18738, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s5_clk_src_init, +}; + +static const struct freq_tbl ftbl_gcc_sdcc1_apps_clk_src[] = { + F(144000, P_BI_TCXO, 16, 3, 25), + F(400000, P_BI_TCXO, 12, 1, 4), + F(20000000, P_GPLL0_OUT_AUX2_DIV, 5, 1, 3), + F(25000000, P_GPLL0_OUT_AUX2_DIV, 6, 1, 2), + F(50000000, P_GPLL0_OUT_AUX2_DIV, 6, 0, 0), + F(100000000, P_GPLL0_OUT_AUX2_DIV, 3, 0, 0), + F(192000000, P_GPLL6_OUT_MAIN, 2, 0, 0), + F(384000000, P_GPLL6_OUT_MAIN, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { + .cmd_rcgr = 0x12028, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_sdcc1_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc1_apps_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_floor_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_sdcc1_ice_core_clk_src[] = { + F(75000000, P_GPLL0_OUT_AUX2_DIV, 4, 0, 0), + F(150000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = { + .cmd_rcgr = 0x12010, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_sdcc1_ice_core_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc1_ice_core_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_floor_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_sdcc2_apps_clk_src[] = { + F(400000, P_BI_TCXO, 12, 1, 4), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(25000000, P_GPLL0_OUT_AUX2_DIV, 12, 0, 0), + F(50000000, P_GPLL0_OUT_AUX2_DIV, 6, 0, 0), + F(100000000, P_GPLL0_OUT_AUX2_DIV, 3, 0, 0), + F(202000000, P_GPLL8_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { + .cmd_rcgr = 0x1400c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_8, + .freq_tbl = ftbl_gcc_sdcc2_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc2_apps_clk_src", + .parent_data = gcc_parent_data_8, + .num_parents = ARRAY_SIZE(gcc_parent_data_8), + .ops = &clk_rcg2_floor_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_ufs_phy_axi_clk_src[] = { + F(25000000, P_GPLL0_OUT_AUX2_DIV, 12, 0, 0), + F(50000000, P_GPLL0_OUT_AUX2_DIV, 6, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + F(240000000, P_GPLL0_OUT_MAIN, 2.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_ufs_phy_axi_clk_src = { + .cmd_rcgr = 0x77020, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_ufs_phy_axi_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_axi_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_ufs_phy_ice_core_clk_src[] = { + F(37500000, P_GPLL0_OUT_AUX2_DIV, 8, 0, 0), + F(75000000, P_GPLL0_OUT_AUX2_DIV, 4, 0, 0), + F(150000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_ufs_phy_ice_core_clk_src = { + .cmd_rcgr = 0x77048, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_ufs_phy_ice_core_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_ice_core_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_ufs_phy_phy_aux_clk_src = { + .cmd_rcgr = 0x7707c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_4, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_phy_aux_clk_src", + .parent_data = gcc_parent_data_4, + .num_parents = ARRAY_SIZE(gcc_parent_data_4), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_ufs_phy_unipro_core_clk_src[] = { + F(37500000, P_GPLL0_OUT_AUX2_DIV, 8, 0, 0), + F(75000000, P_GPLL0_OUT_MAIN, 8, 0, 0), + F(150000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_ufs_phy_unipro_core_clk_src = { + .cmd_rcgr = 0x77060, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_ufs_phy_unipro_core_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_unipro_core_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb20_sec_master_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(60000000, P_GPLL0_OUT_MAIN, 10, 0, 0), + F(120000000, P_GPLL0_OUT_MAIN, 5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_usb20_sec_master_clk_src = { + .cmd_rcgr = 0xa601c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_usb20_sec_master_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb20_sec_master_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_usb20_sec_mock_utmi_clk_src = { + .cmd_rcgr = 0xa6034, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pdm2_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb20_sec_mock_utmi_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb2_sec_phy_aux_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_usb2_sec_phy_aux_clk_src = { + .cmd_rcgr = 0xa6060, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_usb2_sec_phy_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb2_sec_phy_aux_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb30_prim_master_clk_src[] = { + F(66666667, P_GPLL0_OUT_AUX2_DIV, 4.5, 0, 0), + F(133333333, P_GPLL0_OUT_MAIN, 4.5, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + F(240000000, P_GPLL0_OUT_MAIN, 2.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_usb30_prim_master_clk_src = { + .cmd_rcgr = 0xf01c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_usb30_prim_master_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_master_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb30_prim_mock_utmi_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(20000000, P_GPLL0_OUT_AUX2_DIV, 15, 0, 0), + F(40000000, P_GPLL0_OUT_AUX2_DIV, 7.5, 0, 0), + F(60000000, P_GPLL0_OUT_MAIN, 10, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_usb30_prim_mock_utmi_clk_src = { + .cmd_rcgr = 0xf034, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_usb30_prim_mock_utmi_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_mock_utmi_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_usb3_prim_phy_aux_clk_src = { + .cmd_rcgr = 0xf060, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_usb2_sec_phy_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_phy_aux_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_vsensor_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(400000000, P_GPLL0_OUT_MAIN, 1.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_vsensor_clk_src = { + .cmd_rcgr = 0x7a018, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_9, + .freq_tbl = ftbl_gcc_vsensor_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_vsensor_clk_src", + .parent_data = gcc_parent_data_9, + .num_parents = ARRAY_SIZE(gcc_parent_data_9), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_aggre_ufs_phy_axi_clk = { + .halt_reg = 0x770c0, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x770c0, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x770c0, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_aggre_ufs_phy_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_aggre_usb2_sec_axi_clk = { + .halt_reg = 0xa6084, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xa6084, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_aggre_usb2_sec_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb20_sec_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_aggre_usb3_prim_axi_clk = { + .halt_reg = 0xf07c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xf07c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_aggre_usb3_prim_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb30_prim_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ahb2phy_east_clk = { + .halt_reg = 0x6a008, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6a008, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x6a008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ahb2phy_east_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ahb2phy_west_clk = { + .halt_reg = 0x6a004, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6a004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x6a004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ahb2phy_west_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_boot_rom_ahb_clk = { + .halt_reg = 0x38004, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x38004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(10), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_boot_rom_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_camera_hf_axi_clk = { + .halt_reg = 0xb030, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xb030, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_camera_hf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ce1_ahb_clk = { + .halt_reg = 0x4100c, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x4100c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(3), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ce1_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ce1_axi_clk = { + .halt_reg = 0x41008, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(4), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ce1_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ce1_clk = { + .halt_reg = 0x41004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(5), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ce1_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cfg_noc_usb2_sec_axi_clk = { + .halt_reg = 0xa609c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xa609c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_cfg_noc_usb2_sec_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb20_sec_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cfg_noc_usb3_prim_axi_clk = { + .halt_reg = 0xf078, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xf078, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_cfg_noc_usb3_prim_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb30_prim_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cpuss_ahb_clk = { + .halt_reg = 0x48000, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(21), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_cpuss_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_cpuss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ddrss_gpu_axi_clk = { + .halt_reg = 0x71154, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x71154, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ddrss_gpu_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_disp_gpll0_div_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(20), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_disp_gpll0_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gpll0_out_aux2_div.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_disp_hf_axi_clk = { + .halt_reg = 0xb038, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xb038, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_disp_hf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_emac_axi_clk = { + .halt_reg = 0x6010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x6010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_emac_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_emac_ptp_clk = { + .halt_reg = 0x6034, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x6034, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_emac_ptp_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_emac_ptp_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_emac_rgmii_clk = { + .halt_reg = 0x6018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x6018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_emac_rgmii_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_emac_rgmii_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_emac_slv_ahb_clk = { + .halt_reg = 0x6014, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x6014, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x6014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_emac_slv_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp1_clk = { + .halt_reg = 0x64000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x64000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gp1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gp1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp2_clk = { + .halt_reg = 0x65000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x65000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gp2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gp2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp3_clk = { + .halt_reg = 0x66000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x66000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gp3_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gp3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_gpll0_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(15), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpu_gpll0_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gpll0.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_gpll0_div_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(16), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpu_gpll0_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gpll0_out_aux2_div.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_iref_clk = { + .halt_reg = 0x8c010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8c010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpu_iref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_memnoc_gfx_clk = { + .halt_reg = 0x7100c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x7100c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpu_memnoc_gfx_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_snoc_dvm_gfx_clk = { + .halt_reg = 0x71018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x71018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpu_snoc_dvm_gfx_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie0_phy_refgen_clk = { + .halt_reg = 0x6f02c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x6f02c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie0_phy_refgen_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie_phy_refgen_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_aux_clk = { + .halt_reg = 0x6b020, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(3), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie_0_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_cfg_ahb_clk = { + .halt_reg = 0x6b01c, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6b01c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(2), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_cfg_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_clkref_clk = { + .halt_reg = 0x8c00c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8c00c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_mstr_axi_clk = { + .halt_reg = 0x6b018, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(1), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_mstr_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_pipe_clk = { + .halt_reg = 0x6b024, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(4), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_pipe_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_slv_axi_clk = { + .halt_reg = 0x6b014, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6b014, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_slv_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_slv_q2a_axi_clk = { + .halt_reg = 0x6b010, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(5), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_slv_q2a_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_phy_aux_clk = { + .halt_reg = 0x6f004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x6f004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_phy_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie_0_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pdm2_clk = { + .halt_reg = 0x3300c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3300c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pdm2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pdm2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pdm_ahb_clk = { + .halt_reg = 0x33004, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x33004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x33004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pdm_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pdm_xo4_clk = { + .halt_reg = 0x33008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x33008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pdm_xo4_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_prng_ahb_clk = { + .halt_reg = 0x34004, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x34004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(13), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_prng_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_camera_nrt_ahb_clk = { + .halt_reg = 0xb018, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0xb018, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0xb018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_camera_nrt_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_disp_ahb_clk = { + .halt_reg = 0xb020, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0xb020, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0xb020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_disp_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_pcie_ahb_clk = { + .halt_reg = 0x6b044, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6b044, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(28), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_pcie_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_video_vcodec_ahb_clk = { + .halt_reg = 0xb014, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0xb014, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0xb014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_video_vcodec_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qspi_cnoc_periph_ahb_clk = { + .halt_reg = 0x4b000, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4b000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qspi_cnoc_periph_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qspi_core_clk = { + .halt_reg = 0x4b004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4b004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qspi_core_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qspi_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_core_2x_clk = { + .halt_reg = 0x17014, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(9), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap0_core_2x_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_core_clk = { + .halt_reg = 0x1700c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(8), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap0_core_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s0_clk = { + .halt_reg = 0x17144, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(10), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap0_s0_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap0_s0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s1_clk = { + .halt_reg = 0x17274, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(11), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap0_s1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap0_s1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s2_clk = { + .halt_reg = 0x173a4, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(12), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap0_s2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap0_s2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s3_clk = { + .halt_reg = 0x174d4, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(13), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap0_s3_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap0_s3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s4_clk = { + .halt_reg = 0x17604, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(14), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap0_s4_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap0_s4_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s5_clk = { + .halt_reg = 0x17734, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(15), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap0_s5_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap0_s5_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_core_2x_clk = { + .halt_reg = 0x18014, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(18), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_core_2x_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_core_clk = { + .halt_reg = 0x1800c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(19), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_core_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s0_clk = { + .halt_reg = 0x18144, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(22), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s0_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s1_clk = { + .halt_reg = 0x18274, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(23), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s2_clk = { + .halt_reg = 0x183a4, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(24), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s3_clk = { + .halt_reg = 0x184d4, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(25), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s3_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s4_clk = { + .halt_reg = 0x18604, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(26), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s4_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s4_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s5_clk = { + .halt_reg = 0x18734, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(27), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s5_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s5_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_0_m_ahb_clk = { + .halt_reg = 0x17004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(6), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_0_m_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_0_s_ahb_clk = { + .halt_reg = 0x17008, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x17008, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(7), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_0_s_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_1_m_ahb_clk = { + .halt_reg = 0x18004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(20), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_1_m_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_1_s_ahb_clk = { + .halt_reg = 0x18008, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x18008, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(21), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_1_s_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_rx1_usb2_clkref_clk = { + .halt_reg = 0x8c030, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8c030, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_rx1_usb2_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_rx3_usb2_clkref_clk = { + .halt_reg = 0x8c038, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x8c038, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_rx3_usb2_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc1_ahb_clk = { + .halt_reg = 0x12008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x12008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc1_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc1_apps_clk = { + .halt_reg = 0x12004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x12004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc1_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sdcc1_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc1_ice_core_clk = { + .halt_reg = 0x1200c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1200c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc1_ice_core_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sdcc1_ice_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc2_ahb_clk = { + .halt_reg = 0x14008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x14008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc2_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc2_apps_clk = { + .halt_reg = 0x14004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x14004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc2_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sdcc2_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sys_noc_cpuss_ahb_clk = { + .halt_reg = 0x4819c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sys_noc_cpuss_ahb_clk", + .parent_data = &(const struct clk_parent_data) { + .hw = &gcc_cpuss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_card_clkref_clk = { + .halt_reg = 0x8c004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x8c004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_card_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_mem_clkref_clk = { + .halt_reg = 0x8c000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8c000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_mem_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_ahb_clk = { + .halt_reg = 0x77014, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x77014, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_axi_clk = { + .halt_reg = 0x77010, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77010, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_ice_core_clk = { + .halt_reg = 0x77044, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77044, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77044, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_ice_core_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_ice_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_phy_aux_clk = { + .halt_reg = 0x77078, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77078, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77078, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_phy_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_rx_symbol_0_clk = { + .halt_reg = 0x7701c, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x7701c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_rx_symbol_0_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_tx_symbol_0_clk = { + .halt_reg = 0x77018, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x77018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_tx_symbol_0_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_unipro_core_clk = { + .halt_reg = 0x77040, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77040, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77040, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_unipro_core_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_unipro_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb20_sec_master_clk = { + .halt_reg = 0xa6010, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xa6010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb20_sec_master_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb20_sec_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb20_sec_mock_utmi_clk = { + .halt_reg = 0xa6018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xa6018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb20_sec_mock_utmi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb20_sec_mock_utmi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb20_sec_sleep_clk = { + .halt_reg = 0xa6014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xa6014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb20_sec_sleep_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb2_prim_clkref_clk = { + .halt_reg = 0x8c028, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x8c028, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb2_prim_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb2_sec_clkref_clk = { + .halt_reg = 0x8c018, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x8c018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb2_sec_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb2_sec_phy_aux_clk = { + .halt_reg = 0xa6050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xa6050, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb2_sec_phy_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb2_sec_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb2_sec_phy_com_aux_clk = { + .halt_reg = 0xa6054, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xa6054, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb2_sec_phy_com_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb2_sec_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb2_sec_phy_pipe_clk = { + .halt_reg = 0xa6058, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0xa6058, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb2_sec_phy_pipe_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb30_prim_master_clk = { + .halt_reg = 0xf010, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xf010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_master_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb30_prim_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb30_prim_mock_utmi_clk = { + .halt_reg = 0xf018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xf018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_mock_utmi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb30_prim_mock_utmi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb30_prim_sleep_clk = { + .halt_reg = 0xf014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xf014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_sleep_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_clkref_clk = { + .halt_reg = 0x8c014, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x8c014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_phy_aux_clk = { + .halt_reg = 0xf050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xf050, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_phy_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb3_prim_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_phy_com_aux_clk = { + .halt_reg = 0xf054, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xf054, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_phy_com_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb3_prim_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_phy_pipe_clk = { + .halt_reg = 0xf058, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0xf058, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_phy_pipe_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_sec_clkref_clk = { + .halt_reg = 0x8c008, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x8c008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_sec_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_video_axi0_clk = { + .halt_reg = 0xb024, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xb024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_video_axi0_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_hw *gcc_qcs615_hws[] = { + [GPLL0_OUT_AUX2_DIV] = &gpll0_out_aux2_div.hw, + [GPLL3_OUT_AUX2_DIV] = &gpll3_out_aux2_div.hw, +}; + +static struct gdsc emac_gdsc = { + .gdscr = 0x6004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0x2, + .pd = { + .name = "emac_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc pcie_0_gdsc = { + .gdscr = 0x6b004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0x2, + .pd = { + .name = "pcie_0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc ufs_phy_gdsc = { + .gdscr = 0x77004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0x2, + .pd = { + .name = "ufs_phy_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc usb20_sec_gdsc = { + .gdscr = 0xa6004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0x2, + .pd = { + .name = "usb20_sec_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc usb30_prim_gdsc = { + .gdscr = 0xf004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0x2, + .pd = { + .name = "usb30_prim_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc hlos1_vote_aggre_noc_mmu_audio_tbu_gdsc = { + .gdscr = 0x7d040, + .pd = { + .name = "hlos1_vote_aggre_noc_mmu_audio_tbu", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_aggre_noc_mmu_tbu1_gdsc = { + .gdscr = 0x7d044, + .pd = { + .name = "hlos1_vote_aggre_noc_mmu_tbu1", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_aggre_noc_mmu_tbu2_gdsc = { + .gdscr = 0x7d048, + .pd = { + .name = "hlos1_vote_aggre_noc_mmu_tbu2", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc = { + .gdscr = 0x7d04c, + .pd = { + .name = "hlos1_vote_aggre_noc_mmu_pcie_tbu", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = { + .gdscr = 0x7d050, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf_gdsc = { + .gdscr = 0x7d054, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_sf_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc = { + .gdscr = 0x7d058, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct clk_regmap *gcc_qcs615_clocks[] = { + [GCC_AGGRE_UFS_PHY_AXI_CLK] = &gcc_aggre_ufs_phy_axi_clk.clkr, + [GCC_AGGRE_USB2_SEC_AXI_CLK] = &gcc_aggre_usb2_sec_axi_clk.clkr, + [GCC_AGGRE_USB3_PRIM_AXI_CLK] = &gcc_aggre_usb3_prim_axi_clk.clkr, + [GCC_AHB2PHY_EAST_CLK] = &gcc_ahb2phy_east_clk.clkr, + [GCC_AHB2PHY_WEST_CLK] = &gcc_ahb2phy_west_clk.clkr, + [GCC_BOOT_ROM_AHB_CLK] = &gcc_boot_rom_ahb_clk.clkr, + [GCC_CAMERA_HF_AXI_CLK] = &gcc_camera_hf_axi_clk.clkr, + [GCC_CE1_AHB_CLK] = &gcc_ce1_ahb_clk.clkr, + [GCC_CE1_AXI_CLK] = &gcc_ce1_axi_clk.clkr, + [GCC_CE1_CLK] = &gcc_ce1_clk.clkr, + [GCC_CFG_NOC_USB2_SEC_AXI_CLK] = &gcc_cfg_noc_usb2_sec_axi_clk.clkr, + [GCC_CFG_NOC_USB3_PRIM_AXI_CLK] = &gcc_cfg_noc_usb3_prim_axi_clk.clkr, + [GCC_CPUSS_AHB_CLK] = &gcc_cpuss_ahb_clk.clkr, + [GCC_CPUSS_AHB_CLK_SRC] = &gcc_cpuss_ahb_clk_src.clkr, + [GCC_DDRSS_GPU_AXI_CLK] = &gcc_ddrss_gpu_axi_clk.clkr, + [GCC_DISP_GPLL0_DIV_CLK_SRC] = &gcc_disp_gpll0_div_clk_src.clkr, + [GCC_DISP_HF_AXI_CLK] = &gcc_disp_hf_axi_clk.clkr, + [GCC_EMAC_AXI_CLK] = &gcc_emac_axi_clk.clkr, + [GCC_EMAC_PTP_CLK] = &gcc_emac_ptp_clk.clkr, + [GCC_EMAC_PTP_CLK_SRC] = &gcc_emac_ptp_clk_src.clkr, + [GCC_EMAC_RGMII_CLK] = &gcc_emac_rgmii_clk.clkr, + [GCC_EMAC_RGMII_CLK_SRC] = &gcc_emac_rgmii_clk_src.clkr, + [GCC_EMAC_SLV_AHB_CLK] = &gcc_emac_slv_ahb_clk.clkr, + [GCC_GP1_CLK] = &gcc_gp1_clk.clkr, + [GCC_GP1_CLK_SRC] = &gcc_gp1_clk_src.clkr, + [GCC_GP2_CLK] = &gcc_gp2_clk.clkr, + [GCC_GP2_CLK_SRC] = &gcc_gp2_clk_src.clkr, + [GCC_GP3_CLK] = &gcc_gp3_clk.clkr, + [GCC_GP3_CLK_SRC] = &gcc_gp3_clk_src.clkr, + [GCC_GPU_GPLL0_CLK_SRC] = &gcc_gpu_gpll0_clk_src.clkr, + [GCC_GPU_GPLL0_DIV_CLK_SRC] = &gcc_gpu_gpll0_div_clk_src.clkr, + [GCC_GPU_IREF_CLK] = &gcc_gpu_iref_clk.clkr, + [GCC_GPU_MEMNOC_GFX_CLK] = &gcc_gpu_memnoc_gfx_clk.clkr, + [GCC_GPU_SNOC_DVM_GFX_CLK] = &gcc_gpu_snoc_dvm_gfx_clk.clkr, + [GCC_PCIE0_PHY_REFGEN_CLK] = &gcc_pcie0_phy_refgen_clk.clkr, + [GCC_PCIE_0_AUX_CLK] = &gcc_pcie_0_aux_clk.clkr, + [GCC_PCIE_0_AUX_CLK_SRC] = &gcc_pcie_0_aux_clk_src.clkr, + [GCC_PCIE_0_CFG_AHB_CLK] = &gcc_pcie_0_cfg_ahb_clk.clkr, + [GCC_PCIE_0_CLKREF_CLK] = &gcc_pcie_0_clkref_clk.clkr, + [GCC_PCIE_0_MSTR_AXI_CLK] = &gcc_pcie_0_mstr_axi_clk.clkr, + [GCC_PCIE_0_PIPE_CLK] = &gcc_pcie_0_pipe_clk.clkr, + [GCC_PCIE_0_SLV_AXI_CLK] = &gcc_pcie_0_slv_axi_clk.clkr, + [GCC_PCIE_0_SLV_Q2A_AXI_CLK] = &gcc_pcie_0_slv_q2a_axi_clk.clkr, + [GCC_PCIE_PHY_AUX_CLK] = &gcc_pcie_phy_aux_clk.clkr, + [GCC_PCIE_PHY_REFGEN_CLK_SRC] = &gcc_pcie_phy_refgen_clk_src.clkr, + [GCC_PDM2_CLK] = &gcc_pdm2_clk.clkr, + [GCC_PDM2_CLK_SRC] = &gcc_pdm2_clk_src.clkr, + [GCC_PDM_AHB_CLK] = &gcc_pdm_ahb_clk.clkr, + [GCC_PDM_XO4_CLK] = &gcc_pdm_xo4_clk.clkr, + [GCC_PRNG_AHB_CLK] = &gcc_prng_ahb_clk.clkr, + [GCC_QMIP_CAMERA_NRT_AHB_CLK] = &gcc_qmip_camera_nrt_ahb_clk.clkr, + [GCC_QMIP_DISP_AHB_CLK] = &gcc_qmip_disp_ahb_clk.clkr, + [GCC_QMIP_PCIE_AHB_CLK] = &gcc_qmip_pcie_ahb_clk.clkr, + [GCC_QMIP_VIDEO_VCODEC_AHB_CLK] = &gcc_qmip_video_vcodec_ahb_clk.clkr, + [GCC_QSPI_CNOC_PERIPH_AHB_CLK] = &gcc_qspi_cnoc_periph_ahb_clk.clkr, + [GCC_QSPI_CORE_CLK] = &gcc_qspi_core_clk.clkr, + [GCC_QSPI_CORE_CLK_SRC] = &gcc_qspi_core_clk_src.clkr, + [GCC_QUPV3_WRAP0_CORE_2X_CLK] = &gcc_qupv3_wrap0_core_2x_clk.clkr, + [GCC_QUPV3_WRAP0_CORE_CLK] = &gcc_qupv3_wrap0_core_clk.clkr, + [GCC_QUPV3_WRAP0_S0_CLK] = &gcc_qupv3_wrap0_s0_clk.clkr, + [GCC_QUPV3_WRAP0_S0_CLK_SRC] = &gcc_qupv3_wrap0_s0_clk_src.clkr, + [GCC_QUPV3_WRAP0_S1_CLK] = &gcc_qupv3_wrap0_s1_clk.clkr, + [GCC_QUPV3_WRAP0_S1_CLK_SRC] = &gcc_qupv3_wrap0_s1_clk_src.clkr, + [GCC_QUPV3_WRAP0_S2_CLK] = &gcc_qupv3_wrap0_s2_clk.clkr, + [GCC_QUPV3_WRAP0_S2_CLK_SRC] = &gcc_qupv3_wrap0_s2_clk_src.clkr, + [GCC_QUPV3_WRAP0_S3_CLK] = &gcc_qupv3_wrap0_s3_clk.clkr, + [GCC_QUPV3_WRAP0_S3_CLK_SRC] = &gcc_qupv3_wrap0_s3_clk_src.clkr, + [GCC_QUPV3_WRAP0_S4_CLK] = &gcc_qupv3_wrap0_s4_clk.clkr, + [GCC_QUPV3_WRAP0_S4_CLK_SRC] = &gcc_qupv3_wrap0_s4_clk_src.clkr, + [GCC_QUPV3_WRAP0_S5_CLK] = &gcc_qupv3_wrap0_s5_clk.clkr, + [GCC_QUPV3_WRAP0_S5_CLK_SRC] = &gcc_qupv3_wrap0_s5_clk_src.clkr, + [GCC_QUPV3_WRAP1_CORE_2X_CLK] = &gcc_qupv3_wrap1_core_2x_clk.clkr, + [GCC_QUPV3_WRAP1_CORE_CLK] = &gcc_qupv3_wrap1_core_clk.clkr, + [GCC_QUPV3_WRAP1_S0_CLK] = &gcc_qupv3_wrap1_s0_clk.clkr, + [GCC_QUPV3_WRAP1_S0_CLK_SRC] = &gcc_qupv3_wrap1_s0_clk_src.clkr, + [GCC_QUPV3_WRAP1_S1_CLK] = &gcc_qupv3_wrap1_s1_clk.clkr, + [GCC_QUPV3_WRAP1_S1_CLK_SRC] = &gcc_qupv3_wrap1_s1_clk_src.clkr, + [GCC_QUPV3_WRAP1_S2_CLK] = &gcc_qupv3_wrap1_s2_clk.clkr, + [GCC_QUPV3_WRAP1_S2_CLK_SRC] = &gcc_qupv3_wrap1_s2_clk_src.clkr, + [GCC_QUPV3_WRAP1_S3_CLK] = &gcc_qupv3_wrap1_s3_clk.clkr, + [GCC_QUPV3_WRAP1_S3_CLK_SRC] = &gcc_qupv3_wrap1_s3_clk_src.clkr, + [GCC_QUPV3_WRAP1_S4_CLK] = &gcc_qupv3_wrap1_s4_clk.clkr, + [GCC_QUPV3_WRAP1_S4_CLK_SRC] = &gcc_qupv3_wrap1_s4_clk_src.clkr, + [GCC_QUPV3_WRAP1_S5_CLK] = &gcc_qupv3_wrap1_s5_clk.clkr, + [GCC_QUPV3_WRAP1_S5_CLK_SRC] = &gcc_qupv3_wrap1_s5_clk_src.clkr, + [GCC_QUPV3_WRAP_0_M_AHB_CLK] = &gcc_qupv3_wrap_0_m_ahb_clk.clkr, + [GCC_QUPV3_WRAP_0_S_AHB_CLK] = &gcc_qupv3_wrap_0_s_ahb_clk.clkr, + [GCC_QUPV3_WRAP_1_M_AHB_CLK] = &gcc_qupv3_wrap_1_m_ahb_clk.clkr, + [GCC_QUPV3_WRAP_1_S_AHB_CLK] = &gcc_qupv3_wrap_1_s_ahb_clk.clkr, + [GCC_RX1_USB2_CLKREF_CLK] = &gcc_rx1_usb2_clkref_clk.clkr, + [GCC_RX3_USB2_CLKREF_CLK] = &gcc_rx3_usb2_clkref_clk.clkr, + [GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr, + [GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr, + [GCC_SDCC1_APPS_CLK_SRC] = &gcc_sdcc1_apps_clk_src.clkr, + [GCC_SDCC1_ICE_CORE_CLK] = &gcc_sdcc1_ice_core_clk.clkr, + [GCC_SDCC1_ICE_CORE_CLK_SRC] = &gcc_sdcc1_ice_core_clk_src.clkr, + [GCC_SDCC2_AHB_CLK] = &gcc_sdcc2_ahb_clk.clkr, + [GCC_SDCC2_APPS_CLK] = &gcc_sdcc2_apps_clk.clkr, + [GCC_SDCC2_APPS_CLK_SRC] = &gcc_sdcc2_apps_clk_src.clkr, + [GCC_SYS_NOC_CPUSS_AHB_CLK] = &gcc_sys_noc_cpuss_ahb_clk.clkr, + [GCC_UFS_CARD_CLKREF_CLK] = &gcc_ufs_card_clkref_clk.clkr, + [GCC_UFS_MEM_CLKREF_CLK] = &gcc_ufs_mem_clkref_clk.clkr, + [GCC_UFS_PHY_AHB_CLK] = &gcc_ufs_phy_ahb_clk.clkr, + [GCC_UFS_PHY_AXI_CLK] = &gcc_ufs_phy_axi_clk.clkr, + [GCC_UFS_PHY_AXI_CLK_SRC] = &gcc_ufs_phy_axi_clk_src.clkr, + [GCC_UFS_PHY_ICE_CORE_CLK] = &gcc_ufs_phy_ice_core_clk.clkr, + [GCC_UFS_PHY_ICE_CORE_CLK_SRC] = &gcc_ufs_phy_ice_core_clk_src.clkr, + [GCC_UFS_PHY_PHY_AUX_CLK] = &gcc_ufs_phy_phy_aux_clk.clkr, + [GCC_UFS_PHY_PHY_AUX_CLK_SRC] = &gcc_ufs_phy_phy_aux_clk_src.clkr, + [GCC_UFS_PHY_RX_SYMBOL_0_CLK] = &gcc_ufs_phy_rx_symbol_0_clk.clkr, + [GCC_UFS_PHY_TX_SYMBOL_0_CLK] = &gcc_ufs_phy_tx_symbol_0_clk.clkr, + [GCC_UFS_PHY_UNIPRO_CORE_CLK] = &gcc_ufs_phy_unipro_core_clk.clkr, + [GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC] = &gcc_ufs_phy_unipro_core_clk_src.clkr, + [GCC_USB20_SEC_MASTER_CLK] = &gcc_usb20_sec_master_clk.clkr, + [GCC_USB20_SEC_MASTER_CLK_SRC] = &gcc_usb20_sec_master_clk_src.clkr, + [GCC_USB20_SEC_MOCK_UTMI_CLK] = &gcc_usb20_sec_mock_utmi_clk.clkr, + [GCC_USB20_SEC_MOCK_UTMI_CLK_SRC] = &gcc_usb20_sec_mock_utmi_clk_src.clkr, + [GCC_USB20_SEC_SLEEP_CLK] = &gcc_usb20_sec_sleep_clk.clkr, + [GCC_USB2_PRIM_CLKREF_CLK] = &gcc_usb2_prim_clkref_clk.clkr, + [GCC_USB2_SEC_CLKREF_CLK] = &gcc_usb2_sec_clkref_clk.clkr, + [GCC_USB2_SEC_PHY_AUX_CLK] = &gcc_usb2_sec_phy_aux_clk.clkr, + [GCC_USB2_SEC_PHY_AUX_CLK_SRC] = &gcc_usb2_sec_phy_aux_clk_src.clkr, + [GCC_USB2_SEC_PHY_COM_AUX_CLK] = &gcc_usb2_sec_phy_com_aux_clk.clkr, + [GCC_USB2_SEC_PHY_PIPE_CLK] = &gcc_usb2_sec_phy_pipe_clk.clkr, + [GCC_USB30_PRIM_MASTER_CLK] = &gcc_usb30_prim_master_clk.clkr, + [GCC_USB30_PRIM_MASTER_CLK_SRC] = &gcc_usb30_prim_master_clk_src.clkr, + [GCC_USB30_PRIM_MOCK_UTMI_CLK] = &gcc_usb30_prim_mock_utmi_clk.clkr, + [GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC] = &gcc_usb30_prim_mock_utmi_clk_src.clkr, + [GCC_USB30_PRIM_SLEEP_CLK] = &gcc_usb30_prim_sleep_clk.clkr, + [GCC_USB3_PRIM_CLKREF_CLK] = &gcc_usb3_prim_clkref_clk.clkr, + [GCC_USB3_PRIM_PHY_AUX_CLK] = &gcc_usb3_prim_phy_aux_clk.clkr, + [GCC_USB3_PRIM_PHY_AUX_CLK_SRC] = &gcc_usb3_prim_phy_aux_clk_src.clkr, + [GCC_USB3_PRIM_PHY_COM_AUX_CLK] = &gcc_usb3_prim_phy_com_aux_clk.clkr, + [GCC_USB3_PRIM_PHY_PIPE_CLK] = &gcc_usb3_prim_phy_pipe_clk.clkr, + [GCC_USB3_SEC_CLKREF_CLK] = &gcc_usb3_sec_clkref_clk.clkr, + [GCC_VIDEO_AXI0_CLK] = &gcc_video_axi0_clk.clkr, + [GCC_VSENSOR_CLK_SRC] = &gcc_vsensor_clk_src.clkr, + [GPLL0] = &gpll0.clkr, + [GPLL3] = &gpll3.clkr, + [GPLL4] = &gpll4.clkr, + [GPLL6] = &gpll6.clkr, + [GPLL6_OUT_MAIN] = &gpll6_out_main.clkr, + [GPLL7] = &gpll7.clkr, + [GPLL8] = &gpll8.clkr, + [GPLL8_OUT_MAIN] = &gpll8_out_main.clkr, +}; + +static struct gdsc *gcc_qcs615_gdscs[] = { + [EMAC_GDSC] = &emac_gdsc, + [PCIE_0_GDSC] = &pcie_0_gdsc, + [UFS_PHY_GDSC] = &ufs_phy_gdsc, + [USB20_SEC_GDSC] = &usb20_sec_gdsc, + [USB30_PRIM_GDSC] = &usb30_prim_gdsc, + [HLOS1_VOTE_AGGRE_NOC_MMU_AUDIO_TBU_GDSC] = &hlos1_vote_aggre_noc_mmu_audio_tbu_gdsc, + [HLOS1_VOTE_AGGRE_NOC_MMU_TBU1_GDSC] = &hlos1_vote_aggre_noc_mmu_tbu1_gdsc, + [HLOS1_VOTE_AGGRE_NOC_MMU_TBU2_GDSC] = &hlos1_vote_aggre_noc_mmu_tbu2_gdsc, + [HLOS1_VOTE_AGGRE_NOC_MMU_PCIE_TBU_GDSC] = &hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_SF_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_sf_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc, +}; + +static const struct qcom_reset_map gcc_qcs615_resets[] = { + [GCC_EMAC_BCR] = { 0x6000 }, + [GCC_QUSB2PHY_PRIM_BCR] = { 0xd000 }, + [GCC_QUSB2PHY_SEC_BCR] = { 0xd004 }, + [GCC_USB30_PRIM_BCR] = { 0xf000 }, + [GCC_USB2_PHY_SEC_BCR] = { 0x50018 }, + [GCC_USB3_DP_PHY_SEC_BCR] = { 0x50020 }, + [GCC_USB3PHY_PHY_SEC_BCR] = { 0x5001c }, + [GCC_PCIE_0_BCR] = { 0x6b000 }, + [GCC_PCIE_0_PHY_BCR] = { 0x6c01c }, + [GCC_PCIE_PHY_BCR] = { 0x6f000 }, + [GCC_PCIE_PHY_COM_BCR] = { 0x6f010 }, + [GCC_UFS_PHY_BCR] = { 0x77000 }, + [GCC_USB20_SEC_BCR] = { 0xa6000 }, + [GCC_USB3PHY_PHY_PRIM_SP0_BCR] = { 0x50008 }, + [GCC_USB3_PHY_PRIM_SP0_BCR] = { 0x50000 }, + [GCC_SDCC1_BCR] = { 0x12000 }, + [GCC_SDCC2_BCR] = { 0x14000 }, +}; + +static const struct clk_rcg_dfs_data gcc_dfs_clocks[] = { + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s0_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s1_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s2_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s3_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s4_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s5_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s0_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s1_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s2_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s3_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s4_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s5_clk_src), +}; + +static const struct regmap_config gcc_qcs615_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0xa609c, + .fast_io = true, +}; + +static const struct qcom_cc_desc gcc_qcs615_desc = { + .config = &gcc_qcs615_regmap_config, + .clk_hws = gcc_qcs615_hws, + .num_clk_hws = ARRAY_SIZE(gcc_qcs615_hws), + .clks = gcc_qcs615_clocks, + .num_clks = ARRAY_SIZE(gcc_qcs615_clocks), + .resets = gcc_qcs615_resets, + .num_resets = ARRAY_SIZE(gcc_qcs615_resets), + .gdscs = gcc_qcs615_gdscs, + .num_gdscs = ARRAY_SIZE(gcc_qcs615_gdscs), +}; + +static const struct of_device_id gcc_qcs615_match_table[] = { + { .compatible = "qcom,qcs615-gcc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gcc_qcs615_match_table); + +static int gcc_qcs615_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + int ret; + + regmap = qcom_cc_map(pdev, &gcc_qcs615_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + /* + * Disable the GPLL0 active input to MM blocks and GPU + * via MISC registers. + */ + regmap_update_bits(regmap, 0x0b084, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x9b000, BIT(0), BIT(0)); + + /* Keep some clocks always enabled */ + qcom_branch_set_clk_en(regmap, 0xb008); /* GCC_CAMERA_AHB_CLK */ + qcom_branch_set_clk_en(regmap, 0xb044); /* GCC_CAMERA_XO_CLK */ + qcom_branch_set_clk_en(regmap, 0xb00c); /* GCC_DISP_AHB_CLK */ + qcom_branch_set_clk_en(regmap, 0xb048); /* GCC_DISP_XO_CLK */ + qcom_branch_set_clk_en(regmap, 0x71004); /* GCC_GPU_CFG_AHB_CLK */ + qcom_branch_set_clk_en(regmap, 0xb004); /* GCC_VIDEO_AHB_CLK */ + qcom_branch_set_clk_en(regmap, 0xb040); /* GCC_VIDEO_XO_CLK */ + qcom_branch_set_clk_en(regmap, 0x480040); /* GCC_CPUSS_GNOC_CLK */ + + ret = qcom_cc_register_rcg_dfs(regmap, gcc_dfs_clocks, + ARRAY_SIZE(gcc_dfs_clocks)); + if (ret) + return ret; + + return qcom_cc_really_probe(&pdev->dev, &gcc_qcs615_desc, regmap); +} + +static struct platform_driver gcc_qcs615_driver = { + .probe = gcc_qcs615_probe, + .driver = { + .name = "gcc-qcs615", + .of_match_table = gcc_qcs615_match_table, + }, +}; + +static int __init gcc_qcs615_init(void) +{ + return platform_driver_register(&gcc_qcs615_driver); +} +subsys_initcall(gcc_qcs615_init); + +static void __exit gcc_qcs615_exit(void) +{ + platform_driver_unregister(&gcc_qcs615_driver); +} +module_exit(gcc_qcs615_exit); + +MODULE_DESCRIPTION("QTI GCC QCS615 Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index dc3aa7014c3e..6d0f9cede5cf 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -284,11 +284,6 @@ static struct clk_rcg2 gcc_sdm670_cpuss_rbcpr_clk_src = { }; static const struct freq_tbl ftbl_gcc_gp1_clk_src[] = { - F(19200000, P_BI_TCXO, 1, 0, 0), - F(25000000, P_GPLL0_OUT_EVEN, 12, 0, 0), - F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0), - F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), - F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), { } }; @@ -302,7 +297,7 @@ static struct clk_rcg2 gcc_gp1_clk_src = { .name = "gcc_gp1_clk_src", .parent_data = gcc_parent_data_1, .num_parents = ARRAY_SIZE(gcc_parent_data_1), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_gp_ops, }, }; @@ -316,7 +311,7 @@ static struct clk_rcg2 gcc_gp2_clk_src = { .name = "gcc_gp2_clk_src", .parent_data = gcc_parent_data_1, .num_parents = ARRAY_SIZE(gcc_parent_data_1), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_gp_ops, }, }; @@ -330,7 +325,7 @@ static struct clk_rcg2 gcc_gp3_clk_src = { .name = "gcc_gp3_clk_src", .parent_data = gcc_parent_data_1, .num_parents = ARRAY_SIZE(gcc_parent_data_1), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_gp_ops, }, }; @@ -454,7 +449,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s0_clk_src_init = { .name = "gcc_qupv3_wrap0_s0_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap0_s0_clk_src = { @@ -470,7 +465,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s1_clk_src_init = { .name = "gcc_qupv3_wrap0_s1_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap0_s1_clk_src = { @@ -486,7 +481,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s2_clk_src_init = { .name = "gcc_qupv3_wrap0_s2_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap0_s2_clk_src = { @@ -502,7 +497,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s3_clk_src_init = { .name = "gcc_qupv3_wrap0_s3_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap0_s3_clk_src = { @@ -518,7 +513,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s4_clk_src_init = { .name = "gcc_qupv3_wrap0_s4_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap0_s4_clk_src = { @@ -534,7 +529,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s5_clk_src_init = { .name = "gcc_qupv3_wrap0_s5_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap0_s5_clk_src = { @@ -550,7 +545,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s6_clk_src_init = { .name = "gcc_qupv3_wrap0_s6_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap0_s6_clk_src = { @@ -566,7 +561,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s7_clk_src_init = { .name = "gcc_qupv3_wrap0_s7_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap0_s7_clk_src = { @@ -582,7 +577,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s0_clk_src_init = { .name = "gcc_qupv3_wrap1_s0_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap1_s0_clk_src = { @@ -598,7 +593,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s1_clk_src_init = { .name = "gcc_qupv3_wrap1_s1_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap1_s1_clk_src = { @@ -614,7 +609,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s2_clk_src_init = { .name = "gcc_qupv3_wrap1_s2_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap1_s2_clk_src = { @@ -630,7 +625,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s3_clk_src_init = { .name = "gcc_qupv3_wrap1_s3_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap1_s3_clk_src = { @@ -646,7 +641,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s4_clk_src_init = { .name = "gcc_qupv3_wrap1_s4_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap1_s4_clk_src = { @@ -662,7 +657,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s5_clk_src_init = { .name = "gcc_qupv3_wrap1_s5_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap1_s5_clk_src = { @@ -678,7 +673,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s6_clk_src_init = { .name = "gcc_qupv3_wrap1_s6_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap1_s6_clk_src = { @@ -694,7 +689,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s7_clk_src_init = { .name = "gcc_qupv3_wrap1_s7_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_ops, }; static struct clk_rcg2 gcc_qupv3_wrap1_s7_clk_src = { diff --git a/drivers/clk/qcom/gcc-sm6350.c b/drivers/clk/qcom/gcc-sm6350.c index a811fad2aa27..74346dc02606 100644 --- a/drivers/clk/qcom/gcc-sm6350.c +++ b/drivers/clk/qcom/gcc-sm6350.c @@ -182,6 +182,14 @@ static const struct clk_parent_data gcc_parent_data_2_ao[] = { { .hw = &gpll0_out_odd.clkr.hw }, }; +static const struct parent_map gcc_parent_map_3[] = { + { P_BI_TCXO, 0 }, +}; + +static const struct clk_parent_data gcc_parent_data_3[] = { + { .fw_name = "bi_tcxo" }, +}; + static const struct parent_map gcc_parent_map_4[] = { { P_BI_TCXO, 0 }, { P_GPLL0_OUT_MAIN, 1 }, @@ -701,13 +709,12 @@ static struct clk_rcg2 gcc_ufs_phy_phy_aux_clk_src = { .cmd_rcgr = 0x3a0b0, .mnd_width = 0, .hid_width = 5, + .parent_map = gcc_parent_map_3, .freq_tbl = ftbl_gcc_ufs_phy_phy_aux_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "gcc_ufs_phy_phy_aux_clk_src", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "bi_tcxo", - }, - .num_parents = 1, + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), .ops = &clk_rcg2_ops, }, }; @@ -764,13 +771,12 @@ static struct clk_rcg2 gcc_usb30_prim_mock_utmi_clk_src = { .cmd_rcgr = 0x1a034, .mnd_width = 0, .hid_width = 5, + .parent_map = gcc_parent_map_3, .freq_tbl = ftbl_gcc_usb30_prim_mock_utmi_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "gcc_usb30_prim_mock_utmi_clk_src", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "bi_tcxo", - }, - .num_parents = 1, + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), .ops = &clk_rcg2_ops, }, }; diff --git a/drivers/clk/qcom/gcc-sm8550.c b/drivers/clk/qcom/gcc-sm8550.c index 5abaeddd6afc..862a9bf73bcb 100644 --- a/drivers/clk/qcom/gcc-sm8550.c +++ b/drivers/clk/qcom/gcc-sm8550.c @@ -3003,7 +3003,7 @@ static struct gdsc pcie_0_gdsc = { .pd = { .name = "pcie_0_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3014,7 +3014,7 @@ static struct gdsc pcie_0_phy_gdsc = { .pd = { .name = "pcie_0_phy_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3025,7 +3025,7 @@ static struct gdsc pcie_1_gdsc = { .pd = { .name = "pcie_1_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3036,7 +3036,7 @@ static struct gdsc pcie_1_phy_gdsc = { .pd = { .name = "pcie_1_phy_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; diff --git a/drivers/clk/qcom/gcc-sm8650.c b/drivers/clk/qcom/gcc-sm8650.c index fd9d6544bdd5..9dd5c48f33be 100644 --- a/drivers/clk/qcom/gcc-sm8650.c +++ b/drivers/clk/qcom/gcc-sm8650.c @@ -3437,7 +3437,7 @@ static struct gdsc pcie_0_gdsc = { .pd = { .name = "pcie_0_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE, }; @@ -3448,7 +3448,7 @@ static struct gdsc pcie_0_phy_gdsc = { .pd = { .name = "pcie_0_phy_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE, }; @@ -3459,7 +3459,7 @@ static struct gdsc pcie_1_gdsc = { .pd = { .name = "pcie_1_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE, }; @@ -3470,7 +3470,7 @@ static struct gdsc pcie_1_phy_gdsc = { .pd = { .name = "pcie_1_phy_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE, }; diff --git a/drivers/clk/qcom/gcc-sm8750.c b/drivers/clk/qcom/gcc-sm8750.c new file mode 100644 index 000000000000..b36d70976095 --- /dev/null +++ b/drivers/clk/qcom/gcc-sm8750.c @@ -0,0 +1,3274 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-pll.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "clk-regmap-phy-mux.h" +#include "common.h" +#include "gdsc.h" +#include "reset.h" + +enum { + DT_BI_TCXO, + DT_BI_TCXO_AO, + DT_SLEEP_CLK, + DT_PCIE_0_PIPE_CLK, + DT_UFS_PHY_RX_SYMBOL_0_CLK, + DT_UFS_PHY_RX_SYMBOL_1_CLK, + DT_UFS_PHY_TX_SYMBOL_0_CLK, + DT_USB3_PHY_WRAPPER_GCC_USB30_PIPE_CLK, +}; + +enum { + P_BI_TCXO, + P_GCC_GPLL0_OUT_EVEN, + P_GCC_GPLL0_OUT_MAIN, + P_GCC_GPLL1_OUT_MAIN, + P_GCC_GPLL4_OUT_MAIN, + P_GCC_GPLL7_OUT_MAIN, + P_GCC_GPLL9_OUT_MAIN, + P_PCIE_0_PIPE_CLK, + P_SLEEP_CLK, + P_UFS_PHY_RX_SYMBOL_0_CLK, + P_UFS_PHY_RX_SYMBOL_1_CLK, + P_UFS_PHY_TX_SYMBOL_0_CLK, + P_USB3_PHY_WRAPPER_GCC_USB30_PIPE_CLK, +}; + +static struct clk_alpha_pll gcc_gpll0 = { + .offset = 0x0, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TAYCAN_ELU], + .clkr = { + .enable_reg = 0x52020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpll0", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_taycan_elu_ops, + }, + }, +}; + +static const struct clk_div_table post_div_table_gcc_gpll0_out_even[] = { + { 0x1, 2 }, + { } +}; + +static struct clk_alpha_pll_postdiv gcc_gpll0_out_even = { + .offset = 0x0, + .post_div_shift = 10, + .post_div_table = post_div_table_gcc_gpll0_out_even, + .num_post_div = ARRAY_SIZE(post_div_table_gcc_gpll0_out_even), + .width = 4, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TAYCAN_ELU], + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_gpll0_out_even", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gpll0.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_taycan_elu_ops, + }, +}; + +static struct clk_alpha_pll gcc_gpll1 = { + .offset = 0x1000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TAYCAN_ELU], + .clkr = { + .enable_reg = 0x52020, + .enable_mask = BIT(1), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpll1", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_taycan_elu_ops, + }, + }, +}; + +static struct clk_alpha_pll gcc_gpll4 = { + .offset = 0x4000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TAYCAN_ELU], + .clkr = { + .enable_reg = 0x52020, + .enable_mask = BIT(4), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpll4", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_taycan_elu_ops, + }, + }, +}; + +static struct clk_alpha_pll gcc_gpll7 = { + .offset = 0x7000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TAYCAN_ELU], + .clkr = { + .enable_reg = 0x52020, + .enable_mask = BIT(7), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpll7", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_taycan_elu_ops, + }, + }, +}; + +static struct clk_alpha_pll gcc_gpll9 = { + .offset = 0x9000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TAYCAN_ELU], + .clkr = { + .enable_reg = 0x52020, + .enable_mask = BIT(9), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpll9", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_taycan_elu_ops, + }, + }, +}; + +static const struct parent_map gcc_parent_map_0[] = { + { P_BI_TCXO, 0 }, + { P_GCC_GPLL0_OUT_MAIN, 1 }, + { P_GCC_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_0[] = { + { .index = DT_BI_TCXO }, + { .hw = &gcc_gpll0.clkr.hw }, + { .hw = &gcc_gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_1[] = { + { P_BI_TCXO, 0 }, + { P_GCC_GPLL0_OUT_MAIN, 1 }, + { P_SLEEP_CLK, 5 }, + { P_GCC_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_1[] = { + { .index = DT_BI_TCXO }, + { .hw = &gcc_gpll0.clkr.hw }, + { .index = DT_SLEEP_CLK }, + { .hw = &gcc_gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_2[] = { + { P_BI_TCXO, 0 }, + { P_GCC_GPLL0_OUT_MAIN, 1 }, + { P_GCC_GPLL1_OUT_MAIN, 4 }, + { P_GCC_GPLL4_OUT_MAIN, 5 }, + { P_GCC_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_2[] = { + { .index = DT_BI_TCXO }, + { .hw = &gcc_gpll0.clkr.hw }, + { .hw = &gcc_gpll1.clkr.hw }, + { .hw = &gcc_gpll4.clkr.hw }, + { .hw = &gcc_gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_3[] = { + { P_BI_TCXO, 0 }, + { P_GCC_GPLL0_OUT_MAIN, 1 }, + { P_GCC_GPLL4_OUT_MAIN, 5 }, + { P_GCC_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_3[] = { + { .index = DT_BI_TCXO }, + { .hw = &gcc_gpll0.clkr.hw }, + { .hw = &gcc_gpll4.clkr.hw }, + { .hw = &gcc_gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_4[] = { + { P_BI_TCXO, 0 }, + { P_SLEEP_CLK, 5 }, +}; + +static const struct clk_parent_data gcc_parent_data_4[] = { + { .index = DT_BI_TCXO }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_parent_map_5[] = { + { P_BI_TCXO, 0 }, + { P_GCC_GPLL0_OUT_MAIN, 1 }, + { P_GCC_GPLL7_OUT_MAIN, 2 }, + { P_GCC_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_5[] = { + { .index = DT_BI_TCXO }, + { .hw = &gcc_gpll0.clkr.hw }, + { .hw = &gcc_gpll7.clkr.hw }, + { .hw = &gcc_gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_6[] = { + { P_BI_TCXO, 0 }, +}; + +static const struct clk_parent_data gcc_parent_data_6[] = { + { .index = DT_BI_TCXO }, +}; + +static const struct parent_map gcc_parent_map_8[] = { + { P_BI_TCXO, 0 }, + { P_GCC_GPLL0_OUT_MAIN, 1 }, + { P_GCC_GPLL9_OUT_MAIN, 2 }, + { P_GCC_GPLL4_OUT_MAIN, 5 }, + { P_GCC_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_8[] = { + { .index = DT_BI_TCXO }, + { .hw = &gcc_gpll0.clkr.hw }, + { .hw = &gcc_gpll9.clkr.hw }, + { .hw = &gcc_gpll4.clkr.hw }, + { .hw = &gcc_gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_9[] = { + { P_UFS_PHY_RX_SYMBOL_0_CLK, 0 }, + { P_BI_TCXO, 2 }, +}; + +static const struct clk_parent_data gcc_parent_data_9[] = { + { .index = DT_UFS_PHY_RX_SYMBOL_0_CLK }, + { .index = DT_BI_TCXO }, +}; + +static const struct parent_map gcc_parent_map_10[] = { + { P_UFS_PHY_RX_SYMBOL_1_CLK, 0 }, + { P_BI_TCXO, 2 }, +}; + +static const struct clk_parent_data gcc_parent_data_10[] = { + { .index = DT_UFS_PHY_RX_SYMBOL_1_CLK }, + { .index = DT_BI_TCXO }, +}; + +static const struct parent_map gcc_parent_map_11[] = { + { P_UFS_PHY_TX_SYMBOL_0_CLK, 0 }, + { P_BI_TCXO, 2 }, +}; + +static const struct clk_parent_data gcc_parent_data_11[] = { + { .index = DT_UFS_PHY_TX_SYMBOL_0_CLK }, + { .index = DT_BI_TCXO }, +}; + +static const struct parent_map gcc_parent_map_12[] = { + { P_USB3_PHY_WRAPPER_GCC_USB30_PIPE_CLK, 0 }, + { P_BI_TCXO, 2 }, +}; + +static const struct clk_parent_data gcc_parent_data_12[] = { + { .index = DT_USB3_PHY_WRAPPER_GCC_USB30_PIPE_CLK }, + { .index = DT_BI_TCXO }, +}; + +static struct clk_regmap_phy_mux gcc_pcie_0_pipe_clk_src = { + .reg = 0x6b080, + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_pipe_clk_src", + .parent_data = &(const struct clk_parent_data){ + .index = DT_PCIE_0_PIPE_CLK, + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, + }, + }, +}; + +static struct clk_regmap_mux gcc_ufs_phy_rx_symbol_0_clk_src = { + .reg = 0x77068, + .shift = 0, + .width = 2, + .parent_map = gcc_parent_map_9, + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_rx_symbol_0_clk_src", + .parent_data = gcc_parent_data_9, + .num_parents = ARRAY_SIZE(gcc_parent_data_9), + .ops = &clk_regmap_mux_closest_ops, + }, + }, +}; + +static struct clk_regmap_mux gcc_ufs_phy_rx_symbol_1_clk_src = { + .reg = 0x770ec, + .shift = 0, + .width = 2, + .parent_map = gcc_parent_map_10, + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_rx_symbol_1_clk_src", + .parent_data = gcc_parent_data_10, + .num_parents = ARRAY_SIZE(gcc_parent_data_10), + .ops = &clk_regmap_mux_closest_ops, + }, + }, +}; + +static struct clk_regmap_mux gcc_ufs_phy_tx_symbol_0_clk_src = { + .reg = 0x77058, + .shift = 0, + .width = 2, + .parent_map = gcc_parent_map_11, + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_tx_symbol_0_clk_src", + .parent_data = gcc_parent_data_11, + .num_parents = ARRAY_SIZE(gcc_parent_data_11), + .ops = &clk_regmap_mux_closest_ops, + }, + }, +}; + +static struct clk_regmap_mux gcc_usb3_prim_phy_pipe_clk_src = { + .reg = 0x39070, + .shift = 0, + .width = 2, + .parent_map = gcc_parent_map_12, + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_phy_pipe_clk_src", + .parent_data = gcc_parent_data_12, + .num_parents = ARRAY_SIZE(gcc_parent_data_12), + .ops = &clk_regmap_mux_closest_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_gcc_gp1_clk_src[] = { + F(50000000, P_GCC_GPLL0_OUT_EVEN, 6, 0, 0), + F(100000000, P_GCC_GPLL0_OUT_MAIN, 6, 0, 0), + F(200000000, P_GCC_GPLL0_OUT_MAIN, 3, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_gp1_clk_src = { + .cmd_rcgr = 0x64004, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_gp1_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_gp2_clk_src = { + .cmd_rcgr = 0x65004, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_gp2_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_gp3_clk_src = { + .cmd_rcgr = 0x66004, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_gp3_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcie_0_aux_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcie_0_aux_clk_src = { + .cmd_rcgr = 0x6b084, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_4, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_aux_clk_src", + .parent_data = gcc_parent_data_4, + .num_parents = ARRAY_SIZE(gcc_parent_data_4), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcie_0_phy_rchng_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(100000000, P_GCC_GPLL0_OUT_EVEN, 3, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcie_0_phy_rchng_clk_src = { + .cmd_rcgr = 0x6b068, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_phy_rchng_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_phy_rchng_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pdm2_clk_src[] = { + F(60000000, P_GCC_GPLL0_OUT_MAIN, 10, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pdm2_clk_src = { + .cmd_rcgr = 0x33010, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pdm2_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pdm2_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s0_clk_src = { + .cmd_rcgr = 0x17008, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s0_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s1_clk_src = { + .cmd_rcgr = 0x17024, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s1_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s2_clk_src = { + .cmd_rcgr = 0x17040, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s2_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s3_clk_src = { + .cmd_rcgr = 0x1705c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s3_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s4_clk_src = { + .cmd_rcgr = 0x17078, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s4_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s5_clk_src = { + .cmd_rcgr = 0x17094, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s5_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s6_clk_src = { + .cmd_rcgr = 0x170b0, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s6_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s7_clk_src = { + .cmd_rcgr = 0x170cc, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s7_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s8_clk_src = { + .cmd_rcgr = 0x170e8, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s8_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_qupv3_i2c_s9_clk_src = { + .cmd_rcgr = 0x17104, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s9_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +/* Check this frequency table.*/ +static const struct freq_tbl ftbl_gcc_qupv3_wrap1_qspi_ref_clk_src[] = { + F(7372800, P_GCC_GPLL0_OUT_EVEN, 1, 384, 15625), + F(14745600, P_GCC_GPLL0_OUT_EVEN, 1, 768, 15625), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(29491200, P_GCC_GPLL0_OUT_EVEN, 1, 1536, 15625), + F(32000000, P_GCC_GPLL0_OUT_EVEN, 1, 8, 75), + F(48000000, P_GCC_GPLL0_OUT_EVEN, 1, 4, 25), + F(51200000, P_GCC_GPLL0_OUT_EVEN, 1, 64, 375), + F(64000000, P_GCC_GPLL0_OUT_EVEN, 1, 16, 75), + F(75000000, P_GCC_GPLL0_OUT_EVEN, 4, 0, 0), + F(80000000, P_GCC_GPLL0_OUT_EVEN, 1, 4, 15), + F(96000000, P_GCC_GPLL0_OUT_EVEN, 1, 8, 25), + F(100000000, P_GCC_GPLL0_OUT_MAIN, 6, 0, 0), + F(102400000, P_GCC_GPLL0_OUT_EVEN, 1, 128, 375), + F(112000000, P_GCC_GPLL0_OUT_EVEN, 1, 28, 75), + F(117964800, P_GCC_GPLL0_OUT_EVEN, 1, 6144, 15625), + F(120000000, P_GCC_GPLL0_OUT_MAIN, 5, 0, 0), + F(150000000, P_GCC_GPLL0_OUT_EVEN, 2, 0, 0), + F(250000000, P_GCC_GPLL7_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_init_data gcc_qupv3_wrap1_qspi_ref_clk_src_init = { + .name = "gcc_qupv3_wrap1_qspi_ref_clk_src", + .parent_data = gcc_parent_data_5, + .num_parents = ARRAY_SIZE(gcc_parent_data_5), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_qspi_ref_clk_src = { + .cmd_rcgr = 0x188c0, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_5, + .freq_tbl = ftbl_gcc_qupv3_wrap1_qspi_ref_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_qspi_ref_clk_src_init, +}; + +static const struct freq_tbl ftbl_gcc_qupv3_wrap1_s0_clk_src[] = { + F(7372800, P_GCC_GPLL0_OUT_EVEN, 1, 384, 15625), + F(14745600, P_GCC_GPLL0_OUT_EVEN, 1, 768, 15625), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(29491200, P_GCC_GPLL0_OUT_EVEN, 1, 1536, 15625), + F(32000000, P_GCC_GPLL0_OUT_EVEN, 1, 8, 75), + F(48000000, P_GCC_GPLL0_OUT_EVEN, 1, 4, 25), + F(51200000, P_GCC_GPLL0_OUT_EVEN, 1, 64, 375), + F(64000000, P_GCC_GPLL0_OUT_EVEN, 1, 16, 75), + F(75000000, P_GCC_GPLL0_OUT_EVEN, 4, 0, 0), + F(80000000, P_GCC_GPLL0_OUT_EVEN, 1, 4, 15), + F(96000000, P_GCC_GPLL0_OUT_EVEN, 1, 8, 25), + F(100000000, P_GCC_GPLL0_OUT_MAIN, 6, 0, 0), + F(102400000, P_GCC_GPLL0_OUT_EVEN, 1, 128, 375), + F(112000000, P_GCC_GPLL0_OUT_EVEN, 1, 28, 75), + F(117964800, P_GCC_GPLL0_OUT_EVEN, 1, 6144, 15625), + F(120000000, P_GCC_GPLL0_OUT_MAIN, 5, 0, 0), + { } +}; + +static struct clk_init_data gcc_qupv3_wrap1_s0_clk_src_init = { + .name = "gcc_qupv3_wrap1_s0_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s0_clk_src = { + .cmd_rcgr = 0x18014, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s0_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s1_clk_src_init = { + .name = "gcc_qupv3_wrap1_s1_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s1_clk_src = { + .cmd_rcgr = 0x18150, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s1_clk_src_init, +}; + +static const struct freq_tbl ftbl_gcc_qupv3_wrap1_s3_clk_src[] = { + F(7372800, P_GCC_GPLL0_OUT_EVEN, 1, 384, 15625), + F(14745600, P_GCC_GPLL0_OUT_EVEN, 1, 768, 15625), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(29491200, P_GCC_GPLL0_OUT_EVEN, 1, 1536, 15625), + F(32000000, P_GCC_GPLL0_OUT_EVEN, 1, 8, 75), + F(48000000, P_GCC_GPLL0_OUT_EVEN, 1, 4, 25), + F(51200000, P_GCC_GPLL0_OUT_EVEN, 1, 64, 375), + F(64000000, P_GCC_GPLL0_OUT_EVEN, 1, 16, 75), + F(75000000, P_GCC_GPLL0_OUT_EVEN, 4, 0, 0), + F(80000000, P_GCC_GPLL0_OUT_EVEN, 1, 4, 15), + F(96000000, P_GCC_GPLL0_OUT_EVEN, 1, 8, 25), + F(100000000, P_GCC_GPLL0_OUT_MAIN, 6, 0, 0), + { } +}; + +static struct clk_init_data gcc_qupv3_wrap1_s3_clk_src_init = { + .name = "gcc_qupv3_wrap1_s3_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s3_clk_src = { + .cmd_rcgr = 0x182a0, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s3_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s3_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s4_clk_src_init = { + .name = "gcc_qupv3_wrap1_s4_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s4_clk_src = { + .cmd_rcgr = 0x183dc, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s4_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s5_clk_src_init = { + .name = "gcc_qupv3_wrap1_s5_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s5_clk_src = { + .cmd_rcgr = 0x18518, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s3_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s5_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s6_clk_src_init = { + .name = "gcc_qupv3_wrap1_s6_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s6_clk_src = { + .cmd_rcgr = 0x18654, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s3_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s6_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s7_clk_src_init = { + .name = "gcc_qupv3_wrap1_s7_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s7_clk_src = { + .cmd_rcgr = 0x18790, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s3_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s7_clk_src_init, +}; + +static const struct freq_tbl ftbl_gcc_qupv3_wrap2_ibi_ctrl_0_clk_src[] = { + F(37500000, P_GCC_GPLL0_OUT_EVEN, 8, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_qupv3_wrap2_ibi_ctrl_0_clk_src = { + .cmd_rcgr = 0x1e9f4, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_qupv3_wrap2_ibi_ctrl_0_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_ibi_ctrl_0_clk_src", + .parent_data = gcc_parent_data_2, + .num_parents = ARRAY_SIZE(gcc_parent_data_2), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_init_data gcc_qupv3_wrap2_s0_clk_src_init = { + .name = "gcc_qupv3_wrap2_s0_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap2_s0_clk_src = { + .cmd_rcgr = 0x1e014, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap2_s0_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap2_s1_clk_src_init = { + .name = "gcc_qupv3_wrap2_s1_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap2_s1_clk_src = { + .cmd_rcgr = 0x1e150, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap2_s1_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap2_s2_clk_src_init = { + .name = "gcc_qupv3_wrap2_s2_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap2_s2_clk_src = { + .cmd_rcgr = 0x1e28c, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap2_s2_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap2_s3_clk_src_init = { + .name = "gcc_qupv3_wrap2_s3_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap2_s3_clk_src = { + .cmd_rcgr = 0x1e3c8, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap2_s3_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap2_s4_clk_src_init = { + .name = "gcc_qupv3_wrap2_s4_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap2_s4_clk_src = { + .cmd_rcgr = 0x1e504, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s3_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap2_s4_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap2_s5_clk_src_init = { + .name = "gcc_qupv3_wrap2_s5_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap2_s5_clk_src = { + .cmd_rcgr = 0x1e640, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s3_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap2_s5_clk_src_init, +}; + +static const struct freq_tbl ftbl_gcc_qupv3_wrap2_s6_clk_src[] = { + F(7372800, P_GCC_GPLL0_OUT_EVEN, 1, 384, 15625), + F(14745600, P_GCC_GPLL0_OUT_EVEN, 1, 768, 15625), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(29491200, P_GCC_GPLL0_OUT_EVEN, 1, 1536, 15625), + F(32000000, P_GCC_GPLL0_OUT_EVEN, 1, 8, 75), + F(48000000, P_GCC_GPLL0_OUT_EVEN, 1, 4, 25), + F(51200000, P_GCC_GPLL0_OUT_EVEN, 1, 64, 375), + F(64000000, P_GCC_GPLL0_OUT_EVEN, 1, 16, 75), + F(75000000, P_GCC_GPLL0_OUT_EVEN, 4, 0, 0), + F(80000000, P_GCC_GPLL0_OUT_EVEN, 1, 4, 15), + F(96000000, P_GCC_GPLL0_OUT_EVEN, 1, 8, 25), + F(100000000, P_GCC_GPLL0_OUT_MAIN, 6, 0, 0), + F(102400000, P_GCC_GPLL0_OUT_EVEN, 1, 128, 375), + F(112000000, P_GCC_GPLL0_OUT_EVEN, 1, 28, 75), + F(117964800, P_GCC_GPLL0_OUT_EVEN, 1, 6144, 15625), + F(128000000, P_GCC_GPLL0_OUT_MAIN, 1, 16, 75), + { } +}; + +static struct clk_init_data gcc_qupv3_wrap2_s6_clk_src_init = { + .name = "gcc_qupv3_wrap2_s6_clk_src", + .parent_data = gcc_parent_data_5, + .num_parents = ARRAY_SIZE(gcc_parent_data_5), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap2_s6_clk_src = { + .cmd_rcgr = 0x1e77c, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_5, + .freq_tbl = ftbl_gcc_qupv3_wrap2_s6_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap2_s6_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap2_s7_clk_src_init = { + .name = "gcc_qupv3_wrap2_s7_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap2_s7_clk_src = { + .cmd_rcgr = 0x1e8b8, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap1_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap2_s7_clk_src_init, +}; + +static const struct freq_tbl ftbl_gcc_sdcc2_apps_clk_src[] = { + F(400000, P_BI_TCXO, 12, 1, 4), + F(25000000, P_GCC_GPLL0_OUT_EVEN, 12, 0, 0), + F(50000000, P_GCC_GPLL0_OUT_EVEN, 6, 0, 0), + F(100000000, P_GCC_GPLL0_OUT_EVEN, 3, 0, 0), + F(202000000, P_GCC_GPLL9_OUT_MAIN, 4, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { + .cmd_rcgr = 0x1401c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_8, + .freq_tbl = ftbl_gcc_sdcc2_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc2_apps_clk_src", + .parent_data = gcc_parent_data_8, + .num_parents = ARRAY_SIZE(gcc_parent_data_8), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_floor_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_sdcc4_apps_clk_src[] = { + F(400000, P_BI_TCXO, 12, 1, 4), + F(25000000, P_GCC_GPLL0_OUT_EVEN, 12, 0, 0), + F(75000000, P_GCC_GPLL0_OUT_EVEN, 4, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { + .cmd_rcgr = 0x1601c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_sdcc4_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc4_apps_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_floor_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_ufs_phy_axi_clk_src[] = { + F(25000000, P_GCC_GPLL0_OUT_EVEN, 12, 0, 0), + F(100000000, P_GCC_GPLL0_OUT_EVEN, 3, 0, 0), + F(201500000, P_GCC_GPLL4_OUT_MAIN, 4, 0, 0), + F(403000000, P_GCC_GPLL4_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_ufs_phy_axi_clk_src = { + .cmd_rcgr = 0x77034, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_ufs_phy_axi_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_axi_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_ufs_phy_ice_core_clk_src[] = { + F(100000000, P_GCC_GPLL0_OUT_EVEN, 3, 0, 0), + F(201500000, P_GCC_GPLL4_OUT_MAIN, 4, 0, 0), + F(403000000, P_GCC_GPLL4_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_ufs_phy_ice_core_clk_src = { + .cmd_rcgr = 0x7708c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_ufs_phy_ice_core_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_ice_core_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_ufs_phy_phy_aux_clk_src[] = { + F(9600000, P_BI_TCXO, 2, 0, 0), + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_ufs_phy_phy_aux_clk_src = { + .cmd_rcgr = 0x770c0, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_6, + .freq_tbl = ftbl_gcc_ufs_phy_phy_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_phy_aux_clk_src", + .parent_data = gcc_parent_data_6, + .num_parents = ARRAY_SIZE(gcc_parent_data_6), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_ufs_phy_unipro_core_clk_src = { + .cmd_rcgr = 0x770a4, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_ufs_phy_ice_core_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_unipro_core_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb30_prim_master_clk_src[] = { + F(66666667, P_GCC_GPLL0_OUT_EVEN, 4.5, 0, 0), + F(133333333, P_GCC_GPLL0_OUT_MAIN, 4.5, 0, 0), + F(200000000, P_GCC_GPLL0_OUT_MAIN, 3, 0, 0), + F(240000000, P_GCC_GPLL0_OUT_MAIN, 2.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_usb30_prim_master_clk_src = { + .cmd_rcgr = 0x39030, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_usb30_prim_master_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_master_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_usb30_prim_mock_utmi_clk_src = { + .cmd_rcgr = 0x39048, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_mock_utmi_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gcc_usb3_prim_phy_aux_clk_src = { + .cmd_rcgr = 0x39074, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_4, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_phy_aux_clk_src", + .parent_data = gcc_parent_data_4, + .num_parents = ARRAY_SIZE(gcc_parent_data_4), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_regmap_div gcc_qupv3_wrap1_s2_clk_src = { + .reg = 0x1828c, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s2_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_qspi_ref_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_regmap_div gcc_usb30_prim_mock_utmi_postdiv_clk_src = { + .reg = 0x39060, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_mock_utmi_postdiv_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb30_prim_mock_utmi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_branch gcc_aggre_noc_pcie_axi_clk = { + .halt_reg = 0x10068, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x10068, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(12), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_aggre_noc_pcie_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_aggre_ufs_phy_axi_clk = { + .halt_reg = 0x770f0, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x770f0, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x770f0, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_aggre_ufs_phy_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_aggre_usb3_prim_axi_clk = { + .halt_reg = 0x39090, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x39090, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x39090, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_aggre_usb3_prim_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb30_prim_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_boot_rom_ahb_clk = { + .halt_reg = 0x38004, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x38004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(10), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_boot_rom_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_camera_hf_axi_clk = { + .halt_reg = 0x26014, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x26014, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x26014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_camera_hf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_camera_sf_axi_clk = { + .halt_reg = 0x26024, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x26024, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x26024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_camera_sf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cfg_noc_pcie_anoc_ahb_clk = { + .halt_reg = 0x10050, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x10050, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(20), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_cfg_noc_pcie_anoc_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cfg_noc_usb3_prim_axi_clk = { + .halt_reg = 0x3908c, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x3908c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x3908c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_cfg_noc_usb3_prim_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb30_prim_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cnoc_pcie_sf_axi_clk = { + .halt_reg = 0x10058, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x10058, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(6), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_cnoc_pcie_sf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ddrss_gpu_axi_clk = { + .halt_reg = 0x71150, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x71150, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x71150, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ddrss_gpu_axi_clk", + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch gcc_ddrss_pcie_sf_qtb_clk = { + .halt_reg = 0x1007c, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x1007c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(19), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ddrss_pcie_sf_qtb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_disp_hf_axi_clk = { + .halt_reg = 0x27008, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0x27008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_disp_hf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_eva_axi0_clk = { + .halt_reg = 0x9f008, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x9f008, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x9f008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_eva_axi0_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_eva_axi0c_clk = { + .halt_reg = 0x9f018, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x9f018, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x9f018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_eva_axi0c_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp1_clk = { + .halt_reg = 0x64000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x64000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gp1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gp1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp2_clk = { + .halt_reg = 0x65000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x65000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gp2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gp2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp3_clk = { + .halt_reg = 0x66000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x66000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gp3_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gp3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_gemnoc_gfx_clk = { + .halt_reg = 0x71010, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x71010, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x71010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpu_gemnoc_gfx_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_gpll0_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(15), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpu_gpll0_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gpll0.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_gpll0_div_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(16), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gpu_gpll0_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gpll0_out_even.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_aux_clk = { + .halt_reg = 0x6b044, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(3), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie_0_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_cfg_ahb_clk = { + .halt_reg = 0x6b040, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6b040, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(2), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_cfg_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_mstr_axi_clk = { + .halt_reg = 0x6b030, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x6b030, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(1), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_mstr_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_phy_rchng_clk = { + .halt_reg = 0x6b064, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(22), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_phy_rchng_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie_0_phy_rchng_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_pipe_clk = { + .halt_reg = 0x6b054, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(4), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_pipe_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie_0_pipe_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_slv_axi_clk = { + .halt_reg = 0x6b020, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6b020, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_slv_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_slv_q2a_axi_clk = { + .halt_reg = 0x6b01c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(5), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_0_slv_q2a_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pdm2_clk = { + .halt_reg = 0x3300c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3300c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pdm2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pdm2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pdm_ahb_clk = { + .halt_reg = 0x33004, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x33004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x33004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pdm_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pdm_xo4_clk = { + .halt_reg = 0x33008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x33008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pdm_xo4_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_camera_cmd_ahb_clk = { + .halt_reg = 0x26010, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x26010, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x26010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_camera_cmd_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_camera_nrt_ahb_clk = { + .halt_reg = 0x26008, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x26008, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x26008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_camera_nrt_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_camera_rt_ahb_clk = { + .halt_reg = 0x2600c, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x2600c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x2600c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_camera_rt_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_gpu_ahb_clk = { + .halt_reg = 0x71008, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x71008, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x71008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_gpu_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_pcie_ahb_clk = { + .halt_reg = 0x6b018, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6b018, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(11), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_pcie_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_video_cv_cpu_ahb_clk = { + .halt_reg = 0x32014, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x32014, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x32014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_video_cv_cpu_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_video_cvp_ahb_clk = { + .halt_reg = 0x32008, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x32008, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x32008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_video_cvp_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_video_v_cpu_ahb_clk = { + .halt_reg = 0x32010, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x32010, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x32010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_video_v_cpu_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qmip_video_vcodec_ahb_clk = { + .halt_reg = 0x3200c, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x3200c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x3200c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qmip_video_vcodec_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_core_clk = { + .halt_reg = 0x23004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(8), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_core_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s0_clk = { + .halt_reg = 0x17004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(10), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s0_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s1_clk = { + .halt_reg = 0x17020, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(11), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s2_clk = { + .halt_reg = 0x1703c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(12), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s3_clk = { + .halt_reg = 0x17058, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(13), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s3_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s4_clk = { + .halt_reg = 0x17074, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(14), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s4_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s4_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s5_clk = { + .halt_reg = 0x17090, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(15), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s5_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s5_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s6_clk = { + .halt_reg = 0x170ac, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(16), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s6_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s6_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s7_clk = { + .halt_reg = 0x170c8, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(17), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s7_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s7_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s8_clk = { + .halt_reg = 0x170e4, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(14), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s8_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s8_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s9_clk = { + .halt_reg = 0x17100, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(15), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s9_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_i2c_s9_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_i2c_s_ahb_clk = { + .halt_reg = 0x23000, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x23000, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(7), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_i2c_s_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_core_2x_clk = { + .halt_reg = 0x2315c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(18), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_core_2x_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_core_clk = { + .halt_reg = 0x23148, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(19), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_core_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_qspi_ref_clk = { + .halt_reg = 0x188bc, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(29), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_qspi_ref_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_qspi_ref_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s0_clk = { + .halt_reg = 0x18004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(22), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s0_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s1_clk = { + .halt_reg = 0x18140, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(23), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s2_clk = { + .halt_reg = 0x1827c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(24), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s3_clk = { + .halt_reg = 0x18290, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(25), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s3_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s4_clk = { + .halt_reg = 0x183cc, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(26), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s4_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s4_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s5_clk = { + .halt_reg = 0x18508, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(27), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s5_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s5_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s6_clk = { + .halt_reg = 0x18644, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(28), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s6_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s6_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s7_clk = { + .halt_reg = 0x18780, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(16), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap1_s7_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap1_s7_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_core_2x_clk = { + .halt_reg = 0x232b4, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(3), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_core_2x_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_core_clk = { + .halt_reg = 0x232a0, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_core_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_ibi_ctrl_2_clk = { + .halt_reg = 0x1e9ec, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x1e9ec, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(27), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_ibi_ctrl_2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_ibi_ctrl_0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_ibi_ctrl_3_clk = { + .halt_reg = 0x1e9f0, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x1e9f0, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(28), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_ibi_ctrl_3_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_ibi_ctrl_0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_s0_clk = { + .halt_reg = 0x1e004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(4), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_s0_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_s0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_s1_clk = { + .halt_reg = 0x1e140, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(5), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_s1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_s1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_s2_clk = { + .halt_reg = 0x1e27c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(6), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_s2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_s2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_s3_clk = { + .halt_reg = 0x1e3b8, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(7), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_s3_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_s3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_s4_clk = { + .halt_reg = 0x1e4f4, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(8), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_s4_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_s4_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_s5_clk = { + .halt_reg = 0x1e630, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(9), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_s5_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_s5_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_s6_clk = { + .halt_reg = 0x1e76c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(10), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_s6_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_s6_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap2_s7_clk = { + .halt_reg = 0x1e8a8, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(17), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap2_s7_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qupv3_wrap2_s7_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_1_m_ahb_clk = { + .halt_reg = 0x23140, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x23140, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(20), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_1_m_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_1_s_ahb_clk = { + .halt_reg = 0x23144, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x23144, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52008, + .enable_mask = BIT(21), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_1_s_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_2_ibi_2_ahb_clk = { + .halt_reg = 0x1e9e4, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x1e9e4, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(25), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_2_ibi_2_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_2_ibi_3_ahb_clk = { + .halt_reg = 0x1e9e8, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x1e9e8, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(26), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_2_ibi_3_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_2_m_ahb_clk = { + .halt_reg = 0x23298, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x23298, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(2), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_2_m_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_2_s_ahb_clk = { + .halt_reg = 0x2329c, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x2329c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52010, + .enable_mask = BIT(1), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qupv3_wrap_2_s_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc2_ahb_clk = { + .halt_reg = 0x14014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x14014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc2_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc2_apps_clk = { + .halt_reg = 0x14004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x14004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc2_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sdcc2_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc4_ahb_clk = { + .halt_reg = 0x16014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x16014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc4_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc4_apps_clk = { + .halt_reg = 0x16004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x16004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc4_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sdcc4_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_ahb_clk = { + .halt_reg = 0x77028, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x77028, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77028, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_axi_clk = { + .halt_reg = 0x77018, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x77018, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_ice_core_clk = { + .halt_reg = 0x7707c, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x7707c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x7707c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_ice_core_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_ice_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_phy_aux_clk = { + .halt_reg = 0x770bc, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x770bc, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x770bc, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_phy_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_rx_symbol_0_clk = { + .halt_reg = 0x77030, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x77030, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_rx_symbol_0_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_rx_symbol_0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_rx_symbol_1_clk = { + .halt_reg = 0x770d8, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x770d8, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_rx_symbol_1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_rx_symbol_1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_tx_symbol_0_clk = { + .halt_reg = 0x7702c, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x7702c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_tx_symbol_0_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_tx_symbol_0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_unipro_core_clk = { + .halt_reg = 0x7706c, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x7706c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x7706c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ufs_phy_unipro_core_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_ufs_phy_unipro_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb30_prim_master_clk = { + .halt_reg = 0x39018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x39018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_master_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb30_prim_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb30_prim_mock_utmi_clk = { + .halt_reg = 0x3902c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3902c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_mock_utmi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb30_prim_mock_utmi_postdiv_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb30_prim_sleep_clk = { + .halt_reg = 0x39028, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x39028, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb30_prim_sleep_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_phy_aux_clk = { + .halt_reg = 0x39064, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x39064, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_phy_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb3_prim_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_phy_com_aux_clk = { + .halt_reg = 0x39068, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x39068, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_phy_com_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb3_prim_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_phy_pipe_clk = { + .halt_reg = 0x3906c, + .halt_check = BRANCH_HALT_DELAY, + .hwcg_reg = 0x3906c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x3906c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb3_prim_phy_pipe_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb3_prim_phy_pipe_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_video_axi0_clk = { + .halt_reg = 0x32018, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x32018, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x32018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_video_axi0_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_video_axi1_clk = { + .halt_reg = 0x32028, + .halt_check = BRANCH_HALT_SKIP, + .hwcg_reg = 0x32028, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x32028, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_video_axi1_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct gdsc gcc_pcie_0_gdsc = { + .gdscr = 0x6b004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, + .collapse_ctrl = 0x5214c, + .collapse_mask = BIT(0), + .pd = { + .name = "gcc_pcie_0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE, +}; + +static struct gdsc gcc_pcie_0_phy_gdsc = { + .gdscr = 0x6c000, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0x2, + .collapse_ctrl = 0x5214c, + .collapse_mask = BIT(2), + .pd = { + .name = "gcc_pcie_0_phy_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE, +}; + +static struct gdsc gcc_ufs_mem_phy_gdsc = { + .gdscr = 0x9e000, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0x2, + .pd = { + .name = "gcc_ufs_mem_phy_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, +}; + +static struct gdsc gcc_ufs_phy_gdsc = { + .gdscr = 0x77004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, + .pd = { + .name = "gcc_ufs_phy_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, +}; + +static struct gdsc gcc_usb30_prim_gdsc = { + .gdscr = 0x39004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, + .pd = { + .name = "gcc_usb30_prim_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, +}; + +static struct gdsc gcc_usb3_phy_gdsc = { + .gdscr = 0x50018, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0x2, + .pd = { + .name = "gcc_usb3_phy_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, +}; + +static struct clk_regmap *gcc_sm8750_clocks[] = { + [GCC_AGGRE_NOC_PCIE_AXI_CLK] = &gcc_aggre_noc_pcie_axi_clk.clkr, + [GCC_AGGRE_UFS_PHY_AXI_CLK] = &gcc_aggre_ufs_phy_axi_clk.clkr, + [GCC_AGGRE_USB3_PRIM_AXI_CLK] = &gcc_aggre_usb3_prim_axi_clk.clkr, + [GCC_BOOT_ROM_AHB_CLK] = &gcc_boot_rom_ahb_clk.clkr, + [GCC_CAMERA_HF_AXI_CLK] = &gcc_camera_hf_axi_clk.clkr, + [GCC_CAMERA_SF_AXI_CLK] = &gcc_camera_sf_axi_clk.clkr, + [GCC_CFG_NOC_PCIE_ANOC_AHB_CLK] = &gcc_cfg_noc_pcie_anoc_ahb_clk.clkr, + [GCC_CFG_NOC_USB3_PRIM_AXI_CLK] = &gcc_cfg_noc_usb3_prim_axi_clk.clkr, + [GCC_CNOC_PCIE_SF_AXI_CLK] = &gcc_cnoc_pcie_sf_axi_clk.clkr, + [GCC_DDRSS_GPU_AXI_CLK] = &gcc_ddrss_gpu_axi_clk.clkr, + [GCC_DDRSS_PCIE_SF_QTB_CLK] = &gcc_ddrss_pcie_sf_qtb_clk.clkr, + [GCC_DISP_HF_AXI_CLK] = &gcc_disp_hf_axi_clk.clkr, + [GCC_EVA_AXI0_CLK] = &gcc_eva_axi0_clk.clkr, + [GCC_EVA_AXI0C_CLK] = &gcc_eva_axi0c_clk.clkr, + [GCC_GP1_CLK] = &gcc_gp1_clk.clkr, + [GCC_GP1_CLK_SRC] = &gcc_gp1_clk_src.clkr, + [GCC_GP2_CLK] = &gcc_gp2_clk.clkr, + [GCC_GP2_CLK_SRC] = &gcc_gp2_clk_src.clkr, + [GCC_GP3_CLK] = &gcc_gp3_clk.clkr, + [GCC_GP3_CLK_SRC] = &gcc_gp3_clk_src.clkr, + [GCC_GPLL0] = &gcc_gpll0.clkr, + [GCC_GPLL0_OUT_EVEN] = &gcc_gpll0_out_even.clkr, + [GCC_GPLL1] = &gcc_gpll1.clkr, + [GCC_GPLL4] = &gcc_gpll4.clkr, + [GCC_GPLL7] = &gcc_gpll7.clkr, + [GCC_GPLL9] = &gcc_gpll9.clkr, + [GCC_GPU_GEMNOC_GFX_CLK] = &gcc_gpu_gemnoc_gfx_clk.clkr, + [GCC_GPU_GPLL0_CLK_SRC] = &gcc_gpu_gpll0_clk_src.clkr, + [GCC_GPU_GPLL0_DIV_CLK_SRC] = &gcc_gpu_gpll0_div_clk_src.clkr, + [GCC_PCIE_0_AUX_CLK] = &gcc_pcie_0_aux_clk.clkr, + [GCC_PCIE_0_AUX_CLK_SRC] = &gcc_pcie_0_aux_clk_src.clkr, + [GCC_PCIE_0_CFG_AHB_CLK] = &gcc_pcie_0_cfg_ahb_clk.clkr, + [GCC_PCIE_0_MSTR_AXI_CLK] = &gcc_pcie_0_mstr_axi_clk.clkr, + [GCC_PCIE_0_PHY_RCHNG_CLK] = &gcc_pcie_0_phy_rchng_clk.clkr, + [GCC_PCIE_0_PHY_RCHNG_CLK_SRC] = &gcc_pcie_0_phy_rchng_clk_src.clkr, + [GCC_PCIE_0_PIPE_CLK] = &gcc_pcie_0_pipe_clk.clkr, + [GCC_PCIE_0_PIPE_CLK_SRC] = &gcc_pcie_0_pipe_clk_src.clkr, + [GCC_PCIE_0_SLV_AXI_CLK] = &gcc_pcie_0_slv_axi_clk.clkr, + [GCC_PCIE_0_SLV_Q2A_AXI_CLK] = &gcc_pcie_0_slv_q2a_axi_clk.clkr, + [GCC_PDM2_CLK] = &gcc_pdm2_clk.clkr, + [GCC_PDM2_CLK_SRC] = &gcc_pdm2_clk_src.clkr, + [GCC_PDM_AHB_CLK] = &gcc_pdm_ahb_clk.clkr, + [GCC_PDM_XO4_CLK] = &gcc_pdm_xo4_clk.clkr, + [GCC_QMIP_CAMERA_CMD_AHB_CLK] = &gcc_qmip_camera_cmd_ahb_clk.clkr, + [GCC_QMIP_CAMERA_NRT_AHB_CLK] = &gcc_qmip_camera_nrt_ahb_clk.clkr, + [GCC_QMIP_CAMERA_RT_AHB_CLK] = &gcc_qmip_camera_rt_ahb_clk.clkr, + [GCC_QMIP_GPU_AHB_CLK] = &gcc_qmip_gpu_ahb_clk.clkr, + [GCC_QMIP_PCIE_AHB_CLK] = &gcc_qmip_pcie_ahb_clk.clkr, + [GCC_QMIP_VIDEO_CV_CPU_AHB_CLK] = &gcc_qmip_video_cv_cpu_ahb_clk.clkr, + [GCC_QMIP_VIDEO_CVP_AHB_CLK] = &gcc_qmip_video_cvp_ahb_clk.clkr, + [GCC_QMIP_VIDEO_V_CPU_AHB_CLK] = &gcc_qmip_video_v_cpu_ahb_clk.clkr, + [GCC_QMIP_VIDEO_VCODEC_AHB_CLK] = &gcc_qmip_video_vcodec_ahb_clk.clkr, + [GCC_QUPV3_I2C_CORE_CLK] = &gcc_qupv3_i2c_core_clk.clkr, + [GCC_QUPV3_I2C_S0_CLK] = &gcc_qupv3_i2c_s0_clk.clkr, + [GCC_QUPV3_I2C_S0_CLK_SRC] = &gcc_qupv3_i2c_s0_clk_src.clkr, + [GCC_QUPV3_I2C_S1_CLK] = &gcc_qupv3_i2c_s1_clk.clkr, + [GCC_QUPV3_I2C_S1_CLK_SRC] = &gcc_qupv3_i2c_s1_clk_src.clkr, + [GCC_QUPV3_I2C_S2_CLK] = &gcc_qupv3_i2c_s2_clk.clkr, + [GCC_QUPV3_I2C_S2_CLK_SRC] = &gcc_qupv3_i2c_s2_clk_src.clkr, + [GCC_QUPV3_I2C_S3_CLK] = &gcc_qupv3_i2c_s3_clk.clkr, + [GCC_QUPV3_I2C_S3_CLK_SRC] = &gcc_qupv3_i2c_s3_clk_src.clkr, + [GCC_QUPV3_I2C_S4_CLK] = &gcc_qupv3_i2c_s4_clk.clkr, + [GCC_QUPV3_I2C_S4_CLK_SRC] = &gcc_qupv3_i2c_s4_clk_src.clkr, + [GCC_QUPV3_I2C_S5_CLK] = &gcc_qupv3_i2c_s5_clk.clkr, + [GCC_QUPV3_I2C_S5_CLK_SRC] = &gcc_qupv3_i2c_s5_clk_src.clkr, + [GCC_QUPV3_I2C_S6_CLK] = &gcc_qupv3_i2c_s6_clk.clkr, + [GCC_QUPV3_I2C_S6_CLK_SRC] = &gcc_qupv3_i2c_s6_clk_src.clkr, + [GCC_QUPV3_I2C_S7_CLK] = &gcc_qupv3_i2c_s7_clk.clkr, + [GCC_QUPV3_I2C_S7_CLK_SRC] = &gcc_qupv3_i2c_s7_clk_src.clkr, + [GCC_QUPV3_I2C_S8_CLK] = &gcc_qupv3_i2c_s8_clk.clkr, + [GCC_QUPV3_I2C_S8_CLK_SRC] = &gcc_qupv3_i2c_s8_clk_src.clkr, + [GCC_QUPV3_I2C_S9_CLK] = &gcc_qupv3_i2c_s9_clk.clkr, + [GCC_QUPV3_I2C_S9_CLK_SRC] = &gcc_qupv3_i2c_s9_clk_src.clkr, + [GCC_QUPV3_I2C_S_AHB_CLK] = &gcc_qupv3_i2c_s_ahb_clk.clkr, + [GCC_QUPV3_WRAP1_CORE_2X_CLK] = &gcc_qupv3_wrap1_core_2x_clk.clkr, + [GCC_QUPV3_WRAP1_CORE_CLK] = &gcc_qupv3_wrap1_core_clk.clkr, + [GCC_QUPV3_WRAP1_QSPI_REF_CLK] = &gcc_qupv3_wrap1_qspi_ref_clk.clkr, + [GCC_QUPV3_WRAP1_QSPI_REF_CLK_SRC] = &gcc_qupv3_wrap1_qspi_ref_clk_src.clkr, + [GCC_QUPV3_WRAP1_S0_CLK] = &gcc_qupv3_wrap1_s0_clk.clkr, + [GCC_QUPV3_WRAP1_S0_CLK_SRC] = &gcc_qupv3_wrap1_s0_clk_src.clkr, + [GCC_QUPV3_WRAP1_S1_CLK] = &gcc_qupv3_wrap1_s1_clk.clkr, + [GCC_QUPV3_WRAP1_S1_CLK_SRC] = &gcc_qupv3_wrap1_s1_clk_src.clkr, + [GCC_QUPV3_WRAP1_S2_CLK] = &gcc_qupv3_wrap1_s2_clk.clkr, + [GCC_QUPV3_WRAP1_S2_CLK_SRC] = &gcc_qupv3_wrap1_s2_clk_src.clkr, + [GCC_QUPV3_WRAP1_S3_CLK] = &gcc_qupv3_wrap1_s3_clk.clkr, + [GCC_QUPV3_WRAP1_S3_CLK_SRC] = &gcc_qupv3_wrap1_s3_clk_src.clkr, + [GCC_QUPV3_WRAP1_S4_CLK] = &gcc_qupv3_wrap1_s4_clk.clkr, + [GCC_QUPV3_WRAP1_S4_CLK_SRC] = &gcc_qupv3_wrap1_s4_clk_src.clkr, + [GCC_QUPV3_WRAP1_S5_CLK] = &gcc_qupv3_wrap1_s5_clk.clkr, + [GCC_QUPV3_WRAP1_S5_CLK_SRC] = &gcc_qupv3_wrap1_s5_clk_src.clkr, + [GCC_QUPV3_WRAP1_S6_CLK] = &gcc_qupv3_wrap1_s6_clk.clkr, + [GCC_QUPV3_WRAP1_S6_CLK_SRC] = &gcc_qupv3_wrap1_s6_clk_src.clkr, + [GCC_QUPV3_WRAP1_S7_CLK] = &gcc_qupv3_wrap1_s7_clk.clkr, + [GCC_QUPV3_WRAP1_S7_CLK_SRC] = &gcc_qupv3_wrap1_s7_clk_src.clkr, + [GCC_QUPV3_WRAP2_CORE_2X_CLK] = &gcc_qupv3_wrap2_core_2x_clk.clkr, + [GCC_QUPV3_WRAP2_CORE_CLK] = &gcc_qupv3_wrap2_core_clk.clkr, + [GCC_QUPV3_WRAP2_IBI_CTRL_0_CLK_SRC] = &gcc_qupv3_wrap2_ibi_ctrl_0_clk_src.clkr, + [GCC_QUPV3_WRAP2_IBI_CTRL_2_CLK] = &gcc_qupv3_wrap2_ibi_ctrl_2_clk.clkr, + [GCC_QUPV3_WRAP2_IBI_CTRL_3_CLK] = &gcc_qupv3_wrap2_ibi_ctrl_3_clk.clkr, + [GCC_QUPV3_WRAP2_S0_CLK] = &gcc_qupv3_wrap2_s0_clk.clkr, + [GCC_QUPV3_WRAP2_S0_CLK_SRC] = &gcc_qupv3_wrap2_s0_clk_src.clkr, + [GCC_QUPV3_WRAP2_S1_CLK] = &gcc_qupv3_wrap2_s1_clk.clkr, + [GCC_QUPV3_WRAP2_S1_CLK_SRC] = &gcc_qupv3_wrap2_s1_clk_src.clkr, + [GCC_QUPV3_WRAP2_S2_CLK] = &gcc_qupv3_wrap2_s2_clk.clkr, + [GCC_QUPV3_WRAP2_S2_CLK_SRC] = &gcc_qupv3_wrap2_s2_clk_src.clkr, + [GCC_QUPV3_WRAP2_S3_CLK] = &gcc_qupv3_wrap2_s3_clk.clkr, + [GCC_QUPV3_WRAP2_S3_CLK_SRC] = &gcc_qupv3_wrap2_s3_clk_src.clkr, + [GCC_QUPV3_WRAP2_S4_CLK] = &gcc_qupv3_wrap2_s4_clk.clkr, + [GCC_QUPV3_WRAP2_S4_CLK_SRC] = &gcc_qupv3_wrap2_s4_clk_src.clkr, + [GCC_QUPV3_WRAP2_S5_CLK] = &gcc_qupv3_wrap2_s5_clk.clkr, + [GCC_QUPV3_WRAP2_S5_CLK_SRC] = &gcc_qupv3_wrap2_s5_clk_src.clkr, + [GCC_QUPV3_WRAP2_S6_CLK] = &gcc_qupv3_wrap2_s6_clk.clkr, + [GCC_QUPV3_WRAP2_S6_CLK_SRC] = &gcc_qupv3_wrap2_s6_clk_src.clkr, + [GCC_QUPV3_WRAP2_S7_CLK] = &gcc_qupv3_wrap2_s7_clk.clkr, + [GCC_QUPV3_WRAP2_S7_CLK_SRC] = &gcc_qupv3_wrap2_s7_clk_src.clkr, + [GCC_QUPV3_WRAP_1_M_AHB_CLK] = &gcc_qupv3_wrap_1_m_ahb_clk.clkr, + [GCC_QUPV3_WRAP_1_S_AHB_CLK] = &gcc_qupv3_wrap_1_s_ahb_clk.clkr, + [GCC_QUPV3_WRAP_2_IBI_2_AHB_CLK] = &gcc_qupv3_wrap_2_ibi_2_ahb_clk.clkr, + [GCC_QUPV3_WRAP_2_IBI_3_AHB_CLK] = &gcc_qupv3_wrap_2_ibi_3_ahb_clk.clkr, + [GCC_QUPV3_WRAP_2_M_AHB_CLK] = &gcc_qupv3_wrap_2_m_ahb_clk.clkr, + [GCC_QUPV3_WRAP_2_S_AHB_CLK] = &gcc_qupv3_wrap_2_s_ahb_clk.clkr, + [GCC_SDCC2_AHB_CLK] = &gcc_sdcc2_ahb_clk.clkr, + [GCC_SDCC2_APPS_CLK] = &gcc_sdcc2_apps_clk.clkr, + [GCC_SDCC2_APPS_CLK_SRC] = &gcc_sdcc2_apps_clk_src.clkr, + [GCC_SDCC4_AHB_CLK] = &gcc_sdcc4_ahb_clk.clkr, + [GCC_SDCC4_APPS_CLK] = &gcc_sdcc4_apps_clk.clkr, + [GCC_SDCC4_APPS_CLK_SRC] = &gcc_sdcc4_apps_clk_src.clkr, + [GCC_UFS_PHY_AHB_CLK] = &gcc_ufs_phy_ahb_clk.clkr, + [GCC_UFS_PHY_AXI_CLK] = &gcc_ufs_phy_axi_clk.clkr, + [GCC_UFS_PHY_AXI_CLK_SRC] = &gcc_ufs_phy_axi_clk_src.clkr, + [GCC_UFS_PHY_ICE_CORE_CLK] = &gcc_ufs_phy_ice_core_clk.clkr, + [GCC_UFS_PHY_ICE_CORE_CLK_SRC] = &gcc_ufs_phy_ice_core_clk_src.clkr, + [GCC_UFS_PHY_PHY_AUX_CLK] = &gcc_ufs_phy_phy_aux_clk.clkr, + [GCC_UFS_PHY_PHY_AUX_CLK_SRC] = &gcc_ufs_phy_phy_aux_clk_src.clkr, + [GCC_UFS_PHY_RX_SYMBOL_0_CLK] = &gcc_ufs_phy_rx_symbol_0_clk.clkr, + [GCC_UFS_PHY_RX_SYMBOL_0_CLK_SRC] = &gcc_ufs_phy_rx_symbol_0_clk_src.clkr, + [GCC_UFS_PHY_RX_SYMBOL_1_CLK] = &gcc_ufs_phy_rx_symbol_1_clk.clkr, + [GCC_UFS_PHY_RX_SYMBOL_1_CLK_SRC] = &gcc_ufs_phy_rx_symbol_1_clk_src.clkr, + [GCC_UFS_PHY_TX_SYMBOL_0_CLK] = &gcc_ufs_phy_tx_symbol_0_clk.clkr, + [GCC_UFS_PHY_TX_SYMBOL_0_CLK_SRC] = &gcc_ufs_phy_tx_symbol_0_clk_src.clkr, + [GCC_UFS_PHY_UNIPRO_CORE_CLK] = &gcc_ufs_phy_unipro_core_clk.clkr, + [GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC] = &gcc_ufs_phy_unipro_core_clk_src.clkr, + [GCC_USB30_PRIM_MASTER_CLK] = &gcc_usb30_prim_master_clk.clkr, + [GCC_USB30_PRIM_MASTER_CLK_SRC] = &gcc_usb30_prim_master_clk_src.clkr, + [GCC_USB30_PRIM_MOCK_UTMI_CLK] = &gcc_usb30_prim_mock_utmi_clk.clkr, + [GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC] = &gcc_usb30_prim_mock_utmi_clk_src.clkr, + [GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC] = &gcc_usb30_prim_mock_utmi_postdiv_clk_src.clkr, + [GCC_USB30_PRIM_SLEEP_CLK] = &gcc_usb30_prim_sleep_clk.clkr, + [GCC_USB3_PRIM_PHY_AUX_CLK] = &gcc_usb3_prim_phy_aux_clk.clkr, + [GCC_USB3_PRIM_PHY_AUX_CLK_SRC] = &gcc_usb3_prim_phy_aux_clk_src.clkr, + [GCC_USB3_PRIM_PHY_COM_AUX_CLK] = &gcc_usb3_prim_phy_com_aux_clk.clkr, + [GCC_USB3_PRIM_PHY_PIPE_CLK] = &gcc_usb3_prim_phy_pipe_clk.clkr, + [GCC_USB3_PRIM_PHY_PIPE_CLK_SRC] = &gcc_usb3_prim_phy_pipe_clk_src.clkr, + [GCC_VIDEO_AXI0_CLK] = &gcc_video_axi0_clk.clkr, + [GCC_VIDEO_AXI1_CLK] = &gcc_video_axi1_clk.clkr, +}; + +static struct gdsc *gcc_sm8750_gdscs[] = { + [GCC_PCIE_0_GDSC] = &gcc_pcie_0_gdsc, + [GCC_PCIE_0_PHY_GDSC] = &gcc_pcie_0_phy_gdsc, + [GCC_UFS_MEM_PHY_GDSC] = &gcc_ufs_mem_phy_gdsc, + [GCC_UFS_PHY_GDSC] = &gcc_ufs_phy_gdsc, + [GCC_USB30_PRIM_GDSC] = &gcc_usb30_prim_gdsc, + [GCC_USB3_PHY_GDSC] = &gcc_usb3_phy_gdsc, +}; + +static const struct qcom_reset_map gcc_sm8750_resets[] = { + [GCC_CAMERA_BCR] = { 0x26000 }, + [GCC_DISPLAY_BCR] = { 0x27000 }, + [GCC_EVA_BCR] = { 0x9f000 }, + [GCC_EVA_AXI0_CLK_ARES] = { 0x9f008, 2 }, + [GCC_EVA_AXI0C_CLK_ARES] = { 0x9f018, 2 }, + [GCC_GPU_BCR] = { 0x71000 }, + [GCC_PCIE_0_BCR] = { 0x6b000 }, + [GCC_PCIE_0_LINK_DOWN_BCR] = { 0x6c014 }, + [GCC_PCIE_0_NOCSR_COM_PHY_BCR] = { 0x6c020 }, + [GCC_PCIE_0_PHY_BCR] = { 0x6c01c }, + [GCC_PCIE_0_PHY_NOCSR_COM_PHY_BCR] = { 0x6c028 }, + [GCC_PCIE_PHY_BCR] = { 0x6f000 }, + [GCC_PCIE_PHY_CFG_AHB_BCR] = { 0x6f00c }, + [GCC_PCIE_PHY_COM_BCR] = { 0x6f010 }, + [GCC_PCIE_RSCC_BCR] = { 0x11000 }, + [GCC_PDM_BCR] = { 0x33000 }, + [GCC_QUPV3_WRAPPER_1_BCR] = { 0x18000 }, + [GCC_QUPV3_WRAPPER_2_BCR] = { 0x1e000 }, + [GCC_QUPV3_WRAPPER_I2C_BCR] = { 0x17000 }, + [GCC_QUSB2PHY_PRIM_BCR] = { 0x12000 }, + [GCC_QUSB2PHY_SEC_BCR] = { 0x12004 }, + [GCC_SDCC2_BCR] = { 0x14000 }, + [GCC_SDCC4_BCR] = { 0x16000 }, + [GCC_UFS_PHY_BCR] = { 0x77000 }, + [GCC_USB30_PRIM_BCR] = { 0x39000 }, + [GCC_USB3_DP_PHY_PRIM_BCR] = { 0x50008 }, + [GCC_USB3_DP_PHY_SEC_BCR] = { 0x50014 }, + [GCC_USB3_PHY_PRIM_BCR] = { 0x50000 }, + [GCC_USB3_PHY_SEC_BCR] = { 0x5000c }, + [GCC_USB3PHY_PHY_PRIM_BCR] = { 0x50004 }, + [GCC_USB3PHY_PHY_SEC_BCR] = { 0x50010 }, + [GCC_VIDEO_BCR] = { 0x32000 }, + [GCC_VIDEO_AXI0_CLK_ARES] = { 0x32018, 2 }, + [GCC_VIDEO_AXI1_CLK_ARES] = { 0x32028, 2 }, +}; + + +static const struct clk_rcg_dfs_data gcc_dfs_clocks[] = { + DEFINE_RCG_DFS(gcc_qupv3_wrap1_qspi_ref_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s0_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s1_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s3_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s4_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s5_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s6_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s7_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap2_s0_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap2_s1_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap2_s2_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap2_s3_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap2_s4_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap2_s5_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap2_s6_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap2_s7_clk_src), +}; + +static const struct regmap_config gcc_sm8750_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x1f41f0, + .fast_io = true, +}; + +static const struct qcom_cc_desc gcc_sm8750_desc = { + .config = &gcc_sm8750_regmap_config, + .clks = gcc_sm8750_clocks, + .num_clks = ARRAY_SIZE(gcc_sm8750_clocks), + .resets = gcc_sm8750_resets, + .num_resets = ARRAY_SIZE(gcc_sm8750_resets), + .gdscs = gcc_sm8750_gdscs, + .num_gdscs = ARRAY_SIZE(gcc_sm8750_gdscs), +}; + +static const struct of_device_id gcc_sm8750_match_table[] = { + { .compatible = "qcom,sm8750-gcc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gcc_sm8750_match_table); + +static int gcc_sm8750_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + int ret; + + regmap = qcom_cc_map(pdev, &gcc_sm8750_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + ret = qcom_cc_register_rcg_dfs(regmap, gcc_dfs_clocks, + ARRAY_SIZE(gcc_dfs_clocks)); + if (ret) + return ret; + + /* + * Keep clocks always enabled: + * gcc_cam_bist_mclk_ahb_clk + * gcc_camera_ahb_clk + * gcc_camera_xo_clk + * gcc_disp_ahb_clk + * gcc_eva_ahb_clk + * gcc_eva_xo_clk + * gcc_gpu_cfg_ahb_clk + * gcc_video_ahb_clk + * gcc_video_xo_clk + * gcc_pcie_rscc_cfg_ahb_clk + * gcc_pcie_rscc_xo_clk + */ + qcom_branch_set_clk_en(regmap, 0xa0004); + qcom_branch_set_clk_en(regmap, 0x26004); + qcom_branch_set_clk_en(regmap, 0x26034); + qcom_branch_set_clk_en(regmap, 0x27004); + qcom_branch_set_clk_en(regmap, 0x9f004); + qcom_branch_set_clk_en(regmap, 0x9f01c); + qcom_branch_set_clk_en(regmap, 0x71004); + qcom_branch_set_clk_en(regmap, 0x32004); + qcom_branch_set_clk_en(regmap, 0x32038); + regmap_update_bits(regmap, 0x52010, BIT(20), BIT(20)); + regmap_update_bits(regmap, 0x52010, BIT(21), BIT(21)); + + /* FORCE_MEM_CORE_ON for ufs phy ice core clocks */ + qcom_branch_set_force_mem_core(regmap, gcc_ufs_phy_ice_core_clk, true); + + return qcom_cc_really_probe(&pdev->dev, &gcc_sm8750_desc, regmap); +} + +static struct platform_driver gcc_sm8750_driver = { + .probe = gcc_sm8750_probe, + .driver = { + .name = "gcc-sm8750", + .of_match_table = gcc_sm8750_match_table, + }, +}; + +static int __init gcc_sm8750_init(void) +{ + return platform_driver_register(&gcc_sm8750_driver); +} +subsys_initcall(gcc_sm8750_init); + +static void __exit gcc_sm8750_exit(void) +{ + platform_driver_unregister(&gcc_sm8750_driver); +} +module_exit(gcc_sm8750_exit); + +MODULE_DESCRIPTION("QTI GCC SM8750 Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c index 8ea25aa25dff..7288af845434 100644 --- a/drivers/clk/qcom/gcc-x1e80100.c +++ b/drivers/clk/qcom/gcc-x1e80100.c @@ -6083,7 +6083,7 @@ static struct gdsc gcc_usb20_prim_gdsc = { .pd = { .name = "gcc_usb20_prim_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; diff --git a/drivers/clk/qcom/gpucc-x1p42100.c b/drivers/clk/qcom/gpucc-x1p42100.c new file mode 100644 index 000000000000..dba783339613 --- /dev/null +++ b/drivers/clk/qcom/gpucc-x1p42100.c @@ -0,0 +1,587 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023-2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-pll.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "common.h" +#include "gdsc.h" +#include "reset.h" + +enum { + DT_BI_TCXO, + DT_GPLL0_OUT_MAIN, + DT_GPLL0_OUT_MAIN_DIV, +}; + +enum { + P_BI_TCXO, + P_GPLL0_OUT_MAIN, + P_GPLL0_OUT_MAIN_DIV, + P_GPU_CC_PLL0_OUT_MAIN, + P_GPU_CC_PLL1_OUT_MAIN, +}; + +static const struct pll_vco lucid_ole_vco[] = { + { 249600000, 2300000000, 0 }, +}; + +/* 560.0 MHz Configuration */ +static const struct alpha_pll_config gpu_cc_pll0_config = { + .l = 0x1d, + .alpha = 0x2aaa, + .config_ctl_val = 0x20485699, + .config_ctl_hi_val = 0x00182261, + .config_ctl_hi1_val = 0x82aa299c, + .test_ctl_val = 0x00000000, + .test_ctl_hi_val = 0x00000003, + .test_ctl_hi1_val = 0x00009000, + .test_ctl_hi2_val = 0x00000034, + .user_ctl_val = 0x00000000, + .user_ctl_hi_val = 0x00000005, +}; + +static struct clk_alpha_pll gpu_cc_pll0 = { + .offset = 0x0, + .vco_table = lucid_ole_vco, + .num_vco = ARRAY_SIZE(lucid_ole_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID_OLE], + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_pll0", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_lucid_evo_ops, + }, + }, +}; + +/* 440.0 MHz Configuration */ +static const struct alpha_pll_config gpu_cc_pll1_config = { + .l = 0x16, + .alpha = 0xeaaa, + .config_ctl_val = 0x20485699, + .config_ctl_hi_val = 0x00182261, + .config_ctl_hi1_val = 0x82aa299c, + .test_ctl_val = 0x00000000, + .test_ctl_hi_val = 0x00000003, + .test_ctl_hi1_val = 0x00009000, + .test_ctl_hi2_val = 0x00000034, + .user_ctl_val = 0x00000000, + .user_ctl_hi_val = 0x00000005, +}; + +static struct clk_alpha_pll gpu_cc_pll1 = { + .offset = 0x1000, + .vco_table = lucid_ole_vco, + .num_vco = ARRAY_SIZE(lucid_ole_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID_OLE], + .clkr = { + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_pll1", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_lucid_evo_ops, + }, + }, +}; + +static const struct parent_map gpu_cc_parent_map_0[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 5 }, + { P_GPLL0_OUT_MAIN_DIV, 6 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_0[] = { + { .index = DT_BI_TCXO }, + { .index = DT_GPLL0_OUT_MAIN }, + { .index = DT_GPLL0_OUT_MAIN_DIV }, +}; + +static const struct parent_map gpu_cc_parent_map_1[] = { + { P_BI_TCXO, 0 }, + { P_GPU_CC_PLL0_OUT_MAIN, 1 }, + { P_GPU_CC_PLL1_OUT_MAIN, 3 }, + { P_GPLL0_OUT_MAIN, 5 }, + { P_GPLL0_OUT_MAIN_DIV, 6 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_1[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpu_cc_pll0.clkr.hw }, + { .hw = &gpu_cc_pll1.clkr.hw }, + { .index = DT_GPLL0_OUT_MAIN }, + { .index = DT_GPLL0_OUT_MAIN_DIV }, +}; + +static const struct parent_map gpu_cc_parent_map_2[] = { + { P_BI_TCXO, 0 }, + { P_GPU_CC_PLL1_OUT_MAIN, 3 }, + { P_GPLL0_OUT_MAIN, 5 }, + { P_GPLL0_OUT_MAIN_DIV, 6 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_2[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpu_cc_pll1.clkr.hw }, + { .index = DT_GPLL0_OUT_MAIN }, + { .index = DT_GPLL0_OUT_MAIN_DIV }, +}; + +static const struct freq_tbl ftbl_gpu_cc_ff_clk_src[] = { + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_ff_clk_src = { + .cmd_rcgr = 0x9474, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_0, + .freq_tbl = ftbl_gpu_cc_ff_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_ff_clk_src", + .parent_data = gpu_cc_parent_data_0, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gpu_cc_gmu_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(220000000, P_GPU_CC_PLL1_OUT_MAIN, 2, 0, 0), + F(550000000, P_GPU_CC_PLL1_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_gmu_clk_src = { + .cmd_rcgr = 0x9318, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_1, + .freq_tbl = ftbl_gpu_cc_gmu_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_gmu_clk_src", + .parent_data = gpu_cc_parent_data_1, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_rcg2 gpu_cc_hub_clk_src = { + .cmd_rcgr = 0x93ec, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_2, + .freq_tbl = ftbl_gpu_cc_ff_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_hub_clk_src", + .parent_data = gpu_cc_parent_data_2, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_2), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static struct clk_branch gpu_cc_ahb_clk = { + .halt_reg = 0x911c, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x911c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_hub_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_crc_ahb_clk = { + .halt_reg = 0x9120, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x9120, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_crc_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_hub_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_accu_shift_clk = { + .halt_reg = 0x9480, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x9480, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_cx_accu_shift_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_ff_clk = { + .halt_reg = 0x914c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x914c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_cx_ff_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_ff_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_gmu_clk = { + .halt_reg = 0x913c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x913c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_cx_gmu_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_gmu_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cxo_clk = { + .halt_reg = 0x9144, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x9144, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_cxo_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_freq_measure_clk = { + .halt_reg = 0x9008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x9008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_freq_measure_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_gx_accu_shift_clk = { + .halt_reg = 0x947c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x947c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_gx_accu_shift_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_gx_gmu_clk = { + .halt_reg = 0x90bc, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x90bc, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_gx_gmu_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_gmu_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_gx_vsense_clk = { + .halt_reg = 0x90b0, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x90b0, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_gx_vsense_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_hub_aon_clk = { + .halt_reg = 0x93e8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x93e8, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_hub_aon_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_hub_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_hub_cx_int_clk = { + .halt_reg = 0x9148, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x9148, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_hub_cx_int_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_hub_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_memnoc_gfx_clk = { + .halt_reg = 0x9150, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x9150, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_memnoc_gfx_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_mnd1x_0_gfx3d_clk = { + .halt_reg = 0x9288, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x9288, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_mnd1x_0_gfx3d_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_mnd1x_1_gfx3d_clk = { + .halt_reg = 0x928c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x928c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_mnd1x_1_gfx3d_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_sleep_clk = { + .halt_reg = 0x9134, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x9134, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_sleep_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct gdsc gpu_cc_cx_gdsc = { + .gdscr = 0x9108, + .gds_hw_ctrl = 0x953c, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, + .pd = { + .name = "gpu_cc_cx_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, +}; + +static struct gdsc gpu_cc_gx_gdsc = { + .gdscr = 0x905c, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, + .pd = { + .name = "gpu_cc_gx_gdsc", + .power_on = gdsc_gx_do_nothing_enable, + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = CLAMP_IO | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, +}; + +static struct clk_regmap *gpu_cc_x1p42100_clocks[] = { + [GPU_CC_AHB_CLK] = &gpu_cc_ahb_clk.clkr, + [GPU_CC_CRC_AHB_CLK] = &gpu_cc_crc_ahb_clk.clkr, + [GPU_CC_CX_ACCU_SHIFT_CLK] = &gpu_cc_cx_accu_shift_clk.clkr, + [GPU_CC_CX_FF_CLK] = &gpu_cc_cx_ff_clk.clkr, + [GPU_CC_CX_GMU_CLK] = &gpu_cc_cx_gmu_clk.clkr, + [GPU_CC_CXO_CLK] = &gpu_cc_cxo_clk.clkr, + [GPU_CC_FF_CLK_SRC] = &gpu_cc_ff_clk_src.clkr, + [GPU_CC_FREQ_MEASURE_CLK] = &gpu_cc_freq_measure_clk.clkr, + [GPU_CC_GMU_CLK_SRC] = &gpu_cc_gmu_clk_src.clkr, + [GPU_CC_GX_ACCU_SHIFT_CLK] = &gpu_cc_gx_accu_shift_clk.clkr, + [GPU_CC_GX_GMU_CLK] = &gpu_cc_gx_gmu_clk.clkr, + [GPU_CC_GX_VSENSE_CLK] = &gpu_cc_gx_vsense_clk.clkr, + [GPU_CC_HUB_AON_CLK] = &gpu_cc_hub_aon_clk.clkr, + [GPU_CC_HUB_CLK_SRC] = &gpu_cc_hub_clk_src.clkr, + [GPU_CC_HUB_CX_INT_CLK] = &gpu_cc_hub_cx_int_clk.clkr, + [GPU_CC_MEMNOC_GFX_CLK] = &gpu_cc_memnoc_gfx_clk.clkr, + [GPU_CC_MND1X_0_GFX3D_CLK] = &gpu_cc_mnd1x_0_gfx3d_clk.clkr, + [GPU_CC_MND1X_1_GFX3D_CLK] = &gpu_cc_mnd1x_1_gfx3d_clk.clkr, + [GPU_CC_PLL0] = &gpu_cc_pll0.clkr, + [GPU_CC_PLL1] = &gpu_cc_pll1.clkr, + [GPU_CC_SLEEP_CLK] = &gpu_cc_sleep_clk.clkr, +}; + +static struct gdsc *gpu_cc_x1p42100_gdscs[] = { + [GPU_CX_GDSC] = &gpu_cc_cx_gdsc, + [GPU_GX_GDSC] = &gpu_cc_gx_gdsc, +}; + +static const struct qcom_reset_map gpu_cc_x1p42100_resets[] = { + [GPU_CC_ACD_BCR] = { 0x9358 }, + [GPU_CC_CB_BCR] = { 0x93a0 }, + [GPU_CC_CX_BCR] = { 0x9104 }, + [GPU_CC_FAST_HUB_BCR] = { 0x93e4 }, + [GPU_CC_FF_BCR] = { 0x9470 }, + [GPU_CC_GFX3D_AON_BCR] = { 0x9198 }, + [GPU_CC_GMU_BCR] = { 0x9314 }, + [GPU_CC_GX_BCR] = { 0x9058 }, + [GPU_CC_XO_BCR] = { 0x9000 }, +}; + +static const struct regmap_config gpu_cc_x1p42100_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x9988, + .fast_io = true, +}; + +static struct qcom_cc_desc gpu_cc_x1p42100_desc = { + .config = &gpu_cc_x1p42100_regmap_config, + .clks = gpu_cc_x1p42100_clocks, + .num_clks = ARRAY_SIZE(gpu_cc_x1p42100_clocks), + .resets = gpu_cc_x1p42100_resets, + .num_resets = ARRAY_SIZE(gpu_cc_x1p42100_resets), + .gdscs = gpu_cc_x1p42100_gdscs, + .num_gdscs = ARRAY_SIZE(gpu_cc_x1p42100_gdscs), +}; + +static const struct of_device_id gpu_cc_x1p42100_match_table[] = { + { .compatible = "qcom,x1p42100-gpucc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gpu_cc_x1p42100_match_table); + +static int gpu_cc_x1p42100_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + int ret; + + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return ret; + + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) + return ret; + + regmap = qcom_cc_map(pdev, &gpu_cc_x1p42100_desc); + if (IS_ERR(regmap)) { + pm_runtime_put(&pdev->dev); + return PTR_ERR(regmap); + } + + clk_lucid_ole_pll_configure(&gpu_cc_pll0, regmap, &gpu_cc_pll0_config); + clk_lucid_ole_pll_configure(&gpu_cc_pll1, regmap, &gpu_cc_pll1_config); + + /* Keep some clocks always enabled */ + qcom_branch_set_clk_en(regmap, 0x93a4); /* GPU_CC_CB_CLK */ + qcom_branch_set_clk_en(regmap, 0x9004); /* GPU_CC_CXO_AON_CLK */ + qcom_branch_set_clk_en(regmap, 0x900c); /* GPU_CC_DEMET_CLK */ + + ret = qcom_cc_really_probe(&pdev->dev, &gpu_cc_x1p42100_desc, regmap); + + pm_runtime_put(&pdev->dev); + + return ret; +} + +static struct platform_driver gpu_cc_x1p42100_driver = { + .probe = gpu_cc_x1p42100_probe, + .driver = { + .name = "gpucc-x1p42100", + .of_match_table = gpu_cc_x1p42100_match_table, + }, +}; + +module_platform_driver(gpu_cc_x1p42100_driver); + +MODULE_DESCRIPTION("QTI GPUCC X1P42100 Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/qcom/ipq-cmn-pll.c b/drivers/clk/qcom/ipq-cmn-pll.c new file mode 100644 index 000000000000..432d4c4b7aa6 --- /dev/null +++ b/drivers/clk/qcom/ipq-cmn-pll.c @@ -0,0 +1,435 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +/* + * CMN PLL block expects the reference clock from on-board Wi-Fi block, + * and supplies fixed rate clocks as output to the networking hardware + * blocks and to GCC. The networking related blocks include PPE (packet + * process engine), the externally connected PHY or switch devices, and + * the PCS. + * + * On the IPQ9574 SoC, there are three clocks with 50 MHZ and one clock + * with 25 MHZ which are output from the CMN PLL to Ethernet PHY (or switch), + * and one clock with 353 MHZ to PPE. The other fixed rate output clocks + * are supplied to GCC (24 MHZ as XO and 32 KHZ as sleep clock), and to PCS + * with 31.25 MHZ. + * + * +---------+ + * | GCC | + * +--+---+--+ + * AHB CLK| |SYS CLK + * V V + * +-------+---+------+ + * | +-------------> eth0-50mhz + * REF CLK | IPQ9574 | + * -------->+ +-------------> eth1-50mhz + * | CMN PLL block | + * | +-------------> eth2-50mhz + * | | + * +----+----+----+---+-------------> eth-25mhz + * | | | + * V V V + * GCC PCS NSS/PPE + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define CMN_PLL_REFCLK_SRC_SELECTION 0x28 +#define CMN_PLL_REFCLK_SRC_DIV GENMASK(9, 8) + +#define CMN_PLL_LOCKED 0x64 +#define CMN_PLL_CLKS_LOCKED BIT(8) + +#define CMN_PLL_POWER_ON_AND_RESET 0x780 +#define CMN_ANA_EN_SW_RSTN BIT(6) + +#define CMN_PLL_REFCLK_CONFIG 0x784 +#define CMN_PLL_REFCLK_EXTERNAL BIT(9) +#define CMN_PLL_REFCLK_DIV GENMASK(8, 4) +#define CMN_PLL_REFCLK_INDEX GENMASK(3, 0) + +#define CMN_PLL_CTRL 0x78c +#define CMN_PLL_CTRL_LOCK_DETECT_EN BIT(15) + +#define CMN_PLL_DIVIDER_CTRL 0x794 +#define CMN_PLL_DIVIDER_CTRL_FACTOR GENMASK(9, 0) + +/** + * struct cmn_pll_fixed_output_clk - CMN PLL output clocks information + * @id: Clock specifier to be supplied + * @name: Clock name to be registered + * @rate: Clock rate + */ +struct cmn_pll_fixed_output_clk { + unsigned int id; + const char *name; + unsigned long rate; +}; + +/** + * struct clk_cmn_pll - CMN PLL hardware specific data + * @regmap: hardware regmap. + * @hw: handle between common and hardware-specific interfaces + */ +struct clk_cmn_pll { + struct regmap *regmap; + struct clk_hw hw; +}; + +#define CLK_PLL_OUTPUT(_id, _name, _rate) { \ + .id = _id, \ + .name = _name, \ + .rate = _rate, \ +} + +#define to_clk_cmn_pll(_hw) container_of(_hw, struct clk_cmn_pll, hw) + +static const struct regmap_config ipq_cmn_pll_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x7fc, + .fast_io = true, +}; + +static const struct cmn_pll_fixed_output_clk ipq9574_output_clks[] = { + CLK_PLL_OUTPUT(XO_24MHZ_CLK, "xo-24mhz", 24000000UL), + CLK_PLL_OUTPUT(SLEEP_32KHZ_CLK, "sleep-32khz", 32000UL), + CLK_PLL_OUTPUT(PCS_31P25MHZ_CLK, "pcs-31p25mhz", 31250000UL), + CLK_PLL_OUTPUT(NSS_1200MHZ_CLK, "nss-1200mhz", 1200000000UL), + CLK_PLL_OUTPUT(PPE_353MHZ_CLK, "ppe-353mhz", 353000000UL), + CLK_PLL_OUTPUT(ETH0_50MHZ_CLK, "eth0-50mhz", 50000000UL), + CLK_PLL_OUTPUT(ETH1_50MHZ_CLK, "eth1-50mhz", 50000000UL), + CLK_PLL_OUTPUT(ETH2_50MHZ_CLK, "eth2-50mhz", 50000000UL), + CLK_PLL_OUTPUT(ETH_25MHZ_CLK, "eth-25mhz", 25000000UL), +}; + +/* + * CMN PLL has the single parent clock, which supports the several + * possible parent clock rates, each parent clock rate is reflected + * by the specific reference index value in the hardware. + */ +static int ipq_cmn_pll_find_freq_index(unsigned long parent_rate) +{ + int index = -EINVAL; + + switch (parent_rate) { + case 25000000: + index = 3; + break; + case 31250000: + index = 4; + break; + case 40000000: + index = 6; + break; + case 48000000: + case 96000000: + /* + * Parent clock rate 48 MHZ and 96 MHZ take the same value + * of reference clock index. 96 MHZ needs the source clock + * divider to be programmed as 2. + */ + index = 7; + break; + case 50000000: + index = 8; + break; + default: + break; + } + + return index; +} + +static unsigned long clk_cmn_pll_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct clk_cmn_pll *cmn_pll = to_clk_cmn_pll(hw); + u32 val, factor; + + /* + * The value of CMN_PLL_DIVIDER_CTRL_FACTOR is automatically adjusted + * by HW according to the parent clock rate. + */ + regmap_read(cmn_pll->regmap, CMN_PLL_DIVIDER_CTRL, &val); + factor = FIELD_GET(CMN_PLL_DIVIDER_CTRL_FACTOR, val); + + return parent_rate * 2 * factor; +} + +static int clk_cmn_pll_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + int ret; + + /* Validate the rate of the single parent clock. */ + ret = ipq_cmn_pll_find_freq_index(req->best_parent_rate); + + return ret < 0 ? ret : 0; +} + +/* + * This function is used to initialize the CMN PLL to enable the fixed + * rate output clocks. It is expected to be configured once. + */ +static int clk_cmn_pll_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct clk_cmn_pll *cmn_pll = to_clk_cmn_pll(hw); + int ret, index; + u32 val; + + /* + * Configure the reference input clock selection as per the given + * parent clock. The output clock rates are always of fixed value. + */ + index = ipq_cmn_pll_find_freq_index(parent_rate); + if (index < 0) + return index; + + ret = regmap_update_bits(cmn_pll->regmap, CMN_PLL_REFCLK_CONFIG, + CMN_PLL_REFCLK_INDEX, + FIELD_PREP(CMN_PLL_REFCLK_INDEX, index)); + if (ret) + return ret; + + /* + * Update the source clock rate selection and source clock + * divider as 2 when the parent clock rate is 96 MHZ. + */ + if (parent_rate == 96000000) { + ret = regmap_update_bits(cmn_pll->regmap, CMN_PLL_REFCLK_CONFIG, + CMN_PLL_REFCLK_DIV, + FIELD_PREP(CMN_PLL_REFCLK_DIV, 2)); + if (ret) + return ret; + + ret = regmap_update_bits(cmn_pll->regmap, CMN_PLL_REFCLK_SRC_SELECTION, + CMN_PLL_REFCLK_SRC_DIV, + FIELD_PREP(CMN_PLL_REFCLK_SRC_DIV, 0)); + if (ret) + return ret; + } + + /* Enable PLL locked detect. */ + ret = regmap_set_bits(cmn_pll->regmap, CMN_PLL_CTRL, + CMN_PLL_CTRL_LOCK_DETECT_EN); + if (ret) + return ret; + + /* + * Reset the CMN PLL block to ensure the updated configurations + * take effect. + */ + ret = regmap_clear_bits(cmn_pll->regmap, CMN_PLL_POWER_ON_AND_RESET, + CMN_ANA_EN_SW_RSTN); + if (ret) + return ret; + + usleep_range(1000, 1200); + ret = regmap_set_bits(cmn_pll->regmap, CMN_PLL_POWER_ON_AND_RESET, + CMN_ANA_EN_SW_RSTN); + if (ret) + return ret; + + /* Stability check of CMN PLL output clocks. */ + return regmap_read_poll_timeout(cmn_pll->regmap, CMN_PLL_LOCKED, val, + (val & CMN_PLL_CLKS_LOCKED), + 100, 100 * USEC_PER_MSEC); +} + +static const struct clk_ops clk_cmn_pll_ops = { + .recalc_rate = clk_cmn_pll_recalc_rate, + .determine_rate = clk_cmn_pll_determine_rate, + .set_rate = clk_cmn_pll_set_rate, +}; + +static struct clk_hw *ipq_cmn_pll_clk_hw_register(struct platform_device *pdev) +{ + struct clk_parent_data pdata = { .index = 0 }; + struct device *dev = &pdev->dev; + struct clk_init_data init = {}; + struct clk_cmn_pll *cmn_pll; + struct regmap *regmap; + void __iomem *base; + int ret; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return ERR_CAST(base); + + regmap = devm_regmap_init_mmio(dev, base, &ipq_cmn_pll_regmap_config); + if (IS_ERR(regmap)) + return ERR_CAST(regmap); + + cmn_pll = devm_kzalloc(dev, sizeof(*cmn_pll), GFP_KERNEL); + if (!cmn_pll) + return ERR_PTR(-ENOMEM); + + init.name = "cmn_pll"; + init.parent_data = &pdata; + init.num_parents = 1; + init.ops = &clk_cmn_pll_ops; + + cmn_pll->hw.init = &init; + cmn_pll->regmap = regmap; + + ret = devm_clk_hw_register(dev, &cmn_pll->hw); + if (ret) + return ERR_PTR(ret); + + return &cmn_pll->hw; +} + +static int ipq_cmn_pll_register_clks(struct platform_device *pdev) +{ + const struct cmn_pll_fixed_output_clk *fixed_clk; + struct clk_hw_onecell_data *hw_data; + struct device *dev = &pdev->dev; + struct clk_hw *cmn_pll_hw; + unsigned int num_clks; + struct clk_hw *hw; + int ret, i; + + fixed_clk = ipq9574_output_clks; + num_clks = ARRAY_SIZE(ipq9574_output_clks); + + hw_data = devm_kzalloc(dev, struct_size(hw_data, hws, num_clks + 1), + GFP_KERNEL); + if (!hw_data) + return -ENOMEM; + + /* + * Register the CMN PLL clock, which is the parent clock of + * the fixed rate output clocks. + */ + cmn_pll_hw = ipq_cmn_pll_clk_hw_register(pdev); + if (IS_ERR(cmn_pll_hw)) + return PTR_ERR(cmn_pll_hw); + + /* Register the fixed rate output clocks. */ + for (i = 0; i < num_clks; i++) { + hw = clk_hw_register_fixed_rate_parent_hw(dev, fixed_clk[i].name, + cmn_pll_hw, 0, + fixed_clk[i].rate); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto unregister_fixed_clk; + } + + hw_data->hws[fixed_clk[i].id] = hw; + } + + /* + * Provide the CMN PLL clock. The clock rate of CMN PLL + * is configured to 12 GHZ by DT property assigned-clock-rates-u64. + */ + hw_data->hws[CMN_PLL_CLK] = cmn_pll_hw; + hw_data->num = num_clks + 1; + + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, hw_data); + if (ret) + goto unregister_fixed_clk; + + platform_set_drvdata(pdev, hw_data); + + return 0; + +unregister_fixed_clk: + while (i > 0) + clk_hw_unregister(hw_data->hws[fixed_clk[--i].id]); + + return ret; +} + +static int ipq_cmn_pll_clk_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + int ret; + + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; + + ret = devm_pm_clk_create(dev); + if (ret) + return ret; + + /* + * To access the CMN PLL registers, the GCC AHB & SYS clocks + * of CMN PLL block need to be enabled. + */ + ret = pm_clk_add(dev, "ahb"); + if (ret) + return dev_err_probe(dev, ret, "Fail to add AHB clock\n"); + + ret = pm_clk_add(dev, "sys"); + if (ret) + return dev_err_probe(dev, ret, "Fail to add SYS clock\n"); + + ret = pm_runtime_resume_and_get(dev); + if (ret) + return ret; + + /* Register CMN PLL clock and fixed rate output clocks. */ + ret = ipq_cmn_pll_register_clks(pdev); + pm_runtime_put(dev); + if (ret) + return dev_err_probe(dev, ret, + "Fail to register CMN PLL clocks\n"); + + return 0; +} + +static void ipq_cmn_pll_clk_remove(struct platform_device *pdev) +{ + struct clk_hw_onecell_data *hw_data = platform_get_drvdata(pdev); + int i; + + /* + * The clock with index CMN_PLL_CLK is unregistered by + * device management. + */ + for (i = 0; i < hw_data->num; i++) { + if (i != CMN_PLL_CLK) + clk_hw_unregister(hw_data->hws[i]); + } +} + +static const struct dev_pm_ops ipq_cmn_pll_pm_ops = { + SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL) +}; + +static const struct of_device_id ipq_cmn_pll_clk_ids[] = { + { .compatible = "qcom,ipq9574-cmn-pll", }, + { } +}; +MODULE_DEVICE_TABLE(of, ipq_cmn_pll_clk_ids); + +static struct platform_driver ipq_cmn_pll_clk_driver = { + .probe = ipq_cmn_pll_clk_probe, + .remove = ipq_cmn_pll_clk_remove, + .driver = { + .name = "ipq_cmn_pll", + .of_match_table = ipq_cmn_pll_clk_ids, + .pm = &ipq_cmn_pll_pm_ops, + }, +}; +module_platform_driver(ipq_cmn_pll_clk_driver); + +MODULE_DESCRIPTION("Qualcomm Technologies, Inc. IPQ CMN PLL Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/qcom/lpasscc-sm6115.c b/drivers/clk/qcom/lpasscc-sm6115.c new file mode 100644 index 000000000000..8ffdab71b948 --- /dev/null +++ b/drivers/clk/qcom/lpasscc-sm6115.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022, 2023 Linaro Limited + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "common.h" +#include "reset.h" + +static const struct qcom_reset_map lpass_audiocc_sm6115_resets[] = { + [LPASS_AUDIO_SWR_RX_CGCR] = { .reg = 0x98, .bit = 1, .udelay = 500 }, +}; + +static struct regmap_config lpass_audiocc_sm6115_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .name = "lpass-audio-csr", + .max_register = 0x1000, +}; + +static const struct qcom_cc_desc lpass_audiocc_sm6115_reset_desc = { + .config = &lpass_audiocc_sm6115_regmap_config, + .resets = lpass_audiocc_sm6115_resets, + .num_resets = ARRAY_SIZE(lpass_audiocc_sm6115_resets), +}; + +static const struct qcom_reset_map lpasscc_sm6115_resets[] = { + [LPASS_SWR_TX_CONFIG_CGCR] = { .reg = 0x100, .bit = 1, .udelay = 500 }, +}; + +static struct regmap_config lpasscc_sm6115_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .name = "lpass-tcsr", + .max_register = 0x1000, +}; + +static const struct qcom_cc_desc lpasscc_sm6115_reset_desc = { + .config = &lpasscc_sm6115_regmap_config, + .resets = lpasscc_sm6115_resets, + .num_resets = ARRAY_SIZE(lpasscc_sm6115_resets), +}; + +static const struct of_device_id lpasscc_sm6115_match_table[] = { + { + .compatible = "qcom,sm6115-lpassaudiocc", + .data = &lpass_audiocc_sm6115_reset_desc, + }, { + .compatible = "qcom,sm6115-lpasscc", + .data = &lpasscc_sm6115_reset_desc, + }, + { }, +}; +MODULE_DEVICE_TABLE(of, lpasscc_sm6115_match_table); + +static int lpasscc_sm6115_probe(struct platform_device *pdev) +{ + const struct qcom_cc_desc *desc = of_device_get_match_data(&pdev->dev); + + return qcom_cc_probe_by_index(pdev, 0, desc); +} + +static struct platform_driver lpasscc_sm6115_driver = { + .probe = lpasscc_sm6115_probe, + .driver = { + .name = "lpasscc-sm6115", + .of_match_table = lpasscc_sm6115_match_table, + }, +}; + +module_platform_driver(lpasscc_sm6115_driver); + +MODULE_DESCRIPTION("QTI LPASSCC SM6115 Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c index 3f41249c5ae4..20d1c43f35d9 100644 --- a/drivers/clk/qcom/mmcc-msm8960.c +++ b/drivers/clk/qcom/mmcc-msm8960.c @@ -37,6 +37,7 @@ enum { P_DSI2_PLL_DSICLK, P_DSI1_PLL_BYTECLK, P_DSI2_PLL_BYTECLK, + P_LVDS_PLL, }; #define F_MN(f, s, _m, _n) { .freq = f, .src = s, .m = _m, .n = _n } @@ -143,6 +144,20 @@ static const struct clk_parent_data mmcc_pxo_dsi2_dsi1[] = { { .fw_name = "dsi1pll", .name = "dsi1pll" }, }; +static const struct parent_map mmcc_pxo_dsi2_dsi1_lvds_map[] = { + { P_PXO, 0 }, + { P_DSI2_PLL_DSICLK, 1 }, + { P_LVDS_PLL, 2 }, + { P_DSI1_PLL_DSICLK, 3 }, +}; + +static const struct clk_parent_data mmcc_pxo_dsi2_dsi1_lvds[] = { + { .fw_name = "pxo", .name = "pxo_board" }, + { .fw_name = "dsi2pll", .name = "dsi2pll" }, + { .fw_name = "lvdspll", .name = "mpd4_lvds_pll" }, + { .fw_name = "dsi1pll", .name = "dsi1pll" }, +}; + static const struct parent_map mmcc_pxo_dsi1_dsi2_byte_map[] = { { P_PXO, 0 }, { P_DSI1_PLL_BYTECLK, 1 }, @@ -2439,26 +2454,42 @@ static struct clk_rcg dsi2_pixel_src = { }, .s = { .src_sel_shift = 0, - .parent_map = mmcc_pxo_dsi2_dsi1_map, + .parent_map = mmcc_pxo_dsi2_dsi1_lvds_map, }, .clkr = { .enable_reg = 0x0094, .enable_mask = BIT(2), .hw.init = &(struct clk_init_data){ .name = "dsi2_pixel_src", - .parent_data = mmcc_pxo_dsi2_dsi1, - .num_parents = ARRAY_SIZE(mmcc_pxo_dsi2_dsi1), + .parent_data = mmcc_pxo_dsi2_dsi1_lvds, + .num_parents = ARRAY_SIZE(mmcc_pxo_dsi2_dsi1_lvds), .ops = &clk_rcg_pixel_ops, }, }, }; +static struct clk_branch dsi2_pixel_lvds_src = { + .clkr = { + .enable_reg = 0x0094, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "dsi2_pixel_lvds_src", + .parent_hws = (const struct clk_hw*[]){ + &dsi2_pixel_src.clkr.hw + }, + .num_parents = 1, + .ops = &clk_branch_simple_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; + static struct clk_branch dsi2_pixel_clk = { .halt_reg = 0x01d0, .halt_bit = 19, .clkr = { .enable_reg = 0x0094, - .enable_mask = BIT(0), + .enable_mask = 0, .hw.init = &(struct clk_init_data){ .name = "mdp_pclk2_clk", .parent_hws = (const struct clk_hw*[]){ @@ -2471,6 +2502,24 @@ static struct clk_branch dsi2_pixel_clk = { }, }; +static struct clk_branch lvds_clk = { + .halt_reg = 0x024c, + .halt_bit = 6, + .clkr = { + .enable_reg = 0x0264, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "mdp_lvds_clk", + .parent_hws = (const struct clk_hw*[]){ + &dsi2_pixel_lvds_src.clkr.hw + }, + .num_parents = 1, + .ops = &clk_branch_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; + static struct clk_branch gfx2d0_ahb_clk = { .hwcg_reg = 0x0038, .hwcg_bit = 28, @@ -2799,6 +2848,8 @@ static struct clk_regmap *mmcc_msm8960_clks[] = { [CSIPHY1_TIMER_CLK] = &csiphy1_timer_clk.clkr, [CSIPHY0_TIMER_CLK] = &csiphy0_timer_clk.clkr, [PLL2] = &pll2.clkr, + [DSI2_PIXEL_LVDS_SRC] = &dsi2_pixel_lvds_src.clkr, + [LVDS_CLK] = &lvds_clk.clkr, }; static const struct qcom_reset_map mmcc_msm8960_resets[] = { @@ -2983,6 +3034,8 @@ static struct clk_regmap *mmcc_apq8064_clks[] = { [VCAP_CLK] = &vcap_clk.clkr, [VCAP_NPL_CLK] = &vcap_npl_clk.clkr, [PLL15] = &pll15.clkr, + [DSI2_PIXEL_LVDS_SRC] = &dsi2_pixel_lvds_src.clkr, + [LVDS_CLK] = &lvds_clk.clkr, }; static const struct qcom_reset_map mmcc_apq8064_resets[] = { diff --git a/drivers/clk/qcom/tcsrcc-sm8750.c b/drivers/clk/qcom/tcsrcc-sm8750.c new file mode 100644 index 000000000000..242e320986ef --- /dev/null +++ b/drivers/clk/qcom/tcsrcc-sm8750.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include + +#include + +#include "clk-branch.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "common.h" + +enum { + DT_BI_TCXO_PAD, +}; + +static struct clk_branch tcsr_pcie_0_clkref_en = { + .halt_reg = 0x0, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x0, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "tcsr_pcie_0_clkref_en", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch tcsr_ufs_clkref_en = { + .halt_reg = 0x1000, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "tcsr_ufs_clkref_en", + .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO_PAD, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch tcsr_usb2_clkref_en = { + .halt_reg = 0x2000, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x2000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "tcsr_usb2_clkref_en", + .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO_PAD, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch tcsr_usb3_clkref_en = { + .halt_reg = 0x3000, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x3000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "tcsr_usb3_clkref_en", + .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO_PAD, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_regmap *tcsr_cc_sm8750_clocks[] = { + [TCSR_PCIE_0_CLKREF_EN] = &tcsr_pcie_0_clkref_en.clkr, + [TCSR_UFS_CLKREF_EN] = &tcsr_ufs_clkref_en.clkr, + [TCSR_USB2_CLKREF_EN] = &tcsr_usb2_clkref_en.clkr, + [TCSR_USB3_CLKREF_EN] = &tcsr_usb3_clkref_en.clkr, +}; + +static const struct regmap_config tcsr_cc_sm8750_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x3000, + .fast_io = true, +}; + +static const struct qcom_cc_desc tcsr_cc_sm8750_desc = { + .config = &tcsr_cc_sm8750_regmap_config, + .clks = tcsr_cc_sm8750_clocks, + .num_clks = ARRAY_SIZE(tcsr_cc_sm8750_clocks), +}; + +static const struct of_device_id tcsr_cc_sm8750_match_table[] = { + { .compatible = "qcom,sm8750-tcsr" }, + { } +}; +MODULE_DEVICE_TABLE(of, tcsr_cc_sm8750_match_table); + +static int tcsr_cc_sm8750_probe(struct platform_device *pdev) +{ + return qcom_cc_probe(pdev, &tcsr_cc_sm8750_desc); +} + +static struct platform_driver tcsr_cc_sm8750_driver = { + .probe = tcsr_cc_sm8750_probe, + .driver = { + .name = "tcsr_cc-sm8750", + .of_match_table = tcsr_cc_sm8750_match_table, + }, +}; + +static int __init tcsr_cc_sm8750_init(void) +{ + return platform_driver_register(&tcsr_cc_sm8750_driver); +} +subsys_initcall(tcsr_cc_sm8750_init); + +static void __exit tcsr_cc_sm8750_exit(void) +{ + platform_driver_unregister(&tcsr_cc_sm8750_driver); +} +module_exit(tcsr_cc_sm8750_exit); + +MODULE_DESCRIPTION("QTI TCSR_CC SM8750 Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/ralink/clk-mtmips.c b/drivers/clk/ralink/clk-mtmips.c index 97b8ca0f9181..19d433034884 100644 --- a/drivers/clk/ralink/clk-mtmips.c +++ b/drivers/clk/ralink/clk-mtmips.c @@ -266,7 +266,6 @@ err_clk_unreg: } static struct mtmips_clk_fixed rt3883_fixed_clocks[] = { - CLK_FIXED("xtal", NULL, 40000000), CLK_FIXED("periph", "xtal", 40000000) }; diff --git a/drivers/clk/renesas/Kconfig b/drivers/clk/renesas/Kconfig index ff01f5f0ed20..5a4bc3f94d49 100644 --- a/drivers/clk/renesas/Kconfig +++ b/drivers/clk/renesas/Kconfig @@ -40,6 +40,7 @@ config CLK_RENESAS select CLK_R9A07G054 if ARCH_R9A07G054 select CLK_R9A08G045 if ARCH_R9A08G045 select CLK_R9A09G011 if ARCH_R9A09G011 + select CLK_R9A09G047 if ARCH_R9A09G047 select CLK_R9A09G057 if ARCH_R9A09G057 select CLK_SH73A0 if ARCH_SH73A0 @@ -194,6 +195,10 @@ config CLK_R9A09G011 bool "RZ/V2M clock support" if COMPILE_TEST select CLK_RZG2L +config CLK_R9A09G047 + bool "RZ/G3E clock support" if COMPILE_TEST + select CLK_RZV2H + config CLK_R9A09G057 bool "RZ/V2H(P) clock support" if COMPILE_TEST select CLK_RZV2H @@ -234,7 +239,7 @@ config CLK_RZG2L select RESET_CONTROLLER config CLK_RZV2H - bool "RZ/V2H(P) family clock support" if COMPILE_TEST + bool "RZ/{G3E,V2H(P)} family clock support" if COMPILE_TEST select RESET_CONTROLLER config CLK_RENESAS_VBATTB diff --git a/drivers/clk/renesas/Makefile b/drivers/clk/renesas/Makefile index 82efaa835ac7..2d6e746939c4 100644 --- a/drivers/clk/renesas/Makefile +++ b/drivers/clk/renesas/Makefile @@ -37,6 +37,7 @@ obj-$(CONFIG_CLK_R9A07G044) += r9a07g044-cpg.o obj-$(CONFIG_CLK_R9A07G054) += r9a07g044-cpg.o obj-$(CONFIG_CLK_R9A08G045) += r9a08g045-cpg.o obj-$(CONFIG_CLK_R9A09G011) += r9a09g011-cpg.o +obj-$(CONFIG_CLK_R9A09G047) += r9a09g047-cpg.o obj-$(CONFIG_CLK_R9A09G057) += r9a09g057-cpg.o obj-$(CONFIG_CLK_SH73A0) += clk-sh73a0.o diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index 55c8dd032fc3..d45571096b96 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -238,6 +238,10 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("pfc2", 917, R8A779G0_CLK_CP), DEF_MOD("pfc3", 918, R8A779G0_CLK_CP), DEF_MOD("tsc", 919, R8A779G0_CLK_CL16M), + DEF_MOD("vspx0", 1028, R8A779G0_CLK_S0D1_VIO), + DEF_MOD("vspx1", 1029, R8A779G0_CLK_S0D1_VIO), + DEF_MOD("fcpvx0", 1100, R8A779G0_CLK_S0D1_VIO), + DEF_MOD("fcpvx1", 1101, R8A779G0_CLK_S0D1_VIO), DEF_MOD("tsn", 2723, R8A779G0_CLK_S0D4_HSC), DEF_MOD("ssiu", 2926, R8A779G0_CLK_S0D6_PER), DEF_MOD("ssi", 2927, R8A779G0_CLK_S0D6_PER), diff --git a/drivers/clk/renesas/r8a779h0-cpg-mssr.c b/drivers/clk/renesas/r8a779h0-cpg-mssr.c index 9067e407cbc6..607fa815b6c1 100644 --- a/drivers/clk/renesas/r8a779h0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779h0-cpg-mssr.c @@ -177,6 +177,9 @@ static const struct mssr_mod_clk r8a779h0_mod_clks[] __initconst = { DEF_MOD("canfd0", 328, R8A779H0_CLK_SASYNCPERD2), DEF_MOD("csi40", 331, R8A779H0_CLK_CSI), DEF_MOD("csi41", 400, R8A779H0_CLK_CSI), + DEF_MOD("dis0", 411, R8A779H0_CLK_VIOBUSD2), + DEF_MOD("dsitxlink0", 415, R8A779H0_CLK_VIOBUSD2), + DEF_MOD("fcpvd0", 508, R8A779H0_CLK_VIOBUSD2), DEF_MOD("hscif0", 514, R8A779H0_CLK_SASYNCPERD1), DEF_MOD("hscif1", 515, R8A779H0_CLK_SASYNCPERD1), DEF_MOD("hscif2", 516, R8A779H0_CLK_SASYNCPERD1), @@ -225,6 +228,7 @@ static const struct mssr_mod_clk r8a779h0_mod_clks[] __initconst = { DEF_MOD("vin15", 811, R8A779H0_CLK_S0D4_VIO), DEF_MOD("vin16", 812, R8A779H0_CLK_S0D4_VIO), DEF_MOD("vin17", 813, R8A779H0_CLK_S0D4_VIO), + DEF_MOD("vspd0", 830, R8A779H0_CLK_VIOBUSD2), DEF_MOD("wdt1:wdt0", 907, R8A779H0_CLK_R), DEF_MOD("cmt0", 910, R8A779H0_CLK_R), DEF_MOD("cmt1", 911, R8A779H0_CLK_R), diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c index c1348e2d450c..dcda19318b2a 100644 --- a/drivers/clk/renesas/r9a06g032-clocks.c +++ b/drivers/clk/renesas/r9a06g032-clocks.c @@ -20,15 +20,24 @@ #include #include #include +#include #include #include #include #include #define R9A06G032_SYSCTRL_USB 0x00 -#define R9A06G032_SYSCTRL_USB_H2MODE (1<<1) +#define R9A06G032_SYSCTRL_USB_H2MODE BIT(1) #define R9A06G032_SYSCTRL_DMAMUX 0xA0 +#define R9A06G032_SYSCTRL_RSTEN 0x120 +#define R9A06G032_SYSCTRL_RSTEN_MRESET_EN BIT(0) +#define R9A06G032_SYSCTRL_RSTCTRL 0x198 +/* These work for both reset registers */ +#define R9A06G032_SYSCTRL_SWRST BIT(6) +#define R9A06G032_SYSCTRL_WDA7RST_1 BIT(2) +#define R9A06G032_SYSCTRL_WDA7RST_0 BIT(1) + /** * struct regbit - describe one bit in a register * @reg: offset of register relative to base address, @@ -1270,6 +1279,12 @@ static void r9a06g032_clocks_del_clk_provider(void *data) of_clk_del_provider(data); } +static int r9a06g032_restart_handler(struct sys_off_data *data) +{ + writel(R9A06G032_SYSCTRL_SWRST, sysctrl_priv->reg + R9A06G032_SYSCTRL_RSTCTRL); + return NOTIFY_DONE; +} + static void __init r9a06g032_init_h2mode(struct r9a06g032_priv *clocks) { struct device_node *usbf_np; @@ -1324,6 +1339,18 @@ static int __init r9a06g032_clocks_probe(struct platform_device *pdev) r9a06g032_init_h2mode(clocks); + /* Clear potentially pending resets */ + writel(R9A06G032_SYSCTRL_WDA7RST_0 | R9A06G032_SYSCTRL_WDA7RST_1, + clocks->reg + R9A06G032_SYSCTRL_RSTCTRL); + /* Allow software reset */ + writel(R9A06G032_SYSCTRL_SWRST | R9A06G032_SYSCTRL_RSTEN_MRESET_EN, + clocks->reg + R9A06G032_SYSCTRL_RSTEN); + + error = devm_register_sys_off_handler(dev, SYS_OFF_MODE_RESTART, SYS_OFF_PRIO_HIGH, + r9a06g032_restart_handler, NULL); + if (error) + dev_warn(dev, "couldn't register restart handler (%d)\n", error); + for (i = 0; i < ARRAY_SIZE(r9a06g032_clocks); ++i) { const struct r9a06g032_clkdesc *d = &r9a06g032_clocks[i]; const char *parent_name = d->source ? diff --git a/drivers/clk/renesas/r9a08g045-cpg.c b/drivers/clk/renesas/r9a08g045-cpg.c index b2ae8cdc4723..0e7e3bf05b52 100644 --- a/drivers/clk/renesas/r9a08g045-cpg.c +++ b/drivers/clk/renesas/r9a08g045-cpg.c @@ -187,6 +187,7 @@ static const struct cpg_core_clk r9a08g045_core_clks[] __initconst = { DEF_FIXED("OSC", R9A08G045_OSCCLK, CLK_EXTAL, 1, 1), DEF_FIXED("OSC2", R9A08G045_OSCCLK2, CLK_EXTAL, 1, 3), DEF_FIXED("HP", R9A08G045_CLK_HP, CLK_PLL6, 1, 2), + DEF_FIXED("TSU", R9A08G045_CLK_TSU, CLK_PLL2_DIV2, 1, 8), }; static const struct rzg2l_mod_clk r9a08g045_mod_clks[] = { @@ -209,6 +210,14 @@ static const struct rzg2l_mod_clk r9a08g045_mod_clks[] = { DEF_MOD("sdhi2_imclk2", R9A08G045_SDHI2_IMCLK2, CLK_SD2_DIV4, 0x554, 9), DEF_MOD("sdhi2_clk_hs", R9A08G045_SDHI2_CLK_HS, R9A08G045_CLK_SD2, 0x554, 10), DEF_MOD("sdhi2_aclk", R9A08G045_SDHI2_ACLK, R9A08G045_CLK_P1, 0x554, 11), + DEF_MOD("ssi0_pclk2", R9A08G045_SSI0_PCLK2, R9A08G045_CLK_P0, 0x570, 0), + DEF_MOD("ssi0_sfr", R9A08G045_SSI0_PCLK_SFR, R9A08G045_CLK_P0, 0x570, 1), + DEF_MOD("ssi1_pclk2", R9A08G045_SSI1_PCLK2, R9A08G045_CLK_P0, 0x570, 2), + DEF_MOD("ssi1_sfr", R9A08G045_SSI1_PCLK_SFR, R9A08G045_CLK_P0, 0x570, 3), + DEF_MOD("ssi2_pclk2", R9A08G045_SSI2_PCLK2, R9A08G045_CLK_P0, 0x570, 4), + DEF_MOD("ssi2_sfr", R9A08G045_SSI2_PCLK_SFR, R9A08G045_CLK_P0, 0x570, 5), + DEF_MOD("ssi3_pclk2", R9A08G045_SSI3_PCLK2, R9A08G045_CLK_P0, 0x570, 6), + DEF_MOD("ssi3_sfr", R9A08G045_SSI3_PCLK_SFR, R9A08G045_CLK_P0, 0x570, 7), DEF_MOD("usb0_host", R9A08G045_USB_U2H0_HCLK, R9A08G045_CLK_P1, 0x578, 0), DEF_MOD("usb1_host", R9A08G045_USB_U2H1_HCLK, R9A08G045_CLK_P1, 0x578, 1), DEF_MOD("usb0_func", R9A08G045_USB_U2P_EXR_CPUCLK, R9A08G045_CLK_P1, 0x578, 2), @@ -224,7 +233,14 @@ static const struct rzg2l_mod_clk r9a08g045_mod_clks[] = { DEF_MOD("i2c2_pclk", R9A08G045_I2C2_PCLK, R9A08G045_CLK_P0, 0x580, 2), DEF_MOD("i2c3_pclk", R9A08G045_I2C3_PCLK, R9A08G045_CLK_P0, 0x580, 3), DEF_MOD("scif0_clk_pck", R9A08G045_SCIF0_CLK_PCK, R9A08G045_CLK_P0, 0x584, 0), + DEF_MOD("scif1_clk_pck", R9A08G045_SCIF1_CLK_PCK, R9A08G045_CLK_P0, 0x584, 1), + DEF_MOD("scif2_clk_pck", R9A08G045_SCIF2_CLK_PCK, R9A08G045_CLK_P0, 0x584, 2), + DEF_MOD("scif3_clk_pck", R9A08G045_SCIF3_CLK_PCK, R9A08G045_CLK_P0, 0x584, 3), + DEF_MOD("scif4_clk_pck", R9A08G045_SCIF4_CLK_PCK, R9A08G045_CLK_P0, 0x584, 4), + DEF_MOD("scif5_clk_pck", R9A08G045_SCIF5_CLK_PCK, R9A08G045_CLK_P0, 0x584, 5), DEF_MOD("gpio_hclk", R9A08G045_GPIO_HCLK, R9A08G045_OSCCLK, 0x598, 0), + DEF_MOD("adc_adclk", R9A08G045_ADC_ADCLK, R9A08G045_CLK_TSU, 0x5a8, 0), + DEF_MOD("adc_pclk", R9A08G045_ADC_PCLK, R9A08G045_CLK_TSU, 0x5a8, 1), DEF_MOD("vbat_bclk", R9A08G045_VBAT_BCLK, R9A08G045_OSCCLK, 0x614, 0), }; @@ -238,6 +254,10 @@ static const struct rzg2l_reset r9a08g045_resets[] = { DEF_RST(R9A08G045_SDHI0_IXRST, 0x854, 0), DEF_RST(R9A08G045_SDHI1_IXRST, 0x854, 1), DEF_RST(R9A08G045_SDHI2_IXRST, 0x854, 2), + DEF_RST(R9A08G045_SSI0_RST_M2_REG, 0x870, 0), + DEF_RST(R9A08G045_SSI1_RST_M2_REG, 0x870, 1), + DEF_RST(R9A08G045_SSI2_RST_M2_REG, 0x870, 2), + DEF_RST(R9A08G045_SSI3_RST_M2_REG, 0x870, 3), DEF_RST(R9A08G045_USB_U2H0_HRESETN, 0x878, 0), DEF_RST(R9A08G045_USB_U2H1_HRESETN, 0x878, 1), DEF_RST(R9A08G045_USB_U2P_EXL_SYSRST, 0x878, 2), @@ -249,9 +269,16 @@ static const struct rzg2l_reset r9a08g045_resets[] = { DEF_RST(R9A08G045_I2C2_MRST, 0x880, 2), DEF_RST(R9A08G045_I2C3_MRST, 0x880, 3), DEF_RST(R9A08G045_SCIF0_RST_SYSTEM_N, 0x884, 0), + DEF_RST(R9A08G045_SCIF1_RST_SYSTEM_N, 0x884, 1), + DEF_RST(R9A08G045_SCIF2_RST_SYSTEM_N, 0x884, 2), + DEF_RST(R9A08G045_SCIF3_RST_SYSTEM_N, 0x884, 3), + DEF_RST(R9A08G045_SCIF4_RST_SYSTEM_N, 0x884, 4), + DEF_RST(R9A08G045_SCIF5_RST_SYSTEM_N, 0x884, 5), DEF_RST(R9A08G045_GPIO_RSTN, 0x898, 0), DEF_RST(R9A08G045_GPIO_PORT_RESETN, 0x898, 1), DEF_RST(R9A08G045_GPIO_SPARE_RESETN, 0x898, 2), + DEF_RST(R9A08G045_ADC_PRESETN, 0x8a8, 0), + DEF_RST(R9A08G045_ADC_ADRST_N, 0x8a8, 1), DEF_RST(R9A08G045_VBAT_BRESETN, 0x914, 0), }; @@ -286,6 +313,14 @@ static const struct rzg2l_cpg_pm_domain_init_data r9a08g045_pm_domains[] = { DEF_REG_CONF(CPG_BUS_PERI_COM_MSTOP, BIT(1)), 0), DEF_PD("sdhi2", R9A08G045_PD_SDHI2, DEF_REG_CONF(CPG_BUS_PERI_COM_MSTOP, BIT(11)), 0), + DEF_PD("ssi0", R9A08G045_PD_SSI0, + DEF_REG_CONF(CPG_BUS_MCPU1_MSTOP, BIT(10)), 0), + DEF_PD("ssi1", R9A08G045_PD_SSI1, + DEF_REG_CONF(CPG_BUS_MCPU1_MSTOP, BIT(11)), 0), + DEF_PD("ssi2", R9A08G045_PD_SSI2, + DEF_REG_CONF(CPG_BUS_MCPU1_MSTOP, BIT(12)), 0), + DEF_PD("ssi3", R9A08G045_PD_SSI3, + DEF_REG_CONF(CPG_BUS_MCPU1_MSTOP, BIT(13)), 0), DEF_PD("usb0", R9A08G045_PD_USB0, DEF_REG_CONF(CPG_BUS_PERI_COM_MSTOP, GENMASK(6, 5)), 0), DEF_PD("usb1", R9A08G045_PD_USB1, @@ -306,6 +341,18 @@ static const struct rzg2l_cpg_pm_domain_init_data r9a08g045_pm_domains[] = { DEF_REG_CONF(CPG_BUS_MCPU2_MSTOP, BIT(13)), 0), DEF_PD("scif0", R9A08G045_PD_SCIF0, DEF_REG_CONF(CPG_BUS_MCPU2_MSTOP, BIT(1)), 0), + DEF_PD("scif1", R9A08G045_PD_SCIF1, + DEF_REG_CONF(CPG_BUS_MCPU2_MSTOP, BIT(2)), 0), + DEF_PD("scif2", R9A08G045_PD_SCIF2, + DEF_REG_CONF(CPG_BUS_MCPU2_MSTOP, BIT(3)), 0), + DEF_PD("scif3", R9A08G045_PD_SCIF3, + DEF_REG_CONF(CPG_BUS_MCPU2_MSTOP, BIT(4)), 0), + DEF_PD("scif4", R9A08G045_PD_SCIF4, + DEF_REG_CONF(CPG_BUS_MCPU2_MSTOP, BIT(5)), 0), + DEF_PD("scif5", R9A08G045_PD_SCIF5, + DEF_REG_CONF(CPG_BUS_MCPU3_MSTOP, BIT(4)), 0), + DEF_PD("adc", R9A08G045_PD_ADC, + DEF_REG_CONF(CPG_BUS_MCPU2_MSTOP, BIT(14)), 0), DEF_PD("vbat", R9A08G045_PD_VBAT, DEF_REG_CONF(CPG_BUS_MCPU3_MSTOP, BIT(8)), GENPD_FLAG_ALWAYS_ON), diff --git a/drivers/clk/renesas/r9a09g047-cpg.c b/drivers/clk/renesas/r9a09g047-cpg.c new file mode 100644 index 000000000000..536d922bed70 --- /dev/null +++ b/drivers/clk/renesas/r9a09g047-cpg.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Renesas RZ/G3E CPG driver + * + * Copyright (C) 2024 Renesas Electronics Corp. + */ + +#include +#include +#include +#include + +#include + +#include "rzv2h-cpg.h" + +enum clk_ids { + /* Core Clock Outputs exported to DT */ + LAST_DT_CORE_CLK = R9A09G047_IOTOP_0_SHCLK, + + /* External Input Clocks */ + CLK_AUDIO_EXTAL, + CLK_RTXIN, + CLK_QEXTAL, + + /* PLL Clocks */ + CLK_PLLCM33, + CLK_PLLCLN, + CLK_PLLDTY, + CLK_PLLCA55, + + /* Internal Core Clocks */ + CLK_PLLCM33_DIV16, + CLK_PLLCLN_DIV16, + CLK_PLLDTY_ACPU, + CLK_PLLDTY_ACPU_DIV4, + + /* Module Clocks */ + MOD_CLK_BASE, +}; + +static const struct clk_div_table dtable_1_8[] = { + {0, 1}, + {1, 2}, + {2, 4}, + {3, 8}, + {0, 0}, +}; + +static const struct clk_div_table dtable_2_64[] = { + {0, 2}, + {1, 4}, + {2, 8}, + {3, 16}, + {4, 64}, + {0, 0}, +}; + +static const struct cpg_core_clk r9a09g047_core_clks[] __initconst = { + /* External Clock Inputs */ + DEF_INPUT("audio_extal", CLK_AUDIO_EXTAL), + DEF_INPUT("rtxin", CLK_RTXIN), + DEF_INPUT("qextal", CLK_QEXTAL), + + /* PLL Clocks */ + DEF_FIXED(".pllcm33", CLK_PLLCM33, CLK_QEXTAL, 200, 3), + DEF_FIXED(".pllcln", CLK_PLLCLN, CLK_QEXTAL, 200, 3), + DEF_FIXED(".plldty", CLK_PLLDTY, CLK_QEXTAL, 200, 3), + DEF_PLL(".pllca55", CLK_PLLCA55, CLK_QEXTAL, PLL_CONF(0x64)), + + /* Internal Core Clocks */ + DEF_FIXED(".pllcm33_div16", CLK_PLLCM33_DIV16, CLK_PLLCM33, 1, 16), + + DEF_FIXED(".pllcln_div16", CLK_PLLCLN_DIV16, CLK_PLLCLN, 1, 16), + + DEF_DDIV(".plldty_acpu", CLK_PLLDTY_ACPU, CLK_PLLDTY, CDDIV0_DIVCTL2, dtable_2_64), + DEF_FIXED(".plldty_acpu_div4", CLK_PLLDTY_ACPU_DIV4, CLK_PLLDTY_ACPU, 1, 4), + + /* Core Clocks */ + DEF_FIXED("sys_0_pclk", R9A09G047_SYS_0_PCLK, CLK_QEXTAL, 1, 1), + DEF_DDIV("ca55_0_coreclk0", R9A09G047_CA55_0_CORECLK0, CLK_PLLCA55, + CDDIV1_DIVCTL0, dtable_1_8), + DEF_DDIV("ca55_0_coreclk1", R9A09G047_CA55_0_CORECLK1, CLK_PLLCA55, + CDDIV1_DIVCTL1, dtable_1_8), + DEF_DDIV("ca55_0_coreclk2", R9A09G047_CA55_0_CORECLK2, CLK_PLLCA55, + CDDIV1_DIVCTL2, dtable_1_8), + DEF_DDIV("ca55_0_coreclk3", R9A09G047_CA55_0_CORECLK3, CLK_PLLCA55, + CDDIV1_DIVCTL3, dtable_1_8), + DEF_FIXED("iotop_0_shclk", R9A09G047_IOTOP_0_SHCLK, CLK_PLLCM33_DIV16, 1, 1), +}; + +static const struct rzv2h_mod_clk r9a09g047_mod_clks[] __initconst = { + DEF_MOD_CRITICAL("gic_0_gicclk", CLK_PLLDTY_ACPU_DIV4, 1, 3, 0, 19, + BUS_MSTOP(3, BIT(5))), + DEF_MOD("scif_0_clk_pck", CLK_PLLCM33_DIV16, 8, 15, 4, 15, + BUS_MSTOP(3, BIT(14))), + DEF_MOD("riic_8_ckm", CLK_PLLCM33_DIV16, 9, 3, 4, 19, + BUS_MSTOP(3, BIT(13))), + DEF_MOD("riic_0_ckm", CLK_PLLCLN_DIV16, 9, 4, 4, 20, + BUS_MSTOP(1, BIT(1))), + DEF_MOD("riic_1_ckm", CLK_PLLCLN_DIV16, 9, 5, 4, 21, + BUS_MSTOP(1, BIT(2))), + DEF_MOD("riic_2_ckm", CLK_PLLCLN_DIV16, 9, 6, 4, 22, + BUS_MSTOP(1, BIT(3))), + DEF_MOD("riic_3_ckm", CLK_PLLCLN_DIV16, 9, 7, 4, 23, + BUS_MSTOP(1, BIT(4))), + DEF_MOD("riic_4_ckm", CLK_PLLCLN_DIV16, 9, 8, 4, 24, + BUS_MSTOP(1, BIT(5))), + DEF_MOD("riic_5_ckm", CLK_PLLCLN_DIV16, 9, 9, 4, 25, + BUS_MSTOP(1, BIT(6))), + DEF_MOD("riic_6_ckm", CLK_PLLCLN_DIV16, 9, 10, 4, 26, + BUS_MSTOP(1, BIT(7))), + DEF_MOD("riic_7_ckm", CLK_PLLCLN_DIV16, 9, 11, 4, 27, + BUS_MSTOP(1, BIT(8))), +}; + +static const struct rzv2h_reset r9a09g047_resets[] __initconst = { + DEF_RST(3, 0, 1, 1), /* SYS_0_PRESETN */ + DEF_RST(3, 8, 1, 9), /* GIC_0_GICRESET_N */ + DEF_RST(3, 9, 1, 10), /* GIC_0_DBG_GICRESET_N */ + DEF_RST(9, 5, 4, 6), /* SCIF_0_RST_SYSTEM_N */ + DEF_RST(9, 8, 4, 9), /* RIIC_0_MRST */ + DEF_RST(9, 9, 4, 10), /* RIIC_1_MRST */ + DEF_RST(9, 10, 4, 11), /* RIIC_2_MRST */ + DEF_RST(9, 11, 4, 12), /* RIIC_3_MRST */ + DEF_RST(9, 12, 4, 13), /* RIIC_4_MRST */ + DEF_RST(9, 13, 4, 14), /* RIIC_5_MRST */ + DEF_RST(9, 14, 4, 15), /* RIIC_6_MRST */ + DEF_RST(9, 15, 4, 16), /* RIIC_7_MRST */ + DEF_RST(10, 0, 4, 17), /* RIIC_8_MRST */ +}; + +const struct rzv2h_cpg_info r9a09g047_cpg_info __initconst = { + /* Core Clocks */ + .core_clks = r9a09g047_core_clks, + .num_core_clks = ARRAY_SIZE(r9a09g047_core_clks), + .last_dt_core_clk = LAST_DT_CORE_CLK, + .num_total_core_clks = MOD_CLK_BASE, + + /* Module Clocks */ + .mod_clks = r9a09g047_mod_clks, + .num_mod_clks = ARRAY_SIZE(r9a09g047_mod_clks), + .num_hw_mod_clks = 28 * 16, + + /* Resets */ + .resets = r9a09g047_resets, + .num_resets = ARRAY_SIZE(r9a09g047_resets), + + .num_mstop_bits = 208, +}; diff --git a/drivers/clk/renesas/r9a09g057-cpg.c b/drivers/clk/renesas/r9a09g057-cpg.c index 7c4507fd34e6..3705e18f66ad 100644 --- a/drivers/clk/renesas/r9a09g057-cpg.c +++ b/drivers/clk/renesas/r9a09g057-cpg.c @@ -28,6 +28,7 @@ enum clk_ids { CLK_PLLCLN, CLK_PLLDTY, CLK_PLLCA55, + CLK_PLLVDO, /* Internal Core Clocks */ CLK_PLLCM33_DIV16, @@ -35,7 +36,13 @@ enum clk_ids { CLK_PLLCLN_DIV8, CLK_PLLCLN_DIV16, CLK_PLLDTY_ACPU, + CLK_PLLDTY_ACPU_DIV2, CLK_PLLDTY_ACPU_DIV4, + CLK_PLLDTY_DIV16, + CLK_PLLVDO_CRU0, + CLK_PLLVDO_CRU1, + CLK_PLLVDO_CRU2, + CLK_PLLVDO_CRU3, /* Module Clocks */ MOD_CLK_BASE, @@ -49,6 +56,12 @@ static const struct clk_div_table dtable_1_8[] = { {0, 0}, }; +static const struct clk_div_table dtable_2_4[] = { + {0, 2}, + {1, 4}, + {0, 0}, +}; + static const struct clk_div_table dtable_2_64[] = { {0, 2}, {1, 4}, @@ -69,6 +82,7 @@ static const struct cpg_core_clk r9a09g057_core_clks[] __initconst = { DEF_FIXED(".pllcln", CLK_PLLCLN, CLK_QEXTAL, 200, 3), DEF_FIXED(".plldty", CLK_PLLDTY, CLK_QEXTAL, 200, 3), DEF_PLL(".pllca55", CLK_PLLCA55, CLK_QEXTAL, PLL_CONF(0x64)), + DEF_FIXED(".pllvdo", CLK_PLLVDO, CLK_QEXTAL, 105, 2), /* Internal Core Clocks */ DEF_FIXED(".pllcm33_div16", CLK_PLLCM33_DIV16, CLK_PLLCM33, 1, 16), @@ -78,7 +92,14 @@ static const struct cpg_core_clk r9a09g057_core_clks[] __initconst = { DEF_FIXED(".pllcln_div16", CLK_PLLCLN_DIV16, CLK_PLLCLN, 1, 16), DEF_DDIV(".plldty_acpu", CLK_PLLDTY_ACPU, CLK_PLLDTY, CDDIV0_DIVCTL2, dtable_2_64), + DEF_FIXED(".plldty_acpu_div2", CLK_PLLDTY_ACPU_DIV2, CLK_PLLDTY_ACPU, 1, 2), DEF_FIXED(".plldty_acpu_div4", CLK_PLLDTY_ACPU_DIV4, CLK_PLLDTY_ACPU, 1, 4), + DEF_FIXED(".plldty_div16", CLK_PLLDTY_DIV16, CLK_PLLDTY, 1, 16), + + DEF_DDIV(".pllvdo_cru0", CLK_PLLVDO_CRU0, CLK_PLLVDO, CDDIV3_DIVCTL3, dtable_2_4), + DEF_DDIV(".pllvdo_cru1", CLK_PLLVDO_CRU1, CLK_PLLVDO, CDDIV4_DIVCTL0, dtable_2_4), + DEF_DDIV(".pllvdo_cru2", CLK_PLLVDO_CRU2, CLK_PLLVDO, CDDIV4_DIVCTL1, dtable_2_4), + DEF_DDIV(".pllvdo_cru3", CLK_PLLVDO_CRU3, CLK_PLLVDO, CDDIV4_DIVCTL2, dtable_2_4), /* Core Clocks */ DEF_FIXED("sys_0_pclk", R9A09G057_SYS_0_PCLK, CLK_QEXTAL, 1, 1), @@ -94,49 +115,117 @@ static const struct cpg_core_clk r9a09g057_core_clks[] __initconst = { }; static const struct rzv2h_mod_clk r9a09g057_mod_clks[] __initconst = { - DEF_MOD_CRITICAL("icu_0_pclk_i", CLK_PLLCM33_DIV16, 0, 5, 0, 5), - DEF_MOD("gtm_0_pclk", CLK_PLLCM33_DIV16, 4, 3, 2, 3), - DEF_MOD("gtm_1_pclk", CLK_PLLCM33_DIV16, 4, 4, 2, 4), - DEF_MOD("gtm_2_pclk", CLK_PLLCLN_DIV16, 4, 5, 2, 5), - DEF_MOD("gtm_3_pclk", CLK_PLLCLN_DIV16, 4, 6, 2, 6), - DEF_MOD("gtm_4_pclk", CLK_PLLCLN_DIV16, 4, 7, 2, 7), - DEF_MOD("gtm_5_pclk", CLK_PLLCLN_DIV16, 4, 8, 2, 8), - DEF_MOD("gtm_6_pclk", CLK_PLLCLN_DIV16, 4, 9, 2, 9), - DEF_MOD("gtm_7_pclk", CLK_PLLCLN_DIV16, 4, 10, 2, 10), - DEF_MOD("wdt_0_clkp", CLK_PLLCM33_DIV16, 4, 11, 2, 11), - DEF_MOD("wdt_0_clk_loco", CLK_QEXTAL, 4, 12, 2, 12), - DEF_MOD("wdt_1_clkp", CLK_PLLCLN_DIV16, 4, 13, 2, 13), - DEF_MOD("wdt_1_clk_loco", CLK_QEXTAL, 4, 14, 2, 14), - DEF_MOD("wdt_2_clkp", CLK_PLLCLN_DIV16, 4, 15, 2, 15), - DEF_MOD("wdt_2_clk_loco", CLK_QEXTAL, 5, 0, 2, 16), - DEF_MOD("wdt_3_clkp", CLK_PLLCLN_DIV16, 5, 1, 2, 17), - DEF_MOD("wdt_3_clk_loco", CLK_QEXTAL, 5, 2, 2, 18), - DEF_MOD("scif_0_clk_pck", CLK_PLLCM33_DIV16, 8, 15, 4, 15), - DEF_MOD("riic_8_ckm", CLK_PLLCM33_DIV16, 9, 3, 4, 19), - DEF_MOD("riic_0_ckm", CLK_PLLCLN_DIV16, 9, 4, 4, 20), - DEF_MOD("riic_1_ckm", CLK_PLLCLN_DIV16, 9, 5, 4, 21), - DEF_MOD("riic_2_ckm", CLK_PLLCLN_DIV16, 9, 6, 4, 22), - DEF_MOD("riic_3_ckm", CLK_PLLCLN_DIV16, 9, 7, 4, 23), - DEF_MOD("riic_4_ckm", CLK_PLLCLN_DIV16, 9, 8, 4, 24), - DEF_MOD("riic_5_ckm", CLK_PLLCLN_DIV16, 9, 9, 4, 25), - DEF_MOD("riic_6_ckm", CLK_PLLCLN_DIV16, 9, 10, 4, 26), - DEF_MOD("riic_7_ckm", CLK_PLLCLN_DIV16, 9, 11, 4, 27), - DEF_MOD("sdhi_0_imclk", CLK_PLLCLN_DIV8, 10, 3, 5, 3), - DEF_MOD("sdhi_0_imclk2", CLK_PLLCLN_DIV8, 10, 4, 5, 4), - DEF_MOD("sdhi_0_clk_hs", CLK_PLLCLN_DIV2, 10, 5, 5, 5), - DEF_MOD("sdhi_0_aclk", CLK_PLLDTY_ACPU_DIV4, 10, 6, 5, 6), - DEF_MOD("sdhi_1_imclk", CLK_PLLCLN_DIV8, 10, 7, 5, 7), - DEF_MOD("sdhi_1_imclk2", CLK_PLLCLN_DIV8, 10, 8, 5, 8), - DEF_MOD("sdhi_1_clk_hs", CLK_PLLCLN_DIV2, 10, 9, 5, 9), - DEF_MOD("sdhi_1_aclk", CLK_PLLDTY_ACPU_DIV4, 10, 10, 5, 10), - DEF_MOD("sdhi_2_imclk", CLK_PLLCLN_DIV8, 10, 11, 5, 11), - DEF_MOD("sdhi_2_imclk2", CLK_PLLCLN_DIV8, 10, 12, 5, 12), - DEF_MOD("sdhi_2_clk_hs", CLK_PLLCLN_DIV2, 10, 13, 5, 13), - DEF_MOD("sdhi_2_aclk", CLK_PLLDTY_ACPU_DIV4, 10, 14, 5, 14), + DEF_MOD_CRITICAL("icu_0_pclk_i", CLK_PLLCM33_DIV16, 0, 5, 0, 5, + BUS_MSTOP_NONE), + DEF_MOD_CRITICAL("gic_0_gicclk", CLK_PLLDTY_ACPU_DIV4, 1, 3, 0, 19, + BUS_MSTOP(3, BIT(5))), + DEF_MOD("gtm_0_pclk", CLK_PLLCM33_DIV16, 4, 3, 2, 3, + BUS_MSTOP(5, BIT(10))), + DEF_MOD("gtm_1_pclk", CLK_PLLCM33_DIV16, 4, 4, 2, 4, + BUS_MSTOP(5, BIT(11))), + DEF_MOD("gtm_2_pclk", CLK_PLLCLN_DIV16, 4, 5, 2, 5, + BUS_MSTOP(2, BIT(13))), + DEF_MOD("gtm_3_pclk", CLK_PLLCLN_DIV16, 4, 6, 2, 6, + BUS_MSTOP(2, BIT(14))), + DEF_MOD("gtm_4_pclk", CLK_PLLCLN_DIV16, 4, 7, 2, 7, + BUS_MSTOP(11, BIT(13))), + DEF_MOD("gtm_5_pclk", CLK_PLLCLN_DIV16, 4, 8, 2, 8, + BUS_MSTOP(11, BIT(14))), + DEF_MOD("gtm_6_pclk", CLK_PLLCLN_DIV16, 4, 9, 2, 9, + BUS_MSTOP(11, BIT(15))), + DEF_MOD("gtm_7_pclk", CLK_PLLCLN_DIV16, 4, 10, 2, 10, + BUS_MSTOP(12, BIT(0))), + DEF_MOD("wdt_0_clkp", CLK_PLLCM33_DIV16, 4, 11, 2, 11, + BUS_MSTOP(3, BIT(10))), + DEF_MOD("wdt_0_clk_loco", CLK_QEXTAL, 4, 12, 2, 12, + BUS_MSTOP(3, BIT(10))), + DEF_MOD("wdt_1_clkp", CLK_PLLCLN_DIV16, 4, 13, 2, 13, + BUS_MSTOP(1, BIT(0))), + DEF_MOD("wdt_1_clk_loco", CLK_QEXTAL, 4, 14, 2, 14, + BUS_MSTOP(1, BIT(0))), + DEF_MOD("wdt_2_clkp", CLK_PLLCLN_DIV16, 4, 15, 2, 15, + BUS_MSTOP(5, BIT(12))), + DEF_MOD("wdt_2_clk_loco", CLK_QEXTAL, 5, 0, 2, 16, + BUS_MSTOP(5, BIT(12))), + DEF_MOD("wdt_3_clkp", CLK_PLLCLN_DIV16, 5, 1, 2, 17, + BUS_MSTOP(5, BIT(13))), + DEF_MOD("wdt_3_clk_loco", CLK_QEXTAL, 5, 2, 2, 18, + BUS_MSTOP(5, BIT(13))), + DEF_MOD("scif_0_clk_pck", CLK_PLLCM33_DIV16, 8, 15, 4, 15, + BUS_MSTOP(3, BIT(14))), + DEF_MOD("riic_8_ckm", CLK_PLLCM33_DIV16, 9, 3, 4, 19, + BUS_MSTOP(3, BIT(13))), + DEF_MOD("riic_0_ckm", CLK_PLLCLN_DIV16, 9, 4, 4, 20, + BUS_MSTOP(1, BIT(1))), + DEF_MOD("riic_1_ckm", CLK_PLLCLN_DIV16, 9, 5, 4, 21, + BUS_MSTOP(1, BIT(2))), + DEF_MOD("riic_2_ckm", CLK_PLLCLN_DIV16, 9, 6, 4, 22, + BUS_MSTOP(1, BIT(3))), + DEF_MOD("riic_3_ckm", CLK_PLLCLN_DIV16, 9, 7, 4, 23, + BUS_MSTOP(1, BIT(4))), + DEF_MOD("riic_4_ckm", CLK_PLLCLN_DIV16, 9, 8, 4, 24, + BUS_MSTOP(1, BIT(5))), + DEF_MOD("riic_5_ckm", CLK_PLLCLN_DIV16, 9, 9, 4, 25, + BUS_MSTOP(1, BIT(6))), + DEF_MOD("riic_6_ckm", CLK_PLLCLN_DIV16, 9, 10, 4, 26, + BUS_MSTOP(1, BIT(7))), + DEF_MOD("riic_7_ckm", CLK_PLLCLN_DIV16, 9, 11, 4, 27, + BUS_MSTOP(1, BIT(8))), + DEF_MOD("sdhi_0_imclk", CLK_PLLCLN_DIV8, 10, 3, 5, 3, + BUS_MSTOP(8, BIT(2))), + DEF_MOD("sdhi_0_imclk2", CLK_PLLCLN_DIV8, 10, 4, 5, 4, + BUS_MSTOP(8, BIT(2))), + DEF_MOD("sdhi_0_clk_hs", CLK_PLLCLN_DIV2, 10, 5, 5, 5, + BUS_MSTOP(8, BIT(2))), + DEF_MOD("sdhi_0_aclk", CLK_PLLDTY_ACPU_DIV4, 10, 6, 5, 6, + BUS_MSTOP(8, BIT(2))), + DEF_MOD("sdhi_1_imclk", CLK_PLLCLN_DIV8, 10, 7, 5, 7, + BUS_MSTOP(8, BIT(3))), + DEF_MOD("sdhi_1_imclk2", CLK_PLLCLN_DIV8, 10, 8, 5, 8, + BUS_MSTOP(8, BIT(3))), + DEF_MOD("sdhi_1_clk_hs", CLK_PLLCLN_DIV2, 10, 9, 5, 9, + BUS_MSTOP(8, BIT(3))), + DEF_MOD("sdhi_1_aclk", CLK_PLLDTY_ACPU_DIV4, 10, 10, 5, 10, + BUS_MSTOP(8, BIT(3))), + DEF_MOD("sdhi_2_imclk", CLK_PLLCLN_DIV8, 10, 11, 5, 11, + BUS_MSTOP(8, BIT(4))), + DEF_MOD("sdhi_2_imclk2", CLK_PLLCLN_DIV8, 10, 12, 5, 12, + BUS_MSTOP(8, BIT(4))), + DEF_MOD("sdhi_2_clk_hs", CLK_PLLCLN_DIV2, 10, 13, 5, 13, + BUS_MSTOP(8, BIT(4))), + DEF_MOD("sdhi_2_aclk", CLK_PLLDTY_ACPU_DIV4, 10, 14, 5, 14, + BUS_MSTOP(8, BIT(4))), + DEF_MOD("cru_0_aclk", CLK_PLLDTY_ACPU_DIV2, 13, 2, 6, 18, + BUS_MSTOP(9, BIT(4))), + DEF_MOD_NO_PM("cru_0_vclk", CLK_PLLVDO_CRU0, 13, 3, 6, 19, + BUS_MSTOP(9, BIT(4))), + DEF_MOD("cru_0_pclk", CLK_PLLDTY_DIV16, 13, 4, 6, 20, + BUS_MSTOP(9, BIT(4))), + DEF_MOD("cru_1_aclk", CLK_PLLDTY_ACPU_DIV2, 13, 5, 6, 21, + BUS_MSTOP(9, BIT(5))), + DEF_MOD_NO_PM("cru_1_vclk", CLK_PLLVDO_CRU1, 13, 6, 6, 22, + BUS_MSTOP(9, BIT(5))), + DEF_MOD("cru_1_pclk", CLK_PLLDTY_DIV16, 13, 7, 6, 23, + BUS_MSTOP(9, BIT(5))), + DEF_MOD("cru_2_aclk", CLK_PLLDTY_ACPU_DIV2, 13, 8, 6, 24, + BUS_MSTOP(9, BIT(6))), + DEF_MOD_NO_PM("cru_2_vclk", CLK_PLLVDO_CRU2, 13, 9, 6, 25, + BUS_MSTOP(9, BIT(6))), + DEF_MOD("cru_2_pclk", CLK_PLLDTY_DIV16, 13, 10, 6, 26, + BUS_MSTOP(9, BIT(6))), + DEF_MOD("cru_3_aclk", CLK_PLLDTY_ACPU_DIV2, 13, 11, 6, 27, + BUS_MSTOP(9, BIT(7))), + DEF_MOD_NO_PM("cru_3_vclk", CLK_PLLVDO_CRU3, 13, 12, 6, 28, + BUS_MSTOP(9, BIT(7))), + DEF_MOD("cru_3_pclk", CLK_PLLDTY_DIV16, 13, 13, 6, 29, + BUS_MSTOP(9, BIT(7))), }; static const struct rzv2h_reset r9a09g057_resets[] __initconst = { + DEF_RST(3, 0, 1, 1), /* SYS_0_PRESETN */ DEF_RST(3, 6, 1, 7), /* ICU_0_PRESETN_I */ + DEF_RST(3, 8, 1, 9), /* GIC_0_GICRESET_N */ + DEF_RST(3, 9, 1, 10), /* GIC_0_DBG_GICRESET_N */ DEF_RST(6, 13, 2, 30), /* GTM_0_PRESETZ */ DEF_RST(6, 14, 2, 31), /* GTM_1_PRESETZ */ DEF_RST(6, 15, 3, 0), /* GTM_2_PRESETZ */ @@ -162,6 +251,18 @@ static const struct rzv2h_reset r9a09g057_resets[] __initconst = { DEF_RST(10, 7, 4, 24), /* SDHI_0_IXRST */ DEF_RST(10, 8, 4, 25), /* SDHI_1_IXRST */ DEF_RST(10, 9, 4, 26), /* SDHI_2_IXRST */ + DEF_RST(12, 5, 5, 22), /* CRU_0_PRESETN */ + DEF_RST(12, 6, 5, 23), /* CRU_0_ARESETN */ + DEF_RST(12, 7, 5, 24), /* CRU_0_S_RESETN */ + DEF_RST(12, 8, 5, 25), /* CRU_1_PRESETN */ + DEF_RST(12, 9, 5, 26), /* CRU_1_ARESETN */ + DEF_RST(12, 10, 5, 27), /* CRU_1_S_RESETN */ + DEF_RST(12, 11, 5, 28), /* CRU_2_PRESETN */ + DEF_RST(12, 12, 5, 29), /* CRU_2_ARESETN */ + DEF_RST(12, 13, 5, 30), /* CRU_2_S_RESETN */ + DEF_RST(12, 14, 5, 31), /* CRU_3_PRESETN */ + DEF_RST(12, 15, 6, 0), /* CRU_3_ARESETN */ + DEF_RST(13, 0, 6, 1), /* CRU_3_S_RESETN */ }; const struct rzv2h_cpg_info r9a09g057_cpg_info __initconst = { @@ -179,4 +280,6 @@ const struct rzv2h_cpg_info r9a09g057_cpg_info __initconst = { /* Resets */ .resets = r9a09g057_resets, .num_resets = ARRAY_SIZE(r9a09g057_resets), + + .num_mstop_bits = 192, }; diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c index 79e7a90c3b1b..bf85501709f0 100644 --- a/drivers/clk/renesas/renesas-cpg-mssr.c +++ b/drivers/clk/renesas/renesas-cpg-mssr.c @@ -979,7 +979,7 @@ static void __init cpg_mssr_reserved_exit(struct cpg_mssr_priv *priv) static int __init cpg_mssr_reserved_init(struct cpg_mssr_priv *priv, const struct cpg_mssr_info *info) { - struct device_node *soc = of_find_node_by_path("/soc"); + struct device_node *soc __free(device_node) = of_find_node_by_path("/soc"); struct device_node *node; uint32_t args[MAX_PHANDLE_ARGS]; unsigned int *ids = NULL; diff --git a/drivers/clk/renesas/rzv2h-cpg.c b/drivers/clk/renesas/rzv2h-cpg.c index b524a9d33610..a4c1e92e1fd7 100644 --- a/drivers/clk/renesas/rzv2h-cpg.c +++ b/drivers/clk/renesas/rzv2h-cpg.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -40,6 +41,9 @@ #define GET_RST_OFFSET(x) (0x900 + ((x) * 4)) #define GET_RST_MON_OFFSET(x) (0xA00 + ((x) * 4)) +#define CPG_BUS_1_MSTOP (0xd00) +#define CPG_BUS_MSTOP(m) (CPG_BUS_1_MSTOP + ((m) - 1) * 4) + #define KDIV(val) ((s16)FIELD_GET(GENMASK(31, 16), (val))) #define MDIV(val) FIELD_GET(GENMASK(15, 6), (val)) #define PDIV(val) FIELD_GET(GENMASK(5, 0), (val)) @@ -64,6 +68,7 @@ * @resets: Array of resets * @num_resets: Number of Module Resets in info->resets[] * @last_dt_core_clk: ID of the last Core Clock exported to DT + * @mstop_count: Array of mstop values * @rcdev: Reset controller entity */ struct rzv2h_cpg_priv { @@ -78,6 +83,8 @@ struct rzv2h_cpg_priv { unsigned int num_resets; unsigned int last_dt_core_clk; + atomic_t *mstop_count; + struct reset_controller_dev rcdev; }; @@ -97,7 +104,9 @@ struct pll_clk { * struct mod_clock - Module clock * * @priv: CPG private data + * @mstop_data: mstop data relating to module clock * @hw: handle between common and hardware-specific interfaces + * @no_pm: flag to indicate PM is not supported * @on_index: register offset * @on_bit: ON/MON bit * @mon_index: monitor register offset @@ -105,7 +114,9 @@ struct pll_clk { */ struct mod_clock { struct rzv2h_cpg_priv *priv; + unsigned int mstop_data; struct clk_hw hw; + bool no_pm; u8 on_index; u8 on_bit; s8 mon_index; @@ -431,8 +442,71 @@ fail: core->name, PTR_ERR(clk)); } +static void rzv2h_mod_clock_mstop_enable(struct rzv2h_cpg_priv *priv, + u32 mstop_data) +{ + unsigned long mstop_mask = FIELD_GET(BUS_MSTOP_BITS_MASK, mstop_data); + u16 mstop_index = FIELD_GET(BUS_MSTOP_IDX_MASK, mstop_data); + unsigned int index = (mstop_index - 1) * 16; + atomic_t *mstop = &priv->mstop_count[index]; + unsigned long flags; + unsigned int i; + u32 val = 0; + + spin_lock_irqsave(&priv->rmw_lock, flags); + for_each_set_bit(i, &mstop_mask, 16) { + if (!atomic_read(&mstop[i])) + val |= BIT(i) << 16; + atomic_inc(&mstop[i]); + } + if (val) + writel(val, priv->base + CPG_BUS_MSTOP(mstop_index)); + spin_unlock_irqrestore(&priv->rmw_lock, flags); +} + +static void rzv2h_mod_clock_mstop_disable(struct rzv2h_cpg_priv *priv, + u32 mstop_data) +{ + unsigned long mstop_mask = FIELD_GET(BUS_MSTOP_BITS_MASK, mstop_data); + u16 mstop_index = FIELD_GET(BUS_MSTOP_IDX_MASK, mstop_data); + unsigned int index = (mstop_index - 1) * 16; + atomic_t *mstop = &priv->mstop_count[index]; + unsigned long flags; + unsigned int i; + u32 val = 0; + + spin_lock_irqsave(&priv->rmw_lock, flags); + for_each_set_bit(i, &mstop_mask, 16) { + if (!atomic_read(&mstop[i]) || + atomic_dec_and_test(&mstop[i])) + val |= BIT(i) << 16 | BIT(i); + } + if (val) + writel(val, priv->base + CPG_BUS_MSTOP(mstop_index)); + spin_unlock_irqrestore(&priv->rmw_lock, flags); +} + +static int rzv2h_mod_clock_is_enabled(struct clk_hw *hw) +{ + struct mod_clock *clock = to_mod_clock(hw); + struct rzv2h_cpg_priv *priv = clock->priv; + u32 bitmask; + u32 offset; + + if (clock->mon_index >= 0) { + offset = GET_CLK_MON_OFFSET(clock->mon_index); + bitmask = BIT(clock->mon_bit); + } else { + offset = GET_CLK_ON_OFFSET(clock->on_index); + bitmask = BIT(clock->on_bit); + } + + return readl(priv->base + offset) & bitmask; +} + static int rzv2h_mod_clock_endisable(struct clk_hw *hw, bool enable) { + bool enabled = rzv2h_mod_clock_is_enabled(hw); struct mod_clock *clock = to_mod_clock(hw); unsigned int reg = GET_CLK_ON_OFFSET(clock->on_index); struct rzv2h_cpg_priv *priv = clock->priv; @@ -444,11 +518,20 @@ static int rzv2h_mod_clock_endisable(struct clk_hw *hw, bool enable) dev_dbg(dev, "CLK_ON 0x%x/%pC %s\n", reg, hw->clk, enable ? "ON" : "OFF"); - value = bitmask << 16; - if (enable) - value |= bitmask; + if (enabled == enable) + return 0; - writel(value, priv->base + reg); + value = bitmask << 16; + if (enable) { + value |= bitmask; + writel(value, priv->base + reg); + if (clock->mstop_data != BUS_MSTOP_NONE) + rzv2h_mod_clock_mstop_enable(priv, clock->mstop_data); + } else { + if (clock->mstop_data != BUS_MSTOP_NONE) + rzv2h_mod_clock_mstop_disable(priv, clock->mstop_data); + writel(value, priv->base + reg); + } if (!enable || clock->mon_index < 0) return 0; @@ -474,24 +557,6 @@ static void rzv2h_mod_clock_disable(struct clk_hw *hw) rzv2h_mod_clock_endisable(hw, false); } -static int rzv2h_mod_clock_is_enabled(struct clk_hw *hw) -{ - struct mod_clock *clock = to_mod_clock(hw); - struct rzv2h_cpg_priv *priv = clock->priv; - u32 bitmask; - u32 offset; - - if (clock->mon_index >= 0) { - offset = GET_CLK_MON_OFFSET(clock->mon_index); - bitmask = BIT(clock->mon_bit); - } else { - offset = GET_CLK_ON_OFFSET(clock->on_index); - bitmask = BIT(clock->on_bit); - } - - return readl(priv->base + offset) & bitmask; -} - static const struct clk_ops rzv2h_mod_clock_ops = { .enable = rzv2h_mod_clock_enable, .disable = rzv2h_mod_clock_disable, @@ -541,8 +606,10 @@ rzv2h_cpg_register_mod_clk(const struct rzv2h_mod_clk *mod, clock->on_bit = mod->on_bit; clock->mon_index = mod->mon_index; clock->mon_bit = mod->mon_bit; + clock->no_pm = mod->no_pm; clock->priv = priv; clock->hw.init = &init; + clock->mstop_data = mod->mstop_data; ret = devm_clk_hw_register(dev, &clock->hw); if (ret) { @@ -552,6 +619,41 @@ rzv2h_cpg_register_mod_clk(const struct rzv2h_mod_clk *mod, priv->clks[id] = clock->hw.clk; + /* + * Ensure the module clocks and MSTOP bits are synchronized when they are + * turned ON by the bootloader. Enable MSTOP bits for module clocks that were + * turned ON in an earlier boot stage. + */ + if (clock->mstop_data != BUS_MSTOP_NONE && + !mod->critical && rzv2h_mod_clock_is_enabled(&clock->hw)) { + rzv2h_mod_clock_mstop_enable(priv, clock->mstop_data); + } else if (clock->mstop_data != BUS_MSTOP_NONE && mod->critical) { + unsigned long mstop_mask = FIELD_GET(BUS_MSTOP_BITS_MASK, clock->mstop_data); + u16 mstop_index = FIELD_GET(BUS_MSTOP_IDX_MASK, clock->mstop_data); + unsigned int index = (mstop_index - 1) * 16; + atomic_t *mstop = &priv->mstop_count[index]; + unsigned long flags; + unsigned int i; + u32 val = 0; + + /* + * Critical clocks are turned ON immediately upon registration, and the + * MSTOP counter is updated through the rzv2h_mod_clock_enable() path. + * However, if the critical clocks were already turned ON by the initial + * bootloader, synchronize the atomic counter here and clear the MSTOP bit. + */ + spin_lock_irqsave(&priv->rmw_lock, flags); + for_each_set_bit(i, &mstop_mask, 16) { + if (atomic_read(&mstop[i])) + continue; + val |= BIT(i) << 16; + atomic_inc(&mstop[i]); + } + if (val) + writel(val, priv->base + CPG_BUS_MSTOP(mstop_index)); + spin_unlock_irqrestore(&priv->rmw_lock, flags); + } + return; fail: @@ -668,17 +770,51 @@ struct rzv2h_cpg_pd { struct generic_pm_domain genpd; }; +static bool rzv2h_cpg_is_pm_clk(struct rzv2h_cpg_pd *pd, + const struct of_phandle_args *clkspec) +{ + if (clkspec->np != pd->genpd.dev.of_node || clkspec->args_count != 2) + return false; + + switch (clkspec->args[0]) { + case CPG_MOD: { + struct rzv2h_cpg_priv *priv = pd->priv; + unsigned int id = clkspec->args[1]; + struct mod_clock *clock; + + if (id >= priv->num_mod_clks) + return false; + + if (priv->clks[priv->num_core_clks + id] == ERR_PTR(-ENOENT)) + return false; + + clock = to_mod_clock(__clk_get_hw(priv->clks[priv->num_core_clks + id])); + + return !clock->no_pm; + } + + case CPG_CORE: + default: + return false; + } +} + static int rzv2h_cpg_attach_dev(struct generic_pm_domain *domain, struct device *dev) { + struct rzv2h_cpg_pd *pd = container_of(domain, struct rzv2h_cpg_pd, genpd); struct device_node *np = dev->of_node; struct of_phandle_args clkspec; bool once = true; struct clk *clk; + unsigned int i; int error; - int i = 0; - while (!of_parse_phandle_with_args(np, "clocks", "#clock-cells", i, - &clkspec)) { + for (i = 0; !of_parse_phandle_with_args(np, "clocks", "#clock-cells", i, &clkspec); i++) { + if (!rzv2h_cpg_is_pm_clk(pd, &clkspec)) { + of_node_put(clkspec.np); + continue; + } + if (once) { once = false; error = pm_clk_create(dev); @@ -700,7 +836,6 @@ static int rzv2h_cpg_attach_dev(struct generic_pm_domain *domain, struct device error); goto fail_put; } - i++; } return 0; @@ -786,6 +921,11 @@ static int __init rzv2h_cpg_probe(struct platform_device *pdev) if (!clks) return -ENOMEM; + priv->mstop_count = devm_kcalloc(dev, info->num_mstop_bits, + sizeof(*priv->mstop_count), GFP_KERNEL); + if (!priv->mstop_count) + return -ENOMEM; + priv->resets = devm_kmemdup(dev, info->resets, sizeof(*info->resets) * info->num_resets, GFP_KERNEL); if (!priv->resets) @@ -832,6 +972,12 @@ static const struct of_device_id rzv2h_cpg_match[] = { .compatible = "renesas,r9a09g057-cpg", .data = &r9a09g057_cpg_info, }, +#endif +#ifdef CONFIG_CLK_R9A09G047 + { + .compatible = "renesas,r9a09g047-cpg", + .data = &r9a09g047_cpg_info, + }, #endif { /* sentinel */ } }; diff --git a/drivers/clk/renesas/rzv2h-cpg.h b/drivers/clk/renesas/rzv2h-cpg.h index 819029c81904..fd8eb985c75b 100644 --- a/drivers/clk/renesas/rzv2h-cpg.h +++ b/drivers/clk/renesas/rzv2h-cpg.h @@ -8,6 +8,8 @@ #ifndef __RENESAS_RZV2H_CPG_H__ #define __RENESAS_RZV2H_CPG_H__ +#include + /** * struct ddiv - Structure for dynamic switching divider * @@ -33,12 +35,24 @@ struct ddiv { #define CPG_CDDIV0 (0x400) #define CPG_CDDIV1 (0x404) +#define CPG_CDDIV3 (0x40C) +#define CPG_CDDIV4 (0x410) #define CDDIV0_DIVCTL2 DDIV_PACK(CPG_CDDIV0, 8, 3, 2) #define CDDIV1_DIVCTL0 DDIV_PACK(CPG_CDDIV1, 0, 2, 4) #define CDDIV1_DIVCTL1 DDIV_PACK(CPG_CDDIV1, 4, 2, 5) #define CDDIV1_DIVCTL2 DDIV_PACK(CPG_CDDIV1, 8, 2, 6) #define CDDIV1_DIVCTL3 DDIV_PACK(CPG_CDDIV1, 12, 2, 7) +#define CDDIV3_DIVCTL3 DDIV_PACK(CPG_CDDIV3, 12, 1, 15) +#define CDDIV4_DIVCTL0 DDIV_PACK(CPG_CDDIV4, 0, 1, 16) +#define CDDIV4_DIVCTL1 DDIV_PACK(CPG_CDDIV4, 4, 1, 17) +#define CDDIV4_DIVCTL2 DDIV_PACK(CPG_CDDIV4, 8, 1, 18) + +#define BUS_MSTOP_IDX_MASK GENMASK(31, 16) +#define BUS_MSTOP_BITS_MASK GENMASK(15, 0) +#define BUS_MSTOP(idx, mask) (FIELD_PREP_CONST(BUS_MSTOP_IDX_MASK, (idx)) | \ + FIELD_PREP_CONST(BUS_MSTOP_BITS_MASK, (mask))) +#define BUS_MSTOP_NONE GENMASK(31, 0) /** * Definitions of CPG Core Clocks @@ -98,8 +112,10 @@ enum clk_types { * struct rzv2h_mod_clk - Module Clocks definitions * * @name: handle between common and hardware-specific interfaces + * @mstop_data: packed data mstop register offset and mask * @parent: id of parent clock * @critical: flag to indicate the clock is critical + * @no_pm: flag to indicate PM is not supported * @on_index: control register index * @on_bit: ON bit * @mon_index: monitor register index @@ -107,30 +123,37 @@ enum clk_types { */ struct rzv2h_mod_clk { const char *name; + u32 mstop_data; u16 parent; bool critical; + bool no_pm; u8 on_index; u8 on_bit; s8 mon_index; u8 mon_bit; }; -#define DEF_MOD_BASE(_name, _parent, _critical, _onindex, _onbit, _monindex, _monbit) \ +#define DEF_MOD_BASE(_name, _mstop, _parent, _critical, _no_pm, _onindex, _onbit, _monindex, _monbit) \ { \ .name = (_name), \ + .mstop_data = (_mstop), \ .parent = (_parent), \ .critical = (_critical), \ + .no_pm = (_no_pm), \ .on_index = (_onindex), \ .on_bit = (_onbit), \ .mon_index = (_monindex), \ .mon_bit = (_monbit), \ } -#define DEF_MOD(_name, _parent, _onindex, _onbit, _monindex, _monbit) \ - DEF_MOD_BASE(_name, _parent, false, _onindex, _onbit, _monindex, _monbit) +#define DEF_MOD(_name, _parent, _onindex, _onbit, _monindex, _monbit, _mstop) \ + DEF_MOD_BASE(_name, _mstop, _parent, false, false, _onindex, _onbit, _monindex, _monbit) -#define DEF_MOD_CRITICAL(_name, _parent, _onindex, _onbit, _monindex, _monbit) \ - DEF_MOD_BASE(_name, _parent, true, _onindex, _onbit, _monindex, _monbit) +#define DEF_MOD_CRITICAL(_name, _parent, _onindex, _onbit, _monindex, _monbit, _mstop) \ + DEF_MOD_BASE(_name, _mstop, _parent, true, false, _onindex, _onbit, _monindex, _monbit) + +#define DEF_MOD_NO_PM(_name, _parent, _onindex, _onbit, _monindex, _monbit, _mstop) \ + DEF_MOD_BASE(_name, _mstop, _parent, false, true, _onindex, _onbit, _monindex, _monbit) /** * struct rzv2h_reset - Reset definitions @@ -172,6 +195,9 @@ struct rzv2h_reset { * * @resets: Array of Module Reset definitions * @num_resets: Number of entries in resets[] + * + * @num_mstop_bits: Maximum number of MSTOP bits supported, equivalent to the + * number of CPG_BUS_m_MSTOP registers multiplied by 16. */ struct rzv2h_cpg_info { /* Core Clocks */ @@ -188,8 +214,11 @@ struct rzv2h_cpg_info { /* Resets */ const struct rzv2h_reset *resets; unsigned int num_resets; + + unsigned int num_mstop_bits; }; +extern const struct rzv2h_cpg_info r9a09g047_cpg_info; extern const struct rzv2h_cpg_info r9a09g057_cpg_info; #endif /* __RENESAS_RZV2H_CPG_H__ */ diff --git a/drivers/clk/rockchip/Makefile b/drivers/clk/rockchip/Makefile index af2ade54a7ef..3fe7616f0ebe 100644 --- a/drivers/clk/rockchip/Makefile +++ b/drivers/clk/rockchip/Makefile @@ -13,6 +13,7 @@ clk-rockchip-y += clk-inverter.o clk-rockchip-y += clk-mmc-phase.o clk-rockchip-y += clk-muxgrf.o clk-rockchip-y += clk-ddr.o +clk-rockchip-y += gate-link.o clk-rockchip-$(CONFIG_RESET_CONTROLLER) += softrst.o obj-$(CONFIG_CLK_PX30) += clk-px30.o diff --git a/drivers/clk/rockchip/clk-rk3588.c b/drivers/clk/rockchip/clk-rk3588.c index 0ffaf639f807..4031733def4e 100644 --- a/drivers/clk/rockchip/clk-rk3588.c +++ b/drivers/clk/rockchip/clk-rk3588.c @@ -12,28 +12,6 @@ #include #include "clk.h" -/* - * Recent Rockchip SoCs have a new hardware block called Native Interface - * Unit (NIU), which gates clocks to devices behind them. These effectively - * need two parent clocks. - * - * Downstream enables the linked clock via runtime PM whenever the gate is - * enabled. This implementation uses separate clock nodes for each of the - * linked gate clocks, which leaks parts of the clock tree into DT. - * - * The GATE_LINK macro instead takes the second parent via 'linkname', but - * ignores the information. Once the clock framework is ready to handle it, the - * information should be passed on here. But since these clocks are required to - * access multiple relevant IP blocks, such as PCIe or USB, we mark all linked - * clocks critical until a better solution is available. This will waste some - * power, but avoids leaking implementation details into DT or hanging the - * system. - */ -#define GATE_LINK(_id, cname, pname, linkedclk, f, o, b, gf) \ - GATE(_id, cname, pname, f, o, b, gf) -#define RK3588_LINKED_CLK CLK_IS_CRITICAL - - #define RK3588_GRF_SOC_STATUS0 0x600 #define RK3588_PHYREF_ALT_GATE 0xc38 @@ -266,6 +244,8 @@ static struct rockchip_pll_rate_table rk3588_pll_rates[] = { }, \ } +static struct rockchip_clk_provider *early_ctx; + static struct rockchip_cpuclk_rate_table rk3588_cpub0clk_rates[] __initdata = { RK3588_CPUB01CLK_RATE(2496000000, 1), RK3588_CPUB01CLK_RATE(2400000000, 1), @@ -694,7 +674,7 @@ static struct rockchip_pll_clock rk3588_pll_clks[] __initdata = { RK3588_MODE_CON0, 10, 15, 0, rk3588_pll_rates), }; -static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { +static struct rockchip_clk_branch rk3588_early_clk_branches[] __initdata = { /* * CRU Clock-Architecture */ @@ -792,10 +772,10 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { COMPOSITE(MCLK_GMAC0_OUT, "mclk_gmac0_out", gpll_cpll_p, 0, RK3588_CLKSEL_CON(15), 7, 1, MFLAGS, 0, 7, DFLAGS, RK3588_CLKGATE_CON(5), 3, GFLAGS), - COMPOSITE(REFCLKO25M_ETH0_OUT, "refclko25m_eth0_out", gpll_cpll_p, 0, + COMPOSITE(REFCLKO25M_ETH0_OUT, "refclko25m_eth0_out", gpll_cpll_p, CLK_IS_CRITICAL, RK3588_CLKSEL_CON(15), 15, 1, MFLAGS, 8, 7, DFLAGS, RK3588_CLKGATE_CON(5), 4, GFLAGS), - COMPOSITE(REFCLKO25M_ETH1_OUT, "refclko25m_eth1_out", gpll_cpll_p, 0, + COMPOSITE(REFCLKO25M_ETH1_OUT, "refclko25m_eth1_out", gpll_cpll_p, CLK_IS_CRITICAL, RK3588_CLKSEL_CON(16), 7, 1, MFLAGS, 0, 7, DFLAGS, RK3588_CLKGATE_CON(5), 5, GFLAGS), COMPOSITE(CLK_CIFOUT_OUT, "clk_cifout_out", gpll_cpll_24m_spll_p, 0, @@ -1456,7 +1436,7 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { COMPOSITE_NODIV(HCLK_NVM_ROOT, "hclk_nvm_root", mux_200m_100m_50m_24m_p, 0, RK3588_CLKSEL_CON(77), 0, 2, MFLAGS, RK3588_CLKGATE_CON(31), 0, GFLAGS), - COMPOSITE(ACLK_NVM_ROOT, "aclk_nvm_root", gpll_cpll_p, RK3588_LINKED_CLK, + COMPOSITE(ACLK_NVM_ROOT, "aclk_nvm_root", gpll_cpll_p, 0, RK3588_CLKSEL_CON(77), 7, 1, MFLAGS, 2, 5, DFLAGS, RK3588_CLKGATE_CON(31), 1, GFLAGS), GATE(ACLK_EMMC, "aclk_emmc", "aclk_nvm_root", 0, @@ -1685,13 +1665,13 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { RK3588_CLKGATE_CON(42), 9, GFLAGS), /* vdpu */ - COMPOSITE(ACLK_VDPU_ROOT, "aclk_vdpu_root", gpll_cpll_aupll_p, RK3588_LINKED_CLK, + COMPOSITE(ACLK_VDPU_ROOT, "aclk_vdpu_root", gpll_cpll_aupll_p, 0, RK3588_CLKSEL_CON(98), 5, 2, MFLAGS, 0, 5, DFLAGS, RK3588_CLKGATE_CON(44), 0, GFLAGS), COMPOSITE_NODIV(ACLK_VDPU_LOW_ROOT, "aclk_vdpu_low_root", mux_400m_200m_100m_24m_p, 0, RK3588_CLKSEL_CON(98), 7, 2, MFLAGS, RK3588_CLKGATE_CON(44), 1, GFLAGS), - COMPOSITE_NODIV(HCLK_VDPU_ROOT, "hclk_vdpu_root", mux_200m_100m_50m_24m_p, RK3588_LINKED_CLK, + COMPOSITE_NODIV(HCLK_VDPU_ROOT, "hclk_vdpu_root", mux_200m_100m_50m_24m_p, 0, RK3588_CLKSEL_CON(98), 9, 2, MFLAGS, RK3588_CLKGATE_CON(44), 2, GFLAGS), COMPOSITE(ACLK_JPEG_DECODER_ROOT, "aclk_jpeg_decoder_root", gpll_cpll_aupll_spll_p, 0, @@ -1742,9 +1722,9 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { COMPOSITE(ACLK_RKVENC0_ROOT, "aclk_rkvenc0_root", gpll_cpll_npll_p, 0, RK3588_CLKSEL_CON(102), 7, 2, MFLAGS, 2, 5, DFLAGS, RK3588_CLKGATE_CON(47), 1, GFLAGS), - GATE(HCLK_RKVENC0, "hclk_rkvenc0", "hclk_rkvenc0_root", RK3588_LINKED_CLK, + GATE(HCLK_RKVENC0, "hclk_rkvenc0", "hclk_rkvenc0_root", 0, RK3588_CLKGATE_CON(47), 4, GFLAGS), - GATE(ACLK_RKVENC0, "aclk_rkvenc0", "aclk_rkvenc0_root", RK3588_LINKED_CLK, + GATE(ACLK_RKVENC0, "aclk_rkvenc0", "aclk_rkvenc0_root", 0, RK3588_CLKGATE_CON(47), 5, GFLAGS), COMPOSITE(CLK_RKVENC0_CORE, "clk_rkvenc0_core", gpll_cpll_aupll_npll_p, 0, RK3588_CLKSEL_CON(102), 14, 2, MFLAGS, 9, 5, DFLAGS, @@ -1754,10 +1734,10 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { RK3588_CLKGATE_CON(48), 6, GFLAGS), /* vi */ - COMPOSITE(ACLK_VI_ROOT, "aclk_vi_root", gpll_cpll_npll_aupll_spll_p, RK3588_LINKED_CLK, + COMPOSITE(ACLK_VI_ROOT, "aclk_vi_root", gpll_cpll_npll_aupll_spll_p, 0, RK3588_CLKSEL_CON(106), 5, 3, MFLAGS, 0, 5, DFLAGS, RK3588_CLKGATE_CON(49), 0, GFLAGS), - COMPOSITE_NODIV(HCLK_VI_ROOT, "hclk_vi_root", mux_200m_100m_50m_24m_p, RK3588_LINKED_CLK, + COMPOSITE_NODIV(HCLK_VI_ROOT, "hclk_vi_root", mux_200m_100m_50m_24m_p, 0, RK3588_CLKSEL_CON(106), 8, 2, MFLAGS, RK3588_CLKGATE_CON(49), 1, GFLAGS), COMPOSITE_NODIV(PCLK_VI_ROOT, "pclk_vi_root", mux_100m_50m_24m_p, 0, @@ -1927,10 +1907,10 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { COMPOSITE(ACLK_VOP_ROOT, "aclk_vop_root", gpll_cpll_dmyaupll_npll_spll_p, 0, RK3588_CLKSEL_CON(110), 5, 3, MFLAGS, 0, 5, DFLAGS, RK3588_CLKGATE_CON(52), 0, GFLAGS), - COMPOSITE_NODIV(ACLK_VOP_LOW_ROOT, "aclk_vop_low_root", mux_400m_200m_100m_24m_p, RK3588_LINKED_CLK, + COMPOSITE_NODIV(ACLK_VOP_LOW_ROOT, "aclk_vop_low_root", mux_400m_200m_100m_24m_p, 0, RK3588_CLKSEL_CON(110), 8, 2, MFLAGS, RK3588_CLKGATE_CON(52), 1, GFLAGS), - COMPOSITE_NODIV(HCLK_VOP_ROOT, "hclk_vop_root", mux_200m_100m_50m_24m_p, RK3588_LINKED_CLK, + COMPOSITE_NODIV(HCLK_VOP_ROOT, "hclk_vop_root", mux_200m_100m_50m_24m_p, 0, RK3588_CLKSEL_CON(110), 10, 2, MFLAGS, RK3588_CLKGATE_CON(52), 2, GFLAGS), COMPOSITE_NODIV(PCLK_VOP_ROOT, "pclk_vop_root", mux_100m_50m_24m_p, 0, @@ -2428,10 +2408,12 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { RK3588_CLKGATE_CON(68), 5, GFLAGS), GATE(ACLK_AV1, "aclk_av1", "aclk_av1_pre", 0, RK3588_CLKGATE_CON(68), 2, GFLAGS), +}; +static struct rockchip_clk_branch rk3588_clk_branches[] = { GATE_LINK(ACLK_ISP1_PRE, "aclk_isp1_pre", "aclk_isp1_root", ACLK_VI_ROOT, 0, RK3588_CLKGATE_CON(26), 6, GFLAGS), GATE_LINK(HCLK_ISP1_PRE, "hclk_isp1_pre", "hclk_isp1_root", HCLK_VI_ROOT, 0, RK3588_CLKGATE_CON(26), 8, GFLAGS), - GATE_LINK(HCLK_NVM, "hclk_nvm", "hclk_nvm_root", ACLK_NVM_ROOT, RK3588_LINKED_CLK, RK3588_CLKGATE_CON(31), 2, GFLAGS), + GATE_LINK(HCLK_NVM, "hclk_nvm", "hclk_nvm_root", ACLK_NVM_ROOT, 0, RK3588_CLKGATE_CON(31), 2, GFLAGS), GATE_LINK(ACLK_USB, "aclk_usb", "aclk_usb_root", ACLK_VO1USB_TOP_ROOT, 0, RK3588_CLKGATE_CON(42), 2, GFLAGS), GATE_LINK(HCLK_USB, "hclk_usb", "hclk_usb_root", HCLK_VO1USB_TOP_ROOT, 0, RK3588_CLKGATE_CON(42), 3, GFLAGS), GATE_LINK(ACLK_JPEG_DECODER_PRE, "aclk_jpeg_decoder_pre", "aclk_jpeg_decoder_root", ACLK_VDPU_ROOT, 0, RK3588_CLKGATE_CON(44), 7, GFLAGS), @@ -2443,9 +2425,9 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { GATE_LINK(HCLK_RKVDEC1_PRE, "hclk_rkvdec1_pre", "hclk_rkvdec1_root", HCLK_VDPU_ROOT, 0, RK3588_CLKGATE_CON(41), 4, GFLAGS), GATE_LINK(ACLK_RKVDEC1_PRE, "aclk_rkvdec1_pre", "aclk_rkvdec1_root", ACLK_VDPU_ROOT, 0, RK3588_CLKGATE_CON(41), 5, GFLAGS), GATE_LINK(ACLK_HDCP0_PRE, "aclk_hdcp0_pre", "aclk_vo0_root", ACLK_VOP_LOW_ROOT, 0, RK3588_CLKGATE_CON(55), 9, GFLAGS), - GATE_LINK(HCLK_VO0, "hclk_vo0", "hclk_vo0_root", HCLK_VOP_ROOT, RK3588_LINKED_CLK, RK3588_CLKGATE_CON(55), 5, GFLAGS), + GATE_LINK(HCLK_VO0, "hclk_vo0", "hclk_vo0_root", HCLK_VOP_ROOT, 0, RK3588_CLKGATE_CON(55), 5, GFLAGS), GATE_LINK(ACLK_HDCP1_PRE, "aclk_hdcp1_pre", "aclk_hdcp1_root", ACLK_VO1USB_TOP_ROOT, 0, RK3588_CLKGATE_CON(59), 6, GFLAGS), - GATE_LINK(HCLK_VO1, "hclk_vo1", "hclk_vo1_root", HCLK_VO1USB_TOP_ROOT, RK3588_LINKED_CLK, RK3588_CLKGATE_CON(59), 9, GFLAGS), + GATE_LINK(HCLK_VO1, "hclk_vo1", "hclk_vo1_root", HCLK_VO1USB_TOP_ROOT, 0, RK3588_CLKGATE_CON(59), 9, GFLAGS), GATE_LINK(ACLK_AV1_PRE, "aclk_av1_pre", "aclk_av1_root", ACLK_VDPU_ROOT, 0, RK3588_CLKGATE_CON(68), 1, GFLAGS), GATE_LINK(PCLK_AV1_PRE, "pclk_av1_pre", "pclk_av1_root", HCLK_VDPU_ROOT, 0, RK3588_CLKGATE_CON(68), 4, GFLAGS), GATE_LINK(HCLK_SDIO_PRE, "hclk_sdio_pre", "hclk_sdio_root", HCLK_NVM, 0, RK3588_CLKGATE_CON(75), 1, GFLAGS), @@ -2453,26 +2435,31 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { GATE_LINK(PCLK_VO1GRF, "pclk_vo1grf", "pclk_vo1_root", HCLK_VO1, CLK_IGNORE_UNUSED, RK3588_CLKGATE_CON(59), 12, GFLAGS), }; -static void __init rk3588_clk_init(struct device_node *np) +static void __init rk3588_clk_early_init(struct device_node *np) { struct rockchip_clk_provider *ctx; - unsigned long clk_nr_clks; + unsigned long clk_nr_clks, max_clk_id1, max_clk_id2; void __iomem *reg_base; - clk_nr_clks = rockchip_clk_find_max_clk_id(rk3588_clk_branches, - ARRAY_SIZE(rk3588_clk_branches)) + 1; + max_clk_id1 = rockchip_clk_find_max_clk_id(rk3588_clk_branches, + ARRAY_SIZE(rk3588_clk_branches)); + max_clk_id2 = rockchip_clk_find_max_clk_id(rk3588_early_clk_branches, + ARRAY_SIZE(rk3588_early_clk_branches)); + clk_nr_clks = max(max_clk_id1, max_clk_id2) + 1; + reg_base = of_iomap(np, 0); if (!reg_base) { pr_err("%s: could not map cru region\n", __func__); return; } - ctx = rockchip_clk_init(np, reg_base, clk_nr_clks); + ctx = rockchip_clk_init_early(np, reg_base, clk_nr_clks); if (IS_ERR(ctx)) { pr_err("%s: rockchip clk init failed\n", __func__); iounmap(reg_base); return; } + early_ctx = ctx; rockchip_clk_register_plls(ctx, rk3588_pll_clks, ARRAY_SIZE(rk3588_pll_clks), @@ -2491,14 +2478,55 @@ static void __init rk3588_clk_init(struct device_node *np) &rk3588_cpub1clk_data, rk3588_cpub1clk_rates, ARRAY_SIZE(rk3588_cpub1clk_rates)); - rockchip_clk_register_branches(ctx, rk3588_clk_branches, - ARRAY_SIZE(rk3588_clk_branches)); - - rk3588_rst_init(np, reg_base); - - rockchip_register_restart_notifier(ctx, RK3588_GLB_SRST_FST, NULL); + rockchip_clk_register_branches(ctx, rk3588_early_clk_branches, + ARRAY_SIZE(rk3588_early_clk_branches)); rockchip_clk_of_add_provider(np, ctx); } +CLK_OF_DECLARE_DRIVER(rk3588_cru, "rockchip,rk3588-cru", rk3588_clk_early_init); -CLK_OF_DECLARE(rk3588_cru, "rockchip,rk3588-cru", rk3588_clk_init); +static int clk_rk3588_probe(struct platform_device *pdev) +{ + struct rockchip_clk_provider *ctx = early_ctx; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + + rockchip_clk_register_late_branches(dev, ctx, rk3588_clk_branches, + ARRAY_SIZE(rk3588_clk_branches)); + + rockchip_clk_finalize(ctx); + + rk3588_rst_init(np, ctx->reg_base); + rockchip_register_restart_notifier(ctx, RK3588_GLB_SRST_FST, NULL); + + /* + * Re-add clock provider, so that the newly added clocks are also + * re-parented and get their defaults configured. + */ + of_clk_del_provider(np); + rockchip_clk_of_add_provider(np, ctx); + + return 0; +} + +static const struct of_device_id clk_rk3588_match_table[] = { + { + .compatible = "rockchip,rk3588-cru", + }, + { } +}; + +static struct platform_driver clk_rk3588_driver = { + .probe = clk_rk3588_probe, + .driver = { + .name = "clk-rk3588", + .of_match_table = clk_rk3588_match_table, + .suppress_bind_attrs = true, + }, +}; + +static int __init rockchip_clk_rk3588_drv_register(void) +{ + return platform_driver_register(&clk_rk3588_driver); +} +core_initcall(rockchip_clk_rk3588_drv_register); diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c index 88629a9abc9c..cbf93ea119a9 100644 --- a/drivers/clk/rockchip/clk.c +++ b/drivers/clk/rockchip/clk.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -197,12 +198,6 @@ static void rockchip_fractional_approximation(struct clk_hw *hw, clk_fractional_divider_general_approximation(hw, rate, parent_rate, m, n); } -static void rockchip_clk_add_lookup(struct rockchip_clk_provider *ctx, - struct clk *clk, unsigned int id) -{ - ctx->clk_data.clks[id] = clk; -} - static struct clk *rockchip_clk_register_frac_branch( struct rockchip_clk_provider *ctx, const char *name, const char *const *parent_names, u8 num_parents, @@ -292,7 +287,7 @@ static struct clk *rockchip_clk_register_frac_branch( return mux_clk; } - rockchip_clk_add_lookup(ctx, mux_clk, child->id); + rockchip_clk_set_lookup(ctx, mux_clk, child->id); /* notifier on the fraction divider to catch rate changes */ if (frac->mux_frac_idx >= 0) { @@ -359,14 +354,17 @@ static struct clk *rockchip_clk_register_factor_branch(const char *name, return hw->clk; } -struct rockchip_clk_provider *rockchip_clk_init(struct device_node *np, - void __iomem *base, - unsigned long nr_clks) +static struct rockchip_clk_provider *rockchip_clk_init_base( + struct device_node *np, void __iomem *base, + unsigned long nr_clks, bool has_late_clocks) { struct rockchip_clk_provider *ctx; struct clk **clk_table; + struct clk *default_clk_val; int i; + default_clk_val = ERR_PTR(has_late_clocks ? -EPROBE_DEFER : -ENOENT); + ctx = kzalloc(sizeof(struct rockchip_clk_provider), GFP_KERNEL); if (!ctx) return ERR_PTR(-ENOMEM); @@ -376,7 +374,7 @@ struct rockchip_clk_provider *rockchip_clk_init(struct device_node *np, goto err_free; for (i = 0; i < nr_clks; ++i) - clk_table[i] = ERR_PTR(-ENOENT); + clk_table[i] = default_clk_val; ctx->reg_base = base; ctx->clk_data.clks = clk_table; @@ -393,8 +391,33 @@ err_free: kfree(ctx); return ERR_PTR(-ENOMEM); } + +struct rockchip_clk_provider *rockchip_clk_init(struct device_node *np, + void __iomem *base, + unsigned long nr_clks) +{ + return rockchip_clk_init_base(np, base, nr_clks, false); +} EXPORT_SYMBOL_GPL(rockchip_clk_init); +struct rockchip_clk_provider *rockchip_clk_init_early(struct device_node *np, + void __iomem *base, + unsigned long nr_clks) +{ + return rockchip_clk_init_base(np, base, nr_clks, true); +} +EXPORT_SYMBOL_GPL(rockchip_clk_init_early); + +void rockchip_clk_finalize(struct rockchip_clk_provider *ctx) +{ + int i; + + for (i = 0; i < ctx->clk_data.clk_num; ++i) + if (ctx->clk_data.clks[i] == ERR_PTR(-EPROBE_DEFER)) + ctx->clk_data.clks[i] = ERR_PTR(-ENOENT); +} +EXPORT_SYMBOL_GPL(rockchip_clk_finalize); + void rockchip_clk_of_add_provider(struct device_node *np, struct rockchip_clk_provider *ctx) { @@ -424,7 +447,7 @@ void rockchip_clk_register_plls(struct rockchip_clk_provider *ctx, continue; } - rockchip_clk_add_lookup(ctx, clk, list->id); + rockchip_clk_set_lookup(ctx, clk, list->id); } } EXPORT_SYMBOL_GPL(rockchip_clk_register_plls); @@ -446,6 +469,29 @@ unsigned long rockchip_clk_find_max_clk_id(struct rockchip_clk_branch *list, } EXPORT_SYMBOL_GPL(rockchip_clk_find_max_clk_id); +static struct platform_device *rockchip_clk_register_gate_link( + struct device *parent_dev, + struct rockchip_clk_provider *ctx, + struct rockchip_clk_branch *clkbr) +{ + struct rockchip_gate_link_platdata gate_link_pdata = { + .ctx = ctx, + .clkbr = clkbr, + }; + + struct platform_device_info pdevinfo = { + .parent = parent_dev, + .name = "rockchip-gate-link-clk", + .id = clkbr->id, + .fwnode = dev_fwnode(parent_dev), + .of_node_reused = true, + .data = &gate_link_pdata, + .size_data = sizeof(gate_link_pdata), + }; + + return platform_device_register_full(&pdevinfo); +} + void rockchip_clk_register_branches(struct rockchip_clk_provider *ctx, struct rockchip_clk_branch *list, unsigned int nr_clk) @@ -571,6 +617,9 @@ void rockchip_clk_register_branches(struct rockchip_clk_provider *ctx, list->div_width, list->div_flags, ctx->reg_base, &ctx->lock); break; + case branch_linked_gate: + /* must be registered late, fall-through for error message */ + break; } /* none of the cases above matched */ @@ -586,11 +635,36 @@ void rockchip_clk_register_branches(struct rockchip_clk_provider *ctx, continue; } - rockchip_clk_add_lookup(ctx, clk, list->id); + rockchip_clk_set_lookup(ctx, clk, list->id); } } EXPORT_SYMBOL_GPL(rockchip_clk_register_branches); +void rockchip_clk_register_late_branches(struct device *dev, + struct rockchip_clk_provider *ctx, + struct rockchip_clk_branch *list, + unsigned int nr_clk) +{ + unsigned int idx; + + for (idx = 0; idx < nr_clk; idx++, list++) { + struct platform_device *pdev = NULL; + + switch (list->branch_type) { + case branch_linked_gate: + pdev = rockchip_clk_register_gate_link(dev, ctx, list); + break; + default: + dev_err(dev, "unknown clock type %d\n", list->branch_type); + break; + } + + if (!pdev) + dev_err(dev, "failed to register device for clock %s\n", list->name); + } +} +EXPORT_SYMBOL_GPL(rockchip_clk_register_late_branches); + void rockchip_clk_register_armclk(struct rockchip_clk_provider *ctx, unsigned int lookup_id, const char *name, const char *const *parent_names, @@ -610,7 +684,7 @@ void rockchip_clk_register_armclk(struct rockchip_clk_provider *ctx, return; } - rockchip_clk_add_lookup(ctx, clk, lookup_id); + rockchip_clk_set_lookup(ctx, clk, lookup_id); } EXPORT_SYMBOL_GPL(rockchip_clk_register_armclk); diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h index f1957e1c1178..9b37d44b9e5d 100644 --- a/drivers/clk/rockchip/clk.h +++ b/drivers/clk/rockchip/clk.h @@ -570,6 +570,7 @@ enum rockchip_clk_branch_type { branch_divider, branch_fraction_divider, branch_gate, + branch_linked_gate, branch_mmc, branch_inverter, branch_factor, @@ -597,6 +598,7 @@ struct rockchip_clk_branch { int gate_offset; u8 gate_shift; u8 gate_flags; + unsigned int linked_clk_id; struct rockchip_clk_branch *child; }; @@ -895,6 +897,20 @@ struct rockchip_clk_branch { .gate_flags = gf, \ } +#define GATE_LINK(_id, cname, pname, linkedclk, f, o, b, gf) \ + { \ + .id = _id, \ + .branch_type = branch_linked_gate, \ + .name = cname, \ + .parent_names = (const char *[]){ pname }, \ + .linked_clk_id = linkedclk, \ + .num_parents = 1, \ + .flags = f, \ + .gate_offset = o, \ + .gate_shift = b, \ + .gate_flags = gf, \ + } + #define MMC(_id, cname, pname, offset, shift) \ { \ .id = _id, \ @@ -1022,8 +1038,28 @@ struct rockchip_clk_branch { #define SGRF_GATE(_id, cname, pname) \ FACTOR(_id, cname, pname, 0, 1, 1) +static inline struct clk *rockchip_clk_get_lookup(struct rockchip_clk_provider *ctx, + unsigned int id) +{ + return ctx->clk_data.clks[id]; +} + +static inline void rockchip_clk_set_lookup(struct rockchip_clk_provider *ctx, + struct clk *clk, unsigned int id) +{ + ctx->clk_data.clks[id] = clk; +} + +struct rockchip_gate_link_platdata { + struct rockchip_clk_provider *ctx; + struct rockchip_clk_branch *clkbr; +}; + struct rockchip_clk_provider *rockchip_clk_init(struct device_node *np, void __iomem *base, unsigned long nr_clks); +struct rockchip_clk_provider *rockchip_clk_init_early(struct device_node *np, + void __iomem *base, unsigned long nr_clks); +void rockchip_clk_finalize(struct rockchip_clk_provider *ctx); void rockchip_clk_of_add_provider(struct device_node *np, struct rockchip_clk_provider *ctx); unsigned long rockchip_clk_find_max_clk_id(struct rockchip_clk_branch *list, @@ -1031,6 +1067,10 @@ unsigned long rockchip_clk_find_max_clk_id(struct rockchip_clk_branch *list, void rockchip_clk_register_branches(struct rockchip_clk_provider *ctx, struct rockchip_clk_branch *list, unsigned int nr_clk); +void rockchip_clk_register_late_branches(struct device *dev, + struct rockchip_clk_provider *ctx, + struct rockchip_clk_branch *list, + unsigned int nr_clk); void rockchip_clk_register_plls(struct rockchip_clk_provider *ctx, struct rockchip_pll_clock *pll_list, unsigned int nr_pll, int grf_lock_offset); diff --git a/drivers/clk/rockchip/gate-link.c b/drivers/clk/rockchip/gate-link.c new file mode 100644 index 000000000000..cd0f7a2d30ab --- /dev/null +++ b/drivers/clk/rockchip/gate-link.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2024 Collabora Ltd. + * Author: Sebastian Reichel + */ + +#include +#include +#include +#include +#include +#include "clk.h" + +static int rk_clk_gate_link_register(struct device *dev, + struct rockchip_clk_provider *ctx, + struct rockchip_clk_branch *clkbr) +{ + unsigned long flags = clkbr->flags | CLK_SET_RATE_PARENT; + struct clk *clk; + + clk = clk_register_gate(dev, clkbr->name, clkbr->parent_names[0], + flags, ctx->reg_base + clkbr->gate_offset, + clkbr->gate_shift, clkbr->gate_flags, + &ctx->lock); + + if (IS_ERR(clk)) + return PTR_ERR(clk); + + rockchip_clk_set_lookup(ctx, clk, clkbr->id); + return 0; +} + +static int rk_clk_gate_link_probe(struct platform_device *pdev) +{ + struct rockchip_gate_link_platdata *pdata; + struct device *dev = &pdev->dev; + struct clk *linked_clk; + int ret; + + pdata = dev_get_platdata(dev); + if (!pdata) + return dev_err_probe(dev, -ENODEV, "missing platform data"); + + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; + + ret = devm_pm_clk_create(dev); + if (ret) + return ret; + + linked_clk = rockchip_clk_get_lookup(pdata->ctx, pdata->clkbr->linked_clk_id); + ret = pm_clk_add_clk(dev, linked_clk); + if (ret) + return ret; + + ret = rk_clk_gate_link_register(dev, pdata->ctx, pdata->clkbr); + if (ret) + goto err; + + return 0; + +err: + pm_clk_remove_clk(dev, linked_clk); + return ret; +} + +static const struct dev_pm_ops rk_clk_gate_link_pm_ops = { + SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL) +}; + +static struct platform_driver rk_clk_gate_link_driver = { + .probe = rk_clk_gate_link_probe, + .driver = { + .name = "rockchip-gate-link-clk", + .pm = &rk_clk_gate_link_pm_ops, + .suppress_bind_attrs = true, + }, +}; + +static int __init rk_clk_gate_link_drv_register(void) +{ + return platform_driver_register(&rk_clk_gate_link_driver); +} +core_initcall(rk_clk_gate_link_drv_register); diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile index 7a88331a658d..90e5b114872c 100644 --- a/drivers/clk/samsung/Makefile +++ b/drivers/clk/samsung/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK) += clk-exynos7.o obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK) += clk-exynos7885.o obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK) += clk-exynos850.o obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK) += clk-exynos8895.o +obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK) += clk-exynos990.o obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK) += clk-exynosautov9.o obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK) += clk-exynosautov920.o obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK) += clk-gs101.o diff --git a/drivers/clk/samsung/clk-exynos990.c b/drivers/clk/samsung/clk-exynos990.c new file mode 100644 index 000000000000..8e2a2e8eccee --- /dev/null +++ b/drivers/clk/samsung/clk-exynos990.c @@ -0,0 +1,1343 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Igor Belwon + * + * Common Clock Framework support for Exynos990. + */ + +#include +#include +#include +#include + +#include + +#include "clk.h" +#include "clk-exynos-arm64.h" +#include "clk-pll.h" + +/* NOTE: Must be equal to the last clock ID increased by one */ +#define CLKS_NR_TOP (CLK_GOUT_CMU_VRA_BUS + 1) +#define CLKS_NR_HSI0 (CLK_GOUT_HSI0_XIU_D_HSI0_ACLK + 1) + +/* ---- CMU_TOP ------------------------------------------------------------- */ + +/* Register Offset definitions for CMU_TOP (0x1a330000) */ +#define PLL_LOCKTIME_PLL_G3D 0x0000 +#define PLL_LOCKTIME_PLL_MMC 0x0004 +#define PLL_LOCKTIME_PLL_SHARED0 0x0008 +#define PLL_LOCKTIME_PLL_SHARED1 0x000c +#define PLL_LOCKTIME_PLL_SHARED2 0x0010 +#define PLL_LOCKTIME_PLL_SHARED3 0x0014 +#define PLL_LOCKTIME_PLL_SHARED4 0x0018 +#define PLL_CON0_PLL_G3D 0x0100 +#define PLL_CON3_PLL_G3D 0x010c +#define PLL_CON0_PLL_MMC 0x0140 +#define PLL_CON3_PLL_MMC 0x014c +#define PLL_CON0_PLL_SHARED0 0x0180 +#define PLL_CON3_PLL_SHARED0 0x018c +#define PLL_CON0_PLL_SHARED1 0x01c0 +#define PLL_CON3_PLL_SHARED1 0x01cc +#define PLL_CON0_PLL_SHARED2 0x0200 +#define PLL_CON3_PLL_SHARED2 0x020c +#define PLL_CON0_PLL_SHARED3 0x0240 +#define PLL_CON3_PLL_SHARED3 0x024c +#define PLL_CON0_PLL_SHARED4 0x0280 +#define PLL_CON3_PLL_SHARED4 0x028c +#define CLK_CON_MUX_MUX_CLKCMU_APM_BUS 0x1004 +#define CLK_CON_MUX_MUX_CLKCMU_AUD_CPU 0x1008 +#define CLK_CON_MUX_MUX_CLKCMU_BUS0_BUS 0x100c +#define CLK_CON_MUX_MUX_CLKCMU_BUS1_BUS 0x1010 +#define CLK_CON_MUX_MUX_CLKCMU_BUS1_SSS 0x1014 +#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK0 0x1018 +#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK1 0x101c +#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK2 0x1020 +#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK3 0x1024 +#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK4 0x1028 +#define CLK_CON_MUX_MUX_CLKCMU_CIS_CLK5 0x102c +#define CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST 0x1030 +#define CLK_CON_MUX_MUX_CLKCMU_CORE_BUS 0x1034 +#define CLK_CON_MUX_MUX_CLKCMU_CPUCL0_DBG_BUS 0x1038 +#define CLK_CON_MUX_MUX_CLKCMU_CPUCL0_SWITCH 0x103c +#define CLK_CON_MUX_MUX_CLKCMU_CPUCL1_SWITCH 0x1040 +#define CLK_CON_MUX_MUX_CLKCMU_CPUCL2_BUSP 0x1044 +#define CLK_CON_MUX_MUX_CLKCMU_CPUCL2_SWITCH 0x1048 +#define CLK_CON_MUX_MUX_CLKCMU_CSIS_BUS 0x104c +#define CLK_CON_MUX_MUX_CLKCMU_CSIS_OIS_MCU 0x1050 +#define CLK_CON_MUX_MUX_CLKCMU_DNC_BUS 0x1054 +#define CLK_CON_MUX_MUX_CLKCMU_DNC_BUSM 0x1058 +#define CLK_CON_MUX_MUX_CLKCMU_DNS_BUS 0x105c +#define CLK_CON_MUX_MUX_CLKCMU_DPU 0x1060 +#define CLK_CON_MUX_MUX_CLKCMU_DPU_ALT 0x1064 +#define CLK_CON_MUX_MUX_CLKCMU_DSP_BUS 0x1068 +#define CLK_CON_MUX_MUX_CLKCMU_G2D_G2D 0x106c +#define CLK_CON_MUX_MUX_CLKCMU_G2D_MSCL 0x1070 +#define CLK_CON_MUX_MUX_CLKCMU_HPM 0x1074 +#define CLK_CON_MUX_MUX_CLKCMU_HSI0_BUS 0x1078 +#define CLK_CON_MUX_MUX_CLKCMU_HSI0_DPGTC 0x107c +#define CLK_CON_MUX_MUX_CLKCMU_HSI0_USB31DRD 0x1080 +#define CLK_CON_MUX_MUX_CLKCMU_HSI0_USBDP_DEBUG 0x1084 +#define CLK_CON_MUX_MUX_CLKCMU_HSI1_BUS 0x1088 +#define CLK_CON_MUX_MUX_CLKCMU_HSI1_MMC_CARD 0x108c +#define CLK_CON_MUX_MUX_CLKCMU_HSI1_PCIE 0x1090 +#define CLK_CON_MUX_MUX_CLKCMU_HSI1_UFS_CARD 0x1094 +#define CLK_CON_MUX_MUX_CLKCMU_HSI1_UFS_EMBD 0x1098 +#define CLK_CON_MUX_MUX_CLKCMU_HSI2_BUS 0x109c +#define CLK_CON_MUX_MUX_CLKCMU_HSI2_PCIE 0x10a0 +#define CLK_CON_MUX_MUX_CLKCMU_IPP_BUS 0x10a4 +#define CLK_CON_MUX_MUX_CLKCMU_ITP_BUS 0x10a8 +#define CLK_CON_MUX_MUX_CLKCMU_MCSC_BUS 0x10ac +#define CLK_CON_MUX_MUX_CLKCMU_MCSC_GDC 0x10b0 +#define CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST_CPU 0x10b4 +#define CLK_CON_MUX_MUX_CLKCMU_MFC0_MFC0 0x10b8 +#define CLK_CON_MUX_MUX_CLKCMU_MFC0_WFD 0x10bc +#define CLK_CON_MUX_MUX_CLKCMU_MIF_BUSP 0x10c0 +#define CLK_CON_MUX_MUX_CLKCMU_MIF_SWITCH 0x10c4 +#define CLK_CON_MUX_MUX_CLKCMU_NPU_BUS 0x10c8 +#define CLK_CON_MUX_MUX_CLKCMU_PERIC0_BUS 0x10cc +#define CLK_CON_MUX_MUX_CLKCMU_PERIC0_IP 0x10d0 +#define CLK_CON_MUX_MUX_CLKCMU_PERIC1_BUS 0x10d4 +#define CLK_CON_MUX_MUX_CLKCMU_PERIC1_IP 0x10d8 +#define CLK_CON_MUX_MUX_CLKCMU_PERIS_BUS 0x10dc +#define CLK_CON_MUX_MUX_CLKCMU_SSP_BUS 0x10e0 +#define CLK_CON_MUX_MUX_CLKCMU_TNR_BUS 0x10e4 +#define CLK_CON_MUX_MUX_CLKCMU_VRA_BUS 0x10e8 +#define CLK_CON_DIV_CLKCMU_APM_BUS 0x1800 +#define CLK_CON_DIV_CLKCMU_AUD_CPU 0x1804 +#define CLK_CON_DIV_CLKCMU_BUS0_BUS 0x1808 +#define CLK_CON_DIV_CLKCMU_BUS1_BUS 0x180c +#define CLK_CON_DIV_CLKCMU_BUS1_SSS 0x1810 +#define CLK_CON_DIV_CLKCMU_CIS_CLK0 0x1814 +#define CLK_CON_DIV_CLKCMU_CIS_CLK1 0x1818 +#define CLK_CON_DIV_CLKCMU_CIS_CLK2 0x181c +#define CLK_CON_DIV_CLKCMU_CIS_CLK3 0x1820 +#define CLK_CON_DIV_CLKCMU_CIS_CLK4 0x1824 +#define CLK_CON_DIV_CLKCMU_CIS_CLK5 0x1828 +#define CLK_CON_DIV_CLKCMU_CMU_BOOST 0x182c +#define CLK_CON_DIV_CLKCMU_CORE_BUS 0x1830 +#define CLK_CON_DIV_CLKCMU_CPUCL0_DBG_BUS 0x1834 +#define CLK_CON_DIV_CLKCMU_CPUCL0_SWITCH 0x1838 +#define CLK_CON_DIV_CLKCMU_CPUCL1_SWITCH 0x183c +#define CLK_CON_DIV_CLKCMU_CPUCL2_BUSP 0x1840 +#define CLK_CON_DIV_CLKCMU_CPUCL2_SWITCH 0x1844 +#define CLK_CON_DIV_CLKCMU_CSIS_BUS 0x1848 +#define CLK_CON_DIV_CLKCMU_CSIS_OIS_MCU 0x184c +#define CLK_CON_DIV_CLKCMU_DNC_BUS 0x1850 +#define CLK_CON_DIV_CLKCMU_DNC_BUSM 0x1854 +#define CLK_CON_DIV_CLKCMU_DNS_BUS 0x1858 +#define CLK_CON_DIV_CLKCMU_DSP_BUS 0x185c +#define CLK_CON_DIV_CLKCMU_G2D_G2D 0x1860 +#define CLK_CON_DIV_CLKCMU_G2D_MSCL 0x1864 +#define CLK_CON_DIV_CLKCMU_G3D_SWITCH 0x1868 +#define CLK_CON_DIV_CLKCMU_HPM 0x186c +#define CLK_CON_DIV_CLKCMU_HSI0_BUS 0x1870 +#define CLK_CON_DIV_CLKCMU_HSI0_DPGTC 0x1874 +#define CLK_CON_DIV_CLKCMU_HSI0_USB31DRD 0x1878 +#define CLK_CON_DIV_CLKCMU_HSI0_USBDP_DEBUG 0x187c +#define CLK_CON_DIV_CLKCMU_HSI1_BUS 0x1880 +#define CLK_CON_DIV_CLKCMU_HSI1_MMC_CARD 0x1884 +#define CLK_CON_DIV_CLKCMU_HSI1_PCIE 0x1888 +#define CLK_CON_DIV_CLKCMU_HSI1_UFS_CARD 0x188c +#define CLK_CON_DIV_CLKCMU_HSI1_UFS_EMBD 0x1890 +#define CLK_CON_DIV_CLKCMU_HSI2_BUS 0x1894 +#define CLK_CON_DIV_CLKCMU_HSI2_PCIE 0x1898 +#define CLK_CON_DIV_CLKCMU_IPP_BUS 0x189c +#define CLK_CON_DIV_CLKCMU_ITP_BUS 0x18a0 +#define CLK_CON_DIV_CLKCMU_MCSC_BUS 0x18a4 +#define CLK_CON_DIV_CLKCMU_MCSC_GDC 0x18a8 +#define CLK_CON_DIV_CLKCMU_CMU_BOOST_CPU 0x18ac +#define CLK_CON_DIV_CLKCMU_MFC0_MFC0 0x18b0 +#define CLK_CON_DIV_CLKCMU_MFC0_WFD 0x18b4 +#define CLK_CON_DIV_CLKCMU_MIF_BUSP 0x18b8 +#define CLK_CON_DIV_CLKCMU_NPU_BUS 0x18bc +#define CLK_CON_DIV_CLKCMU_OTP 0x18c0 +#define CLK_CON_DIV_CLKCMU_PERIC0_BUS 0x18c4 +#define CLK_CON_DIV_CLKCMU_PERIC0_IP 0x18c8 +#define CLK_CON_DIV_CLKCMU_PERIC1_BUS 0x18cc +#define CLK_CON_DIV_CLKCMU_PERIC1_IP 0x18d0 +#define CLK_CON_DIV_CLKCMU_PERIS_BUS 0x18d4 +#define CLK_CON_DIV_CLKCMU_SSP_BUS 0x18d8 +#define CLK_CON_DIV_CLKCMU_TNR_BUS 0x18dc +#define CLK_CON_DIV_CLKCMU_VRA_BUS 0x18e0 +#define CLK_CON_DIV_DIV_CLKCMU_DPU 0x18e8 +#define CLK_CON_DIV_DIV_CLKCMU_DPU_ALT 0x18ec +#define CLK_CON_DIV_PLL_SHARED0_DIV2 0x18f4 +#define CLK_CON_DIV_PLL_SHARED0_DIV3 0x18f8 +#define CLK_CON_DIV_PLL_SHARED0_DIV4 0x18fc +#define CLK_CON_DIV_PLL_SHARED1_DIV2 0x1900 +#define CLK_CON_DIV_PLL_SHARED1_DIV3 0x1904 +#define CLK_CON_DIV_PLL_SHARED1_DIV4 0x1908 +#define CLK_CON_DIV_PLL_SHARED2_DIV2 0x190c +#define CLK_CON_DIV_PLL_SHARED4_DIV2 0x1910 +#define CLK_CON_DIV_PLL_SHARED4_DIV3 0x1914 +#define CLK_CON_DIV_PLL_SHARED4_DIV4 0x1918 +#define CLK_CON_GAT_CLKCMU_G3D_BUS 0x2000 +#define CLK_CON_GAT_CLKCMU_MIF_SWITCH 0x2004 +#define CLK_CON_GAT_GATE_CLKCMU_APM_BUS 0x2008 +#define CLK_CON_GAT_GATE_CLKCMU_AUD_CPU 0x200c +#define CLK_CON_GAT_GATE_CLKCMU_BUS0_BUS 0x2010 +#define CLK_CON_GAT_GATE_CLKCMU_BUS1_BUS 0x2014 +#define CLK_CON_GAT_GATE_CLKCMU_BUS1_SSS 0x2018 +#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK0 0x201c +#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK1 0x2020 +#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK2 0x2024 +#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK3 0x2028 +#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK4 0x202c +#define CLK_CON_GAT_GATE_CLKCMU_CIS_CLK5 0x2030 +#define CLK_CON_GAT_GATE_CLKCMU_CORE_BUS 0x2034 +#define CLK_CON_GAT_GATE_CLKCMU_CPUCL0_DBG_BUS 0x2038 +#define CLK_CON_GAT_GATE_CLKCMU_CPUCL0_SWITCH 0x203c +#define CLK_CON_GAT_GATE_CLKCMU_CPUCL1_SWITCH 0x2040 +#define CLK_CON_GAT_GATE_CLKCMU_CPUCL2_BUSP 0x2044 +#define CLK_CON_GAT_GATE_CLKCMU_CPUCL2_SWITCH 0x2048 +#define CLK_CON_GAT_GATE_CLKCMU_CSIS_BUS 0x204c +#define CLK_CON_GAT_GATE_CLKCMU_CSIS_OIS_MCU 0x2050 +#define CLK_CON_GAT_GATE_CLKCMU_DNC_BUS 0x2054 +#define CLK_CON_GAT_GATE_CLKCMU_DNC_BUSM 0x2058 +#define CLK_CON_GAT_GATE_CLKCMU_DNS_BUS 0x205c +#define CLK_CON_GAT_GATE_CLKCMU_DPU 0x2060 +#define CLK_CON_GAT_GATE_CLKCMU_DPU_BUS 0x2064 +#define CLK_CON_GAT_GATE_CLKCMU_DSP_BUS 0x2068 +#define CLK_CON_GAT_GATE_CLKCMU_G2D_G2D 0x206c +#define CLK_CON_GAT_GATE_CLKCMU_G2D_MSCL 0x2070 +#define CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH 0x2074 +#define CLK_CON_GAT_GATE_CLKCMU_HPM 0x2078 +#define CLK_CON_GAT_GATE_CLKCMU_HSI0_BUS 0x207c +#define CLK_CON_GAT_GATE_CLKCMU_HSI0_DPGTC 0x2080 +#define CLK_CON_GAT_GATE_CLKCMU_HSI0_USB31DRD 0x2084 +#define CLK_CON_GAT_GATE_CLKCMU_HSI0_USBDP_DEBUG 0x2088 +#define CLK_CON_GAT_GATE_CLKCMU_HSI1_BUS 0x208c +#define CLK_CON_GAT_GATE_CLKCMU_HSI1_MMC_CARD 0x2090 +#define CLK_CON_GAT_GATE_CLKCMU_HSI1_PCIE 0x2094 +#define CLK_CON_GAT_GATE_CLKCMU_HSI1_UFS_CARD 0x2098 +#define CLK_CON_GAT_GATE_CLKCMU_HSI1_UFS_EMBD 0x209c +#define CLK_CON_GAT_GATE_CLKCMU_HSI2_BUS 0x20a0 +#define CLK_CON_GAT_GATE_CLKCMU_HSI2_PCIE 0x20a4 +#define CLK_CON_GAT_GATE_CLKCMU_IPP_BUS 0x20a8 +#define CLK_CON_GAT_GATE_CLKCMU_ITP_BUS 0x20ac +#define CLK_CON_GAT_GATE_CLKCMU_MCSC_BUS 0x20b0 +#define CLK_CON_GAT_GATE_CLKCMU_MCSC_GDC 0x20b4 +#define CLK_CON_GAT_GATE_CLKCMU_MFC0_MFC0 0x20bc +#define CLK_CON_GAT_GATE_CLKCMU_MFC0_WFD 0x20c0 +#define CLK_CON_GAT_GATE_CLKCMU_MIF_BUSP 0x20c4 +#define CLK_CON_GAT_GATE_CLKCMU_NPU_BUS 0x20c8 +#define CLK_CON_GAT_GATE_CLKCMU_PERIC0_BUS 0x20cc +#define CLK_CON_GAT_GATE_CLKCMU_PERIC0_IP 0x20d0 +#define CLK_CON_GAT_GATE_CLKCMU_PERIC1_BUS 0x20d4 +#define CLK_CON_GAT_GATE_CLKCMU_PERIC1_IP 0x20d8 +#define CLK_CON_GAT_GATE_CLKCMU_PERIS_BUS 0x20dc +#define CLK_CON_GAT_GATE_CLKCMU_SSP_BUS 0x20e0 +#define CLK_CON_GAT_GATE_CLKCMU_TNR_BUS 0x20e4 +#define CLK_CON_GAT_GATE_CLKCMU_VRA_BUS 0x20e8 + +static const unsigned long top_clk_regs[] __initconst = { + PLL_LOCKTIME_PLL_G3D, + PLL_LOCKTIME_PLL_MMC, + PLL_LOCKTIME_PLL_SHARED0, + PLL_LOCKTIME_PLL_SHARED1, + PLL_LOCKTIME_PLL_SHARED2, + PLL_LOCKTIME_PLL_SHARED3, + PLL_LOCKTIME_PLL_SHARED4, + PLL_CON3_PLL_G3D, + PLL_CON3_PLL_MMC, + PLL_CON3_PLL_SHARED0, + PLL_CON3_PLL_SHARED1, + PLL_CON3_PLL_SHARED2, + PLL_CON3_PLL_SHARED3, + PLL_CON3_PLL_SHARED4, + CLK_CON_MUX_MUX_CLKCMU_APM_BUS, + CLK_CON_MUX_MUX_CLKCMU_AUD_CPU, + CLK_CON_MUX_MUX_CLKCMU_BUS0_BUS, + CLK_CON_MUX_MUX_CLKCMU_BUS1_BUS, + CLK_CON_MUX_MUX_CLKCMU_BUS1_SSS, + CLK_CON_MUX_MUX_CLKCMU_CIS_CLK0, + CLK_CON_MUX_MUX_CLKCMU_CIS_CLK1, + CLK_CON_MUX_MUX_CLKCMU_CIS_CLK2, + CLK_CON_MUX_MUX_CLKCMU_CIS_CLK3, + CLK_CON_MUX_MUX_CLKCMU_CIS_CLK4, + CLK_CON_MUX_MUX_CLKCMU_CIS_CLK5, + CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST, + CLK_CON_MUX_MUX_CLKCMU_CORE_BUS, + CLK_CON_MUX_MUX_CLKCMU_CPUCL0_DBG_BUS, + CLK_CON_MUX_MUX_CLKCMU_CPUCL0_SWITCH, + CLK_CON_MUX_MUX_CLKCMU_CPUCL1_SWITCH, + CLK_CON_MUX_MUX_CLKCMU_CPUCL2_BUSP, + CLK_CON_MUX_MUX_CLKCMU_CPUCL2_SWITCH, + CLK_CON_MUX_MUX_CLKCMU_CSIS_BUS, + CLK_CON_MUX_MUX_CLKCMU_CSIS_OIS_MCU, + CLK_CON_MUX_MUX_CLKCMU_DNC_BUS, + CLK_CON_MUX_MUX_CLKCMU_DNC_BUSM, + CLK_CON_MUX_MUX_CLKCMU_DNS_BUS, + CLK_CON_MUX_MUX_CLKCMU_DPU, + CLK_CON_MUX_MUX_CLKCMU_DPU_ALT, + CLK_CON_MUX_MUX_CLKCMU_DSP_BUS, + CLK_CON_MUX_MUX_CLKCMU_G2D_G2D, + CLK_CON_MUX_MUX_CLKCMU_G2D_MSCL, + CLK_CON_MUX_MUX_CLKCMU_HPM, + CLK_CON_MUX_MUX_CLKCMU_HSI0_BUS, + CLK_CON_MUX_MUX_CLKCMU_HSI0_DPGTC, + CLK_CON_MUX_MUX_CLKCMU_HSI0_USB31DRD, + CLK_CON_MUX_MUX_CLKCMU_HSI0_USBDP_DEBUG, + CLK_CON_MUX_MUX_CLKCMU_HSI1_BUS, + CLK_CON_MUX_MUX_CLKCMU_HSI1_MMC_CARD, + CLK_CON_MUX_MUX_CLKCMU_HSI1_PCIE, + CLK_CON_MUX_MUX_CLKCMU_HSI1_UFS_CARD, + CLK_CON_MUX_MUX_CLKCMU_HSI1_UFS_EMBD, + CLK_CON_MUX_MUX_CLKCMU_HSI2_BUS, + CLK_CON_MUX_MUX_CLKCMU_HSI2_PCIE, + CLK_CON_MUX_MUX_CLKCMU_IPP_BUS, + CLK_CON_MUX_MUX_CLKCMU_ITP_BUS, + CLK_CON_MUX_MUX_CLKCMU_MCSC_BUS, + CLK_CON_MUX_MUX_CLKCMU_MCSC_GDC, + CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST_CPU, + CLK_CON_MUX_MUX_CLKCMU_MFC0_MFC0, + CLK_CON_MUX_MUX_CLKCMU_MFC0_WFD, + CLK_CON_MUX_MUX_CLKCMU_MIF_BUSP, + CLK_CON_MUX_MUX_CLKCMU_MIF_SWITCH, + CLK_CON_MUX_MUX_CLKCMU_NPU_BUS, + CLK_CON_MUX_MUX_CLKCMU_PERIC0_BUS, + CLK_CON_MUX_MUX_CLKCMU_PERIC0_IP, + CLK_CON_MUX_MUX_CLKCMU_PERIC1_BUS, + CLK_CON_MUX_MUX_CLKCMU_PERIC1_IP, + CLK_CON_MUX_MUX_CLKCMU_PERIS_BUS, + CLK_CON_MUX_MUX_CLKCMU_SSP_BUS, + CLK_CON_MUX_MUX_CLKCMU_TNR_BUS, + CLK_CON_MUX_MUX_CLKCMU_VRA_BUS, + CLK_CON_DIV_CLKCMU_APM_BUS, + CLK_CON_DIV_CLKCMU_AUD_CPU, + CLK_CON_DIV_CLKCMU_BUS0_BUS, + CLK_CON_DIV_CLKCMU_BUS1_BUS, + CLK_CON_DIV_CLKCMU_BUS1_SSS, + CLK_CON_DIV_CLKCMU_CIS_CLK0, + CLK_CON_DIV_CLKCMU_CIS_CLK1, + CLK_CON_DIV_CLKCMU_CIS_CLK2, + CLK_CON_DIV_CLKCMU_CIS_CLK3, + CLK_CON_DIV_CLKCMU_CIS_CLK4, + CLK_CON_DIV_CLKCMU_CIS_CLK5, + CLK_CON_DIV_CLKCMU_CMU_BOOST, + CLK_CON_DIV_CLKCMU_CORE_BUS, + CLK_CON_DIV_CLKCMU_CPUCL0_DBG_BUS, + CLK_CON_DIV_CLKCMU_CPUCL0_SWITCH, + CLK_CON_DIV_CLKCMU_CPUCL1_SWITCH, + CLK_CON_DIV_CLKCMU_CPUCL2_BUSP, + CLK_CON_DIV_CLKCMU_CPUCL2_SWITCH, + CLK_CON_DIV_CLKCMU_CSIS_BUS, + CLK_CON_DIV_CLKCMU_CSIS_OIS_MCU, + CLK_CON_DIV_CLKCMU_DNC_BUS, + CLK_CON_DIV_CLKCMU_DNC_BUSM, + CLK_CON_DIV_CLKCMU_DNS_BUS, + CLK_CON_DIV_CLKCMU_DSP_BUS, + CLK_CON_DIV_CLKCMU_G2D_G2D, + CLK_CON_DIV_CLKCMU_G2D_MSCL, + CLK_CON_DIV_CLKCMU_G3D_SWITCH, + CLK_CON_DIV_CLKCMU_HPM, + CLK_CON_DIV_CLKCMU_HSI0_BUS, + CLK_CON_DIV_CLKCMU_HSI0_DPGTC, + CLK_CON_DIV_CLKCMU_HSI0_USB31DRD, + CLK_CON_DIV_CLKCMU_HSI0_USBDP_DEBUG, + CLK_CON_DIV_CLKCMU_HSI1_BUS, + CLK_CON_DIV_CLKCMU_HSI1_MMC_CARD, + CLK_CON_DIV_CLKCMU_HSI1_PCIE, + CLK_CON_DIV_CLKCMU_HSI1_UFS_CARD, + CLK_CON_DIV_CLKCMU_HSI1_UFS_EMBD, + CLK_CON_DIV_CLKCMU_HSI2_BUS, + CLK_CON_DIV_CLKCMU_HSI2_PCIE, + CLK_CON_DIV_CLKCMU_IPP_BUS, + CLK_CON_DIV_CLKCMU_ITP_BUS, + CLK_CON_DIV_CLKCMU_MCSC_BUS, + CLK_CON_DIV_CLKCMU_MCSC_GDC, + CLK_CON_DIV_CLKCMU_CMU_BOOST_CPU, + CLK_CON_DIV_CLKCMU_MFC0_MFC0, + CLK_CON_DIV_CLKCMU_MFC0_WFD, + CLK_CON_DIV_CLKCMU_MIF_BUSP, + CLK_CON_DIV_CLKCMU_NPU_BUS, + CLK_CON_DIV_CLKCMU_OTP, + CLK_CON_DIV_CLKCMU_PERIC0_BUS, + CLK_CON_DIV_CLKCMU_PERIC0_IP, + CLK_CON_DIV_CLKCMU_PERIC1_BUS, + CLK_CON_DIV_CLKCMU_PERIC1_IP, + CLK_CON_DIV_CLKCMU_PERIS_BUS, + CLK_CON_DIV_CLKCMU_SSP_BUS, + CLK_CON_DIV_CLKCMU_TNR_BUS, + CLK_CON_DIV_CLKCMU_VRA_BUS, + CLK_CON_DIV_DIV_CLKCMU_DPU, + CLK_CON_DIV_DIV_CLKCMU_DPU_ALT, + CLK_CON_DIV_PLL_SHARED0_DIV2, + CLK_CON_DIV_PLL_SHARED0_DIV3, + CLK_CON_DIV_PLL_SHARED0_DIV4, + CLK_CON_DIV_PLL_SHARED1_DIV2, + CLK_CON_DIV_PLL_SHARED1_DIV3, + CLK_CON_DIV_PLL_SHARED1_DIV4, + CLK_CON_DIV_PLL_SHARED2_DIV2, + CLK_CON_DIV_PLL_SHARED4_DIV2, + CLK_CON_DIV_PLL_SHARED4_DIV3, + CLK_CON_DIV_PLL_SHARED4_DIV4, + CLK_CON_GAT_CLKCMU_G3D_BUS, + CLK_CON_GAT_CLKCMU_MIF_SWITCH, + CLK_CON_GAT_GATE_CLKCMU_APM_BUS, + CLK_CON_GAT_GATE_CLKCMU_AUD_CPU, + CLK_CON_GAT_GATE_CLKCMU_BUS0_BUS, + CLK_CON_GAT_GATE_CLKCMU_BUS1_BUS, + CLK_CON_GAT_GATE_CLKCMU_BUS1_SSS, + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK0, + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK1, + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK2, + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK3, + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK4, + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK5, + CLK_CON_GAT_GATE_CLKCMU_CORE_BUS, + CLK_CON_GAT_GATE_CLKCMU_CPUCL0_DBG_BUS, + CLK_CON_GAT_GATE_CLKCMU_CPUCL0_SWITCH, + CLK_CON_GAT_GATE_CLKCMU_CPUCL1_SWITCH, + CLK_CON_GAT_GATE_CLKCMU_CPUCL2_BUSP, + CLK_CON_GAT_GATE_CLKCMU_CPUCL2_SWITCH, + CLK_CON_GAT_GATE_CLKCMU_CSIS_BUS, + CLK_CON_GAT_GATE_CLKCMU_CSIS_OIS_MCU, + CLK_CON_GAT_GATE_CLKCMU_DNC_BUS, + CLK_CON_GAT_GATE_CLKCMU_DNC_BUSM, + CLK_CON_GAT_GATE_CLKCMU_DNS_BUS, + CLK_CON_GAT_GATE_CLKCMU_DPU, + CLK_CON_GAT_GATE_CLKCMU_DPU_BUS, + CLK_CON_GAT_GATE_CLKCMU_DSP_BUS, + CLK_CON_GAT_GATE_CLKCMU_G2D_G2D, + CLK_CON_GAT_GATE_CLKCMU_G2D_MSCL, + CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH, + CLK_CON_GAT_GATE_CLKCMU_HPM, + CLK_CON_GAT_GATE_CLKCMU_HSI0_BUS, + CLK_CON_GAT_GATE_CLKCMU_HSI0_DPGTC, + CLK_CON_GAT_GATE_CLKCMU_HSI0_USB31DRD, + CLK_CON_GAT_GATE_CLKCMU_HSI0_USBDP_DEBUG, + CLK_CON_GAT_GATE_CLKCMU_HSI1_BUS, + CLK_CON_GAT_GATE_CLKCMU_HSI1_MMC_CARD, + CLK_CON_GAT_GATE_CLKCMU_HSI1_PCIE, + CLK_CON_GAT_GATE_CLKCMU_HSI1_UFS_CARD, + CLK_CON_GAT_GATE_CLKCMU_HSI1_UFS_EMBD, + CLK_CON_GAT_GATE_CLKCMU_HSI2_BUS, + CLK_CON_GAT_GATE_CLKCMU_HSI2_PCIE, + CLK_CON_GAT_GATE_CLKCMU_IPP_BUS, + CLK_CON_GAT_GATE_CLKCMU_ITP_BUS, + CLK_CON_GAT_GATE_CLKCMU_MCSC_BUS, + CLK_CON_GAT_GATE_CLKCMU_MCSC_GDC, + CLK_CON_GAT_GATE_CLKCMU_MFC0_MFC0, + CLK_CON_GAT_GATE_CLKCMU_MFC0_WFD, + CLK_CON_GAT_GATE_CLKCMU_MIF_BUSP, + CLK_CON_GAT_GATE_CLKCMU_NPU_BUS, + CLK_CON_GAT_GATE_CLKCMU_PERIC0_BUS, + CLK_CON_GAT_GATE_CLKCMU_PERIC0_IP, + CLK_CON_GAT_GATE_CLKCMU_PERIC1_BUS, + CLK_CON_GAT_GATE_CLKCMU_PERIC1_IP, + CLK_CON_GAT_GATE_CLKCMU_PERIS_BUS, + CLK_CON_GAT_GATE_CLKCMU_SSP_BUS, + CLK_CON_GAT_GATE_CLKCMU_TNR_BUS, + CLK_CON_GAT_GATE_CLKCMU_VRA_BUS, +}; + +static const struct samsung_pll_clock top_pll_clks[] __initconst = { + PLL(pll_0717x, CLK_FOUT_SHARED0_PLL, "fout_shared0_pll", "oscclk", + PLL_LOCKTIME_PLL_SHARED0, PLL_CON3_PLL_SHARED0, NULL), + PLL(pll_0717x, CLK_FOUT_SHARED1_PLL, "fout_shared1_pll", "oscclk", + PLL_LOCKTIME_PLL_SHARED1, PLL_CON3_PLL_SHARED1, NULL), + PLL(pll_0718x, CLK_FOUT_SHARED2_PLL, "fout_shared2_pll", "oscclk", + PLL_LOCKTIME_PLL_SHARED2, PLL_CON3_PLL_SHARED2, NULL), + PLL(pll_0718x, CLK_FOUT_SHARED3_PLL, "fout_shared3_pll", "oscclk", + PLL_LOCKTIME_PLL_SHARED3, PLL_CON3_PLL_SHARED3, NULL), + PLL(pll_0717x, CLK_FOUT_SHARED4_PLL, "fout_shared4_pll", "oscclk", + PLL_LOCKTIME_PLL_SHARED4, PLL_CON3_PLL_SHARED4, NULL), + PLL(pll_0732x, CLK_FOUT_MMC_PLL, "fout_mmc_pll", "oscclk", + PLL_LOCKTIME_PLL_MMC, PLL_CON3_PLL_MMC, NULL), + PLL(pll_0718x, CLK_FOUT_G3D_PLL, "fout_g3d_pll", "oscclk", + PLL_LOCKTIME_PLL_G3D, PLL_CON3_PLL_G3D, NULL), +}; + +/* Parent clock list for CMU_TOP muxes*/ +PNAME(mout_pll_shared0_p) = { "oscclk", "fout_shared0_pll" }; +PNAME(mout_pll_shared1_p) = { "oscclk", "fout_shared1_pll" }; +PNAME(mout_pll_shared2_p) = { "oscclk", "fout_shared2_pll" }; +PNAME(mout_pll_shared3_p) = { "oscclk", "fout_shared3_pll" }; +PNAME(mout_pll_shared4_p) = { "oscclk", "fout_shared4_pll" }; +PNAME(mout_pll_mmc_p) = { "oscclk", "fout_mmc_pll" }; +PNAME(mout_pll_g3d_p) = { "oscclk", "fout_g3d_pll" }; +PNAME(mout_cmu_apm_bus_p) = { "dout_cmu_shared0_div2", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_aud_cpu_p) = { "dout_cmu_shared0_div2", + "fout_shared2_pll", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4" }; +PNAME(mout_cmu_bus0_bus_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_bus1_bus_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_bus1_sss_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_cis_clk0_p) = { "oscclk", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_cis_clk1_p) = { "oscclk", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_cis_clk2_p) = { "oscclk", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_cis_clk3_p) = { "oscclk", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_cis_clk4_p) = { "oscclk", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_cis_clk5_p) = { "oscclk", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_cmu_boost_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_core_bus_p) = { "dout_cmu_shared0_div2", + "dout_cmu_shared1_div2", + "fout_shared2_pll", + "dout_cmu_shared0_div3", + "dout_cmu_shared1_div3", + "dout_cmu_shared0_div4", + "fout_shared3_pll", "oscclk" }; +PNAME(mout_cmu_cpucl0_dbg_bus_p) = { "fout_shared2_pll", + "dout_cmu_shared0_div3", + "dout_cmu_shared0_div4", + "oscclk" }; +PNAME(mout_cmu_cpucl0_switch_p) = { "fout_shared4_pll", + "dout_cmu_shared0_div2", + "fout_shared2_pll", + "dout_cmu_shared0_div4" }; +PNAME(mout_cmu_cpucl1_switch_p) = { "fout_shared4_pll", + "dout_cmu_shared0_div2", + "fout_shared2_pll", + "dout_cmu_shared0_div4" }; +PNAME(mout_cmu_cpucl2_busp_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_cpucl2_switch_p) = { "fout_shared4_pll", + "dout_cmu_shared0_div2", + "fout_shared2_pll", + "dout_cmu_shared0_div4" }; +PNAME(mout_cmu_csis_bus_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared4_div3" }; +PNAME(mout_cmu_csis_ois_mcu_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_dnc_bus_p) = { "dout_cmu_shared1_div2", + "fout_shared2_pll", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4" }; +PNAME(mout_cmu_dnc_busm_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared2_div2", + "dout_cmu_shared4_div4" }; +PNAME(mout_cmu_dns_bus_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2", + "oscclk", "oscclk" }; +PNAME(mout_cmu_dpu_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared0_div4" }; +PNAME(mout_cmu_dpu_alt_p) = { "dout_cmu_shared4_div2", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_dsp_bus_p) = { "dout_cmu_shared0_div2", + "dout_cmu_shared1_div2", + "fout_shared2_pll", + "dout_cmu_shared4_div2", + "fout_shared3_pll", "oscclk", + "oscclk", "oscclk" }; +PNAME(mout_cmu_g2d_g2d_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_g2d_mscl_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2", + "dout_cmu_shared4_div4", + "oscclk" }; +PNAME(mout_cmu_hpm_p) = { "oscclk", + "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_hsi0_bus_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_hsi0_dpgtc_p) = { "oscclk", "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_hsi0_usb31drd_p) = { "oscclk", "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_hsi0_usbdp_debug_p) = { "oscclk", "fout_shared2_pll" }; +PNAME(mout_cmu_hsi1_bus_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2", + "fout_mmc_pll", "oscclk", "oscclk" }; +PNAME(mout_cmu_hsi1_mmc_card_p) = { "oscclk", "fout_shared2_pll", + "fout_mmc_pll", + "dout_cmu_shared0_div4" }; +PNAME(mout_cmu_hsi1_pcie_p) = { "oscclk", "fout_shared2_pll" }; +PNAME(mout_cmu_hsi1_ufs_card_p) = { "oscclk", "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_hsi1_ufs_embd_p) = { "oscclk", "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_hsi2_bus_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_hsi2_pcie_p) = { "oscclk", "fout_shared2_pll" }; +PNAME(mout_cmu_ipp_bus_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared4_div3", + "oscclk", "oscclk", "oscclk" }; +PNAME(mout_cmu_itp_bus_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2", + "oscclk", "oscclk" }; +PNAME(mout_cmu_mcsc_bus_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2", + "oscclk", "oscclk" }; +PNAME(mout_cmu_mcsc_gdc_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2", + "oscclk", "oscclk" }; +PNAME(mout_cmu_cmu_boost_cpu_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_mfc0_mfc0_p) = { "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_mfc0_wfd_p) = { "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_mif_busp_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_mif_switch_p) = { "fout_shared0_pll", + "fout_shared1_pll", + "dout_cmu_shared0_div2", + "dout_cmu_shared1_div2", + "fout_shared2_pll", + "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2", + "oscclk" }; +PNAME(mout_cmu_npu_bus_p) = { "dout_cmu_shared0_div2", + "dout_cmu_shared1_div2", + "fout_shared2_pll", + "dout_cmu_shared4_div2", + "fout_shared3_pll", "oscclk", + "oscclk", "oscclk" }; +PNAME(mout_cmu_peric0_bus_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_peric0_ip_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_peric1_bus_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_peric1_ip_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_peris_bus_p) = { "dout_cmu_shared0_div4", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_ssp_bus_p) = { "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2" }; +PNAME(mout_cmu_tnr_bus_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared1_div4", + "dout_cmu_shared4_div3", + "dout_cmu_shared2_div2", + "oscclk", "oscclk" }; +PNAME(mout_cmu_vra_bus_p) = { "dout_cmu_shared0_div3", + "dout_cmu_shared4_div2", + "dout_cmu_shared0_div4", + "dout_cmu_shared4_div3" }; + +/* + * Register name to clock name mangling strategy used in this file + * + * Replace PLL_CON{0,3}_PLL with CLK_MOUT_PLL and mout_pll + * Replace CLK_CON_MUX_MUX_CLKCMU with CLK_MOUT_CMU and mout_cmu + * Replace CLK_CON_DIV_CLKCMU with CLK_DOUT_CMU_CMU and dout_cmu_cmu + * Replace CLK_CON_DIV_DIV_CLKCMU with CLK_DOUT_CMU_CMU and dout_cmu_cmu + * Replace CLK_CON_DIV_PLL_CLKCMU with CLK_DOUT_CMU_CMU and dout_cmu_cmu + * Replace CLK_CON_GAT_CLKCMU with CLK_GOUT_CMU and gout_cmu + * Replace CLK_CON_GAT_GATE_CLKCMU with CLK_GOUT_CMU and gout_cmu + * + * For gates remove _UID _BLK _IPCLKPORT, _I and _RSTNSYNC + */ + +static const struct samsung_mux_clock top_mux_clks[] __initconst = { + MUX(CLK_MOUT_PLL_SHARED0, "mout_pll_shared0", mout_pll_shared0_p, + PLL_CON3_PLL_SHARED0, 4, 1), + MUX(CLK_MOUT_PLL_SHARED1, "mout_pll_shared1", mout_pll_shared1_p, + PLL_CON3_PLL_SHARED1, 4, 1), + MUX(CLK_MOUT_PLL_SHARED2, "mout_pll_shared2", mout_pll_shared2_p, + PLL_CON3_PLL_SHARED2, 4, 1), + MUX(CLK_MOUT_PLL_SHARED3, "mout_pll_shared3", mout_pll_shared3_p, + PLL_CON3_PLL_SHARED3, 4, 1), + MUX(CLK_MOUT_PLL_SHARED4, "mout_pll_shared4", mout_pll_shared4_p, + PLL_CON0_PLL_SHARED4, 4, 1), + MUX(CLK_MOUT_PLL_MMC, "mout_pll_mmc", mout_pll_mmc_p, + PLL_CON0_PLL_MMC, 4, 1), + MUX(CLK_MOUT_PLL_G3D, "mout_pll_g3d", mout_pll_g3d_p, + PLL_CON0_PLL_G3D, 4, 1), + MUX(CLK_MOUT_CMU_APM_BUS, "mout_cmu_apm_bus", + mout_cmu_apm_bus_p, CLK_CON_MUX_MUX_CLKCMU_APM_BUS, 0, 1), + MUX(CLK_MOUT_CMU_AUD_CPU, "mout_cmu_aud_cpu", + mout_cmu_aud_cpu_p, CLK_CON_MUX_MUX_CLKCMU_AUD_CPU, 0, 2), + MUX(CLK_MOUT_CMU_BUS0_BUS, "mout_cmu_bus0_bus", + mout_cmu_bus0_bus_p, CLK_CON_MUX_MUX_CLKCMU_BUS0_BUS, 0, 2), + MUX(CLK_MOUT_CMU_BUS1_BUS, "mout_cmu_bus1_bus", + mout_cmu_bus1_bus_p, CLK_CON_MUX_MUX_CLKCMU_BUS1_BUS, 0, 2), + MUX(CLK_MOUT_CMU_BUS1_SSS, "mout_cmu_bus1_sss", + mout_cmu_bus1_sss_p, CLK_CON_MUX_MUX_CLKCMU_BUS1_SSS, 0, 2), + MUX(CLK_MOUT_CMU_CIS_CLK0, "mout_cmu_cis_clk0", + mout_cmu_cis_clk0_p, CLK_CON_MUX_MUX_CLKCMU_CIS_CLK0, 0, 1), + MUX(CLK_MOUT_CMU_CIS_CLK1, "mout_cmu_cis_clk1", + mout_cmu_cis_clk1_p, CLK_CON_MUX_MUX_CLKCMU_CIS_CLK1, 0, 1), + MUX(CLK_MOUT_CMU_CIS_CLK2, "mout_cmu_cis_clk2", + mout_cmu_cis_clk2_p, CLK_CON_MUX_MUX_CLKCMU_CIS_CLK2, 0, 1), + MUX(CLK_MOUT_CMU_CIS_CLK3, "mout_cmu_cis_clk3", + mout_cmu_cis_clk3_p, CLK_CON_MUX_MUX_CLKCMU_CIS_CLK3, 0, 1), + MUX(CLK_MOUT_CMU_CIS_CLK4, "mout_cmu_cis_clk4", + mout_cmu_cis_clk4_p, CLK_CON_MUX_MUX_CLKCMU_CIS_CLK4, 0, 1), + MUX(CLK_MOUT_CMU_CIS_CLK5, "mout_cmu_cis_clk5", + mout_cmu_cis_clk5_p, CLK_CON_MUX_MUX_CLKCMU_CIS_CLK5, 0, 1), + MUX(CLK_MOUT_CMU_CMU_BOOST, "mout_cmu_cmu_boost", + mout_cmu_cmu_boost_p, CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST, 0, 2), + MUX(CLK_MOUT_CMU_CORE_BUS, "mout_cmu_core_bus", + mout_cmu_core_bus_p, CLK_CON_MUX_MUX_CLKCMU_CORE_BUS, 0, 3), + MUX(CLK_MOUT_CMU_CPUCL0_DBG_BUS, "mout_cmu_cpucl0_dbg_bus", + mout_cmu_cpucl0_dbg_bus_p, CLK_CON_MUX_MUX_CLKCMU_CPUCL0_DBG_BUS, + 0, 2), + MUX(CLK_MOUT_CMU_CPUCL0_SWITCH, "mout_cmu_cpucl0_switch", + mout_cmu_cpucl0_switch_p, CLK_CON_MUX_MUX_CLKCMU_CPUCL0_SWITCH, + 0, 2), + MUX(CLK_MOUT_CMU_CPUCL1_SWITCH, "mout_cmu_cpucl1_switch", + mout_cmu_cpucl1_switch_p, CLK_CON_MUX_MUX_CLKCMU_CPUCL1_SWITCH, + 0, 2), + MUX(CLK_MOUT_CMU_CPUCL2_BUSP, "mout_cmu_cpucl2_busp", + mout_cmu_cpucl2_busp_p, CLK_CON_MUX_MUX_CLKCMU_CPUCL2_BUSP, + 0, 1), + MUX(CLK_MOUT_CMU_CPUCL2_SWITCH, "mout_cmu_cpucl2_switch", + mout_cmu_cpucl2_switch_p, CLK_CON_MUX_MUX_CLKCMU_CPUCL2_SWITCH, + 0, 2), + MUX(CLK_MOUT_CMU_CSIS_BUS, "mout_cmu_csis_bus", + mout_cmu_csis_bus_p, CLK_CON_MUX_MUX_CLKCMU_CSIS_BUS, 0, 2), + MUX(CLK_MOUT_CMU_CSIS_OIS_MCU, "mout_cmu_csis_ois_mcu", + mout_cmu_csis_ois_mcu_p, CLK_CON_MUX_MUX_CLKCMU_CSIS_OIS_MCU, + 0, 1), + MUX(CLK_MOUT_CMU_DNC_BUS, "mout_cmu_dnc_bus", + mout_cmu_dnc_bus_p, CLK_CON_MUX_MUX_CLKCMU_DNC_BUS, 0, 2), + MUX(CLK_MOUT_CMU_DNC_BUSM, "mout_cmu_dnc_busm", + mout_cmu_dnc_busm_p, CLK_CON_MUX_MUX_CLKCMU_DNC_BUSM, 0, 2), + MUX(CLK_MOUT_CMU_DNS_BUS, "mout_cmu_dns_bus", + mout_cmu_dns_bus_p, CLK_CON_MUX_MUX_CLKCMU_DNS_BUS, 0, 3), + MUX(CLK_MOUT_CMU_DPU, "mout_cmu_dpu", + mout_cmu_dpu_p, CLK_CON_MUX_MUX_CLKCMU_DPU, 0, 1), + MUX(CLK_MOUT_CMU_DPU_ALT, "mout_cmu_dpu_alt", + mout_cmu_dpu_alt_p, CLK_CON_MUX_MUX_CLKCMU_DPU_ALT, 0, 2), + MUX(CLK_MOUT_CMU_DSP_BUS, "mout_cmu_dsp_bus", + mout_cmu_dsp_bus_p, CLK_CON_MUX_MUX_CLKCMU_DSP_BUS, 0, 2), + MUX(CLK_MOUT_CMU_G2D_G2D, "mout_cmu_g2d_g2d", + mout_cmu_g2d_g2d_p, CLK_CON_MUX_MUX_CLKCMU_G2D_G2D, 0, 2), + MUX(CLK_MOUT_CMU_G2D_MSCL, "mout_cmu_g2d_mscl", + mout_cmu_g2d_mscl_p, CLK_CON_MUX_MUX_CLKCMU_G2D_MSCL, 0, 1), + MUX(CLK_MOUT_CMU_HPM, "mout_cmu_hpm", + mout_cmu_hpm_p, CLK_CON_MUX_MUX_CLKCMU_HPM, 0, 2), + MUX(CLK_MOUT_CMU_HSI0_BUS, "mout_cmu_hsi0_bus", + mout_cmu_hsi0_bus_p, CLK_CON_MUX_MUX_CLKCMU_HSI0_BUS, 0, 1), + MUX(CLK_MOUT_CMU_HSI0_DPGTC, "mout_cmu_hsi0_dpgtc", + mout_cmu_hsi0_dpgtc_p, CLK_CON_MUX_MUX_CLKCMU_HSI0_DPGTC, 0, 2), + MUX(CLK_MOUT_CMU_HSI0_USB31DRD, "mout_cmu_hsi0_usb31drd", + mout_cmu_hsi0_usb31drd_p, CLK_CON_MUX_MUX_CLKCMU_HSI0_USB31DRD, + 0, 2), + MUX(CLK_MOUT_CMU_HSI0_USBDP_DEBUG, "mout_cmu_hsi0_usbdp_debug", + mout_cmu_hsi0_usbdp_debug_p, + CLK_CON_MUX_MUX_CLKCMU_HSI0_USBDP_DEBUG, 0, 2), + MUX(CLK_MOUT_CMU_HSI1_BUS, "mout_cmu_hsi1_bus", + mout_cmu_hsi1_bus_p, CLK_CON_MUX_MUX_CLKCMU_HSI1_BUS, 0, 3), + MUX(CLK_MOUT_CMU_HSI1_MMC_CARD, "mout_cmu_hsi1_mmc_card", + mout_cmu_hsi1_mmc_card_p, CLK_CON_MUX_MUX_CLKCMU_HSI1_MMC_CARD, + 0, 2), + MUX(CLK_MOUT_CMU_HSI1_PCIE, "mout_cmu_hsi1_pcie", + mout_cmu_hsi1_pcie_p, CLK_CON_MUX_MUX_CLKCMU_HSI1_PCIE, 0, 1), + MUX(CLK_MOUT_CMU_HSI1_UFS_CARD, "mout_cmu_hsi1_ufs_card", + mout_cmu_hsi1_ufs_card_p, CLK_CON_MUX_MUX_CLKCMU_HSI1_UFS_CARD, + 0, 2), + MUX(CLK_MOUT_CMU_HSI1_UFS_EMBD, "mout_cmu_hsi1_ufs_embd", + mout_cmu_hsi1_ufs_embd_p, CLK_CON_MUX_MUX_CLKCMU_HSI1_UFS_EMBD, + 0, 1), + MUX(CLK_MOUT_CMU_HSI2_BUS, "mout_cmu_hsi2_bus", + mout_cmu_hsi2_bus_p, CLK_CON_MUX_MUX_CLKCMU_HSI2_BUS, 0, 1), + MUX(CLK_MOUT_CMU_HSI2_PCIE, "mout_cmu_hsi2_pcie", + mout_cmu_hsi2_pcie_p, CLK_CON_MUX_MUX_CLKCMU_HSI2_PCIE, 0, 1), + MUX(CLK_MOUT_CMU_IPP_BUS, "mout_cmu_ipp_bus", + mout_cmu_ipp_bus_p, CLK_CON_MUX_MUX_CLKCMU_IPP_BUS, 0, 3), + MUX(CLK_MOUT_CMU_ITP_BUS, "mout_cmu_itp_bus", + mout_cmu_itp_bus_p, CLK_CON_MUX_MUX_CLKCMU_ITP_BUS, 0, 3), + MUX(CLK_MOUT_CMU_MCSC_BUS, "mout_cmu_mcsc_bus", + mout_cmu_mcsc_bus_p, CLK_CON_MUX_MUX_CLKCMU_MCSC_BUS, 0, 3), + MUX(CLK_MOUT_CMU_MCSC_GDC, "mout_cmu_mcsc_gdc", + mout_cmu_mcsc_gdc_p, CLK_CON_MUX_MUX_CLKCMU_MCSC_GDC, 0, 3), + MUX(CLK_MOUT_CMU_CMU_BOOST_CPU, "mout_cmu_cmu_boost_cpu", + mout_cmu_cmu_boost_cpu_p, CLK_CON_MUX_MUX_CLKCMU_CMU_BOOST_CPU, + 0, 2), + MUX(CLK_MOUT_CMU_MFC0_MFC0, "mout_cmu_mfc0_mfc0", + mout_cmu_mfc0_mfc0_p, CLK_CON_MUX_MUX_CLKCMU_MFC0_MFC0, 0, 2), + MUX(CLK_MOUT_CMU_MFC0_WFD, "mout_cmu_mfc0_wfd", + mout_cmu_mfc0_wfd_p, CLK_CON_MUX_MUX_CLKCMU_MFC0_WFD, 0, 2), + MUX(CLK_MOUT_CMU_MIF_BUSP, "mout_cmu_mif_busp", + mout_cmu_mif_busp_p, CLK_CON_MUX_MUX_CLKCMU_MIF_BUSP, 0, 2), + MUX(CLK_MOUT_CMU_MIF_SWITCH, "mout_cmu_mif_switch", + mout_cmu_mif_switch_p, CLK_CON_MUX_MUX_CLKCMU_MIF_SWITCH, 0, 3), + MUX(CLK_MOUT_CMU_NPU_BUS, "mout_cmu_npu_bus", + mout_cmu_npu_bus_p, CLK_CON_MUX_MUX_CLKCMU_NPU_BUS, 0, 3), + MUX(CLK_MOUT_CMU_PERIC0_BUS, "mout_cmu_peric0_bus", + mout_cmu_peric0_bus_p, CLK_CON_MUX_MUX_CLKCMU_PERIC0_BUS, 0, 1), + MUX(CLK_MOUT_CMU_PERIC0_IP, "mout_cmu_peric0_ip", + mout_cmu_peric0_ip_p, CLK_CON_MUX_MUX_CLKCMU_PERIC0_IP, 0, 1), + MUX(CLK_MOUT_CMU_PERIC1_BUS, "mout_cmu_peric1_bus", + mout_cmu_peric1_bus_p, CLK_CON_MUX_MUX_CLKCMU_PERIC1_BUS, 0, 1), + MUX(CLK_MOUT_CMU_PERIC1_IP, "mout_cmu_peric1_ip", + mout_cmu_peric1_ip_p, CLK_CON_MUX_MUX_CLKCMU_PERIC1_IP, 0, 1), + MUX(CLK_MOUT_CMU_PERIS_BUS, "mout_cmu_peris_bus", + mout_cmu_peris_bus_p, CLK_CON_MUX_MUX_CLKCMU_PERIS_BUS, 0, 1), + MUX(CLK_MOUT_CMU_SSP_BUS, "mout_cmu_ssp_bus", + mout_cmu_ssp_bus_p, CLK_CON_MUX_MUX_CLKCMU_SSP_BUS, 0, 2), + MUX(CLK_MOUT_CMU_TNR_BUS, "mout_cmu_tnr_bus", + mout_cmu_tnr_bus_p, CLK_CON_MUX_MUX_CLKCMU_TNR_BUS, 0, 3), + MUX(CLK_MOUT_CMU_VRA_BUS, "mout_cmu_vra_bus", + mout_cmu_vra_bus_p, CLK_CON_MUX_MUX_CLKCMU_VRA_BUS, 0, 2), +}; + +static const struct samsung_div_clock top_div_clks[] __initconst = { + /* SHARED0 region*/ + DIV(CLK_DOUT_CMU_SHARED0_DIV2, "dout_cmu_shared0_div2", "mout_pll_shared0", + CLK_CON_DIV_PLL_SHARED0_DIV2, 0, 1), + DIV(CLK_DOUT_CMU_SHARED0_DIV3, "dout_cmu_shared0_div3", "mout_pll_shared0", + CLK_CON_DIV_PLL_SHARED0_DIV3, 0, 2), + DIV(CLK_DOUT_CMU_SHARED0_DIV4, "dout_cmu_shared0_div4", "dout_cmu_shared0_div2", + CLK_CON_DIV_PLL_SHARED0_DIV4, 0, 1), + + /* SHARED1 region*/ + DIV(CLK_DOUT_CMU_SHARED1_DIV2, "dout_cmu_shared1_div2", "mout_pll_shared1", + CLK_CON_DIV_PLL_SHARED1_DIV2, 0, 1), + DIV(CLK_DOUT_CMU_SHARED1_DIV3, "dout_cmu_shared1_div3", "mout_pll_shared1", + CLK_CON_DIV_PLL_SHARED1_DIV3, 0, 2), + DIV(CLK_DOUT_CMU_SHARED1_DIV4, "dout_cmu_shared1_div4", "dout_cmu_shared1_div2", + CLK_CON_DIV_PLL_SHARED1_DIV4, 0, 1), + + /* SHARED2 region */ + DIV(CLK_DOUT_CMU_SHARED2_DIV2, "dout_cmu_shared2_div2", "mout_pll_shared2", + CLK_CON_DIV_PLL_SHARED2_DIV2, 0, 1), + + /* SHARED4 region*/ + DIV(CLK_DOUT_CMU_SHARED4_DIV2, "dout_cmu_shared4_div2", "mout_pll_shared4", + CLK_CON_DIV_PLL_SHARED4_DIV2, 0, 1), + DIV(CLK_DOUT_CMU_SHARED4_DIV3, "dout_cmu_shared4_div3", "mout_pll_shared4", + CLK_CON_DIV_PLL_SHARED4_DIV3, 0, 2), + DIV(CLK_DOUT_CMU_SHARED4_DIV4, "dout_cmu_shared4_div4", "mout_pll_shared4", + CLK_CON_DIV_PLL_SHARED4_DIV4, 0, 1), + + DIV(CLK_DOUT_CMU_APM_BUS, "dout_cmu_apm_bus", "gout_cmu_apm_bus", + CLK_CON_DIV_CLKCMU_APM_BUS, 0, 3), + DIV(CLK_DOUT_CMU_AUD_CPU, "dout_cmu_aud_cpu", "gout_cmu_aud_cpu", + CLK_CON_DIV_CLKCMU_AUD_CPU, 0, 3), + DIV(CLK_DOUT_CMU_BUS0_BUS, "dout_cmu_bus0_bus", "gout_cmu_bus0_bus", + CLK_CON_DIV_CLKCMU_BUS0_BUS, 0, 4), + DIV(CLK_DOUT_CMU_BUS1_BUS, "dout_cmu_bus1_bus", "gout_cmu_bus1_bus", + CLK_CON_DIV_CLKCMU_BUS1_BUS, 0, 4), + DIV(CLK_DOUT_CMU_BUS1_SSS, "dout_cmu_bus1_sss", "gout_cmu_bus1_sss", + CLK_CON_DIV_CLKCMU_BUS1_SSS, 0, 4), + DIV(CLK_DOUT_CMU_CIS_CLK0, "dout_cmu_cis_clk0", "gout_cmu_cis_clk0", + CLK_CON_DIV_CLKCMU_CIS_CLK0, 0, 5), + DIV(CLK_DOUT_CMU_CIS_CLK1, "dout_cmu_cis_clk1", "gout_cmu_cis_clk1", + CLK_CON_DIV_CLKCMU_CIS_CLK1, 0, 5), + DIV(CLK_DOUT_CMU_CIS_CLK2, "dout_cmu_cis_clk2", "gout_cmu_cis_clk2", + CLK_CON_DIV_CLKCMU_CIS_CLK2, 0, 5), + DIV(CLK_DOUT_CMU_CIS_CLK3, "dout_cmu_cis_clk3", "gout_cmu_cis_clk3", + CLK_CON_DIV_CLKCMU_CIS_CLK3, 0, 5), + DIV(CLK_DOUT_CMU_CIS_CLK4, "dout_cmu_cis_clk4", "gout_cmu_cis_clk4", + CLK_CON_DIV_CLKCMU_CIS_CLK4, 0, 5), + DIV(CLK_DOUT_CMU_CIS_CLK5, "dout_cmu_cis_clk5", "gout_cmu_cis_clk5", + CLK_CON_DIV_CLKCMU_CIS_CLK5, 0, 5), + DIV(CLK_DOUT_CMU_CMU_BOOST, "dout_cmu_cmu_boost", "mout_cmu_cmu_boost", + CLK_CON_DIV_CLKCMU_CMU_BOOST, 0, 2), + DIV(CLK_DOUT_CMU_CORE_BUS, "dout_cmu_core_bus", "gout_cmu_core_bus", + CLK_CON_DIV_CLKCMU_CORE_BUS, 0, 4), + DIV(CLK_DOUT_CMU_CPUCL0_DBG_BUS, "dout_cmu_cpucl0_debug", + "gout_cmu_cpucl0_dbg_bus", CLK_CON_DIV_CLKCMU_CPUCL0_DBG_BUS, + 0, 3), + DIV(CLK_DOUT_CMU_CPUCL0_SWITCH, "dout_cmu_cpucl0_switch", + "gout_cmu_cpucl0_switch", CLK_CON_DIV_CLKCMU_CPUCL0_SWITCH, 0, 3), + DIV(CLK_DOUT_CMU_CPUCL1_SWITCH, "dout_cmu_cpucl1_switch", + "gout_cmu_cpucl1_switch", CLK_CON_DIV_CLKCMU_CPUCL1_SWITCH, 0, 3), + DIV(CLK_DOUT_CMU_CPUCL2_BUSP, "dout_cmu_cpucl2_busp", + "gout_cmu_cpucl2_busp", CLK_CON_DIV_CLKCMU_CPUCL2_BUSP, 0, 4), + DIV(CLK_DOUT_CMU_CPUCL2_SWITCH, "dout_cmu_cpucl2_switch", + "gout_cmu_cpucl2_switch", CLK_CON_DIV_CLKCMU_CPUCL2_SWITCH, 0, 3), + DIV(CLK_DOUT_CMU_CSIS_BUS, "dout_cmu_csis_bus", "gout_cmu_csis_bus", + CLK_CON_DIV_CLKCMU_CSIS_BUS, 0, 4), + DIV(CLK_DOUT_CMU_CSIS_OIS_MCU, "dout_cmu_csis_ois_mcu", + "gout_cmu_csis_ois_mcu", CLK_CON_DIV_CLKCMU_CSIS_OIS_MCU, 0, 4), + DIV(CLK_DOUT_CMU_DNC_BUS, "dout_cmu_dnc_bus", "gout_cmu_dnc_bus", + CLK_CON_DIV_CLKCMU_DNC_BUS, 0, 4), + DIV(CLK_DOUT_CMU_DNC_BUSM, "dout_cmu_dnc_busm", "gout_cmu_dnc_busm", + CLK_CON_DIV_CLKCMU_DNC_BUSM, 0, 4), + DIV(CLK_DOUT_CMU_DNS_BUS, "dout_cmu_dns_bus", "gout_cmu_dns_bus", + CLK_CON_DIV_CLKCMU_DNS_BUS, 0, 4), + DIV(CLK_DOUT_CMU_DSP_BUS, "dout_cmu_dsp_bus", "gout_cmu_dsp_bus", + CLK_CON_DIV_CLKCMU_DSP_BUS, 0, 4), + DIV(CLK_DOUT_CMU_G2D_G2D, "dout_cmu_g2d_g2d", "gout_cmu_g2d_g2d", + CLK_CON_DIV_CLKCMU_G2D_G2D, 0, 4), + DIV(CLK_DOUT_CMU_G2D_MSCL, "dout_cmu_g2d_mscl", "gout_cmu_g2d_mscl", + CLK_CON_DIV_CLKCMU_G2D_MSCL, 0, 4), + DIV(CLK_DOUT_CMU_G3D_SWITCH, "dout_cmu_g3d_switch", + "gout_cmu_g3d_switch", CLK_CON_DIV_CLKCMU_G3D_SWITCH, 0, 3), + DIV(CLK_DOUT_CMU_HPM, "dout_cmu_hpm", "gout_cmu_hpm", + CLK_CON_DIV_CLKCMU_HPM, 0, 2), + DIV(CLK_DOUT_CMU_HSI0_BUS, "dout_cmu_hsi0_bus", "gout_cmu_hsi0_bus", + CLK_CON_DIV_CLKCMU_HSI0_BUS, 0, 4), + DIV(CLK_DOUT_CMU_HSI0_DPGTC, "dout_cmu_hsi0_dpgtc", "gout_cmu_hsi0_dpgtc", + CLK_CON_DIV_CLKCMU_HSI0_DPGTC, 0, 3), + DIV(CLK_DOUT_CMU_HSI0_USB31DRD, "dout_cmu_hsi0_usb31drd", + "gout_cmu_hsi0_usb31drd", CLK_CON_DIV_CLKCMU_HSI0_USB31DRD, 0, 4), + DIV(CLK_DOUT_CMU_HSI0_USBDP_DEBUG, "dout_cmu_hsi0_usbdp_debug", + "gout_cmu_hsi0_usbdp_debug", CLK_CON_DIV_CLKCMU_HSI0_USBDP_DEBUG, + 0, 4), + DIV(CLK_DOUT_CMU_HSI1_BUS, "dout_cmu_hsi1_bus", "gout_cmu_hsi1_bus", + CLK_CON_DIV_CLKCMU_HSI1_BUS, 0, 3), + DIV(CLK_DOUT_CMU_HSI1_MMC_CARD, "dout_cmu_hsi1_mmc_card", + "gout_cmu_hsi1_mmc_card", CLK_CON_DIV_CLKCMU_HSI1_MMC_CARD, + 0, 9), + DIV(CLK_DOUT_CMU_HSI1_PCIE, "dout_cmu_hsi1_pcie", "gout_cmu_hsi1_pcie", + CLK_CON_DIV_CLKCMU_HSI1_PCIE, 0, 7), + DIV(CLK_DOUT_CMU_HSI1_UFS_CARD, "dout_cmu_hsi1_ufs_card", + "gout_cmu_hsi1_ufs_card", CLK_CON_DIV_CLKCMU_HSI1_UFS_CARD, + 0, 3), + DIV(CLK_DOUT_CMU_HSI1_UFS_EMBD, "dout_cmu_hsi1_ufs_embd", + "gout_cmu_hsi1_ufs_embd", CLK_CON_DIV_CLKCMU_HSI1_UFS_EMBD, + 0, 3), + DIV(CLK_DOUT_CMU_HSI2_BUS, "dout_cmu_hsi2_bus", "gout_cmu_hsi2_bus", + CLK_CON_DIV_CLKCMU_HSI2_BUS, 0, 4), + DIV(CLK_DOUT_CMU_HSI2_PCIE, "dout_cmu_hsi2_pcie", "gout_cmu_hsi2_pcie", + CLK_CON_DIV_CLKCMU_HSI2_PCIE, 0, 7), + DIV(CLK_DOUT_CMU_IPP_BUS, "dout_cmu_ipp_bus", "gout_cmu_ipp_bus", + CLK_CON_DIV_CLKCMU_IPP_BUS, 0, 4), + DIV(CLK_DOUT_CMU_ITP_BUS, "dout_cmu_itp_bus", "gout_cmu_itp_bus", + CLK_CON_DIV_CLKCMU_ITP_BUS, 0, 4), + DIV(CLK_DOUT_CMU_MCSC_BUS, "dout_cmu_mcsc_bus", "gout_cmu_mcsc_bus", + CLK_CON_DIV_CLKCMU_MCSC_BUS, 0, 4), + DIV(CLK_DOUT_CMU_MCSC_GDC, "dout_cmu_mcsc_gdc", "gout_cmu_mcsc_gdc", + CLK_CON_DIV_CLKCMU_MCSC_GDC, 0, 4), + DIV(CLK_DOUT_CMU_CMU_BOOST_CPU, "dout_cmu_cmu_boost_cpu", + "mout_cmu_cmu_boost_cpu", CLK_CON_DIV_CLKCMU_CMU_BOOST_CPU, + 0, 2), + DIV(CLK_DOUT_CMU_MFC0_MFC0, "dout_cmu_mfc0_mfc0", "gout_cmu_mfc0_mfc0", + CLK_CON_DIV_CLKCMU_MFC0_MFC0, 0, 4), + DIV(CLK_DOUT_CMU_MFC0_WFD, "dout_cmu_mfc0_wfd", "gout_cmu_mfc0_wfd", + CLK_CON_DIV_CLKCMU_MFC0_WFD, 0, 4), + DIV(CLK_DOUT_CMU_MIF_BUSP, "dout_cmu_mif_busp", "gout_cmu_mif_busp", + CLK_CON_DIV_CLKCMU_MIF_BUSP, 0, 4), + DIV(CLK_DOUT_CMU_NPU_BUS, "dout_cmu_npu_bus", "gout_cmu_npu_bus", + CLK_CON_DIV_CLKCMU_NPU_BUS, 0, 4), + DIV(CLK_DOUT_CMU_PERIC0_BUS, "dout_cmu_peric0_bus", "gout_cmu_peric0_bus", + CLK_CON_DIV_CLKCMU_PERIC0_BUS, 0, 4), + DIV(CLK_DOUT_CMU_PERIC0_IP, "dout_cmu_peric0_ip", "gout_cmu_peric0_ip", + CLK_CON_DIV_CLKCMU_PERIC0_IP, 0, 4), + DIV(CLK_DOUT_CMU_PERIC1_BUS, "dout_cmu_peric1_bus", "gout_cmu_peric1_bus", + CLK_CON_DIV_CLKCMU_PERIC1_BUS, 0, 4), + DIV(CLK_DOUT_CMU_PERIC1_IP, "dout_cmu_peric1_ip", "gout_cmu_peric1_ip", + CLK_CON_DIV_CLKCMU_PERIC1_IP, 0, 4), + DIV(CLK_DOUT_CMU_PERIS_BUS, "dout_cmu_peris_bus", "gout_cmu_peris_bus", + CLK_CON_DIV_CLKCMU_PERIS_BUS, 0, 4), + DIV(CLK_DOUT_CMU_SSP_BUS, "dout_cmu_ssp_bus", "gout_cmu_ssp_bus", + CLK_CON_DIV_CLKCMU_SSP_BUS, 0, 4), + DIV(CLK_DOUT_CMU_TNR_BUS, "dout_cmu_tnr_bus", "gout_cmu_tnr_bus", + CLK_CON_DIV_CLKCMU_TNR_BUS, 0, 4), + DIV(CLK_DOUT_CMU_VRA_BUS, "dout_cmu_vra_bus", "gout_cmu_vra_bus", + CLK_CON_DIV_CLKCMU_VRA_BUS, 0, 4), + DIV(CLK_DOUT_CMU_DPU, "dout_cmu_clkcmu_dpu", "gout_cmu_dpu", + CLK_CON_DIV_DIV_CLKCMU_DPU, 0, 4), +}; + +static const struct samsung_gate_clock top_gate_clks[] __initconst = { + GATE(CLK_GOUT_CMU_APM_BUS, "gout_cmu_apm_bus", "mout_cmu_apm_bus", + CLK_CON_GAT_GATE_CLKCMU_APM_BUS, 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_AUD_CPU, "gout_cmu_aud_cpu", "mout_cmu_aud_cpu", + CLK_CON_GAT_GATE_CLKCMU_AUD_CPU, 21, 0, 0), + GATE(CLK_GOUT_CMU_BUS0_BUS, "gout_cmu_bus0_bus", "mout_cmu_bus0_bus", + CLK_CON_GAT_GATE_CLKCMU_BUS0_BUS, 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_BUS1_BUS, "gout_cmu_bus1_bus", "mout_cmu_bus1_bus", + CLK_CON_GAT_GATE_CLKCMU_BUS1_BUS, 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_BUS1_SSS, "gout_cmu_bus1_sss", "mout_cmu_bus1_sss", + CLK_CON_GAT_GATE_CLKCMU_BUS1_SSS, 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_CIS_CLK0, "gout_cmu_cis_clk0", "mout_cmu_cis_clk0", + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK0, 21, 0, 0), + GATE(CLK_GOUT_CMU_CIS_CLK1, "gout_cmu_cis_clk1", "mout_cmu_cis_clk1", + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK1, 21, 0, 0), + GATE(CLK_GOUT_CMU_CIS_CLK2, "gout_cmu_cis_clk2", "mout_cmu_cis_clk2", + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK2, 21, 0, 0), + GATE(CLK_GOUT_CMU_CIS_CLK3, "gout_cmu_cis_clk3", "mout_cmu_cis_clk3", + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK3, 21, 0, 0), + GATE(CLK_GOUT_CMU_CIS_CLK4, "gout_cmu_cis_clk4", "mout_cmu_cis_clk4", + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK4, 21, 0, 0), + GATE(CLK_GOUT_CMU_CIS_CLK5, "gout_cmu_cis_clk5", "mout_cmu_cis_clk5", + CLK_CON_GAT_GATE_CLKCMU_CIS_CLK5, 21, 0, 0), + GATE(CLK_GOUT_CMU_CORE_BUS, "gout_cmu_core_bus", "mout_cmu_core_bus", + CLK_CON_GAT_GATE_CLKCMU_CORE_BUS, 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_CPUCL0_DBG_BUS, "gout_cmu_cpucl0_dbg_bus", + "mout_cmu_cpucl0_dbg_bus", CLK_CON_GAT_GATE_CLKCMU_CPUCL0_DBG_BUS, + 21, 0, 0), + GATE(CLK_GOUT_CMU_CPUCL0_SWITCH, "gout_cmu_cpucl0_switch", + "mout_cmu_cpucl0_switch", CLK_CON_GAT_GATE_CLKCMU_CPUCL0_SWITCH, + 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_CPUCL1_SWITCH, "gout_cmu_cpucl1_switch", + "mout_cmu_cpucl1_switch", CLK_CON_GAT_GATE_CLKCMU_CPUCL1_SWITCH, + 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_CPUCL2_BUSP, "gout_cmu_cpucl2_busp", + "mout_cmu_cpucl2_busp", CLK_CON_GAT_GATE_CLKCMU_CPUCL2_BUSP, + 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_CPUCL2_SWITCH, "gout_cmu_cpucl2_switch", + "mout_cmu_cpucl2_switch", CLK_CON_GAT_GATE_CLKCMU_CPUCL2_SWITCH, + 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_CSIS_BUS, "gout_cmu_csis_bus", "mout_cmu_csis_bus", + CLK_CON_GAT_GATE_CLKCMU_CSIS_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_CSIS_OIS_MCU, "gout_cmu_csis_ois_mcu", + "mout_cmu_csis_ois_mcu", CLK_CON_GAT_GATE_CLKCMU_CSIS_OIS_MCU, + 21, 0, 0), + GATE(CLK_GOUT_CMU_DNC_BUS, "gout_cmu_dnc_bus", "mout_cmu_dnc_bus", + CLK_CON_GAT_GATE_CLKCMU_DNC_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_DNC_BUSM, "gout_cmu_dnc_busm", "mout_cmu_dnc_busm", + CLK_CON_GAT_GATE_CLKCMU_DNC_BUSM, 21, 0, 0), + GATE(CLK_GOUT_CMU_DNS_BUS, "gout_cmu_dns_bus", "mout_cmu_dns_bus", + CLK_CON_GAT_GATE_CLKCMU_DNS_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_DPU, "gout_cmu_dpu", "mout_cmu_dpu", + CLK_CON_GAT_GATE_CLKCMU_DPU, 21, 0, 0), + GATE(CLK_GOUT_CMU_DPU_BUS, "gout_cmu_dpu_bus", "mout_cmu_dpu_alt", + CLK_CON_GAT_GATE_CLKCMU_DPU_BUS, 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_DSP_BUS, "gout_cmu_dsp_bus", "mout_cmu_dsp_bus", + CLK_CON_GAT_GATE_CLKCMU_DSP_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_G2D_G2D, "gout_cmu_g2d_g2d", "mout_cmu_g2d_g2d", + CLK_CON_GAT_GATE_CLKCMU_G2D_G2D, 21, 0, 0), + GATE(CLK_GOUT_CMU_G2D_MSCL, "gout_cmu_g2d_mscl", "mout_cmu_g2d_mscl", + CLK_CON_GAT_GATE_CLKCMU_G2D_MSCL, 21, 0, 0), + GATE(CLK_GOUT_CMU_G3D_SWITCH, "gout_cmu_g3d_switch", + "fout_shared2_pll", CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH, + 21, 0, 0), + GATE(CLK_GOUT_CMU_HPM, "gout_cmu_hpm", "mout_cmu_hpm", + CLK_CON_GAT_GATE_CLKCMU_HPM, 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI0_BUS, "gout_cmu_hsi0_bus", + "mout_cmu_hsi0_bus", CLK_CON_GAT_GATE_CLKCMU_HSI0_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI0_DPGTC, "gout_cmu_hsi0_dpgtc", + "mout_cmu_hsi0_dpgtc", CLK_CON_GAT_GATE_CLKCMU_HSI0_DPGTC, + 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI0_USB31DRD, "gout_cmu_hsi0_usb31drd", + "mout_cmu_hsi0_usb31drd", CLK_CON_GAT_GATE_CLKCMU_HSI0_USB31DRD, + 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI0_USBDP_DEBUG, "gout_cmu_hsi0_usbdp_debug", + "mout_cmu_hsi0_usbdp_debug", CLK_CON_GAT_GATE_CLKCMU_HSI0_USBDP_DEBUG, + 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI1_BUS, "gout_cmu_hsi1_bus", "mout_cmu_hsi1_bus", + CLK_CON_GAT_GATE_CLKCMU_HSI1_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI1_MMC_CARD, "gout_cmu_hsi1_mmc_card", + "mout_cmu_hsi1_mmc_card", CLK_CON_GAT_GATE_CLKCMU_HSI1_MMC_CARD, + 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI1_PCIE, "gout_cmu_hsi1_pcie", + "mout_cmu_hsi1_pcie", CLK_CON_GAT_GATE_CLKCMU_HSI1_PCIE, + 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI1_UFS_CARD, "gout_cmu_hsi1_ufs_card", + "mout_cmu_hsi1_ufs_card", CLK_CON_GAT_GATE_CLKCMU_HSI1_UFS_CARD, + 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI1_UFS_EMBD, "gout_cmu_hsi1_ufs_embd", + "mout_cmu_hsi1_ufs_embd", CLK_CON_GAT_GATE_CLKCMU_HSI1_UFS_EMBD, + 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI2_BUS, "gout_cmu_hsi2_bus", "mout_cmu_hsi2_bus", + CLK_CON_GAT_GATE_CLKCMU_HSI2_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_HSI2_PCIE, "gout_cmu_hsi2_pcie", + "mout_cmu_hsi2_pcie", CLK_CON_GAT_GATE_CLKCMU_HSI2_PCIE, + 21, 0, 0), + GATE(CLK_GOUT_CMU_IPP_BUS, "gout_cmu_ipp_bus", "mout_cmu_ipp_bus", + CLK_CON_GAT_GATE_CLKCMU_IPP_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_ITP_BUS, "gout_cmu_itp_bus", "mout_cmu_itp_bus", + CLK_CON_GAT_GATE_CLKCMU_ITP_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_MCSC_BUS, "gout_cmu_mcsc_bus", "mout_cmu_mcsc_bus", + CLK_CON_GAT_GATE_CLKCMU_MCSC_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_MCSC_GDC, "gout_cmu_mcsc_gdc", "mout_cmu_mcsc_gdc", + CLK_CON_GAT_GATE_CLKCMU_MCSC_GDC, 21, 0, 0), + GATE(CLK_GOUT_CMU_MFC0_MFC0, "gout_cmu_mfc0_mfc0", + "mout_cmu_mfc0_mfc0", CLK_CON_GAT_GATE_CLKCMU_MFC0_MFC0, + 21, 0, 0), + GATE(CLK_GOUT_CMU_MFC0_WFD, "gout_cmu_mfc0_wfd", "mout_cmu_mfc0_wfd", + CLK_CON_GAT_GATE_CLKCMU_MFC0_WFD, 21, 0, 0), + GATE(CLK_GOUT_CMU_MIF_BUSP, "gout_cmu_mif_busp", "mout_cmu_mif_busp", + CLK_CON_GAT_GATE_CLKCMU_MIF_BUSP, 21, 0, 0), + GATE(CLK_GOUT_CMU_NPU_BUS, "gout_cmu_npu_bus", "mout_cmu_npu_bus", + CLK_CON_GAT_GATE_CLKCMU_NPU_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_PERIC0_BUS, "gout_cmu_peric0_bus", + "mout_cmu_peric0_bus", CLK_CON_GAT_GATE_CLKCMU_PERIC0_BUS, + 21, 0, 0), + GATE(CLK_GOUT_CMU_PERIC0_IP, "gout_cmu_peric0_ip", + "mout_cmu_peric0_ip", CLK_CON_GAT_GATE_CLKCMU_PERIC0_IP, + 21, 0, 0), + GATE(CLK_GOUT_CMU_PERIC1_BUS, "gout_cmu_peric1_bus", + "mout_cmu_peric1_bus", CLK_CON_GAT_GATE_CLKCMU_PERIC1_BUS, + 21, 0, 0), + GATE(CLK_GOUT_CMU_PERIC1_IP, "gout_cmu_peric1_ip", + "mout_cmu_peric1_ip", CLK_CON_GAT_GATE_CLKCMU_PERIC1_IP, + 21, 0, 0), + GATE(CLK_GOUT_CMU_PERIS_BUS, "gout_cmu_peris_bus", + "mout_cmu_peris_bus", CLK_CON_GAT_GATE_CLKCMU_PERIS_BUS, + 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_CMU_SSP_BUS, "gout_cmu_ssp_bus", "mout_cmu_ssp_bus", + CLK_CON_GAT_GATE_CLKCMU_SSP_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_TNR_BUS, "gout_cmu_tnr_bus", "mout_cmu_tnr_bus", + CLK_CON_GAT_GATE_CLKCMU_TNR_BUS, 21, 0, 0), + GATE(CLK_GOUT_CMU_VRA_BUS, "gout_cmu_vra_bus", "mout_cmu_vra_bus", + CLK_CON_GAT_GATE_CLKCMU_VRA_BUS, 21, 0, 0), +}; + +static const struct samsung_cmu_info top_cmu_info __initconst = { + .pll_clks = top_pll_clks, + .nr_pll_clks = ARRAY_SIZE(top_pll_clks), + .mux_clks = top_mux_clks, + .nr_mux_clks = ARRAY_SIZE(top_mux_clks), + .div_clks = top_div_clks, + .nr_div_clks = ARRAY_SIZE(top_div_clks), + .gate_clks = top_gate_clks, + .nr_gate_clks = ARRAY_SIZE(top_gate_clks), + .nr_clk_ids = CLKS_NR_TOP, + .clk_regs = top_clk_regs, + .nr_clk_regs = ARRAY_SIZE(top_clk_regs), +}; + +static void __init exynos990_cmu_top_init(struct device_node *np) +{ + exynos_arm64_register_cmu(NULL, np, &top_cmu_info); +} + +/* Register CMU_TOP early, as it's a dependency for other early domains */ +CLK_OF_DECLARE(exynos990_cmu_top, "samsung,exynos990-cmu-top", + exynos990_cmu_top_init); + +/* ---- CMU_HSI0 ------------------------------------------------------------ */ + +/* Register Offset definitions for CMU_HSI0 (0x10a00000) */ +#define PLL_CON0_MUX_CLKCMU_HSI0_BUS_USER 0x0600 +#define PLL_CON0_MUX_CLKCMU_HSI0_USB31DRD_USER 0x0620 +#define PLL_CON0_MUX_CLKCMU_HSI0_USBDP_DEBUG_USER 0x0630 +#define PLL_CON0_MUX_CLKCMU_HSI0_DPGTC_USER 0x0610 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_DP_LINK_IPCLKPORT_I_DP_GTC_CLK 0x2004 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_PPMU_HSI0_BUS1_IPCLKPORT_ACLK 0x2018 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_LHS_ACEL_D_HSI0_IPCLKPORT_I_CLK 0x2014 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_RSTNSYNC_CLK_HSI0_BUS_IPCLKPORT_CLK 0x2020 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_VGEN_LITE_HSI0_IPCLKPORT_CLK 0x2044 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_DP_LINK_IPCLKPORT_I_PCLK 0x2008 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_D_TZPC_HSI0_IPCLKPORT_PCLK 0x200c +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_LHM_AXI_P_HSI0_IPCLKPORT_I_CLK 0x2010 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_PPMU_HSI0_BUS1_IPCLKPORT_PCLK 0x201c +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_SYSMMU_USB_IPCLKPORT_CLK_S2 0x2024 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_SYSREG_HSI0_IPCLKPORT_PCLK 0x2028 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_ACLK_PHYCTRL 0x202c +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USB31DRD_REF_CLK_40 0x2034 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USBDPPHY_SCL_APB_PCLK 0x203c +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USBPCS_APB_CLK 0x2040 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_BUS_CLK_EARLY 0x2030 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_HSI0_CMU_HSI0_IPCLKPORT_PCLK 0x2000 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_XIU_D_HSI0_IPCLKPORT_ACLK 0x2048 +#define CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USBDPPHY_REF_SOC_PLL 0x2038 + +static const unsigned long hsi0_clk_regs[] __initconst = { + PLL_CON0_MUX_CLKCMU_HSI0_BUS_USER, + PLL_CON0_MUX_CLKCMU_HSI0_USB31DRD_USER, + PLL_CON0_MUX_CLKCMU_HSI0_USBDP_DEBUG_USER, + PLL_CON0_MUX_CLKCMU_HSI0_DPGTC_USER, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_DP_LINK_IPCLKPORT_I_DP_GTC_CLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_DP_LINK_IPCLKPORT_I_PCLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_PPMU_HSI0_BUS1_IPCLKPORT_ACLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_LHS_ACEL_D_HSI0_IPCLKPORT_I_CLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_RSTNSYNC_CLK_HSI0_BUS_IPCLKPORT_CLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_VGEN_LITE_HSI0_IPCLKPORT_CLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_D_TZPC_HSI0_IPCLKPORT_PCLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_LHM_AXI_P_HSI0_IPCLKPORT_I_CLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_PPMU_HSI0_BUS1_IPCLKPORT_PCLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_SYSMMU_USB_IPCLKPORT_CLK_S2, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_SYSREG_HSI0_IPCLKPORT_PCLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_ACLK_PHYCTRL, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USBDPPHY_SCL_APB_PCLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USBPCS_APB_CLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_BUS_CLK_EARLY, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_HSI0_CMU_HSI0_IPCLKPORT_PCLK, + CLK_CON_GAT_GOUT_BLK_HSI0_UID_XIU_D_HSI0_IPCLKPORT_ACLK, +}; + +PNAME(mout_hsi0_bus_user_p) = { "oscclk", "dout_cmu_hsi0_bus" }; +PNAME(mout_hsi0_usb31drd_user_p) = { "oscclk", "dout_cmu_hsi0_usb31drd" }; +PNAME(mout_hsi0_usbdp_debug_user_p) = { "oscclk", + "dout_cmu_hsi0_usbdp_debug" }; +PNAME(mout_hsi0_dpgtc_user_p) = { "oscclk", "dout_cmu_hsi0_dpgtc" }; + +static const struct samsung_mux_clock hsi0_mux_clks[] __initconst = { + MUX(CLK_MOUT_HSI0_BUS_USER, "mout_hsi0_bus_user", + mout_hsi0_bus_user_p, PLL_CON0_MUX_CLKCMU_HSI0_BUS_USER, + 4, 1), + MUX(CLK_MOUT_HSI0_USB31DRD_USER, "mout_hsi0_usb31drd_user", + mout_hsi0_usb31drd_user_p, PLL_CON0_MUX_CLKCMU_HSI0_USB31DRD_USER, + 4, 1), + MUX(CLK_MOUT_HSI0_USBDP_DEBUG_USER, "mout_hsi0_usbdp_debug_user", + mout_hsi0_usbdp_debug_user_p, + PLL_CON0_MUX_CLKCMU_HSI0_USBDP_DEBUG_USER, + 4, 1), + MUX(CLK_MOUT_HSI0_DPGTC_USER, "mout_hsi0_dpgtc_user", + mout_hsi0_dpgtc_user_p, PLL_CON0_MUX_CLKCMU_HSI0_DPGTC_USER, + 4, 1), +}; + +static const struct samsung_gate_clock hsi0_gate_clks[] __initconst = { + GATE(CLK_GOUT_HSI0_DP_LINK_DP_GTC_CLK, + "gout_hsi0_dp_link_dp_gtc_clk", "mout_hsi0_dpgtc_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_DP_LINK_IPCLKPORT_I_DP_GTC_CLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_DP_LINK_PCLK, + "gout_hsi0_dp_link_pclk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_DP_LINK_IPCLKPORT_I_PCLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_D_TZPC_HSI0_PCLK, + "gout_hsi0_d_tzpc_hsi0_pclk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_D_TZPC_HSI0_IPCLKPORT_PCLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_LHM_AXI_P_HSI0_CLK, + "gout_hsi0_lhm_axi_p_hsi0_clk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_LHM_AXI_P_HSI0_IPCLKPORT_I_CLK, + 21, CLK_IS_CRITICAL, 0), + GATE(CLK_GOUT_HSI0_PPMU_HSI0_BUS1_ACLK, + "gout_hsi0_ppmu_hsi0_bus1_aclk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_PPMU_HSI0_BUS1_IPCLKPORT_ACLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_PPMU_HSI0_BUS1_PCLK, + "gout_hsi0_ppmu_hsi0_bus1_pclk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_PPMU_HSI0_BUS1_IPCLKPORT_PCLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_CLK_HSI0_BUS_CLK, + "gout_hsi0_clk_hsi0_bus_clk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_RSTNSYNC_CLK_HSI0_BUS_IPCLKPORT_CLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_SYSMMU_USB_CLK_S2, + "gout_hsi0_sysmmu_usb_clk_s2", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_SYSMMU_USB_IPCLKPORT_CLK_S2, + 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_HSI0_SYSREG_HSI0_PCLK, + "gout_hsi0_sysreg_hsi0_pclk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_SYSREG_HSI0_IPCLKPORT_PCLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_USB31DRD_ACLK_PHYCTRL, + "gout_hsi0_usb31drd_aclk_phyctrl", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_ACLK_PHYCTRL, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_USB31DRD_BUS_CLK_EARLY, + "gout_hsi0_usb31drd_bus_clk_early", + "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_BUS_CLK_EARLY, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_USB31DRD_USB31DRD_REF_CLK_40, + "gout_hsi0_usb31drd_usb31drd_ref_clk_40", + "mout_hsi0_usb31drd_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USB31DRD_REF_CLK_40, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_USB31DRD_USBDPPHY_REF_SOC_PLL, + "gout_hsi0_usb31drd_usbdpphy_ref_soc_pll", + "mout_hsi0_usbdp_debug_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USBDPPHY_REF_SOC_PLL, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_USB31DRD_USBDPPHY_SCL_APB, + "gout_hsi0_usb31drd_ipclkport_i_usbdpphy_scl_apb_pclk", + "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USBDPPHY_SCL_APB_PCLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_USB31DRD_USBPCS_APB_CLK, + "gout_hsi0_usb31drd_usbpcs_apb_clk", + "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_USB31DRD_IPCLKPORT_I_USBPCS_APB_CLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_VGEN_LITE_HSI0_CLK, + "gout_hsi0_vgen_lite_ipclkport_clk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_VGEN_LITE_HSI0_IPCLKPORT_CLK, + 21, 0, 0), + GATE(CLK_GOUT_HSI0_CMU_HSI0_PCLK, + "gout_hsi0_cmu_hsi0_pclk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_HSI0_CMU_HSI0_IPCLKPORT_PCLK, + 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_HSI0_XIU_D_HSI0_ACLK, + "gout_hsi0_xiu_d_hsi0_aclk", "mout_hsi0_bus_user", + CLK_CON_GAT_GOUT_BLK_HSI0_UID_XIU_D_HSI0_IPCLKPORT_ACLK, + 21, CLK_IGNORE_UNUSED, 0), +}; + +static const struct samsung_cmu_info hsi0_cmu_info __initconst = { + .mux_clks = hsi0_mux_clks, + .nr_mux_clks = ARRAY_SIZE(hsi0_mux_clks), + .gate_clks = hsi0_gate_clks, + .nr_gate_clks = ARRAY_SIZE(hsi0_gate_clks), + .nr_clk_ids = CLKS_NR_HSI0, + .clk_regs = hsi0_clk_regs, + .nr_clk_regs = ARRAY_SIZE(hsi0_clk_regs), + .clk_name = "bus", +}; + +/* ----- platform_driver ----- */ + +static int __init exynos990_cmu_probe(struct platform_device *pdev) +{ + const struct samsung_cmu_info *info; + struct device *dev = &pdev->dev; + + info = of_device_get_match_data(dev); + exynos_arm64_register_cmu(dev, dev->of_node, info); + + return 0; +} + +static const struct of_device_id exynos990_cmu_of_match[] = { + { + .compatible = "samsung,exynos990-cmu-hsi0", + .data = &hsi0_cmu_info, + }, + { }, +}; + +static struct platform_driver exynos990_cmu_driver __refdata = { + .driver = { + .name = "exynos990-cmu", + .of_match_table = exynos990_cmu_of_match, + .suppress_bind_attrs = true, + }, + .probe = exynos990_cmu_probe, +}; + +static int __init exynos990_cmu_init(void) +{ + return platform_driver_register(&exynos990_cmu_driver); +} + +core_initcall(exynos990_cmu_init); diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c index be6b51694919..2e94bba6c396 100644 --- a/drivers/clk/samsung/clk-pll.c +++ b/drivers/clk/samsung/clk-pll.c @@ -430,7 +430,10 @@ static const struct clk_ops samsung_pll36xx_clk_min_ops = { #define PLL0822X_LOCK_STAT_SHIFT (29) #define PLL0822X_ENABLE_SHIFT (31) -/* PLL1418x is similar to PLL0822x, except that MDIV is one bit smaller */ +/* + * PLL1418x, PLL0717x and PLL0718x are similar + * to PLL0822x, except that MDIV is one bit smaller + */ #define PLL1418X_MDIV_MASK (0x1FF) static unsigned long samsung_pll0822x_recalc_rate(struct clk_hw *hw, @@ -441,10 +444,14 @@ static unsigned long samsung_pll0822x_recalc_rate(struct clk_hw *hw, u64 fvco = parent_rate; pll_con3 = readl_relaxed(pll->con_reg); - if (pll->type != pll_1418x) + + if (pll->type != pll_1418x && + pll->type != pll_0717x && + pll->type != pll_0718x) mdiv = (pll_con3 >> PLL0822X_MDIV_SHIFT) & PLL0822X_MDIV_MASK; else mdiv = (pll_con3 >> PLL0822X_MDIV_SHIFT) & PLL1418X_MDIV_MASK; + pdiv = (pll_con3 >> PLL0822X_PDIV_SHIFT) & PLL0822X_PDIV_MASK; sdiv = (pll_con3 >> PLL0822X_SDIV_SHIFT) & PLL0822X_SDIV_MASK; @@ -1377,6 +1384,9 @@ static void __init _samsung_clk_register_pll(struct samsung_clk_provider *ctx, case pll_0516x: case pll_0517x: case pll_0518x: + case pll_0717x: + case pll_0718x: + case pll_0732x: pll->enable_offs = PLL0822X_ENABLE_SHIFT; pll->lock_offs = PLL0822X_LOCK_STAT_SHIFT; if (!pll->rate_table) diff --git a/drivers/clk/samsung/clk-pll.h b/drivers/clk/samsung/clk-pll.h index 858ab367eb65..6ddc54d173a0 100644 --- a/drivers/clk/samsung/clk-pll.h +++ b/drivers/clk/samsung/clk-pll.h @@ -45,6 +45,9 @@ enum samsung_pll_type { pll_531x, pll_1051x, pll_1052x, + pll_0717x, + pll_0718x, + pll_0732x, }; #define PLL_RATE(_fin, _m, _p, _s, _k, _ks) \ diff --git a/drivers/clk/socfpga/clk-pll-a10.c b/drivers/clk/socfpga/clk-pll-a10.c index b028f25c658a..62eed964c3d0 100644 --- a/drivers/clk/socfpga/clk-pll-a10.c +++ b/drivers/clk/socfpga/clk-pll-a10.c @@ -35,7 +35,7 @@ static unsigned long clk_pll_recalc_rate(struct clk_hw *hwclk, unsigned long parent_rate) { struct socfpga_pll *socfpgaclk = to_socfpga_clk(hwclk); - unsigned long divf, divq, reg; + u32 divf, divq, reg; unsigned long long vco_freq; /* read VCO1 reg for numerator and denominator */ diff --git a/drivers/clk/starfive/clk-starfive-jh7100-audio.c b/drivers/clk/starfive/clk-starfive-jh7100-audio.c index 1fcf4e62f347..7de23f6749aa 100644 --- a/drivers/clk/starfive/clk-starfive-jh7100-audio.c +++ b/drivers/clk/starfive/clk-starfive-jh7100-audio.c @@ -84,17 +84,6 @@ static const struct jh71x0_clk_data jh7100_audclk_data[] = { JH7100_AUDCLK_AUDIO_12288), }; -static struct clk_hw *jh7100_audclk_get(struct of_phandle_args *clkspec, void *data) -{ - struct jh71x0_clk_priv *priv = data; - unsigned int idx = clkspec->args[0]; - - if (idx < JH7100_AUDCLK_END) - return &priv->reg[idx].hw; - - return ERR_PTR(-EINVAL); -} - static int jh7100_audclk_probe(struct platform_device *pdev) { struct jh71x0_clk_priv *priv; @@ -106,6 +95,7 @@ static int jh7100_audclk_probe(struct platform_device *pdev) return -ENOMEM; spin_lock_init(&priv->rmw_lock); + priv->num_reg = JH7100_AUDCLK_END; priv->dev = &pdev->dev; priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) @@ -146,7 +136,7 @@ static int jh7100_audclk_probe(struct platform_device *pdev) return ret; } - return devm_of_clk_add_hw_provider(priv->dev, jh7100_audclk_get, priv); + return devm_of_clk_add_hw_provider(priv->dev, jh71x0_clk_get, priv); } static const struct of_device_id jh7100_audclk_match[] = { diff --git a/drivers/clk/starfive/clk-starfive-jh7110-aon.c b/drivers/clk/starfive/clk-starfive-jh7110-aon.c index 418efdad719b..6f67587f4335 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-aon.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-aon.c @@ -54,17 +54,6 @@ static const struct jh71x0_clk_data jh7110_aonclk_data[] = { JH71X0_GATE(JH7110_AONCLK_RTC_CAL, "rtc_cal", 0, JH7110_AONCLK_OSC), }; -static struct clk_hw *jh7110_aonclk_get(struct of_phandle_args *clkspec, void *data) -{ - struct jh71x0_clk_priv *priv = data; - unsigned int idx = clkspec->args[0]; - - if (idx < JH7110_AONCLK_END) - return &priv->reg[idx].hw; - - return ERR_PTR(-EINVAL); -} - static int jh7110_aoncrg_probe(struct platform_device *pdev) { struct jh71x0_clk_priv *priv; @@ -78,6 +67,7 @@ static int jh7110_aoncrg_probe(struct platform_device *pdev) return -ENOMEM; spin_lock_init(&priv->rmw_lock); + priv->num_reg = JH7110_AONCLK_END; priv->dev = &pdev->dev; priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) @@ -127,7 +117,7 @@ static int jh7110_aoncrg_probe(struct platform_device *pdev) return ret; } - ret = devm_of_clk_add_hw_provider(&pdev->dev, jh7110_aonclk_get, priv); + ret = devm_of_clk_add_hw_provider(&pdev->dev, jh71x0_clk_get, priv); if (ret) return ret; diff --git a/drivers/clk/starfive/clk-starfive-jh7110-isp.c b/drivers/clk/starfive/clk-starfive-jh7110-isp.c index 8c4c3a958a9f..f3fa069db193 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-isp.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-isp.c @@ -75,17 +75,6 @@ static inline int jh7110_isp_top_rst_init(struct jh71x0_clk_priv *priv) return reset_control_deassert(top_rsts); } -static struct clk_hw *jh7110_ispclk_get(struct of_phandle_args *clkspec, void *data) -{ - struct jh71x0_clk_priv *priv = data; - unsigned int idx = clkspec->args[0]; - - if (idx < JH7110_ISPCLK_END) - return &priv->reg[idx].hw; - - return ERR_PTR(-EINVAL); -} - #ifdef CONFIG_PM static int jh7110_ispcrg_suspend(struct device *dev) { @@ -126,6 +115,7 @@ static int jh7110_ispcrg_probe(struct platform_device *pdev) return -ENOMEM; spin_lock_init(&priv->rmw_lock); + priv->num_reg = JH7110_ISPCLK_END; priv->dev = &pdev->dev; priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) @@ -186,7 +176,7 @@ static int jh7110_ispcrg_probe(struct platform_device *pdev) goto err_exit; } - ret = devm_of_clk_add_hw_provider(&pdev->dev, jh7110_ispclk_get, priv); + ret = devm_of_clk_add_hw_provider(&pdev->dev, jh71x0_clk_get, priv); if (ret) goto err_exit; diff --git a/drivers/clk/starfive/clk-starfive-jh7110-stg.c b/drivers/clk/starfive/clk-starfive-jh7110-stg.c index dafcb7190592..2a5ad0e07d1d 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-stg.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-stg.c @@ -75,17 +75,6 @@ static const struct jh71x0_clk_data jh7110_stgclk_data[] = { JH71X0_GATE(JH7110_STGCLK_DMA1P_AHB, "dma1p_ahb", 0, JH7110_STGCLK_STG_AXIAHB), }; -static struct clk_hw *jh7110_stgclk_get(struct of_phandle_args *clkspec, void *data) -{ - struct jh71x0_clk_priv *priv = data; - unsigned int idx = clkspec->args[0]; - - if (idx < JH7110_STGCLK_END) - return &priv->reg[idx].hw; - - return ERR_PTR(-EINVAL); -} - static int jh7110_stgcrg_probe(struct platform_device *pdev) { struct jh71x0_clk_priv *priv; @@ -98,6 +87,7 @@ static int jh7110_stgcrg_probe(struct platform_device *pdev) return -ENOMEM; spin_lock_init(&priv->rmw_lock); + priv->num_reg = JH7110_STGCLK_END; priv->dev = &pdev->dev; priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) @@ -145,7 +135,7 @@ static int jh7110_stgcrg_probe(struct platform_device *pdev) return ret; } - ret = devm_of_clk_add_hw_provider(&pdev->dev, jh7110_stgclk_get, priv); + ret = devm_of_clk_add_hw_provider(&pdev->dev, jh71x0_clk_get, priv); if (ret) return ret; diff --git a/drivers/clk/starfive/clk-starfive-jh7110-sys.c b/drivers/clk/starfive/clk-starfive-jh7110-sys.c index 17325f17696f..e9d8168d02b8 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-sys.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-sys.c @@ -323,17 +323,6 @@ static const struct jh71x0_clk_data jh7110_sysclk_data[] __initconst = { JH7110_SYSCLK_OSC), }; -static struct clk_hw *jh7110_sysclk_get(struct of_phandle_args *clkspec, void *data) -{ - struct jh71x0_clk_priv *priv = data; - unsigned int idx = clkspec->args[0]; - - if (idx < JH7110_SYSCLK_END) - return &priv->reg[idx].hw; - - return ERR_PTR(-EINVAL); -} - static void jh7110_reset_unregister_adev(void *_adev) { struct auxiliary_device *adev = _adev; @@ -425,6 +414,7 @@ static int __init jh7110_syscrg_probe(struct platform_device *pdev) return -ENOMEM; spin_lock_init(&priv->rmw_lock); + priv->num_reg = JH7110_SYSCLK_END; priv->dev = &pdev->dev; priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) @@ -526,7 +516,7 @@ static int __init jh7110_syscrg_probe(struct platform_device *pdev) return ret; } - ret = devm_of_clk_add_hw_provider(&pdev->dev, jh7110_sysclk_get, priv); + ret = devm_of_clk_add_hw_provider(&pdev->dev, jh71x0_clk_get, priv); if (ret) return ret; diff --git a/drivers/clk/starfive/clk-starfive-jh7110-vout.c b/drivers/clk/starfive/clk-starfive-jh7110-vout.c index 04eeed199087..bad20d5d794a 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-vout.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-vout.c @@ -80,17 +80,6 @@ static int jh7110_vout_top_rst_init(struct jh71x0_clk_priv *priv) return reset_control_deassert(top_rst); } -static struct clk_hw *jh7110_voutclk_get(struct of_phandle_args *clkspec, void *data) -{ - struct jh71x0_clk_priv *priv = data; - unsigned int idx = clkspec->args[0]; - - if (idx < JH7110_VOUTCLK_END) - return &priv->reg[idx].hw; - - return ERR_PTR(-EINVAL); -} - #ifdef CONFIG_PM static int jh7110_voutcrg_suspend(struct device *dev) { @@ -131,6 +120,7 @@ static int jh7110_voutcrg_probe(struct platform_device *pdev) return -ENOMEM; spin_lock_init(&priv->rmw_lock); + priv->num_reg = JH7110_VOUTCLK_END; priv->dev = &pdev->dev; priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) @@ -193,7 +183,7 @@ static int jh7110_voutcrg_probe(struct platform_device *pdev) goto err_exit; } - ret = devm_of_clk_add_hw_provider(&pdev->dev, jh7110_voutclk_get, priv); + ret = devm_of_clk_add_hw_provider(&pdev->dev, jh71x0_clk_get, priv); if (ret) goto err_exit; diff --git a/drivers/clk/starfive/clk-starfive-jh71x0.c b/drivers/clk/starfive/clk-starfive-jh71x0.c index aebc99264a0b..80e9157347eb 100644 --- a/drivers/clk/starfive/clk-starfive-jh71x0.c +++ b/drivers/clk/starfive/clk-starfive-jh71x0.c @@ -325,3 +325,15 @@ const struct clk_ops *starfive_jh71x0_clk_ops(u32 max) return &jh71x0_clk_inv_ops; } EXPORT_SYMBOL_GPL(starfive_jh71x0_clk_ops); + +struct clk_hw *jh71x0_clk_get(struct of_phandle_args *clkspec, void *data) +{ + struct jh71x0_clk_priv *priv = data; + unsigned int idx = clkspec->args[0]; + + if (idx < priv->num_reg) + return &priv->reg[idx].hw; + + return ERR_PTR(-EINVAL); +} +EXPORT_SYMBOL_GPL(jh71x0_clk_get); diff --git a/drivers/clk/starfive/clk-starfive-jh71x0.h b/drivers/clk/starfive/clk-starfive-jh71x0.h index e3f441393e48..9d5dec1d5cd1 100644 --- a/drivers/clk/starfive/clk-starfive-jh71x0.h +++ b/drivers/clk/starfive/clk-starfive-jh71x0.h @@ -117,9 +117,11 @@ struct jh71x0_clk_priv { struct clk *original_clk; struct notifier_block pll_clk_nb; struct clk_hw *pll[3]; - struct jh71x0_clk reg[]; + unsigned int num_reg; + struct jh71x0_clk reg[] __counted_by(num_reg); }; const struct clk_ops *starfive_jh71x0_clk_ops(u32 max); +struct clk_hw *jh71x0_clk_get(struct of_phandle_args *clkspec, void *data); #endif diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a100.c b/drivers/clk/sunxi-ng/ccu-sun50i-a100.c index 7133377d4163..1f81c7ac41af 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a100.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a100.c @@ -436,7 +436,7 @@ static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0", mmc_parents, 0x830, 24, 2, /* mux */ BIT(31), /* gate */ 2, /* post-div */ - CLK_SET_RATE_NO_REPARENT); + 0); static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1", mmc_parents, 0x834, 0, 4, /* M */ @@ -444,7 +444,7 @@ static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1", mmc_parents, 0x834, 24, 2, /* mux */ BIT(31), /* gate */ 2, /* post-div */ - CLK_SET_RATE_NO_REPARENT); + 0); static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc_parents, 0x838, 0, 4, /* M */ @@ -452,7 +452,7 @@ static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc_parents, 0x838, 24, 2, /* mux */ BIT(31), /* gate */ 2, /* post-div */ - CLK_SET_RATE_NO_REPARENT); + 0); static SUNXI_CCU_GATE(bus_mmc0_clk, "bus-mmc0", "ahb3", 0x84c, BIT(0), 0); static SUNXI_CCU_GATE(bus_mmc1_clk, "bus-mmc1", "ahb3", 0x84c, BIT(1), 0); diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c index 3a7d61c81667..ba1ad267f123 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c @@ -535,11 +535,11 @@ static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de", de_parents, CLK_SET_RATE_PARENT); /* - * DSI output seems to work only when PLL_MIPI selected. Set it and prevent - * the mux from reparenting. + * Experiments showed that RGB output requires pll-video0-2x, while DSI + * requires pll-mipi. It will not work with incorrect clock, the screen will + * be blank. + * sun50i-a64.dtsi assigns pll-mipi as TCON0 parent by default */ -#define SUN50I_A64_TCON0_CLK_REG 0x118 - static const char * const tcon0_parents[] = { "pll-mipi", "pll-video0-2x" }; static const u8 tcon0_table[] = { 0, 2, }; static SUNXI_CCU_MUX_TABLE_WITH_GATE_CLOSEST(tcon0_clk, "tcon0", tcon0_parents, @@ -959,11 +959,6 @@ static int sun50i_a64_ccu_probe(struct platform_device *pdev) writel(0x515, reg + SUN50I_A64_PLL_MIPI_REG); - /* Set PLL MIPI as parent for TCON0 */ - val = readl(reg + SUN50I_A64_TCON0_CLK_REG); - val &= ~GENMASK(26, 24); - writel(val | (0 << 24), reg + SUN50I_A64_TCON0_CLK_REG); - ret = devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_a64_ccu_desc); if (ret) return ret; diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h index a8c11c0b4e06..dfba88a5ad0f 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h @@ -21,7 +21,6 @@ /* PLL_VIDEO0 exported for HDMI PHY */ -#define CLK_PLL_VIDEO0_2X 8 #define CLK_PLL_VE 9 #define CLK_PLL_DDR0 10 @@ -32,7 +31,6 @@ #define CLK_PLL_PERIPH1_2X 14 #define CLK_PLL_VIDEO1 15 #define CLK_PLL_GPU 16 -#define CLK_PLL_MIPI 17 #define CLK_PLL_HSIC 18 #define CLK_PLL_DE 19 #define CLK_PLL_DDR1 20 diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h616.c b/drivers/clk/sunxi-ng/ccu-sun50i-h616.c index 1086669b91da..190816c35da9 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h616.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h616.c @@ -1107,11 +1107,24 @@ static const u32 usb2_clk_regs[] = { SUN50I_H616_USB3_CLK_REG, }; +static struct ccu_mux_nb sun50i_h616_cpu_nb = { + .common = &cpux_clk.common, + .cm = &cpux_clk.mux, + .delay_us = 1, /* manual doesn't really say */ + .bypass_index = 4, /* PLL_PERI0@600MHz, as recommended by manual */ +}; + +static struct ccu_pll_nb sun50i_h616_pll_cpu_nb = { + .common = &pll_cpux_clk.common, + .enable = BIT(29), /* LOCK_ENABLE */ + .lock = BIT(28), +}; + static int sun50i_h616_ccu_probe(struct platform_device *pdev) { void __iomem *reg; u32 val; - int i; + int ret, i; reg = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(reg)) @@ -1166,7 +1179,18 @@ static int sun50i_h616_ccu_probe(struct platform_device *pdev) val |= BIT(24); writel(val, reg + SUN50I_H616_HDMI_CEC_CLK_REG); - return devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h616_ccu_desc); + ret = devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h616_ccu_desc); + if (ret) + return ret; + + /* Reparent CPU during CPU PLL rate changes */ + ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, + &sun50i_h616_cpu_nb); + + /* Re-lock the CPU PLL after any rate changes */ + ccu_pll_notifier_register(&sun50i_h616_pll_cpu_nb); + + return 0; } static const struct of_device_id sun50i_h616_ccu_ids[] = { diff --git a/drivers/clk/thead/clk-th1520-ap.c b/drivers/clk/thead/clk-th1520-ap.c index 17e32ae08720..4c9555fc6184 100644 --- a/drivers/clk/thead/clk-th1520-ap.c +++ b/drivers/clk/thead/clk-th1520-ap.c @@ -657,7 +657,7 @@ static struct ccu_div apb_pclk = { .hw.init = CLK_HW_INIT_PARENTS_DATA("apb-pclk", apb_parents, &ccu_div_ops, - 0), + CLK_IGNORE_UNUSED), }, }; @@ -779,6 +779,13 @@ static struct ccu_div dpu1_clk = { }, }; +static CLK_FIXED_FACTOR_HW(emmc_sdio_ref_clk, "emmc-sdio-ref", + &video_pll_clk.common.hw, 4, 1, 0); + +static const struct clk_parent_data emmc_sdio_ref_clk_pd[] = { + { .hw = &emmc_sdio_ref_clk.hw }, +}; + static CCU_GATE(CLK_BROM, brom_clk, "brom", ahb2_cpusys_hclk_pd, 0x100, BIT(4), 0); static CCU_GATE(CLK_BMU, bmu_clk, "bmu", axi4_cpusys2_aclk_pd, 0x100, BIT(5), 0); static CCU_GATE(CLK_AON2CPU_A2X, aon2cpu_a2x_clk, "aon2cpu-a2x", axi4_cpusys2_aclk_pd, @@ -787,18 +794,18 @@ static CCU_GATE(CLK_X2X_CPUSYS, x2x_cpusys_clk, "x2x-cpusys", axi4_cpusys2_aclk_ 0x134, BIT(7), 0); static CCU_GATE(CLK_CPU2AON_X2H, cpu2aon_x2h_clk, "cpu2aon-x2h", axi_aclk_pd, 0x138, BIT(8), 0); static CCU_GATE(CLK_CPU2PERI_X2H, cpu2peri_x2h_clk, "cpu2peri-x2h", axi4_cpusys2_aclk_pd, - 0x140, BIT(9), 0); + 0x140, BIT(9), CLK_IGNORE_UNUSED); static CCU_GATE(CLK_PERISYS_APB1_HCLK, perisys_apb1_hclk, "perisys-apb1-hclk", perisys_ahb_hclk_pd, 0x150, BIT(9), 0); static CCU_GATE(CLK_PERISYS_APB2_HCLK, perisys_apb2_hclk, "perisys-apb2-hclk", perisys_ahb_hclk_pd, - 0x150, BIT(10), 0); + 0x150, BIT(10), CLK_IGNORE_UNUSED); static CCU_GATE(CLK_PERISYS_APB3_HCLK, perisys_apb3_hclk, "perisys-apb3-hclk", perisys_ahb_hclk_pd, - 0x150, BIT(11), 0); + 0x150, BIT(11), CLK_IGNORE_UNUSED); static CCU_GATE(CLK_PERISYS_APB4_HCLK, perisys_apb4_hclk, "perisys-apb4-hclk", perisys_ahb_hclk_pd, 0x150, BIT(12), 0); static CCU_GATE(CLK_NPU_AXI, npu_axi_clk, "npu-axi", axi_aclk_pd, 0x1c8, BIT(5), 0); static CCU_GATE(CLK_CPU2VP, cpu2vp_clk, "cpu2vp", axi_aclk_pd, 0x1e0, BIT(13), 0); -static CCU_GATE(CLK_EMMC_SDIO, emmc_sdio_clk, "emmc-sdio", video_pll_clk_pd, 0x204, BIT(30), 0); +static CCU_GATE(CLK_EMMC_SDIO, emmc_sdio_clk, "emmc-sdio", emmc_sdio_ref_clk_pd, 0x204, BIT(30), 0); static CCU_GATE(CLK_GMAC1, gmac1_clk, "gmac1", gmac_pll_clk_pd, 0x204, BIT(26), 0); static CCU_GATE(CLK_PADCTRL1, padctrl1_clk, "padctrl1", perisys_apb_pclk_pd, 0x204, BIT(24), 0); static CCU_GATE(CLK_DSMART, dsmart_clk, "dsmart", perisys_apb_pclk_pd, 0x204, BIT(23), 0); @@ -889,7 +896,6 @@ static struct ccu_common *th1520_div_clks[] = { &vo_axi_clk.common, &vp_apb_clk.common, &vp_axi_clk.common, - &cpu2vp_clk.common, &venc_clk.common, &dpu0_clk.common, &dpu1_clk.common, @@ -909,6 +915,7 @@ static struct ccu_common *th1520_gate_clks[] = { &bmu_clk.common, &cpu2aon_x2h_clk.common, &cpu2peri_x2h_clk.common, + &cpu2vp_clk.common, &perisys_apb1_hclk.common, &perisys_apb2_hclk.common, &perisys_apb3_hclk.common, @@ -1041,7 +1048,8 @@ static int th1520_clk_probe(struct platform_device *pdev) hw = devm_clk_hw_register_gate_parent_data(dev, cg->common.hw.init->name, cg->common.hw.init->parent_data, - 0, base + cg->common.cfg0, + cg->common.hw.init->flags, + base + cg->common.cfg0, ffs(cg->enable) - 1, 0, NULL); if (IS_ERR(hw)) return PTR_ERR(hw); @@ -1059,6 +1067,10 @@ static int th1520_clk_probe(struct platform_device *pdev) return ret; priv->hws[CLK_PLL_GMAC_100M] = &gmac_pll_clk_100m.hw; + ret = devm_clk_hw_register(dev, &emmc_sdio_ref_clk.hw); + if (ret) + return ret; + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, priv); if (ret) return ret; diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c index f2117fef7c7d..9c75dcc9a534 100644 --- a/drivers/clk/ti/clk.c +++ b/drivers/clk/ti/clk.c @@ -449,10 +449,7 @@ void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem) { struct clk_iomap *io; - io = memblock_alloc(sizeof(*io), SMP_CACHE_BYTES); - if (!io) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*io)); + io = memblock_alloc_or_panic(sizeof(*io), SMP_CACHE_BYTES); io->mem = mem; diff --git a/drivers/clk/ti/mux.c b/drivers/clk/ti/mux.c index 216d85d6aac6..f684fc306ecc 100644 --- a/drivers/clk/ti/mux.c +++ b/drivers/clk/ti/mux.c @@ -180,7 +180,7 @@ static void of_mux_clk_setup(struct device_node *node) pr_err("mux-clock %pOFn must have parents\n", node); return; } - parent_names = kzalloc((sizeof(char *) * num_parents), GFP_KERNEL); + parent_names = kcalloc(num_parents, sizeof(char *), GFP_KERNEL); if (!parent_names) goto cleanup; diff --git a/drivers/clk/xilinx/clk-xlnx-clock-wizard.c b/drivers/clk/xilinx/clk-xlnx-clock-wizard.c index b2233d3ff9a9..bbf7714480e7 100644 --- a/drivers/clk/xilinx/clk-xlnx-clock-wizard.c +++ b/drivers/clk/xilinx/clk-xlnx-clock-wizard.c @@ -52,6 +52,8 @@ #define WZRD_CLKFBOUT_MULT_SHIFT 8 #define WZRD_CLKFBOUT_MULT_MASK (0xff << WZRD_CLKFBOUT_MULT_SHIFT) +#define WZRD_CLKFBOUT_MULT_FRAC_MASK GENMASK(25, 16) +#define WZRD_CLKFBOUT_O_MASK GENMASK(7, 0) #define WZRD_CLKFBOUT_L_SHIFT 0 #define WZRD_CLKFBOUT_H_SHIFT 8 #define WZRD_CLKFBOUT_L_MASK GENMASK(7, 0) @@ -87,14 +89,14 @@ #define DIV_O 0x01 #define DIV_ALL 0x03 -#define WZRD_M_MIN 2 -#define WZRD_M_MAX 128 -#define WZRD_D_MIN 1 -#define WZRD_D_MAX 106 -#define WZRD_VCO_MIN 800000000 -#define WZRD_VCO_MAX 1600000000 -#define WZRD_O_MIN 1 -#define WZRD_O_MAX 128 +#define WZRD_M_MIN 2ULL +#define WZRD_M_MAX 128ULL +#define WZRD_D_MIN 1ULL +#define WZRD_D_MAX 106ULL +#define WZRD_VCO_MIN 800000000ULL +#define WZRD_VCO_MAX 1600000000ULL +#define WZRD_O_MIN 2ULL +#define WZRD_O_MAX 128ULL #define VER_WZRD_M_MIN 4 #define VER_WZRD_M_MAX 432 #define VER_WZRD_D_MIN 1 @@ -153,8 +155,10 @@ struct clk_wzrd { * @flags: clk_wzrd divider flags * @table: array of value/divider pairs, last entry should have div = 0 * @m: value of the multiplier + * @m_frac: fractional value of the multiplier * @d: value of the common divider * @o: value of the leaf divider + * @o_frac: value of the fractional leaf divider * @lock: register lock */ struct clk_wzrd_divider { @@ -166,8 +170,10 @@ struct clk_wzrd_divider { u8 flags; const struct clk_div_table *table; u32 m; + u32 m_frac; u32 d; u32 o; + u32 o_frac; spinlock_t *lock; /* divider lock */ }; @@ -372,38 +378,40 @@ static int clk_wzrd_get_divisors(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); - u64 vco_freq, freq, diff, vcomin, vcomax; - u32 m, d, o; - u32 mmin, mmax, dmin, dmax, omin, omax; + u64 vco_freq, freq, diff, vcomin, vcomax, best_diff = -1ULL; + u64 m, d, o; + u64 mmin, mmax, dmin, dmax, omin, omax, mdmin, mdmax; - mmin = WZRD_M_MIN; - mmax = WZRD_M_MAX; + mmin = WZRD_M_MIN << 3; + mmax = WZRD_M_MAX << 3; dmin = WZRD_D_MIN; dmax = WZRD_D_MAX; - omin = WZRD_O_MIN; - omax = WZRD_O_MAX; - vcomin = WZRD_VCO_MIN; - vcomax = WZRD_VCO_MAX; + omin = WZRD_O_MIN << 3; + omax = WZRD_O_MAX << 3; + vcomin = WZRD_VCO_MIN << 3; + vcomax = WZRD_VCO_MAX << 3; for (m = mmin; m <= mmax; m++) { - for (d = dmin; d <= dmax; d++) { - vco_freq = DIV_ROUND_CLOSEST((parent_rate * m), d); - if (vco_freq >= vcomin && vco_freq <= vcomax) { - for (o = omin; o <= omax; o++) { - freq = DIV_ROUND_CLOSEST_ULL(vco_freq, o); - diff = abs(freq - rate); - - if (diff < WZRD_MIN_ERR) { - divider->m = m; - divider->d = d; - divider->o = o; - return 0; - } - } + mdmin = max(dmin, div64_u64(parent_rate * m + vcomax / 2, vcomax)); + mdmax = min(dmax, div64_u64(parent_rate * m + vcomin / 2, vcomin)); + for (d = mdmin; d <= mdmax; d++) { + vco_freq = DIV_ROUND_CLOSEST_ULL((parent_rate * m), d); + o = DIV_ROUND_CLOSEST_ULL(vco_freq, rate); + if (o < omin || o > omax) + continue; + freq = DIV_ROUND_CLOSEST_ULL(vco_freq, o); + diff = freq - rate; + if (diff < best_diff) { + best_diff = diff; + divider->m = m >> 3; + divider->m_frac = (m - (divider->m << 3)) * 125; + divider->d = d; + divider->o = o >> 3; + divider->o_frac = (o - (divider->o << 3)) * 125; } } } - return -EBUSY; + return best_diff < WZRD_MIN_ERR ? 0 : -EBUSY; } static int clk_wzrd_reconfig(struct clk_wzrd_divider *divider, void __iomem *div_addr) @@ -496,33 +504,22 @@ static int clk_wzrd_dynamic_all_nolock(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); - unsigned long vco_freq, rate_div, clockout0_div; void __iomem *div_addr; - u32 reg, pre, f; + u32 reg; int err; err = clk_wzrd_get_divisors(hw, rate, parent_rate); if (err) return err; - vco_freq = DIV_ROUND_CLOSEST(parent_rate * divider->m, divider->d); - rate_div = DIV_ROUND_CLOSEST_ULL((vco_freq * WZRD_FRAC_POINTS), rate); - - clockout0_div = div_u64(rate_div, WZRD_FRAC_POINTS); - - pre = DIV_ROUND_CLOSEST_ULL(vco_freq * WZRD_FRAC_POINTS, rate); - f = (pre - (clockout0_div * WZRD_FRAC_POINTS)); - f &= WZRD_CLKOUT_FRAC_MASK; - - reg = FIELD_PREP(WZRD_CLKOUT_DIVIDE_MASK, clockout0_div) | - FIELD_PREP(WZRD_CLKOUT0_FRAC_MASK, f); + reg = FIELD_PREP(WZRD_CLKOUT_DIVIDE_MASK, divider->o) | + FIELD_PREP(WZRD_CLKOUT0_FRAC_MASK, divider->o_frac); writel(reg, divider->base + WZRD_CLK_CFG_REG(0, 2)); - /* Set divisor and clear phase offset */ reg = FIELD_PREP(WZRD_CLKFBOUT_MULT_MASK, divider->m) | + FIELD_PREP(WZRD_CLKFBOUT_MULT_FRAC_MASK, divider->m_frac) | FIELD_PREP(WZRD_DIVCLK_DIVIDE_MASK, divider->d); writel(reg, divider->base + WZRD_CLK_CFG_REG(0, 0)); - writel(divider->o, divider->base + WZRD_CLK_CFG_REG(0, 2)); writel(0, divider->base + WZRD_CLK_CFG_REG(0, 3)); div_addr = divider->base + WZRD_DR_INIT_REG_OFFSET; return clk_wzrd_reconfig(divider, div_addr); @@ -564,18 +561,19 @@ static unsigned long clk_wzrd_recalc_rate_all(struct clk_hw *hw, unsigned long parent_rate) { struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); - u32 m, d, o, div, reg, f; + u32 m, d, o, reg, f, mf; + u64 mul; reg = readl(divider->base + WZRD_CLK_CFG_REG(0, 0)); d = FIELD_GET(WZRD_DIVCLK_DIVIDE_MASK, reg); m = FIELD_GET(WZRD_CLKFBOUT_MULT_MASK, reg); + mf = FIELD_GET(WZRD_CLKFBOUT_MULT_FRAC_MASK, reg); reg = readl(divider->base + WZRD_CLK_CFG_REG(0, 2)); o = FIELD_GET(WZRD_DIVCLK_DIVIDE_MASK, reg); f = FIELD_GET(WZRD_CLKOUT0_FRAC_MASK, reg); - div = DIV_ROUND_CLOSEST(d * (WZRD_FRAC_POINTS * o + f), WZRD_FRAC_POINTS); - return divider_recalc_rate(hw, parent_rate * m, div, divider->table, - divider->flags, divider->width); + mul = m * 1000 + mf; + return DIV_ROUND_CLOSEST_ULL(parent_rate * mul, d * (o * 1000 + f)); } static unsigned long clk_wzrd_recalc_rate_all_ver(struct clk_hw *hw, @@ -646,6 +644,25 @@ static unsigned long clk_wzrd_recalc_rate_all_ver(struct clk_hw *hw, static long clk_wzrd_round_rate_all(struct clk_hw *hw, unsigned long rate, unsigned long *prate) +{ + struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); + u32 m, d, o; + int err; + + err = clk_wzrd_get_divisors(hw, rate, *prate); + if (err) + return err; + + m = divider->m; + d = divider->d; + o = divider->o; + + rate = div_u64(*prate * (m * 1000 + divider->m_frac), d * (o * 1000 + divider->o_frac)); + return rate; +} + +static long clk_wzrd_ver_round_rate_all(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) { struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); unsigned long int_freq; @@ -678,7 +695,7 @@ static const struct clk_ops clk_wzrd_ver_divider_ops = { }; static const struct clk_ops clk_wzrd_ver_div_all_ops = { - .round_rate = clk_wzrd_round_rate_all, + .round_rate = clk_wzrd_ver_round_rate_all, .set_rate = clk_wzrd_dynamic_all_ver, .recalc_rate = clk_wzrd_recalc_rate_all_ver, }; diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..f00019b078a7 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -23,11 +23,12 @@ #include #include #include -#include +#include #include static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 92a83a9bb2e1..d64b07ec48e5 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -232,7 +232,7 @@ config CPUFREQ_VIRT If in doubt, say N. config CPUFREQ_DT_PLATDEV - tristate "Generic DT based cpufreq platdev driver" + bool "Generic DT based cpufreq platdev driver" depends on OF help This adds a generic DT based cpufreq platdev driver for frequency @@ -325,8 +325,6 @@ config QORIQ_CPUFREQ This adds the CPUFreq driver support for Freescale QorIQ SoCs which are capable of changing the CPU's frequency dynamically. -endif - config ACPI_CPPC_CPUFREQ tristate "CPUFreq driver based on the ACPI CPPC spec" depends on ACPI_PROCESSOR @@ -355,4 +353,6 @@ config ACPI_CPPC_CPUFREQ_FIE If in doubt, say N. +endif + endmenu diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 5f7e13e60c80..0ee5c691fb36 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -15,6 +15,14 @@ config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM To compile this driver as a module, choose M here: the module will be called sun50i-cpufreq-nvmem. +config ARM_AIROHA_SOC_CPUFREQ + tristate "Airoha EN7581 SoC CPUFreq support" + depends on (ARCH_AIROHA && OF) || COMPILE_TEST + select PM_OPP + default ARCH_AIROHA + help + This adds the CPUFreq driver for Airoha EN7581 SoCs. + config ARM_APPLE_SOC_CPUFREQ tristate "Apple Silicon SoC CPUFreq support" depends on ARCH_APPLE || (COMPILE_TEST && 64BIT) diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index d35a28dd9463..890fff99f37d 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -53,6 +53,7 @@ obj-$(CONFIG_X86_AMD_FREQ_SENSITIVITY) += amd_freq_sensitivity.o ################################################################################## # ARM SoC drivers +obj-$(CONFIG_ARM_AIROHA_SOC_CPUFREQ) += airoha-cpufreq.o obj-$(CONFIG_ARM_APPLE_SOC_CPUFREQ) += apple-soc-cpufreq.o obj-$(CONFIG_ARM_ARMADA_37XX_CPUFREQ) += armada-37xx-cpufreq.o obj-$(CONFIG_ARM_ARMADA_8K_CPUFREQ) += armada-8k-cpufreq.o diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index c9ebacf5c88e..463b69a2dff5 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -623,7 +623,14 @@ static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c) #endif #ifdef CONFIG_ACPI_CPPC_LIB -static u64 get_max_boost_ratio(unsigned int cpu) +/* + * get_max_boost_ratio: Computes the max_boost_ratio as the ratio + * between the highest_perf and the nominal_perf. + * + * Returns the max_boost_ratio for @cpu. Returns the CPPC nominal + * frequency via @nominal_freq if it is non-NULL pointer. + */ +static u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq) { struct cppc_perf_caps perf_caps; u64 highest_perf, nominal_perf; @@ -652,6 +659,9 @@ static u64 get_max_boost_ratio(unsigned int cpu) nominal_perf = perf_caps.nominal_perf; + if (nominal_freq) + *nominal_freq = perf_caps.nominal_freq; + if (!highest_perf || !nominal_perf) { pr_debug("CPU%d: highest or nominal performance missing\n", cpu); return 0; @@ -664,8 +674,12 @@ static u64 get_max_boost_ratio(unsigned int cpu) return div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); } + #else -static inline u64 get_max_boost_ratio(unsigned int cpu) { return 0; } +static inline u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq) +{ + return 0; +} #endif static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) @@ -675,9 +689,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) struct acpi_cpufreq_data *data; unsigned int cpu = policy->cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); + u64 max_boost_ratio, nominal_freq = 0; unsigned int valid_states = 0; unsigned int result = 0; - u64 max_boost_ratio; unsigned int i; #ifdef CONFIG_SMP static int blacklisted; @@ -827,16 +841,20 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) } freq_table[valid_states].frequency = CPUFREQ_TABLE_END; - max_boost_ratio = get_max_boost_ratio(cpu); + max_boost_ratio = get_max_boost_ratio(cpu, &nominal_freq); if (max_boost_ratio) { - unsigned int freq = freq_table[0].frequency; + unsigned int freq = nominal_freq; /* - * Because the loop above sorts the freq_table entries in the - * descending order, freq is the maximum frequency in the table. - * Assume that it corresponds to the CPPC nominal frequency and - * use it to set cpuinfo.max_freq. + * The loop above sorts the freq_table entries in the + * descending order. If ACPI CPPC has not advertised + * the nominal frequency (this is possible in CPPC + * revisions prior to 3), then use the first entry in + * the pstate table as a proxy for nominal frequency. */ + if (!freq) + freq = freq_table[0].frequency; + policy->cpuinfo.max_freq = freq * max_boost_ratio >> SCHED_CAPACITY_SHIFT; } else { /* @@ -891,11 +909,6 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency) pr_warn(FW_WARN "P-state 0 is not max freq\n"); - if (acpi_cpufreq_driver.set_boost) { - set_boost(policy, acpi_cpufreq_driver.boost_enabled); - policy->boost_enabled = acpi_cpufreq_driver.boost_enabled; - } - return result; err_unreg: diff --git a/drivers/cpufreq/airoha-cpufreq.c b/drivers/cpufreq/airoha-cpufreq.c new file mode 100644 index 000000000000..4fe39eadd163 --- /dev/null +++ b/drivers/cpufreq/airoha-cpufreq.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include +#include + +#include "cpufreq-dt.h" + +struct airoha_cpufreq_priv { + int opp_token; + struct dev_pm_domain_list *pd_list; + struct platform_device *cpufreq_dt; +}; + +static struct platform_device *cpufreq_pdev; + +/* NOP function to disable OPP from setting clock */ +static int airoha_cpufreq_config_clks_nop(struct device *dev, + struct opp_table *opp_table, + struct dev_pm_opp *opp, + void *data, bool scaling_down) +{ + return 0; +} + +static const char * const airoha_cpufreq_clk_names[] = { "cpu", NULL }; +static const char * const airoha_cpufreq_pd_names[] = { "perf" }; + +static int airoha_cpufreq_probe(struct platform_device *pdev) +{ + const struct dev_pm_domain_attach_data attach_data = { + .pd_names = airoha_cpufreq_pd_names, + .num_pd_names = ARRAY_SIZE(airoha_cpufreq_pd_names), + .pd_flags = PD_FLAG_DEV_LINK_ON | PD_FLAG_REQUIRED_OPP, + }; + struct dev_pm_opp_config config = { + .clk_names = airoha_cpufreq_clk_names, + .config_clks = airoha_cpufreq_config_clks_nop, + }; + struct platform_device *cpufreq_dt; + struct airoha_cpufreq_priv *priv; + struct device *dev = &pdev->dev; + struct device *cpu_dev; + int ret; + + /* CPUs refer to the same OPP table */ + cpu_dev = get_cpu_device(0); + if (!cpu_dev) + return -ENODEV; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + /* Set OPP table conf with NOP config_clks */ + priv->opp_token = dev_pm_opp_set_config(cpu_dev, &config); + if (priv->opp_token < 0) + return dev_err_probe(dev, priv->opp_token, "Failed to set OPP config\n"); + + /* Attach PM for OPP */ + ret = dev_pm_domain_attach_list(cpu_dev, &attach_data, + &priv->pd_list); + if (ret) + goto clear_opp_config; + + cpufreq_dt = platform_device_register_simple("cpufreq-dt", -1, NULL, 0); + ret = PTR_ERR_OR_ZERO(cpufreq_dt); + if (ret) { + dev_err(dev, "failed to create cpufreq-dt device: %d\n", ret); + goto detach_pm; + } + + priv->cpufreq_dt = cpufreq_dt; + platform_set_drvdata(pdev, priv); + + return 0; + +detach_pm: + dev_pm_domain_detach_list(priv->pd_list); +clear_opp_config: + dev_pm_opp_clear_config(priv->opp_token); + + return ret; +} + +static void airoha_cpufreq_remove(struct platform_device *pdev) +{ + struct airoha_cpufreq_priv *priv = platform_get_drvdata(pdev); + + platform_device_unregister(priv->cpufreq_dt); + + dev_pm_domain_detach_list(priv->pd_list); + + dev_pm_opp_clear_config(priv->opp_token); +} + +static struct platform_driver airoha_cpufreq_driver = { + .probe = airoha_cpufreq_probe, + .remove = airoha_cpufreq_remove, + .driver = { + .name = "airoha-cpufreq", + }, +}; + +static const struct of_device_id airoha_cpufreq_match_list[] __initconst = { + { .compatible = "airoha,en7581" }, + {}, +}; +MODULE_DEVICE_TABLE(of, airoha_cpufreq_match_list); + +static int __init airoha_cpufreq_init(void) +{ + struct device_node *np = of_find_node_by_path("/"); + const struct of_device_id *match; + int ret; + + if (!np) + return -ENODEV; + + match = of_match_node(airoha_cpufreq_match_list, np); + of_node_put(np); + if (!match) + return -ENODEV; + + ret = platform_driver_register(&airoha_cpufreq_driver); + if (unlikely(ret < 0)) + return ret; + + cpufreq_pdev = platform_device_register_data(NULL, "airoha-cpufreq", + -1, match, sizeof(*match)); + ret = PTR_ERR_OR_ZERO(cpufreq_pdev); + if (ret) + platform_driver_unregister(&airoha_cpufreq_driver); + + return ret; +} +module_init(airoha_cpufreq_init); + +static void __exit airoha_cpufreq_exit(void) +{ + platform_device_unregister(cpufreq_pdev); + platform_driver_unregister(&airoha_cpufreq_driver); +} +module_exit(airoha_cpufreq_exit); + +MODULE_AUTHOR("Christian Marangi "); +MODULE_DESCRIPTION("CPUfreq driver for Airoha SoCs"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/amd-pstate-trace.h b/drivers/cpufreq/amd-pstate-trace.h index 35f38ae67fb1..8d692415d905 100644 --- a/drivers/cpufreq/amd-pstate-trace.h +++ b/drivers/cpufreq/amd-pstate-trace.h @@ -32,7 +32,6 @@ TRACE_EVENT(amd_pstate_perf, u64 aperf, u64 tsc, unsigned int cpu_id, - bool changed, bool fast_switch ), @@ -44,7 +43,6 @@ TRACE_EVENT(amd_pstate_perf, aperf, tsc, cpu_id, - changed, fast_switch ), @@ -57,7 +55,6 @@ TRACE_EVENT(amd_pstate_perf, __field(unsigned long long, aperf) __field(unsigned long long, tsc) __field(unsigned int, cpu_id) - __field(bool, changed) __field(bool, fast_switch) ), @@ -70,11 +67,10 @@ TRACE_EVENT(amd_pstate_perf, __entry->aperf = aperf; __entry->tsc = tsc; __entry->cpu_id = cpu_id; - __entry->changed = changed; __entry->fast_switch = fast_switch; ), - TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu freq=%llu mperf=%llu aperf=%llu tsc=%llu cpu_id=%u changed=%s fast_switch=%s", + TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu freq=%llu mperf=%llu aperf=%llu tsc=%llu cpu_id=%u fast_switch=%s", (unsigned long)__entry->min_perf, (unsigned long)__entry->target_perf, (unsigned long)__entry->capacity, @@ -83,11 +79,55 @@ TRACE_EVENT(amd_pstate_perf, (unsigned long long)__entry->aperf, (unsigned long long)__entry->tsc, (unsigned int)__entry->cpu_id, - (__entry->changed) ? "true" : "false", (__entry->fast_switch) ? "true" : "false" ) ); +TRACE_EVENT(amd_pstate_epp_perf, + + TP_PROTO(unsigned int cpu_id, + unsigned int highest_perf, + unsigned int epp, + unsigned int min_perf, + unsigned int max_perf, + bool boost + ), + + TP_ARGS(cpu_id, + highest_perf, + epp, + min_perf, + max_perf, + boost), + + TP_STRUCT__entry( + __field(unsigned int, cpu_id) + __field(unsigned int, highest_perf) + __field(unsigned int, epp) + __field(unsigned int, min_perf) + __field(unsigned int, max_perf) + __field(bool, boost) + ), + + TP_fast_assign( + __entry->cpu_id = cpu_id; + __entry->highest_perf = highest_perf; + __entry->epp = epp; + __entry->min_perf = min_perf; + __entry->max_perf = max_perf; + __entry->boost = boost; + ), + + TP_printk("cpu%u: [%u<->%u]/%u, epp=%u, boost=%u", + (unsigned int)__entry->cpu_id, + (unsigned int)__entry->min_perf, + (unsigned int)__entry->max_perf, + (unsigned int)__entry->highest_perf, + (unsigned int)__entry->epp, + (bool)__entry->boost + ) +); + #endif /* _AMD_PSTATE_TRACE_H */ /* This part must be outside protection */ diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c index a261d7300951..3a0a380c3590 100644 --- a/drivers/cpufreq/amd-pstate-ut.c +++ b/drivers/cpufreq/amd-pstate-ut.c @@ -207,7 +207,6 @@ static void amd_pstate_ut_check_freq(u32 index) int cpu = 0; struct cpufreq_policy *policy = NULL; struct amd_cpudata *cpudata = NULL; - u32 nominal_freq_khz; for_each_possible_cpu(cpu) { policy = cpufreq_cpu_get(cpu); @@ -215,14 +214,13 @@ static void amd_pstate_ut_check_freq(u32 index) break; cpudata = policy->driver_data; - nominal_freq_khz = cpudata->nominal_freq*1000; - if (!((cpudata->max_freq >= nominal_freq_khz) && - (nominal_freq_khz > cpudata->lowest_nonlinear_freq) && + if (!((cpudata->max_freq >= cpudata->nominal_freq) && + (cpudata->nominal_freq > cpudata->lowest_nonlinear_freq) && (cpudata->lowest_nonlinear_freq > cpudata->min_freq) && (cpudata->min_freq > 0))) { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; pr_err("%s cpu%d max=%d >= nominal=%d > lowest_nonlinear=%d > min=%d > 0, the formula is incorrect!\n", - __func__, cpu, cpudata->max_freq, nominal_freq_khz, + __func__, cpu, cpudata->max_freq, cpudata->nominal_freq, cpudata->lowest_nonlinear_freq, cpudata->min_freq); goto skip_test; } @@ -236,13 +234,13 @@ static void amd_pstate_ut_check_freq(u32 index) if (cpudata->boost_supported) { if ((policy->max == cpudata->max_freq) || - (policy->max == nominal_freq_khz)) + (policy->max == cpudata->nominal_freq)) amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS; else { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; pr_err("%s cpu%d policy_max=%d should be equal cpu_max=%d or cpu_nominal=%d !\n", __func__, cpu, policy->max, cpudata->max_freq, - nominal_freq_khz); + cpudata->nominal_freq); goto skip_test; } } else { diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index d7630bab2516..dd9b8d6993d6 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -22,6 +22,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -88,6 +89,11 @@ static bool cppc_enabled; static bool amd_pstate_prefcore = true; static struct quirk_entry *quirks; +#define AMD_CPPC_MAX_PERF_MASK GENMASK(7, 0) +#define AMD_CPPC_MIN_PERF_MASK GENMASK(15, 8) +#define AMD_CPPC_DES_PERF_MASK GENMASK(23, 16) +#define AMD_CPPC_EPP_PERF_MASK GENMASK(31, 24) + /* * AMD Energy Preference Performance (EPP) * The EPP is used in the CCLK DPM controller to drive @@ -180,120 +186,145 @@ static inline int get_mode_idx_from_str(const char *str, size_t size) static DEFINE_MUTEX(amd_pstate_limits_lock); static DEFINE_MUTEX(amd_pstate_driver_lock); -static s16 amd_pstate_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached) +static s16 msr_get_epp(struct amd_cpudata *cpudata) +{ + u64 value; + int ret; + + ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value); + if (ret < 0) { + pr_debug("Could not retrieve energy perf value (%d)\n", ret); + return ret; + } + + return FIELD_GET(AMD_CPPC_EPP_PERF_MASK, value); +} + +DEFINE_STATIC_CALL(amd_pstate_get_epp, msr_get_epp); + +static inline s16 amd_pstate_get_epp(struct amd_cpudata *cpudata) +{ + return static_call(amd_pstate_get_epp)(cpudata); +} + +static s16 shmem_get_epp(struct amd_cpudata *cpudata) { u64 epp; int ret; - if (cpu_feature_enabled(X86_FEATURE_CPPC)) { - if (!cppc_req_cached) { - epp = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, - &cppc_req_cached); - if (epp) - return epp; - } - epp = (cppc_req_cached >> 24) & 0xFF; - } else { - ret = cppc_get_epp_perf(cpudata->cpu, &epp); - if (ret < 0) { - pr_debug("Could not retrieve energy perf value (%d)\n", ret); - return -EIO; - } + ret = cppc_get_epp_perf(cpudata->cpu, &epp); + if (ret < 0) { + pr_debug("Could not retrieve energy perf value (%d)\n", ret); + return ret; } return (s16)(epp & 0xff); } -static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata) +static int msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf, + u32 des_perf, u32 max_perf, u32 epp, bool fast_switch) { - s16 epp; - int index = -EINVAL; + u64 value, prev; - epp = amd_pstate_get_epp(cpudata, 0); - if (epp < 0) - return epp; + value = prev = READ_ONCE(cpudata->cppc_req_cached); - switch (epp) { - case AMD_CPPC_EPP_PERFORMANCE: - index = EPP_INDEX_PERFORMANCE; - break; - case AMD_CPPC_EPP_BALANCE_PERFORMANCE: - index = EPP_INDEX_BALANCE_PERFORMANCE; - break; - case AMD_CPPC_EPP_BALANCE_POWERSAVE: - index = EPP_INDEX_BALANCE_POWERSAVE; - break; - case AMD_CPPC_EPP_POWERSAVE: - index = EPP_INDEX_POWERSAVE; - break; - default: - break; + value &= ~(AMD_CPPC_MAX_PERF_MASK | AMD_CPPC_MIN_PERF_MASK | + AMD_CPPC_DES_PERF_MASK | AMD_CPPC_EPP_PERF_MASK); + value |= FIELD_PREP(AMD_CPPC_MAX_PERF_MASK, max_perf); + value |= FIELD_PREP(AMD_CPPC_DES_PERF_MASK, des_perf); + value |= FIELD_PREP(AMD_CPPC_MIN_PERF_MASK, min_perf); + value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp); + + if (value == prev) + return 0; + + if (fast_switch) { + wrmsrl(MSR_AMD_CPPC_REQ, value); + return 0; + } else { + int ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); + + if (ret) + return ret; } - return index; -} + WRITE_ONCE(cpudata->cppc_req_cached, value); + WRITE_ONCE(cpudata->epp_cached, epp); -static void msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf, - u32 des_perf, u32 max_perf, bool fast_switch) -{ - if (fast_switch) - wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached)); - else - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, - READ_ONCE(cpudata->cppc_req_cached)); + return 0; } DEFINE_STATIC_CALL(amd_pstate_update_perf, msr_update_perf); -static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata, +static inline int amd_pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf, u32 des_perf, - u32 max_perf, bool fast_switch) + u32 max_perf, u32 epp, + bool fast_switch) { - static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf, - max_perf, fast_switch); + return static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf, + max_perf, epp, fast_switch); } -static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) +static int msr_set_epp(struct amd_cpudata *cpudata, u32 epp) { + u64 value, prev; int ret; - struct cppc_perf_ctrls perf_ctrls; - if (cpu_feature_enabled(X86_FEATURE_CPPC)) { - u64 value = READ_ONCE(cpudata->cppc_req_cached); + value = prev = READ_ONCE(cpudata->cppc_req_cached); + value &= ~AMD_CPPC_EPP_PERF_MASK; + value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp); - value &= ~GENMASK_ULL(31, 24); - value |= (u64)epp << 24; - WRITE_ONCE(cpudata->cppc_req_cached, value); + if (value == prev) + return 0; - ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); - if (!ret) - cpudata->epp_cached = epp; - } else { - amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U, - cpudata->max_limit_perf, false); - - perf_ctrls.energy_perf = epp; - ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); - if (ret) { - pr_debug("failed to set energy perf value (%d)\n", ret); - return ret; - } - cpudata->epp_cached = epp; + ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); + if (ret) { + pr_err("failed to set energy perf value (%d)\n", ret); + return ret; } + /* update both so that msr_update_perf() can effectively check */ + WRITE_ONCE(cpudata->epp_cached, epp); + WRITE_ONCE(cpudata->cppc_req_cached, value); + return ret; } -static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata, - int pref_index) +DEFINE_STATIC_CALL(amd_pstate_set_epp, msr_set_epp); + +static inline int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) +{ + return static_call(amd_pstate_set_epp)(cpudata, epp); +} + +static int shmem_set_epp(struct amd_cpudata *cpudata, u32 epp) { - int epp = -EINVAL; int ret; + struct cppc_perf_ctrls perf_ctrls; + + if (epp == cpudata->epp_cached) + return 0; + + perf_ctrls.energy_perf = epp; + ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); + if (ret) { + pr_debug("failed to set energy perf value (%d)\n", ret); + return ret; + } + WRITE_ONCE(cpudata->epp_cached, epp); + + return ret; +} + +static int amd_pstate_set_energy_pref_index(struct cpufreq_policy *policy, + int pref_index) +{ + struct amd_cpudata *cpudata = policy->driver_data; + int epp; if (!pref_index) epp = cpudata->epp_default; - - if (epp == -EINVAL) + else epp = epp_values[pref_index]; if (epp > 0 && cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) { @@ -301,9 +332,15 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata, return -EBUSY; } - ret = amd_pstate_set_epp(cpudata, epp); + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, + epp, + FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached), + policy->boost_enabled); + } - return ret; + return amd_pstate_set_epp(cpudata, epp); } static inline int msr_cppc_enable(bool enable) @@ -374,15 +411,19 @@ static inline int amd_pstate_cppc_enable(bool enable) static int msr_init_perf(struct amd_cpudata *cpudata) { - u64 cap1; + u64 cap1, numerator; int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, &cap1); if (ret) return ret; - WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); - WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1)); + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); + if (ret) + return ret; + + WRITE_ONCE(cpudata->highest_perf, numerator); + WRITE_ONCE(cpudata->max_limit_perf, numerator); WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); @@ -394,13 +435,18 @@ static int msr_init_perf(struct amd_cpudata *cpudata) static int shmem_init_perf(struct amd_cpudata *cpudata) { struct cppc_perf_caps cppc_perf; + u64 numerator; int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); if (ret) return ret; - WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf); - WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf); + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); + if (ret) + return ret; + + WRITE_ONCE(cpudata->highest_perf, numerator); + WRITE_ONCE(cpudata->max_limit_perf, numerator); WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); WRITE_ONCE(cpudata->lowest_nonlinear_perf, cppc_perf.lowest_nonlinear_perf); @@ -433,17 +479,23 @@ static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata) return static_call(amd_pstate_init_perf)(cpudata); } -static void shmem_update_perf(struct amd_cpudata *cpudata, - u32 min_perf, u32 des_perf, - u32 max_perf, bool fast_switch) +static int shmem_update_perf(struct amd_cpudata *cpudata, u32 min_perf, + u32 des_perf, u32 max_perf, u32 epp, bool fast_switch) { struct cppc_perf_ctrls perf_ctrls; + if (cppc_state == AMD_PSTATE_ACTIVE) { + int ret = shmem_set_epp(cpudata, epp); + + if (ret) + return ret; + } + perf_ctrls.max_perf = max_perf; perf_ctrls.min_perf = min_perf; perf_ctrls.desired_perf = des_perf; - cppc_set_perf(cpudata->cpu, &perf_ctrls); + return cppc_set_perf(cpudata->cpu, &perf_ctrls); } static inline bool amd_pstate_sample(struct amd_cpudata *cpudata) @@ -484,14 +536,8 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, { unsigned long max_freq; struct cpufreq_policy *policy = cpufreq_cpu_get(cpudata->cpu); - u64 prev = READ_ONCE(cpudata->cppc_req_cached); u32 nominal_perf = READ_ONCE(cpudata->nominal_perf); - u64 value = prev; - min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); - max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); max_freq = READ_ONCE(cpudata->max_limit_freq); @@ -502,34 +548,18 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, des_perf = 0; } - value &= ~AMD_CPPC_MIN_PERF(~0L); - value |= AMD_CPPC_MIN_PERF(min_perf); - - value &= ~AMD_CPPC_DES_PERF(~0L); - value |= AMD_CPPC_DES_PERF(des_perf); - /* limit the max perf when core performance boost feature is disabled */ if (!cpudata->boost_supported) max_perf = min_t(unsigned long, nominal_perf, max_perf); - value &= ~AMD_CPPC_MAX_PERF(~0L); - value |= AMD_CPPC_MAX_PERF(max_perf); - if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) { trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq, cpudata->cur.mperf, cpudata->cur.aperf, cpudata->cur.tsc, - cpudata->cpu, (value != prev), fast_switch); + cpudata->cpu, fast_switch); } - if (value == prev) - goto cpufreq_policy_put; + amd_pstate_update_perf(cpudata, min_perf, des_perf, max_perf, 0, fast_switch); - WRITE_ONCE(cpudata->cppc_req_cached, value); - - amd_pstate_update_perf(cpudata, min_perf, des_perf, - max_perf, fast_switch); - -cpufreq_policy_put: cpufreq_cpu_put(policy); } @@ -561,23 +591,16 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy_data) static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) { - u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf; + u32 max_limit_perf, min_limit_perf, max_perf, max_freq; struct amd_cpudata *cpudata = policy->driver_data; - if (cpudata->boost_supported && !policy->boost_enabled) - max_perf = READ_ONCE(cpudata->nominal_perf); - else - max_perf = READ_ONCE(cpudata->highest_perf); + max_perf = READ_ONCE(cpudata->highest_perf); + max_freq = READ_ONCE(cpudata->max_freq); + max_limit_perf = div_u64(policy->max * max_perf, max_freq); + min_limit_perf = div_u64(policy->min * max_perf, max_freq); - max_limit_perf = div_u64(policy->max * max_perf, policy->cpuinfo.max_freq); - min_limit_perf = div_u64(policy->min * max_perf, policy->cpuinfo.max_freq); - - lowest_perf = READ_ONCE(cpudata->lowest_perf); - if (min_limit_perf < lowest_perf) - min_limit_perf = lowest_perf; - - if (max_limit_perf < min_limit_perf) - max_limit_perf = min_limit_perf; + if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) + min_limit_perf = min(cpudata->nominal_perf, max_limit_perf); WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); @@ -698,8 +721,8 @@ static int amd_pstate_cpu_boost_update(struct cpufreq_policy *policy, bool on) if (on) policy->cpuinfo.max_freq = max_freq; - else if (policy->cpuinfo.max_freq > nominal_freq * 1000) - policy->cpuinfo.max_freq = nominal_freq * 1000; + else if (policy->cpuinfo.max_freq > nominal_freq) + policy->cpuinfo.max_freq = nominal_freq; policy->max = policy->cpuinfo.max_freq; @@ -721,12 +744,11 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) pr_err("Boost mode is not supported by this processor or SBIOS\n"); return -EOPNOTSUPP; } - mutex_lock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); + ret = amd_pstate_cpu_boost_update(policy, state); - WRITE_ONCE(cpudata->boost_state, !ret ? state : false); policy->boost_enabled = !ret ? state : false; refresh_frequency_limits(policy); - mutex_unlock(&amd_pstate_driver_lock); return ret; } @@ -746,9 +768,6 @@ static int amd_pstate_init_boost_support(struct amd_cpudata *cpudata) goto exit_err; } - /* at least one CPU supports CPB, even if others fail later on to set up */ - current_pstate_driver->boost_enabled = true; - ret = rdmsrl_on_cpu(cpudata->cpu, MSR_K7_HWCR, &boost_val); if (ret) { pr_err_once("failed to read initial CPU boost state!\n"); @@ -796,7 +815,7 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) * sched_set_itmt_support(true) has been called and it is valid to * update them at any time after it has been called. */ - sched_set_itmt_core_prio((int)READ_ONCE(cpudata->highest_perf), cpudata->cpu); + sched_set_itmt_core_prio((int)READ_ONCE(cpudata->prefcore_ranking), cpudata->cpu); schedule_work(&sched_prefcore_work); } @@ -817,7 +836,8 @@ static void amd_pstate_update_limits(unsigned int cpu) if (!amd_pstate_prefcore) return; - mutex_lock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); + ret = amd_get_highest_perf(cpu, &cur_high); if (ret) goto free_cpufreq_put; @@ -837,7 +857,6 @@ free_cpufreq_put: if (!highest_perf_changed) cpufreq_update_policy(cpu); - mutex_unlock(&amd_pstate_driver_lock); } /* @@ -889,10 +908,8 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) { int ret; u32 min_freq, max_freq; - u64 numerator; - u32 nominal_perf, nominal_freq; + u32 highest_perf, nominal_perf, nominal_freq; u32 lowest_nonlinear_perf, lowest_nonlinear_freq; - u32 boost_ratio, lowest_nonlinear_ratio; struct cppc_perf_caps cppc_perf; ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); @@ -900,32 +917,25 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) return ret; if (quirks && quirks->lowest_freq) - min_freq = quirks->lowest_freq * 1000; + min_freq = quirks->lowest_freq; else - min_freq = cppc_perf.lowest_freq * 1000; + min_freq = cppc_perf.lowest_freq; if (quirks && quirks->nominal_freq) - nominal_freq = quirks->nominal_freq ; + nominal_freq = quirks->nominal_freq; else nominal_freq = cppc_perf.nominal_freq; + highest_perf = READ_ONCE(cpudata->highest_perf); nominal_perf = READ_ONCE(cpudata->nominal_perf); - - ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); - if (ret) - return ret; - boost_ratio = div_u64(numerator << SCHED_CAPACITY_SHIFT, nominal_perf); - max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000; + max_freq = div_u64((u64)highest_perf * nominal_freq, nominal_perf); lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); - lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT, - nominal_perf); - lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT) * 1000; - - WRITE_ONCE(cpudata->min_freq, min_freq); - WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq); - WRITE_ONCE(cpudata->nominal_freq, nominal_freq); - WRITE_ONCE(cpudata->max_freq, max_freq); + lowest_nonlinear_freq = div_u64((u64)nominal_freq * lowest_nonlinear_perf, nominal_perf); + WRITE_ONCE(cpudata->min_freq, min_freq * 1000); + WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq * 1000); + WRITE_ONCE(cpudata->nominal_freq, nominal_freq * 1000); + WRITE_ONCE(cpudata->max_freq, max_freq * 1000); /** * Below values need to be initialized correctly, otherwise driver will fail to load @@ -935,13 +945,13 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) */ if (min_freq <= 0 || max_freq <= 0 || nominal_freq <= 0 || min_freq > max_freq) { pr_err("min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect\n", - min_freq, max_freq, nominal_freq * 1000); + min_freq, max_freq, nominal_freq); return -EINVAL; } - if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq * 1000) { + if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq) { pr_err("lowest_nonlinear_freq(%d) value is out of range [min_freq(%d), nominal_freq(%d)]\n", - lowest_nonlinear_freq, min_freq, nominal_freq * 1000); + lowest_nonlinear_freq, min_freq, nominal_freq); return -EINVAL; } @@ -1158,7 +1168,6 @@ static ssize_t show_energy_performance_available_preferences( static ssize_t store_energy_performance_preference( struct cpufreq_policy *policy, const char *buf, size_t count) { - struct amd_cpudata *cpudata = policy->driver_data; char str_preference[21]; ssize_t ret; @@ -1170,11 +1179,11 @@ static ssize_t store_energy_performance_preference( if (ret < 0) return -EINVAL; - mutex_lock(&amd_pstate_limits_lock); - ret = amd_pstate_set_energy_pref_index(cpudata, ret); - mutex_unlock(&amd_pstate_limits_lock); + guard(mutex)(&amd_pstate_limits_lock); - return ret ?: count; + ret = amd_pstate_set_energy_pref_index(policy, ret); + + return ret ? ret : count; } static ssize_t show_energy_performance_preference( @@ -1183,9 +1192,22 @@ static ssize_t show_energy_performance_preference( struct amd_cpudata *cpudata = policy->driver_data; int preference; - preference = amd_pstate_get_energy_pref_index(cpudata); - if (preference < 0) - return preference; + switch (cpudata->epp_cached) { + case AMD_CPPC_EPP_PERFORMANCE: + preference = EPP_INDEX_PERFORMANCE; + break; + case AMD_CPPC_EPP_BALANCE_PERFORMANCE: + preference = EPP_INDEX_BALANCE_PERFORMANCE; + break; + case AMD_CPPC_EPP_BALANCE_POWERSAVE: + preference = EPP_INDEX_BALANCE_POWERSAVE; + break; + case AMD_CPPC_EPP_POWERSAVE: + preference = EPP_INDEX_POWERSAVE; + break; + default: + return -EINVAL; + } return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]); } @@ -1234,6 +1256,9 @@ static int amd_pstate_register_driver(int mode) return ret; } + /* at least one CPU supports CPB */ + current_pstate_driver->boost_enabled = cpu_feature_enabled(X86_FEATURE_CPB); + ret = cpufreq_register_driver(current_pstate_driver); if (ret) { amd_pstate_driver_cleanup(); @@ -1338,13 +1363,10 @@ EXPORT_SYMBOL_GPL(amd_pstate_update_status); static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *buf) { - ssize_t ret; - mutex_lock(&amd_pstate_driver_lock); - ret = amd_pstate_show_status(buf); - mutex_unlock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); - return ret; + return amd_pstate_show_status(buf); } static ssize_t status_store(struct device *a, struct device_attribute *b, @@ -1353,9 +1375,8 @@ static ssize_t status_store(struct device *a, struct device_attribute *b, char *p = memchr(buf, '\n', count); int ret; - mutex_lock(&amd_pstate_driver_lock); + guard(mutex)(&amd_pstate_driver_lock); ret = amd_pstate_update_status(buf, p ? p - buf : count); - mutex_unlock(&amd_pstate_driver_lock); return ret < 0 ? ret : count; } @@ -1449,7 +1470,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) return -ENOMEM; cpudata->cpu = policy->cpu; - cpudata->epp_policy = 0; ret = amd_pstate_init_perf(cpudata); if (ret) @@ -1475,8 +1495,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) policy->driver_data = cpudata; - cpudata->epp_cached = cpudata->epp_default = amd_pstate_get_epp(cpudata, 0); - policy->min = policy->cpuinfo.min_freq; policy->max = policy->cpuinfo.max_freq; @@ -1487,10 +1505,13 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) * the default cpufreq governor is neither powersave nor performance. */ if (amd_pstate_acpi_pm_profile_server() || - amd_pstate_acpi_pm_profile_undefined()) + amd_pstate_acpi_pm_profile_undefined()) { policy->policy = CPUFREQ_POLICY_PERFORMANCE; - else + cpudata->epp_default = amd_pstate_get_epp(cpudata); + } else { policy->policy = CPUFREQ_POLICY_POWERSAVE; + cpudata->epp_default = AMD_CPPC_EPP_BALANCE_PERFORMANCE; + } if (cpu_feature_enabled(X86_FEATURE_CPPC)) { ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value); @@ -1503,6 +1524,9 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) return ret; WRITE_ONCE(cpudata->cppc_cap1_cached, value); } + ret = amd_pstate_set_epp(cpudata, cpudata->epp_default); + if (ret) + return ret; current_pstate_driver->adjust_perf = NULL; @@ -1528,51 +1552,24 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; - u32 max_perf, min_perf; - u64 value; - s16 epp; + u32 epp; - max_perf = READ_ONCE(cpudata->highest_perf); - min_perf = READ_ONCE(cpudata->lowest_perf); amd_pstate_update_min_max_limit(policy); - max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); - min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, - cpudata->max_limit_perf); - value = READ_ONCE(cpudata->cppc_req_cached); - - if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) - min_perf = min(cpudata->nominal_perf, max_perf); - - /* Initial min/max values for CPPC Performance Controls Register */ - value &= ~AMD_CPPC_MIN_PERF(~0L); - value |= AMD_CPPC_MIN_PERF(min_perf); - - value &= ~AMD_CPPC_MAX_PERF(~0L); - value |= AMD_CPPC_MAX_PERF(max_perf); - - /* CPPC EPP feature require to set zero to the desire perf bit */ - value &= ~AMD_CPPC_DES_PERF(~0L); - value |= AMD_CPPC_DES_PERF(0); - - cpudata->epp_policy = cpudata->policy; - - /* Get BIOS pre-defined epp value */ - epp = amd_pstate_get_epp(cpudata, value); - if (epp < 0) { - /** - * This return value can only be negative for shared_memory - * systems where EPP register read/write not supported. - */ - return epp; - } - if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) epp = 0; + else + epp = READ_ONCE(cpudata->epp_cached); - WRITE_ONCE(cpudata->cppc_req_cached, value); - return amd_pstate_set_epp(cpudata, epp); + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, epp, + cpudata->min_limit_perf, + cpudata->max_limit_perf, + policy->boost_enabled); + } + + return amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U, + cpudata->max_limit_perf, epp, false); } static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) @@ -1601,87 +1598,63 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) return 0; } -static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata) +static int amd_pstate_epp_reenable(struct cpufreq_policy *policy) { - struct cppc_perf_ctrls perf_ctrls; - u64 value, max_perf; + struct amd_cpudata *cpudata = policy->driver_data; + u64 max_perf; int ret; ret = amd_pstate_cppc_enable(true); if (ret) pr_err("failed to enable amd pstate during resume, return %d\n", ret); - value = READ_ONCE(cpudata->cppc_req_cached); max_perf = READ_ONCE(cpudata->highest_perf); - if (cpu_feature_enabled(X86_FEATURE_CPPC)) { - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); - } else { - perf_ctrls.max_perf = max_perf; - cppc_set_perf(cpudata->cpu, &perf_ctrls); - perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(cpudata->epp_cached); - cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, + cpudata->epp_cached, + FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cpudata->cppc_req_cached), + max_perf, policy->boost_enabled); } + + return amd_pstate_update_perf(cpudata, 0, 0, max_perf, cpudata->epp_cached, false); } static int amd_pstate_epp_cpu_online(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; + int ret; pr_debug("AMD CPU Core %d going online\n", cpudata->cpu); - if (cppc_state == AMD_PSTATE_ACTIVE) { - amd_pstate_epp_reenable(cpudata); - cpudata->suspended = false; - } + ret = amd_pstate_epp_reenable(policy); + if (ret) + return ret; + cpudata->suspended = false; return 0; } -static void amd_pstate_epp_offline(struct cpufreq_policy *policy) -{ - struct amd_cpudata *cpudata = policy->driver_data; - struct cppc_perf_ctrls perf_ctrls; - int min_perf; - u64 value; - - min_perf = READ_ONCE(cpudata->lowest_perf); - value = READ_ONCE(cpudata->cppc_req_cached); - - mutex_lock(&amd_pstate_limits_lock); - if (cpu_feature_enabled(X86_FEATURE_CPPC)) { - cpudata->epp_policy = CPUFREQ_POLICY_UNKNOWN; - - /* Set max perf same as min perf */ - value &= ~AMD_CPPC_MAX_PERF(~0L); - value |= AMD_CPPC_MAX_PERF(min_perf); - value &= ~AMD_CPPC_MIN_PERF(~0L); - value |= AMD_CPPC_MIN_PERF(min_perf); - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); - } else { - perf_ctrls.desired_perf = 0; - perf_ctrls.min_perf = min_perf; - perf_ctrls.max_perf = min_perf; - cppc_set_perf(cpudata->cpu, &perf_ctrls); - perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(HWP_EPP_BALANCE_POWERSAVE); - cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); - } - mutex_unlock(&amd_pstate_limits_lock); -} - static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy) { struct amd_cpudata *cpudata = policy->driver_data; - - pr_debug("AMD CPU Core %d going offline\n", cpudata->cpu); + int min_perf; if (cpudata->suspended) return 0; - if (cppc_state == AMD_PSTATE_ACTIVE) - amd_pstate_epp_offline(policy); + min_perf = READ_ONCE(cpudata->lowest_perf); - return 0; + guard(mutex)(&amd_pstate_limits_lock); + + if (trace_amd_pstate_epp_perf_enabled()) { + trace_amd_pstate_epp_perf(cpudata->cpu, cpudata->highest_perf, + AMD_CPPC_EPP_BALANCE_POWERSAVE, + min_perf, min_perf, policy->boost_enabled); + } + + return amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, + AMD_CPPC_EPP_BALANCE_POWERSAVE, false); } static int amd_pstate_epp_suspend(struct cpufreq_policy *policy) @@ -1709,12 +1682,10 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy) struct amd_cpudata *cpudata = policy->driver_data; if (cpudata->suspended) { - mutex_lock(&amd_pstate_limits_lock); + guard(mutex)(&amd_pstate_limits_lock); /* enable amd pstate from suspend state*/ - amd_pstate_epp_reenable(cpudata); - - mutex_unlock(&amd_pstate_limits_lock); + amd_pstate_epp_reenable(policy); cpudata->suspended = false; } @@ -1867,12 +1838,8 @@ static int __init amd_pstate_init(void) static_call_update(amd_pstate_cppc_enable, shmem_cppc_enable); static_call_update(amd_pstate_init_perf, shmem_init_perf); static_call_update(amd_pstate_update_perf, shmem_update_perf); - } - - ret = amd_pstate_register_driver(cppc_state); - if (ret) { - pr_err("failed to register with return %d\n", ret); - return ret; + static_call_update(amd_pstate_get_epp, shmem_get_epp); + static_call_update(amd_pstate_set_epp, shmem_set_epp); } if (amd_pstate_prefcore) { @@ -1881,6 +1848,12 @@ static int __init amd_pstate_init(void) return ret; } + ret = amd_pstate_register_driver(cppc_state); + if (ret) { + pr_err("failed to register with return %d\n", ret); + return ret; + } + dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &amd_pstate_global_attr_group); diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h index cd573bc6b6db..9747e3be6cee 100644 --- a/drivers/cpufreq/amd-pstate.h +++ b/drivers/cpufreq/amd-pstate.h @@ -57,7 +57,6 @@ struct amd_aperf_mperf { * @hw_prefcore: check whether HW supports preferred core featue. * Only when hw_prefcore and early prefcore param are true, * AMD P-State driver supports preferred core featue. - * @epp_policy: Last saved policy used to set energy-performance preference * @epp_cached: Cached CPPC energy-performance preference value * @policy: Cpufreq policy value * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value @@ -94,13 +93,11 @@ struct amd_cpudata { bool hw_prefcore; /* EPP feature related attributes*/ - s16 epp_policy; s16 epp_cached; u32 policy; u64 cppc_cap1_cached; bool suspended; s16 epp_default; - bool boost_state; }; /* diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c index 4dcacab9b4bf..269b18c62d04 100644 --- a/drivers/cpufreq/apple-soc-cpufreq.c +++ b/drivers/cpufreq/apple-soc-cpufreq.c @@ -22,11 +22,14 @@ #include #include -#define APPLE_DVFS_CMD 0x20 -#define APPLE_DVFS_CMD_BUSY BIT(31) -#define APPLE_DVFS_CMD_SET BIT(25) -#define APPLE_DVFS_CMD_PS2 GENMASK(16, 12) -#define APPLE_DVFS_CMD_PS1 GENMASK(4, 0) +#define APPLE_DVFS_CMD 0x20 +#define APPLE_DVFS_CMD_BUSY BIT(31) +#define APPLE_DVFS_CMD_SET BIT(25) +#define APPLE_DVFS_CMD_PS1_S5L8960X GENMASK(24, 22) +#define APPLE_DVFS_CMD_PS1_S5L8960X_SHIFT 22 +#define APPLE_DVFS_CMD_PS2 GENMASK(15, 12) +#define APPLE_DVFS_CMD_PS1 GENMASK(4, 0) +#define APPLE_DVFS_CMD_PS1_SHIFT 0 /* Same timebase as CPU counter (24MHz) */ #define APPLE_DVFS_LAST_CHG_TIME 0x38 @@ -35,6 +38,9 @@ * Apple ran out of bits and had to shift this in T8112... */ #define APPLE_DVFS_STATUS 0x50 +#define APPLE_DVFS_STATUS_CUR_PS_S5L8960X GENMASK(5, 3) +#define APPLE_DVFS_STATUS_CUR_PS_SHIFT_S5L8960X 3 +#define APPLE_DVFS_STATUS_TGT_PS_S5L8960X GENMASK(2, 0) #define APPLE_DVFS_STATUS_CUR_PS_T8103 GENMASK(7, 4) #define APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8103 4 #define APPLE_DVFS_STATUS_TGT_PS_T8103 GENMASK(3, 0) @@ -52,12 +58,15 @@ #define APPLE_DVFS_PLL_FACTOR_MULT GENMASK(31, 16) #define APPLE_DVFS_PLL_FACTOR_DIV GENMASK(15, 0) -#define APPLE_DVFS_TRANSITION_TIMEOUT 100 +#define APPLE_DVFS_TRANSITION_TIMEOUT 400 struct apple_soc_cpufreq_info { + bool has_ps2; u64 max_pstate; u64 cur_pstate_mask; u64 cur_pstate_shift; + u64 ps1_mask; + u64 ps1_shift; }; struct apple_cpu_priv { @@ -68,24 +77,46 @@ struct apple_cpu_priv { static struct cpufreq_driver apple_soc_cpufreq_driver; +static const struct apple_soc_cpufreq_info soc_s5l8960x_info = { + .has_ps2 = false, + .max_pstate = 7, + .cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_S5L8960X, + .cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_S5L8960X, + .ps1_mask = APPLE_DVFS_CMD_PS1_S5L8960X, + .ps1_shift = APPLE_DVFS_CMD_PS1_S5L8960X_SHIFT, +}; + static const struct apple_soc_cpufreq_info soc_t8103_info = { + .has_ps2 = true, .max_pstate = 15, .cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_T8103, .cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8103, + .ps1_mask = APPLE_DVFS_CMD_PS1, + .ps1_shift = APPLE_DVFS_CMD_PS1_SHIFT, }; static const struct apple_soc_cpufreq_info soc_t8112_info = { + .has_ps2 = false, .max_pstate = 31, .cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_T8112, .cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8112, + .ps1_mask = APPLE_DVFS_CMD_PS1, + .ps1_shift = APPLE_DVFS_CMD_PS1_SHIFT, }; static const struct apple_soc_cpufreq_info soc_default_info = { + .has_ps2 = false, .max_pstate = 15, .cur_pstate_mask = 0, /* fallback */ + .ps1_mask = APPLE_DVFS_CMD_PS1, + .ps1_shift = APPLE_DVFS_CMD_PS1_SHIFT, }; static const struct of_device_id apple_soc_cpufreq_of_match[] __maybe_unused = { + { + .compatible = "apple,s5l8960x-cluster-cpufreq", + .data = &soc_s5l8960x_info, + }, { .compatible = "apple,t8103-cluster-cpufreq", .data = &soc_t8103_info, @@ -109,7 +140,7 @@ static unsigned int apple_soc_cpufreq_get_rate(unsigned int cpu) unsigned int pstate; if (priv->info->cur_pstate_mask) { - u64 reg = readq_relaxed(priv->reg_base + APPLE_DVFS_STATUS); + u32 reg = readl_relaxed(priv->reg_base + APPLE_DVFS_STATUS); pstate = (reg & priv->info->cur_pstate_mask) >> priv->info->cur_pstate_shift; } else { @@ -148,9 +179,12 @@ static int apple_soc_cpufreq_set_target(struct cpufreq_policy *policy, return -EIO; } - reg &= ~(APPLE_DVFS_CMD_PS1 | APPLE_DVFS_CMD_PS2); - reg |= FIELD_PREP(APPLE_DVFS_CMD_PS1, pstate); - reg |= FIELD_PREP(APPLE_DVFS_CMD_PS2, pstate); + reg &= ~priv->info->ps1_mask; + reg |= pstate << priv->info->ps1_shift; + if (priv->info->has_ps2) { + reg &= ~APPLE_DVFS_CMD_PS2; + reg |= FIELD_PREP(APPLE_DVFS_CMD_PS2, pstate); + } reg |= APPLE_DVFS_CMD_SET; writeq_relaxed(reg, priv->reg_base + APPLE_DVFS_CMD); @@ -275,7 +309,7 @@ static int apple_soc_cpufreq_init(struct cpufreq_policy *policy) transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev); if (!transition_latency) - transition_latency = CPUFREQ_ETERNAL; + transition_latency = APPLE_DVFS_TRANSITION_TIMEOUT * NSEC_PER_USEC; policy->cpuinfo.transition_latency = transition_latency; policy->dvfs_possible_from_any_cpu = true; diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index bd8f75accfa0..8f512448382f 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -225,7 +225,7 @@ static void __init cppc_freq_invariance_init(void) if (fie_disabled) return; - kworker_fie = kthread_create_worker(0, "cppc_fie"); + kworker_fie = kthread_run_worker(0, "cppc_fie"); if (IS_ERR(kworker_fie)) { pr_warn("%s: failed to create kworker_fie: %ld\n", __func__, PTR_ERR(kworker_fie)); @@ -611,7 +611,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * Section 8.4.7.1.1.5 of ACPI 6.1 spec) */ policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf); - policy->max = cppc_perf_to_khz(caps, caps->nominal_perf); + policy->max = cppc_perf_to_khz(caps, policy->boost_enabled ? + caps->highest_perf : caps->nominal_perf); /* * Set cpuinfo.min_freq to Lowest to make the full range of performance @@ -619,7 +620,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * nonlinear perf */ policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf); - policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf); + policy->cpuinfo.max_freq = policy->max; policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu); policy->shared_type = cpu_data->shared_type; diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 2a3e8bd317c9..2aa00769cf09 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -103,6 +103,8 @@ static const struct of_device_id allowlist[] __initconst = { * platforms using "operating-points-v2" property. */ static const struct of_device_id blocklist[] __initconst = { + { .compatible = "airoha,en7581", }, + { .compatible = "allwinner,sun50i-a100" }, { .compatible = "allwinner,sun50i-h6", }, { .compatible = "allwinner,sun50i-h616", }, @@ -235,5 +237,3 @@ create_pdev: sizeof(struct cpufreq_dt_platform_data))); } core_initcall(cpufreq_dt_platdev_init); -MODULE_DESCRIPTION("Generic DT based cpufreq platdev driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 1a4cae54a01b..e0048856ecee 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -602,12 +603,12 @@ static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr, if (cpufreq_boost_trigger_state(enable)) { pr_err("%s: Cannot %s BOOST!\n", - __func__, enable ? "enable" : "disable"); + __func__, str_enable_disable(enable)); return -EINVAL; } pr_debug("%s: cpufreq BOOST %s\n", - __func__, enable ? "enabled" : "disabled"); + __func__, str_enabled_disabled(enable)); return count; } @@ -1409,10 +1410,6 @@ static int cpufreq_online(unsigned int cpu) goto out_free_policy; } - /* Let the per-policy boost flag mirror the cpufreq_driver boost during init */ - if (cpufreq_boost_enabled() && policy_has_boost_freq(policy)) - policy->boost_enabled = true; - /* * The initialization has succeeded and the policy is online. * If there is a problem with its frequency table, take it @@ -1475,6 +1472,10 @@ static int cpufreq_online(unsigned int cpu) blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_CREATE_POLICY, policy); + } else { + ret = freq_qos_update_request(policy->max_freq_req, policy->max); + if (ret < 0) + goto out_destroy_policy; } if (cpufreq_driver->get && has_target()) { @@ -1538,7 +1539,7 @@ static int cpufreq_online(unsigned int cpu) /* * Register with the energy model before - * sugov_eas_rebuild_sd() is called, which will result + * em_rebuild_sched_domains() is called, which will result * in rebuilding of the sched domains, which should only be done * once the energy model is properly initialized for the policy * first. @@ -1569,6 +1570,18 @@ static int cpufreq_online(unsigned int cpu) if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); + /* Let the per-policy boost flag mirror the cpufreq_driver boost during init */ + if (policy->boost_enabled != cpufreq_boost_enabled()) { + policy->boost_enabled = cpufreq_boost_enabled(); + ret = cpufreq_driver->set_boost(policy, policy->boost_enabled); + if (ret) { + /* If the set_boost fails, the online operation is not affected */ + pr_info("%s: CPU%d: Cannot %s BOOST\n", __func__, policy->cpu, + policy->boost_enabled ? "enable" : "disable"); + policy->boost_enabled = !policy->boost_enabled; + } + } + pr_debug("initialization complete\n"); return 0; @@ -2812,7 +2825,7 @@ err_reset_state: write_unlock_irqrestore(&cpufreq_driver_lock, flags); pr_err("%s: Cannot %s BOOST\n", - __func__, state ? "enable" : "disable"); + __func__, str_enable_disable(state)); return ret; } diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b8e2396a708a..9c4cc01fd51a 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -302,11 +303,11 @@ static bool hwp_is_hybrid; static struct cpufreq_driver *intel_pstate_driver __read_mostly; -#define HYBRID_SCALING_FACTOR 78741 +#define HYBRID_SCALING_FACTOR_ADL 78741 #define HYBRID_SCALING_FACTOR_MTL 80000 #define HYBRID_SCALING_FACTOR_LNL 86957 -static int hybrid_scaling_factor = HYBRID_SCALING_FACTOR; +static int hybrid_scaling_factor; static inline int core_get_scaling(void) { @@ -414,18 +415,15 @@ static int intel_pstate_get_cppc_guaranteed(int cpu) static int intel_pstate_cppc_get_scaling(int cpu) { struct cppc_perf_caps cppc_perf; - int ret; - - ret = cppc_get_perf_caps(cpu, &cppc_perf); /* - * If the nominal frequency and the nominal performance are not - * zero and the ratio between them is not 100, return the hybrid - * scaling factor. + * Compute the perf-to-frequency scaling factor for the given CPU if + * possible, unless it would be 0. */ - if (!ret && cppc_perf.nominal_perf && cppc_perf.nominal_freq && - cppc_perf.nominal_perf * 100 != cppc_perf.nominal_freq) - return hybrid_scaling_factor; + if (!cppc_get_perf_caps(cpu, &cppc_perf) && + cppc_perf.nominal_perf && cppc_perf.nominal_freq) + return div_u64(cppc_perf.nominal_freq * KHZ_PER_MHZ, + cppc_perf.nominal_perf); return core_get_scaling(); } @@ -2211,24 +2209,30 @@ static void hybrid_get_type(void *data) static int hwp_get_cpu_scaling(int cpu) { - u8 cpu_type = 0; + if (hybrid_scaling_factor) { + u8 cpu_type = 0; - smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1); - /* P-cores have a smaller perf level-to-freqency scaling factor. */ - if (cpu_type == 0x40) - return hybrid_scaling_factor; + smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1); - /* Use default core scaling for E-cores */ - if (cpu_type == 0x20) + /* + * Return the hybrid scaling factor for P-cores and use the + * default core scaling for E-cores. + */ + if (cpu_type == 0x40) + return hybrid_scaling_factor; + + if (cpu_type == 0x20) + return core_get_scaling(); + } + + /* Use core scaling on non-hybrid systems. */ + if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) return core_get_scaling(); /* - * If reached here, this system is either non-hybrid (like Tiger - * Lake) or hybrid-capable (like Alder Lake or Raptor Lake) with - * no E cores (in which case CPUID for hybrid support is 0). - * - * The CPPC nominal_frequency field is 0 for non-hybrid systems, - * so the default core scaling will be used for them. + * The system is hybrid, but the hybrid scaling factor is not known or + * the CPU type is not one of the above, so use CPPC to compute the + * scaling factor for this CPU. */ return intel_pstate_cppc_get_scaling(cpu); } @@ -2709,7 +2713,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum) } cpu->epp_powersave = -EINVAL; - cpu->epp_policy = 0; + cpu->epp_policy = CPUFREQ_POLICY_UNKNOWN; intel_pstate_get_cpu_pstates(cpu); @@ -3665,8 +3669,12 @@ static const struct x86_cpu_id intel_epp_default[] = { }; static const struct x86_cpu_id intel_hybrid_scaling_factor[] = { + X86_MATCH_VFM(INTEL_ALDERLAKE, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_ALDERLAKE_L, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_RAPTORLAKE, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_RAPTORLAKE_P, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_RAPTORLAKE_S, HYBRID_SCALING_FACTOR_ADL), X86_MATCH_VFM(INTEL_METEORLAKE_L, HYBRID_SCALING_FACTOR_MTL), - X86_MATCH_VFM(INTEL_ARROWLAKE, HYBRID_SCALING_FACTOR_MTL), X86_MATCH_VFM(INTEL_LUNARLAKE_M, HYBRID_SCALING_FACTOR_LNL), {} }; diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 8de759247771..ae79d909943b 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -281,7 +282,7 @@ next: pr_info("cpufreq pstate min 0x%x nominal 0x%x max 0x%x\n", pstate_min, pstate_nominal, pstate_max); pr_info("Workload Optimized Frequency is %s in the platform\n", - (powernv_pstate_info.wof_enabled) ? "enabled" : "disabled"); + str_enabled_disabled(powernv_pstate_info.wof_enabled)); pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids); if (!pstate_ids) { diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 98129565acb8..b2e7e89feaac 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -143,14 +143,12 @@ static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) } /* Get the frequency requested by the cpufreq core for the CPU */ -static unsigned int qcom_cpufreq_get_freq(unsigned int cpu) +static unsigned int qcom_cpufreq_get_freq(struct cpufreq_policy *policy) { struct qcom_cpufreq_data *data; const struct qcom_cpufreq_soc_data *soc_data; - struct cpufreq_policy *policy; unsigned int index; - policy = cpufreq_cpu_get_raw(cpu); if (!policy) return 0; @@ -163,12 +161,10 @@ static unsigned int qcom_cpufreq_get_freq(unsigned int cpu) return policy->freq_table[index].frequency; } -static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) +static unsigned int __qcom_cpufreq_hw_get(struct cpufreq_policy *policy) { struct qcom_cpufreq_data *data; - struct cpufreq_policy *policy; - policy = cpufreq_cpu_get_raw(cpu); if (!policy) return 0; @@ -177,7 +173,12 @@ static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) if (data->throttle_irq >= 0) return qcom_lmh_get_throttle_freq(data) / HZ_PER_KHZ; - return qcom_cpufreq_get_freq(cpu); + return qcom_cpufreq_get_freq(policy); +} + +static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) +{ + return __qcom_cpufreq_hw_get(cpufreq_cpu_get_raw(cpu)); } static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy, @@ -363,7 +364,7 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) * If h/w throttled frequency is higher than what cpufreq has requested * for, then stop polling and switch back to interrupt mechanism. */ - if (throttled_freq >= qcom_cpufreq_get_freq(cpu)) + if (throttled_freq >= qcom_cpufreq_get_freq(cpufreq_cpu_get_raw(cpu))) enable_irq(data->throttle_irq); else mod_delayed_work(system_highpri_wq, &data->throttle_work, @@ -441,7 +442,6 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) return data->throttle_irq; data->cancel_throttle = false; - data->policy = policy; mutex_init(&data->throttle_lock); INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll); @@ -552,6 +552,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) policy->driver_data = data; policy->dvfs_possible_from_any_cpu = true; + data->policy = policy; ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy); if (ret) { @@ -622,11 +623,24 @@ static unsigned long qcom_cpufreq_hw_recalc_rate(struct clk_hw *hw, unsigned lon { struct qcom_cpufreq_data *data = container_of(hw, struct qcom_cpufreq_data, cpu_clk); - return qcom_lmh_get_throttle_freq(data); + return __qcom_cpufreq_hw_get(data->policy) * HZ_PER_KHZ; +} + +/* + * Since we cannot determine the closest rate of the target rate, let's just + * return the actual rate at which the clock is running at. This is needed to + * make clk_set_rate() API work properly. + */ +static int qcom_cpufreq_hw_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) +{ + req->rate = qcom_cpufreq_hw_recalc_rate(hw, 0); + + return 0; } static const struct clk_ops qcom_cpufreq_hw_clk_ops = { .recalc_rate = qcom_cpufreq_hw_recalc_rate, + .determine_rate = qcom_cpufreq_hw_determine_rate, }; static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c index c6bdfc308e99..9cef71528076 100644 --- a/drivers/cpufreq/s3c64xx-cpufreq.c +++ b/drivers/cpufreq/s3c64xx-cpufreq.c @@ -24,6 +24,7 @@ struct s3c64xx_dvfs { unsigned int vddarm_max; }; +#ifdef CONFIG_REGULATOR static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = { [0] = { 1000000, 1150000 }, [1] = { 1050000, 1150000 }, @@ -31,6 +32,7 @@ static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = { [3] = { 1200000, 1350000 }, [4] = { 1300000, 1350000 }, }; +#endif static struct cpufreq_frequency_table s3c64xx_freq_table[] = { { 0, 0, 66000 }, @@ -51,15 +53,16 @@ static struct cpufreq_frequency_table s3c64xx_freq_table[] = { static int s3c64xx_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index) { - struct s3c64xx_dvfs *dvfs; - unsigned int old_freq, new_freq; + unsigned int new_freq = s3c64xx_freq_table[index].frequency; int ret; +#ifdef CONFIG_REGULATOR + struct s3c64xx_dvfs *dvfs; + unsigned int old_freq; + old_freq = clk_get_rate(policy->clk) / 1000; - new_freq = s3c64xx_freq_table[index].frequency; dvfs = &s3c64xx_dvfs_table[s3c64xx_freq_table[index].driver_data]; -#ifdef CONFIG_REGULATOR if (vddarm && new_freq > old_freq) { ret = regulator_set_voltage(vddarm, dvfs->vddarm_min, diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 07d6f9a9b7c8..b8fe758aeb01 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -26,6 +27,8 @@ struct scmi_data { int nr_opp; struct device *cpu_dev; cpumask_var_t opp_shared_cpus; + struct notifier_block limit_notify_nb; + struct freq_qos_request limits_freq_req; }; static struct scmi_protocol_handle *ph; @@ -174,6 +177,22 @@ static struct freq_attr *scmi_cpufreq_hw_attr[] = { NULL, }; +static int scmi_limit_notify_cb(struct notifier_block *nb, unsigned long event, void *data) +{ + struct scmi_data *priv = container_of(nb, struct scmi_data, limit_notify_nb); + struct scmi_perf_limits_report *limit_notify = data; + unsigned int limit_freq_khz; + int ret; + + limit_freq_khz = limit_notify->range_max_freq / HZ_PER_KHZ; + + ret = freq_qos_update_request(&priv->limits_freq_req, limit_freq_khz); + if (ret < 0) + pr_warn("failed to update freq constraint: %d\n", ret); + + return NOTIFY_OK; +} + static int scmi_cpufreq_init(struct cpufreq_policy *policy) { int ret, nr_opp, domain; @@ -181,6 +200,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) struct device *cpu_dev; struct scmi_data *priv; struct cpufreq_frequency_table *freq_table; + struct scmi_device *sdev = cpufreq_get_driver_data(); cpu_dev = get_cpu_device(policy->cpu); if (!cpu_dev) { @@ -294,6 +314,23 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) } } + ret = freq_qos_add_request(&policy->constraints, &priv->limits_freq_req, FREQ_QOS_MAX, + FREQ_QOS_MAX_DEFAULT_VALUE); + if (ret < 0) { + dev_err(cpu_dev, "failed to add qos limits request: %d\n", ret); + goto out_free_table; + } + + priv->limit_notify_nb.notifier_call = scmi_limit_notify_cb; + ret = sdev->handle->notify_ops->event_notifier_register(sdev->handle, SCMI_PROTOCOL_PERF, + SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED, + &priv->domain_id, + &priv->limit_notify_nb); + if (ret) + dev_warn(&sdev->dev, + "failed to register for limits change notifier for domain %d\n", + priv->domain_id); + return 0; out_free_table: @@ -313,7 +350,13 @@ out_free_priv: static void scmi_cpufreq_exit(struct cpufreq_policy *policy) { struct scmi_data *priv = policy->driver_data; + struct scmi_device *sdev = cpufreq_get_driver_data(); + sdev->handle->notify_ops->event_notifier_unregister(sdev->handle, SCMI_PROTOCOL_PERF, + SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED, + &priv->domain_id, + &priv->limit_notify_nb); + freq_qos_remove_request(&priv->limits_freq_req); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); dev_pm_opp_remove_all_dynamic(priv->cpu_dev); free_cpumask_var(priv->opp_shared_cpus); @@ -372,6 +415,8 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev) if (!handle) return -ENODEV; + scmi_cpufreq_driver.driver_data = sdev; + perf_ops = handle->devm_protocol_get(sdev, SCMI_PROTOCOL_PERF, &ph); if (IS_ERR(perf_ops)) return PTR_ERR(perf_ops); diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c index 8a0cd5312a59..15899dd77c08 100644 --- a/drivers/cpufreq/sparc-us2e-cpufreq.c +++ b/drivers/cpufreq/sparc-us2e-cpufreq.c @@ -323,7 +323,7 @@ static int __init us2e_freq_init(void) impl = ((ver >> 32) & 0xffff); if (manuf == 0x17 && impl == 0x13) { - us2e_freq_table = kzalloc(NR_CPUS * sizeof(*us2e_freq_table), + us2e_freq_table = kcalloc(NR_CPUS, sizeof(*us2e_freq_table), GFP_KERNEL); if (!us2e_freq_table) return -ENOMEM; diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c index b50f9d13e6d2..de50a2f3b124 100644 --- a/drivers/cpufreq/sparc-us3-cpufreq.c +++ b/drivers/cpufreq/sparc-us3-cpufreq.c @@ -171,7 +171,7 @@ static int __init us3_freq_init(void) impl == CHEETAH_PLUS_IMPL || impl == JAGUAR_IMPL || impl == PANTHER_IMPL)) { - us3_freq_table = kzalloc(NR_CPUS * sizeof(*us3_freq_table), + us3_freq_table = kcalloc(NR_CPUS, sizeof(*us3_freq_table), GFP_KERNEL); if (!us3_freq_table) return -ENOMEM; diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c index 146f97068022..5fb5228f6bf1 100644 --- a/drivers/cpuidle/cpuidle-psci-domain.c +++ b/drivers/cpuidle/cpuidle-psci-domain.c @@ -72,6 +72,7 @@ static int psci_pd_init(struct device_node *np, bool use_osi) */ if (use_osi) { pd->power_off = psci_pd_power_off; + pd->flags |= GENPD_FLAG_ACTIVE_WAKEUP; if (IS_ENABLED(CONFIG_PREEMPT_RT)) pd->flags |= GENPD_FLAG_RPM_ALWAYS_ON; } else { diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index 14462c092039..0c92a628bbd4 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -504,12 +504,12 @@ static int sbi_cpuidle_probe(struct platform_device *pdev) int cpu, ret; struct cpuidle_driver *drv; struct cpuidle_device *dev; - struct device_node *np, *pds_node; + struct device_node *pds_node; /* Detect OSI support based on CPU DT nodes */ sbi_cpuidle_use_osi = true; for_each_possible_cpu(cpu) { - np = of_cpu_device_node_get(cpu); + struct device_node *np __free(device_node) = of_cpu_device_node_get(cpu); if (np && of_property_present(np, "power-domains") && of_property_present(np, "power-domain-names")) { diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index f2992f92d8db..8fe5e1b47ef9 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -10,25 +10,27 @@ * DOC: teo-description * * The idea of this governor is based on the observation that on many systems - * timer events are two or more orders of magnitude more frequent than any - * other interrupts, so they are likely to be the most significant cause of CPU - * wakeups from idle states. Moreover, information about what happened in the - * (relatively recent) past can be used to estimate whether or not the deepest - * idle state with target residency within the (known) time till the closest - * timer event, referred to as the sleep length, is likely to be suitable for - * the upcoming CPU idle period and, if not, then which of the shallower idle - * states to choose instead of it. + * timer interrupts are two or more orders of magnitude more frequent than any + * other interrupt types, so they are likely to dominate CPU wakeup patterns. + * Moreover, in principle, the time when the next timer event is going to occur + * can be determined at the idle state selection time, although doing that may + * be costly, so it can be regarded as the most reliable source of information + * for idle state selection. * - * Of course, non-timer wakeup sources are more important in some use cases - * which can be covered by taking a few most recent idle time intervals of the - * CPU into account. However, even in that context it is not necessary to - * consider idle duration values greater than the sleep length, because the - * closest timer will ultimately wake up the CPU anyway unless it is woken up - * earlier. + * Of course, non-timer wakeup sources are more important in some use cases, + * but even then it is generally unnecessary to consider idle duration values + * greater than the time time till the next timer event, referred as the sleep + * length in what follows, because the closest timer will ultimately wake up the + * CPU anyway unless it is woken up earlier. * - * Thus this governor estimates whether or not the prospective idle duration of - * a CPU is likely to be significantly shorter than the sleep length and selects - * an idle state for it accordingly. + * However, since obtaining the sleep length may be costly, the governor first + * checks if it can select a shallow idle state using wakeup pattern information + * from recent times, in which case it can do without knowing the sleep length + * at all. For this purpose, it counts CPU wakeup events and looks for an idle + * state whose target residency has not exceeded the idle duration (measured + * after wakeup) in the majority of relevant recent cases. If the target + * residency of that state is small enough, it may be used right away and the + * sleep length need not be determined. * * The computations carried out by this governor are based on using bins whose * boundaries are aligned with the target residency parameter values of the CPU @@ -49,47 +51,50 @@ * sleep length and the idle duration measured after CPU wakeup fall into the * same bin (that is, the CPU appears to wake up "on time" relative to the sleep * length). In turn, the "intercepts" metric reflects the relative frequency of - * situations in which the measured idle duration is so much shorter than the - * sleep length that the bin it falls into corresponds to an idle state - * shallower than the one whose bin is fallen into by the sleep length (these - * situations are referred to as "intercepts" below). + * non-timer wakeup events for which the measured idle duration falls into a bin + * that corresponds to an idle state shallower than the one whose bin is fallen + * into by the sleep length (these events are also referred to as "intercepts" + * below). + * + * The governor also counts "intercepts" with the measured idle duration below + * the tick period length and uses this information when deciding whether or not + * to stop the scheduler tick. * * In order to select an idle state for a CPU, the governor takes the following * steps (modulo the possible latency constraint that must be taken into account * too): * - * 1. Find the deepest CPU idle state whose target residency does not exceed - * the current sleep length (the candidate idle state) and compute 2 sums as - * follows: + * 1. Find the deepest enabled CPU idle state (the candidate idle state) and + * compute 2 sums as follows: * - * - The sum of the "hits" and "intercepts" metrics for the candidate state - * and all of the deeper idle states (it represents the cases in which the - * CPU was idle long enough to avoid being intercepted if the sleep length - * had been equal to the current one). + * - The sum of the "hits" metric for all of the idle states shallower than + * the candidate one (it represents the cases in which the CPU was likely + * woken up by a timer). * - * - The sum of the "intercepts" metrics for all of the idle states shallower - * than the candidate one (it represents the cases in which the CPU was not - * idle long enough to avoid being intercepted if the sleep length had been - * equal to the current one). + * - The sum of the "intercepts" metric for all of the idle states shallower + * than the candidate one (it represents the cases in which the CPU was + * likely woken up by a non-timer wakeup source). * - * 2. If the second sum is greater than the first one the CPU is likely to wake - * up early, so look for an alternative idle state to select. + * 2. If the second sum computed in step 1 is greater than a half of the sum of + * both metrics for the candidate state bin and all subsequent bins(if any), + * a shallower idle state is likely to be more suitable, so look for it. * - * - Traverse the idle states shallower than the candidate one in the + * - Traverse the enabled idle states shallower than the candidate one in the * descending order. * * - For each of them compute the sum of the "intercepts" metrics over all * of the idle states between it and the candidate one (including the * former and excluding the latter). * - * - If each of these sums that needs to be taken into account (because the - * check related to it has indicated that the CPU is likely to wake up - * early) is greater than a half of the corresponding sum computed in step - * 1 (which means that the target residency of the state in question had - * not exceeded the idle duration in over a half of the relevant cases), - * select the given idle state instead of the candidate one. + * - If this sum is greater than a half of the second sum computed in step 1, + * use the given idle state as the new candidate one. * - * 3. By default, select the candidate state. + * 3. If the current candidate state is state 0 or its target residency is short + * enough, return it and prevent the scheduler tick from being stopped. + * + * 4. Obtain the sleep length value and check if it is below the target + * residency of the current candidate state, in which case a new shallower + * candidate state needs to be found, so look for it. */ #include @@ -100,6 +105,12 @@ #include "gov.h" +/* + * Idle state exit latency threshold used for deciding whether or not to check + * the time till the closest expected timer event. + */ +#define LATENCY_THRESHOLD_NS (RESIDENCY_THRESHOLD_NS / 2) + /* * The PULSE value is added to metrics when they grow and the DECAY_SHIFT value * is used for decreasing metrics on a regular basis. @@ -119,18 +130,20 @@ struct teo_bin { /** * struct teo_cpu - CPU data used by the TEO cpuidle governor. - * @time_span_ns: Time between idle state selection and post-wakeup update. * @sleep_length_ns: Time till the closest timer event (at the selection time). * @state_bins: Idle state data bins for this CPU. * @total: Grand total of the "intercepts" and "hits" metrics for all bins. - * @tick_hits: Number of "hits" after TICK_NSEC. + * @tick_intercepts: "Intercepts" before TICK_NSEC. + * @short_idles: Wakeups after short idle periods. + * @artificial_wakeup: Set if the wakeup has been triggered by a safety net. */ struct teo_cpu { - s64 time_span_ns; s64 sleep_length_ns; struct teo_bin state_bins[CPUIDLE_STATE_MAX]; unsigned int total; - unsigned int tick_hits; + unsigned int tick_intercepts; + unsigned int short_idles; + bool artificial_wakeup; }; static DEFINE_PER_CPU(struct teo_cpu, teo_cpus); @@ -147,23 +160,17 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) s64 target_residency_ns; u64 measured_ns; - if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) { + cpu_data->short_idles -= cpu_data->short_idles >> DECAY_SHIFT; + + if (cpu_data->artificial_wakeup) { /* - * One of the safety nets has triggered or the wakeup was close - * enough to the closest timer event expected at the idle state - * selection time to be discarded. + * If one of the safety nets has triggered, assume that this + * might have been a long sleep. */ measured_ns = U64_MAX; } else { u64 lat_ns = drv->states[dev->last_state_idx].exit_latency_ns; - /* - * The computations below are to determine whether or not the - * (saved) time till the next timer event and the measured idle - * duration fall into the same "bin", so use last_residency_ns - * for that instead of time_span_ns which includes the cpuidle - * overhead. - */ measured_ns = dev->last_residency_ns; /* * The delay between the wakeup and the first instruction @@ -171,14 +178,16 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * time, so take 1/2 of the exit latency as a very rough * approximation of the average of it. */ - if (measured_ns >= lat_ns) + if (measured_ns >= lat_ns) { measured_ns -= lat_ns / 2; - else + if (measured_ns < RESIDENCY_THRESHOLD_NS) + cpu_data->short_idles += PULSE; + } else { measured_ns /= 2; + cpu_data->short_idles += PULSE; + } } - cpu_data->total = 0; - /* * Decay the "hits" and "intercepts" metrics for all of the bins and * find the bins that the sleep length and the measured idle duration @@ -190,8 +199,6 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) bin->hits -= bin->hits >> DECAY_SHIFT; bin->intercepts -= bin->intercepts >> DECAY_SHIFT; - cpu_data->total += bin->hits + bin->intercepts; - target_residency_ns = drv->states[i].target_residency_ns; if (target_residency_ns <= cpu_data->sleep_length_ns) { @@ -201,38 +208,22 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) } } - /* - * If the deepest state's target residency is below the tick length, - * make a record of it to help teo_select() decide whether or not - * to stop the tick. This effectively adds an extra hits-only bin - * beyond the last state-related one. - */ - if (target_residency_ns < TICK_NSEC) { - cpu_data->tick_hits -= cpu_data->tick_hits >> DECAY_SHIFT; - - cpu_data->total += cpu_data->tick_hits; - - if (TICK_NSEC <= cpu_data->sleep_length_ns) { - idx_timer = drv->state_count; - if (TICK_NSEC <= measured_ns) { - cpu_data->tick_hits += PULSE; - goto end; - } - } - } - + cpu_data->tick_intercepts -= cpu_data->tick_intercepts >> DECAY_SHIFT; /* * If the measured idle duration falls into the same bin as the sleep * length, this is a "hit", so update the "hits" metric for that bin. * Otherwise, update the "intercepts" metric for the bin fallen into by * the measured idle duration. */ - if (idx_timer == idx_duration) + if (idx_timer == idx_duration) { cpu_data->state_bins[idx_timer].hits += PULSE; - else + } else { cpu_data->state_bins[idx_duration].intercepts += PULSE; + if (TICK_NSEC <= measured_ns) + cpu_data->tick_intercepts += PULSE; + } -end: + cpu_data->total -= cpu_data->total >> DECAY_SHIFT; cpu_data->total += PULSE; } @@ -280,14 +271,12 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); s64 latency_req = cpuidle_governor_latency_req(dev->cpu); ktime_t delta_tick = TICK_NSEC / 2; - unsigned int tick_intercept_sum = 0; unsigned int idx_intercept_sum = 0; unsigned int intercept_sum = 0; unsigned int idx_hit_sum = 0; unsigned int hit_sum = 0; int constraint_idx = 0; int idx0 = 0, idx = -1; - int prev_intercept_idx; s64 duration_ns; int i; @@ -296,10 +285,14 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, dev->last_state_idx = -1; } - cpu_data->time_span_ns = local_clock(); /* - * Set the expected sleep length to infinity in case of an early - * return. + * Set the sleep length to infinity in case the invocation of + * tick_nohz_get_sleep_length() below is skipped, in which case it won't + * be known whether or not the subsequent wakeup is caused by a timer. + * It is generally fine to count the wakeup as an intercept then, except + * for the cases when the CPU is mostly woken up by timers and there may + * be opportunities to ask for a deeper idle state when no imminent + * timers are scheduled which may be missed. */ cpu_data->sleep_length_ns = KTIME_MAX; @@ -355,17 +348,13 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, goto end; } - tick_intercept_sum = intercept_sum + - cpu_data->state_bins[drv->state_count-1].intercepts; - /* * If the sum of the intercepts metric for all of the idle states * shallower than the current candidate one (idx) is greater than the * sum of the intercepts and hits metrics for the candidate state and - * all of the deeper states a shallower idle state is likely to be a + * all of the deeper states, a shallower idle state is likely to be a * better choice. */ - prev_intercept_idx = idx; if (2 * idx_intercept_sum > cpu_data->total - idx_hit_sum) { int first_suitable_idx = idx; @@ -391,41 +380,38 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * first enabled state that is deep enough. */ if (teo_state_ok(i, drv) && - !dev->states_usage[i].disable) + !dev->states_usage[i].disable) { idx = i; - else - idx = first_suitable_idx; - + break; + } + idx = first_suitable_idx; break; } if (dev->states_usage[i].disable) continue; - if (!teo_state_ok(i, drv)) { + if (teo_state_ok(i, drv)) { /* - * The current state is too shallow, but if an - * alternative candidate state has been found, - * it may still turn out to be a better choice. + * The current state is deep enough, but still + * there may be a better one. */ - if (first_suitable_idx != idx) - continue; - - break; + first_suitable_idx = i; + continue; } - first_suitable_idx = i; + /* + * The current state is too shallow, so if no suitable + * states other than the initial candidate have been + * found, give up (the remaining states to check are + * shallower still), but otherwise the first suitable + * state other than the initial candidate may turn out + * to be preferable. + */ + if (first_suitable_idx == idx) + break; } } - if (!idx && prev_intercept_idx) { - /* - * We have to query the sleep length here otherwise we don't - * know after wakeup if our guess was correct. - */ - duration_ns = tick_nohz_get_sleep_length(&delta_tick); - cpu_data->sleep_length_ns = duration_ns; - goto out_tick; - } /* * If there is a latency constraint, it may be necessary to select an @@ -435,24 +421,39 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, idx = constraint_idx; /* - * Skip the timers check if state 0 is the current candidate one, - * because an immediate non-timer wakeup is expected in that case. + * If either the candidate state is state 0 or its target residency is + * low enough, there is basically nothing more to do, but if the sleep + * length is not updated, the subsequent wakeup will be counted as an + * "intercept" which may be problematic in the cases when timer wakeups + * are dominant. Namely, it may effectively prevent deeper idle states + * from being selected at one point even if no imminent timers are + * scheduled. + * + * However, frequent timers in the RESIDENCY_THRESHOLD_NS range on one + * CPU are unlikely (user space has a default 50 us slack value for + * hrtimers and there are relatively few timers with a lower deadline + * value in the kernel), and even if they did happen, the potential + * benefit from using a deep idle state in that case would be + * questionable anyway for latency reasons. Thus if the measured idle + * duration falls into that range in the majority of cases, assume + * non-timer wakeups to be dominant and skip updating the sleep length + * to reduce latency. + * + * Also, if the latency constraint is sufficiently low, it will force + * shallow idle states regardless of the wakeup type, so the sleep + * length need not be known in that case. */ - if (!idx) - goto out_tick; - - /* - * If state 0 is a polling one, check if the target residency of - * the current candidate state is low enough and skip the timers - * check in that case too. - */ - if ((drv->states[0].flags & CPUIDLE_FLAG_POLLING) && - drv->states[idx].target_residency_ns < RESIDENCY_THRESHOLD_NS) + if ((!idx || drv->states[idx].target_residency_ns < RESIDENCY_THRESHOLD_NS) && + (2 * cpu_data->short_idles >= cpu_data->total || + latency_req < LATENCY_THRESHOLD_NS)) goto out_tick; duration_ns = tick_nohz_get_sleep_length(&delta_tick); cpu_data->sleep_length_ns = duration_ns; + if (!idx) + goto out_tick; + /* * If the closest expected timer is before the target residency of the * candidate state, a shallower one needs to be found. @@ -469,7 +470,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * total wakeup events, do not stop the tick. */ if (drv->states[idx].target_residency_ns < TICK_NSEC && - tick_intercept_sum > cpu_data->total / 2 + cpu_data->total / 8) + cpu_data->tick_intercepts > cpu_data->total / 2 + cpu_data->total / 8) duration_ns = TICK_NSEC / 2; end: @@ -506,17 +507,16 @@ static void teo_reflect(struct cpuidle_device *dev, int state) struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); dev->last_state_idx = state; - /* - * If the wakeup was not "natural", but triggered by one of the safety - * nets, assume that the CPU might have been idle for the entire sleep - * length time. - */ if (dev->poll_time_limit || (tick_nohz_idle_got_tick() && cpu_data->sleep_length_ns > TICK_NSEC)) { + /* + * The wakeup was not "genuine", but triggered by one of the + * safety nets. + */ dev->poll_time_limit = false; - cpu_data->time_span_ns = cpu_data->sleep_length_ns; + cpu_data->artificial_wakeup = true; } else { - cpu_data->time_span_ns = local_clock() - cpu_data->time_span_ns; + cpu_data->artificial_wakeup = false; } } diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 0a9cdd31cbd9..19ab145f912e 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -200,23 +200,6 @@ config S390_PRNG It is available as of z9. -config CRYPTO_DEV_NIAGARA2 - tristate "Niagara2 Stream Processing Unit driver" - select CRYPTO_LIB_DES - select CRYPTO_SKCIPHER - select CRYPTO_HASH - select CRYPTO_MD5 - select CRYPTO_SHA1 - select CRYPTO_SHA256 - depends on SPARC64 - help - Each core of a Niagara2 processor contains a Stream - Processing Unit, which itself contains several cryptographic - sub-units. One set provides the Modular Arithmetic Unit, - used for SSL offload. The other set provides the Cipher - Group, which can perform encryption, decryption, hashing, - checksumming, and raw copies. - config CRYPTO_DEV_SL3516 tristate "Storlink SL3516 crypto offloader" depends on ARCH_GEMINI || COMPILE_TEST diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile index ad4ccef67d12..fef18ffdb128 100644 --- a/drivers/crypto/Makefile +++ b/drivers/crypto/Makefile @@ -21,8 +21,6 @@ obj-$(CONFIG_CRYPTO_DEV_HIFN_795X) += hifn_795x.o obj-$(CONFIG_CRYPTO_DEV_IMGTEC_HASH) += img-hash.o obj-$(CONFIG_CRYPTO_DEV_MARVELL) += marvell/ obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o -obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o -n2_crypto-y := n2_core.o n2_asm.o obj-$(CONFIG_CRYPTO_DEV_NX) += nx/ obj-$(CONFIG_CRYPTO_DEV_OMAP) += omap-crypto.o obj-$(CONFIG_CRYPTO_DEV_OMAP_AES) += omap-aes-driver.o diff --git a/drivers/crypto/bcm/spu.c b/drivers/crypto/bcm/spu.c index 6283e8c6d51d..86c227caa722 100644 --- a/drivers/crypto/bcm/spu.c +++ b/drivers/crypto/bcm/spu.c @@ -836,7 +836,6 @@ u16 spum_cipher_req_init(u8 *spu_hdr, struct spu_cipher_parms *cipher_parms) u32 cipher_bits = 0; u32 ecf_bits = 0; u8 sctx_words = 0; - u8 *ptr = spu_hdr; flow_log("%s()\n", __func__); flow_log(" cipher alg:%u mode:%u type %u\n", cipher_parms->alg, @@ -847,7 +846,6 @@ u16 spum_cipher_req_init(u8 *spu_hdr, struct spu_cipher_parms *cipher_parms) /* starting out: zero the header (plus some) */ memset(spu_hdr, 0, sizeof(struct SPUHEADER)); - ptr += sizeof(struct SPUHEADER); /* format master header word */ /* Do not set the next bit even though the datasheet says to */ @@ -861,10 +859,8 @@ u16 spum_cipher_req_init(u8 *spu_hdr, struct spu_cipher_parms *cipher_parms) /* copy the encryption keys in the SAD entry */ if (cipher_parms->alg) { - if (cipher_parms->key_len) { - ptr += cipher_parms->key_len; + if (cipher_parms->key_len) sctx_words += cipher_parms->key_len / 4; - } /* * if encrypting then set IV size, use SCTX IV unless no IV @@ -873,7 +869,6 @@ u16 spum_cipher_req_init(u8 *spu_hdr, struct spu_cipher_parms *cipher_parms) if (cipher_parms->iv_len) { /* Use SCTX IV */ ecf_bits |= SCTX_IV; - ptr += cipher_parms->iv_len; sctx_words += cipher_parms->iv_len / 4; } } diff --git a/drivers/crypto/caam/blob_gen.c b/drivers/crypto/caam/blob_gen.c index 87781c1534ee..079a22cc9f02 100644 --- a/drivers/crypto/caam/blob_gen.c +++ b/drivers/crypto/caam/blob_gen.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2015 Pengutronix, Steffen Trumtrar * Copyright (C) 2021 Pengutronix, Ahmad Fatoum + * Copyright 2024 NXP */ #define pr_fmt(fmt) "caam blob_gen: " fmt @@ -104,7 +105,7 @@ int caam_process_blob(struct caam_blob_priv *priv, } ctrlpriv = dev_get_drvdata(jrdev->parent); - moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->ctrl->perfmon.status)); + moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->jr[0]->perfmon.status)); if (moo != CSTA_MOO_SECURE && moo != CSTA_MOO_TRUSTED) dev_warn(jrdev, "using insecure test key, enable HAB to use unique device key!\n"); diff --git a/drivers/crypto/ccp/dbc.c b/drivers/crypto/ccp/dbc.c index 5b105a23f699..410084a9039c 100644 --- a/drivers/crypto/ccp/dbc.c +++ b/drivers/crypto/ccp/dbc.c @@ -7,6 +7,8 @@ * Author: Mario Limonciello */ +#include + #include "dbc.h" #define DBC_DEFAULT_TIMEOUT (10 * MSEC_PER_SEC) @@ -137,64 +139,49 @@ static long dbc_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return -ENODEV; dbc_dev = psp_master->dbc_data; - mutex_lock(&dbc_dev->ioctl_mutex); + guard(mutex)(&dbc_dev->ioctl_mutex); switch (cmd) { case DBCIOCNONCE: - if (copy_from_user(dbc_dev->payload, argp, sizeof(struct dbc_user_nonce))) { - ret = -EFAULT; - goto unlock; - } + if (copy_from_user(dbc_dev->payload, argp, sizeof(struct dbc_user_nonce))) + return -EFAULT; ret = send_dbc_nonce(dbc_dev); if (ret) - goto unlock; + return ret; - if (copy_to_user(argp, dbc_dev->payload, sizeof(struct dbc_user_nonce))) { - ret = -EFAULT; - goto unlock; - } + if (copy_to_user(argp, dbc_dev->payload, sizeof(struct dbc_user_nonce))) + return -EFAULT; break; case DBCIOCUID: - if (copy_from_user(dbc_dev->payload, argp, sizeof(struct dbc_user_setuid))) { - ret = -EFAULT; - goto unlock; - } + if (copy_from_user(dbc_dev->payload, argp, sizeof(struct dbc_user_setuid))) + return -EFAULT; *dbc_dev->payload_size = dbc_dev->header_size + sizeof(struct dbc_user_setuid); ret = send_dbc_cmd(dbc_dev, PSP_DYNAMIC_BOOST_SET_UID); if (ret) - goto unlock; + return ret; - if (copy_to_user(argp, dbc_dev->payload, sizeof(struct dbc_user_setuid))) { - ret = -EFAULT; - goto unlock; - } + if (copy_to_user(argp, dbc_dev->payload, sizeof(struct dbc_user_setuid))) + return -EFAULT; break; case DBCIOCPARAM: - if (copy_from_user(dbc_dev->payload, argp, sizeof(struct dbc_user_param))) { - ret = -EFAULT; - goto unlock; - } + if (copy_from_user(dbc_dev->payload, argp, sizeof(struct dbc_user_param))) + return -EFAULT; *dbc_dev->payload_size = dbc_dev->header_size + sizeof(struct dbc_user_param); ret = send_dbc_parameter(dbc_dev); if (ret) - goto unlock; + return ret; - if (copy_to_user(argp, dbc_dev->payload, sizeof(struct dbc_user_param))) { - ret = -EFAULT; - goto unlock; - } + if (copy_to_user(argp, dbc_dev->payload, sizeof(struct dbc_user_param))) + return -EFAULT; break; default: - ret = -EINVAL; - + return -EINVAL; } -unlock: - mutex_unlock(&dbc_dev->ioctl_mutex); - return ret; + return 0; } static const struct file_operations dbc_fops = { diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index af018afd9cd7..2e87ca0e292a 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -249,7 +249,7 @@ static struct file *open_file_as_root(const char *filename, int flags, umode_t m fp = file_open_root(&root, filename, flags, mode); path_put(&root); - revert_creds(old_cred); + put_cred(revert_creds(old_cred)); return fp; } diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index 96fde9437b4b..f5b47e5ff48a 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -1209,7 +1209,6 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->mode = uacce_mode; qm->pdev = pdev; - qm->ver = pdev->revision; qm->sqe_size = HPRE_SQE_SIZE; qm->dev_name = hpre_name; @@ -1396,6 +1395,17 @@ static enum acc_err_result hpre_get_err_result(struct hisi_qm *qm) return ACC_ERR_RECOVERED; } +static bool hpre_dev_is_abnormal(struct hisi_qm *qm) +{ + u32 err_status; + + err_status = hpre_get_hw_err_status(qm); + if (err_status & qm->err_info.dev_shutdown_mask) + return true; + + return false; +} + static void hpre_err_info_init(struct hisi_qm *qm) { struct hisi_qm_err_info *err_info = &qm->err_info; @@ -1428,6 +1438,7 @@ static const struct hisi_qm_err_ini hpre_err_ini = { .show_last_dfx_regs = hpre_show_last_dfx_regs, .err_info_init = hpre_err_info_init, .get_err_result = hpre_get_err_result, + .dev_is_abnormal = hpre_dev_is_abnormal, }; static int hpre_pf_probe_init(struct hpre *hpre) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 19c1b5d3c954..d3f5d108b898 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -30,8 +30,6 @@ /* mailbox */ #define QM_MB_PING_ALL_VFS 0xffff -#define QM_MB_CMD_DATA_SHIFT 32 -#define QM_MB_CMD_DATA_MASK GENMASK(31, 0) #define QM_MB_STATUS_MASK GENMASK(12, 9) /* sqc shift */ @@ -102,6 +100,8 @@ #define QM_PM_CTRL 0x100148 #define QM_IDLE_DISABLE BIT(9) +#define QM_SUB_VERSION_ID 0x210 + #define QM_VFT_CFG_DATA_L 0x100064 #define QM_VFT_CFG_DATA_H 0x100068 #define QM_SQC_VFT_BUF_SIZE (7ULL << 8) @@ -119,6 +119,7 @@ #define QM_SQC_VFT_BASE_MASK_V2 GENMASK(15, 0) #define QM_SQC_VFT_NUM_SHIFT_V2 45 #define QM_SQC_VFT_NUM_MASK_V2 GENMASK(9, 0) +#define QM_MAX_QC_TYPE 2 #define QM_ABNORMAL_INT_SOURCE 0x100000 #define QM_ABNORMAL_INT_MASK 0x100004 @@ -176,6 +177,10 @@ #define QM_IFC_INT_MASK 0x0024 #define QM_IFC_INT_STATUS 0x0028 #define QM_IFC_INT_SET_V 0x002C +#define QM_PF2VF_PF_W 0x104700 +#define QM_VF2PF_PF_R 0x104800 +#define QM_VF2PF_VF_W 0x320 +#define QM_PF2VF_VF_R 0x380 #define QM_IFC_SEND_ALL_VFS GENMASK(6, 0) #define QM_IFC_INT_SOURCE_CLR GENMASK(63, 0) #define QM_IFC_INT_SOURCE_MASK BIT(0) @@ -185,8 +190,11 @@ #define QM_WAIT_DST_ACK 10 #define QM_MAX_PF_WAIT_COUNT 10 #define QM_MAX_VF_WAIT_COUNT 40 -#define QM_VF_RESET_WAIT_US 20000 -#define QM_VF_RESET_WAIT_CNT 3000 +#define QM_VF_RESET_WAIT_US 20000 +#define QM_VF_RESET_WAIT_CNT 3000 +#define QM_VF2PF_REG_SIZE 4 +#define QM_IFC_CMD_MASK GENMASK(31, 0) +#define QM_IFC_DATA_SHIFT 32 #define QM_VF_RESET_WAIT_TIMEOUT_US \ (QM_VF_RESET_WAIT_US * QM_VF_RESET_WAIT_CNT) @@ -234,8 +242,6 @@ #define QM_QOS_MAX_CIR_U 6 #define QM_AUTOSUSPEND_DELAY 3000 -#define QM_DEV_ALG_MAX_LEN 256 - /* abnormal status value for stopping queue */ #define QM_STOP_QUEUE_FAIL 1 #define QM_DUMP_SQC_FAIL 3 @@ -276,7 +282,7 @@ enum qm_alg_type { ALG_TYPE_1, }; -enum qm_mb_cmd { +enum qm_ifc_cmd { QM_PF_FLR_PREPARE = 0x01, QM_PF_SRST_PREPARE, QM_PF_RESET_DONE, @@ -333,6 +339,7 @@ static const struct hisi_qm_cap_info qm_cap_info_comm[] = { {QM_SUPPORT_STOP_FUNC, 0x3100, 0, BIT(10), 0x0, 0x0, 0x1}, {QM_SUPPORT_MB_COMMAND, 0x3100, 0, BIT(11), 0x0, 0x0, 0x1}, {QM_SUPPORT_SVA_PREFETCH, 0x3100, 0, BIT(14), 0x0, 0x0, 0x1}, + {QM_SUPPORT_DAE, 0x3100, 0, BIT(15), 0x0, 0x0, 0x0}, }; static const struct hisi_qm_cap_info qm_cap_info_pf[] = { @@ -396,6 +403,11 @@ struct hisi_qm_hw_ops { void (*hw_error_uninit)(struct hisi_qm *qm); enum acc_err_result (*hw_error_handle)(struct hisi_qm *qm); int (*set_msi)(struct hisi_qm *qm, bool set); + + /* (u64)msg = (u32)data << 32 | (enum qm_ifc_cmd)cmd */ + int (*set_ifc_begin)(struct hisi_qm *qm, enum qm_ifc_cmd cmd, u32 data, u32 fun_num); + void (*set_ifc_end)(struct hisi_qm *qm); + int (*get_ifc)(struct hisi_qm *qm, enum qm_ifc_cmd *cmd, u32 *data, u32 fun_num); }; struct hisi_qm_hw_error { @@ -501,15 +513,20 @@ static u32 qm_get_dev_err_status(struct hisi_qm *qm) /* Check if the error causes the master ooo block */ static bool qm_check_dev_error(struct hisi_qm *qm) { - u32 val, dev_val; + struct hisi_qm *pf_qm = pci_get_drvdata(pci_physfn(qm->pdev)); + u32 err_status; - if (qm->fun_type == QM_HW_VF) + if (pf_qm->fun_type == QM_HW_VF) return false; - val = qm_get_hw_error_status(qm) & qm->err_info.qm_shutdown_mask; - dev_val = qm_get_dev_err_status(qm) & qm->err_info.dev_shutdown_mask; + err_status = qm_get_hw_error_status(pf_qm); + if (err_status & pf_qm->err_info.qm_shutdown_mask) + return true; - return val || dev_val; + if (pf_qm->err_ini->dev_is_abnormal) + return pf_qm->err_ini->dev_is_abnormal(pf_qm); + + return false; } static int qm_wait_reset_finish(struct hisi_qm *qm) @@ -654,7 +671,6 @@ EXPORT_SYMBOL_GPL(hisi_qm_mb); /* op 0: set xqc information to hardware, 1: get xqc information from hardware. */ int qm_set_and_get_xqc(struct hisi_qm *qm, u8 cmd, void *xqc, u32 qp_id, bool op) { - struct hisi_qm *pf_qm = pci_get_drvdata(pci_physfn(qm->pdev)); struct qm_mailbox mailbox; dma_addr_t xqc_dma; void *tmp_xqc; @@ -688,7 +704,7 @@ int qm_set_and_get_xqc(struct hisi_qm *qm, u8 cmd, void *xqc, u32 qp_id, bool op } /* Setting xqc will fail if master OOO is blocked. */ - if (qm_check_dev_error(pf_qm)) { + if (qm_check_dev_error(qm)) { dev_err(&qm->pdev->dev, "failed to send mailbox since qm is stop!\n"); return -EIO; } @@ -855,10 +871,10 @@ int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *d strcat(algs, dev_algs[i].alg); ptr = strrchr(algs, '\n'); - if (ptr) { + if (ptr) *ptr = '\0'; - qm->uacce->algs = algs; - } + + qm->uacce->algs = algs; return 0; } @@ -1052,11 +1068,10 @@ static void qm_disable_qp(struct hisi_qm *qm, u32 qp_id) static void qm_reset_function(struct hisi_qm *qm) { - struct hisi_qm *pf_qm = pci_get_drvdata(pci_physfn(qm->pdev)); struct device *dev = &qm->pdev->dev; int ret; - if (qm_check_dev_error(pf_qm)) + if (qm_check_dev_error(qm)) return; ret = qm_reset_prepare_ready(qm); @@ -1540,17 +1555,15 @@ static void qm_clear_cmd_interrupt(struct hisi_qm *qm, u64 vf_mask) static void qm_handle_vf_msg(struct hisi_qm *qm, u32 vf_id) { struct device *dev = &qm->pdev->dev; - u32 cmd; - u64 msg; + enum qm_ifc_cmd cmd; int ret; - ret = qm_get_mb_cmd(qm, &msg, vf_id); + ret = qm->ops->get_ifc(qm, &cmd, NULL, vf_id); if (ret) { - dev_err(dev, "failed to get msg from VF(%u)!\n", vf_id); + dev_err(dev, "failed to get command from VF(%u)!\n", vf_id); return; } - cmd = msg & QM_MB_CMD_DATA_MASK; switch (cmd) { case QM_VF_PREPARE_FAIL: dev_err(dev, "failed to stop VF(%u)!\n", vf_id); @@ -1562,7 +1575,7 @@ static void qm_handle_vf_msg(struct hisi_qm *qm, u32 vf_id) case QM_VF_START_DONE: break; default: - dev_err(dev, "unsupported cmd %u sent by VF(%u)!\n", cmd, vf_id); + dev_err(dev, "unsupported command(0x%x) sent by VF(%u)!\n", cmd, vf_id); break; } } @@ -1630,17 +1643,14 @@ static void qm_trigger_pf_interrupt(struct hisi_qm *qm) writel(val, qm->io_base + QM_IFC_INT_SET_V); } -static int qm_ping_single_vf(struct hisi_qm *qm, u64 cmd, u32 fun_num) +static int qm_ping_single_vf(struct hisi_qm *qm, enum qm_ifc_cmd cmd, u32 data, u32 fun_num) { struct device *dev = &qm->pdev->dev; - struct qm_mailbox mailbox; int cnt = 0; u64 val; int ret; - qm_mb_pre_init(&mailbox, QM_MB_CMD_SRC, cmd, fun_num, 0); - mutex_lock(&qm->mailbox_lock); - ret = qm_mb_nolock(qm, &mailbox); + ret = qm->ops->set_ifc_begin(qm, cmd, data, fun_num); if (ret) { dev_err(dev, "failed to send command to vf(%u)!\n", fun_num); goto err_unlock; @@ -1662,27 +1672,23 @@ static int qm_ping_single_vf(struct hisi_qm *qm, u64 cmd, u32 fun_num) } err_unlock: - mutex_unlock(&qm->mailbox_lock); + qm->ops->set_ifc_end(qm); return ret; } -static int qm_ping_all_vfs(struct hisi_qm *qm, u64 cmd) +static int qm_ping_all_vfs(struct hisi_qm *qm, enum qm_ifc_cmd cmd) { struct device *dev = &qm->pdev->dev; u32 vfs_num = qm->vfs_num; - struct qm_mailbox mailbox; u64 val = 0; int cnt = 0; int ret; u32 i; - qm_mb_pre_init(&mailbox, QM_MB_CMD_SRC, cmd, QM_MB_PING_ALL_VFS, 0); - mutex_lock(&qm->mailbox_lock); - /* PF sends command to all VFs by mailbox */ - ret = qm_mb_nolock(qm, &mailbox); + ret = qm->ops->set_ifc_begin(qm, cmd, 0, QM_MB_PING_ALL_VFS); if (ret) { - dev_err(dev, "failed to send command to VFs!\n"); - mutex_unlock(&qm->mailbox_lock); + dev_err(dev, "failed to send command(0x%x) to all vfs!\n", cmd); + qm->ops->set_ifc_end(qm); return ret; } @@ -1692,7 +1698,7 @@ static int qm_ping_all_vfs(struct hisi_qm *qm, u64 cmd) val = readq(qm->io_base + QM_IFC_READY_STATUS); /* If all VFs acked, PF notifies VFs successfully. */ if (!(val & GENMASK(vfs_num, 1))) { - mutex_unlock(&qm->mailbox_lock); + qm->ops->set_ifc_end(qm); return 0; } @@ -1700,7 +1706,7 @@ static int qm_ping_all_vfs(struct hisi_qm *qm, u64 cmd) break; } - mutex_unlock(&qm->mailbox_lock); + qm->ops->set_ifc_end(qm); /* Check which vf respond timeout. */ for (i = 1; i <= vfs_num; i++) { @@ -1711,18 +1717,15 @@ static int qm_ping_all_vfs(struct hisi_qm *qm, u64 cmd) return -ETIMEDOUT; } -static int qm_ping_pf(struct hisi_qm *qm, u64 cmd) +static int qm_ping_pf(struct hisi_qm *qm, enum qm_ifc_cmd cmd) { - struct qm_mailbox mailbox; int cnt = 0; u32 val; int ret; - qm_mb_pre_init(&mailbox, QM_MB_CMD_SRC, cmd, 0, 0); - mutex_lock(&qm->mailbox_lock); - ret = qm_mb_nolock(qm, &mailbox); + ret = qm->ops->set_ifc_begin(qm, cmd, 0, 0); if (ret) { - dev_err(&qm->pdev->dev, "failed to send command to PF!\n"); + dev_err(&qm->pdev->dev, "failed to send command(0x%x) to PF!\n", cmd); goto unlock; } @@ -1741,7 +1744,8 @@ static int qm_ping_pf(struct hisi_qm *qm, u64 cmd) } unlock: - mutex_unlock(&qm->mailbox_lock); + qm->ops->set_ifc_end(qm); + return ret; } @@ -1842,6 +1846,94 @@ static int qm_set_msi_v3(struct hisi_qm *qm, bool set) return ret; } +static int qm_set_ifc_begin_v3(struct hisi_qm *qm, enum qm_ifc_cmd cmd, u32 data, u32 fun_num) +{ + struct qm_mailbox mailbox; + u64 msg; + + msg = cmd | (u64)data << QM_IFC_DATA_SHIFT; + + qm_mb_pre_init(&mailbox, QM_MB_CMD_SRC, msg, fun_num, 0); + mutex_lock(&qm->mailbox_lock); + return qm_mb_nolock(qm, &mailbox); +} + +static void qm_set_ifc_end_v3(struct hisi_qm *qm) +{ + mutex_unlock(&qm->mailbox_lock); +} + +static int qm_get_ifc_v3(struct hisi_qm *qm, enum qm_ifc_cmd *cmd, u32 *data, u32 fun_num) +{ + u64 msg; + int ret; + + ret = qm_get_mb_cmd(qm, &msg, fun_num); + if (ret) + return ret; + + *cmd = msg & QM_IFC_CMD_MASK; + + if (data) + *data = msg >> QM_IFC_DATA_SHIFT; + + return 0; +} + +static int qm_set_ifc_begin_v4(struct hisi_qm *qm, enum qm_ifc_cmd cmd, u32 data, u32 fun_num) +{ + uintptr_t offset; + u64 msg; + + if (qm->fun_type == QM_HW_PF) + offset = QM_PF2VF_PF_W; + else + offset = QM_VF2PF_VF_W; + + msg = cmd | (u64)data << QM_IFC_DATA_SHIFT; + + mutex_lock(&qm->ifc_lock); + writeq(msg, qm->io_base + offset); + + return 0; +} + +static void qm_set_ifc_end_v4(struct hisi_qm *qm) +{ + mutex_unlock(&qm->ifc_lock); +} + +static u64 qm_get_ifc_pf(struct hisi_qm *qm, u32 fun_num) +{ + uintptr_t offset; + + offset = QM_VF2PF_PF_R + QM_VF2PF_REG_SIZE * fun_num; + + return (u64)readl(qm->io_base + offset); +} + +static u64 qm_get_ifc_vf(struct hisi_qm *qm) +{ + return readq(qm->io_base + QM_PF2VF_VF_R); +} + +static int qm_get_ifc_v4(struct hisi_qm *qm, enum qm_ifc_cmd *cmd, u32 *data, u32 fun_num) +{ + u64 msg; + + if (qm->fun_type == QM_HW_PF) + msg = qm_get_ifc_pf(qm, fun_num); + else + msg = qm_get_ifc_vf(qm); + + *cmd = msg & QM_IFC_CMD_MASK; + + if (data) + *data = msg >> QM_IFC_DATA_SHIFT; + + return 0; +} + static const struct hisi_qm_hw_ops qm_hw_ops_v1 = { .qm_db = qm_db_v1, .hw_error_init = qm_hw_error_init_v1, @@ -1864,6 +1956,21 @@ static const struct hisi_qm_hw_ops qm_hw_ops_v3 = { .hw_error_uninit = qm_hw_error_uninit_v3, .hw_error_handle = qm_hw_error_handle_v2, .set_msi = qm_set_msi_v3, + .set_ifc_begin = qm_set_ifc_begin_v3, + .set_ifc_end = qm_set_ifc_end_v3, + .get_ifc = qm_get_ifc_v3, +}; + +static const struct hisi_qm_hw_ops qm_hw_ops_v4 = { + .get_vft = qm_get_vft_v2, + .qm_db = qm_db_v2, + .hw_error_init = qm_hw_error_init_v3, + .hw_error_uninit = qm_hw_error_uninit_v3, + .hw_error_handle = qm_hw_error_handle_v2, + .set_msi = qm_set_msi_v3, + .set_ifc_begin = qm_set_ifc_begin_v4, + .set_ifc_end = qm_set_ifc_end_v4, + .get_ifc = qm_get_ifc_v4, }; static void *qm_get_avail_sqe(struct hisi_qp *qp) @@ -2156,12 +2263,11 @@ static int qm_wait_qp_empty(struct hisi_qm *qm, u32 *state, u32 qp_id) static int qm_drain_qp(struct hisi_qp *qp) { struct hisi_qm *qm = qp->qm; - struct hisi_qm *pf_qm = pci_get_drvdata(pci_physfn(qm->pdev)); u32 state = 0; int ret; /* No need to judge if master OOO is blocked. */ - if (qm_check_dev_error(pf_qm)) + if (qm_check_dev_error(qm)) return 0; /* HW V3 supports drain qp by device */ @@ -2475,7 +2581,7 @@ static long hisi_qm_uacce_ioctl(struct uacce_queue *q, unsigned int cmd, sizeof(struct hisi_qp_ctx))) return -EFAULT; - if (qp_ctx.qc_type != 0 && qp_ctx.qc_type != 1) + if (qp_ctx.qc_type > QM_MAX_QC_TYPE) return -EINVAL; qm_set_sqctype(q, qp_ctx.qc_type); @@ -2843,11 +2949,14 @@ static void hisi_qm_pre_init(struct hisi_qm *qm) qm->ops = &qm_hw_ops_v1; else if (qm->ver == QM_HW_V2) qm->ops = &qm_hw_ops_v2; - else + else if (qm->ver == QM_HW_V3) qm->ops = &qm_hw_ops_v3; + else + qm->ops = &qm_hw_ops_v4; pci_set_drvdata(pdev, qm); mutex_init(&qm->mailbox_lock); + mutex_init(&qm->ifc_lock); init_rwsem(&qm->qps_lock); qm->qp_in_used = 0; if (test_bit(QM_SUPPORT_RPM, &qm->caps)) { @@ -3607,7 +3716,6 @@ static u32 qm_get_shaper_vft_qos(struct hisi_qm *qm, u32 fun_index) static void qm_vf_get_qos(struct hisi_qm *qm, u32 fun_num) { struct device *dev = &qm->pdev->dev; - u64 mb_cmd; u32 qos; int ret; @@ -3617,10 +3725,9 @@ static void qm_vf_get_qos(struct hisi_qm *qm, u32 fun_num) return; } - mb_cmd = QM_PF_SET_QOS | (u64)qos << QM_MB_CMD_DATA_SHIFT; - ret = qm_ping_single_vf(qm, mb_cmd, fun_num); + ret = qm_ping_single_vf(qm, QM_PF_SET_QOS, qos, fun_num); if (ret) - dev_err(dev, "failed to send cmd to VF(%u)!\n", fun_num); + dev_err(dev, "failed to send command(0x%x) to VF(%u)!\n", QM_PF_SET_QOS, fun_num); } static int qm_vf_read_qos(struct hisi_qm *qm) @@ -4109,7 +4216,7 @@ stop_fail: return ret; } -static int qm_try_stop_vfs(struct hisi_qm *qm, u64 cmd, +static int qm_try_stop_vfs(struct hisi_qm *qm, enum qm_ifc_cmd cmd, enum qm_stop_reason stop_reason) { struct pci_dev *pdev = qm->pdev; @@ -4122,7 +4229,7 @@ static int qm_try_stop_vfs(struct hisi_qm *qm, u64 cmd, if (test_bit(QM_SUPPORT_MB_COMMAND, &qm->caps)) { ret = qm_ping_all_vfs(qm, cmd); if (ret) - pci_err(pdev, "failed to send cmd to all VFs before PF reset!\n"); + pci_err(pdev, "failed to send command to all VFs before PF reset!\n"); } else { ret = qm_vf_reset_prepare(qm, stop_reason); if (ret) @@ -4137,6 +4244,12 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) struct pci_dev *pdev = qm->pdev; int ret; + if (qm->err_ini->set_priv_status) { + ret = qm->err_ini->set_priv_status(qm); + if (ret) + return ret; + } + ret = qm_reset_prepare_ready(qm); if (ret) { pci_err(pdev, "Controller reset not ready!\n"); @@ -4298,7 +4411,7 @@ restart_fail: return ret; } -static int qm_try_start_vfs(struct hisi_qm *qm, enum qm_mb_cmd cmd) +static int qm_try_start_vfs(struct hisi_qm *qm, enum qm_ifc_cmd cmd) { struct pci_dev *pdev = qm->pdev; int ret; @@ -4527,7 +4640,7 @@ void hisi_qm_reset_prepare(struct pci_dev *pdev) * Check whether there is an ECC mbit error, If it occurs, need to * wait for soft reset to fix it. */ - while (qm_check_dev_error(pf_qm)) { + while (qm_check_dev_error(qm)) { msleep(++delay); if (delay > QM_RESET_WAIT_TIMEOUT) return; @@ -4675,7 +4788,7 @@ static void hisi_qm_controller_reset(struct work_struct *rst_work) static void qm_pf_reset_vf_prepare(struct hisi_qm *qm, enum qm_stop_reason stop_reason) { - enum qm_mb_cmd cmd = QM_VF_PREPARE_DONE; + enum qm_ifc_cmd cmd = QM_VF_PREPARE_DONE; struct pci_dev *pdev = qm->pdev; int ret; @@ -4709,7 +4822,7 @@ out: static void qm_pf_reset_vf_done(struct hisi_qm *qm) { - enum qm_mb_cmd cmd = QM_VF_START_DONE; + enum qm_ifc_cmd cmd = QM_VF_START_DONE; struct pci_dev *pdev = qm->pdev; int ret; @@ -4732,7 +4845,6 @@ static int qm_wait_pf_reset_finish(struct hisi_qm *qm) { struct device *dev = &qm->pdev->dev; u32 val, cmd; - u64 msg; int ret; /* Wait for reset to finish */ @@ -4749,16 +4861,15 @@ static int qm_wait_pf_reset_finish(struct hisi_qm *qm) * Whether message is got successfully, * VF needs to ack PF by clearing the interrupt. */ - ret = qm_get_mb_cmd(qm, &msg, 0); + ret = qm->ops->get_ifc(qm, &cmd, NULL, 0); qm_clear_cmd_interrupt(qm, 0); if (ret) { - dev_err(dev, "failed to get msg from PF in reset done!\n"); + dev_err(dev, "failed to get command from PF in reset done!\n"); return ret; } - cmd = msg & QM_MB_CMD_DATA_MASK; if (cmd != QM_PF_RESET_DONE) { - dev_err(dev, "the cmd(%u) is not reset done!\n", cmd); + dev_err(dev, "the command(0x%x) is not reset done!\n", cmd); ret = -EINVAL; } @@ -4795,22 +4906,21 @@ err_get_status: static void qm_handle_cmd_msg(struct hisi_qm *qm, u32 fun_num) { struct device *dev = &qm->pdev->dev; - u64 msg; - u32 cmd; + enum qm_ifc_cmd cmd; + u32 data; int ret; /* * Get the msg from source by sending mailbox. Whether message is got * successfully, destination needs to ack source by clearing the interrupt. */ - ret = qm_get_mb_cmd(qm, &msg, fun_num); + ret = qm->ops->get_ifc(qm, &cmd, &data, fun_num); qm_clear_cmd_interrupt(qm, BIT(fun_num)); if (ret) { - dev_err(dev, "failed to get msg from source!\n"); + dev_err(dev, "failed to get command from source!\n"); return; } - cmd = msg & QM_MB_CMD_DATA_MASK; switch (cmd) { case QM_PF_FLR_PREPARE: qm_pf_reset_vf_process(qm, QM_DOWN); @@ -4822,10 +4932,10 @@ static void qm_handle_cmd_msg(struct hisi_qm *qm, u32 fun_num) qm_vf_get_qos(qm, fun_num); break; case QM_PF_SET_QOS: - qm->mb_qos = msg >> QM_MB_CMD_DATA_SHIFT; + qm->mb_qos = data; break; default: - dev_err(dev, "unsupported cmd %u sent by function(%u)!\n", cmd, fun_num); + dev_err(dev, "unsupported command(0x%x) sent by function(%u)!\n", cmd, fun_num); break; } } @@ -5167,6 +5277,20 @@ static int qm_get_hw_caps(struct hisi_qm *qm) return qm_pre_store_caps(qm); } +static void qm_get_version(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + u32 sub_version_id; + + qm->ver = pdev->revision; + + if (pdev->revision == QM_HW_V3) { + sub_version_id = readl(qm->io_base + QM_SUB_VERSION_ID); + if (sub_version_id) + qm->ver = sub_version_id; + } +} + static int qm_get_pci_res(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -5186,6 +5310,8 @@ static int qm_get_pci_res(struct hisi_qm *qm) goto err_request_mem_regions; } + qm_get_version(qm); + ret = qm_get_hw_caps(qm); if (ret) goto err_ioremap; @@ -5205,6 +5331,7 @@ static int qm_get_pci_res(struct hisi_qm *qm) qm->db_interval = 0; } + hisi_qm_pre_init(qm); ret = qm_get_qp_num(qm); if (ret) goto err_db_ioremap; @@ -5247,6 +5374,14 @@ static int qm_clear_device(struct hisi_qm *qm) return ret; } + if (qm->err_ini->set_priv_status) { + ret = qm->err_ini->set_priv_status(qm); + if (ret) { + writel(0x0, qm->io_base + ACC_MASTER_GLOBAL_CTRL); + return ret; + } + } + return qm_reset_device(qm); } @@ -5461,8 +5596,6 @@ int hisi_qm_init(struct hisi_qm *qm) struct device *dev = &pdev->dev; int ret; - hisi_qm_pre_init(qm); - ret = hisi_qm_pci_init(qm); if (ret) return ret; @@ -5598,6 +5731,12 @@ static int qm_prepare_for_suspend(struct hisi_qm *qm) if (ret) return ret; + if (qm->err_ini->set_priv_status) { + ret = qm->err_ini->set_priv_status(qm); + if (ret) + return ret; + } + ret = qm_set_pf_mse(qm, false); if (ret) pci_err(pdev, "failed to disable MSE before suspending!\n"); diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h index 356188bee6fb..4b9970230822 100644 --- a/drivers/crypto/hisilicon/sec2/sec.h +++ b/drivers/crypto/hisilicon/sec2/sec.h @@ -37,6 +37,7 @@ struct sec_aead_req { u8 *a_ivin; dma_addr_t a_ivin_dma; struct aead_request *aead_req; + bool fallback; }; /* SEC request of Crypto */ @@ -90,9 +91,7 @@ struct sec_auth_ctx { dma_addr_t a_key_dma; u8 *a_key; u8 a_key_len; - u8 mac_len; u8 a_alg; - bool fallback; struct crypto_shash *hash_tfm; struct crypto_aead *fallback_aead_tfm; }; diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index ae9ebbb4103d..66bc07da9eb6 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -948,15 +948,14 @@ static int sec_aead_mac_init(struct sec_aead_req *req) struct aead_request *aead_req = req->aead_req; struct crypto_aead *tfm = crypto_aead_reqtfm(aead_req); size_t authsize = crypto_aead_authsize(tfm); - u8 *mac_out = req->out_mac; struct scatterlist *sgl = aead_req->src; + u8 *mac_out = req->out_mac; size_t copy_size; off_t skip_size; /* Copy input mac */ skip_size = aead_req->assoclen + aead_req->cryptlen - authsize; - copy_size = sg_pcopy_to_buffer(sgl, sg_nents(sgl), mac_out, - authsize, skip_size); + copy_size = sg_pcopy_to_buffer(sgl, sg_nents(sgl), mac_out, authsize, skip_size); if (unlikely(copy_size != authsize)) return -EINVAL; @@ -1120,10 +1119,7 @@ static int sec_aead_setauthsize(struct crypto_aead *aead, unsigned int authsize) struct sec_ctx *ctx = crypto_tfm_ctx(tfm); struct sec_auth_ctx *a_ctx = &ctx->a_ctx; - if (unlikely(a_ctx->fallback_aead_tfm)) - return crypto_aead_setauthsize(a_ctx->fallback_aead_tfm, authsize); - - return 0; + return crypto_aead_setauthsize(a_ctx->fallback_aead_tfm, authsize); } static int sec_aead_fallback_setkey(struct sec_auth_ctx *a_ctx, @@ -1139,7 +1135,6 @@ static int sec_aead_fallback_setkey(struct sec_auth_ctx *a_ctx, static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key, const u32 keylen, const enum sec_hash_alg a_alg, const enum sec_calg c_alg, - const enum sec_mac_len mac_len, const enum sec_cmode c_mode) { struct sec_ctx *ctx = crypto_aead_ctx(tfm); @@ -1151,7 +1146,6 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key, ctx->a_ctx.a_alg = a_alg; ctx->c_ctx.c_alg = c_alg; - ctx->a_ctx.mac_len = mac_len; c_ctx->c_mode = c_mode; if (c_mode == SEC_CMODE_CCM || c_mode == SEC_CMODE_GCM) { @@ -1162,13 +1156,7 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key, } memcpy(c_ctx->c_key, key, keylen); - if (unlikely(a_ctx->fallback_aead_tfm)) { - ret = sec_aead_fallback_setkey(a_ctx, tfm, key, keylen); - if (ret) - return ret; - } - - return 0; + return sec_aead_fallback_setkey(a_ctx, tfm, key, keylen); } ret = crypto_authenc_extractkeys(&keys, key, keylen); @@ -1187,10 +1175,15 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key, goto bad_key; } - if ((ctx->a_ctx.mac_len & SEC_SQE_LEN_RATE_MASK) || - (ctx->a_ctx.a_key_len & SEC_SQE_LEN_RATE_MASK)) { + if (ctx->a_ctx.a_key_len & SEC_SQE_LEN_RATE_MASK) { ret = -EINVAL; - dev_err(dev, "MAC or AUTH key length error!\n"); + dev_err(dev, "AUTH key length error!\n"); + goto bad_key; + } + + ret = sec_aead_fallback_setkey(a_ctx, tfm, key, keylen); + if (ret) { + dev_err(dev, "set sec fallback key err!\n"); goto bad_key; } @@ -1202,27 +1195,19 @@ bad_key: } -#define GEN_SEC_AEAD_SETKEY_FUNC(name, aalg, calg, maclen, cmode) \ -static int sec_setkey_##name(struct crypto_aead *tfm, const u8 *key, \ - u32 keylen) \ -{ \ - return sec_aead_setkey(tfm, key, keylen, aalg, calg, maclen, cmode);\ +#define GEN_SEC_AEAD_SETKEY_FUNC(name, aalg, calg, cmode) \ +static int sec_setkey_##name(struct crypto_aead *tfm, const u8 *key, u32 keylen) \ +{ \ + return sec_aead_setkey(tfm, key, keylen, aalg, calg, cmode); \ } -GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha1, SEC_A_HMAC_SHA1, - SEC_CALG_AES, SEC_HMAC_SHA1_MAC, SEC_CMODE_CBC) -GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha256, SEC_A_HMAC_SHA256, - SEC_CALG_AES, SEC_HMAC_SHA256_MAC, SEC_CMODE_CBC) -GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha512, SEC_A_HMAC_SHA512, - SEC_CALG_AES, SEC_HMAC_SHA512_MAC, SEC_CMODE_CBC) -GEN_SEC_AEAD_SETKEY_FUNC(aes_ccm, 0, SEC_CALG_AES, - SEC_HMAC_CCM_MAC, SEC_CMODE_CCM) -GEN_SEC_AEAD_SETKEY_FUNC(aes_gcm, 0, SEC_CALG_AES, - SEC_HMAC_GCM_MAC, SEC_CMODE_GCM) -GEN_SEC_AEAD_SETKEY_FUNC(sm4_ccm, 0, SEC_CALG_SM4, - SEC_HMAC_CCM_MAC, SEC_CMODE_CCM) -GEN_SEC_AEAD_SETKEY_FUNC(sm4_gcm, 0, SEC_CALG_SM4, - SEC_HMAC_GCM_MAC, SEC_CMODE_GCM) +GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha1, SEC_A_HMAC_SHA1, SEC_CALG_AES, SEC_CMODE_CBC) +GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha256, SEC_A_HMAC_SHA256, SEC_CALG_AES, SEC_CMODE_CBC) +GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha512, SEC_A_HMAC_SHA512, SEC_CALG_AES, SEC_CMODE_CBC) +GEN_SEC_AEAD_SETKEY_FUNC(aes_ccm, 0, SEC_CALG_AES, SEC_CMODE_CCM) +GEN_SEC_AEAD_SETKEY_FUNC(aes_gcm, 0, SEC_CALG_AES, SEC_CMODE_GCM) +GEN_SEC_AEAD_SETKEY_FUNC(sm4_ccm, 0, SEC_CALG_SM4, SEC_CMODE_CCM) +GEN_SEC_AEAD_SETKEY_FUNC(sm4_gcm, 0, SEC_CALG_SM4, SEC_CMODE_GCM) static int sec_aead_sgl_map(struct sec_ctx *ctx, struct sec_req *req) { @@ -1470,9 +1455,10 @@ static void sec_skcipher_callback(struct sec_ctx *ctx, struct sec_req *req, static void set_aead_auth_iv(struct sec_ctx *ctx, struct sec_req *req) { struct aead_request *aead_req = req->aead_req.aead_req; - struct sec_cipher_req *c_req = &req->c_req; + struct crypto_aead *tfm = crypto_aead_reqtfm(aead_req); + size_t authsize = crypto_aead_authsize(tfm); struct sec_aead_req *a_req = &req->aead_req; - size_t authsize = ctx->a_ctx.mac_len; + struct sec_cipher_req *c_req = &req->c_req; u32 data_size = aead_req->cryptlen; u8 flage = 0; u8 cm, cl; @@ -1513,10 +1499,8 @@ static void set_aead_auth_iv(struct sec_ctx *ctx, struct sec_req *req) static void sec_aead_set_iv(struct sec_ctx *ctx, struct sec_req *req) { struct aead_request *aead_req = req->aead_req.aead_req; - struct crypto_aead *tfm = crypto_aead_reqtfm(aead_req); - size_t authsize = crypto_aead_authsize(tfm); - struct sec_cipher_req *c_req = &req->c_req; struct sec_aead_req *a_req = &req->aead_req; + struct sec_cipher_req *c_req = &req->c_req; memcpy(c_req->c_ivin, aead_req->iv, ctx->c_ctx.ivsize); @@ -1524,15 +1508,11 @@ static void sec_aead_set_iv(struct sec_ctx *ctx, struct sec_req *req) /* * CCM 16Byte Cipher_IV: {1B_Flage,13B_IV,2B_counter}, * the counter must set to 0x01 + * CCM 16Byte Auth_IV: {1B_AFlage,13B_IV,2B_Ptext_length} */ - ctx->a_ctx.mac_len = authsize; - /* CCM 16Byte Auth_IV: {1B_AFlage,13B_IV,2B_Ptext_length} */ set_aead_auth_iv(ctx, req); - } - - /* GCM 12Byte Cipher_IV == Auth_IV */ - if (ctx->c_ctx.c_mode == SEC_CMODE_GCM) { - ctx->a_ctx.mac_len = authsize; + } else if (ctx->c_ctx.c_mode == SEC_CMODE_GCM) { + /* GCM 12Byte Cipher_IV == Auth_IV */ memcpy(a_req->a_ivin, c_req->c_ivin, SEC_AIV_SIZE); } } @@ -1542,9 +1522,11 @@ static void sec_auth_bd_fill_xcm(struct sec_auth_ctx *ctx, int dir, { struct sec_aead_req *a_req = &req->aead_req; struct aead_request *aq = a_req->aead_req; + struct crypto_aead *tfm = crypto_aead_reqtfm(aq); + size_t authsize = crypto_aead_authsize(tfm); /* C_ICV_Len is MAC size, 0x4 ~ 0x10 */ - sec_sqe->type2.icvw_kmode |= cpu_to_le16((u16)ctx->mac_len); + sec_sqe->type2.icvw_kmode |= cpu_to_le16((u16)authsize); /* mode set to CCM/GCM, don't set {A_Alg, AKey_Len, MAC_Len} */ sec_sqe->type2.a_key_addr = sec_sqe->type2.c_key_addr; @@ -1568,9 +1550,11 @@ static void sec_auth_bd_fill_xcm_v3(struct sec_auth_ctx *ctx, int dir, { struct sec_aead_req *a_req = &req->aead_req; struct aead_request *aq = a_req->aead_req; + struct crypto_aead *tfm = crypto_aead_reqtfm(aq); + size_t authsize = crypto_aead_authsize(tfm); /* C_ICV_Len is MAC size, 0x4 ~ 0x10 */ - sqe3->c_icv_key |= cpu_to_le16((u16)ctx->mac_len << SEC_MAC_OFFSET_V3); + sqe3->c_icv_key |= cpu_to_le16((u16)authsize << SEC_MAC_OFFSET_V3); /* mode set to CCM/GCM, don't set {A_Alg, AKey_Len, MAC_Len} */ sqe3->a_key_addr = sqe3->c_key_addr; @@ -1594,11 +1578,12 @@ static void sec_auth_bd_fill_ex(struct sec_auth_ctx *ctx, int dir, struct sec_aead_req *a_req = &req->aead_req; struct sec_cipher_req *c_req = &req->c_req; struct aead_request *aq = a_req->aead_req; + struct crypto_aead *tfm = crypto_aead_reqtfm(aq); + size_t authsize = crypto_aead_authsize(tfm); sec_sqe->type2.a_key_addr = cpu_to_le64(ctx->a_key_dma); - sec_sqe->type2.mac_key_alg = - cpu_to_le32(ctx->mac_len / SEC_SQE_LEN_RATE); + sec_sqe->type2.mac_key_alg = cpu_to_le32(authsize / SEC_SQE_LEN_RATE); sec_sqe->type2.mac_key_alg |= cpu_to_le32((u32)((ctx->a_key_len) / @@ -1648,11 +1633,13 @@ static void sec_auth_bd_fill_ex_v3(struct sec_auth_ctx *ctx, int dir, struct sec_aead_req *a_req = &req->aead_req; struct sec_cipher_req *c_req = &req->c_req; struct aead_request *aq = a_req->aead_req; + struct crypto_aead *tfm = crypto_aead_reqtfm(aq); + size_t authsize = crypto_aead_authsize(tfm); sqe3->a_key_addr = cpu_to_le64(ctx->a_key_dma); sqe3->auth_mac_key |= - cpu_to_le32((u32)(ctx->mac_len / + cpu_to_le32((u32)(authsize / SEC_SQE_LEN_RATE) << SEC_MAC_OFFSET_V3); sqe3->auth_mac_key |= @@ -1703,9 +1690,9 @@ static void sec_aead_callback(struct sec_ctx *c, struct sec_req *req, int err) { struct aead_request *a_req = req->aead_req.aead_req; struct crypto_aead *tfm = crypto_aead_reqtfm(a_req); + size_t authsize = crypto_aead_authsize(tfm); struct sec_aead_req *aead_req = &req->aead_req; struct sec_cipher_req *c_req = &req->c_req; - size_t authsize = crypto_aead_authsize(tfm); struct sec_qp_ctx *qp_ctx = req->qp_ctx; struct aead_request *backlog_aead_req; struct sec_req *backlog_req; @@ -1718,10 +1705,8 @@ static void sec_aead_callback(struct sec_ctx *c, struct sec_req *req, int err) if (!err && c_req->encrypt) { struct scatterlist *sgl = a_req->dst; - sz = sg_pcopy_from_buffer(sgl, sg_nents(sgl), - aead_req->out_mac, - authsize, a_req->cryptlen + - a_req->assoclen); + sz = sg_pcopy_from_buffer(sgl, sg_nents(sgl), aead_req->out_mac, + authsize, a_req->cryptlen + a_req->assoclen); if (unlikely(sz != authsize)) { dev_err(c->dev, "copy out mac err!\n"); err = -EINVAL; @@ -1929,8 +1914,10 @@ static void sec_aead_exit(struct crypto_aead *tfm) static int sec_aead_ctx_init(struct crypto_aead *tfm, const char *hash_name) { + struct aead_alg *alg = crypto_aead_alg(tfm); struct sec_ctx *ctx = crypto_aead_ctx(tfm); - struct sec_auth_ctx *auth_ctx = &ctx->a_ctx; + struct sec_auth_ctx *a_ctx = &ctx->a_ctx; + const char *aead_name = alg->base.cra_name; int ret; ret = sec_aead_init(tfm); @@ -1939,11 +1926,20 @@ static int sec_aead_ctx_init(struct crypto_aead *tfm, const char *hash_name) return ret; } - auth_ctx->hash_tfm = crypto_alloc_shash(hash_name, 0, 0); - if (IS_ERR(auth_ctx->hash_tfm)) { + a_ctx->hash_tfm = crypto_alloc_shash(hash_name, 0, 0); + if (IS_ERR(a_ctx->hash_tfm)) { dev_err(ctx->dev, "aead alloc shash error!\n"); sec_aead_exit(tfm); - return PTR_ERR(auth_ctx->hash_tfm); + return PTR_ERR(a_ctx->hash_tfm); + } + + a_ctx->fallback_aead_tfm = crypto_alloc_aead(aead_name, 0, + CRYPTO_ALG_NEED_FALLBACK | CRYPTO_ALG_ASYNC); + if (IS_ERR(a_ctx->fallback_aead_tfm)) { + dev_err(ctx->dev, "aead driver alloc fallback tfm error!\n"); + crypto_free_shash(ctx->a_ctx.hash_tfm); + sec_aead_exit(tfm); + return PTR_ERR(a_ctx->fallback_aead_tfm); } return 0; @@ -1953,6 +1949,7 @@ static void sec_aead_ctx_exit(struct crypto_aead *tfm) { struct sec_ctx *ctx = crypto_aead_ctx(tfm); + crypto_free_aead(ctx->a_ctx.fallback_aead_tfm); crypto_free_shash(ctx->a_ctx.hash_tfm); sec_aead_exit(tfm); } @@ -1979,7 +1976,6 @@ static int sec_aead_xcm_ctx_init(struct crypto_aead *tfm) sec_aead_exit(tfm); return PTR_ERR(a_ctx->fallback_aead_tfm); } - a_ctx->fallback = false; return 0; } @@ -2233,21 +2229,20 @@ static int sec_aead_spec_check(struct sec_ctx *ctx, struct sec_req *sreq) { struct aead_request *req = sreq->aead_req.aead_req; struct crypto_aead *tfm = crypto_aead_reqtfm(req); - size_t authsize = crypto_aead_authsize(tfm); + size_t sz = crypto_aead_authsize(tfm); u8 c_mode = ctx->c_ctx.c_mode; struct device *dev = ctx->dev; int ret; - if (unlikely(req->cryptlen + req->assoclen > MAX_INPUT_DATA_LEN || - req->assoclen > SEC_MAX_AAD_LEN)) { - dev_err(dev, "aead input spec error!\n"); + /* Hardware does not handle cases where authsize is less than 4 bytes */ + if (unlikely(sz < MIN_MAC_LEN)) { + sreq->aead_req.fallback = true; return -EINVAL; } - if (unlikely((c_mode == SEC_CMODE_GCM && authsize < DES_BLOCK_SIZE) || - (c_mode == SEC_CMODE_CCM && (authsize < MIN_MAC_LEN || - authsize & MAC_LEN_MASK)))) { - dev_err(dev, "aead input mac length error!\n"); + if (unlikely(req->cryptlen + req->assoclen > MAX_INPUT_DATA_LEN || + req->assoclen > SEC_MAX_AAD_LEN)) { + dev_err(dev, "aead input spec error!\n"); return -EINVAL; } @@ -2266,7 +2261,7 @@ static int sec_aead_spec_check(struct sec_ctx *ctx, struct sec_req *sreq) if (sreq->c_req.encrypt) sreq->c_req.c_len = req->cryptlen; else - sreq->c_req.c_len = req->cryptlen - authsize; + sreq->c_req.c_len = req->cryptlen - sz; if (c_mode == SEC_CMODE_CBC) { if (unlikely(sreq->c_req.c_len & (AES_BLOCK_SIZE - 1))) { dev_err(dev, "aead crypto length error!\n"); @@ -2292,8 +2287,8 @@ static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq) if (ctx->sec->qm.ver == QM_HW_V2) { if (unlikely(!req->cryptlen || (!sreq->c_req.encrypt && - req->cryptlen <= authsize))) { - ctx->a_ctx.fallback = true; + req->cryptlen <= authsize))) { + sreq->aead_req.fallback = true; return -EINVAL; } } @@ -2321,16 +2316,9 @@ static int sec_aead_soft_crypto(struct sec_ctx *ctx, bool encrypt) { struct sec_auth_ctx *a_ctx = &ctx->a_ctx; - struct device *dev = ctx->dev; struct aead_request *subreq; int ret; - /* Kunpeng920 aead mode not support input 0 size */ - if (!a_ctx->fallback_aead_tfm) { - dev_err(dev, "aead fallback tfm is NULL!\n"); - return -EINVAL; - } - subreq = aead_request_alloc(a_ctx->fallback_aead_tfm, GFP_KERNEL); if (!subreq) return -ENOMEM; @@ -2362,10 +2350,11 @@ static int sec_aead_crypto(struct aead_request *a_req, bool encrypt) req->aead_req.aead_req = a_req; req->c_req.encrypt = encrypt; req->ctx = ctx; + req->aead_req.fallback = false; ret = sec_aead_param_check(ctx, req); if (unlikely(ret)) { - if (ctx->a_ctx.fallback) + if (req->aead_req.fallback) return sec_aead_soft_crypto(ctx, a_req, encrypt); return -EINVAL; } diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.h b/drivers/crypto/hisilicon/sec2/sec_crypto.h index 27a0ee5ad913..04725b514382 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.h +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.h @@ -23,17 +23,6 @@ enum sec_hash_alg { SEC_A_HMAC_SHA512 = 0x15, }; -enum sec_mac_len { - SEC_HMAC_CCM_MAC = 16, - SEC_HMAC_GCM_MAC = 16, - SEC_SM3_MAC = 32, - SEC_HMAC_SM3_MAC = 32, - SEC_HMAC_MD5_MAC = 16, - SEC_HMAC_SHA1_MAC = 20, - SEC_HMAC_SHA256_MAC = 32, - SEC_HMAC_SHA512_MAC = 64, -}; - enum sec_cmode { SEC_CMODE_ECB = 0x0, SEC_CMODE_CBC = 0x1, diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index 8ec5333bb5aa..72cf48d1f3ab 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -1097,6 +1097,17 @@ static enum acc_err_result sec_get_err_result(struct hisi_qm *qm) return ACC_ERR_RECOVERED; } +static bool sec_dev_is_abnormal(struct hisi_qm *qm) +{ + u32 err_status; + + err_status = sec_get_hw_err_status(qm); + if (err_status & qm->err_info.dev_shutdown_mask) + return true; + + return false; +} + static void sec_err_info_init(struct hisi_qm *qm) { struct hisi_qm_err_info *err_info = &qm->err_info; @@ -1129,6 +1140,7 @@ static const struct hisi_qm_err_ini sec_err_ini = { .show_last_dfx_regs = sec_show_last_dfx_regs, .err_info_init = sec_err_info_init, .get_err_result = sec_get_err_result, + .dev_is_abnormal = sec_dev_is_abnormal, }; static int sec_pf_probe_init(struct sec_dev *sec) @@ -1180,7 +1192,6 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) int ret; qm->pdev = pdev; - qm->ver = pdev->revision; qm->mode = uacce_mode; qm->sqe_size = SEC_SQE_SIZE; qm->dev_name = sec_name; diff --git a/drivers/crypto/hisilicon/zip/Makefile b/drivers/crypto/hisilicon/zip/Makefile index a936f099ee22..13de020b77d6 100644 --- a/drivers/crypto/hisilicon/zip/Makefile +++ b/drivers/crypto/hisilicon/zip/Makefile @@ -1,2 +1,2 @@ obj-$(CONFIG_CRYPTO_DEV_HISI_ZIP) += hisi_zip.o -hisi_zip-objs = zip_main.o zip_crypto.o +hisi_zip-objs = zip_main.o zip_crypto.o dae_main.o diff --git a/drivers/crypto/hisilicon/zip/dae_main.c b/drivers/crypto/hisilicon/zip/dae_main.c new file mode 100644 index 000000000000..6f22e4c36e49 --- /dev/null +++ b/drivers/crypto/hisilicon/zip/dae_main.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 HiSilicon Limited. */ + +#include +#include +#include +#include "zip.h" + +/* memory */ +#define DAE_MEM_START_OFFSET 0x331040 +#define DAE_MEM_DONE_OFFSET 0x331044 +#define DAE_MEM_START_MASK 0x1 +#define DAE_MEM_DONE_MASK 0x1 +#define DAE_REG_RD_INTVRL_US 10 +#define DAE_REG_RD_TMOUT_US USEC_PER_SEC + +#define DAE_ALG_NAME "hashagg" + +/* error */ +#define DAE_AXI_CFG_OFFSET 0x331000 +#define DAE_AXI_SHUTDOWN_MASK (BIT(0) | BIT(5)) +#define DAE_ERR_SOURCE_OFFSET 0x331C84 +#define DAE_ERR_STATUS_OFFSET 0x331C88 +#define DAE_ERR_CE_OFFSET 0x331CA0 +#define DAE_ERR_CE_MASK BIT(3) +#define DAE_ERR_NFE_OFFSET 0x331CA4 +#define DAE_ERR_NFE_MASK 0x17 +#define DAE_ERR_FE_OFFSET 0x331CA8 +#define DAE_ERR_FE_MASK 0 +#define DAE_ECC_MBIT_MASK BIT(2) +#define DAE_ECC_INFO_OFFSET 0x33400C +#define DAE_ERR_SHUTDOWN_OFFSET 0x331CAC +#define DAE_ERR_SHUTDOWN_MASK 0x17 +#define DAE_ERR_ENABLE_OFFSET 0x331C80 +#define DAE_ERR_ENABLE_MASK (DAE_ERR_FE_MASK | DAE_ERR_NFE_MASK | DAE_ERR_CE_MASK) +#define DAE_AM_CTRL_GLOBAL_OFFSET 0x330000 +#define DAE_AM_RETURN_OFFSET 0x330150 +#define DAE_AM_RETURN_MASK 0x3 +#define DAE_AXI_CFG_OFFSET 0x331000 +#define DAE_AXI_SHUTDOWN_EN_MASK (BIT(0) | BIT(5)) + +struct hisi_dae_hw_error { + u32 int_msk; + const char *msg; +}; + +static const struct hisi_dae_hw_error dae_hw_error[] = { + { .int_msk = BIT(0), .msg = "dae_axi_bus_err" }, + { .int_msk = BIT(1), .msg = "dae_axi_poison_err" }, + { .int_msk = BIT(2), .msg = "dae_ecc_2bit_err" }, + { .int_msk = BIT(3), .msg = "dae_ecc_1bit_err" }, + { .int_msk = BIT(4), .msg = "dae_fsm_hbeat_err" }, +}; + +static inline bool dae_is_support(struct hisi_qm *qm) +{ + if (test_bit(QM_SUPPORT_DAE, &qm->caps)) + return true; + + return false; +} + +int hisi_dae_set_user_domain(struct hisi_qm *qm) +{ + u32 val; + int ret; + + if (!dae_is_support(qm)) + return 0; + + val = readl(qm->io_base + DAE_MEM_START_OFFSET); + val |= DAE_MEM_START_MASK; + writel(val, qm->io_base + DAE_MEM_START_OFFSET); + ret = readl_relaxed_poll_timeout(qm->io_base + DAE_MEM_DONE_OFFSET, val, + val & DAE_MEM_DONE_MASK, + DAE_REG_RD_INTVRL_US, DAE_REG_RD_TMOUT_US); + if (ret) + pci_err(qm->pdev, "failed to init dae memory!\n"); + + return ret; +} + +int hisi_dae_set_alg(struct hisi_qm *qm) +{ + size_t len; + + if (!dae_is_support(qm)) + return 0; + + if (!qm->uacce) + return 0; + + len = strlen(qm->uacce->algs); + /* A line break may be required */ + if (len + strlen(DAE_ALG_NAME) + 1 >= QM_DEV_ALG_MAX_LEN) { + pci_err(qm->pdev, "algorithm name is too long!\n"); + return -EINVAL; + } + + if (len) + strcat((char *)qm->uacce->algs, "\n"); + + strcat((char *)qm->uacce->algs, DAE_ALG_NAME); + + return 0; +} + +static void hisi_dae_master_ooo_ctrl(struct hisi_qm *qm, bool enable) +{ + u32 axi_val, err_val; + + axi_val = readl(qm->io_base + DAE_AXI_CFG_OFFSET); + if (enable) { + axi_val |= DAE_AXI_SHUTDOWN_MASK; + err_val = DAE_ERR_SHUTDOWN_MASK; + } else { + axi_val &= ~DAE_AXI_SHUTDOWN_MASK; + err_val = 0; + } + + writel(axi_val, qm->io_base + DAE_AXI_CFG_OFFSET); + writel(err_val, qm->io_base + DAE_ERR_SHUTDOWN_OFFSET); +} + +void hisi_dae_hw_error_enable(struct hisi_qm *qm) +{ + if (!dae_is_support(qm)) + return; + + /* clear dae hw error source if having */ + writel(DAE_ERR_ENABLE_MASK, qm->io_base + DAE_ERR_SOURCE_OFFSET); + + /* configure error type */ + writel(DAE_ERR_CE_MASK, qm->io_base + DAE_ERR_CE_OFFSET); + writel(DAE_ERR_NFE_MASK, qm->io_base + DAE_ERR_NFE_OFFSET); + writel(DAE_ERR_FE_MASK, qm->io_base + DAE_ERR_FE_OFFSET); + + hisi_dae_master_ooo_ctrl(qm, true); + + /* enable dae hw error interrupts */ + writel(DAE_ERR_ENABLE_MASK, qm->io_base + DAE_ERR_ENABLE_OFFSET); +} + +void hisi_dae_hw_error_disable(struct hisi_qm *qm) +{ + if (!dae_is_support(qm)) + return; + + writel(0, qm->io_base + DAE_ERR_ENABLE_OFFSET); + hisi_dae_master_ooo_ctrl(qm, false); +} + +static u32 hisi_dae_get_hw_err_status(struct hisi_qm *qm) +{ + return readl(qm->io_base + DAE_ERR_STATUS_OFFSET); +} + +static void hisi_dae_clear_hw_err_status(struct hisi_qm *qm, u32 err_sts) +{ + if (!dae_is_support(qm)) + return; + + writel(err_sts, qm->io_base + DAE_ERR_SOURCE_OFFSET); +} + +static void hisi_dae_disable_error_report(struct hisi_qm *qm, u32 err_type) +{ + writel(DAE_ERR_NFE_MASK & (~err_type), qm->io_base + DAE_ERR_NFE_OFFSET); +} + +static void hisi_dae_log_hw_error(struct hisi_qm *qm, u32 err_type) +{ + const struct hisi_dae_hw_error *err = dae_hw_error; + struct device *dev = &qm->pdev->dev; + u32 ecc_info; + size_t i; + + for (i = 0; i < ARRAY_SIZE(dae_hw_error); i++) { + err = &dae_hw_error[i]; + if (!(err->int_msk & err_type)) + continue; + + dev_err(dev, "%s [error status=0x%x] found\n", + err->msg, err->int_msk); + + if (err->int_msk & DAE_ECC_MBIT_MASK) { + ecc_info = readl(qm->io_base + DAE_ECC_INFO_OFFSET); + dev_err(dev, "dae multi ecc sram info 0x%x\n", ecc_info); + } + } +} + +enum acc_err_result hisi_dae_get_err_result(struct hisi_qm *qm) +{ + u32 err_status; + + if (!dae_is_support(qm)) + return ACC_ERR_NONE; + + err_status = hisi_dae_get_hw_err_status(qm); + if (!err_status) + return ACC_ERR_NONE; + + hisi_dae_log_hw_error(qm, err_status); + + if (err_status & DAE_ERR_NFE_MASK) { + /* Disable the same error reporting until device is recovered. */ + hisi_dae_disable_error_report(qm, err_status); + return ACC_ERR_NEED_RESET; + } + hisi_dae_clear_hw_err_status(qm, err_status); + + return ACC_ERR_RECOVERED; +} + +bool hisi_dae_dev_is_abnormal(struct hisi_qm *qm) +{ + u32 err_status; + + if (!dae_is_support(qm)) + return false; + + err_status = hisi_dae_get_hw_err_status(qm); + if (err_status & DAE_ERR_NFE_MASK) + return true; + + return false; +} + +int hisi_dae_close_axi_master_ooo(struct hisi_qm *qm) +{ + u32 val; + int ret; + + if (!dae_is_support(qm)) + return 0; + + val = readl(qm->io_base + DAE_AM_CTRL_GLOBAL_OFFSET); + val |= BIT(0); + writel(val, qm->io_base + DAE_AM_CTRL_GLOBAL_OFFSET); + + ret = readl_relaxed_poll_timeout(qm->io_base + DAE_AM_RETURN_OFFSET, + val, (val == DAE_AM_RETURN_MASK), + DAE_REG_RD_INTVRL_US, DAE_REG_RD_TMOUT_US); + if (ret) + dev_err(&qm->pdev->dev, "failed to close dae axi ooo!\n"); + + return ret; +} + +void hisi_dae_open_axi_master_ooo(struct hisi_qm *qm) +{ + u32 val; + + if (!dae_is_support(qm)) + return; + + val = readl(qm->io_base + DAE_AXI_CFG_OFFSET); + + writel(val & ~DAE_AXI_SHUTDOWN_EN_MASK, qm->io_base + DAE_AXI_CFG_OFFSET); + writel(val | DAE_AXI_SHUTDOWN_EN_MASK, qm->io_base + DAE_AXI_CFG_OFFSET); +} diff --git a/drivers/crypto/hisilicon/zip/zip.h b/drivers/crypto/hisilicon/zip/zip.h index 2fecf346c3c9..9fb2a9c01132 100644 --- a/drivers/crypto/hisilicon/zip/zip.h +++ b/drivers/crypto/hisilicon/zip/zip.h @@ -103,4 +103,12 @@ int zip_create_qps(struct hisi_qp **qps, int qp_num, int node); int hisi_zip_register_to_crypto(struct hisi_qm *qm); void hisi_zip_unregister_from_crypto(struct hisi_qm *qm); bool hisi_zip_alg_support(struct hisi_qm *qm, u32 alg); +int hisi_dae_set_user_domain(struct hisi_qm *qm); +int hisi_dae_set_alg(struct hisi_qm *qm); +void hisi_dae_hw_error_disable(struct hisi_qm *qm); +void hisi_dae_hw_error_enable(struct hisi_qm *qm); +void hisi_dae_open_axi_master_ooo(struct hisi_qm *qm); +int hisi_dae_close_axi_master_ooo(struct hisi_qm *qm); +bool hisi_dae_dev_is_abnormal(struct hisi_qm *qm); +enum acc_err_result hisi_dae_get_err_result(struct hisi_qm *qm); #endif diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 9239b251c2d7..d8ba23b7cc7d 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -582,7 +582,7 @@ static int hisi_zip_set_user_domain_and_cache(struct hisi_qm *qm) hisi_zip_enable_clock_gate(qm); - return 0; + return hisi_dae_set_user_domain(qm); } static void hisi_zip_master_ooo_ctrl(struct hisi_qm *qm, bool enable) @@ -631,6 +631,8 @@ static void hisi_zip_hw_error_enable(struct hisi_qm *qm) /* enable ZIP hw error interrupts */ writel(0, qm->io_base + HZIP_CORE_INT_MASK_REG); + + hisi_dae_hw_error_enable(qm); } static void hisi_zip_hw_error_disable(struct hisi_qm *qm) @@ -643,6 +645,8 @@ static void hisi_zip_hw_error_disable(struct hisi_qm *qm) writel(ce | nfe | HZIP_CORE_INT_RAS_FE_ENB_MASK, qm->io_base + HZIP_CORE_INT_MASK_REG); hisi_zip_master_ooo_ctrl(qm, false); + + hisi_dae_hw_error_disable(qm); } static inline struct hisi_qm *file_to_qm(struct ctrl_debug_file *file) @@ -1129,6 +1133,8 @@ static void hisi_zip_open_axi_master_ooo(struct hisi_qm *qm) writel(val | HZIP_AXI_SHUTDOWN_ENABLE, qm->io_base + HZIP_SOFT_CTRL_ZIP_CONTROL); + + hisi_dae_open_axi_master_ooo(qm); } static void hisi_zip_close_axi_master_ooo(struct hisi_qm *qm) @@ -1147,8 +1153,11 @@ static void hisi_zip_close_axi_master_ooo(struct hisi_qm *qm) static enum acc_err_result hisi_zip_get_err_result(struct hisi_qm *qm) { + enum acc_err_result zip_result = ACC_ERR_NONE; + enum acc_err_result dae_result; u32 err_status; + /* Get device hardware new error status */ err_status = hisi_zip_get_hw_err_status(qm); if (err_status) { if (err_status & qm->err_info.ecc_2bits_mask) @@ -1159,11 +1168,32 @@ static enum acc_err_result hisi_zip_get_err_result(struct hisi_qm *qm) /* Disable the same error reporting until device is recovered. */ hisi_zip_disable_error_report(qm, err_status); return ACC_ERR_NEED_RESET; + } else { + hisi_zip_clear_hw_err_status(qm, err_status); } - hisi_zip_clear_hw_err_status(qm, err_status); } - return ACC_ERR_RECOVERED; + dae_result = hisi_dae_get_err_result(qm); + + return (zip_result == ACC_ERR_NEED_RESET || + dae_result == ACC_ERR_NEED_RESET) ? + ACC_ERR_NEED_RESET : ACC_ERR_RECOVERED; +} + +static bool hisi_zip_dev_is_abnormal(struct hisi_qm *qm) +{ + u32 err_status; + + err_status = hisi_zip_get_hw_err_status(qm); + if (err_status & qm->err_info.dev_shutdown_mask) + return true; + + return hisi_dae_dev_is_abnormal(qm); +} + +static int hisi_zip_set_priv_status(struct hisi_qm *qm) +{ + return hisi_dae_close_axi_master_ooo(qm); } static void hisi_zip_err_info_init(struct hisi_qm *qm) @@ -1200,6 +1230,8 @@ static const struct hisi_qm_err_ini hisi_zip_err_ini = { .show_last_dfx_regs = hisi_zip_show_last_dfx_regs, .err_info_init = hisi_zip_err_info_init, .get_err_result = hisi_zip_get_err_result, + .set_priv_status = hisi_zip_set_priv_status, + .dev_is_abnormal = hisi_zip_dev_is_abnormal, }; static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) @@ -1264,7 +1296,6 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) int ret; qm->pdev = pdev; - qm->ver = pdev->revision; qm->mode = uacce_mode; qm->sqe_size = HZIP_SQE_SIZE; qm->dev_name = hisi_zip_name; @@ -1301,17 +1332,24 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) ret = zip_pre_store_cap_reg(qm); if (ret) { pci_err(qm->pdev, "Failed to pre-store capability registers!\n"); - hisi_qm_uninit(qm); - return ret; + goto err_qm_uninit; } alg_msk = qm->cap_tables.dev_cap_table[ZIP_ALG_BITMAP].cap_val; ret = hisi_qm_set_algs(qm, alg_msk, zip_dev_algs, ARRAY_SIZE(zip_dev_algs)); if (ret) { pci_err(qm->pdev, "Failed to set zip algs!\n"); - hisi_qm_uninit(qm); + goto err_qm_uninit; } + ret = hisi_dae_set_alg(qm); + if (ret) + goto err_qm_uninit; + + return 0; + +err_qm_uninit: + hisi_qm_uninit(qm); return ret; } diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c index 9e557649e5d0..c3776b0de51d 100644 --- a/drivers/crypto/intel/iaa/iaa_crypto_main.c +++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c @@ -173,7 +173,7 @@ static int set_iaa_sync_mode(const char *name) async_mode = false; use_irq = false; } else if (sysfs_streq(name, "async")) { - async_mode = true; + async_mode = false; use_irq = false; } else if (sysfs_streq(name, "async_irq")) { async_mode = true; diff --git a/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c b/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c index 449c6d3ab2db..fcc0cf4df637 100644 --- a/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c +++ b/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c @@ -471,6 +471,7 @@ static int init_ixp_crypto(struct device *dev) return -ENODEV; } npe_id = npe_spec.args[0]; + of_node_put(npe_spec.np); ret = of_parse_phandle_with_fixed_args(np, "queue-rx", 1, 0, &queue_spec); @@ -479,6 +480,7 @@ static int init_ixp_crypto(struct device *dev) return -ENODEV; } recv_qid = queue_spec.args[0]; + of_node_put(queue_spec.np); ret = of_parse_phandle_with_fixed_args(np, "queue-txready", 1, 0, &queue_spec); @@ -487,6 +489,7 @@ static int init_ixp_crypto(struct device *dev) return -ENODEV; } send_qid = queue_spec.args[0]; + of_node_put(queue_spec.np); } else { /* * Hardcoded engine when using platform data, this goes away diff --git a/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c b/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c index c8241f5a0a26..f20ae7e35a0d 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c +++ b/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c @@ -473,22 +473,6 @@ unlock_and_exit: } DEFINE_SHOW_STORE_ATTRIBUTE(tl_control); -static int get_rp_index_from_file(const struct file *f, u8 *rp_id, u8 rp_num) -{ - char alpha; - u8 index; - int ret; - - ret = sscanf(f->f_path.dentry->d_name.name, ADF_TL_RP_REGS_FNAME, &alpha); - if (ret != 1) - return -EINVAL; - - index = ADF_TL_DBG_RP_INDEX_ALPHA(alpha); - *rp_id = index; - - return 0; -} - static int adf_tl_dbg_change_rp_index(struct adf_accel_dev *accel_dev, unsigned int new_rp_num, unsigned int rp_regs_index) @@ -611,18 +595,11 @@ static int tl_rp_data_show(struct seq_file *s, void *unused) { struct adf_accel_dev *accel_dev = s->private; u8 rp_regs_index; - u8 max_rp; - int ret; if (!accel_dev) return -EINVAL; - max_rp = GET_TL_DATA(accel_dev).max_rp; - ret = get_rp_index_from_file(s->file, &rp_regs_index, max_rp); - if (ret) { - dev_dbg(&GET_DEV(accel_dev), "invalid RP data file name\n"); - return ret; - } + rp_regs_index = debugfs_get_aux_num(s->file); return tl_print_rp_data(accel_dev, s, rp_regs_index); } @@ -635,7 +612,6 @@ static ssize_t tl_rp_data_write(struct file *file, const char __user *userbuf, struct adf_telemetry *telemetry; unsigned int new_rp_num; u8 rp_regs_index; - u8 max_rp; int ret; accel_dev = seq_f->private; @@ -643,15 +619,10 @@ static ssize_t tl_rp_data_write(struct file *file, const char __user *userbuf, return -EINVAL; telemetry = accel_dev->telemetry; - max_rp = GET_TL_DATA(accel_dev).max_rp; mutex_lock(&telemetry->wr_lock); - ret = get_rp_index_from_file(file, &rp_regs_index, max_rp); - if (ret) { - dev_dbg(&GET_DEV(accel_dev), "invalid RP data file name\n"); - goto unlock_and_exit; - } + rp_regs_index = debugfs_get_aux_num(file); ret = kstrtou32_from_user(userbuf, count, 10, &new_rp_num); if (ret) @@ -689,7 +660,8 @@ void adf_tl_dbgfs_add(struct adf_accel_dev *accel_dev) for (i = 0; i < max_rp; i++) { snprintf(name, sizeof(name), ADF_TL_RP_REGS_FNAME, ADF_TL_DBG_RP_ALPHA_INDEX(i)); - debugfs_create_file(name, 0644, dir, accel_dev, &tl_rp_data_fops); + debugfs_create_file_aux_num(name, 0644, dir, accel_dev, i, + &tl_rp_data_fops); } } diff --git a/drivers/crypto/n2_asm.S b/drivers/crypto/n2_asm.S deleted file mode 100644 index 9a67dbf340f4..000000000000 --- a/drivers/crypto/n2_asm.S +++ /dev/null @@ -1,96 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* n2_asm.S: Hypervisor calls for NCS support. - * - * Copyright (C) 2009 David S. Miller - */ - -#include -#include -#include "n2_core.h" - - /* o0: queue type - * o1: RA of queue - * o2: num entries in queue - * o3: address of queue handle return - */ -ENTRY(sun4v_ncs_qconf) - mov HV_FAST_NCS_QCONF, %o5 - ta HV_FAST_TRAP - stx %o1, [%o3] - retl - nop -ENDPROC(sun4v_ncs_qconf) - - /* %o0: queue handle - * %o1: address of queue type return - * %o2: address of queue base address return - * %o3: address of queue num entries return - */ -ENTRY(sun4v_ncs_qinfo) - mov %o1, %g1 - mov %o2, %g2 - mov %o3, %g3 - mov HV_FAST_NCS_QINFO, %o5 - ta HV_FAST_TRAP - stx %o1, [%g1] - stx %o2, [%g2] - stx %o3, [%g3] - retl - nop -ENDPROC(sun4v_ncs_qinfo) - - /* %o0: queue handle - * %o1: address of head offset return - */ -ENTRY(sun4v_ncs_gethead) - mov %o1, %o2 - mov HV_FAST_NCS_GETHEAD, %o5 - ta HV_FAST_TRAP - stx %o1, [%o2] - retl - nop -ENDPROC(sun4v_ncs_gethead) - - /* %o0: queue handle - * %o1: address of tail offset return - */ -ENTRY(sun4v_ncs_gettail) - mov %o1, %o2 - mov HV_FAST_NCS_GETTAIL, %o5 - ta HV_FAST_TRAP - stx %o1, [%o2] - retl - nop -ENDPROC(sun4v_ncs_gettail) - - /* %o0: queue handle - * %o1: new tail offset - */ -ENTRY(sun4v_ncs_settail) - mov HV_FAST_NCS_SETTAIL, %o5 - ta HV_FAST_TRAP - retl - nop -ENDPROC(sun4v_ncs_settail) - - /* %o0: queue handle - * %o1: address of devino return - */ -ENTRY(sun4v_ncs_qhandle_to_devino) - mov %o1, %o2 - mov HV_FAST_NCS_QHANDLE_TO_DEVINO, %o5 - ta HV_FAST_TRAP - stx %o1, [%o2] - retl - nop -ENDPROC(sun4v_ncs_qhandle_to_devino) - - /* %o0: queue handle - * %o1: new head offset - */ -ENTRY(sun4v_ncs_sethead_marker) - mov HV_FAST_NCS_SETHEAD_MARKER, %o5 - ta HV_FAST_TRAP - retl - nop -ENDPROC(sun4v_ncs_sethead_marker) diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c deleted file mode 100644 index 14c302d2db79..000000000000 --- a/drivers/crypto/n2_core.c +++ /dev/null @@ -1,2168 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* n2_core.c: Niagara2 Stream Processing Unit (SPU) crypto support. - * - * Copyright (C) 2010, 2011 David S. Miller - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include -#include - -#include "n2_core.h" - -#define DRV_MODULE_NAME "n2_crypto" -#define DRV_MODULE_VERSION "0.2" -#define DRV_MODULE_RELDATE "July 28, 2011" - -static const char version[] = - DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; - -MODULE_AUTHOR("David S. Miller "); -MODULE_DESCRIPTION("Niagara2 Crypto driver"); -MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_MODULE_VERSION); - -#define N2_CRA_PRIORITY 200 - -static DEFINE_MUTEX(spu_lock); - -struct spu_queue { - cpumask_t sharing; - unsigned long qhandle; - - spinlock_t lock; - u8 q_type; - void *q; - unsigned long head; - unsigned long tail; - struct list_head jobs; - - unsigned long devino; - - char irq_name[32]; - unsigned int irq; - - struct list_head list; -}; - -struct spu_qreg { - struct spu_queue *queue; - unsigned long type; -}; - -static struct spu_queue **cpu_to_cwq; -static struct spu_queue **cpu_to_mau; - -static unsigned long spu_next_offset(struct spu_queue *q, unsigned long off) -{ - if (q->q_type == HV_NCS_QTYPE_MAU) { - off += MAU_ENTRY_SIZE; - if (off == (MAU_ENTRY_SIZE * MAU_NUM_ENTRIES)) - off = 0; - } else { - off += CWQ_ENTRY_SIZE; - if (off == (CWQ_ENTRY_SIZE * CWQ_NUM_ENTRIES)) - off = 0; - } - return off; -} - -struct n2_request_common { - struct list_head entry; - unsigned int offset; -}; -#define OFFSET_NOT_RUNNING (~(unsigned int)0) - -/* An async job request records the final tail value it used in - * n2_request_common->offset, test to see if that offset is in - * the range old_head, new_head, inclusive. - */ -static inline bool job_finished(struct spu_queue *q, unsigned int offset, - unsigned long old_head, unsigned long new_head) -{ - if (old_head <= new_head) { - if (offset > old_head && offset <= new_head) - return true; - } else { - if (offset > old_head || offset <= new_head) - return true; - } - return false; -} - -/* When the HEAD marker is unequal to the actual HEAD, we get - * a virtual device INO interrupt. We should process the - * completed CWQ entries and adjust the HEAD marker to clear - * the IRQ. - */ -static irqreturn_t cwq_intr(int irq, void *dev_id) -{ - unsigned long off, new_head, hv_ret; - struct spu_queue *q = dev_id; - - pr_err("CPU[%d]: Got CWQ interrupt for qhdl[%lx]\n", - smp_processor_id(), q->qhandle); - - spin_lock(&q->lock); - - hv_ret = sun4v_ncs_gethead(q->qhandle, &new_head); - - pr_err("CPU[%d]: CWQ gethead[%lx] hv_ret[%lu]\n", - smp_processor_id(), new_head, hv_ret); - - for (off = q->head; off != new_head; off = spu_next_offset(q, off)) { - /* XXX ... XXX */ - } - - hv_ret = sun4v_ncs_sethead_marker(q->qhandle, new_head); - if (hv_ret == HV_EOK) - q->head = new_head; - - spin_unlock(&q->lock); - - return IRQ_HANDLED; -} - -static irqreturn_t mau_intr(int irq, void *dev_id) -{ - struct spu_queue *q = dev_id; - unsigned long head, hv_ret; - - spin_lock(&q->lock); - - pr_err("CPU[%d]: Got MAU interrupt for qhdl[%lx]\n", - smp_processor_id(), q->qhandle); - - hv_ret = sun4v_ncs_gethead(q->qhandle, &head); - - pr_err("CPU[%d]: MAU gethead[%lx] hv_ret[%lu]\n", - smp_processor_id(), head, hv_ret); - - sun4v_ncs_sethead_marker(q->qhandle, head); - - spin_unlock(&q->lock); - - return IRQ_HANDLED; -} - -static void *spu_queue_next(struct spu_queue *q, void *cur) -{ - return q->q + spu_next_offset(q, cur - q->q); -} - -static int spu_queue_num_free(struct spu_queue *q) -{ - unsigned long head = q->head; - unsigned long tail = q->tail; - unsigned long end = (CWQ_ENTRY_SIZE * CWQ_NUM_ENTRIES); - unsigned long diff; - - if (head > tail) - diff = head - tail; - else - diff = (end - tail) + head; - - return (diff / CWQ_ENTRY_SIZE) - 1; -} - -static void *spu_queue_alloc(struct spu_queue *q, int num_entries) -{ - int avail = spu_queue_num_free(q); - - if (avail >= num_entries) - return q->q + q->tail; - - return NULL; -} - -static unsigned long spu_queue_submit(struct spu_queue *q, void *last) -{ - unsigned long hv_ret, new_tail; - - new_tail = spu_next_offset(q, last - q->q); - - hv_ret = sun4v_ncs_settail(q->qhandle, new_tail); - if (hv_ret == HV_EOK) - q->tail = new_tail; - return hv_ret; -} - -static u64 control_word_base(unsigned int len, unsigned int hmac_key_len, - int enc_type, int auth_type, - unsigned int hash_len, - bool sfas, bool sob, bool eob, bool encrypt, - int opcode) -{ - u64 word = (len - 1) & CONTROL_LEN; - - word |= ((u64) opcode << CONTROL_OPCODE_SHIFT); - word |= ((u64) enc_type << CONTROL_ENC_TYPE_SHIFT); - word |= ((u64) auth_type << CONTROL_AUTH_TYPE_SHIFT); - if (sfas) - word |= CONTROL_STORE_FINAL_AUTH_STATE; - if (sob) - word |= CONTROL_START_OF_BLOCK; - if (eob) - word |= CONTROL_END_OF_BLOCK; - if (encrypt) - word |= CONTROL_ENCRYPT; - if (hmac_key_len) - word |= ((u64) (hmac_key_len - 1)) << CONTROL_HMAC_KEY_LEN_SHIFT; - if (hash_len) - word |= ((u64) (hash_len - 1)) << CONTROL_HASH_LEN_SHIFT; - - return word; -} - -#if 0 -static inline bool n2_should_run_async(struct spu_queue *qp, int this_len) -{ - if (this_len >= 64 || - qp->head != qp->tail) - return true; - return false; -} -#endif - -struct n2_ahash_alg { - struct list_head entry; - const u8 *hash_zero; - const u8 *hash_init; - u8 hw_op_hashsz; - u8 digest_size; - u8 auth_type; - u8 hmac_type; - struct ahash_alg alg; -}; - -static inline struct n2_ahash_alg *n2_ahash_alg(struct crypto_tfm *tfm) -{ - struct crypto_alg *alg = tfm->__crt_alg; - struct ahash_alg *ahash_alg; - - ahash_alg = container_of(alg, struct ahash_alg, halg.base); - - return container_of(ahash_alg, struct n2_ahash_alg, alg); -} - -struct n2_hmac_alg { - const char *child_alg; - struct n2_ahash_alg derived; -}; - -static inline struct n2_hmac_alg *n2_hmac_alg(struct crypto_tfm *tfm) -{ - struct crypto_alg *alg = tfm->__crt_alg; - struct ahash_alg *ahash_alg; - - ahash_alg = container_of(alg, struct ahash_alg, halg.base); - - return container_of(ahash_alg, struct n2_hmac_alg, derived.alg); -} - -struct n2_hash_ctx { - struct crypto_ahash *fallback_tfm; -}; - -#define N2_HASH_KEY_MAX 32 /* HW limit for all HMAC requests */ - -struct n2_hmac_ctx { - struct n2_hash_ctx base; - - struct crypto_shash *child_shash; - - int hash_key_len; - unsigned char hash_key[N2_HASH_KEY_MAX]; -}; - -struct n2_hash_req_ctx { - union { - struct md5_state md5; - struct sha1_state sha1; - struct sha256_state sha256; - } u; - - struct ahash_request fallback_req; -}; - -static int n2_hash_async_init(struct ahash_request *req) -{ - struct n2_hash_req_ctx *rctx = ahash_request_ctx(req); - struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct n2_hash_ctx *ctx = crypto_ahash_ctx(tfm); - - ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm); - rctx->fallback_req.base.flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP; - - return crypto_ahash_init(&rctx->fallback_req); -} - -static int n2_hash_async_update(struct ahash_request *req) -{ - struct n2_hash_req_ctx *rctx = ahash_request_ctx(req); - struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct n2_hash_ctx *ctx = crypto_ahash_ctx(tfm); - - ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm); - rctx->fallback_req.base.flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP; - rctx->fallback_req.nbytes = req->nbytes; - rctx->fallback_req.src = req->src; - - return crypto_ahash_update(&rctx->fallback_req); -} - -static int n2_hash_async_final(struct ahash_request *req) -{ - struct n2_hash_req_ctx *rctx = ahash_request_ctx(req); - struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct n2_hash_ctx *ctx = crypto_ahash_ctx(tfm); - - ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm); - rctx->fallback_req.base.flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP; - rctx->fallback_req.result = req->result; - - return crypto_ahash_final(&rctx->fallback_req); -} - -static int n2_hash_async_finup(struct ahash_request *req) -{ - struct n2_hash_req_ctx *rctx = ahash_request_ctx(req); - struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct n2_hash_ctx *ctx = crypto_ahash_ctx(tfm); - - ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm); - rctx->fallback_req.base.flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP; - rctx->fallback_req.nbytes = req->nbytes; - rctx->fallback_req.src = req->src; - rctx->fallback_req.result = req->result; - - return crypto_ahash_finup(&rctx->fallback_req); -} - -static int n2_hash_async_noimport(struct ahash_request *req, const void *in) -{ - return -ENOSYS; -} - -static int n2_hash_async_noexport(struct ahash_request *req, void *out) -{ - return -ENOSYS; -} - -static int n2_hash_cra_init(struct crypto_tfm *tfm) -{ - const char *fallback_driver_name = crypto_tfm_alg_name(tfm); - struct crypto_ahash *ahash = __crypto_ahash_cast(tfm); - struct n2_hash_ctx *ctx = crypto_ahash_ctx(ahash); - struct crypto_ahash *fallback_tfm; - int err; - - fallback_tfm = crypto_alloc_ahash(fallback_driver_name, 0, - CRYPTO_ALG_NEED_FALLBACK); - if (IS_ERR(fallback_tfm)) { - pr_warn("Fallback driver '%s' could not be loaded!\n", - fallback_driver_name); - err = PTR_ERR(fallback_tfm); - goto out; - } - - crypto_ahash_set_reqsize(ahash, (sizeof(struct n2_hash_req_ctx) + - crypto_ahash_reqsize(fallback_tfm))); - - ctx->fallback_tfm = fallback_tfm; - return 0; - -out: - return err; -} - -static void n2_hash_cra_exit(struct crypto_tfm *tfm) -{ - struct crypto_ahash *ahash = __crypto_ahash_cast(tfm); - struct n2_hash_ctx *ctx = crypto_ahash_ctx(ahash); - - crypto_free_ahash(ctx->fallback_tfm); -} - -static int n2_hmac_cra_init(struct crypto_tfm *tfm) -{ - const char *fallback_driver_name = crypto_tfm_alg_name(tfm); - struct crypto_ahash *ahash = __crypto_ahash_cast(tfm); - struct n2_hmac_ctx *ctx = crypto_ahash_ctx(ahash); - struct n2_hmac_alg *n2alg = n2_hmac_alg(tfm); - struct crypto_ahash *fallback_tfm; - struct crypto_shash *child_shash; - int err; - - fallback_tfm = crypto_alloc_ahash(fallback_driver_name, 0, - CRYPTO_ALG_NEED_FALLBACK); - if (IS_ERR(fallback_tfm)) { - pr_warn("Fallback driver '%s' could not be loaded!\n", - fallback_driver_name); - err = PTR_ERR(fallback_tfm); - goto out; - } - - child_shash = crypto_alloc_shash(n2alg->child_alg, 0, 0); - if (IS_ERR(child_shash)) { - pr_warn("Child shash '%s' could not be loaded!\n", - n2alg->child_alg); - err = PTR_ERR(child_shash); - goto out_free_fallback; - } - - crypto_ahash_set_reqsize(ahash, (sizeof(struct n2_hash_req_ctx) + - crypto_ahash_reqsize(fallback_tfm))); - - ctx->child_shash = child_shash; - ctx->base.fallback_tfm = fallback_tfm; - return 0; - -out_free_fallback: - crypto_free_ahash(fallback_tfm); - -out: - return err; -} - -static void n2_hmac_cra_exit(struct crypto_tfm *tfm) -{ - struct crypto_ahash *ahash = __crypto_ahash_cast(tfm); - struct n2_hmac_ctx *ctx = crypto_ahash_ctx(ahash); - - crypto_free_ahash(ctx->base.fallback_tfm); - crypto_free_shash(ctx->child_shash); -} - -static int n2_hmac_async_setkey(struct crypto_ahash *tfm, const u8 *key, - unsigned int keylen) -{ - struct n2_hmac_ctx *ctx = crypto_ahash_ctx(tfm); - struct crypto_shash *child_shash = ctx->child_shash; - struct crypto_ahash *fallback_tfm; - int err, bs, ds; - - fallback_tfm = ctx->base.fallback_tfm; - err = crypto_ahash_setkey(fallback_tfm, key, keylen); - if (err) - return err; - - bs = crypto_shash_blocksize(child_shash); - ds = crypto_shash_digestsize(child_shash); - BUG_ON(ds > N2_HASH_KEY_MAX); - if (keylen > bs) { - err = crypto_shash_tfm_digest(child_shash, key, keylen, - ctx->hash_key); - if (err) - return err; - keylen = ds; - } else if (keylen <= N2_HASH_KEY_MAX) - memcpy(ctx->hash_key, key, keylen); - - ctx->hash_key_len = keylen; - - return err; -} - -static unsigned long wait_for_tail(struct spu_queue *qp) -{ - unsigned long head, hv_ret; - - do { - hv_ret = sun4v_ncs_gethead(qp->qhandle, &head); - if (hv_ret != HV_EOK) { - pr_err("Hypervisor error on gethead\n"); - break; - } - if (head == qp->tail) { - qp->head = head; - break; - } - } while (1); - return hv_ret; -} - -static unsigned long submit_and_wait_for_tail(struct spu_queue *qp, - struct cwq_initial_entry *ent) -{ - unsigned long hv_ret = spu_queue_submit(qp, ent); - - if (hv_ret == HV_EOK) - hv_ret = wait_for_tail(qp); - - return hv_ret; -} - -static int n2_do_async_digest(struct ahash_request *req, - unsigned int auth_type, unsigned int digest_size, - unsigned int result_size, void *hash_loc, - unsigned long auth_key, unsigned int auth_key_len) -{ - struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct cwq_initial_entry *ent; - struct crypto_hash_walk walk; - struct spu_queue *qp; - unsigned long flags; - int err = -ENODEV; - int nbytes, cpu; - - /* The total effective length of the operation may not - * exceed 2^16. - */ - if (unlikely(req->nbytes > (1 << 16))) { - struct n2_hash_req_ctx *rctx = ahash_request_ctx(req); - struct n2_hash_ctx *ctx = crypto_ahash_ctx(tfm); - - ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm); - rctx->fallback_req.base.flags = - req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP; - rctx->fallback_req.nbytes = req->nbytes; - rctx->fallback_req.src = req->src; - rctx->fallback_req.result = req->result; - - return crypto_ahash_digest(&rctx->fallback_req); - } - - nbytes = crypto_hash_walk_first(req, &walk); - - cpu = get_cpu(); - qp = cpu_to_cwq[cpu]; - if (!qp) - goto out; - - spin_lock_irqsave(&qp->lock, flags); - - /* XXX can do better, improve this later by doing a by-hand scatterlist - * XXX walk, etc. - */ - ent = qp->q + qp->tail; - - ent->control = control_word_base(nbytes, auth_key_len, 0, - auth_type, digest_size, - false, true, false, false, - OPCODE_INPLACE_BIT | - OPCODE_AUTH_MAC); - ent->src_addr = __pa(walk.data); - ent->auth_key_addr = auth_key; - ent->auth_iv_addr = __pa(hash_loc); - ent->final_auth_state_addr = 0UL; - ent->enc_key_addr = 0UL; - ent->enc_iv_addr = 0UL; - ent->dest_addr = __pa(hash_loc); - - nbytes = crypto_hash_walk_done(&walk, 0); - while (nbytes > 0) { - ent = spu_queue_next(qp, ent); - - ent->control = (nbytes - 1); - ent->src_addr = __pa(walk.data); - ent->auth_key_addr = 0UL; - ent->auth_iv_addr = 0UL; - ent->final_auth_state_addr = 0UL; - ent->enc_key_addr = 0UL; - ent->enc_iv_addr = 0UL; - ent->dest_addr = 0UL; - - nbytes = crypto_hash_walk_done(&walk, 0); - } - ent->control |= CONTROL_END_OF_BLOCK; - - if (submit_and_wait_for_tail(qp, ent) != HV_EOK) - err = -EINVAL; - else - err = 0; - - spin_unlock_irqrestore(&qp->lock, flags); - - if (!err) - memcpy(req->result, hash_loc, result_size); -out: - put_cpu(); - - return err; -} - -static int n2_hash_async_digest(struct ahash_request *req) -{ - struct n2_ahash_alg *n2alg = n2_ahash_alg(req->base.tfm); - struct n2_hash_req_ctx *rctx = ahash_request_ctx(req); - int ds; - - ds = n2alg->digest_size; - if (unlikely(req->nbytes == 0)) { - memcpy(req->result, n2alg->hash_zero, ds); - return 0; - } - memcpy(&rctx->u, n2alg->hash_init, n2alg->hw_op_hashsz); - - return n2_do_async_digest(req, n2alg->auth_type, - n2alg->hw_op_hashsz, ds, - &rctx->u, 0UL, 0); -} - -static int n2_hmac_async_digest(struct ahash_request *req) -{ - struct n2_hmac_alg *n2alg = n2_hmac_alg(req->base.tfm); - struct n2_hash_req_ctx *rctx = ahash_request_ctx(req); - struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); - struct n2_hmac_ctx *ctx = crypto_ahash_ctx(tfm); - int ds; - - ds = n2alg->derived.digest_size; - if (unlikely(req->nbytes == 0) || - unlikely(ctx->hash_key_len > N2_HASH_KEY_MAX)) { - struct n2_hash_req_ctx *rctx = ahash_request_ctx(req); - struct n2_hash_ctx *ctx = crypto_ahash_ctx(tfm); - - ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm); - rctx->fallback_req.base.flags = - req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP; - rctx->fallback_req.nbytes = req->nbytes; - rctx->fallback_req.src = req->src; - rctx->fallback_req.result = req->result; - - return crypto_ahash_digest(&rctx->fallback_req); - } - memcpy(&rctx->u, n2alg->derived.hash_init, - n2alg->derived.hw_op_hashsz); - - return n2_do_async_digest(req, n2alg->derived.hmac_type, - n2alg->derived.hw_op_hashsz, ds, - &rctx->u, - __pa(&ctx->hash_key), - ctx->hash_key_len); -} - -struct n2_skcipher_context { - int key_len; - int enc_type; - union { - u8 aes[AES_MAX_KEY_SIZE]; - u8 des[DES_KEY_SIZE]; - u8 des3[3 * DES_KEY_SIZE]; - } key; -}; - -#define N2_CHUNK_ARR_LEN 16 - -struct n2_crypto_chunk { - struct list_head entry; - unsigned long iv_paddr : 44; - unsigned long arr_len : 20; - unsigned long dest_paddr; - unsigned long dest_final; - struct { - unsigned long src_paddr : 44; - unsigned long src_len : 20; - } arr[N2_CHUNK_ARR_LEN]; -}; - -struct n2_request_context { - struct skcipher_walk walk; - struct list_head chunk_list; - struct n2_crypto_chunk chunk; - u8 temp_iv[16]; -}; - -/* The SPU allows some level of flexibility for partial cipher blocks - * being specified in a descriptor. - * - * It merely requires that every descriptor's length field is at least - * as large as the cipher block size. This means that a cipher block - * can span at most 2 descriptors. However, this does not allow a - * partial block to span into the final descriptor as that would - * violate the rule (since every descriptor's length must be at lest - * the block size). So, for example, assuming an 8 byte block size: - * - * 0xe --> 0xa --> 0x8 - * - * is a valid length sequence, whereas: - * - * 0xe --> 0xb --> 0x7 - * - * is not a valid sequence. - */ - -struct n2_skcipher_alg { - struct list_head entry; - u8 enc_type; - struct skcipher_alg skcipher; -}; - -static inline struct n2_skcipher_alg *n2_skcipher_alg(struct crypto_skcipher *tfm) -{ - struct skcipher_alg *alg = crypto_skcipher_alg(tfm); - - return container_of(alg, struct n2_skcipher_alg, skcipher); -} - -static int n2_aes_setkey(struct crypto_skcipher *skcipher, const u8 *key, - unsigned int keylen) -{ - struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher); - struct n2_skcipher_context *ctx = crypto_tfm_ctx(tfm); - struct n2_skcipher_alg *n2alg = n2_skcipher_alg(skcipher); - - ctx->enc_type = (n2alg->enc_type & ENC_TYPE_CHAINING_MASK); - - switch (keylen) { - case AES_KEYSIZE_128: - ctx->enc_type |= ENC_TYPE_ALG_AES128; - break; - case AES_KEYSIZE_192: - ctx->enc_type |= ENC_TYPE_ALG_AES192; - break; - case AES_KEYSIZE_256: - ctx->enc_type |= ENC_TYPE_ALG_AES256; - break; - default: - return -EINVAL; - } - - ctx->key_len = keylen; - memcpy(ctx->key.aes, key, keylen); - return 0; -} - -static int n2_des_setkey(struct crypto_skcipher *skcipher, const u8 *key, - unsigned int keylen) -{ - struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher); - struct n2_skcipher_context *ctx = crypto_tfm_ctx(tfm); - struct n2_skcipher_alg *n2alg = n2_skcipher_alg(skcipher); - int err; - - err = verify_skcipher_des_key(skcipher, key); - if (err) - return err; - - ctx->enc_type = n2alg->enc_type; - - ctx->key_len = keylen; - memcpy(ctx->key.des, key, keylen); - return 0; -} - -static int n2_3des_setkey(struct crypto_skcipher *skcipher, const u8 *key, - unsigned int keylen) -{ - struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher); - struct n2_skcipher_context *ctx = crypto_tfm_ctx(tfm); - struct n2_skcipher_alg *n2alg = n2_skcipher_alg(skcipher); - int err; - - err = verify_skcipher_des3_key(skcipher, key); - if (err) - return err; - - ctx->enc_type = n2alg->enc_type; - - ctx->key_len = keylen; - memcpy(ctx->key.des3, key, keylen); - return 0; -} - -static inline int skcipher_descriptor_len(int nbytes, unsigned int block_size) -{ - int this_len = nbytes; - - this_len -= (nbytes & (block_size - 1)); - return this_len > (1 << 16) ? (1 << 16) : this_len; -} - -static int __n2_crypt_chunk(struct crypto_skcipher *skcipher, - struct n2_crypto_chunk *cp, - struct spu_queue *qp, bool encrypt) -{ - struct n2_skcipher_context *ctx = crypto_skcipher_ctx(skcipher); - struct cwq_initial_entry *ent; - bool in_place; - int i; - - ent = spu_queue_alloc(qp, cp->arr_len); - if (!ent) { - pr_info("queue_alloc() of %d fails\n", - cp->arr_len); - return -EBUSY; - } - - in_place = (cp->dest_paddr == cp->arr[0].src_paddr); - - ent->control = control_word_base(cp->arr[0].src_len, - 0, ctx->enc_type, 0, 0, - false, true, false, encrypt, - OPCODE_ENCRYPT | - (in_place ? OPCODE_INPLACE_BIT : 0)); - ent->src_addr = cp->arr[0].src_paddr; - ent->auth_key_addr = 0UL; - ent->auth_iv_addr = 0UL; - ent->final_auth_state_addr = 0UL; - ent->enc_key_addr = __pa(&ctx->key); - ent->enc_iv_addr = cp->iv_paddr; - ent->dest_addr = (in_place ? 0UL : cp->dest_paddr); - - for (i = 1; i < cp->arr_len; i++) { - ent = spu_queue_next(qp, ent); - - ent->control = cp->arr[i].src_len - 1; - ent->src_addr = cp->arr[i].src_paddr; - ent->auth_key_addr = 0UL; - ent->auth_iv_addr = 0UL; - ent->final_auth_state_addr = 0UL; - ent->enc_key_addr = 0UL; - ent->enc_iv_addr = 0UL; - ent->dest_addr = 0UL; - } - ent->control |= CONTROL_END_OF_BLOCK; - - return (spu_queue_submit(qp, ent) != HV_EOK) ? -EINVAL : 0; -} - -static int n2_compute_chunks(struct skcipher_request *req) -{ - struct n2_request_context *rctx = skcipher_request_ctx(req); - struct skcipher_walk *walk = &rctx->walk; - struct n2_crypto_chunk *chunk; - unsigned long dest_prev; - unsigned int tot_len; - bool prev_in_place; - int err, nbytes; - - err = skcipher_walk_async(walk, req); - if (err) - return err; - - INIT_LIST_HEAD(&rctx->chunk_list); - - chunk = &rctx->chunk; - INIT_LIST_HEAD(&chunk->entry); - - chunk->iv_paddr = 0UL; - chunk->arr_len = 0; - chunk->dest_paddr = 0UL; - - prev_in_place = false; - dest_prev = ~0UL; - tot_len = 0; - - while ((nbytes = walk->nbytes) != 0) { - unsigned long dest_paddr, src_paddr; - bool in_place; - int this_len; - - src_paddr = (page_to_phys(walk->src.phys.page) + - walk->src.phys.offset); - dest_paddr = (page_to_phys(walk->dst.phys.page) + - walk->dst.phys.offset); - in_place = (src_paddr == dest_paddr); - this_len = skcipher_descriptor_len(nbytes, walk->blocksize); - - if (chunk->arr_len != 0) { - if (in_place != prev_in_place || - (!prev_in_place && - dest_paddr != dest_prev) || - chunk->arr_len == N2_CHUNK_ARR_LEN || - tot_len + this_len > (1 << 16)) { - chunk->dest_final = dest_prev; - list_add_tail(&chunk->entry, - &rctx->chunk_list); - chunk = kzalloc(sizeof(*chunk), GFP_ATOMIC); - if (!chunk) { - err = -ENOMEM; - break; - } - INIT_LIST_HEAD(&chunk->entry); - } - } - if (chunk->arr_len == 0) { - chunk->dest_paddr = dest_paddr; - tot_len = 0; - } - chunk->arr[chunk->arr_len].src_paddr = src_paddr; - chunk->arr[chunk->arr_len].src_len = this_len; - chunk->arr_len++; - - dest_prev = dest_paddr + this_len; - prev_in_place = in_place; - tot_len += this_len; - - err = skcipher_walk_done(walk, nbytes - this_len); - if (err) - break; - } - if (!err && chunk->arr_len != 0) { - chunk->dest_final = dest_prev; - list_add_tail(&chunk->entry, &rctx->chunk_list); - } - - return err; -} - -static void n2_chunk_complete(struct skcipher_request *req, void *final_iv) -{ - struct n2_request_context *rctx = skcipher_request_ctx(req); - struct n2_crypto_chunk *c, *tmp; - - if (final_iv) - memcpy(rctx->walk.iv, final_iv, rctx->walk.blocksize); - - list_for_each_entry_safe(c, tmp, &rctx->chunk_list, entry) { - list_del(&c->entry); - if (unlikely(c != &rctx->chunk)) - kfree(c); - } - -} - -static int n2_do_ecb(struct skcipher_request *req, bool encrypt) -{ - struct n2_request_context *rctx = skcipher_request_ctx(req); - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - int err = n2_compute_chunks(req); - struct n2_crypto_chunk *c, *tmp; - unsigned long flags, hv_ret; - struct spu_queue *qp; - - if (err) - return err; - - qp = cpu_to_cwq[get_cpu()]; - err = -ENODEV; - if (!qp) - goto out; - - spin_lock_irqsave(&qp->lock, flags); - - list_for_each_entry_safe(c, tmp, &rctx->chunk_list, entry) { - err = __n2_crypt_chunk(tfm, c, qp, encrypt); - if (err) - break; - list_del(&c->entry); - if (unlikely(c != &rctx->chunk)) - kfree(c); - } - if (!err) { - hv_ret = wait_for_tail(qp); - if (hv_ret != HV_EOK) - err = -EINVAL; - } - - spin_unlock_irqrestore(&qp->lock, flags); - -out: - put_cpu(); - - n2_chunk_complete(req, NULL); - return err; -} - -static int n2_encrypt_ecb(struct skcipher_request *req) -{ - return n2_do_ecb(req, true); -} - -static int n2_decrypt_ecb(struct skcipher_request *req) -{ - return n2_do_ecb(req, false); -} - -static int n2_do_chaining(struct skcipher_request *req, bool encrypt) -{ - struct n2_request_context *rctx = skcipher_request_ctx(req); - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - unsigned long flags, hv_ret, iv_paddr; - int err = n2_compute_chunks(req); - struct n2_crypto_chunk *c, *tmp; - struct spu_queue *qp; - void *final_iv_addr; - - final_iv_addr = NULL; - - if (err) - return err; - - qp = cpu_to_cwq[get_cpu()]; - err = -ENODEV; - if (!qp) - goto out; - - spin_lock_irqsave(&qp->lock, flags); - - if (encrypt) { - iv_paddr = __pa(rctx->walk.iv); - list_for_each_entry_safe(c, tmp, &rctx->chunk_list, - entry) { - c->iv_paddr = iv_paddr; - err = __n2_crypt_chunk(tfm, c, qp, true); - if (err) - break; - iv_paddr = c->dest_final - rctx->walk.blocksize; - list_del(&c->entry); - if (unlikely(c != &rctx->chunk)) - kfree(c); - } - final_iv_addr = __va(iv_paddr); - } else { - list_for_each_entry_safe_reverse(c, tmp, &rctx->chunk_list, - entry) { - if (c == &rctx->chunk) { - iv_paddr = __pa(rctx->walk.iv); - } else { - iv_paddr = (tmp->arr[tmp->arr_len-1].src_paddr + - tmp->arr[tmp->arr_len-1].src_len - - rctx->walk.blocksize); - } - if (!final_iv_addr) { - unsigned long pa; - - pa = (c->arr[c->arr_len-1].src_paddr + - c->arr[c->arr_len-1].src_len - - rctx->walk.blocksize); - final_iv_addr = rctx->temp_iv; - memcpy(rctx->temp_iv, __va(pa), - rctx->walk.blocksize); - } - c->iv_paddr = iv_paddr; - err = __n2_crypt_chunk(tfm, c, qp, false); - if (err) - break; - list_del(&c->entry); - if (unlikely(c != &rctx->chunk)) - kfree(c); - } - } - if (!err) { - hv_ret = wait_for_tail(qp); - if (hv_ret != HV_EOK) - err = -EINVAL; - } - - spin_unlock_irqrestore(&qp->lock, flags); - -out: - put_cpu(); - - n2_chunk_complete(req, err ? NULL : final_iv_addr); - return err; -} - -static int n2_encrypt_chaining(struct skcipher_request *req) -{ - return n2_do_chaining(req, true); -} - -static int n2_decrypt_chaining(struct skcipher_request *req) -{ - return n2_do_chaining(req, false); -} - -struct n2_skcipher_tmpl { - const char *name; - const char *drv_name; - u8 block_size; - u8 enc_type; - struct skcipher_alg skcipher; -}; - -static const struct n2_skcipher_tmpl skcipher_tmpls[] = { - /* DES: ECB CBC and CFB are supported */ - { .name = "ecb(des)", - .drv_name = "ecb-des", - .block_size = DES_BLOCK_SIZE, - .enc_type = (ENC_TYPE_ALG_DES | - ENC_TYPE_CHAINING_ECB), - .skcipher = { - .min_keysize = DES_KEY_SIZE, - .max_keysize = DES_KEY_SIZE, - .setkey = n2_des_setkey, - .encrypt = n2_encrypt_ecb, - .decrypt = n2_decrypt_ecb, - }, - }, - { .name = "cbc(des)", - .drv_name = "cbc-des", - .block_size = DES_BLOCK_SIZE, - .enc_type = (ENC_TYPE_ALG_DES | - ENC_TYPE_CHAINING_CBC), - .skcipher = { - .ivsize = DES_BLOCK_SIZE, - .min_keysize = DES_KEY_SIZE, - .max_keysize = DES_KEY_SIZE, - .setkey = n2_des_setkey, - .encrypt = n2_encrypt_chaining, - .decrypt = n2_decrypt_chaining, - }, - }, - - /* 3DES: ECB CBC and CFB are supported */ - { .name = "ecb(des3_ede)", - .drv_name = "ecb-3des", - .block_size = DES_BLOCK_SIZE, - .enc_type = (ENC_TYPE_ALG_3DES | - ENC_TYPE_CHAINING_ECB), - .skcipher = { - .min_keysize = 3 * DES_KEY_SIZE, - .max_keysize = 3 * DES_KEY_SIZE, - .setkey = n2_3des_setkey, - .encrypt = n2_encrypt_ecb, - .decrypt = n2_decrypt_ecb, - }, - }, - { .name = "cbc(des3_ede)", - .drv_name = "cbc-3des", - .block_size = DES_BLOCK_SIZE, - .enc_type = (ENC_TYPE_ALG_3DES | - ENC_TYPE_CHAINING_CBC), - .skcipher = { - .ivsize = DES_BLOCK_SIZE, - .min_keysize = 3 * DES_KEY_SIZE, - .max_keysize = 3 * DES_KEY_SIZE, - .setkey = n2_3des_setkey, - .encrypt = n2_encrypt_chaining, - .decrypt = n2_decrypt_chaining, - }, - }, - - /* AES: ECB CBC and CTR are supported */ - { .name = "ecb(aes)", - .drv_name = "ecb-aes", - .block_size = AES_BLOCK_SIZE, - .enc_type = (ENC_TYPE_ALG_AES128 | - ENC_TYPE_CHAINING_ECB), - .skcipher = { - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .setkey = n2_aes_setkey, - .encrypt = n2_encrypt_ecb, - .decrypt = n2_decrypt_ecb, - }, - }, - { .name = "cbc(aes)", - .drv_name = "cbc-aes", - .block_size = AES_BLOCK_SIZE, - .enc_type = (ENC_TYPE_ALG_AES128 | - ENC_TYPE_CHAINING_CBC), - .skcipher = { - .ivsize = AES_BLOCK_SIZE, - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .setkey = n2_aes_setkey, - .encrypt = n2_encrypt_chaining, - .decrypt = n2_decrypt_chaining, - }, - }, - { .name = "ctr(aes)", - .drv_name = "ctr-aes", - .block_size = AES_BLOCK_SIZE, - .enc_type = (ENC_TYPE_ALG_AES128 | - ENC_TYPE_CHAINING_COUNTER), - .skcipher = { - .ivsize = AES_BLOCK_SIZE, - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .setkey = n2_aes_setkey, - .encrypt = n2_encrypt_chaining, - .decrypt = n2_encrypt_chaining, - }, - }, - -}; -#define NUM_CIPHER_TMPLS ARRAY_SIZE(skcipher_tmpls) - -static LIST_HEAD(skcipher_algs); - -struct n2_hash_tmpl { - const char *name; - const u8 *hash_zero; - const u8 *hash_init; - u8 hw_op_hashsz; - u8 digest_size; - u8 statesize; - u8 block_size; - u8 auth_type; - u8 hmac_type; -}; - -static const __le32 n2_md5_init[MD5_HASH_WORDS] = { - cpu_to_le32(MD5_H0), - cpu_to_le32(MD5_H1), - cpu_to_le32(MD5_H2), - cpu_to_le32(MD5_H3), -}; -static const u32 n2_sha1_init[SHA1_DIGEST_SIZE / 4] = { - SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4, -}; -static const u32 n2_sha256_init[SHA256_DIGEST_SIZE / 4] = { - SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3, - SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7, -}; -static const u32 n2_sha224_init[SHA256_DIGEST_SIZE / 4] = { - SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3, - SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7, -}; - -static const struct n2_hash_tmpl hash_tmpls[] = { - { .name = "md5", - .hash_zero = md5_zero_message_hash, - .hash_init = (u8 *)n2_md5_init, - .auth_type = AUTH_TYPE_MD5, - .hmac_type = AUTH_TYPE_HMAC_MD5, - .hw_op_hashsz = MD5_DIGEST_SIZE, - .digest_size = MD5_DIGEST_SIZE, - .statesize = sizeof(struct md5_state), - .block_size = MD5_HMAC_BLOCK_SIZE }, - { .name = "sha1", - .hash_zero = sha1_zero_message_hash, - .hash_init = (u8 *)n2_sha1_init, - .auth_type = AUTH_TYPE_SHA1, - .hmac_type = AUTH_TYPE_HMAC_SHA1, - .hw_op_hashsz = SHA1_DIGEST_SIZE, - .digest_size = SHA1_DIGEST_SIZE, - .statesize = sizeof(struct sha1_state), - .block_size = SHA1_BLOCK_SIZE }, - { .name = "sha256", - .hash_zero = sha256_zero_message_hash, - .hash_init = (u8 *)n2_sha256_init, - .auth_type = AUTH_TYPE_SHA256, - .hmac_type = AUTH_TYPE_HMAC_SHA256, - .hw_op_hashsz = SHA256_DIGEST_SIZE, - .digest_size = SHA256_DIGEST_SIZE, - .statesize = sizeof(struct sha256_state), - .block_size = SHA256_BLOCK_SIZE }, - { .name = "sha224", - .hash_zero = sha224_zero_message_hash, - .hash_init = (u8 *)n2_sha224_init, - .auth_type = AUTH_TYPE_SHA256, - .hmac_type = AUTH_TYPE_RESERVED, - .hw_op_hashsz = SHA256_DIGEST_SIZE, - .digest_size = SHA224_DIGEST_SIZE, - .statesize = sizeof(struct sha256_state), - .block_size = SHA224_BLOCK_SIZE }, -}; -#define NUM_HASH_TMPLS ARRAY_SIZE(hash_tmpls) - -static LIST_HEAD(ahash_algs); -static LIST_HEAD(hmac_algs); - -static int algs_registered; - -static void __n2_unregister_algs(void) -{ - struct n2_skcipher_alg *skcipher, *skcipher_tmp; - struct n2_ahash_alg *alg, *alg_tmp; - struct n2_hmac_alg *hmac, *hmac_tmp; - - list_for_each_entry_safe(skcipher, skcipher_tmp, &skcipher_algs, entry) { - crypto_unregister_skcipher(&skcipher->skcipher); - list_del(&skcipher->entry); - kfree(skcipher); - } - list_for_each_entry_safe(hmac, hmac_tmp, &hmac_algs, derived.entry) { - crypto_unregister_ahash(&hmac->derived.alg); - list_del(&hmac->derived.entry); - kfree(hmac); - } - list_for_each_entry_safe(alg, alg_tmp, &ahash_algs, entry) { - crypto_unregister_ahash(&alg->alg); - list_del(&alg->entry); - kfree(alg); - } -} - -static int n2_skcipher_init_tfm(struct crypto_skcipher *tfm) -{ - crypto_skcipher_set_reqsize(tfm, sizeof(struct n2_request_context)); - return 0; -} - -static int __n2_register_one_skcipher(const struct n2_skcipher_tmpl *tmpl) -{ - struct n2_skcipher_alg *p = kzalloc(sizeof(*p), GFP_KERNEL); - struct skcipher_alg *alg; - int err; - - if (!p) - return -ENOMEM; - - alg = &p->skcipher; - *alg = tmpl->skcipher; - - snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name); - snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s-n2", tmpl->drv_name); - alg->base.cra_priority = N2_CRA_PRIORITY; - alg->base.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC | - CRYPTO_ALG_ALLOCATES_MEMORY; - alg->base.cra_blocksize = tmpl->block_size; - p->enc_type = tmpl->enc_type; - alg->base.cra_ctxsize = sizeof(struct n2_skcipher_context); - alg->base.cra_module = THIS_MODULE; - alg->init = n2_skcipher_init_tfm; - - list_add(&p->entry, &skcipher_algs); - err = crypto_register_skcipher(alg); - if (err) { - pr_err("%s alg registration failed\n", alg->base.cra_name); - list_del(&p->entry); - kfree(p); - } else { - pr_info("%s alg registered\n", alg->base.cra_name); - } - return err; -} - -static int __n2_register_one_hmac(struct n2_ahash_alg *n2ahash) -{ - struct n2_hmac_alg *p = kzalloc(sizeof(*p), GFP_KERNEL); - struct ahash_alg *ahash; - struct crypto_alg *base; - int err; - - if (!p) - return -ENOMEM; - - p->child_alg = n2ahash->alg.halg.base.cra_name; - memcpy(&p->derived, n2ahash, sizeof(struct n2_ahash_alg)); - INIT_LIST_HEAD(&p->derived.entry); - - ahash = &p->derived.alg; - ahash->digest = n2_hmac_async_digest; - ahash->setkey = n2_hmac_async_setkey; - - base = &ahash->halg.base; - err = -EINVAL; - if (snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)", - p->child_alg) >= CRYPTO_MAX_ALG_NAME) - goto out_free_p; - if (snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "hmac-%s-n2", - p->child_alg) >= CRYPTO_MAX_ALG_NAME) - goto out_free_p; - - base->cra_ctxsize = sizeof(struct n2_hmac_ctx); - base->cra_init = n2_hmac_cra_init; - base->cra_exit = n2_hmac_cra_exit; - - list_add(&p->derived.entry, &hmac_algs); - err = crypto_register_ahash(ahash); - if (err) { - pr_err("%s alg registration failed\n", base->cra_name); - list_del(&p->derived.entry); -out_free_p: - kfree(p); - } else { - pr_info("%s alg registered\n", base->cra_name); - } - return err; -} - -static int __n2_register_one_ahash(const struct n2_hash_tmpl *tmpl) -{ - struct n2_ahash_alg *p = kzalloc(sizeof(*p), GFP_KERNEL); - struct hash_alg_common *halg; - struct crypto_alg *base; - struct ahash_alg *ahash; - int err; - - if (!p) - return -ENOMEM; - - p->hash_zero = tmpl->hash_zero; - p->hash_init = tmpl->hash_init; - p->auth_type = tmpl->auth_type; - p->hmac_type = tmpl->hmac_type; - p->hw_op_hashsz = tmpl->hw_op_hashsz; - p->digest_size = tmpl->digest_size; - - ahash = &p->alg; - ahash->init = n2_hash_async_init; - ahash->update = n2_hash_async_update; - ahash->final = n2_hash_async_final; - ahash->finup = n2_hash_async_finup; - ahash->digest = n2_hash_async_digest; - ahash->export = n2_hash_async_noexport; - ahash->import = n2_hash_async_noimport; - - halg = &ahash->halg; - halg->digestsize = tmpl->digest_size; - halg->statesize = tmpl->statesize; - - base = &halg->base; - snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name); - snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s-n2", tmpl->name); - base->cra_priority = N2_CRA_PRIORITY; - base->cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | - CRYPTO_ALG_NEED_FALLBACK; - base->cra_blocksize = tmpl->block_size; - base->cra_ctxsize = sizeof(struct n2_hash_ctx); - base->cra_module = THIS_MODULE; - base->cra_init = n2_hash_cra_init; - base->cra_exit = n2_hash_cra_exit; - - list_add(&p->entry, &ahash_algs); - err = crypto_register_ahash(ahash); - if (err) { - pr_err("%s alg registration failed\n", base->cra_name); - list_del(&p->entry); - kfree(p); - } else { - pr_info("%s alg registered\n", base->cra_name); - } - if (!err && p->hmac_type != AUTH_TYPE_RESERVED) - err = __n2_register_one_hmac(p); - return err; -} - -static int n2_register_algs(void) -{ - int i, err = 0; - - mutex_lock(&spu_lock); - if (algs_registered++) - goto out; - - for (i = 0; i < NUM_HASH_TMPLS; i++) { - err = __n2_register_one_ahash(&hash_tmpls[i]); - if (err) { - __n2_unregister_algs(); - goto out; - } - } - for (i = 0; i < NUM_CIPHER_TMPLS; i++) { - err = __n2_register_one_skcipher(&skcipher_tmpls[i]); - if (err) { - __n2_unregister_algs(); - goto out; - } - } - -out: - mutex_unlock(&spu_lock); - return err; -} - -static void n2_unregister_algs(void) -{ - mutex_lock(&spu_lock); - if (!--algs_registered) - __n2_unregister_algs(); - mutex_unlock(&spu_lock); -} - -/* To map CWQ queues to interrupt sources, the hypervisor API provides - * a devino. This isn't very useful to us because all of the - * interrupts listed in the device_node have been translated to - * Linux virtual IRQ cookie numbers. - * - * So we have to back-translate, going through the 'intr' and 'ino' - * property tables of the n2cp MDESC node, matching it with the OF - * 'interrupts' property entries, in order to figure out which - * devino goes to which already-translated IRQ. - */ -static int find_devino_index(struct platform_device *dev, struct spu_mdesc_info *ip, - unsigned long dev_ino) -{ - const unsigned int *dev_intrs; - unsigned int intr; - int i; - - for (i = 0; i < ip->num_intrs; i++) { - if (ip->ino_table[i].ino == dev_ino) - break; - } - if (i == ip->num_intrs) - return -ENODEV; - - intr = ip->ino_table[i].intr; - - dev_intrs = of_get_property(dev->dev.of_node, "interrupts", NULL); - if (!dev_intrs) - return -ENODEV; - - for (i = 0; i < dev->archdata.num_irqs; i++) { - if (dev_intrs[i] == intr) - return i; - } - - return -ENODEV; -} - -static int spu_map_ino(struct platform_device *dev, struct spu_mdesc_info *ip, - const char *irq_name, struct spu_queue *p, - irq_handler_t handler) -{ - unsigned long herr; - int index; - - herr = sun4v_ncs_qhandle_to_devino(p->qhandle, &p->devino); - if (herr) - return -EINVAL; - - index = find_devino_index(dev, ip, p->devino); - if (index < 0) - return index; - - p->irq = dev->archdata.irqs[index]; - - sprintf(p->irq_name, "%s-%d", irq_name, index); - - return request_irq(p->irq, handler, 0, p->irq_name, p); -} - -static struct kmem_cache *queue_cache[2]; - -static void *new_queue(unsigned long q_type) -{ - return kmem_cache_zalloc(queue_cache[q_type - 1], GFP_KERNEL); -} - -static void free_queue(void *p, unsigned long q_type) -{ - kmem_cache_free(queue_cache[q_type - 1], p); -} - -static int queue_cache_init(void) -{ - if (!queue_cache[HV_NCS_QTYPE_MAU - 1]) - queue_cache[HV_NCS_QTYPE_MAU - 1] = - kmem_cache_create("mau_queue", - (MAU_NUM_ENTRIES * - MAU_ENTRY_SIZE), - MAU_ENTRY_SIZE, 0, NULL); - if (!queue_cache[HV_NCS_QTYPE_MAU - 1]) - return -ENOMEM; - - if (!queue_cache[HV_NCS_QTYPE_CWQ - 1]) - queue_cache[HV_NCS_QTYPE_CWQ - 1] = - kmem_cache_create("cwq_queue", - (CWQ_NUM_ENTRIES * - CWQ_ENTRY_SIZE), - CWQ_ENTRY_SIZE, 0, NULL); - if (!queue_cache[HV_NCS_QTYPE_CWQ - 1]) { - kmem_cache_destroy(queue_cache[HV_NCS_QTYPE_MAU - 1]); - queue_cache[HV_NCS_QTYPE_MAU - 1] = NULL; - return -ENOMEM; - } - return 0; -} - -static void queue_cache_destroy(void) -{ - kmem_cache_destroy(queue_cache[HV_NCS_QTYPE_MAU - 1]); - kmem_cache_destroy(queue_cache[HV_NCS_QTYPE_CWQ - 1]); - queue_cache[HV_NCS_QTYPE_MAU - 1] = NULL; - queue_cache[HV_NCS_QTYPE_CWQ - 1] = NULL; -} - -static long spu_queue_register_workfn(void *arg) -{ - struct spu_qreg *qr = arg; - struct spu_queue *p = qr->queue; - unsigned long q_type = qr->type; - unsigned long hv_ret; - - hv_ret = sun4v_ncs_qconf(q_type, __pa(p->q), - CWQ_NUM_ENTRIES, &p->qhandle); - if (!hv_ret) - sun4v_ncs_sethead_marker(p->qhandle, 0); - - return hv_ret ? -EINVAL : 0; -} - -static int spu_queue_register(struct spu_queue *p, unsigned long q_type) -{ - int cpu = cpumask_any_and(&p->sharing, cpu_online_mask); - struct spu_qreg qr = { .queue = p, .type = q_type }; - - return work_on_cpu_safe(cpu, spu_queue_register_workfn, &qr); -} - -static int spu_queue_setup(struct spu_queue *p) -{ - int err; - - p->q = new_queue(p->q_type); - if (!p->q) - return -ENOMEM; - - err = spu_queue_register(p, p->q_type); - if (err) { - free_queue(p->q, p->q_type); - p->q = NULL; - } - - return err; -} - -static void spu_queue_destroy(struct spu_queue *p) -{ - unsigned long hv_ret; - - if (!p->q) - return; - - hv_ret = sun4v_ncs_qconf(p->q_type, p->qhandle, 0, &p->qhandle); - - if (!hv_ret) - free_queue(p->q, p->q_type); -} - -static void spu_list_destroy(struct list_head *list) -{ - struct spu_queue *p, *n; - - list_for_each_entry_safe(p, n, list, list) { - int i; - - for (i = 0; i < NR_CPUS; i++) { - if (cpu_to_cwq[i] == p) - cpu_to_cwq[i] = NULL; - } - - if (p->irq) { - free_irq(p->irq, p); - p->irq = 0; - } - spu_queue_destroy(p); - list_del(&p->list); - kfree(p); - } -} - -/* Walk the backward arcs of a CWQ 'exec-unit' node, - * gathering cpu membership information. - */ -static int spu_mdesc_walk_arcs(struct mdesc_handle *mdesc, - struct platform_device *dev, - u64 node, struct spu_queue *p, - struct spu_queue **table) -{ - u64 arc; - - mdesc_for_each_arc(arc, mdesc, node, MDESC_ARC_TYPE_BACK) { - u64 tgt = mdesc_arc_target(mdesc, arc); - const char *name = mdesc_node_name(mdesc, tgt); - const u64 *id; - - if (strcmp(name, "cpu")) - continue; - id = mdesc_get_property(mdesc, tgt, "id", NULL); - if (table[*id] != NULL) { - dev_err(&dev->dev, "%pOF: SPU cpu slot already set.\n", - dev->dev.of_node); - return -EINVAL; - } - cpumask_set_cpu(*id, &p->sharing); - table[*id] = p; - } - return 0; -} - -/* Process an 'exec-unit' MDESC node of type 'cwq'. */ -static int handle_exec_unit(struct spu_mdesc_info *ip, struct list_head *list, - struct platform_device *dev, struct mdesc_handle *mdesc, - u64 node, const char *iname, unsigned long q_type, - irq_handler_t handler, struct spu_queue **table) -{ - struct spu_queue *p; - int err; - - p = kzalloc(sizeof(struct spu_queue), GFP_KERNEL); - if (!p) { - dev_err(&dev->dev, "%pOF: Could not allocate SPU queue.\n", - dev->dev.of_node); - return -ENOMEM; - } - - cpumask_clear(&p->sharing); - spin_lock_init(&p->lock); - p->q_type = q_type; - INIT_LIST_HEAD(&p->jobs); - list_add(&p->list, list); - - err = spu_mdesc_walk_arcs(mdesc, dev, node, p, table); - if (err) - return err; - - err = spu_queue_setup(p); - if (err) - return err; - - return spu_map_ino(dev, ip, iname, p, handler); -} - -static int spu_mdesc_scan(struct mdesc_handle *mdesc, struct platform_device *dev, - struct spu_mdesc_info *ip, struct list_head *list, - const char *exec_name, unsigned long q_type, - irq_handler_t handler, struct spu_queue **table) -{ - int err = 0; - u64 node; - - mdesc_for_each_node_by_name(mdesc, node, "exec-unit") { - const char *type; - - type = mdesc_get_property(mdesc, node, "type", NULL); - if (!type || strcmp(type, exec_name)) - continue; - - err = handle_exec_unit(ip, list, dev, mdesc, node, - exec_name, q_type, handler, table); - if (err) { - spu_list_destroy(list); - break; - } - } - - return err; -} - -static int get_irq_props(struct mdesc_handle *mdesc, u64 node, - struct spu_mdesc_info *ip) -{ - const u64 *ino; - int ino_len; - int i; - - ino = mdesc_get_property(mdesc, node, "ino", &ino_len); - if (!ino) { - printk("NO 'ino'\n"); - return -ENODEV; - } - - ip->num_intrs = ino_len / sizeof(u64); - ip->ino_table = kzalloc((sizeof(struct ino_blob) * - ip->num_intrs), - GFP_KERNEL); - if (!ip->ino_table) - return -ENOMEM; - - for (i = 0; i < ip->num_intrs; i++) { - struct ino_blob *b = &ip->ino_table[i]; - b->intr = i + 1; - b->ino = ino[i]; - } - - return 0; -} - -static int grab_mdesc_irq_props(struct mdesc_handle *mdesc, - struct platform_device *dev, - struct spu_mdesc_info *ip, - const char *node_name) -{ - u64 node, reg; - - if (of_property_read_reg(dev->dev.of_node, 0, ®, NULL) < 0) - return -ENODEV; - - mdesc_for_each_node_by_name(mdesc, node, "virtual-device") { - const char *name; - const u64 *chdl; - - name = mdesc_get_property(mdesc, node, "name", NULL); - if (!name || strcmp(name, node_name)) - continue; - chdl = mdesc_get_property(mdesc, node, "cfg-handle", NULL); - if (!chdl || (*chdl != reg)) - continue; - ip->cfg_handle = *chdl; - return get_irq_props(mdesc, node, ip); - } - - return -ENODEV; -} - -static unsigned long n2_spu_hvapi_major; -static unsigned long n2_spu_hvapi_minor; - -static int n2_spu_hvapi_register(void) -{ - int err; - - n2_spu_hvapi_major = 2; - n2_spu_hvapi_minor = 0; - - err = sun4v_hvapi_register(HV_GRP_NCS, - n2_spu_hvapi_major, - &n2_spu_hvapi_minor); - - if (!err) - pr_info("Registered NCS HVAPI version %lu.%lu\n", - n2_spu_hvapi_major, - n2_spu_hvapi_minor); - - return err; -} - -static void n2_spu_hvapi_unregister(void) -{ - sun4v_hvapi_unregister(HV_GRP_NCS); -} - -static int global_ref; - -static int grab_global_resources(void) -{ - int err = 0; - - mutex_lock(&spu_lock); - - if (global_ref++) - goto out; - - err = n2_spu_hvapi_register(); - if (err) - goto out; - - err = queue_cache_init(); - if (err) - goto out_hvapi_release; - - err = -ENOMEM; - cpu_to_cwq = kcalloc(NR_CPUS, sizeof(struct spu_queue *), - GFP_KERNEL); - if (!cpu_to_cwq) - goto out_queue_cache_destroy; - - cpu_to_mau = kcalloc(NR_CPUS, sizeof(struct spu_queue *), - GFP_KERNEL); - if (!cpu_to_mau) - goto out_free_cwq_table; - - err = 0; - -out: - if (err) - global_ref--; - mutex_unlock(&spu_lock); - return err; - -out_free_cwq_table: - kfree(cpu_to_cwq); - cpu_to_cwq = NULL; - -out_queue_cache_destroy: - queue_cache_destroy(); - -out_hvapi_release: - n2_spu_hvapi_unregister(); - goto out; -} - -static void release_global_resources(void) -{ - mutex_lock(&spu_lock); - if (!--global_ref) { - kfree(cpu_to_cwq); - cpu_to_cwq = NULL; - - kfree(cpu_to_mau); - cpu_to_mau = NULL; - - queue_cache_destroy(); - n2_spu_hvapi_unregister(); - } - mutex_unlock(&spu_lock); -} - -static struct n2_crypto *alloc_n2cp(void) -{ - struct n2_crypto *np = kzalloc(sizeof(struct n2_crypto), GFP_KERNEL); - - if (np) - INIT_LIST_HEAD(&np->cwq_list); - - return np; -} - -static void free_n2cp(struct n2_crypto *np) -{ - kfree(np->cwq_info.ino_table); - np->cwq_info.ino_table = NULL; - - kfree(np); -} - -static void n2_spu_driver_version(void) -{ - static int n2_spu_version_printed; - - if (n2_spu_version_printed++ == 0) - pr_info("%s", version); -} - -static int n2_crypto_probe(struct platform_device *dev) -{ - struct mdesc_handle *mdesc; - struct n2_crypto *np; - int err; - - n2_spu_driver_version(); - - pr_info("Found N2CP at %pOF\n", dev->dev.of_node); - - np = alloc_n2cp(); - if (!np) { - dev_err(&dev->dev, "%pOF: Unable to allocate n2cp.\n", - dev->dev.of_node); - return -ENOMEM; - } - - err = grab_global_resources(); - if (err) { - dev_err(&dev->dev, "%pOF: Unable to grab global resources.\n", - dev->dev.of_node); - goto out_free_n2cp; - } - - mdesc = mdesc_grab(); - - if (!mdesc) { - dev_err(&dev->dev, "%pOF: Unable to grab MDESC.\n", - dev->dev.of_node); - err = -ENODEV; - goto out_free_global; - } - err = grab_mdesc_irq_props(mdesc, dev, &np->cwq_info, "n2cp"); - if (err) { - dev_err(&dev->dev, "%pOF: Unable to grab IRQ props.\n", - dev->dev.of_node); - mdesc_release(mdesc); - goto out_free_global; - } - - err = spu_mdesc_scan(mdesc, dev, &np->cwq_info, &np->cwq_list, - "cwq", HV_NCS_QTYPE_CWQ, cwq_intr, - cpu_to_cwq); - mdesc_release(mdesc); - - if (err) { - dev_err(&dev->dev, "%pOF: CWQ MDESC scan failed.\n", - dev->dev.of_node); - goto out_free_global; - } - - err = n2_register_algs(); - if (err) { - dev_err(&dev->dev, "%pOF: Unable to register algorithms.\n", - dev->dev.of_node); - goto out_free_spu_list; - } - - dev_set_drvdata(&dev->dev, np); - - return 0; - -out_free_spu_list: - spu_list_destroy(&np->cwq_list); - -out_free_global: - release_global_resources(); - -out_free_n2cp: - free_n2cp(np); - - return err; -} - -static void n2_crypto_remove(struct platform_device *dev) -{ - struct n2_crypto *np = dev_get_drvdata(&dev->dev); - - n2_unregister_algs(); - - spu_list_destroy(&np->cwq_list); - - release_global_resources(); - - free_n2cp(np); -} - -static struct n2_mau *alloc_ncp(void) -{ - struct n2_mau *mp = kzalloc(sizeof(struct n2_mau), GFP_KERNEL); - - if (mp) - INIT_LIST_HEAD(&mp->mau_list); - - return mp; -} - -static void free_ncp(struct n2_mau *mp) -{ - kfree(mp->mau_info.ino_table); - mp->mau_info.ino_table = NULL; - - kfree(mp); -} - -static int n2_mau_probe(struct platform_device *dev) -{ - struct mdesc_handle *mdesc; - struct n2_mau *mp; - int err; - - n2_spu_driver_version(); - - pr_info("Found NCP at %pOF\n", dev->dev.of_node); - - mp = alloc_ncp(); - if (!mp) { - dev_err(&dev->dev, "%pOF: Unable to allocate ncp.\n", - dev->dev.of_node); - return -ENOMEM; - } - - err = grab_global_resources(); - if (err) { - dev_err(&dev->dev, "%pOF: Unable to grab global resources.\n", - dev->dev.of_node); - goto out_free_ncp; - } - - mdesc = mdesc_grab(); - - if (!mdesc) { - dev_err(&dev->dev, "%pOF: Unable to grab MDESC.\n", - dev->dev.of_node); - err = -ENODEV; - goto out_free_global; - } - - err = grab_mdesc_irq_props(mdesc, dev, &mp->mau_info, "ncp"); - if (err) { - dev_err(&dev->dev, "%pOF: Unable to grab IRQ props.\n", - dev->dev.of_node); - mdesc_release(mdesc); - goto out_free_global; - } - - err = spu_mdesc_scan(mdesc, dev, &mp->mau_info, &mp->mau_list, - "mau", HV_NCS_QTYPE_MAU, mau_intr, - cpu_to_mau); - mdesc_release(mdesc); - - if (err) { - dev_err(&dev->dev, "%pOF: MAU MDESC scan failed.\n", - dev->dev.of_node); - goto out_free_global; - } - - dev_set_drvdata(&dev->dev, mp); - - return 0; - -out_free_global: - release_global_resources(); - -out_free_ncp: - free_ncp(mp); - - return err; -} - -static void n2_mau_remove(struct platform_device *dev) -{ - struct n2_mau *mp = dev_get_drvdata(&dev->dev); - - spu_list_destroy(&mp->mau_list); - - release_global_resources(); - - free_ncp(mp); -} - -static const struct of_device_id n2_crypto_match[] = { - { - .name = "n2cp", - .compatible = "SUNW,n2-cwq", - }, - { - .name = "n2cp", - .compatible = "SUNW,vf-cwq", - }, - { - .name = "n2cp", - .compatible = "SUNW,kt-cwq", - }, - {}, -}; - -MODULE_DEVICE_TABLE(of, n2_crypto_match); - -static struct platform_driver n2_crypto_driver = { - .driver = { - .name = "n2cp", - .of_match_table = n2_crypto_match, - }, - .probe = n2_crypto_probe, - .remove = n2_crypto_remove, -}; - -static const struct of_device_id n2_mau_match[] = { - { - .name = "ncp", - .compatible = "SUNW,n2-mau", - }, - { - .name = "ncp", - .compatible = "SUNW,vf-mau", - }, - { - .name = "ncp", - .compatible = "SUNW,kt-mau", - }, - {}, -}; - -MODULE_DEVICE_TABLE(of, n2_mau_match); - -static struct platform_driver n2_mau_driver = { - .driver = { - .name = "ncp", - .of_match_table = n2_mau_match, - }, - .probe = n2_mau_probe, - .remove = n2_mau_remove, -}; - -static struct platform_driver * const drivers[] = { - &n2_crypto_driver, - &n2_mau_driver, -}; - -static int __init n2_init(void) -{ - return platform_register_drivers(drivers, ARRAY_SIZE(drivers)); -} - -static void __exit n2_exit(void) -{ - platform_unregister_drivers(drivers, ARRAY_SIZE(drivers)); -} - -module_init(n2_init); -module_exit(n2_exit); diff --git a/drivers/crypto/n2_core.h b/drivers/crypto/n2_core.h deleted file mode 100644 index 2406763b0306..000000000000 --- a/drivers/crypto/n2_core.h +++ /dev/null @@ -1,232 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _N2_CORE_H -#define _N2_CORE_H - -#ifndef __ASSEMBLY__ - -struct ino_blob { - u64 intr; - u64 ino; -}; - -struct spu_mdesc_info { - u64 cfg_handle; - struct ino_blob *ino_table; - int num_intrs; -}; - -struct n2_crypto { - struct spu_mdesc_info cwq_info; - struct list_head cwq_list; -}; - -struct n2_mau { - struct spu_mdesc_info mau_info; - struct list_head mau_list; -}; - -#define CWQ_ENTRY_SIZE 64 -#define CWQ_NUM_ENTRIES 64 - -#define MAU_ENTRY_SIZE 64 -#define MAU_NUM_ENTRIES 64 - -struct cwq_initial_entry { - u64 control; - u64 src_addr; - u64 auth_key_addr; - u64 auth_iv_addr; - u64 final_auth_state_addr; - u64 enc_key_addr; - u64 enc_iv_addr; - u64 dest_addr; -}; - -struct cwq_ext_entry { - u64 len; - u64 src_addr; - u64 resv1; - u64 resv2; - u64 resv3; - u64 resv4; - u64 resv5; - u64 resv6; -}; - -struct cwq_final_entry { - u64 control; - u64 src_addr; - u64 resv1; - u64 resv2; - u64 resv3; - u64 resv4; - u64 resv5; - u64 resv6; -}; - -#define CONTROL_LEN 0x000000000000ffffULL -#define CONTROL_LEN_SHIFT 0 -#define CONTROL_HMAC_KEY_LEN 0x0000000000ff0000ULL -#define CONTROL_HMAC_KEY_LEN_SHIFT 16 -#define CONTROL_ENC_TYPE 0x00000000ff000000ULL -#define CONTROL_ENC_TYPE_SHIFT 24 -#define ENC_TYPE_ALG_RC4_STREAM 0x00ULL -#define ENC_TYPE_ALG_RC4_NOSTREAM 0x04ULL -#define ENC_TYPE_ALG_DES 0x08ULL -#define ENC_TYPE_ALG_3DES 0x0cULL -#define ENC_TYPE_ALG_AES128 0x10ULL -#define ENC_TYPE_ALG_AES192 0x14ULL -#define ENC_TYPE_ALG_AES256 0x18ULL -#define ENC_TYPE_ALG_RESERVED 0x1cULL -#define ENC_TYPE_ALG_MASK 0x1cULL -#define ENC_TYPE_CHAINING_ECB 0x00ULL -#define ENC_TYPE_CHAINING_CBC 0x01ULL -#define ENC_TYPE_CHAINING_CFB 0x02ULL -#define ENC_TYPE_CHAINING_COUNTER 0x03ULL -#define ENC_TYPE_CHAINING_MASK 0x03ULL -#define CONTROL_AUTH_TYPE 0x0000001f00000000ULL -#define CONTROL_AUTH_TYPE_SHIFT 32 -#define AUTH_TYPE_RESERVED 0x00ULL -#define AUTH_TYPE_MD5 0x01ULL -#define AUTH_TYPE_SHA1 0x02ULL -#define AUTH_TYPE_SHA256 0x03ULL -#define AUTH_TYPE_CRC32 0x04ULL -#define AUTH_TYPE_HMAC_MD5 0x05ULL -#define AUTH_TYPE_HMAC_SHA1 0x06ULL -#define AUTH_TYPE_HMAC_SHA256 0x07ULL -#define AUTH_TYPE_TCP_CHECKSUM 0x08ULL -#define AUTH_TYPE_SSL_HMAC_MD5 0x09ULL -#define AUTH_TYPE_SSL_HMAC_SHA1 0x0aULL -#define AUTH_TYPE_SSL_HMAC_SHA256 0x0bULL -#define CONTROL_STRAND 0x000000e000000000ULL -#define CONTROL_STRAND_SHIFT 37 -#define CONTROL_HASH_LEN 0x0000ff0000000000ULL -#define CONTROL_HASH_LEN_SHIFT 40 -#define CONTROL_INTERRUPT 0x0001000000000000ULL -#define CONTROL_STORE_FINAL_AUTH_STATE 0x0002000000000000ULL -#define CONTROL_RESERVED 0x001c000000000000ULL -#define CONTROL_HV_DONE 0x0004000000000000ULL -#define CONTROL_HV_PROTOCOL_ERROR 0x0008000000000000ULL -#define CONTROL_HV_HARDWARE_ERROR 0x0010000000000000ULL -#define CONTROL_END_OF_BLOCK 0x0020000000000000ULL -#define CONTROL_START_OF_BLOCK 0x0040000000000000ULL -#define CONTROL_ENCRYPT 0x0080000000000000ULL -#define CONTROL_OPCODE 0xff00000000000000ULL -#define CONTROL_OPCODE_SHIFT 56 -#define OPCODE_INPLACE_BIT 0x80ULL -#define OPCODE_SSL_KEYBLOCK 0x10ULL -#define OPCODE_COPY 0x20ULL -#define OPCODE_ENCRYPT 0x40ULL -#define OPCODE_AUTH_MAC 0x41ULL - -#endif /* !(__ASSEMBLY__) */ - -/* NCS v2.0 hypervisor interfaces */ -#define HV_NCS_QTYPE_MAU 0x01 -#define HV_NCS_QTYPE_CWQ 0x02 - -/* ncs_qconf() - * TRAP: HV_FAST_TRAP - * FUNCTION: HV_FAST_NCS_QCONF - * ARG0: Queue type (HV_NCS_QTYPE_{MAU,CWQ}) - * ARG1: Real address of queue, or handle for unconfigure - * ARG2: Number of entries in queue, zero for unconfigure - * RET0: status - * RET1: queue handle - * - * Configure a queue in the stream processing unit. - * - * The real address given as the base must be 64-byte - * aligned. - * - * The queue size can range from a minimum of 2 to a maximum - * of 64. The queue size must be a power of two. - * - * To unconfigure a queue, specify a length of zero and place - * the queue handle into ARG1. - * - * On configure success the hypervisor will set the FIRST, HEAD, - * and TAIL registers to the address of the first entry in the - * queue. The LAST register will be set to point to the last - * entry in the queue. - */ -#define HV_FAST_NCS_QCONF 0x111 - -/* ncs_qinfo() - * TRAP: HV_FAST_TRAP - * FUNCTION: HV_FAST_NCS_QINFO - * ARG0: Queue handle - * RET0: status - * RET1: Queue type (HV_NCS_QTYPE_{MAU,CWQ}) - * RET2: Queue base address - * RET3: Number of entries - */ -#define HV_FAST_NCS_QINFO 0x112 - -/* ncs_gethead() - * TRAP: HV_FAST_TRAP - * FUNCTION: HV_FAST_NCS_GETHEAD - * ARG0: Queue handle - * RET0: status - * RET1: queue head offset - */ -#define HV_FAST_NCS_GETHEAD 0x113 - -/* ncs_gettail() - * TRAP: HV_FAST_TRAP - * FUNCTION: HV_FAST_NCS_GETTAIL - * ARG0: Queue handle - * RET0: status - * RET1: queue tail offset - */ -#define HV_FAST_NCS_GETTAIL 0x114 - -/* ncs_settail() - * TRAP: HV_FAST_TRAP - * FUNCTION: HV_FAST_NCS_SETTAIL - * ARG0: Queue handle - * ARG1: New tail offset - * RET0: status - */ -#define HV_FAST_NCS_SETTAIL 0x115 - -/* ncs_qhandle_to_devino() - * TRAP: HV_FAST_TRAP - * FUNCTION: HV_FAST_NCS_QHANDLE_TO_DEVINO - * ARG0: Queue handle - * RET0: status - * RET1: devino - */ -#define HV_FAST_NCS_QHANDLE_TO_DEVINO 0x116 - -/* ncs_sethead_marker() - * TRAP: HV_FAST_TRAP - * FUNCTION: HV_FAST_NCS_SETHEAD_MARKER - * ARG0: Queue handle - * ARG1: New head offset - * RET0: status - */ -#define HV_FAST_NCS_SETHEAD_MARKER 0x117 - -#ifndef __ASSEMBLY__ -extern unsigned long sun4v_ncs_qconf(unsigned long queue_type, - unsigned long queue_ra, - unsigned long num_entries, - unsigned long *qhandle); -extern unsigned long sun4v_ncs_qinfo(unsigned long qhandle, - unsigned long *queue_type, - unsigned long *queue_ra, - unsigned long *num_entries); -extern unsigned long sun4v_ncs_gethead(unsigned long qhandle, - unsigned long *head); -extern unsigned long sun4v_ncs_gettail(unsigned long qhandle, - unsigned long *tail); -extern unsigned long sun4v_ncs_settail(unsigned long qhandle, - unsigned long tail); -extern unsigned long sun4v_ncs_qhandle_to_devino(unsigned long qhandle, - unsigned long *devino); -extern unsigned long sun4v_ncs_sethead_marker(unsigned long qhandle, - unsigned long head); -#endif /* !(__ASSEMBLY__) */ - -#endif /* _N2_CORE_H */ diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c index e27b84616743..551dd32a8db0 100644 --- a/drivers/crypto/omap-aes.c +++ b/drivers/crypto/omap-aes.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -272,9 +271,9 @@ static int omap_aes_crypt_dma(struct omap_aes_dev *dd, int ret; if (dd->pio_only) { - scatterwalk_start(&dd->in_walk, dd->in_sg); + dd->in_sg_offset = 0; if (out_sg_len) - scatterwalk_start(&dd->out_walk, dd->out_sg); + dd->out_sg_offset = 0; /* Enable DATAIN interrupt and let it take care of the rest */ @@ -871,21 +870,18 @@ static irqreturn_t omap_aes_irq(int irq, void *dev_id) BUG_ON(!dd->in_sg); - BUG_ON(_calc_walked(in) > dd->in_sg->length); + BUG_ON(dd->in_sg_offset > dd->in_sg->length); - src = sg_virt(dd->in_sg) + _calc_walked(in); + src = sg_virt(dd->in_sg) + dd->in_sg_offset; for (i = 0; i < AES_BLOCK_WORDS; i++) { omap_aes_write(dd, AES_REG_DATA_N(dd, i), *src); - - scatterwalk_advance(&dd->in_walk, 4); - if (dd->in_sg->length == _calc_walked(in)) { + dd->in_sg_offset += 4; + if (dd->in_sg_offset == dd->in_sg->length) { dd->in_sg = sg_next(dd->in_sg); if (dd->in_sg) { - scatterwalk_start(&dd->in_walk, - dd->in_sg); - src = sg_virt(dd->in_sg) + - _calc_walked(in); + dd->in_sg_offset = 0; + src = sg_virt(dd->in_sg); } } else { src++; @@ -904,20 +900,18 @@ static irqreturn_t omap_aes_irq(int irq, void *dev_id) BUG_ON(!dd->out_sg); - BUG_ON(_calc_walked(out) > dd->out_sg->length); + BUG_ON(dd->out_sg_offset > dd->out_sg->length); - dst = sg_virt(dd->out_sg) + _calc_walked(out); + dst = sg_virt(dd->out_sg) + dd->out_sg_offset; for (i = 0; i < AES_BLOCK_WORDS; i++) { *dst = omap_aes_read(dd, AES_REG_DATA_N(dd, i)); - scatterwalk_advance(&dd->out_walk, 4); - if (dd->out_sg->length == _calc_walked(out)) { + dd->out_sg_offset += 4; + if (dd->out_sg_offset == dd->out_sg->length) { dd->out_sg = sg_next(dd->out_sg); if (dd->out_sg) { - scatterwalk_start(&dd->out_walk, - dd->out_sg); - dst = sg_virt(dd->out_sg) + - _calc_walked(out); + dd->out_sg_offset = 0; + dst = sg_virt(dd->out_sg); } } else { dst++; diff --git a/drivers/crypto/omap-aes.h b/drivers/crypto/omap-aes.h index 0f35c9164764..41d67780fd45 100644 --- a/drivers/crypto/omap-aes.h +++ b/drivers/crypto/omap-aes.h @@ -14,8 +14,6 @@ #define DST_MAXBURST 4 #define DMA_MIN (DST_MAXBURST * sizeof(u32)) -#define _calc_walked(inout) (dd->inout##_walk.offset - dd->inout##_sg->offset) - /* * OMAP TRM gives bitfields as start:end, where start is the higher bit * number. For example 7:0 @@ -186,8 +184,8 @@ struct omap_aes_dev { struct scatterlist out_sgl; struct scatterlist *orig_out; - struct scatter_walk in_walk; - struct scatter_walk out_walk; + unsigned int in_sg_offset; + unsigned int out_sg_offset; struct dma_chan *dma_lch_in; struct dma_chan *dma_lch_out; int in_sg_len; diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c index 498cbd585ed1..a099460d5f21 100644 --- a/drivers/crypto/omap-des.c +++ b/drivers/crypto/omap-des.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -40,8 +39,6 @@ #define DES_BLOCK_WORDS (DES_BLOCK_SIZE >> 2) -#define _calc_walked(inout) (dd->inout##_walk.offset - dd->inout##_sg->offset) - #define DES_REG_KEY(dd, x) ((dd)->pdata->key_ofs - \ ((x ^ 0x01) * 0x04)) @@ -152,8 +149,8 @@ struct omap_des_dev { struct scatterlist out_sgl; struct scatterlist *orig_out; - struct scatter_walk in_walk; - struct scatter_walk out_walk; + unsigned int in_sg_offset; + unsigned int out_sg_offset; struct dma_chan *dma_lch_in; struct dma_chan *dma_lch_out; int in_sg_len; @@ -379,8 +376,8 @@ static int omap_des_crypt_dma(struct crypto_tfm *tfm, int ret; if (dd->pio_only) { - scatterwalk_start(&dd->in_walk, dd->in_sg); - scatterwalk_start(&dd->out_walk, dd->out_sg); + dd->in_sg_offset = 0; + dd->out_sg_offset = 0; /* Enable DATAIN interrupt and let it take care of the rest */ @@ -836,21 +833,18 @@ static irqreturn_t omap_des_irq(int irq, void *dev_id) BUG_ON(!dd->in_sg); - BUG_ON(_calc_walked(in) > dd->in_sg->length); + BUG_ON(dd->in_sg_offset > dd->in_sg->length); - src = sg_virt(dd->in_sg) + _calc_walked(in); + src = sg_virt(dd->in_sg) + dd->in_sg_offset; for (i = 0; i < DES_BLOCK_WORDS; i++) { omap_des_write(dd, DES_REG_DATA_N(dd, i), *src); - - scatterwalk_advance(&dd->in_walk, 4); - if (dd->in_sg->length == _calc_walked(in)) { + dd->in_sg_offset += 4; + if (dd->in_sg_offset == dd->in_sg->length) { dd->in_sg = sg_next(dd->in_sg); if (dd->in_sg) { - scatterwalk_start(&dd->in_walk, - dd->in_sg); - src = sg_virt(dd->in_sg) + - _calc_walked(in); + dd->in_sg_offset = 0; + src = sg_virt(dd->in_sg); } } else { src++; @@ -869,20 +863,18 @@ static irqreturn_t omap_des_irq(int irq, void *dev_id) BUG_ON(!dd->out_sg); - BUG_ON(_calc_walked(out) > dd->out_sg->length); + BUG_ON(dd->out_sg_offset > dd->out_sg->length); - dst = sg_virt(dd->out_sg) + _calc_walked(out); + dst = sg_virt(dd->out_sg) + dd->out_sg_offset; for (i = 0; i < DES_BLOCK_WORDS; i++) { *dst = omap_des_read(dd, DES_REG_DATA_N(dd, i)); - scatterwalk_advance(&dd->out_walk, 4); - if (dd->out_sg->length == _calc_walked(out)) { + dd->out_sg_offset += 4; + if (dd->out_sg_offset == dd->out_sg->length) { dd->out_sg = sg_next(dd->out_sg); if (dd->out_sg) { - scatterwalk_start(&dd->out_walk, - dd->out_sg); - dst = sg_virt(dd->out_sg) + - _calc_walked(out); + dd->out_sg_offset = 0; + dst = sg_virt(dd->out_sg); } } else { dst++; diff --git a/drivers/crypto/qce/aead.c b/drivers/crypto/qce/aead.c index 7d811728f047..97b56e92ea33 100644 --- a/drivers/crypto/qce/aead.c +++ b/drivers/crypto/qce/aead.c @@ -786,7 +786,7 @@ static int qce_aead_register_one(const struct qce_aead_def *def, struct qce_devi alg->init = qce_aead_init; alg->exit = qce_aead_exit; - alg->base.cra_priority = 300; + alg->base.cra_priority = 275; alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY | CRYPTO_ALG_KERN_DRIVER_ONLY | diff --git a/drivers/crypto/qce/core.c b/drivers/crypto/qce/core.c index e228a31fe28d..e95e84486d9a 100644 --- a/drivers/crypto/qce/core.c +++ b/drivers/crypto/qce/core.c @@ -3,14 +3,15 @@ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved. */ +#include #include +#include #include #include #include #include #include #include -#include #include #include #include @@ -37,9 +38,10 @@ static const struct qce_algo_ops *qce_ops[] = { #endif }; -static void qce_unregister_algs(struct qce_device *qce) +static void qce_unregister_algs(void *data) { const struct qce_algo_ops *ops; + struct qce_device *qce = data; int i; for (i = 0; i < ARRAY_SIZE(qce_ops); i++) { @@ -48,19 +50,22 @@ static void qce_unregister_algs(struct qce_device *qce) } } -static int qce_register_algs(struct qce_device *qce) +static int devm_qce_register_algs(struct qce_device *qce) { const struct qce_algo_ops *ops; - int i, ret = -ENODEV; + int i, j, ret = -ENODEV; for (i = 0; i < ARRAY_SIZE(qce_ops); i++) { ops = qce_ops[i]; ret = ops->register_algs(qce); - if (ret) - break; + if (ret) { + for (j = i - 1; j >= 0; j--) + ops->unregister_algs(qce); + return ret; + } } - return ret; + return devm_add_action_or_reset(qce->dev, qce_unregister_algs, qce); } static int qce_handle_request(struct crypto_async_request *async_req) @@ -84,55 +89,49 @@ static int qce_handle_queue(struct qce_device *qce, struct crypto_async_request *req) { struct crypto_async_request *async_req, *backlog; - unsigned long flags; int ret = 0, err; - spin_lock_irqsave(&qce->lock, flags); + scoped_guard(mutex, &qce->lock) { + if (req) + ret = crypto_enqueue_request(&qce->queue, req); - if (req) - ret = crypto_enqueue_request(&qce->queue, req); + /* busy, do not dequeue request */ + if (qce->req) + return ret; - /* busy, do not dequeue request */ - if (qce->req) { - spin_unlock_irqrestore(&qce->lock, flags); - return ret; + backlog = crypto_get_backlog(&qce->queue); + async_req = crypto_dequeue_request(&qce->queue); + if (async_req) + qce->req = async_req; } - backlog = crypto_get_backlog(&qce->queue); - async_req = crypto_dequeue_request(&qce->queue); - if (async_req) - qce->req = async_req; - - spin_unlock_irqrestore(&qce->lock, flags); - if (!async_req) return ret; if (backlog) { - spin_lock_bh(&qce->lock); - crypto_request_complete(backlog, -EINPROGRESS); - spin_unlock_bh(&qce->lock); + scoped_guard(mutex, &qce->lock) + crypto_request_complete(backlog, -EINPROGRESS); } err = qce_handle_request(async_req); if (err) { qce->result = err; - tasklet_schedule(&qce->done_tasklet); + schedule_work(&qce->done_work); } return ret; } -static void qce_tasklet_req_done(unsigned long data) +static void qce_req_done_work(struct work_struct *work) { - struct qce_device *qce = (struct qce_device *)data; + struct qce_device *qce = container_of(work, struct qce_device, + done_work); struct crypto_async_request *req; - unsigned long flags; - spin_lock_irqsave(&qce->lock, flags); - req = qce->req; - qce->req = NULL; - spin_unlock_irqrestore(&qce->lock, flags); + scoped_guard(mutex, &qce->lock) { + req = qce->req; + qce->req = NULL; + } if (req) crypto_request_complete(req, qce->result); @@ -149,7 +148,7 @@ static int qce_async_request_enqueue(struct qce_device *qce, static void qce_async_request_done(struct qce_device *qce, int ret) { qce->result = ret; - tasklet_schedule(&qce->done_tasklet); + schedule_work(&qce->done_work); } static int qce_check_version(struct qce_device *qce) @@ -209,15 +208,15 @@ static int qce_crypto_probe(struct platform_device *pdev) if (ret < 0) return ret; - qce->core = devm_clk_get_optional(qce->dev, "core"); + qce->core = devm_clk_get_optional_enabled(qce->dev, "core"); if (IS_ERR(qce->core)) return PTR_ERR(qce->core); - qce->iface = devm_clk_get_optional(qce->dev, "iface"); + qce->iface = devm_clk_get_optional_enabled(qce->dev, "iface"); if (IS_ERR(qce->iface)) return PTR_ERR(qce->iface); - qce->bus = devm_clk_get_optional(qce->dev, "bus"); + qce->bus = devm_clk_get_optional_enabled(qce->dev, "bus"); if (IS_ERR(qce->bus)) return PTR_ERR(qce->bus); @@ -229,64 +228,25 @@ static int qce_crypto_probe(struct platform_device *pdev) if (ret) return ret; - ret = clk_prepare_enable(qce->core); + ret = devm_qce_dma_request(qce->dev, &qce->dma); if (ret) - goto err_mem_path_disable; - - ret = clk_prepare_enable(qce->iface); - if (ret) - goto err_clks_core; - - ret = clk_prepare_enable(qce->bus); - if (ret) - goto err_clks_iface; - - ret = qce_dma_request(qce->dev, &qce->dma); - if (ret) - goto err_clks; + return ret; ret = qce_check_version(qce); if (ret) - goto err_clks; + return ret; - spin_lock_init(&qce->lock); - tasklet_init(&qce->done_tasklet, qce_tasklet_req_done, - (unsigned long)qce); + ret = devm_mutex_init(qce->dev, &qce->lock); + if (ret) + return ret; + + INIT_WORK(&qce->done_work, qce_req_done_work); crypto_init_queue(&qce->queue, QCE_QUEUE_LENGTH); qce->async_req_enqueue = qce_async_request_enqueue; qce->async_req_done = qce_async_request_done; - ret = qce_register_algs(qce); - if (ret) - goto err_dma; - - return 0; - -err_dma: - qce_dma_release(&qce->dma); -err_clks: - clk_disable_unprepare(qce->bus); -err_clks_iface: - clk_disable_unprepare(qce->iface); -err_clks_core: - clk_disable_unprepare(qce->core); -err_mem_path_disable: - icc_set_bw(qce->mem_path, 0, 0); - - return ret; -} - -static void qce_crypto_remove(struct platform_device *pdev) -{ - struct qce_device *qce = platform_get_drvdata(pdev); - - tasklet_kill(&qce->done_tasklet); - qce_unregister_algs(qce); - qce_dma_release(&qce->dma); - clk_disable_unprepare(qce->bus); - clk_disable_unprepare(qce->iface); - clk_disable_unprepare(qce->core); + return devm_qce_register_algs(qce); } static const struct of_device_id qce_crypto_of_match[] = { @@ -299,7 +259,6 @@ MODULE_DEVICE_TABLE(of, qce_crypto_of_match); static struct platform_driver qce_crypto_driver = { .probe = qce_crypto_probe, - .remove = qce_crypto_remove, .driver = { .name = KBUILD_MODNAME, .of_match_table = qce_crypto_of_match, diff --git a/drivers/crypto/qce/core.h b/drivers/crypto/qce/core.h index 228fcd69ec51..eb6fa7a8b64a 100644 --- a/drivers/crypto/qce/core.h +++ b/drivers/crypto/qce/core.h @@ -6,13 +6,16 @@ #ifndef _CORE_H_ #define _CORE_H_ +#include +#include + #include "dma.h" /** * struct qce_device - crypto engine device structure * @queue: crypto request queue * @lock: the lock protects queue and req - * @done_tasklet: done tasklet object + * @done_work: workqueue context * @req: current active request * @result: result of current transform * @base: virtual IO base @@ -28,8 +31,8 @@ */ struct qce_device { struct crypto_queue queue; - spinlock_t lock; - struct tasklet_struct done_tasklet; + struct mutex lock; + struct work_struct done_work; struct crypto_async_request *req; int result; void __iomem *base; diff --git a/drivers/crypto/qce/dma.c b/drivers/crypto/qce/dma.c index 46db5bf366b4..1dec7aea852d 100644 --- a/drivers/crypto/qce/dma.c +++ b/drivers/crypto/qce/dma.c @@ -3,12 +3,22 @@ * Copyright (c) 2012-2014, The Linux Foundation. All rights reserved. */ +#include #include #include #include "dma.h" -int qce_dma_request(struct device *dev, struct qce_dma_data *dma) +static void qce_dma_release(void *data) +{ + struct qce_dma_data *dma = data; + + dma_release_channel(dma->txchan); + dma_release_channel(dma->rxchan); + kfree(dma->result_buf); +} + +int devm_qce_dma_request(struct device *dev, struct qce_dma_data *dma) { int ret; @@ -31,7 +41,8 @@ int qce_dma_request(struct device *dev, struct qce_dma_data *dma) dma->ignore_buf = dma->result_buf + QCE_RESULT_BUF_SZ; - return 0; + return devm_add_action_or_reset(dev, qce_dma_release, dma); + error_nomem: dma_release_channel(dma->rxchan); error_rx: @@ -39,13 +50,6 @@ error_rx: return ret; } -void qce_dma_release(struct qce_dma_data *dma) -{ - dma_release_channel(dma->txchan); - dma_release_channel(dma->rxchan); - kfree(dma->result_buf); -} - struct scatterlist * qce_sgtable_add(struct sg_table *sgt, struct scatterlist *new_sgl, unsigned int max_len) diff --git a/drivers/crypto/qce/dma.h b/drivers/crypto/qce/dma.h index 786402169360..31629185000e 100644 --- a/drivers/crypto/qce/dma.h +++ b/drivers/crypto/qce/dma.h @@ -34,8 +34,7 @@ struct qce_dma_data { void *ignore_buf; }; -int qce_dma_request(struct device *dev, struct qce_dma_data *dma); -void qce_dma_release(struct qce_dma_data *dma); +int devm_qce_dma_request(struct device *dev, struct qce_dma_data *dma); int qce_dma_prep_sgs(struct qce_dma_data *dma, struct scatterlist *sg_in, int in_ents, struct scatterlist *sg_out, int out_ents, dma_async_tx_callback cb, void *cb_param); diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c index fc72af8aa9a7..71b748183cfa 100644 --- a/drivers/crypto/qce/sha.c +++ b/drivers/crypto/qce/sha.c @@ -482,7 +482,7 @@ static int qce_ahash_register_one(const struct qce_ahash_def *def, base = &alg->halg.base; base->cra_blocksize = def->blocksize; - base->cra_priority = 300; + base->cra_priority = 175; base->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY; base->cra_ctxsize = sizeof(struct qce_sha_ctx); base->cra_alignmask = 0; diff --git a/drivers/crypto/qce/skcipher.c b/drivers/crypto/qce/skcipher.c index 5b493fdc1e74..ffb334eb5b34 100644 --- a/drivers/crypto/qce/skcipher.c +++ b/drivers/crypto/qce/skcipher.c @@ -461,7 +461,7 @@ static int qce_skcipher_register_one(const struct qce_skcipher_def *def, alg->encrypt = qce_skcipher_encrypt; alg->decrypt = qce_skcipher_decrypt; - alg->base.cra_priority = 300; + alg->base.cra_priority = 275; alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY | CRYPTO_ALG_KERN_DRIVER_ONLY; diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c index 9d130592cc0a..d734c9a56786 100644 --- a/drivers/crypto/tegra/tegra-se-aes.c +++ b/drivers/crypto/tegra/tegra-se-aes.c @@ -1750,10 +1750,13 @@ static int tegra_cmac_digest(struct ahash_request *req) struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct tegra_cmac_ctx *ctx = crypto_ahash_ctx(tfm); struct tegra_cmac_reqctx *rctx = ahash_request_ctx(req); + int ret; + + ret = tegra_cmac_init(req); + if (ret) + return ret; - tegra_cmac_init(req); rctx->task |= SHA_UPDATE | SHA_FINAL; - return crypto_transfer_hash_request_to_engine(ctx->se->engine, req); } diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c index 4d4bd727f498..0b5cdd5676b1 100644 --- a/drivers/crypto/tegra/tegra-se-hash.c +++ b/drivers/crypto/tegra/tegra-se-hash.c @@ -615,13 +615,16 @@ static int tegra_sha_digest(struct ahash_request *req) struct tegra_sha_reqctx *rctx = ahash_request_ctx(req); struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct tegra_sha_ctx *ctx = crypto_ahash_ctx(tfm); + int ret; if (ctx->fallback) return tegra_sha_fallback_digest(req); - tegra_sha_init(req); - rctx->task |= SHA_UPDATE | SHA_FINAL; + ret = tegra_sha_init(req); + if (ret) + return ret; + rctx->task |= SHA_UPDATE | SHA_FINAL; return crypto_transfer_hash_request_to_engine(ctx->se->engine, req); } diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 28edd5822486..50e6a45b30ba 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -703,7 +703,7 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) return 0; } -static int commit_reap(struct device *dev, const void *data) +static int commit_reap(struct device *dev, void *data) { struct cxl_port *port = to_cxl_port(dev->parent); struct cxl_decoder *cxld; diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 9d58ab9d33c5..013b869b66cb 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -252,9 +252,9 @@ static int devm_cxl_enable_mem(struct device *host, struct cxl_dev_state *cxlds) } /* require dvsec ranges to be covered by a locked platform window */ -static int dvsec_range_allowed(struct device *dev, void *arg) +static int dvsec_range_allowed(struct device *dev, const void *arg) { - struct range *dev_range = arg; + const struct range *dev_range = arg; struct cxl_decoder *cxld; if (!is_root_decoder(dev)) @@ -291,11 +291,11 @@ static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm) return devm_add_action_or_reset(host, disable_hdm, cxlhdm); } -int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, +int cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds, struct cxl_endpoint_dvsec_info *info) { - struct pci_dev *pdev = to_pci_dev(dev); - struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + struct device *dev = cxlds->dev; int hdm_count, rc, i, ranges = 0; int d = cxlds->cxl_dvsec; u16 cap, ctrl; diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index b3378d3f6acb..8853415c106a 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -51,17 +51,6 @@ struct cxl_nvdimm_bridge *to_cxl_nvdimm_bridge(struct device *dev) } EXPORT_SYMBOL_NS_GPL(to_cxl_nvdimm_bridge, "CXL"); -bool is_cxl_nvdimm_bridge(struct device *dev) -{ - return dev->type == &cxl_nvdimm_bridge_type; -} -EXPORT_SYMBOL_NS_GPL(is_cxl_nvdimm_bridge, "CXL"); - -static int match_nvdimm_bridge(struct device *dev, void *data) -{ - return is_cxl_nvdimm_bridge(dev); -} - /** * cxl_find_nvdimm_bridge() - find a bridge device relative to a port * @port: any descendant port of an nvdimm-bridge associated @@ -75,7 +64,9 @@ struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_port *port) if (!cxl_root) return NULL; - dev = device_find_child(&cxl_root->port.dev, NULL, match_nvdimm_bridge); + dev = device_find_child(&cxl_root->port.dev, + &cxl_nvdimm_bridge_type, + device_match_type); if (!dev) return NULL; diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index d77899650798..e8d11a988fd9 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -778,7 +778,7 @@ out: return rc; } -static int check_commit_order(struct device *dev, const void *data) +static int check_commit_order(struct device *dev, void *data) { struct cxl_decoder *cxld = to_cxl_decoder(dev); @@ -792,7 +792,7 @@ static int check_commit_order(struct device *dev, const void *data) return 0; } -static int match_free_decoder(struct device *dev, void *data) +static int match_free_decoder(struct device *dev, const void *data) { struct cxl_port *port = to_cxl_port(dev->parent); struct cxl_decoder *cxld; @@ -824,9 +824,9 @@ static int match_free_decoder(struct device *dev, void *data) return 1; } -static int match_auto_decoder(struct device *dev, void *data) +static int match_auto_decoder(struct device *dev, const void *data) { - struct cxl_region_params *p = data; + const struct cxl_region_params *p = data; struct cxl_decoder *cxld; struct range *r; @@ -1295,6 +1295,7 @@ static int cxl_port_setup_targets(struct cxl_port *port, struct cxl_region_params *p = &cxlr->params; struct cxl_decoder *cxld = cxl_rr->decoder; struct cxl_switch_decoder *cxlsd; + struct cxl_port *iter = port; u16 eig, peig; u8 eiw, peiw; @@ -1311,16 +1312,26 @@ static int cxl_port_setup_targets(struct cxl_port *port, cxlsd = to_cxl_switch_decoder(&cxld->dev); if (cxl_rr->nr_targets_set) { - int i, distance; + int i, distance = 1; + struct cxl_region_ref *cxl_rr_iter; /* - * Passthrough decoders impose no distance requirements between - * peers + * The "distance" between peer downstream ports represents which + * endpoint positions in the region interleave a given port can + * host. + * + * For example, at the root of a hierarchy the distance is + * always 1 as every index targets a different host-bridge. At + * each subsequent switch level those ports map every Nth region + * position where N is the width of the switch == distance. */ - if (cxl_rr->nr_targets == 1) - distance = 0; - else - distance = p->nr_targets / cxl_rr->nr_targets; + do { + cxl_rr_iter = cxl_rr_load(iter, cxlr); + distance *= cxl_rr_iter->nr_targets; + iter = to_cxl_port(iter->dev.parent); + } while (!is_cxl_root(iter)); + distance *= cxlrd->cxlsd.cxld.interleave_ways; + for (i = 0; i < cxl_rr->nr_targets_set; i++) if (ep->dport == cxlsd->target[i]) { rc = check_last_peer(cxled, ep, cxl_rr, @@ -1722,10 +1733,12 @@ static struct cxl_port *next_port(struct cxl_port *port) return port->parent_dport->port; } -static int match_switch_decoder_by_range(struct device *dev, void *data) +static int match_switch_decoder_by_range(struct device *dev, + const void *data) { struct cxl_switch_decoder *cxlsd; - struct range *r1, *r2 = data; + const struct range *r1, *r2 = data; + if (!is_switch_decoder(dev)) return 0; @@ -3176,9 +3189,10 @@ err: return rc; } -static int match_root_decoder_by_range(struct device *dev, void *data) +static int match_root_decoder_by_range(struct device *dev, + const void *data) { - struct range *r1, *r2 = data; + const struct range *r1, *r2 = data; struct cxl_root_decoder *cxlrd; if (!is_root_decoder(dev)) @@ -3189,11 +3203,11 @@ static int match_root_decoder_by_range(struct device *dev, void *data) return range_contains(r1, r2); } -static int match_region_by_range(struct device *dev, void *data) +static int match_region_by_range(struct device *dev, const void *data) { struct cxl_region_params *p; struct cxl_region *cxlr; - struct range *r = data; + const struct range *r = data; int rc = 0; if (!is_cxl_region(dev)) diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c index 59cb35b40c7e..117c2e94c761 100644 --- a/drivers/cxl/core/regs.c +++ b/drivers/cxl/core/regs.c @@ -289,21 +289,17 @@ static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi, return true; } -/** - * cxl_find_regblock_instance() - Locate a register block by type / index - * @pdev: The CXL PCI device to enumerate. - * @type: Register Block Indicator id - * @map: Enumeration output, clobbered on error - * @index: Index into which particular instance of a regblock wanted in the - * order found in register locator DVSEC. +/* + * __cxl_find_regblock_instance() - Locate a register block or count instances by type / index + * Use CXL_INSTANCES_COUNT for @index if counting instances. * - * Return: 0 if register block enumerated, negative error code otherwise - * - * A CXL DVSEC may point to one or more register blocks, search for them - * by @type and @index. + * __cxl_find_regblock_instance() may return: + * 0 - if register block enumerated. + * >= 0 - if counting instances. + * < 0 - error code otherwise. */ -int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, - struct cxl_register_map *map, int index) +static int __cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, + struct cxl_register_map *map, int index) { u32 regloc_size, regblocks; int instance = 0; @@ -342,8 +338,30 @@ int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, } map->resource = CXL_RESOURCE_NONE; + if (index == CXL_INSTANCES_COUNT) + return instance; + return -ENODEV; } + +/** + * cxl_find_regblock_instance() - Locate a register block by type / index + * @pdev: The CXL PCI device to enumerate. + * @type: Register Block Indicator id + * @map: Enumeration output, clobbered on error + * @index: Index into which particular instance of a regblock wanted in the + * order found in register locator DVSEC. + * + * Return: 0 if register block enumerated, negative error code otherwise + * + * A CXL DVSEC may point to one or more register blocks, search for them + * by @type and @index. + */ +int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, + struct cxl_register_map *map, unsigned int index) +{ + return __cxl_find_regblock_instance(pdev, type, map, index); +} EXPORT_SYMBOL_NS_GPL(cxl_find_regblock_instance, "CXL"); /** @@ -360,7 +378,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_find_regblock_instance, "CXL"); int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type, struct cxl_register_map *map) { - return cxl_find_regblock_instance(pdev, type, map, 0); + return __cxl_find_regblock_instance(pdev, type, map, 0); } EXPORT_SYMBOL_NS_GPL(cxl_find_regblock, "CXL"); @@ -371,19 +389,13 @@ EXPORT_SYMBOL_NS_GPL(cxl_find_regblock, "CXL"); * * Some regblocks may be repeated. Count how many instances. * - * Return: count of matching regblocks. + * Return: non-negative count of matching regblocks, negative error code otherwise. */ int cxl_count_regblock(struct pci_dev *pdev, enum cxl_regloc_type type) { struct cxl_register_map map; - int rc, count = 0; - while (1) { - rc = cxl_find_regblock_instance(pdev, type, &map, count); - if (rc) - return count; - count++; - } + return __cxl_find_regblock_instance(pdev, type, &map, CXL_INSTANCES_COUNT); } EXPORT_SYMBOL_NS_GPL(cxl_count_regblock, "CXL"); diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 8389a94adb1a..cea706b683b5 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -166,11 +166,13 @@ TRACE_EVENT(cxl_overflow, #define CXL_EVENT_RECORD_FLAG_MAINT_NEEDED BIT(3) #define CXL_EVENT_RECORD_FLAG_PERF_DEGRADED BIT(4) #define CXL_EVENT_RECORD_FLAG_HW_REPLACE BIT(5) +#define CXL_EVENT_RECORD_FLAG_MAINT_OP_SUB_CLASS_VALID BIT(6) #define show_hdr_flags(flags) __print_flags(flags, " | ", \ { CXL_EVENT_RECORD_FLAG_PERMANENT, "PERMANENT_CONDITION" }, \ { CXL_EVENT_RECORD_FLAG_MAINT_NEEDED, "MAINTENANCE_NEEDED" }, \ { CXL_EVENT_RECORD_FLAG_PERF_DEGRADED, "PERFORMANCE_DEGRADED" }, \ - { CXL_EVENT_RECORD_FLAG_HW_REPLACE, "HARDWARE_REPLACEMENT_NEEDED" } \ + { CXL_EVENT_RECORD_FLAG_HW_REPLACE, "HARDWARE_REPLACEMENT_NEEDED" }, \ + { CXL_EVENT_RECORD_FLAG_MAINT_OP_SUB_CLASS_VALID, "MAINT_OP_SUB_CLASS_VALID" } \ ) /* @@ -197,7 +199,8 @@ TRACE_EVENT(cxl_overflow, __field(u16, hdr_related_handle) \ __field(u64, hdr_timestamp) \ __field(u8, hdr_length) \ - __field(u8, hdr_maint_op_class) + __field(u8, hdr_maint_op_class) \ + __field(u8, hdr_maint_op_sub_class) #define CXL_EVT_TP_fast_assign(cxlmd, l, hdr) \ __assign_str(memdev); \ @@ -209,17 +212,19 @@ TRACE_EVENT(cxl_overflow, __entry->hdr_handle = le16_to_cpu((hdr).handle); \ __entry->hdr_related_handle = le16_to_cpu((hdr).related_handle); \ __entry->hdr_timestamp = le64_to_cpu((hdr).timestamp); \ - __entry->hdr_maint_op_class = (hdr).maint_op_class + __entry->hdr_maint_op_class = (hdr).maint_op_class; \ + __entry->hdr_maint_op_sub_class = (hdr).maint_op_sub_class #define CXL_EVT_TP_printk(fmt, ...) \ TP_printk("memdev=%s host=%s serial=%lld log=%s : time=%llu uuid=%pUb " \ "len=%d flags='%s' handle=%x related_handle=%x " \ - "maint_op_class=%u : " fmt, \ + "maint_op_class=%u maint_op_sub_class=%u : " fmt, \ __get_str(memdev), __get_str(host), __entry->serial, \ cxl_event_log_type_str(__entry->log), \ __entry->hdr_timestamp, &__entry->hdr_uuid, __entry->hdr_length,\ show_hdr_flags(__entry->hdr_flags), __entry->hdr_handle, \ __entry->hdr_related_handle, __entry->hdr_maint_op_class, \ + __entry->hdr_maint_op_sub_class, \ ##__VA_ARGS__) TRACE_EVENT(cxl_generic_event, @@ -263,9 +268,31 @@ TRACE_EVENT(cxl_generic_event, { CXL_DPA_NOT_REPAIRABLE, "NOT_REPAIRABLE" } \ ) +/* + * Component ID Format + * CXL 3.1 section 8.2.9.2.1; Table 8-44 + */ +#define CXL_PLDM_COMPONENT_ID_ENTITY_VALID BIT(0) +#define CXL_PLDM_COMPONENT_ID_RES_VALID BIT(1) + +#define show_comp_id_pldm_flags(flags) __print_flags(flags, " | ", \ + { CXL_PLDM_COMPONENT_ID_ENTITY_VALID, "PLDM Entity ID" }, \ + { CXL_PLDM_COMPONENT_ID_RES_VALID, "Resource ID" } \ +) + +#define show_pldm_entity_id(flags, valid_comp_id, valid_id_format, comp_id) \ + (flags & valid_comp_id && flags & valid_id_format) ? \ + (comp_id[0] & CXL_PLDM_COMPONENT_ID_ENTITY_VALID) ? \ + __print_hex(&comp_id[1], 6) : "0x00" : "0x00" + +#define show_pldm_resource_id(flags, valid_comp_id, valid_id_format, comp_id) \ + (flags & valid_comp_id && flags & valid_id_format) ? \ + (comp_id[0] & CXL_PLDM_COMPONENT_ID_RES_VALID) ? \ + __print_hex(&comp_id[7], 4) : "0x00" : "0x00" + /* * General Media Event Record - GMER - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + * CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45 */ #define CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT BIT(0) #define CXL_GMER_EVT_DESC_THRESHOLD_EVENT BIT(1) @@ -279,10 +306,18 @@ TRACE_EVENT(cxl_generic_event, #define CXL_GMER_MEM_EVT_TYPE_ECC_ERROR 0x00 #define CXL_GMER_MEM_EVT_TYPE_INV_ADDR 0x01 #define CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR 0x02 -#define show_gmer_mem_event_type(type) __print_symbolic(type, \ - { CXL_GMER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ - { CXL_GMER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ - { CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" } \ +#define CXL_GMER_MEM_EVT_TYPE_TE_STATE_VIOLATION 0x03 +#define CXL_GMER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR 0x04 +#define CXL_GMER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE 0x05 +#define CXL_GMER_MEM_EVT_TYPE_CKID_VIOLATION 0x06 +#define show_gmer_mem_event_type(type) __print_symbolic(type, \ + { CXL_GMER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ + { CXL_GMER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ + { CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" }, \ + { CXL_GMER_MEM_EVT_TYPE_TE_STATE_VIOLATION, "TE State Violation" }, \ + { CXL_GMER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR, "Scrub Media ECC Error" }, \ + { CXL_GMER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE, "Adv Prog CME Counter Expiration" }, \ + { CXL_GMER_MEM_EVT_TYPE_CKID_VIOLATION, "CKID Violation" } \ ) #define CXL_GMER_TRANS_UNKNOWN 0x00 @@ -292,6 +327,8 @@ TRACE_EVENT(cxl_generic_event, #define CXL_GMER_TRANS_HOST_INJECT_POISON 0x04 #define CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB 0x05 #define CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT 0x06 +#define CXL_GMER_TRANS_INTERNAL_MEDIA_ECS 0x07 +#define CXL_GMER_TRANS_MEDIA_INITIALIZATION 0x08 #define show_trans_type(type) __print_symbolic(type, \ { CXL_GMER_TRANS_UNKNOWN, "Unknown" }, \ { CXL_GMER_TRANS_HOST_READ, "Host Read" }, \ @@ -299,18 +336,57 @@ TRACE_EVENT(cxl_generic_event, { CXL_GMER_TRANS_HOST_SCAN_MEDIA, "Host Scan Media" }, \ { CXL_GMER_TRANS_HOST_INJECT_POISON, "Host Inject Poison" }, \ { CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB, "Internal Media Scrub" }, \ - { CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT, "Internal Media Management" } \ + { CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT, "Internal Media Management" }, \ + { CXL_GMER_TRANS_INTERNAL_MEDIA_ECS, "Internal Media Error Check Scrub" }, \ + { CXL_GMER_TRANS_MEDIA_INITIALIZATION, "Media Initialization" } \ ) #define CXL_GMER_VALID_CHANNEL BIT(0) #define CXL_GMER_VALID_RANK BIT(1) #define CXL_GMER_VALID_DEVICE BIT(2) #define CXL_GMER_VALID_COMPONENT BIT(3) +#define CXL_GMER_VALID_COMPONENT_ID_FORMAT BIT(4) #define show_valid_flags(flags) __print_flags(flags, "|", \ { CXL_GMER_VALID_CHANNEL, "CHANNEL" }, \ { CXL_GMER_VALID_RANK, "RANK" }, \ { CXL_GMER_VALID_DEVICE, "DEVICE" }, \ - { CXL_GMER_VALID_COMPONENT, "COMPONENT" } \ + { CXL_GMER_VALID_COMPONENT, "COMPONENT" }, \ + { CXL_GMER_VALID_COMPONENT_ID_FORMAT, "COMPONENT PLDM FORMAT" } \ +) + +#define CXL_GMER_CME_EV_FLAG_CME_MULTIPLE_MEDIA BIT(0) +#define CXL_GMER_CME_EV_FLAG_THRESHOLD_EXCEEDED BIT(1) +#define show_cme_threshold_ev_flags(flags) __print_flags(flags, "|", \ + { \ + CXL_GMER_CME_EV_FLAG_CME_MULTIPLE_MEDIA, \ + "Corrected Memory Errors in Multiple Media Components" \ + }, { \ + CXL_GMER_CME_EV_FLAG_THRESHOLD_EXCEEDED, \ + "Exceeded Programmable Threshold" \ + } \ +) + +#define CXL_GMER_MEM_EVT_SUB_TYPE_NOT_REPORTED 0x00 +#define CXL_GMER_MEM_EVT_SUB_TYPE_INTERNAL_DATAPATH_ERROR 0x01 +#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_COMMAND_TRAINING_ERROR 0x02 +#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CONTROL_TRAINING_ERROR 0x03 +#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_DATA_TRAINING_ERROR 0x04 +#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CRC_ERROR 0x05 +#define show_mem_event_sub_type(sub_type) __print_symbolic(sub_type, \ + { CXL_GMER_MEM_EVT_SUB_TYPE_NOT_REPORTED, "Not Reported" }, \ + { CXL_GMER_MEM_EVT_SUB_TYPE_INTERNAL_DATAPATH_ERROR, "Internal Datapath Error" }, \ + { \ + CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_COMMAND_TRAINING_ERROR, \ + "Media Link Command Training Error" \ + }, { \ + CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CONTROL_TRAINING_ERROR, \ + "Media Link Control Training Error" \ + }, { \ + CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_DATA_TRAINING_ERROR, \ + "Media Link Data Training Error" \ + }, { \ + CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CRC_ERROR, "Media Link CRC Error" \ + } \ ) TRACE_EVENT(cxl_general_media, @@ -336,6 +412,9 @@ TRACE_EVENT(cxl_general_media, __field(u16, validity_flags) __field(u8, rank) __field(u8, dpa_flags) + __field(u32, cme_count) + __field(u8, sub_type) + __field(u8, cme_threshold_ev_flags) __string(region_name, cxlr ? dev_name(&cxlr->dev) : "") ), @@ -350,6 +429,7 @@ TRACE_EVENT(cxl_general_media, __entry->dpa &= CXL_DPA_MASK; __entry->descriptor = rec->media_hdr.descriptor; __entry->type = rec->media_hdr.type; + __entry->sub_type = rec->sub_type; __entry->transaction_type = rec->media_hdr.transaction_type; __entry->channel = rec->media_hdr.channel; __entry->rank = rec->media_hdr.rank; @@ -365,27 +445,40 @@ TRACE_EVENT(cxl_general_media, __assign_str(region_name); uuid_copy(&__entry->region_uuid, &uuid_null); } + __entry->cme_threshold_ev_flags = rec->cme_threshold_ev_flags; + __entry->cme_count = get_unaligned_le24(rec->cme_count); ), CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' " \ - "descriptor='%s' type='%s' transaction_type='%s' channel=%u rank=%u " \ - "device=%x comp_id=%s validity_flags='%s' " \ - "hpa=%llx region=%s region_uuid=%pUb", + "descriptor='%s' type='%s' sub_type='%s' " \ + "transaction_type='%s' channel=%u rank=%u " \ + "device=%x validity_flags='%s' " \ + "comp_id=%s comp_id_pldm_valid_flags='%s' " \ + "pldm_entity_id=%s pldm_resource_id=%s " \ + "hpa=%llx region=%s region_uuid=%pUb " \ + "cme_threshold_ev_flags='%s' cme_count=%u", __entry->dpa, show_dpa_flags(__entry->dpa_flags), show_event_desc_flags(__entry->descriptor), show_gmer_mem_event_type(__entry->type), + show_mem_event_sub_type(__entry->sub_type), show_trans_type(__entry->transaction_type), __entry->channel, __entry->rank, __entry->device, - __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), show_valid_flags(__entry->validity_flags), - __entry->hpa, __get_str(region_name), &__entry->region_uuid + __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), + show_comp_id_pldm_flags(__entry->comp_id[0]), + show_pldm_entity_id(__entry->validity_flags, CXL_GMER_VALID_COMPONENT, + CXL_GMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + show_pldm_resource_id(__entry->validity_flags, CXL_GMER_VALID_COMPONENT, + CXL_GMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + __entry->hpa, __get_str(region_name), &__entry->region_uuid, + show_cme_threshold_ev_flags(__entry->cme_threshold_ev_flags), __entry->cme_count ) ); /* * DRAM Event Record - DER * - * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 + * CXL rev 3.1 section 8.2.9.2.1.2; Table 8-46 */ /* * DRAM Event Record defines many fields the same as the General Media Event @@ -395,11 +488,17 @@ TRACE_EVENT(cxl_general_media, #define CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR 0x01 #define CXL_DER_MEM_EVT_TYPE_INV_ADDR 0x02 #define CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR 0x03 -#define show_dram_mem_event_type(type) __print_symbolic(type, \ - { CXL_DER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ - { CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR, "Scrub Media ECC Error" }, \ - { CXL_DER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ - { CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" } \ +#define CXL_DER_MEM_EVT_TYPE_TE_STATE_VIOLATION 0x04 +#define CXL_DER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE 0x05 +#define CXL_DER_MEM_EVT_TYPE_CKID_VIOLATION 0x06 +#define show_dram_mem_event_type(type) __print_symbolic(type, \ + { CXL_DER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ + { CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR, "Scrub Media ECC Error" }, \ + { CXL_DER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ + { CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" }, \ + { CXL_DER_MEM_EVT_TYPE_TE_STATE_VIOLATION, "TE State Violation" }, \ + { CXL_DER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE, "Adv Prog CME Counter Expiration" }, \ + { CXL_DER_MEM_EVT_TYPE_CKID_VIOLATION, "CKID Violation" } \ ) #define CXL_DER_VALID_CHANNEL BIT(0) @@ -410,15 +509,21 @@ TRACE_EVENT(cxl_general_media, #define CXL_DER_VALID_ROW BIT(5) #define CXL_DER_VALID_COLUMN BIT(6) #define CXL_DER_VALID_CORRECTION_MASK BIT(7) -#define show_dram_valid_flags(flags) __print_flags(flags, "|", \ - { CXL_DER_VALID_CHANNEL, "CHANNEL" }, \ - { CXL_DER_VALID_RANK, "RANK" }, \ - { CXL_DER_VALID_NIBBLE, "NIBBLE" }, \ - { CXL_DER_VALID_BANK_GROUP, "BANK GROUP" }, \ - { CXL_DER_VALID_BANK, "BANK" }, \ - { CXL_DER_VALID_ROW, "ROW" }, \ - { CXL_DER_VALID_COLUMN, "COLUMN" }, \ - { CXL_DER_VALID_CORRECTION_MASK, "CORRECTION MASK" } \ +#define CXL_DER_VALID_COMPONENT BIT(8) +#define CXL_DER_VALID_COMPONENT_ID_FORMAT BIT(9) +#define CXL_DER_VALID_SUB_CHANNEL BIT(10) +#define show_dram_valid_flags(flags) __print_flags(flags, "|", \ + { CXL_DER_VALID_CHANNEL, "CHANNEL" }, \ + { CXL_DER_VALID_RANK, "RANK" }, \ + { CXL_DER_VALID_NIBBLE, "NIBBLE" }, \ + { CXL_DER_VALID_BANK_GROUP, "BANK GROUP" }, \ + { CXL_DER_VALID_BANK, "BANK" }, \ + { CXL_DER_VALID_ROW, "ROW" }, \ + { CXL_DER_VALID_COLUMN, "COLUMN" }, \ + { CXL_DER_VALID_CORRECTION_MASK, "CORRECTION MASK" }, \ + { CXL_DER_VALID_COMPONENT, "COMPONENT" }, \ + { CXL_DER_VALID_COMPONENT_ID_FORMAT, "COMPONENT PLDM FORMAT" }, \ + { CXL_DER_VALID_SUB_CHANNEL, "SUB CHANNEL" } \ ) TRACE_EVENT(cxl_dram, @@ -447,6 +552,12 @@ TRACE_EVENT(cxl_dram, __field(u8, bank_group) /* Out of order to pack trace record */ __field(u8, bank) /* Out of order to pack trace record */ __field(u8, dpa_flags) /* Out of order to pack trace record */ + /* Following are out of order to pack trace record */ + __array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE) + __field(u32, cvme_count) + __field(u8, sub_type) + __field(u8, sub_channel) + __field(u8, cme_threshold_ev_flags) __string(region_name, cxlr ? dev_name(&cxlr->dev) : "") ), @@ -460,6 +571,7 @@ TRACE_EVENT(cxl_dram, __entry->dpa &= CXL_DPA_MASK; __entry->descriptor = rec->media_hdr.descriptor; __entry->type = rec->media_hdr.type; + __entry->sub_type = rec->sub_type; __entry->transaction_type = rec->media_hdr.transaction_type; __entry->validity_flags = get_unaligned_le16(rec->media_hdr.validity_flags); __entry->channel = rec->media_hdr.channel; @@ -479,30 +591,47 @@ TRACE_EVENT(cxl_dram, __assign_str(region_name); uuid_copy(&__entry->region_uuid, &uuid_null); } + memcpy(__entry->comp_id, &rec->component_id, + CXL_EVENT_GEN_MED_COMP_ID_SIZE); + __entry->sub_channel = rec->sub_channel; + __entry->cme_threshold_ev_flags = rec->cme_threshold_ev_flags; + __entry->cvme_count = get_unaligned_le24(rec->cvme_count); ), - CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' " \ + CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' sub_type='%s' " \ "transaction_type='%s' channel=%u rank=%u nibble_mask=%x " \ "bank_group=%u bank=%u row=%u column=%u cor_mask=%s " \ "validity_flags='%s' " \ - "hpa=%llx region=%s region_uuid=%pUb", + "comp_id=%s comp_id_pldm_valid_flags='%s' " \ + "pldm_entity_id=%s pldm_resource_id=%s " \ + "hpa=%llx region=%s region_uuid=%pUb " \ + "sub_channel=%u cme_threshold_ev_flags='%s' cvme_count=%u", __entry->dpa, show_dpa_flags(__entry->dpa_flags), show_event_desc_flags(__entry->descriptor), show_dram_mem_event_type(__entry->type), + show_mem_event_sub_type(__entry->sub_type), show_trans_type(__entry->transaction_type), __entry->channel, __entry->rank, __entry->nibble_mask, __entry->bank_group, __entry->bank, __entry->row, __entry->column, __print_hex(__entry->cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE), show_dram_valid_flags(__entry->validity_flags), - __entry->hpa, __get_str(region_name), &__entry->region_uuid + __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), + show_comp_id_pldm_flags(__entry->comp_id[0]), + show_pldm_entity_id(__entry->validity_flags, CXL_DER_VALID_COMPONENT, + CXL_DER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + show_pldm_resource_id(__entry->validity_flags, CXL_DER_VALID_COMPONENT, + CXL_DER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + __entry->hpa, __get_str(region_name), &__entry->region_uuid, + __entry->sub_channel, show_cme_threshold_ev_flags(__entry->cme_threshold_ev_flags), + __entry->cvme_count ) ); /* * Memory Module Event Record - MMER * - * CXL res 3.0 section 8.2.9.2.1.3; Table 8-45 + * CXL res 3.1 section 8.2.9.2.1.3; Table 8-47 */ #define CXL_MMER_HEALTH_STATUS_CHANGE 0x00 #define CXL_MMER_MEDIA_STATUS_CHANGE 0x01 @@ -510,27 +639,35 @@ TRACE_EVENT(cxl_dram, #define CXL_MMER_TEMP_CHANGE 0x03 #define CXL_MMER_DATA_PATH_ERROR 0x04 #define CXL_MMER_LSA_ERROR 0x05 +#define CXL_MMER_UNRECOV_SIDEBAND_BUS_ERROR 0x06 +#define CXL_MMER_MEMORY_MEDIA_FRU_ERROR 0x07 +#define CXL_MMER_POWER_MANAGEMENT_FAULT 0x08 #define show_dev_evt_type(type) __print_symbolic(type, \ { CXL_MMER_HEALTH_STATUS_CHANGE, "Health Status Change" }, \ { CXL_MMER_MEDIA_STATUS_CHANGE, "Media Status Change" }, \ { CXL_MMER_LIFE_USED_CHANGE, "Life Used Change" }, \ { CXL_MMER_TEMP_CHANGE, "Temperature Change" }, \ { CXL_MMER_DATA_PATH_ERROR, "Data Path Error" }, \ - { CXL_MMER_LSA_ERROR, "LSA Error" } \ + { CXL_MMER_LSA_ERROR, "LSA Error" }, \ + { CXL_MMER_UNRECOV_SIDEBAND_BUS_ERROR, "Unrecoverable Internal Sideband Bus Error" }, \ + { CXL_MMER_MEMORY_MEDIA_FRU_ERROR, "Memory Media FRU Error" }, \ + { CXL_MMER_POWER_MANAGEMENT_FAULT, "Power Management Fault" } \ ) /* * Device Health Information - DHI * - * CXL res 3.0 section 8.2.9.8.3.1; Table 8-100 + * CXL res 3.1 section 8.2.9.9.3.1; Table 8-133 */ #define CXL_DHI_HS_MAINTENANCE_NEEDED BIT(0) #define CXL_DHI_HS_PERFORMANCE_DEGRADED BIT(1) #define CXL_DHI_HS_HW_REPLACEMENT_NEEDED BIT(2) +#define CXL_DHI_HS_MEM_CAPACITY_DEGRADED BIT(3) #define show_health_status_flags(flags) __print_flags(flags, "|", \ { CXL_DHI_HS_MAINTENANCE_NEEDED, "MAINTENANCE_NEEDED" }, \ { CXL_DHI_HS_PERFORMANCE_DEGRADED, "PERFORMANCE_DEGRADED" }, \ - { CXL_DHI_HS_HW_REPLACEMENT_NEEDED, "REPLACEMENT_NEEDED" } \ + { CXL_DHI_HS_HW_REPLACEMENT_NEEDED, "REPLACEMENT_NEEDED" }, \ + { CXL_DHI_HS_MEM_CAPACITY_DEGRADED, "MEM_CAPACITY_DEGRADED" } \ ) #define CXL_DHI_MS_NORMAL 0x00 @@ -584,6 +721,26 @@ TRACE_EVENT(cxl_dram, #define CXL_DHI_AS_COR_VOL_ERR_CNT(as) ((as & 0x10) >> 4) #define CXL_DHI_AS_COR_PER_ERR_CNT(as) ((as & 0x20) >> 5) +#define CXL_MMER_VALID_COMPONENT BIT(0) +#define CXL_MMER_VALID_COMPONENT_ID_FORMAT BIT(1) +#define show_mem_module_valid_flags(flags) __print_flags(flags, "|", \ + { CXL_MMER_VALID_COMPONENT, "COMPONENT" }, \ + { CXL_MMER_VALID_COMPONENT_ID_FORMAT, "COMPONENT PLDM FORMAT" } \ +) +#define CXL_MMER_DEV_EVT_SUB_TYPE_NOT_REPORTED 0x00 +#define CXL_MMER_DEV_EVT_SUB_TYPE_INVALID_CONFIG_DATA 0x01 +#define CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_CONFIG_DATA 0x02 +#define CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_MEM_MEDIA_FRU 0x03 +#define show_dev_event_sub_type(sub_type) __print_symbolic(sub_type, \ + { CXL_MMER_DEV_EVT_SUB_TYPE_NOT_REPORTED, "Not Reported" }, \ + { CXL_MMER_DEV_EVT_SUB_TYPE_INVALID_CONFIG_DATA, "Invalid Config Data" }, \ + { CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_CONFIG_DATA, "Unsupported Config Data" }, \ + { \ + CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_MEM_MEDIA_FRU, \ + "Unsupported Memory Media FRU" \ + } \ +) + TRACE_EVENT(cxl_memory_module, TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, @@ -606,6 +763,9 @@ TRACE_EVENT(cxl_memory_module, __field(u32, cor_per_err_cnt) __field(s16, device_temp) __field(u8, add_status) + __field(u8, event_sub_type) + __array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE) + __field(u16, validity_flags) ), TP_fast_assign( @@ -614,6 +774,7 @@ TRACE_EVENT(cxl_memory_module, /* Memory Module Event */ __entry->event_type = rec->event_type; + __entry->event_sub_type = rec->event_sub_type; /* Device Health Info */ __entry->health_status = rec->info.health_status; @@ -624,13 +785,20 @@ TRACE_EVENT(cxl_memory_module, __entry->cor_per_err_cnt = get_unaligned_le32(rec->info.cor_per_err_cnt); __entry->device_temp = get_unaligned_le16(rec->info.device_temp); __entry->add_status = rec->info.add_status; + __entry->validity_flags = get_unaligned_le16(rec->validity_flags); + memcpy(__entry->comp_id, &rec->component_id, + CXL_EVENT_GEN_MED_COMP_ID_SIZE); ), - CXL_EVT_TP_printk("event_type='%s' health_status='%s' media_status='%s' " \ - "as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \ + CXL_EVT_TP_printk("event_type='%s' event_sub_type='%s' health_status='%s' " \ + "media_status='%s' as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \ "as_cor_per_err_cnt=%s life_used=%u device_temp=%d " \ - "dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u", + "dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u " \ + "validity_flags='%s' " \ + "comp_id=%s comp_id_pldm_valid_flags='%s' " \ + "pldm_entity_id=%s pldm_resource_id=%s", show_dev_evt_type(__entry->event_type), + show_dev_event_sub_type(__entry->event_sub_type), show_health_status_flags(__entry->health_status), show_media_status(__entry->media_status), show_two_bit_status(CXL_DHI_AS_LIFE_USED(__entry->add_status)), @@ -639,7 +807,14 @@ TRACE_EVENT(cxl_memory_module, show_one_bit_status(CXL_DHI_AS_COR_PER_ERR_CNT(__entry->add_status)), __entry->life_used, __entry->device_temp, __entry->dirty_shutdown_cnt, __entry->cor_vol_err_cnt, - __entry->cor_per_err_cnt + __entry->cor_per_err_cnt, + show_mem_module_valid_flags(__entry->validity_flags), + __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), + show_comp_id_pldm_flags(__entry->comp_id[0]), + show_pldm_entity_id(__entry->validity_flags, CXL_MMER_VALID_COMPONENT, + CXL_MMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + show_pldm_resource_id(__entry->validity_flags, CXL_MMER_VALID_COMPONENT, + CXL_MMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id) ) ); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index f6015f24ad38..bbbaa0d0a670 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -302,10 +302,11 @@ int cxl_map_device_regs(const struct cxl_register_map *map, struct cxl_device_regs *regs); int cxl_map_pmu_regs(struct cxl_register_map *map, struct cxl_pmu_regs *regs); +#define CXL_INSTANCES_COUNT -1 enum cxl_regloc_type; int cxl_count_regblock(struct pci_dev *pdev, enum cxl_regloc_type type); int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, - struct cxl_register_map *map, int index); + struct cxl_register_map *map, unsigned int index); int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type, struct cxl_register_map *map); int cxl_setup_regs(struct cxl_register_map *map); @@ -821,7 +822,8 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, struct cxl_endpoint_dvsec_info *info); int devm_cxl_add_passthrough_decoder(struct cxl_port *port); -int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, +struct cxl_dev_state; +int cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds, struct cxl_endpoint_dvsec_info *info); bool is_cxl_region(struct device *dev); @@ -864,7 +866,6 @@ struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host, struct cxl_port *port); struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm(struct device *dev); -bool is_cxl_nvdimm_bridge(struct device *dev); int devm_cxl_add_nvdimm(struct cxl_port *parent_port, struct cxl_memdev *cxlmd); struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_port *port); diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 0241d1d7133a..a96e54c6259e 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -836,6 +836,9 @@ static ssize_t rcd_pcie_cap_emit(struct device *dev, u16 offset, char *buf, size if (!root_dev) return -ENXIO; + if (!dport->regs.rcd_pcie_cap) + return -ENXIO; + guard(device)(root_dev); if (!root_dev->driver) return -ENXIO; @@ -904,7 +907,8 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct cxl_dev_state *cxlds; struct cxl_register_map map; struct cxl_memdev *cxlmd; - int i, rc, pmu_count; + int rc, pmu_count; + unsigned int i; bool irq_avail; /* @@ -1006,6 +1010,9 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return rc; pmu_count = cxl_count_regblock(pdev, CXL_REGLOC_RBI_PMU); + if (pmu_count < 0) + return pmu_count; + for (i = 0; i < pmu_count; i++) { struct cxl_pmu_regs pmu_regs; @@ -1032,8 +1039,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - rc = cxl_pci_ras_unmask(pdev); - if (rc) + if (cxl_pci_ras_unmask(pdev)) dev_dbg(&pdev->dev, "No RAS reporting unmasked\n"); pci_save_state(pdev); diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index 4c83f6a22e58..d2bfd1ff5492 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -98,7 +98,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) struct cxl_port *root; int rc; - rc = cxl_dvsec_rr_decode(cxlds->dev, port, &info); + rc = cxl_dvsec_rr_decode(cxlds, &info); if (rc < 0) return rc; diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c index 3ebac2496679..70219099c604 100644 --- a/drivers/devfreq/devfreq-event.c +++ b/drivers/devfreq/devfreq-event.c @@ -244,13 +244,9 @@ struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(struct device *dev, edev = NULL; out: mutex_unlock(&devfreq_event_list_lock); - - if (!edev) { - of_node_put(node); - return ERR_PTR(-ENODEV); - } - of_node_put(node); + if (!edev) + return ERR_PTR(-ENODEV); return edev; } diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c index 7d06c476d8e9..b9ea7ad2e51b 100644 --- a/drivers/devfreq/exynos-bus.c +++ b/drivers/devfreq/exynos-bus.c @@ -236,8 +236,7 @@ err_regulator: return ret; } -static int exynos_bus_parse_of(struct device_node *np, - struct exynos_bus *bus) +static int exynos_bus_parse_of(struct exynos_bus *bus) { struct device *dev = bus->dev; struct dev_pm_opp *opp; @@ -408,7 +407,7 @@ static int exynos_bus_probe(struct platform_device *pdev) } /* Parse the device-tree to get the resource information */ - ret = exynos_bus_parse_of(np, bus); + ret = exynos_bus_parse_of(bus); if (ret < 0) goto err_reg; diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 7eeee3a38202..5baa83b85515 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -60,7 +60,7 @@ static void __dma_buf_debugfs_list_add(struct dma_buf *dmabuf) { } -static void __dma_buf_debugfs_list_del(struct file *file) +static void __dma_buf_debugfs_list_del(struct dma_buf *dmabuf) { } #endif diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 8ce1f074c2d3..cc7398cc17d6 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -297,7 +297,7 @@ static const struct dma_buf_ops udmabuf_ops = { }; #define SEALS_WANTED (F_SEAL_SHRINK) -#define SEALS_DENIED (F_SEAL_WRITE) +#define SEALS_DENIED (F_SEAL_WRITE|F_SEAL_FUTURE_WRITE) static int check_memfd_seals(struct file *memfd) { @@ -317,12 +317,10 @@ static int check_memfd_seals(struct file *memfd) return 0; } -static int export_udmabuf(struct udmabuf *ubuf, - struct miscdevice *device, - u32 flags) +static struct dma_buf *export_udmabuf(struct udmabuf *ubuf, + struct miscdevice *device) { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); - struct dma_buf *buf; ubuf->device = device; exp_info.ops = &udmabuf_ops; @@ -330,11 +328,7 @@ static int export_udmabuf(struct udmabuf *ubuf, exp_info.priv = ubuf; exp_info.flags = O_RDWR; - buf = dma_buf_export(&exp_info); - if (IS_ERR(buf)) - return PTR_ERR(buf); - - return dma_buf_fd(buf, flags); + return dma_buf_export(&exp_info); } static long udmabuf_pin_folios(struct udmabuf *ubuf, struct file *memfd, @@ -391,6 +385,7 @@ static long udmabuf_create(struct miscdevice *device, struct folio **folios = NULL; pgoff_t pgcnt = 0, pglimit; struct udmabuf *ubuf; + struct dma_buf *dmabuf; long ret = -EINVAL; u32 i, flags; @@ -436,23 +431,39 @@ static long udmabuf_create(struct miscdevice *device, goto err; } + /* + * Take the inode lock to protect against concurrent + * memfd_add_seals(), which takes this lock in write mode. + */ + inode_lock_shared(file_inode(memfd)); ret = check_memfd_seals(memfd); - if (ret < 0) { - fput(memfd); - goto err; - } + if (ret) + goto out_unlock; ret = udmabuf_pin_folios(ubuf, memfd, list[i].offset, list[i].size, folios); +out_unlock: + inode_unlock_shared(file_inode(memfd)); fput(memfd); if (ret) goto err; } flags = head->flags & UDMABUF_FLAGS_CLOEXEC ? O_CLOEXEC : 0; - ret = export_udmabuf(ubuf, device, flags); - if (ret < 0) + dmabuf = export_udmabuf(ubuf, device); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); goto err; + } + /* + * Ownership of ubuf is held by the dmabuf from here. + * If the following dma_buf_fd() fails, dma_buf_put() cleans up both the + * dmabuf and the ubuf (through udmabuf_ops.release). + */ + + ret = dma_buf_fd(dmabuf, flags); + if (ret < 0) + dma_buf_put(dmabuf); kvfree(folios); return ret; diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index e994d6e0779e..8afea2e23360 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -162,8 +162,8 @@ config DMA_SA11X0 config DMA_SUN4I tristate "Allwinner A10 DMA SoCs support" - depends on MACH_SUN4I || MACH_SUN5I || MACH_SUN7I - default (MACH_SUN4I || MACH_SUN5I || MACH_SUN7I) + depends on MACH_SUN4I || MACH_SUN5I || MACH_SUN7I || MACH_SUNIV + default (MACH_SUN4I || MACH_SUN5I || MACH_SUN7I || MACH_SUNIV) select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help @@ -740,8 +740,6 @@ source "drivers/dma/bestcomm/Kconfig" source "drivers/dma/mediatek/Kconfig" -source "drivers/dma/ptdma/Kconfig" - source "drivers/dma/qcom/Kconfig" source "drivers/dma/dw/Kconfig" diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 5b2a52f4f2ee..19ba465011a6 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -16,7 +16,6 @@ obj-$(CONFIG_DMATEST) += dmatest.o obj-$(CONFIG_ALTERA_MSGDMA) += altera-msgdma.o obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/ -obj-$(CONFIG_AMD_PTDMA) += ptdma/ obj-$(CONFIG_APPLE_ADMAC) += apple-admac.o obj-$(CONFIG_AT_HDMAC) += at_hdmac.o obj-$(CONFIG_AT_XDMAC) += at_xdmac.o diff --git a/drivers/dma/amd/Kconfig b/drivers/dma/amd/Kconfig index 7d1f51d69675..00d874872a8f 100644 --- a/drivers/dma/amd/Kconfig +++ b/drivers/dma/amd/Kconfig @@ -1,4 +1,32 @@ # SPDX-License-Identifier: GPL-2.0-only +# + +config AMD_AE4DMA + tristate "AMD AE4DMA Engine" + depends on (X86_64 || COMPILE_TEST) && PCI + depends on AMD_PTDMA + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + help + Enable support for the AMD AE4DMA controller. This controller + provides DMA capabilities to perform high bandwidth memory to + memory and IO copy operations. It performs DMA transfer through + queue-based descriptor management. This DMA controller is intended + to be used with AMD Non-Transparent Bridge devices and not for + general purpose peripheral DMA. + +config AMD_PTDMA + tristate "AMD PassThru DMA Engine" + depends on X86_64 && PCI + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + help + Enable support for the AMD PTDMA controller. This controller + provides DMA capabilities to perform high bandwidth memory to + memory and IO copy operations. It performs DMA transfer through + queue-based descriptor management. This DMA controller is intended + to be used with AMD Non-Transparent Bridge devices and not for + general purpose peripheral DMA. config AMD_QDMA tristate "AMD Queue-based DMA" diff --git a/drivers/dma/amd/Makefile b/drivers/dma/amd/Makefile index 37212be9364f..11278c06374d 100644 --- a/drivers/dma/amd/Makefile +++ b/drivers/dma/amd/Makefile @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_AMD_AE4DMA) += ae4dma/ +obj-$(CONFIG_AMD_PTDMA) += ptdma/ obj-$(CONFIG_AMD_QDMA) += qdma/ diff --git a/drivers/dma/amd/ae4dma/Makefile b/drivers/dma/amd/ae4dma/Makefile new file mode 100644 index 000000000000..e918f85a80ec --- /dev/null +++ b/drivers/dma/amd/ae4dma/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# AMD AE4DMA driver +# + +obj-$(CONFIG_AMD_AE4DMA) += ae4dma.o + +ae4dma-objs := ae4dma-dev.o + +ae4dma-$(CONFIG_PCI) += ae4dma-pci.o diff --git a/drivers/dma/amd/ae4dma/ae4dma-dev.c b/drivers/dma/amd/ae4dma/ae4dma-dev.c new file mode 100644 index 000000000000..8de3bef41b58 --- /dev/null +++ b/drivers/dma/amd/ae4dma/ae4dma-dev.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD AE4DMA driver + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Basavaraj Natikar + */ + +#include "ae4dma.h" + +static unsigned int max_hw_q = 1; +module_param(max_hw_q, uint, 0444); +MODULE_PARM_DESC(max_hw_q, "max hw queues supported by engine (any non-zero value, default: 1)"); + +static void ae4_pending_work(struct work_struct *work) +{ + struct ae4_cmd_queue *ae4cmd_q = container_of(work, struct ae4_cmd_queue, p_work.work); + struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q; + struct pt_cmd *cmd; + u32 cridx; + + for (;;) { + wait_event_interruptible(ae4cmd_q->q_w, + ((atomic64_read(&ae4cmd_q->done_cnt)) < + atomic64_read(&ae4cmd_q->intr_cnt))); + + atomic64_inc(&ae4cmd_q->done_cnt); + + mutex_lock(&ae4cmd_q->cmd_lock); + cridx = readl(cmd_q->reg_control + AE4_RD_IDX_OFF); + while ((ae4cmd_q->dridx != cridx) && !list_empty(&ae4cmd_q->cmd)) { + cmd = list_first_entry(&ae4cmd_q->cmd, struct pt_cmd, entry); + list_del(&cmd->entry); + + ae4_check_status_error(ae4cmd_q, ae4cmd_q->dridx); + cmd->pt_cmd_callback(cmd->data, cmd->ret); + + ae4cmd_q->q_cmd_count--; + ae4cmd_q->dridx = (ae4cmd_q->dridx + 1) % CMD_Q_LEN; + + complete_all(&ae4cmd_q->cmp); + } + mutex_unlock(&ae4cmd_q->cmd_lock); + } +} + +static irqreturn_t ae4_core_irq_handler(int irq, void *data) +{ + struct ae4_cmd_queue *ae4cmd_q = data; + struct pt_cmd_queue *cmd_q; + struct pt_device *pt; + u32 status; + + cmd_q = &ae4cmd_q->cmd_q; + pt = cmd_q->pt; + + pt->total_interrupts++; + atomic64_inc(&ae4cmd_q->intr_cnt); + + status = readl(cmd_q->reg_control + AE4_INTR_STS_OFF); + if (status & BIT(0)) { + status &= GENMASK(31, 1); + writel(status, cmd_q->reg_control + AE4_INTR_STS_OFF); + } + + wake_up(&ae4cmd_q->q_w); + + return IRQ_HANDLED; +} + +void ae4_destroy_work(struct ae4_device *ae4) +{ + struct ae4_cmd_queue *ae4cmd_q; + int i; + + for (i = 0; i < ae4->cmd_q_count; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + + if (!ae4cmd_q->pws) + break; + + cancel_delayed_work_sync(&ae4cmd_q->p_work); + destroy_workqueue(ae4cmd_q->pws); + } +} + +int ae4_core_init(struct ae4_device *ae4) +{ + struct pt_device *pt = &ae4->pt; + struct ae4_cmd_queue *ae4cmd_q; + struct device *dev = pt->dev; + struct pt_cmd_queue *cmd_q; + int i, ret = 0; + + writel(max_hw_q, pt->io_regs); + + for (i = 0; i < max_hw_q; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + ae4cmd_q->id = ae4->cmd_q_count; + ae4->cmd_q_count++; + + cmd_q = &ae4cmd_q->cmd_q; + cmd_q->pt = pt; + + cmd_q->reg_control = pt->io_regs + ((i + 1) * AE4_Q_SZ); + + ret = devm_request_irq(dev, ae4->ae4_irq[i], ae4_core_irq_handler, 0, + dev_name(pt->dev), ae4cmd_q); + if (ret) + return ret; + + cmd_q->qsize = Q_SIZE(sizeof(struct ae4dma_desc)); + + cmd_q->qbase = dmam_alloc_coherent(dev, cmd_q->qsize, &cmd_q->qbase_dma, + GFP_KERNEL); + if (!cmd_q->qbase) + return -ENOMEM; + } + + for (i = 0; i < ae4->cmd_q_count; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + + cmd_q = &ae4cmd_q->cmd_q; + + cmd_q->reg_control = pt->io_regs + ((i + 1) * AE4_Q_SZ); + + /* Update the device registers with queue information. */ + writel(CMD_Q_LEN, cmd_q->reg_control + AE4_MAX_IDX_OFF); + + cmd_q->qdma_tail = cmd_q->qbase_dma; + writel(lower_32_bits(cmd_q->qdma_tail), cmd_q->reg_control + AE4_Q_BASE_L_OFF); + writel(upper_32_bits(cmd_q->qdma_tail), cmd_q->reg_control + AE4_Q_BASE_H_OFF); + + INIT_LIST_HEAD(&ae4cmd_q->cmd); + init_waitqueue_head(&ae4cmd_q->q_w); + + ae4cmd_q->pws = alloc_ordered_workqueue("ae4dma_%d", WQ_MEM_RECLAIM, ae4cmd_q->id); + if (!ae4cmd_q->pws) { + ae4_destroy_work(ae4); + return -ENOMEM; + } + INIT_DELAYED_WORK(&ae4cmd_q->p_work, ae4_pending_work); + queue_delayed_work(ae4cmd_q->pws, &ae4cmd_q->p_work, usecs_to_jiffies(100)); + + init_completion(&ae4cmd_q->cmp); + } + + ret = pt_dmaengine_register(pt); + if (ret) + ae4_destroy_work(ae4); + else + ptdma_debugfs_setup(pt); + + return ret; +} diff --git a/drivers/dma/amd/ae4dma/ae4dma-pci.c b/drivers/dma/amd/ae4dma/ae4dma-pci.c new file mode 100644 index 000000000000..aad0dc4294a3 --- /dev/null +++ b/drivers/dma/amd/ae4dma/ae4dma-pci.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD AE4DMA driver + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Basavaraj Natikar + */ + +#include "ae4dma.h" + +static int ae4_get_irqs(struct ae4_device *ae4) +{ + struct ae4_msix *ae4_msix = ae4->ae4_msix; + struct pt_device *pt = &ae4->pt; + struct device *dev = pt->dev; + struct pci_dev *pdev; + int i, v, ret; + + pdev = to_pci_dev(dev); + + for (v = 0; v < ARRAY_SIZE(ae4_msix->msix_entry); v++) + ae4_msix->msix_entry[v].entry = v; + + ret = pci_alloc_irq_vectors(pdev, v, v, PCI_IRQ_MSIX); + if (ret != v) { + if (ret > 0) + pci_free_irq_vectors(pdev); + + dev_err(dev, "could not enable MSI-X (%d), trying MSI\n", ret); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (ret < 0) { + dev_err(dev, "could not enable MSI (%d)\n", ret); + return ret; + } + + ret = pci_irq_vector(pdev, 0); + if (ret < 0) { + pci_free_irq_vectors(pdev); + return ret; + } + + for (i = 0; i < MAX_AE4_HW_QUEUES; i++) + ae4->ae4_irq[i] = ret; + + } else { + ae4_msix->msix_count = ret; + for (i = 0; i < MAX_AE4_HW_QUEUES; i++) + ae4->ae4_irq[i] = ae4_msix->msix_entry[i].vector; + } + + return ret; +} + +static void ae4_free_irqs(struct ae4_device *ae4) +{ + struct ae4_msix *ae4_msix = ae4->ae4_msix; + struct pt_device *pt = &ae4->pt; + struct device *dev = pt->dev; + struct pci_dev *pdev; + + pdev = to_pci_dev(dev); + + if (ae4_msix && (ae4_msix->msix_count || ae4->ae4_irq[MAX_AE4_HW_QUEUES - 1])) + pci_free_irq_vectors(pdev); +} + +static void ae4_deinit(struct ae4_device *ae4) +{ + ae4_free_irqs(ae4); +} + +static int ae4_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + struct ae4_device *ae4; + struct pt_device *pt; + int bar_mask; + int ret = 0; + + ae4 = devm_kzalloc(dev, sizeof(*ae4), GFP_KERNEL); + if (!ae4) + return -ENOMEM; + + ae4->ae4_msix = devm_kzalloc(dev, sizeof(struct ae4_msix), GFP_KERNEL); + if (!ae4->ae4_msix) + return -ENOMEM; + + ret = pcim_enable_device(pdev); + if (ret) + goto ae4_error; + + bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); + ret = pcim_iomap_regions(pdev, bar_mask, "ae4dma"); + if (ret) + goto ae4_error; + + pt = &ae4->pt; + pt->dev = dev; + pt->ver = AE4_DMA_VERSION; + + pt->io_regs = pcim_iomap_table(pdev)[0]; + if (!pt->io_regs) { + ret = -ENOMEM; + goto ae4_error; + } + + ret = ae4_get_irqs(ae4); + if (ret < 0) + goto ae4_error; + + pci_set_master(pdev); + + dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)); + + dev_set_drvdata(dev, ae4); + + ret = ae4_core_init(ae4); + if (ret) + goto ae4_error; + + return 0; + +ae4_error: + ae4_deinit(ae4); + + return ret; +} + +static void ae4_pci_remove(struct pci_dev *pdev) +{ + struct ae4_device *ae4 = dev_get_drvdata(&pdev->dev); + + ae4_destroy_work(ae4); + ae4_deinit(ae4); +} + +static const struct pci_device_id ae4_pci_table[] = { + { PCI_VDEVICE(AMD, 0x14C8), }, + { PCI_VDEVICE(AMD, 0x14DC), }, + { PCI_VDEVICE(AMD, 0x149B), }, + /* Last entry must be zero */ + { 0, } +}; +MODULE_DEVICE_TABLE(pci, ae4_pci_table); + +static struct pci_driver ae4_pci_driver = { + .name = "ae4dma", + .id_table = ae4_pci_table, + .probe = ae4_pci_probe, + .remove = ae4_pci_remove, +}; + +module_pci_driver(ae4_pci_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("AMD AE4DMA driver"); diff --git a/drivers/dma/amd/ae4dma/ae4dma.h b/drivers/dma/amd/ae4dma/ae4dma.h new file mode 100644 index 000000000000..265c5d436008 --- /dev/null +++ b/drivers/dma/amd/ae4dma/ae4dma.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD AE4DMA driver + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Basavaraj Natikar + */ +#ifndef __AE4DMA_H__ +#define __AE4DMA_H__ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../ptdma/ptdma.h" +#include "../../virt-dma.h" + +#define MAX_AE4_HW_QUEUES 16 + +#define AE4_DESC_COMPLETED 0x03 + +#define AE4_MAX_IDX_OFF 0x08 +#define AE4_RD_IDX_OFF 0x0c +#define AE4_WR_IDX_OFF 0x10 +#define AE4_INTR_STS_OFF 0x14 +#define AE4_Q_BASE_L_OFF 0x18 +#define AE4_Q_BASE_H_OFF 0x1c +#define AE4_Q_SZ 0x20 + +#define AE4_DMA_VERSION 4 +#define CMD_AE4_DESC_DW0_VAL 2 + +struct ae4_msix { + int msix_count; + struct msix_entry msix_entry[MAX_AE4_HW_QUEUES]; +}; + +struct ae4_cmd_queue { + struct ae4_device *ae4; + struct pt_cmd_queue cmd_q; + struct list_head cmd; + /* protect command operations */ + struct mutex cmd_lock; + struct delayed_work p_work; + struct workqueue_struct *pws; + struct completion cmp; + wait_queue_head_t q_w; + atomic64_t intr_cnt; + atomic64_t done_cnt; + u64 q_cmd_count; + u32 dridx; + u32 tail_wi; + u32 id; +}; + +union dwou { + u32 dw0; + struct dword0 { + u8 byte0; + u8 byte1; + u16 timestamp; + } dws; +}; + +struct dword1 { + u8 status; + u8 err_code; + u16 desc_id; +}; + +struct ae4dma_desc { + union dwou dwouv; + struct dword1 dw1; + u32 length; + u32 rsvd; + u32 src_hi; + u32 src_lo; + u32 dst_hi; + u32 dst_lo; +}; + +struct ae4_device { + struct pt_device pt; + struct ae4_msix *ae4_msix; + struct ae4_cmd_queue ae4cmd_q[MAX_AE4_HW_QUEUES]; + unsigned int ae4_irq[MAX_AE4_HW_QUEUES]; + unsigned int cmd_q_count; +}; + +int ae4_core_init(struct ae4_device *ae4); +void ae4_destroy_work(struct ae4_device *ae4); +void ae4_check_status_error(struct ae4_cmd_queue *ae4cmd_q, int idx); +#endif diff --git a/drivers/dma/ptdma/Makefile b/drivers/dma/amd/ptdma/Makefile similarity index 100% rename from drivers/dma/ptdma/Makefile rename to drivers/dma/amd/ptdma/Makefile diff --git a/drivers/dma/ptdma/ptdma-debugfs.c b/drivers/dma/amd/ptdma/ptdma-debugfs.c similarity index 52% rename from drivers/dma/ptdma/ptdma-debugfs.c rename to drivers/dma/amd/ptdma/ptdma-debugfs.c index c8307d3044a3..c7c90bbf6fd8 100644 --- a/drivers/dma/ptdma/ptdma-debugfs.c +++ b/drivers/dma/amd/ptdma/ptdma-debugfs.c @@ -13,6 +13,7 @@ #include #include "ptdma.h" +#include "../ae4dma/ae4dma.h" /* DebugFS helpers */ #define RI_VERSION_NUM 0x0000003F @@ -23,11 +24,19 @@ static int pt_debugfs_info_show(struct seq_file *s, void *p) { struct pt_device *pt = s->private; + struct ae4_device *ae4; unsigned int regval; seq_printf(s, "Device name: %s\n", dev_name(pt->dev)); - seq_printf(s, " # Queues: %d\n", 1); - seq_printf(s, " # Cmds: %d\n", pt->cmd_count); + + if (pt->ver == AE4_DMA_VERSION) { + ae4 = container_of(pt, struct ae4_device, pt); + seq_printf(s, " # Queues: %d\n", ae4->cmd_q_count); + seq_printf(s, " # Cmds per queue: %d\n", CMD_Q_LEN); + } else { + seq_printf(s, " # Queues: %d\n", 1); + seq_printf(s, " # Cmds: %d\n", pt->cmd_count); + } regval = ioread32(pt->io_regs + CMD_PT_VERSION); @@ -55,6 +64,7 @@ static int pt_debugfs_stats_show(struct seq_file *s, void *p) static int pt_debugfs_queue_show(struct seq_file *s, void *p) { struct pt_cmd_queue *cmd_q = s->private; + struct pt_device *pt; unsigned int regval; if (!cmd_q) @@ -62,18 +72,24 @@ static int pt_debugfs_queue_show(struct seq_file *s, void *p) seq_printf(s, " Pass-Thru: %ld\n", cmd_q->total_pt_ops); - regval = ioread32(cmd_q->reg_control + 0x000C); + pt = cmd_q->pt; + if (pt->ver == AE4_DMA_VERSION) { + regval = readl(cmd_q->reg_control + 0x4); + seq_printf(s, " Enabled Interrupts:: status 0x%x\n", regval); + } else { + regval = ioread32(cmd_q->reg_control + 0x000C); - seq_puts(s, " Enabled Interrupts:"); - if (regval & INT_EMPTY_QUEUE) - seq_puts(s, " EMPTY"); - if (regval & INT_QUEUE_STOPPED) - seq_puts(s, " STOPPED"); - if (regval & INT_ERROR) - seq_puts(s, " ERROR"); - if (regval & INT_COMPLETION) - seq_puts(s, " COMPLETION"); - seq_puts(s, "\n"); + seq_puts(s, " Enabled Interrupts:"); + if (regval & INT_EMPTY_QUEUE) + seq_puts(s, " EMPTY"); + if (regval & INT_QUEUE_STOPPED) + seq_puts(s, " STOPPED"); + if (regval & INT_ERROR) + seq_puts(s, " ERROR"); + if (regval & INT_COMPLETION) + seq_puts(s, " COMPLETION"); + seq_puts(s, "\n"); + } return 0; } @@ -84,8 +100,12 @@ DEFINE_SHOW_ATTRIBUTE(pt_debugfs_stats); void ptdma_debugfs_setup(struct pt_device *pt) { - struct pt_cmd_queue *cmd_q; struct dentry *debugfs_q_instance; + struct ae4_cmd_queue *ae4cmd_q; + struct pt_cmd_queue *cmd_q; + struct ae4_device *ae4; + char name[30]; + int i; if (!debugfs_initialized()) return; @@ -96,11 +116,28 @@ void ptdma_debugfs_setup(struct pt_device *pt) debugfs_create_file("stats", 0400, pt->dma_dev.dbg_dev_root, pt, &pt_debugfs_stats_fops); - cmd_q = &pt->cmd_q; - debugfs_q_instance = - debugfs_create_dir("q", pt->dma_dev.dbg_dev_root); + if (pt->ver == AE4_DMA_VERSION) { + ae4 = container_of(pt, struct ae4_device, pt); + for (i = 0; i < ae4->cmd_q_count; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + cmd_q = &ae4cmd_q->cmd_q; - debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q, - &pt_debugfs_queue_fops); + memset(name, 0, sizeof(name)); + snprintf(name, 29, "q%d", ae4cmd_q->id); + + debugfs_q_instance = + debugfs_create_dir(name, pt->dma_dev.dbg_dev_root); + + debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q, + &pt_debugfs_queue_fops); + } + } else { + debugfs_q_instance = + debugfs_create_dir("q", pt->dma_dev.dbg_dev_root); + cmd_q = &pt->cmd_q; + debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q, + &pt_debugfs_queue_fops); + } } +EXPORT_SYMBOL_GPL(ptdma_debugfs_setup); diff --git a/drivers/dma/ptdma/ptdma-dev.c b/drivers/dma/amd/ptdma/ptdma-dev.c similarity index 100% rename from drivers/dma/ptdma/ptdma-dev.c rename to drivers/dma/amd/ptdma/ptdma-dev.c diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/amd/ptdma/ptdma-dmaengine.c similarity index 59% rename from drivers/dma/ptdma/ptdma-dmaengine.c rename to drivers/dma/amd/ptdma/ptdma-dmaengine.c index f79240734807..35c84ec9608b 100644 --- a/drivers/dma/ptdma/ptdma-dmaengine.c +++ b/drivers/dma/amd/ptdma/ptdma-dmaengine.c @@ -9,9 +9,58 @@ * Author: Gary R Hook */ +#include #include "ptdma.h" -#include "../dmaengine.h" -#include "../virt-dma.h" +#include "../ae4dma/ae4dma.h" +#include "../../dmaengine.h" + +static char *ae4_error_codes[] = { + "", + "ERR 01: INVALID HEADER DW0", + "ERR 02: INVALID STATUS", + "ERR 03: INVALID LENGTH - 4 BYTE ALIGNMENT", + "ERR 04: INVALID SRC ADDR - 4 BYTE ALIGNMENT", + "ERR 05: INVALID DST ADDR - 4 BYTE ALIGNMENT", + "ERR 06: INVALID ALIGNMENT", + "ERR 07: INVALID DESCRIPTOR", +}; + +static void ae4_log_error(struct pt_device *d, int e) +{ + /* ERR 01 - 07 represents Invalid AE4 errors */ + if (e <= 7) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", ae4_error_codes[e], e); + /* ERR 08 - 15 represents Invalid Descriptor errors */ + else if (e > 7 && e <= 15) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "INVALID DESCRIPTOR", e); + /* ERR 16 - 31 represents Firmware errors */ + else if (e > 15 && e <= 31) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "FIRMWARE ERROR", e); + /* ERR 32 - 63 represents Fatal errors */ + else if (e > 31 && e <= 63) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "FATAL ERROR", e); + /* ERR 64 - 255 represents PTE errors */ + else if (e > 63 && e <= 255) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "PTE ERROR", e); + else + dev_info(d->dev, "Unknown AE4DMA error"); +} + +void ae4_check_status_error(struct ae4_cmd_queue *ae4cmd_q, int idx) +{ + struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q; + struct ae4dma_desc desc; + u8 status; + + memcpy(&desc, &cmd_q->qbase[idx], sizeof(struct ae4dma_desc)); + status = desc.dw1.status; + if (status && status != AE4_DESC_COMPLETED) { + cmd_q->cmd_error = desc.dw1.err_code; + if (cmd_q->cmd_error) + ae4_log_error(cmd_q->pt, cmd_q->cmd_error); + } +} +EXPORT_SYMBOL_GPL(ae4_check_status_error); static inline struct pt_dma_chan *to_pt_chan(struct dma_chan *dma_chan) { @@ -45,7 +94,71 @@ static void pt_do_cleanup(struct virt_dma_desc *vd) kmem_cache_free(pt->dma_desc_cache, desc); } -static int pt_dma_start_desc(struct pt_dma_desc *desc) +static struct pt_cmd_queue *pt_get_cmd_queue(struct pt_device *pt, struct pt_dma_chan *chan) +{ + struct ae4_cmd_queue *ae4cmd_q; + struct pt_cmd_queue *cmd_q; + struct ae4_device *ae4; + + if (pt->ver == AE4_DMA_VERSION) { + ae4 = container_of(pt, struct ae4_device, pt); + ae4cmd_q = &ae4->ae4cmd_q[chan->id]; + cmd_q = &ae4cmd_q->cmd_q; + } else { + cmd_q = &pt->cmd_q; + } + + return cmd_q; +} + +static int ae4_core_execute_cmd(struct ae4dma_desc *desc, struct ae4_cmd_queue *ae4cmd_q) +{ + bool soc = FIELD_GET(DWORD0_SOC, desc->dwouv.dw0); + struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q; + + if (soc) { + desc->dwouv.dw0 |= FIELD_PREP(DWORD0_IOC, desc->dwouv.dw0); + desc->dwouv.dw0 &= ~DWORD0_SOC; + } + + mutex_lock(&ae4cmd_q->cmd_lock); + memcpy(&cmd_q->qbase[ae4cmd_q->tail_wi], desc, sizeof(struct ae4dma_desc)); + ae4cmd_q->q_cmd_count++; + ae4cmd_q->tail_wi = (ae4cmd_q->tail_wi + 1) % CMD_Q_LEN; + writel(ae4cmd_q->tail_wi, cmd_q->reg_control + AE4_WR_IDX_OFF); + mutex_unlock(&ae4cmd_q->cmd_lock); + + wake_up(&ae4cmd_q->q_w); + + return 0; +} + +static int pt_core_perform_passthru_ae4(struct pt_cmd_queue *cmd_q, + struct pt_passthru_engine *pt_engine) +{ + struct ae4_cmd_queue *ae4cmd_q = container_of(cmd_q, struct ae4_cmd_queue, cmd_q); + struct ae4dma_desc desc; + + cmd_q->cmd_error = 0; + cmd_q->total_pt_ops++; + memset(&desc, 0, sizeof(desc)); + desc.dwouv.dws.byte0 = CMD_AE4_DESC_DW0_VAL; + + desc.dw1.status = 0; + desc.dw1.err_code = 0; + desc.dw1.desc_id = 0; + + desc.length = pt_engine->src_len; + + desc.src_lo = upper_32_bits(pt_engine->src_dma); + desc.src_hi = lower_32_bits(pt_engine->src_dma); + desc.dst_lo = upper_32_bits(pt_engine->dst_dma); + desc.dst_hi = lower_32_bits(pt_engine->dst_dma); + + return ae4_core_execute_cmd(&desc, ae4cmd_q); +} + +static int pt_dma_start_desc(struct pt_dma_desc *desc, struct pt_dma_chan *chan) { struct pt_passthru_engine *pt_engine; struct pt_device *pt; @@ -56,13 +169,18 @@ static int pt_dma_start_desc(struct pt_dma_desc *desc) pt_cmd = &desc->pt_cmd; pt = pt_cmd->pt; - cmd_q = &pt->cmd_q; + + cmd_q = pt_get_cmd_queue(pt, chan); + pt_engine = &pt_cmd->passthru; pt->tdata.cmd = pt_cmd; /* Execute the command */ - pt_cmd->ret = pt_core_perform_passthru(cmd_q, pt_engine); + if (pt->ver == AE4_DMA_VERSION) + pt_cmd->ret = pt_core_perform_passthru_ae4(cmd_q, pt_engine); + else + pt_cmd->ret = pt_core_perform_passthru(cmd_q, pt_engine); return 0; } @@ -151,7 +269,7 @@ static void pt_cmd_callback(void *data, int err) if (!desc) break; - ret = pt_dma_start_desc(desc); + ret = pt_dma_start_desc(desc, chan); if (!ret) break; @@ -186,7 +304,10 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan, { struct pt_dma_chan *chan = to_pt_chan(dma_chan); struct pt_passthru_engine *pt_engine; + struct pt_device *pt = chan->pt; + struct ae4_cmd_queue *ae4cmd_q; struct pt_dma_desc *desc; + struct ae4_device *ae4; struct pt_cmd *pt_cmd; desc = pt_alloc_dma_desc(chan, flags); @@ -194,7 +315,7 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan, return NULL; pt_cmd = &desc->pt_cmd; - pt_cmd->pt = chan->pt; + pt_cmd->pt = pt; pt_engine = &pt_cmd->passthru; pt_cmd->engine = PT_ENGINE_PASSTHRU; pt_engine->src_dma = src; @@ -205,6 +326,14 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan, desc->len = len; + if (pt->ver == AE4_DMA_VERSION) { + ae4 = container_of(pt, struct ae4_device, pt); + ae4cmd_q = &ae4->ae4cmd_q[chan->id]; + mutex_lock(&ae4cmd_q->cmd_lock); + list_add_tail(&pt_cmd->entry, &ae4cmd_q->cmd); + mutex_unlock(&ae4cmd_q->cmd_lock); + } + return desc; } @@ -258,24 +387,43 @@ static void pt_issue_pending(struct dma_chan *dma_chan) pt_cmd_callback(desc, 0); } +static void pt_check_status_trans_ae4(struct pt_device *pt, struct pt_cmd_queue *cmd_q) +{ + struct ae4_cmd_queue *ae4cmd_q = container_of(cmd_q, struct ae4_cmd_queue, cmd_q); + int i; + + for (i = 0; i < CMD_Q_LEN; i++) + ae4_check_status_error(ae4cmd_q, i); +} + static enum dma_status pt_tx_status(struct dma_chan *c, dma_cookie_t cookie, struct dma_tx_state *txstate) { - struct pt_device *pt = to_pt_chan(c)->pt; - struct pt_cmd_queue *cmd_q = &pt->cmd_q; + struct pt_dma_chan *chan = to_pt_chan(c); + struct pt_device *pt = chan->pt; + struct pt_cmd_queue *cmd_q; + + cmd_q = pt_get_cmd_queue(pt, chan); + + if (pt->ver == AE4_DMA_VERSION) + pt_check_status_trans_ae4(pt, cmd_q); + else + pt_check_status_trans(pt, cmd_q); - pt_check_status_trans(pt, cmd_q); return dma_cookie_status(c, cookie, txstate); } static int pt_pause(struct dma_chan *dma_chan) { struct pt_dma_chan *chan = to_pt_chan(dma_chan); + struct pt_device *pt = chan->pt; + struct pt_cmd_queue *cmd_q; unsigned long flags; spin_lock_irqsave(&chan->vc.lock, flags); - pt_stop_queue(&chan->pt->cmd_q); + cmd_q = pt_get_cmd_queue(pt, chan); + pt_stop_queue(cmd_q); spin_unlock_irqrestore(&chan->vc.lock, flags); return 0; @@ -285,10 +433,13 @@ static int pt_resume(struct dma_chan *dma_chan) { struct pt_dma_chan *chan = to_pt_chan(dma_chan); struct pt_dma_desc *desc = NULL; + struct pt_device *pt = chan->pt; + struct pt_cmd_queue *cmd_q; unsigned long flags; spin_lock_irqsave(&chan->vc.lock, flags); - pt_start_queue(&chan->pt->cmd_q); + cmd_q = pt_get_cmd_queue(pt, chan); + pt_start_queue(cmd_q); desc = pt_next_dma_desc(chan); spin_unlock_irqrestore(&chan->vc.lock, flags); @@ -302,11 +453,17 @@ static int pt_resume(struct dma_chan *dma_chan) static int pt_terminate_all(struct dma_chan *dma_chan) { struct pt_dma_chan *chan = to_pt_chan(dma_chan); + struct pt_device *pt = chan->pt; + struct pt_cmd_queue *cmd_q; unsigned long flags; - struct pt_cmd_queue *cmd_q = &chan->pt->cmd_q; LIST_HEAD(head); - iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010); + cmd_q = pt_get_cmd_queue(pt, chan); + if (pt->ver == AE4_DMA_VERSION) + pt_stop_queue(cmd_q); + else + iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010); + spin_lock_irqsave(&chan->vc.lock, flags); vchan_get_all_descriptors(&chan->vc, &head); spin_unlock_irqrestore(&chan->vc.lock, flags); @@ -319,14 +476,24 @@ static int pt_terminate_all(struct dma_chan *dma_chan) int pt_dmaengine_register(struct pt_device *pt) { - struct pt_dma_chan *chan; struct dma_device *dma_dev = &pt->dma_dev; - char *cmd_cache_name; + struct ae4_cmd_queue *ae4cmd_q = NULL; + struct ae4_device *ae4 = NULL; + struct pt_dma_chan *chan; char *desc_cache_name; - int ret; + char *cmd_cache_name; + int ret, i; + + if (pt->ver == AE4_DMA_VERSION) + ae4 = container_of(pt, struct ae4_device, pt); + + if (ae4) + pt->pt_dma_chan = devm_kcalloc(pt->dev, ae4->cmd_q_count, + sizeof(*pt->pt_dma_chan), GFP_KERNEL); + else + pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan), + GFP_KERNEL); - pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan), - GFP_KERNEL); if (!pt->pt_dma_chan) return -ENOMEM; @@ -368,9 +535,6 @@ int pt_dmaengine_register(struct pt_device *pt) INIT_LIST_HEAD(&dma_dev->channels); - chan = pt->pt_dma_chan; - chan->pt = pt; - /* Set base and prep routines */ dma_dev->device_free_chan_resources = pt_free_chan_resources; dma_dev->device_prep_dma_memcpy = pt_prep_dma_memcpy; @@ -382,8 +546,21 @@ int pt_dmaengine_register(struct pt_device *pt) dma_dev->device_terminate_all = pt_terminate_all; dma_dev->device_synchronize = pt_synchronize; - chan->vc.desc_free = pt_do_cleanup; - vchan_init(&chan->vc, dma_dev); + if (ae4) { + for (i = 0; i < ae4->cmd_q_count; i++) { + chan = pt->pt_dma_chan + i; + ae4cmd_q = &ae4->ae4cmd_q[i]; + chan->id = ae4cmd_q->id; + chan->pt = pt; + chan->vc.desc_free = pt_do_cleanup; + vchan_init(&chan->vc, dma_dev); + } + } else { + chan = pt->pt_dma_chan; + chan->pt = pt; + chan->vc.desc_free = pt_do_cleanup; + vchan_init(&chan->vc, dma_dev); + } ret = dma_async_device_register(dma_dev); if (ret) @@ -399,6 +576,7 @@ err_cache: return ret; } +EXPORT_SYMBOL_GPL(pt_dmaengine_register); void pt_dmaengine_unregister(struct pt_device *pt) { diff --git a/drivers/dma/ptdma/ptdma-pci.c b/drivers/dma/amd/ptdma/ptdma-pci.c similarity index 100% rename from drivers/dma/ptdma/ptdma-pci.c rename to drivers/dma/amd/ptdma/ptdma-pci.c diff --git a/drivers/dma/ptdma/ptdma.h b/drivers/dma/amd/ptdma/ptdma.h similarity index 99% rename from drivers/dma/ptdma/ptdma.h rename to drivers/dma/amd/ptdma/ptdma.h index 39bc37268235..0a7939105e51 100644 --- a/drivers/dma/ptdma/ptdma.h +++ b/drivers/dma/amd/ptdma/ptdma.h @@ -22,7 +22,7 @@ #include #include -#include "../virt-dma.h" +#include "../../virt-dma.h" #define MAX_PT_NAME_LEN 16 #define MAX_DMAPOOL_NAME_LEN 32 @@ -184,6 +184,7 @@ struct pt_dma_desc { struct pt_dma_chan { struct virt_dma_chan vc; struct pt_device *pt; + u32 id; }; struct pt_cmd_queue { @@ -262,6 +263,7 @@ struct pt_device { unsigned long total_interrupts; struct pt_tasklet_data tdata; + int ver; }; /* diff --git a/drivers/dma/amd/qdma/qdma.c b/drivers/dma/amd/qdma/qdma.c index 6d9079458fe9..8fb2d5e1df20 100644 --- a/drivers/dma/amd/qdma/qdma.c +++ b/drivers/dma/amd/qdma/qdma.c @@ -7,9 +7,9 @@ #include #include #include +#include #include #include -#include #include #include #include @@ -283,16 +283,20 @@ static int qdma_check_queue_status(struct qdma_device *qdev, static int qdma_clear_queue_context(const struct qdma_queue *queue) { - enum qdma_ctxt_type h2c_types[] = { QDMA_CTXT_DESC_SW_H2C, - QDMA_CTXT_DESC_HW_H2C, - QDMA_CTXT_DESC_CR_H2C, - QDMA_CTXT_PFTCH, }; - enum qdma_ctxt_type c2h_types[] = { QDMA_CTXT_DESC_SW_C2H, - QDMA_CTXT_DESC_HW_C2H, - QDMA_CTXT_DESC_CR_C2H, - QDMA_CTXT_PFTCH, }; + static const enum qdma_ctxt_type h2c_types[] = { + QDMA_CTXT_DESC_SW_H2C, + QDMA_CTXT_DESC_HW_H2C, + QDMA_CTXT_DESC_CR_H2C, + QDMA_CTXT_PFTCH, + }; + static const enum qdma_ctxt_type c2h_types[] = { + QDMA_CTXT_DESC_SW_C2H, + QDMA_CTXT_DESC_HW_C2H, + QDMA_CTXT_DESC_CR_C2H, + QDMA_CTXT_PFTCH, + }; struct qdma_device *qdev = queue->qdev; - enum qdma_ctxt_type *type; + const enum qdma_ctxt_type *type; int ret, num, i; if (queue->dir == DMA_MEM_TO_DEV) { @@ -492,18 +496,9 @@ static int qdma_device_verify(struct qdma_device *qdev) static int qdma_device_setup(struct qdma_device *qdev) { - struct device *dev = &qdev->pdev->dev; u32 ring_sz = QDMA_DEFAULT_RING_SIZE; int ret = 0; - while (dev && get_dma_ops(dev)) - dev = dev->parent; - if (!dev) { - qdma_err(qdev, "dma device not found"); - return -EINVAL; - } - set_dma_ops(&qdev->pdev->dev, get_dma_ops(dev)); - ret = qdma_setup_fmap_context(qdev); if (ret) { qdma_err(qdev, "Failed setup fmap context"); @@ -548,11 +543,12 @@ static void qdma_free_queue_resources(struct dma_chan *chan) { struct qdma_queue *queue = to_qdma_queue(chan); struct qdma_device *qdev = queue->qdev; - struct device *dev = qdev->dma_dev.dev; + struct qdma_platdata *pdata; qdma_clear_queue_context(queue); vchan_free_chan_resources(&queue->vchan); - dma_free_coherent(dev, queue->ring_size * QDMA_MM_DESC_SIZE, + pdata = dev_get_platdata(&qdev->pdev->dev); + dma_free_coherent(pdata->dma_dev, queue->ring_size * QDMA_MM_DESC_SIZE, queue->desc_base, queue->dma_desc_base); } @@ -565,6 +561,7 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) struct qdma_queue *queue = to_qdma_queue(chan); struct qdma_device *qdev = queue->qdev; struct qdma_ctxt_sw_desc desc; + struct qdma_platdata *pdata; size_t size; int ret; @@ -572,8 +569,9 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) if (ret) return ret; + pdata = dev_get_platdata(&qdev->pdev->dev); size = queue->ring_size * QDMA_MM_DESC_SIZE; - queue->desc_base = dma_alloc_coherent(qdev->dma_dev.dev, size, + queue->desc_base = dma_alloc_coherent(pdata->dma_dev, size, &queue->dma_desc_base, GFP_KERNEL); if (!queue->desc_base) { @@ -588,7 +586,7 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) if (ret) { qdma_err(qdev, "Failed to setup SW desc ctxt for %s", chan->name); - dma_free_coherent(qdev->dma_dev.dev, size, queue->desc_base, + dma_free_coherent(pdata->dma_dev, size, queue->desc_base, queue->dma_desc_base); return ret; } @@ -948,8 +946,9 @@ static int qdma_init_error_irq(struct qdma_device *qdev) static int qdmam_alloc_qintr_rings(struct qdma_device *qdev) { - u32 ctxt[QDMA_CTXT_REGMAP_LEN]; + struct qdma_platdata *pdata = dev_get_platdata(&qdev->pdev->dev); struct device *dev = &qdev->pdev->dev; + u32 ctxt[QDMA_CTXT_REGMAP_LEN]; struct qdma_intr_ring *ring; struct qdma_ctxt_intr intr_ctxt; u32 vector; @@ -969,7 +968,8 @@ static int qdmam_alloc_qintr_rings(struct qdma_device *qdev) ring->msix_id = qdev->err_irq_idx + i + 1; ring->ridx = i; ring->color = 1; - ring->base = dmam_alloc_coherent(dev, QDMA_INTR_RING_SIZE, + ring->base = dmam_alloc_coherent(pdata->dma_dev, + QDMA_INTR_RING_SIZE, &ring->dev_base, GFP_KERNEL); if (!ring->base) { qdma_err(qdev, "Failed to alloc intr ring %d", i); diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index c499173d80b2..bd49f0374291 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -153,6 +153,8 @@ static int admac_alloc_sram_carveout(struct admac_data *ad, { struct admac_sram *sram; int i, ret = 0, nblocks; + ad->txcache.size = readl_relaxed(ad->base + REG_TX_SRAM_SIZE); + ad->rxcache.size = readl_relaxed(ad->base + REG_RX_SRAM_SIZE); if (dir == DMA_MEM_TO_DEV) sram = &ad->txcache; @@ -912,12 +914,7 @@ static int admac_probe(struct platform_device *pdev) goto free_irq; } - ad->txcache.size = readl_relaxed(ad->base + REG_TX_SRAM_SIZE); - ad->rxcache.size = readl_relaxed(ad->base + REG_RX_SRAM_SIZE); - dev_info(&pdev->dev, "Audio DMA Controller\n"); - dev_info(&pdev->dev, "imprint %x TX cache %u RX cache %u\n", - readl_relaxed(ad->base + REG_IMPRINT), ad->txcache.size, ad->rxcache.size); return 0; diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 9c7b40220004..ba25c23164e7 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1363,6 +1363,8 @@ at_xdmac_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value, return NULL; desc = at_xdmac_memset_create_desc(chan, atchan, dest, len, value); + if (!desc) + return NULL; list_add_tail(&desc->desc_node, &desc->descs_list); desc->tx_dma_desc.cookie = -EBUSY; diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index 7ba52dee40a9..20b10c15c696 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -875,6 +875,27 @@ static struct dma_chan *bcm2835_dma_xlate(struct of_phandle_args *spec, return chan; } +static int bcm2835_dma_suspend_late(struct device *dev) +{ + struct bcm2835_dmadev *od = dev_get_drvdata(dev); + struct bcm2835_chan *c, *next; + + list_for_each_entry_safe(c, next, &od->ddev.channels, + vc.chan.device_node) { + void __iomem *chan_base = c->chan_base; + + /* Check if DMA channel is busy */ + if (readl(chan_base + BCM2835_DMA_ADDR)) + return -EBUSY; + } + + return 0; +} + +static const struct dev_pm_ops bcm2835_dma_pm_ops = { + SET_LATE_SYSTEM_SLEEP_PM_OPS(bcm2835_dma_suspend_late, NULL) +}; + static int bcm2835_dma_probe(struct platform_device *pdev) { struct bcm2835_dmadev *od; @@ -1033,6 +1054,7 @@ static struct platform_driver bcm2835_dma_driver = { .driver = { .name = "bcm2835-dma", .of_match_table = of_match_ptr(bcm2835_dma_of_match), + .pm = pm_ptr(&bcm2835_dma_pm_ops), }, }; diff --git a/drivers/dma/dw/acpi.c b/drivers/dma/dw/acpi.c index c510c109d2c3..b6452fffa657 100644 --- a/drivers/dma/dw/acpi.c +++ b/drivers/dma/dw/acpi.c @@ -8,13 +8,15 @@ static bool dw_dma_acpi_filter(struct dma_chan *chan, void *param) { + struct dw_dma *dw = to_dw_dma(chan->device); + struct dw_dma_chip_pdata *data = dev_get_drvdata(dw->dma.dev); struct acpi_dma_spec *dma_spec = param; struct dw_dma_slave slave = { .dma_dev = dma_spec->dev, .src_id = dma_spec->slave_id, .dst_id = dma_spec->slave_id, - .m_master = 0, - .p_master = 1, + .m_master = data->m_master, + .p_master = data->p_master, }; return dw_dma_filter(chan, &slave); diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h index 563ce73488db..f1bd06a20cd6 100644 --- a/drivers/dma/dw/internal.h +++ b/drivers/dma/dw/internal.h @@ -51,11 +51,15 @@ struct dw_dma_chip_pdata { int (*probe)(struct dw_dma_chip *chip); int (*remove)(struct dw_dma_chip *chip); struct dw_dma_chip *chip; + u8 m_master; + u8 p_master; }; static __maybe_unused const struct dw_dma_chip_pdata dw_dma_chip_pdata = { .probe = dw_dma_probe, .remove = dw_dma_remove, + .m_master = 0, + .p_master = 1, }; static const struct dw_dma_platform_data idma32_pdata = { @@ -72,6 +76,8 @@ static __maybe_unused const struct dw_dma_chip_pdata idma32_chip_pdata = { .pdata = &idma32_pdata, .probe = idma32_dma_probe, .remove = idma32_dma_remove, + .m_master = 0, + .p_master = 0, }; static const struct dw_dma_platform_data xbar_pdata = { @@ -88,6 +94,8 @@ static __maybe_unused const struct dw_dma_chip_pdata xbar_chip_pdata = { .pdata = &xbar_pdata, .probe = idma32_dma_probe, .remove = idma32_dma_remove, + .m_master = 0, + .p_master = 0, }; #endif /* _DMA_DW_INTERNAL_H */ diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index ad2d4d012cf7..e8a0eb81726a 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -56,10 +56,10 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid) if (ret) return ret; - dw_dma_acpi_controller_register(chip->dw); - pci_set_drvdata(pdev, data); + dw_dma_acpi_controller_register(chip->dw); + return 0; } diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index b7f15ab96855..443b2430466c 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -480,8 +480,8 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan, bool disable_req, bool enable_sg) { struct dma_slave_config *cfg = &fsl_chan->cfg; + u32 burst = 0; u16 csr = 0; - u32 burst; /* * eDMA hardware SGs require the TCDs to be stored in little @@ -496,16 +496,30 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan, fsl_edma_set_tcd_to_le(fsl_chan, tcd, soff, soff); - if (fsl_chan->is_multi_fifo) { - /* set mloff to support multiple fifo */ - burst = cfg->direction == DMA_DEV_TO_MEM ? - cfg->src_maxburst : cfg->dst_maxburst; - nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4)); - /* enable DMLOE/SMLOE */ - if (cfg->direction == DMA_MEM_TO_DEV) { + /* If we expect to have either multi_fifo or a port window size, + * we will use minor loop offset, meaning bits 29-10 will be used for + * address offset, while bits 9-0 will be used to tell DMA how much + * data to read from addr. + * If we don't have either of those, will use a major loop reading from addr + * nbytes (29bits). + */ + if (cfg->direction == DMA_MEM_TO_DEV) { + if (fsl_chan->is_multi_fifo) + burst = cfg->dst_maxburst * 4; + if (cfg->dst_port_window_size) + burst = cfg->dst_port_window_size * cfg->dst_addr_width; + if (burst) { + nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-burst); nbytes |= EDMA_V3_TCD_NBYTES_DMLOE; nbytes &= ~EDMA_V3_TCD_NBYTES_SMLOE; - } else { + } + } else { + if (fsl_chan->is_multi_fifo) + burst = cfg->src_maxburst * 4; + if (cfg->src_port_window_size) + burst = cfg->src_port_window_size * cfg->src_addr_width; + if (burst) { + nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-burst); nbytes |= EDMA_V3_TCD_NBYTES_SMLOE; nbytes &= ~EDMA_V3_TCD_NBYTES_DMLOE; } @@ -623,11 +637,15 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic( dst_addr = fsl_chan->dma_dev_addr; soff = fsl_chan->cfg.dst_addr_width; doff = fsl_chan->is_multi_fifo ? 4 : 0; + if (fsl_chan->cfg.dst_port_window_size) + doff = fsl_chan->cfg.dst_addr_width; } else if (direction == DMA_DEV_TO_MEM) { src_addr = fsl_chan->dma_dev_addr; dst_addr = dma_buf_next; soff = fsl_chan->is_multi_fifo ? 4 : 0; doff = fsl_chan->cfg.src_addr_width; + if (fsl_chan->cfg.src_port_window_size) + soff = fsl_chan->cfg.src_addr_width; } else { /* DMA_DEV_TO_DEV */ src_addr = fsl_chan->cfg.src_addr; diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index ce37e1ee9c46..10a5565ddfd7 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -68,6 +68,8 @@ #define EDMA_V3_CH_CSR_EEI BIT(2) #define EDMA_V3_CH_CSR_DONE BIT(30) #define EDMA_V3_CH_CSR_ACTIVE BIT(31) +#define EDMA_V3_CH_ES_ERR BIT(31) +#define EDMA_V3_MP_ES_VLD BIT(31) enum fsl_edma_pm_state { RUNNING = 0, @@ -166,6 +168,7 @@ struct fsl_edma_chan { struct work_struct issue_worker; struct platform_device *pdev; struct device *pd_dev; + struct device_link *pd_dev_link; u32 srcid; struct clk *clk; int priority; @@ -240,6 +243,7 @@ struct fsl_edma_engine { const struct fsl_edma_drvdata *drvdata; u32 n_chans; int txirq; + int txirq_16_31; int errirq; bool big_endian; struct edma_regs regs; diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 60de1003193a..f989b6c9c0a9 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -3,10 +3,11 @@ * drivers/dma/fsl-edma.c * * Copyright 2013-2014 Freescale Semiconductor, Inc. + * Copyright 2024 NXP * * Driver for the Freescale eDMA engine with flexible channel multiplexing * capability for DMA request sources. The eDMA block can be found on some - * Vybrid and Layerscape SoCs. + * Vybrid, Layerscape and S32G SoCs. */ #include @@ -72,6 +73,60 @@ static irqreturn_t fsl_edma2_tx_handler(int irq, void *devi_id) return fsl_edma_tx_handler(irq, fsl_chan->edma); } +static irqreturn_t fsl_edma3_or_tx_handler(int irq, void *dev_id, + u8 start, u8 end) +{ + struct fsl_edma_engine *fsl_edma = dev_id; + struct fsl_edma_chan *chan; + int i; + + end = min(end, fsl_edma->n_chans); + + for (i = start; i < end; i++) { + chan = &fsl_edma->chans[i]; + + fsl_edma3_tx_handler(irq, chan); + } + + return IRQ_HANDLED; +} + +static irqreturn_t fsl_edma3_tx_0_15_handler(int irq, void *dev_id) +{ + return fsl_edma3_or_tx_handler(irq, dev_id, 0, 16); +} + +static irqreturn_t fsl_edma3_tx_16_31_handler(int irq, void *dev_id) +{ + return fsl_edma3_or_tx_handler(irq, dev_id, 16, 32); +} + +static irqreturn_t fsl_edma3_or_err_handler(int irq, void *dev_id) +{ + struct fsl_edma_engine *fsl_edma = dev_id; + struct edma_regs *regs = &fsl_edma->regs; + unsigned int err, ch, ch_es; + struct fsl_edma_chan *chan; + + err = edma_readl(fsl_edma, regs->es); + if (!(err & EDMA_V3_MP_ES_VLD)) + return IRQ_NONE; + + for (ch = 0; ch < fsl_edma->n_chans; ch++) { + chan = &fsl_edma->chans[ch]; + + ch_es = edma_readl_chreg(chan, ch_es); + if (!(ch_es & EDMA_V3_CH_ES_ERR)) + continue; + + edma_writel_chreg(chan, EDMA_V3_CH_ES_ERR, ch_es); + fsl_edma_disable_request(chan); + fsl_edma->chans[ch].status = DMA_ERROR; + } + + return IRQ_HANDLED; +} + static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id) { struct fsl_edma_engine *fsl_edma = dev_id; @@ -274,6 +329,49 @@ static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engi return 0; } +static int fsl_edma3_or_irq_init(struct platform_device *pdev, + struct fsl_edma_engine *fsl_edma) +{ + int ret; + + fsl_edma->txirq = platform_get_irq_byname(pdev, "tx-0-15"); + if (fsl_edma->txirq < 0) + return fsl_edma->txirq; + + fsl_edma->txirq_16_31 = platform_get_irq_byname(pdev, "tx-16-31"); + if (fsl_edma->txirq_16_31 < 0) + return fsl_edma->txirq_16_31; + + fsl_edma->errirq = platform_get_irq_byname(pdev, "err"); + if (fsl_edma->errirq < 0) + return fsl_edma->errirq; + + ret = devm_request_irq(&pdev->dev, fsl_edma->txirq, + fsl_edma3_tx_0_15_handler, 0, "eDMA tx0_15", + fsl_edma); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Can't register eDMA tx0_15 IRQ.\n"); + + if (fsl_edma->n_chans > 16) { + ret = devm_request_irq(&pdev->dev, fsl_edma->txirq_16_31, + fsl_edma3_tx_16_31_handler, 0, + "eDMA tx16_31", fsl_edma); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Can't register eDMA tx16_31 IRQ.\n"); + } + + ret = devm_request_irq(&pdev->dev, fsl_edma->errirq, + fsl_edma3_or_err_handler, 0, "eDMA err", + fsl_edma); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Can't register eDMA err IRQ.\n"); + + return 0; +} + static int fsl_edma2_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma) @@ -404,6 +502,14 @@ static struct fsl_edma_drvdata imx95_data5 = { .setup_irq = fsl_edma3_irq_init, }; +static const struct fsl_edma_drvdata s32g2_data = { + .dmamuxs = DMAMUX_NR, + .chreg_space_sz = EDMA_TCD, + .chreg_off = 0x4000, + .flags = FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MUX_SWAP, + .setup_irq = fsl_edma3_or_irq_init, +}; + static const struct of_device_id fsl_edma_dt_ids[] = { { .compatible = "fsl,vf610-edma", .data = &vf610_data}, { .compatible = "fsl,ls1028a-edma", .data = &ls1028a_data}, @@ -413,14 +519,38 @@ static const struct of_device_id fsl_edma_dt_ids[] = { { .compatible = "fsl,imx93-edma3", .data = &imx93_data3}, { .compatible = "fsl,imx93-edma4", .data = &imx93_data4}, { .compatible = "fsl,imx95-edma5", .data = &imx95_data5}, + { .compatible = "nxp,s32g2-edma", .data = &s32g2_data}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids); +static void fsl_edma3_detach_pd(struct fsl_edma_engine *fsl_edma) +{ + struct fsl_edma_chan *fsl_chan; + int i; + + for (i = 0; i < fsl_edma->n_chans; i++) { + if (fsl_edma->chan_masked & BIT(i)) + continue; + fsl_chan = &fsl_edma->chans[i]; + if (fsl_chan->pd_dev_link) + device_link_del(fsl_chan->pd_dev_link); + if (fsl_chan->pd_dev) { + dev_pm_domain_detach(fsl_chan->pd_dev, false); + pm_runtime_dont_use_autosuspend(fsl_chan->pd_dev); + pm_runtime_set_suspended(fsl_chan->pd_dev); + } + } +} + +static void devm_fsl_edma3_detach_pd(void *data) +{ + fsl_edma3_detach_pd(data); +} + static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma) { struct fsl_edma_chan *fsl_chan; - struct device_link *link; struct device *pd_chan; struct device *dev; int i; @@ -436,15 +566,16 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng pd_chan = dev_pm_domain_attach_by_id(dev, i); if (IS_ERR_OR_NULL(pd_chan)) { dev_err(dev, "Failed attach pd %d\n", i); - return -EINVAL; + goto detach; } - link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | + fsl_chan->pd_dev_link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (!link) { + if (!fsl_chan->pd_dev_link) { dev_err(dev, "Failed to add device_link to %d\n", i); - return -EINVAL; + dev_pm_domain_detach(pd_chan, false); + goto detach; } fsl_chan->pd_dev = pd_chan; @@ -455,6 +586,10 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng } return 0; + +detach: + fsl_edma3_detach_pd(fsl_edma); + return -EINVAL; } static int fsl_edma_probe(struct platform_device *pdev) @@ -517,10 +652,6 @@ static int fsl_edma_probe(struct platform_device *pdev) for (i = 0; i < fsl_edma->drvdata->dmamuxs; i++) { char clkname[32]; - /* eDMAv3 mux register move to TCD area if ch_mux exist */ - if (drvdata->flags & FSL_EDMA_DRV_SPLIT_REG) - break; - fsl_edma->muxbase[i] = devm_platform_ioremap_resource(pdev, 1 + i); if (IS_ERR(fsl_edma->muxbase[i])) { @@ -544,6 +675,9 @@ static int fsl_edma_probe(struct platform_device *pdev) ret = fsl_edma3_attach_pd(pdev, fsl_edma); if (ret) return ret; + ret = devm_add_action_or_reset(&pdev->dev, devm_fsl_edma3_detach_pd, fsl_edma); + if (ret) + return ret; } if (drvdata->flags & FSL_EDMA_DRV_TCD64) @@ -646,7 +780,7 @@ static int fsl_edma_probe(struct platform_device *pdev) } ret = of_dma_controller_register(np, - drvdata->flags & FSL_EDMA_DRV_SPLIT_REG ? fsl_edma3_xlate : fsl_edma_xlate, + drvdata->dmamuxs ? fsl_edma_xlate : fsl_edma3_xlate, fsl_edma); if (ret) { dev_err(&pdev->dev, diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 57f1bf2ab20b..ff94ee892339 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -28,7 +28,6 @@ struct idxd_cdev_context { * global to avoid conflict file names. */ static DEFINE_IDA(file_ida); -static DEFINE_MUTEX(ida_lock); /* * ictx is an array based off of accelerator types. enum idxd_type @@ -123,9 +122,7 @@ static void idxd_file_dev_release(struct device *dev) struct idxd_device *idxd = wq->idxd; int rc; - mutex_lock(&ida_lock); ida_free(&file_ida, ctx->id); - mutex_unlock(&ida_lock); /* Wait for in-flight operations to complete. */ if (wq_shared(wq)) { @@ -284,9 +281,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) } idxd_cdev = wq->idxd_cdev; - mutex_lock(&ida_lock); ctx->id = ida_alloc(&file_ida, GFP_KERNEL); - mutex_unlock(&ida_lock); if (ctx->id < 0) { dev_warn(dev, "ida alloc failure\n"); goto failed_ida; diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index d84e21daa991..214b8039439f 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -374,6 +374,17 @@ struct idxd_device { struct dentry *dbgfs_evl_file; bool user_submission_safe; + + struct idxd_saved_states *idxd_saved; +}; + +struct idxd_saved_states { + struct idxd_device saved_idxd; + struct idxd_evl saved_evl; + struct idxd_engine **saved_engines; + struct idxd_wq **saved_wqs; + struct idxd_group **saved_groups; + unsigned long *saved_wq_enable_map; }; static inline unsigned int evl_ent_size(struct idxd_device *idxd) @@ -725,8 +736,6 @@ static inline void idxd_desc_complete(struct idxd_desc *desc, &desc->txd, &status); } -int idxd_register_bus_type(void); -void idxd_unregister_bus_type(void); int idxd_register_devices(struct idxd_device *idxd); void idxd_unregister_devices(struct idxd_device *idxd); void idxd_wqs_quiesce(struct idxd_device *idxd); @@ -742,6 +751,8 @@ void idxd_unmask_error_interrupts(struct idxd_device *idxd); /* device control */ int idxd_device_drv_probe(struct idxd_dev *idxd_dev); +int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev, + const struct pci_device_id *id); void idxd_device_drv_remove(struct idxd_dev *idxd_dev); int idxd_drv_enable_wq(struct idxd_wq *wq); void idxd_drv_disable_wq(struct idxd_wq *wq); diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 140f8d772bee..b946f78f85e1 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -78,6 +78,8 @@ static struct pci_device_id idxd_pci_tbl[] = { { PCI_DEVICE_DATA(INTEL, IAX_SPR0, &idxd_driver_data[IDXD_TYPE_IAX]) }, /* IAA on DMR platforms */ { PCI_DEVICE_DATA(INTEL, IAA_DMR, &idxd_driver_data[IDXD_TYPE_IAX]) }, + /* IAA PTL platforms */ + { PCI_DEVICE_DATA(INTEL, IAA_PTL, &idxd_driver_data[IDXD_TYPE_IAX]) }, { 0, } }; MODULE_DEVICE_TABLE(pci, idxd_pci_tbl); @@ -723,67 +725,464 @@ static void idxd_cleanup(struct idxd_device *idxd) idxd_disable_sva(idxd->pdev); } -static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +/* + * Attach IDXD device to IDXD driver. + */ +static int idxd_bind(struct device_driver *drv, const char *buf) { - struct device *dev = &pdev->dev; - struct idxd_device *idxd; - struct idxd_driver_data *data = (struct idxd_driver_data *)id->driver_data; + const struct bus_type *bus = drv->bus; + struct device *dev; + int err = -ENODEV; + + dev = bus_find_device_by_name(bus, NULL, buf); + if (dev) + err = device_driver_attach(drv, dev); + + put_device(dev); + + return err; +} + +/* + * Detach IDXD device from driver. + */ +static void idxd_unbind(struct device_driver *drv, const char *buf) +{ + const struct bus_type *bus = drv->bus; + struct device *dev; + + dev = bus_find_device_by_name(bus, NULL, buf); + if (dev && dev->driver == drv) + device_release_driver(dev); + + put_device(dev); +} + +#define idxd_free_saved_configs(saved_configs, count) \ + do { \ + int i; \ + \ + for (i = 0; i < (count); i++) \ + kfree(saved_configs[i]); \ + } while (0) + +static void idxd_free_saved(struct idxd_group **saved_groups, + struct idxd_engine **saved_engines, + struct idxd_wq **saved_wqs, + struct idxd_device *idxd) +{ + if (saved_groups) + idxd_free_saved_configs(saved_groups, idxd->max_groups); + if (saved_engines) + idxd_free_saved_configs(saved_engines, idxd->max_engines); + if (saved_wqs) + idxd_free_saved_configs(saved_wqs, idxd->max_wqs); +} + +/* + * Save IDXD device configurations including engines, groups, wqs etc. + * The saved configurations can be restored when needed. + */ +static int idxd_device_config_save(struct idxd_device *idxd, + struct idxd_saved_states *idxd_saved) +{ + struct device *dev = &idxd->pdev->dev; + int i; + + memcpy(&idxd_saved->saved_idxd, idxd, sizeof(*idxd)); + + if (idxd->evl) { + memcpy(&idxd_saved->saved_evl, idxd->evl, + sizeof(struct idxd_evl)); + } + + struct idxd_group **saved_groups __free(kfree) = + kcalloc_node(idxd->max_groups, + sizeof(struct idxd_group *), + GFP_KERNEL, dev_to_node(dev)); + if (!saved_groups) + return -ENOMEM; + + for (i = 0; i < idxd->max_groups; i++) { + struct idxd_group *saved_group __free(kfree) = + kzalloc_node(sizeof(*saved_group), GFP_KERNEL, + dev_to_node(dev)); + + if (!saved_group) { + /* Free saved groups */ + idxd_free_saved(saved_groups, NULL, NULL, idxd); + + return -ENOMEM; + } + + memcpy(saved_group, idxd->groups[i], sizeof(*saved_group)); + saved_groups[i] = no_free_ptr(saved_group); + } + + struct idxd_engine **saved_engines = + kcalloc_node(idxd->max_engines, + sizeof(struct idxd_engine *), + GFP_KERNEL, dev_to_node(dev)); + if (!saved_engines) { + /* Free saved groups */ + idxd_free_saved(saved_groups, NULL, NULL, idxd); + + return -ENOMEM; + } + for (i = 0; i < idxd->max_engines; i++) { + struct idxd_engine *saved_engine __free(kfree) = + kzalloc_node(sizeof(*saved_engine), GFP_KERNEL, + dev_to_node(dev)); + if (!saved_engine) { + /* Free saved groups and engines */ + idxd_free_saved(saved_groups, saved_engines, NULL, + idxd); + + return -ENOMEM; + } + + memcpy(saved_engine, idxd->engines[i], sizeof(*saved_engine)); + saved_engines[i] = no_free_ptr(saved_engine); + } + + unsigned long *saved_wq_enable_map __free(bitmap) = + bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, + dev_to_node(dev)); + if (!saved_wq_enable_map) { + /* Free saved groups and engines */ + idxd_free_saved(saved_groups, saved_engines, NULL, idxd); + + return -ENOMEM; + } + + bitmap_copy(saved_wq_enable_map, idxd->wq_enable_map, idxd->max_wqs); + + struct idxd_wq **saved_wqs __free(kfree) = + kcalloc_node(idxd->max_wqs, sizeof(struct idxd_wq *), + GFP_KERNEL, dev_to_node(dev)); + if (!saved_wqs) { + /* Free saved groups and engines */ + idxd_free_saved(saved_groups, saved_engines, NULL, idxd); + + return -ENOMEM; + } + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *saved_wq __free(kfree) = + kzalloc_node(sizeof(*saved_wq), GFP_KERNEL, + dev_to_node(dev)); + struct idxd_wq *wq; + + if (!saved_wq) { + /* Free saved groups, engines, and wqs */ + idxd_free_saved(saved_groups, saved_engines, saved_wqs, + idxd); + + return -ENOMEM; + } + + if (!test_bit(i, saved_wq_enable_map)) + continue; + + wq = idxd->wqs[i]; + mutex_lock(&wq->wq_lock); + memcpy(saved_wq, wq, sizeof(*saved_wq)); + saved_wqs[i] = no_free_ptr(saved_wq); + mutex_unlock(&wq->wq_lock); + } + + /* Save configurations */ + idxd_saved->saved_groups = no_free_ptr(saved_groups); + idxd_saved->saved_engines = no_free_ptr(saved_engines); + idxd_saved->saved_wq_enable_map = no_free_ptr(saved_wq_enable_map); + idxd_saved->saved_wqs = no_free_ptr(saved_wqs); + + return 0; +} + +/* + * Restore IDXD device configurations including engines, groups, wqs etc + * that were saved before. + */ +static void idxd_device_config_restore(struct idxd_device *idxd, + struct idxd_saved_states *idxd_saved) +{ + struct idxd_evl *saved_evl = &idxd_saved->saved_evl; + int i; + + idxd->rdbuf_limit = idxd_saved->saved_idxd.rdbuf_limit; + + if (saved_evl) + idxd->evl->size = saved_evl->size; + + for (i = 0; i < idxd->max_groups; i++) { + struct idxd_group *saved_group, *group; + + saved_group = idxd_saved->saved_groups[i]; + group = idxd->groups[i]; + + group->rdbufs_allowed = saved_group->rdbufs_allowed; + group->rdbufs_reserved = saved_group->rdbufs_reserved; + group->tc_a = saved_group->tc_a; + group->tc_b = saved_group->tc_b; + group->use_rdbuf_limit = saved_group->use_rdbuf_limit; + + kfree(saved_group); + } + kfree(idxd_saved->saved_groups); + + for (i = 0; i < idxd->max_engines; i++) { + struct idxd_engine *saved_engine, *engine; + + saved_engine = idxd_saved->saved_engines[i]; + engine = idxd->engines[i]; + + engine->group = saved_engine->group; + + kfree(saved_engine); + } + kfree(idxd_saved->saved_engines); + + bitmap_copy(idxd->wq_enable_map, idxd_saved->saved_wq_enable_map, + idxd->max_wqs); + bitmap_free(idxd_saved->saved_wq_enable_map); + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *saved_wq, *wq; + size_t len; + + if (!test_bit(i, idxd->wq_enable_map)) + continue; + + saved_wq = idxd_saved->saved_wqs[i]; + wq = idxd->wqs[i]; + + mutex_lock(&wq->wq_lock); + + wq->group = saved_wq->group; + wq->flags = saved_wq->flags; + wq->threshold = saved_wq->threshold; + wq->size = saved_wq->size; + wq->priority = saved_wq->priority; + wq->type = saved_wq->type; + len = strlen(saved_wq->name) + 1; + strscpy(wq->name, saved_wq->name, len); + wq->max_xfer_bytes = saved_wq->max_xfer_bytes; + wq->max_batch_size = saved_wq->max_batch_size; + wq->enqcmds_retries = saved_wq->enqcmds_retries; + wq->descs = saved_wq->descs; + wq->idxd_chan = saved_wq->idxd_chan; + len = strlen(saved_wq->driver_name) + 1; + strscpy(wq->driver_name, saved_wq->driver_name, len); + + mutex_unlock(&wq->wq_lock); + + kfree(saved_wq); + } + + kfree(idxd_saved->saved_wqs); +} + +static void idxd_reset_prepare(struct pci_dev *pdev) +{ + struct idxd_device *idxd = pci_get_drvdata(pdev); + struct device *dev = &idxd->pdev->dev; + const char *idxd_name; int rc; + dev = &idxd->pdev->dev; + idxd_name = dev_name(idxd_confdev(idxd)); + + struct idxd_saved_states *idxd_saved __free(kfree) = + kzalloc_node(sizeof(*idxd_saved), GFP_KERNEL, + dev_to_node(&pdev->dev)); + if (!idxd_saved) { + dev_err(dev, "HALT: no memory\n"); + + return; + } + + /* Save IDXD configurations. */ + rc = idxd_device_config_save(idxd, idxd_saved); + if (rc < 0) { + dev_err(dev, "HALT: cannot save %s configs\n", idxd_name); + + return; + } + + idxd->idxd_saved = no_free_ptr(idxd_saved); + + /* Save PCI device state. */ + pci_save_state(idxd->pdev); +} + +static void idxd_reset_done(struct pci_dev *pdev) +{ + struct idxd_device *idxd = pci_get_drvdata(pdev); + const char *idxd_name; + struct device *dev; + int rc, i; + + if (!idxd->idxd_saved) + return; + + dev = &idxd->pdev->dev; + idxd_name = dev_name(idxd_confdev(idxd)); + + /* Restore PCI device state. */ + pci_restore_state(idxd->pdev); + + /* Unbind idxd device from driver. */ + idxd_unbind(&idxd_drv.drv, idxd_name); + + /* + * Probe PCI device without allocating or changing + * idxd software data which keeps the same as before FLR. + */ + idxd_pci_probe_alloc(idxd, NULL, NULL); + + /* Restore IDXD configurations. */ + idxd_device_config_restore(idxd, idxd->idxd_saved); + + /* Re-configure IDXD device if allowed. */ + if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) { + rc = idxd_device_config(idxd); + if (rc < 0) { + dev_err(dev, "HALT: %s config fails\n", idxd_name); + goto out; + } + } + + /* Bind IDXD device to driver. */ + rc = idxd_bind(&idxd_drv.drv, idxd_name); + if (rc < 0) { + dev_err(dev, "HALT: binding %s to driver fails\n", idxd_name); + goto out; + } + + /* Bind enabled wq in the IDXD device to driver. */ + for (i = 0; i < idxd->max_wqs; i++) { + if (test_bit(i, idxd->wq_enable_map)) { + struct idxd_wq *wq = idxd->wqs[i]; + char wq_name[32]; + + wq->state = IDXD_WQ_DISABLED; + sprintf(wq_name, "wq%d.%d", idxd->id, wq->id); + /* + * Bind to user driver depending on wq type. + * + * Currently only support user type WQ. Will support + * kernel type WQ in the future. + */ + if (wq->type == IDXD_WQT_USER) + rc = idxd_bind(&idxd_user_drv.drv, wq_name); + else + rc = -EINVAL; + if (rc < 0) { + clear_bit(i, idxd->wq_enable_map); + dev_err(dev, + "HALT: unable to re-enable wq %s\n", + dev_name(wq_confdev(wq))); + } + } + } +out: + kfree(idxd->idxd_saved); +} + +static const struct pci_error_handlers idxd_error_handler = { + .reset_prepare = idxd_reset_prepare, + .reset_done = idxd_reset_done, +}; + +/* + * Probe idxd PCI device. + * If idxd is not given, need to allocate idxd and set up its data. + * + * If idxd is given, idxd was allocated and setup already. Just need to + * configure device without re-allocating and re-configuring idxd data. + * This is useful for recovering from FLR. + */ +int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev, + const struct pci_device_id *id) +{ + bool alloc_idxd = idxd ? false : true; + struct idxd_driver_data *data; + struct device *dev; + int rc; + + pdev = idxd ? idxd->pdev : pdev; + dev = &pdev->dev; + data = id ? (struct idxd_driver_data *)id->driver_data : NULL; rc = pci_enable_device(pdev); if (rc) return rc; - dev_dbg(dev, "Alloc IDXD context\n"); - idxd = idxd_alloc(pdev, data); - if (!idxd) { - rc = -ENOMEM; - goto err_idxd_alloc; - } + if (alloc_idxd) { + dev_dbg(dev, "Alloc IDXD context\n"); + idxd = idxd_alloc(pdev, data); + if (!idxd) { + rc = -ENOMEM; + goto err_idxd_alloc; + } - dev_dbg(dev, "Mapping BARs\n"); - idxd->reg_base = pci_iomap(pdev, IDXD_MMIO_BAR, 0); - if (!idxd->reg_base) { - rc = -ENOMEM; - goto err_iomap; - } + dev_dbg(dev, "Mapping BARs\n"); + idxd->reg_base = pci_iomap(pdev, IDXD_MMIO_BAR, 0); + if (!idxd->reg_base) { + rc = -ENOMEM; + goto err_iomap; + } - dev_dbg(dev, "Set DMA masks\n"); - rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (rc) - goto err; + dev_dbg(dev, "Set DMA masks\n"); + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (rc) + goto err; + } dev_dbg(dev, "Set PCI master\n"); pci_set_master(pdev); pci_set_drvdata(pdev, idxd); - idxd->hw.version = ioread32(idxd->reg_base + IDXD_VER_OFFSET); - rc = idxd_probe(idxd); - if (rc) { - dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n"); - goto err; - } + if (alloc_idxd) { + idxd->hw.version = ioread32(idxd->reg_base + IDXD_VER_OFFSET); + rc = idxd_probe(idxd); + if (rc) { + dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n"); + goto err; + } - if (data->load_device_defaults) { - rc = data->load_device_defaults(idxd); + if (data->load_device_defaults) { + rc = data->load_device_defaults(idxd); + if (rc) + dev_warn(dev, "IDXD loading device defaults failed\n"); + } + + rc = idxd_register_devices(idxd); + if (rc) { + dev_err(dev, "IDXD sysfs setup failed\n"); + goto err_dev_register; + } + + rc = idxd_device_init_debugfs(idxd); if (rc) - dev_warn(dev, "IDXD loading device defaults failed\n"); + dev_warn(dev, "IDXD debugfs failed to setup\n"); } - rc = idxd_register_devices(idxd); - if (rc) { - dev_err(dev, "IDXD sysfs setup failed\n"); - goto err_dev_register; - } + if (!alloc_idxd) { + /* Release interrupts in the IDXD device. */ + idxd_cleanup_interrupts(idxd); - rc = idxd_device_init_debugfs(idxd); - if (rc) - dev_warn(dev, "IDXD debugfs failed to setup\n"); + /* Re-enable interrupts in the IDXD device. */ + rc = idxd_setup_interrupts(idxd); + if (rc) + dev_warn(dev, "IDXD interrupts failed to setup\n"); + } dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n", idxd->hw.version); - idxd->user_submission_safe = data->user_submission_safe; + if (data) + idxd->user_submission_safe = data->user_submission_safe; return 0; @@ -798,6 +1197,11 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return rc; } +static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + return idxd_pci_probe_alloc(NULL, pdev, id); +} + void idxd_wqs_quiesce(struct idxd_device *idxd) { struct idxd_wq *wq; @@ -864,6 +1268,7 @@ static struct pci_driver idxd_pci_driver = { .probe = idxd_pci_probe, .remove = idxd_remove, .shutdown = idxd_shutdown, + .err_handler = &idxd_error_handler, }; static int __init idxd_init_module(void) diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index fc049c9c9892..1107db3ce0a3 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -383,15 +383,65 @@ static void process_evl_entries(struct idxd_device *idxd) mutex_unlock(&evl->lock); } +static void idxd_device_flr(struct work_struct *work) +{ + struct idxd_device *idxd = container_of(work, struct idxd_device, work); + int rc; + + /* + * IDXD device requires a Function Level Reset (FLR). + * pci_reset_function() will reset the device with FLR. + */ + rc = pci_reset_function(idxd->pdev); + if (rc) + dev_err(&idxd->pdev->dev, "FLR failed\n"); +} + +static irqreturn_t idxd_halt(struct idxd_device *idxd) +{ + union gensts_reg gensts; + + gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET); + if (gensts.state == IDXD_DEVICE_STATE_HALT) { + idxd->state = IDXD_DEV_HALTED; + if (gensts.reset_type == IDXD_DEVICE_RESET_SOFTWARE) { + /* + * If we need a software reset, we will throw the work + * on a system workqueue in order to allow interrupts + * for the device command completions. + */ + INIT_WORK(&idxd->work, idxd_device_reinit); + queue_work(idxd->wq, &idxd->work); + } else if (gensts.reset_type == IDXD_DEVICE_RESET_FLR) { + idxd->state = IDXD_DEV_HALTED; + idxd_mask_error_interrupts(idxd); + dev_dbg(&idxd->pdev->dev, + "idxd halted, doing FLR. After FLR, configs are restored\n"); + INIT_WORK(&idxd->work, idxd_device_flr); + queue_work(idxd->wq, &idxd->work); + + } else { + idxd->state = IDXD_DEV_HALTED; + idxd_wqs_quiesce(idxd); + idxd_wqs_unmap_portal(idxd); + idxd_device_clear_state(idxd); + dev_err(&idxd->pdev->dev, + "idxd halted, need system reset"); + + return -ENXIO; + } + } + + return IRQ_HANDLED; +} + irqreturn_t idxd_misc_thread(int vec, void *data) { struct idxd_irq_entry *irq_entry = data; struct idxd_device *idxd = ie_to_idxd(irq_entry); struct device *dev = &idxd->pdev->dev; - union gensts_reg gensts; u32 val = 0; int i; - bool err = false; u32 cause; cause = ioread32(idxd->reg_base + IDXD_INTCAUSE_OFFSET); @@ -401,7 +451,7 @@ irqreturn_t idxd_misc_thread(int vec, void *data) iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET); if (cause & IDXD_INTC_HALT_STATE) - goto halt; + return idxd_halt(idxd); if (cause & IDXD_INTC_ERR) { spin_lock(&idxd->dev_lock); @@ -435,7 +485,6 @@ irqreturn_t idxd_misc_thread(int vec, void *data) for (i = 0; i < 4; i++) dev_warn_ratelimited(dev, "err[%d]: %#16.16llx\n", i, idxd->sw_err.bits[i]); - err = true; } if (cause & IDXD_INTC_INT_HANDLE_REVOKED) { @@ -480,34 +529,6 @@ irqreturn_t idxd_misc_thread(int vec, void *data) dev_warn_once(dev, "Unexpected interrupt cause bits set: %#x\n", val); - if (!err) - goto out; - -halt: - gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET); - if (gensts.state == IDXD_DEVICE_STATE_HALT) { - idxd->state = IDXD_DEV_HALTED; - if (gensts.reset_type == IDXD_DEVICE_RESET_SOFTWARE) { - /* - * If we need a software reset, we will throw the work - * on a system workqueue in order to allow interrupts - * for the device command completions. - */ - INIT_WORK(&idxd->work, idxd_device_reinit); - queue_work(idxd->wq, &idxd->work); - } else { - idxd->state = IDXD_DEV_HALTED; - idxd_wqs_quiesce(idxd); - idxd_wqs_unmap_portal(idxd); - idxd_device_clear_state(idxd); - dev_err(&idxd->pdev->dev, - "idxd halted, need %s.\n", - gensts.reset_type == IDXD_DEVICE_RESET_FLR ? - "FLR" : "system reset"); - } - } - -out: return IRQ_HANDLED; } diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index c426511f2104..006ba206ab1b 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -9,6 +9,7 @@ #define PCI_DEVICE_ID_INTEL_DSA_GNRD 0x11fb #define PCI_DEVICE_ID_INTEL_DSA_DMR 0x1212 #define PCI_DEVICE_ID_INTEL_IAA_DMR 0x1216 +#define PCI_DEVICE_ID_INTEL_IAA_PTL 0xb02d #define DEVICE_VERSION_1 0x100 #define DEVICE_VERSION_2 0x200 diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index f706eae0e76b..6af493f6ba77 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1979,13 +1979,3 @@ void idxd_unregister_devices(struct idxd_device *idxd) device_unregister(group_confdev(group)); } } - -int idxd_register_bus_type(void) -{ - return bus_register(&dsa_bus_type); -} - -void idxd_unregister_bus_type(void) -{ - bus_unregister(&dsa_bus_type); -} diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c index 17f6b6367113..c9aba2304de7 100644 --- a/drivers/dma/ioat/dca.c +++ b/drivers/dma/ioat/dca.c @@ -10,6 +10,8 @@ #include #include +#include + /* either a kernel change is needed, or we need something like this in kernel */ #ifndef CONFIG_SMP #include @@ -58,11 +60,11 @@ static int dca_enabled_in_bios(struct pci_dev *pdev) { /* CPUID level 9 returns DCA configuration */ /* Bit 0 indicates DCA enabled by the BIOS */ - unsigned long cpuid_level_9; + u32 eax; int res; - cpuid_level_9 = cpuid_eax(9); - res = test_bit(0, &cpuid_level_9); + eax = cpuid_eax(CPUID_LEAF_DCA); + res = eax & BIT(0); if (!res) dev_dbg(&pdev->dev, "DCA is disabled in BIOS\n"); diff --git a/drivers/dma/loongson2-apb-dma.c b/drivers/dma/loongson2-apb-dma.c index 367ed34ce4da..c528f02b9f84 100644 --- a/drivers/dma/loongson2-apb-dma.c +++ b/drivers/dma/loongson2-apb-dma.c @@ -31,7 +31,7 @@ #define LDMA_ASK_VALID BIT(2) #define LDMA_START BIT(3) /* DMA start operation */ #define LDMA_STOP BIT(4) /* DMA stop operation */ -#define LDMA_CONFIG_MASK GENMASK(4, 0) /* DMA controller config bits mask */ +#define LDMA_CONFIG_MASK GENMASK_ULL(4, 0) /* DMA controller config bits mask */ /* Bitfields in ndesc_addr field of HW descriptor */ #define LDMA_DESC_EN BIT(0) /*1: The next descriptor is valid */ diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 43efce77bb57..fa6e4646fdc2 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -1369,10 +1369,9 @@ static int mv_xor_probe(struct platform_device *pdev) return 0; if (pdev->dev.of_node) { - struct device_node *np; int i = 0; - for_each_child_of_node(pdev->dev.of_node, np) { + for_each_child_of_node_scoped(pdev->dev.of_node, np) { struct mv_xor_chan *chan; dma_cap_mask_t cap_mask; int irq; diff --git a/drivers/dma/ptdma/Kconfig b/drivers/dma/ptdma/Kconfig deleted file mode 100644 index b430edd709f9..000000000000 --- a/drivers/dma/ptdma/Kconfig +++ /dev/null @@ -1,13 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -config AMD_PTDMA - tristate "AMD PassThru DMA Engine" - depends on X86_64 && PCI - select DMA_ENGINE - select DMA_VIRTUAL_CHANNELS - help - Enable support for the AMD PTDMA controller. This controller - provides DMA capabilities to perform high bandwidth memory to - memory and IO copy operations. It performs DMA transfer through - queue-based descriptor management. This DMA controller is intended - to be used with AMD Non-Transparent Bridge devices and not for - general purpose peripheral DMA. diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c index bbc3276992bb..c14557efd577 100644 --- a/drivers/dma/qcom/bam_dma.c +++ b/drivers/dma/qcom/bam_dma.c @@ -59,6 +59,9 @@ struct bam_desc_hw { #define DESC_FLAG_NWD BIT(12) #define DESC_FLAG_CMD BIT(11) +#define BAM_NDP_REVISION_START 0x20 +#define BAM_NDP_REVISION_END 0x27 + struct bam_async_desc { struct virt_dma_desc vd; @@ -398,6 +401,7 @@ struct bam_device { /* dma start transaction tasklet */ struct tasklet_struct task; + u32 bam_revision; }; /** @@ -441,8 +445,10 @@ static void bam_reset(struct bam_device *bdev) writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL)); /* set descriptor threshold, start with 4 bytes */ - writel_relaxed(DEFAULT_CNT_THRSHLD, - bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); + if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START, + BAM_NDP_REVISION_END)) + writel_relaxed(DEFAULT_CNT_THRSHLD, + bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); /* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */ writel_relaxed(BAM_CNFG_BITS_DEFAULT, bam_addr(bdev, 0, BAM_CNFG_BITS)); @@ -1000,9 +1006,10 @@ static void bam_apply_new_config(struct bam_chan *bchan, maxburst = bchan->slave.src_maxburst; else maxburst = bchan->slave.dst_maxburst; - - writel_relaxed(maxburst, - bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); + if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START, + BAM_NDP_REVISION_END)) + writel_relaxed(maxburst, + bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); } bchan->reconfigure = 0; @@ -1192,10 +1199,11 @@ static int bam_init(struct bam_device *bdev) u32 val; /* read revision and configuration information */ - if (!bdev->num_ees) { - val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION)); + val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION)); + if (!bdev->num_ees) bdev->num_ees = (val >> NUM_EES_SHIFT) & NUM_EES_MASK; - } + + bdev->bam_revision = val & REVISION_MASK; /* check that configured EE is within range */ if (bdev->ee >= bdev->num_ees) diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c index 52a7c8f2498f..b1f0001cc99c 100644 --- a/drivers/dma/qcom/gpi.c +++ b/drivers/dma/qcom/gpi.c @@ -18,6 +18,7 @@ #include "../virt-dma.h" #define TRE_TYPE_DMA 0x10 +#define TRE_TYPE_IMMEDIATE_DMA 0x11 #define TRE_TYPE_GO 0x20 #define TRE_TYPE_CONFIG0 0x22 @@ -64,6 +65,7 @@ /* DMA TRE */ #define TRE_DMA_LEN GENMASK(23, 0) +#define TRE_DMA_IMMEDIATE_LEN GENMASK(3, 0) /* Register offsets from gpi-top */ #define GPII_n_CH_k_CNTXT_0_OFFS(n, k) (0x20000 + (0x4000 * (n)) + (0x80 * (k))) @@ -1711,6 +1713,7 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc, dma_addr_t address; struct gpi_tre *tre; unsigned int i; + int len; /* first create config tre if applicable */ if (direction == DMA_MEM_TO_DEV && spi->set_config) { @@ -1763,14 +1766,30 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc, tre_idx++; address = sg_dma_address(sgl); - tre->dword[0] = lower_32_bits(address); - tre->dword[1] = upper_32_bits(address); + len = sg_dma_len(sgl); - tre->dword[2] = u32_encode_bits(sg_dma_len(sgl), TRE_DMA_LEN); + /* Support Immediate dma for write transfers for data length up to 8 bytes */ + if (direction == DMA_MEM_TO_DEV && len <= 2 * sizeof(tre->dword[0])) { + /* + * For Immediate dma, data length may not always be length of 8 bytes, + * it can be length less than 8, hence initialize both dword's with 0 + */ + tre->dword[0] = 0; + tre->dword[1] = 0; + memcpy(&tre->dword[0], sg_virt(sgl), len); - tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE); - if (direction == DMA_MEM_TO_DEV) - tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT); + tre->dword[2] = u32_encode_bits(len, TRE_DMA_IMMEDIATE_LEN); + tre->dword[3] = u32_encode_bits(TRE_TYPE_IMMEDIATE_DMA, TRE_FLAGS_TYPE); + } else { + tre->dword[0] = lower_32_bits(address); + tre->dword[1] = upper_32_bits(address); + + tre->dword[2] = u32_encode_bits(len, TRE_DMA_LEN); + tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE); + } + + tre->dword[3] |= u32_encode_bits(direction == DMA_MEM_TO_DEV, + TRE_FLAGS_IEOT); for (i = 0; i < tre_idx; i++) dev_dbg(dev, "TRE:%d %x:%x:%x:%x\n", i, desc->tre[i].dword[0], diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index 2679c1f09faf..0c45ce8c74aa 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -2023,6 +2023,10 @@ static const struct of_device_id rcar_dmac_of_ids[] = { .compatible = "renesas,rcar-gen4-dmac", .data = &rcar_gen4_dmac_data, }, { + /* + * Backward compatibility for between v5.12 - v5.19 + * which didn't combined with "renesas,rcar-gen4-dmac" + */ .compatible = "renesas,dmac-r8a779a0", .data = &rcar_gen4_dmac_data, }, diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c index f37cdf6f2179..24796aaaddfa 100644 --- a/drivers/dma/sun4i-dma.c +++ b/drivers/dma/sun4i-dma.c @@ -13,7 +13,9 @@ #include #include #include +#include #include +#include #include #include @@ -31,12 +33,21 @@ #define SUN4I_DMA_CFG_SRC_ADDR_MODE(mode) ((mode) << 5) #define SUN4I_DMA_CFG_SRC_DRQ_TYPE(type) (type) +#define SUNIV_DMA_CFG_DST_DATA_WIDTH(width) ((width) << 24) +#define SUNIV_DMA_CFG_SRC_DATA_WIDTH(width) ((width) << 8) + +#define SUN4I_MAX_BURST 8 +#define SUNIV_MAX_BURST 4 + /** Normal DMA register values **/ /* Normal DMA source/destination data request type values */ #define SUN4I_NDMA_DRQ_TYPE_SDRAM 0x16 #define SUN4I_NDMA_DRQ_TYPE_LIMIT (0x1F + 1) +#define SUNIV_NDMA_DRQ_TYPE_SDRAM 0x11 +#define SUNIV_NDMA_DRQ_TYPE_LIMIT (0x17 + 1) + /** Normal DMA register layout **/ /* Dedicated DMA source/destination address mode values */ @@ -50,6 +61,9 @@ #define SUN4I_NDMA_CFG_BYTE_COUNT_MODE_REMAIN BIT(15) #define SUN4I_NDMA_CFG_SRC_NON_SECURE BIT(6) +#define SUNIV_NDMA_CFG_CONT_MODE BIT(29) +#define SUNIV_NDMA_CFG_WAIT_STATE(n) ((n) << 26) + /** Dedicated DMA register values **/ /* Dedicated DMA source/destination address mode values */ @@ -62,6 +76,9 @@ #define SUN4I_DDMA_DRQ_TYPE_SDRAM 0x1 #define SUN4I_DDMA_DRQ_TYPE_LIMIT (0x1F + 1) +#define SUNIV_DDMA_DRQ_TYPE_SDRAM 0x1 +#define SUNIV_DDMA_DRQ_TYPE_LIMIT (0x9 + 1) + /** Dedicated DMA register layout **/ /* Dedicated DMA configuration register layout */ @@ -115,6 +132,11 @@ #define SUN4I_DMA_NR_MAX_VCHANS \ (SUN4I_NDMA_NR_MAX_VCHANS + SUN4I_DDMA_NR_MAX_VCHANS) +#define SUNIV_NDMA_NR_MAX_CHANNELS 4 +#define SUNIV_DDMA_NR_MAX_CHANNELS 4 +#define SUNIV_NDMA_NR_MAX_VCHANS (24 * 2 - 1) +#define SUNIV_DDMA_NR_MAX_VCHANS 10 + /* This set of SUN4I_DDMA timing parameters were found experimentally while * working with the SPI driver and seem to make it behave correctly */ #define SUN4I_DDMA_MAGIC_SPI_PARAMETERS \ @@ -132,6 +154,33 @@ #define SUN4I_DDMA_MAX_SEG_SIZE SZ_16M #define SUN4I_DMA_MAX_SEG_SIZE SUN4I_NDMA_MAX_SEG_SIZE +/* + * Hardware channels / ports representation + * + * The hardware is used in several SoCs, with differing numbers + * of channels and endpoints. This structure ties those numbers + * to a certain compatible string. + */ +struct sun4i_dma_config { + u32 ndma_nr_max_channels; + u32 ndma_nr_max_vchans; + + u32 ddma_nr_max_channels; + u32 ddma_nr_max_vchans; + + u32 dma_nr_max_channels; + + void (*set_dst_data_width)(u32 *p_cfg, s8 data_width); + void (*set_src_data_width)(u32 *p_cfg, s8 data_width); + int (*convert_burst)(u32 maxburst); + + u8 ndma_drq_sdram; + u8 ddma_drq_sdram; + + u8 max_burst; + bool has_reset; +}; + struct sun4i_dma_pchan { /* Register base of channel */ void __iomem *base; @@ -170,7 +219,7 @@ struct sun4i_dma_contract { }; struct sun4i_dma_dev { - DECLARE_BITMAP(pchans_used, SUN4I_DMA_NR_MAX_CHANNELS); + unsigned long *pchans_used; struct dma_device slave; struct sun4i_dma_pchan *pchans; struct sun4i_dma_vchan *vchans; @@ -178,6 +227,8 @@ struct sun4i_dma_dev { struct clk *clk; int irq; spinlock_t lock; + const struct sun4i_dma_config *cfg; + struct reset_control *rst; }; static struct sun4i_dma_dev *to_sun4i_dma_dev(struct dma_device *dev) @@ -200,7 +251,27 @@ static struct device *chan2dev(struct dma_chan *chan) return &chan->dev->device; } -static int convert_burst(u32 maxburst) +static void set_dst_data_width_a10(u32 *p_cfg, s8 data_width) +{ + *p_cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(data_width); +} + +static void set_src_data_width_a10(u32 *p_cfg, s8 data_width) +{ + *p_cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(data_width); +} + +static void set_dst_data_width_f1c100s(u32 *p_cfg, s8 data_width) +{ + *p_cfg |= SUNIV_DMA_CFG_DST_DATA_WIDTH(data_width); +} + +static void set_src_data_width_f1c100s(u32 *p_cfg, s8 data_width) +{ + *p_cfg |= SUNIV_DMA_CFG_SRC_DATA_WIDTH(data_width); +} + +static int convert_burst_a10(u32 maxburst) { if (maxburst > 8) return -EINVAL; @@ -209,6 +280,15 @@ static int convert_burst(u32 maxburst) return (maxburst >> 2); } +static int convert_burst_f1c100s(u32 maxburst) +{ + if (maxburst > 4) + return -EINVAL; + + /* 1 -> 0, 4 -> 1 */ + return (maxburst >> 2); +} + static int convert_buswidth(enum dma_slave_buswidth addr_width) { if (addr_width > DMA_SLAVE_BUSWIDTH_4_BYTES) @@ -233,15 +313,15 @@ static struct sun4i_dma_pchan *find_and_use_pchan(struct sun4i_dma_dev *priv, int i, max; /* - * pchans 0-SUN4I_NDMA_NR_MAX_CHANNELS are normal, and - * SUN4I_NDMA_NR_MAX_CHANNELS+ are dedicated ones + * pchans 0-priv->cfg->ndma_nr_max_channels are normal, and + * priv->cfg->ndma_nr_max_channels+ are dedicated ones */ if (vchan->is_dedicated) { - i = SUN4I_NDMA_NR_MAX_CHANNELS; - max = SUN4I_DMA_NR_MAX_CHANNELS; + i = priv->cfg->ndma_nr_max_channels; + max = priv->cfg->dma_nr_max_channels; } else { i = 0; - max = SUN4I_NDMA_NR_MAX_CHANNELS; + max = priv->cfg->ndma_nr_max_channels; } spin_lock_irqsave(&priv->lock, flags); @@ -444,6 +524,7 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, size_t len, struct dma_slave_config *sconfig, enum dma_transfer_direction direction) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_promise *promise; int ret; @@ -467,13 +548,13 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, sconfig->src_addr_width, sconfig->dst_addr_width); /* Source burst */ - ret = convert_burst(sconfig->src_maxburst); + ret = priv->cfg->convert_burst(sconfig->src_maxburst); if (ret < 0) goto fail; promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret); /* Destination burst */ - ret = convert_burst(sconfig->dst_maxburst); + ret = priv->cfg->convert_burst(sconfig->dst_maxburst); if (ret < 0) goto fail; promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret); @@ -482,13 +563,13 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, ret = convert_buswidth(sconfig->src_addr_width); if (ret < 0) goto fail; - promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret); + priv->cfg->set_src_data_width(&promise->cfg, ret); /* Destination bus width */ ret = convert_buswidth(sconfig->dst_addr_width); if (ret < 0) goto fail; - promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret); + priv->cfg->set_dst_data_width(&promise->cfg, ret); return promise; @@ -510,6 +591,7 @@ static struct sun4i_dma_promise * generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, size_t len, struct dma_slave_config *sconfig) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_promise *promise; int ret; @@ -524,13 +606,13 @@ generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, SUN4I_DDMA_CFG_BYTE_COUNT_MODE_REMAIN; /* Source burst */ - ret = convert_burst(sconfig->src_maxburst); + ret = priv->cfg->convert_burst(sconfig->src_maxburst); if (ret < 0) goto fail; promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret); /* Destination burst */ - ret = convert_burst(sconfig->dst_maxburst); + ret = priv->cfg->convert_burst(sconfig->dst_maxburst); if (ret < 0) goto fail; promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret); @@ -539,13 +621,13 @@ generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, ret = convert_buswidth(sconfig->src_addr_width); if (ret < 0) goto fail; - promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret); + priv->cfg->set_src_data_width(&promise->cfg, ret); /* Destination bus width */ ret = convert_buswidth(sconfig->dst_addr_width); if (ret < 0) goto fail; - promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret); + priv->cfg->set_dst_data_width(&promise->cfg, ret); return promise; @@ -622,6 +704,7 @@ static struct dma_async_tx_descriptor * sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, size_t len, unsigned long flags) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan); struct dma_slave_config *sconfig = &vchan->cfg; struct sun4i_dma_promise *promise; @@ -638,8 +721,8 @@ sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, */ sconfig->src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; sconfig->dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - sconfig->src_maxburst = 8; - sconfig->dst_maxburst = 8; + sconfig->src_maxburst = priv->cfg->max_burst; + sconfig->dst_maxburst = priv->cfg->max_burst; if (vchan->is_dedicated) promise = generate_ddma_promise(chan, src, dest, len, sconfig); @@ -654,11 +737,13 @@ sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, /* Configure memcpy mode */ if (vchan->is_dedicated) { - promise->cfg |= SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_DDMA_DRQ_TYPE_SDRAM) | - SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_DDMA_DRQ_TYPE_SDRAM); + promise->cfg |= + SUN4I_DMA_CFG_SRC_DRQ_TYPE(priv->cfg->ddma_drq_sdram) | + SUN4I_DMA_CFG_DST_DRQ_TYPE(priv->cfg->ddma_drq_sdram); } else { - promise->cfg |= SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM) | - SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM); + promise->cfg |= + SUN4I_DMA_CFG_SRC_DRQ_TYPE(priv->cfg->ndma_drq_sdram) | + SUN4I_DMA_CFG_DST_DRQ_TYPE(priv->cfg->ndma_drq_sdram); } /* Fill the contract with our only promise */ @@ -673,6 +758,7 @@ sun4i_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf, size_t len, size_t period_len, enum dma_transfer_direction dir, unsigned long flags) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan); struct dma_slave_config *sconfig = &vchan->cfg; struct sun4i_dma_promise *promise; @@ -696,11 +782,11 @@ sun4i_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf, size_t len, if (vchan->is_dedicated) { io_mode = SUN4I_DDMA_ADDR_MODE_IO; linear_mode = SUN4I_DDMA_ADDR_MODE_LINEAR; - ram_type = SUN4I_DDMA_DRQ_TYPE_SDRAM; + ram_type = priv->cfg->ddma_drq_sdram; } else { io_mode = SUN4I_NDMA_ADDR_MODE_IO; linear_mode = SUN4I_NDMA_ADDR_MODE_LINEAR; - ram_type = SUN4I_NDMA_DRQ_TYPE_SDRAM; + ram_type = priv->cfg->ndma_drq_sdram; } if (dir == DMA_MEM_TO_DEV) { @@ -793,6 +879,7 @@ sun4i_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_transfer_direction dir, unsigned long flags, void *context) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan); struct dma_slave_config *sconfig = &vchan->cfg; struct sun4i_dma_promise *promise; @@ -818,11 +905,11 @@ sun4i_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, if (vchan->is_dedicated) { io_mode = SUN4I_DDMA_ADDR_MODE_IO; linear_mode = SUN4I_DDMA_ADDR_MODE_LINEAR; - ram_type = SUN4I_DDMA_DRQ_TYPE_SDRAM; + ram_type = priv->cfg->ddma_drq_sdram; } else { io_mode = SUN4I_NDMA_ADDR_MODE_IO; linear_mode = SUN4I_NDMA_ADDR_MODE_LINEAR; - ram_type = SUN4I_NDMA_DRQ_TYPE_SDRAM; + ram_type = priv->cfg->ndma_drq_sdram; } if (dir == DMA_MEM_TO_DEV) @@ -1150,6 +1237,10 @@ static int sun4i_dma_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; + priv->cfg = of_device_get_match_data(&pdev->dev); + if (!priv->cfg) + return -ENODEV; + priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) return PTR_ERR(priv->base); @@ -1164,6 +1255,13 @@ static int sun4i_dma_probe(struct platform_device *pdev) return PTR_ERR(priv->clk); } + if (priv->cfg->has_reset) { + priv->rst = devm_reset_control_get_exclusive_deasserted(&pdev->dev, NULL); + if (IS_ERR(priv->rst)) + return dev_err_probe(&pdev->dev, PTR_ERR(priv->rst), + "Failed to get reset control\n"); + } + platform_set_drvdata(pdev, priv); spin_lock_init(&priv->lock); @@ -1197,23 +1295,26 @@ static int sun4i_dma_probe(struct platform_device *pdev) priv->slave.dev = &pdev->dev; - priv->pchans = devm_kcalloc(&pdev->dev, SUN4I_DMA_NR_MAX_CHANNELS, + priv->pchans = devm_kcalloc(&pdev->dev, priv->cfg->dma_nr_max_channels, sizeof(struct sun4i_dma_pchan), GFP_KERNEL); priv->vchans = devm_kcalloc(&pdev->dev, SUN4I_DMA_NR_MAX_VCHANS, sizeof(struct sun4i_dma_vchan), GFP_KERNEL); - if (!priv->vchans || !priv->pchans) + priv->pchans_used = devm_kcalloc(&pdev->dev, + BITS_TO_LONGS(priv->cfg->dma_nr_max_channels), + sizeof(unsigned long), GFP_KERNEL); + if (!priv->vchans || !priv->pchans || !priv->pchans_used) return -ENOMEM; /* - * [0..SUN4I_NDMA_NR_MAX_CHANNELS) are normal pchans, and - * [SUN4I_NDMA_NR_MAX_CHANNELS..SUN4I_DMA_NR_MAX_CHANNELS) are + * [0..priv->cfg->ndma_nr_max_channels) are normal pchans, and + * [priv->cfg->ndma_nr_max_channels..priv->cfg->dma_nr_max_channels) are * dedicated ones */ - for (i = 0; i < SUN4I_NDMA_NR_MAX_CHANNELS; i++) + for (i = 0; i < priv->cfg->ndma_nr_max_channels; i++) priv->pchans[i].base = priv->base + SUN4I_NDMA_CHANNEL_REG_BASE(i); - for (j = 0; i < SUN4I_DMA_NR_MAX_CHANNELS; i++, j++) { + for (j = 0; i < priv->cfg->dma_nr_max_channels; i++, j++) { priv->pchans[i].base = priv->base + SUN4I_DDMA_CHANNEL_REG_BASE(j); priv->pchans[i].is_dedicated = 1; @@ -1284,8 +1385,51 @@ static void sun4i_dma_remove(struct platform_device *pdev) clk_disable_unprepare(priv->clk); } +static struct sun4i_dma_config sun4i_a10_dma_cfg = { + .ndma_nr_max_channels = SUN4I_NDMA_NR_MAX_CHANNELS, + .ndma_nr_max_vchans = SUN4I_NDMA_NR_MAX_VCHANS, + + .ddma_nr_max_channels = SUN4I_DDMA_NR_MAX_CHANNELS, + .ddma_nr_max_vchans = SUN4I_DDMA_NR_MAX_VCHANS, + + .dma_nr_max_channels = SUN4I_DMA_NR_MAX_CHANNELS, + + .set_dst_data_width = set_dst_data_width_a10, + .set_src_data_width = set_src_data_width_a10, + .convert_burst = convert_burst_a10, + + .ndma_drq_sdram = SUN4I_NDMA_DRQ_TYPE_SDRAM, + .ddma_drq_sdram = SUN4I_DDMA_DRQ_TYPE_SDRAM, + + .max_burst = SUN4I_MAX_BURST, + .has_reset = false, +}; + +static struct sun4i_dma_config suniv_f1c100s_dma_cfg = { + .ndma_nr_max_channels = SUNIV_NDMA_NR_MAX_CHANNELS, + .ndma_nr_max_vchans = SUNIV_NDMA_NR_MAX_VCHANS, + + .ddma_nr_max_channels = SUNIV_DDMA_NR_MAX_CHANNELS, + .ddma_nr_max_vchans = SUNIV_DDMA_NR_MAX_VCHANS, + + .dma_nr_max_channels = SUNIV_NDMA_NR_MAX_CHANNELS + + SUNIV_DDMA_NR_MAX_CHANNELS, + + .set_dst_data_width = set_dst_data_width_f1c100s, + .set_src_data_width = set_src_data_width_f1c100s, + .convert_burst = convert_burst_f1c100s, + + .ndma_drq_sdram = SUNIV_NDMA_DRQ_TYPE_SDRAM, + .ddma_drq_sdram = SUNIV_DDMA_DRQ_TYPE_SDRAM, + + .max_burst = SUNIV_MAX_BURST, + .has_reset = true, +}; + static const struct of_device_id sun4i_dma_match[] = { - { .compatible = "allwinner,sun4i-a10-dma" }, + { .compatible = "allwinner,sun4i-a10-dma", .data = &sun4i_a10_dma_cfg }, + { .compatible = "allwinner,suniv-f1c100s-dma", + .data = &suniv_f1c100s_dma_cfg }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, sun4i_dma_match); diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index cacf3757adc2..4d6fe0efa76e 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -231,6 +231,7 @@ struct tegra_dma_channel { bool config_init; char name[30]; enum dma_transfer_direction sid_dir; + enum dma_status status; int id; int irq; int slave_id; @@ -393,6 +394,8 @@ static int tegra_dma_pause(struct tegra_dma_channel *tdc) tegra_dma_dump_chan_regs(tdc); } + tdc->status = DMA_PAUSED; + return ret; } @@ -419,6 +422,8 @@ static void tegra_dma_resume(struct tegra_dma_channel *tdc) val = tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSRE); val &= ~TEGRA_GPCDMA_CHAN_CSRE_PAUSE; tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSRE, val); + + tdc->status = DMA_IN_PROGRESS; } static int tegra_dma_device_resume(struct dma_chan *dc) @@ -544,6 +549,7 @@ static void tegra_dma_xfer_complete(struct tegra_dma_channel *tdc) tegra_dma_sid_free(tdc); tdc->dma_desc = NULL; + tdc->status = DMA_COMPLETE; } static void tegra_dma_chan_decode_error(struct tegra_dma_channel *tdc, @@ -716,6 +722,7 @@ static int tegra_dma_terminate_all(struct dma_chan *dc) tdc->dma_desc = NULL; } + tdc->status = DMA_COMPLETE; tegra_dma_sid_free(tdc); vchan_get_all_descriptors(&tdc->vc, &head); spin_unlock_irqrestore(&tdc->vc.lock, flags); @@ -769,6 +776,9 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc, if (ret == DMA_COMPLETE) return ret; + if (tdc->status == DMA_PAUSED) + ret = DMA_PAUSED; + spin_lock_irqsave(&tdc->vc.lock, flags); vd = vchan_find_desc(&tdc->vc, cookie); if (vd) { diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index 2953008d42ef..6896da8ac7ef 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -43,6 +43,10 @@ #define ADMA_CH_CONFIG_MAX_BUFS 8 #define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs) (reqs << 4) +#define TEGRA186_ADMA_GLOBAL_PAGE_CHGRP 0x30 +#define TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ 0x70 +#define TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ 0x84 + #define ADMA_CH_FIFO_CTRL 0x2c #define ADMA_CH_TX_FIFO_SIZE_SHIFT 8 #define ADMA_CH_RX_FIFO_SIZE_SHIFT 0 @@ -96,6 +100,7 @@ struct tegra_adma_chip_data { unsigned int ch_fifo_size_mask; unsigned int sreq_index_offset; bool has_outstanding_reqs; + void (*set_global_pg_config)(struct tegra_adma *tdma); }; /* @@ -151,6 +156,7 @@ struct tegra_adma { struct dma_device dma_dev; struct device *dev; void __iomem *base_addr; + void __iomem *ch_base_addr; struct clk *ahub_clk; unsigned int nr_channels; unsigned long *dma_chan_mask; @@ -159,6 +165,7 @@ struct tegra_adma { /* Used to store global command register state when suspending */ unsigned int global_cmd; + unsigned int ch_page_no; const struct tegra_adma_chip_data *cdata; @@ -176,6 +183,11 @@ static inline u32 tdma_read(struct tegra_adma *tdma, u32 reg) return readl(tdma->base_addr + tdma->cdata->global_reg_offset + reg); } +static inline void tdma_ch_global_write(struct tegra_adma *tdma, u32 reg, u32 val) +{ + writel(val, tdma->ch_base_addr + tdma->cdata->global_reg_offset + reg); +} + static inline void tdma_ch_write(struct tegra_adma_chan *tdc, u32 reg, u32 val) { writel(val, tdc->chan_addr + reg); @@ -217,13 +229,30 @@ static int tegra_adma_slave_config(struct dma_chan *dc, return 0; } +static void tegra186_adma_global_page_config(struct tegra_adma *tdma) +{ + /* + * Clear the default page1 channel group configs and program + * the global registers based on the actual page usage + */ + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_CHGRP, 0); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ, 0); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ, 0); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_CHGRP + (tdma->ch_page_no * 0x4), 0xff); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ + (tdma->ch_page_no * 0x4), 0x1ffffff); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ + (tdma->ch_page_no * 0x4), 0xffffff); +} + static int tegra_adma_init(struct tegra_adma *tdma) { u32 status; int ret; - /* Clear any interrupts */ - tdma_write(tdma, tdma->cdata->ch_base_offset + tdma->cdata->global_int_clear, 0x1); + /* Clear any channels group global interrupts */ + tdma_ch_global_write(tdma, tdma->cdata->global_int_clear, 0x1); + + if (!tdma->base_addr) + return 0; /* Assert soft reset */ tdma_write(tdma, ADMA_GLOBAL_SOFT_RESET, 0x1); @@ -237,6 +266,9 @@ static int tegra_adma_init(struct tegra_adma *tdma) if (ret) return ret; + if (tdma->cdata->set_global_pg_config) + tdma->cdata->set_global_pg_config(tdma); + /* Enable global ADMA registers */ tdma_write(tdma, ADMA_GLOBAL_CMD, 1); @@ -736,7 +768,9 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev) struct tegra_adma_chan *tdc; int i; - tdma->global_cmd = tdma_read(tdma, ADMA_GLOBAL_CMD); + if (tdma->base_addr) + tdma->global_cmd = tdma_read(tdma, ADMA_GLOBAL_CMD); + if (!tdma->global_cmd) goto clk_disable; @@ -777,7 +811,11 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev) dev_err(dev, "ahub clk_enable failed: %d\n", ret); return ret; } - tdma_write(tdma, ADMA_GLOBAL_CMD, tdma->global_cmd); + if (tdma->base_addr) { + tdma_write(tdma, ADMA_GLOBAL_CMD, tdma->global_cmd); + if (tdma->cdata->set_global_pg_config) + tdma->cdata->set_global_pg_config(tdma); + } if (!tdma->global_cmd) return 0; @@ -817,6 +855,7 @@ static const struct tegra_adma_chip_data tegra210_chip_data = { .ch_fifo_size_mask = 0xf, .sreq_index_offset = 2, .has_outstanding_reqs = false, + .set_global_pg_config = NULL, }; static const struct tegra_adma_chip_data tegra186_chip_data = { @@ -833,6 +872,7 @@ static const struct tegra_adma_chip_data tegra186_chip_data = { .ch_fifo_size_mask = 0x1f, .sreq_index_offset = 4, .has_outstanding_reqs = true, + .set_global_pg_config = tegra186_adma_global_page_config, }; static const struct of_device_id tegra_adma_of_match[] = { @@ -846,7 +886,8 @@ static int tegra_adma_probe(struct platform_device *pdev) { const struct tegra_adma_chip_data *cdata; struct tegra_adma *tdma; - int ret, i; + struct resource *res_page, *res_base; + int ret, i, page_no; cdata = of_device_get_match_data(&pdev->dev); if (!cdata) { @@ -865,9 +906,35 @@ static int tegra_adma_probe(struct platform_device *pdev) tdma->nr_channels = cdata->nr_channels; platform_set_drvdata(pdev, tdma); - tdma->base_addr = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(tdma->base_addr)) - return PTR_ERR(tdma->base_addr); + res_page = platform_get_resource_byname(pdev, IORESOURCE_MEM, "page"); + if (res_page) { + tdma->ch_base_addr = devm_ioremap_resource(&pdev->dev, res_page); + if (IS_ERR(tdma->ch_base_addr)) + return PTR_ERR(tdma->ch_base_addr); + + res_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "global"); + if (res_base) { + page_no = (res_page->start - res_base->start) / cdata->ch_base_offset; + if (page_no <= 0) + return -EINVAL; + tdma->ch_page_no = page_no - 1; + tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base); + if (IS_ERR(tdma->base_addr)) + return PTR_ERR(tdma->base_addr); + } + } else { + /* If no 'page' property found, then reg DT binding would be legacy */ + res_base = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (res_base) { + tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base); + if (IS_ERR(tdma->base_addr)) + return PTR_ERR(tdma->base_addr); + } else { + return -ENODEV; + } + + tdma->ch_base_addr = tdma->base_addr + cdata->ch_base_offset; + } tdma->ahub_clk = devm_clk_get(&pdev->dev, "d_audio"); if (IS_ERR(tdma->ahub_clk)) { @@ -900,8 +967,7 @@ static int tegra_adma_probe(struct platform_device *pdev) if (!test_bit(i, tdma->dma_chan_mask)) continue; - tdc->chan_addr = tdma->base_addr + cdata->ch_base_offset - + (cdata->ch_reg_size * i); + tdc->chan_addr = tdma->ch_base_addr + (cdata->ch_reg_size * i); tdc->irq = of_irq_get(pdev->dev.of_node, i); if (tdc->irq <= 0) { diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index 343e986e66e7..4ece125b2ae7 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -208,7 +208,6 @@ struct edma_desc { struct edma_cc; struct edma_tc { - struct device_node *node; u16 id; }; @@ -2460,19 +2459,19 @@ static int edma_probe(struct platform_device *pdev) goto err_reg1; } - for (i = 0;; i++) { + for (i = 0; i < ecc->num_tc; i++) { ret = of_parse_phandle_with_fixed_args(node, "ti,tptcs", 1, i, &tc_args); - if (ret || i == ecc->num_tc) + if (ret) break; - ecc->tc_list[i].node = tc_args.np; ecc->tc_list[i].id = i; queue_priority_mapping[i][1] = tc_args.args[0]; if (queue_priority_mapping[i][1] > lowest_priority) { lowest_priority = queue_priority_mapping[i][1]; info->default_queue = i; } + of_node_put(tc_args.np); } /* See if we have optional dma-channel-mask array */ diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index b3f27b3f9209..7ed1956b4642 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -4404,6 +4404,18 @@ static struct udma_match_data j721s2_bcdma_csi_data = { .soc_data = &j721s2_bcdma_csi_soc_data, }; +static struct udma_match_data j722s_bcdma_csi_data = { + .type = DMA_TYPE_BCDMA, + .psil_base = 0x3100, + .enable_memcpy_support = false, + .burst_size = { + TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */ + 0, /* No H Channels */ + 0, /* No UH Channels */ + }, + .soc_data = &j721s2_bcdma_csi_soc_data, +}; + static const struct of_device_id udma_of_match[] = { { .compatible = "ti,am654-navss-main-udmap", @@ -4435,6 +4447,10 @@ static const struct of_device_id udma_of_match[] = { .compatible = "ti,j721s2-dmss-bcdma-csi", .data = &j721s2_bcdma_csi_data, }, + { + .compatible = "ti,j722s-dmss-bcdma-csi", + .data = &j722s_bcdma_csi_data, + }, { /* Sentinel */ }, }; MODULE_DEVICE_TABLE(of, udma_of_match); diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 93772abc3b49..0d88b1a670e1 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -390,15 +390,11 @@ static int xdma_xfer_start(struct xdma_chan *xchan) */ static int xdma_xfer_stop(struct xdma_chan *xchan) { - int ret; struct xdma_device *xdev = xchan->xdev_hdl; /* clear run stop bit to prevent any further auto-triggering */ - ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C, - CHAN_CTRL_RUN_STOP); - if (ret) - return ret; - return ret; + return regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C, + CHAN_CTRL_RUN_STOP); } /** diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 1bdd57de87a6..108a7287f4cd 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -1404,16 +1404,18 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan) dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg); - j = chan->desc_submitcount; - reg = dma_read(chan, XILINX_DMA_REG_PARK_PTR); - if (chan->direction == DMA_MEM_TO_DEV) { - reg &= ~XILINX_DMA_PARK_PTR_RD_REF_MASK; - reg |= j << XILINX_DMA_PARK_PTR_RD_REF_SHIFT; - } else { - reg &= ~XILINX_DMA_PARK_PTR_WR_REF_MASK; - reg |= j << XILINX_DMA_PARK_PTR_WR_REF_SHIFT; + if (config->park) { + j = chan->desc_submitcount; + reg = dma_read(chan, XILINX_DMA_REG_PARK_PTR); + if (chan->direction == DMA_MEM_TO_DEV) { + reg &= ~XILINX_DMA_PARK_PTR_RD_REF_MASK; + reg |= j << XILINX_DMA_PARK_PTR_RD_REF_SHIFT; + } else { + reg &= ~XILINX_DMA_PARK_PTR_WR_REF_MASK; + reg |= j << XILINX_DMA_PARK_PTR_WR_REF_SHIFT; + } + dma_write(chan, XILINX_DMA_REG_PARK_PTR, reg); } - dma_write(chan, XILINX_DMA_REG_PARK_PTR, reg); /* Start the hardware */ xilinx_dma_start(chan); diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 06f7b43a6f78..2051a7c944a5 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -78,6 +78,7 @@ config EDAC_GHES config EDAC_AMD64 tristate "AMD64 (Opteron, Athlon64)" depends on AMD_NB && EDAC_DECODE_MCE + depends on AMD_NODE imply AMD_ATL help Support for error detection and correction of DRAM ECC errors on @@ -303,14 +304,6 @@ config EDAC_PASEMI Support for error detection and correction on PA Semi PWRficient. -config EDAC_CELL - tristate "Cell Broadband Engine memory controller" - depends on PPC_CELL_COMMON - help - Support for error detection and correction on the - Cell Broadband Engine internal memory controller - on platform without a hypervisor - config EDAC_CPC925 tristate "IBM CPC925 Memory Controller (PPC970FX)" depends on PPC64 @@ -546,5 +539,13 @@ config EDAC_VERSAL Support injecting both correctable and uncorrectable errors for debugging purposes. +config EDAC_LOONGSON + tristate "Loongson Memory Controller" + depends on LOONGARCH && ACPI + help + Support for error detection and correction on the Loongson + family memory controller. This driver reports single bit + errors (CE) only. Loongson-3A5000/3C5000/3D5000/3A6000/3C6000 + are compatible. endif # EDAC diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index f9cf19d8d13d..89789ba8275f 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -62,8 +62,6 @@ obj-$(CONFIG_EDAC_SKX) += skx_edac.o skx_edac_common.o i10nm_edac-y := i10nm_base.o obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o skx_edac_common.o -obj-$(CONFIG_EDAC_CELL) += cell_edac.o - obj-$(CONFIG_EDAC_HIGHBANK_MC) += highbank_mc_edac.o obj-$(CONFIG_EDAC_HIGHBANK_L2) += highbank_l2_edac.o @@ -86,3 +84,4 @@ obj-$(CONFIG_EDAC_DMC520) += dmc520_edac.o obj-$(CONFIG_EDAC_NPCM) += npcm_edac.o obj-$(CONFIG_EDAC_ZYNQMP) += zynqmp_edac.o obj-$(CONFIG_EDAC_VERSAL) += versal_edac.o +obj-$(CONFIG_EDAC_LOONGSON) += loongson_edac.o diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 5d356b7c4589..8414ceb43e4a 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -2,6 +2,7 @@ #include #include "amd64_edac.h" #include +#include static struct edac_pci_ctl_info *pci_ctl; diff --git a/drivers/edac/cell_edac.c b/drivers/edac/cell_edac.c deleted file mode 100644 index c2420e2287ff..000000000000 --- a/drivers/edac/cell_edac.c +++ /dev/null @@ -1,281 +0,0 @@ -/* - * Cell MIC driver for ECC counting - * - * Copyright 2007 Benjamin Herrenschmidt, IBM Corp. - * - * - * This file may be distributed under the terms of the - * GNU General Public License. - */ -#undef DEBUG - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "edac_module.h" - -struct cell_edac_priv -{ - struct cbe_mic_tm_regs __iomem *regs; - int node; - int chanmask; -#ifdef DEBUG - u64 prev_fir; -#endif -}; - -static void cell_edac_count_ce(struct mem_ctl_info *mci, int chan, u64 ar) -{ - struct cell_edac_priv *priv = mci->pvt_info; - struct csrow_info *csrow = mci->csrows[0]; - unsigned long address, pfn, offset, syndrome; - - dev_dbg(mci->pdev, "ECC CE err on node %d, channel %d, ar = 0x%016llx\n", - priv->node, chan, ar); - - /* Address decoding is likely a bit bogus, to dbl check */ - address = (ar & 0xffffffffe0000000ul) >> 29; - if (priv->chanmask == 0x3) - address = (address << 1) | chan; - pfn = address >> PAGE_SHIFT; - offset = address & ~PAGE_MASK; - syndrome = (ar & 0x000000001fe00000ul) >> 21; - - /* TODO: Decoding of the error address */ - edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, - csrow->first_page + pfn, offset, syndrome, - 0, chan, -1, "", ""); -} - -static void cell_edac_count_ue(struct mem_ctl_info *mci, int chan, u64 ar) -{ - struct cell_edac_priv *priv = mci->pvt_info; - struct csrow_info *csrow = mci->csrows[0]; - unsigned long address, pfn, offset; - - dev_dbg(mci->pdev, "ECC UE err on node %d, channel %d, ar = 0x%016llx\n", - priv->node, chan, ar); - - /* Address decoding is likely a bit bogus, to dbl check */ - address = (ar & 0xffffffffe0000000ul) >> 29; - if (priv->chanmask == 0x3) - address = (address << 1) | chan; - pfn = address >> PAGE_SHIFT; - offset = address & ~PAGE_MASK; - - /* TODO: Decoding of the error address */ - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, - csrow->first_page + pfn, offset, 0, - 0, chan, -1, "", ""); -} - -static void cell_edac_check(struct mem_ctl_info *mci) -{ - struct cell_edac_priv *priv = mci->pvt_info; - u64 fir, addreg, clear = 0; - - fir = in_be64(&priv->regs->mic_fir); -#ifdef DEBUG - if (fir != priv->prev_fir) { - dev_dbg(mci->pdev, "fir change : 0x%016lx\n", fir); - priv->prev_fir = fir; - } -#endif - if ((priv->chanmask & 0x1) && (fir & CBE_MIC_FIR_ECC_SINGLE_0_ERR)) { - addreg = in_be64(&priv->regs->mic_df_ecc_address_0); - clear |= CBE_MIC_FIR_ECC_SINGLE_0_RESET; - cell_edac_count_ce(mci, 0, addreg); - } - if ((priv->chanmask & 0x2) && (fir & CBE_MIC_FIR_ECC_SINGLE_1_ERR)) { - addreg = in_be64(&priv->regs->mic_df_ecc_address_1); - clear |= CBE_MIC_FIR_ECC_SINGLE_1_RESET; - cell_edac_count_ce(mci, 1, addreg); - } - if ((priv->chanmask & 0x1) && (fir & CBE_MIC_FIR_ECC_MULTI_0_ERR)) { - addreg = in_be64(&priv->regs->mic_df_ecc_address_0); - clear |= CBE_MIC_FIR_ECC_MULTI_0_RESET; - cell_edac_count_ue(mci, 0, addreg); - } - if ((priv->chanmask & 0x2) && (fir & CBE_MIC_FIR_ECC_MULTI_1_ERR)) { - addreg = in_be64(&priv->regs->mic_df_ecc_address_1); - clear |= CBE_MIC_FIR_ECC_MULTI_1_RESET; - cell_edac_count_ue(mci, 1, addreg); - } - - /* The procedure for clearing FIR bits is a bit ... weird */ - if (clear) { - fir &= ~(CBE_MIC_FIR_ECC_ERR_MASK | CBE_MIC_FIR_ECC_SET_MASK); - fir |= CBE_MIC_FIR_ECC_RESET_MASK; - fir &= ~clear; - out_be64(&priv->regs->mic_fir, fir); - (void)in_be64(&priv->regs->mic_fir); - - mb(); /* sync up */ -#ifdef DEBUG - fir = in_be64(&priv->regs->mic_fir); - dev_dbg(mci->pdev, "fir clear : 0x%016lx\n", fir); -#endif - } -} - -static void cell_edac_init_csrows(struct mem_ctl_info *mci) -{ - struct csrow_info *csrow = mci->csrows[0]; - struct dimm_info *dimm; - struct cell_edac_priv *priv = mci->pvt_info; - struct device_node *np; - int j; - u32 nr_pages; - - for_each_node_by_name(np, "memory") { - struct resource r; - - /* We "know" that the Cell firmware only creates one entry - * in the "memory" nodes. If that changes, this code will - * need to be adapted. - */ - if (of_address_to_resource(np, 0, &r)) - continue; - if (of_node_to_nid(np) != priv->node) - continue; - csrow->first_page = r.start >> PAGE_SHIFT; - nr_pages = resource_size(&r) >> PAGE_SHIFT; - csrow->last_page = csrow->first_page + nr_pages - 1; - - for (j = 0; j < csrow->nr_channels; j++) { - dimm = csrow->channels[j]->dimm; - dimm->mtype = MEM_XDR; - dimm->edac_mode = EDAC_SECDED; - dimm->nr_pages = nr_pages / csrow->nr_channels; - } - dev_dbg(mci->pdev, - "Initialized on node %d, chanmask=0x%x," - " first_page=0x%lx, nr_pages=0x%x\n", - priv->node, priv->chanmask, - csrow->first_page, nr_pages); - break; - } - of_node_put(np); -} - -static int cell_edac_probe(struct platform_device *pdev) -{ - struct cbe_mic_tm_regs __iomem *regs; - struct mem_ctl_info *mci; - struct edac_mc_layer layers[2]; - struct cell_edac_priv *priv; - u64 reg; - int rc, chanmask, num_chans; - - regs = cbe_get_cpu_mic_tm_regs(cbe_node_to_cpu(pdev->id)); - if (regs == NULL) - return -ENODEV; - - edac_op_state = EDAC_OPSTATE_POLL; - - /* Get channel population */ - reg = in_be64(®s->mic_mnt_cfg); - dev_dbg(&pdev->dev, "MIC_MNT_CFG = 0x%016llx\n", reg); - chanmask = 0; - if (reg & CBE_MIC_MNT_CFG_CHAN_0_POP) - chanmask |= 0x1; - if (reg & CBE_MIC_MNT_CFG_CHAN_1_POP) - chanmask |= 0x2; - if (chanmask == 0) { - dev_warn(&pdev->dev, - "Yuck ! No channel populated ? Aborting !\n"); - return -ENODEV; - } - dev_dbg(&pdev->dev, "Initial FIR = 0x%016llx\n", - in_be64(®s->mic_fir)); - - /* Allocate & init EDAC MC data structure */ - num_chans = chanmask == 3 ? 2 : 1; - - layers[0].type = EDAC_MC_LAYER_CHIP_SELECT; - layers[0].size = 1; - layers[0].is_virt_csrow = true; - layers[1].type = EDAC_MC_LAYER_CHANNEL; - layers[1].size = num_chans; - layers[1].is_virt_csrow = false; - mci = edac_mc_alloc(pdev->id, ARRAY_SIZE(layers), layers, - sizeof(struct cell_edac_priv)); - if (mci == NULL) - return -ENOMEM; - priv = mci->pvt_info; - priv->regs = regs; - priv->node = pdev->id; - priv->chanmask = chanmask; - mci->pdev = &pdev->dev; - mci->mtype_cap = MEM_FLAG_XDR; - mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_EC | EDAC_FLAG_SECDED; - mci->edac_cap = EDAC_FLAG_EC | EDAC_FLAG_SECDED; - mci->mod_name = "cell_edac"; - mci->ctl_name = "MIC"; - mci->dev_name = dev_name(&pdev->dev); - mci->edac_check = cell_edac_check; - cell_edac_init_csrows(mci); - - /* Register with EDAC core */ - rc = edac_mc_add_mc(mci); - if (rc) { - dev_err(&pdev->dev, "failed to register with EDAC core\n"); - edac_mc_free(mci); - return rc; - } - - return 0; -} - -static void cell_edac_remove(struct platform_device *pdev) -{ - struct mem_ctl_info *mci = edac_mc_del_mc(&pdev->dev); - if (mci) - edac_mc_free(mci); -} - -static struct platform_driver cell_edac_driver = { - .driver = { - .name = "cbe-mic", - }, - .probe = cell_edac_probe, - .remove = cell_edac_remove, -}; - -static int __init cell_edac_init(void) -{ - /* Sanity check registers data structure */ - BUILD_BUG_ON(offsetof(struct cbe_mic_tm_regs, - mic_df_ecc_address_0) != 0xf8); - BUILD_BUG_ON(offsetof(struct cbe_mic_tm_regs, - mic_df_ecc_address_1) != 0x1b8); - BUILD_BUG_ON(offsetof(struct cbe_mic_tm_regs, - mic_df_config) != 0x218); - BUILD_BUG_ON(offsetof(struct cbe_mic_tm_regs, - mic_fir) != 0x230); - BUILD_BUG_ON(offsetof(struct cbe_mic_tm_regs, - mic_mnt_cfg) != 0x210); - BUILD_BUG_ON(offsetof(struct cbe_mic_tm_regs, - mic_exc) != 0x208); - - return platform_driver_register(&cell_edac_driver); -} - -static void __exit cell_edac_exit(void) -{ - platform_driver_unregister(&cell_edac_driver); -} - -module_init(cell_edac_init); -module_exit(cell_edac_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Benjamin Herrenschmidt "); -MODULE_DESCRIPTION("ECC counting for Cell MIC"); diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index d6eed727b0cd..0959320fe51c 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -214,7 +214,7 @@ static int edac_mc_alloc_csrows(struct mem_ctl_info *mci) unsigned int row, chn; /* - * Alocate and fill the csrow/channels structs + * Allocate and fill the csrow/channels structs */ mci->csrows = kcalloc(tot_csrows, sizeof(*mci->csrows), GFP_KERNEL); if (!mci->csrows) diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 4200aec04831..0f338adf7d93 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -422,7 +422,7 @@ static inline int nr_pages_per_csrow(struct csrow_info *csrow) return nr_pages; } -/* Create a CSROW object under specifed edac_mc_device */ +/* Create a CSROW object under specified edac_mc_device */ static int edac_create_csrow_object(struct mem_ctl_info *mci, struct csrow_info *csrow, int index) { @@ -449,7 +449,7 @@ static int edac_create_csrow_object(struct mem_ctl_info *mci, return 0; } -/* Create a CSROW object under specifed edac_mc_device */ +/* Create a CSROW object under specified edac_mc_device */ static int edac_create_csrow_objects(struct mem_ctl_info *mci) { int err, i; @@ -636,7 +636,7 @@ static void dimm_release(struct device *dev) */ } -/* Create a DIMM object under specifed memory controller device */ +/* Create a DIMM object under specified memory controller device */ static int edac_create_dimm_object(struct mem_ctl_info *mci, struct dimm_info *dimm) { diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c index 51556c72a967..f45d849d3f15 100644 --- a/drivers/edac/i10nm_base.c +++ b/drivers/edac/i10nm_base.c @@ -938,16 +938,18 @@ static struct res_config gnr_cfg = { }; static const struct x86_cpu_id i10nm_cpuids[] = { - X86_MATCH_VFM_STEPPINGS(INTEL_ATOM_TREMONT_D, X86_STEPPINGS(0x0, 0x3), &i10nm_cfg0), - X86_MATCH_VFM_STEPPINGS(INTEL_ATOM_TREMONT_D, X86_STEPPINGS(0x4, 0xf), &i10nm_cfg1), - X86_MATCH_VFM_STEPPINGS(INTEL_ICELAKE_X, X86_STEPPINGS(0x0, 0x3), &i10nm_cfg0), - X86_MATCH_VFM_STEPPINGS(INTEL_ICELAKE_X, X86_STEPPINGS(0x4, 0xf), &i10nm_cfg1), - X86_MATCH_VFM_STEPPINGS(INTEL_ICELAKE_D, X86_STEPPINGS(0x0, 0xf), &i10nm_cfg1), - X86_MATCH_VFM_STEPPINGS(INTEL_SAPPHIRERAPIDS_X, X86_STEPPINGS(0x0, 0xf), &spr_cfg), - X86_MATCH_VFM_STEPPINGS(INTEL_EMERALDRAPIDS_X, X86_STEPPINGS(0x0, 0xf), &spr_cfg), - X86_MATCH_VFM_STEPPINGS(INTEL_GRANITERAPIDS_X, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), - X86_MATCH_VFM_STEPPINGS(INTEL_ATOM_CRESTMONT_X, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), - X86_MATCH_VFM_STEPPINGS(INTEL_ATOM_CRESTMONT, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), + X86_MATCH_VFM_STEPS(INTEL_ATOM_TREMONT_D, X86_STEP_MIN, 0x3, &i10nm_cfg0), + X86_MATCH_VFM_STEPS(INTEL_ATOM_TREMONT_D, 0x4, X86_STEP_MAX, &i10nm_cfg1), + X86_MATCH_VFM_STEPS(INTEL_ICELAKE_X, X86_STEP_MIN, 0x3, &i10nm_cfg0), + X86_MATCH_VFM_STEPS(INTEL_ICELAKE_X, 0x4, X86_STEP_MAX, &i10nm_cfg1), + X86_MATCH_VFM( INTEL_ICELAKE_D, &i10nm_cfg1), + + X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &spr_cfg), + X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &spr_cfg), + X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, &gnr_cfg), + X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &gnr_cfg), + X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &gnr_cfg), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, &gnr_cfg), {} }; MODULE_DEVICE_TABLE(x86cpu, i10nm_cpuids); @@ -1010,7 +1012,7 @@ static struct notifier_block i10nm_mce_dec = { static int __init i10nm_init(void) { - u8 mc = 0, src_id = 0, node_id = 0; + u8 mc = 0, src_id = 0; const struct x86_cpu_id *id; struct res_config *cfg; const char *owner; @@ -1070,19 +1072,14 @@ static int __init i10nm_init(void) if (rc < 0) goto fail; - rc = skx_get_node_id(d, &node_id); - if (rc < 0) - goto fail; - - edac_dbg(2, "src_id = %d node_id = %d\n", src_id, node_id); + edac_dbg(2, "src_id = %d\n", src_id); for (i = 0; i < imc_num; i++) { if (!d->imc[i].mdev) continue; d->imc[i].mc = mc++; d->imc[i].lmc = i; - d->imc[i].src_id = src_id; - d->imc[i].node_id = node_id; + d->imc[i].src_id = src_id; if (d->imc[i].hbm_mc) { d->imc[i].chan_mmio_sz = cfg->hbm_chan_mmio_sz; d->imc[i].num_channels = cfg->hbm_chan_num; diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c index 4b5a71f8739d..4a1bebc1ff14 100644 --- a/drivers/edac/i5000_edac.c +++ b/drivers/edac/i5000_edac.c @@ -338,11 +338,11 @@ struct i5000_pvt { u16 mir0, mir1, mir2; - u16 b0_mtr[NUM_MTRS]; /* Memory Technlogy Reg */ + u16 b0_mtr[NUM_MTRS]; /* Memory Technology Reg */ u16 b0_ambpresent0; /* Branch 0, Channel 0 */ - u16 b0_ambpresent1; /* Brnach 0, Channel 1 */ + u16 b0_ambpresent1; /* Branch 0, Channel 1 */ - u16 b1_mtr[NUM_MTRS]; /* Memory Technlogy Reg */ + u16 b1_mtr[NUM_MTRS]; /* Memory Technology Reg */ u16 b1_ambpresent0; /* Branch 1, Channel 8 */ u16 b1_ambpresent1; /* Branch 1, Channel 1 */ @@ -1210,7 +1210,7 @@ static void i5000_get_mc_regs(struct mem_ctl_info *mci) &pvt->b0_ambpresent1); edac_dbg(2, "\t\tAMB-Branch 0-present1 0x%x:\n", pvt->b0_ambpresent1); - /* Only if we have 2 branchs (4 channels) */ + /* Only if we have 2 branches (4 channels) */ if (pvt->maxch < CHANNELS_PER_BRANCH) { pvt->b1_ambpresent0 = 0; pvt->b1_ambpresent1 = 0; diff --git a/drivers/edac/loongson_edac.c b/drivers/edac/loongson_edac.c new file mode 100644 index 000000000000..38745800ed01 --- /dev/null +++ b/drivers/edac/loongson_edac.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited. + */ + +#include +#include +#include +#include +#include +#include +#include "edac_module.h" + +#define ECC_CS_COUNT_REG 0x18 + +struct loongson_edac_pvt { + void __iomem *ecc_base; + + /* + * The ECC register in this controller records the number of errors + * encountered since reset and cannot be zeroed so in order to be able + * to report the error count at each check, this records the previous + * register state. + */ + int last_ce_count; +}; + +static int read_ecc(struct mem_ctl_info *mci) +{ + struct loongson_edac_pvt *pvt = mci->pvt_info; + u64 ecc; + int cs; + + ecc = readq(pvt->ecc_base + ECC_CS_COUNT_REG); + /* cs0 -- cs3 */ + cs = ecc & 0xff; + cs += (ecc >> 8) & 0xff; + cs += (ecc >> 16) & 0xff; + cs += (ecc >> 24) & 0xff; + + return cs; +} + +static void edac_check(struct mem_ctl_info *mci) +{ + struct loongson_edac_pvt *pvt = mci->pvt_info; + int new, add; + + new = read_ecc(mci); + add = new - pvt->last_ce_count; + pvt->last_ce_count = new; + if (add <= 0) + return; + + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, add, + 0, 0, 0, 0, 0, -1, "error", ""); +} + +static void dimm_config_init(struct mem_ctl_info *mci) +{ + struct dimm_info *dimm; + u32 size, npages; + + /* size not used */ + size = -1; + npages = MiB_TO_PAGES(size); + + dimm = edac_get_dimm(mci, 0, 0, 0); + dimm->nr_pages = npages; + snprintf(dimm->label, sizeof(dimm->label), + "MC#%uChannel#%u_DIMM#%u", mci->mc_idx, 0, 0); + dimm->grain = 8; +} + +static void pvt_init(struct mem_ctl_info *mci, void __iomem *vbase) +{ + struct loongson_edac_pvt *pvt = mci->pvt_info; + + pvt->ecc_base = vbase; + pvt->last_ce_count = read_ecc(mci); +} + +static int edac_probe(struct platform_device *pdev) +{ + struct edac_mc_layer layers[2]; + struct mem_ctl_info *mci; + void __iomem *vbase; + int ret; + + vbase = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(vbase)) + return PTR_ERR(vbase); + + layers[0].type = EDAC_MC_LAYER_CHANNEL; + layers[0].size = 1; + layers[0].is_virt_csrow = false; + layers[1].type = EDAC_MC_LAYER_SLOT; + layers[1].size = 1; + layers[1].is_virt_csrow = true; + mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, + sizeof(struct loongson_edac_pvt)); + if (mci == NULL) + return -ENOMEM; + + mci->mc_idx = edac_device_alloc_index(); + mci->mtype_cap = MEM_FLAG_RDDR4; + mci->edac_ctl_cap = EDAC_FLAG_NONE; + mci->edac_cap = EDAC_FLAG_NONE; + mci->mod_name = "loongson_edac.c"; + mci->ctl_name = "loongson_edac_ctl"; + mci->dev_name = "loongson_edac_dev"; + mci->ctl_page_to_phys = NULL; + mci->pdev = &pdev->dev; + mci->error_desc.grain = 8; + mci->edac_check = edac_check; + + pvt_init(mci, vbase); + dimm_config_init(mci); + + ret = edac_mc_add_mc(mci); + if (ret) { + edac_dbg(0, "MC: failed edac_mc_add_mc()\n"); + edac_mc_free(mci); + return ret; + } + edac_op_state = EDAC_OPSTATE_POLL; + + return 0; +} + +static void edac_remove(struct platform_device *pdev) +{ + struct mem_ctl_info *mci = edac_mc_del_mc(&pdev->dev); + + if (mci) + edac_mc_free(mci); +} + +static const struct acpi_device_id loongson_edac_acpi_match[] = { + {"LOON0010", 0}, + {} +}; +MODULE_DEVICE_TABLE(acpi, loongson_edac_acpi_match); + +static struct platform_driver loongson_edac_driver = { + .probe = edac_probe, + .remove = edac_remove, + .driver = { + .name = "loongson-mc-edac", + .acpi_match_table = loongson_edac_acpi_match, + }, +}; +module_platform_driver(loongson_edac_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Zhao Qunqin "); +MODULE_DESCRIPTION("EDAC driver for loongson memory controller"); diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c index 14cfd394b469..29897b21fb8e 100644 --- a/drivers/edac/skx_base.c +++ b/drivers/edac/skx_base.c @@ -164,7 +164,7 @@ static struct res_config skx_cfg = { }; static const struct x86_cpu_id skx_cpuids[] = { - X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x0, 0xf), &skx_cfg), + X86_MATCH_VFM(INTEL_SKYLAKE_X, &skx_cfg), { } }; MODULE_DEVICE_TABLE(x86cpu, skx_cpuids); @@ -600,7 +600,7 @@ static int __init skx_init(void) const struct munit *m; const char *owner; int rc = 0, i, off[3] = {0xd0, 0xd4, 0xd8}; - u8 mc = 0, src_id, node_id; + u8 mc = 0, src_id; struct skx_dev *d; edac_dbg(2, "\n"); @@ -650,15 +650,12 @@ static int __init skx_init(void) rc = skx_get_src_id(d, 0xf0, &src_id); if (rc < 0) goto fail; - rc = skx_get_node_id(d, &node_id); - if (rc < 0) - goto fail; - edac_dbg(2, "src_id=%d node_id=%d\n", src_id, node_id); + + edac_dbg(2, "src_id = %d\n", src_id); for (i = 0; i < SKX_NUM_IMC; i++) { d->imc[i].mc = mc++; d->imc[i].lmc = i; d->imc[i].src_id = src_id; - d->imc[i].node_id = node_id; rc = skx_register_mci(&d->imc[i], d->imc[i].chan[0].cdev, "Skylake Socket", EDAC_MOD_STR, skx_get_dimm_config, cfg); diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 6cf17af7d911..f7bd930e058f 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "edac_module.h" #include "skx_common.h" @@ -221,10 +222,42 @@ void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log) } EXPORT_SYMBOL_GPL(skx_set_decode); +static int skx_get_pkg_id(struct skx_dev *d, u8 *id) +{ + int node; + int cpu; + + node = pcibus_to_node(d->util_all->bus); + if (numa_valid_node(node)) { + for_each_cpu(cpu, cpumask_of_pcibus(d->util_all->bus)) { + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->initialized && cpu_to_node(cpu) == node) { + *id = c->topo.pkg_id; + return 0; + } + } + } + + skx_printk(KERN_ERR, "Failed to get package ID from NUMA information\n"); + return -ENODEV; +} + int skx_get_src_id(struct skx_dev *d, int off, u8 *id) { u32 reg; + /* + * The 3-bit source IDs in PCI configuration space registers are limited + * to 8 unique IDs, and each ID is local to a UPI/QPI domain. + * + * Source IDs cannot be used to map devices to sockets on UV systems + * because they can exceed 8 sockets and have multiple UPI/QPI domains + * with identical, repeating source IDs. + */ + if (is_uv_system()) + return skx_get_pkg_id(d, id); + if (pci_read_config_dword(d->util_all, off, ®)) { skx_printk(KERN_ERR, "Failed to read src id\n"); return -ENODEV; @@ -235,20 +268,6 @@ int skx_get_src_id(struct skx_dev *d, int off, u8 *id) } EXPORT_SYMBOL_GPL(skx_get_src_id); -int skx_get_node_id(struct skx_dev *d, u8 *id) -{ - u32 reg; - - if (pci_read_config_dword(d->util_all, 0xf4, ®)) { - skx_printk(KERN_ERR, "Failed to read node id\n"); - return -ENODEV; - } - - *id = GET_BITFIELD(reg, 0, 2); - return 0; -} -EXPORT_SYMBOL_GPL(skx_get_node_id); - static int get_width(u32 mtr) { switch (GET_BITFIELD(mtr, 8, 9)) { @@ -507,7 +526,7 @@ int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev, pvt->imc = imc; mci->ctl_name = kasprintf(GFP_KERNEL, "%s#%d IMC#%d", ctl_name, - imc->node_id, imc->lmc); + imc->src_id, imc->lmc); if (!mci->ctl_name) { rc = -ENOMEM; goto fail0; diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index 54bba8a62f72..b0845bdd4516 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -103,7 +103,7 @@ struct skx_dev { bool hbm_mc; u8 mc; /* system wide mc# */ u8 lmc; /* socket relative mc# */ - u8 src_id, node_id; + u8 src_id; struct skx_channel { struct pci_dev *cdev; struct pci_dev *edev; @@ -244,7 +244,6 @@ void skx_set_mem_cfg(bool mem_cfg_2lm); void skx_set_res_cfg(struct res_config *cfg); int skx_get_src_id(struct skx_dev *d, int off, u8 *id); -int skx_get_node_id(struct skx_dev *d, u8 *id); int skx_get_all_bus_mappings(struct res_config *cfg, struct list_head **list); diff --git a/drivers/extcon/extcon-fsa9480.c b/drivers/extcon/extcon-fsa9480.c index e458ce0c45ab..b11b43171063 100644 --- a/drivers/extcon/extcon-fsa9480.c +++ b/drivers/extcon/extcon-fsa9480.c @@ -350,7 +350,7 @@ static const struct dev_pm_ops fsa9480_pm_ops = { }; static const struct i2c_device_id fsa9480_id[] = { - { "fsa9480", 0 }, + { "fsa9480" }, {} }; MODULE_DEVICE_TABLE(i2c, fsa9480_id); diff --git a/drivers/extcon/extcon-ptn5150.c b/drivers/extcon/extcon-ptn5150.c index 4616da7e5430..78ad86c4a3be 100644 --- a/drivers/extcon/extcon-ptn5150.c +++ b/drivers/extcon/extcon-ptn5150.c @@ -338,7 +338,7 @@ static const struct of_device_id ptn5150_dt_match[] = { MODULE_DEVICE_TABLE(of, ptn5150_dt_match); static const struct i2c_device_id ptn5150_i2c_id[] = { - { "ptn5150", 0 }, + { "ptn5150" }, { } }; MODULE_DEVICE_TABLE(i2c, ptn5150_i2c_id); diff --git a/drivers/extcon/extcon-rtk-type-c.c b/drivers/extcon/extcon-rtk-type-c.c index bdc2b7b3a246..82b60b927e41 100644 --- a/drivers/extcon/extcon-rtk-type-c.c +++ b/drivers/extcon/extcon-rtk-type-c.c @@ -1369,6 +1369,8 @@ static int extcon_rtk_type_c_probe(struct platform_device *pdev) } type_c->type_c_cfg = devm_kzalloc(dev, sizeof(*type_c_cfg), GFP_KERNEL); + if (!type_c->type_c_cfg) + return -ENOMEM; memcpy(type_c->type_c_cfg, type_c_cfg, sizeof(*type_c_cfg)); diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index a99fe35f1f0d..ec3e21ad2025 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -988,7 +988,7 @@ int fw_device_set_broadcast_channel(struct device *dev, void *gen) return 0; } -static int compare_configuration_rom(struct device *dev, void *data) +static int compare_configuration_rom(struct device *dev, const void *data) { const struct fw_device *old = fw_device(dev); const u32 *config_rom = data; @@ -1039,7 +1039,7 @@ static void fw_device_init(struct work_struct *work) // // serialize config_rom access. scoped_guard(rwsem_read, &fw_device_rwsem) { - found = device_find_child(card->device, (void *)device->config_rom, + found = device_find_child(card->device, device->config_rom, compare_configuration_rom); } if (found) { diff --git a/drivers/firewire/device-attribute-test.c b/drivers/firewire/device-attribute-test.c index 2f123c6b0a16..97478a96d1c9 100644 --- a/drivers/firewire/device-attribute-test.c +++ b/drivers/firewire/device-attribute-test.c @@ -99,6 +99,7 @@ static void device_attr_simple_avc(struct kunit *test) struct device *unit0_dev = (struct device *)&unit0.device; static const int unit0_expected_ids[] = {0x00ffffff, 0x00ffffff, 0x0000a02d, 0x00010001}; char *buf = kunit_kzalloc(test, PAGE_SIZE, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf); int ids[4] = {0, 0, 0, 0}; // Ensure associations for node and unit devices. @@ -180,6 +181,7 @@ static void device_attr_legacy_avc(struct kunit *test) struct device *unit0_dev = (struct device *)&unit0.device; static const int unit0_expected_ids[] = {0x00012345, 0x00fedcba, 0x00abcdef, 0x00543210}; char *buf = kunit_kzalloc(test, PAGE_SIZE, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf); int ids[4] = {0, 0, 0, 0}; // Ensure associations for node and unit devices. diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index c02aed11b590..edaedd156a6d 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -3301,8 +3301,7 @@ static int ohci_set_iso_channels(struct fw_iso_context *base, u64 *channels) } } -#ifdef CONFIG_PM -static void ohci_resume_iso_dma(struct fw_ohci *ohci) +static void __maybe_unused ohci_resume_iso_dma(struct fw_ohci *ohci) { int i; struct iso_context *ctx; @@ -3319,7 +3318,6 @@ static void ohci_resume_iso_dma(struct fw_ohci *ohci) ohci_start_iso(&ctx->base, 0, ctx->sync, ctx->tags); } } -#endif static int queue_iso_transmit(struct iso_context *ctx, struct fw_iso_packet *packet, @@ -3888,39 +3886,25 @@ static void pci_remove(struct pci_dev *dev) dev_notice(&dev->dev, "removing fw-ohci device\n"); } -#ifdef CONFIG_PM -static int pci_suspend(struct pci_dev *dev, pm_message_t state) +static int __maybe_unused pci_suspend(struct device *dev) { - struct fw_ohci *ohci = pci_get_drvdata(dev); - int err; + struct pci_dev *pdev = to_pci_dev(dev); + struct fw_ohci *ohci = pci_get_drvdata(pdev); software_reset(ohci); - err = pci_save_state(dev); - if (err) { - ohci_err(ohci, "pci_save_state failed\n"); - return err; - } - err = pci_set_power_state(dev, pci_choose_state(dev, state)); - if (err) - ohci_err(ohci, "pci_set_power_state failed with %d\n", err); - pmac_ohci_off(dev); + pmac_ohci_off(pdev); return 0; } -static int pci_resume(struct pci_dev *dev) + +static int __maybe_unused pci_resume(struct device *dev) { - struct fw_ohci *ohci = pci_get_drvdata(dev); + struct pci_dev *pdev = to_pci_dev(dev); + struct fw_ohci *ohci = pci_get_drvdata(pdev); int err; - pmac_ohci_on(dev); - pci_set_power_state(dev, PCI_D0); - pci_restore_state(dev); - err = pci_enable_device(dev); - if (err) { - ohci_err(ohci, "pci_enable_device failed\n"); - return err; - } + pmac_ohci_on(pdev); /* Some systems don't setup GUID register on resume from ram */ if (!reg_read(ohci, OHCI1394_GUIDLo) && @@ -3937,7 +3921,6 @@ static int pci_resume(struct pci_dev *dev) return 0; } -#endif static const struct pci_device_id pci_table[] = { { PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_FIREWIRE_OHCI, ~0) }, @@ -3946,15 +3929,14 @@ static const struct pci_device_id pci_table[] = { MODULE_DEVICE_TABLE(pci, pci_table); +static SIMPLE_DEV_PM_OPS(pci_pm_ops, pci_suspend, pci_resume); + static struct pci_driver fw_ohci_pci_driver = { .name = ohci_driver_name, .id_table = pci_table, .probe = pci_probe, .remove = pci_remove, -#ifdef CONFIG_PM - .resume = pci_resume, - .suspend = pci_suspend, -#endif + .driver.pm = &pci_pm_ops, }; static int __init fw_ohci_init(void) diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 827dee0f57dd..1a19828114cf 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -1490,7 +1490,7 @@ static int sbp2_scsi_queuecommand(struct Scsi_Host *shost, return retval; } -static int sbp2_scsi_slave_alloc(struct scsi_device *sdev) +static int sbp2_scsi_sdev_init(struct scsi_device *sdev) { struct sbp2_logical_unit *lu = sdev->hostdata; @@ -1506,8 +1506,8 @@ static int sbp2_scsi_slave_alloc(struct scsi_device *sdev) return 0; } -static int sbp2_scsi_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int sbp2_scsi_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct sbp2_logical_unit *lu = sdev->hostdata; @@ -1590,8 +1590,8 @@ static const struct scsi_host_template scsi_driver_template = { .name = "SBP-2 IEEE-1394", .proc_name = "sbp2", .queuecommand = sbp2_scsi_queuecommand, - .slave_alloc = sbp2_scsi_slave_alloc, - .device_configure = sbp2_scsi_device_configure, + .sdev_init = sbp2_scsi_sdev_init, + .sdev_configure = sbp2_scsi_sdev_configure, .eh_abort_handler = sbp2_scsi_abort, .this_id = -1, .sg_tablesize = SG_ALL, diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index eb17d03b66fe..dfda5ffc14db 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -187,13 +187,18 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) return valid; } -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { int id, ret; + uuid_t uuid; struct device *dev; struct ffa_device *ffa_dev; + if (!part_info) + return NULL; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); if (id < 0) return NULL; @@ -210,9 +215,11 @@ struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->id = id; - ffa_dev->vm_id = vm_id; + ffa_dev->vm_id = part_info->id; + ffa_dev->properties = part_info->properties; ffa_dev->ops = ops; - uuid_copy(&ffa_dev->uuid, uuid); + import_uuid(&uuid, (u8 *)part_info->uuid); + uuid_copy(&ffa_dev->uuid, &uuid); ret = device_register(&ffa_dev->dev); if (ret) { diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index b14cbdae94e8..2c2ec3c35f15 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1387,7 +1387,6 @@ static struct notifier_block ffa_bus_nb = { static int ffa_setup_partitions(void) { int count, idx, ret; - uuid_t uuid; struct ffa_device *ffa_dev; struct ffa_dev_part_info *info; struct ffa_partition_info *pbuf, *tpbuf; @@ -1406,23 +1405,19 @@ static int ffa_setup_partitions(void) xa_init(&drv_info->partition_info); for (idx = 0, tpbuf = pbuf; idx < count; idx++, tpbuf++) { - import_uuid(&uuid, (u8 *)tpbuf->uuid); - /* Note that if the UUID will be uuid_null, that will require * ffa_bus_notifier() to find the UUID of this partition id * with help of ffa_device_match_uuid(). FF-A v1.1 and above * provides UUID here for each partition as part of the * discovery API and the same is passed. */ - ffa_dev = ffa_device_register(&uuid, tpbuf->id, &ffa_drv_ops); + ffa_dev = ffa_device_register(tpbuf, &ffa_drv_ops); if (!ffa_dev) { pr_err("%s: failed to register partition ID 0x%x\n", __func__, tpbuf->id); continue; } - ffa_dev->properties = tpbuf->properties; - if (drv_info->version > FFA_VERSION_1_0 && !(tpbuf->properties & FFA_PARTITION_AARCH64_EXEC)) ffa_mode_32bit_set(ffa_dev); diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 157172a5f2b5..a3386bf36de5 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -238,10 +238,10 @@ static int scmi_dev_match(struct device *dev, const struct device_driver *drv) return 0; } -static int scmi_match_by_id_table(struct device *dev, void *data) +static int scmi_match_by_id_table(struct device *dev, const void *data) { struct scmi_device *sdev = to_scmi_dev(dev); - struct scmi_device_id *id_table = data; + const struct scmi_device_id *id_table = data; return sdev->protocol_id == id_table->protocol_id && (id_table->name && !strcmp(sdev->name, id_table->name)); diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index 48b12f81141d..10ea7962323e 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -442,7 +442,7 @@ struct scmi_transport_core_operations { */ struct scmi_transport { struct device *supplier; - struct scmi_desc *desc; + struct scmi_desc desc; struct scmi_transport_core_operations **core_ops; }; @@ -468,7 +468,7 @@ static int __tag##_probe(struct platform_device *pdev) \ device_set_of_node_from_dev(&spdev->dev, dev); \ \ strans.supplier = dev; \ - strans.desc = &(__desc); \ + memcpy(&strans.desc, &(__desc), sizeof(strans.desc)); \ strans.core_ops = &(__core_ops); \ \ ret = platform_device_add_data(spdev, &strans, sizeof(strans)); \ diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 1b5fb2c4ce86..60050da54bf2 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -43,6 +44,8 @@ #define CREATE_TRACE_POINTS #include +#define SCMI_VENDOR_MODULE_ALIAS_FMT "scmi-protocol-0x%02x-%s" + static DEFINE_IDA(scmi_id); static DEFINE_XARRAY(scmi_protocols); @@ -275,6 +278,44 @@ scmi_vendor_protocol_lookup(int protocol_id, char *vendor_id, return proto; } +static const struct scmi_protocol * +scmi_vendor_protocol_get(int protocol_id, struct scmi_revision_info *version) +{ + const struct scmi_protocol *proto; + + proto = scmi_vendor_protocol_lookup(protocol_id, version->vendor_id, + version->sub_vendor_id, + version->impl_ver); + if (!proto) { + int ret; + + pr_debug("Looking for '" SCMI_VENDOR_MODULE_ALIAS_FMT "'\n", + protocol_id, version->vendor_id); + + /* Note that vendor_id is mandatory for vendor protocols */ + ret = request_module(SCMI_VENDOR_MODULE_ALIAS_FMT, + protocol_id, version->vendor_id); + if (ret) { + pr_warn("Problem loading module for protocol 0x%x\n", + protocol_id); + return NULL; + } + + /* Lookup again, once modules loaded */ + proto = scmi_vendor_protocol_lookup(protocol_id, + version->vendor_id, + version->sub_vendor_id, + version->impl_ver); + } + + if (proto) + pr_info("Loaded SCMI Vendor Protocol 0x%x - %s %s %X\n", + protocol_id, proto->vendor_id ?: "", + proto->sub_vendor_id ?: "", proto->impl_ver); + + return proto; +} + static const struct scmi_protocol * scmi_protocol_get(int protocol_id, struct scmi_revision_info *version) { @@ -283,10 +324,8 @@ scmi_protocol_get(int protocol_id, struct scmi_revision_info *version) if (protocol_id < SCMI_PROTOCOL_VENDOR_BASE) proto = xa_load(&scmi_protocols, protocol_id); else - proto = scmi_vendor_protocol_lookup(protocol_id, - version->vendor_id, - version->sub_vendor_id, - version->impl_ver); + proto = scmi_vendor_protocol_get(protocol_id, version); + if (!proto || !try_module_get(proto->owner)) { pr_warn("SCMI Protocol 0x%x not found!\n", protocol_id); return NULL; @@ -294,11 +333,6 @@ scmi_protocol_get(int protocol_id, struct scmi_revision_info *version) pr_debug("Found SCMI Protocol 0x%x\n", protocol_id); - if (protocol_id >= SCMI_PROTOCOL_VENDOR_BASE) - pr_info("Loaded SCMI Vendor Protocol 0x%x - %s %s %X\n", - protocol_id, proto->vendor_id ?: "", - proto->sub_vendor_id ?: "", proto->impl_ver); - return proto; } @@ -366,7 +400,9 @@ int scmi_protocol_register(const struct scmi_protocol *proto) return ret; } - pr_debug("Registered SCMI Protocol 0x%x\n", proto->id); + pr_debug("Registered SCMI Protocol 0x%x - %s %s 0x%08X\n", + proto->id, proto->vendor_id, proto->sub_vendor_id, + proto->impl_ver); return 0; } @@ -3028,7 +3064,7 @@ static const struct scmi_desc *scmi_transport_setup(struct device *dev) int ret; trans = dev_get_platdata(dev); - if (!trans || !trans->desc || !trans->supplier || !trans->core_ops) + if (!trans || !trans->supplier || !trans->core_ops) return NULL; if (!device_link_add(dev, trans->supplier, DL_FLAG_AUTOREMOVE_CONSUMER)) { @@ -3043,33 +3079,33 @@ static const struct scmi_desc *scmi_transport_setup(struct device *dev) dev_info(dev, "Using %s\n", dev_driver_string(trans->supplier)); ret = of_property_read_u32(dev->of_node, "arm,max-rx-timeout-ms", - &trans->desc->max_rx_timeout_ms); + &trans->desc.max_rx_timeout_ms); if (ret && ret != -EINVAL) dev_err(dev, "Malformed arm,max-rx-timeout-ms DT property.\n"); ret = of_property_read_u32(dev->of_node, "arm,max-msg-size", - &trans->desc->max_msg_size); + &trans->desc.max_msg_size); if (ret && ret != -EINVAL) dev_err(dev, "Malformed arm,max-msg-size DT property.\n"); ret = of_property_read_u32(dev->of_node, "arm,max-msg", - &trans->desc->max_msg); + &trans->desc.max_msg); if (ret && ret != -EINVAL) dev_err(dev, "Malformed arm,max-msg DT property.\n"); dev_info(dev, "SCMI max-rx-timeout: %dms / max-msg-size: %dbytes / max-msg: %d\n", - trans->desc->max_rx_timeout_ms, trans->desc->max_msg_size, - trans->desc->max_msg); + trans->desc.max_rx_timeout_ms, trans->desc.max_msg_size, + trans->desc.max_msg); /* System wide atomic threshold for atomic ops .. if any */ if (!of_property_read_u32(dev->of_node, "atomic-threshold-us", - &trans->desc->atomic_threshold)) + &trans->desc.atomic_threshold)) dev_info(dev, "SCMI System wide atomic threshold set to %u us\n", - trans->desc->atomic_threshold); + trans->desc.atomic_threshold); - return trans->desc; + return &trans->desc; } static int scmi_probe(struct platform_device *pdev) diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index 9e89a6a763da..7cc0d616b8de 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -886,10 +886,8 @@ static __poll_t scmi_dbg_raw_mode_message_poll(struct file *filp, static int scmi_dbg_raw_mode_open(struct inode *inode, struct file *filp) { - u8 id; struct scmi_raw_mode_info *raw; struct scmi_dbg_raw_data *rd; - const char *id_str = filp->f_path.dentry->d_parent->d_name.name; if (!inode->i_private) return -ENODEV; @@ -915,8 +913,8 @@ static int scmi_dbg_raw_mode_open(struct inode *inode, struct file *filp) } /* Grab channel ID from debugfs entry naming if any */ - if (!kstrtou8(id_str, 16, &id)) - rd->chan_id = id; + /* not set - reassing 0 we already had after kzalloc() */ + rd->chan_id = debugfs_get_aux_num(filp); rd->raw = raw; filp->private_data = rd; @@ -1225,10 +1223,12 @@ void *scmi_raw_mode_init(const struct scmi_handle *handle, snprintf(cdir, 8, "0x%02X", channels[i]); chd = debugfs_create_dir(cdir, top_chans); - debugfs_create_file("message", 0600, chd, raw, + debugfs_create_file_aux_num("message", 0600, chd, + raw, channels[i], &scmi_dbg_raw_mode_message_fops); - debugfs_create_file("message_async", 0600, chd, raw, + debugfs_create_file_aux_num("message_async", 0600, chd, + raw, channels[i], &scmi_dbg_raw_mode_message_async_fops); } } diff --git a/drivers/firmware/arm_scmi/transports/mailbox.c b/drivers/firmware/arm_scmi/transports/mailbox.c index b66df2981456..bd041c99b92b 100644 --- a/drivers/firmware/arm_scmi/transports/mailbox.c +++ b/drivers/firmware/arm_scmi/transports/mailbox.c @@ -378,6 +378,7 @@ static const struct of_device_id scmi_of_match[] = { { .compatible = "arm,scmi" }, { /* Sentinel */ }, }; +MODULE_DEVICE_TABLE(of, scmi_of_match); DEFINE_SCMI_TRANSPORT_DRIVER(scmi_mailbox, scmi_mailbox_driver, scmi_mailbox_desc, scmi_of_match, core); diff --git a/drivers/firmware/arm_scmi/transports/smc.c b/drivers/firmware/arm_scmi/transports/smc.c index f632a62cfb3e..21abb571e4f2 100644 --- a/drivers/firmware/arm_scmi/transports/smc.c +++ b/drivers/firmware/arm_scmi/transports/smc.c @@ -301,6 +301,7 @@ static const struct of_device_id scmi_of_match[] = { { .compatible = "qcom,scmi-smc" }, { /* Sentinel */ }, }; +MODULE_DEVICE_TABLE(of, scmi_of_match); DEFINE_SCMI_TRANSPORT_DRIVER(scmi_smc, scmi_smc_driver, scmi_smc_desc, scmi_of_match, core); diff --git a/drivers/firmware/arm_scmi/transports/virtio.c b/drivers/firmware/arm_scmi/transports/virtio.c index 41aea33776a9..cb934db9b2b4 100644 --- a/drivers/firmware/arm_scmi/transports/virtio.c +++ b/drivers/firmware/arm_scmi/transports/virtio.c @@ -921,6 +921,7 @@ static const struct virtio_device_id id_table[] = { { VIRTIO_ID_SCMI, VIRTIO_DEV_ANY_ID }, { 0 } }; +MODULE_DEVICE_TABLE(virtio, id_table); static struct virtio_driver virtio_scmi_driver = { .driver.name = "scmi-virtio", diff --git a/drivers/firmware/arm_scmi/vendors/imx/Kconfig b/drivers/firmware/arm_scmi/vendors/imx/Kconfig index 2883ed24a84d..a01bf5e47301 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/Kconfig +++ b/drivers/firmware/arm_scmi/vendors/imx/Kconfig @@ -15,6 +15,7 @@ config IMX_SCMI_BBM_EXT config IMX_SCMI_MISC_EXT tristate "i.MX SCMI MISC EXTENSION" depends on ARM_SCMI_PROTOCOL || (COMPILE_TEST && OF) + depends on IMX_SCMI_MISC_DRV default y if ARCH_MXC help This enables i.MX System MISC control logic such as gpio expander diff --git a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-bbm.c b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-bbm.c index 17799eacf06c..aa176c1a5eef 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-bbm.c +++ b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-bbm.c @@ -374,10 +374,11 @@ static const struct scmi_protocol scmi_imx_bbm = { .ops = &scmi_imx_bbm_proto_ops, .events = &scmi_imx_bbm_protocol_events, .supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION, - .vendor_id = "NXP", - .sub_vendor_id = "IMX", + .vendor_id = SCMI_IMX_VENDOR, + .sub_vendor_id = SCMI_IMX_SUBVENDOR, }; module_scmi_protocol(scmi_imx_bbm); +MODULE_ALIAS("scmi-protocol-" __stringify(SCMI_PROTOCOL_IMX_BBM) "-" SCMI_IMX_VENDOR); MODULE_DESCRIPTION("i.MX SCMI BBM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c index a86ab9b35953..83b69fc4fba5 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c +++ b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c @@ -309,10 +309,11 @@ static const struct scmi_protocol scmi_imx_misc = { .ops = &scmi_imx_misc_proto_ops, .events = &scmi_imx_misc_protocol_events, .supported_version = SCMI_PROTOCOL_SUPPORTED_VERSION, - .vendor_id = "NXP", - .sub_vendor_id = "IMX", + .vendor_id = SCMI_IMX_VENDOR, + .sub_vendor_id = SCMI_IMX_SUBVENDOR, }; module_scmi_protocol(scmi_imx_misc); +MODULE_ALIAS("scmi-protocol-" __stringify(SCMI_PROTOCOL_IMX_MISC) "-" SCMI_IMX_VENDOR); MODULE_DESCRIPTION("i.MX SCMI MISC driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/firmware/cirrus/Kconfig b/drivers/firmware/cirrus/Kconfig index 3ccbe14e4b0c..0a883091259a 100644 --- a/drivers/firmware/cirrus/Kconfig +++ b/drivers/firmware/cirrus/Kconfig @@ -3,3 +3,21 @@ config FW_CS_DSP tristate default n + +config FW_CS_DSP_KUNIT_TEST_UTILS + tristate + depends on KUNIT && REGMAP + select FW_CS_DSP + +config FW_CS_DSP_KUNIT_TEST + tristate "KUnit tests for Cirrus Logic cs_dsp" if !KUNIT_ALL_TESTS + depends on KUNIT && REGMAP + default KUNIT_ALL_TESTS + select FW_CS_DSP + select FW_CS_DSP_KUNIT_TEST_UTILS + help + This builds KUnit tests for cs_dsp. + For more information on KUnit and unit tests in general, + please refer to the KUnit documentation in + Documentation/dev-tools/kunit/. + If in doubt, say "N". diff --git a/drivers/firmware/cirrus/Makefile b/drivers/firmware/cirrus/Makefile index b91318ca0ff4..b32dfa869491 100644 --- a/drivers/firmware/cirrus/Makefile +++ b/drivers/firmware/cirrus/Makefile @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 # obj-$(CONFIG_FW_CS_DSP) += cs_dsp.o + +obj-y += test/ diff --git a/drivers/firmware/cirrus/test/Makefile b/drivers/firmware/cirrus/test/Makefile new file mode 100644 index 000000000000..7a24a6079ddc --- /dev/null +++ b/drivers/firmware/cirrus/test/Makefile @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: GPL-2.0 +# + +cs_dsp_test_utils-objs := \ + cs_dsp_mock_mem_maps.o \ + cs_dsp_mock_bin.o \ + cs_dsp_mock_regmap.o \ + cs_dsp_mock_utils.o \ + cs_dsp_mock_wmfw.o + +cs_dsp_test-objs := \ + cs_dsp_test_bin.o \ + cs_dsp_test_bin_error.o \ + cs_dsp_test_callbacks.o \ + cs_dsp_test_control_parse.o \ + cs_dsp_test_control_cache.o \ + cs_dsp_test_control_rw.o \ + cs_dsp_test_wmfw.o \ + cs_dsp_test_wmfw_error.o \ + cs_dsp_tests.o + +obj-$(CONFIG_FW_CS_DSP_KUNIT_TEST_UTILS) += cs_dsp_test_utils.o +obj-$(CONFIG_FW_CS_DSP_KUNIT_TEST) += cs_dsp_test.o diff --git a/drivers/firmware/cirrus/test/cs_dsp_mock_bin.c b/drivers/firmware/cirrus/test/cs_dsp_mock_bin.c new file mode 100644 index 000000000000..49d84f7e59e6 --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_mock_bin.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// bin file builder for cs_dsp KUnit tests. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Buffer large enough for bin file content */ +#define CS_DSP_MOCK_BIN_BUF_SIZE 32768 + +KUNIT_DEFINE_ACTION_WRAPPER(vfree_action_wrapper, vfree, void *) + +struct cs_dsp_mock_bin_builder { + struct cs_dsp_test *test_priv; + void *buf; + void *write_p; + size_t bytes_used; +}; + +/** + * cs_dsp_mock_bin_get_firmware() - Get struct firmware wrapper for data. + * + * @builder: Pointer to struct cs_dsp_mock_bin_builder. + * + * Return: Pointer to a struct firmware wrapper for the data. + */ +struct firmware *cs_dsp_mock_bin_get_firmware(struct cs_dsp_mock_bin_builder *builder) +{ + struct firmware *fw; + + fw = kunit_kzalloc(builder->test_priv->test, sizeof(*fw), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(builder->test_priv->test, fw); + + fw->data = builder->buf; + fw->size = builder->bytes_used; + + return fw; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_bin_get_firmware, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_bin_add_raw_block() - Add a data block to the bin file. + * + * @builder: Pointer to struct cs_dsp_mock_bin_builder. + * @alg_id: Algorithm ID. + * @alg_ver: Algorithm version. + * @type: Type of the block. + * @offset: Offset. + * @payload_data: Pointer to buffer containing the payload data. + * @payload_len_bytes: Length of payload data in bytes. + */ +void cs_dsp_mock_bin_add_raw_block(struct cs_dsp_mock_bin_builder *builder, + unsigned int alg_id, unsigned int alg_ver, + int type, unsigned int offset, + const void *payload_data, size_t payload_len_bytes) +{ + struct wmfw_coeff_item *item; + size_t bytes_needed = struct_size_t(struct wmfw_coeff_item, data, payload_len_bytes); + + KUNIT_ASSERT_TRUE(builder->test_priv->test, + (builder->write_p + bytes_needed) < + (builder->buf + CS_DSP_MOCK_BIN_BUF_SIZE)); + + item = builder->write_p; + + item->offset = cpu_to_le16(offset); + item->type = cpu_to_le16(type); + item->id = cpu_to_le32(alg_id); + item->ver = cpu_to_le32(alg_ver << 8); + item->len = cpu_to_le32(payload_len_bytes); + + if (payload_len_bytes) + memcpy(item->data, payload_data, payload_len_bytes); + + builder->write_p += bytes_needed; + builder->bytes_used += bytes_needed; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_bin_add_raw_block, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +static void cs_dsp_mock_bin_add_name_or_info(struct cs_dsp_mock_bin_builder *builder, + const char *info, int type) +{ + size_t info_len = strlen(info); + char *tmp = NULL; + + if (info_len % 4) { + /* Create a padded string with length a multiple of 4 */ + info_len = round_up(info_len, 4); + tmp = kunit_kzalloc(builder->test_priv->test, info_len, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(builder->test_priv->test, tmp); + memcpy(tmp, info, info_len); + info = tmp; + } + + cs_dsp_mock_bin_add_raw_block(builder, 0, 0, WMFW_INFO_TEXT, 0, info, info_len); + kunit_kfree(builder->test_priv->test, tmp); +} + +/** + * cs_dsp_mock_bin_add_info() - Add an info block to the bin file. + * + * @builder: Pointer to struct cs_dsp_mock_bin_builder. + * @info: Pointer to info string to be copied into the file. + * + * The string will be padded to a length that is a multiple of 4 bytes. + */ +void cs_dsp_mock_bin_add_info(struct cs_dsp_mock_bin_builder *builder, + const char *info) +{ + cs_dsp_mock_bin_add_name_or_info(builder, info, WMFW_INFO_TEXT); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_bin_add_info, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_bin_add_name() - Add a name block to the bin file. + * + * @builder: Pointer to struct cs_dsp_mock_bin_builder. + * @name: Pointer to name string to be copied into the file. + */ +void cs_dsp_mock_bin_add_name(struct cs_dsp_mock_bin_builder *builder, + const char *name) +{ + cs_dsp_mock_bin_add_name_or_info(builder, name, WMFW_NAME_TEXT); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_bin_add_name, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_bin_add_patch() - Add a patch data block to the bin file. + * + * @builder: Pointer to struct cs_dsp_mock_bin_builder. + * @alg_id: Algorithm ID for the patch. + * @alg_ver: Algorithm version for the patch. + * @mem_region: Memory region for the patch. + * @reg_addr_offset: Offset to start of data in register addresses. + * @payload_data: Pointer to buffer containing the payload data. + * @payload_len_bytes: Length of payload data in bytes. + */ +void cs_dsp_mock_bin_add_patch(struct cs_dsp_mock_bin_builder *builder, + unsigned int alg_id, unsigned int alg_ver, + int mem_region, unsigned int reg_addr_offset, + const void *payload_data, size_t payload_len_bytes) +{ + /* Payload length must be a multiple of 4 */ + KUNIT_ASSERT_EQ(builder->test_priv->test, payload_len_bytes % 4, 0); + + cs_dsp_mock_bin_add_raw_block(builder, alg_id, alg_ver, + mem_region, reg_addr_offset, + payload_data, payload_len_bytes); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_bin_add_patch, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_bin_init() - Initialize a struct cs_dsp_mock_bin_builder. + * + * @priv: Pointer to struct cs_dsp_test. + * @format_version: Required bin format version. + * @fw_version: Firmware version to put in bin file. + * + * Return: Pointer to created struct cs_dsp_mock_bin_builder. + */ +struct cs_dsp_mock_bin_builder *cs_dsp_mock_bin_init(struct cs_dsp_test *priv, + int format_version, + unsigned int fw_version) +{ + struct cs_dsp_mock_bin_builder *builder; + struct wmfw_coeff_hdr *hdr; + + builder = kunit_kzalloc(priv->test, sizeof(*builder), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(priv->test, builder); + builder->test_priv = priv; + + builder->buf = vmalloc(CS_DSP_MOCK_BIN_BUF_SIZE); + KUNIT_ASSERT_NOT_NULL(priv->test, builder->buf); + kunit_add_action_or_reset(priv->test, vfree_action_wrapper, builder->buf); + + /* Create header */ + hdr = builder->buf; + memcpy(hdr->magic, "WMDR", sizeof(hdr->magic)); + hdr->len = cpu_to_le32(offsetof(struct wmfw_coeff_hdr, data)); + hdr->ver = cpu_to_le32(fw_version | (format_version << 24)); + hdr->core_ver = cpu_to_le32(((u32)priv->dsp->type << 24) | priv->dsp->rev); + + builder->write_p = hdr->data; + builder->bytes_used = offsetof(struct wmfw_coeff_hdr, data); + + return builder; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_bin_init, "FW_CS_DSP_KUNIT_TEST_UTILS"); diff --git a/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c b/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c new file mode 100644 index 000000000000..161272e47bda --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c @@ -0,0 +1,752 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// Mock DSP memory maps for cs_dsp KUnit tests. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include +#include +#include +#include +#include + +const struct cs_dsp_region cs_dsp_mock_halo_dsp1_regions[] = { + { .type = WMFW_HALO_PM_PACKED, .base = 0x3800000 }, + { .type = WMFW_HALO_XM_PACKED, .base = 0x2000000 }, + { .type = WMFW_HALO_YM_PACKED, .base = 0x2C00000 }, + { .type = WMFW_ADSP2_XM, .base = 0x2800000 }, + { .type = WMFW_ADSP2_YM, .base = 0x3400000 }, +}; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_halo_dsp1_regions, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/* List of sizes in bytes, for each entry above */ +const unsigned int cs_dsp_mock_halo_dsp1_region_sizes[] = { + 0x5000, /* PM_PACKED */ + 0x6000, /* XM_PACKED */ + 0x47F4, /* YM_PACKED */ + 0x8000, /* XM_UNPACKED_24 */ + 0x5FF8, /* YM_UNPACKED_24 */ + + 0 /* terminator */ +}; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_halo_dsp1_region_sizes, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +const struct cs_dsp_region cs_dsp_mock_adsp2_32bit_dsp1_regions[] = { + { .type = WMFW_ADSP2_PM, .base = 0x080000 }, + { .type = WMFW_ADSP2_XM, .base = 0x0a0000 }, + { .type = WMFW_ADSP2_YM, .base = 0x0c0000 }, + { .type = WMFW_ADSP2_ZM, .base = 0x0e0000 }, +}; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_adsp2_32bit_dsp1_regions, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/* List of sizes in bytes, for each entry above */ +const unsigned int cs_dsp_mock_adsp2_32bit_dsp1_region_sizes[] = { + 0x9000, /* PM */ + 0xa000, /* ZM */ + 0x2000, /* XM */ + 0x2000, /* YM */ + + 0 /* terminator */ +}; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_adsp2_32bit_dsp1_region_sizes, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +const struct cs_dsp_region cs_dsp_mock_adsp2_16bit_dsp1_regions[] = { + { .type = WMFW_ADSP2_PM, .base = 0x100000 }, + { .type = WMFW_ADSP2_ZM, .base = 0x180000 }, + { .type = WMFW_ADSP2_XM, .base = 0x190000 }, + { .type = WMFW_ADSP2_YM, .base = 0x1a8000 }, +}; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_adsp2_16bit_dsp1_regions, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/* List of sizes in bytes, for each entry above */ +const unsigned int cs_dsp_mock_adsp2_16bit_dsp1_region_sizes[] = { + 0x6000, /* PM */ + 0x800, /* ZM */ + 0x800, /* XM */ + 0x800, /* YM */ + + 0 /* terminator */ +}; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_adsp2_16bit_dsp1_region_sizes, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +int cs_dsp_mock_count_regions(const unsigned int *region_sizes) +{ + int i; + + for (i = 0; region_sizes[i]; ++i) + ; + + return i; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_count_regions, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_size_of_region() - Return size of given memory region. + * + * @dsp: Pointer to struct cs_dsp. + * @mem_type: Memory region type. + * + * Return: Size of region in bytes. + */ +unsigned int cs_dsp_mock_size_of_region(const struct cs_dsp *dsp, int mem_type) +{ + const unsigned int *sizes; + int i; + + if (dsp->mem == cs_dsp_mock_halo_dsp1_regions) + sizes = cs_dsp_mock_halo_dsp1_region_sizes; + else if (dsp->mem == cs_dsp_mock_adsp2_32bit_dsp1_regions) + sizes = cs_dsp_mock_adsp2_32bit_dsp1_region_sizes; + else if (dsp->mem == cs_dsp_mock_adsp2_16bit_dsp1_regions) + sizes = cs_dsp_mock_adsp2_16bit_dsp1_region_sizes; + else + return 0; + + for (i = 0; i < dsp->num_mems; ++i) { + if (dsp->mem[i].type == mem_type) + return sizes[i]; + } + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_size_of_region, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_base_addr_for_mem() - Base register address for memory region. + * + * @priv: Pointer to struct cs_dsp_test. + * @mem_type: Memory region type. + * + * Return: Base register address of region. + */ +unsigned int cs_dsp_mock_base_addr_for_mem(struct cs_dsp_test *priv, int mem_type) +{ + int num_mems = priv->dsp->num_mems; + const struct cs_dsp_region *region = priv->dsp->mem; + int i; + + for (i = 0; i < num_mems; ++i) { + if (region[i].type == mem_type) + return region[i].base; + } + + KUNIT_FAIL(priv->test, "Unexpected region %d\n", mem_type); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_base_addr_for_mem, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_reg_addr_inc_per_unpacked_word() - Unpacked register address increment per DSP word. + * + * @priv: Pointer to struct cs_dsp_test. + * + * Return: Amount by which register address increments to move to the next + * DSP word in unpacked XM/YM/ZM. + */ +unsigned int cs_dsp_mock_reg_addr_inc_per_unpacked_word(struct cs_dsp_test *priv) +{ + switch (priv->dsp->type) { + case WMFW_ADSP2: + return 2; /* two 16-bit register indexes per XM/YM/ZM word */ + case WMFW_HALO: + return 4; /* one byte-addressed 32-bit register per XM/YM/ZM word */ + default: + KUNIT_FAIL(priv->test, "Unexpected DSP type\n"); + return -1; + } +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_reg_addr_inc_per_unpacked_word, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_reg_block_length_bytes() - Number of bytes in an access block. + * + * @priv: Pointer to struct cs_dsp_test. + * @mem_type: Memory region type. + * + * Return: Total number of bytes in a group of registers forming the + * smallest bus access size (including any padding bits). For unpacked + * memory this is the number of registers containing one DSP word. + * For packed memory this is the number of registers in one packed + * access block. + */ +unsigned int cs_dsp_mock_reg_block_length_bytes(struct cs_dsp_test *priv, int mem_type) +{ + switch (priv->dsp->type) { + case WMFW_ADSP2: + switch (mem_type) { + case WMFW_ADSP2_PM: + return 3 * regmap_get_val_bytes(priv->dsp->regmap); + case WMFW_ADSP2_XM: + case WMFW_ADSP2_YM: + case WMFW_ADSP2_ZM: + return sizeof(u32); + default: + break; + } + break; + case WMFW_HALO: + switch (mem_type) { + case WMFW_ADSP2_XM: + case WMFW_ADSP2_YM: + return sizeof(u32); + case WMFW_HALO_PM_PACKED: + return 5 * sizeof(u32); + case WMFW_HALO_XM_PACKED: + case WMFW_HALO_YM_PACKED: + return 3 * sizeof(u32); + default: + break; + } + break; + default: + KUNIT_FAIL(priv->test, "Unexpected DSP type\n"); + return 0; + } + + KUNIT_FAIL(priv->test, "Unexpected mem type\n"); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_reg_block_length_bytes, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_reg_block_length_registers() - Number of registers in an access block. + * + * @priv: Pointer to struct cs_dsp_test. + * @mem_type: Memory region type. + * + * Return: Total number of register forming the smallest bus access size. + * For unpacked memory this is the number of registers containing one + * DSP word. For packed memory this is the number of registers in one + * packed access block. + */ +unsigned int cs_dsp_mock_reg_block_length_registers(struct cs_dsp_test *priv, int mem_type) +{ + return cs_dsp_mock_reg_block_length_bytes(priv, mem_type) / + regmap_get_val_bytes(priv->dsp->regmap); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_reg_block_length_registers, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_reg_block_length_dsp_words() - Number of dsp_words in an access block. + * + * @priv: Pointer to struct cs_dsp_test. + * @mem_type: Memory region type. + * + * Return: Total number of DSP words in a group of registers forming the + * smallest bus access size. + */ +unsigned int cs_dsp_mock_reg_block_length_dsp_words(struct cs_dsp_test *priv, int mem_type) +{ + switch (priv->dsp->type) { + case WMFW_ADSP2: + switch (mem_type) { + case WMFW_ADSP2_PM: + return regmap_get_val_bytes(priv->dsp->regmap) / 2; + case WMFW_ADSP2_XM: + case WMFW_ADSP2_YM: + case WMFW_ADSP2_ZM: + return 1; + default: + break; + } + break; + case WMFW_HALO: + switch (mem_type) { + case WMFW_ADSP2_XM: + case WMFW_ADSP2_YM: + return 1; + case WMFW_HALO_PM_PACKED: + case WMFW_HALO_XM_PACKED: + case WMFW_HALO_YM_PACKED: + return 4; + default: + break; + } + break; + default: + KUNIT_FAIL(priv->test, "Unexpected DSP type\n"); + return 0; + } + + KUNIT_FAIL(priv->test, "Unexpected mem type\n"); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_reg_block_length_dsp_words, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_has_zm() - DSP has ZM + * + * @priv: Pointer to struct cs_dsp_test. + * + * Return: True if DSP has ZM. + */ +bool cs_dsp_mock_has_zm(struct cs_dsp_test *priv) +{ + switch (priv->dsp->type) { + case WMFW_ADSP2: + return true; + default: + return false; + } +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_has_zm, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_packed_to_unpacked_mem_type() - Unpacked region that is + * the same memory as a packed region. + * + * @packed_mem_type: Type of packed memory region. + * + * Return: unpacked type that is the same memory as packed_mem_type. + */ +int cs_dsp_mock_packed_to_unpacked_mem_type(int packed_mem_type) +{ + switch (packed_mem_type) { + case WMFW_HALO_XM_PACKED: + return WMFW_ADSP2_XM; + case WMFW_HALO_YM_PACKED: + return WMFW_ADSP2_YM; + default: + return -1; + } +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_packed_to_unpacked_mem_type, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_num_dsp_words_to_num_packed_regs() - Number of DSP words + * to number of packed registers. + * + * @num_dsp_words: Number of DSP words. + * + * Convert number of DSP words to number of packed registers rounded + * down to the nearest register. + * + * Return: Number of packed registers. + */ +unsigned int cs_dsp_mock_num_dsp_words_to_num_packed_regs(unsigned int num_dsp_words) +{ + /* There are 3 registers for every 4 packed words */ + return (num_dsp_words * 3) / 4; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_num_dsp_words_to_num_packed_regs, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +static const struct wmfw_halo_id_hdr cs_dsp_mock_halo_xm_hdr = { + .fw = { + .core_id = cpu_to_be32(WMFW_HALO << 16), + .block_rev = cpu_to_be32(3 << 16), + .vendor_id = cpu_to_be32(0x2), + .id = cpu_to_be32(0xabcdef), + .ver = cpu_to_be32(0x090101), + }, + + /* + * Leave enough space for this header and 40 algorithm descriptors. + * base and size are counted in DSP words. + */ + .xm_base = cpu_to_be32(((sizeof(struct wmfw_halo_id_hdr) + + (40 * sizeof(struct wmfw_halo_alg_hdr))) + / 4) * 3), + .xm_size = cpu_to_be32(0x20), + + /* Allocate a dummy word of YM */ + .ym_base = cpu_to_be32(0), + .ym_size = cpu_to_be32(1), + + .n_algs = 0, +}; + +static const struct wmfw_adsp2_id_hdr cs_dsp_mock_adsp2_xm_hdr = { + .fw = { + .core_id = cpu_to_be32(WMFW_ADSP2 << 16), + .core_rev = cpu_to_be32(2 << 16), + .id = cpu_to_be32(0xabcdef), + .ver = cpu_to_be32(0x090101), + }, + + /* + * Leave enough space for this header and 40 algorithm descriptors. + * base and size are counted in DSP words. + */ + .xm = cpu_to_be32(((sizeof(struct wmfw_adsp2_id_hdr) + + (40 * sizeof(struct wmfw_adsp2_alg_hdr))) + / 4) * 3), + + .ym = cpu_to_be32(0), + .zm = cpu_to_be32(0), + + .n_algs = 0, +}; + +/** + * cs_dsp_mock_xm_header_get_alg_base_in_words() - Algorithm base offset in DSP words. + * + * @priv: Pointer to struct cs_dsp_test. + * @alg_id: Algorithm ID. + * @mem_type: Memory region type. + * + * Lookup an algorithm in the XM header and return the base offset in + * DSP words of the algorithm data in the requested memory region. + * + * Return: Offset in DSP words. + */ +unsigned int cs_dsp_mock_xm_header_get_alg_base_in_words(struct cs_dsp_test *priv, + unsigned int alg_id, + int mem_type) +{ + unsigned int xm = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_XM); + union { + struct wmfw_adsp2_alg_hdr adsp2; + struct wmfw_halo_alg_hdr halo; + } alg; + unsigned int alg_hdr_addr; + unsigned int val, xm_base = 0, ym_base = 0, zm_base = 0; + int ret; + + switch (priv->dsp->type) { + case WMFW_ADSP2: + alg_hdr_addr = xm + (sizeof(struct wmfw_adsp2_id_hdr) / 2); + for (;; alg_hdr_addr += sizeof(alg.adsp2) / 2) { + ret = regmap_read(priv->dsp->regmap, alg_hdr_addr, &val); + KUNIT_ASSERT_GE(priv->test, ret, 0); + KUNIT_ASSERT_NE(priv->test, val, 0xbedead); + ret = regmap_raw_read(priv->dsp->regmap, alg_hdr_addr, + &alg.adsp2, sizeof(alg.adsp2)); + KUNIT_ASSERT_GE(priv->test, ret, 0); + if (be32_to_cpu(alg.adsp2.alg.id) == alg_id) { + xm_base = be32_to_cpu(alg.adsp2.xm); + ym_base = be32_to_cpu(alg.adsp2.ym); + zm_base = be32_to_cpu(alg.adsp2.zm); + break; + } + } + break; + case WMFW_HALO: + alg_hdr_addr = xm + sizeof(struct wmfw_halo_id_hdr); + for (;; alg_hdr_addr += sizeof(alg.halo)) { + ret = regmap_read(priv->dsp->regmap, alg_hdr_addr, &val); + KUNIT_ASSERT_GE(priv->test, ret, 0); + KUNIT_ASSERT_NE(priv->test, val, 0xbedead); + ret = regmap_raw_read(priv->dsp->regmap, alg_hdr_addr, + &alg.halo, sizeof(alg.halo)); + KUNIT_ASSERT_GE(priv->test, ret, 0); + if (be32_to_cpu(alg.halo.alg.id) == alg_id) { + xm_base = be32_to_cpu(alg.halo.xm_base); + ym_base = be32_to_cpu(alg.halo.ym_base); + break; + } + } + break; + default: + KUNIT_FAIL(priv->test, "Unexpected DSP type %d\n", priv->dsp->type); + return 0; + } + + switch (mem_type) { + case WMFW_ADSP2_XM: + case WMFW_HALO_XM_PACKED: + return xm_base; + case WMFW_ADSP2_YM: + case WMFW_HALO_YM_PACKED: + return ym_base; + case WMFW_ADSP2_ZM: + return zm_base; + default: + KUNIT_FAIL(priv->test, "Bad mem_type\n"); + return 0; + } +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_xm_header_get_alg_base_in_words, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_xm_header_get_fw_version_from_regmap() - Firmware version. + * + * @priv: Pointer to struct cs_dsp_test. + * + * Return: Firmware version word value. + */ +unsigned int cs_dsp_mock_xm_header_get_fw_version_from_regmap(struct cs_dsp_test *priv) +{ + unsigned int xm = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_XM); + union { + struct wmfw_id_hdr adsp2; + struct wmfw_v3_id_hdr halo; + } hdr; + + switch (priv->dsp->type) { + case WMFW_ADSP2: + regmap_raw_read(priv->dsp->regmap, xm, &hdr.adsp2, sizeof(hdr.adsp2)); + return be32_to_cpu(hdr.adsp2.ver); + case WMFW_HALO: + regmap_raw_read(priv->dsp->regmap, xm, &hdr.halo, sizeof(hdr.halo)); + return be32_to_cpu(hdr.halo.ver); + default: + KUNIT_FAIL(priv->test, NULL); + return 0; + } +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_xm_header_get_fw_version_from_regmap, + "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_xm_header_get_fw_version() - Firmware version. + * + * @header: Pointer to struct cs_dsp_mock_xm_header. + * + * Return: Firmware version word value. + */ +unsigned int cs_dsp_mock_xm_header_get_fw_version(struct cs_dsp_mock_xm_header *header) +{ + const struct wmfw_id_hdr *adsp2_hdr; + const struct wmfw_v3_id_hdr *halo_hdr; + + switch (header->test_priv->dsp->type) { + case WMFW_ADSP2: + adsp2_hdr = header->blob_data; + return be32_to_cpu(adsp2_hdr->ver); + case WMFW_HALO: + halo_hdr = header->blob_data; + return be32_to_cpu(halo_hdr->ver); + default: + KUNIT_FAIL(header->test_priv->test, NULL); + return 0; + } +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_xm_header_get_fw_version, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_xm_header_drop_from_regmap_cache() - Drop XM header from regmap cache. + * + * @priv: Pointer to struct cs_dsp_test. + */ +void cs_dsp_mock_xm_header_drop_from_regmap_cache(struct cs_dsp_test *priv) +{ + unsigned int xm = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_XM); + unsigned int bytes; + __be32 num_algs_be32; + unsigned int num_algs; + + switch (priv->dsp->type) { + case WMFW_ADSP2: + /* + * Could be one 32-bit register or two 16-bit registers. + * A raw read will read the requested number of bytes. + */ + regmap_raw_read(priv->dsp->regmap, + xm + (offsetof(struct wmfw_adsp2_id_hdr, n_algs) / 2), + &num_algs_be32, sizeof(num_algs_be32)); + num_algs = be32_to_cpu(num_algs_be32); + bytes = sizeof(struct wmfw_adsp2_id_hdr) + + (num_algs * sizeof(struct wmfw_adsp2_alg_hdr)) + + 4 /* terminator word */; + + regcache_drop_region(priv->dsp->regmap, xm, xm + (bytes / 2) - 1); + break; + case WMFW_HALO: + regmap_read(priv->dsp->regmap, + xm + offsetof(struct wmfw_halo_id_hdr, n_algs), + &num_algs); + bytes = sizeof(struct wmfw_halo_id_hdr) + + (num_algs * sizeof(struct wmfw_halo_alg_hdr)) + + 4 /* terminator word */; + + regcache_drop_region(priv->dsp->regmap, xm, xm + bytes - 4); + break; + default: + break; + } +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_xm_header_drop_from_regmap_cache, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +static void cs_dsp_mock_xm_header_add_adsp2_algs(struct cs_dsp_mock_xm_header *builder, + const struct cs_dsp_mock_alg_def *algs, + size_t num_algs) +{ + struct wmfw_adsp2_id_hdr *hdr = builder->blob_data; + unsigned int next_free_xm_word, next_free_ym_word, next_free_zm_word; + + next_free_xm_word = be32_to_cpu(hdr->xm); + next_free_ym_word = be32_to_cpu(hdr->ym); + next_free_zm_word = be32_to_cpu(hdr->zm); + + /* Set num_algs in XM header. */ + hdr->n_algs = cpu_to_be32(num_algs); + + /* Create algorithm descriptor list */ + struct wmfw_adsp2_alg_hdr *alg_info = + (struct wmfw_adsp2_alg_hdr *)(&hdr[1]); + + for (; num_algs > 0; num_algs--, algs++, alg_info++) { + unsigned int alg_xm_last, alg_ym_last, alg_zm_last; + + alg_info->alg.id = cpu_to_be32(algs->id); + alg_info->alg.ver = cpu_to_be32(algs->ver); + alg_info->xm = cpu_to_be32(algs->xm_base_words); + alg_info->ym = cpu_to_be32(algs->ym_base_words); + alg_info->zm = cpu_to_be32(algs->zm_base_words); + + /* Check if we need to auto-allocate base addresses */ + if (!alg_info->xm && algs->xm_size_words) + alg_info->xm = cpu_to_be32(next_free_xm_word); + + if (!alg_info->ym && algs->ym_size_words) + alg_info->ym = cpu_to_be32(next_free_ym_word); + + if (!alg_info->zm && algs->zm_size_words) + alg_info->zm = cpu_to_be32(next_free_zm_word); + + alg_xm_last = be32_to_cpu(alg_info->xm) + algs->xm_size_words - 1; + if (alg_xm_last > next_free_xm_word) + next_free_xm_word = alg_xm_last; + + alg_ym_last = be32_to_cpu(alg_info->ym) + algs->ym_size_words - 1; + if (alg_ym_last > next_free_ym_word) + next_free_ym_word = alg_ym_last; + + alg_zm_last = be32_to_cpu(alg_info->zm) + algs->zm_size_words - 1; + if (alg_zm_last > next_free_zm_word) + next_free_zm_word = alg_zm_last; + } + + /* Write list terminator */ + *(__be32 *)(alg_info) = cpu_to_be32(0xbedead); +} + +static void cs_dsp_mock_xm_header_add_halo_algs(struct cs_dsp_mock_xm_header *builder, + const struct cs_dsp_mock_alg_def *algs, + size_t num_algs) +{ + struct wmfw_halo_id_hdr *hdr = builder->blob_data; + unsigned int next_free_xm_word, next_free_ym_word; + + /* Assume we're starting with bare header */ + next_free_xm_word = be32_to_cpu(hdr->xm_base) + be32_to_cpu(hdr->xm_size) - 1; + next_free_ym_word = be32_to_cpu(hdr->ym_base) + be32_to_cpu(hdr->ym_size) - 1; + + /* Set num_algs in XM header */ + hdr->n_algs = cpu_to_be32(num_algs); + + /* Create algorithm descriptor list */ + struct wmfw_halo_alg_hdr *alg_info = + (struct wmfw_halo_alg_hdr *)(&hdr[1]); + + for (; num_algs > 0; num_algs--, algs++, alg_info++) { + unsigned int alg_xm_last, alg_ym_last; + + alg_info->alg.id = cpu_to_be32(algs->id); + alg_info->alg.ver = cpu_to_be32(algs->ver); + alg_info->xm_base = cpu_to_be32(algs->xm_base_words); + alg_info->xm_size = cpu_to_be32(algs->xm_size_words); + alg_info->ym_base = cpu_to_be32(algs->ym_base_words); + alg_info->ym_size = cpu_to_be32(algs->ym_size_words); + + /* Check if we need to auto-allocate base addresses */ + if (!alg_info->xm_base && alg_info->xm_size) + alg_info->xm_base = cpu_to_be32(next_free_xm_word); + + if (!alg_info->ym_base && alg_info->ym_size) + alg_info->ym_base = cpu_to_be32(next_free_ym_word); + + alg_xm_last = be32_to_cpu(alg_info->xm_base) + be32_to_cpu(alg_info->xm_size) - 1; + if (alg_xm_last > next_free_xm_word) + next_free_xm_word = alg_xm_last; + + alg_ym_last = be32_to_cpu(alg_info->ym_base) + be32_to_cpu(alg_info->ym_size) - 1; + if (alg_ym_last > next_free_ym_word) + next_free_ym_word = alg_ym_last; + } + + /* Write list terminator */ + *(__be32 *)(alg_info) = cpu_to_be32(0xbedead); +} + +/** + * cs_dsp_mock_xm_header_write_to_regmap() - Write XM header to regmap. + * + * @header: Pointer to struct cs_dsp_mock_xm_header. + * + * The data in header is written to the XM addresses in the regmap. + * + * Return: 0 on success, else negative error code. + */ +int cs_dsp_mock_xm_header_write_to_regmap(struct cs_dsp_mock_xm_header *header) +{ + struct cs_dsp_test *priv = header->test_priv; + unsigned int reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_XM); + + /* + * One 32-bit word corresponds to one 32-bit unpacked XM word so the + * blob can be written directly to the regmap. + */ + return regmap_raw_write(priv->dsp->regmap, reg_addr, + header->blob_data, header->blob_size_bytes); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_xm_header_write_to_regmap, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_create_mock_xm_header() - Create a dummy XM header. + * + * @priv: Pointer to struct cs_dsp_test. + * @algs: Pointer to array of struct cs_dsp_mock_alg_def listing the + * dummy algorithm entries to include in the XM header. + * @num_algs: Number of entries in the algs array. + * + * Return: Pointer to created struct cs_dsp_mock_xm_header. + */ +struct cs_dsp_mock_xm_header *cs_dsp_create_mock_xm_header(struct cs_dsp_test *priv, + const struct cs_dsp_mock_alg_def *algs, + size_t num_algs) +{ + struct cs_dsp_mock_xm_header *builder; + size_t total_bytes_required; + const void *header; + size_t header_size_bytes; + + builder = kunit_kzalloc(priv->test, sizeof(*builder), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(priv->test, builder); + builder->test_priv = priv; + + switch (priv->dsp->type) { + case WMFW_ADSP2: + header = &cs_dsp_mock_adsp2_xm_hdr; + header_size_bytes = sizeof(cs_dsp_mock_adsp2_xm_hdr); + total_bytes_required = header_size_bytes + + (num_algs * sizeof(struct wmfw_adsp2_alg_hdr)) + + 4; /* terminator word */ + break; + case WMFW_HALO: + header = &cs_dsp_mock_halo_xm_hdr, + header_size_bytes = sizeof(cs_dsp_mock_halo_xm_hdr); + total_bytes_required = header_size_bytes + + (num_algs * sizeof(struct wmfw_halo_alg_hdr)) + + 4; /* terminator word */ + break; + default: + KUNIT_FAIL(priv->test, "%s unexpected DSP type %d\n", + __func__, priv->dsp->type); + return NULL; + } + + builder->blob_data = kunit_kzalloc(priv->test, total_bytes_required, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(priv->test, builder->blob_data); + builder->blob_size_bytes = total_bytes_required; + + memcpy(builder->blob_data, header, header_size_bytes); + + switch (priv->dsp->type) { + case WMFW_ADSP2: + cs_dsp_mock_xm_header_add_adsp2_algs(builder, algs, num_algs); + break; + case WMFW_HALO: + cs_dsp_mock_xm_header_add_halo_algs(builder, algs, num_algs); + break; + default: + break; + } + + return builder; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_create_mock_xm_header, "FW_CS_DSP_KUNIT_TEST_UTILS"); diff --git a/drivers/firmware/cirrus/test/cs_dsp_mock_regmap.c b/drivers/firmware/cirrus/test/cs_dsp_mock_regmap.c new file mode 100644 index 000000000000..fb8e4a5d189a --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_mock_regmap.c @@ -0,0 +1,367 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// Mock regmap for cs_dsp KUnit tests. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include +#include +#include +#include +#include + +static int cs_dsp_mock_regmap_read(void *context, const void *reg_buf, + const size_t reg_size, void *val_buf, + size_t val_size) +{ + struct cs_dsp_test *priv = context; + + /* Should never get here because the regmap is cache-only */ + KUNIT_FAIL(priv->test, "Unexpected bus read @%#x", *(u32 *)reg_buf); + + return -EIO; +} + +static int cs_dsp_mock_regmap_gather_write(void *context, + const void *reg_buf, size_t reg_size, + const void *val_buf, size_t val_size) +{ + struct cs_dsp_test *priv = context; + + priv->saw_bus_write = true; + + /* Should never get here because the regmap is cache-only */ + KUNIT_FAIL(priv->test, "Unexpected bus gather_write @%#x", *(u32 *)reg_buf); + + return -EIO; +} + +static int cs_dsp_mock_regmap_write(void *context, const void *val_buf, size_t val_size) +{ + struct cs_dsp_test *priv = context; + + priv->saw_bus_write = true; + + /* Should never get here because the regmap is cache-only */ + KUNIT_FAIL(priv->test, "Unexpected bus write @%#x", *(u32 *)val_buf); + + return -EIO; +} + +static const struct regmap_bus cs_dsp_mock_regmap_bus = { + .read = cs_dsp_mock_regmap_read, + .write = cs_dsp_mock_regmap_write, + .gather_write = cs_dsp_mock_regmap_gather_write, + .reg_format_endian_default = REGMAP_ENDIAN_LITTLE, + .val_format_endian_default = REGMAP_ENDIAN_LITTLE, +}; + +static const struct reg_default adsp2_32bit_register_defaults[] = { + { 0xffe00, 0x0000 }, /* CONTROL */ + { 0xffe02, 0x0000 }, /* CLOCKING */ + { 0xffe04, 0x0001 }, /* STATUS1: RAM_RDY=1 */ + { 0xffe30, 0x0000 }, /* WDMW_CONFIG_1 */ + { 0xffe32, 0x0000 }, /* WDMA_CONFIG_2 */ + { 0xffe34, 0x0000 }, /* RDMA_CONFIG_1 */ + { 0xffe40, 0x0000 }, /* SCRATCH_0_1 */ + { 0xffe42, 0x0000 }, /* SCRATCH_2_3 */ +}; + +static const struct regmap_range adsp2_32bit_registers[] = { + regmap_reg_range(0x80000, 0x88ffe), /* PM */ + regmap_reg_range(0xa0000, 0xa9ffe), /* XM */ + regmap_reg_range(0xc0000, 0xc1ffe), /* YM */ + regmap_reg_range(0xe0000, 0xe1ffe), /* ZM */ + regmap_reg_range(0xffe00, 0xffe7c), /* CORE CTRL */ +}; + +const unsigned int cs_dsp_mock_adsp2_32bit_sysbase = 0xffe00; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_adsp2_32bit_sysbase, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +static const struct regmap_access_table adsp2_32bit_rw = { + .yes_ranges = adsp2_32bit_registers, + .n_yes_ranges = ARRAY_SIZE(adsp2_32bit_registers), +}; + +static const struct regmap_config cs_dsp_mock_regmap_adsp2_32bit = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 2, + .reg_format_endian = REGMAP_ENDIAN_LITTLE, + .val_format_endian = REGMAP_ENDIAN_BIG, + .wr_table = &adsp2_32bit_rw, + .rd_table = &adsp2_32bit_rw, + .max_register = 0xffe7c, + .reg_defaults = adsp2_32bit_register_defaults, + .num_reg_defaults = ARRAY_SIZE(adsp2_32bit_register_defaults), + .cache_type = REGCACHE_MAPLE, +}; + +static const struct reg_default adsp2_16bit_register_defaults[] = { + { 0x1100, 0x0000 }, /* CONTROL */ + { 0x1101, 0x0000 }, /* CLOCKING */ + { 0x1104, 0x0001 }, /* STATUS1: RAM_RDY=1 */ + { 0x1130, 0x0000 }, /* WDMW_CONFIG_1 */ + { 0x1131, 0x0000 }, /* WDMA_CONFIG_2 */ + { 0x1134, 0x0000 }, /* RDMA_CONFIG_1 */ + { 0x1140, 0x0000 }, /* SCRATCH_0 */ + { 0x1141, 0x0000 }, /* SCRATCH_1 */ + { 0x1142, 0x0000 }, /* SCRATCH_2 */ + { 0x1143, 0x0000 }, /* SCRATCH_3 */ +}; + +static const struct regmap_range adsp2_16bit_registers[] = { + regmap_reg_range(0x001100, 0x001143), /* CORE CTRL */ + regmap_reg_range(0x100000, 0x105fff), /* PM */ + regmap_reg_range(0x180000, 0x1807ff), /* ZM */ + regmap_reg_range(0x190000, 0x1947ff), /* XM */ + regmap_reg_range(0x1a8000, 0x1a97ff), /* YM */ +}; + +const unsigned int cs_dsp_mock_adsp2_16bit_sysbase = 0x001100; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_adsp2_16bit_sysbase, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +static const struct regmap_access_table adsp2_16bit_rw = { + .yes_ranges = adsp2_16bit_registers, + .n_yes_ranges = ARRAY_SIZE(adsp2_16bit_registers), +}; + +static const struct regmap_config cs_dsp_mock_regmap_adsp2_16bit = { + .reg_bits = 32, + .val_bits = 16, + .reg_stride = 1, + .reg_format_endian = REGMAP_ENDIAN_LITTLE, + .val_format_endian = REGMAP_ENDIAN_BIG, + .wr_table = &adsp2_16bit_rw, + .rd_table = &adsp2_16bit_rw, + .max_register = 0x1a97ff, + .reg_defaults = adsp2_16bit_register_defaults, + .num_reg_defaults = ARRAY_SIZE(adsp2_16bit_register_defaults), + .cache_type = REGCACHE_MAPLE, +}; + +static const struct reg_default halo_register_defaults[] = { + /* CORE */ + { 0x2b80010, 0 }, /* HALO_CORE_SOFT_RESET */ + { 0x2b805c0, 0 }, /* HALO_SCRATCH1 */ + { 0x2b805c8, 0 }, /* HALO_SCRATCH2 */ + { 0x2b805d0, 0 }, /* HALO_SCRATCH3 */ + { 0x2b805c8, 0 }, /* HALO_SCRATCH4 */ + { 0x2bc1000, 0 }, /* HALO_CCM_CORE_CONTROL */ + { 0x2bc7000, 0 }, /* HALO_WDT_CONTROL */ + + /* SYSINFO */ + { 0x25e2040, 0 }, /* HALO_AHBM_WINDOW_DEBUG_0 */ + { 0x25e2044, 0 }, /* HALO_AHBM_WINDOW_DEBUG_1 */ +}; + +static const struct regmap_range halo_readable_registers[] = { + regmap_reg_range(0x2000000, 0x2005fff), /* XM_PACKED */ + regmap_reg_range(0x25e0000, 0x25e004f), /* SYSINFO */ + regmap_reg_range(0x25e2000, 0x25e2047), /* SYSINFO */ + regmap_reg_range(0x2800000, 0x2807fff), /* XM */ + regmap_reg_range(0x2b80000, 0x2bc700b), /* CORE CTRL */ + regmap_reg_range(0x2c00000, 0x2c047f3), /* YM_PACKED */ + regmap_reg_range(0x3400000, 0x3405ff7), /* YM */ + regmap_reg_range(0x3800000, 0x3804fff), /* PM_PACKED */ +}; + +static const struct regmap_range halo_writeable_registers[] = { + regmap_reg_range(0x2000000, 0x2005fff), /* XM_PACKED */ + regmap_reg_range(0x2800000, 0x2807fff), /* XM */ + regmap_reg_range(0x2b80000, 0x2bc700b), /* CORE CTRL */ + regmap_reg_range(0x2c00000, 0x2c047f3), /* YM_PACKED */ + regmap_reg_range(0x3400000, 0x3405ff7), /* YM */ + regmap_reg_range(0x3800000, 0x3804fff), /* PM_PACKED */ +}; + +const unsigned int cs_dsp_mock_halo_core_base = 0x2b80000; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_halo_core_base, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +const unsigned int cs_dsp_mock_halo_sysinfo_base = 0x25e0000; +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_halo_sysinfo_base, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +static const struct regmap_access_table halo_readable = { + .yes_ranges = halo_readable_registers, + .n_yes_ranges = ARRAY_SIZE(halo_readable_registers), +}; + +static const struct regmap_access_table halo_writeable = { + .yes_ranges = halo_writeable_registers, + .n_yes_ranges = ARRAY_SIZE(halo_writeable_registers), +}; + +static const struct regmap_config cs_dsp_mock_regmap_halo = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + .reg_format_endian = REGMAP_ENDIAN_LITTLE, + .val_format_endian = REGMAP_ENDIAN_BIG, + .wr_table = &halo_writeable, + .rd_table = &halo_readable, + .max_register = 0x3804ffc, + .reg_defaults = halo_register_defaults, + .num_reg_defaults = ARRAY_SIZE(halo_register_defaults), + .cache_type = REGCACHE_MAPLE, +}; + +/** + * cs_dsp_mock_regmap_drop_range() - drop a range of registers from the cache. + * + * @priv: Pointer to struct cs_dsp_test object. + * @first_reg: Address of first register to drop. + * @last_reg: Address of last register to drop. + */ +void cs_dsp_mock_regmap_drop_range(struct cs_dsp_test *priv, + unsigned int first_reg, unsigned int last_reg) +{ + regcache_drop_region(priv->dsp->regmap, first_reg, last_reg); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_regmap_drop_range, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_regmap_drop_regs() - drop a number of registers from the cache. + * + * @priv: Pointer to struct cs_dsp_test object. + * @first_reg: Address of first register to drop. + * @num_regs: Number of registers to drop. + */ +void cs_dsp_mock_regmap_drop_regs(struct cs_dsp_test *priv, + unsigned int first_reg, size_t num_regs) +{ + int stride = regmap_get_reg_stride(priv->dsp->regmap); + unsigned int last = first_reg + (stride * (num_regs - 1)); + + cs_dsp_mock_regmap_drop_range(priv, first_reg, last); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_regmap_drop_regs, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_regmap_drop_bytes() - drop a number of bytes from the cache. + * + * @priv: Pointer to struct cs_dsp_test object. + * @first_reg: Address of first register to drop. + * @num_bytes: Number of bytes to drop from the cache. Will be rounded + * down to a whole number of registers. Trailing bytes that + * are not a multiple of the register size will not be dropped. + * (This is intended to help detect math errors in test code.) + */ +void cs_dsp_mock_regmap_drop_bytes(struct cs_dsp_test *priv, + unsigned int first_reg, size_t num_bytes) +{ + size_t num_regs = num_bytes / regmap_get_val_bytes(priv->dsp->regmap); + + cs_dsp_mock_regmap_drop_regs(priv, first_reg, num_regs); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_regmap_drop_bytes, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_regmap_drop_system_regs() - Drop DSP system registers from the cache. + * + * @priv: Pointer to struct cs_dsp_test object. + * + * Drops all DSP system registers from the regmap cache. + */ +void cs_dsp_mock_regmap_drop_system_regs(struct cs_dsp_test *priv) +{ + switch (priv->dsp->type) { + case WMFW_ADSP2: + if (priv->dsp->base) { + regcache_drop_region(priv->dsp->regmap, + priv->dsp->base, + priv->dsp->base + 0x7c); + } + return; + case WMFW_HALO: + if (priv->dsp->base) { + regcache_drop_region(priv->dsp->regmap, + priv->dsp->base, + priv->dsp->base + 0x47000); + } + + /* sysinfo registers are read-only so don't drop them */ + return; + default: + return; + } +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_regmap_drop_system_regs, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_regmap_is_dirty() - Test for dirty registers in the cache. + * + * @priv: Pointer to struct cs_dsp_test object. + * @drop_system_regs: If true the DSP system regs will be dropped from + * the cache before checking for dirty. + * + * All registers that are expected to be written must have been dropped + * from the cache (DSP system registers can be dropped by passing + * drop_system_regs == true). If any unexpected registers were written + * there will still be dirty entries in the cache and a cache sync will + * cause a write. + * + * Returns: true if there were dirty entries, false if not. + */ +bool cs_dsp_mock_regmap_is_dirty(struct cs_dsp_test *priv, bool drop_system_regs) +{ + if (drop_system_regs) + cs_dsp_mock_regmap_drop_system_regs(priv); + + priv->saw_bus_write = false; + regcache_cache_only(priv->dsp->regmap, false); + regcache_sync(priv->dsp->regmap); + regcache_cache_only(priv->dsp->regmap, true); + + return priv->saw_bus_write; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_regmap_is_dirty, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_regmap_init() - Initialize a mock regmap. + * + * @priv: Pointer to struct cs_dsp_test object. This must have a + * valid pointer to a struct cs_dsp in which the type and + * rev fields are set to the type of DSP to be simulated. + * + * On success the priv->dsp->regmap will point to the created + * regmap instance. + * + * Return: zero on success, else negative error code. + */ +int cs_dsp_mock_regmap_init(struct cs_dsp_test *priv) +{ + const struct regmap_config *config; + int ret; + + switch (priv->dsp->type) { + case WMFW_HALO: + config = &cs_dsp_mock_regmap_halo; + break; + case WMFW_ADSP2: + if (priv->dsp->rev == 0) + config = &cs_dsp_mock_regmap_adsp2_16bit; + else + config = &cs_dsp_mock_regmap_adsp2_32bit; + break; + default: + config = NULL; + break; + } + + priv->dsp->regmap = devm_regmap_init(priv->dsp->dev, + &cs_dsp_mock_regmap_bus, + priv, + config); + if (IS_ERR(priv->dsp->regmap)) { + ret = PTR_ERR(priv->dsp->regmap); + kunit_err(priv->test, "Failed to allocate register map: %d\n", ret); + return ret; + } + + /* Put regmap in cache-only so it accumulates the writes done by cs_dsp */ + regcache_cache_only(priv->dsp->regmap, true); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_regmap_init, "FW_CS_DSP_KUNIT_TEST_UTILS"); diff --git a/drivers/firmware/cirrus/test/cs_dsp_mock_utils.c b/drivers/firmware/cirrus/test/cs_dsp_mock_utils.c new file mode 100644 index 000000000000..cbd0bf72b7de --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_mock_utils.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// Utility module for cs_dsp KUnit testing. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include + +MODULE_DESCRIPTION("Utilities for Cirrus Logic DSP driver testing"); +MODULE_AUTHOR("Richard Fitzgerald "); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS("FW_CS_DSP"); diff --git a/drivers/firmware/cirrus/test/cs_dsp_mock_wmfw.c b/drivers/firmware/cirrus/test/cs_dsp_mock_wmfw.c new file mode 100644 index 000000000000..5a3ac03ac37f --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_mock_wmfw.c @@ -0,0 +1,473 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// wmfw file builder for cs_dsp KUnit tests. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Buffer large enough for bin file content */ +#define CS_DSP_MOCK_WMFW_BUF_SIZE 131072 + +struct cs_dsp_mock_wmfw_builder { + struct cs_dsp_test *test_priv; + int format_version; + void *buf; + size_t buf_size_bytes; + void *write_p; + size_t bytes_used; + + void *alg_data_header; + unsigned int num_coeffs; +}; + +struct wmfw_adsp2_halo_header { + struct wmfw_header header; + struct wmfw_adsp2_sizes sizes; + struct wmfw_footer footer; +} __packed; + +struct wmfw_long_string { + __le16 len; + u8 data[] __nonstring __counted_by(len); +} __packed; + +struct wmfw_short_string { + u8 len; + u8 data[] __nonstring __counted_by(len); +} __packed; + +KUNIT_DEFINE_ACTION_WRAPPER(vfree_action_wrapper, vfree, void *) + +/** + * cs_dsp_mock_wmfw_format_version() - Return format version. + * + * @builder: Pointer to struct cs_dsp_mock_wmfw_builder. + * + * Return: Format version. + */ +int cs_dsp_mock_wmfw_format_version(struct cs_dsp_mock_wmfw_builder *builder) +{ + return builder->format_version; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_wmfw_format_version, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_wmfw_get_firmware() - Get struct firmware wrapper for data. + * + * @builder: Pointer to struct cs_dsp_mock_wmfw_builder. + * + * Return: Pointer to a struct firmware wrapper for the data. + */ +struct firmware *cs_dsp_mock_wmfw_get_firmware(struct cs_dsp_mock_wmfw_builder *builder) +{ + struct firmware *fw; + + if (!builder) + return NULL; + + fw = kunit_kzalloc(builder->test_priv->test, sizeof(*fw), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(builder->test_priv->test, fw); + + fw->data = builder->buf; + fw->size = builder->bytes_used; + + return fw; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_wmfw_get_firmware, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_wmfw_add_raw_block() - Add a block to the wmfw file. + * + * @builder: Pointer to struct cs_dsp_mock_bin_builder. + * @block_type: Block type. + * @offset: Offset. + * @payload_data: Pointer to buffer containing the payload data, + * or NULL if no data. + * @payload_len_bytes: Length of payload data in bytes, or zero. + */ +void cs_dsp_mock_wmfw_add_raw_block(struct cs_dsp_mock_wmfw_builder *builder, + int block_type, unsigned int offset, + const void *payload_data, size_t payload_len_bytes) +{ + struct wmfw_region *header = builder->write_p; + unsigned int bytes_needed = struct_size_t(struct wmfw_region, data, payload_len_bytes); + + KUNIT_ASSERT_TRUE(builder->test_priv->test, + (builder->write_p + bytes_needed) < + (builder->buf + CS_DSP_MOCK_WMFW_BUF_SIZE)); + + header->offset = cpu_to_le32(offset | (block_type << 24)); + header->len = cpu_to_le32(payload_len_bytes); + if (payload_len_bytes > 0) + memcpy(header->data, payload_data, payload_len_bytes); + + builder->write_p += bytes_needed; + builder->bytes_used += bytes_needed; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_wmfw_add_raw_block, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_wmfw_add_info() - Add an info block to the wmfw file. + * + * @builder: Pointer to struct cs_dsp_mock_bin_builder. + * @info: Pointer to info string to be copied into the file. + * + * The string will be padded to a length that is a multiple of 4 bytes. + */ +void cs_dsp_mock_wmfw_add_info(struct cs_dsp_mock_wmfw_builder *builder, + const char *info) +{ + size_t info_len = strlen(info); + char *tmp = NULL; + + if (info_len % 4) { + /* Create a padded string with length a multiple of 4 */ + info_len = round_up(info_len, 4); + tmp = kunit_kzalloc(builder->test_priv->test, info_len, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(builder->test_priv->test, tmp); + memcpy(tmp, info, info_len); + info = tmp; + } + + cs_dsp_mock_wmfw_add_raw_block(builder, WMFW_INFO_TEXT, 0, info, info_len); + kunit_kfree(builder->test_priv->test, tmp); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_wmfw_add_info, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +/** + * cs_dsp_mock_wmfw_add_data_block() - Add a data block to the wmfw file. + * + * @builder: Pointer to struct cs_dsp_mock_bin_builder. + * @mem_region: Memory region for the block. + * @mem_offset_dsp_words: Offset to start of destination in DSP words. + * @payload_data: Pointer to buffer containing the payload data. + * @payload_len_bytes: Length of payload data in bytes. + */ +void cs_dsp_mock_wmfw_add_data_block(struct cs_dsp_mock_wmfw_builder *builder, + int mem_region, unsigned int mem_offset_dsp_words, + const void *payload_data, size_t payload_len_bytes) +{ + /* Blob payload length must be a multiple of 4 */ + KUNIT_ASSERT_EQ(builder->test_priv->test, payload_len_bytes % 4, 0); + + cs_dsp_mock_wmfw_add_raw_block(builder, mem_region, mem_offset_dsp_words, + payload_data, payload_len_bytes); +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_wmfw_add_data_block, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +void cs_dsp_mock_wmfw_start_alg_info_block(struct cs_dsp_mock_wmfw_builder *builder, + unsigned int alg_id, + const char *name, + const char *description) +{ + struct wmfw_region *rgn = builder->write_p; + struct wmfw_adsp_alg_data *v1; + struct wmfw_short_string *shortstring; + struct wmfw_long_string *longstring; + size_t bytes_needed, name_len, description_len; + int offset; + + /* Bytes needed for region header */ + bytes_needed = offsetof(struct wmfw_region, data); + + builder->alg_data_header = builder->write_p; + builder->num_coeffs = 0; + + switch (builder->format_version) { + case 0: + KUNIT_FAIL(builder->test_priv->test, "wmfwV0 does not have alg blocks\n"); + return; + case 1: + bytes_needed += offsetof(struct wmfw_adsp_alg_data, data); + KUNIT_ASSERT_TRUE(builder->test_priv->test, + (builder->write_p + bytes_needed) < + (builder->buf + CS_DSP_MOCK_WMFW_BUF_SIZE)); + + memset(builder->write_p, 0, bytes_needed); + + /* Create region header */ + rgn->offset = cpu_to_le32(WMFW_ALGORITHM_DATA << 24); + + /* Create algorithm entry */ + v1 = (struct wmfw_adsp_alg_data *)&rgn->data[0]; + v1->id = cpu_to_le32(alg_id); + if (name) + strscpy(v1->name, name, sizeof(v1->name)); + + if (description) + strscpy(v1->descr, description, sizeof(v1->descr)); + break; + default: + name_len = 0; + description_len = 0; + + if (name) + name_len = strlen(name); + + if (description) + description_len = strlen(description); + + bytes_needed += sizeof(__le32); /* alg id */ + bytes_needed += round_up(name_len + sizeof(u8), sizeof(__le32)); + bytes_needed += round_up(description_len + sizeof(__le16), sizeof(__le32)); + bytes_needed += sizeof(__le32); /* coeff count */ + + KUNIT_ASSERT_TRUE(builder->test_priv->test, + (builder->write_p + bytes_needed) < + (builder->buf + CS_DSP_MOCK_WMFW_BUF_SIZE)); + + memset(builder->write_p, 0, bytes_needed); + + /* Create region header */ + rgn->offset = cpu_to_le32(WMFW_ALGORITHM_DATA << 24); + + /* Create algorithm entry */ + *(__force __le32 *)&rgn->data[0] = cpu_to_le32(alg_id); + + shortstring = (struct wmfw_short_string *)&rgn->data[4]; + shortstring->len = name_len; + + if (name_len) + memcpy(shortstring->data, name, name_len); + + /* Round up to next __le32 */ + offset = round_up(4 + struct_size_t(struct wmfw_short_string, data, name_len), + sizeof(__le32)); + + longstring = (struct wmfw_long_string *)&rgn->data[offset]; + longstring->len = cpu_to_le16(description_len); + + if (description_len) + memcpy(longstring->data, description, description_len); + break; + } + + builder->write_p += bytes_needed; + builder->bytes_used += bytes_needed; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_wmfw_start_alg_info_block, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +void cs_dsp_mock_wmfw_add_coeff_desc(struct cs_dsp_mock_wmfw_builder *builder, + const struct cs_dsp_mock_coeff_def *def) +{ + struct wmfw_adsp_coeff_data *v1; + struct wmfw_short_string *shortstring; + struct wmfw_long_string *longstring; + size_t bytes_needed, shortname_len, fullname_len, description_len; + __le32 *ple32; + + KUNIT_ASSERT_NOT_NULL(builder->test_priv->test, builder->alg_data_header); + + switch (builder->format_version) { + case 0: + return; + case 1: + bytes_needed = offsetof(struct wmfw_adsp_coeff_data, data); + KUNIT_ASSERT_TRUE(builder->test_priv->test, + (builder->write_p + bytes_needed) < + (builder->buf + CS_DSP_MOCK_WMFW_BUF_SIZE)); + + v1 = (struct wmfw_adsp_coeff_data *)builder->write_p; + memset(v1, 0, sizeof(*v1)); + v1->hdr.offset = cpu_to_le16(def->offset_dsp_words); + v1->hdr.type = cpu_to_le16(def->mem_type); + v1->hdr.size = cpu_to_le32(bytes_needed - sizeof(v1->hdr)); + v1->ctl_type = cpu_to_le16(def->type); + v1->flags = cpu_to_le16(def->flags); + v1->len = cpu_to_le32(def->length_bytes); + + if (def->fullname) + strscpy(v1->name, def->fullname, sizeof(v1->name)); + + if (def->description) + strscpy(v1->descr, def->description, sizeof(v1->descr)); + break; + default: + fullname_len = 0; + description_len = 0; + shortname_len = strlen(def->shortname); + + if (def->fullname) + fullname_len = strlen(def->fullname); + + if (def->description) + description_len = strlen(def->description); + + bytes_needed = sizeof(__le32) * 2; /* type, offset and size */ + bytes_needed += round_up(shortname_len + sizeof(u8), sizeof(__le32)); + bytes_needed += round_up(fullname_len + sizeof(u8), sizeof(__le32)); + bytes_needed += round_up(description_len + sizeof(__le16), sizeof(__le32)); + bytes_needed += sizeof(__le32) * 2; /* flags, type and length */ + KUNIT_ASSERT_TRUE(builder->test_priv->test, + (builder->write_p + bytes_needed) < + (builder->buf + CS_DSP_MOCK_WMFW_BUF_SIZE)); + + ple32 = (__force __le32 *)builder->write_p; + *ple32++ = cpu_to_le32(def->offset_dsp_words | (def->mem_type << 16)); + *ple32++ = cpu_to_le32(bytes_needed - sizeof(__le32) - sizeof(__le32)); + + shortstring = (__force struct wmfw_short_string *)ple32; + shortstring->len = shortname_len; + memcpy(shortstring->data, def->shortname, shortname_len); + + /* Round up to next __le32 multiple */ + ple32 += round_up(struct_size_t(struct wmfw_short_string, data, shortname_len), + sizeof(*ple32)) / sizeof(*ple32); + + shortstring = (__force struct wmfw_short_string *)ple32; + shortstring->len = fullname_len; + memcpy(shortstring->data, def->fullname, fullname_len); + + /* Round up to next __le32 multiple */ + ple32 += round_up(struct_size_t(struct wmfw_short_string, data, fullname_len), + sizeof(*ple32)) / sizeof(*ple32); + + longstring = (__force struct wmfw_long_string *)ple32; + longstring->len = cpu_to_le16(description_len); + memcpy(longstring->data, def->description, description_len); + + /* Round up to next __le32 multiple */ + ple32 += round_up(struct_size_t(struct wmfw_long_string, data, description_len), + sizeof(*ple32)) / sizeof(*ple32); + + *ple32++ = cpu_to_le32(def->type | (def->flags << 16)); + *ple32 = cpu_to_le32(def->length_bytes); + break; + } + + builder->write_p += bytes_needed; + builder->bytes_used += bytes_needed; + builder->num_coeffs++; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_wmfw_add_coeff_desc, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +void cs_dsp_mock_wmfw_end_alg_info_block(struct cs_dsp_mock_wmfw_builder *builder) +{ + struct wmfw_region *rgn = builder->alg_data_header; + struct wmfw_adsp_alg_data *v1; + const struct wmfw_short_string *shortstring; + const struct wmfw_long_string *longstring; + size_t offset; + + KUNIT_ASSERT_NOT_NULL(builder->test_priv->test, rgn); + + /* Fill in data size */ + rgn->len = cpu_to_le32((u8 *)builder->write_p - (u8 *)rgn->data); + + /* Fill in coefficient count */ + switch (builder->format_version) { + case 0: + return; + case 1: + v1 = (struct wmfw_adsp_alg_data *)&rgn->data[0]; + v1->ncoeff = cpu_to_le32(builder->num_coeffs); + break; + default: + offset = 4; /* skip alg id */ + + /* Get name length and round up to __le32 multiple */ + shortstring = (const struct wmfw_short_string *)&rgn->data[offset]; + offset += round_up(struct_size_t(struct wmfw_short_string, data, shortstring->len), + sizeof(__le32)); + + /* Get description length and round up to __le32 multiple */ + longstring = (const struct wmfw_long_string *)&rgn->data[offset]; + offset += round_up(struct_size_t(struct wmfw_long_string, data, + le16_to_cpu(longstring->len)), + sizeof(__le32)); + + *(__force __le32 *)&rgn->data[offset] = cpu_to_le32(builder->num_coeffs); + break; + } + + builder->alg_data_header = NULL; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_wmfw_end_alg_info_block, "FW_CS_DSP_KUNIT_TEST_UTILS"); + +static void cs_dsp_init_adsp2_halo_wmfw(struct cs_dsp_mock_wmfw_builder *builder) +{ + struct wmfw_adsp2_halo_header *hdr = builder->buf; + const struct cs_dsp *dsp = builder->test_priv->dsp; + + memcpy(hdr->header.magic, "WMFW", sizeof(hdr->header.magic)); + hdr->header.len = cpu_to_le32(sizeof(*hdr)); + hdr->header.ver = builder->format_version; + hdr->header.core = dsp->type; + hdr->header.rev = cpu_to_le16(dsp->rev); + + hdr->sizes.pm = cpu_to_le32(cs_dsp_mock_size_of_region(dsp, WMFW_ADSP2_PM)); + hdr->sizes.xm = cpu_to_le32(cs_dsp_mock_size_of_region(dsp, WMFW_ADSP2_XM)); + hdr->sizes.ym = cpu_to_le32(cs_dsp_mock_size_of_region(dsp, WMFW_ADSP2_YM)); + + switch (dsp->type) { + case WMFW_ADSP2: + hdr->sizes.zm = cpu_to_le32(cs_dsp_mock_size_of_region(dsp, WMFW_ADSP2_ZM)); + break; + default: + break; + } + + builder->write_p = &hdr[1]; + builder->bytes_used += sizeof(*hdr); +} + +/** + * cs_dsp_mock_wmfw_init() - Initialize a struct cs_dsp_mock_wmfw_builder. + * + * @priv: Pointer to struct cs_dsp_test. + * @format_version: Required wmfw format version. + * + * Return: Pointer to created struct cs_dsp_mock_wmfw_builder. + */ +struct cs_dsp_mock_wmfw_builder *cs_dsp_mock_wmfw_init(struct cs_dsp_test *priv, + int format_version) +{ + struct cs_dsp_mock_wmfw_builder *builder; + + /* If format version isn't given use the default for the target core */ + if (format_version < 0) { + switch (priv->dsp->type) { + case WMFW_ADSP2: + format_version = 2; + break; + default: + format_version = 3; + break; + } + } + + builder = kunit_kzalloc(priv->test, sizeof(*builder), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(priv->test, builder); + + builder->test_priv = priv; + builder->format_version = format_version; + + builder->buf = vmalloc(CS_DSP_MOCK_WMFW_BUF_SIZE); + KUNIT_ASSERT_NOT_NULL(priv->test, builder->buf); + kunit_add_action_or_reset(priv->test, vfree_action_wrapper, builder->buf); + + builder->buf_size_bytes = CS_DSP_MOCK_WMFW_BUF_SIZE; + + switch (priv->dsp->type) { + case WMFW_ADSP2: + case WMFW_HALO: + cs_dsp_init_adsp2_halo_wmfw(builder); + break; + default: + break; + } + + return builder; +} +EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_wmfw_init, "FW_CS_DSP_KUNIT_TEST_UTILS"); diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_bin.c b/drivers/firmware/cirrus/test/cs_dsp_test_bin.c new file mode 100644 index 000000000000..1e161bbc5b4a --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_test_bin.c @@ -0,0 +1,2556 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// KUnit tests for cs_dsp. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Test method is: + * + * 1) Create a mock regmap in cache-only mode so that all writes will be cached. + * 2) Create a XM header with an algorithm list in the cached regmap. + * 3) Create dummy wmfw file to satisfy cs_dsp. + * 4) Create bin file content. + * 5) Call cs_dsp_power_up() with the bin file. + * 6) Readback the cached value of registers that should have been written and + * check they have the correct value. + * 7) All the registers that are expected to have been written are dropped from + * the cache (including the XM header). This should leave the cache clean. + * 8) If the cache is still dirty there have been unexpected writes. + * + * There are multiple different schemes used for addressing across + * ADSP2 and Halo Core DSPs: + * + * dsp words: The addressing scheme used by the DSP, pointers and lengths + * in DSP memory use this. A memory region (XM, YM, ZM) is + * also required to create a unique DSP memory address. + * registers: Addresses in the register map. Older ADSP2 devices have + * 16-bit registers with an address stride of 1. Newer ADSP2 + * devices have 32-bit registers with an address stride of 2. + * Halo Core devices have 32-bit registers with a stride of 4. + * unpacked: Registers that have a 1:1 mapping to DSP words + * packed: Registers that pack multiple DSP words more efficiently into + * multiple 32-bit registers. Because of this the relationship + * between a packed _register_ address and the corresponding + * _dsp word_ address is different from unpacked registers. + * Packed registers can only be accessed as a group of + * multiple registers, therefore can only read/write a group + * of multiple DSP words. + * Packed registers only exist on Halo Core DSPs. + * + * Addresses can also be relative to the start of an algorithm, and this + * can be expressed in dsp words, register addresses, or bytes. + */ + +KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *) +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *) + +struct cs_dsp_test_local { + struct cs_dsp_mock_bin_builder *bin_builder; + struct cs_dsp_mock_wmfw_builder *wmfw_builder; + struct firmware *wmfw; +}; + +struct bin_test_param { + const char *name; + int mem_type; + unsigned int offset_words; + int alg_idx; +}; + +static const struct cs_dsp_mock_alg_def bin_test_mock_algs[] = { + { + .id = 0xfafa, + .ver = 0x100000, + .xm_size_words = 164, + .ym_size_words = 164, + .zm_size_words = 164, + }, + { + .id = 0xfbfb, + .ver = 0x100000, + .xm_size_words = 99, + .ym_size_words = 99, + .zm_size_words = 99, + }, + { + .id = 0xc321, + .ver = 0x100000, + .xm_size_words = 120, + .ym_size_words = 120, + .zm_size_words = 120, + }, + { + .id = 0xb123, + .ver = 0x100000, + .xm_size_words = 96, + .ym_size_words = 96, + .zm_size_words = 96, + }, +}; + +/* + * Convert number of DSP words to number of packed registers rounded + * down to the nearest register. + * There are 3 registers for every 4 packed words. + */ +static unsigned int _num_words_to_num_packed_regs(unsigned int num_dsp_words) +{ + return (num_dsp_words * 3) / 4; +} + +/* bin file that patches a single DSP word */ +static void bin_patch_one_word(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + u32 reg_val, payload_data; + unsigned int alg_base_words, reg_addr; + struct firmware *fw; + + get_random_bytes(&payload_data, sizeof(payload_data)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + param->offset_words * reg_inc_per_word, + &payload_data, sizeof(payload_data)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + ((alg_base_words + param->offset_words) * reg_inc_per_word); + reg_val = 0; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, + ®_val, sizeof(reg_val)), + 0); + KUNIT_EXPECT_EQ(test, reg_val, payload_data); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_regmap_drop_range(priv, reg_addr, reg_addr + reg_inc_per_word - 1); + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* bin file with a single payload that patches consecutive words */ +static void bin_patch_one_multiword(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + u32 payload_data[16], readback[16]; + unsigned int alg_base_words, reg_addr; + struct firmware *fw; + + static_assert(ARRAY_SIZE(readback) == ARRAY_SIZE(payload_data)); + + get_random_bytes(&payload_data, sizeof(payload_data)); + memset(readback, 0, sizeof(readback)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + param->offset_words * reg_inc_per_word, + payload_data, sizeof(payload_data)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + ((alg_base_words + param->offset_words) * reg_inc_per_word); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, sizeof(payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_regmap_drop_range(priv, reg_addr, + reg_addr + (reg_inc_per_word * ARRAY_SIZE(payload_data))); + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* bin file with a multiple one-word payloads that patch consecutive words */ +static void bin_patch_multi_oneword(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + u32 payload_data[16], readback[16]; + unsigned int alg_base_words, reg_addr; + struct firmware *fw; + int i; + + static_assert(ARRAY_SIZE(readback) == ARRAY_SIZE(payload_data)); + + get_random_bytes(&payload_data, sizeof(payload_data)); + memset(readback, 0, sizeof(readback)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + + /* Add one payload per word */ + for (i = 0; i < ARRAY_SIZE(payload_data); ++i) { + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (param->offset_words + i) * reg_inc_per_word, + &payload_data[i], sizeof(payload_data[i])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + ((alg_base_words + param->offset_words) * reg_inc_per_word); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, sizeof(payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_range(priv, reg_addr, + reg_addr + (reg_inc_per_word * ARRAY_SIZE(payload_data))); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file with a multiple one-word payloads that patch a block of consecutive + * words but the payloads are not in address order. + */ +static void bin_patch_multi_oneword_unordered(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + u32 payload_data[16], readback[16]; + static const u8 word_order[] = { 10, 2, 12, 4, 0, 11, 6, 1, 3, 15, 5, 13, 8, 7, 9, 14 }; + unsigned int alg_base_words, reg_addr; + struct firmware *fw; + int i; + + static_assert(ARRAY_SIZE(readback) == ARRAY_SIZE(payload_data)); + static_assert(ARRAY_SIZE(word_order) == ARRAY_SIZE(payload_data)); + + get_random_bytes(&payload_data, sizeof(payload_data)); + memset(readback, 0, sizeof(readback)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + + /* Add one payload per word */ + for (i = 0; i < ARRAY_SIZE(word_order); ++i) { + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (param->offset_words + word_order[i]) * + reg_inc_per_word, + &payload_data[word_order[i]], sizeof(payload_data[0])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + ((alg_base_words + param->offset_words) * reg_inc_per_word); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, sizeof(payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_range(priv, reg_addr, + reg_addr + (reg_inc_per_word * ARRAY_SIZE(payload_data))); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file with a multiple one-word payloads. The payloads are not in address + * order and collectively do not patch a contiguous block of memory. + */ +static void bin_patch_multi_oneword_sparse_unordered(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + static const u8 word_offsets[] = { + 11, 69, 59, 61, 32, 75, 4, 38, 70, 13, 79, 47, 46, 53, 18, 44, + 54, 35, 51, 21, 26, 45, 27, 41, 66, 2, 17, 56, 40, 9, 8, 20, + 29, 19, 63, 42, 12, 16, 43, 3, 5, 55, 52, 22 + }; + u32 payload_data[44]; + unsigned int alg_base_words, reg_addr; + struct firmware *fw; + u32 reg_val; + int i; + + static_assert(ARRAY_SIZE(word_offsets) == ARRAY_SIZE(payload_data)); + + get_random_bytes(&payload_data, sizeof(payload_data)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + + /* Add one payload per word */ + for (i = 0; i < ARRAY_SIZE(word_offsets); ++i) { + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + word_offsets[i] * reg_inc_per_word, + &payload_data[i], sizeof(payload_data[i])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + for (i = 0; i < ARRAY_SIZE(word_offsets); ++i) { + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + ((alg_base_words + word_offsets[i]) * reg_inc_per_word); + reg_val = 0; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, ®_val, + sizeof(reg_val)), + 0); + KUNIT_EXPECT_MEMEQ(test, ®_val, &payload_data[i], sizeof(reg_val)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_range(priv, reg_addr, reg_addr + reg_inc_per_word - 1); + } + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file that patches a single DSP word in each of the memory regions + * of one algorithm. + */ +static void bin_patch_one_word_multiple_mems(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + unsigned int alg_xm_base_words, alg_ym_base_words, alg_zm_base_words; + unsigned int reg_addr; + u32 payload_data[3]; + struct firmware *fw; + u32 reg_val; + + get_random_bytes(&payload_data, sizeof(payload_data)); + + alg_xm_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + WMFW_ADSP2_XM); + alg_ym_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + WMFW_ADSP2_YM); + + if (cs_dsp_mock_has_zm(priv)) { + alg_zm_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + WMFW_ADSP2_ZM); + } else { + alg_zm_base_words = 0; + } + + /* Add words to XM, YM and ZM */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + WMFW_ADSP2_XM, + param->offset_words * reg_inc_per_word, + &payload_data[0], sizeof(payload_data[0])); + + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + WMFW_ADSP2_YM, + param->offset_words * reg_inc_per_word, + &payload_data[1], sizeof(payload_data[1])); + + if (cs_dsp_mock_has_zm(priv)) { + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + WMFW_ADSP2_ZM, + param->offset_words * reg_inc_per_word, + &payload_data[2], sizeof(payload_data[2])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_XM) + + ((alg_xm_base_words + param->offset_words) * reg_inc_per_word); + reg_val = 0; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, ®_val, sizeof(reg_val)), + 0); + KUNIT_EXPECT_EQ(test, reg_val, payload_data[0]); + + cs_dsp_mock_regmap_drop_range(priv, reg_addr, reg_addr + reg_inc_per_word - 1); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_YM) + + ((alg_ym_base_words + param->offset_words) * reg_inc_per_word); + reg_val = 0; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, ®_val, sizeof(reg_val)), + 0); + KUNIT_EXPECT_EQ(test, reg_val, payload_data[1]); + + cs_dsp_mock_regmap_drop_range(priv, reg_addr, reg_addr + reg_inc_per_word - 1); + + if (cs_dsp_mock_has_zm(priv)) { + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_ZM) + + ((alg_zm_base_words + param->offset_words) * reg_inc_per_word); + reg_val = 0; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, ®_val, + sizeof(reg_val)), + 0); + KUNIT_EXPECT_EQ(test, reg_val, payload_data[2]); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_range(priv, reg_addr, reg_addr + reg_inc_per_word - 1); + } + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file that patches a single DSP word in multiple algorithms. + */ +static void bin_patch_one_word_multiple_algs(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + u32 payload_data[ARRAY_SIZE(bin_test_mock_algs)]; + unsigned int alg_base_words; + unsigned int reg_inc_per_word, reg_addr; + struct firmware *fw; + u32 reg_val; + int i; + + get_random_bytes(&payload_data, sizeof(payload_data)); + + /* Add one payload per algorithm */ + for (i = 0; i < ARRAY_SIZE(bin_test_mock_algs); ++i) { + reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[i].id, + bin_test_mock_algs[i].ver, + param->mem_type, + param->offset_words * reg_inc_per_word, + &payload_data[i], sizeof(payload_data[i])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + for (i = 0; i < ARRAY_SIZE(bin_test_mock_algs); ++i) { + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[i].id, + param->mem_type); + reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + ((alg_base_words + param->offset_words) * reg_inc_per_word); + reg_val = 0; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, ®_val, + sizeof(reg_val)), + 0); + KUNIT_EXPECT_EQ(test, reg_val, payload_data[i]); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_range(priv, reg_addr, reg_addr + reg_inc_per_word - 1); + } + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file that patches a single DSP word in multiple algorithms. + * The algorithms are not patched in the same order they appear in the XM header. + */ +static void bin_patch_one_word_multiple_algs_unordered(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + static const u8 alg_order[] = { 3, 0, 2, 1 }; + u32 payload_data[ARRAY_SIZE(bin_test_mock_algs)]; + unsigned int alg_base_words; + unsigned int reg_inc_per_word, reg_addr; + struct firmware *fw; + u32 reg_val; + int i, alg_idx; + + static_assert(ARRAY_SIZE(alg_order) == ARRAY_SIZE(bin_test_mock_algs)); + + get_random_bytes(&payload_data, sizeof(payload_data)); + + /* Add one payload per algorithm */ + for (i = 0; i < ARRAY_SIZE(bin_test_mock_algs); ++i) { + alg_idx = alg_order[i]; + reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[alg_idx].id, + bin_test_mock_algs[alg_idx].ver, + param->mem_type, + param->offset_words * reg_inc_per_word, + &payload_data[i], sizeof(payload_data[i])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + for (i = 0; i < ARRAY_SIZE(bin_test_mock_algs); ++i) { + alg_idx = alg_order[i]; + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[alg_idx].id, + param->mem_type); + reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + ((alg_base_words + param->offset_words) * reg_inc_per_word); + reg_val = 0; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, ®_val, + sizeof(reg_val)), + 0); + KUNIT_EXPECT_EQ(test, reg_val, payload_data[i]); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_range(priv, reg_addr, reg_addr + reg_inc_per_word - 1); + } + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* bin file that patches a single packed block of DSP words */ +static void bin_patch_1_packed(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + u32 packed_payload[3], readback[3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + packed_payload, sizeof(packed_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload, sizeof(packed_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that is one word longer than a packed block using one + * packed block followed by one unpacked word. + */ +static void bin_patch_1_packed_1_single_trailing(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payload[1], readback[3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payload, sizeof(unpacked_payload)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + /* Patch packed block */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + /* ... and the unpacked word following that */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((patch_pos_words + 4) - alg_base_words) * 4, + unpacked_payload, sizeof(unpacked_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (patch_pos_words + 4) * 4; + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payload)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payload, sizeof(unpacked_payload)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that is two words longer than a packed block using one + * packed block followed by two blocks of one unpacked word. + */ +static void bin_patch_1_packed_2_single_trailing(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payloads[2], readback[3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payloads)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payloads, sizeof(unpacked_payloads)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + /* Patch packed block */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + /* ... and the unpacked words following that */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((patch_pos_words + 4) - alg_base_words) * 4, + &unpacked_payloads[0], sizeof(unpacked_payloads[0])); + + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((patch_pos_words + 5) - alg_base_words) * 4, + &unpacked_payloads[1], sizeof(unpacked_payloads[1])); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payloads */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (patch_pos_words + 4) * 4; + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payloads)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payloads, sizeof(unpacked_payloads)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payloads)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that is three words longer than a packed block using one + * packed block followed by three blocks of one unpacked word. + */ +static void bin_patch_1_packed_3_single_trailing(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payloads[3], readback[3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payloads)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payloads, sizeof(unpacked_payloads)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + /* Patch packed block */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + /* ... and the unpacked words following that */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((patch_pos_words + 4) - alg_base_words) * 4, + &unpacked_payloads[0], sizeof(unpacked_payloads[0])); + + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((patch_pos_words + 5) - alg_base_words) * 4, + &unpacked_payloads[1], sizeof(unpacked_payloads[1])); + + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((patch_pos_words + 6) - alg_base_words) * 4, + &unpacked_payloads[2], sizeof(unpacked_payloads[2])); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payloads */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (patch_pos_words + 4) * 4; + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payloads)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payloads, sizeof(unpacked_payloads)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payloads)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that is two words longer than a packed block using one + * packed block followed by a block of two unpacked words. + */ +static void bin_patch_1_packed_2_trailing(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payload[2], readback[3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payload, sizeof(unpacked_payload)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + /* Patch packed block */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + /* ... and the unpacked words following that */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((patch_pos_words + 4) - alg_base_words) * 4, + unpacked_payload, sizeof(unpacked_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (patch_pos_words + 4) * 4; + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payload)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payload, sizeof(unpacked_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that is three words longer than a packed block using one + * packed block followed by a block of three unpacked words. + */ +static void bin_patch_1_packed_3_trailing(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payload[3], readback[3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payload, sizeof(unpacked_payload)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + /* Patch packed block */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + /* ... and the unpacked words following that */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((patch_pos_words + 4) - alg_base_words) * 4, + unpacked_payload, sizeof(unpacked_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (patch_pos_words + 4) * 4; + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payload)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payload, sizeof(unpacked_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that starts one word before a packed boundary using one + * unpacked word followed by one packed block. + */ +static void bin_patch_1_single_leading_1_packed(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payload[1], readback[3]; + unsigned int alg_base_words, packed_patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payload, sizeof(unpacked_payload)); + memset(readback, 0, sizeof(readback)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round packed start word up to a packed boundary and move to the next boundary */ + packed_patch_pos_words = round_up(alg_base_words + param->offset_words, 4) + 4; + + /* Patch the leading unpacked word */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((packed_patch_pos_words - 1) - alg_base_words) * 4, + unpacked_payload, sizeof(unpacked_payload)); + /* ... then the packed block */ + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(packed_patch_pos_words); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (packed_patch_pos_words - 1) * 4; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payload)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payload, sizeof(unpacked_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that starts two words before a packed boundary using two + * unpacked words followed by one packed block. + */ +static void bin_patch_2_single_leading_1_packed(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payload[2], readback[3]; + unsigned int alg_base_words, packed_patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payload, sizeof(unpacked_payload)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round packed start word up to a packed boundary and move to the next boundary */ + packed_patch_pos_words = round_up(alg_base_words + param->offset_words, 4) + 4; + + /* Patch the leading unpacked words */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((packed_patch_pos_words - 2) - alg_base_words) * 4, + &unpacked_payload[0], sizeof(unpacked_payload[0])); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((packed_patch_pos_words - 1) - alg_base_words) * 4, + &unpacked_payload[1], sizeof(unpacked_payload[1])); + /* ... then the packed block */ + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(packed_patch_pos_words); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (packed_patch_pos_words - 2) * 4; + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payload)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payload, sizeof(unpacked_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that starts two words before a packed boundary using one + * block of two unpacked words followed by one packed block. + */ +static void bin_patch_2_leading_1_packed(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payload[2], readback[3]; + unsigned int alg_base_words, packed_patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payload, sizeof(unpacked_payload)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round packed start word up to a packed boundary and move to the next boundary */ + packed_patch_pos_words = round_up(alg_base_words + param->offset_words, 4) + 4; + + /* Patch the leading unpacked words */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((packed_patch_pos_words - 2) - alg_base_words) * 4, + unpacked_payload, sizeof(unpacked_payload)); + /* ... then the packed block */ + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(packed_patch_pos_words); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (packed_patch_pos_words - 2) * 4; + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payload)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payload, sizeof(unpacked_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that starts three words before a packed boundary using three + * unpacked words followed by one packed block. + */ +static void bin_patch_3_single_leading_1_packed(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payload[3], readback[3]; + unsigned int alg_base_words, packed_patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payload, sizeof(unpacked_payload)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round packed start word up to a packed boundary and move to the next boundary */ + packed_patch_pos_words = round_up(alg_base_words + param->offset_words, 4) + 4; + + /* Patch the leading unpacked words */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((packed_patch_pos_words - 3) - alg_base_words) * 4, + &unpacked_payload[0], sizeof(unpacked_payload[0])); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((packed_patch_pos_words - 2) - alg_base_words) * 4, + &unpacked_payload[1], sizeof(unpacked_payload[1])); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((packed_patch_pos_words - 1) - alg_base_words) * 4, + &unpacked_payload[2], sizeof(unpacked_payload[2])); + /* ... then the packed block */ + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(packed_patch_pos_words); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (packed_patch_pos_words - 3) * 4; + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payload)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payload, sizeof(unpacked_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Patch data that starts three words before a packed boundary using one + * block of three unpacked words followed by one packed block. + */ +static void bin_patch_3_leading_1_packed(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + unsigned int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + u32 packed_payload[3], unpacked_payload[3], readback[3]; + unsigned int alg_base_words, packed_patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + static_assert(sizeof(readback) >= sizeof(unpacked_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + get_random_bytes(unpacked_payload, sizeof(unpacked_payload)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round packed start word up to a packed boundary and move to the next boundary */ + packed_patch_pos_words = round_up(alg_base_words + param->offset_words, 4) + 4; + + /* Patch the leading unpacked words */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + unpacked_mem_type, + ((packed_patch_pos_words - 3) - alg_base_words) * 4, + unpacked_payload, sizeof(unpacked_payload)); + /* ... then the packed block */ + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(packed_patch_pos_words); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + &packed_payload, sizeof(packed_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, &packed_payload, sizeof(packed_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload)); + + /* Content of unpacked registers should match unpacked_payload */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + (packed_patch_pos_words - 3) * 4; + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, &readback, + sizeof(unpacked_payload)), + 0); + KUNIT_EXPECT_MEMEQ(test, &readback, unpacked_payload, sizeof(unpacked_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* bin file with a multiple payloads that each patch one packed block. */ +static void bin_patch_multi_onepacked(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + u32 packed_payloads[8][3], readback[8][3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int payload_offset; + unsigned int reg_addr; + struct firmware *fw; + int i; + + static_assert(sizeof(readback) == sizeof(packed_payloads)); + + get_random_bytes(packed_payloads, sizeof(packed_payloads)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + + /* Add one payload per packed block */ + for (i = 0; i < ARRAY_SIZE(packed_payloads); ++i) { + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words + (i * 4)); + payload_offset = (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4; + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + payload_offset, + &packed_payloads[i], sizeof(packed_payloads[i])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payloads */ + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payloads, sizeof(packed_payloads)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payloads)); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file with a multiple payloads that each patch one packed block. + * The payloads are not in address order. + */ +static void bin_patch_multi_onepacked_unordered(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + static const u8 payload_order[] = { 4, 3, 6, 1, 0, 7, 5, 2 }; + u32 packed_payloads[8][3], readback[8][3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int payload_offset; + unsigned int reg_addr; + struct firmware *fw; + int i; + + static_assert(ARRAY_SIZE(payload_order) == ARRAY_SIZE(packed_payloads)); + static_assert(sizeof(readback) == sizeof(packed_payloads)); + + get_random_bytes(packed_payloads, sizeof(packed_payloads)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + + /* Add one payload per packed block */ + for (i = 0; i < ARRAY_SIZE(payload_order); ++i) { + patch_pos_in_packed_regs = + _num_words_to_num_packed_regs(patch_pos_words + (payload_order[i] * 4)); + payload_offset = (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4; + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + payload_offset, + &packed_payloads[payload_order[i]], + sizeof(packed_payloads[0])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content in registers should match the order of data in packed_payloads */ + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payloads, sizeof(packed_payloads)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payloads)); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file with a multiple payloads that each patch one packed block. + * The payloads are not in address order. The patched memory is not contiguous. + */ +static void bin_patch_multi_onepacked_sparse_unordered(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + static const u8 word_offsets[] = { 60, 24, 76, 4, 40, 52, 48, 36, 12 }; + u32 packed_payloads[9][3], readback[3]; + unsigned int alg_base_words, alg_base_in_packed_regs; + unsigned int patch_pos_words, patch_pos_in_packed_regs, payload_offset; + unsigned int reg_addr; + struct firmware *fw; + int i; + + static_assert(ARRAY_SIZE(word_offsets) == ARRAY_SIZE(packed_payloads)); + static_assert(sizeof(readback) == sizeof(packed_payloads[0])); + + get_random_bytes(packed_payloads, sizeof(packed_payloads)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Add one payload per packed block */ + for (i = 0; i < ARRAY_SIZE(word_offsets); ++i) { + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + word_offsets[i], 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + payload_offset = (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4; + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + param->mem_type, + payload_offset, + &packed_payloads[i], + sizeof(packed_payloads[0])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed registers should match packed_payloads */ + for (i = 0; i < ARRAY_SIZE(word_offsets); ++i) { + patch_pos_words = round_up(alg_base_words + word_offsets[i], 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payloads[i], sizeof(packed_payloads[i])); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payloads[i])); + } + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file that patches a single packed block in each of the memory regions + * of one algorithm. + */ +static void bin_patch_1_packed_multiple_mems(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + u32 packed_xm_payload[3], packed_ym_payload[3], readback[3]; + unsigned int alg_xm_base_words, alg_ym_base_words; + unsigned int xm_patch_pos_words, ym_patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr; + struct firmware *fw; + + static_assert(sizeof(readback) == sizeof(packed_xm_payload)); + static_assert(sizeof(readback) == sizeof(packed_ym_payload)); + + get_random_bytes(packed_xm_payload, sizeof(packed_xm_payload)); + get_random_bytes(packed_ym_payload, sizeof(packed_ym_payload)); + + alg_xm_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + WMFW_HALO_XM_PACKED); + alg_ym_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[param->alg_idx].id, + WMFW_HALO_YM_PACKED); + + /* Round patch start word up to a packed boundary */ + xm_patch_pos_words = round_up(alg_xm_base_words + param->offset_words, 4); + ym_patch_pos_words = round_up(alg_ym_base_words + param->offset_words, 4); + + /* Add XM and YM patches */ + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_xm_base_words); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(xm_patch_pos_words); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + WMFW_HALO_XM_PACKED, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + packed_xm_payload, sizeof(packed_xm_payload)); + + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_ym_base_words); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(ym_patch_pos_words); + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[param->alg_idx].id, + bin_test_mock_algs[param->alg_idx].ver, + WMFW_HALO_YM_PACKED, + (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4, + packed_ym_payload, sizeof(packed_ym_payload)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of packed XM registers should match packed_xm_payload */ + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(xm_patch_pos_words); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_HALO_XM_PACKED) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_xm_payload, sizeof(packed_xm_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_xm_payload)); + + /* Content of packed YM registers should match packed_ym_payload */ + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(ym_patch_pos_words); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_HALO_YM_PACKED) + + (patch_pos_in_packed_regs * 4); + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_ym_payload, sizeof(packed_ym_payload)); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_ym_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file that patches a single packed block in multiple algorithms. + */ +static void bin_patch_1_packed_multiple_algs(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + u32 packed_payload[ARRAY_SIZE(bin_test_mock_algs)][3]; + u32 readback[ARRAY_SIZE(bin_test_mock_algs)][3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr, payload_offset; + struct firmware *fw; + int i; + + static_assert(sizeof(readback) == sizeof(packed_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + + /* For each algorithm patch one DSP word to a value from packed_payload */ + for (i = 0; i < ARRAY_SIZE(bin_test_mock_algs); ++i) { + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[i].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + payload_offset = (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4; + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[i].id, + bin_test_mock_algs[i].ver, + param->mem_type, + payload_offset, + packed_payload[i], sizeof(packed_payload[i])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + memset(readback, 0, sizeof(readback)); + + /* + * Readback the registers that should have been written. Place + * the values into the expected location in readback[] so that + * the content of readback[] should match packed_payload[] + */ + for (i = 0; i < ARRAY_SIZE(bin_test_mock_algs); ++i) { + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[i].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, + readback[i], sizeof(readback[i])), + 0); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload[i])); + } + + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload, sizeof(packed_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file that patches a single packed block in multiple algorithms. + * The algorithms are not patched in the same order they appear in the XM header. + */ +static void bin_patch_1_packed_multiple_algs_unordered(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + static const u8 alg_order[] = { 3, 0, 2, 1 }; + u32 packed_payload[ARRAY_SIZE(bin_test_mock_algs)][3]; + u32 readback[ARRAY_SIZE(bin_test_mock_algs)][3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr, payload_offset; + struct firmware *fw; + int i, alg_idx; + + static_assert(ARRAY_SIZE(alg_order) == ARRAY_SIZE(bin_test_mock_algs)); + static_assert(sizeof(readback) == sizeof(packed_payload)); + + get_random_bytes(packed_payload, sizeof(packed_payload)); + + /* + * For each algorithm index in alg_order[] patch one DSP word in + * that algorithm to a value from packed_payload. + */ + for (i = 0; i < ARRAY_SIZE(alg_order); ++i) { + alg_idx = alg_order[i]; + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[alg_idx].id, + param->mem_type); + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + + /* Round patch start word up to a packed boundary */ + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + payload_offset = (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4; + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[alg_idx].id, + bin_test_mock_algs[alg_idx].ver, + param->mem_type, + payload_offset, + packed_payload[i], sizeof(packed_payload[i])); + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + memset(readback, 0, sizeof(readback)); + + /* + * Readback the registers that should have been written. Place + * the values into the expected location in readback[] so that + * the content of readback[] should match packed_payload[] + */ + for (i = 0; i < ARRAY_SIZE(alg_order); ++i) { + alg_idx = alg_order[i]; + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[alg_idx].id, + param->mem_type); + + patch_pos_words = round_up(alg_base_words + param->offset_words, 4); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, + readback[i], sizeof(readback[i])), + 0); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(packed_payload[i])); + } + + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload, sizeof(packed_payload)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * bin file that contains a mix of packed and unpacked words. + * payloads are in random offset order. Offsets that are on a packed boundary + * are written as a packed block. Offsets that are not on a packed boundary + * are written as a single unpacked word. + */ +static void bin_patch_mixed_packed_unpacked_random(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + const struct bin_test_param *param = test->param_value; + static const u8 offset_words[] = { + 58, 68, 50, 10, 44, 17, 74, 36, 8, 7, 49, 11, 78, 57, 65, 2, + 48, 38, 22, 70, 77, 21, 61, 56, 75, 34, 27, 3, 31, 20, 43, 63, + 5, 30, 32, 25, 33, 79, 29, 0, 37, 60, 69, 52, 13, 12, 24, 26, + 4, 51, 76, 72, 16, 6, 39, 62, 15, 41, 28, 73, 53, 40, 45, 54, + 14, 55, 46, 66, 64, 59, 23, 9, 67, 47, 19, 71, 35, 18, 42, 1, + }; + struct { + u32 packed[80][3]; + u32 unpacked[80]; + } *payload; + u32 readback[3]; + unsigned int alg_base_words, patch_pos_words; + unsigned int alg_base_in_packed_regs, patch_pos_in_packed_regs; + unsigned int reg_addr, payload_offset; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + struct firmware *fw; + int i; + + payload = kunit_kmalloc(test, sizeof(*payload), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, payload); + + get_random_bytes(payload->packed, sizeof(payload->packed)); + get_random_bytes(payload->unpacked, sizeof(payload->unpacked)); + + /* Create a patch entry for every offset in offset_words[] */ + for (i = 0; i < ARRAY_SIZE(offset_words); ++i) { + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[0].id, + param->mem_type); + /* + * If the offset is on a packed boundary use a packed payload else + * use an unpacked word + */ + patch_pos_words = alg_base_words + offset_words[i]; + if ((patch_pos_words % 4) == 0) { + alg_base_in_packed_regs = _num_words_to_num_packed_regs(alg_base_words); + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + payload_offset = (patch_pos_in_packed_regs - alg_base_in_packed_regs) * 4; + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[0].id, + bin_test_mock_algs[0].ver, + param->mem_type, + payload_offset, + payload->packed[i], + sizeof(payload->packed[i])); + } else { + payload_offset = offset_words[i] * 4; + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[0].id, + bin_test_mock_algs[0].ver, + unpacked_mem_type, + payload_offset, + &payload->unpacked[i], + sizeof(payload->unpacked[i])); + } + } + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* + * Readback the packed registers that should have been written. + * Place the values into the expected location in readback[] so + * that the content of readback[] should match payload->packed[] + */ + for (i = 0; i < ARRAY_SIZE(offset_words); ++i) { + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[0].id, + param->mem_type); + patch_pos_words = alg_base_words + offset_words[i]; + + /* Skip if the offset is not on a packed boundary */ + if ((patch_pos_words % 4) != 0) + continue; + + patch_pos_in_packed_regs = _num_words_to_num_packed_regs(patch_pos_words); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type) + + (patch_pos_in_packed_regs * 4); + + memset(readback, 0, sizeof(readback)); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(readback)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload->packed[i], sizeof(payload->packed[i])); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(payload->packed[i])); + } + + /* + * Readback the unpacked registers that should have been written. + * Place the values into the expected location in readback[] so + * that the content of readback[] should match payload->unpacked[] + */ + for (i = 0; i < ARRAY_SIZE(offset_words); ++i) { + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[0].id, + unpacked_mem_type); + + patch_pos_words = alg_base_words + offset_words[i]; + + /* Skip if the offset is on a packed boundary */ + if ((patch_pos_words % 4) == 0) + continue; + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type) + + ((patch_pos_words) * 4); + + readback[0] = 0; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, + &readback[0], sizeof(readback[0])), + 0); + KUNIT_EXPECT_EQ(test, readback[0], payload->unpacked[i]); + + /* Drop expected writes from the cache */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(payload->unpacked[i])); + } + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* Bin file with name and multiple info blocks */ +static void bin_patch_name_and_info(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + unsigned int reg_inc_per_word = cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + u32 reg_val, payload_data; + char *infobuf; + unsigned int alg_base_words, reg_addr; + struct firmware *fw; + + get_random_bytes(&payload_data, sizeof(payload_data)); + + alg_base_words = cs_dsp_mock_xm_header_get_alg_base_in_words(priv, + bin_test_mock_algs[0].id, + WMFW_ADSP2_YM); + + /* Add a name block and info block */ + cs_dsp_mock_bin_add_name(priv->local->bin_builder, "The name"); + cs_dsp_mock_bin_add_info(priv->local->bin_builder, "Some info"); + + /* Add a big block of info */ + infobuf = kunit_kzalloc(test, 512, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, infobuf); + + for (; strlcat(infobuf, "Waffle{Blah}\n", 512) < 512; ) + ; + + cs_dsp_mock_bin_add_info(priv->local->bin_builder, infobuf); + + /* Add a patch */ + cs_dsp_mock_bin_add_patch(priv->local->bin_builder, + bin_test_mock_algs[0].id, + bin_test_mock_algs[0].ver, + WMFW_ADSP2_YM, + 0, + &payload_data, sizeof(payload_data)); + + fw = cs_dsp_mock_bin_get_firmware(priv->local->bin_builder); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, priv->local->wmfw, "mock_wmfw", + fw, "mock_bin", "misc"), + 0); + + /* Content of registers should match payload_data */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_YM); + reg_addr += alg_base_words * reg_inc_per_word; + reg_val = 0; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, + ®_val, sizeof(reg_val)), + 0); + KUNIT_EXPECT_EQ(test, reg_val, payload_data); +} + +static int cs_dsp_bin_test_common_init(struct kunit *test, struct cs_dsp *dsp) +{ + struct cs_dsp_test *priv; + struct cs_dsp_mock_xm_header *xm_hdr; + struct device *test_dev; + int ret; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->local = kunit_kzalloc(test, sizeof(struct cs_dsp_test_local), GFP_KERNEL); + if (!priv->local) + return -ENOMEM; + + priv->test = test; + priv->dsp = dsp; + test->priv = priv; + + /* Create dummy struct device */ + test_dev = kunit_device_register(test, "cs_dsp_test_drv"); + if (IS_ERR(test_dev)) + return PTR_ERR(test_dev); + + dsp->dev = get_device(test_dev); + if (!dsp->dev) + return -ENODEV; + + ret = kunit_add_action_or_reset(test, _put_device_wrapper, dsp->dev); + if (ret) + return ret; + + dev_set_drvdata(dsp->dev, priv); + + /* Allocate regmap */ + ret = cs_dsp_mock_regmap_init(priv); + if (ret) + return ret; + + /* Create an XM header */ + xm_hdr = cs_dsp_create_mock_xm_header(priv, + bin_test_mock_algs, + ARRAY_SIZE(bin_test_mock_algs)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, xm_hdr); + ret = cs_dsp_mock_xm_header_write_to_regmap(xm_hdr); + KUNIT_ASSERT_EQ(test, ret, 0); + + priv->local->bin_builder = + cs_dsp_mock_bin_init(priv, 1, + cs_dsp_mock_xm_header_get_fw_version_from_regmap(priv)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv->local->bin_builder); + + /* We must provide a dummy wmfw to load */ + priv->local->wmfw_builder = cs_dsp_mock_wmfw_init(priv, -1); + priv->local->wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + dsp->client_ops = kunit_kzalloc(test, sizeof(*dsp->client_ops), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dsp->client_ops); + + switch (dsp->type) { + case WMFW_ADSP2: + ret = cs_dsp_adsp2_init(dsp); + break; + case WMFW_HALO: + ret = cs_dsp_halo_init(dsp); + break; + default: + KUNIT_FAIL(test, "Untested DSP type %d\n", dsp->type); + return -EINVAL; + } + + if (ret) + return ret; + + /* Automatically call cs_dsp_remove() when test case ends */ + return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); +} + +static int cs_dsp_bin_test_halo_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_HALO; + dsp->mem = cs_dsp_mock_halo_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_halo_dsp1_region_sizes); + dsp->base = cs_dsp_mock_halo_core_base; + dsp->base_sysinfo = cs_dsp_mock_halo_sysinfo_base; + + return cs_dsp_bin_test_common_init(test, dsp); +} + +static int cs_dsp_bin_test_adsp2_32bit_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 1; + dsp->mem = cs_dsp_mock_adsp2_32bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_32bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_32bit_sysbase; + + return cs_dsp_bin_test_common_init(test, dsp); +} + +static int cs_dsp_bin_test_adsp2_16bit_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 0; + dsp->mem = cs_dsp_mock_adsp2_16bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_16bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_16bit_sysbase; + + return cs_dsp_bin_test_common_init(test, dsp); +} + +/* Parameterize on choice of XM or YM with a range of word offsets */ +static const struct bin_test_param x_or_y_and_offset_param_cases[] = { + { .mem_type = WMFW_ADSP2_XM, .offset_words = 0 }, + { .mem_type = WMFW_ADSP2_XM, .offset_words = 1 }, + { .mem_type = WMFW_ADSP2_XM, .offset_words = 2 }, + { .mem_type = WMFW_ADSP2_XM, .offset_words = 3 }, + { .mem_type = WMFW_ADSP2_XM, .offset_words = 4 }, + { .mem_type = WMFW_ADSP2_XM, .offset_words = 23 }, + { .mem_type = WMFW_ADSP2_XM, .offset_words = 22 }, + { .mem_type = WMFW_ADSP2_XM, .offset_words = 21 }, + { .mem_type = WMFW_ADSP2_XM, .offset_words = 20 }, + + { .mem_type = WMFW_ADSP2_YM, .offset_words = 0 }, + { .mem_type = WMFW_ADSP2_YM, .offset_words = 1 }, + { .mem_type = WMFW_ADSP2_YM, .offset_words = 2 }, + { .mem_type = WMFW_ADSP2_YM, .offset_words = 3 }, + { .mem_type = WMFW_ADSP2_YM, .offset_words = 4 }, + { .mem_type = WMFW_ADSP2_YM, .offset_words = 23 }, + { .mem_type = WMFW_ADSP2_YM, .offset_words = 22 }, + { .mem_type = WMFW_ADSP2_YM, .offset_words = 21 }, + { .mem_type = WMFW_ADSP2_YM, .offset_words = 20 }, +}; + +/* Parameterize on ZM with a range of word offsets */ +static const struct bin_test_param z_and_offset_param_cases[] = { + { .mem_type = WMFW_ADSP2_ZM, .offset_words = 0 }, + { .mem_type = WMFW_ADSP2_ZM, .offset_words = 1 }, + { .mem_type = WMFW_ADSP2_ZM, .offset_words = 2 }, + { .mem_type = WMFW_ADSP2_ZM, .offset_words = 3 }, + { .mem_type = WMFW_ADSP2_ZM, .offset_words = 4 }, + { .mem_type = WMFW_ADSP2_ZM, .offset_words = 23 }, + { .mem_type = WMFW_ADSP2_ZM, .offset_words = 22 }, + { .mem_type = WMFW_ADSP2_ZM, .offset_words = 21 }, + { .mem_type = WMFW_ADSP2_ZM, .offset_words = 20 }, +}; + +/* Parameterize on choice of packed XM or YM with a range of word offsets */ +static const struct bin_test_param packed_x_or_y_and_offset_param_cases[] = { + { .mem_type = WMFW_HALO_XM_PACKED, .offset_words = 0 }, + { .mem_type = WMFW_HALO_XM_PACKED, .offset_words = 4 }, + { .mem_type = WMFW_HALO_XM_PACKED, .offset_words = 8 }, + { .mem_type = WMFW_HALO_XM_PACKED, .offset_words = 12 }, + + { .mem_type = WMFW_HALO_YM_PACKED, .offset_words = 0 }, + { .mem_type = WMFW_HALO_YM_PACKED, .offset_words = 4 }, + { .mem_type = WMFW_HALO_YM_PACKED, .offset_words = 8 }, + { .mem_type = WMFW_HALO_YM_PACKED, .offset_words = 12 }, +}; + +static void x_or_y_or_z_and_offset_param_desc(const struct bin_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%s@%u", + cs_dsp_mem_region_name(param->mem_type), + param->offset_words); +} + +KUNIT_ARRAY_PARAM(x_or_y_and_offset, + x_or_y_and_offset_param_cases, + x_or_y_or_z_and_offset_param_desc); + +KUNIT_ARRAY_PARAM(z_and_offset, + z_and_offset_param_cases, + x_or_y_or_z_and_offset_param_desc); + +KUNIT_ARRAY_PARAM(packed_x_or_y_and_offset, + packed_x_or_y_and_offset_param_cases, + x_or_y_or_z_and_offset_param_desc); + +/* Parameterize on choice of packed XM or YM */ +static const struct bin_test_param packed_x_or_y_param_cases[] = { + { .mem_type = WMFW_HALO_XM_PACKED, .offset_words = 0 }, + { .mem_type = WMFW_HALO_YM_PACKED, .offset_words = 0 }, +}; + +static void x_or_y_or_z_param_desc(const struct bin_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%s", cs_dsp_mem_region_name(param->mem_type)); +} + +KUNIT_ARRAY_PARAM(packed_x_or_y, packed_x_or_y_param_cases, x_or_y_or_z_param_desc); + +static const struct bin_test_param offset_param_cases[] = { + { .offset_words = 0 }, + { .offset_words = 1 }, + { .offset_words = 2 }, + { .offset_words = 3 }, + { .offset_words = 4 }, + { .offset_words = 23 }, + { .offset_words = 22 }, + { .offset_words = 21 }, + { .offset_words = 20 }, +}; + +static void offset_param_desc(const struct bin_test_param *param, char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "@%u", param->offset_words); +} + +KUNIT_ARRAY_PARAM(offset, offset_param_cases, offset_param_desc); + +static const struct bin_test_param alg_param_cases[] = { + { .alg_idx = 0 }, + { .alg_idx = 1 }, + { .alg_idx = 2 }, + { .alg_idx = 3 }, +}; + +static void alg_param_desc(const struct bin_test_param *param, char *desc) +{ + WARN_ON(param->alg_idx >= ARRAY_SIZE(bin_test_mock_algs)); + + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "alg[%u] (%#x)", + param->alg_idx, bin_test_mock_algs[param->alg_idx].id); +} + +KUNIT_ARRAY_PARAM(alg, alg_param_cases, alg_param_desc); + +static const struct bin_test_param x_or_y_and_alg_param_cases[] = { + { .mem_type = WMFW_ADSP2_XM, .alg_idx = 0 }, + { .mem_type = WMFW_ADSP2_XM, .alg_idx = 1 }, + { .mem_type = WMFW_ADSP2_XM, .alg_idx = 2 }, + { .mem_type = WMFW_ADSP2_XM, .alg_idx = 3 }, + + { .mem_type = WMFW_ADSP2_YM, .alg_idx = 0 }, + { .mem_type = WMFW_ADSP2_YM, .alg_idx = 1 }, + { .mem_type = WMFW_ADSP2_YM, .alg_idx = 2 }, + { .mem_type = WMFW_ADSP2_YM, .alg_idx = 3 }, +}; + +static void x_or_y_or_z_and_alg_param_desc(const struct bin_test_param *param, char *desc) +{ + WARN_ON(param->alg_idx >= ARRAY_SIZE(bin_test_mock_algs)); + + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%s alg[%u] (%#x)", + cs_dsp_mem_region_name(param->mem_type), + param->alg_idx, bin_test_mock_algs[param->alg_idx].id); +} + +KUNIT_ARRAY_PARAM(x_or_y_and_alg, x_or_y_and_alg_param_cases, x_or_y_or_z_and_alg_param_desc); + +static const struct bin_test_param z_and_alg_param_cases[] = { + { .mem_type = WMFW_ADSP2_ZM, .alg_idx = 0 }, + { .mem_type = WMFW_ADSP2_ZM, .alg_idx = 1 }, + { .mem_type = WMFW_ADSP2_ZM, .alg_idx = 2 }, + { .mem_type = WMFW_ADSP2_ZM, .alg_idx = 3 }, +}; + +KUNIT_ARRAY_PARAM(z_and_alg, z_and_alg_param_cases, x_or_y_or_z_and_alg_param_desc); + +static const struct bin_test_param packed_x_or_y_and_alg_param_cases[] = { + { .mem_type = WMFW_HALO_XM_PACKED, .alg_idx = 0 }, + { .mem_type = WMFW_HALO_XM_PACKED, .alg_idx = 1 }, + { .mem_type = WMFW_HALO_XM_PACKED, .alg_idx = 2 }, + { .mem_type = WMFW_HALO_XM_PACKED, .alg_idx = 3 }, + + { .mem_type = WMFW_HALO_YM_PACKED, .alg_idx = 0 }, + { .mem_type = WMFW_HALO_YM_PACKED, .alg_idx = 1 }, + { .mem_type = WMFW_HALO_YM_PACKED, .alg_idx = 2 }, + { .mem_type = WMFW_HALO_YM_PACKED, .alg_idx = 3 }, +}; + +KUNIT_ARRAY_PARAM(packed_x_or_y_and_alg, packed_x_or_y_and_alg_param_cases, + x_or_y_or_z_and_alg_param_desc); + +static struct kunit_case cs_dsp_bin_test_cases_halo[] = { + /* Unpacked memory */ + KUNIT_CASE_PARAM(bin_patch_one_word, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_multiword, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_oneword, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_oneword_unordered, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_mems, offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_mems, alg_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_oneword_sparse_unordered, x_or_y_and_alg_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_algs, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_algs_unordered, x_or_y_and_offset_gen_params), + + /* Packed memory tests */ + KUNIT_CASE_PARAM(bin_patch_1_packed, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_packed_1_single_trailing, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_packed_2_single_trailing, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_packed_3_single_trailing, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_packed_2_trailing, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_packed_3_trailing, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_single_leading_1_packed, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_2_single_leading_1_packed, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_2_leading_1_packed, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_3_single_leading_1_packed, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_3_leading_1_packed, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_onepacked, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_onepacked_unordered, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_packed_multiple_mems, offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_packed_multiple_mems, alg_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_onepacked_sparse_unordered, + packed_x_or_y_and_alg_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_packed_multiple_algs, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_1_packed_multiple_algs_unordered, + packed_x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_mixed_packed_unpacked_random, + packed_x_or_y_gen_params), + + KUNIT_CASE(bin_patch_name_and_info), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_bin_test_cases_adsp2[] = { + /* XM and YM */ + KUNIT_CASE_PARAM(bin_patch_one_word, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_multiword, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_oneword, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_oneword_unordered, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_oneword_sparse_unordered, x_or_y_and_alg_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_algs, x_or_y_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_algs_unordered, x_or_y_and_offset_gen_params), + + /* ZM */ + KUNIT_CASE_PARAM(bin_patch_one_word, z_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_multiword, z_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_oneword, z_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_oneword_unordered, z_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_multi_oneword_sparse_unordered, z_and_alg_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_algs, z_and_offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_algs_unordered, z_and_offset_gen_params), + + /* Other */ + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_mems, offset_gen_params), + KUNIT_CASE_PARAM(bin_patch_one_word_multiple_mems, alg_gen_params), + + KUNIT_CASE(bin_patch_name_and_info), + + { } /* terminator */ +}; + +static struct kunit_suite cs_dsp_bin_test_halo = { + .name = "cs_dsp_bin_halo", + .init = cs_dsp_bin_test_halo_init, + .test_cases = cs_dsp_bin_test_cases_halo, +}; + +static struct kunit_suite cs_dsp_bin_test_adsp2_32bit = { + .name = "cs_dsp_bin_adsp2_32bit", + .init = cs_dsp_bin_test_adsp2_32bit_init, + .test_cases = cs_dsp_bin_test_cases_adsp2, +}; + +static struct kunit_suite cs_dsp_bin_test_adsp2_16bit = { + .name = "cs_dsp_bin_adsp2_16bit", + .init = cs_dsp_bin_test_adsp2_16bit_init, + .test_cases = cs_dsp_bin_test_cases_adsp2, +}; + +kunit_test_suites(&cs_dsp_bin_test_halo, + &cs_dsp_bin_test_adsp2_32bit, + &cs_dsp_bin_test_adsp2_16bit); diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c b/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c new file mode 100644 index 000000000000..5dcf62f19faf --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c @@ -0,0 +1,600 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// KUnit tests for cs_dsp. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. +// + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *); +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *); + +struct cs_dsp_test_local { + struct cs_dsp_mock_bin_builder *bin_builder; + struct cs_dsp_mock_xm_header *xm_header; + struct cs_dsp_mock_wmfw_builder *wmfw_builder; + struct firmware *wmfw; + int wmfw_version; +}; + +struct cs_dsp_bin_test_param { + int block_type; +}; + +static const struct cs_dsp_mock_alg_def cs_dsp_bin_err_test_mock_algs[] = { + { + .id = 0xfafa, + .ver = 0x100000, + .xm_size_words = 164, + .ym_size_words = 164, + .zm_size_words = 164, + }, +}; + +/* Load a bin containing unknown blocks. They should be skipped. */ +static void bin_load_with_unknown_blocks(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *bin; + unsigned int reg_addr; + u8 *payload_data, *readback; + u8 random_data[8]; + const unsigned int payload_size_bytes = 64; + + payload_data = kunit_kmalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + get_random_bytes(payload_data, payload_size_bytes); + + readback = kunit_kzalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Add some unknown blocks at the start of the bin */ + get_random_bytes(random_data, sizeof(random_data)); + cs_dsp_mock_bin_add_raw_block(local->bin_builder, + cs_dsp_bin_err_test_mock_algs[0].id, + cs_dsp_bin_err_test_mock_algs[0].ver, + 0xf5, 0, + random_data, sizeof(random_data)); + cs_dsp_mock_bin_add_raw_block(local->bin_builder, + cs_dsp_bin_err_test_mock_algs[0].id, + cs_dsp_bin_err_test_mock_algs[0].ver, + 0xf500, 0, + random_data, sizeof(random_data)); + cs_dsp_mock_bin_add_raw_block(local->bin_builder, + cs_dsp_bin_err_test_mock_algs[0].id, + cs_dsp_bin_err_test_mock_algs[0].ver, + 0xc300, 0, + random_data, sizeof(random_data)); + + /* Add a single payload to be written to DSP memory */ + cs_dsp_mock_bin_add_raw_block(local->bin_builder, + cs_dsp_bin_err_test_mock_algs[0].id, + cs_dsp_bin_err_test_mock_algs[0].ver, + WMFW_ADSP2_YM, 0, + payload_data, payload_size_bytes); + + bin = cs_dsp_mock_bin_get_firmware(local->bin_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + /* Check that the payload was written to memory */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_YM); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, payload_size_bytes); +} + +/* Load a bin that doesn't have a valid magic marker. */ +static void bin_err_wrong_magic(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *bin; + + /* Sanity-check that the wmfw loads ok without the bin */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + bin = cs_dsp_mock_bin_get_firmware(local->bin_builder); + + memcpy((void *)bin->data, "WMFW", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + memcpy((void *)bin->data, "xMDR", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + memcpy((void *)bin->data, "WxDR", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + memcpy((void *)bin->data, "WMxR", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + memcpy((void *)bin->data, "WMDx", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + memset((void *)bin->data, 0, 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); +} + +/* Load a bin that is too short for a valid header. */ +static void bin_err_too_short_for_header(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *bin; + + /* Sanity-check that the wmfw loads ok without the bin */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + bin = cs_dsp_mock_bin_get_firmware(local->bin_builder); + do { + bin->size--; + + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + } while (bin->size > 0); +} + +/* Header length field isn't a valid header length. */ +static void bin_err_bad_header_length(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *bin; + struct wmfw_coeff_hdr *header; + unsigned int real_len, len; + + /* Sanity-check that the wmfw loads ok without the bin */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + bin = cs_dsp_mock_bin_get_firmware(local->bin_builder); + header = (struct wmfw_coeff_hdr *)bin->data; + real_len = le32_to_cpu(header->len); + + for (len = 0; len < real_len; len++) { + header->len = cpu_to_le32(len); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + } + + for (len = real_len + 1; len < real_len + 7; len++) { + header->len = cpu_to_le32(len); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + } + + header->len = cpu_to_le32(0xffffffff); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + header->len = cpu_to_le32(0x80000000); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + header->len = cpu_to_le32(0x7fffffff); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); +} + +/* Wrong core type in header. */ +static void bin_err_bad_core_type(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *bin; + struct wmfw_coeff_hdr *header; + + /* Sanity-check that the wmfw loads ok without the bin */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + bin = cs_dsp_mock_bin_get_firmware(local->bin_builder); + header = (struct wmfw_coeff_hdr *)bin->data; + + header->core_ver = cpu_to_le32(0); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + header->core_ver = cpu_to_le32(1); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + header->core_ver = cpu_to_le32(priv->dsp->type + 1); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + header->core_ver = cpu_to_le32(0xff); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); +} + +/* File too short to contain a full block header */ +static void bin_too_short_for_block_header(struct kunit *test) +{ + const struct cs_dsp_bin_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *bin; + unsigned int header_length; + + /* Sanity-check that the wmfw loads ok without the bin */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + bin = cs_dsp_mock_bin_get_firmware(local->bin_builder); + header_length = bin->size; + kunit_kfree(test, bin); + + cs_dsp_mock_bin_add_raw_block(local->bin_builder, + cs_dsp_bin_err_test_mock_algs[0].id, + cs_dsp_bin_err_test_mock_algs[0].ver, + param->block_type, 0, + NULL, 0); + + bin = cs_dsp_mock_bin_get_firmware(local->bin_builder); + KUNIT_ASSERT_GT(test, bin->size, header_length); + + for (bin->size--; bin->size > header_length; bin->size--) { + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + } +} + +/* File too short to contain the block payload */ +static void bin_too_short_for_block_payload(struct kunit *test) +{ + const struct cs_dsp_bin_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *bin; + static const u8 payload[256] = { }; + int i; + + /* Sanity-check that the wmfw loads ok without the bin */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + cs_dsp_mock_bin_add_raw_block(local->bin_builder, + cs_dsp_bin_err_test_mock_algs[0].id, + cs_dsp_bin_err_test_mock_algs[0].ver, + param->block_type, 0, + payload, sizeof(payload)); + + bin = cs_dsp_mock_bin_get_firmware(local->bin_builder); + for (i = 0; i < sizeof(payload); i++) { + bin->size--; + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + } +} + +/* Block payload length is a garbage value */ +static void bin_block_payload_len_garbage(struct kunit *test) +{ + const struct cs_dsp_bin_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *bin; + struct wmfw_coeff_hdr *header; + struct wmfw_coeff_item *block; + u32 payload = 0; + + /* Sanity-check that the wmfw loads ok without the bin */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + cs_dsp_mock_bin_add_raw_block(local->bin_builder, + cs_dsp_bin_err_test_mock_algs[0].id, + cs_dsp_bin_err_test_mock_algs[0].ver, + param->block_type, 0, + &payload, sizeof(payload)); + + bin = cs_dsp_mock_bin_get_firmware(local->bin_builder); + header = (struct wmfw_coeff_hdr *)bin->data; + block = (struct wmfw_coeff_item *)&bin->data[le32_to_cpu(header->len)]; + + /* Sanity check that we're looking at the correct part of the bin */ + KUNIT_ASSERT_EQ(test, le16_to_cpu(block->type), param->block_type); + KUNIT_ASSERT_EQ(test, le32_to_cpu(block->len), sizeof(payload)); + + block->len = cpu_to_le32(0x8000); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + block->len = cpu_to_le32(0xffff); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + block->len = cpu_to_le32(0x7fffffff); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + block->len = cpu_to_le32(0x80000000); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); + + block->len = cpu_to_le32(0xffffffff); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, local->wmfw, "wmfw", bin, "bin", "misc"), + 0); +} + +static void cs_dsp_bin_err_test_exit(struct kunit *test) +{ + /* + * Testing error conditions can produce a lot of log output + * from cs_dsp error messages, so rate limit the test cases. + */ + usleep_range(200, 500); +} + +static int cs_dsp_bin_err_test_common_init(struct kunit *test, struct cs_dsp *dsp, + int wmfw_version) +{ + struct cs_dsp_test *priv; + struct cs_dsp_test_local *local; + struct device *test_dev; + int ret; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + local = kunit_kzalloc(test, sizeof(struct cs_dsp_test_local), GFP_KERNEL); + if (!local) + return -ENOMEM; + + priv->test = test; + priv->dsp = dsp; + test->priv = priv; + priv->local = local; + priv->local->wmfw_version = wmfw_version; + + /* Create dummy struct device */ + test_dev = kunit_device_register(test, "cs_dsp_test_drv"); + if (IS_ERR(test_dev)) + return PTR_ERR(test_dev); + + dsp->dev = get_device(test_dev); + if (!dsp->dev) + return -ENODEV; + + ret = kunit_add_action_or_reset(test, _put_device_wrapper, dsp->dev); + if (ret) + return ret; + + dev_set_drvdata(dsp->dev, priv); + + /* Allocate regmap */ + ret = cs_dsp_mock_regmap_init(priv); + if (ret) + return ret; + + /* + * There must always be a XM header with at least 1 algorithm, so create + * a dummy one that tests can use and extract it to a data payload. + */ + local->xm_header = cs_dsp_create_mock_xm_header(priv, + cs_dsp_bin_err_test_mock_algs, + ARRAY_SIZE(cs_dsp_bin_err_test_mock_algs)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->xm_header); + + local->wmfw_builder = cs_dsp_mock_wmfw_init(priv, priv->local->wmfw_version); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->wmfw_builder); + + /* Add dummy XM header payload to wmfw */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_ADSP2_XM, 0, + local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + local->wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + local->bin_builder = + cs_dsp_mock_bin_init(priv, 1, + cs_dsp_mock_xm_header_get_fw_version_from_regmap(priv)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->bin_builder); + + /* Init cs_dsp */ + dsp->client_ops = kunit_kzalloc(test, sizeof(*dsp->client_ops), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dsp->client_ops); + + switch (dsp->type) { + case WMFW_ADSP2: + ret = cs_dsp_adsp2_init(dsp); + break; + case WMFW_HALO: + ret = cs_dsp_halo_init(dsp); + break; + default: + KUNIT_FAIL(test, "Untested DSP type %d\n", dsp->type); + return -EINVAL; + } + + if (ret) + return ret; + + /* Automatically call cs_dsp_remove() when test case ends */ + return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); +} + +static int cs_dsp_bin_err_test_halo_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_HALO; + dsp->mem = cs_dsp_mock_halo_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_halo_dsp1_region_sizes); + dsp->base = cs_dsp_mock_halo_core_base; + dsp->base_sysinfo = cs_dsp_mock_halo_sysinfo_base; + + return cs_dsp_bin_err_test_common_init(test, dsp, 3); +} + +static int cs_dsp_bin_err_test_adsp2_32bit_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 1; + dsp->mem = cs_dsp_mock_adsp2_32bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_32bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_32bit_sysbase; + + return cs_dsp_bin_err_test_common_init(test, dsp, 2); +} + +static int cs_dsp_bin_err_test_adsp2_16bit_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 0; + dsp->mem = cs_dsp_mock_adsp2_16bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_16bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_16bit_sysbase; + + return cs_dsp_bin_err_test_common_init(test, dsp, 1); +} + +static struct kunit_case cs_dsp_bin_err_test_cases_halo[] = { + + { } /* terminator */ +}; + +static void cs_dsp_bin_err_block_types_desc(const struct cs_dsp_bin_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "block_type:%#x", param->block_type); +} + +/* Some block types to test against, including illegal types */ +static const struct cs_dsp_bin_test_param bin_test_block_types_cases[] = { + { .block_type = WMFW_INFO_TEXT << 8 }, + { .block_type = WMFW_METADATA << 8 }, + { .block_type = WMFW_ADSP2_PM }, + { .block_type = WMFW_ADSP2_XM }, + { .block_type = 0x33 }, + { .block_type = 0xf500 }, + { .block_type = 0xc000 }, +}; + +KUNIT_ARRAY_PARAM(bin_test_block_types, + bin_test_block_types_cases, + cs_dsp_bin_err_block_types_desc); + +static struct kunit_case cs_dsp_bin_err_test_cases_adsp2[] = { + KUNIT_CASE(bin_load_with_unknown_blocks), + KUNIT_CASE(bin_err_wrong_magic), + KUNIT_CASE(bin_err_too_short_for_header), + KUNIT_CASE(bin_err_bad_header_length), + KUNIT_CASE(bin_err_bad_core_type), + + KUNIT_CASE_PARAM(bin_too_short_for_block_header, bin_test_block_types_gen_params), + KUNIT_CASE_PARAM(bin_too_short_for_block_payload, bin_test_block_types_gen_params), + KUNIT_CASE_PARAM(bin_block_payload_len_garbage, bin_test_block_types_gen_params), + + { } /* terminator */ +}; + +static struct kunit_suite cs_dsp_bin_err_test_halo = { + .name = "cs_dsp_bin_err_halo", + .init = cs_dsp_bin_err_test_halo_init, + .exit = cs_dsp_bin_err_test_exit, + .test_cases = cs_dsp_bin_err_test_cases_halo, +}; + +static struct kunit_suite cs_dsp_bin_err_test_adsp2_32bit = { + .name = "cs_dsp_bin_err_adsp2_32bit", + .init = cs_dsp_bin_err_test_adsp2_32bit_init, + .exit = cs_dsp_bin_err_test_exit, + .test_cases = cs_dsp_bin_err_test_cases_adsp2, +}; + +static struct kunit_suite cs_dsp_bin_err_test_adsp2_16bit = { + .name = "cs_dsp_bin_err_adsp2_16bit", + .init = cs_dsp_bin_err_test_adsp2_16bit_init, + .exit = cs_dsp_bin_err_test_exit, + .test_cases = cs_dsp_bin_err_test_cases_adsp2, +}; + +kunit_test_suites(&cs_dsp_bin_err_test_halo, + &cs_dsp_bin_err_test_adsp2_32bit, + &cs_dsp_bin_err_test_adsp2_16bit); diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_callbacks.c b/drivers/firmware/cirrus/test/cs_dsp_test_callbacks.c new file mode 100644 index 000000000000..8a9b66a3b7d3 --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_test_callbacks.c @@ -0,0 +1,688 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// KUnit tests for cs_dsp. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. +// + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ADSP2_LOCK_REGION_CTRL 0x7A +#define ADSP2_WDT_TIMEOUT_STS_MASK 0x2000 + +KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *) +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *) + +struct cs_dsp_test_local { + struct cs_dsp_mock_wmfw_builder *wmfw_builder; + + int num_control_add; + int num_control_remove; + int num_pre_run; + int num_post_run; + int num_pre_stop; + int num_post_stop; + int num_watchdog_expired; + + struct cs_dsp_coeff_ctl *passed_ctl[16]; + struct cs_dsp *passed_dsp; +}; + +struct cs_dsp_callbacks_test_param { + const struct cs_dsp_client_ops *ops; + const char *case_name; +}; + +static const struct cs_dsp_mock_alg_def cs_dsp_callbacks_test_mock_algs[] = { + { + .id = 0xfafa, + .ver = 0x100000, + .xm_size_words = 164, + .ym_size_words = 164, + .zm_size_words = 164, + }, +}; + +static const struct cs_dsp_mock_coeff_def mock_coeff_template = { + .shortname = "Dummy Coeff", + .type = WMFW_CTL_TYPE_BYTES, + .mem_type = WMFW_ADSP2_YM, + .flags = WMFW_CTL_FLAG_VOLATILE, + .length_bytes = 4, +}; + +static int cs_dsp_test_control_add_callback(struct cs_dsp_coeff_ctl *ctl) +{ + struct kunit *test = kunit_get_current_test(); + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + + local->passed_ctl[local->num_control_add] = ctl; + local->num_control_add++; + + return 0; +} + +static void cs_dsp_test_control_remove_callback(struct cs_dsp_coeff_ctl *ctl) +{ + struct kunit *test = kunit_get_current_test(); + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + + local->passed_ctl[local->num_control_remove] = ctl; + local->num_control_remove++; +} + +static int cs_dsp_test_pre_run_callback(struct cs_dsp *dsp) +{ + struct kunit *test = kunit_get_current_test(); + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + + local->passed_dsp = dsp; + local->num_pre_run++; + + return 0; +} + +static int cs_dsp_test_post_run_callback(struct cs_dsp *dsp) +{ + struct kunit *test = kunit_get_current_test(); + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + + local->passed_dsp = dsp; + local->num_post_run++; + + return 0; +} + +static void cs_dsp_test_pre_stop_callback(struct cs_dsp *dsp) +{ + struct kunit *test = kunit_get_current_test(); + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + + local->passed_dsp = dsp; + local->num_pre_stop++; +} + +static void cs_dsp_test_post_stop_callback(struct cs_dsp *dsp) +{ + struct kunit *test = kunit_get_current_test(); + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + + local->passed_dsp = dsp; + local->num_post_stop++; +} + +static void cs_dsp_test_watchdog_expired_callback(struct cs_dsp *dsp) +{ + struct kunit *test = kunit_get_current_test(); + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + + local->passed_dsp = dsp; + local->num_watchdog_expired++; +} + +static const struct cs_dsp_client_ops cs_dsp_callback_test_client_ops = { + .control_add = cs_dsp_test_control_add_callback, + .control_remove = cs_dsp_test_control_remove_callback, + .pre_run = cs_dsp_test_pre_run_callback, + .post_run = cs_dsp_test_post_run_callback, + .pre_stop = cs_dsp_test_pre_stop_callback, + .post_stop = cs_dsp_test_post_stop_callback, + .watchdog_expired = cs_dsp_test_watchdog_expired_callback, +}; + +static const struct cs_dsp_client_ops cs_dsp_callback_test_empty_client_ops = { + /* No entries */ +}; + +static void cs_dsp_test_run_stop_callbacks(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + + KUNIT_EXPECT_EQ(test, cs_dsp_run(priv->dsp), 0); + KUNIT_EXPECT_EQ(test, local->num_pre_run, 1); + KUNIT_EXPECT_EQ(test, local->num_post_run, 1); + KUNIT_EXPECT_EQ(test, local->num_pre_stop, 0); + KUNIT_EXPECT_EQ(test, local->num_post_stop, 0); + KUNIT_EXPECT_PTR_EQ(test, local->passed_dsp, priv->dsp); + local->passed_dsp = NULL; + + cs_dsp_stop(priv->dsp); + KUNIT_EXPECT_EQ(test, local->num_pre_run, 1); + KUNIT_EXPECT_EQ(test, local->num_post_run, 1); + KUNIT_EXPECT_EQ(test, local->num_pre_stop, 1); + KUNIT_EXPECT_EQ(test, local->num_post_stop, 1); + KUNIT_EXPECT_PTR_EQ(test, local->passed_dsp, priv->dsp); + local->passed_dsp = NULL; + + KUNIT_EXPECT_EQ(test, cs_dsp_run(priv->dsp), 0); + KUNIT_EXPECT_EQ(test, local->num_pre_run, 2); + KUNIT_EXPECT_EQ(test, local->num_post_run, 2); + KUNIT_EXPECT_EQ(test, local->num_pre_stop, 1); + KUNIT_EXPECT_EQ(test, local->num_post_stop, 1); + KUNIT_EXPECT_PTR_EQ(test, local->passed_dsp, priv->dsp); + local->passed_dsp = NULL; + + cs_dsp_stop(priv->dsp); + KUNIT_EXPECT_EQ(test, local->num_pre_run, 2); + KUNIT_EXPECT_EQ(test, local->num_post_run, 2); + KUNIT_EXPECT_EQ(test, local->num_pre_stop, 2); + KUNIT_EXPECT_EQ(test, local->num_post_stop, 2); + KUNIT_EXPECT_PTR_EQ(test, local->passed_dsp, priv->dsp); + local->passed_dsp = NULL; +} + +static void cs_dsp_test_ctl_v1_callbacks(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + int i; + + /* Add a control for each memory */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_callbacks_test_mock_algs[0].id, + "dummyalg", NULL); + def.shortname = "zm"; + def.mem_type = WMFW_ADSP2_ZM; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + def.shortname = "ym"; + def.mem_type = WMFW_ADSP2_YM; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + def.shortname = "xm"; + def.mem_type = WMFW_ADSP2_XM; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + + /* There should have been an add callback for each control */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), 3); + KUNIT_EXPECT_EQ(test, local->num_control_add, 3); + KUNIT_EXPECT_EQ(test, local->num_control_remove, 0); + + i = 0; + list_for_each_entry_reverse(ctl, &priv->dsp->ctl_list, list) + KUNIT_EXPECT_PTR_EQ(test, local->passed_ctl[i++], ctl); + + /* + * Call cs_dsp_remove() and there should be a remove callback + * for each control + */ + memset(local->passed_ctl, 0, sizeof(local->passed_ctl)); + cs_dsp_remove(priv->dsp); + + /* Prevent double cleanup */ + kunit_remove_action(priv->test, _cs_dsp_remove_wrapper, priv->dsp); + + KUNIT_EXPECT_EQ(test, local->num_control_add, 3); + KUNIT_EXPECT_EQ(test, local->num_control_remove, 3); + + i = 0; + list_for_each_entry_reverse(ctl, &priv->dsp->ctl_list, list) + KUNIT_EXPECT_PTR_EQ(test, local->passed_ctl[i++], ctl); +} + +static void cs_dsp_test_ctl_v2_callbacks(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + char name[2] = { }; + int i; + + /* Add some controls */ + def.shortname = name; + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_callbacks_test_mock_algs[0].id, + "dummyalg", NULL); + for (i = 0; i < ARRAY_SIZE(local->passed_ctl); ++i) { + name[0] = 'A' + i; + def.offset_dsp_words = i; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + } + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + + /* There should have been an add callback for each control */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), + ARRAY_SIZE(local->passed_ctl)); + KUNIT_EXPECT_EQ(test, local->num_control_add, ARRAY_SIZE(local->passed_ctl)); + KUNIT_EXPECT_EQ(test, local->num_control_remove, 0); + + i = 0; + list_for_each_entry_reverse(ctl, &priv->dsp->ctl_list, list) + KUNIT_EXPECT_PTR_EQ(test, local->passed_ctl[i++], ctl); + + /* + * Call cs_dsp_remove() and there should be a remove callback + * for each control + */ + memset(local->passed_ctl, 0, sizeof(local->passed_ctl)); + cs_dsp_remove(priv->dsp); + + /* Prevent double cleanup */ + kunit_remove_action(priv->test, _cs_dsp_remove_wrapper, priv->dsp); + + KUNIT_EXPECT_EQ(test, local->num_control_add, ARRAY_SIZE(local->passed_ctl)); + KUNIT_EXPECT_EQ(test, local->num_control_remove, ARRAY_SIZE(local->passed_ctl)); + + i = 0; + list_for_each_entry_reverse(ctl, &priv->dsp->ctl_list, list) + KUNIT_EXPECT_PTR_EQ(test, local->passed_ctl[i++], ctl); +} + +static void cs_dsp_test_no_callbacks(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct firmware *wmfw; + + /* Add a controls */ + def.shortname = "A"; + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_callbacks_test_mock_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Run a sequence of ops that would invoke callbacks */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + KUNIT_EXPECT_EQ(test, cs_dsp_run(priv->dsp), 0); + cs_dsp_stop(priv->dsp); + cs_dsp_remove(priv->dsp); + + /* Prevent double cleanup */ + kunit_remove_action(priv->test, _cs_dsp_remove_wrapper, priv->dsp); + + /* Something went very wrong if any of our callbacks were called */ + KUNIT_EXPECT_EQ(test, local->num_control_add, 0); + KUNIT_EXPECT_EQ(test, local->num_control_remove, 0); + KUNIT_EXPECT_EQ(test, local->num_pre_run, 0); + KUNIT_EXPECT_EQ(test, local->num_post_run, 0); + KUNIT_EXPECT_EQ(test, local->num_pre_stop, 0); + KUNIT_EXPECT_EQ(test, local->num_post_stop, 0); +} + +static void cs_dsp_test_adsp2v2_watchdog_callback(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + + KUNIT_EXPECT_EQ(test, cs_dsp_run(priv->dsp), 0); + + /* Set the watchdog timeout bit */ + regmap_write(priv->dsp->regmap, priv->dsp->base + ADSP2_LOCK_REGION_CTRL, + ADSP2_WDT_TIMEOUT_STS_MASK); + + /* Notify an interrupt and the watchdog callback should be called */ + cs_dsp_adsp2_bus_error(priv->dsp); + KUNIT_EXPECT_EQ(test, local->num_watchdog_expired, 1); + KUNIT_EXPECT_PTR_EQ(test, local->passed_dsp, priv->dsp); +} + +static void cs_dsp_test_adsp2v2_watchdog_no_callbacks(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + KUNIT_EXPECT_EQ(test, cs_dsp_run(priv->dsp), 0); + + /* Set the watchdog timeout bit */ + regmap_write(priv->dsp->regmap, priv->dsp->base + ADSP2_LOCK_REGION_CTRL, + ADSP2_WDT_TIMEOUT_STS_MASK); + + /* Notify an interrupt, which will look for a watchdog callback */ + cs_dsp_adsp2_bus_error(priv->dsp); + KUNIT_EXPECT_EQ(test, local->num_watchdog_expired, 0); +} + +static void cs_dsp_test_halo_watchdog_callback(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + + KUNIT_EXPECT_EQ(test, cs_dsp_run(priv->dsp), 0); + + /* Notify an interrupt and the watchdog callback should be called */ + cs_dsp_halo_wdt_expire(priv->dsp); + KUNIT_EXPECT_EQ(test, local->num_watchdog_expired, 1); + KUNIT_EXPECT_PTR_EQ(test, local->passed_dsp, priv->dsp); +} + +static void cs_dsp_test_halo_watchdog_no_callbacks(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + KUNIT_EXPECT_EQ(test, cs_dsp_run(priv->dsp), 0); + + /* Notify an interrupt, which will look for a watchdog callback */ + cs_dsp_halo_wdt_expire(priv->dsp); + KUNIT_EXPECT_EQ(test, local->num_watchdog_expired, 0); +} + +static int cs_dsp_callbacks_test_common_init(struct kunit *test, struct cs_dsp *dsp, + int wmfw_version) +{ + const struct cs_dsp_callbacks_test_param *param = test->param_value; + struct cs_dsp_test *priv; + struct cs_dsp_test_local *local; + struct device *test_dev; + struct cs_dsp_mock_xm_header *xm_header; + int ret; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + local = kunit_kzalloc(test, sizeof(struct cs_dsp_test_local), GFP_KERNEL); + if (!local) + return -ENOMEM; + + priv->test = test; + priv->dsp = dsp; + test->priv = priv; + priv->local = local; + + /* Create dummy struct device */ + test_dev = kunit_device_register(test, "cs_dsp_test_drv"); + if (IS_ERR(test_dev)) + return PTR_ERR(test_dev); + + dsp->dev = get_device(test_dev); + if (!dsp->dev) + return -ENODEV; + + ret = kunit_add_action_or_reset(test, _put_device_wrapper, dsp->dev); + if (ret) + return ret; + + dev_set_drvdata(dsp->dev, priv); + + /* Allocate regmap */ + ret = cs_dsp_mock_regmap_init(priv); + if (ret) + return ret; + + /* + * There must always be a XM header with at least 1 algorithm, + * so create a dummy one and pre-populate XM so the wmfw doesn't + * have to contain an XM blob. + */ + xm_header = cs_dsp_create_mock_xm_header(priv, + cs_dsp_callbacks_test_mock_algs, + ARRAY_SIZE(cs_dsp_callbacks_test_mock_algs)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, xm_header); + cs_dsp_mock_xm_header_write_to_regmap(xm_header); + + local->wmfw_builder = cs_dsp_mock_wmfw_init(priv, wmfw_version); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->wmfw_builder); + + /* Add dummy XM header payload to wmfw */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_ADSP2_XM, 0, + xm_header->blob_data, + xm_header->blob_size_bytes); + + /* Init cs_dsp */ + dsp->client_ops = param->ops; + + switch (dsp->type) { + case WMFW_ADSP2: + ret = cs_dsp_adsp2_init(dsp); + break; + case WMFW_HALO: + ret = cs_dsp_halo_init(dsp); + break; + default: + KUNIT_FAIL(test, "Untested DSP type %d\n", dsp->type); + return -EINVAL; + } + + if (ret) + return ret; + + /* Automatically call cs_dsp_remove() when test case ends */ + return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); +} + +static int cs_dsp_callbacks_test_halo_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_HALO; + dsp->mem = cs_dsp_mock_halo_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_halo_dsp1_region_sizes); + dsp->base = cs_dsp_mock_halo_core_base; + dsp->base_sysinfo = cs_dsp_mock_halo_sysinfo_base; + + return cs_dsp_callbacks_test_common_init(test, dsp, 3); +} + +static int cs_dsp_callbacks_test_adsp2_32bit_init(struct kunit *test, int rev) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = rev; + dsp->mem = cs_dsp_mock_adsp2_32bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_32bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_32bit_sysbase; + + return cs_dsp_callbacks_test_common_init(test, dsp, 2); +} + +static int cs_dsp_callbacks_test_adsp2v2_32bit_init(struct kunit *test) +{ + return cs_dsp_callbacks_test_adsp2_32bit_init(test, 2); +} + +static int cs_dsp_callbacks_test_adsp2v1_32bit_init(struct kunit *test) +{ + return cs_dsp_callbacks_test_adsp2_32bit_init(test, 1); +} + +static int cs_dsp_callbacks_test_adsp2_16bit_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 0; + dsp->mem = cs_dsp_mock_adsp2_16bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_16bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_16bit_sysbase; + + return cs_dsp_callbacks_test_common_init(test, dsp, 1); +} + +static void cs_dsp_callbacks_param_desc(const struct cs_dsp_callbacks_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%s", param->case_name); +} + +/* Parameterize on different client callback ops tables */ +static const struct cs_dsp_callbacks_test_param cs_dsp_callbacks_ops_cases[] = { + { .ops = &cs_dsp_callback_test_client_ops, .case_name = "all ops" }, +}; + +KUNIT_ARRAY_PARAM(cs_dsp_callbacks_ops, + cs_dsp_callbacks_ops_cases, + cs_dsp_callbacks_param_desc); + +static const struct cs_dsp_callbacks_test_param cs_dsp_no_callbacks_cases[] = { + { .ops = &cs_dsp_callback_test_empty_client_ops, .case_name = "empty ops" }, +}; + +KUNIT_ARRAY_PARAM(cs_dsp_no_callbacks, + cs_dsp_no_callbacks_cases, + cs_dsp_callbacks_param_desc); + +static struct kunit_case cs_dsp_callbacks_adsp2_wmfwv1_test_cases[] = { + KUNIT_CASE_PARAM(cs_dsp_test_run_stop_callbacks, cs_dsp_callbacks_ops_gen_params), + KUNIT_CASE_PARAM(cs_dsp_test_ctl_v1_callbacks, cs_dsp_callbacks_ops_gen_params), + KUNIT_CASE_PARAM(cs_dsp_test_no_callbacks, cs_dsp_no_callbacks_gen_params), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_callbacks_adsp2_wmfwv2_test_cases[] = { + KUNIT_CASE_PARAM(cs_dsp_test_run_stop_callbacks, cs_dsp_callbacks_ops_gen_params), + KUNIT_CASE_PARAM(cs_dsp_test_ctl_v2_callbacks, cs_dsp_callbacks_ops_gen_params), + KUNIT_CASE_PARAM(cs_dsp_test_no_callbacks, cs_dsp_no_callbacks_gen_params), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_callbacks_halo_test_cases[] = { + KUNIT_CASE_PARAM(cs_dsp_test_run_stop_callbacks, cs_dsp_callbacks_ops_gen_params), + KUNIT_CASE_PARAM(cs_dsp_test_ctl_v2_callbacks, cs_dsp_callbacks_ops_gen_params), + KUNIT_CASE_PARAM(cs_dsp_test_no_callbacks, cs_dsp_no_callbacks_gen_params), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_watchdog_adsp2v2_test_cases[] = { + KUNIT_CASE_PARAM(cs_dsp_test_adsp2v2_watchdog_callback, cs_dsp_callbacks_ops_gen_params), + KUNIT_CASE_PARAM(cs_dsp_test_adsp2v2_watchdog_no_callbacks, cs_dsp_no_callbacks_gen_params), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_watchdog_halo_test_cases[] = { + KUNIT_CASE_PARAM(cs_dsp_test_halo_watchdog_callback, cs_dsp_callbacks_ops_gen_params), + KUNIT_CASE_PARAM(cs_dsp_test_halo_watchdog_no_callbacks, cs_dsp_no_callbacks_gen_params), + + { } /* terminator */ +}; + +static struct kunit_suite cs_dsp_callbacks_test_halo = { + .name = "cs_dsp_callbacks_halo", + .init = cs_dsp_callbacks_test_halo_init, + .test_cases = cs_dsp_callbacks_halo_test_cases, +}; + +static struct kunit_suite cs_dsp_callbacks_test_adsp2v2_32bit = { + .name = "cs_dsp_callbacks_adsp2v2_32bit_wmfwv2", + .init = cs_dsp_callbacks_test_adsp2v2_32bit_init, + .test_cases = cs_dsp_callbacks_adsp2_wmfwv2_test_cases, +}; + +static struct kunit_suite cs_dsp_callbacks_test_adsp2v1_32bit = { + .name = "cs_dsp_callbacks_adsp2v1_32bit_wmfwv2", + .init = cs_dsp_callbacks_test_adsp2v1_32bit_init, + .test_cases = cs_dsp_callbacks_adsp2_wmfwv2_test_cases, +}; + +static struct kunit_suite cs_dsp_callbacks_test_adsp2_16bit = { + .name = "cs_dsp_callbacks_adsp2_16bit_wmfwv1", + .init = cs_dsp_callbacks_test_adsp2_16bit_init, + .test_cases = cs_dsp_callbacks_adsp2_wmfwv1_test_cases, +}; + +static struct kunit_suite cs_dsp_watchdog_test_adsp2v2_32bit = { + .name = "cs_dsp_watchdog_adsp2v2_32bit", + .init = cs_dsp_callbacks_test_adsp2v2_32bit_init, + .test_cases = cs_dsp_watchdog_adsp2v2_test_cases, +}; + +static struct kunit_suite cs_dsp_watchdog_test_halo_32bit = { + .name = "cs_dsp_watchdog_halo", + .init = cs_dsp_callbacks_test_halo_init, + .test_cases = cs_dsp_watchdog_halo_test_cases, +}; + +kunit_test_suites(&cs_dsp_callbacks_test_halo, + &cs_dsp_callbacks_test_adsp2v2_32bit, + &cs_dsp_callbacks_test_adsp2v1_32bit, + &cs_dsp_callbacks_test_adsp2_16bit, + &cs_dsp_watchdog_test_adsp2v2_32bit, + &cs_dsp_watchdog_test_halo_32bit); diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_control_cache.c b/drivers/firmware/cirrus/test/cs_dsp_test_control_cache.c new file mode 100644 index 000000000000..83386cc978e3 --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_test_control_cache.c @@ -0,0 +1,3282 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// KUnit tests for cs_dsp. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *); +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_stop_wrapper, cs_dsp_stop, struct cs_dsp *); +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *); + +struct cs_dsp_test_local { + struct cs_dsp_mock_xm_header *xm_header; + struct cs_dsp_mock_wmfw_builder *wmfw_builder; + int wmfw_version; +}; + +struct cs_dsp_ctl_cache_test_param { + int mem_type; + int alg_id; + unsigned int offs_words; + unsigned int len_bytes; + u16 ctl_type; + u16 flags; +}; + +static const struct cs_dsp_mock_alg_def cs_dsp_ctl_cache_test_algs[] = { + { + .id = 0xfafa, + .ver = 0x100000, + .xm_base_words = 60, + .xm_size_words = 1000, + .ym_base_words = 0, + .ym_size_words = 1000, + .zm_base_words = 0, + .zm_size_words = 1000, + }, + { + .id = 0xb, + .ver = 0x100001, + .xm_base_words = 1060, + .xm_size_words = 1000, + .ym_base_words = 1000, + .ym_size_words = 1000, + .zm_base_words = 1000, + .zm_size_words = 1000, + }, + { + .id = 0x9f1234, + .ver = 0x100500, + .xm_base_words = 2060, + .xm_size_words = 32, + .ym_base_words = 2000, + .ym_size_words = 32, + .zm_base_words = 2000, + .zm_size_words = 32, + }, + { + .id = 0xff00ff, + .ver = 0x300113, + .xm_base_words = 2100, + .xm_size_words = 32, + .ym_base_words = 2032, + .ym_size_words = 32, + .zm_base_words = 2032, + .zm_size_words = 32, + }, +}; + +static const struct cs_dsp_mock_coeff_def mock_coeff_template = { + .shortname = "Dummy Coeff", + .type = WMFW_CTL_TYPE_BYTES, + .mem_type = WMFW_ADSP2_YM, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + .length_bytes = 4, +}; + +static const char * const cs_dsp_ctl_cache_test_fw_names[] = { + "misc", "mbc/vss", "haps", +}; + +static int _find_alg_entry(struct kunit *test, unsigned int alg_id) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_cache_test_algs); ++i) { + if (cs_dsp_ctl_cache_test_algs[i].id == alg_id) + break; + } + + KUNIT_ASSERT_LT(test, i, ARRAY_SIZE(cs_dsp_ctl_cache_test_algs)); + + return i; +} + +static int _get_alg_mem_base_words(struct kunit *test, int alg_index, int mem_type) +{ + switch (mem_type) { + case WMFW_ADSP2_XM: + return cs_dsp_ctl_cache_test_algs[alg_index].xm_base_words; + case WMFW_ADSP2_YM: + return cs_dsp_ctl_cache_test_algs[alg_index].ym_base_words; + case WMFW_ADSP2_ZM: + return cs_dsp_ctl_cache_test_algs[alg_index].zm_base_words; + default: + KUNIT_FAIL(test, "Bug in test: illegal memory type %d\n", mem_type); + return 0; + } +} + +static struct cs_dsp_mock_wmfw_builder *_create_dummy_wmfw(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_wmfw_builder *builder; + + builder = cs_dsp_mock_wmfw_init(priv, local->wmfw_version); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, builder); + + /* Init an XM header */ + cs_dsp_mock_wmfw_add_data_block(builder, + WMFW_ADSP2_XM, 0, + local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + return builder; +} + +/* + * Memory allocated for control cache must be large enough. + * This creates multiple controls of different sizes so only works on + * wmfw V2 and later. + */ +static void cs_dsp_ctl_v2_cache_alloc(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + unsigned int reg, alg_base_words, alg_size_bytes; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + char ctl_name[4]; + u32 *reg_vals; + int num_ctls; + + /* Create some DSP data to initialize the control cache */ + alg_base_words = _get_alg_mem_base_words(test, 0, WMFW_ADSP2_YM); + alg_size_bytes = cs_dsp_ctl_cache_test_algs[0].ym_size_words * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + reg_vals = kunit_kzalloc(test, alg_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + reg = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_YM); + reg += alg_base_words * cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, alg_size_bytes); + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[0].id, + "dummyalg", NULL); + + /* Create controls of different sizes */ + def.mem_type = WMFW_ADSP2_YM; + def.shortname = ctl_name; + num_ctls = 0; + for (def.length_bytes = 4; def.length_bytes <= 64; def.length_bytes += 4) { + snprintf(ctl_name, ARRAY_SIZE(ctl_name), "%x", def.length_bytes); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + num_ctls++; + def.offset_dsp_words += def.length_bytes / sizeof(u32); + } + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + KUNIT_EXPECT_EQ(test, list_count_nodes(&dsp->ctl_list), num_ctls); + + /* Check that the block allocated for the cache is large enough */ + list_for_each_entry(ctl, &dsp->ctl_list, list) + KUNIT_EXPECT_GE(test, ksize(ctl->cache), ctl->len); +} + +/* + * Content of registers backing a control should be read into the + * control cache when the firmware is downloaded. + */ +static void cs_dsp_ctl_cache_init(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* + * The data should have been populated into the control cache + * so should be readable through the control. + */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * For a non-volatile write-only control the cache should be zero-filled + * when the firmware is downloaded. + */ +static void cs_dsp_ctl_cache_init_write_only(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *readback, *zeros; + + zeros = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, zeros); + + readback = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create a non-volatile write-only control */ + def.flags = param->flags & ~WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* + * The control cache should have been zero-filled so should be + * readable through the control. + */ + get_random_bytes(readback, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, zeros, param->len_bytes); +} + +/* + * Multiple different firmware with identical controls. + * This is legal because different firmwares could contain the same + * algorithm. + * The control cache should be initialized only with the data from + * the firmware containing it. + */ +static void cs_dsp_ctl_cache_init_multiple_fw_same_controls(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder[3]; + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *walkctl, *ctl[3]; + struct firmware *wmfw; + u32 *reg_vals[3], *readback; + int i; + + static_assert(ARRAY_SIZE(ctl) == ARRAY_SIZE(builder)); + static_assert(ARRAY_SIZE(reg_vals) == ARRAY_SIZE(builder)); + static_assert(ARRAY_SIZE(cs_dsp_ctl_cache_test_fw_names) >= ARRAY_SIZE(builder)); + + /* Create an identical control in each firmware but with different alg id */ + for (i = 0; i < ARRAY_SIZE(builder); i++) { + builder[i] = _create_dummy_wmfw(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, builder[i]); + + cs_dsp_mock_wmfw_start_alg_info_block(builder[i], + cs_dsp_ctl_cache_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(builder[i], &def); + cs_dsp_mock_wmfw_end_alg_info_block(builder[i]); + } + + for (i = 0; i < ARRAY_SIZE(reg_vals); i++) { + reg_vals[i] = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals[i]); + } + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* + * For each firmware create random content in the register backing + * the control. Then download, start, stop and power-down. + */ + for (i = 0; i < ARRAY_SIZE(builder); i++) { + alg_base_words = _get_alg_mem_base_words(test, 0, def.mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, def.mem_type); + reg += (alg_base_words + def.offset_dsp_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + + get_random_bytes(reg_vals[i], def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals[i], def.length_bytes); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder[i]); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(dsp, wmfw, + cs_dsp_ctl_cache_test_fw_names[i], + NULL, NULL, + cs_dsp_ctl_cache_test_fw_names[i]), + 0); + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + cs_dsp_power_down(dsp); + } + + /* There should now be 3 controls */ + KUNIT_ASSERT_EQ(test, list_count_nodes(&dsp->ctl_list), 3); + + /* + * There's no requirement for the control list to be in any + * particular order, so don't assume the order. + */ + for (i = 0; i < ARRAY_SIZE(ctl); i++) + ctl[i] = NULL; + + list_for_each_entry(walkctl, &dsp->ctl_list, list) { + if (strcmp(walkctl->fw_name, cs_dsp_ctl_cache_test_fw_names[0]) == 0) + ctl[0] = walkctl; + else if (strcmp(walkctl->fw_name, cs_dsp_ctl_cache_test_fw_names[1]) == 0) + ctl[1] = walkctl; + else if (strcmp(walkctl->fw_name, cs_dsp_ctl_cache_test_fw_names[2]) == 0) + ctl[2] = walkctl; + } + + KUNIT_ASSERT_NOT_NULL(test, ctl[0]); + KUNIT_ASSERT_NOT_NULL(test, ctl[1]); + KUNIT_ASSERT_NOT_NULL(test, ctl[2]); + + /* + * The data should have been populated into the control cache + * so should be readable through the control. + */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[0], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[0], def.length_bytes); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[1], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[1], def.length_bytes); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[2], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[2], def.length_bytes); +} + +/* + * Multiple different firmware with controls identical except for alg id. + * This is legal because the controls are qualified by algorithm id. + * The control cache should be initialized only with the data from + * the firmware containing it. + */ +static void cs_dsp_ctl_cache_init_multiple_fwalgid_same_controls(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder[3]; + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *walkctl, *ctl[3]; + struct firmware *wmfw; + u32 *reg_vals[3], *readback; + int i; + + static_assert(ARRAY_SIZE(ctl) == ARRAY_SIZE(builder)); + static_assert(ARRAY_SIZE(reg_vals) == ARRAY_SIZE(builder)); + static_assert(ARRAY_SIZE(cs_dsp_ctl_cache_test_fw_names) >= ARRAY_SIZE(builder)); + + /* Create an identical control in each firmware but with different alg id */ + for (i = 0; i < ARRAY_SIZE(builder); i++) { + builder[i] = _create_dummy_wmfw(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, builder[i]); + + cs_dsp_mock_wmfw_start_alg_info_block(builder[i], + cs_dsp_ctl_cache_test_algs[i].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(builder[i], &def); + cs_dsp_mock_wmfw_end_alg_info_block(builder[i]); + } + + for (i = 0; i < ARRAY_SIZE(reg_vals); i++) { + reg_vals[i] = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals[i]); + } + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* + * For each firmware create random content in the register backing + * the control. Then download, start, stop and power-down. + */ + for (i = 0; i < ARRAY_SIZE(builder); i++) { + alg_base_words = _get_alg_mem_base_words(test, i, def.mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, def.mem_type); + reg += (alg_base_words + def.offset_dsp_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + + get_random_bytes(reg_vals[i], def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals[i], def.length_bytes); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder[i]); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(dsp, wmfw, + cs_dsp_ctl_cache_test_fw_names[i], + NULL, NULL, + cs_dsp_ctl_cache_test_fw_names[i]), + 0); + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + cs_dsp_power_down(dsp); + } + + /* There should now be 3 controls */ + KUNIT_ASSERT_EQ(test, list_count_nodes(&dsp->ctl_list), 3); + + /* + * There's no requirement for the control list to be in any + * particular order, so don't assume the order. + */ + for (i = 0; i < ARRAY_SIZE(ctl); i++) + ctl[i] = NULL; + + list_for_each_entry(walkctl, &dsp->ctl_list, list) { + if (cs_dsp_ctl_cache_test_algs[0].id == walkctl->alg_region.alg) + ctl[0] = walkctl; + else if (cs_dsp_ctl_cache_test_algs[1].id == walkctl->alg_region.alg) + ctl[1] = walkctl; + else if (cs_dsp_ctl_cache_test_algs[2].id == walkctl->alg_region.alg) + ctl[2] = walkctl; + } + + KUNIT_ASSERT_NOT_NULL(test, ctl[0]); + KUNIT_ASSERT_NOT_NULL(test, ctl[1]); + KUNIT_ASSERT_NOT_NULL(test, ctl[2]); + + /* + * The data should have been populated into the control cache + * so should be readable through the control. + */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[0], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[0], def.length_bytes); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[1], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[1], def.length_bytes); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[2], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[2], def.length_bytes); +} + +/* + * Firmware with controls at the same position in different memories. + * The control cache should be initialized with content from the + * correct memory region. + */ +static void cs_dsp_ctl_cache_init_multiple_mems(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *walkctl, *ctl[3]; + struct firmware *wmfw; + u32 *reg_vals[3], *readback; + int i; + + static_assert(ARRAY_SIZE(ctl) == ARRAY_SIZE(reg_vals)); + + for (i = 0; i < ARRAY_SIZE(reg_vals); i++) { + reg_vals[i] = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals[i]); + get_random_bytes(reg_vals[i], def.length_bytes); + } + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[0].id, + "dummyalg", NULL); + + /* Create controls identical except for memory region */ + def.mem_type = WMFW_ADSP2_YM; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + def.mem_type = WMFW_ADSP2_XM; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + if (cs_dsp_mock_has_zm(priv)) { + def.mem_type = WMFW_ADSP2_ZM; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + } + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Create random content in the registers backing each control */ + alg_base_words = _get_alg_mem_base_words(test, 0, WMFW_ADSP2_YM); + reg = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_YM); + reg += (alg_base_words + def.offset_dsp_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals[0], def.length_bytes); + + alg_base_words = _get_alg_mem_base_words(test, 0, WMFW_ADSP2_XM); + reg = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_XM); + reg += (alg_base_words + def.offset_dsp_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals[1], def.length_bytes); + + if (cs_dsp_mock_has_zm(priv)) { + alg_base_words = _get_alg_mem_base_words(test, 0, WMFW_ADSP2_ZM); + reg = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_ZM); + reg += (alg_base_words + def.offset_dsp_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals[2], def.length_bytes); + } + + /* Download, run, stop and power-down the firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + cs_dsp_power_down(dsp); + + /* There should now be 2 or 3 controls */ + KUNIT_ASSERT_EQ(test, list_count_nodes(&dsp->ctl_list), + cs_dsp_mock_has_zm(priv) ? 3 : 2); + + /* + * There's no requirement for the control list to be in any + * particular order, so don't assume the order. + */ + for (i = 0; i < ARRAY_SIZE(ctl); i++) + ctl[i] = NULL; + + list_for_each_entry(walkctl, &dsp->ctl_list, list) { + if (walkctl->alg_region.type == WMFW_ADSP2_YM) + ctl[0] = walkctl; + if (walkctl->alg_region.type == WMFW_ADSP2_XM) + ctl[1] = walkctl; + if (walkctl->alg_region.type == WMFW_ADSP2_ZM) + ctl[2] = walkctl; + } + + + /* + * The data should have been populated into the control cache + * so should be readable through the control. + */ + KUNIT_ASSERT_NOT_NULL(test, ctl[0]); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[0], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[0], def.length_bytes); + + KUNIT_ASSERT_NOT_NULL(test, ctl[1]); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[1], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[1], def.length_bytes); + + if (cs_dsp_mock_has_zm(priv)) { + KUNIT_ASSERT_NOT_NULL(test, ctl[2]); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[2], 0, readback, + def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[2], def.length_bytes); + } +} + +/* + * Firmware with controls at the same position in different algorithms + * The control cache should be initialized with content from the + * memory of the algorithm it points to. + */ +static void cs_dsp_ctl_cache_init_multiple_algs(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *walkctl, *ctl[3]; + struct firmware *wmfw; + u32 *reg_vals[3], *readback; + int i; + + static_assert(ARRAY_SIZE(ctl) == ARRAY_SIZE(reg_vals)); + static_assert(ARRAY_SIZE(reg_vals) <= ARRAY_SIZE(cs_dsp_ctl_cache_test_algs)); + + for (i = 0; i < ARRAY_SIZE(reg_vals); i++) { + reg_vals[i] = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals[i]); + get_random_bytes(reg_vals[i], def.length_bytes); + } + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create controls identical except for algorithm */ + for (i = 0; i < ARRAY_SIZE(reg_vals); i++) { + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[i].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + } + + /* Create random content in the registers backing each control */ + for (i = 0; i < ARRAY_SIZE(reg_vals); i++) { + alg_base_words = _get_alg_mem_base_words(test, i, def.mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, def.mem_type); + reg += (alg_base_words + def.offset_dsp_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals[i], def.length_bytes); + } + + /* Download, run, stop and power-down the firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + cs_dsp_power_down(dsp); + + /* There should now be 3 controls */ + KUNIT_ASSERT_EQ(test, list_count_nodes(&dsp->ctl_list), 3); + + /* + * There's no requirement for the control list to be in any + * particular order, so don't assume the order. + */ + for (i = 0; i < ARRAY_SIZE(ctl); i++) + ctl[i] = NULL; + + list_for_each_entry(walkctl, &dsp->ctl_list, list) { + if (walkctl->alg_region.alg == cs_dsp_ctl_cache_test_algs[0].id) + ctl[0] = walkctl; + if (walkctl->alg_region.alg == cs_dsp_ctl_cache_test_algs[1].id) + ctl[1] = walkctl; + if (walkctl->alg_region.alg == cs_dsp_ctl_cache_test_algs[2].id) + ctl[2] = walkctl; + } + + KUNIT_ASSERT_NOT_NULL(test, ctl[0]); + KUNIT_ASSERT_NOT_NULL(test, ctl[1]); + KUNIT_ASSERT_NOT_NULL(test, ctl[2]); + + /* + * The data should have been populated into the control cache + * so should be readable through the control. + */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[0], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[0], def.length_bytes); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[1], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[1], def.length_bytes); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[2], 0, readback, + def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[2], def.length_bytes); +} + +/* + * Firmware with controls in the same algorithm and memory but at + * different offsets. + * The control cache should be initialized with content from the + * correct offset. + * Only for wmfw format V2 and later. V1 only supports one control per + * memory per algorithm. + */ +static void cs_dsp_ctl_cache_init_multiple_offsets(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + unsigned int reg, alg_base_words, alg_base_reg; + struct cs_dsp_coeff_ctl *walkctl, *ctl[3]; + struct firmware *wmfw; + u32 *reg_vals[3], *readback; + int i; + + static_assert(ARRAY_SIZE(ctl) == ARRAY_SIZE(reg_vals)); + static_assert(ARRAY_SIZE(reg_vals) <= ARRAY_SIZE(cs_dsp_ctl_cache_test_algs)); + + for (i = 0; i < ARRAY_SIZE(reg_vals); i++) { + reg_vals[i] = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals[i]); + get_random_bytes(reg_vals[i], def.length_bytes); + } + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[0].id, + "dummyalg", NULL); + + /* Create controls identical except for offset */ + def.length_bytes = 8; + def.offset_dsp_words = 0; + def.shortname = "CtlA"; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + def.offset_dsp_words = 5; + def.shortname = "CtlB"; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + def.offset_dsp_words = 8; + def.shortname = "CtlC"; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Create random content in the registers backing each control */ + alg_base_words = _get_alg_mem_base_words(test, 0, def.mem_type); + alg_base_reg = cs_dsp_mock_base_addr_for_mem(priv, def.mem_type); + alg_base_reg += alg_base_words * cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + + reg = alg_base_reg; + regmap_raw_write(dsp->regmap, reg, reg_vals[0], def.length_bytes); + reg = alg_base_reg + (5 * cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv)); + regmap_raw_write(dsp->regmap, reg, reg_vals[1], def.length_bytes); + reg = alg_base_reg + (8 * cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv)); + regmap_raw_write(dsp->regmap, reg, reg_vals[2], def.length_bytes); + + /* Download, run, stop and power-down the firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + cs_dsp_power_down(dsp); + + /* There should now be 3 controls */ + KUNIT_ASSERT_EQ(test, list_count_nodes(&dsp->ctl_list), 3); + + /* + * There's no requirement for the control list to be in any + * particular order, so don't assume the order. + */ + for (i = 0; i < ARRAY_SIZE(ctl); i++) + ctl[i] = NULL; + + list_for_each_entry(walkctl, &dsp->ctl_list, list) { + if (walkctl->offset == 0) + ctl[0] = walkctl; + if (walkctl->offset == 5) + ctl[1] = walkctl; + if (walkctl->offset == 8) + ctl[2] = walkctl; + } + + KUNIT_ASSERT_NOT_NULL(test, ctl[0]); + KUNIT_ASSERT_NOT_NULL(test, ctl[1]); + KUNIT_ASSERT_NOT_NULL(test, ctl[2]); + + /* + * The data should have been populated into the control cache + * so should be readable through the control. + */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[0], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[0], def.length_bytes); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[1], 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[1], def.length_bytes); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl[2], 0, readback, + def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals[2], def.length_bytes); +} + +/* + * Read from a cached control before the firmware is started. + * Should return the data in the cache. + */ +static void cs_dsp_ctl_cache_read_not_started(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP but don't start firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the data from the control cache */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Read from a cached control after the firmware has been stopped. + * Should return the data in the cache. + */ +static void cs_dsp_ctl_cache_read_stopped(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start and stop the firmware */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the data from the control cache */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Read from a cached control after the DSP has been powered-up and + * then powered-down without running. + * Should return the data in the cache. + */ +static void cs_dsp_ctl_cache_read_powered_down(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP then power-down */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(dsp); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the data from the control cache */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Read from a cached control after the firmware has been run and + * stopped, then the DSP has been powered-down. + * Should return the data in the cache. + */ +static void cs_dsp_ctl_cache_read_stopped_powered_down(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start and stop the firmware then power-down */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + cs_dsp_power_down(dsp); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the data from the control cache */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Read from a cached control when a different firmware is currently + * loaded into the DSP. + * Should return the data in the cache. + */ +static void cs_dsp_ctl_cache_read_not_current_loaded_fw(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Power-down DSP then power-up with a different firmware */ + cs_dsp_power_down(dsp); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the data from the control cache */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Read from a cached control when a different firmware is currently + * running. + * Should return the data in the cache. + */ +static void cs_dsp_ctl_cache_read_not_current_running_fw(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP then power-down */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(dsp); + + /* Power-up with a different firmware and run it */ + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the data from the control cache */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Read from a cached control with non-zero flags while the firmware is + * running. + * Should return the data in the cache, not from the registers. + */ +static void cs_dsp_ctl_cache_read_running(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *init_reg_vals, *new_reg_vals, *readback; + + init_reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, init_reg_vals); + + new_reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, new_reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create data in the registers backing the control */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(init_reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, init_reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start the firmware running */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* + * Change the values in the registers backing the control then drop + * them from the regmap cache. This allows checking that the control + * read is returning values from the control cache and not accessing + * the registers. + */ + KUNIT_ASSERT_EQ(test, + regmap_raw_write(dsp->regmap, reg, new_reg_vals, param->len_bytes), + 0); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + /* Control should readback the origin data from its cache */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, init_reg_vals, param->len_bytes); + + /* Stop and power-down the DSP */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + cs_dsp_power_down(dsp); + + /* Control should readback from the cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, init_reg_vals, param->len_bytes); +} + +/* + * Read from a cached control with flags == 0 while the firmware is + * running. + * Should behave as volatile and read from the registers. + * (This is for backwards compatibility with old firmware versions) + */ +static void cs_dsp_ctl_cache_read_running_zero_flags(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *init_reg_vals, *new_reg_vals, *readback; + + init_reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, init_reg_vals); + + new_reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, new_reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Zero-fill the registers backing the control */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, init_reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = 0; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start the firmware running */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Change the values in the registers backing the control */ + get_random_bytes(new_reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, new_reg_vals, param->len_bytes); + + /* Control should readback the new data from the registers */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, new_reg_vals, param->len_bytes); + + /* Stop and power-down the DSP */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + cs_dsp_power_down(dsp); + + /* Change the values in the registers backing the control */ + regmap_raw_write(dsp->regmap, reg, init_reg_vals, param->len_bytes); + + /* Control should readback from the cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, new_reg_vals, param->len_bytes); +} + +/* + * Write to a cached control while the firmware is running. + * This should be a writethrough operation, writing to the cache and + * the registers. + */ +static void cs_dsp_ctl_cache_writethrough(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + memset(reg_vals, 0, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Write new data to the control, it should be written to the registers */ + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + KUNIT_ASSERT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write unchanged data to a cached control while the firmware is running. + * The control write should return 0 to indicate that the content + * didn't change. + */ +static void cs_dsp_ctl_cache_writethrough_unchanged(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* + * If the control is write-only the cache will have been zero-initialized + * so the first write will always indicate a change. + */ + if (def.flags && !(def.flags & WMFW_CTL_FLAG_READABLE)) { + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, + param->len_bytes), + 1); + } + + /* + * Write the same data to the control, cs_dsp_coeff_lock_and_write_ctrl() + * should return 0 to indicate the content didn't change. + */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); + KUNIT_ASSERT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write unchanged data to a cached control while the firmware is not started. + * The control write should return 0 to indicate that the cache content + * didn't change. + */ +static void cs_dsp_ctl_cache_write_unchanged_not_started(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* + * If the control is write-only the cache will have been zero-initialized + * so the first write will always indicate a change. + */ + if (def.flags && !(def.flags & WMFW_CTL_FLAG_READABLE)) { + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, + param->len_bytes), + 1); + } + + /* + * Write the same data to the control, cs_dsp_coeff_lock_and_write_ctrl() + * should return 0 to indicate the content didn't change. + */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); + KUNIT_ASSERT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write to a cached control while the firmware is loaded but not + * started. + * This should write to the cache only. + */ +static void cs_dsp_ctl_cache_write_not_started(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP but don't start firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Write new data to the control, it should not be written to the registers */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + + /* Registers should not have been written so regmap cache should still be clean */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write to a cached control after the firmware has been loaded, + * started and stopped. + * This should write to the cache only. + */ +static void cs_dsp_ctl_cache_write_stopped(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start and stop the firmware */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Write new data to the control, it should not be written to the registers */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + + /* Registers should not have been written so regmap cache should still be clean */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write to a cached control after the firmware has been loaded, + * then the DSP powered-down. + * This should write to the cache only. + */ +static void cs_dsp_ctl_cache_write_powered_down(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP then power-down */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(dsp); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Write new data to the control, it should not be written to the registers */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + + /* Registers should not have been written so regmap cache should still be clean */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write to a cached control after the firmware has been loaded, + * started, stopped, and then the DSP powered-down. + * This should write to the cache only. + */ +static void cs_dsp_ctl_cache_write_stopped_powered_down(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start and stop the firmware then power-down */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + cs_dsp_power_down(dsp); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Write new data to the control, it should not be written to the registers */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + + /* Registers should not have been written so regmap cache should still be clean */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write to a cached control that is not in the currently loaded firmware. + * This should write to the cache only. + */ +static void cs_dsp_ctl_cache_write_not_current_loaded_fw(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Get the control */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Power-down DSP then power-up with a different firmware */ + cs_dsp_power_down(dsp); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + + /* Control from unloaded firmware should be disabled */ + KUNIT_EXPECT_FALSE(test, ctl->enabled); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* + * It should be possible to write new data to the control from + * the first firmware. But this should not be written to the + * registers. + */ + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + + /* Registers should not have been written so regmap cache should still be clean */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write to a cached control that is not in the currently running firmware. + * This should write to the cache only. + */ +static void cs_dsp_ctl_cache_write_not_current_running_fw(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP then power-down */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(dsp); + + /* Get the control */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Power-up with a different firmware and run it */ + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Control from unloaded firmware should be disabled */ + KUNIT_EXPECT_FALSE(test, ctl->enabled); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* + * It should be possible to write new data to the control from + * the first firmware. But this should not be written to the + * registers. + */ + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + + /* Registers should not have been written so regmap cache should still be clean */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write to a cached control before running the firmware. + * The value written to the cache should be synced out to the registers + * backing the control when the firmware is run. + */ +static void cs_dsp_ctl_cache_sync_write_before_run(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP but don't start firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Write new data to the control, it should not be written to the registers */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMNEQ(test, readback, reg_vals, param->len_bytes); + + /* Start the firmware and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write to a cached control while the firmware is running. + * The value written should be synced out to the registers + * backing the control when the firmware is next run. + */ +static void cs_dsp_ctl_cache_sync_write_while_running(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *init_vals, *ctl_vals, *readback; + + init_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, init_vals); + + ctl_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctl_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Zero-fill the registers backing the control */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, init_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP and start firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Write new data to the control */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(ctl_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, ctl_vals, param->len_bytes), + 1); + + /* Stop firmware and zero the registers backing the control */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + regmap_raw_write(dsp->regmap, reg, init_vals, param->len_bytes); + KUNIT_ASSERT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, init_vals, param->len_bytes); + + /* Start the firmware and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); +} + +/* + * Write to a cached control after stopping the firmware. + * The value written to the cache should be synced out to the registers + * backing the control when the firmware is next run. + */ +static void cs_dsp_ctl_cache_sync_write_after_stop(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP but don't start firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start and stop the firmware */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + + /* Write new data to the control, it should not be written to the registers */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMNEQ(test, readback, reg_vals, param->len_bytes); + + /* Start the firmware and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Write to a cached control that is not in the currently loaded firmware. + * The value written to the cache should be synced out to the registers + * backing the control the next time the firmware containing the + * control is run. + */ +static void cs_dsp_ctl_cache_sync_write_not_current_fw(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP but don't start firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Get the control */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Power-down DSP then power-up with a different firmware */ + cs_dsp_power_down(dsp); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + + /* Write new data to the control, it should not be written to the registers */ + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMNEQ(test, readback, reg_vals, param->len_bytes); + + /* Power-down DSP then power-up with the original firmware */ + cs_dsp_power_down(dsp); + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start the firmware and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * The value in the control cache should be synced out to the registers + * backing the control every time the firmware containing the control + * is run. + */ +static void cs_dsp_ctl_cache_sync_reapply_every_run(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *init_vals, *readback, *ctl_vals; + + init_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, init_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + ctl_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctl_vals); + + /* Zero-fill the registers backing the control */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, init_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP but don't start firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Write new data to the control */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(ctl_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, ctl_vals, param->len_bytes), + 1); + + /* Start the firmware and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); + + /* Stop the firmware and reset the registers */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + regmap_raw_write(dsp->regmap, reg, init_vals, param->len_bytes); + + /* Start the firmware again and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); +} + +/* + * The value in the control cache should be retained if the same + * firmware is downloaded again. It should be synced out to the + * registers backing the control after the firmware containing the + * control is downloaded again and run. + */ +static void cs_dsp_ctl_cache_sync_reapply_after_fw_reload(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *init_vals, *readback, *ctl_vals; + + init_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, init_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + ctl_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctl_vals); + + /* Zero-fill the registers backing the control */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, init_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP but don't start firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Write new data to the control */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(ctl_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, ctl_vals, param->len_bytes), + 1); + + /* Start the firmware and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); + + /* Stop the firmware and power-down the DSP */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + cs_dsp_power_down(dsp); + + /* Reset the registers */ + regmap_raw_write(dsp->regmap, reg, init_vals, param->len_bytes); + + /* Download the firmware again, the cache content should not change */ + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start the firmware and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); +} + +/* + * The value in the control cache should be retained after a different + * firmware is downloaded. + * When the firmware containing the control is downloaded and run + * the value in the control cache should be synced out to the registers + * backing the control. + */ +static void cs_dsp_ctl_cache_sync_reapply_after_fw_swap(struct kunit *test) +{ + const struct cs_dsp_ctl_cache_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *init_vals, *readback, *ctl_vals; + + init_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, init_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + ctl_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctl_vals); + + /* Zero-fill the registers backing the control */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, init_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_cache_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP but don't start firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Write new data to the control */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + get_random_bytes(ctl_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, ctl_vals, param->len_bytes), + 1); + + /* Start the firmware and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); + + /* Stop the firmware and power-down the DSP */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + cs_dsp_power_down(dsp); + + /* Reset the registers */ + regmap_raw_write(dsp->regmap, reg, init_vals, param->len_bytes); + + /* Download and run a different firmware */ + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_power_down(dsp); + + /* Reset the registers */ + regmap_raw_write(dsp->regmap, reg, init_vals, param->len_bytes); + + /* Download the original firmware again */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + KUNIT_EXPECT_TRUE(test, ctl->set); + + /* Start the firmware and the cached data should be written to registers */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + KUNIT_EXPECT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); + + /* Control should readback the new data from the control cache */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, param->len_bytes); +} + +static int cs_dsp_ctl_cache_test_common_init(struct kunit *test, struct cs_dsp *dsp, + int wmfw_version) +{ + struct cs_dsp_test *priv; + struct cs_dsp_test_local *local; + struct device *test_dev; + int ret; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + local = kunit_kzalloc(test, sizeof(struct cs_dsp_test_local), GFP_KERNEL); + if (!local) + return -ENOMEM; + + priv->test = test; + priv->dsp = dsp; + test->priv = priv; + priv->local = local; + priv->local->wmfw_version = wmfw_version; + + /* Create dummy struct device */ + test_dev = kunit_device_register(test, "cs_dsp_test_drv"); + if (IS_ERR(test_dev)) + return PTR_ERR(test_dev); + + dsp->dev = get_device(test_dev); + if (!dsp->dev) + return -ENODEV; + + ret = kunit_add_action_or_reset(test, _put_device_wrapper, dsp->dev); + if (ret) + return ret; + + dev_set_drvdata(dsp->dev, priv); + + /* Allocate regmap */ + ret = cs_dsp_mock_regmap_init(priv); + if (ret) + return ret; + + /* + * There must always be a XM header with at least 1 algorithm, so create + * a dummy one that tests can use and extract it to a data blob. + */ + local->xm_header = cs_dsp_create_mock_xm_header(priv, + cs_dsp_ctl_cache_test_algs, + ARRAY_SIZE(cs_dsp_ctl_cache_test_algs)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->xm_header); + + /* Create wmfw builder */ + local->wmfw_builder = _create_dummy_wmfw(test); + + /* Init cs_dsp */ + dsp->client_ops = kunit_kzalloc(test, sizeof(*dsp->client_ops), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dsp->client_ops); + + switch (dsp->type) { + case WMFW_ADSP2: + ret = cs_dsp_adsp2_init(dsp); + break; + case WMFW_HALO: + ret = cs_dsp_halo_init(dsp); + break; + default: + KUNIT_FAIL(test, "Untested DSP type %d\n", dsp->type); + return -EINVAL; + } + + if (ret) + return ret; + + /* Automatically call cs_dsp_remove() when test case ends */ + return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); +} + +static int cs_dsp_ctl_cache_test_halo_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_HALO; + dsp->mem = cs_dsp_mock_halo_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_halo_dsp1_region_sizes); + dsp->base = cs_dsp_mock_halo_core_base; + dsp->base_sysinfo = cs_dsp_mock_halo_sysinfo_base; + + return cs_dsp_ctl_cache_test_common_init(test, dsp, 3); +} + +static int cs_dsp_ctl_cache_test_adsp2_32bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 1; + dsp->mem = cs_dsp_mock_adsp2_32bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_32bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_32bit_sysbase; + + return cs_dsp_ctl_cache_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_ctl_cache_test_adsp2_32bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_ctl_cache_test_adsp2_32bit_init(test, 1); +} + +static int cs_dsp_ctl_cache_test_adsp2_32bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_ctl_cache_test_adsp2_32bit_init(test, 2); +} + +static int cs_dsp_ctl_cache_test_adsp2_16bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 0; + dsp->mem = cs_dsp_mock_adsp2_16bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_16bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_16bit_sysbase; + + return cs_dsp_ctl_cache_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_ctl_cache_test_adsp2_16bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_ctl_cache_test_adsp2_16bit_init(test, 1); +} + +static int cs_dsp_ctl_cache_test_adsp2_16bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_ctl_cache_test_adsp2_16bit_init(test, 2); +} + +static void cs_dsp_ctl_all_param_desc(const struct cs_dsp_ctl_cache_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "alg:%#x %s@%u len:%u flags:%#x", + param->alg_id, cs_dsp_mem_region_name(param->mem_type), + param->offs_words, param->len_bytes, param->flags); +} + +/* All parameters populated, with various lengths */ +static const struct cs_dsp_ctl_cache_test_param all_pop_varying_len_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 8 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 12 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 16 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 48 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 100 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 512 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 1000 }, +}; +KUNIT_ARRAY_PARAM(all_pop_varying_len, all_pop_varying_len_cases, + cs_dsp_ctl_all_param_desc); + +/* All parameters populated, with various offsets */ +static const struct cs_dsp_ctl_cache_test_param all_pop_varying_offset_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 0, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 2, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 3, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 8, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 10, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 128, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 180, .len_bytes = 4 }, +}; +KUNIT_ARRAY_PARAM(all_pop_varying_offset, all_pop_varying_offset_cases, + cs_dsp_ctl_all_param_desc); + +/* All parameters populated, with various X and Y memory regions */ +static const struct cs_dsp_ctl_cache_test_param all_pop_varying_xy_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_XM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, +}; +KUNIT_ARRAY_PARAM(all_pop_varying_xy, all_pop_varying_xy_cases, + cs_dsp_ctl_all_param_desc); + +/* All parameters populated, using ZM */ +static const struct cs_dsp_ctl_cache_test_param all_pop_z_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_ZM, .offs_words = 1, .len_bytes = 4 }, +}; +KUNIT_ARRAY_PARAM(all_pop_z, all_pop_z_cases, cs_dsp_ctl_all_param_desc); + +/* All parameters populated, with various algorithm ids */ +static const struct cs_dsp_ctl_cache_test_param all_pop_varying_alg_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xb, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0x9f1234, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xff00ff, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, +}; +KUNIT_ARRAY_PARAM(all_pop_varying_alg, all_pop_varying_alg_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * non-volatile readable control + */ +static const struct cs_dsp_ctl_cache_test_param all_pop_nonvol_readable_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = 0 + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_nonvol_readable_flags, + all_pop_nonvol_readable_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * non-volatile readable control, except flags==0 + */ +static const struct cs_dsp_ctl_cache_test_param all_pop_nonvol_readable_nonzero_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_nonvol_readable_nonzero_flags, + all_pop_nonvol_readable_nonzero_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * non-volatile writeable control + */ +static const struct cs_dsp_ctl_cache_test_param all_pop_nonvol_writeable_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = 0 + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_nonvol_writeable_flags, + all_pop_nonvol_writeable_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * non-volatile write-only control of varying lengths + */ +static const struct cs_dsp_ctl_cache_test_param all_pop_nonvol_write_only_length_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 512, + .flags = WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 512, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_nonvol_write_only_length, + all_pop_nonvol_write_only_length_cases, + cs_dsp_ctl_all_param_desc); + +static struct kunit_case cs_dsp_ctl_cache_test_cases_v1[] = { + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_z_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_nonvol_readable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init_write_only, + all_pop_nonvol_write_only_length_gen_params), + + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_fw_same_controls), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_fwalgid_same_controls), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_mems), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_algs), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_not_started, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_stopped, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_powered_down, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_stopped_powered_down, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_not_current_loaded_fw, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_not_current_running_fw, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_running, + all_pop_nonvol_readable_nonzero_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_running_zero_flags, + all_pop_varying_len_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_z_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_z_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_unchanged_not_started, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_not_started, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_stopped, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_powered_down, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_stopped_powered_down, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_not_current_loaded_fw, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_not_current_running_fw, + all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_before_run, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_while_running, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_after_stop, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_not_current_fw, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_reapply_every_run, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_reapply_after_fw_reload, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_reapply_after_fw_swap, + all_pop_nonvol_writeable_flags_gen_params), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_ctl_cache_test_cases_v2[] = { + KUNIT_CASE(cs_dsp_ctl_v2_cache_alloc), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_z_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_nonvol_readable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init_write_only, + all_pop_nonvol_write_only_length_gen_params), + + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_fw_same_controls), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_fwalgid_same_controls), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_mems), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_algs), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_offsets), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_not_started, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_stopped, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_powered_down, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_stopped_powered_down, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_not_current_loaded_fw, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_not_current_running_fw, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_running, + all_pop_nonvol_readable_nonzero_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_running_zero_flags, + all_pop_varying_len_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_z_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_z_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_unchanged_not_started, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_not_started, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_stopped, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_powered_down, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_stopped_powered_down, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_not_current_loaded_fw, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_not_current_running_fw, + all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_before_run, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_while_running, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_after_stop, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_not_current_fw, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_reapply_every_run, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_reapply_after_fw_reload, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_reapply_after_fw_swap, + all_pop_nonvol_writeable_flags_gen_params), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_ctl_cache_test_cases_v3[] = { + KUNIT_CASE(cs_dsp_ctl_v2_cache_alloc), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init, all_pop_nonvol_readable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_init_write_only, + all_pop_nonvol_write_only_length_gen_params), + + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_fw_same_controls), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_fwalgid_same_controls), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_mems), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_algs), + KUNIT_CASE(cs_dsp_ctl_cache_init_multiple_offsets), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_not_started, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_stopped, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_powered_down, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_stopped_powered_down, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_not_current_loaded_fw, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_not_current_running_fw, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_read_running, + all_pop_nonvol_readable_nonzero_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough, all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_writethrough_unchanged, + all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_unchanged_not_started, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_not_started, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_stopped, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_powered_down, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_stopped_powered_down, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_not_current_loaded_fw, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_write_not_current_running_fw, + all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_before_run, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_while_running, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_after_stop, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_write_not_current_fw, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_reapply_every_run, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_reapply_after_fw_reload, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_cache_sync_reapply_after_fw_swap, + all_pop_nonvol_writeable_flags_gen_params), + + { } /* terminator */ +}; + +static struct kunit_suite cs_dsp_ctl_cache_test_halo = { + .name = "cs_dsp_ctl_cache_wmfwV3_halo", + .init = cs_dsp_ctl_cache_test_halo_init, + .test_cases = cs_dsp_ctl_cache_test_cases_v3, +}; + +static struct kunit_suite cs_dsp_ctl_cache_test_adsp2_32bit_wmfw1 = { + .name = "cs_dsp_ctl_cache_wmfwV1_adsp2_32bit", + .init = cs_dsp_ctl_cache_test_adsp2_32bit_wmfw1_init, + .test_cases = cs_dsp_ctl_cache_test_cases_v1, +}; + +static struct kunit_suite cs_dsp_ctl_cache_test_adsp2_32bit_wmfw2 = { + .name = "cs_dsp_ctl_cache_wmfwV2_adsp2_32bit", + .init = cs_dsp_ctl_cache_test_adsp2_32bit_wmfw2_init, + .test_cases = cs_dsp_ctl_cache_test_cases_v2, +}; + +static struct kunit_suite cs_dsp_ctl_cache_test_adsp2_16bit_wmfw1 = { + .name = "cs_dsp_ctl_cache_wmfwV1_adsp2_16bit", + .init = cs_dsp_ctl_cache_test_adsp2_16bit_wmfw1_init, + .test_cases = cs_dsp_ctl_cache_test_cases_v1, +}; + +static struct kunit_suite cs_dsp_ctl_cache_test_adsp2_16bit_wmfw2 = { + .name = "cs_dsp_ctl_cache_wmfwV2_adsp2_16bit", + .init = cs_dsp_ctl_cache_test_adsp2_16bit_wmfw2_init, + .test_cases = cs_dsp_ctl_cache_test_cases_v2, +}; + +kunit_test_suites(&cs_dsp_ctl_cache_test_halo, + &cs_dsp_ctl_cache_test_adsp2_32bit_wmfw1, + &cs_dsp_ctl_cache_test_adsp2_32bit_wmfw2, + &cs_dsp_ctl_cache_test_adsp2_16bit_wmfw1, + &cs_dsp_ctl_cache_test_adsp2_16bit_wmfw2); diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_control_parse.c b/drivers/firmware/cirrus/test/cs_dsp_test_control_parse.c new file mode 100644 index 000000000000..cb90964740ea --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_test_control_parse.c @@ -0,0 +1,1851 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// KUnit tests for cs_dsp. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *); +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *); + +struct cs_dsp_test_local { + struct cs_dsp_mock_xm_header *xm_header; + struct cs_dsp_mock_wmfw_builder *wmfw_builder; + int wmfw_version; +}; + +struct cs_dsp_ctl_parse_test_param { + int mem_type; + int alg_id; + unsigned int offset; + unsigned int length; + u16 ctl_type; + u16 flags; +}; + +static const struct cs_dsp_mock_alg_def cs_dsp_ctl_parse_test_algs[] = { + { + .id = 0xfafa, + .ver = 0x100000, + .xm_size_words = 164, + .ym_size_words = 164, + .zm_size_words = 164, + }, + { + .id = 0xb, + .ver = 0x100001, + .xm_size_words = 8, + .ym_size_words = 8, + .zm_size_words = 8, + }, + { + .id = 0x9f1234, + .ver = 0x100500, + .xm_size_words = 16, + .ym_size_words = 16, + .zm_size_words = 16, + }, + { + .id = 0xff00ff, + .ver = 0x300113, + .xm_size_words = 16, + .ym_size_words = 16, + .zm_size_words = 16, + }, +}; + +static const struct cs_dsp_mock_coeff_def mock_coeff_template = { + .shortname = "Dummy Coeff", + .type = WMFW_CTL_TYPE_BYTES, + .mem_type = WMFW_ADSP2_YM, + .flags = WMFW_CTL_FLAG_VOLATILE, + .length_bytes = 4, +}; + +/* Algorithm info block without controls should load */ +static void cs_dsp_ctl_parse_no_coeffs(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); +} + +/* + * V1 controls do not have names, the name field in the coefficient entry + * should be ignored. + */ +static void cs_dsp_ctl_parse_v1_name(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + def.fullname = "Dummy"; + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, 0); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * V1 controls do not have names, the name field in the coefficient entry + * should be ignored. Test with a zero-length name string. + */ +static void cs_dsp_ctl_parse_empty_v1_name(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + def.fullname = "\0"; + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, 0); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * V1 controls do not have names, the name field in the coefficient entry + * should be ignored. Test with a maximum length name string. + */ +static void cs_dsp_ctl_parse_max_v1_name(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + char *name; + + name = kunit_kzalloc(test, 256, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, name); + memset(name, 'A', 255); + def.fullname = name; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, 0); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* Short name from coeff descriptor should be used as control name. */ +static void cs_dsp_ctl_parse_short_name(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, strlen(def.shortname)); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, def.shortname, ctl->subname_len); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * Short name from coeff descriptor should be used as control name. + * Test with a short name that is a single character. + */ +static void cs_dsp_ctl_parse_min_short_name(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + def.shortname = "Q"; + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, 1); + KUNIT_EXPECT_EQ(test, ctl->subname[0], 'Q'); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * Short name from coeff descriptor should be used as control name. + * Test with a maximum length name. + */ +static void cs_dsp_ctl_parse_max_short_name(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + char *name; + struct firmware *wmfw; + + name = kunit_kmalloc(test, 255, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, name); + memset(name, 'A', 255); + + def.shortname = name; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, 255); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, name, ctl->subname_len); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * Full name from coeff descriptor should be ignored. It is a variable + * length field so affects the position of subsequent fields. + * Test with a 1-character full name. + */ +static void cs_dsp_ctl_parse_with_min_fullname(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + def.fullname = "Q"; + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, strlen(def.shortname)); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, def.shortname, ctl->subname_len); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * Full name from coeff descriptor should be ignored. It is a variable + * length field so affects the position of subsequent fields. + * Test with a maximum length full name. + */ +static void cs_dsp_ctl_parse_with_max_fullname(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + char *fullname; + + fullname = kunit_kmalloc(test, 255, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, fullname); + memset(fullname, 'A', 255); + def.fullname = fullname; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, strlen(def.shortname)); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, def.shortname, ctl->subname_len); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * Description from coeff descriptor should be ignored. It is a variable + * length field so affects the position of subsequent fields. + * Test with a 1-character description + */ +static void cs_dsp_ctl_parse_with_min_description(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + def.description = "Q"; + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, strlen(def.shortname)); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, def.shortname, ctl->subname_len); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * Description from coeff descriptor should be ignored. It is a variable + * length field so affects the position of subsequent fields. + * Test with a maximum length description + */ +static void cs_dsp_ctl_parse_with_max_description(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + char *description; + + description = kunit_kmalloc(test, 65535, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, description); + memset(description, 'A', 65535); + def.description = description; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, strlen(def.shortname)); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, def.shortname, ctl->subname_len); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * Full name and description from coeff descriptor are variable length + * fields so affects the position of subsequent fields. + * Test with a maximum length full name and description + */ +static void cs_dsp_ctl_parse_with_max_fullname_and_description(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + char *fullname, *description; + + fullname = kunit_kmalloc(test, 255, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, fullname); + memset(fullname, 'A', 255); + def.fullname = fullname; + + description = kunit_kmalloc(test, 65535, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, description); + memset(description, 'A', 65535); + def.description = description; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, strlen(def.shortname)); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, def.shortname, ctl->subname_len); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +static const char * const cs_dsp_ctl_alignment_test_names[] = { + "1", "12", "123", "1234", "12345", "123456", "1234567", + "12345678", "123456789", "123456789A", "123456789AB", + "123456789ABC", "123456789ABCD", "123456789ABCDE", + "123456789ABCDEF", +}; + +/* + * Variable-length string fields are padded to a multiple of 4-bytes. + * Test this with various lengths of short name. + */ +static void cs_dsp_ctl_shortname_alignment(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + int i; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_alignment_test_names); i++) { + def.shortname = cs_dsp_ctl_alignment_test_names[i]; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + } + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_alignment_test_names); i++) { + mutex_lock(&priv->dsp->pwr_lock); + ctl = cs_dsp_get_ctl(priv->dsp, cs_dsp_ctl_alignment_test_names[i], + def.mem_type, cs_dsp_ctl_parse_test_algs[0].id); + mutex_unlock(&priv->dsp->pwr_lock); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, i + 1); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, cs_dsp_ctl_alignment_test_names[i], + ctl->subname_len); + /* Test fields that are parsed after the variable-length fields */ + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); + } +} + +/* + * Variable-length string fields are padded to a multiple of 4-bytes. + * Test this with various lengths of full name. + */ +static void cs_dsp_ctl_fullname_alignment(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + char ctl_name[4]; + struct firmware *wmfw; + int i; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_alignment_test_names); i++) { + /* + * Create a unique control name of 3 characters so that + * the shortname field is exactly 4 bytes long including + * the length byte. + */ + snprintf(ctl_name, sizeof(ctl_name), "%03d", i); + KUNIT_ASSERT_EQ(test, strlen(ctl_name), 3); + def.shortname = ctl_name; + + def.fullname = cs_dsp_ctl_alignment_test_names[i]; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + } + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_alignment_test_names); i++) { + snprintf(ctl_name, sizeof(ctl_name), "%03d", i); + + mutex_lock(&priv->dsp->pwr_lock); + ctl = cs_dsp_get_ctl(priv->dsp, ctl_name, def.mem_type, + cs_dsp_ctl_parse_test_algs[0].id); + mutex_unlock(&priv->dsp->pwr_lock); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, 3); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, ctl_name, ctl->subname_len); + /* Test fields that are parsed after the variable-length fields */ + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); + } +} + +/* + * Variable-length string fields are padded to a multiple of 4-bytes. + * Test this with various lengths of description. + */ +static void cs_dsp_ctl_description_alignment(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + char ctl_name[4]; + struct firmware *wmfw; + int i; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_alignment_test_names); i++) { + /* + * Create a unique control name of 3 characters so that + * the shortname field is exactly 4 bytes long including + * the length byte. + */ + snprintf(ctl_name, sizeof(ctl_name), "%03d", i); + KUNIT_ASSERT_EQ(test, strlen(ctl_name), 3); + def.shortname = ctl_name; + + def.description = cs_dsp_ctl_alignment_test_names[i]; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + } + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_alignment_test_names); i++) { + snprintf(ctl_name, sizeof(ctl_name), "%03d", i); + + mutex_lock(&priv->dsp->pwr_lock); + ctl = cs_dsp_get_ctl(priv->dsp, ctl_name, def.mem_type, + cs_dsp_ctl_parse_test_algs[0].id); + mutex_unlock(&priv->dsp->pwr_lock); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, 3); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, ctl_name, ctl->subname_len); + /* Test fields that are parsed after the variable-length fields */ + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); + } +} + +static const char * const cs_dsp_get_ctl_test_names[] = { + "Up", "Down", "Switch", "Mute", + "Left Up", "Left Down", "Right Up", "Right Down", + "Left Mute", "Right Mute", + "_trunc_1", "_trunc_2", " trunc", +}; + +/* Test using cs_dsp_get_ctl() to lookup various controls. */ +static void cs_dsp_get_ctl_test(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + int i; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_get_ctl_test_names); i++) { + def.shortname = cs_dsp_get_ctl_test_names[i]; + def.offset_dsp_words = i; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + } + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_get_ctl_test_names); i++) { + mutex_lock(&priv->dsp->pwr_lock); + ctl = cs_dsp_get_ctl(priv->dsp, cs_dsp_get_ctl_test_names[i], + def.mem_type, cs_dsp_ctl_parse_test_algs[0].id); + mutex_unlock(&priv->dsp->pwr_lock); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, strlen(cs_dsp_get_ctl_test_names[i])); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, cs_dsp_get_ctl_test_names[i], + ctl->subname_len); + KUNIT_EXPECT_EQ(test, ctl->offset, i); + } +} + +/* + * cs_dsp_get_ctl() searches for the control in the currently loaded + * firmware, so create identical controls in multiple firmware and + * test that the correct one is found. + */ +static void cs_dsp_get_ctl_test_multiple_wmfw(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct cs_dsp_mock_wmfw_builder *builder2; + struct firmware *wmfw; + + def.shortname = "_A_CONTROL"; + + /* Create a second mock wmfw builder */ + builder2 = cs_dsp_mock_wmfw_init(priv, + cs_dsp_mock_wmfw_format_version(local->wmfw_builder)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, builder2); + cs_dsp_mock_wmfw_add_data_block(builder2, + WMFW_ADSP2_XM, 0, + local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + /* Load a 'misc' firmware with a control */ + def.offset_dsp_words = 1; + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(priv->dsp); + + /* Load a 'mbc/vss' firmware with a control of the same name */ + def.offset_dsp_words = 2; + cs_dsp_mock_wmfw_start_alg_info_block(builder2, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(builder2, &def); + cs_dsp_mock_wmfw_end_alg_info_block(builder2); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_fw2", NULL, NULL, "mbc/vss"), 0); + + /* A lookup should return the control for the current firmware */ + mutex_lock(&priv->dsp->pwr_lock); + ctl = cs_dsp_get_ctl(priv->dsp, def.shortname, + def.mem_type, cs_dsp_ctl_parse_test_algs[0].id); + mutex_unlock(&priv->dsp->pwr_lock); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->offset, 2); + + /* Re-load the 'misc' firmware and a lookup should return its control */ + cs_dsp_power_down(priv->dsp); + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + mutex_lock(&priv->dsp->pwr_lock); + ctl = cs_dsp_get_ctl(priv->dsp, def.shortname, + def.mem_type, cs_dsp_ctl_parse_test_algs[0].id); + mutex_unlock(&priv->dsp->pwr_lock); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->offset, 1); +} + +/* Test that the value of the memory type field is parsed correctly. */ +static void cs_dsp_ctl_parse_memory_type(struct kunit *test) +{ + const struct cs_dsp_ctl_parse_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + /* kunit_skip() marks the test skipped forever, so just return */ + if ((param->mem_type == WMFW_ADSP2_ZM) && !cs_dsp_mock_has_zm(priv)) + return; + + def.mem_type = param->mem_type; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->alg_region.type, param->mem_type); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * Test that the algorithm id from the parent alg-info block is + * correctly stored in the cs_dsp_coeff_ctl. + */ +static void cs_dsp_ctl_parse_alg_id(struct kunit *test) +{ + const struct cs_dsp_ctl_parse_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + param->alg_id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->alg_region.alg, param->alg_id); + KUNIT_EXPECT_EQ(test, ctl->alg_region.type, def.mem_type); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* + * Test that the values of (alg id, memory type) tuple is parsed correctly. + * The alg id is parsed from the alg-info block, but the memory type is + * parsed from the coefficient info descriptor. + */ +static void cs_dsp_ctl_parse_alg_mem(struct kunit *test) +{ + const struct cs_dsp_ctl_parse_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + /* kunit_skip() marks the test skipped forever, so just return */ + if ((param->mem_type == WMFW_ADSP2_ZM) && !cs_dsp_mock_has_zm(priv)) + return; + + def.mem_type = param->mem_type; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + param->alg_id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->alg_region.alg, param->alg_id); + KUNIT_EXPECT_EQ(test, ctl->alg_region.type, param->mem_type); +} + +/* Test that the value of the offset field is parsed correctly. */ +static void cs_dsp_ctl_parse_offset(struct kunit *test) +{ + const struct cs_dsp_ctl_parse_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + def.offset_dsp_words = param->offset; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->offset, param->offset); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* Test that the value of the length field is parsed correctly. */ +static void cs_dsp_ctl_parse_length(struct kunit *test) +{ + const struct cs_dsp_ctl_parse_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + def.length_bytes = param->length; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->offset, def.offset_dsp_words); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->len, param->length); +} + +/* Test that the value of the control type field is parsed correctly. */ +static void cs_dsp_ctl_parse_ctl_type(struct kunit *test) +{ + const struct cs_dsp_ctl_parse_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + + def.type = param->ctl_type; + def.flags = param->flags; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->type, param->ctl_type); + KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* Test that the value of the flags field is parsed correctly. */ +static void cs_dsp_ctl_parse_flags(struct kunit *test) +{ + const struct cs_dsp_ctl_parse_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 reg_val; + + /* + * Non volatile controls will be read to initialize the cache + * so the regmap cache must contain something to read. + */ + reg_val = 0xf11100; + regmap_raw_write(priv->dsp->regmap, + cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_YM), + ®_val, sizeof(reg_val)); + + def.flags = param->flags; + def.mem_type = WMFW_ADSP2_YM; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->type, def.type); + KUNIT_EXPECT_EQ(test, ctl->flags, param->flags); + KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); +} + +/* Test that invalid combinations of (control type, flags) are rejected. */ +static void cs_dsp_ctl_illegal_type_flags(struct kunit *test) +{ + const struct cs_dsp_ctl_parse_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct firmware *wmfw; + u32 reg_val; + + /* + * Non volatile controls will be read to initialize the cache + * so the regmap cache must contain something to read. + */ + reg_val = 0xf11100; + regmap_raw_write(priv->dsp->regmap, + cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_YM), + ®_val, sizeof(reg_val)); + + def.type = param->ctl_type; + def.flags = param->flags; + def.mem_type = WMFW_ADSP2_YM; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_LT(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); +} + +/* Test that the correct firmware name is entered in the cs_dsp_coeff_ctl. */ +static void cs_dsp_ctl_parse_fw_name(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *walkctl, *ctl1, *ctl2; + struct cs_dsp_mock_wmfw_builder *builder2; + struct firmware *wmfw; + + /* Create a second mock wmfw builder */ + builder2 = cs_dsp_mock_wmfw_init(priv, + cs_dsp_mock_wmfw_format_version(local->wmfw_builder)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, builder2); + cs_dsp_mock_wmfw_add_data_block(builder2, + WMFW_ADSP2_XM, 0, + local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + /* Load a 'misc' firmware with a control */ + def.offset_dsp_words = 1; + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(priv->dsp); + + /* Load a 'mbc/vss' firmware with a control */ + def.offset_dsp_words = 2; + cs_dsp_mock_wmfw_start_alg_info_block(builder2, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(builder2, &def); + cs_dsp_mock_wmfw_end_alg_info_block(builder2); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_fw2", NULL, NULL, "mbc/vss"), 0); + + /* Both controls should be in the list (order not guaranteed) */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), 2); + ctl1 = NULL; + ctl2 = NULL; + list_for_each_entry(walkctl, &priv->dsp->ctl_list, list) { + if (strcmp(walkctl->fw_name, "misc") == 0) + ctl1 = walkctl; + else if (strcmp(walkctl->fw_name, "mbc/vss") == 0) + ctl2 = walkctl; + } + + KUNIT_EXPECT_NOT_NULL(test, ctl1); + KUNIT_EXPECT_NOT_NULL(test, ctl2); + KUNIT_EXPECT_EQ(test, ctl1->offset, 1); + KUNIT_EXPECT_EQ(test, ctl2->offset, 2); +} + +/* Controls are unique if the algorithm ID is different */ +static void cs_dsp_ctl_alg_id_uniqueness(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl1, *ctl2; + struct firmware *wmfw; + + /* Create an algorithm containing the control */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Create a different algorithm containing an identical control */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[1].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(priv->dsp); + + /* Both controls should be in the list */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), 2); + ctl1 = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + ctl2 = list_next_entry(ctl1, list); + KUNIT_EXPECT_NOT_NULL(test, ctl1); + KUNIT_EXPECT_NOT_NULL(test, ctl2); + KUNIT_EXPECT_NE(test, ctl1->alg_region.alg, ctl2->alg_region.alg); + KUNIT_EXPECT_EQ(test, ctl1->alg_region.type, ctl2->alg_region.type); + KUNIT_EXPECT_EQ(test, ctl1->offset, ctl2->offset); + KUNIT_EXPECT_EQ(test, ctl1->type, ctl2->type); + KUNIT_EXPECT_EQ(test, ctl1->flags, ctl2->flags); + KUNIT_EXPECT_EQ(test, ctl1->len, ctl2->len); + KUNIT_EXPECT_STREQ(test, ctl1->fw_name, ctl2->fw_name); + KUNIT_EXPECT_EQ(test, ctl1->subname_len, ctl2->subname_len); + if (ctl1->subname_len) + KUNIT_EXPECT_MEMEQ(test, ctl1->subname, ctl2->subname, ctl1->subname_len); +} + +/* Controls are unique if the memory region is different */ +static void cs_dsp_ctl_mem_uniqueness(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl1, *ctl2; + struct firmware *wmfw; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + /* Create control in XM */ + def.mem_type = WMFW_ADSP2_XM; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + /* Create control in YM */ + def.mem_type = WMFW_ADSP2_YM; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(priv->dsp); + + /* Both controls should be in the list */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), 2); + ctl1 = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + ctl2 = list_next_entry(ctl1, list); + KUNIT_EXPECT_NOT_NULL(test, ctl1); + KUNIT_EXPECT_NOT_NULL(test, ctl2); + KUNIT_EXPECT_EQ(test, ctl1->alg_region.alg, ctl2->alg_region.alg); + KUNIT_EXPECT_NE(test, ctl1->alg_region.type, ctl2->alg_region.type); + KUNIT_EXPECT_EQ(test, ctl1->offset, ctl2->offset); + KUNIT_EXPECT_EQ(test, ctl1->type, ctl2->type); + KUNIT_EXPECT_EQ(test, ctl1->flags, ctl2->flags); + KUNIT_EXPECT_EQ(test, ctl1->len, ctl2->len); + KUNIT_EXPECT_STREQ(test, ctl1->fw_name, ctl2->fw_name); + KUNIT_EXPECT_EQ(test, ctl1->subname_len, ctl2->subname_len); + if (ctl1->subname_len) + KUNIT_EXPECT_MEMEQ(test, ctl1->subname, ctl2->subname, ctl1->subname_len); +} + +/* Controls are unique if they are in different firmware */ +static void cs_dsp_ctl_fw_uniqueness(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl1, *ctl2; + struct cs_dsp_mock_wmfw_builder *builder2; + struct firmware *wmfw; + + /* Create a second mock wmfw builder */ + builder2 = cs_dsp_mock_wmfw_init(priv, + cs_dsp_mock_wmfw_format_version(local->wmfw_builder)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, builder2); + cs_dsp_mock_wmfw_add_data_block(builder2, + WMFW_ADSP2_XM, 0, + local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + /* Load a 'misc' firmware with a control */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(priv->dsp); + + /* Load a 'mbc/vss' firmware with the same control */ + cs_dsp_mock_wmfw_start_alg_info_block(builder2, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(builder2, &def); + cs_dsp_mock_wmfw_end_alg_info_block(builder2); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw2", + NULL, NULL, "mbc/vss"), 0); + cs_dsp_power_down(priv->dsp); + + /* Both controls should be in the list */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), 2); + ctl1 = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + ctl2 = list_next_entry(ctl1, list); + KUNIT_EXPECT_NOT_NULL(test, ctl1); + KUNIT_EXPECT_NOT_NULL(test, ctl2); + KUNIT_EXPECT_EQ(test, ctl1->alg_region.alg, ctl2->alg_region.alg); + KUNIT_EXPECT_EQ(test, ctl1->alg_region.type, ctl2->alg_region.type); + KUNIT_EXPECT_EQ(test, ctl1->offset, ctl2->offset); + KUNIT_EXPECT_EQ(test, ctl1->type, ctl2->type); + KUNIT_EXPECT_EQ(test, ctl1->flags, ctl2->flags); + KUNIT_EXPECT_EQ(test, ctl1->len, ctl2->len); + KUNIT_EXPECT_STRNEQ(test, ctl1->fw_name, ctl2->fw_name); + KUNIT_EXPECT_EQ(test, ctl1->subname_len, ctl2->subname_len); + if (ctl1->subname_len) + KUNIT_EXPECT_MEMEQ(test, ctl1->subname, ctl2->subname, ctl1->subname_len); +} + +/* + * Controls from a wmfw are only added to the list once. If the same + * wmfw is reloaded the controls are not added again. + * This creates multiple algorithms with one control each, which will + * work on both V1 format and >=V2 format controls. + */ +static void cs_dsp_ctl_squash_reloaded_controls(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctls[ARRAY_SIZE(cs_dsp_ctl_parse_test_algs)]; + struct cs_dsp_coeff_ctl *walkctl; + struct firmware *wmfw; + int i; + + /* Create some algorithms with a control */ + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_parse_test_algs); i++) { + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[i].id, + "dummyalg", NULL); + def.mem_type = WMFW_ADSP2_YM; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + } + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(priv->dsp); + + /* All controls should be in the list */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), + ARRAY_SIZE(cs_dsp_ctl_parse_test_algs)); + + /* Take a copy of the pointers to controls to compare against. */ + i = 0; + list_for_each_entry(walkctl, &priv->dsp->ctl_list, list) { + KUNIT_ASSERT_LT(test, i, ARRAY_SIZE(ctls)); + ctls[i++] = walkctl; + } + + + /* Load the wmfw again */ + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(priv->dsp); + + /* The number of controls should be the same */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), + ARRAY_SIZE(cs_dsp_ctl_parse_test_algs)); + + /* And they should be the same objects */ + i = 0; + list_for_each_entry(walkctl, &priv->dsp->ctl_list, list) { + KUNIT_ASSERT_LT(test, i, ARRAY_SIZE(ctls)); + KUNIT_ASSERT_PTR_EQ(test, walkctl, ctls[i++]); + } +} + +/* + * Controls from a wmfw are only added to the list once. If the same + * wmfw is reloaded the controls are not added again. + * This tests >=V2 firmware that can have multiple named controls in + * the same algorithm. + */ +static void cs_dsp_ctl_v2_squash_reloaded_controls(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctls[ARRAY_SIZE(cs_dsp_get_ctl_test_names)]; + struct cs_dsp_coeff_ctl *walkctl; + struct firmware *wmfw; + int i; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + + /* Create some controls */ + for (i = 0; i < ARRAY_SIZE(cs_dsp_get_ctl_test_names); i++) { + def.shortname = cs_dsp_get_ctl_test_names[i]; + def.offset_dsp_words = i; + if (i & BIT(0)) + def.mem_type = WMFW_ADSP2_XM; + else + def.mem_type = WMFW_ADSP2_YM; + + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + } + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(priv->dsp); + + /* All controls should be in the list */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), + ARRAY_SIZE(cs_dsp_get_ctl_test_names)); + + /* Take a copy of the pointers to controls to compare against. */ + i = 0; + list_for_each_entry(walkctl, &priv->dsp->ctl_list, list) { + KUNIT_ASSERT_LT(test, i, ARRAY_SIZE(ctls)); + ctls[i++] = walkctl; + } + + + /* Load the wmfw again */ + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + cs_dsp_power_down(priv->dsp); + + /* The number of controls should be the same */ + KUNIT_EXPECT_EQ(test, list_count_nodes(&priv->dsp->ctl_list), + ARRAY_SIZE(cs_dsp_get_ctl_test_names)); + + /* And they should be the same objects */ + i = 0; + list_for_each_entry(walkctl, &priv->dsp->ctl_list, list) { + KUNIT_ASSERT_LT(test, i, ARRAY_SIZE(ctls)); + KUNIT_ASSERT_PTR_EQ(test, walkctl, ctls[i++]); + } +} + +static const char * const cs_dsp_ctl_v2_compare_len_names[] = { + "LEFT", + "LEFT_", + "LEFT_SPK", + "LEFT_SPK_V", + "LEFT_SPK_VOL", + "LEFT_SPK_MUTE", + "LEFT_SPK_1", + "LEFT_X", + "LEFT2", +}; + +/* + * When comparing shortnames the full length of both strings is + * considered, not only the characters in of the shortest string. + * So that "LEFT" is not the same as "LEFT2". + * This is specifically to test for the bug that was fixed by commit: + * 7ac1102b227b ("firmware: cs_dsp: Fix new control name check") + */ +static void cs_dsp_ctl_v2_compare_len(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + int i; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_parse_test_algs[0].id, + "dummyalg", NULL); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_v2_compare_len_names); i++) { + def.shortname = cs_dsp_ctl_v2_compare_len_names[i]; + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + } + + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(priv->dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_v2_compare_len_names); i++) { + mutex_lock(&priv->dsp->pwr_lock); + ctl = cs_dsp_get_ctl(priv->dsp, cs_dsp_ctl_v2_compare_len_names[i], + def.mem_type, cs_dsp_ctl_parse_test_algs[0].id); + mutex_unlock(&priv->dsp->pwr_lock); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, + strlen(cs_dsp_ctl_v2_compare_len_names[i])); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, cs_dsp_ctl_v2_compare_len_names[i], + ctl->subname_len); + } +} + +static int cs_dsp_ctl_parse_test_common_init(struct kunit *test, struct cs_dsp *dsp, + int wmfw_version) +{ + struct cs_dsp_test *priv; + struct cs_dsp_test_local *local; + struct device *test_dev; + int ret; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + local = kunit_kzalloc(test, sizeof(struct cs_dsp_test_local), GFP_KERNEL); + if (!local) + return -ENOMEM; + + priv->test = test; + priv->dsp = dsp; + test->priv = priv; + priv->local = local; + priv->local->wmfw_version = wmfw_version; + + /* Create dummy struct device */ + test_dev = kunit_device_register(test, "cs_dsp_test_drv"); + if (IS_ERR(test_dev)) + return PTR_ERR(test_dev); + + dsp->dev = get_device(test_dev); + if (!dsp->dev) + return -ENODEV; + + ret = kunit_add_action_or_reset(test, _put_device_wrapper, dsp->dev); + if (ret) + return ret; + + dev_set_drvdata(dsp->dev, priv); + + /* Allocate regmap */ + ret = cs_dsp_mock_regmap_init(priv); + if (ret) + return ret; + + /* + * There must always be a XM header with at least 1 algorithm, so create + * a dummy one that tests can use and extract it to a data blob. + */ + local->xm_header = cs_dsp_create_mock_xm_header(priv, + cs_dsp_ctl_parse_test_algs, + ARRAY_SIZE(cs_dsp_ctl_parse_test_algs)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->xm_header); + + local->wmfw_builder = cs_dsp_mock_wmfw_init(priv, priv->local->wmfw_version); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->wmfw_builder); + + /* Add dummy XM header blob to wmfw */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_ADSP2_XM, 0, + local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + /* Init cs_dsp */ + dsp->client_ops = kunit_kzalloc(test, sizeof(*dsp->client_ops), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dsp->client_ops); + + switch (dsp->type) { + case WMFW_ADSP2: + ret = cs_dsp_adsp2_init(dsp); + break; + case WMFW_HALO: + ret = cs_dsp_halo_init(dsp); + break; + default: + KUNIT_FAIL(test, "Untested DSP type %d\n", dsp->type); + return -EINVAL; + } + + if (ret) + return ret; + + /* Automatically call cs_dsp_remove() when test case ends */ + return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); +} + +static int cs_dsp_ctl_parse_test_halo_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_HALO; + dsp->mem = cs_dsp_mock_halo_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_halo_dsp1_region_sizes); + dsp->base = cs_dsp_mock_halo_core_base; + dsp->base_sysinfo = cs_dsp_mock_halo_sysinfo_base; + + return cs_dsp_ctl_parse_test_common_init(test, dsp, 3); +} + +static int cs_dsp_ctl_parse_test_adsp2_32bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 1; + dsp->mem = cs_dsp_mock_adsp2_32bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_32bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_32bit_sysbase; + + return cs_dsp_ctl_parse_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_ctl_parse_test_adsp2_32bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_ctl_parse_test_adsp2_32bit_init(test, 1); +} + +static int cs_dsp_ctl_parse_test_adsp2_32bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_ctl_parse_test_adsp2_32bit_init(test, 2); +} + +static int cs_dsp_ctl_parse_test_adsp2_16bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 0; + dsp->mem = cs_dsp_mock_adsp2_16bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_16bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_16bit_sysbase; + + return cs_dsp_ctl_parse_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_ctl_parse_test_adsp2_16bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_ctl_parse_test_adsp2_16bit_init(test, 1); +} + +static int cs_dsp_ctl_parse_test_adsp2_16bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_ctl_parse_test_adsp2_16bit_init(test, 2); +} + +static const struct cs_dsp_ctl_parse_test_param cs_dsp_ctl_mem_type_param_cases[] = { + { .mem_type = WMFW_ADSP2_XM }, + { .mem_type = WMFW_ADSP2_YM }, + { .mem_type = WMFW_ADSP2_ZM }, +}; + +static void cs_dsp_ctl_mem_type_desc(const struct cs_dsp_ctl_parse_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%s", + cs_dsp_mem_region_name(param->mem_type)); +} + +KUNIT_ARRAY_PARAM(cs_dsp_ctl_mem_type, + cs_dsp_ctl_mem_type_param_cases, + cs_dsp_ctl_mem_type_desc); + +static const struct cs_dsp_ctl_parse_test_param cs_dsp_ctl_alg_id_param_cases[] = { + { .alg_id = 0xb }, + { .alg_id = 0xfafa }, + { .alg_id = 0x9f1234 }, + { .alg_id = 0xff00ff }, +}; + +static void cs_dsp_ctl_alg_id_desc(const struct cs_dsp_ctl_parse_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "alg_id:%#x", param->alg_id); +} + +KUNIT_ARRAY_PARAM(cs_dsp_ctl_alg_id, + cs_dsp_ctl_alg_id_param_cases, + cs_dsp_ctl_alg_id_desc); + +static const struct cs_dsp_ctl_parse_test_param cs_dsp_ctl_offset_param_cases[] = { + { .offset = 0x0 }, + { .offset = 0x1 }, + { .offset = 0x2 }, + { .offset = 0x3 }, + { .offset = 0x4 }, + { .offset = 0x5 }, + { .offset = 0x6 }, + { .offset = 0x7 }, + { .offset = 0xe0 }, + { .offset = 0xf1 }, + { .offset = 0xfffe }, + { .offset = 0xffff }, +}; + +static void cs_dsp_ctl_offset_desc(const struct cs_dsp_ctl_parse_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "offset:%#x", param->offset); +} + +KUNIT_ARRAY_PARAM(cs_dsp_ctl_offset, + cs_dsp_ctl_offset_param_cases, + cs_dsp_ctl_offset_desc); + +static const struct cs_dsp_ctl_parse_test_param cs_dsp_ctl_length_param_cases[] = { + { .length = 0x4 }, + { .length = 0x8 }, + { .length = 0x18 }, + { .length = 0xf000 }, +}; + +static void cs_dsp_ctl_length_desc(const struct cs_dsp_ctl_parse_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "length:%#x", param->length); +} + +KUNIT_ARRAY_PARAM(cs_dsp_ctl_length, + cs_dsp_ctl_length_param_cases, + cs_dsp_ctl_length_desc); + +/* Note: some control types mandate specific flags settings */ +static const struct cs_dsp_ctl_parse_test_param cs_dsp_ctl_type_param_cases[] = { + { .ctl_type = WMFW_CTL_TYPE_BYTES, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_ACKED, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE | + WMFW_CTL_FLAG_SYS }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_SYS }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE | + WMFW_CTL_FLAG_SYS }, +}; + +static void cs_dsp_ctl_type_flags_desc(const struct cs_dsp_ctl_parse_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "ctl_type:%#x flags:%#x", + param->ctl_type, param->flags); +} + +KUNIT_ARRAY_PARAM(cs_dsp_ctl_type, + cs_dsp_ctl_type_param_cases, + cs_dsp_ctl_type_flags_desc); + +static const struct cs_dsp_ctl_parse_test_param cs_dsp_ctl_flags_param_cases[] = { + { .flags = 0 }, + { .flags = WMFW_CTL_FLAG_READABLE }, + { .flags = WMFW_CTL_FLAG_WRITEABLE }, + { .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE }, + { .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE }, + { .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE }, + { .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE }, + { .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE | + WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, +}; + +static void cs_dsp_ctl_flags_desc(const struct cs_dsp_ctl_parse_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "flags:%#x", param->flags); +} + +KUNIT_ARRAY_PARAM(cs_dsp_ctl_flags, + cs_dsp_ctl_flags_param_cases, + cs_dsp_ctl_flags_desc); + +static const struct cs_dsp_ctl_parse_test_param cs_dsp_ctl_illegal_type_flags_param_cases[] = { + /* ACKED control must be volatile + read + write */ + { .ctl_type = WMFW_CTL_TYPE_ACKED, .flags = 0 }, + { .ctl_type = WMFW_CTL_TYPE_ACKED, .flags = WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_ACKED, .flags = WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_ACKED, .flags = WMFW_CTL_FLAG_VOLATILE }, + { .ctl_type = WMFW_CTL_TYPE_ACKED, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_ACKED, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE }, + + /* HOSTEVENT must be system + volatile + read + write */ + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, .flags = 0 }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, .flags = WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, .flags = WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, .flags = WMFW_CTL_FLAG_VOLATILE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, .flags = WMFW_CTL_FLAG_SYS }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOSTEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE }, + + /* FWEVENT rules same as HOSTEVENT */ + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, .flags = 0 }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, .flags = WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, .flags = WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, .flags = WMFW_CTL_FLAG_VOLATILE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, .flags = WMFW_CTL_FLAG_SYS }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_FWEVENT, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE }, + + /* + * HOSTBUFFER must be system + volatile + readable or + * system + volatile + readable + writeable + */ + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, .flags = 0 }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, .flags = WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, .flags = WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE}, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, .flags = WMFW_CTL_FLAG_VOLATILE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, .flags = WMFW_CTL_FLAG_SYS }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE }, + { .ctl_type = WMFW_CTL_TYPE_HOST_BUFFER, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE }, +}; + +KUNIT_ARRAY_PARAM(cs_dsp_ctl_illegal_type_flags, + cs_dsp_ctl_illegal_type_flags_param_cases, + cs_dsp_ctl_type_flags_desc); + +static struct kunit_case cs_dsp_ctl_parse_test_cases_v1[] = { + KUNIT_CASE(cs_dsp_ctl_parse_no_coeffs), + KUNIT_CASE(cs_dsp_ctl_parse_v1_name), + KUNIT_CASE(cs_dsp_ctl_parse_empty_v1_name), + KUNIT_CASE(cs_dsp_ctl_parse_max_v1_name), + + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_memory_type, cs_dsp_ctl_mem_type_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_alg_id, cs_dsp_ctl_alg_id_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_alg_mem, cs_dsp_ctl_mem_type_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_offset, cs_dsp_ctl_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_length, cs_dsp_ctl_length_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_ctl_type, cs_dsp_ctl_type_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_flags, cs_dsp_ctl_flags_gen_params), + KUNIT_CASE(cs_dsp_ctl_parse_fw_name), + + KUNIT_CASE(cs_dsp_ctl_alg_id_uniqueness), + KUNIT_CASE(cs_dsp_ctl_mem_uniqueness), + KUNIT_CASE(cs_dsp_ctl_fw_uniqueness), + KUNIT_CASE(cs_dsp_ctl_squash_reloaded_controls), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_ctl_parse_test_cases_v2_v3[] = { + KUNIT_CASE(cs_dsp_ctl_parse_no_coeffs), + KUNIT_CASE(cs_dsp_ctl_parse_short_name), + KUNIT_CASE(cs_dsp_ctl_parse_min_short_name), + KUNIT_CASE(cs_dsp_ctl_parse_max_short_name), + KUNIT_CASE(cs_dsp_ctl_parse_with_min_fullname), + KUNIT_CASE(cs_dsp_ctl_parse_with_max_fullname), + KUNIT_CASE(cs_dsp_ctl_parse_with_min_description), + KUNIT_CASE(cs_dsp_ctl_parse_with_max_description), + KUNIT_CASE(cs_dsp_ctl_parse_with_max_fullname_and_description), + KUNIT_CASE(cs_dsp_ctl_shortname_alignment), + KUNIT_CASE(cs_dsp_ctl_fullname_alignment), + KUNIT_CASE(cs_dsp_ctl_description_alignment), + KUNIT_CASE(cs_dsp_get_ctl_test), + KUNIT_CASE(cs_dsp_get_ctl_test_multiple_wmfw), + + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_memory_type, cs_dsp_ctl_mem_type_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_alg_id, cs_dsp_ctl_alg_id_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_alg_mem, cs_dsp_ctl_mem_type_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_offset, cs_dsp_ctl_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_length, cs_dsp_ctl_length_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_ctl_type, cs_dsp_ctl_type_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_parse_flags, cs_dsp_ctl_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_illegal_type_flags, + cs_dsp_ctl_illegal_type_flags_gen_params), + KUNIT_CASE(cs_dsp_ctl_parse_fw_name), + + KUNIT_CASE(cs_dsp_ctl_alg_id_uniqueness), + KUNIT_CASE(cs_dsp_ctl_mem_uniqueness), + KUNIT_CASE(cs_dsp_ctl_fw_uniqueness), + KUNIT_CASE(cs_dsp_ctl_squash_reloaded_controls), + KUNIT_CASE(cs_dsp_ctl_v2_squash_reloaded_controls), + KUNIT_CASE(cs_dsp_ctl_v2_compare_len), + + { } /* terminator */ +}; + +static struct kunit_suite cs_dsp_ctl_parse_test_halo = { + .name = "cs_dsp_ctl_parse_wmfwV3_halo", + .init = cs_dsp_ctl_parse_test_halo_init, + .test_cases = cs_dsp_ctl_parse_test_cases_v2_v3, +}; + +static struct kunit_suite cs_dsp_ctl_parse_test_adsp2_32bit_wmfw1 = { + .name = "cs_dsp_ctl_parse_wmfwV1_adsp2_32bit", + .init = cs_dsp_ctl_parse_test_adsp2_32bit_wmfw1_init, + .test_cases = cs_dsp_ctl_parse_test_cases_v1, +}; + +static struct kunit_suite cs_dsp_ctl_parse_test_adsp2_32bit_wmfw2 = { + .name = "cs_dsp_ctl_parse_wmfwV2_adsp2_32bit", + .init = cs_dsp_ctl_parse_test_adsp2_32bit_wmfw2_init, + .test_cases = cs_dsp_ctl_parse_test_cases_v2_v3, +}; + +static struct kunit_suite cs_dsp_ctl_parse_test_adsp2_16bit_wmfw1 = { + .name = "cs_dsp_ctl_parse_wmfwV1_adsp2_16bit", + .init = cs_dsp_ctl_parse_test_adsp2_16bit_wmfw1_init, + .test_cases = cs_dsp_ctl_parse_test_cases_v1, +}; + +static struct kunit_suite cs_dsp_ctl_parse_test_adsp2_16bit_wmfw2 = { + .name = "cs_dsp_ctl_parse_wmfwV2_adsp2_16bit", + .init = cs_dsp_ctl_parse_test_adsp2_16bit_wmfw2_init, + .test_cases = cs_dsp_ctl_parse_test_cases_v2_v3, +}; + +kunit_test_suites(&cs_dsp_ctl_parse_test_halo, + &cs_dsp_ctl_parse_test_adsp2_32bit_wmfw1, + &cs_dsp_ctl_parse_test_adsp2_32bit_wmfw2, + &cs_dsp_ctl_parse_test_adsp2_16bit_wmfw1, + &cs_dsp_ctl_parse_test_adsp2_16bit_wmfw2); diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_control_rw.c b/drivers/firmware/cirrus/test/cs_dsp_test_control_rw.c new file mode 100644 index 000000000000..bda00a95d4f9 --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_test_control_rw.c @@ -0,0 +1,2669 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// KUnit tests for cs_dsp. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *); +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_stop_wrapper, cs_dsp_stop, struct cs_dsp *); +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *); + +struct cs_dsp_test_local { + struct cs_dsp_mock_xm_header *xm_header; + struct cs_dsp_mock_wmfw_builder *wmfw_builder; + int wmfw_version; +}; + +struct cs_dsp_ctl_rw_test_param { + int mem_type; + int alg_id; + unsigned int offs_words; + unsigned int len_bytes; + u16 ctl_type; + u16 flags; +}; + +static const struct cs_dsp_mock_alg_def cs_dsp_ctl_rw_test_algs[] = { + { + .id = 0xfafa, + .ver = 0x100000, + .xm_base_words = 60, + .xm_size_words = 1000, + .ym_base_words = 0, + .ym_size_words = 1000, + .zm_base_words = 0, + .zm_size_words = 1000, + }, + { + .id = 0xb, + .ver = 0x100001, + .xm_base_words = 1060, + .xm_size_words = 1000, + .ym_base_words = 1000, + .ym_size_words = 1000, + .zm_base_words = 1000, + .zm_size_words = 1000, + }, + { + .id = 0x9f1234, + .ver = 0x100500, + .xm_base_words = 2060, + .xm_size_words = 32, + .ym_base_words = 2000, + .ym_size_words = 32, + .zm_base_words = 2000, + .zm_size_words = 32, + }, + { + .id = 0xff00ff, + .ver = 0x300113, + .xm_base_words = 2100, + .xm_size_words = 32, + .ym_base_words = 2032, + .ym_size_words = 32, + .zm_base_words = 2032, + .zm_size_words = 32, + }, +}; + +static const struct cs_dsp_mock_coeff_def mock_coeff_template = { + .shortname = "Dummy Coeff", + .type = WMFW_CTL_TYPE_BYTES, + .mem_type = WMFW_ADSP2_YM, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + .length_bytes = 4, +}; + +static int _find_alg_entry(struct kunit *test, unsigned int alg_id) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cs_dsp_ctl_rw_test_algs); ++i) { + if (cs_dsp_ctl_rw_test_algs[i].id == alg_id) + break; + } + + KUNIT_ASSERT_LT(test, i, ARRAY_SIZE(cs_dsp_ctl_rw_test_algs)); + + return i; +} + +static int _get_alg_mem_base_words(struct kunit *test, int alg_index, int mem_type) +{ + switch (mem_type) { + case WMFW_ADSP2_XM: + return cs_dsp_ctl_rw_test_algs[alg_index].xm_base_words; + case WMFW_ADSP2_YM: + return cs_dsp_ctl_rw_test_algs[alg_index].ym_base_words; + case WMFW_ADSP2_ZM: + return cs_dsp_ctl_rw_test_algs[alg_index].zm_base_words; + default: + KUNIT_FAIL(test, "Bug in test: illegal memory type %d\n", mem_type); + return 0; + } +} + +static struct cs_dsp_mock_wmfw_builder *_create_dummy_wmfw(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp_mock_wmfw_builder *builder; + + builder = cs_dsp_mock_wmfw_init(priv, local->wmfw_version); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, builder); + + /* Init an XM header */ + cs_dsp_mock_wmfw_add_data_block(builder, + WMFW_ADSP2_XM, 0, + local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + return builder; +} + +/* + * Write to a control while the firmware is running. + * This should write to the underlying registers. + */ +static void cs_dsp_ctl_write_running(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + memset(reg_vals, 0, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* + * Write new data to the control, it should be written to the registers + * and cs_dsp_coeff_lock_and_write_ctrl() should return 1 to indicate + * that the control content changed. + */ + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 1); + KUNIT_ASSERT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, param->len_bytes), 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Read from a volatile control while the firmware is running. + * This should return the current state of the underlying registers. + */ +static void cs_dsp_ctl_read_volatile_running(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + memset(reg_vals, 0, param->len_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Read the control, it should return the current register content */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); + + /* + * Change the register content and read the control, it should return + * the new register content + */ + get_random_bytes(reg_vals, param->len_bytes); + KUNIT_ASSERT_EQ(test, regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes), 0); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, param->len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, param->len_bytes); +} + +/* + * Read from a volatile control before the firmware is started. + * This should return an error. + */ +static void cs_dsp_ctl_read_volatile_not_started(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Read the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); +} + +/* + * Read from a volatile control after the firmware has stopped. + * This should return an error. + */ +static void cs_dsp_ctl_read_volatile_stopped(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start and stop the firmware */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + + /* Read the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); +} + +/* + * Read from a volatile control after the DSP has been powered down. + * This should return an error. + */ +static void cs_dsp_ctl_read_volatile_stopped_powered_down(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start and stop the firmware then power down */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + cs_dsp_power_down(dsp); + + /* Read the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); +} + +/* + * Read from a volatile control when a different firmware is currently + * loaded into the DSP. + * Should return an error. + */ +static void cs_dsp_ctl_read_volatile_not_current_loaded_fw(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Power-down DSP then power-up with a different firmware */ + cs_dsp_power_down(dsp); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + + /* Read the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); +} + +/* + * Read from a volatile control when a different firmware is currently + * running. + * Should return an error. + */ +static void cs_dsp_ctl_read_volatile_not_current_running_fw(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Power-down DSP then power-up with a different firmware */ + cs_dsp_power_down(dsp); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Read the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); +} + +/* + * Write to a volatile control before the firmware is started. + * This should return an error. + */ +static void cs_dsp_ctl_write_volatile_not_started(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + /* Write the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); + + /* Should not have been any writes to registers */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write to a volatile control after the firmware has stopped. + * This should return an error. + */ +static void cs_dsp_ctl_write_volatile_stopped(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start and stop the firmware */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + /* Write the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); + + /* Should not have been any writes to registers */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write to a volatile control after the DSP has been powered down. + * This should return an error. + */ +static void cs_dsp_ctl_write_volatile_stopped_powered_down(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kzalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Start and stop the firmware then power down */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + cs_dsp_power_down(dsp); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + /* Write the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); + + /* Should not have been any writes to registers */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write to a volatile control when a different firmware is currently + * loaded into the DSP. + * Should return an error. + */ +static void cs_dsp_ctl_write_volatile_not_current_loaded_fw(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Power-down DSP then power-up with a different firmware */ + cs_dsp_power_down(dsp); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + /* Write the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); + + /* Should not have been any writes to registers */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write to a volatile control when a different firmware is currently + * running. + * Should return an error. + */ +static void cs_dsp_ctl_write_volatile_not_current_running_fw(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + struct cs_dsp_mock_wmfw_builder *builder2 = _create_dummy_wmfw(test); + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + reg_vals = kunit_kmalloc(test, param->len_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some DSP data to be read into the control cache */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, param->len_bytes); + + /* Create control pointing to this data */ + def.flags = param->flags | WMFW_CTL_FLAG_VOLATILE; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + /* Power-up DSP */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + /* Power-down DSP then power-up with a different firmware */ + cs_dsp_power_down(dsp); + wmfw = cs_dsp_mock_wmfw_get_firmware(builder2); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw2", NULL, NULL, "mbc.vss"), 0); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + /* Write the control, it should return an error */ + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, param->len_bytes), + 0); + + /* Should not have been any writes to registers */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Read from an offset into the control data. Should return only the + * portion of data from the offset position. + */ +static void cs_dsp_ctl_read_with_seek(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + unsigned int seek_words; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = 48; + + reg_vals = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + for (seek_words = 1; seek_words < (def.length_bytes / sizeof(u32)); seek_words++) { + unsigned int len_bytes = def.length_bytes - (seek_words * sizeof(u32)); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, seek_words, + readback, len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, ®_vals[seek_words], len_bytes); + } +} + +/* + * Read from an offset into the control cache. Should return only the + * portion of data from the offset position. + * Same as cs_dsp_ctl_read_with_seek() except the control is cached + * and the firmware is not running. + */ +static void cs_dsp_ctl_read_cache_with_seek(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + unsigned int seek_words; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = 48; + + reg_vals = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start and stop the firmware so the read will come from the cache */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + + for (seek_words = 1; seek_words < (def.length_bytes / sizeof(u32)); seek_words++) { + unsigned int len_bytes = def.length_bytes - (seek_words * sizeof(u32)); + + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, seek_words, + readback, len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, ®_vals[seek_words], len_bytes); + } +} + +/* + * Read less than the full length of data from a control. Should return + * only the requested number of bytes. + */ +static void cs_dsp_ctl_read_truncated(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + unsigned int len_bytes; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = 48; + + reg_vals = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Reads are only allowed to be a multiple of the DSP word length */ + for (len_bytes = sizeof(u32); len_bytes < def.length_bytes; len_bytes += sizeof(u32)) { + memset(readback, 0, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, len_bytes); + KUNIT_EXPECT_MEMNEQ(test, + (u8 *)readback + len_bytes, + (u8 *)reg_vals + len_bytes, + def.length_bytes - len_bytes); + } +} + +/* + * Read less than the full length of data from a cached control. + * Should return only the requested number of bytes. + * Same as cs_dsp_ctl_read_truncated() except the control is cached + * and the firmware is not running. + */ +static void cs_dsp_ctl_read_cache_truncated(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback; + unsigned int len_bytes; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = 48; + + reg_vals = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start and stop the firmware so the read will come from the cache */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + + /* Reads are only allowed to be a multiple of the DSP word length */ + for (len_bytes = sizeof(u32); len_bytes < def.length_bytes; len_bytes += sizeof(u32)) { + memset(readback, 0, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, len_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, len_bytes); + KUNIT_EXPECT_MEMNEQ(test, + (u8 *)readback + len_bytes, + (u8 *)reg_vals + len_bytes, + def.length_bytes - len_bytes); + } +} + +/* + * Write to an offset into the control data. Should only change the + * portion of data from the offset position. + */ +static void cs_dsp_ctl_write_with_seek(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback, *new_data; + unsigned int seek_words; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = 48; + + reg_vals = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + new_data = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, new_data); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + for (seek_words = 1; seek_words < (def.length_bytes / sizeof(u32)); seek_words++) { + unsigned int len_bytes = def.length_bytes - (seek_words * sizeof(u32)); + + /* Reset the register values to the test data */ + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + get_random_bytes(new_data, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, seek_words, + new_data, len_bytes), + 1); + KUNIT_ASSERT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, def.length_bytes), + 0); + /* Initial portion of readback should be unchanged */ + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, seek_words * sizeof(u32)); + KUNIT_EXPECT_MEMEQ(test, &readback[seek_words], new_data, len_bytes); + } +} + +/* + * Write to an offset into the control cache. Should only change the + * portion of data from the offset position. + * Same as cs_dsp_ctl_write_with_seek() except the control is cached + * and the firmware is not running. + */ +static void cs_dsp_ctl_write_cache_with_seek(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback, *new_data; + unsigned int seek_words; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = 48; + + reg_vals = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + new_data = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, new_data); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start and stop the firmware so the read will come from the cache */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + + for (seek_words = 1; seek_words < (def.length_bytes / sizeof(u32)); seek_words++) { + unsigned int len_bytes = def.length_bytes - (seek_words * sizeof(u32)); + + /* Reset the cache to the test data */ + KUNIT_EXPECT_GE(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, + def.length_bytes), + 0); + + get_random_bytes(new_data, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, seek_words, + new_data, len_bytes), + 1); + + memset(readback, 0, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, + def.length_bytes), + 0); + /* Initial portion of readback should be unchanged */ + KUNIT_EXPECT_MEMEQ(test, readback, reg_vals, seek_words * sizeof(u32)); + KUNIT_EXPECT_MEMEQ(test, &readback[seek_words], new_data, len_bytes); + } +} + +/* + * Write less than the full length of data to a control. Should only + * change the requested number of bytes. + */ +static void cs_dsp_ctl_write_truncated(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback, *new_data; + unsigned int len_bytes; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = 48; + + reg_vals = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + new_data = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, new_data); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Writes are only allowed to be a multiple of the DSP word length */ + for (len_bytes = sizeof(u32); len_bytes < def.length_bytes; len_bytes += sizeof(u32)) { + /* Reset the register values to the test data */ + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + get_random_bytes(new_data, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, new_data, len_bytes), + 1); + + memset(readback, 0, def.length_bytes); + KUNIT_ASSERT_EQ(test, regmap_raw_read(dsp->regmap, reg, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, new_data, len_bytes); + KUNIT_EXPECT_MEMEQ(test, + (u8 *)readback + len_bytes, + (u8 *)reg_vals + len_bytes, + def.length_bytes - len_bytes); + } +} + +/* + * Write less than the full length of data to a cached control. + * Should only change the requested number of bytes. + * Same as cs_dsp_ctl_write_truncated() except the control is cached + * and the firmware is not running. + */ +static void cs_dsp_ctl_write_cache_truncated(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals, *readback, *new_data; + unsigned int len_bytes; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = 48; + + reg_vals = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + readback = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + new_data = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, new_data); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + get_random_bytes(reg_vals, def.length_bytes); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start and stop the firmware so the read will come from the cache */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + cs_dsp_stop(dsp); + + /* Writes are only allowed to be a multiple of the DSP word length */ + for (len_bytes = sizeof(u32); len_bytes < def.length_bytes; len_bytes += sizeof(u32)) { + /* Reset the cache to the test data */ + KUNIT_EXPECT_GE(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, + def.length_bytes), + 0); + + get_random_bytes(new_data, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, new_data, len_bytes), + 1); + + memset(readback, 0, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, + def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, new_data, len_bytes); + KUNIT_EXPECT_MEMEQ(test, + (u8 *)readback + len_bytes, + (u8 *)reg_vals + len_bytes, + def.length_bytes - len_bytes); + } +} + +/* + * Read from an offset that is beyond the end of the control data. + * Should return an error. + */ +static void cs_dsp_ctl_read_with_seek_oob(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + unsigned int seek_words; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + reg_vals = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + seek_words = def.length_bytes / sizeof(u32); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, seek_words, + reg_vals, def.length_bytes), + 0); + + if (!(def.flags & WMFW_CTL_FLAG_VOLATILE)) { + /* Stop firmware and repeat the read from the cache */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + KUNIT_ASSERT_FALSE(test, dsp->running); + + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, seek_words, + reg_vals, def.length_bytes), + 0); + } +} + +/* + * Read more data than the length of the control data. + * Should return an error. + */ +static void cs_dsp_ctl_read_with_length_overflow(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + reg_vals = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, reg_vals, def.length_bytes + 1), + 0); + + if (!(def.flags & WMFW_CTL_FLAG_VOLATILE)) { + /* Stop firmware and repeat the read from the cache */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + KUNIT_ASSERT_FALSE(test, dsp->running); + + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, reg_vals, + def.length_bytes + 1), + 0); + } +} + +/* + * Read with a seek and length that ends beyond the end of control data. + * Should return an error. + */ +static void cs_dsp_ctl_read_with_seek_and_length_oob(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + reg_vals = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* + * Read full control length but at a start offset of 1 so that + * offset + length exceeds the length of the control. + */ + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 1, reg_vals, def.length_bytes), + 0); + + if (!(def.flags & WMFW_CTL_FLAG_VOLATILE)) { + /* Stop firmware and repeat the read from the cache */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + KUNIT_ASSERT_FALSE(test, dsp->running); + + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 1, reg_vals, + def.length_bytes), + 0); + } +} + +/* + * Write to an offset that is beyond the end of the control data. + * Should return an error without touching any registers. + */ +static void cs_dsp_ctl_write_with_seek_oob(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + unsigned int seek_words; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + reg_vals = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + get_random_bytes(reg_vals, def.length_bytes); + seek_words = def.length_bytes / sizeof(u32); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, seek_words, + reg_vals, def.length_bytes), + 0); + + if (!(def.flags & WMFW_CTL_FLAG_VOLATILE)) { + /* Stop firmware and repeat the write to the cache */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + KUNIT_ASSERT_FALSE(test, dsp->running); + + get_random_bytes(reg_vals, def.length_bytes); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, seek_words, + reg_vals, def.length_bytes), + 0); + } + + /* Check that it didn't write any registers */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write more data than the length of the control data. + * Should return an error. + */ +static void cs_dsp_ctl_write_with_length_overflow(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + reg_vals = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + get_random_bytes(reg_vals, def.length_bytes); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, def.length_bytes + 1), + 0); + + if (!(def.flags & WMFW_CTL_FLAG_VOLATILE)) { + /* Stop firmware and repeat the write to the cache */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + KUNIT_ASSERT_FALSE(test, dsp->running); + + get_random_bytes(reg_vals, def.length_bytes); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, + def.length_bytes + 1), + 0); + } + + /* Check that it didn't write any registers */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write with a seek and length that ends beyond the end of control data. + * Should return an error. + */ +static void cs_dsp_ctl_write_with_seek_and_length_oob(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + reg_vals = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + /* + * Write full control length but at a start offset of 1 so that + * offset + length exceeeds the length of the control. + */ + get_random_bytes(reg_vals, def.length_bytes); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 1, reg_vals, def.length_bytes), + 0); + + if (!(def.flags & WMFW_CTL_FLAG_VOLATILE)) { + /* Stop firmware and repeat the write to the cache */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + KUNIT_ASSERT_FALSE(test, dsp->running); + + get_random_bytes(reg_vals, def.length_bytes); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 1, reg_vals, + def.length_bytes), + 0); + } + + /* Check that it didn't write any registers */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Read from a write-only control. This is legal because controls can + * always be read. Write-only only indicates that it is not useful to + * populate the cache from the DSP memory. + */ +static void cs_dsp_ctl_read_from_writeonly(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *ctl_vals, *readback; + + /* Sanity check parameters */ + KUNIT_ASSERT_TRUE(test, param->flags & WMFW_CTL_FLAG_WRITEABLE); + KUNIT_ASSERT_FALSE(test, param->flags & WMFW_CTL_FLAG_READABLE); + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + ctl_vals = kunit_kmalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctl_vals); + + readback = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Write some test data to the control */ + get_random_bytes(ctl_vals, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, ctl_vals, def.length_bytes), + 1); + + /* Read back the data */ + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, def.length_bytes); + + if (!(def.flags & WMFW_CTL_FLAG_VOLATILE)) { + /* Stop firmware and repeat the read from the cache */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + KUNIT_ASSERT_FALSE(test, dsp->running); + + memset(readback, 0, def.length_bytes); + KUNIT_EXPECT_EQ(test, + cs_dsp_coeff_lock_and_read_ctrl(ctl, 0, readback, + def.length_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, ctl_vals, def.length_bytes); + } +} + +/* + * Write to a read-only control. + * This should return an error without writing registers. + */ +static void cs_dsp_ctl_write_to_readonly(struct kunit *test) +{ + const struct cs_dsp_ctl_rw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct cs_dsp *dsp = priv->dsp; + struct cs_dsp_mock_coeff_def def = mock_coeff_template; + int alg_idx = _find_alg_entry(test, param->alg_id); + unsigned int reg, alg_base_words; + struct cs_dsp_coeff_ctl *ctl; + struct firmware *wmfw; + u32 *reg_vals; + + /* Sanity check parameters */ + KUNIT_ASSERT_FALSE(test, param->flags & WMFW_CTL_FLAG_WRITEABLE); + KUNIT_ASSERT_TRUE(test, param->flags & WMFW_CTL_FLAG_READABLE); + + def.flags = param->flags; + def.mem_type = param->mem_type; + def.offset_dsp_words = param->offs_words; + def.length_bytes = param->len_bytes; + + reg_vals = kunit_kzalloc(test, def.length_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, reg_vals); + + /* Create some initial register content */ + alg_base_words = _get_alg_mem_base_words(test, alg_idx, param->mem_type); + reg = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg += (alg_base_words + param->offs_words) * + cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv); + regmap_raw_write(dsp->regmap, reg, reg_vals, def.length_bytes); + + /* Create control pointing to this data */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_ctl_rw_test_algs[alg_idx].id, + "dummyalg", NULL); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &def); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_ASSERT_EQ(test, cs_dsp_power_up(dsp, wmfw, "mock_fw", NULL, NULL, "misc"), 0); + + ctl = list_first_entry_or_null(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + + /* Start the firmware and add an action to stop it during cleanup */ + KUNIT_ASSERT_EQ(test, cs_dsp_run(dsp), 0); + KUNIT_ASSERT_EQ(test, kunit_add_action_or_reset(test, _cs_dsp_stop_wrapper, dsp), 0); + + /* Drop expected writes and the regmap cache should be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + cs_dsp_mock_regmap_drop_bytes(priv, reg, param->len_bytes); + + get_random_bytes(reg_vals, def.length_bytes); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, def.length_bytes), + 0); + + if (!(def.flags & WMFW_CTL_FLAG_VOLATILE)) { + /* Stop firmware and repeat the write to the cache */ + kunit_release_action(test, _cs_dsp_stop_wrapper, dsp); + KUNIT_ASSERT_FALSE(test, dsp->running); + + get_random_bytes(reg_vals, def.length_bytes); + KUNIT_EXPECT_LT(test, + cs_dsp_coeff_lock_and_write_ctrl(ctl, 0, reg_vals, + def.length_bytes), + 0); + } + + /* Check that it didn't write any registers */ + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +static int cs_dsp_ctl_rw_test_common_init(struct kunit *test, struct cs_dsp *dsp, + int wmfw_version) +{ + struct cs_dsp_test *priv; + struct cs_dsp_test_local *local; + struct device *test_dev; + int ret; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + local = kunit_kzalloc(test, sizeof(struct cs_dsp_test_local), GFP_KERNEL); + if (!local) + return -ENOMEM; + + priv->test = test; + priv->dsp = dsp; + test->priv = priv; + priv->local = local; + priv->local->wmfw_version = wmfw_version; + + /* Create dummy struct device */ + test_dev = kunit_device_register(test, "cs_dsp_test_drv"); + if (IS_ERR(test_dev)) + return PTR_ERR(test_dev); + + dsp->dev = get_device(test_dev); + if (!dsp->dev) + return -ENODEV; + + ret = kunit_add_action_or_reset(test, _put_device_wrapper, dsp->dev); + if (ret) + return ret; + + dev_set_drvdata(dsp->dev, priv); + + /* Allocate regmap */ + ret = cs_dsp_mock_regmap_init(priv); + if (ret) + return ret; + + /* + * There must always be a XM header with at least 1 algorithm, so create + * a dummy one that tests can use and extract it to a data blob. + */ + local->xm_header = cs_dsp_create_mock_xm_header(priv, + cs_dsp_ctl_rw_test_algs, + ARRAY_SIZE(cs_dsp_ctl_rw_test_algs)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->xm_header); + + /* Create wmfw builder */ + local->wmfw_builder = _create_dummy_wmfw(test); + + /* Init cs_dsp */ + dsp->client_ops = kunit_kzalloc(test, sizeof(*dsp->client_ops), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dsp->client_ops); + + switch (dsp->type) { + case WMFW_ADSP2: + ret = cs_dsp_adsp2_init(dsp); + break; + case WMFW_HALO: + ret = cs_dsp_halo_init(dsp); + break; + default: + KUNIT_FAIL(test, "Untested DSP type %d\n", dsp->type); + return -EINVAL; + } + + if (ret) + return ret; + + /* Automatically call cs_dsp_remove() when test case ends */ + return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); +} + +static int cs_dsp_ctl_rw_test_halo_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_HALO; + dsp->mem = cs_dsp_mock_halo_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_halo_dsp1_region_sizes); + dsp->base = cs_dsp_mock_halo_core_base; + dsp->base_sysinfo = cs_dsp_mock_halo_sysinfo_base; + + return cs_dsp_ctl_rw_test_common_init(test, dsp, 3); +} + +static int cs_dsp_ctl_rw_test_adsp2_32bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 1; + dsp->mem = cs_dsp_mock_adsp2_32bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_32bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_32bit_sysbase; + + return cs_dsp_ctl_rw_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_ctl_rw_test_adsp2_32bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_ctl_rw_test_adsp2_32bit_init(test, 1); +} + +static int cs_dsp_ctl_rw_test_adsp2_32bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_ctl_rw_test_adsp2_32bit_init(test, 2); +} + +static int cs_dsp_ctl_rw_test_adsp2_16bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 0; + dsp->mem = cs_dsp_mock_adsp2_16bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_16bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_16bit_sysbase; + + return cs_dsp_ctl_rw_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_ctl_rw_test_adsp2_16bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_ctl_rw_test_adsp2_16bit_init(test, 1); +} + +static int cs_dsp_ctl_rw_test_adsp2_16bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_ctl_rw_test_adsp2_16bit_init(test, 2); +} + +static void cs_dsp_ctl_all_param_desc(const struct cs_dsp_ctl_rw_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "alg:%#x %s@%u len:%u flags:%#x", + param->alg_id, cs_dsp_mem_region_name(param->mem_type), + param->offs_words, param->len_bytes, param->flags); +} + +/* All parameters populated, with various lengths */ +static const struct cs_dsp_ctl_rw_test_param all_pop_varying_len_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 8 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 12 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 16 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 48 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 100 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 512 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 1000 }, +}; +KUNIT_ARRAY_PARAM(all_pop_varying_len, all_pop_varying_len_cases, + cs_dsp_ctl_all_param_desc); + +/* All parameters populated, with various offsets */ +static const struct cs_dsp_ctl_rw_test_param all_pop_varying_offset_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 0, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 2, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 3, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 8, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 10, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 128, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 180, .len_bytes = 4 }, +}; +KUNIT_ARRAY_PARAM(all_pop_varying_offset, all_pop_varying_offset_cases, + cs_dsp_ctl_all_param_desc); + +/* All parameters populated, with various X and Y memory regions */ +static const struct cs_dsp_ctl_rw_test_param all_pop_varying_xy_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_XM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, +}; +KUNIT_ARRAY_PARAM(all_pop_varying_xy, all_pop_varying_xy_cases, + cs_dsp_ctl_all_param_desc); + +/* All parameters populated, using ZM */ +static const struct cs_dsp_ctl_rw_test_param all_pop_z_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_ZM, .offs_words = 1, .len_bytes = 4 }, +}; +KUNIT_ARRAY_PARAM(all_pop_z, all_pop_z_cases, cs_dsp_ctl_all_param_desc); + +/* All parameters populated, with various algorithm ids */ +static const struct cs_dsp_ctl_rw_test_param all_pop_varying_alg_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xb, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0x9f1234, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, + { .alg_id = 0xff00ff, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4 }, +}; +KUNIT_ARRAY_PARAM(all_pop_varying_alg, all_pop_varying_alg_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * readable control. + */ +static const struct cs_dsp_ctl_rw_test_param all_pop_readable_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = 0 + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | + WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_readable_flags, + all_pop_readable_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * read-only control + */ +static const struct cs_dsp_ctl_rw_test_param all_pop_readonly_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_readonly_flags, + all_pop_readonly_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * non-volatile readable control + */ +static const struct cs_dsp_ctl_rw_test_param all_pop_nonvol_readable_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = 0 + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_nonvol_readable_flags, + all_pop_nonvol_readable_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * writeable control + */ +static const struct cs_dsp_ctl_rw_test_param all_pop_writeable_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = 0 + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | + WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_writeable_flags, + all_pop_writeable_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * write-only control + */ +static const struct cs_dsp_ctl_rw_test_param all_pop_writeonly_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_writeonly_flags, + all_pop_writeonly_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * non-volatile writeable control + */ +static const struct cs_dsp_ctl_rw_test_param all_pop_nonvol_writeable_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = 0 + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_nonvol_writeable_flags, + all_pop_nonvol_writeable_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * volatile readable control. + */ +static const struct cs_dsp_ctl_rw_test_param all_pop_volatile_readable_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = 0 /* flags == 0 is volatile while firmware is running */ + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_READABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | + WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_volatile_readable_flags, + all_pop_volatile_readable_flags_cases, + cs_dsp_ctl_all_param_desc); + +/* + * All parameters populated, with all combinations of flags for a + * volatile readable control. + */ +static const struct cs_dsp_ctl_rw_test_param all_pop_volatile_writeable_flags_cases[] = { + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = 0 /* flags == 0 is volatile while firmware is running */ + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_WRITEABLE, + }, + { .alg_id = 0xfafa, .mem_type = WMFW_ADSP2_YM, .offs_words = 1, .len_bytes = 4, + .flags = WMFW_CTL_FLAG_VOLATILE | WMFW_CTL_FLAG_SYS | + WMFW_CTL_FLAG_READABLE | WMFW_CTL_FLAG_WRITEABLE, + }, +}; +KUNIT_ARRAY_PARAM(all_pop_volatile_writeable_flags, + all_pop_volatile_writeable_flags_cases, + cs_dsp_ctl_all_param_desc); + +static struct kunit_case cs_dsp_ctl_rw_test_cases_adsp[] = { + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_z_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_running, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_running, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_running, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_running, all_pop_z_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_running, + all_pop_volatile_readable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_not_started, + all_pop_volatile_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_stopped, + all_pop_volatile_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_stopped_powered_down, + all_pop_volatile_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_not_current_loaded_fw, + all_pop_volatile_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_not_current_running_fw, + all_pop_volatile_readable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_not_started, + all_pop_volatile_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_stopped, + all_pop_volatile_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_stopped_powered_down, + all_pop_volatile_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_not_current_loaded_fw, + all_pop_volatile_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_not_current_running_fw, + all_pop_volatile_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_with_seek, + all_pop_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_cache_with_seek, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_truncated, + all_pop_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_cache_truncated, + all_pop_nonvol_readable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_write_with_seek, + all_pop_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_cache_with_seek, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_truncated, + all_pop_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_cache_truncated, + all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_with_seek_oob, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_with_length_overflow, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_with_seek_and_length_oob, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_with_seek_oob, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_with_length_overflow, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_with_seek_and_length_oob, + all_pop_varying_len_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_from_writeonly, + all_pop_writeonly_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_to_readonly, + all_pop_readonly_flags_gen_params), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_ctl_rw_test_cases_halo[] = { + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_varying_alg_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_running, all_pop_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_running, all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_running, all_pop_varying_offset_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_running, all_pop_varying_xy_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_running, + all_pop_volatile_readable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_not_started, + all_pop_volatile_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_stopped, + all_pop_volatile_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_stopped_powered_down, + all_pop_volatile_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_not_current_loaded_fw, + all_pop_volatile_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_volatile_not_current_running_fw, + all_pop_volatile_readable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_not_started, + all_pop_volatile_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_stopped, + all_pop_volatile_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_stopped_powered_down, + all_pop_volatile_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_not_current_loaded_fw, + all_pop_volatile_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_volatile_not_current_running_fw, + all_pop_volatile_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_with_seek, + all_pop_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_cache_with_seek, + all_pop_nonvol_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_truncated, + all_pop_readable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_cache_truncated, + all_pop_nonvol_readable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_write_with_seek, + all_pop_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_cache_with_seek, + all_pop_nonvol_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_truncated, + all_pop_writeable_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_cache_truncated, + all_pop_nonvol_writeable_flags_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_with_seek_oob, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_with_length_overflow, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_read_with_seek_and_length_oob, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_with_seek_oob, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_with_length_overflow, + all_pop_varying_len_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_with_seek_and_length_oob, + all_pop_varying_len_gen_params), + + KUNIT_CASE_PARAM(cs_dsp_ctl_read_from_writeonly, + all_pop_writeonly_flags_gen_params), + KUNIT_CASE_PARAM(cs_dsp_ctl_write_to_readonly, + all_pop_readonly_flags_gen_params), + + { } /* terminator */ +}; + +static struct kunit_suite cs_dsp_ctl_rw_test_halo = { + .name = "cs_dsp_ctl_rw_wmfwV3_halo", + .init = cs_dsp_ctl_rw_test_halo_init, + .test_cases = cs_dsp_ctl_rw_test_cases_halo, +}; + +static struct kunit_suite cs_dsp_ctl_rw_test_adsp2_32bit_wmfw1 = { + .name = "cs_dsp_ctl_rw_wmfwV1_adsp2_32bit", + .init = cs_dsp_ctl_rw_test_adsp2_32bit_wmfw1_init, + .test_cases = cs_dsp_ctl_rw_test_cases_adsp, +}; + +static struct kunit_suite cs_dsp_ctl_rw_test_adsp2_32bit_wmfw2 = { + .name = "cs_dsp_ctl_rw_wmfwV2_adsp2_32bit", + .init = cs_dsp_ctl_rw_test_adsp2_32bit_wmfw2_init, + .test_cases = cs_dsp_ctl_rw_test_cases_adsp, +}; + +static struct kunit_suite cs_dsp_ctl_rw_test_adsp2_16bit_wmfw1 = { + .name = "cs_dsp_ctl_rw_wmfwV1_adsp2_16bit", + .init = cs_dsp_ctl_rw_test_adsp2_16bit_wmfw1_init, + .test_cases = cs_dsp_ctl_rw_test_cases_adsp, +}; + +static struct kunit_suite cs_dsp_ctl_rw_test_adsp2_16bit_wmfw2 = { + .name = "cs_dsp_ctl_rw_wmfwV2_adsp2_16bit", + .init = cs_dsp_ctl_rw_test_adsp2_16bit_wmfw2_init, + .test_cases = cs_dsp_ctl_rw_test_cases_adsp, +}; + +kunit_test_suites(&cs_dsp_ctl_rw_test_halo, + &cs_dsp_ctl_rw_test_adsp2_32bit_wmfw1, + &cs_dsp_ctl_rw_test_adsp2_32bit_wmfw2, + &cs_dsp_ctl_rw_test_adsp2_16bit_wmfw1, + &cs_dsp_ctl_rw_test_adsp2_16bit_wmfw2); diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_wmfw.c b/drivers/firmware/cirrus/test/cs_dsp_test_wmfw.c new file mode 100644 index 000000000000..9e997c4ee2d6 --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_test_wmfw.c @@ -0,0 +1,2211 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// KUnit tests for cs_dsp. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. +// + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Test method is: + * + * 1) Create a mock regmap in cache-only mode so that all writes will be cached. + * 2) Create dummy wmfw file. + * 3) Call cs_dsp_power_up() with the bin file. + * 4) Readback the cached value of registers that should have been written and + * check they have the correct value. + * 5) All the registers that are expected to have been written are dropped from + * the cache. This should leave the cache clean. + * 6) If the cache is still dirty there have been unexpected writes. + */ + +KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *) +KUNIT_DEFINE_ACTION_WRAPPER(_vfree_wrapper, vfree, void *) +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *) + +struct cs_dsp_test_local { + struct cs_dsp_mock_xm_header *xm_header; + struct cs_dsp_mock_wmfw_builder *wmfw_builder; + int wmfw_version; +}; + +struct cs_dsp_wmfw_test_param { + unsigned int num_blocks; + int mem_type; +}; + +static const struct cs_dsp_mock_alg_def cs_dsp_wmfw_test_mock_algs[] = { + { + .id = 0xfafa, + .ver = 0x100000, + .xm_size_words = 164, + .ym_size_words = 164, + .zm_size_words = 164, + }, +}; + +/* + * wmfw that writes the XM header. + * cs_dsp always reads this back from unpacked XM. + */ +static void wmfw_write_xm_header_unpacked(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + unsigned int reg_addr; + u8 *readback; + + /* XM header payload was added to wmfw by test case init function */ + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + /* Read raw so endianness and register width don't matter */ + readback = kunit_kzalloc(test, local->xm_header->blob_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_XM); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + local->xm_header->blob_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* Write one payload of length param->num_blocks */ +static void wmfw_write_one_payload(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int reg_addr; + u8 *payload_data, *readback; + unsigned int mem_offset_dsp_words = 0; + unsigned int payload_size_bytes; + + payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, param->mem_type); + + /* payloads must be a multiple of 4 bytes and a whole number of DSP registers */ + do { + payload_size_bytes += cs_dsp_mock_reg_block_length_bytes(priv, param->mem_type); + } while (payload_size_bytes % 4); + + payload_data = kunit_kmalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + get_random_bytes(payload_data, payload_size_bytes); + + readback = kunit_kzalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Tests on XM must be after the XM header */ + if (param->mem_type == WMFW_ADSP2_XM) + mem_offset_dsp_words += local->xm_header->blob_size_bytes / sizeof(u32); + + /* Add a single payload */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + param->mem_type, mem_offset_dsp_words, + payload_data, payload_size_bytes); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg_addr += cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv) * mem_offset_dsp_words; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, payload_size_bytes); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, payload_size_bytes); + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* Write several smallest possible payloads for the given memory type */ +static void wmfw_write_multiple_oneblock_payloads(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int reg_addr; + u8 *payload_data, *readback; + unsigned int mem_offset_dsp_words = 0; + unsigned int payload_size_bytes, payload_size_dsp_words; + const unsigned int num_payloads = param->num_blocks; + int i; + + /* payloads must be a multiple of 4 bytes and a whole number of DSP registers */ + payload_size_dsp_words = 0; + payload_size_bytes = 0; + do { + payload_size_dsp_words += cs_dsp_mock_reg_block_length_dsp_words(priv, + param->mem_type); + payload_size_bytes += cs_dsp_mock_reg_block_length_bytes(priv, param->mem_type); + } while (payload_size_bytes % 4); + + payload_data = kunit_kcalloc(test, num_payloads, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + + readback = kunit_kcalloc(test, num_payloads, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + get_random_bytes(payload_data, num_payloads * payload_size_bytes); + + /* Tests on XM must be after the XM header */ + if (param->mem_type == WMFW_ADSP2_XM) + mem_offset_dsp_words += local->xm_header->blob_size_bytes / payload_size_bytes; + + /* Add multiple payloads of one block each */ + for (i = 0; i < num_payloads; ++i) { + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + param->mem_type, + mem_offset_dsp_words + (i * payload_size_dsp_words), + &payload_data[i * payload_size_bytes], + payload_size_bytes); + } + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg_addr += cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv) * mem_offset_dsp_words; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + num_payloads * payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, num_payloads * payload_size_bytes); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, num_payloads * payload_size_bytes); + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write several smallest possible payloads of the given memory type + * in reverse address order + */ +static void wmfw_write_multiple_oneblock_payloads_reverse(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int reg_addr; + u8 *payload_data, *readback; + unsigned int mem_offset_dsp_words = 0; + unsigned int payload_size_bytes, payload_size_dsp_words; + const unsigned int num_payloads = param->num_blocks; + int i; + + /* payloads must be a multiple of 4 bytes and a whole number of DSP registers */ + payload_size_dsp_words = 0; + payload_size_bytes = 0; + do { + payload_size_dsp_words += cs_dsp_mock_reg_block_length_dsp_words(priv, + param->mem_type); + payload_size_bytes += cs_dsp_mock_reg_block_length_bytes(priv, param->mem_type); + } while (payload_size_bytes % 4); + + payload_data = kunit_kcalloc(test, num_payloads, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + + readback = kunit_kcalloc(test, num_payloads, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + get_random_bytes(payload_data, num_payloads * payload_size_bytes); + + /* Tests on XM must be after the XM header */ + if (param->mem_type == WMFW_ADSP2_XM) + mem_offset_dsp_words += local->xm_header->blob_size_bytes / payload_size_bytes; + + /* Add multiple payloads of one block each */ + for (i = num_payloads - 1; i >= 0; --i) { + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + param->mem_type, + mem_offset_dsp_words + (i * payload_size_dsp_words), + &payload_data[i * payload_size_bytes], + payload_size_bytes); + } + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg_addr += cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv) * mem_offset_dsp_words; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + num_payloads * payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, num_payloads * payload_size_bytes); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, num_payloads * payload_size_bytes); + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write multiple payloads of length param->num_blocks. + * The payloads are not in address order and collectively do not patch + * a contiguous block of memory. + */ +static void wmfw_write_multiple_payloads_sparse_unordered(struct kunit *test) +{ + static const unsigned int random_offsets[] = { + 11, 69, 59, 61, 32, 75, 4, 38, 70, 13, 79, 47, 46, 53, 18, 44, + 54, 35, 51, 21, 26, 45, 27, 41, 66, 2, 17, 56, 40, 9, 8, 20, + 29, 19, 63, 42, 12, 16, 43, 3, 5, 55, 52, 22 + }; + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int reg_addr; + u8 *payload_data, *readback; + unsigned int mem_offset_dsp_words = 0; + unsigned int payload_size_bytes, payload_size_dsp_words; + const int num_payloads = ARRAY_SIZE(random_offsets); + int i; + + payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, param->mem_type); + payload_size_dsp_words = param->num_blocks * + cs_dsp_mock_reg_block_length_dsp_words(priv, param->mem_type); + + /* payloads must be a multiple of 4 bytes and a whole number of DSP registers */ + do { + payload_size_dsp_words += cs_dsp_mock_reg_block_length_dsp_words(priv, + param->mem_type); + payload_size_bytes += cs_dsp_mock_reg_block_length_bytes(priv, param->mem_type); + } while (payload_size_bytes % 4); + + payload_data = kunit_kcalloc(test, num_payloads, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + get_random_bytes(payload_data, payload_size_bytes); + + readback = kunit_kcalloc(test, num_payloads, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Tests on XM must be after the XM header */ + if (param->mem_type == WMFW_ADSP2_XM) + mem_offset_dsp_words += local->xm_header->blob_size_bytes / payload_size_bytes; + + /* Add multiple payloads of one block each at "random" locations */ + for (i = 0; i < num_payloads; ++i) { + unsigned int offset = random_offsets[i] * payload_size_dsp_words; + + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + param->mem_type, + mem_offset_dsp_words + offset, + &payload_data[i * payload_size_bytes], + payload_size_bytes); + } + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + for (i = 0; i < num_payloads; ++i) { + unsigned int offset_num_regs = (random_offsets[i] * payload_size_bytes) / + regmap_get_val_bytes(priv->dsp->regmap); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, param->mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + reg_addr += cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv) * mem_offset_dsp_words; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, + &readback[i * payload_size_bytes], + payload_size_bytes), + 0); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, payload_size_bytes); + } + + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, payload_size_bytes); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* Write the whole of PM in a single unpacked payload */ +static void wmfw_write_all_unpacked_pm(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int reg_addr; + u8 *payload_data, *readback; + unsigned int payload_size_bytes; + + payload_size_bytes = cs_dsp_mock_size_of_region(priv->dsp, WMFW_ADSP2_PM); + payload_data = vmalloc(payload_size_bytes); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + kunit_add_action_or_reset(priv->test, _vfree_wrapper, payload_data); + + readback = vmalloc(payload_size_bytes); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + kunit_add_action_or_reset(priv->test, _vfree_wrapper, readback); + memset(readback, 0, payload_size_bytes); + + /* Add a single PM payload */ + get_random_bytes(payload_data, payload_size_bytes); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_ADSP2_PM, 0, + payload_data, payload_size_bytes); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_PM); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, payload_size_bytes); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, payload_size_bytes); + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* Write the whole of PM in a single packed payload */ +static void wmfw_write_all_packed_pm(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int reg_addr; + u8 *payload_data, *readback; + unsigned int payload_size_bytes; + + payload_size_bytes = cs_dsp_mock_size_of_region(priv->dsp, WMFW_HALO_PM_PACKED); + payload_data = vmalloc(payload_size_bytes); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + kunit_add_action_or_reset(priv->test, _vfree_wrapper, payload_data); + + readback = vmalloc(payload_size_bytes); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + kunit_add_action_or_reset(priv->test, _vfree_wrapper, readback); + memset(readback, 0, payload_size_bytes); + + /* Add a single PM payload */ + get_random_bytes(payload_data, payload_size_bytes); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_HALO_PM_PACKED, 0, + payload_data, payload_size_bytes); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_HALO_PM_PACKED); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, payload_size_bytes); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, payload_size_bytes); + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write a series of payloads to various unpacked memory regions. + * The payloads are of various lengths and offsets, driven by the + * payload_defs table. The offset and length are both given as a + * number of minimum-sized register blocks to keep the maths simpler. + * (Where a minimum-sized register block is the smallest number of + * registers that contain a whole number of DSP words.) + */ +static void wmfw_write_multiple_unpacked_mem(struct kunit *test) +{ + static const struct { + int mem_type; + unsigned int offset_num_blocks; + unsigned int num_blocks; + } payload_defs[] = { + { WMFW_ADSP2_PM, 11, 60 }, + { WMFW_ADSP2_ZM, 69, 8 }, + { WMFW_ADSP2_YM, 32, 74 }, + { WMFW_ADSP2_XM, 70, 38 }, + { WMFW_ADSP2_PM, 84, 48 }, + { WMFW_ADSP2_XM, 46, 18 }, + { WMFW_ADSP2_PM, 0, 8 }, + { WMFW_ADSP2_YM, 0, 30 }, + { WMFW_ADSP2_PM, 160, 50 }, + { WMFW_ADSP2_ZM, 21, 26 }, + }; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int payload_size_bytes, offset_num_dsp_words; + unsigned int reg_addr, offset_bytes, offset_num_regs; + void **payload_data; + void *readback; + int i, ret; + + payload_data = kunit_kcalloc(test, ARRAY_SIZE(payload_defs), sizeof(*payload_data), + GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + + for (i = 0; i < ARRAY_SIZE(payload_defs); ++i) { + payload_size_bytes = payload_defs[i].num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, + payload_defs[i].mem_type); + + payload_data[i] = kunit_kmalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data[i]); + get_random_bytes(payload_data[i], payload_size_bytes); + + offset_num_dsp_words = payload_defs[i].offset_num_blocks * + cs_dsp_mock_reg_block_length_dsp_words(priv, + payload_defs[i].mem_type); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + payload_defs[i].mem_type, + offset_num_dsp_words, + payload_data[i], + payload_size_bytes); + } + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + for (i = 0; i < ARRAY_SIZE(payload_defs); ++i) { + payload_size_bytes = payload_defs[i].num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, + payload_defs[i].mem_type); + + readback = kunit_kzalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + offset_bytes = payload_defs[i].offset_num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, payload_defs[i].mem_type); + offset_num_regs = offset_bytes / regmap_get_val_bytes(priv->dsp->regmap); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, payload_defs[i].mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + ret = regmap_raw_read(priv->dsp->regmap, reg_addr, readback, payload_size_bytes); + KUNIT_EXPECT_EQ_MSG(test, ret, 0, "%s @%u num:%u\n", + cs_dsp_mem_region_name(payload_defs[i].mem_type), + payload_defs[i].offset_num_blocks, payload_defs[i].num_blocks); + KUNIT_EXPECT_MEMEQ_MSG(test, readback, payload_data[i], payload_size_bytes, + "%s @%u num:%u\n", + cs_dsp_mem_region_name(payload_defs[i].mem_type), + payload_defs[i].offset_num_blocks, + payload_defs[i].num_blocks); + + kunit_kfree(test, readback); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, payload_size_bytes); + } + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write a series of payloads to various packed and unpacked memory regions. + * The payloads are of various lengths and offsets, driven by the + * payload_defs table. The offset and length are both given as a + * number of minimum-sized register blocks to keep the maths simpler. + * (Where a minimum-sized register block is the smallest number of + * registers that contain a whole number of DSP words.) + */ +static void wmfw_write_multiple_packed_unpacked_mem(struct kunit *test) +{ + static const struct { + int mem_type; + unsigned int offset_num_blocks; + unsigned int num_blocks; + } payload_defs[] = { + { WMFW_HALO_PM_PACKED, 11, 60 }, + { WMFW_ADSP2_YM, 69, 8 }, + { WMFW_HALO_YM_PACKED, 32, 74 }, + { WMFW_HALO_XM_PACKED, 70, 38 }, + { WMFW_HALO_PM_PACKED, 84, 48 }, + { WMFW_HALO_XM_PACKED, 46, 18 }, + { WMFW_HALO_PM_PACKED, 0, 8 }, + { WMFW_HALO_YM_PACKED, 0, 30 }, + { WMFW_HALO_PM_PACKED, 160, 50 }, + { WMFW_ADSP2_XM, 21, 26 }, + }; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int payload_size_bytes, offset_num_dsp_words; + unsigned int reg_addr, offset_bytes, offset_num_regs; + void **payload_data; + void *readback; + int i, ret; + + payload_data = kunit_kcalloc(test, ARRAY_SIZE(payload_defs), sizeof(*payload_data), + GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + + for (i = 0; i < ARRAY_SIZE(payload_defs); ++i) { + payload_size_bytes = payload_defs[i].num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, + payload_defs[i].mem_type); + + payload_data[i] = kunit_kmalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data[i]); + get_random_bytes(payload_data[i], payload_size_bytes); + + offset_num_dsp_words = payload_defs[i].offset_num_blocks * + cs_dsp_mock_reg_block_length_dsp_words(priv, + payload_defs[i].mem_type); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + payload_defs[i].mem_type, + offset_num_dsp_words, + payload_data[i], + payload_size_bytes); + } + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + for (i = 0; i < ARRAY_SIZE(payload_defs); ++i) { + payload_size_bytes = payload_defs[i].num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, + payload_defs[i].mem_type); + + readback = kunit_kzalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + offset_bytes = payload_defs[i].offset_num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, payload_defs[i].mem_type); + offset_num_regs = offset_bytes / regmap_get_val_bytes(priv->dsp->regmap); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, payload_defs[i].mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + ret = regmap_raw_read(priv->dsp->regmap, reg_addr, readback, payload_size_bytes); + KUNIT_EXPECT_EQ_MSG(test, ret, 0, "%s @%u num:%u\n", + cs_dsp_mem_region_name(payload_defs[i].mem_type), + payload_defs[i].offset_num_blocks, + payload_defs[i].num_blocks); + KUNIT_EXPECT_MEMEQ_MSG(test, readback, payload_data[i], payload_size_bytes, + "%s @%u num:%u\n", + cs_dsp_mem_region_name(payload_defs[i].mem_type), + payload_defs[i].offset_num_blocks, + payload_defs[i].num_blocks); + + kunit_kfree(test, readback); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, payload_size_bytes); + } + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is one word longer than a packed block multiple, + * using one packed payload followed by one unpacked word. + */ +static void wmfw_write_packed_1_unpacked_trailing(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int mem_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[1]; + unsigned int packed_payload_size_bytes, packed_payload_size_dsp_words; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + packed_payload_size_dsp_words = param->num_blocks * dsp_words_per_packed_block; + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) { + mem_offset_dsp_words += local->xm_header->blob_size_bytes / sizeof(u32); + + /* Round up to multiple of packed block length */ + mem_offset_dsp_words = roundup(mem_offset_dsp_words, dsp_words_per_packed_block); + } + + /* Add a single packed payload */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, mem_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + /* + * Add payload of one unpacked word to DSP memory right after + * the packed payload words. + */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + mem_offset_dsp_words + packed_payload_size_dsp_words, + unpacked_payload_data, sizeof(unpacked_payload_data)); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked word was written correctly and drop + * it from the regmap cache. The unpacked payload is offset within + * unpacked register space by the number of DSP words that were + * written in the packed payload. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + offset_num_regs += (packed_payload_size_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is two words longer than a packed block multiple, + * using one packed payload followed by one payload of two unpacked words. + */ +static void wmfw_write_packed_2_unpacked_trailing(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int mem_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[2]; + unsigned int packed_payload_size_bytes, packed_payload_size_dsp_words; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + packed_payload_size_dsp_words = param->num_blocks * dsp_words_per_packed_block; + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) { + mem_offset_dsp_words += local->xm_header->blob_size_bytes / sizeof(u32); + + /* Round up to multiple of packed block length */ + mem_offset_dsp_words = roundup(mem_offset_dsp_words, dsp_words_per_packed_block); + } + + /* Add a single packed payload */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, mem_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + /* + * Add payload of two unpacked words to DSP memory right after + * the packed payload words. + */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + mem_offset_dsp_words + packed_payload_size_dsp_words, + unpacked_payload_data, sizeof(unpacked_payload_data)); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked words were written correctly and drop + * them from the regmap cache. The unpacked payload is offset + * within unpacked register space by the number of DSP words + * that were written in the packed payload. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + offset_num_regs += (packed_payload_size_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is three words longer than a packed block multiple, + * using one packed payload followed by one payload of three unpacked words. + */ +static void wmfw_write_packed_3_unpacked_trailing(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int mem_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[3]; + unsigned int packed_payload_size_bytes, packed_payload_size_dsp_words; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + packed_payload_size_dsp_words = param->num_blocks * dsp_words_per_packed_block; + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) { + mem_offset_dsp_words += local->xm_header->blob_size_bytes / sizeof(u32); + + /* Round up to multiple of packed block length */ + mem_offset_dsp_words = roundup(mem_offset_dsp_words, dsp_words_per_packed_block); + } + + /* Add a single packed payload */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, mem_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + /* + * Add payload of three unpacked words to DSP memory right after + * the packed payload words. + */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + mem_offset_dsp_words + packed_payload_size_dsp_words, + unpacked_payload_data, sizeof(unpacked_payload_data)); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked words were written correctly and drop + * them from the regmap cache. The unpacked payload is offset + * within unpacked register space by the number of DSP words + * that were written in the packed payload. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + offset_num_regs += (packed_payload_size_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is two words longer than a packed block multiple, + * using one packed payload followed by two payloads of one unpacked word each. + */ +static void wmfw_write_packed_2_single_unpacked_trailing(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int mem_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[2]; + unsigned int packed_payload_size_bytes, packed_payload_size_dsp_words; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + packed_payload_size_dsp_words = param->num_blocks * dsp_words_per_packed_block; + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) { + mem_offset_dsp_words += local->xm_header->blob_size_bytes / sizeof(u32); + + /* Round up to multiple of packed block length */ + mem_offset_dsp_words = roundup(mem_offset_dsp_words, dsp_words_per_packed_block); + } + + /* Add a single packed payload */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, mem_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + /* + * Add two unpacked words to DSP memory right after the packed + * payload words. Each unpacked word in its own payload. + */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + mem_offset_dsp_words + packed_payload_size_dsp_words, + &unpacked_payload_data[0], + sizeof(unpacked_payload_data[0])); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + mem_offset_dsp_words + packed_payload_size_dsp_words + 1, + &unpacked_payload_data[1], + sizeof(unpacked_payload_data[1])); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked words were written correctly and drop + * them from the regmap cache. The unpacked words are offset + * within unpacked register space by the number of DSP words + * that were written in the packed payload. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + offset_num_regs += (packed_payload_size_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is three words longer than a packed block multiple, + * using one packed payload followed by three payloads of one unpacked word each. + */ +static void wmfw_write_packed_3_single_unpacked_trailing(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int mem_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[3]; + unsigned int packed_payload_size_bytes, packed_payload_size_dsp_words; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + packed_payload_size_dsp_words = param->num_blocks * dsp_words_per_packed_block; + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) { + mem_offset_dsp_words += local->xm_header->blob_size_bytes / sizeof(u32); + + /* Round up to multiple of packed block length */ + mem_offset_dsp_words = roundup(mem_offset_dsp_words, dsp_words_per_packed_block); + } + + /* Add a single packed payload */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, mem_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + /* + * Add three unpacked words to DSP memory right after the packed + * payload words. Each unpacked word in its own payload. + */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + mem_offset_dsp_words + packed_payload_size_dsp_words, + &unpacked_payload_data[0], + sizeof(unpacked_payload_data[0])); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + mem_offset_dsp_words + packed_payload_size_dsp_words + 1, + &unpacked_payload_data[1], + sizeof(unpacked_payload_data[1])); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + mem_offset_dsp_words + packed_payload_size_dsp_words + 2, + &unpacked_payload_data[2], + sizeof(unpacked_payload_data[2])); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked words were written correctly and drop + * them from the regmap cache. The unpacked words are offset + * within unpacked register space by the number of DSP words + * that were written in the packed payload. + */ + offset_num_regs = (mem_offset_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + offset_num_regs += (packed_payload_size_dsp_words / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is one word longer than a packed block multiple, + * and does not start on a packed alignment. Use one unpacked word + * followed by a packed payload. + */ +static void wmfw_write_packed_1_unpacked_leading(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int packed_payload_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[1]; + unsigned int packed_payload_size_bytes; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) + packed_payload_offset_dsp_words += local->xm_header->blob_size_bytes / + sizeof(u32); + /* + * Leave space for an unaligned word before the packed block and + * round the packed block start to multiple of packed block length. + */ + packed_payload_offset_dsp_words += 1; + packed_payload_offset_dsp_words = roundup(packed_payload_offset_dsp_words, + dsp_words_per_packed_block); + + /* Add a single unpacked word right before the first word of packed data */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + packed_payload_offset_dsp_words - 1, + unpacked_payload_data, sizeof(unpacked_payload_data)); + + /* Add payload of packed data to the DSP memory after the unpacked word. */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, + packed_payload_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (packed_payload_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked word was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = ((packed_payload_offset_dsp_words - 1) / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is two words longer than a packed block multiple, + * and does not start on a packed alignment. Use one payload of two unpacked + * words followed by a packed payload. + */ +static void wmfw_write_packed_2_unpacked_leading(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int packed_payload_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[2]; + unsigned int packed_payload_size_bytes; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) + packed_payload_offset_dsp_words += local->xm_header->blob_size_bytes / + sizeof(u32); + /* + * Leave space for two unaligned words before the packed block and + * round the packed block start to multiple of packed block length. + */ + packed_payload_offset_dsp_words += 2; + packed_payload_offset_dsp_words = roundup(packed_payload_offset_dsp_words, + dsp_words_per_packed_block); + + /* + * Add two unpacked words as a single payload right before the + * first word of packed data + */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + packed_payload_offset_dsp_words - 2, + unpacked_payload_data, sizeof(unpacked_payload_data)); + + /* Add payload of packed data to the DSP memory after the unpacked words. */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, + packed_payload_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (packed_payload_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked words were written correctly and drop + * them from the regmap cache. + */ + offset_num_regs = ((packed_payload_offset_dsp_words - 2) / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is three words longer than a packed block multiple, + * and does not start on a packed alignment. Use one payload of three unpacked + * words followed by a packed payload. + */ +static void wmfw_write_packed_3_unpacked_leading(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int packed_payload_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[3]; + unsigned int packed_payload_size_bytes; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) + packed_payload_offset_dsp_words += local->xm_header->blob_size_bytes / + sizeof(u32); + /* + * Leave space for three unaligned words before the packed block and + * round the packed block start to multiple of packed block length. + */ + packed_payload_offset_dsp_words += 3; + packed_payload_offset_dsp_words = roundup(packed_payload_offset_dsp_words, + dsp_words_per_packed_block); + + /* + * Add three unpacked words as a single payload right before the + * first word of packed data + */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + packed_payload_offset_dsp_words - 3, + unpacked_payload_data, sizeof(unpacked_payload_data)); + + /* Add payload of packed data to the DSP memory after the unpacked words. */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, + packed_payload_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (packed_payload_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked words were written correctly and drop + * them from the regmap cache. + */ + offset_num_regs = ((packed_payload_offset_dsp_words - 3) / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is two words longer than a packed block multiple, + * and does not start on a packed alignment. Use two payloads of one unpacked + * word each, followed by a packed payload. + */ +static void wmfw_write_packed_2_single_unpacked_leading(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int packed_payload_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[2]; + unsigned int packed_payload_size_bytes; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) + packed_payload_offset_dsp_words += local->xm_header->blob_size_bytes / + sizeof(u32); + /* + * Leave space for two unaligned words before the packed block and + * round the packed block start to multiple of packed block length. + */ + packed_payload_offset_dsp_words += 2; + packed_payload_offset_dsp_words = roundup(packed_payload_offset_dsp_words, + dsp_words_per_packed_block); + + /* + * Add two unpacked words as two payloads each containing a single + * unpacked word. + */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + packed_payload_offset_dsp_words - 2, + &unpacked_payload_data[0], + sizeof(unpacked_payload_data[0])); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + packed_payload_offset_dsp_words - 1, + &unpacked_payload_data[1], + sizeof(unpacked_payload_data[1])); + + /* Add payload of packed data to the DSP memory after the unpacked words. */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, + packed_payload_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (packed_payload_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked words were written correctly and drop + * them from the regmap cache. + */ + offset_num_regs = ((packed_payload_offset_dsp_words - 2) / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* + * Write XM/YM data that is three words longer than a packed block multiple, + * and does not start on a packed alignment. Use three payloads of one unpacked + * word each, followed by a packed payload. + */ +static void wmfw_write_packed_3_single_unpacked_leading(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + int packed_mem_type = param->mem_type; + int unpacked_mem_type = cs_dsp_mock_packed_to_unpacked_mem_type(param->mem_type); + unsigned int dsp_words_per_packed_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, packed_mem_type); + unsigned int dsp_words_per_unpacked_block = + cs_dsp_mock_reg_block_length_dsp_words(priv, unpacked_mem_type); + unsigned int packed_payload_offset_dsp_words = 0; + struct firmware *wmfw; + unsigned int reg_addr; + void *packed_payload_data, *readback; + u32 unpacked_payload_data[3]; + unsigned int packed_payload_size_bytes; + unsigned int offset_num_regs; + + packed_payload_size_bytes = param->num_blocks * + cs_dsp_mock_reg_block_length_bytes(priv, packed_mem_type); + + packed_payload_data = kunit_kmalloc(test, packed_payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, packed_payload_data); + get_random_bytes(packed_payload_data, packed_payload_size_bytes); + + get_random_bytes(unpacked_payload_data, sizeof(unpacked_payload_data)); + + readback = kunit_kzalloc(test, packed_payload_size_bytes, GFP_KERNEL); + + /* Tests on XM must be after the XM header */ + if (unpacked_mem_type == WMFW_ADSP2_XM) + packed_payload_offset_dsp_words += local->xm_header->blob_size_bytes / + sizeof(u32); + /* + * Leave space for two unaligned words before the packed block and + * round the packed block start to multiple of packed block length. + */ + packed_payload_offset_dsp_words += 3; + packed_payload_offset_dsp_words = roundup(packed_payload_offset_dsp_words, + dsp_words_per_packed_block); + + /* + * Add three unpacked words as three payloads each containing a single + * unpacked word. + */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + packed_payload_offset_dsp_words - 3, + &unpacked_payload_data[0], + sizeof(unpacked_payload_data[0])); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + packed_payload_offset_dsp_words - 2, + &unpacked_payload_data[1], + sizeof(unpacked_payload_data[1])); + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + unpacked_mem_type, + packed_payload_offset_dsp_words - 1, + &unpacked_payload_data[2], + sizeof(unpacked_payload_data[2])); + + /* Add payload of packed data to the DSP memory after the unpacked words. */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + packed_mem_type, + packed_payload_offset_dsp_words, + packed_payload_data, packed_payload_size_bytes); + + /* Download the wmfw */ + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + /* + * Check that the packed payload was written correctly and drop + * it from the regmap cache. + */ + offset_num_regs = (packed_payload_offset_dsp_words / dsp_words_per_packed_block) * + cs_dsp_mock_reg_block_length_registers(priv, packed_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, packed_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + packed_payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, packed_payload_data, packed_payload_size_bytes); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, packed_payload_size_bytes); + + /* + * Check that the unpacked words were written correctly and drop + * them from the regmap cache. + */ + offset_num_regs = ((packed_payload_offset_dsp_words - 3) / dsp_words_per_unpacked_block) * + cs_dsp_mock_reg_block_length_registers(priv, unpacked_mem_type); + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, unpacked_mem_type); + reg_addr += offset_num_regs * regmap_get_reg_stride(priv->dsp->regmap); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, + sizeof(unpacked_payload_data)), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, unpacked_payload_data, sizeof(unpacked_payload_data)); + + cs_dsp_mock_regmap_drop_bytes(priv, reg_addr, sizeof(unpacked_payload_data)); + + /* Drop expected writes and the cache should then be clean */ + cs_dsp_mock_xm_header_drop_from_regmap_cache(priv); + KUNIT_EXPECT_FALSE(test, cs_dsp_mock_regmap_is_dirty(priv, true)); +} + +/* Load a wmfw containing multiple info blocks */ +static void wmfw_load_with_info(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int reg_addr; + u8 *payload_data, *readback; + char *infobuf; + const unsigned int payload_size_bytes = 48; + int ret; + + payload_data = kunit_kmalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + get_random_bytes(payload_data, payload_size_bytes); + + readback = kunit_kzalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Add a couple of info blocks at the start of the wmfw */ + cs_dsp_mock_wmfw_add_info(local->wmfw_builder, "This is a timestamp"); + cs_dsp_mock_wmfw_add_info(local->wmfw_builder, "This is some more info"); + + /* Add a single payload */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_ADSP2_YM, 0, + payload_data, payload_size_bytes); + + /* Add a bigger info block then another small one*/ + infobuf = kunit_kzalloc(test, 512, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, infobuf); + + for (; strlcat(infobuf, "Waffle{Blah}\n", 512) < 512;) + ; + + cs_dsp_mock_wmfw_add_info(local->wmfw_builder, infobuf); + cs_dsp_mock_wmfw_add_info(local->wmfw_builder, "Another block of info"); + + /* Add another payload */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_ADSP2_YM, 64, + payload_data, payload_size_bytes); + + wmfw = cs_dsp_mock_wmfw_get_firmware(priv->local->wmfw_builder); + + ret = cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"); + KUNIT_EXPECT_EQ_MSG(test, ret, 0, "cs_dsp_power_up failed: %d\n", ret); + + /* Check first payload was written */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_YM); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, payload_size_bytes); + + /* Check second payload was written */ + reg_addr += cs_dsp_mock_reg_addr_inc_per_unpacked_word(priv) * 64; + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, payload_size_bytes); +} + +static int cs_dsp_wmfw_test_common_init(struct kunit *test, struct cs_dsp *dsp, + int wmfw_version) +{ + struct cs_dsp_test *priv; + struct cs_dsp_test_local *local; + struct device *test_dev; + int ret; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + local = kunit_kzalloc(test, sizeof(struct cs_dsp_test_local), GFP_KERNEL); + if (!local) + return -ENOMEM; + + priv->test = test; + priv->dsp = dsp; + test->priv = priv; + priv->local = local; + priv->local->wmfw_version = wmfw_version; + + /* Create dummy struct device */ + test_dev = kunit_device_register(test, "cs_dsp_test_drv"); + if (IS_ERR(test_dev)) + return PTR_ERR(test_dev); + + dsp->dev = get_device(test_dev); + if (!dsp->dev) + return -ENODEV; + + ret = kunit_add_action_or_reset(test, _put_device_wrapper, dsp->dev); + if (ret) + return ret; + + dev_set_drvdata(dsp->dev, priv); + + /* Allocate regmap */ + ret = cs_dsp_mock_regmap_init(priv); + if (ret) + return ret; + + /* + * There must always be a XM header with at least 1 algorithm, so create + * a dummy one that tests can use and extract it to a data payload. + */ + local->xm_header = cs_dsp_create_mock_xm_header(priv, + cs_dsp_wmfw_test_mock_algs, + ARRAY_SIZE(cs_dsp_wmfw_test_mock_algs)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->xm_header); + + local->wmfw_builder = cs_dsp_mock_wmfw_init(priv, priv->local->wmfw_version); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->wmfw_builder); + + /* Add dummy XM header payload to wmfw */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_ADSP2_XM, 0, + local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + /* Init cs_dsp */ + dsp->client_ops = kunit_kzalloc(test, sizeof(*dsp->client_ops), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dsp->client_ops); + + switch (dsp->type) { + case WMFW_ADSP2: + ret = cs_dsp_adsp2_init(dsp); + break; + case WMFW_HALO: + ret = cs_dsp_halo_init(dsp); + break; + default: + KUNIT_FAIL(test, "Untested DSP type %d\n", dsp->type); + return -EINVAL; + } + + if (ret) + return ret; + + /* Automatically call cs_dsp_remove() when test case ends */ + return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); +} + +static int cs_dsp_wmfw_test_halo_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_HALO; + dsp->mem = cs_dsp_mock_halo_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_halo_dsp1_region_sizes); + dsp->base = cs_dsp_mock_halo_core_base; + dsp->base_sysinfo = cs_dsp_mock_halo_sysinfo_base; + + return cs_dsp_wmfw_test_common_init(test, dsp, 3); +} + +static int cs_dsp_wmfw_test_adsp2_32bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 1; + dsp->mem = cs_dsp_mock_adsp2_32bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_32bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_32bit_sysbase; + + return cs_dsp_wmfw_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_wmfw_test_adsp2_32bit_wmfw0_init(struct kunit *test) +{ + return cs_dsp_wmfw_test_adsp2_32bit_init(test, 0); +} + +static int cs_dsp_wmfw_test_adsp2_32bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_wmfw_test_adsp2_32bit_init(test, 1); +} + +static int cs_dsp_wmfw_test_adsp2_32bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_wmfw_test_adsp2_32bit_init(test, 2); +} + +static int cs_dsp_wmfw_test_adsp2_16bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 0; + dsp->mem = cs_dsp_mock_adsp2_16bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_16bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_16bit_sysbase; + + return cs_dsp_wmfw_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_wmfw_test_adsp2_16bit_wmfw0_init(struct kunit *test) +{ + return cs_dsp_wmfw_test_adsp2_16bit_init(test, 0); +} + +static int cs_dsp_wmfw_test_adsp2_16bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_wmfw_test_adsp2_16bit_init(test, 1); +} + +static int cs_dsp_wmfw_test_adsp2_16bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_wmfw_test_adsp2_16bit_init(test, 2); +} + +static void cs_dsp_mem_param_desc(const struct cs_dsp_wmfw_test_param *param, char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%s num_blocks:%u", + cs_dsp_mem_region_name(param->mem_type), + param->num_blocks); +} + +static const struct cs_dsp_wmfw_test_param adsp2_all_num_blocks_param_cases[] = { + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 1 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 2 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 3 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 4 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 5 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 6 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 12 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 13 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 14 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 15 }, + { .mem_type = WMFW_ADSP2_PM, .num_blocks = 16 }, + + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 1 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 2 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 3 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 4 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 5 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 6 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 12 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 13 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 14 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 15 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 16 }, + + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 1 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 2 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 3 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 4 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 5 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 6 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 12 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 13 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 14 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 15 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 16 }, + + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 1 }, + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 2 }, + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 3 }, + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 4 }, + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 5 }, + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 6 }, + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 12 }, + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 13 }, + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 14 }, + { .mem_type = WMFW_ADSP2_ZM, .num_blocks = 15 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 16 }, +}; + +KUNIT_ARRAY_PARAM(adsp2_all_num_blocks, + adsp2_all_num_blocks_param_cases, + cs_dsp_mem_param_desc); + +static const struct cs_dsp_wmfw_test_param halo_all_num_blocks_param_cases[] = { + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 1 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 2 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 3 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 4 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 5 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 6 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 12 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 13 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 14 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 15 }, + { .mem_type = WMFW_HALO_PM_PACKED, .num_blocks = 16 }, + + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 1 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 2 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 3 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 4 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 5 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 6 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 12 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 13 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 14 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 15 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 16 }, + + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 1 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 2 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 3 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 4 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 5 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 6 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 12 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 13 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 14 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 15 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 16 }, + + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 1 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 2 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 3 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 4 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 5 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 6 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 12 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 13 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 14 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 15 }, + { .mem_type = WMFW_ADSP2_XM, .num_blocks = 16 }, + + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 1 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 2 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 3 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 4 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 5 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 6 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 12 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 13 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 14 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 15 }, + { .mem_type = WMFW_ADSP2_YM, .num_blocks = 16 }, +}; + +KUNIT_ARRAY_PARAM(halo_all_num_blocks, + halo_all_num_blocks_param_cases, + cs_dsp_mem_param_desc); + +static const struct cs_dsp_wmfw_test_param packed_xy_num_blocks_param_cases[] = { + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 1 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 2 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 3 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 4 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 5 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 6 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 12 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 13 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 14 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 15 }, + { .mem_type = WMFW_HALO_XM_PACKED, .num_blocks = 16 }, + + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 1 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 2 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 3 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 4 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 5 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 6 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 12 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 13 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 14 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 15 }, + { .mem_type = WMFW_HALO_YM_PACKED, .num_blocks = 16 }, +}; + +KUNIT_ARRAY_PARAM(packed_xy_num_blocks, + packed_xy_num_blocks_param_cases, + cs_dsp_mem_param_desc); + +static struct kunit_case cs_dsp_wmfw_test_cases_halo[] = { + KUNIT_CASE(wmfw_write_xm_header_unpacked), + + KUNIT_CASE_PARAM(wmfw_write_one_payload, + halo_all_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_multiple_oneblock_payloads, + halo_all_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_multiple_oneblock_payloads_reverse, + halo_all_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_multiple_payloads_sparse_unordered, + halo_all_num_blocks_gen_params), + + KUNIT_CASE(wmfw_write_all_packed_pm), + KUNIT_CASE(wmfw_write_multiple_packed_unpacked_mem), + + KUNIT_CASE_PARAM(wmfw_write_packed_1_unpacked_trailing, + packed_xy_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_packed_2_unpacked_trailing, + packed_xy_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_packed_3_unpacked_trailing, + packed_xy_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_packed_2_single_unpacked_trailing, + packed_xy_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_packed_3_single_unpacked_trailing, + packed_xy_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_packed_1_unpacked_leading, + packed_xy_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_packed_2_unpacked_leading, + packed_xy_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_packed_3_unpacked_leading, + packed_xy_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_packed_2_single_unpacked_leading, + packed_xy_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_packed_3_single_unpacked_leading, + packed_xy_num_blocks_gen_params), + + KUNIT_CASE(wmfw_load_with_info), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_wmfw_test_cases_adsp2[] = { + KUNIT_CASE(wmfw_write_xm_header_unpacked), + KUNIT_CASE_PARAM(wmfw_write_one_payload, + adsp2_all_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_multiple_oneblock_payloads, + adsp2_all_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_multiple_oneblock_payloads_reverse, + adsp2_all_num_blocks_gen_params), + KUNIT_CASE_PARAM(wmfw_write_multiple_payloads_sparse_unordered, + adsp2_all_num_blocks_gen_params), + + KUNIT_CASE(wmfw_write_all_unpacked_pm), + KUNIT_CASE(wmfw_write_multiple_unpacked_mem), + + KUNIT_CASE(wmfw_load_with_info), + + { } /* terminator */ +}; + +static struct kunit_suite cs_dsp_wmfw_test_halo = { + .name = "cs_dsp_wmfwV3_halo", + .init = cs_dsp_wmfw_test_halo_init, + .test_cases = cs_dsp_wmfw_test_cases_halo, +}; + +static struct kunit_suite cs_dsp_wmfw_test_adsp2_32bit_wmfw0 = { + .name = "cs_dsp_wmfwV0_adsp2_32bit", + .init = cs_dsp_wmfw_test_adsp2_32bit_wmfw0_init, + .test_cases = cs_dsp_wmfw_test_cases_adsp2, +}; + +static struct kunit_suite cs_dsp_wmfw_test_adsp2_32bit_wmfw1 = { + .name = "cs_dsp_wmfwV1_adsp2_32bit", + .init = cs_dsp_wmfw_test_adsp2_32bit_wmfw1_init, + .test_cases = cs_dsp_wmfw_test_cases_adsp2, +}; + +static struct kunit_suite cs_dsp_wmfw_test_adsp2_32bit_wmfw2 = { + .name = "cs_dsp_wmfwV2_adsp2_32bit", + .init = cs_dsp_wmfw_test_adsp2_32bit_wmfw2_init, + .test_cases = cs_dsp_wmfw_test_cases_adsp2, +}; + +static struct kunit_suite cs_dsp_wmfw_test_adsp2_16bit_wmfw0 = { + .name = "cs_dsp_wmfwV0_adsp2_16bit", + .init = cs_dsp_wmfw_test_adsp2_16bit_wmfw0_init, + .test_cases = cs_dsp_wmfw_test_cases_adsp2, +}; + +static struct kunit_suite cs_dsp_wmfw_test_adsp2_16bit_wmfw1 = { + .name = "cs_dsp_wmfwV1_adsp2_16bit", + .init = cs_dsp_wmfw_test_adsp2_16bit_wmfw1_init, + .test_cases = cs_dsp_wmfw_test_cases_adsp2, +}; + +static struct kunit_suite cs_dsp_wmfw_test_adsp2_16bit_wmfw2 = { + .name = "cs_dsp_wmfwV2_adsp2_16bit", + .init = cs_dsp_wmfw_test_adsp2_16bit_wmfw2_init, + .test_cases = cs_dsp_wmfw_test_cases_adsp2, +}; + +kunit_test_suites(&cs_dsp_wmfw_test_halo, + &cs_dsp_wmfw_test_adsp2_32bit_wmfw0, + &cs_dsp_wmfw_test_adsp2_32bit_wmfw1, + &cs_dsp_wmfw_test_adsp2_32bit_wmfw2, + &cs_dsp_wmfw_test_adsp2_16bit_wmfw0, + &cs_dsp_wmfw_test_adsp2_16bit_wmfw1, + &cs_dsp_wmfw_test_adsp2_16bit_wmfw2); diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_wmfw_error.c b/drivers/firmware/cirrus/test/cs_dsp_test_wmfw_error.c new file mode 100644 index 000000000000..c309843261d7 --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_test_wmfw_error.c @@ -0,0 +1,1347 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// KUnit tests for cs_dsp. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. +// + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *); +KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *); + +struct cs_dsp_test_local { + struct cs_dsp_mock_xm_header *xm_header; + struct cs_dsp_mock_wmfw_builder *wmfw_builder; + int wmfw_version; +}; + +struct cs_dsp_wmfw_test_param { + int block_type; +}; + +static const struct cs_dsp_mock_alg_def cs_dsp_wmfw_err_test_mock_algs[] = { + { + .id = 0xfafa, + .ver = 0x100000, + .xm_size_words = 164, + .ym_size_words = 164, + .zm_size_words = 164, + }, +}; + +static const struct cs_dsp_mock_coeff_def mock_coeff_template = { + .shortname = "Dummy Coeff", + .type = WMFW_CTL_TYPE_BYTES, + .mem_type = WMFW_ADSP2_YM, + .flags = WMFW_CTL_FLAG_VOLATILE, + .length_bytes = 4, +}; + +/* Load a wmfw containing unknown blocks. They should be skipped. */ +static void wmfw_load_with_unknown_blocks(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int reg_addr; + u8 *payload_data, *readback; + u8 random_data[8]; + const unsigned int payload_size_bytes = 64; + + /* Add dummy XM header payload to wmfw */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_ADSP2_XM, 0, + local->xm_header->blob_data, + local->xm_header->blob_size_bytes); + + payload_data = kunit_kmalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, payload_data); + get_random_bytes(payload_data, payload_size_bytes); + + readback = kunit_kzalloc(test, payload_size_bytes, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, readback); + + /* Add some unknown blocks at the start of the wmfw */ + get_random_bytes(random_data, sizeof(random_data)); + cs_dsp_mock_wmfw_add_raw_block(local->wmfw_builder, 0xf5, 0, + random_data, sizeof(random_data)); + cs_dsp_mock_wmfw_add_raw_block(local->wmfw_builder, 0xc0, 0, random_data, + sizeof(random_data)); + cs_dsp_mock_wmfw_add_raw_block(local->wmfw_builder, 0x33, 0, NULL, 0); + + /* Add a single payload to be written to DSP memory */ + cs_dsp_mock_wmfw_add_data_block(local->wmfw_builder, + WMFW_ADSP2_YM, 0, + payload_data, payload_size_bytes); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + /* Check that the payload was written to memory */ + reg_addr = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_YM); + KUNIT_EXPECT_EQ(test, + regmap_raw_read(priv->dsp->regmap, reg_addr, readback, payload_size_bytes), + 0); + KUNIT_EXPECT_MEMEQ(test, readback, payload_data, payload_size_bytes); +} + +/* Load a wmfw that doesn't have a valid magic marker. */ +static void wmfw_err_wrong_magic(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + memcpy((void *)wmfw->data, "WMDR", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + memcpy((void *)wmfw->data, "xMFW", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + memcpy((void *)wmfw->data, "WxFW", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + memcpy((void *)wmfw->data, "WMxW", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + memcpy((void *)wmfw->data, "WMFx", 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + memset((void *)wmfw->data, 0, 4); + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); +} + +/* Load a wmfw that is too short for a valid header. */ +static void wmfw_err_too_short_for_header(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + do { + wmfw->size--; + + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + } while (wmfw->size > 0); +} + +/* Header length field isn't a valid header length. */ +static void wmfw_err_bad_header_length(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + unsigned int real_len, len; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + real_len = le32_to_cpu(header->len); + + for (len = 0; len < real_len; len++) { + header->len = cpu_to_le32(len); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + } + + for (len = real_len + 1; len < real_len + 7; len++) { + header->len = cpu_to_le32(len); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + } + + header->len = cpu_to_le32(0xffffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + header->len = cpu_to_le32(0x80000000); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + header->len = cpu_to_le32(0x7fffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +/* Wrong core type in header. */ +static void wmfw_err_bad_core_type(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + + header->core = 0; + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + header->core = 1; + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + header->core = priv->dsp->type + 1; + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + + header->core = 0xff; + KUNIT_EXPECT_LT(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); +} + +/* File too short to contain a full block header */ +static void wmfw_too_short_for_block_header(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int header_length; + u32 dummy_payload = 0; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + header_length = wmfw->size; + kunit_kfree(test, wmfw); + + /* Add the block. A block must have at least 4 bytes of payload */ + cs_dsp_mock_wmfw_add_raw_block(local->wmfw_builder, param->block_type, 0, + &dummy_payload, sizeof(dummy_payload)); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + KUNIT_ASSERT_GT(test, wmfw->size, header_length); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + for (wmfw->size--; wmfw->size > header_length; wmfw->size--) { + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + } +} + +/* File too short to contain the block payload */ +static void wmfw_too_short_for_block_payload(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + static const u8 payload[256] = { }; + int i; + + cs_dsp_mock_wmfw_add_raw_block(local->wmfw_builder, param->block_type, 0, + payload, sizeof(payload)); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + for (i = 0; i < sizeof(payload); i++) { + wmfw->size--; + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + } +} + +/* Block payload length is a garbage value */ +static void wmfw_block_payload_len_garbage(struct kunit *test) +{ + const struct cs_dsp_wmfw_test_param *param = test->param_value; + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + u32 payload = 0; + + + cs_dsp_mock_wmfw_add_raw_block(local->wmfw_builder, param->block_type, 0, + &payload, sizeof(payload)); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + + /* Sanity check that we're looking at the correct part of the wmfw */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(region->offset) >> 24, param->block_type); + KUNIT_ASSERT_EQ(test, le32_to_cpu(region->len), sizeof(payload)); + + region->len = cpu_to_le32(0x8000); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + region->len = cpu_to_le32(0xffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + region->len = cpu_to_le32(0x7fffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + region->len = cpu_to_le32(0x80000000); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + region->len = cpu_to_le32(0xffffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +/* File too short to contain an algorithm header */ +static void wmfw_too_short_for_alg_header(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + unsigned int header_length; + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + header_length = wmfw->size; + kunit_kfree(test, wmfw); + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + NULL, NULL); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + KUNIT_ASSERT_GT(test, wmfw->size, header_length); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + for (wmfw->size--; wmfw->size > header_length; wmfw->size--) { + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + } +} + +/* V1 algorithm name does not have NUL terminator */ +static void wmfw_v1_alg_name_unterminated(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + struct wmfw_adsp_alg_data *alg_data; + struct cs_dsp_coeff_ctl *ctl; + + /* Create alg info block with a coefficient */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", "de"); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &mock_coeff_template); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (struct wmfw_adsp_alg_data *)region->data; + + /* Sanity check we're pointing at the alg header */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data->id), cs_dsp_wmfw_err_test_mock_algs[0].id); + + /* Write a string to the alg name that overflows the array */ + memset(alg_data->descr, 0, sizeof(alg_data->descr)); + memset(alg_data->name, 'A', sizeof(alg_data->name)); + memset(alg_data->descr, 'A', sizeof(alg_data->descr) - 1); + + /* + * Sanity-check that a strlen would overflow alg_data->name. + * FORTIFY_STRING obstructs testing what strlen() would actually + * return, so instead verify that a strnlen() returns + * sizeof(alg_data->name[]), therefore it doesn't have a NUL. + */ + KUNIT_ASSERT_EQ(test, strnlen(alg_data->name, sizeof(alg_data->name)), + sizeof(alg_data->name)); + + /* + * The alg name isn't stored, but cs_dsp parses the name field. + * It should load the file successfully and create the control. + * If FORTIFY_STRING is enabled it will detect a buffer overflow + * if cs_dsp string length walks past end of alg name array. + */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, 0); +} + +/* V2+ algorithm name exceeds length of containing block */ +static void wmfw_v2_alg_name_exceeds_block(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + __le32 *alg_data; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", NULL); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (__force __le32 *)region->data; + + /* + * Sanity check we're pointing at the alg header of + * [ alg_id ][name_len]abc + */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data[0]), cs_dsp_wmfw_err_test_mock_algs[0].id); + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data[1]), 3 | ('a' << 8) | ('b' << 16) | ('c' << 24)); + KUNIT_ASSERT_EQ(test, *(u8 *)&alg_data[1], 3); + + /* Set name string length longer than available space */ + *(u8 *)&alg_data[1] = 4; + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *(u8 *)&alg_data[1] = 7; + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *(u8 *)&alg_data[1] = 0x80; + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *(u8 *)&alg_data[1] = 0xff; + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +/* V2+ algorithm description exceeds length of containing block */ +static void wmfw_v2_alg_description_exceeds_block(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + __le32 *alg_data; + + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", "de"); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (__force __le32 *)region->data; + + /* + * Sanity check we're pointing at the alg header of + * [ alg_id ][name_len]abc[desc_len]de + */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data[0]), cs_dsp_wmfw_err_test_mock_algs[0].id); + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data[2]), 2 | ('d' << 16) | ('e' << 24)); + KUNIT_ASSERT_EQ(test, le16_to_cpu(*(__le16 *)&alg_data[2]), 2); + + /* Set name string length longer than available space */ + *(__le16 *)&alg_data[2] = cpu_to_le16(4); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *(__le16 *)&alg_data[2] = cpu_to_le16(7); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *(__le16 *)&alg_data[2] = cpu_to_le16(0x80); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *(__le16 *)&alg_data[2] = cpu_to_le16(0xff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *(__le16 *)&alg_data[2] = cpu_to_le16(0x8000); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *(__le16 *)&alg_data[2] = cpu_to_le16(0xffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +/* V1 coefficient count exceeds length of containing block */ +static void wmfw_v1_coeff_count_exceeds_block(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + struct wmfw_adsp_alg_data *alg_data; + + /* Create alg info block with a coefficient */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", "de"); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &mock_coeff_template); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (struct wmfw_adsp_alg_data *)region->data; + + /* Sanity check we're pointing at the alg header */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data->id), cs_dsp_wmfw_err_test_mock_algs[0].id); + + /* Add one to the coefficient count */ + alg_data->ncoeff = cpu_to_le32(le32_to_cpu(alg_data->ncoeff) + 1); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + /* Make the coefficient count garbage */ + alg_data->ncoeff = cpu_to_le32(0xffffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + alg_data->ncoeff = cpu_to_le32(0x7fffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + alg_data->ncoeff = cpu_to_le32(0x80000000); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +/* V2+ coefficient count exceeds length of containing block */ +static void wmfw_v2_coeff_count_exceeds_block(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + __le32 *alg_data, *ncoeff; + + /* Create alg info block with a coefficient */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", "de"); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &mock_coeff_template); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (__force __le32 *)region->data; + + /* Sanity check we're pointing at the alg header */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data[0]), cs_dsp_wmfw_err_test_mock_algs[0].id); + + ncoeff = (__force __le32 *)&alg_data[3]; + KUNIT_ASSERT_EQ(test, le32_to_cpu(*ncoeff), 1); + + /* Add one to the coefficient count */ + *ncoeff = cpu_to_le32(2); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + /* Make the coefficient count garbage */ + *ncoeff = cpu_to_le32(0xffffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *ncoeff = cpu_to_le32(0x7fffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + *ncoeff = cpu_to_le32(0x80000000); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +/* V2+ coefficient block size exceeds length of containing block */ +static void wmfw_v2_coeff_block_size_exceeds_block(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + __le32 *alg_data, *coeff; + + /* Create alg info block with a coefficient */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", "de"); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &mock_coeff_template); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (__force __le32 *)region->data; + + /* Sanity check we're pointing at the alg header */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data[0]), cs_dsp_wmfw_err_test_mock_algs[0].id); + + /* Sanity check we're pointing at the coeff block */ + coeff = (__force __le32 *)&alg_data[4]; + KUNIT_ASSERT_EQ(test, le32_to_cpu(coeff[0]), mock_coeff_template.mem_type << 16); + + /* Add one to the block size */ + coeff[1] = cpu_to_le32(le32_to_cpu(coeff[1]) + 1); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + /* Make the block size garbage */ + coeff[1] = cpu_to_le32(0xffffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + coeff[1] = cpu_to_le32(0x7fffffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + coeff[1] = cpu_to_le32(0x80000000); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +/* V1 coeff name does not have NUL terminator */ +static void wmfw_v1_coeff_name_unterminated(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + struct wmfw_adsp_alg_data *alg_data; + struct wmfw_adsp_coeff_data *coeff; + struct cs_dsp_coeff_ctl *ctl; + + /* Create alg info block with a coefficient */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", "de"); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &mock_coeff_template); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (struct wmfw_adsp_alg_data *)region->data; + + /* Sanity check we're pointing at the alg header */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data->id), cs_dsp_wmfw_err_test_mock_algs[0].id); + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data->ncoeff), 1); + + coeff = (void *)alg_data->data; + + /* Write a string to the coeff name that overflows the array */ + memset(coeff->descr, 0, sizeof(coeff->descr)); + memset(coeff->name, 'A', sizeof(coeff->name)); + memset(coeff->descr, 'A', sizeof(coeff->descr) - 1); + + /* + * Sanity-check that a strlen would overflow coeff->name. + * FORTIFY_STRING obstructs testing what strlen() would actually + * return, so instead verify that a strnlen() returns + * sizeof(coeff->name[]), therefore it doesn't have a NUL. + */ + KUNIT_ASSERT_EQ(test, strnlen(coeff->name, sizeof(coeff->name)), + sizeof(coeff->name)); + + /* + * V1 controls do not have names, but cs_dsp parses the name + * field. It should load the file successfully and create the + * control. + * If FORTIFY_STRING is enabled it will detect a buffer overflow + * if cs_dsp string length walks past end of coeff name array. + */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + 0); + ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + KUNIT_ASSERT_NOT_NULL(test, ctl); + KUNIT_EXPECT_EQ(test, ctl->subname_len, 0); +} + +/* V2+ coefficient shortname exceeds length of coeff block */ +static void wmfw_v2_coeff_shortname_exceeds_block(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + __le32 *alg_data, *coeff; + + /* Create alg info block with a coefficient */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", "de"); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &mock_coeff_template); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (__force __le32 *)region->data; + + /* Sanity check we're pointing at the alg header */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data[0]), cs_dsp_wmfw_err_test_mock_algs[0].id); + + /* Sanity check we're pointing at the coeff block */ + coeff = (__force __le32 *)&alg_data[4]; + KUNIT_ASSERT_EQ(test, le32_to_cpu(coeff[0]), mock_coeff_template.mem_type << 16); + + /* Add one to the shortname length */ + coeff[2] = cpu_to_le32(le32_to_cpu(coeff[2]) + 1); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + /* Maximum shortname length */ + coeff[2] = cpu_to_le32(255); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +/* V2+ coefficient fullname exceeds length of coeff block */ +static void wmfw_v2_coeff_fullname_exceeds_block(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + __le32 *alg_data, *coeff, *fullname; + size_t shortlen; + + /* Create alg info block with a coefficient */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", "de"); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &mock_coeff_template); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (__force __le32 *)region->data; + + /* Sanity check we're pointing at the alg header */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data[0]), cs_dsp_wmfw_err_test_mock_algs[0].id); + + /* Sanity check we're pointing at the coeff block */ + coeff = (__force __le32 *)&alg_data[4]; + KUNIT_ASSERT_EQ(test, le32_to_cpu(coeff[0]), mock_coeff_template.mem_type << 16); + + /* Fullname follows the shortname rounded up to a __le32 boundary */ + shortlen = round_up(le32_to_cpu(coeff[2]) & 0xff, sizeof(__le32)); + fullname = &coeff[2] + (shortlen / sizeof(*coeff)); + + /* Fullname increases in blocks of __le32 so increase past the current __le32 */ + fullname[0] = cpu_to_le32(round_up(le32_to_cpu(fullname[0]) + 1, sizeof(__le32))); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + /* Maximum fullname length */ + fullname[0] = cpu_to_le32(255); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +/* V2+ coefficient description exceeds length of coeff block */ +static void wmfw_v2_coeff_description_exceeds_block(struct kunit *test) +{ + struct cs_dsp_test *priv = test->priv; + struct cs_dsp_test_local *local = priv->local; + struct firmware *wmfw; + struct wmfw_header *header; + struct wmfw_region *region; + __le32 *alg_data, *coeff, *fullname, *description; + size_t namelen; + + /* Create alg info block with a coefficient */ + cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, + cs_dsp_wmfw_err_test_mock_algs[0].id, + "abc", "de"); + cs_dsp_mock_wmfw_add_coeff_desc(local->wmfw_builder, &mock_coeff_template); + cs_dsp_mock_wmfw_end_alg_info_block(local->wmfw_builder); + + wmfw = cs_dsp_mock_wmfw_get_firmware(local->wmfw_builder); + + /* Sanity-check that the good wmfw loads ok */ + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "wmfw", NULL, NULL, "misc"), + 0); + cs_dsp_power_down(priv->dsp); + + header = (struct wmfw_header *)wmfw->data; + region = (struct wmfw_region *)&wmfw->data[le32_to_cpu(header->len)]; + alg_data = (__force __le32 *)region->data; + + /* Sanity check we're pointing at the alg header */ + KUNIT_ASSERT_EQ(test, le32_to_cpu(alg_data[0]), cs_dsp_wmfw_err_test_mock_algs[0].id); + + /* Sanity check we're pointing at the coeff block */ + coeff = (__force __le32 *)&alg_data[4]; + KUNIT_ASSERT_EQ(test, le32_to_cpu(coeff[0]), mock_coeff_template.mem_type << 16); + + /* Description follows the shortname and fullname rounded up to __le32 boundaries */ + namelen = round_up(le32_to_cpu(coeff[2]) & 0xff, sizeof(__le32)); + fullname = &coeff[2] + (namelen / sizeof(*coeff)); + namelen = round_up(le32_to_cpu(fullname[0]) & 0xff, sizeof(__le32)); + description = fullname + (namelen / sizeof(*fullname)); + + /* Description increases in blocks of __le32 so increase past the current __le32 */ + description[0] = cpu_to_le32(round_up(le32_to_cpu(fullname[0]) + 1, sizeof(__le32))); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); + + /* Maximum description length */ + fullname[0] = cpu_to_le32(0xffff); + KUNIT_EXPECT_EQ(test, + cs_dsp_power_up(priv->dsp, wmfw, "mock_wmfw", NULL, NULL, "misc"), + -EOVERFLOW); +} + +static void cs_dsp_wmfw_err_test_exit(struct kunit *test) +{ + /* + * Testing error conditions can produce a lot of log output + * from cs_dsp error messages, so rate limit the test cases. + */ + usleep_range(200, 500); +} + +static int cs_dsp_wmfw_err_test_common_init(struct kunit *test, struct cs_dsp *dsp, + int wmfw_version) +{ + struct cs_dsp_test *priv; + struct cs_dsp_test_local *local; + struct device *test_dev; + int ret; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + local = kunit_kzalloc(test, sizeof(struct cs_dsp_test_local), GFP_KERNEL); + if (!local) + return -ENOMEM; + + priv->test = test; + priv->dsp = dsp; + test->priv = priv; + priv->local = local; + local->wmfw_version = wmfw_version; + + /* Create dummy struct device */ + test_dev = kunit_device_register(test, "cs_dsp_test_drv"); + if (IS_ERR(test_dev)) + return PTR_ERR(test_dev); + + dsp->dev = get_device(test_dev); + if (!dsp->dev) + return -ENODEV; + + ret = kunit_add_action_or_reset(test, _put_device_wrapper, dsp->dev); + if (ret) + return ret; + + dev_set_drvdata(dsp->dev, priv); + + /* Allocate regmap */ + ret = cs_dsp_mock_regmap_init(priv); + if (ret) + return ret; + + /* + * There must always be a XM header with at least 1 algorithm, + * so create a dummy one and pre-populate XM so the wmfw doesn't + * have to contain an XM blob. + */ + local->xm_header = cs_dsp_create_mock_xm_header(priv, + cs_dsp_wmfw_err_test_mock_algs, + ARRAY_SIZE(cs_dsp_wmfw_err_test_mock_algs)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->xm_header); + cs_dsp_mock_xm_header_write_to_regmap(local->xm_header); + + local->wmfw_builder = cs_dsp_mock_wmfw_init(priv, local->wmfw_version); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->wmfw_builder); + + /* Init cs_dsp */ + dsp->client_ops = kunit_kzalloc(test, sizeof(*dsp->client_ops), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dsp->client_ops); + + switch (dsp->type) { + case WMFW_ADSP2: + ret = cs_dsp_adsp2_init(dsp); + break; + case WMFW_HALO: + ret = cs_dsp_halo_init(dsp); + break; + default: + KUNIT_FAIL(test, "Untested DSP type %d\n", dsp->type); + return -EINVAL; + } + + if (ret) + return ret; + + /* Automatically call cs_dsp_remove() when test case ends */ + return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); +} + +static int cs_dsp_wmfw_err_test_halo_init(struct kunit *test) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_HALO; + dsp->mem = cs_dsp_mock_halo_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_halo_dsp1_region_sizes); + dsp->base = cs_dsp_mock_halo_core_base; + dsp->base_sysinfo = cs_dsp_mock_halo_sysinfo_base; + + return cs_dsp_wmfw_err_test_common_init(test, dsp, 3); +} + +static int cs_dsp_wmfw_err_test_adsp2_32bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 1; + dsp->mem = cs_dsp_mock_adsp2_32bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_32bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_32bit_sysbase; + + return cs_dsp_wmfw_err_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_wmfw_err_test_adsp2_32bit_wmfw0_init(struct kunit *test) +{ + return cs_dsp_wmfw_err_test_adsp2_32bit_init(test, 0); +} + +static int cs_dsp_wmfw_err_test_adsp2_32bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_wmfw_err_test_adsp2_32bit_init(test, 1); +} + +static int cs_dsp_wmfw_err_test_adsp2_32bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_wmfw_err_test_adsp2_32bit_init(test, 2); +} + +static int cs_dsp_wmfw_err_test_adsp2_16bit_init(struct kunit *test, int wmfw_ver) +{ + struct cs_dsp *dsp; + + /* Fill in cs_dsp and initialize */ + dsp = kunit_kzalloc(test, sizeof(*dsp), GFP_KERNEL); + if (!dsp) + return -ENOMEM; + + dsp->num = 1; + dsp->type = WMFW_ADSP2; + dsp->rev = 0; + dsp->mem = cs_dsp_mock_adsp2_16bit_dsp1_regions; + dsp->num_mems = cs_dsp_mock_count_regions(cs_dsp_mock_adsp2_16bit_dsp1_region_sizes); + dsp->base = cs_dsp_mock_adsp2_16bit_sysbase; + + return cs_dsp_wmfw_err_test_common_init(test, dsp, wmfw_ver); +} + +static int cs_dsp_wmfw_err_test_adsp2_16bit_wmfw0_init(struct kunit *test) +{ + return cs_dsp_wmfw_err_test_adsp2_16bit_init(test, 0); +} + +static int cs_dsp_wmfw_err_test_adsp2_16bit_wmfw1_init(struct kunit *test) +{ + return cs_dsp_wmfw_err_test_adsp2_16bit_init(test, 1); +} + +static int cs_dsp_wmfw_err_test_adsp2_16bit_wmfw2_init(struct kunit *test) +{ + return cs_dsp_wmfw_err_test_adsp2_16bit_init(test, 2); +} + +static void cs_dsp_wmfw_err_block_types_desc(const struct cs_dsp_wmfw_test_param *param, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "block_type:%#x", param->block_type); +} + +static const struct cs_dsp_wmfw_test_param wmfw_valid_block_types_adsp2_cases[] = { + { .block_type = WMFW_INFO_TEXT }, + { .block_type = WMFW_ADSP2_PM }, + { .block_type = WMFW_ADSP2_YM }, +}; + +KUNIT_ARRAY_PARAM(wmfw_valid_block_types_adsp2, + wmfw_valid_block_types_adsp2_cases, + cs_dsp_wmfw_err_block_types_desc); + +static const struct cs_dsp_wmfw_test_param wmfw_valid_block_types_halo_cases[] = { + { .block_type = WMFW_INFO_TEXT }, + { .block_type = WMFW_HALO_PM_PACKED }, + { .block_type = WMFW_ADSP2_YM }, +}; + +KUNIT_ARRAY_PARAM(wmfw_valid_block_types_halo, + wmfw_valid_block_types_halo_cases, + cs_dsp_wmfw_err_block_types_desc); + +static const struct cs_dsp_wmfw_test_param wmfw_invalid_block_types_cases[] = { + { .block_type = 0x33 }, + { .block_type = 0xf5 }, + { .block_type = 0xc0 }, +}; + +KUNIT_ARRAY_PARAM(wmfw_invalid_block_types, + wmfw_invalid_block_types_cases, + cs_dsp_wmfw_err_block_types_desc); + +static struct kunit_case cs_dsp_wmfw_err_test_cases_v0[] = { + KUNIT_CASE(wmfw_load_with_unknown_blocks), + KUNIT_CASE(wmfw_err_wrong_magic), + KUNIT_CASE(wmfw_err_too_short_for_header), + KUNIT_CASE(wmfw_err_bad_header_length), + KUNIT_CASE(wmfw_err_bad_core_type), + + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_valid_block_types_adsp2_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_payload, wmfw_valid_block_types_adsp2_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + KUNIT_CASE_PARAM(wmfw_block_payload_len_garbage, wmfw_valid_block_types_adsp2_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_wmfw_err_test_cases_v1[] = { + KUNIT_CASE(wmfw_load_with_unknown_blocks), + KUNIT_CASE(wmfw_err_wrong_magic), + KUNIT_CASE(wmfw_err_too_short_for_header), + KUNIT_CASE(wmfw_err_bad_header_length), + KUNIT_CASE(wmfw_err_bad_core_type), + + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_valid_block_types_adsp2_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_payload, wmfw_valid_block_types_adsp2_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + KUNIT_CASE_PARAM(wmfw_block_payload_len_garbage, wmfw_valid_block_types_adsp2_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + + KUNIT_CASE(wmfw_too_short_for_alg_header), + KUNIT_CASE(wmfw_v1_alg_name_unterminated), + KUNIT_CASE(wmfw_v1_coeff_count_exceeds_block), + KUNIT_CASE(wmfw_v1_coeff_name_unterminated), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_wmfw_err_test_cases_v2[] = { + KUNIT_CASE(wmfw_load_with_unknown_blocks), + KUNIT_CASE(wmfw_err_wrong_magic), + KUNIT_CASE(wmfw_err_too_short_for_header), + KUNIT_CASE(wmfw_err_bad_header_length), + KUNIT_CASE(wmfw_err_bad_core_type), + + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_valid_block_types_adsp2_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_payload, wmfw_valid_block_types_adsp2_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + KUNIT_CASE_PARAM(wmfw_block_payload_len_garbage, wmfw_valid_block_types_adsp2_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + + KUNIT_CASE(wmfw_too_short_for_alg_header), + KUNIT_CASE(wmfw_v2_alg_name_exceeds_block), + KUNIT_CASE(wmfw_v2_alg_description_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_count_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_block_size_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_shortname_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_fullname_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_description_exceeds_block), + + { } /* terminator */ +}; + +static struct kunit_case cs_dsp_wmfw_err_test_cases_v3[] = { + KUNIT_CASE(wmfw_load_with_unknown_blocks), + KUNIT_CASE(wmfw_err_wrong_magic), + KUNIT_CASE(wmfw_err_too_short_for_header), + KUNIT_CASE(wmfw_err_bad_header_length), + KUNIT_CASE(wmfw_err_bad_core_type), + + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_valid_block_types_halo_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_payload, wmfw_valid_block_types_halo_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + KUNIT_CASE_PARAM(wmfw_block_payload_len_garbage, wmfw_valid_block_types_halo_gen_params), + KUNIT_CASE_PARAM(wmfw_too_short_for_block_header, wmfw_invalid_block_types_gen_params), + + KUNIT_CASE(wmfw_too_short_for_alg_header), + KUNIT_CASE(wmfw_v2_alg_name_exceeds_block), + KUNIT_CASE(wmfw_v2_alg_description_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_count_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_block_size_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_shortname_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_fullname_exceeds_block), + KUNIT_CASE(wmfw_v2_coeff_description_exceeds_block), + + { } /* terminator */ +}; + +static struct kunit_suite cs_dsp_wmfw_err_test_halo = { + .name = "cs_dsp_wmfwV3_err_halo", + .init = cs_dsp_wmfw_err_test_halo_init, + .exit = cs_dsp_wmfw_err_test_exit, + .test_cases = cs_dsp_wmfw_err_test_cases_v3, +}; + +static struct kunit_suite cs_dsp_wmfw_err_test_adsp2_32bit_wmfw0 = { + .name = "cs_dsp_wmfwV0_err_adsp2_32bit", + .init = cs_dsp_wmfw_err_test_adsp2_32bit_wmfw0_init, + .exit = cs_dsp_wmfw_err_test_exit, + .test_cases = cs_dsp_wmfw_err_test_cases_v0, +}; + +static struct kunit_suite cs_dsp_wmfw_err_test_adsp2_32bit_wmfw1 = { + .name = "cs_dsp_wmfwV1_err_adsp2_32bit", + .init = cs_dsp_wmfw_err_test_adsp2_32bit_wmfw1_init, + .exit = cs_dsp_wmfw_err_test_exit, + .test_cases = cs_dsp_wmfw_err_test_cases_v1, +}; + +static struct kunit_suite cs_dsp_wmfw_err_test_adsp2_32bit_wmfw2 = { + .name = "cs_dsp_wmfwV2_err_adsp2_32bit", + .init = cs_dsp_wmfw_err_test_adsp2_32bit_wmfw2_init, + .exit = cs_dsp_wmfw_err_test_exit, + .test_cases = cs_dsp_wmfw_err_test_cases_v2, +}; + +static struct kunit_suite cs_dsp_wmfw_err_test_adsp2_16bit_wmfw0 = { + .name = "cs_dsp_wmfwV0_err_adsp2_16bit", + .init = cs_dsp_wmfw_err_test_adsp2_16bit_wmfw0_init, + .exit = cs_dsp_wmfw_err_test_exit, + .test_cases = cs_dsp_wmfw_err_test_cases_v0, +}; + +static struct kunit_suite cs_dsp_wmfw_err_test_adsp2_16bit_wmfw1 = { + .name = "cs_dsp_wmfwV1_err_adsp2_16bit", + .init = cs_dsp_wmfw_err_test_adsp2_16bit_wmfw1_init, + .exit = cs_dsp_wmfw_err_test_exit, + .test_cases = cs_dsp_wmfw_err_test_cases_v1, +}; + +static struct kunit_suite cs_dsp_wmfw_err_test_adsp2_16bit_wmfw2 = { + .name = "cs_dsp_wmfwV2_err_adsp2_16bit", + .init = cs_dsp_wmfw_err_test_adsp2_16bit_wmfw2_init, + .exit = cs_dsp_wmfw_err_test_exit, + .test_cases = cs_dsp_wmfw_err_test_cases_v2, +}; + +kunit_test_suites(&cs_dsp_wmfw_err_test_halo, + &cs_dsp_wmfw_err_test_adsp2_32bit_wmfw0, + &cs_dsp_wmfw_err_test_adsp2_32bit_wmfw1, + &cs_dsp_wmfw_err_test_adsp2_32bit_wmfw2, + &cs_dsp_wmfw_err_test_adsp2_16bit_wmfw0, + &cs_dsp_wmfw_err_test_adsp2_16bit_wmfw1, + &cs_dsp_wmfw_err_test_adsp2_16bit_wmfw2); diff --git a/drivers/firmware/cirrus/test/cs_dsp_tests.c b/drivers/firmware/cirrus/test/cs_dsp_tests.c new file mode 100644 index 000000000000..7b829a03ca52 --- /dev/null +++ b/drivers/firmware/cirrus/test/cs_dsp_tests.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// Utility module for cs_dsp KUnit testing. +// +// Copyright (C) 2024 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include + +MODULE_DESCRIPTION("KUnit tests for Cirrus Logic DSP driver"); +MODULE_AUTHOR("Richard Fitzgerald "); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS("FW_CS_DSP"); +MODULE_IMPORT_NS("FW_CS_DSP_KUNIT_TEST_UTILS"); diff --git a/drivers/firmware/efi/dev-path-parser.c b/drivers/firmware/efi/dev-path-parser.c index 937be269fee8..13ea141c0def 100644 --- a/drivers/firmware/efi/dev-path-parser.c +++ b/drivers/firmware/efi/dev-path-parser.c @@ -47,9 +47,9 @@ static long __init parse_acpi_path(const struct efi_dev_path *node, return 0; } -static int __init match_pci_dev(struct device *dev, void *data) +static int __init match_pci_dev(struct device *dev, const void *data) { - unsigned int devfn = *(unsigned int *)data; + unsigned int devfn = *(const unsigned int *)data; return dev_is_pci(dev) && to_pci_dev(dev)->devfn == devfn; } diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 60c64b81d2c3..8296bf985d1d 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -148,9 +148,6 @@ static ssize_t systab_show(struct kobject *kobj, if (efi.smbios != EFI_INVALID_TABLE_ADDR) str += sprintf(str, "SMBIOS=0x%lx\n", efi.smbios); - if (IS_ENABLED(CONFIG_X86)) - str = efi_systab_show_arch(str); - return str - buf; } diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index ed4e8ddbe76a..1141cd06011f 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -11,7 +11,7 @@ cflags-y := $(KBUILD_CFLAGS) cflags-$(CONFIG_X86_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small -cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ \ +cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ -std=gnu11 \ -fPIC -fno-strict-aliasing -mno-red-zone \ -mno-mmx -mno-sse -fshort-wchar \ -Wno-pointer-sign \ diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index c0c81ca4237e..fd6dc790c5a8 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -47,9 +47,10 @@ bool __pure __efi_soft_reserve_enabled(void) */ efi_status_t efi_parse_options(char const *cmdline) { - size_t len; + char *buf __free(efi_pool) = NULL; efi_status_t status; - char *str, *buf; + size_t len; + char *str; if (!cmdline) return EFI_SUCCESS; @@ -102,7 +103,6 @@ efi_status_t efi_parse_options(char const *cmdline) efi_parse_option_graphics(val + strlen("efifb:")); } } - efi_bs_call(free_pool, buf); return EFI_SUCCESS; } @@ -250,7 +250,7 @@ static efi_status_t efi_measure_tagged_event(unsigned long load_addr, u64, const union efistub_event *); struct { u32 hash_log_extend_event; } mixed_mode; } method; - struct efistub_measured_event *evt; + struct efistub_measured_event *evt __free(efi_pool) = NULL; int size = struct_size(evt, tagged_event.tagged_event_data, events[event].event_data_len); efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID; @@ -312,7 +312,6 @@ static efi_status_t efi_measure_tagged_event(unsigned long load_addr, status = efi_fn_call(&method, hash_log_extend_event, protocol, 0, load_addr, load_size, &evt->event_data); - efi_bs_call(free_pool, evt); if (status == EFI_SUCCESS) return EFI_SUCCESS; diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c index 382b54f40603..874f63b4a383 100644 --- a/drivers/firmware/efi/libstub/efi-stub.c +++ b/drivers/firmware/efi/libstub/efi-stub.c @@ -10,6 +10,7 @@ */ #include +#include #include #include "efistub.h" @@ -53,25 +54,16 @@ void __weak free_screen_info(struct screen_info *si) static struct screen_info *setup_graphics(void) { - efi_guid_t gop_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID; - efi_status_t status; - unsigned long size; - void **gop_handle = NULL; - struct screen_info *si = NULL; + struct screen_info *si, tmp = {}; - size = 0; - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - &gop_proto, NULL, &size, gop_handle); - if (status == EFI_BUFFER_TOO_SMALL) { - si = alloc_screen_info(); - if (!si) - return NULL; - status = efi_setup_gop(si, &gop_proto, size); - if (status != EFI_SUCCESS) { - free_screen_info(si); - return NULL; - } - } + if (efi_setup_gop(&tmp) != EFI_SUCCESS) + return NULL; + + si = alloc_screen_info(); + if (!si) + return NULL; + + *si = tmp; return si; } @@ -112,8 +104,8 @@ static u32 get_supported_rt_services(void) efi_status_t efi_handle_cmdline(efi_loaded_image_t *image, char **cmdline_ptr) { + char *cmdline __free(efi_pool) = NULL; efi_status_t status; - char *cmdline; /* * Get the command line from EFI, using the LOADED_IMAGE @@ -128,25 +120,24 @@ efi_status_t efi_handle_cmdline(efi_loaded_image_t *image, char **cmdline_ptr) if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { status = efi_parse_options(cmdline); - if (status != EFI_SUCCESS) - goto fail_free_cmdline; + if (status != EFI_SUCCESS) { + efi_err("Failed to parse EFI load options\n"); + return status; + } } if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) || IS_ENABLED(CONFIG_CMDLINE_FORCE) || cmdline[0] == 0) { status = efi_parse_options(CONFIG_CMDLINE); - if (status != EFI_SUCCESS) - goto fail_free_cmdline; + if (status != EFI_SUCCESS) { + efi_err("Failed to parse built-in command line\n"); + return status; + } } - *cmdline_ptr = cmdline; + *cmdline_ptr = no_free_ptr(cmdline); return EFI_SUCCESS; - -fail_free_cmdline: - efi_err("Failed to parse options\n"); - efi_bs_call(free_pool, cmdline); - return status; } efi_status_t efi_stub_common(efi_handle_t handle, diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 76e44c185f29..d96d4494070d 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -4,6 +4,7 @@ #define _DRIVERS_FIRMWARE_EFI_EFISTUB_H #include +#include #include #include #include @@ -122,11 +123,10 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, #define efi_get_handle_num(size) \ ((size) / (efi_is_native() ? sizeof(efi_handle_t) : sizeof(u32))) -#define for_each_efi_handle(handle, array, size, i) \ - for (i = 0; \ - i < efi_get_handle_num(size) && \ - ((handle = efi_get_handle_at((array), i)) || true); \ - i++) +#define for_each_efi_handle(handle, array, num) \ + for (int __i = 0; __i < (num) && \ + ((handle = efi_get_handle_at((array), __i)) || true); \ + __i++) static inline void efi_set_u64_split(u64 data, u32 *lo, u32 *hi) @@ -171,7 +171,7 @@ void efi_set_u64_split(u64 data, u32 *lo, u32 *hi) * the EFI memory map. Other related structures, e.g. x86 e820ext, need * to factor in this headroom requirement as well. */ -#define EFI_MMAP_NR_SLACK_SLOTS 8 +#define EFI_MMAP_NR_SLACK_SLOTS 32 typedef struct efi_generic_dev_path efi_device_path_protocol_t; @@ -314,7 +314,9 @@ union efi_boot_services { void *close_protocol; void *open_protocol_information; void *protocols_per_handle; - void *locate_handle_buffer; + efi_status_t (__efiapi *locate_handle_buffer)(int, efi_guid_t *, + void *, unsigned long *, + efi_handle_t **); efi_status_t (__efiapi *locate_protocol)(efi_guid_t *, void *, void **); efi_status_t (__efiapi *install_multiple_protocol_interfaces)(efi_handle_t *, ...); @@ -1053,6 +1055,7 @@ void efi_puts(const char *str); __printf(1, 2) int efi_printk(char const *fmt, ...); void efi_free(unsigned long size, unsigned long addr); +DEFINE_FREE(efi_pool, void *, if (_T) efi_bs_call(free_pool, _T)); void efi_apply_loadoptions_quirk(const void **load_options, u32 *load_options_size); @@ -1082,8 +1085,7 @@ efi_status_t efi_parse_options(char const *cmdline); void efi_parse_option_graphics(char *option); -efi_status_t efi_setup_gop(struct screen_info *si, efi_guid_t *proto, - unsigned long size); +efi_status_t efi_setup_gop(struct screen_info *si); efi_status_t handle_cmdline_files(efi_loaded_image_t *image, const efi_char16_t *optstr, diff --git a/drivers/firmware/efi/libstub/gop.c b/drivers/firmware/efi/libstub/gop.c index ea5da307d542..3785fb4986b4 100644 --- a/drivers/firmware/efi/libstub/gop.c +++ b/drivers/firmware/efi/libstub/gop.c @@ -133,13 +133,11 @@ void efi_parse_option_graphics(char *option) static u32 choose_mode_modenum(efi_graphics_output_protocol_t *gop) { - efi_status_t status; - + efi_graphics_output_mode_info_t *info __free(efi_pool) = NULL; efi_graphics_output_protocol_mode_t *mode; - efi_graphics_output_mode_info_t *info; unsigned long info_size; - u32 max_mode, cur_mode; + efi_status_t status; int pf; mode = efi_table_attr(gop, mode); @@ -154,17 +152,13 @@ static u32 choose_mode_modenum(efi_graphics_output_protocol_t *gop) return cur_mode; } - status = efi_call_proto(gop, query_mode, cmdline.mode, - &info_size, &info); + status = efi_call_proto(gop, query_mode, cmdline.mode, &info_size, &info); if (status != EFI_SUCCESS) { efi_err("Couldn't get mode information\n"); return cur_mode; } pf = info->pixel_format; - - efi_bs_call(free_pool, info); - if (pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX) { efi_err("Invalid PixelFormat\n"); return cur_mode; @@ -173,6 +167,28 @@ static u32 choose_mode_modenum(efi_graphics_output_protocol_t *gop) return cmdline.mode; } +static u32 choose_mode(efi_graphics_output_protocol_t *gop, + bool (*match)(const efi_graphics_output_mode_info_t *, u32, void *), + void *ctx) +{ + efi_graphics_output_protocol_mode_t *mode = efi_table_attr(gop, mode); + u32 max_mode = efi_table_attr(mode, max_mode); + + for (u32 m = 0; m < max_mode; m++) { + efi_graphics_output_mode_info_t *info __free(efi_pool) = NULL; + unsigned long info_size; + efi_status_t status; + + status = efi_call_proto(gop, query_mode, m, &info_size, &info); + if (status != EFI_SUCCESS) + continue; + + if (match(info, m, ctx)) + return m; + } + return (unsigned long)ctx; +} + static u8 pixel_bpp(int pixel_format, efi_pixel_bitmask_t pixel_info) { if (pixel_format == PIXEL_BIT_MASK) { @@ -185,192 +201,117 @@ static u8 pixel_bpp(int pixel_format, efi_pixel_bitmask_t pixel_info) return 32; } +static bool match_res(const efi_graphics_output_mode_info_t *info, u32 mode, void *ctx) +{ + efi_pixel_bitmask_t pi = info->pixel_information; + int pf = info->pixel_format; + + if (pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX) + return false; + + return cmdline.res.width == info->horizontal_resolution && + cmdline.res.height == info->vertical_resolution && + (cmdline.res.format < 0 || cmdline.res.format == pf) && + (!cmdline.res.depth || cmdline.res.depth == pixel_bpp(pf, pi)); +} + static u32 choose_mode_res(efi_graphics_output_protocol_t *gop) { - efi_status_t status; + efi_graphics_output_protocol_mode_t *mode = efi_table_attr(gop, mode); + unsigned long cur_mode = efi_table_attr(mode, mode); - efi_graphics_output_protocol_mode_t *mode; - efi_graphics_output_mode_info_t *info; - unsigned long info_size; - - u32 max_mode, cur_mode; - int pf; - efi_pixel_bitmask_t pi; - u32 m, w, h; - - mode = efi_table_attr(gop, mode); - - cur_mode = efi_table_attr(mode, mode); - info = efi_table_attr(mode, info); - pf = info->pixel_format; - pi = info->pixel_information; - w = info->horizontal_resolution; - h = info->vertical_resolution; - - if (w == cmdline.res.width && h == cmdline.res.height && - (cmdline.res.format < 0 || cmdline.res.format == pf) && - (!cmdline.res.depth || cmdline.res.depth == pixel_bpp(pf, pi))) + if (match_res(efi_table_attr(mode, info), cur_mode, NULL)) return cur_mode; - max_mode = efi_table_attr(mode, max_mode); + return choose_mode(gop, match_res, (void *)cur_mode); +} - for (m = 0; m < max_mode; m++) { - if (m == cur_mode) - continue; +struct match { + u32 mode; + u32 area; + u8 depth; +}; - status = efi_call_proto(gop, query_mode, m, - &info_size, &info); - if (status != EFI_SUCCESS) - continue; +static bool match_auto(const efi_graphics_output_mode_info_t *info, u32 mode, void *ctx) +{ + u32 area = info->horizontal_resolution * info->vertical_resolution; + efi_pixel_bitmask_t pi = info->pixel_information; + int pf = info->pixel_format; + u8 depth = pixel_bpp(pf, pi); + struct match *m = ctx; - pf = info->pixel_format; - pi = info->pixel_information; - w = info->horizontal_resolution; - h = info->vertical_resolution; + if (pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX) + return false; - efi_bs_call(free_pool, info); + if (area > m->area || (area == m->area && depth > m->depth)) + *m = (struct match){ mode, area, depth }; - if (pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX) - continue; - if (w == cmdline.res.width && h == cmdline.res.height && - (cmdline.res.format < 0 || cmdline.res.format == pf) && - (!cmdline.res.depth || cmdline.res.depth == pixel_bpp(pf, pi))) - return m; - } - - efi_err("Couldn't find requested mode\n"); - - return cur_mode; + return false; } static u32 choose_mode_auto(efi_graphics_output_protocol_t *gop) { - efi_status_t status; + struct match match = {}; - efi_graphics_output_protocol_mode_t *mode; - efi_graphics_output_mode_info_t *info; - unsigned long info_size; + choose_mode(gop, match_auto, &match); - u32 max_mode, cur_mode, best_mode, area; - u8 depth; - int pf; - efi_pixel_bitmask_t pi; - u32 m, w, h, a; - u8 d; + return match.mode; +} - mode = efi_table_attr(gop, mode); +static bool match_list(const efi_graphics_output_mode_info_t *info, u32 mode, void *ctx) +{ + efi_pixel_bitmask_t pi = info->pixel_information; + u32 cur_mode = (unsigned long)ctx; + int pf = info->pixel_format; + const char *dstr; + u8 depth = 0; + bool valid; - cur_mode = efi_table_attr(mode, mode); - max_mode = efi_table_attr(mode, max_mode); + valid = !(pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX); - info = efi_table_attr(mode, info); - - pf = info->pixel_format; - pi = info->pixel_information; - w = info->horizontal_resolution; - h = info->vertical_resolution; - - best_mode = cur_mode; - area = w * h; - depth = pixel_bpp(pf, pi); - - for (m = 0; m < max_mode; m++) { - if (m == cur_mode) - continue; - - status = efi_call_proto(gop, query_mode, m, - &info_size, &info); - if (status != EFI_SUCCESS) - continue; - - pf = info->pixel_format; - pi = info->pixel_information; - w = info->horizontal_resolution; - h = info->vertical_resolution; - - efi_bs_call(free_pool, info); - - if (pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX) - continue; - a = w * h; - if (a < area) - continue; - d = pixel_bpp(pf, pi); - if (a > area || d > depth) { - best_mode = m; - area = a; - depth = d; - } + switch (pf) { + case PIXEL_RGB_RESERVED_8BIT_PER_COLOR: + dstr = "rgb"; + break; + case PIXEL_BGR_RESERVED_8BIT_PER_COLOR: + dstr = "bgr"; + break; + case PIXEL_BIT_MASK: + dstr = ""; + depth = pixel_bpp(pf, pi); + break; + case PIXEL_BLT_ONLY: + dstr = "blt"; + break; + default: + dstr = "xxx"; + break; } - return best_mode; + efi_printk("Mode %3u %c%c: Resolution %ux%u-%s%.0hhu\n", + mode, + (mode == cur_mode) ? '*' : ' ', + !valid ? '-' : ' ', + info->horizontal_resolution, + info->vertical_resolution, + dstr, depth); + + return false; } static u32 choose_mode_list(efi_graphics_output_protocol_t *gop) { - efi_status_t status; - - efi_graphics_output_protocol_mode_t *mode; - efi_graphics_output_mode_info_t *info; - unsigned long info_size; - - u32 max_mode, cur_mode; - int pf; - efi_pixel_bitmask_t pi; - u32 m, w, h; - u8 d; - const char *dstr; - bool valid; + efi_graphics_output_protocol_mode_t *mode = efi_table_attr(gop, mode); + unsigned long cur_mode = efi_table_attr(mode, mode); + u32 max_mode = efi_table_attr(mode, max_mode); efi_input_key_t key; - - mode = efi_table_attr(gop, mode); - - cur_mode = efi_table_attr(mode, mode); - max_mode = efi_table_attr(mode, max_mode); + efi_status_t status; efi_printk("Available graphics modes are 0-%u\n", max_mode-1); efi_puts(" * = current mode\n" " - = unusable mode\n"); - for (m = 0; m < max_mode; m++) { - status = efi_call_proto(gop, query_mode, m, - &info_size, &info); - if (status != EFI_SUCCESS) - continue; - pf = info->pixel_format; - pi = info->pixel_information; - w = info->horizontal_resolution; - h = info->vertical_resolution; - - efi_bs_call(free_pool, info); - - valid = !(pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX); - d = 0; - switch (pf) { - case PIXEL_RGB_RESERVED_8BIT_PER_COLOR: - dstr = "rgb"; - break; - case PIXEL_BGR_RESERVED_8BIT_PER_COLOR: - dstr = "bgr"; - break; - case PIXEL_BIT_MASK: - dstr = ""; - d = pixel_bpp(pf, pi); - break; - case PIXEL_BLT_ONLY: - dstr = "blt"; - break; - default: - dstr = "xxx"; - break; - } - - efi_printk("Mode %3u %c%c: Resolution %ux%u-%s%.0hhu\n", - m, - m == cur_mode ? '*' : ' ', - !valid ? '-' : ' ', - w, h, dstr, d); - } + choose_mode(gop, match_list, (void *)cur_mode); efi_puts("\nPress any key to continue (or wait 10 seconds)\n"); status = efi_wait_for_key(10 * EFI_USEC_PER_SEC, &key); @@ -461,26 +402,25 @@ setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, } } -static efi_graphics_output_protocol_t * -find_gop(efi_guid_t *proto, unsigned long size, void **handles) +static efi_graphics_output_protocol_t *find_gop(unsigned long num, + const efi_handle_t handles[]) { efi_graphics_output_protocol_t *first_gop; efi_handle_t h; - int i; first_gop = NULL; - for_each_efi_handle(h, handles, size, i) { + for_each_efi_handle(h, handles, num) { efi_status_t status; efi_graphics_output_protocol_t *gop; efi_graphics_output_protocol_mode_t *mode; efi_graphics_output_mode_info_t *info; - - efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; void *dummy = NULL; - status = efi_bs_call(handle_protocol, h, proto, (void **)&gop); + status = efi_bs_call(handle_protocol, h, + &EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID, + (void **)&gop); if (status != EFI_SUCCESS) continue; @@ -500,7 +440,8 @@ find_gop(efi_guid_t *proto, unsigned long size, void **handles) * Once we've found a GOP supporting ConOut, * don't bother looking any further. */ - status = efi_bs_call(handle_protocol, h, &conout_proto, &dummy); + status = efi_bs_call(handle_protocol, h, + &EFI_CONSOLE_OUT_DEVICE_GUID, &dummy); if (status == EFI_SUCCESS) return gop; @@ -511,16 +452,22 @@ find_gop(efi_guid_t *proto, unsigned long size, void **handles) return first_gop; } -static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, - unsigned long size, void **handles) +efi_status_t efi_setup_gop(struct screen_info *si) { - efi_graphics_output_protocol_t *gop; + efi_handle_t *handles __free(efi_pool) = NULL; efi_graphics_output_protocol_mode_t *mode; efi_graphics_output_mode_info_t *info; + efi_graphics_output_protocol_t *gop; + efi_status_t status; + unsigned long num; - gop = find_gop(proto, size, handles); + status = efi_bs_call(locate_handle_buffer, EFI_LOCATE_BY_PROTOCOL, + &EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID, NULL, &num, + &handles); + if (status != EFI_SUCCESS) + return status; - /* Did we find any GOPs? */ + gop = find_gop(num, handles); if (!gop) return EFI_NOT_FOUND; @@ -552,29 +499,3 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, return EFI_SUCCESS; } - -/* - * See if we have Graphics Output Protocol - */ -efi_status_t efi_setup_gop(struct screen_info *si, efi_guid_t *proto, - unsigned long size) -{ - efi_status_t status; - void **gop_handle = NULL; - - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, - (void **)&gop_handle); - if (status != EFI_SUCCESS) - return status; - - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, proto, NULL, - &size, gop_handle); - if (status != EFI_SUCCESS) - goto free_handle; - - status = setup_gop(si, proto, size, gop_handle); - -free_handle: - efi_bs_call(free_pool, gop_handle); - return status; -} diff --git a/drivers/firmware/efi/libstub/kaslr.c b/drivers/firmware/efi/libstub/kaslr.c index 6318c40bda38..4bc963e999eb 100644 --- a/drivers/firmware/efi/libstub/kaslr.c +++ b/drivers/firmware/efi/libstub/kaslr.c @@ -57,7 +57,7 @@ u32 efi_kaslr_get_phys_seed(efi_handle_t image_handle) */ static bool check_image_region(u64 base, u64 size) { - struct efi_boot_memmap *map; + struct efi_boot_memmap *map __free(efi_pool) = NULL; efi_status_t status; bool ret = false; int map_offset; @@ -80,8 +80,6 @@ static bool check_image_region(u64 base, u64 size) } } - efi_bs_call(free_pool, map); - return ret; } diff --git a/drivers/firmware/efi/libstub/mem.c b/drivers/firmware/efi/libstub/mem.c index 4f1fa302234d..9c82259eea81 100644 --- a/drivers/firmware/efi/libstub/mem.c +++ b/drivers/firmware/efi/libstub/mem.c @@ -20,10 +20,10 @@ efi_status_t efi_get_memory_map(struct efi_boot_memmap **map, bool install_cfg_tbl) { + struct efi_boot_memmap tmp, *m __free(efi_pool) = NULL; int memtype = install_cfg_tbl ? EFI_ACPI_RECLAIM_MEMORY : EFI_LOADER_DATA; efi_guid_t tbl_guid = LINUX_EFI_BOOT_MEMMAP_GUID; - struct efi_boot_memmap *m, tmp; efi_status_t status; unsigned long size; @@ -48,24 +48,20 @@ efi_status_t efi_get_memory_map(struct efi_boot_memmap **map, */ status = efi_bs_call(install_configuration_table, &tbl_guid, m); if (status != EFI_SUCCESS) - goto free_map; + return status; } m->buff_size = m->map_size = size; status = efi_bs_call(get_memory_map, &m->map_size, m->map, &m->map_key, &m->desc_size, &m->desc_ver); - if (status != EFI_SUCCESS) - goto uninstall_table; + if (status != EFI_SUCCESS) { + if (install_cfg_tbl) + efi_bs_call(install_configuration_table, &tbl_guid, NULL); + return status; + } - *map = m; + *map = no_free_ptr(m); return EFI_SUCCESS; - -uninstall_table: - if (install_cfg_tbl) - efi_bs_call(install_configuration_table, &tbl_guid, NULL); -free_map: - efi_bs_call(free_pool, m); - return status; } /** diff --git a/drivers/firmware/efi/libstub/pci.c b/drivers/firmware/efi/libstub/pci.c index 99fb25d2bcf5..1dccf77958d3 100644 --- a/drivers/firmware/efi/libstub/pci.c +++ b/drivers/firmware/efi/libstub/pci.c @@ -16,37 +16,20 @@ void efi_pci_disable_bridge_busmaster(void) { efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - unsigned long pci_handle_size = 0; - efi_handle_t *pci_handle = NULL; + efi_handle_t *pci_handle __free(efi_pool) = NULL; + unsigned long pci_handle_num; efi_handle_t handle; efi_status_t status; u16 class, command; - int i; - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, &pci_proto, - NULL, &pci_handle_size, NULL); - - if (status != EFI_BUFFER_TOO_SMALL) { - if (status != EFI_SUCCESS && status != EFI_NOT_FOUND) - efi_err("Failed to locate PCI I/O handles'\n"); + status = efi_bs_call(locate_handle_buffer, EFI_LOCATE_BY_PROTOCOL, + &pci_proto, NULL, &pci_handle_num, &pci_handle); + if (status != EFI_SUCCESS) { + efi_err("Failed to locate PCI I/O handles\n"); return; } - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, pci_handle_size, - (void **)&pci_handle); - if (status != EFI_SUCCESS) { - efi_err("Failed to allocate memory for 'pci_handle'\n"); - return; - } - - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, &pci_proto, - NULL, &pci_handle_size, pci_handle); - if (status != EFI_SUCCESS) { - efi_err("Failed to locate PCI I/O handles'\n"); - goto free_handle; - } - - for_each_efi_handle(handle, pci_handle, pci_handle_size, i) { + for_each_efi_handle(handle, pci_handle, pci_handle_num) { efi_pci_io_protocol_t *pci; unsigned long segment_nr, bus_nr, device_nr, func_nr; @@ -82,7 +65,7 @@ void efi_pci_disable_bridge_busmaster(void) efi_bs_call(disconnect_controller, handle, NULL, NULL); } - for_each_efi_handle(handle, pci_handle, pci_handle_size, i) { + for_each_efi_handle(handle, pci_handle, pci_handle_num) { efi_pci_io_protocol_t *pci; status = efi_bs_call(handle_protocol, handle, &pci_proto, @@ -108,7 +91,4 @@ void efi_pci_disable_bridge_busmaster(void) if (status != EFI_SUCCESS) efi_err("Failed to disable PCI busmastering\n"); } - -free_handle: - efi_bs_call(free_pool, pci_handle); } diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index c41e7b2091cd..e5872e38d9a4 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -59,9 +59,9 @@ efi_status_t efi_random_alloc(unsigned long size, unsigned long alloc_min, unsigned long alloc_max) { + struct efi_boot_memmap *map __free(efi_pool) = NULL; unsigned long total_slots = 0, target_slot; unsigned long total_mirrored_slots = 0; - struct efi_boot_memmap *map; efi_status_t status; int map_offset; @@ -130,7 +130,5 @@ efi_status_t efi_random_alloc(unsigned long size, break; } - efi_bs_call(free_pool, map); - return status; } diff --git a/drivers/firmware/efi/libstub/relocate.c b/drivers/firmware/efi/libstub/relocate.c index d694bcfa1074..99b45d1cd624 100644 --- a/drivers/firmware/efi/libstub/relocate.c +++ b/drivers/firmware/efi/libstub/relocate.c @@ -23,14 +23,14 @@ efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, unsigned long *addr, unsigned long min) { - struct efi_boot_memmap *map; + struct efi_boot_memmap *map __free(efi_pool) = NULL; efi_status_t status; unsigned long nr_pages; int i; status = efi_get_memory_map(&map, false); if (status != EFI_SUCCESS) - goto fail; + return status; /* * Enforce minimum alignment that EFI or Linux requires when @@ -79,11 +79,9 @@ efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, } if (i == map->map_size / map->desc_size) - status = EFI_NOT_FOUND; + return EFI_NOT_FOUND; - efi_bs_call(free_pool, map); -fail: - return status; + return EFI_SUCCESS; } /** diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 188c8000d245..863910e9eefc 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -42,7 +42,7 @@ union sev_memory_acceptance_protocol { static efi_status_t preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) { - struct pci_setup_rom *rom = NULL; + struct pci_setup_rom *rom __free(efi_pool) = NULL; efi_status_t status; unsigned long size; uint64_t romsize; @@ -75,14 +75,13 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) rom->data.len = size - sizeof(struct setup_data); rom->data.next = 0; rom->pcilen = romsize; - *__rom = rom; status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16, PCI_VENDOR_ID, 1, &rom->vendor); if (status != EFI_SUCCESS) { efi_err("Failed to read rom->vendor\n"); - goto free_struct; + return status; } status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16, @@ -90,21 +89,18 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) if (status != EFI_SUCCESS) { efi_err("Failed to read rom->devid\n"); - goto free_struct; + return status; } status = efi_call_proto(pci, get_location, &rom->segment, &rom->bus, &rom->device, &rom->function); if (status != EFI_SUCCESS) - goto free_struct; + return status; memcpy(rom->romdata, romimage, romsize); - return status; - -free_struct: - efi_bs_call(free_pool, rom); - return status; + *__rom = no_free_ptr(rom); + return EFI_SUCCESS; } /* @@ -119,38 +115,23 @@ free_struct: static void setup_efi_pci(struct boot_params *params) { efi_status_t status; - void **pci_handle = NULL; + efi_handle_t *pci_handle __free(efi_pool) = NULL; efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - unsigned long size = 0; struct setup_data *data; + unsigned long num; efi_handle_t h; - int i; - - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - &pci_proto, NULL, &size, pci_handle); - - if (status == EFI_BUFFER_TOO_SMALL) { - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, - (void **)&pci_handle); - - if (status != EFI_SUCCESS) { - efi_err("Failed to allocate memory for 'pci_handle'\n"); - return; - } - - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - &pci_proto, NULL, &size, pci_handle); - } + status = efi_bs_call(locate_handle_buffer, EFI_LOCATE_BY_PROTOCOL, + &pci_proto, NULL, &num, &pci_handle); if (status != EFI_SUCCESS) - goto free_handle; + return; data = (struct setup_data *)(unsigned long)params->hdr.setup_data; while (data && data->next) data = (struct setup_data *)(unsigned long)data->next; - for_each_efi_handle(h, pci_handle, size, i) { + for_each_efi_handle(h, pci_handle, num) { efi_pci_io_protocol_t *pci = NULL; struct pci_setup_rom *rom; @@ -170,9 +151,6 @@ static void setup_efi_pci(struct boot_params *params) data = (struct setup_data *)rom; } - -free_handle: - efi_bs_call(free_pool, pci_handle); } static void retrieve_apple_device_properties(struct boot_params *boot_params) @@ -405,116 +383,13 @@ static void setup_quirks(struct boot_params *boot_params) } } -/* - * See if we have Universal Graphics Adapter (UGA) protocol - */ -static efi_status_t -setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) -{ - efi_status_t status; - u32 width, height; - void **uga_handle = NULL; - efi_uga_draw_protocol_t *uga = NULL, *first_uga; - efi_handle_t handle; - int i; - - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, - (void **)&uga_handle); - if (status != EFI_SUCCESS) - return status; - - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - uga_proto, NULL, &size, uga_handle); - if (status != EFI_SUCCESS) - goto free_handle; - - height = 0; - width = 0; - - first_uga = NULL; - for_each_efi_handle(handle, uga_handle, size, i) { - efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; - u32 w, h, depth, refresh; - void *pciio; - - status = efi_bs_call(handle_protocol, handle, uga_proto, - (void **)&uga); - if (status != EFI_SUCCESS) - continue; - - pciio = NULL; - efi_bs_call(handle_protocol, handle, &pciio_proto, &pciio); - - status = efi_call_proto(uga, get_mode, &w, &h, &depth, &refresh); - if (status == EFI_SUCCESS && (!first_uga || pciio)) { - width = w; - height = h; - - /* - * Once we've found a UGA supporting PCIIO, - * don't bother looking any further. - */ - if (pciio) - break; - - first_uga = uga; - } - } - - if (!width && !height) - goto free_handle; - - /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; - - si->lfb_depth = 32; - si->lfb_width = width; - si->lfb_height = height; - - si->red_size = 8; - si->red_pos = 16; - si->green_size = 8; - si->green_pos = 8; - si->blue_size = 8; - si->blue_pos = 0; - si->rsvd_size = 8; - si->rsvd_pos = 24; - -free_handle: - efi_bs_call(free_pool, uga_handle); - - return status; -} - static void setup_graphics(struct boot_params *boot_params) { - efi_guid_t graphics_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID; - struct screen_info *si; - efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; - efi_status_t status; - unsigned long size; - void **gop_handle = NULL; - void **uga_handle = NULL; + struct screen_info *si = memset(&boot_params->screen_info, 0, sizeof(*si)); - si = &boot_params->screen_info; - memset(si, 0, sizeof(*si)); - - size = 0; - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - &graphics_proto, NULL, &size, gop_handle); - if (status == EFI_BUFFER_TOO_SMALL) - status = efi_setup_gop(si, &graphics_proto, size); - - if (status != EFI_SUCCESS) { - size = 0; - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - &uga_proto, NULL, &size, uga_handle); - if (status == EFI_BUFFER_TOO_SMALL) - setup_uga(si, &uga_proto, size); - } + efi_setup_gop(si); } - static void __noreturn efi_exit(efi_handle_t handle, efi_status_t status) { efi_bs_call(exit, handle, status, 0, NULL); @@ -737,7 +612,7 @@ static efi_status_t allocate_e820(struct boot_params *params, struct setup_data **e820ext, u32 *e820ext_size) { - struct efi_boot_memmap *map; + struct efi_boot_memmap *map __free(efi_pool) = NULL; efi_status_t status; __u32 nr_desc; @@ -751,13 +626,14 @@ static efi_status_t allocate_e820(struct boot_params *params, EFI_MMAP_NR_SLACK_SLOTS; status = alloc_e820ext(nr_e820ext, e820ext, e820ext_size); + if (status != EFI_SUCCESS) + return status; } - if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) && status == EFI_SUCCESS) - status = allocate_unaccepted_bitmap(nr_desc, map); + if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY)) + return allocate_unaccepted_bitmap(nr_desc, map); - efi_bs_call(free_pool, map); - return status; + return EFI_SUCCESS; } struct exit_boot_struct { diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c index cc807ed35aed..1e509595ac03 100644 --- a/drivers/firmware/efi/sysfb_efi.c +++ b/drivers/firmware/efi/sysfb_efi.c @@ -91,6 +91,7 @@ void efifb_setup_from_dmi(struct screen_info *si, const char *opt) _ret_; \ }) +#ifdef CONFIG_EFI static int __init efifb_set_system(const struct dmi_system_id *id) { struct efifb_dmi_info *info = id->driver_data; @@ -346,7 +347,6 @@ static const struct fwnode_operations efifb_fwnode_ops = { .add_links = efifb_add_links, }; -#ifdef CONFIG_EFI static struct fwnode_handle efifb_fwnode; __init void sysfb_apply_efi_quirks(void) diff --git a/drivers/firmware/google/cbmem.c b/drivers/firmware/google/cbmem.c index 66042160b361..773d05078e0a 100644 --- a/drivers/firmware/google/cbmem.c +++ b/drivers/firmware/google/cbmem.c @@ -30,7 +30,7 @@ static struct cbmem_entry *to_cbmem_entry(struct kobject *kobj) } static ssize_t mem_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t pos, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct cbmem_entry *entry = to_cbmem_entry(kobj); @@ -40,7 +40,7 @@ static ssize_t mem_read(struct file *filp, struct kobject *kobj, } static ssize_t mem_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t pos, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct cbmem_entry *entry = to_cbmem_entry(kobj); @@ -53,7 +53,7 @@ static ssize_t mem_write(struct file *filp, struct kobject *kobj, memcpy(entry->mem_file_buf + pos, buf, count); return count; } -static BIN_ATTR_ADMIN_RW(mem, 0); +static const BIN_ATTR_ADMIN_RW(mem, 0); static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -79,14 +79,14 @@ static struct attribute *attrs[] = { NULL, }; -static struct bin_attribute *bin_attrs[] = { +static const struct bin_attribute *const bin_attrs[] = { &bin_attr_mem, NULL, }; static const struct attribute_group cbmem_entry_group = { .attrs = attrs, - .bin_attrs = bin_attrs, + .bin_attrs_new = bin_attrs, }; static const struct attribute_group *dev_groups[] = { diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c index 24e666d5c3d1..e8fb00dcaf65 100644 --- a/drivers/firmware/google/gsmi.c +++ b/drivers/firmware/google/gsmi.c @@ -488,7 +488,7 @@ static const struct efivar_operations efivar_ops = { #endif /* CONFIG_EFI */ static ssize_t eventlog_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct gsmi_set_eventlog_param param = { @@ -528,9 +528,9 @@ static ssize_t eventlog_write(struct file *filp, struct kobject *kobj, } -static struct bin_attribute eventlog_bin_attr = { +static const struct bin_attribute eventlog_bin_attr = { .attr = {.name = "append_to_eventlog", .mode = 0200}, - .write = eventlog_write, + .write_new = eventlog_write, }; static ssize_t gsmi_clear_eventlog_store(struct kobject *kobj, diff --git a/drivers/firmware/google/memconsole.c b/drivers/firmware/google/memconsole.c index b9d99fe1ff0f..d957af6f9349 100644 --- a/drivers/firmware/google/memconsole.c +++ b/drivers/firmware/google/memconsole.c @@ -14,7 +14,7 @@ #include "memconsole.h" static ssize_t memconsole_read(struct file *filp, struct kobject *kobp, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { ssize_t (*memconsole_read_func)(char *, loff_t, size_t); @@ -28,7 +28,7 @@ static ssize_t memconsole_read(struct file *filp, struct kobject *kobp, static struct bin_attribute memconsole_bin_attr = { .attr = {.name = "log", .mode = 0444}, - .read = memconsole_read, + .read_new = memconsole_read, }; void memconsole_setup(ssize_t (*read_func)(char *, loff_t, size_t)) diff --git a/drivers/firmware/google/vpd.c b/drivers/firmware/google/vpd.c index 1749529f63d4..254ac6545d68 100644 --- a/drivers/firmware/google/vpd.c +++ b/drivers/firmware/google/vpd.c @@ -56,7 +56,7 @@ static struct vpd_section ro_vpd; static struct vpd_section rw_vpd; static ssize_t vpd_attrib_read(struct file *filp, struct kobject *kobp, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct vpd_attrib_info *info = bin_attr->private; @@ -121,7 +121,7 @@ static int vpd_section_attrib_add(const u8 *key, u32 key_len, info->bin_attr.attr.name = info->key; info->bin_attr.attr.mode = 0444; info->bin_attr.size = value_len; - info->bin_attr.read = vpd_attrib_read; + info->bin_attr.read_new = vpd_attrib_read; info->bin_attr.private = info; info->value = value; @@ -156,7 +156,7 @@ static void vpd_section_attrib_destroy(struct vpd_section *sec) } static ssize_t vpd_section_read(struct file *filp, struct kobject *kobp, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct vpd_section *sec = bin_attr->private; @@ -201,7 +201,7 @@ static int vpd_section_init(const char *name, struct vpd_section *sec, sec->bin_attr.attr.name = sec->raw_name; sec->bin_attr.attr.mode = 0444; sec->bin_attr.size = size; - sec->bin_attr.read = vpd_section_read; + sec->bin_attr.read_new = vpd_section_read; sec->bin_attr.private = sec; err = sysfs_create_bin_file(vpd_kobj, &sec->bin_attr); diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig index 477d3f32d99a..907cd149c40a 100644 --- a/drivers/firmware/imx/Kconfig +++ b/drivers/firmware/imx/Kconfig @@ -25,7 +25,6 @@ config IMX_SCU config IMX_SCMI_MISC_DRV tristate "IMX SCMI MISC Protocol driver" - depends on IMX_SCMI_MISC_EXT || COMPILE_TEST default y if ARCH_MXC help The System Controller Management Interface firmware (SCMI FW) is diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c index 38a03698cec9..e194f7acb2a9 100644 --- a/drivers/firmware/microchip/mpfs-auto-update.c +++ b/drivers/firmware/microchip/mpfs-auto-update.c @@ -402,10 +402,10 @@ static int mpfs_auto_update_available(struct mpfs_auto_update_priv *priv) return -EIO; /* - * Bit 5 of byte 1 is "UL_Auto Update" & if it is set, Auto Update is + * Bit 5 of byte 1 is "UL_IAP" & if it is set, Auto Update is * not possible. */ - if (response_msg[1] & AUTO_UPDATE_FEATURE_ENABLED) + if ((((u8 *)response_msg)[1] & AUTO_UPDATE_FEATURE_ENABLED)) return -EPERM; return 0; diff --git a/drivers/firmware/qcom/qcom_scm-smc.c b/drivers/firmware/qcom/qcom_scm-smc.c index 2b4c2826f572..574930729ddd 100644 --- a/drivers/firmware/qcom/qcom_scm-smc.c +++ b/drivers/firmware/qcom/qcom_scm-smc.c @@ -152,7 +152,6 @@ int __scm_smc_call(struct device *dev, const struct qcom_scm_desc *desc, enum qcom_scm_convention qcom_convention, struct qcom_scm_res *res, bool atomic) { - struct qcom_tzmem_pool *mempool = qcom_scm_get_tzmem_pool(); int arglen = desc->arginfo & 0xf; int i, ret; void *args_virt __free(qcom_tzmem) = NULL; @@ -173,6 +172,11 @@ int __scm_smc_call(struct device *dev, const struct qcom_scm_desc *desc, smc.args[i + SCM_SMC_FIRST_REG_IDX] = desc->args[i]; if (unlikely(arglen > SCM_SMC_N_REG_ARGS)) { + struct qcom_tzmem_pool *mempool = qcom_scm_get_tzmem_pool(); + + if (!mempool) + return -EINVAL; + args_virt = qcom_tzmem_alloc(mempool, SCM_SMC_N_EXT_ARGS * sizeof(u64), flag); diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c index 72bf87ddcd96..f0569bb9411f 100644 --- a/drivers/firmware/qcom/qcom_scm.c +++ b/drivers/firmware/qcom/qcom_scm.c @@ -217,7 +217,10 @@ static DEFINE_SPINLOCK(scm_query_lock); struct qcom_tzmem_pool *qcom_scm_get_tzmem_pool(void) { - return __scm ? __scm->mempool : NULL; + if (!qcom_scm_is_available()) + return NULL; + + return __scm->mempool; } static enum qcom_scm_convention __get_convention(void) @@ -1279,6 +1282,220 @@ int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size, } EXPORT_SYMBOL_GPL(qcom_scm_ice_set_key); +bool qcom_scm_has_wrapped_key_support(void) +{ + return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_ES, + QCOM_SCM_ES_DERIVE_SW_SECRET) && + __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_ES, + QCOM_SCM_ES_GENERATE_ICE_KEY) && + __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_ES, + QCOM_SCM_ES_PREPARE_ICE_KEY) && + __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_ES, + QCOM_SCM_ES_IMPORT_ICE_KEY); +} +EXPORT_SYMBOL_GPL(qcom_scm_has_wrapped_key_support); + +/** + * qcom_scm_derive_sw_secret() - Derive software secret from wrapped key + * @eph_key: an ephemerally-wrapped key + * @eph_key_size: size of @eph_key in bytes + * @sw_secret: output buffer for the software secret + * @sw_secret_size: size of the software secret to derive in bytes + * + * Derive a software secret from an ephemerally-wrapped key for software crypto + * operations. This is done by calling into the secure execution environment, + * which then calls into the hardware to unwrap and derive the secret. + * + * For more information on sw_secret, see the "Hardware-wrapped keys" section of + * Documentation/block/inline-encryption.rst. + * + * Return: 0 on success; -errno on failure. + */ +int qcom_scm_derive_sw_secret(const u8 *eph_key, size_t eph_key_size, + u8 *sw_secret, size_t sw_secret_size) +{ + struct qcom_scm_desc desc = { + .svc = QCOM_SCM_SVC_ES, + .cmd = QCOM_SCM_ES_DERIVE_SW_SECRET, + .arginfo = QCOM_SCM_ARGS(4, QCOM_SCM_RW, QCOM_SCM_VAL, + QCOM_SCM_RW, QCOM_SCM_VAL), + .owner = ARM_SMCCC_OWNER_SIP, + }; + int ret; + + void *eph_key_buf __free(qcom_tzmem) = qcom_tzmem_alloc(__scm->mempool, + eph_key_size, + GFP_KERNEL); + if (!eph_key_buf) + return -ENOMEM; + + void *sw_secret_buf __free(qcom_tzmem) = qcom_tzmem_alloc(__scm->mempool, + sw_secret_size, + GFP_KERNEL); + if (!sw_secret_buf) + return -ENOMEM; + + memcpy(eph_key_buf, eph_key, eph_key_size); + desc.args[0] = qcom_tzmem_to_phys(eph_key_buf); + desc.args[1] = eph_key_size; + desc.args[2] = qcom_tzmem_to_phys(sw_secret_buf); + desc.args[3] = sw_secret_size; + + ret = qcom_scm_call(__scm->dev, &desc, NULL); + if (!ret) + memcpy(sw_secret, sw_secret_buf, sw_secret_size); + + memzero_explicit(eph_key_buf, eph_key_size); + memzero_explicit(sw_secret_buf, sw_secret_size); + return ret; +} +EXPORT_SYMBOL_GPL(qcom_scm_derive_sw_secret); + +/** + * qcom_scm_generate_ice_key() - Generate a wrapped key for storage encryption + * @lt_key: output buffer for the long-term wrapped key + * @lt_key_size: size of @lt_key in bytes. Must be the exact wrapped key size + * used by the SoC. + * + * Generate a key using the built-in HW module in the SoC. The resulting key is + * returned wrapped with the platform-specific Key Encryption Key. + * + * Return: 0 on success; -errno on failure. + */ +int qcom_scm_generate_ice_key(u8 *lt_key, size_t lt_key_size) +{ + struct qcom_scm_desc desc = { + .svc = QCOM_SCM_SVC_ES, + .cmd = QCOM_SCM_ES_GENERATE_ICE_KEY, + .arginfo = QCOM_SCM_ARGS(2, QCOM_SCM_RW, QCOM_SCM_VAL), + .owner = ARM_SMCCC_OWNER_SIP, + }; + int ret; + + void *lt_key_buf __free(qcom_tzmem) = qcom_tzmem_alloc(__scm->mempool, + lt_key_size, + GFP_KERNEL); + if (!lt_key_buf) + return -ENOMEM; + + desc.args[0] = qcom_tzmem_to_phys(lt_key_buf); + desc.args[1] = lt_key_size; + + ret = qcom_scm_call(__scm->dev, &desc, NULL); + if (!ret) + memcpy(lt_key, lt_key_buf, lt_key_size); + + memzero_explicit(lt_key_buf, lt_key_size); + return ret; +} +EXPORT_SYMBOL_GPL(qcom_scm_generate_ice_key); + +/** + * qcom_scm_prepare_ice_key() - Re-wrap a key with the per-boot ephemeral key + * @lt_key: a long-term wrapped key + * @lt_key_size: size of @lt_key in bytes + * @eph_key: output buffer for the ephemerally-wrapped key + * @eph_key_size: size of @eph_key in bytes. Must be the exact wrapped key size + * used by the SoC. + * + * Given a long-term wrapped key, re-wrap it with the per-boot ephemeral key for + * added protection. The resulting key will only be valid for the current boot. + * + * Return: 0 on success; -errno on failure. + */ +int qcom_scm_prepare_ice_key(const u8 *lt_key, size_t lt_key_size, + u8 *eph_key, size_t eph_key_size) +{ + struct qcom_scm_desc desc = { + .svc = QCOM_SCM_SVC_ES, + .cmd = QCOM_SCM_ES_PREPARE_ICE_KEY, + .arginfo = QCOM_SCM_ARGS(4, QCOM_SCM_RO, QCOM_SCM_VAL, + QCOM_SCM_RW, QCOM_SCM_VAL), + .owner = ARM_SMCCC_OWNER_SIP, + }; + int ret; + + void *lt_key_buf __free(qcom_tzmem) = qcom_tzmem_alloc(__scm->mempool, + lt_key_size, + GFP_KERNEL); + if (!lt_key_buf) + return -ENOMEM; + + void *eph_key_buf __free(qcom_tzmem) = qcom_tzmem_alloc(__scm->mempool, + eph_key_size, + GFP_KERNEL); + if (!eph_key_buf) + return -ENOMEM; + + memcpy(lt_key_buf, lt_key, lt_key_size); + desc.args[0] = qcom_tzmem_to_phys(lt_key_buf); + desc.args[1] = lt_key_size; + desc.args[2] = qcom_tzmem_to_phys(eph_key_buf); + desc.args[3] = eph_key_size; + + ret = qcom_scm_call(__scm->dev, &desc, NULL); + if (!ret) + memcpy(eph_key, eph_key_buf, eph_key_size); + + memzero_explicit(lt_key_buf, lt_key_size); + memzero_explicit(eph_key_buf, eph_key_size); + return ret; +} +EXPORT_SYMBOL_GPL(qcom_scm_prepare_ice_key); + +/** + * qcom_scm_import_ice_key() - Import key for storage encryption + * @raw_key: the raw key to import + * @raw_key_size: size of @raw_key in bytes + * @lt_key: output buffer for the long-term wrapped key + * @lt_key_size: size of @lt_key in bytes. Must be the exact wrapped key size + * used by the SoC. + * + * Import a raw key and return a long-term wrapped key. Uses the SoC's HWKM to + * wrap the raw key using the platform-specific Key Encryption Key. + * + * Return: 0 on success; -errno on failure. + */ +int qcom_scm_import_ice_key(const u8 *raw_key, size_t raw_key_size, + u8 *lt_key, size_t lt_key_size) +{ + struct qcom_scm_desc desc = { + .svc = QCOM_SCM_SVC_ES, + .cmd = QCOM_SCM_ES_IMPORT_ICE_KEY, + .arginfo = QCOM_SCM_ARGS(4, QCOM_SCM_RO, QCOM_SCM_VAL, + QCOM_SCM_RW, QCOM_SCM_VAL), + .owner = ARM_SMCCC_OWNER_SIP, + }; + int ret; + + void *raw_key_buf __free(qcom_tzmem) = qcom_tzmem_alloc(__scm->mempool, + raw_key_size, + GFP_KERNEL); + if (!raw_key_buf) + return -ENOMEM; + + void *lt_key_buf __free(qcom_tzmem) = qcom_tzmem_alloc(__scm->mempool, + lt_key_size, + GFP_KERNEL); + if (!lt_key_buf) + return -ENOMEM; + + memcpy(raw_key_buf, raw_key, raw_key_size); + desc.args[0] = qcom_tzmem_to_phys(raw_key_buf); + desc.args[1] = raw_key_size; + desc.args[2] = qcom_tzmem_to_phys(lt_key_buf); + desc.args[3] = lt_key_size; + + ret = qcom_scm_call(__scm->dev, &desc, NULL); + if (!ret) + memcpy(lt_key, lt_key_buf, lt_key_size); + + memzero_explicit(raw_key_buf, raw_key_size); + memzero_explicit(lt_key_buf, lt_key_size); + return ret; +} +EXPORT_SYMBOL_GPL(qcom_scm_import_ice_key); + /** * qcom_scm_hdcp_available() - Check if secure environment supports HDCP. * @@ -1768,18 +1985,23 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_send); + any potential issues with this, only allow validated machines for now. */ static const struct of_device_id qcom_scm_qseecom_allowlist[] __maybe_unused = { + { .compatible = "asus,vivobook-s15" }, { .compatible = "dell,xps13-9345" }, + { .compatible = "hp,omnibook-x14" }, + { .compatible = "huawei,gaokun3" }, { .compatible = "lenovo,flex-5g" }, { .compatible = "lenovo,thinkpad-t14s" }, { .compatible = "lenovo,thinkpad-x13s", }, { .compatible = "lenovo,yoga-slim7x" }, { .compatible = "microsoft,arcata", }, + { .compatible = "microsoft,blackrock" }, { .compatible = "microsoft,romulus13", }, { .compatible = "microsoft,romulus15", }, { .compatible = "qcom,sc8180x-primus" }, { .compatible = "qcom,x1e001de-devkit" }, { .compatible = "qcom,x1e80100-crd" }, { .compatible = "qcom,x1e80100-qcp" }, + { .compatible = "qcom,x1p42100-crd" }, { } }; @@ -1867,7 +2089,8 @@ static int qcom_scm_qseecom_init(struct qcom_scm *scm) */ bool qcom_scm_is_available(void) { - return !!READ_ONCE(__scm); + /* Paired with smp_store_release() in qcom_scm_probe */ + return !!smp_load_acquire(&__scm); } EXPORT_SYMBOL_GPL(qcom_scm_is_available); @@ -2024,18 +2247,22 @@ static int qcom_scm_probe(struct platform_device *pdev) if (ret) return ret; - /* Let all above stores be available after this */ + /* Paired with smp_load_acquire() in qcom_scm_is_available(). */ smp_store_release(&__scm, scm); irq = platform_get_irq_optional(pdev, 0); if (irq < 0) { - if (irq != -ENXIO) - return irq; + if (irq != -ENXIO) { + ret = irq; + goto err; + } } else { ret = devm_request_threaded_irq(__scm->dev, irq, NULL, qcom_scm_irq_handler, IRQF_ONESHOT, "qcom-scm", __scm); - if (ret < 0) - return dev_err_probe(scm->dev, ret, "Failed to request qcom-scm irq\n"); + if (ret < 0) { + dev_err_probe(scm->dev, ret, "Failed to request qcom-scm irq\n"); + goto err; + } } __get_convention(); @@ -2054,14 +2281,18 @@ static int qcom_scm_probe(struct platform_device *pdev) qcom_scm_disable_sdi(); ret = of_reserved_mem_device_init(__scm->dev); - if (ret && ret != -ENODEV) - return dev_err_probe(__scm->dev, ret, - "Failed to setup the reserved memory region for TZ mem\n"); + if (ret && ret != -ENODEV) { + dev_err_probe(__scm->dev, ret, + "Failed to setup the reserved memory region for TZ mem\n"); + goto err; + } ret = qcom_tzmem_enable(__scm->dev); - if (ret) - return dev_err_probe(__scm->dev, ret, - "Failed to enable the TrustZone memory allocator\n"); + if (ret) { + dev_err_probe(__scm->dev, ret, + "Failed to enable the TrustZone memory allocator\n"); + goto err; + } memset(&pool_config, 0, sizeof(pool_config)); pool_config.initial_size = 0; @@ -2069,9 +2300,11 @@ static int qcom_scm_probe(struct platform_device *pdev) pool_config.max_size = SZ_256K; __scm->mempool = devm_qcom_tzmem_pool_new(__scm->dev, &pool_config); - if (IS_ERR(__scm->mempool)) - return dev_err_probe(__scm->dev, PTR_ERR(__scm->mempool), - "Failed to create the SCM memory pool\n"); + if (IS_ERR(__scm->mempool)) { + dev_err_probe(__scm->dev, PTR_ERR(__scm->mempool), + "Failed to create the SCM memory pool\n"); + goto err; + } /* * Initialize the QSEECOM interface. @@ -2087,6 +2320,12 @@ static int qcom_scm_probe(struct platform_device *pdev) WARN(ret < 0, "failed to initialize qseecom: %d\n", ret); return 0; + +err: + /* Paired with smp_load_acquire() in qcom_scm_is_available(). */ + smp_store_release(&__scm, NULL); + + return ret; } static void qcom_scm_shutdown(struct platform_device *pdev) diff --git a/drivers/firmware/qcom/qcom_scm.h b/drivers/firmware/qcom/qcom_scm.h index e36b2f67607f..097369d38b84 100644 --- a/drivers/firmware/qcom/qcom_scm.h +++ b/drivers/firmware/qcom/qcom_scm.h @@ -128,6 +128,10 @@ struct qcom_tzmem_pool *qcom_scm_get_tzmem_pool(void); #define QCOM_SCM_SVC_ES 0x10 /* Enterprise Security */ #define QCOM_SCM_ES_INVALIDATE_ICE_KEY 0x03 #define QCOM_SCM_ES_CONFIG_SET_ICE_KEY 0x04 +#define QCOM_SCM_ES_DERIVE_SW_SECRET 0x07 +#define QCOM_SCM_ES_GENERATE_ICE_KEY 0x08 +#define QCOM_SCM_ES_PREPARE_ICE_KEY 0x09 +#define QCOM_SCM_ES_IMPORT_ICE_KEY 0x0a #define QCOM_SCM_SVC_HDCP 0x11 #define QCOM_SCM_HDCP_INVOKE 0x01 diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index c5c78b869561..3c52cb73237a 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -967,18 +967,15 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg) /* first client will create kernel thread */ if (!chan->ctrl->task) { chan->ctrl->task = - kthread_create_on_node(svc_normal_to_secure_thread, - (void *)chan->ctrl, - cpu_to_node(cpu), - "svc_smc_hvc_thread"); + kthread_run_on_cpu(svc_normal_to_secure_thread, + (void *)chan->ctrl, + cpu, "svc_smc_hvc_thread"); if (IS_ERR(chan->ctrl->task)) { dev_err(chan->ctrl->dev, "failed to create svc_smc_hvc_thread\n"); kfree(p_data); return -EINVAL; } - kthread_bind(chan->ctrl->task, cpu); - wake_up_process(chan->ctrl->task); } pr_debug("%s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__, diff --git a/drivers/fpga/dfl-afu-dma-region.c b/drivers/fpga/dfl-afu-dma-region.c index 02b60fde0430..5aa7b8884374 100644 --- a/drivers/fpga/dfl-afu-dma-region.c +++ b/drivers/fpga/dfl-afu-dma-region.c @@ -16,26 +16,26 @@ #include "dfl-afu.h" -void afu_dma_region_init(struct dfl_feature_platform_data *pdata) +void afu_dma_region_init(struct dfl_feature_dev_data *fdata) { - struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata); + struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata); afu->dma_regions = RB_ROOT; } /** * afu_dma_pin_pages - pin pages of given dma memory region - * @pdata: feature device platform data + * @fdata: feature dev data * @region: dma memory region to be pinned * * Pin all the pages of given dfl_afu_dma_region. * Return 0 for success or negative error code. */ -static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata, +static int afu_dma_pin_pages(struct dfl_feature_dev_data *fdata, struct dfl_afu_dma_region *region) { int npages = region->length >> PAGE_SHIFT; - struct device *dev = &pdata->dev->dev; + struct device *dev = &fdata->dev->dev; int ret, pinned; ret = account_locked_vm(current->mm, npages, true); @@ -73,17 +73,17 @@ unlock_vm: /** * afu_dma_unpin_pages - unpin pages of given dma memory region - * @pdata: feature device platform data + * @fdata: feature dev data * @region: dma memory region to be unpinned * * Unpin all the pages of given dfl_afu_dma_region. * Return 0 for success or negative error code. */ -static void afu_dma_unpin_pages(struct dfl_feature_platform_data *pdata, +static void afu_dma_unpin_pages(struct dfl_feature_dev_data *fdata, struct dfl_afu_dma_region *region) { long npages = region->length >> PAGE_SHIFT; - struct device *dev = &pdata->dev->dev; + struct device *dev = &fdata->dev->dev; unpin_user_pages(region->pages, npages); kfree(region->pages); @@ -133,20 +133,20 @@ static bool dma_region_check_iova(struct dfl_afu_dma_region *region, /** * afu_dma_region_add - add given dma region to rbtree - * @pdata: feature device platform data + * @fdata: feature dev data * @region: dma region to be added * * Return 0 for success, -EEXIST if dma region has already been added. * - * Needs to be called with pdata->lock heold. + * Needs to be called with fdata->lock held. */ -static int afu_dma_region_add(struct dfl_feature_platform_data *pdata, +static int afu_dma_region_add(struct dfl_feature_dev_data *fdata, struct dfl_afu_dma_region *region) { - struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata); + struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata); struct rb_node **new, *parent = NULL; - dev_dbg(&pdata->dev->dev, "add region (iova = %llx)\n", + dev_dbg(&fdata->dev->dev, "add region (iova = %llx)\n", (unsigned long long)region->iova); new = &afu->dma_regions.rb_node; @@ -177,50 +177,50 @@ static int afu_dma_region_add(struct dfl_feature_platform_data *pdata, /** * afu_dma_region_remove - remove given dma region from rbtree - * @pdata: feature device platform data + * @fdata: feature dev data * @region: dma region to be removed * - * Needs to be called with pdata->lock heold. + * Needs to be called with fdata->lock held. */ -static void afu_dma_region_remove(struct dfl_feature_platform_data *pdata, +static void afu_dma_region_remove(struct dfl_feature_dev_data *fdata, struct dfl_afu_dma_region *region) { struct dfl_afu *afu; - dev_dbg(&pdata->dev->dev, "del region (iova = %llx)\n", + dev_dbg(&fdata->dev->dev, "del region (iova = %llx)\n", (unsigned long long)region->iova); - afu = dfl_fpga_pdata_get_private(pdata); + afu = dfl_fpga_fdata_get_private(fdata); rb_erase(®ion->node, &afu->dma_regions); } /** * afu_dma_region_destroy - destroy all regions in rbtree - * @pdata: feature device platform data + * @fdata: feature dev data * - * Needs to be called with pdata->lock heold. + * Needs to be called with fdata->lock held. */ -void afu_dma_region_destroy(struct dfl_feature_platform_data *pdata) +void afu_dma_region_destroy(struct dfl_feature_dev_data *fdata) { - struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata); + struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata); struct rb_node *node = rb_first(&afu->dma_regions); struct dfl_afu_dma_region *region; while (node) { region = container_of(node, struct dfl_afu_dma_region, node); - dev_dbg(&pdata->dev->dev, "del region (iova = %llx)\n", + dev_dbg(&fdata->dev->dev, "del region (iova = %llx)\n", (unsigned long long)region->iova); rb_erase(node, &afu->dma_regions); if (region->iova) - dma_unmap_page(dfl_fpga_pdata_to_parent(pdata), + dma_unmap_page(dfl_fpga_fdata_to_parent(fdata), region->iova, region->length, DMA_BIDIRECTIONAL); if (region->pages) - afu_dma_unpin_pages(pdata, region); + afu_dma_unpin_pages(fdata, region); node = rb_next(node); kfree(region); @@ -229,7 +229,7 @@ void afu_dma_region_destroy(struct dfl_feature_platform_data *pdata) /** * afu_dma_region_find - find the dma region from rbtree based on iova and size - * @pdata: feature device platform data + * @fdata: feature dev data * @iova: address of the dma memory area * @size: size of the dma memory area * @@ -239,14 +239,14 @@ void afu_dma_region_destroy(struct dfl_feature_platform_data *pdata) * [@iova, @iova+size) * If nothing is matched returns NULL. * - * Needs to be called with pdata->lock held. + * Needs to be called with fdata->lock held. */ struct dfl_afu_dma_region * -afu_dma_region_find(struct dfl_feature_platform_data *pdata, u64 iova, u64 size) +afu_dma_region_find(struct dfl_feature_dev_data *fdata, u64 iova, u64 size) { - struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata); + struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata); struct rb_node *node = afu->dma_regions.rb_node; - struct device *dev = &pdata->dev->dev; + struct device *dev = &fdata->dev->dev; while (node) { struct dfl_afu_dma_region *region; @@ -276,20 +276,20 @@ afu_dma_region_find(struct dfl_feature_platform_data *pdata, u64 iova, u64 size) /** * afu_dma_region_find_iova - find the dma region from rbtree by iova - * @pdata: feature device platform data + * @fdata: feature dev data * @iova: address of the dma region * - * Needs to be called with pdata->lock held. + * Needs to be called with fdata->lock held. */ static struct dfl_afu_dma_region * -afu_dma_region_find_iova(struct dfl_feature_platform_data *pdata, u64 iova) +afu_dma_region_find_iova(struct dfl_feature_dev_data *fdata, u64 iova) { - return afu_dma_region_find(pdata, iova, 0); + return afu_dma_region_find(fdata, iova, 0); } /** * afu_dma_map_region - map memory region for dma - * @pdata: feature device platform data + * @fdata: feature dev data * @user_addr: address of the memory region * @length: size of the memory region * @iova: pointer of iova address @@ -298,9 +298,10 @@ afu_dma_region_find_iova(struct dfl_feature_platform_data *pdata, u64 iova) * of the memory region via @iova. * Return 0 for success, otherwise error code. */ -int afu_dma_map_region(struct dfl_feature_platform_data *pdata, +int afu_dma_map_region(struct dfl_feature_dev_data *fdata, u64 user_addr, u64 length, u64 *iova) { + struct device *dev = &fdata->dev->dev; struct dfl_afu_dma_region *region; int ret; @@ -323,47 +324,47 @@ int afu_dma_map_region(struct dfl_feature_platform_data *pdata, region->length = length; /* Pin the user memory region */ - ret = afu_dma_pin_pages(pdata, region); + ret = afu_dma_pin_pages(fdata, region); if (ret) { - dev_err(&pdata->dev->dev, "failed to pin memory region\n"); + dev_err(dev, "failed to pin memory region\n"); goto free_region; } /* Only accept continuous pages, return error else */ if (!afu_dma_check_continuous_pages(region)) { - dev_err(&pdata->dev->dev, "pages are not continuous\n"); + dev_err(dev, "pages are not continuous\n"); ret = -EINVAL; goto unpin_pages; } /* As pages are continuous then start to do DMA mapping */ - region->iova = dma_map_page(dfl_fpga_pdata_to_parent(pdata), + region->iova = dma_map_page(dfl_fpga_fdata_to_parent(fdata), region->pages[0], 0, region->length, DMA_BIDIRECTIONAL); - if (dma_mapping_error(dfl_fpga_pdata_to_parent(pdata), region->iova)) { - dev_err(&pdata->dev->dev, "failed to map for dma\n"); + if (dma_mapping_error(dfl_fpga_fdata_to_parent(fdata), region->iova)) { + dev_err(dev, "failed to map for dma\n"); ret = -EFAULT; goto unpin_pages; } *iova = region->iova; - mutex_lock(&pdata->lock); - ret = afu_dma_region_add(pdata, region); - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + ret = afu_dma_region_add(fdata, region); + mutex_unlock(&fdata->lock); if (ret) { - dev_err(&pdata->dev->dev, "failed to add dma region\n"); + dev_err(dev, "failed to add dma region\n"); goto unmap_dma; } return 0; unmap_dma: - dma_unmap_page(dfl_fpga_pdata_to_parent(pdata), + dma_unmap_page(dfl_fpga_fdata_to_parent(fdata), region->iova, region->length, DMA_BIDIRECTIONAL); unpin_pages: - afu_dma_unpin_pages(pdata, region); + afu_dma_unpin_pages(fdata, region); free_region: kfree(region); return ret; @@ -371,34 +372,34 @@ free_region: /** * afu_dma_unmap_region - unmap dma memory region - * @pdata: feature device platform data + * @fdata: feature dev data * @iova: dma address of the region * * Unmap dma memory region based on @iova. * Return 0 for success, otherwise error code. */ -int afu_dma_unmap_region(struct dfl_feature_platform_data *pdata, u64 iova) +int afu_dma_unmap_region(struct dfl_feature_dev_data *fdata, u64 iova) { struct dfl_afu_dma_region *region; - mutex_lock(&pdata->lock); - region = afu_dma_region_find_iova(pdata, iova); + mutex_lock(&fdata->lock); + region = afu_dma_region_find_iova(fdata, iova); if (!region) { - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return -EINVAL; } if (region->in_use) { - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return -EBUSY; } - afu_dma_region_remove(pdata, region); - mutex_unlock(&pdata->lock); + afu_dma_region_remove(fdata, region); + mutex_unlock(&fdata->lock); - dma_unmap_page(dfl_fpga_pdata_to_parent(pdata), + dma_unmap_page(dfl_fpga_fdata_to_parent(fdata), region->iova, region->length, DMA_BIDIRECTIONAL); - afu_dma_unpin_pages(pdata, region); + afu_dma_unpin_pages(fdata, region); kfree(region); return 0; diff --git a/drivers/fpga/dfl-afu-error.c b/drivers/fpga/dfl-afu-error.c index ab7be6217368..0f392d1f6d45 100644 --- a/drivers/fpga/dfl-afu-error.c +++ b/drivers/fpga/dfl-afu-error.c @@ -28,37 +28,36 @@ #define ERROR_MASK GENMASK_ULL(63, 0) /* mask or unmask port errors by the error mask register. */ -static void __afu_port_err_mask(struct device *dev, bool mask) +static void __afu_port_err_mask(struct dfl_feature_dev_data *fdata, bool mask) { void __iomem *base; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR); writeq(mask ? ERROR_MASK : 0, base + PORT_ERROR_MASK); } static void afu_port_err_mask(struct device *dev, bool mask) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); - mutex_lock(&pdata->lock); - __afu_port_err_mask(dev, mask); - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + __afu_port_err_mask(fdata, mask); + mutex_unlock(&fdata->lock); } /* clear port errors. */ static int afu_port_err_clear(struct device *dev, u64 err) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); - struct platform_device *pdev = to_platform_device(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base_err, *base_hdr; int enable_ret = 0, ret = -EBUSY; u64 v; - base_err = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR); - base_hdr = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base_err = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR); + base_hdr = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); /* * clear Port Errors @@ -80,12 +79,12 @@ static int afu_port_err_clear(struct device *dev, u64 err) } /* Halt Port by keeping Port in reset */ - ret = __afu_port_disable(pdev); + ret = __afu_port_disable(fdata); if (ret) goto done; /* Mask all errors */ - __afu_port_err_mask(dev, true); + __afu_port_err_mask(fdata, true); /* Clear errors if err input matches with current port errors.*/ v = readq(base_err + PORT_ERROR); @@ -102,28 +101,28 @@ static int afu_port_err_clear(struct device *dev, u64 err) } /* Clear mask */ - __afu_port_err_mask(dev, false); + __afu_port_err_mask(fdata, false); /* Enable the Port by clearing the reset */ - enable_ret = __afu_port_enable(pdev); + enable_ret = __afu_port_enable(fdata); done: - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return enable_ret ? enable_ret : ret; } static ssize_t errors_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 error; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); error = readq(base + PORT_ERROR); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)error); } @@ -146,15 +145,15 @@ static DEVICE_ATTR_RW(errors); static ssize_t first_error_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 error; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); error = readq(base + PORT_FIRST_ERROR); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)error); } @@ -164,16 +163,16 @@ static ssize_t first_malformed_req_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 req0, req1; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); req0 = readq(base + PORT_MALFORMED_REQ0); req1 = readq(base + PORT_MALFORMED_REQ1); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%016llx%016llx\n", (unsigned long long)req1, (unsigned long long)req0); @@ -191,12 +190,14 @@ static umode_t port_err_attrs_visible(struct kobject *kobj, struct attribute *attr, int n) { struct device *dev = kobj_to_dev(kobj); + struct dfl_feature_dev_data *fdata; + fdata = to_dfl_feature_dev_data(dev); /* * sysfs entries are visible only if related private feature is * enumerated. */ - if (!dfl_get_feature_by_id(dev, PORT_FEATURE_ID_ERROR)) + if (!dfl_get_feature_by_id(fdata, PORT_FEATURE_ID_ERROR)) return 0; return attr->mode; diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c index 2fd4f07ed081..3bf8e7338dbe 100644 --- a/drivers/fpga/dfl-afu-main.c +++ b/drivers/fpga/dfl-afu-main.c @@ -26,7 +26,7 @@ /** * __afu_port_enable - enable a port by clear reset - * @pdev: port platform device. + * @fdata: port feature dev data. * * Enable Port by clear the port soft reset bit, which is set by default. * The AFU is unable to respond to any MMIO access while in reset. @@ -35,18 +35,17 @@ * * The caller needs to hold lock for protection. */ -int __afu_port_enable(struct platform_device *pdev) +int __afu_port_enable(struct dfl_feature_dev_data *fdata) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); void __iomem *base; u64 v; - WARN_ON(!pdata->disable_count); + WARN_ON(!fdata->disable_count); - if (--pdata->disable_count != 0) + if (--fdata->disable_count != 0) return 0; - base = dfl_get_feature_ioaddr_by_id(&pdev->dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); /* Clear port soft reset */ v = readq(base + PORT_HDR_CTRL); @@ -60,7 +59,8 @@ int __afu_port_enable(struct platform_device *pdev) if (readq_poll_timeout(base + PORT_HDR_CTRL, v, !(v & PORT_CTRL_SFTRST_ACK), RST_POLL_INVL, RST_POLL_TIMEOUT)) { - dev_err(&pdev->dev, "timeout, failure to enable device\n"); + dev_err(fdata->dfl_cdev->parent, + "timeout, failure to enable device\n"); return -ETIMEDOUT; } @@ -69,22 +69,21 @@ int __afu_port_enable(struct platform_device *pdev) /** * __afu_port_disable - disable a port by hold reset - * @pdev: port platform device. + * @fdata: port feature dev data. * * Disable Port by setting the port soft reset bit, it puts the port into reset. * * The caller needs to hold lock for protection. */ -int __afu_port_disable(struct platform_device *pdev) +int __afu_port_disable(struct dfl_feature_dev_data *fdata) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); void __iomem *base; u64 v; - if (pdata->disable_count++ != 0) + if (fdata->disable_count++ != 0) return 0; - base = dfl_get_feature_ioaddr_by_id(&pdev->dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); /* Set port soft reset */ v = readq(base + PORT_HDR_CTRL); @@ -99,7 +98,8 @@ int __afu_port_disable(struct platform_device *pdev) if (readq_poll_timeout(base + PORT_HDR_CTRL, v, v & PORT_CTRL_SFTRST_ACK, RST_POLL_INVL, RST_POLL_TIMEOUT)) { - dev_err(&pdev->dev, "timeout, failure to disable device\n"); + dev_err(fdata->dfl_cdev->parent, + "timeout, failure to disable device\n"); return -ETIMEDOUT; } @@ -118,34 +118,34 @@ int __afu_port_disable(struct platform_device *pdev) * (disabled). Any attempts on MMIO access to AFU while in reset, will * result errors reported via port error reporting sub feature (if present). */ -static int __port_reset(struct platform_device *pdev) +static int __port_reset(struct dfl_feature_dev_data *fdata) { int ret; - ret = __afu_port_disable(pdev); + ret = __afu_port_disable(fdata); if (ret) return ret; - return __afu_port_enable(pdev); + return __afu_port_enable(fdata); } static int port_reset(struct platform_device *pdev) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); int ret; - mutex_lock(&pdata->lock); - ret = __port_reset(pdev); - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + ret = __port_reset(fdata); + mutex_unlock(&fdata->lock); return ret; } -static int port_get_id(struct platform_device *pdev) +static int port_get_id(struct dfl_feature_dev_data *fdata) { void __iomem *base; - base = dfl_get_feature_ioaddr_by_id(&pdev->dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); return FIELD_GET(PORT_CAP_PORT_NUM, readq(base + PORT_HDR_CAP)); } @@ -153,7 +153,8 @@ static int port_get_id(struct platform_device *pdev) static ssize_t id_show(struct device *dev, struct device_attribute *attr, char *buf) { - int id = port_get_id(to_platform_device(dev)); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); + int id = port_get_id(fdata); return scnprintf(buf, PAGE_SIZE, "%d\n", id); } @@ -162,15 +163,15 @@ static DEVICE_ATTR_RO(id); static ssize_t ltr_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); v = readq(base + PORT_HDR_CTRL); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "%x\n", (u8)FIELD_GET(PORT_CTRL_LATENCY, v)); } @@ -179,7 +180,7 @@ static ssize_t ltr_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; bool ltr; u64 v; @@ -187,14 +188,14 @@ ltr_store(struct device *dev, struct device_attribute *attr, if (kstrtobool(buf, <r)) return -EINVAL; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); v = readq(base + PORT_HDR_CTRL); v &= ~PORT_CTRL_LATENCY; v |= FIELD_PREP(PORT_CTRL_LATENCY, ltr ? 1 : 0); writeq(v, base + PORT_HDR_CTRL); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return count; } @@ -203,15 +204,15 @@ static DEVICE_ATTR_RW(ltr); static ssize_t ap1_event_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); v = readq(base + PORT_HDR_STS); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "%x\n", (u8)FIELD_GET(PORT_STS_AP1_EVT, v)); } @@ -220,18 +221,18 @@ static ssize_t ap1_event_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; bool clear; if (kstrtobool(buf, &clear) || !clear) return -EINVAL; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); writeq(PORT_STS_AP1_EVT, base + PORT_HDR_STS); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return count; } @@ -241,15 +242,15 @@ static ssize_t ap2_event_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); v = readq(base + PORT_HDR_STS); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "%x\n", (u8)FIELD_GET(PORT_STS_AP2_EVT, v)); } @@ -258,18 +259,18 @@ static ssize_t ap2_event_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; bool clear; if (kstrtobool(buf, &clear) || !clear) return -EINVAL; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); writeq(PORT_STS_AP2_EVT, base + PORT_HDR_STS); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return count; } @@ -278,15 +279,15 @@ static DEVICE_ATTR_RW(ap2_event); static ssize_t power_state_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); v = readq(base + PORT_HDR_STS); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%x\n", (u8)FIELD_GET(PORT_STS_PWR_STATE, v)); } @@ -296,18 +297,18 @@ static ssize_t userclk_freqcmd_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); u64 userclk_freq_cmd; void __iomem *base; if (kstrtou64(buf, 0, &userclk_freq_cmd)) return -EINVAL; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); writeq(userclk_freq_cmd, base + PORT_HDR_USRCLK_CMD0); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return count; } @@ -317,18 +318,18 @@ static ssize_t userclk_freqcntrcmd_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); u64 userclk_freqcntr_cmd; void __iomem *base; if (kstrtou64(buf, 0, &userclk_freqcntr_cmd)) return -EINVAL; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); writeq(userclk_freqcntr_cmd, base + PORT_HDR_USRCLK_CMD1); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return count; } @@ -338,15 +339,15 @@ static ssize_t userclk_freqsts_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); u64 userclk_freqsts; void __iomem *base; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); userclk_freqsts = readq(base + PORT_HDR_USRCLK_STS0); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)userclk_freqsts); } @@ -356,15 +357,15 @@ static ssize_t userclk_freqcntrsts_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); u64 userclk_freqcntrsts; void __iomem *base; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); userclk_freqcntrsts = readq(base + PORT_HDR_USRCLK_STS1); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)userclk_freqcntrsts); @@ -388,10 +389,12 @@ static umode_t port_hdr_attrs_visible(struct kobject *kobj, struct attribute *attr, int n) { struct device *dev = kobj_to_dev(kobj); + struct dfl_feature_dev_data *fdata; umode_t mode = attr->mode; void __iomem *base; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER); + fdata = to_dfl_feature_dev_data(dev); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER); if (dfl_feature_revision(base) > 0) { /* @@ -456,21 +459,21 @@ static const struct dfl_feature_ops port_hdr_ops = { static ssize_t afu_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 guidl, guidh; - base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_AFU); + base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_AFU); - mutex_lock(&pdata->lock); - if (pdata->disable_count) { - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + if (fdata->disable_count) { + mutex_unlock(&fdata->lock); return -EBUSY; } guidl = readq(base + GUID_L); guidh = readq(base + GUID_H); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return scnprintf(buf, PAGE_SIZE, "%016llx%016llx\n", guidh, guidl); } @@ -485,12 +488,14 @@ static umode_t port_afu_attrs_visible(struct kobject *kobj, struct attribute *attr, int n) { struct device *dev = kobj_to_dev(kobj); + struct dfl_feature_dev_data *fdata; + fdata = to_dfl_feature_dev_data(dev); /* * sysfs entries are visible only if related private feature is * enumerated. */ - if (!dfl_get_feature_by_id(dev, PORT_FEATURE_ID_AFU)) + if (!dfl_get_feature_by_id(fdata, PORT_FEATURE_ID_AFU)) return 0; return attr->mode; @@ -504,9 +509,10 @@ static const struct attribute_group port_afu_group = { static int port_afu_init(struct platform_device *pdev, struct dfl_feature *feature) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); struct resource *res = &pdev->resource[feature->resource_index]; - return afu_mmio_region_add(dev_get_platdata(&pdev->dev), + return afu_mmio_region_add(fdata, DFL_PORT_REGION_INDEX_AFU, resource_size(res), res->start, DFL_PORT_REGION_MMAP | DFL_PORT_REGION_READ | @@ -525,9 +531,10 @@ static const struct dfl_feature_ops port_afu_ops = { static int port_stp_init(struct platform_device *pdev, struct dfl_feature *feature) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); struct resource *res = &pdev->resource[feature->resource_index]; - return afu_mmio_region_add(dev_get_platdata(&pdev->dev), + return afu_mmio_region_add(fdata, DFL_PORT_REGION_INDEX_STP, resource_size(res), res->start, DFL_PORT_REGION_MMAP | DFL_PORT_REGION_READ | @@ -595,22 +602,18 @@ static struct dfl_feature_driver port_feature_drvs[] = { static int afu_open(struct inode *inode, struct file *filp) { - struct platform_device *fdev = dfl_fpga_inode_to_feature_dev(inode); - struct dfl_feature_platform_data *pdata; + struct dfl_feature_dev_data *fdata = dfl_fpga_inode_to_feature_dev_data(inode); + struct platform_device *fdev = fdata->dev; int ret; - pdata = dev_get_platdata(&fdev->dev); - if (WARN_ON(!pdata)) - return -ENODEV; - - mutex_lock(&pdata->lock); - ret = dfl_feature_dev_use_begin(pdata, filp->f_flags & O_EXCL); + mutex_lock(&fdata->lock); + ret = dfl_feature_dev_use_begin(fdata, filp->f_flags & O_EXCL); if (!ret) { dev_dbg(&fdev->dev, "Device File Opened %d Times\n", - dfl_feature_dev_use_count(pdata)); + dfl_feature_dev_use_count(fdata)); filp->private_data = fdev; } - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return ret; } @@ -618,29 +621,29 @@ static int afu_open(struct inode *inode, struct file *filp) static int afu_release(struct inode *inode, struct file *filp) { struct platform_device *pdev = filp->private_data; - struct dfl_feature_platform_data *pdata; + struct dfl_feature_dev_data *fdata; struct dfl_feature *feature; dev_dbg(&pdev->dev, "Device File Release\n"); - pdata = dev_get_platdata(&pdev->dev); + fdata = to_dfl_feature_dev_data(&pdev->dev); - mutex_lock(&pdata->lock); - dfl_feature_dev_use_end(pdata); + mutex_lock(&fdata->lock); + dfl_feature_dev_use_end(fdata); - if (!dfl_feature_dev_use_count(pdata)) { - dfl_fpga_dev_for_each_feature(pdata, feature) + if (!dfl_feature_dev_use_count(fdata)) { + dfl_fpga_dev_for_each_feature(fdata, feature) dfl_fpga_set_irq_triggers(feature, 0, feature->nr_irqs, NULL); - __port_reset(pdev); - afu_dma_region_destroy(pdata); + __port_reset(fdata); + afu_dma_region_destroy(fdata); } - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return 0; } -static long afu_ioctl_check_extension(struct dfl_feature_platform_data *pdata, +static long afu_ioctl_check_extension(struct dfl_feature_dev_data *fdata, unsigned long arg) { /* No extension support for now */ @@ -648,7 +651,7 @@ static long afu_ioctl_check_extension(struct dfl_feature_platform_data *pdata, } static long -afu_ioctl_get_info(struct dfl_feature_platform_data *pdata, void __user *arg) +afu_ioctl_get_info(struct dfl_feature_dev_data *fdata, void __user *arg) { struct dfl_fpga_port_info info; struct dfl_afu *afu; @@ -662,12 +665,12 @@ afu_ioctl_get_info(struct dfl_feature_platform_data *pdata, void __user *arg) if (info.argsz < minsz) return -EINVAL; - mutex_lock(&pdata->lock); - afu = dfl_fpga_pdata_get_private(pdata); + mutex_lock(&fdata->lock); + afu = dfl_fpga_fdata_get_private(fdata); info.flags = 0; info.num_regions = afu->num_regions; info.num_umsgs = afu->num_umsgs; - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; @@ -675,7 +678,7 @@ afu_ioctl_get_info(struct dfl_feature_platform_data *pdata, void __user *arg) return 0; } -static long afu_ioctl_get_region_info(struct dfl_feature_platform_data *pdata, +static long afu_ioctl_get_region_info(struct dfl_feature_dev_data *fdata, void __user *arg) { struct dfl_fpga_port_region_info rinfo; @@ -691,7 +694,7 @@ static long afu_ioctl_get_region_info(struct dfl_feature_platform_data *pdata, if (rinfo.argsz < minsz || rinfo.padding) return -EINVAL; - ret = afu_mmio_region_get_by_index(pdata, rinfo.index, ®ion); + ret = afu_mmio_region_get_by_index(fdata, rinfo.index, ®ion); if (ret) return ret; @@ -706,7 +709,7 @@ static long afu_ioctl_get_region_info(struct dfl_feature_platform_data *pdata, } static long -afu_ioctl_dma_map(struct dfl_feature_platform_data *pdata, void __user *arg) +afu_ioctl_dma_map(struct dfl_feature_dev_data *fdata, void __user *arg) { struct dfl_fpga_port_dma_map map; unsigned long minsz; @@ -720,16 +723,16 @@ afu_ioctl_dma_map(struct dfl_feature_platform_data *pdata, void __user *arg) if (map.argsz < minsz || map.flags) return -EINVAL; - ret = afu_dma_map_region(pdata, map.user_addr, map.length, &map.iova); + ret = afu_dma_map_region(fdata, map.user_addr, map.length, &map.iova); if (ret) return ret; if (copy_to_user(arg, &map, sizeof(map))) { - afu_dma_unmap_region(pdata, map.iova); + afu_dma_unmap_region(fdata, map.iova); return -EFAULT; } - dev_dbg(&pdata->dev->dev, "dma map: ua=%llx, len=%llx, iova=%llx\n", + dev_dbg(&fdata->dev->dev, "dma map: ua=%llx, len=%llx, iova=%llx\n", (unsigned long long)map.user_addr, (unsigned long long)map.length, (unsigned long long)map.iova); @@ -738,7 +741,7 @@ afu_ioctl_dma_map(struct dfl_feature_platform_data *pdata, void __user *arg) } static long -afu_ioctl_dma_unmap(struct dfl_feature_platform_data *pdata, void __user *arg) +afu_ioctl_dma_unmap(struct dfl_feature_dev_data *fdata, void __user *arg) { struct dfl_fpga_port_dma_unmap unmap; unsigned long minsz; @@ -751,33 +754,33 @@ afu_ioctl_dma_unmap(struct dfl_feature_platform_data *pdata, void __user *arg) if (unmap.argsz < minsz || unmap.flags) return -EINVAL; - return afu_dma_unmap_region(pdata, unmap.iova); + return afu_dma_unmap_region(fdata, unmap.iova); } static long afu_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct platform_device *pdev = filp->private_data; - struct dfl_feature_platform_data *pdata; + struct dfl_feature_dev_data *fdata; struct dfl_feature *f; long ret; dev_dbg(&pdev->dev, "%s cmd 0x%x\n", __func__, cmd); - pdata = dev_get_platdata(&pdev->dev); + fdata = to_dfl_feature_dev_data(&pdev->dev); switch (cmd) { case DFL_FPGA_GET_API_VERSION: return DFL_FPGA_API_VERSION; case DFL_FPGA_CHECK_EXTENSION: - return afu_ioctl_check_extension(pdata, arg); + return afu_ioctl_check_extension(fdata, arg); case DFL_FPGA_PORT_GET_INFO: - return afu_ioctl_get_info(pdata, (void __user *)arg); + return afu_ioctl_get_info(fdata, (void __user *)arg); case DFL_FPGA_PORT_GET_REGION_INFO: - return afu_ioctl_get_region_info(pdata, (void __user *)arg); + return afu_ioctl_get_region_info(fdata, (void __user *)arg); case DFL_FPGA_PORT_DMA_MAP: - return afu_ioctl_dma_map(pdata, (void __user *)arg); + return afu_ioctl_dma_map(fdata, (void __user *)arg); case DFL_FPGA_PORT_DMA_UNMAP: - return afu_ioctl_dma_unmap(pdata, (void __user *)arg); + return afu_ioctl_dma_unmap(fdata, (void __user *)arg); default: /* * Let sub-feature's ioctl function to handle the cmd @@ -785,7 +788,7 @@ static long afu_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) * handled in this sub feature, and returns 0 and other * error code if cmd is handled. */ - dfl_fpga_dev_for_each_feature(pdata, f) + dfl_fpga_dev_for_each_feature(fdata, f) if (f->ops && f->ops->ioctl) { ret = f->ops->ioctl(pdev, f, cmd, arg); if (ret != -ENODEV) @@ -805,8 +808,8 @@ static const struct vm_operations_struct afu_vma_ops = { static int afu_mmap(struct file *filp, struct vm_area_struct *vma) { struct platform_device *pdev = filp->private_data; - struct dfl_feature_platform_data *pdata; u64 size = vma->vm_end - vma->vm_start; + struct dfl_feature_dev_data *fdata; struct dfl_afu_mmio_region region; u64 offset; int ret; @@ -814,10 +817,10 @@ static int afu_mmap(struct file *filp, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; - pdata = dev_get_platdata(&pdev->dev); + fdata = to_dfl_feature_dev_data(&pdev->dev); offset = vma->vm_pgoff << PAGE_SHIFT; - ret = afu_mmio_region_get_by_offset(pdata, offset, size, ®ion); + ret = afu_mmio_region_get_by_offset(fdata, offset, size, ®ion); if (ret) return ret; @@ -851,46 +854,45 @@ static const struct file_operations afu_fops = { static int afu_dev_init(struct platform_device *pdev) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); struct dfl_afu *afu; afu = devm_kzalloc(&pdev->dev, sizeof(*afu), GFP_KERNEL); if (!afu) return -ENOMEM; - mutex_lock(&pdata->lock); - dfl_fpga_pdata_set_private(pdata, afu); - afu_mmio_region_init(pdata); - afu_dma_region_init(pdata); - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + dfl_fpga_fdata_set_private(fdata, afu); + afu_mmio_region_init(fdata); + afu_dma_region_init(fdata); + mutex_unlock(&fdata->lock); return 0; } static int afu_dev_destroy(struct platform_device *pdev) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); - mutex_lock(&pdata->lock); - afu_mmio_region_destroy(pdata); - afu_dma_region_destroy(pdata); - dfl_fpga_pdata_set_private(pdata, NULL); - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + afu_mmio_region_destroy(fdata); + afu_dma_region_destroy(fdata); + dfl_fpga_fdata_set_private(fdata, NULL); + mutex_unlock(&fdata->lock); return 0; } -static int port_enable_set(struct platform_device *pdev, bool enable) +static int port_enable_set(struct dfl_feature_dev_data *fdata, bool enable) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); int ret; - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); if (enable) - ret = __afu_port_enable(pdev); + ret = __afu_port_enable(fdata); else - ret = __afu_port_disable(pdev); - mutex_unlock(&pdata->lock); + ret = __afu_port_disable(fdata); + mutex_unlock(&fdata->lock); return ret; } diff --git a/drivers/fpga/dfl-afu-region.c b/drivers/fpga/dfl-afu-region.c index 2e7b41629406..b11a5b21e666 100644 --- a/drivers/fpga/dfl-afu-region.c +++ b/drivers/fpga/dfl-afu-region.c @@ -12,11 +12,11 @@ /** * afu_mmio_region_init - init function for afu mmio region support - * @pdata: afu platform device's pdata. + * @fdata: afu feature dev data */ -void afu_mmio_region_init(struct dfl_feature_platform_data *pdata) +void afu_mmio_region_init(struct dfl_feature_dev_data *fdata) { - struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata); + struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata); INIT_LIST_HEAD(&afu->regions); } @@ -39,7 +39,7 @@ static struct dfl_afu_mmio_region *get_region_by_index(struct dfl_afu *afu, /** * afu_mmio_region_add - add a mmio region to given feature dev. * - * @pdata: afu platform device's pdata. + * @fdata: afu feature dev data * @region_index: region index. * @region_size: region size. * @phys: region's physical address of this region. @@ -47,14 +47,15 @@ static struct dfl_afu_mmio_region *get_region_by_index(struct dfl_afu *afu, * * Return: 0 on success, negative error code otherwise. */ -int afu_mmio_region_add(struct dfl_feature_platform_data *pdata, +int afu_mmio_region_add(struct dfl_feature_dev_data *fdata, u32 region_index, u64 region_size, u64 phys, u32 flags) { + struct device *dev = &fdata->dev->dev; struct dfl_afu_mmio_region *region; struct dfl_afu *afu; int ret = 0; - region = devm_kzalloc(&pdata->dev->dev, sizeof(*region), GFP_KERNEL); + region = devm_kzalloc(dev, sizeof(*region), GFP_KERNEL); if (!region) return -ENOMEM; @@ -63,13 +64,13 @@ int afu_mmio_region_add(struct dfl_feature_platform_data *pdata, region->phys = phys; region->flags = flags; - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); - afu = dfl_fpga_pdata_get_private(pdata); + afu = dfl_fpga_fdata_get_private(fdata); /* check if @index already exists */ if (get_region_by_index(afu, region_index)) { - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); ret = -EEXIST; goto exit; } @@ -80,37 +81,37 @@ int afu_mmio_region_add(struct dfl_feature_platform_data *pdata, afu->region_cur_offset += region_size; afu->num_regions++; - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return 0; exit: - devm_kfree(&pdata->dev->dev, region); + devm_kfree(dev, region); return ret; } /** * afu_mmio_region_destroy - destroy all mmio regions under given feature dev. - * @pdata: afu platform device's pdata. + * @fdata: afu feature dev data */ -void afu_mmio_region_destroy(struct dfl_feature_platform_data *pdata) +void afu_mmio_region_destroy(struct dfl_feature_dev_data *fdata) { - struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata); + struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata); struct dfl_afu_mmio_region *tmp, *region; list_for_each_entry_safe(region, tmp, &afu->regions, node) - devm_kfree(&pdata->dev->dev, region); + devm_kfree(&fdata->dev->dev, region); } /** * afu_mmio_region_get_by_index - find an afu region by index. - * @pdata: afu platform device's pdata. + * @fdata: afu feature dev data * @region_index: region index. * @pregion: ptr to region for result. * * Return: 0 on success, negative error code otherwise. */ -int afu_mmio_region_get_by_index(struct dfl_feature_platform_data *pdata, +int afu_mmio_region_get_by_index(struct dfl_feature_dev_data *fdata, u32 region_index, struct dfl_afu_mmio_region *pregion) { @@ -118,8 +119,8 @@ int afu_mmio_region_get_by_index(struct dfl_feature_platform_data *pdata, struct dfl_afu *afu; int ret = 0; - mutex_lock(&pdata->lock); - afu = dfl_fpga_pdata_get_private(pdata); + mutex_lock(&fdata->lock); + afu = dfl_fpga_fdata_get_private(fdata); region = get_region_by_index(afu, region_index); if (!region) { ret = -EINVAL; @@ -127,14 +128,14 @@ int afu_mmio_region_get_by_index(struct dfl_feature_platform_data *pdata, } *pregion = *region; exit: - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return ret; } /** * afu_mmio_region_get_by_offset - find an afu mmio region by offset and size * - * @pdata: afu platform device's pdata. + * @fdata: afu feature dev data * @offset: region offset from start of the device fd. * @size: region size. * @pregion: ptr to region for result. @@ -144,7 +145,7 @@ exit: * * Return: 0 on success, negative error code otherwise. */ -int afu_mmio_region_get_by_offset(struct dfl_feature_platform_data *pdata, +int afu_mmio_region_get_by_offset(struct dfl_feature_dev_data *fdata, u64 offset, u64 size, struct dfl_afu_mmio_region *pregion) { @@ -152,8 +153,8 @@ int afu_mmio_region_get_by_offset(struct dfl_feature_platform_data *pdata, struct dfl_afu *afu; int ret = 0; - mutex_lock(&pdata->lock); - afu = dfl_fpga_pdata_get_private(pdata); + mutex_lock(&fdata->lock); + afu = dfl_fpga_fdata_get_private(fdata); for_each_region(region, afu) if (region->offset <= offset && region->offset + region->size >= offset + size) { @@ -162,6 +163,6 @@ int afu_mmio_region_get_by_offset(struct dfl_feature_platform_data *pdata, } ret = -EINVAL; exit: - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return ret; } diff --git a/drivers/fpga/dfl-afu.h b/drivers/fpga/dfl-afu.h index 7bef3e300aa2..03be4f0969c7 100644 --- a/drivers/fpga/dfl-afu.h +++ b/drivers/fpga/dfl-afu.h @@ -76,27 +76,27 @@ struct dfl_afu { struct rb_root dma_regions; }; -/* hold pdata->lock when call __afu_port_enable/disable */ -int __afu_port_enable(struct platform_device *pdev); -int __afu_port_disable(struct platform_device *pdev); +/* hold fdata->lock when call __afu_port_enable/disable */ +int __afu_port_enable(struct dfl_feature_dev_data *fdata); +int __afu_port_disable(struct dfl_feature_dev_data *fdata); -void afu_mmio_region_init(struct dfl_feature_platform_data *pdata); -int afu_mmio_region_add(struct dfl_feature_platform_data *pdata, +void afu_mmio_region_init(struct dfl_feature_dev_data *fdata); +int afu_mmio_region_add(struct dfl_feature_dev_data *fdata, u32 region_index, u64 region_size, u64 phys, u32 flags); -void afu_mmio_region_destroy(struct dfl_feature_platform_data *pdata); -int afu_mmio_region_get_by_index(struct dfl_feature_platform_data *pdata, +void afu_mmio_region_destroy(struct dfl_feature_dev_data *fdata); +int afu_mmio_region_get_by_index(struct dfl_feature_dev_data *fdata, u32 region_index, struct dfl_afu_mmio_region *pregion); -int afu_mmio_region_get_by_offset(struct dfl_feature_platform_data *pdata, +int afu_mmio_region_get_by_offset(struct dfl_feature_dev_data *fdata, u64 offset, u64 size, struct dfl_afu_mmio_region *pregion); -void afu_dma_region_init(struct dfl_feature_platform_data *pdata); -void afu_dma_region_destroy(struct dfl_feature_platform_data *pdata); -int afu_dma_map_region(struct dfl_feature_platform_data *pdata, +void afu_dma_region_init(struct dfl_feature_dev_data *fdata); +void afu_dma_region_destroy(struct dfl_feature_dev_data *fdata); +int afu_dma_map_region(struct dfl_feature_dev_data *fdata, u64 user_addr, u64 length, u64 *iova); -int afu_dma_unmap_region(struct dfl_feature_platform_data *pdata, u64 iova); +int afu_dma_unmap_region(struct dfl_feature_dev_data *fdata, u64 iova); struct dfl_afu_dma_region * -afu_dma_region_find(struct dfl_feature_platform_data *pdata, +afu_dma_region_find(struct dfl_feature_dev_data *fdata, u64 iova, u64 size); extern const struct dfl_feature_ops port_err_ops; diff --git a/drivers/fpga/dfl-fme-br.c b/drivers/fpga/dfl-fme-br.c index 950c606c59d4..28b0f9d062ac 100644 --- a/drivers/fpga/dfl-fme-br.c +++ b/drivers/fpga/dfl-fme-br.c @@ -22,34 +22,34 @@ struct fme_br_priv { struct dfl_fme_br_pdata *pdata; struct dfl_fpga_port_ops *port_ops; - struct platform_device *port_pdev; + struct dfl_feature_dev_data *port_fdata; }; static int fme_bridge_enable_set(struct fpga_bridge *bridge, bool enable) { struct fme_br_priv *priv = bridge->priv; - struct platform_device *port_pdev; + struct dfl_feature_dev_data *port_fdata; struct dfl_fpga_port_ops *ops; - if (!priv->port_pdev) { - port_pdev = dfl_fpga_cdev_find_port(priv->pdata->cdev, - &priv->pdata->port_id, - dfl_fpga_check_port_id); - if (!port_pdev) + if (!priv->port_fdata) { + port_fdata = dfl_fpga_cdev_find_port_data(priv->pdata->cdev, + &priv->pdata->port_id, + dfl_fpga_check_port_id); + if (!port_fdata) return -ENODEV; - priv->port_pdev = port_pdev; + priv->port_fdata = port_fdata; } - if (priv->port_pdev && !priv->port_ops) { - ops = dfl_fpga_port_ops_get(priv->port_pdev); + if (priv->port_fdata && !priv->port_ops) { + ops = dfl_fpga_port_ops_get(priv->port_fdata); if (!ops || !ops->enable_set) return -ENOENT; priv->port_ops = ops; } - return priv->port_ops->enable_set(priv->port_pdev, enable); + return priv->port_ops->enable_set(priv->port_fdata, enable); } static const struct fpga_bridge_ops fme_bridge_ops = { @@ -85,8 +85,6 @@ static void fme_br_remove(struct platform_device *pdev) fpga_bridge_unregister(br); - if (priv->port_pdev) - put_device(&priv->port_pdev->dev); if (priv->port_ops) dfl_fpga_port_ops_put(priv->port_ops); } diff --git a/drivers/fpga/dfl-fme-error.c b/drivers/fpga/dfl-fme-error.c index 51c2892ec06d..f00d949efe69 100644 --- a/drivers/fpga/dfl-fme-error.c +++ b/drivers/fpga/dfl-fme-error.c @@ -42,15 +42,15 @@ static ssize_t pcie0_errors_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 value; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); value = readq(base + PCIE0_ERROR); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)value); } @@ -59,7 +59,7 @@ static ssize_t pcie0_errors_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; int ret = 0; u64 v, val; @@ -67,9 +67,9 @@ static ssize_t pcie0_errors_store(struct device *dev, if (kstrtou64(buf, 0, &val)) return -EINVAL; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); writeq(GENMASK_ULL(63, 0), base + PCIE0_ERROR_MASK); v = readq(base + PCIE0_ERROR); @@ -79,7 +79,7 @@ static ssize_t pcie0_errors_store(struct device *dev, ret = -EINVAL; writeq(0ULL, base + PCIE0_ERROR_MASK); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return ret ? ret : count; } static DEVICE_ATTR_RW(pcie0_errors); @@ -87,15 +87,15 @@ static DEVICE_ATTR_RW(pcie0_errors); static ssize_t pcie1_errors_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 value; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); value = readq(base + PCIE1_ERROR); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)value); } @@ -104,7 +104,7 @@ static ssize_t pcie1_errors_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; int ret = 0; u64 v, val; @@ -112,9 +112,9 @@ static ssize_t pcie1_errors_store(struct device *dev, if (kstrtou64(buf, 0, &val)) return -EINVAL; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); writeq(GENMASK_ULL(63, 0), base + PCIE1_ERROR_MASK); v = readq(base + PCIE1_ERROR); @@ -124,7 +124,7 @@ static ssize_t pcie1_errors_store(struct device *dev, ret = -EINVAL; writeq(0ULL, base + PCIE1_ERROR_MASK); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return ret ? ret : count; } static DEVICE_ATTR_RW(pcie1_errors); @@ -132,9 +132,10 @@ static DEVICE_ATTR_RW(pcie1_errors); static ssize_t nonfatal_errors_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); return sprintf(buf, "0x%llx\n", (unsigned long long)readq(base + RAS_NONFAT_ERROR)); @@ -144,9 +145,10 @@ static DEVICE_ATTR_RO(nonfatal_errors); static ssize_t catfatal_errors_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); return sprintf(buf, "0x%llx\n", (unsigned long long)readq(base + RAS_CATFAT_ERROR)); @@ -156,15 +158,15 @@ static DEVICE_ATTR_RO(catfatal_errors); static ssize_t inject_errors_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); v = readq(base + RAS_ERROR_INJECT); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)FIELD_GET(INJECT_ERROR_MASK, v)); @@ -174,7 +176,7 @@ static ssize_t inject_errors_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u8 inject_error; u64 v; @@ -185,14 +187,14 @@ static ssize_t inject_errors_store(struct device *dev, if (inject_error & ~INJECT_ERROR_MASK) return -EINVAL; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); v = readq(base + RAS_ERROR_INJECT); v &= ~INJECT_ERROR_MASK; v |= FIELD_PREP(INJECT_ERROR_MASK, inject_error); writeq(v, base + RAS_ERROR_INJECT); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return count; } @@ -201,15 +203,15 @@ static DEVICE_ATTR_RW(inject_errors); static ssize_t fme_errors_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 value; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); value = readq(base + FME_ERROR); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)value); } @@ -218,7 +220,7 @@ static ssize_t fme_errors_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v, val; int ret = 0; @@ -226,9 +228,9 @@ static ssize_t fme_errors_store(struct device *dev, if (kstrtou64(buf, 0, &val)) return -EINVAL; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); writeq(GENMASK_ULL(63, 0), base + FME_ERROR_MASK); v = readq(base + FME_ERROR); @@ -240,7 +242,7 @@ static ssize_t fme_errors_store(struct device *dev, /* Workaround: disable MBP_ERROR if feature revision is 0 */ writeq(dfl_feature_revision(base) ? 0ULL : MBP_ERROR, base + FME_ERROR_MASK); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return ret ? ret : count; } static DEVICE_ATTR_RW(fme_errors); @@ -248,15 +250,15 @@ static DEVICE_ATTR_RW(fme_errors); static ssize_t first_error_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 value; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); value = readq(base + FME_FIRST_ERROR); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)value); } @@ -265,15 +267,15 @@ static DEVICE_ATTR_RO(first_error); static ssize_t next_error_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 value; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); value = readq(base + FME_NEXT_ERROR); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return sprintf(buf, "0x%llx\n", (unsigned long long)value); } @@ -295,12 +297,14 @@ static umode_t fme_global_err_attrs_visible(struct kobject *kobj, struct attribute *attr, int n) { struct device *dev = kobj_to_dev(kobj); + struct dfl_feature_dev_data *fdata; + fdata = to_dfl_feature_dev_data(dev); /* * sysfs entries are visible only if related private feature is * enumerated. */ - if (!dfl_get_feature_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR)) + if (!dfl_get_feature_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR)) return 0; return attr->mode; @@ -314,12 +318,12 @@ const struct attribute_group fme_global_err_group = { static void fme_err_mask(struct device *dev, bool mask) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); /* Workaround: keep MBP_ERROR always masked if revision is 0 */ if (dfl_feature_revision(base)) @@ -332,7 +336,7 @@ static void fme_err_mask(struct device *dev, bool mask) writeq(mask ? ERROR_MASK : 0, base + RAS_NONFAT_ERROR_MASK); writeq(mask ? ERROR_MASK : 0, base + RAS_CATFAT_ERROR_MASK); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); } static int fme_global_err_init(struct platform_device *pdev, diff --git a/drivers/fpga/dfl-fme-main.c b/drivers/fpga/dfl-fme-main.c index f8d89a4a6ccb..8aca2fb20e87 100644 --- a/drivers/fpga/dfl-fme-main.c +++ b/drivers/fpga/dfl-fme-main.c @@ -28,10 +28,11 @@ static ssize_t ports_num_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER); v = readq(base + FME_HDR_CAP); @@ -47,10 +48,11 @@ static DEVICE_ATTR_RO(ports_num); static ssize_t bitstream_id_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER); v = readq(base + FME_HDR_BITSTREAM_ID); @@ -65,10 +67,11 @@ static DEVICE_ATTR_RO(bitstream_id); static ssize_t bitstream_metadata_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER); v = readq(base + FME_HDR_BITSTREAM_MD); @@ -79,10 +82,11 @@ static DEVICE_ATTR_RO(bitstream_metadata); static ssize_t cache_size_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER); v = readq(base + FME_HDR_CAP); @@ -94,10 +98,11 @@ static DEVICE_ATTR_RO(cache_size); static ssize_t fabric_version_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER); v = readq(base + FME_HDR_CAP); @@ -109,10 +114,11 @@ static DEVICE_ATTR_RO(fabric_version); static ssize_t socket_id_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER); v = readq(base + FME_HDR_CAP); @@ -135,10 +141,10 @@ static const struct attribute_group fme_hdr_group = { .attrs = fme_hdr_attrs, }; -static long fme_hdr_ioctl_release_port(struct dfl_feature_platform_data *pdata, +static long fme_hdr_ioctl_release_port(struct dfl_feature_dev_data *fdata, unsigned long arg) { - struct dfl_fpga_cdev *cdev = pdata->dfl_cdev; + struct dfl_fpga_cdev *cdev = fdata->dfl_cdev; int port_id; if (get_user(port_id, (int __user *)arg)) @@ -147,10 +153,10 @@ static long fme_hdr_ioctl_release_port(struct dfl_feature_platform_data *pdata, return dfl_fpga_cdev_release_port(cdev, port_id); } -static long fme_hdr_ioctl_assign_port(struct dfl_feature_platform_data *pdata, +static long fme_hdr_ioctl_assign_port(struct dfl_feature_dev_data *fdata, unsigned long arg) { - struct dfl_fpga_cdev *cdev = pdata->dfl_cdev; + struct dfl_fpga_cdev *cdev = fdata->dfl_cdev; int port_id; if (get_user(port_id, (int __user *)arg)) @@ -163,13 +169,13 @@ static long fme_hdr_ioctl(struct platform_device *pdev, struct dfl_feature *feature, unsigned int cmd, unsigned long arg) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); switch (cmd) { case DFL_FPGA_FME_PORT_RELEASE: - return fme_hdr_ioctl_release_port(pdata, arg); + return fme_hdr_ioctl_release_port(fdata, arg); case DFL_FPGA_FME_PORT_ASSIGN: - return fme_hdr_ioctl_assign_port(pdata, arg); + return fme_hdr_ioctl_assign_port(fdata, arg); } return -ENODEV; @@ -411,14 +417,14 @@ static int power_hwmon_read(struct device *dev, enum hwmon_sensor_types type, static int power_hwmon_write(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long val) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev->parent); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev->parent); struct dfl_feature *feature = dev_get_drvdata(dev); int ret = 0; u64 v; val = clamp_val(val / MICRO, 0, PWR_THRESHOLD_MAX); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); switch (attr) { case hwmon_power_max: @@ -438,7 +444,7 @@ static int power_hwmon_write(struct device *dev, enum hwmon_sensor_types type, break; } - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return ret; } @@ -589,7 +595,7 @@ static struct dfl_feature_driver fme_feature_drvs[] = { }, }; -static long fme_ioctl_check_extension(struct dfl_feature_platform_data *pdata, +static long fme_ioctl_check_extension(struct dfl_feature_dev_data *fdata, unsigned long arg) { /* No extension support for now */ @@ -598,49 +604,46 @@ static long fme_ioctl_check_extension(struct dfl_feature_platform_data *pdata, static int fme_open(struct inode *inode, struct file *filp) { - struct platform_device *fdev = dfl_fpga_inode_to_feature_dev(inode); - struct dfl_feature_platform_data *pdata = dev_get_platdata(&fdev->dev); + struct dfl_feature_dev_data *fdata = dfl_fpga_inode_to_feature_dev_data(inode); + struct platform_device *fdev = fdata->dev; int ret; - if (WARN_ON(!pdata)) - return -ENODEV; - - mutex_lock(&pdata->lock); - ret = dfl_feature_dev_use_begin(pdata, filp->f_flags & O_EXCL); + mutex_lock(&fdata->lock); + ret = dfl_feature_dev_use_begin(fdata, filp->f_flags & O_EXCL); if (!ret) { dev_dbg(&fdev->dev, "Device File Opened %d Times\n", - dfl_feature_dev_use_count(pdata)); - filp->private_data = pdata; + dfl_feature_dev_use_count(fdata)); + filp->private_data = fdata; } - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return ret; } static int fme_release(struct inode *inode, struct file *filp) { - struct dfl_feature_platform_data *pdata = filp->private_data; - struct platform_device *pdev = pdata->dev; + struct dfl_feature_dev_data *fdata = filp->private_data; + struct platform_device *pdev = fdata->dev; struct dfl_feature *feature; dev_dbg(&pdev->dev, "Device File Release\n"); - mutex_lock(&pdata->lock); - dfl_feature_dev_use_end(pdata); + mutex_lock(&fdata->lock); + dfl_feature_dev_use_end(fdata); - if (!dfl_feature_dev_use_count(pdata)) - dfl_fpga_dev_for_each_feature(pdata, feature) + if (!dfl_feature_dev_use_count(fdata)) + dfl_fpga_dev_for_each_feature(fdata, feature) dfl_fpga_set_irq_triggers(feature, 0, feature->nr_irqs, NULL); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return 0; } static long fme_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { - struct dfl_feature_platform_data *pdata = filp->private_data; - struct platform_device *pdev = pdata->dev; + struct dfl_feature_dev_data *fdata = filp->private_data; + struct platform_device *pdev = fdata->dev; struct dfl_feature *f; long ret; @@ -650,7 +653,7 @@ static long fme_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case DFL_FPGA_GET_API_VERSION: return DFL_FPGA_API_VERSION; case DFL_FPGA_CHECK_EXTENSION: - return fme_ioctl_check_extension(pdata, arg); + return fme_ioctl_check_extension(fdata, arg); default: /* * Let sub-feature's ioctl function to handle the cmd. @@ -658,7 +661,7 @@ static long fme_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) * handled in this sub feature, and returns 0 or other * error code if cmd is handled. */ - dfl_fpga_dev_for_each_feature(pdata, f) { + dfl_fpga_dev_for_each_feature(fdata, f) { if (f->ops && f->ops->ioctl) { ret = f->ops->ioctl(pdev, f, cmd, arg); if (ret != -ENODEV) @@ -672,27 +675,27 @@ static long fme_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) static int fme_dev_init(struct platform_device *pdev) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); struct dfl_fme *fme; fme = devm_kzalloc(&pdev->dev, sizeof(*fme), GFP_KERNEL); if (!fme) return -ENOMEM; - mutex_lock(&pdata->lock); - dfl_fpga_pdata_set_private(pdata, fme); - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + dfl_fpga_fdata_set_private(fdata, fme); + mutex_unlock(&fdata->lock); return 0; } static void fme_dev_destroy(struct platform_device *pdev) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); - mutex_lock(&pdata->lock); - dfl_fpga_pdata_set_private(pdata, NULL); - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + dfl_fpga_fdata_set_private(fdata, NULL); + mutex_unlock(&fdata->lock); } static const struct file_operations fme_fops = { diff --git a/drivers/fpga/dfl-fme-pr.c b/drivers/fpga/dfl-fme-pr.c index cdcf6dea4cc9..b878b260af38 100644 --- a/drivers/fpga/dfl-fme-pr.c +++ b/drivers/fpga/dfl-fme-pr.c @@ -65,7 +65,7 @@ static struct fpga_region *dfl_fme_region_find(struct dfl_fme *fme, int port_id) static int fme_pr(struct platform_device *pdev, unsigned long arg) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); void __user *argp = (void __user *)arg; struct dfl_fpga_fme_port_pr port_pr; struct fpga_image_info *info; @@ -87,8 +87,7 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg) return -EINVAL; /* get fme header region */ - fme_hdr = dfl_get_feature_ioaddr_by_id(&pdev->dev, - FME_FEATURE_ID_HEADER); + fme_hdr = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER); /* check port id */ v = readq(fme_hdr + FME_HDR_CAP); @@ -123,8 +122,8 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg) info->flags |= FPGA_MGR_PARTIAL_RECONFIG; - mutex_lock(&pdata->lock); - fme = dfl_fpga_pdata_get_private(pdata); + mutex_lock(&fdata->lock); + fme = dfl_fpga_fdata_get_private(fdata); /* fme device has been unregistered. */ if (!fme) { ret = -EINVAL; @@ -156,7 +155,7 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg) put_device(®ion->dev); unlock_exit: - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); free_exit: vfree(buf); return ret; @@ -164,16 +163,16 @@ free_exit: /** * dfl_fme_create_mgr - create fpga mgr platform device as child device + * @fdata: fme feature dev data * @feature: sub feature info - * @pdata: fme platform_device's pdata * * Return: mgr platform device if successful, and error code otherwise. */ static struct platform_device * -dfl_fme_create_mgr(struct dfl_feature_platform_data *pdata, +dfl_fme_create_mgr(struct dfl_feature_dev_data *fdata, struct dfl_feature *feature) { - struct platform_device *mgr, *fme = pdata->dev; + struct platform_device *mgr, *fme = fdata->dev; struct dfl_fme_mgr_pdata mgr_pdata; int ret = -ENOMEM; @@ -209,11 +208,11 @@ create_mgr_err: /** * dfl_fme_destroy_mgr - destroy fpga mgr platform device - * @pdata: fme platform device's pdata + * @fdata: fme feature dev data */ -static void dfl_fme_destroy_mgr(struct dfl_feature_platform_data *pdata) +static void dfl_fme_destroy_mgr(struct dfl_feature_dev_data *fdata) { - struct dfl_fme *priv = dfl_fpga_pdata_get_private(pdata); + struct dfl_fme *priv = dfl_fpga_fdata_get_private(fdata); platform_device_unregister(priv->mgr); } @@ -221,15 +220,15 @@ static void dfl_fme_destroy_mgr(struct dfl_feature_platform_data *pdata) /** * dfl_fme_create_bridge - create fme fpga bridge platform device as child * - * @pdata: fme platform device's pdata + * @fdata: fme feature dev data * @port_id: port id for the bridge to be created. * * Return: bridge platform device if successful, and error code otherwise. */ static struct dfl_fme_bridge * -dfl_fme_create_bridge(struct dfl_feature_platform_data *pdata, int port_id) +dfl_fme_create_bridge(struct dfl_feature_dev_data *fdata, int port_id) { - struct device *dev = &pdata->dev->dev; + struct device *dev = &fdata->dev->dev; struct dfl_fme_br_pdata br_pdata; struct dfl_fme_bridge *fme_br; int ret = -ENOMEM; @@ -238,7 +237,7 @@ dfl_fme_create_bridge(struct dfl_feature_platform_data *pdata, int port_id) if (!fme_br) return ERR_PTR(ret); - br_pdata.cdev = pdata->dfl_cdev; + br_pdata.cdev = fdata->dfl_cdev; br_pdata.port_id = port_id; fme_br->br = platform_device_alloc(DFL_FPGA_FME_BRIDGE, @@ -274,11 +273,11 @@ static void dfl_fme_destroy_bridge(struct dfl_fme_bridge *fme_br) /** * dfl_fme_destroy_bridges - destroy all fpga bridge platform device - * @pdata: fme platform device's pdata + * @fdata: fme feature dev data */ -static void dfl_fme_destroy_bridges(struct dfl_feature_platform_data *pdata) +static void dfl_fme_destroy_bridges(struct dfl_feature_dev_data *fdata) { - struct dfl_fme *priv = dfl_fpga_pdata_get_private(pdata); + struct dfl_fme *priv = dfl_fpga_fdata_get_private(fdata); struct dfl_fme_bridge *fbridge, *tmp; list_for_each_entry_safe(fbridge, tmp, &priv->bridge_list, node) { @@ -290,7 +289,7 @@ static void dfl_fme_destroy_bridges(struct dfl_feature_platform_data *pdata) /** * dfl_fme_create_region - create fpga region platform device as child * - * @pdata: fme platform device's pdata + * @fdata: fme feature dev data * @mgr: mgr platform device needed for region * @br: br platform device needed for region * @port_id: port id @@ -298,12 +297,12 @@ static void dfl_fme_destroy_bridges(struct dfl_feature_platform_data *pdata) * Return: fme region if successful, and error code otherwise. */ static struct dfl_fme_region * -dfl_fme_create_region(struct dfl_feature_platform_data *pdata, +dfl_fme_create_region(struct dfl_feature_dev_data *fdata, struct platform_device *mgr, struct platform_device *br, int port_id) { struct dfl_fme_region_pdata region_pdata; - struct device *dev = &pdata->dev->dev; + struct device *dev = &fdata->dev->dev; struct dfl_fme_region *fme_region; int ret = -ENOMEM; @@ -353,11 +352,11 @@ static void dfl_fme_destroy_region(struct dfl_fme_region *fme_region) /** * dfl_fme_destroy_regions - destroy all fme regions - * @pdata: fme platform device's pdata + * @fdata: fme feature dev data */ -static void dfl_fme_destroy_regions(struct dfl_feature_platform_data *pdata) +static void dfl_fme_destroy_regions(struct dfl_feature_dev_data *fdata) { - struct dfl_fme *priv = dfl_fpga_pdata_get_private(pdata); + struct dfl_fme *priv = dfl_fpga_fdata_get_private(fdata); struct dfl_fme_region *fme_region, *tmp; list_for_each_entry_safe(fme_region, tmp, &priv->region_list, node) { @@ -369,7 +368,7 @@ static void dfl_fme_destroy_regions(struct dfl_feature_platform_data *pdata) static int pr_mgmt_init(struct platform_device *pdev, struct dfl_feature *feature) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); struct dfl_fme_region *fme_region; struct dfl_fme_bridge *fme_br; struct platform_device *mgr; @@ -378,18 +377,17 @@ static int pr_mgmt_init(struct platform_device *pdev, int ret = -ENODEV, i = 0; u64 fme_cap, port_offset; - fme_hdr = dfl_get_feature_ioaddr_by_id(&pdev->dev, - FME_FEATURE_ID_HEADER); + fme_hdr = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER); - mutex_lock(&pdata->lock); - priv = dfl_fpga_pdata_get_private(pdata); + mutex_lock(&fdata->lock); + priv = dfl_fpga_fdata_get_private(fdata); /* Initialize the region and bridge sub device list */ INIT_LIST_HEAD(&priv->region_list); INIT_LIST_HEAD(&priv->bridge_list); /* Create fpga mgr platform device */ - mgr = dfl_fme_create_mgr(pdata, feature); + mgr = dfl_fme_create_mgr(fdata, feature); if (IS_ERR(mgr)) { dev_err(&pdev->dev, "fail to create fpga mgr pdev\n"); goto unlock; @@ -405,7 +403,7 @@ static int pr_mgmt_init(struct platform_device *pdev, continue; /* Create bridge for each port */ - fme_br = dfl_fme_create_bridge(pdata, i); + fme_br = dfl_fme_create_bridge(fdata, i); if (IS_ERR(fme_br)) { ret = PTR_ERR(fme_br); goto destroy_region; @@ -414,7 +412,7 @@ static int pr_mgmt_init(struct platform_device *pdev, list_add(&fme_br->node, &priv->bridge_list); /* Create region for each port */ - fme_region = dfl_fme_create_region(pdata, mgr, + fme_region = dfl_fme_create_region(fdata, mgr, fme_br->br, i); if (IS_ERR(fme_region)) { ret = PTR_ERR(fme_region); @@ -423,30 +421,30 @@ static int pr_mgmt_init(struct platform_device *pdev, list_add(&fme_region->node, &priv->region_list); } - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return 0; destroy_region: - dfl_fme_destroy_regions(pdata); - dfl_fme_destroy_bridges(pdata); - dfl_fme_destroy_mgr(pdata); + dfl_fme_destroy_regions(fdata); + dfl_fme_destroy_bridges(fdata); + dfl_fme_destroy_mgr(fdata); unlock: - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); return ret; } static void pr_mgmt_uinit(struct platform_device *pdev, struct dfl_feature *feature) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); - dfl_fme_destroy_regions(pdata); - dfl_fme_destroy_bridges(pdata); - dfl_fme_destroy_mgr(pdata); - mutex_unlock(&pdata->lock); + dfl_fme_destroy_regions(fdata); + dfl_fme_destroy_bridges(fdata); + dfl_fme_destroy_mgr(fdata); + mutex_unlock(&fdata->lock); } static long fme_pr_ioctl(struct platform_device *pdev, diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index c406b949026f..7022657243c0 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -119,17 +119,6 @@ static void dfl_id_free(enum dfl_id_type type, int id) mutex_unlock(&dfl_id_mutex); } -static enum dfl_id_type feature_dev_id_type(struct platform_device *pdev) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(dfl_devs); i++) - if (!strcmp(dfl_devs[i].name, pdev->name)) - return i; - - return DFL_ID_MAX; -} - static enum dfl_id_type dfh_id_to_type(u16 id) { int i; @@ -156,12 +145,12 @@ static LIST_HEAD(dfl_port_ops_list); /** * dfl_fpga_port_ops_get - get matched port ops from the global list - * @pdev: platform device to match with associated port ops. + * @fdata: feature dev data to match with associated port ops. * Return: matched port ops on success, NULL otherwise. * * Please note that must dfl_fpga_port_ops_put after use the port_ops. */ -struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct platform_device *pdev) +struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct dfl_feature_dev_data *fdata) { struct dfl_fpga_port_ops *ops = NULL; @@ -171,7 +160,7 @@ struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct platform_device *pdev) list_for_each_entry(ops, &dfl_port_ops_list, node) { /* match port_ops using the name of platform device */ - if (!strcmp(pdev->name, ops->name)) { + if (!strcmp(fdata->pdev_name, ops->name)) { if (!try_module_get(ops->owner)) ops = NULL; goto done; @@ -222,27 +211,26 @@ EXPORT_SYMBOL_GPL(dfl_fpga_port_ops_del); /** * dfl_fpga_check_port_id - check the port id - * @pdev: port platform device. + * @fdata: port feature dev data. * @pport_id: port id to compare. * * Return: 1 if port device matches with given port id, otherwise 0. */ -int dfl_fpga_check_port_id(struct platform_device *pdev, void *pport_id) +int dfl_fpga_check_port_id(struct dfl_feature_dev_data *fdata, void *pport_id) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); struct dfl_fpga_port_ops *port_ops; - if (pdata->id != FEATURE_DEV_ID_UNUSED) - return pdata->id == *(int *)pport_id; + if (fdata->id != FEATURE_DEV_ID_UNUSED) + return fdata->id == *(int *)pport_id; - port_ops = dfl_fpga_port_ops_get(pdev); + port_ops = dfl_fpga_port_ops_get(fdata); if (!port_ops || !port_ops->get_id) return 0; - pdata->id = port_ops->get_id(pdev); + fdata->id = port_ops->get_id(fdata); dfl_fpga_port_ops_put(port_ops); - return pdata->id == *(int *)pport_id; + return fdata->id == *(int *)pport_id; } EXPORT_SYMBOL_GPL(dfl_fpga_check_port_id); @@ -351,10 +339,10 @@ static void release_dfl_dev(struct device *dev) } static struct dfl_device * -dfl_dev_add(struct dfl_feature_platform_data *pdata, +dfl_dev_add(struct dfl_feature_dev_data *fdata, struct dfl_feature *feature) { - struct platform_device *pdev = pdata->dev; + struct platform_device *pdev = fdata->dev; struct resource *parent_res; struct dfl_device *ddev; int id, i, ret; @@ -380,11 +368,11 @@ dfl_dev_add(struct dfl_feature_platform_data *pdata, if (ret) goto put_dev; - ddev->type = feature_dev_id_type(pdev); + ddev->type = fdata->type; ddev->feature_id = feature->id; ddev->revision = feature->revision; ddev->dfh_version = feature->dfh_version; - ddev->cdev = pdata->dfl_cdev; + ddev->cdev = fdata->dfl_cdev; if (feature->param_size) { ddev->params = kmemdup(feature->params, feature->param_size, GFP_KERNEL); if (!ddev->params) { @@ -435,11 +423,11 @@ put_dev: return ERR_PTR(ret); } -static void dfl_devs_remove(struct dfl_feature_platform_data *pdata) +static void dfl_devs_remove(struct dfl_feature_dev_data *fdata) { struct dfl_feature *feature; - dfl_fpga_dev_for_each_feature(pdata, feature) { + dfl_fpga_dev_for_each_feature(fdata, feature) { if (feature->ddev) { device_unregister(&feature->ddev->dev); feature->ddev = NULL; @@ -447,13 +435,13 @@ static void dfl_devs_remove(struct dfl_feature_platform_data *pdata) } } -static int dfl_devs_add(struct dfl_feature_platform_data *pdata) +static int dfl_devs_add(struct dfl_feature_dev_data *fdata) { struct dfl_feature *feature; struct dfl_device *ddev; int ret; - dfl_fpga_dev_for_each_feature(pdata, feature) { + dfl_fpga_dev_for_each_feature(fdata, feature) { if (feature->ioaddr) continue; @@ -462,7 +450,7 @@ static int dfl_devs_add(struct dfl_feature_platform_data *pdata) goto err; } - ddev = dfl_dev_add(pdata, feature); + ddev = dfl_dev_add(fdata, feature); if (IS_ERR(ddev)) { ret = PTR_ERR(ddev); goto err; @@ -474,7 +462,7 @@ static int dfl_devs_add(struct dfl_feature_platform_data *pdata) return 0; err: - dfl_devs_remove(pdata); + dfl_devs_remove(fdata); return ret; } @@ -504,12 +492,12 @@ EXPORT_SYMBOL(dfl_driver_unregister); */ void dfl_fpga_dev_feature_uinit(struct platform_device *pdev) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); struct dfl_feature *feature; - dfl_devs_remove(pdata); + dfl_devs_remove(fdata); - dfl_fpga_dev_for_each_feature(pdata, feature) { + dfl_fpga_dev_for_each_feature(fdata, feature) { if (feature->ops) { if (feature->ops->uinit) feature->ops->uinit(pdev, feature); @@ -520,7 +508,6 @@ void dfl_fpga_dev_feature_uinit(struct platform_device *pdev) EXPORT_SYMBOL_GPL(dfl_fpga_dev_feature_uinit); static int dfl_feature_instance_init(struct platform_device *pdev, - struct dfl_feature_platform_data *pdata, struct dfl_feature *feature, struct dfl_feature_driver *drv) { @@ -579,16 +566,15 @@ static bool dfl_feature_drv_match(struct dfl_feature *feature, int dfl_fpga_dev_feature_init(struct platform_device *pdev, struct dfl_feature_driver *feature_drvs) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); struct dfl_feature_driver *drv = feature_drvs; struct dfl_feature *feature; int ret; while (drv->ops) { - dfl_fpga_dev_for_each_feature(pdata, feature) { + dfl_fpga_dev_for_each_feature(fdata, feature) { if (dfl_feature_drv_match(feature, drv)) { - ret = dfl_feature_instance_init(pdev, pdata, - feature, drv); + ret = dfl_feature_instance_init(pdev, feature, drv); if (ret) goto exit; } @@ -596,7 +582,7 @@ int dfl_fpga_dev_feature_init(struct platform_device *pdev, drv++; } - ret = dfl_devs_add(pdata); + ret = dfl_devs_add(fdata); if (ret) goto exit; @@ -695,7 +681,7 @@ EXPORT_SYMBOL_GPL(dfl_fpga_dev_ops_unregister); * @nr_irqs: number of irqs for all feature devices. * @irq_table: Linux IRQ numbers for all irqs, indexed by local irq index of * this device. - * @feature_dev: current feature device. + * @type: the current FIU type. * @ioaddr: header register region address of current FIU in enumeration. * @start: register resource start of current FIU. * @len: max register resource length of current FIU. @@ -708,7 +694,7 @@ struct build_feature_devs_info { unsigned int nr_irqs; int *irq_table; - struct platform_device *feature_dev; + enum dfl_id_type type; void __iomem *ioaddr; resource_size_t start; resource_size_t len; @@ -743,50 +729,62 @@ struct dfl_feature_info { u64 params[]; }; -static void dfl_fpga_cdev_add_port_dev(struct dfl_fpga_cdev *cdev, - struct platform_device *port) +static void dfl_fpga_cdev_add_port_data(struct dfl_fpga_cdev *cdev, + struct dfl_feature_dev_data *fdata) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&port->dev); - mutex_lock(&cdev->lock); - list_add(&pdata->node, &cdev->port_dev_list); - get_device(&pdata->dev->dev); + list_add(&fdata->node, &cdev->port_dev_list); mutex_unlock(&cdev->lock); } -/* - * register current feature device, it is called when we need to switch to - * another feature parsing or we have parsed all features on given device - * feature list. - */ -static int build_info_commit_dev(struct build_feature_devs_info *binfo) +static void dfl_id_free_action(void *arg) { - struct platform_device *fdev = binfo->feature_dev; - struct dfl_feature_platform_data *pdata; + struct dfl_feature_dev_data *fdata = arg; + + dfl_id_free(fdata->type, fdata->pdev_id); +} + +static struct dfl_feature_dev_data * +binfo_create_feature_dev_data(struct build_feature_devs_info *binfo) +{ + enum dfl_id_type type = binfo->type; struct dfl_feature_info *finfo, *p; - enum dfl_id_type type; + struct dfl_feature_dev_data *fdata; int ret, index = 0, res_idx = 0; - type = feature_dev_id_type(fdev); if (WARN_ON_ONCE(type >= DFL_ID_MAX)) - return -EINVAL; + return ERR_PTR(-EINVAL); - /* - * we do not need to care for the memory which is associated with - * the platform device. After calling platform_device_unregister(), - * it will be automatically freed by device's release() callback, - * platform_device_release(). - */ - pdata = kzalloc(struct_size(pdata, features, binfo->feature_num), GFP_KERNEL); - if (!pdata) - return -ENOMEM; + fdata = devm_kzalloc(binfo->dev, sizeof(*fdata), GFP_KERNEL); + if (!fdata) + return ERR_PTR(-ENOMEM); - pdata->dev = fdev; - pdata->num = binfo->feature_num; - pdata->dfl_cdev = binfo->cdev; - pdata->id = FEATURE_DEV_ID_UNUSED; - mutex_init(&pdata->lock); - lockdep_set_class_and_name(&pdata->lock, &dfl_pdata_keys[type], + fdata->features = devm_kcalloc(binfo->dev, binfo->feature_num, + sizeof(*fdata->features), GFP_KERNEL); + if (!fdata->features) + return ERR_PTR(-ENOMEM); + + fdata->resources = devm_kcalloc(binfo->dev, binfo->feature_num, + sizeof(*fdata->resources), GFP_KERNEL); + if (!fdata->resources) + return ERR_PTR(-ENOMEM); + + fdata->type = type; + + fdata->pdev_id = dfl_id_alloc(type, binfo->dev); + if (fdata->pdev_id < 0) + return ERR_PTR(fdata->pdev_id); + + ret = devm_add_action_or_reset(binfo->dev, dfl_id_free_action, fdata); + if (ret) + return ERR_PTR(ret); + + fdata->pdev_name = dfl_devs[type].name; + fdata->num = binfo->feature_num; + fdata->dfl_cdev = binfo->cdev; + fdata->id = FEATURE_DEV_ID_UNUSED; + mutex_init(&fdata->lock); + lockdep_set_class_and_name(&fdata->lock, &dfl_pdata_keys[type], dfl_pdata_key_strings[type]); /* @@ -795,25 +793,15 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo) * works properly for port device. * and it should always be 0 for fme device. */ - WARN_ON(pdata->disable_count); - - fdev->dev.platform_data = pdata; - - /* each sub feature has one MMIO resource */ - fdev->num_resources = binfo->feature_num; - fdev->resource = kcalloc(binfo->feature_num, sizeof(*fdev->resource), - GFP_KERNEL); - if (!fdev->resource) - return -ENOMEM; + WARN_ON(fdata->disable_count); /* fill features and resource information for feature dev */ list_for_each_entry_safe(finfo, p, &binfo->sub_features, node) { - struct dfl_feature *feature = &pdata->features[index++]; + struct dfl_feature *feature = &fdata->features[index++]; struct dfl_feature_irq_ctx *ctx; unsigned int i; /* save resource information for each feature */ - feature->dev = fdev; feature->id = finfo->fid; feature->revision = finfo->revision; feature->dfh_version = finfo->dfh_version; @@ -823,7 +811,7 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo) finfo->params, finfo->param_size, GFP_KERNEL); if (!feature->params) - return -ENOMEM; + return ERR_PTR(-ENOMEM); feature->param_size = finfo->param_size; } @@ -840,17 +828,17 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo) devm_ioremap_resource(binfo->dev, &finfo->mmio_res); if (IS_ERR(feature->ioaddr)) - return PTR_ERR(feature->ioaddr); + return ERR_CAST(feature->ioaddr); } else { feature->resource_index = res_idx; - fdev->resource[res_idx++] = finfo->mmio_res; + fdata->resources[res_idx++] = finfo->mmio_res; } if (finfo->nr_irqs) { ctx = devm_kcalloc(binfo->dev, finfo->nr_irqs, sizeof(*ctx), GFP_KERNEL); if (!ctx) - return -ENOMEM; + return ERR_PTR(-ENOMEM); for (i = 0; i < finfo->nr_irqs; i++) ctx[i].irq = @@ -864,55 +852,94 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo) kfree(finfo); } - ret = platform_device_add(binfo->feature_dev); - if (!ret) { - if (type == PORT_ID) - dfl_fpga_cdev_add_port_dev(binfo->cdev, - binfo->feature_dev); - else - binfo->cdev->fme_dev = - get_device(&binfo->feature_dev->dev); - /* - * reset it to avoid build_info_free() freeing their resource. - * - * The resource of successfully registered feature devices - * will be freed by platform_device_unregister(). See the - * comments in build_info_create_dev(). - */ - binfo->feature_dev = NULL; - } + fdata->resource_num = res_idx; + + return fdata; +} + +/* + * register current feature device, it is called when we need to switch to + * another feature parsing or we have parsed all features on given device + * feature list. + */ +static int feature_dev_register(struct dfl_feature_dev_data *fdata) +{ + struct dfl_feature_platform_data pdata = {}; + struct platform_device *fdev; + struct dfl_feature *feature; + int ret; + + fdev = platform_device_alloc(fdata->pdev_name, fdata->pdev_id); + if (!fdev) + return -ENOMEM; + + fdata->dev = fdev; + + fdev->dev.parent = &fdata->dfl_cdev->region->dev; + fdev->dev.devt = dfl_get_devt(dfl_devs[fdata->type].devt_type, fdev->id); + + dfl_fpga_dev_for_each_feature(fdata, feature) + feature->dev = fdev; + + ret = platform_device_add_resources(fdev, fdata->resources, + fdata->resource_num); + if (ret) + goto err_put_dev; + + pdata.fdata = fdata; + ret = platform_device_add_data(fdev, &pdata, sizeof(pdata)); + if (ret) + goto err_put_dev; + + ret = platform_device_add(fdev); + if (ret) + goto err_put_dev; + + return 0; + +err_put_dev: + platform_device_put(fdev); + + fdata->dev = NULL; + + dfl_fpga_dev_for_each_feature(fdata, feature) + feature->dev = NULL; return ret; } -static int -build_info_create_dev(struct build_feature_devs_info *binfo, - enum dfl_id_type type) +static void feature_dev_unregister(struct dfl_feature_dev_data *fdata) { - struct platform_device *fdev; + struct dfl_feature *feature; - if (type >= DFL_ID_MAX) - return -EINVAL; + platform_device_unregister(fdata->dev); - /* - * we use -ENODEV as the initialization indicator which indicates - * whether the id need to be reclaimed - */ - fdev = platform_device_alloc(dfl_devs[type].name, -ENODEV); - if (!fdev) - return -ENOMEM; + fdata->dev = NULL; - binfo->feature_dev = fdev; - binfo->feature_num = 0; + dfl_fpga_dev_for_each_feature(fdata, feature) + feature->dev = NULL; +} - INIT_LIST_HEAD(&binfo->sub_features); +static int build_info_commit_dev(struct build_feature_devs_info *binfo) +{ + struct dfl_feature_dev_data *fdata; + int ret; - fdev->id = dfl_id_alloc(type, &fdev->dev); - if (fdev->id < 0) - return fdev->id; + fdata = binfo_create_feature_dev_data(binfo); + if (IS_ERR(fdata)) + return PTR_ERR(fdata); - fdev->dev.parent = &binfo->cdev->region->dev; - fdev->dev.devt = dfl_get_devt(dfl_devs[type].devt_type, fdev->id); + ret = feature_dev_register(fdata); + if (ret) + return ret; + + if (binfo->type == PORT_ID) + dfl_fpga_cdev_add_port_data(binfo->cdev, fdata); + else + binfo->cdev->fme_dev = get_device(&fdata->dev->dev); + + /* reset the binfo for next FIU */ + binfo->type = DFL_ID_MAX; return 0; } @@ -921,22 +948,11 @@ static void build_info_free(struct build_feature_devs_info *binfo) { struct dfl_feature_info *finfo, *p; - /* - * it is a valid id, free it. See comments in - * build_info_create_dev() - */ - if (binfo->feature_dev && binfo->feature_dev->id >= 0) { - dfl_id_free(feature_dev_id_type(binfo->feature_dev), - binfo->feature_dev->id); - - list_for_each_entry_safe(finfo, p, &binfo->sub_features, node) { - list_del(&finfo->node); - kfree(finfo); - } + list_for_each_entry_safe(finfo, p, &binfo->sub_features, node) { + list_del(&finfo->node); + kfree(finfo); } - platform_device_put(binfo->feature_dev); - devm_kfree(binfo->dev, binfo); } @@ -1025,7 +1041,7 @@ static int parse_feature_irqs(struct build_feature_devs_info *binfo, * Instead, features with interrupt functionality provide * the information in feature specific registers. */ - type = feature_dev_id_type(binfo->feature_dev); + type = binfo->type; if (type == PORT_ID) { switch (fid) { case PORT_FEATURE_ID_UINT: @@ -1217,7 +1233,7 @@ static int parse_feature_port_afu(struct build_feature_devs_info *binfo, return create_feature_instance(binfo, ofst, size, FEATURE_ID_AFU); } -#define is_feature_dev_detected(binfo) (!!(binfo)->feature_dev) +#define is_feature_dev_detected(binfo) ((binfo)->type != DFL_ID_MAX) static int parse_feature_afu(struct build_feature_devs_info *binfo, resource_size_t ofst) @@ -1227,12 +1243,11 @@ static int parse_feature_afu(struct build_feature_devs_info *binfo, return -EINVAL; } - switch (feature_dev_id_type(binfo->feature_dev)) { + switch (binfo->type) { case PORT_ID: return parse_feature_port_afu(binfo, ofst); default: - dev_info(binfo->dev, "AFU belonging to FIU %s is not supported yet.\n", - binfo->feature_dev->name); + dev_info(binfo->dev, "AFU belonging to FIU is not supported yet.\n"); } return 0; @@ -1273,6 +1288,7 @@ static void build_info_complete(struct build_feature_devs_info *binfo) static int parse_feature_fiu(struct build_feature_devs_info *binfo, resource_size_t ofst) { + enum dfl_id_type type; int ret = 0; u32 offset; u16 id; @@ -1294,10 +1310,13 @@ static int parse_feature_fiu(struct build_feature_devs_info *binfo, v = readq(binfo->ioaddr + DFH); id = FIELD_GET(DFH_ID, v); - /* create platform device for dfl feature dev */ - ret = build_info_create_dev(binfo, dfh_id_to_type(id)); - if (ret) - return ret; + type = dfh_id_to_type(id); + if (type >= DFL_ID_MAX) + return -EINVAL; + + binfo->type = type; + binfo->feature_num = 0; + INIT_LIST_HEAD(&binfo->sub_features); ret = create_feature_instance(binfo, 0, 0, 0); if (ret) @@ -1515,13 +1534,9 @@ EXPORT_SYMBOL_GPL(dfl_fpga_enum_info_add_irq); static int remove_feature_dev(struct device *dev, void *data) { - struct platform_device *pdev = to_platform_device(dev); - enum dfl_id_type type = feature_dev_id_type(pdev); - int id = pdev->id; + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev); - platform_device_unregister(pdev); - - dfl_id_free(type, id); + feature_dev_unregister(fdata); return 0; } @@ -1573,6 +1588,7 @@ dfl_fpga_feature_devs_enumerate(struct dfl_fpga_enum_info *info) goto unregister_region_exit; } + binfo->type = DFL_ID_MAX; binfo->dev = info->dev; binfo->cdev = cdev; @@ -1614,25 +1630,10 @@ EXPORT_SYMBOL_GPL(dfl_fpga_feature_devs_enumerate); */ void dfl_fpga_feature_devs_remove(struct dfl_fpga_cdev *cdev) { - struct dfl_feature_platform_data *pdata, *ptmp; - mutex_lock(&cdev->lock); if (cdev->fme_dev) put_device(cdev->fme_dev); - list_for_each_entry_safe(pdata, ptmp, &cdev->port_dev_list, node) { - struct platform_device *port_dev = pdata->dev; - - /* remove released ports */ - if (!device_is_registered(&port_dev->dev)) { - dfl_id_free(feature_dev_id_type(port_dev), - port_dev->id); - platform_device_put(port_dev); - } - - list_del(&pdata->node); - put_device(&port_dev->dev); - } mutex_unlock(&cdev->lock); remove_feature_devs(cdev); @@ -1643,7 +1644,7 @@ void dfl_fpga_feature_devs_remove(struct dfl_fpga_cdev *cdev) EXPORT_SYMBOL_GPL(dfl_fpga_feature_devs_remove); /** - * __dfl_fpga_cdev_find_port - find a port under given container device + * __dfl_fpga_cdev_find_port_data - find a port under given container device * * @cdev: container device * @data: data passed to match function @@ -1656,23 +1657,20 @@ EXPORT_SYMBOL_GPL(dfl_fpga_feature_devs_remove); * * NOTE: you will need to drop the device reference with put_device() after use. */ -struct platform_device * -__dfl_fpga_cdev_find_port(struct dfl_fpga_cdev *cdev, void *data, - int (*match)(struct platform_device *, void *)) +struct dfl_feature_dev_data * +__dfl_fpga_cdev_find_port_data(struct dfl_fpga_cdev *cdev, void *data, + int (*match)(struct dfl_feature_dev_data *, void *)) { - struct dfl_feature_platform_data *pdata; - struct platform_device *port_dev; + struct dfl_feature_dev_data *fdata; - list_for_each_entry(pdata, &cdev->port_dev_list, node) { - port_dev = pdata->dev; - - if (match(port_dev, data) && get_device(&port_dev->dev)) - return port_dev; + list_for_each_entry(fdata, &cdev->port_dev_list, node) { + if (match(fdata, data)) + return fdata; } return NULL; } -EXPORT_SYMBOL_GPL(__dfl_fpga_cdev_find_port); +EXPORT_SYMBOL_GPL(__dfl_fpga_cdev_find_port_data); static int __init dfl_fpga_init(void) { @@ -1706,33 +1704,28 @@ static int __init dfl_fpga_init(void) */ int dfl_fpga_cdev_release_port(struct dfl_fpga_cdev *cdev, int port_id) { - struct dfl_feature_platform_data *pdata; - struct platform_device *port_pdev; + struct dfl_feature_dev_data *fdata; int ret = -ENODEV; mutex_lock(&cdev->lock); - port_pdev = __dfl_fpga_cdev_find_port(cdev, &port_id, - dfl_fpga_check_port_id); - if (!port_pdev) + fdata = __dfl_fpga_cdev_find_port_data(cdev, &port_id, + dfl_fpga_check_port_id); + if (!fdata) goto unlock_exit; - if (!device_is_registered(&port_pdev->dev)) { + if (!fdata->dev) { ret = -EBUSY; - goto put_dev_exit; + goto unlock_exit; } - pdata = dev_get_platdata(&port_pdev->dev); - - mutex_lock(&pdata->lock); - ret = dfl_feature_dev_use_begin(pdata, true); - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + ret = dfl_feature_dev_use_begin(fdata, true); + mutex_unlock(&fdata->lock); if (ret) - goto put_dev_exit; + goto unlock_exit; - platform_device_del(port_pdev); + feature_dev_unregister(fdata); cdev->released_port_num++; -put_dev_exit: - put_device(&port_pdev->dev); unlock_exit: mutex_unlock(&cdev->lock); return ret; @@ -1752,34 +1745,29 @@ EXPORT_SYMBOL_GPL(dfl_fpga_cdev_release_port); */ int dfl_fpga_cdev_assign_port(struct dfl_fpga_cdev *cdev, int port_id) { - struct dfl_feature_platform_data *pdata; - struct platform_device *port_pdev; + struct dfl_feature_dev_data *fdata; int ret = -ENODEV; mutex_lock(&cdev->lock); - port_pdev = __dfl_fpga_cdev_find_port(cdev, &port_id, - dfl_fpga_check_port_id); - if (!port_pdev) + fdata = __dfl_fpga_cdev_find_port_data(cdev, &port_id, + dfl_fpga_check_port_id); + if (!fdata) goto unlock_exit; - if (device_is_registered(&port_pdev->dev)) { + if (fdata->dev) { ret = -EBUSY; - goto put_dev_exit; + goto unlock_exit; } - ret = platform_device_add(port_pdev); + ret = feature_dev_register(fdata); if (ret) - goto put_dev_exit; + goto unlock_exit; - pdata = dev_get_platdata(&port_pdev->dev); - - mutex_lock(&pdata->lock); - dfl_feature_dev_use_end(pdata); - mutex_unlock(&pdata->lock); + mutex_lock(&fdata->lock); + dfl_feature_dev_use_end(fdata); + mutex_unlock(&fdata->lock); cdev->released_port_num--; -put_dev_exit: - put_device(&port_pdev->dev); unlock_exit: mutex_unlock(&cdev->lock); return ret; @@ -1789,10 +1777,11 @@ EXPORT_SYMBOL_GPL(dfl_fpga_cdev_assign_port); static void config_port_access_mode(struct device *fme_dev, int port_id, bool is_vf) { + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(fme_dev); void __iomem *base; u64 v; - base = dfl_get_feature_ioaddr_by_id(fme_dev, FME_FEATURE_ID_HEADER); + base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER); v = readq(base + FME_HDR_PORT_OFST(port_id)); @@ -1816,14 +1805,14 @@ static void config_port_access_mode(struct device *fme_dev, int port_id, */ void dfl_fpga_cdev_config_ports_pf(struct dfl_fpga_cdev *cdev) { - struct dfl_feature_platform_data *pdata; + struct dfl_feature_dev_data *fdata; mutex_lock(&cdev->lock); - list_for_each_entry(pdata, &cdev->port_dev_list, node) { - if (device_is_registered(&pdata->dev->dev)) + list_for_each_entry(fdata, &cdev->port_dev_list, node) { + if (fdata->dev) continue; - config_port_pf_mode(cdev->fme_dev, pdata->id); + config_port_pf_mode(cdev->fme_dev, fdata->id); } mutex_unlock(&cdev->lock); } @@ -1842,7 +1831,7 @@ EXPORT_SYMBOL_GPL(dfl_fpga_cdev_config_ports_pf); */ int dfl_fpga_cdev_config_ports_vf(struct dfl_fpga_cdev *cdev, int num_vfs) { - struct dfl_feature_platform_data *pdata; + struct dfl_feature_dev_data *fdata; int ret = 0; mutex_lock(&cdev->lock); @@ -1856,11 +1845,11 @@ int dfl_fpga_cdev_config_ports_vf(struct dfl_fpga_cdev *cdev, int num_vfs) goto done; } - list_for_each_entry(pdata, &cdev->port_dev_list, node) { - if (device_is_registered(&pdata->dev->dev)) + list_for_each_entry(fdata, &cdev->port_dev_list, node) { + if (fdata->dev) continue; - config_port_vf_mode(cdev->fme_dev, pdata->id); + config_port_vf_mode(cdev->fme_dev, fdata->id); } done: mutex_unlock(&cdev->lock); @@ -1993,7 +1982,7 @@ long dfl_feature_ioctl_set_irq(struct platform_device *pdev, struct dfl_feature *feature, unsigned long arg) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev); struct dfl_fpga_irq_set hdr; s32 *fds; long ret; @@ -2013,9 +2002,9 @@ long dfl_feature_ioctl_set_irq(struct platform_device *pdev, if (IS_ERR(fds)) return PTR_ERR(fds); - mutex_lock(&pdata->lock); + mutex_lock(&fdata->lock); ret = dfl_fpga_set_irq_triggers(feature, hdr.start, hdr.count, fds); - mutex_unlock(&pdata->lock); + mutex_unlock(&fdata->lock); kfree(fds); return ret; diff --git a/drivers/fpga/dfl.h b/drivers/fpga/dfl.h index 5063d73b0d82..95539f1213cb 100644 --- a/drivers/fpga/dfl.h +++ b/drivers/fpga/dfl.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -206,6 +207,8 @@ #define PORT_UINT_CAP_INT_NUM GENMASK_ULL(11, 0) /* Interrupts num */ #define PORT_UINT_CAP_FST_VECT GENMASK_ULL(23, 12) /* First Vector */ +struct dfl_feature_dev_data; + /** * struct dfl_fpga_port_ops - port ops * @@ -219,15 +222,15 @@ struct dfl_fpga_port_ops { const char *name; struct module *owner; struct list_head node; - int (*get_id)(struct platform_device *pdev); - int (*enable_set)(struct platform_device *pdev, bool enable); + int (*get_id)(struct dfl_feature_dev_data *fdata); + int (*enable_set)(struct dfl_feature_dev_data *fdata, bool enable); }; void dfl_fpga_port_ops_add(struct dfl_fpga_port_ops *ops); void dfl_fpga_port_ops_del(struct dfl_fpga_port_ops *ops); -struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct platform_device *pdev); +struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct dfl_feature_dev_data *fdata); void dfl_fpga_port_ops_put(struct dfl_fpga_port_ops *ops); -int dfl_fpga_check_port_id(struct platform_device *pdev, void *pport_id); +int dfl_fpga_check_port_id(struct dfl_feature_dev_data *fdata, void *pport_id); /** * struct dfl_feature_id - dfl private feature id @@ -300,26 +303,32 @@ struct dfl_feature { #define FEATURE_DEV_ID_UNUSED (-1) /** - * struct dfl_feature_platform_data - platform data for feature devices + * struct dfl_feature_dev_data - dfl enumeration data for dfl feature dev. * - * @node: node to link feature devs to container device's port_dev_list. - * @lock: mutex to protect platform data. - * @cdev: cdev of feature dev. - * @dev: ptr to platform device linked with this platform data. + * @node: node to link the data structure to container device's port_dev_list. + * @lock: mutex to protect feature dev data. + * @dev: ptr to the feature's platform device linked with this structure. + * @type: type of DFL FIU for the feature dev. See enum dfl_id_type. + * @pdev_id: platform device id for the feature dev. + * @pdev_name: platform device name for the feature dev. * @dfl_cdev: ptr to container device. - * @id: id used for this feature device. + * @id: id used for the feature device. * @disable_count: count for port disable. * @excl_open: set on feature device exclusive open. * @open_count: count for feature device open. * @num: number for sub features. * @private: ptr to feature dev private data. - * @features: sub features of this feature dev. + * @features: sub features for the feature dev. + * @resource_num: number of resources for the feature dev. + * @resources: resources for the feature dev. */ -struct dfl_feature_platform_data { +struct dfl_feature_dev_data { struct list_head node; struct mutex lock; - struct cdev cdev; struct platform_device *dev; + enum dfl_id_type type; + int pdev_id; + const char *pdev_name; struct dfl_fpga_cdev *dfl_cdev; int id; unsigned int disable_count; @@ -327,55 +336,68 @@ struct dfl_feature_platform_data { int open_count; void *private; int num; - struct dfl_feature features[]; + struct dfl_feature *features; + int resource_num; + struct resource *resources; +}; + +/** + * struct dfl_feature_platform_data - platform data for feature devices + * + * @cdev: cdev of feature dev. + * @fdata: dfl enumeration data for the dfl feature device. + */ +struct dfl_feature_platform_data { + struct cdev cdev; + struct dfl_feature_dev_data *fdata; }; static inline -int dfl_feature_dev_use_begin(struct dfl_feature_platform_data *pdata, +int dfl_feature_dev_use_begin(struct dfl_feature_dev_data *fdata, bool excl) { - if (pdata->excl_open) + if (fdata->excl_open) return -EBUSY; if (excl) { - if (pdata->open_count) + if (fdata->open_count) return -EBUSY; - pdata->excl_open = true; + fdata->excl_open = true; } - pdata->open_count++; + fdata->open_count++; return 0; } static inline -void dfl_feature_dev_use_end(struct dfl_feature_platform_data *pdata) +void dfl_feature_dev_use_end(struct dfl_feature_dev_data *fdata) { - pdata->excl_open = false; + fdata->excl_open = false; - if (WARN_ON(pdata->open_count <= 0)) + if (WARN_ON(fdata->open_count <= 0)) return; - pdata->open_count--; + fdata->open_count--; } static inline -int dfl_feature_dev_use_count(struct dfl_feature_platform_data *pdata) +int dfl_feature_dev_use_count(struct dfl_feature_dev_data *fdata) { - return pdata->open_count; + return fdata->open_count; } static inline -void dfl_fpga_pdata_set_private(struct dfl_feature_platform_data *pdata, +void dfl_fpga_fdata_set_private(struct dfl_feature_dev_data *fdata, void *private) { - pdata->private = private; + fdata->private = private; } static inline -void *dfl_fpga_pdata_get_private(struct dfl_feature_platform_data *pdata) +void *dfl_fpga_fdata_get_private(struct dfl_feature_dev_data *fdata) { - return pdata->private; + return fdata->private; } struct dfl_feature_ops { @@ -398,37 +420,36 @@ int dfl_fpga_dev_ops_register(struct platform_device *pdev, struct module *owner); void dfl_fpga_dev_ops_unregister(struct platform_device *pdev); -static inline -struct platform_device *dfl_fpga_inode_to_feature_dev(struct inode *inode) +static inline struct dfl_feature_dev_data * +dfl_fpga_inode_to_feature_dev_data(struct inode *inode) { struct dfl_feature_platform_data *pdata; pdata = container_of(inode->i_cdev, struct dfl_feature_platform_data, cdev); - return pdata->dev; + return pdata->fdata; } -#define dfl_fpga_dev_for_each_feature(pdata, feature) \ - for ((feature) = (pdata)->features; \ - (feature) < (pdata)->features + (pdata)->num; (feature)++) +#define dfl_fpga_dev_for_each_feature(fdata, feature) \ + for ((feature) = (fdata)->features; \ + (feature) < (fdata)->features + (fdata)->num; (feature)++) -static inline -struct dfl_feature *dfl_get_feature_by_id(struct device *dev, u16 id) +static inline struct dfl_feature * +dfl_get_feature_by_id(struct dfl_feature_dev_data *fdata, u16 id) { - struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); struct dfl_feature *feature; - dfl_fpga_dev_for_each_feature(pdata, feature) + dfl_fpga_dev_for_each_feature(fdata, feature) if (feature->id == id) return feature; return NULL; } -static inline -void __iomem *dfl_get_feature_ioaddr_by_id(struct device *dev, u16 id) +static inline void __iomem * +dfl_get_feature_ioaddr_by_id(struct dfl_feature_dev_data *fdata, u16 id) { - struct dfl_feature *feature = dfl_get_feature_by_id(dev, id); + struct dfl_feature *feature = dfl_get_feature_by_id(fdata, id); if (feature && feature->ioaddr) return feature->ioaddr; @@ -437,10 +458,18 @@ void __iomem *dfl_get_feature_ioaddr_by_id(struct device *dev, u16 id) return NULL; } -static inline -struct device *dfl_fpga_pdata_to_parent(struct dfl_feature_platform_data *pdata) +static inline struct dfl_feature_dev_data * +to_dfl_feature_dev_data(struct device *dev) { - return pdata->dev->dev.parent->parent; + struct dfl_feature_platform_data *pdata = dev_get_platdata(dev); + + return pdata->fdata; +} + +static inline +struct device *dfl_fpga_fdata_to_parent(struct dfl_feature_dev_data *fdata) +{ + return fdata->dev->dev.parent->parent; } static inline bool dfl_feature_is_fme(void __iomem *base) @@ -522,26 +551,21 @@ struct dfl_fpga_cdev * dfl_fpga_feature_devs_enumerate(struct dfl_fpga_enum_info *info); void dfl_fpga_feature_devs_remove(struct dfl_fpga_cdev *cdev); -/* - * need to drop the device reference with put_device() after use port platform - * device returned by __dfl_fpga_cdev_find_port and dfl_fpga_cdev_find_port - * functions. - */ -struct platform_device * -__dfl_fpga_cdev_find_port(struct dfl_fpga_cdev *cdev, void *data, - int (*match)(struct platform_device *, void *)); +struct dfl_feature_dev_data * +__dfl_fpga_cdev_find_port_data(struct dfl_fpga_cdev *cdev, void *data, + int (*match)(struct dfl_feature_dev_data *, void *)); -static inline struct platform_device * -dfl_fpga_cdev_find_port(struct dfl_fpga_cdev *cdev, void *data, - int (*match)(struct platform_device *, void *)) +static inline struct dfl_feature_dev_data * +dfl_fpga_cdev_find_port_data(struct dfl_fpga_cdev *cdev, void *data, + int (*match)(struct dfl_feature_dev_data *, void *)) { - struct platform_device *pdev; + struct dfl_feature_dev_data *fdata; mutex_lock(&cdev->lock); - pdev = __dfl_fpga_cdev_find_port(cdev, data, match); + fdata = __dfl_fpga_cdev_find_port_data(cdev, data, match); mutex_unlock(&cdev->lock); - return pdev; + return fdata; } int dfl_fpga_cdev_release_port(struct dfl_fpga_cdev *cdev, int port_id); diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 93ee3aa092f8..add5ad29a673 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -529,9 +529,9 @@ config GPIO_OCTEON family of SOCs. config GPIO_OMAP - tristate "TI OMAP GPIO support" if ARCH_OMAP2PLUS || COMPILE_TEST + tristate "TI OMAP GPIO support" + depends on ARCH_OMAP || COMPILE_TEST default y if ARCH_OMAP - depends on ARM select GENERIC_IRQ_CHIP select GPIOLIB_IRQCHIP help diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c index 73e660c5e38a..17ab039c7413 100644 --- a/drivers/gpio/gpio-altera.c +++ b/drivers/gpio/gpio-altera.c @@ -32,14 +32,12 @@ * will be blocked until the current one completes. * @interrupt_trigger : specifies the hardware configured IRQ trigger type * (rising, falling, both, high) -* @mapped_irq : kernel mapped irq number. */ struct altera_gpio_chip { struct gpio_chip gc; void __iomem *regs; raw_spinlock_t gpio_lock; int interrupt_trigger; - int mapped_irq; }; static void altera_gpio_irq_unmask(struct irq_data *d) @@ -235,6 +233,7 @@ static int altera_gpio_probe(struct platform_device *pdev) int reg, ret; struct altera_gpio_chip *altera_gc; struct gpio_irq_chip *girq; + int mapped_irq; altera_gc = devm_kzalloc(&pdev->dev, sizeof(*altera_gc), GFP_KERNEL); if (!altera_gc) @@ -271,8 +270,8 @@ static int altera_gpio_probe(struct platform_device *pdev) if (IS_ERR(altera_gc->regs)) return dev_err_probe(dev, PTR_ERR(altera_gc->regs), "failed to ioremap memory resource\n"); - altera_gc->mapped_irq = platform_get_irq_optional(pdev, 0); - if (altera_gc->mapped_irq < 0) + mapped_irq = platform_get_irq_optional(pdev, 0); + if (mapped_irq < 0) goto skip_irq; if (device_property_read_u32(dev, "altr,interrupt-type", ®)) { @@ -296,7 +295,7 @@ static int altera_gpio_probe(struct platform_device *pdev) return -ENOMEM; girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_bad_irq; - girq->parents[0] = altera_gc->mapped_irq; + girq->parents[0] = mapped_irq; skip_irq: ret = devm_gpiochip_add_data(dev, &altera_gc->gc, altera_gc); diff --git a/drivers/gpio/gpio-loongson-64bit.c b/drivers/gpio/gpio-loongson-64bit.c index 6749d4dd6d64..7f4d78fd800e 100644 --- a/drivers/gpio/gpio-loongson-64bit.c +++ b/drivers/gpio/gpio-loongson-64bit.c @@ -237,9 +237,9 @@ static const struct loongson_gpio_chip_data loongson_gpio_ls2k2000_data1 = { static const struct loongson_gpio_chip_data loongson_gpio_ls2k2000_data2 = { .label = "ls2k2000_gpio", .mode = BIT_CTRL_MODE, - .conf_offset = 0x84, - .in_offset = 0x88, - .out_offset = 0x80, + .conf_offset = 0x4, + .in_offset = 0x8, + .out_offset = 0x0, }; static const struct loongson_gpio_chip_data loongson_gpio_ls3a5000_data = { diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c index 24417c3247b0..0cd4c36ae8aa 100644 --- a/drivers/gpio/gpio-mpc8xxx.c +++ b/drivers/gpio/gpio-mpc8xxx.c @@ -285,6 +285,7 @@ static const struct mpc8xxx_gpio_devtype mpc8xxx_gpio_devtype_default = { }; static const struct of_device_id mpc8xxx_gpio_ids[] = { + { .compatible = "fsl,mpc8314-gpio", }, { .compatible = "fsl,mpc8349-gpio", }, { .compatible = "fsl,mpc8572-gpio", .data = &mpc8572_gpio_devtype, }, { .compatible = "fsl,mpc8610-gpio", }, diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c index 4cb455b2bdee..619b6fb9d833 100644 --- a/drivers/gpio/gpio-mxc.c +++ b/drivers/gpio/gpio-mxc.c @@ -490,8 +490,7 @@ static int mxc_gpio_probe(struct platform_device *pdev) port->gc.request = mxc_gpio_request; port->gc.free = mxc_gpio_free; port->gc.to_irq = mxc_gpio_to_irq; - port->gc.base = (pdev->id < 0) ? of_alias_get_id(np, "gpio") * 32 : - pdev->id * 32; + port->gc.base = of_alias_get_id(np, "gpio") * 32; err = devm_gpiochip_add_data(&pdev->dev, &port->gc, port); if (err) diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 272febc3230e..be4c9981ebc4 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -1088,7 +1088,8 @@ static int pca953x_probe(struct i2c_client *client) */ reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(reset_gpio)) - return PTR_ERR(reset_gpio); + return dev_err_probe(dev, PTR_ERR(reset_gpio), + "Failed to get reset gpio\n"); } chip->client = client; diff --git a/drivers/gpio/gpio-regmap.c b/drivers/gpio/gpio-regmap.c index 71684dee2ca5..05f8781b5204 100644 --- a/drivers/gpio/gpio-regmap.c +++ b/drivers/gpio/gpio-regmap.c @@ -262,6 +262,8 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config chip->label = config->label ?: dev_name(config->parent); chip->can_sleep = regmap_might_sleep(config->regmap); + chip->request = gpiochip_generic_request; + chip->free = gpiochip_generic_free; chip->get = gpio_regmap_get; if (gpio->reg_set_base && gpio->reg_clr_base) chip->set = gpio_regmap_set_with_clear; diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index f387dad81f29..a086087ada17 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -413,11 +413,6 @@ static int gpio_sim_setup_sysfs(struct gpio_sim_chip *chip) return devm_add_action_or_reset(dev, gpio_sim_sysfs_remove, chip); } -static int gpio_sim_dev_match_fwnode(struct device *dev, void *data) -{ - return device_match_fwnode(dev, data); -} - static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) { struct gpio_sim_chip *chip; @@ -503,7 +498,7 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) if (ret) return ret; - chip->dev = device_find_child(dev, swnode, gpio_sim_dev_match_fwnode); + chip->dev = device_find_child(dev, swnode, device_match_fwnode); if (!chip->dev) return -ENODEV; @@ -1027,6 +1022,30 @@ static void gpio_sim_device_deactivate(struct gpio_sim_device *dev) dev->pdev = NULL; } +static void +gpio_sim_device_lockup_configfs(struct gpio_sim_device *dev, bool lock) +{ + struct configfs_subsystem *subsys = dev->group.cg_subsys; + struct gpio_sim_bank *bank; + struct gpio_sim_line *line; + + /* + * The device only needs to depend on leaf line entries. This is + * sufficient to lock up all the configfs entries that the + * instantiated, alive device depends on. + */ + list_for_each_entry(bank, &dev->bank_list, siblings) { + list_for_each_entry(line, &bank->line_list, siblings) { + if (lock) + WARN_ON(configfs_depend_item_unlocked( + subsys, &line->group.cg_item)); + else + configfs_undepend_item_unlocked( + &line->group.cg_item); + } + } +} + static ssize_t gpio_sim_device_config_live_store(struct config_item *item, const char *page, size_t count) @@ -1039,14 +1058,24 @@ gpio_sim_device_config_live_store(struct config_item *item, if (ret) return ret; - guard(mutex)(&dev->lock); + if (live) + gpio_sim_device_lockup_configfs(dev, true); - if (live == gpio_sim_device_is_live(dev)) - ret = -EPERM; - else if (live) - ret = gpio_sim_device_activate(dev); - else - gpio_sim_device_deactivate(dev); + scoped_guard(mutex, &dev->lock) { + if (live == gpio_sim_device_is_live(dev)) + ret = -EPERM; + else if (live) + ret = gpio_sim_device_activate(dev); + else + gpio_sim_device_deactivate(dev); + } + + /* + * Undepend is required only if device disablement (live == 0) + * succeeds or if device enablement (live == 1) fails. + */ + if (live == !!ret) + gpio_sim_device_lockup_configfs(dev, false); return ret ?: count; } diff --git a/drivers/gpio/gpio-tps65219.c b/drivers/gpio/gpio-tps65219.c index cd1f17041f8c..526640c39a11 100644 --- a/drivers/gpio/gpio-tps65219.c +++ b/drivers/gpio/gpio-tps65219.c @@ -15,8 +15,6 @@ #define TPS65219_GPIO0_DIR_MASK BIT(3) #define TPS65219_GPIO0_OFFSET 2 #define TPS65219_GPIO0_IDX 0 -#define TPS65219_GPIO_DIR_IN 1 -#define TPS65219_GPIO_DIR_OUT 0 struct tps65219_gpio { struct gpio_chip gpio_chip; @@ -61,7 +59,7 @@ static int tps65219_gpio_get(struct gpio_chip *gc, unsigned int offset) * status bit. */ - if (tps65219_gpio_get_direction(gc, offset) == TPS65219_GPIO_DIR_OUT) + if (tps65219_gpio_get_direction(gc, offset) == GPIO_LINE_DIRECTION_OUT) return -ENOTSUPP; return ret; @@ -124,10 +122,10 @@ static int tps65219_gpio_direction_input(struct gpio_chip *gc, unsigned int offs return -ENOTSUPP; } - if (tps65219_gpio_get_direction(gc, offset) == TPS65219_GPIO_DIR_IN) + if (tps65219_gpio_get_direction(gc, offset) == GPIO_LINE_DIRECTION_IN) return 0; - return tps65219_gpio_change_direction(gc, offset, TPS65219_GPIO_DIR_IN); + return tps65219_gpio_change_direction(gc, offset, GPIO_LINE_DIRECTION_IN); } static int tps65219_gpio_direction_output(struct gpio_chip *gc, unsigned int offset, int value) @@ -136,10 +134,10 @@ static int tps65219_gpio_direction_output(struct gpio_chip *gc, unsigned int off if (offset != TPS65219_GPIO0_IDX) return 0; - if (tps65219_gpio_get_direction(gc, offset) == TPS65219_GPIO_DIR_OUT) + if (tps65219_gpio_get_direction(gc, offset) == GPIO_LINE_DIRECTION_OUT) return 0; - return tps65219_gpio_change_direction(gc, offset, TPS65219_GPIO_DIR_OUT); + return tps65219_gpio_change_direction(gc, offset, GPIO_LINE_DIRECTION_OUT); } static const struct gpio_chip tps65219_template_chip = { diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c index 5e26eb3adabb..18f523a15b3c 100644 --- a/drivers/gpio/gpio-tqmx86.c +++ b/drivers/gpio/gpio-tqmx86.c @@ -29,18 +29,22 @@ #define TQMX86_GPIIC 3 /* GPI Interrupt Configuration Register */ #define TQMX86_GPIIS 4 /* GPI Interrupt Status Register */ -#define TQMX86_GPII_NONE 0 -#define TQMX86_GPII_FALLING BIT(0) -#define TQMX86_GPII_RISING BIT(1) -/* Stored in irq_type as a trigger type, but not actually valid as a register - * value, so the name doesn't use "GPII" +/* + * NONE, FALLING and RISING use the same bit patterns that can be programmed to + * the GPII register (after passing them to the TQMX86_GPII_ macros to shift + * them to the right position) */ -#define TQMX86_INT_BOTH (BIT(0) | BIT(1)) -#define TQMX86_GPII_MASK (BIT(0) | BIT(1)) -#define TQMX86_GPII_BITS 2 +#define TQMX86_INT_TRIG_NONE 0 +#define TQMX86_INT_TRIG_FALLING BIT(0) +#define TQMX86_INT_TRIG_RISING BIT(1) +#define TQMX86_INT_TRIG_BOTH (BIT(0) | BIT(1)) +#define TQMX86_INT_TRIG_MASK (BIT(0) | BIT(1)) /* Stored in irq_type with GPII bits */ #define TQMX86_INT_UNMASKED BIT(2) +#define TQMX86_GPIIC_CONFIG(i, v) ((v) << (2 * (i))) +#define TQMX86_GPIIC_MASK(i) TQMX86_GPIIC_CONFIG(i, TQMX86_INT_TRIG_MASK) + struct tqmx86_gpio_data { struct gpio_chip chip; void __iomem *io_base; @@ -48,7 +52,7 @@ struct tqmx86_gpio_data { /* Lock must be held for accessing output and irq_type fields */ raw_spinlock_t spinlock; DECLARE_BITMAP(output, TQMX86_NGPIO); - u8 irq_type[TQMX86_NGPI]; + u8 irq_type[TQMX86_NGPIO]; }; static u8 tqmx86_gpio_read(struct tqmx86_gpio_data *gd, unsigned int reg) @@ -62,6 +66,18 @@ static void tqmx86_gpio_write(struct tqmx86_gpio_data *gd, u8 val, iowrite8(val, gd->io_base + reg); } +static void tqmx86_gpio_clrsetbits(struct tqmx86_gpio_data *gpio, + u8 clr, u8 set, unsigned int reg) + __must_hold(&gpio->spinlock) +{ + u8 val = tqmx86_gpio_read(gpio, reg); + + val &= ~clr; + val |= set; + + tqmx86_gpio_write(gpio, val, reg); +} + static int tqmx86_gpio_get(struct gpio_chip *chip, unsigned int offset) { struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); @@ -69,127 +85,137 @@ static int tqmx86_gpio_get(struct gpio_chip *chip, unsigned int offset) return !!(tqmx86_gpio_read(gpio, TQMX86_GPIOD) & BIT(offset)); } +static void _tqmx86_gpio_set(struct tqmx86_gpio_data *gpio, unsigned int offset, + int value) + __must_hold(&gpio->spinlock) +{ + __assign_bit(offset, gpio->output, value); + tqmx86_gpio_write(gpio, bitmap_get_value8(gpio->output, 0), TQMX86_GPIOD); +} + static void tqmx86_gpio_set(struct gpio_chip *chip, unsigned int offset, int value) { struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); - unsigned long flags; - raw_spin_lock_irqsave(&gpio->spinlock, flags); - __assign_bit(offset, gpio->output, value); - tqmx86_gpio_write(gpio, bitmap_get_value8(gpio->output, 0), TQMX86_GPIOD); - raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + guard(raw_spinlock_irqsave)(&gpio->spinlock); + + _tqmx86_gpio_set(gpio, offset, value); } static int tqmx86_gpio_direction_input(struct gpio_chip *chip, unsigned int offset) { - /* Direction cannot be changed. Validate is an input. */ - if (BIT(offset) & TQMX86_DIR_INPUT_MASK) - return 0; - else - return -EINVAL; + struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); + + guard(raw_spinlock_irqsave)(&gpio->spinlock); + + tqmx86_gpio_clrsetbits(gpio, BIT(offset), 0, TQMX86_GPIODD); + + return 0; } static int tqmx86_gpio_direction_output(struct gpio_chip *chip, unsigned int offset, int value) { - /* Direction cannot be changed, validate is an output */ - if (BIT(offset) & TQMX86_DIR_INPUT_MASK) - return -EINVAL; + struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); + + guard(raw_spinlock_irqsave)(&gpio->spinlock); + + _tqmx86_gpio_set(gpio, offset, value); + tqmx86_gpio_clrsetbits(gpio, 0, BIT(offset), TQMX86_GPIODD); - tqmx86_gpio_set(chip, offset, value); return 0; } static int tqmx86_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) { - if (TQMX86_DIR_INPUT_MASK & BIT(offset)) - return GPIO_LINE_DIRECTION_IN; + struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); + u8 val; - return GPIO_LINE_DIRECTION_OUT; + val = tqmx86_gpio_read(gpio, TQMX86_GPIODD); + + if (val & BIT(offset)) + return GPIO_LINE_DIRECTION_OUT; + + return GPIO_LINE_DIRECTION_IN; } -static void tqmx86_gpio_irq_config(struct tqmx86_gpio_data *gpio, int offset) +static void tqmx86_gpio_irq_config(struct tqmx86_gpio_data *gpio, int hwirq) __must_hold(&gpio->spinlock) { - u8 type = TQMX86_GPII_NONE, gpiic; + u8 type = TQMX86_INT_TRIG_NONE; + int gpiic_irq = hwirq - TQMX86_NGPO; - if (gpio->irq_type[offset] & TQMX86_INT_UNMASKED) { - type = gpio->irq_type[offset] & TQMX86_GPII_MASK; + if (gpio->irq_type[hwirq] & TQMX86_INT_UNMASKED) { + type = gpio->irq_type[hwirq] & TQMX86_INT_TRIG_MASK; - if (type == TQMX86_INT_BOTH) - type = tqmx86_gpio_get(&gpio->chip, offset + TQMX86_NGPO) - ? TQMX86_GPII_FALLING - : TQMX86_GPII_RISING; + if (type == TQMX86_INT_TRIG_BOTH) + type = tqmx86_gpio_get(&gpio->chip, hwirq) + ? TQMX86_INT_TRIG_FALLING + : TQMX86_INT_TRIG_RISING; } - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~(TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS)); - gpiic |= type << (offset * TQMX86_GPII_BITS); - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + tqmx86_gpio_clrsetbits(gpio, + TQMX86_GPIIC_MASK(gpiic_irq), + TQMX86_GPIIC_CONFIG(gpiic_irq, type), + TQMX86_GPIIC); } static void tqmx86_gpio_irq_mask(struct irq_data *data) { - unsigned int offset = (data->hwirq - TQMX86_NGPO); struct tqmx86_gpio_data *gpio = gpiochip_get_data( irq_data_get_irq_chip_data(data)); - unsigned long flags; - raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpio->irq_type[offset] &= ~TQMX86_INT_UNMASKED; - tqmx86_gpio_irq_config(gpio, offset); - raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + scoped_guard(raw_spinlock_irqsave, &gpio->spinlock) { + gpio->irq_type[data->hwirq] &= ~TQMX86_INT_UNMASKED; + tqmx86_gpio_irq_config(gpio, data->hwirq); + } gpiochip_disable_irq(&gpio->chip, irqd_to_hwirq(data)); } static void tqmx86_gpio_irq_unmask(struct irq_data *data) { - unsigned int offset = (data->hwirq - TQMX86_NGPO); struct tqmx86_gpio_data *gpio = gpiochip_get_data( irq_data_get_irq_chip_data(data)); - unsigned long flags; gpiochip_enable_irq(&gpio->chip, irqd_to_hwirq(data)); - raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpio->irq_type[offset] |= TQMX86_INT_UNMASKED; - tqmx86_gpio_irq_config(gpio, offset); - raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + guard(raw_spinlock_irqsave)(&gpio->spinlock); + + gpio->irq_type[data->hwirq] |= TQMX86_INT_UNMASKED; + tqmx86_gpio_irq_config(gpio, data->hwirq); } static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type) { struct tqmx86_gpio_data *gpio = gpiochip_get_data( irq_data_get_irq_chip_data(data)); - unsigned int offset = (data->hwirq - TQMX86_NGPO); unsigned int edge_type = type & IRQF_TRIGGER_MASK; - unsigned long flags; u8 new_type; switch (edge_type) { case IRQ_TYPE_EDGE_RISING: - new_type = TQMX86_GPII_RISING; + new_type = TQMX86_INT_TRIG_RISING; break; case IRQ_TYPE_EDGE_FALLING: - new_type = TQMX86_GPII_FALLING; + new_type = TQMX86_INT_TRIG_FALLING; break; case IRQ_TYPE_EDGE_BOTH: - new_type = TQMX86_INT_BOTH; + new_type = TQMX86_INT_TRIG_BOTH; break; default: return -EINVAL; /* not supported */ } - raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpio->irq_type[offset] &= ~TQMX86_GPII_MASK; - gpio->irq_type[offset] |= new_type; - tqmx86_gpio_irq_config(gpio, offset); - raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + guard(raw_spinlock_irqsave)(&gpio->spinlock); + + gpio->irq_type[data->hwirq] &= ~TQMX86_INT_TRIG_MASK; + gpio->irq_type[data->hwirq] |= new_type; + tqmx86_gpio_irq_config(gpio, data->hwirq); return 0; } @@ -199,8 +225,8 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc) struct gpio_chip *chip = irq_desc_get_handler_data(desc); struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); struct irq_chip *irq_chip = irq_desc_get_chip(desc); - unsigned long irq_bits, flags; - int i; + unsigned long irq_bits; + int i, hwirq; u8 irq_status; chained_irq_enter(irq_chip, desc); @@ -210,32 +236,38 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc) irq_bits = irq_status; - raw_spin_lock_irqsave(&gpio->spinlock, flags); - for_each_set_bit(i, &irq_bits, TQMX86_NGPI) { - /* - * Edge-both triggers are implemented by flipping the edge - * trigger after each interrupt, as the controller only supports - * either rising or falling edge triggers, but not both. - * - * Internally, the TQMx86 GPIO controller has separate status - * registers for rising and falling edge interrupts. GPIIC - * configures which bits from which register are visible in the - * interrupt status register GPIIS and defines what triggers the - * parent IRQ line. Writing to GPIIS always clears both rising - * and falling interrupt flags internally, regardless of the - * currently configured trigger. - * - * In consequence, we can cleanly implement the edge-both - * trigger in software by first clearing the interrupt and then - * setting the new trigger based on the current GPIO input in - * tqmx86_gpio_irq_config() - even if an edge arrives between - * reading the input and setting the trigger, we will have a new - * interrupt pending. - */ - if ((gpio->irq_type[i] & TQMX86_GPII_MASK) == TQMX86_INT_BOTH) - tqmx86_gpio_irq_config(gpio, i); + scoped_guard(raw_spinlock_irqsave, &gpio->spinlock) { + for_each_set_bit(i, &irq_bits, TQMX86_NGPI) { + hwirq = i + TQMX86_NGPO; + + /* + * Edge-both triggers are implemented by flipping the + * edge trigger after each interrupt, as the controller + * only supports either rising or falling edge triggers, + * but not both. + * + * Internally, the TQMx86 GPIO controller has separate + * status registers for rising and falling edge + * interrupts. GPIIC configures which bits from which + * register are visible in the interrupt status register + * GPIIS and defines what triggers the parent IRQ line. + * Writing to GPIIS always clears both rising and + * falling interrupt flags internally, regardless of the + * currently configured trigger. + * + * In consequence, we can cleanly implement the + * edge-both trigger in software by first clearing the + * interrupt and then setting the new trigger based on + * the current GPIO input in tqmx86_gpio_irq_config() - + * even if an edge arrives between reading the input and + * setting the trigger, we will have a new interrupt + * pending. + */ + if ((gpio->irq_type[hwirq] & TQMX86_INT_TRIG_MASK) == + TQMX86_INT_TRIG_BOTH) + tqmx86_gpio_irq_config(gpio, hwirq); + } } - raw_spin_unlock_irqrestore(&gpio->spinlock, flags); for_each_set_bit(i, &irq_bits, TQMX86_NGPI) generic_handle_domain_irq(gpio->chip.irq.domain, diff --git a/drivers/gpio/gpio-twl6040.c b/drivers/gpio/gpio-twl6040.c index 6c3fbf382dba..b9171bf66168 100644 --- a/drivers/gpio/gpio-twl6040.c +++ b/drivers/gpio/gpio-twl6040.c @@ -22,7 +22,7 @@ static int twl6040gpo_get(struct gpio_chip *chip, unsigned offset) { - struct twl6040 *twl6040 = dev_get_drvdata(chip->parent->parent); + struct twl6040 *twl6040 = gpiochip_get_data(chip); int ret = 0; ret = twl6040_reg_read(twl6040, TWL6040_REG_GPOCTL); @@ -46,7 +46,7 @@ static int twl6040gpo_direction_out(struct gpio_chip *chip, unsigned offset, static void twl6040gpo_set(struct gpio_chip *chip, unsigned offset, int value) { - struct twl6040 *twl6040 = dev_get_drvdata(chip->parent->parent); + struct twl6040 *twl6040 = gpiochip_get_data(chip); int ret; u8 gpoctl; @@ -91,7 +91,7 @@ static int gpo_twl6040_probe(struct platform_device *pdev) twl6040gpo_chip.parent = &pdev->dev; - ret = devm_gpiochip_add_data(&pdev->dev, &twl6040gpo_chip, NULL); + ret = devm_gpiochip_add_data(&pdev->dev, &twl6040gpo_chip, twl6040); if (ret < 0) { dev_err(&pdev->dev, "could not register gpiochip, %d\n", ret); twl6040gpo_chip.ngpio = 0; diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c index 91b6352c957c..e89f299f2140 100644 --- a/drivers/gpio/gpio-virtuser.c +++ b/drivers/gpio/gpio-virtuser.c @@ -1410,7 +1410,7 @@ gpio_virtuser_make_lookup_table(struct gpio_virtuser_device *dev) size_t num_entries = gpio_virtuser_get_lookup_count(dev); struct gpio_virtuser_lookup_entry *entry; struct gpio_virtuser_lookup *lookup; - unsigned int i = 0; + unsigned int i = 0, idx; lockdep_assert_held(&dev->lock); @@ -1424,12 +1424,12 @@ gpio_virtuser_make_lookup_table(struct gpio_virtuser_device *dev) return -ENOMEM; list_for_each_entry(lookup, &dev->lookup_list, siblings) { + idx = 0; list_for_each_entry(entry, &lookup->entry_list, siblings) { - table->table[i] = + table->table[i++] = GPIO_LOOKUP_IDX(entry->key, entry->offset < 0 ? U16_MAX : entry->offset, - lookup->con_id, i, entry->flags); - i++; + lookup->con_id, idx++, entry->flags); } } @@ -1439,6 +1439,15 @@ gpio_virtuser_make_lookup_table(struct gpio_virtuser_device *dev) return 0; } +static void +gpio_virtuser_remove_lookup_table(struct gpio_virtuser_device *dev) +{ + gpiod_remove_lookup_table(dev->lookup_table); + kfree(dev->lookup_table->dev_id); + kfree(dev->lookup_table); + dev->lookup_table = NULL; +} + static struct fwnode_handle * gpio_virtuser_make_device_swnode(struct gpio_virtuser_device *dev) { @@ -1487,10 +1496,8 @@ gpio_virtuser_device_activate(struct gpio_virtuser_device *dev) pdevinfo.fwnode = swnode; ret = gpio_virtuser_make_lookup_table(dev); - if (ret) { - fwnode_remove_software_node(swnode); - return ret; - } + if (ret) + goto err_remove_swnode; reinit_completion(&dev->probe_completion); dev->driver_bound = false; @@ -1498,23 +1505,31 @@ gpio_virtuser_device_activate(struct gpio_virtuser_device *dev) pdev = platform_device_register_full(&pdevinfo); if (IS_ERR(pdev)) { + ret = PTR_ERR(pdev); bus_unregister_notifier(&platform_bus_type, &dev->bus_notifier); - fwnode_remove_software_node(swnode); - return PTR_ERR(pdev); + goto err_remove_lookup_table; } wait_for_completion(&dev->probe_completion); bus_unregister_notifier(&platform_bus_type, &dev->bus_notifier); if (!dev->driver_bound) { - platform_device_unregister(pdev); - fwnode_remove_software_node(swnode); - return -ENXIO; + ret = -ENXIO; + goto err_unregister_pdev; } dev->pdev = pdev; return 0; + +err_unregister_pdev: + platform_device_unregister(pdev); +err_remove_lookup_table: + gpio_virtuser_remove_lookup_table(dev); +err_remove_swnode: + fwnode_remove_software_node(swnode); + + return ret; } static void @@ -1526,10 +1541,33 @@ gpio_virtuser_device_deactivate(struct gpio_virtuser_device *dev) swnode = dev_fwnode(&dev->pdev->dev); platform_device_unregister(dev->pdev); + gpio_virtuser_remove_lookup_table(dev); fwnode_remove_software_node(swnode); dev->pdev = NULL; - gpiod_remove_lookup_table(dev->lookup_table); - kfree(dev->lookup_table); +} + +static void +gpio_virtuser_device_lockup_configfs(struct gpio_virtuser_device *dev, bool lock) +{ + struct configfs_subsystem *subsys = dev->group.cg_subsys; + struct gpio_virtuser_lookup_entry *entry; + struct gpio_virtuser_lookup *lookup; + + /* + * The device only needs to depend on leaf lookup entries. This is + * sufficient to lock up all the configfs entries that the + * instantiated, alive device depends on. + */ + list_for_each_entry(lookup, &dev->lookup_list, siblings) { + list_for_each_entry(entry, &lookup->entry_list, siblings) { + if (lock) + WARN_ON(configfs_depend_item_unlocked( + subsys, &entry->group.cg_item)); + else + configfs_undepend_item_unlocked( + &entry->group.cg_item); + } + } } static ssize_t @@ -1544,15 +1582,24 @@ gpio_virtuser_device_config_live_store(struct config_item *item, if (ret) return ret; - guard(mutex)(&dev->lock); - - if (live == gpio_virtuser_device_is_live(dev)) - return -EPERM; - if (live) - ret = gpio_virtuser_device_activate(dev); - else - gpio_virtuser_device_deactivate(dev); + gpio_virtuser_device_lockup_configfs(dev, true); + + scoped_guard(mutex, &dev->lock) { + if (live == gpio_virtuser_device_is_live(dev)) + ret = -EPERM; + else if (live) + ret = gpio_virtuser_device_activate(dev); + else + gpio_virtuser_device_deactivate(dev); + } + + /* + * Undepend is required only if device disablement (live == 0) + * succeeds or if device enablement (live == 1) fails. + */ + if (live == !!ret) + gpio_virtuser_device_lockup_configfs(dev, false); return ret ?: count; } diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c index c6a8f2c82680..792d94c49077 100644 --- a/drivers/gpio/gpio-xilinx.c +++ b/drivers/gpio/gpio-xilinx.c @@ -65,7 +65,7 @@ struct xgpio_instance { DECLARE_BITMAP(state, 64); DECLARE_BITMAP(last_irq_read, 64); DECLARE_BITMAP(dir, 64); - spinlock_t gpio_lock; /* For serializing operations */ + raw_spinlock_t gpio_lock; /* For serializing operations */ int irq; DECLARE_BITMAP(enable, 64); DECLARE_BITMAP(rising_edge, 64); @@ -179,14 +179,14 @@ static void xgpio_set(struct gpio_chip *gc, unsigned int gpio, int val) struct xgpio_instance *chip = gpiochip_get_data(gc); int bit = xgpio_to_bit(chip, gpio); - spin_lock_irqsave(&chip->gpio_lock, flags); + raw_spin_lock_irqsave(&chip->gpio_lock, flags); /* Write to GPIO signal and set its direction to output */ __assign_bit(bit, chip->state, val); xgpio_write_ch(chip, XGPIO_DATA_OFFSET, bit, chip->state); - spin_unlock_irqrestore(&chip->gpio_lock, flags); + raw_spin_unlock_irqrestore(&chip->gpio_lock, flags); } /** @@ -210,7 +210,7 @@ static void xgpio_set_multiple(struct gpio_chip *gc, unsigned long *mask, bitmap_remap(hw_mask, mask, chip->sw_map, chip->hw_map, 64); bitmap_remap(hw_bits, bits, chip->sw_map, chip->hw_map, 64); - spin_lock_irqsave(&chip->gpio_lock, flags); + raw_spin_lock_irqsave(&chip->gpio_lock, flags); bitmap_replace(state, chip->state, hw_bits, hw_mask, 64); @@ -218,7 +218,7 @@ static void xgpio_set_multiple(struct gpio_chip *gc, unsigned long *mask, bitmap_copy(chip->state, state, 64); - spin_unlock_irqrestore(&chip->gpio_lock, flags); + raw_spin_unlock_irqrestore(&chip->gpio_lock, flags); } /** @@ -236,13 +236,13 @@ static int xgpio_dir_in(struct gpio_chip *gc, unsigned int gpio) struct xgpio_instance *chip = gpiochip_get_data(gc); int bit = xgpio_to_bit(chip, gpio); - spin_lock_irqsave(&chip->gpio_lock, flags); + raw_spin_lock_irqsave(&chip->gpio_lock, flags); /* Set the GPIO bit in shadow register and set direction as input */ __set_bit(bit, chip->dir); xgpio_write_ch(chip, XGPIO_TRI_OFFSET, bit, chip->dir); - spin_unlock_irqrestore(&chip->gpio_lock, flags); + raw_spin_unlock_irqrestore(&chip->gpio_lock, flags); return 0; } @@ -265,7 +265,7 @@ static int xgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) struct xgpio_instance *chip = gpiochip_get_data(gc); int bit = xgpio_to_bit(chip, gpio); - spin_lock_irqsave(&chip->gpio_lock, flags); + raw_spin_lock_irqsave(&chip->gpio_lock, flags); /* Write state of GPIO signal */ __assign_bit(bit, chip->state, val); @@ -275,7 +275,7 @@ static int xgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) __clear_bit(bit, chip->dir); xgpio_write_ch(chip, XGPIO_TRI_OFFSET, bit, chip->dir); - spin_unlock_irqrestore(&chip->gpio_lock, flags); + raw_spin_unlock_irqrestore(&chip->gpio_lock, flags); return 0; } @@ -398,7 +398,7 @@ static void xgpio_irq_mask(struct irq_data *irq_data) int bit = xgpio_to_bit(chip, irq_offset); u32 mask = BIT(bit / 32), temp; - spin_lock_irqsave(&chip->gpio_lock, flags); + raw_spin_lock_irqsave(&chip->gpio_lock, flags); __clear_bit(bit, chip->enable); @@ -408,7 +408,7 @@ static void xgpio_irq_mask(struct irq_data *irq_data) temp &= ~mask; xgpio_writereg(chip->regs + XGPIO_IPIER_OFFSET, temp); } - spin_unlock_irqrestore(&chip->gpio_lock, flags); + raw_spin_unlock_irqrestore(&chip->gpio_lock, flags); gpiochip_disable_irq(&chip->gc, irq_offset); } @@ -428,7 +428,7 @@ static void xgpio_irq_unmask(struct irq_data *irq_data) gpiochip_enable_irq(&chip->gc, irq_offset); - spin_lock_irqsave(&chip->gpio_lock, flags); + raw_spin_lock_irqsave(&chip->gpio_lock, flags); __set_bit(bit, chip->enable); @@ -447,7 +447,7 @@ static void xgpio_irq_unmask(struct irq_data *irq_data) xgpio_writereg(chip->regs + XGPIO_IPIER_OFFSET, val); } - spin_unlock_irqrestore(&chip->gpio_lock, flags); + raw_spin_unlock_irqrestore(&chip->gpio_lock, flags); } /** @@ -512,7 +512,7 @@ static void xgpio_irqhandler(struct irq_desc *desc) chained_irq_enter(irqchip, desc); - spin_lock(&chip->gpio_lock); + raw_spin_lock(&chip->gpio_lock); xgpio_read_ch_all(chip, XGPIO_DATA_OFFSET, all); @@ -529,7 +529,7 @@ static void xgpio_irqhandler(struct irq_desc *desc) bitmap_copy(chip->last_irq_read, all, 64); bitmap_or(all, rising, falling, 64); - spin_unlock(&chip->gpio_lock); + raw_spin_unlock(&chip->gpio_lock); dev_dbg(gc->parent, "IRQ rising %*pb falling %*pb\n", 64, rising, 64, falling); @@ -620,7 +620,7 @@ static int xgpio_probe(struct platform_device *pdev) bitmap_set(chip->hw_map, 0, width[0]); bitmap_set(chip->hw_map, 32, width[1]); - spin_lock_init(&chip->gpio_lock); + raw_spin_lock_init(&chip->gpio_lock); chip->gc.base = -1; chip->gc.ngpio = bitmap_weight(chip->hw_map, 64); diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 6f1cf235073d..fbef3f471bd0 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -99,6 +99,7 @@ config DRM_KUNIT_TEST config DRM_KMS_HELPER tristate depends on DRM + select FB_CORE if DRM_FBDEV_EMULATION help CRTC helpers for KMS drivers. @@ -293,6 +294,8 @@ config DRM_TTM_HELPER tristate depends on DRM select DRM_TTM + select DRM_KMS_HELPER if DRM_FBDEV_EMULATION + select FB_CORE if DRM_FBDEV_EMULATION select FB_SYSMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION help Helpers for ttm-based gem objects @@ -300,6 +303,8 @@ config DRM_TTM_HELPER config DRM_GEM_DMA_HELPER tristate depends on DRM + select DRM_KMS_HELPER if DRM_FBDEV_EMULATION + select FB_CORE if DRM_FBDEV_EMULATION select FB_DMAMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION help Choose this if you need the GEM DMA helper functions @@ -307,6 +312,8 @@ config DRM_GEM_DMA_HELPER config DRM_GEM_SHMEM_HELPER tristate depends on DRM && MMU + select DRM_KMS_HELPER if DRM_FBDEV_EMULATION + select FB_CORE if DRM_FBDEV_EMULATION select FB_SYSMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION help Choose this if you need the GEM shmem helper functions diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 2e5732dfd425..2c1b38c5cfc6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -715,8 +715,9 @@ err: void amdgpu_amdkfd_set_compute_idle(struct amdgpu_device *adev, bool idle) { enum amd_powergating_state state = idle ? AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE; - if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11 && - ((adev->mes.kiq_version & AMDGPU_MES_VERSION_MASK) <= 64)) { + if ((IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 11 && + ((adev->mes.kiq_version & AMDGPU_MES_VERSION_MASK) <= 64)) || + (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 12)) { pr_debug("GFXOFF is %s\n", idle ? "enabled" : "disabled"); amdgpu_gfx_off_ctrl(adev, idle); } else if ((IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) == 9) && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index cc66ebb7bae1..441568163e20 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -1131,6 +1131,9 @@ uint64_t kgd_gfx_v9_hqd_get_pq_addr(struct amdgpu_device *adev, uint32_t low, high; uint64_t queue_addr = 0; + if (!amdgpu_gpu_recovery) + return 0; + kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst); amdgpu_gfx_rlc_enter_safe_mode(adev, inst); @@ -1179,6 +1182,9 @@ uint64_t kgd_gfx_v9_hqd_reset(struct amdgpu_device *adev, uint32_t low, high, pipe_reset_data = 0; uint64_t queue_addr = 0; + if (!amdgpu_gpu_recovery) + return 0; + kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst); amdgpu_gfx_rlc_enter_safe_mode(adev, inst); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 5df21529b3b1..5cc5f59e3018 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1105,7 +1105,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) * We can't use gang submit on with reserved VMIDs when the VM changes * can't be invalidated by more than one engine at the same time. */ - if (p->gang_size > 1 && !p->adev->vm_manager.concurrent_flush) { + if (p->gang_size > 1 && !adev->vm_manager.concurrent_flush) { for (i = 0; i < p->gang_size; ++i) { struct drm_sched_entity *entity = p->entities[i]; struct drm_gpu_scheduler *sched = entity->rq->sched; @@ -1189,7 +1189,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (!bo) continue; - amdgpu_vm_bo_invalidate(adev, bo, false); + amdgpu_vm_bo_invalidate(bo, false); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 36053b3d48b3..d100bb7a137c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2365,8 +2365,8 @@ int amdgpu_device_ip_block_add(struct amdgpu_device *adev, break; } - DRM_INFO("add ip block number %d <%s>\n", adev->num_ip_blocks, - ip_block_version->funcs->name); + dev_info(adev->dev, "detected ip block number %d <%s>\n", + adev->num_ip_blocks, ip_block_version->funcs->name); adev->ip_blocks[adev->num_ip_blocks].adev = adev; @@ -6157,6 +6157,44 @@ static void amdgpu_device_partner_bandwidth(struct amdgpu_device *adev, } } +/** + * amdgpu_device_gpu_bandwidth - find the bandwidth of the GPU + * + * @adev: amdgpu_device pointer + * @speed: pointer to the speed of the link + * @width: pointer to the width of the link + * + * Evaluate the hierarchy to find the speed and bandwidth capabilities of the + * AMD dGPU which may be a virtual upstream bridge. + */ +static void amdgpu_device_gpu_bandwidth(struct amdgpu_device *adev, + enum pci_bus_speed *speed, + enum pcie_link_width *width) +{ + struct pci_dev *parent = adev->pdev; + + if (!speed || !width) + return; + + parent = pci_upstream_bridge(parent); + if (parent && parent->vendor == PCI_VENDOR_ID_ATI) { + /* use the upstream/downstream switches internal to dGPU */ + *speed = pcie_get_speed_cap(parent); + *width = pcie_get_width_cap(parent); + while ((parent = pci_upstream_bridge(parent))) { + if (parent->vendor == PCI_VENDOR_ID_ATI) { + /* use the upstream/downstream switches internal to dGPU */ + *speed = pcie_get_speed_cap(parent); + *width = pcie_get_width_cap(parent); + } + } + } else { + /* use the device itself */ + *speed = pcie_get_speed_cap(adev->pdev); + *width = pcie_get_width_cap(adev->pdev); + } +} + /** * amdgpu_device_get_pcie_info - fence pcie info about the PCIE slot * @@ -6168,9 +6206,8 @@ static void amdgpu_device_partner_bandwidth(struct amdgpu_device *adev, */ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev) { - struct pci_dev *pdev; enum pci_bus_speed speed_cap, platform_speed_cap; - enum pcie_link_width platform_link_width; + enum pcie_link_width platform_link_width, link_width; if (amdgpu_pcie_gen_cap) adev->pm.pcie_gen_mask = amdgpu_pcie_gen_cap; @@ -6192,11 +6229,10 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev) amdgpu_device_partner_bandwidth(adev, &platform_speed_cap, &platform_link_width); + amdgpu_device_gpu_bandwidth(adev, &speed_cap, &link_width); if (adev->pm.pcie_gen_mask == 0) { /* asic caps */ - pdev = adev->pdev; - speed_cap = pcie_get_speed_cap(pdev); if (speed_cap == PCI_SPEED_UNKNOWN) { adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 | CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 | @@ -6252,51 +6288,103 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev) } } if (adev->pm.pcie_mlw_mask == 0) { + /* asic caps */ + if (link_width == PCIE_LNK_WIDTH_UNKNOWN) { + adev->pm.pcie_mlw_mask |= AMDGPU_DEFAULT_ASIC_PCIE_MLW_MASK; + } else { + switch (link_width) { + case PCIE_LNK_X32: + adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X32 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1); + break; + case PCIE_LNK_X16: + adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1); + break; + case PCIE_LNK_X12: + adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1); + break; + case PCIE_LNK_X8: + adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1); + break; + case PCIE_LNK_X4: + adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1); + break; + case PCIE_LNK_X2: + adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1); + break; + case PCIE_LNK_X1: + adev->pm.pcie_mlw_mask |= CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1; + break; + default: + break; + } + } + /* platform caps */ if (platform_link_width == PCIE_LNK_WIDTH_UNKNOWN) { adev->pm.pcie_mlw_mask |= AMDGPU_DEFAULT_PCIE_MLW_MASK; } else { switch (platform_link_width) { case PCIE_LNK_X32: - adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); + adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); break; case PCIE_LNK_X16: - adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); + adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); break; case PCIE_LNK_X12: - adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); + adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); break; case PCIE_LNK_X8: - adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); + adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); break; case PCIE_LNK_X4: - adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); + adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); break; case PCIE_LNK_X2: - adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | - CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); + adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 | + CAIL_PCIE_LINK_WIDTH_SUPPORT_X1); break; case PCIE_LNK_X1: - adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1; + adev->pm.pcie_mlw_mask |= CAIL_PCIE_LINK_WIDTH_SUPPORT_X1; break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 8e81a83d37d8..9f627caedc3f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -36,6 +36,7 @@ #include "amdgpu_gem.h" #include "amdgpu_dma_buf.h" #include "amdgpu_xgmi.h" +#include "amdgpu_vm.h" #include #include #include @@ -60,6 +61,8 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) attach->peer2peer = false; + amdgpu_vm_bo_update_shared(bo); + return 0; } @@ -345,7 +348,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) /* FIXME: This should be after the "if", but needs a fix to make sure * DMABuf imports are initialized in the right VM list. */ - amdgpu_vm_bo_invalidate(adev, bo, false); + amdgpu_vm_bo_invalidate(bo, false); if (!bo->tbo.resource || bo->tbo.resource->mem_type == TTM_PL_SYSTEM) return; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 492b09d84571..817116e53d44 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -280,7 +280,7 @@ module_param_named(gartsize, amdgpu_gart_size, uint, 0600); /** * DOC: gttsize (int) * Restrict the size of GTT domain (for userspace use) in MiB for testing. - * The default is -1 (Use 1/2 RAM, minimum value is 3GB). + * The default is -1 (Use value specified by TTM). */ MODULE_PARM_DESC(gttsize, "Size of the GTT userspace domain in megabytes (-1 = auto)"); module_param_named(gttsize, amdgpu_gtt_size, int, 0600); @@ -399,7 +399,7 @@ module_param_named(runpm, amdgpu_runtime_pm, int, 0444); * the kernel log for the list of IPs on the asic. The default is 0xffffffff (enable all blocks on a device). */ MODULE_PARM_DESC(ip_block_mask, "IP Block Mask (all blocks enabled (default))"); -module_param_named(ip_block_mask, amdgpu_ip_block_mask, uint, 0444); +module_param_named_unsafe(ip_block_mask, amdgpu_ip_block_mask, uint, 0444); /** * DOC: bapm (int) @@ -457,7 +457,7 @@ module_param_named(vm_update_mode, amdgpu_vm_update_mode, int, 0444); * Enable experimental hw support (1 = enable). The default is 0 (disabled). */ MODULE_PARM_DESC(exp_hw_support, "experimental hw support (1 = enable, 0 = disable (default))"); -module_param_named(exp_hw_support, amdgpu_exp_hw_support, int, 0444); +module_param_named_unsafe(exp_hw_support, amdgpu_exp_hw_support, int, 0444); /** * DOC: dc (int) @@ -568,14 +568,14 @@ module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444); * Set to enable GPU recovery mechanism (1 = enable, 0 = disable). The default is -1 (auto, disabled except SRIOV). */ MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto)"); -module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444); +module_param_named_unsafe(gpu_recovery, amdgpu_gpu_recovery, int, 0444); /** * DOC: emu_mode (int) * Set value 1 to enable emulation mode. This is only needed when running on an emulator. The default is 0 (disabled). */ MODULE_PARM_DESC(emu_mode, "Emulation mode, (1 = enable, 0 = disable)"); -module_param_named(emu_mode, amdgpu_emu_mode, int, 0444); +module_param_named_unsafe(emu_mode, amdgpu_emu_mode, int, 0444); /** * DOC: ras_enable (int) @@ -730,7 +730,7 @@ module_param_named(noretry, amdgpu_noretry, int, 0644); */ MODULE_PARM_DESC(force_asic_type, "A non negative value used to specify the asic type for all supported GPUs"); -module_param_named(force_asic_type, amdgpu_force_asic_type, int, 0444); +module_param_named_unsafe(force_asic_type, amdgpu_force_asic_type, int, 0444); /** * DOC: use_xgmi_p2p (int) @@ -749,7 +749,7 @@ module_param_named(use_xgmi_p2p, amdgpu_use_xgmi_p2p, int, 0444); * assigns queues to HQDs. */ int sched_policy = KFD_SCHED_POLICY_HWS; -module_param(sched_policy, int, 0444); +module_param_unsafe(sched_policy, int, 0444); MODULE_PARM_DESC(sched_policy, "Scheduling policy (0 = HWS (Default), 1 = HWS without over-subscription, 2 = Non-HWS (Used for debugging only)"); @@ -799,7 +799,7 @@ MODULE_PARM_DESC(send_sigterm, * Setting 1 enables halt on hang. */ int halt_if_hws_hang; -module_param(halt_if_hws_hang, int, 0644); +module_param_unsafe(halt_if_hws_hang, int, 0644); MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)"); /** @@ -808,7 +808,7 @@ MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (defau * check says. Default value: false (rely on MEC2 firmware version check). */ bool hws_gws_support; -module_param(hws_gws_support, bool, 0444); +module_param_unsafe(hws_gws_support, bool, 0444); MODULE_PARM_DESC(hws_gws_support, "Assume MEC2 FW supports GWS barriers (false = rely on FW version check (Default), true = force supported)"); /** @@ -841,7 +841,7 @@ MODULE_PARM_DESC(no_system_mem_limit, "disable system memory limit (false = defa */ int amdgpu_no_queue_eviction_on_vm_fault; MODULE_PARM_DESC(no_queue_eviction_on_vm_fault, "No queue eviction on VM fault (0 = queue eviction, 1 = no queue eviction)"); -module_param_named(no_queue_eviction_on_vm_fault, amdgpu_no_queue_eviction_on_vm_fault, int, 0444); +module_param_named_unsafe(no_queue_eviction_on_vm_fault, amdgpu_no_queue_eviction_on_vm_fault, int, 0444); #endif /** @@ -849,7 +849,7 @@ module_param_named(no_queue_eviction_on_vm_fault, amdgpu_no_queue_eviction_on_vm */ int amdgpu_mtype_local; MODULE_PARM_DESC(mtype_local, "MTYPE for local memory (0 = MTYPE_RW (default), 1 = MTYPE_NC, 2 = MTYPE_CC)"); -module_param_named(mtype_local, amdgpu_mtype_local, int, 0444); +module_param_named_unsafe(mtype_local, amdgpu_mtype_local, int, 0444); /** * DOC: pcie_p2p (bool) @@ -953,7 +953,7 @@ module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444); * GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco) */ MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco/bamaco)"); -module_param_named(reset_method, amdgpu_reset_method, int, 0644); +module_param_named_unsafe(reset_method, amdgpu_reset_method, int, 0644); /** * DOC: bad_page_threshold (int) Bad page threshold is specifies the @@ -1049,7 +1049,7 @@ module_param_named(seamless, amdgpu_seamless, int, 0444); * - 0x4: Disable GPU soft recovery, always do a full reset */ MODULE_PARM_DESC(debug_mask, "debug options for amdgpu, disabled by default"); -module_param_named(debug_mask, amdgpu_debug_mask, uint, 0444); +module_param_named_unsafe(debug_mask, amdgpu_debug_mask, uint, 0444); /** * DOC: agp (int) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c index df2cf5c33925..91d638098889 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c @@ -60,7 +60,7 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) struct amdgpu_fpriv *fpriv = file->driver_priv; struct amdgpu_vm *vm = &fpriv->vm; - struct amdgpu_mem_stats stats[__AMDGPU_PL_LAST + 1] = { }; + struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM]; ktime_t usage[AMDGPU_HW_IP_NUM]; const char *pl_name[] = { [TTM_PL_VRAM] = "vram", @@ -72,15 +72,8 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) [AMDGPU_PL_DOORBELL] = "doorbell", }; unsigned int hw_ip, i; - int ret; - - ret = amdgpu_bo_reserve(vm->root.bo, false); - if (ret) - return; - - amdgpu_vm_get_memory(vm, stats, ARRAY_SIZE(stats)); - amdgpu_bo_unreserve(vm->root.bo); + amdgpu_vm_get_memory(vm, stats); amdgpu_ctx_mgr_usage(&fpriv->ctx_mgr, usage); /* @@ -114,9 +107,11 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) drm_printf(p, "amd-evicted-vram:\t%llu KiB\n", stats[TTM_PL_VRAM].evicted/1024UL); drm_printf(p, "amd-requested-vram:\t%llu KiB\n", - stats[TTM_PL_VRAM].requested/1024UL); + (stats[TTM_PL_VRAM].drm.shared + + stats[TTM_PL_VRAM].drm.private) / 1024UL); drm_printf(p, "amd-requested-gtt:\t%llu KiB\n", - stats[TTM_PL_TT].requested/1024UL); + (stats[TTM_PL_TT].drm.shared + + stats[TTM_PL_TT].drm.private) / 1024UL); for (hw_ip = 0; hw_ip < AMDGPU_HW_IP_NUM; ++hw_ip) { if (!usage[hw_ip]) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fw_attestation.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fw_attestation.c index 2d4b67175b55..328a1b963548 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fw_attestation.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fw_attestation.c @@ -122,6 +122,10 @@ static int amdgpu_is_fw_attestation_supported(struct amdgpu_device *adev) if (adev->flags & AMD_IS_APU) return 0; + if (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(14, 0, 2) || + amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(14, 0, 3)) + return 0; + if (adev->asic_type >= CHIP_SIENNA_CICHLID) return 1; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 1a5df8b94661..69429df09477 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -42,6 +42,7 @@ #include "amdgpu_dma_buf.h" #include "amdgpu_hmm.h" #include "amdgpu_xgmi.h" +#include "amdgpu_vm.h" static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf) { @@ -87,10 +88,8 @@ static void amdgpu_gem_object_free(struct drm_gem_object *gobj) { struct amdgpu_bo *aobj = gem_to_amdgpu_bo(gobj); - if (aobj) { - amdgpu_hmm_unregister(aobj); - ttm_bo_put(&aobj->tbo); - } + amdgpu_hmm_unregister(aobj); + ttm_bo_put(&aobj->tbo); } int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, @@ -179,6 +178,7 @@ static int amdgpu_gem_object_open(struct drm_gem_object *obj, if (r) return r; + amdgpu_vm_bo_update_shared(abo); bo_va = amdgpu_vm_bo_find(vm, abo); if (!bo_va) bo_va = amdgpu_vm_bo_add(adev, vm, abo); @@ -252,6 +252,7 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj, goto out_unlock; amdgpu_vm_bo_del(adev, bo_va); + amdgpu_vm_bo_update_shared(bo); if (!amdgpu_vm_ready(vm)) goto out_unlock; @@ -839,7 +840,6 @@ error: int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { - struct amdgpu_device *adev = drm_to_adev(dev); struct drm_amdgpu_gem_op *args = data; struct drm_gem_object *gobj; struct amdgpu_vm_bo_base *base; @@ -899,7 +899,7 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, robj->allowed_domains |= AMDGPU_GEM_DOMAIN_GTT; if (robj->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) - amdgpu_vm_bo_invalidate(adev, robj, true); + amdgpu_vm_bo_invalidate(robj, true); amdgpu_bo_unreserve(robj); break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 6d5d81f0dc4e..784b03abb3a4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -2054,6 +2054,7 @@ void amdgpu_gfx_enforce_isolation_ring_begin_use(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; u32 idx; + bool sched_work = false; if (!adev->gfx.enable_cleaner_shader) return; @@ -2072,9 +2073,12 @@ void amdgpu_gfx_enforce_isolation_ring_begin_use(struct amdgpu_ring *ring) mutex_lock(&adev->enforce_isolation_mutex); if (adev->enforce_isolation[idx]) { if (adev->kfd.init_complete) - amdgpu_gfx_kfd_sch_ctrl(adev, idx, false); + sched_work = true; } mutex_unlock(&adev->enforce_isolation_mutex); + + if (sched_work) + amdgpu_gfx_kfd_sch_ctrl(adev, idx, false); } /** @@ -2090,6 +2094,7 @@ void amdgpu_gfx_enforce_isolation_ring_end_use(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; u32 idx; + bool sched_work = false; if (!adev->gfx.enable_cleaner_shader) return; @@ -2105,9 +2110,12 @@ void amdgpu_gfx_enforce_isolation_ring_end_use(struct amdgpu_ring *ring) mutex_lock(&adev->enforce_isolation_mutex); if (adev->enforce_isolation[idx]) { if (adev->kfd.init_complete) - amdgpu_gfx_kfd_sch_ctrl(adev, idx, true); + sched_work = true; } mutex_unlock(&adev->enforce_isolation_mutex); + + if (sched_work) + amdgpu_gfx_kfd_sch_ctrl(adev, idx, true); } /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index d751995dc131..2ea98ec60220 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -191,8 +191,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs, need_ctx_switch = ring->current_ctx != fence_ctx; if (ring->funcs->emit_pipeline_sync && job && ((tmp = amdgpu_sync_get_fence(&job->explicit_sync)) || - (amdgpu_sriov_vf(adev) && need_ctx_switch) || - amdgpu_vm_need_pipeline_sync(ring, job))) { + need_ctx_switch || amdgpu_vm_need_pipeline_sync(ring, job))) { + need_pipe_sync = true; if (tmp) @@ -297,7 +297,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs, amdgpu_ring_patch_cond_exec(ring, cond_exec); ring->current_ctx = fence_ctx; - if (vm && ring->funcs->emit_switch_buffer) + if (job && ring->funcs->emit_switch_buffer) amdgpu_ring_emit_switch_buffer(ring); if (ring->funcs->emit_wave_limit && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 016a6f6c4267..98528ee94c15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -846,7 +846,7 @@ out: case AMDGPU_INFO_DEV_INFO: { struct drm_amdgpu_info_device *dev_info; uint64_t vm_size; - uint32_t pcie_gen_mask; + uint32_t pcie_gen_mask, pcie_width_mask; dev_info = kzalloc(sizeof(*dev_info), GFP_KERNEL); if (!dev_info) @@ -934,15 +934,18 @@ out: dev_info->tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask; /* Combine the chip gen mask with the platform (CPU/mobo) mask. */ - pcie_gen_mask = adev->pm.pcie_gen_mask & (adev->pm.pcie_gen_mask >> 16); + pcie_gen_mask = adev->pm.pcie_gen_mask & + (adev->pm.pcie_gen_mask >> CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT); + pcie_width_mask = adev->pm.pcie_mlw_mask & + (adev->pm.pcie_mlw_mask >> CAIL_PCIE_LINK_WIDTH_SUPPORT_SHIFT); dev_info->pcie_gen = fls(pcie_gen_mask); dev_info->pcie_num_lanes = - adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 ? 32 : - adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 ? 16 : - adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 ? 12 : - adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 ? 8 : - adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 ? 4 : - adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 ? 2 : 1; + pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X32 ? 32 : + pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16 ? 16 : + pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12 ? 12 : + pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 ? 8 : + pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 ? 4 : + pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 ? 2 : 1; dev_info->tcp_cache_size = adev->gfx.config.gc_tcp_l1_size; dev_info->num_sqc_per_wgp = adev->gfx.config.gc_num_sqc_per_wgp; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index c6f93cbd6739..2df2444ee892 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -40,7 +40,7 @@ #define AMDGPU_MES_VERSION_MASK 0x00000fff #define AMDGPU_MES_API_VERSION_MASK 0x00fff000 #define AMDGPU_MES_FEAT_VERSION_MASK 0xff000000 -#define AMDGPU_MES_MSCRATCH_SIZE 0x8000 +#define AMDGPU_MES_MSCRATCH_SIZE 0x40000 enum amdgpu_mes_priority_level { AMDGPU_MES_PRIORITY_LEVEL_LOW = 0, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 4f057996ef35..96f4b8904e9a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1251,7 +1251,6 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict, struct ttm_resource *new_mem) { - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct ttm_resource *old_mem = bo->resource; struct amdgpu_bo *abo; @@ -1259,7 +1258,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, return; abo = ttm_to_amdgpu_bo(bo); - amdgpu_vm_bo_invalidate(adev, abo, evict); + amdgpu_vm_bo_move(abo, new_mem, evict); amdgpu_bo_kunmap(abo); @@ -1272,75 +1271,6 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, old_mem ? old_mem->mem_type : -1); } -void amdgpu_bo_get_memory(struct amdgpu_bo *bo, - struct amdgpu_mem_stats *stats, - unsigned int sz) -{ - const unsigned int domain_to_pl[] = { - [ilog2(AMDGPU_GEM_DOMAIN_CPU)] = TTM_PL_SYSTEM, - [ilog2(AMDGPU_GEM_DOMAIN_GTT)] = TTM_PL_TT, - [ilog2(AMDGPU_GEM_DOMAIN_VRAM)] = TTM_PL_VRAM, - [ilog2(AMDGPU_GEM_DOMAIN_GDS)] = AMDGPU_PL_GDS, - [ilog2(AMDGPU_GEM_DOMAIN_GWS)] = AMDGPU_PL_GWS, - [ilog2(AMDGPU_GEM_DOMAIN_OA)] = AMDGPU_PL_OA, - [ilog2(AMDGPU_GEM_DOMAIN_DOORBELL)] = AMDGPU_PL_DOORBELL, - }; - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - struct ttm_resource *res = bo->tbo.resource; - struct drm_gem_object *obj = &bo->tbo.base; - uint64_t size = amdgpu_bo_size(bo); - unsigned int type; - - if (!res) { - /* - * If no backing store use one of the preferred domain for basic - * stats. We take the MSB since that should give a reasonable - * view. - */ - BUILD_BUG_ON(TTM_PL_VRAM < TTM_PL_TT || - TTM_PL_VRAM < TTM_PL_SYSTEM); - type = fls(bo->preferred_domains & AMDGPU_GEM_DOMAIN_MASK); - if (!type) - return; - type--; - if (drm_WARN_ON_ONCE(&adev->ddev, - type >= ARRAY_SIZE(domain_to_pl))) - return; - type = domain_to_pl[type]; - } else { - type = res->mem_type; - } - - if (drm_WARN_ON_ONCE(&adev->ddev, type >= sz)) - return; - - /* DRM stats common fields: */ - - if (drm_gem_object_is_shared_for_memory_stats(obj)) - stats[type].drm.shared += size; - else - stats[type].drm.private += size; - - if (res) { - stats[type].drm.resident += size; - - if (!dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_BOOKKEEP)) - stats[type].drm.active += size; - else if (bo->flags & AMDGPU_GEM_CREATE_DISCARDABLE) - stats[type].drm.purgeable += size; - } - - /* amdgpu specific stats: */ - - if (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) { - stats[TTM_PL_VRAM].requested += size; - if (type != TTM_PL_VRAM) - stats[TTM_PL_VRAM].evicted += size; - } else if (bo->preferred_domains & AMDGPU_GEM_DOMAIN_GTT) { - stats[TTM_PL_TT].requested += size; - } -} - /** * amdgpu_bo_release_notify - notification about a BO being released * @bo: pointer to a buffer object @@ -1555,6 +1485,45 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo) return amdgpu_gmc_sign_extend(offset); } +/** + * amdgpu_bo_mem_stats_placement - bo placement for memory accounting + * @bo: the buffer object we should look at + * + * BO can have multiple preferred placements, to avoid double counting we want + * to file it under a single placement for memory stats. + * Luckily, if we take the highest set bit in preferred_domains the result is + * quite sensible. + * + * Returns: + * Which of the placements should the BO be accounted under. + */ +uint32_t amdgpu_bo_mem_stats_placement(struct amdgpu_bo *bo) +{ + uint32_t domain = bo->preferred_domains & AMDGPU_GEM_DOMAIN_MASK; + + if (!domain) + return TTM_PL_SYSTEM; + + switch (rounddown_pow_of_two(domain)) { + case AMDGPU_GEM_DOMAIN_CPU: + return TTM_PL_SYSTEM; + case AMDGPU_GEM_DOMAIN_GTT: + return TTM_PL_TT; + case AMDGPU_GEM_DOMAIN_VRAM: + return TTM_PL_VRAM; + case AMDGPU_GEM_DOMAIN_GDS: + return AMDGPU_PL_GDS; + case AMDGPU_GEM_DOMAIN_GWS: + return AMDGPU_PL_GWS; + case AMDGPU_GEM_DOMAIN_OA: + return AMDGPU_PL_OA; + case AMDGPU_GEM_DOMAIN_DOORBELL: + return AMDGPU_PL_DOORBELL; + default: + return TTM_PL_SYSTEM; + } +} + /** * amdgpu_bo_get_preferred_domain - get preferred domain * @adev: amdgpu device object diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index ab3fe7b42da7..375448627f7b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -305,9 +305,7 @@ int amdgpu_bo_sync_wait_resv(struct amdgpu_device *adev, struct dma_resv *resv, int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr); u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo); u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo); -void amdgpu_bo_get_memory(struct amdgpu_bo *bo, - struct amdgpu_mem_stats *stats, - unsigned int size); +uint32_t amdgpu_bo_mem_stats_placement(struct amdgpu_bo *bo); uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, uint32_t domain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 3c1b08441a6f..babe94ade247 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -3020,10 +3020,7 @@ static int psp_hw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; mutex_lock(&adev->firmware.mutex); - /* - * This sequence is just used on hw_init only once, no need on - * resume. - */ + ret = amdgpu_ucode_init_bo(adev); if (ret) goto failed; @@ -3148,6 +3145,10 @@ static int psp_resume(struct amdgpu_ip_block *ip_block) mutex_lock(&adev->firmware.mutex); + ret = amdgpu_ucode_init_bo(adev); + if (ret) + goto failed; + ret = psp_hw_start(psp); if (ret) goto failed; @@ -3891,10 +3892,12 @@ static ssize_t psp_usbc_pd_fw_sysfs_read(struct device *dev, { struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); + struct amdgpu_ip_block *ip_block; uint32_t fw_ver; int ret; - if (!adev->ip_blocks[AMD_IP_BLOCK_TYPE_PSP].status.late_initialized) { + ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP); + if (!ip_block || !ip_block->status.late_initialized) { dev_info(adev->dev, "PSP block is not ready yet\n."); return -EBUSY; } @@ -3923,8 +3926,10 @@ static ssize_t psp_usbc_pd_fw_sysfs_write(struct device *dev, struct amdgpu_bo *fw_buf_bo = NULL; uint64_t fw_pri_mc_addr; void *fw_pri_cpu_addr; + struct amdgpu_ip_block *ip_block; - if (!adev->ip_blocks[AMD_IP_BLOCK_TYPE_PSP].status.late_initialized) { + ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP); + if (!ip_block || !ip_block->status.late_initialized) { dev_err(adev->dev, "PSP block is not ready yet."); return -EBUSY; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 01c947066a2e..f0924aa3f4e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2832,8 +2832,10 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, mutex_lock(&con->recovery_lock); data = con->eh_data; - if (!data) + if (!data) { + /* Returning 0 as the absence of eh_data is acceptable */ goto free; + } for (i = 0; i < pages; i++) { if (from_rom && @@ -2845,26 +2847,34 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, * one row */ if (amdgpu_umc_pages_in_a_row(adev, &err_data, - bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT)) + bps[i].retired_page << + AMDGPU_GPU_PAGE_SHIFT)) { + ret = -EINVAL; goto free; - else + } else { find_pages_per_pa = true; + } } else { /* unsupported cases */ + ret = -EOPNOTSUPP; goto free; } } } else { if (amdgpu_umc_pages_in_a_row(adev, &err_data, - bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT)) + bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT)) { + ret = -EINVAL; goto free; + } } } else { if (from_rom && !find_pages_per_pa) { if (bps[i].retired_page & UMC_CHANNEL_IDX_V2) { /* bad page in any NPS mode in eeprom */ - if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data)) + if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data)) { + ret = -EINVAL; goto free; + } } else { /* legacy bad page in eeprom, generated only in * NPS1 mode @@ -2881,6 +2891,7 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, /* non-nps1 mode, old RAS TA * can't support it */ + ret = -EOPNOTSUPP; goto free; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 632295bf3875..174badca27e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -362,13 +362,13 @@ static int amdgpu_debugfs_sdma_sched_mask_set(void *data, u64 val) if (!adev) return -ENODEV; - mask = (1 << adev->sdma.num_instances) - 1; + mask = BIT_ULL(adev->sdma.num_instances) - 1; if ((val & mask) == 0) return -EINVAL; for (i = 0; i < adev->sdma.num_instances; ++i) { ring = &adev->sdma.instance[i].ring; - if (val & (1 << i)) + if (val & BIT_ULL(i)) ring->sched.ready = true; else ring->sched.ready = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h index 2db58b5812a8..5f60736051d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h @@ -107,6 +107,7 @@ struct amdgpu_sdma { struct amdgpu_irq_src doorbell_invalid_irq; struct amdgpu_irq_src pool_timeout_irq; struct amdgpu_irq_src srbm_write_irq; + struct amdgpu_irq_src ctxt_empty_irq; int num_instances; uint32_t sdma_mask; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 2d85f1ec3041..ff286940ab43 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -2066,6 +2066,7 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_GDS); ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_GWS); ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_OA); + ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_DOORBELL); ttm_device_fini(&adev->mman.bdev); adev->mman.initialized = false; DRM_INFO("amdgpu: ttm finalized\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 2852a6064c9a..461fb8090ae0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -26,15 +26,15 @@ #include #include +#include #include "amdgpu_vram_mgr.h" -#include "amdgpu.h" #define AMDGPU_PL_GDS (TTM_PL_PRIV + 0) #define AMDGPU_PL_GWS (TTM_PL_PRIV + 1) #define AMDGPU_PL_OA (TTM_PL_PRIV + 2) #define AMDGPU_PL_PREEMPT (TTM_PL_PRIV + 3) #define AMDGPU_PL_DOORBELL (TTM_PL_PRIV + 4) -#define __AMDGPU_PL_LAST (TTM_PL_PRIV + 4) +#define __AMDGPU_PL_NUM (TTM_PL_PRIV + 5) #define AMDGPU_GTT_MAX_TRANSFER_SIZE 512 #define AMDGPU_GTT_NUM_TRANSFER_WINDOWS 2 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index c9c48b782ec1..5c07777d3239 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -36,6 +36,7 @@ #include #include #include "amdgpu.h" +#include "amdgpu_vm.h" #include "amdgpu_trace.h" #include "amdgpu_amdkfd.h" #include "amdgpu_gmc.h" @@ -310,6 +311,111 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm) spin_unlock(&vm->status_lock); } +/** + * amdgpu_vm_update_shared - helper to update shared memory stat + * @base: base structure for tracking BO usage in a VM + * + * Takes the vm status_lock and updates the shared memory stat. If the basic + * stat changed (e.g. buffer was moved) amdgpu_vm_update_stats need to be called + * as well. + */ +static void amdgpu_vm_update_shared(struct amdgpu_vm_bo_base *base) +{ + struct amdgpu_vm *vm = base->vm; + struct amdgpu_bo *bo = base->bo; + uint64_t size = amdgpu_bo_size(bo); + uint32_t bo_memtype = amdgpu_bo_mem_stats_placement(bo); + bool shared; + + spin_lock(&vm->status_lock); + shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base); + if (base->shared != shared) { + base->shared = shared; + if (shared) { + vm->stats[bo_memtype].drm.shared += size; + vm->stats[bo_memtype].drm.private -= size; + } else { + vm->stats[bo_memtype].drm.shared -= size; + vm->stats[bo_memtype].drm.private += size; + } + } + spin_unlock(&vm->status_lock); +} + +/** + * amdgpu_vm_bo_update_shared - callback when bo gets shared/unshared + * @bo: amdgpu buffer object + * + * Update the per VM stats for all the vm if needed from private to shared or + * vice versa. + */ +void amdgpu_vm_bo_update_shared(struct amdgpu_bo *bo) +{ + struct amdgpu_vm_bo_base *base; + + for (base = bo->vm_bo; base; base = base->next) + amdgpu_vm_update_shared(base); +} + +/** + * amdgpu_vm_update_stats_locked - helper to update normal memory stat + * @base: base structure for tracking BO usage in a VM + * @res: the ttm_resource to use for the purpose of accounting, may or may not + * be bo->tbo.resource + * @sign: if we should add (+1) or subtract (-1) from the stat + * + * Caller need to have the vm status_lock held. Useful for when multiple update + * need to happen at the same time. + */ +static void amdgpu_vm_update_stats_locked(struct amdgpu_vm_bo_base *base, + struct ttm_resource *res, int sign) +{ + struct amdgpu_vm *vm = base->vm; + struct amdgpu_bo *bo = base->bo; + int64_t size = sign * amdgpu_bo_size(bo); + uint32_t bo_memtype = amdgpu_bo_mem_stats_placement(bo); + + /* For drm-total- and drm-shared-, BO are accounted by their preferred + * placement, see also amdgpu_bo_mem_stats_placement. + */ + if (base->shared) + vm->stats[bo_memtype].drm.shared += size; + else + vm->stats[bo_memtype].drm.private += size; + + if (res && res->mem_type < __AMDGPU_PL_NUM) { + uint32_t res_memtype = res->mem_type; + + vm->stats[res_memtype].drm.resident += size; + /* BO only count as purgeable if it is resident, + * since otherwise there's nothing to purge. + */ + if (bo->flags & AMDGPU_GEM_CREATE_DISCARDABLE) + vm->stats[res_memtype].drm.purgeable += size; + if (!(bo->preferred_domains & amdgpu_mem_type_to_domain(res_memtype))) + vm->stats[bo_memtype].evicted += size; + } +} + +/** + * amdgpu_vm_update_stats - helper to update normal memory stat + * @base: base structure for tracking BO usage in a VM + * @res: the ttm_resource to use for the purpose of accounting, may or may not + * be bo->tbo.resource + * @sign: if we should add (+1) or subtract (-1) from the stat + * + * Updates the basic memory stat when bo is added/deleted/moved. + */ +void amdgpu_vm_update_stats(struct amdgpu_vm_bo_base *base, + struct ttm_resource *res, int sign) +{ + struct amdgpu_vm *vm = base->vm; + + spin_lock(&vm->status_lock); + amdgpu_vm_update_stats_locked(base, res, sign); + spin_unlock(&vm->status_lock); +} + /** * amdgpu_vm_bo_base_init - Adds bo to the list of bos associated with the vm * @@ -333,6 +439,11 @@ void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, base->next = bo->vm_bo; bo->vm_bo = base; + spin_lock(&vm->status_lock); + base->shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base); + amdgpu_vm_update_stats_locked(base, bo->tbo.resource, +1); + spin_unlock(&vm->status_lock); + if (!amdgpu_vm_is_bo_always_valid(vm, bo)) return; @@ -1083,53 +1194,11 @@ error_free: return r; } -static void amdgpu_vm_bo_get_memory(struct amdgpu_bo_va *bo_va, - struct amdgpu_mem_stats *stats, - unsigned int size) -{ - struct amdgpu_vm *vm = bo_va->base.vm; - struct amdgpu_bo *bo = bo_va->base.bo; - - if (!bo) - return; - - /* - * For now ignore BOs which are currently locked and potentially - * changing their location. - */ - if (!amdgpu_vm_is_bo_always_valid(vm, bo) && - !dma_resv_trylock(bo->tbo.base.resv)) - return; - - amdgpu_bo_get_memory(bo, stats, size); - if (!amdgpu_vm_is_bo_always_valid(vm, bo)) - dma_resv_unlock(bo->tbo.base.resv); -} - void amdgpu_vm_get_memory(struct amdgpu_vm *vm, - struct amdgpu_mem_stats *stats, - unsigned int size) + struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM]) { - struct amdgpu_bo_va *bo_va, *tmp; - spin_lock(&vm->status_lock); - list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) - amdgpu_vm_bo_get_memory(bo_va, stats, size); - - list_for_each_entry_safe(bo_va, tmp, &vm->evicted, base.vm_status) - amdgpu_vm_bo_get_memory(bo_va, stats, size); - - list_for_each_entry_safe(bo_va, tmp, &vm->relocated, base.vm_status) - amdgpu_vm_bo_get_memory(bo_va, stats, size); - - list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) - amdgpu_vm_bo_get_memory(bo_va, stats, size); - - list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) - amdgpu_vm_bo_get_memory(bo_va, stats, size); - - list_for_each_entry_safe(bo_va, tmp, &vm->done, base.vm_status) - amdgpu_vm_bo_get_memory(bo_va, stats, size); + memcpy(stats, vm->stats, sizeof(*stats) * __AMDGPU_PL_NUM); spin_unlock(&vm->status_lock); } @@ -2075,6 +2144,7 @@ void amdgpu_vm_bo_del(struct amdgpu_device *adev, if (*base != &bo_va->base) continue; + amdgpu_vm_update_stats(*base, bo->tbo.resource, -1); *base = bo_va->base.next; break; } @@ -2143,14 +2213,12 @@ bool amdgpu_vm_evictable(struct amdgpu_bo *bo) /** * amdgpu_vm_bo_invalidate - mark the bo as invalid * - * @adev: amdgpu_device pointer * @bo: amdgpu buffer object * @evicted: is the BO evicted * * Mark @bo as invalid. */ -void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, - struct amdgpu_bo *bo, bool evicted) +void amdgpu_vm_bo_invalidate(struct amdgpu_bo *bo, bool evicted) { struct amdgpu_vm_bo_base *bo_base; @@ -2175,6 +2243,32 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, } } +/** + * amdgpu_vm_bo_move - handle BO move + * + * @bo: amdgpu buffer object + * @new_mem: the new placement of the BO move + * @evicted: is the BO evicted + * + * Update the memory stats for the new placement and mark @bo as invalid. + */ +void amdgpu_vm_bo_move(struct amdgpu_bo *bo, struct ttm_resource *new_mem, + bool evicted) +{ + struct amdgpu_vm_bo_base *bo_base; + + for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { + struct amdgpu_vm *vm = bo_base->vm; + + spin_lock(&vm->status_lock); + amdgpu_vm_update_stats_locked(bo_base, bo->tbo.resource, -1); + amdgpu_vm_update_stats_locked(bo_base, new_mem, +1); + spin_unlock(&vm->status_lock); + } + + amdgpu_vm_bo_invalidate(bo, evicted); +} + /** * amdgpu_vm_get_block_size - calculate VM page table size as power of two * @@ -2594,6 +2688,16 @@ void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm) vm->is_compute_context = false; } +static int amdgpu_vm_stats_is_zero(struct amdgpu_vm *vm) +{ + for (int i = 0; i < __AMDGPU_PL_NUM; ++i) { + if (!(drm_memory_stats_is_zero(&vm->stats[i].drm) && + vm->stats[i].evicted == 0)) + return false; + } + return true; +} + /** * amdgpu_vm_fini - tear down a vm instance * @@ -2617,7 +2721,6 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) root = amdgpu_bo_ref(vm->root.bo); amdgpu_bo_reserve(root, true); - amdgpu_vm_put_task_info(vm->task_info); amdgpu_vm_set_pasid(adev, vm, 0); dma_fence_wait(vm->last_unlocked, false); dma_fence_put(vm->last_unlocked); @@ -2666,6 +2769,16 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) } ttm_lru_bulk_move_fini(&adev->mman.bdev, &vm->lru_bulk_move); + + if (!amdgpu_vm_stats_is_zero(vm)) { + struct amdgpu_task_info *ti = vm->task_info; + + dev_warn(adev->dev, + "VM memory stats for proc %s(%d) task %s(%d) is non-zero when fini\n", + ti->process_name, ti->pid, ti->task_name, ti->tgid); + } + + amdgpu_vm_put_task_info(vm->task_info); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 5d119ac26c4f..a3e128e373bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -35,6 +35,7 @@ #include "amdgpu_sync.h" #include "amdgpu_ring.h" #include "amdgpu_ids.h" +#include "amdgpu_ttm.h" struct drm_exec; @@ -202,9 +203,13 @@ struct amdgpu_vm_bo_base { /* protected by bo being reserved */ struct amdgpu_vm_bo_base *next; - /* protected by spinlock */ + /* protected by vm status_lock */ struct list_head vm_status; + /* if the bo is counted as shared in mem stats + * protected by vm status_lock */ + bool shared; + /* protected by the BO being reserved */ bool moved; }; @@ -324,10 +329,7 @@ struct amdgpu_vm_fault_info { struct amdgpu_mem_stats { struct drm_memory_stats drm; - /* buffers that requested this placement */ - uint64_t requested; - /* buffers that requested this placement - * but are currently evicted */ + /* buffers that requested this placement but are currently evicted */ uint64_t evicted; }; @@ -345,6 +347,9 @@ struct amdgpu_vm { /* Lock to protect vm_bo add/del/move on all lists of vm */ spinlock_t status_lock; + /* Memory statistics for this vm, protected by status_lock */ + struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM]; + /* Per-VM and PT BOs who needs a validation */ struct list_head evicted; @@ -524,8 +529,12 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, bool clear); bool amdgpu_vm_evictable(struct amdgpu_bo *bo); -void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, - struct amdgpu_bo *bo, bool evicted); +void amdgpu_vm_bo_invalidate(struct amdgpu_bo *bo, bool evicted); +void amdgpu_vm_update_stats(struct amdgpu_vm_bo_base *base, + struct ttm_resource *new_res, int sign); +void amdgpu_vm_bo_update_shared(struct amdgpu_bo *bo); +void amdgpu_vm_bo_move(struct amdgpu_bo *bo, struct ttm_resource *new_mem, + bool evicted); uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr); struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm, struct amdgpu_bo *bo); @@ -576,8 +585,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm); void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_get_memory(struct amdgpu_vm *vm, - struct amdgpu_mem_stats *stats, - unsigned int size); + struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM]); int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct amdgpu_bo_vm *vmbo, bool immediate); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index f78a0434a48f..b0bf21682115 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -537,6 +537,7 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) if (!entry->bo) return; + amdgpu_vm_update_stats(entry, entry->bo->tbo.resource, -1); entry->bo->vm_bo = NULL; ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 7d26a962f811..ff5e52025266 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -567,7 +567,6 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, else remaining_size -= size; } - mutex_unlock(&mgr->lock); if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && adjust_dcc_size) { struct drm_buddy_block *dcc_block; @@ -584,6 +583,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, (u64)vres->base.size, &vres->blocks); } + mutex_unlock(&mgr->lock); vres->base.start = 0; size = max_t(u64, amdgpu_vram_mgr_blocks_size(&vres->blocks), diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c index e209b5e101df..23b6f7a4aa4a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c @@ -427,7 +427,7 @@ void amdgpu_xcp_release_sched(struct amdgpu_device *adev, return; sched = entity->entity.rq->sched; - if (sched->ready) { + if (drm_sched_wqueue_ready(sched)) { ring = to_amdgpu_ring(entity->entity.rq->sched); atomic_dec(&adev->xcp_mgr->xcp[ring->xcp_id].ref_cnt); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 003522c2d902..5ba263fe5512 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -45,6 +45,7 @@ #include "clearstate_gfx10.h" #include "v10_structs.h" #include "gfx_v10_0.h" +#include "gfx_v10_0_cleaner_shader.h" #include "nbio_v2_3.h" /* @@ -4738,6 +4739,23 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block) break; } switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(10, 3, 0): + case IP_VERSION(10, 3, 2): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + adev->gfx.cleaner_shader_ptr = gfx_10_3_0_cleaner_shader_hex; + adev->gfx.cleaner_shader_size = sizeof(gfx_10_3_0_cleaner_shader_hex); + if (adev->gfx.me_fw_version >= 64 && + adev->gfx.pfp_fw_version >= 100 && + adev->gfx.mec_fw_version >= 122) { + adev->gfx.enable_cleaner_shader = true; + r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size); + if (r) { + adev->gfx.enable_cleaner_shader = false; + dev_err(adev->dev, "Failed to initialize cleaner shader\n"); + } + } + break; default: adev->gfx.enable_cleaner_shader = false; break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0_cleaner_shader.h b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0_cleaner_shader.h new file mode 100644 index 000000000000..663c2572d440 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0_cleaner_shader.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright 2025 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/* Define the cleaner shader gfx_10_3_0 */ +static const u32 gfx_10_3_0_cleaner_shader_hex[] = { + 0xb0804004, 0xbf8a0000, + 0xbe8203b8, 0xbefc0380, + 0x7e008480, 0x7e028480, + 0x7e048480, 0x7e068480, + 0x7e088480, 0x7e0a8480, + 0x7e0c8480, 0x7e0e8480, + 0xbefc0302, 0x80828802, + 0xbf84fff5, 0xbe8203ff, + 0x80000000, 0x87020002, + 0xbf840012, 0xbefe03c1, + 0xbeff03c1, 0xd7650001, + 0x0001007f, 0xd7660001, + 0x0002027e, 0x16020288, + 0xbe8203bf, 0xbefc03c1, + 0xd9382000, 0x00020201, + 0xd9386040, 0x00040401, + 0xd70f6a01, 0x000202ff, + 0x00000400, 0x80828102, + 0xbf84fff7, 0xbefc03ff, + 0x00000068, 0xbe803080, + 0xbe813080, 0xbe823080, + 0xbe833080, 0x80fc847c, + 0xbf84fffa, 0xbeea0480, + 0xbeec0480, 0xbeee0480, + 0xbef00480, 0xbef20480, + 0xbef40480, 0xbef60480, + 0xbef80480, 0xbefa0480, + 0xbf810000, 0xbf9f0000, + 0xbf9f0000, 0xbf9f0000, + 0xbf9f0000, 0xbf9f0000, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_3_0_cleaner_shader.asm b/drivers/gpu/drm/amd/amdgpu/gfx_v10_3_0_cleaner_shader.asm new file mode 100644 index 000000000000..0e1c246166c0 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_3_0_cleaner_shader.asm @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright 2025 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +// This shader is to clean LDS, SGPRs and VGPRs. It is first 64 Dwords or 256 bytes of 192 Dwords cleaner shader. +//To turn this shader program on for complitaion change this to main and lower shader main to main_1 + +// GFX10.3 : Clear SGPRs, VGPRs and LDS +// Launch 32 waves per CU (16 per SIMD) as a workgroup (threadgroup) to fill every wave slot +// Waves are "wave32" and have 64 VGPRs each, which uses all 1024 VGPRs per SIMD +// Waves are launched in "CU" mode, and the workgroup shares 64KB of LDS (half of the WGP's LDS) +// It takes 2 workgroups to use all of LDS: one on each CU of the WGP +// Each wave clears SGPRs 0 - 107 +// Each wave clears VGPRs 0 - 63 +// The first wave of the workgroup clears its 64KB of LDS +// The shader starts with "S_BARRIER" to ensure SPI has launched all waves of the workgroup +// before any wave in the workgroup could end. Without this, it is possible not all SGPRs get cleared. + + +shader main + asic(GFX10) + type(CS) + wave_size(32) +// Note: original source code from SQ team + +// +// Create 32 waves in a threadgroup (CS waves) +// Each allocates 64 VGPRs +// The workgroup allocates all of LDS (64kbytes) +// +// Takes about 2500 clocks to run. +// (theorhetical fastest = 1024clks vgpr + 640lds = 1660 clks) +// + S_BARRIER + s_mov_b32 s2, 0x00000038 // Loop 64/8=8 times (loop unrolled for performance) + s_mov_b32 m0, 0 + // + // CLEAR VGPRs + // +label_0005: + v_movreld_b32 v0, 0 + v_movreld_b32 v1, 0 + v_movreld_b32 v2, 0 + v_movreld_b32 v3, 0 + v_movreld_b32 v4, 0 + v_movreld_b32 v5, 0 + v_movreld_b32 v6, 0 + v_movreld_b32 v7, 0 + s_mov_b32 m0, s2 + s_sub_u32 s2, s2, 8 + s_cbranch_scc0 label_0005 + // + s_mov_b32 s2, 0x80000000 // Bit31 is first_wave + s_and_b32 s2, s2, s0 // sgpr0 has tg_size (first_wave) term as in ucode only COMPUTE_PGM_RSRC2.tg_size_en is set + s_cbranch_scc0 label_0023 // Clean LDS if its first wave of ThreadGroup/WorkGroup + // CLEAR LDS + // + s_mov_b32 exec_lo, 0xffffffff + s_mov_b32 exec_hi, 0xffffffff + v_mbcnt_lo_u32_b32 v1, exec_hi, 0 // Set V1 to thread-ID (0..63) + v_mbcnt_hi_u32_b32 v1, exec_lo, v1 // Set V1 to thread-ID (0..63) + v_mul_u32_u24 v1, 0x00000008, v1 // * 8, so each thread is a double-dword address (8byte) + s_mov_b32 s2, 0x00000003f // 64 loop iterations + s_mov_b32 m0, 0xffffffff + // Clear all of LDS space + // Each FirstWave of WorkGroup clears 64kbyte block + +label_001F: + ds_write2_b64 v1, v[2:3], v[2:3] offset1:32 + ds_write2_b64 v1, v[4:5], v[4:5] offset0:64 offset1:96 + v_add_co_u32 v1, vcc, 0x00000400, v1 + s_sub_u32 s2, s2, 1 + s_cbranch_scc0 label_001F + + // + // CLEAR SGPRs + // +label_0023: + s_mov_b32 m0, 0x00000068 // Loop 108/4=27 times (loop unrolled for performance) +label_sgpr_loop: + s_movreld_b32 s0, 0 + s_movreld_b32 s1, 0 + s_movreld_b32 s2, 0 + s_movreld_b32 s3, 0 + s_sub_u32 m0, m0, 4 + s_cbranch_scc0 label_sgpr_loop + + //clear vcc + s_mov_b32 flat_scratch_lo, 0 //clear flat scratch lo SGPR + s_mov_b32 flat_scratch_hi, 0 //clear flat scratch hi SGPR + s_mov_b64 vcc, 0 //clear vcc + s_mov_b64 ttmp0, 0 //Clear ttmp0 and ttmp1 + s_mov_b64 ttmp2, 0 //Clear ttmp2 and ttmp3 + s_mov_b64 ttmp4, 0 //Clear ttmp4 and ttmp5 + s_mov_b64 ttmp6, 0 //Clear ttmp6 and ttmp7 + s_mov_b64 ttmp8, 0 //Clear ttmp8 and ttmp9 + s_mov_b64 ttmp10, 0 //Clear ttmp10 and ttmp11 + s_mov_b64 ttmp12, 0 //Clear ttmp12 and ttmp13 + s_mov_b64 ttmp14, 0 //Clear ttmp14 and ttmp15 + + s_endpgm + +end + + diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index fe5d7cd814f7..56c06b72a70a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1891,6 +1891,7 @@ static u32 gfx_v11_0_get_rb_active_bitmap(struct amdgpu_device *adev) static void gfx_v11_0_setup_rb(struct amdgpu_device *adev) { + u32 rb_bitmap_per_sa; u32 rb_bitmap_width_per_sa; u32 max_sa; u32 active_sa_bitmap; @@ -1908,9 +1909,11 @@ static void gfx_v11_0_setup_rb(struct amdgpu_device *adev) adev->gfx.config.max_sh_per_se; rb_bitmap_width_per_sa = adev->gfx.config.max_backends_per_se / adev->gfx.config.max_sh_per_se; + rb_bitmap_per_sa = amdgpu_gfx_create_bitmask(rb_bitmap_width_per_sa); + for (i = 0; i < max_sa; i++) { if (active_sa_bitmap & (1 << i)) - active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa)); + active_rb_bitmap |= (rb_bitmap_per_sa << (i * rb_bitmap_width_per_sa)); } active_rb_bitmap &= global_active_rb_bitmap; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 40c47a2dd060..2523221a2519 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -1352,6 +1352,14 @@ static int gfx_v12_0_sw_init(struct amdgpu_ip_block *ip_block) } switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(12, 0, 0): + case IP_VERSION(12, 0, 1): + if (adev->gfx.me_fw_version >= 2480 && + adev->gfx.pfp_fw_version >= 2530 && + adev->gfx.mec_fw_version >= 2680 && + adev->mes.fw_version[0] >= 100) + adev->gfx.enable_cleaner_shader = true; + break; default: adev->gfx.enable_cleaner_shader = false; break; @@ -1442,11 +1450,19 @@ static int gfx_v12_0_sw_init(struct amdgpu_ip_block *ip_block) } } - /* TODO: Add queue reset mask when FW fully supports it */ adev->gfx.gfx_supported_reset = amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]); adev->gfx.compute_supported_reset = amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]); + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(12, 0, 0): + case IP_VERSION(12, 0, 1): + if ((adev->gfx.me_fw_version >= 2660) && + (adev->gfx.mec_fw_version >= 2920)) { + adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; + adev->gfx.gfx_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; + } + } if (!adev->enable_mes_kiq) { r = amdgpu_gfx_kiq_init(adev, GFX12_MEC_HPD_SIZE, 0); @@ -1615,6 +1631,7 @@ static u32 gfx_v12_0_get_rb_active_bitmap(struct amdgpu_device *adev) static void gfx_v12_0_setup_rb(struct amdgpu_device *adev) { + u32 rb_bitmap_per_sa; u32 rb_bitmap_width_per_sa; u32 max_sa; u32 active_sa_bitmap; @@ -1632,12 +1649,14 @@ static void gfx_v12_0_setup_rb(struct amdgpu_device *adev) adev->gfx.config.max_sh_per_se; rb_bitmap_width_per_sa = adev->gfx.config.max_backends_per_se / adev->gfx.config.max_sh_per_se; + rb_bitmap_per_sa = amdgpu_gfx_create_bitmask(rb_bitmap_width_per_sa); + for (i = 0; i < max_sa; i++) { if (active_sa_bitmap & (1 << i)) - active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa)); + active_rb_bitmap |= (rb_bitmap_per_sa << (i * rb_bitmap_width_per_sa)); } - active_rb_bitmap |= global_active_rb_bitmap; + active_rb_bitmap &= global_active_rb_bitmap; adev->gfx.config.backend_enable_mask = active_rb_bitmap; adev->gfx.config.num_rbs = hweight32(active_rb_bitmap); } @@ -4002,17 +4021,6 @@ static void gfx_v12_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade if (def != data) WREG32_SOC15(GC, 0, regRLC_CGCG_CGLS_CTRL_3D, data); - - data = RREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL); - data &= ~SDMA0_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; - WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data); - - /* Some ASICs only have one SDMA instance, not need to configure SDMA1 */ - if (adev->sdma.num_instances > 1) { - data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); - data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; - WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); - } } } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index af73f85527b7..6a025438f9d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -5639,8 +5639,6 @@ static void gfx_v8_0_update_medium_grain_clock_gating(struct amdgpu_device *adev { uint32_t temp, data; - amdgpu_gfx_rlc_enter_safe_mode(adev, 0); - /* It is disabled by HW by default */ if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) { if (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) { @@ -5734,8 +5732,6 @@ static void gfx_v8_0_update_medium_grain_clock_gating(struct amdgpu_device *adev /* 7- wait for RLC_SERDES_CU_MASTER & RLC_SERDES_NONCU_MASTER idle */ gfx_v8_0_wait_for_rlc_serdes(adev); } - - amdgpu_gfx_rlc_exit_safe_mode(adev, 0); } static void gfx_v8_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev, @@ -5745,8 +5741,6 @@ static void gfx_v8_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev temp = data = RREG32(mmRLC_CGCG_CGLS_CTRL); - amdgpu_gfx_rlc_enter_safe_mode(adev, 0); - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)) { temp1 = data1 = RREG32(mmRLC_CGTT_MGCG_OVERRIDE); data1 &= ~RLC_CGTT_MGCG_OVERRIDE__CGCG_MASK; @@ -5827,12 +5821,12 @@ static void gfx_v8_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev } gfx_v8_0_wait_for_rlc_serdes(adev); - - amdgpu_gfx_rlc_exit_safe_mode(adev, 0); } static int gfx_v8_0_update_gfx_clock_gating(struct amdgpu_device *adev, bool enable) { + amdgpu_gfx_rlc_enter_safe_mode(adev, 0); + if (enable) { /* CGCG/CGLS should be enabled after MGCG/MGLS/TS(CG/LS) * === MGCG + MGLS + TS(CG/LS) === @@ -5846,6 +5840,8 @@ static int gfx_v8_0_update_gfx_clock_gating(struct amdgpu_device *adev, gfx_v8_0_update_coarse_grain_clock_gating(adev, enable); gfx_v8_0_update_medium_grain_clock_gating(adev, enable); } + + amdgpu_gfx_rlc_exit_safe_mode(adev, 0); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 4b5006dc3d34..fa572b40989e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -4964,8 +4964,6 @@ static void gfx_v9_0_update_medium_grain_clock_gating(struct amdgpu_device *adev { uint32_t data, def; - amdgpu_gfx_rlc_enter_safe_mode(adev, 0); - /* It is disabled by HW by default */ if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) { /* 1 - RLC_CGTT_MGCG_OVERRIDE */ @@ -5030,8 +5028,6 @@ static void gfx_v9_0_update_medium_grain_clock_gating(struct amdgpu_device *adev WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data); } } - - amdgpu_gfx_rlc_exit_safe_mode(adev, 0); } static void gfx_v9_0_update_3d_clock_gating(struct amdgpu_device *adev, @@ -5042,8 +5038,6 @@ static void gfx_v9_0_update_3d_clock_gating(struct amdgpu_device *adev, if (!adev->gfx.num_gfx_rings) return; - amdgpu_gfx_rlc_enter_safe_mode(adev, 0); - /* Enable 3D CGCG/CGLS */ if (enable) { /* write cmd to clear cgcg/cgls ov */ @@ -5085,8 +5079,6 @@ static void gfx_v9_0_update_3d_clock_gating(struct amdgpu_device *adev, if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D, data); } - - amdgpu_gfx_rlc_exit_safe_mode(adev, 0); } static void gfx_v9_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev, @@ -5094,8 +5086,6 @@ static void gfx_v9_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev { uint32_t def, data; - amdgpu_gfx_rlc_enter_safe_mode(adev, 0); - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)) { def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); /* unset CGCG override */ @@ -5137,13 +5127,12 @@ static void gfx_v9_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, data); } - - amdgpu_gfx_rlc_exit_safe_mode(adev, 0); } static int gfx_v9_0_update_gfx_clock_gating(struct amdgpu_device *adev, bool enable) { + amdgpu_gfx_rlc_enter_safe_mode(adev, 0); if (enable) { /* CGCG/CGLS should be enabled after MGCG/MGLS * === MGCG + MGLS === @@ -5163,6 +5152,7 @@ static int gfx_v9_0_update_gfx_clock_gating(struct amdgpu_device *adev, /* === MGCG + MGLS === */ gfx_v9_0_update_medium_grain_clock_gating(adev, enable); } + amdgpu_gfx_rlc_exit_safe_mode(adev, 0); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index a5bdcaf7a081..2ba185875baa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -579,11 +579,16 @@ static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev, { int err; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, AMDGPU_UCODE_REQUIRED, "amdgpu/%s_sjt_mec.bin", chip_name); - else + + if (err) + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, + AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_mec.bin", chip_name); + } else err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, AMDGPU_UCODE_REQUIRED, "amdgpu/%s_mec.bin", chip_name); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 5b537806b4da..901e924e69ad 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -756,7 +756,8 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) if (amdgpu_mes_log_enable) { mes_set_hw_res_pkt.enable_mes_event_int_logging = 1; - mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr + pipe * AMDGPU_MES_LOG_BUFFER_SIZE; + mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr + + pipe * (AMDGPU_MES_LOG_BUFFER_SIZE + AMDGPU_MES_MSCRATCH_SIZE); } if (enforce_isolation) @@ -983,29 +984,50 @@ static void mes_v12_0_enable(struct amdgpu_device *adev, bool enable) uint32_t pipe, data = 0; if (enable) { - data = RREG32_SOC15(GC, 0, regCP_MES_CNTL); - data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE0_RESET, 1); - data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, 1); - WREG32_SOC15(GC, 0, regCP_MES_CNTL, data); - mutex_lock(&adev->srbm_mutex); for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { soc21_grbm_select(adev, 3, pipe, 0, 0); + if (amdgpu_mes_log_enable) { + u32 log_size = AMDGPU_MES_LOG_BUFFER_SIZE + AMDGPU_MES_MSCRATCH_SIZE; + /* In case uni mes is not enabled, only program for pipe 0 */ + if (adev->mes.event_log_size >= (pipe + 1) * log_size) { + WREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_LO, + lower_32_bits(adev->mes.event_log_gpu_addr + + pipe * log_size + AMDGPU_MES_LOG_BUFFER_SIZE)); + WREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_HI, + upper_32_bits(adev->mes.event_log_gpu_addr + + pipe * log_size + AMDGPU_MES_LOG_BUFFER_SIZE)); + dev_info(adev->dev, "Setup CP MES MSCRATCH address : 0x%x. 0x%x\n", + RREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_HI), + RREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_LO)); + } + } + + data = RREG32_SOC15(GC, 0, regCP_MES_CNTL); + if (pipe == 0) + data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE0_RESET, 1); + else + data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, 1); + WREG32_SOC15(GC, 0, regCP_MES_CNTL, data); ucode_addr = adev->mes.uc_start_addr[pipe] >> 2; WREG32_SOC15(GC, 0, regCP_MES_PRGRM_CNTR_START, lower_32_bits(ucode_addr)); WREG32_SOC15(GC, 0, regCP_MES_PRGRM_CNTR_START_HI, upper_32_bits(ucode_addr)); + + /* unhalt MES and activate one pipe each loop */ + data = REG_SET_FIELD(0, CP_MES_CNTL, MES_PIPE0_ACTIVE, 1); + if (pipe) + data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_ACTIVE, 1); + dev_info(adev->dev, "program CP_MES_CNTL : 0x%x\n", data); + + WREG32_SOC15(GC, 0, regCP_MES_CNTL, data); + } soc21_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); - /* unhalt MES and activate pipe0 */ - data = REG_SET_FIELD(0, CP_MES_CNTL, MES_PIPE0_ACTIVE, 1); - data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_ACTIVE, 1); - WREG32_SOC15(GC, 0, regCP_MES_CNTL, data); - if (amdgpu_emu_mode) msleep(100); else if (adev->enable_uni_mes) @@ -1479,8 +1501,9 @@ static int mes_v12_0_sw_init(struct amdgpu_ip_block *ip_block) adev->mes.kiq_hw_fini = &mes_v12_0_kiq_hw_fini; adev->mes.enable_legacy_queue_map = true; - adev->mes.event_log_size = adev->enable_uni_mes ? (AMDGPU_MAX_MES_PIPES * AMDGPU_MES_LOG_BUFFER_SIZE) : AMDGPU_MES_LOG_BUFFER_SIZE; - + adev->mes.event_log_size = adev->enable_uni_mes ? + (AMDGPU_MAX_MES_PIPES * (AMDGPU_MES_LOG_BUFFER_SIZE + AMDGPU_MES_MSCRATCH_SIZE)) : + (AMDGPU_MES_LOG_BUFFER_SIZE + AMDGPU_MES_MSCRATCH_SIZE); r = amdgpu_mes_init(adev); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index 56507ae919b0..5e0066cd6c51 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -1406,6 +1406,12 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block) &adev->sdma.srbm_write_irq); if (r) return r; + + r = amdgpu_irq_add_id(adev, sdma_v4_4_2_seq_to_irq_id(i), + SDMA0_4_0__SRCID__SDMA_CTXEMPTY, + &adev->sdma.ctxt_empty_irq); + if (r) + return r; } for (i = 0; i < adev->sdma.num_instances; i++) { @@ -1602,7 +1608,7 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid) int i, r; u32 inst_mask; - if ((adev->flags & AMD_IS_APU) || amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) return -EINVAL; /* stop queue */ @@ -1814,6 +1820,16 @@ static int sdma_v4_4_2_process_srbm_write_irq(struct amdgpu_device *adev, return 0; } +static int sdma_v4_4_2_process_ctxt_empty_irq(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + struct amdgpu_iv_entry *entry) +{ + /* There is nothing useful to be done here, only kept for debug */ + dev_dbg_ratelimited(adev->dev, "SDMA context empty interrupt"); + sdma_v4_4_2_print_iv_entry(adev, entry); + return 0; +} + static void sdma_v4_4_2_inst_update_medium_grain_light_sleep( struct amdgpu_device *adev, bool enable, uint32_t inst_mask) { @@ -2096,6 +2112,10 @@ static const struct amdgpu_irq_src_funcs sdma_v4_4_2_srbm_write_irq_funcs = { .process = sdma_v4_4_2_process_srbm_write_irq, }; +static const struct amdgpu_irq_src_funcs sdma_v4_4_2_ctxt_empty_irq_funcs = { + .process = sdma_v4_4_2_process_ctxt_empty_irq, +}; + static void sdma_v4_4_2_set_irq_funcs(struct amdgpu_device *adev) { adev->sdma.trap_irq.num_types = adev->sdma.num_instances; @@ -2104,6 +2124,7 @@ static void sdma_v4_4_2_set_irq_funcs(struct amdgpu_device *adev) adev->sdma.doorbell_invalid_irq.num_types = adev->sdma.num_instances; adev->sdma.pool_timeout_irq.num_types = adev->sdma.num_instances; adev->sdma.srbm_write_irq.num_types = adev->sdma.num_instances; + adev->sdma.ctxt_empty_irq.num_types = adev->sdma.num_instances; adev->sdma.trap_irq.funcs = &sdma_v4_4_2_trap_irq_funcs; adev->sdma.illegal_inst_irq.funcs = &sdma_v4_4_2_illegal_inst_irq_funcs; @@ -2112,6 +2133,7 @@ static void sdma_v4_4_2_set_irq_funcs(struct amdgpu_device *adev) adev->sdma.doorbell_invalid_irq.funcs = &sdma_v4_4_2_doorbell_invalid_irq_funcs; adev->sdma.pool_timeout_irq.funcs = &sdma_v4_4_2_pool_timeout_irq_funcs; adev->sdma.srbm_write_irq.funcs = &sdma_v4_4_2_srbm_write_irq_funcs; + adev->sdma.ctxt_empty_irq.funcs = &sdma_v4_4_2_ctxt_empty_irq_funcs; } /** diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index 388b44ed5928..984f0e705078 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -274,7 +274,7 @@ static const uint32_t cwsr_trap_gfx8_hex[] = { static const uint32_t cwsr_trap_gfx9_hex[] = { - 0xbf820001, 0xbf820258, + 0xbf820001, 0xbf820259, 0xb8f8f802, 0x8978ff78, 0x00020006, 0xb8fbf803, 0x866eff78, 0x00002000, @@ -390,141 +390,36 @@ static const uint32_t cwsr_trap_gfx9_hex[] = { 0xbefe007c, 0xbefc0070, 0xc0611c7a, 0x0000007c, 0xbf8cc07f, 0x80708470, - 0xbefc007e, 0x867aff7f, - 0x04000000, 0xbeef0080, - 0x876f6f7a, 0xb8f02a05, - 0x80708170, 0x8e708a70, - 0xb8fb1605, 0x807b817b, - 0x8e7b847b, 0x8e76827b, - 0xbef600ff, 0x01000000, - 0xbef20174, 0x80747074, - 0x82758075, 0xbefc0080, - 0xbf800000, 0xbe802b00, - 0xbe822b02, 0xbe842b04, - 0xbe862b06, 0xbe882b08, - 0xbe8a2b0a, 0xbe8c2b0c, - 0xbe8e2b0e, 0xc06b003a, - 0x00000000, 0xbf8cc07f, - 0xc06b013a, 0x00000010, - 0xbf8cc07f, 0xc06b023a, - 0x00000020, 0xbf8cc07f, - 0xc06b033a, 0x00000030, - 0xbf8cc07f, 0x8074c074, - 0x82758075, 0x807c907c, - 0xbf0a7b7c, 0xbf85ffe7, - 0xbef40172, 0xbef00080, - 0xbefe00c1, 0xbeff00c1, - 0xbee80080, 0xbee90080, - 0xbef600ff, 0x01000000, - 0x867aff78, 0x00400000, - 0xbf850003, 0xb8faf803, - 0x897a7aff, 0x10000000, - 0xbf85004d, 0xbe840080, - 0xd2890000, 0x00000900, - 0x80048104, 0xd2890001, - 0x00000900, 0x80048104, - 0xd2890002, 0x00000900, - 0x80048104, 0xd2890003, - 0x00000900, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000901, 0x80048104, - 0xd2890001, 0x00000901, - 0x80048104, 0xd2890002, - 0x00000901, 0x80048104, - 0xd2890003, 0x00000901, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000902, - 0x80048104, 0xd2890001, - 0x00000902, 0x80048104, - 0xd2890002, 0x00000902, - 0x80048104, 0xd2890003, - 0x00000902, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000903, 0x80048104, - 0xd2890001, 0x00000903, - 0x80048104, 0xd2890002, - 0x00000903, 0x80048104, - 0xd2890003, 0x00000903, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbf820008, - 0xe0724000, 0x701d0000, - 0xe0724100, 0x701d0100, - 0xe0724200, 0x701d0200, - 0xe0724300, 0x701d0300, - 0xbefe00c1, 0xbeff00c1, - 0xb8fb4306, 0x867bc17b, - 0xbf840063, 0xbf8a0000, - 0x867aff6f, 0x04000000, - 0xbf84005f, 0x8e7b867b, - 0x8e7b827b, 0xbef6007b, + 0xbefc007e, 0xbf108080, + 0x867aff7f, 0x04000000, + 0xbeef0080, 0x876f6f7a, 0xb8f02a05, 0x80708170, - 0x8e708a70, 0xb8fa1605, - 0x807a817a, 0x8e7a867a, - 0x80707a70, 0x8070ff70, - 0x00000080, 0xbef600ff, - 0x01000000, 0xbefc0080, - 0xd28c0002, 0x000100c1, - 0xd28d0003, 0x000204c1, - 0x867aff78, 0x00400000, - 0xbf850003, 0xb8faf803, - 0x897a7aff, 0x10000000, - 0xbf850030, 0x24040682, - 0xd86e4000, 0x00000002, - 0xbf8cc07f, 0xbe840080, - 0xd2890000, 0x00000900, - 0x80048104, 0xd2890001, - 0x00000900, 0x80048104, - 0xd2890002, 0x00000900, - 0x80048104, 0xd2890003, - 0x00000900, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000901, 0x80048104, - 0xd2890001, 0x00000901, - 0x80048104, 0xd2890002, - 0x00000901, 0x80048104, - 0xd2890003, 0x00000901, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0x680404ff, - 0x00000200, 0xd0c9006a, - 0x0000f702, 0xbf87ffd2, - 0xbf820015, 0xd1060002, - 0x00011103, 0x7e0602ff, - 0x00000200, 0xbefc00ff, - 0x00010000, 0xbe800077, - 0x8677ff77, 0xff7fffff, - 0x8777ff77, 0x00058000, - 0xd8ec0000, 0x00000002, - 0xbf8cc07f, 0xe0765000, - 0x701d0002, 0x68040702, - 0xd0c9006a, 0x0000f702, - 0xbf87fff7, 0xbef70000, - 0xbef000ff, 0x00000400, - 0xbefe00c1, 0xbeff00c1, - 0xb8fb2a05, 0x807b817b, - 0x8e7b827b, 0xbef600ff, - 0x01000000, 0xbefc0084, - 0xbf0a7b7c, 0xbf84006d, - 0xbf11017c, 0x807bff7b, - 0x00001000, 0x867aff78, + 0x8e708a70, 0xb8fb1605, + 0x807b817b, 0x8e7b847b, + 0x8e76827b, 0xbef600ff, + 0x01000000, 0xbef20174, + 0x80747074, 0x82758075, + 0xbefc0080, 0xbf800000, + 0xbe802b00, 0xbe822b02, + 0xbe842b04, 0xbe862b06, + 0xbe882b08, 0xbe8a2b0a, + 0xbe8c2b0c, 0xbe8e2b0e, + 0xc06b003a, 0x00000000, + 0xbf8cc07f, 0xc06b013a, + 0x00000010, 0xbf8cc07f, + 0xc06b023a, 0x00000020, + 0xbf8cc07f, 0xc06b033a, + 0x00000030, 0xbf8cc07f, + 0x8074c074, 0x82758075, + 0x807c907c, 0xbf0a7b7c, + 0xbf85ffe7, 0xbef40172, + 0xbef00080, 0xbefe00c1, + 0xbeff00c1, 0xbee80080, + 0xbee90080, 0xbef600ff, + 0x01000000, 0x867aff78, 0x00400000, 0xbf850003, 0xb8faf803, 0x897a7aff, - 0x10000000, 0xbf850051, + 0x10000000, 0xbf85004d, 0xbe840080, 0xd2890000, 0x00000900, 0x80048104, 0xd2890001, 0x00000900, @@ -563,118 +458,224 @@ static const uint32_t cwsr_trap_gfx9_hex[] = { 0xc069003a, 0x00000070, 0xbf8cc07f, 0x80709070, 0xbf06c004, 0xbf84ffee, - 0x807c847c, 0xbf0a7b7c, - 0xbf85ffb1, 0xbf9c0000, - 0xbf820012, 0x7e000300, - 0x7e020301, 0x7e040302, - 0x7e060303, 0xe0724000, + 0xbf820008, 0xe0724000, 0x701d0000, 0xe0724100, 0x701d0100, 0xe0724200, 0x701d0200, 0xe0724300, - 0x701d0300, 0x807c847c, - 0x8070ff70, 0x00000400, - 0xbf0a7b7c, 0xbf85ffef, - 0xbf9c0000, 0xbf8200c7, - 0xbef4007e, 0x8675ff7f, - 0x0000ffff, 0x8775ff75, - 0x00040000, 0xbef60080, - 0xbef700ff, 0x00807fac, - 0x866eff7f, 0x04000000, - 0xbf84001e, 0xbefe00c1, - 0xbeff00c1, 0xb8ef4306, - 0x866fc16f, 0xbf840019, - 0x8e6f866f, 0x8e6f826f, - 0xbef6006f, 0xb8f82a05, - 0x80788178, 0x8e788a78, - 0xb8ee1605, 0x806e816e, - 0x8e6e866e, 0x80786e78, - 0x8078ff78, 0x00000080, + 0x701d0300, 0xbefe00c1, + 0xbeff00c1, 0xb8fb4306, + 0x867bc17b, 0xbf840063, + 0xbf8a0000, 0x867aff6f, + 0x04000000, 0xbf84005f, + 0x8e7b867b, 0x8e7b827b, + 0xbef6007b, 0xb8f02a05, + 0x80708170, 0x8e708a70, + 0xb8fa1605, 0x807a817a, + 0x8e7a867a, 0x80707a70, + 0x8070ff70, 0x00000080, 0xbef600ff, 0x01000000, - 0xbefc0080, 0xe0510000, - 0x781d0000, 0xe0510100, - 0x781d0000, 0x807cff7c, - 0x00000200, 0x8078ff78, - 0x00000200, 0xbf0a6f7c, - 0xbf85fff6, 0xbefe00c1, - 0xbeff00c1, 0xbef600ff, - 0x01000000, 0xb8ef2a05, - 0x806f816f, 0x8e6f826f, - 0x806fff6f, 0x00008000, - 0xbef80080, 0xbeee0078, - 0x8078ff78, 0x00000400, - 0xbefc0084, 0xbf11087c, - 0xe0524000, 0x781d0000, - 0xe0524100, 0x781d0100, - 0xe0524200, 0x781d0200, - 0xe0524300, 0x781d0300, - 0xbf8c0f70, 0x7e000300, - 0x7e020301, 0x7e040302, - 0x7e060303, 0x807c847c, - 0x8078ff78, 0x00000400, - 0xbf0a6f7c, 0xbf85ffee, - 0xbf9c0000, 0xe0524000, - 0x6e1d0000, 0xe0524100, - 0x6e1d0100, 0xe0524200, - 0x6e1d0200, 0xe0524300, - 0x6e1d0300, 0xbf8c0f70, + 0xbefc0080, 0xd28c0002, + 0x000100c1, 0xd28d0003, + 0x000204c1, 0x867aff78, + 0x00400000, 0xbf850003, + 0xb8faf803, 0x897a7aff, + 0x10000000, 0xbf850030, + 0x24040682, 0xd86e4000, + 0x00000002, 0xbf8cc07f, + 0xbe840080, 0xd2890000, + 0x00000900, 0x80048104, + 0xd2890001, 0x00000900, + 0x80048104, 0xd2890002, + 0x00000900, 0x80048104, + 0xd2890003, 0x00000900, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0xbe840080, + 0xd2890000, 0x00000901, + 0x80048104, 0xd2890001, + 0x00000901, 0x80048104, + 0xd2890002, 0x00000901, + 0x80048104, 0xd2890003, + 0x00000901, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0x680404ff, 0x00000200, + 0xd0c9006a, 0x0000f702, + 0xbf87ffd2, 0xbf820015, + 0xd1060002, 0x00011103, + 0x7e0602ff, 0x00000200, + 0xbefc00ff, 0x00010000, + 0xbe800077, 0x8677ff77, + 0xff7fffff, 0x8777ff77, + 0x00058000, 0xd8ec0000, + 0x00000002, 0xbf8cc07f, + 0xe0765000, 0x701d0002, + 0x68040702, 0xd0c9006a, + 0x0000f702, 0xbf87fff7, + 0xbef70000, 0xbef000ff, + 0x00000400, 0xbefe00c1, + 0xbeff00c1, 0xb8fb2a05, + 0x807b817b, 0x8e7b827b, + 0xbef600ff, 0x01000000, + 0xbefc0084, 0xbf0a7b7c, + 0xbf84006d, 0xbf11017c, + 0x807bff7b, 0x00001000, + 0x867aff78, 0x00400000, + 0xbf850003, 0xb8faf803, + 0x897a7aff, 0x10000000, + 0xbf850051, 0xbe840080, + 0xd2890000, 0x00000900, + 0x80048104, 0xd2890001, + 0x00000900, 0x80048104, + 0xd2890002, 0x00000900, + 0x80048104, 0xd2890003, + 0x00000900, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000901, 0x80048104, + 0xd2890001, 0x00000901, + 0x80048104, 0xd2890002, + 0x00000901, 0x80048104, + 0xd2890003, 0x00000901, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0xbe840080, + 0xd2890000, 0x00000902, + 0x80048104, 0xd2890001, + 0x00000902, 0x80048104, + 0xd2890002, 0x00000902, + 0x80048104, 0xd2890003, + 0x00000902, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000903, 0x80048104, + 0xd2890001, 0x00000903, + 0x80048104, 0xd2890002, + 0x00000903, 0x80048104, + 0xd2890003, 0x00000903, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0x807c847c, + 0xbf0a7b7c, 0xbf85ffb1, + 0xbf9c0000, 0xbf820012, + 0x7e000300, 0x7e020301, + 0x7e040302, 0x7e060303, + 0xe0724000, 0x701d0000, + 0xe0724100, 0x701d0100, + 0xe0724200, 0x701d0200, + 0xe0724300, 0x701d0300, + 0x807c847c, 0x8070ff70, + 0x00000400, 0xbf0a7b7c, + 0xbf85ffef, 0xbf9c0000, + 0xbf8200c7, 0xbef4007e, + 0x8675ff7f, 0x0000ffff, + 0x8775ff75, 0x00040000, + 0xbef60080, 0xbef700ff, + 0x00807fac, 0x866eff7f, + 0x04000000, 0xbf84001e, + 0xbefe00c1, 0xbeff00c1, + 0xb8ef4306, 0x866fc16f, + 0xbf840019, 0x8e6f866f, + 0x8e6f826f, 0xbef6006f, 0xb8f82a05, 0x80788178, 0x8e788a78, 0xb8ee1605, 0x806e816e, 0x8e6e866e, - 0x80786e78, 0x80f8c078, - 0xb8ef1605, 0x806f816f, - 0x8e6f846f, 0x8e76826f, + 0x80786e78, 0x8078ff78, + 0x00000080, 0xbef600ff, + 0x01000000, 0xbefc0080, + 0xe0510000, 0x781d0000, + 0xe0510100, 0x781d0000, + 0x807cff7c, 0x00000200, + 0x8078ff78, 0x00000200, + 0xbf0a6f7c, 0xbf85fff6, + 0xbefe00c1, 0xbeff00c1, 0xbef600ff, 0x01000000, - 0xbefc006f, 0xc031003a, - 0x00000078, 0x80f8c078, - 0xbf8cc07f, 0x80fc907c, - 0xbf800000, 0xbe802d00, - 0xbe822d02, 0xbe842d04, - 0xbe862d06, 0xbe882d08, - 0xbe8a2d0a, 0xbe8c2d0c, - 0xbe8e2d0e, 0xbf06807c, - 0xbf84fff0, 0xb8f82a05, + 0xb8ef2a05, 0x806f816f, + 0x8e6f826f, 0x806fff6f, + 0x00008000, 0xbef80080, + 0xbeee0078, 0x8078ff78, + 0x00000400, 0xbefc0084, + 0xbf11087c, 0xe0524000, + 0x781d0000, 0xe0524100, + 0x781d0100, 0xe0524200, + 0x781d0200, 0xe0524300, + 0x781d0300, 0xbf8c0f70, + 0x7e000300, 0x7e020301, + 0x7e040302, 0x7e060303, + 0x807c847c, 0x8078ff78, + 0x00000400, 0xbf0a6f7c, + 0xbf85ffee, 0xbf9c0000, + 0xe0524000, 0x6e1d0000, + 0xe0524100, 0x6e1d0100, + 0xe0524200, 0x6e1d0200, + 0xe0524300, 0x6e1d0300, + 0xbf8c0f70, 0xb8f82a05, 0x80788178, 0x8e788a78, 0xb8ee1605, 0x806e816e, 0x8e6e866e, 0x80786e78, - 0xbef60084, 0xbef600ff, - 0x01000000, 0xc0211bfa, + 0x80f8c078, 0xb8ef1605, + 0x806f816f, 0x8e6f846f, + 0x8e76826f, 0xbef600ff, + 0x01000000, 0xbefc006f, + 0xc031003a, 0x00000078, + 0x80f8c078, 0xbf8cc07f, + 0x80fc907c, 0xbf800000, + 0xbe802d00, 0xbe822d02, + 0xbe842d04, 0xbe862d06, + 0xbe882d08, 0xbe8a2d0a, + 0xbe8c2d0c, 0xbe8e2d0e, + 0xbf06807c, 0xbf84fff0, + 0xb8f82a05, 0x80788178, + 0x8e788a78, 0xb8ee1605, + 0x806e816e, 0x8e6e866e, + 0x80786e78, 0xbef60084, + 0xbef600ff, 0x01000000, + 0xc0211bfa, 0x00000078, + 0x80788478, 0xc0211b3a, 0x00000078, 0x80788478, - 0xc0211b3a, 0x00000078, - 0x80788478, 0xc0211b7a, + 0xc0211b7a, 0x00000078, + 0x80788478, 0xc0211c3a, 0x00000078, 0x80788478, - 0xc0211c3a, 0x00000078, - 0x80788478, 0xc0211c7a, + 0xc0211c7a, 0x00000078, + 0x80788478, 0xc0211eba, 0x00000078, 0x80788478, - 0xc0211eba, 0x00000078, - 0x80788478, 0xc0211efa, + 0xc0211efa, 0x00000078, + 0x80788478, 0xc0211a3a, 0x00000078, 0x80788478, - 0xc0211a3a, 0x00000078, - 0x80788478, 0xc0211a7a, + 0xc0211a7a, 0x00000078, + 0x80788478, 0xc0211cfa, 0x00000078, 0x80788478, - 0xc0211cfa, 0x00000078, - 0x80788478, 0xbf8cc07f, - 0xbefc006f, 0xbefe0070, - 0xbeff0071, 0x866f7bff, - 0x000003ff, 0xb96f4803, - 0x866f7bff, 0xfffff800, - 0x8f6f8b6f, 0xb96fa2c3, - 0xb973f801, 0xb8ee2a05, - 0x806e816e, 0x8e6e8a6e, - 0xb8ef1605, 0x806f816f, - 0x8e6f866f, 0x806e6f6e, - 0x806e746e, 0x826f8075, - 0x866fff6f, 0x0000ffff, - 0xc00b1c37, 0x00000050, - 0xc00b1d37, 0x00000060, - 0xc0031e77, 0x00000074, - 0xbf8cc07f, 0x8f6e8b77, - 0x866eff6e, 0x001f8000, - 0xb96ef807, 0x866dff6d, - 0x0000ffff, 0x86fe7e7e, - 0x86ea6a6a, 0x8f6e837a, - 0xb96ee0c2, 0xbf800002, - 0xb97a0002, 0xbf8a0000, - 0xbe801f6c, 0xbf9b0000, + 0xbf8cc07f, 0xbefc006f, + 0xbefe0070, 0xbeff0071, + 0x866f7bff, 0x000003ff, + 0xb96f4803, 0x866f7bff, + 0xfffff800, 0x8f6f8b6f, + 0xb96fa2c3, 0xb973f801, + 0xb8ee2a05, 0x806e816e, + 0x8e6e8a6e, 0xb8ef1605, + 0x806f816f, 0x8e6f866f, + 0x806e6f6e, 0x806e746e, + 0x826f8075, 0x866fff6f, + 0x0000ffff, 0xc00b1c37, + 0x00000050, 0xc00b1d37, + 0x00000060, 0xc0031e77, + 0x00000074, 0xbf8cc07f, + 0x8f6e8b77, 0x866eff6e, + 0x001f8000, 0xb96ef807, + 0x866dff6d, 0x0000ffff, + 0x86fe7e7e, 0x86ea6a6a, + 0x8f6e837a, 0xb96ee0c2, + 0xbf800002, 0xb97a0002, + 0xbf8a0000, 0xbe801f6c, + 0xbf9b0000, 0x00000000, }; static const uint32_t cwsr_trap_nv1x_hex[] = { @@ -1302,7 +1303,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = { }; static const uint32_t cwsr_trap_arcturus_hex[] = { - 0xbf820001, 0xbf8202d4, + 0xbf820001, 0xbf8202d5, 0xb8f8f802, 0x8978ff78, 0x00020006, 0xb8fbf803, 0x866eff78, 0x00002000, @@ -1419,99 +1420,37 @@ static const uint32_t cwsr_trap_arcturus_hex[] = { 0xbefe007c, 0xbefc0070, 0xc0611c7a, 0x0000007c, 0xbf8cc07f, 0x80708470, - 0xbefc007e, 0x867aff7f, - 0x04000000, 0xbeef0080, - 0x876f6f7a, 0xb8f02a05, - 0x80708170, 0x8e708a70, - 0x8e708170, 0xb8fb1605, - 0x807b817b, 0x8e7b847b, - 0x8e76827b, 0xbef600ff, - 0x01000000, 0xbef20174, - 0x80747074, 0x82758075, - 0xbefc0080, 0xbf800000, - 0xbe802b00, 0xbe822b02, - 0xbe842b04, 0xbe862b06, - 0xbe882b08, 0xbe8a2b0a, - 0xbe8c2b0c, 0xbe8e2b0e, - 0xc06b003a, 0x00000000, - 0xbf8cc07f, 0xc06b013a, - 0x00000010, 0xbf8cc07f, - 0xc06b023a, 0x00000020, - 0xbf8cc07f, 0xc06b033a, - 0x00000030, 0xbf8cc07f, - 0x8074c074, 0x82758075, - 0x807c907c, 0xbf0a7b7c, - 0xbf85ffe7, 0xbef40172, - 0xbef00080, 0xbefe00c1, - 0xbeff00c1, 0xbee80080, - 0xbee90080, 0xbef600ff, - 0x01000000, 0x867aff78, - 0x00400000, 0xbf850003, - 0xb8faf803, 0x897a7aff, - 0x10000000, 0xbf85004d, - 0xbe840080, 0xd2890000, - 0x00000900, 0x80048104, - 0xd2890001, 0x00000900, - 0x80048104, 0xd2890002, - 0x00000900, 0x80048104, - 0xd2890003, 0x00000900, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000901, - 0x80048104, 0xd2890001, - 0x00000901, 0x80048104, - 0xd2890002, 0x00000901, - 0x80048104, 0xd2890003, - 0x00000901, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000902, 0x80048104, - 0xd2890001, 0x00000902, - 0x80048104, 0xd2890002, - 0x00000902, 0x80048104, - 0xd2890003, 0x00000902, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000903, - 0x80048104, 0xd2890001, - 0x00000903, 0x80048104, - 0xd2890002, 0x00000903, - 0x80048104, 0xd2890003, - 0x00000903, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbf820008, 0xe0724000, - 0x701d0000, 0xe0724100, - 0x701d0100, 0xe0724200, - 0x701d0200, 0xe0724300, - 0x701d0300, 0xbefe00c1, - 0xbeff00c1, 0xb8fb4306, - 0x867bc17b, 0xbf840064, - 0xbf8a0000, 0x867aff6f, - 0x04000000, 0xbf840060, - 0x8e7b867b, 0x8e7b827b, - 0xbef6007b, 0xb8f02a05, - 0x80708170, 0x8e708a70, - 0x8e708170, 0xb8fa1605, - 0x807a817a, 0x8e7a867a, - 0x80707a70, 0x8070ff70, - 0x00000080, 0xbef600ff, - 0x01000000, 0xbefc0080, - 0xd28c0002, 0x000100c1, - 0xd28d0003, 0x000204c1, + 0xbefc007e, 0xbf108080, + 0x867aff7f, 0x04000000, + 0xbeef0080, 0x876f6f7a, + 0xb8f02a05, 0x80708170, + 0x8e708a70, 0x8e708170, + 0xb8fb1605, 0x807b817b, + 0x8e7b847b, 0x8e76827b, + 0xbef600ff, 0x01000000, + 0xbef20174, 0x80747074, + 0x82758075, 0xbefc0080, + 0xbf800000, 0xbe802b00, + 0xbe822b02, 0xbe842b04, + 0xbe862b06, 0xbe882b08, + 0xbe8a2b0a, 0xbe8c2b0c, + 0xbe8e2b0e, 0xc06b003a, + 0x00000000, 0xbf8cc07f, + 0xc06b013a, 0x00000010, + 0xbf8cc07f, 0xc06b023a, + 0x00000020, 0xbf8cc07f, + 0xc06b033a, 0x00000030, + 0xbf8cc07f, 0x8074c074, + 0x82758075, 0x807c907c, + 0xbf0a7b7c, 0xbf85ffe7, + 0xbef40172, 0xbef00080, + 0xbefe00c1, 0xbeff00c1, + 0xbee80080, 0xbee90080, + 0xbef600ff, 0x01000000, 0x867aff78, 0x00400000, 0xbf850003, 0xb8faf803, 0x897a7aff, 0x10000000, - 0xbf850030, 0x24040682, - 0xd86e4000, 0x00000002, - 0xbf8cc07f, 0xbe840080, + 0xbf85004d, 0xbe840080, 0xd2890000, 0x00000900, 0x80048104, 0xd2890001, 0x00000900, 0x80048104, @@ -1530,31 +1469,50 @@ static const uint32_t cwsr_trap_arcturus_hex[] = { 0x80048104, 0xc069003a, 0x00000070, 0xbf8cc07f, 0x80709070, 0xbf06c004, - 0xbf84ffee, 0x680404ff, - 0x00000200, 0xd0c9006a, - 0x0000f702, 0xbf87ffd2, - 0xbf820015, 0xd1060002, - 0x00011103, 0x7e0602ff, - 0x00000200, 0xbefc00ff, - 0x00010000, 0xbe800077, - 0x8677ff77, 0xff7fffff, - 0x8777ff77, 0x00058000, - 0xd8ec0000, 0x00000002, - 0xbf8cc07f, 0xe0765000, - 0x701d0002, 0x68040702, - 0xd0c9006a, 0x0000f702, - 0xbf87fff7, 0xbef70000, - 0xbef000ff, 0x00000400, + 0xbf84ffee, 0xbe840080, + 0xd2890000, 0x00000902, + 0x80048104, 0xd2890001, + 0x00000902, 0x80048104, + 0xd2890002, 0x00000902, + 0x80048104, 0xd2890003, + 0x00000902, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000903, 0x80048104, + 0xd2890001, 0x00000903, + 0x80048104, 0xd2890002, + 0x00000903, 0x80048104, + 0xd2890003, 0x00000903, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0xbf820008, + 0xe0724000, 0x701d0000, + 0xe0724100, 0x701d0100, + 0xe0724200, 0x701d0200, + 0xe0724300, 0x701d0300, 0xbefe00c1, 0xbeff00c1, - 0xb8fb2a05, 0x807b817b, - 0x8e7b827b, 0xbef600ff, - 0x01000000, 0xbefc0084, - 0xbf0a7b7c, 0xbf84006d, - 0xbf11017c, 0x807bff7b, - 0x00001000, 0x867aff78, + 0xb8fb4306, 0x867bc17b, + 0xbf840064, 0xbf8a0000, + 0x867aff6f, 0x04000000, + 0xbf840060, 0x8e7b867b, + 0x8e7b827b, 0xbef6007b, + 0xb8f02a05, 0x80708170, + 0x8e708a70, 0x8e708170, + 0xb8fa1605, 0x807a817a, + 0x8e7a867a, 0x80707a70, + 0x8070ff70, 0x00000080, + 0xbef600ff, 0x01000000, + 0xbefc0080, 0xd28c0002, + 0x000100c1, 0xd28d0003, + 0x000204c1, 0x867aff78, 0x00400000, 0xbf850003, 0xb8faf803, 0x897a7aff, - 0x10000000, 0xbf850051, + 0x10000000, 0xbf850030, + 0x24040682, 0xd86e4000, + 0x00000002, 0xbf8cc07f, 0xbe840080, 0xd2890000, 0x00000900, 0x80048104, 0xd2890001, 0x00000900, @@ -1574,215 +1532,259 @@ static const uint32_t cwsr_trap_arcturus_hex[] = { 0xc069003a, 0x00000070, 0xbf8cc07f, 0x80709070, 0xbf06c004, 0xbf84ffee, + 0x680404ff, 0x00000200, + 0xd0c9006a, 0x0000f702, + 0xbf87ffd2, 0xbf820015, + 0xd1060002, 0x00011103, + 0x7e0602ff, 0x00000200, + 0xbefc00ff, 0x00010000, + 0xbe800077, 0x8677ff77, + 0xff7fffff, 0x8777ff77, + 0x00058000, 0xd8ec0000, + 0x00000002, 0xbf8cc07f, + 0xe0765000, 0x701d0002, + 0x68040702, 0xd0c9006a, + 0x0000f702, 0xbf87fff7, + 0xbef70000, 0xbef000ff, + 0x00000400, 0xbefe00c1, + 0xbeff00c1, 0xb8fb2a05, + 0x807b817b, 0x8e7b827b, + 0xbef600ff, 0x01000000, + 0xbefc0084, 0xbf0a7b7c, + 0xbf84006d, 0xbf11017c, + 0x807bff7b, 0x00001000, + 0x867aff78, 0x00400000, + 0xbf850003, 0xb8faf803, + 0x897a7aff, 0x10000000, + 0xbf850051, 0xbe840080, + 0xd2890000, 0x00000900, + 0x80048104, 0xd2890001, + 0x00000900, 0x80048104, + 0xd2890002, 0x00000900, + 0x80048104, 0xd2890003, + 0x00000900, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, 0xbe840080, 0xd2890000, - 0x00000902, 0x80048104, - 0xd2890001, 0x00000902, + 0x00000901, 0x80048104, + 0xd2890001, 0x00000901, 0x80048104, 0xd2890002, - 0x00000902, 0x80048104, - 0xd2890003, 0x00000902, + 0x00000901, 0x80048104, + 0xd2890003, 0x00000901, 0x80048104, 0xc069003a, 0x00000070, 0xbf8cc07f, 0x80709070, 0xbf06c004, 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000903, + 0xd2890000, 0x00000902, 0x80048104, 0xd2890001, - 0x00000903, 0x80048104, - 0xd2890002, 0x00000903, + 0x00000902, 0x80048104, + 0xd2890002, 0x00000902, 0x80048104, 0xd2890003, - 0x00000903, 0x80048104, + 0x00000902, 0x80048104, 0xc069003a, 0x00000070, 0xbf8cc07f, 0x80709070, 0xbf06c004, 0xbf84ffee, - 0x807c847c, 0xbf0a7b7c, - 0xbf85ffb1, 0xbf9c0000, - 0xbf820012, 0x7e000300, - 0x7e020301, 0x7e040302, - 0x7e060303, 0xe0724000, - 0x701d0000, 0xe0724100, - 0x701d0100, 0xe0724200, - 0x701d0200, 0xe0724300, - 0x701d0300, 0x807c847c, - 0x8070ff70, 0x00000400, - 0xbf0a7b7c, 0xbf85ffef, - 0xbf9c0000, 0xbefc0080, - 0xbf11017c, 0x867aff78, - 0x00400000, 0xbf850003, - 0xb8faf803, 0x897a7aff, - 0x10000000, 0xbf850059, + 0xbe840080, 0xd2890000, + 0x00000903, 0x80048104, + 0xd2890001, 0x00000903, + 0x80048104, 0xd2890002, + 0x00000903, 0x80048104, + 0xd2890003, 0x00000903, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0x807c847c, + 0xbf0a7b7c, 0xbf85ffb1, + 0xbf9c0000, 0xbf820012, + 0x7e000300, 0x7e020301, + 0x7e040302, 0x7e060303, + 0xe0724000, 0x701d0000, + 0xe0724100, 0x701d0100, + 0xe0724200, 0x701d0200, + 0xe0724300, 0x701d0300, + 0x807c847c, 0x8070ff70, + 0x00000400, 0xbf0a7b7c, + 0xbf85ffef, 0xbf9c0000, + 0xbefc0080, 0xbf11017c, + 0x867aff78, 0x00400000, + 0xbf850003, 0xb8faf803, + 0x897a7aff, 0x10000000, + 0xbf850059, 0xd3d84000, + 0x18000100, 0xd3d84001, + 0x18000101, 0xd3d84002, + 0x18000102, 0xd3d84003, + 0x18000103, 0xbe840080, + 0xd2890000, 0x00000900, + 0x80048104, 0xd2890001, + 0x00000900, 0x80048104, + 0xd2890002, 0x00000900, + 0x80048104, 0xd2890003, + 0x00000900, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000901, 0x80048104, + 0xd2890001, 0x00000901, + 0x80048104, 0xd2890002, + 0x00000901, 0x80048104, + 0xd2890003, 0x00000901, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0xbe840080, + 0xd2890000, 0x00000902, + 0x80048104, 0xd2890001, + 0x00000902, 0x80048104, + 0xd2890002, 0x00000902, + 0x80048104, 0xd2890003, + 0x00000902, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000903, 0x80048104, + 0xd2890001, 0x00000903, + 0x80048104, 0xd2890002, + 0x00000903, 0x80048104, + 0xd2890003, 0x00000903, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0x807c847c, + 0xbf0a7b7c, 0xbf85ffa9, + 0xbf9c0000, 0xbf820016, 0xd3d84000, 0x18000100, 0xd3d84001, 0x18000101, 0xd3d84002, 0x18000102, 0xd3d84003, 0x18000103, - 0xbe840080, 0xd2890000, - 0x00000900, 0x80048104, - 0xd2890001, 0x00000900, - 0x80048104, 0xd2890002, - 0x00000900, 0x80048104, - 0xd2890003, 0x00000900, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000901, - 0x80048104, 0xd2890001, - 0x00000901, 0x80048104, - 0xd2890002, 0x00000901, - 0x80048104, 0xd2890003, - 0x00000901, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000902, 0x80048104, - 0xd2890001, 0x00000902, - 0x80048104, 0xd2890002, - 0x00000902, 0x80048104, - 0xd2890003, 0x00000902, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000903, - 0x80048104, 0xd2890001, - 0x00000903, 0x80048104, - 0xd2890002, 0x00000903, - 0x80048104, 0xd2890003, - 0x00000903, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0x807c847c, 0xbf0a7b7c, - 0xbf85ffa9, 0xbf9c0000, - 0xbf820016, 0xd3d84000, - 0x18000100, 0xd3d84001, - 0x18000101, 0xd3d84002, - 0x18000102, 0xd3d84003, - 0x18000103, 0xe0724000, - 0x701d0000, 0xe0724100, - 0x701d0100, 0xe0724200, - 0x701d0200, 0xe0724300, - 0x701d0300, 0x807c847c, - 0x8070ff70, 0x00000400, - 0xbf0a7b7c, 0xbf85ffeb, - 0xbf9c0000, 0xbf8200e3, - 0xbef4007e, 0x8675ff7f, - 0x0000ffff, 0x8775ff75, - 0x00040000, 0xbef60080, - 0xbef700ff, 0x00807fac, - 0x866eff7f, 0x04000000, - 0xbf84001f, 0xbefe00c1, - 0xbeff00c1, 0xb8ef4306, - 0x866fc16f, 0xbf84001a, - 0x8e6f866f, 0x8e6f826f, - 0xbef6006f, 0xb8f82a05, - 0x80788178, 0x8e788a78, - 0x8e788178, 0xb8ee1605, - 0x806e816e, 0x8e6e866e, - 0x80786e78, 0x8078ff78, - 0x00000080, 0xbef600ff, - 0x01000000, 0xbefc0080, - 0xe0510000, 0x781d0000, - 0xe0510100, 0x781d0000, - 0x807cff7c, 0x00000200, - 0x8078ff78, 0x00000200, - 0xbf0a6f7c, 0xbf85fff6, + 0xe0724000, 0x701d0000, + 0xe0724100, 0x701d0100, + 0xe0724200, 0x701d0200, + 0xe0724300, 0x701d0300, + 0x807c847c, 0x8070ff70, + 0x00000400, 0xbf0a7b7c, + 0xbf85ffeb, 0xbf9c0000, + 0xbf8200e3, 0xbef4007e, + 0x8675ff7f, 0x0000ffff, + 0x8775ff75, 0x00040000, + 0xbef60080, 0xbef700ff, + 0x00807fac, 0x866eff7f, + 0x04000000, 0xbf84001f, 0xbefe00c1, 0xbeff00c1, + 0xb8ef4306, 0x866fc16f, + 0xbf84001a, 0x8e6f866f, + 0x8e6f826f, 0xbef6006f, + 0xb8f82a05, 0x80788178, + 0x8e788a78, 0x8e788178, + 0xb8ee1605, 0x806e816e, + 0x8e6e866e, 0x80786e78, + 0x8078ff78, 0x00000080, 0xbef600ff, 0x01000000, - 0xb8ef2a05, 0x806f816f, - 0x8e6f826f, 0x806fff6f, - 0x00008000, 0xbef80080, - 0xbeee0078, 0x8078ff78, - 0x00000400, 0xbefc0084, - 0xbf11087c, 0xe0524000, - 0x781d0000, 0xe0524100, - 0x781d0100, 0xe0524200, - 0x781d0200, 0xe0524300, - 0x781d0300, 0xbf8c0f70, - 0x7e000300, 0x7e020301, - 0x7e040302, 0x7e060303, - 0x807c847c, 0x8078ff78, - 0x00000400, 0xbf0a6f7c, - 0xbf85ffee, 0xbefc0080, - 0xbf11087c, 0xe0524000, - 0x781d0000, 0xe0524100, - 0x781d0100, 0xe0524200, - 0x781d0200, 0xe0524300, - 0x781d0300, 0xbf8c0f70, - 0xd3d94000, 0x18000100, - 0xd3d94001, 0x18000101, - 0xd3d94002, 0x18000102, - 0xd3d94003, 0x18000103, - 0x807c847c, 0x8078ff78, - 0x00000400, 0xbf0a6f7c, - 0xbf85ffea, 0xbf9c0000, - 0xe0524000, 0x6e1d0000, - 0xe0524100, 0x6e1d0100, - 0xe0524200, 0x6e1d0200, - 0xe0524300, 0x6e1d0300, - 0xbf8c0f70, 0xb8f82a05, - 0x80788178, 0x8e788a78, - 0x8e788178, 0xb8ee1605, - 0x806e816e, 0x8e6e866e, - 0x80786e78, 0x80f8c078, - 0xb8ef1605, 0x806f816f, - 0x8e6f846f, 0x8e76826f, - 0xbef600ff, 0x01000000, - 0xbefc006f, 0xc031003a, - 0x00000078, 0x80f8c078, - 0xbf8cc07f, 0x80fc907c, - 0xbf800000, 0xbe802d00, - 0xbe822d02, 0xbe842d04, - 0xbe862d06, 0xbe882d08, - 0xbe8a2d0a, 0xbe8c2d0c, - 0xbe8e2d0e, 0xbf06807c, - 0xbf84fff0, 0xb8f82a05, - 0x80788178, 0x8e788a78, - 0x8e788178, 0xb8ee1605, - 0x806e816e, 0x8e6e866e, - 0x80786e78, 0xbef60084, - 0xbef600ff, 0x01000000, - 0xc0211bfa, 0x00000078, - 0x80788478, 0xc0211b3a, + 0xbefc0080, 0xe0510000, + 0x781d0000, 0xe0510100, + 0x781d0000, 0x807cff7c, + 0x00000200, 0x8078ff78, + 0x00000200, 0xbf0a6f7c, + 0xbf85fff6, 0xbefe00c1, + 0xbeff00c1, 0xbef600ff, + 0x01000000, 0xb8ef2a05, + 0x806f816f, 0x8e6f826f, + 0x806fff6f, 0x00008000, + 0xbef80080, 0xbeee0078, + 0x8078ff78, 0x00000400, + 0xbefc0084, 0xbf11087c, + 0xe0524000, 0x781d0000, + 0xe0524100, 0x781d0100, + 0xe0524200, 0x781d0200, + 0xe0524300, 0x781d0300, + 0xbf8c0f70, 0x7e000300, + 0x7e020301, 0x7e040302, + 0x7e060303, 0x807c847c, + 0x8078ff78, 0x00000400, + 0xbf0a6f7c, 0xbf85ffee, + 0xbefc0080, 0xbf11087c, + 0xe0524000, 0x781d0000, + 0xe0524100, 0x781d0100, + 0xe0524200, 0x781d0200, + 0xe0524300, 0x781d0300, + 0xbf8c0f70, 0xd3d94000, + 0x18000100, 0xd3d94001, + 0x18000101, 0xd3d94002, + 0x18000102, 0xd3d94003, + 0x18000103, 0x807c847c, + 0x8078ff78, 0x00000400, + 0xbf0a6f7c, 0xbf85ffea, + 0xbf9c0000, 0xe0524000, + 0x6e1d0000, 0xe0524100, + 0x6e1d0100, 0xe0524200, + 0x6e1d0200, 0xe0524300, + 0x6e1d0300, 0xbf8c0f70, + 0xb8f82a05, 0x80788178, + 0x8e788a78, 0x8e788178, + 0xb8ee1605, 0x806e816e, + 0x8e6e866e, 0x80786e78, + 0x80f8c078, 0xb8ef1605, + 0x806f816f, 0x8e6f846f, + 0x8e76826f, 0xbef600ff, + 0x01000000, 0xbefc006f, + 0xc031003a, 0x00000078, + 0x80f8c078, 0xbf8cc07f, + 0x80fc907c, 0xbf800000, + 0xbe802d00, 0xbe822d02, + 0xbe842d04, 0xbe862d06, + 0xbe882d08, 0xbe8a2d0a, + 0xbe8c2d0c, 0xbe8e2d0e, + 0xbf06807c, 0xbf84fff0, + 0xb8f82a05, 0x80788178, + 0x8e788a78, 0x8e788178, + 0xb8ee1605, 0x806e816e, + 0x8e6e866e, 0x80786e78, + 0xbef60084, 0xbef600ff, + 0x01000000, 0xc0211bfa, 0x00000078, 0x80788478, - 0xc0211b7a, 0x00000078, - 0x80788478, 0xc0211c3a, + 0xc0211b3a, 0x00000078, + 0x80788478, 0xc0211b7a, 0x00000078, 0x80788478, - 0xc0211c7a, 0x00000078, - 0x80788478, 0xc0211eba, + 0xc0211c3a, 0x00000078, + 0x80788478, 0xc0211c7a, 0x00000078, 0x80788478, - 0xc0211efa, 0x00000078, - 0x80788478, 0xc0211a3a, + 0xc0211eba, 0x00000078, + 0x80788478, 0xc0211efa, 0x00000078, 0x80788478, - 0xc0211a7a, 0x00000078, - 0x80788478, 0xc0211cfa, + 0xc0211a3a, 0x00000078, + 0x80788478, 0xc0211a7a, 0x00000078, 0x80788478, - 0xbf8cc07f, 0xbefc006f, - 0xbefe0070, 0xbeff0071, - 0x866f7bff, 0x000003ff, - 0xb96f4803, 0x866f7bff, - 0xfffff800, 0x8f6f8b6f, - 0xb96fa2c3, 0xb973f801, - 0xb8ee2a05, 0x806e816e, - 0x8e6e8a6e, 0x8e6e816e, - 0xb8ef1605, 0x806f816f, - 0x8e6f866f, 0x806e6f6e, - 0x806e746e, 0x826f8075, - 0x866fff6f, 0x0000ffff, - 0xc00b1c37, 0x00000050, - 0xc00b1d37, 0x00000060, - 0xc0031e77, 0x00000074, - 0xbf8cc07f, 0x8f6e8b77, - 0x866eff6e, 0x001f8000, - 0xb96ef807, 0x866dff6d, - 0x0000ffff, 0x86fe7e7e, - 0x86ea6a6a, 0x8f6e837a, - 0xb96ee0c2, 0xbf800002, - 0xb97a0002, 0xbf8a0000, - 0xbe801f6c, 0xbf9b0000, + 0xc0211cfa, 0x00000078, + 0x80788478, 0xbf8cc07f, + 0xbefc006f, 0xbefe0070, + 0xbeff0071, 0x866f7bff, + 0x000003ff, 0xb96f4803, + 0x866f7bff, 0xfffff800, + 0x8f6f8b6f, 0xb96fa2c3, + 0xb973f801, 0xb8ee2a05, + 0x806e816e, 0x8e6e8a6e, + 0x8e6e816e, 0xb8ef1605, + 0x806f816f, 0x8e6f866f, + 0x806e6f6e, 0x806e746e, + 0x826f8075, 0x866fff6f, + 0x0000ffff, 0xc00b1c37, + 0x00000050, 0xc00b1d37, + 0x00000060, 0xc0031e77, + 0x00000074, 0xbf8cc07f, + 0x8f6e8b77, 0x866eff6e, + 0x001f8000, 0xb96ef807, + 0x866dff6d, 0x0000ffff, + 0x86fe7e7e, 0x86ea6a6a, + 0x8f6e837a, 0xb96ee0c2, + 0xbf800002, 0xb97a0002, + 0xbf8a0000, 0xbe801f6c, + 0xbf9b0000, 0x00000000, }; static const uint32_t cwsr_trap_aldebaran_hex[] = { - 0xbf820001, 0xbf8202df, + 0xbf820001, 0xbf8202e0, 0xb8f8f802, 0x8978ff78, 0x00020006, 0xb8fbf803, 0x866eff78, 0x00002000, @@ -1899,36 +1901,99 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = { 0xbefe007c, 0xbefc0070, 0xc0611c7a, 0x0000007c, 0xbf8cc07f, 0x80708470, - 0xbefc007e, 0x867aff7f, - 0x04000000, 0xbeef0080, - 0x876f6f7a, 0xb8f02985, - 0x80708170, 0x8e708a70, - 0x8e708170, 0xb8fb1605, - 0x807b817b, 0x8e7b847b, - 0x8e76827b, 0xbef600ff, - 0x01000000, 0xbef20174, - 0x80747074, 0x82758075, - 0xbefc0080, 0xbf800000, - 0xbe802b00, 0xbe822b02, - 0xbe842b04, 0xbe862b06, - 0xbe882b08, 0xbe8a2b0a, - 0xbe8c2b0c, 0xbe8e2b0e, - 0xc06b003a, 0x00000000, - 0xbf8cc07f, 0xc06b013a, - 0x00000010, 0xbf8cc07f, - 0xc06b023a, 0x00000020, - 0xbf8cc07f, 0xc06b033a, - 0x00000030, 0xbf8cc07f, - 0x8074c074, 0x82758075, - 0x807c907c, 0xbf0a7b7c, - 0xbf85ffe7, 0xbef40172, - 0xbef00080, 0xbefe00c1, - 0xbeff00c1, 0xbee80080, - 0xbee90080, 0xbef600ff, - 0x01000000, 0x867aff78, + 0xbefc007e, 0xbf108080, + 0x867aff7f, 0x04000000, + 0xbeef0080, 0x876f6f7a, + 0xb8f02985, 0x80708170, + 0x8e708a70, 0x8e708170, + 0xb8fb1605, 0x807b817b, + 0x8e7b847b, 0x8e76827b, + 0xbef600ff, 0x01000000, + 0xbef20174, 0x80747074, + 0x82758075, 0xbefc0080, + 0xbf800000, 0xbe802b00, + 0xbe822b02, 0xbe842b04, + 0xbe862b06, 0xbe882b08, + 0xbe8a2b0a, 0xbe8c2b0c, + 0xbe8e2b0e, 0xc06b003a, + 0x00000000, 0xbf8cc07f, + 0xc06b013a, 0x00000010, + 0xbf8cc07f, 0xc06b023a, + 0x00000020, 0xbf8cc07f, + 0xc06b033a, 0x00000030, + 0xbf8cc07f, 0x8074c074, + 0x82758075, 0x807c907c, + 0xbf0a7b7c, 0xbf85ffe7, + 0xbef40172, 0xbef00080, + 0xbefe00c1, 0xbeff00c1, + 0xbee80080, 0xbee90080, + 0xbef600ff, 0x01000000, + 0x867aff78, 0x00400000, + 0xbf850003, 0xb8faf803, + 0x897a7aff, 0x10000000, + 0xbf85004d, 0xbe840080, + 0xd2890000, 0x00000900, + 0x80048104, 0xd2890001, + 0x00000900, 0x80048104, + 0xd2890002, 0x00000900, + 0x80048104, 0xd2890003, + 0x00000900, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000901, 0x80048104, + 0xd2890001, 0x00000901, + 0x80048104, 0xd2890002, + 0x00000901, 0x80048104, + 0xd2890003, 0x00000901, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0xbe840080, + 0xd2890000, 0x00000902, + 0x80048104, 0xd2890001, + 0x00000902, 0x80048104, + 0xd2890002, 0x00000902, + 0x80048104, 0xd2890003, + 0x00000902, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000903, 0x80048104, + 0xd2890001, 0x00000903, + 0x80048104, 0xd2890002, + 0x00000903, 0x80048104, + 0xd2890003, 0x00000903, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0xbf820008, + 0xe0724000, 0x701d0000, + 0xe0724100, 0x701d0100, + 0xe0724200, 0x701d0200, + 0xe0724300, 0x701d0300, + 0xbefe00c1, 0xbeff00c1, + 0xb8fb4306, 0x867bc17b, + 0xbf840064, 0xbf8a0000, + 0x867aff6f, 0x04000000, + 0xbf840060, 0x8e7b867b, + 0x8e7b827b, 0xbef6007b, + 0xb8f02985, 0x80708170, + 0x8e708a70, 0x8e708170, + 0xb8fa1605, 0x807a817a, + 0x8e7a867a, 0x80707a70, + 0x8070ff70, 0x00000080, + 0xbef600ff, 0x01000000, + 0xbefc0080, 0xd28c0002, + 0x000100c1, 0xd28d0003, + 0x000204c1, 0x867aff78, 0x00400000, 0xbf850003, 0xb8faf803, 0x897a7aff, - 0x10000000, 0xbf85004d, + 0x10000000, 0xbf850030, + 0x24040682, 0xd86e4000, + 0x00000002, 0xbf8cc07f, 0xbe840080, 0xd2890000, 0x00000900, 0x80048104, 0xd2890001, 0x00000900, @@ -1948,50 +2013,31 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = { 0xc069003a, 0x00000070, 0xbf8cc07f, 0x80709070, 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000902, 0x80048104, - 0xd2890001, 0x00000902, - 0x80048104, 0xd2890002, - 0x00000902, 0x80048104, - 0xd2890003, 0x00000902, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000903, - 0x80048104, 0xd2890001, - 0x00000903, 0x80048104, - 0xd2890002, 0x00000903, - 0x80048104, 0xd2890003, - 0x00000903, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbf820008, 0xe0724000, - 0x701d0000, 0xe0724100, - 0x701d0100, 0xe0724200, - 0x701d0200, 0xe0724300, - 0x701d0300, 0xbefe00c1, - 0xbeff00c1, 0xb8fb4306, - 0x867bc17b, 0xbf840064, - 0xbf8a0000, 0x867aff6f, - 0x04000000, 0xbf840060, - 0x8e7b867b, 0x8e7b827b, - 0xbef6007b, 0xb8f02985, - 0x80708170, 0x8e708a70, - 0x8e708170, 0xb8fa1605, - 0x807a817a, 0x8e7a867a, - 0x80707a70, 0x8070ff70, - 0x00000080, 0xbef600ff, - 0x01000000, 0xbefc0080, - 0xd28c0002, 0x000100c1, - 0xd28d0003, 0x000204c1, + 0x680404ff, 0x00000200, + 0xd0c9006a, 0x0000f702, + 0xbf87ffd2, 0xbf820015, + 0xd1060002, 0x00011103, + 0x7e0602ff, 0x00000200, + 0xbefc00ff, 0x00010000, + 0xbe800077, 0x8677ff77, + 0xff7fffff, 0x8777ff77, + 0x00058000, 0xd8ec0000, + 0x00000002, 0xbf8cc07f, + 0xe0765000, 0x701d0002, + 0x68040702, 0xd0c9006a, + 0x0000f702, 0xbf87fff7, + 0xbef70000, 0xbef000ff, + 0x00000400, 0xbefe00c1, + 0xbeff00c1, 0xb8fb2b05, + 0x807b817b, 0x8e7b827b, + 0xbef600ff, 0x01000000, + 0xbefc0084, 0xbf0a7b7c, + 0xbf84006d, 0xbf11017c, + 0x807bff7b, 0x00001000, 0x867aff78, 0x00400000, 0xbf850003, 0xb8faf803, 0x897a7aff, 0x10000000, - 0xbf850030, 0x24040682, - 0xd86e4000, 0x00000002, - 0xbf8cc07f, 0xbe840080, + 0xbf850051, 0xbe840080, 0xd2890000, 0x00000900, 0x80048104, 0xd2890001, 0x00000900, 0x80048104, @@ -2010,31 +2056,51 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = { 0x80048104, 0xc069003a, 0x00000070, 0xbf8cc07f, 0x80709070, 0xbf06c004, - 0xbf84ffee, 0x680404ff, - 0x00000200, 0xd0c9006a, - 0x0000f702, 0xbf87ffd2, - 0xbf820015, 0xd1060002, - 0x00011103, 0x7e0602ff, - 0x00000200, 0xbefc00ff, - 0x00010000, 0xbe800077, - 0x8677ff77, 0xff7fffff, - 0x8777ff77, 0x00058000, - 0xd8ec0000, 0x00000002, - 0xbf8cc07f, 0xe0765000, - 0x701d0002, 0x68040702, - 0xd0c9006a, 0x0000f702, - 0xbf87fff7, 0xbef70000, - 0xbef000ff, 0x00000400, - 0xbefe00c1, 0xbeff00c1, - 0xb8fb2b05, 0x807b817b, - 0x8e7b827b, 0xbef600ff, - 0x01000000, 0xbefc0084, - 0xbf0a7b7c, 0xbf84006d, - 0xbf11017c, 0x807bff7b, - 0x00001000, 0x867aff78, + 0xbf84ffee, 0xbe840080, + 0xd2890000, 0x00000902, + 0x80048104, 0xd2890001, + 0x00000902, 0x80048104, + 0xd2890002, 0x00000902, + 0x80048104, 0xd2890003, + 0x00000902, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000903, 0x80048104, + 0xd2890001, 0x00000903, + 0x80048104, 0xd2890002, + 0x00000903, 0x80048104, + 0xd2890003, 0x00000903, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0x807c847c, + 0xbf0a7b7c, 0xbf85ffb1, + 0xbf9c0000, 0xbf820012, + 0x7e000300, 0x7e020301, + 0x7e040302, 0x7e060303, + 0xe0724000, 0x701d0000, + 0xe0724100, 0x701d0100, + 0xe0724200, 0x701d0200, + 0xe0724300, 0x701d0300, + 0x807c847c, 0x8070ff70, + 0x00000400, 0xbf0a7b7c, + 0xbf85ffef, 0xbf9c0000, + 0xb8fb2985, 0x807b817b, + 0x8e7b837b, 0xb8fa2b05, + 0x807a817a, 0x8e7a827a, + 0x80fb7a7b, 0x867b7b7b, + 0xbf84007a, 0x807bff7b, + 0x00001000, 0xbefc0080, + 0xbf11017c, 0x867aff78, 0x00400000, 0xbf850003, 0xb8faf803, 0x897a7aff, - 0x10000000, 0xbf850051, + 0x10000000, 0xbf850059, + 0xd3d84000, 0x18000100, + 0xd3d84001, 0x18000101, + 0xd3d84002, 0x18000102, + 0xd3d84003, 0x18000103, 0xbe840080, 0xd2890000, 0x00000900, 0x80048104, 0xd2890001, 0x00000900, @@ -2074,202 +2140,139 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = { 0xbf8cc07f, 0x80709070, 0xbf06c004, 0xbf84ffee, 0x807c847c, 0xbf0a7b7c, - 0xbf85ffb1, 0xbf9c0000, - 0xbf820012, 0x7e000300, - 0x7e020301, 0x7e040302, - 0x7e060303, 0xe0724000, + 0xbf85ffa9, 0xbf9c0000, + 0xbf820016, 0xd3d84000, + 0x18000100, 0xd3d84001, + 0x18000101, 0xd3d84002, + 0x18000102, 0xd3d84003, + 0x18000103, 0xe0724000, 0x701d0000, 0xe0724100, 0x701d0100, 0xe0724200, 0x701d0200, 0xe0724300, 0x701d0300, 0x807c847c, 0x8070ff70, 0x00000400, - 0xbf0a7b7c, 0xbf85ffef, - 0xbf9c0000, 0xb8fb2985, - 0x807b817b, 0x8e7b837b, - 0xb8fa2b05, 0x807a817a, - 0x8e7a827a, 0x80fb7a7b, - 0x867b7b7b, 0xbf84007a, - 0x807bff7b, 0x00001000, - 0xbefc0080, 0xbf11017c, - 0x867aff78, 0x00400000, - 0xbf850003, 0xb8faf803, - 0x897a7aff, 0x10000000, - 0xbf850059, 0xd3d84000, - 0x18000100, 0xd3d84001, - 0x18000101, 0xd3d84002, - 0x18000102, 0xd3d84003, - 0x18000103, 0xbe840080, - 0xd2890000, 0x00000900, - 0x80048104, 0xd2890001, - 0x00000900, 0x80048104, - 0xd2890002, 0x00000900, - 0x80048104, 0xd2890003, - 0x00000900, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000901, 0x80048104, - 0xd2890001, 0x00000901, - 0x80048104, 0xd2890002, - 0x00000901, 0x80048104, - 0xd2890003, 0x00000901, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000902, - 0x80048104, 0xd2890001, - 0x00000902, 0x80048104, - 0xd2890002, 0x00000902, - 0x80048104, 0xd2890003, - 0x00000902, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000903, 0x80048104, - 0xd2890001, 0x00000903, - 0x80048104, 0xd2890002, - 0x00000903, 0x80048104, - 0xd2890003, 0x00000903, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0x807c847c, - 0xbf0a7b7c, 0xbf85ffa9, - 0xbf9c0000, 0xbf820016, - 0xd3d84000, 0x18000100, - 0xd3d84001, 0x18000101, - 0xd3d84002, 0x18000102, - 0xd3d84003, 0x18000103, - 0xe0724000, 0x701d0000, - 0xe0724100, 0x701d0100, - 0xe0724200, 0x701d0200, - 0xe0724300, 0x701d0300, - 0x807c847c, 0x8070ff70, - 0x00000400, 0xbf0a7b7c, - 0xbf85ffeb, 0xbf9c0000, - 0xbf8200ee, 0xbef4007e, - 0x8675ff7f, 0x0000ffff, - 0x8775ff75, 0x00040000, - 0xbef60080, 0xbef700ff, - 0x00807fac, 0x866eff7f, - 0x04000000, 0xbf84001f, + 0xbf0a7b7c, 0xbf85ffeb, + 0xbf9c0000, 0xbf8200ee, + 0xbef4007e, 0x8675ff7f, + 0x0000ffff, 0x8775ff75, + 0x00040000, 0xbef60080, + 0xbef700ff, 0x00807fac, + 0x866eff7f, 0x04000000, + 0xbf84001f, 0xbefe00c1, + 0xbeff00c1, 0xb8ef4306, + 0x866fc16f, 0xbf84001a, + 0x8e6f866f, 0x8e6f826f, + 0xbef6006f, 0xb8f82985, + 0x80788178, 0x8e788a78, + 0x8e788178, 0xb8ee1605, + 0x806e816e, 0x8e6e866e, + 0x80786e78, 0x8078ff78, + 0x00000080, 0xbef600ff, + 0x01000000, 0xbefc0080, + 0xe0510000, 0x781d0000, + 0xe0510100, 0x781d0000, + 0x807cff7c, 0x00000200, + 0x8078ff78, 0x00000200, + 0xbf0a6f7c, 0xbf85fff6, 0xbefe00c1, 0xbeff00c1, - 0xb8ef4306, 0x866fc16f, - 0xbf84001a, 0x8e6f866f, - 0x8e6f826f, 0xbef6006f, - 0xb8f82985, 0x80788178, - 0x8e788a78, 0x8e788178, - 0xb8ee1605, 0x806e816e, - 0x8e6e866e, 0x80786e78, - 0x8078ff78, 0x00000080, 0xbef600ff, 0x01000000, - 0xbefc0080, 0xe0510000, - 0x781d0000, 0xe0510100, - 0x781d0000, 0x807cff7c, - 0x00000200, 0x8078ff78, - 0x00000200, 0xbf0a6f7c, - 0xbf85fff6, 0xbefe00c1, - 0xbeff00c1, 0xbef600ff, - 0x01000000, 0xb8ef2b05, - 0x806f816f, 0x8e6f826f, - 0x806fff6f, 0x00008000, - 0xbef80080, 0xbeee0078, - 0x8078ff78, 0x00000400, - 0xbefc0084, 0xbf11087c, - 0xe0524000, 0x781d0000, - 0xe0524100, 0x781d0100, - 0xe0524200, 0x781d0200, - 0xe0524300, 0x781d0300, - 0xbf8c0f70, 0x7e000300, - 0x7e020301, 0x7e040302, - 0x7e060303, 0x807c847c, - 0x8078ff78, 0x00000400, - 0xbf0a6f7c, 0xbf85ffee, - 0xb8ef2985, 0x806f816f, - 0x8e6f836f, 0xb8f92b05, - 0x80798179, 0x8e798279, - 0x80ef796f, 0x866f6f6f, - 0xbf84001a, 0x806fff6f, - 0x00008000, 0xbefc0080, + 0xb8ef2b05, 0x806f816f, + 0x8e6f826f, 0x806fff6f, + 0x00008000, 0xbef80080, + 0xbeee0078, 0x8078ff78, + 0x00000400, 0xbefc0084, 0xbf11087c, 0xe0524000, 0x781d0000, 0xe0524100, 0x781d0100, 0xe0524200, 0x781d0200, 0xe0524300, 0x781d0300, 0xbf8c0f70, - 0xd3d94000, 0x18000100, - 0xd3d94001, 0x18000101, - 0xd3d94002, 0x18000102, - 0xd3d94003, 0x18000103, + 0x7e000300, 0x7e020301, + 0x7e040302, 0x7e060303, 0x807c847c, 0x8078ff78, 0x00000400, 0xbf0a6f7c, - 0xbf85ffea, 0xbf9c0000, - 0xe0524000, 0x6e1d0000, - 0xe0524100, 0x6e1d0100, - 0xe0524200, 0x6e1d0200, - 0xe0524300, 0x6e1d0300, - 0xbf8c0f70, 0xb8f82985, - 0x80788178, 0x8e788a78, - 0x8e788178, 0xb8ee1605, - 0x806e816e, 0x8e6e866e, - 0x80786e78, 0x80f8c078, - 0xb8ef1605, 0x806f816f, - 0x8e6f846f, 0x8e76826f, - 0xbef600ff, 0x01000000, - 0xbefc006f, 0xc031003a, - 0x00000078, 0x80f8c078, - 0xbf8cc07f, 0x80fc907c, - 0xbf800000, 0xbe802d00, - 0xbe822d02, 0xbe842d04, - 0xbe862d06, 0xbe882d08, - 0xbe8a2d0a, 0xbe8c2d0c, - 0xbe8e2d0e, 0xbf06807c, - 0xbf84fff0, 0xb8f82985, - 0x80788178, 0x8e788a78, - 0x8e788178, 0xb8ee1605, - 0x806e816e, 0x8e6e866e, - 0x80786e78, 0xbef60084, - 0xbef600ff, 0x01000000, - 0xc0211bfa, 0x00000078, - 0x80788478, 0xc0211b3a, + 0xbf85ffee, 0xb8ef2985, + 0x806f816f, 0x8e6f836f, + 0xb8f92b05, 0x80798179, + 0x8e798279, 0x80ef796f, + 0x866f6f6f, 0xbf84001a, + 0x806fff6f, 0x00008000, + 0xbefc0080, 0xbf11087c, + 0xe0524000, 0x781d0000, + 0xe0524100, 0x781d0100, + 0xe0524200, 0x781d0200, + 0xe0524300, 0x781d0300, + 0xbf8c0f70, 0xd3d94000, + 0x18000100, 0xd3d94001, + 0x18000101, 0xd3d94002, + 0x18000102, 0xd3d94003, + 0x18000103, 0x807c847c, + 0x8078ff78, 0x00000400, + 0xbf0a6f7c, 0xbf85ffea, + 0xbf9c0000, 0xe0524000, + 0x6e1d0000, 0xe0524100, + 0x6e1d0100, 0xe0524200, + 0x6e1d0200, 0xe0524300, + 0x6e1d0300, 0xbf8c0f70, + 0xb8f82985, 0x80788178, + 0x8e788a78, 0x8e788178, + 0xb8ee1605, 0x806e816e, + 0x8e6e866e, 0x80786e78, + 0x80f8c078, 0xb8ef1605, + 0x806f816f, 0x8e6f846f, + 0x8e76826f, 0xbef600ff, + 0x01000000, 0xbefc006f, + 0xc031003a, 0x00000078, + 0x80f8c078, 0xbf8cc07f, + 0x80fc907c, 0xbf800000, + 0xbe802d00, 0xbe822d02, + 0xbe842d04, 0xbe862d06, + 0xbe882d08, 0xbe8a2d0a, + 0xbe8c2d0c, 0xbe8e2d0e, + 0xbf06807c, 0xbf84fff0, + 0xb8f82985, 0x80788178, + 0x8e788a78, 0x8e788178, + 0xb8ee1605, 0x806e816e, + 0x8e6e866e, 0x80786e78, + 0xbef60084, 0xbef600ff, + 0x01000000, 0xc0211bfa, 0x00000078, 0x80788478, - 0xc0211b7a, 0x00000078, - 0x80788478, 0xc0211c3a, + 0xc0211b3a, 0x00000078, + 0x80788478, 0xc0211b7a, 0x00000078, 0x80788478, - 0xc0211c7a, 0x00000078, - 0x80788478, 0xc0211eba, + 0xc0211c3a, 0x00000078, + 0x80788478, 0xc0211c7a, 0x00000078, 0x80788478, - 0xc0211efa, 0x00000078, - 0x80788478, 0xc0211a3a, + 0xc0211eba, 0x00000078, + 0x80788478, 0xc0211efa, 0x00000078, 0x80788478, - 0xc0211a7a, 0x00000078, - 0x80788478, 0xc0211cfa, + 0xc0211a3a, 0x00000078, + 0x80788478, 0xc0211a7a, 0x00000078, 0x80788478, - 0xbf8cc07f, 0xbefc006f, - 0xbefe0070, 0xbeff0071, - 0x866f7bff, 0x000003ff, - 0xb96f4803, 0x866f7bff, - 0xfffff800, 0x8f6f8b6f, - 0xb96fa2c3, 0xb973f801, - 0xb8ee2985, 0x806e816e, - 0x8e6e8a6e, 0x8e6e816e, - 0xb8ef1605, 0x806f816f, - 0x8e6f866f, 0x806e6f6e, - 0x806e746e, 0x826f8075, - 0x866fff6f, 0x0000ffff, - 0xc00b1c37, 0x00000050, - 0xc00b1d37, 0x00000060, - 0xc0031e77, 0x00000074, - 0xbf8cc07f, 0x8f6e8b77, - 0x866eff6e, 0x001f8000, - 0xb96ef807, 0x866dff6d, - 0x0000ffff, 0x86fe7e7e, - 0x86ea6a6a, 0x8f6e837a, - 0xb96ee0c2, 0xbf800002, - 0xb97a0002, 0xbf8a0000, - 0xbe801f6c, 0xbf9b0000, + 0xc0211cfa, 0x00000078, + 0x80788478, 0xbf8cc07f, + 0xbefc006f, 0xbefe0070, + 0xbeff0071, 0x866f7bff, + 0x000003ff, 0xb96f4803, + 0x866f7bff, 0xfffff800, + 0x8f6f8b6f, 0xb96fa2c3, + 0xb973f801, 0xb8ee2985, + 0x806e816e, 0x8e6e8a6e, + 0x8e6e816e, 0xb8ef1605, + 0x806f816f, 0x8e6f866f, + 0x806e6f6e, 0x806e746e, + 0x826f8075, 0x866fff6f, + 0x0000ffff, 0xc00b1c37, + 0x00000050, 0xc00b1d37, + 0x00000060, 0xc0031e77, + 0x00000074, 0xbf8cc07f, + 0x8f6e8b77, 0x866eff6e, + 0x001f8000, 0xb96ef807, + 0x866dff6d, 0x0000ffff, + 0x86fe7e7e, 0x86ea6a6a, + 0x8f6e837a, 0xb96ee0c2, + 0xbf800002, 0xb97a0002, + 0xbf8a0000, 0xbe801f6c, + 0xbf9b0000, 0x00000000, }; static const uint32_t cwsr_trap_gfx10_hex[] = { @@ -3151,7 +3154,7 @@ static const uint32_t cwsr_trap_gfx11_hex[] = { }; static const uint32_t cwsr_trap_gfx9_4_3_hex[] = { - 0xbf820001, 0xbf8202db, + 0xbf820001, 0xbf8202dc, 0xb8f8f802, 0x8978ff78, 0x00020006, 0xb8fbf803, 0x866eff78, 0x00002000, @@ -3266,36 +3269,99 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = { 0xbefe007c, 0xbefc0070, 0xc0611c7a, 0x0000007c, 0xbf8cc07f, 0x80708470, - 0xbefc007e, 0x867aff7f, - 0x04000000, 0xbeef0080, - 0x876f6f7a, 0xb8f02985, - 0x80708170, 0x8e708a70, - 0x8e708170, 0xb8fb1605, - 0x807b817b, 0x8e7b847b, - 0x8e76827b, 0xbef600ff, - 0x01000000, 0xbef20174, - 0x80747074, 0x82758075, - 0xbefc0080, 0xbf800000, - 0xbe802b00, 0xbe822b02, - 0xbe842b04, 0xbe862b06, - 0xbe882b08, 0xbe8a2b0a, - 0xbe8c2b0c, 0xbe8e2b0e, - 0xc06b003a, 0x00000000, - 0xbf8cc07f, 0xc06b013a, - 0x00000010, 0xbf8cc07f, - 0xc06b023a, 0x00000020, - 0xbf8cc07f, 0xc06b033a, - 0x00000030, 0xbf8cc07f, - 0x8074c074, 0x82758075, - 0x807c907c, 0xbf0a7b7c, - 0xbf85ffe7, 0xbef40172, - 0xbef00080, 0xbefe00c1, - 0xbeff00c1, 0xbee80080, - 0xbee90080, 0xbef600ff, - 0x01000000, 0x867aff78, + 0xbefc007e, 0xbf108080, + 0x867aff7f, 0x04000000, + 0xbeef0080, 0x876f6f7a, + 0xb8f02985, 0x80708170, + 0x8e708a70, 0x8e708170, + 0xb8fb1605, 0x807b817b, + 0x8e7b847b, 0x8e76827b, + 0xbef600ff, 0x01000000, + 0xbef20174, 0x80747074, + 0x82758075, 0xbefc0080, + 0xbf800000, 0xbe802b00, + 0xbe822b02, 0xbe842b04, + 0xbe862b06, 0xbe882b08, + 0xbe8a2b0a, 0xbe8c2b0c, + 0xbe8e2b0e, 0xc06b003a, + 0x00000000, 0xbf8cc07f, + 0xc06b013a, 0x00000010, + 0xbf8cc07f, 0xc06b023a, + 0x00000020, 0xbf8cc07f, + 0xc06b033a, 0x00000030, + 0xbf8cc07f, 0x8074c074, + 0x82758075, 0x807c907c, + 0xbf0a7b7c, 0xbf85ffe7, + 0xbef40172, 0xbef00080, + 0xbefe00c1, 0xbeff00c1, + 0xbee80080, 0xbee90080, + 0xbef600ff, 0x01000000, + 0x867aff78, 0x00400000, + 0xbf850003, 0xb8faf803, + 0x897a7aff, 0x10000000, + 0xbf85004d, 0xbe840080, + 0xd2890000, 0x00000900, + 0x80048104, 0xd2890001, + 0x00000900, 0x80048104, + 0xd2890002, 0x00000900, + 0x80048104, 0xd2890003, + 0x00000900, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000901, 0x80048104, + 0xd2890001, 0x00000901, + 0x80048104, 0xd2890002, + 0x00000901, 0x80048104, + 0xd2890003, 0x00000901, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0xbe840080, + 0xd2890000, 0x00000902, + 0x80048104, 0xd2890001, + 0x00000902, 0x80048104, + 0xd2890002, 0x00000902, + 0x80048104, 0xd2890003, + 0x00000902, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000903, 0x80048104, + 0xd2890001, 0x00000903, + 0x80048104, 0xd2890002, + 0x00000903, 0x80048104, + 0xd2890003, 0x00000903, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0xbf820008, + 0xe0724000, 0x701d0000, + 0xe0724100, 0x701d0100, + 0xe0724200, 0x701d0200, + 0xe0724300, 0x701d0300, + 0xbefe00c1, 0xbeff00c1, + 0xb8fb4306, 0x867bc17b, + 0xbf840064, 0xbf8a0000, + 0x867aff6f, 0x04000000, + 0xbf840060, 0x8e7b867b, + 0x8e7b827b, 0xbef6007b, + 0xb8f02985, 0x80708170, + 0x8e708a70, 0x8e708170, + 0xb8fa1605, 0x807a817a, + 0x8e7a867a, 0x80707a70, + 0x8070ff70, 0x00000080, + 0xbef600ff, 0x01000000, + 0xbefc0080, 0xd28c0002, + 0x000100c1, 0xd28d0003, + 0x000204c1, 0x867aff78, 0x00400000, 0xbf850003, 0xb8faf803, 0x897a7aff, - 0x10000000, 0xbf85004d, + 0x10000000, 0xbf850030, + 0x24040682, 0xd86e4000, + 0x00000002, 0xbf8cc07f, 0xbe840080, 0xd2890000, 0x00000900, 0x80048104, 0xd2890001, 0x00000900, @@ -3315,50 +3381,31 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = { 0xc069003a, 0x00000070, 0xbf8cc07f, 0x80709070, 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000902, 0x80048104, - 0xd2890001, 0x00000902, - 0x80048104, 0xd2890002, - 0x00000902, 0x80048104, - 0xd2890003, 0x00000902, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000903, - 0x80048104, 0xd2890001, - 0x00000903, 0x80048104, - 0xd2890002, 0x00000903, - 0x80048104, 0xd2890003, - 0x00000903, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbf820008, 0xe0724000, - 0x701d0000, 0xe0724100, - 0x701d0100, 0xe0724200, - 0x701d0200, 0xe0724300, - 0x701d0300, 0xbefe00c1, - 0xbeff00c1, 0xb8fb4306, - 0x867bc17b, 0xbf840064, - 0xbf8a0000, 0x867aff6f, - 0x04000000, 0xbf840060, - 0x8e7b867b, 0x8e7b827b, - 0xbef6007b, 0xb8f02985, - 0x80708170, 0x8e708a70, - 0x8e708170, 0xb8fa1605, - 0x807a817a, 0x8e7a867a, - 0x80707a70, 0x8070ff70, - 0x00000080, 0xbef600ff, - 0x01000000, 0xbefc0080, - 0xd28c0002, 0x000100c1, - 0xd28d0003, 0x000204c1, + 0x680404ff, 0x00000200, + 0xd0c9006a, 0x0000f702, + 0xbf87ffd2, 0xbf820015, + 0xd1060002, 0x00011103, + 0x7e0602ff, 0x00000200, + 0xbefc00ff, 0x00010000, + 0xbe800077, 0x8677ff77, + 0xff7fffff, 0x8777ff77, + 0x00058000, 0xd8ec0000, + 0x00000002, 0xbf8cc07f, + 0xe0765000, 0x701d0002, + 0x68040702, 0xd0c9006a, + 0x0000f702, 0xbf87fff7, + 0xbef70000, 0xbef000ff, + 0x00000400, 0xbefe00c1, + 0xbeff00c1, 0xb8fb2b05, + 0x807b817b, 0x8e7b827b, + 0xbef600ff, 0x01000000, + 0xbefc0084, 0xbf0a7b7c, + 0xbf84006d, 0xbf11017c, + 0x807bff7b, 0x00001000, 0x867aff78, 0x00400000, 0xbf850003, 0xb8faf803, 0x897a7aff, 0x10000000, - 0xbf850030, 0x24040682, - 0xd86e4000, 0x00000002, - 0xbf8cc07f, 0xbe840080, + 0xbf850051, 0xbe840080, 0xd2890000, 0x00000900, 0x80048104, 0xd2890001, 0x00000900, 0x80048104, @@ -3377,31 +3424,51 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = { 0x80048104, 0xc069003a, 0x00000070, 0xbf8cc07f, 0x80709070, 0xbf06c004, - 0xbf84ffee, 0x680404ff, - 0x00000200, 0xd0c9006a, - 0x0000f702, 0xbf87ffd2, - 0xbf820015, 0xd1060002, - 0x00011103, 0x7e0602ff, - 0x00000200, 0xbefc00ff, - 0x00010000, 0xbe800077, - 0x8677ff77, 0xff7fffff, - 0x8777ff77, 0x00058000, - 0xd8ec0000, 0x00000002, - 0xbf8cc07f, 0xe0765000, - 0x701d0002, 0x68040702, - 0xd0c9006a, 0x0000f702, - 0xbf87fff7, 0xbef70000, - 0xbef000ff, 0x00000400, - 0xbefe00c1, 0xbeff00c1, - 0xb8fb2b05, 0x807b817b, - 0x8e7b827b, 0xbef600ff, - 0x01000000, 0xbefc0084, - 0xbf0a7b7c, 0xbf84006d, - 0xbf11017c, 0x807bff7b, - 0x00001000, 0x867aff78, + 0xbf84ffee, 0xbe840080, + 0xd2890000, 0x00000902, + 0x80048104, 0xd2890001, + 0x00000902, 0x80048104, + 0xd2890002, 0x00000902, + 0x80048104, 0xd2890003, + 0x00000902, 0x80048104, + 0xc069003a, 0x00000070, + 0xbf8cc07f, 0x80709070, + 0xbf06c004, 0xbf84ffee, + 0xbe840080, 0xd2890000, + 0x00000903, 0x80048104, + 0xd2890001, 0x00000903, + 0x80048104, 0xd2890002, + 0x00000903, 0x80048104, + 0xd2890003, 0x00000903, + 0x80048104, 0xc069003a, + 0x00000070, 0xbf8cc07f, + 0x80709070, 0xbf06c004, + 0xbf84ffee, 0x807c847c, + 0xbf0a7b7c, 0xbf85ffb1, + 0xbf9c0000, 0xbf820012, + 0x7e000300, 0x7e020301, + 0x7e040302, 0x7e060303, + 0xe0724000, 0x701d0000, + 0xe0724100, 0x701d0100, + 0xe0724200, 0x701d0200, + 0xe0724300, 0x701d0300, + 0x807c847c, 0x8070ff70, + 0x00000400, 0xbf0a7b7c, + 0xbf85ffef, 0xbf9c0000, + 0xb8fb2985, 0x807b817b, + 0x8e7b837b, 0xb8fa2b05, + 0x807a817a, 0x8e7a827a, + 0x80fb7a7b, 0x867b7b7b, + 0xbf84007a, 0x807bff7b, + 0x00001000, 0xbefc0080, + 0xbf11017c, 0x867aff78, 0x00400000, 0xbf850003, 0xb8faf803, 0x897a7aff, - 0x10000000, 0xbf850051, + 0x10000000, 0xbf850059, + 0xd3d84000, 0x18000100, + 0xd3d84001, 0x18000101, + 0xd3d84002, 0x18000102, + 0xd3d84003, 0x18000103, 0xbe840080, 0xd2890000, 0x00000900, 0x80048104, 0xd2890001, 0x00000900, @@ -3441,202 +3508,139 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = { 0xbf8cc07f, 0x80709070, 0xbf06c004, 0xbf84ffee, 0x807c847c, 0xbf0a7b7c, - 0xbf85ffb1, 0xbf9c0000, - 0xbf820012, 0x7e000300, - 0x7e020301, 0x7e040302, - 0x7e060303, 0xe0724000, + 0xbf85ffa9, 0xbf9c0000, + 0xbf820016, 0xd3d84000, + 0x18000100, 0xd3d84001, + 0x18000101, 0xd3d84002, + 0x18000102, 0xd3d84003, + 0x18000103, 0xe0724000, 0x701d0000, 0xe0724100, 0x701d0100, 0xe0724200, 0x701d0200, 0xe0724300, 0x701d0300, 0x807c847c, 0x8070ff70, 0x00000400, - 0xbf0a7b7c, 0xbf85ffef, - 0xbf9c0000, 0xb8fb2985, - 0x807b817b, 0x8e7b837b, - 0xb8fa2b05, 0x807a817a, - 0x8e7a827a, 0x80fb7a7b, - 0x867b7b7b, 0xbf84007a, - 0x807bff7b, 0x00001000, - 0xbefc0080, 0xbf11017c, - 0x867aff78, 0x00400000, - 0xbf850003, 0xb8faf803, - 0x897a7aff, 0x10000000, - 0xbf850059, 0xd3d84000, - 0x18000100, 0xd3d84001, - 0x18000101, 0xd3d84002, - 0x18000102, 0xd3d84003, - 0x18000103, 0xbe840080, - 0xd2890000, 0x00000900, - 0x80048104, 0xd2890001, - 0x00000900, 0x80048104, - 0xd2890002, 0x00000900, - 0x80048104, 0xd2890003, - 0x00000900, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000901, 0x80048104, - 0xd2890001, 0x00000901, - 0x80048104, 0xd2890002, - 0x00000901, 0x80048104, - 0xd2890003, 0x00000901, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0xbe840080, - 0xd2890000, 0x00000902, - 0x80048104, 0xd2890001, - 0x00000902, 0x80048104, - 0xd2890002, 0x00000902, - 0x80048104, 0xd2890003, - 0x00000902, 0x80048104, - 0xc069003a, 0x00000070, - 0xbf8cc07f, 0x80709070, - 0xbf06c004, 0xbf84ffee, - 0xbe840080, 0xd2890000, - 0x00000903, 0x80048104, - 0xd2890001, 0x00000903, - 0x80048104, 0xd2890002, - 0x00000903, 0x80048104, - 0xd2890003, 0x00000903, - 0x80048104, 0xc069003a, - 0x00000070, 0xbf8cc07f, - 0x80709070, 0xbf06c004, - 0xbf84ffee, 0x807c847c, - 0xbf0a7b7c, 0xbf85ffa9, - 0xbf9c0000, 0xbf820016, - 0xd3d84000, 0x18000100, - 0xd3d84001, 0x18000101, - 0xd3d84002, 0x18000102, - 0xd3d84003, 0x18000103, - 0xe0724000, 0x701d0000, - 0xe0724100, 0x701d0100, - 0xe0724200, 0x701d0200, - 0xe0724300, 0x701d0300, - 0x807c847c, 0x8070ff70, - 0x00000400, 0xbf0a7b7c, - 0xbf85ffeb, 0xbf9c0000, - 0xbf8200ee, 0xbef4007e, - 0x8675ff7f, 0x0000ffff, - 0x8775ff75, 0x00040000, - 0xbef60080, 0xbef700ff, - 0x00807fac, 0x866eff7f, - 0x04000000, 0xbf84001f, + 0xbf0a7b7c, 0xbf85ffeb, + 0xbf9c0000, 0xbf8200ee, + 0xbef4007e, 0x8675ff7f, + 0x0000ffff, 0x8775ff75, + 0x00040000, 0xbef60080, + 0xbef700ff, 0x00807fac, + 0x866eff7f, 0x04000000, + 0xbf84001f, 0xbefe00c1, + 0xbeff00c1, 0xb8ef4306, + 0x866fc16f, 0xbf84001a, + 0x8e6f866f, 0x8e6f826f, + 0xbef6006f, 0xb8f82985, + 0x80788178, 0x8e788a78, + 0x8e788178, 0xb8ee1605, + 0x806e816e, 0x8e6e866e, + 0x80786e78, 0x8078ff78, + 0x00000080, 0xbef600ff, + 0x01000000, 0xbefc0080, + 0xe0510000, 0x781d0000, + 0xe0510100, 0x781d0000, + 0x807cff7c, 0x00000200, + 0x8078ff78, 0x00000200, + 0xbf0a6f7c, 0xbf85fff6, 0xbefe00c1, 0xbeff00c1, - 0xb8ef4306, 0x866fc16f, - 0xbf84001a, 0x8e6f866f, - 0x8e6f826f, 0xbef6006f, - 0xb8f82985, 0x80788178, - 0x8e788a78, 0x8e788178, - 0xb8ee1605, 0x806e816e, - 0x8e6e866e, 0x80786e78, - 0x8078ff78, 0x00000080, 0xbef600ff, 0x01000000, - 0xbefc0080, 0xe0510000, - 0x781d0000, 0xe0510100, - 0x781d0000, 0x807cff7c, - 0x00000200, 0x8078ff78, - 0x00000200, 0xbf0a6f7c, - 0xbf85fff6, 0xbefe00c1, - 0xbeff00c1, 0xbef600ff, - 0x01000000, 0xb8ef2b05, - 0x806f816f, 0x8e6f826f, - 0x806fff6f, 0x00008000, - 0xbef80080, 0xbeee0078, - 0x8078ff78, 0x00000400, - 0xbefc0084, 0xbf11087c, - 0xe0524000, 0x781d0000, - 0xe0524100, 0x781d0100, - 0xe0524200, 0x781d0200, - 0xe0524300, 0x781d0300, - 0xbf8c0f70, 0x7e000300, - 0x7e020301, 0x7e040302, - 0x7e060303, 0x807c847c, - 0x8078ff78, 0x00000400, - 0xbf0a6f7c, 0xbf85ffee, - 0xb8ef2985, 0x806f816f, - 0x8e6f836f, 0xb8f92b05, - 0x80798179, 0x8e798279, - 0x80ef796f, 0x866f6f6f, - 0xbf84001a, 0x806fff6f, - 0x00008000, 0xbefc0080, + 0xb8ef2b05, 0x806f816f, + 0x8e6f826f, 0x806fff6f, + 0x00008000, 0xbef80080, + 0xbeee0078, 0x8078ff78, + 0x00000400, 0xbefc0084, 0xbf11087c, 0xe0524000, 0x781d0000, 0xe0524100, 0x781d0100, 0xe0524200, 0x781d0200, 0xe0524300, 0x781d0300, 0xbf8c0f70, - 0xd3d94000, 0x18000100, - 0xd3d94001, 0x18000101, - 0xd3d94002, 0x18000102, - 0xd3d94003, 0x18000103, + 0x7e000300, 0x7e020301, + 0x7e040302, 0x7e060303, 0x807c847c, 0x8078ff78, 0x00000400, 0xbf0a6f7c, - 0xbf85ffea, 0xbf9c0000, - 0xe0524000, 0x6e1d0000, - 0xe0524100, 0x6e1d0100, - 0xe0524200, 0x6e1d0200, - 0xe0524300, 0x6e1d0300, - 0xbf8c0f70, 0xb8f82985, - 0x80788178, 0x8e788a78, - 0x8e788178, 0xb8ee1605, - 0x806e816e, 0x8e6e866e, - 0x80786e78, 0x80f8c078, - 0xb8ef1605, 0x806f816f, - 0x8e6f846f, 0x8e76826f, - 0xbef600ff, 0x01000000, - 0xbefc006f, 0xc031003a, - 0x00000078, 0x80f8c078, - 0xbf8cc07f, 0x80fc907c, - 0xbf800000, 0xbe802d00, - 0xbe822d02, 0xbe842d04, - 0xbe862d06, 0xbe882d08, - 0xbe8a2d0a, 0xbe8c2d0c, - 0xbe8e2d0e, 0xbf06807c, - 0xbf84fff0, 0xb8f82985, - 0x80788178, 0x8e788a78, - 0x8e788178, 0xb8ee1605, - 0x806e816e, 0x8e6e866e, - 0x80786e78, 0xbef60084, - 0xbef600ff, 0x01000000, - 0xc0211bfa, 0x00000078, - 0x80788478, 0xc0211b3a, + 0xbf85ffee, 0xb8ef2985, + 0x806f816f, 0x8e6f836f, + 0xb8f92b05, 0x80798179, + 0x8e798279, 0x80ef796f, + 0x866f6f6f, 0xbf84001a, + 0x806fff6f, 0x00008000, + 0xbefc0080, 0xbf11087c, + 0xe0524000, 0x781d0000, + 0xe0524100, 0x781d0100, + 0xe0524200, 0x781d0200, + 0xe0524300, 0x781d0300, + 0xbf8c0f70, 0xd3d94000, + 0x18000100, 0xd3d94001, + 0x18000101, 0xd3d94002, + 0x18000102, 0xd3d94003, + 0x18000103, 0x807c847c, + 0x8078ff78, 0x00000400, + 0xbf0a6f7c, 0xbf85ffea, + 0xbf9c0000, 0xe0524000, + 0x6e1d0000, 0xe0524100, + 0x6e1d0100, 0xe0524200, + 0x6e1d0200, 0xe0524300, + 0x6e1d0300, 0xbf8c0f70, + 0xb8f82985, 0x80788178, + 0x8e788a78, 0x8e788178, + 0xb8ee1605, 0x806e816e, + 0x8e6e866e, 0x80786e78, + 0x80f8c078, 0xb8ef1605, + 0x806f816f, 0x8e6f846f, + 0x8e76826f, 0xbef600ff, + 0x01000000, 0xbefc006f, + 0xc031003a, 0x00000078, + 0x80f8c078, 0xbf8cc07f, + 0x80fc907c, 0xbf800000, + 0xbe802d00, 0xbe822d02, + 0xbe842d04, 0xbe862d06, + 0xbe882d08, 0xbe8a2d0a, + 0xbe8c2d0c, 0xbe8e2d0e, + 0xbf06807c, 0xbf84fff0, + 0xb8f82985, 0x80788178, + 0x8e788a78, 0x8e788178, + 0xb8ee1605, 0x806e816e, + 0x8e6e866e, 0x80786e78, + 0xbef60084, 0xbef600ff, + 0x01000000, 0xc0211bfa, 0x00000078, 0x80788478, - 0xc0211b7a, 0x00000078, - 0x80788478, 0xc0211c3a, + 0xc0211b3a, 0x00000078, + 0x80788478, 0xc0211b7a, 0x00000078, 0x80788478, - 0xc0211c7a, 0x00000078, - 0x80788478, 0xc0211eba, + 0xc0211c3a, 0x00000078, + 0x80788478, 0xc0211c7a, 0x00000078, 0x80788478, - 0xc0211efa, 0x00000078, - 0x80788478, 0xc0211a3a, + 0xc0211eba, 0x00000078, + 0x80788478, 0xc0211efa, 0x00000078, 0x80788478, - 0xc0211a7a, 0x00000078, - 0x80788478, 0xc0211cfa, + 0xc0211a3a, 0x00000078, + 0x80788478, 0xc0211a7a, 0x00000078, 0x80788478, - 0xbf8cc07f, 0xbefc006f, - 0xbefe0070, 0xbeff0071, - 0x866f7bff, 0x000003ff, - 0xb96f4803, 0x866f7bff, - 0xfffff800, 0x8f6f8b6f, - 0xb96fa2c3, 0xb973f801, - 0xb8ee2985, 0x806e816e, - 0x8e6e8a6e, 0x8e6e816e, - 0xb8ef1605, 0x806f816f, - 0x8e6f866f, 0x806e6f6e, - 0x806e746e, 0x826f8075, - 0x866fff6f, 0x0000ffff, - 0xc00b1c37, 0x00000050, - 0xc00b1d37, 0x00000060, - 0xc0031e77, 0x00000074, - 0xbf8cc07f, 0x8f6e8b79, - 0x866eff6e, 0x001f8000, - 0xb96ef807, 0x866dff6d, - 0x0000ffff, 0x86fe7e7e, - 0x86ea6a6a, 0x8f6e837a, - 0xb96ee0c2, 0xbf800002, - 0xb97a0002, 0xbf8a0000, - 0xbe801f6c, 0xbf9b0000, + 0xc0211cfa, 0x00000078, + 0x80788478, 0xbf8cc07f, + 0xbefc006f, 0xbefe0070, + 0xbeff0071, 0x866f7bff, + 0x000003ff, 0xb96f4803, + 0x866f7bff, 0xfffff800, + 0x8f6f8b6f, 0xb96fa2c3, + 0xb973f801, 0xb8ee2985, + 0x806e816e, 0x8e6e8a6e, + 0x8e6e816e, 0xb8ef1605, + 0x806f816f, 0x8e6f866f, + 0x806e6f6e, 0x806e746e, + 0x826f8075, 0x866fff6f, + 0x0000ffff, 0xc00b1c37, + 0x00000050, 0xc00b1d37, + 0x00000060, 0xc0031e77, + 0x00000074, 0xbf8cc07f, + 0x8f6e8b79, 0x866eff6e, + 0x001f8000, 0xb96ef807, + 0x866dff6d, 0x0000ffff, + 0x86fe7e7e, 0x86ea6a6a, + 0x8f6e837a, 0xb96ee0c2, + 0xbf800002, 0xb97a0002, + 0xbf8a0000, 0xbe801f6c, + 0xbf9b0000, 0x00000000, }; static const uint32_t cwsr_trap_gfx12_hex[] = { @@ -4124,27 +4128,25 @@ static const uint32_t cwsr_trap_gfx12_hex[] = { }; static const uint32_t cwsr_trap_gfx9_5_0_hex[] = { - 0xbf820001, 0xbf8202d8, + 0xbf820001, 0xbf8202ca, 0xb8f8f802, 0x8978ff78, 0x00020006, 0xb8fbf803, 0x866eff78, 0x00002000, - 0xbf840008, 0xbf0d986d, - 0xbf85001f, 0x866eff7b, - 0x00000400, 0xbf850061, - 0xbf8e0010, 0xb8fbf803, - 0xbf82fffa, 0x866eff7b, - 0x03800900, 0xbf850015, - 0x866eff7b, 0x000071ff, - 0xbf840008, 0x866fff7b, - 0x00007080, 0xbf840001, - 0xbeee1a87, 0xb8eff801, - 0x8e6e8c6e, 0x866e6f6e, - 0xbf85000a, 0xbf0d986d, - 0xbf850003, 0x866eff6d, - 0x00ff0000, 0xbf850005, - 0xbf0d986d, 0xbf850004, + 0xbf840009, 0x866eff6d, + 0x00ff0000, 0xbf85001a, 0x866eff7b, 0x00000400, - 0xbf850046, 0xbeed1a9d, + 0xbf850051, 0xbf8e0010, + 0xb8fbf803, 0xbf82fffa, + 0x866eff7b, 0x03c00900, + 0xbf850011, 0x866eff7b, + 0x000071ff, 0xbf840008, + 0x866fff7b, 0x00007080, + 0xbf840001, 0xbeee1a87, + 0xb8eff801, 0x8e6e8c6e, + 0x866e6f6e, 0xbf850006, + 0x866eff6d, 0x00ff0000, + 0xbf850003, 0x866eff7b, + 0x00000400, 0xbf85003a, 0xb8faf807, 0x867aff7a, 0x001f8000, 0x8e7a8b7a, 0x8979ff79, 0xfc000000, @@ -4153,100 +4155,95 @@ static const uint32_t cwsr_trap_gfx9_5_0_hex[] = { 0xb8fbf813, 0x8efa887a, 0xbf0d8f7b, 0xbf840002, 0x877bff7b, 0xffff0000, - 0xc0031cfd, 0x00000010, - 0xc0071bbd, 0x00000000, + 0xc0031bbd, 0x00000010, + 0xbf8cc07f, 0x8e6e976e, + 0x8979ff79, 0x00800000, + 0x87796e79, 0xc0071bbd, + 0x00000000, 0xbf8cc07f, 0xc0071ebd, 0x00000008, - 0xbf8cc07f, 0x8e739773, - 0x8979ff79, 0x01800000, - 0x87797379, 0xbf0d986d, - 0xbf840009, 0xbf0d9879, - 0xbf850007, 0x896dff6d, - 0x01ff0000, 0xba7f0583, - 0x00000000, 0xbf0d9d6d, - 0xbeed189d, 0xbf840012, - 0xbef91898, 0xbeed189d, - 0x86ee6e6e, 0xbf840001, - 0xbe801d6e, 0x866eff6d, - 0x01ff0000, 0xbf850005, - 0x8778ff78, 0x00002000, - 0x80ec886c, 0x82ed806d, - 0xbf820005, 0x866eff6d, - 0x01000000, 0xbf850002, - 0x806c846c, 0x826d806d, - 0x866dff6d, 0x0000ffff, - 0x8f7a8b79, 0x867aff7a, - 0x001f8000, 0xb97af807, - 0x86fe7e7e, 0x86ea6a6a, - 0x8f6e8378, 0xb96ee0c2, - 0xbf800002, 0xb9780002, - 0xbe801f6c, 0x866dff6d, - 0x0000ffff, 0xbefa0080, - 0xb97a0283, 0xb8faf807, + 0xbf8cc07f, 0x86ee6e6e, + 0xbf840001, 0xbe801d6e, + 0x866eff6d, 0x01ff0000, + 0xbf850005, 0x8778ff78, + 0x00002000, 0x80ec886c, + 0x82ed806d, 0xbf820005, + 0x866eff6d, 0x01000000, + 0xbf850002, 0x806c846c, + 0x826d806d, 0x866dff6d, + 0x0000ffff, 0x8f7a8b79, 0x867aff7a, 0x001f8000, - 0x8e7a8b7a, 0x8979ff79, - 0xfc000000, 0x87797a79, - 0xba7ff807, 0x00000000, - 0xbeee007e, 0xbeef007f, - 0xbefe0180, 0xbf900004, - 0x877a8478, 0xb97af802, - 0xbf8e0002, 0xbf88fffe, - 0xb8fa2985, 0x807a817a, - 0x8e7a8a7a, 0x8e7a817a, - 0xb8fb1605, 0x807b817b, - 0x8e7b867b, 0x807a7b7a, - 0x807a7e7a, 0x827b807f, - 0x867bff7b, 0x0000ffff, - 0xc04b1c3d, 0x00000050, - 0xbf8cc07f, 0xc04b1d3d, - 0x00000060, 0xbf8cc07f, - 0xc0431e7d, 0x00000074, - 0xbf8cc07f, 0xbef4007e, - 0x8675ff7f, 0x0000ffff, - 0x8775ff75, 0x00040000, - 0xbef60080, 0xbef700ff, - 0x00807fac, 0xbef1007c, - 0xbef00080, 0xb8f02985, - 0x80708170, 0x8e708a70, - 0x8e708170, 0xb8fa1605, - 0x807a817a, 0x8e7a867a, - 0x80707a70, 0xbef60084, - 0xbef600ff, 0x01000000, - 0xbefe007c, 0xbefc0070, - 0xc0611c7a, 0x0000007c, - 0xbf8cc07f, 0x80708470, - 0xbefc007e, 0xbefe007c, - 0xbefc0070, 0xc0611b3a, - 0x0000007c, 0xbf8cc07f, - 0x80708470, 0xbefc007e, - 0xbefe007c, 0xbefc0070, - 0xc0611b7a, 0x0000007c, - 0xbf8cc07f, 0x80708470, - 0xbefc007e, 0xbefe007c, - 0xbefc0070, 0xc0611bba, - 0x0000007c, 0xbf8cc07f, - 0x80708470, 0xbefc007e, - 0xbefe007c, 0xbefc0070, - 0xc0611bfa, 0x0000007c, - 0xbf8cc07f, 0x80708470, - 0xbefc007e, 0xbefe007c, - 0xbefc0070, 0xc0611e3a, - 0x0000007c, 0xbf8cc07f, - 0x80708470, 0xbefc007e, - 0xb8fbf803, 0xbefe007c, - 0xbefc0070, 0xc0611efa, - 0x0000007c, 0xbf8cc07f, - 0x80708470, 0xbefc007e, - 0xbefe007c, 0xbefc0070, - 0xc0611a3a, 0x0000007c, - 0xbf8cc07f, 0x80708470, - 0xbefc007e, 0xbefe007c, - 0xbefc0070, 0xc0611a7a, - 0x0000007c, 0xbf8cc07f, - 0x80708470, 0xbefc007e, - 0xb8f1f801, 0xbefe007c, + 0xb97af807, 0x86fe7e7e, + 0x86ea6a6a, 0x8f6e8378, + 0xb96ee0c2, 0xbf800002, + 0xb9780002, 0xbe801f6c, + 0x866dff6d, 0x0000ffff, + 0xbefa0080, 0xb97a0283, + 0xb8faf807, 0x867aff7a, + 0x001f8000, 0x8e7a8b7a, + 0x8979ff79, 0xfc000000, + 0x87797a79, 0xba7ff807, + 0x00000000, 0xbeee007e, + 0xbeef007f, 0xbefe0180, + 0xbf900004, 0x877a8478, + 0xb97af802, 0xbf8e0002, + 0xbf88fffe, 0xb8fa2985, + 0x807a817a, 0x8e7a8a7a, + 0x8e7a817a, 0xb8fb1605, + 0x807b817b, 0x8e7b867b, + 0x807a7b7a, 0x807a7e7a, + 0x827b807f, 0x867bff7b, + 0x0000ffff, 0xc04b1c3d, + 0x00000050, 0xbf8cc07f, + 0xc04b1d3d, 0x00000060, + 0xbf8cc07f, 0xc0431e7d, + 0x00000074, 0xbf8cc07f, + 0xbef4007e, 0x8675ff7f, + 0x0000ffff, 0x8775ff75, + 0x00040000, 0xbef60080, + 0xbef700ff, 0x00807fac, + 0xbef1007c, 0xbef00080, + 0xb8f02985, 0x80708170, + 0x8e708a70, 0x8e708170, + 0xb8fa1605, 0x807a817a, + 0x8e7a867a, 0x80707a70, + 0xbef60084, 0xbef600ff, + 0x01000000, 0xbefe007c, 0xbefc0070, 0xc0611c7a, 0x0000007c, 0xbf8cc07f, 0x80708470, 0xbefc007e, + 0xbefe007c, 0xbefc0070, + 0xc0611b3a, 0x0000007c, + 0xbf8cc07f, 0x80708470, + 0xbefc007e, 0xbefe007c, + 0xbefc0070, 0xc0611b7a, + 0x0000007c, 0xbf8cc07f, + 0x80708470, 0xbefc007e, + 0xbefe007c, 0xbefc0070, + 0xc0611bba, 0x0000007c, + 0xbf8cc07f, 0x80708470, + 0xbefc007e, 0xbefe007c, + 0xbefc0070, 0xc0611bfa, + 0x0000007c, 0xbf8cc07f, + 0x80708470, 0xbefc007e, + 0xbefe007c, 0xbefc0070, + 0xc0611e3a, 0x0000007c, + 0xbf8cc07f, 0x80708470, + 0xbefc007e, 0xb8fbf803, + 0xbefe007c, 0xbefc0070, + 0xc0611efa, 0x0000007c, + 0xbf8cc07f, 0x80708470, + 0xbefc007e, 0xbefe007c, + 0xbefc0070, 0xc0611a3a, + 0x0000007c, 0xbf8cc07f, + 0x80708470, 0xbefc007e, + 0xbefe007c, 0xbefc0070, + 0xc0611a7a, 0x0000007c, + 0xbf8cc07f, 0x80708470, + 0xbefc007e, 0xb8f1f801, + 0xbefe007c, 0xbefc0070, + 0xc0611c7a, 0x0000007c, + 0xbf8cc07f, 0x80708470, + 0xbefc007e, 0xbf108080, 0x867aff7f, 0x04000000, 0xbeef0080, 0x876f6f7a, 0xb8f02985, 0x80708170, diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm index 44772eec9ef4..96fbb16ceb21 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm @@ -34,41 +34,24 @@ * cpp -DASIC_FAMILY=CHIP_PLUM_BONITO cwsr_trap_handler_gfx10.asm -P -o gfx11.sp3 * sp3 gfx11.sp3 -hex gfx11.hex * - * gfx12: - * cpp -DASIC_FAMILY=CHIP_GFX12 cwsr_trap_handler_gfx10.asm -P -o gfx12.sp3 - * sp3 gfx12.sp3 -hex gfx12.hex */ #define CHIP_NAVI10 26 #define CHIP_SIENNA_CICHLID 30 #define CHIP_PLUM_BONITO 36 -#define CHIP_GFX12 37 #define NO_SQC_STORE (ASIC_FAMILY >= CHIP_SIENNA_CICHLID) #define HAVE_XNACK (ASIC_FAMILY < CHIP_SIENNA_CICHLID) #define HAVE_SENDMSG_RTN (ASIC_FAMILY >= CHIP_PLUM_BONITO) #define HAVE_BUFFER_LDS_LOAD (ASIC_FAMILY < CHIP_PLUM_BONITO) -#define SW_SA_TRAP (ASIC_FAMILY >= CHIP_PLUM_BONITO && ASIC_FAMILY < CHIP_GFX12) +#define SW_SA_TRAP (ASIC_FAMILY == CHIP_PLUM_BONITO) #define SAVE_AFTER_XNACK_ERROR (HAVE_XNACK && !NO_SQC_STORE) // workaround for TCP store failure after XNACK error when ALLOW_REPLAY=0, for debugger #define SINGLE_STEP_MISSED_WORKAROUND 1 //workaround for lost MODE.DEBUG_EN exception when SAVECTX raised -#if ASIC_FAMILY < CHIP_GFX12 #define S_COHERENCE glc:1 #define V_COHERENCE slc:1 glc:1 #define S_WAITCNT_0 s_waitcnt 0 -#else -#define S_COHERENCE scope:SCOPE_SYS -#define V_COHERENCE scope:SCOPE_SYS -#define S_WAITCNT_0 s_wait_idle -#define HW_REG_SHADER_FLAT_SCRATCH_LO HW_REG_WAVE_SCRATCH_BASE_LO -#define HW_REG_SHADER_FLAT_SCRATCH_HI HW_REG_WAVE_SCRATCH_BASE_HI -#define HW_REG_GPR_ALLOC HW_REG_WAVE_GPR_ALLOC -#define HW_REG_LDS_ALLOC HW_REG_WAVE_LDS_ALLOC -#define HW_REG_MODE HW_REG_WAVE_MODE -#endif - -#if ASIC_FAMILY < CHIP_GFX12 var SQ_WAVE_STATUS_SPI_PRIO_MASK = 0x00000006 var SQ_WAVE_STATUS_HALT_MASK = 0x2000 var SQ_WAVE_STATUS_ECC_ERR_MASK = 0x20000 @@ -81,21 +64,6 @@ var S_STATUS_ALWAYS_CLEAR_MASK = SQ_WAVE_STATUS_SPI_PRIO_MASK|SQ_WAVE_STATUS_E var S_STATUS_HALT_MASK = SQ_WAVE_STATUS_HALT_MASK var S_SAVE_PC_HI_TRAP_ID_MASK = 0x00FF0000 var S_SAVE_PC_HI_HT_MASK = 0x01000000 -#else -var SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK = 0x4 -var SQ_WAVE_STATE_PRIV_SCC_SHIFT = 9 -var SQ_WAVE_STATE_PRIV_SYS_PRIO_MASK = 0xC00 -var SQ_WAVE_STATE_PRIV_HALT_MASK = 0x4000 -var SQ_WAVE_STATE_PRIV_POISON_ERR_MASK = 0x8000 -var SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT = 15 -var SQ_WAVE_STATUS_WAVE64_SHIFT = 29 -var SQ_WAVE_STATUS_WAVE64_SIZE = 1 -var SQ_WAVE_LDS_ALLOC_GRANULARITY = 9 -var S_STATUS_HWREG = HW_REG_WAVE_STATE_PRIV -var S_STATUS_ALWAYS_CLEAR_MASK = SQ_WAVE_STATE_PRIV_SYS_PRIO_MASK|SQ_WAVE_STATE_PRIV_POISON_ERR_MASK -var S_STATUS_HALT_MASK = SQ_WAVE_STATE_PRIV_HALT_MASK -var S_SAVE_PC_HI_TRAP_ID_MASK = 0xF0000000 -#endif var SQ_WAVE_STATUS_NO_VGPRS_SHIFT = 24 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT = 12 @@ -110,7 +78,6 @@ var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT = 8 var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT = 12 #endif -#if ASIC_FAMILY < CHIP_GFX12 var SQ_WAVE_TRAPSTS_SAVECTX_MASK = 0x400 var SQ_WAVE_TRAPSTS_EXCP_MASK = 0x1FF var SQ_WAVE_TRAPSTS_SAVECTX_SHIFT = 10 @@ -161,39 +128,6 @@ var S_TRAPSTS_RESTORE_PART_3_SIZE = 32 - S_TRAPSTS_RESTORE_PART_3_SHIFT var S_TRAPSTS_HWREG = HW_REG_TRAPSTS var S_TRAPSTS_SAVE_CONTEXT_MASK = SQ_WAVE_TRAPSTS_SAVECTX_MASK var S_TRAPSTS_SAVE_CONTEXT_SHIFT = SQ_WAVE_TRAPSTS_SAVECTX_SHIFT -#else -var SQ_WAVE_EXCP_FLAG_PRIV_ADDR_WATCH_MASK = 0xF -var SQ_WAVE_EXCP_FLAG_PRIV_MEM_VIOL_MASK = 0x10 -var SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT = 5 -var SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK = 0x20 -var SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_MASK = 0x40 -var SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT = 6 -var SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK = 0x80 -var SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT = 7 -var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_MASK = 0x100 -var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT = 8 -var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_END_MASK = 0x200 -var SQ_WAVE_EXCP_FLAG_PRIV_TRAP_AFTER_INST_MASK = 0x800 -var SQ_WAVE_TRAP_CTRL_ADDR_WATCH_MASK = 0x80 -var SQ_WAVE_TRAP_CTRL_TRAP_AFTER_INST_MASK = 0x200 - -var S_TRAPSTS_HWREG = HW_REG_WAVE_EXCP_FLAG_PRIV -var S_TRAPSTS_SAVE_CONTEXT_MASK = SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK -var S_TRAPSTS_SAVE_CONTEXT_SHIFT = SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT -var S_TRAPSTS_NON_MASKABLE_EXCP_MASK = SQ_WAVE_EXCP_FLAG_PRIV_MEM_VIOL_MASK |\ - SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_MASK |\ - SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK |\ - SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_MASK |\ - SQ_WAVE_EXCP_FLAG_PRIV_WAVE_END_MASK |\ - SQ_WAVE_EXCP_FLAG_PRIV_TRAP_AFTER_INST_MASK -var S_TRAPSTS_RESTORE_PART_1_SIZE = SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT -var S_TRAPSTS_RESTORE_PART_2_SHIFT = SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT -var S_TRAPSTS_RESTORE_PART_2_SIZE = SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT - SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT -var S_TRAPSTS_RESTORE_PART_3_SHIFT = SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT -var S_TRAPSTS_RESTORE_PART_3_SIZE = 32 - S_TRAPSTS_RESTORE_PART_3_SHIFT -var BARRIER_STATE_SIGNAL_OFFSET = 16 -var BARRIER_STATE_VALID_OFFSET = 0 -#endif // bits [31:24] unused by SPI debug data var TTMP11_SAVE_REPLAY_W64H_SHIFT = 31 @@ -305,11 +239,7 @@ L_TRAP_NO_BARRIER: L_HALTED: // Host trap may occur while wave is halted. -#if ASIC_FAMILY < CHIP_GFX12 s_and_b32 ttmp2, s_save_pc_hi, S_SAVE_PC_HI_TRAP_ID_MASK -#else - s_and_b32 ttmp2, s_save_trapsts, SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK -#endif s_cbranch_scc1 L_FETCH_2ND_TRAP L_CHECK_SAVE: @@ -336,7 +266,6 @@ L_NOT_HALTED: // Check for maskable exceptions in trapsts.excp and trapsts.excp_hi. // Maskable exceptions only cause the wave to enter the trap handler if // their respective bit in mode.excp_en is set. -#if ASIC_FAMILY < CHIP_GFX12 s_and_b32 ttmp2, s_save_trapsts, SQ_WAVE_TRAPSTS_EXCP_MASK|SQ_WAVE_TRAPSTS_EXCP_HI_MASK s_cbranch_scc0 L_CHECK_TRAP_ID @@ -349,17 +278,6 @@ L_NOT_ADDR_WATCH: s_lshl_b32 ttmp2, ttmp2, SQ_WAVE_MODE_EXCP_EN_SHIFT s_and_b32 ttmp2, ttmp2, ttmp3 s_cbranch_scc1 L_FETCH_2ND_TRAP -#else - s_getreg_b32 ttmp2, hwreg(HW_REG_WAVE_EXCP_FLAG_USER) - s_and_b32 ttmp3, s_save_trapsts, SQ_WAVE_EXCP_FLAG_PRIV_ADDR_WATCH_MASK - s_cbranch_scc0 L_NOT_ADDR_WATCH - s_or_b32 ttmp2, ttmp2, SQ_WAVE_TRAP_CTRL_ADDR_WATCH_MASK - -L_NOT_ADDR_WATCH: - s_getreg_b32 ttmp3, hwreg(HW_REG_WAVE_TRAP_CTRL) - s_and_b32 ttmp2, ttmp3, ttmp2 - s_cbranch_scc1 L_FETCH_2ND_TRAP -#endif L_CHECK_TRAP_ID: // Check trap_id != 0 @@ -369,13 +287,8 @@ L_CHECK_TRAP_ID: #if SINGLE_STEP_MISSED_WORKAROUND // Prioritize single step exception over context save. // Second-level trap will halt wave and RFE, re-entering for SAVECTX. -#if ASIC_FAMILY < CHIP_GFX12 s_getreg_b32 ttmp2, hwreg(HW_REG_MODE) s_and_b32 ttmp2, ttmp2, SQ_WAVE_MODE_DEBUG_EN_MASK -#else - // WAVE_TRAP_CTRL is already in ttmp3. - s_and_b32 ttmp3, ttmp3, SQ_WAVE_TRAP_CTRL_TRAP_AFTER_INST_MASK -#endif s_cbranch_scc1 L_FETCH_2ND_TRAP #endif @@ -425,12 +338,7 @@ L_NO_NEXT_TRAP: s_cbranch_scc1 L_TRAP_CASE // Host trap will not cause trap re-entry. -#if ASIC_FAMILY < CHIP_GFX12 s_and_b32 ttmp2, s_save_pc_hi, S_SAVE_PC_HI_HT_MASK -#else - s_getreg_b32 ttmp2, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV) - s_and_b32 ttmp2, ttmp2, SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK -#endif s_cbranch_scc1 L_EXIT_TRAP s_or_b32 s_save_status, s_save_status, S_STATUS_HALT_MASK @@ -457,16 +365,7 @@ L_EXIT_TRAP: s_and_b64 exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32 s_and_b64 vcc, vcc, vcc // Restore STATUS.VCCZ, not writable by s_setreg_b32 -#if ASIC_FAMILY < CHIP_GFX12 s_setreg_b32 hwreg(S_STATUS_HWREG), s_save_status -#else - // STATE_PRIV.BARRIER_COMPLETE may have changed since we read it. - // Only restore fields which the trap handler changes. - s_lshr_b32 s_save_status, s_save_status, SQ_WAVE_STATE_PRIV_SCC_SHIFT - s_setreg_b32 hwreg(S_STATUS_HWREG, SQ_WAVE_STATE_PRIV_SCC_SHIFT, \ - SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT - SQ_WAVE_STATE_PRIV_SCC_SHIFT + 1), s_save_status -#endif - s_rfe_b64 [ttmp0, ttmp1] L_SAVE: @@ -478,14 +377,6 @@ L_SAVE: s_endpgm L_HAVE_VGPRS: #endif -#if ASIC_FAMILY >= CHIP_GFX12 - s_getreg_b32 s_save_tmp, hwreg(HW_REG_WAVE_STATUS) - s_bitcmp1_b32 s_save_tmp, SQ_WAVE_STATUS_NO_VGPRS_SHIFT - s_cbranch_scc0 L_HAVE_VGPRS - s_endpgm -L_HAVE_VGPRS: -#endif - s_and_b32 s_save_pc_hi, s_save_pc_hi, 0x0000ffff //pc[47:32] s_mov_b32 s_save_tmp, 0 s_setreg_b32 hwreg(S_TRAPSTS_HWREG, S_TRAPSTS_SAVE_CONTEXT_SHIFT, 1), s_save_tmp //clear saveCtx bit @@ -671,19 +562,6 @@ L_SAVE_HWREG: s_mov_b32 m0, 0x0 //Next lane of v2 to write to #endif -#if ASIC_FAMILY >= CHIP_GFX12 - // Ensure no further changes to barrier or LDS state. - // STATE_PRIV.BARRIER_COMPLETE may change up to this point. - s_barrier_signal -2 - s_barrier_wait -2 - - // Re-read final state of BARRIER_COMPLETE field for save. - s_getreg_b32 s_save_tmp, hwreg(S_STATUS_HWREG) - s_and_b32 s_save_tmp, s_save_tmp, SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK - s_andn2_b32 s_save_status, s_save_status, SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK - s_or_b32 s_save_status, s_save_status, s_save_tmp -#endif - write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset) write_hwreg_to_mem(s_save_pc_lo, s_save_buf_rsrc0, s_save_mem_offset) s_andn2_b32 s_save_tmp, s_save_pc_hi, S_SAVE_PC_HI_FIRST_WAVE_MASK @@ -707,21 +585,6 @@ L_SAVE_HWREG: s_getreg_b32 s_save_m0, hwreg(HW_REG_SHADER_FLAT_SCRATCH_HI) write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset) -#if ASIC_FAMILY >= CHIP_GFX12 - s_getreg_b32 s_save_m0, hwreg(HW_REG_WAVE_EXCP_FLAG_USER) - write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset) - - s_getreg_b32 s_save_m0, hwreg(HW_REG_WAVE_TRAP_CTRL) - write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset) - - s_getreg_b32 s_save_tmp, hwreg(HW_REG_WAVE_STATUS) - write_hwreg_to_mem(s_save_tmp, s_save_buf_rsrc0, s_save_mem_offset) - - s_get_barrier_state s_save_tmp, -1 - s_wait_kmcnt (0) - write_hwreg_to_mem(s_save_tmp, s_save_buf_rsrc0, s_save_mem_offset) -#endif - #if NO_SQC_STORE // Write HWREGs with 16 VGPR lanes. TTMPs occupy space after this. s_mov_b32 exec_lo, 0xFFFF @@ -814,9 +677,7 @@ L_SAVE_LDS_NORMAL: s_and_b32 s_save_alloc_size, s_save_alloc_size, 0xFFFFFFFF //lds_size is zero? s_cbranch_scc0 L_SAVE_LDS_DONE //no lds used? jump to L_SAVE_DONE -#if ASIC_FAMILY < CHIP_GFX12 s_barrier //LDS is used? wait for other waves in the same TG -#endif s_and_b32 s_save_tmp, s_save_pc_hi, S_SAVE_PC_HI_FIRST_WAVE_MASK s_cbranch_scc0 L_SAVE_LDS_DONE @@ -1081,11 +942,6 @@ L_RESTORE: s_mov_b32 s_restore_buf_rsrc2, 0 //NUM_RECORDS initial value = 0 (in bytes) s_mov_b32 s_restore_buf_rsrc3, S_RESTORE_BUF_RSRC_WORD3_MISC -#if ASIC_FAMILY >= CHIP_GFX12 - // Save s_restore_spi_init_hi for later use. - s_mov_b32 s_restore_spi_init_hi_save, s_restore_spi_init_hi -#endif - //determine it is wave32 or wave64 get_wave_size2(s_restore_size) @@ -1320,9 +1176,7 @@ L_RESTORE_SGPR: // s_barrier with MODE.DEBUG_EN=1, STATUS.PRIV=1 incorrectly asserts debug exception. // Clear DEBUG_EN before and restore MODE after the barrier. s_setreg_imm32_b32 hwreg(HW_REG_MODE), 0 -#if ASIC_FAMILY < CHIP_GFX12 s_barrier //barrier to ensure the readiness of LDS before access attemps from any other wave in the same TG -#endif /* restore HW registers */ L_RESTORE_HWREG: @@ -1334,11 +1188,6 @@ L_RESTORE_HWREG: s_mov_b32 s_restore_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes -#if ASIC_FAMILY >= CHIP_GFX12 - // Restore s_restore_spi_init_hi before the saved value gets clobbered. - s_mov_b32 s_restore_spi_init_hi, s_restore_spi_init_hi_save -#endif - read_hwreg_from_mem(s_restore_m0, s_restore_buf_rsrc0, s_restore_mem_offset) read_hwreg_from_mem(s_restore_pc_lo, s_restore_buf_rsrc0, s_restore_mem_offset) read_hwreg_from_mem(s_restore_pc_hi, s_restore_buf_rsrc0, s_restore_mem_offset) @@ -1358,44 +1207,6 @@ L_RESTORE_HWREG: s_setreg_b32 hwreg(HW_REG_SHADER_FLAT_SCRATCH_HI), s_restore_flat_scratch -#if ASIC_FAMILY >= CHIP_GFX12 - read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset) - S_WAITCNT_0 - s_setreg_b32 hwreg(HW_REG_WAVE_EXCP_FLAG_USER), s_restore_tmp - - read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset) - S_WAITCNT_0 - s_setreg_b32 hwreg(HW_REG_WAVE_TRAP_CTRL), s_restore_tmp - - // Only the first wave needs to restore the workgroup barrier. - s_and_b32 s_restore_tmp, s_restore_spi_init_hi, S_RESTORE_SPI_INIT_FIRST_WAVE_MASK - s_cbranch_scc0 L_SKIP_BARRIER_RESTORE - - // Skip over WAVE_STATUS, since there is no state to restore from it - s_add_u32 s_restore_mem_offset, s_restore_mem_offset, 4 - - read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset) - S_WAITCNT_0 - - s_bitcmp1_b32 s_restore_tmp, BARRIER_STATE_VALID_OFFSET - s_cbranch_scc0 L_SKIP_BARRIER_RESTORE - - // extract the saved signal count from s_restore_tmp - s_lshr_b32 s_restore_tmp, s_restore_tmp, BARRIER_STATE_SIGNAL_OFFSET - - // We need to call s_barrier_signal repeatedly to restore the signal - // count of the work group barrier. The member count is already - // initialized with the number of waves in the work group. -L_BARRIER_RESTORE_LOOP: - s_and_b32 s_restore_tmp, s_restore_tmp, s_restore_tmp - s_cbranch_scc0 L_SKIP_BARRIER_RESTORE - s_barrier_signal -1 - s_add_i32 s_restore_tmp, s_restore_tmp, -1 - s_branch L_BARRIER_RESTORE_LOOP - -L_SKIP_BARRIER_RESTORE: -#endif - s_mov_b32 m0, s_restore_m0 s_mov_b32 exec_lo, s_restore_exec_lo s_mov_b32 exec_hi, s_restore_exec_hi @@ -1453,13 +1264,6 @@ L_RETURN_WITHOUT_PRIV: s_setreg_b32 hwreg(S_STATUS_HWREG), s_restore_status // SCC is included, which is changed by previous salu -#if ASIC_FAMILY >= CHIP_GFX12 - // Make barrier and LDS state visible to all waves in the group. - // STATE_PRIV.BARRIER_COMPLETE may change after this point. - s_barrier_signal -2 - s_barrier_wait -2 -#endif - s_rfe_b64 s_restore_pc_lo //Return to the main shader program and resume execution L_END_PGM: @@ -1598,11 +1402,7 @@ function get_hwreg_size_bytes end function get_wave_size2(s_reg) -#if ASIC_FAMILY < CHIP_GFX12 s_getreg_b32 s_reg, hwreg(HW_REG_IB_STS2,SQ_WAVE_IB_STS2_WAVE64_SHIFT,SQ_WAVE_IB_STS2_WAVE64_SIZE) -#else - s_getreg_b32 s_reg, hwreg(HW_REG_WAVE_STATUS,SQ_WAVE_STATUS_WAVE64_SHIFT,SQ_WAVE_STATUS_WAVE64_SIZE) -#endif s_lshl_b32 s_reg, s_reg, S_WAVE_SIZE end diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm new file mode 100644 index 000000000000..1740e98c6719 --- /dev/null +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm @@ -0,0 +1,1126 @@ +/* + * Copyright 2018 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/* To compile this assembly code: + * + * gfx12: + * cpp -DASIC_FAMILY=CHIP_GFX12 cwsr_trap_handler_gfx12.asm -P -o gfx12.sp3 + * sp3 gfx12.sp3 -hex gfx12.hex + */ + +#define CHIP_GFX12 37 + +#define SINGLE_STEP_MISSED_WORKAROUND 1 //workaround for lost TRAP_AFTER_INST exception when SAVECTX raised + +var SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK = 0x4 +var SQ_WAVE_STATE_PRIV_SCC_SHIFT = 9 +var SQ_WAVE_STATE_PRIV_SYS_PRIO_MASK = 0xC00 +var SQ_WAVE_STATE_PRIV_HALT_MASK = 0x4000 +var SQ_WAVE_STATE_PRIV_POISON_ERR_MASK = 0x8000 +var SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT = 15 +var SQ_WAVE_STATUS_WAVE64_SHIFT = 29 +var SQ_WAVE_STATUS_WAVE64_SIZE = 1 +var SQ_WAVE_STATUS_NO_VGPRS_SHIFT = 24 +var SQ_WAVE_STATE_PRIV_ALWAYS_CLEAR_MASK = SQ_WAVE_STATE_PRIV_SYS_PRIO_MASK|SQ_WAVE_STATE_PRIV_POISON_ERR_MASK +var S_SAVE_PC_HI_TRAP_ID_MASK = 0xF0000000 + +var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT = 12 +var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE = 9 +var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE = 8 +var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT = 12 +var SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SHIFT = 24 +var SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SIZE = 4 +var SQ_WAVE_LDS_ALLOC_GRANULARITY = 9 + +var SQ_WAVE_EXCP_FLAG_PRIV_ADDR_WATCH_MASK = 0xF +var SQ_WAVE_EXCP_FLAG_PRIV_MEM_VIOL_MASK = 0x10 +var SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT = 5 +var SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK = 0x20 +var SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_MASK = 0x40 +var SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT = 6 +var SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK = 0x80 +var SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT = 7 +var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_MASK = 0x100 +var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT = 8 +var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_END_MASK = 0x200 +var SQ_WAVE_EXCP_FLAG_PRIV_TRAP_AFTER_INST_MASK = 0x800 +var SQ_WAVE_TRAP_CTRL_ADDR_WATCH_MASK = 0x80 +var SQ_WAVE_TRAP_CTRL_TRAP_AFTER_INST_MASK = 0x200 + +var SQ_WAVE_EXCP_FLAG_PRIV_NON_MASKABLE_EXCP_MASK= SQ_WAVE_EXCP_FLAG_PRIV_MEM_VIOL_MASK |\ + SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_MASK |\ + SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK |\ + SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_MASK |\ + SQ_WAVE_EXCP_FLAG_PRIV_WAVE_END_MASK |\ + SQ_WAVE_EXCP_FLAG_PRIV_TRAP_AFTER_INST_MASK +var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_1_SIZE = SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT +var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT = SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT +var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SIZE = SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT - SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT +var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT = SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT +var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SIZE = 32 - SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT +var BARRIER_STATE_SIGNAL_OFFSET = 16 +var BARRIER_STATE_VALID_OFFSET = 0 + +var TTMP11_DEBUG_TRAP_ENABLED_SHIFT = 23 +var TTMP11_DEBUG_TRAP_ENABLED_MASK = 0x800000 + +// SQ_SEL_X/Y/Z/W, BUF_NUM_FORMAT_FLOAT, (0 for MUBUF stride[17:14] +// when ADD_TID_ENABLE and BUF_DATA_FORMAT_32 for MTBUF), ADD_TID_ENABLE +var S_SAVE_BUF_RSRC_WORD1_STRIDE = 0x00040000 +var S_SAVE_BUF_RSRC_WORD3_MISC = 0x10807FAC +var S_SAVE_SPI_INIT_FIRST_WAVE_MASK = 0x04000000 +var S_SAVE_SPI_INIT_FIRST_WAVE_SHIFT = 26 + +var S_SAVE_PC_HI_FIRST_WAVE_MASK = 0x80000000 +var S_SAVE_PC_HI_FIRST_WAVE_SHIFT = 31 + +var s_sgpr_save_num = 108 + +var s_save_spi_init_lo = exec_lo +var s_save_spi_init_hi = exec_hi +var s_save_pc_lo = ttmp0 +var s_save_pc_hi = ttmp1 +var s_save_exec_lo = ttmp2 +var s_save_exec_hi = ttmp3 +var s_save_state_priv = ttmp12 +var s_save_excp_flag_priv = ttmp15 +var s_save_xnack_mask = s_save_excp_flag_priv +var s_wave_size = ttmp7 +var s_save_buf_rsrc0 = ttmp8 +var s_save_buf_rsrc1 = ttmp9 +var s_save_buf_rsrc2 = ttmp10 +var s_save_buf_rsrc3 = ttmp11 +var s_save_mem_offset = ttmp4 +var s_save_alloc_size = s_save_excp_flag_priv +var s_save_tmp = ttmp14 +var s_save_m0 = ttmp5 +var s_save_ttmps_lo = s_save_tmp +var s_save_ttmps_hi = s_save_excp_flag_priv + +var S_RESTORE_BUF_RSRC_WORD1_STRIDE = S_SAVE_BUF_RSRC_WORD1_STRIDE +var S_RESTORE_BUF_RSRC_WORD3_MISC = S_SAVE_BUF_RSRC_WORD3_MISC + +var S_RESTORE_SPI_INIT_FIRST_WAVE_MASK = 0x04000000 +var S_RESTORE_SPI_INIT_FIRST_WAVE_SHIFT = 26 +var S_WAVE_SIZE = 25 + +var s_restore_spi_init_lo = exec_lo +var s_restore_spi_init_hi = exec_hi +var s_restore_mem_offset = ttmp12 +var s_restore_alloc_size = ttmp3 +var s_restore_tmp = ttmp2 +var s_restore_mem_offset_save = s_restore_tmp +var s_restore_m0 = s_restore_alloc_size +var s_restore_mode = ttmp7 +var s_restore_flat_scratch = s_restore_tmp +var s_restore_pc_lo = ttmp0 +var s_restore_pc_hi = ttmp1 +var s_restore_exec_lo = ttmp4 +var s_restore_exec_hi = ttmp5 +var s_restore_state_priv = ttmp14 +var s_restore_excp_flag_priv = ttmp15 +var s_restore_xnack_mask = ttmp13 +var s_restore_buf_rsrc0 = ttmp8 +var s_restore_buf_rsrc1 = ttmp9 +var s_restore_buf_rsrc2 = ttmp10 +var s_restore_buf_rsrc3 = ttmp11 +var s_restore_size = ttmp6 +var s_restore_ttmps_lo = s_restore_tmp +var s_restore_ttmps_hi = s_restore_alloc_size +var s_restore_spi_init_hi_save = s_restore_exec_hi + +shader main + asic(DEFAULT) + type(CS) + wave_size(32) + + s_branch L_SKIP_RESTORE //NOT restore. might be a regular trap or save + +L_JUMP_TO_RESTORE: + s_branch L_RESTORE + +L_SKIP_RESTORE: + s_getreg_b32 s_save_state_priv, hwreg(HW_REG_WAVE_STATE_PRIV) //save STATUS since we will change SCC + + // Clear SPI_PRIO: do not save with elevated priority. + // Clear ECC_ERR: prevents SQC store and triggers FATAL_HALT if setreg'd. + s_andn2_b32 s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_ALWAYS_CLEAR_MASK + + s_getreg_b32 s_save_excp_flag_priv, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV) + + s_and_b32 ttmp2, s_save_state_priv, SQ_WAVE_STATE_PRIV_HALT_MASK + s_cbranch_scc0 L_NOT_HALTED + +L_HALTED: + // Host trap may occur while wave is halted. + s_and_b32 ttmp2, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK + s_cbranch_scc1 L_FETCH_2ND_TRAP + +L_CHECK_SAVE: + s_and_b32 ttmp2, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK + s_cbranch_scc1 L_SAVE + + // Wave is halted but neither host trap nor SAVECTX is raised. + // Caused by instruction fetch memory violation. + // Spin wait until context saved to prevent interrupt storm. + s_sleep 0x10 + s_getreg_b32 s_save_excp_flag_priv, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV) + s_branch L_CHECK_SAVE + +L_NOT_HALTED: + // Let second-level handle non-SAVECTX exception or trap. + // Any concurrent SAVECTX will be handled upon re-entry once halted. + + // Check non-maskable exceptions. memory_violation, illegal_instruction + // and xnack_error exceptions always cause the wave to enter the trap + // handler. + s_and_b32 ttmp2, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_NON_MASKABLE_EXCP_MASK + s_cbranch_scc1 L_FETCH_2ND_TRAP + + // Check for maskable exceptions in trapsts.excp and trapsts.excp_hi. + // Maskable exceptions only cause the wave to enter the trap handler if + // their respective bit in mode.excp_en is set. + s_getreg_b32 ttmp2, hwreg(HW_REG_WAVE_EXCP_FLAG_USER) + s_and_b32 ttmp3, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_ADDR_WATCH_MASK + s_cbranch_scc0 L_NOT_ADDR_WATCH + s_or_b32 ttmp2, ttmp2, SQ_WAVE_TRAP_CTRL_ADDR_WATCH_MASK + +L_NOT_ADDR_WATCH: + s_getreg_b32 ttmp3, hwreg(HW_REG_WAVE_TRAP_CTRL) + s_and_b32 ttmp2, ttmp3, ttmp2 + s_cbranch_scc1 L_FETCH_2ND_TRAP + +L_CHECK_TRAP_ID: + // Check trap_id != 0 + s_and_b32 ttmp2, s_save_pc_hi, S_SAVE_PC_HI_TRAP_ID_MASK + s_cbranch_scc1 L_FETCH_2ND_TRAP + +#if SINGLE_STEP_MISSED_WORKAROUND + // Prioritize single step exception over context save. + // Second-level trap will halt wave and RFE, re-entering for SAVECTX. + // WAVE_TRAP_CTRL is already in ttmp3. + s_and_b32 ttmp3, ttmp3, SQ_WAVE_TRAP_CTRL_TRAP_AFTER_INST_MASK + s_cbranch_scc1 L_FETCH_2ND_TRAP +#endif + + s_and_b32 ttmp2, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK + s_cbranch_scc1 L_SAVE + +L_FETCH_2ND_TRAP: + // Read second-level TBA/TMA from first-level TMA and jump if available. + // ttmp[2:5] and ttmp12 can be used (others hold SPI-initialized debug data) + // ttmp12 holds SQ_WAVE_STATUS + s_sendmsg_rtn_b64 [ttmp14, ttmp15], sendmsg(MSG_RTN_GET_TMA) + s_wait_idle + s_lshl_b64 [ttmp14, ttmp15], [ttmp14, ttmp15], 0x8 + + s_bitcmp1_b32 ttmp15, 0xF + s_cbranch_scc0 L_NO_SIGN_EXTEND_TMA + s_or_b32 ttmp15, ttmp15, 0xFFFF0000 +L_NO_SIGN_EXTEND_TMA: + + s_load_dword ttmp2, [ttmp14, ttmp15], 0x10 scope:SCOPE_SYS // debug trap enabled flag + s_wait_idle + s_lshl_b32 ttmp2, ttmp2, TTMP11_DEBUG_TRAP_ENABLED_SHIFT + s_andn2_b32 ttmp11, ttmp11, TTMP11_DEBUG_TRAP_ENABLED_MASK + s_or_b32 ttmp11, ttmp11, ttmp2 + + s_load_dwordx2 [ttmp2, ttmp3], [ttmp14, ttmp15], 0x0 scope:SCOPE_SYS // second-level TBA + s_wait_idle + s_load_dwordx2 [ttmp14, ttmp15], [ttmp14, ttmp15], 0x8 scope:SCOPE_SYS // second-level TMA + s_wait_idle + + s_and_b64 [ttmp2, ttmp3], [ttmp2, ttmp3], [ttmp2, ttmp3] + s_cbranch_scc0 L_NO_NEXT_TRAP // second-level trap handler not been set + s_setpc_b64 [ttmp2, ttmp3] // jump to second-level trap handler + +L_NO_NEXT_TRAP: + // If not caused by trap then halt wave to prevent re-entry. + s_and_b32 ttmp2, s_save_pc_hi, S_SAVE_PC_HI_TRAP_ID_MASK + s_cbranch_scc1 L_TRAP_CASE + + // Host trap will not cause trap re-entry. + s_getreg_b32 ttmp2, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV) + s_and_b32 ttmp2, ttmp2, SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK + s_cbranch_scc1 L_EXIT_TRAP + s_or_b32 s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_HALT_MASK + + // If the PC points to S_ENDPGM then context save will fail if STATE_PRIV.HALT is set. + // Rewind the PC to prevent this from occurring. + s_sub_u32 ttmp0, ttmp0, 0x8 + s_subb_u32 ttmp1, ttmp1, 0x0 + + s_branch L_EXIT_TRAP + +L_TRAP_CASE: + // Advance past trap instruction to prevent re-entry. + s_add_u32 ttmp0, ttmp0, 0x4 + s_addc_u32 ttmp1, ttmp1, 0x0 + +L_EXIT_TRAP: + s_and_b32 ttmp1, ttmp1, 0xFFFF + + // Restore SQ_WAVE_STATUS. + s_and_b64 exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32 + s_and_b64 vcc, vcc, vcc // Restore STATUS.VCCZ, not writable by s_setreg_b32 + + // STATE_PRIV.BARRIER_COMPLETE may have changed since we read it. + // Only restore fields which the trap handler changes. + s_lshr_b32 s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_SCC_SHIFT + s_setreg_b32 hwreg(HW_REG_WAVE_STATE_PRIV, SQ_WAVE_STATE_PRIV_SCC_SHIFT, \ + SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT - SQ_WAVE_STATE_PRIV_SCC_SHIFT + 1), s_save_state_priv + + s_rfe_b64 [ttmp0, ttmp1] + +L_SAVE: + // If VGPRs have been deallocated then terminate the wavefront. + // It has no remaining program to run and cannot save without VGPRs. + s_getreg_b32 s_save_tmp, hwreg(HW_REG_WAVE_STATUS) + s_bitcmp1_b32 s_save_tmp, SQ_WAVE_STATUS_NO_VGPRS_SHIFT + s_cbranch_scc0 L_HAVE_VGPRS + s_endpgm +L_HAVE_VGPRS: + + s_and_b32 s_save_pc_hi, s_save_pc_hi, 0x0000ffff //pc[47:32] + s_mov_b32 s_save_tmp, 0 + s_setreg_b32 hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV, SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT, 1), s_save_tmp //clear saveCtx bit + + /* inform SPI the readiness and wait for SPI's go signal */ + s_mov_b32 s_save_exec_lo, exec_lo //save EXEC and use EXEC for the go signal from SPI + s_mov_b32 s_save_exec_hi, exec_hi + s_mov_b64 exec, 0x0 //clear EXEC to get ready to receive + + s_sendmsg_rtn_b64 [exec_lo, exec_hi], sendmsg(MSG_RTN_SAVE_WAVE) + s_wait_idle + + // Save first_wave flag so we can clear high bits of save address. + s_and_b32 s_save_tmp, s_save_spi_init_hi, S_SAVE_SPI_INIT_FIRST_WAVE_MASK + s_lshl_b32 s_save_tmp, s_save_tmp, (S_SAVE_PC_HI_FIRST_WAVE_SHIFT - S_SAVE_SPI_INIT_FIRST_WAVE_SHIFT) + s_or_b32 s_save_pc_hi, s_save_pc_hi, s_save_tmp + + // Trap temporaries must be saved via VGPR but all VGPRs are in use. + // There is no ttmp space to hold the resource constant for VGPR save. + // Save v0 by itself since it requires only two SGPRs. + s_mov_b32 s_save_ttmps_lo, exec_lo + s_and_b32 s_save_ttmps_hi, exec_hi, 0xFFFF + s_mov_b32 exec_lo, 0xFFFFFFFF + s_mov_b32 exec_hi, 0xFFFFFFFF + global_store_dword_addtid v0, [s_save_ttmps_lo, s_save_ttmps_hi] scope:SCOPE_SYS + v_mov_b32 v0, 0x0 + s_mov_b32 exec_lo, s_save_ttmps_lo + s_mov_b32 exec_hi, s_save_ttmps_hi + + // Save trap temporaries 4-11, 13 initialized by SPI debug dispatch logic + // ttmp SR memory offset : size(VGPR)+size(SVGPR)+size(SGPR)+0x40 + get_wave_size2(s_save_ttmps_hi) + get_vgpr_size_bytes(s_save_ttmps_lo, s_save_ttmps_hi) + get_svgpr_size_bytes(s_save_ttmps_hi) + s_add_u32 s_save_ttmps_lo, s_save_ttmps_lo, s_save_ttmps_hi + s_and_b32 s_save_ttmps_hi, s_save_spi_init_hi, 0xFFFF + s_add_u32 s_save_ttmps_lo, s_save_ttmps_lo, get_sgpr_size_bytes() + s_add_u32 s_save_ttmps_lo, s_save_ttmps_lo, s_save_spi_init_lo + s_addc_u32 s_save_ttmps_hi, s_save_ttmps_hi, 0x0 + + v_writelane_b32 v0, ttmp4, 0x4 + v_writelane_b32 v0, ttmp5, 0x5 + v_writelane_b32 v0, ttmp6, 0x6 + v_writelane_b32 v0, ttmp7, 0x7 + v_writelane_b32 v0, ttmp8, 0x8 + v_writelane_b32 v0, ttmp9, 0x9 + v_writelane_b32 v0, ttmp10, 0xA + v_writelane_b32 v0, ttmp11, 0xB + v_writelane_b32 v0, ttmp13, 0xD + v_writelane_b32 v0, exec_lo, 0xE + v_writelane_b32 v0, exec_hi, 0xF + + s_mov_b32 exec_lo, 0x3FFF + s_mov_b32 exec_hi, 0x0 + global_store_dword_addtid v0, [s_save_ttmps_lo, s_save_ttmps_hi] offset:0x40 scope:SCOPE_SYS + v_readlane_b32 ttmp14, v0, 0xE + v_readlane_b32 ttmp15, v0, 0xF + s_mov_b32 exec_lo, ttmp14 + s_mov_b32 exec_hi, ttmp15 + + /* setup Resource Contants */ + s_mov_b32 s_save_buf_rsrc0, s_save_spi_init_lo //base_addr_lo + s_and_b32 s_save_buf_rsrc1, s_save_spi_init_hi, 0x0000FFFF //base_addr_hi + s_or_b32 s_save_buf_rsrc1, s_save_buf_rsrc1, S_SAVE_BUF_RSRC_WORD1_STRIDE + s_mov_b32 s_save_buf_rsrc2, 0 //NUM_RECORDS initial value = 0 (in bytes) although not neccessarily inited + s_mov_b32 s_save_buf_rsrc3, S_SAVE_BUF_RSRC_WORD3_MISC + + s_mov_b32 s_save_m0, m0 + + /* global mem offset */ + s_mov_b32 s_save_mem_offset, 0x0 + get_wave_size2(s_wave_size) + + /* save first 4 VGPRs, needed for SGPR save */ + s_mov_b32 exec_lo, 0xFFFFFFFF //need every thread from now on + s_lshr_b32 m0, s_wave_size, S_WAVE_SIZE + s_and_b32 m0, m0, 1 + s_cmp_eq_u32 m0, 1 + s_cbranch_scc1 L_ENABLE_SAVE_4VGPR_EXEC_HI + s_mov_b32 exec_hi, 0x00000000 + s_branch L_SAVE_4VGPR_WAVE32 +L_ENABLE_SAVE_4VGPR_EXEC_HI: + s_mov_b32 exec_hi, 0xFFFFFFFF + s_branch L_SAVE_4VGPR_WAVE64 +L_SAVE_4VGPR_WAVE32: + s_mov_b32 s_save_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + // VGPR Allocated in 4-GPR granularity + + buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128 + buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128*2 + buffer_store_dword v3, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128*3 + s_branch L_SAVE_HWREG + +L_SAVE_4VGPR_WAVE64: + s_mov_b32 s_save_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + // VGPR Allocated in 4-GPR granularity + + buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256 + buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256*2 + buffer_store_dword v3, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256*3 + + /* save HW registers */ + +L_SAVE_HWREG: + // HWREG SR memory offset : size(VGPR)+size(SVGPR)+size(SGPR) + get_vgpr_size_bytes(s_save_mem_offset, s_wave_size) + get_svgpr_size_bytes(s_save_tmp) + s_add_u32 s_save_mem_offset, s_save_mem_offset, s_save_tmp + s_add_u32 s_save_mem_offset, s_save_mem_offset, get_sgpr_size_bytes() + + s_mov_b32 s_save_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + v_mov_b32 v0, 0x0 //Offset[31:0] from buffer resource + v_mov_b32 v1, 0x0 //Offset[63:32] from buffer resource + v_mov_b32 v2, 0x0 //Set of SGPRs for TCP store + s_mov_b32 m0, 0x0 //Next lane of v2 to write to + + // Ensure no further changes to barrier or LDS state. + // STATE_PRIV.BARRIER_COMPLETE may change up to this point. + s_barrier_signal -2 + s_barrier_wait -2 + + // Re-read final state of BARRIER_COMPLETE field for save. + s_getreg_b32 s_save_tmp, hwreg(HW_REG_WAVE_STATE_PRIV) + s_and_b32 s_save_tmp, s_save_tmp, SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK + s_andn2_b32 s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK + s_or_b32 s_save_state_priv, s_save_state_priv, s_save_tmp + + write_hwreg_to_v2(s_save_m0) + write_hwreg_to_v2(s_save_pc_lo) + s_andn2_b32 s_save_tmp, s_save_pc_hi, S_SAVE_PC_HI_FIRST_WAVE_MASK + write_hwreg_to_v2(s_save_tmp) + write_hwreg_to_v2(s_save_exec_lo) + write_hwreg_to_v2(s_save_exec_hi) + write_hwreg_to_v2(s_save_state_priv) + + s_getreg_b32 s_save_tmp, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV) + write_hwreg_to_v2(s_save_tmp) + + write_hwreg_to_v2(s_save_xnack_mask) + + s_getreg_b32 s_save_m0, hwreg(HW_REG_WAVE_MODE) + write_hwreg_to_v2(s_save_m0) + + s_getreg_b32 s_save_m0, hwreg(HW_REG_WAVE_SCRATCH_BASE_LO) + write_hwreg_to_v2(s_save_m0) + + s_getreg_b32 s_save_m0, hwreg(HW_REG_WAVE_SCRATCH_BASE_HI) + write_hwreg_to_v2(s_save_m0) + + s_getreg_b32 s_save_m0, hwreg(HW_REG_WAVE_EXCP_FLAG_USER) + write_hwreg_to_v2(s_save_m0) + + s_getreg_b32 s_save_m0, hwreg(HW_REG_WAVE_TRAP_CTRL) + write_hwreg_to_v2(s_save_m0) + + s_getreg_b32 s_save_tmp, hwreg(HW_REG_WAVE_STATUS) + write_hwreg_to_v2(s_save_tmp) + + s_get_barrier_state s_save_tmp, -1 + s_wait_kmcnt (0) + write_hwreg_to_v2(s_save_tmp) + + // Write HWREGs with 16 VGPR lanes. TTMPs occupy space after this. + s_mov_b32 exec_lo, 0xFFFF + s_mov_b32 exec_hi, 0x0 + buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS + + // Write SGPRs with 32 VGPR lanes. This works in wave32 and wave64 mode. + s_mov_b32 exec_lo, 0xFFFFFFFF + + /* save SGPRs */ + // Save SGPR before LDS save, then the s0 to s4 can be used during LDS save... + + // SGPR SR memory offset : size(VGPR)+size(SVGPR) + get_vgpr_size_bytes(s_save_mem_offset, s_wave_size) + get_svgpr_size_bytes(s_save_tmp) + s_add_u32 s_save_mem_offset, s_save_mem_offset, s_save_tmp + s_mov_b32 s_save_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + s_mov_b32 ttmp13, 0x0 //next VGPR lane to copy SGPR into + + s_mov_b32 m0, 0x0 //SGPR initial index value =0 + s_nop 0x0 //Manually inserted wait states +L_SAVE_SGPR_LOOP: + // SGPR is allocated in 16 SGPR granularity + s_movrels_b64 s0, s0 //s0 = s[0+m0], s1 = s[1+m0] + s_movrels_b64 s2, s2 //s2 = s[2+m0], s3 = s[3+m0] + s_movrels_b64 s4, s4 //s4 = s[4+m0], s5 = s[5+m0] + s_movrels_b64 s6, s6 //s6 = s[6+m0], s7 = s[7+m0] + s_movrels_b64 s8, s8 //s8 = s[8+m0], s9 = s[9+m0] + s_movrels_b64 s10, s10 //s10 = s[10+m0], s11 = s[11+m0] + s_movrels_b64 s12, s12 //s12 = s[12+m0], s13 = s[13+m0] + s_movrels_b64 s14, s14 //s14 = s[14+m0], s15 = s[15+m0] + + write_16sgpr_to_v2(s0) + + s_cmp_eq_u32 ttmp13, 0x20 //have 32 VGPR lanes filled? + s_cbranch_scc0 L_SAVE_SGPR_SKIP_TCP_STORE + + buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS + s_add_u32 s_save_mem_offset, s_save_mem_offset, 0x80 + s_mov_b32 ttmp13, 0x0 + v_mov_b32 v2, 0x0 +L_SAVE_SGPR_SKIP_TCP_STORE: + + s_add_u32 m0, m0, 16 //next sgpr index + s_cmp_lt_u32 m0, 96 //scc = (m0 < first 96 SGPR) ? 1 : 0 + s_cbranch_scc1 L_SAVE_SGPR_LOOP //first 96 SGPR save is complete? + + //save the rest 12 SGPR + s_movrels_b64 s0, s0 //s0 = s[0+m0], s1 = s[1+m0] + s_movrels_b64 s2, s2 //s2 = s[2+m0], s3 = s[3+m0] + s_movrels_b64 s4, s4 //s4 = s[4+m0], s5 = s[5+m0] + s_movrels_b64 s6, s6 //s6 = s[6+m0], s7 = s[7+m0] + s_movrels_b64 s8, s8 //s8 = s[8+m0], s9 = s[9+m0] + s_movrels_b64 s10, s10 //s10 = s[10+m0], s11 = s[11+m0] + write_12sgpr_to_v2(s0) + + buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS + + /* save LDS */ + +L_SAVE_LDS: + // Change EXEC to all threads... + s_mov_b32 exec_lo, 0xFFFFFFFF //need every thread from now on + s_lshr_b32 m0, s_wave_size, S_WAVE_SIZE + s_and_b32 m0, m0, 1 + s_cmp_eq_u32 m0, 1 + s_cbranch_scc1 L_ENABLE_SAVE_LDS_EXEC_HI + s_mov_b32 exec_hi, 0x00000000 + s_branch L_SAVE_LDS_NORMAL +L_ENABLE_SAVE_LDS_EXEC_HI: + s_mov_b32 exec_hi, 0xFFFFFFFF +L_SAVE_LDS_NORMAL: + s_getreg_b32 s_save_alloc_size, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE) + s_and_b32 s_save_alloc_size, s_save_alloc_size, 0xFFFFFFFF //lds_size is zero? + s_cbranch_scc0 L_SAVE_LDS_DONE //no lds used? jump to L_SAVE_DONE + + s_and_b32 s_save_tmp, s_save_pc_hi, S_SAVE_PC_HI_FIRST_WAVE_MASK + s_cbranch_scc0 L_SAVE_LDS_DONE + + // first wave do LDS save; + + s_lshl_b32 s_save_alloc_size, s_save_alloc_size, SQ_WAVE_LDS_ALLOC_GRANULARITY + s_mov_b32 s_save_buf_rsrc2, s_save_alloc_size //NUM_RECORDS in bytes + + // LDS at offset: size(VGPR)+size(SVGPR)+SIZE(SGPR)+SIZE(HWREG) + // + get_vgpr_size_bytes(s_save_mem_offset, s_wave_size) + get_svgpr_size_bytes(s_save_tmp) + s_add_u32 s_save_mem_offset, s_save_mem_offset, s_save_tmp + s_add_u32 s_save_mem_offset, s_save_mem_offset, get_sgpr_size_bytes() + s_add_u32 s_save_mem_offset, s_save_mem_offset, get_hwreg_size_bytes() + + s_mov_b32 s_save_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + //load 0~63*4(byte address) to vgpr v0 + v_mbcnt_lo_u32_b32 v0, -1, 0 + v_mbcnt_hi_u32_b32 v0, -1, v0 + v_mul_u32_u24 v0, 4, v0 + + s_lshr_b32 m0, s_wave_size, S_WAVE_SIZE + s_and_b32 m0, m0, 1 + s_cmp_eq_u32 m0, 1 + s_mov_b32 m0, 0x0 + s_cbranch_scc1 L_SAVE_LDS_W64 + +L_SAVE_LDS_W32: + s_mov_b32 s3, 128 + s_nop 0 + s_nop 0 + s_nop 0 +L_SAVE_LDS_LOOP_W32: + ds_read_b32 v1, v0 + s_wait_idle + buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS + + s_add_u32 m0, m0, s3 //every buffer_store_lds does 128 bytes + s_add_u32 s_save_mem_offset, s_save_mem_offset, s3 + v_add_nc_u32 v0, v0, 128 //mem offset increased by 128 bytes + s_cmp_lt_u32 m0, s_save_alloc_size //scc=(m0 < s_save_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_SAVE_LDS_LOOP_W32 //LDS save is complete? + + s_branch L_SAVE_LDS_DONE + +L_SAVE_LDS_W64: + s_mov_b32 s3, 256 + s_nop 0 + s_nop 0 + s_nop 0 +L_SAVE_LDS_LOOP_W64: + ds_read_b32 v1, v0 + s_wait_idle + buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS + + s_add_u32 m0, m0, s3 //every buffer_store_lds does 256 bytes + s_add_u32 s_save_mem_offset, s_save_mem_offset, s3 + v_add_nc_u32 v0, v0, 256 //mem offset increased by 256 bytes + s_cmp_lt_u32 m0, s_save_alloc_size //scc=(m0 < s_save_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_SAVE_LDS_LOOP_W64 //LDS save is complete? + +L_SAVE_LDS_DONE: + /* save VGPRs - set the Rest VGPRs */ +L_SAVE_VGPR: + // VGPR SR memory offset: 0 + s_mov_b32 exec_lo, 0xFFFFFFFF //need every thread from now on + s_lshr_b32 m0, s_wave_size, S_WAVE_SIZE + s_and_b32 m0, m0, 1 + s_cmp_eq_u32 m0, 1 + s_cbranch_scc1 L_ENABLE_SAVE_VGPR_EXEC_HI + s_mov_b32 s_save_mem_offset, (0+128*4) // for the rest VGPRs + s_mov_b32 exec_hi, 0x00000000 + s_branch L_SAVE_VGPR_NORMAL +L_ENABLE_SAVE_VGPR_EXEC_HI: + s_mov_b32 s_save_mem_offset, (0+256*4) // for the rest VGPRs + s_mov_b32 exec_hi, 0xFFFFFFFF +L_SAVE_VGPR_NORMAL: + s_getreg_b32 s_save_alloc_size, hwreg(HW_REG_WAVE_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE) + s_add_u32 s_save_alloc_size, s_save_alloc_size, 1 + s_lshl_b32 s_save_alloc_size, s_save_alloc_size, 2 //Number of VGPRs = (vgpr_size + 1) * 4 (non-zero value) + //determine it is wave32 or wave64 + s_lshr_b32 m0, s_wave_size, S_WAVE_SIZE + s_and_b32 m0, m0, 1 + s_cmp_eq_u32 m0, 1 + s_cbranch_scc1 L_SAVE_VGPR_WAVE64 + + s_mov_b32 s_save_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + // VGPR Allocated in 4-GPR granularity + + // VGPR store using dw burst + s_mov_b32 m0, 0x4 //VGPR initial index value =4 + s_cmp_lt_u32 m0, s_save_alloc_size + s_cbranch_scc0 L_SAVE_VGPR_END + +L_SAVE_VGPR_W32_LOOP: + v_movrels_b32 v0, v0 //v0 = v[0+m0] + v_movrels_b32 v1, v1 //v1 = v[1+m0] + v_movrels_b32 v2, v2 //v2 = v[2+m0] + v_movrels_b32 v3, v3 //v3 = v[3+m0] + + buffer_store_dword v0, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS + buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128 + buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128*2 + buffer_store_dword v3, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128*3 + + s_add_u32 m0, m0, 4 //next vgpr index + s_add_u32 s_save_mem_offset, s_save_mem_offset, 128*4 //every buffer_store_dword does 128 bytes + s_cmp_lt_u32 m0, s_save_alloc_size //scc = (m0 < s_save_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_SAVE_VGPR_W32_LOOP //VGPR save is complete? + + s_branch L_SAVE_VGPR_END + +L_SAVE_VGPR_WAVE64: + s_mov_b32 s_save_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + // VGPR store using dw burst + s_mov_b32 m0, 0x4 //VGPR initial index value =4 + s_cmp_lt_u32 m0, s_save_alloc_size + s_cbranch_scc0 L_SAVE_SHARED_VGPR + +L_SAVE_VGPR_W64_LOOP: + v_movrels_b32 v0, v0 //v0 = v[0+m0] + v_movrels_b32 v1, v1 //v1 = v[1+m0] + v_movrels_b32 v2, v2 //v2 = v[2+m0] + v_movrels_b32 v3, v3 //v3 = v[3+m0] + + buffer_store_dword v0, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS + buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256 + buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256*2 + buffer_store_dword v3, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256*3 + + s_add_u32 m0, m0, 4 //next vgpr index + s_add_u32 s_save_mem_offset, s_save_mem_offset, 256*4 //every buffer_store_dword does 256 bytes + s_cmp_lt_u32 m0, s_save_alloc_size //scc = (m0 < s_save_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_SAVE_VGPR_W64_LOOP //VGPR save is complete? + +L_SAVE_SHARED_VGPR: + s_getreg_b32 s_save_alloc_size, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SIZE) + s_and_b32 s_save_alloc_size, s_save_alloc_size, 0xFFFFFFFF //shared_vgpr_size is zero? + s_cbranch_scc0 L_SAVE_VGPR_END //no shared_vgpr used? jump to L_SAVE_LDS + s_lshl_b32 s_save_alloc_size, s_save_alloc_size, 3 //Number of SHARED_VGPRs = shared_vgpr_size * 8 (non-zero value) + //m0 now has the value of normal vgpr count, just add the m0 with shared_vgpr count to get the total count. + //save shared_vgpr will start from the index of m0 + s_add_u32 s_save_alloc_size, s_save_alloc_size, m0 + s_mov_b32 exec_lo, 0xFFFFFFFF + s_mov_b32 exec_hi, 0x00000000 + +L_SAVE_SHARED_VGPR_WAVE64_LOOP: + v_movrels_b32 v0, v0 //v0 = v[0+m0] + buffer_store_dword v0, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS + s_add_u32 m0, m0, 1 //next vgpr index + s_add_u32 s_save_mem_offset, s_save_mem_offset, 128 + s_cmp_lt_u32 m0, s_save_alloc_size //scc = (m0 < s_save_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_SAVE_SHARED_VGPR_WAVE64_LOOP //SHARED_VGPR save is complete? + +L_SAVE_VGPR_END: + s_branch L_END_PGM + +L_RESTORE: + /* Setup Resource Contants */ + s_mov_b32 s_restore_buf_rsrc0, s_restore_spi_init_lo //base_addr_lo + s_and_b32 s_restore_buf_rsrc1, s_restore_spi_init_hi, 0x0000FFFF //base_addr_hi + s_or_b32 s_restore_buf_rsrc1, s_restore_buf_rsrc1, S_RESTORE_BUF_RSRC_WORD1_STRIDE + s_mov_b32 s_restore_buf_rsrc2, 0 //NUM_RECORDS initial value = 0 (in bytes) + s_mov_b32 s_restore_buf_rsrc3, S_RESTORE_BUF_RSRC_WORD3_MISC + + // Save s_restore_spi_init_hi for later use. + s_mov_b32 s_restore_spi_init_hi_save, s_restore_spi_init_hi + + //determine it is wave32 or wave64 + get_wave_size2(s_restore_size) + + s_and_b32 s_restore_tmp, s_restore_spi_init_hi, S_RESTORE_SPI_INIT_FIRST_WAVE_MASK + s_cbranch_scc0 L_RESTORE_VGPR + + /* restore LDS */ +L_RESTORE_LDS: + s_mov_b32 exec_lo, 0xFFFFFFFF //need every thread from now on + s_lshr_b32 m0, s_restore_size, S_WAVE_SIZE + s_and_b32 m0, m0, 1 + s_cmp_eq_u32 m0, 1 + s_cbranch_scc1 L_ENABLE_RESTORE_LDS_EXEC_HI + s_mov_b32 exec_hi, 0x00000000 + s_branch L_RESTORE_LDS_NORMAL +L_ENABLE_RESTORE_LDS_EXEC_HI: + s_mov_b32 exec_hi, 0xFFFFFFFF +L_RESTORE_LDS_NORMAL: + s_getreg_b32 s_restore_alloc_size, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE) + s_and_b32 s_restore_alloc_size, s_restore_alloc_size, 0xFFFFFFFF //lds_size is zero? + s_cbranch_scc0 L_RESTORE_VGPR //no lds used? jump to L_RESTORE_VGPR + s_lshl_b32 s_restore_alloc_size, s_restore_alloc_size, SQ_WAVE_LDS_ALLOC_GRANULARITY + s_mov_b32 s_restore_buf_rsrc2, s_restore_alloc_size //NUM_RECORDS in bytes + + // LDS at offset: size(VGPR)+size(SVGPR)+SIZE(SGPR)+SIZE(HWREG) + // + get_vgpr_size_bytes(s_restore_mem_offset, s_restore_size) + get_svgpr_size_bytes(s_restore_tmp) + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, get_sgpr_size_bytes() + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, get_hwreg_size_bytes() + + s_mov_b32 s_restore_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + s_lshr_b32 m0, s_restore_size, S_WAVE_SIZE + s_and_b32 m0, m0, 1 + s_cmp_eq_u32 m0, 1 + s_mov_b32 m0, 0x0 + s_cbranch_scc1 L_RESTORE_LDS_LOOP_W64 + +L_RESTORE_LDS_LOOP_W32: + buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset + s_wait_idle + ds_store_addtid_b32 v0 + s_add_u32 m0, m0, 128 // 128 DW + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, 128 //mem offset increased by 128DW + s_cmp_lt_u32 m0, s_restore_alloc_size //scc=(m0 < s_restore_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_RESTORE_LDS_LOOP_W32 //LDS restore is complete? + s_branch L_RESTORE_VGPR + +L_RESTORE_LDS_LOOP_W64: + buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset + s_wait_idle + ds_store_addtid_b32 v0 + s_add_u32 m0, m0, 256 // 256 DW + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, 256 //mem offset increased by 256DW + s_cmp_lt_u32 m0, s_restore_alloc_size //scc=(m0 < s_restore_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_RESTORE_LDS_LOOP_W64 //LDS restore is complete? + + /* restore VGPRs */ +L_RESTORE_VGPR: + // VGPR SR memory offset : 0 + s_mov_b32 s_restore_mem_offset, 0x0 + s_mov_b32 exec_lo, 0xFFFFFFFF //need every thread from now on + s_lshr_b32 m0, s_restore_size, S_WAVE_SIZE + s_and_b32 m0, m0, 1 + s_cmp_eq_u32 m0, 1 + s_cbranch_scc1 L_ENABLE_RESTORE_VGPR_EXEC_HI + s_mov_b32 exec_hi, 0x00000000 + s_branch L_RESTORE_VGPR_NORMAL +L_ENABLE_RESTORE_VGPR_EXEC_HI: + s_mov_b32 exec_hi, 0xFFFFFFFF +L_RESTORE_VGPR_NORMAL: + s_getreg_b32 s_restore_alloc_size, hwreg(HW_REG_WAVE_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE) + s_add_u32 s_restore_alloc_size, s_restore_alloc_size, 1 + s_lshl_b32 s_restore_alloc_size, s_restore_alloc_size, 2 //Number of VGPRs = (vgpr_size + 1) * 4 (non-zero value) + //determine it is wave32 or wave64 + s_lshr_b32 m0, s_restore_size, S_WAVE_SIZE + s_and_b32 m0, m0, 1 + s_cmp_eq_u32 m0, 1 + s_cbranch_scc1 L_RESTORE_VGPR_WAVE64 + + s_mov_b32 s_restore_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + // VGPR load using dw burst + s_mov_b32 s_restore_mem_offset_save, s_restore_mem_offset // restore start with v1, v0 will be the last + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, 128*4 + s_mov_b32 m0, 4 //VGPR initial index value = 4 + s_cmp_lt_u32 m0, s_restore_alloc_size + s_cbranch_scc0 L_RESTORE_SGPR + +L_RESTORE_VGPR_WAVE32_LOOP: + buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS + buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:128 + buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:128*2 + buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:128*3 + s_wait_idle + v_movreld_b32 v0, v0 //v[0+m0] = v0 + v_movreld_b32 v1, v1 + v_movreld_b32 v2, v2 + v_movreld_b32 v3, v3 + s_add_u32 m0, m0, 4 //next vgpr index + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, 128*4 //every buffer_load_dword does 128 bytes + s_cmp_lt_u32 m0, s_restore_alloc_size //scc = (m0 < s_restore_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_RESTORE_VGPR_WAVE32_LOOP //VGPR restore (except v0) is complete? + + /* VGPR restore on v0 */ + buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS + buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:128 + buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:128*2 + buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:128*3 + s_wait_idle + + s_branch L_RESTORE_SGPR + +L_RESTORE_VGPR_WAVE64: + s_mov_b32 s_restore_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + // VGPR load using dw burst + s_mov_b32 s_restore_mem_offset_save, s_restore_mem_offset // restore start with v4, v0 will be the last + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, 256*4 + s_mov_b32 m0, 4 //VGPR initial index value = 4 + s_cmp_lt_u32 m0, s_restore_alloc_size + s_cbranch_scc0 L_RESTORE_SHARED_VGPR + +L_RESTORE_VGPR_WAVE64_LOOP: + buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS + buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:256 + buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:256*2 + buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:256*3 + s_wait_idle + v_movreld_b32 v0, v0 //v[0+m0] = v0 + v_movreld_b32 v1, v1 + v_movreld_b32 v2, v2 + v_movreld_b32 v3, v3 + s_add_u32 m0, m0, 4 //next vgpr index + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, 256*4 //every buffer_load_dword does 256 bytes + s_cmp_lt_u32 m0, s_restore_alloc_size //scc = (m0 < s_restore_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_RESTORE_VGPR_WAVE64_LOOP //VGPR restore (except v0) is complete? + +L_RESTORE_SHARED_VGPR: + s_getreg_b32 s_restore_alloc_size, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SIZE) //shared_vgpr_size + s_and_b32 s_restore_alloc_size, s_restore_alloc_size, 0xFFFFFFFF //shared_vgpr_size is zero? + s_cbranch_scc0 L_RESTORE_V0 //no shared_vgpr used? + s_lshl_b32 s_restore_alloc_size, s_restore_alloc_size, 3 //Number of SHARED_VGPRs = shared_vgpr_size * 8 (non-zero value) + //m0 now has the value of normal vgpr count, just add the m0 with shared_vgpr count to get the total count. + //restore shared_vgpr will start from the index of m0 + s_add_u32 s_restore_alloc_size, s_restore_alloc_size, m0 + s_mov_b32 exec_lo, 0xFFFFFFFF + s_mov_b32 exec_hi, 0x00000000 +L_RESTORE_SHARED_VGPR_WAVE64_LOOP: + buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS + s_wait_idle + v_movreld_b32 v0, v0 //v[0+m0] = v0 + s_add_u32 m0, m0, 1 //next vgpr index + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, 128 + s_cmp_lt_u32 m0, s_restore_alloc_size //scc = (m0 < s_restore_alloc_size) ? 1 : 0 + s_cbranch_scc1 L_RESTORE_SHARED_VGPR_WAVE64_LOOP //VGPR restore (except v0) is complete? + + s_mov_b32 exec_hi, 0xFFFFFFFF //restore back exec_hi before restoring V0!! + + /* VGPR restore on v0 */ +L_RESTORE_V0: + buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS + buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:256 + buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:256*2 + buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:256*3 + s_wait_idle + + /* restore SGPRs */ + //will be 2+8+16*6 + // SGPR SR memory offset : size(VGPR)+size(SVGPR) +L_RESTORE_SGPR: + get_vgpr_size_bytes(s_restore_mem_offset, s_restore_size) + get_svgpr_size_bytes(s_restore_tmp) + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, get_sgpr_size_bytes() + s_sub_u32 s_restore_mem_offset, s_restore_mem_offset, 20*4 //s108~s127 is not saved + + s_mov_b32 s_restore_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + s_mov_b32 m0, s_sgpr_save_num + + read_4sgpr_from_mem(s0, s_restore_buf_rsrc0, s_restore_mem_offset) + s_wait_idle + + s_sub_u32 m0, m0, 4 // Restore from S[0] to S[104] + s_nop 0 // hazard SALU M0=> S_MOVREL + + s_movreld_b64 s0, s0 //s[0+m0] = s0 + s_movreld_b64 s2, s2 + + read_8sgpr_from_mem(s0, s_restore_buf_rsrc0, s_restore_mem_offset) + s_wait_idle + + s_sub_u32 m0, m0, 8 // Restore from S[0] to S[96] + s_nop 0 // hazard SALU M0=> S_MOVREL + + s_movreld_b64 s0, s0 //s[0+m0] = s0 + s_movreld_b64 s2, s2 + s_movreld_b64 s4, s4 + s_movreld_b64 s6, s6 + + L_RESTORE_SGPR_LOOP: + read_16sgpr_from_mem(s0, s_restore_buf_rsrc0, s_restore_mem_offset) + s_wait_idle + + s_sub_u32 m0, m0, 16 // Restore from S[n] to S[0] + s_nop 0 // hazard SALU M0=> S_MOVREL + + s_movreld_b64 s0, s0 //s[0+m0] = s0 + s_movreld_b64 s2, s2 + s_movreld_b64 s4, s4 + s_movreld_b64 s6, s6 + s_movreld_b64 s8, s8 + s_movreld_b64 s10, s10 + s_movreld_b64 s12, s12 + s_movreld_b64 s14, s14 + + s_cmp_eq_u32 m0, 0 //scc = (m0 < s_sgpr_save_num) ? 1 : 0 + s_cbranch_scc0 L_RESTORE_SGPR_LOOP + + // s_barrier with STATE_PRIV.TRAP_AFTER_INST=1, STATUS.PRIV=1 incorrectly asserts debug exception. + // Clear DEBUG_EN before and restore MODE after the barrier. + s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE), 0 + + /* restore HW registers */ +L_RESTORE_HWREG: + // HWREG SR memory offset : size(VGPR)+size(SVGPR)+size(SGPR) + get_vgpr_size_bytes(s_restore_mem_offset, s_restore_size) + get_svgpr_size_bytes(s_restore_tmp) + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, get_sgpr_size_bytes() + + s_mov_b32 s_restore_buf_rsrc2, 0x1000000 //NUM_RECORDS in bytes + + // Restore s_restore_spi_init_hi before the saved value gets clobbered. + s_mov_b32 s_restore_spi_init_hi, s_restore_spi_init_hi_save + + read_hwreg_from_mem(s_restore_m0, s_restore_buf_rsrc0, s_restore_mem_offset) + read_hwreg_from_mem(s_restore_pc_lo, s_restore_buf_rsrc0, s_restore_mem_offset) + read_hwreg_from_mem(s_restore_pc_hi, s_restore_buf_rsrc0, s_restore_mem_offset) + read_hwreg_from_mem(s_restore_exec_lo, s_restore_buf_rsrc0, s_restore_mem_offset) + read_hwreg_from_mem(s_restore_exec_hi, s_restore_buf_rsrc0, s_restore_mem_offset) + read_hwreg_from_mem(s_restore_state_priv, s_restore_buf_rsrc0, s_restore_mem_offset) + read_hwreg_from_mem(s_restore_excp_flag_priv, s_restore_buf_rsrc0, s_restore_mem_offset) + read_hwreg_from_mem(s_restore_xnack_mask, s_restore_buf_rsrc0, s_restore_mem_offset) + read_hwreg_from_mem(s_restore_mode, s_restore_buf_rsrc0, s_restore_mem_offset) + read_hwreg_from_mem(s_restore_flat_scratch, s_restore_buf_rsrc0, s_restore_mem_offset) + s_wait_idle + + s_setreg_b32 hwreg(HW_REG_WAVE_SCRATCH_BASE_LO), s_restore_flat_scratch + + read_hwreg_from_mem(s_restore_flat_scratch, s_restore_buf_rsrc0, s_restore_mem_offset) + s_wait_idle + + s_setreg_b32 hwreg(HW_REG_WAVE_SCRATCH_BASE_HI), s_restore_flat_scratch + + read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset) + s_wait_idle + s_setreg_b32 hwreg(HW_REG_WAVE_EXCP_FLAG_USER), s_restore_tmp + + read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset) + s_wait_idle + s_setreg_b32 hwreg(HW_REG_WAVE_TRAP_CTRL), s_restore_tmp + + // Only the first wave needs to restore the workgroup barrier. + s_and_b32 s_restore_tmp, s_restore_spi_init_hi, S_RESTORE_SPI_INIT_FIRST_WAVE_MASK + s_cbranch_scc0 L_SKIP_BARRIER_RESTORE + + // Skip over WAVE_STATUS, since there is no state to restore from it + s_add_u32 s_restore_mem_offset, s_restore_mem_offset, 4 + + read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset) + s_wait_idle + + s_bitcmp1_b32 s_restore_tmp, BARRIER_STATE_VALID_OFFSET + s_cbranch_scc0 L_SKIP_BARRIER_RESTORE + + // extract the saved signal count from s_restore_tmp + s_lshr_b32 s_restore_tmp, s_restore_tmp, BARRIER_STATE_SIGNAL_OFFSET + + // We need to call s_barrier_signal repeatedly to restore the signal + // count of the work group barrier. The member count is already + // initialized with the number of waves in the work group. +L_BARRIER_RESTORE_LOOP: + s_and_b32 s_restore_tmp, s_restore_tmp, s_restore_tmp + s_cbranch_scc0 L_SKIP_BARRIER_RESTORE + s_barrier_signal -1 + s_add_i32 s_restore_tmp, s_restore_tmp, -1 + s_branch L_BARRIER_RESTORE_LOOP + +L_SKIP_BARRIER_RESTORE: + + s_mov_b32 m0, s_restore_m0 + s_mov_b32 exec_lo, s_restore_exec_lo + s_mov_b32 exec_hi, s_restore_exec_hi + + // EXCP_FLAG_PRIV.SAVE_CONTEXT and HOST_TRAP may have changed. + // Only restore the other fields to avoid clobbering them. + s_setreg_b32 hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV, 0, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_1_SIZE), s_restore_excp_flag_priv + s_lshr_b32 s_restore_excp_flag_priv, s_restore_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT + s_setreg_b32 hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SIZE), s_restore_excp_flag_priv + s_lshr_b32 s_restore_excp_flag_priv, s_restore_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT - SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT + s_setreg_b32 hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SIZE), s_restore_excp_flag_priv + + s_setreg_b32 hwreg(HW_REG_WAVE_MODE), s_restore_mode + + // Restore trap temporaries 4-11, 13 initialized by SPI debug dispatch logic + // ttmp SR memory offset : size(VGPR)+size(SVGPR)+size(SGPR)+0x40 + get_vgpr_size_bytes(s_restore_ttmps_lo, s_restore_size) + get_svgpr_size_bytes(s_restore_ttmps_hi) + s_add_u32 s_restore_ttmps_lo, s_restore_ttmps_lo, s_restore_ttmps_hi + s_add_u32 s_restore_ttmps_lo, s_restore_ttmps_lo, get_sgpr_size_bytes() + s_add_u32 s_restore_ttmps_lo, s_restore_ttmps_lo, s_restore_buf_rsrc0 + s_addc_u32 s_restore_ttmps_hi, s_restore_buf_rsrc1, 0x0 + s_and_b32 s_restore_ttmps_hi, s_restore_ttmps_hi, 0xFFFF + s_load_dwordx4 [ttmp4, ttmp5, ttmp6, ttmp7], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x50 scope:SCOPE_SYS + s_load_dwordx4 [ttmp8, ttmp9, ttmp10, ttmp11], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x60 scope:SCOPE_SYS + s_load_dword ttmp13, [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x74 scope:SCOPE_SYS + s_wait_idle + + s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff //pc[47:32] //Do it here in order not to affect STATUS + s_and_b64 exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32 + s_and_b64 vcc, vcc, vcc // Restore STATUS.VCCZ, not writable by s_setreg_b32 + + s_setreg_b32 hwreg(HW_REG_WAVE_STATE_PRIV), s_restore_state_priv // SCC is included, which is changed by previous salu + + // Make barrier and LDS state visible to all waves in the group. + // STATE_PRIV.BARRIER_COMPLETE may change after this point. + s_barrier_signal -2 + s_barrier_wait -2 + + s_rfe_b64 s_restore_pc_lo //Return to the main shader program and resume execution + +L_END_PGM: + s_endpgm_saved +end + +function write_hwreg_to_v2(s) + // Copy into VGPR for later TCP store. + v_writelane_b32 v2, s, m0 + s_add_u32 m0, m0, 0x1 +end + + +function write_16sgpr_to_v2(s) + // Copy into VGPR for later TCP store. + for var sgpr_idx = 0; sgpr_idx < 16; sgpr_idx ++ + v_writelane_b32 v2, s[sgpr_idx], ttmp13 + s_add_u32 ttmp13, ttmp13, 0x1 + end +end + +function write_12sgpr_to_v2(s) + // Copy into VGPR for later TCP store. + for var sgpr_idx = 0; sgpr_idx < 12; sgpr_idx ++ + v_writelane_b32 v2, s[sgpr_idx], ttmp13 + s_add_u32 ttmp13, ttmp13, 0x1 + end +end + +function read_hwreg_from_mem(s, s_rsrc, s_mem_offset) + s_buffer_load_dword s, s_rsrc, s_mem_offset scope:SCOPE_SYS + s_add_u32 s_mem_offset, s_mem_offset, 4 +end + +function read_16sgpr_from_mem(s, s_rsrc, s_mem_offset) + s_sub_u32 s_mem_offset, s_mem_offset, 4*16 + s_buffer_load_dwordx16 s, s_rsrc, s_mem_offset scope:SCOPE_SYS +end + +function read_8sgpr_from_mem(s, s_rsrc, s_mem_offset) + s_sub_u32 s_mem_offset, s_mem_offset, 4*8 + s_buffer_load_dwordx8 s, s_rsrc, s_mem_offset scope:SCOPE_SYS +end + +function read_4sgpr_from_mem(s, s_rsrc, s_mem_offset) + s_sub_u32 s_mem_offset, s_mem_offset, 4*4 + s_buffer_load_dwordx4 s, s_rsrc, s_mem_offset scope:SCOPE_SYS +end + +function get_vgpr_size_bytes(s_vgpr_size_byte, s_size) + s_getreg_b32 s_vgpr_size_byte, hwreg(HW_REG_WAVE_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE) + s_add_u32 s_vgpr_size_byte, s_vgpr_size_byte, 1 + s_bitcmp1_b32 s_size, S_WAVE_SIZE + s_cbranch_scc1 L_ENABLE_SHIFT_W64 + s_lshl_b32 s_vgpr_size_byte, s_vgpr_size_byte, (2+7) //Number of VGPRs = (vgpr_size + 1) * 4 * 32 * 4 (non-zero value) + s_branch L_SHIFT_DONE +L_ENABLE_SHIFT_W64: + s_lshl_b32 s_vgpr_size_byte, s_vgpr_size_byte, (2+8) //Number of VGPRs = (vgpr_size + 1) * 4 * 64 * 4 (non-zero value) +L_SHIFT_DONE: +end + +function get_svgpr_size_bytes(s_svgpr_size_byte) + s_getreg_b32 s_svgpr_size_byte, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SIZE) + s_lshl_b32 s_svgpr_size_byte, s_svgpr_size_byte, (3+7) +end + +function get_sgpr_size_bytes + return 512 +end + +function get_hwreg_size_bytes + return 128 +end + +function get_wave_size2(s_reg) + s_getreg_b32 s_reg, hwreg(HW_REG_WAVE_STATUS,SQ_WAVE_STATUS_WAVE64_SHIFT,SQ_WAVE_STATUS_WAVE64_SIZE) + s_lshl_b32 s_reg, s_reg, S_WAVE_SIZE +end diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm index 0eabb7a8cab9..6869e07a2fff 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm @@ -447,7 +447,9 @@ L_SAVE: s_getreg_b32 s_save_m0, hwreg(HW_REG_MODE) //MODE write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset) - + // Clear VSKIP state now that MODE.VSKIP has been saved. + // If user shader set it then vector instructions would be skipped. + s_setvskip 0,0 /* the first wave in the threadgroup */ s_and_b32 s_save_tmp, s_save_spi_init_hi, S_SAVE_SPI_INIT_FIRST_WAVE_MASK // extract fisrt wave bit diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c index 312dfa84f29f..a8abc3091801 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c @@ -350,10 +350,27 @@ int kfd_dbg_set_mes_debug_mode(struct kfd_process_device *pdd, bool sq_trap_en) { uint32_t spi_dbg_cntl = pdd->spi_dbg_override | pdd->spi_dbg_launch_mode; uint32_t flags = pdd->process->dbg_flags; + struct amdgpu_device *adev = pdd->dev->adev; + int r; if (!kfd_dbg_is_per_vmid_supported(pdd->dev)) return 0; + if (!pdd->proc_ctx_cpu_ptr) { + r = amdgpu_amdkfd_alloc_gtt_mem(adev, + AMDGPU_MES_PROC_CTX_SIZE, + &pdd->proc_ctx_bo, + &pdd->proc_ctx_gpu_addr, + &pdd->proc_ctx_cpu_ptr, + false); + if (r) { + dev_err(adev->dev, + "failed to allocate process context bo\n"); + return r; + } + memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); + } + return amdgpu_mes_set_shader_debugger(pdd->dev->adev, pdd->proc_ctx_gpu_addr, spi_dbg_cntl, pdd->watch_points, flags, sq_trap_en); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 1405e8affd48..d4593374e7a1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -2325,9 +2325,9 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, */ mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ]; if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd)) { + while (halt_if_hws_hang) + schedule(); if (reset_queues_on_hws_hang(dqm)) { - while (halt_if_hws_hang) - schedule(); dqm->is_hws_hang = true; kfd_hws_hang(dqm); retval = -ETIME; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 4b275937d05e..d05d199b5e44 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -278,10 +278,11 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, struct migrate_vma *migrate, struct dma_fence **mfence, dma_addr_t *scratch, uint64_t ttm_res_offset) { - uint64_t npages = migrate->cpages; + uint64_t npages = migrate->npages; struct amdgpu_device *adev = node->adev; struct device *dev = adev->dev; struct amdgpu_res_cursor cursor; + uint64_t mpages = 0; dma_addr_t *src; uint64_t *dst; uint64_t i, j; @@ -295,14 +296,16 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, amdgpu_res_first(prange->ttm_res, ttm_res_offset, npages << PAGE_SHIFT, &cursor); - for (i = j = 0; i < npages; i++) { + for (i = j = 0; (i < npages) && (mpages < migrate->cpages); i++) { struct page *spage; - dst[i] = cursor.start + (j << PAGE_SHIFT); - migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]); - svm_migrate_get_vram_page(prange, migrate->dst[i]); - migrate->dst[i] = migrate_pfn(migrate->dst[i]); - + if (migrate->src[i] & MIGRATE_PFN_MIGRATE) { + dst[i] = cursor.start + (j << PAGE_SHIFT); + migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]); + svm_migrate_get_vram_page(prange, migrate->dst[i]); + migrate->dst[i] = migrate_pfn(migrate->dst[i]); + mpages++; + } spage = migrate_pfn_to_page(migrate->src[i]); if (spage && !is_zone_device_page(spage)) { src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE, @@ -353,9 +356,12 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, out_free_vram_pages: if (r) { pr_debug("failed %d to copy memory to vram\n", r); - while (i--) { + for (i = 0; i < npages && mpages; i++) { + if (!dst[i]) + continue; svm_migrate_put_vram_page(adev, dst[i]); migrate->dst[i] = 0; + mpages--; } } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index c32b255c0eb2..d8cd913aa772 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 0976b5b0e8e8..083f83c94531 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1160,7 +1160,8 @@ static void kfd_process_wq_release(struct work_struct *work) */ synchronize_rcu(); ef = rcu_access_pointer(p->ef); - dma_fence_signal(ef); + if (ef) + dma_fence_signal(ef); kfd_process_remove_sysfs(p); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 9df56f8e09f9..bcddd989c7f3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -86,9 +86,12 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd) if (pdd->already_dequeued) return; - + /* The MES context flush needs to filter out the case which the + * KFD process is created without setting up the MES context and + * queue for creating a compute queue. + */ dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd); - if (dev->kfd->shared_resources.enable_mes && + if (dev->kfd->shared_resources.enable_mes && !!pdd->proc_ctx_gpu_addr && down_read_trylock(&dev->adev->reset_domain->sem)) { amdgpu_mes_flush_shader_debugger(dev->adev, pdd->proc_ctx_gpu_addr); diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 11e3f2f3b174..abd3b6564373 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -8,6 +8,8 @@ config DRM_AMD_DC bool "AMD DC - Enable new display engine" default y depends on BROKEN || !CC_IS_CLANG || ARM64 || LOONGARCH || RISCV || SPARC64 || X86_64 + select CEC_CORE + select CEC_NOTIFIER select SND_HDA_COMPONENT if SND_HDA_CORE # !CC_IS_CLANG: https://github.com/ClangBuiltLinux/linux/issues/1752 select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && !(CC_IS_CLANG && (ARM64 || LOONGARCH || RISCV)) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b631b2eba0f0..ac3fd81fecef 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -98,6 +98,7 @@ #include #include +#include #include #include "ivsrcid/dcn/irqsrcs_dcn_1_0.h" @@ -2033,6 +2034,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (amdgpu_dc_debug_mask & DC_FORCE_SUBVP_MCLK_SWITCH) adev->dm.dc->debug.force_subvp_mclk_switch = true; + if (amdgpu_dc_debug_mask & DC_DISABLE_SUBVP) + adev->dm.dc->debug.force_disable_subvp = true; + if (amdgpu_dc_debug_mask & DC_ENABLE_DML2) { adev->dm.dc->debug.using_dml2 = true; adev->dm.dc->debug.using_dml21 = true; @@ -2158,6 +2162,10 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) amdgpu_dm_crtc_secure_display_create_contexts(adev); if (!adev->dm.secure_display_ctx.crtc_ctx) DRM_ERROR("amdgpu: failed to initialize secure display contexts.\n"); + + if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(4, 0, 1)) + adev->dm.secure_display_ctx.support_mul_roi = true; + #endif DRM_DEBUG_DRIVER("KMS initialized.\n"); @@ -2750,6 +2758,48 @@ out_fail: mutex_unlock(&mgr->lock); } +void hdmi_cec_unset_edid(struct amdgpu_dm_connector *aconnector) +{ + struct cec_notifier *n = aconnector->notifier; + + if (!n) + return; + + cec_notifier_phys_addr_invalidate(n); +} + +void hdmi_cec_set_edid(struct amdgpu_dm_connector *aconnector) +{ + struct drm_connector *connector = &aconnector->base; + struct cec_notifier *n = aconnector->notifier; + + if (!n) + return; + + cec_notifier_set_phys_addr(n, + connector->display_info.source_physical_address); +} + +static void s3_handle_hdmi_cec(struct drm_device *ddev, bool suspend) +{ + struct amdgpu_dm_connector *aconnector; + struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; + + drm_connector_list_iter_begin(ddev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { + if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) + continue; + + aconnector = to_amdgpu_dm_connector(connector); + if (suspend) + hdmi_cec_unset_edid(aconnector); + else + hdmi_cec_set_edid(aconnector); + } + drm_connector_list_iter_end(&conn_iter); +} + static void s3_handle_mst(struct drm_device *dev, bool suspend) { struct amdgpu_dm_connector *aconnector; @@ -3021,6 +3071,8 @@ static int dm_suspend(struct amdgpu_ip_block *ip_block) if (IS_ERR(adev->dm.cached_state)) return PTR_ERR(adev->dm.cached_state); + s3_handle_hdmi_cec(adev_to_drm(adev), true); + s3_handle_mst(adev_to_drm(adev), true); amdgpu_dm_irq_suspend(adev); @@ -3293,6 +3345,8 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) */ amdgpu_dm_irq_resume_early(adev); + s3_handle_hdmi_cec(ddev, false); + /* On resume we need to rewrite the MSTM control bits to enable MST*/ s3_handle_mst(ddev, false); @@ -3607,6 +3661,7 @@ void amdgpu_dm_update_connector_after_detect( dc_sink_retain(aconnector->dc_sink); if (sink->dc_edid.length == 0) { aconnector->drm_edid = NULL; + hdmi_cec_unset_edid(aconnector); if (aconnector->dc_link->aux_mode) { drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux); } @@ -3616,6 +3671,7 @@ void amdgpu_dm_update_connector_after_detect( aconnector->drm_edid = drm_edid_alloc(edid, sink->dc_edid.length); drm_edid_connector_update(connector, aconnector->drm_edid); + hdmi_cec_set_edid(aconnector); if (aconnector->dc_link->aux_mode) drm_dp_cec_attach(&aconnector->dm_dp_aux.aux, connector->display_info.source_physical_address); @@ -3632,6 +3688,7 @@ void amdgpu_dm_update_connector_after_detect( amdgpu_dm_update_freesync_caps(connector, aconnector->drm_edid); update_connector_ext_caps(aconnector); } else { + hdmi_cec_unset_edid(aconnector); drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux); amdgpu_dm_update_freesync_caps(connector, NULL); aconnector->num_modes = 0; @@ -7048,6 +7105,7 @@ static void amdgpu_dm_connector_unregister(struct drm_connector *connector) if (amdgpu_dm_should_create_sysfs(amdgpu_dm_connector)) sysfs_remove_group(&connector->kdev->kobj, &amdgpu_group); + cec_notifier_conn_unregister(amdgpu_dm_connector->notifier); drm_dp_aux_unregister(&amdgpu_dm_connector->dm_dp_aux.aux); } @@ -8284,6 +8342,27 @@ create_i2c(struct ddc_service *ddc_service, return i2c; } +int amdgpu_dm_initialize_hdmi_connector(struct amdgpu_dm_connector *aconnector) +{ + struct cec_connector_info conn_info; + struct drm_device *ddev = aconnector->base.dev; + struct device *hdmi_dev = ddev->dev; + + if (amdgpu_dc_debug_mask & DC_DISABLE_HDMI_CEC) { + drm_info(ddev, "HDMI-CEC feature masked\n"); + return -EINVAL; + } + + cec_fill_conn_info_from_drm(&conn_info, &aconnector->base); + aconnector->notifier = + cec_notifier_conn_register(hdmi_dev, NULL, &conn_info); + if (!aconnector->notifier) { + drm_err(ddev, "Failed to create cec notifier\n"); + return -ENOMEM; + } + + return 0; +} /* * Note: this function assumes that dc_link_detect() was called for the @@ -8347,6 +8426,10 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm, drm_connector_attach_encoder( &aconnector->base, &aencoder->base); + if (connector_type == DRM_MODE_CONNECTOR_HDMIA || + connector_type == DRM_MODE_CONNECTOR_HDMIB) + amdgpu_dm_initialize_hdmi_connector(aconnector); + if (connector_type == DRM_MODE_CONNECTOR_DisplayPort || connector_type == DRM_MODE_CONNECTOR_eDP) amdgpu_dm_initialize_dp_connector(dm, aconnector, link->link_index); @@ -8406,16 +8489,6 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, struct amdgpu_crtc *acrtc, struct dm_crtc_state *acrtc_state) { - /* - * We have no guarantee that the frontend index maps to the same - * backend index - some even map to more than one. - * - * TODO: Use a different interrupt or check DC itself for the mapping. - */ - int irq_type = - amdgpu_display_crtc_idx_to_irq_type( - adev, - acrtc->crtc_id); struct drm_vblank_crtc_config config = {0}; struct dc_crtc_timing *timing; int offdelay; @@ -8441,28 +8514,7 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, drm_crtc_vblank_on_config(&acrtc->base, &config); - - amdgpu_irq_get( - adev, - &adev->pageflip_irq, - irq_type); -#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) - amdgpu_irq_get( - adev, - &adev->vline0_irq, - irq_type); -#endif } else { -#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) - amdgpu_irq_put( - adev, - &adev->vline0_irq, - irq_type); -#endif - amdgpu_irq_put( - adev, - &adev->pageflip_irq, - irq_type); drm_crtc_vblank_off(&acrtc->base); } } @@ -8933,6 +8985,7 @@ static void amdgpu_dm_enable_self_refresh(struct amdgpu_crtc *acrtc_attach, struct replay_settings *pr = &acrtc_state->stream->link->replay_settings; struct amdgpu_dm_connector *aconn = (struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context; + bool vrr_active = amdgpu_dm_crtc_vrr_active(acrtc_state); if (acrtc_state->update_type > UPDATE_TYPE_FAST) { if (pr->config.replay_supported && !pr->replay_feature_enabled) @@ -8959,14 +9012,15 @@ static void amdgpu_dm_enable_self_refresh(struct amdgpu_crtc *acrtc_attach, * adequate number of fast atomic commits to notify KMD * of update events. See `vblank_control_worker()`. */ - if (acrtc_attach->dm_irq_params.allow_sr_entry && + if (!vrr_active && + acrtc_attach->dm_irq_params.allow_sr_entry && #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) && #endif (current_ts - psr->psr_dirty_rects_change_timestamp_ns) > 500000000) { if (pr->replay_feature_enabled && !pr->replay_allow_active) amdgpu_dm_replay_enable(acrtc_state->stream, true); - if (psr->psr_version >= DC_PSR_VERSION_SU_1 && + if (psr->psr_version == DC_PSR_VERSION_SU_1 && !psr->psr_allow_active && !aconn->disallow_edp_enter_psr) amdgpu_dm_psr_enable(acrtc_state->stream); } @@ -9137,7 +9191,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, acrtc_state->stream->link->psr_settings.psr_dirty_rects_change_timestamp_ns = timestamp_ns; if (acrtc_state->stream->link->psr_settings.psr_allow_active) - amdgpu_dm_psr_disable(acrtc_state->stream); + amdgpu_dm_psr_disable(acrtc_state->stream, true); mutex_unlock(&dm->dc_lock); } } @@ -9303,11 +9357,11 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->stream_update.abm_level = &acrtc_state->abm_level; mutex_lock(&dm->dc_lock); - if (acrtc_state->update_type > UPDATE_TYPE_FAST) { + if ((acrtc_state->update_type > UPDATE_TYPE_FAST) || vrr_active) { if (acrtc_state->stream->link->replay_settings.replay_allow_active) amdgpu_dm_replay_disable(acrtc_state->stream); if (acrtc_state->stream->link->psr_settings.psr_allow_active) - amdgpu_dm_psr_disable(acrtc_state->stream); + amdgpu_dm_psr_disable(acrtc_state->stream, true); } mutex_unlock(&dm->dc_lock); @@ -10066,14 +10120,19 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) if (amdgpu_dm_is_valid_crc_source(cur_crc_src)) { #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) if (amdgpu_dm_crc_window_is_activated(crtc)) { + uint8_t cnt; spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); - acrtc->dm_irq_params.window_param.update_win = true; + for (cnt = 0; cnt < MAX_CRC_WINDOW_NUM; cnt++) { + if (acrtc->dm_irq_params.window_param[cnt].enable) { + acrtc->dm_irq_params.window_param[cnt].update_win = true; - /** - * It takes 2 frames for HW to stably generate CRC when - * resuming from suspend, so we set skip_frame_cnt 2. - */ - acrtc->dm_irq_params.window_param.skip_frame_cnt = 2; + /** + * It takes 2 frames for HW to stably generate CRC when + * resuming from suspend, so we set skip_frame_cnt 2. + */ + acrtc->dm_irq_params.window_param[cnt].skip_frame_cnt = 2; + } + } spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); } #endif @@ -11161,8 +11220,8 @@ dm_get_plane_scale(struct drm_plane_state *plane_state, int plane_src_w, plane_src_h; dm_get_oriented_plane_size(plane_state, &plane_src_w, &plane_src_h); - *out_plane_scale_w = plane_state->crtc_w * 1000 / plane_src_w; - *out_plane_scale_h = plane_state->crtc_h * 1000 / plane_src_h; + *out_plane_scale_w = plane_src_w ? plane_state->crtc_w * 1000 / plane_src_w : 0; + *out_plane_scale_h = plane_src_h ? plane_state->crtc_h * 1000 / plane_src_h : 0; } /* @@ -11416,6 +11475,30 @@ static int dm_crtc_get_cursor_mode(struct amdgpu_device *adev, return 0; } +static bool amdgpu_dm_crtc_mem_type_changed(struct drm_device *dev, + struct drm_atomic_state *state, + struct drm_crtc_state *crtc_state) +{ + struct drm_plane *plane; + struct drm_plane_state *new_plane_state, *old_plane_state; + + drm_for_each_plane_mask(plane, dev, crtc_state->plane_mask) { + new_plane_state = drm_atomic_get_plane_state(state, plane); + old_plane_state = drm_atomic_get_plane_state(state, plane); + + if (IS_ERR(new_plane_state) || IS_ERR(old_plane_state)) { + DRM_ERROR("Failed to get plane state for plane %s\n", plane->name); + return false; + } + + if (old_plane_state->fb && new_plane_state->fb && + get_mem_type(old_plane_state->fb) != get_mem_type(new_plane_state->fb)) + return true; + } + + return false; +} + /** * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM. * @@ -11613,10 +11696,6 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, /* Remove exiting planes if they are modified */ for_each_oldnew_plane_in_descending_zpos(state, plane, old_plane_state, new_plane_state) { - if (old_plane_state->fb && new_plane_state->fb && - get_mem_type(old_plane_state->fb) != - get_mem_type(new_plane_state->fb)) - lock_and_validation_needed = true; ret = dm_update_plane_state(dc, state, plane, old_plane_state, @@ -11911,9 +11990,11 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, /* * Only allow async flips for fast updates that don't change - * the FB pitch, the DCC state, rotation, etc. + * the FB pitch, the DCC state, rotation, mem_type, etc. */ - if (new_crtc_state->async_flip && lock_and_validation_needed) { + if (new_crtc_state->async_flip && + (lock_and_validation_needed || + amdgpu_dm_crtc_mem_type_changed(dev, state, new_crtc_state))) { drm_dbg_atomic(crtc->dev, "[CRTC:%d:%s] async flips are only supported for fast updates\n", crtc->base.id, crtc->name); @@ -12245,10 +12326,14 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector, if (edid && (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT || sink->sink_signal == SIGNAL_TYPE_EDP)) { - amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq; - amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq; - if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10) - freesync_capable = true; + if (amdgpu_dm_connector->dc_link && + amdgpu_dm_connector->dc_link->dpcd_caps.allow_invalid_MSA_timing_param) { + amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq; + amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq; + if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10) + freesync_capable = true; + } + parse_amd_vsdb(amdgpu_dm_connector, edid, &vsdb_info); if (vsdb_info.replay_mode) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index e46e1365fe91..d2703ca7dff3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -671,6 +671,8 @@ struct amdgpu_dm_connector { uint32_t connector_id; int bl_idx; + struct cec_notifier *notifier; + /* we need to mind the EDID between detect and get modes due to analog/digital/tvencoder */ const struct drm_edid *drm_edid; @@ -697,6 +699,8 @@ struct amdgpu_dm_connector { struct drm_dp_mst_port *mst_output_port; struct amdgpu_dm_connector *mst_root; struct drm_dp_aux *dsc_aux; + uint32_t mst_local_bw; + uint16_t vc_full_pbn; struct mutex handle_mst_msg_ready; /* TODO see if we can merge with ddc_bus or make a dm_connector */ @@ -1010,4 +1014,8 @@ void dm_free_gpu_mem(struct amdgpu_device *adev, bool amdgpu_dm_is_headless(struct amdgpu_device *adev); +void hdmi_cec_set_edid(struct amdgpu_dm_connector *aconnector); +void hdmi_cec_unset_edid(struct amdgpu_dm_connector *aconnector); +int amdgpu_dm_initialize_hdmi_connector(struct amdgpu_dm_connector *aconnector); + #endif /* __AMDGPU_DM_H__ */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c index 6fdc306a4a86..033bd817d871 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c @@ -30,6 +30,7 @@ #include "amdgpu_dm.h" #include "dc.h" #include "amdgpu_securedisplay.h" +#include "amdgpu_dm_psr.h" static const char *const pipe_crc_sources[] = { "none", @@ -295,33 +296,41 @@ static void amdgpu_dm_set_crc_window_default(struct drm_crtc *crtc, struct dc_st struct drm_device *drm_dev = crtc->dev; struct amdgpu_display_manager *dm = &drm_to_adev(drm_dev)->dm; struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); - bool was_activated; struct amdgpu_dm_connector *aconnector; + bool was_activated; uint8_t phy_id; + unsigned long flags; + int i; - spin_lock_irq(&drm_dev->event_lock); - was_activated = acrtc->dm_irq_params.window_param.activated; - acrtc->dm_irq_params.window_param.x_start = 0; - acrtc->dm_irq_params.window_param.y_start = 0; - acrtc->dm_irq_params.window_param.x_end = 0; - acrtc->dm_irq_params.window_param.y_end = 0; - acrtc->dm_irq_params.window_param.activated = false; - acrtc->dm_irq_params.window_param.update_win = false; - acrtc->dm_irq_params.window_param.skip_frame_cnt = 0; - spin_unlock_irq(&drm_dev->event_lock); + spin_lock_irqsave(&drm_dev->event_lock, flags); + was_activated = acrtc->dm_irq_params.crc_window_activated; + for (i = 0; i < MAX_CRC_WINDOW_NUM; i++) { + acrtc->dm_irq_params.window_param[i].x_start = 0; + acrtc->dm_irq_params.window_param[i].y_start = 0; + acrtc->dm_irq_params.window_param[i].x_end = 0; + acrtc->dm_irq_params.window_param[i].y_end = 0; + acrtc->dm_irq_params.window_param[i].enable = false; + acrtc->dm_irq_params.window_param[i].update_win = false; + acrtc->dm_irq_params.window_param[i].skip_frame_cnt = 0; + } + acrtc->dm_irq_params.crc_window_activated = false; + spin_unlock_irqrestore(&drm_dev->event_lock, flags); /* Disable secure_display if it was enabled */ - if (was_activated) { + if (was_activated && dm->secure_display_ctx.op_mode == LEGACY_MODE) { /* stop ROI update on this crtc */ flush_work(&dm->secure_display_ctx.crtc_ctx[crtc->index].notify_ta_work); flush_work(&dm->secure_display_ctx.crtc_ctx[crtc->index].forward_roi_work); - aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; - if (aconnector && get_phy_id(dm, aconnector, &phy_id)) - dc_stream_forward_crc_window(stream, NULL, phy_id, true); - else + if (aconnector && get_phy_id(dm, aconnector, &phy_id)) { + if (dm->secure_display_ctx.support_mul_roi) + dc_stream_forward_multiple_crc_window(stream, NULL, phy_id, true); + else + dc_stream_forward_crc_window(stream, NULL, phy_id, true); + } else { DRM_DEBUG_DRIVER("%s Can't find matching phy id", __func__); + } } } @@ -335,7 +344,11 @@ static void amdgpu_dm_crtc_notify_ta_to_read(struct work_struct *work) struct amdgpu_dm_connector *aconnector; uint8_t phy_inst; struct amdgpu_display_manager *dm; + struct crc_data crc_cpy[MAX_CRC_WINDOW_NUM]; + unsigned long flags; + uint8_t roi_idx = 0; int ret; + int i; crtc_ctx = container_of(work, struct secure_display_crtc_context, notify_ta_work); crtc = crtc_ctx->crtc; @@ -364,18 +377,36 @@ static void amdgpu_dm_crtc_notify_ta_to_read(struct work_struct *work) } mutex_unlock(&crtc->dev->mode_config.mutex); + spin_lock_irqsave(&crtc->dev->event_lock, flags); + memcpy(crc_cpy, crtc_ctx->crc_info.crc, sizeof(struct crc_data) * MAX_CRC_WINDOW_NUM); + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + /* need lock for multiple crtcs to use the command buffer */ mutex_lock(&psp->securedisplay_context.mutex); - - psp_prep_securedisplay_cmd_buf(psp, &securedisplay_cmd, - TA_SECUREDISPLAY_COMMAND__SEND_ROI_CRC); - - securedisplay_cmd->securedisplay_in_message.send_roi_crc.phy_id = phy_inst; - /* PSP TA is expected to finish data transmission over I2C within current frame, * even there are up to 4 crtcs request to send in this frame. */ - ret = psp_securedisplay_invoke(psp, TA_SECUREDISPLAY_COMMAND__SEND_ROI_CRC); + if (dm->secure_display_ctx.support_mul_roi) { + psp_prep_securedisplay_cmd_buf(psp, &securedisplay_cmd, + TA_SECUREDISPLAY_COMMAND__SEND_ROI_CRC_V2); + + securedisplay_cmd->securedisplay_in_message.send_roi_crc_v2.phy_id = phy_inst; + + for (i = 0; i < MAX_CRC_WINDOW_NUM; i++) { + if (crc_cpy[i].crc_ready) + roi_idx |= 1 << i; + } + securedisplay_cmd->securedisplay_in_message.send_roi_crc_v2.roi_idx = roi_idx; + + ret = psp_securedisplay_invoke(psp, TA_SECUREDISPLAY_COMMAND__SEND_ROI_CRC_V2); + } else { + psp_prep_securedisplay_cmd_buf(psp, &securedisplay_cmd, + TA_SECUREDISPLAY_COMMAND__SEND_ROI_CRC); + + securedisplay_cmd->securedisplay_in_message.send_roi_crc.phy_id = phy_inst; + + ret = psp_securedisplay_invoke(psp, TA_SECUREDISPLAY_COMMAND__SEND_ROI_CRC); + } if (!ret) { if (securedisplay_cmd->status != TA_SECUREDISPLAY_STATUS__SUCCESS) @@ -393,6 +424,8 @@ amdgpu_dm_forward_crc_window(struct work_struct *work) struct drm_crtc *crtc; struct dc_stream_state *stream; struct amdgpu_dm_connector *aconnector; + struct crc_window roi_cpy[MAX_CRC_WINDOW_NUM]; + unsigned long flags; uint8_t phy_id; crtc_ctx = container_of(work, struct secure_display_crtc_context, forward_roi_work); @@ -416,9 +449,17 @@ amdgpu_dm_forward_crc_window(struct work_struct *work) } mutex_unlock(&crtc->dev->mode_config.mutex); + spin_lock_irqsave(&crtc->dev->event_lock, flags); + memcpy(roi_cpy, crtc_ctx->roi, sizeof(struct crc_window) * MAX_CRC_WINDOW_NUM); + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + mutex_lock(&dm->dc_lock); - dc_stream_forward_crc_window(stream, &crtc_ctx->rect, - phy_id, false); + if (dm->secure_display_ctx.support_mul_roi) + dc_stream_forward_multiple_crc_window(stream, roi_cpy, + phy_id, false); + else + dc_stream_forward_crc_window(stream, &roi_cpy[0].rect, + phy_id, false); mutex_unlock(&dm->dc_lock); } @@ -429,7 +470,7 @@ bool amdgpu_dm_crc_window_is_activated(struct drm_crtc *crtc) bool ret = false; spin_lock_irq(&drm_dev->event_lock); - ret = acrtc->dm_irq_params.window_param.activated; + ret = acrtc->dm_irq_params.crc_window_activated; spin_unlock_irq(&drm_dev->event_lock); return ret; @@ -467,10 +508,14 @@ int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc, mutex_lock(&adev->dm.dc_lock); + /* For PSR1, check that the panel has exited PSR */ + if (stream_state->link->psr_settings.psr_version < DC_PSR_VERSION_SU_1) + amdgpu_dm_psr_wait_disable(stream_state); + /* Enable or disable CRTC CRC generation */ if (dm_is_crc_source_crtc(source) || source == AMDGPU_DM_PIPE_CRC_SOURCE_NONE) { if (!dc_stream_configure_crc(stream_state->ctx->dc, - stream_state, NULL, enable, enable)) { + stream_state, NULL, enable, enable, 0, true)) { ret = -EINVAL; goto unlock; } @@ -604,6 +649,17 @@ int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name) } + /* + * Reading the CRC requires the vblank interrupt handler to be + * enabled. Keep a reference until CRC capture stops. + */ + enabled = amdgpu_dm_is_valid_crc_source(cur_crc_src); + if (!enabled && enable) { + ret = drm_crtc_vblank_get(crtc); + if (ret) + goto cleanup; + } + #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) /* Reset secure_display when we change crc source from debugfs */ amdgpu_dm_set_crc_window_default(crtc, crtc_state->stream); @@ -614,16 +670,7 @@ int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name) goto cleanup; } - /* - * Reading the CRC requires the vblank interrupt handler to be - * enabled. Keep a reference until CRC capture stops. - */ - enabled = amdgpu_dm_is_valid_crc_source(cur_crc_src); if (!enabled && enable) { - ret = drm_crtc_vblank_get(crtc); - if (ret) - goto cleanup; - if (dm_is_crc_source_dprx(source)) { if (drm_dp_start_crc(aux, crtc)) { DRM_DEBUG_DRIVER("dp start crc failed\n"); @@ -651,7 +698,8 @@ int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name) #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) /* Initialize phy id mapping table for secure display*/ - if (!dm->secure_display_ctx.phy_mapping_updated) + if (dm->secure_display_ctx.op_mode == LEGACY_MODE && + !dm->secure_display_ctx.phy_mapping_updated) update_phy_id_mapping(adev); #endif @@ -709,7 +757,7 @@ void amdgpu_dm_crtc_handle_crc_irq(struct drm_crtc *crtc) } if (dm_is_crc_source_crtc(cur_crc_src)) { - if (!dc_stream_get_crc(stream_state->ctx->dc, stream_state, + if (!dc_stream_get_crc(stream_state->ctx->dc, stream_state, 0, &crcs[0], &crcs[1], &crcs[2])) return; @@ -726,7 +774,16 @@ void amdgpu_dm_crtc_handle_crc_window_irq(struct drm_crtc *crtc) struct amdgpu_crtc *acrtc = NULL; struct amdgpu_device *adev = NULL; struct secure_display_crtc_context *crtc_ctx = NULL; + bool reset_crc_frame_count[MAX_CRC_WINDOW_NUM] = {false}; + uint32_t crc_r[MAX_CRC_WINDOW_NUM] = {0}; + uint32_t crc_g[MAX_CRC_WINDOW_NUM] = {0}; + uint32_t crc_b[MAX_CRC_WINDOW_NUM] = {0}; unsigned long flags1; + bool forward_roi_change = false; + bool notify_ta = false; + bool all_crc_ready = true; + struct dc_stream_state *stream_state; + int i; if (crtc == NULL) return; @@ -734,21 +791,21 @@ void amdgpu_dm_crtc_handle_crc_window_irq(struct drm_crtc *crtc) acrtc = to_amdgpu_crtc(crtc); adev = drm_to_adev(crtc->dev); drm_dev = crtc->dev; + stream_state = to_dm_crtc_state(crtc->state)->stream; spin_lock_irqsave(&drm_dev->event_lock, flags1); cur_crc_src = acrtc->dm_irq_params.crc_src; /* Early return if CRC capture is not enabled. */ if (!amdgpu_dm_is_valid_crc_source(cur_crc_src) || - !dm_is_crc_source_crtc(cur_crc_src)) - goto cleanup; + !dm_is_crc_source_crtc(cur_crc_src)) { + spin_unlock_irqrestore(&drm_dev->event_lock, flags1); + return; + } - if (!acrtc->dm_irq_params.window_param.activated) - goto cleanup; - - if (acrtc->dm_irq_params.window_param.skip_frame_cnt) { - acrtc->dm_irq_params.window_param.skip_frame_cnt -= 1; - goto cleanup; + if (!acrtc->dm_irq_params.crc_window_activated) { + spin_unlock_irqrestore(&drm_dev->event_lock, flags1); + return; } crtc_ctx = &adev->dm.secure_display_ctx.crtc_ctx[acrtc->crtc_id]; @@ -759,32 +816,110 @@ void amdgpu_dm_crtc_handle_crc_window_irq(struct drm_crtc *crtc) crtc_ctx->crtc = crtc; } - if (acrtc->dm_irq_params.window_param.update_win) { - /* prepare work for dmub to update ROI */ - crtc_ctx->rect.x = acrtc->dm_irq_params.window_param.x_start; - crtc_ctx->rect.y = acrtc->dm_irq_params.window_param.y_start; - crtc_ctx->rect.width = acrtc->dm_irq_params.window_param.x_end - - acrtc->dm_irq_params.window_param.x_start; - crtc_ctx->rect.height = acrtc->dm_irq_params.window_param.y_end - - acrtc->dm_irq_params.window_param.y_start; - schedule_work(&crtc_ctx->forward_roi_work); + for (i = 0; i < MAX_CRC_WINDOW_NUM; i++) { + struct crc_params crc_window = { + .windowa_x_start = acrtc->dm_irq_params.window_param[i].x_start, + .windowa_y_start = acrtc->dm_irq_params.window_param[i].y_start, + .windowa_x_end = acrtc->dm_irq_params.window_param[i].x_end, + .windowa_y_end = acrtc->dm_irq_params.window_param[i].y_end, + .windowb_x_start = acrtc->dm_irq_params.window_param[i].x_start, + .windowb_y_start = acrtc->dm_irq_params.window_param[i].y_start, + .windowb_x_end = acrtc->dm_irq_params.window_param[i].x_end, + .windowb_y_end = acrtc->dm_irq_params.window_param[i].y_end, + }; - acrtc->dm_irq_params.window_param.update_win = false; + crtc_ctx->roi[i].enable = acrtc->dm_irq_params.window_param[i].enable; - /* Statically skip 1 frame, because we may need to wait below things - * before sending ROI to dmub: - * 1. We defer the work by using system workqueue. - * 2. We may need to wait for dc_lock before accessing dmub. - */ - acrtc->dm_irq_params.window_param.skip_frame_cnt = 1; + if (!acrtc->dm_irq_params.window_param[i].enable) { + crtc_ctx->crc_info.crc[i].crc_ready = false; + continue; + } - } else { - /* prepare work for psp to read ROI/CRC and send to I2C */ - schedule_work(&crtc_ctx->notify_ta_work); + if (acrtc->dm_irq_params.window_param[i].skip_frame_cnt) { + acrtc->dm_irq_params.window_param[i].skip_frame_cnt -= 1; + crtc_ctx->crc_info.crc[i].crc_ready = false; + continue; + } + + if (acrtc->dm_irq_params.window_param[i].update_win) { + crtc_ctx->roi[i].rect.x = crc_window.windowa_x_start; + crtc_ctx->roi[i].rect.y = crc_window.windowa_y_start; + crtc_ctx->roi[i].rect.width = crc_window.windowa_x_end - + crc_window.windowa_x_start; + crtc_ctx->roi[i].rect.height = crc_window.windowa_y_end - + crc_window.windowa_y_start; + + if (adev->dm.secure_display_ctx.op_mode == LEGACY_MODE) + /* forward task to dmub to update ROI */ + forward_roi_change = true; + else if (adev->dm.secure_display_ctx.op_mode == DISPLAY_CRC_MODE) + /* update ROI via dm*/ + dc_stream_configure_crc(stream_state->ctx->dc, stream_state, + &crc_window, true, true, i, false); + + reset_crc_frame_count[i] = true; + + acrtc->dm_irq_params.window_param[i].update_win = false; + + /* Statically skip 1 frame, because we may need to wait below things + * before sending ROI to dmub: + * 1. We defer the work by using system workqueue. + * 2. We may need to wait for dc_lock before accessing dmub. + */ + acrtc->dm_irq_params.window_param[i].skip_frame_cnt = 1; + crtc_ctx->crc_info.crc[i].crc_ready = false; + } else { + if (!dc_stream_get_crc(stream_state->ctx->dc, stream_state, i, + &crc_r[i], &crc_g[i], &crc_b[i])) + DRM_ERROR("Secure Display: fail to get crc from engine %d\n", i); + + if (adev->dm.secure_display_ctx.op_mode == LEGACY_MODE) + /* forward task to psp to read ROI/CRC and output via I2C */ + notify_ta = true; + else if (adev->dm.secure_display_ctx.op_mode == DISPLAY_CRC_MODE) + /* Avoid ROI window get changed, keep overwriting. */ + dc_stream_configure_crc(stream_state->ctx->dc, stream_state, + &crc_window, true, true, i, false); + + /* crc ready for psp to read out */ + crtc_ctx->crc_info.crc[i].crc_ready = true; + } } -cleanup: spin_unlock_irqrestore(&drm_dev->event_lock, flags1); + + if (forward_roi_change) + schedule_work(&crtc_ctx->forward_roi_work); + + if (notify_ta) + schedule_work(&crtc_ctx->notify_ta_work); + + spin_lock_irqsave(&crtc_ctx->crc_info.lock, flags1); + for (i = 0; i < MAX_CRC_WINDOW_NUM; i++) { + crtc_ctx->crc_info.crc[i].crc_R = crc_r[i]; + crtc_ctx->crc_info.crc[i].crc_G = crc_g[i]; + crtc_ctx->crc_info.crc[i].crc_B = crc_b[i]; + + if (!crtc_ctx->roi[i].enable) { + crtc_ctx->crc_info.crc[i].frame_count = 0; + continue; + } + + if (!crtc_ctx->crc_info.crc[i].crc_ready) + all_crc_ready = false; + + if (reset_crc_frame_count[i] || crtc_ctx->crc_info.crc[i].frame_count == UINT_MAX) + /* Reset the reference frame count after user update the ROI + * or it reaches the maximum value. + */ + crtc_ctx->crc_info.crc[i].frame_count = 0; + else + crtc_ctx->crc_info.crc[i].frame_count += 1; + } + spin_unlock_irqrestore(&crtc_ctx->crc_info.lock, flags1); + + if (all_crc_ready) + complete_all(&crtc_ctx->crc_info.completion); } void amdgpu_dm_crtc_secure_display_create_contexts(struct amdgpu_device *adev) @@ -805,9 +940,11 @@ void amdgpu_dm_crtc_secure_display_create_contexts(struct amdgpu_device *adev) INIT_WORK(&crtc_ctx[i].forward_roi_work, amdgpu_dm_forward_crc_window); INIT_WORK(&crtc_ctx[i].notify_ta_work, amdgpu_dm_crtc_notify_ta_to_read); crtc_ctx[i].crtc = &adev->mode_info.crtcs[i]->base; + spin_lock_init(&crtc_ctx[i].crc_info.lock); } adev->dm.secure_display_ctx.crtc_ctx = crtc_ctx; - return; + + adev->dm.secure_display_ctx.op_mode = DISPLAY_CRC_MODE; } #endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h index 4ec2510bc312..3da056c8d20b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h @@ -42,6 +42,14 @@ enum amdgpu_dm_pipe_crc_source { #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY #define MAX_CRTC 6 +enum secure_display_mode { + /* via dmub + psp */ + LEGACY_MODE = 0, + /* driver directly */ + DISPLAY_CRC_MODE, + SECURE_DISPLAY_MODE_MAX, +}; + struct phy_id_mapping { bool assigned; bool is_mst; @@ -51,13 +59,27 @@ struct phy_id_mapping { u8 rad[8]; }; +struct crc_data { + uint32_t crc_R; + uint32_t crc_G; + uint32_t crc_B; + uint32_t frame_count; + bool crc_ready; +}; + +struct crc_info { + struct crc_data crc[MAX_CRC_WINDOW_NUM]; + struct completion completion; + spinlock_t lock; +}; + struct crc_window_param { uint16_t x_start; uint16_t y_start; uint16_t x_end; uint16_t y_end; /* CRC window is activated or not*/ - bool activated; + bool enable; /* Update crc window during vertical blank or not */ bool update_win; /* skip reading/writing for few frames */ @@ -74,13 +96,17 @@ struct secure_display_crtc_context { struct drm_crtc *crtc; /* Region of Interest (ROI) */ - struct rect rect; + struct crc_window roi[MAX_CRC_WINDOW_NUM]; + + struct crc_info crc_info; }; struct secure_display_context { struct secure_display_crtc_context *crtc_ctx; - + /* Whether dmub support multiple ROI setting */ + bool support_mul_roi; + enum secure_display_mode op_mode; bool phy_mapping_updated; int phy_id_mapping_cnt; struct phy_id_mapping phy_id_mapping[MAX_CRTC]; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 64a041c2af05..36a830a7440f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -93,7 +93,7 @@ int amdgpu_dm_crtc_set_vupdate_irq(struct drm_crtc *crtc, bool enable) return rc; } -bool amdgpu_dm_crtc_vrr_active(struct dm_crtc_state *dm_state) +bool amdgpu_dm_crtc_vrr_active(const struct dm_crtc_state *dm_state) { return dm_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE || dm_state->freesync_config.state == VRR_STATE_ACTIVE_FIXED; @@ -142,7 +142,7 @@ static void amdgpu_dm_crtc_set_panel_sr_feature( amdgpu_dm_replay_enable(vblank_work->stream, true); } else if (vblank_enabled) { if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1 && is_sr_active) - amdgpu_dm_psr_disable(vblank_work->stream); + amdgpu_dm_psr_disable(vblank_work->stream, false); } else if (link->psr_settings.psr_feature_enabled && allow_sr_entry && !is_sr_active && !is_crc_window_active) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.h index 17e948753f59..c1212947a77b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.h @@ -37,7 +37,7 @@ int amdgpu_dm_crtc_set_vupdate_irq(struct drm_crtc *crtc, bool enable); bool amdgpu_dm_crtc_vrr_active_irq(struct amdgpu_crtc *acrtc); -bool amdgpu_dm_crtc_vrr_active(struct dm_crtc_state *dm_state); +bool amdgpu_dm_crtc_vrr_active(const struct dm_crtc_state *dm_state); int amdgpu_dm_crtc_enable_vblank(struct drm_crtc *crtc); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index bc3e7a82b402..049046c60462 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -25,6 +25,7 @@ #include #include +#include #include "dc.h" #include "amdgpu.h" @@ -2848,6 +2849,67 @@ static int is_dpia_link_show(struct seq_file *m, void *data) return 0; } +/** + * hdmi_cec_state_show - Read out the HDMI-CEC feature status + * @m: sequence file. + * @data: unused. + * + * Return 0 on success + */ +static int hdmi_cec_state_show(struct seq_file *m, void *data) +{ + struct drm_connector *connector = m->private; + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + + seq_printf(m, "%s:%d\n", connector->name, connector->base.id); + seq_printf(m, "HDMI-CEC status: %d\n", aconnector->notifier ? 1 : 0); + + return 0; +} + +/** + * hdmi_cec_state_write - Enable/Disable HDMI-CEC feature from driver side + * @f: file structure. + * @buf: userspace buffer. set to '1' to enable; '0' to disable cec feature. + * @size: size of buffer from userpsace. + * @pos: unused. + * + * Return size on success, error code on failure + */ +static ssize_t hdmi_cec_state_write(struct file *f, const char __user *buf, + size_t size, loff_t *pos) +{ + int ret; + bool enable; + struct amdgpu_dm_connector *aconnector = file_inode(f)->i_private; + struct drm_device *ddev = aconnector->base.dev; + + if (size == 0) + return -EINVAL; + + ret = kstrtobool_from_user(buf, size, &enable); + if (ret) { + drm_dbg_driver(ddev, "invalid user data !\n"); + return ret; + } + + if (enable) { + if (aconnector->notifier) + return -EINVAL; + ret = amdgpu_dm_initialize_hdmi_connector(aconnector); + if (ret) + return ret; + hdmi_cec_set_edid(aconnector); + } else { + if (!aconnector->notifier) + return -EINVAL; + cec_notifier_conn_unregister(aconnector->notifier); + aconnector->notifier = NULL; + } + + return size; +} + DEFINE_SHOW_ATTRIBUTE(dp_dsc_fec_support); DEFINE_SHOW_ATTRIBUTE(dmub_fw_state); DEFINE_SHOW_ATTRIBUTE(dmub_tracebuffer); @@ -2860,6 +2922,7 @@ DEFINE_SHOW_ATTRIBUTE(psr_capability); DEFINE_SHOW_ATTRIBUTE(dp_is_mst_connector); DEFINE_SHOW_ATTRIBUTE(dp_mst_progress_status); DEFINE_SHOW_ATTRIBUTE(is_dpia_link); +DEFINE_SHOW_STORE_ATTRIBUTE(hdmi_cec_state); static const struct file_operations dp_dsc_clock_en_debugfs_fops = { .owner = THIS_MODULE, @@ -2995,7 +3058,8 @@ static const struct { char *name; const struct file_operations *fops; } hdmi_debugfs_entries[] = { - {"hdcp_sink_capability", &hdcp_sink_capability_fops} + {"hdcp_sink_capability", &hdcp_sink_capability_fops}, + {"hdmi_cec_state", &hdmi_cec_state_fops} }; /* @@ -3480,8 +3544,8 @@ static int crc_win_x_start_set(void *data, u64 val) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); spin_lock_irq(&drm_dev->event_lock); - acrtc->dm_irq_params.window_param.x_start = (uint16_t) val; - acrtc->dm_irq_params.window_param.update_win = false; + acrtc->dm_irq_params.window_param[0].x_start = (uint16_t) val; + acrtc->dm_irq_params.window_param[0].update_win = false; spin_unlock_irq(&drm_dev->event_lock); return 0; @@ -3497,7 +3561,7 @@ static int crc_win_x_start_get(void *data, u64 *val) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); spin_lock_irq(&drm_dev->event_lock); - *val = acrtc->dm_irq_params.window_param.x_start; + *val = acrtc->dm_irq_params.window_param[0].x_start; spin_unlock_irq(&drm_dev->event_lock); return 0; @@ -3517,8 +3581,8 @@ static int crc_win_y_start_set(void *data, u64 val) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); spin_lock_irq(&drm_dev->event_lock); - acrtc->dm_irq_params.window_param.y_start = (uint16_t) val; - acrtc->dm_irq_params.window_param.update_win = false; + acrtc->dm_irq_params.window_param[0].y_start = (uint16_t) val; + acrtc->dm_irq_params.window_param[0].update_win = false; spin_unlock_irq(&drm_dev->event_lock); return 0; @@ -3534,7 +3598,7 @@ static int crc_win_y_start_get(void *data, u64 *val) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); spin_lock_irq(&drm_dev->event_lock); - *val = acrtc->dm_irq_params.window_param.y_start; + *val = acrtc->dm_irq_params.window_param[0].y_start; spin_unlock_irq(&drm_dev->event_lock); return 0; @@ -3553,8 +3617,8 @@ static int crc_win_x_end_set(void *data, u64 val) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); spin_lock_irq(&drm_dev->event_lock); - acrtc->dm_irq_params.window_param.x_end = (uint16_t) val; - acrtc->dm_irq_params.window_param.update_win = false; + acrtc->dm_irq_params.window_param[0].x_end = (uint16_t) val; + acrtc->dm_irq_params.window_param[0].update_win = false; spin_unlock_irq(&drm_dev->event_lock); return 0; @@ -3570,7 +3634,7 @@ static int crc_win_x_end_get(void *data, u64 *val) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); spin_lock_irq(&drm_dev->event_lock); - *val = acrtc->dm_irq_params.window_param.x_end; + *val = acrtc->dm_irq_params.window_param[0].x_end; spin_unlock_irq(&drm_dev->event_lock); return 0; @@ -3589,8 +3653,8 @@ static int crc_win_y_end_set(void *data, u64 val) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); spin_lock_irq(&drm_dev->event_lock); - acrtc->dm_irq_params.window_param.y_end = (uint16_t) val; - acrtc->dm_irq_params.window_param.update_win = false; + acrtc->dm_irq_params.window_param[0].y_end = (uint16_t) val; + acrtc->dm_irq_params.window_param[0].update_win = false; spin_unlock_irq(&drm_dev->event_lock); return 0; @@ -3606,7 +3670,7 @@ static int crc_win_y_end_get(void *data, u64 *val) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); spin_lock_irq(&drm_dev->event_lock); - *val = acrtc->dm_irq_params.window_param.y_end; + *val = acrtc->dm_irq_params.window_param[0].y_end; spin_unlock_irq(&drm_dev->event_lock); return 0; @@ -3629,13 +3693,14 @@ static int crc_win_update_set(void *data, u64 val) /* PSR may write to OTG CRC window control register, * so close it before starting secure_display. */ - amdgpu_dm_psr_disable(acrtc->dm_irq_params.stream); + amdgpu_dm_psr_disable(acrtc->dm_irq_params.stream, true); spin_lock_irq(&adev_to_drm(adev)->event_lock); - acrtc->dm_irq_params.window_param.activated = true; - acrtc->dm_irq_params.window_param.update_win = true; - acrtc->dm_irq_params.window_param.skip_frame_cnt = 0; + acrtc->dm_irq_params.window_param[0].enable = true; + acrtc->dm_irq_params.window_param[0].update_win = true; + acrtc->dm_irq_params.window_param[0].skip_frame_cnt = 0; + acrtc->dm_irq_params.crc_window_activated = true; spin_unlock_irq(&adev_to_drm(adev)->event_lock); mutex_unlock(&adev->dm.dc_lock); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 6cbbb71d752b..fbd80d8545a8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -885,6 +885,12 @@ bool dm_helpers_dp_write_dsc_enable( return ret; } +bool dm_helpers_dp_write_hblank_reduction(struct dc_context *ctx, const struct dc_stream_state *stream) +{ + // TODO + return false; +} + bool dm_helpers_is_dp_sink_present(struct dc_link *link) { bool dp_sink_present; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h index 6a7ecc1e4602..6c9de834455b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h @@ -39,7 +39,9 @@ struct dm_irq_params { #ifdef CONFIG_DEBUG_FS enum amdgpu_dm_pipe_crc_source crc_src; #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY - struct crc_window_param window_param; + struct crc_window_param window_param[MAX_CRC_WINDOW_NUM]; + /* At least one CRC window is activated or not*/ + bool crc_window_activated; #endif #endif }; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 56fa2b9b5d7a..07e744da7bf4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -155,6 +155,17 @@ amdgpu_dm_mst_connector_late_register(struct drm_connector *connector) return 0; } + +static inline void +amdgpu_dm_mst_reset_mst_connector_setting(struct amdgpu_dm_connector *aconnector) +{ + aconnector->drm_edid = NULL; + aconnector->dsc_aux = NULL; + aconnector->mst_output_port->passthrough_aux = NULL; + aconnector->mst_local_bw = 0; + aconnector->vc_full_pbn = 0; +} + static void amdgpu_dm_mst_connector_early_unregister(struct drm_connector *connector) { @@ -182,9 +193,7 @@ amdgpu_dm_mst_connector_early_unregister(struct drm_connector *connector) dc_sink_release(dc_sink); aconnector->dc_sink = NULL; - aconnector->drm_edid = NULL; - aconnector->dsc_aux = NULL; - port->passthrough_aux = NULL; + amdgpu_dm_mst_reset_mst_connector_setting(aconnector); } aconnector->mst_status = MST_STATUS_DEFAULT; @@ -504,9 +513,7 @@ dm_dp_mst_detect(struct drm_connector *connector, dc_sink_release(aconnector->dc_sink); aconnector->dc_sink = NULL; - aconnector->drm_edid = NULL; - aconnector->dsc_aux = NULL; - port->passthrough_aux = NULL; + amdgpu_dm_mst_reset_mst_connector_setting(aconnector); amdgpu_dm_set_mst_status(&aconnector->mst_status, MST_REMOTE_EDID | MST_ALLOCATE_NEW_PAYLOAD | MST_CLEAR_ALLOCATED_PAYLOAD, @@ -1820,9 +1827,18 @@ enum dc_status dm_dp_mst_is_port_support_mode( struct drm_dp_mst_port *immediate_upstream_port = NULL; uint32_t end_link_bw = 0; - /*Get last DP link BW capability*/ - if (dp_get_link_current_set_bw(&aconnector->mst_output_port->aux, &end_link_bw)) { - if (stream_kbps > end_link_bw) { + /*Get last DP link BW capability. Mode shall be supported by Legacy peer*/ + if (aconnector->mst_output_port->pdt != DP_PEER_DEVICE_DP_LEGACY_CONV && + aconnector->mst_output_port->pdt != DP_PEER_DEVICE_NONE) { + if (aconnector->vc_full_pbn != aconnector->mst_output_port->full_pbn) { + dp_get_link_current_set_bw(&aconnector->mst_output_port->aux, &end_link_bw); + aconnector->vc_full_pbn = aconnector->mst_output_port->full_pbn; + aconnector->mst_local_bw = end_link_bw; + } else { + end_link_bw = aconnector->mst_local_bw; + } + + if (end_link_bw > 0 && stream_kbps > end_link_bw) { DRM_DEBUG_DRIVER("MST_DSC dsc decode at last link." "Mode required bw can't fit into last link\n"); return DC_FAIL_BANDWIDTH_VALIDATE; @@ -1836,11 +1852,15 @@ enum dc_status dm_dp_mst_is_port_support_mode( if (immediate_upstream_port) { virtual_channel_bw_in_kbps = kbps_from_pbn(immediate_upstream_port->full_pbn); virtual_channel_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps); - if (bw_range.min_kbps > virtual_channel_bw_in_kbps) { - DRM_DEBUG_DRIVER("MST_DSC dsc decode at last link." - "Max dsc compression can't fit into MST available bw\n"); - return DC_FAIL_BANDWIDTH_VALIDATE; - } + } else { + /* For topology LCT 1 case - only one mstb*/ + virtual_channel_bw_in_kbps = root_link_bw_in_kbps; + } + + if (bw_range.min_kbps > virtual_channel_bw_in_kbps) { + DRM_DEBUG_DRIVER("MST_DSC dsc decode at last link." + "Max dsc compression can't fit into MST available bw\n"); + return DC_FAIL_BANDWIDTH_VALIDATE; } } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 1ec4e4b9ea94..774cc3f4f3fd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -177,7 +177,7 @@ static unsigned int amdgpu_dm_plane_modifier_gfx9_swizzle_mode(uint64_t modifier return AMD_FMT_MOD_GET(TILE, modifier); } -static void amdgpu_dm_plane_fill_gfx8_tiling_info_from_flags(union dc_tiling_info *tiling_info, +static void amdgpu_dm_plane_fill_gfx8_tiling_info_from_flags(struct dc_tiling_info *tiling_info, uint64_t tiling_flags) { /* Fill GFX8 params */ @@ -190,6 +190,7 @@ static void amdgpu_dm_plane_fill_gfx8_tiling_info_from_flags(union dc_tiling_inf tile_split = AMDGPU_TILING_GET(tiling_flags, TILE_SPLIT); num_banks = AMDGPU_TILING_GET(tiling_flags, NUM_BANKS); + tiling_info->gfxversion = DcGfxVersion8; /* XXX fix me for VI */ tiling_info->gfx8.num_banks = num_banks; tiling_info->gfx8.array_mode = @@ -210,7 +211,7 @@ static void amdgpu_dm_plane_fill_gfx8_tiling_info_from_flags(union dc_tiling_inf } static void amdgpu_dm_plane_fill_gfx9_tiling_info_from_device(const struct amdgpu_device *adev, - union dc_tiling_info *tiling_info) + struct dc_tiling_info *tiling_info) { /* Fill GFX9 params */ tiling_info->gfx9.num_pipes = @@ -231,7 +232,7 @@ static void amdgpu_dm_plane_fill_gfx9_tiling_info_from_device(const struct amdgp } static void amdgpu_dm_plane_fill_gfx9_tiling_info_from_modifier(const struct amdgpu_device *adev, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, uint64_t modifier) { unsigned int mod_bank_xor_bits = AMD_FMT_MOD_GET(BANK_XOR_BITS, modifier); @@ -261,7 +262,7 @@ static void amdgpu_dm_plane_fill_gfx9_tiling_info_from_modifier(const struct amd static int amdgpu_dm_plane_validate_dcc(struct amdgpu_device *adev, const enum surface_pixel_format format, const enum dc_rotation_angle rotation, - const union dc_tiling_info *tiling_info, + const struct dc_tiling_info *tiling_info, const struct dc_plane_dcc_param *dcc, const struct dc_plane_address *address, const struct plane_size *plane_size) @@ -308,7 +309,7 @@ static int amdgpu_dm_plane_fill_gfx9_plane_attributes_from_modifiers(struct amdg const enum surface_pixel_format format, const enum dc_rotation_angle rotation, const struct plane_size *plane_size, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct dc_plane_dcc_param *dcc, struct dc_plane_address *address) { @@ -317,6 +318,7 @@ static int amdgpu_dm_plane_fill_gfx9_plane_attributes_from_modifiers(struct amdg amdgpu_dm_plane_fill_gfx9_tiling_info_from_modifier(adev, tiling_info, modifier); tiling_info->gfx9.swizzle = amdgpu_dm_plane_modifier_gfx9_swizzle_mode(modifier); + tiling_info->gfxversion = DcGfxVersion9; if (amdgpu_dm_plane_modifier_has_dcc(modifier)) { uint64_t dcc_address = afb->address + afb->base.offsets[1]; @@ -358,7 +360,7 @@ static int amdgpu_dm_plane_fill_gfx12_plane_attributes_from_modifiers(struct amd const enum surface_pixel_format format, const enum dc_rotation_angle rotation, const struct plane_size *plane_size, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct dc_plane_dcc_param *dcc, struct dc_plane_address *address) { @@ -369,6 +371,7 @@ static int amdgpu_dm_plane_fill_gfx12_plane_attributes_from_modifiers(struct amd amdgpu_dm_plane_fill_gfx9_tiling_info_from_device(adev, tiling_info); tiling_info->gfx9.swizzle = amdgpu_dm_plane_modifier_gfx9_swizzle_mode(modifier); + tiling_info->gfxversion = DcGfxAddr3; if (amdgpu_dm_plane_modifier_has_dcc(modifier)) { int max_compressed_block = AMD_FMT_MOD_GET(DCC_MAX_COMPRESSED_BLOCK, modifier); @@ -834,7 +837,7 @@ int amdgpu_dm_plane_fill_plane_buffer_attributes(struct amdgpu_device *adev, const enum surface_pixel_format format, const enum dc_rotation_angle rotation, const uint64_t tiling_flags, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, struct dc_plane_dcc_param *dcc, struct dc_plane_address *address, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h index 2eef13b1c05a..615d2ab2b803 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h @@ -47,7 +47,7 @@ int amdgpu_dm_plane_fill_plane_buffer_attributes(struct amdgpu_device *adev, const enum surface_pixel_format format, const enum dc_rotation_angle rotation, const uint64_t tiling_flags, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, struct dc_plane_dcc_param *dcc, struct dc_plane_address *address, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c index f40240aafe98..45858bf1523d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -201,14 +201,13 @@ void amdgpu_dm_psr_enable(struct dc_stream_state *stream) * * Return: true if success */ -bool amdgpu_dm_psr_disable(struct dc_stream_state *stream) +bool amdgpu_dm_psr_disable(struct dc_stream_state *stream, bool wait) { - unsigned int power_opt = 0; bool psr_enable = false; DRM_DEBUG_DRIVER("Disabling psr...\n"); - return dc_link_set_psr_allow_active(stream->link, &psr_enable, true, false, &power_opt); + return dc_link_set_psr_allow_active(stream->link, &psr_enable, wait, false, NULL); } /* @@ -251,3 +250,33 @@ bool amdgpu_dm_psr_is_active_allowed(struct amdgpu_display_manager *dm) return allow_active; } + +/** + * amdgpu_dm_psr_wait_disable() - Wait for eDP panel to exit PSR + * @stream: stream state attached to the eDP link + * + * Waits for a max of 500ms for the eDP panel to exit PSR. + * + * Return: true if panel exited PSR, false otherwise. + */ +bool amdgpu_dm_psr_wait_disable(struct dc_stream_state *stream) +{ + enum dc_psr_state psr_state = PSR_STATE0; + struct dc_link *link = stream->link; + int retry_count; + + if (link == NULL) + return false; + + for (retry_count = 0; retry_count <= 1000; retry_count++) { + dc_link_get_psr_state(link, &psr_state); + if (psr_state == PSR_STATE0) + break; + udelay(500); + } + + if (retry_count == 1000) + return false; + + return true; +} diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h index cd2d45c2b5ef..e2366321a3c1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h @@ -34,8 +34,9 @@ void amdgpu_dm_set_psr_caps(struct dc_link *link); void amdgpu_dm_psr_enable(struct dc_stream_state *stream); bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream); -bool amdgpu_dm_psr_disable(struct dc_stream_state *stream); +bool amdgpu_dm_psr_disable(struct dc_stream_state *stream, bool wait); bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm); bool amdgpu_dm_psr_is_active_allowed(struct amdgpu_display_manager *dm); +bool amdgpu_dm_psr_wait_disable(struct dc_stream_state *stream); #endif /* AMDGPU_DM_AMDGPU_DM_PSR_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index c9a6de110b74..a62f6c51301c 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -3088,11 +3088,12 @@ static enum bp_result construct_integrated_info( info->ext_disp_conn_info.path[i].ext_encoder_obj_id.id, info->ext_disp_conn_info.path[i].caps ); - if (info->ext_disp_conn_info.path[i].caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) - DC_LOG_BIOS("BIOS EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN on path %d\n", i); + if ((info->ext_disp_conn_info.path[i].caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) + DC_LOG_BIOS("BIOS AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN on path %d\n", i); else if (bp->base.ctx->dc->config.force_bios_fixed_vs) { - info->ext_disp_conn_info.path[i].caps |= EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN; - DC_LOG_BIOS("driver forced EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN on path %d\n", i); + info->ext_disp_conn_info.path[i].caps &= ~AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK; + info->ext_disp_conn_info.path[i].caps |= AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN; + DC_LOG_BIOS("driver forced AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN on path %d\n", i); } } // Log the Checksum and Voltage Swing diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index 2a74140d7ebf..1648226586e2 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -89,7 +89,7 @@ #define mmCLK1_CLK4_ALLOW_DS 0x16EA8 #define mmCLK1_CLK5_ALLOW_DS 0x16EB1 -#define mmCLK5_spll_field_8 0x1B04B +#define mmCLK5_spll_field_8 0x1B24B #define mmDENTIST_DISPCLK_CNTL 0x0124 #define regDENTIST_DISPCLK_CNTL 0x0064 #define regDENTIST_DISPCLK_CNTL_BASE_IDX 1 @@ -401,6 +401,7 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base, if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) { if (clk_mgr->base.ctx->dc->config.allow_0_dtb_clk) dcn35_smu_set_dtbclk(clk_mgr, false); + clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en; } /* check that we're not already in lower */ @@ -418,11 +419,17 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base, } if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) { - dcn35_smu_set_dtbclk(clk_mgr, true); - clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en; + int actual_dtbclk = 0; dcn35_update_clocks_update_dtb_dto(clk_mgr, context, new_clocks->ref_dtbclk_khz); - clk_mgr_base->clks.ref_dtbclk_khz = new_clocks->ref_dtbclk_khz; + dcn35_smu_set_dtbclk(clk_mgr, true); + + actual_dtbclk = REG_READ(CLK1_CLK4_CURRENT_CNT); + + if (actual_dtbclk) { + clk_mgr_base->clks.ref_dtbclk_khz = new_clocks->ref_dtbclk_khz; + clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en; + } } /* check that we're not already in D0 */ @@ -584,12 +591,10 @@ static bool dcn35_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base) static void init_clk_states(struct clk_mgr *clk_mgr) { - struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr); uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz; + memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks)); - if (clk_mgr_int->smu_ver >= SMU_VER_THRESHOLD) - clk_mgr->clks.dtbclk_en = true; // request DTBCLK disable on first commit clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk; // restore ref_dtbclk clk_mgr->clks.p_state_change_support = true; clk_mgr->clks.prev_p_state_change_support = true; @@ -600,6 +605,7 @@ static void init_clk_states(struct clk_mgr *clk_mgr) void dcn35_init_clocks(struct clk_mgr *clk_mgr) { struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr); + init_clk_states(clk_mgr); // to adjust dp_dto reference clock if ssc is enable otherwise to apply dprefclk diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dalsmc.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dalsmc.h index dbfdd3487da5..2e0d34fd7512 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dalsmc.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dalsmc.h @@ -43,7 +43,9 @@ #define DALSMC_MSG_ActiveUclkFclk 0x18 #define DALSMC_MSG_IdleUclkFclk 0x19 #define DALSMC_MSG_SetUclkPstateAllow 0x1A -#define DALSMC_Message_Count 0x1B +#define DALSMC_MSG_SubvpUclkFclk 0x1B +#define DALSMC_MSG_GetNumUmcChannels 0x1C +#define DALSMC_Message_Count 0x1D typedef enum { FCLK_SWITCH_DISALLOW, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c index 5b4e1e8a9ae2..8082bb877611 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c @@ -628,207 +628,6 @@ static void dcn401_update_clocks_update_dentist( } -static void dcn401_update_clocks_legacy(struct clk_mgr *clk_mgr_base, - struct dc_state *context, - bool safe_to_lower) -{ - struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); - struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk; - struct dc *dc = clk_mgr_base->ctx->dc; - int display_count; - bool update_dppclk = false; - bool update_dispclk = false; - bool enter_display_off = false; - bool dpp_clock_lowered = false; - struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu; - bool force_reset = false; - bool update_uclk = false, update_fclk = false; - bool p_state_change_support; - bool fclk_p_state_change_support; - int total_plane_count; - - if (dc->work_arounds.skip_clock_update) - return; - - if (clk_mgr_base->clks.dispclk_khz == 0 || - (dc->debug.force_clock_mode & 0x1)) { - /* This is from resume or boot up, if forced_clock cfg option used, - * we bypass program dispclk and DPPCLK, but need set them for S3. - */ - force_reset = true; - - dcn2_read_clocks_from_hw_dentist(clk_mgr_base); - - /* Force_clock_mode 0x1: force reset the clock even it is the same clock - * as long as it is in Passive level. - */ - } - display_count = clk_mgr_helper_get_active_display_cnt(dc, context); - - if (display_count == 0) - enter_display_off = true; - - if (clk_mgr->smu_present) { - if (enter_display_off == safe_to_lower) - dcn401_smu_set_num_of_displays(clk_mgr, display_count); - - clk_mgr_base->clks.fclk_prev_p_state_change_support = clk_mgr_base->clks.fclk_p_state_change_support; - - total_plane_count = clk_mgr_helper_get_active_plane_cnt(dc, context); - fclk_p_state_change_support = new_clocks->fclk_p_state_change_support || (total_plane_count == 0); - - if (should_update_pstate_support(safe_to_lower, fclk_p_state_change_support, clk_mgr_base->clks.fclk_p_state_change_support)) { - clk_mgr_base->clks.fclk_p_state_change_support = fclk_p_state_change_support; - - /* To enable FCLK P-state switching, send PSTATE_SUPPORTED message to PMFW */ - if (clk_mgr_base->clks.fclk_p_state_change_support) { - /* Handle the code for sending a message to PMFW that FCLK P-state change is supported */ - dcn401_smu_send_fclk_pstate_message(clk_mgr, true); - } - } - - if (dc->debug.force_min_dcfclk_mhz > 0) - new_clocks->dcfclk_khz = (new_clocks->dcfclk_khz > (dc->debug.force_min_dcfclk_mhz * 1000)) ? - new_clocks->dcfclk_khz : (dc->debug.force_min_dcfclk_mhz * 1000); - - if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, clk_mgr_base->clks.dcfclk_khz)) { - clk_mgr_base->clks.dcfclk_khz = new_clocks->dcfclk_khz; - if (dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_DCFCLK)) - dcn401_smu_set_hard_min_by_freq(clk_mgr, PPCLK_DCFCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dcfclk_khz)); - } - - if (should_set_clock(safe_to_lower, new_clocks->dcfclk_deep_sleep_khz, clk_mgr_base->clks.dcfclk_deep_sleep_khz)) { - clk_mgr_base->clks.dcfclk_deep_sleep_khz = new_clocks->dcfclk_deep_sleep_khz; - if (dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_DCFCLK)) - dcn401_smu_set_min_deep_sleep_dcef_clk(clk_mgr, khz_to_mhz_ceil(clk_mgr_base->clks.dcfclk_deep_sleep_khz)); - } - - if (should_set_clock(safe_to_lower, new_clocks->socclk_khz, clk_mgr_base->clks.socclk_khz)) - /* We don't actually care about socclk, don't notify SMU of hard min */ - clk_mgr_base->clks.socclk_khz = new_clocks->socclk_khz; - - clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support; - clk_mgr_base->clks.prev_num_ways = clk_mgr_base->clks.num_ways; - - if (clk_mgr_base->clks.num_ways != new_clocks->num_ways && - clk_mgr_base->clks.num_ways < new_clocks->num_ways) { - clk_mgr_base->clks.num_ways = new_clocks->num_ways; - if (dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_UCLK)) - dcn401_smu_send_cab_for_uclk_message(clk_mgr, clk_mgr_base->clks.num_ways); - } - - - p_state_change_support = new_clocks->p_state_change_support || (total_plane_count == 0); - if (should_update_pstate_support(safe_to_lower, p_state_change_support, clk_mgr_base->clks.prev_p_state_change_support)) { - clk_mgr_base->clks.p_state_change_support = p_state_change_support; - clk_mgr_base->clks.fw_based_mclk_switching = p_state_change_support && new_clocks->fw_based_mclk_switching; - - /* to disable P-State switching, set UCLK min = max */ - if (!clk_mgr_base->clks.p_state_change_support && dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_UCLK)) - dcn401_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, - clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1].memclk_mhz); - } - - /* Always update saved value, even if new value not set due to P-State switching unsupported. Also check safe_to_lower for FCLK */ - if (safe_to_lower && (clk_mgr_base->clks.fclk_p_state_change_support != clk_mgr_base->clks.fclk_prev_p_state_change_support)) { - update_fclk = true; - } - - if (!clk_mgr_base->clks.fclk_p_state_change_support && - update_fclk && - dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_FCLK)) { - /* Handle code for sending a message to PMFW that FCLK P-state change is not supported */ - dcn401_smu_send_fclk_pstate_message(clk_mgr, false); - } - - /* Always update saved value, even if new value not set due to P-State switching unsupported */ - if (should_set_clock(safe_to_lower, new_clocks->dramclk_khz, clk_mgr_base->clks.dramclk_khz)) { - clk_mgr_base->clks.dramclk_khz = new_clocks->dramclk_khz; - update_uclk = true; - } - - /* set UCLK to requested value if P-State switching is supported, or to re-enable P-State switching */ - if (clk_mgr_base->clks.p_state_change_support && - (update_uclk || !clk_mgr_base->clks.prev_p_state_change_support) && - dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_UCLK)) - dcn401_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)); - - if (clk_mgr_base->clks.num_ways != new_clocks->num_ways && - clk_mgr_base->clks.num_ways > new_clocks->num_ways) { - clk_mgr_base->clks.num_ways = new_clocks->num_ways; - if (dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_UCLK)) - dcn401_smu_send_cab_for_uclk_message(clk_mgr, clk_mgr_base->clks.num_ways); - } - } - - if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr_base->clks.dppclk_khz)) { - if (clk_mgr_base->clks.dppclk_khz > new_clocks->dppclk_khz) - dpp_clock_lowered = true; - - clk_mgr_base->clks.dppclk_khz = new_clocks->dppclk_khz; - clk_mgr_base->clks.actual_dppclk_khz = new_clocks->dppclk_khz; - - if (clk_mgr->smu_present && !dpp_clock_lowered && dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_DPPCLK)) - clk_mgr_base->clks.actual_dppclk_khz = dcn401_set_hard_min_by_freq_optimized(clk_mgr, PPCLK_DPPCLK, clk_mgr_base->clks.dppclk_khz); - update_dppclk = true; - } - - if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; - - if (clk_mgr->smu_present && dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_DISPCLK)) - clk_mgr_base->clks.actual_dispclk_khz = dcn401_set_hard_min_by_freq_optimized(clk_mgr, PPCLK_DISPCLK, clk_mgr_base->clks.dispclk_khz); - - update_dispclk = true; - } - - if (!new_clocks->dtbclk_en && dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_DTBCLK)) { - new_clocks->ref_dtbclk_khz = clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz * 1000; - } - - /* clock limits are received with MHz precision, divide by 1000 to prevent setting clocks at every call */ - if (!dc->debug.disable_dtb_ref_clk_switch && - should_set_clock(safe_to_lower, new_clocks->ref_dtbclk_khz / 1000, clk_mgr_base->clks.ref_dtbclk_khz / 1000) && - dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_DTBCLK)) { - /* DCCG requires KHz precision for DTBCLK */ - clk_mgr_base->clks.ref_dtbclk_khz = - dcn401_smu_set_hard_min_by_freq(clk_mgr, PPCLK_DTBCLK, khz_to_mhz_ceil(new_clocks->ref_dtbclk_khz)); - - dcn401_update_clocks_update_dtb_dto(clk_mgr, context, clk_mgr_base->clks.ref_dtbclk_khz); - } - - if (dc->config.forced_clocks == false || (force_reset && safe_to_lower)) { - if (dpp_clock_lowered) { - /* if clock is being lowered, increase DTO before lowering refclk */ - dcn401_update_clocks_update_dpp_dto(clk_mgr, context, - safe_to_lower, clk_mgr_base->clks.dppclk_khz); - dcn401_update_clocks_update_dentist(clk_mgr, context); - if (clk_mgr->smu_present && dcn401_is_ppclk_dpm_enabled(clk_mgr, PPCLK_DPPCLK)) { - clk_mgr_base->clks.actual_dppclk_khz = dcn401_set_hard_min_by_freq_optimized(clk_mgr, PPCLK_DPPCLK, - clk_mgr_base->clks.dppclk_khz); - dcn401_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower, - clk_mgr_base->clks.actual_dppclk_khz); - } - - } else { - /* if clock is being raised, increase refclk before lowering DTO */ - if (update_dppclk || update_dispclk) - dcn401_update_clocks_update_dentist(clk_mgr, context); - /* There is a check inside dcn20_update_clocks_update_dpp_dto which ensures - * that we do not lower dto when it is not safe to lower. We do not need to - * compare the current and new dppclk before calling this function. - */ - dcn401_update_clocks_update_dpp_dto(clk_mgr, context, - safe_to_lower, clk_mgr_base->clks.actual_dppclk_khz); - } - } - - if (update_dispclk && dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) - /*update dmcu for wait_loop count*/ - dmcu->funcs->set_psr_wait_loop(dmcu, - clk_mgr_base->clks.dispclk_khz / 1000 / 7); -} - static void dcn401_execute_block_sequence(struct clk_mgr *clk_mgr_base, unsigned int num_steps) { struct clk_mgr_internal *clk_mgr_internal = TO_CLK_MGR_INTERNAL(clk_mgr_base); @@ -1008,15 +807,15 @@ static unsigned int dcn401_build_update_bandwidth_clocks_sequence( update_active_fclk = true; update_idle_fclk = true; - /* To enable FCLK P-state switching, send PSTATE_SUPPORTED message to PMFW */ - if (clk_mgr_base->clks.fclk_p_state_change_support) { - /* Handle the code for sending a message to PMFW that FCLK P-state change is supported */ - if (dcn401_is_ppclk_dpm_enabled(clk_mgr_internal, PPCLK_FCLK)) { - block_sequence[num_steps].params.update_pstate_support_params.support = true; - block_sequence[num_steps].func = CLK_MGR401_UPDATE_FCLK_PSTATE_SUPPORT; - num_steps++; - } - } + /* To enable FCLK P-state switching, send PSTATE_SUPPORTED message to PMFW (message not supported on DCN401)*/ + // if (clk_mgr_base->clks.fclk_p_state_change_support) { + // /* Handle the code for sending a message to PMFW that FCLK P-state change is supported */ + // if (dcn401_is_ppclk_dpm_enabled(clk_mgr_internal, PPCLK_FCLK)) { + // block_sequence[num_steps].params.update_pstate_support_params.support = true; + // block_sequence[num_steps].func = CLK_MGR401_UPDATE_FCLK_PSTATE_SUPPORT; + // num_steps++; + // } + // } } if (!clk_mgr_base->clks.fclk_p_state_change_support && dcn401_is_ppclk_dpm_enabled(clk_mgr_internal, PPCLK_FCLK)) { @@ -1224,14 +1023,14 @@ static unsigned int dcn401_build_update_bandwidth_clocks_sequence( // (*num_steps)++; // } - /* disable FCLK P-State support if needed */ - if (!fclk_p_state_change_support && - should_update_pstate_support(safe_to_lower, fclk_p_state_change_support, clk_mgr_base->clks.fclk_prev_p_state_change_support) && - dcn401_is_ppclk_dpm_enabled(clk_mgr_internal, PPCLK_FCLK)) { - block_sequence[num_steps].params.update_pstate_support_params.support = false; - block_sequence[num_steps].func = CLK_MGR401_UPDATE_FCLK_PSTATE_SUPPORT; - num_steps++; - } + /* disable FCLK P-State support if needed (message not supported on DCN401)*/ + // if (!fclk_p_state_change_support && + // should_update_pstate_support(safe_to_lower, fclk_p_state_change_support, clk_mgr_base->clks.fclk_prev_p_state_change_support) && + // dcn401_is_ppclk_dpm_enabled(clk_mgr_internal, PPCLK_FCLK)) { + // block_sequence[num_steps].params.update_pstate_support_params.support = false; + // block_sequence[num_steps].func = CLK_MGR401_UPDATE_FCLK_PSTATE_SUPPORT; + // num_steps++; + // } } if (new_clocks->fw_based_mclk_switching != clk_mgr_base->clks.fw_based_mclk_switching && @@ -1412,11 +1211,6 @@ static void dcn401_update_clocks(struct clk_mgr *clk_mgr_base, unsigned int num_steps = 0; - if (dc->debug.enable_legacy_clock_update) { - dcn401_update_clocks_legacy(clk_mgr_base, context, safe_to_lower); - return; - } - /* build bandwidth related clocks update sequence */ num_steps = dcn401_build_update_bandwidth_clocks_sequence(clk_mgr_base, context, @@ -1551,6 +1345,20 @@ static void dcn401_set_hard_min_memclk(struct clk_mgr *clk_mgr_base, bool curren dcn401_execute_block_sequence(clk_mgr_base, num_steps); } +static int dcn401_get_hard_min_memclk(struct clk_mgr *clk_mgr_base) +{ + struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + + return clk_mgr->base.ctx->dc->current_state->bw_ctx.bw.dcn.clk.dramclk_khz; +} + +static int dcn401_get_hard_min_fclk(struct clk_mgr *clk_mgr_base) +{ + struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + + return clk_mgr->base.ctx->dc->current_state->bw_ctx.bw.dcn.clk.fclk_khz; +} + /* Get current memclk states, update bounding box */ static void dcn401_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base) { @@ -1595,6 +1403,15 @@ static void dcn401_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base) if (clk_mgr->dpm_present && !num_levels) clk_mgr->dpm_present = false; + clk_mgr_base->bw_params->num_channels = dcn401_smu_get_num_of_umc_channels(clk_mgr); + if (clk_mgr_base->ctx->dc_bios) { + /* use BIOS values if none provided by PMFW */ + if (clk_mgr_base->bw_params->num_channels == 0) { + clk_mgr_base->bw_params->num_channels = clk_mgr_base->ctx->dc_bios->vram_info.num_chans; + } + clk_mgr_base->bw_params->dram_channel_width_bytes = clk_mgr_base->ctx->dc_bios->vram_info.dram_channel_width_bytes; + } + /* Refresh bounding box */ clk_mgr_base->ctx->dc->res_pool->funcs->update_bw_bounding_box( clk_mgr->base.ctx->dc, clk_mgr_base->bw_params); @@ -1684,6 +1501,8 @@ static struct clk_mgr_funcs dcn401_funcs = { .enable_pme_wa = dcn401_enable_pme_wa, .is_smu_present = dcn401_is_smu_present, .get_dispclk_from_dentist = dcn401_get_dispclk_from_dentist, + .get_hard_min_memclk = dcn401_get_hard_min_memclk, + .get_hard_min_fclk = dcn401_get_hard_min_fclk, }; struct clk_mgr_internal *dcn401_clk_mgr_construct( diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c index b02a41179b41..21c35528f61f 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c @@ -25,6 +25,9 @@ #ifndef DALSMC_MSG_SubvpUclkFclk #define DALSMC_MSG_SubvpUclkFclk 0x1B #endif +#ifndef DALSMC_MSG_GetNumUmcChannels +#define DALSMC_MSG_GetNumUmcChannels 0x1C +#endif /* * Function to be used instead of REG_WAIT macro because the wait ends when @@ -334,3 +337,14 @@ void dcn401_smu_set_num_of_displays(struct clk_mgr_internal *clk_mgr, uint32_t n dcn401_smu_send_msg_with_param(clk_mgr, DALSMC_MSG_NumOfDisplays, num_displays, NULL); } + +unsigned int dcn401_smu_get_num_of_umc_channels(struct clk_mgr_internal *clk_mgr) +{ + unsigned int response = 0; + + dcn401_smu_send_msg_with_param(clk_mgr, DALSMC_MSG_GetNumUmcChannels, 0, &response); + + smu_print("SMU Get Num UMC Channels: num_umc_channels = %d\n", response); + + return response; +} diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h index 42cf7885a7cb..e02eb1294b37 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h @@ -28,5 +28,6 @@ bool dcn401_smu_set_subvp_uclk_fclk_hardmin(struct clk_mgr_internal *clk_mgr, uint16_t fclk_freq_mhz); void dcn401_smu_set_min_deep_sleep_dcef_clk(struct clk_mgr_internal *clk_mgr, uint32_t freq_mhz); void dcn401_smu_set_num_of_displays(struct clk_mgr_internal *clk_mgr, uint32_t num_displays); +unsigned int dcn401_smu_get_num_of_umc_channels(struct clk_mgr_internal *clk_mgr); #endif /* __DCN401_CLK_MGR_SMU_MSG_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index dfa36368ae63..cecaadf741ad 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -615,6 +615,68 @@ dc_stream_forward_crc_window(struct dc_stream_state *stream, return true; } + +static void +dc_stream_forward_dmub_multiple_crc_window(struct dc_dmub_srv *dmub_srv, + struct crc_window *window, struct otg_phy_mux *mux_mapping, bool stop) +{ + int i; + union dmub_rb_cmd cmd = {0}; + + cmd.secure_display.mul_roi_ctl.phy_id = mux_mapping->phy_output_num; + cmd.secure_display.mul_roi_ctl.otg_id = mux_mapping->otg_output_num; + + cmd.secure_display.header.type = DMUB_CMD__SECURE_DISPLAY; + + if (stop) { + cmd.secure_display.header.sub_type = DMUB_CMD__SECURE_DISPLAY_MULTIPLE_CRC_STOP_UPDATE; + } else { + cmd.secure_display.header.sub_type = DMUB_CMD__SECURE_DISPLAY_MULTIPLE_CRC_WIN_NOTIFY; + for (i = 0; i < MAX_CRC_WINDOW_NUM; i++) { + cmd.secure_display.mul_roi_ctl.roi_ctl[i].x_start = window[i].rect.x; + cmd.secure_display.mul_roi_ctl.roi_ctl[i].y_start = window[i].rect.y; + cmd.secure_display.mul_roi_ctl.roi_ctl[i].x_end = window[i].rect.x + window[i].rect.width; + cmd.secure_display.mul_roi_ctl.roi_ctl[i].y_end = window[i].rect.y + window[i].rect.height; + cmd.secure_display.mul_roi_ctl.roi_ctl[i].enable = window[i].enable; + } + } + + dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); +} + +bool +dc_stream_forward_multiple_crc_window(struct dc_stream_state *stream, + struct crc_window *window, uint8_t phy_id, bool stop) +{ + struct dc_dmub_srv *dmub_srv; + struct otg_phy_mux mux_mapping; + struct pipe_ctx *pipe; + int i; + struct dc *dc = stream->ctx->dc; + + for (i = 0; i < MAX_PIPES; i++) { + pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + if (pipe->stream == stream && !pipe->top_pipe && !pipe->prev_odm_pipe) + break; + } + + /* Stream not found */ + if (i == MAX_PIPES) + return false; + + mux_mapping.phy_output_num = phy_id; + mux_mapping.otg_output_num = pipe->stream_res.tg->inst; + + dmub_srv = dc->ctx->dmub_srv; + + /* forward to dmub only. no dmcu support*/ + if (dmub_srv) + dc_stream_forward_dmub_multiple_crc_window(dmub_srv, window, &mux_mapping, stop); + else + return false; + + return true; +} #endif /* CONFIG_DRM_AMD_SECURE_DISPLAY */ /** @@ -625,15 +687,17 @@ dc_stream_forward_crc_window(struct dc_stream_state *stream, * @enable: Enable CRC if true, disable otherwise. * @continuous: Capture CRC on every frame if true. Otherwise, only capture * once. + * @idx: Capture CRC on which CRC engine instance + * @reset: Reset CRC engine before the configuration * - * By default, only CRC0 is configured, and the entire frame is used to - * calculate the CRC. + * By default, the entire frame is used to calculate the CRC. * * Return: %false if the stream is not found or CRC capture is not supported; * %true if the stream has been configured. */ bool dc_stream_configure_crc(struct dc *dc, struct dc_stream_state *stream, - struct crc_params *crc_window, bool enable, bool continuous) + struct crc_params *crc_window, bool enable, bool continuous, + uint8_t idx, bool reset) { struct pipe_ctx *pipe; struct crc_params param; @@ -677,6 +741,9 @@ bool dc_stream_configure_crc(struct dc *dc, struct dc_stream_state *stream, param.continuous_mode = continuous; param.enable = enable; + param.crc_eng_inst = idx; + param.reset = reset; + tg = pipe->stream_res.tg; /* Only call if supported */ @@ -691,6 +758,7 @@ bool dc_stream_configure_crc(struct dc *dc, struct dc_stream_state *stream, * * @dc: DC object. * @stream: The DC stream state of the stream to get CRCs from. + * @idx: index of crc engine to get CRC from * @r_cr: CRC value for the red component. * @g_y: CRC value for the green component. * @b_cb: CRC value for the blue component. @@ -700,7 +768,7 @@ bool dc_stream_configure_crc(struct dc *dc, struct dc_stream_state *stream, * Return: * %false if stream is not found, or if CRCs are not enabled. */ -bool dc_stream_get_crc(struct dc *dc, struct dc_stream_state *stream, +bool dc_stream_get_crc(struct dc *dc, struct dc_stream_state *stream, uint8_t idx, uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb) { int i; @@ -721,7 +789,7 @@ bool dc_stream_get_crc(struct dc *dc, struct dc_stream_state *stream, tg = pipe->stream_res.tg; if (tg->funcs->get_crc) - return tg->funcs->get_crc(tg, r_cr, g_y, b_cb); + return tg->funcs->get_crc(tg, idx, r_cr, g_y, b_cb); DC_LOG_WARNING("CRC capture not supported."); return false; } @@ -1173,6 +1241,8 @@ static void dc_update_visual_confirm_color(struct dc *dc, struct dc_state *conte get_mclk_switch_visual_confirm_color(pipe_ctx, &(pipe_ctx->visual_confirm_color)); else if (dc->debug.visual_confirm == VISUAL_CONFIRM_FAMS2) get_fams2_visual_confirm_color(dc, context, pipe_ctx, &(pipe_ctx->visual_confirm_color)); + else if (dc->debug.visual_confirm == VISUAL_CONFIRM_VABC) + get_vabc_visual_confirm_color(pipe_ctx, &(pipe_ctx->visual_confirm_color)); } } } @@ -2492,7 +2562,7 @@ static enum surface_update_type get_plane_info_update_type(const struct dc *dc, if (memcmp(&u->plane_info->tiling_info, &u->surface->tiling_info, - sizeof(union dc_tiling_info)) != 0) { + sizeof(struct dc_tiling_info)) != 0) { update_flags->bits.swizzle_change = 1; elevate_update_type(&update_type, UPDATE_TYPE_MED); @@ -4519,7 +4589,7 @@ static bool commit_minimal_transition_based_on_current_context(struct dc *dc, struct pipe_split_policy_backup policy; struct dc_state *intermediate_context; struct dc_state *old_current_state = dc->current_state; - struct dc_surface_update srf_updates[MAX_SURFACE_NUM] = {0}; + struct dc_surface_update srf_updates[MAX_SURFACES] = {0}; int surface_count; /* @@ -5316,13 +5386,9 @@ void dc_set_power_state(struct dc *dc, enum dc_acpi_cm_power_state power_state) dc->vm_pa_config.valid) { dc->hwss.init_sys_ctx(dc->hwseq, dc, &dc->vm_pa_config); } - /*mark d0 last*/ - dc->power_state = power_state; break; default: ASSERT(dc->current_state->stream_count == 0); - /*mark d3 first*/ - dc->power_state = power_state; dc_dmub_srv_notify_fw_dc_power_state(dc->ctx->dmub_srv, power_state); dc_state_destruct(dc->current_state); @@ -5446,6 +5512,11 @@ bool dc_set_ips_disable(struct dc *dc, unsigned int disable_ips) void dc_allow_idle_optimizations_internal(struct dc *dc, bool allow, char const *caller_name) { + int idle_fclk_khz = 0, idle_dramclk_khz = 0, i = 0; + enum mall_stream_type subvp_pipe_type[MAX_PIPES] = {0}; + struct pipe_ctx *pipe = NULL; + struct dc_state *context = dc->current_state; + if (dc->debug.disable_idle_power_optimizations) { DC_LOG_DEBUG("%s: disabled\n", __func__); return; @@ -5470,6 +5541,23 @@ void dc_allow_idle_optimizations_internal(struct dc *dc, bool allow, char const dc->idle_optimizations_allowed = allow; DC_LOG_DEBUG("%s: %s\n", __func__, allow ? "enabled" : "disabled"); } + + // log idle clocks and sub vp pipe types at idle optimization time + if (dc->clk_mgr != NULL && dc->clk_mgr->funcs->get_hard_min_fclk) + idle_fclk_khz = dc->clk_mgr->funcs->get_hard_min_fclk(dc->clk_mgr); + + if (dc->clk_mgr != NULL && dc->clk_mgr->funcs->get_hard_min_memclk) + idle_dramclk_khz = dc->clk_mgr->funcs->get_hard_min_memclk(dc->clk_mgr); + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + subvp_pipe_type[i] = dc_state_get_pipe_subvp_type(context, pipe); + } + + DC_LOG_DC("%s: allow_idle=%d\n HardMinUClk_Khz=%d HardMinDramclk_Khz=%d\n Pipe_0=%d Pipe_1=%d Pipe_2=%d Pipe_3=%d Pipe_4=%d Pipe_5=%d (caller=%s)\n", + __func__, allow, idle_fclk_khz, idle_dramclk_khz, subvp_pipe_type[0], subvp_pipe_type[1], subvp_pipe_type[2], + subvp_pipe_type[3], subvp_pipe_type[4], subvp_pipe_type[5], caller_name); + } void dc_exit_ips_for_hw_access_internal(struct dc *dc, const char *caller_name) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c index 252af83e34a5..6eb9bae3af91 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c @@ -425,6 +425,44 @@ void get_hdr_visual_confirm_color( } } +/* Visual Confirm color definition for VABC */ +void get_vabc_visual_confirm_color( + struct pipe_ctx *pipe_ctx, + struct tg_color *color) +{ + uint32_t color_value = MAX_TG_COLOR_VALUE; + struct dc_link *edp_link = NULL; + + if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link) { + if (pipe_ctx->stream->link->connector_signal == SIGNAL_TYPE_EDP) + edp_link = pipe_ctx->stream->link; + } + + if (edp_link) { + switch (edp_link->backlight_control_type) { + case BACKLIGHT_CONTROL_PWM: + color->color_r_cr = color_value; + color->color_g_y = 0; + color->color_b_cb = 0; + break; + case BACKLIGHT_CONTROL_AMD_AUX: + color->color_r_cr = 0; + color->color_g_y = color_value; + color->color_b_cb = 0; + break; + case BACKLIGHT_CONTROL_VESA_AUX: + color->color_r_cr = 0; + color->color_g_y = 0; + color->color_b_cb = color_value; + break; + } + } else { + color->color_r_cr = 0; + color->color_g_y = 0; + color->color_b_cb = 0; + } +} + void get_subvp_visual_confirm_color( struct pipe_ctx *pipe_ctx, struct tg_color *color) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c index 457d60eeb486..c1b79b379447 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c @@ -125,6 +125,14 @@ uint32_t dc_link_bandwidth_kbps( return link->dc->link_srv->dp_link_bandwidth_kbps(link, link_settings); } +uint32_t dc_link_required_hblank_size_bytes( + const struct dc_link *link, + struct dp_audio_bandwidth_params *audio_params) +{ + return link->dc->link_srv->dp_required_hblank_size_bytes(link, + audio_params); +} + void dc_get_cur_link_res_map(const struct dc *dc, uint32_t *map) { dc->link_srv->get_cur_res_map(dc, map); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 626f75b6ad00..520a34a42827 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -4478,7 +4478,7 @@ static void set_hfvs_info_packet( static void adaptive_sync_override_dp_info_packets_sdp_line_num( const struct dc_crtc_timing *timing, struct enc_sdp_line_num *sdp_line_num, - struct _vcs_dpi_display_pipe_dest_params_st *pipe_dlg_param) + unsigned int vstartup_start) { uint32_t asic_blank_start = 0; uint32_t asic_blank_end = 0; @@ -4493,8 +4493,8 @@ static void adaptive_sync_override_dp_info_packets_sdp_line_num( asic_blank_end = (asic_blank_start - tg->v_border_bottom - tg->v_addressable - tg->v_border_top); - if (pipe_dlg_param->vstartup_start > asic_blank_end) { - v_update = (tg->v_total - (pipe_dlg_param->vstartup_start - asic_blank_end)); + if (vstartup_start > asic_blank_end) { + v_update = (tg->v_total - (vstartup_start - asic_blank_end)); sdp_line_num->adaptive_sync_line_num_valid = true; sdp_line_num->adaptive_sync_line_num = (tg->v_total - v_update - 1); } else { @@ -4507,7 +4507,7 @@ static void set_adaptive_sync_info_packet( struct dc_info_packet *info_packet, const struct dc_stream_state *stream, struct encoder_info_frame *info_frame, - struct _vcs_dpi_display_pipe_dest_params_st *pipe_dlg_param) + unsigned int vstartup_start) { if (!stream->adaptive_sync_infopacket.valid) return; @@ -4515,7 +4515,7 @@ static void set_adaptive_sync_info_packet( adaptive_sync_override_dp_info_packets_sdp_line_num( &stream->timing, &info_frame->sdp_line_num, - pipe_dlg_param); + vstartup_start); *info_packet = stream->adaptive_sync_infopacket; } @@ -4548,6 +4548,7 @@ void resource_build_info_frame(struct pipe_ctx *pipe_ctx) { enum signal_type signal = SIGNAL_TYPE_NONE; struct encoder_info_frame *info = &pipe_ctx->stream_res.encoder_info_frame; + unsigned int vstartup_start = 0; /* default all packets to invalid */ info->avi.valid = false; @@ -4561,6 +4562,9 @@ void resource_build_info_frame(struct pipe_ctx *pipe_ctx) info->adaptive_sync.valid = false; signal = pipe_ctx->stream->signal; + if (pipe_ctx->stream->ctx->dc->res_pool->funcs->get_vstartup_for_pipe) + vstartup_start = pipe_ctx->stream->ctx->dc->res_pool->funcs->get_vstartup_for_pipe(pipe_ctx); + /* HDMi and DP have different info packets*/ if (dc_is_hdmi_signal(signal)) { set_avi_info_frame(&info->avi, pipe_ctx); @@ -4582,7 +4586,7 @@ void resource_build_info_frame(struct pipe_ctx *pipe_ctx) set_adaptive_sync_info_packet(&info->adaptive_sync, pipe_ctx->stream, info, - &pipe_ctx->pipe_dlg_param); + vstartup_start); } patch_gamut_packet_checksum(&info->gamut); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index e006f816ff2f..1b2cce127981 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -483,9 +483,9 @@ bool dc_state_add_plane( if (stream_status == NULL) { dm_error("Existing stream not found; failed to attach surface!\n"); goto out; - } else if (stream_status->plane_count == MAX_SURFACE_NUM) { + } else if (stream_status->plane_count == MAX_SURFACES) { dm_error("Surface: can not attach plane_state %p! Maximum is: %d\n", - plane_state, MAX_SURFACE_NUM); + plane_state, MAX_SURFACES); goto out; } else if (!otg_master_pipe) { goto out; @@ -600,7 +600,7 @@ bool dc_state_rem_all_planes_for_stream( { int i, old_plane_count; struct dc_stream_status *stream_status = NULL; - struct dc_plane_state *del_planes[MAX_SURFACE_NUM] = { 0 }; + struct dc_plane_state *del_planes[MAX_SURFACES] = { 0 }; for (i = 0; i < state->stream_count; i++) if (state->streams[i] == stream) { @@ -875,7 +875,7 @@ bool dc_state_rem_all_phantom_planes_for_stream( { int i, old_plane_count; struct dc_stream_status *stream_status = NULL; - struct dc_plane_state *del_planes[MAX_SURFACE_NUM] = { 0 }; + struct dc_plane_state *del_planes[MAX_SURFACES] = { 0 }; for (i = 0; i < state->stream_count; i++) if (state->streams[i] == phantom_stream) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 701b7e4f2920..e8134c47fe0d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -37,6 +37,8 @@ #define DC_LOGGER dc->ctx->logger #ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#endif +#ifndef MAX #define MAX(x, y) ((x > y) ? x : y) #endif diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 8c6347413038..053481ab69ef 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -55,9 +55,9 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.314" +#define DC_VER "3.2.316" -#define MAX_SURFACES 3 +#define MAX_SURFACES 4 #define MAX_PLANES 6 #define MAX_STREAMS 6 #define MIN_VIEWPORT_SIZE 12 @@ -472,6 +472,7 @@ struct dc_config { bool disable_hbr_audio_dp2; bool consolidated_dpia_dp_lt; bool set_pipe_unlock_order; + bool enable_dpia_pre_training; }; enum visual_confirm { @@ -488,6 +489,7 @@ enum visual_confirm { VISUAL_CONFIRM_MCLK_SWITCH = 16, VISUAL_CONFIRM_FAMS2 = 19, VISUAL_CONFIRM_HW_CURSOR = 20, + VISUAL_CONFIRM_VABC = 21, }; enum dc_psr_power_opts { @@ -775,7 +777,8 @@ union dpia_debug_options { uint32_t enable_force_tbt3_work_around:1; /* bit 4 */ uint32_t disable_usb4_pm_support:1; /* bit 5 */ uint32_t enable_consolidated_dpia_dp_lt:1; /* bit 6 */ - uint32_t reserved:25; + uint32_t enable_dpia_pre_training:1; /* bit 7 */ + uint32_t reserved:24; } bits; uint32_t raw; }; @@ -1060,7 +1063,6 @@ struct dc_debug_options { uint32_t dml21_disable_pstate_method_mask; union fw_assisted_mclk_switch_version fams_version; union dmub_fams2_global_feature_config fams2_config; - bool enable_legacy_clock_update; unsigned int force_cositing; unsigned int disable_spl; unsigned int force_easf; @@ -1305,7 +1307,7 @@ struct dc_plane_state { struct rect clip_rect; struct plane_size plane_size; - union dc_tiling_info tiling_info; + struct dc_tiling_info tiling_info; struct dc_plane_dcc_param dcc; @@ -1376,7 +1378,7 @@ struct dc_plane_state { struct dc_plane_info { struct plane_size plane_size; - union dc_tiling_info tiling_info; + struct dc_tiling_info tiling_info; struct dc_plane_dcc_param dcc; enum surface_pixel_format format; enum dc_rotation_angle rotation; @@ -1403,7 +1405,7 @@ struct dc_scratch_space { * store current value in plane states so we can still recover * a valid current state during dc update. */ - struct dc_plane_state plane_states[MAX_SURFACE_NUM]; + struct dc_plane_state plane_states[MAX_SURFACES]; struct dc_stream_state stream_state; }; @@ -2025,6 +2027,24 @@ uint32_t dc_link_bandwidth_kbps( const struct dc_link *link, const struct dc_link_settings *link_setting); +struct dp_audio_bandwidth_params { + const struct dc_crtc_timing *crtc_timing; + enum dp_link_encoding link_encoding; + uint32_t channel_count; + uint32_t sample_rate_hz; +}; + +/* The function calculates the minimum size of hblank (in bytes) needed to + * support the specified channel count and sample rate combination, given the + * link encoding and timing to be used. This calculation is not supported + * for 8b/10b SST. + * + * return - min hblank size in bytes, 0 if 8b/10b SST. + */ +uint32_t dc_link_required_hblank_size_bytes( + const struct dc_link *link, + struct dp_audio_bandwidth_params *audio_params); + /* The function takes a snapshot of current link resource allocation state * @dc: pointer to dc of the dm calling this * @map: a dc link resource snapshot defined internally to dc. @@ -2384,6 +2404,13 @@ struct dc_sink_dsc_caps { struct dsc_dec_dpcd_caps dsc_dec_caps; }; +struct dc_sink_hblank_expansion_caps { + // 'true' if these are virtual DPCD's HBlank expansion caps (immediately upstream of sink in MST topology), + // 'false' if they are sink's HBlank expansion caps + bool is_virtual_dpcd_hblank_expansion; + struct hblank_expansion_dpcd_caps dpcd_caps; +}; + struct dc_sink_fec_caps { bool is_rx_fec_supported; bool is_topology_fec_supported; @@ -2410,6 +2437,7 @@ struct dc_sink { struct scdc_caps scdc_caps; struct dc_sink_dsc_caps dsc_caps; struct dc_sink_fec_caps fec_caps; + struct dc_sink_hblank_expansion_caps hblank_expansion_caps; bool is_vsc_sdp_colorimetry_supported; diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index 8dd6eb044829..94ce8fe74481 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -969,6 +969,21 @@ union dp_sink_video_fallback_formats { uint8_t raw; }; +union dp_receive_port0_cap { + struct { + uint8_t RESERVED :1; + uint8_t LOCAL_EDID_PRESENT :1; + uint8_t ASSOCIATED_TO_PRECEDING_PORT:1; + uint8_t HBLANK_EXPANSION_CAPABLE :1; + uint8_t BUFFER_SIZE_UNIT :1; + uint8_t BUFFER_SIZE_PER_PORT :1; + uint8_t HBLANK_REDUCTION_CAPABLE :1; + uint8_t RESERVED2:1; + uint8_t BUFFER_SIZE:8; + } bits; + uint8_t raw[2]; +}; + union dpcd_max_uncompressed_pixel_rate_cap { struct { uint16_t max_uncompressed_pixel_rate_cap :15; @@ -1193,6 +1208,7 @@ struct dpcd_caps { struct replay_info pr_info; uint16_t edp_oled_emission_rate; + union dp_receive_port0_cap receive_port0_cap; }; union dpcd_sink_ext_caps { diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h index 9014c2409817..9d18f1c08079 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h @@ -94,6 +94,11 @@ uint32_t dc_dsc_stream_bandwidth_overhead_in_kbps( const int num_slices_h, const bool is_dp); +void dc_dsc_dump_decoder_caps(const struct display_stream_compressor *dsc, + const struct dsc_dec_dpcd_caps *dsc_sink_caps); +void dc_dsc_dump_encoder_caps(const struct display_stream_compressor *dsc, + const struct dc_crtc_timing *timing); + /* TODO - Hardware/specs limitation should be owned by dc dsc and returned to DM, * and DM can choose to OVERRIDE the limitation on CASE BY CASE basis. * Hardware/specs limitation should not be writable by DM. diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index c10567ec1c81..5ac55601a6da 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -341,89 +341,101 @@ enum swizzle_mode_addr3_values { DC_ADDR3_SW_UNKNOWN = DC_ADDR3_SW_MAX }; -union dc_tiling_info { +enum dc_gfxversion { + DcGfxVersion7 = 0, + DcGfxVersion8, + DcGfxVersion9, + DcGfxVersion10, + DcGfxVersion11, + DcGfxAddr3, + DcGfxVersionUnknown +}; - struct { - /* Specifies the number of memory banks for tiling - * purposes. - * Only applies to 2D and 3D tiling modes. - * POSSIBLE VALUES: 2,4,8,16 - */ - unsigned int num_banks; - /* Specifies the number of tiles in the x direction - * to be incorporated into the same bank. - * Only applies to 2D and 3D tiling modes. - * POSSIBLE VALUES: 1,2,4,8 - */ - unsigned int bank_width; - unsigned int bank_width_c; - /* Specifies the number of tiles in the y direction to - * be incorporated into the same bank. - * Only applies to 2D and 3D tiling modes. - * POSSIBLE VALUES: 1,2,4,8 - */ - unsigned int bank_height; - unsigned int bank_height_c; - /* Specifies the macro tile aspect ratio. Only applies - * to 2D and 3D tiling modes. - */ - unsigned int tile_aspect; - unsigned int tile_aspect_c; - /* Specifies the number of bytes that will be stored - * contiguously for each tile. - * If the tile data requires more storage than this - * amount, it is split into multiple slices. - * This field must not be larger than - * GB_ADDR_CONFIG.DRAM_ROW_SIZE. - * Only applies to 2D and 3D tiling modes. - * For color render targets, TILE_SPLIT >= 256B. - */ - enum tile_split_values tile_split; - enum tile_split_values tile_split_c; - /* Specifies the addressing within a tile. - * 0x0 - DISPLAY_MICRO_TILING - * 0x1 - THIN_MICRO_TILING - * 0x2 - DEPTH_MICRO_TILING - * 0x3 - ROTATED_MICRO_TILING - */ - enum tile_mode_values tile_mode; - enum tile_mode_values tile_mode_c; - /* Specifies the number of pipes and how they are - * interleaved in the surface. - * Refer to memory addressing document for complete - * details and constraints. - */ - unsigned int pipe_config; - /* Specifies the tiling mode of the surface. - * THIN tiles use an 8x8x1 tile size. - * THICK tiles use an 8x8x4 tile size. - * 2D tiling modes rotate banks for successive Z slices - * 3D tiling modes rotate pipes and banks for Z slices - * Refer to memory addressing document for complete - * details and constraints. - */ - enum array_mode_values array_mode; - } gfx8; + struct dc_tiling_info { + unsigned int gfxversion; // Specifies which part of the union to use. Must use DalGfxVersion enum + union { + struct { + /* Specifies the number of memory banks for tiling + * purposes. + * Only applies to 2D and 3D tiling modes. + * POSSIBLE VALUES: 2,4,8,16 + */ + unsigned int num_banks; + /* Specifies the number of tiles in the x direction + * to be incorporated into the same bank. + * Only applies to 2D and 3D tiling modes. + * POSSIBLE VALUES: 1,2,4,8 + */ + unsigned int bank_width; + unsigned int bank_width_c; + /* Specifies the number of tiles in the y direction to + * be incorporated into the same bank. + * Only applies to 2D and 3D tiling modes. + * POSSIBLE VALUES: 1,2,4,8 + */ + unsigned int bank_height; + unsigned int bank_height_c; + /* Specifies the macro tile aspect ratio. Only applies + * to 2D and 3D tiling modes. + */ + unsigned int tile_aspect; + unsigned int tile_aspect_c; + /* Specifies the number of bytes that will be stored + * contiguously for each tile. + * If the tile data requires more storage than this + * amount, it is split into multiple slices. + * This field must not be larger than + * GB_ADDR_CONFIG.DRAM_ROW_SIZE. + * Only applies to 2D and 3D tiling modes. + * For color render targets, TILE_SPLIT >= 256B. + */ + enum tile_split_values tile_split; + enum tile_split_values tile_split_c; + /* Specifies the addressing within a tile. + * 0x0 - DISPLAY_MICRO_TILING + * 0x1 - THIN_MICRO_TILING + * 0x2 - DEPTH_MICRO_TILING + * 0x3 - ROTATED_MICRO_TILING + */ + enum tile_mode_values tile_mode; + enum tile_mode_values tile_mode_c; + /* Specifies the number of pipes and how they are + * interleaved in the surface. + * Refer to memory addressing document for complete + * details and constraints. + */ + unsigned int pipe_config; + /* Specifies the tiling mode of the surface. + * THIN tiles use an 8x8x1 tile size. + * THICK tiles use an 8x8x4 tile size. + * 2D tiling modes rotate banks for successive Z slices + * 3D tiling modes rotate pipes and banks for Z slices + * Refer to memory addressing document for complete + * details and constraints. + */ + enum array_mode_values array_mode; + } gfx8; - struct { - enum swizzle_mode_values swizzle; - unsigned int num_pipes; - unsigned int max_compressed_frags; - unsigned int pipe_interleave; + struct { + enum swizzle_mode_values swizzle; + unsigned int num_pipes; + unsigned int max_compressed_frags; + unsigned int pipe_interleave; - unsigned int num_banks; - unsigned int num_shader_engines; - unsigned int num_rb_per_se; - bool shaderEnable; + unsigned int num_banks; + unsigned int num_shader_engines; + unsigned int num_rb_per_se; + bool shaderEnable; - bool meta_linear; - bool rb_aligned; - bool pipe_aligned; - unsigned int num_pkrs; - } gfx9;/*gfx9, gfx10 and above*/ - struct { - enum swizzle_mode_addr3_values swizzle; - } gfx_addr3;/*gfx with addr3 and above*/ + bool meta_linear; + bool rb_aligned; + bool pipe_aligned; + unsigned int num_pkrs; + } gfx9;/*gfx9, gfx10 and above*/ + struct { + enum swizzle_mode_addr3_values swizzle; + } gfx_addr3;/*gfx with addr3 and above*/ + }; }; /* Rotation angle */ @@ -975,6 +987,9 @@ struct dc_crtc_timing { struct dc_crtc_timing_flags flags; uint32_t dsc_fixed_bits_per_pixel_x16; /* DSC target bitrate in 1/16 of bpp (e.g. 128 -> 8bpp) */ struct dc_dsc_config dsc_cfg; + + /* The number of pixels that HBlank has been expanded by from the original EDID timing. */ + uint32_t expanded_hblank; }; enum trigger_delay { diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 713884103aea..3e303c7808fb 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -56,7 +56,7 @@ struct dc_stream_status { int plane_count; int audio_inst; struct timing_sync_info timing_sync_info; - struct dc_plane_state *plane_states[MAX_SURFACE_NUM]; + struct dc_plane_state *plane_states[MAX_SURFACES]; bool is_abm_supported; struct mall_stream_config mall_stream_config; bool fpo_in_use; @@ -539,16 +539,24 @@ bool dc_stream_forward_crc_window(struct dc_stream_state *stream, struct rect *rect, uint8_t phy_id, bool is_stop); + +bool dc_stream_forward_multiple_crc_window(struct dc_stream_state *stream, + struct crc_window *window, + uint8_t phy_id, + bool stop); #endif bool dc_stream_configure_crc(struct dc *dc, struct dc_stream_state *stream, struct crc_params *crc_window, bool enable, - bool continuous); + bool continuous, + uint8_t idx, + bool reset); bool dc_stream_get_crc(struct dc *dc, struct dc_stream_state *stream, + uint8_t idx, uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb); diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index edf4df1d03b5..0c2aa91f0a11 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -76,7 +76,6 @@ struct dc_perf_trace { unsigned long last_entry_write; }; -#define MAX_SURFACE_NUM 6 #define NUM_PIXEL_FORMATS 10 enum tiling_mode { @@ -875,6 +874,14 @@ struct dsc_dec_dpcd_caps { bool is_dp; /* Decoded format */ }; +struct hblank_expansion_dpcd_caps { + bool expansion_supported; + bool reduction_supported; + bool buffer_unit_bytes; /* True: buffer size in bytes. False: buffer size in pixels*/ + bool buffer_per_port; /* True: buffer size per port. False: buffer size per lane*/ + uint32_t buffer_size; /* Add 1 to value and multiply by 32 */ +}; + struct dc_golden_table { uint16_t dc_golden_table_ver; uint32_t aux_dphy_rx_control0_val; @@ -932,10 +939,17 @@ enum backlight_control_type { }; #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) +#define MAX_CRC_WINDOW_NUM 2 + struct otg_phy_mux { uint8_t phy_output_num; uint8_t otg_output_num; }; + +struct crc_window { + struct rect rect; + bool enable; +}; #endif enum dc_detect_reason { @@ -1052,10 +1066,13 @@ enum replay_FW_Message_type { union replay_error_status { struct { - unsigned char STATE_TRANSITION_ERROR :1; - unsigned char LINK_CRC_ERROR :1; - unsigned char DESYNC_ERROR :1; - unsigned char RESERVED :5; + unsigned int STATE_TRANSITION_ERROR :1; + unsigned int LINK_CRC_ERROR :1; + unsigned int DESYNC_ERROR :1; + unsigned int RESERVED_3 :1; + unsigned int LOW_RR_INCORRECT_VTOTAL :1; + unsigned int NO_DOUBLED_RR :1; + unsigned int RESERVED_6_7 :2; } bits; unsigned char raw; }; @@ -1102,6 +1119,8 @@ struct replay_config { union replay_error_status replay_error_status; /* Replay Low Hz enable Options */ union replay_low_refresh_rate_enable_options low_rr_enable_options; + /* Replay coasting vtotal is within low refresh rate range. */ + bool low_rr_activated; }; /* Replay feature flags*/ @@ -1126,10 +1145,12 @@ struct replay_settings { uint32_t defer_update_coasting_vtotal_table[PR_COASTING_TYPE_NUM]; /* Maximum link off frame count */ uint32_t link_off_frame_count; - /* Replay pseudo vtotal for abm + ips on full screen video which can improve ips residency */ - uint16_t abm_with_ips_on_full_screen_video_pseudo_vtotal; + /* Replay pseudo vtotal for low refresh rate*/ + uint16_t low_rr_full_screen_video_pseudo_vtotal; /* Replay last pseudo vtotal set to DMUB */ uint16_t last_pseudo_vtotal; + /* Replay desync error */ + uint32_t replay_desync_error_fail_count; }; /* To split out "global" and "per-panel" config settings. diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c index ebd174be5786..1c2009e38aa1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c @@ -98,7 +98,7 @@ static enum mi_bits_per_pixel get_mi_bpp( } static enum mi_tiling_format get_mi_tiling( - union dc_tiling_info *tiling_info) + struct dc_tiling_info *tiling_info) { switch (tiling_info->gfx8.array_mode) { case DC_ARRAY_1D_TILED_THIN1: @@ -133,7 +133,7 @@ static bool is_vert_scan(enum dc_rotation_angle rotation) static void dce_mi_program_pte_vm( struct mem_input *mi, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, enum dc_rotation_angle rotation) { struct dce_mem_input *dce_mi = TO_DCE_MEM_INPUT(mi); @@ -430,7 +430,7 @@ static void dce120_mi_program_display_marks(struct mem_input *mi, } static void program_tiling( - struct dce_mem_input *dce_mi, const union dc_tiling_info *info) + struct dce_mem_input *dce_mi, const struct dc_tiling_info *info) { if (dce_mi->masks->GRPH_SW_MODE) { /* GFX9 */ REG_UPDATE_6(GRPH_CONTROL, @@ -650,7 +650,7 @@ static void dce_mi_clear_tiling( static void dce_mi_program_surface_config( struct mem_input *mi, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -670,7 +670,7 @@ static void dce_mi_program_surface_config( static void dce60_mi_program_surface_config( struct mem_input *mi, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, /* not used in DCE6 */ struct dc_plane_dcc_param *dcc, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c index bf636b28e3e1..5bb8b78bf250 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c @@ -63,7 +63,8 @@ void dmub_hw_lock_mgr_inbox0_cmd(struct dc_dmub_srv *dmub_srv, bool should_use_dmub_lock(struct dc_link *link) { - if (link->psr_settings.psr_version == DC_PSR_VERSION_SU_1) + if (link->psr_settings.psr_version == DC_PSR_VERSION_SU_1 || + link->psr_settings.psr_version == DC_PSR_VERSION_1) return true; if (link->replay_settings.replay_feature_enabled) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c index 8a3fbf95c48f..2c43c2422638 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c @@ -162,7 +162,7 @@ static void enable(struct dce_mem_input *mem_input110) static void program_tiling( struct dce_mem_input *mem_input110, - const union dc_tiling_info *info, + const struct dc_tiling_info *info, const enum surface_pixel_format pixel_format) { uint32_t value = 0; @@ -523,7 +523,7 @@ static const unsigned int dvmm_Hw_Setting_Linear[4][9] = { /* Helper to get table entry from surface info */ static const unsigned int *get_dvmm_hw_setting( - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, enum surface_pixel_format format, bool chroma) { @@ -563,7 +563,7 @@ static const unsigned int *get_dvmm_hw_setting( static void dce_mem_input_v_program_pte_vm( struct mem_input *mem_input, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, enum dc_rotation_angle rotation) { struct dce_mem_input *mem_input110 = TO_DCE_MEM_INPUT(mem_input); @@ -636,7 +636,7 @@ static void dce_mem_input_v_program_pte_vm( static void dce_mem_input_v_program_surface_config( struct mem_input *mem_input, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c index fa422a8cbced..61b0807693fb 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c @@ -2127,70 +2127,131 @@ bool dce110_configure_crc(struct timing_generator *tg, cntl_addr = CRTC_REG(mmCRTC_CRC_CNTL); - /* First, disable CRC before we configure it. */ - dm_write_reg(tg->ctx, cntl_addr, 0); + if (!params->enable || params->reset) + /* First, disable CRC before we configure it. */ + dm_write_reg(tg->ctx, cntl_addr, 0); if (!params->enable) return true; /* Program frame boundaries */ - /* Window A x axis start and end. */ - value = 0; - addr = CRTC_REG(mmCRTC_CRC0_WINDOWA_X_CONTROL); - set_reg_field_value(value, params->windowa_x_start, - CRTC_CRC0_WINDOWA_X_CONTROL, - CRTC_CRC0_WINDOWA_X_START); - set_reg_field_value(value, params->windowa_x_end, - CRTC_CRC0_WINDOWA_X_CONTROL, - CRTC_CRC0_WINDOWA_X_END); - dm_write_reg(tg->ctx, addr, value); + switch (params->crc_eng_inst) { + case 0: + /* Window A x axis start and end. */ + value = 0; + addr = CRTC_REG(mmCRTC_CRC0_WINDOWA_X_CONTROL); + set_reg_field_value(value, params->windowa_x_start, + CRTC_CRC0_WINDOWA_X_CONTROL, + CRTC_CRC0_WINDOWA_X_START); + set_reg_field_value(value, params->windowa_x_end, + CRTC_CRC0_WINDOWA_X_CONTROL, + CRTC_CRC0_WINDOWA_X_END); + dm_write_reg(tg->ctx, addr, value); - /* Window A y axis start and end. */ - value = 0; - addr = CRTC_REG(mmCRTC_CRC0_WINDOWA_Y_CONTROL); - set_reg_field_value(value, params->windowa_y_start, - CRTC_CRC0_WINDOWA_Y_CONTROL, - CRTC_CRC0_WINDOWA_Y_START); - set_reg_field_value(value, params->windowa_y_end, - CRTC_CRC0_WINDOWA_Y_CONTROL, - CRTC_CRC0_WINDOWA_Y_END); - dm_write_reg(tg->ctx, addr, value); + /* Window A y axis start and end. */ + value = 0; + addr = CRTC_REG(mmCRTC_CRC0_WINDOWA_Y_CONTROL); + set_reg_field_value(value, params->windowa_y_start, + CRTC_CRC0_WINDOWA_Y_CONTROL, + CRTC_CRC0_WINDOWA_Y_START); + set_reg_field_value(value, params->windowa_y_end, + CRTC_CRC0_WINDOWA_Y_CONTROL, + CRTC_CRC0_WINDOWA_Y_END); + dm_write_reg(tg->ctx, addr, value); - /* Window B x axis start and end. */ - value = 0; - addr = CRTC_REG(mmCRTC_CRC0_WINDOWB_X_CONTROL); - set_reg_field_value(value, params->windowb_x_start, - CRTC_CRC0_WINDOWB_X_CONTROL, - CRTC_CRC0_WINDOWB_X_START); - set_reg_field_value(value, params->windowb_x_end, - CRTC_CRC0_WINDOWB_X_CONTROL, - CRTC_CRC0_WINDOWB_X_END); - dm_write_reg(tg->ctx, addr, value); + /* Window B x axis start and end. */ + value = 0; + addr = CRTC_REG(mmCRTC_CRC0_WINDOWB_X_CONTROL); + set_reg_field_value(value, params->windowb_x_start, + CRTC_CRC0_WINDOWB_X_CONTROL, + CRTC_CRC0_WINDOWB_X_START); + set_reg_field_value(value, params->windowb_x_end, + CRTC_CRC0_WINDOWB_X_CONTROL, + CRTC_CRC0_WINDOWB_X_END); + dm_write_reg(tg->ctx, addr, value); - /* Window B y axis start and end. */ - value = 0; - addr = CRTC_REG(mmCRTC_CRC0_WINDOWB_Y_CONTROL); - set_reg_field_value(value, params->windowb_y_start, - CRTC_CRC0_WINDOWB_Y_CONTROL, - CRTC_CRC0_WINDOWB_Y_START); - set_reg_field_value(value, params->windowb_y_end, - CRTC_CRC0_WINDOWB_Y_CONTROL, - CRTC_CRC0_WINDOWB_Y_END); - dm_write_reg(tg->ctx, addr, value); + /* Window B y axis start and end. */ + value = 0; + addr = CRTC_REG(mmCRTC_CRC0_WINDOWB_Y_CONTROL); + set_reg_field_value(value, params->windowb_y_start, + CRTC_CRC0_WINDOWB_Y_CONTROL, + CRTC_CRC0_WINDOWB_Y_START); + set_reg_field_value(value, params->windowb_y_end, + CRTC_CRC0_WINDOWB_Y_CONTROL, + CRTC_CRC0_WINDOWB_Y_END); + dm_write_reg(tg->ctx, addr, value); - /* Set crc mode and selection, and enable. Only using CRC0*/ - value = 0; - set_reg_field_value(value, params->continuous_mode ? 1 : 0, - CRTC_CRC_CNTL, CRTC_CRC_CONT_EN); - set_reg_field_value(value, params->selection, - CRTC_CRC_CNTL, CRTC_CRC0_SELECT); - set_reg_field_value(value, 1, CRTC_CRC_CNTL, CRTC_CRC_EN); - dm_write_reg(tg->ctx, cntl_addr, value); + /* Set crc mode and selection, and enable.*/ + value = 0; + set_reg_field_value(value, params->continuous_mode ? 1 : 0, + CRTC_CRC_CNTL, CRTC_CRC_CONT_EN); + set_reg_field_value(value, params->selection, + CRTC_CRC_CNTL, CRTC_CRC0_SELECT); + set_reg_field_value(value, 1, CRTC_CRC_CNTL, CRTC_CRC_EN); + dm_write_reg(tg->ctx, cntl_addr, value); + break; + case 1: + /* Window A x axis start and end. */ + value = 0; + addr = CRTC_REG(mmCRTC_CRC1_WINDOWA_X_CONTROL); + set_reg_field_value(value, params->windowa_x_start, + CRTC_CRC1_WINDOWA_X_CONTROL, + CRTC_CRC1_WINDOWA_X_START); + set_reg_field_value(value, params->windowa_x_end, + CRTC_CRC1_WINDOWA_X_CONTROL, + CRTC_CRC1_WINDOWA_X_END); + dm_write_reg(tg->ctx, addr, value); + + /* Window A y axis start and end. */ + value = 0; + addr = CRTC_REG(mmCRTC_CRC1_WINDOWA_Y_CONTROL); + set_reg_field_value(value, params->windowa_y_start, + CRTC_CRC1_WINDOWA_Y_CONTROL, + CRTC_CRC1_WINDOWA_Y_START); + set_reg_field_value(value, params->windowa_y_end, + CRTC_CRC1_WINDOWA_Y_CONTROL, + CRTC_CRC1_WINDOWA_Y_END); + dm_write_reg(tg->ctx, addr, value); + + /* Window B x axis start and end. */ + value = 0; + addr = CRTC_REG(mmCRTC_CRC1_WINDOWB_X_CONTROL); + set_reg_field_value(value, params->windowb_x_start, + CRTC_CRC1_WINDOWB_X_CONTROL, + CRTC_CRC1_WINDOWB_X_START); + set_reg_field_value(value, params->windowb_x_end, + CRTC_CRC1_WINDOWB_X_CONTROL, + CRTC_CRC1_WINDOWB_X_END); + dm_write_reg(tg->ctx, addr, value); + + /* Window B y axis start and end. */ + value = 0; + addr = CRTC_REG(mmCRTC_CRC1_WINDOWB_Y_CONTROL); + set_reg_field_value(value, params->windowb_y_start, + CRTC_CRC1_WINDOWB_Y_CONTROL, + CRTC_CRC1_WINDOWB_Y_START); + set_reg_field_value(value, params->windowb_y_end, + CRTC_CRC1_WINDOWB_Y_CONTROL, + CRTC_CRC1_WINDOWB_Y_END); + dm_write_reg(tg->ctx, addr, value); + + /* Set crc mode and selection, and enable.*/ + value = 0; + set_reg_field_value(value, params->continuous_mode ? 1 : 0, + CRTC_CRC_CNTL, CRTC_CRC_CONT_EN); + set_reg_field_value(value, params->selection, + CRTC_CRC_CNTL, CRTC_CRC1_SELECT); + set_reg_field_value(value, 1, CRTC_CRC_CNTL, CRTC_CRC_EN); + dm_write_reg(tg->ctx, cntl_addr, value); + break; + default: + return false; + } return true; } -bool dce110_get_crc(struct timing_generator *tg, +bool dce110_get_crc(struct timing_generator *tg, uint8_t idx, uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb) { uint32_t addr = 0; @@ -2206,14 +2267,30 @@ bool dce110_get_crc(struct timing_generator *tg, if (!field) return false; - addr = CRTC_REG(mmCRTC_CRC0_DATA_RG); - value = dm_read_reg(tg->ctx, addr); - *r_cr = get_reg_field_value(value, CRTC_CRC0_DATA_RG, CRC0_R_CR); - *g_y = get_reg_field_value(value, CRTC_CRC0_DATA_RG, CRC0_G_Y); + switch (idx) { + case 0: + addr = CRTC_REG(mmCRTC_CRC0_DATA_RG); + value = dm_read_reg(tg->ctx, addr); + *r_cr = get_reg_field_value(value, CRTC_CRC0_DATA_RG, CRC0_R_CR); + *g_y = get_reg_field_value(value, CRTC_CRC0_DATA_RG, CRC0_G_Y); - addr = CRTC_REG(mmCRTC_CRC0_DATA_B); - value = dm_read_reg(tg->ctx, addr); - *b_cb = get_reg_field_value(value, CRTC_CRC0_DATA_B, CRC0_B_CB); + addr = CRTC_REG(mmCRTC_CRC0_DATA_B); + value = dm_read_reg(tg->ctx, addr); + *b_cb = get_reg_field_value(value, CRTC_CRC0_DATA_B, CRC0_B_CB); + break; + case 1: + addr = CRTC_REG(mmCRTC_CRC1_DATA_RG); + value = dm_read_reg(tg->ctx, addr); + *r_cr = get_reg_field_value(value, CRTC_CRC1_DATA_RG, CRC1_R_CR); + *g_y = get_reg_field_value(value, CRTC_CRC1_DATA_RG, CRC1_G_Y); + + addr = CRTC_REG(mmCRTC_CRC1_DATA_B); + value = dm_read_reg(tg->ctx, addr); + *b_cb = get_reg_field_value(value, CRTC_CRC1_DATA_B, CRC1_B_CB); + break; + default: + return false; + } return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h index ee4de740aceb..e4f5cad64f32 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h @@ -286,7 +286,7 @@ bool dce110_arm_vert_intr( bool dce110_configure_crc(struct timing_generator *tg, const struct crc_params *params); -bool dce110_get_crc(struct timing_generator *tg, +bool dce110_get_crc(struct timing_generator *tg, uint8_t idx, uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb); bool dce110_is_two_pixels_per_container(const struct dc_crtc_timing *timing); diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c index fcf59348eb62..31c4f44ceaac 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c @@ -1100,45 +1100,79 @@ static bool dce120_configure_crc(struct timing_generator *tg, if (!dce120_is_tg_enabled(tg)) return false; - /* First, disable CRC before we configure it. */ - dm_write_reg_soc15(tg->ctx, mmCRTC0_CRTC_CRC_CNTL, - tg110->offsets.crtc, 0); + if (!params->enable || params->reset) + /* First, disable CRC before we configure it. */ + dm_write_reg_soc15(tg->ctx, mmCRTC0_CRTC_CRC_CNTL, + tg110->offsets.crtc, 0); if (!params->enable) return true; /* Program frame boundaries */ - /* Window A x axis start and end. */ - CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC0_WINDOWA_X_CONTROL, - CRTC_CRC0_WINDOWA_X_START, params->windowa_x_start, - CRTC_CRC0_WINDOWA_X_END, params->windowa_x_end); + switch (params->crc_eng_inst) { + case 0: + /* Window A x axis start and end. */ + CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC0_WINDOWA_X_CONTROL, + CRTC_CRC0_WINDOWA_X_START, params->windowa_x_start, + CRTC_CRC0_WINDOWA_X_END, params->windowa_x_end); - /* Window A y axis start and end. */ - CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC0_WINDOWA_Y_CONTROL, - CRTC_CRC0_WINDOWA_Y_START, params->windowa_y_start, - CRTC_CRC0_WINDOWA_Y_END, params->windowa_y_end); + /* Window A y axis start and end. */ + CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC0_WINDOWA_Y_CONTROL, + CRTC_CRC0_WINDOWA_Y_START, params->windowa_y_start, + CRTC_CRC0_WINDOWA_Y_END, params->windowa_y_end); - /* Window B x axis start and end. */ - CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC0_WINDOWB_X_CONTROL, - CRTC_CRC0_WINDOWB_X_START, params->windowb_x_start, - CRTC_CRC0_WINDOWB_X_END, params->windowb_x_end); + /* Window B x axis start and end. */ + CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC0_WINDOWB_X_CONTROL, + CRTC_CRC0_WINDOWB_X_START, params->windowb_x_start, + CRTC_CRC0_WINDOWB_X_END, params->windowb_x_end); - /* Window B y axis start and end. */ - CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC0_WINDOWB_Y_CONTROL, - CRTC_CRC0_WINDOWB_Y_START, params->windowb_y_start, - CRTC_CRC0_WINDOWB_Y_END, params->windowb_y_end); + /* Window B y axis start and end. */ + CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC0_WINDOWB_Y_CONTROL, + CRTC_CRC0_WINDOWB_Y_START, params->windowb_y_start, + CRTC_CRC0_WINDOWB_Y_END, params->windowb_y_end); - /* Set crc mode and selection, and enable. Only using CRC0*/ - CRTC_REG_UPDATE_3(CRTC0_CRTC_CRC_CNTL, - CRTC_CRC_EN, params->continuous_mode ? 1 : 0, - CRTC_CRC0_SELECT, params->selection, - CRTC_CRC_EN, 1); + /* Set crc mode and selection, and enable.*/ + CRTC_REG_UPDATE_3(CRTC0_CRTC_CRC_CNTL, + CRTC_CRC_CONT_EN, params->continuous_mode ? 1 : 0, + CRTC_CRC0_SELECT, params->selection, + CRTC_CRC_EN, 1); + break; + case 1: + /* Window A x axis start and end. */ + CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC1_WINDOWA_X_CONTROL, + CRTC_CRC1_WINDOWA_X_START, params->windowa_x_start, + CRTC_CRC1_WINDOWA_X_END, params->windowa_x_end); + + /* Window A y axis start and end. */ + CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC1_WINDOWA_Y_CONTROL, + CRTC_CRC1_WINDOWA_Y_START, params->windowa_y_start, + CRTC_CRC1_WINDOWA_Y_END, params->windowa_y_end); + + /* Window B x axis start and end. */ + CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC1_WINDOWB_X_CONTROL, + CRTC_CRC1_WINDOWB_X_START, params->windowb_x_start, + CRTC_CRC1_WINDOWB_X_END, params->windowb_x_end); + + /* Window B y axis start and end. */ + CRTC_REG_UPDATE_2(CRTC0_CRTC_CRC1_WINDOWB_Y_CONTROL, + CRTC_CRC1_WINDOWB_Y_START, params->windowb_y_start, + CRTC_CRC1_WINDOWB_Y_END, params->windowb_y_end); + + /* Set crc mode and selection, and enable */ + CRTC_REG_UPDATE_3(CRTC0_CRTC_CRC_CNTL, + CRTC_CRC_CONT_EN, params->continuous_mode ? 1 : 0, + CRTC_CRC1_SELECT, params->selection, + CRTC_CRC_EN, 1); + break; + default: + return false; + } return true; } -static bool dce120_get_crc(struct timing_generator *tg, uint32_t *r_cr, - uint32_t *g_y, uint32_t *b_cb) +static bool dce120_get_crc(struct timing_generator *tg, uint8_t idx, + uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb) { struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg); uint32_t value, field; @@ -1151,14 +1185,30 @@ static bool dce120_get_crc(struct timing_generator *tg, uint32_t *r_cr, if (!field) return false; - value = dm_read_reg_soc15(tg->ctx, mmCRTC0_CRTC_CRC0_DATA_RG, - tg110->offsets.crtc); - *r_cr = get_reg_field_value(value, CRTC0_CRTC_CRC0_DATA_RG, CRC0_R_CR); - *g_y = get_reg_field_value(value, CRTC0_CRTC_CRC0_DATA_RG, CRC0_G_Y); + switch (idx) { + case 0: + value = dm_read_reg_soc15(tg->ctx, mmCRTC0_CRTC_CRC0_DATA_RG, + tg110->offsets.crtc); + *r_cr = get_reg_field_value(value, CRTC0_CRTC_CRC0_DATA_RG, CRC0_R_CR); + *g_y = get_reg_field_value(value, CRTC0_CRTC_CRC0_DATA_RG, CRC0_G_Y); - value = dm_read_reg_soc15(tg->ctx, mmCRTC0_CRTC_CRC0_DATA_B, - tg110->offsets.crtc); - *b_cb = get_reg_field_value(value, CRTC0_CRTC_CRC0_DATA_B, CRC0_B_CB); + value = dm_read_reg_soc15(tg->ctx, mmCRTC0_CRTC_CRC0_DATA_B, + tg110->offsets.crtc); + *b_cb = get_reg_field_value(value, CRTC0_CRTC_CRC0_DATA_B, CRC0_B_CB); + break; + case 1: + value = dm_read_reg_soc15(tg->ctx, mmCRTC0_CRTC_CRC1_DATA_RG, + tg110->offsets.crtc); + *r_cr = get_reg_field_value(value, CRTC0_CRTC_CRC1_DATA_RG, CRC1_R_CR); + *g_y = get_reg_field_value(value, CRTC0_CRTC_CRC1_DATA_RG, CRC1_G_Y); + + value = dm_read_reg_soc15(tg->ctx, mmCRTC0_CRTC_CRC1_DATA_B, + tg110->offsets.crtc); + *b_cb = get_reg_field_value(value, CRTC0_CRTC_CRC1_DATA_B, CRC1_B_CB); + break; + default: + return false; + } return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn31/dcn31_dio_link_encoder.c index b2cea59ba5d4..9a92f73d5b7f 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn31/dcn31_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn31/dcn31_dio_link_encoder.c @@ -653,8 +653,9 @@ void dcn31_link_encoder_get_max_link_cap(struct link_encoder *enc, struct dc_lin if (!query_dp_alt_from_dmub(enc, &cmd)) return; - if (cmd.query_dp_alt.data.is_usb && - cmd.query_dp_alt.data.is_dp4 == 0) + if (cmd.query_dp_alt.data.is_dp_alt_disable == 0 && + cmd.query_dp_alt.data.is_usb && + cmd.query_dp_alt.data.is_dp4 == 0) link_settings->lane_count = MIN(LANE_COUNT_TWO, link_settings->lane_count); return; diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c index d4a3e811aa39..ea0c9a9d0bd6 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c @@ -28,6 +28,7 @@ #include "link_encoder.h" #include "dcn31/dcn31_dio_link_encoder.h" #include "dcn35_dio_link_encoder.h" +#include "dc_dmub_srv.h" #define CTX \ enc10->base.ctx #define DC_LOGGER \ @@ -159,6 +160,8 @@ static const struct link_encoder_funcs dcn35_link_enc_funcs = { .is_in_alt_mode = dcn31_link_encoder_is_in_alt_mode, .get_max_link_cap = dcn31_link_encoder_get_max_link_cap, .set_dio_phy_mux = dcn31_link_encoder_set_dio_phy_mux, + .enable_dpia_output = dcn35_link_encoder_enable_dpia_output, + .disable_dpia_output = dcn35_link_encoder_disable_dpia_output, }; void dcn35_link_encoder_construct( @@ -265,3 +268,80 @@ void dcn35_link_encoder_construct( enc10->base.features.flags.bits.HDMI_6GB_EN = 0; } + +/* DPIA equivalent of link_transmitter_control. */ +static bool link_dpia_control(struct dc_context *dc_ctx, + struct dmub_cmd_dig_dpia_control_data *dpia_control) +{ + union dmub_rb_cmd cmd; + + memset(&cmd, 0, sizeof(cmd)); + + cmd.dig1_dpia_control.header.type = DMUB_CMD__DPIA; + cmd.dig1_dpia_control.header.sub_type = + DMUB_CMD__DPIA_DIG1_DPIA_CONTROL; + cmd.dig1_dpia_control.header.payload_bytes = + sizeof(cmd.dig1_dpia_control) - + sizeof(cmd.dig1_dpia_control.header); + + cmd.dig1_dpia_control.dpia_control = *dpia_control; + + dc_wake_and_execute_dmub_cmd(dc_ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + + return true; +} + +static void link_encoder_disable(struct dcn10_link_encoder *enc10) +{ + /* reset training complete */ + REG_UPDATE(DP_LINK_CNTL, DP_LINK_TRAINING_COMPLETE, 0); +} + +void dcn35_link_encoder_enable_dpia_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + uint8_t dpia_id, + uint8_t digmode, + uint8_t fec_rdy) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + struct dmub_cmd_dig_dpia_control_data dpia_control = { 0 }; + + enc1_configure_encoder(enc10, link_settings); + + dpia_control.action = (uint8_t)TRANSMITTER_CONTROL_ENABLE; + dpia_control.enc_id = enc->preferred_engine; + dpia_control.mode_laneset.digmode = digmode; + dpia_control.lanenum = (uint8_t)link_settings->lane_count; + dpia_control.symclk_10khz = link_settings->link_rate * + LINK_RATE_REF_FREQ_IN_KHZ / 10; + /* DIG_BE_CNTL.DIG_HPD_SELECT set to 5 (hpdsel - 1) to indicate HPD pin unused by DPIA. */ + dpia_control.hpdsel = 6; + dpia_control.dpia_id = dpia_id; + dpia_control.fec_rdy = fec_rdy; + + DC_LOG_DEBUG("%s: DPIA(%d) - enc_id(%d)\n", __func__, dpia_control.dpia_id, dpia_control.enc_id); + link_dpia_control(enc->ctx, &dpia_control); +} + +void dcn35_link_encoder_disable_dpia_output( + struct link_encoder *enc, + uint8_t dpia_id, + uint8_t digmode) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + struct dmub_cmd_dig_dpia_control_data dpia_control = { 0 }; + + if (enc->funcs->is_dig_enabled && !enc->funcs->is_dig_enabled(enc)) + return; + + dpia_control.action = (uint8_t)TRANSMITTER_CONTROL_DISABLE; + dpia_control.enc_id = enc->preferred_engine; + dpia_control.mode_laneset.digmode = digmode; + dpia_control.dpia_id = dpia_id; + + DC_LOG_DEBUG("%s: DPIA(%d) - enc_id(%d)\n", __func__, dpia_control.dpia_id, dpia_control.enc_id); + link_dpia_control(enc->ctx, &dpia_control); + + link_encoder_disable(enc10); +} diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h index d546a3676304..f9d4221f4b43 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h @@ -144,4 +144,22 @@ bool dcn35_is_dig_enabled(struct link_encoder *enc); enum signal_type dcn35_get_dig_mode(struct link_encoder *enc); void dcn35_link_encoder_setup(struct link_encoder *enc, enum signal_type signal); +/* + * Enable DP transmitter and its encoder for dpia port. + */ +void dcn35_link_encoder_enable_dpia_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + uint8_t dpia_id, + uint8_t digmode, + uint8_t fec_rdy); + +/* + * Disable transmitter and its encoder for dpia port. + */ +void dcn35_link_encoder_disable_dpia_output( + struct link_encoder *enc, + uint8_t dpia_id, + uint8_t digmode); + #endif /* __DC_LINK_ENCODER__DCN35_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h index 2e4a46f1b499..5efddd48d5c5 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h +++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h @@ -158,6 +158,11 @@ bool dm_helpers_dp_write_dsc_enable( const struct dc_stream_state *stream, bool enable ); + +bool dm_helpers_dp_write_hblank_reduction( + struct dc_context *ctx, + const struct dc_stream_state *stream); + bool dm_helpers_is_dp_sink_present( struct dc_link *link); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 86ac7d59fd32..0748ef36a16a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -1595,6 +1595,7 @@ double dml32_TruncToValidBPP( unsigned int NonDSCBPP0; unsigned int NonDSCBPP1; unsigned int NonDSCBPP2; + unsigned int NonDSCBPP3 = BPP_INVALID; if (Format == dm_420) { NonDSCBPP0 = 12; @@ -1603,6 +1604,7 @@ double dml32_TruncToValidBPP( MinDSCBPP = 6; MaxDSCBPP = 1.5 * DSCInputBitPerComponent - 1.0 / 16; } else if (Format == dm_444) { + NonDSCBPP3 = 18; NonDSCBPP0 = 24; NonDSCBPP1 = 30; NonDSCBPP2 = 36; @@ -1667,6 +1669,8 @@ double dml32_TruncToValidBPP( return NonDSCBPP1; else if (MaxLinkBPP >= NonDSCBPP0) return 16.0; + else if ((Output == dm_dp2p0 || Output == dm_dp) && NonDSCBPP3 != BPP_INVALID && MaxLinkBPP >= NonDSCBPP3) + return NonDSCBPP3; // Special case to allow 6bpc RGB for DP connections. else return BPP_INVALID; } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c index beed7adbbd43..47d785204f29 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c @@ -195,9 +195,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .dcn_downspread_percent = 0.5, .gpuvm_min_page_size_bytes = 4096, .hostvm_min_page_size_bytes = 4096, - .do_urgent_latency_adjustment = 1, + .do_urgent_latency_adjustment = 0, .urgent_latency_adjustment_fabric_clock_component_us = 0, - .urgent_latency_adjustment_fabric_clock_reference_mhz = 3000, + .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, }; void dcn35_build_wm_range_table_fpu(struct clk_mgr *clk_mgr) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h index 072bd0539605..6b2ab4ec2b5f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h @@ -66,11 +66,15 @@ static inline double dml_max5(double a, double b, double c, double d, double e) static inline double dml_ceil(double a, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_ceil2(a, granularity); } static inline double dml_floor(double a, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_floor2(a, granularity); } @@ -114,11 +118,15 @@ static inline double dml_ceil_2(double f) static inline double dml_ceil_ex(double x, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_ceil2(x, granularity); } static inline double dml_floor_ex(double x, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_floor2(x, granularity); } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/Makefile b/drivers/gpu/drm/amd/display/dc/dml2/Makefile index d9c27ebe12ee..91c4f3b4bd5f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml2/Makefile @@ -29,7 +29,11 @@ dml2_rcflags := $(CC_FLAGS_NO_FPU) ifneq ($(CONFIG_FRAME_WARN),0) ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) +ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy) +frame_warn_flag := -Wframe-larger-than=4096 +else frame_warn_flag := -Wframe-larger-than=3072 +endif else frame_warn_flag := -Wframe-larger-than=2048 endif diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c index 35bc917631ae..84a2de9a76d4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c @@ -1736,7 +1736,7 @@ static void CalculateBytePerPixelAndBlockSizes( #endif } // CalculateBytePerPixelAndBlockSizes -static dml_float_t CalculateTWait( +static noinline_for_stack dml_float_t CalculateTWait( dml_uint_t PrefetchMode, enum dml_use_mall_for_pstate_change_mode UseMALLForPStateChange, dml_bool_t SynchronizeDRRDisplaysForUCLKPStateChangeFinal, @@ -4458,7 +4458,7 @@ static void CalculateSwathWidth( } } // CalculateSwathWidth -static dml_float_t CalculateExtraLatency( +static noinline_for_stack dml_float_t CalculateExtraLatency( dml_uint_t RoundTripPingLatencyCycles, dml_uint_t ReorderingBytes, dml_float_t DCFCLK, @@ -5915,7 +5915,7 @@ static dml_uint_t DSCDelayRequirement( return DSCDelayRequirement_val; } -static dml_bool_t CalculateVActiveBandwithSupport(dml_uint_t NumberOfActiveSurfaces, +static noinline_for_stack dml_bool_t CalculateVActiveBandwithSupport(dml_uint_t NumberOfActiveSurfaces, dml_float_t ReturnBW, dml_bool_t NotUrgentLatencyHiding[], dml_float_t ReadBandwidthLuma[], @@ -6019,7 +6019,7 @@ static void CalculatePrefetchBandwithSupport( #endif } -static dml_float_t CalculateBandwidthAvailableForImmediateFlip( +static noinline_for_stack dml_float_t CalculateBandwidthAvailableForImmediateFlip( dml_uint_t NumberOfActiveSurfaces, dml_float_t ReturnBW, dml_float_t ReadBandwidthLuma[], @@ -6213,7 +6213,7 @@ static dml_uint_t CalculateMaxVStartup( return max_vstartup_lines; } -static void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *mode_lib, +static noinline_for_stack void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *mode_lib, struct CalculatePrefetchSchedule_params_st *CalculatePrefetchSchedule_params, dml_uint_t j, dml_uint_t k) @@ -6265,7 +6265,7 @@ static void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *m CalculatePrefetchSchedule_params->Tno_bw = &mode_lib->ms.Tno_bw[k]; } -static void dml_prefetch_check(struct display_mode_lib_st *mode_lib) +static noinline_for_stack void dml_prefetch_check(struct display_mode_lib_st *mode_lib) { struct dml_core_mode_support_locals_st *s = &mode_lib->scratch.dml_core_mode_support_locals; struct CalculatePrefetchSchedule_params_st *CalculatePrefetchSchedule_params = &mode_lib->scratch.CalculatePrefetchSchedule_params; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c index efb099905496..b9c6b45f6872 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c @@ -10,7 +10,6 @@ #include "dml21_utils.h" #include "dml21_translation_helper.h" #include "bounding_boxes/dcn4_soc_bb.h" -#include "bounding_boxes/dcn3_soc_bb.h" static void dml21_init_socbb_params(struct dml2_initialize_instance_in_out *dml_init, const struct dml2_configuration_options *config, @@ -20,10 +19,6 @@ static void dml21_init_socbb_params(struct dml2_initialize_instance_in_out *dml_ const struct dml2_soc_qos_parameters *qos_params; switch (in_dc->ctx->dce_version) { - case DCN_VERSION_3_2: // TODO : Temporary for N-1 validation. Remove this after N-1 validation phase is complete. - soc_bb = &dml2_socbb_dcn31; - qos_params = &dml_dcn31_soc_qos_params; - break; case DCN_VERSION_4_01: default: if (config->bb_from_dmub) @@ -60,9 +55,6 @@ static void dml21_init_ip_params(struct dml2_initialize_instance_in_out *dml_ini const struct dml2_ip_capabilities *ip_caps; switch (in_dc->ctx->dce_version) { - case DCN_VERSION_3_2: // TODO : Temporary for N-1 validation. Remove this after N-1 validation phase is complete. - ip_caps = &dml2_dcn31_max_ip_caps; - break; case DCN_VERSION_4_01: default: ip_caps = &dml2_dcn401_max_ip_caps; @@ -302,12 +294,17 @@ void dml21_apply_soc_bb_overrides(struct dml2_initialize_instance_in_out *dml_in dml_soc_bb->power_management_parameters.stutter_exit_latency_us = (in_dc->ctx->dc_bios->bb_info.dram_sr_exit_latency_100ns + 9) / 10; - if (in_dc->ctx->dc_bios->vram_info.num_chans) { + if (dc_bw_params->num_channels) { + dml_clk_table->dram_config.channel_count = dc_bw_params->num_channels; + dml_soc_bb->mall_allocated_for_dcn_mbytes = in_dc->caps.mall_size_total / 1048576; + } else if (in_dc->ctx->dc_bios->vram_info.num_chans) { dml_clk_table->dram_config.channel_count = in_dc->ctx->dc_bios->vram_info.num_chans; dml_soc_bb->mall_allocated_for_dcn_mbytes = in_dc->caps.mall_size_total / 1048576; } - if (in_dc->ctx->dc_bios->vram_info.dram_channel_width_bytes) { + if (dc_bw_params->dram_channel_width_bytes) { + dml_clk_table->dram_config.channel_width_bytes = dc_bw_params->dram_channel_width_bytes; + } else if (in_dc->ctx->dc_bios->vram_info.dram_channel_width_bytes) { dml_clk_table->dram_config.channel_width_bytes = in_dc->ctx->dc_bios->vram_info.dram_channel_width_bytes; } @@ -721,11 +718,21 @@ static void populate_dml21_surface_config_from_plane_state( surface->dcc.informative.fraction_of_zero_size_request_plane1 = plane_state->dcc.independent_64b_blks_c; surface->dcc.plane0.pitch = plane_state->dcc.meta_pitch; surface->dcc.plane1.pitch = plane_state->dcc.meta_pitch_c; - if (in_dc->ctx->dce_version < DCN_VERSION_4_01) { - /* needed for N-1 testing */ + + // Update swizzle / array mode based on the gfx_format + switch (plane_state->tiling_info.gfxversion) { + case DcGfxVersion7: + case DcGfxVersion8: + // Placeholder for programming the array_mode + break; + case DcGfxVersion9: + case DcGfxVersion10: + case DcGfxVersion11: surface->tiling = gfx9_to_dml2_swizzle_mode(plane_state->tiling_info.gfx9.swizzle); - } else { + break; + case DcGfxAddr3: surface->tiling = gfx_addr3_to_dml2_swizzle_mode(plane_state->tiling_info.gfx_addr3.swizzle); + break; } } @@ -1081,28 +1088,6 @@ void dml21_copy_clocks_to_dc_state(struct dml2_context *in_ctx, struct dc_state context->bw_ctx.bw.dcn.clk.subvp_prefetch_fclk_khz = in_ctx->v21.mode_programming.programming->min_clocks.dcn4x.svp_prefetch_no_throttle.fclk_khz; } -void dml21_extract_legacy_watermark_set(const struct dc *in_dc, struct dcn_watermarks *watermark, enum dml2_dchub_watermark_reg_set_index reg_set_idx, struct dml2_context *in_ctx) -{ - struct dml2_core_internal_display_mode_lib *mode_lib = &in_ctx->v21.dml_init.dml2_instance->core_instance.clean_me_up.mode_lib; - double refclk_freq_in_mhz = (in_ctx->v21.display_config.overrides.hw.dlg_ref_clk_mhz > 0) ? (double)in_ctx->v21.display_config.overrides.hw.dlg_ref_clk_mhz : mode_lib->soc.dchub_refclk_mhz; - - if (reg_set_idx >= DML2_DCHUB_WATERMARK_SET_NUM) { - /* invalid register set index */ - return; - } - - /* convert to legacy format (time in ns) */ - watermark->urgent_ns = ((double)in_ctx->v21.mode_programming.programming->global_regs.wm_regs[reg_set_idx].urgent / refclk_freq_in_mhz) * 1000.0; - watermark->pte_meta_urgent_ns = ((double)in_ctx->v21.mode_programming.programming->global_regs.wm_regs[reg_set_idx].urgent / refclk_freq_in_mhz) * 1000.0; - watermark->cstate_pstate.cstate_enter_plus_exit_ns = ((double)in_ctx->v21.mode_programming.programming->global_regs.wm_regs[reg_set_idx].sr_enter / refclk_freq_in_mhz) * 1000.0; - watermark->cstate_pstate.cstate_exit_ns = ((double)in_ctx->v21.mode_programming.programming->global_regs.wm_regs[reg_set_idx].sr_exit / refclk_freq_in_mhz) * 1000.0; - watermark->cstate_pstate.pstate_change_ns = ((double)in_ctx->v21.mode_programming.programming->global_regs.wm_regs[reg_set_idx].uclk_pstate / refclk_freq_in_mhz) * 1000.0; - watermark->urgent_latency_ns = ((double)in_ctx->v21.mode_programming.programming->global_regs.wm_regs[reg_set_idx].urgent / refclk_freq_in_mhz) * 1000.0; - watermark->cstate_pstate.fclk_pstate_change_ns = ((double)in_ctx->v21.mode_programming.programming->global_regs.wm_regs[reg_set_idx].fclk_pstate / refclk_freq_in_mhz) * 1000.0; - watermark->frac_urg_bw_flip = in_ctx->v21.mode_programming.programming->global_regs.wm_regs[reg_set_idx].frac_urg_bw_flip; - watermark->frac_urg_bw_nom = in_ctx->v21.mode_programming.programming->global_regs.wm_regs[reg_set_idx].frac_urg_bw_nom; -} - static struct dml2_dchub_watermark_regs *wm_set_index_to_dc_wm_set(union dcn_watermark_set *watermarks, const enum dml2_dchub_watermark_reg_set_index wm_index) { struct dml2_dchub_watermark_regs *wm_regs = NULL; @@ -1146,53 +1131,6 @@ void dml21_extract_watermark_sets(const struct dc *in_dc, union dcn_watermark_se } } - -void dml21_populate_pipe_ctx_dlg_params(struct dml2_context *dml_ctx, struct dc_state *context, struct pipe_ctx *pipe_ctx, struct dml2_per_stream_programming *stream_programming) -{ - unsigned int hactive, vactive, hblank_start, vblank_start, hblank_end, vblank_end; - struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; - union dml2_global_sync_programming *global_sync = &stream_programming->global_sync; - - hactive = timing->h_addressable + timing->h_border_left + timing->h_border_right + pipe_ctx->hblank_borrow; - vactive = timing->v_addressable + timing->v_border_bottom + timing->v_border_top; - hblank_start = pipe_ctx->stream->timing.h_total - pipe_ctx->stream->timing.h_front_porch; - vblank_start = pipe_ctx->stream->timing.v_total - pipe_ctx->stream->timing.v_front_porch; - - hblank_end = hblank_start - timing->h_addressable - timing->h_border_left - timing->h_border_right - pipe_ctx->hblank_borrow; - vblank_end = vblank_start - timing->v_addressable - timing->v_border_top - timing->v_border_bottom; - - if (dml_ctx->config.svp_pstate.callbacks.get_pipe_subvp_type(context, pipe_ctx) == SUBVP_PHANTOM) { - /* phantom has its own global sync */ - global_sync = &stream_programming->phantom_stream.global_sync; - } - - pipe_ctx->pipe_dlg_param.vstartup_start = global_sync->dcn4x.vstartup_lines; - pipe_ctx->pipe_dlg_param.vupdate_offset = global_sync->dcn4x.vupdate_offset_pixels; - pipe_ctx->pipe_dlg_param.vupdate_width = global_sync->dcn4x.vupdate_vupdate_width_pixels; - pipe_ctx->pipe_dlg_param.vready_offset = global_sync->dcn4x.vready_offset_pixels; - pipe_ctx->pipe_dlg_param.pstate_keepout = global_sync->dcn4x.pstate_keepout_start_lines; - - pipe_ctx->pipe_dlg_param.otg_inst = pipe_ctx->stream_res.tg->inst; - - pipe_ctx->pipe_dlg_param.hactive = hactive; - pipe_ctx->pipe_dlg_param.vactive = vactive; - pipe_ctx->pipe_dlg_param.htotal = pipe_ctx->stream->timing.h_total; - pipe_ctx->pipe_dlg_param.vtotal = pipe_ctx->stream->timing.v_total; - pipe_ctx->pipe_dlg_param.hblank_end = hblank_end; - pipe_ctx->pipe_dlg_param.vblank_end = vblank_end; - pipe_ctx->pipe_dlg_param.hblank_start = hblank_start; - pipe_ctx->pipe_dlg_param.vblank_start = vblank_start; - pipe_ctx->pipe_dlg_param.vfront_porch = pipe_ctx->stream->timing.v_front_porch; - pipe_ctx->pipe_dlg_param.pixel_rate_mhz = pipe_ctx->stream->timing.pix_clk_100hz / 10000.00; - pipe_ctx->pipe_dlg_param.refresh_rate = ((timing->pix_clk_100hz * 100) / timing->h_total) / timing->v_total; - pipe_ctx->pipe_dlg_param.vtotal_max = pipe_ctx->stream->adjust.v_total_max; - pipe_ctx->pipe_dlg_param.vtotal_min = pipe_ctx->stream->adjust.v_total_min; - pipe_ctx->pipe_dlg_param.recout_height = pipe_ctx->plane_res.scl_data.recout.height; - pipe_ctx->pipe_dlg_param.recout_width = pipe_ctx->plane_res.scl_data.recout.width; - pipe_ctx->pipe_dlg_param.full_recout_height = pipe_ctx->plane_res.scl_data.recout.height; - pipe_ctx->pipe_dlg_param.full_recout_width = pipe_ctx->plane_res.scl_data.recout.width; -} - void dml21_map_hw_resources(struct dml2_context *dml_ctx) { unsigned int i = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.h index 476a7f6e4875..069b939c672a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.h +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.h @@ -21,8 +21,6 @@ void dml21_initialize_soc_bb_params(struct dml2_initialize_instance_in_out *dml_ void dml21_initialize_ip_params(struct dml2_initialize_instance_in_out *dml_init, const struct dml2_configuration_options *config, const struct dc *in_dc); bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_state *context, struct dml2_context *dml_ctx); void dml21_copy_clocks_to_dc_state(struct dml2_context *in_ctx, struct dc_state *context); -void dml21_populate_pipe_ctx_dlg_params(struct dml2_context *dml_ctx, struct dc_state *context, struct pipe_ctx *pipe_ctx, struct dml2_per_stream_programming *stream_programming); -void dml21_extract_legacy_watermark_set(const struct dc *in_dc, struct dcn_watermarks *watermark, enum dml2_dchub_watermark_reg_set_index reg_set_idx, struct dml2_context *in_ctx); void dml21_extract_watermark_sets(const struct dc *in_dc, union dcn_watermark_set *watermarks, struct dml2_context *in_ctx); void dml21_map_hw_resources(struct dml2_context *dml_ctx); void dml21_get_pipe_mcache_config(struct dc_state *context, struct pipe_ctx *pipe_ctx, struct dml2_per_plane_programming *pln_prog, struct dml2_pipe_configuration_descriptor *mcache_pipe_config); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_utils.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_utils.c index cb966f8d3216..1e56d995cd0e 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_utils.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_utils.c @@ -142,108 +142,21 @@ int dml21_find_dc_pipes_for_plane(const struct dc *in_dc, return num_pipes; } - -void dml21_update_pipe_ctx_dchub_regs(struct dml2_display_rq_regs *rq_regs, - struct dml2_display_dlg_regs *disp_dlg_regs, - struct dml2_display_ttu_regs *disp_ttu_regs, - struct pipe_ctx *out) +void dml21_pipe_populate_global_sync(struct dml2_context *dml_ctx, + struct dc_state *context, + struct pipe_ctx *pipe_ctx, + struct dml2_per_stream_programming *stream_programming) { - memset(&out->rq_regs, 0, sizeof(out->rq_regs)); - out->rq_regs.rq_regs_l.chunk_size = rq_regs->rq_regs_l.chunk_size; - out->rq_regs.rq_regs_l.min_chunk_size = rq_regs->rq_regs_l.min_chunk_size; - //out->rq_regs.rq_regs_l.meta_chunk_size = rq_regs->rq_regs_l.meta_chunk_size; - //out->rq_regs.rq_regs_l.min_meta_chunk_size = rq_regs->rq_regs_l.min_meta_chunk_size; - out->rq_regs.rq_regs_l.dpte_group_size = rq_regs->rq_regs_l.dpte_group_size; - out->rq_regs.rq_regs_l.mpte_group_size = rq_regs->rq_regs_l.mpte_group_size; - out->rq_regs.rq_regs_l.swath_height = rq_regs->rq_regs_l.swath_height; - out->rq_regs.rq_regs_l.pte_row_height_linear = rq_regs->rq_regs_l.pte_row_height_linear; + union dml2_global_sync_programming *global_sync = &stream_programming->global_sync; - out->rq_regs.rq_regs_c.chunk_size = rq_regs->rq_regs_c.chunk_size; - out->rq_regs.rq_regs_c.min_chunk_size = rq_regs->rq_regs_c.min_chunk_size; - //out->rq_regs.rq_regs_c.meta_chunk_size = rq_regs->rq_regs_c.meta_chunk_size; - //out->rq_regs.rq_regs_c.min_meta_chunk_size = rq_regs->rq_regs_c.min_meta_chunk_size; - out->rq_regs.rq_regs_c.dpte_group_size = rq_regs->rq_regs_c.dpte_group_size; - out->rq_regs.rq_regs_c.mpte_group_size = rq_regs->rq_regs_c.mpte_group_size; - out->rq_regs.rq_regs_c.swath_height = rq_regs->rq_regs_c.swath_height; - out->rq_regs.rq_regs_c.pte_row_height_linear = rq_regs->rq_regs_c.pte_row_height_linear; + if (dml_ctx->config.svp_pstate.callbacks.get_pipe_subvp_type(context, pipe_ctx) == SUBVP_PHANTOM) { + /* phantom has its own global sync */ + global_sync = &stream_programming->phantom_stream.global_sync; + } - out->rq_regs.drq_expansion_mode = rq_regs->drq_expansion_mode; - out->rq_regs.prq_expansion_mode = rq_regs->prq_expansion_mode; - //out->rq_regs.mrq_expansion_mode = rq_regs->mrq_expansion_mode; - out->rq_regs.crq_expansion_mode = rq_regs->crq_expansion_mode; - out->rq_regs.plane1_base_address = rq_regs->plane1_base_address; - out->unbounded_req = rq_regs->unbounded_request_enabled; - - memset(&out->dlg_regs, 0, sizeof(out->dlg_regs)); - out->dlg_regs.refcyc_h_blank_end = disp_dlg_regs->refcyc_h_blank_end; - out->dlg_regs.dlg_vblank_end = disp_dlg_regs->dlg_vblank_end; - out->dlg_regs.min_dst_y_next_start = disp_dlg_regs->min_dst_y_next_start; - out->dlg_regs.refcyc_per_htotal = disp_dlg_regs->refcyc_per_htotal; - out->dlg_regs.refcyc_x_after_scaler = disp_dlg_regs->refcyc_x_after_scaler; - out->dlg_regs.dst_y_after_scaler = disp_dlg_regs->dst_y_after_scaler; - out->dlg_regs.dst_y_prefetch = disp_dlg_regs->dst_y_prefetch; - out->dlg_regs.dst_y_per_vm_vblank = disp_dlg_regs->dst_y_per_vm_vblank; - out->dlg_regs.dst_y_per_row_vblank = disp_dlg_regs->dst_y_per_row_vblank; - out->dlg_regs.dst_y_per_vm_flip = disp_dlg_regs->dst_y_per_vm_flip; - out->dlg_regs.dst_y_per_row_flip = disp_dlg_regs->dst_y_per_row_flip; - out->dlg_regs.ref_freq_to_pix_freq = disp_dlg_regs->ref_freq_to_pix_freq; - out->dlg_regs.vratio_prefetch = disp_dlg_regs->vratio_prefetch; - out->dlg_regs.vratio_prefetch_c = disp_dlg_regs->vratio_prefetch_c; - out->dlg_regs.refcyc_per_tdlut_group = disp_dlg_regs->refcyc_per_tdlut_group; - out->dlg_regs.refcyc_per_pte_group_vblank_l = disp_dlg_regs->refcyc_per_pte_group_vblank_l; - out->dlg_regs.refcyc_per_pte_group_vblank_c = disp_dlg_regs->refcyc_per_pte_group_vblank_c; - //out->dlg_regs.refcyc_per_meta_chunk_vblank_l = disp_dlg_regs->refcyc_per_meta_chunk_vblank_l; - //out->dlg_regs.refcyc_per_meta_chunk_vblank_c = disp_dlg_regs->refcyc_per_meta_chunk_vblank_c; - out->dlg_regs.refcyc_per_pte_group_flip_l = disp_dlg_regs->refcyc_per_pte_group_flip_l; - out->dlg_regs.refcyc_per_pte_group_flip_c = disp_dlg_regs->refcyc_per_pte_group_flip_c; - //out->dlg_regs.refcyc_per_meta_chunk_flip_l = disp_dlg_regs->refcyc_per_meta_chunk_flip_l; - //out->dlg_regs.refcyc_per_meta_chunk_flip_c = disp_dlg_regs->refcyc_per_meta_chunk_flip_c; - out->dlg_regs.dst_y_per_pte_row_nom_l = disp_dlg_regs->dst_y_per_pte_row_nom_l; - out->dlg_regs.dst_y_per_pte_row_nom_c = disp_dlg_regs->dst_y_per_pte_row_nom_c; - out->dlg_regs.refcyc_per_pte_group_nom_l = disp_dlg_regs->refcyc_per_pte_group_nom_l; - out->dlg_regs.refcyc_per_pte_group_nom_c = disp_dlg_regs->refcyc_per_pte_group_nom_c; - //out->dlg_regs.dst_y_per_meta_row_nom_l = disp_dlg_regs->dst_y_per_meta_row_nom_l; - //out->dlg_regs.dst_y_per_meta_row_nom_c = disp_dlg_regs->dst_y_per_meta_row_nom_c; - //out->dlg_regs.refcyc_per_meta_chunk_nom_l = disp_dlg_regs->refcyc_per_meta_chunk_nom_l; - //out->dlg_regs.refcyc_per_meta_chunk_nom_c = disp_dlg_regs->refcyc_per_meta_chunk_nom_c; - out->dlg_regs.refcyc_per_line_delivery_pre_l = disp_dlg_regs->refcyc_per_line_delivery_pre_l; - out->dlg_regs.refcyc_per_line_delivery_pre_c = disp_dlg_regs->refcyc_per_line_delivery_pre_c; - out->dlg_regs.refcyc_per_line_delivery_l = disp_dlg_regs->refcyc_per_line_delivery_l; - out->dlg_regs.refcyc_per_line_delivery_c = disp_dlg_regs->refcyc_per_line_delivery_c; - out->dlg_regs.refcyc_per_vm_group_vblank = disp_dlg_regs->refcyc_per_vm_group_vblank; - out->dlg_regs.refcyc_per_vm_group_flip = disp_dlg_regs->refcyc_per_vm_group_flip; - out->dlg_regs.refcyc_per_vm_req_vblank = disp_dlg_regs->refcyc_per_vm_req_vblank; - out->dlg_regs.refcyc_per_vm_req_flip = disp_dlg_regs->refcyc_per_vm_req_flip; - out->dlg_regs.dst_y_offset_cur0 = disp_dlg_regs->dst_y_offset_cur0; - out->dlg_regs.chunk_hdl_adjust_cur0 = disp_dlg_regs->chunk_hdl_adjust_cur0; - //out->dlg_regs.dst_y_offset_cur1 = disp_dlg_regs->dst_y_offset_cur1; - //out->dlg_regs.chunk_hdl_adjust_cur1 = disp_dlg_regs->chunk_hdl_adjust_cur1; - out->dlg_regs.vready_after_vcount0 = disp_dlg_regs->vready_after_vcount0; - out->dlg_regs.dst_y_delta_drq_limit = disp_dlg_regs->dst_y_delta_drq_limit; - out->dlg_regs.refcyc_per_vm_dmdata = disp_dlg_regs->refcyc_per_vm_dmdata; - out->dlg_regs.dmdata_dl_delta = disp_dlg_regs->dmdata_dl_delta; - - memset(&out->ttu_regs, 0, sizeof(out->ttu_regs)); - out->ttu_regs.qos_level_low_wm = disp_ttu_regs->qos_level_low_wm; - out->ttu_regs.qos_level_high_wm = disp_ttu_regs->qos_level_high_wm; - out->ttu_regs.min_ttu_vblank = disp_ttu_regs->min_ttu_vblank; - out->ttu_regs.qos_level_flip = disp_ttu_regs->qos_level_flip; - out->ttu_regs.refcyc_per_req_delivery_l = disp_ttu_regs->refcyc_per_req_delivery_l; - out->ttu_regs.refcyc_per_req_delivery_c = disp_ttu_regs->refcyc_per_req_delivery_c; - out->ttu_regs.refcyc_per_req_delivery_cur0 = disp_ttu_regs->refcyc_per_req_delivery_cur0; - //out->ttu_regs.refcyc_per_req_delivery_cur1 = disp_ttu_regs->refcyc_per_req_delivery_cur1; - out->ttu_regs.refcyc_per_req_delivery_pre_l = disp_ttu_regs->refcyc_per_req_delivery_pre_l; - out->ttu_regs.refcyc_per_req_delivery_pre_c = disp_ttu_regs->refcyc_per_req_delivery_pre_c; - out->ttu_regs.refcyc_per_req_delivery_pre_cur0 = disp_ttu_regs->refcyc_per_req_delivery_pre_cur0; - //out->ttu_regs.refcyc_per_req_delivery_pre_cur1 = disp_ttu_regs->refcyc_per_req_delivery_pre_cur1; - out->ttu_regs.qos_level_fixed_l = disp_ttu_regs->qos_level_fixed_l; - out->ttu_regs.qos_level_fixed_c = disp_ttu_regs->qos_level_fixed_c; - out->ttu_regs.qos_level_fixed_cur0 = disp_ttu_regs->qos_level_fixed_cur0; - //out->ttu_regs.qos_level_fixed_cur1 = disp_ttu_regs->qos_level_fixed_cur1; - out->ttu_regs.qos_ramp_disable_l = disp_ttu_regs->qos_ramp_disable_l; - out->ttu_regs.qos_ramp_disable_c = disp_ttu_regs->qos_ramp_disable_c; - out->ttu_regs.qos_ramp_disable_cur0 = disp_ttu_regs->qos_ramp_disable_cur0; - //out->ttu_regs.qos_ramp_disable_cur1 = disp_ttu_regs->qos_ramp_disable_cur1; + memcpy(&pipe_ctx->global_sync, + global_sync, + sizeof(union dml2_global_sync_programming)); } void dml21_populate_mall_allocation_size(struct dc_state *context, @@ -301,28 +214,16 @@ void dml21_program_dc_pipe(struct dml2_context *dml_ctx, struct dc_state *contex { unsigned int pipe_reg_index = 0; - dml21_populate_pipe_ctx_dlg_params(dml_ctx, context, pipe_ctx, stream_prog); + dml21_pipe_populate_global_sync(dml_ctx, context, pipe_ctx, stream_prog); find_pipe_regs_idx(dml_ctx, pipe_ctx, &pipe_reg_index); if (dml_ctx->config.svp_pstate.callbacks.get_pipe_subvp_type(context, pipe_ctx) == SUBVP_PHANTOM) { memcpy(&pipe_ctx->hubp_regs, pln_prog->phantom_plane.pipe_regs[pipe_reg_index], sizeof(struct dml2_dchub_per_pipe_register_set)); pipe_ctx->unbounded_req = false; - - /* legacy only, should be removed later */ - dml21_update_pipe_ctx_dchub_regs(&pln_prog->phantom_plane.pipe_regs[pipe_reg_index]->rq_regs, - &pln_prog->phantom_plane.pipe_regs[pipe_reg_index]->dlg_regs, - &pln_prog->phantom_plane.pipe_regs[pipe_reg_index]->ttu_regs, pipe_ctx); - pipe_ctx->det_buffer_size_kb = 0; } else { memcpy(&pipe_ctx->hubp_regs, pln_prog->pipe_regs[pipe_reg_index], sizeof(struct dml2_dchub_per_pipe_register_set)); pipe_ctx->unbounded_req = pln_prog->pipe_regs[pipe_reg_index]->rq_regs.unbounded_request_enabled; - - /* legacy only, should be removed later */ - dml21_update_pipe_ctx_dchub_regs(&pln_prog->pipe_regs[pipe_reg_index]->rq_regs, - &pln_prog->pipe_regs[pipe_reg_index]->dlg_regs, - &pln_prog->pipe_regs[pipe_reg_index]->ttu_regs, pipe_ctx); - pipe_ctx->det_buffer_size_kb = pln_prog->pipe_regs[pipe_reg_index]->det_size * 64; } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_utils.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_utils.h index d5153fbac921..4bff52eaaef8 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_utils.h +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_utils.h @@ -18,10 +18,10 @@ struct dml2_display_ttu_regs; int dml21_helper_find_dml_pipe_idx_by_stream_id(struct dml2_context *ctx, unsigned int stream_id); int dml21_find_dml_pipe_idx_by_plane_id(struct dml2_context *ctx, unsigned int plane_id); bool dml21_get_plane_id(const struct dc_state *state, const struct dc_plane_state *plane, unsigned int *plane_id); -void dml21_update_pipe_ctx_dchub_regs(struct dml2_display_rq_regs *rq_regs, - struct dml2_display_dlg_regs *disp_dlg_regs, - struct dml2_display_ttu_regs *disp_ttu_regs, - struct pipe_ctx *out); +void dml21_pipe_populate_global_sync(struct dml2_context *dml_ctx, + struct dc_state *context, + struct pipe_ctx *pipe_ctx, + struct dml2_per_stream_programming *stream_programming); void dml21_populate_mall_allocation_size(struct dc_state *context, struct dml2_context *in_ctx, struct dml2_per_plane_programming *pln_prog, diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c index bbc28b9a15a3..fb80ba9287b6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c @@ -75,7 +75,6 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context **dml_ctx, co { switch (in_dc->ctx->dce_version) { case DCN_VERSION_4_01: - case DCN_VERSION_3_2: // TODO : Temporary for N-1 validation. Remove this after N-1 validation phase is complete. (*dml_ctx)->v21.dml_init.options.project_id = dml2_project_dcn4x_stage2_auto_drr_svp; break; default: @@ -233,13 +232,6 @@ static bool dml21_mode_check_and_programming(const struct dc *in_dc, struct dc_s dml21_calculate_rq_and_dlg_params(in_dc, context, &context->res_ctx, dml_ctx, in_dc->res_pool->pipe_count); dml21_copy_clocks_to_dc_state(dml_ctx, context); dml21_extract_watermark_sets(in_dc, &context->bw_ctx.bw.dcn.watermarks, dml_ctx); - if (in_dc->ctx->dce_version == DCN_VERSION_3_2) { - dml21_extract_legacy_watermark_set(in_dc, &context->bw_ctx.bw.dcn.watermarks.a, DML2_DCHUB_WATERMARK_SET_A, dml_ctx); - dml21_extract_legacy_watermark_set(in_dc, &context->bw_ctx.bw.dcn.watermarks.b, DML2_DCHUB_WATERMARK_SET_A, dml_ctx); - dml21_extract_legacy_watermark_set(in_dc, &context->bw_ctx.bw.dcn.watermarks.c, DML2_DCHUB_WATERMARK_SET_A, dml_ctx); - dml21_extract_legacy_watermark_set(in_dc, &context->bw_ctx.bw.dcn.watermarks.d, DML2_DCHUB_WATERMARK_SET_A, dml_ctx); - } - dml21_build_fams2_programming(in_dc, context, dml_ctx); } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/bounding_boxes/dcn3_soc_bb.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/bounding_boxes/dcn3_soc_bb.h deleted file mode 100644 index d82c681a5402..000000000000 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/bounding_boxes/dcn3_soc_bb.h +++ /dev/null @@ -1,401 +0,0 @@ -/* - * Copyright 2022 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - * Authors: AMD - * - */ - -#ifndef __DML_DML_DCN3_SOC_BB__ -#define __DML_DML_DCN3_SOC_BB__ - -#include "dml_top_soc_parameter_types.h" - -static const struct dml2_soc_qos_parameters dml_dcn31_soc_qos_params = { - .derate_table = { - .system_active_urgent = { - .dram_derate_percent_pixel = 22, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 76, - .dcfclk_derate_percent = 100, - }, - .system_active_average = { - .dram_derate_percent_pixel = 17, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 57, - .dcfclk_derate_percent = 75, - }, - .dcn_mall_prefetch_urgent = { - .dram_derate_percent_pixel = 22, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 76, - .dcfclk_derate_percent = 100, - }, - .dcn_mall_prefetch_average = { - .dram_derate_percent_pixel = 17, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 57, - .dcfclk_derate_percent = 75, - }, - .system_idle_average = { - .dram_derate_percent_pixel = 17, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 57, - .dcfclk_derate_percent = 100, - }, - }, - .writeback = { - .base_latency_us = 12, - .scaling_factor_us = 0, - .scaling_factor_mhz = 0, - }, - .qos_params = { - .dcn4x = { - .df_qos_response_time_fclk_cycles = 300, - .max_round_trip_to_furthest_cs_fclk_cycles = 350, - .mall_overhead_fclk_cycles = 50, - .meta_trip_adder_fclk_cycles = 36, - .average_transport_distance_fclk_cycles = 257, - .umc_urgent_ramp_latency_margin = 50, - .umc_max_latency_margin = 30, - .umc_average_latency_margin = 20, - .fabric_max_transport_latency_margin = 20, - .fabric_average_transport_latency_margin = 10, - - .per_uclk_dpm_params = { - { - .minimum_uclk_khz = 97, - .urgent_ramp_uclk_cycles = 472, - .trip_to_memory_uclk_cycles = 827, - .meta_trip_to_memory_uclk_cycles = 827, - .maximum_latency_when_urgent_uclk_cycles = 72, - .average_latency_when_urgent_uclk_cycles = 61, - .maximum_latency_when_non_urgent_uclk_cycles = 827, - .average_latency_when_non_urgent_uclk_cycles = 118, - }, - { - .minimum_uclk_khz = 435, - .urgent_ramp_uclk_cycles = 546, - .trip_to_memory_uclk_cycles = 848, - .meta_trip_to_memory_uclk_cycles = 848, - .maximum_latency_when_urgent_uclk_cycles = 146, - .average_latency_when_urgent_uclk_cycles = 90, - .maximum_latency_when_non_urgent_uclk_cycles = 848, - .average_latency_when_non_urgent_uclk_cycles = 135, - }, - { - .minimum_uclk_khz = 731, - .urgent_ramp_uclk_cycles = 632, - .trip_to_memory_uclk_cycles = 874, - .meta_trip_to_memory_uclk_cycles = 874, - .maximum_latency_when_urgent_uclk_cycles = 232, - .average_latency_when_urgent_uclk_cycles = 124, - .maximum_latency_when_non_urgent_uclk_cycles = 874, - .average_latency_when_non_urgent_uclk_cycles = 155, - }, - { - .minimum_uclk_khz = 1187, - .urgent_ramp_uclk_cycles = 716, - .trip_to_memory_uclk_cycles = 902, - .meta_trip_to_memory_uclk_cycles = 902, - .maximum_latency_when_urgent_uclk_cycles = 316, - .average_latency_when_urgent_uclk_cycles = 160, - .maximum_latency_when_non_urgent_uclk_cycles = 902, - .average_latency_when_non_urgent_uclk_cycles = 177, - }, - }, - }, - }, - .qos_type = dml2_qos_param_type_dcn4x, -}; - -static const struct dml2_soc_bb dml2_socbb_dcn31 = { - .clk_table = { - .uclk = { - .clk_values_khz = {97000, 435000, 731000, 1187000}, - .num_clk_values = 4, - }, - .fclk = { - .clk_values_khz = {300000, 2500000}, - .num_clk_values = 2, - }, - .dcfclk = { - .clk_values_khz = {200000, 1800000}, - .num_clk_values = 2, - }, - .dispclk = { - .clk_values_khz = {100000, 2000000}, - .num_clk_values = 2, - }, - .dppclk = { - .clk_values_khz = {100000, 2000000}, - .num_clk_values = 2, - }, - .dtbclk = { - .clk_values_khz = {100000, 2000000}, - .num_clk_values = 2, - }, - .phyclk = { - .clk_values_khz = {810000, 810000}, - .num_clk_values = 2, - }, - .socclk = { - .clk_values_khz = {300000, 1600000}, - .num_clk_values = 2, - }, - .dscclk = { - .clk_values_khz = {666667, 666667}, - .num_clk_values = 2, - }, - .phyclk_d18 = { - .clk_values_khz = {625000, 625000}, - .num_clk_values = 2, - }, - .phyclk_d32 = { - .clk_values_khz = {2000000, 2000000}, - .num_clk_values = 2, - }, - .dram_config = { - .channel_width_bytes = 2, - .channel_count = 16, - .transactions_per_clock = 16, - }, - }, - - .qos_parameters = { - .derate_table = { - .system_active_urgent = { - .dram_derate_percent_pixel = 22, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 76, - .dcfclk_derate_percent = 100, - }, - .system_active_average = { - .dram_derate_percent_pixel = 17, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 57, - .dcfclk_derate_percent = 75, - }, - .dcn_mall_prefetch_urgent = { - .dram_derate_percent_pixel = 22, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 76, - .dcfclk_derate_percent = 100, - }, - .dcn_mall_prefetch_average = { - .dram_derate_percent_pixel = 17, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 57, - .dcfclk_derate_percent = 75, - }, - .system_idle_average = { - .dram_derate_percent_pixel = 17, - .dram_derate_percent_vm = 0, - .dram_derate_percent_pixel_and_vm = 0, - .fclk_derate_percent = 57, - .dcfclk_derate_percent = 100, - }, - }, - .writeback = { - .base_latency_us = 0, - .scaling_factor_us = 0, - .scaling_factor_mhz = 0, - }, - .qos_params = { - .dcn4x = { - .df_qos_response_time_fclk_cycles = 300, - .max_round_trip_to_furthest_cs_fclk_cycles = 350, - .mall_overhead_fclk_cycles = 50, - .meta_trip_adder_fclk_cycles = 36, - .average_transport_distance_fclk_cycles = 260, - .umc_urgent_ramp_latency_margin = 50, - .umc_max_latency_margin = 30, - .umc_average_latency_margin = 20, - .fabric_max_transport_latency_margin = 20, - .fabric_average_transport_latency_margin = 10, - - .per_uclk_dpm_params = { - { - // State 1 - .minimum_uclk_khz = 0, - .urgent_ramp_uclk_cycles = 472, - .trip_to_memory_uclk_cycles = 827, - .meta_trip_to_memory_uclk_cycles = 827, - .maximum_latency_when_urgent_uclk_cycles = 72, - .average_latency_when_urgent_uclk_cycles = 72, - .maximum_latency_when_non_urgent_uclk_cycles = 827, - .average_latency_when_non_urgent_uclk_cycles = 117, - }, - { - // State 2 - .minimum_uclk_khz = 0, - .urgent_ramp_uclk_cycles = 546, - .trip_to_memory_uclk_cycles = 848, - .meta_trip_to_memory_uclk_cycles = 848, - .maximum_latency_when_urgent_uclk_cycles = 146, - .average_latency_when_urgent_uclk_cycles = 146, - .maximum_latency_when_non_urgent_uclk_cycles = 848, - .average_latency_when_non_urgent_uclk_cycles = 133, - }, - { - // State 3 - .minimum_uclk_khz = 0, - .urgent_ramp_uclk_cycles = 564, - .trip_to_memory_uclk_cycles = 853, - .meta_trip_to_memory_uclk_cycles = 853, - .maximum_latency_when_urgent_uclk_cycles = 164, - .average_latency_when_urgent_uclk_cycles = 164, - .maximum_latency_when_non_urgent_uclk_cycles = 853, - .average_latency_when_non_urgent_uclk_cycles = 136, - }, - { - // State 4 - .minimum_uclk_khz = 0, - .urgent_ramp_uclk_cycles = 613, - .trip_to_memory_uclk_cycles = 869, - .meta_trip_to_memory_uclk_cycles = 869, - .maximum_latency_when_urgent_uclk_cycles = 213, - .average_latency_when_urgent_uclk_cycles = 213, - .maximum_latency_when_non_urgent_uclk_cycles = 869, - .average_latency_when_non_urgent_uclk_cycles = 149, - }, - { - // State 5 - .minimum_uclk_khz = 0, - .urgent_ramp_uclk_cycles = 632, - .trip_to_memory_uclk_cycles = 874, - .meta_trip_to_memory_uclk_cycles = 874, - .maximum_latency_when_urgent_uclk_cycles = 232, - .average_latency_when_urgent_uclk_cycles = 232, - .maximum_latency_when_non_urgent_uclk_cycles = 874, - .average_latency_when_non_urgent_uclk_cycles = 153, - }, - { - // State 6 - .minimum_uclk_khz = 0, - .urgent_ramp_uclk_cycles = 665, - .trip_to_memory_uclk_cycles = 885, - .meta_trip_to_memory_uclk_cycles = 885, - .maximum_latency_when_urgent_uclk_cycles = 265, - .average_latency_when_urgent_uclk_cycles = 265, - .maximum_latency_when_non_urgent_uclk_cycles = 885, - .average_latency_when_non_urgent_uclk_cycles = 161, - }, - { - // State 7 - .minimum_uclk_khz = 0, - .urgent_ramp_uclk_cycles = 689, - .trip_to_memory_uclk_cycles = 895, - .meta_trip_to_memory_uclk_cycles = 895, - .maximum_latency_when_urgent_uclk_cycles = 289, - .average_latency_when_urgent_uclk_cycles = 289, - .maximum_latency_when_non_urgent_uclk_cycles = 895, - .average_latency_when_non_urgent_uclk_cycles = 167, - }, - { - // State 8 - .minimum_uclk_khz = 0, - .urgent_ramp_uclk_cycles = 716, - .trip_to_memory_uclk_cycles = 902, - .meta_trip_to_memory_uclk_cycles = 902, - .maximum_latency_when_urgent_uclk_cycles = 316, - .average_latency_when_urgent_uclk_cycles = 316, - .maximum_latency_when_non_urgent_uclk_cycles = 902, - .average_latency_when_non_urgent_uclk_cycles = 174, - }, - }, - }, - }, - .qos_type = dml2_qos_param_type_dcn4x, - }, - - .power_management_parameters = { - .dram_clk_change_blackout_us = 400, - .fclk_change_blackout_us = 0, - .g7_ppt_blackout_us = 0, - .stutter_enter_plus_exit_latency_us = 50, - .stutter_exit_latency_us = 43, - .z8_stutter_enter_plus_exit_latency_us = 0, - .z8_stutter_exit_latency_us = 0, - }, - - .vmin_limit = { - .dispclk_khz = 600 * 1000, - }, - - .dprefclk_mhz = 700, - .xtalclk_mhz = 100, - .pcie_refclk_mhz = 100, - .dchub_refclk_mhz = 50, - .mall_allocated_for_dcn_mbytes = 64, - .max_outstanding_reqs = 512, - .fabric_datapath_to_dcn_data_return_bytes = 64, - .return_bus_width_bytes = 64, - .hostvm_min_page_size_kbytes = 0, - .gpuvm_min_page_size_kbytes = 256, - .phy_downspread_percent = 0, - .dcn_downspread_percent = 0, - .dispclk_dppclk_vco_speed_mhz = 4500, - .do_urgent_latency_adjustment = 0, - .mem_word_bytes = 32, - .num_dcc_mcaches = 8, - .mcache_size_bytes = 2048, - .mcache_line_size_bytes = 32, - .max_fclk_for_uclk_dpm_khz = 1250 * 1000, -}; - -static const struct dml2_ip_capabilities dml2_dcn31_max_ip_caps = { - .pipe_count = 4, - .otg_count = 4, - .num_dsc = 4, - .max_num_dp2p0_streams = 4, - .max_num_hdmi_frl_outputs = 1, - .max_num_dp2p0_outputs = 4, - .rob_buffer_size_kbytes = 192, - .config_return_buffer_size_in_kbytes = 1152, - .meta_fifo_size_in_kentries = 22, - .compressed_buffer_segment_size_in_kbytes = 64, - .subvp_drr_scheduling_margin_us = 100, - .subvp_prefetch_end_to_mall_start_us = 15, - .subvp_fw_processing_delay = 15, - - .fams2 = { - .max_allow_delay_us = 100 * 1000, - .scheduling_delay_us = 50, - .vertical_interrupt_ack_delay_us = 18, - .allow_programming_delay_us = 18, - .min_allow_width_us = 20, - .subvp_df_throttle_delay_us = 100, - .subvp_programming_delay_us = 18, - .subvp_prefetch_to_mall_delay_us = 18, - .drr_programming_delay_us = 18, - }, -}; - -#endif /* __DML_DML_DCN3_SOC_BB__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c index b9ec243cf9ba..8ed49a9df378 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c @@ -600,8 +600,8 @@ static void CalculateBytePerPixelAndBlockSizes( { *BytePerPixelDETY = 0; *BytePerPixelDETC = 0; - *BytePerPixelY = 0; - *BytePerPixelC = 0; + *BytePerPixelY = 1; + *BytePerPixelC = 1; if (SourcePixelFormat == dml2_444_64) { *BytePerPixelDETY = 8; @@ -2778,7 +2778,7 @@ static double dml_get_return_bandwidth_available( return return_bw_mbps; } -static void calculate_bandwidth_available( +static noinline_for_stack void calculate_bandwidth_available( double avg_bandwidth_available_min[dml2_core_internal_soc_state_max], double avg_bandwidth_available[dml2_core_internal_soc_state_max][dml2_core_internal_bw_max], double urg_bandwidth_available_min[dml2_core_internal_soc_state_max], // min between SDP and DRAM @@ -3528,10 +3528,9 @@ static void CalculateUrgentBurstFactor( dml2_printf("DML::%s: UrgentBurstFactorChroma = %f\n", __func__, *UrgentBurstFactorChroma); dml2_printf("DML::%s: NotEnoughUrgentLatencyHiding = %d\n", __func__, *NotEnoughUrgentLatencyHiding); #endif - } -static void CalculateDCFCLKDeepSleep( +static void CalculateDCFCLKDeepSleepTdlut( const struct dml2_display_cfg *display_cfg, unsigned int NumberOfActiveSurfaces, unsigned int BytePerPixelY[], @@ -3546,6 +3545,10 @@ static void CalculateDCFCLKDeepSleep( double ReadBandwidthChroma[], unsigned int ReturnBusWidth, + double dispclk, + unsigned int tdlut_bytes_to_deliver[], + double prefetch_swath_time_us[], + // Output double *DCFClkDeepSleep) { @@ -3580,6 +3583,22 @@ static void CalculateDCFCLKDeepSleep( } DCFClkDeepSleepPerSurface[k] = math_max2(DCFClkDeepSleepPerSurface[k], pixel_rate_mhz / 16); + // adjust for 3dlut delivery time + if (display_cfg->plane_descriptors[k].tdlut.setup_for_tdlut && tdlut_bytes_to_deliver[k] > 0) { + double tdlut_required_deepsleep_dcfclk = (double) tdlut_bytes_to_deliver[k] / 64.0 / prefetch_swath_time_us[k]; + + dml2_printf("DML::%s: k=%d, DCFClkDeepSleepPerSurface = %f\n", __func__, k, DCFClkDeepSleepPerSurface[k]); + dml2_printf("DML::%s: k=%d, tdlut_bytes_to_deliver = %d\n", __func__, k, tdlut_bytes_to_deliver[k]); + dml2_printf("DML::%s: k=%d, prefetch_swath_time_us = %f\n", __func__, k, prefetch_swath_time_us[k]); + dml2_printf("DML::%s: k=%d, tdlut_required_deepsleep_dcfclk = %f\n", __func__, k, tdlut_required_deepsleep_dcfclk); + + // increase the deepsleep dcfclk to match the original dispclk throughput rate + if (tdlut_required_deepsleep_dcfclk > DCFClkDeepSleepPerSurface[k]) { + DCFClkDeepSleepPerSurface[k] = math_max2(DCFClkDeepSleepPerSurface[k], tdlut_required_deepsleep_dcfclk); + DCFClkDeepSleepPerSurface[k] = math_max2(DCFClkDeepSleepPerSurface[k], dispclk / 4.0); + } + } + #ifdef __DML_VBA_DEBUG__ dml2_printf("DML::%s: k=%u, PixelClock = %f\n", __func__, k, pixel_rate_mhz); dml2_printf("DML::%s: k=%u, DCFClkDeepSleepPerSurface = %f\n", __func__, k, DCFClkDeepSleepPerSurface[k]); @@ -3602,9 +3621,56 @@ static void CalculateDCFCLKDeepSleep( for (unsigned int k = 0; k < NumberOfActiveSurfaces; ++k) { *DCFClkDeepSleep = math_max2(*DCFClkDeepSleep, DCFClkDeepSleepPerSurface[k]); } + dml2_printf("DML::%s: DCFClkDeepSleep = %f (final)\n", __func__, *DCFClkDeepSleep); } +static noinline_for_stack void CalculateDCFCLKDeepSleep( + const struct dml2_display_cfg *display_cfg, + unsigned int NumberOfActiveSurfaces, + unsigned int BytePerPixelY[], + unsigned int BytePerPixelC[], + unsigned int SwathWidthY[], + unsigned int SwathWidthC[], + unsigned int DPPPerSurface[], + double PSCL_THROUGHPUT[], + double PSCL_THROUGHPUT_CHROMA[], + double Dppclk[], + double ReadBandwidthLuma[], + double ReadBandwidthChroma[], + unsigned int ReturnBusWidth, + + // Output + double *DCFClkDeepSleep) +{ + double zero_double[DML2_MAX_PLANES]; + unsigned int zero_integer[DML2_MAX_PLANES]; + + memset(zero_double, 0, DML2_MAX_PLANES * sizeof(double)); + memset(zero_integer, 0, DML2_MAX_PLANES * sizeof(unsigned int)); + + CalculateDCFCLKDeepSleepTdlut( + display_cfg, + NumberOfActiveSurfaces, + BytePerPixelY, + BytePerPixelC, + SwathWidthY, + SwathWidthC, + DPPPerSurface, + PSCL_THROUGHPUT, + PSCL_THROUGHPUT_CHROMA, + Dppclk, + ReadBandwidthLuma, + ReadBandwidthChroma, + ReturnBusWidth, + 0, + zero_integer, //tdlut_bytes_to_deliver, + zero_double, //prefetch_swath_time_us, + + // Output + DCFClkDeepSleep); +} + static double CalculateWriteBackDelay( enum dml2_source_format_class WritebackPixelFormat, double WritebackHRatio, @@ -4076,7 +4142,7 @@ static bool ValidateODMMode(enum dml2_odm_mode ODMMode, return true; } -static void CalculateODMMode( +static noinline_for_stack void CalculateODMMode( unsigned int MaximumPixelsPerLinePerDSCUnit, unsigned int HActive, enum dml2_output_format_class OutFormat, @@ -4173,7 +4239,7 @@ static void CalculateODMMode( #endif } -static void CalculateOutputLink( +static noinline_for_stack void CalculateOutputLink( struct dml2_core_internal_scratch *s, double PHYCLK, double PHYCLKD18, @@ -4604,6 +4670,7 @@ static void calculate_tdlut_setting( *p->tdlut_groups_per_2row_ub = 0; *p->tdlut_opt_time = 0; *p->tdlut_drain_time = 0; + *p->tdlut_bytes_to_deliver = 0; *p->tdlut_bytes_per_group = 0; *p->tdlut_pte_bytes_per_frame = 0; *p->tdlut_bytes_per_frame = 0; @@ -4672,6 +4739,7 @@ static void calculate_tdlut_setting( *p->tdlut_groups_per_2row_ub = (unsigned int)math_ceil2((double) *p->tdlut_bytes_per_frame / *p->tdlut_bytes_per_group, 1); *p->tdlut_opt_time = (*p->tdlut_bytes_per_frame - p->cursor_buffer_size * 1024) / tdlut_drain_rate; *p->tdlut_drain_time = p->cursor_buffer_size * 1024 / tdlut_drain_rate; + *p->tdlut_bytes_to_deliver = (unsigned int) (p->cursor_buffer_size * 1024.0); } #ifdef __DML_VBA_DEBUG__ @@ -4692,6 +4760,7 @@ static void calculate_tdlut_setting( dml2_printf("DML::%s: tdlut_delivery_cycles = %u\n", __func__, tdlut_delivery_cycles); dml2_printf("DML::%s: tdlut_opt_time = %f\n", __func__, *p->tdlut_opt_time); dml2_printf("DML::%s: tdlut_drain_time = %f\n", __func__, *p->tdlut_drain_time); + dml2_printf("DML::%s: tdlut_bytes_to_deliver = %d\n", __func__, *p->tdlut_bytes_to_deliver); dml2_printf("DML::%s: tdlut_groups_per_2row_ub = %d\n", __func__, *p->tdlut_groups_per_2row_ub); #endif } @@ -5700,6 +5769,7 @@ static bool CalculatePrefetchSchedule(struct dml2_core_internal_scratch *scratch s->cursor_prefetch_bytes = (unsigned int)math_max2(p->cursor_bytes_per_chunk, 4 * p->cursor_bytes_per_line); *p->prefetch_cursor_bw = p->num_cursors * s->cursor_prefetch_bytes / (s->LinesToRequestPrefetchPixelData * s->LineTime); + *p->prefetch_swath_time_us = (s->LinesToRequestPrefetchPixelData * s->LineTime); #ifdef __DML_VBA_DEBUG__ dml2_printf("DML::%s: TimeForFetchingVM = %f\n", __func__, s->TimeForFetchingVM); @@ -5710,6 +5780,7 @@ static bool CalculatePrefetchSchedule(struct dml2_core_internal_scratch *scratch dml2_printf("DML::%s: dst_y_per_row_vblank = %f\n", __func__, *p->dst_y_per_row_vblank); dml2_printf("DML::%s: LinesToRequestPrefetchPixelData = %f\n", __func__, s->LinesToRequestPrefetchPixelData); dml2_printf("DML::%s: PrefetchSourceLinesY = %f\n", __func__, p->PrefetchSourceLinesY); + dml2_printf("DML::%s: prefetch_swath_time_us = %f\n", __func__, *p->prefetch_swath_time_us); dml2_printf("DML::%s: cursor_bytes_per_chunk = %d\n", __func__, p->cursor_bytes_per_chunk); dml2_printf("DML::%s: cursor_bytes_per_line = %d\n", __func__, p->cursor_bytes_per_line); @@ -5928,7 +5999,7 @@ static double calculate_impacted_Tsw(unsigned int exclude_plane_idx, unsigned in } // a global check against the aggregate effect of the per plane prefetch schedule -static bool CheckGlobalPrefetchAdmissibility(struct dml2_core_internal_scratch *scratch, +static noinline_for_stack bool CheckGlobalPrefetchAdmissibility(struct dml2_core_internal_scratch *scratch, struct dml2_core_calcs_CheckGlobalPrefetchAdmissibility_params *p) { struct dml2_core_calcs_CheckGlobalPrefetchAdmissibility_locals *s = &scratch->CheckGlobalPrefetchAdmissibility_locals; @@ -6941,7 +7012,7 @@ static void calculate_bytes_to_fetch_required_to_hide_latency( } } -static void calculate_vactive_det_fill_latency( +static noinline_for_stack void calculate_vactive_det_fill_latency( const struct dml2_display_cfg *display_cfg, unsigned int num_active_planes, unsigned int bytes_required_l[], @@ -8817,6 +8888,7 @@ static bool dml_core_mode_support(struct dml2_core_calcs_mode_support_ex *in_out calculate_tdlut_setting_params->tdlut_groups_per_2row_ub = &s->tdlut_groups_per_2row_ub[k]; calculate_tdlut_setting_params->tdlut_opt_time = &s->tdlut_opt_time[k]; calculate_tdlut_setting_params->tdlut_drain_time = &s->tdlut_drain_time[k]; + calculate_tdlut_setting_params->tdlut_bytes_to_deliver = &s->tdlut_bytes_to_deliver[k]; calculate_tdlut_setting_params->tdlut_bytes_per_group = &s->tdlut_bytes_per_group[k]; calculate_tdlut_setting(&mode_lib->scratch, calculate_tdlut_setting_params); @@ -9009,6 +9081,7 @@ static bool dml_core_mode_support(struct dml2_core_calcs_mode_support_ex *in_out CalculatePrefetchSchedule_params->prefetch_sw_bytes = &s->prefetch_sw_bytes[k]; CalculatePrefetchSchedule_params->Tpre_rounded = &s->Tpre_rounded[k]; CalculatePrefetchSchedule_params->Tpre_oto = &s->Tpre_oto[k]; + CalculatePrefetchSchedule_params->prefetch_swath_time_us = &s->prefetch_swath_time_us[k]; mode_lib->ms.NoTimeForPrefetch[k] = CalculatePrefetchSchedule(&mode_lib->scratch, CalculatePrefetchSchedule_params); @@ -9017,6 +9090,27 @@ static bool dml_core_mode_support(struct dml2_core_calcs_mode_support_ex *in_out dml2_printf("DML::%s: k=%d, dst_y_per_row_vblank = %f\n", __func__, k, *CalculatePrefetchSchedule_params->dst_y_per_row_vblank); } // for k num_planes + CalculateDCFCLKDeepSleepTdlut( + display_cfg, + mode_lib->ms.num_active_planes, + mode_lib->ms.BytePerPixelY, + mode_lib->ms.BytePerPixelC, + mode_lib->ms.SwathWidthY, + mode_lib->ms.SwathWidthC, + mode_lib->ms.NoOfDPP, + mode_lib->ms.PSCL_FACTOR, + mode_lib->ms.PSCL_FACTOR_CHROMA, + mode_lib->ms.RequiredDPPCLK, + mode_lib->ms.vactive_sw_bw_l, + mode_lib->ms.vactive_sw_bw_c, + mode_lib->soc.return_bus_width_bytes, + mode_lib->ms.RequiredDISPCLK, + s->tdlut_bytes_to_deliver, + s->prefetch_swath_time_us, + + /* Output */ + &mode_lib->ms.dcfclk_deepsleep); + for (k = 0; k < mode_lib->ms.num_active_planes; k++) { if (mode_lib->ms.dst_y_prefetch[k] < 2.0 || mode_lib->ms.LinesForVM[k] >= 32.0 @@ -10368,12 +10462,6 @@ static bool dml_core_mode_programming(struct dml2_core_calcs_mode_programming_ex dml2_assert(s->SOCCLK > 0); #ifdef __DML_VBA_DEBUG__ - // dml2_printf_dml_display_cfg_timing(&display_cfg->timing, s->num_active_planes); - // dml2_printf_dml_display_cfg_plane(&display_cfg->plane, s->num_active_planes); - // dml2_printf_dml_display_cfg_surface(&display_cfg->surface, s->num_active_planes); - // dml2_printf_dml_display_cfg_output(&display_cfg->output, s->num_active_planes); - // dml2_printf_dml_display_cfg_hw_resource(&display_cfg->hw, s->num_active_planes); - dml2_printf("DML::%s: num_active_planes = %u\n", __func__, s->num_active_planes); dml2_printf("DML::%s: num_active_pipes = %u\n", __func__, mode_lib->mp.num_active_pipes); dml2_printf("DML::%s: Dcfclk = %f\n", __func__, mode_lib->mp.Dcfclk); @@ -10832,8 +10920,8 @@ static bool dml_core_mode_programming(struct dml2_core_calcs_mode_programming_ex calculate_tdlut_setting_params->tdlut_groups_per_2row_ub = &s->tdlut_groups_per_2row_ub[k]; calculate_tdlut_setting_params->tdlut_opt_time = &s->tdlut_opt_time[k]; calculate_tdlut_setting_params->tdlut_drain_time = &s->tdlut_drain_time[k]; + calculate_tdlut_setting_params->tdlut_bytes_to_deliver = &s->tdlut_bytes_to_deliver[k]; calculate_tdlut_setting_params->tdlut_bytes_per_group = &s->tdlut_bytes_per_group[k]; - calculate_tdlut_setting(&mode_lib->scratch, calculate_tdlut_setting_params); } @@ -11219,6 +11307,7 @@ static bool dml_core_mode_programming(struct dml2_core_calcs_mode_programming_ex CalculatePrefetchSchedule_params->prefetch_sw_bytes = &s->prefetch_sw_bytes[k]; CalculatePrefetchSchedule_params->Tpre_rounded = &s->Tpre_rounded[k]; CalculatePrefetchSchedule_params->Tpre_oto = &s->Tpre_oto[k]; + CalculatePrefetchSchedule_params->prefetch_swath_time_us = &s->dummy_single[0]; mode_lib->mp.NoTimeToPrefetch[k] = CalculatePrefetchSchedule(&mode_lib->scratch, CalculatePrefetchSchedule_params); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h index 4f54e54102ef..23c0fca5515f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h @@ -958,6 +958,7 @@ struct dml2_core_calcs_mode_support_locals { unsigned int tdlut_groups_per_2row_ub[DML2_MAX_PLANES]; double tdlut_opt_time[DML2_MAX_PLANES]; double tdlut_drain_time[DML2_MAX_PLANES]; + unsigned int tdlut_bytes_to_deliver[DML2_MAX_PLANES]; unsigned int tdlut_bytes_per_group[DML2_MAX_PLANES]; unsigned int cursor_bytes_per_chunk[DML2_MAX_PLANES]; @@ -979,6 +980,7 @@ struct dml2_core_calcs_mode_support_locals { enum dml2_source_format_class pixel_format[DML2_MAX_PLANES]; unsigned int lb_source_lines_l[DML2_MAX_PLANES]; unsigned int lb_source_lines_c[DML2_MAX_PLANES]; + double prefetch_swath_time_us[DML2_MAX_PLANES]; }; struct dml2_core_calcs_mode_programming_locals { @@ -1042,6 +1044,7 @@ struct dml2_core_calcs_mode_programming_locals { unsigned int tdlut_groups_per_2row_ub[DML2_MAX_PLANES]; double tdlut_opt_time[DML2_MAX_PLANES]; double tdlut_drain_time[DML2_MAX_PLANES]; + unsigned int tdlut_bytes_to_deliver[DML2_MAX_PLANES]; unsigned int tdlut_bytes_per_group[DML2_MAX_PLANES]; unsigned int cursor_bytes_per_chunk[DML2_MAX_PLANES]; @@ -1809,6 +1812,7 @@ struct dml2_core_calcs_CalculatePrefetchSchedule_params { unsigned int *VReadyOffsetPix; double *prefetch_cursor_bw; double *prefetch_sw_bytes; + double *prefetch_swath_time_us; }; struct dml2_core_calcs_CheckGlobalPrefetchAdmissibility_params { @@ -1993,6 +1997,7 @@ struct dml2_core_calcs_calculate_tdlut_setting_params { unsigned int *tdlut_groups_per_2row_ub; double *tdlut_opt_time; double *tdlut_drain_time; + unsigned int *tdlut_bytes_to_deliver; unsigned int *tdlut_bytes_per_group; }; @@ -2137,7 +2142,6 @@ struct dml2_core_calcs_mode_programming_ex { const struct core_display_cfg_support_info *cfg_support_info; int min_clk_index; struct dml2_display_cfg_programming *programming; - }; #endif diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_utils.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_utils.c index 1548dfc68b8e..456b3f8a6d38 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_utils.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_utils.c @@ -556,7 +556,7 @@ bool dml2_core_utils_is_dual_plane(enum dml2_source_format_class source_format) { bool ret_val = 0; - if ((source_format == dml2_420_12) || (source_format == dml2_420_8) || (source_format == dml2_420_10) || (source_format == dml2_rgbe_alpha)) + if (dml2_core_utils_is_420(source_format) || dml2_core_utils_is_422_planar(source_format) || (source_format == dml2_rgbe_alpha)) ret_val = 1; return ret_val; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_dpmm/dml2_dpmm_dcn4.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_dpmm/dml2_dpmm_dcn4.c index 8a78b9adfc62..fc77fb34a19a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_dpmm/dml2_dpmm_dcn4.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_dpmm/dml2_dpmm_dcn4.c @@ -212,7 +212,7 @@ static bool add_margin_and_round_to_dfs_grainularity(double clock_khz, double ma clock_khz *= 1.0 + margin; - divider = (unsigned int)(DFS_DIVIDER_RANGE_SCALE_FACTOR * (vco_freq_khz / clock_khz)); + divider = (unsigned int)((int)DFS_DIVIDER_RANGE_SCALE_FACTOR * (vco_freq_khz / clock_khz)); /* we want to floor here to get higher clock than required rather than lower */ if (divider < DFS_DIVIDER_RANGE_2_START) { @@ -417,11 +417,11 @@ static bool map_min_clocks_to_dpm(const struct dml2_core_mode_support_result *mo static bool are_timings_trivially_synchronizable(struct dml2_display_cfg *display_config, int mask) { - unsigned char i; + unsigned int i; bool identical = true; bool contains_drr = false; - unsigned char remap_array[DML2_MAX_PLANES]; - unsigned char remap_array_size = 0; + unsigned int remap_array[DML2_MAX_PLANES]; + unsigned int remap_array_size = 0; // Create a remap array to enable simple iteration through only masked stream indicies for (i = 0; i < display_config->num_streams; i++) { @@ -456,10 +456,10 @@ static bool are_timings_trivially_synchronizable(struct dml2_display_cfg *displa static int find_smallest_idle_time_in_vblank_us(struct dml2_dpmm_map_mode_to_soc_dpm_params_in_out *in_out, int mask) { - unsigned char i; + unsigned int i; int min_idle_us = 0; - unsigned char remap_array[DML2_MAX_PLANES]; - unsigned char remap_array_size = 0; + unsigned int remap_array[DML2_MAX_PLANES]; + unsigned int remap_array_size = 0; const struct dml2_core_mode_support_result *mode_support_result = &in_out->display_cfg->mode_support_result; // Create a remap array to enable simple iteration through only masked stream indicies diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c index a31db5742675..e763c8e45da8 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c @@ -195,11 +195,11 @@ static int count_planes_with_stream_index(const struct dml2_display_cfg *display static bool are_timings_trivially_synchronizable(struct display_configuation_with_meta *display_config, int mask) { - unsigned char i; + unsigned int i; bool identical = true; bool contains_drr = false; - unsigned char remap_array[DML2_MAX_PLANES]; - unsigned char remap_array_size = 0; + unsigned int remap_array[DML2_MAX_PLANES]; + unsigned int remap_array_size = 0; // Create a remap array to enable simple iteration through only masked stream indicies for (i = 0; i < display_config->display_config.num_streams; i++) { @@ -347,8 +347,12 @@ static int find_highest_odm_load_stream_index( int odm_load, highest_odm_load = -1, highest_odm_load_index = -1; for (i = 0; i < display_config->num_streams; i++) { - odm_load = display_config->stream_descriptors[i].timing.pixel_clock_khz + if (mode_support_result->cfg_support_info.stream_support_info[i].odms_used > 0) + odm_load = display_config->stream_descriptors[i].timing.pixel_clock_khz / mode_support_result->cfg_support_info.stream_support_info[i].odms_used; + else + odm_load = 0; + if (odm_load > highest_odm_load) { highest_odm_load_index = i; highest_odm_load = odm_load; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c index 1efbc0329f85..a3324f7b9ba6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c @@ -813,8 +813,12 @@ static int find_highest_odm_load_stream_index( int odm_load, highest_odm_load = -1, highest_odm_load_index = -1; for (i = 0; i < display_config->num_streams; i++) { - odm_load = display_config->stream_descriptors[i].timing.pixel_clock_khz + if (mode_support_result->cfg_support_info.stream_support_info[i].odms_used > 0) + odm_load = display_config->stream_descriptors[i].timing.pixel_clock_khz / mode_support_result->cfg_support_info.stream_support_info[i].odms_used; + else + odm_load = 0; + if (odm_load > highest_odm_load) { highest_odm_load_index = i; highest_odm_load = odm_load; @@ -986,7 +990,7 @@ static bool all_timings_support_vactive(const struct dml2_pmo_instance *pmo, const struct display_configuation_with_meta *display_config, unsigned int mask) { - unsigned char i; + unsigned int i; bool valid = true; // Create a remap array to enable simple iteration through only masked stream indicies @@ -1035,7 +1039,7 @@ static bool all_timings_support_drr(const struct dml2_pmo_instance *pmo, const struct display_configuation_with_meta *display_config, unsigned int mask) { - unsigned char i; + unsigned int i; for (i = 0; i < DML2_MAX_PLANES; i++) { const struct dml2_stream_parameters *stream_descriptor; const struct dml2_fams2_meta *stream_fams2_meta; @@ -1077,7 +1081,7 @@ static bool all_timings_support_svp(const struct dml2_pmo_instance *pmo, const struct dml2_plane_parameters *plane_descriptor; const struct dml2_fams2_meta *stream_fams2_meta; unsigned int microschedule_vlines; - unsigned char i; + unsigned int i; unsigned int num_planes_per_stream[DML2_MAX_PLANES] = { 0 }; @@ -1194,7 +1198,7 @@ static enum dml2_uclk_pstate_change_strategy pstate_method_to_uclk_pstate_strate static bool all_planes_match_method(const struct display_configuation_with_meta *display_cfg, int plane_mask, enum dml2_pstate_method method) { - unsigned char i; + unsigned int i; for (i = 0; i < DML2_MAX_PLANES; i++) { if (is_bit_set_in_bitfield(plane_mask, i)) { @@ -1372,7 +1376,7 @@ static bool is_config_schedulable( if (j_disallow_us < jp1_disallow_us) { /* swap as A < B */ swap(s->pmo_dcn4.sorted_group_gtl_disallow_index[j], - s->pmo_dcn4.sorted_group_gtl_disallow_index[j+1]); + s->pmo_dcn4.sorted_group_gtl_disallow_index[j + 1]); swapped = true; } } @@ -1431,7 +1435,7 @@ static bool is_config_schedulable( if (j_period_us < jp1_period_us) { /* swap as A < B */ swap(s->pmo_dcn4.sorted_group_gtl_period_index[j], - s->pmo_dcn4.sorted_group_gtl_period_index[j+1]); + s->pmo_dcn4.sorted_group_gtl_period_index[j + 1]); swapped = true; } } @@ -1545,7 +1549,7 @@ static bool validate_pstate_support_strategy_cofunctionality(struct dml2_pmo_ins { struct dml2_pmo_scratch *s = &pmo->scratch; - unsigned char stream_index = 0; + unsigned int stream_index = 0; unsigned int svp_count = 0; unsigned int svp_stream_mask = 0; @@ -1609,7 +1613,7 @@ static bool validate_pstate_support_strategy_cofunctionality(struct dml2_pmo_ins static int get_vactive_pstate_margin(const struct display_configuation_with_meta *display_cfg, int plane_mask) { - unsigned char i; + unsigned int i; int min_vactive_margin_us = 0xFFFFFFF; for (i = 0; i < DML2_MAX_PLANES; i++) { @@ -1817,7 +1821,7 @@ bool pmo_dcn4_fams2_init_for_pstate_support(struct dml2_pmo_init_for_pstate_supp const struct dml2_pmo_pstate_strategy *strategy_list = NULL; struct dml2_pmo_pstate_strategy override_base_strategy = { 0 }; unsigned int strategy_list_size = 0; - unsigned char plane_index, stream_index, i; + unsigned int plane_index, stream_index, i; bool build_override_strategy = true; state->performed = true; @@ -1940,7 +1944,7 @@ static void setup_planes_for_drr_by_mask(struct display_configuation_with_meta * struct dml2_pmo_instance *pmo, int plane_mask) { - unsigned char plane_index; + unsigned int plane_index; struct dml2_plane_parameters *plane; for (plane_index = 0; plane_index < display_config->display_config.num_planes; plane_index++) { @@ -1961,7 +1965,7 @@ static void setup_planes_for_svp_by_mask(struct display_configuation_with_meta * { struct dml2_pmo_scratch *scratch = &pmo->scratch; - unsigned char plane_index; + unsigned int plane_index; int stream_index = -1; for (plane_index = 0; plane_index < display_config->display_config.num_planes; plane_index++) { @@ -1984,7 +1988,7 @@ static void setup_planes_for_svp_drr_by_mask(struct display_configuation_with_me { struct dml2_pmo_scratch *scratch = &pmo->scratch; - unsigned char plane_index; + unsigned int plane_index; int stream_index = -1; for (plane_index = 0; plane_index < display_config->display_config.num_planes; plane_index++) { @@ -2005,7 +2009,7 @@ static void setup_planes_for_vblank_by_mask(struct display_configuation_with_met struct dml2_pmo_instance *pmo, int plane_mask) { - unsigned char plane_index; + unsigned int plane_index; struct dml2_plane_parameters *plane; for (plane_index = 0; plane_index < display_config->display_config.num_planes; plane_index++) { @@ -2025,7 +2029,7 @@ static void setup_planes_for_vblank_drr_by_mask(struct display_configuation_with struct dml2_pmo_instance *pmo, int plane_mask) { - unsigned char plane_index; + unsigned int plane_index; struct dml2_plane_parameters *plane; for (plane_index = 0; plane_index < display_config->display_config.num_planes; plane_index++) { @@ -2042,7 +2046,7 @@ static void setup_planes_for_vactive_by_mask(struct display_configuation_with_me struct dml2_pmo_instance *pmo, int plane_mask) { - unsigned char plane_index; + unsigned int plane_index; unsigned int stream_index; for (plane_index = 0; plane_index < display_config->display_config.num_planes; plane_index++) { @@ -2063,7 +2067,7 @@ static void setup_planes_for_vactive_drr_by_mask(struct display_configuation_wit struct dml2_pmo_instance *pmo, int plane_mask) { - unsigned char plane_index; + unsigned int plane_index; unsigned int stream_index; for (plane_index = 0; plane_index < display_config->display_config.num_planes; plane_index++) { @@ -2131,7 +2135,7 @@ static bool setup_display_config(struct display_configuation_with_meta *display_ static int get_minimum_reserved_time_us_for_planes(struct display_configuation_with_meta *display_config, int plane_mask) { int min_time_us = 0xFFFFFF; - unsigned char plane_index = 0; + unsigned int plane_index = 0; for (plane_index = 0; plane_index < display_config->display_config.num_planes; plane_index++) { if (is_bit_set_in_bitfield(plane_mask, plane_index)) { diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_interfaces.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_interfaces.c index 5f6dfc24df69..f88931ccbc5e 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_interfaces.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_interfaces.c @@ -15,7 +15,6 @@ bool dml2_initialize_instance(struct dml2_initialize_instance_in_out *in_out) { switch (in_out->options.project_id) { case dml2_project_dcn4x_stage1: - return false; case dml2_project_dcn4x_stage2: case dml2_project_dcn4x_stage2_auto_drr_svp: return dml2_top_soc15_initialize_instance(in_out); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_legacy.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_legacy.c index db0a30fdb58d..5e14d85821e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_legacy.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_legacy.c @@ -2,3 +2,9 @@ // // Copyright 2024 Advanced Micro Devices, Inc. +#include "dml2_top_legacy.h" +#include "dml2_top_soc15.h" +#include "dml2_core_factory.h" +#include "dml2_pmo_factory.h" +#include "display_mode_core_structs.h" + diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_soc15.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_soc15.c index b39029c0e56f..a8f58f8448e4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_soc15.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_soc15.c @@ -545,6 +545,7 @@ bool dml2_top_mcache_validate_admissability(struct top_mcache_validate_admissabi if (odm_combine_factor > 1) { max_per_pipe_vp_p0 = plane->surface.plane0.width; temp = (unsigned int)math_ceil(plane->composition.scaler_info.plane0.h_ratio * stream->timing.h_active / odm_combine_factor); + if (temp < max_per_pipe_vp_p0) max_per_pipe_vp_p0 = temp; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_soc15.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_soc15.h index 6fda201af898..53bd8602f9ef 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_soc15.h +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_top/dml2_top_soc15.h @@ -1,6 +1,7 @@ // SPDX-License-Identifier: MIT // // Copyright 2024 Advanced Micro Devices, Inc. + #ifndef __DML2_TOP_SOC15_H__ #define __DML2_TOP_SOC15_H__ #include "dml2_internal_shared_types.h" diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/inc/dml2_internal_shared_types.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/inc/dml2_internal_shared_types.h index d94b310d6eec..7fb6026bcb49 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/inc/dml2_internal_shared_types.h +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/inc/dml2_internal_shared_types.h @@ -357,8 +357,6 @@ struct dml2_pmo_pstate_strategy { enum dml2_pstate_method per_stream_pstate_method[DML2_MAX_PLANES]; bool allow_state_increase; }; - - struct dml2_core_mode_support_in_out { /* * Inputs diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c index 3d29169dd6bb..6b3b8803e0ae 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c @@ -813,7 +813,7 @@ static bool remove_all_phantom_planes_for_stream(struct dml2_context *ctx, struc { int i, old_plane_count; struct dc_stream_status *stream_status = NULL; - struct dc_plane_state *del_planes[MAX_SURFACE_NUM] = { 0 }; + struct dc_plane_state *del_planes[MAX_SURFACES] = { 0 }; for (i = 0; i < context->stream_count; i++) if (context->streams[i] == stream) { diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c index 340791d40ecb..68b882d28195 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c @@ -747,11 +747,10 @@ static inline struct dml2_context *dml2_allocate_memory(void) static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2) { - // TODO : Temporarily add DCN_VERSION_3_2 for N-1 validation. Remove DCN_VERSION_3_2 after N-1 validation phase is complete. - if ((in_dc->debug.using_dml21) && (in_dc->ctx->dce_version == DCN_VERSION_4_01 || in_dc->ctx->dce_version == DCN_VERSION_3_2)) { - dml21_reinit(in_dc, dml2, config); + if ((in_dc->debug.using_dml21) && (in_dc->ctx->dce_version == DCN_VERSION_4_01)) { + dml21_reinit(in_dc, dml2, config); return; - } + } // Store config options (*dml2)->config = *config; @@ -786,10 +785,8 @@ static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_op bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2) { - // TODO : Temporarily add DCN_VERSION_3_2 for N-1 validation. Remove DCN_VERSION_3_2 after N-1 validation phase is complete. - if ((in_dc->debug.using_dml21) && (in_dc->ctx->dce_version == DCN_VERSION_4_01 || in_dc->ctx->dce_version == DCN_VERSION_3_2)) { + if ((in_dc->debug.using_dml21) && (in_dc->ctx->dce_version == DCN_VERSION_4_01)) return dml21_create(in_dc, dml2, config); - } // Allocate Mode Lib Ctx *dml2 = dml2_allocate_memory(); @@ -857,8 +854,7 @@ void dml2_reinit(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2) { - // TODO : Temporarily add DCN_VERSION_3_2 for N-1 validation. Remove DCN_VERSION_3_2 after N-1 validation phase is complete. - if ((in_dc->debug.using_dml21) && (in_dc->ctx->dce_version == DCN_VERSION_4_01 || in_dc->ctx->dce_version == DCN_VERSION_3_2)) { + if ((in_dc->debug.using_dml21) && (in_dc->ctx->dce_version == DCN_VERSION_4_01)) { dml21_reinit(in_dc, dml2, config); return; } diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c index e1da48b05d00..75fb77bca83b 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c @@ -194,6 +194,9 @@ void dpp_reset(struct dpp *dpp_base) dpp->filter_h = NULL; dpp->filter_v = NULL; + memset(&dpp_base->pos, 0, sizeof(dpp_base->pos)); + memset(&dpp_base->att, 0, sizeof(dpp_base->att)); + memset(&dpp->scl_data, 0, sizeof(dpp->scl_data)); memset(&dpp->pwl_data, 0, sizeof(dpp->pwl_data)); } @@ -480,10 +483,11 @@ void dpp1_set_cursor_position( if (src_y_offset + cursor_height <= 0) cur_en = 0; /* not visible beyond top edge*/ - REG_UPDATE(CURSOR0_CONTROL, - CUR0_ENABLE, cur_en); + if (dpp_base->pos.cur0_ctl.bits.cur0_enable != cur_en) { + REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en); - dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en; + dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en; + } } void dpp1_cnv_set_optional_cursor_attributes( diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c index 3b6ca7974e18..1236e0f9a256 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c @@ -154,9 +154,11 @@ void dpp401_set_cursor_position( struct dcn401_dpp *dpp = TO_DCN401_DPP(dpp_base); uint32_t cur_en = pos->enable ? 1 : 0; - REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en); + if (dpp_base->pos.cur0_ctl.bits.cur0_enable != cur_en) { + REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en); - dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en; + dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en; + } } void dpp401_set_optional_cursor_attributes( diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index d9aaebfa3a0a..11535922b5ff 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -30,6 +30,9 @@ #include "rc_calc.h" #include "fixed31_32.h" +#define DC_LOGGER \ + dsc->ctx->logger + /* This module's internal functions */ /* default DSC policy target bitrate limit is 16bpp */ @@ -480,6 +483,48 @@ bool dc_dsc_compute_bandwidth_range( return is_dsc_possible; } +void dc_dsc_dump_encoder_caps(const struct display_stream_compressor *dsc, + const struct dc_crtc_timing *timing) +{ + struct dsc_enc_caps dsc_enc_caps; + + get_dsc_enc_caps(dsc, &dsc_enc_caps, timing->pix_clk_100hz); + + DC_LOG_DSC("dsc encoder caps:"); + DC_LOG_DSC("\tdsc_version 0x%x", dsc_enc_caps.dsc_version); + DC_LOG_DSC("\tslice_caps 0x%x", dsc_enc_caps.slice_caps.raw); + DC_LOG_DSC("\tlb_bit_depth %d", dsc_enc_caps.lb_bit_depth); + DC_LOG_DSC("\tis_block_pred_supported %d", dsc_enc_caps.is_block_pred_supported); + DC_LOG_DSC("\tcolor_formats 0x%x", dsc_enc_caps.color_formats.raw); + DC_LOG_DSC("\tcolor_depth 0x%x", dsc_enc_caps.color_depth.raw); + DC_LOG_DSC("\tmax_total_throughput_mps %d", dsc_enc_caps.max_total_throughput_mps); + DC_LOG_DSC("\tmax_slice_width %d", dsc_enc_caps.max_slice_width); + DC_LOG_DSC("\tbpp_increment_div %d", dsc_enc_caps.bpp_increment_div); +} + +void dc_dsc_dump_decoder_caps(const struct display_stream_compressor *dsc, + const struct dsc_dec_dpcd_caps *dsc_sink_caps) +{ + DC_LOG_DSC("dsc decoder caps:"); + DC_LOG_DSC("\tis_dsc_supported %d", dsc_sink_caps->is_dsc_supported); + DC_LOG_DSC("\tdsc_version 0x%x", dsc_sink_caps->dsc_version); + DC_LOG_DSC("\trc_buffer_size %d", dsc_sink_caps->rc_buffer_size); + DC_LOG_DSC("\tslice_caps1 0x%x", dsc_sink_caps->slice_caps1.raw); + DC_LOG_DSC("\tslice_caps2 0x%x", dsc_sink_caps->slice_caps2.raw); + DC_LOG_DSC("\tlb_bit_depth %d", dsc_sink_caps->lb_bit_depth); + DC_LOG_DSC("\tis_block_pred_supported %d", dsc_sink_caps->is_block_pred_supported); + DC_LOG_DSC("\tedp_max_bits_per_pixel %d", dsc_sink_caps->edp_max_bits_per_pixel); + DC_LOG_DSC("\tcolor_formats 0x%x", dsc_sink_caps->color_formats.raw); + DC_LOG_DSC("\tthroughput_mode_0_mps %d", dsc_sink_caps->throughput_mode_0_mps); + DC_LOG_DSC("\tthroughput_mode_1_mps %d", dsc_sink_caps->throughput_mode_1_mps); + DC_LOG_DSC("\tmax_slice_width %d", dsc_sink_caps->max_slice_width); + DC_LOG_DSC("\tbpp_increment_div %d", dsc_sink_caps->bpp_increment_div); + DC_LOG_DSC("\tbranch_overall_throughput_0_mps %d", dsc_sink_caps->branch_overall_throughput_0_mps); + DC_LOG_DSC("\tbranch_overall_throughput_1_mps %d", dsc_sink_caps->branch_overall_throughput_1_mps); + DC_LOG_DSC("\tbranch_max_line_width %d", dsc_sink_caps->branch_max_line_width); + DC_LOG_DSC("\tis_dp %d", dsc_sink_caps->is_dp); +} + static void get_dsc_enc_caps( const struct display_stream_compressor *dsc, struct dsc_enc_caps *dsc_enc_caps, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c index f0ba944553df..9b026600b90e 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c @@ -140,7 +140,7 @@ void hubp1_vready_workaround(struct hubp *hubp, void hubp1_program_tiling( struct hubp *hubp, - const union dc_tiling_info *info, + const struct dc_tiling_info *info, const enum surface_pixel_format pixel_format) { struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp); @@ -546,10 +546,16 @@ void hubp1_dcc_control(struct hubp *hubp, bool enable, SECONDARY_SURFACE_DCC_IND_64B_BLK, dcc_ind_64b_blk); } +void hubp_reset(struct hubp *hubp) +{ + memset(&hubp->pos, 0, sizeof(hubp->pos)); + memset(&hubp->att, 0, sizeof(hubp->att)); +} + void hubp1_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -1351,8 +1357,9 @@ static void hubp1_wait_pipe_read_start(struct hubp *hubp) void hubp1_init(struct hubp *hubp) { - //do nothing + hubp_reset(hubp); } + static const struct hubp_funcs dcn10_hubp_funcs = { .hubp_program_surface_flip_and_addr = hubp1_program_surface_flip_and_addr, @@ -1365,6 +1372,7 @@ static const struct hubp_funcs dcn10_hubp_funcs = { .hubp_set_vm_context0_settings = hubp1_set_vm_context0_settings, .set_blank = hubp1_set_blank, .dcc_control = hubp1_dcc_control, + .hubp_reset = hubp_reset, .mem_program_viewport = min_set_viewport, .set_hubp_blank_en = hubp1_set_hubp_blank_en, .set_cursor_attributes = hubp1_cursor_set_attributes, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h index 631350cd4f2e..c7765e6f09e6 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h @@ -706,7 +706,7 @@ struct dcn10_hubp { void hubp1_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -739,13 +739,15 @@ void hubp1_program_rotation( void hubp1_program_tiling( struct hubp *hubp, - const union dc_tiling_info *info, + const struct dc_tiling_info *info, const enum surface_pixel_format pixel_format); void hubp1_dcc_control(struct hubp *hubp, bool enable, enum hubp_ind_block_size independent_64b_blks); +void hubp_reset(struct hubp *hubp); + bool hubp1_program_surface_flip_and_addr( struct hubp *hubp, const struct dc_plane_address *address, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c index 200194544bf0..91259b896e03 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c @@ -310,7 +310,7 @@ void hubp2_setup_interdependent( */ static void hubp2_program_tiling( struct dcn20_hubp *hubp2, - const union dc_tiling_info *info, + const struct dc_tiling_info *info, const enum surface_pixel_format pixel_format) { REG_UPDATE_3(DCSURF_ADDR_CONFIG, @@ -550,7 +550,7 @@ void hubp2_program_pixel_format( void hubp2_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -1058,11 +1058,13 @@ void hubp2_cursor_set_position( if (src_y_offset + cursor_height <= 0) cur_en = 0; /* not visible beyond top edge*/ - if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0) - hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr); + if (hubp->pos.cur_ctl.bits.cur_enable != cur_en) { + if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0) + hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr); - REG_UPDATE(CURSOR_CONTROL, + REG_UPDATE(CURSOR_CONTROL, CURSOR_ENABLE, cur_en); + } REG_SET_2(CURSOR_POSITION, 0, CURSOR_X_POSITION, pos->x, @@ -1674,6 +1676,7 @@ static struct hubp_funcs dcn20_hubp_funcs = { .set_blank = hubp2_set_blank, .set_blank_regs = hubp2_set_blank_regs, .dcc_control = hubp2_dcc_control, + .hubp_reset = hubp_reset, .mem_program_viewport = min_set_viewport, .set_cursor_attributes = hubp2_cursor_set_attributes, .set_cursor_position = hubp2_cursor_set_position, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.h index 7fd9240868c3..6968087a3605 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.h @@ -382,7 +382,7 @@ void hubp2_program_pixel_format( void hubp2_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c index d910e4a54c34..ec88ee424a7f 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c @@ -42,7 +42,7 @@ static void hubp201_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -121,6 +121,7 @@ static struct hubp_funcs dcn201_hubp_funcs = { .set_cursor_position = hubp1_cursor_set_position, .set_blank = hubp1_set_blank, .dcc_control = hubp1_dcc_control, + .hubp_reset = hubp_reset, .mem_program_viewport = min_set_viewport, .hubp_clk_cntl = hubp1_clk_cntl, .hubp_vtg_sel = hubp1_vtg_sel, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c index edbdb8c88d5c..e2740482e1cf 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c @@ -811,6 +811,8 @@ static void hubp21_init(struct hubp *hubp) struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp); //hubp[i].HUBPREQ_DEBUG.HUBPREQ_DEBUG[26] = 1; REG_WRITE(HUBPREQ_DEBUG, 1 << 26); + + hubp_reset(hubp); } static struct hubp_funcs dcn21_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, @@ -823,6 +825,7 @@ static struct hubp_funcs dcn21_hubp_funcs = { .hubp_set_vm_system_aperture_settings = hubp21_set_vm_system_aperture_settings, .set_blank = hubp1_set_blank, .dcc_control = hubp1_dcc_control, + .hubp_reset = hubp_reset, .mem_program_viewport = hubp21_set_viewport, .set_cursor_attributes = hubp2_cursor_set_attributes, .set_cursor_position = hubp1_cursor_set_position, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c index 3b16c3cda2c3..be0ac613675a 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c @@ -318,7 +318,7 @@ bool hubp3_program_surface_flip_and_addr( void hubp3_program_tiling( struct dcn20_hubp *hubp2, - const union dc_tiling_info *info, + const struct dc_tiling_info *info, const enum surface_pixel_format pixel_format) { REG_UPDATE_4(DCSURF_ADDR_CONFIG, @@ -411,7 +411,7 @@ void hubp3_dmdata_set_attributes( void hubp3_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -499,6 +499,8 @@ void hubp3_init(struct hubp *hubp) struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); //hubp[i].HUBPREQ_DEBUG.HUBPREQ_DEBUG[26] = 1; REG_WRITE(HUBPREQ_DEBUG, 1 << 26); + + hubp_reset(hubp); } static struct hubp_funcs dcn30_hubp_funcs = { @@ -513,6 +515,7 @@ static struct hubp_funcs dcn30_hubp_funcs = { .set_blank = hubp2_set_blank, .set_blank_regs = hubp2_set_blank_regs, .dcc_control = hubp3_dcc_control, + .hubp_reset = hubp_reset, .mem_program_viewport = min_set_viewport, .set_cursor_attributes = hubp2_cursor_set_attributes, .set_cursor_position = hubp2_cursor_set_position, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.h index cfb01bf340a1..b7d7adf0b58c 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.h @@ -264,7 +264,7 @@ bool hubp3_program_surface_flip_and_addr( void hubp3_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -280,7 +280,7 @@ void hubp3_setup( void hubp3_program_tiling( struct dcn20_hubp *hubp2, - const union dc_tiling_info *info, + const struct dc_tiling_info *info, const enum surface_pixel_format pixel_format); void hubp3_dcc_control(struct hubp *hubp, bool enable, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c index 46b804ed05fb..c2900c79a2d3 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c @@ -79,6 +79,7 @@ static struct hubp_funcs dcn31_hubp_funcs = { .hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings, .set_blank = hubp2_set_blank, .dcc_control = hubp3_dcc_control, + .hubp_reset = hubp_reset, .mem_program_viewport = min_set_viewport, .set_cursor_attributes = hubp2_cursor_set_attributes, .set_cursor_position = hubp2_cursor_set_position, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c index 8b5bd73b8094..edd37898d550 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c @@ -181,6 +181,7 @@ static struct hubp_funcs dcn32_hubp_funcs = { .set_blank = hubp2_set_blank, .set_blank_regs = hubp2_set_blank_regs, .dcc_control = hubp3_dcc_control, + .hubp_reset = hubp_reset, .mem_program_viewport = min_set_viewport, .set_cursor_attributes = hubp32_cursor_set_attributes, .set_cursor_position = hubp2_cursor_set_position, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c index eb62042dfafc..5661d7a80d54 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c @@ -172,7 +172,7 @@ void hubp35_program_pixel_format( void hubp35_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -199,6 +199,7 @@ static struct hubp_funcs dcn35_hubp_funcs = { .hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings, .set_blank = hubp2_set_blank, .dcc_control = hubp3_dcc_control, + .hubp_reset = hubp_reset, .mem_program_viewport = min_set_viewport, .set_cursor_attributes = hubp2_cursor_set_attributes, .set_cursor_position = hubp2_cursor_set_position, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.h index 586b43aa5834..d913f80b3130 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.h @@ -65,7 +65,7 @@ void hubp35_program_pixel_format( void hubp35_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c index 09f730cfbf8e..5ed195377a6c 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c @@ -141,34 +141,48 @@ void hubp401_update_mall_sel(struct hubp *hubp, uint32_t mall_sel, bool c_cursor void hubp401_init(struct hubp *hubp) { - //For now nothing to do, HUBPREQ_DEBUG_DB register is removed on DCN4x. + hubp_reset(hubp); } void hubp401_vready_at_or_After_vsync(struct hubp *hubp, - struct _vcs_dpi_display_pipe_dest_params_st *pipe_dest) + union dml2_global_sync_programming *pipe_global_sync, + struct dc_crtc_timing *timing) { - uint32_t value = 0; + unsigned int vstartup_lines = pipe_global_sync->dcn4x.vstartup_lines; + unsigned int vupdate_offset_pixels = pipe_global_sync->dcn4x.vupdate_offset_pixels; + unsigned int vupdate_width_pixels = pipe_global_sync->dcn4x.vupdate_vupdate_width_pixels; + unsigned int vready_offset_pixels = pipe_global_sync->dcn4x.vready_offset_pixels; + unsigned int htotal = timing->h_total; + unsigned int vblank_start = 0; + unsigned int vblank_end = 0; + unsigned int pixel_width = 0; + uint32_t reg_value = 0; + bool is_vready_at_or_after_vsync = false; struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + /* * if (VSTARTUP_START - (VREADY_OFFSET+VUPDATE_WIDTH+VUPDATE_OFFSET)/htotal) <= OTG_V_BLANK_END * Set HUBP_VREADY_AT_OR_AFTER_VSYNC = 1 * else * Set HUBP_VREADY_AT_OR_AFTER_VSYNC = 0 */ - if (pipe_dest->htotal != 0) { - if ((pipe_dest->vstartup_start - (pipe_dest->vready_offset+pipe_dest->vupdate_width - + pipe_dest->vupdate_offset) / pipe_dest->htotal) <= pipe_dest->vblank_end) { - value = 1; - } else - value = 0; + if (htotal != 0) { + vblank_start = timing->v_total - timing->v_front_porch; + vblank_end = vblank_start - timing->v_addressable - timing->v_border_top - timing->v_border_bottom; + pixel_width = vready_offset_pixels + vupdate_width_pixels + vupdate_offset_pixels; + + is_vready_at_or_after_vsync = (vstartup_lines - pixel_width / htotal) <= vblank_end; + + if (is_vready_at_or_after_vsync) + reg_value = 1; } - REG_UPDATE(DCHUBP_CNTL, HUBP_VREADY_AT_OR_AFTER_VSYNC, value); + REG_UPDATE(DCHUBP_CNTL, HUBP_VREADY_AT_OR_AFTER_VSYNC, reg_value); } void hubp401_program_requestor( struct hubp *hubp, - struct _vcs_dpi_display_rq_regs_st *rq_regs) + struct dml2_display_rq_regs *rq_regs) { struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); @@ -196,8 +210,8 @@ void hubp401_program_requestor( void hubp401_program_deadline( struct hubp *hubp, - struct _vcs_dpi_display_dlg_regs_st *dlg_attr, - struct _vcs_dpi_display_ttu_regs_st *ttu_attr) + struct dml2_display_dlg_regs *dlg_attr, + struct dml2_display_ttu_regs *ttu_attr) { struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); @@ -294,66 +308,64 @@ void hubp401_program_deadline( void hubp401_setup( struct hubp *hubp, - struct _vcs_dpi_display_dlg_regs_st *dlg_attr, - struct _vcs_dpi_display_ttu_regs_st *ttu_attr, - struct _vcs_dpi_display_rq_regs_st *rq_regs, - struct _vcs_dpi_display_pipe_dest_params_st *pipe_dest) + struct dml2_dchub_per_pipe_register_set *pipe_regs, + union dml2_global_sync_programming *pipe_global_sync, + struct dc_crtc_timing *timing) { /* otg is locked when this func is called. Register are double buffered. * disable the requestors is not needed */ - hubp401_vready_at_or_After_vsync(hubp, pipe_dest); - hubp401_program_requestor(hubp, rq_regs); - hubp401_program_deadline(hubp, dlg_attr, ttu_attr); + hubp401_vready_at_or_After_vsync(hubp, pipe_global_sync, timing); + hubp401_program_requestor(hubp, &pipe_regs->rq_regs); + hubp401_program_deadline(hubp, &pipe_regs->dlg_regs, &pipe_regs->ttu_regs); } void hubp401_setup_interdependent( struct hubp *hubp, - struct _vcs_dpi_display_dlg_regs_st *dlg_attr, - struct _vcs_dpi_display_ttu_regs_st *ttu_attr) + struct dml2_dchub_per_pipe_register_set *pipe_regs) { struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); REG_SET_2(PREFETCH_SETTINGS, 0, - DST_Y_PREFETCH, dlg_attr->dst_y_prefetch, - VRATIO_PREFETCH, dlg_attr->vratio_prefetch); + DST_Y_PREFETCH, pipe_regs->dlg_regs.dst_y_prefetch, + VRATIO_PREFETCH, pipe_regs->dlg_regs.vratio_prefetch); REG_SET(PREFETCH_SETTINGS_C, 0, - VRATIO_PREFETCH_C, dlg_attr->vratio_prefetch_c); + VRATIO_PREFETCH_C, pipe_regs->dlg_regs.vratio_prefetch_c); REG_SET_2(VBLANK_PARAMETERS_0, 0, - DST_Y_PER_VM_VBLANK, dlg_attr->dst_y_per_vm_vblank, - DST_Y_PER_ROW_VBLANK, dlg_attr->dst_y_per_row_vblank); + DST_Y_PER_VM_VBLANK, pipe_regs->dlg_regs.dst_y_per_vm_vblank, + DST_Y_PER_ROW_VBLANK, pipe_regs->dlg_regs.dst_y_per_row_vblank); REG_SET_2(FLIP_PARAMETERS_0, 0, - DST_Y_PER_VM_FLIP, dlg_attr->dst_y_per_vm_flip, - DST_Y_PER_ROW_FLIP, dlg_attr->dst_y_per_row_flip); + DST_Y_PER_VM_FLIP, pipe_regs->dlg_regs.dst_y_per_vm_flip, + DST_Y_PER_ROW_FLIP, pipe_regs->dlg_regs.dst_y_per_row_flip); REG_SET(VBLANK_PARAMETERS_3, 0, - REFCYC_PER_META_CHUNK_VBLANK_L, dlg_attr->refcyc_per_meta_chunk_vblank_l); + REFCYC_PER_META_CHUNK_VBLANK_L, pipe_regs->dlg_regs.refcyc_per_meta_chunk_vblank_l); REG_SET(VBLANK_PARAMETERS_4, 0, - REFCYC_PER_META_CHUNK_VBLANK_C, dlg_attr->refcyc_per_meta_chunk_vblank_c); + REFCYC_PER_META_CHUNK_VBLANK_C, pipe_regs->dlg_regs.refcyc_per_meta_chunk_vblank_c); REG_SET(FLIP_PARAMETERS_2, 0, - REFCYC_PER_META_CHUNK_FLIP_L, dlg_attr->refcyc_per_meta_chunk_flip_l); + REFCYC_PER_META_CHUNK_FLIP_L, pipe_regs->dlg_regs.refcyc_per_meta_chunk_flip_l); REG_SET_2(PER_LINE_DELIVERY_PRE, 0, - REFCYC_PER_LINE_DELIVERY_PRE_L, dlg_attr->refcyc_per_line_delivery_pre_l, - REFCYC_PER_LINE_DELIVERY_PRE_C, dlg_attr->refcyc_per_line_delivery_pre_c); + REFCYC_PER_LINE_DELIVERY_PRE_L, pipe_regs->dlg_regs.refcyc_per_line_delivery_pre_l, + REFCYC_PER_LINE_DELIVERY_PRE_C, pipe_regs->dlg_regs.refcyc_per_line_delivery_pre_c); REG_SET(DCN_SURF0_TTU_CNTL1, 0, REFCYC_PER_REQ_DELIVERY_PRE, - ttu_attr->refcyc_per_req_delivery_pre_l); + pipe_regs->ttu_regs.refcyc_per_req_delivery_pre_l); REG_SET(DCN_SURF1_TTU_CNTL1, 0, REFCYC_PER_REQ_DELIVERY_PRE, - ttu_attr->refcyc_per_req_delivery_pre_c); + pipe_regs->ttu_regs.refcyc_per_req_delivery_pre_c); REG_SET(DCN_CUR0_TTU_CNTL1, 0, - REFCYC_PER_REQ_DELIVERY_PRE, ttu_attr->refcyc_per_req_delivery_pre_cur0); + REFCYC_PER_REQ_DELIVERY_PRE, pipe_regs->ttu_regs.refcyc_per_req_delivery_pre_cur0); REG_SET_2(DCN_GLOBAL_TTU_CNTL, 0, - MIN_TTU_VBLANK, ttu_attr->min_ttu_vblank, - QoS_LEVEL_FLIP, ttu_attr->qos_level_flip); + MIN_TTU_VBLANK, pipe_regs->ttu_regs.min_ttu_vblank, + QoS_LEVEL_FLIP, pipe_regs->ttu_regs.qos_level_flip); } @@ -532,7 +544,7 @@ void hubp401_dcc_control(struct hubp *hubp, void hubp401_program_tiling( struct dcn20_hubp *hubp2, - const union dc_tiling_info *info, + const struct dc_tiling_info *info, const enum surface_pixel_format pixel_format) { /* DCSURF_ADDR_CONFIG still shows up in reg spec, but does not need to be programmed for DCN4x @@ -580,7 +592,7 @@ void hubp401_program_size( void hubp401_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -730,11 +742,13 @@ void hubp401_cursor_set_position( dc_fixpt_from_int(dst_x_offset), param->h_scale_ratio)); - if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0) - hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr); + if (hubp->pos.cur_ctl.bits.cur_enable != cur_en) { + if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0) + hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr); - REG_UPDATE(CURSOR_CONTROL, - CURSOR_ENABLE, cur_en); + REG_UPDATE(CURSOR_CONTROL, + CURSOR_ENABLE, cur_en); + } REG_SET_2(CURSOR_POSITION, 0, CURSOR_X_POSITION, x_pos, @@ -981,11 +995,12 @@ static struct hubp_funcs dcn401_hubp_funcs = { .hubp_program_surface_flip_and_addr = hubp401_program_surface_flip_and_addr, .hubp_program_surface_config = hubp401_program_surface_config, .hubp_is_flip_pending = hubp2_is_flip_pending, - .hubp_setup = hubp401_setup, - .hubp_setup_interdependent = hubp401_setup_interdependent, + .hubp_setup2 = hubp401_setup, + .hubp_setup_interdependent2 = hubp401_setup_interdependent, .hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings, .set_blank = hubp2_set_blank, .set_blank_regs = hubp2_set_blank_regs, + .hubp_reset = hubp_reset, .mem_program_viewport = hubp401_set_viewport, .set_cursor_attributes = hubp32_cursor_set_attributes, .set_cursor_position = hubp401_cursor_set_position, diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h index 9b200a55bf9d..6e1d4c90ddd4 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h @@ -256,29 +256,15 @@ void hubp401_update_mall_sel(struct hubp *hubp, uint32_t mall_sel, bool c_cursor); -void hubp401_vready_at_or_After_vsync(struct hubp *hubp, - struct _vcs_dpi_display_pipe_dest_params_st *pipe_dest); - -void hubp401_program_requestor( - struct hubp *hubp, - struct _vcs_dpi_display_rq_regs_st *rq_regs); - -void hubp401_program_deadline( - struct hubp *hubp, - struct _vcs_dpi_display_dlg_regs_st *dlg_attr, - struct _vcs_dpi_display_ttu_regs_st *ttu_attr); - void hubp401_setup( struct hubp *hubp, - struct _vcs_dpi_display_dlg_regs_st *dlg_attr, - struct _vcs_dpi_display_ttu_regs_st *ttu_attr, - struct _vcs_dpi_display_rq_regs_st *rq_regs, - struct _vcs_dpi_display_pipe_dest_params_st *pipe_dest); + struct dml2_dchub_per_pipe_register_set *pipe_regs, + union dml2_global_sync_programming *pipe_global_sync, + struct dc_crtc_timing *timing); void hubp401_setup_interdependent( struct hubp *hubp, - struct _vcs_dpi_display_dlg_regs_st *dlg_attr, - struct _vcs_dpi_display_ttu_regs_st *ttu_attr); + struct dml2_dchub_per_pipe_register_set *pipe_regs); bool hubp401_program_surface_flip_and_addr( struct hubp *hubp, @@ -290,7 +276,7 @@ void hubp401_dcc_control(struct hubp *hubp, void hubp401_program_tiling( struct dcn20_hubp *hubp2, - const union dc_tiling_info *info, + const struct dc_tiling_info *info, const enum surface_pixel_format pixel_format); void hubp401_program_size( @@ -302,7 +288,7 @@ void hubp401_program_size( void hubp401_program_surface_config( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, @@ -365,4 +351,17 @@ void hubp401_program_3dlut_fl_mode(struct hubp *hubp, enum hubp_3dlut_fl_mode mo void hubp401_clear_tiling(struct hubp *hubp); +void hubp401_vready_at_or_After_vsync(struct hubp *hubp, + union dml2_global_sync_programming *pipe_global_sync, + struct dc_crtc_timing *timing); + +void hubp401_program_requestor( + struct hubp *hubp, + struct dml2_display_rq_regs *rq_regs); + +void hubp401_program_deadline( + struct hubp *hubp, + struct dml2_display_dlg_regs *dlg_attr, + struct dml2_display_ttu_regs *ttu_attr); + #endif /* __DC_HUBP_DCN401_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 681bb92c6069..44e405e9bc97 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -1286,6 +1286,7 @@ void dcn10_plane_atomic_power_down(struct dc *dc, if (hws->funcs.hubp_pg_control) hws->funcs.hubp_pg_control(hws, hubp->inst, false); + hubp->funcs->hubp_reset(hubp); dpp->funcs->dpp_reset(dpp); REG_SET(DC_IP_REQUEST_CNTL, 0, @@ -1447,6 +1448,7 @@ void dcn10_init_pipes(struct dc *dc, struct dc_state *context) /* Disable on the current state so the new one isn't cleared. */ pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + hubp->funcs->hubp_reset(hubp); dpp->funcs->dpp_reset(dpp); pipe_ctx->stream_res.tg = tg; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index b029ec1b26d3..a5e18ab72394 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -1288,7 +1288,7 @@ static void dcn20_power_on_plane_resources( } } -static void dcn20_enable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx, +void dcn20_enable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx, struct dc_state *context) { //if (dc->debug.sanity_checks) { @@ -1467,7 +1467,7 @@ void dcn20_pipe_control_lock( } } -static void dcn20_detect_pipe_changes(struct dc_state *old_state, +void dcn20_detect_pipe_changes(struct dc_state *old_state, struct dc_state *new_state, struct pipe_ctx *old_pipe, struct pipe_ctx *new_pipe) @@ -1655,7 +1655,7 @@ static void dcn20_detect_pipe_changes(struct dc_state *old_state, } } -static void dcn20_update_dchubp_dpp( +void dcn20_update_dchubp_dpp( struct dc *dc, struct pipe_ctx *pipe_ctx, struct dc_state *context) @@ -1678,25 +1678,41 @@ static void dcn20_update_dchubp_dpp( * VTG is within DCHUBBUB which is commond block share by each pipe HUBP. * VTG is 1:1 mapping with OTG. Each pipe HUBP will select which VTG */ + if (pipe_ctx->update_flags.bits.hubp_rq_dlg_ttu) { hubp->funcs->hubp_vtg_sel(hubp, pipe_ctx->stream_res.tg->inst); - hubp->funcs->hubp_setup( - hubp, - &pipe_ctx->dlg_regs, - &pipe_ctx->ttu_regs, - &pipe_ctx->rq_regs, - &pipe_ctx->pipe_dlg_param); + if (hubp->funcs->hubp_setup2) { + hubp->funcs->hubp_setup2( + hubp, + &pipe_ctx->hubp_regs, + &pipe_ctx->global_sync, + &pipe_ctx->stream->timing); + } else { + hubp->funcs->hubp_setup( + hubp, + &pipe_ctx->dlg_regs, + &pipe_ctx->ttu_regs, + &pipe_ctx->rq_regs, + &pipe_ctx->pipe_dlg_param); + } } if (pipe_ctx->update_flags.bits.unbounded_req && hubp->funcs->set_unbounded_requesting) hubp->funcs->set_unbounded_requesting(hubp, pipe_ctx->unbounded_req); - if (pipe_ctx->update_flags.bits.hubp_interdependent) - hubp->funcs->hubp_setup_interdependent( - hubp, - &pipe_ctx->dlg_regs, - &pipe_ctx->ttu_regs); + if (pipe_ctx->update_flags.bits.hubp_interdependent) { + if (hubp->funcs->hubp_setup_interdependent2) { + hubp->funcs->hubp_setup_interdependent2( + hubp, + &pipe_ctx->hubp_regs); + } else { + hubp->funcs->hubp_setup_interdependent( + hubp, + &pipe_ctx->dlg_regs, + &pipe_ctx->ttu_regs); + } + } if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.plane_changed || @@ -1756,10 +1772,9 @@ static void dcn20_update_dchubp_dpp( &pipe_ctx->plane_res.scl_data.viewport_c); viewport_changed = true; } - if (hubp->funcs->hubp_program_mcache_id_and_split_coordinate) - hubp->funcs->hubp_program_mcache_id_and_split_coordinate( - hubp, - &pipe_ctx->mcache_regs); + + if (hubp->funcs->hubp_program_mcache_id_and_split_coordinate) + hubp->funcs->hubp_program_mcache_id_and_split_coordinate(hubp, &pipe_ctx->mcache_regs); /* Any updates are handled in dc interface, just need to apply existing for plane enable */ if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed || @@ -1838,7 +1853,7 @@ static void dcn20_update_dchubp_dpp( hubp->funcs->phantom_hubp_post_enable(hubp); } -static int calculate_vready_offset_for_group(struct pipe_ctx *pipe) +static int dcn20_calculate_vready_offset_for_group(struct pipe_ctx *pipe) { struct pipe_ctx *other_pipe; int vready_offset = pipe->pipe_dlg_param.vready_offset; @@ -1864,6 +1879,30 @@ static int calculate_vready_offset_for_group(struct pipe_ctx *pipe) return vready_offset; } +static void dcn20_program_tg( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct dc_state *context, + struct dce_hwseq *hws) +{ + pipe_ctx->stream_res.tg->funcs->program_global_sync( + pipe_ctx->stream_res.tg, + dcn20_calculate_vready_offset_for_group(pipe_ctx), + pipe_ctx->pipe_dlg_param.vstartup_start, + pipe_ctx->pipe_dlg_param.vupdate_offset, + pipe_ctx->pipe_dlg_param.vupdate_width, + pipe_ctx->pipe_dlg_param.pstate_keepout); + + if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM) + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + + pipe_ctx->stream_res.tg->funcs->set_vtg_params( + pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing, true); + + if (hws->funcs.setup_vupdate_interrupt) + hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx); +} + static void dcn20_program_pipe( struct dc *dc, struct pipe_ctx *pipe_ctx, @@ -1874,33 +1913,17 @@ static void dcn20_program_pipe( /* Only need to unblank on top pipe */ if (resource_is_pipe_type(pipe_ctx, OTG_MASTER)) { if (pipe_ctx->update_flags.bits.enable || - pipe_ctx->update_flags.bits.odm || - pipe_ctx->stream->update_flags.bits.abm_level) + pipe_ctx->update_flags.bits.odm || + pipe_ctx->stream->update_flags.bits.abm_level) hws->funcs.blank_pixel_data(dc, pipe_ctx, - !pipe_ctx->plane_state || - !pipe_ctx->plane_state->visible); + !pipe_ctx->plane_state || + !pipe_ctx->plane_state->visible); } /* Only update TG on top pipe */ if (pipe_ctx->update_flags.bits.global_sync && !pipe_ctx->top_pipe - && !pipe_ctx->prev_odm_pipe) { - pipe_ctx->stream_res.tg->funcs->program_global_sync( - pipe_ctx->stream_res.tg, - calculate_vready_offset_for_group(pipe_ctx), - pipe_ctx->pipe_dlg_param.vstartup_start, - pipe_ctx->pipe_dlg_param.vupdate_offset, - pipe_ctx->pipe_dlg_param.vupdate_width, - pipe_ctx->pipe_dlg_param.pstate_keepout); - - if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM) - pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); - - pipe_ctx->stream_res.tg->funcs->set_vtg_params( - pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing, true); - - if (hws->funcs.setup_vupdate_interrupt) - hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx); - } + && !pipe_ctx->prev_odm_pipe) + dcn20_program_tg(dc, pipe_ctx, context, hws); if (pipe_ctx->update_flags.bits.odm) hws->funcs.update_odm(dc, context, pipe_ctx); @@ -1931,22 +1954,22 @@ static void dcn20_program_pipe( dcn20_update_dchubp_dpp(dc, pipe_ctx, context); if (pipe_ctx->plane_state && (pipe_ctx->update_flags.bits.enable || - pipe_ctx->plane_state->update_flags.bits.hdr_mult)) + pipe_ctx->plane_state->update_flags.bits.hdr_mult)) hws->funcs.set_hdr_multiplier(pipe_ctx); if (hws->funcs.populate_mcm_luts) { if (pipe_ctx->plane_state) { hws->funcs.populate_mcm_luts(dc, pipe_ctx, pipe_ctx->plane_state->mcm_luts, - pipe_ctx->plane_state->lut_bank_a); + pipe_ctx->plane_state->lut_bank_a); pipe_ctx->plane_state->lut_bank_a = !pipe_ctx->plane_state->lut_bank_a; } } if (pipe_ctx->plane_state && - (pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change || - pipe_ctx->plane_state->update_flags.bits.gamma_change || - pipe_ctx->plane_state->update_flags.bits.lut_3d || - pipe_ctx->update_flags.bits.enable)) + (pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change || + pipe_ctx->plane_state->update_flags.bits.gamma_change || + pipe_ctx->plane_state->update_flags.bits.lut_3d || + pipe_ctx->update_flags.bits.enable)) hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state); /* dcn10_translate_regamma_to_hw_format takes 750us to finish @@ -1954,10 +1977,10 @@ static void dcn20_program_pipe( * updating on slave planes */ if (pipe_ctx->update_flags.bits.enable || - pipe_ctx->update_flags.bits.plane_changed || - pipe_ctx->stream->update_flags.bits.out_tf || - (pipe_ctx->plane_state && - pipe_ctx->plane_state->update_flags.bits.output_tf_change)) + pipe_ctx->update_flags.bits.plane_changed || + pipe_ctx->stream->update_flags.bits.out_tf || + (pipe_ctx->plane_state && + pipe_ctx->plane_state->update_flags.bits.output_tf_change)) hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream); /* If the pipe has been enabled or has a different opp, we @@ -1966,7 +1989,7 @@ static void dcn20_program_pipe( * causes a different pipe to be chosen to odm combine with. */ if (pipe_ctx->update_flags.bits.enable - || pipe_ctx->update_flags.bits.opp_changed) { + || pipe_ctx->update_flags.bits.opp_changed) { pipe_ctx->stream_res.opp->funcs->opp_set_dyn_expansion( pipe_ctx->stream_res.opp, @@ -1996,14 +2019,14 @@ static void dcn20_program_pipe( memset(¶ms, 0, sizeof(params)); odm_opp->funcs->opp_program_bit_depth_reduction(odm_opp, ¶ms); dc->hwss.set_disp_pattern_generator(dc, - pipe_ctx, - pipe_ctx->stream_res.test_pattern_params.test_pattern, - pipe_ctx->stream_res.test_pattern_params.color_space, - pipe_ctx->stream_res.test_pattern_params.color_depth, - NULL, - pipe_ctx->stream_res.test_pattern_params.width, - pipe_ctx->stream_res.test_pattern_params.height, - pipe_ctx->stream_res.test_pattern_params.offset); + pipe_ctx, + pipe_ctx->stream_res.test_pattern_params.test_pattern, + pipe_ctx->stream_res.test_pattern_params.color_space, + pipe_ctx->stream_res.test_pattern_params.color_depth, + NULL, + pipe_ctx->stream_res.test_pattern_params.width, + pipe_ctx->stream_res.test_pattern_params.height, + pipe_ctx->stream_res.test_pattern_params.offset); } } @@ -2012,11 +2035,12 @@ void dcn20_program_front_end_for_ctx( struct dc_state *context) { int i; - struct dce_hwseq *hws = dc->hwseq; - DC_LOGGER_INIT(dc->ctx->logger); unsigned int prev_hubp_count = 0; unsigned int hubp_count = 0; - struct pipe_ctx *pipe; + struct dce_hwseq *hws = dc->hwseq; + struct pipe_ctx *pipe = NULL; + + DC_LOGGER_INIT(dc->ctx->logger); if (resource_is_pipe_topology_changed(dc->current_state, context)) resource_log_pipe_topology_update(dc, context); @@ -2029,7 +2053,7 @@ void dcn20_program_front_end_for_ctx( ASSERT(!pipe->plane_state->triplebuffer_flips); /*turn off triple buffer for full update*/ dc->hwss.program_triplebuffer( - dc, pipe, pipe->plane_state->triplebuffer_flips); + dc, pipe, pipe->plane_state->triplebuffer_flips); } } } @@ -2044,30 +2068,31 @@ void dcn20_program_front_end_for_ctx( if (prev_hubp_count == 0 && hubp_count > 0) { if (dc->res_pool->hubbub->funcs->force_pstate_change_control) dc->res_pool->hubbub->funcs->force_pstate_change_control( - dc->res_pool->hubbub, true, false); + dc->res_pool->hubbub, true, false); udelay(500); } /* Set pipe update flags and lock pipes */ for (i = 0; i < dc->res_pool->pipe_count; i++) dcn20_detect_pipe_changes(dc->current_state, context, &dc->current_state->res_ctx.pipe_ctx[i], - &context->res_ctx.pipe_ctx[i]); + &context->res_ctx.pipe_ctx[i]); /* When disabling phantom pipes, turn on phantom OTG first (so we can get double * buffer updates properly) */ for (i = 0; i < dc->res_pool->pipe_count; i++) { struct dc_stream_state *stream = dc->current_state->res_ctx.pipe_ctx[i].stream; + pipe = &dc->current_state->res_ctx.pipe_ctx[i]; if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable && stream && - dc_state_get_pipe_subvp_type(dc->current_state, pipe) == SUBVP_PHANTOM) { + dc_state_get_pipe_subvp_type(dc->current_state, pipe) == SUBVP_PHANTOM) { struct timing_generator *tg = dc->current_state->res_ctx.pipe_ctx[i].stream_res.tg; if (tg->funcs->enable_crtc) { - if (dc->hwseq->funcs.blank_pixel_data) { + if (dc->hwseq->funcs.blank_pixel_data) dc->hwseq->funcs.blank_pixel_data(dc, pipe, true); - } + tg->funcs->enable_crtc(tg); } } @@ -2075,15 +2100,15 @@ void dcn20_program_front_end_for_ctx( /* OTG blank before disabling all front ends */ for (i = 0; i < dc->res_pool->pipe_count; i++) if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable - && !context->res_ctx.pipe_ctx[i].top_pipe - && !context->res_ctx.pipe_ctx[i].prev_odm_pipe - && context->res_ctx.pipe_ctx[i].stream) + && !context->res_ctx.pipe_ctx[i].top_pipe + && !context->res_ctx.pipe_ctx[i].prev_odm_pipe + && context->res_ctx.pipe_ctx[i].stream) hws->funcs.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true); /* Disconnect mpcc */ for (i = 0; i < dc->res_pool->pipe_count; i++) if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable - || context->res_ctx.pipe_ctx[i].update_flags.bits.opp_changed) { + || context->res_ctx.pipe_ctx[i].update_flags.bits.opp_changed) { struct hubbub *hubbub = dc->res_pool->hubbub; /* Phantom pipe DET should be 0, but if a pipe in use is being transitioned to phantom @@ -2093,13 +2118,18 @@ void dcn20_program_front_end_for_ctx( * DET allocation. */ if ((context->res_ctx.pipe_ctx[i].update_flags.bits.disable || - (context->res_ctx.pipe_ctx[i].plane_state && dc_state_get_pipe_subvp_type(context, &context->res_ctx.pipe_ctx[i]) == SUBVP_PHANTOM))) { + (context->res_ctx.pipe_ctx[i].plane_state && + dc_state_get_pipe_subvp_type(context, &context->res_ctx.pipe_ctx[i]) + == SUBVP_PHANTOM))) { if (hubbub->funcs->program_det_size) - hubbub->funcs->program_det_size(hubbub, dc->current_state->res_ctx.pipe_ctx[i].plane_res.hubp->inst, 0); + hubbub->funcs->program_det_size(hubbub, + dc->current_state->res_ctx.pipe_ctx[i].plane_res.hubp->inst, 0); if (dc->res_pool->hubbub->funcs->program_det_segments) - dc->res_pool->hubbub->funcs->program_det_segments(hubbub, dc->current_state->res_ctx.pipe_ctx[i].plane_res.hubp->inst, 0); + dc->res_pool->hubbub->funcs->program_det_segments( + hubbub, dc->current_state->res_ctx.pipe_ctx[i].plane_res.hubp->inst, 0); } - hws->funcs.plane_atomic_disconnect(dc, dc->current_state, &dc->current_state->res_ctx.pipe_ctx[i]); + hws->funcs.plane_atomic_disconnect(dc, dc->current_state, + &dc->current_state->res_ctx.pipe_ctx[i]); DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx); } @@ -2107,9 +2137,9 @@ void dcn20_program_front_end_for_ctx( for (i = 0; i < dc->res_pool->pipe_count; i++) { pipe = &context->res_ctx.pipe_ctx[i]; if (resource_is_pipe_type(pipe, OTG_MASTER) && - !resource_is_pipe_type(pipe, DPP_PIPE) && - pipe->update_flags.bits.odm && - hws->funcs.update_odm) + !resource_is_pipe_type(pipe, DPP_PIPE) && + pipe->update_flags.bits.odm && + hws->funcs.update_odm) hws->funcs.update_odm(dc, context, pipe); } @@ -2127,25 +2157,28 @@ void dcn20_program_front_end_for_ctx( else { /* Don't program phantom pipes in the regular front end programming sequence. * There is an MPO transition case where a pipe being used by a video plane is - * transitioned directly to be a phantom pipe when closing the MPO video. However - * the phantom pipe will program a new HUBP_VTG_SEL (update takes place right away), - * but the MPO still exists until the double buffered update of the main pipe so we - * will get a frame of underflow if the phantom pipe is programmed here. + * transitioned directly to be a phantom pipe when closing the MPO video. + * However the phantom pipe will program a new HUBP_VTG_SEL (update takes place + * right away) but the MPO still exists until the double buffered update of the + * main pipe so we will get a frame of underflow if the phantom pipe is + * programmed here. */ - if (pipe->stream && dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM) + if (pipe->stream && + dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM) dcn20_program_pipe(dc, pipe, context); } pipe = pipe->bottom_pipe; } } + /* Program secondary blending tree and writeback pipes */ pipe = &context->res_ctx.pipe_ctx[i]; if (!pipe->top_pipe && !pipe->prev_odm_pipe - && pipe->stream && pipe->stream->num_wb_info > 0 - && (pipe->update_flags.raw || (pipe->plane_state && pipe->plane_state->update_flags.raw) - || pipe->stream->update_flags.raw) - && hws->funcs.program_all_writeback_pipes_in_tree) + && pipe->stream && pipe->stream->num_wb_info > 0 + && (pipe->update_flags.raw || (pipe->plane_state && pipe->plane_state->update_flags.raw) + || pipe->stream->update_flags.raw) + && hws->funcs.program_all_writeback_pipes_in_tree) hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context); /* Avoid underflow by check of pipe line read when adding 2nd plane. */ @@ -2164,7 +2197,7 @@ void dcn20_program_front_end_for_ctx( * buffered pending status clear and reset opp head pipe's none double buffered * registers to their initial state. */ -static void post_unlock_reset_opp(struct dc *dc, +void dcn20_post_unlock_reset_opp(struct dc *dc, struct pipe_ctx *opp_head) { struct display_stream_compressor *dsc = opp_head->stream_res.dsc; @@ -2201,16 +2234,17 @@ void dcn20_post_unlock_program_front_end( struct dc *dc, struct dc_state *context) { - int i; - const unsigned int TIMEOUT_FOR_PIPE_ENABLE_US = 100000; + // Timeout for pipe enable + unsigned int timeout_us = 100000; unsigned int polling_interval_us = 1; struct dce_hwseq *hwseq = dc->hwseq; + int i; for (i = 0; i < dc->res_pool->pipe_count; i++) if (resource_is_pipe_type(&dc->current_state->res_ctx.pipe_ctx[i], OPP_HEAD) && - !resource_is_pipe_type(&context->res_ctx.pipe_ctx[i], OPP_HEAD)) - post_unlock_reset_opp(dc, - &dc->current_state->res_ctx.pipe_ctx[i]); + !resource_is_pipe_type(&context->res_ctx.pipe_ctx[i], OPP_HEAD)) + dcn20_post_unlock_reset_opp(dc, + &dc->current_state->res_ctx.pipe_ctx[i]); for (i = 0; i < dc->res_pool->pipe_count; i++) if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable) @@ -2226,11 +2260,12 @@ void dcn20_post_unlock_program_front_end( struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; // Don't check flip pending on phantom pipes if (pipe->plane_state && !pipe->top_pipe && pipe->update_flags.bits.enable && - dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM) { + dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM) { struct hubp *hubp = pipe->plane_res.hubp; int j = 0; - for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_US / polling_interval_us - && hubp->funcs->hubp_is_flip_pending(hubp); j++) + + for (j = 0; j < timeout_us / polling_interval_us + && hubp->funcs->hubp_is_flip_pending(hubp); j++) udelay(polling_interval_us); } } @@ -2244,15 +2279,14 @@ void dcn20_post_unlock_program_front_end( * before we've transitioned to 2:1 or 4:1 */ if (resource_is_pipe_type(old_pipe, OTG_MASTER) && resource_is_pipe_type(pipe, OTG_MASTER) && - resource_get_odm_slice_count(old_pipe) < resource_get_odm_slice_count(pipe) && - dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM) { + resource_get_odm_slice_count(old_pipe) < resource_get_odm_slice_count(pipe) && + dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM) { int j = 0; struct timing_generator *tg = pipe->stream_res.tg; - if (tg->funcs->get_optc_double_buffer_pending) { - for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_US / polling_interval_us - && tg->funcs->get_optc_double_buffer_pending(tg); j++) + for (j = 0; j < timeout_us / polling_interval_us + && tg->funcs->get_optc_double_buffer_pending(tg); j++) udelay(polling_interval_us); } } @@ -2260,7 +2294,7 @@ void dcn20_post_unlock_program_front_end( if (dc->res_pool->hubbub->funcs->force_pstate_change_control) dc->res_pool->hubbub->funcs->force_pstate_change_control( - dc->res_pool->hubbub, false, false); + dc->res_pool->hubbub, false, false); for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; @@ -2291,11 +2325,11 @@ void dcn20_post_unlock_program_front_end( return; /* P-State support transitions: - * Natural -> FPO: P-State disabled in prepare, force disallow anytime is safe - * FPO -> Natural: Unforce anytime after FW disable is safe (P-State will assert naturally) - * Unsupported -> FPO: P-State enabled in optimize, force disallow anytime is safe - * FPO -> Unsupported: P-State disabled in prepare, unforce disallow anytime is safe - * FPO <-> SubVP: Force disallow is maintained on the FPO / SubVP pipes + * Natural -> FPO: P-State disabled in prepare, force disallow anytime is safe + * FPO -> Natural: Unforce anytime after FW disable is safe (P-State will assert naturally) + * Unsupported -> FPO: P-State enabled in optimize, force disallow anytime is safe + * FPO -> Unsupported: P-State disabled in prepare, unforce disallow anytime is safe + * FPO <-> SubVP: Force disallow is maintained on the FPO / SubVP pipes */ if (hwseq->funcs.update_force_pstate) dc->hwseq->funcs.update_force_pstate(dc, context); @@ -2310,12 +2344,11 @@ void dcn20_post_unlock_program_front_end( if (hwseq->wa.DEGVIDCN21) dc->res_pool->hubbub->funcs->apply_DEDCN21_147_wa(dc->res_pool->hubbub); - /* WA for stutter underflow during MPO transitions when adding 2nd plane */ if (hwseq->wa.disallow_self_refresh_during_multi_plane_transition) { if (dc->current_state->stream_status[0].plane_count == 1 && - context->stream_status[0].plane_count > 1) { + context->stream_status[0].plane_count > 1) { struct timing_generator *tg = dc->res_pool->timing_generators[0]; @@ -2463,7 +2496,7 @@ bool dcn20_update_bandwidth( pipe_ctx->stream_res.tg->funcs->program_global_sync( pipe_ctx->stream_res.tg, - calculate_vready_offset_for_group(pipe_ctx), + dcn20_calculate_vready_offset_for_group(pipe_ctx), pipe_ctx->pipe_dlg_param.vstartup_start, pipe_ctx->pipe_dlg_param.vupdate_offset, pipe_ctx->pipe_dlg_param.vupdate_width, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h index 5c874f7b0683..9d1ad3b29ca5 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h @@ -154,6 +154,21 @@ void dcn20_setup_gsl_group_as_lock( const struct dc *dc, struct pipe_ctx *pipe_ctx, bool enable); - +void dcn20_detect_pipe_changes( + struct dc_state *old_state, + struct dc_state *new_state, + struct pipe_ctx *old_pipe, + struct pipe_ctx *new_pipe); +void dcn20_enable_plane( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct dc_state *context); +void dcn20_update_dchubp_dpp( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct dc_state *context); +void dcn20_post_unlock_reset_opp( + struct dc *dc, + struct pipe_ctx *opp_head); #endif /* __DC_HWSS_DCN20_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c index 2e6ecf939fbd..ee4de9ddfef4 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c @@ -1399,12 +1399,12 @@ void dcn32_disable_link_output(struct dc_link *link, link_hwss->disable_link_output(link, link_res, signal); link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF; - - if (signal == SIGNAL_TYPE_EDP && - link->dc->hwss.edp_power_control && - !link->skip_implict_edp_power_control) - link->dc->hwss.edp_power_control(link, false); - else if (dmcu != NULL && dmcu->funcs->unlock_phy) + /* + * Add the logic to extract BOTH power up and power down sequences + * from enable/disable link output and only call edp panel control + * in enable_link_dp and disable_link_dp once. + */ + if (dmcu != NULL && dmcu->funcs->unlock_phy) dmcu->funcs->unlock_phy(dmcu); dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index d5f76cc69c73..623cde76debf 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -800,6 +800,7 @@ void dcn35_init_pipes(struct dc *dc, struct dc_state *context) /* Disable on the current state so the new one isn't cleared. */ pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + hubp->funcs->hubp_reset(hubp); dpp->funcs->dpp_reset(dpp); pipe_ctx->stream_res.tg = tg; @@ -956,6 +957,7 @@ void dcn35_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx) /*to do, need to support both case*/ hubp->power_gated = true; + hubp->funcs->hubp_reset(hubp); dpp->funcs->dpp_reset(dpp); pipe_ctx->stream = NULL; @@ -1032,8 +1034,13 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context, if (pipe_ctx->plane_res.dpp || pipe_ctx->stream_res.opp) update_state->pg_pipe_res_update[PG_MPCC][pipe_ctx->plane_res.mpcc_inst] = false; - if (pipe_ctx->stream_res.dsc) + if (pipe_ctx->stream_res.dsc) { update_state->pg_pipe_res_update[PG_DSC][pipe_ctx->stream_res.dsc->inst] = false; + if (dc->caps.sequential_ono) { + update_state->pg_pipe_res_update[PG_HUBP][pipe_ctx->stream_res.dsc->inst] = false; + update_state->pg_pipe_res_update[PG_DPP][pipe_ctx->stream_res.dsc->inst] = false; + } + } if (pipe_ctx->stream_res.opp) update_state->pg_pipe_res_update[PG_OPP][pipe_ctx->stream_res.opp->inst] = false; @@ -1591,3 +1598,37 @@ bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx) return false; } + +/* + * Set powerup to true for every pipe to match pre-OS configuration. + */ +static void dcn35_calc_blocks_to_ungate_for_hw_release(struct dc *dc, struct pg_block_update *update_state) +{ + int i = 0, j = 0; + + memset(update_state, 0, sizeof(struct pg_block_update)); + + for (i = 0; i < dc->res_pool->pipe_count; i++) + for (j = 0; j < PG_HW_PIPE_RESOURCES_NUM_ELEMENT; j++) + update_state->pg_pipe_res_update[j][i] = true; + + update_state->pg_res_update[PG_HPO] = true; + update_state->pg_res_update[PG_DWB] = true; +} + +/* + * The purpose is to power up all gatings to restore optimization to pre-OS env. + * Re-use hwss func and existing PG&RCG flags to decide powerup sequence. + */ +void dcn35_hardware_release(struct dc *dc) +{ + struct pg_block_update pg_update_state; + + dcn35_calc_blocks_to_ungate_for_hw_release(dc, &pg_update_state); + + if (dc->hwss.root_clock_control) + dc->hwss.root_clock_control(dc, &pg_update_state, true); + /*power up required HW block*/ + if (dc->hwss.hw_block_power_up) + dc->hwss.hw_block_power_up(dc, &pg_update_state); +} diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h index e27b3609020f..0b1d6f608edd 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h @@ -99,4 +99,6 @@ void dcn35_set_long_vblank(struct pipe_ctx **pipe_ctx, bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx); +void dcn35_hardware_release(struct dc *dc); + #endif /* __DC_HWSS_DCN35_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c index 5ca8db2b2d03..c7acaf97974c 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c @@ -122,6 +122,11 @@ static const struct hw_sequencer_funcs dcn35_funcs = { .root_clock_control = dcn35_root_clock_control, .set_long_vtotal = dcn35_set_long_vblank, .calculate_pix_rate_divider = dcn32_calculate_pix_rate_divider, + .hardware_release = dcn35_hardware_release, + .detect_pipe_changes = dcn20_detect_pipe_changes, + .enable_plane = dcn20_enable_plane, + .update_dchubp_dpp = dcn20_update_dchubp_dpp, + .post_unlock_reset_opp = dcn20_post_unlock_reset_opp, }; static const struct hwseq_private_funcs dcn35_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c index 8cb0fbd301d8..555a9f590cd7 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c @@ -3,6 +3,7 @@ // Copyright 2024 Advanced Micro Devices, Inc. #include "dm_services.h" +#include "basics/dc_common.h" #include "dm_helpers.h" #include "core_types.h" #include "resource.h" @@ -126,91 +127,6 @@ void dcn401_program_gamut_remap(struct pipe_ctx *pipe_ctx) mpc->funcs->set_gamut_remap(mpc, mpcc_id, &mpc_adjust); } -struct ips_ono_region_state dcn401_read_ono_state(struct dc *dc, uint8_t region) -{ - struct dce_hwseq *hws = dc->hwseq; - struct ips_ono_region_state state = {0, 0}; - - switch (region) { - case 0: - /* dccg, dio, dcio */ - REG_GET_2(DOMAIN22_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 1: - /* dchubbub, dchvm, dchubbubmem */ - REG_GET_2(DOMAIN23_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 2: - /* mpc, opp, optc, dwb */ - REG_GET_2(DOMAIN24_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 3: - /* hpo */ - REG_GET_2(DOMAIN25_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 4: - /* dchubp0, dpp0 */ - REG_GET_2(DOMAIN0_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 5: - /* dsc0 */ - REG_GET_2(DOMAIN16_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 6: - /* dchubp1, dpp1 */ - REG_GET_2(DOMAIN1_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 7: - /* dsc1 */ - REG_GET_2(DOMAIN17_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 8: - /* dchubp2, dpp2 */ - REG_GET_2(DOMAIN2_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 9: - /* dsc2 */ - REG_GET_2(DOMAIN18_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 10: - /* dchubp3, dpp3 */ - REG_GET_2(DOMAIN3_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - case 11: - /* dsc3 */ - REG_GET_2(DOMAIN19_PG_STATUS, - DOMAIN_DESIRED_PWR_STATE, &state.desire_pwr_state, - DOMAIN_PGFSM_PWR_STATUS, &state.current_pwr_state); - break; - default: - break; - } - - return state; -} - void dcn401_init_hw(struct dc *dc) { struct abm **abms = dc->res_pool->multiple_abms; @@ -881,15 +797,15 @@ enum dc_status dcn401_enable_stream_timing( patched_crtc_timing.h_addressable = patched_crtc_timing.h_addressable + pipe_ctx->hblank_borrow; pipe_ctx->stream_res.tg->funcs->program_timing( - pipe_ctx->stream_res.tg, - &patched_crtc_timing, - pipe_ctx->pipe_dlg_param.vready_offset, - pipe_ctx->pipe_dlg_param.vstartup_start, - pipe_ctx->pipe_dlg_param.vupdate_offset, - pipe_ctx->pipe_dlg_param.vupdate_width, - pipe_ctx->pipe_dlg_param.pstate_keepout, - pipe_ctx->stream->signal, - true); + pipe_ctx->stream_res.tg, + &patched_crtc_timing, + (unsigned int)pipe_ctx->global_sync.dcn4x.vready_offset_pixels, + (unsigned int)pipe_ctx->global_sync.dcn4x.vstartup_lines, + (unsigned int)pipe_ctx->global_sync.dcn4x.vupdate_offset_pixels, + (unsigned int)pipe_ctx->global_sync.dcn4x.vupdate_vupdate_width_pixels, + (unsigned int)pipe_ctx->global_sync.dcn4x.pstate_keepout_start_lines, + pipe_ctx->stream->signal, + true); for (i = 0; i < opp_cnt; i++) { opp_heads[i]->stream_res.opp->funcs->opp_pipe_clock_control( @@ -2013,3 +1929,730 @@ void dcn401_reset_hw_ctx_wrap( } } } + +static unsigned int dcn401_calculate_vready_offset_for_group(struct pipe_ctx *pipe) +{ + struct pipe_ctx *other_pipe; + unsigned int vready_offset = pipe->global_sync.dcn4x.vready_offset_pixels; + + /* Always use the largest vready_offset of all connected pipes */ + for (other_pipe = pipe->bottom_pipe; other_pipe != NULL; other_pipe = other_pipe->bottom_pipe) { + if (other_pipe->global_sync.dcn4x.vready_offset_pixels > vready_offset) + vready_offset = other_pipe->global_sync.dcn4x.vready_offset_pixels; + } + for (other_pipe = pipe->top_pipe; other_pipe != NULL; other_pipe = other_pipe->top_pipe) { + if (other_pipe->global_sync.dcn4x.vready_offset_pixels > vready_offset) + vready_offset = other_pipe->global_sync.dcn4x.vready_offset_pixels; + } + for (other_pipe = pipe->next_odm_pipe; other_pipe != NULL; other_pipe = other_pipe->next_odm_pipe) { + if (other_pipe->global_sync.dcn4x.vready_offset_pixels > vready_offset) + vready_offset = other_pipe->global_sync.dcn4x.vready_offset_pixels; + } + for (other_pipe = pipe->prev_odm_pipe; other_pipe != NULL; other_pipe = other_pipe->prev_odm_pipe) { + if (other_pipe->global_sync.dcn4x.vready_offset_pixels > vready_offset) + vready_offset = other_pipe->global_sync.dcn4x.vready_offset_pixels; + } + + return vready_offset; +} + +static void dcn401_program_tg( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct dc_state *context, + struct dce_hwseq *hws) +{ + pipe_ctx->stream_res.tg->funcs->program_global_sync( + pipe_ctx->stream_res.tg, + dcn401_calculate_vready_offset_for_group(pipe_ctx), + (unsigned int)pipe_ctx->global_sync.dcn4x.vstartup_lines, + (unsigned int)pipe_ctx->global_sync.dcn4x.vupdate_offset_pixels, + (unsigned int)pipe_ctx->global_sync.dcn4x.vupdate_vupdate_width_pixels, + (unsigned int)pipe_ctx->global_sync.dcn4x.pstate_keepout_start_lines); + + if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM) + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + + pipe_ctx->stream_res.tg->funcs->set_vtg_params( + pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing, true); + + if (hws->funcs.setup_vupdate_interrupt) + hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx); +} + +static void dcn401_program_pipe( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct dc_state *context) +{ + struct dce_hwseq *hws = dc->hwseq; + + /* Only need to unblank on top pipe */ + if (resource_is_pipe_type(pipe_ctx, OTG_MASTER)) { + if (pipe_ctx->update_flags.bits.enable || + pipe_ctx->update_flags.bits.odm || + pipe_ctx->stream->update_flags.bits.abm_level) + hws->funcs.blank_pixel_data(dc, pipe_ctx, + !pipe_ctx->plane_state || + !pipe_ctx->plane_state->visible); + } + + /* Only update TG on top pipe */ + if (pipe_ctx->update_flags.bits.global_sync && !pipe_ctx->top_pipe + && !pipe_ctx->prev_odm_pipe) + dcn401_program_tg(dc, pipe_ctx, context, hws); + + if (pipe_ctx->update_flags.bits.odm) + hws->funcs.update_odm(dc, context, pipe_ctx); + + if (pipe_ctx->update_flags.bits.enable) { + if (hws->funcs.enable_plane) + hws->funcs.enable_plane(dc, pipe_ctx, context); + else + dc->hwss.enable_plane(dc, pipe_ctx, context); + + if (dc->res_pool->hubbub->funcs->force_wm_propagate_to_pipes) + dc->res_pool->hubbub->funcs->force_wm_propagate_to_pipes(dc->res_pool->hubbub); + } + + if (pipe_ctx->update_flags.bits.det_size) { + if (dc->res_pool->hubbub->funcs->program_det_size) + dc->res_pool->hubbub->funcs->program_det_size( + dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->det_buffer_size_kb); + if (dc->res_pool->hubbub->funcs->program_det_segments) + dc->res_pool->hubbub->funcs->program_det_segments( + dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->hubp_regs.det_size); + } + + if (pipe_ctx->update_flags.raw || + (pipe_ctx->plane_state && pipe_ctx->plane_state->update_flags.raw) || + pipe_ctx->stream->update_flags.raw) + dc->hwss.update_dchubp_dpp(dc, pipe_ctx, context); + + if (pipe_ctx->plane_state && (pipe_ctx->update_flags.bits.enable || + pipe_ctx->plane_state->update_flags.bits.hdr_mult)) + hws->funcs.set_hdr_multiplier(pipe_ctx); + + if (hws->funcs.populate_mcm_luts) { + if (pipe_ctx->plane_state) { + hws->funcs.populate_mcm_luts(dc, pipe_ctx, pipe_ctx->plane_state->mcm_luts, + pipe_ctx->plane_state->lut_bank_a); + pipe_ctx->plane_state->lut_bank_a = !pipe_ctx->plane_state->lut_bank_a; + } + } + + if (pipe_ctx->plane_state && + (pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change || + pipe_ctx->plane_state->update_flags.bits.gamma_change || + pipe_ctx->plane_state->update_flags.bits.lut_3d || + pipe_ctx->update_flags.bits.enable)) + hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state); + + /* dcn10_translate_regamma_to_hw_format takes 750us to finish + * only do gamma programming for powering on, internal memcmp to avoid + * updating on slave planes + */ + if (pipe_ctx->update_flags.bits.enable || + pipe_ctx->update_flags.bits.plane_changed || + pipe_ctx->stream->update_flags.bits.out_tf || + (pipe_ctx->plane_state && + pipe_ctx->plane_state->update_flags.bits.output_tf_change)) + hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream); + + /* If the pipe has been enabled or has a different opp, we + * should reprogram the fmt. This deals with cases where + * interation between mpc and odm combine on different streams + * causes a different pipe to be chosen to odm combine with. + */ + if (pipe_ctx->update_flags.bits.enable + || pipe_ctx->update_flags.bits.opp_changed) { + + pipe_ctx->stream_res.opp->funcs->opp_set_dyn_expansion( + pipe_ctx->stream_res.opp, + COLOR_SPACE_YCBCR601, + pipe_ctx->stream->timing.display_color_depth, + pipe_ctx->stream->signal); + + pipe_ctx->stream_res.opp->funcs->opp_program_fmt( + pipe_ctx->stream_res.opp, + &pipe_ctx->stream->bit_depth_params, + &pipe_ctx->stream->clamping); + } + + /* Set ABM pipe after other pipe configurations done */ + if ((pipe_ctx->plane_state && pipe_ctx->plane_state->visible)) { + if (pipe_ctx->stream_res.abm) { + dc->hwss.set_pipe(pipe_ctx); + pipe_ctx->stream_res.abm->funcs->set_abm_level(pipe_ctx->stream_res.abm, + pipe_ctx->stream->abm_level); + } + } + + if (pipe_ctx->update_flags.bits.test_pattern_changed) { + struct output_pixel_processor *odm_opp = pipe_ctx->stream_res.opp; + struct bit_depth_reduction_params params; + + memset(¶ms, 0, sizeof(params)); + odm_opp->funcs->opp_program_bit_depth_reduction(odm_opp, ¶ms); + dc->hwss.set_disp_pattern_generator(dc, + pipe_ctx, + pipe_ctx->stream_res.test_pattern_params.test_pattern, + pipe_ctx->stream_res.test_pattern_params.color_space, + pipe_ctx->stream_res.test_pattern_params.color_depth, + NULL, + pipe_ctx->stream_res.test_pattern_params.width, + pipe_ctx->stream_res.test_pattern_params.height, + pipe_ctx->stream_res.test_pattern_params.offset); + } +} + +void dcn401_program_front_end_for_ctx( + struct dc *dc, + struct dc_state *context) +{ + int i; + unsigned int prev_hubp_count = 0; + unsigned int hubp_count = 0; + struct dce_hwseq *hws = dc->hwseq; + struct pipe_ctx *pipe = NULL; + + DC_LOGGER_INIT(dc->ctx->logger); + + if (resource_is_pipe_topology_changed(dc->current_state, context)) + resource_log_pipe_topology_update(dc, context); + + if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + + if (!pipe->top_pipe && !pipe->prev_odm_pipe && pipe->plane_state) { + if (pipe->plane_state->triplebuffer_flips) + BREAK_TO_DEBUGGER(); + + /*turn off triple buffer for full update*/ + dc->hwss.program_triplebuffer( + dc, pipe, pipe->plane_state->triplebuffer_flips); + } + } + } + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (dc->current_state->res_ctx.pipe_ctx[i].plane_state) + prev_hubp_count++; + if (context->res_ctx.pipe_ctx[i].plane_state) + hubp_count++; + } + + if (prev_hubp_count == 0 && hubp_count > 0) { + if (dc->res_pool->hubbub->funcs->force_pstate_change_control) + dc->res_pool->hubbub->funcs->force_pstate_change_control( + dc->res_pool->hubbub, true, false); + udelay(500); + } + + /* Set pipe update flags and lock pipes */ + for (i = 0; i < dc->res_pool->pipe_count; i++) + dc->hwss.detect_pipe_changes(dc->current_state, context, &dc->current_state->res_ctx.pipe_ctx[i], + &context->res_ctx.pipe_ctx[i]); + + /* When disabling phantom pipes, turn on phantom OTG first (so we can get double + * buffer updates properly) + */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct dc_stream_state *stream = dc->current_state->res_ctx.pipe_ctx[i].stream; + + pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable && stream && + dc_state_get_pipe_subvp_type(dc->current_state, pipe) == SUBVP_PHANTOM) { + struct timing_generator *tg = dc->current_state->res_ctx.pipe_ctx[i].stream_res.tg; + + if (tg->funcs->enable_crtc) { + if (dc->hwseq->funcs.blank_pixel_data) + dc->hwseq->funcs.blank_pixel_data(dc, pipe, true); + + tg->funcs->enable_crtc(tg); + } + } + } + /* OTG blank before disabling all front ends */ + for (i = 0; i < dc->res_pool->pipe_count; i++) + if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable + && !context->res_ctx.pipe_ctx[i].top_pipe + && !context->res_ctx.pipe_ctx[i].prev_odm_pipe + && context->res_ctx.pipe_ctx[i].stream) + hws->funcs.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true); + + + /* Disconnect mpcc */ + for (i = 0; i < dc->res_pool->pipe_count; i++) + if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable + || context->res_ctx.pipe_ctx[i].update_flags.bits.opp_changed) { + struct hubbub *hubbub = dc->res_pool->hubbub; + + /* Phantom pipe DET should be 0, but if a pipe in use is being transitioned to phantom + * then we want to do the programming here (effectively it's being disabled). If we do + * the programming later the DET won't be updated until the OTG for the phantom pipe is + * turned on (i.e. in an MCLK switch) which can come in too late and cause issues with + * DET allocation. + */ + if ((context->res_ctx.pipe_ctx[i].update_flags.bits.disable || + (context->res_ctx.pipe_ctx[i].plane_state && + dc_state_get_pipe_subvp_type(context, &context->res_ctx.pipe_ctx[i]) == + SUBVP_PHANTOM))) { + if (hubbub->funcs->program_det_size) + hubbub->funcs->program_det_size(hubbub, + dc->current_state->res_ctx.pipe_ctx[i].plane_res.hubp->inst, 0); + if (dc->res_pool->hubbub->funcs->program_det_segments) + dc->res_pool->hubbub->funcs->program_det_segments( + hubbub, dc->current_state->res_ctx.pipe_ctx[i].plane_res.hubp->inst, 0); + } + hws->funcs.plane_atomic_disconnect(dc, dc->current_state, + &dc->current_state->res_ctx.pipe_ctx[i]); + DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx); + } + + /* update ODM for blanked OTG master pipes */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + if (resource_is_pipe_type(pipe, OTG_MASTER) && + !resource_is_pipe_type(pipe, DPP_PIPE) && + pipe->update_flags.bits.odm && + hws->funcs.update_odm) + hws->funcs.update_odm(dc, context, pipe); + } + + /* + * Program all updated pipes, order matters for mpcc setup. Start with + * top pipe and program all pipes that follow in order + */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->plane_state && !pipe->top_pipe) { + while (pipe) { + if (hws->funcs.program_pipe) + hws->funcs.program_pipe(dc, pipe, context); + else { + /* Don't program phantom pipes in the regular front end programming sequence. + * There is an MPO transition case where a pipe being used by a video plane is + * transitioned directly to be a phantom pipe when closing the MPO video. + * However the phantom pipe will program a new HUBP_VTG_SEL (update takes place + * right away) but the MPO still exists until the double buffered update of the + * main pipe so we will get a frame of underflow if the phantom pipe is + * programmed here. + */ + if (pipe->stream && + dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM) + dcn401_program_pipe(dc, pipe, context); + } + + pipe = pipe->bottom_pipe; + } + } + + /* Program secondary blending tree and writeback pipes */ + pipe = &context->res_ctx.pipe_ctx[i]; + if (!pipe->top_pipe && !pipe->prev_odm_pipe + && pipe->stream && pipe->stream->num_wb_info > 0 + && (pipe->update_flags.raw || (pipe->plane_state && pipe->plane_state->update_flags.raw) + || pipe->stream->update_flags.raw) + && hws->funcs.program_all_writeback_pipes_in_tree) + hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context); + + /* Avoid underflow by check of pipe line read when adding 2nd plane. */ + if (hws->wa.wait_hubpret_read_start_during_mpo_transition && + !pipe->top_pipe && + pipe->stream && + pipe->plane_res.hubp->funcs->hubp_wait_pipe_read_start && + dc->current_state->stream_status[0].plane_count == 1 && + context->stream_status[0].plane_count > 1) { + pipe->plane_res.hubp->funcs->hubp_wait_pipe_read_start(pipe->plane_res.hubp); + } + } +} + +void dcn401_post_unlock_program_front_end( + struct dc *dc, + struct dc_state *context) +{ + // Timeout for pipe enable + unsigned int timeout_us = 100000; + unsigned int polling_interval_us = 1; + struct dce_hwseq *hwseq = dc->hwseq; + int i; + + DC_LOGGER_INIT(dc->ctx->logger); + + for (i = 0; i < dc->res_pool->pipe_count; i++) + if (resource_is_pipe_type(&dc->current_state->res_ctx.pipe_ctx[i], OPP_HEAD) && + !resource_is_pipe_type(&context->res_ctx.pipe_ctx[i], OPP_HEAD)) + dc->hwss.post_unlock_reset_opp(dc, + &dc->current_state->res_ctx.pipe_ctx[i]); + + for (i = 0; i < dc->res_pool->pipe_count; i++) + if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable) + dc->hwss.disable_plane(dc, dc->current_state, &dc->current_state->res_ctx.pipe_ctx[i]); + + /* + * If we are enabling a pipe, we need to wait for pending clear as this is a critical + * part of the enable operation otherwise, DM may request an immediate flip which + * will cause HW to perform an "immediate enable" (as opposed to "vsync enable") which + * is unsupported on DCN. + */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + // Don't check flip pending on phantom pipes + if (pipe->plane_state && !pipe->top_pipe && pipe->update_flags.bits.enable && + dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM) { + struct hubp *hubp = pipe->plane_res.hubp; + int j = 0; + + for (j = 0; j < timeout_us / polling_interval_us + && hubp->funcs->hubp_is_flip_pending(hubp); j++) + udelay(polling_interval_us); + } + } + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + /* When going from a smaller ODM slice count to larger, we must ensure double + * buffer update completes before we return to ensure we don't reduce DISPCLK + * before we've transitioned to 2:1 or 4:1 + */ + if (resource_is_pipe_type(old_pipe, OTG_MASTER) && resource_is_pipe_type(pipe, OTG_MASTER) && + resource_get_odm_slice_count(old_pipe) < resource_get_odm_slice_count(pipe) && + dc_state_get_pipe_subvp_type(context, pipe) != SUBVP_PHANTOM) { + int j = 0; + struct timing_generator *tg = pipe->stream_res.tg; + + if (tg->funcs->get_optc_double_buffer_pending) { + for (j = 0; j < timeout_us / polling_interval_us + && tg->funcs->get_optc_double_buffer_pending(tg); j++) + udelay(polling_interval_us); + } + } + } + + if (dc->res_pool->hubbub->funcs->force_pstate_change_control) + dc->res_pool->hubbub->funcs->force_pstate_change_control( + dc->res_pool->hubbub, false, false); + + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->plane_state && !pipe->top_pipe) { + /* Program phantom pipe here to prevent a frame of underflow in the MPO transition + * case (if a pipe being used for a video plane transitions to a phantom pipe, it + * can underflow due to HUBP_VTG_SEL programming if done in the regular front end + * programming sequence). + */ + while (pipe) { + if (pipe->stream && dc_state_get_pipe_subvp_type(context, pipe) == SUBVP_PHANTOM) { + /* When turning on the phantom pipe we want to run through the + * entire enable sequence, so apply all the "enable" flags. + */ + if (dc->hwss.apply_update_flags_for_phantom) + dc->hwss.apply_update_flags_for_phantom(pipe); + if (dc->hwss.update_phantom_vp_position) + dc->hwss.update_phantom_vp_position(dc, context, pipe); + dcn401_program_pipe(dc, pipe, context); + } + pipe = pipe->bottom_pipe; + } + } + } + + if (!hwseq) + return; + + /* P-State support transitions: + * Natural -> FPO: P-State disabled in prepare, force disallow anytime is safe + * FPO -> Natural: Unforce anytime after FW disable is safe (P-State will assert naturally) + * Unsupported -> FPO: P-State enabled in optimize, force disallow anytime is safe + * FPO -> Unsupported: P-State disabled in prepare, unforce disallow anytime is safe + * FPO <-> SubVP: Force disallow is maintained on the FPO / SubVP pipes + */ + if (hwseq->funcs.update_force_pstate) + dc->hwseq->funcs.update_force_pstate(dc, context); + + /* Only program the MALL registers after all the main and phantom pipes + * are done programming. + */ + if (hwseq->funcs.program_mall_pipe_config) + hwseq->funcs.program_mall_pipe_config(dc, context); + + /* WA to apply WM setting*/ + if (hwseq->wa.DEGVIDCN21) + dc->res_pool->hubbub->funcs->apply_DEDCN21_147_wa(dc->res_pool->hubbub); + + + /* WA for stutter underflow during MPO transitions when adding 2nd plane */ + if (hwseq->wa.disallow_self_refresh_during_multi_plane_transition) { + + if (dc->current_state->stream_status[0].plane_count == 1 && + context->stream_status[0].plane_count > 1) { + + struct timing_generator *tg = dc->res_pool->timing_generators[0]; + + dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub, false); + + hwseq->wa_state.disallow_self_refresh_during_multi_plane_transition_applied = true; + hwseq->wa_state.disallow_self_refresh_during_multi_plane_transition_applied_on_frame = + tg->funcs->get_frame_count(tg); + } + } +} + +bool dcn401_update_bandwidth( + struct dc *dc, + struct dc_state *context) +{ + int i; + struct dce_hwseq *hws = dc->hwseq; + + /* recalculate DML parameters */ + if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) + return false; + + /* apply updated bandwidth parameters */ + dc->hwss.prepare_bandwidth(dc, context); + + /* update hubp configs for all pipes */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->plane_state == NULL) + continue; + + if (pipe_ctx->top_pipe == NULL) { + bool blank = !is_pipe_tree_visible(pipe_ctx); + + pipe_ctx->stream_res.tg->funcs->program_global_sync( + pipe_ctx->stream_res.tg, + dcn401_calculate_vready_offset_for_group(pipe_ctx), + (unsigned int)pipe_ctx->global_sync.dcn4x.vstartup_lines, + (unsigned int)pipe_ctx->global_sync.dcn4x.vupdate_offset_pixels, + (unsigned int)pipe_ctx->global_sync.dcn4x.vupdate_vupdate_width_pixels, + (unsigned int)pipe_ctx->global_sync.dcn4x.pstate_keepout_start_lines); + + pipe_ctx->stream_res.tg->funcs->set_vtg_params( + pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing, false); + + if (pipe_ctx->prev_odm_pipe == NULL) + hws->funcs.blank_pixel_data(dc, pipe_ctx, blank); + + if (hws->funcs.setup_vupdate_interrupt) + hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx); + } + + if (pipe_ctx->plane_res.hubp->funcs->hubp_setup2) + pipe_ctx->plane_res.hubp->funcs->hubp_setup2( + pipe_ctx->plane_res.hubp, + &pipe_ctx->hubp_regs, + &pipe_ctx->global_sync, + &pipe_ctx->stream->timing); + } + + return true; +} + +void dcn401_detect_pipe_changes(struct dc_state *old_state, + struct dc_state *new_state, + struct pipe_ctx *old_pipe, + struct pipe_ctx *new_pipe) +{ + bool old_is_phantom = dc_state_get_pipe_subvp_type(old_state, old_pipe) == SUBVP_PHANTOM; + bool new_is_phantom = dc_state_get_pipe_subvp_type(new_state, new_pipe) == SUBVP_PHANTOM; + + unsigned int old_pipe_vready_offset_pixels = old_pipe->global_sync.dcn4x.vready_offset_pixels; + unsigned int new_pipe_vready_offset_pixels = new_pipe->global_sync.dcn4x.vready_offset_pixels; + unsigned int old_pipe_vstartup_lines = old_pipe->global_sync.dcn4x.vstartup_lines; + unsigned int new_pipe_vstartup_lines = new_pipe->global_sync.dcn4x.vstartup_lines; + unsigned int old_pipe_vupdate_offset_pixels = old_pipe->global_sync.dcn4x.vupdate_offset_pixels; + unsigned int new_pipe_vupdate_offset_pixels = new_pipe->global_sync.dcn4x.vupdate_offset_pixels; + unsigned int old_pipe_vupdate_width_pixels = old_pipe->global_sync.dcn4x.vupdate_vupdate_width_pixels; + unsigned int new_pipe_vupdate_width_pixels = new_pipe->global_sync.dcn4x.vupdate_vupdate_width_pixels; + + new_pipe->update_flags.raw = 0; + + /* If non-phantom pipe is being transitioned to a phantom pipe, + * set disable and return immediately. This is because the pipe + * that was previously in use must be fully disabled before we + * can "enable" it as a phantom pipe (since the OTG will certainly + * be different). The post_unlock sequence will set the correct + * update flags to enable the phantom pipe. + */ + if (old_pipe->plane_state && !old_is_phantom && + new_pipe->plane_state && new_is_phantom) { + new_pipe->update_flags.bits.disable = 1; + return; + } + + if (resource_is_pipe_type(new_pipe, OTG_MASTER) && + resource_is_odm_topology_changed(new_pipe, old_pipe)) + /* Detect odm changes */ + new_pipe->update_flags.bits.odm = 1; + + /* Exit on unchanged, unused pipe */ + if (!old_pipe->plane_state && !new_pipe->plane_state) + return; + /* Detect pipe enable/disable */ + if (!old_pipe->plane_state && new_pipe->plane_state) { + new_pipe->update_flags.bits.enable = 1; + new_pipe->update_flags.bits.mpcc = 1; + new_pipe->update_flags.bits.dppclk = 1; + new_pipe->update_flags.bits.hubp_interdependent = 1; + new_pipe->update_flags.bits.hubp_rq_dlg_ttu = 1; + new_pipe->update_flags.bits.unbounded_req = 1; + new_pipe->update_flags.bits.gamut_remap = 1; + new_pipe->update_flags.bits.scaler = 1; + new_pipe->update_flags.bits.viewport = 1; + new_pipe->update_flags.bits.det_size = 1; + if (new_pipe->stream->test_pattern.type != DP_TEST_PATTERN_VIDEO_MODE && + new_pipe->stream_res.test_pattern_params.width != 0 && + new_pipe->stream_res.test_pattern_params.height != 0) + new_pipe->update_flags.bits.test_pattern_changed = 1; + if (!new_pipe->top_pipe && !new_pipe->prev_odm_pipe) { + new_pipe->update_flags.bits.odm = 1; + new_pipe->update_flags.bits.global_sync = 1; + } + return; + } + + /* For SubVP we need to unconditionally enable because any phantom pipes are + * always removed then newly added for every full updates whenever SubVP is in use. + * The remove-add sequence of the phantom pipe always results in the pipe + * being blanked in enable_stream_timing (DPG). + */ + if (new_pipe->stream && dc_state_get_pipe_subvp_type(new_state, new_pipe) == SUBVP_PHANTOM) + new_pipe->update_flags.bits.enable = 1; + + /* Phantom pipes are effectively disabled, if the pipe was previously phantom + * we have to enable + */ + if (old_pipe->plane_state && old_is_phantom && + new_pipe->plane_state && !new_is_phantom) + new_pipe->update_flags.bits.enable = 1; + + if (old_pipe->plane_state && !new_pipe->plane_state) { + new_pipe->update_flags.bits.disable = 1; + return; + } + + /* Detect plane change */ + if (old_pipe->plane_state != new_pipe->plane_state) + new_pipe->update_flags.bits.plane_changed = true; + + /* Detect top pipe only changes */ + if (resource_is_pipe_type(new_pipe, OTG_MASTER)) { + /* Detect global sync changes */ + if ((old_pipe_vready_offset_pixels != new_pipe_vready_offset_pixels) + || (old_pipe_vstartup_lines != new_pipe_vstartup_lines) + || (old_pipe_vupdate_offset_pixels != new_pipe_vupdate_offset_pixels) + || (old_pipe_vupdate_width_pixels != new_pipe_vupdate_width_pixels)) + new_pipe->update_flags.bits.global_sync = 1; + } + + if (old_pipe->det_buffer_size_kb != new_pipe->det_buffer_size_kb) + new_pipe->update_flags.bits.det_size = 1; + + /* + * Detect opp / tg change, only set on change, not on enable + * Assume mpcc inst = pipe index, if not this code needs to be updated + * since mpcc is what is affected by these. In fact all of our sequence + * makes this assumption at the moment with how hubp reset is matched to + * same index mpcc reset. + */ + if (old_pipe->stream_res.opp != new_pipe->stream_res.opp) + new_pipe->update_flags.bits.opp_changed = 1; + if (old_pipe->stream_res.tg != new_pipe->stream_res.tg) + new_pipe->update_flags.bits.tg_changed = 1; + + /* + * Detect mpcc blending changes, only dpp inst and opp matter here, + * mpccs getting removed/inserted update connected ones during their own + * programming + */ + if (old_pipe->plane_res.dpp != new_pipe->plane_res.dpp + || old_pipe->stream_res.opp != new_pipe->stream_res.opp) + new_pipe->update_flags.bits.mpcc = 1; + + /* Detect dppclk change */ + if (old_pipe->plane_res.bw.dppclk_khz != new_pipe->plane_res.bw.dppclk_khz) + new_pipe->update_flags.bits.dppclk = 1; + + /* Check for scl update */ + if (memcmp(&old_pipe->plane_res.scl_data, &new_pipe->plane_res.scl_data, sizeof(struct scaler_data))) + new_pipe->update_flags.bits.scaler = 1; + /* Check for vp update */ + if (memcmp(&old_pipe->plane_res.scl_data.viewport, &new_pipe->plane_res.scl_data.viewport, sizeof(struct rect)) + || memcmp(&old_pipe->plane_res.scl_data.viewport_c, + &new_pipe->plane_res.scl_data.viewport_c, sizeof(struct rect))) + new_pipe->update_flags.bits.viewport = 1; + + /* Detect dlg/ttu/rq updates */ + { + struct dml2_display_dlg_regs old_dlg_regs = old_pipe->hubp_regs.dlg_regs; + struct dml2_display_ttu_regs old_ttu_regs = old_pipe->hubp_regs.ttu_regs; + struct dml2_display_rq_regs old_rq_regs = old_pipe->hubp_regs.rq_regs; + struct dml2_display_dlg_regs *new_dlg_regs = &new_pipe->hubp_regs.dlg_regs; + struct dml2_display_ttu_regs *new_ttu_regs = &new_pipe->hubp_regs.ttu_regs; + struct dml2_display_rq_regs *new_rq_regs = &new_pipe->hubp_regs.rq_regs; + + /* Detect pipe interdependent updates */ + if ((old_dlg_regs.dst_y_prefetch != new_dlg_regs->dst_y_prefetch) + || (old_dlg_regs.vratio_prefetch != new_dlg_regs->vratio_prefetch) + || (old_dlg_regs.vratio_prefetch_c != new_dlg_regs->vratio_prefetch_c) + || (old_dlg_regs.dst_y_per_vm_vblank != new_dlg_regs->dst_y_per_vm_vblank) + || (old_dlg_regs.dst_y_per_row_vblank != new_dlg_regs->dst_y_per_row_vblank) + || (old_dlg_regs.dst_y_per_vm_flip != new_dlg_regs->dst_y_per_vm_flip) + || (old_dlg_regs.dst_y_per_row_flip != new_dlg_regs->dst_y_per_row_flip) + || (old_dlg_regs.refcyc_per_meta_chunk_vblank_l != new_dlg_regs->refcyc_per_meta_chunk_vblank_l) + || (old_dlg_regs.refcyc_per_meta_chunk_vblank_c != new_dlg_regs->refcyc_per_meta_chunk_vblank_c) + || (old_dlg_regs.refcyc_per_meta_chunk_flip_l != new_dlg_regs->refcyc_per_meta_chunk_flip_l) + || (old_dlg_regs.refcyc_per_line_delivery_pre_l != new_dlg_regs->refcyc_per_line_delivery_pre_l) + || (old_dlg_regs.refcyc_per_line_delivery_pre_c != new_dlg_regs->refcyc_per_line_delivery_pre_c) + || (old_ttu_regs.refcyc_per_req_delivery_pre_l != new_ttu_regs->refcyc_per_req_delivery_pre_l) + || (old_ttu_regs.refcyc_per_req_delivery_pre_c != new_ttu_regs->refcyc_per_req_delivery_pre_c) + || (old_ttu_regs.refcyc_per_req_delivery_pre_cur0 != + new_ttu_regs->refcyc_per_req_delivery_pre_cur0) + || (old_ttu_regs.min_ttu_vblank != new_ttu_regs->min_ttu_vblank) + || (old_ttu_regs.qos_level_flip != new_ttu_regs->qos_level_flip)) { + old_dlg_regs.dst_y_prefetch = new_dlg_regs->dst_y_prefetch; + old_dlg_regs.vratio_prefetch = new_dlg_regs->vratio_prefetch; + old_dlg_regs.vratio_prefetch_c = new_dlg_regs->vratio_prefetch_c; + old_dlg_regs.dst_y_per_vm_vblank = new_dlg_regs->dst_y_per_vm_vblank; + old_dlg_regs.dst_y_per_row_vblank = new_dlg_regs->dst_y_per_row_vblank; + old_dlg_regs.dst_y_per_vm_flip = new_dlg_regs->dst_y_per_vm_flip; + old_dlg_regs.dst_y_per_row_flip = new_dlg_regs->dst_y_per_row_flip; + old_dlg_regs.refcyc_per_meta_chunk_vblank_l = new_dlg_regs->refcyc_per_meta_chunk_vblank_l; + old_dlg_regs.refcyc_per_meta_chunk_vblank_c = new_dlg_regs->refcyc_per_meta_chunk_vblank_c; + old_dlg_regs.refcyc_per_meta_chunk_flip_l = new_dlg_regs->refcyc_per_meta_chunk_flip_l; + old_dlg_regs.refcyc_per_line_delivery_pre_l = new_dlg_regs->refcyc_per_line_delivery_pre_l; + old_dlg_regs.refcyc_per_line_delivery_pre_c = new_dlg_regs->refcyc_per_line_delivery_pre_c; + old_ttu_regs.refcyc_per_req_delivery_pre_l = new_ttu_regs->refcyc_per_req_delivery_pre_l; + old_ttu_regs.refcyc_per_req_delivery_pre_c = new_ttu_regs->refcyc_per_req_delivery_pre_c; + old_ttu_regs.refcyc_per_req_delivery_pre_cur0 = new_ttu_regs->refcyc_per_req_delivery_pre_cur0; + old_ttu_regs.min_ttu_vblank = new_ttu_regs->min_ttu_vblank; + old_ttu_regs.qos_level_flip = new_ttu_regs->qos_level_flip; + new_pipe->update_flags.bits.hubp_interdependent = 1; + } + /* Detect any other updates to ttu/rq/dlg */ + if (memcmp(&old_dlg_regs, new_dlg_regs, sizeof(old_dlg_regs)) || + memcmp(&old_ttu_regs, new_ttu_regs, sizeof(old_ttu_regs)) || + memcmp(&old_rq_regs, new_rq_regs, sizeof(old_rq_regs))) + new_pipe->update_flags.bits.hubp_rq_dlg_ttu = 1; + } + + if (old_pipe->unbounded_req != new_pipe->unbounded_req) + new_pipe->update_flags.bits.unbounded_req = 1; + + if (memcmp(&old_pipe->stream_res.test_pattern_params, + &new_pipe->stream_res.test_pattern_params, sizeof(struct test_pattern_params))) { + new_pipe->update_flags.bits.test_pattern_changed = 1; + } +} diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.h index 28a513dfc005..17cea748789e 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.h @@ -63,8 +63,6 @@ void dcn401_set_cursor_position(struct pipe_ctx *pipe_ctx); bool dcn401_apply_idle_power_optimizations(struct dc *dc, bool enable); -struct ips_ono_region_state dcn401_read_ono_state(struct dc *dc, - uint8_t region); void dcn401_wait_for_dcc_meta_propagation(const struct dc *dc, const struct pipe_ctx *top_pipe_to_program); @@ -96,5 +94,12 @@ void dcn401_reset_hw_ctx_wrap( struct dc *dc, struct dc_state *context); void dcn401_perform_3dlut_wa_unlock(struct pipe_ctx *pipe_ctx); - +void dcn401_program_front_end_for_ctx(struct dc *dc, struct dc_state *context); +void dcn401_post_unlock_program_front_end(struct dc *dc, struct dc_state *context); +bool dcn401_update_bandwidth(struct dc *dc, struct dc_state *context); +void dcn401_detect_pipe_changes( + struct dc_state *old_state, + struct dc_state *new_state, + struct pipe_ctx *old_pipe, + struct pipe_ctx *new_pipe); #endif /* __DC_HWSS_DCN401_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c index b30f665d98a6..44cb376f97c1 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c @@ -17,9 +17,9 @@ static const struct hw_sequencer_funcs dcn401_funcs = { .init_hw = dcn401_init_hw, .apply_ctx_to_hw = dce110_apply_ctx_to_hw, .apply_ctx_for_surface = NULL, - .program_front_end_for_ctx = dcn20_program_front_end_for_ctx, + .program_front_end_for_ctx = dcn401_program_front_end_for_ctx, .wait_for_pending_cleared = dcn10_wait_for_pending_cleared, - .post_unlock_program_front_end = dcn20_post_unlock_program_front_end, + .post_unlock_program_front_end = dcn401_post_unlock_program_front_end, .update_plane_addr = dcn20_update_plane_addr, .update_dchub = dcn10_update_dchub, .update_pending_status = dcn10_update_pending_status, @@ -42,7 +42,7 @@ static const struct hw_sequencer_funcs dcn401_funcs = { .cursor_lock = dcn10_cursor_lock, .prepare_bandwidth = dcn401_prepare_bandwidth, .optimize_bandwidth = dcn401_optimize_bandwidth, - .update_bandwidth = dcn20_update_bandwidth, + .update_bandwidth = dcn401_update_bandwidth, .set_drr = dcn10_set_drr, .get_position = dcn10_get_position, .set_static_screen_control = dcn31_set_static_screen_control, @@ -99,6 +99,10 @@ static const struct hw_sequencer_funcs dcn401_funcs = { .fams2_global_control_lock_fast = dcn401_fams2_global_control_lock_fast, .program_outstanding_updates = dcn401_program_outstanding_updates, .wait_for_all_pending_updates = dcn30_wait_for_all_pending_updates, + .detect_pipe_changes = dcn401_detect_pipe_changes, + .enable_plane = dcn20_enable_plane, + .update_dchubp_dpp = dcn20_update_dchubp_dpp, + .post_unlock_reset_opp = dcn20_post_unlock_reset_opp, }; static const struct hwseq_private_funcs dcn401_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h index a5bb10d7b160..a7d66cfd93c9 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h @@ -194,7 +194,6 @@ enum block_sequence_func { DMUB_SUBVP_SAVE_SURF_ADDR, HUBP_WAIT_FOR_DCC_META_PROP, DMUB_FAMS2_GLOBAL_CONTROL_LOCK_FAST, - }; struct block_sequence { @@ -458,6 +457,18 @@ struct hw_sequencer_funcs { struct dc_state *context); void (*setup_hpo_hw_control)(const struct dce_hwseq *hws, bool enable); void (*wait_for_all_pending_updates)(const struct pipe_ctx *pipe_ctx); + void (*detect_pipe_changes)(struct dc_state *old_state, + struct dc_state *new_state, + struct pipe_ctx *old_pipe, + struct pipe_ctx *new_pipe); + void (*enable_plane)(struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct dc_state *context); + void (*update_dchubp_dpp)(struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct dc_state *context); + void (*post_unlock_reset_opp)(struct dc *dc, + struct pipe_ctx *opp_head); }; void color_space_to_black_color( @@ -485,11 +496,12 @@ void get_hdr_visual_confirm_color( void get_mpctree_visual_confirm_color( struct pipe_ctx *pipe_ctx, struct tg_color *color); - +void get_vabc_visual_confirm_color( + struct pipe_ctx *pipe_ctx, + struct tg_color *color); void get_subvp_visual_confirm_color( struct pipe_ctx *pipe_ctx, struct tg_color *color); - void get_fams2_visual_confirm_color( struct dc *dc, struct dc_state *context, diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 06a420154888..d558efc6e12f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -217,6 +217,7 @@ struct resource_funcs { */ int (*get_power_profile)(const struct dc_state *context); unsigned int (*get_det_buffer_size)(const struct dc_state *context); + unsigned int (*get_vstartup_for_pipe)(struct pipe_ctx *pipe_ctx); }; struct audio_support{ @@ -465,6 +466,7 @@ struct pipe_ctx { unsigned int surface_size_in_mall_bytes; struct dml2_dchub_per_pipe_register_set hubp_regs; struct dml2_hubp_pipe_mcache_regs mcache_regs; + union dml2_global_sync_programming global_sync; struct dwbc *dwbc; struct mcif_wb *mcif_wb; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index 2d06067ff36d..c14d64687a3d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -306,6 +306,9 @@ struct clk_mgr_funcs { */ void (*set_hard_min_memclk)(struct clk_mgr *clk_mgr, bool current_mode); + int (*get_hard_min_memclk)(struct clk_mgr *clk_mgr); + int (*get_hard_min_fclk)(struct clk_mgr *clk_mgr); + /* Send message to PMFW to set hard max memclk frequency to highest DPM */ void (*set_hard_max_memclk)(struct clk_mgr *clk_mgr); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index d0878fc0cc94..b610beb075d5 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -42,6 +42,7 @@ #include "cursor_reg_cache.h" #include "dml2/dml21/inc/dml_top_dchub_registers.h" +#include "dml2/dml21/inc/dml_top_types.h" #define OPP_ID_INVALID 0xf #define MAX_TTU 0xffffff @@ -144,14 +145,26 @@ struct hubp_funcs { struct _vcs_dpi_display_rq_regs_st *rq_regs, struct _vcs_dpi_display_pipe_dest_params_st *pipe_dest); + void (*hubp_setup2)( + struct hubp *hubp, + struct dml2_dchub_per_pipe_register_set *pipe_regs, + union dml2_global_sync_programming *pipe_global_sync, + struct dc_crtc_timing *timing); + void (*hubp_setup_interdependent)( struct hubp *hubp, struct _vcs_dpi_display_dlg_regs_st *dlg_regs, struct _vcs_dpi_display_ttu_regs_st *ttu_regs); + void (*hubp_setup_interdependent2)( + struct hubp *hubp, + struct dml2_dchub_per_pipe_register_set *pipe_regs); + void (*dcc_control)(struct hubp *hubp, bool enable, enum hubp_ind_block_size blk_size); + void (*hubp_reset)(struct hubp *hubp); + void (*mem_program_viewport)( struct hubp *hubp, const struct rect *viewport, @@ -165,7 +178,7 @@ struct hubp_funcs { void (*hubp_program_pte_vm)( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, enum dc_rotation_angle rotation); void (*hubp_set_vm_system_aperture_settings)( @@ -179,7 +192,7 @@ struct hubp_funcs { void (*hubp_program_surface_config)( struct hubp *hubp, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h index af9183f5d69b..08c16ba52a51 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h @@ -168,6 +168,14 @@ struct link_encoder_funcs { struct link_encoder *enc, enum encoder_type_select sel, uint32_t hpo_inst); + void (*enable_dpia_output)(struct link_encoder *enc, + const struct dc_link_settings *link_settings, + uint8_t dpia_id, + uint8_t digmode, + uint8_t fec_rdy); + void (*disable_dpia_output)(struct link_encoder *link_enc, + uint8_t dpia_id, + uint8_t digmode); }; /* diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h index 4f5d102455ca..42fbc70f7056 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h @@ -150,7 +150,7 @@ struct mem_input_funcs { void (*mem_input_program_pte_vm)( struct mem_input *mem_input, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, enum dc_rotation_angle rotation); void (*mem_input_set_vm_system_aperture_settings)( @@ -164,7 +164,7 @@ struct mem_input_funcs { void (*mem_input_program_surface_config)( struct mem_input *mem_input, enum surface_pixel_format format, - union dc_tiling_info *tiling_info, + struct dc_tiling_info *tiling_info, struct plane_size *plane_size, enum dc_rotation_angle rotation, struct dc_plane_dcc_param *dcc, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/optc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/optc.h index 03cbcbb36f1c..6fdc9809280c 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/optc.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/optc.h @@ -210,7 +210,7 @@ void optc1_enable_crtc_reset(struct timing_generator *optc, bool optc1_configure_crc(struct timing_generator *optc, const struct crc_params *params); -bool optc1_get_crc(struct timing_generator *optc, +bool optc1_get_crc(struct timing_generator *optc, uint8_t idx, uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h index b74e18cc1e66..9885cb3c310f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h @@ -141,6 +141,9 @@ struct crc_params { bool continuous_mode; bool enable; + + uint8_t crc_eng_inst; + bool reset; }; /** @@ -291,7 +294,7 @@ struct timing_generator_funcs { * @get_crc: Get CRCs for the given timing generator. Return false if * CRCs are not enabled (via configure_crc). */ - bool (*get_crc)(struct timing_generator *tg, + bool (*get_crc)(struct timing_generator *tg, uint8_t idx, uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb); void (*program_manual_trigger)(struct timing_generator *optc); diff --git a/drivers/gpu/drm/amd/display/dc/inc/link.h b/drivers/gpu/drm/amd/display/dc/inc/link.h index f04292086c08..fd1f9d3db039 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/link.h +++ b/drivers/gpu/drm/amd/display/dc/inc/link.h @@ -148,6 +148,10 @@ struct link_service { const struct dc_stream_state *stream, const unsigned int num_streams); + uint32_t (*dp_required_hblank_size_bytes)( + const struct dc_link *link, + struct dp_audio_bandwidth_params *audio_params); + /*************************** DPMS *************************************/ void (*set_dpms_on)(struct dc_state *state, struct pipe_ctx *pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c index ff8fe1a94965..96febabf464a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c +++ b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c @@ -251,7 +251,7 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link) link_training_settings.lttpr_mode = dp_decide_lttpr_mode(link, &link->cur_link_settings); - if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && + if (((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && link_training_settings.lttpr_mode == LTTPR_MODE_TRANSPARENT) dp_fixed_vs_pe_read_lane_adjust( link, @@ -646,7 +646,7 @@ bool dp_set_test_pattern( if (IS_DP_PHY_PATTERN(test_pattern)) { /* Set DPCD Lane Settings before running test pattern */ if (p_link_settings != NULL) { - if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && + if (((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && p_link_settings->lttpr_mode == LTTPR_MODE_TRANSPARENT) { dp_fixed_vs_pe_set_retimer_lane_settings( link, diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c index 3e47a6735912..06faa461067b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c @@ -164,7 +164,9 @@ void disable_dio_link_output(struct dc_link *link, { struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); - link_enc->funcs->disable_output(link_enc, signal); + if (link_enc != NULL) + link_enc->funcs->disable_output(link_enc, signal); + link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); } diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c index 348ea4cb832d..a6d1d7641ab4 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c @@ -187,7 +187,7 @@ static const struct link_hwss dio_fixed_vs_pe_retimer_link_hwss = { bool requires_fixed_vs_pe_retimer_dio_link_hwss(const struct dc_link *link) { - return (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN); + return ((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN); } const struct link_hwss *get_dio_fixed_vs_pe_retimer_link_hwss(void) diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c index 6499807af72a..36adf95744fe 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c @@ -77,17 +77,74 @@ static void set_dio_dpia_lane_settings(struct dc_link *link, { } +static void enable_dpia_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal, + enum clock_source_id clock_source, + const struct dc_link_settings *link_settings) +{ + struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + + if (link_enc != NULL) { + if (link->dc->config.enable_dpia_pre_training && link_enc->funcs->enable_dpia_output) { + uint8_t fec_rdy = link->dc->link_srv->dp_should_enable_fec(link); + uint8_t digmode = dc_is_dp_sst_signal(signal) ? DIG_SST_MODE : DIG_MST_MODE; + + link_enc->funcs->enable_dpia_output( + link_enc, + link_settings, + link->ddc_hw_inst, + digmode, + fec_rdy); + } else { + if (dc_is_dp_sst_signal(signal)) + link_enc->funcs->enable_dp_output( + link_enc, + link_settings, + clock_source); + else + link_enc->funcs->enable_dp_mst_output( + link_enc, + link_settings, + clock_source); + } + + } + + link->dc->link_srv->dp_trace_source_sequence(link, + DPCD_SOURCE_SEQ_AFTER_ENABLE_LINK_PHY); +} + +static void disable_dpia_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal) +{ + struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + + if (link_enc != NULL) { + if (link->dc->config.enable_dpia_pre_training && link_enc->funcs->disable_dpia_output) { + uint8_t digmode = dc_is_dp_sst_signal(signal) ? DIG_SST_MODE : DIG_MST_MODE; + + link_enc->funcs->disable_dpia_output(link_enc, link->ddc_hw_inst, digmode); + } else + link_enc->funcs->disable_output(link_enc, signal); + } + + link->dc->link_srv->dp_trace_source_sequence(link, + DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); +} + static const struct link_hwss dpia_link_hwss = { .setup_stream_encoder = setup_dio_stream_encoder, .reset_stream_encoder = reset_dio_stream_encoder, .setup_stream_attribute = setup_dio_stream_attribute, - .disable_link_output = disable_dio_link_output, + .disable_link_output = disable_dpia_link_output, .setup_audio_output = setup_dio_audio_output, .enable_audio_packet = enable_dio_audio_packet, .disable_audio_packet = disable_dio_audio_packet, .ext = { .set_throttled_vcp_size = set_dio_throttled_vcp_size, - .enable_dp_link_output = enable_dio_dp_link_output, + .enable_dp_link_output = enable_dpia_link_output, .set_dp_link_test_pattern = set_dio_dpia_link_test_pattern, .set_dp_lane_settings = set_dio_dpia_lane_settings, .update_stream_allocation_table = update_dpia_stream_allocation_table, diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.h b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.h index ad16ec5d9bb7..259e0f4775e1 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.h +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.h @@ -27,6 +27,9 @@ #include "link_hwss.h" +#define DIG_SST_MODE 0 +#define DIG_MST_MODE 5 + const struct link_hwss *get_dpia_link_hwss(void); bool can_use_dpia_link_hwss(const struct dc_link *link, const struct link_resource *link_res); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index e026c728042a..550e1a098fa2 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -829,7 +829,8 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, if (link->dc->debug.skip_detection_link_training || dc_is_embedded_signal(link->local_sink->sink_signal) || - link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + !link->dc->config.enable_dpia_pre_training)) { destrictive = false; } else if (link_dp_get_encoding_format(&max_link_cap) == DP_8b_10b_ENCODING) { diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index 60e64e0138a3..ec7de9c01fab 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -772,6 +772,20 @@ static bool dp_set_dsc_on_rx(struct pipe_ctx *pipe_ctx, bool enable) return result; } +static bool dp_set_hblank_reduction_on_rx(struct pipe_ctx *pipe_ctx) +{ + struct dc *dc = pipe_ctx->stream->ctx->dc; + struct dc_stream_state *stream = pipe_ctx->stream; + bool result = false; + + if (dc_is_virtual_signal(stream->signal)) + result = true; + else + result = dm_helpers_dp_write_hblank_reduction(dc->ctx, stream); + return result; +} + + /* The stream with these settings can be sent (unblanked) only after DSC was enabled on RX first, * i.e. after dp_enable_dsc_on_rx() had been called */ @@ -1960,8 +1974,8 @@ static void enable_link_hdmi(struct pipe_ctx *pipe_ctx) if (dc_is_hdmi_signal(pipe_ctx->stream->signal)) { unsigned short masked_chip_caps = pipe_ctx->stream->link->chip_caps & - EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK; - if (masked_chip_caps == EXT_DISPLAY_PATH_CAPS__HDMI20_TISN65DP159RSBT) { + AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK; + if (masked_chip_caps == AMD_EXT_DISPLAY_PATH_CAPS__HDMI20_TISN65DP159RSBT) { /* DP159, Retimer settings */ eng_id = pipe_ctx->stream_res.stream_enc->id; @@ -1972,7 +1986,7 @@ static void enable_link_hdmi(struct pipe_ctx *pipe_ctx) write_i2c_default_retimer_setting(pipe_ctx, is_vga_mode, is_over_340mhz); } - } else if (masked_chip_caps == EXT_DISPLAY_PATH_CAPS__HDMI20_PI3EQX1204) { + } else if (masked_chip_caps == AMD_EXT_DISPLAY_PATH_CAPS__HDMI20_PI3EQX1204) { /* PI3EQX1204, Redriver settings */ write_i2c_redriver_setting(pipe_ctx, is_over_340mhz); } @@ -2028,7 +2042,7 @@ static enum dc_status enable_link_dp(struct dc_state *state, int lt_attempts = LINK_TRAINING_ATTEMPTS; // Increase retry count if attempting DP1.x on FIXED_VS link - if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && + if (((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) lt_attempts = 10; @@ -2043,7 +2057,8 @@ static enum dc_status enable_link_dp(struct dc_state *state, /* Train with fallback when enabling DPIA link. Conventional links are * trained with fallback during sink detection. */ - if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + !link->dc->config.enable_dpia_pre_training) do_fallback = true; /* @@ -2379,13 +2394,13 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) enum engine_id eng_id = pipe_ctx->stream_res.stream_enc->id; unsigned short masked_chip_caps = link->chip_caps & - EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK; + AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK; //Need to inform that sink is going to use legacy HDMI mode. write_scdc_data( link->ddc, 165000,//vbios only handles 165Mhz. false); - if (masked_chip_caps == EXT_DISPLAY_PATH_CAPS__HDMI20_TISN65DP159RSBT) { + if (masked_chip_caps == AMD_EXT_DISPLAY_PATH_CAPS__HDMI20_TISN65DP159RSBT) { /* DP159, Retimer settings */ if (get_ext_hdmi_settings(pipe_ctx, eng_id, &settings)) write_i2c_retimer_setting(pipe_ctx, @@ -2393,7 +2408,7 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) else write_i2c_default_retimer_setting(pipe_ctx, false, false); - } else if (masked_chip_caps == EXT_DISPLAY_PATH_CAPS__HDMI20_PI3EQX1204) { + } else if (masked_chip_caps == AMD_EXT_DISPLAY_PATH_CAPS__HDMI20_PI3EQX1204) { /* PI3EQX1204, Redriver settings */ write_i2c_redriver_setting(pipe_ctx, false); } @@ -2533,6 +2548,15 @@ void link_set_dpms_on( if (pipe_ctx->stream->dpms_off) return; + /* For Dp tunneling link, a pending HPD means that we have a race condition between processing + * current link and processing the pending HPD. If we enable the link now, we may end up with a + * link that is not actually connected to a sink. So we skip enabling the link in this case. + */ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && link->is_hpd_pending) { + DC_LOG_DEBUG("%s, Link%d HPD is pending, not enable it.\n", __func__, link->link_index); + return; + } + /* Have to setup DSC before DIG FE and BE are connected (which happens before the * link training). This is to make sure the bandwidth sent to DIG BE won't be * bigger than what the link and/or DIG BE can handle. VBID[6]/CompressedStream_flag @@ -2598,6 +2622,9 @@ void link_set_dpms_on( } } + if (dc_is_dp_signal(pipe_ctx->stream->signal)) + dp_set_hblank_reduction_on_rx(pipe_ctx); + if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) allocate_usb4_bandwidth(pipe_ctx->stream); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c index 5e1b5ab9fbc6..a7877d57a00f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c @@ -101,6 +101,7 @@ static void construct_link_service_validation(struct link_service *link_srv) link_srv->validate_mode_timing = link_validate_mode_timing; link_srv->dp_link_bandwidth_kbps = dp_link_bandwidth_kbps; link_srv->validate_dpia_bandwidth = link_validate_dpia_bandwidth; + link_srv->dp_required_hblank_size_bytes = dp_required_hblank_size_bytes; } /* link dpms owns the programming sequence of stream's dpms state associated @@ -698,7 +699,7 @@ static bool construct_phy(struct dc_link *link, link->chip_caps); } - if (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) { + if ((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) { link->bios_forced_drive_settings.VOLTAGE_SWING = (bios->integrated_info->ext_disp_conn_info.fixdpvoltageswing & 0x3); link->bios_forced_drive_settings.PRE_EMPHASIS = diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c index 60f15a9ba7a5..29606fda029d 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c @@ -409,3 +409,182 @@ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const un return dpia_validate_usb4_bw(dpia_link, bw_needed, num_dpias); } + +struct dp_audio_layout_config { + uint8_t layouts_per_sample_denom; + uint8_t symbols_per_layout; + uint8_t max_layouts_per_audio_sdp; +}; + +static void get_audio_layout_config( + uint32_t channel_count, + enum dp_link_encoding encoding, + struct dp_audio_layout_config *output) +{ + memset(output, 0, sizeof(struct dp_audio_layout_config)); + + /* Assuming L-PCM audio. Current implementation uses max 1 layout per SDP, + * with each layout being the same size (8ch layout). + */ + if (encoding == DP_8b_10b_ENCODING) { + if (channel_count == 2) { + output->layouts_per_sample_denom = 4; + output->symbols_per_layout = 40; + output->max_layouts_per_audio_sdp = 1; + } else if (channel_count == 8 || channel_count == 6) { + output->layouts_per_sample_denom = 1; + output->symbols_per_layout = 40; + output->max_layouts_per_audio_sdp = 1; + } + } else if (encoding == DP_128b_132b_ENCODING) { + if (channel_count == 2) { + output->layouts_per_sample_denom = 4; + output->symbols_per_layout = 10; + output->max_layouts_per_audio_sdp = 1; + } else if (channel_count == 8 || channel_count == 6) { + output->layouts_per_sample_denom = 1; + output->symbols_per_layout = 10; + output->max_layouts_per_audio_sdp = 1; + } + } +} + +static uint32_t get_av_stream_map_lane_count( + enum dp_link_encoding encoding, + enum dc_lane_count lane_count, + bool is_mst) +{ + uint32_t av_stream_map_lane_count = 0; + + if (encoding == DP_8b_10b_ENCODING) { + if (!is_mst) + av_stream_map_lane_count = lane_count; + else + av_stream_map_lane_count = 4; + } else if (encoding == DP_128b_132b_ENCODING) { + av_stream_map_lane_count = 4; + } + + ASSERT(av_stream_map_lane_count != 0); + + return av_stream_map_lane_count; +} + +static uint32_t get_audio_sdp_overhead( + enum dp_link_encoding encoding, + enum dc_lane_count lane_count, + bool is_mst) +{ + uint32_t audio_sdp_overhead = 0; + + if (encoding == DP_8b_10b_ENCODING) { + if (is_mst) + audio_sdp_overhead = 16; /* 4 * 2 + 8 */ + else + audio_sdp_overhead = lane_count * 2 + 8; + } else if (encoding == DP_128b_132b_ENCODING) { + audio_sdp_overhead = 10; /* 4 x 2.5 */ + } + + ASSERT(audio_sdp_overhead != 0); + + return audio_sdp_overhead; +} + +/* Current calculation only applicable for 8b/10b MST and 128b/132b SST/MST. + */ +static uint32_t calculate_overhead_hblank_bw_in_symbols( + uint32_t max_slice_h) +{ + uint32_t overhead_hblank_bw = 0; /* in stream symbols */ + + overhead_hblank_bw += max_slice_h * 4; /* EOC overhead */ + overhead_hblank_bw += 12; /* Main link overhead (VBID, BS/BE) */ + + return overhead_hblank_bw; +} + +uint32_t dp_required_hblank_size_bytes( + const struct dc_link *link, + struct dp_audio_bandwidth_params *audio_params) +{ + /* Main logic from dce_audio is duplicated here, with the main + * difference being: + * - Pre-determined lane count of 4 + * - Assumed 16 dsc slices for worst case + * - Assumed SDP split disabled for worst case + * TODO: Unify logic from dce_audio to prevent duplicated logic. + */ + + const struct dc_crtc_timing *timing = audio_params->crtc_timing; + const uint32_t channel_count = audio_params->channel_count; + const uint32_t sample_rate_hz = audio_params->sample_rate_hz; + const enum dp_link_encoding link_encoding = audio_params->link_encoding; + + // 8b/10b MST and 128b/132b are always 4 logical lanes. + const uint32_t lane_count = 4; + const bool is_mst = (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT); + // Maximum slice count is with ODM 4:1, 4 slices per DSC + const uint32_t max_slices_h = 16; + + const uint32_t av_stream_map_lane_count = get_av_stream_map_lane_count( + link_encoding, lane_count, is_mst); + const uint32_t audio_sdp_overhead = get_audio_sdp_overhead( + link_encoding, lane_count, is_mst); + struct dp_audio_layout_config layout_config; + + if (link_encoding == DP_8b_10b_ENCODING && link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT) + return 0; + + get_audio_layout_config( + channel_count, link_encoding, &layout_config); + + /* DP spec recommends between 1.05 to 1.1 safety margin to prevent sample under-run */ + struct fixed31_32 audio_sdp_margin = dc_fixpt_from_fraction(110, 100); + struct fixed31_32 horizontal_line_freq_khz = dc_fixpt_from_fraction( + timing->pix_clk_100hz, (long long)timing->h_total * 10); + struct fixed31_32 samples_per_line; + struct fixed31_32 layouts_per_line; + struct fixed31_32 symbols_per_sdp_max_layout; + struct fixed31_32 remainder; + uint32_t num_sdp_with_max_layouts; + uint32_t required_symbols_per_hblank; + uint32_t required_bytes_per_hblank = 0; + + samples_per_line = dc_fixpt_from_fraction(sample_rate_hz, 1000); + samples_per_line = dc_fixpt_div(samples_per_line, horizontal_line_freq_khz); + layouts_per_line = dc_fixpt_div_int(samples_per_line, layout_config.layouts_per_sample_denom); + // HBlank expansion usage assumes SDP split disabled to allow for worst case. + layouts_per_line = dc_fixpt_from_int(dc_fixpt_ceil(layouts_per_line)); + + num_sdp_with_max_layouts = dc_fixpt_floor( + dc_fixpt_div_int(layouts_per_line, layout_config.max_layouts_per_audio_sdp)); + symbols_per_sdp_max_layout = dc_fixpt_from_int( + layout_config.max_layouts_per_audio_sdp * layout_config.symbols_per_layout); + symbols_per_sdp_max_layout = dc_fixpt_add_int(symbols_per_sdp_max_layout, audio_sdp_overhead); + symbols_per_sdp_max_layout = dc_fixpt_mul(symbols_per_sdp_max_layout, audio_sdp_margin); + required_symbols_per_hblank = num_sdp_with_max_layouts; + required_symbols_per_hblank *= ((dc_fixpt_ceil(symbols_per_sdp_max_layout) + av_stream_map_lane_count) / + av_stream_map_lane_count) * av_stream_map_lane_count; + + if (num_sdp_with_max_layouts != dc_fixpt_ceil( + dc_fixpt_div_int(layouts_per_line, layout_config.max_layouts_per_audio_sdp))) { + remainder = dc_fixpt_sub_int(layouts_per_line, + num_sdp_with_max_layouts * layout_config.max_layouts_per_audio_sdp); + remainder = dc_fixpt_mul_int(remainder, layout_config.symbols_per_layout); + remainder = dc_fixpt_add_int(remainder, audio_sdp_overhead); + remainder = dc_fixpt_mul(remainder, audio_sdp_margin); + required_symbols_per_hblank += ((dc_fixpt_ceil(remainder) + av_stream_map_lane_count) / + av_stream_map_lane_count) * av_stream_map_lane_count; + } + + required_symbols_per_hblank += calculate_overhead_hblank_bw_in_symbols(max_slices_h); + + if (link_encoding == DP_8b_10b_ENCODING) + required_bytes_per_hblank = required_symbols_per_hblank; // 8 bits per 8b/10b symbol + else if (link_encoding == DP_128b_132b_ENCODING) + required_bytes_per_hblank = required_symbols_per_hblank * 4; // 32 bits per 128b/132b symbol + + return required_bytes_per_hblank; +} + diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.h b/drivers/gpu/drm/amd/display/dc/link/link_validation.h index 595fb05946e9..bf398c49c3e8 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.h +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.h @@ -37,4 +37,9 @@ uint32_t dp_link_bandwidth_kbps( const struct dc_link *link, const struct dc_link_settings *link_settings); + +uint32_t dp_required_hblank_size_bytes( + const struct dc_link *link, + struct dp_audio_bandwidth_params *audio_params); + #endif /* __LINK_VALIDATION_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_ddc.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_ddc.c index d6d5bbf2108c..267180e7bc48 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_ddc.c @@ -505,7 +505,7 @@ bool try_to_configure_aux_timeout(struct ddc_service *ddc, bool result = false; struct ddc *ddc_pin = ddc->ddc_pin; - if ((ddc->link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && + if (((ddc->link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && !ddc->link->dc->debug.disable_fixed_vs_aux_timeout_wa && ddc->ctx->dce_version == DCN_VERSION_3_1) { /* Fixed VS workaround for AUX timeout */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index ce9d799d2386..44c3023a7731 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -1554,7 +1554,7 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link) /* If this chip cap is set, at least one retimer must exist in the chain * Override count to 1 if we receive a known bad count (0 or an invalid value) */ - if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && + if (((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && (dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == 0)) { /* If you see this message consistently, either the host platform has FIXED_VS flag * incorrectly configured or the sink device is returning an invalid count. @@ -1779,6 +1779,11 @@ static bool retrieve_link_cap(struct dc_link *link) link->test_pattern_enabled = false; link->compliance_test_state.raw = 0; + link->dpcd_caps.receive_port0_cap.raw[0] = + dpcd_data[DP_RECEIVE_PORT_0_CAP_0 - DP_DPCD_REV]; + link->dpcd_caps.receive_port0_cap.raw[1] = + dpcd_data[DP_RECEIVE_PORT_0_BUFFER_SIZE - DP_DPCD_REV]; + /* read sink count */ core_link_read_dpcd(link, DP_SINK_COUNT, @@ -2307,6 +2312,14 @@ bool dp_verify_link_cap_with_retries( } else { link->verified_link_cap = last_verified_link_cap; } + + /* For Dp tunneling link, a pending HPD means that we have a race condition between processing + * current link and processing the pending HPD. Since the training is failed, we should just brak + * the loop so that we have chance to process the pending HPD. + */ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && link->is_hpd_pending) + break; + fsleep(10 * 1000); } diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c index 48abeaa88678..a08403c022ea 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c @@ -226,6 +226,8 @@ static void handle_hpd_irq_replay_sink(struct dc_link *link) replay_configuration.bits.STATE_TRANSITION_ERROR_STATUS) { bool allow_active; + link->replay_settings.config.replay_error_status.raw |= replay_error_status.raw; + if (link->replay_settings.config.force_disable_desync_error_check) return; @@ -237,6 +239,9 @@ static void handle_hpd_irq_replay_sink(struct dc_link *link) &replay_configuration.raw, sizeof(replay_configuration.raw)); + /* Update desync error counter */ + link->replay_settings.replay_desync_error_fail_count++; + /* Acknowledge and clear error bits */ dm_helpers_dp_write_dpcd( link->ctx, @@ -408,7 +413,8 @@ bool dp_handle_hpd_rx_irq(struct dc_link *link, if (hpd_irq_dpcd_data.bytes.device_service_irq.bits.AUTOMATED_TEST) { // Workaround for DP 1.4a LL Compliance CTS as USB4 has to share encoders unlike DP and USBC - if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + !link->dc->config.enable_dpia_pre_training) link->skip_fallback_on_link_loss = true; device_service_clear.bits.AUTOMATED_TEST = 1; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c index bafa52a0165a..2c73ac87cd66 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c @@ -104,7 +104,7 @@ void dp_set_hw_lane_settings( // Don't return here if using FIXED_VS link HWSS and encoding is 128b/132b if ((link_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && !is_immediate_downstream(link, offset) && - (!(link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) || + (!((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) || link_dp_get_encoding_format(&link_settings->link_settings) == DP_8b_10b_ENCODING)) return; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c index 754c895e1bfb..88d4288cde0f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c @@ -739,7 +739,7 @@ void override_training_settings( if (overrides->ffe_preset != NULL) lt_settings->ffe_preset = overrides->ffe_preset; /* Override HW lane settings with BIOS forced values if present */ - if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && + if ((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && lt_settings->lttpr_mode == LTTPR_MODE_TRANSPARENT) { lt_settings->voltage_swing = &link->bios_forced_drive_settings.VOLTAGE_SWING; lt_settings->pre_emphasis = &link->bios_forced_drive_settings.PRE_EMPHASIS; @@ -1574,7 +1574,7 @@ enum link_training_result dp_perform_link_training( * Per DP specs starting from here, DPTX device shall not issue * Non-LT AUX transactions inside training mode. */ - if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && encoding == DP_8b_10b_ENCODING) + if (((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && encoding == DP_8b_10b_ENCODING) status = dp_perform_fixed_vs_pe_training_sequence(link, link_res, <_settings); else if (encoding == DP_8b_10b_ENCODING) status = dp_perform_8b_10b_link_training(link, link_res, <_settings); diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c index 097d06023e64..19d5ebc6763c 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c @@ -302,7 +302,6 @@ void optc1_program_timing( /* Enable stereo - only when we need to pack 3D frame. Other types * of stereo handled in explicit call */ - if (optc->funcs->is_two_pixels_per_container(&patched_crtc_timing) || optc1->opp_count == 2) h_div = H_TIMING_DIV_BY2; @@ -1471,37 +1470,71 @@ bool optc1_configure_crc(struct timing_generator *optc, if (!optc1_is_tg_enabled(optc)) return false; - REG_WRITE(OTG_CRC_CNTL, 0); + if (!params->enable || params->reset) + REG_WRITE(OTG_CRC_CNTL, 0); if (!params->enable) return true; /* Program frame boundaries */ - /* Window A x axis start and end. */ - REG_UPDATE_2(OTG_CRC0_WINDOWA_X_CONTROL, - OTG_CRC0_WINDOWA_X_START, params->windowa_x_start, - OTG_CRC0_WINDOWA_X_END, params->windowa_x_end); + switch (params->crc_eng_inst) { + case 0: + /* Window A x axis start and end. */ + REG_UPDATE_2(OTG_CRC0_WINDOWA_X_CONTROL, + OTG_CRC0_WINDOWA_X_START, params->windowa_x_start, + OTG_CRC0_WINDOWA_X_END, params->windowa_x_end); - /* Window A y axis start and end. */ - REG_UPDATE_2(OTG_CRC0_WINDOWA_Y_CONTROL, - OTG_CRC0_WINDOWA_Y_START, params->windowa_y_start, - OTG_CRC0_WINDOWA_Y_END, params->windowa_y_end); + /* Window A y axis start and end. */ + REG_UPDATE_2(OTG_CRC0_WINDOWA_Y_CONTROL, + OTG_CRC0_WINDOWA_Y_START, params->windowa_y_start, + OTG_CRC0_WINDOWA_Y_END, params->windowa_y_end); - /* Window B x axis start and end. */ - REG_UPDATE_2(OTG_CRC0_WINDOWB_X_CONTROL, - OTG_CRC0_WINDOWB_X_START, params->windowb_x_start, - OTG_CRC0_WINDOWB_X_END, params->windowb_x_end); + /* Window B x axis start and end. */ + REG_UPDATE_2(OTG_CRC0_WINDOWB_X_CONTROL, + OTG_CRC0_WINDOWB_X_START, params->windowb_x_start, + OTG_CRC0_WINDOWB_X_END, params->windowb_x_end); - /* Window B y axis start and end. */ - REG_UPDATE_2(OTG_CRC0_WINDOWB_Y_CONTROL, - OTG_CRC0_WINDOWB_Y_START, params->windowb_y_start, - OTG_CRC0_WINDOWB_Y_END, params->windowb_y_end); + /* Window B y axis start and end. */ + REG_UPDATE_2(OTG_CRC0_WINDOWB_Y_CONTROL, + OTG_CRC0_WINDOWB_Y_START, params->windowb_y_start, + OTG_CRC0_WINDOWB_Y_END, params->windowb_y_end); - /* Set crc mode and selection, and enable. Only using CRC0*/ - REG_UPDATE_3(OTG_CRC_CNTL, - OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0, - OTG_CRC0_SELECT, params->selection, - OTG_CRC_EN, 1); + /* Set crc mode and selection, and enable.*/ + REG_UPDATE_3(OTG_CRC_CNTL, + OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0, + OTG_CRC0_SELECT, params->selection, + OTG_CRC_EN, 1); + break; + case 1: + /* Window A x axis start and end. */ + REG_UPDATE_2(OTG_CRC1_WINDOWA_X_CONTROL, + OTG_CRC1_WINDOWA_X_START, params->windowa_x_start, + OTG_CRC1_WINDOWA_X_END, params->windowa_x_end); + + /* Window A y axis start and end. */ + REG_UPDATE_2(OTG_CRC1_WINDOWA_Y_CONTROL, + OTG_CRC1_WINDOWA_Y_START, params->windowa_y_start, + OTG_CRC1_WINDOWA_Y_END, params->windowa_y_end); + + /* Window B x axis start and end. */ + REG_UPDATE_2(OTG_CRC1_WINDOWB_X_CONTROL, + OTG_CRC1_WINDOWB_X_START, params->windowb_x_start, + OTG_CRC1_WINDOWB_X_END, params->windowb_x_end); + + /* Window B y axis start and end. */ + REG_UPDATE_2(OTG_CRC1_WINDOWB_Y_CONTROL, + OTG_CRC1_WINDOWB_Y_START, params->windowb_y_start, + OTG_CRC1_WINDOWB_Y_END, params->windowb_y_end); + + /* Set crc mode and selection, and enable.*/ + REG_UPDATE_3(OTG_CRC_CNTL, + OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0, + OTG_CRC1_SELECT, params->selection, + OTG_CRC_EN, 1); + break; + default: + return false; + } return true; } @@ -1510,6 +1543,7 @@ bool optc1_configure_crc(struct timing_generator *optc, * optc1_get_crc - Capture CRC result per component * * @optc: timing_generator instance. + * @idx: index of crc engine to get CRC from * @r_cr: 16-bit primary CRC signature for red data. * @g_y: 16-bit primary CRC signature for green data. * @b_cb: 16-bit primary CRC signature for blue data. @@ -1521,7 +1555,7 @@ bool optc1_configure_crc(struct timing_generator *optc, * If CRC is disabled, return false; otherwise, return true, and the CRC * results in the parameters. */ -bool optc1_get_crc(struct timing_generator *optc, +bool optc1_get_crc(struct timing_generator *optc, uint8_t idx, uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb) { uint32_t field = 0; @@ -1533,14 +1567,30 @@ bool optc1_get_crc(struct timing_generator *optc, if (!field) return false; - /* OTG_CRC0_DATA_RG has the CRC16 results for the red and green component */ - REG_GET_2(OTG_CRC0_DATA_RG, - CRC0_R_CR, r_cr, - CRC0_G_Y, g_y); + switch (idx) { + case 0: + /* OTG_CRC0_DATA_RG has the CRC16 results for the red and green component */ + REG_GET_2(OTG_CRC0_DATA_RG, + CRC0_R_CR, r_cr, + CRC0_G_Y, g_y); - /* OTG_CRC0_DATA_B has the CRC16 results for the blue component */ - REG_GET(OTG_CRC0_DATA_B, - CRC0_B_CB, b_cb); + /* OTG_CRC0_DATA_B has the CRC16 results for the blue component */ + REG_GET(OTG_CRC0_DATA_B, + CRC0_B_CB, b_cb); + break; + case 1: + /* OTG_CRC1_DATA_RG has the CRC16 results for the red and green component */ + REG_GET_2(OTG_CRC1_DATA_RG, + CRC1_R_CR, r_cr, + CRC1_G_Y, g_y); + + /* OTG_CRC1_DATA_B has the CRC16 results for the blue component */ + REG_GET(OTG_CRC1_DATA_B, + CRC1_B_CB, b_cb); + break; + default: + return false; + } return true; } diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h index 40757f20d73f..159172178d51 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h @@ -86,6 +86,12 @@ SRI(OTG_CRC0_WINDOWA_Y_CONTROL, OTG, inst),\ SRI(OTG_CRC0_WINDOWB_X_CONTROL, OTG, inst),\ SRI(OTG_CRC0_WINDOWB_Y_CONTROL, OTG, inst),\ + SRI(OTG_CRC1_DATA_RG, OTG, inst),\ + SRI(OTG_CRC1_DATA_B, OTG, inst),\ + SRI(OTG_CRC1_WINDOWA_X_CONTROL, OTG, inst),\ + SRI(OTG_CRC1_WINDOWA_Y_CONTROL, OTG, inst),\ + SRI(OTG_CRC1_WINDOWB_X_CONTROL, OTG, inst),\ + SRI(OTG_CRC1_WINDOWB_Y_CONTROL, OTG, inst),\ SR(GSL_SOURCE_SELECT),\ SRI(OTG_GLOBAL_CONTROL2, OTG, inst),\ SRI(OTG_TRIGA_MANUAL_TRIG, OTG, inst) @@ -315,6 +321,7 @@ struct dcn_optc_registers { SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_CHECK_ALL_FIELDS, mask_sh),\ SF(OTG0_OTG_CRC_CNTL, OTG_CRC_CONT_EN, mask_sh),\ SF(OTG0_OTG_CRC_CNTL, OTG_CRC0_SELECT, mask_sh),\ + SF(OTG0_OTG_CRC_CNTL, OTG_CRC1_SELECT, mask_sh),\ SF(OTG0_OTG_CRC_CNTL, OTG_CRC_EN, mask_sh),\ SF(OTG0_OTG_CRC0_DATA_RG, CRC0_R_CR, mask_sh),\ SF(OTG0_OTG_CRC0_DATA_RG, CRC0_G_Y, mask_sh),\ @@ -327,6 +334,17 @@ struct dcn_optc_registers { SF(OTG0_OTG_CRC0_WINDOWB_X_CONTROL, OTG_CRC0_WINDOWB_X_END, mask_sh),\ SF(OTG0_OTG_CRC0_WINDOWB_Y_CONTROL, OTG_CRC0_WINDOWB_Y_START, mask_sh),\ SF(OTG0_OTG_CRC0_WINDOWB_Y_CONTROL, OTG_CRC0_WINDOWB_Y_END, mask_sh),\ + SF(OTG0_OTG_CRC1_DATA_RG, CRC1_R_CR, mask_sh),\ + SF(OTG0_OTG_CRC1_DATA_RG, CRC1_G_Y, mask_sh),\ + SF(OTG0_OTG_CRC1_DATA_B, CRC1_B_CB, mask_sh),\ + SF(OTG0_OTG_CRC1_WINDOWA_X_CONTROL, OTG_CRC1_WINDOWA_X_START, mask_sh),\ + SF(OTG0_OTG_CRC1_WINDOWA_X_CONTROL, OTG_CRC1_WINDOWA_X_END, mask_sh),\ + SF(OTG0_OTG_CRC1_WINDOWA_Y_CONTROL, OTG_CRC1_WINDOWA_Y_START, mask_sh),\ + SF(OTG0_OTG_CRC1_WINDOWA_Y_CONTROL, OTG_CRC1_WINDOWA_Y_END, mask_sh),\ + SF(OTG0_OTG_CRC1_WINDOWB_X_CONTROL, OTG_CRC1_WINDOWB_X_START, mask_sh),\ + SF(OTG0_OTG_CRC1_WINDOWB_X_CONTROL, OTG_CRC1_WINDOWB_X_END, mask_sh),\ + SF(OTG0_OTG_CRC1_WINDOWB_Y_CONTROL, OTG_CRC1_WINDOWB_Y_START, mask_sh),\ + SF(OTG0_OTG_CRC1_WINDOWB_Y_CONTROL, OTG_CRC1_WINDOWB_Y_END, mask_sh),\ SF(GSL_SOURCE_SELECT, GSL0_READY_SOURCE_SEL, mask_sh),\ SF(GSL_SOURCE_SELECT, GSL1_READY_SOURCE_SEL, mask_sh),\ SF(GSL_SOURCE_SELECT, GSL2_READY_SOURCE_SEL, mask_sh),\ @@ -482,6 +500,7 @@ struct dcn_optc_registers { type OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN;\ type OTG_CRC_CONT_EN;\ type OTG_CRC0_SELECT;\ + type OTG_CRC1_SELECT;\ type OTG_CRC_EN;\ type CRC0_R_CR;\ type CRC0_G_Y;\ diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c index dfa9364fe5a6..d21e82b927d0 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c @@ -183,34 +183,87 @@ static bool optc35_configure_crc(struct timing_generator *optc, { struct optc *optc1 = DCN10TG_FROM_TG(optc); + /* Cannot configure crc on a CRTC that is disabled */ if (!optc1_is_tg_enabled(optc)) return false; - REG_WRITE(OTG_CRC_CNTL, 0); + + if (!params->enable || params->reset) + REG_WRITE(OTG_CRC_CNTL, 0); + if (!params->enable) return true; - REG_UPDATE_2(OTG_CRC0_WINDOWA_X_CONTROL, - OTG_CRC0_WINDOWA_X_START, params->windowa_x_start, - OTG_CRC0_WINDOWA_X_END, params->windowa_x_end); - REG_UPDATE_2(OTG_CRC0_WINDOWA_Y_CONTROL, - OTG_CRC0_WINDOWA_Y_START, params->windowa_y_start, - OTG_CRC0_WINDOWA_Y_END, params->windowa_y_end); - REG_UPDATE_2(OTG_CRC0_WINDOWB_X_CONTROL, - OTG_CRC0_WINDOWB_X_START, params->windowb_x_start, - OTG_CRC0_WINDOWB_X_END, params->windowb_x_end); - REG_UPDATE_2(OTG_CRC0_WINDOWB_Y_CONTROL, - OTG_CRC0_WINDOWB_Y_START, params->windowb_y_start, - OTG_CRC0_WINDOWB_Y_END, params->windowb_y_end); - if (optc1->base.ctx->dc->debug.otg_crc_db && optc1->tg_mask->OTG_CRC_WINDOW_DB_EN != 0) { - REG_UPDATE_4(OTG_CRC_CNTL, - OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0, - OTG_CRC0_SELECT, params->selection, - OTG_CRC_EN, 1, - OTG_CRC_WINDOW_DB_EN, 1); - } else - REG_UPDATE_3(OTG_CRC_CNTL, - OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0, - OTG_CRC0_SELECT, params->selection, - OTG_CRC_EN, 1); + + /* Program frame boundaries */ + switch (params->crc_eng_inst) { + case 0: + /* Window A x axis start and end. */ + REG_UPDATE_2(OTG_CRC0_WINDOWA_X_CONTROL, + OTG_CRC0_WINDOWA_X_START, params->windowa_x_start, + OTG_CRC0_WINDOWA_X_END, params->windowa_x_end); + + /* Window A y axis start and end. */ + REG_UPDATE_2(OTG_CRC0_WINDOWA_Y_CONTROL, + OTG_CRC0_WINDOWA_Y_START, params->windowa_y_start, + OTG_CRC0_WINDOWA_Y_END, params->windowa_y_end); + + /* Window B x axis start and end. */ + REG_UPDATE_2(OTG_CRC0_WINDOWB_X_CONTROL, + OTG_CRC0_WINDOWB_X_START, params->windowb_x_start, + OTG_CRC0_WINDOWB_X_END, params->windowb_x_end); + + /* Window B y axis start and end. */ + REG_UPDATE_2(OTG_CRC0_WINDOWB_Y_CONTROL, + OTG_CRC0_WINDOWB_Y_START, params->windowb_y_start, + OTG_CRC0_WINDOWB_Y_END, params->windowb_y_end); + + if (optc1->base.ctx->dc->debug.otg_crc_db && optc1->tg_mask->OTG_CRC_WINDOW_DB_EN != 0) + REG_UPDATE_4(OTG_CRC_CNTL, + OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0, + OTG_CRC0_SELECT, params->selection, + OTG_CRC_EN, 1, + OTG_CRC_WINDOW_DB_EN, 1); + else + REG_UPDATE_3(OTG_CRC_CNTL, + OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0, + OTG_CRC0_SELECT, params->selection, + OTG_CRC_EN, 1); + break; + case 1: + /* Window A x axis start and end. */ + REG_UPDATE_2(OTG_CRC1_WINDOWA_X_CONTROL, + OTG_CRC1_WINDOWA_X_START, params->windowa_x_start, + OTG_CRC1_WINDOWA_X_END, params->windowa_x_end); + + /* Window A y axis start and end. */ + REG_UPDATE_2(OTG_CRC1_WINDOWA_Y_CONTROL, + OTG_CRC1_WINDOWA_Y_START, params->windowa_y_start, + OTG_CRC1_WINDOWA_Y_END, params->windowa_y_end); + + /* Window B x axis start and end. */ + REG_UPDATE_2(OTG_CRC1_WINDOWB_X_CONTROL, + OTG_CRC1_WINDOWB_X_START, params->windowb_x_start, + OTG_CRC1_WINDOWB_X_END, params->windowb_x_end); + + /* Window B y axis start and end. */ + REG_UPDATE_2(OTG_CRC1_WINDOWB_Y_CONTROL, + OTG_CRC1_WINDOWB_Y_START, params->windowb_y_start, + OTG_CRC1_WINDOWB_Y_END, params->windowb_y_end); + + if (optc1->base.ctx->dc->debug.otg_crc_db && optc1->tg_mask->OTG_CRC_WINDOW_DB_EN != 0) + REG_UPDATE_4(OTG_CRC_CNTL, + OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0, + OTG_CRC1_SELECT, params->selection, + OTG_CRC_EN, 1, + OTG_CRC_WINDOW_DB_EN, 1); + else + REG_UPDATE_3(OTG_CRC_CNTL, + OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0, + OTG_CRC1_SELECT, params->selection, + OTG_CRC_EN, 1); + break; + default: + return false; + } return true; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c index 770a380cc03d..e92f14d50adb 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c @@ -1258,6 +1258,11 @@ struct stream_encoder *dcn10_find_first_free_match_stream_enc_for_link( return NULL; } +unsigned int dcn10_get_vstartup_for_pipe(struct pipe_ctx *pipe_ctx) +{ + return pipe_ctx->pipe_dlg_param.vstartup_start; +} + static const struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn10_get_dcc_compression_cap }; @@ -1272,7 +1277,8 @@ static const struct resource_funcs dcn10_res_pool_funcs = { .validate_global = dcn10_validate_global, .add_stream_to_ctx = dcn10_add_stream_to_ctx, .patch_unknown_plane_state = dcn10_patch_unknown_plane_state, - .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link + .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static uint32_t read_pipe_fuses(struct dc_context *ctx) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.h index bf8e33cd8147..7bc1be53e800 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.h +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.h @@ -51,6 +51,7 @@ struct stream_encoder *dcn10_find_first_free_match_stream_enc_for_link( const struct resource_pool *pool, struct dc_stream_state *stream); +unsigned int dcn10_get_vstartup_for_pipe(struct pipe_ctx *pipe_ctx); #endif /* __DC_RESOURCE_DCN10_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c index 5c616b1f7bf7..5c6dc710e96c 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c @@ -2229,7 +2229,8 @@ static const struct resource_funcs dcn20_res_pool_funcs = { .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, .set_mcif_arb_params = dcn20_set_mcif_arb_params, .populate_dml_pipes = dcn20_populate_dml_pipes_from_context, - .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link + .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; bool dcn20_dwbc_create(struct dc_context *ctx, struct resource_pool *pool) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn201/dcn201_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn201/dcn201_resource.c index 9f37f0097feb..43fa2cb117f3 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn201/dcn201_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn201/dcn201_resource.c @@ -1079,7 +1079,8 @@ static struct resource_funcs dcn201_res_pool_funcs = { .populate_dml_writeback_from_context = dcn201_populate_dml_writeback_from_context, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, .set_mcif_arb_params = dcn20_set_mcif_arb_params, - .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link + .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static bool dcn201_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn21/dcn21_resource.c index 021ba8ac5c8c..2615c36d5ffe 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn21/dcn21_resource.c @@ -1378,6 +1378,7 @@ static const struct resource_funcs dcn21_res_pool_funcs = { .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link, .update_bw_bounding_box = dcn21_update_bw_bounding_box, .get_panel_config_defaults = dcn21_get_panel_config_defaults, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static bool dcn21_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c index bfd0eccbed28..13202ce30d66 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c @@ -2250,6 +2250,7 @@ static const struct resource_funcs dcn30_res_pool_funcs = { .update_bw_bounding_box = dcn30_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, .get_panel_config_defaults = dcn30_get_panel_config_defaults, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; #define CTX ctx diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c index a9816affd312..121a86a59833 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c @@ -671,9 +671,9 @@ static const struct dc_plane_cap plane_cap = { /* 6:1 downscaling ratio: 1000/6 = 166.666 */ .max_downscale_factor = { - .argb8888 = 167, - .nv12 = 167, - .fp16 = 167 + .argb8888 = 358, + .nv12 = 358, + .fp16 = 358 }, 64, 64 @@ -693,7 +693,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_dcc = DCC_ENABLE, .vsr_support = true, .performance_trace = false, - .max_downscale_src_width = 7680,/*upto 8K*/ + .max_downscale_src_width = 4096,/*upto true 4k*/ .scl_reset_length10 = true, .sanity_checks = false, .underflow_assert_delay_us = 0xFFFFFFFF, @@ -1400,7 +1400,8 @@ static struct resource_funcs dcn301_res_pool_funcs = { .acquire_post_bldn_3dlut = dcn30_acquire_post_bldn_3dlut, .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn301_update_bw_bounding_box, - .patch_unknown_plane_state = dcn20_patch_unknown_plane_state + .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static bool dcn301_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c index 7baefc910a3d..012c5fd52cb1 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c @@ -1151,6 +1151,7 @@ static struct resource_funcs dcn302_res_pool_funcs = { .update_bw_bounding_box = dcn302_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, .get_panel_config_defaults = dcn302_get_panel_config_defaults, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static struct dc_cap_funcs cap_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c index 8a57d46ad15f..a8d0b4686f9a 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c @@ -1096,6 +1096,7 @@ static struct resource_funcs dcn303_res_pool_funcs = { .update_bw_bounding_box = dcn303_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, .get_panel_config_defaults = dcn303_get_panel_config_defaults, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static struct dc_cap_funcs cap_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c index 54ec3d8e920c..911bd60d4fbc 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c @@ -1849,6 +1849,7 @@ static struct resource_funcs dcn31_res_pool_funcs = { .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, .get_panel_config_defaults = dcn31_get_panel_config_defaults, .get_det_buffer_size = dcn31_get_det_buffer_size, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static struct clock_source *dcn30_clock_source_create( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c index 2794473f2aff..e3ba105034f8 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c @@ -1778,6 +1778,7 @@ static struct resource_funcs dcn314_res_pool_funcs = { .get_panel_config_defaults = dcn314_get_panel_config_defaults, .get_preferred_eng_id_dpia = dcn314_get_preferred_eng_id_dpia, .get_det_buffer_size = dcn31_get_det_buffer_size, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static struct clock_source *dcn30_clock_source_create( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c index 4ee33eb3381d..14acef036b5a 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c @@ -1846,6 +1846,7 @@ static struct resource_funcs dcn315_res_pool_funcs = { .get_panel_config_defaults = dcn315_get_panel_config_defaults, .get_power_profile = dcn315_get_power_profile, .get_det_buffer_size = dcn31_get_det_buffer_size, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static bool dcn315_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c index 79eddbafe3c2..568094827212 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c @@ -1720,6 +1720,7 @@ static struct resource_funcs dcn316_res_pool_funcs = { .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, .get_panel_config_defaults = dcn316_get_panel_config_defaults, .get_det_buffer_size = dcn31_get_det_buffer_size, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static bool dcn316_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c index 12d247a7ec45..664302876019 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c @@ -2066,6 +2066,7 @@ static struct resource_funcs dcn32_res_pool_funcs = { .add_phantom_pipes = dcn32_add_phantom_pipes, .build_pipe_pix_clk_params = dcn20_build_pipe_pix_clk_params, .calculate_mall_ways_from_bytes = dcn32_calculate_mall_ways_from_bytes, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static uint32_t read_pipe_fuses(struct dc_context *ctx) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c index 06b9479c8bd3..38d76434683e 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c @@ -1624,6 +1624,7 @@ static struct resource_funcs dcn321_res_pool_funcs = { .add_phantom_pipes = dcn32_add_phantom_pipes, .build_pipe_pix_clk_params = dcn20_build_pipe_pix_clk_params, .calculate_mall_ways_from_bytes = dcn32_calculate_mall_ways_from_bytes, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static uint32_t read_pipe_fuses(struct dc_context *ctx) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 89e2adcf2a28..8ee3d99ea2aa 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -1752,6 +1752,13 @@ static bool dcn35_validate_bandwidth(struct dc *dc, return out; } +enum dc_status dcn35_patch_unknown_plane_state(struct dc_plane_state *plane_state) +{ + plane_state->tiling_info.gfxversion = DcGfxVersion9; + dcn20_patch_unknown_plane_state(plane_state); + return DC_OK; +} + static struct resource_funcs dcn35_res_pool_funcs = { .destroy = dcn35_destroy_resource_pool, @@ -1775,10 +1782,11 @@ static struct resource_funcs dcn35_res_pool_funcs = { .acquire_post_bldn_3dlut = dcn30_acquire_post_bldn_3dlut, .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn35_update_bw_bounding_box_fpu, - .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .patch_unknown_plane_state = dcn35_patch_unknown_plane_state, .get_panel_config_defaults = dcn35_get_panel_config_defaults, .get_preferred_eng_id_dpia = dcn35_get_preferred_eng_id_dpia, .get_det_buffer_size = dcn31_get_det_buffer_size, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static bool dcn35_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.h index f97bb4cb3761..9d03a55d90cf 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.h +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.h @@ -35,6 +35,7 @@ extern struct _vcs_dpi_ip_params_st dcn3_5_ip; extern struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc; +enum dc_status dcn35_patch_unknown_plane_state(struct dc_plane_state *plane_state); struct dcn35_resource_pool { struct resource_pool base; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index 263a37c1cd3a..14f7c3acdc96 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -1754,10 +1754,11 @@ static struct resource_funcs dcn351_res_pool_funcs = { .acquire_post_bldn_3dlut = dcn30_acquire_post_bldn_3dlut, .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn351_update_bw_bounding_box_fpu, - .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .patch_unknown_plane_state = dcn35_patch_unknown_plane_state, .get_panel_config_defaults = dcn35_get_panel_config_defaults, .get_preferred_eng_id_dpia = dcn351_get_preferred_eng_id_dpia, .get_det_buffer_size = dcn31_get_det_buffer_size, + .get_vstartup_for_pipe = dcn10_get_vstartup_for_pipe }; static bool dcn351_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c index 09f5b8b40791..c1ebc6b1c937 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c @@ -737,7 +737,7 @@ static const struct dc_debug_options debug_defaults_drv = { .enable_stall_recovery = true, } }, - .force_cositing = CHROMA_COSITING_TOPLEFT + 1, + .force_cositing = CHROMA_COSITING_NONE + 1, }; static struct dce_aux *dcn401_aux_engine_create( @@ -1297,6 +1297,29 @@ static struct hpo_dp_link_encoder *dcn401_hpo_dp_link_encoder_create( return &hpo_dp_enc31->base; } +static unsigned int dcn401_calc_num_avail_chans_for_mall(struct dc *dc, unsigned int num_chans) +{ + unsigned int num_available_chans = 1; + + /* channels for MALL must be a power of 2 */ + while (num_chans > 1) { + num_available_chans = (num_available_chans << 1); + num_chans = (num_chans >> 1); + } + + /* cannot be odd */ + num_available_chans &= ~1; + + /* clamp to max available channels for MALL per ASIC */ + if (ASICREV_IS_GC_12_0_0_A0(dc->ctx->asic_id.hw_internal_rev)) { + num_available_chans = num_available_chans > 16 ? 16 : num_available_chans; + } else if (ASICREV_IS_GC_12_0_1_A0(dc->ctx->asic_id.hw_internal_rev)) { + num_available_chans = num_available_chans > 8 ? 8 : num_available_chans; + } + + return num_available_chans; +} + static struct dce_hwseq *dcn401_hwseq_create( struct dc_context *ctx) { @@ -1592,6 +1615,14 @@ static void dcn401_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b memcpy(dml2_opt, &dc->dml2_options, sizeof(dc->dml2_options)); + /* re-calculate the available MALL size if required */ + if (bw_params->num_channels > 0) { + dc->caps.max_cab_allocation_bytes = dcn401_calc_num_avail_chans_for_mall( + dc, bw_params->num_channels) * + dc->caps.mall_size_per_mem_channel * 1024 * 1024; + dc->caps.mall_size_total = dc->caps.max_cab_allocation_bytes; + } + DC_FP_START(); dcn401_update_bw_bounding_box_fpu(dc, bw_params); @@ -1609,6 +1640,7 @@ static void dcn401_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b enum dc_status dcn401_patch_unknown_plane_state(struct dc_plane_state *plane_state) { + plane_state->tiling_info.gfxversion = DcGfxAddr3; plane_state->tiling_info.gfx_addr3.swizzle = DC_ADDR3_SW_64KB_2D; return DC_OK; } @@ -1708,27 +1740,9 @@ static int dcn401_get_power_profile(const struct dc_state *context) return dpm_level; } -static unsigned int dcn401_calc_num_avail_chans_for_mall(struct dc *dc, unsigned int num_chans) +static unsigned int dcn401_get_vstartup_for_pipe(struct pipe_ctx *pipe_ctx) { - unsigned int num_available_chans = 1; - - /* channels for MALL must be a power of 2 */ - while (num_chans > 1) { - num_available_chans = (num_available_chans << 1); - num_chans = (num_chans >> 1); - } - - /* cannot be odd */ - num_available_chans &= ~1; - - /* clamp to max available channels for MALL per ASIC */ - if (ASICREV_IS_GC_12_0_0_A0(dc->ctx->asic_id.hw_internal_rev)) { - num_available_chans = num_available_chans > 16 ? 16 : num_available_chans; - } else if (ASICREV_IS_GC_12_0_1_A0(dc->ctx->asic_id.hw_internal_rev)) { - num_available_chans = num_available_chans > 8 ? 8 : num_available_chans; - } - - return num_available_chans; + return pipe_ctx->global_sync.dcn4x.vstartup_lines; } static struct resource_funcs dcn401_res_pool_funcs = { @@ -1758,6 +1772,7 @@ static struct resource_funcs dcn401_res_pool_funcs = { .build_pipe_pix_clk_params = dcn401_build_pipe_pix_clk_params, .calculate_mall_ways_from_bytes = dcn32_calculate_mall_ways_from_bytes, .get_power_profile = dcn401_get_power_profile, + .get_vstartup_for_pipe = dcn401_get_vstartup_for_pipe }; static uint32_t read_pipe_fuses(struct dc_context *ctx) diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c index 1306ce0321e2..38a9a0d68058 100644 --- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c +++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c @@ -11,6 +11,41 @@ #define IDENTITY_RATIO(ratio) (spl_fixpt_u2d19(ratio) == (1 << 19)) #define MIN_VIEWPORT_SIZE 12 +static bool spl_is_yuv420(enum spl_pixel_format format) +{ + if ((format >= SPL_PIXEL_FORMAT_420BPP8) && + (format <= SPL_PIXEL_FORMAT_420BPP10)) + return true; + + return false; +} + +static bool spl_is_rgb8(enum spl_pixel_format format) +{ + if (format == SPL_PIXEL_FORMAT_ARGB8888) + return true; + + return false; +} + +static bool spl_is_video_format(enum spl_pixel_format format) +{ + if (format >= SPL_PIXEL_FORMAT_VIDEO_BEGIN + && format <= SPL_PIXEL_FORMAT_VIDEO_END) + return true; + else + return false; +} + +static bool spl_is_subsampled_format(enum spl_pixel_format format) +{ + if (format >= SPL_PIXEL_FORMAT_SUBSAMPLED_BEGIN + && format <= SPL_PIXEL_FORMAT_SUBSAMPLED_END) + return true; + else + return false; +} + static struct spl_rect intersect_rec(const struct spl_rect *r0, const struct spl_rect *r1) { struct spl_rect rec; @@ -408,8 +443,7 @@ static void spl_calculate_scaling_ratios(struct spl_in *spl_in, spl_scratch->scl_data.ratios.horz_c = spl_scratch->scl_data.ratios.horz; spl_scratch->scl_data.ratios.vert_c = spl_scratch->scl_data.ratios.vert; - if (spl_in->basic_in.format == SPL_PIXEL_FORMAT_420BPP8 - || spl_in->basic_in.format == SPL_PIXEL_FORMAT_420BPP10) { + if (spl_is_yuv420(spl_in->basic_in.format)) { spl_scratch->scl_data.ratios.horz_c.value /= 2; spl_scratch->scl_data.ratios.vert_c.value /= 2; } @@ -546,41 +580,6 @@ static void spl_calculate_init_and_vp(bool flip_scan_dir, *vp_offset = src_size - *vp_offset - *vp_size; } -static bool spl_is_yuv420(enum spl_pixel_format format) -{ - if ((format >= SPL_PIXEL_FORMAT_420BPP8) && - (format <= SPL_PIXEL_FORMAT_420BPP10)) - return true; - - return false; -} - -static bool spl_is_rgb8(enum spl_pixel_format format) -{ - if (format == SPL_PIXEL_FORMAT_ARGB8888) - return true; - - return false; -} - -static bool spl_is_video_format(enum spl_pixel_format format) -{ - if (format >= SPL_PIXEL_FORMAT_VIDEO_BEGIN - && format <= SPL_PIXEL_FORMAT_VIDEO_END) - return true; - else - return false; -} - -static bool spl_is_subsampled_format(enum spl_pixel_format format) -{ - if (format >= SPL_PIXEL_FORMAT_SUBSAMPLED_BEGIN - && format <= SPL_PIXEL_FORMAT_SUBSAMPLED_END) - return true; - else - return false; -} - /*Calculate inits and viewport */ static void spl_calculate_inits_and_viewports(struct spl_in *spl_in, struct spl_scratch *spl_scratch) @@ -591,8 +590,7 @@ static void spl_calculate_inits_and_viewports(struct spl_in *spl_in, struct spl_rect recout_clip_in_recout_dst; struct spl_rect overlap_in_active_timing; struct spl_rect odm_slice = calculate_odm_slice_in_timing_active(spl_in); - int vpc_div = (spl_in->basic_in.format == SPL_PIXEL_FORMAT_420BPP8 - || spl_in->basic_in.format == SPL_PIXEL_FORMAT_420BPP10) ? 2 : 1; + int vpc_div = spl_is_subsampled_format(spl_in->basic_in.format) ? 2 : 1; bool orthogonal_rotation, flip_vert_scan_dir, flip_horz_scan_dir; struct spl_fixed31_32 init_adj_h = spl_fixpt_zero; struct spl_fixed31_32 init_adj_v = spl_fixpt_zero; @@ -620,11 +618,6 @@ static void spl_calculate_inits_and_viewports(struct spl_in *spl_in, &flip_vert_scan_dir, &flip_horz_scan_dir); - if (orthogonal_rotation) { - spl_swap(src.width, src.height); - spl_swap(flip_vert_scan_dir, flip_horz_scan_dir); - } - if (spl_is_subsampled_format(spl_in->basic_in.format)) { /* this gives the direction of the cositing (negative will move * left, right otherwise) @@ -633,15 +626,15 @@ static void spl_calculate_inits_and_viewports(struct spl_in *spl_in, switch (spl_in->basic_in.cositing) { - case CHROMA_COSITING_LEFT: - init_adj_h = spl_fixpt_zero; - init_adj_v = spl_fixpt_from_fraction(sign, 4); - break; - case CHROMA_COSITING_NONE: + case CHROMA_COSITING_TOPLEFT: init_adj_h = spl_fixpt_from_fraction(sign, 4); init_adj_v = spl_fixpt_from_fraction(sign, 4); break; - case CHROMA_COSITING_TOPLEFT: + case CHROMA_COSITING_LEFT: + init_adj_h = spl_fixpt_from_fraction(sign, 4); + init_adj_v = spl_fixpt_zero; + break; + case CHROMA_COSITING_NONE: default: init_adj_h = spl_fixpt_zero; init_adj_v = spl_fixpt_zero; @@ -649,6 +642,12 @@ static void spl_calculate_inits_and_viewports(struct spl_in *spl_in, } } + if (orthogonal_rotation) { + spl_swap(src.width, src.height); + spl_swap(flip_vert_scan_dir, flip_horz_scan_dir); + spl_swap(init_adj_h, init_adj_v); + } + spl_calculate_init_and_vp( flip_horz_scan_dir, recout_clip_in_recout_dst.x, @@ -1599,7 +1598,7 @@ static void spl_set_easf_data(struct spl_scratch *spl_scratch, struct spl_out *s 0x0; // fp1.5.10, C3 coefficient } - if (spl_is_video_format(format)) { /* TODO: 0 = RGB, 1 = YUV */ + if (spl_is_subsampled_format(format)) { /* TODO: 0 = RGB, 1 = YUV */ dscl_prog_data->easf_matrix_mode = 1; /* * 2-bit, BF3 chroma mode correction calculation mode diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 59990929e44e..d0fe324cb537 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -431,7 +431,68 @@ union replay_debug_flags { */ uint32_t enable_ips_residency_profiling : 1; - uint32_t reserved : 20; + /** + * 0x1000 (bit 12) + * @enable_coasting_vtotal_check: Enable Coasting_vtotal_check + */ + uint32_t enable_coasting_vtotal_check : 1; + /** + * 0x2000 (bit 13) + * @enable_visual_confirm_debug: Enable Visual Confirm Debug + */ + uint32_t enable_visual_confirm_debug : 1; + + uint32_t reserved : 18; + } bitfields; + + uint32_t u32All; +}; + +/** + * Flags record error state. + */ +union replay_visual_confirm_error_state_flags { + struct { + /** + * 0x1 (bit 0) - Desync Error flag. + */ + uint32_t desync_error : 1; + + /** + * 0x2 (bit 1) - State Transition Error flag. + */ + uint32_t state_transition_error : 1; + + /** + * 0x4 (bit 2) - Crc Error flag + */ + uint32_t crc_error : 1; + + /** + * 0x8 (bit 3) - Reserved + */ + uint32_t reserved_3 : 1; + + /** + * 0x10 (bit 4) - Incorrect Coasting vtotal checking --> use debug flag to control DPCD write. + * Added new debug flag to control DPCD. + */ + uint32_t incorrect_vtotal_in_static_screen : 1; + + /** + * 0x20 (bit 5) - No doubled Refresh Rate. + */ + uint32_t no_double_rr : 1; + + /** + * Reserved bit 6-7 + */ + uint32_t reserved_6_7 : 2; + + /** + * Reserved bit 9-31 + */ + uint32_t reserved_9_31 : 24; } bitfields; uint32_t u32All; @@ -3644,6 +3705,8 @@ enum dmub_cmd_replay_general_subtype { */ REPLAY_GENERAL_CMD_DISABLED_ADAPTIVE_SYNC_SDP, REPLAY_GENERAL_CMD_DISABLED_DESYNC_ERROR_DETECTION, + REPLAY_GENERAL_CMD_UPDATE_ERROR_STATUS, + REPLAY_GENERAL_CMD_SET_LOW_RR_ACTIVATE, }; /** diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 95838c7ab054..29ccd3532d13 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -996,9 +996,9 @@ void set_replay_coasting_vtotal(struct dc_link *link, link->replay_settings.coasting_vtotal_table[type] = vtotal; } -void set_replay_ips_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal) +void set_replay_low_rr_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal) { - link->replay_settings.abm_with_ips_on_full_screen_video_pseudo_vtotal = vtotal; + link->replay_settings.low_rr_full_screen_video_pseudo_vtotal = vtotal; } void calculate_replay_link_off_frame_count(struct dc_link *link, @@ -1039,3 +1039,8 @@ bool fill_custom_backlight_caps(unsigned int config_no, struct dm_acpi_atif_back memcpy(caps->data_points, custom_backlight_profiles[config_no].data_points, data_points_size); return true; } + +void reset_replay_dsync_error_count(struct dc_link *link) +{ + link->replay_settings.replay_desync_error_fail_count = 0; +} diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h index cac302e8fa10..758a8aa31fbe 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h @@ -62,7 +62,7 @@ void set_replay_defer_update_coasting_vtotal(struct dc_link *link, uint32_t vtotal); void update_replay_coasting_vtotal_from_defer(struct dc_link *link, enum replay_coasting_vtotal_type type); -void set_replay_ips_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal); +void set_replay_low_rr_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal); void calculate_replay_link_off_frame_count(struct dc_link *link, uint16_t vtotal, uint16_t htotal); @@ -78,4 +78,5 @@ bool psr_su_set_dsc_slice_height(struct dc *dc, struct dc_link *link, bool fill_custom_backlight_caps(unsigned int config_no, struct dm_acpi_atif_backlight_caps *caps); +void reset_replay_dsync_error_count(struct dc_link *link); #endif /* MODULES_POWER_POWER_HELPERS_H_ */ diff --git a/drivers/gpu/drm/amd/include/amd_pcie.h b/drivers/gpu/drm/amd/include/amd_pcie.h index a1ece3eecdf5..a08611cb8041 100644 --- a/drivers/gpu/drm/amd/include/amd_pcie.h +++ b/drivers/gpu/drm/amd/include/amd_pcie.h @@ -49,6 +49,17 @@ | CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3) /* Following flags shows PCIe lane width switch supported in driver which are decided by chipset and ASIC */ + +#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1 0x00000001 +#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 0x00000002 +#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 0x00000004 +#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 0x00000008 +#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12 0x00000010 +#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16 0x00000020 +#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X32 0x00000040 +#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_MASK 0x0000FFFF +#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_SHIFT 0 + #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X1 0x00010000 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 0x00020000 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 0x00040000 @@ -56,6 +67,7 @@ #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 0x00100000 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 0x00200000 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 0x00400000 +#define CAIL_PCIE_LINK_WIDTH_SUPPORT_MASK 0xFFFF0000 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_SHIFT 16 /* 1/2/4/8/16 lanes */ @@ -65,4 +77,10 @@ | CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 \ | CAIL_PCIE_LINK_WIDTH_SUPPORT_X16) +#define AMDGPU_DEFAULT_ASIC_PCIE_MLW_MASK (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1 \ + | CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 \ + | CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 \ + | CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 \ + | CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16) + #endif diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 98d9e840b0e2..6dccee403a3d 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -344,6 +344,16 @@ enum DC_DEBUG_MASK { * eDP display from ACPI _DDC method. */ DC_DISABLE_ACPI_EDID = 0x8000, + + /** + * @DC_DISABLE_HDMI_CEC: If set, disable HDMI-CEC feature in amdgpu driver. + */ + DC_DISABLE_HDMI_CEC = 0x10000, + + /** + * @DC_DISABLE_SUBVP: If set, disable DCN Sub-Viewport feature in amdgpu driver. + */ + DC_DISABLE_SUBVP = 0x20000, }; enum amd_dpm_forced_level; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h index 0f96b8c59a0e..274b3e1cc4fb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h @@ -34,6 +34,8 @@ #define NUM_PCIE_BITRATES 4 #define NUM_XGMI_BITRATES 4 #define NUM_XGMI_WIDTHS 3 +#define NUM_SOC_P2S_TABLES 3 +#define NUM_TDP_GROUPS 4 typedef enum { /*0*/ FEATURE_DATA_CALCULATION = 0, @@ -80,8 +82,10 @@ typedef enum { /*41*/ FEATURE_CXL_QOS = 41, /*42*/ FEATURE_SOC_DC_RTC = 42, /*43*/ FEATURE_GFX_DC_RTC = 43, +/*44*/ FEATURE_DVM_MIN_PSM = 44, +/*45*/ FEATURE_PRC = 45, -/*44*/ NUM_FEATURES = 44 +/*46*/ NUM_FEATURES = 46 } FEATURE_LIST_e; //enum for MPIO PCIe gen speed msgs @@ -123,7 +127,7 @@ typedef enum { VOLTAGE_GUARDBAND_COUNT } GFX_GUARDBAND_e; -#define SMU_METRICS_TABLE_VERSION 0xE +#define SMU_METRICS_TABLE_VERSION 0xF typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; @@ -234,6 +238,9 @@ typedef struct __attribute__((packed, aligned(4))) { //PCIE BW Data and error count uint32_t PCIeOtherEndRecoveryAcc; // The Pcie counter itself is accumulated + + //Total App Clock Counter + uint64_t GfxclkBelowHostLimitAcc[8]; } MetricsTableX_t; typedef struct __attribute__((packed, aligned(4))) { @@ -328,13 +335,14 @@ typedef struct __attribute__((packed, aligned(4))) { uint32_t JpegBusy[32]; } MetricsTableA_t; -#define SMU_VF_METRICS_TABLE_VERSION 0x3 +#define SMU_VF_METRICS_TABLE_VERSION 0x5 typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; uint32_t InstGfxclk_TargFreq; uint64_t AccGfxclk_TargFreq; uint64_t AccGfxRsmuDpm_Busy; + uint64_t AccGfxclkBelowHostLimit; } VfMetricsTable_t; #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index ae3563d71fa0..8d4a96e23326 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -107,6 +107,7 @@ struct smu_13_0_dpm_context { struct smu_13_0_dpm_tables dpm_tables; uint32_t workload_policy_mask; uint32_t dcef_min_ds_clk; + uint64_t caps; }; enum smu_13_0_power_state { @@ -303,5 +304,7 @@ int smu_v13_0_set_wbrf_exclusion_ranges(struct smu_context *smu, int smu_v13_0_get_boot_freq_by_index(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *value); + +void smu_v13_0_interrupt_work(struct smu_context *smu); #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index f6b029354327..83163d7c7f00 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1732,7 +1732,6 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu, gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity; gpu_metrics->average_umc_activity = metrics.AverageUclkActivity; - gpu_metrics->average_mm_activity = 0; /* Valid power data is available only from primary die */ if (aldebaran_is_primary(smu)) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 7bb45ff6d5c8..fbbdfa54f6a2 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1321,11 +1321,11 @@ static int smu_v13_0_set_irq_state(struct amdgpu_device *adev, return 0; } -static int smu_v13_0_ack_ac_dc_interrupt(struct smu_context *smu) +void smu_v13_0_interrupt_work(struct smu_context *smu) { - return smu_cmn_send_smc_msg(smu, - SMU_MSG_ReenableAcDcInterrupt, - NULL); + smu_cmn_send_smc_msg(smu, + SMU_MSG_ReenableAcDcInterrupt, + NULL); } #define THM_11_0__SRCID__THM_DIG_THERM_L2H 0 /* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH */ @@ -1378,12 +1378,12 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, switch (ctxid) { case SMU_IH_INTERRUPT_CONTEXT_ID_AC: dev_dbg(adev->dev, "Switched to AC mode!\n"); - smu_v13_0_ack_ac_dc_interrupt(smu); + schedule_work(&smu->interrupt_work); adev->pm.ac_power = true; break; case SMU_IH_INTERRUPT_CONTEXT_ID_DC: dev_dbg(adev->dev, "Switched to DC mode!\n"); - smu_v13_0_ack_ac_dc_interrupt(smu); + schedule_work(&smu->interrupt_work); adev->pm.ac_power = false; break; case SMU_IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING: diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 3aa705aae4c0..0551a3311217 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2643,11 +2643,12 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, &backend_workload_mask); /* Add optimizations for SMU13.0.0/10. Reuse the power saving profile */ - if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) && - ((smu->adev->pm.fw_version == 0x004e6601) || - (smu->adev->pm.fw_version >= 0x004e7300))) || - (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) && - smu->adev->pm.fw_version >= 0x00504500)) { + if ((workload_mask & (1 << PP_SMC_POWER_PROFILE_COMPUTE)) && + ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) && + ((smu->adev->pm.fw_version == 0x004e6601) || + (smu->adev->pm.fw_version >= 0x004e7300))) || + (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) && + smu->adev->pm.fw_version >= 0x00504500))) { workload_type = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_WORKLOAD, PP_SMC_POWER_PROFILE_POWERSAVING); @@ -3219,6 +3220,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .is_asic_wbrf_supported = smu_v13_0_0_wbrf_support_check, .enable_uclk_shadow = smu_v13_0_enable_uclk_shadow, .set_wbrf_exclusion_ranges = smu_v13_0_set_wbrf_exclusion_ranges, + .interrupt_work = smu_v13_0_interrupt_work, }; void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 5b86df0c8536..da7bd9227afe 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -101,23 +101,24 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_14.bin"); #define MCA_BANK_IPID(_ip, _hwid, _type) \ [AMDGPU_MCA_IP_##_ip] = { .hwid = _hwid, .mcatype = _type, } -static inline bool smu_v13_0_6_is_unified_metrics(struct smu_context *smu) -{ - return (smu->adev->flags & AMD_IS_APU) && - smu->smc_fw_version <= 0x4556900; -} +#define SMU_CAP(x) SMU_13_0_6_CAPS_##x -static inline bool smu_v13_0_6_is_other_end_count_available(struct smu_context *smu) -{ - switch (amdgpu_ip_version(smu->adev, MP1_HWIP, 0)) { - case IP_VERSION(13, 0, 6): - return smu->smc_fw_version >= 0x557600; - case IP_VERSION(13, 0, 14): - return smu->smc_fw_version >= 0x05550E00; - default: - return false; - } -} +enum smu_v13_0_6_caps { + SMU_CAP(DPM), + SMU_CAP(UNI_METRICS), + SMU_CAP(DPM_POLICY), + SMU_CAP(OTHER_END_METRICS), + SMU_CAP(SET_UCLK_MAX), + SMU_CAP(PCIE_METRICS), + SMU_CAP(HST_LIMIT_METRICS), + SMU_CAP(MCA_DEBUG_MODE), + SMU_CAP(PER_INST_METRICS), + SMU_CAP(CTF_LIMIT), + SMU_CAP(RMA_MSG), + SMU_CAP(ACA_SYND), + SMU_CAP(SDMA_RESET), + SMU_CAP(ALL), +}; struct mca_bank_ipid { enum amdgpu_mca_ip ip; @@ -281,6 +282,162 @@ struct smu_v13_0_6_dpm_map { uint32_t *freq_table; }; +static inline void smu_v13_0_6_cap_set(struct smu_context *smu, + enum smu_v13_0_6_caps cap) +{ + struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; + + dpm_context->caps |= BIT_ULL(cap); +} + +static inline void smu_v13_0_6_cap_clear(struct smu_context *smu, + enum smu_v13_0_6_caps cap) +{ + struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; + + dpm_context->caps &= ~BIT_ULL(cap); +} + +static inline bool smu_v13_0_6_cap_supported(struct smu_context *smu, + enum smu_v13_0_6_caps cap) +{ + struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; + + return !!(dpm_context->caps & BIT_ULL(cap)); +} + +static void smu_v13_0_14_init_caps(struct smu_context *smu) +{ + enum smu_v13_0_6_caps default_cap_list[] = { SMU_CAP(DPM), + SMU_CAP(UNI_METRICS), + SMU_CAP(SET_UCLK_MAX), + SMU_CAP(DPM_POLICY), + SMU_CAP(PCIE_METRICS), + SMU_CAP(CTF_LIMIT), + SMU_CAP(MCA_DEBUG_MODE), + SMU_CAP(RMA_MSG), + SMU_CAP(ACA_SYND) }; + uint32_t fw_ver = smu->smc_fw_version; + + for (int i = 0; i < ARRAY_SIZE(default_cap_list); i++) + smu_v13_0_6_cap_set(smu, default_cap_list[i]); + + if (fw_ver >= 0x05550E00) + smu_v13_0_6_cap_set(smu, SMU_CAP(OTHER_END_METRICS)); + if (fw_ver >= 0x05551000) + smu_v13_0_6_cap_set(smu, SMU_CAP(HST_LIMIT_METRICS)); + if (fw_ver >= 0x05550B00) + smu_v13_0_6_cap_set(smu, SMU_CAP(PER_INST_METRICS)); + if (fw_ver >= 0x5551200) + smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET)); +} + +static void smu_v13_0_12_init_caps(struct smu_context *smu) +{ + enum smu_v13_0_6_caps default_cap_list[] = { SMU_CAP(DPM), + SMU_CAP(UNI_METRICS), + SMU_CAP(PCIE_METRICS), + SMU_CAP(CTF_LIMIT), + SMU_CAP(MCA_DEBUG_MODE), + SMU_CAP(RMA_MSG), + SMU_CAP(ACA_SYND) }; + uint32_t fw_ver = smu->smc_fw_version; + + for (int i = 0; i < ARRAY_SIZE(default_cap_list); i++) + smu_v13_0_6_cap_set(smu, default_cap_list[i]); + + if (fw_ver < 0x00561900) + smu_v13_0_6_cap_clear(smu, SMU_CAP(DPM)); + + if (fw_ver >= 0x00561700) + smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET)); +} + +static void smu_v13_0_6_init_caps(struct smu_context *smu) +{ + enum smu_v13_0_6_caps default_cap_list[] = { SMU_CAP(DPM), + SMU_CAP(UNI_METRICS), + SMU_CAP(SET_UCLK_MAX), + SMU_CAP(DPM_POLICY), + SMU_CAP(PCIE_METRICS), + SMU_CAP(CTF_LIMIT), + SMU_CAP(MCA_DEBUG_MODE), + SMU_CAP(RMA_MSG), + SMU_CAP(ACA_SYND) }; + struct amdgpu_device *adev = smu->adev; + uint32_t fw_ver = smu->smc_fw_version; + uint32_t pgm = (fw_ver >> 24) & 0xFF; + + for (int i = 0; i < ARRAY_SIZE(default_cap_list); i++) + smu_v13_0_6_cap_set(smu, default_cap_list[i]); + + if (fw_ver < 0x552F00) + smu_v13_0_6_cap_clear(smu, SMU_CAP(DPM)); + if (fw_ver < 0x554500) + smu_v13_0_6_cap_clear(smu, SMU_CAP(CTF_LIMIT)); + + if (adev->flags & AMD_IS_APU) { + smu_v13_0_6_cap_clear(smu, SMU_CAP(PCIE_METRICS)); + smu_v13_0_6_cap_clear(smu, SMU_CAP(DPM_POLICY)); + smu_v13_0_6_cap_clear(smu, SMU_CAP(RMA_MSG)); + smu_v13_0_6_cap_clear(smu, SMU_CAP(ACA_SYND)); + + if (fw_ver <= 0x4556900) + smu_v13_0_6_cap_clear(smu, SMU_CAP(UNI_METRICS)); + if (fw_ver >= 0x04556F00) + smu_v13_0_6_cap_set(smu, SMU_CAP(HST_LIMIT_METRICS)); + if (fw_ver >= 0x04556A00) + smu_v13_0_6_cap_set(smu, SMU_CAP(PER_INST_METRICS)); + } else { + if (fw_ver >= 0x557600) + smu_v13_0_6_cap_set(smu, SMU_CAP(OTHER_END_METRICS)); + if (fw_ver < 0x00556000) + smu_v13_0_6_cap_clear(smu, SMU_CAP(DPM_POLICY)); + if (amdgpu_sriov_vf(adev) && (fw_ver < 0x556600)) + smu_v13_0_6_cap_clear(smu, SMU_CAP(SET_UCLK_MAX)); + if (fw_ver < 0x556300) + smu_v13_0_6_cap_clear(smu, SMU_CAP(PCIE_METRICS)); + if (fw_ver < 0x554800) + smu_v13_0_6_cap_clear(smu, SMU_CAP(MCA_DEBUG_MODE)); + if (fw_ver >= 0x556F00) + smu_v13_0_6_cap_set(smu, SMU_CAP(PER_INST_METRICS)); + if (fw_ver < 0x00555a00) + smu_v13_0_6_cap_clear(smu, SMU_CAP(RMA_MSG)); + if (fw_ver < 0x00555600) + smu_v13_0_6_cap_clear(smu, SMU_CAP(ACA_SYND)); + if (pgm == 0 && fw_ver >= 0x557900) + smu_v13_0_6_cap_set(smu, SMU_CAP(HST_LIMIT_METRICS)); + } + if (((pgm == 7) && (fw_ver >= 0x7550700)) || + ((pgm == 0) && (fw_ver >= 0x00557900)) || + ((pgm == 4) && (fw_ver >= 0x4557000))) + smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET)); +} + +static void smu_v13_0_x_init_caps(struct smu_context *smu) +{ + switch (amdgpu_ip_version(smu->adev, MP1_HWIP, 0)) { + case IP_VERSION(13, 0, 12): + return smu_v13_0_12_init_caps(smu); + case IP_VERSION(13, 0, 14): + return smu_v13_0_14_init_caps(smu); + default: + return smu_v13_0_6_init_caps(smu); + } +} + +static int smu_v13_0_6_check_fw_version(struct smu_context *smu) +{ + int r; + + r = smu_v13_0_check_fw_version(smu); + /* Initialize caps flags once fw version is fetched */ + if (!r) + smu_v13_0_x_init_caps(smu); + + return r; +} + static int smu_v13_0_6_init_microcode(struct smu_context *smu) { const struct smc_firmware_header_v2_1 *v2_1; @@ -602,7 +759,7 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu) MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table; struct PPTable_t *pptable = (struct PPTable_t *)smu_table->driver_pptable; - bool flag = smu_v13_0_6_is_unified_metrics(smu); + bool flag = !smu_v13_0_6_cap_supported(smu, SMU_CAP(UNI_METRICS)); int ret, i, retry = 100; uint32_t table_version; @@ -798,8 +955,7 @@ static int smu_v13_0_6_set_default_dpm_table(struct smu_context *smu) smu_v13_0_6_setup_driver_pptable(smu); /* DPM policy not supported in older firmwares */ - if (!(smu->adev->flags & AMD_IS_APU) && - (smu->smc_fw_version < 0x00556000)) { + if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(DPM_POLICY))) { struct smu_dpm_context *smu_dpm = &smu->smu_dpm; smu_dpm->dpm_policies->policy_mask &= @@ -976,7 +1132,7 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu, struct smu_table_context *smu_table = &smu->smu_table; MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table; MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table; - bool flag = smu_v13_0_6_is_unified_metrics(smu); + bool flag = !smu_v13_0_6_cap_supported(smu, SMU_CAP(UNI_METRICS)); struct amdgpu_device *adev = smu->adev; int ret = 0; int xcc_id; @@ -989,7 +1145,7 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu, switch (member) { case METRICS_CURR_GFXCLK: case METRICS_AVERAGE_GFXCLK: - if (smu->smc_fw_version >= 0x552F00) { + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(DPM))) { xcc_id = GET_INST(GC, 0); *value = SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency, flag)[xcc_id]); } else { @@ -1676,7 +1832,7 @@ static int smu_v13_0_6_notify_unload(struct smu_context *smu) static int smu_v13_0_6_mca_set_debug_mode(struct smu_context *smu, bool enable) { /* NOTE: this ClearMcaOnRead message is only supported for smu version 85.72.0 or higher */ - if (smu->smc_fw_version < 0x554800) + if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(MCA_DEBUG_MODE))) return 0; return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ClearMcaOnRead, @@ -1821,9 +1977,8 @@ static int smu_v13_0_6_set_soft_freq_limited_range(struct smu_context *smu, if (max == pstate_table->uclk_pstate.curr.max) return 0; /* For VF, only allowed in FW versions 85.102 or greater */ - if (amdgpu_sriov_vf(adev) && - ((smu->smc_fw_version < 0x556600) || - (adev->flags & AMD_IS_APU))) + if (!smu_v13_0_6_cap_supported(smu, + SMU_CAP(SET_UCLK_MAX))) return -EOPNOTSUPP; /* Only max clock limiting is allowed for UCLK */ ret = smu_v13_0_set_soft_freq_limited_range( @@ -2027,7 +2182,7 @@ static int smu_v13_0_6_get_enabled_mask(struct smu_context *smu, ret = smu_cmn_get_enabled_mask(smu, feature_mask); - if (ret == -EIO && smu->smc_fw_version < 0x552F00) { + if (ret == -EIO && !smu_v13_0_6_cap_supported(smu, SMU_CAP(DPM))) { *feature_mask = 0; ret = 0; } @@ -2320,11 +2475,10 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu) static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table) { - bool per_inst, smu_13_0_6_per_inst, smu_13_0_14_per_inst, apu_per_inst; struct smu_table_context *smu_table = &smu->smu_table; struct gpu_metrics_v1_7 *gpu_metrics = (struct gpu_metrics_v1_7 *)smu_table->gpu_metrics_table; - bool flag = smu_v13_0_6_is_unified_metrics(smu); + bool flag = !smu_v13_0_6_cap_supported(smu, SMU_CAP(UNI_METRICS)); int ret = 0, xcc_id, inst, i, j, k, idx; struct amdgpu_device *adev = smu->adev; MetricsTableX_t *metrics_x; @@ -2332,6 +2486,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table struct amdgpu_xcp *xcp; u16 link_width_level; u32 inst_mask; + bool per_inst; metrics_x = kzalloc(max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)), GFP_KERNEL); ret = smu_v13_0_6_get_metrics_table(smu, metrics_x, true); @@ -2358,6 +2513,9 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table gpu_metrics->average_umc_activity = SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization, flag)); + gpu_metrics->mem_max_bandwidth = + SMUQ10_ROUND(GET_METRIC_FIELD(MaxDramBandwidth, flag)); + gpu_metrics->curr_socket_power = SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower, flag)); /* Energy counter reported in 15.259uJ (2^-16) units */ @@ -2402,7 +2560,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table * table for both pf & one vf for smu version 85.99.0 or higher else report only * for pf from registers */ - if (smu->smc_fw_version >= 0x556300) { + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(PCIE_METRICS))) { gpu_metrics->pcie_link_width = metrics_x->PCIeLinkWidth; gpu_metrics->pcie_link_speed = pcie_gen_to_speed(metrics_x->PCIeLinkSpeed); @@ -2431,7 +2589,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table metrics_x->PCIeNAKSentCountAcc; gpu_metrics->pcie_nak_rcvd_count_acc = metrics_x->PCIeNAKReceivedCountAcc; - if (smu_v13_0_6_is_other_end_count_available(smu)) + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(OTHER_END_METRICS))) gpu_metrics->pcie_lc_perf_other_end_recovery = metrics_x->PCIeOtherEndRecoveryAcc; @@ -2456,17 +2614,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table gpu_metrics->num_partition = adev->xcp_mgr->num_xcps; - apu_per_inst = (adev->flags & AMD_IS_APU) && (smu->smc_fw_version >= 0x04556A00); - smu_13_0_6_per_inst = !(adev->flags & AMD_IS_APU) && - (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) - == IP_VERSION(13, 0, 6)) && - (smu->smc_fw_version >= 0x556F00); - smu_13_0_14_per_inst = !(adev->flags & AMD_IS_APU) && - (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) - == IP_VERSION(13, 0, 14)) && - (smu->smc_fw_version >= 0x05550B00); - - per_inst = apu_per_inst || smu_13_0_6_per_inst || smu_13_0_14_per_inst; + per_inst = smu_v13_0_6_cap_supported(smu, SMU_CAP(PER_INST_METRICS)); for_each_xcp(adev->xcp_mgr, xcp, i) { amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_VCN, &inst_mask); @@ -2496,6 +2644,12 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table SMUQ10_ROUND(metrics_x->GfxBusy[inst]); gpu_metrics->xcp_stats[i].gfx_busy_acc[idx] = SMUQ10_ROUND(metrics_x->GfxBusyAcc[inst]); + + if (smu_v13_0_6_cap_supported( + smu, SMU_CAP(HST_LIMIT_METRICS))) + gpu_metrics->xcp_stats[i].gfx_below_host_limit_acc[idx] = + SMUQ10_ROUND(metrics_x->GfxclkBelowHostLimitAcc + [inst]); idx++; } } @@ -2600,7 +2754,7 @@ static int smu_v13_0_6_get_thermal_temperature_range(struct smu_context *smu, return -EINVAL; /*Check smu version, GetCtfLimit message only supported for smu version 85.69 or higher */ - if (smu->smc_fw_version < 0x554500) + if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(CTF_LIMIT))) return 0; /* Get SOC Max operating temperature */ @@ -2702,11 +2856,10 @@ static int smu_v13_0_6_smu_send_hbm_bad_page_num(struct smu_context *smu, static int smu_v13_0_6_send_rma_reason(struct smu_context *smu) { - struct amdgpu_device *adev = smu->adev; int ret; /* NOTE: the message is only valid on dGPU with pmfw 85.90.0 and above */ - if ((adev->flags & AMD_IS_APU) || smu->smc_fw_version < 0x00555a00) + if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(RMA_MSG))) return 0; ret = smu_cmn_send_smc_msg(smu, SMU_MSG_RmaDueToBadPageThreshold, NULL); @@ -2720,17 +2873,13 @@ static int smu_v13_0_6_send_rma_reason(struct smu_context *smu) static int smu_v13_0_6_reset_sdma(struct smu_context *smu, uint32_t inst_mask) { - struct amdgpu_device *adev = smu->adev; int ret = 0; - /* the message is only valid on SMU 13.0.6 with pmfw 85.121.00 and above */ - if ((adev->flags & AMD_IS_APU) || - amdgpu_ip_version(adev, MP1_HWIP, 0) != IP_VERSION(13, 0, 6) || - smu->smc_fw_version < 0x00557900) - return 0; + if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(SDMA_RESET))) + return -EOPNOTSUPP; ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_ResetSDMA, inst_mask, NULL); + SMU_MSG_ResetSDMA, inst_mask, NULL); if (ret) dev_err(smu->adev->dev, "failed to send ResetSDMA event with mask 0x%x\n", @@ -3049,7 +3198,7 @@ static bool mca_smu_bank_is_valid(const struct mca_ras_info *mca_ras, struct amd if (instlo != 0x03b30400) return false; - if (!(adev->flags & AMD_IS_APU) && smu->smc_fw_version >= 0x00555600) { + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(ACA_SYND))) { errcode = MCA_REG__SYND__ERRORINFORMATION(entry->regs[MCA_REG_IDX_SYND]); errcode &= 0xff; } else { @@ -3335,9 +3484,10 @@ static int aca_smu_get_valid_aca_bank(struct amdgpu_device *adev, static int aca_smu_parse_error_code(struct amdgpu_device *adev, struct aca_bank *bank) { + struct smu_context *smu = adev->powerplay.pp_handle; int error_code; - if (!(adev->flags & AMD_IS_APU) && adev->pm.fw_version >= 0x00555600) + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(ACA_SYND))) error_code = ACA_REG__SYND__ERRORINFORMATION(bank->regs[ACA_REG_IDX_SYND]); else error_code = ACA_REG__STATUS__ERRORCODE(bank->regs[ACA_REG_IDX_STATUS]); @@ -3375,7 +3525,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = { .fini_power = smu_v13_0_fini_power, .check_fw_status = smu_v13_0_6_check_fw_status, /* pptable related */ - .check_fw_version = smu_v13_0_check_fw_version, + .check_fw_version = smu_v13_0_6_check_fw_version, .set_driver_table_location = smu_v13_0_set_driver_table_location, .set_tool_table_location = smu_v13_0_set_tool_table_location, .notify_memory_pool_location = smu_v13_0_notify_memory_pool_location, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index aabb94796005..55ef18517b0f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2797,6 +2797,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .is_asic_wbrf_supported = smu_v13_0_7_wbrf_support_check, .enable_uclk_shadow = smu_v13_0_enable_uclk_shadow, .set_wbrf_exclusion_ranges = smu_v13_0_set_wbrf_exclusion_ranges, + .interrupt_work = smu_v13_0_interrupt_work, }; void smu_v13_0_7_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c index 61f4a38e7d2b..657bc3dd18df 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c @@ -153,7 +153,16 @@ static int adv7511_hdmi_hw_params(struct device *dev, void *data, ADV7511_AUDIO_CFG3_LEN_MASK, len); regmap_update_bits(adv7511->regmap, ADV7511_REG_I2C_FREQ_ID_CFG, ADV7511_I2C_FREQ_ID_CFG_RATE_MASK, rate << 4); - regmap_write(adv7511->regmap, 0x73, 0x1); + + /* send current Audio infoframe values while updating */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(5), BIT(5)); + + regmap_write(adv7511->regmap, ADV7511_REG_AUDIO_INFOFRAME(0), 0x1); + + /* use Audio infoframe updated info */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(5), 0); return 0; } @@ -184,8 +193,9 @@ static int audio_startup(struct device *dev, void *data) regmap_update_bits(adv7511->regmap, ADV7511_REG_GC(0), BIT(7) | BIT(6), BIT(7)); /* use Audio infoframe updated info */ - regmap_update_bits(adv7511->regmap, ADV7511_REG_GC(1), + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, BIT(5), 0); + /* enable SPDIF receiver */ if (adv7511->audio_source == ADV7511_AUDIO_SOURCE_SPDIF) regmap_update_bits(adv7511->regmap, ADV7511_REG_AUDIO_CONFIG, @@ -204,7 +214,8 @@ static void audio_shutdown(struct device *dev, void *data) } static int adv7511_hdmi_i2s_get_dai_id(struct snd_soc_component *component, - struct device_node *endpoint) + struct device_node *endpoint, + void *data) { struct of_endpoint of_ep; int ret; diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index eb5919b38263..a13b3d8ab6ac 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1241,8 +1241,10 @@ static int adv7511_probe(struct i2c_client *i2c) return ret; ret = adv7511_init_regulators(adv7511); - if (ret) - return dev_err_probe(dev, ret, "failed to init regulators\n"); + if (ret) { + dev_err_probe(dev, ret, "failed to init regulators\n"); + goto err_of_node_put; + } /* * The power down GPIO is optional. If present, toggle it from active to @@ -1363,6 +1365,8 @@ err_i2c_unregister_edid: i2c_unregister_device(adv7511->i2c_edid); uninit_regulators: adv7511_uninit_regulators(adv7511); +err_of_node_put: + of_node_put(adv7511->host_node); return ret; } @@ -1371,6 +1375,8 @@ static void adv7511_remove(struct i2c_client *i2c) { struct adv7511 *adv7511 = i2c_get_clientdata(i2c); + of_node_put(adv7511->host_node); + adv7511_uninit_regulators(adv7511); drm_bridge_remove(&adv7511->bridge); diff --git a/drivers/gpu/drm/bridge/adv7511/adv7533.c b/drivers/gpu/drm/bridge/adv7511/adv7533.c index 4481489aaf5e..122ad91e8a32 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7533.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7533.c @@ -172,7 +172,7 @@ int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv) of_property_read_u32(np, "adi,dsi-lanes", &num_lanes); - if (num_lanes < 1 || num_lanes > 4) + if (num_lanes < 2 || num_lanes > 4) return -EINVAL; adv->num_dsi_lanes = num_lanes; @@ -181,8 +181,6 @@ int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv) if (!adv->host_node) return -ENODEV; - of_node_put(adv->host_node); - adv->use_timing_gen = !of_property_read_bool(np, "adi,disable-timing-generator"); diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index 6238eabd2328..4be34d5c7a3b 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -1952,7 +1952,8 @@ static void anx7625_audio_shutdown(struct device *dev, void *data) } static int anx7625_hdmi_i2s_get_dai_id(struct snd_soc_component *component, - struct device_node *endpoint) + struct device_node *endpoint, + void *data) { struct of_endpoint of_ep; int ret; @@ -2139,49 +2140,6 @@ static void hdcp_check_work_func(struct work_struct *work) drm_modeset_unlock(&drm_dev->mode_config.connection_mutex); } -static int anx7625_connector_atomic_check(struct anx7625_data *ctx, - struct drm_connector_state *state) -{ - struct device *dev = ctx->dev; - int cp; - - dev_dbg(dev, "hdcp state check\n"); - cp = state->content_protection; - - if (cp == ctx->hdcp_cp) - return 0; - - if (cp == DRM_MODE_CONTENT_PROTECTION_DESIRED) { - if (ctx->dp_en) { - dev_dbg(dev, "enable HDCP\n"); - anx7625_hdcp_enable(ctx); - - queue_delayed_work(ctx->hdcp_workqueue, - &ctx->hdcp_work, - msecs_to_jiffies(2000)); - } - } - - if (cp == DRM_MODE_CONTENT_PROTECTION_UNDESIRED) { - if (ctx->hdcp_cp != DRM_MODE_CONTENT_PROTECTION_ENABLED) { - dev_err(dev, "current CP is not ENABLED\n"); - return -EINVAL; - } - anx7625_hdcp_disable(ctx); - ctx->hdcp_cp = DRM_MODE_CONTENT_PROTECTION_UNDESIRED; - drm_hdcp_update_content_protection(ctx->connector, - ctx->hdcp_cp); - dev_dbg(dev, "update CP to UNDESIRE\n"); - } - - if (cp == DRM_MODE_CONTENT_PROTECTION_ENABLED) { - dev_err(dev, "Userspace illegal set to PROTECTION ENABLE\n"); - return -EINVAL; - } - - return 0; -} - static int anx7625_bridge_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flags flags) { @@ -2418,7 +2376,7 @@ static int anx7625_bridge_atomic_check(struct drm_bridge *bridge, anx7625_bridge_mode_fixup(bridge, &crtc_state->mode, &crtc_state->adjusted_mode); - return anx7625_connector_atomic_check(ctx, conn_state); + return 0; } static void anx7625_bridge_atomic_enable(struct drm_bridge *bridge, @@ -2427,6 +2385,7 @@ static void anx7625_bridge_atomic_enable(struct drm_bridge *bridge, struct anx7625_data *ctx = bridge_to_anx7625(bridge); struct device *dev = ctx->dev; struct drm_connector *connector; + struct drm_connector_state *conn_state; dev_dbg(dev, "drm atomic enable\n"); @@ -2441,6 +2400,22 @@ static void anx7625_bridge_atomic_enable(struct drm_bridge *bridge, _anx7625_hpd_polling(ctx, 5000 * 100); anx7625_dp_start(ctx); + + conn_state = drm_atomic_get_new_connector_state(state->base.state, connector); + + if (WARN_ON(!conn_state)) + return; + + if (conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) { + if (ctx->dp_en) { + dev_dbg(dev, "enable HDCP\n"); + anx7625_hdcp_enable(ctx); + + queue_delayed_work(ctx->hdcp_workqueue, + &ctx->hdcp_work, + msecs_to_jiffies(2000)); + } + } } static void anx7625_bridge_atomic_disable(struct drm_bridge *bridge, @@ -2451,6 +2426,17 @@ static void anx7625_bridge_atomic_disable(struct drm_bridge *bridge, dev_dbg(dev, "drm atomic disable\n"); + flush_workqueue(ctx->hdcp_workqueue); + + if (ctx->connector && + ctx->hdcp_cp == DRM_MODE_CONTENT_PROTECTION_ENABLED) { + anx7625_hdcp_disable(ctx); + ctx->hdcp_cp = DRM_MODE_CONTENT_PROTECTION_DESIRED; + drm_hdcp_update_content_protection(ctx->connector, + ctx->hdcp_cp); + dev_dbg(dev, "update CP to DESIRE\n"); + } + ctx->connector = NULL; anx7625_dp_stop(ctx); diff --git a/drivers/gpu/drm/bridge/ite-it6263.c b/drivers/gpu/drm/bridge/ite-it6263.c index 44af1f25034a..306b5e374b9e 100644 --- a/drivers/gpu/drm/bridge/ite-it6263.c +++ b/drivers/gpu/drm/bridge/ite-it6263.c @@ -569,15 +569,6 @@ static int it6263_read_edid(void *data, u8 *buf, unsigned int block, size_t len) return 0; } -static int it6263_bridge_atomic_check(struct drm_bridge *bridge, - struct drm_bridge_state *bridge_state, - struct drm_crtc_state *crtc_state, - struct drm_connector_state *conn_state) -{ - return drm_atomic_helper_connector_hdmi_check(conn_state->connector, - conn_state->state); -} - static void it6263_bridge_atomic_disable(struct drm_bridge *bridge, struct drm_bridge_state *old_bridge_state) @@ -812,7 +803,6 @@ static const struct drm_bridge_funcs it6263_bridge_funcs = { .mode_valid = it6263_bridge_mode_valid, .atomic_disable = it6263_bridge_atomic_disable, .atomic_enable = it6263_bridge_atomic_enable, - .atomic_check = it6263_bridge_atomic_check, .detect = it6263_bridge_detect, .edid_read = it6263_bridge_edid_read, .atomic_get_input_bus_fmts = it6263_bridge_atomic_get_input_bus_fmts, @@ -864,8 +854,8 @@ static int it6263_probe(struct i2c_client *client) it->lvds_i2c = devm_i2c_new_dummy_device(dev, client->adapter, LVDS_INPUT_CTRL_I2C_ADDR); if (IS_ERR(it->lvds_i2c)) - dev_err_probe(it->dev, PTR_ERR(it->lvds_i2c), - "failed to allocate I2C device for LVDS\n"); + return dev_err_probe(it->dev, PTR_ERR(it->lvds_i2c), + "failed to allocate I2C device for LVDS\n"); it->lvds_regmap = devm_regmap_init_i2c(it->lvds_i2c, &it6263_lvds_regmap_config); diff --git a/drivers/gpu/drm/bridge/ite-it6505.c b/drivers/gpu/drm/bridge/ite-it6505.c index 0faad10ba8e4..88ef76a37fe6 100644 --- a/drivers/gpu/drm/bridge/ite-it6505.c +++ b/drivers/gpu/drm/bridge/ite-it6505.c @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -126,6 +127,7 @@ #define REG_AUX_OUT_DATA0 0x27 #define REG_AUX_CMD_REQ 0x2B +#define M_AUX_REQ_CMD 0x0F #define AUX_BUSY BIT(5) #define REG_AUX_DATA_0_7 0x2C @@ -266,6 +268,18 @@ #define REG_SSC_CTRL1 0x189 #define REG_SSC_CTRL2 0x18A +#define REG_AUX_USER_CTRL 0x190 +#define EN_USER_AUX BIT(0) +#define USER_AUX_DONE BIT(1) +#define AUX_EVENT BIT(4) + +#define REG_AUX_USER_DATA_REC 0x191 +#define M_AUX_IN_REC 0xF0 +#define M_AUX_OUT_REC 0x0F + +#define REG_AUX_USER_REPLY 0x19A +#define REG_AUX_USER_RXB(n) (n + 0x19B) + #define RBR DP_LINK_BW_1_62 #define HBR DP_LINK_BW_2_7 #define HBR2 DP_LINK_BW_5_4 @@ -296,11 +310,13 @@ #define MAX_LANE_COUNT 4 #define MAX_LINK_RATE HBR #define AUTO_TRAIN_RETRY 3 -#define MAX_HDCP_DOWN_STREAM_COUNT 10 +#define MAX_HDCP_DOWN_STREAM_COUNT 127 #define MAX_CR_LEVEL 0x03 #define MAX_EQ_LEVEL 0x03 #define AUX_WAIT_TIMEOUT_MS 15 -#define AUX_FIFO_MAX_SIZE 32 +#define AUX_FIFO_MAX_SIZE 16 +#define AUX_I2C_MAX_SIZE 4 +#define AUX_I2C_DEFER_RETRY 4 #define PIXEL_CLK_DELAY 1 #define PIXEL_CLK_INVERSE 0 #define ADJUST_PHASE_THRESHOLD 80000 @@ -323,7 +339,15 @@ enum aux_cmd_type { CMD_AUX_NATIVE_READ = 0x0, CMD_AUX_NATIVE_WRITE = 0x5, + CMD_AUX_GI2C_ADR = 0x08, + CMD_AUX_GI2C_READ = 0x09, + CMD_AUX_GI2C_WRITE = 0x0A, CMD_AUX_I2C_EDID_READ = 0xB, + CMD_AUX_I2C_READ = 0x0D, + CMD_AUX_I2C_WRITE = 0x0C, + + /* KSV read with AUX FIFO extend from CMD_AUX_NATIVE_READ*/ + CMD_AUX_GET_KSV_LIST = 0x10, }; enum aux_cmd_reply { @@ -965,7 +989,8 @@ static ssize_t it6505_aux_operation(struct it6505 *it6505, it6505_set_bits(it6505, REG_AUX_CTRL, AUX_USER_MODE, AUX_USER_MODE); aux_op_start: - if (cmd == CMD_AUX_I2C_EDID_READ) { + /* HW AUX FIFO supports only EDID and DCPD KSV FIFO area */ + if (cmd == CMD_AUX_I2C_EDID_READ || cmd == CMD_AUX_GET_KSV_LIST) { /* AUX EDID FIFO has max length of AUX_FIFO_MAX_SIZE bytes. */ size = min_t(size_t, size, AUX_FIFO_MAX_SIZE); /* Enable AUX FIFO read back and clear FIFO */ @@ -996,7 +1021,7 @@ aux_op_start: size); /* Aux Fire */ - it6505_write(it6505, REG_AUX_CMD_REQ, cmd); + it6505_write(it6505, REG_AUX_CMD_REQ, FIELD_GET(M_AUX_REQ_CMD, cmd)); ret = it6505_aux_wait(it6505); if (ret < 0) @@ -1030,7 +1055,7 @@ aux_op_start: goto aux_op_start; } - if (cmd == CMD_AUX_I2C_EDID_READ) { + if (cmd == CMD_AUX_I2C_EDID_READ || cmd == CMD_AUX_GET_KSV_LIST) { for (i = 0; i < size; i++) { ret = it6505_read(it6505, REG_AUX_DATA_FIFO); if (ret < 0) @@ -1055,7 +1080,7 @@ aux_op_start: ret = i; aux_op_err: - if (cmd == CMD_AUX_I2C_EDID_READ) { + if (cmd == CMD_AUX_I2C_EDID_READ || cmd == CMD_AUX_GET_KSV_LIST) { /* clear AUX FIFO */ it6505_set_bits(it6505, REG_AUX_CTRL, AUX_EN_FIFO_READ | CLR_EDID_FIFO, @@ -1076,10 +1101,14 @@ static ssize_t it6505_aux_do_transfer(struct it6505 *it6505, size_t size, enum aux_cmd_reply *reply) { int i, ret_size, ret = 0, request_size; + int fifo_max_size = (cmd == CMD_AUX_I2C_EDID_READ || cmd == CMD_AUX_GET_KSV_LIST) ? + AUX_FIFO_MAX_SIZE : 4; mutex_lock(&it6505->aux_lock); - for (i = 0; i < size; i += 4) { - request_size = min((int)size - i, 4); + i = 0; + do { + request_size = min_t(int, (int)size - i, fifo_max_size); + ret_size = it6505_aux_operation(it6505, cmd, address + i, buffer + i, request_size, reply); @@ -1088,14 +1117,170 @@ static ssize_t it6505_aux_do_transfer(struct it6505 *it6505, goto aux_op_err; } + i += request_size; ret += ret_size; - } + } while (i < size); aux_op_err: mutex_unlock(&it6505->aux_lock); return ret; } +static bool it6505_aux_i2c_reply_defer(u8 reply) +{ + if (reply == DP_AUX_NATIVE_REPLY_DEFER || reply == DP_AUX_I2C_REPLY_DEFER) + return true; + return false; +} + +static bool it6505_aux_i2c_reply_nack(u8 reply) +{ + if (reply == DP_AUX_NATIVE_REPLY_NACK || reply == DP_AUX_I2C_REPLY_NACK) + return true; + return false; +} + +static int it6505_aux_i2c_wait(struct it6505 *it6505, u8 *reply) +{ + int err = 0; + unsigned long timeout; + struct device *dev = it6505->dev; + + timeout = jiffies + msecs_to_jiffies(AUX_WAIT_TIMEOUT_MS) + 1; + + do { + if (it6505_read(it6505, REG_AUX_USER_CTRL) & AUX_EVENT) + break; + if (time_after(jiffies, timeout)) { + dev_err(dev, "Timed out waiting AUX I2C, BUSY = %X\n", + it6505_aux_op_finished(it6505)); + err = -ETIMEDOUT; + goto end_aux_i2c_wait; + } + usleep_range(300, 800); + } while (!it6505_aux_op_finished(it6505)); + + *reply = it6505_read(it6505, REG_AUX_USER_REPLY) >> 4; + + if (*reply == 0) + goto end_aux_i2c_wait; + + if (it6505_aux_i2c_reply_defer(*reply)) + err = -EBUSY; + else if (it6505_aux_i2c_reply_nack(*reply)) + err = -ENXIO; + +end_aux_i2c_wait: + it6505_set_bits(it6505, REG_AUX_USER_CTRL, USER_AUX_DONE, USER_AUX_DONE); + return err; +} + +static int it6505_aux_i2c_readb(struct it6505 *it6505, u8 *buf, size_t size, u8 *reply) +{ + int ret, i; + int retry; + + for (retry = 0; retry < AUX_I2C_DEFER_RETRY; retry++) { + it6505_write(it6505, REG_AUX_CMD_REQ, CMD_AUX_GI2C_READ); + + ret = it6505_aux_i2c_wait(it6505, reply); + if (it6505_aux_i2c_reply_defer(*reply)) + continue; + if (ret >= 0) + break; + } + + for (i = 0; i < size; i++) + buf[i] = it6505_read(it6505, REG_AUX_USER_RXB(0 + i)); + + return size; +} + +static int it6505_aux_i2c_writeb(struct it6505 *it6505, u8 *buf, size_t size, u8 *reply) +{ + int i, ret; + int retry; + + for (i = 0; i < size; i++) + it6505_write(it6505, REG_AUX_OUT_DATA0 + i, buf[i]); + + for (retry = 0; retry < AUX_I2C_DEFER_RETRY; retry++) { + it6505_write(it6505, REG_AUX_CMD_REQ, CMD_AUX_GI2C_WRITE); + + ret = it6505_aux_i2c_wait(it6505, reply); + if (it6505_aux_i2c_reply_defer(*reply)) + continue; + if (ret >= 0) + break; + } + return size; +} + +static ssize_t it6505_aux_i2c_operation(struct it6505 *it6505, + struct drm_dp_aux_msg *msg) +{ + int ret; + ssize_t request_size, data_cnt = 0; + u8 *buffer = msg->buffer; + + /* set AUX user mode */ + it6505_set_bits(it6505, REG_AUX_CTRL, + AUX_USER_MODE | AUX_NO_SEGMENT_WR, AUX_USER_MODE); + it6505_set_bits(it6505, REG_AUX_USER_CTRL, EN_USER_AUX, EN_USER_AUX); + /* clear AUX FIFO */ + it6505_set_bits(it6505, REG_AUX_CTRL, + AUX_EN_FIFO_READ | CLR_EDID_FIFO, + AUX_EN_FIFO_READ | CLR_EDID_FIFO); + + it6505_set_bits(it6505, REG_AUX_CTRL, + AUX_EN_FIFO_READ | CLR_EDID_FIFO, 0x00); + + it6505_write(it6505, REG_AUX_ADR_0_7, 0x00); + it6505_write(it6505, REG_AUX_ADR_8_15, msg->address << 1); + + if (msg->size == 0) { + /* IIC Start/STOP dummy write */ + it6505_write(it6505, REG_AUX_ADR_16_19, msg->request); + it6505_write(it6505, REG_AUX_CMD_REQ, CMD_AUX_GI2C_ADR); + ret = it6505_aux_i2c_wait(it6505, &msg->reply); + goto end_aux_i2c_transfer; + } + + /* IIC data transfer */ + data_cnt = 0; + do { + request_size = min_t(ssize_t, msg->size - data_cnt, AUX_I2C_MAX_SIZE); + it6505_write(it6505, REG_AUX_ADR_16_19, + msg->request | ((request_size - 1) << 4)); + if ((msg->request & DP_AUX_I2C_READ) == DP_AUX_I2C_READ) + ret = it6505_aux_i2c_readb(it6505, &buffer[data_cnt], + request_size, &msg->reply); + else + ret = it6505_aux_i2c_writeb(it6505, &buffer[data_cnt], + request_size, &msg->reply); + + if (ret < 0) + goto end_aux_i2c_transfer; + + data_cnt += request_size; + } while (data_cnt < msg->size); + ret = data_cnt; +end_aux_i2c_transfer: + + it6505_set_bits(it6505, REG_AUX_USER_CTRL, EN_USER_AUX, 0); + it6505_set_bits(it6505, REG_AUX_CTRL, AUX_USER_MODE, 0); + return ret; +} + +static ssize_t it6505_aux_i2c_transfer(struct drm_dp_aux *aux, + struct drm_dp_aux_msg *msg) +{ + struct it6505 *it6505 = container_of(aux, struct it6505, aux); + + guard(mutex)(&it6505->aux_lock); + return it6505_aux_i2c_operation(it6505, msg); +} + static ssize_t it6505_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) { @@ -1105,9 +1290,8 @@ static ssize_t it6505_aux_transfer(struct drm_dp_aux *aux, int ret; enum aux_cmd_reply reply; - /* IT6505 doesn't support arbitrary I2C read / write. */ if (is_i2c) - return -EINVAL; + return it6505_aux_i2c_transfer(aux, msg); switch (msg->request) { case DP_AUX_NATIVE_READ: @@ -1178,6 +1362,37 @@ static int it6505_get_edid_block(void *data, u8 *buf, unsigned int block, return 0; } +static int it6505_get_ksvlist(struct it6505 *it6505, u8 *buf, size_t len) +{ + struct device *dev = it6505->dev; + enum aux_cmd_reply reply; + int request_size, ret; + int i = 0; + + do { + request_size = min_t(int, (int)len - i, 15); + + ret = it6505_aux_do_transfer(it6505, CMD_AUX_GET_KSV_LIST, + DP_AUX_HDCP_KSV_FIFO, + buf + i, request_size, &reply); + + DRM_DEV_DEBUG_DRIVER(dev, "request_size = %d, ret =%d", request_size, ret); + if (ret < 0) + return ret; + + i += request_size; + } while (i < len); + + DRM_DEV_DEBUG_DRIVER(dev, "ksv read cnt = %d down_stream_cnt=%d ", i, i / 5); + + for (i = 0 ; i < len; i += 5) { + DRM_DEV_DEBUG_DRIVER(dev, "ksv[%d] = %02X%02X%02X%02X%02X", + i / 5, buf[i], buf[i + 1], buf[i + 2], buf[i + 3], buf[i + 4]); + } + + return len; +} + static void it6505_variable_config(struct it6505 *it6505) { it6505->link_rate_bw_code = HBR; @@ -1959,7 +2174,7 @@ static int it6505_setup_sha1_input(struct it6505 *it6505, u8 *sha1_input) { struct device *dev = it6505->dev; u8 binfo[2]; - int down_stream_count, i, err, msg_count = 0; + int down_stream_count, err, msg_count = 0; err = it6505_get_dpcd(it6505, DP_AUX_HDCP_BINFO, binfo, ARRAY_SIZE(binfo)); @@ -1984,18 +2199,11 @@ static int it6505_setup_sha1_input(struct it6505 *it6505, u8 *sha1_input) down_stream_count); return 0; } + err = it6505_get_ksvlist(it6505, sha1_input, down_stream_count * 5); + if (err < 0) + return err; - for (i = 0; i < down_stream_count; i++) { - err = it6505_get_dpcd(it6505, DP_AUX_HDCP_KSV_FIFO + - (i % 3) * DRM_HDCP_KSV_LEN, - sha1_input + msg_count, - DRM_HDCP_KSV_LEN); - - if (err < 0) - return err; - - msg_count += 5; - } + msg_count += down_stream_count * 5; it6505->hdcp_down_stream_count = down_stream_count; sha1_input[msg_count++] = binfo[0]; @@ -2023,7 +2231,7 @@ static bool it6505_hdcp_part2_ksvlist_check(struct it6505 *it6505) { struct device *dev = it6505->dev; u8 av[5][4], bv[5][4]; - int i, err; + int i, err, retry; i = it6505_setup_sha1_input(it6505, it6505->sha1_input); if (i <= 0) { @@ -2032,22 +2240,28 @@ static bool it6505_hdcp_part2_ksvlist_check(struct it6505 *it6505) } it6505_sha1_digest(it6505, it6505->sha1_input, i, (u8 *)av); + /*1B-05 V' must retry 3 times */ + for (retry = 0; retry < 3; retry++) { + err = it6505_get_dpcd(it6505, DP_AUX_HDCP_V_PRIME(0), (u8 *)bv, + sizeof(bv)); - err = it6505_get_dpcd(it6505, DP_AUX_HDCP_V_PRIME(0), (u8 *)bv, - sizeof(bv)); + if (err < 0) { + dev_err(dev, "Read V' value Fail %d", retry); + continue; + } - if (err < 0) { - dev_err(dev, "Read V' value Fail"); - return false; + for (i = 0; i < 5; i++) { + if (bv[i][3] != av[i][0] || bv[i][2] != av[i][1] || + av[i][1] != av[i][2] || bv[i][0] != av[i][3]) + break; + + DRM_DEV_DEBUG_DRIVER(dev, "V' all match!! %d, %d", retry, i); + return true; + } } - for (i = 0; i < 5; i++) - if (bv[i][3] != av[i][0] || bv[i][2] != av[i][1] || - bv[i][1] != av[i][2] || bv[i][0] != av[i][3]) - return false; - - DRM_DEV_DEBUG_DRIVER(dev, "V' all match!!"); - return true; + DRM_DEV_DEBUG_DRIVER(dev, "V' NOT match!! %d", retry); + return false; } static void it6505_hdcp_wait_ksv_list(struct work_struct *work) @@ -2055,12 +2269,13 @@ static void it6505_hdcp_wait_ksv_list(struct work_struct *work) struct it6505 *it6505 = container_of(work, struct it6505, hdcp_wait_ksv_list); struct device *dev = it6505->dev; - unsigned int timeout = 5000; - u8 bstatus = 0; + u8 bstatus; bool ksv_list_check; + /* 1B-04 wait ksv list for 5s */ + unsigned long timeout = jiffies + + msecs_to_jiffies(5000) + 1; - timeout /= 20; - while (timeout > 0) { + for (;;) { if (!it6505_get_sink_hpd_status(it6505)) return; @@ -2069,27 +2284,23 @@ static void it6505_hdcp_wait_ksv_list(struct work_struct *work) if (bstatus & DP_BSTATUS_READY) break; - msleep(20); - timeout--; - } + if (time_after(jiffies, timeout)) { + DRM_DEV_DEBUG_DRIVER(dev, "KSV list wait timeout"); + goto timeout; + } - if (timeout == 0) { - DRM_DEV_DEBUG_DRIVER(dev, "timeout and ksv list wait failed"); - goto timeout; + msleep(20); } ksv_list_check = it6505_hdcp_part2_ksvlist_check(it6505); DRM_DEV_DEBUG_DRIVER(dev, "ksv list ready, ksv list check %s", ksv_list_check ? "pass" : "fail"); - if (ksv_list_check) { - it6505_set_bits(it6505, REG_HDCP_TRIGGER, - HDCP_TRIGGER_KSV_DONE, HDCP_TRIGGER_KSV_DONE); + + if (ksv_list_check) return; - } + timeout: - it6505_set_bits(it6505, REG_HDCP_TRIGGER, - HDCP_TRIGGER_KSV_DONE | HDCP_TRIGGER_KSV_FAIL, - HDCP_TRIGGER_KSV_DONE | HDCP_TRIGGER_KSV_FAIL); + it6505_start_hdcp(it6505); } static void it6505_hdcp_work(struct work_struct *work) @@ -2312,14 +2523,20 @@ static int it6505_process_hpd_irq(struct it6505 *it6505) DRM_DEV_DEBUG_DRIVER(dev, "dp_irq_vector = 0x%02x", dp_irq_vector); if (dp_irq_vector & DP_CP_IRQ) { - it6505_set_bits(it6505, REG_HDCP_TRIGGER, HDCP_TRIGGER_CPIRQ, - HDCP_TRIGGER_CPIRQ); - bstatus = it6505_dpcd_read(it6505, DP_AUX_HDCP_BSTATUS); if (bstatus < 0) return bstatus; DRM_DEV_DEBUG_DRIVER(dev, "Bstatus = 0x%02x", bstatus); + + /*Check BSTATUS when recive CP_IRQ */ + if (bstatus & DP_BSTATUS_R0_PRIME_READY && + it6505->hdcp_status == HDCP_AUTH_GOING) + it6505_set_bits(it6505, REG_HDCP_TRIGGER, HDCP_TRIGGER_CPIRQ, + HDCP_TRIGGER_CPIRQ); + else if (bstatus & (DP_BSTATUS_REAUTH_REQ | DP_BSTATUS_LINK_FAILURE) && + it6505->hdcp_status == HDCP_AUTH_DONE) + it6505_start_hdcp(it6505); } ret = drm_dp_dpcd_read_link_status(&it6505->aux, link_status); @@ -2456,7 +2673,11 @@ static void it6505_irq_hdcp_ksv_check(struct it6505 *it6505) { struct device *dev = it6505->dev; - DRM_DEV_DEBUG_DRIVER(dev, "HDCP event Interrupt"); + DRM_DEV_DEBUG_DRIVER(dev, "HDCP repeater R0 event Interrupt"); + /* 1B01 HDCP encription should start when R0 is ready*/ + it6505_set_bits(it6505, REG_HDCP_TRIGGER, + HDCP_TRIGGER_KSV_DONE, HDCP_TRIGGER_KSV_DONE); + schedule_work(&it6505->hdcp_wait_ksv_list); } diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c index 940083e5d2dd..23edcde6b9a7 100644 --- a/drivers/gpu/drm/bridge/ite-it66121.c +++ b/drivers/gpu/drm/bridge/ite-it66121.c @@ -1466,7 +1466,6 @@ static const struct hdmi_codec_ops it66121_audio_codec_ops = { .audio_shutdown = it66121_audio_shutdown, .mute_stream = it66121_audio_mute, .get_eld = it66121_audio_get_eld, - .no_capture_mute = 1, }; static int it66121_audio_codec_init(struct it66121_ctx *ctx, struct device *dev) @@ -1476,11 +1475,12 @@ static int it66121_audio_codec_init(struct it66121_ctx *ctx, struct device *dev) .i2s = 1, /* Only i2s support for now */ .spdif = 0, .max_i2s_channels = 8, + .no_capture_mute = 1, }; dev_dbg(dev, "%s\n", __func__); - if (!of_property_read_bool(dev->of_node, "#sound-dai-cells")) { + if (!of_property_present(dev->of_node, "#sound-dai-cells")) { dev_info(dev, "No \"#sound-dai-cells\", no audio\n"); return 0; } diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 74f726efc746..e650cd83fc8d 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -45,7 +45,6 @@ struct lt9611 { struct device_node *dsi1_node; struct mipi_dsi_device *dsi0; struct mipi_dsi_device *dsi1; - struct platform_device *audio_pdev; bool ac_mode; @@ -767,15 +766,6 @@ static enum drm_mode_status lt9611_bridge_mode_valid(struct drm_bridge *bridge, return MODE_OK; } -static int lt9611_bridge_atomic_check(struct drm_bridge *bridge, - struct drm_bridge_state *bridge_state, - struct drm_crtc_state *crtc_state, - struct drm_connector_state *conn_state) -{ - return drm_atomic_helper_connector_hdmi_check(conn_state->connector, - conn_state->state); -} - static void lt9611_bridge_atomic_pre_enable(struct drm_bridge *bridge, struct drm_bridge_state *old_bridge_state) { @@ -864,6 +854,10 @@ static int lt9611_hdmi_clear_infoframe(struct drm_bridge *bridge, unsigned int mask; switch (type) { + case HDMI_INFOFRAME_TYPE_AUDIO: + mask = LT9611_INFOFRAME_AUDIO; + break; + case HDMI_INFOFRAME_TYPE_AVI: mask = LT9611_INFOFRAME_AVI; break; @@ -897,6 +891,11 @@ static int lt9611_hdmi_write_infoframe(struct drm_bridge *bridge, int i; switch (type) { + case HDMI_INFOFRAME_TYPE_AUDIO: + mask = LT9611_INFOFRAME_AUDIO; + addr = 0x84b2; + break; + case HDMI_INFOFRAME_TYPE_AVI: mask = LT9611_INFOFRAME_AVI; addr = 0x8440; @@ -940,6 +939,55 @@ lt9611_hdmi_tmds_char_rate_valid(const struct drm_bridge *bridge, return MODE_OK; } +static int lt9611_hdmi_audio_startup(struct drm_connector *connector, + struct drm_bridge *bridge) +{ + struct lt9611 *lt9611 = bridge_to_lt9611(bridge); + + regmap_write(lt9611->regmap, 0x82d6, 0x8c); + regmap_write(lt9611->regmap, 0x82d7, 0x04); + + regmap_write(lt9611->regmap, 0x8406, 0x08); + regmap_write(lt9611->regmap, 0x8407, 0x10); + + regmap_write(lt9611->regmap, 0x8434, 0xd5); + + return 0; +} + +static int lt9611_hdmi_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *fmt, + struct hdmi_codec_params *hparms) +{ + struct lt9611 *lt9611 = bridge_to_lt9611(bridge); + + if (hparms->sample_rate == 48000) + regmap_write(lt9611->regmap, 0x840f, 0x2b); + else if (hparms->sample_rate == 96000) + regmap_write(lt9611->regmap, 0x840f, 0xab); + else + return -EINVAL; + + regmap_write(lt9611->regmap, 0x8435, 0x00); + regmap_write(lt9611->regmap, 0x8436, 0x18); + regmap_write(lt9611->regmap, 0x8437, 0x00); + + return drm_atomic_helper_connector_hdmi_update_audio_infoframe(connector, + &hparms->cea); +} + +static void lt9611_hdmi_audio_shutdown(struct drm_connector *connector, + struct drm_bridge *bridge) +{ + struct lt9611 *lt9611 = bridge_to_lt9611(bridge); + + drm_atomic_helper_connector_hdmi_clear_audio_infoframe(connector); + + regmap_write(lt9611->regmap, 0x8406, 0x00); + regmap_write(lt9611->regmap, 0x8407, 0x00); +} + static const struct drm_bridge_funcs lt9611_bridge_funcs = { .attach = lt9611_bridge_attach, .mode_valid = lt9611_bridge_mode_valid, @@ -947,7 +995,6 @@ static const struct drm_bridge_funcs lt9611_bridge_funcs = { .edid_read = lt9611_bridge_edid_read, .hpd_enable = lt9611_bridge_hpd_enable, - .atomic_check = lt9611_bridge_atomic_check, .atomic_pre_enable = lt9611_bridge_atomic_pre_enable, .atomic_enable = lt9611_bridge_atomic_enable, .atomic_disable = lt9611_bridge_atomic_disable, @@ -960,6 +1007,10 @@ static const struct drm_bridge_funcs lt9611_bridge_funcs = { .hdmi_tmds_char_rate_valid = lt9611_hdmi_tmds_char_rate_valid, .hdmi_write_infoframe = lt9611_hdmi_write_infoframe, .hdmi_clear_infoframe = lt9611_hdmi_clear_infoframe, + + .hdmi_audio_startup = lt9611_hdmi_audio_startup, + .hdmi_audio_prepare = lt9611_hdmi_audio_prepare, + .hdmi_audio_shutdown = lt9611_hdmi_audio_shutdown, }; static int lt9611_parse_dt(struct device *dev, @@ -1013,101 +1064,6 @@ static int lt9611_read_device_rev(struct lt9611 *lt9611) return ret; } -static int lt9611_hdmi_hw_params(struct device *dev, void *data, - struct hdmi_codec_daifmt *fmt, - struct hdmi_codec_params *hparms) -{ - struct lt9611 *lt9611 = data; - - if (hparms->sample_rate == 48000) - regmap_write(lt9611->regmap, 0x840f, 0x2b); - else if (hparms->sample_rate == 96000) - regmap_write(lt9611->regmap, 0x840f, 0xab); - else - return -EINVAL; - - regmap_write(lt9611->regmap, 0x8435, 0x00); - regmap_write(lt9611->regmap, 0x8436, 0x18); - regmap_write(lt9611->regmap, 0x8437, 0x00); - - return 0; -} - -static int lt9611_audio_startup(struct device *dev, void *data) -{ - struct lt9611 *lt9611 = data; - - regmap_write(lt9611->regmap, 0x82d6, 0x8c); - regmap_write(lt9611->regmap, 0x82d7, 0x04); - - regmap_write(lt9611->regmap, 0x8406, 0x08); - regmap_write(lt9611->regmap, 0x8407, 0x10); - - regmap_write(lt9611->regmap, 0x8434, 0xd5); - - return 0; -} - -static void lt9611_audio_shutdown(struct device *dev, void *data) -{ - struct lt9611 *lt9611 = data; - - regmap_write(lt9611->regmap, 0x8406, 0x00); - regmap_write(lt9611->regmap, 0x8407, 0x00); -} - -static int lt9611_hdmi_i2s_get_dai_id(struct snd_soc_component *component, - struct device_node *endpoint) -{ - struct of_endpoint of_ep; - int ret; - - ret = of_graph_parse_endpoint(endpoint, &of_ep); - if (ret < 0) - return ret; - - /* - * HDMI sound should be located as reg = <2> - * Then, it is sound port 0 - */ - if (of_ep.port == 2) - return 0; - - return -EINVAL; -} - -static const struct hdmi_codec_ops lt9611_codec_ops = { - .hw_params = lt9611_hdmi_hw_params, - .audio_shutdown = lt9611_audio_shutdown, - .audio_startup = lt9611_audio_startup, - .get_dai_id = lt9611_hdmi_i2s_get_dai_id, -}; - -static struct hdmi_codec_pdata codec_data = { - .ops = <9611_codec_ops, - .max_i2s_channels = 8, - .i2s = 1, -}; - -static int lt9611_audio_init(struct device *dev, struct lt9611 *lt9611) -{ - codec_data.data = lt9611; - lt9611->audio_pdev = - platform_device_register_data(dev, HDMI_CODEC_DRV_NAME, - PLATFORM_DEVID_AUTO, - &codec_data, sizeof(codec_data)); - - return PTR_ERR_OR_ZERO(lt9611->audio_pdev); -} - -static void lt9611_audio_exit(struct lt9611 *lt9611) -{ - if (lt9611->audio_pdev) { - platform_device_unregister(lt9611->audio_pdev); - lt9611->audio_pdev = NULL; - } -} - static int lt9611_probe(struct i2c_client *client) { struct lt9611 *lt9611; @@ -1171,6 +1127,9 @@ static int lt9611_probe(struct i2c_client *client) i2c_set_clientdata(client, lt9611); + /* Disable Audio InfoFrame, enabled by default */ + regmap_update_bits(lt9611->regmap, 0x843d, LT9611_INFOFRAME_AUDIO, 0); + lt9611->bridge.funcs = <9611_bridge_funcs; lt9611->bridge.of_node = client->dev.of_node; lt9611->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID | @@ -1179,6 +1138,9 @@ static int lt9611_probe(struct i2c_client *client) lt9611->bridge.type = DRM_MODE_CONNECTOR_HDMIA; lt9611->bridge.vendor = "Lontium"; lt9611->bridge.product = "LT9611"; + lt9611->bridge.hdmi_audio_dev = dev; + lt9611->bridge.hdmi_audio_max_i2s_playback_channels = 8; + lt9611->bridge.hdmi_audio_dai_port = 2; drm_bridge_add(<9611->bridge); @@ -1200,10 +1162,6 @@ static int lt9611_probe(struct i2c_client *client) lt9611_enable_hpd_interrupts(lt9611); - ret = lt9611_audio_init(dev, lt9611); - if (ret) - goto err_remove_bridge; - return 0; err_remove_bridge: @@ -1224,7 +1182,6 @@ static void lt9611_remove(struct i2c_client *client) struct lt9611 *lt9611 = i2c_get_clientdata(client); disable_irq(client->irq); - lt9611_audio_exit(lt9611); drm_bridge_remove(<9611->bridge); regulator_bulk_disable(ARRAY_SIZE(lt9611->supplies), lt9611->supplies); diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c index db9a5466060b..f4c3ff1fdc69 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c @@ -522,7 +522,8 @@ static void lt9611uxc_audio_shutdown(struct device *dev, void *data) } static int lt9611uxc_hdmi_i2s_get_dai_id(struct snd_soc_component *component, - struct device_node *endpoint) + struct device_node *endpoint, + void *data) { struct of_endpoint of_ep; int ret; diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c index 127da22011b3..bf2d1632b020 100644 --- a/drivers/gpu/drm/bridge/sii902x.c +++ b/drivers/gpu/drm/bridge/sii902x.c @@ -815,7 +815,8 @@ static int sii902x_audio_get_eld(struct device *dev, void *data, } static int sii902x_audio_get_dai_id(struct snd_soc_component *component, - struct device_node *endpoint) + struct device_node *endpoint, + void *data) { struct of_endpoint of_ep; int ret; @@ -840,7 +841,6 @@ static const struct hdmi_codec_ops sii902x_audio_codec_ops = { .mute_stream = sii902x_audio_mute, .get_eld = sii902x_audio_get_eld, .get_dai_id = sii902x_audio_get_dai_id, - .no_capture_mute = 1, }; static int sii902x_audio_codec_init(struct sii902x *sii902x, @@ -863,11 +863,12 @@ static int sii902x_audio_codec_init(struct sii902x *sii902x, .i2s = 1, /* Only i2s support for now. */ .spdif = 0, .max_i2s_channels = 0, + .no_capture_mute = 1, }; u8 lanes[4]; int num_lanes, i; - if (!of_property_read_bool(dev->of_node, "#sound-dai-cells")) { + if (!of_property_present(dev->of_node, "#sound-dai-cells")) { dev_dbg(dev, "%s: No \"#sound-dai-cells\", no audio\n", __func__); return 0; diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c index f1c5a8d0fa90..2c903c9fe805 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c @@ -148,7 +148,8 @@ static int dw_hdmi_i2s_get_eld(struct device *dev, void *data, uint8_t *buf, } static int dw_hdmi_i2s_get_dai_id(struct snd_soc_component *component, - struct device_node *endpoint) + struct device_node *endpoint, + void *data) { struct of_endpoint of_ep; int ret; diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c index c686671e4850..b281cabfe992 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c @@ -361,22 +361,6 @@ static int dw_hdmi_qp_config_drm_infoframe(struct dw_hdmi_qp *hdmi, return 0; } -static int dw_hdmi_qp_bridge_atomic_check(struct drm_bridge *bridge, - struct drm_bridge_state *bridge_state, - struct drm_crtc_state *crtc_state, - struct drm_connector_state *conn_state) -{ - struct dw_hdmi_qp *hdmi = bridge->driver_private; - int ret; - - ret = drm_atomic_helper_connector_hdmi_check(conn_state->connector, - conn_state->state); - if (ret) - dev_dbg(hdmi->dev, "%s failed: %d\n", __func__, ret); - - return ret; -} - static void dw_hdmi_qp_bridge_atomic_enable(struct drm_bridge *bridge, struct drm_bridge_state *old_state) { @@ -503,7 +487,6 @@ static const struct drm_bridge_funcs dw_hdmi_qp_bridge_funcs = { .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, .atomic_reset = drm_atomic_helper_bridge_reset, - .atomic_check = dw_hdmi_qp_bridge_atomic_check, .atomic_enable = dw_hdmi_qp_bridge_atomic_enable, .atomic_disable = dw_hdmi_qp_bridge_atomic_disable, .detect = dw_hdmi_qp_bridge_detect, diff --git a/drivers/gpu/drm/display/Kconfig b/drivers/gpu/drm/display/Kconfig index 6a4e892afcf8..8d22b7627d41 100644 --- a/drivers/gpu/drm/display/Kconfig +++ b/drivers/gpu/drm/display/Kconfig @@ -15,6 +15,7 @@ if DRM_DISPLAY_HELPER config DRM_BRIDGE_CONNECTOR bool + select DRM_DISPLAY_HDMI_AUDIO_HELPER select DRM_DISPLAY_HDMI_STATE_HELPER help DRM connector implementation terminating DRM bridge chains. @@ -75,6 +76,12 @@ config DRM_DISPLAY_HDCP_HELPER help DRM display helpers for HDCP. +config DRM_DISPLAY_HDMI_AUDIO_HELPER + bool + help + DRM display helpers for HDMI Audio functionality (generic HDMI Codec + implementation). + config DRM_DISPLAY_HDMI_HELPER bool help @@ -82,6 +89,7 @@ config DRM_DISPLAY_HDMI_HELPER config DRM_DISPLAY_HDMI_STATE_HELPER bool + select DRM_DISPLAY_HDMI_AUDIO_HELPER select DRM_DISPLAY_HDMI_HELPER help DRM KMS state helpers for HDMI. diff --git a/drivers/gpu/drm/display/Makefile b/drivers/gpu/drm/display/Makefile index 629c834c3192..b17879b957d5 100644 --- a/drivers/gpu/drm/display/Makefile +++ b/drivers/gpu/drm/display/Makefile @@ -14,6 +14,8 @@ drm_display_helper-$(CONFIG_DRM_DISPLAY_DP_TUNNEL) += \ drm_display_helper-$(CONFIG_DRM_DISPLAY_DSC_HELPER) += \ drm_dsc_helper.o drm_display_helper-$(CONFIG_DRM_DISPLAY_HDCP_HELPER) += drm_hdcp_helper.o +drm_display_helper-$(CONFIG_DRM_DISPLAY_HDMI_AUDIO_HELPER) += \ + drm_hdmi_audio_helper.o drm_display_helper-$(CONFIG_DRM_DISPLAY_HDMI_HELPER) += \ drm_hdmi_helper.o \ drm_scdc_helper.o diff --git a/drivers/gpu/drm/display/drm_bridge_connector.c b/drivers/gpu/drm/display/drm_bridge_connector.c index 512ced87ea18..56f977bbe62d 100644 --- a/drivers/gpu/drm/display/drm_bridge_connector.c +++ b/drivers/gpu/drm/display/drm_bridge_connector.c @@ -17,7 +17,9 @@ #include #include #include +#include #include +#include #include #include @@ -180,11 +182,15 @@ drm_bridge_connector_detect(struct drm_connector *connector, bool force) struct drm_bridge_connector *bridge_connector = to_drm_bridge_connector(connector); struct drm_bridge *detect = bridge_connector->bridge_detect; + struct drm_bridge *hdmi = bridge_connector->bridge_hdmi; enum drm_connector_status status; if (detect) { status = detect->funcs->detect(detect); + if (hdmi) + drm_atomic_helper_connector_hdmi_hotplug(connector, status); + drm_bridge_connector_hpd_notify(connector, status); } else { switch (connector->connector_type) { @@ -203,6 +209,16 @@ drm_bridge_connector_detect(struct drm_connector *connector, bool force) return status; } +static void drm_bridge_connector_force(struct drm_connector *connector) +{ + struct drm_bridge_connector *bridge_connector = + to_drm_bridge_connector(connector); + struct drm_bridge *hdmi = bridge_connector->bridge_hdmi; + + if (hdmi) + drm_atomic_helper_connector_hdmi_force(connector); +} + static void drm_bridge_connector_debugfs_init(struct drm_connector *connector, struct dentry *root) { @@ -231,6 +247,7 @@ static void drm_bridge_connector_reset(struct drm_connector *connector) static const struct drm_connector_funcs drm_bridge_connector_funcs = { .reset = drm_bridge_connector_reset, .detect = drm_bridge_connector_detect, + .force = drm_bridge_connector_force, .fill_modes = drm_helper_probe_single_connector_modes, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, @@ -276,6 +293,14 @@ static int drm_bridge_connector_get_modes(struct drm_connector *connector) to_drm_bridge_connector(connector); struct drm_bridge *bridge; + /* + * If there is a HDMI bridge, EDID has been updated as a part of + * the .detect(). Just update the modes here. + */ + bridge = bridge_connector->bridge_hdmi; + if (bridge) + return drm_edid_connector_add_modes(connector); + /* * If display exposes EDID, then we parse that in the normal way to * build table of supported modes. @@ -313,11 +338,24 @@ drm_bridge_connector_mode_valid(struct drm_connector *connector, return MODE_OK; } +static int drm_bridge_connector_atomic_check(struct drm_connector *connector, + struct drm_atomic_state *state) +{ + struct drm_bridge_connector *bridge_connector = + to_drm_bridge_connector(connector); + + if (bridge_connector->bridge_hdmi) + return drm_atomic_helper_connector_hdmi_check(connector, state); + + return 0; +} + static const struct drm_connector_helper_funcs drm_bridge_connector_helper_funcs = { .get_modes = drm_bridge_connector_get_modes, .mode_valid = drm_bridge_connector_mode_valid, .enable_hpd = drm_bridge_connector_enable_hpd, .disable_hpd = drm_bridge_connector_disable_hpd, + .atomic_check = drm_bridge_connector_atomic_check, }; static enum drm_mode_status @@ -368,10 +406,94 @@ static int drm_bridge_connector_write_infoframe(struct drm_connector *connector, return bridge->funcs->hdmi_write_infoframe(bridge, type, buffer, len); } +static const struct drm_edid * +drm_bridge_connector_read_edid(struct drm_connector *connector) +{ + struct drm_bridge_connector *bridge_connector = + to_drm_bridge_connector(connector); + struct drm_bridge *bridge; + + bridge = bridge_connector->bridge_edid; + if (!bridge) + return NULL; + + return drm_bridge_edid_read(bridge, connector); +} + static const struct drm_connector_hdmi_funcs drm_bridge_connector_hdmi_funcs = { .tmds_char_rate_valid = drm_bridge_connector_tmds_char_rate_valid, .clear_infoframe = drm_bridge_connector_clear_infoframe, .write_infoframe = drm_bridge_connector_write_infoframe, + .read_edid = drm_bridge_connector_read_edid, +}; + +static int drm_bridge_connector_audio_startup(struct drm_connector *connector) +{ + struct drm_bridge_connector *bridge_connector = + to_drm_bridge_connector(connector); + struct drm_bridge *bridge; + + bridge = bridge_connector->bridge_hdmi; + if (!bridge) + return -EINVAL; + + if (!bridge->funcs->hdmi_audio_startup) + return 0; + + return bridge->funcs->hdmi_audio_startup(connector, bridge); +} + +static int drm_bridge_connector_audio_prepare(struct drm_connector *connector, + struct hdmi_codec_daifmt *fmt, + struct hdmi_codec_params *hparms) +{ + struct drm_bridge_connector *bridge_connector = + to_drm_bridge_connector(connector); + struct drm_bridge *bridge; + + bridge = bridge_connector->bridge_hdmi; + if (!bridge) + return -EINVAL; + + return bridge->funcs->hdmi_audio_prepare(connector, bridge, fmt, hparms); +} + +static void drm_bridge_connector_audio_shutdown(struct drm_connector *connector) +{ + struct drm_bridge_connector *bridge_connector = + to_drm_bridge_connector(connector); + struct drm_bridge *bridge; + + bridge = bridge_connector->bridge_hdmi; + if (!bridge) + return; + + bridge->funcs->hdmi_audio_shutdown(connector, bridge); +} + +static int drm_bridge_connector_audio_mute_stream(struct drm_connector *connector, + bool enable, int direction) +{ + struct drm_bridge_connector *bridge_connector = + to_drm_bridge_connector(connector); + struct drm_bridge *bridge; + + bridge = bridge_connector->bridge_hdmi; + if (!bridge) + return -EINVAL; + + if (bridge->funcs->hdmi_audio_mute_stream) + return bridge->funcs->hdmi_audio_mute_stream(connector, bridge, + enable, direction); + else + return -ENOTSUPP; +} + +static const struct drm_connector_hdmi_audio_funcs drm_bridge_connector_hdmi_audio_funcs = { + .startup = drm_bridge_connector_audio_startup, + .prepare = drm_bridge_connector_audio_prepare, + .shutdown = drm_bridge_connector_audio_shutdown, + .mute_stream = drm_bridge_connector_audio_mute_stream, }; /* ----------------------------------------------------------------------------- @@ -473,7 +595,12 @@ struct drm_connector *drm_bridge_connector_init(struct drm_device *drm, if (connector_type == DRM_MODE_CONNECTOR_Unknown) return ERR_PTR(-EINVAL); - if (bridge_connector->bridge_hdmi) + if (bridge_connector->bridge_hdmi) { + if (!connector->ycbcr_420_allowed) + supported_formats &= ~BIT(HDMI_COLORSPACE_YUV420); + + bridge = bridge_connector->bridge_hdmi; + ret = drmm_connector_hdmi_init(drm, connector, bridge_connector->bridge_hdmi->vendor, bridge_connector->bridge_hdmi->product, @@ -482,12 +609,31 @@ struct drm_connector *drm_bridge_connector_init(struct drm_device *drm, connector_type, ddc, supported_formats, max_bpc); - else + if (ret) + return ERR_PTR(ret); + + if (bridge->hdmi_audio_max_i2s_playback_channels || + bridge->hdmi_audio_spdif_playback) { + if (!bridge->funcs->hdmi_audio_prepare || + !bridge->funcs->hdmi_audio_shutdown) + return ERR_PTR(-EINVAL); + + ret = drm_connector_hdmi_audio_init(connector, + bridge->hdmi_audio_dev, + &drm_bridge_connector_hdmi_audio_funcs, + bridge->hdmi_audio_max_i2s_playback_channels, + bridge->hdmi_audio_spdif_playback, + bridge->hdmi_audio_dai_port); + if (ret) + return ERR_PTR(ret); + } + } else { ret = drmm_connector_init(drm, connector, &drm_bridge_connector_funcs, connector_type, ddc); - if (ret) - return ERR_PTR(ret); + if (ret) + return ERR_PTR(ret); + } drm_connector_helper_add(connector, &drm_bridge_connector_helper_funcs); diff --git a/drivers/gpu/drm/display/drm_dp_tunnel.c b/drivers/gpu/drm/display/drm_dp_tunnel.c index 48b2df120086..90fe07a89260 100644 --- a/drivers/gpu/drm/display/drm_dp_tunnel.c +++ b/drivers/gpu/drm/display/drm_dp_tunnel.c @@ -1896,8 +1896,8 @@ static void destroy_mgr(struct drm_dp_tunnel_mgr *mgr) * * Creates a DP tunnel manager for @dev. * - * Returns a pointer to the tunnel manager if created successfully or NULL in - * case of an error. + * Returns a pointer to the tunnel manager if created successfully or error + * pointer in case of failure. */ struct drm_dp_tunnel_mgr * drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) @@ -1907,7 +1907,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) mgr = kzalloc(sizeof(*mgr), GFP_KERNEL); if (!mgr) - return NULL; + return ERR_PTR(-ENOMEM); mgr->dev = dev; init_waitqueue_head(&mgr->bw_req_queue); @@ -1916,7 +1916,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) if (!mgr->groups) { kfree(mgr); - return NULL; + return ERR_PTR(-ENOMEM); } #ifdef CONFIG_DRM_DISPLAY_DP_TUNNEL_STATE_DEBUG @@ -1927,7 +1927,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) if (!init_group(mgr, &mgr->groups[i])) { destroy_mgr(mgr); - return NULL; + return ERR_PTR(-ENOMEM); } mgr->group_count++; diff --git a/drivers/gpu/drm/display/drm_hdmi_audio_helper.c b/drivers/gpu/drm/display/drm_hdmi_audio_helper.c new file mode 100644 index 000000000000..05afc9f0bdd6 --- /dev/null +++ b/drivers/gpu/drm/display/drm_hdmi_audio_helper.c @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright (c) 2024 Linaro Ltd + */ + +#include +#include +#include + +#include +#include +#include + +#include + +static int drm_connector_hdmi_audio_startup(struct device *dev, void *data) +{ + struct drm_connector *connector = data; + const struct drm_connector_hdmi_audio_funcs *funcs = + connector->hdmi_audio.funcs; + + if (funcs->startup) + return funcs->startup(connector); + + return 0; +} + +static int drm_connector_hdmi_audio_prepare(struct device *dev, void *data, + struct hdmi_codec_daifmt *fmt, + struct hdmi_codec_params *hparms) +{ + struct drm_connector *connector = data; + const struct drm_connector_hdmi_audio_funcs *funcs = + connector->hdmi_audio.funcs; + + return funcs->prepare(connector, fmt, hparms); +} + +static void drm_connector_hdmi_audio_shutdown(struct device *dev, void *data) +{ + struct drm_connector *connector = data; + const struct drm_connector_hdmi_audio_funcs *funcs = + connector->hdmi_audio.funcs; + + return funcs->shutdown(connector); +} + +static int drm_connector_hdmi_audio_mute_stream(struct device *dev, void *data, + bool enable, int direction) +{ + struct drm_connector *connector = data; + const struct drm_connector_hdmi_audio_funcs *funcs = + connector->hdmi_audio.funcs; + + if (funcs->mute_stream) + return funcs->mute_stream(connector, enable, direction); + + return -ENOTSUPP; +} + +static int drm_connector_hdmi_audio_get_dai_id(struct snd_soc_component *comment, + struct device_node *endpoint, + void *data) +{ + struct drm_connector *connector = data; + struct of_endpoint of_ep; + int ret; + + if (connector->hdmi_audio.dai_port < 0) + return -ENOTSUPP; + + ret = of_graph_parse_endpoint(endpoint, &of_ep); + if (ret < 0) + return ret; + + if (of_ep.port == connector->hdmi_audio.dai_port) + return 0; + + return -EINVAL; +} + +static int drm_connector_hdmi_audio_get_eld(struct device *dev, void *data, + uint8_t *buf, size_t len) +{ + struct drm_connector *connector = data; + + mutex_lock(&connector->eld_mutex); + memcpy(buf, connector->eld, min(sizeof(connector->eld), len)); + mutex_unlock(&connector->eld_mutex); + + return 0; +} + +static int drm_connector_hdmi_audio_hook_plugged_cb(struct device *dev, + void *data, + hdmi_codec_plugged_cb fn, + struct device *codec_dev) +{ + struct drm_connector *connector = data; + + mutex_lock(&connector->hdmi_audio.lock); + + connector->hdmi_audio.plugged_cb = fn; + connector->hdmi_audio.plugged_cb_dev = codec_dev; + + fn(codec_dev, connector->hdmi_audio.last_state); + + mutex_unlock(&connector->hdmi_audio.lock); + + return 0; +} + +void drm_connector_hdmi_audio_plugged_notify(struct drm_connector *connector, + bool plugged) +{ + mutex_lock(&connector->hdmi_audio.lock); + + connector->hdmi_audio.last_state = plugged; + + if (connector->hdmi_audio.plugged_cb && + connector->hdmi_audio.plugged_cb_dev) + connector->hdmi_audio.plugged_cb(connector->hdmi_audio.plugged_cb_dev, + connector->hdmi_audio.last_state); + + mutex_unlock(&connector->hdmi_audio.lock); +} +EXPORT_SYMBOL(drm_connector_hdmi_audio_plugged_notify); + +static const struct hdmi_codec_ops drm_connector_hdmi_audio_ops = { + .audio_startup = drm_connector_hdmi_audio_startup, + .prepare = drm_connector_hdmi_audio_prepare, + .audio_shutdown = drm_connector_hdmi_audio_shutdown, + .mute_stream = drm_connector_hdmi_audio_mute_stream, + .get_eld = drm_connector_hdmi_audio_get_eld, + .get_dai_id = drm_connector_hdmi_audio_get_dai_id, + .hook_plugged_cb = drm_connector_hdmi_audio_hook_plugged_cb, +}; + +/** + * drm_connector_hdmi_audio_init - Initialize HDMI Codec device for the DRM connector + * @connector: A pointer to the connector to allocate codec for + * @hdmi_codec_dev: device to be used as a parent for the HDMI Codec + * @funcs: callbacks for this HDMI Codec + * @max_i2s_playback_channels: maximum number of playback I2S channels + * @spdif_playback: set if HDMI codec has S/PDIF playback port + * @dai_port: sound DAI port, -1 if it is not enabled + * + * Create a HDMI codec device to be used with the specified connector. + * + * Returns: + * Zero on success, error code on failure. + */ +int drm_connector_hdmi_audio_init(struct drm_connector *connector, + struct device *hdmi_codec_dev, + const struct drm_connector_hdmi_audio_funcs *funcs, + unsigned int max_i2s_playback_channels, + bool spdif_playback, + int dai_port) +{ + struct hdmi_codec_pdata codec_pdata = { + .ops = &drm_connector_hdmi_audio_ops, + .max_i2s_channels = max_i2s_playback_channels, + .i2s = !!max_i2s_playback_channels, + .spdif = spdif_playback, + .no_i2s_capture = true, + .no_spdif_capture = true, + .data = connector, + }; + struct platform_device *pdev; + + if (!funcs || + !funcs->prepare || + !funcs->shutdown) + return -EINVAL; + + connector->hdmi_audio.funcs = funcs; + connector->hdmi_audio.dai_port = dai_port; + + pdev = platform_device_register_data(hdmi_codec_dev, + HDMI_CODEC_DRV_NAME, + PLATFORM_DEVID_AUTO, + &codec_pdata, sizeof(codec_pdata)); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); + + connector->hdmi_audio.codec_pdev = pdev; + + return 0; +} +EXPORT_SYMBOL(drm_connector_hdmi_audio_init); diff --git a/drivers/gpu/drm/display/drm_hdmi_state_helper.c b/drivers/gpu/drm/display/drm_hdmi_state_helper.c index d678c635a693..9b2ee2385634 100644 --- a/drivers/gpu/drm/display/drm_hdmi_state_helper.c +++ b/drivers/gpu/drm/display/drm_hdmi_state_helper.c @@ -5,6 +5,7 @@ #include #include +#include #include #include @@ -502,6 +503,9 @@ int drm_atomic_helper_connector_hdmi_check(struct drm_connector *connector, connector_state_get_mode(new_conn_state); int ret; + if (!new_conn_state->crtc || !new_conn_state->best_encoder) + return 0; + new_conn_state->hdmi.is_limited_range = hdmi_is_limited_range(connector, new_conn_state); ret = hdmi_compute_config(connector, new_conn_state, mode); @@ -777,3 +781,61 @@ drm_atomic_helper_connector_hdmi_clear_audio_infoframe(struct drm_connector *con return ret; } EXPORT_SYMBOL(drm_atomic_helper_connector_hdmi_clear_audio_infoframe); + +static void +drm_atomic_helper_connector_hdmi_update(struct drm_connector *connector, + enum drm_connector_status status) +{ + const struct drm_edid *drm_edid; + + if (status == connector_status_disconnected) { + // TODO: also handle CEC and scramber, HDMI sink disconnected. + drm_connector_hdmi_audio_plugged_notify(connector, false); + drm_edid_connector_update(connector, NULL); + return; + } + + if (connector->hdmi.funcs->read_edid) + drm_edid = connector->hdmi.funcs->read_edid(connector); + else + drm_edid = drm_edid_read(connector); + + drm_edid_connector_update(connector, drm_edid); + + drm_edid_free(drm_edid); + + if (status == connector_status_connected) { + // TODO: also handle CEC and scramber, HDMI sink is now connected. + drm_connector_hdmi_audio_plugged_notify(connector, true); + } +} + +/** + * drm_atomic_helper_connector_hdmi_hotplug - Handle the hotplug event for the HDMI connector + * @connector: A pointer to the HDMI connector + * @status: Connection status + * + * This function should be called as a part of the .detect() / .detect_ctx() + * callbacks, updating the HDMI-specific connector's data. + */ +void drm_atomic_helper_connector_hdmi_hotplug(struct drm_connector *connector, + enum drm_connector_status status) +{ + drm_atomic_helper_connector_hdmi_update(connector, status); +} +EXPORT_SYMBOL(drm_atomic_helper_connector_hdmi_hotplug); + +/** + * drm_atomic_helper_connector_hdmi_force - HDMI Connector implementation of the force callback + * @connector: A pointer to the HDMI connector + * + * This function implements the .force() callback for the HDMI connectors. It + * can either be used directly as the callback or should be called from within + * the .force() callback implementation to maintain the HDMI-specific + * connector's data. + */ +void drm_atomic_helper_connector_hdmi_force(struct drm_connector *connector) +{ + drm_atomic_helper_connector_hdmi_update(connector, connector->status); +} +EXPORT_SYMBOL(drm_atomic_helper_connector_hdmi_force); diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c index c6af46dd02bf..241a384ebce3 100644 --- a/drivers/gpu/drm/drm_bridge.c +++ b/drivers/gpu/drm/drm_bridge.c @@ -207,6 +207,10 @@ void drm_bridge_add(struct drm_bridge *bridge) { mutex_init(&bridge->hpd_mutex); + if (bridge->ops & DRM_BRIDGE_OP_HDMI) + bridge->ycbcr_420_allowed = !!(bridge->supported_formats & + BIT(HDMI_COLORSPACE_YUV420)); + mutex_lock(&bridge_lock); list_add_tail(&bridge->list, &bridge_list); mutex_unlock(&bridge_lock); diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 251f94313717..aca442c25209 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -743,6 +743,15 @@ retry: if ((conn_configured & mask) != mask && conn_configured != conn_seq) goto retry; + for (i = 0; i < count; i++) { + struct drm_connector *connector = connectors[i]; + + if (connector->has_tile) + drm_client_get_tile_offsets(dev, connectors, connector_count, + modes, offsets, i, + connector->tile_h_loc, connector->tile_v_loc); + } + /* * If the BIOS didn't enable everything it could, fall back to have the * same user experiencing of lighting up as much as possible like the diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index ae6e71305f30..5f24d6b41cc6 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -33,6 +33,7 @@ #include #include +#include #include #include @@ -281,6 +282,7 @@ static int drm_connector_init_only(struct drm_device *dev, mutex_init(&connector->eld_mutex); mutex_init(&connector->edid_override_mutex); mutex_init(&connector->hdmi.infoframes.lock); + mutex_init(&connector->hdmi_audio.lock); connector->edid_blob_ptr = NULL; connector->epoch_counter = 0; connector->tile_blob_ptr = NULL; @@ -590,6 +592,9 @@ int drmm_connector_hdmi_init(struct drm_device *dev, if (!supported_formats || !(supported_formats & BIT(HDMI_COLORSPACE_RGB))) return -EINVAL; + if (connector->ycbcr_420_allowed != !!(supported_formats & BIT(HDMI_COLORSPACE_YUV420))) + return -EINVAL; + if (!(max_bpc == 8 || max_bpc == 10 || max_bpc == 12)) return -EINVAL; @@ -714,6 +719,8 @@ void drm_connector_cleanup(struct drm_connector *connector) DRM_CONNECTOR_REGISTERED)) drm_connector_unregister(connector); + platform_device_unregister(connector->hdmi_audio.codec_pdev); + if (connector->privacy_screen) { drm_privacy_screen_put(connector->privacy_screen); connector->privacy_screen = NULL; @@ -750,6 +757,7 @@ void drm_connector_cleanup(struct drm_connector *connector) connector->funcs->atomic_destroy_state(connector, connector->state); + mutex_destroy(&connector->hdmi_audio.lock); mutex_destroy(&connector->hdmi.infoframes.lock); mutex_destroy(&connector->mutex); diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index c2c172eb25df..3cf440eee8a2 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -26,6 +26,7 @@ * DEALINGS IN THE SOFTWARE. */ +#include #include #include #include @@ -820,6 +821,37 @@ void drm_dev_put(struct drm_device *dev) } EXPORT_SYMBOL(drm_dev_put); +static void drmm_cg_unregister_region(struct drm_device *dev, void *arg) +{ + dmem_cgroup_unregister_region(arg); +} + +/** + * drmm_cgroup_register_region - Register a region of a DRM device to cgroups + * @dev: device for region + * @region_name: Region name for registering + * @size: Size of region in bytes + * + * This decreases the ref-count of @dev by one. The device is destroyed if the + * ref-count drops to zero. + */ +struct dmem_cgroup_region *drmm_cgroup_register_region(struct drm_device *dev, const char *region_name, u64 size) +{ + struct dmem_cgroup_region *region; + int ret; + + region = dmem_cgroup_register_region(size, "drm/%s/%s", dev->unique, region_name); + if (IS_ERR_OR_NULL(region)) + return region; + + ret = drmm_add_action_or_reset(dev, drmm_cg_unregister_region, region); + if (ret) + return ERR_PTR(ret); + + return region; +} +EXPORT_SYMBOL_GPL(drmm_cgroup_register_region); + static int create_compat_control_link(struct drm_device *dev) { struct drm_minor *minor; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index c9008113111b..fb3614a7ba44 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1354,14 +1354,14 @@ int drm_fb_helper_set_par(struct fb_info *info) } EXPORT_SYMBOL(drm_fb_helper_set_par); -static void pan_set(struct drm_fb_helper *fb_helper, int x, int y) +static void pan_set(struct drm_fb_helper *fb_helper, int dx, int dy) { struct drm_mode_set *mode_set; mutex_lock(&fb_helper->client.modeset_mutex); drm_client_for_each_modeset(mode_set, &fb_helper->client) { - mode_set->x = x; - mode_set->y = y; + mode_set->x += dx; + mode_set->y += dy; } mutex_unlock(&fb_helper->client.modeset_mutex); } @@ -1370,16 +1370,18 @@ static int pan_display_atomic(struct fb_var_screeninfo *var, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; - int ret; + int ret, dx, dy; - pan_set(fb_helper, var->xoffset, var->yoffset); + dx = var->xoffset - info->var.xoffset; + dy = var->yoffset - info->var.yoffset; + pan_set(fb_helper, dx, dy); ret = drm_client_modeset_commit_locked(&fb_helper->client); if (!ret) { info->var.xoffset = var->xoffset; info->var.yoffset = var->yoffset; } else - pan_set(fb_helper, info->var.xoffset, info->var.yoffset); + pan_set(fb_helper, -dx, -dy); return ret; } diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index cb5f22f5bbb6..2289e71e2fa2 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -845,6 +845,16 @@ static void print_size(struct drm_printer *p, const char *stat, drm_printf(p, "drm-%s-%s:\t%llu%s\n", stat, region, sz, units[u]); } +int drm_memory_stats_is_zero(const struct drm_memory_stats *stats) +{ + return (stats->shared == 0 && + stats->private == 0 && + stats->resident == 0 && + stats->purgeable == 0 && + stats->active == 0); +} +EXPORT_SYMBOL(drm_memory_stats_is_zero); + /** * drm_print_memory_stats - A helper to print memory stats * @p: The printer to print output to @@ -860,7 +870,9 @@ void drm_print_memory_stats(struct drm_printer *p, { print_size(p, "total", region, stats->private + stats->shared); print_size(p, "shared", region, stats->shared); - print_size(p, "active", region, stats->active); + + if (supported_status & DRM_GEM_OBJECT_ACTIVE) + print_size(p, "active", region, stats->active); if (supported_status & DRM_GEM_OBJECT_RESIDENT) print_size(p, "resident", region, stats->resident); @@ -893,15 +905,13 @@ void drm_show_memory_stats(struct drm_printer *p, struct drm_file *file) if (obj->funcs && obj->funcs->status) { s = obj->funcs->status(obj); - supported_status = DRM_GEM_OBJECT_RESIDENT | - DRM_GEM_OBJECT_PURGEABLE; + supported_status |= s; } - if (drm_gem_object_is_shared_for_memory_stats(obj)) { + if (drm_gem_object_is_shared_for_memory_stats(obj)) status.shared += obj->size; - } else { + else status.private += obj->size; - } if (s & DRM_GEM_OBJECT_RESIDENT) { status.resident += add_size; @@ -914,6 +924,7 @@ void drm_show_memory_stats(struct drm_printer *p, struct drm_file *file) if (!dma_resv_test_signaled(obj->resv, dma_resv_usage_rw(true))) { status.active += add_size; + supported_status |= DRM_GEM_OBJECT_ACTIVE; /* If still active, don't count as purgeable: */ s &= ~DRM_GEM_OBJECT_PURGEABLE; diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 513c04f74420..e72f855fc495 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1286,14 +1286,11 @@ EXPORT_SYMBOL(drm_mode_set_name); */ int drm_mode_vrefresh(const struct drm_display_mode *mode) { - unsigned int num, den; + unsigned int num = 1, den = 1; if (mode->htotal == 0 || mode->vtotal == 0) return 0; - num = mode->clock; - den = mode->htotal * mode->vtotal; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) num *= 2; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) @@ -1301,6 +1298,12 @@ int drm_mode_vrefresh(const struct drm_display_mode *mode) if (mode->vscan > 1) den *= mode->vscan; + if (check_mul_overflow(mode->clock, num, &num)) + return 0; + + if (check_mul_overflow(mode->htotal * mode->vtotal, den, &den)) + return 0; + return DIV_ROUND_CLOSEST_ULL(mul_u32_u32(num, 1000), den); } EXPORT_SYMBOL(drm_mode_vrefresh); diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index 2379e501c08b..9940e96d35e3 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -414,7 +414,7 @@ bool drm_is_panel_follower(struct device *dev) * don't bother trying to parse it here. We just need to know if the * property is there. */ - return of_property_read_bool(dev->of_node, "panel"); + return of_property_present(dev->of_node, "panel"); } EXPORT_SYMBOL(drm_is_panel_follower); diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index ef2d490965ba..bcf248f69252 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -931,7 +931,7 @@ impl QrImage<'_> { /// They must remain valid for the duration of the function call. #[no_mangle] pub unsafe extern "C" fn drm_panic_qr_generate( - url: *const i8, + url: *const kernel::ffi::c_char, data: *mut u8, data_len: usize, data_size: usize, diff --git a/drivers/gpu/drm/drm_vblank_work.c b/drivers/gpu/drm/drm_vblank_work.c index 1752ffb44e1d..9cc71120246f 100644 --- a/drivers/gpu/drm/drm_vblank_work.c +++ b/drivers/gpu/drm/drm_vblank_work.c @@ -277,7 +277,7 @@ int drm_vblank_worker_init(struct drm_vblank_crtc *vblank) INIT_LIST_HEAD(&vblank->pending_work); init_waitqueue_head(&vblank->work_wait_queue); - worker = kthread_create_worker(0, "card%d-crtc%d", + worker = kthread_run_worker(0, "card%d-crtc%d", vblank->dev->primary->index, vblank->pipe); if (IS_ERR(worker)) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.c b/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.c index 7aa5f14d0c87..3a221923f15d 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.c @@ -9,7 +9,6 @@ #include "etnaviv_gem.h" #include "etnaviv_gpu.h" #include "etnaviv_mmu.h" -#include "etnaviv_perfmon.h" #define SUBALLOC_SIZE SZ_512K #define SUBALLOC_GRANULE SZ_4K @@ -100,7 +99,7 @@ retry: mutex_unlock(&suballoc->lock); ret = wait_event_interruptible_timeout(suballoc->free_event, suballoc->free_space, - msecs_to_jiffies(10 * 1000)); + secs_to_jiffies(10)); if (!ret) { dev_err(suballoc->dev, "Timeout waiting for cmdbuf space\n"); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 00707001d112..3e91747ed339 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -488,7 +488,16 @@ static const struct drm_ioctl_desc etnaviv_ioctls[] = { ETNA_IOCTL(PM_QUERY_SIG, pm_query_sig, DRM_RENDER_ALLOW), }; -DEFINE_DRM_GEM_FOPS(fops); +static void etnaviv_show_fdinfo(struct drm_printer *p, struct drm_file *file) +{ + drm_show_memory_stats(p, file); +} + +static const struct file_operations fops = { + .owner = THIS_MODULE, + DRM_GEM_FOPS, + .show_fdinfo = drm_show_fdinfo, +}; static const struct drm_driver etnaviv_drm_driver = { .driver_features = DRIVER_GEM | DRIVER_RENDER, @@ -498,6 +507,7 @@ static const struct drm_driver etnaviv_drm_driver = { #ifdef CONFIG_DEBUG_FS .debugfs_init = etnaviv_debugfs_init, #endif + .show_fdinfo = etnaviv_show_fdinfo, .ioctls = etnaviv_ioctls, .num_ioctls = DRM_ETNAVIV_NUM_IOCTLS, .fops = &fops, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 16473c371444..2f844e82bc46 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -342,6 +342,7 @@ void *etnaviv_gem_vmap(struct drm_gem_object *obj) static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj) { struct page **pages; + pgprot_t prot; lockdep_assert_held(&obj->lock); @@ -349,8 +350,19 @@ static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj) if (IS_ERR(pages)) return NULL; - return vmap(pages, obj->base.size >> PAGE_SHIFT, - VM_MAP, pgprot_writecombine(PAGE_KERNEL)); + switch (obj->flags & ETNA_BO_CACHE_MASK) { + case ETNA_BO_CACHED: + prot = PAGE_KERNEL; + break; + case ETNA_BO_UNCACHED: + prot = pgprot_noncached(PAGE_KERNEL); + break; + case ETNA_BO_WC: + default: + prot = pgprot_writecombine(PAGE_KERNEL); + } + + return vmap(pages, obj->base.size >> PAGE_SHIFT, VM_MAP, prot); } static inline enum dma_data_direction etnaviv_op_to_dma_dir(u32 op) @@ -528,6 +540,17 @@ void etnaviv_gem_obj_add(struct drm_device *dev, struct drm_gem_object *obj) mutex_unlock(&priv->gem_lock); } +static enum drm_gem_object_status etnaviv_gem_status(struct drm_gem_object *obj) +{ + struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); + enum drm_gem_object_status status = 0; + + if (etnaviv_obj->pages) + status |= DRM_GEM_OBJECT_RESIDENT; + + return status; +} + static const struct vm_operations_struct vm_ops = { .fault = etnaviv_gem_fault, .open = drm_gem_vm_open, @@ -541,6 +564,7 @@ static const struct drm_gem_object_funcs etnaviv_gem_object_funcs = { .get_sg_table = etnaviv_gem_prime_get_sg_table, .vmap = etnaviv_gem_prime_vmap, .mmap = etnaviv_gem_mmap, + .status = etnaviv_gem_status, .vm_ops = &vm_ops, }; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.h b/drivers/gpu/drm/etnaviv/etnaviv_gem.h index 687555aae807..e5ee82a0674c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.h @@ -44,9 +44,7 @@ struct etnaviv_gem_object { u32 flags; struct list_head gem_node; - struct etnaviv_gpu *gpu; /* non-null if active */ atomic_t gpu_active; - u32 access; struct page **pages; struct sg_table *sgt; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 2d4c112ce033..cf0d9049bcf1 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "etnaviv_cmdbuf.h" @@ -172,6 +173,29 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) return 0; } +static int etnaviv_gpu_reset_deassert(struct etnaviv_gpu *gpu) +{ + int ret; + + /* + * 32 core clock cycles (slowest clock) required before deassertion + * 1 microsecond might match all implementations without computation + */ + usleep_range(1, 2); + + ret = reset_control_deassert(gpu->rst); + if (ret) + return ret; + + /* + * 128 core clock cycles (slowest clock) required before any activity on AHB + * 1 microsecond might match all implementations without computation + */ + usleep_range(1, 2); + + return 0; +} + static inline bool etnaviv_is_model_rev(struct etnaviv_gpu *gpu, u32 model, u32 revision) { return gpu->identity.model == model && @@ -799,6 +823,12 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) goto pm_put; } + ret = etnaviv_gpu_reset_deassert(gpu); + if (ret) { + dev_err(gpu->dev, "GPU reset deassert failed\n"); + goto fail; + } + etnaviv_hw_identify(gpu); if (gpu->identity.model == 0) { @@ -1860,6 +1890,17 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev) if (IS_ERR(gpu->mmio)) return PTR_ERR(gpu->mmio); + + /* Get Reset: */ + gpu->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL); + if (IS_ERR(gpu->rst)) + return dev_err_probe(dev, PTR_ERR(gpu->rst), + "failed to get reset\n"); + + err = reset_control_assert(gpu->rst); + if (err) + return dev_err_probe(dev, err, "failed to assert reset\n"); + /* Get Interrupt: */ gpu->irq = platform_get_irq(pdev, 0); if (gpu->irq < 0) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index 4d8a7d48ade3..5cb46c84e03a 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -93,6 +93,7 @@ struct etnaviv_event { struct etnaviv_cmdbuf_suballoc; struct regulator; struct clk; +struct reset_control; #define ETNA_NR_EVENTS 30 @@ -158,6 +159,7 @@ struct etnaviv_gpu { struct clk *clk_reg; struct clk *clk_core; struct clk *clk_shader; + struct reset_control *rst; unsigned int freq_scale; unsigned int fe_waitcycles; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c index 7e065b3723cf..df5192083b20 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c @@ -19,12 +19,6 @@ static void etnaviv_context_unmap(struct etnaviv_iommu_context *context, size_t unmapped_page, unmapped = 0; size_t pgsize = SZ_4K; - if (!IS_ALIGNED(iova | size, pgsize)) { - pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%zx\n", - iova, size, pgsize); - return; - } - while (unmapped < size) { unmapped_page = context->global->ops->unmap(context, iova, pgsize); @@ -45,12 +39,6 @@ static int etnaviv_context_map(struct etnaviv_iommu_context *context, size_t orig_size = size; int ret = 0; - if (!IS_ALIGNED(iova | paddr | size, pgsize)) { - pr_err("unaligned: iova 0x%lx pa %pa size 0x%zx min_pagesz 0x%zx\n", - iova, &paddr, size, pgsize); - return -EINVAL; - } - while (size) { ret = context->global->ops->map(context, iova, paddr, pgsize, prot); @@ -82,11 +70,19 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, return -EINVAL; for_each_sgtable_dma_sg(sgt, sg, i) { - phys_addr_t pa = sg_dma_address(sg) - sg->offset; - unsigned int da_len = sg_dma_len(sg) + sg->offset; + phys_addr_t pa = sg_dma_address(sg); + unsigned int da_len = sg_dma_len(sg); unsigned int bytes = min_t(unsigned int, da_len, va_len); - VERB("map[%d]: %08x %pap(%x)", i, iova, &pa, bytes); + VERB("map[%d]: %08x %pap(%x)", i, da, &pa, bytes); + + if (!IS_ALIGNED(iova | pa | bytes, SZ_4K)) { + dev_err(context->global->dev, + "unaligned: iova 0x%x pa %pa size 0x%x\n", + iova, &pa, bytes); + ret = -EINVAL; + goto fail; + } ret = etnaviv_context_map(context, da, pa, bytes, prot); if (ret) diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 7a57d4a23e41..176fd8871759 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1660,7 +1660,6 @@ static const struct hdmi_codec_ops audio_codec_ops = { .audio_shutdown = hdmi_audio_shutdown, .mute_stream = hdmi_audio_mute, .get_eld = hdmi_audio_get_eld, - .no_capture_mute = 1, }; static int hdmi_register_audio_device(struct hdmi_context *hdata) @@ -1669,6 +1668,7 @@ static int hdmi_register_audio_device(struct hdmi_context *hdata) .ops = &audio_codec_ops, .max_i2s_channels = 6, .i2s = 1, + .no_capture_mute = 1, }; hdata->audio.pdev = platform_device_register_data( diff --git a/drivers/gpu/drm/hisilicon/hibmc/Makefile b/drivers/gpu/drm/hisilicon/hibmc/Makefile index d25c75e60d3d..95a4ed599d98 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/Makefile +++ b/drivers/gpu/drm/hisilicon/hibmc/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_drm_i2c.o +hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_drm_i2c.o \ + dp/dp_aux.o dp/dp_link.o dp/dp_hw.o hibmc_drm_dp.o obj-$(CONFIG_DRM_HISI_HIBMC) += hibmc-drm.o diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_aux.c b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_aux.c new file mode 100644 index 000000000000..0a903cce1fa9 --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_aux.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Hisilicon Limited. + +#include +#include +#include +#include +#include +#include "dp_comm.h" +#include "dp_reg.h" + +#define HIBMC_AUX_CMD_REQ_LEN GENMASK(7, 4) +#define HIBMC_AUX_CMD_ADDR GENMASK(27, 8) +#define HIBMC_AUX_CMD_I2C_ADDR_ONLY BIT(28) +#define HIBMC_BYTES_IN_U32 4 +#define HIBMC_AUX_I2C_WRITE_SUCCESS 0x1 +#define HIBMC_DP_MIN_PULSE_NUM 0x9 +#define BITS_IN_U8 8 + +static inline void hibmc_dp_aux_reset(struct hibmc_dp_dev *dp) +{ + hibmc_dp_reg_write_field(dp, HIBMC_DP_DPTX_RST_CTRL, HIBMC_DP_CFG_AUX_RST_N, 0x0); + usleep_range(10, 15); + hibmc_dp_reg_write_field(dp, HIBMC_DP_DPTX_RST_CTRL, HIBMC_DP_CFG_AUX_RST_N, 0x1); +} + +static void hibmc_dp_aux_read_data(struct hibmc_dp_dev *dp, u8 *buf, u8 size) +{ + u32 reg_num; + u32 value; + u32 num; + u8 i, j; + + reg_num = DIV_ROUND_UP(size, HIBMC_BYTES_IN_U32); + for (i = 0; i < reg_num; i++) { + /* number of bytes read from a single register */ + num = min(size - i * HIBMC_BYTES_IN_U32, HIBMC_BYTES_IN_U32); + value = readl(dp->base + HIBMC_DP_AUX_RD_DATA0 + i * HIBMC_BYTES_IN_U32); + /* convert the 32-bit value of the register to the buffer. */ + for (j = 0; j < num; j++) + buf[i * HIBMC_BYTES_IN_U32 + j] = value >> (j * BITS_IN_U8); + } +} + +static void hibmc_dp_aux_write_data(struct hibmc_dp_dev *dp, u8 *buf, u8 size) +{ + u32 reg_num; + u32 value; + u32 num; + u8 i, j; + + reg_num = DIV_ROUND_UP(size, HIBMC_BYTES_IN_U32); + for (i = 0; i < reg_num; i++) { + /* number of bytes written to a single register */ + num = min_t(u8, size - i * HIBMC_BYTES_IN_U32, HIBMC_BYTES_IN_U32); + value = 0; + /* obtain the 32-bit value written to a single register. */ + for (j = 0; j < num; j++) + value |= buf[i * HIBMC_BYTES_IN_U32 + j] << (j * BITS_IN_U8); + /* writing data to a single register */ + writel(value, dp->base + HIBMC_DP_AUX_WR_DATA0 + i * HIBMC_BYTES_IN_U32); + } +} + +static u32 hibmc_dp_aux_build_cmd(const struct drm_dp_aux_msg *msg) +{ + u32 aux_cmd = msg->request; + + if (msg->size) + aux_cmd |= FIELD_PREP(HIBMC_AUX_CMD_REQ_LEN, (msg->size - 1)); + else + aux_cmd |= FIELD_PREP(HIBMC_AUX_CMD_I2C_ADDR_ONLY, 1); + + aux_cmd |= FIELD_PREP(HIBMC_AUX_CMD_ADDR, msg->address); + + return aux_cmd; +} + +/* ret >= 0, ret is size; ret < 0, ret is err code */ +static int hibmc_dp_aux_parse_xfer(struct hibmc_dp_dev *dp, struct drm_dp_aux_msg *msg) +{ + u32 buf_data_cnt; + u32 aux_status; + + aux_status = readl(dp->base + HIBMC_DP_AUX_STATUS); + msg->reply = FIELD_GET(HIBMC_DP_CFG_AUX_STATUS, aux_status); + + if (aux_status & HIBMC_DP_CFG_AUX_TIMEOUT) + return -ETIMEDOUT; + + /* only address */ + if (!msg->size) + return 0; + + if (msg->reply != DP_AUX_NATIVE_REPLY_ACK) + return -EIO; + + buf_data_cnt = FIELD_GET(HIBMC_DP_CFG_AUX_READY_DATA_BYTE, aux_status); + + switch (msg->request) { + case DP_AUX_NATIVE_WRITE: + return msg->size; + case DP_AUX_I2C_WRITE | DP_AUX_I2C_MOT: + if (buf_data_cnt == HIBMC_AUX_I2C_WRITE_SUCCESS) + return msg->size; + else + return FIELD_GET(HIBMC_DP_CFG_AUX, aux_status); + case DP_AUX_NATIVE_READ: + case DP_AUX_I2C_READ | DP_AUX_I2C_MOT: + buf_data_cnt--; + if (buf_data_cnt != msg->size) { + /* only the successful part of data is read */ + return -EBUSY; + } + + /* all data is successfully read */ + hibmc_dp_aux_read_data(dp, msg->buffer, msg->size); + return msg->size; + default: + return -EINVAL; + } +} + +/* ret >= 0 ,ret is size; ret < 0, ret is err code */ +static ssize_t hibmc_dp_aux_xfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) +{ + struct hibmc_dp_dev *dp = container_of(aux, struct hibmc_dp_dev, aux); + u32 aux_cmd; + int ret; + u32 val; /* val will be assigned at the beginning of readl_poll_timeout function */ + + writel(0, dp->base + HIBMC_DP_AUX_WR_DATA0); + writel(0, dp->base + HIBMC_DP_AUX_WR_DATA1); + writel(0, dp->base + HIBMC_DP_AUX_WR_DATA2); + writel(0, dp->base + HIBMC_DP_AUX_WR_DATA3); + + hibmc_dp_aux_write_data(dp, msg->buffer, msg->size); + + aux_cmd = hibmc_dp_aux_build_cmd(msg); + writel(aux_cmd, dp->base + HIBMC_DP_AUX_CMD_ADDR); + + /* enable aux transfer */ + hibmc_dp_reg_write_field(dp, HIBMC_DP_AUX_REQ, HIBMC_DP_CFG_AUX_REQ, 0x1); + ret = readl_poll_timeout(dp->base + HIBMC_DP_AUX_REQ, val, + !(val & HIBMC_DP_CFG_AUX_REQ), 50, 5000); + if (ret) { + hibmc_dp_aux_reset(dp); + return ret; + } + + return hibmc_dp_aux_parse_xfer(dp, msg); +} + +void hibmc_dp_aux_init(struct hibmc_dp_dev *dp) +{ + hibmc_dp_reg_write_field(dp, HIBMC_DP_AUX_REQ, HIBMC_DP_CFG_AUX_SYNC_LEN_SEL, 0x0); + hibmc_dp_reg_write_field(dp, HIBMC_DP_AUX_REQ, HIBMC_DP_CFG_AUX_TIMER_TIMEOUT, 0x1); + hibmc_dp_reg_write_field(dp, HIBMC_DP_AUX_REQ, HIBMC_DP_CFG_AUX_MIN_PULSE_NUM, + HIBMC_DP_MIN_PULSE_NUM); + + dp->aux.transfer = hibmc_dp_aux_xfer; + dp->aux.is_remote = 0; + drm_dp_aux_init(&dp->aux); +} diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_comm.h b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_comm.h new file mode 100644 index 000000000000..2c52a4476c4d --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_comm.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (c) 2024 Hisilicon Limited. */ + +#ifndef DP_COMM_H +#define DP_COMM_H + +#include +#include +#include +#include +#include +#include +#include +#include + +#define HIBMC_DP_LANE_NUM_MAX 2 + +struct hibmc_link_status { + bool clock_recovered; + bool channel_equalized; +}; + +struct hibmc_link_cap { + u8 link_rate; + u8 lanes; +}; + +struct hibmc_dp_link { + struct hibmc_link_status status; + u8 train_set[HIBMC_DP_LANE_NUM_MAX]; + struct hibmc_link_cap cap; +}; + +struct hibmc_dp_dev { + struct drm_dp_aux aux; + struct drm_device *dev; + void __iomem *base; + struct mutex lock; /* protects concurrent RW in hibmc_dp_reg_write_field() */ + struct hibmc_dp_link link; + u8 dpcd[DP_RECEIVER_CAP_SIZE]; +}; + +#define dp_field_modify(reg_value, mask, val) \ + do { \ + (reg_value) &= ~(mask); \ + (reg_value) |= FIELD_PREP(mask, val); \ + } while (0) \ + +#define hibmc_dp_reg_write_field(dp, offset, mask, val) \ + do { \ + typeof(dp) _dp = dp; \ + typeof(_dp->base) addr = (_dp->base + (offset)); \ + mutex_lock(&_dp->lock); \ + u32 reg_value = readl(addr); \ + dp_field_modify(reg_value, mask, val); \ + writel(reg_value, addr); \ + mutex_unlock(&_dp->lock); \ + } while (0) + +void hibmc_dp_aux_init(struct hibmc_dp_dev *dp); +int hibmc_dp_link_training(struct hibmc_dp_dev *dp); + +#endif diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_config.h b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_config.h new file mode 100644 index 000000000000..74dd9956144e --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_config.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (c) 2024 Hisilicon Limited. */ + +#ifndef DP_CONFIG_H +#define DP_CONFIG_H + +#define HIBMC_DP_BPP 24 +#define HIBMC_DP_SYMBOL_PER_FCLK 4 +#define HIBMC_DP_MSA1 0x20 +#define HIBMC_DP_MSA2 0x845c00 +#define HIBMC_DP_OFFSET 0x1e0000 +#define HIBMC_DP_HDCP 0x2 +#define HIBMC_DP_INT_RST 0xffff +#define HIBMC_DP_DPTX_RST 0x3ff +#define HIBMC_DP_CLK_EN 0x7 +#define HIBMC_DP_SYNC_EN_MASK 0x3 +#define HIBMC_DP_LINK_RATE_CAL 27 + +#endif diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.c b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.c new file mode 100644 index 000000000000..a8d543881c09 --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Hisilicon Limited. + +#include +#include +#include "dp_config.h" +#include "dp_comm.h" +#include "dp_reg.h" +#include "dp_hw.h" + +static void hibmc_dp_set_tu(struct hibmc_dp_dev *dp, struct drm_display_mode *mode) +{ + u32 tu_symbol_frac_size; + u32 tu_symbol_size; + u32 rate_ks; + u8 lane_num; + u32 value; + u32 bpp; + + lane_num = dp->link.cap.lanes; + if (lane_num == 0) { + drm_err(dp->dev, "set tu failed, lane num cannot be 0!\n"); + return; + } + + bpp = HIBMC_DP_BPP; + rate_ks = dp->link.cap.link_rate * HIBMC_DP_LINK_RATE_CAL; + value = (mode->clock * bpp * 5) / (61 * lane_num * rate_ks); + + if (value % 10 == 9) { /* 9 carry */ + tu_symbol_size = value / 10 + 1; + tu_symbol_frac_size = 0; + } else { + tu_symbol_size = value / 10; + tu_symbol_frac_size = value % 10 + 1; + } + + drm_dbg_dp(dp->dev, "tu value: %u.%u value: %u\n", + tu_symbol_size, tu_symbol_frac_size, value); + + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_PACKET, + HIBMC_DP_CFG_STREAM_TU_SYMBOL_SIZE, tu_symbol_size); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_PACKET, + HIBMC_DP_CFG_STREAM_TU_SYMBOL_FRAC_SIZE, tu_symbol_frac_size); +} + +static void hibmc_dp_set_sst(struct hibmc_dp_dev *dp, struct drm_display_mode *mode) +{ + u32 hblank_size; + u32 htotal_size; + u32 htotal_int; + u32 hblank_int; + u32 fclk; /* flink_clock */ + + fclk = dp->link.cap.link_rate * HIBMC_DP_LINK_RATE_CAL; + + /* Considering the effect of spread spectrum, the value may be deviated. + * The coefficient (0.9947) is used to offset the deviation. + */ + htotal_int = mode->htotal * 9947 / 10000; + htotal_size = htotal_int * fclk / (HIBMC_DP_SYMBOL_PER_FCLK * (mode->clock / 1000)); + + hblank_int = mode->htotal - mode->hdisplay - mode->hdisplay * 53 / 10000; + hblank_size = hblank_int * fclk * 9947 / + (mode->clock * 10 * HIBMC_DP_SYMBOL_PER_FCLK); + + drm_dbg_dp(dp->dev, "h_active %u v_active %u htotal_size %u hblank_size %u", + mode->hdisplay, mode->vdisplay, htotal_size, hblank_size); + drm_dbg_dp(dp->dev, "flink_clock %u pixel_clock %d", fclk, mode->clock / 1000); + + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_HORIZONTAL_SIZE, + HIBMC_DP_CFG_STREAM_HTOTAL_SIZE, htotal_size); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_HORIZONTAL_SIZE, + HIBMC_DP_CFG_STREAM_HBLANK_SIZE, hblank_size); +} + +static void hibmc_dp_link_cfg(struct hibmc_dp_dev *dp, struct drm_display_mode *mode) +{ + u32 timing_delay; + u32 vblank; + u32 hstart; + u32 vstart; + + vblank = mode->vtotal - mode->vdisplay; + timing_delay = mode->htotal - mode->hsync_start; + hstart = mode->htotal - mode->hsync_start; + vstart = mode->vtotal - mode->vsync_start; + + hibmc_dp_reg_write_field(dp, HIBMC_DP_TIMING_GEN_CONFIG0, + HIBMC_DP_CFG_TIMING_GEN0_HBLANK, mode->htotal - mode->hdisplay); + hibmc_dp_reg_write_field(dp, HIBMC_DP_TIMING_GEN_CONFIG0, + HIBMC_DP_CFG_TIMING_GEN0_HACTIVE, mode->hdisplay); + + hibmc_dp_reg_write_field(dp, HIBMC_DP_TIMING_GEN_CONFIG2, + HIBMC_DP_CFG_TIMING_GEN0_VBLANK, vblank); + hibmc_dp_reg_write_field(dp, HIBMC_DP_TIMING_GEN_CONFIG2, + HIBMC_DP_CFG_TIMING_GEN0_VACTIVE, mode->vdisplay); + hibmc_dp_reg_write_field(dp, HIBMC_DP_TIMING_GEN_CONFIG3, + HIBMC_DP_CFG_TIMING_GEN0_VFRONT_PORCH, + mode->vsync_start - mode->vdisplay); + + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CONFIG0, + HIBMC_DP_CFG_STREAM_HACTIVE, mode->hdisplay); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CONFIG0, + HIBMC_DP_CFG_STREAM_HBLANK, mode->htotal - mode->hdisplay); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CONFIG2, + HIBMC_DP_CFG_STREAM_HSYNC_WIDTH, + mode->hsync_end - mode->hsync_start); + + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CONFIG1, + HIBMC_DP_CFG_STREAM_VACTIVE, mode->vdisplay); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CONFIG1, + HIBMC_DP_CFG_STREAM_VBLANK, vblank); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CONFIG3, + HIBMC_DP_CFG_STREAM_VFRONT_PORCH, + mode->vsync_start - mode->vdisplay); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CONFIG3, + HIBMC_DP_CFG_STREAM_VSYNC_WIDTH, + mode->vsync_end - mode->vsync_start); + + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_MSA0, + HIBMC_DP_CFG_STREAM_VSTART, vstart); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_MSA0, + HIBMC_DP_CFG_STREAM_HSTART, hstart); + + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CTRL, HIBMC_DP_CFG_STREAM_VSYNC_POLARITY, + mode->flags & DRM_MODE_FLAG_PVSYNC ? 1 : 0); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CTRL, HIBMC_DP_CFG_STREAM_HSYNC_POLARITY, + mode->flags & DRM_MODE_FLAG_PHSYNC ? 1 : 0); + + /* MSA mic 0 and 1 */ + writel(HIBMC_DP_MSA1, dp->base + HIBMC_DP_VIDEO_MSA1); + writel(HIBMC_DP_MSA2, dp->base + HIBMC_DP_VIDEO_MSA2); + + hibmc_dp_set_tu(dp, mode); + + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CTRL, HIBMC_DP_CFG_STREAM_RGB_ENABLE, 0x1); + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CTRL, HIBMC_DP_CFG_STREAM_VIDEO_MAPPING, 0); + + /* divide 2: up even */ + if (timing_delay % 2) + timing_delay++; + + hibmc_dp_reg_write_field(dp, HIBMC_DP_TIMING_MODEL_CTRL, + HIBMC_DP_CFG_PIXEL_NUM_TIMING_MODE_SEL1, timing_delay); + + hibmc_dp_set_sst(dp, mode); +} + +int hibmc_dp_hw_init(struct hibmc_dp *dp) +{ + struct drm_device *drm_dev = dp->drm_dev; + struct hibmc_dp_dev *dp_dev; + + dp_dev = devm_kzalloc(drm_dev->dev, sizeof(struct hibmc_dp_dev), GFP_KERNEL); + if (!dp_dev) + return -ENOMEM; + + mutex_init(&dp_dev->lock); + + dp->dp_dev = dp_dev; + + dp_dev->dev = drm_dev; + dp_dev->base = dp->mmio + HIBMC_DP_OFFSET; + + hibmc_dp_aux_init(dp_dev); + + dp_dev->link.cap.lanes = 0x2; + dp_dev->link.cap.link_rate = DP_LINK_BW_2_7; + + /* hdcp data */ + writel(HIBMC_DP_HDCP, dp_dev->base + HIBMC_DP_HDCP_CFG); + /* int init */ + writel(0, dp_dev->base + HIBMC_DP_INTR_ENABLE); + writel(HIBMC_DP_INT_RST, dp_dev->base + HIBMC_DP_INTR_ORIGINAL_STATUS); + /* rst */ + writel(HIBMC_DP_DPTX_RST, dp_dev->base + HIBMC_DP_DPTX_RST_CTRL); + /* clock enable */ + writel(HIBMC_DP_CLK_EN, dp_dev->base + HIBMC_DP_DPTX_CLK_CTRL); + + return 0; +} + +void hibmc_dp_display_en(struct hibmc_dp *dp, bool enable) +{ + struct hibmc_dp_dev *dp_dev = dp->dp_dev; + + if (enable) { + hibmc_dp_reg_write_field(dp_dev, HIBMC_DP_VIDEO_CTRL, BIT(0), 0x1); + writel(HIBMC_DP_SYNC_EN_MASK, dp_dev->base + HIBMC_DP_TIMING_SYNC_CTRL); + hibmc_dp_reg_write_field(dp_dev, HIBMC_DP_DPTX_GCTL0, BIT(10), 0x1); + writel(HIBMC_DP_SYNC_EN_MASK, dp_dev->base + HIBMC_DP_TIMING_SYNC_CTRL); + } else { + hibmc_dp_reg_write_field(dp_dev, HIBMC_DP_DPTX_GCTL0, BIT(10), 0); + writel(HIBMC_DP_SYNC_EN_MASK, dp_dev->base + HIBMC_DP_TIMING_SYNC_CTRL); + hibmc_dp_reg_write_field(dp_dev, HIBMC_DP_VIDEO_CTRL, BIT(0), 0); + writel(HIBMC_DP_SYNC_EN_MASK, dp_dev->base + HIBMC_DP_TIMING_SYNC_CTRL); + } + + msleep(50); +} + +int hibmc_dp_mode_set(struct hibmc_dp *dp, struct drm_display_mode *mode) +{ + struct hibmc_dp_dev *dp_dev = dp->dp_dev; + int ret; + + if (!dp_dev->link.status.channel_equalized) { + ret = hibmc_dp_link_training(dp_dev); + if (ret) { + drm_err(dp->drm_dev, "dp link training failed, ret: %d\n", ret); + return ret; + } + } + + hibmc_dp_display_en(dp, false); + hibmc_dp_link_cfg(dp_dev, mode); + + return 0; +} diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.h b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.h new file mode 100644 index 000000000000..4dc13b3d9875 --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (c) 2024 Hisilicon Limited. */ + +#ifndef DP_KAPI_H +#define DP_KAPI_H + +#include +#include +#include +#include +#include +#include + +struct hibmc_dp_dev; + +struct hibmc_dp { + struct hibmc_dp_dev *dp_dev; + struct drm_device *drm_dev; + struct drm_encoder encoder; + struct drm_connector connector; + void __iomem *mmio; +}; + +int hibmc_dp_hw_init(struct hibmc_dp *dp); +int hibmc_dp_mode_set(struct hibmc_dp *dp, struct drm_display_mode *mode); +void hibmc_dp_display_en(struct hibmc_dp *dp, bool enable); + +#endif diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c new file mode 100644 index 000000000000..f6355c16cc0a --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Hisilicon Limited. + +#include +#include +#include +#include "dp_comm.h" +#include "dp_reg.h" + +#define HIBMC_EQ_MAX_RETRY 5 + +static int hibmc_dp_link_training_configure(struct hibmc_dp_dev *dp) +{ + u8 buf[2]; + int ret; + + /* DP 2 lane */ + hibmc_dp_reg_write_field(dp, HIBMC_DP_PHYIF_CTRL0, HIBMC_DP_CFG_LANE_DATA_EN, + dp->link.cap.lanes == 0x2 ? 0x3 : 0x1); + hibmc_dp_reg_write_field(dp, HIBMC_DP_DPTX_GCTL0, HIBMC_DP_CFG_PHY_LANE_NUM, + dp->link.cap.lanes == 0x2 ? 0x1 : 0); + + /* enhanced frame */ + hibmc_dp_reg_write_field(dp, HIBMC_DP_VIDEO_CTRL, HIBMC_DP_CFG_STREAM_FRAME_MODE, 0x1); + + /* set rate and lane count */ + buf[0] = dp->link.cap.link_rate; + buf[1] = DP_LANE_COUNT_ENHANCED_FRAME_EN | dp->link.cap.lanes; + ret = drm_dp_dpcd_write(&dp->aux, DP_LINK_BW_SET, buf, sizeof(buf)); + if (ret != sizeof(buf)) { + drm_dbg_dp(dp->dev, "dp aux write link rate and lanes failed, ret: %d\n", ret); + return ret >= 0 ? -EIO : ret; + } + + /* set 8b/10b and downspread */ + buf[0] = DP_SPREAD_AMP_0_5; + buf[1] = DP_SET_ANSI_8B10B; + ret = drm_dp_dpcd_write(&dp->aux, DP_DOWNSPREAD_CTRL, buf, sizeof(buf)); + if (ret != sizeof(buf)) { + drm_dbg_dp(dp->dev, "dp aux write 8b/10b and downspread failed, ret: %d\n", ret); + return ret >= 0 ? -EIO : ret; + } + + ret = drm_dp_read_dpcd_caps(&dp->aux, dp->dpcd); + if (ret) + drm_err(dp->dev, "dp aux read dpcd failed, ret: %d\n", ret); + + return ret; +} + +static int hibmc_dp_link_set_pattern(struct hibmc_dp_dev *dp, int pattern) +{ + int ret; + u8 val; + u8 buf; + + buf = (u8)pattern; + if (pattern != DP_TRAINING_PATTERN_DISABLE && pattern != DP_TRAINING_PATTERN_4) { + buf |= DP_LINK_SCRAMBLING_DISABLE; + hibmc_dp_reg_write_field(dp, HIBMC_DP_PHYIF_CTRL0, HIBMC_DP_CFG_SCRAMBLE_EN, 0x1); + } else { + hibmc_dp_reg_write_field(dp, HIBMC_DP_PHYIF_CTRL0, HIBMC_DP_CFG_SCRAMBLE_EN, 0); + } + + switch (pattern) { + case DP_TRAINING_PATTERN_DISABLE: + val = 0; + break; + case DP_TRAINING_PATTERN_1: + val = 1; + break; + case DP_TRAINING_PATTERN_2: + val = 2; + break; + case DP_TRAINING_PATTERN_3: + val = 3; + break; + case DP_TRAINING_PATTERN_4: + val = 4; + break; + default: + return -EINVAL; + } + + hibmc_dp_reg_write_field(dp, HIBMC_DP_PHYIF_CTRL0, HIBMC_DP_CFG_PAT_SEL, val); + + ret = drm_dp_dpcd_write(&dp->aux, DP_TRAINING_PATTERN_SET, &buf, sizeof(buf)); + if (ret != sizeof(buf)) { + drm_dbg_dp(dp->dev, "dp aux write training pattern set failed\n"); + return ret >= 0 ? -EIO : ret; + } + + return 0; +} + +static int hibmc_dp_link_training_cr_pre(struct hibmc_dp_dev *dp) +{ + u8 *train_set = dp->link.train_set; + int ret; + u8 i; + + ret = hibmc_dp_link_training_configure(dp); + if (ret) + return ret; + + ret = hibmc_dp_link_set_pattern(dp, DP_TRAINING_PATTERN_1); + if (ret) + return ret; + + for (i = 0; i < dp->link.cap.lanes; i++) + train_set[i] = DP_TRAIN_VOLTAGE_SWING_LEVEL_2; + + ret = drm_dp_dpcd_write(&dp->aux, DP_TRAINING_LANE0_SET, train_set, dp->link.cap.lanes); + if (ret != dp->link.cap.lanes) { + drm_dbg_dp(dp->dev, "dp aux write training lane set failed\n"); + return ret >= 0 ? -EIO : ret; + } + + return 0; +} + +static bool hibmc_dp_link_get_adjust_train(struct hibmc_dp_dev *dp, + u8 lane_status[DP_LINK_STATUS_SIZE]) +{ + u8 train_set[HIBMC_DP_LANE_NUM_MAX] = {0}; + u8 lane; + + for (lane = 0; lane < dp->link.cap.lanes; lane++) + train_set[lane] = drm_dp_get_adjust_request_voltage(lane_status, lane) | + drm_dp_get_adjust_request_pre_emphasis(lane_status, lane); + + if (memcmp(dp->link.train_set, train_set, HIBMC_DP_LANE_NUM_MAX)) { + memcpy(dp->link.train_set, train_set, HIBMC_DP_LANE_NUM_MAX); + return true; + } + + return false; +} + +static inline int hibmc_dp_link_reduce_rate(struct hibmc_dp_dev *dp) +{ + switch (dp->link.cap.link_rate) { + case DP_LINK_BW_2_7: + dp->link.cap.link_rate = DP_LINK_BW_1_62; + return 0; + case DP_LINK_BW_5_4: + dp->link.cap.link_rate = DP_LINK_BW_2_7; + return 0; + case DP_LINK_BW_8_1: + dp->link.cap.link_rate = DP_LINK_BW_5_4; + return 0; + default: + return -EINVAL; + } +} + +static inline int hibmc_dp_link_reduce_lane(struct hibmc_dp_dev *dp) +{ + switch (dp->link.cap.lanes) { + case 0x2: + dp->link.cap.lanes--; + break; + case 0x1: + drm_err(dp->dev, "dp link training reduce lane failed, already reach minimum\n"); + return -EIO; + default: + return -EINVAL; + } + + return 0; +} + +static int hibmc_dp_link_training_cr(struct hibmc_dp_dev *dp) +{ + u8 lane_status[DP_LINK_STATUS_SIZE] = {0}; + bool level_changed; + u32 voltage_tries; + u32 cr_tries; + int ret; + + /* + * DP 1.4 spec define 10 for maxtries value, for pre DP 1.4 version set a limit of 80 + * (4 voltage levels x 4 preemphasis levels x 5 identical voltage retries) + */ + + voltage_tries = 1; + for (cr_tries = 0; cr_tries < 80; cr_tries++) { + drm_dp_link_train_clock_recovery_delay(&dp->aux, dp->dpcd); + + ret = drm_dp_dpcd_read_link_status(&dp->aux, lane_status); + if (ret != DP_LINK_STATUS_SIZE) { + drm_err(dp->dev, "Get lane status failed\n"); + return ret; + } + + if (drm_dp_clock_recovery_ok(lane_status, dp->link.cap.lanes)) { + drm_dbg_dp(dp->dev, "dp link training cr done\n"); + dp->link.status.clock_recovered = true; + return 0; + } + + if (voltage_tries == 5) { + drm_dbg_dp(dp->dev, "same voltage tries 5 times\n"); + dp->link.status.clock_recovered = false; + return 0; + } + + level_changed = hibmc_dp_link_get_adjust_train(dp, lane_status); + ret = drm_dp_dpcd_write(&dp->aux, DP_TRAINING_LANE0_SET, dp->link.train_set, + dp->link.cap.lanes); + if (ret != dp->link.cap.lanes) { + drm_dbg_dp(dp->dev, "Update link training failed\n"); + return ret >= 0 ? -EIO : ret; + } + + voltage_tries = level_changed ? 1 : voltage_tries + 1; + } + + drm_err(dp->dev, "dp link training clock recovery 80 times failed\n"); + dp->link.status.clock_recovered = false; + + return 0; +} + +static int hibmc_dp_link_training_channel_eq(struct hibmc_dp_dev *dp) +{ + u8 lane_status[DP_LINK_STATUS_SIZE] = {0}; + u8 eq_tries; + int ret; + + ret = hibmc_dp_link_set_pattern(dp, DP_TRAINING_PATTERN_2); + if (ret) + return ret; + + for (eq_tries = 0; eq_tries < HIBMC_EQ_MAX_RETRY; eq_tries++) { + drm_dp_link_train_channel_eq_delay(&dp->aux, dp->dpcd); + + ret = drm_dp_dpcd_read_link_status(&dp->aux, lane_status); + if (ret != DP_LINK_STATUS_SIZE) { + drm_err(dp->dev, "get lane status failed\n"); + break; + } + + if (!drm_dp_clock_recovery_ok(lane_status, dp->link.cap.lanes)) { + drm_dbg_dp(dp->dev, "clock recovery check failed\n"); + drm_dbg_dp(dp->dev, "cannot continue channel equalization\n"); + dp->link.status.clock_recovered = false; + break; + } + + if (drm_dp_channel_eq_ok(lane_status, dp->link.cap.lanes)) { + dp->link.status.channel_equalized = true; + drm_dbg_dp(dp->dev, "dp link training eq done\n"); + break; + } + + hibmc_dp_link_get_adjust_train(dp, lane_status); + ret = drm_dp_dpcd_write(&dp->aux, DP_TRAINING_LANE0_SET, + dp->link.train_set, dp->link.cap.lanes); + if (ret != dp->link.cap.lanes) { + drm_dbg_dp(dp->dev, "Update link training failed\n"); + ret = (ret >= 0) ? -EIO : ret; + break; + } + } + + if (eq_tries == HIBMC_EQ_MAX_RETRY) + drm_err(dp->dev, "channel equalization failed %u times\n", eq_tries); + + hibmc_dp_link_set_pattern(dp, DP_TRAINING_PATTERN_DISABLE); + + return ret < 0 ? ret : 0; +} + +static int hibmc_dp_link_downgrade_training_cr(struct hibmc_dp_dev *dp) +{ + if (hibmc_dp_link_reduce_rate(dp)) + return hibmc_dp_link_reduce_lane(dp); + + return 0; +} + +static int hibmc_dp_link_downgrade_training_eq(struct hibmc_dp_dev *dp) +{ + if ((dp->link.status.clock_recovered && !dp->link.status.channel_equalized)) { + if (!hibmc_dp_link_reduce_lane(dp)) + return 0; + } + + return hibmc_dp_link_reduce_rate(dp); +} + +int hibmc_dp_link_training(struct hibmc_dp_dev *dp) +{ + struct hibmc_dp_link *link = &dp->link; + int ret; + + while (true) { + ret = hibmc_dp_link_training_cr_pre(dp); + if (ret) + goto err; + + ret = hibmc_dp_link_training_cr(dp); + if (ret) + goto err; + + if (!link->status.clock_recovered) { + ret = hibmc_dp_link_downgrade_training_cr(dp); + if (ret) + goto err; + continue; + } + + ret = hibmc_dp_link_training_channel_eq(dp); + if (ret) + goto err; + + if (!link->status.channel_equalized) { + ret = hibmc_dp_link_downgrade_training_eq(dp); + if (ret) + goto err; + continue; + } + + return 0; + } + +err: + hibmc_dp_link_set_pattern(dp, DP_TRAINING_PATTERN_DISABLE); + + return ret; +} diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_reg.h b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_reg.h new file mode 100644 index 000000000000..4a515c726d52 --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_reg.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (c) 2024 Hisilicon Limited. */ + +#ifndef DP_REG_H +#define DP_REG_H + +#define HIBMC_DP_AUX_CMD_ADDR 0x50 +#define HIBMC_DP_AUX_WR_DATA0 0x54 +#define HIBMC_DP_AUX_WR_DATA1 0x58 +#define HIBMC_DP_AUX_WR_DATA2 0x5c +#define HIBMC_DP_AUX_WR_DATA3 0x60 +#define HIBMC_DP_AUX_RD_DATA0 0x64 +#define HIBMC_DP_AUX_REQ 0x74 +#define HIBMC_DP_AUX_STATUS 0x78 +#define HIBMC_DP_PHYIF_CTRL0 0xa0 +#define HIBMC_DP_VIDEO_CTRL 0x100 +#define HIBMC_DP_VIDEO_CONFIG0 0x104 +#define HIBMC_DP_VIDEO_CONFIG1 0x108 +#define HIBMC_DP_VIDEO_CONFIG2 0x10c +#define HIBMC_DP_VIDEO_CONFIG3 0x110 +#define HIBMC_DP_VIDEO_PACKET 0x114 +#define HIBMC_DP_VIDEO_MSA0 0x118 +#define HIBMC_DP_VIDEO_MSA1 0x11c +#define HIBMC_DP_VIDEO_MSA2 0x120 +#define HIBMC_DP_VIDEO_HORIZONTAL_SIZE 0X124 +#define HIBMC_DP_TIMING_GEN_CONFIG0 0x26c +#define HIBMC_DP_TIMING_GEN_CONFIG2 0x274 +#define HIBMC_DP_TIMING_GEN_CONFIG3 0x278 +#define HIBMC_DP_HDCP_CFG 0x600 +#define HIBMC_DP_DPTX_RST_CTRL 0x700 +#define HIBMC_DP_DPTX_CLK_CTRL 0x704 +#define HIBMC_DP_DPTX_GCTL0 0x708 +#define HIBMC_DP_INTR_ENABLE 0x720 +#define HIBMC_DP_INTR_ORIGINAL_STATUS 0x728 +#define HIBMC_DP_TIMING_MODEL_CTRL 0x884 +#define HIBMC_DP_TIMING_SYNC_CTRL 0xFF0 + +#define HIBMC_DP_CFG_AUX_SYNC_LEN_SEL BIT(1) +#define HIBMC_DP_CFG_AUX_TIMER_TIMEOUT BIT(2) +#define HIBMC_DP_CFG_STREAM_FRAME_MODE BIT(6) +#define HIBMC_DP_CFG_AUX_MIN_PULSE_NUM GENMASK(13, 9) +#define HIBMC_DP_CFG_LANE_DATA_EN GENMASK(11, 8) +#define HIBMC_DP_CFG_PHY_LANE_NUM GENMASK(2, 1) +#define HIBMC_DP_CFG_AUX_REQ BIT(0) +#define HIBMC_DP_CFG_AUX_RST_N BIT(4) +#define HIBMC_DP_CFG_AUX_TIMEOUT BIT(0) +#define HIBMC_DP_CFG_AUX_READY_DATA_BYTE GENMASK(16, 12) +#define HIBMC_DP_CFG_AUX GENMASK(24, 17) +#define HIBMC_DP_CFG_AUX_STATUS GENMASK(11, 4) +#define HIBMC_DP_CFG_SCRAMBLE_EN BIT(0) +#define HIBMC_DP_CFG_PAT_SEL GENMASK(7, 4) +#define HIBMC_DP_CFG_TIMING_GEN0_HACTIVE GENMASK(31, 16) +#define HIBMC_DP_CFG_TIMING_GEN0_HBLANK GENMASK(15, 0) +#define HIBMC_DP_CFG_TIMING_GEN0_VACTIVE GENMASK(31, 16) +#define HIBMC_DP_CFG_TIMING_GEN0_VBLANK GENMASK(15, 0) +#define HIBMC_DP_CFG_TIMING_GEN0_VFRONT_PORCH GENMASK(31, 16) +#define HIBMC_DP_CFG_STREAM_HACTIVE GENMASK(31, 16) +#define HIBMC_DP_CFG_STREAM_HBLANK GENMASK(15, 0) +#define HIBMC_DP_CFG_STREAM_HSYNC_WIDTH GENMASK(15, 0) +#define HIBMC_DP_CFG_STREAM_VACTIVE GENMASK(31, 16) +#define HIBMC_DP_CFG_STREAM_VBLANK GENMASK(15, 0) +#define HIBMC_DP_CFG_STREAM_VFRONT_PORCH GENMASK(31, 16) +#define HIBMC_DP_CFG_STREAM_VSYNC_WIDTH GENMASK(15, 0) +#define HIBMC_DP_CFG_STREAM_VSTART GENMASK(31, 16) +#define HIBMC_DP_CFG_STREAM_HSTART GENMASK(15, 0) +#define HIBMC_DP_CFG_STREAM_VSYNC_POLARITY BIT(8) +#define HIBMC_DP_CFG_STREAM_HSYNC_POLARITY BIT(7) +#define HIBMC_DP_CFG_STREAM_RGB_ENABLE BIT(1) +#define HIBMC_DP_CFG_STREAM_VIDEO_MAPPING GENMASK(5, 2) +#define HIBMC_DP_CFG_PIXEL_NUM_TIMING_MODE_SEL1 GENMASK(31, 16) +#define HIBMC_DP_CFG_STREAM_TU_SYMBOL_SIZE GENMASK(5, 0) +#define HIBMC_DP_CFG_STREAM_TU_SYMBOL_FRAC_SIZE GENMASK(9, 6) +#define HIBMC_DP_CFG_STREAM_HTOTAL_SIZE GENMASK(31, 16) +#define HIBMC_DP_CFG_STREAM_HBLANK_SIZE GENMASK(15, 0) + +#endif diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_dp.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_dp.c new file mode 100644 index 000000000000..603d6b198a54 --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_dp.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Hisilicon Limited. + +#include + +#include +#include +#include +#include +#include +#include + +#include "hibmc_drm_drv.h" +#include "dp/dp_hw.h" + +static int hibmc_dp_connector_get_modes(struct drm_connector *connector) +{ + int count; + + count = drm_add_modes_noedid(connector, connector->dev->mode_config.max_width, + connector->dev->mode_config.max_height); + drm_set_preferred_mode(connector, 1024, 768); // temporary implementation + + return count; +} + +static const struct drm_connector_helper_funcs hibmc_dp_conn_helper_funcs = { + .get_modes = hibmc_dp_connector_get_modes, +}; + +static const struct drm_connector_funcs hibmc_dp_conn_funcs = { + .reset = drm_atomic_helper_connector_reset, + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = drm_connector_cleanup, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +static inline int hibmc_dp_prepare(struct hibmc_dp *dp, struct drm_display_mode *mode) +{ + int ret; + + hibmc_dp_display_en(dp, false); + + ret = hibmc_dp_mode_set(dp, mode); + if (ret) + drm_err(dp->drm_dev, "hibmc dp mode set failed: %d\n", ret); + + return ret; +} + +static void hibmc_dp_encoder_enable(struct drm_encoder *drm_encoder, + struct drm_atomic_state *state) +{ + struct hibmc_dp *dp = container_of(drm_encoder, struct hibmc_dp, encoder); + struct drm_display_mode *mode = &drm_encoder->crtc->state->mode; + + if (hibmc_dp_prepare(dp, mode)) + return; + + hibmc_dp_display_en(dp, true); +} + +static void hibmc_dp_encoder_disable(struct drm_encoder *drm_encoder, + struct drm_atomic_state *state) +{ + struct hibmc_dp *dp = container_of(drm_encoder, struct hibmc_dp, encoder); + + hibmc_dp_display_en(dp, false); +} + +static const struct drm_encoder_helper_funcs hibmc_dp_encoder_helper_funcs = { + .atomic_enable = hibmc_dp_encoder_enable, + .atomic_disable = hibmc_dp_encoder_disable, +}; + +int hibmc_dp_init(struct hibmc_drm_private *priv) +{ + struct drm_device *dev = &priv->dev; + struct drm_crtc *crtc = &priv->crtc; + struct hibmc_dp *dp = &priv->dp; + struct drm_connector *connector = &dp->connector; + struct drm_encoder *encoder = &dp->encoder; + int ret; + + dp->mmio = priv->mmio; + dp->drm_dev = dev; + + ret = hibmc_dp_hw_init(&priv->dp); + if (ret) { + drm_err(dev, "hibmc dp hw init failed: %d\n", ret); + return ret; + } + + hibmc_dp_display_en(&priv->dp, false); + + encoder->possible_crtcs = drm_crtc_mask(crtc); + ret = drmm_encoder_init(dev, encoder, NULL, DRM_MODE_ENCODER_TMDS, NULL); + if (ret) { + drm_err(dev, "init dp encoder failed: %d\n", ret); + return ret; + } + + drm_encoder_helper_add(encoder, &hibmc_dp_encoder_helper_funcs); + + ret = drm_connector_init(dev, connector, &hibmc_dp_conn_funcs, + DRM_MODE_CONNECTOR_DisplayPort); + if (ret) { + drm_err(dev, "init dp connector failed: %d\n", ret); + return ret; + } + + drm_connector_helper_add(connector, &hibmc_dp_conn_helper_funcs); + + drm_connector_attach_encoder(connector, encoder); + + return 0; +} diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c index 7f814c32ed34..e6de6d5edf6b 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c @@ -28,6 +28,10 @@ #include "hibmc_drm_drv.h" #include "hibmc_drm_regs.h" +#define HIBMC_DP_HOST_SERDES_CTRL 0x1f001c +#define HIBMC_DP_HOST_SERDES_CTRL_VAL 0x8a00 +#define HIBMC_DP_HOST_SERDES_CTRL_MASK 0x7ffff + DEFINE_DRM_GEM_FOPS(hibmc_fops); static irqreturn_t hibmc_interrupt(int irq, void *arg) @@ -117,6 +121,14 @@ static int hibmc_kms_init(struct hibmc_drm_private *priv) return ret; } + /* if DP existed, init DP */ + if ((readl(priv->mmio + HIBMC_DP_HOST_SERDES_CTRL) & + HIBMC_DP_HOST_SERDES_CTRL_MASK) == HIBMC_DP_HOST_SERDES_CTRL_VAL) { + ret = hibmc_dp_init(priv); + if (ret) + drm_err(dev, "failed to init dp: %d\n", ret); + } + ret = hibmc_vdac_init(priv); if (ret) { drm_err(dev, "failed to init vdac: %d\n", ret); @@ -327,6 +339,8 @@ static int hibmc_pci_probe(struct pci_dev *pdev, goto err_return; } + pci_set_master(pdev); + ret = hibmc_load(dev); if (ret) { drm_err(dev, "failed to load hibmc: %d\n", ret); diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h index 6b566f3aeecb..d982f1e4b958 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h @@ -20,9 +20,12 @@ #include -struct hibmc_connector { - struct drm_connector base; +#include "dp/dp_hw.h" +struct hibmc_vdac { + struct drm_device *dev; + struct drm_encoder encoder; + struct drm_connector connector; struct i2c_adapter adapter; struct i2c_algo_bit_data bit_data; }; @@ -35,13 +38,13 @@ struct hibmc_drm_private { struct drm_device dev; struct drm_plane primary_plane; struct drm_crtc crtc; - struct drm_encoder encoder; - struct hibmc_connector connector; + struct hibmc_vdac vdac; + struct hibmc_dp dp; }; -static inline struct hibmc_connector *to_hibmc_connector(struct drm_connector *connector) +static inline struct hibmc_vdac *to_hibmc_vdac(struct drm_connector *connector) { - return container_of(connector, struct hibmc_connector, base); + return container_of(connector, struct hibmc_vdac, connector); } static inline struct hibmc_drm_private *to_hibmc_drm_private(struct drm_device *dev) @@ -57,6 +60,8 @@ void hibmc_set_current_gate(struct hibmc_drm_private *priv, int hibmc_de_init(struct hibmc_drm_private *priv); int hibmc_vdac_init(struct hibmc_drm_private *priv); -int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_connector *connector); +int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *connector); + +int hibmc_dp_init(struct hibmc_drm_private *priv); #endif diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c index e6e48651c15c..99b3b77b5445 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c @@ -25,8 +25,8 @@ static void hibmc_set_i2c_signal(void *data, u32 mask, int value) { - struct hibmc_connector *hibmc_connector = data; - struct hibmc_drm_private *priv = to_hibmc_drm_private(hibmc_connector->base.dev); + struct hibmc_vdac *vdac = data; + struct hibmc_drm_private *priv = to_hibmc_drm_private(vdac->connector.dev); u32 tmp_dir = readl(priv->mmio + GPIO_DATA_DIRECTION); if (value) { @@ -45,8 +45,8 @@ static void hibmc_set_i2c_signal(void *data, u32 mask, int value) static int hibmc_get_i2c_signal(void *data, u32 mask) { - struct hibmc_connector *hibmc_connector = data; - struct hibmc_drm_private *priv = to_hibmc_drm_private(hibmc_connector->base.dev); + struct hibmc_vdac *vdac = data; + struct hibmc_drm_private *priv = to_hibmc_drm_private(vdac->connector.dev); u32 tmp_dir = readl(priv->mmio + GPIO_DATA_DIRECTION); if ((tmp_dir & mask) != mask) { @@ -77,22 +77,21 @@ static int hibmc_ddc_getscl(void *data) return hibmc_get_i2c_signal(data, I2C_SCL_MASK); } -int hibmc_ddc_create(struct drm_device *drm_dev, - struct hibmc_connector *connector) +int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *vdac) { - connector->adapter.owner = THIS_MODULE; - snprintf(connector->adapter.name, I2C_NAME_SIZE, "HIS i2c bit bus"); - connector->adapter.dev.parent = drm_dev->dev; - i2c_set_adapdata(&connector->adapter, connector); - connector->adapter.algo_data = &connector->bit_data; + vdac->adapter.owner = THIS_MODULE; + snprintf(vdac->adapter.name, I2C_NAME_SIZE, "HIS i2c bit bus"); + vdac->adapter.dev.parent = drm_dev->dev; + i2c_set_adapdata(&vdac->adapter, vdac); + vdac->adapter.algo_data = &vdac->bit_data; - connector->bit_data.udelay = 20; - connector->bit_data.timeout = usecs_to_jiffies(2000); - connector->bit_data.data = connector; - connector->bit_data.setsda = hibmc_ddc_setsda; - connector->bit_data.setscl = hibmc_ddc_setscl; - connector->bit_data.getsda = hibmc_ddc_getsda; - connector->bit_data.getscl = hibmc_ddc_getscl; + vdac->bit_data.udelay = 20; + vdac->bit_data.timeout = usecs_to_jiffies(2000); + vdac->bit_data.data = vdac; + vdac->bit_data.setsda = hibmc_ddc_setsda; + vdac->bit_data.setscl = hibmc_ddc_setscl; + vdac->bit_data.getsda = hibmc_ddc_getsda; + vdac->bit_data.getscl = hibmc_ddc_getscl; - return i2c_bit_add_bus(&connector->adapter); + return i2c_bit_add_bus(&vdac->adapter); } diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index 409c551c92af..05e19ea4c9f9 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -24,11 +24,11 @@ static int hibmc_connector_get_modes(struct drm_connector *connector) { - struct hibmc_connector *hibmc_connector = to_hibmc_connector(connector); + struct hibmc_vdac *vdac = to_hibmc_vdac(connector); const struct drm_edid *drm_edid; int count; - drm_edid = drm_edid_read_ddc(connector, &hibmc_connector->adapter); + drm_edid = drm_edid_read_ddc(connector, &vdac->adapter); drm_edid_connector_update(connector, drm_edid); @@ -51,9 +51,9 @@ out: static void hibmc_connector_destroy(struct drm_connector *connector) { - struct hibmc_connector *hibmc_connector = to_hibmc_connector(connector); + struct hibmc_vdac *vdac = to_hibmc_vdac(connector); - i2c_del_adapter(&hibmc_connector->adapter); + i2c_del_adapter(&vdac->adapter); drm_connector_cleanup(connector); } @@ -93,20 +93,20 @@ static const struct drm_encoder_helper_funcs hibmc_encoder_helper_funcs = { int hibmc_vdac_init(struct hibmc_drm_private *priv) { struct drm_device *dev = &priv->dev; - struct hibmc_connector *hibmc_connector = &priv->connector; - struct drm_encoder *encoder = &priv->encoder; + struct hibmc_vdac *vdac = &priv->vdac; + struct drm_encoder *encoder = &vdac->encoder; struct drm_crtc *crtc = &priv->crtc; - struct drm_connector *connector = &hibmc_connector->base; + struct drm_connector *connector = &vdac->connector; int ret; - ret = hibmc_ddc_create(dev, hibmc_connector); + ret = hibmc_ddc_create(dev, vdac); if (ret) { drm_err(dev, "failed to create ddc: %d\n", ret); return ret; } encoder->possible_crtcs = drm_crtc_mask(crtc); - ret = drm_simple_encoder_init(dev, encoder, DRM_MODE_ENCODER_DAC); + ret = drmm_encoder_init(dev, encoder, NULL, DRM_MODE_ENCODER_DAC, NULL); if (ret) { drm_err(dev, "failed to init encoder: %d\n", ret); return ret; @@ -117,7 +117,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) ret = drm_connector_init_with_ddc(dev, connector, &hibmc_connector_funcs, DRM_MODE_CONNECTOR_VGA, - &hibmc_connector->adapter); + &vdac->adapter); if (ret) { drm_err(dev, "failed to init connector: %d\n", ret); return ret; diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index 57ce77c2be24..82d4a4e206a5 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -1165,7 +1165,6 @@ static const struct hdmi_codec_ops audio_codec_ops = { .audio_shutdown = tda998x_audio_shutdown, .mute_stream = tda998x_audio_mute_stream, .get_eld = tda998x_audio_get_eld, - .no_capture_mute = 1, }; static int tda998x_audio_codec_init(struct tda998x_priv *priv, @@ -1176,6 +1175,7 @@ static int tda998x_audio_codec_init(struct tda998x_priv *priv, .max_i2s_channels = 2, .no_i2s_capture = 1, .no_spdif_capture = 1, + .no_capture_mute = 1, }; if (priv->audio_port_enable[AUDIO_ROUTE_I2S]) diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index 144d4311c0e8..48b0b9755b2b 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -3081,7 +3081,10 @@ int intel_mtl_tbt_calc_port_clock(struct intel_encoder *encoder) val = intel_de_read(display, XELPDP_PORT_CLOCK_CTL(display, encoder->port)); - clock = REG_FIELD_GET(XELPDP_DDI_CLOCK_SELECT_MASK, val); + if (DISPLAY_VER(display) >= 30) + clock = REG_FIELD_GET(XE3_DDI_CLOCK_SELECT_MASK, val); + else + clock = REG_FIELD_GET(XELPDP_DDI_CLOCK_SELECT_MASK, val); drm_WARN_ON(display->drm, !(val & XELPDP_FORWARD_CLOCK_UNGATE)); drm_WARN_ON(display->drm, !(val & XELPDP_TBT_CLOCK_REQUEST)); @@ -3096,13 +3099,18 @@ int intel_mtl_tbt_calc_port_clock(struct intel_encoder *encoder) return 540000; case XELPDP_DDI_CLOCK_SELECT_TBT_810: return 810000; + case XELPDP_DDI_CLOCK_SELECT_TBT_312_5: + return 1000000; + case XELPDP_DDI_CLOCK_SELECT_TBT_625: + return 2000000; default: MISSING_CASE(clock); return 162000; } } -static int intel_mtl_tbt_clock_select(int clock) +static int intel_mtl_tbt_clock_select(struct intel_display *display, + int clock) { switch (clock) { case 162000: @@ -3113,6 +3121,18 @@ static int intel_mtl_tbt_clock_select(int clock) return XELPDP_DDI_CLOCK_SELECT_TBT_540; case 810000: return XELPDP_DDI_CLOCK_SELECT_TBT_810; + case 1000000: + if (DISPLAY_VER(display) < 30) { + drm_WARN_ON(display->drm, "UHBR10 not supported for the platform\n"); + return XELPDP_DDI_CLOCK_SELECT_TBT_162; + } + return XELPDP_DDI_CLOCK_SELECT_TBT_312_5; + case 2000000: + if (DISPLAY_VER(display) < 30) { + drm_WARN_ON(display->drm, "UHBR20 not supported for the platform\n"); + return XELPDP_DDI_CLOCK_SELECT_TBT_162; + } + return XELPDP_DDI_CLOCK_SELECT_TBT_625; default: MISSING_CASE(clock); return XELPDP_DDI_CLOCK_SELECT_TBT_162; @@ -3125,15 +3145,26 @@ static void intel_mtl_tbt_pll_enable(struct intel_encoder *encoder, struct intel_display *display = to_intel_display(encoder); enum phy phy = intel_encoder_to_phy(encoder); u32 val = 0; + u32 mask; /* * 1. Program PORT_CLOCK_CTL REGISTER to configure * clock muxes, gating and SSC */ - val |= XELPDP_DDI_CLOCK_SELECT(intel_mtl_tbt_clock_select(crtc_state->port_clock)); + + if (DISPLAY_VER(display) >= 30) { + mask = XE3_DDI_CLOCK_SELECT_MASK; + val |= XE3_DDI_CLOCK_SELECT(intel_mtl_tbt_clock_select(display, crtc_state->port_clock)); + } else { + mask = XELPDP_DDI_CLOCK_SELECT_MASK; + val |= XELPDP_DDI_CLOCK_SELECT(intel_mtl_tbt_clock_select(display, crtc_state->port_clock)); + } + + mask |= XELPDP_FORWARD_CLOCK_UNGATE; val |= XELPDP_FORWARD_CLOCK_UNGATE; + intel_de_rmw(display, XELPDP_PORT_CLOCK_CTL(display, encoder->port), - XELPDP_DDI_CLOCK_SELECT_MASK | XELPDP_FORWARD_CLOCK_UNGATE, val); + mask, val); /* 2. Read back PORT_CLOCK_CTL REGISTER */ val = intel_de_read(display, XELPDP_PORT_CLOCK_CTL(display, encoder->port)); diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy_regs.h b/drivers/gpu/drm/i915/display/intel_cx0_phy_regs.h index 5794ece42e92..4a3cf08007e3 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy_regs.h +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy_regs.h @@ -192,7 +192,9 @@ #define XELPDP_TBT_CLOCK_REQUEST REG_BIT(19) #define XELPDP_TBT_CLOCK_ACK REG_BIT(18) #define XELPDP_DDI_CLOCK_SELECT_MASK REG_GENMASK(15, 12) +#define XE3_DDI_CLOCK_SELECT_MASK REG_GENMASK(16, 12) #define XELPDP_DDI_CLOCK_SELECT(val) REG_FIELD_PREP(XELPDP_DDI_CLOCK_SELECT_MASK, val) +#define XE3_DDI_CLOCK_SELECT(val) REG_FIELD_PREP(XE3_DDI_CLOCK_SELECT_MASK, val) #define XELPDP_DDI_CLOCK_SELECT_NONE 0x0 #define XELPDP_DDI_CLOCK_SELECT_MAXPCLK 0x8 #define XELPDP_DDI_CLOCK_SELECT_DIV18CLK 0x9 @@ -200,6 +202,8 @@ #define XELPDP_DDI_CLOCK_SELECT_TBT_270 0xd #define XELPDP_DDI_CLOCK_SELECT_TBT_540 0xe #define XELPDP_DDI_CLOCK_SELECT_TBT_810 0xf +#define XELPDP_DDI_CLOCK_SELECT_TBT_312_5 0x18 +#define XELPDP_DDI_CLOCK_SELECT_TBT_625 0x19 #define XELPDP_FORWARD_CLOCK_UNGATE REG_BIT(10) #define XELPDP_LANE1_PHY_CLOCK_SELECT REG_BIT(8) #define XELPDP_SSC_ENABLE_PLLA REG_BIT(1) diff --git a/drivers/gpu/drm/i915/display/intel_display_driver.c b/drivers/gpu/drm/i915/display/intel_display_driver.c index 73ea0e906014..c4120a834698 100644 --- a/drivers/gpu/drm/i915/display/intel_display_driver.c +++ b/drivers/gpu/drm/i915/display/intel_display_driver.c @@ -397,7 +397,6 @@ void intel_display_driver_resume_access(struct intel_display *display) */ bool intel_display_driver_check_access(struct intel_display *display) { - char comm[TASK_COMM_LEN]; char current_task[TASK_COMM_LEN + 16]; char allowed_task[TASK_COMM_LEN + 16] = "none"; @@ -406,12 +405,11 @@ bool intel_display_driver_check_access(struct intel_display *display) return true; snprintf(current_task, sizeof(current_task), "%s[%d]", - get_task_comm(comm, current), - task_pid_vnr(current)); + current->comm, task_pid_vnr(current)); if (display->access.allowed_task) snprintf(allowed_task, sizeof(allowed_task), "%s[%d]", - get_task_comm(comm, display->access.allowed_task), + display->access.allowed_task->comm, task_pid_vnr(display->access.allowed_task)); drm_dbg_kms(display->drm, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index 3198b64ad7db..388f90784d8a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -52,29 +52,6 @@ bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) mr->type == INTEL_MEMORY_STOLEN_LOCAL); } -/** - * __i915_gem_object_is_lmem - Whether the object is resident in - * lmem while in the fence signaling critical path. - * @obj: The object to check. - * - * This function is intended to be called from within the fence signaling - * path where the fence, or a pin, keeps the object from being migrated. For - * example during gpu reset or similar. - * - * Return: Whether the object is resident in lmem. - */ -bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) -{ - struct intel_memory_region *mr = READ_ONCE(obj->mm.region); - -#ifdef CONFIG_LOCKDEP - GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, DMA_RESV_USAGE_BOOKKEEP) && - i915_gem_object_evictable(obj)); -#endif - return mr && (mr->type == INTEL_MEMORY_LOCAL || - mr->type == INTEL_MEMORY_STOLEN_LOCAL); -} - /** * __i915_gem_object_create_lmem_with_ps - Create lmem object and force the * minimum page size for the backing pages. diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h index 5a7a14e85c3f..ecd8f1a633a1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h @@ -19,8 +19,6 @@ i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj, bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj); -bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj); - struct drm_i915_gem_object * i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915, const void *data, size_t size); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c index 89d4dc8b60c6..eb0158e43417 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c @@ -369,7 +369,7 @@ static int live_parallel_switch(void *arg) if (!data[n].ce[0]) continue; - worker = kthread_create_worker(0, "igt/parallel:%s", + worker = kthread_run_worker(0, "igt/parallel:%s", data[n].ce[0]->engine->name); if (IS_ERR(worker)) { err = PTR_ERR(worker); diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 33b55c581552..5a625518d1a9 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -1113,6 +1113,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt) * Warn CI about the unrecoverable wedged condition. * Time for a reboot. */ + gt_err(gt, "Unrecoverable wedged condition\n"); add_taint_for_CI(gt->i915, TAINT_WARN); return false; } @@ -1264,8 +1265,10 @@ void intel_gt_reset(struct intel_gt *gt, } ret = resume(gt); - if (ret) + if (ret) { + gt_err(gt, "Failed to resume (%d)\n", ret); goto taint; + } finish: reset_finish(gt, awake); @@ -1608,6 +1611,7 @@ void intel_gt_set_wedged_on_init(struct intel_gt *gt) set_bit(I915_WEDGED_ON_INIT, >->reset.flags); /* Wedged on init is non-recoverable */ + gt_err(gt, "Non-recoverable wedged on init\n"); add_taint_for_CI(gt->i915, TAINT_WARN); } diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c index 59da4b7bd262..b74d9205c0f5 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.c +++ b/drivers/gpu/drm/i915/gt/intel_ring.c @@ -308,30 +308,6 @@ u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords) return cs; } -/* Align the ring tail to a cacheline boundary */ -int intel_ring_cacheline_align(struct i915_request *rq) -{ - int num_dwords; - void *cs; - - num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32); - if (num_dwords == 0) - return 0; - - num_dwords = CACHELINE_DWORDS - num_dwords; - GEM_BUG_ON(num_dwords & 1); - - cs = intel_ring_begin(rq, num_dwords); - if (IS_ERR(cs)) - return PTR_ERR(cs); - - memset64(cs, (u64)MI_NOOP << 32 | MI_NOOP, num_dwords / 2); - intel_ring_advance(rq, cs + num_dwords); - - GEM_BUG_ON(rq->ring->emit & (CACHELINE_BYTES - 1)); - return 0; -} - #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_ring.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h index 1b32dadfb8c3..64b322e25f36 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.h +++ b/drivers/gpu/drm/i915/gt/intel_ring.h @@ -16,7 +16,6 @@ struct intel_ring * intel_engine_create_ring(struct intel_engine_cs *engine, int size); u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords); -int intel_ring_cacheline_align(struct i915_request *rq); unsigned int intel_ring_update_space(struct intel_ring *ring); diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index f0b75986afb9..6e9977b2d180 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -26,6 +26,7 @@ #include "shmem_utils.h" #include "intel_engine_heartbeat.h" #include "intel_engine_pm.h" +#include "intel_gt_print.h" /* Rough estimate of the typical request size, performing a flush, * set-context and then emitting the batch. @@ -230,8 +231,13 @@ static int xcs_resume(struct intel_engine_cs *engine) set_pp_dir(engine); - /* First wake the ring up to an empty/idle ring */ - for ((kt) = ktime_get() + (2 * NSEC_PER_MSEC); + /* + * First wake the ring up to an empty/idle ring. + * Use 50ms of delay to let the engine write successfully + * for all platforms. Experimented with different values and + * determined that 50ms works best based on testing. + */ + for ((kt) = ktime_get() + (50 * NSEC_PER_MSEC); ktime_before(ktime_get(), (kt)); cpu_relax()) { /* * In case of resets fails because engine resumes from @@ -282,16 +288,16 @@ static int xcs_resume(struct intel_engine_cs *engine) return 0; err: - drm_err(&engine->i915->drm, - "%s initialization failed; " - "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n", - engine->name, - ENGINE_READ(engine, RING_CTL), - ENGINE_READ(engine, RING_CTL) & RING_VALID, - ENGINE_READ(engine, RING_HEAD), ring->head, - ENGINE_READ(engine, RING_TAIL), ring->tail, - ENGINE_READ(engine, RING_START), - i915_ggtt_offset(ring->vma)); + gt_err(engine->gt, "%s initialization failed\n", engine->name); + ENGINE_TRACE(engine, + "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n", + ENGINE_READ(engine, RING_CTL), + ENGINE_READ(engine, RING_CTL) & RING_VALID, + ENGINE_READ(engine, RING_HEAD), ring->head, + ENGINE_READ(engine, RING_TAIL), ring->tail, + ENGINE_READ(engine, RING_START), + i915_ggtt_offset(ring->vma)); + GEM_TRACE_DUMP(); return -EIO; } diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 07bc0bbee20f..d7717de17ecc 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -3574,7 +3574,7 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags) arg[id].batch = NULL; arg[id].count = 0; - worker[id] = kthread_create_worker(0, "igt/smoke:%d", id); + worker[id] = kthread_run_worker(0, "igt/smoke:%d", id); if (IS_ERR(worker[id])) { err = PTR_ERR(worker[id]); break; diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c index d99061735c58..f057c16410e7 100644 --- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -1025,7 +1025,7 @@ static int __igt_reset_engines(struct intel_gt *gt, threads[tmp].engine = other; threads[tmp].flags = flags; - worker = kthread_create_worker(0, "igt/%s", + worker = kthread_run_worker(0, "igt/%s", other->name); if (IS_ERR(worker)) { err = PTR_ERR(worker); diff --git a/drivers/gpu/drm/i915/gt/selftest_migrate.c b/drivers/gpu/drm/i915/gt/selftest_migrate.c index ca460cee4f8b..1bf7b88d9a9d 100644 --- a/drivers/gpu/drm/i915/gt/selftest_migrate.c +++ b/drivers/gpu/drm/i915/gt/selftest_migrate.c @@ -262,7 +262,7 @@ static int clear(struct intel_migrate *migrate, { struct drm_i915_private *i915 = migrate->context->engine->i915; struct drm_i915_gem_object *obj; - struct i915_request *rq; + struct i915_request *rq = NULL; struct i915_gem_ww_ctx ww; u32 *vaddr, val = 0; bool ccs_cap = false; diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c index b272a7d44599..908483ab0bc8 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rc6.c +++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c @@ -8,6 +8,7 @@ #include "intel_gpu_commands.h" #include "intel_gt_requests.h" #include "intel_ring.h" +#include "intel_rps.h" #include "selftest_rc6.h" #include "selftests/i915_random.h" @@ -38,6 +39,9 @@ int live_rc6_manual(void *arg) ktime_t dt; u64 res[2]; int err = 0; + u32 rc0_freq = 0; + u32 rc6_freq = 0; + struct intel_rps *rps = >->rps; /* * Our claim is that we can "encourage" the GPU to enter rc6 at will. @@ -66,6 +70,7 @@ int live_rc6_manual(void *arg) rc0_power = librapl_energy_uJ() - rc0_power; dt = ktime_sub(ktime_get(), dt); res[1] = rc6_residency(rc6); + rc0_freq = intel_rps_read_actual_frequency_fw(rps); if ((res[1] - res[0]) >> 10) { pr_err("RC6 residency increased by %lldus while disabled for 1000ms!\n", (res[1] - res[0]) >> 10); @@ -77,7 +82,11 @@ int live_rc6_manual(void *arg) rc0_power = div64_u64(NSEC_PER_SEC * rc0_power, ktime_to_ns(dt)); if (!rc0_power) { - pr_err("No power measured while in RC0\n"); + if (rc0_freq) + pr_debug("No power measured while in RC0! GPU Freq: %u in RC0\n", + rc0_freq); + else + pr_err("No power and freq measured while in RC0\n"); err = -EINVAL; goto out_unlock; } @@ -90,7 +99,8 @@ int live_rc6_manual(void *arg) intel_uncore_forcewake_flush(rc6_to_uncore(rc6), FORCEWAKE_ALL); dt = ktime_get(); rc6_power = librapl_energy_uJ(); - msleep(100); + msleep(1000); + rc6_freq = intel_rps_read_actual_frequency_fw(rps); rc6_power = librapl_energy_uJ() - rc6_power; dt = ktime_sub(ktime_get(), dt); res[1] = rc6_residency(rc6); @@ -108,7 +118,8 @@ int live_rc6_manual(void *arg) pr_info("GPU consumed %llduW in RC0 and %llduW in RC6\n", rc0_power, rc6_power); if (2 * rc6_power > rc0_power) { - pr_err("GPU leaked energy while in RC6!\n"); + pr_err("GPU leaked energy while in RC6! GPU Freq: %u in RC6 and %u in RC0\n", + rc6_freq, rc0_freq); err = -EINVAL; goto out_unlock; } diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c index 4ecc4ae74a54..e218b229681f 100644 --- a/drivers/gpu/drm/i915/gt/selftest_slpc.c +++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c @@ -489,7 +489,7 @@ static int live_slpc_tile_interaction(void *arg) return -ENOMEM; for_each_gt(gt, i915, i) { - threads[i].worker = kthread_create_worker(0, "igt/slpc_parallel:%d", gt->info.id); + threads[i].worker = kthread_run_worker(0, "igt/slpc_parallel:%d", gt->info.id); if (IS_ERR(threads[i].worker)) { ret = PTR_ERR(threads[i].worker); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c index 222c95f62156..e8a04e476c57 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c @@ -18,7 +18,7 @@ #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE SZ_2M #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE SZ_16M #define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE SZ_1M -#elif defined(CONFIG_DRM_I915_DEBUG_GEM) +#elif IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE SZ_1M #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE SZ_2M #define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE SZ_1M diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index d7ac31c3254c..b3cbf85c00cb 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -427,19 +427,6 @@ void intel_huc_fini(struct intel_huc *huc) intel_uc_fw_fini(&huc->fw); } -void intel_huc_suspend(struct intel_huc *huc) -{ - if (!intel_uc_fw_is_loadable(&huc->fw)) - return; - - /* - * in the unlikely case that we're suspending before the GSC has - * completed its loading sequence, just stop waiting. We'll restart - * on resume. - */ - delayed_huc_load_complete(huc); -} - static const char *auth_mode_string(struct intel_huc *huc, enum intel_huc_authentication_type type) { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h index ba5cb08e9e7b..d5e441b9e08d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h @@ -57,7 +57,6 @@ int intel_huc_sanitize(struct intel_huc *huc); void intel_huc_init_early(struct intel_huc *huc); int intel_huc_init(struct intel_huc *huc); void intel_huc_fini(struct intel_huc *huc); -void intel_huc_suspend(struct intel_huc *huc); int intel_huc_auth(struct intel_huc *huc, enum intel_huc_authentication_type type); int intel_huc_wait_for_auth_complete(struct intel_huc *huc, enum intel_huc_authentication_type type); diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 35319228bc51..0dbc4e289300 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -527,24 +527,6 @@ int i915_active_acquire(struct i915_active *ref) return err; } -int i915_active_acquire_for_context(struct i915_active *ref, u64 idx) -{ - struct i915_active_fence *active; - int err; - - err = i915_active_acquire(ref); - if (err) - return err; - - active = active_instance(ref, idx); - if (!active) { - i915_active_release(ref); - return -ENOMEM; - } - - return 0; /* return with active ref */ -} - void i915_active_release(struct i915_active *ref) { debug_active_assert(ref); diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h index 77c676ecc263..821f7c21ea9b 100644 --- a/drivers/gpu/drm/i915/i915_active.h +++ b/drivers/gpu/drm/i915/i915_active.h @@ -186,7 +186,6 @@ int i915_request_await_active(struct i915_request *rq, #define I915_ACTIVE_AWAIT_BARRIER BIT(2) int i915_active_acquire(struct i915_active *ref); -int i915_active_acquire_for_context(struct i915_active *ref, u64 idx); bool i915_active_acquire_if_busy(struct i915_active *ref); void i915_active_release(struct i915_active *ref); diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c index f58682505491..168d7375304b 100644 --- a/drivers/gpu/drm/i915/i915_drm_client.c +++ b/drivers/gpu/drm/i915/i915_drm_client.c @@ -102,6 +102,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file) for_each_memory_region(mr, i915, id) drm_print_memory_stats(p, &stats[id], + DRM_GEM_OBJECT_ACTIVE | DRM_GEM_OBJECT_RESIDENT | DRM_GEM_OBJECT_PURGEABLE, mr->uabi_name); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index eb7b4e21b124..bec164e884ae 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -4807,7 +4807,7 @@ err_unlock: return ret; } -static struct ctl_table oa_table[] = { +static const struct ctl_table oa_table[] = { { .procname = "perf_stream_paranoid", .data = &i915_perf_stream_paranoid, diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index acae30a04a94..88870844b5bd 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -492,7 +492,7 @@ static int mock_breadcrumbs_smoketest(void *arg) for (n = 0; n < ncpus; n++) { struct kthread_worker *worker; - worker = kthread_create_worker(0, "igt/%d", n); + worker = kthread_run_worker(0, "igt/%d", n); if (IS_ERR(worker)) { ret = PTR_ERR(worker); ncpus = n; @@ -1645,7 +1645,7 @@ static int live_parallel_engines(void *arg) for_each_uabi_engine(engine, i915) { struct kthread_worker *worker; - worker = kthread_create_worker(0, "igt/parallel:%s", + worker = kthread_run_worker(0, "igt/parallel:%s", engine->name); if (IS_ERR(worker)) { err = PTR_ERR(worker); @@ -1806,7 +1806,7 @@ static int live_breadcrumbs_smoketest(void *arg) unsigned int i = idx * ncpus + n; struct kthread_worker *worker; - worker = kthread_create_worker(0, "igt/%d.%d", idx, n); + worker = kthread_run_worker(0, "igt/%d.%d", idx, n); if (IS_ERR(worker)) { ret = PTR_ERR(worker); goto out_flush; @@ -3219,7 +3219,7 @@ static int perf_parallel_engines(void *arg) memset(&engines[idx].p, 0, sizeof(engines[idx].p)); - worker = kthread_create_worker(0, "igt:%s", + worker = kthread_run_worker(0, "igt:%s", engine->name); if (IS_ERR(worker)) { err = PTR_ERR(worker); diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig index f496e6cfdfe0..e47debd60619 100644 --- a/drivers/gpu/drm/mediatek/Kconfig +++ b/drivers/gpu/drm/mediatek/Kconfig @@ -14,9 +14,6 @@ config DRM_MEDIATEK select DRM_BRIDGE_CONNECTOR select DRM_MIPI_DSI select DRM_PANEL - select MEMORY - select MTK_SMI - select PHY_MTK_MIPI_DSI select VIDEOMODE_HELPERS help Choose this option if you have a Mediatek SoCs. @@ -27,7 +24,6 @@ config DRM_MEDIATEK config DRM_MEDIATEK_DP tristate "DRM DPTX Support for MediaTek SoCs" depends on DRM_MEDIATEK - select PHY_MTK_DP select DRM_DISPLAY_HELPER select DRM_DISPLAY_DP_HELPER select DRM_DISPLAY_DP_AUX_BUS @@ -38,6 +34,5 @@ config DRM_MEDIATEK_HDMI tristate "DRM HDMI Support for Mediatek SoCs" depends on DRM_MEDIATEK select SND_SOC_HDMI_CODEC if SND_SOC - select PHY_MTK_HDMI help DRM/KMS HDMI driver for Mediatek SoCs diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index eb0e1233ad04..5674f5707cca 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -112,6 +112,11 @@ static void mtk_drm_finish_page_flip(struct mtk_crtc *mtk_crtc) drm_crtc_handle_vblank(&mtk_crtc->base); +#if IS_REACHABLE(CONFIG_MTK_CMDQ) + if (mtk_crtc->cmdq_client.chan) + return; +#endif + spin_lock_irqsave(&mtk_crtc->config_lock, flags); if (!mtk_crtc->config_updating && mtk_crtc->pending_needs_vblank) { mtk_crtc_finish_page_flip(mtk_crtc); @@ -284,10 +289,8 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) state = to_mtk_crtc_state(mtk_crtc->base.state); spin_lock_irqsave(&mtk_crtc->config_lock, flags); - if (mtk_crtc->config_updating) { - spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + if (mtk_crtc->config_updating) goto ddp_cmdq_cb_out; - } state->pending_config = false; @@ -315,10 +318,15 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) mtk_crtc->pending_async_planes = false; } - spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); - ddp_cmdq_cb_out: + if (mtk_crtc->pending_needs_vblank) { + mtk_crtc_finish_page_flip(mtk_crtc); + mtk_crtc->pending_needs_vblank = false; + } + + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + mtk_crtc->cmdq_vblank_cnt = 0; wake_up(&mtk_crtc->cb_blocking_queue); } @@ -606,13 +614,18 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank) */ mtk_crtc->cmdq_vblank_cnt = 3; + spin_lock_irqsave(&mtk_crtc->config_lock, flags); + mtk_crtc->config_updating = false; + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle); mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0); } -#endif +#else spin_lock_irqsave(&mtk_crtc->config_lock, flags); mtk_crtc->config_updating = false; spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); +#endif mutex_unlock(&mtk_crtc->hw_lock); } diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index f731d4fbe8b6..df82cea4bb79 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -460,6 +460,29 @@ static unsigned int mtk_ovl_fmt_convert(struct mtk_disp_ovl *ovl, } } +static void mtk_ovl_afbc_layer_config(struct mtk_disp_ovl *ovl, + unsigned int idx, + struct mtk_plane_pending_state *pending, + struct cmdq_pkt *cmdq_pkt) +{ + unsigned int pitch_msb = pending->pitch >> 16; + unsigned int hdr_pitch = pending->hdr_pitch; + unsigned int hdr_addr = pending->hdr_addr; + + if (pending->modifier != DRM_FORMAT_MOD_LINEAR) { + mtk_ddp_write_relaxed(cmdq_pkt, hdr_addr, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_ADDR(ovl, idx)); + mtk_ddp_write_relaxed(cmdq_pkt, + OVL_PITCH_MSB_2ND_SUBBUF | pitch_msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + mtk_ddp_write_relaxed(cmdq_pkt, hdr_pitch, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_PITCH(ovl, idx)); + } else { + mtk_ddp_write_relaxed(cmdq_pkt, pitch_msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + } +} + void mtk_ovl_layer_config(struct device *dev, unsigned int idx, struct mtk_plane_state *state, struct cmdq_pkt *cmdq_pkt) @@ -467,25 +490,14 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); struct mtk_plane_pending_state *pending = &state->pending; unsigned int addr = pending->addr; - unsigned int hdr_addr = pending->hdr_addr; - unsigned int pitch = pending->pitch; - unsigned int hdr_pitch = pending->hdr_pitch; + unsigned int pitch_lsb = pending->pitch & GENMASK(15, 0); unsigned int fmt = pending->format; + unsigned int rotation = pending->rotation; unsigned int offset = (pending->y << 16) | pending->x; unsigned int src_size = (pending->height << 16) | pending->width; unsigned int blend_mode = state->base.pixel_blend_mode; unsigned int ignore_pixel_alpha = 0; unsigned int con; - bool is_afbc = pending->modifier != DRM_FORMAT_MOD_LINEAR; - union overlay_pitch { - struct split_pitch { - u16 lsb; - u16 msb; - } split_pitch; - u32 pitch; - } overlay_pitch; - - overlay_pitch.pitch = pitch; if (!pending->enable) { mtk_ovl_layer_off(dev, idx, cmdq_pkt); @@ -513,22 +525,30 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, ignore_pixel_alpha = OVL_CONST_BLEND; } - if (pending->rotation & DRM_MODE_REFLECT_Y) { + /* + * Treat rotate 180 as flip x + flip y, and XOR the original rotation value + * to flip x + flip y to support both in the same time. + */ + if (rotation & DRM_MODE_ROTATE_180) + rotation ^= DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y; + + if (rotation & DRM_MODE_REFLECT_Y) { con |= OVL_CON_VIRT_FLIP; addr += (pending->height - 1) * pending->pitch; } - if (pending->rotation & DRM_MODE_REFLECT_X) { + if (rotation & DRM_MODE_REFLECT_X) { con |= OVL_CON_HORZ_FLIP; addr += pending->pitch - 1; } if (ovl->data->supports_afbc) - mtk_ovl_set_afbc(ovl, cmdq_pkt, idx, is_afbc); + mtk_ovl_set_afbc(ovl, cmdq_pkt, idx, + pending->modifier != DRM_FORMAT_MOD_LINEAR); mtk_ddp_write_relaxed(cmdq_pkt, con, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_CON(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb | ignore_pixel_alpha, + mtk_ddp_write_relaxed(cmdq_pkt, pitch_lsb | ignore_pixel_alpha, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH(idx)); mtk_ddp_write_relaxed(cmdq_pkt, src_size, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_SRC_SIZE(idx)); @@ -537,19 +557,8 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, mtk_ddp_write_relaxed(cmdq_pkt, addr, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_ADDR(ovl, idx)); - if (is_afbc) { - mtk_ddp_write_relaxed(cmdq_pkt, hdr_addr, &ovl->cmdq_reg, ovl->regs, - DISP_REG_OVL_HDR_ADDR(ovl, idx)); - mtk_ddp_write_relaxed(cmdq_pkt, - OVL_PITCH_MSB_2ND_SUBBUF | overlay_pitch.split_pitch.msb, - &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, hdr_pitch, &ovl->cmdq_reg, ovl->regs, - DISP_REG_OVL_HDR_PITCH(ovl, idx)); - } else { - mtk_ddp_write_relaxed(cmdq_pkt, - overlay_pitch.split_pitch.msb, - &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); - } + if (ovl->data->supports_afbc) + mtk_ovl_afbc_layer_config(ovl, idx, pending, cmdq_pkt); mtk_ovl_set_bit_depth(dev, idx, fmt, cmdq_pkt); mtk_ovl_layer_on(dev, idx, cmdq_pkt); diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 36713c176cfc..cd385ba4c66a 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -543,18 +543,16 @@ static int mtk_dp_set_color_format(struct mtk_dp *mtk_dp, enum dp_pixelformat color_format) { u32 val; - - /* update MISC0 */ - mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_3034, - color_format << DP_TEST_COLOR_FORMAT_SHIFT, - DP_TEST_COLOR_FORMAT_MASK); + u32 misc0_color; switch (color_format) { case DP_PIXELFORMAT_YUV422: val = PIXEL_ENCODE_FORMAT_DP_ENC0_P0_YCBCR422; + misc0_color = DP_COLOR_FORMAT_YCbCr422; break; case DP_PIXELFORMAT_RGB: val = PIXEL_ENCODE_FORMAT_DP_ENC0_P0_RGB; + misc0_color = DP_COLOR_FORMAT_RGB; break; default: drm_warn(mtk_dp->drm_dev, "Unsupported color format: %d\n", @@ -562,6 +560,11 @@ static int mtk_dp_set_color_format(struct mtk_dp *mtk_dp, return -EINVAL; } + /* update MISC0 */ + mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_3034, + misc0_color, + DP_TEST_COLOR_FORMAT_MASK); + mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_303C, val, PIXEL_ENCODE_FORMAT_DP_ENC0_P0_MASK); return 0; @@ -1135,6 +1138,18 @@ static void mtk_dp_digital_sw_reset(struct mtk_dp *mtk_dp) 0, DP_TX_TRANSMITTER_4P_RESET_SW_DP_TRANS_P0); } +static void mtk_dp_sdp_path_reset(struct mtk_dp *mtk_dp) +{ + mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_3004, + SDP_RESET_SW_DP_ENC0_P0, + SDP_RESET_SW_DP_ENC0_P0); + + /* Wait for sdp path reset to complete */ + usleep_range(1000, 5000); + mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_3004, + 0, SDP_RESET_SW_DP_ENC0_P0); +} + static void mtk_dp_set_lanes(struct mtk_dp *mtk_dp, int lanes) { mtk_dp_update_bits(mtk_dp, MTK_DP_TRANS_P0_35F0, @@ -1165,17 +1180,25 @@ static void mtk_dp_get_calibration_data(struct mtk_dp *mtk_dp) buf = (u32 *)nvmem_cell_read(cell, &len); nvmem_cell_put(cell); - if (IS_ERR(buf) || ((len / sizeof(u32)) != 4)) { + if (IS_ERR(buf)) { dev_warn(dev, "Failed to read nvmem_cell_read\n"); - - if (!IS_ERR(buf)) - kfree(buf); - goto use_default_val; } + /* The cell length is in bytes. Convert it to be compatible with u32 buffer. */ + len /= sizeof(u32); + for (i = 0; i < MTK_DP_CAL_MAX; i++) { fmt = &mtk_dp->data->efuse_fmt[i]; + + if (fmt->idx >= len) { + dev_warn(mtk_dp->dev, + "Out-of-bound efuse data access, fmt idx = %d, buf len = %zu\n", + fmt->idx, len); + kfree(buf); + goto use_default_val; + } + cal_data[i] = (buf[fmt->idx] >> fmt->shift) & fmt->mask; if (cal_data[i] < fmt->min_val || cal_data[i] > fmt->max_val) { @@ -2100,7 +2123,6 @@ static enum drm_connector_status mtk_dp_bdg_detect(struct drm_bridge *bridge) struct mtk_dp *mtk_dp = mtk_dp_from_bridge(bridge); enum drm_connector_status ret = connector_status_disconnected; bool enabled = mtk_dp->enabled; - u8 sink_count = 0; if (!mtk_dp->train_info.cable_plugged_in) return ret; @@ -2115,8 +2137,8 @@ static enum drm_connector_status mtk_dp_bdg_detect(struct drm_bridge *bridge) * function, we just need to check the HPD connection to check * whether we connect to a sink device. */ - drm_dp_dpcd_readb(&mtk_dp->aux, DP_SINK_COUNT, &sink_count); - if (DP_GET_SINK_COUNT(sink_count)) + + if (drm_dp_read_sink_count(&mtk_dp->aux) > 0) ret = connector_status_connected; if (!enabled) @@ -2397,6 +2419,9 @@ static void mtk_dp_bridge_atomic_disable(struct drm_bridge *bridge, DP_PWR_STATE_BANDGAP_TPLL, DP_PWR_STATE_MASK); + /* SDP path reset sw*/ + mtk_dp_sdp_path_reset(mtk_dp); + /* Ensure the sink is muted */ msleep(20); } @@ -2408,12 +2433,19 @@ mtk_dp_bridge_mode_valid(struct drm_bridge *bridge, { struct mtk_dp *mtk_dp = mtk_dp_from_bridge(bridge); u32 bpp = info->color_formats & DRM_COLOR_FORMAT_YCBCR422 ? 16 : 24; - u32 rate = min_t(u32, drm_dp_max_link_rate(mtk_dp->rx_cap) * - drm_dp_max_lane_count(mtk_dp->rx_cap), - drm_dp_bw_code_to_link_rate(mtk_dp->max_linkrate) * - mtk_dp->max_lanes); + u32 lane_count_min = mtk_dp->train_info.lane_count; + u32 rate = drm_dp_bw_code_to_link_rate(mtk_dp->train_info.link_rate) * + lane_count_min; - if (rate < mode->clock * bpp / 8) + /* + *FEC overhead is approximately 2.4% from DP 1.4a spec 2.2.1.4.2. + *The down-spread amplitude shall either be disabled (0.0%) or up + *to 0.5% from 1.4a 3.5.2.6. Add up to approximately 3% total overhead. + * + *Because rate is already divided by 10, + *mode->clock does not need to be multiplied by 10 + */ + if ((rate * 97 / 100) < (mode->clock * bpp / 8)) return MODE_CLOCK_HIGH; return MODE_OK; @@ -2454,10 +2486,9 @@ static u32 *mtk_dp_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct drm_display_info *display_info = &conn_state->connector->display_info; - u32 rate = min_t(u32, drm_dp_max_link_rate(mtk_dp->rx_cap) * - drm_dp_max_lane_count(mtk_dp->rx_cap), - drm_dp_bw_code_to_link_rate(mtk_dp->max_linkrate) * - mtk_dp->max_lanes); + u32 lane_count_min = mtk_dp->train_info.lane_count; + u32 rate = drm_dp_bw_code_to_link_rate(mtk_dp->train_info.link_rate) * + lane_count_min; *num_input_fmts = 0; @@ -2466,8 +2497,8 @@ static u32 *mtk_dp_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, * datarate of YUV422 and sink device supports YUV422, we output YUV422 * format. Use this condition, we can support more resolution. */ - if ((rate < (mode->clock * 24 / 8)) && - (rate > (mode->clock * 16 / 8)) && + if (((rate * 97 / 100) < (mode->clock * 24 / 8)) && + ((rate * 97 / 100) > (mode->clock * 16 / 8)) && (display_info->color_formats & DRM_COLOR_FORMAT_YCBCR422)) { input_fmts = kcalloc(1, sizeof(*input_fmts), GFP_KERNEL); if (!input_fmts) @@ -2615,7 +2646,6 @@ static const struct hdmi_codec_ops mtk_dp_audio_codec_ops = { .audio_shutdown = mtk_dp_audio_shutdown, .get_eld = mtk_dp_audio_get_eld, .hook_plugged_cb = mtk_dp_audio_hook_plugged_cb, - .no_capture_mute = 1, }; static int mtk_dp_register_audio_driver(struct device *dev) @@ -2626,6 +2656,7 @@ static int mtk_dp_register_audio_driver(struct device *dev) .max_i2s_channels = 8, .i2s = 1, .data = mtk_dp, + .no_capture_mute = 1, }; mtk_dp->audio_pdev = platform_device_register_data(dev, diff --git a/drivers/gpu/drm/mediatek/mtk_dp_reg.h b/drivers/gpu/drm/mediatek/mtk_dp_reg.h index 709b79480693..8ad7a9cc259e 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp_reg.h +++ b/drivers/gpu/drm/mediatek/mtk_dp_reg.h @@ -86,6 +86,7 @@ #define MTK_DP_ENC0_P0_3004 0x3004 #define VIDEO_M_CODE_SEL_DP_ENC0_P0_MASK BIT(8) #define DP_TX_ENCODER_4P_RESET_SW_DP_ENC0_P0 BIT(9) +#define SDP_RESET_SW_DP_ENC0_P0 BIT(13) #define MTK_DP_ENC0_P0_3010 0x3010 #define HTOTAL_SW_DP_ENC0_P0_MASK GENMASK(15, 0) #define MTK_DP_ENC0_P0_3014 0x3014 diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 49af2b19a85a..f22ad2882697 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -358,7 +358,7 @@ static const struct of_device_id mtk_drm_of_ids[] = { }; MODULE_DEVICE_TABLE(of, mtk_drm_of_ids); -static int mtk_drm_match(struct device *dev, void *data) +static int mtk_drm_match(struct device *dev, const void *data) { if (!strncmp(dev_name(dev), "mediatek-drm", sizeof("mediatek-drm") - 1)) return true; @@ -372,11 +372,12 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) struct mtk_drm_private *temp_drm_priv; struct device_node *phandle = dev->parent->of_node; const struct of_device_id *of_id; + struct device_node *node; struct device *drm_dev; unsigned int cnt = 0; int i, j; - for_each_child_of_node_scoped(phandle->parent, node) { + for_each_child_of_node(phandle->parent, node) { struct platform_device *pdev; of_id = of_match_node(mtk_drm_of_ids, node); @@ -405,8 +406,10 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) if (temp_drm_priv->mtk_drm_bound) cnt++; - if (cnt == MAX_CRTC) + if (cnt == MAX_CRTC) { + of_node_put(node); break; + } } if (drm_priv->data->mmsys_dev_num == cnt) { @@ -671,6 +674,8 @@ err_deinit: err_free: private->drm = NULL; drm_dev_put(drm); + for (i = 0; i < private->data->mmsys_dev_num; i++) + private->all_drm_private[i]->drm = NULL; return ret; } @@ -898,7 +903,7 @@ static int mtk_drm_of_ddp_path_build_one(struct device *dev, enum mtk_crtc_path const unsigned int **out_path, unsigned int *out_path_len) { - struct device_node *next, *prev, *vdo = dev->parent->of_node; + struct device_node *next = NULL, *prev, *vdo = dev->parent->of_node; unsigned int temp_path[DDP_COMPONENT_DRM_ID_MAX] = { 0 }; unsigned int *final_ddp_path; unsigned short int idx = 0; @@ -1087,7 +1092,7 @@ static int mtk_drm_probe(struct platform_device *pdev) /* No devicetree graphs support: go with hardcoded paths if present */ dev_dbg(dev, "Using hardcoded paths for MMSYS %u\n", mtk_drm_data->mmsys_id); private->data = mtk_drm_data; - }; + } private->all_drm_private = devm_kmalloc_array(dev, private->data->mmsys_dev_num, sizeof(*private->all_drm_private), diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index e61b9bc68e9a..40752f232054 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -139,11 +139,11 @@ #define CLK_HS_POST GENMASK(15, 8) #define CLK_HS_EXIT GENMASK(23, 16) -#define DSI_VM_CMD_CON 0x130 +/* DSI_VM_CMD_CON */ #define VM_CMD_EN BIT(0) #define TS_VFP_EN BIT(5) -#define DSI_SHADOW_DEBUG 0x190U +/* DSI_SHADOW_DEBUG */ #define FORCE_COMMIT BIT(0) #define BYPASS_SHADOW BIT(1) @@ -187,6 +187,8 @@ struct phy; struct mtk_dsi_driver_data { const u32 reg_cmdq_off; + const u32 reg_vm_cmd_off; + const u32 reg_shadow_dbg_off; bool has_shadow_ctl; bool has_size_ctl; bool cmdq_long_packet_ctl; @@ -246,23 +248,22 @@ static void mtk_dsi_phy_timconfig(struct mtk_dsi *dsi) u32 data_rate_mhz = DIV_ROUND_UP(dsi->data_rate, HZ_PER_MHZ); struct mtk_phy_timing *timing = &dsi->phy_timing; - timing->lpx = (80 * data_rate_mhz / (8 * 1000)) + 1; - timing->da_hs_prepare = (59 * data_rate_mhz + 4 * 1000) / 8000 + 1; - timing->da_hs_zero = (163 * data_rate_mhz + 11 * 1000) / 8000 + 1 - + timing->lpx = (60 * data_rate_mhz / (8 * 1000)) + 1; + timing->da_hs_prepare = (80 * data_rate_mhz + 4 * 1000) / 8000; + timing->da_hs_zero = (170 * data_rate_mhz + 10 * 1000) / 8000 + 1 - timing->da_hs_prepare; - timing->da_hs_trail = (78 * data_rate_mhz + 7 * 1000) / 8000 + 1; + timing->da_hs_trail = timing->da_hs_prepare + 1; - timing->ta_go = 4 * timing->lpx; - timing->ta_sure = 3 * timing->lpx / 2; - timing->ta_get = 5 * timing->lpx; - timing->da_hs_exit = (118 * data_rate_mhz / (8 * 1000)) + 1; + timing->ta_go = 4 * timing->lpx - 2; + timing->ta_sure = timing->lpx + 2; + timing->ta_get = 4 * timing->lpx; + timing->da_hs_exit = 2 * timing->lpx + 1; - timing->clk_hs_prepare = (57 * data_rate_mhz / (8 * 1000)) + 1; - timing->clk_hs_post = (65 * data_rate_mhz + 53 * 1000) / 8000 + 1; - timing->clk_hs_trail = (78 * data_rate_mhz + 7 * 1000) / 8000 + 1; - timing->clk_hs_zero = (330 * data_rate_mhz / (8 * 1000)) + 1 - - timing->clk_hs_prepare; - timing->clk_hs_exit = (118 * data_rate_mhz / (8 * 1000)) + 1; + timing->clk_hs_prepare = 70 * data_rate_mhz / (8 * 1000); + timing->clk_hs_post = timing->clk_hs_prepare + 8; + timing->clk_hs_trail = timing->clk_hs_prepare; + timing->clk_hs_zero = timing->clk_hs_trail * 4; + timing->clk_hs_exit = 2 * timing->clk_hs_trail; timcon0 = FIELD_PREP(LPX, timing->lpx) | FIELD_PREP(HS_PREP, timing->da_hs_prepare) | @@ -367,8 +368,8 @@ static void mtk_dsi_set_mode(struct mtk_dsi *dsi) static void mtk_dsi_set_vm_cmd(struct mtk_dsi *dsi) { - mtk_dsi_mask(dsi, DSI_VM_CMD_CON, VM_CMD_EN, VM_CMD_EN); - mtk_dsi_mask(dsi, DSI_VM_CMD_CON, TS_VFP_EN, TS_VFP_EN); + mtk_dsi_mask(dsi, dsi->driver_data->reg_vm_cmd_off, VM_CMD_EN, VM_CMD_EN); + mtk_dsi_mask(dsi, dsi->driver_data->reg_vm_cmd_off, TS_VFP_EN, TS_VFP_EN); } static void mtk_dsi_rxtx_control(struct mtk_dsi *dsi) @@ -714,7 +715,7 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi) if (dsi->driver_data->has_shadow_ctl) writel(FORCE_COMMIT | BYPASS_SHADOW, - dsi->regs + DSI_SHADOW_DEBUG); + dsi->regs + dsi->driver_data->reg_shadow_dbg_off); mtk_dsi_reset_engine(dsi); mtk_dsi_phy_timconfig(dsi); @@ -1263,26 +1264,36 @@ static void mtk_dsi_remove(struct platform_device *pdev) static const struct mtk_dsi_driver_data mt8173_dsi_driver_data = { .reg_cmdq_off = 0x200, + .reg_vm_cmd_off = 0x130, + .reg_shadow_dbg_off = 0x190 }; static const struct mtk_dsi_driver_data mt2701_dsi_driver_data = { .reg_cmdq_off = 0x180, + .reg_vm_cmd_off = 0x130, + .reg_shadow_dbg_off = 0x190 }; static const struct mtk_dsi_driver_data mt8183_dsi_driver_data = { .reg_cmdq_off = 0x200, + .reg_vm_cmd_off = 0x130, + .reg_shadow_dbg_off = 0x190, .has_shadow_ctl = true, .has_size_ctl = true, }; static const struct mtk_dsi_driver_data mt8186_dsi_driver_data = { .reg_cmdq_off = 0xd00, + .reg_vm_cmd_off = 0x200, + .reg_shadow_dbg_off = 0xc00, .has_shadow_ctl = true, .has_size_ctl = true, }; static const struct mtk_dsi_driver_data mt8188_dsi_driver_data = { .reg_cmdq_off = 0xd00, + .reg_vm_cmd_off = 0x200, + .reg_shadow_dbg_off = 0xc00, .has_shadow_ctl = true, .has_size_ctl = true, .cmdq_long_packet_ctl = true, diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 70dc1d4460ad..ca82bc829cb9 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1660,7 +1660,6 @@ static const struct hdmi_codec_ops mtk_hdmi_audio_codec_ops = { .mute_stream = mtk_hdmi_audio_mute, .get_eld = mtk_hdmi_audio_get_eld, .hook_plugged_cb = mtk_hdmi_audio_hook_plugged_cb, - .no_capture_mute = 1, }; static int mtk_hdmi_register_audio_driver(struct device *dev) @@ -1671,6 +1670,7 @@ static int mtk_hdmi_register_audio_driver(struct device *dev) .max_i2s_channels = 2, .i2s = 1, .data = hdmi, + .no_capture_mute = 1, }; struct platform_device *pdev; diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index f274d9430cc3..5df20cbeafb8 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -78,6 +78,7 @@ msm-display-$(CONFIG_DRM_MSM_DPU) += \ disp/dpu1/dpu_hw_catalog.o \ disp/dpu1/dpu_hw_cdm.o \ disp/dpu1/dpu_hw_ctl.o \ + disp/dpu1/dpu_hw_cwb.o \ disp/dpu1/dpu_hw_dsc.o \ disp/dpu1/dpu_hw_dsc_1_2.o \ disp/dpu1/dpu_hw_interrupts.o \ diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 50c490b492f0..f1b18a6663f7 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -251,8 +251,8 @@ static int a4xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A4XX_UCHE_CACHE_WAYS_VFD, 0x07); /* Disable L2 bypass to avoid UCHE out of bounds errors */ - gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_LO, 0xffff0000); - gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_HI, 0xffff0000); + gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_LO, lower_32_bits(adreno_gpu->uche_trap_base)); + gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_HI, upper_32_bits(adreno_gpu->uche_trap_base)); gpu_write(gpu, REG_A4XX_CP_DEBUG, (1 << 25) | (adreno_is_a420(adreno_gpu) ? (1 << 29) : 0)); @@ -693,6 +693,8 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) if (ret) goto fail; + adreno_gpu->uche_trap_base = 0xffff0000ffff0000ull; + if (!gpu->aspace) { /* TODO we think it is possible to configure the GPU to * restrict access to VRAM carveout. But the required diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index ee89db72e36e..71dca78cd7a5 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -750,10 +750,10 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A5XX_UCHE_CACHE_WAYS, 0x02); /* Disable L2 bypass in the UCHE */ - gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_LO, 0xFFFF0000); - gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_HI, 0x0001FFFF); - gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_LO, 0xFFFF0000); - gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_HI, 0x0001FFFF); + gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_LO, lower_32_bits(adreno_gpu->uche_trap_base)); + gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_HI, upper_32_bits(adreno_gpu->uche_trap_base)); + gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_LO, lower_32_bits(adreno_gpu->uche_trap_base)); + gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_HI, upper_32_bits(adreno_gpu->uche_trap_base)); /* Set the GMEM VA range (0 to gpu->gmem) */ gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MIN_LO, 0x00100000); @@ -1760,11 +1760,6 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) unsigned int nr_rings; int ret; - if (!pdev) { - DRM_DEV_ERROR(dev->dev, "No A5XX device is defined\n"); - return ERR_PTR(-ENXIO); - } - a5xx_gpu = kzalloc(sizeof(*a5xx_gpu), GFP_KERNEL); if (!a5xx_gpu) return ERR_PTR(-ENOMEM); @@ -1805,5 +1800,7 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) adreno_gpu->ubwc_config.macrotile_mode = 0; adreno_gpu->ubwc_config.ubwc_swizzle = 0x7; + adreno_gpu->uche_trap_base = 0x0001ffffffff0000ull; + return gpu; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 0c560e84ad5a..edffb7737a97 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -1388,6 +1388,17 @@ static const struct adreno_info a7xx_gpus[] = { .pwrup_reglist = &a7xx_pwrup_reglist, .gmu_chipid = 0x7020100, .gmu_cgc_mode = 0x00020202, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(3), + .perfmode_bw = 16500000, + }, + { /* sentinel */ }, + }, }, .address_space_size = SZ_16G, .preempt_record_size = 4192 * SZ_1K, @@ -1432,6 +1443,17 @@ static const struct adreno_info a7xx_gpus[] = { .pwrup_reglist = &a7xx_pwrup_reglist, .gmu_chipid = 0x7090100, .gmu_cgc_mode = 0x00020202, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(2), + .perfmode_bw = 10687500, + }, + { /* sentinel */ }, + }, }, .address_space_size = SZ_16G, .preempt_record_size = 3572 * SZ_1K, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 14db7376c712..65d38b25c070 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include "a6xx_gpu.h" @@ -109,9 +110,11 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, bool suspended) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const struct a6xx_info *info = adreno_gpu->info->a6xx; struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct a6xx_gmu *gmu = &a6xx_gpu->gmu; u32 perf_index; + u32 bw_index = 0; unsigned long gpu_freq; int ret = 0; @@ -124,6 +127,37 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, if (gpu_freq == gmu->gpu_freqs[perf_index]) break; + /* If enabled, find the corresponding DDR bandwidth index */ + if (info->bcms && gmu->nr_gpu_bws > 1) { + unsigned int bw = dev_pm_opp_get_bw(opp, true, 0); + + for (bw_index = 0; bw_index < gmu->nr_gpu_bws - 1; bw_index++) { + if (bw == gmu->gpu_bw_table[bw_index]) + break; + } + + /* Vote AB as a fraction of the max bandwidth, starting from A750 */ + if (bw && adreno_is_a750_family(adreno_gpu)) { + u64 tmp; + + /* For now, vote for 25% of the bandwidth */ + tmp = bw * 25; + do_div(tmp, 100); + + /* + * The AB vote consists of a 16 bit wide quantized level + * against the maximum supported bandwidth. + * Quantization can be calculated as below: + * vote = (bandwidth * 2^16) / max bandwidth + */ + tmp *= MAX_AB_VOTE; + do_div(tmp, gmu->gpu_bw_table[gmu->nr_gpu_bws - 1]); + + bw_index |= AB_VOTE(clamp(tmp, 1, MAX_AB_VOTE)); + bw_index |= AB_VOTE_ENABLE; + } + } + gmu->current_perf_index = perf_index; gmu->freq = gmu->gpu_freqs[perf_index]; @@ -139,8 +173,10 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, return; if (!gmu->legacy) { - a6xx_hfi_set_freq(gmu, perf_index); - dev_pm_opp_set_opp(&gpu->pdev->dev, opp); + a6xx_hfi_set_freq(gmu, perf_index, bw_index); + /* With Bandwidth voting, we now vote for all resources, so skip OPP set */ + if (!bw_index) + dev_pm_opp_set_opp(&gpu->pdev->dev, opp); return; } @@ -729,6 +765,7 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) const struct firmware *fw_image = adreno_gpu->fw[ADRENO_FW_GMU]; const struct block_header *blk; u32 reg_offset; + u32 ver; u32 itcm_base = 0x00000000; u32 dtcm_base = 0x00040000; @@ -775,6 +812,12 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) } } + ver = gmu_read(gmu, REG_A6XX_GMU_CORE_FW_VERSION); + DRM_INFO("Loaded GMU firmware v%u.%u.%u\n", + FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver), + FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver), + FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver)); + return 0; } @@ -1265,7 +1308,7 @@ static int a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo, bo->virt = msm_gem_get_vaddr(bo->obj); bo->size = size; - msm_gem_object_set_name(bo->obj, name); + msm_gem_object_set_name(bo->obj, "%s", name); return 0; } @@ -1287,6 +1330,104 @@ static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu) return 0; } +/** + * struct bcm_db - Auxiliary data pertaining to each Bus Clock Manager (BCM) + * @unit: divisor used to convert bytes/sec bw value to an RPMh msg + * @width: multiplier used to convert bytes/sec bw value to an RPMh msg + * @vcd: virtual clock domain that this bcm belongs to + * @reserved: reserved field + */ +struct bcm_db { + __le32 unit; + __le16 width; + u8 vcd; + u8 reserved; +}; + +static int a6xx_gmu_rpmh_bw_votes_init(struct adreno_gpu *adreno_gpu, + const struct a6xx_info *info, + struct a6xx_gmu *gmu) +{ + const struct bcm_db *bcm_data[GMU_MAX_BCMS] = { 0 }; + unsigned int bcm_index, bw_index, bcm_count = 0; + + /* Retrieve BCM data from cmd-db */ + for (bcm_index = 0; bcm_index < GMU_MAX_BCMS; bcm_index++) { + const struct a6xx_bcm *bcm = &info->bcms[bcm_index]; + size_t count; + + /* Stop at NULL terminated bcm entry */ + if (!bcm->name) + break; + + bcm_data[bcm_index] = cmd_db_read_aux_data(bcm->name, &count); + if (IS_ERR(bcm_data[bcm_index])) + return PTR_ERR(bcm_data[bcm_index]); + + if (!count) { + dev_err(gmu->dev, "invalid BCM '%s' aux data size\n", + bcm->name); + return -EINVAL; + } + + bcm_count++; + } + + /* Generate BCM votes values for each bandwidth & BCM */ + for (bw_index = 0; bw_index < gmu->nr_gpu_bws; bw_index++) { + u32 *data = gmu->gpu_ib_votes[bw_index]; + u32 bw = gmu->gpu_bw_table[bw_index]; + + /* Calculations loosely copied from bcm_aggregate() & tcs_cmd_gen() */ + for (bcm_index = 0; bcm_index < bcm_count; bcm_index++) { + const struct a6xx_bcm *bcm = &info->bcms[bcm_index]; + bool commit = false; + u64 peak; + u32 vote; + + if (bcm_index == bcm_count - 1 || + (bcm_data[bcm_index + 1] && + bcm_data[bcm_index]->vcd != bcm_data[bcm_index + 1]->vcd)) + commit = true; + + if (!bw) { + data[bcm_index] = BCM_TCS_CMD(commit, false, 0, 0); + continue; + } + + if (bcm->fixed) { + u32 perfmode = 0; + + /* GMU on A6xx votes perfmode on all valid bandwidth */ + if (!adreno_is_a7xx(adreno_gpu) || + (bcm->perfmode_bw && bw >= bcm->perfmode_bw)) + perfmode = bcm->perfmode; + + data[bcm_index] = BCM_TCS_CMD(commit, true, 0, perfmode); + continue; + } + + /* Multiply the bandwidth by the width of the connection */ + peak = (u64)bw * le16_to_cpu(bcm_data[bcm_index]->width); + do_div(peak, bcm->buswidth); + + /* Input bandwidth value is in KBps, scale the value to BCM unit */ + peak *= 1000; + do_div(peak, le32_to_cpu(bcm_data[bcm_index]->unit)); + + vote = clamp(peak, 1, BCM_TCS_CMD_VOTE_MASK); + + /* GMUs on A7xx votes on both x & y */ + if (adreno_is_a7xx(adreno_gpu)) + data[bcm_index] = BCM_TCS_CMD(commit, true, vote, vote); + else + data[bcm_index] = BCM_TCS_CMD(commit, true, 0, vote); + } + } + + return 0; +} + /* Return the 'arc-level' for the given frequency */ static unsigned int a6xx_gmu_get_arc_level(struct device *dev, unsigned long freq) @@ -1390,12 +1531,15 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, * The GMU votes with the RPMh for itself and on behalf of the GPU but we need * to construct the list of votes on the CPU and send it over. Query the RPMh * voltage levels and build the votes + * The GMU can also vote for DDR interconnects, use the OPP bandwidth entries + * and BCM parameters to build the votes. */ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + const struct a6xx_info *info = adreno_gpu->info->a6xx; struct msm_gpu *gpu = &adreno_gpu->base; int ret; @@ -1407,6 +1551,10 @@ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) ret |= a6xx_gmu_rpmh_arc_votes_init(gmu->dev, gmu->cx_arc_votes, gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl"); + /* Build the interconnect votes */ + if (info->bcms && gmu->nr_gpu_bws > 1) + ret |= a6xx_gmu_rpmh_bw_votes_init(adreno_gpu, info, gmu); + return ret; } @@ -1442,10 +1590,43 @@ static int a6xx_gmu_build_freq_table(struct device *dev, unsigned long *freqs, return index; } +static int a6xx_gmu_build_bw_table(struct device *dev, unsigned long *bandwidths, + u32 size) +{ + int count = dev_pm_opp_get_opp_count(dev); + struct dev_pm_opp *opp; + int i, index = 0; + unsigned int bandwidth = 1; + + /* + * The OPP table doesn't contain the "off" bandwidth level so we need to + * add 1 to the table size to account for it + */ + + if (WARN(count + 1 > size, + "The GMU bandwidth table is being truncated\n")) + count = size - 1; + + /* Set the "off" bandwidth */ + bandwidths[index++] = 0; + + for (i = 0; i < count; i++) { + opp = dev_pm_opp_find_bw_ceil(dev, &bandwidth, 0); + if (IS_ERR(opp)) + break; + + dev_pm_opp_put(opp); + bandwidths[index++] = bandwidth++; + } + + return index; +} + static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + const struct a6xx_info *info = adreno_gpu->info->a6xx; struct msm_gpu *gpu = &adreno_gpu->base; int ret = 0; @@ -1472,6 +1653,14 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) gmu->current_perf_index = gmu->nr_gpu_freqs - 1; + /* + * The GMU also handles GPU Interconnect Votes so build a list + * of DDR bandwidths from the GPU OPP table + */ + if (info->bcms) + gmu->nr_gpu_bws = a6xx_gmu_build_bw_table(&gpu->pdev->dev, + gmu->gpu_bw_table, ARRAY_SIZE(gmu->gpu_bw_table)); + /* Build the list of RPMh votes that we'll send to the GMU */ return a6xx_gmu_rpmh_votes_init(gmu); } @@ -1603,7 +1792,9 @@ int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) gmu->dev = &pdev->dev; - of_dma_configure(gmu->dev, node, true); + ret = of_dma_configure(gmu->dev, node, true); + if (ret) + return ret; pm_runtime_enable(gmu->dev); @@ -1668,7 +1859,9 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) gmu->dev = &pdev->dev; - of_dma_configure(gmu->dev, node, true); + ret = of_dma_configure(gmu->dev, node, true); + if (ret) + return ret; /* Fow now, don't do anything fancy until we get our feet under us */ gmu->idle_level = GMU_IDLE_STATE_ACTIVE; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index b4a79f88ccf4..0c888b326cfb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -19,6 +19,18 @@ struct a6xx_gmu_bo { u64 iova; }; +#define GMU_MAX_GX_FREQS 16 +#define GMU_MAX_CX_FREQS 4 +#define GMU_MAX_BCMS 3 + +struct a6xx_bcm { + char *name; + unsigned int buswidth; + bool fixed; + unsigned int perfmode; + unsigned int perfmode_bw; +}; + /* * These define the different GMU wake up options - these define how both the * CPU and the GMU bring up the hardware @@ -79,12 +91,16 @@ struct a6xx_gmu { int current_perf_index; int nr_gpu_freqs; - unsigned long gpu_freqs[16]; - u32 gx_arc_votes[16]; + unsigned long gpu_freqs[GMU_MAX_GX_FREQS]; + u32 gx_arc_votes[GMU_MAX_GX_FREQS]; + + int nr_gpu_bws; + unsigned long gpu_bw_table[GMU_MAX_GX_FREQS]; + u32 gpu_ib_votes[GMU_MAX_GX_FREQS][GMU_MAX_BCMS]; int nr_gmu_freqs; - unsigned long gmu_freqs[4]; - u32 cx_arc_votes[4]; + unsigned long gmu_freqs[GMU_MAX_CX_FREQS]; + u32 cx_arc_votes[GMU_MAX_CX_FREQS]; unsigned long freq; @@ -193,7 +209,7 @@ void a6xx_hfi_init(struct a6xx_gmu *gmu); int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state); void a6xx_hfi_stop(struct a6xx_gmu *gmu); int a6xx_hfi_send_prep_slumber(struct a6xx_gmu *gmu); -int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, int index); +int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, u32 perf_index, u32 bw_index); bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu); bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 019610341df1..0ae29a7c8a4d 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1123,12 +1123,12 @@ static int hw_init(struct msm_gpu *gpu) /* Disable L2 bypass in the UCHE */ if (adreno_is_a7xx(adreno_gpu)) { - gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, 0x0001fffffffff000llu); - gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, 0x0001fffffffff000llu); + gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base); } else { - gpu_write64(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX, 0x0001ffffffffffc0llu); - gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, 0x0001fffffffff000llu); - gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, 0x0001fffffffff000llu); + gpu_write64(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX, adreno_gpu->uche_trap_base + 0xfc0); + gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base); } if (!(adreno_is_a650_family(adreno_gpu) || @@ -2533,6 +2533,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) } } + adreno_gpu->uche_trap_base = 0x1fffffffff000ull; + if (gpu->aspace) msm_mmu_set_fault_handler(gpu->aspace->mmu, gpu, a6xx_fault_handler); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 4aceffb6aae8..9201a53dd341 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -44,6 +44,7 @@ struct a6xx_info { u32 gmu_chipid; u32 gmu_cgc_mode; u32 prim_fifo_threshold; + const struct a6xx_bcm *bcms; }; struct a6xx_gpu { diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index cb8844ed46b2..0989aee3dd2c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -6,6 +6,7 @@ #include #include +#include #include "a6xx_gmu.h" #include "a6xx_gmu.xml.h" @@ -259,6 +260,48 @@ static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu) NULL, 0); } +static void a6xx_generate_bw_table(const struct a6xx_info *info, struct a6xx_gmu *gmu, + struct a6xx_hfi_msg_bw_table *msg) +{ + unsigned int i, j; + + for (i = 0; i < GMU_MAX_BCMS; i++) { + if (!info->bcms[i].name) + break; + msg->ddr_cmds_addrs[i] = cmd_db_read_addr(info->bcms[i].name); + } + msg->ddr_cmds_num = i; + + for (i = 0; i < gmu->nr_gpu_bws; ++i) + for (j = 0; j < msg->ddr_cmds_num; j++) + msg->ddr_cmds_data[i][j] = gmu->gpu_ib_votes[i][j]; + msg->bw_level_num = gmu->nr_gpu_bws; + + /* Compute the wait bitmask with each BCM having the commit bit */ + msg->ddr_wait_bitmask = 0; + for (j = 0; j < msg->ddr_cmds_num; j++) + if (msg->ddr_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK) + msg->ddr_wait_bitmask |= BIT(j); + + /* + * These are the CX (CNOC) votes - these are used by the GMU + * The 'CN0' BCM is used on all targets, and votes are basically + * 'off' and 'on' states with first bit to enable the path. + */ + + msg->cnoc_cmds_addrs[0] = cmd_db_read_addr("CN0"); + msg->cnoc_cmds_num = 1; + + msg->cnoc_cmds_data[0][0] = BCM_TCS_CMD(true, false, 0, 0); + msg->cnoc_cmds_data[1][0] = BCM_TCS_CMD(true, true, 0, BIT(0)); + + /* Compute the wait bitmask with each BCM having the commit bit */ + msg->cnoc_wait_bitmask = 0; + for (j = 0; j < msg->cnoc_cmds_num; j++) + if (msg->cnoc_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK) + msg->cnoc_wait_bitmask |= BIT(j); +} + static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg) { /* Send a single "off" entry since the 618 GMU doesn't do bus scaling */ @@ -664,6 +707,7 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu) struct a6xx_hfi_msg_bw_table *msg; struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + const struct a6xx_info *info = adreno_gpu->info->a6xx; if (gmu->bw_table) goto send; @@ -672,7 +716,9 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu) if (!msg) return -ENOMEM; - if (adreno_is_a618(adreno_gpu)) + if (info->bcms && gmu->nr_gpu_bws > 1) + a6xx_generate_bw_table(info, gmu, msg); + else if (adreno_is_a618(adreno_gpu)) a618_build_bw_table(msg); else if (adreno_is_a619(adreno_gpu)) a619_build_bw_table(msg); @@ -726,13 +772,13 @@ static int a6xx_hfi_send_core_fw_start(struct a6xx_gmu *gmu) sizeof(msg), NULL, 0); } -int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, int index) +int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, u32 freq_index, u32 bw_index) { struct a6xx_hfi_gx_bw_perf_vote_cmd msg = { 0 }; msg.ack_type = 1; /* blocking */ - msg.freq = index; - msg.bw = 0; /* TODO: bus scaling */ + msg.freq = freq_index; + msg.bw = bw_index; return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_GX_BW_PERF_VOTE, &msg, sizeof(msg), NULL, 0); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h index 528110169398..52ba4a07d7b9 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h @@ -173,6 +173,11 @@ struct a6xx_hfi_gx_bw_perf_vote_cmd { u32 bw; }; +#define AB_VOTE_MASK GENMASK(31, 16) +#define MAX_AB_VOTE (FIELD_MAX(AB_VOTE_MASK) - 1) +#define AB_VOTE(vote) FIELD_PREP(AB_VOTE_MASK, (vote)) +#define AB_VOTE_ENABLE BIT(8) + #define HFI_H2F_MSG_PREPARE_SLUMBER 33 struct a6xx_hfi_prep_slumber_cmd { diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 75f5367e73ca..1238f3265978 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -310,10 +310,11 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx, uint32_t param, uint64_t *value, uint32_t *len) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct drm_device *drm = gpu->dev; /* No pointer params yet */ if (*len != 0) - return -EINVAL; + return UERR(EINVAL, drm, "invalid len"); switch (param) { case MSM_PARAM_GPU_ID: @@ -365,12 +366,12 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx, return 0; case MSM_PARAM_VA_START: if (ctx->aspace == gpu->aspace) - return -EINVAL; + return UERR(EINVAL, drm, "requires per-process pgtables"); *value = ctx->aspace->va_start; return 0; case MSM_PARAM_VA_SIZE: if (ctx->aspace == gpu->aspace) - return -EINVAL; + return UERR(EINVAL, drm, "requires per-process pgtables"); *value = ctx->aspace->va_size; return 0; case MSM_PARAM_HIGHEST_BANK_BIT: @@ -385,15 +386,19 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx, case MSM_PARAM_MACROTILE_MODE: *value = adreno_gpu->ubwc_config.macrotile_mode; return 0; + case MSM_PARAM_UCHE_TRAP_BASE: + *value = adreno_gpu->uche_trap_base; + return 0; default: - DBG("%s: invalid param: %u", gpu->name, param); - return -EINVAL; + return UERR(EINVAL, drm, "%s: invalid param: %u", gpu->name, param); } } int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, uint32_t param, uint64_t value, uint32_t len) { + struct drm_device *drm = gpu->dev; + switch (param) { case MSM_PARAM_COMM: case MSM_PARAM_CMDLINE: @@ -401,11 +406,11 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, * that should be a reasonable upper bound */ if (len > PAGE_SIZE) - return -EINVAL; + return UERR(EINVAL, drm, "invalid len"); break; default: if (len != 0) - return -EINVAL; + return UERR(EINVAL, drm, "invalid len"); } switch (param) { @@ -434,11 +439,10 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, } case MSM_PARAM_SYSPROF: if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + return UERR(EPERM, drm, "invalid permissions"); return msm_file_private_set_sysprof(ctx, gpu, value); default: - DBG("%s: invalid param: %u", gpu->name, param); - return -EINVAL; + return UERR(EINVAL, drm, "%s: invalid param: %u", gpu->name, param); } } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index e71f420f8b3a..dcf454629ce0 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -253,6 +253,8 @@ struct adreno_gpu { bool gmu_is_wrapper; bool has_ray_tracing; + + u64 uche_trap_base; }; #define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base) @@ -559,6 +561,11 @@ static inline int adreno_is_a740_family(struct adreno_gpu *gpu) gpu->info->family == ADRENO_7XX_GEN3; } +static inline int adreno_is_a750_family(struct adreno_gpu *gpu) +{ + return gpu->info->family == ADRENO_7XX_GEN3; +} + static inline int adreno_is_a7xx(struct adreno_gpu *gpu) { /* Update with non-fake (i.e. non-A702) Gen 7 GPUs */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h index eb5dfff2ec4f..bcb39807fe61 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h @@ -160,6 +160,7 @@ static const struct dpu_lm_cfg sm8650_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, .pingpong = PINGPONG_2, + .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, .base = 0x47000, .len = 0x400, @@ -167,6 +168,7 @@ static const struct dpu_lm_cfg sm8650_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, .pingpong = PINGPONG_3, + .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, .base = 0x48000, .len = 0x400, @@ -252,25 +254,25 @@ static const struct dpu_pingpong_cfg sm8650_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, .base = 0x66000, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, .base = 0x66400, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_8", .id = PINGPONG_8, + .name = "pingpong_cwb_2", .id = PINGPONG_CWB_2, .base = 0x7e000, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_4, }, { - .name = "pingpong_9", .id = PINGPONG_9, + .name = "pingpong_cwb_3", .id = PINGPONG_CWB_3, .base = 0x7e400, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, @@ -350,6 +352,25 @@ static const struct dpu_wb_cfg sm8650_wb[] = { }, }; +static const struct dpu_cwb_cfg sm8650_cwb[] = { + { + .name = "cwb_0", .id = CWB_0, + .base = 0x66200, .len = 0x8, + }, + { + .name = "cwb_1", .id = CWB_1, + .base = 0x66600, .len = 0x8, + }, + { + .name = "cwb_2", .id = CWB_2, + .base = 0x7E200, .len = 0x8, + }, + { + .name = "cwb_3", .id = CWB_3, + .base = 0x7E600, .len = 0x8, + }, +}; + static const struct dpu_intf_cfg sm8650_intf[] = { { .name = "intf_0", .id = INTF_0, @@ -447,6 +468,8 @@ const struct dpu_mdss_cfg dpu_sm8650_cfg = { .merge_3d = sm8650_merge_3d, .wb_count = ARRAY_SIZE(sm8650_wb), .wb = sm8650_wb, + .cwb_count = ARRAY_SIZE(sm8650_cwb), + .cwb = sm8650_cwb, .intf_count = ARRAY_SIZE(sm8650_intf), .intf = sm8650_intf, .vbif_count = ARRAY_SIZE(sm8650_vbif), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h index cbbdaebe357e..daef07924886 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h @@ -65,6 +65,54 @@ static const struct dpu_sspp_cfg sdm670_sspp[] = { }, }; +static const struct dpu_lm_cfg sdm670_lm[] = { + { + .name = "lm_0", .id = LM_0, + .base = 0x44000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_1, + .pingpong = PINGPONG_0, + .dspp = DSPP_0, + }, { + .name = "lm_1", .id = LM_1, + .base = 0x45000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_0, + .pingpong = PINGPONG_1, + .dspp = DSPP_1, + }, { + .name = "lm_2", .id = LM_2, + .base = 0x46000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_5, + .pingpong = PINGPONG_2, + }, { + .name = "lm_5", .id = LM_5, + .base = 0x49000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_2, + .pingpong = PINGPONG_3, + }, +}; + +static const struct dpu_dspp_cfg sdm670_dspp[] = { + { + .name = "dspp_0", .id = DSPP_0, + .base = 0x54000, .len = 0x1800, + .features = DSPP_SC7180_MASK, + .sblk = &sdm845_dspp_sblk, + }, { + .name = "dspp_1", .id = DSPP_1, + .base = 0x56000, .len = 0x1800, + .features = DSPP_SC7180_MASK, + .sblk = &sdm845_dspp_sblk, + }, +}; + static const struct dpu_dsc_cfg sdm670_dsc[] = { { .name = "dsc_0", .id = DSC_0, @@ -88,8 +136,10 @@ const struct dpu_mdss_cfg dpu_sdm670_cfg = { .ctl = sdm845_ctl, .sspp_count = ARRAY_SIZE(sdm670_sspp), .sspp = sdm670_sspp, - .mixer_count = ARRAY_SIZE(sdm845_lm), - .mixer = sdm845_lm, + .mixer_count = ARRAY_SIZE(sdm670_lm), + .mixer = sdm670_lm, + .dspp_count = ARRAY_SIZE(sdm670_dspp), + .dspp = sdm670_dspp, .pingpong_count = ARRAY_SIZE(sdm845_pp), .pingpong = sdm845_pp, .dsc_count = ARRAY_SIZE(sdm670_dsc), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 6ccfde82fecd..421afacb7248 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -164,6 +164,7 @@ static const struct dpu_lm_cfg sm8150_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, .pingpong = PINGPONG_2, + .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, .base = 0x47000, .len = 0x320, @@ -171,6 +172,7 @@ static const struct dpu_lm_cfg sm8150_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, .pingpong = PINGPONG_3, + .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, .base = 0x48000, .len = 0x320, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index bab19ddd1d4f..641023b102bf 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -163,6 +163,7 @@ static const struct dpu_lm_cfg sc8180x_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, .pingpong = PINGPONG_2, + .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, .base = 0x47000, .len = 0x320, @@ -170,6 +171,7 @@ static const struct dpu_lm_cfg sc8180x_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, .pingpong = PINGPONG_3, + .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, .base = 0x48000, .len = 0x320, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h new file mode 100644 index 000000000000..621a2140f675 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h @@ -0,0 +1,254 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DPU_5_3_SM6150_H +#define _DPU_5_3_SM6150_H + +static const struct dpu_caps sm6150_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0x9, + .has_dim_layer = true, + .has_idle_pc = true, + .max_linewidth = 2160, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, + .max_hdeci_exp = MAX_HORZ_DECIMATION, + .max_vdeci_exp = MAX_VERT_DECIMATION, +}; + +static const struct dpu_mdp_cfg sm6150_mdp = { + .name = "top_0", + .base = 0x0, .len = 0x45c, + .features = 0, + .clk_ctrls = { + [DPU_CLK_CTRL_VIG0] = { .reg_off = 0x2ac, .bit_off = 0 }, + [DPU_CLK_CTRL_DMA0] = { .reg_off = 0x2ac, .bit_off = 8 }, + [DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 }, + [DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8 }, + [DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8 }, + }, +}; + +static const struct dpu_ctl_cfg sm6150_ctl[] = { + { + .name = "ctl_0", .id = CTL_0, + .base = 0x1000, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), + }, { + .name = "ctl_1", .id = CTL_1, + .base = 0x1200, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), + }, { + .name = "ctl_2", .id = CTL_2, + .base = 0x1400, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11), + }, { + .name = "ctl_3", .id = CTL_3, + .base = 0x1600, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12), + }, { + .name = "ctl_4", .id = CTL_4, + .base = 0x1800, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 13), + }, { + .name = "ctl_5", .id = CTL_5, + .base = 0x1a00, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 23), + }, +}; + +static const struct dpu_sspp_cfg sm6150_sspp[] = { + { + .name = "sspp_0", .id = SSPP_VIG0, + .base = 0x4000, .len = 0x1f0, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_2_4, + .xin_id = 0, + .type = SSPP_TYPE_VIG, + .clk_ctrl = DPU_CLK_CTRL_VIG0, + }, { + .name = "sspp_8", .id = SSPP_DMA0, + .base = 0x24000, .len = 0x1f0, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 1, + .type = SSPP_TYPE_DMA, + .clk_ctrl = DPU_CLK_CTRL_DMA0, + }, { + .name = "sspp_9", .id = SSPP_DMA1, + .base = 0x26000, .len = 0x1f0, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 5, + .type = SSPP_TYPE_DMA, + .clk_ctrl = DPU_CLK_CTRL_DMA1, + }, { + .name = "sspp_10", .id = SSPP_DMA2, + .base = 0x28000, .len = 0x1f0, + .features = DMA_CURSOR_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 9, + .type = SSPP_TYPE_DMA, + .clk_ctrl = DPU_CLK_CTRL_DMA2, + }, { + .name = "sspp_11", .id = SSPP_DMA3, + .base = 0x2a000, .len = 0x1f0, + .features = DMA_CURSOR_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 13, + .type = SSPP_TYPE_DMA, + .clk_ctrl = DPU_CLK_CTRL_DMA3, + }, +}; + +static const struct dpu_lm_cfg sm6150_lm[] = { + { + .name = "lm_0", .id = LM_0, + .base = 0x44000, .len = 0x320, + .features = MIXER_QCM2290_MASK, + .sblk = &sdm845_lm_sblk, + .pingpong = PINGPONG_0, + .dspp = DSPP_0, + .lm_pair = LM_1, + }, { + .name = "lm_1", .id = LM_1, + .base = 0x45000, .len = 0x320, + .features = MIXER_QCM2290_MASK, + .sblk = &sdm845_lm_sblk, + .pingpong = PINGPONG_1, + .lm_pair = LM_0, + }, { + .name = "lm_2", .id = LM_2, + .base = 0x46000, .len = 0x320, + .features = MIXER_QCM2290_MASK, + .sblk = &sdm845_lm_sblk, + .pingpong = PINGPONG_2, + }, +}; + +static const struct dpu_dspp_cfg sm6150_dspp[] = { + { + .name = "dspp_0", .id = DSPP_0, + .base = 0x54000, .len = 0x1800, + .features = DSPP_SC7180_MASK, + .sblk = &sdm845_dspp_sblk, + }, +}; + +static const struct dpu_pingpong_cfg sm6150_pp[] = { + { + .name = "pingpong_0", .id = PINGPONG_0, + .base = 0x70000, .len = 0xd4, + .features = PINGPONG_SM8150_MASK, + .sblk = &sdm845_pp_sblk, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), + }, { + .name = "pingpong_1", .id = PINGPONG_1, + .base = 0x70800, .len = 0xd4, + .features = PINGPONG_SM8150_MASK, + .sblk = &sdm845_pp_sblk, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), + }, { + .name = "pingpong_2", .id = PINGPONG_2, + .base = 0x71000, .len = 0xd4, + .features = PINGPONG_SM8150_MASK, + .sblk = &sdm845_pp_sblk, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), + }, +}; + +static const struct dpu_intf_cfg sm6150_intf[] = { + { + .name = "intf_0", .id = INTF_0, + .base = 0x6a000, .len = 0x280, + .features = INTF_SC7180_MASK, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_0, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), + }, { + .name = "intf_1", .id = INTF_1, + .base = 0x6a800, .len = 0x2c0, + .features = INTF_SC7180_MASK, + .type = INTF_DSI, + .controller_id = MSM_DSI_CONTROLLER_0, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), + .intr_tear_rd_ptr = DPU_IRQ_IDX(MDP_INTF1_TEAR_INTR, 2), + }, { + .name = "intf_3", .id = INTF_3, + .base = 0x6b800, .len = 0x280, + .features = INTF_SC7180_MASK, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_1, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31), + }, +}; + +static const struct dpu_perf_cfg sm6150_perf_data = { + .max_bw_low = 4800000, + .max_bw_high = 4800000, + .min_core_ib = 2400000, + .min_llcc_ib = 0, + .min_dram_ib = 800000, + .min_prefill_lines = 24, + .danger_lut_tbl = {0xf, 0xffff, 0x0}, + .safe_lut_tbl = {0xfff8, 0xf000, 0xffff}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(sm8150_qos_linear), + .entries = sm8150_qos_linear + }, + {.nentry = ARRAY_SIZE(sc7180_qos_macrotile), + .entries = sc7180_qos_macrotile + }, + {.nentry = ARRAY_SIZE(sc7180_qos_nrt), + .entries = sc7180_qos_nrt + }, + /* TODO: macrotile-qseed is different from macrotile */ + }, + .cdp_cfg = { + {.rd_enable = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, +}; + +static const struct dpu_mdss_version sm6150_mdss_ver = { + .core_major_ver = 5, + .core_minor_ver = 3, +}; + +const struct dpu_mdss_cfg dpu_sm6150_cfg = { + .mdss_ver = &sm6150_mdss_ver, + .caps = &sm6150_dpu_caps, + .mdp = &sm6150_mdp, + .ctl_count = ARRAY_SIZE(sm6150_ctl), + .ctl = sm6150_ctl, + .sspp_count = ARRAY_SIZE(sm6150_sspp), + .sspp = sm6150_sspp, + .mixer_count = ARRAY_SIZE(sm6150_lm), + .mixer = sm6150_lm, + .dspp_count = ARRAY_SIZE(sm6150_dspp), + .dspp = sm6150_dspp, + .pingpong_count = ARRAY_SIZE(sm6150_pp), + .pingpong = sm6150_pp, + .intf_count = ARRAY_SIZE(sm6150_intf), + .intf = sm6150_intf, + .vbif_count = ARRAY_SIZE(sdm845_vbif), + .vbif = sdm845_vbif, + .perf = &sm6150_perf_data, +}; + +#endif diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h index a57d50b1f028..e8916ae826a6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h @@ -162,6 +162,7 @@ static const struct dpu_lm_cfg sm8250_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, .pingpong = PINGPONG_2, + .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, .base = 0x47000, .len = 0x320, @@ -169,6 +170,7 @@ static const struct dpu_lm_cfg sm8250_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, .pingpong = PINGPONG_3, + .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, .base = 0x48000, .len = 0x320, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index aced16e350da..f7c08e89c882 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -162,6 +162,7 @@ static const struct dpu_lm_cfg sm8350_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, .pingpong = PINGPONG_2, + .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, .base = 0x47000, .len = 0x320, @@ -169,6 +170,7 @@ static const struct dpu_lm_cfg sm8350_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, .pingpong = PINGPONG_3, + .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, .base = 0x48000, .len = 0x320, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index a1779c5597ae..08742472f9cc 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -257,13 +257,13 @@ static const struct dpu_pingpong_cfg sm8450_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, .base = 0x65800, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, .base = 0x65c00, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h index 907b4d7ceb47..76ec72a32378 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h @@ -256,13 +256,13 @@ static const struct dpu_pingpong_cfg sa8775p_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_6", .id = PINGPONG_CWB_0, .base = 0x65800, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_7", .id = PINGPONG_CWB_1, .base = 0x65c00, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index ad48defa154f..4d3787fceb72 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -160,6 +160,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, .pingpong = PINGPONG_2, + .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, .base = 0x47000, .len = 0x320, @@ -167,6 +168,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, .pingpong = PINGPONG_3, + .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, .base = 0x48000, .len = 0x320, @@ -251,13 +253,13 @@ static const struct dpu_pingpong_cfg sm8550_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, .base = 0x66000, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, .base = 0x66400, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h index a3e60ac70689..6b112e3d17da 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h @@ -159,6 +159,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, .pingpong = PINGPONG_2, + .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, .base = 0x47000, .len = 0x320, @@ -166,6 +167,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, .pingpong = PINGPONG_3, + .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, .base = 0x48000, .len = 0x320, @@ -251,13 +253,13 @@ static const struct dpu_pingpong_cfg x1e80100_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, .base = 0x66000, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, .base = 0x66400, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, @@ -389,8 +391,8 @@ static const struct dpu_intf_cfg x1e80100_intf[] = { .type = INTF_DP, .controller_id = MSM_DP_CONTROLLER_2, .prog_fetch_lines_worst_case = 24, - .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), - .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), }, { .name = "intf_7", .id = INTF_7, .base = 0x3b000, .len = 0x280, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 9f6ffd344693..7191b1a6d41b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -732,6 +732,13 @@ static int _dpu_crtc_check_and_setup_lm_bounds(struct drm_crtc *crtc, struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); int i; + /* if we cannot merge 2 LMs (no 3d mux) better to fail earlier + * before even checking the width after the split + */ + if (!dpu_kms->catalog->caps->has_3d_merge && + adj_mode->hdisplay > dpu_kms->catalog->caps->max_mixer_width) + return -E2BIG; + for (i = 0; i < cstate->num_mixers; i++) { struct drm_rect *r = &cstate->lm_bounds[i]; r->x1 = crtc_split_width * i; @@ -1182,6 +1189,49 @@ static bool dpu_crtc_needs_dirtyfb(struct drm_crtc_state *cstate) return false; } +static int dpu_crtc_reassign_planes(struct drm_crtc *crtc, struct drm_crtc_state *crtc_state) +{ + int total_planes = crtc->dev->mode_config.num_total_plane; + struct drm_atomic_state *state = crtc_state->state; + struct dpu_global_state *global_state; + struct drm_plane_state **states; + struct drm_plane *plane; + int ret; + + global_state = dpu_kms_get_global_state(crtc_state->state); + if (IS_ERR(global_state)) + return PTR_ERR(global_state); + + dpu_rm_release_all_sspp(global_state, crtc); + + if (!crtc_state->enable) + return 0; + + states = kcalloc(total_planes, sizeof(*states), GFP_KERNEL); + if (!states) + return -ENOMEM; + + drm_atomic_crtc_state_for_each_plane(plane, crtc_state) { + struct drm_plane_state *plane_state = + drm_atomic_get_plane_state(state, plane); + + if (IS_ERR(plane_state)) { + ret = PTR_ERR(plane_state); + goto done; + } + + states[plane_state->normalized_zpos] = plane_state; + } + + ret = dpu_assign_plane_resources(global_state, state, crtc, states, total_planes); + +done: + kfree(states); + return ret; + + return 0; +} + static int dpu_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { @@ -1197,6 +1247,13 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, bool needs_dirtyfb = dpu_crtc_needs_dirtyfb(crtc_state); + if (dpu_use_virtual_planes && + (crtc_state->planes_changed || crtc_state->zpos_changed)) { + rc = dpu_crtc_reassign_planes(crtc, crtc_state); + if (rc < 0) + return rc; + } + if (!crtc_state->enable || !drm_atomic_crtc_effectively_active(crtc_state)) { DRM_DEBUG_ATOMIC("crtc%d -> enable %d, active %d, skip atomic_check\n", crtc->base.id, crtc_state->enable, @@ -1251,6 +1308,12 @@ static enum drm_mode_status dpu_crtc_mode_valid(struct drm_crtc *crtc, { struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + /* if there is no 3d_mux block we cannot merge LMs so we cannot + * split the large layer into 2 LMs, filter out such modes + */ + if (!dpu_kms->catalog->caps->has_3d_merge && + mode->hdisplay > dpu_kms->catalog->caps->max_mixer_width) + return MODE_BAD_HVALUE; /* * max crtc width is equal to the max mixer width * 2 and max height is 4K */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 83de7564e2c1..5172ab4dea99 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -800,7 +800,7 @@ static int dpu_encoder_virt_atomic_check( if (!crtc_state->active_changed || crtc_state->enable) ret = dpu_rm_reserve(&dpu_kms->rm, global_state, - drm_enc, crtc_state, topology); + drm_enc, crtc_state, &topology); if (!ret) dpu_encoder_assign_crtc_resources(dpu_kms, drm_enc, global_state, crtc_state); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 2cbf41f33cc0..0b342c043875 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -765,6 +765,7 @@ static const struct dpu_qos_lut_entry sc7180_qos_nrt[] = { #include "catalog/dpu_5_0_sm8150.h" #include "catalog/dpu_5_1_sc8180x.h" #include "catalog/dpu_5_2_sm7150.h" +#include "catalog/dpu_5_3_sm6150.h" #include "catalog/dpu_5_4_sm6125.h" #include "catalog/dpu_6_0_sm8250.h" diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index c701d18c3522..4cea19e1a203 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -613,6 +613,16 @@ struct dpu_wb_cfg { enum dpu_clk_ctrl_type clk_ctrl; }; +/* + * struct dpu_cwb_cfg : MDP CWB mux instance info + * @id: enum identifying this block + * @base: register base offset to mdss + * @features bit mask identifying sub-blocks/features + */ +struct dpu_cwb_cfg { + DPU_HW_BLK_INFO; +}; + /** * struct dpu_vbif_dynamic_ot_cfg - dynamic OT setting * @pps pixel per seconds @@ -815,6 +825,9 @@ struct dpu_mdss_cfg { u32 dspp_count; const struct dpu_dspp_cfg *dspp; + u32 cwb_count; + const struct dpu_cwb_cfg *cwb; + /* Add additional block data structures here */ const struct dpu_perf_cfg *perf; @@ -839,6 +852,7 @@ extern const struct dpu_mdss_cfg dpu_sm8250_cfg; extern const struct dpu_mdss_cfg dpu_sc7180_cfg; extern const struct dpu_mdss_cfg dpu_sm6115_cfg; extern const struct dpu_mdss_cfg dpu_sm6125_cfg; +extern const struct dpu_mdss_cfg dpu_sm6150_cfg; extern const struct dpu_mdss_cfg dpu_sm6350_cfg; extern const struct dpu_mdss_cfg dpu_qcm2290_cfg; extern const struct dpu_mdss_cfg dpu_sm6375_cfg; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.c new file mode 100644 index 000000000000..ae785f4ff0d4 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved + */ + +#include +#include "dpu_hw_cwb.h" + +#include + +#define CWB_MUX 0x000 +#define CWB_MODE 0x004 + +/* CWB mux block bit definitions */ +#define CWB_MUX_MASK GENMASK(3, 0) +#define CWB_MODE_MASK GENMASK(2, 0) + +static void dpu_hw_cwb_config(struct dpu_hw_cwb *ctx, + struct dpu_hw_cwb_setup_cfg *cwb_cfg) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + int cwb_mux_cfg = 0xF; + enum dpu_pingpong pp; + enum cwb_mode_input input; + + if (!cwb_cfg) + return; + + input = cwb_cfg->input; + pp = cwb_cfg->pp_idx; + + if (input >= INPUT_MODE_MAX) + return; + + /* + * The CWB_MUX register takes the pingpong index for the real-time + * display + */ + if ((pp != PINGPONG_NONE) && (pp < PINGPONG_MAX)) + cwb_mux_cfg = FIELD_PREP(CWB_MUX_MASK, pp - PINGPONG_0); + + input = FIELD_PREP(CWB_MODE_MASK, input); + + DPU_REG_WRITE(c, CWB_MUX, cwb_mux_cfg); + DPU_REG_WRITE(c, CWB_MODE, input); +} + +/** + * dpu_hw_cwb_init() - Initializes the writeback hw driver object with cwb. + * @dev: Corresponding device for devres management + * @cfg: wb_path catalog entry for which driver object is required + * @addr: mapped register io address of MDP + * Return: Error code or allocated dpu_hw_wb context + */ +struct dpu_hw_cwb *dpu_hw_cwb_init(struct drm_device *dev, + const struct dpu_cwb_cfg *cfg, + void __iomem *addr) +{ + struct dpu_hw_cwb *c; + + if (!addr) + return ERR_PTR(-EINVAL); + + c = drmm_kzalloc(dev, sizeof(*c), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + c->hw.blk_addr = addr + cfg->base; + c->hw.log_mask = DPU_DBG_MASK_CWB; + + c->idx = cfg->id; + c->ops.config_cwb = dpu_hw_cwb_config; + + return c; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.h new file mode 100644 index 000000000000..96b6edf6b2bb --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved + */ + +#ifndef _DPU_HW_CWB_H +#define _DPU_HW_CWB_H + +#include "dpu_hw_util.h" + +struct dpu_hw_cwb; + +enum cwb_mode_input { + INPUT_MODE_LM_OUT, + INPUT_MODE_DSPP_OUT, + INPUT_MODE_MAX +}; + +/** + * struct dpu_hw_cwb_setup_cfg : Describes configuration for CWB mux + * @pp_idx: Index of the real-time pinpong that the CWB mux will + * feed the CWB mux + * @input: Input tap point + */ +struct dpu_hw_cwb_setup_cfg { + enum dpu_pingpong pp_idx; + enum cwb_mode_input input; +}; + +/** + * + * struct dpu_hw_cwb_ops : Interface to the cwb hw driver functions + * @config_cwb: configure CWB mux + */ +struct dpu_hw_cwb_ops { + void (*config_cwb)(struct dpu_hw_cwb *ctx, + struct dpu_hw_cwb_setup_cfg *cwb_cfg); +}; + +/** + * struct dpu_hw_cwb : CWB mux driver object + * @base: Hardware block base structure + * @hw: Block hardware details + * @idx: CWB index + * @ops: handle to operations possible for this CWB + */ +struct dpu_hw_cwb { + struct dpu_hw_blk base; + struct dpu_hw_blk_reg_map hw; + + enum dpu_cwb idx; + + struct dpu_hw_cwb_ops ops; +}; + +/** + * dpu_hw_cwb - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_cwb *to_dpu_hw_cwb(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_cwb, base); +} + +struct dpu_hw_cwb *dpu_hw_cwb_init(struct drm_device *dev, + const struct dpu_cwb_cfg *cfg, + void __iomem *addr); + +#endif /*_DPU_HW_CWB_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h index f8806a4d317b..ba7bb05efe9b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. */ #ifndef _DPU_HW_MDSS_H @@ -181,10 +183,10 @@ enum dpu_pingpong { PINGPONG_3, PINGPONG_4, PINGPONG_5, - PINGPONG_6, - PINGPONG_7, - PINGPONG_8, - PINGPONG_9, + PINGPONG_CWB_0, + PINGPONG_CWB_1, + PINGPONG_CWB_2, + PINGPONG_CWB_3, PINGPONG_S0, PINGPONG_MAX }; @@ -350,6 +352,7 @@ struct dpu_mdss_color { #define DPU_DBG_MASK_DSPP (1 << 10) #define DPU_DBG_MASK_DSC (1 << 11) #define DPU_DBG_MASK_CDM (1 << 12) +#define DPU_DBG_MASK_CWB (1 << 13) /** * struct dpu_hw_tear_check - Struct contains parameters to configure diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c index fb9f90957762..4853e516c487 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c @@ -173,7 +173,9 @@ static void dpu_hw_wb_bind_pingpong_blk( mux_cfg = DPU_REG_READ(c, WB_MUX); mux_cfg &= ~0xf; - if (pp) + if (pp >= PINGPONG_CWB_0) + mux_cfg |= (pp < PINGPONG_CWB_2) ? 0xd : 0xb; + else if (pp) mux_cfg |= (pp - PINGPONG_0) & 0x7; else mux_cfg |= 0xf; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 8b251f87a052..97e9cb8c2b09 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -51,6 +51,9 @@ #define DPU_DEBUGFS_DIR "msm_dpu" #define DPU_DEBUGFS_HWMASKNAME "hw_log_mask" +bool dpu_use_virtual_planes; +module_param(dpu_use_virtual_planes, bool, 0); + static int dpu_kms_hw_init(struct msm_kms *kms); static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms); @@ -829,8 +832,11 @@ static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms) type, catalog->sspp[i].features, catalog->sspp[i].features & BIT(DPU_SSPP_CURSOR)); - plane = dpu_plane_init(dev, catalog->sspp[i].id, type, - (1UL << max_crtc_count) - 1); + if (dpu_use_virtual_planes) + plane = dpu_plane_init_virtual(dev, type, (1UL << max_crtc_count) - 1); + else + plane = dpu_plane_init(dev, catalog->sspp[i].id, type, + (1UL << max_crtc_count) - 1); if (IS_ERR(plane)) { DPU_ERROR("dpu_plane_init failed\n"); ret = PTR_ERR(plane); @@ -932,12 +938,14 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k /* dump CTL sub-blocks HW regs info */ for (i = 0; i < cat->ctl_count; i++) msm_disp_snapshot_add_block(disp_state, cat->ctl[i].len, - dpu_kms->mmio + cat->ctl[i].base, cat->ctl[i].name); + dpu_kms->mmio + cat->ctl[i].base, "%s", + cat->ctl[i].name); /* dump DSPP sub-blocks HW regs info */ for (i = 0; i < cat->dspp_count; i++) { base = dpu_kms->mmio + cat->dspp[i].base; - msm_disp_snapshot_add_block(disp_state, cat->dspp[i].len, base, cat->dspp[i].name); + msm_disp_snapshot_add_block(disp_state, cat->dspp[i].len, base, + "%s", cat->dspp[i].name); if (cat->dspp[i].sblk && cat->dspp[i].sblk->pcc.len > 0) msm_disp_snapshot_add_block(disp_state, cat->dspp[i].sblk->pcc.len, @@ -949,13 +957,14 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k /* dump INTF sub-blocks HW regs info */ for (i = 0; i < cat->intf_count; i++) msm_disp_snapshot_add_block(disp_state, cat->intf[i].len, - dpu_kms->mmio + cat->intf[i].base, cat->intf[i].name); + dpu_kms->mmio + cat->intf[i].base, "%s", + cat->intf[i].name); /* dump PP sub-blocks HW regs info */ for (i = 0; i < cat->pingpong_count; i++) { base = dpu_kms->mmio + cat->pingpong[i].base; msm_disp_snapshot_add_block(disp_state, cat->pingpong[i].len, base, - cat->pingpong[i].name); + "%s", cat->pingpong[i].name); /* TE2 sub-block has length of 0, so will not print it */ @@ -969,7 +978,8 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k /* dump SSPP sub-blocks HW regs info */ for (i = 0; i < cat->sspp_count; i++) { base = dpu_kms->mmio + cat->sspp[i].base; - msm_disp_snapshot_add_block(disp_state, cat->sspp[i].len, base, cat->sspp[i].name); + msm_disp_snapshot_add_block(disp_state, cat->sspp[i].len, base, + "%s", cat->sspp[i].name); if (cat->sspp[i].sblk && cat->sspp[i].sblk->scaler_blk.len > 0) msm_disp_snapshot_add_block(disp_state, cat->sspp[i].sblk->scaler_blk.len, @@ -987,12 +997,14 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k /* dump LM sub-blocks HW regs info */ for (i = 0; i < cat->mixer_count; i++) msm_disp_snapshot_add_block(disp_state, cat->mixer[i].len, - dpu_kms->mmio + cat->mixer[i].base, cat->mixer[i].name); + dpu_kms->mmio + cat->mixer[i].base, + "%s", cat->mixer[i].name); /* dump WB sub-blocks HW regs info */ for (i = 0; i < cat->wb_count; i++) msm_disp_snapshot_add_block(disp_state, cat->wb[i].len, - dpu_kms->mmio + cat->wb[i].base, cat->wb[i].name); + dpu_kms->mmio + cat->wb[i].base, "%s", + cat->wb[i].name); if (cat->mdp[0].features & BIT(DPU_MDP_PERIPH_0_REMOVED)) { msm_disp_snapshot_add_block(disp_state, MDP_PERIPH_TOP0, @@ -1004,10 +1016,16 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k dpu_kms->mmio + cat->mdp[0].base, "top"); } + /* dump CWB sub-blocks HW regs info */ + for (i = 0; i < cat->cwb_count; i++) + msm_disp_snapshot_add_block(disp_state, cat->cwb[i].len, + dpu_kms->mmio + cat->cwb[i].base, cat->cwb[i].name); + /* dump DSC sub-blocks HW regs info */ for (i = 0; i < cat->dsc_count; i++) { base = dpu_kms->mmio + cat->dsc[i].base; - msm_disp_snapshot_add_block(disp_state, cat->dsc[i].len, base, cat->dsc[i].name); + msm_disp_snapshot_add_block(disp_state, cat->dsc[i].len, base, + "%s", cat->dsc[i].name); if (cat->dsc[i].features & BIT(DPU_DSC_HW_REV_1_2)) { struct dpu_dsc_blk enc = cat->dsc[i].sblk->enc; @@ -1022,7 +1040,16 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k if (cat->cdm) msm_disp_snapshot_add_block(disp_state, cat->cdm->len, - dpu_kms->mmio + cat->cdm->base, cat->cdm->name); + dpu_kms->mmio + cat->cdm->base, + "%s", cat->cdm->name); + + for (i = 0; i < dpu_kms->catalog->vbif_count; i++) { + const struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i]; + + msm_disp_snapshot_add_block(disp_state, vbif->len, + dpu_kms->vbif[vbif->id] + vbif->base, + "%s", vbif->name); + } pm_runtime_put_sync(&dpu_kms->pdev->dev); } @@ -1478,6 +1505,7 @@ static const struct of_device_id dpu_dt_match[] = { { .compatible = "qcom,sc8280xp-dpu", .data = &dpu_sc8280xp_cfg, }, { .compatible = "qcom,sm6115-dpu", .data = &dpu_sm6115_cfg, }, { .compatible = "qcom,sm6125-dpu", .data = &dpu_sm6125_cfg, }, + { .compatible = "qcom,sm6150-dpu", .data = &dpu_sm6150_cfg, }, { .compatible = "qcom,sm6350-dpu", .data = &dpu_sm6350_cfg, }, { .compatible = "qcom,sm6375-dpu", .data = &dpu_sm6375_cfg, }, { .compatible = "qcom,sm7150-dpu", .data = &dpu_sm7150_cfg, }, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index 88d64d43ea1a..547cdb2c0c78 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -54,6 +54,8 @@ #define ktime_compare_safe(A, B) \ ktime_compare(ktime_sub((A), (B)), ktime_set(0, 0)) +extern bool dpu_use_virtual_planes; + struct dpu_kms { struct msm_kms base; struct drm_device *dev; @@ -128,6 +130,8 @@ struct dpu_global_state { uint32_t dspp_to_enc_id[DSPP_MAX - DSPP_0]; uint32_t dsc_to_enc_id[DSC_MAX - DSC_0]; uint32_t cdm_to_enc_id; + + uint32_t sspp_to_crtc_id[SSPP_MAX - SSPP_NONE]; }; struct dpu_global_state diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 3ffac24333a2..098abc2c0003 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -20,7 +20,6 @@ #include "msm_drv.h" #include "msm_mdss.h" #include "dpu_kms.h" -#include "dpu_formats.h" #include "dpu_hw_sspp.h" #include "dpu_hw_util.h" #include "dpu_trace.h" @@ -878,7 +877,7 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, drm_rect_rotate_inv(&pipe_cfg->src_rect, new_plane_state->fb->width, new_plane_state->fb->height, new_plane_state->rotation); - if (r_pipe_cfg->src_rect.x1 != 0) + if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) drm_rect_rotate_inv(&r_pipe_cfg->src_rect, new_plane_state->fb->width, new_plane_state->fb->height, new_plane_state->rotation); @@ -888,6 +887,32 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, return 0; } +static int dpu_plane_is_multirect_parallel_capable(struct dpu_hw_sspp *sspp, + struct dpu_sw_pipe_cfg *pipe_cfg, + const struct msm_format *fmt, + uint32_t max_linewidth) +{ + if (drm_rect_width(&pipe_cfg->src_rect) != drm_rect_width(&pipe_cfg->dst_rect) || + drm_rect_height(&pipe_cfg->src_rect) != drm_rect_height(&pipe_cfg->dst_rect)) + return false; + + if (pipe_cfg->rotation & DRM_MODE_ROTATE_90) + return false; + + if (MSM_FORMAT_IS_YUV(fmt)) + return false; + + if (MSM_FORMAT_IS_UBWC(fmt) && + drm_rect_width(&pipe_cfg->src_rect) > max_linewidth / 2) + return false; + + if (!test_bit(DPU_SSPP_SMART_DMA_V1, &sspp->cap->features) && + !test_bit(DPU_SSPP_SMART_DMA_V2, &sspp->cap->features)) + return false; + + return true; +} + static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, struct drm_atomic_state *state, const struct drm_crtc_state *crtc_state) @@ -901,7 +926,6 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, const struct msm_format *fmt; struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; - uint32_t max_linewidth; uint32_t supported_rotations; const struct dpu_sspp_cfg *pipe_hw_caps; const struct dpu_sspp_sub_blks *sblk; @@ -923,8 +947,6 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, fmt = msm_framebuffer_format(new_plane_state->fb); - max_linewidth = pdpu->catalog->caps->max_linewidth; - supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0; if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION)) @@ -940,41 +962,6 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, return ret; if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) { - /* - * In parallel multirect case only the half of the usual width - * is supported for tiled formats. If we are here, we know that - * full width is more than max_linewidth, thus each rect is - * wider than allowed. - */ - if (MSM_FORMAT_IS_UBWC(fmt) && - drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) { - DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u, tiled format\n", - DRM_RECT_ARG(&pipe_cfg->src_rect), max_linewidth); - return -E2BIG; - } - - if (drm_rect_width(&pipe_cfg->src_rect) != drm_rect_width(&pipe_cfg->dst_rect) || - drm_rect_height(&pipe_cfg->src_rect) != drm_rect_height(&pipe_cfg->dst_rect) || - (!test_bit(DPU_SSPP_SMART_DMA_V1, &pipe->sspp->cap->features) && - !test_bit(DPU_SSPP_SMART_DMA_V2, &pipe->sspp->cap->features)) || - pipe_cfg->rotation & DRM_MODE_ROTATE_90 || - MSM_FORMAT_IS_YUV(fmt)) { - DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u, can't use split source\n", - DRM_RECT_ARG(&pipe_cfg->src_rect), max_linewidth); - return -E2BIG; - } - - /* - * Use multirect for wide plane. We do not support dynamic - * assignment of SSPPs, so we know the configuration. - */ - pipe->multirect_index = DPU_SSPP_RECT_0; - pipe->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; - - r_pipe->sspp = pipe->sspp; - r_pipe->multirect_index = DPU_SSPP_RECT_1; - r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; - ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, fmt, &crtc_state->adjusted_mode); if (ret) @@ -984,6 +971,36 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, return 0; } +static bool dpu_plane_try_multirect_parallel(struct dpu_sw_pipe *pipe, struct dpu_sw_pipe_cfg *pipe_cfg, + struct dpu_sw_pipe *r_pipe, struct dpu_sw_pipe_cfg *r_pipe_cfg, + struct dpu_hw_sspp *sspp, const struct msm_format *fmt, + uint32_t max_linewidth) +{ + r_pipe->sspp = NULL; + + pipe->multirect_index = DPU_SSPP_RECT_SOLO; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; + r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) { + if (!dpu_plane_is_multirect_parallel_capable(pipe->sspp, pipe_cfg, fmt, max_linewidth) || + !dpu_plane_is_multirect_parallel_capable(pipe->sspp, r_pipe_cfg, fmt, max_linewidth)) + return false; + + r_pipe->sspp = pipe->sspp; + + pipe->multirect_index = DPU_SSPP_RECT_0; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; + + r_pipe->multirect_index = DPU_SSPP_RECT_1; + r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; + } + + return true; +} + static int dpu_plane_atomic_check(struct drm_plane *plane, struct drm_atomic_state *state) { @@ -995,14 +1012,19 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); struct dpu_sw_pipe *pipe = &pstate->pipe; struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; + struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; + struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; const struct drm_crtc_state *crtc_state = NULL; + uint32_t max_linewidth = dpu_kms->catalog->caps->max_linewidth; if (new_plane_state->crtc) crtc_state = drm_atomic_get_new_crtc_state(state, new_plane_state->crtc); pipe->sspp = dpu_rm_get_sspp(&dpu_kms->rm, pdpu->pipe); - r_pipe->sspp = NULL; + + if (!pipe->sspp) + return -EINVAL; ret = dpu_plane_atomic_check_nosspp(plane, new_plane_state, crtc_state); if (ret) @@ -1011,14 +1033,155 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, if (!new_plane_state->visible) return 0; - pipe->multirect_index = DPU_SSPP_RECT_SOLO; - pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; - r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; - r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + if (!dpu_plane_try_multirect_parallel(pipe, pipe_cfg, r_pipe, r_pipe_cfg, + pipe->sspp, + msm_framebuffer_format(new_plane_state->fb), + max_linewidth)) { + DPU_DEBUG_PLANE(pdpu, "invalid " DRM_RECT_FMT " /" DRM_RECT_FMT + " max_line:%u, can't use split source\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), + DRM_RECT_ARG(&r_pipe_cfg->src_rect), + max_linewidth); + return -E2BIG; + } return dpu_plane_atomic_check_sspp(plane, state, crtc_state); } +static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *plane_state = + drm_atomic_get_plane_state(state, plane); + struct drm_plane_state *old_plane_state = + drm_atomic_get_old_plane_state(state, plane); + struct dpu_plane_state *pstate = to_dpu_plane_state(plane_state); + struct drm_crtc_state *crtc_state; + int ret; + + if (plane_state->crtc) + crtc_state = drm_atomic_get_new_crtc_state(state, + plane_state->crtc); + + ret = dpu_plane_atomic_check_nosspp(plane, plane_state, crtc_state); + if (ret) + return ret; + + if (!plane_state->visible) { + /* + * resources are freed by dpu_crtc_assign_plane_resources(), + * but clean them here. + */ + pstate->pipe.sspp = NULL; + pstate->r_pipe.sspp = NULL; + + return 0; + } + + /* + * Force resource reallocation if the format of FB or src/dst have + * changed. We might need to allocate different SSPP or SSPPs for this + * plane than the one used previously. + */ + if (!old_plane_state || !old_plane_state->fb || + old_plane_state->src_w != plane_state->src_w || + old_plane_state->src_h != plane_state->src_h || + old_plane_state->src_w != plane_state->src_w || + old_plane_state->crtc_h != plane_state->crtc_h || + msm_framebuffer_format(old_plane_state->fb) != + msm_framebuffer_format(plane_state->fb)) + crtc_state->planes_changed = true; + + return 0; +} + +static int dpu_plane_virtual_assign_resources(struct drm_crtc *crtc, + struct dpu_global_state *global_state, + struct drm_atomic_state *state, + struct drm_plane_state *plane_state) +{ + const struct drm_crtc_state *crtc_state = NULL; + struct drm_plane *plane = plane_state->plane; + struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); + struct dpu_rm_sspp_requirements reqs; + struct dpu_plane_state *pstate; + struct dpu_sw_pipe *pipe; + struct dpu_sw_pipe *r_pipe; + struct dpu_sw_pipe_cfg *pipe_cfg; + struct dpu_sw_pipe_cfg *r_pipe_cfg; + const struct msm_format *fmt; + + if (plane_state->crtc) + crtc_state = drm_atomic_get_new_crtc_state(state, + plane_state->crtc); + + pstate = to_dpu_plane_state(plane_state); + pipe = &pstate->pipe; + r_pipe = &pstate->r_pipe; + pipe_cfg = &pstate->pipe_cfg; + r_pipe_cfg = &pstate->r_pipe_cfg; + + pipe->sspp = NULL; + r_pipe->sspp = NULL; + + if (!plane_state->fb) + return -EINVAL; + + fmt = msm_framebuffer_format(plane_state->fb); + reqs.yuv = MSM_FORMAT_IS_YUV(fmt); + reqs.scale = (plane_state->src_w >> 16 != plane_state->crtc_w) || + (plane_state->src_h >> 16 != plane_state->crtc_h); + + reqs.rot90 = drm_rotation_90_or_270(plane_state->rotation); + + pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, &reqs); + if (!pipe->sspp) + return -ENODEV; + + if (!dpu_plane_try_multirect_parallel(pipe, pipe_cfg, r_pipe, r_pipe_cfg, + pipe->sspp, + msm_framebuffer_format(plane_state->fb), + dpu_kms->catalog->caps->max_linewidth)) { + /* multirect is not possible, use two SSPP blocks */ + r_pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, &reqs); + if (!r_pipe->sspp) + return -ENODEV; + + pipe->multirect_index = DPU_SSPP_RECT_SOLO; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; + r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + } + + return dpu_plane_atomic_check_sspp(plane, state, crtc_state); +} + +int dpu_assign_plane_resources(struct dpu_global_state *global_state, + struct drm_atomic_state *state, + struct drm_crtc *crtc, + struct drm_plane_state **states, + unsigned int num_planes) +{ + unsigned int i; + int ret; + + for (i = 0; i < num_planes; i++) { + struct drm_plane_state *plane_state = states[i]; + + if (!plane_state || + !plane_state->visible) + continue; + + ret = dpu_plane_virtual_assign_resources(crtc, global_state, + state, plane_state); + if (ret) + break; + } + + return ret; +} + static void dpu_plane_flush_csc(struct dpu_plane *pdpu, struct dpu_sw_pipe *pipe) { const struct msm_format *format = @@ -1335,12 +1498,15 @@ static void dpu_plane_atomic_print_state(struct drm_printer *p, drm_printf(p, "\tstage=%d\n", pstate->stage); - drm_printf(p, "\tsspp[0]=%s\n", pipe->sspp->cap->name); - drm_printf(p, "\tmultirect_mode[0]=%s\n", dpu_get_multirect_mode(pipe->multirect_mode)); - drm_printf(p, "\tmultirect_index[0]=%s\n", - dpu_get_multirect_index(pipe->multirect_index)); - drm_printf(p, "\tsrc[0]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&pipe_cfg->src_rect)); - drm_printf(p, "\tdst[0]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&pipe_cfg->dst_rect)); + if (pipe->sspp) { + drm_printf(p, "\tsspp[0]=%s\n", pipe->sspp->cap->name); + drm_printf(p, "\tmultirect_mode[0]=%s\n", + dpu_get_multirect_mode(pipe->multirect_mode)); + drm_printf(p, "\tmultirect_index[0]=%s\n", + dpu_get_multirect_index(pipe->multirect_index)); + drm_printf(p, "\tsrc[0]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&pipe_cfg->src_rect)); + drm_printf(p, "\tdst[0]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&pipe_cfg->dst_rect)); + } if (r_pipe->sspp) { drm_printf(p, "\tsspp[1]=%s\n", r_pipe->sspp->cap->name); @@ -1433,39 +1599,29 @@ static const struct drm_plane_helper_funcs dpu_plane_helper_funcs = { .atomic_update = dpu_plane_atomic_update, }; -/** - * dpu_plane_init - create new dpu plane for the given pipe - * @dev: Pointer to DRM device - * @pipe: dpu hardware pipe identifier - * @type: Plane type - PRIMARY/OVERLAY/CURSOR - * @possible_crtcs: bitmask of crtc that can be attached to the given pipe - * - * Initialize the plane. - */ -struct drm_plane *dpu_plane_init(struct drm_device *dev, - uint32_t pipe, enum drm_plane_type type, - unsigned long possible_crtcs) +static const struct drm_plane_helper_funcs dpu_plane_virtual_helper_funcs = { + .prepare_fb = dpu_plane_prepare_fb, + .cleanup_fb = dpu_plane_cleanup_fb, + .atomic_check = dpu_plane_virtual_atomic_check, + .atomic_update = dpu_plane_atomic_update, +}; + +/* initialize plane */ +static struct drm_plane *dpu_plane_init_common(struct drm_device *dev, + enum drm_plane_type type, + unsigned long possible_crtcs, + bool inline_rotation, + const uint32_t *format_list, + uint32_t num_formats, + enum dpu_sspp pipe) { struct drm_plane *plane = NULL; - const uint32_t *format_list; struct dpu_plane *pdpu; struct msm_drm_private *priv = dev->dev_private; struct dpu_kms *kms = to_dpu_kms(priv->kms); - struct dpu_hw_sspp *pipe_hw; - uint32_t num_formats; uint32_t supported_rotations; int ret; - /* initialize underlying h/w driver */ - pipe_hw = dpu_rm_get_sspp(&kms->rm, pipe); - if (!pipe_hw || !pipe_hw->cap || !pipe_hw->cap->sblk) { - DPU_ERROR("[%u]SSPP is invalid\n", pipe); - return ERR_PTR(-EINVAL); - } - - format_list = pipe_hw->cap->sblk->format_list; - num_formats = pipe_hw->cap->sblk->num_formats; - pdpu = drmm_universal_plane_alloc(dev, struct dpu_plane, base, 0xff, &dpu_plane_funcs, format_list, num_formats, @@ -1491,7 +1647,7 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180; - if (pipe_hw->cap->features & BIT(DPU_SSPP_INLINE_ROTATION)) + if (inline_rotation) supported_rotations |= DRM_MODE_ROTATE_MASK; drm_plane_create_rotation_property(plane, @@ -1499,10 +1655,98 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, drm_plane_enable_fb_damage_clips(plane); - /* success! finalize initialization */ - drm_plane_helper_add(plane, &dpu_plane_helper_funcs); - DPU_DEBUG("%s created for pipe:%u id:%u\n", plane->name, pipe, plane->base.id); return plane; } + +/** + * dpu_plane_init - create new dpu plane for the given pipe + * @dev: Pointer to DRM device + * @pipe: dpu hardware pipe identifier + * @type: Plane type - PRIMARY/OVERLAY/CURSOR + * @possible_crtcs: bitmask of crtc that can be attached to the given pipe + * + * Initialize the plane. + */ +struct drm_plane *dpu_plane_init(struct drm_device *dev, + uint32_t pipe, enum drm_plane_type type, + unsigned long possible_crtcs) +{ + struct drm_plane *plane = NULL; + struct msm_drm_private *priv = dev->dev_private; + struct dpu_kms *kms = to_dpu_kms(priv->kms); + struct dpu_hw_sspp *pipe_hw; + + /* initialize underlying h/w driver */ + pipe_hw = dpu_rm_get_sspp(&kms->rm, pipe); + if (!pipe_hw || !pipe_hw->cap || !pipe_hw->cap->sblk) { + DPU_ERROR("[%u]SSPP is invalid\n", pipe); + return ERR_PTR(-EINVAL); + } + + + plane = dpu_plane_init_common(dev, type, possible_crtcs, + pipe_hw->cap->features & BIT(DPU_SSPP_INLINE_ROTATION), + pipe_hw->cap->sblk->format_list, + pipe_hw->cap->sblk->num_formats, + pipe); + if (IS_ERR(plane)) + return plane; + + drm_plane_helper_add(plane, &dpu_plane_helper_funcs); + + DPU_DEBUG("%s created for pipe:%u id:%u\n", plane->name, + pipe, plane->base.id); + + return plane; +} + +/** + * dpu_plane_init_virtual - create new virtualized DPU plane + * @dev: Pointer to DRM device + * @type: Plane type - PRIMARY/OVERLAY/CURSOR + * @possible_crtcs: bitmask of crtc that can be attached to the given pipe + * + * Initialize the virtual plane with no backing SSPP / pipe. + */ +struct drm_plane *dpu_plane_init_virtual(struct drm_device *dev, + enum drm_plane_type type, + unsigned long possible_crtcs) +{ + struct drm_plane *plane = NULL; + struct msm_drm_private *priv = dev->dev_private; + struct dpu_kms *kms = to_dpu_kms(priv->kms); + bool has_inline_rotation = false; + const u32 *format_list = NULL; + u32 num_formats = 0; + int i; + + /* Determine the largest configuration that we can implement */ + for (i = 0; i < kms->catalog->sspp_count; i++) { + const struct dpu_sspp_cfg *cfg = &kms->catalog->sspp[i]; + + if (test_bit(DPU_SSPP_INLINE_ROTATION, &cfg->features)) + has_inline_rotation = true; + + if (!format_list || + cfg->sblk->csc_blk.len) { + format_list = cfg->sblk->format_list; + num_formats = cfg->sblk->num_formats; + } + } + + plane = dpu_plane_init_common(dev, type, possible_crtcs, + has_inline_rotation, + format_list, + num_formats, + SSPP_NONE); + if (IS_ERR(plane)) + return plane; + + drm_plane_helper_add(plane, &dpu_plane_virtual_helper_funcs); + + DPU_DEBUG("%s created virtual id:%u\n", plane->name, plane->base.id); + + return plane; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h index 97090ca7842b..acd5725175cd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h @@ -62,10 +62,23 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, uint32_t pipe, enum drm_plane_type type, unsigned long possible_crtcs); +struct drm_plane *dpu_plane_init_virtual(struct drm_device *dev, + enum drm_plane_type type, + unsigned long possible_crtcs); + +int dpu_plane_color_fill(struct drm_plane *plane, + uint32_t color, uint32_t alpha); + #ifdef CONFIG_DEBUG_FS void dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable); #else static inline void dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable) {} #endif +int dpu_assign_plane_resources(struct dpu_global_state *global_state, + struct drm_atomic_state *state, + struct drm_crtc *crtc, + struct drm_plane_state **states, + unsigned int num_planes); + #endif /* _DPU_PLANE_H_ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index c247af03dc8e..5baf9df702b8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2023-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #define pr_fmt(fmt) "[drm:%s] " fmt, __func__ @@ -9,6 +9,7 @@ #include "dpu_hw_lm.h" #include "dpu_hw_ctl.h" #include "dpu_hw_cdm.h" +#include "dpu_hw_cwb.h" #include "dpu_hw_pingpong.h" #include "dpu_hw_sspp.h" #include "dpu_hw_intf.h" @@ -26,14 +27,6 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx, return res_map[idx] && res_map[idx] != enc_id; } -/** - * struct dpu_rm_requirements - Reservation requirements parameter bundle - * @topology: selected topology for the display - */ -struct dpu_rm_requirements { - struct msm_display_topology topology; -}; - /** * dpu_rm_init - Read hardware catalog and create reservation tracking objects * for all HW blocks. @@ -130,6 +123,19 @@ int dpu_rm_init(struct drm_device *dev, rm->hw_wb[wb->id - WB_0] = hw; } + for (i = 0; i < cat->cwb_count; i++) { + struct dpu_hw_cwb *hw; + const struct dpu_cwb_cfg *cwb = &cat->cwb[i]; + + hw = dpu_hw_cwb_init(dev, cwb, mmio); + if (IS_ERR(hw)) { + rc = PTR_ERR(hw); + DPU_ERROR("failed cwb object creation: err %d\n", rc); + goto fail; + } + rm->cwb_blks[cwb->id - CWB_0] = &hw->base; + } + for (i = 0; i < cat->ctl_count; i++) { struct dpu_hw_ctl *hw; const struct dpu_ctl_cfg *ctl = &cat->ctl[i]; @@ -241,14 +247,13 @@ static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx) * mixer in rm->pingpong_blks[]. * @dspp_idx: output parameter, index of dspp block attached to the layer * mixer in rm->dspp_blks[]. - * @reqs: input parameter, rm requirements for HW blocks needed in the - * datapath. + * @topology: selected topology for the display * Return: true if lm matches all requirements, false otherwise */ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, struct dpu_global_state *global_state, uint32_t enc_id, int lm_idx, int *pp_idx, int *dspp_idx, - struct dpu_rm_requirements *reqs) + struct msm_display_topology *topology) { const struct dpu_lm_cfg *lm_cfg; int idx; @@ -273,7 +278,7 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, } *pp_idx = idx; - if (!reqs->topology.num_dspp) + if (!topology->num_dspp) return true; idx = lm_cfg->dspp - DSPP_0; @@ -295,7 +300,7 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, static int _dpu_rm_reserve_lms(struct dpu_rm *rm, struct dpu_global_state *global_state, uint32_t enc_id, - struct dpu_rm_requirements *reqs) + struct msm_display_topology *topology) { int lm_idx[MAX_BLOCKS]; @@ -303,14 +308,14 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, int dspp_idx[MAX_BLOCKS] = {0}; int i, lm_count = 0; - if (!reqs->topology.num_lm) { - DPU_ERROR("invalid number of lm: %d\n", reqs->topology.num_lm); + if (!topology->num_lm) { + DPU_ERROR("invalid number of lm: %d\n", topology->num_lm); return -EINVAL; } /* Find a primary mixer */ for (i = 0; i < ARRAY_SIZE(rm->mixer_blks) && - lm_count < reqs->topology.num_lm; i++) { + lm_count < topology->num_lm; i++) { if (!rm->mixer_blks[i]) continue; @@ -319,14 +324,14 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state, enc_id, i, &pp_idx[lm_count], - &dspp_idx[lm_count], reqs)) { + &dspp_idx[lm_count], topology)) { continue; } ++lm_count; /* Valid primary mixer found, find matching peers */ - if (lm_count < reqs->topology.num_lm) { + if (lm_count < topology->num_lm) { int j = _dpu_rm_get_lm_peer(rm, i); /* ignore the peer if there is an error or if the peer was already processed */ @@ -339,7 +344,7 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state, enc_id, j, &pp_idx[lm_count], &dspp_idx[lm_count], - reqs)) { + topology)) { continue; } @@ -348,7 +353,7 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, } } - if (lm_count != reqs->topology.num_lm) { + if (lm_count != topology->num_lm) { DPU_DEBUG("unable to find appropriate mixers\n"); return -ENAVAIL; } @@ -357,7 +362,7 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, global_state->mixer_to_enc_id[lm_idx[i]] = enc_id; global_state->pingpong_to_enc_id[pp_idx[i]] = enc_id; global_state->dspp_to_enc_id[dspp_idx[i]] = - reqs->topology.num_dspp ? enc_id : 0; + topology->num_dspp ? enc_id : 0; trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, enc_id, pp_idx[i] + PINGPONG_0); @@ -594,28 +599,28 @@ static int _dpu_rm_make_reservation( struct dpu_rm *rm, struct dpu_global_state *global_state, struct drm_encoder *enc, - struct dpu_rm_requirements *reqs) + struct msm_display_topology *topology) { int ret; - ret = _dpu_rm_reserve_lms(rm, global_state, enc->base.id, reqs); + ret = _dpu_rm_reserve_lms(rm, global_state, enc->base.id, topology); if (ret) { DPU_ERROR("unable to find appropriate mixers\n"); return ret; } ret = _dpu_rm_reserve_ctls(rm, global_state, enc->base.id, - &reqs->topology); + topology); if (ret) { DPU_ERROR("unable to find appropriate CTL\n"); return ret; } - ret = _dpu_rm_reserve_dsc(rm, global_state, enc, &reqs->topology); + ret = _dpu_rm_reserve_dsc(rm, global_state, enc, topology); if (ret) return ret; - if (reqs->topology.needs_cdm) { + if (topology->needs_cdm) { ret = _dpu_rm_reserve_cdm(rm, global_state, enc); if (ret) { DPU_ERROR("unable to find CDM blk\n"); @@ -626,20 +631,6 @@ static int _dpu_rm_make_reservation( return ret; } -static int _dpu_rm_populate_requirements( - struct drm_encoder *enc, - struct dpu_rm_requirements *reqs, - struct msm_display_topology req_topology) -{ - reqs->topology = req_topology; - - DRM_DEBUG_KMS("num_lm: %d num_dsc: %d num_intf: %d cdm: %d\n", - reqs->topology.num_lm, reqs->topology.num_dsc, - reqs->topology.num_intf, reqs->topology.needs_cdm); - - return 0; -} - static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt, uint32_t enc_id) { @@ -693,9 +684,8 @@ int dpu_rm_reserve( struct dpu_global_state *global_state, struct drm_encoder *enc, struct drm_crtc_state *crtc_state, - struct msm_display_topology topology) + struct msm_display_topology *topology) { - struct dpu_rm_requirements reqs; int ret; /* Check if this is just a page-flip */ @@ -710,13 +700,11 @@ int dpu_rm_reserve( DRM_DEBUG_KMS("reserving hw for enc %d crtc %d\n", enc->base.id, crtc_state->crtc->base.id); - ret = _dpu_rm_populate_requirements(enc, &reqs, topology); - if (ret) { - DPU_ERROR("failed to populate hw requirements\n"); - return ret; - } + DRM_DEBUG_KMS("num_lm: %d num_dsc: %d num_intf: %d\n", + topology->num_lm, topology->num_dsc, + topology->num_intf); - ret = _dpu_rm_make_reservation(rm, global_state, enc, &reqs); + ret = _dpu_rm_make_reservation(rm, global_state, enc, topology); if (ret) DPU_ERROR("failed to reserve hw resources: %d\n", ret); @@ -725,6 +713,88 @@ int dpu_rm_reserve( return ret; } +static struct dpu_hw_sspp *dpu_rm_try_sspp(struct dpu_rm *rm, + struct dpu_global_state *global_state, + struct drm_crtc *crtc, + struct dpu_rm_sspp_requirements *reqs, + unsigned int type) +{ + uint32_t crtc_id = crtc->base.id; + struct dpu_hw_sspp *hw_sspp; + int i; + + for (i = 0; i < ARRAY_SIZE(rm->hw_sspp); i++) { + if (!rm->hw_sspp[i]) + continue; + + if (global_state->sspp_to_crtc_id[i]) + continue; + + hw_sspp = rm->hw_sspp[i]; + + if (hw_sspp->cap->type != type) + continue; + + if (reqs->scale && !hw_sspp->cap->sblk->scaler_blk.len) + continue; + + // TODO: QSEED2 and RGB scalers are not yet supported + if (reqs->scale && !hw_sspp->ops.setup_scaler) + continue; + + if (reqs->yuv && !hw_sspp->cap->sblk->csc_blk.len) + continue; + + if (reqs->rot90 && !(hw_sspp->cap->features & DPU_SSPP_INLINE_ROTATION)) + continue; + + global_state->sspp_to_crtc_id[i] = crtc_id; + + return rm->hw_sspp[i]; + } + + return NULL; +} + +/** + * dpu_rm_reserve_sspp - Reserve the required SSPP for the provided CRTC + * @rm: DPU Resource Manager handle + * @global_state: private global state + * @crtc: DRM CRTC handle + * @reqs: SSPP required features + */ +struct dpu_hw_sspp *dpu_rm_reserve_sspp(struct dpu_rm *rm, + struct dpu_global_state *global_state, + struct drm_crtc *crtc, + struct dpu_rm_sspp_requirements *reqs) +{ + struct dpu_hw_sspp *hw_sspp = NULL; + + if (!reqs->scale && !reqs->yuv) + hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_DMA); + if (!hw_sspp && reqs->scale) + hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_RGB); + if (!hw_sspp) + hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_VIG); + + return hw_sspp; +} + +/** + * dpu_rm_release_all_sspp - Given the CRTC, release all SSPP + * blocks previously reserved for that use case. + * @global_state: resources shared across multiple kms objects + * @crtc: DRM CRTC handle + */ +void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, + struct drm_crtc *crtc) +{ + uint32_t crtc_id = crtc->base.id; + + _dpu_rm_clear_mapping(global_state->sspp_to_crtc_id, + ARRAY_SIZE(global_state->sspp_to_crtc_id), crtc_id); +} + /** * dpu_rm_get_assigned_resources - Get hw resources of the given type that are * assigned to this encoder @@ -859,4 +929,11 @@ void dpu_rm_print_state(struct drm_printer *p, dpu_rm_print_state_helper(p, rm->cdm_blk, global_state->cdm_to_enc_id); drm_puts(p, "\n"); + + drm_puts(p, "\tsspp="); + /* skip SSPP_NONE and start from the next index */ + for (i = SSPP_NONE + 1; i < ARRAY_SIZE(global_state->sspp_to_crtc_id); i++) + dpu_rm_print_state_helper(p, rm->hw_sspp[i] ? &rm->hw_sspp[i]->base : NULL, + global_state->sspp_to_crtc_id[i]); + drm_puts(p, "\n"); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h index ea0e49cb7b0d..99bd594ee0d1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h @@ -20,6 +20,7 @@ struct dpu_global_state; * @ctl_blks: array of ctl hardware resources * @hw_intf: array of intf hardware resources * @hw_wb: array of wb hardware resources + * @hw_cwb: array of cwb hardware resources * @dspp_blks: array of dspp hardware resources * @hw_sspp: array of sspp hardware resources * @cdm_blk: cdm hardware resource @@ -30,6 +31,7 @@ struct dpu_rm { struct dpu_hw_blk *ctl_blks[CTL_MAX - CTL_0]; struct dpu_hw_intf *hw_intf[INTF_MAX - INTF_0]; struct dpu_hw_wb *hw_wb[WB_MAX - WB_0]; + struct dpu_hw_blk *cwb_blks[CWB_MAX - CWB_0]; struct dpu_hw_blk *dspp_blks[DSPP_MAX - DSPP_0]; struct dpu_hw_blk *merge_3d_blks[MERGE_3D_MAX - MERGE_3D_0]; struct dpu_hw_blk *dsc_blks[DSC_MAX - DSC_0]; @@ -37,6 +39,12 @@ struct dpu_rm { struct dpu_hw_blk *cdm_blk; }; +struct dpu_rm_sspp_requirements { + bool yuv; + bool scale; + bool rot90; +}; + /** * struct msm_display_topology - defines a display topology pipeline * @num_lm: number of layer mixers used @@ -63,11 +71,19 @@ int dpu_rm_reserve(struct dpu_rm *rm, struct dpu_global_state *global_state, struct drm_encoder *drm_enc, struct drm_crtc_state *crtc_state, - struct msm_display_topology topology); + struct msm_display_topology *topology); void dpu_rm_release(struct dpu_global_state *global_state, struct drm_encoder *enc); +struct dpu_hw_sspp *dpu_rm_reserve_sspp(struct dpu_rm *rm, + struct dpu_global_state *global_state, + struct drm_crtc *crtc, + struct dpu_rm_sspp_requirements *reqs); + +void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, + struct drm_crtc *crtc); + int dpu_rm_get_assigned_resources(struct dpu_rm *rm, struct dpu_global_state *global_state, uint32_t enc_id, enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c index 16f144cbc0c9..8ff496082902 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c @@ -42,9 +42,6 @@ static int dpu_wb_conn_atomic_check(struct drm_connector *connector, if (!conn_state || !conn_state->connector) { DPU_ERROR("invalid connector state\n"); return -EINVAL; - } else if (conn_state->connector->status != connector_status_connected) { - DPU_ERROR("connector not connected %d\n", conn_state->connector->status); - return -EINVAL; } crtc = conn_state->crtc; diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c index 576995ddce37..8bbc7fb881d5 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c @@ -389,7 +389,7 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev, /* TODO: different regulators in other cases? */ mdp4_lcdc_encoder->regs[0].supply = "lvds-vccs-3p3v"; - mdp4_lcdc_encoder->regs[1].supply = "lvds-vccs-3p3v"; + mdp4_lcdc_encoder->regs[1].supply = "lvds-pll-vdda"; mdp4_lcdc_encoder->regs[2].supply = "lvds-vdda"; ret = devm_regulator_bulk_get(dev->dev, diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.c index e75b97127c0d..2be00b11e557 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.c @@ -109,7 +109,7 @@ int msm_disp_snapshot_init(struct drm_device *drm_dev) mutex_init(&kms->dump_mutex); - kms->dump_worker = kthread_create_worker(0, "%s", "disp_snapshot"); + kms->dump_worker = kthread_run_worker(0, "%s", "disp_snapshot"); if (IS_ERR(kms->dump_worker)) DRM_ERROR("failed to create disp state task\n"); diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index 0fd5e0abaf07..70fdc9fe228a 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -14,6 +14,7 @@ #include "dp_catalog.h" #include "dp_audio.h" #include "dp_panel.h" +#include "dp_reg.h" #include "dp_display.h" #include "dp_utils.h" @@ -28,251 +29,64 @@ struct msm_dp_audio_private { struct msm_dp_audio msm_dp_audio; }; -static u32 msm_dp_audio_get_header(struct msm_dp_catalog *catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header) -{ - return msm_dp_catalog_audio_get_header(catalog, sdp, header); -} - -static void msm_dp_audio_set_header(struct msm_dp_catalog *catalog, - u32 data, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header) -{ - msm_dp_catalog_audio_set_header(catalog, sdp, header, data); -} - static void msm_dp_audio_stream_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x02, + .HB2 = 0x00, + .HB3 = audio->channels - 1, + }; - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x02; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_2); - new_value = value; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_2); - - /* Config header and parity byte 3 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_3); - - new_value = audio->channels - 1; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_3_BIT) - | (parity_byte << PARITY_BYTE_3_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_3); + msm_dp_catalog_write_audio_stream(audio->catalog, &sdp_hdr); } static void msm_dp_audio_timestamp_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x01, + .HB2 = 0x17, + .HB3 = 0x0 | (0x11 << 2), + }; - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x1; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_2); - - new_value = 0x17; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_2); - - /* Config header and parity byte 3 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_3); - - new_value = (0x0 | (0x11 << 2)); - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_3_BIT) - | (parity_byte << PARITY_BYTE_3_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_3); + msm_dp_catalog_write_audio_timestamp(audio->catalog, &sdp_hdr); } static void msm_dp_audio_infoframe_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x84, + .HB2 = 0x1b, + .HB3 = 0x0 | (0x11 << 2), + }; - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x84; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_2); - - new_value = 0x1b; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_2); - - /* Config header and parity byte 3 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_3); - - new_value = (0x0 | (0x11 << 2)); - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_3_BIT) - | (parity_byte << PARITY_BYTE_3_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", - new_value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_3); + msm_dp_catalog_write_audio_infoframe(audio->catalog, &sdp_hdr); } static void msm_dp_audio_copy_management_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x05, + .HB2 = 0x0f, + .HB3 = 0x00, + }; - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x05; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_2); - - new_value = 0x0F; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_2); - - /* Config header and parity byte 3 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_3); - - new_value = 0x0; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_3_BIT) - | (parity_byte << PARITY_BYTE_3_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_3); + msm_dp_catalog_write_audio_copy_mgmt(audio->catalog, &sdp_hdr); } static void msm_dp_audio_isrc_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x06, + .HB2 = 0x0f, + .HB3 = 0x00, + }; - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x06; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_2); - - new_value = 0x0F; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_2); + msm_dp_catalog_write_audio_isrc(audio->catalog, &sdp_hdr); } static void msm_dp_audio_setup_sdp(struct msm_dp_audio_private *audio) @@ -329,10 +143,10 @@ static void msm_dp_audio_safe_to_exit_level(struct msm_dp_audio_private *audio) safe_to_exit_level = 5; break; default: + safe_to_exit_level = 14; drm_dbg_dp(audio->drm_dev, "setting the default safe_to_exit_level = %u\n", safe_to_exit_level); - safe_to_exit_level = 14; break; } @@ -539,14 +353,13 @@ int msm_dp_register_audio_driver(struct device *dev, } struct msm_dp_audio *msm_dp_audio_get(struct platform_device *pdev, - struct msm_dp_panel *panel, struct msm_dp_catalog *catalog) { int rc = 0; struct msm_dp_audio_private *audio; struct msm_dp_audio *msm_dp_audio; - if (!pdev || !panel || !catalog) { + if (!pdev || !catalog) { DRM_ERROR("invalid input\n"); rc = -EINVAL; goto error; @@ -563,8 +376,6 @@ struct msm_dp_audio *msm_dp_audio_get(struct platform_device *pdev, msm_dp_audio = &audio->msm_dp_audio; - msm_dp_catalog_audio_init(catalog); - return msm_dp_audio; error: return ERR_PTR(rc); diff --git a/drivers/gpu/drm/msm/dp/dp_audio.h b/drivers/gpu/drm/msm/dp/dp_audio.h index 1c9efaaa40e5..beea34cbab77 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.h +++ b/drivers/gpu/drm/msm/dp/dp_audio.h @@ -8,7 +8,6 @@ #include -#include "dp_panel.h" #include "dp_catalog.h" #include @@ -28,14 +27,12 @@ struct msm_dp_audio { * Creates and instance of dp audio. * * @pdev: caller's platform device instance. - * @panel: an instance of msm_dp_panel module. * @catalog: an instance of msm_dp_catalog module. * * Returns the error code in case of failure, otherwize * an instance of newly created msm_dp_module. */ struct msm_dp_audio *msm_dp_audio_get(struct platform_device *pdev, - struct msm_dp_panel *panel, struct msm_dp_catalog *catalog); /** diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c index b4c8856fb25d..7b7eadb2f83b 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.c +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -79,7 +79,6 @@ struct msm_dp_catalog_private { struct device *dev; struct drm_device *drm_dev; struct dss_io_data io; - u32 (*audio_map)[DP_AUDIO_SDP_HEADER_MAX]; struct msm_dp_catalog msm_dp_catalog; }; @@ -276,43 +275,6 @@ int msm_dp_catalog_aux_wait_for_hpd_connect_state(struct msm_dp_catalog *msm_dp_ min(wait_us, 2000), wait_us); } -static void dump_regs(void __iomem *base, int len) -{ - int i; - u32 x0, x4, x8, xc; - u32 addr_off = 0; - - len = DIV_ROUND_UP(len, 16); - for (i = 0; i < len; i++) { - x0 = readl_relaxed(base + addr_off); - x4 = readl_relaxed(base + addr_off + 0x04); - x8 = readl_relaxed(base + addr_off + 0x08); - xc = readl_relaxed(base + addr_off + 0x0c); - - pr_info("%08x: %08x %08x %08x %08x", addr_off, x0, x4, x8, xc); - addr_off += 16; - } -} - -void msm_dp_catalog_dump_regs(struct msm_dp_catalog *msm_dp_catalog) -{ - struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, - struct msm_dp_catalog_private, msm_dp_catalog); - struct dss_io_data *io = &catalog->io; - - pr_info("AHB regs\n"); - dump_regs(io->ahb.base, io->ahb.len); - - pr_info("AUXCLK regs\n"); - dump_regs(io->aux.base, io->aux.len); - - pr_info("LCLK regs\n"); - dump_regs(io->link.base, io->link.len); - - pr_info("P0CLK regs\n"); - dump_regs(io->p0.base, io->p0.len); -} - u32 msm_dp_catalog_aux_get_irq(struct msm_dp_catalog *msm_dp_catalog) { struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, @@ -1036,7 +998,6 @@ void msm_dp_catalog_panel_tpg_enable(struct msm_dp_catalog *msm_dp_catalog, display_hctl = (hsync_end_x << 16) | hsync_start_x; - msm_dp_write_p0(catalog, MMSS_DP_INTF_CONFIG, 0x0); msm_dp_write_p0(catalog, MMSS_DP_INTF_HSYNC_CTL, hsync_ctl); msm_dp_write_p0(catalog, MMSS_DP_INTF_VSYNC_PERIOD_F0, vsync_period * hsync_period); @@ -1160,38 +1121,75 @@ struct msm_dp_catalog *msm_dp_catalog_get(struct device *dev) return &catalog->msm_dp_catalog; } -u32 msm_dp_catalog_audio_get_header(struct msm_dp_catalog *msm_dp_catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header) +void msm_dp_catalog_write_audio_stream(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) { - struct msm_dp_catalog_private *catalog; - u32 (*sdp_map)[DP_AUDIO_SDP_HEADER_MAX]; + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + u32 header[2]; - catalog = container_of(msm_dp_catalog, - struct msm_dp_catalog_private, msm_dp_catalog); + msm_dp_utils_pack_sdp_header(sdp_hdr, header); - sdp_map = catalog->audio_map; - - return msm_dp_read_link(catalog, sdp_map[sdp][header]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_STREAM_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_STREAM_1, header[1]); } -void msm_dp_catalog_audio_set_header(struct msm_dp_catalog *msm_dp_catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header, - u32 data) +void msm_dp_catalog_write_audio_timestamp(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) { - struct msm_dp_catalog_private *catalog; - u32 (*sdp_map)[DP_AUDIO_SDP_HEADER_MAX]; + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + u32 header[2]; - if (!msm_dp_catalog) - return; + msm_dp_utils_pack_sdp_header(sdp_hdr, header); - catalog = container_of(msm_dp_catalog, - struct msm_dp_catalog_private, msm_dp_catalog); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_TIMESTAMP_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_TIMESTAMP_1, header[1]); +} - sdp_map = catalog->audio_map; +void msm_dp_catalog_write_audio_infoframe(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) +{ + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + u32 header[2]; - msm_dp_write_link(catalog, sdp_map[sdp][header], data); + msm_dp_utils_pack_sdp_header(sdp_hdr, header); + + msm_dp_write_link(catalog, MMSS_DP_AUDIO_INFOFRAME_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_INFOFRAME_1, header[1]); +} + +void msm_dp_catalog_write_audio_copy_mgmt(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) +{ + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + u32 header[2]; + + msm_dp_utils_pack_sdp_header(sdp_hdr, header); + + msm_dp_write_link(catalog, MMSS_DP_AUDIO_COPYMANAGEMENT_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_COPYMANAGEMENT_1, header[1]); +} + +void msm_dp_catalog_write_audio_isrc(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) +{ + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + struct dp_sdp_header tmp = *sdp_hdr; + u32 header[2]; + u32 reg; + + /* XXX: is it necessary to preserve this field? */ + reg = msm_dp_read_link(catalog, MMSS_DP_AUDIO_ISRC_1); + tmp.HB3 = FIELD_GET(HEADER_3_MASK, reg); + + msm_dp_utils_pack_sdp_header(&tmp, header); + + msm_dp_write_link(catalog, MMSS_DP_AUDIO_ISRC_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_ISRC_1, header[1]); } void msm_dp_catalog_audio_config_acr(struct msm_dp_catalog *msm_dp_catalog, u32 select) @@ -1277,47 +1275,6 @@ void msm_dp_catalog_audio_config_sdp(struct msm_dp_catalog *msm_dp_catalog) msm_dp_write_link(catalog, MMSS_DP_SDP_CFG2, sdp_cfg2); } -void msm_dp_catalog_audio_init(struct msm_dp_catalog *msm_dp_catalog) -{ - struct msm_dp_catalog_private *catalog; - - static u32 sdp_map[][DP_AUDIO_SDP_HEADER_MAX] = { - { - MMSS_DP_AUDIO_STREAM_0, - MMSS_DP_AUDIO_STREAM_1, - MMSS_DP_AUDIO_STREAM_1, - }, - { - MMSS_DP_AUDIO_TIMESTAMP_0, - MMSS_DP_AUDIO_TIMESTAMP_1, - MMSS_DP_AUDIO_TIMESTAMP_1, - }, - { - MMSS_DP_AUDIO_INFOFRAME_0, - MMSS_DP_AUDIO_INFOFRAME_1, - MMSS_DP_AUDIO_INFOFRAME_1, - }, - { - MMSS_DP_AUDIO_COPYMANAGEMENT_0, - MMSS_DP_AUDIO_COPYMANAGEMENT_1, - MMSS_DP_AUDIO_COPYMANAGEMENT_1, - }, - { - MMSS_DP_AUDIO_ISRC_0, - MMSS_DP_AUDIO_ISRC_1, - MMSS_DP_AUDIO_ISRC_1, - }, - }; - - if (!msm_dp_catalog) - return; - - catalog = container_of(msm_dp_catalog, - struct msm_dp_catalog_private, msm_dp_catalog); - - catalog->audio_map = sdp_map; -} - void msm_dp_catalog_audio_sfe_level(struct msm_dp_catalog *msm_dp_catalog, u32 safe_to_exit_level) { struct msm_dp_catalog_private *catalog; diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.h b/drivers/gpu/drm/msm/dp/dp_catalog.h index e932b17eecbf..6678b0ac9a67 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.h +++ b/drivers/gpu/drm/msm/dp/dp_catalog.h @@ -31,22 +31,6 @@ #define DP_HW_VERSION_1_0 0x10000000 #define DP_HW_VERSION_1_2 0x10020000 -enum msm_dp_catalog_audio_sdp_type { - DP_AUDIO_SDP_STREAM, - DP_AUDIO_SDP_TIMESTAMP, - DP_AUDIO_SDP_INFOFRAME, - DP_AUDIO_SDP_COPYMANAGEMENT, - DP_AUDIO_SDP_ISRC, - DP_AUDIO_SDP_MAX, -}; - -enum msm_dp_catalog_audio_header_type { - DP_AUDIO_SDP_HEADER_1, - DP_AUDIO_SDP_HEADER_2, - DP_AUDIO_SDP_HEADER_3, - DP_AUDIO_SDP_HEADER_MAX, -}; - struct msm_dp_catalog { bool wide_bus_en; }; @@ -104,7 +88,6 @@ int msm_dp_catalog_panel_timing_cfg(struct msm_dp_catalog *msm_dp_catalog, u32 t u32 sync_start, u32 width_blanking, u32 msm_dp_active); void msm_dp_catalog_panel_enable_vsc_sdp(struct msm_dp_catalog *msm_dp_catalog, struct dp_sdp *vsc_sdp); void msm_dp_catalog_panel_disable_vsc_sdp(struct msm_dp_catalog *msm_dp_catalog); -void msm_dp_catalog_dump_regs(struct msm_dp_catalog *msm_dp_catalog); void msm_dp_catalog_panel_tpg_enable(struct msm_dp_catalog *msm_dp_catalog, struct drm_display_mode *drm_mode); void msm_dp_catalog_panel_tpg_disable(struct msm_dp_catalog *msm_dp_catalog); @@ -112,17 +95,19 @@ void msm_dp_catalog_panel_tpg_disable(struct msm_dp_catalog *msm_dp_catalog); struct msm_dp_catalog *msm_dp_catalog_get(struct device *dev); /* DP Audio APIs */ -u32 msm_dp_catalog_audio_get_header(struct msm_dp_catalog *msm_dp_catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header); -void msm_dp_catalog_audio_set_header(struct msm_dp_catalog *msm_dp_catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header, - u32 data); +void msm_dp_catalog_write_audio_stream(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); +void msm_dp_catalog_write_audio_timestamp(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); +void msm_dp_catalog_write_audio_infoframe(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); +void msm_dp_catalog_write_audio_copy_mgmt(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); +void msm_dp_catalog_write_audio_isrc(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); void msm_dp_catalog_audio_config_acr(struct msm_dp_catalog *catalog, u32 select); void msm_dp_catalog_audio_enable(struct msm_dp_catalog *catalog, bool enable); void msm_dp_catalog_audio_config_sdp(struct msm_dp_catalog *catalog); -void msm_dp_catalog_audio_init(struct msm_dp_catalog *catalog); void msm_dp_catalog_audio_sfe_level(struct msm_dp_catalog *catalog, u32 safe_to_exit_level); #endif /* _DP_CATALOG_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index bc2ca8133b79..9c463ae2f8fa 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -178,7 +178,6 @@ static void msm_dp_ctrl_configure_source_params(struct msm_dp_ctrl_private *ctrl u32 cc, tb; msm_dp_catalog_ctrl_lane_mapping(ctrl->catalog); - msm_dp_catalog_ctrl_mainlink_ctrl(ctrl->catalog, true); msm_dp_catalog_setup_peripheral_flush(ctrl->catalog); msm_dp_ctrl_config_ctrl(ctrl); @@ -2071,6 +2070,7 @@ void msm_dp_ctrl_off_link(struct msm_dp_ctrl *msm_dp_ctrl) msm_dp_catalog_ctrl_mainlink_ctrl(ctrl->catalog, false); + dev_pm_opp_set_rate(ctrl->dev, 0); msm_dp_ctrl_link_clk_disable(&ctrl->msm_dp_ctrl); DRM_DEBUG_DP("Before, phy=%p init_count=%d power_on=%d\n", diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index aff51bb973eb..24dd37f1682b 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -722,9 +722,6 @@ static int msm_dp_init_sub_modules(struct msm_dp_display_private *dp) { int rc = 0; struct device *dev = &dp->msm_dp_display.pdev->dev; - struct msm_dp_panel_in panel_in = { - .dev = dev, - }; struct phy *phy; phy = devm_phy_get(dev, "dp"); @@ -765,11 +762,7 @@ static int msm_dp_init_sub_modules(struct msm_dp_display_private *dp) goto error_link; } - panel_in.aux = dp->aux; - panel_in.catalog = dp->catalog; - panel_in.link = dp->link; - - dp->panel = msm_dp_panel_get(&panel_in); + dp->panel = msm_dp_panel_get(dev, dp->aux, dp->link, dp->catalog); if (IS_ERR(dp->panel)) { rc = PTR_ERR(dp->panel); DRM_ERROR("failed to initialize panel, rc = %d\n", rc); @@ -787,7 +780,7 @@ static int msm_dp_init_sub_modules(struct msm_dp_display_private *dp) goto error_ctrl; } - dp->audio = msm_dp_audio_get(dp->msm_dp_display.pdev, dp->panel, dp->catalog); + dp->audio = msm_dp_audio_get(dp->msm_dp_display.pdev, dp->catalog); if (IS_ERR(dp->audio)) { rc = PTR_ERR(dp->audio); pr_err("failed to initialize audio, rc = %d\n", rc); diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 5d7eaa31bf31..92415bf8aa16 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -317,17 +317,6 @@ static int msm_dp_panel_setup_vsc_sdp_yuv_420(struct msm_dp_panel *msm_dp_panel) return 0; } -void msm_dp_panel_dump_regs(struct msm_dp_panel *msm_dp_panel) -{ - struct msm_dp_catalog *catalog; - struct msm_dp_panel_private *panel; - - panel = container_of(msm_dp_panel, struct msm_dp_panel_private, msm_dp_panel); - catalog = panel->catalog; - - msm_dp_catalog_dump_regs(catalog); -} - int msm_dp_panel_timing_cfg(struct msm_dp_panel *msm_dp_panel) { u32 data, total_ver, total_hor; @@ -486,25 +475,26 @@ static int msm_dp_panel_parse_dt(struct msm_dp_panel *msm_dp_panel) return 0; } -struct msm_dp_panel *msm_dp_panel_get(struct msm_dp_panel_in *in) +struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux, + struct msm_dp_link *link, struct msm_dp_catalog *catalog) { struct msm_dp_panel_private *panel; struct msm_dp_panel *msm_dp_panel; int ret; - if (!in->dev || !in->catalog || !in->aux || !in->link) { + if (!dev || !catalog || !aux || !link) { DRM_ERROR("invalid input\n"); return ERR_PTR(-EINVAL); } - panel = devm_kzalloc(in->dev, sizeof(*panel), GFP_KERNEL); + panel = devm_kzalloc(dev, sizeof(*panel), GFP_KERNEL); if (!panel) return ERR_PTR(-ENOMEM); - panel->dev = in->dev; - panel->aux = in->aux; - panel->catalog = in->catalog; - panel->link = in->link; + panel->dev = dev; + panel->aux = aux; + panel->catalog = catalog; + panel->link = link; msm_dp_panel = &panel->msm_dp_panel; msm_dp_panel->max_bw_code = DP_LINK_BW_8_1; diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h index 0e944db3adf2..4906f4f09f24 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.h +++ b/drivers/gpu/drm/msm/dp/dp_panel.h @@ -21,13 +21,6 @@ struct msm_dp_display_mode { bool out_fmt_is_yuv_420; }; -struct msm_dp_panel_in { - struct device *dev; - struct drm_dp_aux *aux; - struct msm_dp_link *link; - struct msm_dp_catalog *catalog; -}; - struct msm_dp_panel_psr { u8 version; u8 capabilities; @@ -55,7 +48,6 @@ struct msm_dp_panel { int msm_dp_panel_init_panel_info(struct msm_dp_panel *msm_dp_panel); int msm_dp_panel_deinit(struct msm_dp_panel *msm_dp_panel); int msm_dp_panel_timing_cfg(struct msm_dp_panel *msm_dp_panel); -void msm_dp_panel_dump_regs(struct msm_dp_panel *msm_dp_panel); int msm_dp_panel_read_sink_caps(struct msm_dp_panel *msm_dp_panel, struct drm_connector *connector); u32 msm_dp_panel_get_mode_bpp(struct msm_dp_panel *msm_dp_panel, u32 mode_max_bpp, @@ -92,6 +84,7 @@ static inline bool is_lane_count_valid(u32 lane_count) lane_count == 4); } -struct msm_dp_panel *msm_dp_panel_get(struct msm_dp_panel_in *in); +struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux, + struct msm_dp_link *link, struct msm_dp_catalog *catalog); void msm_dp_panel_put(struct msm_dp_panel *msm_dp_panel); #endif /* _DP_PANEL_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_utils.c b/drivers/gpu/drm/msm/dp/dp_utils.c index 2a40f07fe2d5..4a5ebb0c33b8 100644 --- a/drivers/gpu/drm/msm/dp/dp_utils.c +++ b/drivers/gpu/drm/msm/dp/dp_utils.c @@ -74,14 +74,8 @@ u8 msm_dp_utils_calculate_parity(u32 data) return parity_byte; } -ssize_t msm_dp_utils_pack_sdp_header(struct dp_sdp_header *sdp_header, u32 *header_buff) +void msm_dp_utils_pack_sdp_header(struct dp_sdp_header *sdp_header, u32 header_buff[2]) { - size_t length; - - length = sizeof(header_buff); - if (length < DP_SDP_HEADER_SIZE) - return -ENOSPC; - header_buff[0] = FIELD_PREP(HEADER_0_MASK, sdp_header->HB0) | FIELD_PREP(PARITY_0_MASK, msm_dp_utils_calculate_parity(sdp_header->HB0)) | FIELD_PREP(HEADER_1_MASK, sdp_header->HB1) | @@ -91,6 +85,4 @@ ssize_t msm_dp_utils_pack_sdp_header(struct dp_sdp_header *sdp_header, u32 *head FIELD_PREP(PARITY_2_MASK, msm_dp_utils_calculate_parity(sdp_header->HB2)) | FIELD_PREP(HEADER_3_MASK, sdp_header->HB3) | FIELD_PREP(PARITY_3_MASK, msm_dp_utils_calculate_parity(sdp_header->HB3)); - - return length; } diff --git a/drivers/gpu/drm/msm/dp/dp_utils.h b/drivers/gpu/drm/msm/dp/dp_utils.h index 88d53157f5b5..2e4f98a863c4 100644 --- a/drivers/gpu/drm/msm/dp/dp_utils.h +++ b/drivers/gpu/drm/msm/dp/dp_utils.h @@ -31,6 +31,6 @@ u8 msm_dp_utils_get_g0_value(u8 data); u8 msm_dp_utils_get_g1_value(u8 data); u8 msm_dp_utils_calculate_parity(u32 data); -ssize_t msm_dp_utils_pack_sdp_header(struct dp_sdp_header *sdp_header, u32 *header_buff); +void msm_dp_utils_pack_sdp_header(struct dp_sdp_header *sdp_header, u32 header_buff[2]); #endif /* _DP_UTILS_H_ */ diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c index 10ba7d153d1c..7754dcec33d0 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c @@ -286,6 +286,8 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = { &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_3_0, &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_3_1, + &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_4_0, &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_4_1, diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h index 4c9b4b37681b..120cb65164c1 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h @@ -23,6 +23,7 @@ #define MSM_DSI_6G_VER_MINOR_V2_2_0 0x20000000 #define MSM_DSI_6G_VER_MINOR_V2_2_1 0x20020001 #define MSM_DSI_6G_VER_MINOR_V2_3_0 0x20030000 +#define MSM_DSI_6G_VER_MINOR_V2_3_1 0x20030001 #define MSM_DSI_6G_VER_MINOR_V2_4_0 0x20040000 #define MSM_DSI_6G_VER_MINOR_V2_4_1 0x20040001 #define MSM_DSI_6G_VER_MINOR_V2_5_0 0x20050000 diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index a98d24b7cb00..007311c21fda 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1831,7 +1831,7 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host) msm_dsi->te_source = devm_kstrdup(dev, te_source, GFP_KERNEL); ret = 0; - if (of_property_read_bool(np, "syscon-sfpb")) { + if (of_property_present(np, "syscon-sfpb")) { msm_host->sfpb = syscon_regmap_lookup_by_phandle(np, "syscon-sfpb"); if (IS_ERR(msm_host->sfpb)) { diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index dd58bc0a49eb..c0bcc6828963 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -567,6 +567,8 @@ static const struct of_device_id dsi_phy_dt_match[] = { .data = &dsi_phy_14nm_8953_cfgs }, { .compatible = "qcom,sm6125-dsi-phy-14nm", .data = &dsi_phy_14nm_2290_cfgs }, + { .compatible = "qcom,sm6150-dsi-phy-14nm", + .data = &dsi_phy_14nm_6150_cfgs }, #endif #ifdef CONFIG_DRM_MSM_DSI_10NM_PHY { .compatible = "qcom,dsi-phy-10nm", diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index 4953459edd63..8985818bb2e0 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -46,6 +46,7 @@ extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8937_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs; +extern const struct msm_dsi_phy_cfg dsi_phy_14nm_6150_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_2290_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_8953_cfgs; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 1723f0e4faa4..2c3cbe0f2870 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -1032,6 +1032,10 @@ static const struct regulator_bulk_data dsi_phy_14nm_73p4mA_regulators[] = { { .supply = "vcca", .init_load_uA = 73400 }, }; +static const struct regulator_bulk_data dsi_phy_14nm_36mA_regulators[] = { + { .supply = "vdda", .init_load_uA = 36000 }, +}; + const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs = { .has_phy_lane = true, .regulator_data = dsi_phy_14nm_17mA_regulators, @@ -1097,3 +1101,20 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_2290_cfgs = { .io_start = { 0x5e94400 }, .num_dsi_phy = 1, }; + +const struct msm_dsi_phy_cfg dsi_phy_14nm_6150_cfgs = { + .has_phy_lane = true, + .regulator_data = dsi_phy_14nm_36mA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_14nm_36mA_regulators), + .ops = { + .enable = dsi_14nm_phy_enable, + .disable = dsi_14nm_phy_disable, + .pll_init = dsi_pll_14nm_init, + .save_pll_state = dsi_14nm_pll_save_state, + .restore_pll_state = dsi_14nm_pll_restore_state, + }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, + .io_start = { 0xae94400 }, + .num_dsi_phy = 1, +}; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c index a719fd33d9d8..33bb48ae58a2 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c @@ -137,7 +137,7 @@ static inline u32 pll_get_integloop_gain(u64 frac_start, u64 bclk, u32 ref_clk, base <<= (digclk_divsel == 2 ? 1 : 0); - return (base <= 2046 ? base : 2046); + return base; } static inline u32 pll_get_pll_cmp(u64 fdata, unsigned long ref_clk) diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 9c45d641b521..a7a2384044ff 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -115,7 +115,7 @@ int msm_atomic_init_pending_timer(struct msm_pending_timer *timer, timer->kms = kms; timer->crtc_idx = crtc_idx; - timer->worker = kthread_create_worker(0, "atomic-worker-%d", crtc_idx); + timer->worker = kthread_run_worker(0, "atomic-worker-%d", crtc_idx); if (IS_ERR(timer->worker)) { int ret = PTR_ERR(timer->worker); timer->worker = NULL; diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 34b971490f10..ff7a7a9f7b0d 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -538,7 +538,7 @@ static int msm_ioctl_gem_info_set_iova(struct drm_device *dev, /* Only supported if per-process address space is supported: */ if (priv->gpu->aspace == ctx->aspace) - return -EOPNOTSUPP; + return UERR(EOPNOTSUPP, dev, "requires per-process pgtables"); if (should_fail(&fail_gem_iova, obj->size)) return -ENOMEM; diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index d8c9a1b19263..fee31680a6d5 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -28,6 +28,7 @@ #include #include +#include #include #include #include @@ -506,6 +507,12 @@ void msm_hrtimer_work_init(struct msm_hrtimer_work *work, clockid_t clock_id, enum hrtimer_mode mode); +/* Helper for returning a UABI error with optional logging which can make + * it easier for userspace to understand what it is doing wrong. + */ +#define UERR(err, drm, fmt, ...) \ + ({ DRM_DEV_DEBUG_DRIVER((drm)->dev, fmt, ##__VA_ARGS__); -(err); }) + #define DBG(fmt, ...) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) #define VERB(fmt, ...) if (0) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index fba78193127d..dee470403036 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -20,8 +20,8 @@ /* For userspace errors, use DRM_UT_DRIVER.. so that userspace can enable * error msgs for debugging, but we don't spam dmesg by default */ -#define SUBMIT_ERROR(submit, fmt, ...) \ - DRM_DEV_DEBUG_DRIVER((submit)->dev->dev, fmt, ##__VA_ARGS__) +#define SUBMIT_ERROR(err, submit, fmt, ...) \ + UERR(err, (submit)->dev, fmt, ##__VA_ARGS__) /* * Cmdstream submission: @@ -142,8 +142,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) || !(submit_bo.flags & MANDATORY_FLAGS)) { - SUBMIT_ERROR(submit, "invalid flags: %x\n", submit_bo.flags); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "invalid flags: %x\n", submit_bo.flags); i = 0; goto out; } @@ -162,8 +161,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, */ obj = idr_find(&file->object_idr, submit->bos[i].handle); if (!obj) { - SUBMIT_ERROR(submit, "invalid handle %u at index %u\n", submit->bos[i].handle, i); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "invalid handle %u at index %u\n", submit->bos[i].handle, i); goto out_unlock; } @@ -206,14 +204,12 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: break; default: - SUBMIT_ERROR(submit, "invalid type: %08x\n", submit_cmd.type); - return -EINVAL; + return SUBMIT_ERROR(EINVAL, submit, "invalid type: %08x\n", submit_cmd.type); } if (submit_cmd.size % 4) { - SUBMIT_ERROR(submit, "non-aligned cmdstream buffer size: %u\n", - submit_cmd.size); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "non-aligned cmdstream buffer size: %u\n", + submit_cmd.size); goto out; } @@ -371,9 +367,8 @@ static int submit_bo(struct msm_gem_submit *submit, uint32_t idx, struct drm_gem_object **obj, uint64_t *iova) { if (idx >= submit->nr_bos) { - SUBMIT_ERROR(submit, "invalid buffer index: %u (out of %u)\n", - idx, submit->nr_bos); - return -EINVAL; + return SUBMIT_ERROR(EINVAL, submit, "invalid buffer index: %u (out of %u)\n", + idx, submit->nr_bos); } if (obj) @@ -392,10 +387,8 @@ static int submit_reloc(struct msm_gem_submit *submit, struct drm_gem_object *ob uint32_t *ptr; int ret = 0; - if (offset % 4) { - SUBMIT_ERROR(submit, "non-aligned cmdstream buffer: %u\n", offset); - return -EINVAL; - } + if (offset % 4) + return SUBMIT_ERROR(EINVAL, submit, "non-aligned cmdstream buffer: %u\n", offset); /* For now, just map the entire thing. Eventually we probably * to do it page-by-page, w/ kmap() if not vmap()d.. @@ -414,9 +407,8 @@ static int submit_reloc(struct msm_gem_submit *submit, struct drm_gem_object *ob uint64_t iova; if (submit_reloc.submit_offset % 4) { - SUBMIT_ERROR(submit, "non-aligned reloc offset: %u\n", - submit_reloc.submit_offset); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "non-aligned reloc offset: %u\n", + submit_reloc.submit_offset); goto out; } @@ -425,8 +417,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct drm_gem_object *ob if ((off >= (obj->size / 4)) || (off < last_offset)) { - SUBMIT_ERROR(submit, "invalid offset %u at reloc %u\n", off, i); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "invalid offset %u at reloc %u\n", off, i); goto out; } @@ -513,12 +504,12 @@ static struct drm_syncobj **msm_parse_deps(struct msm_gem_submit *submit, if (syncobj_desc.point && !drm_core_check_feature(submit->dev, DRIVER_SYNCOBJ_TIMELINE)) { - ret = -EOPNOTSUPP; + ret = SUBMIT_ERROR(EOPNOTSUPP, submit, "syncobj timeline unsupported"); break; } if (syncobj_desc.flags & ~MSM_SUBMIT_SYNCOBJ_FLAGS) { - ret = -EINVAL; + ret = -SUBMIT_ERROR(EINVAL, submit, "invalid syncobj flags: %x", syncobj_desc.flags); break; } @@ -531,7 +522,7 @@ static struct drm_syncobj **msm_parse_deps(struct msm_gem_submit *submit, syncobjs[i] = drm_syncobj_find(file, syncobj_desc.handle); if (!syncobjs[i]) { - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "invalid syncobj handle: %u", i); break; } } @@ -588,14 +579,14 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, post_deps[i].point = syncobj_desc.point; if (syncobj_desc.flags) { - ret = -EINVAL; + ret = UERR(EINVAL, dev, "invalid syncobj flags"); break; } if (syncobj_desc.point) { if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) { - ret = -EOPNOTSUPP; + ret = UERR(EOPNOTSUPP, dev, "syncobj timeline unsupported"); break; } @@ -609,7 +600,7 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, post_deps[i].syncobj = drm_syncobj_find(file, syncobj_desc.handle); if (!post_deps[i].syncobj) { - ret = -EINVAL; + ret = UERR(EINVAL, dev, "invalid syncobj handle"); break; } } @@ -677,10 +668,10 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, * be more clever to dispatch to appropriate gpu module: */ if (MSM_PIPE_ID(args->flags) != MSM_PIPE_3D0) - return -EINVAL; + return UERR(EINVAL, dev, "invalid pipe"); if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_FLAGS) - return -EINVAL; + return UERR(EINVAL, dev, "invalid flags"); if (args->flags & MSM_SUBMIT_SUDO) { if (!IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) || @@ -724,7 +715,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, in_fence = sync_file_get_fence(args->fence_fd); if (!in_fence) { - ret = -EINVAL; + ret = UERR(EINVAL, dev, "invalid in-fence"); goto out_unlock; } @@ -787,10 +778,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, goto out; if (!submit->cmd[i].size || - ((submit->cmd[i].size + submit->cmd[i].offset) > - obj->size / 4)) { - SUBMIT_ERROR(submit, "invalid cmdstream size: %u\n", submit->cmd[i].size * 4); - ret = -EINVAL; + (size_add(submit->cmd[i].size, submit->cmd[i].offset) > obj->size / 4)) { + ret = UERR(EINVAL, dev, "invalid cmdstream size: %u\n", + submit->cmd[i].size * 4); goto out; } @@ -800,8 +790,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, continue; if (!gpu->allow_relocs) { - SUBMIT_ERROR(submit, "relocs not allowed\n"); - ret = -EINVAL; + ret = UERR(EINVAL, dev, "relocs not allowed\n"); goto out; } @@ -827,7 +816,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, (!args->fence || idr_find(&queue->fence_idr, args->fence))) { spin_unlock(&queue->idr_lock); idr_preload_end(); - ret = -EINVAL; + ret = UERR(EINVAL, dev, "invalid in-fence-sn"); goto out; } diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 0d4a3744cfcb..8557998e0c92 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -859,7 +859,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, gpu->funcs = funcs; gpu->name = name; - gpu->worker = kthread_create_worker(0, "gpu-worker"); + gpu->worker = kthread_run_worker(0, "gpu-worker"); if (IS_ERR(gpu->worker)) { ret = PTR_ERR(gpu->worker); gpu->worker = NULL; diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index f3326d09bdbc..38965e12a6bf 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -244,7 +244,6 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) ret = priv->kms_init(ddev); if (ret) { DRM_DEV_ERROR(dev, "failed to load kms\n"); - priv->kms = NULL; return ret; } @@ -269,7 +268,7 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) /* initialize event thread */ ev_thread = &priv->event_thread[drm_crtc_index(crtc)]; ev_thread->dev = ddev; - ev_thread->worker = kthread_create_worker(0, "crtc_event:%d", crtc->base.id); + ev_thread->worker = kthread_run_worker(0, "crtc_event:%d", crtc->base.id); if (IS_ERR(ev_thread->worker)) { ret = PTR_ERR(ev_thread->worker); DRM_DEV_ERROR(dev, "failed to create crtc_event kthread\n"); diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 76b6ae35a3cb..dcb49fd30402 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -166,22 +166,32 @@ static int _msm_mdss_irq_domain_add(struct msm_mdss *msm_mdss) static void msm_mdss_setup_ubwc_dec_20(struct msm_mdss *msm_mdss) { const struct msm_mdss_data *data = msm_mdss->mdss_data; + u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle) | + MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit); - writel_relaxed(data->ubwc_static, msm_mdss->mmio + REG_MDSS_UBWC_STATIC); + if (data->ubwc_bank_spread) + value |= MDSS_UBWC_STATIC_UBWC_BANK_SPREAD; + + if (data->ubwc_enc_version == UBWC_1_0) + value |= MDSS_UBWC_STATIC_UBWC_MIN_ACC_LEN(1); + + writel_relaxed(value, msm_mdss->mmio + REG_MDSS_UBWC_STATIC); } static void msm_mdss_setup_ubwc_dec_30(struct msm_mdss *msm_mdss) { const struct msm_mdss_data *data = msm_mdss->mdss_data; - u32 value = (data->ubwc_swizzle & 0x1) | - (data->highest_bank_bit & 0x3) << 4 | - (data->macrotile_mode & 0x1) << 12; + u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle & 0x1) | + MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit); + + if (data->macrotile_mode) + value |= MDSS_UBWC_STATIC_MACROTILE_MODE; if (data->ubwc_enc_version == UBWC_3_0) - value |= BIT(10); + value |= MDSS_UBWC_STATIC_UBWC_AMSBC; if (data->ubwc_enc_version == UBWC_1_0) - value |= BIT(8); + value |= MDSS_UBWC_STATIC_UBWC_MIN_ACC_LEN(1); writel_relaxed(value, msm_mdss->mmio + REG_MDSS_UBWC_STATIC); } @@ -189,10 +199,14 @@ static void msm_mdss_setup_ubwc_dec_30(struct msm_mdss *msm_mdss) static void msm_mdss_setup_ubwc_dec_40(struct msm_mdss *msm_mdss) { const struct msm_mdss_data *data = msm_mdss->mdss_data; - u32 value = (data->ubwc_swizzle & 0x7) | - (data->ubwc_static & 0x1) << 3 | - (data->highest_bank_bit & 0x7) << 4 | - (data->macrotile_mode & 0x1) << 12; + u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle) | + MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit); + + if (data->ubwc_bank_spread) + value |= MDSS_UBWC_STATIC_UBWC_BANK_SPREAD; + + if (data->macrotile_mode) + value |= MDSS_UBWC_STATIC_MACROTILE_MODE; writel_relaxed(value, msm_mdss->mmio + REG_MDSS_UBWC_STATIC); @@ -572,16 +586,17 @@ static const struct msm_mdss_data sa8775p_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 4, - .ubwc_static = 1, + .ubwc_bank_spread = true, .highest_bank_bit = 0, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 74000, }; static const struct msm_mdss_data sc7180_data = { .ubwc_enc_version = UBWC_2_0, .ubwc_dec_version = UBWC_2_0, - .ubwc_static = 0x1e, + .ubwc_swizzle = 6, + .ubwc_bank_spread = true, .highest_bank_bit = 0x1, .reg_bus_bw = 76800, }; @@ -590,9 +605,9 @@ static const struct msm_mdss_data sc7280_data = { .ubwc_enc_version = UBWC_3_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, .highest_bank_bit = 1, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 74000, }; @@ -600,7 +615,7 @@ static const struct msm_mdss_data sc8180x_data = { .ubwc_enc_version = UBWC_3_0, .ubwc_dec_version = UBWC_3_0, .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 76800, }; @@ -608,9 +623,9 @@ static const struct msm_mdss_data sc8280xp_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 76800, }; @@ -632,7 +647,7 @@ static const struct msm_mdss_data sm6350_data = { .ubwc_enc_version = UBWC_2_0, .ubwc_dec_version = UBWC_2_0, .ubwc_swizzle = 6, - .ubwc_static = 0x1e, + .ubwc_bank_spread = true, .highest_bank_bit = 1, .reg_bus_bw = 76800, }; @@ -655,7 +670,7 @@ static const struct msm_mdss_data sm6115_data = { .ubwc_enc_version = UBWC_1_0, .ubwc_dec_version = UBWC_2_0, .ubwc_swizzle = 7, - .ubwc_static = 0x11f, + .ubwc_bank_spread = true, .highest_bank_bit = 0x1, .reg_bus_bw = 76800, }; @@ -667,14 +682,21 @@ static const struct msm_mdss_data sm6125_data = { .highest_bank_bit = 1, }; +static const struct msm_mdss_data sm6150_data = { + .ubwc_enc_version = UBWC_2_0, + .ubwc_dec_version = UBWC_2_0, + .highest_bank_bit = 1, + .reg_bus_bw = 76800, +}; + static const struct msm_mdss_data sm8250_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 76800, }; @@ -682,10 +704,10 @@ static const struct msm_mdss_data sm8350_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 74000, }; @@ -693,10 +715,10 @@ static const struct msm_mdss_data sm8550_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_3, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 57000, }; @@ -704,10 +726,10 @@ static const struct msm_mdss_data x1e80100_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_3, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, /* TODO: Add reg_bus_bw with real value */ }; @@ -724,6 +746,7 @@ static const struct of_device_id mdss_dt_match[] = { { .compatible = "qcom,sc8280xp-mdss", .data = &sc8280xp_data }, { .compatible = "qcom,sm6115-mdss", .data = &sm6115_data }, { .compatible = "qcom,sm6125-mdss", .data = &sm6125_data }, + { .compatible = "qcom,sm6150-mdss", .data = &sm6150_data }, { .compatible = "qcom,sm6350-mdss", .data = &sm6350_data }, { .compatible = "qcom,sm6375-mdss", .data = &sm6350_data }, { .compatible = "qcom,sm7150-mdss", .data = &sm7150_data }, diff --git a/drivers/gpu/drm/msm/msm_mdss.h b/drivers/gpu/drm/msm/msm_mdss.h index 3afef4b1786d..14dc53704314 100644 --- a/drivers/gpu/drm/msm/msm_mdss.h +++ b/drivers/gpu/drm/msm/msm_mdss.h @@ -11,9 +11,9 @@ struct msm_mdss_data { /* can be read from register 0x58 */ u32 ubwc_dec_version; u32 ubwc_swizzle; - u32 ubwc_static; u32 highest_bank_bit; - u32 macrotile_mode; + bool ubwc_bank_spread; + bool macrotile_mode; u32 reg_bus_bw; }; diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 2fc3eaf81f44..7fed1de63b5d 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -18,7 +18,7 @@ int msm_file_private_set_sysprof(struct msm_file_private *ctx, switch (sysprof) { default: - return -EINVAL; + return UERR(EINVAL, gpu->dev, "Invalid sysprof: %d", sysprof); case 2: pm_runtime_get_sync(&gpu->pdev->dev); fallthrough; diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml index 6531749d30f4..3d2cc339b8f1 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml @@ -52,6 +52,11 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> + + + + + diff --git a/drivers/gpu/drm/msm/registers/display/mdss.xml b/drivers/gpu/drm/msm/registers/display/mdss.xml index ac85caf1575c..6e9f81cd4690 100644 --- a/drivers/gpu/drm/msm/registers/display/mdss.xml +++ b/drivers/gpu/drm/msm/registers/display/mdss.xml @@ -21,7 +21,16 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> - + + + + + + + + + + diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index 8f0c69aad248..21b56cc7605c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -384,7 +384,7 @@ nouveau_acpi_edid(struct drm_device *dev, struct drm_connector *connector) if (ret < 0) return NULL; - return kmemdup(edid, EDID_LENGTH, GFP_KERNEL); + return edid; } bool nouveau_acpi_video_backlight_use_native(void) diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 2cb2e5675807..cd659b9fd1d9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -279,7 +279,6 @@ nouveau_channel_ctor(struct nouveau_cli *cli, bool priv, u64 runm, const u64 plength = 0x10000; const u64 ioffset = plength; const u64 ilength = 0x02000; - char name[TASK_COMM_LEN]; int cid, ret; u64 size; @@ -338,8 +337,7 @@ nouveau_channel_ctor(struct nouveau_cli *cli, bool priv, u64 runm, chan->userd = &chan->user; } - get_task_comm(name, current); - snprintf(args.name, sizeof(args.name), "%s[%d]", name, task_pid_nr(current)); + snprintf(args.name, sizeof(args.name), "%s[%d]", current->comm, task_pid_nr(current)); ret = nvif_object_ctor(&device->object, "abi16ChanUser", 0, hosts[cid].oclass, &args, sizeof(args), &chan->user); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 21d2d9ca5e85..5664c4c71faf 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1175,7 +1175,7 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv) { struct nouveau_drm *drm = nouveau_drm(dev); struct nouveau_cli *cli; - char name[32], tmpname[TASK_COMM_LEN]; + char name[32]; int ret; /* need to bring up power immediately if opening device */ @@ -1185,10 +1185,9 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv) return ret; } - get_task_comm(tmpname, current); rcu_read_lock(); snprintf(name, sizeof(name), "%s[%d]", - tmpname, pid_nr(rcu_dereference(fpriv->pid))); + current->comm, pid_nr(rcu_dereference(fpriv->pid))); rcu_read_unlock(); if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL))) { diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 09686d038d60..7cc84472cece 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -387,11 +387,13 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, if (f) { struct nouveau_channel *prev; bool must_wait = true; + bool local; rcu_read_lock(); prev = rcu_dereference(f->channel); - if (prev && (prev == chan || - fctx->sync(f, prev, chan) == 0)) + local = prev && prev->cli->drm == chan->cli->drm; + if (local && (prev == chan || + fctx->sync(f, prev, chan) == 0)) must_wait = false; rcu_read_unlock(); if (!must_wait) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp77.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp77.c index 841e3b69fcaf..5a0c9b8a79f3 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp77.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp77.c @@ -31,6 +31,7 @@ mcp77_sor = { .state = g94_sor_state, .power = nv50_sor_power, .clock = nv50_sor_clock, + .bl = &nv50_sor_bl, .hdmi = &g84_sor_hdmi, .dp = &g94_sor_dp, }; diff --git a/drivers/gpu/drm/panel/panel-himax-hx83102.c b/drivers/gpu/drm/panel/panel-himax-hx83102.c index 8b48bba18131..3644a7544b93 100644 --- a/drivers/gpu/drm/panel/panel-himax-hx83102.c +++ b/drivers/gpu/drm/panel/panel-himax-hx83102.c @@ -565,6 +565,8 @@ static int hx83102_get_modes(struct drm_panel *panel, struct drm_display_mode *mode; mode = drm_mode_duplicate(connector->dev, m); + if (!mode) + return -ENOMEM; mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; drm_mode_set_name(mode); diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35950.c b/drivers/gpu/drm/panel/panel-novatek-nt35950.c index b036208f9356..08b22b592ab0 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt35950.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt35950.c @@ -481,9 +481,9 @@ static int nt35950_probe(struct mipi_dsi_device *dsi) return dev_err_probe(dev, -EPROBE_DEFER, "Cannot get secondary DSI host\n"); nt->dsi[1] = mipi_dsi_device_register_full(dsi_r_host, info); - if (!nt->dsi[1]) { + if (IS_ERR(nt->dsi[1])) { dev_err(dev, "Cannot get secondary DSI node\n"); - return -ENODEV; + return PTR_ERR(nt->dsi[1]); } num_dsis++; } diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index dbad12a354b6..9b2f128fd309 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -4454,6 +4454,37 @@ static const struct panel_desc ti_nspire_classic_lcd_panel = { .bus_flags = DRM_BUS_FLAG_PIXDATA_SAMPLE_NEGEDGE, }; +static const struct display_timing topland_tian_g07017_01_timing = { + .pixelclock = { 44900000, 51200000, 63000000 }, + .hactive = { 1024, 1024, 1024 }, + .hfront_porch = { 16, 160, 216 }, + .hback_porch = { 160, 160, 160 }, + .hsync_len = { 1, 1, 140 }, + .vactive = { 600, 600, 600 }, + .vfront_porch = { 1, 12, 127 }, + .vback_porch = { 23, 23, 23 }, + .vsync_len = { 1, 1, 20 }, +}; + +static const struct panel_desc topland_tian_g07017_01 = { + .timings = &topland_tian_g07017_01_timing, + .num_timings = 1, + .bpc = 8, + .size = { + .width = 154, + .height = 86, + }, + .delay = { + .prepare = 1, /* 6.5 - 150µs PLL wake-up time */ + .enable = 100, /* 6.4 - Power on: 6 VSyncs */ + .disable = 84, /* 6.4 - Power off: 5 Vsyncs */ + .unprepare = 50, /* 6.4 - Power off: 3 Vsyncs */ + }, + .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, + .connector_type = DRM_MODE_CONNECTOR_LVDS, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, +}; + static const struct drm_display_mode toshiba_lt089ac29000_mode = { .clock = 79500, .hdisplay = 1280, @@ -5139,6 +5170,9 @@ static const struct of_device_id platform_of_match[] = { }, { .compatible = "toshiba,lt089ac29000", .data = &toshiba_lt089ac29000, + }, { + .compatible = "topland,tian-g07017-01", + .data = &topland_tian_g07017_01, }, { .compatible = "tpk,f07a-0102", .data = &tpk_f07a_0102, diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c index eef03d04e0cd..1f72ef7ca74c 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c @@ -1177,6 +1177,7 @@ static int st7701_probe(struct device *dev, int connector_type) return dev_err_probe(dev, ret, "Failed to get orientation\n"); drm_panel_init(&st7701->panel, dev, &st7701_funcs, connector_type); + st7701->panel.prepare_prev_first = true; /** * Once sleep out has been issued, ST7701 IC required to wait 120ms diff --git a/drivers/gpu/drm/panel/panel-synaptics-r63353.c b/drivers/gpu/drm/panel/panel-synaptics-r63353.c index 169c629746c7..17349825543f 100644 --- a/drivers/gpu/drm/panel/panel-synaptics-r63353.c +++ b/drivers/gpu/drm/panel/panel-synaptics-r63353.c @@ -325,7 +325,7 @@ static void r63353_panel_shutdown(struct mipi_dsi_device *dsi) { struct r63353_panel *rpanel = mipi_dsi_get_drvdata(dsi); - r63353_panel_unprepare(&rpanel->base); + drm_panel_unprepare(&rpanel->base); } static const struct r63353_desc sharp_ls068b3sx02_data = { diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index b76337f690ec..b17de83b988b 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -885,7 +885,6 @@ static const struct hdmi_codec_ops audio_codec_ops = { .mute_stream = cdn_dp_audio_mute_stream, .get_eld = cdn_dp_audio_get_eld, .hook_plugged_cb = cdn_dp_audio_hook_plugged_cb, - .no_capture_mute = 1, }; static int cdn_dp_audio_codec_init(struct cdn_dp_device *dp, @@ -896,6 +895,7 @@ static int cdn_dp_audio_codec_init(struct cdn_dp_device *dp, .spdif = 1, .ops = &audio_codec_ops, .max_i2s_channels = 8, + .no_capture_mute = 1, }; dp->audio_pdev = platform_device_register_data( diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index 3ca6a688f5f5..17a98845fd31 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -1454,16 +1454,18 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, vop2_win_write(win, VOP2_WIN_AFBC_HALF_BLOCK_EN, half_block_en); if (afbc_en) { - u32 stride; + u32 stride, block_w; + + /* the afbc superblock is 16 x 16 or 32 x 8 */ + block_w = fb->modifier & AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 ? 32 : 16; - /* the afbc superblock is 16 x 16 */ afbc_format = vop2_convert_afbc_format(fb->format->format); /* Enable color transform for YTR */ if (fb->modifier & AFBC_FORMAT_MOD_YTR) afbc_format |= (1 << 4); - afbc_tile_num = ALIGN(actual_w, 16) >> 4; + afbc_tile_num = ALIGN(actual_w, block_w) / block_w; /* * AFBC pic_vir_width is count by pixel, this is different @@ -1474,6 +1476,9 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, drm_dbg_kms(vop2->drm, "vp%d %s stride[%d] not 64 pixel aligned\n", vp->id, win->data->name, stride); + /* It's for head stride, each head size is 16 byte */ + stride = ALIGN(stride, block_w) / block_w * 16; + uv_swap = vop2_afbc_uv_swap(fb->format->format); /* * This is a workaround for crazy IC design, Cluster @@ -1504,7 +1509,11 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, else vop2_win_write(win, VOP2_WIN_AFBC_AUTO_GATING_EN, 1); - vop2_win_write(win, VOP2_WIN_AFBC_BLOCK_SPLIT_EN, 0); + if (fb->modifier & AFBC_FORMAT_MOD_SPLIT) + vop2_win_write(win, VOP2_WIN_AFBC_BLOCK_SPLIT_EN, 1); + else + vop2_win_write(win, VOP2_WIN_AFBC_BLOCK_SPLIT_EN, 0); + transform_offset = vop2_afbc_transform_offset(pstate, half_block_en); vop2_win_write(win, VOP2_WIN_AFBC_HDR_PTR, yrgb_mst); vop2_win_write(win, VOP2_WIN_AFBC_PIC_SIZE, act_info); diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 7ce25281c74c..57da84908752 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1355,7 +1355,8 @@ EXPORT_SYMBOL(drm_sched_init); * drm_sched_backend_ops.run_job(). Consequently, drm_sched_backend_ops.free_job() * will not be called for all jobs still in drm_gpu_scheduler.pending_list. * There is no solution for this currently. Thus, it is up to the driver to make - * sure that + * sure that: + * * a) drm_sched_fini() is only called after for all submitted jobs * drm_sched_backend_ops.free_job() has been called or that * b) the jobs for which drm_sched_backend_ops.free_job() has not been called diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index f8bbae6393ef..ca2fe17de4a5 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -1237,7 +1237,6 @@ static const struct hdmi_codec_ops audio_codec_ops = { .audio_shutdown = hdmi_audio_shutdown, .mute_stream = hdmi_audio_mute, .get_eld = hdmi_audio_get_eld, - .no_capture_mute = 1, }; static int sti_hdmi_register_audio_driver(struct device *dev, @@ -1247,6 +1246,7 @@ static int sti_hdmi_register_audio_driver(struct device *dev, .ops = &audio_codec_ops, .max_i2s_channels = 8, .i2s = 1, + .no_capture_mute = 1, }; DRM_DEBUG_DRIVER("\n"); diff --git a/drivers/gpu/drm/tests/drm_connector_test.c b/drivers/gpu/drm/tests/drm_connector_test.c index 129e813cfd1b..22e2d959eb31 100644 --- a/drivers/gpu/drm/tests/drm_connector_test.c +++ b/drivers/gpu/drm/tests/drm_connector_test.c @@ -1095,6 +1095,64 @@ static void drm_test_connector_hdmi_init_formats_no_rgb(struct kunit *test) KUNIT_EXPECT_LT(test, ret, 0); } +struct drm_connector_hdmi_init_formats_yuv420_allowed_test { + unsigned long supported_formats; + bool yuv420_allowed; + int expected_result; +}; + +#define YUV420_ALLOWED_TEST(_formats, _allowed, _result) \ + { \ + .supported_formats = BIT(HDMI_COLORSPACE_RGB) | (_formats), \ + .yuv420_allowed = _allowed, \ + .expected_result = _result, \ + } + +static const struct drm_connector_hdmi_init_formats_yuv420_allowed_test +drm_connector_hdmi_init_formats_yuv420_allowed_tests[] = { + YUV420_ALLOWED_TEST(BIT(HDMI_COLORSPACE_YUV420), true, 0), + YUV420_ALLOWED_TEST(BIT(HDMI_COLORSPACE_YUV420), false, -EINVAL), + YUV420_ALLOWED_TEST(BIT(HDMI_COLORSPACE_YUV422), true, -EINVAL), + YUV420_ALLOWED_TEST(BIT(HDMI_COLORSPACE_YUV422), false, 0), +}; + +static void +drm_connector_hdmi_init_formats_yuv420_allowed_desc(const struct drm_connector_hdmi_init_formats_yuv420_allowed_test *t, + char *desc) +{ + sprintf(desc, "supported_formats=0x%lx yuv420_allowed=%d", + t->supported_formats, t->yuv420_allowed); +} + +KUNIT_ARRAY_PARAM(drm_connector_hdmi_init_formats_yuv420_allowed, + drm_connector_hdmi_init_formats_yuv420_allowed_tests, + drm_connector_hdmi_init_formats_yuv420_allowed_desc); + +/* + * Test that the registration of an HDMI connector succeeds only when + * the presence of YUV420 in the supported formats matches the value + * of the ycbcr_420_allowed flag. + */ +static void drm_test_connector_hdmi_init_formats_yuv420_allowed(struct kunit *test) +{ + const struct drm_connector_hdmi_init_formats_yuv420_allowed_test *params; + struct drm_connector_init_priv *priv = test->priv; + int ret; + + params = test->param_value; + priv->connector.ycbcr_420_allowed = params->yuv420_allowed; + + ret = drmm_connector_hdmi_init(&priv->drm, &priv->connector, + "Vendor", "Product", + &dummy_funcs, + &dummy_hdmi_funcs, + DRM_MODE_CONNECTOR_HDMIA, + &priv->ddc, + params->supported_formats, + 8); + KUNIT_EXPECT_EQ(test, ret, params->expected_result); +} + /* * Test that the registration of an HDMI connector with an HDMI * connector type succeeds. @@ -1186,6 +1244,8 @@ static struct kunit_case drmm_connector_hdmi_init_tests[] = { KUNIT_CASE(drm_test_connector_hdmi_init_bpc_null), KUNIT_CASE(drm_test_connector_hdmi_init_formats_empty), KUNIT_CASE(drm_test_connector_hdmi_init_formats_no_rgb), + KUNIT_CASE_PARAM(drm_test_connector_hdmi_init_formats_yuv420_allowed, + drm_connector_hdmi_init_formats_yuv420_allowed_gen_params), KUNIT_CASE(drm_test_connector_hdmi_init_null_ddc), KUNIT_CASE(drm_test_connector_hdmi_init_null_product), KUNIT_CASE(drm_test_connector_hdmi_init_null_vendor), diff --git a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c index c3b693bb966f..b976a5e9aef5 100644 --- a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c +++ b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c @@ -1568,6 +1568,57 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); } +/* Test that atomic check succeeds when disabling a connector. */ +static void drm_test_check_disable_connector(struct kunit *test) +{ + struct drm_atomic_helper_connector_hdmi_priv *priv; + struct drm_modeset_acquire_ctx *ctx; + struct drm_connector_state *conn_state; + struct drm_crtc_state *crtc_state; + struct drm_atomic_state *state; + struct drm_display_mode *preferred; + struct drm_connector *conn; + struct drm_device *drm; + struct drm_crtc *crtc; + int ret; + + priv = drm_kunit_helper_connector_hdmi_init(test, + BIT(HDMI_COLORSPACE_RGB), + 8); + KUNIT_ASSERT_NOT_NULL(test, priv); + + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + + conn = &priv->connector; + preferred = find_preferred_mode(conn); + KUNIT_ASSERT_NOT_NULL(test, preferred); + + drm = &priv->drm; + crtc = priv->crtc; + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + KUNIT_ASSERT_EQ(test, ret, 0); + + state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); + + crtc_state = drm_atomic_get_crtc_state(state, crtc); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_state); + + crtc_state->active = false; + ret = drm_atomic_set_mode_for_crtc(crtc_state, NULL); + KUNIT_EXPECT_EQ(test, ret, 0); + + conn_state = drm_atomic_get_connector_state(state, conn); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, conn_state); + + ret = drm_atomic_set_crtc_for_connector(conn_state, NULL); + KUNIT_EXPECT_EQ(test, ret, 0); + + ret = drm_atomic_check_only(state); + KUNIT_ASSERT_EQ(test, ret, 0); +} + static struct kunit_case drm_atomic_helper_connector_hdmi_check_tests[] = { KUNIT_CASE(drm_test_check_broadcast_rgb_auto_cea_mode), KUNIT_CASE(drm_test_check_broadcast_rgb_auto_cea_mode_vic_1), @@ -1582,6 +1633,7 @@ static struct kunit_case drm_atomic_helper_connector_hdmi_check_tests[] = { */ KUNIT_CASE(drm_test_check_broadcast_rgb_crtc_mode_changed), KUNIT_CASE(drm_test_check_broadcast_rgb_crtc_mode_not_changed), + KUNIT_CASE(drm_test_check_disable_connector), KUNIT_CASE(drm_test_check_hdmi_funcs_reject_rate), KUNIT_CASE(drm_test_check_max_tmds_rate_bpc_fallback), KUNIT_CASE(drm_test_check_max_tmds_rate_format_fallback), diff --git a/drivers/gpu/drm/tests/drm_kunit_helpers.c b/drivers/gpu/drm/tests/drm_kunit_helpers.c index 04a6b8cc62ac..3c0b7824c0be 100644 --- a/drivers/gpu/drm/tests/drm_kunit_helpers.c +++ b/drivers/gpu/drm/tests/drm_kunit_helpers.c @@ -320,8 +320,7 @@ static void kunit_action_drm_mode_destroy(void *ptr) } /** - * drm_kunit_display_mode_from_cea_vic() - return a mode for CEA VIC - for a KUnit test + * drm_kunit_display_mode_from_cea_vic() - return a mode for CEA VIC for a KUnit test * @test: The test context object * @dev: DRM device * @video_code: CEA VIC of the mode diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c index 89a699370a59..c67e1f906785 100644 --- a/drivers/gpu/drm/tiny/bochs.c +++ b/drivers/gpu/drm/tiny/bochs.c @@ -757,7 +757,6 @@ static void bochs_pci_remove(struct pci_dev *pdev) drm_dev_unplug(dev); drm_atomic_helper_shutdown(dev); - drm_dev_put(dev); } static void bochs_pci_shutdown(struct pci_dev *pdev) diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c index 3139fd9128d8..f8f20d2f6174 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c +++ b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c @@ -258,13 +258,13 @@ static void ttm_bo_unreserve_basic(struct kunit *test) bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); bo->priority = bo_prio; - err = ttm_resource_alloc(bo, place, &res1); + err = ttm_resource_alloc(bo, place, &res1, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res1; /* Add a dummy resource to populate LRU */ - ttm_resource_alloc(bo, place, &res2); + ttm_resource_alloc(bo, place, &res2, NULL); dma_resv_lock(bo->base.resv, NULL); ttm_bo_unreserve(bo); @@ -300,12 +300,12 @@ static void ttm_bo_unreserve_pinned(struct kunit *test) dma_resv_lock(bo->base.resv, NULL); ttm_bo_pin(bo); - err = ttm_resource_alloc(bo, place, &res1); + err = ttm_resource_alloc(bo, place, &res1, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res1; /* Add a dummy resource to the pinned list */ - err = ttm_resource_alloc(bo, place, &res2); + err = ttm_resource_alloc(bo, place, &res2, NULL); KUNIT_ASSERT_EQ(test, err, 0); KUNIT_ASSERT_EQ(test, list_is_last(&res2->lru.link, &priv->ttm_dev->unevictable), 1); @@ -355,7 +355,7 @@ static void ttm_bo_unreserve_bulk(struct kunit *test) ttm_bo_set_bulk_move(bo1, &lru_bulk_move); dma_resv_unlock(bo1->base.resv); - err = ttm_resource_alloc(bo1, place, &res1); + err = ttm_resource_alloc(bo1, place, &res1, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo1->resource = res1; @@ -363,7 +363,7 @@ static void ttm_bo_unreserve_bulk(struct kunit *test) ttm_bo_set_bulk_move(bo2, &lru_bulk_move); dma_resv_unlock(bo2->base.resv); - err = ttm_resource_alloc(bo2, place, &res2); + err = ttm_resource_alloc(bo2, place, &res2, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo2->resource = res2; @@ -401,7 +401,7 @@ static void ttm_bo_put_basic(struct kunit *test) bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); bo->type = ttm_bo_type_device; - err = ttm_resource_alloc(bo, place, &res); + err = ttm_resource_alloc(bo, place, &res, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res; @@ -518,7 +518,7 @@ static void ttm_bo_pin_unpin_resource(struct kunit *test) bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); - err = ttm_resource_alloc(bo, place, &res); + err = ttm_resource_alloc(bo, place, &res, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res; @@ -569,7 +569,7 @@ static void ttm_bo_multiple_pin_one_unpin(struct kunit *test) bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL); - err = ttm_resource_alloc(bo, place, &res); + err = ttm_resource_alloc(bo, place, &res, NULL); KUNIT_ASSERT_EQ(test, err, 0); bo->resource = res; diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c index 1adf18481ea0..3148f5d3dbd6 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c +++ b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c @@ -542,7 +542,7 @@ static void ttm_bo_validate_no_placement_signaled(struct kunit *test) bo->ttm = old_tt; } - err = ttm_resource_alloc(bo, place, &bo->resource); + err = ttm_resource_alloc(bo, place, &bo->resource, NULL); KUNIT_EXPECT_EQ(test, err, 0); KUNIT_ASSERT_EQ(test, man->usage, size); @@ -603,7 +603,7 @@ static void ttm_bo_validate_no_placement_not_signaled(struct kunit *test) bo = ttm_bo_kunit_init(test, test->priv, size, NULL); bo->type = params->bo_type; - err = ttm_resource_alloc(bo, place, &bo->resource); + err = ttm_resource_alloc(bo, place, &bo->resource, NULL); KUNIT_EXPECT_EQ(test, err, 0); placement = kunit_kzalloc(test, sizeof(*placement), GFP_KERNEL); diff --git a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c index a9f4b81921c3..e6ea2bd01f07 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c +++ b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c @@ -302,7 +302,7 @@ static void ttm_sys_man_free_basic(struct kunit *test) res = kunit_kzalloc(test, sizeof(*res), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, res); - ttm_resource_alloc(bo, place, &res); + ttm_resource_alloc(bo, place, &res, NULL); man = ttm_manager_type(priv->devs->ttm_dev, mem_type); man->func->free(man, res); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 48c5365efca1..ea5e49858857 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include "ttm_module.h" @@ -499,6 +500,13 @@ struct ttm_bo_evict_walk { struct ttm_resource **res; /** @evicted: Number of successful evictions. */ unsigned long evicted; + + /** @limit_pool: Which pool limit we should test against */ + struct dmem_cgroup_pool_state *limit_pool; + /** @try_low: Whether we should attempt to evict BO's with low watermark threshold */ + bool try_low; + /** @hit_low: If we cannot evict a bo when @try_low is false (first pass) */ + bool hit_low; }; static s64 ttm_bo_evict_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo) @@ -507,6 +515,10 @@ static s64 ttm_bo_evict_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object * container_of(walk, typeof(*evict_walk), walk); s64 lret; + if (!dmem_cgroup_state_evict_valuable(evict_walk->limit_pool, bo->resource->css, + evict_walk->try_low, &evict_walk->hit_low)) + return 0; + if (bo->pin_count || !bo->bdev->funcs->eviction_valuable(bo, evict_walk->place)) return 0; @@ -524,7 +536,7 @@ static s64 ttm_bo_evict_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object * evict_walk->evicted++; if (evict_walk->res) lret = ttm_resource_alloc(evict_walk->evictor, evict_walk->place, - evict_walk->res); + evict_walk->res, NULL); if (lret == 0) return 1; out: @@ -545,7 +557,8 @@ static int ttm_bo_evict_alloc(struct ttm_device *bdev, struct ttm_buffer_object *evictor, struct ttm_operation_ctx *ctx, struct ww_acquire_ctx *ticket, - struct ttm_resource **res) + struct ttm_resource **res, + struct dmem_cgroup_pool_state *limit_pool) { struct ttm_bo_evict_walk evict_walk = { .walk = { @@ -556,22 +569,39 @@ static int ttm_bo_evict_alloc(struct ttm_device *bdev, .place = place, .evictor = evictor, .res = res, + .limit_pool = limit_pool, }; s64 lret; evict_walk.walk.trylock_only = true; lret = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man, 1); + + /* One more attempt if we hit low limit? */ + if (!lret && evict_walk.hit_low) { + evict_walk.try_low = true; + lret = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man, 1); + } if (lret || !ticket) goto out; + /* Reset low limit */ + evict_walk.try_low = evict_walk.hit_low = false; /* If ticket-locking, repeat while making progress. */ evict_walk.walk.trylock_only = false; + +retry: do { /* The walk may clear the evict_walk.walk.ticket field */ evict_walk.walk.ticket = ticket; evict_walk.evicted = 0; lret = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man, 1); } while (!lret && evict_walk.evicted); + + /* We hit the low limit? Try once more */ + if (!lret && evict_walk.hit_low && !evict_walk.try_low) { + evict_walk.try_low = true; + goto retry; + } out: if (lret < 0) return lret; @@ -689,6 +719,7 @@ static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo, for (i = 0; i < placement->num_placement; ++i) { const struct ttm_place *place = &placement->placement[i]; + struct dmem_cgroup_pool_state *limit_pool = NULL; struct ttm_resource_manager *man; bool may_evict; @@ -701,15 +732,20 @@ static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo, continue; may_evict = (force_space && place->mem_type != TTM_PL_SYSTEM); - ret = ttm_resource_alloc(bo, place, res); + ret = ttm_resource_alloc(bo, place, res, force_space ? &limit_pool : NULL); if (ret) { - if (ret != -ENOSPC) + if (ret != -ENOSPC && ret != -EAGAIN) { + dmem_cgroup_pool_state_put(limit_pool); return ret; - if (!may_evict) + } + if (!may_evict) { + dmem_cgroup_pool_state_put(limit_pool); continue; + } ret = ttm_bo_evict_alloc(bdev, man, place, bo, ctx, - ticket, res); + ticket, res, limit_pool); + dmem_cgroup_pool_state_put(limit_pool); if (ret == -EBUSY) continue; if (ret) @@ -1056,6 +1092,8 @@ struct ttm_bo_swapout_walk { struct ttm_lru_walk walk; /** @gfp_flags: The gfp flags to use for ttm_tt_swapout() */ gfp_t gfp_flags; + + bool hit_low, evict_low; }; static s64 @@ -1106,7 +1144,7 @@ ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo) memset(&hop, 0, sizeof(hop)); place.mem_type = TTM_PL_SYSTEM; - ret = ttm_resource_alloc(bo, &place, &evict_mem); + ret = ttm_resource_alloc(bo, &place, &evict_mem, NULL); if (ret) goto out; diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index a87665eb28a6..cc29bbf3eabb 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -350,15 +351,28 @@ EXPORT_SYMBOL(ttm_resource_fini); int ttm_resource_alloc(struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource **res_ptr) + struct ttm_resource **res_ptr, + struct dmem_cgroup_pool_state **ret_limit_pool) { struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, place->mem_type); + struct dmem_cgroup_pool_state *pool = NULL; int ret; + if (man->cg) { + ret = dmem_cgroup_try_charge(man->cg, bo->base.size, &pool, ret_limit_pool); + if (ret) + return ret; + } + ret = man->func->alloc(man, bo, place, res_ptr); - if (ret) + if (ret) { + if (pool) + dmem_cgroup_uncharge(pool, bo->base.size); return ret; + } + + (*res_ptr)->css = pool; spin_lock(&bo->bdev->lru_lock); ttm_resource_add_bulk_move(*res_ptr, bo); @@ -370,6 +384,7 @@ EXPORT_SYMBOL_FOR_TESTS_ONLY(ttm_resource_alloc); void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res) { struct ttm_resource_manager *man; + struct dmem_cgroup_pool_state *pool; if (!*res) return; @@ -377,9 +392,13 @@ void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res) spin_lock(&bo->bdev->lru_lock); ttm_resource_del_bulk_move(*res, bo); spin_unlock(&bo->bdev->lru_lock); + + pool = (*res)->css; man = ttm_manager_type(bo->bdev, (*res)->mem_type); man->func->free(man, *res); *res = NULL; + if (man->cg) + dmem_cgroup_uncharge(pool, bo->base.size); } EXPORT_SYMBOL(ttm_resource_free); diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c index 20bf33702c3c..72b6a119412f 100644 --- a/drivers/gpu/drm/v3d/v3d_irq.c +++ b/drivers/gpu/drm/v3d/v3d_irq.c @@ -107,7 +107,10 @@ v3d_irq(int irq, void *arg) v3d_job_update_stats(&v3d->bin_job->base, V3D_BIN); trace_v3d_bcl_irq(&v3d->drm, fence->seqno); + + v3d->bin_job = NULL; dma_fence_signal(&fence->base); + status = IRQ_HANDLED; } @@ -117,7 +120,10 @@ v3d_irq(int irq, void *arg) v3d_job_update_stats(&v3d->render_job->base, V3D_RENDER); trace_v3d_rcl_irq(&v3d->drm, fence->seqno); + + v3d->render_job = NULL; dma_fence_signal(&fence->base); + status = IRQ_HANDLED; } @@ -127,7 +133,10 @@ v3d_irq(int irq, void *arg) v3d_job_update_stats(&v3d->csd_job->base, V3D_CSD); trace_v3d_csd_irq(&v3d->drm, fence->seqno); + + v3d->csd_job = NULL; dma_fence_signal(&fence->base); + status = IRQ_HANDLED; } @@ -164,7 +173,10 @@ v3d_hub_irq(int irq, void *arg) v3d_job_update_stats(&v3d->tfu_job->base, V3D_TFU); trace_v3d_tfu_irq(&v3d->drm, fence->seqno); + + v3d->tfu_job = NULL; dma_fence_signal(&fence->base); + status = IRQ_HANDLED; } diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig index c5f30b317698..6cc7b7e6294a 100644 --- a/drivers/gpu/drm/vc4/Kconfig +++ b/drivers/gpu/drm/vc4/Kconfig @@ -10,6 +10,7 @@ config DRM_VC4 depends on COMMON_CLK depends on PM select DRM_CLIENT_SELECTION + select DRM_DISPLAY_HDMI_AUDIO_HELPER select DRM_DISPLAY_HDMI_HELPER select DRM_DISPLAY_HDMI_STATE_HELPER select DRM_DISPLAY_HELPER diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 203293a8beca..47d9ada98430 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -31,6 +31,7 @@ * encoder block has CEC support. */ +#include #include #include #include @@ -383,7 +384,6 @@ static void vc4_hdmi_handle_hotplug(struct vc4_hdmi *vc4_hdmi, enum drm_connector_status status) { struct drm_connector *connector = &vc4_hdmi->connector; - const struct drm_edid *drm_edid; int ret; /* @@ -405,17 +405,14 @@ static void vc4_hdmi_handle_hotplug(struct vc4_hdmi *vc4_hdmi, return; } - drm_edid = drm_edid_read_ddc(connector, vc4_hdmi->ddc); + drm_atomic_helper_connector_hdmi_hotplug(connector, status); - drm_edid_connector_update(connector, drm_edid); cec_s_phys_addr(vc4_hdmi->cec_adap, connector->display_info.source_physical_address, false); - if (!drm_edid) + if (status != connector_status_connected) return; - drm_edid_free(drm_edid); - for (;;) { ret = vc4_hdmi_reset_link(connector, ctx); if (ret == -EDEADLK) { @@ -470,31 +467,10 @@ static int vc4_hdmi_connector_detect_ctx(struct drm_connector *connector, static int vc4_hdmi_connector_get_modes(struct drm_connector *connector) { - struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); struct vc4_dev *vc4 = to_vc4_dev(connector->dev); - const struct drm_edid *drm_edid; int ret = 0; - /* - * NOTE: This function should really take vc4_hdmi->mutex, but doing so - * results in reentrancy issues since cec_s_phys_addr() might call - * .adap_enable, which leads to that funtion being called with our mutex - * held. - * - * Concurrency isn't an issue at the moment since we don't share - * any state with any of the other frameworks so we can ignore - * the lock for now. - */ - - drm_edid = drm_edid_read_ddc(connector, vc4_hdmi->ddc); - drm_edid_connector_update(connector, drm_edid); - cec_s_phys_addr(vc4_hdmi->cec_adap, - connector->display_info.source_physical_address, false); - if (!drm_edid) - return 0; - ret = drm_edid_connector_add_modes(connector); - drm_edid_free(drm_edid); if (!vc4->hvs->vc5_hdmi_enable_hdmi_20) { struct drm_device *drm = connector->dev; @@ -570,6 +546,7 @@ static void vc4_hdmi_connector_reset(struct drm_connector *connector) } static const struct drm_connector_funcs vc4_hdmi_connector_funcs = { + .force = drm_atomic_helper_connector_hdmi_force, .fill_modes = drm_helper_probe_single_connector_modes, .reset = vc4_hdmi_connector_reset, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, @@ -584,6 +561,7 @@ static const struct drm_connector_helper_funcs vc4_hdmi_connector_helper_funcs = }; static const struct drm_connector_hdmi_funcs vc4_hdmi_hdmi_connector_funcs; +static const struct drm_connector_hdmi_audio_funcs vc4_hdmi_audio_funcs; static int vc4_hdmi_connector_init(struct drm_device *dev, struct vc4_hdmi *vc4_hdmi) @@ -609,6 +587,12 @@ static int vc4_hdmi_connector_init(struct drm_device *dev, if (ret) return ret; + ret = drm_connector_hdmi_audio_init(connector, dev->dev, + &vc4_hdmi_audio_funcs, + 8, false, -1); + if (ret) + return ret; + drm_connector_helper_add(connector, &vc4_hdmi_connector_helper_funcs); /* @@ -1921,9 +1905,9 @@ static bool vc4_hdmi_audio_can_stream(struct vc4_hdmi *vc4_hdmi) return true; } -static int vc4_hdmi_audio_startup(struct device *dev, void *data) +static int vc4_hdmi_audio_startup(struct drm_connector *connector) { - struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); + struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); struct drm_device *drm = vc4_hdmi->connector.dev; unsigned long flags; int ret = 0; @@ -1985,9 +1969,9 @@ static void vc4_hdmi_audio_reset(struct vc4_hdmi *vc4_hdmi) spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags); } -static void vc4_hdmi_audio_shutdown(struct device *dev, void *data) +static void vc4_hdmi_audio_shutdown(struct drm_connector *connector) { - struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); + struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); struct drm_device *drm = vc4_hdmi->connector.dev; unsigned long flags; int idx; @@ -2057,13 +2041,12 @@ static int sample_rate_to_mai_fmt(int samplerate) } /* HDMI audio codec callbacks */ -static int vc4_hdmi_audio_prepare(struct device *dev, void *data, +static int vc4_hdmi_audio_prepare(struct drm_connector *connector, struct hdmi_codec_daifmt *daifmt, struct hdmi_codec_params *params) { - struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); + struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); struct drm_device *drm = vc4_hdmi->connector.dev; - struct drm_connector *connector = &vc4_hdmi->connector; struct vc4_dev *vc4 = to_vc4_dev(drm); unsigned int sample_rate = params->sample_rate; unsigned int channels = params->channels; @@ -2075,7 +2058,7 @@ static int vc4_hdmi_audio_prepare(struct device *dev, void *data, int ret = 0; int idx; - dev_dbg(dev, "%s: %u Hz, %d bit, %d channels\n", __func__, + dev_dbg(&vc4_hdmi->pdev->dev, "%s: %u Hz, %d bit, %d channels\n", __func__, sample_rate, params->sample_width, channels); mutex_lock(&vc4_hdmi->mutex); @@ -2214,40 +2197,12 @@ static const struct snd_dmaengine_pcm_config pcm_conf = { .prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config, }; -static int vc4_hdmi_audio_get_eld(struct device *dev, void *data, - uint8_t *buf, size_t len) -{ - struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); - struct drm_connector *connector = &vc4_hdmi->connector; - - mutex_lock(&connector->eld_mutex); - memcpy(buf, connector->eld, min(sizeof(connector->eld), len)); - mutex_unlock(&connector->eld_mutex); - - return 0; -} - -static const struct hdmi_codec_ops vc4_hdmi_codec_ops = { - .get_eld = vc4_hdmi_audio_get_eld, +static const struct drm_connector_hdmi_audio_funcs vc4_hdmi_audio_funcs = { + .startup = vc4_hdmi_audio_startup, .prepare = vc4_hdmi_audio_prepare, - .audio_shutdown = vc4_hdmi_audio_shutdown, - .audio_startup = vc4_hdmi_audio_startup, + .shutdown = vc4_hdmi_audio_shutdown, }; -static struct hdmi_codec_pdata vc4_hdmi_codec_pdata = { - .ops = &vc4_hdmi_codec_ops, - .max_i2s_channels = 8, - .i2s = 1, -}; - -static void vc4_hdmi_audio_codec_release(void *ptr) -{ - struct vc4_hdmi *vc4_hdmi = ptr; - - platform_device_unregister(vc4_hdmi->audio.codec_pdev); - vc4_hdmi->audio.codec_pdev = NULL; -} - static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) { const struct vc4_hdmi_register *mai_data = @@ -2255,7 +2210,6 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) struct snd_soc_dai_link *dai_link = &vc4_hdmi->audio.link; struct snd_soc_card *card = &vc4_hdmi->audio.card; struct device *dev = &vc4_hdmi->pdev->dev; - struct platform_device *codec_pdev; const __be32 *addr; int index, len; int ret; @@ -2348,20 +2302,6 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) return ret; } - codec_pdev = platform_device_register_data(dev, HDMI_CODEC_DRV_NAME, - PLATFORM_DEVID_AUTO, - &vc4_hdmi_codec_pdata, - sizeof(vc4_hdmi_codec_pdata)); - if (IS_ERR(codec_pdev)) { - dev_err(dev, "Couldn't register the HDMI codec: %ld\n", PTR_ERR(codec_pdev)); - return PTR_ERR(codec_pdev); - } - vc4_hdmi->audio.codec_pdev = codec_pdev; - - ret = devm_add_action_or_reset(dev, vc4_hdmi_audio_codec_release, vc4_hdmi); - if (ret) - return ret; - dai_link->cpus = &vc4_hdmi->audio.cpu; dai_link->codecs = &vc4_hdmi->audio.codec; dai_link->platforms = &vc4_hdmi->audio.platform; @@ -2374,7 +2314,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) dai_link->stream_name = "MAI PCM"; dai_link->codecs->dai_name = "i2s-hifi"; dai_link->cpus->dai_name = dev_name(dev); - dai_link->codecs->name = dev_name(&codec_pdev->dev); + dai_link->codecs->name = dev_name(&vc4_hdmi->connector.hdmi_audio.codec_pdev->dev); dai_link->platforms->name = dev_name(dev); card->dai_link = dai_link; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index b2424a21da23..e3d989ca302b 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -104,8 +104,6 @@ struct vc4_hdmi_audio { struct snd_soc_dai_link_component codec; struct snd_soc_dai_link_component platform; struct snd_dmaengine_dai_dma_data dma_data; - struct hdmi_audio_infoframe infoframe; - struct platform_device *codec_pdev; bool streaming; }; diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c index b3664c12843d..f92133a01195 100644 --- a/drivers/gpu/drm/virtio/virtgpu_prime.c +++ b/drivers/gpu/drm/virtio/virtgpu_prime.c @@ -189,10 +189,11 @@ static void virtgpu_dma_buf_free_obj(struct drm_gem_object *obj) struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj); struct virtio_gpu_device *vgdev = obj->dev->dev_private; struct dma_buf_attachment *attach = obj->import_attach; - struct dma_resv *resv = attach->dmabuf->resv; if (attach) { - dma_resv_lock(resv, NULL); + struct dma_buf *dmabuf = attach->dmabuf; + + dma_resv_lock(dmabuf->resv, NULL); virtio_gpu_detach_object_fenced(bo); @@ -200,10 +201,10 @@ static void virtgpu_dma_buf_free_obj(struct drm_gem_object *obj) dma_buf_unmap_attachment(attach, bo->sgt, DMA_BIDIRECTIONAL); - dma_resv_unlock(resv); + dma_resv_unlock(dmabuf->resv); - dma_buf_detach(attach->dmabuf, attach); - dma_buf_put(attach->dmabuf); + dma_buf_detach(dmabuf, attach); + dma_buf_put(dmabuf); } if (bo->created) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index a0e433fbcba6..9b5b8c1f063b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -228,7 +228,6 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, VMW_BO_DOMAIN_VRAM, VMW_BO_DOMAIN_VRAM); buf->places[0].lpfn = PFN_UP(bo->resource->size); - buf->busy_places[0].lpfn = PFN_UP(bo->resource->size); ret = ttm_bo_validate(bo, &buf->placement, &ctx); /* For some reason we didn't end up at the start of vram */ @@ -443,7 +442,8 @@ static int vmw_bo_init(struct vmw_private *dev_priv, if (params->pin) ttm_bo_pin(&vmw_bo->tbo); - ttm_bo_unreserve(&vmw_bo->tbo); + if (!params->keep_resv) + ttm_bo_unreserve(&vmw_bo->tbo); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h index 43b5439ec9f7..11e330c7c7f5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h @@ -56,8 +56,9 @@ struct vmw_bo_params { u32 domain; u32 busy_domain; enum ttm_bo_type bo_type; - size_t size; bool pin; + bool keep_resv; + size_t size; struct dma_resv *resv; struct sg_table *sg; }; @@ -83,7 +84,6 @@ struct vmw_bo { struct ttm_placement placement; struct ttm_place places[5]; - struct ttm_place busy_places[5]; /* Protected by reservation */ struct ttm_bo_kmap_obj map; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 1699236fca5a..0f32471c8533 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -403,7 +403,8 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv) .busy_domain = VMW_BO_DOMAIN_SYS, .bo_type = ttm_bo_type_kernel, .size = PAGE_SIZE, - .pin = true + .pin = true, + .keep_resv = true, }; /* @@ -415,10 +416,6 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv) if (unlikely(ret != 0)) return ret; - ret = ttm_bo_reserve(&vbo->tbo, false, true, NULL); - BUG_ON(ret != 0); - vmw_bo_pin_reserved(vbo, true); - ret = ttm_bo_kmap(&vbo->tbo, 0, 1, &map); if (likely(ret == 0)) { result = ttm_kmap_obj_virtual(&map, &dummy); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index b9857f37ca1a..ed5015ced392 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -206,6 +206,7 @@ struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev, .bo_type = ttm_bo_type_sg, .size = attach->dmabuf->size, .pin = false, + .keep_resv = true, .resv = attach->dmabuf->resv, .sg = table, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 8db38927729b..800a79e035ed 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -750,6 +750,7 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, struct vmw_plane_state *old_vps = vmw_plane_state_to_vps(old_state); struct vmw_bo *old_bo = NULL; struct vmw_bo *new_bo = NULL; + struct ww_acquire_ctx ctx; s32 hotspot_x, hotspot_y; int ret; @@ -769,9 +770,11 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, if (du->cursor_surface) du->cursor_age = du->cursor_surface->snooper.age; + ww_acquire_init(&ctx, &reservation_ww_class); + if (!vmw_user_object_is_null(&old_vps->uo)) { old_bo = vmw_user_object_buffer(&old_vps->uo); - ret = ttm_bo_reserve(&old_bo->tbo, false, false, NULL); + ret = ttm_bo_reserve(&old_bo->tbo, false, false, &ctx); if (ret != 0) return; } @@ -779,9 +782,14 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, if (!vmw_user_object_is_null(&vps->uo)) { new_bo = vmw_user_object_buffer(&vps->uo); if (old_bo != new_bo) { - ret = ttm_bo_reserve(&new_bo->tbo, false, false, NULL); - if (ret != 0) + ret = ttm_bo_reserve(&new_bo->tbo, false, false, &ctx); + if (ret != 0) { + if (old_bo) { + ttm_bo_unreserve(&old_bo->tbo); + ww_acquire_fini(&ctx); + } return; + } } else { new_bo = NULL; } @@ -803,10 +811,12 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, hotspot_x, hotspot_y); } - if (old_bo) - ttm_bo_unreserve(&old_bo->tbo); if (new_bo) ttm_bo_unreserve(&new_bo->tbo); + if (old_bo) + ttm_bo_unreserve(&old_bo->tbo); + + ww_acquire_fini(&ctx); du->cursor_x = new_state->crtc_x + du->set_gui_x; du->cursor_y = new_state->crtc_y + du->set_gui_y; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index a01ca3226d0a..7fb1c88bcc47 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -896,7 +896,8 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv, .busy_domain = VMW_BO_DOMAIN_SYS, .bo_type = ttm_bo_type_device, .size = size, - .pin = true + .pin = true, + .keep_resv = true, }; if (!vmw_shader_id_ok(user_key, shader_type)) @@ -906,10 +907,6 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv, if (unlikely(ret != 0)) goto out; - ret = ttm_bo_reserve(&buf->tbo, false, true, NULL); - if (unlikely(ret != 0)) - goto no_reserve; - /* Map and copy shader bytecode. */ ret = ttm_bo_kmap(&buf->tbo, 0, PFN_UP(size), &map); if (unlikely(ret != 0)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 621d98b376bb..5553892d7c3e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -572,15 +572,14 @@ int vmw_bo_create_and_populate(struct vmw_private *dev_priv, .busy_domain = domain, .bo_type = ttm_bo_type_kernel, .size = bo_size, - .pin = true + .pin = true, + .keep_resv = true, }; ret = vmw_bo_create(dev_priv, &bo_params, &vbo); if (unlikely(ret != 0)) return ret; - ret = ttm_bo_reserve(&vbo->tbo, false, true, NULL); - BUG_ON(ret != 0); ret = vmw_ttm_populate(vbo->tbo.bdev, vbo->tbo.ttm, &ctx); if (likely(ret == 0)) { struct vmw_ttm_tt *vmw_tt = diff --git a/drivers/gpu/drm/xe/Kconfig.debug b/drivers/gpu/drm/xe/Kconfig.debug index 2de0de41b8dd..0d749ed44878 100644 --- a/drivers/gpu/drm/xe/Kconfig.debug +++ b/drivers/gpu/drm/xe/Kconfig.debug @@ -66,7 +66,7 @@ config DRM_XE_DEBUG_MEM bool "Enable passing SYS/VRAM addresses to user space" default n help - Pass object location trough uapi. Intended for extended + Pass object location through uapi. Intended for extended testing and development only. Recommended for driver developers only. @@ -104,5 +104,5 @@ config DRM_XE_USERPTR_INVAL_INJECT Choose this option when debugging error paths that are hit during checks for userptr invalidations. - Recomended for driver developers only. + Recommended for driver developers only. If in doubt, say "N". diff --git a/drivers/gpu/drm/xe/abi/guc_capture_abi.h b/drivers/gpu/drm/xe/abi/guc_capture_abi.h index e7898edc6236..dd4117553739 100644 --- a/drivers/gpu/drm/xe/abi/guc_capture_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_capture_abi.h @@ -25,7 +25,7 @@ enum guc_state_capture_type { #define GUC_STATE_CAPTURE_TYPE_MAX (GUC_STATE_CAPTURE_TYPE_ENGINE_INSTANCE + 1) -/* Class indecies for capture_class and capture_instance arrays */ +/* Class indices for capture_class and capture_instance arrays */ enum guc_capture_list_class_type { GUC_CAPTURE_LIST_CLASS_RENDER_COMPUTE = 0, GUC_CAPTURE_LIST_CLASS_VIDEO = 1, diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h index 7dcb118e3d9f..d633f1c739e4 100644 --- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h @@ -132,7 +132,7 @@ enum { * _`GUC_KLV_VGT_POLICY_SCHED_IF_IDLE` : 0x8001 * This config sets whether strict scheduling is enabled whereby any VF * that doesn’t have work to submit is still allocated a fixed execution - * time-slice to ensure active VFs execution is always consitent even + * time-slice to ensure active VFs execution is always consistent even * during other VF reprovisiong / rebooting events. Changing this KLV * impacts all VFs and takes effect on the next VF-Switch event. * @@ -207,7 +207,7 @@ enum { * of and this will never be perfectly-exact (accumulated nano-second * granularity) since the GPUs clock time runs off a different crystal * from the CPUs clock. Changing this KLV on a VF that is currently - * running a context wont take effect until a new context is scheduled in. + * running a context won't take effect until a new context is scheduled in. * That said, when the PF is changing this value from 0x0 to * a non-zero value, it might never take effect if the VF is running an * infinitely long compute or shader kernel. In such a scenario, the @@ -227,7 +227,7 @@ enum { * HW is capable and this will never be perfectly-exact (accumulated * nano-second granularity) since the GPUs clock time runs off a * different crystal from the CPUs clock. Changing this KLV on a VF - * that is currently running a context wont take effect until a new + * that is currently running a context won't take effect until a new * context is scheduled in. * That said, when the PF is changing this value from 0x0 to * a non-zero value, it might never take effect if the VF is running an diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h index 7c78496e6213..d86219dedde2 100644 --- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h @@ -83,6 +83,8 @@ #define RING_IMR(base) XE_REG((base) + 0xa8) #define RING_INT_STATUS_RPT_PTR(base) XE_REG((base) + 0xac) +#define CS_INT_VEC(base) XE_REG((base) + 0x1b8) + #define RING_EIR(base) XE_REG((base) + 0xb0) #define RING_EMR(base) XE_REG((base) + 0xb4) #define RING_ESR(base) XE_REG((base) + 0xb8) @@ -138,6 +140,7 @@ #define RING_MODE(base) XE_REG((base) + 0x29c) #define GFX_DISABLE_LEGACY_MODE REG_BIT(3) +#define GFX_MSIX_INTERRUPT_ENABLE REG_BIT(13) #define RING_TIMESTAMP(base) XE_REG((base) + 0x358) diff --git a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h index 045dfd09db99..57944f90bbf6 100644 --- a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h +++ b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h @@ -25,6 +25,9 @@ #define CTX_INT_SRC_REPORT_REG (CTX_LRI_INT_REPORT_PTR + 3) #define CTX_INT_SRC_REPORT_PTR (CTX_LRI_INT_REPORT_PTR + 4) +#define CTX_CS_INT_VEC_REG 0x5a +#define CTX_CS_INT_VEC_DATA (CTX_CS_INT_VEC_REG + 1) + #define INDIRECT_CTX_RING_HEAD (0x02 + 1) #define INDIRECT_CTX_RING_TAIL (0x04 + 1) #define INDIRECT_CTX_RING_START (0x06 + 1) diff --git a/drivers/gpu/drm/xe/regs/xe_reg_defs.h b/drivers/gpu/drm/xe/regs/xe_reg_defs.h index 51fd40ffafcb..0eedd6c26b1b 100644 --- a/drivers/gpu/drm/xe/regs/xe_reg_defs.h +++ b/drivers/gpu/drm/xe/regs/xe_reg_defs.h @@ -13,7 +13,7 @@ /** * struct xe_reg - Register definition * - * Register defintion to be used by the individual register. Although the same + * Register definition to be used by the individual register. Although the same * definition is used for xe_reg and xe_reg_mcr, they use different internal * APIs for accesses. */ diff --git a/drivers/gpu/drm/xe/regs/xe_regs.h b/drivers/gpu/drm/xe/regs/xe_regs.h index 3293172b0128..6cf282618836 100644 --- a/drivers/gpu/drm/xe/regs/xe_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_regs.h @@ -44,12 +44,16 @@ #define MTL_RP_STATE_CAP XE_REG(0x138000) +#define MTL_GT_RPA_FREQUENCY XE_REG(0x138008) #define MTL_GT_RPE_FREQUENCY XE_REG(0x13800c) #define MTL_MEDIAP_STATE_CAP XE_REG(0x138020) #define MTL_RPN_CAP_MASK REG_GENMASK(24, 16) #define MTL_RP0_CAP_MASK REG_GENMASK(8, 0) +#define MTL_MPA_FREQUENCY XE_REG(0x138028) +#define MTL_RPA_MASK REG_GENMASK(8, 0) + #define MTL_MPE_FREQUENCY XE_REG(0x13802c) #define MTL_RPE_MASK REG_GENMASK(8, 0) diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c index c9ec7a313c6b..6795d1d916e4 100644 --- a/drivers/gpu/drm/xe/tests/xe_bo.c +++ b/drivers/gpu/drm/xe/tests/xe_bo.c @@ -264,10 +264,9 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc * however seems quite fragile not to also restart the GT. Try * to do that here by triggering a GT reset. */ - for_each_gt(__gt, xe, id) { - xe_gt_reset_async(__gt); - flush_work(&__gt->reset.worker); - } + for_each_gt(__gt, xe, id) + xe_gt_reset(__gt); + if (err) { KUNIT_FAIL(test, "restore kernel err=%pe\n", ERR_PTR(err)); @@ -606,8 +605,6 @@ static void xe_bo_shrink_kunit(struct kunit *test) static struct kunit_case xe_bo_tests[] = { KUNIT_CASE_PARAM(xe_ccs_migrate_kunit, xe_pci_live_device_gen_param), KUNIT_CASE_PARAM(xe_bo_evict_kunit, xe_pci_live_device_gen_param), - KUNIT_CASE_PARAM_ATTR(xe_bo_shrink_kunit, xe_pci_live_device_gen_param, - {.speed = KUNIT_SPEED_SLOW}), {} }; @@ -618,3 +615,17 @@ struct kunit_suite xe_bo_test_suite = { .init = xe_kunit_helper_xe_device_live_test_init, }; EXPORT_SYMBOL_IF_KUNIT(xe_bo_test_suite); + +static struct kunit_case xe_bo_shrink_test[] = { + KUNIT_CASE_PARAM_ATTR(xe_bo_shrink_kunit, xe_pci_live_device_gen_param, + {.speed = KUNIT_SPEED_SLOW}), + {} +}; + +VISIBLE_IF_KUNIT +struct kunit_suite xe_bo_shrink_test_suite = { + .name = "xe_bo_shrink", + .test_cases = xe_bo_shrink_test, + .init = xe_kunit_helper_xe_device_live_test_init, +}; +EXPORT_SYMBOL_IF_KUNIT(xe_bo_shrink_test_suite); diff --git a/drivers/gpu/drm/xe/tests/xe_live_test_mod.c b/drivers/gpu/drm/xe/tests/xe_live_test_mod.c index 0d36ab864ec0..81277c77016d 100644 --- a/drivers/gpu/drm/xe/tests/xe_live_test_mod.c +++ b/drivers/gpu/drm/xe/tests/xe_live_test_mod.c @@ -6,11 +6,13 @@ #include extern struct kunit_suite xe_bo_test_suite; +extern struct kunit_suite xe_bo_shrink_test_suite; extern struct kunit_suite xe_dma_buf_test_suite; extern struct kunit_suite xe_migrate_test_suite; extern struct kunit_suite xe_mocs_test_suite; kunit_test_suite(xe_bo_test_suite); +kunit_test_suite(xe_bo_shrink_test_suite); kunit_test_suite(xe_dma_buf_test_suite); kunit_test_suite(xe_migrate_test_suite); kunit_test_suite(xe_mocs_test_suite); diff --git a/drivers/gpu/drm/xe/tests/xe_mocs.c b/drivers/gpu/drm/xe/tests/xe_mocs.c index 6f9b7a266b41..ef1e5256c56a 100644 --- a/drivers/gpu/drm/xe/tests/xe_mocs.c +++ b/drivers/gpu/drm/xe/tests/xe_mocs.c @@ -58,7 +58,7 @@ static void read_l3cc_table(struct xe_gt *gt, mocs_dbg(gt, "reg_val=0x%x\n", reg_val); } else { - /* Just re-use value read on previous iteration */ + /* Just reuse value read on previous iteration */ reg_val >>= 16; } @@ -162,8 +162,7 @@ static int mocs_reset_test_run_device(struct xe_device *xe) if (flags & HAS_LNCF_MOCS) read_l3cc_table(gt, &mocs.table); - xe_gt_reset_async(gt); - flush_work(>->reset.worker); + xe_gt_reset(gt); kunit_info(test, "mocs_reset_test after reset\n"); if (flags & HAS_GLOBAL_MOCS) diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c index ef777dbdf4ec..9570672fce33 100644 --- a/drivers/gpu/drm/xe/xe_bb.c +++ b/drivers/gpu/drm/xe/xe_bb.c @@ -41,7 +41,7 @@ struct xe_bb *xe_bb_new(struct xe_gt *gt, u32 dwords, bool usm) /* * We need to allocate space for the requested number of dwords, * one additional MI_BATCH_BUFFER_END dword, and additional buffer - * space to accomodate the platform-specific hardware prefetch + * space to accommodate the platform-specific hardware prefetch * requirements. */ bb->bo = xe_sa_bo_new(!usm ? tile->mem.kernel_bb_pool : gt->usm.bb_pool, diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 283cd0294570..3f5391d416d4 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -733,7 +733,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, new_mem->mem_type == XE_PL_SYSTEM) { long timeout = dma_resv_wait_timeout(ttm_bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, - true, + false, MAX_SCHEDULE_TIMEOUT); if (timeout < 0) { ret = timeout; @@ -786,7 +786,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, * / resume, some of the pinned memory is required for the * device to resume / use the GPU to move other evicted memory * (user memory) around. This likely could be optimized a bit - * futher where we find the minimum set of pinned memory + * further where we find the minimum set of pinned memory * required for resume but for simplity doing a memcpy for all * pinned memory. */ @@ -857,8 +857,16 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, out: if ((!ttm_bo->resource || ttm_bo->resource->mem_type == XE_PL_SYSTEM) && - ttm_bo->ttm) + ttm_bo->ttm) { + long timeout = dma_resv_wait_timeout(ttm_bo->base.resv, + DMA_RESV_USAGE_KERNEL, + false, + MAX_SCHEDULE_TIMEOUT); + if (timeout < 0) + ret = timeout; + xe_tt_unmap_sg(ttm_bo->ttm); + } return ret; } @@ -867,7 +875,7 @@ out: * xe_bo_evict_pinned() - Evict a pinned VRAM object to system memory * @bo: The buffer object to move. * - * On successful completion, the object memory will be moved to sytem memory. + * On successful completion, the object memory will be moved to system memory. * * This is needed to for special handling of pinned VRAM object during * suspend-resume. @@ -1362,7 +1370,7 @@ static const struct drm_gem_object_funcs xe_gem_object_funcs = { /** * xe_bo_alloc - Allocate storage for a struct xe_bo * - * This funcition is intended to allocate storage to be used for input + * This function is intended to allocate storage to be used for input * to __xe_bo_create_locked(), in the case a pointer to the bo to be * created is needed before the call to __xe_bo_create_locked(). * If __xe_bo_create_locked ends up never to be called, then the @@ -2404,7 +2412,7 @@ int xe_bo_migrate(struct xe_bo *bo, u32 mem_type) * @force_alloc: Set force_alloc in ttm_operation_ctx * * On successful completion, the object memory will be moved to evict - * placement. Ths function blocks until the object has been fully moved. + * placement. This function blocks until the object has been fully moved. * * Return: 0 on success. Negative error code on failure. */ diff --git a/drivers/gpu/drm/xe/xe_bo_doc.h b/drivers/gpu/drm/xe/xe_bo_doc.h index f57d440cc95a..25a884c64bf1 100644 --- a/drivers/gpu/drm/xe/xe_bo_doc.h +++ b/drivers/gpu/drm/xe/xe_bo_doc.h @@ -41,7 +41,7 @@ * created the BO can be mmap'd (via DRM_IOCTL_XE_GEM_MMAP_OFFSET) for user * access and it can be bound for GPU access (via DRM_IOCTL_XE_VM_BIND). All * user BOs are evictable and user BOs are never pinned by XE. The allocation of - * the backing store can be defered from creation time until first use which is + * the backing store can be deferred from creation time until first use which is * either mmap, bind, or pagefault. * * Private BOs diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c index 71636e80b71d..81dc7795c065 100644 --- a/drivers/gpu/drm/xe/xe_devcoredump.c +++ b/drivers/gpu/drm/xe/xe_devcoredump.c @@ -48,7 +48,7 @@ * * **Coredump release**: * After a coredump is generated, it stays in kernel memory until released by - * userpace by writing anything to it, or after an internal timer expires. The + * userspace by writing anything to it, or after an internal timer expires. The * exact timeout may vary and should not be relied upon. Example to release * a coredump: * @@ -119,7 +119,11 @@ static ssize_t __xe_devcoredump_read(char *buffer, size_t count, drm_puts(&p, "\n**** GuC CT ****\n"); xe_guc_ct_snapshot_print(ss->guc.ct, &p); - drm_puts(&p, "\n**** Contexts ****\n"); + /* + * Don't add a new section header here because the mesa debug decoder + * tool expects the context information to be in the 'GuC CT' section. + */ + /* drm_puts(&p, "\n**** Contexts ****\n"); */ xe_guc_exec_queue_snapshot_print(ss->ge, &p); drm_puts(&p, "\n**** Job ****\n"); @@ -416,6 +420,15 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char buff[ASCII85_BUFSZ], *line_buff; size_t line_pos = 0; + /* + * Splitting blobs across multiple lines is not compatible with the mesa + * debug decoder tool. Note that even dropping the explicit '\n' below + * doesn't help because the GuC log is so big some underlying implementation + * still splits the lines at 512K characters. So just bail completely for + * the moment. + */ + return; + #define DMESG_MAX_LINE_LEN 800 #define MIN_SPACE (ASCII85_BUFSZ + 2) /* 85 + "\n\0" */ diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 56d4ffb650da..4e1839b483a0 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -325,7 +325,9 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, xe->info.revid = pdev->revision; xe->info.force_execlist = xe_modparam.force_execlist; - spin_lock_init(&xe->irq.lock); + err = xe_irq_init(xe); + if (err) + goto err; init_waitqueue_head(&xe->ufence_wq); @@ -519,7 +521,7 @@ static int wait_for_lmem_ready(struct xe_device *xe) drm_dbg(&xe->drm, "Waiting for lmem initialization\n"); start = jiffies; - timeout = start + msecs_to_jiffies(60 * 1000); /* 60 sec! */ + timeout = start + secs_to_jiffies(60); /* 60 sec! */ do { if (signal_pending(current)) @@ -604,7 +606,7 @@ static int probe_has_flat_ccs(struct xe_device *xe) u32 reg; /* Always enabled/disabled, no runtime check to do */ - if (GRAPHICS_VER(xe) < 20 || !xe->info.has_flat_ccs) + if (GRAPHICS_VER(xe) < 20 || !xe->info.has_flat_ccs || IS_SRIOV_VF(xe)) return 0; gt = xe_root_mmio_gt(xe); @@ -997,7 +999,7 @@ static void xe_device_wedged_fini(struct drm_device *drm, void *arg) * xe_device_declare_wedged - Declare device wedged * @xe: xe device instance * - * This is a final state that can only be cleared with a mudule + * This is a final state that can only be cleared with a module * re-probe (unbind + bind). * In this state every IOCTL will be blocked so the GT cannot be used. * In general it will be called upon any critical error such as gt reset diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h index f1fbfe916867..fc3c2af3fb7f 100644 --- a/drivers/gpu/drm/xe/xe_device.h +++ b/drivers/gpu/drm/xe/xe_device.h @@ -157,8 +157,7 @@ static inline bool xe_device_has_sriov(struct xe_device *xe) static inline bool xe_device_has_msix(struct xe_device *xe) { - /* TODO: change this when MSI-X support is fully integrated */ - return false; + return xe->irq.msix.nvec > 0; } static inline bool xe_device_has_memirq(struct xe_device *xe) diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index ace22e35e769..8a7b15972413 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -348,6 +348,14 @@ struct xe_device { /** @irq.enabled: interrupts enabled on this device */ atomic_t enabled; + + /** @irq.msix: irq info for platforms that support MSI-X */ + struct { + /** @irq.msix.nvec: number of MSI-X interrupts */ + u16 nvec; + /** @irq.msix.indexes: used to allocate MSI-X indexes */ + struct xarray indexes; + } msix; } irq; /** @ttm: ttm device */ diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c index 298a587da7f1..63f30b6df70b 100644 --- a/drivers/gpu/drm/xe/xe_drm_client.c +++ b/drivers/gpu/drm/xe/xe_drm_client.c @@ -261,6 +261,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file) if (man) { drm_print_memory_stats(p, &stats[mem_type], + DRM_GEM_OBJECT_ACTIVE | DRM_GEM_OBJECT_RESIDENT | (mem_type != XE_PL_SYSTEM ? 0 : DRM_GEM_OBJECT_PURGEABLE), @@ -384,7 +385,7 @@ static void show_run_ticks(struct drm_printer *p, struct drm_file *file) * @p: The drm_printer ptr * @file: The drm_file ptr * - * This is callabck for drm fdinfo interface. Register this callback + * This is callback for drm fdinfo interface. Register this callback * in drm driver ops for show_fdinfo. * * Return: void diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 31cca938956f..df8ce550deb4 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -33,7 +33,7 @@ * * In XE we avoid all of this complication by not allowing a BO list to be * passed into an exec, using the dma-buf implicit sync uAPI, have binds as - * seperate operations, and using the DRM scheduler to flow control the ring. + * separate operations, and using the DRM scheduler to flow control the ring. * Let's deep dive on each of these. * * We can get away from a BO list by forcing the user to use in / out fences on diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index aab9e561153d..7e1abbbfba12 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -8,6 +8,7 @@ #include #include +#include #include #include @@ -16,6 +17,7 @@ #include "xe_hw_engine_class_sysfs.h" #include "xe_hw_engine_group.h" #include "xe_hw_fence.h" +#include "xe_irq.h" #include "xe_lrc.h" #include "xe_macros.h" #include "xe_migrate.h" @@ -68,6 +70,7 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe, q->gt = gt; q->class = hwe->class; q->width = width; + q->msix_vec = XE_IRQ_DEFAULT_MSIX; q->logical_mask = logical_mask; q->fence_irq = >->fence_irq[hwe->class]; q->ring_ops = gt->ring_ops[hwe->class]; @@ -117,7 +120,7 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q) } for (i = 0; i < q->width; ++i) { - q->lrc[i] = xe_lrc_create(q->hwe, q->vm, SZ_16K); + q->lrc[i] = xe_lrc_create(q->hwe, q->vm, SZ_16K, q->msix_vec); if (IS_ERR(q->lrc[i])) { err = PTR_ERR(q->lrc[i]); goto err_unlock; @@ -766,20 +769,21 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q) */ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) { - struct xe_file *xef; + struct xe_device *xe = gt_to_xe(q->gt); struct xe_lrc *lrc; u32 old_ts, new_ts; + int idx; /* - * Jobs that are run during driver load may use an exec_queue, but are - * not associated with a user xe file, so avoid accumulating busyness - * for kernel specific work. + * Jobs that are executed by kernel doesn't have a corresponding xe_file + * and thus are not accounted. */ - if (!q->vm || !q->vm->xef) + if (!q->xef) return; - xef = q->vm->xef; - + /* Synchronize with unbind while holding the xe file open */ + if (!drm_dev_enter(&xe->drm, &idx)) + return; /* * Only sample the first LRC. For parallel submission, all of them are * scheduled together and we compensate that below by multiplying by @@ -790,7 +794,9 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) */ lrc = q->lrc[0]; new_ts = xe_lrc_update_timestamp(lrc, &old_ts); - xef->run_ticks[q->class] += (new_ts - old_ts) * q->width; + q->xef->run_ticks[q->class] += (new_ts - old_ts) * q->width; + + drm_dev_exit(idx); } /** diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 1158b6062a6c..5af5419cec7a 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -41,7 +41,7 @@ struct xe_exec_queue { /** @xef: Back pointer to xe file if this is user created exec queue */ struct xe_file *xef; - /** @gt: graphics tile this exec queue can submit to */ + /** @gt: GT structure this exec queue can submit to */ struct xe_gt *gt; /** * @hwe: A hardware of the same class. May (physical engine) or may not @@ -63,6 +63,8 @@ struct xe_exec_queue { char name[MAX_FENCE_NAME_LEN]; /** @width: width (number BB submitted per exec) of this exec queue */ u16 width; + /** @msix_vec: MSI-X vector (for platforms that support it) */ + u16 msix_vec; /** @fence_irq: fence IRQ used to signal job completion */ struct xe_hw_fence_irq *fence_irq; diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c index a8c416a48812..5ef96deaa881 100644 --- a/drivers/gpu/drm/xe/xe_execlist.c +++ b/drivers/gpu/drm/xe/xe_execlist.c @@ -17,6 +17,7 @@ #include "xe_exec_queue.h" #include "xe_gt.h" #include "xe_hw_fence.h" +#include "xe_irq.h" #include "xe_lrc.h" #include "xe_macros.h" #include "xe_mmio.h" @@ -47,6 +48,7 @@ static void __start_lrc(struct xe_hw_engine *hwe, struct xe_lrc *lrc, struct xe_mmio *mmio = >->mmio; struct xe_device *xe = gt_to_xe(gt); u64 lrc_desc; + u32 ring_mode = _MASKED_BIT_ENABLE(GFX_DISABLE_LEGACY_MODE); lrc_desc = xe_lrc_descriptor(lrc); @@ -80,8 +82,10 @@ static void __start_lrc(struct xe_hw_engine *hwe, struct xe_lrc *lrc, xe_mmio_write32(mmio, RING_HWS_PGA(hwe->mmio_base), xe_bo_ggtt_addr(hwe->hwsp)); xe_mmio_read32(mmio, RING_HWS_PGA(hwe->mmio_base)); - xe_mmio_write32(mmio, RING_MODE(hwe->mmio_base), - _MASKED_BIT_ENABLE(GFX_DISABLE_LEGACY_MODE)); + + if (xe_device_has_msix(gt_to_xe(hwe->gt))) + ring_mode |= _MASKED_BIT_ENABLE(GFX_MSIX_INTERRUPT_ENABLE); + xe_mmio_write32(mmio, RING_MODE(hwe->mmio_base), ring_mode); xe_mmio_write32(mmio, RING_EXECLIST_SQ_CONTENTS_LO(hwe->mmio_base), lower_32_bits(lrc_desc)); @@ -265,7 +269,7 @@ struct xe_execlist_port *xe_execlist_port_create(struct xe_device *xe, port->hwe = hwe; - port->lrc = xe_lrc_create(hwe, NULL, SZ_16K); + port->lrc = xe_lrc_create(hwe, NULL, SZ_16K, XE_IRQ_DEFAULT_MSIX); if (IS_ERR(port->lrc)) { err = PTR_ERR(port->lrc); goto err; diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 05154f9de1a6..5fcb2b4c2c13 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -362,7 +362,7 @@ int xe_ggtt_init(struct xe_ggtt *ggtt) /* * So we don't need to worry about 64K GGTT layout when dealing with - * scratch entires, rather keep the scratch page in system memory on + * scratch entries, rather keep the scratch page in system memory on * platforms where 64K pages are needed for VRAM. */ flags = XE_BO_FLAG_PINNED; diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 41ab7fbebc19..26e64530ada2 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -387,6 +387,10 @@ int xe_gt_init_early(struct xe_gt *gt) xe_force_wake_init_gt(gt, gt_to_fw(gt)); spin_lock_init(>->global_invl_lock); + err = xe_gt_tlb_invalidation_init_early(gt); + if (err) + return err; + return 0; } @@ -588,10 +592,6 @@ int xe_gt_init(struct xe_gt *gt) xe_hw_fence_irq_init(>->fence_irq[i]); } - err = xe_gt_tlb_invalidation_init(gt); - if (err) - return err; - err = xe_gt_pagefault_init(gt); if (err) return err; diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h index 82b9b7f82fca..e504cc33ade4 100644 --- a/drivers/gpu/drm/xe/xe_gt.h +++ b/drivers/gpu/drm/xe/xe_gt.h @@ -37,7 +37,7 @@ int xe_gt_record_default_lrcs(struct xe_gt *gt); /** * xe_gt_record_user_engines - save data related to engines available to - * usersapce + * userspace * @gt: GT structure * * Walk the available HW engines from gt->info.engine_mask and calculate data @@ -56,6 +56,31 @@ void xe_gt_sanitize(struct xe_gt *gt); int xe_gt_sanitize_freq(struct xe_gt *gt); void xe_gt_remove(struct xe_gt *gt); +/** + * xe_gt_wait_for_reset - wait for gt's async reset to finalize. + * @gt: GT structure + * Return: + * %true if it waited for the work to finish execution, + * %false if there was no scheduled reset or it was done. + */ +static inline bool xe_gt_wait_for_reset(struct xe_gt *gt) +{ + return flush_work(>->reset.worker); +} + +/** + * xe_gt_reset - perform synchronous reset + * @gt: GT structure + * Return: + * %true if it waited for the reset to finish, + * %false if there was no scheduled reset. + */ +static inline bool xe_gt_reset(struct xe_gt *gt) +{ + xe_gt_reset_async(gt); + return xe_gt_wait_for_reset(gt); +} + /** * xe_gt_any_hw_engine_by_reset_domain - scan the list of engines and return the * first that matches the same reset domain as @class diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c index b6adfb9f2030..50fffc9ebf62 100644 --- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c +++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c @@ -150,7 +150,7 @@ ccs_mode_store(struct device *kdev, struct device_attribute *attr, xe_gt_info(gt, "Setting compute mode to %d\n", num_engines); gt->ccs_mode = num_engines; xe_gt_record_user_engines(gt); - xe_gt_reset_async(gt); + xe_gt_reset(gt); } mutex_unlock(&xe->drm.filelist_mutex); diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c index 3e8c351a0eab..e7792858b1e4 100644 --- a/drivers/gpu/drm/xe/xe_gt_debugfs.c +++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c @@ -132,11 +132,9 @@ static int force_reset(struct xe_gt *gt, struct drm_printer *p) static int force_reset_sync(struct xe_gt *gt, struct drm_printer *p) { xe_pm_runtime_get(gt_to_xe(gt)); - xe_gt_reset_async(gt); + xe_gt_reset(gt); xe_pm_runtime_put(gt_to_xe(gt)); - flush_work(>->reset.worker); - return 0; } diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c index 6bd39b2c5003..604bdc7c8173 100644 --- a/drivers/gpu/drm/xe/xe_gt_freq.c +++ b/drivers/gpu/drm/xe/xe_gt_freq.c @@ -115,6 +115,20 @@ static ssize_t rpe_freq_show(struct device *dev, } static DEVICE_ATTR_RO(rpe_freq); +static ssize_t rpa_freq_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct xe_guc_pc *pc = dev_to_pc(dev); + u32 freq; + + xe_pm_runtime_get(dev_to_xe(dev)); + freq = xe_guc_pc_get_rpa_freq(pc); + xe_pm_runtime_put(dev_to_xe(dev)); + + return sysfs_emit(buf, "%d\n", freq); +} +static DEVICE_ATTR_RO(rpa_freq); + static ssize_t rpn_freq_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -202,6 +216,7 @@ static const struct attribute *freq_attrs[] = { &dev_attr_act_freq.attr, &dev_attr_cur_freq.attr, &dev_attr_rp0_freq.attr, + &dev_attr_rpa_freq.attr, &dev_attr_rpe_freq.attr, &dev_attr_rpn_freq.attr, &dev_attr_min_freq.attr, diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c index fd80afeef56a..ffd3ba7f6656 100644 --- a/drivers/gpu/drm/xe/xe_gt_idle.c +++ b/drivers/gpu/drm/xe/xe_gt_idle.c @@ -122,10 +122,12 @@ void xe_gt_idle_enable_pg(struct xe_gt *gt) if (!xe_gt_is_media_type(gt)) gtidle->powergate_enable |= RENDER_POWERGATE_ENABLE; - for (i = XE_HW_ENGINE_VCS0, j = 0; i <= XE_HW_ENGINE_VCS7; ++i, ++j) { - if ((gt->info.engine_mask & BIT(i))) - gtidle->powergate_enable |= (VDN_HCP_POWERGATE_ENABLE(j) | - VDN_MFXVDENC_POWERGATE_ENABLE(j)); + if (xe->info.platform != XE_DG1) { + for (i = XE_HW_ENGINE_VCS0, j = 0; i <= XE_HW_ENGINE_VCS7; ++i, ++j) { + if ((gt->info.engine_mask & BIT(i))) + gtidle->powergate_enable |= (VDN_HCP_POWERGATE_ENABLE(j) | + VDN_MFXVDENC_POWERGATE_ENABLE(j)); + } } fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c index 5013d674e17d..a1676b787fdc 100644 --- a/drivers/gpu/drm/xe/xe_gt_mcr.c +++ b/drivers/gpu/drm/xe/xe_gt_mcr.c @@ -371,7 +371,7 @@ void xe_gt_mcr_get_dss_steering(struct xe_gt *gt, unsigned int dss, u16 *group, * @group: steering group ID * @instance: steering instance ID * - * Return: the coverted DSS id. + * Return: the converted DSS id. */ u32 xe_gt_mcr_steering_info_to_dss_id(struct xe_gt *gt, u16 group, u16 instance) { @@ -550,9 +550,9 @@ void xe_gt_mcr_set_implicit_defaults(struct xe_gt *gt) * Returns true if the caller should steer to the @group/@instance values * returned. Returns false if the caller need not perform any steering */ -static bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt, - struct xe_reg_mcr reg_mcr, - u8 *group, u8 *instance) +bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt, + struct xe_reg_mcr reg_mcr, + u8 *group, u8 *instance) { const struct xe_reg reg = to_xe_reg(reg_mcr); const struct xe_mmio_range *implicit_ranges; diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.h b/drivers/gpu/drm/xe/xe_gt_mcr.h index c0cd36021c24..bc06520befab 100644 --- a/drivers/gpu/drm/xe/xe_gt_mcr.h +++ b/drivers/gpu/drm/xe/xe_gt_mcr.h @@ -26,6 +26,10 @@ void xe_gt_mcr_unicast_write(struct xe_gt *gt, struct xe_reg_mcr mcr_reg, void xe_gt_mcr_multicast_write(struct xe_gt *gt, struct xe_reg_mcr mcr_reg, u32 value); +bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt, + struct xe_reg_mcr reg_mcr, + u8 *group, u8 *instance); + void xe_gt_mcr_steering_dump(struct xe_gt *gt, struct drm_printer *p); void xe_gt_mcr_get_dss_steering(struct xe_gt *gt, unsigned int dss, u16 *group, u16 *instance); u32 xe_gt_mcr_steering_info_to_dss_id(struct xe_gt *gt, u16 group, u16 instance); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 65082f12f1a8..878e96281c03 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -2120,7 +2120,7 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid) valid_any = valid_any || (valid_ggtt && is_primary); if (IS_DGFX(xe)) { - bool valid_lmem = pf_get_vf_config_ggtt(primary_gt, vfid); + bool valid_lmem = pf_get_vf_config_lmem(primary_gt, vfid); valid_any = valid_any || (valid_lmem && is_primary); valid_all = valid_all && valid_lmem; @@ -2161,7 +2161,7 @@ bool xe_gt_sriov_pf_config_is_empty(struct xe_gt *gt, unsigned int vfid) * * This function can only be called on PF. * - * Return: mininum size of the buffer or the number of bytes saved, + * Return: minimum size of the buffer or the number of bytes saved, * or a negative error code on failure. */ ssize_t xe_gt_sriov_pf_config_save(struct xe_gt *gt, unsigned int vfid, void *buf, size_t size) diff --git a/drivers/gpu/drm/xe/xe_gt_stats.c b/drivers/gpu/drm/xe/xe_gt_stats.c index c7364a5aef8f..7a6c1d808e41 100644 --- a/drivers/gpu/drm/xe/xe_gt_stats.c +++ b/drivers/gpu/drm/xe/xe_gt_stats.c @@ -12,7 +12,7 @@ /** * xe_gt_stats_incr - Increments the specified stats counter - * @gt: graphics tile + * @gt: GT structure * @id: xe_gt_stats_id type id that needs to be incremented * @incr: value to be incremented with * @@ -32,7 +32,7 @@ static const char *const stat_description[__XE_GT_STATS_NUM_IDS] = { /** * xe_gt_stats_print_info - Print the GT stats - * @gt: graphics tile + * @gt: GT structure * @p: drm_printer where it will be printed out. * * This prints out all the available GT stats. diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 665927b80e9e..0a93831c0a02 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -106,15 +106,15 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work) } /** - * xe_gt_tlb_invalidation_init - Initialize GT TLB invalidation state - * @gt: graphics tile + * xe_gt_tlb_invalidation_init_early - Initialize GT TLB invalidation state + * @gt: GT structure * * Initialize GT TLB invalidation state, purely software initialization, should * be called once during driver load. * * Return: 0 on success, negative error code on error. */ -int xe_gt_tlb_invalidation_init(struct xe_gt *gt) +int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt) { gt->tlb_invalidation.seqno = 1; INIT_LIST_HEAD(>->tlb_invalidation.pending_fences); @@ -128,7 +128,7 @@ int xe_gt_tlb_invalidation_init(struct xe_gt *gt) /** * xe_gt_tlb_invalidation_reset - Initialize GT TLB invalidation reset - * @gt: graphics tile + * @gt: GT structure * * Signal any pending invalidation fences, should be called during a GT reset */ @@ -244,7 +244,7 @@ static int send_tlb_invalidation(struct xe_guc *guc, /** * xe_gt_tlb_invalidation_guc - Issue a TLB invalidation on this GT for the GuC - * @gt: graphics tile + * @gt: GT structure * @fence: invalidation fence which will be signal on TLB invalidation * completion * @@ -277,7 +277,7 @@ static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt, /** * xe_gt_tlb_invalidation_ggtt - Issue a TLB invalidation on this GT for the GGTT - * @gt: graphics tile + * @gt: GT structure * * Issue a TLB invalidation for the GGTT. Completion of TLB invalidation is * synchronous. @@ -326,7 +326,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt) * xe_gt_tlb_invalidation_range - Issue a TLB invalidation on this GT for an * address range * - * @gt: graphics tile + * @gt: GT structure * @fence: invalidation fence which will be signal on TLB invalidation * completion * @start: start address @@ -412,7 +412,7 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt, /** * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT for a VMA - * @gt: graphics tile + * @gt: GT structure * @fence: invalidation fence which will be signal on TLB invalidation * completion, can be NULL * @vma: VMA to invalidate diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index 00b1c6c01e8d..672acfcdf0d7 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -14,7 +14,8 @@ struct xe_gt; struct xe_guc; struct xe_vma; -int xe_gt_tlb_invalidation_init(struct xe_gt *gt); +int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt); + void xe_gt_tlb_invalidation_reset(struct xe_gt *gt); int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt); int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index 4e2868efb620..408365dfe4ee 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -147,6 +147,34 @@ static u32 guc_ctl_ads_flags(struct xe_guc *guc) return flags; } +static bool needs_wa_dual_queue(struct xe_gt *gt) +{ + /* + * The DUAL_QUEUE_WA tells the GuC to not allow concurrent submissions + * on RCS and CCSes with different address spaces, which on DG2 is + * required as a WA for an HW bug. + */ + if (XE_WA(gt, 22011391025)) + return true; + + /* + * On newer platforms, the HW has been updated to not allow parallel + * execution of different address spaces, so the RCS/CCS will stall the + * context switch if one of the other RCS/CCSes is busy with a different + * address space. While functionally correct, having a submission + * stalled on the HW limits the GuC ability to shuffle things around and + * can cause complications if the non-stalled submission runs for a long + * time, because the GuC doesn't know that the stalled submission isn't + * actually running and might declare it as hung. Therefore, we enable + * the DUAL_QUEUE_WA on all newer platforms on GTs that have CCS engines + * to move management back to the GuC. + */ + if (CCS_MASK(gt) && GRAPHICS_VERx100(gt_to_xe(gt)) >= 1270) + return true; + + return false; +} + static u32 guc_ctl_wa_flags(struct xe_guc *guc) { struct xe_device *xe = guc_to_xe(guc); @@ -159,7 +187,7 @@ static u32 guc_ctl_wa_flags(struct xe_guc *guc) if (XE_WA(gt, 14014475959)) flags |= GUC_WA_HOLD_CCS_SWITCHOUT; - if (XE_WA(gt, 22011391025)) + if (needs_wa_dual_queue(gt)) flags |= GUC_WA_DUAL_QUEUE; /* diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c index 943146e5b460..fab259adc380 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.c +++ b/drivers/gpu/drm/xe/xe_guc_ads.c @@ -29,6 +29,7 @@ #include "xe_platform_types.h" #include "xe_uc_fw.h" #include "xe_wa.h" +#include "xe_gt_mcr.h" /* Slack of a few additional entries per engine */ #define ADS_REGSET_EXTRA_MAX 8 @@ -696,6 +697,20 @@ static void guc_mmio_regset_write_one(struct xe_guc_ads *ads, .flags = reg.masked ? GUC_REGSET_MASKED : 0, }; + if (reg.mcr) { + struct xe_reg_mcr mcr_reg = XE_REG_MCR(reg.addr); + u8 group, instance; + + bool steer = xe_gt_mcr_get_nonterminated_steering(ads_to_gt(ads), mcr_reg, + &group, &instance); + + if (steer) { + entry.flags |= FIELD_PREP(GUC_REGSET_STEERING_GROUP, group); + entry.flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, instance); + entry.flags |= GUC_REGSET_STEERING_NEEDED; + } + } + xe_map_memcpy_to(ads_to_xe(ads), regset_map, n_entry * sizeof(entry), &entry, sizeof(entry)); } diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c index 137571fae4ed..f6d523e4c5fe 100644 --- a/drivers/gpu/drm/xe/xe_guc_capture.c +++ b/drivers/gpu/drm/xe/xe_guc_capture.c @@ -1955,7 +1955,7 @@ xe_engine_snapshot_capture_for_queue(struct xe_exec_queue *q) } /* - * xe_guc_capture_put_matched_nodes - Cleanup macthed nodes + * xe_guc_capture_put_matched_nodes - Cleanup matched nodes * @guc: The GuC object * * Free matched node and all nodes with the equal guc_id from diff --git a/drivers/gpu/drm/xe/xe_guc_capture_types.h b/drivers/gpu/drm/xe/xe_guc_capture_types.h index 2057125b1bfa..ca2d390ccbee 100644 --- a/drivers/gpu/drm/xe/xe_guc_capture_types.h +++ b/drivers/gpu/drm/xe/xe_guc_capture_types.h @@ -22,7 +22,7 @@ enum capture_register_data_type { * struct __guc_mmio_reg_descr - GuC mmio register descriptor * * xe_guc_capture module uses these structures to define a register - * (offsets, names, flags,...) that are used at the ADS regisration + * (offsets, names, flags,...) that are used at the ADS registration * time as well as during runtime processing and reporting of error- * capture states generated by GuC just prior to engine reset events. */ @@ -48,7 +48,7 @@ struct __guc_mmio_reg_descr { * * xe_guc_capture module uses these structures to maintain static * tables (per unique platform) that consists of lists of registers - * (offsets, names, flags,...) that are used at the ADS regisration + * (offsets, names, flags,...) that are used at the ADS registration * time as well as during runtime processing and reporting of error- * capture states generated by GuC just prior to engine reset events. */ diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 7d33f3a11e61..8b65c5e959cc 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -710,7 +710,7 @@ static int h2g_write(struct xe_guc_ct *ct, const u32 *action, u32 len, --len; ++action; - /* Write H2G ensuring visable before descriptor update */ + /* Write H2G ensuring visible before descriptor update */ xe_map_memcpy_to(xe, &map, 0, cmd, H2G_CT_HEADERS * sizeof(u32)); xe_map_memcpy_to(xe, &map, H2G_CT_HEADERS * sizeof(u32), action, len * sizeof(u32)); xe_device_wmb(xe); @@ -1383,7 +1383,7 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path) * this function and nowhere else. Hence, they cannot be different * unless two g2h_read calls are running concurrently. Which is not * possible because it is guarded by ct->fast_lock. And yet, some - * discrete platforms are reguarly hitting this error :(. + * discrete platforms are regularly hitting this error :(. * * desc_head rolling backwards shouldn't cause any noticeable * problems - just a delay in GuC being allowed to proceed past that diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c index e8b9faeaef64..df7f130fb663 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.c +++ b/drivers/gpu/drm/xe/xe_guc_pc.c @@ -38,6 +38,7 @@ #define FREQ_INFO_REC XE_REG(MCHBAR_MIRROR_BASE_SNB + 0x5ef0) #define RPE_MASK REG_GENMASK(15, 8) +#define RPA_MASK REG_GENMASK(31, 16) #define GT_PERF_STATUS XE_REG(0x1381b4) #define CAGF_MASK REG_GENMASK(19, 11) @@ -328,6 +329,19 @@ static int pc_set_max_freq(struct xe_guc_pc *pc, u32 freq) freq); } +static void mtl_update_rpa_value(struct xe_guc_pc *pc) +{ + struct xe_gt *gt = pc_to_gt(pc); + u32 reg; + + if (xe_gt_is_media_type(gt)) + reg = xe_mmio_read32(>->mmio, MTL_MPA_FREQUENCY); + else + reg = xe_mmio_read32(>->mmio, MTL_GT_RPA_FREQUENCY); + + pc->rpa_freq = decode_freq(REG_FIELD_GET(MTL_RPA_MASK, reg)); +} + static void mtl_update_rpe_value(struct xe_guc_pc *pc) { struct xe_gt *gt = pc_to_gt(pc); @@ -341,6 +355,25 @@ static void mtl_update_rpe_value(struct xe_guc_pc *pc) pc->rpe_freq = decode_freq(REG_FIELD_GET(MTL_RPE_MASK, reg)); } +static void tgl_update_rpa_value(struct xe_guc_pc *pc) +{ + struct xe_gt *gt = pc_to_gt(pc); + struct xe_device *xe = gt_to_xe(gt); + u32 reg; + + /* + * For PVC we still need to use fused RP1 as the approximation for RPe + * For other platforms than PVC we get the resolved RPe directly from + * PCODE at a different register + */ + if (xe->info.platform == XE_PVC) + reg = xe_mmio_read32(>->mmio, PVC_RP_STATE_CAP); + else + reg = xe_mmio_read32(>->mmio, FREQ_INFO_REC); + + pc->rpa_freq = REG_FIELD_GET(RPA_MASK, reg) * GT_FREQUENCY_MULTIPLIER; +} + static void tgl_update_rpe_value(struct xe_guc_pc *pc) { struct xe_gt *gt = pc_to_gt(pc); @@ -365,10 +398,13 @@ static void pc_update_rp_values(struct xe_guc_pc *pc) struct xe_gt *gt = pc_to_gt(pc); struct xe_device *xe = gt_to_xe(gt); - if (GRAPHICS_VERx100(xe) >= 1270) + if (GRAPHICS_VERx100(xe) >= 1270) { + mtl_update_rpa_value(pc); mtl_update_rpe_value(pc); - else + } else { + tgl_update_rpa_value(pc); tgl_update_rpe_value(pc); + } /* * RPe is decided at runtime by PCODE. In the rare case where that's @@ -421,8 +457,8 @@ int xe_guc_pc_get_cur_freq(struct xe_guc_pc *pc, u32 *freq) * GuC SLPC plays with cur freq request when GuCRC is enabled * Block RC6 for a more reliable read. */ - fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); - if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) { + fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); + if (!xe_force_wake_ref_has_domain(fw_ref, XE_FW_GT)) { xe_force_wake_put(gt_to_fw(gt), fw_ref); return -ETIMEDOUT; } @@ -447,6 +483,19 @@ u32 xe_guc_pc_get_rp0_freq(struct xe_guc_pc *pc) return pc->rp0_freq; } +/** + * xe_guc_pc_get_rpa_freq - Get the RPa freq + * @pc: The GuC PC + * + * Returns: RPa freq. + */ +u32 xe_guc_pc_get_rpa_freq(struct xe_guc_pc *pc) +{ + pc_update_rp_values(pc); + + return pc->rpa_freq; +} + /** * xe_guc_pc_get_rpe_freq - Get the RPe freq * @pc: The GuC PC @@ -481,10 +530,10 @@ u32 xe_guc_pc_get_rpn_freq(struct xe_guc_pc *pc) */ int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq) { - struct xe_gt *gt = pc_to_gt(pc); - unsigned int fw_ref; int ret; + xe_device_assert_mem_access(pc_to_xe(pc)); + mutex_lock(&pc->freq_lock); if (!pc->freq_ready) { /* Might be in the middle of a gt reset */ @@ -492,24 +541,12 @@ int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq) goto out; } - /* - * GuC SLPC plays with min freq request when GuCRC is enabled - * Block RC6 for a more reliable read. - */ - fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); - if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) { - ret = -ETIMEDOUT; - goto fw; - } - ret = pc_action_query_task_state(pc); if (ret) - goto fw; + goto out; *freq = pc_get_min_freq(pc); -fw: - xe_force_wake_put(gt_to_fw(gt), fw_ref); out: mutex_unlock(&pc->freq_lock); return ret; @@ -969,8 +1006,8 @@ int xe_guc_pc_start(struct xe_guc_pc *pc) xe_gt_assert(gt, xe_device_uc_enabled(xe)); - fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); - if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) { + fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); + if (!xe_force_wake_ref_has_domain(fw_ref, XE_FW_GT)) { xe_force_wake_put(gt_to_fw(gt), fw_ref); return -ETIMEDOUT; } diff --git a/drivers/gpu/drm/xe/xe_guc_pc.h b/drivers/gpu/drm/xe/xe_guc_pc.h index efda432fadfc..619f59cd633c 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.h +++ b/drivers/gpu/drm/xe/xe_guc_pc.h @@ -21,6 +21,7 @@ int xe_guc_pc_unset_gucrc_mode(struct xe_guc_pc *pc); u32 xe_guc_pc_get_act_freq(struct xe_guc_pc *pc); int xe_guc_pc_get_cur_freq(struct xe_guc_pc *pc, u32 *freq); u32 xe_guc_pc_get_rp0_freq(struct xe_guc_pc *pc); +u32 xe_guc_pc_get_rpa_freq(struct xe_guc_pc *pc); u32 xe_guc_pc_get_rpe_freq(struct xe_guc_pc *pc); u32 xe_guc_pc_get_rpn_freq(struct xe_guc_pc *pc); int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq); diff --git a/drivers/gpu/drm/xe/xe_guc_pc_types.h b/drivers/gpu/drm/xe/xe_guc_pc_types.h index 13810be015db..2978ac9a249b 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc_types.h +++ b/drivers/gpu/drm/xe/xe_guc_pc_types.h @@ -17,6 +17,8 @@ struct xe_guc_pc { struct xe_bo *bo; /** @rp0_freq: HW RP0 frequency - The Maximum one */ u32 rp0_freq; + /** @rpa_freq: HW RPa frequency - The Achievable one */ + u32 rpa_freq; /** @rpe_freq: HW RPe frequency - The Efficient one */ u32 rpe_freq; /** @rpn_freq: HW RPN frequency - The Minimum one */ diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 9c36329fe857..913c74d6e2ae 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -1226,7 +1226,7 @@ sched_enable: enable_scheduling(q); rearm: /* - * XXX: Ideally want to adjust timeout based on current exection time + * XXX: Ideally want to adjust timeout based on current execution time * but there is not currently an easy way to do in DRM scheduler. With * some thought, do this in a follow up. */ diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c index 2c32dc46f7d4..089834467880 100644 --- a/drivers/gpu/drm/xe/xe_hmm.c +++ b/drivers/gpu/drm/xe/xe_hmm.c @@ -159,7 +159,7 @@ void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma) * This function allocates the storage of the userptr sg table. * It is caller's responsibility to free it calling sg_free_table. * - * returns: 0 for succuss; negative error no on failure + * returns: 0 for success; negative error no on failure */ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, bool is_mm_mmap_locked) diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c index b19366744148..fc447751fe78 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine.c +++ b/drivers/gpu/drm/xe/xe_hw_engine.c @@ -324,6 +324,7 @@ void xe_hw_engine_enable_ring(struct xe_hw_engine *hwe) { u32 ccs_mask = xe_hw_engine_mask_per_class(hwe->gt, XE_ENGINE_CLASS_COMPUTE); + u32 ring_mode = _MASKED_BIT_ENABLE(GFX_DISABLE_LEGACY_MODE); if (hwe->class == XE_ENGINE_CLASS_COMPUTE && ccs_mask) xe_mmio_write32(&hwe->gt->mmio, RCU_MODE, @@ -332,8 +333,10 @@ void xe_hw_engine_enable_ring(struct xe_hw_engine *hwe) xe_hw_engine_mmio_write32(hwe, RING_HWSTAM(0), ~0x0); xe_hw_engine_mmio_write32(hwe, RING_HWS_PGA(0), xe_bo_ggtt_addr(hwe->hwsp)); - xe_hw_engine_mmio_write32(hwe, RING_MODE(0), - _MASKED_BIT_ENABLE(GFX_DISABLE_LEGACY_MODE)); + + if (xe_device_has_msix(gt_to_xe(hwe->gt))) + ring_mode |= _MASKED_BIT_ENABLE(GFX_MSIX_INTERRUPT_ENABLE); + xe_hw_engine_mmio_write32(hwe, RING_MODE(0), ring_mode); xe_hw_engine_mmio_write32(hwe, RING_MI_MODE(0), _MASKED_BIT_DISABLE(STOP_RING)); xe_hw_engine_mmio_read32(hwe, RING_MI_MODE(0)); @@ -419,7 +422,7 @@ hw_engine_setup_default_state(struct xe_hw_engine *hwe) * Bspec: 72161 */ const u8 mocs_write_idx = gt->mocs.uc_index; - const u8 mocs_read_idx = hwe->class == XE_ENGINE_CLASS_COMPUTE && + const u8 mocs_read_idx = hwe->class == XE_ENGINE_CLASS_COMPUTE && IS_DGFX(xe) && (GRAPHICS_VER(xe) >= 20 || xe->info.platform == XE_PVC) ? gt->mocs.wb_index : gt->mocs.uc_index; u32 ring_cmd_cctl_val = REG_FIELD_PREP(CMD_CCTL_WRITE_OVERRIDE_MASK, mocs_write_idx) | @@ -772,7 +775,7 @@ static void check_gsc_availability(struct xe_gt *gt) xe_mmio_write32(>->mmio, GUNIT_GSC_INTR_ENABLE, 0); xe_mmio_write32(>->mmio, GUNIT_GSC_INTR_MASK, ~0); - drm_info(&xe->drm, "gsccs disabled due to lack of FW\n"); + drm_dbg(&xe->drm, "GSC FW not used, disabling gsccs\n"); } } diff --git a/drivers/gpu/drm/xe/xe_hw_engine_types.h b/drivers/gpu/drm/xe/xe_hw_engine_types.h index e14bee95e364..e4191a7a2c31 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine_types.h +++ b/drivers/gpu/drm/xe/xe_hw_engine_types.h @@ -106,7 +106,7 @@ struct xe_hw_engine_class_intf { * Contains all the hardware engine state for physical instances. */ struct xe_hw_engine { - /** @gt: graphics tile this hw engine belongs to */ + /** @gt: GT structure this hw engine belongs to */ struct xe_gt *gt; /** @name: name of this hw engine */ const char *name; diff --git a/drivers/gpu/drm/xe/xe_hw_fence_types.h b/drivers/gpu/drm/xe/xe_hw_fence_types.h index 364a61f4bfda..58a8d09afe5c 100644 --- a/drivers/gpu/drm/xe/xe_hw_fence_types.h +++ b/drivers/gpu/drm/xe/xe_hw_fence_types.h @@ -41,7 +41,7 @@ struct xe_hw_fence_irq { * to a xe_hw_fence_irq, maintains serial seqno. */ struct xe_hw_fence_ctx { - /** @gt: graphics tile of hardware fence context */ + /** @gt: GT structure of hardware fence context */ struct xe_gt *gt; /** @irq: fence irq handler */ struct xe_hw_fence_irq *irq; diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c index 1c509e66694d..32f5a67a917b 100644 --- a/drivers/gpu/drm/xe/xe_irq.c +++ b/drivers/gpu/drm/xe/xe_irq.c @@ -10,6 +10,7 @@ #include #include "display/xe_display.h" +#include "regs/xe_guc_regs.h" #include "regs/xe_irq_regs.h" #include "xe_device.h" #include "xe_drv.h" @@ -29,6 +30,11 @@ #define IIR(offset) XE_REG(offset + 0x8) #define IER(offset) XE_REG(offset + 0xc) +static int xe_irq_msix_init(struct xe_device *xe); +static void xe_irq_msix_free(struct xe_device *xe); +static int xe_irq_msix_request_irqs(struct xe_device *xe); +static void xe_irq_msix_synchronize_irq(struct xe_device *xe); + static void assert_iir_is_zero(struct xe_mmio *mmio, struct xe_reg reg) { u32 val = xe_mmio_read32(mmio, reg); @@ -572,6 +578,11 @@ static void xe_irq_reset(struct xe_device *xe) if (IS_SRIOV_VF(xe)) return vf_irq_reset(xe); + if (xe_device_uses_memirq(xe)) { + for_each_tile(tile, xe, id) + xe_memirq_reset(&tile->memirq); + } + for_each_tile(tile, xe, id) { if (GRAPHICS_VERx100(xe) >= 1210) dg1_irq_reset(tile); @@ -614,6 +625,14 @@ static void xe_irq_postinstall(struct xe_device *xe) if (IS_SRIOV_VF(xe)) return vf_irq_postinstall(xe); + if (xe_device_uses_memirq(xe)) { + struct xe_tile *tile; + unsigned int id; + + for_each_tile(tile, xe, id) + xe_memirq_postinstall(&tile->memirq); + } + xe_display_irq_postinstall(xe, xe_root_mmio_gt(xe)); /* @@ -656,27 +675,11 @@ static irq_handler_t xe_irq_handler(struct xe_device *xe) return xelp_irq_handler; } -static void irq_uninstall(void *arg) -{ - struct xe_device *xe = arg; - struct pci_dev *pdev = to_pci_dev(xe->drm.dev); - int irq; - - if (!atomic_xchg(&xe->irq.enabled, 0)) - return; - - xe_irq_reset(xe); - - irq = pci_irq_vector(pdev, 0); - free_irq(irq, xe); -} - -int xe_irq_install(struct xe_device *xe) +static int xe_irq_msi_request_irqs(struct xe_device *xe) { struct pci_dev *pdev = to_pci_dev(xe->drm.dev); - unsigned int irq_flags = PCI_IRQ_MSIX; irq_handler_t irq_handler; - int err, irq, nvec; + int irq, err; irq_handler = xe_irq_handler(xe); if (!irq_handler) { @@ -684,32 +687,71 @@ int xe_irq_install(struct xe_device *xe) return -EINVAL; } + irq = pci_irq_vector(pdev, 0); + err = request_irq(irq, irq_handler, IRQF_SHARED, DRIVER_NAME, xe); + if (err < 0) { + drm_err(&xe->drm, "Failed to request MSI IRQ %d\n", err); + return err; + } + + return 0; +} + +static void xe_irq_msi_free(struct xe_device *xe) +{ + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + int irq; + + irq = pci_irq_vector(pdev, 0); + free_irq(irq, xe); +} + +static void irq_uninstall(void *arg) +{ + struct xe_device *xe = arg; + + if (!atomic_xchg(&xe->irq.enabled, 0)) + return; + xe_irq_reset(xe); - nvec = pci_msix_vec_count(pdev); - if (nvec <= 0) { - if (nvec == -EINVAL) { - /* MSIX capability is not supported in the device, using MSI */ - irq_flags = PCI_IRQ_MSI; - nvec = 1; - } else { - drm_err(&xe->drm, "MSIX: Failed getting count\n"); - return nvec; - } + if (xe_device_has_msix(xe)) + xe_irq_msix_free(xe); + else + xe_irq_msi_free(xe); +} + +int xe_irq_init(struct xe_device *xe) +{ + spin_lock_init(&xe->irq.lock); + + return xe_irq_msix_init(xe); +} + +int xe_irq_install(struct xe_device *xe) +{ + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + unsigned int irq_flags = PCI_IRQ_MSI; + int nvec = 1; + int err; + + xe_irq_reset(xe); + + if (xe_device_has_msix(xe)) { + nvec = xe->irq.msix.nvec; + irq_flags = PCI_IRQ_MSIX; } err = pci_alloc_irq_vectors(pdev, nvec, nvec, irq_flags); if (err < 0) { - drm_err(&xe->drm, "MSI/MSIX: Failed to enable support %d\n", err); + drm_err(&xe->drm, "Failed to allocate IRQ vectors: %d\n", err); return err; } - irq = pci_irq_vector(pdev, 0); - err = request_irq(irq, irq_handler, IRQF_SHARED, DRIVER_NAME, xe); - if (err < 0) { - drm_err(&xe->drm, "Failed to request MSI/MSIX IRQ %d\n", err); + err = xe_device_has_msix(xe) ? xe_irq_msix_request_irqs(xe) : + xe_irq_msi_request_irqs(xe); + if (err) return err; - } atomic_set(&xe->irq.enabled, 1); @@ -722,18 +764,28 @@ int xe_irq_install(struct xe_device *xe) return 0; free_irq_handler: - free_irq(irq, xe); + if (xe_device_has_msix(xe)) + xe_irq_msix_free(xe); + else + xe_irq_msi_free(xe); return err; } +static void xe_irq_msi_synchronize_irq(struct xe_device *xe) +{ + synchronize_irq(to_pci_dev(xe->drm.dev)->irq); +} + void xe_irq_suspend(struct xe_device *xe) { - int irq = to_pci_dev(xe->drm.dev)->irq; - atomic_set(&xe->irq.enabled, 0); /* no new irqs */ - synchronize_irq(irq); /* flush irqs */ + /* flush irqs */ + if (xe_device_has_msix(xe)) + xe_irq_msix_synchronize_irq(xe); + else + xe_irq_msi_synchronize_irq(xe); xe_irq_reset(xe); /* turn irqs off */ } @@ -754,3 +806,198 @@ void xe_irq_resume(struct xe_device *xe) for_each_gt(gt, xe, id) xe_irq_enable_hwe(gt); } + +/* MSI-X related definitions and functions below. */ + +enum xe_irq_msix_static { + GUC2HOST_MSIX = 0, + DEFAULT_MSIX = XE_IRQ_DEFAULT_MSIX, + /* Must be last */ + NUM_OF_STATIC_MSIX, +}; + +static int xe_irq_msix_init(struct xe_device *xe) +{ + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + int nvec = pci_msix_vec_count(pdev); + + if (nvec == -EINVAL) + return 0; /* MSI */ + + if (nvec < 0) { + drm_err(&xe->drm, "Failed getting MSI-X vectors count: %d\n", nvec); + return nvec; + } + + xe->irq.msix.nvec = nvec; + xa_init_flags(&xe->irq.msix.indexes, XA_FLAGS_ALLOC); + return 0; +} + +static irqreturn_t guc2host_irq_handler(int irq, void *arg) +{ + struct xe_device *xe = arg; + struct xe_tile *tile; + u8 id; + + if (!atomic_read(&xe->irq.enabled)) + return IRQ_NONE; + + for_each_tile(tile, xe, id) + xe_guc_irq_handler(&tile->primary_gt->uc.guc, + GUC_INTR_GUC2HOST); + + return IRQ_HANDLED; +} + +static irqreturn_t xe_irq_msix_default_hwe_handler(int irq, void *arg) +{ + unsigned int tile_id, gt_id; + struct xe_device *xe = arg; + struct xe_memirq *memirq; + struct xe_hw_engine *hwe; + enum xe_hw_engine_id id; + struct xe_tile *tile; + struct xe_gt *gt; + + if (!atomic_read(&xe->irq.enabled)) + return IRQ_NONE; + + for_each_tile(tile, xe, tile_id) { + memirq = &tile->memirq; + if (!memirq->bo) + continue; + + for_each_gt(gt, xe, gt_id) { + if (gt->tile != tile) + continue; + + for_each_hw_engine(hwe, gt, id) + xe_memirq_hwe_handler(memirq, hwe); + } + } + + return IRQ_HANDLED; +} + +static int xe_irq_msix_alloc_vector(struct xe_device *xe, void *irq_buf, + bool dynamic_msix, u16 *msix) +{ + struct xa_limit limit; + int ret; + u32 id; + + limit = (dynamic_msix) ? XA_LIMIT(NUM_OF_STATIC_MSIX, xe->irq.msix.nvec - 1) : + XA_LIMIT(*msix, *msix); + ret = xa_alloc(&xe->irq.msix.indexes, &id, irq_buf, limit, GFP_KERNEL); + if (ret) + return ret; + + if (dynamic_msix) + *msix = id; + + return 0; +} + +static void xe_irq_msix_release_vector(struct xe_device *xe, u16 msix) +{ + xa_erase(&xe->irq.msix.indexes, msix); +} + +static int xe_irq_msix_request_irq_internal(struct xe_device *xe, irq_handler_t handler, + void *irq_buf, const char *name, u16 msix) +{ + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + int ret, irq; + + irq = pci_irq_vector(pdev, msix); + if (irq < 0) + return irq; + + ret = request_irq(irq, handler, IRQF_SHARED, name, irq_buf); + if (ret < 0) + return ret; + + return 0; +} + +int xe_irq_msix_request_irq(struct xe_device *xe, irq_handler_t handler, void *irq_buf, + const char *name, bool dynamic_msix, u16 *msix) +{ + int ret; + + ret = xe_irq_msix_alloc_vector(xe, irq_buf, dynamic_msix, msix); + if (ret) + return ret; + + ret = xe_irq_msix_request_irq_internal(xe, handler, irq_buf, name, *msix); + if (ret) { + drm_err(&xe->drm, "Failed to request IRQ for MSI-X %u\n", *msix); + xe_irq_msix_release_vector(xe, *msix); + return ret; + } + + return 0; +} + +void xe_irq_msix_free_irq(struct xe_device *xe, u16 msix) +{ + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + int irq; + void *irq_buf; + + irq_buf = xa_load(&xe->irq.msix.indexes, msix); + if (!irq_buf) + return; + + irq = pci_irq_vector(pdev, msix); + if (irq < 0) { + drm_err(&xe->drm, "MSI-X %u can't be released, there is no matching IRQ\n", msix); + return; + } + + free_irq(irq, irq_buf); + xe_irq_msix_release_vector(xe, msix); +} + +int xe_irq_msix_request_irqs(struct xe_device *xe) +{ + int err; + u16 msix; + + msix = GUC2HOST_MSIX; + err = xe_irq_msix_request_irq(xe, guc2host_irq_handler, xe, + DRIVER_NAME "-guc2host", false, &msix); + if (err) + return err; + + msix = DEFAULT_MSIX; + err = xe_irq_msix_request_irq(xe, xe_irq_msix_default_hwe_handler, xe, + DRIVER_NAME "-default-msix", false, &msix); + if (err) { + xe_irq_msix_free_irq(xe, GUC2HOST_MSIX); + return err; + } + + return 0; +} + +void xe_irq_msix_free(struct xe_device *xe) +{ + unsigned long msix; + u32 *dummy; + + xa_for_each(&xe->irq.msix.indexes, msix, dummy) + xe_irq_msix_free_irq(xe, msix); + xa_destroy(&xe->irq.msix.indexes); +} + +void xe_irq_msix_synchronize_irq(struct xe_device *xe) +{ + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + unsigned long msix; + u32 *dummy; + + xa_for_each(&xe->irq.msix.indexes, msix, dummy) + synchronize_irq(pci_irq_vector(pdev, msix)); +} diff --git a/drivers/gpu/drm/xe/xe_irq.h b/drivers/gpu/drm/xe/xe_irq.h index 067514e13675..a28bd577ba52 100644 --- a/drivers/gpu/drm/xe/xe_irq.h +++ b/drivers/gpu/drm/xe/xe_irq.h @@ -6,13 +6,21 @@ #ifndef _XE_IRQ_H_ #define _XE_IRQ_H_ +#include + +#define XE_IRQ_DEFAULT_MSIX 1 + struct xe_device; struct xe_tile; struct xe_gt; +int xe_irq_init(struct xe_device *xe); int xe_irq_install(struct xe_device *xe); void xe_irq_suspend(struct xe_device *xe); void xe_irq_resume(struct xe_device *xe); void xe_irq_enable_hwe(struct xe_gt *gt); +int xe_irq_msix_request_irq(struct xe_device *xe, irq_handler_t handler, void *irq_buf, + const char *name, bool dynamic_msix, u16 *msix); +void xe_irq_msix_free_irq(struct xe_device *xe, u16 msix); #endif diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 22e58c6e2a35..bbb9ffbf6367 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -584,6 +584,7 @@ static void set_memory_based_intr(u32 *regs, struct xe_hw_engine *hwe) { struct xe_memirq *memirq = >_to_tile(hwe->gt)->memirq; struct xe_device *xe = gt_to_xe(hwe->gt); + u8 num_regs; if (!xe_device_uses_memirq(xe)) return; @@ -593,12 +594,18 @@ static void set_memory_based_intr(u32 *regs, struct xe_hw_engine *hwe) regs[CTX_INT_MASK_ENABLE_REG] = RING_IMR(0).addr; regs[CTX_INT_MASK_ENABLE_PTR] = xe_memirq_enable_ptr(memirq); - regs[CTX_LRI_INT_REPORT_PTR] = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(2) | + num_regs = xe_device_has_msix(xe) ? 3 : 2; + regs[CTX_LRI_INT_REPORT_PTR] = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(num_regs) | MI_LRI_LRM_CS_MMIO | MI_LRI_FORCE_POSTED; regs[CTX_INT_STATUS_REPORT_REG] = RING_INT_STATUS_RPT_PTR(0).addr; regs[CTX_INT_STATUS_REPORT_PTR] = xe_memirq_status_ptr(memirq, hwe); regs[CTX_INT_SRC_REPORT_REG] = RING_INT_SRC_RPT_PTR(0).addr; regs[CTX_INT_SRC_REPORT_PTR] = xe_memirq_source_ptr(memirq, hwe); + + if (xe_device_has_msix(xe)) { + regs[CTX_CS_INT_VEC_REG] = CS_INT_VEC(0).addr; + /* CTX_CS_INT_VEC_DATA will be set in xe_lrc_init */ + } } static int lrc_ring_mi_mode(struct xe_hw_engine *hwe) @@ -876,7 +883,7 @@ static void xe_lrc_finish(struct xe_lrc *lrc) #define PVC_CTX_ACC_CTR_THOLD (0x2a + 1) static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, - struct xe_vm *vm, u32 ring_size) + struct xe_vm *vm, u32 ring_size, u16 msix_vec) { struct xe_gt *gt = hwe->gt; struct xe_tile *tile = gt_to_tile(gt); @@ -945,6 +952,14 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, xe_drm_client_add_bo(vm->xef->client, lrc->bo); } + if (xe_device_has_msix(xe)) { + xe_lrc_write_ctx_reg(lrc, CTX_INT_STATUS_REPORT_PTR, + xe_memirq_status_ptr(&tile->memirq, hwe)); + xe_lrc_write_ctx_reg(lrc, CTX_INT_SRC_REPORT_PTR, + xe_memirq_source_ptr(&tile->memirq, hwe)); + xe_lrc_write_ctx_reg(lrc, CTX_CS_INT_VEC_DATA, msix_vec << 16 | msix_vec); + } + if (xe_gt_has_indirect_ring_state(gt)) { xe_lrc_write_ctx_reg(lrc, CTX_INDIRECT_RING_STATE, __xe_lrc_indirect_ring_ggtt_addr(lrc)); @@ -1005,6 +1020,7 @@ err_lrc_finish: * @hwe: Hardware Engine * @vm: The VM (address space) * @ring_size: LRC ring size + * @msix_vec: MSI-X interrupt vector (for platforms that support it) * * Allocate and initialize the Logical Ring Context (LRC). * @@ -1012,7 +1028,7 @@ err_lrc_finish: * upon failure. */ struct xe_lrc *xe_lrc_create(struct xe_hw_engine *hwe, struct xe_vm *vm, - u32 ring_size) + u32 ring_size, u16 msix_vec) { struct xe_lrc *lrc; int err; @@ -1021,7 +1037,7 @@ struct xe_lrc *xe_lrc_create(struct xe_hw_engine *hwe, struct xe_vm *vm, if (!lrc) return ERR_PTR(-ENOMEM); - err = xe_lrc_init(lrc, hwe, vm, ring_size); + err = xe_lrc_init(lrc, hwe, vm, ring_size, msix_vec); if (err) { kfree(lrc); return ERR_PTR(err); diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h index b459dcab8787..4206e6a8b50a 100644 --- a/drivers/gpu/drm/xe/xe_lrc.h +++ b/drivers/gpu/drm/xe/xe_lrc.h @@ -42,7 +42,7 @@ struct xe_lrc_snapshot { #define LRC_PPHWSP_SCRATCH_ADDR (0x34 * 4) struct xe_lrc *xe_lrc_create(struct xe_hw_engine *hwe, struct xe_vm *vm, - u32 ring_size); + u32 ring_size, u16 msix_vec); void xe_lrc_destroy(struct kref *ref); /** diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 1b97d90aadda..278bc96cf593 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -1506,7 +1506,7 @@ err_bb: * using the default engine for the updates, they will be performed in the * order they grab the job_mutex. If different engines are used, external * synchronization is needed for overlapping updates to maintain page-table - * consistency. Note that the meaing of "overlapping" is that the updates + * consistency. Note that the meaning of "overlapping" is that the updates * touch the same page-table, which might be a higher-level page-directory. * If no pipelining is needed, then updates may be performed by the cpu. * diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index ec88b18e9baa..eeb96b5f49e2 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -16,7 +16,6 @@ #include "instructions/xe_mi_commands.h" #include "regs/xe_engine_regs.h" #include "regs/xe_gt_regs.h" -#include "regs/xe_lrc_layout.h" #include "regs/xe_oa_regs.h" #include "xe_assert.h" #include "xe_bb.h" @@ -28,7 +27,6 @@ #include "xe_gt_mcr.h" #include "xe_gt_printk.h" #include "xe_guc_pc.h" -#include "xe_lrc.h" #include "xe_macros.h" #include "xe_mmio.h" #include "xe_oa.h" @@ -74,12 +72,6 @@ struct xe_oa_config { struct rcu_head rcu; }; -struct flex { - struct xe_reg reg; - u32 offset; - u32 value; -}; - struct xe_oa_open_param { struct xe_file *xef; u32 oa_unit_id; @@ -97,6 +89,7 @@ struct xe_oa_open_param { int num_syncs; struct xe_sync_entry *syncs; size_t oa_buffer_size; + int wait_num_reports; }; struct xe_oa_config_bo { @@ -241,11 +234,10 @@ static void oa_timestamp_clear(struct xe_oa_stream *stream, u32 *report) static bool xe_oa_buffer_check_unlocked(struct xe_oa_stream *stream) { u32 gtt_offset = xe_bo_ggtt_addr(stream->oa_buffer.bo); + u32 tail, hw_tail, partial_report_size, available; int report_size = stream->oa_buffer.format->size; - u32 tail, hw_tail; unsigned long flags; bool pollin; - u32 partial_report_size; spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); @@ -289,8 +281,8 @@ static bool xe_oa_buffer_check_unlocked(struct xe_oa_stream *stream) stream->oa_buffer.tail = tail; - pollin = xe_oa_circ_diff(stream, stream->oa_buffer.tail, - stream->oa_buffer.head) >= report_size; + available = xe_oa_circ_diff(stream, stream->oa_buffer.tail, stream->oa_buffer.head); + pollin = available >= stream->wait_num_reports * report_size; spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); @@ -605,19 +597,38 @@ static __poll_t xe_oa_poll(struct file *file, poll_table *wait) return ret; } +static void xe_oa_lock_vma(struct xe_exec_queue *q) +{ + if (q->vm) { + down_read(&q->vm->lock); + xe_vm_lock(q->vm, false); + } +} + +static void xe_oa_unlock_vma(struct xe_exec_queue *q) +{ + if (q->vm) { + xe_vm_unlock(q->vm); + up_read(&q->vm->lock); + } +} + static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, enum xe_oa_submit_deps deps, struct xe_bb *bb) { + struct xe_exec_queue *q = stream->exec_q ?: stream->k_exec_q; struct xe_sched_job *job; struct dma_fence *fence; int err = 0; - /* Kernel configuration is issued on stream->k_exec_q, not stream->exec_q */ - job = xe_bb_create_job(stream->k_exec_q, bb); + xe_oa_lock_vma(q); + + job = xe_bb_create_job(q, bb); if (IS_ERR(job)) { err = PTR_ERR(job); goto exit; } + job->ggtt = true; if (deps == XE_OA_SUBMIT_ADD_DEPS) { for (int i = 0; i < stream->num_syncs && !err; i++) @@ -632,10 +643,13 @@ static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, enum xe_oa fence = dma_fence_get(&job->drm.s_fence->finished); xe_sched_job_push(job); + xe_oa_unlock_vma(q); + return fence; err_put_job: xe_sched_job_put(job); exit: + xe_oa_unlock_vma(q); return ERR_PTR(err); } @@ -684,63 +698,19 @@ static void xe_oa_free_configs(struct xe_oa_stream *stream) dma_fence_put(stream->last_fence); } -static void xe_oa_store_flex(struct xe_oa_stream *stream, struct xe_lrc *lrc, - struct xe_bb *bb, const struct flex *flex, u32 count) -{ - u32 offset = xe_bo_ggtt_addr(lrc->bo); - - do { - bb->cs[bb->len++] = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1); - bb->cs[bb->len++] = offset + flex->offset * sizeof(u32); - bb->cs[bb->len++] = 0; - bb->cs[bb->len++] = flex->value; - - } while (flex++, --count); -} - -static int xe_oa_modify_ctx_image(struct xe_oa_stream *stream, struct xe_lrc *lrc, - const struct flex *flex, u32 count) +static int xe_oa_load_with_lri(struct xe_oa_stream *stream, struct xe_oa_reg *reg_lri, u32 count) { struct dma_fence *fence; struct xe_bb *bb; int err; - bb = xe_bb_new(stream->gt, 4 * count, false); + bb = xe_bb_new(stream->gt, 2 * count + 1, false); if (IS_ERR(bb)) { err = PTR_ERR(bb); goto exit; } - xe_oa_store_flex(stream, lrc, bb, flex, count); - - fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_NO_DEPS, bb); - if (IS_ERR(fence)) { - err = PTR_ERR(fence); - goto free_bb; - } - xe_bb_free(bb, fence); - dma_fence_put(fence); - - return 0; -free_bb: - xe_bb_free(bb, NULL); -exit: - return err; -} - -static int xe_oa_load_with_lri(struct xe_oa_stream *stream, struct xe_oa_reg *reg_lri) -{ - struct dma_fence *fence; - struct xe_bb *bb; - int err; - - bb = xe_bb_new(stream->gt, 3, false); - if (IS_ERR(bb)) { - err = PTR_ERR(bb); - goto exit; - } - - write_cs_mi_lri(bb, reg_lri, 1); + write_cs_mi_lri(bb, reg_lri, count); fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_NO_DEPS, bb); if (IS_ERR(fence)) { @@ -760,71 +730,55 @@ exit: static int xe_oa_configure_oar_context(struct xe_oa_stream *stream, bool enable) { const struct xe_oa_format *format = stream->oa_buffer.format; - struct xe_lrc *lrc = stream->exec_q->lrc[0]; - u32 regs_offset = xe_lrc_regs_offset(lrc) / sizeof(u32); u32 oacontrol = __format_to_oactrl(format, OAR_OACONTROL_COUNTER_SEL_MASK) | (enable ? OAR_OACONTROL_COUNTER_ENABLE : 0); - struct flex regs_context[] = { + struct xe_oa_reg reg_lri[] = { { OACTXCONTROL(stream->hwe->mmio_base), - stream->oa->ctx_oactxctrl_offset[stream->hwe->class] + 1, enable ? OA_COUNTER_RESUME : 0, }, + { + OAR_OACONTROL, + oacontrol, + }, { RING_CONTEXT_CONTROL(stream->hwe->mmio_base), - regs_offset + CTX_CONTEXT_CONTROL, - _MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE), + _MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE, + enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0) }, }; - struct xe_oa_reg reg_lri = { OAR_OACONTROL, oacontrol }; - int err; - /* Modify stream hwe context image with regs_context */ - err = xe_oa_modify_ctx_image(stream, stream->exec_q->lrc[0], - regs_context, ARRAY_SIZE(regs_context)); - if (err) - return err; - - /* Apply reg_lri using LRI */ - return xe_oa_load_with_lri(stream, ®_lri); + return xe_oa_load_with_lri(stream, reg_lri, ARRAY_SIZE(reg_lri)); } static int xe_oa_configure_oac_context(struct xe_oa_stream *stream, bool enable) { const struct xe_oa_format *format = stream->oa_buffer.format; - struct xe_lrc *lrc = stream->exec_q->lrc[0]; - u32 regs_offset = xe_lrc_regs_offset(lrc) / sizeof(u32); u32 oacontrol = __format_to_oactrl(format, OAR_OACONTROL_COUNTER_SEL_MASK) | (enable ? OAR_OACONTROL_COUNTER_ENABLE : 0); - struct flex regs_context[] = { + struct xe_oa_reg reg_lri[] = { { OACTXCONTROL(stream->hwe->mmio_base), - stream->oa->ctx_oactxctrl_offset[stream->hwe->class] + 1, enable ? OA_COUNTER_RESUME : 0, }, + { + OAC_OACONTROL, + oacontrol + }, { RING_CONTEXT_CONTROL(stream->hwe->mmio_base), - regs_offset + CTX_CONTEXT_CONTROL, - _MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE) | + _MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE, + enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0) | _MASKED_FIELD(CTX_CTRL_RUN_ALONE, enable ? CTX_CTRL_RUN_ALONE : 0), }, }; - struct xe_oa_reg reg_lri = { OAC_OACONTROL, oacontrol }; - int err; /* Set ccs select to enable programming of OAC_OACONTROL */ xe_mmio_write32(&stream->gt->mmio, __oa_regs(stream)->oa_ctrl, __oa_ccs_select(stream)); - /* Modify stream hwe context image with regs_context */ - err = xe_oa_modify_ctx_image(stream, stream->exec_q->lrc[0], - regs_context, ARRAY_SIZE(regs_context)); - if (err) - return err; - - /* Apply reg_lri using LRI */ - return xe_oa_load_with_lri(stream, ®_lri); + return xe_oa_load_with_lri(stream, reg_lri, ARRAY_SIZE(reg_lri)); } static int xe_oa_configure_oa_context(struct xe_oa_stream *stream, bool enable) @@ -1285,6 +1239,17 @@ static int xe_oa_set_prop_oa_buffer_size(struct xe_oa *oa, u64 value, return 0; } +static int xe_oa_set_prop_wait_num_reports(struct xe_oa *oa, u64 value, + struct xe_oa_open_param *param) +{ + if (!value) { + drm_dbg(&oa->xe->drm, "wait_num_reports %llu\n", value); + return -EINVAL; + } + param->wait_num_reports = value; + return 0; +} + static int xe_oa_set_prop_ret_inval(struct xe_oa *oa, u64 value, struct xe_oa_open_param *param) { @@ -1306,6 +1271,7 @@ static const xe_oa_set_property_fn xe_oa_set_property_funcs_open[] = { [DRM_XE_OA_PROPERTY_NUM_SYNCS] = xe_oa_set_prop_num_syncs, [DRM_XE_OA_PROPERTY_SYNCS] = xe_oa_set_prop_syncs_user, [DRM_XE_OA_PROPERTY_OA_BUFFER_SIZE] = xe_oa_set_prop_oa_buffer_size, + [DRM_XE_OA_PROPERTY_WAIT_NUM_REPORTS] = xe_oa_set_prop_wait_num_reports, }; static const xe_oa_set_property_fn xe_oa_set_property_funcs_config[] = { @@ -1321,6 +1287,7 @@ static const xe_oa_set_property_fn xe_oa_set_property_funcs_config[] = { [DRM_XE_OA_PROPERTY_NUM_SYNCS] = xe_oa_set_prop_num_syncs, [DRM_XE_OA_PROPERTY_SYNCS] = xe_oa_set_prop_syncs_user, [DRM_XE_OA_PROPERTY_OA_BUFFER_SIZE] = xe_oa_set_prop_ret_inval, + [DRM_XE_OA_PROPERTY_WAIT_NUM_REPORTS] = xe_oa_set_prop_ret_inval, }; static int xe_oa_user_ext_set_property(struct xe_oa *oa, enum xe_oa_user_extn_from from, @@ -1704,81 +1671,6 @@ static const struct file_operations xe_oa_fops = { .mmap = xe_oa_mmap, }; -static bool engine_supports_mi_query(struct xe_hw_engine *hwe) -{ - return hwe->class == XE_ENGINE_CLASS_RENDER || - hwe->class == XE_ENGINE_CLASS_COMPUTE; -} - -static bool xe_oa_find_reg_in_lri(u32 *state, u32 reg, u32 *offset, u32 end) -{ - u32 idx = *offset; - u32 len = min(MI_LRI_LEN(state[idx]) + idx, end); - bool found = false; - - idx++; - for (; idx < len; idx += 2) { - if (state[idx] == reg) { - found = true; - break; - } - } - - *offset = idx; - return found; -} - -#define IS_MI_LRI_CMD(x) (REG_FIELD_GET(MI_OPCODE, (x)) == \ - REG_FIELD_GET(MI_OPCODE, MI_LOAD_REGISTER_IMM)) - -static u32 xe_oa_context_image_offset(struct xe_oa_stream *stream, u32 reg) -{ - struct xe_lrc *lrc = stream->exec_q->lrc[0]; - u32 len = (xe_gt_lrc_size(stream->gt, stream->hwe->class) + - lrc->ring.size) / sizeof(u32); - u32 offset = xe_lrc_regs_offset(lrc) / sizeof(u32); - u32 *state = (u32 *)lrc->bo->vmap.vaddr; - - if (drm_WARN_ON(&stream->oa->xe->drm, !state)) - return U32_MAX; - - for (; offset < len; ) { - if (IS_MI_LRI_CMD(state[offset])) { - /* - * We expect reg-value pairs in MI_LRI command, so - * MI_LRI_LEN() should be even - */ - drm_WARN_ON(&stream->oa->xe->drm, - MI_LRI_LEN(state[offset]) & 0x1); - - if (xe_oa_find_reg_in_lri(state, reg, &offset, len)) - break; - } else { - offset++; - } - } - - return offset < len ? offset : U32_MAX; -} - -static int xe_oa_set_ctx_ctrl_offset(struct xe_oa_stream *stream) -{ - struct xe_reg reg = OACTXCONTROL(stream->hwe->mmio_base); - u32 offset = stream->oa->ctx_oactxctrl_offset[stream->hwe->class]; - - /* Do this only once. Failure is stored as offset of U32_MAX */ - if (offset) - goto exit; - - offset = xe_oa_context_image_offset(stream, reg.addr); - stream->oa->ctx_oactxctrl_offset[stream->hwe->class] = offset; - - drm_dbg(&stream->oa->xe->drm, "%s oa ctx control at 0x%08x dword offset\n", - stream->hwe->name, offset); -exit: - return offset && offset != U32_MAX ? 0 : -ENODEV; -} - static int xe_oa_stream_init(struct xe_oa_stream *stream, struct xe_oa_open_param *param) { @@ -1797,6 +1689,7 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream, stream->periodic = param->period_exponent > 0; stream->period_exponent = param->period_exponent; stream->no_preempt = param->no_preempt; + stream->wait_num_reports = param->wait_num_reports; stream->xef = xe_file_get(param->xef); stream->num_syncs = param->num_syncs; @@ -1815,17 +1708,6 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream, else stream->oa_buffer.circ_size = param->oa_buffer_size; - if (stream->exec_q && engine_supports_mi_query(stream->hwe)) { - /* If we don't find the context offset, just return error */ - ret = xe_oa_set_ctx_ctrl_offset(stream); - if (ret) { - drm_err(&stream->oa->xe->drm, - "xe_oa_set_ctx_ctrl_offset failed for %s\n", - stream->hwe->name); - goto exit; - } - } - stream->oa_config = xe_oa_get_oa_config(stream->oa, param->metric_set); if (!stream->oa_config) { drm_dbg(&stream->oa->xe->drm, "Invalid OA config id=%i\n", param->metric_set); @@ -2094,8 +1976,8 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f if (XE_IOCTL_DBG(oa->xe, !param.exec_q)) return -ENOENT; - if (param.exec_q->width > 1) - drm_dbg(&oa->xe->drm, "exec_q->width > 1, programming only exec_q->lrc[0]\n"); + if (XE_IOCTL_DBG(oa->xe, param.exec_q->width > 1)) + return -EOPNOTSUPP; } /* @@ -2156,6 +2038,14 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f if (!param.oa_buffer_size) param.oa_buffer_size = DEFAULT_XE_OA_BUFFER_SIZE; + if (!param.wait_num_reports) + param.wait_num_reports = 1; + if (param.wait_num_reports > param.oa_buffer_size / f->size) { + drm_dbg(&oa->xe->drm, "wait_num_reports %d\n", param.wait_num_reports); + ret = -EINVAL; + goto err_exec_q; + } + ret = xe_oa_parse_syncs(oa, ¶m); if (ret) goto err_exec_q; @@ -2273,6 +2163,7 @@ static const struct xe_mmio_range xe2_oa_mux_regs[] = { { .start = 0x5194, .end = 0x5194 }, /* SYS_MEM_LAT_MEASURE_MERTF_GRP_3D */ { .start = 0x8704, .end = 0x8704 }, /* LMEM_LAT_MEASURE_MCFG_GRP */ { .start = 0xB1BC, .end = 0xB1BC }, /* L3_BANK_LAT_MEASURE_LBCF_GFX */ + { .start = 0xD0E0, .end = 0xD0F4 }, /* VISACTL */ { .start = 0xE18C, .end = 0xE18C }, /* SAMPLER_MODE */ { .start = 0xE590, .end = 0xE590 }, /* TDL_LSC_LAT_MEASURE_TDL_GFX */ { .start = 0x13000, .end = 0x137FC }, /* PES_0_PESL0 - PES_63_UPPER_PESL3 */ diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h index df7793915628..52e33c37d5ee 100644 --- a/drivers/gpu/drm/xe/xe_oa_types.h +++ b/drivers/gpu/drm/xe/xe_oa_types.h @@ -138,9 +138,6 @@ struct xe_oa { /** @metrics_idr: List of dynamic configurations (struct xe_oa_config) */ struct idr metrics_idr; - /** @ctx_oactxctrl_offset: offset of OACTXCONTROL register in context image */ - u32 ctx_oactxctrl_offset[XE_ENGINE_CLASS_MAX]; - /** @oa_formats: tracks all OA formats across platforms */ const struct xe_oa_format *oa_formats; @@ -218,6 +215,9 @@ struct xe_oa_stream { /** @pollin: Whether there is data available to read */ bool pollin; + /** @wait_num_reports: Number of reports to wait for before signalling pollin */ + int wait_num_reports; + /** @periodic: Whether periodic sampling is currently enabled */ bool periodic; diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c index 8ec1b84cbb9e..57cf01efc07f 100644 --- a/drivers/gpu/drm/xe/xe_observation.c +++ b/drivers/gpu/drm/xe/xe_observation.c @@ -56,7 +56,7 @@ int xe_observation_ioctl(struct drm_device *dev, void *data, struct drm_file *fi } } -static struct ctl_table observation_ctl_table[] = { +static const struct ctl_table observation_ctl_table[] = { { .procname = "observation_paranoid", .data = &xe_observation_paranoid, diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 6b7f77425c7f..39be74848e44 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -490,7 +490,7 @@ static void read_gmdid(struct xe_device *xe, enum xe_gmdid_type type, u32 *ver, * least basic xe_gt and xe_guc initialization. * * Since to obtain the value of GMDID_MEDIA we need to use the - * media GuC, temporarly tweak the gt type. + * media GuC, temporarily tweak the gt type. */ xe_gt_assert(gt, gt->info.type == XE_GT_TYPE_UNINITIALIZED); @@ -781,7 +781,7 @@ static void xe_pci_remove(struct pci_dev *pdev) * error injectable functions is proper handling of the error code by the * caller for recovery, which is always the case here. The second * requirement is that no state is changed before the first error return. - * It is not strictly fullfilled for all initialization functions using the + * It is not strictly fulfilled for all initialization functions using the * ALLOW_ERROR_INJECTION() macro but this is acceptable because for those * error cases at probe time, the error code is simply propagated up by the * caller. Therefore there is no consequence on those specific callers when diff --git a/drivers/gpu/drm/xe/xe_pcode.c b/drivers/gpu/drm/xe/xe_pcode.c index d95d9835de42..9333ce776a6e 100644 --- a/drivers/gpu/drm/xe/xe_pcode.c +++ b/drivers/gpu/drm/xe/xe_pcode.c @@ -217,7 +217,7 @@ out: * * It returns 0 on success, and -ERROR number on failure, -EINVAL if max * frequency is higher then the minimal, and other errors directly translated - * from the PCODE Error returs: + * from the PCODE Error returns: * - -ENXIO: "Illegal Command" * - -ETIMEDOUT: "Timed out" * - -EINVAL: "Illegal Data" diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index a6761cb769b2..c9cc0c091dfd 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -7,6 +7,7 @@ #include #include +#include #include #include @@ -390,7 +391,7 @@ int xe_pm_runtime_suspend(struct xe_device *xe) /* * Applying lock for entire list op as xe_ttm_bo_destroy and xe_bo_move_notify - * also checks and delets bo entry from user fault list. + * also checks and deletes bo entry from user fault list. */ mutex_lock(&xe->mem_access.vram_userfault.lock); list_for_each_entry_safe(bo, on, @@ -607,7 +608,8 @@ static bool xe_pm_suspending_or_resuming(struct xe_device *xe) struct device *dev = xe->drm.dev; return dev->power.runtime_status == RPM_SUSPENDING || - dev->power.runtime_status == RPM_RESUMING; + dev->power.runtime_status == RPM_RESUMING || + pm_suspend_target_state != PM_SUSPEND_ON; #else return false; #endif diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 65c3c1688710..1ddcc7e79a93 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -276,7 +276,7 @@ struct xe_pt_stage_bind_walk { /* Also input, but is updated during the walk*/ /** @curs: The DMA address cursor. */ struct xe_res_cursor *curs; - /** @va_curs_start: The Virtual address coresponding to @curs->start */ + /** @va_curs_start: The Virtual address corresponding to @curs->start */ u64 va_curs_start; /* Output */ diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index d2a816f71bf2..c059639613f7 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -672,7 +672,8 @@ static int query_oa_units(struct xe_device *xe, du->oa_unit_type = u->type; du->oa_timestamp_freq = xe_oa_timestamp_frequency(gt); du->capabilities = DRM_XE_OA_CAPS_BASE | DRM_XE_OA_CAPS_SYNCS | - DRM_XE_OA_CAPS_OA_BUFFER_SIZE; + DRM_XE_OA_CAPS_OA_BUFFER_SIZE | + DRM_XE_OA_CAPS_WAIT_NUM_REPORTS; j = 0; for_each_hw_engine(hwe, gt, hwe_id) { diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index 0be4f489d3e1..9f327f27c072 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -221,7 +221,10 @@ static int emit_pipe_imm_ggtt(u32 addr, u32 value, bool stall_only, u32 *dw, static u32 get_ppgtt_flag(struct xe_sched_job *job) { - return job->q->vm ? BIT(8) : 0; + if (job->q->vm && !job->ggtt) + return BIT(8); + + return 0; } static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i) diff --git a/drivers/gpu/drm/xe/xe_rtp.c b/drivers/gpu/drm/xe/xe_rtp.c index b13d4d62f0b1..7a1c78fdfc92 100644 --- a/drivers/gpu/drm/xe/xe_rtp.c +++ b/drivers/gpu/drm/xe/xe_rtp.c @@ -340,3 +340,8 @@ bool xe_rtp_match_first_gslice_fused_off(const struct xe_gt *gt, return dss >= dss_per_gslice; } +bool xe_rtp_match_not_sriov_vf(const struct xe_gt *gt, + const struct xe_hw_engine *hwe) +{ + return !IS_SRIOV_VF(gt_to_xe(gt)); +} diff --git a/drivers/gpu/drm/xe/xe_rtp.h b/drivers/gpu/drm/xe/xe_rtp.h index 827d932b6908..38b9f13bba5e 100644 --- a/drivers/gpu/drm/xe/xe_rtp.h +++ b/drivers/gpu/drm/xe/xe_rtp.h @@ -131,7 +131,7 @@ struct xe_reg_sr; * @ver_end__: Last graphics IP version to match * * Note that the range matching this rule is [ @ver_start__, @ver_end__ ], i.e. - * inclusive on boths sides + * inclusive on both sides * * Refer to XE_RTP_RULES() for expected usage. */ @@ -169,7 +169,7 @@ struct xe_reg_sr; * @ver_end__: Last media IP version to match * * Note that the range matching this rule is [ @ver_start__, @ver_end__ ], i.e. - * inclusive on boths sides + * inclusive on both sides * * Refer to XE_RTP_RULES() for expected usage. */ @@ -476,4 +476,15 @@ bool xe_rtp_match_first_render_or_compute(const struct xe_gt *gt, bool xe_rtp_match_first_gslice_fused_off(const struct xe_gt *gt, const struct xe_hw_engine *hwe); +/* + * xe_rtp_match_not_sriov_vf - Match when not on SR-IOV VF device + * + * @gt: GT structure + * @hwe: Engine instance + * + * Returns: true if device is not VF, false otherwise. + */ +bool xe_rtp_match_not_sriov_vf(const struct xe_gt *gt, + const struct xe_hw_engine *hwe); + #endif diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h index f13f333f00be..d942b20a9f29 100644 --- a/drivers/gpu/drm/xe/xe_sched_job_types.h +++ b/drivers/gpu/drm/xe/xe_sched_job_types.h @@ -56,6 +56,8 @@ struct xe_sched_job { u32 migrate_flush_flags; /** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */ bool ring_ops_flush_tlb; + /** @ggtt: mapped in ggtt. */ + bool ggtt; /** @ptrs: per instance pointers. */ struct xe_job_ptrs ptrs[]; }; diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h b/drivers/gpu/drm/xe/xe_trace_bo.h index 1762dd30ba6d..ea50fee50c7d 100644 --- a/drivers/gpu/drm/xe/xe_trace_bo.h +++ b/drivers/gpu/drm/xe/xe_trace_bo.h @@ -60,8 +60,8 @@ TRACE_EVENT(xe_bo_move, TP_STRUCT__entry( __field(struct xe_bo *, bo) __field(size_t, size) - __field(u32, new_placement) - __field(u32, old_placement) + __string(new_placement_name, xe_mem_type_to_name[new_placement]) + __string(old_placement_name, xe_mem_type_to_name[old_placement]) __string(device_id, __dev_name_bo(bo)) __field(bool, move_lacks_source) ), @@ -69,15 +69,15 @@ TRACE_EVENT(xe_bo_move, TP_fast_assign( __entry->bo = bo; __entry->size = bo->size; - __entry->new_placement = new_placement; - __entry->old_placement = old_placement; + __assign_str(new_placement_name); + __assign_str(old_placement_name); __assign_str(device_id); __entry->move_lacks_source = move_lacks_source; ), TP_printk("move_lacks_source:%s, migrate object %p [size %zu] from %s to %s device_id:%s", __entry->move_lacks_source ? "yes" : "no", __entry->bo, __entry->size, - xe_mem_type_to_name[__entry->old_placement], - xe_mem_type_to_name[__entry->new_placement], __get_str(device_id)) + __get_str(old_placement_name), + __get_str(new_placement_name), __get_str(device_id)) ); DECLARE_EVENT_CLASS(xe_vma, diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c index c95728c45ea4..f4a16e5fa770 100644 --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c @@ -5,6 +5,7 @@ */ #include +#include #include #include @@ -311,6 +312,13 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr, struct ttm_resource_manager *man = &mgr->manager; int err; + if (mem_type != XE_PL_STOLEN) { + const char *name = mem_type == XE_PL_VRAM0 ? "vram0" : "vram1"; + man->cg = drmm_cgroup_register_region(&xe->drm, name, size); + if (IS_ERR(man->cg)) + return PTR_ERR(man->cg); + } + man->func = &xe_ttm_vram_mgr_func; mgr->mem_type = mem_type; mutex_init(&mgr->lock); diff --git a/drivers/gpu/drm/xe/xe_uc_fw_types.h b/drivers/gpu/drm/xe/xe_uc_fw_types.h index 0d8caa0e7354..ad3b35a0e6eb 100644 --- a/drivers/gpu/drm/xe/xe_uc_fw_types.h +++ b/drivers/gpu/drm/xe/xe_uc_fw_types.h @@ -92,7 +92,7 @@ struct xe_uc_fw { const enum xe_uc_fw_status status; /** * @__status: private firmware load status - only to be used - * by firmware laoding code + * by firmware loading code */ enum xe_uc_fw_status __status; }; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index b4a44e1ea167..690330352d4c 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1024,7 +1024,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma) /* * Since userptr pages are not pinned, we can't remove - * the notifer until we're sure the GPU is not accessing + * the notifier until we're sure the GPU is not accessing * them anymore */ mmu_interval_notifier_remove(&userptr->notifier); @@ -2107,7 +2107,7 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op) } } - /* Adjust for partial unbind after removin VMA from VM */ + /* Adjust for partial unbind after removing VMA from VM */ if (!err) { op->base.remap.unmap->va->va.addr = op->remap.start; op->base.remap.unmap->va->va.range = op->remap.range; diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index 3ed12a85cc60..40438c3d9b72 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -34,7 +34,7 @@ GRAPHICS_VERSION(2004) 22019338487 MEDIA_VERSION(2000) GRAPHICS_VERSION(2001) - MEDIA_VERSION(3000), MEDIA_STEP(A0, B0) + MEDIA_VERSION(3000), MEDIA_STEP(A0, B0), FUNC(xe_rtp_match_not_sriov_vf) 22019338487_display PLATFORM(LUNARLAKE) 16023588340 GRAPHICS_VERSION(2001) 14019789679 GRAPHICS_VERSION(1255) diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c index 0b63fd48ea92..979f6d3239ba 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dp.c +++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c @@ -1564,7 +1564,7 @@ static void zynqmp_dp_bridge_atomic_enable(struct drm_bridge *bridge, pm_runtime_get_sync(dp->dev); - mutex_lock(&dp->lock); + guard(mutex)(&dp->lock); zynqmp_dp_disp_enable(dp, old_bridge_state); /* @@ -1624,7 +1624,6 @@ static void zynqmp_dp_bridge_atomic_enable(struct drm_bridge *bridge, zynqmp_dp_write(dp, ZYNQMP_DP_SOFTWARE_RESET, ZYNQMP_DP_SOFTWARE_RESET_ALL); zynqmp_dp_write(dp, ZYNQMP_DP_MAIN_STREAM_ENABLE, 1); - mutex_unlock(&dp->lock); } static void zynqmp_dp_bridge_atomic_disable(struct drm_bridge *bridge, diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.h b/drivers/gpu/drm/xlnx/zynqmp_dpsub.h index 49875529c2a4..d771b8b199e0 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.h +++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.h @@ -60,6 +60,7 @@ struct zynqmp_dpsub_audio; * @layers: Video and graphics layers * @dp: The DisplayPort controller * @dma_align: DMA alignment constraint (must be a power of 2) + * @audio: DP audio data */ struct zynqmp_dpsub { struct device *dev; diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 4d2a89d65b65..b53eb569bd49 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -787,7 +787,7 @@ config HID_NINTENDO Adds support for the Nintendo Switch Joy-Cons, NSO, Pro Controller. All controllers support bluetooth, and the Pro Controller also supports its USB mode. This also includes support for the Nintendo Switch Online - Controllers which include the Genesis, SNES, and N64 controllers. + Controllers which include the NES, Genesis, SNES, and N64 controllers. To compile this driver as a module, choose M here: the module will be called hid-nintendo. @@ -1386,4 +1386,6 @@ source "drivers/hid/amd-sfh-hid/Kconfig" source "drivers/hid/surface-hid/Kconfig" +source "drivers/hid/intel-thc-hid/Kconfig" + endif # HID_SUPPORT diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile index 24de45f3677d..482b096eea28 100644 --- a/drivers/hid/Makefile +++ b/drivers/hid/Makefile @@ -171,3 +171,5 @@ obj-$(INTEL_ISH_FIRMWARE_DOWNLOADER) += intel-ish-hid/ obj-$(CONFIG_AMD_SFH_HID) += amd-sfh-hid/ obj-$(CONFIG_SURFACE_HID_CORE) += surface-hid/ + +obj-$(CONFIG_INTEL_THC_HID) += intel-thc-hid/ diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_common.h b/drivers/hid/amd-sfh-hid/amd_sfh_common.h index e5620d7db569..799b8686a88a 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_common.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_common.h @@ -43,6 +43,7 @@ struct amd_mp2_sensor_info { struct sfh_dev_status { bool is_hpd_present; bool is_als_present; + bool is_sra_present; }; struct amd_mp2_dev { diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index 0c28ca349bcd..48cfd0c58241 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -122,7 +122,7 @@ int amd_sfh_irq_init_v2(struct amd_mp2_dev *privdata) { int rc; - pci_intx(privdata->pdev, true); + pcim_intx(privdata->pdev, true); rc = devm_request_irq(&privdata->pdev->dev, privdata->pdev->irq, amd_sfh_irq_handler, 0, DRIVER_NAME, privdata); @@ -248,7 +248,7 @@ static void amd_mp2_pci_remove(void *privdata) struct amd_mp2_dev *mp2 = privdata; amd_sfh_hid_client_deinit(privdata); mp2->mp2_ops->stop_all(mp2); - pci_intx(mp2->pdev, false); + pcim_intx(mp2->pdev, false); amd_sfh_clear_intr(mp2); } diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c index db36d87d5634..e9929c4aa72e 100644 --- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c +++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c @@ -30,6 +30,7 @@ static int amd_sfh_get_sensor_num(struct amd_mp2_dev *mp2, u8 *sensor_id) case ACCEL_IDX: case GYRO_IDX: case MAG_IDX: + case SRA_IDX: case ALS_IDX: case HPD_IDX: if (BIT(i) & slist->sl.sensors) @@ -58,6 +59,8 @@ static const char *get_sensor_name(int idx) return "gyroscope"; case MAG_IDX: return "magnetometer"; + case SRA_IDX: + return "SRA"; case ALS_IDX: return "ALS"; case HPD_IDX: @@ -130,6 +133,23 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata) for (i = 0; i < cl_data->num_hid_devices; i++) { cl_data->sensor_sts[i] = SENSOR_DISABLED; + + if (cl_data->num_hid_devices == 1 && cl_data->sensor_idx[0] == SRA_IDX) + break; + + if (cl_data->sensor_idx[i] == SRA_IDX) { + info.sensor_idx = cl_data->sensor_idx[i]; + writel(0, privdata->mmio + amd_get_p2c_val(privdata, 0)); + mp2_ops->start(privdata, info); + status = amd_sfh_wait_for_response + (privdata, cl_data->sensor_idx[i], ENABLE_SENSOR); + + cl_data->sensor_sts[i] = (status == 0) ? SENSOR_ENABLED : SENSOR_DISABLED; + if (cl_data->sensor_sts[i] == SENSOR_ENABLED) + privdata->dev_en.is_sra_present = true; + continue; + } + cl_data->sensor_requested_cnt[i] = 0; cl_data->cur_hid_dev = i; cl_idx = cl_data->sensor_idx[i]; @@ -181,6 +201,8 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata) } for (i = 0; i < cl_data->num_hid_devices; i++) { + if (cl_data->sensor_idx[i] == SRA_IDX) + continue; cl_data->cur_hid_dev = i; if (cl_data->sensor_sts[i] == SENSOR_ENABLED) { cl_data->is_any_sensor_enabled = true; @@ -289,7 +311,7 @@ static void amd_mp2_pci_remove(void *privdata) sfh_deinit_emp2(); amd_sfh_hid_client_deinit(privdata); mp2->mp2_ops->stop_all(mp2); - pci_intx(mp2->pdev, false); + pcim_intx(mp2->pdev, false); amd_sfh_clear_intr(mp2); } diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c index 4676f060da26..ffb98b4c36cb 100644 --- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c +++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c @@ -87,6 +87,41 @@ void sfh_interface_init(struct amd_mp2_dev *mp2) emp2 = mp2; } +static int amd_sfh_mode_info(u32 *platform_type, u32 *laptop_placement) +{ + struct sfh_op_mode mode; + + if (!platform_type || !laptop_placement) + return -EINVAL; + + if (!emp2 || !emp2->dev_en.is_sra_present) + return -ENODEV; + + mode.val = readl(emp2->mmio + amd_get_c2p_val(emp2, 3)); + + *platform_type = mode.op_mode.devicemode; + + if (mode.op_mode.ontablestate == 1) { + *laptop_placement = ON_TABLE; + } else if (mode.op_mode.ontablestate == 2) { + *laptop_placement = ON_LAP_MOTION; + } else if (mode.op_mode.inbagstate == 1) { + *laptop_placement = IN_BAG; + } else if (mode.op_mode.outbagstate == 1) { + *laptop_placement = OUT_OF_BAG; + } else if (mode.op_mode.ontablestate == 0 || mode.op_mode.inbagstate == 0 || + mode.op_mode.outbagstate == 0) { + *laptop_placement = LP_UNKNOWN; + pr_warn_once("Unknown laptop placement\n"); + } else if (mode.op_mode.ontablestate == 3 || mode.op_mode.inbagstate == 3 || + mode.op_mode.outbagstate == 3) { + *laptop_placement = LP_UNDEFINED; + pr_warn_once("Undefined laptop placement\n"); + } + + return 0; +} + static int amd_sfh_hpd_info(u8 *user_present) { struct hpd_status hpdstatus; @@ -131,6 +166,9 @@ int amd_get_sfh_info(struct amd_sfh_info *sfh_info, enum sfh_message_type op) return amd_sfh_hpd_info(&sfh_info->user_present); case MT_ALS: return amd_sfh_als_info(&sfh_info->ambient_light); + case MT_SRA: + return amd_sfh_mode_info(&sfh_info->platform_type, + &sfh_info->laptop_placement); } } return -EINVAL; diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.h b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.h index 2c211d28764d..665c99ad779f 100644 --- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.h +++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.h @@ -22,8 +22,9 @@ enum sensor_index { ACCEL_IDX, GYRO_IDX, MAG_IDX, - ALS_IDX = 4, - HPD_IDX = 5, + SRA_IDX, + ALS_IDX, + HPD_IDX, MAX_IDX = 15, }; @@ -164,6 +165,25 @@ struct hpd_status { }; }; +struct sfh_op_mode { + union { + u32 val; + struct { + u32 mode : 3; + u32 lidstatus : 1; + u32 angle : 10; + u32 inbagstatedbg : 2; + u32 ontablestate : 2; + u32 inbagstate : 2; + u32 outbagstate : 2; + u32 inbagmlcstate : 1; + u32 powerstate : 2; + u32 data : 3; + u32 devicemode : 4; + } op_mode; + }; +}; + void sfh_interface_init(struct amd_mp2_dev *mp2); void sfh_deinit_emp2(void); void amd_sfh1_1_set_desc_ops(struct amd_mp2_ops *mp2_ops); diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 506c6f377e7d..46e3e42f9eb5 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -432,6 +432,26 @@ static int asus_kbd_get_functions(struct hid_device *hdev, return ret; } +static int asus_kbd_disable_oobe(struct hid_device *hdev) +{ + const u8 init[][6] = { + { FEATURE_KBD_REPORT_ID, 0x05, 0x20, 0x31, 0x00, 0x08 }, + { FEATURE_KBD_REPORT_ID, 0xBA, 0xC5, 0xC4 }, + { FEATURE_KBD_REPORT_ID, 0xD0, 0x8F, 0x01 }, + { FEATURE_KBD_REPORT_ID, 0xD0, 0x85, 0xFF } + }; + int ret; + + for (size_t i = 0; i < ARRAY_SIZE(init); i++) { + ret = asus_kbd_set_report(hdev, init[i], sizeof(init[i])); + if (ret < 0) + return ret; + } + + hid_info(hdev, "Disabled OOBE for keyboard\n"); + return 0; +} + static void asus_schedule_work(struct asus_kbd_leds *led) { unsigned long flags; @@ -534,6 +554,12 @@ static int asus_kbd_register_leds(struct hid_device *hdev) ret = asus_kbd_init(hdev, FEATURE_KBD_LED_REPORT_ID2); if (ret < 0) return ret; + + if (dmi_match(DMI_PRODUCT_FAMILY, "ProArt P16")) { + ret = asus_kbd_disable_oobe(hdev); + if (ret < 0) + return ret; + } } else { /* Initialize keyboard */ ret = asus_kbd_init(hdev, FEATURE_KBD_REPORT_ID); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 33a191973324..4497b50799db 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1163,6 +1163,8 @@ static void hid_apply_multiplier(struct hid_device *hid, while (multiplier_collection->parent_idx != -1 && multiplier_collection->type != HID_COLLECTION_LOGICAL) multiplier_collection = &hid->collection[multiplier_collection->parent_idx]; + if (multiplier_collection->type != HID_COLLECTION_LOGICAL) + multiplier_collection = NULL; effective_multiplier = hid_calculate_multiplier(hid, multiplier); @@ -2174,9 +2176,9 @@ static bool hid_hiddev(struct hid_device *hdev) static ssize_t -read_report_descriptor(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +report_descriptor_read(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); struct hid_device *hdev = to_hid_device(dev); @@ -2193,24 +2195,17 @@ read_report_descriptor(struct file *filp, struct kobject *kobj, } static ssize_t -show_country(struct device *dev, struct device_attribute *attr, - char *buf) +country_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct hid_device *hdev = to_hid_device(dev); return sprintf(buf, "%02x\n", hdev->country & 0xff); } -static struct bin_attribute dev_bin_attr_report_desc = { - .attr = { .name = "report_descriptor", .mode = 0444 }, - .read = read_report_descriptor, - .size = HID_MAX_DESCRIPTOR_SIZE, -}; +static const BIN_ATTR_RO(report_descriptor, HID_MAX_DESCRIPTOR_SIZE); -static const struct device_attribute dev_attr_country = { - .attr = { .name = "country", .mode = 0444 }, - .show = show_country, -}; +static const DEVICE_ATTR_RO(country); int hid_connect(struct hid_device *hdev, unsigned int connect_mask) { @@ -2800,13 +2795,13 @@ static struct attribute *hid_dev_attrs[] = { &dev_attr_modalias.attr, NULL, }; -static struct bin_attribute *hid_dev_bin_attrs[] = { - &dev_bin_attr_report_desc, +static const struct bin_attribute *hid_dev_bin_attrs[] = { + &bin_attr_report_descriptor, NULL }; static const struct attribute_group hid_dev_group = { .attrs = hid_dev_attrs, - .bin_attrs = hid_dev_bin_attrs, + .bin_attrs_new = hid_dev_bin_attrs, }; __ATTRIBUTE_GROUPS(hid_dev); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 1f47fda809b9..c448de53bf91 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -506,7 +506,6 @@ #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100 #define I2C_VENDOR_ID_GOODIX 0x27c6 -#define I2C_DEVICE_ID_GOODIX_01E0 0x01e0 #define I2C_DEVICE_ID_GOODIX_01E8 0x01e8 #define I2C_DEVICE_ID_GOODIX_01E9 0x01e9 #define I2C_DEVICE_ID_GOODIX_01F0 0x01f0 @@ -1089,6 +1088,8 @@ #define USB_VENDOR_ID_PRODIGE 0x05af #define USB_DEVICE_ID_PRODIGE_CORDLESS 0x3062 +#define I2C_VENDOR_ID_QTEC 0x6243 + #define USB_VENDOR_ID_QUANTA 0x0408 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH 0x3000 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3001 0x3001 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index fda9dce3da99..9d80635a91eb 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -810,10 +810,23 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel break; } - if ((usage->hid & 0xf0) == 0x90) { /* SystemControl*/ - switch (usage->hid & 0xf) { - case 0xb: map_key_clear(KEY_DO_NOT_DISTURB); break; - default: goto ignore; + if ((usage->hid & 0xf0) == 0x90) { /* SystemControl & D-pad */ + switch (usage->hid) { + case HID_GD_UP: usage->hat_dir = 1; break; + case HID_GD_DOWN: usage->hat_dir = 5; break; + case HID_GD_RIGHT: usage->hat_dir = 3; break; + case HID_GD_LEFT: usage->hat_dir = 7; break; + case HID_GD_DO_NOT_DISTURB: + map_key_clear(KEY_DO_NOT_DISTURB); break; + default: goto unknown; + } + + if (usage->hid <= HID_GD_LEFT) { + if (field->dpad) { + map_abs(field->dpad); + goto ignore; + } + map_abs(ABS_HAT0X); } break; } @@ -844,22 +857,6 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel if (field->application == HID_GD_SYSTEM_CONTROL) goto ignore; - if ((usage->hid & 0xf0) == 0x90) { /* D-pad */ - switch (usage->hid) { - case HID_GD_UP: usage->hat_dir = 1; break; - case HID_GD_DOWN: usage->hat_dir = 5; break; - case HID_GD_RIGHT: usage->hat_dir = 3; break; - case HID_GD_LEFT: usage->hat_dir = 7; break; - default: goto unknown; - } - if (field->dpad) { - map_abs(field->dpad); - goto ignore; - } - map_abs(ABS_HAT0X); - break; - } - switch (usage->hid) { /* These usage IDs map directly to the usage codes. */ case HID_GD_X: case HID_GD_Y: case HID_GD_Z: diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index f66194fde891..4d00bc4d656e 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -32,11 +32,22 @@ #include #include +#if IS_ENABLED(CONFIG_ACPI_PLATFORM_PROFILE) +#include +#endif /* CONFIG_ACPI_PLATFORM_PROFILE */ + #include "hid-ids.h" /* Userspace expects F20 for mic-mute KEY_MICMUTE does not work */ #define LENOVO_KEY_MICMUTE KEY_F20 +/* HID raw events for ThinkPad X12 Tabs*/ +#define TP_X12_RAW_HOTKEY_FN_F4 0x00020003 +#define TP_X12_RAW_HOTKEY_FN_F8 0x38001003 +#define TP_X12_RAW_HOTKEY_FN_F10 0x00000803 +#define TP_X12_RAW_HOTKEY_FN_F12 0x00000403 +#define TP_X12_RAW_HOTKEY_FN_SPACE 0x18001003 + struct lenovo_drvdata { u8 led_report[3]; /* Must be first for proper alignment */ int led_state; @@ -71,6 +82,14 @@ struct lenovo_drvdata { #define TP10UBKBD_LED_OFF 1 #define TP10UBKBD_LED_ON 2 +/* Function to report raw_events as key events*/ +static inline void report_key_event(struct input_dev *input, int keycode) +{ + input_report_key(input, keycode, 1); + input_report_key(input, keycode, 0); + input_sync(input); +} + static int lenovo_led_set_tp10ubkbd(struct hid_device *hdev, u8 led_code, enum led_brightness value) { @@ -472,6 +491,8 @@ static int lenovo_input_mapping(struct hid_device *hdev, case USB_DEVICE_ID_LENOVO_TP10UBKBD: return lenovo_input_mapping_tp10_ultrabook_kbd(hdev, hi, field, usage, bit, max); + case USB_DEVICE_ID_LENOVO_X12_TAB: + case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB: case USB_DEVICE_ID_LENOVO_X1_TAB3: return lenovo_input_mapping_x1_tab_kbd(hdev, hi, field, usage, bit, max); @@ -582,6 +603,8 @@ static ssize_t attr_fn_lock_store(struct device *dev, case USB_DEVICE_ID_LENOVO_TPIIBTKBD: lenovo_features_set_cptkbd(hdev); break; + case USB_DEVICE_ID_LENOVO_X12_TAB: + case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: case USB_DEVICE_ID_LENOVO_X1_TAB3: @@ -680,6 +703,62 @@ static const struct attribute_group lenovo_attr_group_cptkbd = { .attrs = lenovo_attributes_cptkbd, }; +/* Function to handle Lenovo Thinkpad TAB X12's HID raw inputs for fn keys*/ +static int lenovo_raw_event_TP_X12_tab(struct hid_device *hdev, u32 raw_data) +{ + struct hid_input *hidinput; + struct input_dev *input = NULL; + + /* Iterate through all associated input devices */ + list_for_each_entry(hidinput, &hdev->inputs, list) { + input = hidinput->input; + if (!input) + continue; + + switch (raw_data) { + /* fn-F20 being used here for MIC mute*/ + case TP_X12_RAW_HOTKEY_FN_F4: + report_key_event(input, LENOVO_KEY_MICMUTE); + return 1; + /* Power-mode or Airplane mode will be called based on the device*/ + case TP_X12_RAW_HOTKEY_FN_F8: + /* + * TP X12 TAB uses Fn-F8 calls Airplanemode + * Whereas TP X12 TAB2 uses Fn-F8 for toggling + * Power modes + */ + if (hdev->product == USB_DEVICE_ID_LENOVO_X12_TAB) { + report_key_event(input, KEY_RFKILL); + return 1; + } +#if IS_ENABLED(CONFIG_ACPI_PLATFORM_PROFILE) + else { + platform_profile_cycle(); + return 1; + } +#endif /* CONFIG_ACPI_PLATFORM_PROFILE */ + return 0; + case TP_X12_RAW_HOTKEY_FN_F10: + /* TAB1 has PICKUP Phone and TAB2 use Snipping tool*/ + (hdev->product == USB_DEVICE_ID_LENOVO_X12_TAB) ? + report_key_event(input, KEY_PICKUP_PHONE) : + report_key_event(input, KEY_SELECTIVE_SCREENSHOT); + return 1; + case TP_X12_RAW_HOTKEY_FN_F12: + /* BookMarks/STAR key*/ + report_key_event(input, KEY_BOOKMARKS); + return 1; + case TP_X12_RAW_HOTKEY_FN_SPACE: + /* Keyboard LED backlight toggle*/ + report_key_event(input, KEY_KBDILLUMTOGGLE); + return 1; + default: + break; + } + } + return 0; +} + static int lenovo_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { @@ -697,6 +776,15 @@ static int lenovo_raw_event(struct hid_device *hdev, data[2] = 0x01; } + /* + * Lenovo TP X12 Tab KBD's Fn+XX is HID raw data defined. Report ID is 0x03 + * e.g.: Raw data received for MIC mute is 0x00020003. + */ + if (unlikely((hdev->product == USB_DEVICE_ID_LENOVO_X12_TAB + || hdev->product == USB_DEVICE_ID_LENOVO_X12_TAB2) + && size >= 3 && report->id == 0x03)) + return lenovo_raw_event_TP_X12_tab(hdev, le32_to_cpu(*(u32 *)data)); + return 0; } @@ -776,6 +864,8 @@ static int lenovo_event(struct hid_device *hdev, struct hid_field *field, case USB_DEVICE_ID_LENOVO_TPIIUSBKBD: case USB_DEVICE_ID_LENOVO_TPIIBTKBD: return lenovo_event_cptkbd(hdev, field, usage, value); + case USB_DEVICE_ID_LENOVO_X12_TAB: + case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: case USB_DEVICE_ID_LENOVO_X1_TAB3: @@ -1057,6 +1147,8 @@ static int lenovo_led_brightness_set(struct led_classdev *led_cdev, case USB_DEVICE_ID_LENOVO_TPKBD: lenovo_led_set_tpkbd(hdev); break; + case USB_DEVICE_ID_LENOVO_X12_TAB: + case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: case USB_DEVICE_ID_LENOVO_X1_TAB3: @@ -1243,8 +1335,15 @@ static int lenovo_probe_tp10ubkbd(struct hid_device *hdev) * We cannot read the state, only set it, so we force it to on here * (which should be a no-op) to make sure that our state matches the * keyboard's FN-lock state. This is the same as what Windows does. + * + * For X12 TAB and TAB2, the default windows behaviour Fn-lock Off. + * Adding additional check to ensure the behaviour in case of + * Thinkpad X12 Tabs. */ - data->fn_lock = true; + + data->fn_lock = !(hdev->product == USB_DEVICE_ID_LENOVO_X12_TAB || + hdev->product == USB_DEVICE_ID_LENOVO_X12_TAB2); + lenovo_led_set_tp10ubkbd(hdev, TP10UBKBD_FN_LOCK_LED, data->fn_lock); ret = sysfs_create_group(&hdev->dev.kobj, &lenovo_attr_group_tp10ubkbd); @@ -1288,6 +1387,8 @@ static int lenovo_probe(struct hid_device *hdev, case USB_DEVICE_ID_LENOVO_TPIIBTKBD: ret = lenovo_probe_cptkbd(hdev); break; + case USB_DEVICE_ID_LENOVO_X12_TAB: + case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: case USB_DEVICE_ID_LENOVO_X1_TAB3: @@ -1375,6 +1476,8 @@ static void lenovo_remove(struct hid_device *hdev) case USB_DEVICE_ID_LENOVO_TPIIBTKBD: lenovo_remove_cptkbd(hdev); break; + case USB_DEVICE_ID_LENOVO_X12_TAB: + case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: case USB_DEVICE_ID_LENOVO_X1_TAB3: @@ -1429,6 +1532,10 @@ static const struct hid_device_id lenovo_devices[] = { USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB3) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X12_TAB) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X12_TAB2) }, { } }; diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index ec110dea8772..a76f17158539 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -52,6 +52,7 @@ module_param(report_undeciphered, bool, 0644); MODULE_PARM_DESC(report_undeciphered, "Report undeciphered multi-touch state field using a MSC_RAW event"); #define TRACKPAD2_2021_BT_VERSION 0x110 +#define TRACKPAD_2024_BT_VERSION 0x314 #define TRACKPAD_REPORT_ID 0x28 #define TRACKPAD2_USB_REPORT_ID 0x02 @@ -567,9 +568,12 @@ static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hd */ if (hdev->vendor == BT_VENDOR_ID_APPLE) { if (input->id.version == TRACKPAD2_2021_BT_VERSION) + input->name = "Apple Inc. Magic Trackpad 2021"; + else if (input->id.version == TRACKPAD_2024_BT_VERSION) { + input->name = "Apple Inc. Magic Trackpad USB-C"; + } else { input->name = "Apple Inc. Magic Trackpad"; - else - input->name = "Apple Inc. Magic Trackpad 2"; + } } else { /* USB_VENDOR_ID_APPLE */ input->name = hdev->name; } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 785743036647..82900857bfd8 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1460,8 +1460,7 @@ static const __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc, { if (hdev->vendor == I2C_VENDOR_ID_GOODIX && (hdev->product == I2C_DEVICE_ID_GOODIX_01E8 || - hdev->product == I2C_DEVICE_ID_GOODIX_01E9 || - hdev->product == I2C_DEVICE_ID_GOODIX_01E0)) { + hdev->product == I2C_DEVICE_ID_GOODIX_01E9)) { if (rdesc[607] == 0x15) { rdesc[607] = 0x25; dev_info( @@ -2086,9 +2085,6 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU, HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX, I2C_DEVICE_ID_GOODIX_01E9) }, - { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU, - HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX, - I2C_DEVICE_ID_GOODIX_01E0) }, /* GoodTouch panels */ { .driver_data = MT_CLS_NSMU, @@ -2318,6 +2314,11 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(HID_BUS_ANY, HID_GROUP_ANY, USB_VENDOR_ID_SIS_TOUCH, HID_ANY_ID) }, + /* Hantick */ + { .driver_data = MT_CLS_NSMU, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288) }, + /* Generic MT device */ { HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH, HID_ANY_ID, HID_ANY_ID) }, diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index 55153a2f7988..11ac246176ae 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -456,14 +456,13 @@ static const struct joycon_ctlr_button_mapping snescon_button_mappings[] = { { /* sentinel */ }, }; -/* - * "A", "B", and "C" are mapped positionally, rather than by label (e.g., "A" - * gets assigned to BTN_EAST instead of BTN_A). - */ static const struct joycon_ctlr_button_mapping gencon_button_mappings[] = { - { BTN_SOUTH, JC_BTN_A, }, - { BTN_EAST, JC_BTN_B, }, - { BTN_WEST, JC_BTN_R, }, + { BTN_A, JC_BTN_A, }, + { BTN_B, JC_BTN_B, }, + { BTN_C, JC_BTN_R, }, + { BTN_X, JC_BTN_X, }, /* MD/GEN 6B Only */ + { BTN_Y, JC_BTN_Y, }, /* MD/GEN 6B Only */ + { BTN_Z, JC_BTN_L, }, /* MD/GEN 6B Only */ { BTN_SELECT, JC_BTN_ZR, }, { BTN_START, JC_BTN_PLUS, }, { BTN_MODE, JC_BTN_HOME, }, @@ -471,9 +470,6 @@ static const struct joycon_ctlr_button_mapping gencon_button_mappings[] = { { /* sentinel */ }, }; -/* - * N64's C buttons get assigned to d-pad directions and registered as buttons. - */ static const struct joycon_ctlr_button_mapping n64con_button_mappings[] = { { BTN_A, JC_BTN_A, }, { BTN_B, JC_BTN_B, }, diff --git a/drivers/hid/hid-roccat-arvo.c b/drivers/hid/hid-roccat-arvo.c index d55aaabab1ed..3048297569c5 100644 --- a/drivers/hid/hid-roccat-arvo.c +++ b/drivers/hid/hid-roccat-arvo.c @@ -224,24 +224,24 @@ static ssize_t arvo_sysfs_read(struct file *fp, } static ssize_t arvo_sysfs_write_button(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, char *buf, - loff_t off, size_t count) + struct kobject *kobj, const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { return arvo_sysfs_write(fp, kobj, buf, off, count, sizeof(struct arvo_button), ARVO_COMMAND_BUTTON); } -static BIN_ATTR(button, 0220, NULL, arvo_sysfs_write_button, - sizeof(struct arvo_button)); +static const BIN_ATTR(button, 0220, NULL, arvo_sysfs_write_button, + sizeof(struct arvo_button)); static ssize_t arvo_sysfs_read_info(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, char *buf, - loff_t off, size_t count) + struct kobject *kobj, const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { return arvo_sysfs_read(fp, kobj, buf, off, count, sizeof(struct arvo_info), ARVO_COMMAND_INFO); } -static BIN_ATTR(info, 0440, arvo_sysfs_read_info, NULL, - sizeof(struct arvo_info)); +static const BIN_ATTR(info, 0440, arvo_sysfs_read_info, NULL, + sizeof(struct arvo_info)); static struct attribute *arvo_attrs[] = { &dev_attr_mode_key.attr, @@ -250,7 +250,7 @@ static struct attribute *arvo_attrs[] = { NULL, }; -static struct bin_attribute *arvo_bin_attributes[] = { +static const struct bin_attribute *const arvo_bin_attributes[] = { &bin_attr_button, &bin_attr_info, NULL, @@ -258,7 +258,7 @@ static struct bin_attribute *arvo_bin_attributes[] = { static const struct attribute_group arvo_group = { .attrs = arvo_attrs, - .bin_attrs = arvo_bin_attributes, + .bin_attrs_new = arvo_bin_attributes, }; static const struct attribute_group *arvo_groups[] = { diff --git a/drivers/hid/hid-roccat-common.h b/drivers/hid/hid-roccat-common.h index 839ddfd931f0..0f9a2db04df9 100644 --- a/drivers/hid/hid-roccat-common.h +++ b/drivers/hid/hid-roccat-common.h @@ -46,8 +46,8 @@ ssize_t roccat_common2_sysfs_write(struct file *fp, struct kobject *kobj, #define ROCCAT_COMMON2_SYSFS_W(thingy, COMMAND, SIZE) \ static ssize_t roccat_common2_sysfs_write_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, char *buf, \ - loff_t off, size_t count) \ + struct kobject *kobj, const struct bin_attribute *attr, \ + char *buf, loff_t off, size_t count) \ { \ return roccat_common2_sysfs_write(fp, kobj, buf, off, count, \ SIZE, COMMAND); \ @@ -55,8 +55,8 @@ static ssize_t roccat_common2_sysfs_write_ ## thingy(struct file *fp, \ #define ROCCAT_COMMON2_SYSFS_R(thingy, COMMAND, SIZE) \ static ssize_t roccat_common2_sysfs_read_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, char *buf, \ - loff_t off, size_t count) \ + struct kobject *kobj, const struct bin_attribute *attr, \ + char *buf, loff_t off, size_t count) \ { \ return roccat_common2_sysfs_read(fp, kobj, buf, off, count, \ SIZE, COMMAND); \ @@ -68,27 +68,27 @@ ROCCAT_COMMON2_SYSFS_R(thingy, COMMAND, SIZE) #define ROCCAT_COMMON2_BIN_ATTRIBUTE_RW(thingy, COMMAND, SIZE) \ ROCCAT_COMMON2_SYSFS_RW(thingy, COMMAND, SIZE); \ -static struct bin_attribute bin_attr_ ## thingy = { \ +static const struct bin_attribute bin_attr_ ## thingy = { \ .attr = { .name = #thingy, .mode = 0660 }, \ .size = SIZE, \ - .read = roccat_common2_sysfs_read_ ## thingy, \ - .write = roccat_common2_sysfs_write_ ## thingy \ + .read_new = roccat_common2_sysfs_read_ ## thingy, \ + .write_new = roccat_common2_sysfs_write_ ## thingy \ } #define ROCCAT_COMMON2_BIN_ATTRIBUTE_R(thingy, COMMAND, SIZE) \ ROCCAT_COMMON2_SYSFS_R(thingy, COMMAND, SIZE); \ -static struct bin_attribute bin_attr_ ## thingy = { \ +static const struct bin_attribute bin_attr_ ## thingy = { \ .attr = { .name = #thingy, .mode = 0440 }, \ .size = SIZE, \ - .read = roccat_common2_sysfs_read_ ## thingy, \ + .read_new = roccat_common2_sysfs_read_ ## thingy, \ } #define ROCCAT_COMMON2_BIN_ATTRIBUTE_W(thingy, COMMAND, SIZE) \ ROCCAT_COMMON2_SYSFS_W(thingy, COMMAND, SIZE); \ -static struct bin_attribute bin_attr_ ## thingy = { \ +static const struct bin_attribute bin_attr_ ## thingy = { \ .attr = { .name = #thingy, .mode = 0220 }, \ .size = SIZE, \ - .write = roccat_common2_sysfs_write_ ## thingy \ + .write_new = roccat_common2_sysfs_write_ ## thingy \ } #endif diff --git a/drivers/hid/hid-roccat-isku.c b/drivers/hid/hid-roccat-isku.c index 0cd6208fb371..65a84bfcc2f8 100644 --- a/drivers/hid/hid-roccat-isku.c +++ b/drivers/hid/hid-roccat-isku.c @@ -156,7 +156,7 @@ static ssize_t isku_sysfs_write(struct file *fp, struct kobject *kobj, #define ISKU_SYSFS_W(thingy, THINGY) \ static ssize_t isku_sysfs_write_ ## thingy(struct file *fp, struct kobject *kobj, \ - struct bin_attribute *attr, char *buf, \ + const struct bin_attribute *attr, char *buf, \ loff_t off, size_t count) \ { \ return isku_sysfs_write(fp, kobj, buf, off, count, \ @@ -165,7 +165,7 @@ static ssize_t isku_sysfs_write_ ## thingy(struct file *fp, struct kobject *kobj #define ISKU_SYSFS_R(thingy, THINGY) \ static ssize_t isku_sysfs_read_ ## thingy(struct file *fp, struct kobject *kobj, \ - struct bin_attribute *attr, char *buf, \ + const struct bin_attribute *attr, char *buf, \ loff_t off, size_t count) \ { \ return isku_sysfs_read(fp, kobj, buf, off, count, \ @@ -178,27 +178,27 @@ ISKU_SYSFS_W(thingy, THINGY) #define ISKU_BIN_ATTR_RW(thingy, THINGY) \ ISKU_SYSFS_RW(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0660 }, \ .size = ISKU_SIZE_ ## THINGY, \ - .read = isku_sysfs_read_ ## thingy, \ - .write = isku_sysfs_write_ ## thingy \ + .read_new = isku_sysfs_read_ ## thingy, \ + .write_new = isku_sysfs_write_ ## thingy \ } #define ISKU_BIN_ATTR_R(thingy, THINGY) \ ISKU_SYSFS_R(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0440 }, \ .size = ISKU_SIZE_ ## THINGY, \ - .read = isku_sysfs_read_ ## thingy, \ + .read_new = isku_sysfs_read_ ## thingy, \ } #define ISKU_BIN_ATTR_W(thingy, THINGY) \ ISKU_SYSFS_W(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0220 }, \ .size = ISKU_SIZE_ ## THINGY, \ - .write = isku_sysfs_write_ ## thingy \ + .write_new = isku_sysfs_write_ ## thingy \ } ISKU_BIN_ATTR_RW(macro, MACRO); @@ -217,7 +217,7 @@ ISKU_BIN_ATTR_W(control, CONTROL); ISKU_BIN_ATTR_W(reset, RESET); ISKU_BIN_ATTR_R(info, INFO); -static struct bin_attribute *isku_bin_attributes[] = { +static const struct bin_attribute *const isku_bin_attributes[] = { &bin_attr_macro, &bin_attr_keys_function, &bin_attr_keys_easyzone, @@ -238,7 +238,7 @@ static struct bin_attribute *isku_bin_attributes[] = { static const struct attribute_group isku_group = { .attrs = isku_attrs, - .bin_attrs = isku_bin_attributes, + .bin_attrs_new = isku_bin_attributes, }; static const struct attribute_group *isku_groups[] = { diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c index 3f8f459edcf3..b3c0242e5a37 100644 --- a/drivers/hid/hid-roccat-kone.c +++ b/drivers/hid/hid-roccat-kone.c @@ -261,7 +261,7 @@ static int kone_get_firmware_version(struct usb_device *usb_dev, int *result) } static ssize_t kone_sysfs_read_settings(struct file *fp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kone_device *kone = hid_get_drvdata(dev_get_drvdata(dev)); @@ -285,7 +285,7 @@ static ssize_t kone_sysfs_read_settings(struct file *fp, struct kobject *kobj, * case of error the old data is still valid */ static ssize_t kone_sysfs_write_settings(struct file *fp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kone_device *kone = hid_get_drvdata(dev_get_drvdata(dev)); @@ -327,11 +327,11 @@ unlock: return sizeof(struct kone_settings); } -static BIN_ATTR(settings, 0660, kone_sysfs_read_settings, - kone_sysfs_write_settings, sizeof(struct kone_settings)); +static const BIN_ATTR(settings, 0660, kone_sysfs_read_settings, + kone_sysfs_write_settings, sizeof(struct kone_settings)); static ssize_t kone_sysfs_read_profilex(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, + struct kobject *kobj, const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kone_device *kone = hid_get_drvdata(dev_get_drvdata(dev)); @@ -351,7 +351,7 @@ static ssize_t kone_sysfs_read_profilex(struct file *fp, /* Writes data only if different to stored data */ static ssize_t kone_sysfs_write_profilex(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, + struct kobject *kobj, const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kone_device *kone = hid_get_drvdata(dev_get_drvdata(dev)); @@ -382,11 +382,11 @@ static ssize_t kone_sysfs_write_profilex(struct file *fp, return sizeof(struct kone_profile); } #define PROFILE_ATTR(number) \ -static struct bin_attribute bin_attr_profile##number = { \ +static const struct bin_attribute bin_attr_profile##number = { \ .attr = { .name = "profile" #number, .mode = 0660 }, \ .size = sizeof(struct kone_profile), \ - .read = kone_sysfs_read_profilex, \ - .write = kone_sysfs_write_profilex, \ + .read_new = kone_sysfs_read_profilex, \ + .write_new = kone_sysfs_write_profilex, \ .private = &profile_numbers[number-1], \ } PROFILE_ATTR(1); @@ -634,7 +634,7 @@ static struct attribute *kone_attrs[] = { NULL, }; -static struct bin_attribute *kone_bin_attributes[] = { +static const struct bin_attribute *const kone_bin_attributes[] = { &bin_attr_settings, &bin_attr_profile1, &bin_attr_profile2, @@ -646,7 +646,7 @@ static struct bin_attribute *kone_bin_attributes[] = { static const struct attribute_group kone_group = { .attrs = kone_attrs, - .bin_attrs = kone_bin_attributes, + .bin_attrs_new = kone_bin_attributes, }; static const struct attribute_group *kone_groups[] = { diff --git a/drivers/hid/hid-roccat-koneplus.c b/drivers/hid/hid-roccat-koneplus.c index 8ccb3b14a1a9..5d8a5ce88b4c 100644 --- a/drivers/hid/hid-roccat-koneplus.c +++ b/drivers/hid/hid-roccat-koneplus.c @@ -128,8 +128,8 @@ static ssize_t koneplus_sysfs_write(struct file *fp, struct kobject *kobj, #define KONEPLUS_SYSFS_W(thingy, THINGY) \ static ssize_t koneplus_sysfs_write_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, char *buf, \ - loff_t off, size_t count) \ + struct kobject *kobj, const struct bin_attribute *attr, \ + char *buf, loff_t off, size_t count) \ { \ return koneplus_sysfs_write(fp, kobj, buf, off, count, \ KONEPLUS_SIZE_ ## THINGY, KONEPLUS_COMMAND_ ## THINGY); \ @@ -137,8 +137,8 @@ static ssize_t koneplus_sysfs_write_ ## thingy(struct file *fp, \ #define KONEPLUS_SYSFS_R(thingy, THINGY) \ static ssize_t koneplus_sysfs_read_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, char *buf, \ - loff_t off, size_t count) \ + struct kobject *kobj, const struct bin_attribute *attr, \ + char *buf, loff_t off, size_t count) \ { \ return koneplus_sysfs_read(fp, kobj, buf, off, count, \ KONEPLUS_SIZE_ ## THINGY, KONEPLUS_COMMAND_ ## THINGY); \ @@ -150,27 +150,27 @@ KONEPLUS_SYSFS_R(thingy, THINGY) #define KONEPLUS_BIN_ATTRIBUTE_RW(thingy, THINGY) \ KONEPLUS_SYSFS_RW(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0660 }, \ .size = KONEPLUS_SIZE_ ## THINGY, \ - .read = koneplus_sysfs_read_ ## thingy, \ - .write = koneplus_sysfs_write_ ## thingy \ + .read_new = koneplus_sysfs_read_ ## thingy, \ + .write_new = koneplus_sysfs_write_ ## thingy \ } #define KONEPLUS_BIN_ATTRIBUTE_R(thingy, THINGY) \ KONEPLUS_SYSFS_R(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0440 }, \ .size = KONEPLUS_SIZE_ ## THINGY, \ - .read = koneplus_sysfs_read_ ## thingy, \ + .read_new = koneplus_sysfs_read_ ## thingy, \ } #define KONEPLUS_BIN_ATTRIBUTE_W(thingy, THINGY) \ KONEPLUS_SYSFS_W(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0220 }, \ .size = KONEPLUS_SIZE_ ## THINGY, \ - .write = koneplus_sysfs_write_ ## thingy \ + .write_new = koneplus_sysfs_write_ ## thingy \ } KONEPLUS_BIN_ATTRIBUTE_W(control, CONTROL); KONEPLUS_BIN_ATTRIBUTE_W(talk, TALK); @@ -183,8 +183,8 @@ KONEPLUS_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS); KONEPLUS_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS); static ssize_t koneplus_sysfs_read_profilex_settings(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, char *buf, - loff_t off, size_t count) + struct kobject *kobj, const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); @@ -201,8 +201,8 @@ static ssize_t koneplus_sysfs_read_profilex_settings(struct file *fp, } static ssize_t koneplus_sysfs_read_profilex_buttons(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, char *buf, - loff_t off, size_t count) + struct kobject *kobj, const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); @@ -219,16 +219,16 @@ static ssize_t koneplus_sysfs_read_profilex_buttons(struct file *fp, } #define PROFILE_ATTR(number) \ -static struct bin_attribute bin_attr_profile##number##_settings = { \ +static const struct bin_attribute bin_attr_profile##number##_settings = { \ .attr = { .name = "profile" #number "_settings", .mode = 0440 }, \ .size = KONEPLUS_SIZE_PROFILE_SETTINGS, \ - .read = koneplus_sysfs_read_profilex_settings, \ + .read_new = koneplus_sysfs_read_profilex_settings, \ .private = &profile_numbers[number-1], \ }; \ -static struct bin_attribute bin_attr_profile##number##_buttons = { \ +static const struct bin_attribute bin_attr_profile##number##_buttons = { \ .attr = { .name = "profile" #number "_buttons", .mode = 0440 }, \ .size = KONEPLUS_SIZE_PROFILE_BUTTONS, \ - .read = koneplus_sysfs_read_profilex_buttons, \ + .read_new = koneplus_sysfs_read_profilex_buttons, \ .private = &profile_numbers[number-1], \ }; PROFILE_ATTR(1); @@ -321,7 +321,7 @@ static struct attribute *koneplus_attrs[] = { NULL, }; -static struct bin_attribute *koneplus_bin_attributes[] = { +static const struct bin_attribute *const koneplus_bin_attributes[] = { &bin_attr_control, &bin_attr_talk, &bin_attr_macro, @@ -346,7 +346,7 @@ static struct bin_attribute *koneplus_bin_attributes[] = { static const struct attribute_group koneplus_group = { .attrs = koneplus_attrs, - .bin_attrs = koneplus_bin_attributes, + .bin_attrs_new = koneplus_bin_attributes, }; static const struct attribute_group *koneplus_groups[] = { diff --git a/drivers/hid/hid-roccat-konepure.c b/drivers/hid/hid-roccat-konepure.c index beca8aef8bbb..7fb705789d4e 100644 --- a/drivers/hid/hid-roccat-konepure.c +++ b/drivers/hid/hid-roccat-konepure.c @@ -47,7 +47,7 @@ ROCCAT_COMMON2_BIN_ATTRIBUTE_R(tcu_image, 0x0c, 0x0404); ROCCAT_COMMON2_BIN_ATTRIBUTE_RW(sensor, 0x0f, 0x06); ROCCAT_COMMON2_BIN_ATTRIBUTE_W(talk, 0x10, 0x10); -static struct bin_attribute *konepure_bin_attrs[] = { +static const struct bin_attribute *const konepure_bin_attrs[] = { &bin_attr_actual_profile, &bin_attr_control, &bin_attr_info, @@ -62,7 +62,7 @@ static struct bin_attribute *konepure_bin_attrs[] = { }; static const struct attribute_group konepure_group = { - .bin_attrs = konepure_bin_attrs, + .bin_attrs_new = konepure_bin_attrs, }; static const struct attribute_group *konepure_groups[] = { diff --git a/drivers/hid/hid-roccat-kovaplus.c b/drivers/hid/hid-roccat-kovaplus.c index 748d4d7cb2fc..e31e4a2e62d5 100644 --- a/drivers/hid/hid-roccat-kovaplus.c +++ b/drivers/hid/hid-roccat-kovaplus.c @@ -171,8 +171,8 @@ static ssize_t kovaplus_sysfs_write(struct file *fp, struct kobject *kobj, #define KOVAPLUS_SYSFS_W(thingy, THINGY) \ static ssize_t kovaplus_sysfs_write_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, char *buf, \ - loff_t off, size_t count) \ + struct kobject *kobj, const struct bin_attribute *attr, \ + char *buf, loff_t off, size_t count) \ { \ return kovaplus_sysfs_write(fp, kobj, buf, off, count, \ KOVAPLUS_SIZE_ ## THINGY, KOVAPLUS_COMMAND_ ## THINGY); \ @@ -180,8 +180,8 @@ static ssize_t kovaplus_sysfs_write_ ## thingy(struct file *fp, \ #define KOVAPLUS_SYSFS_R(thingy, THINGY) \ static ssize_t kovaplus_sysfs_read_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, char *buf, \ - loff_t off, size_t count) \ + struct kobject *kobj, const struct bin_attribute *attr, \ + char *buf, loff_t off, size_t count) \ { \ return kovaplus_sysfs_read(fp, kobj, buf, off, count, \ KOVAPLUS_SIZE_ ## THINGY, KOVAPLUS_COMMAND_ ## THINGY); \ @@ -193,19 +193,19 @@ KOVAPLUS_SYSFS_R(thingy, THINGY) #define KOVAPLUS_BIN_ATTRIBUTE_RW(thingy, THINGY) \ KOVAPLUS_SYSFS_RW(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0660 }, \ .size = KOVAPLUS_SIZE_ ## THINGY, \ - .read = kovaplus_sysfs_read_ ## thingy, \ - .write = kovaplus_sysfs_write_ ## thingy \ + .read_new = kovaplus_sysfs_read_ ## thingy, \ + .write_new = kovaplus_sysfs_write_ ## thingy \ } #define KOVAPLUS_BIN_ATTRIBUTE_W(thingy, THINGY) \ KOVAPLUS_SYSFS_W(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0220 }, \ .size = KOVAPLUS_SIZE_ ## THINGY, \ - .write = kovaplus_sysfs_write_ ## thingy \ + .write_new = kovaplus_sysfs_write_ ## thingy \ } KOVAPLUS_BIN_ATTRIBUTE_W(control, CONTROL); KOVAPLUS_BIN_ATTRIBUTE_RW(info, INFO); @@ -213,8 +213,8 @@ KOVAPLUS_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS); KOVAPLUS_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS); static ssize_t kovaplus_sysfs_read_profilex_settings(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, char *buf, - loff_t off, size_t count) + struct kobject *kobj, const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); @@ -231,8 +231,8 @@ static ssize_t kovaplus_sysfs_read_profilex_settings(struct file *fp, } static ssize_t kovaplus_sysfs_read_profilex_buttons(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, char *buf, - loff_t off, size_t count) + struct kobject *kobj, const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); @@ -249,16 +249,16 @@ static ssize_t kovaplus_sysfs_read_profilex_buttons(struct file *fp, } #define PROFILE_ATTR(number) \ -static struct bin_attribute bin_attr_profile##number##_settings = { \ +static const struct bin_attribute bin_attr_profile##number##_settings = { \ .attr = { .name = "profile" #number "_settings", .mode = 0440 }, \ .size = KOVAPLUS_SIZE_PROFILE_SETTINGS, \ - .read = kovaplus_sysfs_read_profilex_settings, \ + .read_new = kovaplus_sysfs_read_profilex_settings, \ .private = &profile_numbers[number-1], \ }; \ -static struct bin_attribute bin_attr_profile##number##_buttons = { \ +static const struct bin_attribute bin_attr_profile##number##_buttons = { \ .attr = { .name = "profile" #number "_buttons", .mode = 0440 }, \ .size = KOVAPLUS_SIZE_PROFILE_BUTTONS, \ - .read = kovaplus_sysfs_read_profilex_buttons, \ + .read_new = kovaplus_sysfs_read_profilex_buttons, \ .private = &profile_numbers[number-1], \ }; PROFILE_ATTR(1); @@ -379,7 +379,7 @@ static struct attribute *kovaplus_attrs[] = { NULL, }; -static struct bin_attribute *kovaplus_bin_attributes[] = { +static const struct bin_attribute *const kovaplus_bin_attributes[] = { &bin_attr_control, &bin_attr_info, &bin_attr_profile_settings, @@ -399,7 +399,7 @@ static struct bin_attribute *kovaplus_bin_attributes[] = { static const struct attribute_group kovaplus_group = { .attrs = kovaplus_attrs, - .bin_attrs = kovaplus_bin_attributes, + .bin_attrs_new = kovaplus_bin_attributes, }; static const struct attribute_group *kovaplus_groups[] = { diff --git a/drivers/hid/hid-roccat-lua.c b/drivers/hid/hid-roccat-lua.c index d5ddf0d68346..023ec64b4b0e 100644 --- a/drivers/hid/hid-roccat-lua.c +++ b/drivers/hid/hid-roccat-lua.c @@ -66,7 +66,7 @@ static ssize_t lua_sysfs_write(struct file *fp, struct kobject *kobj, #define LUA_SYSFS_W(thingy, THINGY) \ static ssize_t lua_sysfs_write_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, \ + struct kobject *kobj, const struct bin_attribute *attr, \ char *buf, loff_t off, size_t count) \ { \ return lua_sysfs_write(fp, kobj, buf, off, count, \ @@ -75,7 +75,7 @@ static ssize_t lua_sysfs_write_ ## thingy(struct file *fp, \ #define LUA_SYSFS_R(thingy, THINGY) \ static ssize_t lua_sysfs_read_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, \ + struct kobject *kobj, const struct bin_attribute *attr, \ char *buf, loff_t off, size_t count) \ { \ return lua_sysfs_read(fp, kobj, buf, off, count, \ @@ -85,11 +85,11 @@ static ssize_t lua_sysfs_read_ ## thingy(struct file *fp, \ #define LUA_BIN_ATTRIBUTE_RW(thingy, THINGY) \ LUA_SYSFS_W(thingy, THINGY) \ LUA_SYSFS_R(thingy, THINGY) \ -static struct bin_attribute lua_ ## thingy ## _attr = { \ +static const struct bin_attribute lua_ ## thingy ## _attr = { \ .attr = { .name = #thingy, .mode = 0660 }, \ .size = LUA_SIZE_ ## THINGY, \ - .read = lua_sysfs_read_ ## thingy, \ - .write = lua_sysfs_write_ ## thingy \ + .read_new = lua_sysfs_read_ ## thingy, \ + .write_new = lua_sysfs_write_ ## thingy \ }; LUA_BIN_ATTRIBUTE_RW(control, CONTROL) diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c index eeb3d38cd805..2b53fbfbb897 100644 --- a/drivers/hid/hid-roccat-pyra.c +++ b/drivers/hid/hid-roccat-pyra.c @@ -129,8 +129,8 @@ static ssize_t pyra_sysfs_write(struct file *fp, struct kobject *kobj, #define PYRA_SYSFS_W(thingy, THINGY) \ static ssize_t pyra_sysfs_write_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, char *buf, \ - loff_t off, size_t count) \ + struct kobject *kobj, const struct bin_attribute *attr, \ + char *buf, loff_t off, size_t count) \ { \ return pyra_sysfs_write(fp, kobj, buf, off, count, \ PYRA_SIZE_ ## THINGY, PYRA_COMMAND_ ## THINGY); \ @@ -138,8 +138,8 @@ static ssize_t pyra_sysfs_write_ ## thingy(struct file *fp, \ #define PYRA_SYSFS_R(thingy, THINGY) \ static ssize_t pyra_sysfs_read_ ## thingy(struct file *fp, \ - struct kobject *kobj, struct bin_attribute *attr, char *buf, \ - loff_t off, size_t count) \ + struct kobject *kobj, const struct bin_attribute *attr, \ + char *buf, loff_t off, size_t count) \ { \ return pyra_sysfs_read(fp, kobj, buf, off, count, \ PYRA_SIZE_ ## THINGY, PYRA_COMMAND_ ## THINGY); \ @@ -151,27 +151,27 @@ PYRA_SYSFS_R(thingy, THINGY) #define PYRA_BIN_ATTRIBUTE_RW(thingy, THINGY) \ PYRA_SYSFS_RW(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0660 }, \ .size = PYRA_SIZE_ ## THINGY, \ - .read = pyra_sysfs_read_ ## thingy, \ - .write = pyra_sysfs_write_ ## thingy \ + .read_new = pyra_sysfs_read_ ## thingy, \ + .write_new = pyra_sysfs_write_ ## thingy \ } #define PYRA_BIN_ATTRIBUTE_R(thingy, THINGY) \ PYRA_SYSFS_R(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0440 }, \ - .size = PYRA_SIZE_ ## THINGY, \ - .read = pyra_sysfs_read_ ## thingy, \ + .size_new = PYRA_SIZE_ ## THINGY, \ + .read_new = pyra_sysfs_read_ ## thingy, \ } #define PYRA_BIN_ATTRIBUTE_W(thingy, THINGY) \ PYRA_SYSFS_W(thingy, THINGY); \ -static struct bin_attribute bin_attr_##thingy = { \ +static const struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0220 }, \ .size = PYRA_SIZE_ ## THINGY, \ - .write = pyra_sysfs_write_ ## thingy \ + .write_new = pyra_sysfs_write_ ## thingy \ } PYRA_BIN_ATTRIBUTE_W(control, CONTROL); @@ -180,8 +180,8 @@ PYRA_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS); PYRA_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS); static ssize_t pyra_sysfs_read_profilex_settings(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, char *buf, - loff_t off, size_t count) + struct kobject *kobj, const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); @@ -198,8 +198,8 @@ static ssize_t pyra_sysfs_read_profilex_settings(struct file *fp, } static ssize_t pyra_sysfs_read_profilex_buttons(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, char *buf, - loff_t off, size_t count) + struct kobject *kobj, const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); @@ -216,16 +216,16 @@ static ssize_t pyra_sysfs_read_profilex_buttons(struct file *fp, } #define PROFILE_ATTR(number) \ -static struct bin_attribute bin_attr_profile##number##_settings = { \ +static const struct bin_attribute bin_attr_profile##number##_settings = { \ .attr = { .name = "profile" #number "_settings", .mode = 0440 }, \ .size = PYRA_SIZE_PROFILE_SETTINGS, \ - .read = pyra_sysfs_read_profilex_settings, \ + .read_new = pyra_sysfs_read_profilex_settings, \ .private = &profile_numbers[number-1], \ }; \ -static struct bin_attribute bin_attr_profile##number##_buttons = { \ +static const struct bin_attribute bin_attr_profile##number##_buttons = { \ .attr = { .name = "profile" #number "_buttons", .mode = 0440 }, \ .size = PYRA_SIZE_PROFILE_BUTTONS, \ - .read = pyra_sysfs_read_profilex_buttons, \ + .read_new = pyra_sysfs_read_profilex_buttons, \ .private = &profile_numbers[number-1], \ }; PROFILE_ATTR(1); @@ -235,8 +235,8 @@ PROFILE_ATTR(4); PROFILE_ATTR(5); static ssize_t pyra_sysfs_write_settings(struct file *fp, - struct kobject *kobj, struct bin_attribute *attr, char *buf, - loff_t off, size_t count) + struct kobject *kobj, const struct bin_attribute *attr, + char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct pyra_device *pyra = hid_get_drvdata(dev_get_drvdata(dev)); @@ -273,7 +273,7 @@ static ssize_t pyra_sysfs_write_settings(struct file *fp, } PYRA_SYSFS_R(settings, SETTINGS); -static struct bin_attribute bin_attr_settings = +static const struct bin_attribute bin_attr_settings = __BIN_ATTR(settings, (S_IWUSR | S_IRUGO), pyra_sysfs_read_settings, pyra_sysfs_write_settings, PYRA_SIZE_SETTINGS); @@ -334,7 +334,7 @@ static struct attribute *pyra_attrs[] = { NULL, }; -static struct bin_attribute *pyra_bin_attributes[] = { +static const struct bin_attribute *const pyra_bin_attributes[] = { &bin_attr_control, &bin_attr_info, &bin_attr_profile_settings, @@ -355,7 +355,7 @@ static struct bin_attribute *pyra_bin_attributes[] = { static const struct attribute_group pyra_group = { .attrs = pyra_attrs, - .bin_attrs = pyra_bin_attributes, + .bin_attrs_new = pyra_bin_attributes, }; static const struct attribute_group *pyra_groups[] = { diff --git a/drivers/hid/hid-roccat-ryos.c b/drivers/hid/hid-roccat-ryos.c index 57714a4525e2..902dac1e714e 100644 --- a/drivers/hid/hid-roccat-ryos.c +++ b/drivers/hid/hid-roccat-ryos.c @@ -47,7 +47,7 @@ ROCCAT_COMMON2_BIN_ATTRIBUTE_RW(stored_lights, 0x17, 0x0566); ROCCAT_COMMON2_BIN_ATTRIBUTE_W(custom_lights, 0x18, 0x14); ROCCAT_COMMON2_BIN_ATTRIBUTE_RW(light_macro, 0x19, 0x07d2); -static struct bin_attribute *ryos_bin_attrs[] = { +static const struct bin_attribute *const ryos_bin_attrs[] = { &bin_attr_control, &bin_attr_profile, &bin_attr_keys_primary, @@ -70,7 +70,7 @@ static struct bin_attribute *ryos_bin_attrs[] = { }; static const struct attribute_group ryos_group = { - .bin_attrs = ryos_bin_attrs, + .bin_attrs_new = ryos_bin_attrs, }; static const struct attribute_group *ryos_groups[] = { diff --git a/drivers/hid/hid-roccat-savu.c b/drivers/hid/hid-roccat-savu.c index 2baa47a0efc5..7399b8ffb5c7 100644 --- a/drivers/hid/hid-roccat-savu.c +++ b/drivers/hid/hid-roccat-savu.c @@ -30,7 +30,7 @@ ROCCAT_COMMON2_BIN_ATTRIBUTE_RW(macro, 0x8, 0x0823); ROCCAT_COMMON2_BIN_ATTRIBUTE_RW(info, 0x9, 0x08); ROCCAT_COMMON2_BIN_ATTRIBUTE_RW(sensor, 0xc, 0x04); -static struct bin_attribute *savu_bin_attrs[] = { +static const struct bin_attribute *const savu_bin_attrs[] = { &bin_attr_control, &bin_attr_profile, &bin_attr_general, @@ -42,7 +42,7 @@ static struct bin_attribute *savu_bin_attrs[] = { }; static const struct attribute_group savu_group = { - .bin_attrs = savu_bin_attrs, + .bin_attrs_new = savu_bin_attrs, }; static const struct attribute_group *savu_groups[] = { diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 7bd86eef6ec7..4c94c03cb573 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -730,23 +730,30 @@ err_stop_hw: return ret; } +static int sensor_hub_finalize_pending_fn(struct device *dev, void *data) +{ + struct hid_sensor_hub_device *hsdev = dev->platform_data; + + if (hsdev->pending.status) + complete(&hsdev->pending.ready); + + return 0; +} + static void sensor_hub_remove(struct hid_device *hdev) { struct sensor_hub_data *data = hid_get_drvdata(hdev); unsigned long flags; - int i; hid_dbg(hdev, " hardware removed\n"); hid_hw_close(hdev); hid_hw_stop(hdev); + spin_lock_irqsave(&data->lock, flags); - for (i = 0; i < data->hid_sensor_client_cnt; ++i) { - struct hid_sensor_hub_device *hsdev = - data->hid_sensor_hub_client_devs[i].platform_data; - if (hsdev->pending.status) - complete(&hsdev->pending.ready); - } + device_for_each_child(&hdev->dev, NULL, + sensor_hub_finalize_pending_fn); spin_unlock_irqrestore(&data->lock, flags); + mfd_remove_devices(&hdev->dev); mutex_destroy(&data->mutex); } diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c index 6439913372a8..af38fc8eb34f 100644 --- a/drivers/hid/hid-steam.c +++ b/drivers/hid/hid-steam.c @@ -1306,6 +1306,7 @@ static void steam_remove(struct hid_device *hdev) cancel_delayed_work_sync(&steam->mode_switch); cancel_work_sync(&steam->work_connect); + cancel_work_sync(&steam->rumble_work); hid_destroy_device(steam->client_hdev); steam->client_hdev = NULL; steam->client_opened = 0; diff --git a/drivers/hid/hid-steelseries.c b/drivers/hid/hid-steelseries.c index f9ff5be94309..d4bd7848b8c6 100644 --- a/drivers/hid/hid-steelseries.c +++ b/drivers/hid/hid-steelseries.c @@ -19,6 +19,7 @@ #define STEELSERIES_SRWS1 BIT(0) #define STEELSERIES_ARCTIS_1 BIT(1) +#define STEELSERIES_ARCTIS_9 BIT(2) struct steelseries_device { struct hid_device *hdev; @@ -32,6 +33,7 @@ struct steelseries_device { struct power_supply *battery; uint8_t battery_capacity; bool headset_connected; + bool battery_charging; }; #if IS_BUILTIN(CONFIG_LEDS_CLASS) || \ @@ -368,32 +370,35 @@ static void steelseries_srws1_remove(struct hid_device *hdev) hid_hw_stop(hdev); kfree(drv_data); - return; } #endif #define STEELSERIES_HEADSET_BATTERY_TIMEOUT_MS 3000 #define ARCTIS_1_BATTERY_RESPONSE_LEN 8 +#define ARCTIS_9_BATTERY_RESPONSE_LEN 64 static const char arctis_1_battery_request[] = { 0x06, 0x12 }; +static const char arctis_9_battery_request[] = { 0x00, 0x20 }; -static int steelseries_headset_arctis_1_fetch_battery(struct hid_device *hdev) +static int steelseries_headset_request_battery(struct hid_device *hdev, + const char *request, size_t len) { u8 *write_buf; int ret; /* Request battery information */ - write_buf = kmemdup(arctis_1_battery_request, sizeof(arctis_1_battery_request), GFP_KERNEL); + write_buf = kmemdup(request, len, GFP_KERNEL); if (!write_buf) return -ENOMEM; - ret = hid_hw_raw_request(hdev, arctis_1_battery_request[0], - write_buf, sizeof(arctis_1_battery_request), + hid_dbg(hdev, "Sending battery request report"); + ret = hid_hw_raw_request(hdev, request[0], write_buf, len, HID_OUTPUT_REPORT, HID_REQ_SET_REPORT); - if (ret < (int)sizeof(arctis_1_battery_request)) { + if (ret < (int)len) { hid_err(hdev, "hid_hw_raw_request() failed with %d\n", ret); ret = -ENODATA; } + kfree(write_buf); return ret; } @@ -404,7 +409,11 @@ static void steelseries_headset_fetch_battery(struct hid_device *hdev) int ret = 0; if (sd->quirks & STEELSERIES_ARCTIS_1) - ret = steelseries_headset_arctis_1_fetch_battery(hdev); + ret = steelseries_headset_request_battery(hdev, + arctis_1_battery_request, sizeof(arctis_1_battery_request)); + else if (sd->quirks & STEELSERIES_ARCTIS_9) + ret = steelseries_headset_request_battery(hdev, + arctis_9_battery_request, sizeof(arctis_9_battery_request)); if (ret < 0) hid_dbg(hdev, @@ -429,6 +438,9 @@ static void steelseries_headset_battery_timer_tick(struct work_struct *work) steelseries_headset_fetch_battery(hdev); } +#define STEELSERIES_PREFIX "SteelSeries " +#define STEELSERIES_PREFIX_LEN strlen(STEELSERIES_PREFIX) + static int steelseries_headset_battery_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) @@ -437,13 +449,24 @@ static int steelseries_headset_battery_get_property(struct power_supply *psy, int ret = 0; switch (psp) { + case POWER_SUPPLY_PROP_MODEL_NAME: + val->strval = sd->hdev->name; + while (!strncmp(val->strval, STEELSERIES_PREFIX, STEELSERIES_PREFIX_LEN)) + val->strval += STEELSERIES_PREFIX_LEN; + break; + case POWER_SUPPLY_PROP_MANUFACTURER: + val->strval = "SteelSeries"; + break; case POWER_SUPPLY_PROP_PRESENT: val->intval = 1; break; case POWER_SUPPLY_PROP_STATUS: - val->intval = sd->headset_connected ? - POWER_SUPPLY_STATUS_DISCHARGING : - POWER_SUPPLY_STATUS_UNKNOWN; + if (sd->headset_connected) { + val->intval = sd->battery_charging ? + POWER_SUPPLY_STATUS_CHARGING : + POWER_SUPPLY_STATUS_DISCHARGING; + } else + val->intval = POWER_SUPPLY_STATUS_UNKNOWN; break; case POWER_SUPPLY_PROP_SCOPE: val->intval = POWER_SUPPLY_SCOPE_DEVICE; @@ -477,6 +500,8 @@ steelseries_headset_set_wireless_status(struct hid_device *hdev, } static enum power_supply_property steelseries_headset_battery_props[] = { + POWER_SUPPLY_PROP_MODEL_NAME, + POWER_SUPPLY_PROP_MANUFACTURER, POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_SCOPE, @@ -505,6 +530,7 @@ static int steelseries_headset_battery_register(struct steelseries_device *sd) /* avoid the warning of 0% battery while waiting for the first info */ steelseries_headset_set_wireless_status(sd->hdev, false); sd->battery_capacity = 100; + sd->battery_charging = false; sd->battery = devm_power_supply_register(&sd->hdev->dev, &sd->battery_desc, &battery_cfg); @@ -520,9 +546,22 @@ static int steelseries_headset_battery_register(struct steelseries_device *sd) INIT_DELAYED_WORK(&sd->battery_work, steelseries_headset_battery_timer_tick); steelseries_headset_fetch_battery(sd->hdev); + if (sd->quirks & STEELSERIES_ARCTIS_9) { + /* The first fetch_battery request can remain unanswered in some cases */ + schedule_delayed_work(&sd->battery_work, + msecs_to_jiffies(STEELSERIES_HEADSET_BATTERY_TIMEOUT_MS)); + } + return 0; } +static bool steelseries_is_vendor_usage_page(struct hid_device *hdev, uint8_t usage_page) +{ + return hdev->rdesc[0] == 0x06 && + hdev->rdesc[1] == usage_page && + hdev->rdesc[2] == 0xff; +} + static int steelseries_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct steelseries_device *sd; @@ -548,12 +587,20 @@ static int steelseries_probe(struct hid_device *hdev, const struct hid_device_id if (ret) return ret; + if (sd->quirks & STEELSERIES_ARCTIS_9 && + !steelseries_is_vendor_usage_page(hdev, 0xc0)) + return -ENODEV; + spin_lock_init(&sd->lock); ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) return ret; + ret = hid_hw_open(hdev); + if (ret) + return ret; + if (steelseries_headset_battery_register(sd) < 0) hid_err(sd->hdev, "Failed to register battery for headset\n"); @@ -580,6 +627,7 @@ static void steelseries_remove(struct hid_device *hdev) cancel_delayed_work_sync(&sd->battery_work); + hid_hw_close(hdev); hid_hw_stop(hdev); } @@ -599,6 +647,15 @@ static const __u8 *steelseries_srws1_report_fixup(struct hid_device *hdev, return rdesc; } +static uint8_t steelseries_headset_map_capacity(uint8_t capacity, uint8_t min_in, uint8_t max_in) +{ + if (capacity >= max_in) + return 100; + if (capacity <= min_in) + return 0; + return (capacity - min_in) * 100 / (max_in - min_in); +} + static int steelseries_headset_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *read_buf, int size) @@ -606,6 +663,7 @@ static int steelseries_headset_raw_event(struct hid_device *hdev, struct steelseries_device *sd = hid_get_drvdata(hdev); int capacity = sd->battery_capacity; bool connected = sd->headset_connected; + bool charging = sd->battery_charging; unsigned long flags; /* Not a headset */ @@ -630,6 +688,34 @@ static int steelseries_headset_raw_event(struct hid_device *hdev, } } + if (sd->quirks & STEELSERIES_ARCTIS_9) { + hid_dbg(sd->hdev, + "Parsing raw event for Arctis 9 headset (%*ph)\n", size, read_buf); + if (size < ARCTIS_9_BATTERY_RESPONSE_LEN) { + if (!delayed_work_pending(&sd->battery_work)) + goto request_battery; + return 0; + } + + if (read_buf[0] == 0xaa && read_buf[1] == 0x01) { + connected = true; + charging = read_buf[4] == 0x01; + + /* + * Found no official documentation about min and max. + * Values defined by testing. + */ + capacity = steelseries_headset_map_capacity(read_buf[3], 0x68, 0x9d); + } else { + /* + * Device is off and sends the last known status read_buf[1] == 0x03 or + * there is no known status of the device read_buf[0] == 0x55 + */ + connected = false; + charging = false; + } + } + if (connected != sd->headset_connected) { hid_dbg(sd->hdev, "Connected status changed from %sconnected to %sconnected\n", @@ -647,6 +733,15 @@ static int steelseries_headset_raw_event(struct hid_device *hdev, power_supply_changed(sd->battery); } + if (charging != sd->battery_charging) { + hid_dbg(sd->hdev, + "Battery charging status changed from %scharging to %scharging\n", + sd->battery_charging ? "" : "not ", + charging ? "" : "not "); + sd->battery_charging = charging; + power_supply_changed(sd->battery); + } + request_battery: spin_lock_irqsave(&sd->lock, flags); if (!sd->removed) @@ -665,6 +760,10 @@ static const struct hid_device_id steelseries_devices[] = { HID_USB_DEVICE(USB_VENDOR_ID_STEELSERIES, 0x12b6), .driver_data = STEELSERIES_ARCTIS_1 }, + { /* SteelSeries Arctis 9 Wireless for XBox */ + HID_USB_DEVICE(USB_VENDOR_ID_STEELSERIES, 0x12c2), + .driver_data = STEELSERIES_ARCTIS_9 }, + { } }; MODULE_DEVICE_TABLE(hid, steelseries_devices); @@ -683,3 +782,4 @@ MODULE_DESCRIPTION("HID driver for Steelseries devices"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Bastien Nocera "); MODULE_AUTHOR("Simon Wood "); +MODULE_AUTHOR("Christian Mayer "); diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c index cf1679b0d4fb..6c3e758bbb09 100644 --- a/drivers/hid/hid-thrustmaster.c +++ b/drivers/hid/hid-thrustmaster.c @@ -170,6 +170,14 @@ static void thrustmaster_interrupts(struct hid_device *hdev) ep = &usbif->cur_altsetting->endpoint[1]; b_ep = ep->desc.bEndpointAddress; + /* Are the expected endpoints present? */ + u8 ep_addr[1] = {b_ep}; + + if (!usb_check_int_endpoints(usbif, ep_addr)) { + hid_err(hdev, "Unexpected non-int endpoint\n"); + return; + } + for (i = 0; i < ARRAY_SIZE(setup_arr); ++i) { memcpy(send_buf, setup_arr[i], setup_arr_sizes[i]); diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index ef26c7defcf6..a6044996abf2 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -842,7 +842,7 @@ static int uclogic_params_huion_init(struct uclogic_params *params, __u8 *params_ptr = NULL; size_t params_len = 0; /* Parameters string descriptor of a model with touch ring (HS610) */ - const __u8 touch_ring_model_params_buf[] = { + static const __u8 touch_ring_model_params_buf[] = { 0x13, 0x03, 0x70, 0xC6, 0x00, 0x06, 0x7C, 0x00, 0xFF, 0x1F, 0xD8, 0x13, 0x03, 0x0D, 0x10, 0x01, 0x04, 0x3C, 0x3E diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 4e87380d3edd..75544448c239 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -51,6 +51,7 @@ #define I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET BIT(4) #define I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND BIT(5) #define I2C_HID_QUIRK_DELAY_WAKEUP_AFTER_RESUME BIT(6) +#define I2C_HID_QUIRK_RE_POWER_ON BIT(7) /* Command opcodes */ #define I2C_HID_OPCODE_RESET 0x01 @@ -135,6 +136,11 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_BAD_INPUT_SIZE }, { I2C_VENDOR_ID_CIRQUE, I2C_PRODUCT_ID_CIRQUE_1063, I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND }, + /* + * Without additional power on command, at least some QTEC devices send garbage + */ + { I2C_VENDOR_ID_QTEC, HID_ANY_ID, + I2C_HID_QUIRK_RE_POWER_ON }, /* * Sending the wakeup after reset actually break ELAN touchscreen controller */ @@ -1073,7 +1079,11 @@ static int i2c_hid_core_register_hid(struct i2c_hid *ihid) return ret; } - return 0; + /* At least some QTEC devices need this after initialization */ + if (ihid->quirks & I2C_HID_QUIRK_RE_POWER_ON) + ret = i2c_hid_set_power(ihid, I2C_HID_PWR_ON); + + return ret; } static int i2c_hid_core_probe_panel_follower(struct i2c_hid *ihid) diff --git a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c index 513d7a4a1b8a..97f4026b1627 100644 --- a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c +++ b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c @@ -251,27 +251,6 @@ int ishtp_cl_io_rb_recycle(struct ishtp_cl_rb *rb) } EXPORT_SYMBOL(ishtp_cl_io_rb_recycle); -/** - * ishtp_cl_tx_empty() -test whether client device tx buffer is empty - * @cl: Pointer to client device instance - * - * Look client device tx buffer list, and check whether this list is empty - * - * Return: true if client tx buffer list is empty else false - */ -bool ishtp_cl_tx_empty(struct ishtp_cl *cl) -{ - int tx_list_empty; - unsigned long tx_flags; - - spin_lock_irqsave(&cl->tx_list_spinlock, tx_flags); - tx_list_empty = list_empty(&cl->tx_list.list); - spin_unlock_irqrestore(&cl->tx_list_spinlock, tx_flags); - - return !!tx_list_empty; -} -EXPORT_SYMBOL(ishtp_cl_tx_empty); - /** * ishtp_cl_rx_get_rb() -Get a rb from client device rx buffer list * @cl: Pointer to client device instance diff --git a/drivers/hid/intel-ish-hid/ishtp/client.c b/drivers/hid/intel-ish-hid/ishtp/client.c index e61b01e9902e..21a2c0773cc2 100644 --- a/drivers/hid/intel-ish-hid/ishtp/client.c +++ b/drivers/hid/intel-ish-hid/ishtp/client.c @@ -14,25 +14,6 @@ #include "hbm.h" #include "client.h" -int ishtp_cl_get_tx_free_buffer_size(struct ishtp_cl *cl) -{ - unsigned long tx_free_flags; - int size; - - spin_lock_irqsave(&cl->tx_free_list_spinlock, tx_free_flags); - size = cl->tx_ring_free_size * cl->device->fw_client->props.max_msg_length; - spin_unlock_irqrestore(&cl->tx_free_list_spinlock, tx_free_flags); - - return size; -} -EXPORT_SYMBOL(ishtp_cl_get_tx_free_buffer_size); - -int ishtp_cl_get_tx_free_rings(struct ishtp_cl *cl) -{ - return cl->tx_ring_free_size; -} -EXPORT_SYMBOL(ishtp_cl_get_tx_free_rings); - /** * ishtp_read_list_flush() - Flush read queue * @cl: ishtp client instance diff --git a/drivers/hid/intel-ish-hid/ishtp/client.h b/drivers/hid/intel-ish-hid/ishtp/client.h index d9d398fadcf7..0efd49dd2530 100644 --- a/drivers/hid/intel-ish-hid/ishtp/client.h +++ b/drivers/hid/intel-ish-hid/ishtp/client.h @@ -120,8 +120,6 @@ int ishtp_cl_alloc_rx_ring(struct ishtp_cl *cl); int ishtp_cl_alloc_tx_ring(struct ishtp_cl *cl); void ishtp_cl_free_rx_ring(struct ishtp_cl *cl); void ishtp_cl_free_tx_ring(struct ishtp_cl *cl); -int ishtp_cl_get_tx_free_buffer_size(struct ishtp_cl *cl); -int ishtp_cl_get_tx_free_rings(struct ishtp_cl *cl); /* DMA I/F functions */ void recv_ishtp_cl_msg_dma(struct ishtp_device *dev, void *msg, diff --git a/drivers/hid/intel-ish-hid/ishtp/init.c b/drivers/hid/intel-ish-hid/ishtp/init.c index 07fdd52e4c5e..26bf9045a8de 100644 --- a/drivers/hid/intel-ish-hid/ishtp/init.c +++ b/drivers/hid/intel-ish-hid/ishtp/init.c @@ -14,36 +14,6 @@ #include "client.h" #include "loader.h" -/** - * ishtp_dev_state_str() -Convert to string format - * @state: state to convert - * - * Convert state to string for prints - * - * Return: character pointer to converted string - */ -const char *ishtp_dev_state_str(int state) -{ - switch (state) { - case ISHTP_DEV_INITIALIZING: - return "INITIALIZING"; - case ISHTP_DEV_INIT_CLIENTS: - return "INIT_CLIENTS"; - case ISHTP_DEV_ENABLED: - return "ENABLED"; - case ISHTP_DEV_RESETTING: - return "RESETTING"; - case ISHTP_DEV_DISABLED: - return "DISABLED"; - case ISHTP_DEV_POWER_DOWN: - return "POWER_DOWN"; - case ISHTP_DEV_POWER_UP: - return "POWER_UP"; - default: - return "unknown"; - } -} - /** * ishtp_device_init() - ishtp device init * @dev: ISHTP device instance diff --git a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h index effbb442c727..44eddc411e97 100644 --- a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h +++ b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h @@ -57,7 +57,6 @@ enum ishtp_dev_state { ISHTP_DEV_POWER_DOWN, ISHTP_DEV_POWER_UP }; -const char *ishtp_dev_state_str(int state); struct ishtp_cl; diff --git a/drivers/hid/intel-thc-hid/Kconfig b/drivers/hid/intel-thc-hid/Kconfig new file mode 100644 index 000000000000..91ec84902db8 --- /dev/null +++ b/drivers/hid/intel-thc-hid/Kconfig @@ -0,0 +1,43 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2024, Intel Corporation. + +menu "Intel THC HID Support" + depends on X86_64 && PCI + +config INTEL_THC_HID + tristate "Intel Touch Host Controller" + depends on ACPI + select HID + help + THC (Touch Host Controller) is the name of the IP block in PCH that + interfaces with Touch Devices (ex: touchscreen, touchpad etc.). It + is comprised of 3 key functional blocks: A natively half-duplex + Quad I/O capable SPI master; a low latency I2C interface to support + HIDI2C compliant devices; a hardware sequencer with Read/Write DMA + capability to system memory. + + Say Y/M here if you want to support Intel THC. If unsure, say N. + +config INTEL_QUICKSPI + tristate "Intel QuickSPI driver based on Intel Touch Host Controller" + depends on INTEL_THC_HID + help + Intel QuickSPI, based on Touch Host Controller (THC), implements + HIDSPI (HID over SPI) protocol. It configures THC to work at SPI + mode, and controls THC hardware sequencer to accelerate HIDSPI + transaction flow. + + Say Y/M here if you want to support Intel QuickSPI. If unsure, say N. + +config INTEL_QUICKI2C + tristate "Intel QuickI2C driver based on Intel Touch Host Controller" + depends on INTEL_THC_HID + help + Intel QuickI2C, uses Touch Host Controller (THC) hardware, implements + HIDI2C (HID over I2C) protocol. It configures THC to work in I2C + mode, and controls THC hardware sequencer to accelerate HIDI2C + transaction flow. + + Say Y/M here if you want to support Intel QuickI2C. If unsure, say N. + +endmenu diff --git a/drivers/hid/intel-thc-hid/Makefile b/drivers/hid/intel-thc-hid/Makefile new file mode 100644 index 000000000000..6f762d87af07 --- /dev/null +++ b/drivers/hid/intel-thc-hid/Makefile @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile - Intel Touch Host Controller (THC) drivers +# Copyright (c) 2024, Intel Corporation. +# +# + +obj-$(CONFIG_INTEL_THC_HID) += intel-thc.o +intel-thc-objs += intel-thc/intel-thc-dev.o +intel-thc-objs += intel-thc/intel-thc-dma.o + +obj-$(CONFIG_INTEL_QUICKSPI) += intel-quickspi.o +intel-quickspi-objs += intel-quickspi/pci-quickspi.o +intel-quickspi-objs += intel-quickspi/quickspi-hid.o +intel-quickspi-objs += intel-quickspi/quickspi-protocol.o + +obj-$(CONFIG_INTEL_QUICKI2C) += intel-quicki2c.o +intel-quicki2c-objs += intel-quicki2c/pci-quicki2c.o +intel-quicki2c-objs += intel-quicki2c/quicki2c-hid.o +intel-quicki2c-objs += intel-quicki2c/quicki2c-protocol.o + +ccflags-y += -I $(src)/intel-thc diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c new file mode 100644 index 000000000000..2de93f4a25ca --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c @@ -0,0 +1,969 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "intel-thc-dev.h" +#include "intel-thc-hw.h" + +#include "quicki2c-dev.h" +#include "quicki2c-hid.h" +#include "quicki2c-protocol.h" + +/* THC QuickI2C ACPI method to get device properties */ +/* HIDI2C device method */ +static guid_t i2c_hid_guid = + GUID_INIT(0x3cdff6f7, 0x4267, 0x4555, 0xad, 0x05, 0xb3, 0x0a, 0x3d, 0x89, 0x38, 0xde); + +/* platform method */ +static guid_t thc_platform_guid = + GUID_INIT(0x84005682, 0x5b71, 0x41a4, 0x8d, 0x66, 0x81, 0x30, 0xf7, 0x87, 0xa1, 0x38); + +/** + * quicki2c_acpi_get_dsm_property - Query device ACPI DSM parameter + * + * @adev: point to ACPI device + * @guid: ACPI method's guid + * @rev: ACPI method's revision + * @func: ACPI method's function number + * @type: ACPI parameter's data type + * @prop_buf: point to return buffer + * + * This is a helper function for device to query its ACPI DSM parameters. + * + * Return: 0 if success or ENODEV on failed. + */ +static int quicki2c_acpi_get_dsm_property(struct acpi_device *adev, const guid_t *guid, + u64 rev, u64 func, acpi_object_type type, void *prop_buf) +{ + acpi_handle handle = acpi_device_handle(adev); + union acpi_object *obj; + + obj = acpi_evaluate_dsm_typed(handle, guid, rev, func, NULL, type); + if (!obj) { + acpi_handle_err(handle, + "Error _DSM call failed, rev: %d, func: %d, type: %d\n", + (int)rev, (int)func, (int)type); + return -ENODEV; + } + + if (type == ACPI_TYPE_INTEGER) + *(u32 *)prop_buf = (u32)obj->integer.value; + else if (type == ACPI_TYPE_BUFFER) + memcpy(prop_buf, obj->buffer.pointer, obj->buffer.length); + + ACPI_FREE(obj); + + return 0; +} + +/** + * quicki2c_acpi_get_dsd_property - Query device ACPI DSD parameter + * + * @adev: point to ACPI device + * @dsd_method_name: ACPI method's property name + * @type: ACPI parameter's data type + * @prop_buf: point to return buffer + * + * This is a helper function for device to query its ACPI DSD parameters. + * + * Return: 0 if success or ENODEV on failed. + */ +static int quicki2c_acpi_get_dsd_property(struct acpi_device *adev, acpi_string dsd_method_name, + acpi_object_type type, void *prop_buf) +{ + acpi_handle handle = acpi_device_handle(adev); + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object obj = { .type = type }; + struct acpi_object_list arg_list = { + .count = 1, + .pointer = &obj, + }; + union acpi_object *ret_obj; + acpi_status status; + + status = acpi_evaluate_object(handle, dsd_method_name, &arg_list, &buffer); + if (ACPI_FAILURE(status)) { + acpi_handle_err(handle, + "Can't evaluate %s method: %d\n", dsd_method_name, status); + return -ENODEV; + } + + ret_obj = buffer.pointer; + + memcpy(prop_buf, ret_obj->buffer.pointer, ret_obj->buffer.length); + + return 0; +} + +/** + * quicki2c_get_acpi_resources - Query all quicki2c devices' ACPI parameters + * + * @qcdev: point to quicki2c device + * + * This function gets all quicki2c devices' ACPI resource. + * + * Return: 0 if success or error code on failed. + */ +static int quicki2c_get_acpi_resources(struct quicki2c_device *qcdev) +{ + struct acpi_device *adev = ACPI_COMPANION(qcdev->dev); + struct quicki2c_subip_acpi_parameter i2c_param; + struct quicki2c_subip_acpi_config i2c_config; + u32 hid_desc_addr; + int ret = -EINVAL; + + if (!adev) { + dev_err(qcdev->dev, "Invalid acpi device pointer\n"); + return ret; + } + + qcdev->acpi_dev = adev; + + ret = quicki2c_acpi_get_dsm_property(adev, &i2c_hid_guid, + QUICKI2C_ACPI_REVISION_NUM, + QUICKI2C_ACPI_FUNC_NUM_HID_DESC_ADDR, + ACPI_TYPE_INTEGER, + &hid_desc_addr); + if (ret) + return ret; + + qcdev->hid_desc_addr = (u16)hid_desc_addr; + + ret = quicki2c_acpi_get_dsm_property(adev, &thc_platform_guid, + QUICKI2C_ACPI_REVISION_NUM, + QUICKI2C_ACPI_FUNC_NUM_ACTIVE_LTR_VAL, + ACPI_TYPE_INTEGER, + &qcdev->active_ltr_val); + if (ret) + return ret; + + ret = quicki2c_acpi_get_dsm_property(adev, &thc_platform_guid, + QUICKI2C_ACPI_REVISION_NUM, + QUICKI2C_ACPI_FUNC_NUM_LP_LTR_VAL, + ACPI_TYPE_INTEGER, + &qcdev->low_power_ltr_val); + if (ret) + return ret; + + ret = quicki2c_acpi_get_dsd_property(adev, QUICKI2C_ACPI_METHOD_NAME_ICRS, + ACPI_TYPE_BUFFER, &i2c_param); + if (ret) + return ret; + + if (i2c_param.addressing_mode != HIDI2C_ADDRESSING_MODE_7BIT) + return -EOPNOTSUPP; + + qcdev->i2c_slave_addr = i2c_param.device_address; + + ret = quicki2c_acpi_get_dsd_property(adev, QUICKI2C_ACPI_METHOD_NAME_ISUB, + ACPI_TYPE_BUFFER, &i2c_config); + if (ret) + return ret; + + if (i2c_param.connection_speed > 0 && + i2c_param.connection_speed <= QUICKI2C_SUBIP_STANDARD_MODE_MAX_SPEED) { + qcdev->i2c_speed_mode = THC_I2C_STANDARD; + qcdev->i2c_clock_hcnt = i2c_config.SMHX; + qcdev->i2c_clock_lcnt = i2c_config.SMLX; + } else if (i2c_param.connection_speed > QUICKI2C_SUBIP_STANDARD_MODE_MAX_SPEED && + i2c_param.connection_speed <= QUICKI2C_SUBIP_FAST_MODE_MAX_SPEED) { + qcdev->i2c_speed_mode = THC_I2C_FAST_AND_PLUS; + qcdev->i2c_clock_hcnt = i2c_config.FMHX; + qcdev->i2c_clock_lcnt = i2c_config.FMLX; + } else if (i2c_param.connection_speed > QUICKI2C_SUBIP_FAST_MODE_MAX_SPEED && + i2c_param.connection_speed <= QUICKI2C_SUBIP_FASTPLUS_MODE_MAX_SPEED) { + qcdev->i2c_speed_mode = THC_I2C_FAST_AND_PLUS; + qcdev->i2c_clock_hcnt = i2c_config.FPHX; + qcdev->i2c_clock_lcnt = i2c_config.FPLX; + } else if (i2c_param.connection_speed > QUICKI2C_SUBIP_FASTPLUS_MODE_MAX_SPEED && + i2c_param.connection_speed <= QUICKI2C_SUBIP_HIGH_SPEED_MODE_MAX_SPEED) { + qcdev->i2c_speed_mode = THC_I2C_HIGH_SPEED; + qcdev->i2c_clock_hcnt = i2c_config.HMHX; + qcdev->i2c_clock_lcnt = i2c_config.HMLX; + } else { + return -EOPNOTSUPP; + } + + return 0; +} + +/** + * quicki2c_irq_quick_handler - The ISR of the quicki2c driver + * + * @irq: The irq number + * @dev_id: pointer to the device structure + * + * Return: IRQ_WAKE_THREAD if further process needed. + */ +static irqreturn_t quicki2c_irq_quick_handler(int irq, void *dev_id) +{ + struct quicki2c_device *qcdev = dev_id; + + if (qcdev->state == QUICKI2C_DISABLED) + return IRQ_HANDLED; + + /* Disable THC interrupt before current interrupt be handled */ + thc_interrupt_enable(qcdev->thc_hw, false); + + return IRQ_WAKE_THREAD; +} + +/** + * try_recover - Try to recovery THC and Device + * @qcdev: pointer to quicki2c device + * + * This function is a error handler, called when fatal error happens. + * It try to reset Touch Device and re-configure THC to recovery + * transferring between Device and THC. + * + * Return: 0 if successful or error code on failed + */ +static int try_recover(struct quicki2c_device *qcdev) +{ + int ret; + + thc_dma_unconfigure(qcdev->thc_hw); + + ret = thc_dma_configure(qcdev->thc_hw); + if (ret) { + dev_err(qcdev->dev, "Reconfig DMA failed\n"); + return ret; + } + + return 0; +} + +static int handle_input_report(struct quicki2c_device *qcdev) +{ + struct hidi2c_report_packet *pkt = (struct hidi2c_report_packet *)qcdev->input_buf; + int rx_dma_finished = 0; + size_t report_len; + int ret; + + while (!rx_dma_finished) { + ret = thc_rxdma_read(qcdev->thc_hw, THC_RXDMA2, + (u8 *)pkt, &report_len, + &rx_dma_finished); + if (ret) + return ret; + + if (!pkt->len) { + if (qcdev->state == QUICKI2C_RESETING) { + qcdev->reset_ack = true; + wake_up(&qcdev->reset_ack_wq); + + qcdev->state = QUICKI2C_RESETED; + } else { + dev_warn(qcdev->dev, "unexpected DIR happen\n"); + } + + continue; + } + + /* discard samples before driver probe complete */ + if (qcdev->state != QUICKI2C_ENABLED) + continue; + + quicki2c_hid_send_report(qcdev, pkt->data, + HIDI2C_DATA_LEN(le16_to_cpu(pkt->len))); + } + + return 0; +} + +/** + * quicki2c_irq_thread_handler - IRQ thread handler of quicki2c driver + * + * @irq: The IRQ number + * @dev_id: pointer to the quicki2c device structure + * + * Return: IRQ_HANDLED to finish this handler. + */ +static irqreturn_t quicki2c_irq_thread_handler(int irq, void *dev_id) +{ + struct quicki2c_device *qcdev = dev_id; + int err_recover = 0; + int int_mask; + int ret; + + if (qcdev->state == QUICKI2C_DISABLED) + return IRQ_HANDLED; + + ret = pm_runtime_resume_and_get(qcdev->dev); + if (ret) + return IRQ_HANDLED; + + int_mask = thc_interrupt_handler(qcdev->thc_hw); + + if (int_mask & BIT(THC_FATAL_ERR_INT) || int_mask & BIT(THC_TXN_ERR_INT) || + int_mask & BIT(THC_UNKNOWN_INT)) { + err_recover = 1; + goto exit; + } + + if (int_mask & BIT(THC_RXDMA2_INT)) { + err_recover = handle_input_report(qcdev); + if (err_recover) + goto exit; + } + +exit: + thc_interrupt_enable(qcdev->thc_hw, true); + + if (err_recover) + if (try_recover(qcdev)) + qcdev->state = QUICKI2C_DISABLED; + + pm_runtime_mark_last_busy(qcdev->dev); + pm_runtime_put_autosuspend(qcdev->dev); + + return IRQ_HANDLED; +} + +/** + * quicki2c_dev_init - Initialize quicki2c device + * + * @pdev: pointer to the thc pci device + * @mem_addr: The pointer of MMIO memory address + * + * Alloc quicki2c device structure and initialized THC device, + * then configure THC to HIDI2C mode. + * + * If success, enable THC hardware interrupt. + * + * Return: pointer to the quicki2c device structure if success + * or NULL on failed. + */ +static struct quicki2c_device *quicki2c_dev_init(struct pci_dev *pdev, void __iomem *mem_addr) +{ + struct device *dev = &pdev->dev; + struct quicki2c_device *qcdev; + int ret; + + qcdev = devm_kzalloc(dev, sizeof(struct quicki2c_device), GFP_KERNEL); + if (!qcdev) + return ERR_PTR(-ENOMEM); + + qcdev->pdev = pdev; + qcdev->dev = dev; + qcdev->mem_addr = mem_addr; + qcdev->state = QUICKI2C_DISABLED; + + init_waitqueue_head(&qcdev->reset_ack_wq); + + /* thc hw init */ + qcdev->thc_hw = thc_dev_init(qcdev->dev, qcdev->mem_addr); + if (IS_ERR(qcdev->thc_hw)) { + ret = PTR_ERR(qcdev->thc_hw); + dev_err_once(dev, "Failed to initialize THC device context, ret = %d.\n", ret); + return ERR_PTR(ret); + } + + ret = quicki2c_get_acpi_resources(qcdev); + if (ret) { + dev_err_once(dev, "Get ACPI resources failed, ret = %d\n", ret); + return ERR_PTR(ret); + } + + ret = thc_interrupt_quiesce(qcdev->thc_hw, true); + if (ret) + return ERR_PTR(ret); + + ret = thc_port_select(qcdev->thc_hw, THC_PORT_TYPE_I2C); + if (ret) { + dev_err_once(dev, "Failed to select THC port, ret = %d.\n", ret); + return ERR_PTR(ret); + } + + ret = thc_i2c_subip_init(qcdev->thc_hw, qcdev->i2c_slave_addr, + qcdev->i2c_speed_mode, + qcdev->i2c_clock_hcnt, + qcdev->i2c_clock_lcnt); + if (ret) + return ERR_PTR(ret); + + thc_int_trigger_type_select(qcdev->thc_hw, false); + + thc_interrupt_config(qcdev->thc_hw); + + thc_interrupt_enable(qcdev->thc_hw, true); + + qcdev->state = QUICKI2C_INITED; + + return qcdev; +} + +/** + * quicki2c_dev_deinit - De-initialize quicki2c device + * + * @qcdev: pointer to the quicki2c device structure + * + * Disable THC interrupt and deinitilize THC. + */ +static void quicki2c_dev_deinit(struct quicki2c_device *qcdev) +{ + thc_interrupt_enable(qcdev->thc_hw, false); + thc_ltr_unconfig(qcdev->thc_hw); + + qcdev->state = QUICKI2C_DISABLED; +} + +/** + * quicki2c_dma_init - Configure THC DMA for quicki2c device + * @qcdev: pointer to the quicki2c device structure + * + * This function uses TIC's parameters(such as max input length, max output + * length) to allocate THC DMA buffers and configure THC DMA engines. + * + * Return: 0 if success or error code on failed. + */ +static int quicki2c_dma_init(struct quicki2c_device *qcdev) +{ + size_t swdma_max_len; + int ret; + + swdma_max_len = max(le16_to_cpu(qcdev->dev_desc.max_input_len), + le16_to_cpu(qcdev->dev_desc.report_desc_len)); + + ret = thc_dma_set_max_packet_sizes(qcdev->thc_hw, 0, + le16_to_cpu(qcdev->dev_desc.max_input_len), + le16_to_cpu(qcdev->dev_desc.max_output_len), + swdma_max_len); + if (ret) + return ret; + + ret = thc_dma_allocate(qcdev->thc_hw); + if (ret) { + dev_err(qcdev->dev, "Allocate THC DMA buffer failed, ret = %d\n", ret); + return ret; + } + + /* Enable RxDMA */ + ret = thc_dma_configure(qcdev->thc_hw); + if (ret) { + dev_err(qcdev->dev, "Configure THC DMA failed, ret = %d\n", ret); + thc_dma_unconfigure(qcdev->thc_hw); + thc_dma_release(qcdev->thc_hw); + return ret; + } + + return ret; +} + +/** + * quicki2c_dma_deinit - Release THC DMA for quicki2c device + * @qcdev: pointer to the quicki2c device structure + * + * Stop THC DMA engines and release all DMA buffers. + * + */ +static void quicki2c_dma_deinit(struct quicki2c_device *qcdev) +{ + thc_dma_unconfigure(qcdev->thc_hw); + thc_dma_release(qcdev->thc_hw); +} + +/** + * quicki2c_alloc_report_buf - Alloc report buffers + * @qcdev: pointer to the quicki2c device structure + * + * Allocate report descriptor buffer, it will be used for restore TIC HID + * report descriptor. + * + * Allocate input report buffer, it will be used for receive HID input report + * data from TIC. + * + * Allocate output report buffer, it will be used for store HID output report, + * such as set feature. + * + * Return: 0 if success or error code on failed. + */ +static int quicki2c_alloc_report_buf(struct quicki2c_device *qcdev) +{ + size_t max_report_len; + + qcdev->report_descriptor = devm_kzalloc(qcdev->dev, + le16_to_cpu(qcdev->dev_desc.report_desc_len), + GFP_KERNEL); + if (!qcdev->report_descriptor) + return -ENOMEM; + + /* + * Some HIDI2C devices don't declare input/output max length correctly, + * give default 4K buffer to avoid DMA buffer overrun. + */ + max_report_len = max(le16_to_cpu(qcdev->dev_desc.max_input_len), SZ_4K); + + qcdev->input_buf = devm_kzalloc(qcdev->dev, max_report_len, GFP_KERNEL); + if (!qcdev->input_buf) + return -ENOMEM; + + if (!le16_to_cpu(qcdev->dev_desc.max_output_len)) + qcdev->dev_desc.max_output_len = cpu_to_le16(SZ_4K); + + max_report_len = max(le16_to_cpu(qcdev->dev_desc.max_output_len), + max_report_len); + + qcdev->report_buf = devm_kzalloc(qcdev->dev, max_report_len, GFP_KERNEL); + if (!qcdev->report_buf) + return -ENOMEM; + + qcdev->report_len = max_report_len; + + return 0; +} + +/* + * quicki2c_probe: Quicki2c driver probe function + * + * @pdev: point to pci device + * @id: point to pci_device_id structure + * + * This function initializes THC and HIDI2C device, the flow is: + * - do THC pci device initialization + * - query HIDI2C ACPI parameters + * - configure THC to HIDI2C mode + * - go through HIDI2C enumeration flow + * |- read device descriptor + * |- reset HIDI2C device + * - enable THC interrupt and DMA + * - read report descriptor + * - register HID device + * - enable runtime power management + * + * Return 0 if success or error code on failed. + */ +static int quicki2c_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct quicki2c_device *qcdev; + void __iomem *mem_addr; + int ret; + + ret = pcim_enable_device(pdev); + if (ret) { + dev_err_once(&pdev->dev, "Failed to enable PCI device, ret = %d.\n", ret); + return ret; + } + + pci_set_master(pdev); + + ret = pcim_iomap_regions(pdev, BIT(0), KBUILD_MODNAME); + if (ret) { + dev_err_once(&pdev->dev, "Failed to get PCI regions, ret = %d.\n", ret); + goto disable_pci_device; + } + + mem_addr = pcim_iomap_table(pdev)[0]; + + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) { + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) { + dev_err_once(&pdev->dev, "No usable DMA configuration %d\n", ret); + goto unmap_io_region; + } + } + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + dev_err_once(&pdev->dev, + "Failed to allocate IRQ vectors. ret = %d\n", ret); + goto unmap_io_region; + } + + pdev->irq = pci_irq_vector(pdev, 0); + + qcdev = quicki2c_dev_init(pdev, mem_addr); + if (IS_ERR(qcdev)) { + dev_err_once(&pdev->dev, "QuickI2C device init failed\n"); + ret = PTR_ERR(qcdev); + goto unmap_io_region; + } + + pci_set_drvdata(pdev, qcdev); + + ret = devm_request_threaded_irq(&pdev->dev, pdev->irq, + quicki2c_irq_quick_handler, + quicki2c_irq_thread_handler, + IRQF_ONESHOT, KBUILD_MODNAME, + qcdev); + if (ret) { + dev_err_once(&pdev->dev, + "Failed to request threaded IRQ, irq = %d.\n", pdev->irq); + goto dev_deinit; + } + + ret = quicki2c_get_device_descriptor(qcdev); + if (ret) { + dev_err(&pdev->dev, "Get device descriptor failed, ret = %d\n", ret); + goto dev_deinit; + } + + ret = quicki2c_alloc_report_buf(qcdev); + if (ret) { + dev_err(&pdev->dev, "Alloc report buffers failed, ret= %d\n", ret); + goto dev_deinit; + } + + ret = quicki2c_dma_init(qcdev); + if (ret) { + dev_err(&pdev->dev, "Setup THC DMA failed, ret= %d\n", ret); + goto dev_deinit; + } + + ret = thc_interrupt_quiesce(qcdev->thc_hw, false); + if (ret) + goto dev_deinit; + + ret = quicki2c_set_power(qcdev, HIDI2C_ON); + if (ret) { + dev_err(&pdev->dev, "Set Power On command failed, ret= %d\n", ret); + goto dev_deinit; + } + + ret = quicki2c_reset(qcdev); + if (ret) { + dev_err(&pdev->dev, "Reset HIDI2C device failed, ret= %d\n", ret); + goto dev_deinit; + } + + ret = quicki2c_get_report_descriptor(qcdev); + if (ret) { + dev_err(&pdev->dev, "Get report descriptor failed, ret = %d\n", ret); + goto dma_deinit; + } + + ret = quicki2c_hid_probe(qcdev); + if (ret) { + dev_err(&pdev->dev, "Failed to register HID device, ret = %d\n", ret); + goto dma_deinit; + } + + qcdev->state = QUICKI2C_ENABLED; + + /* Enable runtime power management */ + pm_runtime_use_autosuspend(qcdev->dev); + pm_runtime_set_autosuspend_delay(qcdev->dev, DEFAULT_AUTO_SUSPEND_DELAY_MS); + pm_runtime_mark_last_busy(qcdev->dev); + pm_runtime_put_noidle(qcdev->dev); + pm_runtime_put_autosuspend(qcdev->dev); + + dev_dbg(&pdev->dev, "QuickI2C probe success\n"); + + return 0; + +dma_deinit: + quicki2c_dma_deinit(qcdev); +dev_deinit: + quicki2c_dev_deinit(qcdev); +unmap_io_region: + pcim_iounmap_regions(pdev, BIT(0)); +disable_pci_device: + pci_clear_master(pdev); + + return ret; +} + +/** + * quicki2c_remove - Device Removal Routine + * + * @pdev: PCI device structure + * + * This is called by the PCI subsystem to alert the driver + * that it should release a PCI device. + */ +static void quicki2c_remove(struct pci_dev *pdev) +{ + struct quicki2c_device *qcdev; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return; + + quicki2c_hid_remove(qcdev); + quicki2c_dma_deinit(qcdev); + + pm_runtime_get_noresume(qcdev->dev); + + quicki2c_dev_deinit(qcdev); + + pcim_iounmap_regions(pdev, BIT(0)); + pci_clear_master(pdev); +} + +/** + * quicki2c_shutdown - Device Shutdown Routine + * + * @pdev: PCI device structure + * + * This is called from the reboot notifier + * it's a simplified version of remove so we go down + * faster. + */ +static void quicki2c_shutdown(struct pci_dev *pdev) +{ + struct quicki2c_device *qcdev; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return; + + /* Must stop DMA before reboot to avoid DMA entering into unknown state */ + quicki2c_dma_deinit(qcdev); + + quicki2c_dev_deinit(qcdev); +} + +static int quicki2c_suspend(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quicki2c_device *qcdev; + int ret; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return -ENODEV; + + /* + * As I2C is THC subsystem, no register auto save/restore support, + * need driver to do that explicitly for every D3 case. + */ + ret = thc_i2c_subip_regs_save(qcdev->thc_hw); + if (ret) + return ret; + + ret = thc_interrupt_quiesce(qcdev->thc_hw, true); + if (ret) + return ret; + + thc_interrupt_enable(qcdev->thc_hw, false); + + thc_dma_unconfigure(qcdev->thc_hw); + + return 0; +} + +static int quicki2c_resume(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quicki2c_device *qcdev; + int ret; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return -ENODEV; + + ret = thc_port_select(qcdev->thc_hw, THC_PORT_TYPE_I2C); + if (ret) + return ret; + + ret = thc_i2c_subip_regs_restore(qcdev->thc_hw); + if (ret) + return ret; + + thc_interrupt_config(qcdev->thc_hw); + + thc_interrupt_enable(qcdev->thc_hw, true); + + ret = thc_dma_configure(qcdev->thc_hw); + if (ret) + return ret; + + ret = thc_interrupt_quiesce(qcdev->thc_hw, false); + if (ret) + return ret; + + return 0; +} + +static int quicki2c_freeze(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quicki2c_device *qcdev; + int ret; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return -ENODEV; + + ret = thc_interrupt_quiesce(qcdev->thc_hw, true); + if (ret) + return ret; + + thc_interrupt_enable(qcdev->thc_hw, false); + + thc_dma_unconfigure(qcdev->thc_hw); + + return 0; +} + +static int quicki2c_thaw(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quicki2c_device *qcdev; + int ret; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return -ENODEV; + + ret = thc_dma_configure(qcdev->thc_hw); + if (ret) + return ret; + + thc_interrupt_enable(qcdev->thc_hw, true); + + ret = thc_interrupt_quiesce(qcdev->thc_hw, false); + if (ret) + return ret; + + return 0; +} + +static int quicki2c_poweroff(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quicki2c_device *qcdev; + int ret; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return -ENODEV; + + ret = thc_interrupt_quiesce(qcdev->thc_hw, true); + if (ret) + return ret; + + thc_interrupt_enable(qcdev->thc_hw, false); + + thc_ltr_unconfig(qcdev->thc_hw); + + quicki2c_dma_deinit(qcdev); + + return 0; +} + +static int quicki2c_restore(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quicki2c_device *qcdev; + int ret; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return -ENODEV; + + /* Reconfig THC HW when back from hibernate */ + ret = thc_port_select(qcdev->thc_hw, THC_PORT_TYPE_I2C); + if (ret) + return ret; + + ret = thc_i2c_subip_init(qcdev->thc_hw, qcdev->i2c_slave_addr, + qcdev->i2c_speed_mode, + qcdev->i2c_clock_hcnt, + qcdev->i2c_clock_lcnt); + if (ret) + return ret; + + thc_interrupt_config(qcdev->thc_hw); + + thc_interrupt_enable(qcdev->thc_hw, true); + + ret = thc_interrupt_quiesce(qcdev->thc_hw, false); + if (ret) + return ret; + + ret = thc_dma_configure(qcdev->thc_hw); + if (ret) + return ret; + + thc_ltr_config(qcdev->thc_hw, + qcdev->active_ltr_val, + qcdev->low_power_ltr_val); + + thc_change_ltr_mode(qcdev->thc_hw, THC_LTR_MODE_ACTIVE); + + return 0; +} + +static int quicki2c_runtime_suspend(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quicki2c_device *qcdev; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return -ENODEV; + + thc_change_ltr_mode(qcdev->thc_hw, THC_LTR_MODE_LP); + + pci_save_state(pdev); + + return 0; +} + +static int quicki2c_runtime_resume(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quicki2c_device *qcdev; + + qcdev = pci_get_drvdata(pdev); + if (!qcdev) + return -ENODEV; + + thc_change_ltr_mode(qcdev->thc_hw, THC_LTR_MODE_ACTIVE); + + return 0; +} + +static const struct dev_pm_ops quicki2c_pm_ops = { + .suspend = quicki2c_suspend, + .resume = quicki2c_resume, + .freeze = quicki2c_freeze, + .thaw = quicki2c_thaw, + .poweroff = quicki2c_poweroff, + .restore = quicki2c_restore, + .runtime_suspend = quicki2c_runtime_suspend, + .runtime_resume = quicki2c_runtime_resume, + .runtime_idle = NULL, +}; + +static const struct pci_device_id quicki2c_pci_tbl[] = { + {PCI_VDEVICE(INTEL, THC_LNL_DEVICE_ID_I2C_PORT1), }, + {PCI_VDEVICE(INTEL, THC_LNL_DEVICE_ID_I2C_PORT2), }, + {PCI_VDEVICE(INTEL, THC_PTL_H_DEVICE_ID_I2C_PORT1), }, + {PCI_VDEVICE(INTEL, THC_PTL_H_DEVICE_ID_I2C_PORT2), }, + {PCI_VDEVICE(INTEL, THC_PTL_U_DEVICE_ID_I2C_PORT1), }, + {PCI_VDEVICE(INTEL, THC_PTL_U_DEVICE_ID_I2C_PORT2), }, + {} +}; +MODULE_DEVICE_TABLE(pci, quicki2c_pci_tbl); + +static struct pci_driver quicki2c_driver = { + .name = KBUILD_MODNAME, + .id_table = quicki2c_pci_tbl, + .probe = quicki2c_probe, + .remove = quicki2c_remove, + .shutdown = quicki2c_shutdown, + .driver.pm = &quicki2c_pm_ops, + .driver.probe_type = PROBE_PREFER_ASYNCHRONOUS, +}; + +module_pci_driver(quicki2c_driver); + +MODULE_AUTHOR("Xinpeng Sun "); +MODULE_AUTHOR("Even Xu "); + +MODULE_DESCRIPTION("Intel(R) QuickI2C Driver"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS("INTEL_THC"); diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h new file mode 100644 index 000000000000..6ddb584bd611 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h @@ -0,0 +1,186 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#ifndef _QUICKI2C_DEV_H_ +#define _QUICKI2C_DEV_H_ + +#include +#include + +#define THC_LNL_DEVICE_ID_I2C_PORT1 0xA848 +#define THC_LNL_DEVICE_ID_I2C_PORT2 0xA84A +#define THC_PTL_H_DEVICE_ID_I2C_PORT1 0xE348 +#define THC_PTL_H_DEVICE_ID_I2C_PORT2 0xE34A +#define THC_PTL_U_DEVICE_ID_I2C_PORT1 0xE448 +#define THC_PTL_U_DEVICE_ID_I2C_PORT2 0xE44A + +/* Packet size value, the unit is 16 bytes */ +#define MAX_PACKET_SIZE_VALUE_LNL 256 + +/* HIDI2C special ACPI parameters DSD name */ +#define QUICKI2C_ACPI_METHOD_NAME_ICRS "ICRS" +#define QUICKI2C_ACPI_METHOD_NAME_ISUB "ISUB" + +/* HIDI2C special ACPI parameters DSM methods */ +#define QUICKI2C_ACPI_REVISION_NUM 1 +#define QUICKI2C_ACPI_FUNC_NUM_HID_DESC_ADDR 1 +#define QUICKI2C_ACPI_FUNC_NUM_ACTIVE_LTR_VAL 1 +#define QUICKI2C_ACPI_FUNC_NUM_LP_LTR_VAL 2 + +#define QUICKI2C_SUBIP_STANDARD_MODE_MAX_SPEED 100000 +#define QUICKI2C_SUBIP_FAST_MODE_MAX_SPEED 400000 +#define QUICKI2C_SUBIP_FASTPLUS_MODE_MAX_SPEED 1000000 +#define QUICKI2C_SUBIP_HIGH_SPEED_MODE_MAX_SPEED 3400000 + +#define QUICKI2C_DEFAULT_ACTIVE_LTR_VALUE 5 +#define QUICKI2C_DEFAULT_LP_LTR_VALUE 500 +#define QUICKI2C_RPM_TIMEOUT_MS 500 + +/* + * THC uses runtime auto suspend to dynamically switch between THC active LTR + * and low power LTR to save CPU power. + * Default value is 5000ms, that means if no touch event in this time, THC will + * change to low power LTR mode. + */ +#define DEFAULT_AUTO_SUSPEND_DELAY_MS 5000 + +enum quicki2c_dev_state { + QUICKI2C_NONE, + QUICKI2C_RESETING, + QUICKI2C_RESETED, + QUICKI2C_INITED, + QUICKI2C_ENABLED, + QUICKI2C_DISABLED, +}; + +enum { + HIDI2C_ADDRESSING_MODE_7BIT, + HIDI2C_ADDRESSING_MODE_10BIT, +}; + +/** + * struct quicki2c_subip_acpi_parameter - QuickI2C ACPI DSD parameters + * @device_address: I2C device slave address + * @connection_speed: I2C device expected connection speed + * @addressing_mode: I2C device slave address mode, 7bit or 10bit + * + * Those properties get from QUICKI2C_ACPI_METHOD_NAME_ICRS method, used for + * Bus parameter. + */ +struct quicki2c_subip_acpi_parameter { + u16 device_address; + u64 connection_speed; + u8 addressing_mode; +} __packed; + +/** + * struct quicki2c_subip_acpi_config - QuickI2C ACPI DSD parameters + * @SMHX: Standard Mode (100 kbit/s) Serial Clock Line HIGH Period + * @SMLX: Standard Mode (100 kbit/s) Serial Clock Line LOW Period + * @SMTD: Standard Mode (100 kbit/s) Serial Data Line Transmit Hold Period + * @SMRD: Standard Mode (100 kbit/s) Serial Data Receive Hold Period + * @FMHX: Fast Mode (400 kbit/s) Serial Clock Line HIGH Period + * @FMLX: Fast Mode (400 kbit/s) Serial Clock Line LOW Period + * @FMTD: Fast Mode (400 kbit/s) Serial Data Line Transmit Hold Period + * @FMRD: Fast Mode (400 kbit/s) Serial Data Line Receive Hold Period + * @FMSL: Maximum length (in ic_clk_cycles) of suppressed spikes + * in Standard Mode, Fast Mode and Fast Mode Plus + * @FPHX: Fast Mode Plus (1Mbit/sec) Serial Clock Line HIGH Period + * @FPLX: Fast Mode Plus (1Mbit/sec) Serial Clock Line LOW Period + * @FPTD: Fast Mode Plus (1Mbit/sec) Serial Data Line Transmit HOLD Period + * @FPRD: Fast Mode Plus (1Mbit/sec) Serial Data Line Receive HOLD Period + * @HMHX: High Speed Mode Plus (3.4Mbits/sec) Serial Clock Line HIGH Period + * @HMLX: High Speed Mode Plus (3.4Mbits/sec) Serial Clock Line LOW Period + * @HMTD: High Speed Mode Plus (3.4Mbits/sec) Serial Data Line Transmit HOLD Period + * @HMRD: High Speed Mode Plus (3.4Mbits/sec) Serial Data Line Receive HOLD Period + * @HMSL: Maximum length (in ic_clk_cycles) of suppressed spikes in High Speed Mode + * + * Those properties get from QUICKI2C_ACPI_METHOD_NAME_ISUB method, used for + * I2C timing configure. + */ +struct quicki2c_subip_acpi_config { + u64 SMHX; + u64 SMLX; + u64 SMTD; + u64 SMRD; + + u64 FMHX; + u64 FMLX; + u64 FMTD; + u64 FMRD; + u64 FMSL; + + u64 FPHX; + u64 FPLX; + u64 FPTD; + u64 FPRD; + + u64 HMHX; + u64 HMLX; + u64 HMTD; + u64 HMRD; + u64 HMSL; +}; + +struct device; +struct pci_dev; +struct thc_device; +struct hid_device; +struct acpi_device; + +/** + * struct quicki2c_device - THC QuickI2C device struct + * @dev: point to kernel device + * @pdev: point to PCI device + * @thc_hw: point to THC device + * @hid_dev: point to hid device + * @acpi_dev: point to ACPI device + * @driver_data: point to quicki2c specific driver data + * @state: THC I2C device state + * @mem_addr: MMIO memory address + * @dev_desc: device descriptor for HIDI2C protocol + * @i2c_slave_addr: HIDI2C device slave address + * @hid_desc_addr: Register address for retrieve HID device descriptor + * @active_ltr_val: THC active LTR value + * @low_power_ltr_val: THC low power LTR value + * @i2c_speed_mode: 0 - standard mode, 1 - fast mode, 2 - fast mode plus + * @i2c_clock_hcnt: I2C CLK high period time (unit in cycle count) + * @i2c_clock_lcnt: I2C CLK low period time (unit in cycle count) + * @report_descriptor: store a copy of device report descriptor + * @input_buf: store a copy of latest input report data + * @report_buf: store a copy of latest input/output report packet from set/get feature + * @report_len: the length of input/output report packet + * @reset_ack_wq: workqueue for waiting reset response from device + * @reset_ack: indicate reset response received or not + */ +struct quicki2c_device { + struct device *dev; + struct pci_dev *pdev; + struct thc_device *thc_hw; + struct hid_device *hid_dev; + struct acpi_device *acpi_dev; + enum quicki2c_dev_state state; + + void __iomem *mem_addr; + + struct hidi2c_dev_descriptor dev_desc; + u8 i2c_slave_addr; + u16 hid_desc_addr; + + u32 active_ltr_val; + u32 low_power_ltr_val; + + u32 i2c_speed_mode; + u32 i2c_clock_hcnt; + u32 i2c_clock_lcnt; + + u8 *report_descriptor; + u8 *input_buf; + u8 *report_buf; + u32 report_len; + + wait_queue_head_t reset_ack_wq; + bool reset_ack; +}; + +#endif /* _QUICKI2C_DEV_H_ */ diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c new file mode 100644 index 000000000000..5c3ec95bb3fd --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#include +#include +#include + +#include "quicki2c-dev.h" +#include "quicki2c-hid.h" +#include "quicki2c-protocol.h" + +/** + * quicki2c_hid_parse() - HID core parse() callback + * + * @hid: HID device instance + * + * This function gets called during call to hid_add_device + * + * Return: 0 on success and non zero on error. + */ +static int quicki2c_hid_parse(struct hid_device *hid) +{ + struct quicki2c_device *qcdev = hid->driver_data; + + if (qcdev->report_descriptor) + return hid_parse_report(hid, qcdev->report_descriptor, + le16_to_cpu(qcdev->dev_desc.report_desc_len)); + + dev_err_once(qcdev->dev, "invalid report descriptor\n"); + return -EINVAL; +} + +static int quicki2c_hid_start(struct hid_device *hid) +{ + return 0; +} + +static void quicki2c_hid_stop(struct hid_device *hid) +{ +} + +static int quicki2c_hid_open(struct hid_device *hid) +{ + return 0; +} + +static void quicki2c_hid_close(struct hid_device *hid) +{ +} + +static int quicki2c_hid_raw_request(struct hid_device *hid, + unsigned char reportnum, + __u8 *buf, size_t len, + unsigned char rtype, int reqtype) +{ + struct quicki2c_device *qcdev = hid->driver_data; + int ret = 0; + + ret = pm_runtime_resume_and_get(qcdev->dev); + if (ret) + return ret; + + switch (reqtype) { + case HID_REQ_GET_REPORT: + ret = quicki2c_get_report(qcdev, rtype, reportnum, buf, len); + break; + case HID_REQ_SET_REPORT: + ret = quicki2c_set_report(qcdev, rtype, reportnum, buf, len); + break; + default: + dev_err(qcdev->dev, "Not supported request type %d\n", reqtype); + break; + } + + pm_runtime_mark_last_busy(qcdev->dev); + pm_runtime_put_autosuspend(qcdev->dev); + + return ret; +} + +static int quicki2c_hid_power(struct hid_device *hid, int lvl) +{ + return 0; +} + +static struct hid_ll_driver quicki2c_hid_ll_driver = { + .parse = quicki2c_hid_parse, + .start = quicki2c_hid_start, + .stop = quicki2c_hid_stop, + .open = quicki2c_hid_open, + .close = quicki2c_hid_close, + .power = quicki2c_hid_power, + .raw_request = quicki2c_hid_raw_request, +}; + +/** + * quicki2c_hid_probe() - Register HID low level driver + * + * @qcdev: point to quicki2c device + * + * This function is used to allocate and add HID device. + * + * Return: 0 on success, non zero on error. + */ +int quicki2c_hid_probe(struct quicki2c_device *qcdev) +{ + struct hid_device *hid; + int ret; + + hid = hid_allocate_device(); + if (IS_ERR(hid)) + return PTR_ERR(hid); + + hid->ll_driver = &quicki2c_hid_ll_driver; + hid->bus = BUS_PCI; + hid->dev.parent = qcdev->dev; + hid->driver_data = qcdev; + hid->version = le16_to_cpu(qcdev->dev_desc.version_id); + hid->vendor = le16_to_cpu(qcdev->dev_desc.vendor_id); + hid->product = le16_to_cpu(qcdev->dev_desc.product_id); + snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", "quicki2c-hid", + hid->vendor, hid->product); + + ret = hid_add_device(hid); + if (ret) { + hid_destroy_device(hid); + return ret; + } + + qcdev->hid_dev = hid; + + return 0; +} + +/** + * quicki2c_hid_remove() - Destroy HID device + * + * @qcdev: point to quicki2c device + * + * Return: 0 on success, non zero on error. + */ +void quicki2c_hid_remove(struct quicki2c_device *qcdev) +{ + hid_destroy_device(qcdev->hid_dev); +} + +/** + * quicki2c_hid_send_report() - Send HID input report data to HID core + * + * @qcdev: point to quicki2c device + * @data: point to input report data buffer + * @data_len: the length of input report data + * + * Return: 0 on success, non zero on error. + */ +int quicki2c_hid_send_report(struct quicki2c_device *qcdev, + void *data, size_t data_len) +{ + int ret; + + ret = hid_input_report(qcdev->hid_dev, HID_INPUT_REPORT, data, data_len, 1); + if (ret) + dev_err(qcdev->dev, "Failed to send HID input report, ret = %d.\n", ret); + + return ret; +} diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.h b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.h new file mode 100644 index 000000000000..e80df5f339fe --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#ifndef _QUICKI2C_HID_H_ +#define _QUICKI2C_HID_H_ + +struct quicki2c_device; + +int quicki2c_hid_send_report(struct quicki2c_device *qcdev, + void *data, size_t data_size); +int quicki2c_hid_probe(struct quicki2c_device *qcdev); +void quicki2c_hid_remove(struct quicki2c_device *qcdev); + +#endif /* _QUICKI2C_HID_H_ */ diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c new file mode 100644 index 000000000000..f493df0d5dc4 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c @@ -0,0 +1,224 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2024 Intel Corporation */ + +#include +#include +#include + +#include "intel-thc-dev.h" +#include "intel-thc-dma.h" + +#include "quicki2c-dev.h" +#include "quicki2c-hid.h" +#include "quicki2c-protocol.h" + +static int quicki2c_init_write_buf(struct quicki2c_device *qcdev, u32 cmd, int cmd_len, + bool append_data_reg, u8 *data, int data_len, + u8 *write_buf, int write_buf_len) +{ + int buf_len, offset = 0; + + buf_len = HIDI2C_REG_LEN + cmd_len; + + if (append_data_reg) + buf_len += HIDI2C_REG_LEN; + + if (data && data_len) + buf_len += data_len + HIDI2C_LENGTH_LEN; + + if (buf_len > write_buf_len) + return -EINVAL; + + memcpy(write_buf, &qcdev->dev_desc.cmd_reg, HIDI2C_REG_LEN); + offset += HIDI2C_REG_LEN; + memcpy(write_buf + offset, &cmd, cmd_len); + offset += cmd_len; + + if (append_data_reg) { + memcpy(write_buf + offset, &qcdev->dev_desc.data_reg, HIDI2C_REG_LEN); + offset += HIDI2C_REG_LEN; + } + + if (data && data_len) { + __le16 len = cpu_to_le16(data_len + HIDI2C_LENGTH_LEN); + + memcpy(write_buf + offset, &len, HIDI2C_LENGTH_LEN); + offset += HIDI2C_LENGTH_LEN; + memcpy(write_buf + offset, data, data_len); + } + + return buf_len; +} + +static int quicki2c_encode_cmd(struct quicki2c_device *qcdev, u32 *cmd_buf, + u8 opcode, u8 report_type, u8 report_id) +{ + int cmd_len; + + *cmd_buf = FIELD_PREP(HIDI2C_CMD_OPCODE, opcode) | + FIELD_PREP(HIDI2C_CMD_REPORT_TYPE, report_type); + + if (report_id < HIDI2C_CMD_MAX_RI) { + *cmd_buf |= FIELD_PREP(HIDI2C_CMD_REPORT_ID, report_id); + cmd_len = HIDI2C_CMD_LEN; + } else { + *cmd_buf |= FIELD_PREP(HIDI2C_CMD_REPORT_ID, HIDI2C_CMD_MAX_RI) | + FIELD_PREP(HIDI2C_CMD_3RD_BYTE, report_id); + cmd_len = HIDI2C_CMD_LEN_OPT; + } + + return cmd_len; +} + +static int write_cmd_to_txdma(struct quicki2c_device *qcdev, int opcode, + int report_type, int report_id, u8 *buf, int buf_len) +{ + size_t write_buf_len; + int cmd_len, ret; + u32 cmd; + + cmd_len = quicki2c_encode_cmd(qcdev, &cmd, opcode, report_type, report_id); + + ret = quicki2c_init_write_buf(qcdev, cmd, cmd_len, buf ? true : false, buf, + buf_len, qcdev->report_buf, qcdev->report_len); + if (ret < 0) + return ret; + + write_buf_len = ret; + + return thc_dma_write(qcdev->thc_hw, qcdev->report_buf, write_buf_len); +} + +int quicki2c_set_power(struct quicki2c_device *qcdev, enum hidi2c_power_state power_state) +{ + return write_cmd_to_txdma(qcdev, HIDI2C_SET_POWER, HIDI2C_RESERVED, power_state, NULL, 0); +} + +int quicki2c_get_device_descriptor(struct quicki2c_device *qcdev) +{ + u32 read_len = 0; + int ret; + + ret = thc_tic_pio_write_and_read(qcdev->thc_hw, qcdev->hid_desc_addr, + HIDI2C_REG_LEN, NULL, HIDI2C_DEV_DESC_LEN, + &read_len, (u32 *)&qcdev->dev_desc); + if (ret || HIDI2C_DEV_DESC_LEN != read_len) { + dev_err_once(qcdev->dev, "Get device descriptor failed, ret %d, read len %u\n", + ret, read_len); + return -EIO; + } + + if (le16_to_cpu(qcdev->dev_desc.bcd_ver) != HIDI2C_HID_DESC_BCDVERSION) + return -EOPNOTSUPP; + + return 0; +} + +int quicki2c_get_report_descriptor(struct quicki2c_device *qcdev) +{ + u16 desc_reg = le16_to_cpu(qcdev->dev_desc.report_desc_reg); + size_t read_len = le16_to_cpu(qcdev->dev_desc.report_desc_len); + u32 prd_len = read_len; + + return thc_swdma_read(qcdev->thc_hw, (u8 *)&desc_reg, HIDI2C_REG_LEN, + &prd_len, qcdev->report_descriptor, &read_len); +} + +int quicki2c_get_report(struct quicki2c_device *qcdev, u8 report_type, + unsigned int reportnum, void *buf, u32 buf_len) +{ + struct hidi2c_report_packet *rpt; + size_t write_buf_len, read_len = 0; + int cmd_len, rep_type; + u32 cmd; + int ret; + + if (report_type == HID_INPUT_REPORT) { + rep_type = HIDI2C_INPUT; + } else if (report_type == HID_FEATURE_REPORT) { + rep_type = HIDI2C_FEATURE; + } else { + dev_err(qcdev->dev, "Unsupported report type for GET REPORT: %d\n", report_type); + return -EINVAL; + } + + cmd_len = quicki2c_encode_cmd(qcdev, &cmd, HIDI2C_GET_REPORT, rep_type, reportnum); + + ret = quicki2c_init_write_buf(qcdev, cmd, cmd_len, true, NULL, 0, + qcdev->report_buf, qcdev->report_len); + if (ret < 0) + return ret; + + write_buf_len = ret; + + rpt = (struct hidi2c_report_packet *)qcdev->input_buf; + + ret = thc_swdma_read(qcdev->thc_hw, qcdev->report_buf, write_buf_len, + NULL, rpt, &read_len); + if (ret) { + dev_err_once(qcdev->dev, "Get report failed, ret %d, read len (%zu vs %d)\n", + ret, read_len, buf_len); + return ret; + } + + if (HIDI2C_DATA_LEN(le16_to_cpu(rpt->len)) != buf_len || rpt->data[0] != reportnum) { + dev_err_once(qcdev->dev, "Invalid packet, len (%d vs %d) report id (%d vs %d)\n", + le16_to_cpu(rpt->len), buf_len, rpt->data[0], reportnum); + return -EINVAL; + } + + memcpy(buf, rpt->data, buf_len); + + return buf_len; +} + +int quicki2c_set_report(struct quicki2c_device *qcdev, u8 report_type, + unsigned int reportnum, void *buf, u32 buf_len) +{ + int rep_type; + int ret; + + if (report_type == HID_OUTPUT_REPORT) { + rep_type = HIDI2C_OUTPUT; + } else if (report_type == HID_FEATURE_REPORT) { + rep_type = HIDI2C_FEATURE; + } else { + dev_err(qcdev->dev, "Unsupported report type for SET REPORT: %d\n", report_type); + return -EINVAL; + } + + ret = write_cmd_to_txdma(qcdev, HIDI2C_SET_REPORT, rep_type, reportnum, buf, buf_len); + if (ret) { + dev_err_once(qcdev->dev, "Set Report failed, ret %d\n", ret); + return ret; + } + + return buf_len; +} + +#define HIDI2C_RESET_TIMEOUT 5 + +int quicki2c_reset(struct quicki2c_device *qcdev) +{ + int ret; + + qcdev->reset_ack = false; + qcdev->state = QUICKI2C_RESETING; + + ret = write_cmd_to_txdma(qcdev, HIDI2C_RESET, HIDI2C_RESERVED, 0, NULL, 0); + if (ret) { + dev_err_once(qcdev->dev, "Send reset command failed, ret %d\n", ret); + return ret; + } + + ret = wait_event_interruptible_timeout(qcdev->reset_ack_wq, qcdev->reset_ack, + HIDI2C_RESET_TIMEOUT * HZ); + if (ret <= 0 || !qcdev->reset_ack) { + dev_err_once(qcdev->dev, + "Wait reset response timed out ret:%d timeout:%ds\n", + ret, HIDI2C_RESET_TIMEOUT); + return -ETIMEDOUT; + } + + return 0; +} diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.h b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.h new file mode 100644 index 000000000000..bf4908cce59c --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#ifndef _QUICKI2C_PROTOCOL_H_ +#define _QUICKI2C_PROTOCOL_H_ + +#include + +struct quicki2c_device; + +int quicki2c_set_power(struct quicki2c_device *qcdev, enum hidi2c_power_state power_state); +int quicki2c_get_report(struct quicki2c_device *qcdev, u8 report_type, + unsigned int reportnum, void *buf, u32 buf_len); +int quicki2c_set_report(struct quicki2c_device *qcdev, u8 report_type, + unsigned int reportnum, void *buf, u32 buf_len); +int quicki2c_get_device_descriptor(struct quicki2c_device *qcdev); +int quicki2c_get_report_descriptor(struct quicki2c_device *qcdev); +int quicki2c_reset(struct quicki2c_device *qcdev); + +#endif /* _QUICKI2C_PROTOCOL_H_ */ diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c new file mode 100644 index 000000000000..4641e818dfa4 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c @@ -0,0 +1,987 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "intel-thc-dev.h" +#include "intel-thc-hw.h" + +#include "quickspi-dev.h" +#include "quickspi-hid.h" +#include "quickspi-protocol.h" + +struct quickspi_driver_data mtl = { + .max_packet_size_value = MAX_PACKET_SIZE_VALUE_MTL, +}; + +struct quickspi_driver_data lnl = { + .max_packet_size_value = MAX_PACKET_SIZE_VALUE_LNL, +}; + +struct quickspi_driver_data ptl = { + .max_packet_size_value = MAX_PACKET_SIZE_VALUE_LNL, +}; + +/* THC QuickSPI ACPI method to get device properties */ +/* HIDSPI Method: {6e2ac436-0fcf-41af-a265-b32a220dcfab} */ +static guid_t hidspi_guid = + GUID_INIT(0x6e2ac436, 0x0fcf, 0x41af, 0xa2, 0x65, 0xb3, 0x2a, + 0x22, 0x0d, 0xcf, 0xab); + +/* QuickSpi Method: {300D35b7-ac20-413e-8e9c-92e4dafd0afe} */ +static guid_t thc_quickspi_guid = + GUID_INIT(0x300d35b7, 0xac20, 0x413e, 0x8e, 0x9c, 0x92, 0xe4, + 0xda, 0xfd, 0x0a, 0xfe); + +/* Platform Method: {84005682-5b71-41a4-0x8d668130f787a138} */ +static guid_t thc_platform_guid = + GUID_INIT(0x84005682, 0x5b71, 0x41a4, 0x8d, 0x66, 0x81, 0x30, + 0xf7, 0x87, 0xa1, 0x38); + +/** + * thc_acpi_get_property - Query device ACPI parameter + * + * @adev: point to ACPI device + * @guid: ACPI method's guid + * @rev: ACPI method's revision + * @func: ACPI method's function number + * @type: ACPI parameter's data type + * @prop_buf: point to return buffer + * + * This is a helper function for device to query its ACPI parameters. + * + * Return: 0 if successful or ENODEV on failed. + */ +static int thc_acpi_get_property(struct acpi_device *adev, const guid_t *guid, + u64 rev, u64 func, acpi_object_type type, void *prop_buf) +{ + acpi_handle handle = acpi_device_handle(adev); + union acpi_object *obj; + + obj = acpi_evaluate_dsm_typed(handle, guid, rev, func, NULL, type); + if (!obj) { + acpi_handle_err(handle, + "Error _DSM call failed, rev: %llu, func: %llu, type: %u\n", + rev, func, type); + return -ENODEV; + } + + if (type == ACPI_TYPE_INTEGER) + *(u32 *)prop_buf = (u32)obj->integer.value; + else if (type == ACPI_TYPE_BUFFER) + memcpy(prop_buf, obj->buffer.pointer, obj->buffer.length); + + ACPI_FREE(obj); + + return 0; +} + +/** + * quickspi_get_acpi_resources - Query all quickspi devices' ACPI parameters + * + * @qsdev: point to quickspi device + * + * This function gets all quickspi devices' ACPI resource. + * + * Return: 0 if successful or error code on failed. + */ +static int quickspi_get_acpi_resources(struct quickspi_device *qsdev) +{ + struct acpi_device *adev = ACPI_COMPANION(qsdev->dev); + int ret = -EINVAL; + + if (!adev) { + dev_err(qsdev->dev, "no valid ACPI companion\n"); + return ret; + } + + qsdev->acpi_dev = adev; + + ret = thc_acpi_get_property(adev, &hidspi_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_INPUT_REP_HDR_ADDR, + ACPI_TYPE_INTEGER, + &qsdev->input_report_hdr_addr); + if (ret) + return ret; + + ret = thc_acpi_get_property(adev, &hidspi_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_INPUT_REP_BDY_ADDR, + ACPI_TYPE_INTEGER, + &qsdev->input_report_bdy_addr); + if (ret) + return ret; + + ret = thc_acpi_get_property(adev, &hidspi_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_OUTPUT_REP_ADDR, + ACPI_TYPE_INTEGER, + &qsdev->output_report_addr); + if (ret) + return ret; + + ret = thc_acpi_get_property(adev, &hidspi_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_READ_OPCODE, + ACPI_TYPE_BUFFER, + &qsdev->spi_read_opcode); + if (ret) + return ret; + + ret = thc_acpi_get_property(adev, &hidspi_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_WRITE_OPCODE, + ACPI_TYPE_BUFFER, + &qsdev->spi_write_opcode); + if (ret) + return ret; + + ret = thc_acpi_get_property(adev, &hidspi_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_IO_MODE, + ACPI_TYPE_INTEGER, + &qsdev->spi_read_io_mode); + if (ret) + return ret; + + if (qsdev->spi_read_io_mode & SPI_WRITE_IO_MODE) + qsdev->spi_write_io_mode = FIELD_GET(SPI_IO_MODE_OPCODE, qsdev->spi_read_io_mode); + else + qsdev->spi_write_io_mode = THC_SINGLE_IO; + + qsdev->spi_read_io_mode = FIELD_GET(SPI_IO_MODE_OPCODE, qsdev->spi_read_io_mode); + + ret = thc_acpi_get_property(adev, &thc_quickspi_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_CONNECTION_SPEED, + ACPI_TYPE_INTEGER, + &qsdev->spi_freq_val); + if (ret) + return ret; + + ret = thc_acpi_get_property(adev, &thc_quickspi_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_LIMIT_PACKET_SIZE, + ACPI_TYPE_INTEGER, + &qsdev->limit_packet_size); + if (ret) + return ret; + + if (qsdev->limit_packet_size || !qsdev->driver_data) + qsdev->spi_packet_size = DEFAULT_MIN_PACKET_SIZE_VALUE; + else + qsdev->spi_packet_size = qsdev->driver_data->max_packet_size_value; + + ret = thc_acpi_get_property(adev, &thc_quickspi_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_PERFORMANCE_LIMIT, + ACPI_TYPE_INTEGER, + &qsdev->performance_limit); + if (ret) + return ret; + + qsdev->performance_limit = FIELD_GET(PERFORMANCE_LIMITATION, qsdev->performance_limit); + + ret = thc_acpi_get_property(adev, &thc_platform_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_ACTIVE_LTR, + ACPI_TYPE_INTEGER, + &qsdev->active_ltr_val); + if (ret) + return ret; + + ret = thc_acpi_get_property(adev, &thc_platform_guid, + ACPI_QUICKSPI_REVISION_NUM, + ACPI_QUICKSPI_FUNC_NUM_LP_LTR, + ACPI_TYPE_INTEGER, + &qsdev->low_power_ltr_val); + if (ret) + return ret; + + return 0; +} + +/** + * quickspi_irq_quick_handler - The ISR of the quickspi driver + * + * @irq: The irq number + * @dev_id: pointer to the device structure + * + * Return: IRQ_WAKE_THREAD if further process needed. + */ +static irqreturn_t quickspi_irq_quick_handler(int irq, void *dev_id) +{ + struct quickspi_device *qsdev = dev_id; + + if (qsdev->state == QUICKSPI_DISABLED) + return IRQ_HANDLED; + + /* Disable THC interrupt before current interrupt be handled */ + thc_interrupt_enable(qsdev->thc_hw, false); + + return IRQ_WAKE_THREAD; +} + +/** + * try_recover - Try to recovery THC and Device + * @qsdev: pointer to quickspi device + * + * This function is a error handler, called when fatal error happens. + * It try to reset Touch Device and re-configure THC to recovery + * transferring between Device and THC. + * + * Return: 0 if successful or error code on failed. + */ +static int try_recover(struct quickspi_device *qsdev) +{ + int ret; + + ret = reset_tic(qsdev); + if (ret) { + dev_err(qsdev->dev, "Reset touch device failed, ret = %d\n", ret); + return ret; + } + + thc_dma_unconfigure(qsdev->thc_hw); + + ret = thc_dma_configure(qsdev->thc_hw); + if (ret) { + dev_err(qsdev->dev, "Re-configure THC DMA failed, ret = %d\n", ret); + return ret; + } + + return 0; +} + +/** + * quickspi_irq_thread_handler - IRQ thread handler of quickspi driver + * + * @irq: The IRQ number + * @dev_id: pointer to the quickspi device structure + * + * Return: IRQ_HANDLED to finish this handler. + */ +static irqreturn_t quickspi_irq_thread_handler(int irq, void *dev_id) +{ + struct quickspi_device *qsdev = dev_id; + size_t input_len; + int read_finished = 0; + int err_recover = 0; + int int_mask; + int ret; + + if (qsdev->state == QUICKSPI_DISABLED) + return IRQ_HANDLED; + + ret = pm_runtime_resume_and_get(qsdev->dev); + if (ret) + return IRQ_HANDLED; + + int_mask = thc_interrupt_handler(qsdev->thc_hw); + + if (int_mask & BIT(THC_FATAL_ERR_INT) || int_mask & BIT(THC_TXN_ERR_INT)) { + err_recover = 1; + goto end; + } + + if (int_mask & BIT(THC_NONDMA_INT)) { + if (qsdev->state == QUICKSPI_RESETING) { + qsdev->reset_ack = true; + wake_up_interruptible(&qsdev->reset_ack_wq); + } else { + qsdev->nondma_int_received = true; + wake_up_interruptible(&qsdev->nondma_int_received_wq); + } + } + + if (int_mask & BIT(THC_RXDMA2_INT)) { + while (!read_finished) { + ret = thc_rxdma_read(qsdev->thc_hw, THC_RXDMA2, qsdev->input_buf, + &input_len, &read_finished); + if (ret) { + err_recover = 1; + goto end; + } + + quickspi_handle_input_data(qsdev, input_len); + } + } + +end: + thc_interrupt_enable(qsdev->thc_hw, true); + + if (err_recover) + if (try_recover(qsdev)) + qsdev->state = QUICKSPI_DISABLED; + + pm_runtime_mark_last_busy(qsdev->dev); + pm_runtime_put_autosuspend(qsdev->dev); + + return IRQ_HANDLED; +} + +/** + * quickspi_dev_init - Initialize quickspi device + * + * @pdev: pointer to the thc pci device + * @mem_addr: The pointer of MMIO memory address + * @id: point to pci_device_id structure + * + * Alloc quickspi device structure and initialized THC device, + * then configure THC to HIDSPI mode. + * + * If success, enable THC hardware interrupt. + * + * Return: pointer to the quickspi device structure if success + * or NULL on failed. + */ +static struct quickspi_device *quickspi_dev_init(struct pci_dev *pdev, void __iomem *mem_addr, + const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + struct quickspi_device *qsdev; + int ret; + + qsdev = devm_kzalloc(dev, sizeof(struct quickspi_device), GFP_KERNEL); + if (!qsdev) + return ERR_PTR(-ENOMEM); + + qsdev->pdev = pdev; + qsdev->dev = dev; + qsdev->mem_addr = mem_addr; + qsdev->state = QUICKSPI_DISABLED; + qsdev->driver_data = (struct quickspi_driver_data *)id->driver_data; + + init_waitqueue_head(&qsdev->reset_ack_wq); + init_waitqueue_head(&qsdev->nondma_int_received_wq); + init_waitqueue_head(&qsdev->report_desc_got_wq); + init_waitqueue_head(&qsdev->get_report_cmpl_wq); + init_waitqueue_head(&qsdev->set_report_cmpl_wq); + + /* thc hw init */ + qsdev->thc_hw = thc_dev_init(qsdev->dev, qsdev->mem_addr); + if (IS_ERR(qsdev->thc_hw)) { + ret = PTR_ERR(qsdev->thc_hw); + dev_err(dev, "Failed to initialize THC device context, ret = %d.\n", ret); + return ERR_PTR(ret); + } + + ret = thc_interrupt_quiesce(qsdev->thc_hw, true); + if (ret) + return ERR_PTR(ret); + + ret = thc_port_select(qsdev->thc_hw, THC_PORT_TYPE_SPI); + if (ret) { + dev_err(dev, "Failed to select THC port, ret = %d.\n", ret); + return ERR_PTR(ret); + } + + ret = quickspi_get_acpi_resources(qsdev); + if (ret) { + dev_err(dev, "Get ACPI resources failed, ret = %d\n", ret); + return ERR_PTR(ret); + } + + /* THC config for input/output address */ + thc_spi_input_output_address_config(qsdev->thc_hw, + qsdev->input_report_hdr_addr, + qsdev->input_report_bdy_addr, + qsdev->output_report_addr); + + /* THC config for spi read operation */ + ret = thc_spi_read_config(qsdev->thc_hw, qsdev->spi_freq_val, + qsdev->spi_read_io_mode, + qsdev->spi_read_opcode, + qsdev->spi_packet_size); + if (ret) { + dev_err(dev, "thc_spi_read_config failed, ret = %d\n", ret); + return ERR_PTR(ret); + } + + /* THC config for spi write operation */ + ret = thc_spi_write_config(qsdev->thc_hw, qsdev->spi_freq_val, + qsdev->spi_write_io_mode, + qsdev->spi_write_opcode, + qsdev->spi_packet_size, + qsdev->performance_limit); + if (ret) { + dev_err(dev, "thc_spi_write_config failed, ret = %d\n", ret); + return ERR_PTR(ret); + } + + thc_ltr_config(qsdev->thc_hw, + qsdev->active_ltr_val, + qsdev->low_power_ltr_val); + + thc_interrupt_config(qsdev->thc_hw); + + thc_interrupt_enable(qsdev->thc_hw, true); + + qsdev->state = QUICKSPI_INITED; + + return qsdev; +} + +/** + * quickspi_dev_deinit - De-initialize quickspi device + * + * @qsdev: pointer to the quickspi device structure + * + * Disable THC interrupt and deinitilize THC. + */ +static void quickspi_dev_deinit(struct quickspi_device *qsdev) +{ + thc_interrupt_enable(qsdev->thc_hw, false); + thc_ltr_unconfig(qsdev->thc_hw); + + qsdev->state = QUICKSPI_DISABLED; +} + +/** + * quickspi_dma_init - Configure THC DMA for quickspi device + * @qsdev: pointer to the quickspi device structure + * + * This function uses TIC's parameters(such as max input length, max output + * length) to allocate THC DMA buffers and configure THC DMA engines. + * + * Return: 0 if successful or error code on failed. + */ +static int quickspi_dma_init(struct quickspi_device *qsdev) +{ + int ret; + + ret = thc_dma_set_max_packet_sizes(qsdev->thc_hw, 0, + le16_to_cpu(qsdev->dev_desc.max_input_len), + le16_to_cpu(qsdev->dev_desc.max_output_len), + 0); + if (ret) + return ret; + + ret = thc_dma_allocate(qsdev->thc_hw); + if (ret) { + dev_err(qsdev->dev, "Allocate THC DMA buffer failed, ret = %d\n", ret); + return ret; + } + + /* Enable RxDMA */ + ret = thc_dma_configure(qsdev->thc_hw); + if (ret) { + dev_err(qsdev->dev, "Configure THC DMA failed, ret = %d\n", ret); + thc_dma_unconfigure(qsdev->thc_hw); + thc_dma_release(qsdev->thc_hw); + return ret; + } + + return ret; +} + +/** + * quickspi_dma_deinit - Release THC DMA for quickspi device + * @qsdev: pointer to the quickspi device structure + * + * Stop THC DMA engines and release all DMA buffers. + * + */ +static void quickspi_dma_deinit(struct quickspi_device *qsdev) +{ + thc_dma_unconfigure(qsdev->thc_hw); + thc_dma_release(qsdev->thc_hw); +} + +/** + * quickspi_alloc_report_buf - Alloc report buffers + * @qsdev: pointer to the quickspi device structure + * + * Allocate report descriptor buffer, it will be used for restore TIC HID + * report descriptor. + * + * Allocate input report buffer, it will be used for receive HID input report + * data from TIC. + * + * Allocate output report buffer, it will be used for store HID output report, + * such as set feature. + * + * Return: 0 if successful or error code on failed. + */ +static int quickspi_alloc_report_buf(struct quickspi_device *qsdev) +{ + size_t max_report_len; + size_t max_input_len; + + qsdev->report_descriptor = devm_kzalloc(qsdev->dev, + le16_to_cpu(qsdev->dev_desc.rep_desc_len), + GFP_KERNEL); + if (!qsdev->report_descriptor) + return -ENOMEM; + + max_input_len = max(le16_to_cpu(qsdev->dev_desc.rep_desc_len), + le16_to_cpu(qsdev->dev_desc.max_input_len)); + + qsdev->input_buf = devm_kzalloc(qsdev->dev, max_input_len, GFP_KERNEL); + if (!qsdev->input_buf) + return -ENOMEM; + + max_report_len = max(le16_to_cpu(qsdev->dev_desc.max_output_len), + le16_to_cpu(qsdev->dev_desc.max_input_len)); + + qsdev->report_buf = devm_kzalloc(qsdev->dev, max_report_len, GFP_KERNEL); + if (!qsdev->report_buf) + return -ENOMEM; + + return 0; +} + +/* + * quickspi_probe: Quickspi driver probe function + * + * @pdev: point to pci device + * @id: point to pci_device_id structure + * + * This function initializes THC and HIDSPI device, the flow is: + * - do THC pci device initialization + * - query HIDSPI ACPI parameters + * - configure THC to HIDSPI mode + * - go through HIDSPI enumeration flow + * |- reset HIDSPI device + * |- read device descriptor + * - enable THC interrupt and DMA + * - read report descriptor + * - register HID device + * - enable runtime power management + * + * Return 0 if success or error code on failure. + */ +static int quickspi_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct quickspi_device *qsdev; + void __iomem *mem_addr; + int ret; + + ret = pcim_enable_device(pdev); + if (ret) { + dev_err(&pdev->dev, "Failed to enable PCI device, ret = %d.\n", ret); + return ret; + } + + pci_set_master(pdev); + + ret = pcim_iomap_regions(pdev, BIT(0), KBUILD_MODNAME); + if (ret) { + dev_err(&pdev->dev, "Failed to get PCI regions, ret = %d.\n", ret); + goto disable_pci_device; + } + + mem_addr = pcim_iomap_table(pdev)[0]; + + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) { + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) { + dev_err(&pdev->dev, "No usable DMA configuration %d\n", ret); + goto unmap_io_region; + } + } + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + dev_err(&pdev->dev, + "Failed to allocate IRQ vectors. ret = %d\n", ret); + goto unmap_io_region; + } + + pdev->irq = pci_irq_vector(pdev, 0); + + qsdev = quickspi_dev_init(pdev, mem_addr, id); + if (IS_ERR(qsdev)) { + dev_err(&pdev->dev, "QuickSPI device init failed\n"); + ret = PTR_ERR(qsdev); + goto unmap_io_region; + } + + pci_set_drvdata(pdev, qsdev); + + ret = devm_request_threaded_irq(&pdev->dev, pdev->irq, + quickspi_irq_quick_handler, + quickspi_irq_thread_handler, + IRQF_ONESHOT, KBUILD_MODNAME, + qsdev); + if (ret) { + dev_err(&pdev->dev, + "Failed to request threaded IRQ, irq = %d.\n", pdev->irq); + goto dev_deinit; + } + + ret = reset_tic(qsdev); + if (ret) { + dev_err(&pdev->dev, "Reset Touch Device failed, ret = %d\n", ret); + goto dev_deinit; + } + + ret = quickspi_alloc_report_buf(qsdev); + if (ret) { + dev_err(&pdev->dev, "Alloc report buffers failed, ret= %d\n", ret); + goto dev_deinit; + } + + ret = quickspi_dma_init(qsdev); + if (ret) { + dev_err(&pdev->dev, "Setup THC DMA failed, ret= %d\n", ret); + goto dev_deinit; + } + + ret = quickspi_get_report_descriptor(qsdev); + if (ret) { + dev_err(&pdev->dev, "Get report descriptor failed, ret = %d\n", ret); + goto dma_deinit; + } + + ret = quickspi_hid_probe(qsdev); + if (ret) { + dev_err(&pdev->dev, "Failed to register HID device, ret = %d\n", ret); + goto dma_deinit; + } + + qsdev->state = QUICKSPI_ENABLED; + + /* Enable runtime power management */ + pm_runtime_use_autosuspend(qsdev->dev); + pm_runtime_set_autosuspend_delay(qsdev->dev, DEFAULT_AUTO_SUSPEND_DELAY_MS); + pm_runtime_mark_last_busy(qsdev->dev); + pm_runtime_put_noidle(qsdev->dev); + pm_runtime_put_autosuspend(qsdev->dev); + + dev_dbg(&pdev->dev, "QuickSPI probe success\n"); + + return 0; + +dma_deinit: + quickspi_dma_deinit(qsdev); +dev_deinit: + quickspi_dev_deinit(qsdev); +unmap_io_region: + pcim_iounmap_regions(pdev, BIT(0)); +disable_pci_device: + pci_clear_master(pdev); + + return ret; +} + +/** + * quickspi_remove - Device Removal Routine + * + * @pdev: PCI device structure + * + * This is called by the PCI subsystem to alert the driver + * that it should release a PCI device. + */ +static void quickspi_remove(struct pci_dev *pdev) +{ + struct quickspi_device *qsdev; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return; + + quickspi_hid_remove(qsdev); + quickspi_dma_deinit(qsdev); + + pm_runtime_get_noresume(qsdev->dev); + + quickspi_dev_deinit(qsdev); + + pcim_iounmap_regions(pdev, BIT(0)); + pci_clear_master(pdev); +} + +/** + * quickspi_shutdown - Device Shutdown Routine + * + * @pdev: PCI device structure + * + * This is called from the reboot notifier + * it's a simplified version of remove so we go down + * faster. + */ +static void quickspi_shutdown(struct pci_dev *pdev) +{ + struct quickspi_device *qsdev; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return; + + /* Must stop DMA before reboot to avoid DMA entering into unknown state */ + quickspi_dma_deinit(qsdev); + + quickspi_dev_deinit(qsdev); +} + +static int quickspi_suspend(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quickspi_device *qsdev; + int ret; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return -ENODEV; + + ret = quickspi_set_power(qsdev, HIDSPI_SLEEP); + if (ret) + return ret; + + ret = thc_interrupt_quiesce(qsdev->thc_hw, true); + if (ret) + return ret; + + thc_interrupt_enable(qsdev->thc_hw, false); + + thc_dma_unconfigure(qsdev->thc_hw); + + return 0; +} + +static int quickspi_resume(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quickspi_device *qsdev; + int ret; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return -ENODEV; + + ret = thc_port_select(qsdev->thc_hw, THC_PORT_TYPE_SPI); + if (ret) + return ret; + + thc_interrupt_config(qsdev->thc_hw); + + thc_interrupt_enable(qsdev->thc_hw, true); + + ret = thc_dma_configure(qsdev->thc_hw); + if (ret) + return ret; + + ret = thc_interrupt_quiesce(qsdev->thc_hw, false); + if (ret) + return ret; + + ret = quickspi_set_power(qsdev, HIDSPI_ON); + if (ret) + return ret; + + return 0; +} + +static int quickspi_freeze(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quickspi_device *qsdev; + int ret; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return -ENODEV; + + ret = thc_interrupt_quiesce(qsdev->thc_hw, true); + if (ret) + return ret; + + thc_interrupt_enable(qsdev->thc_hw, false); + + thc_dma_unconfigure(qsdev->thc_hw); + + return 0; +} + +static int quickspi_thaw(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quickspi_device *qsdev; + int ret; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return -ENODEV; + + ret = thc_dma_configure(qsdev->thc_hw); + if (ret) + return ret; + + thc_interrupt_enable(qsdev->thc_hw, true); + + ret = thc_interrupt_quiesce(qsdev->thc_hw, false); + if (ret) + return ret; + + return 0; +} + +static int quickspi_poweroff(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quickspi_device *qsdev; + int ret; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return -ENODEV; + + ret = thc_interrupt_quiesce(qsdev->thc_hw, true); + if (ret) + return ret; + + thc_interrupt_enable(qsdev->thc_hw, false); + + thc_ltr_unconfig(qsdev->thc_hw); + + quickspi_dma_deinit(qsdev); + + return 0; +} + +static int quickspi_restore(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quickspi_device *qsdev; + int ret; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return -ENODEV; + + ret = thc_interrupt_quiesce(qsdev->thc_hw, true); + if (ret) + return ret; + + /* Reconfig THC HW when back from hibernate */ + ret = thc_port_select(qsdev->thc_hw, THC_PORT_TYPE_SPI); + if (ret) + return ret; + + thc_spi_input_output_address_config(qsdev->thc_hw, + qsdev->input_report_hdr_addr, + qsdev->input_report_bdy_addr, + qsdev->output_report_addr); + + ret = thc_spi_read_config(qsdev->thc_hw, qsdev->spi_freq_val, + qsdev->spi_read_io_mode, + qsdev->spi_read_opcode, + qsdev->spi_packet_size); + if (ret) + return ret; + + ret = thc_spi_write_config(qsdev->thc_hw, qsdev->spi_freq_val, + qsdev->spi_write_io_mode, + qsdev->spi_write_opcode, + qsdev->spi_packet_size, + qsdev->performance_limit); + if (ret) + return ret; + + thc_interrupt_config(qsdev->thc_hw); + + thc_interrupt_enable(qsdev->thc_hw, true); + + /* TIC may lose power, needs go through reset flow */ + ret = reset_tic(qsdev); + if (ret) + return ret; + + ret = thc_dma_configure(qsdev->thc_hw); + if (ret) + return ret; + + thc_ltr_config(qsdev->thc_hw, + qsdev->active_ltr_val, + qsdev->low_power_ltr_val); + + thc_change_ltr_mode(qsdev->thc_hw, THC_LTR_MODE_ACTIVE); + + return 0; +} + +static int quickspi_runtime_suspend(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quickspi_device *qsdev; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return -ENODEV; + + thc_change_ltr_mode(qsdev->thc_hw, THC_LTR_MODE_LP); + + pci_save_state(pdev); + + return 0; +} + +static int quickspi_runtime_resume(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct quickspi_device *qsdev; + + qsdev = pci_get_drvdata(pdev); + if (!qsdev) + return -ENODEV; + + thc_change_ltr_mode(qsdev->thc_hw, THC_LTR_MODE_ACTIVE); + + return 0; +} + +static const struct dev_pm_ops quickspi_pm_ops = { + .suspend = quickspi_suspend, + .resume = quickspi_resume, + .freeze = quickspi_freeze, + .thaw = quickspi_thaw, + .poweroff = quickspi_poweroff, + .restore = quickspi_restore, + .runtime_suspend = quickspi_runtime_suspend, + .runtime_resume = quickspi_runtime_resume, + .runtime_idle = NULL, +}; + +static const struct pci_device_id quickspi_pci_tbl[] = { + {PCI_DEVICE_DATA(INTEL, THC_MTL_DEVICE_ID_SPI_PORT1, &mtl), }, + {PCI_DEVICE_DATA(INTEL, THC_MTL_DEVICE_ID_SPI_PORT2, &mtl), }, + {PCI_DEVICE_DATA(INTEL, THC_LNL_DEVICE_ID_SPI_PORT1, &lnl), }, + {PCI_DEVICE_DATA(INTEL, THC_LNL_DEVICE_ID_SPI_PORT2, &lnl), }, + {PCI_DEVICE_DATA(INTEL, THC_PTL_H_DEVICE_ID_SPI_PORT1, &ptl), }, + {PCI_DEVICE_DATA(INTEL, THC_PTL_H_DEVICE_ID_SPI_PORT2, &ptl), }, + {PCI_DEVICE_DATA(INTEL, THC_PTL_U_DEVICE_ID_SPI_PORT1, &ptl), }, + {PCI_DEVICE_DATA(INTEL, THC_PTL_U_DEVICE_ID_SPI_PORT2, &ptl), }, + {} +}; +MODULE_DEVICE_TABLE(pci, quickspi_pci_tbl); + +static struct pci_driver quickspi_driver = { + .name = KBUILD_MODNAME, + .id_table = quickspi_pci_tbl, + .probe = quickspi_probe, + .remove = quickspi_remove, + .shutdown = quickspi_shutdown, + .driver.pm = &quickspi_pm_ops, + .driver.probe_type = PROBE_PREFER_ASYNCHRONOUS, +}; + +module_pci_driver(quickspi_driver); + +MODULE_AUTHOR("Xinpeng Sun "); +MODULE_AUTHOR("Even Xu "); + +MODULE_DESCRIPTION("Intel(R) QuickSPI Driver"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS("INTEL_THC"); diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h new file mode 100644 index 000000000000..75179bb26767 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h @@ -0,0 +1,172 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#ifndef _QUICKSPI_DEV_H_ +#define _QUICKSPI_DEV_H_ + +#include +#include +#include +#include + +#include "quickspi-protocol.h" + +#define PCI_DEVICE_ID_INTEL_THC_MTL_DEVICE_ID_SPI_PORT1 0x7E49 +#define PCI_DEVICE_ID_INTEL_THC_MTL_DEVICE_ID_SPI_PORT2 0x7E4B +#define PCI_DEVICE_ID_INTEL_THC_LNL_DEVICE_ID_SPI_PORT1 0xA849 +#define PCI_DEVICE_ID_INTEL_THC_LNL_DEVICE_ID_SPI_PORT2 0xA84B +#define PCI_DEVICE_ID_INTEL_THC_PTL_H_DEVICE_ID_SPI_PORT1 0xE349 +#define PCI_DEVICE_ID_INTEL_THC_PTL_H_DEVICE_ID_SPI_PORT2 0xE34B +#define PCI_DEVICE_ID_INTEL_THC_PTL_U_DEVICE_ID_SPI_PORT1 0xE449 +#define PCI_DEVICE_ID_INTEL_THC_PTL_U_DEVICE_ID_SPI_PORT2 0xE44B + +/* HIDSPI special ACPI parameters DSM methods */ +#define ACPI_QUICKSPI_REVISION_NUM 2 +#define ACPI_QUICKSPI_FUNC_NUM_INPUT_REP_HDR_ADDR 1 +#define ACPI_QUICKSPI_FUNC_NUM_INPUT_REP_BDY_ADDR 2 +#define ACPI_QUICKSPI_FUNC_NUM_OUTPUT_REP_ADDR 3 +#define ACPI_QUICKSPI_FUNC_NUM_READ_OPCODE 4 +#define ACPI_QUICKSPI_FUNC_NUM_WRITE_OPCODE 5 +#define ACPI_QUICKSPI_FUNC_NUM_IO_MODE 6 + +/* QickSPI device special ACPI parameters DSM methods */ +#define ACPI_QUICKSPI_FUNC_NUM_CONNECTION_SPEED 1 +#define ACPI_QUICKSPI_FUNC_NUM_LIMIT_PACKET_SIZE 2 +#define ACPI_QUICKSPI_FUNC_NUM_PERFORMANCE_LIMIT 3 + +/* Platform special ACPI parameters DSM methods */ +#define ACPI_QUICKSPI_FUNC_NUM_ACTIVE_LTR 1 +#define ACPI_QUICKSPI_FUNC_NUM_LP_LTR 2 + +#define SPI_WRITE_IO_MODE BIT(13) +#define SPI_IO_MODE_OPCODE GENMASK(15, 14) +#define PERFORMANCE_LIMITATION GENMASK(15, 0) + +/* Packet size value, the unit is 16 bytes */ +#define DEFAULT_MIN_PACKET_SIZE_VALUE 4 +#define MAX_PACKET_SIZE_VALUE_MTL 128 +#define MAX_PACKET_SIZE_VALUE_LNL 256 + +/* + * THC uses runtime auto suspend to dynamically switch between THC active LTR + * and low power LTR to save CPU power. + * Default value is 5000ms, that means if no touch event in this time, THC will + * change to low power LTR mode. + */ +#define DEFAULT_AUTO_SUSPEND_DELAY_MS 5000 + +enum quickspi_dev_state { + QUICKSPI_NONE, + QUICKSPI_RESETING, + QUICKSPI_RESETED, + QUICKSPI_INITED, + QUICKSPI_ENABLED, + QUICKSPI_DISABLED, +}; + +/** + * struct quickspi_driver_data - Driver specific data for quickspi device + * @max_packet_size_value: identify max packet size, unit is 16 bytes + */ +struct quickspi_driver_data { + u32 max_packet_size_value; +}; + +struct device; +struct pci_dev; +struct thc_device; +struct hid_device; +struct acpi_device; + +/** + * struct quickspi_device - THC QuickSpi device struct + * @dev: point to kernel device + * @pdev: point to PCI device + * @thc_hw: point to THC device + * @hid_dev: point to hid device + * @acpi_dev: point to ACPI device + * @driver_data: point to quickspi specific driver data + * @state: THC SPI device state + * @mem_addr: MMIO memory address + * @dev_desc: device descriptor for HIDSPI protocol + * @input_report_hdr_addr: device input report header address + * @input_report_bdy_addr: device input report body address + * @output_report_bdy_addr: device output report address + * @spi_freq_val: device supported max SPI frequnecy, in Hz + * @spi_read_io_mode: device supported SPI read io mode + * @spi_write_io_mode: device supported SPI write io mode + * @spi_read_opcode: device read opcode + * @spi_write_opcode: device write opcode + * @limit_packet_size: 1 - limit read/write packet to 64Bytes + * 0 - device no packet size limiation for read/write + * @performance_limit: delay time, in ms. + * if device has performance limitation, must give a delay + * before write operation after a read operation. + * @active_ltr_val: THC active LTR value + * @low_power_ltr_val: THC low power LTR value + * @report_descriptor: store a copy of device report descriptor + * @input_buf: store a copy of latest input report data + * @report_buf: store a copy of latest input/output report packet from set/get feature + * @report_len: the length of input/output report packet + * @reset_ack_wq: workqueue for waiting reset response from device + * @reset_ack: indicate reset response received or not + * @nondma_int_received_wq: workqueue for waiting THC non-DMA interrupt + * @nondma_int_received: indicate THC non-DMA interrupt received or not + * @report_desc_got_wq: workqueue for waiting device report descriptor + * @report_desc_got: indicate device report descritor received or not + * @set_power_on_wq: workqueue for waiting set power on response from device + * @set_power_on: indicate set power on response received or not + * @get_feature_cmpl_wq: workqueue for waiting get feature response from device + * @get_feature_cmpl: indicate get feature received or not + * @set_feature_cmpl_wq: workqueue for waiting set feature to device + * @set_feature_cmpl: indicate set feature send complete or not + */ +struct quickspi_device { + struct device *dev; + struct pci_dev *pdev; + struct thc_device *thc_hw; + struct hid_device *hid_dev; + struct acpi_device *acpi_dev; + struct quickspi_driver_data *driver_data; + enum quickspi_dev_state state; + + void __iomem *mem_addr; + + struct hidspi_dev_descriptor dev_desc; + u32 input_report_hdr_addr; + u32 input_report_bdy_addr; + u32 output_report_addr; + u32 spi_freq_val; + u32 spi_read_io_mode; + u32 spi_write_io_mode; + u32 spi_read_opcode; + u32 spi_write_opcode; + u32 limit_packet_size; + u32 spi_packet_size; + u32 performance_limit; + + u32 active_ltr_val; + u32 low_power_ltr_val; + + u8 *report_descriptor; + u8 *input_buf; + u8 *report_buf; + u32 report_len; + + wait_queue_head_t reset_ack_wq; + bool reset_ack; + + wait_queue_head_t nondma_int_received_wq; + bool nondma_int_received; + + wait_queue_head_t report_desc_got_wq; + bool report_desc_got; + + wait_queue_head_t get_report_cmpl_wq; + bool get_report_cmpl; + + wait_queue_head_t set_report_cmpl_wq; + bool set_report_cmpl; +}; + +#endif /* _QUICKSPI_DEV_H_ */ diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c new file mode 100644 index 000000000000..ad52e402c28a --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#include +#include +#include + +#include "quickspi-dev.h" +#include "quickspi-hid.h" + +/** + * quickspi_hid_parse() - HID core parse() callback + * + * @hid: HID device instance + * + * This function gets called during call to hid_add_device + * + * Return: 0 on success and non zero on error. + */ +static int quickspi_hid_parse(struct hid_device *hid) +{ + struct quickspi_device *qsdev = hid->driver_data; + + if (qsdev->report_descriptor) + return hid_parse_report(hid, qsdev->report_descriptor, + le16_to_cpu(qsdev->dev_desc.rep_desc_len)); + + dev_err(qsdev->dev, "invalid report descriptor\n"); + return -EINVAL; +} + +static int quickspi_hid_start(struct hid_device *hid) +{ + return 0; +} + +static void quickspi_hid_stop(struct hid_device *hid) +{ +} + +static int quickspi_hid_open(struct hid_device *hid) +{ + return 0; +} + +static void quickspi_hid_close(struct hid_device *hid) +{ +} + +static int quickspi_hid_raw_request(struct hid_device *hid, + unsigned char reportnum, + __u8 *buf, size_t len, + unsigned char rtype, int reqtype) +{ + struct quickspi_device *qsdev = hid->driver_data; + int ret = 0; + + ret = pm_runtime_resume_and_get(qsdev->dev); + if (ret) + return ret; + + switch (reqtype) { + case HID_REQ_GET_REPORT: + ret = quickspi_get_report(qsdev, rtype, reportnum, buf); + break; + case HID_REQ_SET_REPORT: + ret = quickspi_set_report(qsdev, rtype, reportnum, buf, len); + break; + default: + dev_err_once(qsdev->dev, "Not supported request type %d\n", reqtype); + break; + } + + pm_runtime_mark_last_busy(qsdev->dev); + pm_runtime_put_autosuspend(qsdev->dev); + + return ret; +} + +static int quickspi_hid_power(struct hid_device *hid, int lvl) +{ + return 0; +} + +static struct hid_ll_driver quickspi_hid_ll_driver = { + .parse = quickspi_hid_parse, + .start = quickspi_hid_start, + .stop = quickspi_hid_stop, + .open = quickspi_hid_open, + .close = quickspi_hid_close, + .power = quickspi_hid_power, + .raw_request = quickspi_hid_raw_request, +}; + +/** + * quickspi_hid_probe() - Register HID low level driver + * + * @qsdev: point to quickspi device + * + * This function is used to allocate and add HID device. + * + * Return: 0 on success, non zero on error. + */ +int quickspi_hid_probe(struct quickspi_device *qsdev) +{ + struct hid_device *hid; + int ret; + + hid = hid_allocate_device(); + if (IS_ERR(hid)) + return PTR_ERR(hid); + + hid->ll_driver = &quickspi_hid_ll_driver; + hid->bus = BUS_PCI; + hid->dev.parent = qsdev->dev; + hid->driver_data = qsdev; + hid->version = le16_to_cpu(qsdev->dev_desc.version_id); + hid->vendor = le16_to_cpu(qsdev->dev_desc.vendor_id); + hid->product = le16_to_cpu(qsdev->dev_desc.product_id); + snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", "quickspi-hid", + hid->vendor, hid->product); + + ret = hid_add_device(hid); + if (ret) { + hid_destroy_device(hid); + return ret; + } + + qsdev->hid_dev = hid; + + return 0; +} + +/** + * quickspi_hid_remove() - Destroy HID device + * + * @qsdev: point to quickspi device + * + * Return: 0 on success, non zero on error. + */ +void quickspi_hid_remove(struct quickspi_device *qsdev) +{ + hid_destroy_device(qsdev->hid_dev); +} + +/** + * quickspi_hid_send_report() - Send HID input report data to HID core + * + * @qsdev: point to quickspi device + * @data: point to input report data buffer + * @data_len: the length of input report data + * + * Return: 0 on success, non zero on error. + */ +int quickspi_hid_send_report(struct quickspi_device *qsdev, + void *data, size_t data_len) +{ + int ret; + + ret = hid_input_report(qsdev->hid_dev, HID_INPUT_REPORT, data, data_len, 1); + if (ret) + dev_err(qsdev->dev, "Failed to send HID input report, ret = %d.\n", ret); + + return ret; +} diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.h b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.h new file mode 100644 index 000000000000..f640fa876a40 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#ifndef _QUICKSPI_HID_H_ +#define _QUICKSPI_HID_H_ + +struct quickspi_device; + +int quickspi_hid_send_report(struct quickspi_device *qsdev, + void *data, size_t data_size); +int quickspi_hid_probe(struct quickspi_device *qsdev); +void quickspi_hid_remove(struct quickspi_device *qsdev); + +#endif /* _QUICKSPI_HID_H_ */ diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c new file mode 100644 index 000000000000..7373238ceb18 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c @@ -0,0 +1,414 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright © 2024 Intel Corporation */ + +#include +#include +#include +#include + +#include "intel-thc-dev.h" +#include "intel-thc-dma.h" + +#include "quickspi-dev.h" +#include "quickspi-hid.h" +#include "quickspi-protocol.h" + +/* THC uses HW to accelerate HID over SPI protocol, THC_M_PRT_DEV_INT_CAUSE + * register is used to store message header and body header, below definition + * let driver retrieve needed data filed easier from THC_M_PRT_DEV_INT_CAUSE + * register. + */ +#define HIDSPI_IN_REP_BDY_HDR_REP_TYPE GENMASK(7, 0) + +static int write_cmd_to_txdma(struct quickspi_device *qsdev, + int report_type, int report_id, + u8 *report_buf, const int report_buf_len) +{ + struct output_report *write_buf; + int write_buf_len; + int ret; + + write_buf = (struct output_report *)qsdev->report_buf; + + write_buf->output_hdr.report_type = report_type; + write_buf->output_hdr.content_len = cpu_to_le16(report_buf_len); + write_buf->output_hdr.content_id = report_id; + + if (report_buf && report_buf_len > 0) + memcpy(write_buf->content, report_buf, report_buf_len); + + write_buf_len = HIDSPI_OUTPUT_REPORT_SIZE(report_buf_len); + + ret = thc_dma_write(qsdev->thc_hw, write_buf, write_buf_len); + if (ret) + dev_err_once(qsdev->dev, "DMA write failed, ret = %d\n", ret); + + return ret; +} + +static int quickspi_get_device_descriptor(struct quickspi_device *qsdev) +{ + u8 read_buf[HIDSPI_INPUT_DEVICE_DESCRIPTOR_SIZE]; + struct output_report output_rep; + u32 input_len, read_len = 0; + u32 int_cause_val; + u8 input_rep_type; + int ret; + + output_rep.output_hdr.report_type = DEVICE_DESCRIPTOR; + output_rep.output_hdr.content_len = 0; + output_rep.output_hdr.content_id = 0; + + qsdev->nondma_int_received = false; + + ret = thc_tic_pio_write(qsdev->thc_hw, qsdev->output_report_addr, + HIDSPI_OUTPUT_REPORT_SIZE(0), (u32 *)&output_rep); + if (ret) { + dev_err_once(qsdev->dev, + "Write DEVICE_DESCRIPTOR command failed, ret = %d\n", ret); + return ret; + } + + ret = wait_event_interruptible_timeout(qsdev->nondma_int_received_wq, + qsdev->nondma_int_received, + QUICKSPI_ACK_WAIT_TIMEOUT * HZ); + if (ret <= 0 || !qsdev->nondma_int_received) { + dev_err_once(qsdev->dev, "Wait DEVICE_DESCRIPTOR timeout, ret:%d\n", ret); + return -ETIMEDOUT; + } + qsdev->nondma_int_received = false; + + int_cause_val = thc_int_cause_read(qsdev->thc_hw); + input_len = FIELD_GET(HIDSPI_INPUT_HEADER_REPORT_LEN, int_cause_val); + + input_len = input_len * sizeof(u32); + if (input_len != HIDSPI_INPUT_DEVICE_DESCRIPTOR_SIZE) { + dev_err_once(qsdev->dev, "Receive wrong DEVICE_DESCRIPTOR length, len = %u\n", + input_len); + return -EINVAL; + } + + ret = thc_tic_pio_read(qsdev->thc_hw, qsdev->input_report_bdy_addr, + input_len, &read_len, (u32 *)read_buf); + if (ret || read_len != input_len) { + dev_err_once(qsdev->dev, "Read DEVICE_DESCRIPTOR failed, ret = %d\n", ret); + dev_err_once(qsdev->dev, "DEVICE_DESCRIPTOR expected len = %u, actual read = %u\n", + input_len, read_len); + return ret; + } + + input_rep_type = ((struct input_report_body_header *)read_buf)->input_report_type; + + if (input_rep_type == DEVICE_DESCRIPTOR_RESPONSE) { + memcpy(&qsdev->dev_desc, + read_buf + HIDSPI_INPUT_BODY_HEADER_SIZE, + HIDSPI_DEVICE_DESCRIPTOR_SIZE); + + return 0; + } + + dev_err_once(qsdev->dev, "Unexpected intput report type: %d\n", input_rep_type); + return -EINVAL; +} + +int quickspi_get_report_descriptor(struct quickspi_device *qsdev) +{ + int ret; + + ret = write_cmd_to_txdma(qsdev, REPORT_DESCRIPTOR, 0, NULL, 0); + if (ret) { + dev_err_once(qsdev->dev, + "Write REPORT_DESCRIPTOR command failed, ret = %d\n", ret); + return ret; + } + + ret = wait_event_interruptible_timeout(qsdev->report_desc_got_wq, + qsdev->report_desc_got, + QUICKSPI_ACK_WAIT_TIMEOUT * HZ); + if (ret <= 0 || !qsdev->report_desc_got) { + dev_err_once(qsdev->dev, "Wait Report Descriptor timeout, ret:%d\n", ret); + return -ETIMEDOUT; + } + qsdev->report_desc_got = false; + + return 0; +} + +int quickspi_set_power(struct quickspi_device *qsdev, + enum hidspi_power_state power_state) +{ + u8 cmd_content = power_state; + int ret; + + ret = write_cmd_to_txdma(qsdev, COMMAND_CONTENT, + HIDSPI_SET_POWER_CMD_ID, + &cmd_content, + sizeof(cmd_content)); + if (ret) { + dev_err_once(qsdev->dev, "Write SET_POWER command failed, ret = %d\n", ret); + return ret; + } + + return 0; +} + +void quickspi_handle_input_data(struct quickspi_device *qsdev, u32 buf_len) +{ + struct input_report_body_header *body_hdr; + struct input_report_body *input_body; + u8 *input_report; + u32 input_len; + int ret = 0; + + input_body = (struct input_report_body *)qsdev->input_buf; + body_hdr = &input_body->body_hdr; + input_len = le16_to_cpu(body_hdr->content_len); + + if (HIDSPI_INPUT_BODY_SIZE(input_len) > buf_len) { + dev_err_once(qsdev->dev, "Wrong input report length: %u", + input_len); + return; + } + + switch (body_hdr->input_report_type) { + case REPORT_DESCRIPTOR_RESPONSE: + if (input_len != le16_to_cpu(qsdev->dev_desc.rep_desc_len)) { + dev_err_once(qsdev->dev, "Unexpected report descriptor length: %u\n", + input_len); + return; + } + + memcpy(qsdev->report_descriptor, input_body->content, input_len); + + qsdev->report_desc_got = true; + wake_up_interruptible(&qsdev->report_desc_got_wq); + + break; + + case COMMAND_RESPONSE: + if (body_hdr->content_id == HIDSPI_SET_POWER_CMD_ID) { + dev_dbg(qsdev->dev, "Receive set power on response\n"); + } else { + dev_err_once(qsdev->dev, "Unknown command response type: %u\n", + body_hdr->content_id); + } + + break; + + case RESET_RESPONSE: + if (qsdev->state == QUICKSPI_RESETING) { + qsdev->reset_ack = true; + wake_up_interruptible(&qsdev->reset_ack_wq); + dev_dbg(qsdev->dev, "Receive HIR reset response\n"); + } else { + dev_info(qsdev->dev, "Receive DIR\n"); + } + break; + + case GET_FEATURE_RESPONSE: + case GET_INPUT_REPORT_RESPONSE: + qsdev->report_len = sizeof(body_hdr->content_id) + input_len; + input_report = input_body->content - sizeof(body_hdr->content_id); + + memcpy(qsdev->report_buf, input_report, qsdev->report_len); + + qsdev->get_report_cmpl = true; + wake_up_interruptible(&qsdev->get_report_cmpl_wq); + + break; + + case SET_FEATURE_RESPONSE: + case OUTPUT_REPORT_RESPONSE: + qsdev->set_report_cmpl = true; + wake_up_interruptible(&qsdev->set_report_cmpl_wq); + + break; + + case DATA: + if (qsdev->state != QUICKSPI_ENABLED) + return; + + if (input_len > le16_to_cpu(qsdev->dev_desc.max_input_len)) { + dev_err_once(qsdev->dev, "Unexpected too large input report length: %u\n", + input_len); + return; + } + + input_len = sizeof(body_hdr->content_id) + input_len; + input_report = input_body->content - sizeof(body_hdr->content_id); + + ret = quickspi_hid_send_report(qsdev, input_report, input_len); + if (ret) + dev_err_once(qsdev->dev, "Failed to send HID input report: %d\n", ret); + + break; + + default: + dev_err_once(qsdev->dev, "Unsupported input report type: %u\n", + body_hdr->input_report_type); + break; + } +} + +static int acpi_tic_reset(struct quickspi_device *qsdev) +{ + acpi_status status = 0; + acpi_handle handle; + + if (!qsdev->acpi_dev) + return -ENODEV; + + handle = acpi_device_handle(qsdev->acpi_dev); + status = acpi_execute_simple_method(handle, "_RST", 0); + if (ACPI_FAILURE(status)) { + dev_err_once(qsdev->dev, + "Failed to reset device through ACPI method, ret = %d\n", status); + return -EIO; + } + + return 0; +} + +int reset_tic(struct quickspi_device *qsdev) +{ + u32 actual_read_len, read_len = 0; + u32 input_report_len, reset_response, int_cause_val; + u8 input_rep_type; + int ret; + + qsdev->state = QUICKSPI_RESETING; + + qsdev->reset_ack = false; + + /* First interrupt uses level trigger to avoid missing interrupt */ + thc_int_trigger_type_select(qsdev->thc_hw, false); + + ret = acpi_tic_reset(qsdev); + if (ret) + return ret; + + ret = thc_interrupt_quiesce(qsdev->thc_hw, false); + if (ret) + return ret; + + ret = wait_event_interruptible_timeout(qsdev->reset_ack_wq, + qsdev->reset_ack, + QUICKSPI_ACK_WAIT_TIMEOUT * HZ); + if (ret <= 0 || !qsdev->reset_ack) { + dev_err_once(qsdev->dev, "Wait RESET_RESPONSE timeout, ret:%d\n", ret); + return -ETIMEDOUT; + } + + int_cause_val = thc_int_cause_read(qsdev->thc_hw); + input_report_len = FIELD_GET(HIDSPI_INPUT_HEADER_REPORT_LEN, int_cause_val); + + read_len = input_report_len * sizeof(u32); + if (read_len != HIDSPI_INPUT_BODY_SIZE(0)) { + dev_err_once(qsdev->dev, "Receive wrong RESET_RESPONSE, len = %u\n", + read_len); + return -EINVAL; + } + + /* Switch to edge trigger matching with HIDSPI protocol definition */ + thc_int_trigger_type_select(qsdev->thc_hw, true); + + ret = thc_tic_pio_read(qsdev->thc_hw, qsdev->input_report_bdy_addr, + read_len, &actual_read_len, + (u32 *)&reset_response); + if (ret || actual_read_len != read_len) { + dev_err_once(qsdev->dev, "Read RESET_RESPONSE body failed, ret = %d\n", ret); + dev_err_once(qsdev->dev, "RESET_RESPONSE body expected len = %u, actual = %u\n", + read_len, actual_read_len); + return ret; + } + + input_rep_type = FIELD_GET(HIDSPI_IN_REP_BDY_HDR_REP_TYPE, reset_response); + + if (input_rep_type == RESET_RESPONSE) { + dev_dbg(qsdev->dev, "RESET_RESPONSE received\n"); + } else { + dev_err_once(qsdev->dev, + "Unexpected input report type: %d, expect RESET_RESPONSE\n", + input_rep_type); + return -EINVAL; + } + + qsdev->state = QUICKSPI_RESETED; + + ret = quickspi_get_device_descriptor(qsdev); + if (ret) + return ret; + + return 0; +} + +int quickspi_get_report(struct quickspi_device *qsdev, + u8 report_type, unsigned int report_id, void *buf) +{ + int rep_type; + int ret; + + if (report_type == HID_INPUT_REPORT) { + rep_type = GET_INPUT_REPORT; + } else if (report_type == HID_FEATURE_REPORT) { + rep_type = GET_FEATURE; + } else { + dev_err_once(qsdev->dev, "Unsupported report type for GET REPORT: %d\n", + report_type); + return -EINVAL; + } + + ret = write_cmd_to_txdma(qsdev, rep_type, report_id, NULL, 0); + if (ret) { + dev_err_once(qsdev->dev, "Write GET_REPORT command failed, ret = %d\n", ret); + return ret; + } + + ret = wait_event_interruptible_timeout(qsdev->get_report_cmpl_wq, + qsdev->get_report_cmpl, + QUICKSPI_ACK_WAIT_TIMEOUT * HZ); + if (ret <= 0 || !qsdev->get_report_cmpl) { + dev_err_once(qsdev->dev, "Wait Get Report Response timeout, ret:%d\n", ret); + return -ETIMEDOUT; + } + qsdev->get_report_cmpl = false; + + memcpy(buf, qsdev->report_buf, qsdev->report_len); + + return qsdev->report_len; +} + +int quickspi_set_report(struct quickspi_device *qsdev, + u8 report_type, unsigned int report_id, + void *buf, u32 buf_len) +{ + int rep_type; + int ret; + + if (report_type == HID_OUTPUT_REPORT) { + rep_type = OUTPUT_REPORT; + } else if (report_type == HID_FEATURE_REPORT) { + rep_type = SET_FEATURE; + } else { + dev_err_once(qsdev->dev, "Unsupported report type for SET REPORT: %d\n", + report_type); + return -EINVAL; + } + + ret = write_cmd_to_txdma(qsdev, rep_type, report_id, buf + 1, buf_len - 1); + if (ret) { + dev_err_once(qsdev->dev, "Write SET_REPORT command failed, ret = %d\n", ret); + return ret; + } + + ret = wait_event_interruptible_timeout(qsdev->set_report_cmpl_wq, + qsdev->set_report_cmpl, + QUICKSPI_ACK_WAIT_TIMEOUT * HZ); + if (ret <= 0 || !qsdev->set_report_cmpl) { + dev_err_once(qsdev->dev, "Wait Set Report Response timeout, ret:%d\n", ret); + return -ETIMEDOUT; + } + qsdev->set_report_cmpl = false; + + return buf_len; +} diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.h b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.h new file mode 100644 index 000000000000..775e29c1ed13 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#ifndef _QUICKSPI_PROTOCOL_H_ +#define _QUICKSPI_PROTOCOL_H_ + +#include + +#define QUICKSPI_ACK_WAIT_TIMEOUT 5 + +struct quickspi_device; + +void quickspi_handle_input_data(struct quickspi_device *qsdev, u32 buf_len); +int quickspi_get_report(struct quickspi_device *qsdev, u8 report_type, + unsigned int report_id, void *buf); +int quickspi_set_report(struct quickspi_device *qsdev, u8 report_type, + unsigned int report_id, void *buf, u32 buf_len); +int quickspi_get_report_descriptor(struct quickspi_device *qsdev); + +int quickspi_set_power(struct quickspi_device *qsdev, + enum hidspi_power_state power_state); + +int reset_tic(struct quickspi_device *qsdev); + +#endif /* _QUICKSPI_PROTOCOL_H_ */ diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c new file mode 100644 index 000000000000..4fc78b5a04b5 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c @@ -0,0 +1,1578 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#include +#include + +#include "intel-thc-dev.h" +#include "intel-thc-hw.h" + +static int thc_regmap_read(void *context, unsigned int reg, + unsigned int *val) +{ + struct thc_device *thc_ctx = context; + void __iomem *base = thc_ctx->mmio_addr; + + *val = ioread32(base + reg); + return 0; +} + +static int thc_regmap_write(void *context, unsigned int reg, + unsigned int val) +{ + struct thc_device *thc_ctx = context; + void __iomem *base = thc_ctx->mmio_addr; + + iowrite32(val, base + reg); + return 0; +} + +static const struct regmap_range thc_rw_ranges[] = { + regmap_reg_range(0x10, 0x14), + regmap_reg_range(0x1000, 0x1320), +}; + +static const struct regmap_access_table thc_rw_table = { + .yes_ranges = thc_rw_ranges, + .n_yes_ranges = ARRAY_SIZE(thc_rw_ranges), +}; + +static const struct regmap_config thc_regmap_cfg = { + .name = "thc_regmap_common", + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + .max_register = 0x1320, + .reg_read = thc_regmap_read, + .reg_write = thc_regmap_write, + .cache_type = REGCACHE_NONE, + .fast_io = true, + .rd_table = &thc_rw_table, + .wr_table = &thc_rw_table, + .volatile_table = &thc_rw_table, +}; + +/** + * thc_clear_state - Clear THC hardware state + * + * @dev: The pointer of THC device structure + */ +static void thc_clear_state(const struct thc_device *dev) +{ + u32 val; + + /* Clear interrupt cause register */ + val = THC_M_PRT_ERR_CAUSE_INVLD_DEV_ENTRY | + THC_M_PRT_ERR_CAUSE_FRAME_BABBLE_ERR | + THC_M_PRT_ERR_CAUSE_BUF_OVRRUN_ERR | + THC_M_PRT_ERR_CAUSE_PRD_ENTRY_ERR; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_ERR_CAUSE_OFFSET, val, val); + + /* Clear interrupt error state */ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_1_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_IE_STALL, + THC_M_PRT_READ_DMA_CNTRL_IE_STALL); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_2_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_IE_STALL, + THC_M_PRT_READ_DMA_CNTRL_IE_STALL); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_TXN_ERR_INT_STS, + THC_M_PRT_INT_STATUS_TXN_ERR_INT_STS); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_FATAL_ERR_INT_STS, + THC_M_PRT_INT_STATUS_FATAL_ERR_INT_STS); + + val = THC_M_PRT_INT_EN_TXN_ERR_INT_EN | + THC_M_PRT_INT_EN_FATAL_ERR_INT_EN | + THC_M_PRT_INT_EN_BUF_OVRRUN_ERR_INT_EN; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_INT_EN_OFFSET, val, val); + + val = THC_M_PRT_SW_SEQ_STS_THC_SS_ERR | + THC_M_PRT_SW_SEQ_STS_TSSDONE; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, val, val); + + /* Clear RxDMA state */ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_1_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_IE_EOF, 0); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_2_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_IE_EOF, 0); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_INT_STS_1_OFFSET, + THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS, + THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_INT_STS_2_OFFSET, + THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS, + THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_INT_STS_1_OFFSET, + THC_M_PRT_READ_DMA_INT_STS_NONDMA_INT_STS, + THC_M_PRT_READ_DMA_INT_STS_NONDMA_INT_STS); + + /* Clear TxDMA state */ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_WRITE_DMA_CNTRL_OFFSET, + THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_IE_IOC_DMACPL, + THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_IE_IOC_DMACPL); + + val = THC_M_PRT_WRITE_INT_STS_THC_WRDMA_ERROR_STS | + THC_M_PRT_WRITE_INT_STS_THC_WRDMA_IOC_STS | + THC_M_PRT_WRITE_INT_STS_THC_WRDMA_CMPL_STATUS; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_WRITE_INT_STS_OFFSET, val, val); + + /* Reset all DMAs count */ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_DB_CNT_1_OFFSET, + THC_M_PRT_DB_CNT_1_THC_M_PRT_DB_CNT_RST, + THC_M_PRT_DB_CNT_1_THC_M_PRT_DB_CNT_RST); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_DEVINT_CNT_OFFSET, + THC_M_PRT_DEVINT_CNT_THC_M_PRT_DEVINT_CNT_RST, + THC_M_PRT_DEVINT_CNT_THC_M_PRT_DEVINT_CNT_RST); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_1_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_TPCPR, + THC_M_PRT_READ_DMA_CNTRL_TPCPR); + + /* Reset THC hardware sequence state */ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_FRAME_DROP_CNT_1_OFFSET, + THC_M_PRT_FRAME_DROP_CNT_1_RFDC, + THC_M_PRT_FRAME_DROP_CNT_1_RFDC); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_FRAME_DROP_CNT_2_OFFSET, + THC_M_PRT_FRAME_DROP_CNT_2_RFDC, + THC_M_PRT_FRAME_DROP_CNT_2_RFDC); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_FRM_CNT_1_OFFSET, + THC_M_PRT_FRM_CNT_1_THC_M_PRT_FRM_CNT_RST, + THC_M_PRT_FRM_CNT_1_THC_M_PRT_FRM_CNT_RST); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_FRM_CNT_2_OFFSET, + THC_M_PRT_FRM_CNT_2_THC_M_PRT_FRM_CNT_RST, + THC_M_PRT_FRM_CNT_2_THC_M_PRT_FRM_CNT_RST); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_RXDMA_PKT_CNT_1_OFFSET, + THC_M_PRT_RXDMA_PKT_CNT_1_THC_M_PRT_RXDMA_PKT_CNT_RST, + THC_M_PRT_RXDMA_PKT_CNT_1_THC_M_PRT_RXDMA_PKT_CNT_RST); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_RXDMA_PKT_CNT_2_OFFSET, + THC_M_PRT_RXDMA_PKT_CNT_2_THC_M_PRT_RXDMA_PKT_CNT_RST, + THC_M_PRT_RXDMA_PKT_CNT_2_THC_M_PRT_RXDMA_PKT_CNT_RST); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_SWINT_CNT_1_OFFSET, + THC_M_PRT_SWINT_CNT_1_THC_M_PRT_SWINT_CNT_RST, + THC_M_PRT_SWINT_CNT_1_THC_M_PRT_SWINT_CNT_RST); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_SWINT_CNT_1_OFFSET, + THC_M_PRT_SWINT_CNT_1_THC_M_PRT_SWINT_CNT_RST, + THC_M_PRT_SWINT_CNT_1_THC_M_PRT_SWINT_CNT_RST); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_TX_FRM_CNT_OFFSET, + THC_M_PRT_TX_FRM_CNT_THC_M_PRT_TX_FRM_CNT_RST, + THC_M_PRT_TX_FRM_CNT_THC_M_PRT_TX_FRM_CNT_RST); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_TXDMA_PKT_CNT_OFFSET, + THC_M_PRT_TXDMA_PKT_CNT_THC_M_PRT_TXDMA_PKT_CNT_RST, + THC_M_PRT_TXDMA_PKT_CNT_THC_M_PRT_TXDMA_PKT_CNT_RST); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_UFRM_CNT_1_OFFSET, + THC_M_PRT_UFRM_CNT_1_THC_M_PRT_UFRM_CNT_RST, + THC_M_PRT_UFRM_CNT_1_THC_M_PRT_UFRM_CNT_RST); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_UFRM_CNT_2_OFFSET, + THC_M_PRT_UFRM_CNT_2_THC_M_PRT_UFRM_CNT_RST, + THC_M_PRT_UFRM_CNT_2_THC_M_PRT_UFRM_CNT_RST); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_PRD_EMPTY_CNT_1_OFFSET, + THC_M_PRT_PRD_EMPTY_CNT_1_RPTEC, + THC_M_PRT_PRD_EMPTY_CNT_1_RPTEC); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_PRD_EMPTY_CNT_2_OFFSET, + THC_M_PRT_PRD_EMPTY_CNT_2_RPTEC, + THC_M_PRT_PRD_EMPTY_CNT_2_RPTEC); +} + +/** + * thc_dev_init - Allocate and initialize the THC device structure + * + * @device: The pointer of device structure + * @mem_addr: The pointer of MMIO memory address + * + * Return: The thc_device pointer on success, NULL on failed. + */ +struct thc_device *thc_dev_init(struct device *device, void __iomem *mem_addr) +{ + struct thc_device *thc_dev; + int ret; + + thc_dev = devm_kzalloc(device, sizeof(*thc_dev), GFP_KERNEL); + if (!thc_dev) + return ERR_PTR(-ENOMEM); + + thc_dev->dev = device; + thc_dev->mmio_addr = mem_addr; + thc_dev->thc_regmap = devm_regmap_init(device, NULL, thc_dev, &thc_regmap_cfg); + if (IS_ERR(thc_dev->thc_regmap)) { + ret = PTR_ERR(thc_dev->thc_regmap); + dev_err_once(device, "Failed to init thc_regmap: %d\n", ret); + return ERR_PTR(ret); + } + + thc_clear_state(thc_dev); + + mutex_init(&thc_dev->thc_bus_lock); + init_waitqueue_head(&thc_dev->write_complete_wait); + init_waitqueue_head(&thc_dev->swdma_complete_wait); + + thc_dev->dma_ctx = thc_dma_init(thc_dev); + if (!thc_dev->dma_ctx) { + dev_err_once(device, "DMA context init failed\n"); + return ERR_PTR(-ENOMEM); + } + + return thc_dev; +} +EXPORT_SYMBOL_NS_GPL(thc_dev_init, "INTEL_THC"); + +static int prepare_pio(const struct thc_device *dev, const u8 pio_op, + const u32 address, const u32 size) +{ + u32 sts, ctrl, addr, mask; + + regmap_read(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, &sts); + + /* Check if THC previous PIO still in progress */ + if (sts & THC_M_PRT_SW_SEQ_STS_THC_SS_CIP) { + dev_err_once(dev->dev, "THC PIO is still busy!\n"); + return -EBUSY; + } + + /* Clear error bit and complete bit in state register */ + sts |= THC_M_PRT_SW_SEQ_STS_THC_SS_ERR | + THC_M_PRT_SW_SEQ_STS_TSSDONE; + regmap_write(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, sts); + + /* Set PIO data size, opcode and interrupt capability */ + ctrl = FIELD_PREP(THC_M_PRT_SW_SEQ_CNTRL_THC_SS_BC, size) | + FIELD_PREP(THC_M_PRT_SW_SEQ_CNTRL_THC_SS_CMD, pio_op); + if (dev->pio_int_supported) + ctrl |= THC_M_PRT_SW_SEQ_CNTRL_THC_SS_CD_IE; + + mask = THC_M_PRT_SW_SEQ_CNTRL_THC_SS_BC | + THC_M_PRT_SW_SEQ_CNTRL_THC_SS_CMD | + THC_M_PRT_SW_SEQ_CNTRL_THC_SS_CD_IE; + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_SW_SEQ_CNTRL_OFFSET, mask, ctrl); + + /* Set PIO target address */ + addr = FIELD_PREP(THC_M_PRT_SW_SEQ_DATA0_ADDR_THC_SW_SEQ_DATA0_ADDR, address); + mask = THC_M_PRT_SW_SEQ_DATA0_ADDR_THC_SW_SEQ_DATA0_ADDR; + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_SW_SEQ_DATA0_ADDR_OFFSET, mask, addr); + return 0; +} + +static void pio_start(const struct thc_device *dev, + u32 size_in_bytes, const u32 *buffer) +{ + if (size_in_bytes && buffer) + regmap_bulk_write(dev->thc_regmap, THC_M_PRT_SW_SEQ_DATA1_OFFSET, + buffer, size_in_bytes / sizeof(u32)); + + /* Enable Start bit */ + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_SW_SEQ_CNTRL_OFFSET, + THC_M_PRT_SW_SEQ_CNTRL_TSSGO, + THC_M_PRT_SW_SEQ_CNTRL_TSSGO); +} + +static int pio_complete(const struct thc_device *dev, + u32 *buffer, u32 *size) +{ + u32 sts, ctrl; + + regmap_read(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, &sts); + if (sts & THC_M_PRT_SW_SEQ_STS_THC_SS_ERR) { + dev_err_once(dev->dev, "PIO operation error\n"); + return -EBUSY; + } + + if (buffer && size) { + regmap_read(dev->thc_regmap, THC_M_PRT_SW_SEQ_CNTRL_OFFSET, &ctrl); + *size = FIELD_GET(THC_M_PRT_SW_SEQ_CNTRL_THC_SS_BC, ctrl); + + regmap_bulk_read(dev->thc_regmap, THC_M_PRT_SW_SEQ_DATA1_OFFSET, + buffer, *size / sizeof(u32)); + } + + sts |= THC_M_PRT_SW_SEQ_STS_THC_SS_ERR | THC_M_PRT_SW_SEQ_STS_TSSDONE; + regmap_write(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, sts); + return 0; +} + +static int pio_wait(const struct thc_device *dev) +{ + u32 sts = 0; + int ret; + + ret = regmap_read_poll_timeout(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, sts, + !(sts & THC_M_PRT_SW_SEQ_STS_THC_SS_CIP || + !(sts & THC_M_PRT_SW_SEQ_STS_TSSDONE)), + THC_REGMAP_POLLING_INTERVAL_US, THC_PIO_DONE_TIMEOUT_US); + if (ret) + dev_err_once(dev->dev, "Timeout while polling PIO operation done\n"); + + return ret; +} + +/** + * thc_tic_pio_read - Read data from touch device by PIO + * + * @dev: The pointer of THC private device context + * @address: Slave address for the PIO operation + * @size: Expected read data size + * @actual_size: The pointer of the actual data size read from touch device + * @buffer: The pointer of data buffer to store the data read from touch device + * + * Return: 0 on success, other error codes on failed. + */ +int thc_tic_pio_read(struct thc_device *dev, const u32 address, + const u32 size, u32 *actual_size, u32 *buffer) +{ + u8 opcode; + int ret; + + if (size <= 0 || !actual_size || !buffer) { + dev_err(dev->dev, "Invalid input parameters, size %u, actual_size %p, buffer %p\n", + size, actual_size, buffer); + return -EINVAL; + } + + if (mutex_lock_interruptible(&dev->thc_bus_lock)) + return -EINTR; + + opcode = (dev->port_type == THC_PORT_TYPE_SPI) ? + THC_PIO_OP_SPI_TIC_READ : THC_PIO_OP_I2C_TIC_READ; + + ret = prepare_pio(dev, opcode, address, size); + if (ret < 0) + goto end; + + pio_start(dev, 0, NULL); + + ret = pio_wait(dev); + if (ret < 0) + goto end; + + ret = pio_complete(dev, buffer, actual_size); + +end: + mutex_unlock(&dev->thc_bus_lock); + return ret; +} +EXPORT_SYMBOL_NS_GPL(thc_tic_pio_read, "INTEL_THC"); + +/** + * thc_tic_pio_write - Write data to touch device by PIO + * + * @dev: The pointer of THC private device context + * @address: Slave address for the PIO operation + * @size: PIO write data size + * @buffer: The pointer of the write data buffer + * + * Return: 0 on success, other error codes on failed. + */ +int thc_tic_pio_write(struct thc_device *dev, const u32 address, + const u32 size, const u32 *buffer) +{ + u8 opcode; + int ret; + + if (size <= 0 || !buffer) { + dev_err(dev->dev, "Invalid input parameters, size %u, buffer %p\n", + size, buffer); + return -EINVAL; + } + + if (mutex_lock_interruptible(&dev->thc_bus_lock)) + return -EINTR; + + opcode = (dev->port_type == THC_PORT_TYPE_SPI) ? + THC_PIO_OP_SPI_TIC_WRITE : THC_PIO_OP_I2C_TIC_WRITE; + + ret = prepare_pio(dev, opcode, address, size); + if (ret < 0) + goto end; + + pio_start(dev, size, buffer); + + ret = pio_wait(dev); + if (ret < 0) + goto end; + + ret = pio_complete(dev, NULL, NULL); + +end: + mutex_unlock(&dev->thc_bus_lock); + return ret; +} +EXPORT_SYMBOL_NS_GPL(thc_tic_pio_write, "INTEL_THC"); + +/** + * thc_tic_pio_write_and_read - Write data followed by read data by PIO + * + * @dev: The pointer of THC private device context + * @address: Slave address for the PIO operation + * @write_size: PIO write data size + * @write_buffer: The pointer of the write data buffer + * @read_size: Expected PIO read data size + * @actual_size: The pointer of the actual read data size + * @read_buffer: The pointer of PIO read data buffer + * + * Return: 0 on success, other error codes on failed. + */ +int thc_tic_pio_write_and_read(struct thc_device *dev, const u32 address, + const u32 write_size, const u32 *write_buffer, + const u32 read_size, u32 *actual_size, u32 *read_buffer) +{ + u32 i2c_ctrl, mask; + int ret; + + if (dev->port_type == THC_PORT_TYPE_SPI) { + dev_err(dev->dev, "SPI port type doesn't support pio write and read!"); + return -EINVAL; + } + + if (mutex_lock_interruptible(&dev->thc_bus_lock)) + return -EINTR; + + /* Config i2c PIO write and read sequence */ + i2c_ctrl = FIELD_PREP(THC_M_PRT_SW_SEQ_I2C_WR_CNTRL_THC_PIO_I2C_WBC, write_size); + mask = THC_M_PRT_SW_SEQ_I2C_WR_CNTRL_THC_PIO_I2C_WBC; + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_SW_SEQ_I2C_WR_CNTRL_OFFSET, + mask, i2c_ctrl); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_SW_SEQ_I2C_WR_CNTRL_OFFSET, + THC_M_PRT_SW_SEQ_I2C_WR_CNTRL_THC_I2C_RW_PIO_EN, + THC_M_PRT_SW_SEQ_I2C_WR_CNTRL_THC_I2C_RW_PIO_EN); + + ret = prepare_pio(dev, THC_PIO_OP_I2C_TIC_WRITE_AND_READ, address, read_size); + if (ret < 0) + goto end; + + pio_start(dev, write_size, write_buffer); + + ret = pio_wait(dev); + if (ret < 0) + goto end; + + ret = pio_complete(dev, read_buffer, actual_size); + +end: + mutex_unlock(&dev->thc_bus_lock); + return ret; +} +EXPORT_SYMBOL_NS_GPL(thc_tic_pio_write_and_read, "INTEL_THC"); + +/** + * thc_interrupt_config - Configure THC interrupts + * + * @dev: The pointer of THC private device context + */ +void thc_interrupt_config(struct thc_device *dev) +{ + u32 mbits, mask, r_dma_ctrl_1; + + /* Clear Error reporting interrupt status bits */ + mbits = THC_M_PRT_INT_STATUS_TXN_ERR_INT_STS | + THC_M_PRT_INT_STATUS_FATAL_ERR_INT_STS; + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_INT_STATUS_OFFSET, + mbits, mbits); + + /* Enable Error Reporting Interrupts */ + mbits = THC_M_PRT_INT_EN_TXN_ERR_INT_EN | + THC_M_PRT_INT_EN_FATAL_ERR_INT_EN | + THC_M_PRT_INT_EN_BUF_OVRRUN_ERR_INT_EN; + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_INT_EN_OFFSET, + mbits, mbits); + + /* Clear PIO Interrupt status bits */ + mbits = THC_M_PRT_SW_SEQ_STS_THC_SS_ERR | + THC_M_PRT_SW_SEQ_STS_TSSDONE; + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_SW_SEQ_STS_OFFSET, + mbits, mbits); + + /* Read Interrupts */ + regmap_read(dev->thc_regmap, + THC_M_PRT_READ_DMA_CNTRL_1_OFFSET, + &r_dma_ctrl_1); + /* Disable RxDMA1 */ + r_dma_ctrl_1 &= ~THC_M_PRT_READ_DMA_CNTRL_IE_EOF; + regmap_write(dev->thc_regmap, + THC_M_PRT_READ_DMA_CNTRL_1_OFFSET, + r_dma_ctrl_1); + + /* Ack EOF Interrupt RxDMA1 */ + mbits = THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS; + /* Ack NonDMA Interrupt */ + mbits |= THC_M_PRT_READ_DMA_INT_STS_NONDMA_INT_STS; + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_READ_DMA_INT_STS_1_OFFSET, + mbits, mbits); + + /* Ack EOF Interrupt RxDMA2 */ + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_READ_DMA_INT_STS_2_OFFSET, + THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS, + THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS); + + /* Write Interrupts */ + /* Disable TxDMA */ + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_WRITE_DMA_CNTRL_OFFSET, + THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_IE_IOC_DMACPL, + 0); + + /* Clear TxDMA interrupt status bits */ + mbits = THC_M_PRT_WRITE_INT_STS_THC_WRDMA_ERROR_STS; + mbits |= THC_M_PRT_WRITE_INT_STS_THC_WRDMA_IOC_STS; + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_WRITE_INT_STS_OFFSET, + mbits, mbits); + + /* Enable Non-DMA device inband interrupt */ + r_dma_ctrl_1 |= THC_M_PRT_READ_DMA_CNTRL_IE_NDDI; + regmap_write(dev->thc_regmap, + THC_M_PRT_READ_DMA_CNTRL_1_OFFSET, + r_dma_ctrl_1); + + if (dev->port_type == THC_PORT_TYPE_SPI) { + /* Edge triggered interrupt */ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_TSEQ_CNTRL_1_OFFSET, + THC_M_PRT_TSEQ_CNTRL_1_INT_EDG_DET_EN, + THC_M_PRT_TSEQ_CNTRL_1_INT_EDG_DET_EN); + } else { + /* Level triggered interrupt */ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_TSEQ_CNTRL_1_OFFSET, + THC_M_PRT_TSEQ_CNTRL_1_INT_EDG_DET_EN, 0); + + mbits = THC_M_PRT_INT_EN_THC_I2C_IC_MST_ON_HOLD_INT_EN | + THC_M_PRT_INT_EN_THC_I2C_IC_SCL_STUCK_AT_LOW_DET_INT_EN | + THC_M_PRT_INT_EN_THC_I2C_IC_TX_ABRT_INT_EN | + THC_M_PRT_INT_EN_THC_I2C_IC_TX_OVER_INT_EN | + THC_M_PRT_INT_EN_THC_I2C_IC_RX_FULL_INT_EN | + THC_M_PRT_INT_EN_THC_I2C_IC_RX_OVER_INT_EN | + THC_M_PRT_INT_EN_THC_I2C_IC_RX_UNDER_INT_EN; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_INT_EN_OFFSET, + mbits, mbits); + } + + thc_set_pio_interrupt_support(dev, false); + + /* HIDSPI specific settings */ + if (dev->port_type == THC_PORT_TYPE_SPI) { + mbits = FIELD_PREP(THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_OFFSET, + THC_BIT_OFFSET_INTERRUPT_TYPE) | + FIELD_PREP(THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_LEN, + THC_BIT_LENGTH_INTERRUPT_TYPE) | + FIELD_PREP(THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_EOF_OFFSET, + THC_BIT_OFFSET_LAST_FRAGMENT_FLAG) | + FIELD_PREP(THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_DATA_VAL, + THC_BITMASK_INVALID_TYPE_DATA); + mask = THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_OFFSET | + THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_LEN | + THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_EOF_OFFSET | + THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_DATA_VAL; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_DEVINT_CFG_1_OFFSET, + mask, mbits); + + mbits = FIELD_PREP(THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_UFSIZE_OFFSET, + THC_BIT_OFFSET_MICROFRAME_SIZE) | + FIELD_PREP(THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_UFSIZE_LEN, + THC_BIT_LENGTH_MICROFRAME_SIZE) | + FIELD_PREP(THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_UFSIZE_UNIT, + THC_UNIT_MICROFRAME_SIZE) | + THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_FTYPE_IGNORE | + THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_FTYPE_VAL; + mask = THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_UFSIZE_OFFSET | + THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_UFSIZE_LEN | + THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_UFSIZE_UNIT | + THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_FTYPE_IGNORE | + THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_FTYPE_VAL; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_DEVINT_CFG_2_OFFSET, + mask, mbits); + } +} +EXPORT_SYMBOL_NS_GPL(thc_interrupt_config, "INTEL_THC"); + +/** + * thc_int_trigger_type_select - Select THC interrupt trigger type + * + * @dev: the pointer of THC private device context + * @edge_trigger: determine the interrupt is edge triggered or level triggered + */ +void thc_int_trigger_type_select(struct thc_device *dev, bool edge_trigger) +{ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_TSEQ_CNTRL_1_OFFSET, + THC_M_PRT_TSEQ_CNTRL_1_INT_EDG_DET_EN, + edge_trigger ? THC_M_PRT_TSEQ_CNTRL_1_INT_EDG_DET_EN : 0); +} +EXPORT_SYMBOL_NS_GPL(thc_int_trigger_type_select, "INTEL_THC"); + +/** + * thc_interrupt_enable - Enable or disable THC interrupt + * + * @dev: the pointer of THC private device context + * @int_enable: the flag to control THC interrupt enable or disable + */ +void thc_interrupt_enable(struct thc_device *dev, bool int_enable) +{ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_INT_EN_OFFSET, + THC_M_PRT_INT_EN_GBL_INT_EN, + int_enable ? THC_M_PRT_INT_EN_GBL_INT_EN : 0); +} +EXPORT_SYMBOL_NS_GPL(thc_interrupt_enable, "INTEL_THC"); + +/** + * thc_interrupt_quiesce - Quiesce or unquiesce external touch device interrupt + * + * @dev: the pointer of THC private device context + * @int_quiesce: the flag to determine quiesce or unquiesce device interrupt + * + * Return: 0 on success, other error codes on failed + */ +int thc_interrupt_quiesce(const struct thc_device *dev, bool int_quiesce) +{ + u32 ctrl; + int ret; + + regmap_read(dev->thc_regmap, THC_M_PRT_CONTROL_OFFSET, &ctrl); + if (!(ctrl & THC_M_PRT_CONTROL_THC_DEVINT_QUIESCE_EN) && !int_quiesce) { + dev_warn(dev->dev, "THC interrupt already unquiesce\n"); + return 0; + } + + if ((ctrl & THC_M_PRT_CONTROL_THC_DEVINT_QUIESCE_EN) && int_quiesce) { + dev_warn(dev->dev, "THC interrupt already quiesce\n"); + return 0; + } + + /* Quiesce device interrupt - Set quiesce bit and waiting for THC HW to ACK */ + if (int_quiesce) + regmap_write_bits(dev->thc_regmap, THC_M_PRT_CONTROL_OFFSET, + THC_M_PRT_CONTROL_THC_DEVINT_QUIESCE_EN, + THC_M_PRT_CONTROL_THC_DEVINT_QUIESCE_EN); + + ret = regmap_read_poll_timeout(dev->thc_regmap, THC_M_PRT_CONTROL_OFFSET, ctrl, + ctrl & THC_M_PRT_CONTROL_THC_DEVINT_QUIESCE_HW_STS, + THC_REGMAP_POLLING_INTERVAL_US, THC_QUIESCE_EN_TIMEOUT_US); + if (ret) { + dev_err_once(dev->dev, + "Timeout while waiting THC idle, target quiesce state = %s\n", + int_quiesce ? "true" : "false"); + return ret; + } + + /* Unquiesce device interrupt - Clear the quiesce bit */ + if (!int_quiesce) + regmap_write_bits(dev->thc_regmap, THC_M_PRT_CONTROL_OFFSET, + THC_M_PRT_CONTROL_THC_DEVINT_QUIESCE_EN, 0); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(thc_interrupt_quiesce, "INTEL_THC"); + +/** + * thc_set_pio_interrupt_support - Determine PIO interrupt is supported or not + * + * @dev: The pointer of THC private device context + * @supported: The flag to determine enabling PIO interrupt or not + */ +void thc_set_pio_interrupt_support(struct thc_device *dev, bool supported) +{ + dev->pio_int_supported = supported; +} +EXPORT_SYMBOL_NS_GPL(thc_set_pio_interrupt_support, "INTEL_THC"); + +/** + * thc_ltr_config - Configure THC Latency Tolerance Reporting(LTR) settings + * + * @dev: The pointer of THC private device context + * @active_ltr_us: active LTR value, unit is us + * @lp_ltr_us: low power LTR value, unit is us + */ +void thc_ltr_config(struct thc_device *dev, u32 active_ltr_us, u32 lp_ltr_us) +{ + u32 active_ltr_scale, lp_ltr_scale, ltr_ctrl, ltr_mask, orig, tmp; + + if (active_ltr_us >= THC_LTR_MIN_VAL_SCALE_3 && + active_ltr_us < THC_LTR_MAX_VAL_SCALE_3) { + active_ltr_scale = THC_LTR_SCALE_3; + active_ltr_us = active_ltr_us >> 5; + } else if (active_ltr_us >= THC_LTR_MIN_VAL_SCALE_4 && + active_ltr_us < THC_LTR_MAX_VAL_SCALE_4) { + active_ltr_scale = THC_LTR_SCALE_4; + active_ltr_us = active_ltr_us >> 10; + } else if (active_ltr_us >= THC_LTR_MIN_VAL_SCALE_5 && + active_ltr_us < THC_LTR_MAX_VAL_SCALE_5) { + active_ltr_scale = THC_LTR_SCALE_5; + active_ltr_us = active_ltr_us >> 15; + } else { + active_ltr_scale = THC_LTR_SCALE_2; + } + + if (lp_ltr_us >= THC_LTR_MIN_VAL_SCALE_3 && + lp_ltr_us < THC_LTR_MAX_VAL_SCALE_3) { + lp_ltr_scale = THC_LTR_SCALE_3; + lp_ltr_us = lp_ltr_us >> 5; + } else if (lp_ltr_us >= THC_LTR_MIN_VAL_SCALE_4 && + lp_ltr_us < THC_LTR_MAX_VAL_SCALE_4) { + lp_ltr_scale = THC_LTR_SCALE_4; + lp_ltr_us = lp_ltr_us >> 10; + } else if (lp_ltr_us >= THC_LTR_MIN_VAL_SCALE_5 && + lp_ltr_us < THC_LTR_MAX_VAL_SCALE_5) { + lp_ltr_scale = THC_LTR_SCALE_5; + lp_ltr_us = lp_ltr_us >> 15; + } else { + lp_ltr_scale = THC_LTR_SCALE_2; + } + + regmap_read(dev->thc_regmap, THC_M_CMN_LTR_CTRL_OFFSET, &orig); + ltr_ctrl = FIELD_PREP(THC_M_CMN_LTR_CTRL_ACT_LTR_VAL, active_ltr_us) | + FIELD_PREP(THC_M_CMN_LTR_CTRL_ACT_LTR_SCALE, active_ltr_scale) | + THC_M_CMN_LTR_CTRL_ACTIVE_LTR_REQ | + THC_M_CMN_LTR_CTRL_ACTIVE_LTR_EN | + FIELD_PREP(THC_M_CMN_LTR_CTRL_LP_LTR_VAL, lp_ltr_us) | + FIELD_PREP(THC_M_CMN_LTR_CTRL_LP_LTR_SCALE, lp_ltr_scale) | + THC_M_CMN_LTR_CTRL_LP_LTR_REQ; + + ltr_mask = THC_M_CMN_LTR_CTRL_ACT_LTR_VAL | + THC_M_CMN_LTR_CTRL_ACT_LTR_SCALE | + THC_M_CMN_LTR_CTRL_ACTIVE_LTR_REQ | + THC_M_CMN_LTR_CTRL_ACTIVE_LTR_EN | + THC_M_CMN_LTR_CTRL_LP_LTR_VAL | + THC_M_CMN_LTR_CTRL_LP_LTR_SCALE | + THC_M_CMN_LTR_CTRL_LP_LTR_REQ | + THC_M_CMN_LTR_CTRL_LP_LTR_EN; + + tmp = orig & ~ltr_mask; + tmp |= ltr_ctrl & ltr_mask; + + regmap_write(dev->thc_regmap, THC_M_CMN_LTR_CTRL_OFFSET, tmp); +} +EXPORT_SYMBOL_NS_GPL(thc_ltr_config, "INTEL_THC"); + +/** + * thc_change_ltr_mode - Change THC LTR mode + * + * @dev: The pointer of THC private device context + * @ltr_mode: LTR mode(active or low power) + */ +void thc_change_ltr_mode(struct thc_device *dev, u32 ltr_mode) +{ + if (ltr_mode == THC_LTR_MODE_ACTIVE) { + regmap_write_bits(dev->thc_regmap, THC_M_CMN_LTR_CTRL_OFFSET, + THC_M_CMN_LTR_CTRL_LP_LTR_EN, 0); + regmap_write_bits(dev->thc_regmap, THC_M_CMN_LTR_CTRL_OFFSET, + THC_M_CMN_LTR_CTRL_ACTIVE_LTR_EN, + THC_M_CMN_LTR_CTRL_ACTIVE_LTR_EN); + return; + } + + regmap_write_bits(dev->thc_regmap, THC_M_CMN_LTR_CTRL_OFFSET, + THC_M_CMN_LTR_CTRL_ACTIVE_LTR_EN, 0); + regmap_write_bits(dev->thc_regmap, THC_M_CMN_LTR_CTRL_OFFSET, + THC_M_CMN_LTR_CTRL_LP_LTR_EN, + THC_M_CMN_LTR_CTRL_LP_LTR_EN); +} +EXPORT_SYMBOL_NS_GPL(thc_change_ltr_mode, "INTEL_THC"); + +/** + * thc_ltr_unconfig - Unconfigure THC Latency Tolerance Reporting(LTR) settings + * + * @dev: The pointer of THC private device context + */ +void thc_ltr_unconfig(struct thc_device *dev) +{ + u32 ltr_ctrl, bits_clear; + + regmap_read(dev->thc_regmap, THC_M_CMN_LTR_CTRL_OFFSET, <r_ctrl); + bits_clear = THC_M_CMN_LTR_CTRL_LP_LTR_EN | + THC_M_CMN_LTR_CTRL_ACTIVE_LTR_EN | + THC_M_CMN_LTR_CTRL_LP_LTR_REQ | + THC_M_CMN_LTR_CTRL_ACTIVE_LTR_REQ; + + ltr_ctrl &= ~bits_clear; + + regmap_write(dev->thc_regmap, THC_M_CMN_LTR_CTRL_OFFSET, ltr_ctrl); +} +EXPORT_SYMBOL_NS_GPL(thc_ltr_unconfig, "INTEL_THC"); + +/** + * thc_int_cause_read - Read interrupt cause register value + * + * @dev: The pointer of THC private device context + * + * Return: The interrupt cause register value + */ +u32 thc_int_cause_read(struct thc_device *dev) +{ + u32 int_cause; + + regmap_read(dev->thc_regmap, + THC_M_PRT_DEV_INT_CAUSE_REG_VAL_OFFSET, &int_cause); + + return int_cause; +} +EXPORT_SYMBOL_NS_GPL(thc_int_cause_read, "INTEL_THC"); + +static void thc_print_txn_error_cause(const struct thc_device *dev) +{ + bool known_error = false; + u32 cause = 0; + + regmap_read(dev->thc_regmap, THC_M_PRT_ERR_CAUSE_OFFSET, &cause); + + if (cause & THC_M_PRT_ERR_CAUSE_PRD_ENTRY_ERR) { + dev_err(dev->dev, "TXN Error: Invalid PRD Entry\n"); + known_error = true; + } + if (cause & THC_M_PRT_ERR_CAUSE_BUF_OVRRUN_ERR) { + dev_err(dev->dev, "TXN Error: THC Buffer Overrun\n"); + known_error = true; + } + if (cause & THC_M_PRT_ERR_CAUSE_FRAME_BABBLE_ERR) { + dev_err(dev->dev, "TXN Error: Frame Babble\n"); + known_error = true; + } + if (cause & THC_M_PRT_ERR_CAUSE_INVLD_DEV_ENTRY) { + dev_err(dev->dev, "TXN Error: Invalid Device Register Setting\n"); + known_error = true; + } + + /* Clear interrupt status bits */ + regmap_write(dev->thc_regmap, THC_M_PRT_ERR_CAUSE_OFFSET, cause); + + if (!known_error) + dev_err(dev->dev, "TXN Error does not match any known value: 0x%X\n", + cause); +} + +/** + * thc_interrupt_handler - Handle THC interrupts + * + * THC interrupts include several types: external touch device (TIC) non-DMA + * interrupts, PIO completion interrupts, DMA interrtups, I2C subIP raw + * interrupts and error interrupts. + * + * This is a help function for interrupt processing, it detects interrupt + * type, clear the interrupt status bit and return the interrupt type to caller + * for future processing. + * + * @dev: The pointer of THC private device context + * + * Return: The combined flag for interrupt type + */ +int thc_interrupt_handler(struct thc_device *dev) +{ + u32 read_sts_1, read_sts_2, read_sts_sw, write_sts; + u32 int_sts, err_cause, seq_cntrl, seq_sts; + int interrupt_type = 0; + + regmap_read(dev->thc_regmap, + THC_M_PRT_READ_DMA_INT_STS_1_OFFSET, &read_sts_1); + + if (read_sts_1 & THC_M_PRT_READ_DMA_INT_STS_NONDMA_INT_STS) { + dev_dbg(dev->dev, "THC non-DMA device interrupt\n"); + + regmap_write(dev->thc_regmap, THC_M_PRT_READ_DMA_INT_STS_1_OFFSET, + NONDMA_INT_STS_BIT); + + interrupt_type |= BIT(THC_NONDMA_INT); + + return interrupt_type; + } + + regmap_read(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, &int_sts); + + if (int_sts & THC_M_PRT_INT_STATUS_TXN_ERR_INT_STS) { + dev_err(dev->dev, "THC transaction error, int_sts: 0x%08X\n", int_sts); + thc_print_txn_error_cause(dev); + + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + TXN_ERR_INT_STS_BIT); + + interrupt_type |= BIT(THC_TXN_ERR_INT); + + return interrupt_type; + } + + regmap_read(dev->thc_regmap, THC_M_PRT_ERR_CAUSE_OFFSET, &err_cause); + regmap_read(dev->thc_regmap, + THC_M_PRT_READ_DMA_INT_STS_2_OFFSET, &read_sts_2); + + if (err_cause & THC_M_PRT_ERR_CAUSE_BUF_OVRRUN_ERR || + read_sts_1 & THC_M_PRT_READ_DMA_INT_STS_STALL_STS || + read_sts_2 & THC_M_PRT_READ_DMA_INT_STS_STALL_STS) { + dev_err(dev->dev, "Buffer overrun or RxDMA engine stalled!\n"); + thc_print_txn_error_cause(dev); + + regmap_write(dev->thc_regmap, THC_M_PRT_READ_DMA_INT_STS_2_OFFSET, + THC_M_PRT_READ_DMA_INT_STS_STALL_STS); + regmap_write(dev->thc_regmap, THC_M_PRT_READ_DMA_INT_STS_1_OFFSET, + THC_M_PRT_READ_DMA_INT_STS_STALL_STS); + regmap_write(dev->thc_regmap, THC_M_PRT_ERR_CAUSE_OFFSET, + THC_M_PRT_ERR_CAUSE_BUF_OVRRUN_ERR); + + interrupt_type |= BIT(THC_TXN_ERR_INT); + + return interrupt_type; + } + + if (int_sts & THC_M_PRT_INT_STATUS_FATAL_ERR_INT_STS) { + dev_err_once(dev->dev, "THC FATAL error, int_sts: 0x%08X\n", int_sts); + + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + TXN_FATAL_INT_STS_BIT); + + interrupt_type |= BIT(THC_FATAL_ERR_INT); + + return interrupt_type; + } + + regmap_read(dev->thc_regmap, + THC_M_PRT_SW_SEQ_CNTRL_OFFSET, &seq_cntrl); + regmap_read(dev->thc_regmap, + THC_M_PRT_SW_SEQ_STS_OFFSET, &seq_sts); + + if (seq_cntrl & THC_M_PRT_SW_SEQ_CNTRL_THC_SS_CD_IE && + seq_sts & THC_M_PRT_SW_SEQ_STS_TSSDONE) { + dev_dbg(dev->dev, "THC_SS_CD_IE and TSSDONE are set\n"); + interrupt_type |= BIT(THC_PIO_DONE_INT); + } + + if (read_sts_1 & THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS) { + dev_dbg(dev->dev, "Got RxDMA1 Read Interrupt\n"); + + regmap_write(dev->thc_regmap, + THC_M_PRT_READ_DMA_INT_STS_1_OFFSET, read_sts_1); + + interrupt_type |= BIT(THC_RXDMA1_INT); + } + + if (read_sts_2 & THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS) { + dev_dbg(dev->dev, "Got RxDMA2 Read Interrupt\n"); + + regmap_write(dev->thc_regmap, + THC_M_PRT_READ_DMA_INT_STS_2_OFFSET, read_sts_2); + + interrupt_type |= BIT(THC_RXDMA2_INT); + } + + regmap_read(dev->thc_regmap, + THC_M_PRT_READ_DMA_INT_STS_SW_OFFSET, &read_sts_sw); + + if (read_sts_sw & THC_M_PRT_READ_DMA_INT_STS_DMACPL_STS) { + dev_dbg(dev->dev, "Got SwDMA Read Interrupt\n"); + + regmap_write(dev->thc_regmap, + THC_M_PRT_READ_DMA_INT_STS_SW_OFFSET, read_sts_sw); + + dev->swdma_done = true; + wake_up_interruptible(&dev->swdma_complete_wait); + + interrupt_type |= BIT(THC_SWDMA_INT); + } + + regmap_read(dev->thc_regmap, + THC_M_PRT_WRITE_INT_STS_OFFSET, &write_sts); + + if (write_sts & THC_M_PRT_WRITE_INT_STS_THC_WRDMA_CMPL_STATUS) { + dev_dbg(dev->dev, "Got TxDMA Write complete Interrupt\n"); + + regmap_write(dev->thc_regmap, + THC_M_PRT_WRITE_INT_STS_OFFSET, write_sts); + + dev->write_done = true; + wake_up_interruptible(&dev->write_complete_wait); + + interrupt_type |= BIT(THC_TXDMA_INT); + } + + if (int_sts & THC_M_PRT_INT_STATUS_DEV_RAW_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_DEV_RAW_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_RX_UNDER_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_RX_UNDER_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_RX_OVER_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_RX_OVER_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_RX_FULL_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_RX_FULL_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_TX_OVER_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_TX_OVER_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_TX_EMPTY_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_TX_EMPTY_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_TX_ABRT_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_TX_ABRT_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_ACTIVITY_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_ACTIVITY_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_SCL_STUCK_AT_LOW_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_SCL_STUCK_AT_LOW_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_STOP_DET_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_STOP_DET_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_START_DET_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_START_DET_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + if (int_sts & THC_M_PRT_INT_STATUS_THC_I2C_IC_MST_ON_HOLD_INT_STS) { + regmap_write(dev->thc_regmap, THC_M_PRT_INT_STATUS_OFFSET, + THC_M_PRT_INT_STATUS_THC_I2C_IC_MST_ON_HOLD_INT_STS); + interrupt_type |= BIT(THC_I2CSUBIP_INT); + } + + if (!interrupt_type) + interrupt_type |= BIT(THC_UNKNOWN_INT); + + return interrupt_type; +} +EXPORT_SYMBOL_NS_GPL(thc_interrupt_handler, "INTEL_THC"); + +/** + * thc_port_select - Set THC port type + * + * @dev: The pointer of THC private device context + * @port_type: THC port type to use for current device + * + * Return: 0 on success, other error codes on failed. + */ +int thc_port_select(struct thc_device *dev, enum thc_port_type port_type) +{ + u32 ctrl, mask; + + if (port_type == THC_PORT_TYPE_SPI) { + dev_dbg(dev->dev, "Set THC port type to SPI\n"); + dev->port_type = THC_PORT_TYPE_SPI; + + /* Enable delay of CS assertion and set to default value */ + ctrl = THC_M_PRT_SPI_DUTYC_CFG_SPI_CSA_CK_DELAY_EN | + FIELD_PREP(THC_M_PRT_SPI_DUTYC_CFG_SPI_CSA_CK_DELAY_VAL, + THC_CSA_CK_DELAY_VAL_DEFAULT); + mask = THC_M_PRT_SPI_DUTYC_CFG_SPI_CSA_CK_DELAY_EN | + THC_M_PRT_SPI_DUTYC_CFG_SPI_CSA_CK_DELAY_VAL; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_SPI_DUTYC_CFG_OFFSET, + mask, ctrl); + } else if (port_type == THC_PORT_TYPE_I2C) { + dev_dbg(dev->dev, "Set THC port type to I2C\n"); + dev->port_type = THC_PORT_TYPE_I2C; + + /* Set THC transition arbitration policy to frame boundary for I2C */ + ctrl = FIELD_PREP(THC_M_PRT_CONTROL_THC_ARB_POLICY, + THC_ARB_POLICY_FRAME_BOUNDARY); + mask = THC_M_PRT_CONTROL_THC_ARB_POLICY; + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_CONTROL_OFFSET, mask, ctrl); + } else { + dev_err(dev->dev, "unsupported THC port type: %d\n", port_type); + return -EINVAL; + } + + ctrl = FIELD_PREP(THC_M_PRT_CONTROL_PORT_TYPE, port_type); + mask = THC_M_PRT_CONTROL_PORT_TYPE; + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_CONTROL_OFFSET, mask, ctrl); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(thc_port_select, "INTEL_THC"); + +#define THC_SPI_FREQUENCY_7M 7812500 +#define THC_SPI_FREQUENCY_15M 15625000 +#define THC_SPI_FREQUENCY_17M 17857100 +#define THC_SPI_FREQUENCY_20M 20833000 +#define THC_SPI_FREQUENCY_25M 25000000 +#define THC_SPI_FREQUENCY_31M 31250000 +#define THC_SPI_FREQUENCY_41M 41666700 + +#define THC_SPI_LOW_FREQUENCY THC_SPI_FREQUENCY_17M + +static u8 thc_get_spi_freq_div_val(struct thc_device *dev, u32 spi_freq_val) +{ + int frequency[] = { + THC_SPI_FREQUENCY_7M, + THC_SPI_FREQUENCY_15M, + THC_SPI_FREQUENCY_17M, + THC_SPI_FREQUENCY_20M, + THC_SPI_FREQUENCY_25M, + THC_SPI_FREQUENCY_31M, + THC_SPI_FREQUENCY_41M, + }; + u8 frequency_div[] = { + THC_SPI_FRQ_DIV_2, + THC_SPI_FRQ_DIV_1, + THC_SPI_FRQ_DIV_7, + THC_SPI_FRQ_DIV_6, + THC_SPI_FRQ_DIV_5, + THC_SPI_FRQ_DIV_4, + THC_SPI_FRQ_DIV_3, + }; + int size = ARRAY_SIZE(frequency); + u32 closest_freq; + u8 freq_div; + int i; + + for (i = size - 1; i >= 0; i--) + if ((int)spi_freq_val - frequency[i] >= 0) + break; + + if (i < 0) { + dev_err_once(dev->dev, "Not supported SPI frequency %d\n", spi_freq_val); + return THC_SPI_FRQ_RESERVED; + } + + closest_freq = frequency[i]; + freq_div = frequency_div[i]; + + dev_dbg(dev->dev, + "Setting SPI frequency: spi_freq_val = %u, Closest freq = %u\n", + spi_freq_val, closest_freq); + + return freq_div; +} + +/** + * thc_spi_read_config - Configure SPI bus read attributes + * + * @dev: The pointer of THC private device context + * @spi_freq_val: SPI read frequecy value + * @io_mode: SPI read IO mode + * @opcode: Read opcode + * @spi_rd_mps: SPI read max packet size + * + * Return: 0 on success, other error codes on failed. + */ +int thc_spi_read_config(struct thc_device *dev, u32 spi_freq_val, + u32 io_mode, u32 opcode, u32 spi_rd_mps) +{ + bool is_low_freq = false; + u32 cfg, mask; + u8 freq_div; + + freq_div = thc_get_spi_freq_div_val(dev, spi_freq_val); + if (freq_div == THC_SPI_FRQ_RESERVED) + return -EINVAL; + + if (spi_freq_val < THC_SPI_LOW_FREQUENCY) + is_low_freq = true; + + cfg = FIELD_PREP(THC_M_PRT_SPI_CFG_SPI_TCRF, freq_div) | + FIELD_PREP(THC_M_PRT_SPI_CFG_SPI_TRMODE, io_mode) | + (is_low_freq ? THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN : 0) | + FIELD_PREP(THC_M_PRT_SPI_CFG_SPI_RD_MPS, spi_rd_mps); + mask = THC_M_PRT_SPI_CFG_SPI_TCRF | + THC_M_PRT_SPI_CFG_SPI_TRMODE | + THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN | + THC_M_PRT_SPI_CFG_SPI_RD_MPS; + + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_SPI_CFG_OFFSET, mask, cfg); + + if (io_mode == THC_QUAD_IO) + opcode = FIELD_PREP(THC_M_PRT_SPI_ICRRD_OPCODE_SPI_QIO, opcode); + else if (io_mode == THC_DUAL_IO) + opcode = FIELD_PREP(THC_M_PRT_SPI_ICRRD_OPCODE_SPI_DIO, opcode); + else + opcode = FIELD_PREP(THC_M_PRT_SPI_ICRRD_OPCODE_SPI_SIO, opcode); + + regmap_write(dev->thc_regmap, THC_M_PRT_SPI_ICRRD_OPCODE_OFFSET, opcode); + regmap_write(dev->thc_regmap, THC_M_PRT_SPI_DMARD_OPCODE_OFFSET, opcode); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(thc_spi_read_config, "INTEL_THC"); + +/** + * thc_spi_write_config - Configure SPI bus write attributes + * + * @dev: The pointer of THC private device context + * @spi_freq_val: SPI write frequecy value + * @io_mode: SPI write IO mode + * @opcode: Write opcode + * @spi_wr_mps: SPI write max packet size + * @perf_limit: Performance limitation in unit of 10us + * + * Return: 0 on success, other error codes on failed. + */ +int thc_spi_write_config(struct thc_device *dev, u32 spi_freq_val, + u32 io_mode, u32 opcode, u32 spi_wr_mps, + u32 perf_limit) +{ + bool is_low_freq = false; + u32 cfg, mask; + u8 freq_div; + + freq_div = thc_get_spi_freq_div_val(dev, spi_freq_val); + if (freq_div == THC_SPI_FRQ_RESERVED) + return -EINVAL; + + if (spi_freq_val < THC_SPI_LOW_FREQUENCY) + is_low_freq = true; + + cfg = FIELD_PREP(THC_M_PRT_SPI_CFG_SPI_TCWF, freq_div) | + FIELD_PREP(THC_M_PRT_SPI_CFG_SPI_TWMODE, io_mode) | + (is_low_freq ? THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN : 0) | + FIELD_PREP(THC_M_PRT_SPI_CFG_SPI_WR_MPS, spi_wr_mps); + mask = THC_M_PRT_SPI_CFG_SPI_TCWF | + THC_M_PRT_SPI_CFG_SPI_TWMODE | + THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN | + THC_M_PRT_SPI_CFG_SPI_WR_MPS; + + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_SPI_CFG_OFFSET, mask, cfg); + + if (io_mode == THC_QUAD_IO) + opcode = FIELD_PREP(THC_M_PRT_SPI_ICRRD_OPCODE_SPI_QIO, opcode); + else if (io_mode == THC_DUAL_IO) + opcode = FIELD_PREP(THC_M_PRT_SPI_ICRRD_OPCODE_SPI_DIO, opcode); + else + opcode = FIELD_PREP(THC_M_PRT_SPI_ICRRD_OPCODE_SPI_SIO, opcode); + + regmap_write(dev->thc_regmap, THC_M_PRT_SPI_WR_OPCODE_OFFSET, opcode); + + dev->perf_limit = perf_limit; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(thc_spi_write_config, "INTEL_THC"); + +/** + * thc_spi_input_output_address_config - Configure SPI input and output addresses + * + * @dev: the pointer of THC private device context + * @input_hdr_addr: input report header address + * @input_bdy_addr: input report body address + * @output_addr: output report address + */ +void thc_spi_input_output_address_config(struct thc_device *dev, u32 input_hdr_addr, + u32 input_bdy_addr, u32 output_addr) +{ + regmap_write(dev->thc_regmap, + THC_M_PRT_DEV_INT_CAUSE_ADDR_OFFSET, input_hdr_addr); + regmap_write(dev->thc_regmap, + THC_M_PRT_RD_BULK_ADDR_1_OFFSET, input_bdy_addr); + regmap_write(dev->thc_regmap, + THC_M_PRT_RD_BULK_ADDR_2_OFFSET, input_bdy_addr); + regmap_write(dev->thc_regmap, + THC_M_PRT_WR_BULK_ADDR_OFFSET, output_addr); +} +EXPORT_SYMBOL_NS_GPL(thc_spi_input_output_address_config, "INTEL_THC"); + +static int thc_i2c_subip_pio_read(struct thc_device *dev, const u32 address, + u32 *size, u32 *buffer) +{ + int ret; + + if (!size || *size == 0 || !buffer) { + dev_err(dev->dev, "Invalid input parameters, size %p, buffer %p\n", + size, buffer); + return -EINVAL; + } + + if (mutex_lock_interruptible(&dev->thc_bus_lock)) + return -EINTR; + + ret = prepare_pio(dev, THC_PIO_OP_I2C_SUBSYSTEM_READ, address, *size); + if (ret < 0) + goto end; + + pio_start(dev, 0, NULL); + + ret = pio_wait(dev); + if (ret < 0) + goto end; + + ret = pio_complete(dev, buffer, size); + if (ret < 0) + goto end; + +end: + mutex_unlock(&dev->thc_bus_lock); + + if (ret) + dev_err_once(dev->dev, "Read THC I2C SubIP register failed %d, offset %u\n", + ret, address); + + return ret; +} + +static int thc_i2c_subip_pio_write(struct thc_device *dev, const u32 address, + const u32 size, const u32 *buffer) +{ + int ret; + + if (size == 0 || !buffer) { + dev_err(dev->dev, "Invalid input parameters, size %u, buffer %p\n", + size, buffer); + return -EINVAL; + } + + if (mutex_lock_interruptible(&dev->thc_bus_lock)) + return -EINTR; + + ret = prepare_pio(dev, THC_PIO_OP_I2C_SUBSYSTEM_WRITE, address, size); + if (ret < 0) + goto end; + + pio_start(dev, size, buffer); + + ret = pio_wait(dev); + if (ret < 0) + goto end; + + ret = pio_complete(dev, NULL, NULL); + if (ret < 0) + goto end; + +end: + mutex_unlock(&dev->thc_bus_lock); + + if (ret) + dev_err_once(dev->dev, "Write THC I2C SubIP register failed %d, offset %u\n", + ret, address); + + return ret; +} + +#define I2C_SUBIP_CON_DEFAULT 0x663 +#define I2C_SUBIP_INT_MASK_DEFAULT 0x7FFF +#define I2C_SUBIP_RX_TL_DEFAULT 62 +#define I2C_SUBIP_TX_TL_DEFAULT 0 +#define I2C_SUBIP_DMA_TDLR_DEFAULT 7 +#define I2C_SUBIP_DMA_RDLR_DEFAULT 7 + +static int thc_i2c_subip_set_speed(struct thc_device *dev, const u32 speed, + const u32 hcnt, const u32 lcnt) +{ + u32 hcnt_offset, lcnt_offset; + u32 val; + int ret; + + switch (speed) { + case THC_I2C_STANDARD: + hcnt_offset = THC_I2C_IC_SS_SCL_HCNT_OFFSET; + lcnt_offset = THC_I2C_IC_SS_SCL_LCNT_OFFSET; + break; + + case THC_I2C_FAST_AND_PLUS: + hcnt_offset = THC_I2C_IC_FS_SCL_HCNT_OFFSET; + lcnt_offset = THC_I2C_IC_FS_SCL_LCNT_OFFSET; + break; + + case THC_I2C_HIGH_SPEED: + hcnt_offset = THC_I2C_IC_HS_SCL_HCNT_OFFSET; + lcnt_offset = THC_I2C_IC_HS_SCL_LCNT_OFFSET; + break; + + default: + dev_err_once(dev->dev, "Unsupported i2c speed %d\n", speed); + ret = -EINVAL; + return ret; + } + + ret = thc_i2c_subip_pio_write(dev, hcnt_offset, sizeof(u32), &hcnt); + if (ret < 0) + return ret; + + ret = thc_i2c_subip_pio_write(dev, lcnt_offset, sizeof(u32), &lcnt); + if (ret < 0) + return ret; + + val = I2C_SUBIP_CON_DEFAULT & ~THC_I2C_IC_CON_SPEED; + val |= FIELD_PREP(THC_I2C_IC_CON_SPEED, speed); + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_CON_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + return 0; +} + +static u32 i2c_subip_regs[] = { + THC_I2C_IC_CON_OFFSET, + THC_I2C_IC_TAR_OFFSET, + THC_I2C_IC_INTR_MASK_OFFSET, + THC_I2C_IC_RX_TL_OFFSET, + THC_I2C_IC_TX_TL_OFFSET, + THC_I2C_IC_DMA_CR_OFFSET, + THC_I2C_IC_DMA_TDLR_OFFSET, + THC_I2C_IC_DMA_RDLR_OFFSET, + THC_I2C_IC_SS_SCL_HCNT_OFFSET, + THC_I2C_IC_SS_SCL_LCNT_OFFSET, + THC_I2C_IC_FS_SCL_HCNT_OFFSET, + THC_I2C_IC_FS_SCL_LCNT_OFFSET, + THC_I2C_IC_HS_SCL_HCNT_OFFSET, + THC_I2C_IC_HS_SCL_LCNT_OFFSET, + THC_I2C_IC_ENABLE_OFFSET, +}; + +/** + * thc_i2c_subip_init - Initialize and configure THC I2C subsystem + * + * @dev: The pointer of THC private device context + * @target_address: Slave address of touch device (TIC) + * @speed: I2C bus frequency speed mode + * @hcnt: I2C clock SCL high count + * @lcnt: I2C clock SCL low count + * + * Return: 0 on success, other error codes on failed. + */ +int thc_i2c_subip_init(struct thc_device *dev, const u32 target_address, + const u32 speed, const u32 hcnt, const u32 lcnt) +{ + u32 read_size = sizeof(u32); + u32 val; + int ret; + + ret = thc_i2c_subip_pio_read(dev, THC_I2C_IC_ENABLE_OFFSET, &read_size, &val); + if (ret < 0) + return ret; + + val &= ~THC_I2C_IC_ENABLE_ENABLE; + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_ENABLE_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + ret = thc_i2c_subip_pio_read(dev, THC_I2C_IC_TAR_OFFSET, &read_size, &val); + if (ret < 0) + return ret; + + val &= ~THC_I2C_IC_TAR_IC_TAR; + val |= FIELD_PREP(THC_I2C_IC_TAR_IC_TAR, target_address); + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_TAR_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + ret = thc_i2c_subip_set_speed(dev, speed, hcnt, lcnt); + if (ret < 0) + return ret; + + val = I2C_SUBIP_INT_MASK_DEFAULT; + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_INTR_MASK_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + val = I2C_SUBIP_RX_TL_DEFAULT; + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_RX_TL_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + val = I2C_SUBIP_TX_TL_DEFAULT; + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_TX_TL_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + val = THC_I2C_IC_DMA_CR_RDMAE | THC_I2C_IC_DMA_CR_TDMAE; + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_DMA_CR_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + val = I2C_SUBIP_DMA_TDLR_DEFAULT; + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_DMA_TDLR_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + val = I2C_SUBIP_DMA_RDLR_DEFAULT; + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_DMA_RDLR_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + ret = thc_i2c_subip_pio_read(dev, THC_I2C_IC_ENABLE_OFFSET, &read_size, &val); + if (ret < 0) + return ret; + + val |= THC_I2C_IC_ENABLE_ENABLE; + ret = thc_i2c_subip_pio_write(dev, THC_I2C_IC_ENABLE_OFFSET, sizeof(u32), &val); + if (ret < 0) + return ret; + + dev->i2c_subip_regs = devm_kzalloc(dev->dev, sizeof(i2c_subip_regs), GFP_KERNEL); + if (!dev->i2c_subip_regs) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(thc_i2c_subip_init, "INTEL_THC"); + +/** + * thc_i2c_subip_regs_save - Save THC I2C sub-subsystem register values to THC device context + * + * @dev: The pointer of THC private device context + * + * Return: 0 on success, other error codes on failed. + */ +int thc_i2c_subip_regs_save(struct thc_device *dev) +{ + int ret; + u32 read_size = sizeof(u32); + + for (int i = 0; i < ARRAY_SIZE(i2c_subip_regs); i++) { + ret = thc_i2c_subip_pio_read(dev, i2c_subip_regs[i], + &read_size, (u32 *)&dev->i2c_subip_regs + i); + if (ret < 0) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_NS_GPL(thc_i2c_subip_regs_save, "INTEL_THC"); + +/** + * thc_i2c_subip_regs_restore - Restore THC I2C subsystem registers from THC device context + * + * @dev: The pointer of THC private device context + * + * Return: 0 on success, other error codes on failed. + */ +int thc_i2c_subip_regs_restore(struct thc_device *dev) +{ + int ret; + u32 write_size = sizeof(u32); + + for (int i = 0; i < ARRAY_SIZE(i2c_subip_regs); i++) { + ret = thc_i2c_subip_pio_write(dev, i2c_subip_regs[i], + write_size, (u32 *)&dev->i2c_subip_regs + i); + if (ret < 0) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_NS_GPL(thc_i2c_subip_regs_restore, "INTEL_THC"); + +MODULE_AUTHOR("Xinpeng Sun "); +MODULE_AUTHOR("Even Xu "); + +MODULE_DESCRIPTION("Intel(R) Intel THC Hardware Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.h b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.h new file mode 100644 index 000000000000..0517fee2c668 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#ifndef _INTEL_THC_DEV_H_ +#define _INTEL_THC_DEV_H_ + +#include +#include +#include + +#include "intel-thc-dma.h" + +#define THC_REGMAP_COMMON_OFFSET 0x10 +#define THC_REGMAP_MMIO_OFFSET 0x1000 + +/* + * THC Port type + * @THC_PORT_TYPE_SPI: This port is used for HIDSPI + * @THC_PORT_TYPE_I2C: This port is used for HIDI2C + */ +enum thc_port_type { + THC_PORT_TYPE_SPI = 0, + THC_PORT_TYPE_I2C = 1, +}; + +/** + * THC interrupt flag + * @THC_NONDMA_INT: THC non-DMA interrupt + * @THC_RXDMA1_INT: THC RxDMA1 interrupt + * @THC_RXDMA2_INT: THC RxDMA2 interrupt + * @THC_SWDMA_INT: THC SWDMA interrupt + * @THC_TXDMA_INT: THC TXDMA interrupt + * @THC_PIO_DONE_INT: THC PIO complete interrupt + * @THC_I2CSUBIP_INT: THC I2C subsystem interrupt + * @THC_TXN_ERR_INT: THC transfer error interrupt + * @THC_FATAL_ERR_INT: THC fatal error interrupt + */ +enum thc_int_type { + THC_NONDMA_INT = 0, + THC_RXDMA1_INT = 1, + THC_RXDMA2_INT = 2, + THC_SWDMA_INT = 3, + THC_TXDMA_INT = 4, + THC_PIO_DONE_INT = 5, + THC_I2CSUBIP_INT = 6, + THC_TXN_ERR_INT = 7, + THC_FATAL_ERR_INT = 8, + THC_UNKNOWN_INT +}; + +/** + * struct thc_device - THC private device struct + * @thc_regmap: MMIO regmap structure for accessing THC registers + * @mmio_addr: MMIO registers address + * @thc_bus_lock: mutex locker for THC config + * @port_type: port type of THC port instance + * @pio_int_supported: PIO interrupt supported flag + * @dma_ctx: DMA specific data + * @write_complete_wait: signal event for DMA write complete + * @swdma_complete_wait: signal event for SWDMA sequence complete + * @write_done: bool value that indicates if DMA write is done + * @swdma_done: bool value that indicates if SWDMA swquence is done + * @perf_limit: the delay between read operation and write operation + * @i2c_subip_regs: the copy of THC I2C sub-system registers for resuming restore + */ +struct thc_device { + struct device *dev; + struct regmap *thc_regmap; + void __iomem *mmio_addr; + struct mutex thc_bus_lock; + enum thc_port_type port_type; + bool pio_int_supported; + + struct thc_dma_context *dma_ctx; + + wait_queue_head_t write_complete_wait; + wait_queue_head_t swdma_complete_wait; + bool write_done; + bool swdma_done; + + u32 perf_limit; + + u32 *i2c_subip_regs; +}; + +struct thc_device *thc_dev_init(struct device *device, void __iomem *mem_addr); +int thc_tic_pio_read(struct thc_device *dev, const u32 address, + const u32 size, u32 *actual_size, u32 *buffer); +int thc_tic_pio_write(struct thc_device *dev, const u32 address, + const u32 size, const u32 *buffer); +int thc_tic_pio_write_and_read(struct thc_device *dev, const u32 address, + const u32 write_size, const u32 *write_buffer, + const u32 read_size, u32 *actual_size, u32 *read_buffer); +void thc_interrupt_config(struct thc_device *dev); +void thc_int_trigger_type_select(struct thc_device *dev, bool edge_trigger); +void thc_interrupt_enable(struct thc_device *dev, bool int_enable); +void thc_set_pio_interrupt_support(struct thc_device *dev, bool supported); +int thc_interrupt_quiesce(const struct thc_device *dev, bool int_quiesce); +void thc_ltr_config(struct thc_device *dev, u32 active_ltr_us, u32 lp_ltr_us); +void thc_change_ltr_mode(struct thc_device *dev, u32 ltr_mode); +void thc_ltr_unconfig(struct thc_device *dev); +u32 thc_int_cause_read(struct thc_device *dev); +int thc_interrupt_handler(struct thc_device *dev); +int thc_port_select(struct thc_device *dev, enum thc_port_type port_type); +int thc_spi_read_config(struct thc_device *dev, u32 spi_freq_val, + u32 io_mode, u32 opcode, u32 spi_rd_mps); +int thc_spi_write_config(struct thc_device *dev, u32 spi_freq_val, + u32 io_mode, u32 opcode, u32 spi_wr_mps, u32 perf_limit); +void thc_spi_input_output_address_config(struct thc_device *dev, u32 input_hdr_addr, + u32 input_bdy_addr, u32 output_addr); +int thc_i2c_subip_init(struct thc_device *dev, const u32 target_address, + const u32 speed, const u32 hcnt, const u32 lcnt); +int thc_i2c_subip_regs_save(struct thc_device *dev); +int thc_i2c_subip_regs_restore(struct thc_device *dev); + +#endif /* _INTEL_THC_DEV_H_ */ diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c new file mode 100644 index 000000000000..eb23bea77686 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c @@ -0,0 +1,969 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#include +#include +#include +#include +#include + +#include "intel-thc-dev.h" +#include "intel-thc-dma.h" +#include "intel-thc-hw.h" + +static void dma_set_prd_base_addr(struct thc_device *dev, u64 physical_addr, + struct thc_dma_configuration *dma_config) +{ + u32 addr_high, addr_low; + + if (!dma_config->is_enabled) + return; + + addr_high = upper_32_bits(physical_addr); + addr_low = lower_32_bits(physical_addr); + + regmap_write(dev->thc_regmap, dma_config->prd_base_addr_high, addr_high); + regmap_write(dev->thc_regmap, dma_config->prd_base_addr_low, addr_low); +} + +static void dma_set_start_bit(struct thc_device *dev, + struct thc_dma_configuration *dma_config) +{ + u32 ctrl, mask, mbits, data, offset; + + if (!dma_config->is_enabled) + return; + + switch (dma_config->dma_channel) { + case THC_RXDMA1: + case THC_RXDMA2: + if (dma_config->dma_channel == THC_RXDMA2) { + mbits = FIELD_PREP(THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_DATA_VAL, + THC_BITMASK_INTERRUPT_TYPE_DATA); + mask = THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_DATA_VAL; + regmap_write_bits(dev->thc_regmap, + THC_M_PRT_DEVINT_CFG_1_OFFSET, mask, mbits); + } + + mbits = THC_M_PRT_READ_DMA_CNTRL_IE_EOF | + THC_M_PRT_READ_DMA_CNTRL_SOO | + THC_M_PRT_READ_DMA_CNTRL_IE_STALL | + THC_M_PRT_READ_DMA_CNTRL_IE_ERROR | + THC_M_PRT_READ_DMA_CNTRL_START; + + mask = THC_M_PRT_READ_DMA_CNTRL_TPCWP | mbits; + mask |= THC_M_PRT_READ_DMA_CNTRL_INT_SW_DMA_EN; + ctrl = FIELD_PREP(THC_M_PRT_READ_DMA_CNTRL_TPCWP, THC_POINTER_WRAPAROUND) | mbits; + offset = dma_config->dma_channel == THC_RXDMA1 ? + THC_M_PRT_READ_DMA_CNTRL_1_OFFSET : THC_M_PRT_READ_DMA_CNTRL_2_OFFSET; + regmap_write_bits(dev->thc_regmap, offset, mask, ctrl); + break; + + case THC_SWDMA: + mbits = THC_M_PRT_READ_DMA_CNTRL_IE_DMACPL | + THC_M_PRT_READ_DMA_CNTRL_IE_IOC | + THC_M_PRT_READ_DMA_CNTRL_SOO | + THC_M_PRT_READ_DMA_CNTRL_START; + + mask = THC_M_PRT_READ_DMA_CNTRL_TPCWP | mbits; + ctrl = FIELD_PREP(THC_M_PRT_READ_DMA_CNTRL_TPCWP, THC_POINTER_WRAPAROUND) | mbits; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_SW_OFFSET, + mask, ctrl); + break; + + case THC_TXDMA: + regmap_write_bits(dev->thc_regmap, THC_M_PRT_WRITE_INT_STS_OFFSET, + THC_M_PRT_WRITE_INT_STS_THC_WRDMA_CMPL_STATUS, + THC_M_PRT_WRITE_INT_STS_THC_WRDMA_CMPL_STATUS); + + /* Select interrupt or polling method upon Write completion */ + if (dev->dma_ctx->use_write_interrupts) + data = THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_IE_IOC_DMACPL; + else + data = 0; + + data |= THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_START; + mask = THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_IE_IOC_DMACPL | + THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_START; + regmap_write_bits(dev->thc_regmap, THC_M_PRT_WRITE_DMA_CNTRL_OFFSET, + mask, data); + break; + + default: + break; + } +} + +static void dma_set_prd_control(struct thc_device *dev, u8 entry_count, u8 cb_depth, + struct thc_dma_configuration *dma_config) +{ + u32 ctrl, mask; + + if (!dma_config->is_enabled) + return; + + if (dma_config->dma_channel == THC_TXDMA) { + mask = THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_PTEC; + ctrl = FIELD_PREP(THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_PTEC, entry_count); + } else { + mask = THC_M_PRT_RPRD_CNTRL_PTEC | THC_M_PRT_RPRD_CNTRL_PCD; + ctrl = FIELD_PREP(THC_M_PRT_RPRD_CNTRL_PTEC, entry_count) | + FIELD_PREP(THC_M_PRT_RPRD_CNTRL_PCD, cb_depth); + } + + regmap_write_bits(dev->thc_regmap, dma_config->prd_cntrl, mask, ctrl); +} + +static void dma_clear_prd_control(struct thc_device *dev, + struct thc_dma_configuration *dma_config) +{ + u32 mask; + + if (!dma_config->is_enabled) + return; + + if (dma_config->dma_channel == THC_TXDMA) + mask = THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_PTEC; + else + mask = THC_M_PRT_RPRD_CNTRL_PTEC | THC_M_PRT_RPRD_CNTRL_PCD; + + regmap_write_bits(dev->thc_regmap, dma_config->prd_cntrl, mask, 0); +} + +static u8 dma_get_read_pointer(struct thc_device *dev, + struct thc_dma_configuration *dma_config) +{ + u32 ctrl, read_pointer; + + regmap_read(dev->thc_regmap, dma_config->dma_cntrl, &ctrl); + read_pointer = FIELD_GET(THC_M_PRT_READ_DMA_CNTRL_TPCRP, ctrl); + + dev_dbg(dev->dev, "THC_M_PRT_READ_DMA_CNTRL 0x%x offset 0x%x TPCRP 0x%x\n", + ctrl, dma_config->dma_cntrl, read_pointer); + + return read_pointer; +} + +static u8 dma_get_write_pointer(struct thc_device *dev, + struct thc_dma_configuration *dma_config) +{ + u32 ctrl, write_pointer; + + regmap_read(dev->thc_regmap, dma_config->dma_cntrl, &ctrl); + write_pointer = FIELD_GET(THC_M_PRT_READ_DMA_CNTRL_TPCWP, ctrl); + + dev_dbg(dev->dev, "THC_M_PRT_READ_DMA_CNTRL 0x%x offset 0x%x TPCWP 0x%x\n", + ctrl, dma_config->dma_cntrl, write_pointer); + + return write_pointer; +} + +static void dma_set_write_pointer(struct thc_device *dev, u8 value, + struct thc_dma_configuration *dma_config) +{ + u32 ctrl, mask; + + mask = THC_M_PRT_READ_DMA_CNTRL_TPCWP; + ctrl = FIELD_PREP(THC_M_PRT_READ_DMA_CNTRL_TPCWP, value); + regmap_write_bits(dev->thc_regmap, dma_config->dma_cntrl, mask, ctrl); +} + +static size_t dma_get_max_packet_size(struct thc_device *dev, + struct thc_dma_configuration *dma_config) +{ + return dma_config->max_packet_size; +} + +static void dma_set_max_packet_size(struct thc_device *dev, size_t size, + struct thc_dma_configuration *dma_config) +{ + if (size) { + dma_config->max_packet_size = ALIGN(size, SZ_4K); + dma_config->is_enabled = true; + } +} + +static void thc_copy_one_sgl_to_prd(struct thc_device *dev, + struct thc_dma_configuration *config, + unsigned int ind) +{ + struct thc_prd_table *prd_tbl; + struct scatterlist *sg; + int j; + + prd_tbl = &config->prd_tbls[ind]; + + for_each_sg(config->sgls[ind], sg, config->sgls_nent[ind], j) { + prd_tbl->entries[j].dest_addr = + sg_dma_address(sg) >> THC_ADDRESS_SHIFT; + prd_tbl->entries[j].len = sg_dma_len(sg); + prd_tbl->entries[j].hw_status = 0; + prd_tbl->entries[j].end_of_prd = 0; + } + + /* Set the end_of_prd flag in the last filled entry */ + if (j > 0) + prd_tbl->entries[j - 1].end_of_prd = 1; +} + +static void thc_copy_sgls_to_prd(struct thc_device *dev, + struct thc_dma_configuration *config) +{ + unsigned int i; + + memset(config->prd_tbls, 0, array_size(PRD_TABLE_SIZE, config->prd_tbl_num)); + + for (i = 0; i < config->prd_tbl_num; i++) + thc_copy_one_sgl_to_prd(dev, config, i); +} + +static int setup_dma_buffers(struct thc_device *dev, + struct thc_dma_configuration *config, + enum dma_data_direction dir) +{ + size_t prd_tbls_size = array_size(PRD_TABLE_SIZE, config->prd_tbl_num); + unsigned int i, nent = PRD_ENTRIES_NUM; + dma_addr_t dma_handle; + void *cpu_addr; + size_t buf_sz; + int count; + + if (!config->is_enabled) + return 0; + + memset(config->sgls, 0, sizeof(config->sgls)); + memset(config->sgls_nent, 0, sizeof(config->sgls_nent)); + + cpu_addr = dma_alloc_coherent(dev->dev, prd_tbls_size, + &dma_handle, GFP_KERNEL); + if (!cpu_addr) + return -ENOMEM; + + config->prd_tbls = cpu_addr; + config->prd_tbls_dma_handle = dma_handle; + + buf_sz = dma_get_max_packet_size(dev, config); + + /* Allocate and map the scatter-gather lists, one for each PRD table */ + for (i = 0; i < config->prd_tbl_num; i++) { + config->sgls[i] = sgl_alloc(buf_sz, GFP_KERNEL, &nent); + if (!config->sgls[i] || nent > PRD_ENTRIES_NUM) { + dev_err_once(dev->dev, "sgl_alloc (%uth) failed, nent %u\n", + i, nent); + return -ENOMEM; + } + count = dma_map_sg(dev->dev, config->sgls[i], nent, dir); + + config->sgls_nent[i] = count; + } + + thc_copy_sgls_to_prd(dev, config); + + return 0; +} + +static void thc_reset_dma_settings(struct thc_device *dev) +{ + /* Stop all DMA channels and reset DMA read pointers */ + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_1_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_START, 0); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_2_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_START, 0); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_SW_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_START, 0); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_WRITE_DMA_CNTRL_OFFSET, + THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_START, 0); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_1_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_TPCPR, + THC_M_PRT_READ_DMA_CNTRL_TPCPR); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_2_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_TPCPR, + THC_M_PRT_READ_DMA_CNTRL_TPCPR); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_SW_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_TPCPR, + THC_M_PRT_READ_DMA_CNTRL_TPCPR); +} + +static void release_dma_buffers(struct thc_device *dev, + struct thc_dma_configuration *config) +{ + size_t prd_tbls_size = array_size(PRD_TABLE_SIZE, config->prd_tbl_num); + unsigned int i; + + if (!config->is_enabled) + return; + + for (i = 0; i < config->prd_tbl_num; i++) { + if (!config->sgls[i] | !config->sgls_nent[i]) + continue; + + dma_unmap_sg(dev->dev, config->sgls[i], + config->sgls_nent[i], + config->dir); + + sgl_free(config->sgls[i]); + config->sgls[i] = NULL; + } + + memset(config->prd_tbls, 0, prd_tbls_size); + + if (config->prd_tbls) { + dma_free_coherent(dev->dev, prd_tbls_size, config->prd_tbls, + config->prd_tbls_dma_handle); + config->prd_tbls = NULL; + config->prd_tbls_dma_handle = 0; + } +} + +struct thc_dma_context *thc_dma_init(struct thc_device *dev) +{ + struct thc_dma_context *dma_ctx; + + dma_ctx = devm_kzalloc(dev->dev, sizeof(*dma_ctx), GFP_KERNEL); + if (!dma_ctx) + return NULL; + + dev->dma_ctx = dma_ctx; + + dma_ctx->dma_config[THC_RXDMA1].dma_channel = THC_RXDMA1; + dma_ctx->dma_config[THC_RXDMA2].dma_channel = THC_RXDMA2; + dma_ctx->dma_config[THC_TXDMA].dma_channel = THC_TXDMA; + dma_ctx->dma_config[THC_SWDMA].dma_channel = THC_SWDMA; + + dma_ctx->dma_config[THC_RXDMA1].dir = DMA_FROM_DEVICE; + dma_ctx->dma_config[THC_RXDMA2].dir = DMA_FROM_DEVICE; + dma_ctx->dma_config[THC_TXDMA].dir = DMA_TO_DEVICE; + dma_ctx->dma_config[THC_SWDMA].dir = DMA_FROM_DEVICE; + + dma_ctx->dma_config[THC_RXDMA1].prd_tbl_num = PRD_TABLES_NUM; + dma_ctx->dma_config[THC_RXDMA2].prd_tbl_num = PRD_TABLES_NUM; + dma_ctx->dma_config[THC_TXDMA].prd_tbl_num = 1; + dma_ctx->dma_config[THC_SWDMA].prd_tbl_num = 1; + + dma_ctx->dma_config[THC_RXDMA1].prd_base_addr_high = THC_M_PRT_RPRD_BA_HI_1_OFFSET; + dma_ctx->dma_config[THC_RXDMA2].prd_base_addr_high = THC_M_PRT_RPRD_BA_HI_2_OFFSET; + dma_ctx->dma_config[THC_TXDMA].prd_base_addr_high = THC_M_PRT_WPRD_BA_HI_OFFSET; + dma_ctx->dma_config[THC_SWDMA].prd_base_addr_high = THC_M_PRT_RPRD_BA_HI_SW_OFFSET; + + dma_ctx->dma_config[THC_RXDMA1].prd_base_addr_low = THC_M_PRT_RPRD_BA_LOW_1_OFFSET; + dma_ctx->dma_config[THC_RXDMA2].prd_base_addr_low = THC_M_PRT_RPRD_BA_LOW_2_OFFSET; + dma_ctx->dma_config[THC_TXDMA].prd_base_addr_low = THC_M_PRT_WPRD_BA_LOW_OFFSET; + dma_ctx->dma_config[THC_SWDMA].prd_base_addr_low = THC_M_PRT_RPRD_BA_LOW_SW_OFFSET; + + dma_ctx->dma_config[THC_RXDMA1].prd_cntrl = THC_M_PRT_RPRD_CNTRL_1_OFFSET; + dma_ctx->dma_config[THC_RXDMA2].prd_cntrl = THC_M_PRT_RPRD_CNTRL_2_OFFSET; + dma_ctx->dma_config[THC_TXDMA].prd_cntrl = THC_M_PRT_WRITE_DMA_CNTRL_OFFSET; + dma_ctx->dma_config[THC_SWDMA].prd_cntrl = THC_M_PRT_RPRD_CNTRL_SW_OFFSET; + + dma_ctx->dma_config[THC_RXDMA1].dma_cntrl = THC_M_PRT_READ_DMA_CNTRL_1_OFFSET; + dma_ctx->dma_config[THC_RXDMA2].dma_cntrl = THC_M_PRT_READ_DMA_CNTRL_2_OFFSET; + dma_ctx->dma_config[THC_TXDMA].dma_cntrl = THC_M_PRT_WRITE_DMA_CNTRL_OFFSET; + dma_ctx->dma_config[THC_SWDMA].dma_cntrl = THC_M_PRT_READ_DMA_CNTRL_SW_OFFSET; + + /* Enable write DMA completion interrupt by default */ + dma_ctx->use_write_interrupts = 1; + + return dma_ctx; +} + +/** + * thc_dma_set_max_packet_sizes - Set max packet sizes for all DMA engines + * + * @dev: The pointer of THC private device context + * @mps_read1: RxDMA1 max packet size + * @mps_read2: RxDMA2 max packet size + * @mps_write: TxDMA max packet size + * @mps_swdma: Software DMA max packet size + * + * If mps is not 0, it means the corresponding DMA channel is used, then set + * the flag to turn on this channel. + * + * Return: 0 on success, other error codes on failed. + */ +int thc_dma_set_max_packet_sizes(struct thc_device *dev, size_t mps_read1, + size_t mps_read2, size_t mps_write, + size_t mps_swdma) +{ + if (!dev->dma_ctx) { + dev_err_once(dev->dev, + "Cannot set max packet sizes because DMA context is NULL!\n"); + return -EINVAL; + } + + dma_set_max_packet_size(dev, mps_read1, &dev->dma_ctx->dma_config[THC_RXDMA1]); + dma_set_max_packet_size(dev, mps_read2, &dev->dma_ctx->dma_config[THC_RXDMA2]); + dma_set_max_packet_size(dev, mps_write, &dev->dma_ctx->dma_config[THC_TXDMA]); + dma_set_max_packet_size(dev, mps_swdma, &dev->dma_ctx->dma_config[THC_SWDMA]); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(thc_dma_set_max_packet_sizes, "INTEL_THC"); + +/** + * thc_dma_allocate - Allocate DMA buffers for all DMA engines + * + * @dev: The pointer of THC private device context + * + * Return: 0 on success, other error codes on failed. + */ +int thc_dma_allocate(struct thc_device *dev) +{ + int ret, chan; + + for (chan = 0; chan < MAX_THC_DMA_CHANNEL; chan++) { + ret = setup_dma_buffers(dev, &dev->dma_ctx->dma_config[chan], + dev->dma_ctx->dma_config[chan].dir); + if (ret < 0) { + dev_err_once(dev->dev, "DMA setup failed for DMA channel %d\n", chan); + goto release_bufs; + } + } + + return 0; + +release_bufs: + while (chan--) + release_dma_buffers(dev, &dev->dma_ctx->dma_config[chan]); + + return ret; +} +EXPORT_SYMBOL_NS_GPL(thc_dma_allocate, "INTEL_THC"); + +/** + * thc_dma_release - Release DMA buffers for all DMA engines + * + * @dev: The pointer of THC private device context + */ +void thc_dma_release(struct thc_device *dev) +{ + int chan; + + for (chan = 0; chan < MAX_THC_DMA_CHANNEL; chan++) + release_dma_buffers(dev, &dev->dma_ctx->dma_config[chan]); +} +EXPORT_SYMBOL_NS_GPL(thc_dma_release, "INTEL_THC"); + +static int calc_prd_entries_num(struct thc_prd_table *prd_tbl, + size_t mes_len, u8 *nent) +{ + *nent = DIV_ROUND_UP(mes_len, THC_MIN_BYTES_PER_SG_LIST_ENTRY); + if (*nent > PRD_ENTRIES_NUM) + return -EMSGSIZE; + + return 0; +} + +static size_t calc_message_len(struct thc_prd_table *prd_tbl, u8 *nent) +{ + size_t mes_len = 0; + unsigned int j; + + for (j = 0; j < PRD_ENTRIES_NUM; j++) { + mes_len += prd_tbl->entries[j].len; + if (prd_tbl->entries[j].end_of_prd) + break; + } + + *nent = j + 1; + + return mes_len; +} + +/** + * thc_dma_configure - Configure DMA settings for all DMA engines + * + * @dev: The pointer of THC private device context + * + * Return: 0 on success, other error codes on failed. + */ +int thc_dma_configure(struct thc_device *dev) +{ + struct thc_dma_context *dma_ctx = dev->dma_ctx; + int chan; + + thc_reset_dma_settings(dev); + + if (!dma_ctx) { + dev_err_once(dev->dev, "Cannot do DMA configure because DMA context is NULL\n"); + return -EINVAL; + } + + for (chan = 0; chan < MAX_THC_DMA_CHANNEL; chan++) { + dma_set_prd_base_addr(dev, + dma_ctx->dma_config[chan].prd_tbls_dma_handle, + &dma_ctx->dma_config[chan]); + + dma_set_prd_control(dev, PRD_ENTRIES_NUM - 1, + dma_ctx->dma_config[chan].prd_tbl_num - 1, + &dma_ctx->dma_config[chan]); + } + + /* Start read2 DMA engine */ + dma_set_start_bit(dev, &dma_ctx->dma_config[THC_RXDMA2]); + + dev_dbg(dev->dev, "DMA configured successfully!\n"); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(thc_dma_configure, "INTEL_THC"); + +/** + * thc_dma_unconfigure - Unconfigure DMA settings for all DMA engines + * + * @dev: The pointer of THC private device context + */ +void thc_dma_unconfigure(struct thc_device *dev) +{ + int chan; + + for (chan = 0; chan < MAX_THC_DMA_CHANNEL; chan++) { + dma_set_prd_base_addr(dev, 0, &dev->dma_ctx->dma_config[chan]); + dma_clear_prd_control(dev, &dev->dma_ctx->dma_config[chan]); + } + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_1_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_START, 0); + + regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_2_OFFSET, + THC_M_PRT_READ_DMA_CNTRL_START, 0); +} +EXPORT_SYMBOL_NS_GPL(thc_dma_unconfigure, "INTEL_THC"); + +static int thc_wait_for_dma_pause(struct thc_device *dev, enum thc_dma_channel channel) +{ + u32 ctrl_reg, sts_reg, sts; + int ret; + + ctrl_reg = (channel == THC_RXDMA1) ? THC_M_PRT_READ_DMA_CNTRL_1_OFFSET : + ((channel == THC_RXDMA2) ? THC_M_PRT_READ_DMA_CNTRL_2_OFFSET : + THC_M_PRT_READ_DMA_CNTRL_SW_OFFSET); + + regmap_write_bits(dev->thc_regmap, ctrl_reg, THC_M_PRT_READ_DMA_CNTRL_START, 0); + + sts_reg = (channel == THC_RXDMA1) ? THC_M_PRT_READ_DMA_INT_STS_1_OFFSET : + ((channel == THC_RXDMA2) ? THC_M_PRT_READ_DMA_INT_STS_2_OFFSET : + THC_M_PRT_READ_DMA_INT_STS_SW_OFFSET); + + ret = regmap_read_poll_timeout(dev->thc_regmap, sts_reg, sts, + !(sts & THC_M_PRT_READ_DMA_INT_STS_ACTIVE), + THC_DEFAULT_RXDMA_POLLING_US_INTERVAL, + THC_DEFAULT_RXDMA_POLLING_US_TIMEOUT); + + if (ret) { + dev_err_once(dev->dev, + "Timeout while waiting for DMA %d stop\n", channel); + return ret; + } + + return 0; +} + +static int read_dma_buffer(struct thc_device *dev, + struct thc_dma_configuration *read_config, + u8 prd_table_index, void *read_buff) +{ + struct thc_prd_table *prd_tbl; + struct scatterlist *sg; + size_t mes_len, ret; + u8 nent; + + if (prd_table_index >= read_config->prd_tbl_num) { + dev_err_once(dev->dev, "PRD table index %d too big\n", prd_table_index); + return -EINVAL; + } + + prd_tbl = &read_config->prd_tbls[prd_table_index]; + mes_len = calc_message_len(prd_tbl, &nent); + if (mes_len > read_config->max_packet_size) { + dev_err(dev->dev, + "Message length %zu is bigger than buffer length %lu\n", + mes_len, read_config->max_packet_size); + return -EMSGSIZE; + } + + sg = read_config->sgls[prd_table_index]; + ret = sg_copy_to_buffer(sg, nent, read_buff, mes_len); + if (ret != mes_len) { + dev_err_once(dev->dev, "Copied %zu bytes instead of requested %zu\n", + ret, mes_len); + return -EIO; + } + + return mes_len; +} + +static void update_write_pointer(struct thc_device *dev, + struct thc_dma_configuration *read_config) +{ + u8 write_ptr = dma_get_write_pointer(dev, read_config); + + if (write_ptr + 1 == THC_WRAPAROUND_VALUE_ODD) + dma_set_write_pointer(dev, THC_POINTER_WRAPAROUND, read_config); + else if (write_ptr + 1 == THC_WRAPAROUND_VALUE_EVEN) + dma_set_write_pointer(dev, 0, read_config); + else + dma_set_write_pointer(dev, write_ptr + 1, read_config); +} + +static int is_dma_buf_empty(struct thc_device *dev, + struct thc_dma_configuration *read_config, + u8 *read_ptr, u8 *write_ptr) +{ + *read_ptr = dma_get_read_pointer(dev, read_config); + *write_ptr = dma_get_write_pointer(dev, read_config); + + if ((*read_ptr & THC_POINTER_MASK) == (*write_ptr & THC_POINTER_MASK)) + if (*read_ptr != *write_ptr) + return true; + + return false; +} + +static int thc_dma_read(struct thc_device *dev, + struct thc_dma_configuration *read_config, + void *read_buff, size_t *read_len, int *read_finished) +{ + u8 read_ptr, write_ptr, prd_table_index; + int status; + + if (!is_dma_buf_empty(dev, read_config, &read_ptr, &write_ptr)) { + prd_table_index = write_ptr & THC_POINTER_MASK; + + status = read_dma_buffer(dev, read_config, prd_table_index, read_buff); + if (status <= 0) { + dev_err_once(dev->dev, "read DMA buffer failed %d\n", status); + return -EIO; + } + + *read_len = status; + + /* Clear the relevant PRD table */ + thc_copy_one_sgl_to_prd(dev, read_config, prd_table_index); + + /* Increment the write pointer to let the HW know we have processed this PRD */ + update_write_pointer(dev, read_config); + } + + /* + * This function only reads one frame from PRD table for each call, so we need to + * check if all DMAed data is read out and return the flag to the caller. Caller + * should repeatedly call thc_dma_read() until all DMAed data is handled. + */ + if (read_finished) + *read_finished = is_dma_buf_empty(dev, read_config, &read_ptr, &write_ptr) ? 1 : 0; + + return 0; +} + +/** + * thc_rxdma_read - Read data from RXDMA buffer + * + * @dev: The pointer of THC private device context + * @dma_channel: The RXDMA engine of read data source + * @read_buff: The pointer of the read data buffer + * @read_len: The pointer of the read data length + * @read_finished: The pointer of the flag indicating if all pending data has been read out + * + * Return: 0 on success, other error codes on failed. + */ +int thc_rxdma_read(struct thc_device *dev, enum thc_dma_channel dma_channel, + void *read_buff, size_t *read_len, int *read_finished) +{ + struct thc_dma_configuration *dma_config; + int ret; + + dma_config = &dev->dma_ctx->dma_config[dma_channel]; + + if (!dma_config->is_enabled) { + dev_err_once(dev->dev, "The DMA channel %d is not enabled", dma_channel); + return -EINVAL; + } + + if (!read_buff || !read_len) { + dev_err(dev->dev, "Invalid input parameters, read_buff %p, read_len %p\n", + read_buff, read_len); + return -EINVAL; + } + + if (dma_channel >= THC_TXDMA) { + dev_err(dev->dev, "Unsupported DMA channel for RxDMA read, %d\n", dma_channel); + return -EINVAL; + } + + ret = thc_dma_read(dev, dma_config, read_buff, read_len, read_finished); + + return ret; +} +EXPORT_SYMBOL_NS_GPL(thc_rxdma_read, "INTEL_THC"); + +static int thc_swdma_read_start(struct thc_device *dev, void *write_buff, + size_t write_len, u32 *prd_tbl_len) +{ + u32 mask, val, data0 = 0, data1 = 0; + int ret; + + ret = thc_interrupt_quiesce(dev, true); + if (ret) + return ret; + + if (thc_wait_for_dma_pause(dev, THC_RXDMA1) || thc_wait_for_dma_pause(dev, THC_RXDMA2)) + return -EIO; + + thc_reset_dma_settings(dev); + + mask = THC_M_PRT_RPRD_CNTRL_SW_THC_SWDMA_I2C_WBC | + THC_M_PRT_RPRD_CNTRL_SW_THC_SWDMA_I2C_RX_DLEN_EN; + val = FIELD_PREP(THC_M_PRT_RPRD_CNTRL_SW_THC_SWDMA_I2C_WBC, write_len) | + ((!prd_tbl_len) ? THC_M_PRT_RPRD_CNTRL_SW_THC_SWDMA_I2C_RX_DLEN_EN : 0); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_RPRD_CNTRL_SW_OFFSET, + mask, val); + + if (prd_tbl_len) { + mask = THC_M_PRT_SW_DMA_PRD_TABLE_LEN_THC_M_PRT_SW_DMA_PRD_TABLE_LEN; + val = FIELD_PREP(THC_M_PRT_SW_DMA_PRD_TABLE_LEN_THC_M_PRT_SW_DMA_PRD_TABLE_LEN, + *prd_tbl_len); + regmap_write_bits(dev->thc_regmap, THC_M_PRT_SW_DMA_PRD_TABLE_LEN_OFFSET, + mask, val); + } + + if (write_len <= sizeof(u32)) { + for (int i = 0; i < write_len; i++) + data0 |= *(((u8 *)write_buff) + i) << (i * 8); + + regmap_write(dev->thc_regmap, THC_M_PRT_SW_SEQ_DATA0_ADDR_OFFSET, data0); + } else if (write_len <= 2 * sizeof(u32)) { + data0 = *(u32 *)write_buff; + regmap_write(dev->thc_regmap, THC_M_PRT_SW_SEQ_DATA0_ADDR_OFFSET, data0); + + for (int i = 0; i < write_len - sizeof(u32); i++) + data1 |= *(((u8 *)write_buff) + sizeof(u32) + i) << (i * 8); + + regmap_write(dev->thc_regmap, THC_M_PRT_SW_SEQ_DATA1_OFFSET, data1); + } + dma_set_start_bit(dev, &dev->dma_ctx->dma_config[THC_SWDMA]); + + return 0; +} + +static int thc_swdma_read_completion(struct thc_device *dev) +{ + int ret; + + ret = thc_wait_for_dma_pause(dev, THC_SWDMA); + if (ret) + return ret; + + thc_reset_dma_settings(dev); + + dma_set_start_bit(dev, &dev->dma_ctx->dma_config[THC_RXDMA2]); + + ret = thc_interrupt_quiesce(dev, false); + + return ret; +} + +/** + * thc_swdma_read - Use software DMA to read data from touch device + * + * @dev: The pointer of THC private device context + * @write_buff: The pointer of write buffer for SWDMA sequence + * @write_len: The write data length for SWDMA sequence + * @prd_tbl_len: The prd table length of SWDMA engine, can be set to NULL + * @read_buff: The pointer of the read data buffer + * @read_len: The pointer of the read data length + * + * Return: 0 on success, other error codes on failed. + */ +int thc_swdma_read(struct thc_device *dev, void *write_buff, size_t write_len, + u32 *prd_tbl_len, void *read_buff, size_t *read_len) +{ + int ret; + + if (!(&dev->dma_ctx->dma_config[THC_SWDMA])->is_enabled) { + dev_err_once(dev->dev, "The SWDMA channel is not enabled"); + return -EINVAL; + } + + if (!read_buff || !read_len) { + dev_err(dev->dev, "Invalid input parameters, read_buff %p, read_len %p\n", + read_buff, read_len); + return -EINVAL; + } + + if (mutex_lock_interruptible(&dev->thc_bus_lock)) + return -EINTR; + + dev->swdma_done = false; + + ret = thc_swdma_read_start(dev, write_buff, write_len, prd_tbl_len); + if (ret) + goto end; + + ret = wait_event_interruptible_timeout(dev->swdma_complete_wait, dev->swdma_done, 1 * HZ); + if (ret <= 0 || !dev->swdma_done) { + dev_err_once(dev->dev, "timeout for waiting SWDMA completion\n"); + ret = -ETIMEDOUT; + goto end; + } + + ret = thc_dma_read(dev, &dev->dma_ctx->dma_config[THC_SWDMA], read_buff, read_len, NULL); + if (ret) + goto end; + + ret = thc_swdma_read_completion(dev); + +end: + mutex_unlock(&dev->thc_bus_lock); + return ret; +} +EXPORT_SYMBOL_NS_GPL(thc_swdma_read, "INTEL_THC"); + +static int write_dma_buffer(struct thc_device *dev, + void *buffer, size_t buf_len) +{ + struct thc_dma_configuration *write_config = &dev->dma_ctx->dma_config[THC_TXDMA]; + struct thc_prd_table *prd_tbl; + struct scatterlist *sg; + unsigned long len_left; + size_t ret; + u8 nent; + int i; + + /* There is only one PRD table for write */ + prd_tbl = &write_config->prd_tbls[0]; + + if (calc_prd_entries_num(prd_tbl, buf_len, &nent) < 0) { + dev_err(dev->dev, "Tx message length too big (%zu)\n", buf_len); + return -EOVERFLOW; + } + + sg = write_config->sgls[0]; + ret = sg_copy_from_buffer(sg, nent, buffer, buf_len); + if (ret != buf_len) { + dev_err_once(dev->dev, "Copied %zu bytes instead of requested %zu\n", + ret, buf_len); + return -EIO; + } + + prd_tbl = &write_config->prd_tbls[0]; + len_left = buf_len; + + for_each_sg(write_config->sgls[0], sg, write_config->sgls_nent[0], i) { + if (sg_dma_address(sg) == 0 || sg_dma_len(sg) == 0) { + dev_err_once(dev->dev, "SGList: zero address or length\n"); + return -EINVAL; + } + + prd_tbl->entries[i].dest_addr = + sg_dma_address(sg) >> THC_ADDRESS_SHIFT; + + if (len_left < sg_dma_len(sg)) { + prd_tbl->entries[i].len = len_left; + prd_tbl->entries[i].end_of_prd = 1; + break; + } + + prd_tbl->entries[i].len = sg_dma_len(sg); + prd_tbl->entries[i].end_of_prd = 0; + + len_left -= sg_dma_len(sg); + } + + dma_set_prd_control(dev, i, 0, write_config); + + return 0; +} + +static void thc_ensure_performance_limitations(struct thc_device *dev) +{ + unsigned long delay_usec = 0; + /* + * Minimum amount of delay the THC / QUICKSPI driver must wait + * between end of write operation and begin of read operation. + * This value shall be in 10us multiples. + */ + if (dev->perf_limit > 0) { + delay_usec = dev->perf_limit * 10; + udelay(delay_usec); + } +} + +static void thc_dma_write_completion(struct thc_device *dev) +{ + thc_ensure_performance_limitations(dev); +} + +/** + * thc_dma_write - Use TXDMA to write data to touch device + * + * @dev: The pointer of THC private device context + * @buffer: The pointer of write data buffer + * @buf_len: The write data length + * + * Return: 0 on success, other error codes on failed. + */ +int thc_dma_write(struct thc_device *dev, void *buffer, size_t buf_len) +{ + bool restore_interrupts = false; + u32 sts, ctrl; + int ret; + + if (!(&dev->dma_ctx->dma_config[THC_TXDMA])->is_enabled) { + dev_err_once(dev->dev, "The TxDMA channel is not enabled\n"); + return -EINVAL; + } + + if (!buffer || buf_len <= 0) { + dev_err(dev->dev, "Invalid input parameters, buffer %p\n, buf_len %zu\n", + buffer, buf_len); + return -EINVAL; + } + + regmap_read(dev->thc_regmap, THC_M_PRT_WRITE_INT_STS_OFFSET, &sts); + if (sts & THC_M_PRT_WRITE_INT_STS_THC_WRDMA_ACTIVE) { + dev_err_once(dev->dev, "THC TxDMA is till active and can't start again\n"); + return -EBUSY; + } + + if (mutex_lock_interruptible(&dev->thc_bus_lock)) + return -EINTR; + + regmap_read(dev->thc_regmap, THC_M_PRT_CONTROL_OFFSET, &ctrl); + + ret = write_dma_buffer(dev, buffer, buf_len); + if (ret) + goto end; + + if (dev->perf_limit && !(ctrl & THC_M_PRT_CONTROL_THC_DEVINT_QUIESCE_HW_STS)) { + ret = thc_interrupt_quiesce(dev, true); + if (ret) + goto end; + + restore_interrupts = true; + } + + dev->write_done = false; + + dma_set_start_bit(dev, &dev->dma_ctx->dma_config[THC_TXDMA]); + + ret = wait_event_interruptible_timeout(dev->write_complete_wait, dev->write_done, 1 * HZ); + if (ret <= 0 || !dev->write_done) { + dev_err_once(dev->dev, "timeout for waiting TxDMA completion\n"); + ret = -ETIMEDOUT; + goto end; + } + + thc_dma_write_completion(dev); + mutex_unlock(&dev->thc_bus_lock); + return 0; + +end: + mutex_unlock(&dev->thc_bus_lock); + + if (restore_interrupts) + ret = thc_interrupt_quiesce(dev, false); + + return ret; +} +EXPORT_SYMBOL_NS_GPL(thc_dma_write, "INTEL_THC"); diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h new file mode 100644 index 000000000000..ca923ff2bef9 --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h @@ -0,0 +1,146 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#ifndef _INTEL_THC_DMA_H_ +#define _INTEL_THC_DMA_H_ + +#include +#include +#include +#include +#include + +#define THC_POINTER_MASK GENMASK(6, 0) +#define THC_POINTER_WRAPAROUND 0x80 +#define THC_WRAPAROUND_VALUE_ODD 0x10 +#define THC_WRAPAROUND_VALUE_EVEN 0x90 +#define THC_MIN_BYTES_PER_SG_LIST_ENTRY SZ_4K + +#define THC_DEFAULT_RXDMA_POLLING_US_INTERVAL 100 +#define THC_DEFAULT_RXDMA_POLLING_US_TIMEOUT (10 * USEC_PER_MSEC) + +/* + * THC needs 1KB aligned address, dest_addr is 54 bits, not 64, + * so don't need to send the lower 10-bits of address. + */ +#define THC_ADDRESS_SHIFT 10 + +/** + * THC DMA channels: + * @THC_RXDMA1: legacy channel, reserved for raw data reading + * @THC_RXDMA2: DMA to read HID data from touch device + * @THC_TXDMA: DMA to write to touch device + * @THC_SWDMA: SW triggered DMA to write and read from touch device + */ +enum thc_dma_channel { + THC_RXDMA1 = 0, + THC_RXDMA2 = 1, + THC_TXDMA = 2, + THC_SWDMA = 3, + MAX_THC_DMA_CHANNEL +}; + +/** + * THC DMA Physical Memory Descriptor (PRD) + * @dest_addr: bit[53:0], destination address in system memory + * @int_on_completion: bit[63], if set, thc will trigger interrupt to driver + * @len: bit[87:64], length of this entry + * @end_of_prd: bit[88], if set, this entry is last one of current PRD table + * @hw_status: bit[90:89], hw status bits + */ +struct thc_prd_entry { + u64 dest_addr : 54; + u64 reserved1 : 9; + u64 int_on_completion : 1; + u64 len : 24; + u64 end_of_prd : 1; + u64 hw_status : 2; + u64 reserved2 : 37; +}; + +/* + * Max OS memory fragmentation will be at a 4KB boundary, thus to address 1MB + * of virtually contiguous memory 256 PRD entries are required for a single + * PRD Table. SW writes the number of PRD Entries for each PRD table in the + * THC_M_PRT_RPRD_CNTRL.PTEC register field. The PRD entry's length must be + * multiple of 4KB except for the last entry in a PRD table. + * This is the max possible number of etries supported by HW, in practise we + * there will be less entries in each prd table(the actual number will be + * given by scatter-gather list allocation). + */ +#define PRD_ENTRIES_NUM 16 + +/* + * Number of PRD tables equals to number of data buffers. + * The max number of PRD tables supported by the HW is 128, + * but we allocate only 16. + */ +#define PRD_TABLES_NUM 16 + +/* THC DMA Physical Memory Descriptor Table */ +struct thc_prd_table { + struct thc_prd_entry entries[PRD_ENTRIES_NUM]; +}; + +#define PRD_TABLE_SIZE sizeof(struct thc_prd_table) + +/** + * struct thc_dma_configuration - THC DMA configure + * @dma_channel: DMA channel for current DMA configuration + * @prd_tbls_dma_handle: DMA buffer handle + * @dir: direction of DMA for this config + * @prd_tbls: PRD tables for current DMA + * @sgls: array of pointers to scatter-gather lists + * @sgls_nent: actual number of entries per sg list + * @prd_tbl_num: actual number of PRD tables + * @max_packet_size: size of the buffer needed for 1 DMA message (1 PRD table) + * @prd_base_addr_high: High 32bits memory address where stores PRD table + * @prd_base_addr_low: low 32bits memory address where stores PRD table + * @prd_cntrl: PRD control register value + * @dma_cntrl: DMA control register value + */ +struct thc_dma_configuration { + enum thc_dma_channel dma_channel; + dma_addr_t prd_tbls_dma_handle; + enum dma_data_direction dir; + bool is_enabled; + + struct thc_prd_table *prd_tbls; + struct scatterlist *sgls[PRD_TABLES_NUM]; + u8 sgls_nent[PRD_TABLES_NUM]; + u8 prd_tbl_num; + + size_t max_packet_size; + u32 prd_base_addr_high; + u32 prd_base_addr_low; + u32 prd_cntrl; + u32 dma_cntrl; +}; + +/* + * THC DMA context + * Store all THC Channel configures + */ +struct thc_dma_context { + struct thc_dma_configuration dma_config[MAX_THC_DMA_CHANNEL]; + u8 use_write_interrupts; +}; + +struct thc_device; + +int thc_dma_set_max_packet_sizes(struct thc_device *dev, + size_t mps_read1, size_t mps_read2, + size_t mps_write, size_t mps_swdma); +int thc_dma_allocate(struct thc_device *dev); +int thc_dma_configure(struct thc_device *dev); +void thc_dma_unconfigure(struct thc_device *dev); +void thc_dma_release(struct thc_device *dev); +int thc_rxdma_read(struct thc_device *dev, enum thc_dma_channel dma_channel, + void *read_buff, size_t *read_len, int *read_finished); +int thc_swdma_read(struct thc_device *dev, void *write_buff, size_t write_len, + u32 *prd_tbl_len, void *read_buff, size_t *read_len); +int thc_dma_write(struct thc_device *dev, void *buffer, size_t buf_len); + +struct thc_dma_context *thc_dma_init(struct thc_device *dev); + +#endif /* _INTEL_THC_DMA_H_ */ diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-hw.h b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-hw.h new file mode 100644 index 000000000000..6729c4c25dab --- /dev/null +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-hw.h @@ -0,0 +1,881 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Intel Corporation */ + +#ifndef _INTEL_THC_HW_H_ +#define _INTEL_THC_HW_H_ + +#include + +/* THC registers offset */ +/* Touch Host Controller Control Register */ +#define THC_M_PRT_CONTROL_OFFSET 0x1008 +/* THC SPI Bus Configuration Register */ +#define THC_M_PRT_SPI_CFG_OFFSET 0x1010 +/* THC SPI Bus Read Opcode Register */ +#define THC_M_PRT_SPI_ICRRD_OPCODE_OFFSET 0x1014 +/* THC SPI Bus Read Opcode Register */ +#define THC_M_PRT_SPI_DMARD_OPCODE_OFFSET 0x1018 +/* THC SPI Bus Write Opcode Register */ +#define THC_M_PRT_SPI_WR_OPCODE_OFFSET 0x101C +/* THC Interrupt Enable Register */ +#define THC_M_PRT_INT_EN_OFFSET 0x1020 +/* THC Interrupt Status Register */ +#define THC_M_PRT_INT_STATUS_OFFSET 0x1024 +/* THC Error Cause Register */ +#define THC_M_PRT_ERR_CAUSE_OFFSET 0x1028 +/* THC SW sequencing Control */ +#define THC_M_PRT_SW_SEQ_CNTRL_OFFSET 0x1040 +/* THC SW sequencing Status */ +#define THC_M_PRT_SW_SEQ_STS_OFFSET 0x1044 +/* THC SW Sequencing Data DW0 or SPI Address Register */ +#define THC_M_PRT_SW_SEQ_DATA0_ADDR_OFFSET 0x1048 +/* THC SW sequencing Data DW1 */ +#define THC_M_PRT_SW_SEQ_DATA1_OFFSET 0x104C +/* THC SW sequencing Data DW2 */ +#define THC_M_PRT_SW_SEQ_DATA2_OFFSET 0x1050 +/* THC SW sequencing Data DW3 */ +#define THC_M_PRT_SW_SEQ_DATA3_OFFSET 0x1054 +/* THC SW sequencing Data DW4 */ +#define THC_M_PRT_SW_SEQ_DATA4_OFFSET 0x1058 +/* THC SW sequencing Data DW5 */ +#define THC_M_PRT_SW_SEQ_DATA5_OFFSET 0x105C +/* THC SW sequencing Data DW6 */ +#define THC_M_PRT_SW_SEQ_DATA6_OFFSET 0x1060 +/* THC SW sequencing Data DW7 */ +#define THC_M_PRT_SW_SEQ_DATA7_OFFSET 0x1064 +/* THC SW sequencing Data DW8 */ +#define THC_M_PRT_SW_SEQ_DATA8_OFFSET 0x1068 +/* THC SW sequencing Data DW9 */ +#define THC_M_PRT_SW_SEQ_DATA9_OFFSET 0x106C +/* THC SW sequencing Data DW10 */ +#define THC_M_PRT_SW_SEQ_DATA10_OFFSET 0x1070 +/* THC SW sequencing Data DW11 */ +#define THC_M_PRT_SW_SEQ_DATA11_OFFSET 0x1074 +/* THC SW sequencing Data DW12 */ +#define THC_M_PRT_SW_SEQ_DATA12_OFFSET 0x1078 +/* THC SW sequencing Data DW13 */ +#define THC_M_PRT_SW_SEQ_DATA13_OFFSET 0x107C +/* THC SW sequencing Data DW14 */ +#define THC_M_PRT_SW_SEQ_DATA14_OFFSET 0x1080 +/* THC SW sequencing Data DW15 */ +#define THC_M_PRT_SW_SEQ_DATA15_OFFSET 0x1084 +/* THC SW sequencing Data DW16 */ +#define THC_M_PRT_SW_SEQ_DATA16_OFFSET 0x1088 +/* THC Write PRD Base Address Register Low */ +#define THC_M_PRT_WPRD_BA_LOW_OFFSET 0x1090 +/* THC Write PRD Base Address Register High */ +#define THC_M_PRT_WPRD_BA_HI_OFFSET 0x1094 +/* THC Write DMA Control */ +#define THC_M_PRT_WRITE_DMA_CNTRL_OFFSET 0x1098 +/* THC Write Interrupt Status */ +#define THC_M_PRT_WRITE_INT_STS_OFFSET 0x109C +/* THC Write DMA Error Register */ +#define THC_M_PRT_WRITE_DMA_ERR_OFFSET 0x10A0 +/* THC device address for the bulk write */ +#define THC_M_PRT_WR_BULK_ADDR_OFFSET 0x10B4 +/* THC Device Interrupt Cause Register Address */ +#define THC_M_PRT_DEV_INT_CAUSE_ADDR_OFFSET 0x10B8 +/* THC Device Interrupt Cause Register Value */ +#define THC_M_PRT_DEV_INT_CAUSE_REG_VAL_OFFSET 0x10BC +/* THC TXDMA Frame Count */ +#define THC_M_PRT_TX_FRM_CNT_OFFSET 0x10E0 +/* THC TXDMA Packet Count */ +#define THC_M_PRT_TXDMA_PKT_CNT_OFFSET 0x10E4 +/* THC Device Interrupt Count on this port */ +#define THC_M_PRT_DEVINT_CNT_OFFSET 0x10E8 +/* Touch Device Interrupt Cause register Format Configuration Register 1 */ +#define THC_M_PRT_DEVINT_CFG_1_OFFSET 0x10EC +/* Touch Device Interrupt Cause register Format Configuration Register 2 */ +#define THC_M_PRT_DEVINT_CFG_2_OFFSET 0x10F0 +/* THC Read PRD Base Address Low for the 1st RXDMA */ +#define THC_M_PRT_RPRD_BA_LOW_1_OFFSET 0x1100 +/* THC Read PRD Base Address High for the 1st RXDMA */ +#define THC_M_PRT_RPRD_BA_HI_1_OFFSET 0x1104 +/* THC Read PRD Control for the 1st RXDMA */ +#define THC_M_PRT_RPRD_CNTRL_1_OFFSET 0x1108 +/* THC Read DMA Control for the 1st RXDMA */ +#define THC_M_PRT_READ_DMA_CNTRL_1_OFFSET 0x110C +/* THC Read Interrupt Status for the 1st RXDMA */ +#define THC_M_PRT_READ_DMA_INT_STS_1_OFFSET 0x1110 +/* THC Read DMA Error Register for the 1st RXDMA */ +#define THC_M_PRT_READ_DMA_ERR_1_OFFSET 0x1114 +/* Touch Sequencer GuC Tail Offset Address Low for the 1st RXDMA */ +#define THC_M_PRT_GUC_OFFSET_LOW_1_OFFSET 0x1118 +/* Touch Sequencer GuC Tail Offset Address High for the 1st RXDMA */ +#define THC_M_PRT_GUC_OFFSET_HI_1_OFFSET 0x111C +/* Touch Host Controller GuC Work Queue Item Size for the 1st RXDMA */ +#define THC_M_PRT_GUC_WORKQ_ITEM_SZ_1_OFFSET 0x1120 +/* Touch Host Controller GuC Control register for the 1st RXDMA */ +#define THC_M_PRT_GUC_WORKQ_SZ_1_OFFSET 0x1124 +/* Touch Sequencer Control for the 1st DMA */ +#define THC_M_PRT_TSEQ_CNTRL_1_OFFSET 0x1128 +/* Touch Sequencer GuC Doorbell Address Low for the 1st RXDMA */ +#define THC_M_PRT_GUC_DB_ADDR_LOW_1_OFFSET 0x1130 +/* Touch Sequencer GuC Doorbell Address High for the 1st RXDMA */ +#define THC_M_PRT_GUC_DB_ADDR_HI_1_OFFSET 0x1134 +/* Touch Sequencer GuC Doorbell Data */ +#define THC_M_PRT_GUC_DB_DATA_1_OFFSET 0x1138 +/* Touch Sequencer GuC Tail Offset Initial Value for the 1st RXDMA */ +#define THC_M_PRT_GUC_OFFSET_INITVAL_1_OFFSET 0x1140 +/* THC Device Address for the bulk/touch data read for the 1st RXDMA */ +#define THC_M_PRT_RD_BULK_ADDR_1_OFFSET 0x1170 +/* THC Gfx/SW Doorbell Count from the 1st Stream RXDMA on this port */ +#define THC_M_PRT_DB_CNT_1_OFFSET 0x11A0 +/* THC Frame Count from the 1st Stream RXDMA on this port */ +#define THC_M_PRT_FRM_CNT_1_OFFSET 0x11A4 +/* THC Micro Frame Count from the 1st Stream RXDMA on this port */ +#define THC_M_PRT_UFRM_CNT_1_OFFSET 0x11A8 +/* THC Packet Count from the 1st Stream RXDMA on this port */ +#define THC_M_PRT_RXDMA_PKT_CNT_1_OFFSET 0x11AC +/* + * THC Software Interrupt Count from the 1st Stream RXDMA + * on this port + */ +#define THC_M_PRT_SWINT_CNT_1_OFFSET 0x11B0 +/* Touch Sequencer Frame Drop Counter for the 1st RXDMA */ +#define THC_M_PRT_FRAME_DROP_CNT_1_OFFSET 0x11B4 +/* THC Coaescing 1 */ +#define THC_M_PRT_COALESCE_1_OFFSET 0x11B8 +/* THC Read PRD Base Address Low for the 2nd RXDMA */ +#define THC_M_PRT_RPRD_BA_LOW_2_OFFSET 0x1200 +/* THC Read PRD Base Address High for the 2nd RXDMA */ +#define THC_M_PRT_RPRD_BA_HI_2_OFFSET 0x1204 +/* THC Read PRD Control for the 2nd RXDMA */ +#define THC_M_PRT_RPRD_CNTRL_2_OFFSET 0x1208 +/* THC Read DMA Control for the 2nd RXDMA */ +#define THC_M_PRT_READ_DMA_CNTRL_2_OFFSET 0x120C +/* THC Read Interrupt Status for the 2nd RXDMA */ +#define THC_M_PRT_READ_DMA_INT_STS_2_OFFSET 0x1210 +/* THC Read DMA Error Register for the 2nd RXDMA */ +#define THC_M_PRT_READ_DMA_ERR_2_OFFSET 0x1214 +/* Touch Sequencer GuC Tail Offset Address Low for the 2nd RXDMA */ +#define THC_M_PRT_GUC_OFFSET_LOW_2_OFFSET 0x1218 +/* Touch Sequencer GuC Tail Offset Address High for the 2nd RXDMA */ +#define THC_M_PRT_GUC_OFFSET_HI_2_OFFSET 0x121C +/* Touch Host Controller GuC Work Queue Item Size for the 2nd RXDMA */ +#define THC_M_PRT_GUC_WORKQ_ITEM_SZ_2_OFFSET 0x1220 +/* Touch Host Controller GuC Control register for the 2nd RXDMA */ +#define THC_M_PRT_GUC_WORKQ_SZ_2_OFFSET 0x1224 +/* Touch Sequencer Control for the 2nd DMA */ +#define THC_M_PRT_TSEQ_CNTRL_2_OFFSET 0x1228 +/* Touch Sequencer GuC Doorbell Address Low for the 2nd RXDMA */ +#define THC_M_PRT_GUC_DB_ADDR_LOW_2_OFFSET 0x1230 +/* Touch Sequencer GuC Doorbell Address High for the 2nd RXDMA */ +#define THC_M_PRT_GUC_DB_ADDR_HI_2_OFFSET 0x1234 +/* Touch Sequencer GuC Doorbell Data for PRD2 */ +#define THC_M_PRT_GUC_DB_DATA_2_OFFSET 0x1238 +/* Touch Sequencer GuC Tail Offset Initial Value for the 2nd RXDMA */ +#define THC_M_PRT_GUC_OFFSET_INITVAL_2_OFFSET 0x1240 +/* THC Device Address for the bulk/touch data read for the 2nd RXDMA */ +#define THC_M_PRT_RD_BULK_ADDR_2_OFFSET 0x1270 +/* THC Gfx/SW Doorbell Count from the 2nd Stream RXDMA on this port */ +#define THC_M_PRT_DB_CNT_2_OFFSET 0x12A0 +/* THC Frame Count from the 2nd Stream RXDMA on this port */ +#define THC_M_PRT_FRM_CNT_2_OFFSET 0x12A4 +/* THC Micro Frame Count from the 2nd Stream RXDMA on this port */ +#define THC_M_PRT_UFRM_CNT_2_OFFSET 0x12A8 +/* THC Packet Count from the 2nd Stream RXDMA on this port */ +#define THC_M_PRT_RXDMA_PKT_CNT_2_OFFSET 0x12AC +/* + * THC Software Interrupt Count from the 2nd Stream RXDMA + * on this port + */ +#define THC_M_PRT_SWINT_CNT_2_OFFSET 0x12B0 +/* Touch Sequencer Frame Drop Counter for the 2nd RXDMA */ +#define THC_M_PRT_FRAME_DROP_CNT_2_OFFSET 0x12B4 +/* THC Coaescing 2 */ +#define THC_M_PRT_COALESCE_2_OFFSET 0x12B8 +/* THC SPARE REGISTER */ +#define THC_M_PRT_SPARE_REG_OFFSET 0x12BC +/* THC Read PRD Base Address Low for the SW RXDMA */ +#define THC_M_PRT_RPRD_BA_LOW_SW_OFFSET 0x12C0 +/* THC Read PRD Base Address High for the SW RXDMA */ +#define THC_M_PRT_RPRD_BA_HI_SW_OFFSET 0x12C4 +/* THC Read PRD Control for the SW RXDMA */ +#define THC_M_PRT_RPRD_CNTRL_SW_OFFSET 0x12C8 +/* THC Read DMA Control for the SW RXDMA */ +#define THC_M_PRT_READ_DMA_CNTRL_SW_OFFSET 0x12CC +/* THC Read Interrupt Status for the SW RXDMA */ +#define THC_M_PRT_READ_DMA_INT_STS_SW_OFFSET 0x12D0 +/* Touch Sequencer Control for the SW DMA */ +#define THC_M_PRT_TSEQ_CNTRL_SW_OFFSET 0x12D4 +/* Address for the bulk read for SW DMA engine */ +#define THC_M_PRT_RD_BULK_ADDR_SW_OFFSET 0x12D8 +/* THC Frame Count from the SW RXDMA on this port */ +#define THC_M_PRT_FRM_CNT_SW_OFFSET 0x12DC +/* THC Packet Count from the SW RXDMA on this port */ +#define THC_M_PRT_RXDMA_PKT_CNT_SW_OFFSET 0x12E0 +/* SW DMA PRD Table Length */ +#define THC_M_PRT_SW_DMA_PRD_TABLE_LEN_OFFSET 0x12E4 +/* THC timing based Frame/Interrupt caolescing control register for 1st RXDMA */ +#define THC_M_PRT_COALESCE_CNTRL_1_OFFSET 0x12E8 +/* THC timing based Frame/Interrupt caolescing control register for 2nd RXDMA */ +#define THC_M_PRT_COALESCE_CNTRL_2_OFFSET 0x12EC +/* Touch Sequencer PRD Table Empty Counter for the 1st RXDMA */ +#define THC_M_PRT_PRD_EMPTY_CNT_1_OFFSET 0x12F0 +/* Touch Sequencer PRD Table Empty Counter for the 2nd RXDM */ +#define THC_M_PRT_PRD_EMPTY_CNT_2_OFFSET 0x12F4 +/* THC coalescing status to reflect the current coalescing FSM state for 1st RXDMA */ +#define THC_M_PRT_COALESCE_STS_1_OFFSET 0x12F8 +/* THC coalescing status to reflect the current coalescing FSM state for 2nd RXDMA */ +#define THC_M_PRT_COALESCE_STS_2_OFFSET 0x12FC +/* THC Register for the SPI Port Duty Cycle Configuration */ +#define THC_M_PRT_SPI_DUTYC_CFG_OFFSET 0x1300 +/* THC Register for SW I2C Wtite Sequecning control */ +#define THC_M_PRT_SW_SEQ_I2C_WR_CNTRL_OFFSET 0x1304 +/* THC current Timestamp Register for RXDMA1 */ +#define THC_M_PRT_TIMESTAMP_1_OFFSET 0x1308 +/* THC current Timestamp Register for RXDMA2 */ +#define THC_M_PRT_TIMESTAMP_2_OFFSET 0x130C +/* Current SYNC Event Timestamp Register */ +#define THC_M_PRT_SYNC_TIMESTAMP_OFFSET 0x1310 +/* THC Display Sync Register */ +#define THC_M_PRT_DISP_SYNC_OFFSET 0x1314 +/* THC Display Sync Register */ +#define THC_M_PRT_DISP_SYNC_2_OFFSET 0x1318 +/* THC Register for SW I2C Wtite Sequecning control */ +#define THC_M_PRT_I2C_CFG_OFFSET 0x131C + +/* THC register bits definition */ +#define TXN_ERR_INT_STS_BIT BIT(28) +#define TXN_FATAL_INT_STS_BIT BIT(30) + +#define NONDMA_INT_STS_BIT BIT(4) +#define EOF_INT_STS_BIT BIT(5) + +#define THC_CFG_DID_VID_VID GENMASK(15, 0) +#define THC_CFG_DID_VID_DID GENMASK(31, 16) + +#define THC_CFG_STS_CMD_IOSE BIT(0) +#define THC_CFG_STS_CMD_MSE BIT(1) +#define THC_CFG_STS_CMD_BME BIT(2) +#define THC_CFG_STS_CMD_SPCYC BIT(3) +#define THC_CFG_STS_CMD_MWRIEN BIT(4) +#define THC_CFG_STS_CMD_VGAPS BIT(5) +#define THC_CFG_STS_CMD_PERRR BIT(6) +#define THC_CFG_STS_CMD_SERREN BIT(8) +#define THC_CFG_STS_CMD_FBTBEN BIT(9) +#define THC_CFG_STS_CMD_INTD BIT(10) +#define THC_CFG_STS_CMD_INTS BIT(19) +#define THC_CFG_STS_CMD_CAPL BIT(20) +#define THC_CFG_STS_CMD_MCAP BIT(21) +#define THC_CFG_STS_CMD_FBTBC BIT(23) +#define THC_CFG_STS_CMD_MDPE BIT(24) +#define THC_CFG_STS_CMD_DEVT GENMASK(26, 25) +#define THC_CFG_STS_CMD_STA BIT(27) +#define THC_CFG_STS_CMD_RTA BIT(28) +#define THC_CFG_STS_CMD_RMA BIT(29) +#define THC_CFG_STS_CMD_SSE BIT(30) +#define THC_CFG_STS_CMD_DPE BIT(31) + +#define THC_CFG_CC_RID_RID GENMASK(7, 0) +#define THC_CFG_CC_RID_PI GENMASK(15, 8) +#define THC_CFG_CC_RID_SCC GENMASK(23, 16) +#define THC_CFG_CC_RID_BCC GENMASK(31, 24) + +#define THC_CFG_BIST_HTYPE_LT_CLS_CLSZ GENMASK(7, 0) +#define THC_CFG_BIST_HTYPE_LT_CLS_LT GENMASK(15, 8) +#define THC_CFG_BIST_HTYPE_LT_CLS_HTYPE GENMASK(22, 16) +#define THC_CFG_BIST_HTYPE_LT_CLS_MFD BIT(23) + +#define THC_CFG_BAR0_LOW_MEMSPACE BIT(0) +#define THC_CFG_BAR0_LOW_TYP GENMASK(2, 1) +#define THC_CFG_BAR0_LOW_PREFETCH BIT(3) +#define THC_CFG_BAR0_LOW_MEMSIZE GENMASK(14, 4) +#define THC_CFG_BAR0_LOW_MEMBAR GENMASK(31, 15) +#define THC_CFG_BAR0_HI_MEMBAR GENMASK(31, 0) + +#define THC_CFG_SID_SVID_SSVID GENMASK(15, 0) +#define THC_CFG_SID_SVID_SSID GENMASK(31, 16) + +#define THC_CFG_CAPP_CP GENMASK(7, 0) + +#define THC_CFG_INT_ILINE GENMASK(7, 0) +#define THC_CFG_INT_IPIN GENMASK(15, 8) + +#define THC_CFG_UR_STS_CTL_URRE BIT(0) +#define THC_CFG_UR_STS_CTL_URD BIT(1) +#define THC_CFG_UR_STS_CTL_FD BIT(2) + +#define THC_CFG_MSIMC_MSINP_MSICID_CAPID GENMASK(7, 0) +#define THC_CFG_MSIMC_MSINP_MSICID_NXTP GENMASK(15, 8) +#define THC_CFG_MSIMC_MSINP_MSICID_MSIE BIT(16) +#define THC_CFG_MSIMC_MSINP_MSICID_MMC GENMASK(19, 17) +#define THC_CFG_MSIMC_MSINP_MSICID_MMEN GENMASK(22, 20) +#define THC_CFG_MSIMC_MSINP_MSICID_XAC BIT(23) +#define THC_CFG_MSIMC_MSINP_MSICID_PVMC BIT(24) +#define THC_CFG_MSIMA_MADDR GENMASK(31, 2) +#define THC_CFG_MSIMUA_MAUDDR GENMASK(31, 0) +#define THC_CFG_MSIMD_MDAT GENMASK(15, 0) + +#define THC_CFG_PMCAP_PMNP_PMCID_CAPP GENMASK(7, 0) +#define THC_CFG_PMCAP_PMNP_PMCID_NXTP GENMASK(15, 8) +#define THC_CFG_PMCAP_PMNP_PMCID_VER GENMASK(18, 16) +#define THC_CFG_PMCAP_PMNP_PMCID_PMECLK BIT(19) +#define THC_CFG_PMCAP_PMNP_PMCID_DSI BIT(21) +#define THC_CFG_PMCAP_PMNP_PMCID_AUXC GENMASK(24, 22) +#define THC_CFG_PMCAP_PMNP_PMCID_D1S BIT(25) +#define THC_CFG_PMCAP_PMNP_PMCID_D2S BIT(26) +#define THC_CFG_PMCAP_PMNP_PMCID_PMES GENMASK(31, 27) + +#define THC_CFG_PMD_PMCSRBSE_PMCSR_PWRST GENMASK(1, 0) +#define THC_CFG_PMD_PMCSRBSE_PMCSR_NSR BIT(3) +#define THC_CFG_PMD_PMCSRBSE_PMCSR_PMEEN BIT(8) +#define THC_CFG_PMD_PMCSRBSE_PMCSR_DSEL GENMASK(12, 9) +#define THC_CFG_PMD_PMCSRBSE_PMCSR_DS GENMASK(14, 13) +#define THC_CFG_PMD_PMCSRBSE_PMCSR_PMESTS BIT(15) + +#define THC_CFG_DEVIDLE_CAPPID GENMASK(7, 0) +#define THC_CFG_DEVIDLE_NCAPPP GENMASK(15, 8) +#define THC_CFG_DEVIDLE_LENGTH GENMASK(23, 16) +#define THC_CFG_DEVIDLE_REV GENMASK(27, 24) +#define THC_CFG_DEVIDLE_VID GENMASK(31, 28) + +#define THC_CFG_VSHDR_VSECID GENMASK(15, 0) +#define THC_CFG_VSHDR_VSECR GENMASK(19, 16) +#define THC_CFG_VSHDR_VSECL GENMASK(31, 20) + +#define THC_CFG_SWLTRPTR_VALID BIT(0) +#define THC_CFG_SWLTRPTR_BARNUM GENMASK(3, 1) +#define THC_CFG_SWLTRPTR_SWLTRLOC GENMASK(31, 4) + +#define THC_CFG_DEVIDLEPTR_VALID BIT(0) +#define THC_CFG_DEVIDLEPTR_BARNUM GENMASK(3, 1) +#define THC_CFG_DEVIDLEPTR_DEVIDLELOC GENMASK(31, 4) +#define THC_CFG_DEVIDLEPOL_POLV GENMASK(9, 0) +#define THC_CFG_DEVIDLEPOL_POLS GENMASK(12, 10) + +#define THC_CFG_PCE_SPE BIT(0) +#define THC_CFG_PCE_I3E BIT(1) +#define THC_CFG_PCE_D3HE BIT(2) +#define THC_CFG_PCE_SE BIT(3) +#define THC_CFG_PCE_HAE BIT(5) + +#define THC_CFG_MANID_PROC GENMASK(7, 0) +#define THC_CFG_MANID_MID GENMASK(15, 8) +#define THC_CFG_MANID_MSID GENMASK(23, 16) +#define THC_CFG_MANID_DOT GENMASK(27, 24) + +#define THC_M_CMN_DEVIDLECTRL_CIP BIT(0) +#define THC_M_CMN_DEVIDLECTRL_IR BIT(1) +#define THC_M_CMN_DEVIDLECTRL_DEVIDLE BIT(2) +#define THC_M_CMN_DEVIDLECTRL_RR BIT(3) +#define THC_M_CMN_DEVIDLECTRL_IRC BIT(4) + +#define THC_M_CMN_LTR_CTRL_OFFSET 0x14 +#define THC_M_CMN_LTR_CTRL_ACTIVE_LTR_REQ BIT(0) +#define THC_M_CMN_LTR_CTRL_ACTIVE_LTR_EN BIT(1) +#define THC_M_CMN_LTR_CTRL_LP_LTR_REQ BIT(2) +#define THC_M_CMN_LTR_CTRL_LP_LTR_EN BIT(3) +#define THC_M_CMN_LTR_CTRL_LP_LTR_SCALE GENMASK(6, 4) +#define THC_M_CMN_LTR_CTRL_LP_LTR_VAL GENMASK(16, 7) +#define THC_M_CMN_LTR_CTRL_ACT_LTR_SCALE GENMASK(19, 17) +#define THC_M_CMN_LTR_CTRL_ACT_LTR_VAL GENMASK(29, 20) +#define THC_M_CMN_LTR_CTRL_LAST_LTR_SENT GENMASK(31, 30) + +#define THC_M_PRT_CONTROL_TSFTRST BIT(0) +#define THC_M_PRT_CONTROL_THC_DEVINT_QUIESCE_EN BIT(1) +#define THC_M_PRT_CONTROL_THC_DEVINT_QUIESCE_HW_STS BIT(2) +#define THC_M_PRT_CONTROL_DEVRST BIT(3) +#define THC_M_PRT_CONTROL_THC_DRV_LOCK_EN BIT(13) +#define THC_M_PRT_CONTROL_THC_INSTANCE_INDEX GENMASK(18, 16) +#define THC_M_PRT_CONTROL_PORT_INDEX GENMASK(22, 20) +#define THC_M_PRT_CONTROL_THC_ARB_POLICY GENMASK(25, 24) +#define THC_M_PRT_CONTROL_THC_BIOS_LOCK_EN BIT(27) +#define THC_M_PRT_CONTROL_PORT_SUPPORTED BIT(28) +#define THC_M_PRT_CONTROL_SPI_IO_RDY BIT(29) +#define THC_M_PRT_CONTROL_PORT_TYPE GENMASK(31, 30) + +#define THC_M_PRT_SPI_CFG_SPI_TRDC GENMASK(1, 0) +#define THC_M_PRT_SPI_CFG_SPI_TRMODE GENMASK(3, 2) +#define THC_M_PRT_SPI_CFG_SPI_TCRF GENMASK(6, 4) +#define THC_M_PRT_SPI_CFG_SPI_RD_MPS GENMASK(15, 7) +#define THC_M_PRT_SPI_CFG_SPI_TWMODE GENMASK(19, 18) +#define THC_M_PRT_SPI_CFG_SPI_TCWF GENMASK(22, 20) +#define THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN BIT(23) +#define THC_M_PRT_SPI_CFG_SPI_WR_MPS GENMASK(31, 24) + +#define THC_M_PRT_SPI_ICRRD_OPCODE_SPI_SIO GENMASK(31, 24) +#define THC_M_PRT_SPI_ICRRD_OPCODE_SPI_DIO GENMASK(23, 16) +#define THC_M_PRT_SPI_ICRRD_OPCODE_SPI_QIO GENMASK(15, 8) + +#define THC_M_PRT_INT_EN_SIPE BIT(0) +#define THC_M_PRT_INT_EN_SBO BIT(1) +#define THC_M_PRT_INT_EN_SIDR BIT(2) +#define THC_M_PRT_INT_EN_SOFB BIT(3) +#define THC_M_PRT_INT_EN_INVLD_DEV_ENTRY_INT_EN BIT(9) +#define THC_M_PRT_INT_EN_FRAME_BABBLE_ERR_INT_EN BIT(10) +#define THC_M_PRT_INT_EN_BUF_OVRRUN_ERR_INT_EN BIT(12) +#define THC_M_PRT_INT_EN_PRD_ENTRY_ERR_INT_EN BIT(13) +#define THC_M_PRT_INT_EN_DISP_SYNC_EVT_INT_EN BIT(14) +#define THC_M_PRT_INT_EN_DEV_RAW_INT_EN BIT(15) +#define THC_M_PRT_INT_EN_FATAL_ERR_INT_EN BIT(16) +#define THC_M_PRT_INT_EN_THC_I2C_IC_RX_UNDER_INT_EN BIT(17) +#define THC_M_PRT_INT_EN_THC_I2C_IC_RX_OVER_INT_EN BIT(18) +#define THC_M_PRT_INT_EN_THC_I2C_IC_RX_FULL_INT_EN BIT(19) +#define THC_M_PRT_INT_EN_THC_I2C_IC_TX_OVER_INT_EN BIT(20) +#define THC_M_PRT_INT_EN_THC_I2C_IC_TX_EMPTY_INT_EN BIT(21) +#define THC_M_PRT_INT_EN_THC_I2C_IC_TX_ABRT_INT_EN BIT(22) +#define THC_M_PRT_INT_EN_THC_I2C_IC_SCL_STUCK_AT_LOW_DET_INT_EN BIT(24) +#define THC_M_PRT_INT_EN_THC_I2C_IC_STOP_DET_INT_EN BIT(25) +#define THC_M_PRT_INT_EN_THC_I2C_IC_START_DET_INT_EN BIT(26) +#define THC_M_PRT_INT_EN_THC_I2C_IC_MST_ON_HOLD_INT_EN BIT(27) +#define THC_M_PRT_INT_EN_TXN_ERR_INT_EN BIT(29) +#define THC_M_PRT_INT_EN_GBL_INT_EN BIT(31) + +#define THC_M_PRT_INT_STATUS_DISP_SYNC_EVT_INT_STS BIT(14) +#define THC_M_PRT_INT_STATUS_DEV_RAW_INT_STS BIT(15) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_RX_UNDER_INT_STS BIT(17) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_RX_OVER_INT_STS BIT(18) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_RX_FULL_INT_STS BIT(19) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_TX_OVER_INT_STS BIT(20) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_TX_EMPTY_INT_STS BIT(21) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_TX_ABRT_INT_STS BIT(22) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_ACTIVITY_INT_STS BIT(23) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_SCL_STUCK_AT_LOW_INT_STS BIT(24) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_STOP_DET_INT_STS BIT(25) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_START_DET_INT_STS BIT(26) +#define THC_M_PRT_INT_STATUS_THC_I2C_IC_MST_ON_HOLD_INT_STS BIT(27) +#define THC_M_PRT_INT_STATUS_TXN_ERR_INT_STS BIT(28) +#define THC_M_PRT_INT_STATUS_FATAL_ERR_INT_STS BIT(30) + +#define THC_M_PRT_ERR_CAUSE_INVLD_DEV_ENTRY BIT(9) +#define THC_M_PRT_ERR_CAUSE_FRAME_BABBLE_ERR BIT(10) +#define THC_M_PRT_ERR_CAUSE_BUF_OVRRUN_ERR BIT(12) +#define THC_M_PRT_ERR_CAUSE_PRD_ENTRY_ERR BIT(13) +#define THC_M_PRT_ERR_CAUSE_FATAL_ERR_CAUSE GENMASK(23, 16) + +#define THC_M_PRT_SW_SEQ_CNTRL_TSSGO BIT(0) +#define THC_M_PRT_SW_SEQ_CNTRL_THC_SS_CD_IE BIT(1) +#define THC_M_PRT_SW_SEQ_CNTRL_THC_SS_CMD GENMASK(15, 8) +#define THC_M_PRT_SW_SEQ_CNTRL_THC_SS_BC GENMASK(31, 16) +#define THC_M_PRT_SW_SEQ_STS_TSSDONE BIT(0) +#define THC_M_PRT_SW_SEQ_STS_THC_SS_ERR BIT(1) +#define THC_M_PRT_SW_SEQ_STS_THC_SS_CIP BIT(3) +#define THC_M_PRT_SW_SEQ_DATA0_ADDR_THC_SW_SEQ_DATA0_ADDR GENMASK(31, 0) +#define THC_M_PRT_SW_SEQ_DATA1_THC_SW_SEQ_DATA1 GENMASK(31, 0) + +#define THC_M_PRT_WPRD_BA_LOW_THC_M_PRT_WPRD_BA_LOW GENMASK(31, 12) +#define THC_M_PRT_WPRD_BA_HI_THC_M_PRT_WPRD_BA_HI GENMASK(31, 0) + +#define THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_START BIT(0) +#define THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_IE_IOC_ERROR BIT(1) +#define THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_IE_IOC BIT(2) +#define THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_IE_IOC_DMACPL BIT(3) +#define THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_UHS BIT(23) +#define THC_M_PRT_WRITE_DMA_CNTRL_THC_WRDMA_PTEC GENMASK(31, 24) + +#define THC_M_PRT_WRITE_INT_STS_THC_WRDMA_CMPL_STATUS BIT(0) +#define THC_M_PRT_WRITE_INT_STS_THC_WRDMA_ERROR_STS BIT(1) +#define THC_M_PRT_WRITE_INT_STS_THC_WRDMA_IOC_STS BIT(2) +#define THC_M_PRT_WRITE_INT_STS_THC_WRDMA_ACTIVE BIT(3) + +#define THC_M_PRT_WR_BULK_ADDR_THC_M_PRT_WR_BULK_ADDR GENMASK(31, 0) + +#define THC_M_PRT_DEV_INT_CAUSE_ADDR_THC_M_PRT_DEV_INT_CAUSE_ADDR GENMASK(31, 0) +#define THC_M_PRT_DEV_INT_CAUSE_REG_VAL_INTERRUPT_TYPE GENMASK(3, 0) +#define THC_M_PRT_DEV_INT_CAUSE_REG_VAL_MICRO_FRAME_SIZE GENMASK(23, 4) +#define THC_M_PRT_DEV_INT_CAUSE_REG_VAL_BEGINNING_OF_FRAME BIT(29) +#define THC_M_PRT_DEV_INT_CAUSE_REG_VAL_END_OF_FRAME BIT(30) +#define THC_M_PRT_DEV_INT_CAUSE_REG_VAL_FRAME_TYPE BIT(31) + +#define THC_M_PRT_TX_FRM_CNT_THC_M_PRT_TX_FRM_CNT GENMASK(30, 0) +#define THC_M_PRT_TX_FRM_CNT_THC_M_PRT_TX_FRM_CNT_RST BIT(31) + +#define THC_M_PRT_TXDMA_PKT_CNT_THC_M_PRT_TXDMA_PKT_CNT GENMASK(30, 0) +#define THC_M_PRT_TXDMA_PKT_CNT_THC_M_PRT_TXDMA_PKT_CNT_RST BIT(31) + +#define THC_M_PRT_DEVINT_CNT_THC_M_PRT_DEVINT_CNT GENMASK(30, 0) +#define THC_M_PRT_DEVINT_CNT_THC_M_PRT_DEVINT_CNT_RST BIT(31) + +#define THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_OFFSET GENMASK(4, 0) +#define THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_LEN GENMASK(9, 5) +#define THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_EOF_OFFSET GENMASK(14, 10) +#define THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_SEND_ICR_US_EN BIT(15) +#define THC_M_PRT_DEVINT_CFG_1_THC_M_PRT_INTTYP_DATA_VAL GENMASK(31, 16) + +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_UFSIZE_OFFSET GENMASK(4, 0) +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_UFSIZE_LEN GENMASK(9, 5) +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_UFSIZE_UNIT GENMASK(15, 12) +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_FTYPE_IGNORE BIT(16) +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_FTYPE_VAL BIT(17) +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_RXDMA_ADDRINC_DIS BIT(24) +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_TXDMA_ADDRINC_DIS BIT(25) +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_RXDMA_PKT_STRM_EN BIT(26) +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_TXDMA_PKT_STRM_EN BIT(27) +#define THC_M_PRT_DEVINT_CFG_2_THC_M_PRT_DEVINT_POL BIT(28) + +#define THC_M_PRT_RPRD_BA_LOW_1_THC_M_PRT_RPRD_BA_LOW GENMASK(31, 12) +#define THC_M_PRT_RPRD_BA_HI_1_THC_M_PRT_RPRD_BA_HI GENMASK(31, 0) + +#define THC_M_PRT_RPRD_CNTRL_PCD GENMASK(6, 0) +#define THC_M_PRT_RPRD_CNTRL_PTEC GENMASK(15, 8) +#define THC_M_PRT_RPRD_CNTRL_PREFETCH_WM GENMASK(19, 16) + +#define THC_M_PRT_READ_DMA_CNTRL_START BIT(0) +#define THC_M_PRT_READ_DMA_CNTRL_IE_ERROR BIT(1) +#define THC_M_PRT_READ_DMA_CNTRL_IE_IOC BIT(2) +#define THC_M_PRT_READ_DMA_CNTRL_IE_STALL BIT(3) +#define THC_M_PRT_READ_DMA_CNTRL_IE_NDDI BIT(4) +#define THC_M_PRT_READ_DMA_CNTRL_IE_EOF BIT(5) +#define THC_M_PRT_READ_DMA_CNTRL_IE_DMACPL BIT(7) +#define THC_M_PRT_READ_DMA_CNTRL_TPCRP GENMASK(15, 8) +#define THC_M_PRT_READ_DMA_CNTRL_TPCWP GENMASK(23, 16) +#define THC_M_PRT_READ_DMA_CNTRL_INT_SW_DMA_EN BIT(28) +#define THC_M_PRT_READ_DMA_CNTRL_SOO BIT(29) +#define THC_M_PRT_READ_DMA_CNTRL_UHS BIT(30) +#define THC_M_PRT_READ_DMA_CNTRL_TPCPR BIT(31) + +#define THC_M_PRT_READ_DMA_INT_STS_DMACPL_STS BIT(0) +#define THC_M_PRT_READ_DMA_INT_STS_ERROR_STS BIT(1) +#define THC_M_PRT_READ_DMA_INT_STS_IOC_STS BIT(2) +#define THC_M_PRT_READ_DMA_INT_STS_STALL_STS BIT(3) +#define THC_M_PRT_READ_DMA_INT_STS_NONDMA_INT_STS BIT(4) +#define THC_M_PRT_READ_DMA_INT_STS_EOF_INT_STS BIT(5) +#define THC_M_PRT_READ_DMA_INT_STS_ACTIVE BIT(8) + +#define THC_M_PRT_READ_DMA_ERR_1_DLERR BIT(0) + +#define THC_M_PRT_GUC_OFFSET_LOW_1_THC_M_PRT_GUC_OFFSET_LOW GENMASK(31, 3) +#define THC_M_PRT_GUC_OFFSET_HI_1_THC_M_PRT_GUC_OFFSET_HI GENMASK(31, 0) +#define THC_M_PRT_GUC_WORKQ_ITEM_SZ_1_WORKQ_ITEM_SZ GENMASK(23, 0) +#define THC_M_PRT_GUC_WORKQ_SZ_1_WORKQ_SZ GENMASK(23, 0) +#define THC_M_PRT_GUC_WORKQ_SZ_1_FCD GENMASK(27, 24) +#define THC_M_PRT_GUC_WORKQ_SZ_1_GIC GENMASK(31, 28) + +#define THC_M_PRT_TSEQ_CNTRL_1_RGD BIT(2) +#define THC_M_PRT_TSEQ_CNTRL_1_EGP BIT(3) +#define THC_M_PRT_TSEQ_CNTRL_1_RTO BIT(4) +#define THC_M_PRT_TSEQ_CNTRL_1_EWOG BIT(5) +#define THC_M_PRT_TSEQ_CNTRL_1_RWOGC BIT(6) +#define THC_M_PRT_TSEQ_CNTRL_1_RX_DATA_FIFO_WR_WM GENMASK(25, 16) +#define THC_M_PRT_TSEQ_CNTRL_1_RESET_PREP_CHICKEN BIT(30) +#define THC_M_PRT_TSEQ_CNTRL_1_INT_EDG_DET_EN BIT(31) + +#define THC_M_PRT_GUC_DB_ADDR_LOW_1_GUC_DB_ADDR_LOW GENMASK(31, 2) +#define THC_M_PRT_GUC_DB_ADDR_HI_1_GUC_DB_ADDR_HI GENMASK(31, 0) +#define THC_M_PRT_GUC_DB_DATA_1_GUC_DB_DATA GENMASK(31, 0) +#define THC_M_PRT_GUC_OFFSET_INITVAL_1_THC_M_PRT_GUC_OFFSET_INITVAL GENMASK(31, 0) + +#define THC_M_PRT_RD_BULK_ADDR_1_THC_M_PRT_RD_BULK_ADDR GENMASK(31, 0) + +#define THC_M_PRT_DB_CNT_1_THC_M_PRT_DB_CNT GENMASK(30, 0) +#define THC_M_PRT_DB_CNT_1_THC_M_PRT_DB_CNT_RST BIT(31) + +#define THC_M_PRT_FRM_CNT_1_THC_M_PRT_FRM_CNT GENMASK(30, 0) +#define THC_M_PRT_FRM_CNT_1_THC_M_PRT_FRM_CNT_RST BIT(31) + +#define THC_M_PRT_UFRM_CNT_1_THC_M_PRT_UFRM_CNT GENMASK(30, 0) +#define THC_M_PRT_UFRM_CNT_1_THC_M_PRT_UFRM_CNT_RST BIT(31) + +#define THC_M_PRT_RXDMA_PKT_CNT_1_THC_M_PRT_RXDMA_PKT_CNT GENMASK(30, 0) +#define THC_M_PRT_RXDMA_PKT_CNT_1_THC_M_PRT_RXDMA_PKT_CNT_RST BIT(31) + +#define THC_M_PRT_SWINT_CNT_1_THC_M_PRT_SWINT_CNT GENMASK(30, 0) +#define THC_M_PRT_SWINT_CNT_1_THC_M_PRT_SWINT_CNT_RST BIT(31) + +#define THC_M_PRT_FRAME_DROP_CNT_1_NOFD GENMASK(30, 0) +#define THC_M_PRT_FRAME_DROP_CNT_1_RFDC BIT(31) + +#define THC_M_PRT_COALESCE_1_COALESCE_TIMEOUT GENMASK(6, 0) + +#define THC_M_PRT_RPRD_BA_LOW_2_THC_M_PRT_RPRD_BA_LOW GENMASK(31, 12) +#define THC_M_PRT_RPRD_BA_HI_2_THC_M_PRT_RPRD_BA_HI GENMASK(31, 0) + +#define THC_M_PRT_READ_DMA_ERR_2_DLERR BIT(0) + +#define THC_M_PRT_GUC_OFFSET_LOW_2_THC_M_PRT_GUC_OFFSET_LOW GENMASK(31, 3) +#define THC_M_PRT_GUC_OFFSET_HI_2_THC_M_PRT_GUC_OFFSET_HI GENMASK(31, 0) + +#define THC_M_PRT_GUC_WORKQ_ITEM_SZ_2_WORKQ_ITEM_SZ GENMASK(23, 0) +#define THC_M_PRT_GUC_WORKQ_SZ_2_WORKQ_SZ GENMASK(23, 0) +#define THC_M_PRT_GUC_WORKQ_SZ_2_FCD GENMASK(27, 24) +#define THC_M_PRT_GUC_WORKQ_SZ_2_GIC GENMASK(31, 28) + +#define THC_M_PRT_TSEQ_CNTRL_2_RGD BIT(2) +#define THC_M_PRT_TSEQ_CNTRL_2_EGP BIT(3) +#define THC_M_PRT_TSEQ_CNTRL_2_RTO BIT(4) + +#define THC_M_PRT_GUC_DB_ADDR_LOW_2_GUC_DB_ADDR_LOW GENMASK(31, 2) +#define THC_M_PRT_GUC_DB_ADDR_HI_2_GUC_DB_ADDR_HI GENMASK(31, 0) + +#define THC_M_PRT_GUC_DB_DATA_2_GUC_DB_DATA GENMASK(31, 0) + +#define THC_M_PRT_GUC_OFFSET_INITVAL_2_THC_M_PRT_GUC_OFFSET_INITVAL GENMASK(31, 0) + +#define THC_M_PRT_RD_BULK_ADDR_2_THC_M_PRT_RD_BULK_ADDR GENMASK(31, 0) + +#define THC_M_PRT_DB_CNT_2_THC_M_PRT_DB_CNT GENMASK(30, 0) +#define THC_M_PRT_DB_CNT_2_THC_M_PRT_DB_CNT_RST BIT(31) + +#define THC_M_PRT_FRM_CNT_2_THC_M_PRT_FRM_CNT GENMASK(30, 0) +#define THC_M_PRT_FRM_CNT_2_THC_M_PRT_FRM_CNT_RST BIT(31) + +#define THC_M_PRT_UFRM_CNT_2_THC_M_PRT_UFRM_CNT GENMASK(30, 0) +#define THC_M_PRT_UFRM_CNT_2_THC_M_PRT_UFRM_CNT_RST BIT(31) + +#define THC_M_PRT_RXDMA_PKT_CNT_2_THC_M_PRT_RXDMA_PKT_CNT GENMASK(30, 0) +#define THC_M_PRT_RXDMA_PKT_CNT_2_THC_M_PRT_RXDMA_PKT_CNT_RST BIT(31) + +#define THC_M_PRT_SWINT_CNT_2_THC_M_PRT_SWINT_CNT GENMASK(30, 0) +#define THC_M_PRT_SWINT_CNT_2_THC_M_PRT_SWINT_CNT_RST BIT(31) + +#define THC_M_PRT_FRAME_DROP_CNT_2_NOFD GENMASK(30, 0) +#define THC_M_PRT_FRAME_DROP_CNT_2_RFDC BIT(31) + +#define THC_M_PRT_COALESCE_2_COALESCE_TIMEOUT GENMASK(6, 0) + +#define THC_M_PRT_SW_SEQ_I2C_WR_CNTRL_THC_I2C_RW_PIO_EN BIT(23) +#define THC_M_PRT_SW_SEQ_I2C_WR_CNTRL_THC_PIO_I2C_WBC GENMASK(31, 26) + +#define THC_M_PRT_RPRD_CNTRL_SW_THC_SWDMA_I2C_RX_DLEN_EN BIT(23) +#define THC_M_PRT_RPRD_CNTRL_SW_THC_SWDMA_I2C_WBC GENMASK(31, 26) + +#define THC_M_PRT_PRD_EMPTY_CNT_1_RPTEC BIT(31) +#define THC_M_PRT_PRD_EMPTY_CNT_2_RPTEC BIT(31) + +#define THC_M_PRT_SW_DMA_PRD_TABLE_LEN_THC_M_PRT_SW_DMA_PRD_TABLE_LEN GENMASK(23, 0) + +#define THC_M_PRT_SPI_DUTYC_CFG_SPI_CSA_CK_DELAY_VAL GENMASK(3, 0) +#define THC_M_PRT_SPI_DUTYC_CFG_SPI_CSA_CK_DELAY_EN BIT(25) + +/* CS Assertion delay default value */ +#define THC_CSA_CK_DELAY_VAL_DEFAULT 4 + +/* ARB policy definition */ +/* Arbiter switches on packet boundary */ +#define THC_ARB_POLICY_PACKET_BOUNDARY 0 +/* Arbiter switches on Micro Frame boundary */ +#define THC_ARB_POLICY_UFRAME_BOUNDARY 1 +/* Arbiter switches on Frame boundary */ +#define THC_ARB_POLICY_FRAME_BOUNDARY 2 + +#define THC_REGMAP_POLLING_INTERVAL_US 10 /* 10us */ +#define THC_PIO_DONE_TIMEOUT_US USEC_PER_SEC /* 1s */ + +/* Default configures for HIDSPI */ +#define THC_BIT_OFFSET_INTERRUPT_TYPE 4 +/* input_report_type is 4 bits for HIDSPI */ +#define THC_BIT_LENGTH_INTERRUPT_TYPE 4 +/* Last fragment indicator is bit 15 for HIDSPI */ +#define THC_BIT_OFFSET_LAST_FRAGMENT_FLAG 22 +#define THC_BIT_OFFSET_MICROFRAME_SIZE 8 +/* input_report_length is 14 bits for HIDSPI */ +#define THC_BIT_LENGTH_MICROFRAME_SIZE 14 +/* MFS unit in power of 2 */ +#define THC_UNIT_MICROFRAME_SIZE 2 +#define THC_BITMASK_INTERRUPT_TYPE_DATA 1 +#define THC_BITMASK_INVALID_TYPE_DATA 2 + +/* Interrupt Quiesce default timeout value */ +#define THC_QUIESCE_EN_TIMEOUT_US USEC_PER_SEC /* 1s */ + +/* LTR definition */ +/* + * THC uses scale to calculate final LTR value. + * Scale is geometric progression of 2^5 step, starting from 2^0. + * For example, THC_LTR_SCALE_2(2) means 2^(5 * 2) = 1024, unit is ns. + */ +#define THC_LTR_SCALE_0 0 +#define THC_LTR_SCALE_1 1 +#define THC_LTR_SCALE_2 2 +#define THC_LTR_SCALE_3 3 +#define THC_LTR_SCALE_4 4 +#define THC_LTR_SCALE_5 5 +#define THC_LTR_MODE_ACTIVE 0 +#define THC_LTR_MODE_LP 1 +#define THC_LTR_MIN_VAL_SCALE_3 BIT(10) +#define THC_LTR_MAX_VAL_SCALE_3 BIT(15) +#define THC_LTR_MIN_VAL_SCALE_4 BIT(15) +#define THC_LTR_MAX_VAL_SCALE_4 BIT(20) +#define THC_LTR_MIN_VAL_SCALE_5 BIT(20) +#define THC_LTR_MAX_VAL_SCALE_5 BIT(25) + +/* + * THC PIO opcode default value + * @THC_PIO_OP_SPI_TIC_READ: THC opcode for SPI PIO read + * @THC_PIO_OP_SPI_TIC_WRITE: THC opcode for SPI PIO write + * @THC_PIO_OP_I2C_SUBSYSTEM_READ: THC opcode for read I2C subsystem registers + * @THC_PIO_OP_I2C_SUBSYSTEM_WRITE: THC opcode for write I2C subsystem registers + * @THC_PIO_OP_I2C_TIC_READ: THC opcode for read I2C device + * @THC_PIO_OP_I2C_TIC_WRITE: THC opcode for write I2C device + * @THC_PIO_OP_I2C_TIC_WRITE_AND_READ: THC opcode for write followed by read I2C device + */ +enum thc_pio_opcode { + THC_PIO_OP_SPI_TIC_READ = 0x4, + THC_PIO_OP_SPI_TIC_WRITE = 0x6, + THC_PIO_OP_I2C_SUBSYSTEM_READ = 0x12, + THC_PIO_OP_I2C_SUBSYSTEM_WRITE = 0x13, + THC_PIO_OP_I2C_TIC_READ = 0x14, + THC_PIO_OP_I2C_TIC_WRITE = 0x18, + THC_PIO_OP_I2C_TIC_WRITE_AND_READ = 0x1C, +}; + +/** + * THC SPI IO mode + * @THC_SINGLE_IO: single IO mode, 1(opcode) - 1(address) - 1(data) + * @THC_DUAL_IO: dual IO mode, 1(opcode) - 2(address) - 2(data) + * @THC_QUAD_IO: quad IO mode, 1(opcode) - 4(address) - 4(data) + * @THC_QUAD_PARALLEL_IO: parallel quad IO mode, 4(opcode) - 4(address) - 4(data) + */ +enum thc_spi_iomode { + THC_SINGLE_IO = 0, + THC_DUAL_IO = 1, + THC_QUAD_IO = 2, + THC_QUAD_PARALLEL_IO = 3, +}; + +/** + * THC SPI frequency divider + * + * This DIV final value is determined by THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN bit. + * If THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN isn't be set, THC takes the DIV value directly; + * If THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN is set, THC takes the DIV value multiply by 8. + * + * For example, if THC input clock is 125MHz: + * When THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN isn't set, THC_SPI_FRQ_DIV_3 means DIV is 3, + * THC final clock is 125 / 3 = 41.667MHz; + * When THC_M_PRT_SPI_CFG_SPI_LOW_FREQ_EN is set, THC_SPI_FRQ_DIV_3 means DIV is 3 * 8, + * THC final clock is 125 / (3 * 8) = 5.208MHz; + */ +enum thc_spi_frq_div { + THC_SPI_FRQ_RESERVED = 0, + THC_SPI_FRQ_DIV_1 = 1, + THC_SPI_FRQ_DIV_2 = 2, + THC_SPI_FRQ_DIV_3 = 3, + THC_SPI_FRQ_DIV_4 = 4, + THC_SPI_FRQ_DIV_5 = 5, + THC_SPI_FRQ_DIV_6 = 6, + THC_SPI_FRQ_DIV_7 = 7, +}; + +/* THC I2C sub-system registers */ +#define THC_I2C_IC_CON_OFFSET 0x0 +#define THC_I2C_IC_TAR_OFFSET 0x4 +#define THC_I2C_IC_SAR_OFFSET 0x8 +#define THC_I2C_IC_HS_MADDR_OFFSET 0xC +#define THC_I2C_IC_DATA_CMD_OFFSET 0x10 +#define THC_I2C_IC_SS_SCL_HCNT_OFFSET 0x14 +#define THC_I2C_IC_UFM_SCL_HCNT_OFFSET 0x14 +#define THC_I2C_IC_SS_SCL_LCNT_OFFSET 0x18 +#define THC_I2C_IC_UFM_SCL_LCNT_OFFSET 0x18 +#define THC_I2C_IC_FS_SCL_HCNT_OFFSET 0x1C +#define THC_I2C_IC_UFM_TBUF_CNT_OFFSET 0x1C +#define THC_I2C_IC_FS_SCL_LCNT_OFFSET 0x20 +#define THC_I2C_IC_HS_SCL_HCNT_OFFSET 0x24 +#define THC_I2C_IC_HS_SCL_LCNT_OFFSET 0x28 +#define THC_I2C_IC_INTR_STAT_OFFSET 0x2C +#define THC_I2C_IC_INTR_MASK_OFFSET 0x30 +#define THC_I2C_IC_RAW_INTR_STAT_OFFSET 0x34 +#define THC_I2C_IC_RX_TL_OFFSET 0x38 +#define THC_I2C_IC_TX_TL_OFFSET 0x3C +#define THC_I2C_IC_CLR_INTR_OFFSET 0x40 +#define THC_I2C_IC_CLR_RX_UNDER_OFFSET 0x44 +#define THC_I2C_IC_CLR_RX_OVER_OFFSET 0x48 +#define THC_I2C_IC_CLR_TX_OVER_OFFSET 0x4C +#define THC_I2C_IC_CLR_RD_REQ_OFFSET 0x50 +#define THC_I2C_IC_CLR_TX_ABRT_OFFSET 0x54 +#define THC_I2C_IC_CLR_RX_DONE_OFFSET 0x58 +#define THC_I2C_IC_CLR_ACTIVITY_OFFSET 0x5C +#define THC_I2C_IC_CLR_STOP_DET_OFFSET 0x60 +#define THC_I2C_IC_CLR_START_DET_OFFSET 0x64 +#define THC_I2C_IC_CLR_GEN_CALL_OFFSET 0x68 +#define THC_I2C_IC_ENABLE_OFFSET 0x6C +#define THC_I2C_IC_STATUS_OFFSET 0x70 +#define THC_I2C_IC_TXFLR_OFFSET 0x74 +#define THC_I2C_IC_RXFLR_OFFSET 0x78 +#define THC_I2C_IC_SDA_HOLD_OFFSET 0x7C +#define THC_I2C_IC_TX_ABRT_SOURCE_OFFSET 0x80 +#define THC_I2C_IC_SLV_DATA_NACK_ONLY_OFFSET 0x84 +#define THC_I2C_IC_DMA_CR_OFFSET 0x88 +#define THC_I2C_IC_DMA_TDLR_OFFSET 0x8C +#define THC_I2C_IC_DMA_RDLR_OFFSET 0x90 +#define THC_I2C_IC_SDA_SETUP_OFFSET 0x94 +#define THC_I2C_IC_ACK_GENERAL_CALL_OFFSET 0x98 +#define THC_I2C_IC_ENABLE_STATUS_OFFSET 0x9C +#define THC_I2C_IC_FS_SPKLEN_OFFSET 0xA0 +#define THC_I2C_IC_UFM_SPKLEN_OFFSET 0xA0 +#define THC_I2C_IC_HS_SPKLEN_OFFSET 0xA4 +#define THC_I2C_IC_CLR_RESTART_DET_OFFSET 0xA8 +#define THC_I2C_IC_SCL_STUCK_AT_LOW_TIMEOUT_OFFSET 0xAC +#define THC_I2C_IC_SDA_STUCK_AT_LOW_TIMEOUT_OFFSET 0xB0 +#define THC_I2C_IC_CLR_SCL_STUCK_DET_OFFSET 0xB4 +#define THC_I2C_IC_DEVICE_ID_OFFSET 0xB8 +#define THC_I2C_IC_SMBUS_CLK_LOW_SEXT_OFFSET 0xBC +#define THC_I2C_IC_SMBUS_CLK_LOW_MEXT_OFFSET 0xC0 +#define THC_I2C_IC_SMBUS_THIGH_MAX_IDLE_COUNT_OFFSET 0xC4 +#define THC_I2C_IC_SMBUS_INTR_STAT_OFFSET 0xC8 +#define THC_I2C_IC_SMBUS_INTR_MASK_OFFSET 0xCC +#define THC_I2C_IC_SMBUS_RAW_INTR_STAT_OFFSET 0xD0 +#define THC_I2C_IC_CLR_SMBUS_INTR_OFFSET 0xD4 +#define THC_I2C_IC_OPTIONAL_SAR_OFFSET 0xD8 +#define THC_I2C_IC_SMBUS_UDID_LSB_OFFSET 0xDC +#define THC_I2C_IC_SMBUS_UDID_WORD0_OFFSET 0xDC +#define THC_I2C_IC_SMBUS_UDID_WORD1_OFFSET 0xE0 +#define THC_I2C_IC_SMBUS_UDID_WORD2_OFFSET 0xE4 +#define THC_I2C_IC_SMBUS_UDID_WORD3_OFFSET 0xE8 +#define THC_I2C_IC_COMP_PARAM_1_OFFSET 0xF4 +#define THC_I2C_IC_COMP_VERSION_OFFSET 0xF8 +#define THC_I2C_IC_COMP_TYPE_OFFSET 0xFC + +/** + * THC I2C sub-system supported speed mode + */ +enum THC_I2C_SPEED_MODE { + THC_I2C_STANDARD = 1, + THC_I2C_FAST_AND_PLUS = 2, + THC_I2C_HIGH_SPEED = 3, +}; + +/* THC I2C sub-system register bits definition */ +#define THC_I2C_IC_ENABLE_ENABLE BIT(0) +#define THC_I2C_IC_ENABLE_ABORT BIT(1) +#define THC_I2C_IC_ENABLE_TX_CMD_BLOCK BIT(2) +#define THC_I2C_IC_ENABLE_SDA_STUCK_RECOVERY_ENABLE BIT(3) +#define THC_I2C_IC_ENABLE_SMBUS_CLK_RESET BIT(16) +#define THC_I2C_IC_ENABLE_SMBUS_SUSPEND_EN BIT(17) +#define THC_I2C_IC_ENABLE_SMBUS_ALERT_EN BIT(18) + +#define THC_I2C_IC_CON_MASTER_MODE BIT(0) +#define THC_I2C_IC_CON_SPEED GENMASK(2, 1) +#define THC_I2C_IC_CON_IC_10BITADDR_SLAVE BIT(3) +#define THC_I2C_IC_CON_IC_10BITADDR_MASTER BIT(4) +#define THC_I2C_IC_CON_IC_RESTART_EN BIT(5) +#define THC_I2C_IC_CON_IC_SLAVE_DISABLE BIT(6) +#define THC_I2C_IC_CON_STOP_DET_IFADDRESSED BIT(7) +#define THC_I2C_IC_CON_TX_EMPTY_CTRL BIT(8) +#define THC_I2C_IC_CON_RX_FIFO_FULL_HLD_CTRL BIT(9) +#define THC_I2C_IC_CON_STOP_DET_IF_MASTER_ACTIVE BIT(10) +#define THC_I2C_IC_CON_BUS_CLEAR_FEATURE_CTRL BIT(11) +#define THC_I2C_IC_CON_OPTIONAL_SAR_CTRL BIT(16) +#define THC_I2C_IC_CON_SMBUS_SLAVE_QUICK_EN BIT(17) +#define THC_I2C_IC_CON_SMBUS_ARP_EN BIT(18) +#define THC_I2C_IC_CON_SMBUS_PERSISTENT_SLV_ADDR_EN BIT(19) + +#define THC_I2C_IC_TAR_IC_TAR GENMASK(9, 0) +#define THC_I2C_IC_TAR_GC_OR_START BIT(10) +#define THC_I2C_IC_TAR_SPECIAL BIT(11) +#define THC_I2C_IC_TAR_IC_10BITADDR_MASTER BIT(12) +#define THC_I2C_IC_TAR_DEVICE_ID BIT(13) +#define THC_I2C_IC_TAR_SMBUS_QUICK_CMD BIT(16) + +#define THC_I2C_IC_INTR_MASK_M_RX_UNDER BIT(0) +#define THC_I2C_IC_INTR_MASK_M_RX_OVER BIT(1) +#define THC_I2C_IC_INTR_MASK_M_RX_FULL BIT(2) +#define THC_I2C_IC_INTR_MASK_M_TX_OVER BIT(3) +#define THC_I2C_IC_INTR_MASK_M_TX_EMPTY BIT(4) +#define THC_I2C_IC_INTR_MASK_M_RD_REQ BIT(5) +#define THC_I2C_IC_INTR_MASK_M_TX_ABRT BIT(6) +#define THC_I2C_IC_INTR_MASK_M_RX_DONE BIT(7) +#define THC_I2C_IC_INTR_MASK_M_ACTIVITY BIT(8) +#define THC_I2C_IC_INTR_MASK_M_STOP_DET BIT(9) +#define THC_I2C_IC_INTR_MASK_M_START_DET BIT(10) +#define THC_I2C_IC_INTR_MASK_M_GEN_CALL BIT(11) +#define THC_I2C_IC_INTR_MASK_M_RESTART_DET BIT(12) +#define THC_I2C_IC_INTR_MASK_M_MASTER_ON_HOLD BIT(13) +#define THC_I2C_IC_INTR_MASK_M_SCL_STUCK_AT_LOW BIT(14) + +#define THC_I2C_IC_DMA_CR_RDMAE BIT(0) +#define THC_I2C_IC_DMA_CR_TDMAE BIT(1) + +#endif /* _INTEL_THC_HW_H_ */ diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h index 6f1443999d1d..1deacb4568cb 100644 --- a/drivers/hid/wacom.h +++ b/drivers/hid/wacom.h @@ -218,6 +218,14 @@ static inline __u32 wacom_s32tou(s32 value, __u8 n) return value & (1 << (n - 1)) ? value & (~(~0U << n)) : value; } +static inline u32 wacom_rescale(u32 value, u32 in_max, u32 out_max) +{ + if (in_max == 0 || out_max == 0) + return 0; + value = clamp(value, 0, in_max); + return DIV_ROUND_CLOSEST(value * out_max, in_max); +} + extern const struct hid_device_id wacom_ids[]; void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len); diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 9843b52bd017..8125383932ec 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -1084,6 +1084,17 @@ static ssize_t wacom_luminance_store(struct wacom *wacom, u8 *dest, mutex_lock(&wacom->lock); *dest = value & 0x7f; + for (unsigned int i = 0; i < wacom->led.count; i++) { + struct wacom_group_leds *group = &wacom->led.groups[i]; + + for (unsigned int j = 0; j < group->count; j++) { + if (dest == &wacom->led.llv) + group->leds[j].llv = *dest; + else if (dest == &wacom->led.hlv) + group->leds[j].hlv = *dest; + } + } + err = wacom_led_control(wacom); mutex_unlock(&wacom->lock); @@ -1302,10 +1313,10 @@ enum led_brightness wacom_leds_brightness_get(struct wacom_led *led) struct wacom *wacom = led->wacom; if (wacom->led.max_hlv) - return led->hlv * LED_FULL / wacom->led.max_hlv; + return wacom_rescale(led->hlv, wacom->led.max_hlv, LED_FULL); if (wacom->led.max_llv) - return led->llv * LED_FULL / wacom->led.max_llv; + return wacom_rescale(led->llv, wacom->led.max_llv, LED_FULL); /* device doesn't support brightness tuning */ return LED_FULL; @@ -1337,8 +1348,8 @@ static int wacom_led_brightness_set(struct led_classdev *cdev, goto out; } - led->llv = wacom->led.llv = wacom->led.max_llv * brightness / LED_FULL; - led->hlv = wacom->led.hlv = wacom->led.max_hlv * brightness / LED_FULL; + led->llv = wacom->led.llv = wacom_rescale(brightness, LED_FULL, wacom->led.max_llv); + led->hlv = wacom->led.hlv = wacom_rescale(brightness, LED_FULL, wacom->led.max_hlv); wacom->led.groups[led->group].select = led->id; @@ -1370,17 +1381,6 @@ static int wacom_led_register_one(struct device *dev, struct wacom *wacom, if (!name) return -ENOMEM; - if (!read_only) { - led->trigger.name = name; - error = devm_led_trigger_register(dev, &led->trigger); - if (error) { - hid_err(wacom->hdev, - "failed to register LED trigger %s: %d\n", - led->cdev.name, error); - return error; - } - } - led->group = group; led->id = id; led->wacom = wacom; @@ -1397,6 +1397,19 @@ static int wacom_led_register_one(struct device *dev, struct wacom *wacom, led->cdev.brightness_set = wacom_led_readonly_brightness_set; } + if (!read_only) { + led->trigger.name = name; + if (id == wacom->led.groups[group].select) + led->trigger.brightness = wacom_leds_brightness_get(led); + error = devm_led_trigger_register(dev, &led->trigger); + if (error) { + hid_err(wacom->hdev, + "failed to register LED trigger %s: %d\n", + led->cdev.name, error); + return error; + } + } + error = devm_led_classdev_register(dev, &led->cdev); if (error) { hid_err(wacom->hdev, diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 5501a560fb07..b60bfafc6a8f 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -4946,6 +4946,10 @@ static const struct wacom_features wacom_features_0x94 = HID_DEVICE(BUS_I2C, HID_GROUP_WACOM, USB_VENDOR_ID_WACOM, prod),\ .driver_data = (kernel_ulong_t)&wacom_features_##prod +#define PCI_DEVICE_WACOM(prod) \ + HID_DEVICE(BUS_PCI, HID_GROUP_WACOM, USB_VENDOR_ID_WACOM, prod),\ + .driver_data = (kernel_ulong_t)&wacom_features_##prod + #define USB_DEVICE_LENOVO(prod) \ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, prod), \ .driver_data = (kernel_ulong_t)&wacom_features_##prod @@ -5115,6 +5119,7 @@ const struct hid_device_id wacom_ids[] = { { USB_DEVICE_WACOM(HID_ANY_ID) }, { I2C_DEVICE_WACOM(HID_ANY_ID) }, + { PCI_DEVICE_WACOM(HID_ANY_ID) }, { BT_DEVICE_WACOM(HID_ANY_ID) }, { } }; diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 3c6011a48dab..6e084c207414 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -944,16 +944,6 @@ void vmbus_initiate_unload(bool crash) vmbus_wait_for_unload(); } -static void check_ready_for_resume_event(void) -{ - /* - * If all the old primary channels have been fixed up, then it's safe - * to resume. - */ - if (atomic_dec_and_test(&vmbus_connection.nr_chan_fixup_on_resume)) - complete(&vmbus_connection.ready_for_resume_event); -} - static void vmbus_setup_channel_state(struct vmbus_channel *channel, struct vmbus_channel_offer_channel *offer) { @@ -1109,8 +1099,6 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr) /* Add the channel back to the array of channels. */ vmbus_channel_map_relid(oldchannel); - check_ready_for_resume_event(); - mutex_unlock(&vmbus_connection.channel_mutex); return; } @@ -1296,13 +1284,28 @@ EXPORT_SYMBOL_GPL(vmbus_hvsock_device_unregister); /* * vmbus_onoffers_delivered - - * This is invoked when all offers have been delivered. + * The CHANNELMSG_ALLOFFERS_DELIVERED message arrives after all + * boot-time offers are delivered. A boot-time offer is for the primary + * channel for any virtual hardware configured in the VM at the time it boots. + * Boot-time offers include offers for physical devices assigned to the VM + * via Hyper-V's Discrete Device Assignment (DDA) functionality that are + * handled as virtual PCI devices in Linux (e.g., NVMe devices and GPUs). + * Boot-time offers do not include offers for VMBus sub-channels. Because + * devices can be hot-added to the VM after it is booted, additional channel + * offers that aren't boot-time offers can be received at any time after the + * all-offers-delivered message. * - * Nothing to do here. + * SR-IOV NIC Virtual Functions (VFs) assigned to a VM are not considered + * to be assigned to the VM at boot-time, and offers for VFs may occur after + * the all-offers-delivered message. VFs are optional accelerators to the + * synthetic VMBus NIC and are effectively hot-added only after the VMBus + * NIC channel is opened (once it knows the guest can support it, via the + * sriov bit in the netvsc protocol). */ static void vmbus_onoffers_delivered( struct vmbus_channel_message_header *hdr) { + complete(&vmbus_connection.all_offers_delivered_event); } /* @@ -1578,7 +1581,8 @@ void vmbus_onmessage(struct vmbus_channel_message_header *hdr) } /* - * vmbus_request_offers - Send a request to get all our pending offers. + * vmbus_request_offers - Send a request to get all our pending offers + * and wait for all boot-time offers to arrive. */ int vmbus_request_offers(void) { @@ -1596,6 +1600,10 @@ int vmbus_request_offers(void) msg->msgtype = CHANNELMSG_REQUESTOFFERS; + /* + * This REQUESTOFFERS message will result in the host sending an all + * offers delivered message after all the boot-time offers are sent. + */ ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_message_header), true); @@ -1607,6 +1615,29 @@ int vmbus_request_offers(void) goto cleanup; } + /* + * Wait for the host to send all boot-time offers. + * Keeping it as a best-effort mechanism, where a warning is + * printed if a timeout occurs, and execution is resumed. + */ + if (!wait_for_completion_timeout(&vmbus_connection.all_offers_delivered_event, + secs_to_jiffies(60))) { + pr_warn("timed out waiting for all boot-time offers to be delivered.\n"); + } + + /* + * Flush handling of offer messages (which may initiate work on + * other work queues). + */ + flush_workqueue(vmbus_connection.work_queue); + + /* + * Flush workqueue for processing the incoming offers. Subchannel + * offers and their processing can happen later, so there is no need to + * flush that workqueue here. + */ + flush_workqueue(vmbus_connection.handle_primary_chan_wq); + cleanup: kfree(msginfo); diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index f001ae880e1d..8351360bba16 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -34,8 +34,8 @@ struct vmbus_connection vmbus_connection = { .ready_for_suspend_event = COMPLETION_INITIALIZER( vmbus_connection.ready_for_suspend_event), - .ready_for_resume_event = COMPLETION_INITIALIZER( - vmbus_connection.ready_for_resume_event), + .all_offers_delivered_event = COMPLETION_INITIALIZER( + vmbus_connection.all_offers_delivered_event), }; EXPORT_SYMBOL_GPL(vmbus_connection); diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index c38dcdfcb914..fec2f18679e3 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -28,7 +28,7 @@ #include #include -#include +#include #include @@ -756,7 +756,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, * adding succeeded, it is ok to proceed even if the memory was * not onlined in time. */ - wait_for_completion_timeout(&dm_device.ol_waitevent, 5 * HZ); + wait_for_completion_timeout(&dm_device.ol_waitevent, secs_to_jiffies(5)); post_status(&dm_device); } } @@ -766,16 +766,18 @@ static void hv_online_page(struct page *pg, unsigned int order) struct hv_hotadd_state *has; unsigned long pfn = page_to_pfn(pg); - guard(spinlock_irqsave)(&dm_device.ha_lock); - list_for_each_entry(has, &dm_device.ha_region_list, list) { - /* The page belongs to a different HAS. */ - if (pfn < has->start_pfn || - (pfn + (1UL << order) > has->end_pfn)) - continue; + scoped_guard(spinlock_irqsave, &dm_device.ha_lock) { + list_for_each_entry(has, &dm_device.ha_region_list, list) { + /* The page belongs to a different HAS. */ + if (pfn < has->start_pfn || + (pfn + (1UL << order) > has->end_pfn)) + continue; - hv_bring_pgs_online(has, pfn, 1UL << order); - break; + hv_bring_pgs_online(has, pfn, 1UL << order); + return; + } } + generic_online_page(pg, order); } static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) @@ -1373,7 +1375,8 @@ static int dm_thread_func(void *dm_dev) struct hv_dynmem_device *dm = dm_dev; while (!kthread_should_stop()) { - wait_for_completion_interruptible_timeout(&dm_device.config_event, 1 * HZ); + wait_for_completion_interruptible_timeout(&dm_device.config_event, + secs_to_jiffies(1)); /* * The host expects us to post information on the memory * pressure every second. @@ -1585,7 +1588,7 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, return -ENOSPC; } - hint->type = HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD; + hint->heat_type = HV_EXTMEM_HEAT_HINT_COLD_DISCARD; hint->reserved = 0; for_each_sg(sgl, sg, nents, i) { union hv_gpa_page_range *range; @@ -1748,7 +1751,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); + t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5)); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1806,7 +1809,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); + t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5)); if (t == 0) { ret = -ETIMEDOUT; goto out; diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 7a35c82976e0..f2e6f55d6ca6 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include /* @@ -141,7 +141,7 @@ static int sysctl_record_panic_msg = 1; * sysctl option to allow the user to control whether kmsg data should be * reported to Hyper-V on panic. */ -static struct ctl_table hv_ctl_table[] = { +static const struct ctl_table hv_ctl_table[] = { { .procname = "hyperv_record_panic_msg", .data = &sysctl_record_panic_msg, @@ -278,6 +278,11 @@ static void hv_kmsg_dump_register(void) } } +static inline bool hv_output_page_exists(void) +{ + return hv_root_partition || IS_ENABLED(CONFIG_HYPERV_VTL_MODE); +} + int __init hv_common_init(void) { int i; @@ -340,19 +345,19 @@ int __init hv_common_init(void) BUG_ON(!hyperv_pcpu_input_arg); /* Allocate the per-CPU state for output arg for root */ - if (hv_root_partition) { + if (hv_output_page_exists()) { hyperv_pcpu_output_arg = alloc_percpu(void *); BUG_ON(!hyperv_pcpu_output_arg); } - hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index), + hv_vp_index = kmalloc_array(nr_cpu_ids, sizeof(*hv_vp_index), GFP_KERNEL); if (!hv_vp_index) { hv_common_free(); return -ENOMEM; } - for (i = 0; i < num_possible_cpus(); i++) + for (i = 0; i < nr_cpu_ids; i++) hv_vp_index[i] = VP_INVAL; return 0; @@ -435,7 +440,7 @@ int hv_common_cpu_init(unsigned int cpu) void **inputarg, **outputarg; u64 msr_vp_index; gfp_t flags; - int pgcount = hv_root_partition ? 2 : 1; + const int pgcount = hv_output_page_exists() ? 2 : 1; void *mem; int ret; @@ -453,7 +458,7 @@ int hv_common_cpu_init(unsigned int cpu) if (!mem) return -ENOMEM; - if (hv_root_partition) { + if (hv_output_page_exists()) { outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); *outputarg = (char *)mem + HV_HYP_PAGE_SIZE; } diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index d35b60c06114..62795f6cbb00 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -27,7 +27,7 @@ #include #include #include -#include +#include #include "hyperv_vmbus.h" #include "hv_utils_transport.h" @@ -655,7 +655,7 @@ void hv_kvp_onchannelcallback(void *context) if (host_negotiatied == NEGO_NOT_STARTED) { host_negotiatied = NEGO_IN_PROGRESS; schedule_delayed_work(&kvp_host_handshake_work, - HV_UTIL_NEGO_TIMEOUT * HZ); + secs_to_jiffies(HV_UTIL_NEGO_TIMEOUT)); } return; } @@ -724,7 +724,7 @@ void hv_kvp_onchannelcallback(void *context) */ schedule_work(&kvp_sendkey_work); schedule_delayed_work(&kvp_timeout_work, - HV_UTIL_TIMEOUT * HZ); + secs_to_jiffies(HV_UTIL_TIMEOUT)); return; @@ -767,6 +767,12 @@ hv_kvp_init(struct hv_util_service *srv) */ kvp_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_kvp_init_transport(void) +{ hvt = hvutil_transport_init(kvp_devname, CN_KVP_IDX, CN_KVP_VAL, kvp_on_msg, kvp_on_reset); if (!hvt) diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index 0d2184be1691..2e7f537d53cf 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include "hyperv_vmbus.h" #include "hv_utils_transport.h" @@ -193,7 +193,8 @@ static void vss_send_op(void) vss_transaction.state = HVUTIL_USERSPACE_REQ; schedule_delayed_work(&vss_timeout_work, op == VSS_OP_FREEZE ? - VSS_FREEZE_TIMEOUT * HZ : HV_UTIL_TIMEOUT * HZ); + secs_to_jiffies(VSS_FREEZE_TIMEOUT) : + secs_to_jiffies(HV_UTIL_TIMEOUT)); rc = hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL); if (rc) { @@ -388,6 +389,12 @@ hv_vss_init(struct hv_util_service *srv) */ vss_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_vss_init_transport(void) +{ hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL, vss_on_msg, vss_on_reset); if (!hvt) { diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index c4f525325790..36ee89c0358b 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -141,6 +141,7 @@ static struct hv_util_service util_heartbeat = { static struct hv_util_service util_kvp = { .util_cb = hv_kvp_onchannelcallback, .util_init = hv_kvp_init, + .util_init_transport = hv_kvp_init_transport, .util_pre_suspend = hv_kvp_pre_suspend, .util_pre_resume = hv_kvp_pre_resume, .util_deinit = hv_kvp_deinit, @@ -149,6 +150,7 @@ static struct hv_util_service util_kvp = { static struct hv_util_service util_vss = { .util_cb = hv_vss_onchannelcallback, .util_init = hv_vss_init, + .util_init_transport = hv_vss_init_transport, .util_pre_suspend = hv_vss_pre_suspend, .util_pre_resume = hv_vss_pre_resume, .util_deinit = hv_vss_deinit, @@ -590,10 +592,8 @@ static int util_probe(struct hv_device *dev, srv->channel = dev->channel; if (srv->util_init) { ret = srv->util_init(srv); - if (ret) { - ret = -ENODEV; + if (ret) goto error1; - } } /* @@ -613,6 +613,13 @@ static int util_probe(struct hv_device *dev, if (ret) goto error; + if (srv->util_init_transport) { + ret = srv->util_init_transport(); + if (ret) { + vmbus_close(dev->channel); + goto error; + } + } return 0; error: diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index d2856023d53c..29780f3a7478 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -15,10 +15,10 @@ #include #include #include -#include #include #include #include +#include #include "hv_trace.h" @@ -287,18 +287,10 @@ struct vmbus_connection { struct completion ready_for_suspend_event; /* - * The number of primary channels that should be "fixed up" - * upon resume: these channels are re-offered upon resume, and some - * fields of the channel offers (i.e. child_relid and connection_id) - * can change, so the old offermsg must be fixed up, before the resume - * callbacks of the VSC drivers start to further touch the channels. + * Completed once the host has offered all boot-time channels. + * Note that some channels may still be under process on a workqueue. */ - atomic_t nr_chan_fixup_on_resume; - /* - * vmbus_bus_resume() waits for "nr_chan_fixup_on_resume" to - * drop to zero. - */ - struct completion ready_for_resume_event; + struct completion all_offers_delivered_event; }; @@ -370,12 +362,14 @@ void vmbus_on_event(unsigned long data); void vmbus_on_msg_dpc(unsigned long data); int hv_kvp_init(struct hv_util_service *srv); +int hv_kvp_init_transport(void); void hv_kvp_deinit(void); int hv_kvp_pre_suspend(void); int hv_kvp_pre_resume(void); void hv_kvp_onchannelcallback(void *context); int hv_vss_init(struct hv_util_service *srv); +int hv_vss_init_transport(void); void hv_vss_deinit(void); int hv_vss_pre_suspend(void); int hv_vss_pre_resume(void); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 6d89d37b069a..0f6cd44fff29 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2427,11 +2427,6 @@ static int vmbus_bus_suspend(struct device *dev) if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0) wait_for_completion(&vmbus_connection.ready_for_suspend_event); - if (atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0) { - pr_err("Can not suspend due to a previous failed resuming\n"); - return -EBUSY; - } - mutex_lock(&vmbus_connection.channel_mutex); list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { @@ -2456,22 +2451,18 @@ static int vmbus_bus_suspend(struct device *dev) pr_err("Sub-channel not deleted!\n"); WARN_ON_ONCE(1); } - - atomic_inc(&vmbus_connection.nr_chan_fixup_on_resume); } mutex_unlock(&vmbus_connection.channel_mutex); vmbus_initiate_unload(false); - /* Reset the event for the next resume. */ - reinit_completion(&vmbus_connection.ready_for_resume_event); - return 0; } static int vmbus_bus_resume(struct device *dev) { + struct vmbus_channel *channel; struct vmbus_channel_msginfo *msginfo; size_t msgsize; int ret; @@ -2502,13 +2493,23 @@ static int vmbus_bus_resume(struct device *dev) if (ret != 0) return ret; - WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) == 0); - vmbus_request_offers(); - if (wait_for_completion_timeout( - &vmbus_connection.ready_for_resume_event, 10 * HZ) == 0) - pr_err("Some vmbus device is missing after suspending?\n"); + mutex_lock(&vmbus_connection.channel_mutex); + list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { + if (channel->offermsg.child_relid != INVALID_RELID) + continue; + + /* hvsock channels are not expected to be present. */ + if (is_hvsock_channel(channel)) + continue; + + pr_err("channel %pUl/%pUl not present after resume.\n", + &channel->offermsg.offer.if_type, + &channel->offermsg.offer.if_instance); + /* ToDo: Cleanup these channels here */ + } + mutex_unlock(&vmbus_connection.channel_mutex); /* Reset the event for the next suspend. */ reinit_completion(&vmbus_connection.ready_for_suspend_event); diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index dd376602f3f1..4cbaba15d86e 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -324,7 +324,7 @@ config SENSORS_K8TEMP config SENSORS_K10TEMP tristate "AMD Family 10h+ temperature sensor" - depends on X86 && PCI && AMD_NB + depends on X86 && PCI && AMD_NODE help If you say yes here you get support for the temperature sensor(s) inside your CPU. Supported are later revisions of @@ -413,7 +413,7 @@ config SENSORS_ASPEED will be called aspeed_pwm_tacho. config SENSORS_ASPEED_G6 - tristate "ASPEED g6 PWM and Fan tach driver" + tristate "ASPEED G6 PWM and Fan tach driver" depends on ARCH_ASPEED || COMPILE_TEST depends on PWM help @@ -421,7 +421,7 @@ config SENSORS_ASPEED_G6 controllers. This driver can also be built as a module. If so, the module - will be called aspeed_pwm_tacho. + will be called aspeed_g6_pwm_tach. config SENSORS_ATXP1 tristate "Attansic ATXP1 VID controller" @@ -1412,7 +1412,9 @@ config SENSORS_LM73 config SENSORS_LM75 tristate "National Semiconductor LM75 and compatibles" depends on I2C + depends on I3C || !I3C select REGMAP_I2C + select REGMAP_I3C if I3C help If you say yes here you get support for one common type of temperature sensor chip, with models including: @@ -1822,6 +1824,18 @@ config SENSORS_PWM_FAN This driver can also be built as a module. If so, the module will be called pwm-fan. +config SENSORS_QNAP_MCU_HWMON + tristate "QNAP MCU hardware monitoring" + depends on MFD_QNAP_MCU + depends on THERMAL || THERMAL=n + help + Say yes here to enable support for fan and temperature sensor + connected to a QNAP MCU, as found in a number of QNAP network + attached storage devices. + + This driver can also be built as a module. If so, the module + will be called qnap-mcu-hwmon. + config SENSORS_RASPBERRYPI_HWMON tristate "Raspberry Pi voltage monitor" depends on RASPBERRYPI_FIRMWARE || (COMPILE_TEST && !RASPBERRYPI_FIRMWARE) diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index b827b92f2a78..b7ef0f0562d3 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -189,6 +189,7 @@ obj-$(CONFIG_SENSORS_POWERZ) += powerz.o obj-$(CONFIG_SENSORS_POWR1220) += powr1220.o obj-$(CONFIG_SENSORS_PT5161L) += pt5161l.o obj-$(CONFIG_SENSORS_PWM_FAN) += pwm-fan.o +obj-$(CONFIG_SENSORS_QNAP_MCU_HWMON) += qnap-mcu-hwmon.o obj-$(CONFIG_SENSORS_RASPBERRYPI_HWMON) += raspberrypi-hwmon.o obj-$(CONFIG_SENSORS_SBTSI) += sbtsi_temp.o obj-$(CONFIG_SENSORS_SBRMI) += sbrmi.o diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index 2f1c9d97ad21..44afb07409a4 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -84,6 +84,7 @@ struct acpi_power_meter_resource { u64 power; u64 cap; u64 avg_interval; + bool power_alarm; int sensors_valid; unsigned long sensors_last_updated; struct sensor_device_attribute sensors[NUM_SENSORS]; @@ -292,8 +293,8 @@ static ssize_t set_trip(struct device *dev, struct device_attribute *devattr, struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); struct acpi_device *acpi_dev = to_acpi_device(dev); struct acpi_power_meter_resource *resource = acpi_dev->driver_data; + unsigned long temp, trip_bk; int res; - unsigned long temp; res = kstrtoul(buf, 10, &temp); if (res) @@ -301,13 +302,15 @@ static ssize_t set_trip(struct device *dev, struct device_attribute *devattr, temp = DIV_ROUND_CLOSEST(temp, 1000); - mutex_lock(&resource->lock); + guard(mutex)(&resource->lock); + + trip_bk = resource->trip[attr->index - 7]; resource->trip[attr->index - 7] = temp; res = set_acpi_trip(resource); - mutex_unlock(&resource->lock); - - if (res) + if (res) { + resource->trip[attr->index - 7] = trip_bk; return res; + } return count; } @@ -396,6 +399,9 @@ static ssize_t show_val(struct device *dev, struct acpi_device *acpi_dev = to_acpi_device(dev); struct acpi_power_meter_resource *resource = acpi_dev->driver_data; u64 val = 0; + int ret; + + guard(mutex)(&resource->lock); switch (attr->index) { case 0: @@ -423,10 +429,17 @@ static ssize_t show_val(struct device *dev, val = 0; break; case 6: - if (resource->power > resource->cap) - val = 1; - else - val = 0; + ret = update_meter(resource); + if (ret) + return ret; + /* need to update cap if not to support the notification. */ + if (!(resource->caps.flags & POWER_METER_CAN_NOTIFY)) { + ret = update_cap(resource); + if (ret) + return ret; + } + val = resource->power_alarm || resource->power > resource->cap; + resource->power_alarm = resource->power > resource->cap; break; case 7: case 8: @@ -682,7 +695,7 @@ static int setup_attrs(struct acpi_power_meter_resource *resource) /* _PMD method is optional. */ res = read_domain_devices(resource); - if (res != -ENODEV) + if (res && res != -ENODEV) return res; if (resource->caps.flags & POWER_METER_CAN_MEASURE) { @@ -847,12 +860,20 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME); break; case METER_NOTIFY_CAP: + mutex_lock(&resource->lock); + res = update_cap(resource); + if (res) + dev_err_once(&device->dev, "update cap failed when capping value is changed.\n"); + mutex_unlock(&resource->lock); sysfs_notify(&device->dev.kobj, NULL, POWER_CAP_NAME); break; case METER_NOTIFY_INTERVAL: sysfs_notify(&device->dev.kobj, NULL, POWER_AVG_INTERVAL_NAME); break; case METER_NOTIFY_CAPPING: + mutex_lock(&resource->lock); + resource->power_alarm = true; + mutex_unlock(&resource->lock); sysfs_notify(&device->dev.kobj, NULL, POWER_ALARM_NAME); dev_info(&device->dev, "Capping in progress.\n"); break; diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 9555366aeaf0..43e54dc513da 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -250,6 +250,8 @@ static const struct ec_sensor_info sensors_family_amd_600[] = { EC_SENSOR("Water_In", hwmon_temp, 1, 0x01, 0x00), [ec_sensor_temp_water_out] = EC_SENSOR("Water_Out", hwmon_temp, 1, 0x01, 0x01), + [ec_sensor_fan_cpu_opt] = + EC_SENSOR("CPU_Opt", hwmon_fan, 2, 0x00, 0xb0), }; static const struct ec_sensor_info sensors_family_intel_300[] = { @@ -477,6 +479,15 @@ static const struct ec_board_info board_info_zenith_ii_extreme = { .family = family_amd_500_series, }; +static const struct ec_board_info board_info_tuf_gaming_x670e_plus = { + .sensors = SENSOR_TEMP_CPU | SENSOR_TEMP_CPU_PACKAGE | + SENSOR_TEMP_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_WATER_IN | SENSOR_TEMP_WATER_OUT | + SENSOR_FAN_CPU_OPT, + .mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH, + .family = family_amd_600_series, +}; + #define DMI_EXACT_MATCH_ASUS_BOARD_NAME(name, board_info) \ { \ .matches = { \ @@ -538,6 +549,8 @@ static const struct dmi_system_id dmi_table[] = { &board_info_zenith_ii_extreme), DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG ZENITH II EXTREME ALPHA", &board_info_zenith_ii_extreme), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("TUF GAMING X670E-PLUS", + &board_info_tuf_gaming_x670e_plus), {}, }; diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c index 1dc7e24fe4c5..c80350e499e9 100644 --- a/drivers/hwmon/asus_atk0110.c +++ b/drivers/hwmon/asus_atk0110.c @@ -17,6 +17,7 @@ #include #include #include +#include #define ATK_HID "ATK0110" @@ -441,7 +442,7 @@ static void atk_print_sensor(struct atk_data *data, union acpi_object *obj) flags->integer.value, name->string.pointer, limit1->integer.value, limit2->integer.value, - enable->integer.value ? "enabled" : "disabled"); + str_enabled_disabled(enable->integer.value)); #endif } @@ -1074,8 +1075,7 @@ static int atk_ec_enabled(struct atk_data *data) err = -EIO; } else { err = (buf->value != 0); - dev_dbg(dev, "EC is %sabled\n", - err ? "en" : "dis"); + dev_dbg(dev, "EC is %s\n", str_enabled_disabled(err)); } ACPI_FREE(obj); @@ -1096,18 +1096,15 @@ static int atk_ec_ctl(struct atk_data *data, int enable) obj = atk_sitm(data, &sitm); if (IS_ERR(obj)) { - dev_err(dev, "Failed to %sable the EC\n", - enable ? "en" : "dis"); + dev_err(dev, "Failed to %s the EC\n", str_enable_disable(enable)); return PTR_ERR(obj); } ec_ret = (struct atk_acpi_ret_buffer *)obj->buffer.pointer; if (ec_ret->flags == 0) { - dev_err(dev, "Failed to %sable the EC\n", - enable ? "en" : "dis"); + dev_err(dev, "Failed to %s the EC\n", str_enable_disable(enable)); err = -EIO; } else { - dev_info(dev, "EC %sabled\n", - enable ? "en" : "dis"); + dev_info(dev, "EC %s\n", str_enabled_disabled(enable)); } ACPI_FREE(obj); diff --git a/drivers/hwmon/chipcap2.c b/drivers/hwmon/chipcap2.c index edf454474f11..9d071f7ca9d2 100644 --- a/drivers/hwmon/chipcap2.c +++ b/drivers/hwmon/chipcap2.c @@ -13,6 +13,7 @@ #include #include +#include #include #include #include @@ -556,55 +557,40 @@ static int cc2_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { struct cc2_data *data = dev_get_drvdata(dev); - int ret = 0; - mutex_lock(&data->dev_access_lock); + guard(mutex)(&data->dev_access_lock); switch (type) { case hwmon_temp: - ret = cc2_measurement(data, type, val); - break; + return cc2_measurement(data, type, val); case hwmon_humidity: switch (attr) { case hwmon_humidity_input: - ret = cc2_measurement(data, type, val); - break; + return cc2_measurement(data, type, val); case hwmon_humidity_min: - ret = cc2_get_reg_val(data, CC2_R_ALARM_L_ON, val); - break; + return cc2_get_reg_val(data, CC2_R_ALARM_L_ON, val); case hwmon_humidity_min_hyst: - ret = cc2_get_reg_val(data, CC2_R_ALARM_L_OFF, val); - break; + return cc2_get_reg_val(data, CC2_R_ALARM_L_OFF, val); case hwmon_humidity_max: - ret = cc2_get_reg_val(data, CC2_R_ALARM_H_ON, val); - break; + return cc2_get_reg_val(data, CC2_R_ALARM_H_ON, val); case hwmon_humidity_max_hyst: - ret = cc2_get_reg_val(data, CC2_R_ALARM_H_OFF, val); - break; + return cc2_get_reg_val(data, CC2_R_ALARM_H_OFF, val); case hwmon_humidity_min_alarm: - ret = cc2_humidity_min_alarm_status(data, val); - break; + return cc2_humidity_min_alarm_status(data, val); case hwmon_humidity_max_alarm: - ret = cc2_humidity_max_alarm_status(data, val); - break; + return cc2_humidity_max_alarm_status(data, val); default: - ret = -EOPNOTSUPP; + return -EOPNOTSUPP; } - break; default: - ret = -EOPNOTSUPP; + return -EOPNOTSUPP; } - - mutex_unlock(&data->dev_access_lock); - - return ret; } static int cc2_write(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long val) { struct cc2_data *data = dev_get_drvdata(dev); - int ret; u16 arg; u8 cmd; @@ -614,41 +600,28 @@ static int cc2_write(struct device *dev, enum hwmon_sensor_types type, u32 attr, if (val < 0 || val > CC2_RH_MAX) return -EINVAL; - mutex_lock(&data->dev_access_lock); + guard(mutex)(&data->dev_access_lock); switch (attr) { case hwmon_humidity_min: cmd = CC2_W_ALARM_L_ON; arg = cc2_rh_to_reg(val); - ret = cc2_write_reg(data, cmd, arg); - break; - + return cc2_write_reg(data, cmd, arg); case hwmon_humidity_min_hyst: cmd = CC2_W_ALARM_L_OFF; arg = cc2_rh_to_reg(val); - ret = cc2_write_reg(data, cmd, arg); - break; - + return cc2_write_reg(data, cmd, arg); case hwmon_humidity_max: cmd = CC2_W_ALARM_H_ON; arg = cc2_rh_to_reg(val); - ret = cc2_write_reg(data, cmd, arg); - break; - + return cc2_write_reg(data, cmd, arg); case hwmon_humidity_max_hyst: cmd = CC2_W_ALARM_H_OFF; arg = cc2_rh_to_reg(val); - ret = cc2_write_reg(data, cmd, arg); - break; - + return cc2_write_reg(data, cmd, arg); default: - ret = -EOPNOTSUPP; - break; + return -EOPNOTSUPP; } - - mutex_unlock(&data->dev_access_lock); - - return ret; } static int cc2_request_ready_irq(struct cc2_data *data, struct device *dev) diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index f5bdf842040e..cd00adaad1b4 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -1544,6 +1544,14 @@ static const struct dmi_system_id i8k_whitelist_fan_control[] __initconst = { }, .driver_data = (void *)&i8k_fan_control_data[I8K_FAN_34A3_35A3], }, + { + .ident = "Dell XPS 13 9370", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS 13 9370"), + }, + .driver_data = (void *)&i8k_fan_control_data[I8K_FAN_30A3_31A3], + }, { .ident = "Dell Optiplex 7000", .matches = { diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c index 6bdd21aa005a..291d91f68646 100644 --- a/drivers/hwmon/drivetemp.c +++ b/drivers/hwmon/drivetemp.c @@ -165,6 +165,7 @@ static int drivetemp_scsi_command(struct drivetemp_data *st, { u8 scsi_cmd[MAX_COMMAND_SIZE]; enum req_op op; + int err; memset(scsi_cmd, 0, sizeof(scsi_cmd)); scsi_cmd[0] = ATA_16; @@ -192,8 +193,11 @@ static int drivetemp_scsi_command(struct drivetemp_data *st, scsi_cmd[12] = lba_high; scsi_cmd[14] = ata_command; - return scsi_execute_cmd(st->sdev, scsi_cmd, op, st->smartdata, - ATA_SECT_SIZE, HZ, 5, NULL); + err = scsi_execute_cmd(st->sdev, scsi_cmd, op, st->smartdata, + ATA_SECT_SIZE, 10 * HZ, 5, NULL); + if (err > 0) + err = -EIO; + return err; } static int drivetemp_ata_command(struct drivetemp_data *st, u8 feature, diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index bbb9cc44e29f..9703d60e9bbf 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -158,11 +158,6 @@ static umode_t hwmon_is_visible(const struct hwmon_ops *ops, /* Thermal zone handling */ -/* - * The complex conditional is necessary to avoid a cyclic dependency - * between hwmon and thermal_sys modules. - */ -#ifdef CONFIG_THERMAL_OF static int hwmon_thermal_get_temp(struct thermal_zone_device *tz, int *temp) { struct hwmon_thermal_data *tdata = thermal_zone_device_priv(tz); @@ -268,6 +263,9 @@ static int hwmon_thermal_register_sensors(struct device *dev) void *drvdata = dev_get_drvdata(dev); int i; + if (!IS_ENABLED(CONFIG_THERMAL_OF)) + return 0; + for (i = 1; info[i]; i++) { int j; @@ -296,6 +294,9 @@ static void hwmon_thermal_notify(struct device *dev, int index) struct hwmon_device *hwdev = to_hwmon_device(dev); struct hwmon_thermal_data *tzdata; + if (!IS_ENABLED(CONFIG_THERMAL_OF)) + return; + list_for_each_entry(tzdata, &hwdev->tzdata, node) { if (tzdata->index == index) { thermal_zone_device_update(tzdata->tzd, @@ -304,16 +305,6 @@ static void hwmon_thermal_notify(struct device *dev, int index) } } -#else -static int hwmon_thermal_register_sensors(struct device *dev) -{ - return 0; -} - -static void hwmon_thermal_notify(struct device *dev, int index) { } - -#endif /* IS_REACHABLE(CONFIG_THERMAL) && ... */ - static int hwmon_attr_base(enum hwmon_sensor_types type) { if (type == hwmon_in || type == hwmon_intrusion) @@ -341,7 +332,7 @@ static int hwmon_attr_base(enum hwmon_sensor_types type) static DEFINE_MUTEX(hwmon_pec_mutex); -static int hwmon_match_device(struct device *dev, void *data) +static int hwmon_match_device(struct device *dev, const void *data) { return dev->class == &hwmon_class; } @@ -1179,6 +1170,12 @@ devm_hwmon_device_register_with_info(struct device *dev, const char *name, if (!dev) return ERR_PTR(-EINVAL); + if (!name) { + name = devm_hwmon_sanitize_name(dev, dev_name(dev)); + if (IS_ERR(name)) + return ERR_CAST(name); + } + ptr = devres_alloc(devm_hwmon_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); diff --git a/drivers/hwmon/isl28022.c b/drivers/hwmon/isl28022.c index f9edcfd164c2..3f9b4520b53e 100644 --- a/drivers/hwmon/isl28022.c +++ b/drivers/hwmon/isl28022.c @@ -486,7 +486,7 @@ static int isl28022_probe(struct i2c_client *client) } static const struct i2c_device_id isl28022_ids[] = { - { "isl28022", 0}, + { "isl28022" }, { /* LIST END */ } }; MODULE_DEVICE_TABLE(i2c, isl28022_ids); @@ -506,8 +506,7 @@ static struct i2c_driver isl28022_driver = { .id_table = isl28022_ids, }; -static int __init -isl28022_init(void) +static int __init isl28022_init(void) { int err; @@ -519,15 +518,13 @@ isl28022_init(void) debugfs_remove_recursive(isl28022_debugfs_root); return err; } +module_init(isl28022_init); -static void __exit -isl28022_exit(void) +static void __exit isl28022_exit(void) { i2c_del_driver(&isl28022_driver); debugfs_remove_recursive(isl28022_debugfs_root); } - -module_init(isl28022_init); module_exit(isl28022_exit); MODULE_AUTHOR("Carsten Spieß "); diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 7dc19c5d62ac..d0b4cc9a5011 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include MODULE_DESCRIPTION("AMD Family 10h+ CPU core temperature monitor"); @@ -150,6 +150,11 @@ static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval) F15H_M60H_REPORTED_TEMP_CTRL_OFFSET, regval); } +static u16 amd_pci_dev_to_node_id(struct pci_dev *pdev) +{ + return PCI_SLOT(pdev->devfn) - AMD_NODE0_PCI_SLOT; +} + static void read_tempreg_nb_zen(struct pci_dev *pdev, u32 *regval) { if (amd_smn_read(amd_pci_dev_to_node_id(pdev), diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c index 2c2205aec7d4..d95a3c6c245c 100644 --- a/drivers/hwmon/lm75.c +++ b/drivers/hwmon/lm75.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -38,6 +39,7 @@ enum lm75_type { /* keep sorted in alphabetical order */ max6626, max31725, mcp980x, + p3t1755, pct2075, stds75, stlm75, @@ -104,17 +106,15 @@ static const unsigned short normal_i2c[] = { 0x48, 0x49, 0x4a, 0x4b, 0x4c, #define LM75_REG_MAX 0x03 #define PCT2075_REG_IDLE 0x04 -/* Each client has this additional data */ struct lm75_data { - struct i2c_client *client; struct regmap *regmap; - struct regulator *vs; u16 orig_conf; - u16 current_conf; u8 resolution; /* In bits, 9 to 16 */ unsigned int sample_time; /* In ms */ enum lm75_type kind; const struct lm75_params *params; + u8 reg_buf[1]; + u8 val_buf[3]; }; /*-----------------------------------------------------------------------*/ @@ -222,6 +222,13 @@ static const struct lm75_params device_params[] = { .default_resolution = 9, .default_sample_time = MSEC_PER_SEC / 18, }, + [p3t1755] = { + .clr_mask = 1 << 1 | 1 << 7, /* disable SMBAlert and one-shot */ + .default_resolution = 12, + .default_sample_time = 55, + .num_sample_times = 4, + .sample_times = (unsigned int []){ 28, 55, 110, 220 }, + }, [pct2075] = { .default_resolution = 11, .default_sample_time = MSEC_PER_SEC / 10, @@ -276,6 +283,7 @@ static const struct lm75_params device_params[] = { .default_sample_time = 125, .num_sample_times = 4, .sample_times = (unsigned int []){ 125, 250, 1000, 4000 }, + .alarm = true, }, [tmp175] = { .set_mask = 3 << 5, /* 12-bit mode */ @@ -332,41 +340,11 @@ static inline long lm75_reg_to_mc(s16 temp, u8 resolution) return ((temp >> (16 - resolution)) * 1000) >> (resolution - 8); } -static int lm75_write_config(struct lm75_data *data, u16 set_mask, - u16 clr_mask) +static inline int lm75_write_config(struct lm75_data *data, u16 set_mask, + u16 clr_mask) { - unsigned int value; - - clr_mask |= LM75_SHUTDOWN << (8 * data->params->config_reg_16bits); - value = data->current_conf & ~clr_mask; - value |= set_mask; - - if (data->current_conf != value) { - s32 err; - if (data->params->config_reg_16bits) - err = regmap_write(data->regmap, LM75_REG_CONF, value); - else - err = i2c_smbus_write_byte_data(data->client, - LM75_REG_CONF, - value); - if (err) - return err; - data->current_conf = value; - } - return 0; -} - -static int lm75_read_config(struct lm75_data *data) -{ - int ret; - unsigned int status; - - if (data->params->config_reg_16bits) { - ret = regmap_read(data->regmap, LM75_REG_CONF, &status); - return ret ? ret : status; - } - - return i2c_smbus_read_byte_data(data->client, LM75_REG_CONF); + return regmap_update_bits(data->regmap, LM75_REG_CONF, + clr_mask | LM75_SHUTDOWN, set_mask); } static irqreturn_t lm75_alarm_handler(int irq, void *private) @@ -418,7 +396,8 @@ static int lm75_read(struct device *dev, enum hwmon_sensor_types type, if (attr == hwmon_temp_alarm) { switch (data->kind) { case as6200: - *val = (regval >> 5) & 0x1; + case tmp112: + *val = (regval >> 13) & 0x1; break; default: return -EINVAL; @@ -469,7 +448,6 @@ static int lm75_write_temp(struct device *dev, u32 attr, long temp) static int lm75_update_interval(struct device *dev, long val) { struct lm75_data *data = dev_get_drvdata(dev); - unsigned int reg; u8 index; s32 err; @@ -489,19 +467,14 @@ static int lm75_update_interval(struct device *dev, long val) break; case tmp112: case as6200: - err = regmap_read(data->regmap, LM75_REG_CONF, ®); - if (err < 0) - return err; - reg &= ~0x00c0; - reg |= (3 - index) << 6; - err = regmap_write(data->regmap, LM75_REG_CONF, reg); + err = regmap_update_bits(data->regmap, LM75_REG_CONF, + 0xc000, (3 - index) << 14); if (err < 0) return err; data->sample_time = data->params->sample_times[index]; break; case pct2075: - err = i2c_smbus_write_byte_data(data->client, PCT2075_REG_IDLE, - index + 1); + err = regmap_write(data->regmap, PCT2075_REG_IDLE, index + 1); if (err) return err; data->sample_time = data->params->sample_times[index]; @@ -598,6 +571,115 @@ static bool lm75_is_volatile_reg(struct device *dev, unsigned int reg) return reg == LM75_REG_TEMP || reg == LM75_REG_CONF; } +static int lm75_i2c_reg_read(void *context, unsigned int reg, unsigned int *val) +{ + struct i2c_client *client = context; + struct lm75_data *data = i2c_get_clientdata(client); + int ret; + + if (reg == LM75_REG_CONF) { + if (!data->params->config_reg_16bits) + ret = i2c_smbus_read_byte_data(client, LM75_REG_CONF); + else + ret = i2c_smbus_read_word_data(client, LM75_REG_CONF); + } else { + ret = i2c_smbus_read_word_swapped(client, reg); + } + if (ret < 0) + return ret; + *val = ret; + return 0; +} + +static int lm75_i2c_reg_write(void *context, unsigned int reg, unsigned int val) +{ + struct i2c_client *client = context; + struct lm75_data *data = i2c_get_clientdata(client); + + if (reg == PCT2075_REG_IDLE || + (reg == LM75_REG_CONF && !data->params->config_reg_16bits)) + return i2c_smbus_write_byte_data(client, reg, val); + else if (reg == LM75_REG_CONF) + return i2c_smbus_write_word_data(client, reg, val); + return i2c_smbus_write_word_swapped(client, reg, val); +} + +static const struct regmap_bus lm75_i2c_regmap_bus = { + .reg_read = lm75_i2c_reg_read, + .reg_write = lm75_i2c_reg_write, +}; + +static int lm75_i3c_reg_read(void *context, unsigned int reg, unsigned int *val) +{ + struct i3c_device *i3cdev = context; + struct lm75_data *data = i3cdev_get_drvdata(i3cdev); + struct i3c_priv_xfer xfers[] = { + { + .rnw = false, + .len = 1, + .data.out = data->reg_buf, + }, + { + .rnw = true, + .len = 2, + .data.out = data->val_buf, + }, + }; + int ret; + + data->reg_buf[0] = reg; + + if (reg == LM75_REG_CONF && !data->params->config_reg_16bits) + xfers[1].len--; + + ret = i3c_device_do_priv_xfers(i3cdev, xfers, 2); + if (ret < 0) + return ret; + + if (reg == LM75_REG_CONF && !data->params->config_reg_16bits) + *val = data->val_buf[0]; + else if (reg == LM75_REG_CONF) + *val = data->val_buf[0] | (data->val_buf[1] << 8); + else + *val = data->val_buf[1] | (data->val_buf[0] << 8); + + return 0; +} + +static int lm75_i3c_reg_write(void *context, unsigned int reg, unsigned int val) +{ + struct i3c_device *i3cdev = context; + struct lm75_data *data = i3cdev_get_drvdata(i3cdev); + struct i3c_priv_xfer xfers[] = { + { + .rnw = false, + .len = 3, + .data.out = data->val_buf, + }, + }; + + data->val_buf[0] = reg; + + if (reg == PCT2075_REG_IDLE || + (reg == LM75_REG_CONF && !data->params->config_reg_16bits)) { + xfers[0].len--; + data->val_buf[1] = val & 0xff; + } else if (reg == LM75_REG_CONF) { + data->val_buf[1] = val & 0xff; + data->val_buf[2] = (val >> 8) & 0xff; + } else { + data->val_buf[1] = (val >> 8) & 0xff; + data->val_buf[2] = val & 0xff; + } + + return i3c_device_do_priv_xfers(i3cdev, xfers, 1); +} + +static const struct regmap_bus lm75_i3c_regmap_bus = { + .reg_read = lm75_i3c_reg_read, + .reg_write = lm75_i3c_reg_write, +}; + static const struct regmap_config lm75_regmap_config = { .reg_bits = 8, .val_bits = 16, @@ -610,46 +692,33 @@ static const struct regmap_config lm75_regmap_config = { .use_single_write = true, }; -static void lm75_disable_regulator(void *data) -{ - struct lm75_data *lm75 = data; - - regulator_disable(lm75->vs); -} - static void lm75_remove(void *data) { struct lm75_data *lm75 = data; - struct i2c_client *client = lm75->client; - i2c_smbus_write_byte_data(client, LM75_REG_CONF, lm75->orig_conf); + regmap_write(lm75->regmap, LM75_REG_CONF, lm75->orig_conf); } -static int lm75_probe(struct i2c_client *client) +static int lm75_generic_probe(struct device *dev, const char *name, + enum lm75_type kind, int irq, struct regmap *regmap) { - struct device *dev = &client->dev; struct device *hwmon_dev; struct lm75_data *data; int status, err; - if (!i2c_check_functionality(client->adapter, - I2C_FUNC_SMBUS_BYTE_DATA | I2C_FUNC_SMBUS_WORD_DATA)) - return -EIO; - data = devm_kzalloc(dev, sizeof(struct lm75_data), GFP_KERNEL); if (!data) return -ENOMEM; - data->client = client; - data->kind = (uintptr_t)i2c_get_match_data(client); + /* needed by custom regmap callbacks */ + dev_set_drvdata(dev, data); - data->vs = devm_regulator_get(dev, "vs"); - if (IS_ERR(data->vs)) - return PTR_ERR(data->vs); + data->kind = kind; + data->regmap = regmap; - data->regmap = devm_regmap_init_i2c(client, &lm75_regmap_config); - if (IS_ERR(data->regmap)) - return PTR_ERR(data->regmap); + err = devm_regulator_get_enable(dev, "vs"); + if (err) + return err; /* Set to LM75 resolution (9 bits, 1/2 degree C) and range. * Then tweak to be more precise when appropriate. @@ -661,25 +730,11 @@ static int lm75_probe(struct i2c_client *client) data->sample_time = data->params->default_sample_time; data->resolution = data->params->default_resolution; - /* Enable the power */ - err = regulator_enable(data->vs); - if (err) { - dev_err(dev, "failed to enable regulator: %d\n", err); - return err; - } - - err = devm_add_action_or_reset(dev, lm75_disable_regulator, data); + /* Cache original configuration */ + err = regmap_read(data->regmap, LM75_REG_CONF, &status); if (err) return err; - - /* Cache original configuration */ - status = lm75_read_config(data); - if (status < 0) { - dev_dbg(dev, "Can't read config? %d\n", status); - return status; - } data->orig_conf = status; - data->current_conf = status; err = lm75_write_config(data, data->params->set_mask, data->params->clr_mask); @@ -690,20 +745,19 @@ static int lm75_probe(struct i2c_client *client) if (err) return err; - hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, - data, &lm75_chip_info, - NULL); + hwmon_dev = devm_hwmon_device_register_with_info(dev, name, data, + &lm75_chip_info, NULL); if (IS_ERR(hwmon_dev)) return PTR_ERR(hwmon_dev); - if (client->irq) { + if (irq) { if (data->params->alarm) { err = devm_request_threaded_irq(dev, - client->irq, + irq, NULL, &lm75_alarm_handler, IRQF_ONESHOT, - client->name, + name, hwmon_dev); if (err) return err; @@ -713,12 +767,29 @@ static int lm75_probe(struct i2c_client *client) } } - dev_info(dev, "%s: sensor '%s'\n", dev_name(hwmon_dev), client->name); + dev_info(dev, "%s: sensor '%s'\n", dev_name(hwmon_dev), name); return 0; } -static const struct i2c_device_id lm75_ids[] = { +static int lm75_i2c_probe(struct i2c_client *client) +{ + struct device *dev = &client->dev; + struct regmap *regmap; + + if (!i2c_check_functionality(client->adapter, + I2C_FUNC_SMBUS_BYTE_DATA | I2C_FUNC_SMBUS_WORD_DATA)) + return -EOPNOTSUPP; + + regmap = devm_regmap_init(dev, &lm75_i2c_regmap_bus, client, &lm75_regmap_config); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + return lm75_generic_probe(dev, client->name, (uintptr_t)i2c_get_match_data(client), + client->irq, regmap); +} + +static const struct i2c_device_id lm75_i2c_ids[] = { { "adt75", adt75, }, { "as6200", as6200, }, { "at30ts74", at30ts74, }, @@ -734,6 +805,7 @@ static const struct i2c_device_id lm75_ids[] = { { "max31725", max31725, }, { "max31726", max31725, }, { "mcp980x", mcp980x, }, + { "p3t1755", p3t1755, }, { "pct2075", pct2075, }, { "stds75", stds75, }, { "stlm75", stlm75, }, @@ -750,7 +822,38 @@ static const struct i2c_device_id lm75_ids[] = { { "tmp1075", tmp1075, }, { /* LIST END */ } }; -MODULE_DEVICE_TABLE(i2c, lm75_ids); +MODULE_DEVICE_TABLE(i2c, lm75_i2c_ids); + +struct lm75_i3c_device { + enum lm75_type type; + const char *name; +}; + +static const struct lm75_i3c_device lm75_i3c_p3t1755 = { + .name = "p3t1755", + .type = p3t1755, +}; + +static const struct i3c_device_id lm75_i3c_ids[] = { + I3C_DEVICE(0x011b, 0x152a, &lm75_i3c_p3t1755), + { /* LIST END */ } +}; +MODULE_DEVICE_TABLE(i3c, lm75_i3c_ids); + +static int lm75_i3c_probe(struct i3c_device *i3cdev) +{ + struct device *dev = i3cdev_to_dev(i3cdev); + const struct lm75_i3c_device *id_data; + struct regmap *regmap; + + regmap = devm_regmap_init(dev, &lm75_i3c_regmap_bus, i3cdev, &lm75_regmap_config); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + id_data = i3c_device_match_id(i3cdev, lm75_i3c_ids)->data; + + return lm75_generic_probe(dev, id_data->name, id_data->type, 0, regmap); +} static const struct of_device_id __maybe_unused lm75_of_match[] = { { @@ -813,6 +916,10 @@ static const struct of_device_id __maybe_unused lm75_of_match[] = { .compatible = "maxim,mcp980x", .data = (void *)mcp980x }, + { + .compatible = "nxp,p3t1755", + .data = (void *)p3t1755 + }, { .compatible = "nxp,pct2075", .data = (void *)pct2075 @@ -972,32 +1079,16 @@ static int lm75_detect(struct i2c_client *new_client, #ifdef CONFIG_PM static int lm75_suspend(struct device *dev) { - int status; - struct i2c_client *client = to_i2c_client(dev); + struct lm75_data *data = dev_get_drvdata(dev); - status = i2c_smbus_read_byte_data(client, LM75_REG_CONF); - if (status < 0) { - dev_dbg(&client->dev, "Can't read config? %d\n", status); - return status; - } - status = status | LM75_SHUTDOWN; - i2c_smbus_write_byte_data(client, LM75_REG_CONF, status); - return 0; + return regmap_update_bits(data->regmap, LM75_REG_CONF, LM75_SHUTDOWN, LM75_SHUTDOWN); } static int lm75_resume(struct device *dev) { - int status; - struct i2c_client *client = to_i2c_client(dev); + struct lm75_data *data = dev_get_drvdata(dev); - status = i2c_smbus_read_byte_data(client, LM75_REG_CONF); - if (status < 0) { - dev_dbg(&client->dev, "Can't read config? %d\n", status); - return status; - } - status = status & ~LM75_SHUTDOWN; - i2c_smbus_write_byte_data(client, LM75_REG_CONF, status); - return 0; + return regmap_update_bits(data->regmap, LM75_REG_CONF, LM75_SHUTDOWN, 0); } static const struct dev_pm_ops lm75_dev_pm_ops = { @@ -1009,20 +1100,28 @@ static const struct dev_pm_ops lm75_dev_pm_ops = { #define LM75_DEV_PM_OPS NULL #endif /* CONFIG_PM */ -static struct i2c_driver lm75_driver = { +static struct i2c_driver lm75_i2c_driver = { .class = I2C_CLASS_HWMON, .driver = { .name = "lm75", .of_match_table = of_match_ptr(lm75_of_match), .pm = LM75_DEV_PM_OPS, }, - .probe = lm75_probe, - .id_table = lm75_ids, + .probe = lm75_i2c_probe, + .id_table = lm75_i2c_ids, .detect = lm75_detect, .address_list = normal_i2c, }; -module_i2c_driver(lm75_driver); +static struct i3c_driver lm75_i3c_driver = { + .driver = { + .name = "lm75_i3c", + }, + .probe = lm75_i3c_probe, + .id_table = lm75_i3c_ids, +}; + +module_i3c_i2c_driver(lm75_i3c_driver, &lm75_i2c_driver) MODULE_AUTHOR("Frodo Looijaard "); MODULE_DESCRIPTION("LM75 driver"); diff --git a/drivers/hwmon/ltc2991.c b/drivers/hwmon/ltc2991.c index 7ca139e4b6af..6d5d4cb846da 100644 --- a/drivers/hwmon/ltc2991.c +++ b/drivers/hwmon/ltc2991.c @@ -125,7 +125,7 @@ static int ltc2991_get_curr(struct ltc2991_state *st, u32 reg, int channel, /* Vx-Vy, 19.075uV/LSB */ *val = DIV_ROUND_CLOSEST(sign_extend32(reg_val, 14) * 19075, - st->r_sense_uohm[channel]); + (s32)st->r_sense_uohm[channel]); return 0; } diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c index f71615e06a8f..416ac02e9f74 100644 --- a/drivers/hwmon/nct6683.c +++ b/drivers/hwmon/nct6683.c @@ -175,9 +175,11 @@ superio_exit(int ioreg) #define NCT6683_CUSTOMER_ID_MSI 0x201 #define NCT6683_CUSTOMER_ID_MSI2 0x200 #define NCT6683_CUSTOMER_ID_MSI3 0x207 +#define NCT6683_CUSTOMER_ID_MSI4 0x20d #define NCT6683_CUSTOMER_ID_ASROCK 0xe2c #define NCT6683_CUSTOMER_ID_ASROCK2 0xe1b #define NCT6683_CUSTOMER_ID_ASROCK3 0x1631 +#define NCT6683_CUSTOMER_ID_ASROCK4 0x163e #define NCT6683_REG_BUILD_YEAR 0x604 #define NCT6683_REG_BUILD_MONTH 0x605 @@ -1227,12 +1229,16 @@ static int nct6683_probe(struct platform_device *pdev) break; case NCT6683_CUSTOMER_ID_MSI3: break; + case NCT6683_CUSTOMER_ID_MSI4: + break; case NCT6683_CUSTOMER_ID_ASROCK: break; case NCT6683_CUSTOMER_ID_ASROCK2: break; case NCT6683_CUSTOMER_ID_ASROCK3: break; + case NCT6683_CUSTOMER_ID_ASROCK4: + break; default: if (!force) return -ENODEV; diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c index c243b51837d2..fa3351351825 100644 --- a/drivers/hwmon/nct6775-core.c +++ b/drivers/hwmon/nct6775-core.c @@ -42,6 +42,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#undef DEFAULT_SYMBOL_NAMESPACE +#define DEFAULT_SYMBOL_NAMESPACE "HWMON_NCT6775" + #include #include #include @@ -56,9 +59,6 @@ #include "lm75.h" #include "nct6775.h" -#undef DEFAULT_SYMBOL_NAMESPACE -#define DEFAULT_SYMBOL_NAMESPACE "HWMON_NCT6775" - #define USE_ALTERNATE /* used to set data->name = nct6775_device_names[data->sio_kind] */ diff --git a/drivers/hwmon/occ/p9_sbe.c b/drivers/hwmon/occ/p9_sbe.c index 89761a9c8892..1e3749dfa598 100644 --- a/drivers/hwmon/occ/p9_sbe.c +++ b/drivers/hwmon/occ/p9_sbe.c @@ -30,7 +30,7 @@ struct p9_sbe_occ { #define to_p9_sbe_occ(x) container_of((x), struct p9_sbe_occ, occ) static ssize_t ffdc_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *battr, char *buf, loff_t pos, + const struct bin_attribute *battr, char *buf, loff_t pos, size_t count) { ssize_t rc = 0; @@ -48,7 +48,7 @@ static ssize_t ffdc_read(struct file *filp, struct kobject *kobj, return rc; } -static BIN_ATTR_RO(ffdc, OCC_MAX_RESP_WORDS * 4); +static const BIN_ATTR_RO(ffdc, OCC_MAX_RESP_WORDS * 4); static bool p9_sbe_occ_save_ffdc(struct p9_sbe_occ *ctx, const void *resp, size_t resp_len) diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig index f6d352841953..419469f40ba0 100644 --- a/drivers/hwmon/pmbus/Kconfig +++ b/drivers/hwmon/pmbus/Kconfig @@ -51,7 +51,7 @@ config SENSORS_ADM1275 tristate "Analog Devices ADM1275 and compatibles" help If you say yes here you get hardware monitoring support for Analog - Devices ADM1075, ADM1272, ADM1275, ADM1276, ADM1278, ADM1281, + Devices ADM1075, ADM1272, ADM1273, ADM1275, ADM1276, ADM1278, ADM1281, ADM1293, and ADM1294 Hot-Swap Controller and Digital Power Monitors. This driver can also be built as a module. If so, the module will @@ -85,6 +85,15 @@ config SENSORS_BPA_RS600 This driver can also be built as a module. If so, the module will be called bpa-rs600. +config SENSORS_CRPS + tristate "Intel Common Redundant Power Supply" + help + If you say yes here you get hardware monitoring support for the Intel + Common Redundant Power Supply. + + This driver can also be built as a module. If so, the module will + be called crps. + config SENSORS_DELTA_AHE50DC_FAN tristate "Delta AHE-50DC fan control module" help @@ -251,7 +260,7 @@ config SENSORS_MAX15301 tristate "Maxim MAX15301" help If you say yes here you get hardware monitoring support for Maxim - MAX15301, as well as for Flex BMR461. + MAX15301, MAX15303, as well as for Flex BMR461. This driver can also be built as a module. If so, the module will be called max15301. @@ -510,6 +519,23 @@ config SENSORS_TDA38640_REGULATOR If you say yes here you get regulator support for Infineon TDA38640 as regulator. +config SENSORS_TPS25990 + tristate "TI TPS25990" + help + If you say yes here you get hardware monitoring support for TI + TPS25990. + + This driver can also be built as a module. If so, the module will + be called tps25990. + +config SENSORS_TPS25990_REGULATOR + bool "Regulator support for TPS25990 and compatibles" + depends on SENSORS_TPS25990 && REGULATOR + default SENSORS_TPS25990 + help + If you say yes here you get regulator support for Texas Instruments + TPS25990. + config SENSORS_TPS40422 tristate "TI TPS40422" help diff --git a/drivers/hwmon/pmbus/Makefile b/drivers/hwmon/pmbus/Makefile index d00bcc758b97..c7eb7739b7f8 100644 --- a/drivers/hwmon/pmbus/Makefile +++ b/drivers/hwmon/pmbus/Makefile @@ -51,6 +51,7 @@ obj-$(CONFIG_SENSORS_PXE1610) += pxe1610.o obj-$(CONFIG_SENSORS_Q54SJ108A2) += q54sj108a2.o obj-$(CONFIG_SENSORS_STPDDC60) += stpddc60.o obj-$(CONFIG_SENSORS_TDA38640) += tda38640.o +obj-$(CONFIG_SENSORS_TPS25990) += tps25990.o obj-$(CONFIG_SENSORS_TPS40422) += tps40422.o obj-$(CONFIG_SENSORS_TPS53679) += tps53679.o obj-$(CONFIG_SENSORS_TPS546D24) += tps546d24.o @@ -61,3 +62,4 @@ obj-$(CONFIG_SENSORS_XDPE122) += xdpe12284.o obj-$(CONFIG_SENSORS_XDPE152) += xdpe152c4.o obj-$(CONFIG_SENSORS_ZL6100) += zl6100.o obj-$(CONFIG_SENSORS_PIM4328) += pim4328.o +obj-$(CONFIG_SENSORS_CRPS) += crps.o diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c index 127593e10a03..7d175baa5de2 100644 --- a/drivers/hwmon/pmbus/adm1275.c +++ b/drivers/hwmon/pmbus/adm1275.c @@ -18,7 +18,7 @@ #include #include "pmbus.h" -enum chips { adm1075, adm1272, adm1275, adm1276, adm1278, adm1281, adm1293, adm1294 }; +enum chips { adm1075, adm1272, adm1273, adm1275, adm1276, adm1278, adm1281, adm1293, adm1294 }; #define ADM1275_MFR_STATUS_IOUT_WARN2 BIT(0) #define ADM1293_MFR_STATUS_VAUX_UV_WARN BIT(5) @@ -479,6 +479,7 @@ static int adm1275_read_byte_data(struct i2c_client *client, int page, int reg) static const struct i2c_device_id adm1275_id[] = { { "adm1075", adm1075 }, { "adm1272", adm1272 }, + { "adm1273", adm1273 }, { "adm1275", adm1275 }, { "adm1276", adm1276 }, { "adm1278", adm1278 }, @@ -555,9 +556,9 @@ static int adm1275_probe(struct i2c_client *client) "Device mismatch: Configured %s, detected %s\n", client->name, mid->name); - if (mid->driver_data == adm1272 || mid->driver_data == adm1278 || - mid->driver_data == adm1281 || mid->driver_data == adm1293 || - mid->driver_data == adm1294) + if (mid->driver_data == adm1272 || mid->driver_data == adm1273 || + mid->driver_data == adm1278 || mid->driver_data == adm1281 || + mid->driver_data == adm1293 || mid->driver_data == adm1294) config_read_fn = i2c_smbus_read_word_data; else config_read_fn = i2c_smbus_read_byte_data; @@ -630,6 +631,7 @@ static int adm1275_probe(struct i2c_client *client) PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT; break; case adm1272: + case adm1273: data->have_vout = true; data->have_pin_max = true; data->have_temp_max = true; diff --git a/drivers/hwmon/pmbus/crps.c b/drivers/hwmon/pmbus/crps.c new file mode 100644 index 000000000000..164b33fed312 --- /dev/null +++ b/drivers/hwmon/pmbus/crps.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2024 IBM Corp. + */ + +#include +#include +#include + +#include "pmbus.h" + +static const struct i2c_device_id crps_id[] = { + { "intel_crps185" }, + {} +}; +MODULE_DEVICE_TABLE(i2c, crps_id); + +static struct pmbus_driver_info crps_info = { + .pages = 1, + /* PSU uses default linear data format. */ + .func[0] = PMBUS_HAVE_PIN | PMBUS_HAVE_IOUT | + PMBUS_HAVE_STATUS_IOUT | PMBUS_HAVE_IIN | + PMBUS_HAVE_VIN | PMBUS_HAVE_STATUS_INPUT | + PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | + PMBUS_HAVE_TEMP | PMBUS_HAVE_TEMP2 | + PMBUS_HAVE_STATUS_TEMP | + PMBUS_HAVE_FAN12 | PMBUS_HAVE_STATUS_FAN12, +}; + +static int crps_probe(struct i2c_client *client) +{ + int rc; + struct device *dev = &client->dev; + char buf[I2C_SMBUS_BLOCK_MAX + 2] = { 0 }; + + rc = i2c_smbus_read_block_data(client, PMBUS_MFR_MODEL, buf); + if (rc < 0) + return dev_err_probe(dev, rc, "Failed to read PMBUS_MFR_MODEL\n"); + + if (rc != 7 || strncmp(buf, "03NK260", 7)) { + buf[rc] = '\0'; + return dev_err_probe(dev, -ENODEV, "Model '%s' not supported\n", buf); + } + + rc = pmbus_do_probe(client, &crps_info); + if (rc) + return dev_err_probe(dev, rc, "Failed to probe\n"); + + return 0; +} + +static const struct of_device_id crps_of_match[] = { + { + .compatible = "intel,crps185", + }, + {} +}; +MODULE_DEVICE_TABLE(of, crps_of_match); + +static struct i2c_driver crps_driver = { + .driver = { + .name = "crps", + .of_match_table = crps_of_match, + }, + .probe = crps_probe, + .id_table = crps_id, +}; + +module_i2c_driver(crps_driver); + +MODULE_AUTHOR("Ninad Palsule"); +MODULE_DESCRIPTION("PMBus driver for Intel Common Redundant power supplies"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS("PMBUS"); diff --git a/drivers/hwmon/pmbus/dps920ab.c b/drivers/hwmon/pmbus/dps920ab.c index cc5aac9dfdb3..325111a955e6 100644 --- a/drivers/hwmon/pmbus/dps920ab.c +++ b/drivers/hwmon/pmbus/dps920ab.c @@ -190,12 +190,19 @@ static const struct of_device_id __maybe_unused dps920ab_of_match[] = { MODULE_DEVICE_TABLE(of, dps920ab_of_match); +static const struct i2c_device_id dps920ab_device_id[] = { + { "dps920ab" }, + {} +}; +MODULE_DEVICE_TABLE(i2c, dps920ab_device_id); + static struct i2c_driver dps920ab_driver = { .driver = { .name = "dps920ab", .of_match_table = of_match_ptr(dps920ab_of_match), }, .probe = dps920ab_probe, + .id_table = dps920ab_device_id, }; module_i2c_driver(dps920ab_driver); diff --git a/drivers/hwmon/pmbus/max15301.c b/drivers/hwmon/pmbus/max15301.c index 50dfd477772f..d5810b88ea8d 100644 --- a/drivers/hwmon/pmbus/max15301.c +++ b/drivers/hwmon/pmbus/max15301.c @@ -25,6 +25,7 @@ static const struct i2c_device_id max15301_id[] = { { "bmr461" }, { "max15301" }, + { "max15303" }, {} }; MODULE_DEVICE_TABLE(i2c, max15301_id); diff --git a/drivers/hwmon/pmbus/pmbus.h b/drivers/hwmon/pmbus/pmbus.h index d605412a3173..ddb19c9726d6 100644 --- a/drivers/hwmon/pmbus/pmbus.h +++ b/drivers/hwmon/pmbus/pmbus.h @@ -487,6 +487,8 @@ struct pmbus_driver_info { /* Regulator ops */ extern const struct regulator_ops pmbus_regulator_ops; +int pmbus_regulator_init_cb(struct regulator_dev *rdev, + struct regulator_config *config); /* Macros for filling in array of struct regulator_desc */ #define PMBUS_REGULATOR_STEP(_name, _id, _voltages, _step, _min_uV) \ @@ -501,6 +503,7 @@ extern const struct regulator_ops pmbus_regulator_ops; .n_voltages = _voltages, \ .uV_step = _step, \ .min_uV = _min_uV, \ + .init_cb = pmbus_regulator_init_cb, \ } #define PMBUS_REGULATOR(_name, _id) PMBUS_REGULATOR_STEP(_name, _id, 0, 0, 0) @@ -516,6 +519,7 @@ extern const struct regulator_ops pmbus_regulator_ops; .n_voltages = _voltages, \ .uV_step = _step, \ .min_uV = _min_uV, \ + .init_cb = pmbus_regulator_init_cb, \ } #define PMBUS_REGULATOR_ONE(_name) PMBUS_REGULATOR_STEP_ONE(_name, 0, 0, 0) diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index a1375cb6b648..787683e83db6 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -31,6 +31,9 @@ #define PMBUS_ATTR_ALLOC_SIZE 32 #define PMBUS_NAME_SIZE 24 +static int wp = -1; +module_param(wp, int, 0444); + struct pmbus_sensor { struct pmbus_sensor *next; char name[PMBUS_NAME_SIZE]; /* sysfs sensor name */ @@ -2665,6 +2668,56 @@ static void pmbus_remove_pec(void *dev) device_remove_file(dev, &dev_attr_pec); } +static void pmbus_init_wp(struct i2c_client *client, struct pmbus_data *data) +{ + int ret; + + switch (wp) { + case 0: + _pmbus_write_byte_data(client, -1, + PMBUS_WRITE_PROTECT, 0); + break; + + case 1: + _pmbus_write_byte_data(client, -1, + PMBUS_WRITE_PROTECT, PB_WP_VOUT); + break; + + case 2: + _pmbus_write_byte_data(client, -1, + PMBUS_WRITE_PROTECT, PB_WP_OP); + break; + + case 3: + _pmbus_write_byte_data(client, -1, + PMBUS_WRITE_PROTECT, PB_WP_ALL); + break; + + default: + /* Ignore the other values */ + break; + } + + ret = _pmbus_read_byte_data(client, -1, PMBUS_WRITE_PROTECT); + if (ret < 0) + return; + + switch (ret & PB_WP_ANY) { + case PB_WP_ALL: + data->flags |= PMBUS_OP_PROTECTED; + fallthrough; + case PB_WP_OP: + data->flags |= PMBUS_VOUT_PROTECTED; + fallthrough; + case PB_WP_VOUT: + data->flags |= PMBUS_WRITE_PROTECTED | PMBUS_SKIP_STATUS_CHECK; + break; + + default: + break; + } +} + static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data, struct pmbus_driver_info *info) { @@ -2718,12 +2771,8 @@ static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data, * faults, and we should not try it. Also, in that case, writes into * limit registers need to be disabled. */ - if (!(data->flags & PMBUS_NO_WRITE_PROTECT)) { - ret = _pmbus_read_byte_data(client, -1, PMBUS_WRITE_PROTECT); - - if (ret > 0 && (ret & PB_WP_ANY)) - data->flags |= PMBUS_WRITE_PROTECTED | PMBUS_SKIP_STATUS_CHECK; - } + if (!(data->flags & PMBUS_NO_WRITE_PROTECT)) + pmbus_init_wp(client, data); ret = i2c_smbus_read_byte_data(client, PMBUS_REVISION); if (ret >= 0) @@ -3183,8 +3232,12 @@ static int pmbus_regulator_list_voltage(struct regulator_dev *rdev, { struct device *dev = rdev_get_dev(rdev); struct i2c_client *client = to_i2c_client(dev->parent); + struct pmbus_data *data = i2c_get_clientdata(client); int val, low, high; + if (data->flags & PMBUS_VOUT_PROTECTED) + return 0; + if (selector >= rdev->desc->n_voltages || selector < rdev->desc->linear_min_sel) return -EINVAL; @@ -3219,6 +3272,22 @@ const struct regulator_ops pmbus_regulator_ops = { }; EXPORT_SYMBOL_NS_GPL(pmbus_regulator_ops, "PMBUS"); +int pmbus_regulator_init_cb(struct regulator_dev *rdev, + struct regulator_config *config) +{ + struct pmbus_data *data = config->driver_data; + struct regulation_constraints *constraints = rdev->constraints; + + if (data->flags & PMBUS_OP_PROTECTED) + constraints->valid_ops_mask &= ~REGULATOR_CHANGE_STATUS; + + if (data->flags & PMBUS_VOUT_PROTECTED) + constraints->valid_ops_mask &= ~REGULATOR_CHANGE_VOLTAGE; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(pmbus_regulator_init_cb, "PMBUS"); + static int pmbus_regulator_register(struct pmbus_data *data) { struct device *dev = data->dev; @@ -3465,11 +3534,11 @@ static int pmbus_init_debugfs(struct i2c_client *client, /* * Allocate the max possible entries we need. - * 6 entries device-specific + * 7 entries device-specific * 10 entries page-specific */ entries = devm_kcalloc(data->dev, - 6 + data->info->pages * 10, sizeof(*entries), + 7 + data->info->pages * 10, sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; @@ -3482,6 +3551,15 @@ static int pmbus_init_debugfs(struct i2c_client *client, * assume that values of the following registers are the same for all * pages and report values only for page 0. */ + if (pmbus_check_byte_register(client, 0, PMBUS_REVISION)) { + entries[idx].client = client; + entries[idx].page = 0; + entries[idx].reg = PMBUS_REVISION; + debugfs_create_file("revision", 0444, data->debugfs, + &entries[idx++], + &pmbus_debugfs_ops); + } + if (pmbus_check_block_register(client, 0, PMBUS_MFR_ID)) { entries[idx].client = client; entries[idx].page = 0; diff --git a/drivers/hwmon/pmbus/tps25990.c b/drivers/hwmon/pmbus/tps25990.c new file mode 100644 index 000000000000..0d2655e69549 --- /dev/null +++ b/drivers/hwmon/pmbus/tps25990.c @@ -0,0 +1,436 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Copyright (c) 2024 BayLibre, SAS. +// Author: Jerome Brunet + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "pmbus.h" + +#define TPS25990_READ_VAUX 0xd0 +#define TPS25990_READ_VIN_MIN 0xd1 +#define TPS25990_READ_VIN_PEAK 0xd2 +#define TPS25990_READ_IIN_PEAK 0xd4 +#define TPS25990_READ_PIN_PEAK 0xd5 +#define TPS25990_READ_TEMP_AVG 0xd6 +#define TPS25990_READ_TEMP_PEAK 0xd7 +#define TPS25990_READ_VOUT_MIN 0xda +#define TPS25990_READ_VIN_AVG 0xdc +#define TPS25990_READ_VOUT_AVG 0xdd +#define TPS25990_READ_IIN_AVG 0xde +#define TPS25990_READ_PIN_AVG 0xdf +#define TPS25990_VIREF 0xe0 +#define TPS25990_PK_MIN_AVG 0xea +#define PK_MIN_AVG_RST_PEAK BIT(7) +#define PK_MIN_AVG_RST_AVG BIT(6) +#define PK_MIN_AVG_RST_MIN BIT(5) +#define PK_MIN_AVG_AVG_CNT GENMASK(2, 0) +#define TPS25990_MFR_WRITE_PROTECT 0xf8 +#define TPS25990_UNLOCKED BIT(7) + +#define TPS25990_8B_SHIFT 2 +#define TPS25990_VIN_OVF_NUM 525100 +#define TPS25990_VIN_OVF_DIV 10163 +#define TPS25990_VIN_OVF_OFF 155 +#define TPS25990_IIN_OCF_NUM 953800 +#define TPS25990_IIN_OCF_DIV 129278 +#define TPS25990_IIN_OCF_OFF 157 + +#define PK_MIN_AVG_RST_MASK (PK_MIN_AVG_RST_PEAK | \ + PK_MIN_AVG_RST_AVG | \ + PK_MIN_AVG_RST_MIN) + +/* + * Arbitrary default Rimon value: 1kOhm + * This correspond to an overcurrent limit of 55A, close to the specified limit + * of un-stacked TPS25990 and makes further calculation easier to setup in + * sensor.conf, if necessary + */ +#define TPS25990_DEFAULT_RIMON 1000000000 + +static void tps25990_set_m(int *m, u32 rimon) +{ + u64 val = ((u64)*m) * rimon; + + /* Make sure m fits the s32 type */ + *m = DIV_ROUND_CLOSEST_ULL(val, 1000000); +} + +static int tps25990_mfr_write_protect_set(struct i2c_client *client, + u8 protect) +{ + u8 val; + + switch (protect) { + case 0: + val = 0xa2; + break; + case PB_WP_ALL: + val = 0x0; + break; + default: + return -EINVAL; + } + + return pmbus_write_byte_data(client, -1, TPS25990_MFR_WRITE_PROTECT, + val); +} + +static int tps25990_mfr_write_protect_get(struct i2c_client *client) +{ + int ret = pmbus_read_byte_data(client, -1, TPS25990_MFR_WRITE_PROTECT); + + if (ret < 0) + return ret; + + return (ret & TPS25990_UNLOCKED) ? 0 : PB_WP_ALL; +} + +static int tps25990_read_word_data(struct i2c_client *client, + int page, int phase, int reg) +{ + int ret; + + switch (reg) { + case PMBUS_VIRT_READ_VIN_MAX: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_VIN_PEAK); + break; + + case PMBUS_VIRT_READ_VIN_MIN: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_VIN_MIN); + break; + + case PMBUS_VIRT_READ_VIN_AVG: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_VIN_AVG); + break; + + case PMBUS_VIRT_READ_VOUT_MIN: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_VOUT_MIN); + break; + + case PMBUS_VIRT_READ_VOUT_AVG: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_VOUT_AVG); + break; + + case PMBUS_VIRT_READ_IIN_AVG: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_IIN_AVG); + break; + + case PMBUS_VIRT_READ_IIN_MAX: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_IIN_PEAK); + break; + + case PMBUS_VIRT_READ_TEMP_AVG: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_TEMP_AVG); + break; + + case PMBUS_VIRT_READ_TEMP_MAX: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_TEMP_PEAK); + break; + + case PMBUS_VIRT_READ_PIN_AVG: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_PIN_AVG); + break; + + case PMBUS_VIRT_READ_PIN_MAX: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_PIN_PEAK); + break; + + case PMBUS_VIRT_READ_VMON: + ret = pmbus_read_word_data(client, page, phase, + TPS25990_READ_VAUX); + break; + + case PMBUS_VIN_UV_WARN_LIMIT: + case PMBUS_VIN_UV_FAULT_LIMIT: + case PMBUS_VIN_OV_WARN_LIMIT: + case PMBUS_VOUT_UV_WARN_LIMIT: + case PMBUS_IIN_OC_WARN_LIMIT: + case PMBUS_OT_WARN_LIMIT: + case PMBUS_OT_FAULT_LIMIT: + case PMBUS_PIN_OP_WARN_LIMIT: + /* + * These registers provide an 8 bits value instead of a + * 10bits one. Just shifting twice the register value is + * enough to make the sensor type conversion work, even + * if the datasheet provides different m, b and R for + * those. + */ + ret = pmbus_read_word_data(client, page, phase, reg); + if (ret < 0) + break; + ret <<= TPS25990_8B_SHIFT; + break; + + case PMBUS_VIN_OV_FAULT_LIMIT: + ret = pmbus_read_word_data(client, page, phase, reg); + if (ret < 0) + break; + ret = DIV_ROUND_CLOSEST(ret * TPS25990_VIN_OVF_NUM, + TPS25990_VIN_OVF_DIV); + ret += TPS25990_VIN_OVF_OFF; + break; + + case PMBUS_IIN_OC_FAULT_LIMIT: + /* + * VIREF directly sets the over-current limit at which the eFuse + * will turn the FET off and trigger a fault. Expose it through + * this generic property instead of a manufacturer specific one. + */ + ret = pmbus_read_byte_data(client, page, TPS25990_VIREF); + if (ret < 0) + break; + ret = DIV_ROUND_CLOSEST(ret * TPS25990_IIN_OCF_NUM, + TPS25990_IIN_OCF_DIV); + ret += TPS25990_IIN_OCF_OFF; + break; + + case PMBUS_VIRT_SAMPLES: + ret = pmbus_read_byte_data(client, page, TPS25990_PK_MIN_AVG); + if (ret < 0) + break; + ret = 1 << FIELD_GET(PK_MIN_AVG_AVG_CNT, ret); + break; + + case PMBUS_VIRT_RESET_TEMP_HISTORY: + case PMBUS_VIRT_RESET_VIN_HISTORY: + case PMBUS_VIRT_RESET_IIN_HISTORY: + case PMBUS_VIRT_RESET_PIN_HISTORY: + case PMBUS_VIRT_RESET_VOUT_HISTORY: + ret = 0; + break; + + default: + ret = -ENODATA; + break; + } + + return ret; +} + +static int tps25990_write_word_data(struct i2c_client *client, + int page, int reg, u16 value) +{ + int ret; + + switch (reg) { + case PMBUS_VIN_UV_WARN_LIMIT: + case PMBUS_VIN_UV_FAULT_LIMIT: + case PMBUS_VIN_OV_WARN_LIMIT: + case PMBUS_VOUT_UV_WARN_LIMIT: + case PMBUS_IIN_OC_WARN_LIMIT: + case PMBUS_OT_WARN_LIMIT: + case PMBUS_OT_FAULT_LIMIT: + case PMBUS_PIN_OP_WARN_LIMIT: + value >>= TPS25990_8B_SHIFT; + value = clamp_val(value, 0, 0xff); + ret = pmbus_write_word_data(client, page, reg, value); + break; + + case PMBUS_VIN_OV_FAULT_LIMIT: + value -= TPS25990_VIN_OVF_OFF; + value = DIV_ROUND_CLOSEST(((unsigned int)value) * TPS25990_VIN_OVF_DIV, + TPS25990_VIN_OVF_NUM); + value = clamp_val(value, 0, 0xf); + ret = pmbus_write_word_data(client, page, reg, value); + break; + + case PMBUS_IIN_OC_FAULT_LIMIT: + value -= TPS25990_IIN_OCF_OFF; + value = DIV_ROUND_CLOSEST(((unsigned int)value) * TPS25990_IIN_OCF_DIV, + TPS25990_IIN_OCF_NUM); + value = clamp_val(value, 0, 0x3f); + ret = pmbus_write_byte_data(client, page, TPS25990_VIREF, value); + break; + + case PMBUS_VIRT_SAMPLES: + value = clamp_val(value, 1, 1 << PK_MIN_AVG_AVG_CNT); + value = ilog2(value); + ret = pmbus_update_byte_data(client, page, TPS25990_PK_MIN_AVG, + PK_MIN_AVG_AVG_CNT, + FIELD_PREP(PK_MIN_AVG_AVG_CNT, value)); + break; + + case PMBUS_VIRT_RESET_TEMP_HISTORY: + case PMBUS_VIRT_RESET_VIN_HISTORY: + case PMBUS_VIRT_RESET_IIN_HISTORY: + case PMBUS_VIRT_RESET_PIN_HISTORY: + case PMBUS_VIRT_RESET_VOUT_HISTORY: + /* + * TPS25990 has history resets based on MIN/AVG/PEAK instead of per + * sensor type. Exposing this quirk in hwmon is not desirable so + * reset MIN, AVG and PEAK together. Even is there effectively only + * one reset, which resets everything, expose the 5 entries so + * userspace is not required map a sensor type to another to trigger + * a reset + */ + ret = pmbus_update_byte_data(client, 0, TPS25990_PK_MIN_AVG, + PK_MIN_AVG_RST_MASK, + PK_MIN_AVG_RST_MASK); + break; + + default: + ret = -ENODATA; + break; + } + + return ret; +} + +static int tps25990_read_byte_data(struct i2c_client *client, + int page, int reg) +{ + int ret; + + switch (reg) { + case PMBUS_WRITE_PROTECT: + ret = tps25990_mfr_write_protect_get(client); + break; + + default: + ret = -ENODATA; + break; + } + + return ret; +} + +static int tps25990_write_byte_data(struct i2c_client *client, + int page, int reg, u8 byte) +{ + int ret; + + switch (reg) { + case PMBUS_WRITE_PROTECT: + ret = tps25990_mfr_write_protect_set(client, byte); + break; + + default: + ret = -ENODATA; + break; + } + + return ret; +} + +#if IS_ENABLED(CONFIG_SENSORS_TPS25990_REGULATOR) +static const struct regulator_desc tps25990_reg_desc[] = { + PMBUS_REGULATOR_ONE("vout"), +}; +#endif + +static const struct pmbus_driver_info tps25990_base_info = { + .pages = 1, + .format[PSC_VOLTAGE_IN] = direct, + .m[PSC_VOLTAGE_IN] = 5251, + .b[PSC_VOLTAGE_IN] = 0, + .R[PSC_VOLTAGE_IN] = -2, + .format[PSC_VOLTAGE_OUT] = direct, + .m[PSC_VOLTAGE_OUT] = 5251, + .b[PSC_VOLTAGE_OUT] = 0, + .R[PSC_VOLTAGE_OUT] = -2, + .format[PSC_TEMPERATURE] = direct, + .m[PSC_TEMPERATURE] = 140, + .b[PSC_TEMPERATURE] = 32100, + .R[PSC_TEMPERATURE] = -2, + /* + * Current and Power measurement depends on the ohm value + * of Rimon. m is multiplied by 1000 below to have an integer + * and -3 is added to R to compensate. + */ + .format[PSC_CURRENT_IN] = direct, + .m[PSC_CURRENT_IN] = 9538, + .b[PSC_CURRENT_IN] = 0, + .R[PSC_CURRENT_IN] = -6, + .format[PSC_POWER] = direct, + .m[PSC_POWER] = 4901, + .b[PSC_POWER] = 0, + .R[PSC_POWER] = -7, + .func[0] = (PMBUS_HAVE_VIN | + PMBUS_HAVE_VOUT | + PMBUS_HAVE_VMON | + PMBUS_HAVE_IIN | + PMBUS_HAVE_PIN | + PMBUS_HAVE_TEMP | + PMBUS_HAVE_STATUS_VOUT | + PMBUS_HAVE_STATUS_IOUT | + PMBUS_HAVE_STATUS_INPUT | + PMBUS_HAVE_STATUS_TEMP | + PMBUS_HAVE_SAMPLES), + .read_word_data = tps25990_read_word_data, + .write_word_data = tps25990_write_word_data, + .read_byte_data = tps25990_read_byte_data, + .write_byte_data = tps25990_write_byte_data, + +#if IS_ENABLED(CONFIG_SENSORS_TPS25990_REGULATOR) + .reg_desc = tps25990_reg_desc, + .num_regulators = ARRAY_SIZE(tps25990_reg_desc), +#endif +}; + +static const struct i2c_device_id tps25990_i2c_id[] = { + { "tps25990" }, + {} +}; +MODULE_DEVICE_TABLE(i2c, tps25990_i2c_id); + +static const struct of_device_id tps25990_of_match[] = { + { .compatible = "ti,tps25990" }, + {} +}; +MODULE_DEVICE_TABLE(of, tps25990_of_match); + +static int tps25990_probe(struct i2c_client *client) +{ + struct device *dev = &client->dev; + struct pmbus_driver_info *info; + u32 rimon = TPS25990_DEFAULT_RIMON; + int ret; + + ret = device_property_read_u32(dev, "ti,rimon-micro-ohms", &rimon); + if (ret < 0 && ret != -EINVAL) + return dev_err_probe(dev, ret, "failed to get rimon\n"); + + info = devm_kmemdup(dev, &tps25990_base_info, sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + /* Adapt the current and power scale for each instance */ + tps25990_set_m(&info->m[PSC_CURRENT_IN], rimon); + tps25990_set_m(&info->m[PSC_POWER], rimon); + + return pmbus_do_probe(client, info); +} + +static struct i2c_driver tps25990_driver = { + .driver = { + .name = "tps25990", + .of_match_table = tps25990_of_match, + }, + .probe = tps25990_probe, + .id_table = tps25990_i2c_id, +}; +module_i2c_driver(tps25990_driver); + +MODULE_AUTHOR("Jerome Brunet "); +MODULE_DESCRIPTION("PMBUS driver for TPS25990 eFuse"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS("PMBUS"); diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c index 53a1a968d00d..579d31bb9ac7 100644 --- a/drivers/hwmon/pwm-fan.c +++ b/drivers/hwmon/pwm-fan.c @@ -497,7 +497,7 @@ static int pwm_fan_probe(struct platform_device *pdev) struct device *hwmon; int ret; const struct hwmon_channel_info **channels; - u32 pwm_min_from_stopped = 0; + u32 initial_pwm, pwm_min_from_stopped = 0; u32 *fan_channel_config; int channel_count = 1; /* We always have a PWM channel. */ int i; @@ -545,11 +545,21 @@ static int pwm_fan_probe(struct platform_device *pdev) ctx->enable_mode = pwm_disable_reg_enable; + ret = pwm_fan_get_cooling_data(dev, ctx); + if (ret) + return ret; + + /* use maximum cooling level if provided */ + if (ctx->pwm_fan_cooling_levels) + initial_pwm = ctx->pwm_fan_cooling_levels[ctx->pwm_fan_max_state]; + else + initial_pwm = MAX_PWM; + /* * Set duty cycle to maximum allowed and enable PWM output as well as * the regulator. In case of error nothing is changed */ - ret = set_pwm(ctx, MAX_PWM); + ret = set_pwm(ctx, initial_pwm); if (ret) { dev_err(dev, "Failed to configure PWM: %d\n", ret); return ret; @@ -638,16 +648,16 @@ static int pwm_fan_probe(struct platform_device *pdev) channels[1] = &ctx->fan_channel; } - ret = of_property_read_u32(dev->of_node, "fan-stop-to-start-percent", - &pwm_min_from_stopped); + ret = device_property_read_u32(dev, "fan-stop-to-start-percent", + &pwm_min_from_stopped); if (!ret && pwm_min_from_stopped) { ctx->pwm_duty_cycle_from_stopped = DIV_ROUND_UP_ULL(pwm_min_from_stopped * (ctx->pwm_state.period - 1), 100); } - ret = of_property_read_u32(dev->of_node, "fan-stop-to-start-us", - &ctx->pwm_usec_from_stopped); + ret = device_property_read_u32(dev, "fan-stop-to-start-us", + &ctx->pwm_usec_from_stopped); if (ret) ctx->pwm_usec_from_stopped = 250000; @@ -661,10 +671,6 @@ static int pwm_fan_probe(struct platform_device *pdev) return PTR_ERR(hwmon); } - ret = pwm_fan_get_cooling_data(dev, ctx); - if (ret) - return ret; - ctx->pwm_fan_state = ctx->pwm_fan_max_state; if (IS_ENABLED(CONFIG_THERMAL)) { cdev = devm_thermal_of_cooling_device_register(dev, diff --git a/drivers/hwmon/qnap-mcu-hwmon.c b/drivers/hwmon/qnap-mcu-hwmon.c new file mode 100644 index 000000000000..29057514739c --- /dev/null +++ b/drivers/hwmon/qnap-mcu-hwmon.c @@ -0,0 +1,364 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Driver for hwmon elements found on QNAP-MCU devices + * + * Copyright (C) 2024 Heiko Stuebner + */ + +#include +#include +#include +#include +#include +#include +#include + +struct qnap_mcu_hwmon { + struct qnap_mcu *mcu; + struct device *dev; + + unsigned int pwm_min; + unsigned int pwm_max; + + struct fwnode_handle *fan_node; + unsigned int fan_state; + unsigned int fan_max_state; + unsigned int *fan_cooling_levels; + + struct thermal_cooling_device *cdev; + struct hwmon_chip_info info; +}; + +static int qnap_mcu_hwmon_get_rpm(struct qnap_mcu_hwmon *hwm) +{ + static const u8 cmd[] = { '@', 'F', 'A' }; + u8 reply[6]; + int ret; + + /* poll the fan rpm */ + ret = qnap_mcu_exec(hwm->mcu, cmd, sizeof(cmd), reply, sizeof(reply)); + if (ret) + return ret; + + /* First 2 bytes must mirror the sent command */ + if (memcmp(cmd, reply, 2)) + return -EIO; + + return reply[4] * 30; +} + +static int qnap_mcu_hwmon_get_pwm(struct qnap_mcu_hwmon *hwm) +{ + static const u8 cmd[] = { '@', 'F', 'Z', '0' }; /* 0 = fan-id? */ + u8 reply[4]; + int ret; + + /* poll the fan pwm */ + ret = qnap_mcu_exec(hwm->mcu, cmd, sizeof(cmd), reply, sizeof(reply)); + if (ret) + return ret; + + /* First 3 bytes must mirror the sent command */ + if (memcmp(cmd, reply, 3)) + return -EIO; + + return reply[3]; +} + +static int qnap_mcu_hwmon_set_pwm(struct qnap_mcu_hwmon *hwm, u8 pwm) +{ + const u8 cmd[] = { '@', 'F', 'W', '0', pwm }; /* 0 = fan-id?, pwm 0-255 */ + + /* set the fan pwm */ + return qnap_mcu_exec_with_ack(hwm->mcu, cmd, sizeof(cmd)); +} + +static int qnap_mcu_hwmon_get_temp(struct qnap_mcu_hwmon *hwm) +{ + static const u8 cmd[] = { '@', 'T', '3' }; + u8 reply[4]; + int ret; + + /* poll the fan rpm */ + ret = qnap_mcu_exec(hwm->mcu, cmd, sizeof(cmd), reply, sizeof(reply)); + if (ret) + return ret; + + /* First bytes must mirror the sent command */ + if (memcmp(cmd, reply, sizeof(cmd))) + return -EIO; + + /* + * There is an unknown bit set in bit7. + * Bits [6:0] report the actual temperature as returned by the + * original qnap firmware-tools, so just drop bit7 for now. + */ + return (reply[3] & 0x7f) * 1000; +} + +static int qnap_mcu_hwmon_write(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long val) +{ + struct qnap_mcu_hwmon *hwm = dev_get_drvdata(dev); + + switch (attr) { + case hwmon_pwm_input: + if (val < 0 || val > 255) + return -EINVAL; + + if (val != 0) + val = clamp_val(val, hwm->pwm_min, hwm->pwm_max); + + return qnap_mcu_hwmon_set_pwm(hwm, val); + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int qnap_mcu_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + struct qnap_mcu_hwmon *hwm = dev_get_drvdata(dev); + int ret; + + switch (type) { + case hwmon_pwm: + switch (attr) { + case hwmon_pwm_input: + ret = qnap_mcu_hwmon_get_pwm(hwm); + if (ret < 0) + return ret; + + *val = ret; + return 0; + default: + return -EOPNOTSUPP; + } + case hwmon_fan: + ret = qnap_mcu_hwmon_get_rpm(hwm); + if (ret < 0) + return ret; + + *val = ret; + return 0; + case hwmon_temp: + ret = qnap_mcu_hwmon_get_temp(hwm); + if (ret < 0) + return ret; + + *val = ret; + return 0; + default: + return -EOPNOTSUPP; + } +} + +static umode_t qnap_mcu_hwmon_is_visible(const void *data, + enum hwmon_sensor_types type, + u32 attr, int channel) +{ + switch (type) { + case hwmon_temp: + return 0444; + + case hwmon_pwm: + return 0644; + + case hwmon_fan: + return 0444; + + default: + return 0; + } +} + +static const struct hwmon_ops qnap_mcu_hwmon_hwmon_ops = { + .is_visible = qnap_mcu_hwmon_is_visible, + .read = qnap_mcu_hwmon_read, + .write = qnap_mcu_hwmon_write, +}; + +/* thermal cooling device callbacks */ +static int qnap_mcu_hwmon_get_max_state(struct thermal_cooling_device *cdev, + unsigned long *state) +{ + struct qnap_mcu_hwmon *hwm = cdev->devdata; + + if (!hwm) + return -EINVAL; + + *state = hwm->fan_max_state; + + return 0; +} + +static int qnap_mcu_hwmon_get_cur_state(struct thermal_cooling_device *cdev, + unsigned long *state) +{ + struct qnap_mcu_hwmon *hwm = cdev->devdata; + + if (!hwm) + return -EINVAL; + + *state = hwm->fan_state; + + return 0; +} + +static int qnap_mcu_hwmon_set_cur_state(struct thermal_cooling_device *cdev, + unsigned long state) +{ + struct qnap_mcu_hwmon *hwm = cdev->devdata; + int ret; + + if (!hwm || state > hwm->fan_max_state) + return -EINVAL; + + if (state == hwm->fan_state) + return 0; + + ret = qnap_mcu_hwmon_set_pwm(hwm, hwm->fan_cooling_levels[state]); + if (ret) + return ret; + + hwm->fan_state = state; + + return ret; +} + +static const struct thermal_cooling_device_ops qnap_mcu_hwmon_cooling_ops = { + .get_max_state = qnap_mcu_hwmon_get_max_state, + .get_cur_state = qnap_mcu_hwmon_get_cur_state, + .set_cur_state = qnap_mcu_hwmon_set_cur_state, +}; + +static void devm_fan_node_release(void *data) +{ + struct qnap_mcu_hwmon *hwm = data; + + fwnode_handle_put(hwm->fan_node); +} + +static int qnap_mcu_hwmon_get_cooling_data(struct device *dev, struct qnap_mcu_hwmon *hwm) +{ + struct fwnode_handle *fwnode; + int num, i, ret; + + fwnode = device_get_named_child_node(dev->parent, "fan-0"); + if (!fwnode) + return 0; + + /* if we found the fan-node, we're keeping it until device-unbind */ + hwm->fan_node = fwnode; + ret = devm_add_action_or_reset(dev, devm_fan_node_release, hwm); + if (ret) + return ret; + + num = fwnode_property_count_u32(fwnode, "cooling-levels"); + if (num <= 0) + return dev_err_probe(dev, num ? : -EINVAL, + "Failed to count elements in 'cooling-levels'\n"); + + hwm->fan_cooling_levels = devm_kcalloc(dev, num, sizeof(u32), + GFP_KERNEL); + if (!hwm->fan_cooling_levels) + return -ENOMEM; + + ret = fwnode_property_read_u32_array(fwnode, "cooling-levels", + hwm->fan_cooling_levels, num); + if (ret) + return dev_err_probe(dev, ret, "Failed to read 'cooling-levels'\n"); + + for (i = 0; i < num; i++) { + if (hwm->fan_cooling_levels[i] > hwm->pwm_max) + return dev_err_probe(dev, -EINVAL, "fan state[%d]:%d > %d\n", i, + hwm->fan_cooling_levels[i], hwm->pwm_max); + } + + hwm->fan_max_state = num - 1; + + return 0; +} + +static const struct hwmon_channel_info * const qnap_mcu_hwmon_channels[] = { + HWMON_CHANNEL_INFO(pwm, HWMON_PWM_INPUT), + HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT), + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), + NULL +}; + +static int qnap_mcu_hwmon_probe(struct platform_device *pdev) +{ + struct qnap_mcu *mcu = dev_get_drvdata(pdev->dev.parent); + const struct qnap_mcu_variant *variant = pdev->dev.platform_data; + struct qnap_mcu_hwmon *hwm; + struct thermal_cooling_device *cdev; + struct device *dev = &pdev->dev; + struct device *hwmon; + int ret; + + hwm = devm_kzalloc(dev, sizeof(*hwm), GFP_KERNEL); + if (!hwm) + return -ENOMEM; + + hwm->mcu = mcu; + hwm->dev = &pdev->dev; + hwm->pwm_min = variant->fan_pwm_min; + hwm->pwm_max = variant->fan_pwm_max; + + platform_set_drvdata(pdev, hwm); + + /* + * Set duty cycle to maximum allowed. + */ + ret = qnap_mcu_hwmon_set_pwm(hwm, hwm->pwm_max); + if (ret) + return ret; + + hwm->info.ops = &qnap_mcu_hwmon_hwmon_ops; + hwm->info.info = qnap_mcu_hwmon_channels; + + ret = qnap_mcu_hwmon_get_cooling_data(dev, hwm); + if (ret) + return ret; + + hwm->fan_state = hwm->fan_max_state; + + hwmon = devm_hwmon_device_register_with_info(dev, "qnapmcu", + hwm, &hwm->info, NULL); + if (IS_ERR(hwmon)) + return dev_err_probe(dev, PTR_ERR(hwmon), "Failed to register hwmon device\n"); + + /* + * Only register cooling device when we found cooling-levels. + * qnap_mcu_hwmon_get_cooling_data() will fail when reading malformed + * levels and only succeed with either no or correct cooling levels. + */ + if (IS_ENABLED(CONFIG_THERMAL) && hwm->fan_cooling_levels) { + cdev = devm_thermal_of_cooling_device_register(dev, + to_of_node(hwm->fan_node), "qnap-mcu-hwmon", + hwm, &qnap_mcu_hwmon_cooling_ops); + if (IS_ERR(cdev)) + return dev_err_probe(dev, PTR_ERR(cdev), + "Failed to register qnap-mcu-hwmon as cooling device\n"); + hwm->cdev = cdev; + } + + return 0; +} + +static struct platform_driver qnap_mcu_hwmon_driver = { + .probe = qnap_mcu_hwmon_probe, + .driver = { + .name = "qnap-mcu-hwmon", + }, +}; +module_platform_driver(qnap_mcu_hwmon_driver); + +MODULE_ALIAS("platform:qnap-mcu-hwmon"); +MODULE_AUTHOR("Heiko Stuebner "); +MODULE_DESCRIPTION("QNAP MCU hwmon driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/hwmon/raspberrypi-hwmon.c b/drivers/hwmon/raspberrypi-hwmon.c index 10ef1e1f9458..a2938881ccd2 100644 --- a/drivers/hwmon/raspberrypi-hwmon.c +++ b/drivers/hwmon/raspberrypi-hwmon.c @@ -128,10 +128,32 @@ static int rpi_hwmon_probe(struct platform_device *pdev) return 0; } +static int rpi_hwmon_suspend(struct device *dev) +{ + struct rpi_hwmon_data *data = dev_get_drvdata(dev); + + cancel_delayed_work_sync(&data->get_values_poll_work); + + return 0; +} + +static int rpi_hwmon_resume(struct device *dev) +{ + struct rpi_hwmon_data *data = dev_get_drvdata(dev); + + get_values_poll(&data->get_values_poll_work.work); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(rpi_hwmon_pm_ops, rpi_hwmon_suspend, + rpi_hwmon_resume); + static struct platform_driver rpi_hwmon_driver = { .probe = rpi_hwmon_probe, .driver = { .name = "raspberrypi-hwmon", + .pm = pm_ptr(&rpi_hwmon_pm_ops), }, }; module_platform_driver(rpi_hwmon_driver); diff --git a/drivers/hwmon/spd5118.c b/drivers/hwmon/spd5118.c index 6cee48a3e5c3..358152868d96 100644 --- a/drivers/hwmon/spd5118.c +++ b/drivers/hwmon/spd5118.c @@ -291,12 +291,6 @@ static umode_t spd5118_is_visible(const void *_data, enum hwmon_sensor_types typ } } -static inline bool spd5118_parity8(u8 w) -{ - w ^= w >> 4; - return (0x6996 >> (w & 0xf)) & 1; -} - /* * Bank and vendor id are 8-bit fields with seven data bits and odd parity. * Vendor IDs 0 and 0x7f are invalid. @@ -304,7 +298,7 @@ static inline bool spd5118_parity8(u8 w) */ static bool spd5118_vendor_valid(u8 bank, u8 id) { - if (!spd5118_parity8(bank) || !spd5118_parity8(id)) + if (parity8(bank) == 0 || parity8(id) == 0) return false; id &= 0x7f; diff --git a/drivers/hwmon/tmp108.c b/drivers/hwmon/tmp108.c index fbe673009126..a971ff628435 100644 --- a/drivers/hwmon/tmp108.c +++ b/drivers/hwmon/tmp108.c @@ -8,15 +8,15 @@ #include #include #include -#include +#include #include #include -#include #include #include #include #include #include +#include #include #define DRIVER_NAME "tmp108" @@ -331,6 +331,10 @@ static int tmp108_common_probe(struct device *dev, struct regmap *regmap, char * u32 config; int err; + err = devm_regulator_get_enable(dev, "vcc"); + if (err) + return dev_err_probe(dev, err, "Failed to enable regulator\n"); + tmp108 = devm_kzalloc(dev, sizeof(*tmp108), GFP_KERNEL); if (!tmp108) return -ENOMEM; @@ -417,25 +421,24 @@ static int tmp108_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(tmp108_dev_pm_ops, tmp108_suspend, tmp108_resume); static const struct i2c_device_id tmp108_i2c_ids[] = { + { "p3t1085" }, { "tmp108" }, { } }; MODULE_DEVICE_TABLE(i2c, tmp108_i2c_ids); -#ifdef CONFIG_OF static const struct of_device_id tmp108_of_ids[] = { { .compatible = "nxp,p3t1085", }, { .compatible = "ti,tmp108", }, {} }; MODULE_DEVICE_TABLE(of, tmp108_of_ids); -#endif static struct i2c_driver tmp108_driver = { .driver = { .name = DRIVER_NAME, .pm = pm_sleep_ptr(&tmp108_dev_pm_ops), - .of_match_table = of_match_ptr(tmp108_of_ids), + .of_match_table = tmp108_of_ids, }, .probe = tmp108_probe, .id_table = tmp108_i2c_ids, diff --git a/drivers/hwmon/tmp513.c b/drivers/hwmon/tmp513.c index 926d28cd3fab..5acbfd7d088d 100644 --- a/drivers/hwmon/tmp513.c +++ b/drivers/hwmon/tmp513.c @@ -182,7 +182,7 @@ struct tmp51x_data { struct regmap *regmap; }; -// Set the shift based on the gain 8=4, 4=3, 2=2, 1=1 +// Set the shift based on the gain: 8 -> 1, 4 -> 2, 2 -> 3, 1 -> 4 static inline u8 tmp51x_get_pga_shift(struct tmp51x_data *data) { return 5 - ffs(data->pga_gain); @@ -204,8 +204,11 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos, * 2's complement number shifted by one to four depending * on the pga gain setting. 1lsb = 10uV */ - *val = sign_extend32(regval, 17 - tmp51x_get_pga_shift(data)); - *val = DIV_ROUND_CLOSEST(*val * 10 * MILLI, data->shunt_uohms); + *val = sign_extend32(regval, + reg == TMP51X_SHUNT_CURRENT_RESULT ? + 16 - tmp51x_get_pga_shift(data) : 15); + *val = DIV_ROUND_CLOSEST(*val * 10 * (long)MILLI, (long)data->shunt_uohms); + break; case TMP51X_BUS_VOLTAGE_RESULT: case TMP51X_BUS_VOLTAGE_H_LIMIT: @@ -220,8 +223,8 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos, break; case TMP51X_BUS_CURRENT_RESULT: // Current = (ShuntVoltage * CalibrationRegister) / 4096 - *val = sign_extend32(regval, 16) * data->curr_lsb_ua; - *val = DIV_ROUND_CLOSEST(*val, MILLI); + *val = sign_extend32(regval, 15) * (long)data->curr_lsb_ua; + *val = DIV_ROUND_CLOSEST(*val, (long)MILLI); break; case TMP51X_LOCAL_TEMP_RESULT: case TMP51X_REMOTE_TEMP_RESULT_1: @@ -232,7 +235,7 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos, case TMP51X_REMOTE_TEMP_LIMIT_2: case TMP513_REMOTE_TEMP_LIMIT_3: // 1lsb = 0.0625 degrees centigrade - *val = sign_extend32(regval, 16) >> TMP51X_TEMP_SHIFT; + *val = sign_extend32(regval, 15) >> TMP51X_TEMP_SHIFT; *val = DIV_ROUND_CLOSEST(*val * 625, 10); break; case TMP51X_N_FACTOR_AND_HYST_1: @@ -261,7 +264,7 @@ static int tmp51x_set_value(struct tmp51x_data *data, u8 reg, long val) * The user enter current value and we convert it to * voltage. 1lsb = 10uV */ - val = DIV_ROUND_CLOSEST(val * data->shunt_uohms, 10 * MILLI); + val = DIV_ROUND_CLOSEST(val * (long)data->shunt_uohms, 10 * (long)MILLI); max_val = U16_MAX >> tmp51x_get_pga_shift(data); regval = clamp_val(val, -max_val, max_val); break; diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index ea38ecf26fcb..0a9380350fb5 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -75,22 +75,54 @@ struct coresight_device *coresight_get_percpu_sink(int cpu) } EXPORT_SYMBOL_GPL(coresight_get_percpu_sink); +static struct coresight_device *coresight_get_source(struct list_head *path) +{ + struct coresight_device *csdev; + + if (!path) + return NULL; + + csdev = list_first_entry(path, struct coresight_node, link)->csdev; + if (!coresight_is_device_source(csdev)) + return NULL; + + return csdev; +} + +/** + * coresight_blocks_source - checks whether the connection matches the source + * of path if connection is bound to specific source. + * @src: The source device of the trace path + * @conn: The connection of one outport + * + * Return false if the connection doesn't have a source binded or source of the + * path matches the source binds to connection. + */ +static bool coresight_blocks_source(struct coresight_device *src, + struct coresight_connection *conn) +{ + return conn->filter_src_fwnode && (conn->filter_src_dev != src); +} + static struct coresight_connection * -coresight_find_out_connection(struct coresight_device *src_dev, - struct coresight_device *dest_dev) +coresight_find_out_connection(struct coresight_device *csdev, + struct coresight_device *out_dev, + struct coresight_device *trace_src) { int i; struct coresight_connection *conn; - for (i = 0; i < src_dev->pdata->nr_outconns; i++) { - conn = src_dev->pdata->out_conns[i]; - if (conn->dest_dev == dest_dev) + for (i = 0; i < csdev->pdata->nr_outconns; i++) { + conn = csdev->pdata->out_conns[i]; + if (coresight_blocks_source(trace_src, conn)) + continue; + if (conn->dest_dev == out_dev) return conn; } - dev_err(&src_dev->dev, - "couldn't find output connection, src_dev: %s, dest_dev: %s\n", - dev_name(&src_dev->dev), dev_name(&dest_dev->dev)); + dev_err(&csdev->dev, + "couldn't find output connection, csdev: %s, out_dev: %s\n", + dev_name(&csdev->dev), dev_name(&out_dev->dev)); return ERR_PTR(-ENODEV); } @@ -251,7 +283,8 @@ static void coresight_disable_sink(struct coresight_device *csdev) static int coresight_enable_link(struct coresight_device *csdev, struct coresight_device *parent, - struct coresight_device *child) + struct coresight_device *child, + struct coresight_device *source) { int link_subtype; struct coresight_connection *inconn, *outconn; @@ -259,8 +292,8 @@ static int coresight_enable_link(struct coresight_device *csdev, if (!parent || !child) return -EINVAL; - inconn = coresight_find_out_connection(parent, csdev); - outconn = coresight_find_out_connection(csdev, child); + inconn = coresight_find_out_connection(parent, csdev, source); + outconn = coresight_find_out_connection(csdev, child, source); link_subtype = csdev->subtype.link_subtype; if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG && IS_ERR(inconn)) @@ -273,15 +306,16 @@ static int coresight_enable_link(struct coresight_device *csdev, static void coresight_disable_link(struct coresight_device *csdev, struct coresight_device *parent, - struct coresight_device *child) + struct coresight_device *child, + struct coresight_device *source) { struct coresight_connection *inconn, *outconn; if (!parent || !child) return; - inconn = coresight_find_out_connection(parent, csdev); - outconn = coresight_find_out_connection(csdev, child); + inconn = coresight_find_out_connection(parent, csdev, source); + outconn = coresight_find_out_connection(csdev, child, source); link_ops(csdev)->disable(csdev, inconn, outconn); } @@ -375,7 +409,8 @@ static void coresight_disable_path_from(struct list_head *path, case CORESIGHT_DEV_TYPE_LINK: parent = list_prev_entry(nd, link)->csdev; child = list_next_entry(nd, link)->csdev; - coresight_disable_link(csdev, parent, child); + coresight_disable_link(csdev, parent, child, + coresight_get_source(path)); break; default: break; @@ -418,7 +453,9 @@ int coresight_enable_path(struct list_head *path, enum cs_mode mode, u32 type; struct coresight_node *nd; struct coresight_device *csdev, *parent, *child; + struct coresight_device *source; + source = coresight_get_source(path); list_for_each_entry_reverse(nd, path, link) { csdev = nd->csdev; type = csdev->type; @@ -456,7 +493,7 @@ int coresight_enable_path(struct list_head *path, enum cs_mode mode, case CORESIGHT_DEV_TYPE_LINK: parent = list_prev_entry(nd, link)->csdev; child = list_next_entry(nd, link)->csdev; - ret = coresight_enable_link(csdev, parent, child); + ret = coresight_enable_link(csdev, parent, child, source); if (ret) goto err; break; @@ -619,6 +656,7 @@ static void coresight_drop_device(struct coresight_device *csdev) /** * _coresight_build_path - recursively build a path from a @csdev to a sink. * @csdev: The device to start from. + * @source: The trace source device of the path. * @sink: The final sink we want in this path. * @path: The list to add devices to. * @@ -628,6 +666,7 @@ static void coresight_drop_device(struct coresight_device *csdev) * the source is the first device and the sink the last one. */ static int _coresight_build_path(struct coresight_device *csdev, + struct coresight_device *source, struct coresight_device *sink, struct list_head *path) { @@ -641,7 +680,7 @@ static int _coresight_build_path(struct coresight_device *csdev, if (coresight_is_percpu_source(csdev) && coresight_is_percpu_sink(sink) && sink == per_cpu(csdev_sink, source_ops(csdev)->cpu_id(csdev))) { - if (_coresight_build_path(sink, sink, path) == 0) { + if (_coresight_build_path(sink, source, sink, path) == 0) { found = true; goto out; } @@ -652,8 +691,12 @@ static int _coresight_build_path(struct coresight_device *csdev, struct coresight_device *child_dev; child_dev = csdev->pdata->out_conns[i]->dest_dev; + + if (coresight_blocks_source(source, csdev->pdata->out_conns[i])) + continue; + if (child_dev && - _coresight_build_path(child_dev, sink, path) == 0) { + _coresight_build_path(child_dev, source, sink, path) == 0) { found = true; break; } @@ -698,7 +741,7 @@ struct list_head *coresight_build_path(struct coresight_device *source, INIT_LIST_HEAD(path); - rc = _coresight_build_path(source, sink, path); + rc = _coresight_build_path(source, source, sink, path); if (rc) { kfree(path); return ERR_PTR(rc); @@ -927,6 +970,16 @@ static int coresight_orphan_match(struct device *dev, void *data) for (i = 0; i < src_csdev->pdata->nr_outconns; i++) { conn = src_csdev->pdata->out_conns[i]; + /* Fix filter source device before skip the port */ + if (conn->filter_src_fwnode && !conn->filter_src_dev) { + if (dst_csdev && + (conn->filter_src_fwnode == dst_csdev->dev.fwnode) && + !WARN_ON_ONCE(!coresight_is_device_source(dst_csdev))) + conn->filter_src_dev = dst_csdev; + else + still_orphan = true; + } + /* Skip the port if it's already connected. */ if (conn->dest_dev) continue; @@ -977,18 +1030,40 @@ static int coresight_fixup_orphan_conns(struct coresight_device *csdev) csdev, coresight_orphan_match); } +static int coresight_clear_filter_source(struct device *dev, void *data) +{ + int i; + struct coresight_device *source = data; + struct coresight_device *csdev = to_coresight_device(dev); + + for (i = 0; i < csdev->pdata->nr_outconns; ++i) { + if (csdev->pdata->out_conns[i]->filter_src_dev == source) + csdev->pdata->out_conns[i]->filter_src_dev = NULL; + } + return 0; +} + /* coresight_remove_conns - Remove other device's references to this device */ static void coresight_remove_conns(struct coresight_device *csdev) { int i, j; struct coresight_connection *conn; + if (coresight_is_device_source(csdev)) + bus_for_each_dev(&coresight_bustype, NULL, csdev, + coresight_clear_filter_source); + /* * Remove the input connection references from the destination device * for each output connection. */ for (i = 0; i < csdev->pdata->nr_outconns; i++) { conn = csdev->pdata->out_conns[i]; + if (conn->filter_src_fwnode) { + conn->filter_src_dev = NULL; + fwnode_handle_put(conn->filter_src_fwnode); + } + if (!conn->dest_dev) continue; diff --git a/drivers/hwtracing/coresight/coresight-dummy.c b/drivers/hwtracing/coresight/coresight-dummy.c index 02ef2b945a0c..9be53be8964b 100644 --- a/drivers/hwtracing/coresight/coresight-dummy.c +++ b/drivers/hwtracing/coresight/coresight-dummy.c @@ -11,10 +11,12 @@ #include #include "coresight-priv.h" +#include "coresight-trace-id.h" struct dummy_drvdata { struct device *dev; struct coresight_device *csdev; + u8 traceid; }; DEFINE_CORESIGHT_DEVLIST(source_devs, "dummy_source"); @@ -72,6 +74,32 @@ static const struct coresight_ops dummy_sink_cs_ops = { .sink_ops = &dummy_sink_ops, }; +/* User can get the trace id of dummy source from this node. */ +static ssize_t traceid_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct dummy_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->traceid; + return sysfs_emit(buf, "%#lx\n", val); +} +static DEVICE_ATTR_RO(traceid); + +static struct attribute *coresight_dummy_attrs[] = { + &dev_attr_traceid.attr, + NULL, +}; + +static const struct attribute_group coresight_dummy_group = { + .attrs = coresight_dummy_attrs, +}; + +static const struct attribute_group *coresight_dummy_groups[] = { + &coresight_dummy_group, + NULL, +}; + static int dummy_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -79,6 +107,11 @@ static int dummy_probe(struct platform_device *pdev) struct coresight_platform_data *pdata; struct dummy_drvdata *drvdata; struct coresight_desc desc = { 0 }; + int ret = 0, trace_id = 0; + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; if (of_device_is_compatible(node, "arm,coresight-dummy-source")) { @@ -90,6 +123,26 @@ static int dummy_probe(struct platform_device *pdev) desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS; desc.ops = &dummy_source_cs_ops; + desc.groups = coresight_dummy_groups; + + ret = coresight_get_static_trace_id(dev, &trace_id); + if (!ret) { + /* Get the static id if id is set in device tree. */ + ret = coresight_trace_id_get_static_system_id(trace_id); + if (ret < 0) { + dev_err(dev, "Fail to get static id.\n"); + return ret; + } + } else { + /* Get next available id if id is not set in device tree. */ + trace_id = coresight_trace_id_get_system_id(); + if (trace_id < 0) { + ret = trace_id; + return ret; + } + } + drvdata->traceid = (u8)trace_id; + } else if (of_device_is_compatible(node, "arm,coresight-dummy-sink")) { desc.name = coresight_alloc_device_name(&sink_devs, dev); if (!desc.name) @@ -104,27 +157,35 @@ static int dummy_probe(struct platform_device *pdev) } pdata = coresight_get_platform_data(dev); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); + if (IS_ERR(pdata)) { + ret = PTR_ERR(pdata); + goto free_id; + } pdev->dev.platform_data = pdata; - drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; - drvdata->dev = &pdev->dev; platform_set_drvdata(pdev, drvdata); desc.pdata = pdev->dev.platform_data; desc.dev = &pdev->dev; drvdata->csdev = coresight_register(&desc); - if (IS_ERR(drvdata->csdev)) - return PTR_ERR(drvdata->csdev); + if (IS_ERR(drvdata->csdev)) { + ret = PTR_ERR(drvdata->csdev); + goto free_id; + } pm_runtime_enable(dev); dev_dbg(dev, "Dummy device initialized\n"); - return 0; + ret = 0; + goto out; + +free_id: + if (IS_VALID_CS_TRACE_ID(drvdata->traceid)) + coresight_trace_id_put_system_id(drvdata->traceid); + +out: + return ret; } static void dummy_remove(struct platform_device *pdev) @@ -132,6 +193,8 @@ static void dummy_remove(struct platform_device *pdev) struct dummy_drvdata *drvdata = platform_get_drvdata(pdev); struct device *dev = &pdev->dev; + if (IS_VALID_CS_TRACE_ID(drvdata->traceid)) + coresight_trace_id_put_system_id(drvdata->traceid); pm_runtime_disable(dev); coresight_unregister(drvdata->csdev); } diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index dd8c74f893db..2c1a60577728 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -268,10 +269,28 @@ struct etm4_enable_arg { */ static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata) { + u64 trfcr; + /* If the CPU doesn't support FEAT_TRF, nothing to do */ if (!drvdata->trfcr) return; - cpu_prohibit_trace(); + + trfcr = drvdata->trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE); + + write_trfcr(trfcr); + kvm_tracing_set_el1_configuration(trfcr); +} + +static u64 etm4x_get_kern_user_filter(struct etmv4_drvdata *drvdata) +{ + u64 trfcr = drvdata->trfcr; + + if (drvdata->config.mode & ETM_MODE_EXCL_KERN) + trfcr &= ~TRFCR_EL1_ExTRE; + if (drvdata->config.mode & ETM_MODE_EXCL_USER) + trfcr &= ~TRFCR_EL1_E0TRE; + + return trfcr; } /* @@ -286,18 +305,28 @@ static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata) */ static void etm4x_allow_trace(struct etmv4_drvdata *drvdata) { - u64 trfcr = drvdata->trfcr; + u64 trfcr, guest_trfcr; /* If the CPU doesn't support FEAT_TRF, nothing to do */ - if (!trfcr) + if (!drvdata->trfcr) return; - if (drvdata->config.mode & ETM_MODE_EXCL_KERN) - trfcr &= ~TRFCR_ELx_ExTRE; - if (drvdata->config.mode & ETM_MODE_EXCL_USER) - trfcr &= ~TRFCR_ELx_E0TRE; + if (drvdata->config.mode & ETM_MODE_EXCL_HOST) + trfcr = drvdata->trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE); + else + trfcr = etm4x_get_kern_user_filter(drvdata); write_trfcr(trfcr); + + /* Set filters for guests and pass to KVM */ + if (drvdata->config.mode & ETM_MODE_EXCL_GUEST) + guest_trfcr = drvdata->trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE); + else + guest_trfcr = etm4x_get_kern_user_filter(drvdata); + + /* TRFCR_EL1 doesn't have CX so mask it out. */ + guest_trfcr &= ~TRFCR_EL2_CX; + kvm_tracing_set_el1_configuration(guest_trfcr); } #ifdef CONFIG_ETM4X_IMPDEF_FEATURE @@ -655,6 +684,12 @@ static int etm4_parse_event_config(struct coresight_device *csdev, if (attr->exclude_user) config->mode = ETM_MODE_EXCL_USER; + if (attr->exclude_host) + config->mode |= ETM_MODE_EXCL_HOST; + + if (attr->exclude_guest) + config->mode |= ETM_MODE_EXCL_GUEST; + /* Always start from the default config */ etm4_set_default_config(config); @@ -1141,9 +1176,9 @@ static void cpu_detect_trace_filtering(struct etmv4_drvdata *drvdata) * tracing at the kernel EL and EL0, forcing to use the * virtual time as the timestamp. */ - trfcr = (TRFCR_ELx_TS_VIRTUAL | - TRFCR_ELx_ExTRE | - TRFCR_ELx_E0TRE); + trfcr = (TRFCR_EL1_TS_VIRTUAL | + TRFCR_EL1_ExTRE | + TRFCR_EL1_E0TRE); /* If we are running at EL2, allow tracing the CONTEXTIDR_EL2. */ if (is_kernel_in_hyp_mode()) diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c index a9f19629f3f8..c767f8ae4cf1 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c @@ -2319,11 +2319,11 @@ static ssize_t ts_source_show(struct device *dev, goto out; } - switch (drvdata->trfcr & TRFCR_ELx_TS_MASK) { - case TRFCR_ELx_TS_VIRTUAL: - case TRFCR_ELx_TS_GUEST_PHYSICAL: - case TRFCR_ELx_TS_PHYSICAL: - val = FIELD_GET(TRFCR_ELx_TS_MASK, drvdata->trfcr); + switch (drvdata->trfcr & TRFCR_EL1_TS_MASK) { + case TRFCR_EL1_TS_VIRTUAL: + case TRFCR_EL1_TS_GUEST_PHYSICAL: + case TRFCR_EL1_TS_PHYSICAL: + val = FIELD_GET(TRFCR_EL1_TS_MASK, drvdata->trfcr); break; default: val = -1; diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 9e9165f62e81..1119762b5cec 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -817,7 +817,7 @@ enum etm_impdef_type { * @s_ex_level: Secure ELs where tracing is supported. */ struct etmv4_config { - u32 mode; + u64 mode; u32 pe_sel; u32 cfg; u32 eventctrl0; diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c index 33efe1acbef7..8faf51469bb8 100644 --- a/drivers/hwtracing/coresight/coresight-funnel.c +++ b/drivers/hwtracing/coresight/coresight-funnel.c @@ -86,14 +86,14 @@ static int funnel_enable(struct coresight_device *csdev, bool first_enable = false; spin_lock_irqsave(&drvdata->spinlock, flags); - if (atomic_read(&in->dest_refcnt) == 0) { + if (in->dest_refcnt == 0) { if (drvdata->base) rc = dynamic_funnel_enable_hw(drvdata, in->dest_port); if (!rc) first_enable = true; } if (!rc) - atomic_inc(&in->dest_refcnt); + in->dest_refcnt++; spin_unlock_irqrestore(&drvdata->spinlock, flags); if (first_enable) @@ -130,7 +130,7 @@ static void funnel_disable(struct coresight_device *csdev, bool last_disable = false; spin_lock_irqsave(&drvdata->spinlock, flags); - if (atomic_dec_return(&in->dest_refcnt) == 0) { + if (--in->dest_refcnt == 0) { if (drvdata->base) dynamic_funnel_disable_hw(drvdata, in->dest_port); last_disable = true; diff --git a/drivers/hwtracing/coresight/coresight-platform.c b/drivers/hwtracing/coresight/coresight-platform.c index 64e171eaad82..8192ba3279f0 100644 --- a/drivers/hwtracing/coresight/coresight-platform.c +++ b/drivers/hwtracing/coresight/coresight-platform.c @@ -243,6 +243,27 @@ static int of_coresight_parse_endpoint(struct device *dev, conn.dest_fwnode = fwnode_handle_get(rdev_fwnode); conn.dest_port = rendpoint.port; + /* + * Get the firmware node of the filter source through the + * reference. This could be used to filter the source in + * building path. + */ + conn.filter_src_fwnode = + fwnode_find_reference(&ep->fwnode, "filter-source", 0); + if (IS_ERR(conn.filter_src_fwnode)) { + conn.filter_src_fwnode = NULL; + } else { + conn.filter_src_dev = + coresight_find_csdev_by_fwnode(conn.filter_src_fwnode); + if (conn.filter_src_dev && + !coresight_is_device_source(conn.filter_src_dev)) { + dev_warn(dev, "port %d: Filter handle is not a trace source : %s\n", + conn.src_port, dev_name(&conn.filter_src_dev->dev)); + conn.filter_src_dev = NULL; + conn.filter_src_fwnode = NULL; + } + } + new_conn = coresight_add_out_conn(dev, pdata, &conn); if (IS_ERR_VALUE(new_conn)) { fwnode_handle_put(conn.dest_fwnode); @@ -796,6 +817,12 @@ int coresight_get_cpu(struct device *dev) } EXPORT_SYMBOL_GPL(coresight_get_cpu); +int coresight_get_static_trace_id(struct device *dev, u32 *id) +{ + return fwnode_property_read_u32(dev_fwnode(dev), "arm,static-trace-id", id); +} +EXPORT_SYMBOL_GPL(coresight_get_static_trace_id); + struct coresight_platform_data * coresight_get_platform_data(struct device *dev) { diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 05f891ca6b5c..76403530f33e 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -42,6 +42,9 @@ extern const struct device_type coresight_dev_type[]; #define ETM_MODE_EXCL_KERN BIT(30) #define ETM_MODE_EXCL_USER BIT(31) +#define ETM_MODE_EXCL_HOST BIT(32) +#define ETM_MODE_EXCL_GUEST BIT(33) + struct cs_pair_attribute { struct device_attribute attr; u32 lo_off; diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index 0fba87de6d1a..a1181c9048c0 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -126,7 +126,7 @@ static int replicator_enable(struct coresight_device *csdev, bool first_enable = false; spin_lock_irqsave(&drvdata->spinlock, flags); - if (atomic_read(&out->src_refcnt) == 0) { + if (out->src_refcnt == 0) { if (drvdata->base) rc = dynamic_replicator_enable(drvdata, in->dest_port, out->src_port); @@ -134,7 +134,7 @@ static int replicator_enable(struct coresight_device *csdev, first_enable = true; } if (!rc) - atomic_inc(&out->src_refcnt); + out->src_refcnt++; spin_unlock_irqrestore(&drvdata->spinlock, flags); if (first_enable) @@ -180,7 +180,7 @@ static void replicator_disable(struct coresight_device *csdev, bool last_disable = false; spin_lock_irqsave(&drvdata->spinlock, flags); - if (atomic_dec_return(&out->src_refcnt) == 0) { + if (--out->src_refcnt == 0) { if (drvdata->base) dynamic_replicator_disable(drvdata, in->dest_port, out->src_port); diff --git a/drivers/hwtracing/coresight/coresight-self-hosted-trace.h b/drivers/hwtracing/coresight/coresight-self-hosted-trace.h index 53840a2c41f2..303d71911870 100644 --- a/drivers/hwtracing/coresight/coresight-self-hosted-trace.h +++ b/drivers/hwtracing/coresight/coresight-self-hosted-trace.h @@ -21,13 +21,4 @@ static inline void write_trfcr(u64 val) isb(); } -static inline u64 cpu_prohibit_trace(void) -{ - u64 trfcr = read_trfcr(); - - /* Prohibit tracing at EL0 & the kernel EL */ - write_trfcr(trfcr & ~(TRFCR_ELx_ExTRE | TRFCR_ELx_E0TRE)); - /* Return the original value of the TRFCR */ - return trfcr; -} #endif /* __CORESIGHT_SELF_HOSTED_TRACE_H */ diff --git a/drivers/hwtracing/coresight/coresight-tpda.c b/drivers/hwtracing/coresight/coresight-tpda.c index bfca103f9f84..189a4abc2561 100644 --- a/drivers/hwtracing/coresight/coresight-tpda.c +++ b/drivers/hwtracing/coresight/coresight-tpda.c @@ -24,7 +24,7 @@ DEFINE_CORESIGHT_DEVLIST(tpda_devs, "tpda"); static bool coresight_device_is_tpdm(struct coresight_device *csdev) { - return (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) && + return (coresight_is_device_source(csdev)) && (csdev->subtype.source_subtype == CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM); } @@ -110,6 +110,16 @@ static int tpda_get_element_size(struct tpda_drvdata *drvdata, csdev->pdata->in_conns[i]->dest_port != inport) continue; + /* + * If this port has a hardcoded filter, use the source + * device directly. + */ + if (csdev->pdata->in_conns[i]->filter_src_fwnode) { + in = csdev->pdata->in_conns[i]->filter_src_dev; + if (!in) + continue; + } + if (coresight_device_is_tpdm(in)) { if (drvdata->dsb_esize || drvdata->cmb_esize) return -EEXIST; @@ -124,7 +134,6 @@ static int tpda_get_element_size(struct tpda_drvdata *drvdata, } } - return rc; } @@ -190,10 +199,10 @@ static int tpda_enable(struct coresight_device *csdev, int ret = 0; spin_lock(&drvdata->spinlock); - if (atomic_read(&in->dest_refcnt) == 0) { + if (in->dest_refcnt == 0) { ret = __tpda_enable(drvdata, in->dest_port); if (!ret) { - atomic_inc(&in->dest_refcnt); + in->dest_refcnt++; csdev->refcnt++; dev_dbg(drvdata->dev, "TPDA inport %d enabled.\n", in->dest_port); } @@ -223,7 +232,7 @@ static void tpda_disable(struct coresight_device *csdev, struct tpda_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); spin_lock(&drvdata->spinlock); - if (atomic_dec_return(&in->dest_refcnt) == 0) { + if (--in->dest_refcnt == 0) { __tpda_disable(drvdata, in->dest_port); csdev->refcnt--; } diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c index b7d99e91ab84..c38f9701665e 100644 --- a/drivers/hwtracing/coresight/coresight-tpdm.c +++ b/drivers/hwtracing/coresight/coresight-tpdm.c @@ -640,8 +640,7 @@ static ssize_t dsb_mode_store(struct device *dev, struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); unsigned long val; - if ((kstrtoul(buf, 0, &val)) || (val < 0) || - (val & ~TPDM_DSB_MODE_MASK)) + if ((kstrtoul(buf, 0, &val)) || (val & ~TPDM_DSB_MODE_MASK)) return -EINVAL; spin_lock(&drvdata->spinlock); @@ -1308,8 +1307,8 @@ static void tpdm_remove(struct amba_device *adev) */ static struct amba_id tpdm_ids[] = { { - .id = 0x000f0e00, - .mask = 0x000fff00, + .id = 0x001f0e00, + .mask = 0x00ffff00, }, { 0, 0, NULL }, }; diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index d98e12cb30ec..378af743be45 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -12,6 +12,12 @@ #include "coresight-trace-id.h" +enum trace_id_flags { + TRACE_ID_ANY = 0x0, + TRACE_ID_PREFER_ODD = 0x1, + TRACE_ID_REQ_STATIC = 0x2, +}; + /* Default trace ID map. Used in sysfs mode and for system sources */ static DEFINE_PER_CPU(atomic_t, id_map_default_cpu_ids) = ATOMIC_INIT(0); static struct coresight_trace_id_map id_map_default = { @@ -74,21 +80,25 @@ static int coresight_trace_id_find_odd_id(struct coresight_trace_id_map *id_map) * Otherwise allocate next available ID. */ static int coresight_trace_id_alloc_new_id(struct coresight_trace_id_map *id_map, - int preferred_id, bool prefer_odd_id) + int preferred_id, unsigned int flags) { int id = 0; /* for backwards compatibility, cpu IDs may use preferred value */ - if (IS_VALID_CS_TRACE_ID(preferred_id) && - !test_bit(preferred_id, id_map->used_ids)) { - id = preferred_id; - goto trace_id_allocated; - } else if (prefer_odd_id) { + if (IS_VALID_CS_TRACE_ID(preferred_id)) { + if (!test_bit(preferred_id, id_map->used_ids)) { + id = preferred_id; + goto trace_id_allocated; + } else if (flags & TRACE_ID_REQ_STATIC) + return -EBUSY; + } else if (flags & TRACE_ID_PREFER_ODD) { /* may use odd ids to avoid preferred legacy cpu IDs */ id = coresight_trace_id_find_odd_id(id_map); if (id) goto trace_id_allocated; - } + } else if (!IS_VALID_CS_TRACE_ID(preferred_id) && + (flags & TRACE_ID_REQ_STATIC)) + return -EINVAL; /* * skip reserved bit 0, look at bitmap length of @@ -153,7 +163,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map */ id = coresight_trace_id_alloc_new_id(id_map, CORESIGHT_LEGACY_CPU_TRACE_ID(cpu), - false); + TRACE_ID_ANY); if (!IS_VALID_CS_TRACE_ID(id)) goto get_cpu_id_out_unlock; @@ -188,14 +198,14 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma DUMP_ID_MAP(id_map); } -static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *id_map) +static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *id_map, + int preferred_id, unsigned int traceid_flags) { unsigned long flags; int id; spin_lock_irqsave(&id_map->lock, flags); - /* prefer odd IDs for system components to avoid legacy CPU IDS */ - id = coresight_trace_id_alloc_new_id(id_map, 0, true); + id = coresight_trace_id_alloc_new_id(id_map, preferred_id, traceid_flags); spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID(id); @@ -255,10 +265,19 @@ EXPORT_SYMBOL_GPL(coresight_trace_id_read_cpu_id_map); int coresight_trace_id_get_system_id(void) { - return coresight_trace_id_map_get_system_id(&id_map_default); + /* prefer odd IDs for system components to avoid legacy CPU IDS */ + return coresight_trace_id_map_get_system_id(&id_map_default, 0, + TRACE_ID_PREFER_ODD); } EXPORT_SYMBOL_GPL(coresight_trace_id_get_system_id); +int coresight_trace_id_get_static_system_id(int trace_id) +{ + return coresight_trace_id_map_get_system_id(&id_map_default, + trace_id, TRACE_ID_REQ_STATIC); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_static_system_id); + void coresight_trace_id_put_system_id(int id) { coresight_trace_id_map_put_system_id(&id_map_default, id); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h index 9aae50a553ca..db68e1ec56b6 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.h +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -116,6 +116,15 @@ int coresight_trace_id_read_cpu_id_map(int cpu, struct coresight_trace_id_map *i */ int coresight_trace_id_get_system_id(void); +/** + * Allocate a CoreSight static trace ID for a system component. + * + * Used to allocate static IDs for system trace sources such as dummy source. + * + * return: Trace ID or -EINVAL if allocation is impossible. + */ +int coresight_trace_id_get_static_system_id(int id); + /** * Release an allocated system trace ID. * diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c index 919804b12a67..fff67aac8418 100644 --- a/drivers/hwtracing/coresight/coresight-trbe.c +++ b/drivers/hwtracing/coresight/coresight-trbe.c @@ -17,6 +17,7 @@ #include #include +#include #include #include "coresight-self-hosted-trace.h" @@ -221,6 +222,7 @@ static inline void set_trbe_enabled(struct trbe_cpudata *cpudata, u64 trblimitr) */ trblimitr |= TRBLIMITR_EL1_E; write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); + kvm_enable_trbe(); /* Synchronize the TRBE enable event */ isb(); @@ -239,6 +241,7 @@ static inline void set_trbe_disabled(struct trbe_cpudata *cpudata) */ trblimitr &= ~TRBLIMITR_EL1_E; write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); + kvm_disable_trbe(); if (trbe_needs_drain_after_disable(cpudata)) trbe_drain_buffer(); @@ -253,8 +256,8 @@ static void trbe_drain_and_disable_local(struct trbe_cpudata *cpudata) static void trbe_reset_local(struct trbe_cpudata *cpudata) { - trbe_drain_and_disable_local(cpudata); write_sysreg_s(0, SYS_TRBLIMITR_EL1); + trbe_drain_buffer(); write_sysreg_s(0, SYS_TRBPTR_EL1); write_sysreg_s(0, SYS_TRBBASER_EL1); write_sysreg_s(0, SYS_TRBSR_EL1); @@ -1110,6 +1113,16 @@ static bool is_perf_trbe(struct perf_output_handle *handle) return true; } +static u64 cpu_prohibit_trace(void) +{ + u64 trfcr = read_trfcr(); + + /* Prohibit tracing at EL0 & the kernel EL */ + write_trfcr(trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE)); + /* Return the original value of the TRFCR */ + return trfcr; +} + static irqreturn_t arm_trbe_irq_handler(int irq, void *dev) { struct perf_output_handle **handle_ptr = dev; diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index d72993355473..47d9e6c3bac0 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -857,8 +857,9 @@ static irqreturn_t intel_th_irq(int irq, void *data) /** * intel_th_alloc() - allocate a new Intel TH device and its subdevices * @dev: parent device + * @drvdata: data private to the driver * @devres: resources indexed by th_mmio_idx - * @irq: irq number + * @ndevres: number of entries in the @devres resources */ struct intel_th * intel_th_alloc(struct device *dev, const struct intel_th_drvdata *drvdata, diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index ceb3ecdf884b..fc438f445771 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -503,7 +503,7 @@ config I2C_BRCMSTB tristate "BRCM Settop/DSL I2C controller" depends on ARCH_BCM2835 || ARCH_BCMBCA || ARCH_BRCMSTB || \ BMIPS_GENERIC || COMPILE_TEST - default y + default ARCH_BCM2835 || ARCH_BCMBCA || ARCH_BRCMSTB || BMIPS_GENERIC help If you say yes to this option, support will be included for the I2C interface on the Broadcom Settop/DSL SoCs. @@ -756,6 +756,7 @@ config I2C_IMX config I2C_IMX_LPI2C tristate "IMX Low Power I2C interface" depends on ARCH_MXC || COMPILE_TEST + select I2C_SLAVE help Say Y here if you want to use the Low Power IIC bus controller on the Freescale i.MX processors. @@ -910,7 +911,7 @@ config I2C_MXS config I2C_NOMADIK tristate "ST-Ericsson Nomadik/Ux500 I2C Controller" - depends on ARM_AMBA + depends on ARM_AMBA || COMPILE_TEST help If you say yes to this option, support will be included for the I2C interface from ST-Ericsson's Nomadik and Ux500 architectures, diff --git a/drivers/i2c/busses/i2c-amd756.c b/drivers/i2c/busses/i2c-amd756.c index fa0d5a2c3732..3621c02f1cba 100644 --- a/drivers/i2c/busses/i2c-amd756.c +++ b/drivers/i2c/busses/i2c-amd756.c @@ -211,7 +211,7 @@ static s32 amd756_access(struct i2c_adapter * adap, u16 addr, SMB_HOST_ADDRESS); outb_p(command, SMB_HOST_COMMAND); if (read_write == I2C_SMBUS_WRITE) - outw_p(data->word, SMB_HOST_DATA); /* TODO: endian???? */ + outw_p(data->word, SMB_HOST_DATA); size = AMD756_WORD_DATA; break; case I2C_SMBUS_BLOCK_DATA: @@ -256,7 +256,7 @@ static s32 amd756_access(struct i2c_adapter * adap, u16 addr, data->byte = inw_p(SMB_HOST_DATA); break; case AMD756_WORD_DATA: - data->word = inw_p(SMB_HOST_DATA); /* TODO: endian???? */ + data->word = inw_p(SMB_HOST_DATA); break; case AMD756_BLOCK_DATA: data->block[0] = inw_p(SMB_HOST_DATA) & 0x3f; diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index 71dc0a6688b7..6a909d339681 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -11,23 +11,23 @@ * * ---------------------------------------------------------------------------- */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include #include #include -#include -#include -#include -#include -#include -#include -#include #include -#include -#include -#include -#include -#include -#include #include +#include +#include +#include /* ----- global defines ----------------------------------------------- */ @@ -117,6 +117,8 @@ /* timeout for pm runtime autosuspend */ #define DAVINCI_I2C_PM_TIMEOUT 1000 /* ms */ +#define DAVINCI_I2C_DEFAULT_BUS_FREQ 100 + struct davinci_i2c_dev { struct device *dev; void __iomem *base; @@ -132,13 +134,10 @@ struct davinci_i2c_dev { #ifdef CONFIG_CPU_FREQ struct notifier_block freq_transition; #endif - struct davinci_i2c_platform_data *pdata; -}; - -/* default platform data to use if not supplied in the platform_device */ -static struct davinci_i2c_platform_data davinci_i2c_platform_data_default = { - .bus_freq = 100, - .bus_delay = 0, + /* standard bus frequency (kHz) */ + unsigned int bus_freq; + /* Chip has a ICPFUNC register */ + bool has_pfunc; }; static inline void davinci_i2c_write_reg(struct davinci_i2c_dev *i2c_dev, @@ -168,14 +167,12 @@ static inline void davinci_i2c_reset_ctrl(struct davinci_i2c_dev *i2c_dev, static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev) { - struct davinci_i2c_platform_data *pdata = dev->pdata; u16 psc; u32 clk; u32 d; u32 clkh; u32 clkl; u32 input_clock = clk_get_rate(dev->clk); - struct device_node *of_node = dev->dev->of_node; /* NOTE: I2C Clock divider programming info * As per I2C specs the following formulas provide prescaler @@ -209,19 +206,19 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev) psc++; /* better to run under spec than over */ d = (psc >= 2) ? 5 : 7 - psc; - if (of_node && of_device_is_compatible(of_node, "ti,keystone-i2c")) + if (device_is_compatible(dev->dev, "ti,keystone-i2c")) d = 6; - clk = ((input_clock / (psc + 1)) / (pdata->bus_freq * 1000)); + clk = ((input_clock / (psc + 1)) / (dev->bus_freq * 1000)); /* Avoid driving the bus too fast because of rounding errors above */ - if (input_clock / (psc + 1) / clk > pdata->bus_freq * 1000) + if (input_clock / (psc + 1) / clk > dev->bus_freq * 1000) clk++; /* * According to I2C-BUS Spec 2.1, in FAST-MODE LOW period should be at * least 1.3uS, which is not the case with 50% duty cycle. Driving HIGH * to LOW ratio as 1 to 2 is more safe. */ - if (pdata->bus_freq > 100) + if (dev->bus_freq > 100) clkl = (clk << 1) / 3; else clkl = (clk >> 1); @@ -255,8 +252,6 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev) */ static int i2c_davinci_init(struct davinci_i2c_dev *dev) { - struct davinci_i2c_platform_data *pdata = dev->pdata; - /* put I2C into reset */ davinci_i2c_reset_ctrl(dev, 0); @@ -274,8 +269,7 @@ static int i2c_davinci_init(struct davinci_i2c_dev *dev) davinci_i2c_read_reg(dev, DAVINCI_I2C_CLKL_REG)); dev_dbg(dev->dev, "CLKH = %d\n", davinci_i2c_read_reg(dev, DAVINCI_I2C_CLKH_REG)); - dev_dbg(dev->dev, "bus_freq = %dkHz, bus_delay = %d\n", - pdata->bus_freq, pdata->bus_delay); + dev_dbg(dev->dev, "bus_freq = %dkHz\n", dev->bus_freq); /* Take the I2C module out of reset: */ @@ -309,12 +303,6 @@ static void davinci_i2c_unprepare_recovery(struct i2c_adapter *adap) i2c_davinci_init(dev); } -static struct i2c_bus_recovery_info davinci_i2c_gpio_recovery_info = { - .recover_bus = i2c_generic_scl_recovery, - .prepare_recovery = davinci_i2c_prepare_recovery, - .unprepare_recovery = davinci_i2c_unprepare_recovery, -}; - static void davinci_i2c_set_scl(struct i2c_adapter *adap, int val) { struct davinci_i2c_dev *dev = i2c_get_adapdata(adap); @@ -414,7 +402,6 @@ static int i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop) { struct davinci_i2c_dev *dev = i2c_get_adapdata(adap); - struct davinci_i2c_platform_data *pdata = dev->pdata; u32 flag; u16 w; unsigned long time_left; @@ -424,10 +411,6 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop) return -EADDRNOTAVAIL; } - /* Introduce a delay, required for some boards (e.g Davinci EVM) */ - if (pdata->bus_delay) - udelay(pdata->bus_delay); - /* set the target address */ davinci_i2c_write_reg(dev, DAVINCI_I2C_SAR_REG, msg->addr); @@ -758,8 +741,8 @@ static int davinci_i2c_probe(struct platform_device *pdev) { struct davinci_i2c_dev *dev; struct i2c_adapter *adap; - struct i2c_bus_recovery_info *rinfo; int r, irq; + u32 prop; irq = platform_get_irq(pdev, 0); if (irq < 0) @@ -773,29 +756,15 @@ static int davinci_i2c_probe(struct platform_device *pdev) dev->dev = &pdev->dev; dev->irq = irq; - dev->pdata = dev_get_platdata(&pdev->dev); platform_set_drvdata(pdev, dev); - if (!dev->pdata && pdev->dev.of_node) { - u32 prop; + r = device_property_read_u32(&pdev->dev, "clock-frequency", &prop); + if (r) + prop = DAVINCI_I2C_DEFAULT_BUS_FREQ; - dev->pdata = devm_kzalloc(&pdev->dev, - sizeof(struct davinci_i2c_platform_data), GFP_KERNEL); - if (!dev->pdata) - return -ENOMEM; + dev->bus_freq = prop / 1000; - memcpy(dev->pdata, &davinci_i2c_platform_data_default, - sizeof(struct davinci_i2c_platform_data)); - if (!of_property_read_u32(pdev->dev.of_node, "clock-frequency", - &prop)) - dev->pdata->bus_freq = prop / 1000; - - dev->pdata->has_pfunc = - of_property_read_bool(pdev->dev.of_node, - "ti,has-pfunc"); - } else if (!dev->pdata) { - dev->pdata = &davinci_i2c_platform_data_default; - } + dev->has_pfunc = device_property_present(&pdev->dev, "ti,has-pfunc"); dev->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(dev->clk)) @@ -841,25 +810,10 @@ static int davinci_i2c_probe(struct platform_device *pdev) adap->algo = &i2c_davinci_algo; adap->dev.parent = &pdev->dev; adap->timeout = DAVINCI_I2C_TIMEOUT; - adap->dev.of_node = pdev->dev.of_node; + adap->dev.of_node = dev_of_node(&pdev->dev); - if (dev->pdata->has_pfunc) + if (dev->has_pfunc) adap->bus_recovery_info = &davinci_i2c_scl_recovery_info; - else if (dev->pdata->gpio_recovery) { - rinfo = &davinci_i2c_gpio_recovery_info; - adap->bus_recovery_info = rinfo; - rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", - GPIOD_OUT_HIGH_OPEN_DRAIN); - if (IS_ERR(rinfo->scl_gpiod)) { - r = PTR_ERR(rinfo->scl_gpiod); - goto err_unuse_clocks; - } - rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN); - if (IS_ERR(rinfo->sda_gpiod)) { - r = PTR_ERR(rinfo->sda_gpiod); - goto err_unuse_clocks; - } - } adap->nr = pdev->id; r = i2c_add_numbered_adapter(adap); diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index 183a35038eef..8eb7bd640f8d 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -8,6 +8,9 @@ * Copyright (C) 2007 MontaVista Software Inc. * Copyright (C) 2009 Provigent Ltd. */ + +#define DEFAULT_SYMBOL_NAMESPACE "I2C_DW_COMMON" + #include #include #include @@ -29,8 +32,6 @@ #include #include -#define DEFAULT_SYMBOL_NAMESPACE "I2C_DW_COMMON" - #include "i2c-designware-core.h" static const char *const abort_sources[] = { diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index c8cbe5b1aeb1..2569bf1a72e0 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -8,6 +8,9 @@ * Copyright (C) 2007 MontaVista Software Inc. * Copyright (C) 2009 Provigent Ltd. */ + +#define DEFAULT_SYMBOL_NAMESPACE "I2C_DW" + #include #include #include @@ -22,8 +25,6 @@ #include #include -#define DEFAULT_SYMBOL_NAMESPACE "I2C_DW" - #include "i2c-designware-core.h" #define AMD_TIMEOUT_MIN_US 25 diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c index dc2b788eac5b..5cd4a5f7a472 100644 --- a/drivers/i2c/busses/i2c-designware-slave.c +++ b/drivers/i2c/busses/i2c-designware-slave.c @@ -6,6 +6,9 @@ * * Copyright (C) 2016 Synopsys Inc. */ + +#define DEFAULT_SYMBOL_NAMESPACE "I2C_DW" + #include #include #include @@ -16,8 +19,6 @@ #include #include -#define DEFAULT_SYMBOL_NAMESPACE "I2C_DW" - #include "i2c-designware-core.h" static void i2c_dw_configure_fifo_slave(struct dw_i2c_dev *dev) diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c index e330015087ab..6cdd957ea7e4 100644 --- a/drivers/i2c/busses/i2c-exynos5.c +++ b/drivers/i2c/busses/i2c-exynos5.c @@ -168,6 +168,7 @@ enum i2c_type_exynos { I2C_TYPE_EXYNOS5, I2C_TYPE_EXYNOS7, I2C_TYPE_EXYNOSAUTOV9, + I2C_TYPE_EXYNOS8895, }; struct exynos5_i2c { @@ -240,6 +241,11 @@ static const struct exynos_hsi2c_variant exynosautov9_hsi2c_data = { .hw = I2C_TYPE_EXYNOSAUTOV9, }; +static const struct exynos_hsi2c_variant exynos8895_hsi2c_data = { + .fifo_depth = 64, + .hw = I2C_TYPE_EXYNOS8895, +}; + static const struct of_device_id exynos5_i2c_match[] = { { .compatible = "samsung,exynos5-hsi2c", @@ -256,6 +262,9 @@ static const struct of_device_id exynos5_i2c_match[] = { }, { .compatible = "samsung,exynosautov9-hsi2c", .data = &exynosautov9_hsi2c_data + }, { + .compatible = "samsung,exynos8895-hsi2c", + .data = &exynos8895_hsi2c_data }, {}, }; MODULE_DEVICE_TABLE(of, exynos5_i2c_match); @@ -331,6 +340,14 @@ static int exynos5_i2c_set_timing(struct exynos5_i2c *i2c, bool hs_timings) * clk_cycle := TSCLK_L + TSCLK_H * temp := (CLK_DIV + 1) * (clk_cycle + 2) * + * In case of HSI2C controllers in Exynos8895 + * FPCLK / FI2C = + * (CLK_DIV + 1) * (TSCLK_L + TSCLK_H + 2) + + * 2 * ((FLT_CYCLE + 3) - (FLT_CYCLE + 3) % (CLK_DIV + 1)) + * + * clk_cycle := TSCLK_L + TSCLK_H + * temp := (FPCLK / FI2C) - (FLT_CYCLE + 3) * 2 + * * Constraints: 4 <= temp, 0 <= CLK_DIV < 256, 2 <= clk_cycle <= 510 * * To split SCL clock into low, high periods appropriately, one @@ -352,11 +369,19 @@ static int exynos5_i2c_set_timing(struct exynos5_i2c *i2c, bool hs_timings) * */ t_ftl_cycle = (readl(i2c->regs + HSI2C_CONF) >> 16) & 0x7; - temp = clkin / op_clk - 8 - t_ftl_cycle; - if (i2c->variant->hw != I2C_TYPE_EXYNOS7) - temp -= t_ftl_cycle; + if (i2c->variant->hw == I2C_TYPE_EXYNOS8895) + temp = clkin / op_clk - (t_ftl_cycle + 3) * 2; + else if (i2c->variant->hw == I2C_TYPE_EXYNOS7) + temp = clkin / op_clk - 8 - t_ftl_cycle; + else + temp = clkin / op_clk - 8 - (t_ftl_cycle * 2); div = temp / 512; - clk_cycle = temp / (div + 1) - 2; + + if (i2c->variant->hw == I2C_TYPE_EXYNOS8895) + clk_cycle = (temp + ((t_ftl_cycle + 3) % (div + 1)) * 2) / + (div + 1) - 2; + else + clk_cycle = temp / (div + 1) - 2; if (temp < 4 || div >= 256 || clk_cycle < 2) { dev_err(i2c->dev, "%s clock set-up failed\n", hs_timings ? "HS" : "FS"); @@ -491,6 +516,8 @@ static irqreturn_t exynos5_i2c_irq(int irqno, void *dev_id) switch (i2c->variant->hw) { case I2C_TYPE_EXYNOSAUTOV9: fallthrough; + case I2C_TYPE_EXYNOS8895: + fallthrough; case I2C_TYPE_EXYNOS7: if (int_status & HSI2C_INT_TRANS_DONE) { i2c->trans_done = 1; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 75dab01d43a7..171d29d2770e 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1162,127 +1162,6 @@ static void dmi_check_onboard_devices(const struct dmi_header *dm, void *adap) } } -/* NOTE: Keep this list in sync with drivers/platform/x86/dell-smo8800.c */ -static const char *const acpi_smo8800_ids[] = { - "SMO8800", - "SMO8801", - "SMO8810", - "SMO8811", - "SMO8820", - "SMO8821", - "SMO8830", - "SMO8831", -}; - -static acpi_status check_acpi_smo88xx_device(acpi_handle obj_handle, - u32 nesting_level, - void *context, - void **return_value) -{ - struct acpi_device_info *info; - acpi_status status; - char *hid; - int i; - - status = acpi_get_object_info(obj_handle, &info); - if (ACPI_FAILURE(status)) - return AE_OK; - - if (!(info->valid & ACPI_VALID_HID)) - goto smo88xx_not_found; - - hid = info->hardware_id.string; - if (!hid) - goto smo88xx_not_found; - - i = match_string(acpi_smo8800_ids, ARRAY_SIZE(acpi_smo8800_ids), hid); - if (i < 0) - goto smo88xx_not_found; - - kfree(info); - - *return_value = NULL; - return AE_CTRL_TERMINATE; - -smo88xx_not_found: - kfree(info); - return AE_OK; -} - -static bool is_dell_system_with_lis3lv02d(void) -{ - void *err = ERR_PTR(-ENOENT); - - if (!dmi_match(DMI_SYS_VENDOR, "Dell Inc.")) - return false; - - /* - * Check that ACPI device SMO88xx is present and is functioning. - * Function acpi_get_devices() already filters all ACPI devices - * which are not present or are not functioning. - * ACPI device SMO88xx represents our ST microelectronics lis3lv02d - * accelerometer but unfortunately ACPI does not provide any other - * information (like I2C address). - */ - acpi_get_devices(NULL, check_acpi_smo88xx_device, NULL, &err); - - return !IS_ERR(err); -} - -/* - * Accelerometer's I2C address is not specified in DMI nor ACPI, - * so it is needed to define mapping table based on DMI product names. - */ -static const struct { - const char *dmi_product_name; - unsigned short i2c_addr; -} dell_lis3lv02d_devices[] = { - /* - * Dell platform team told us that these Latitude devices have - * ST microelectronics accelerometer at I2C address 0x29. - */ - { "Latitude E5250", 0x29 }, - { "Latitude E5450", 0x29 }, - { "Latitude E5550", 0x29 }, - { "Latitude E6440", 0x29 }, - { "Latitude E6440 ATG", 0x29 }, - { "Latitude E6540", 0x29 }, - /* - * Additional individual entries were added after verification. - */ - { "Latitude 5480", 0x29 }, - { "Precision 3540", 0x29 }, - { "Vostro V131", 0x1d }, - { "Vostro 5568", 0x29 }, - { "XPS 15 7590", 0x29 }, -}; - -static void register_dell_lis3lv02d_i2c_device(struct i801_priv *priv) -{ - struct i2c_board_info info; - const char *dmi_product_name; - int i; - - dmi_product_name = dmi_get_system_info(DMI_PRODUCT_NAME); - for (i = 0; i < ARRAY_SIZE(dell_lis3lv02d_devices); ++i) { - if (strcmp(dmi_product_name, - dell_lis3lv02d_devices[i].dmi_product_name) == 0) - break; - } - - if (i == ARRAY_SIZE(dell_lis3lv02d_devices)) { - dev_warn(&priv->pci_dev->dev, - "Accelerometer lis3lv02d is present on SMBus but its" - " address is unknown, skipping registration\n"); - return; - } - - memset(&info, 0, sizeof(struct i2c_board_info)); - info.addr = dell_lis3lv02d_devices[i].i2c_addr; - strscpy(info.type, "lis3lv02d", I2C_NAME_SIZE); - i2c_new_client_device(&priv->adapter, &info); -} - /* Register optional targets */ static void i801_probe_optional_targets(struct i801_priv *priv) { @@ -1302,9 +1181,6 @@ static void i801_probe_optional_targets(struct i801_priv *priv) if (dmi_name_in_vendors("FUJITSU")) dmi_walk(dmi_check_onboard_devices, &priv->adapter); - if (is_dell_system_with_lis3lv02d()) - register_dell_lis3lv02d_i2c_device(priv); - /* Instantiate SPD EEPROMs unless the SMBus is multiplexed */ #ifdef CONFIG_I2C_I801_MUX if (!priv->mux_pdev) @@ -1682,13 +1558,16 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) if (!(priv->features & FEATURE_BLOCK_BUFFER)) priv->features &= ~FEATURE_BLOCK_PROC; - err = pcim_enable_device(dev); + /* + * Do not call pcim_enable_device(), because the device has to remain + * enabled on driver detach. See i801_remove() for the reasoning. + */ + err = pci_enable_device(dev); if (err) { dev_err(&dev->dev, "Failed to enable SMBus PCI device (%d)\n", err); return err; } - pcim_pin_device(dev); /* Determine the address of the SMBus area */ priv->smba = pci_resource_start(dev, SMBBAR); diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 8adf2963d764..0d4b3935e687 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -8,6 +8,8 @@ #include #include #include +#include +#include #include #include #include @@ -29,6 +31,7 @@ #define LPI2C_MCR 0x10 /* i2c contrl register */ #define LPI2C_MSR 0x14 /* i2c status register */ #define LPI2C_MIER 0x18 /* i2c interrupt enable */ +#define LPI2C_MDER 0x1C /* i2c DMA enable */ #define LPI2C_MCFGR0 0x20 /* i2c master configuration */ #define LPI2C_MCFGR1 0x24 /* i2c master configuration */ #define LPI2C_MCFGR2 0x28 /* i2c master configuration */ @@ -40,6 +43,20 @@ #define LPI2C_MTDR 0x60 /* i2c master TX data register */ #define LPI2C_MRDR 0x70 /* i2c master RX data register */ +#define LPI2C_SCR 0x110 /* i2c target control register */ +#define LPI2C_SSR 0x114 /* i2c target status register */ +#define LPI2C_SIER 0x118 /* i2c target interrupt enable */ +#define LPI2C_SDER 0x11C /* i2c target DMA enable */ +#define LPI2C_SCFGR0 0x120 /* i2c target configuration */ +#define LPI2C_SCFGR1 0x124 /* i2c target configuration */ +#define LPI2C_SCFGR2 0x128 /* i2c target configuration */ +#define LPI2C_SAMR 0x140 /* i2c target address match */ +#define LPI2C_SASR 0x150 /* i2c target address status */ +#define LPI2C_STAR 0x154 /* i2c target transmit ACK */ +#define LPI2C_STDR 0x160 /* i2c target transmit data */ +#define LPI2C_SRDR 0x170 /* i2c target receive data */ +#define LPI2C_SRDROR 0x178 /* i2c target receive data read only */ + /* i2c command */ #define TRAN_DATA 0X00 #define RECV_DATA 0X01 @@ -70,11 +87,50 @@ #define MCFGR1_AUTOSTOP BIT(8) #define MCFGR1_IGNACK BIT(9) #define MRDR_RXEMPTY BIT(14) +#define MDER_TDDE BIT(0) +#define MDER_RDDE BIT(1) + +#define SCR_SEN BIT(0) +#define SCR_RST BIT(1) +#define SCR_FILTEN BIT(4) +#define SCR_RTF BIT(8) +#define SCR_RRF BIT(9) +#define SSR_TDF BIT(0) +#define SSR_RDF BIT(1) +#define SSR_AVF BIT(2) +#define SSR_TAF BIT(3) +#define SSR_RSF BIT(8) +#define SSR_SDF BIT(9) +#define SSR_BEF BIT(10) +#define SSR_FEF BIT(11) +#define SSR_SBF BIT(24) +#define SSR_BBF BIT(25) +#define SSR_CLEAR_BITS (SSR_RSF | SSR_SDF | SSR_BEF | SSR_FEF) +#define SIER_TDIE BIT(0) +#define SIER_RDIE BIT(1) +#define SIER_AVIE BIT(2) +#define SIER_TAIE BIT(3) +#define SIER_RSIE BIT(8) +#define SIER_SDIE BIT(9) +#define SIER_BEIE BIT(10) +#define SIER_FEIE BIT(11) +#define SIER_AM0F BIT(12) +#define SCFGR1_RXSTALL BIT(1) +#define SCFGR1_TXDSTALL BIT(2) +#define SCFGR2_FILTSDA_SHIFT 24 +#define SCFGR2_FILTSCL_SHIFT 16 +#define SCFGR2_CLKHOLD(x) (x) +#define SCFGR2_FILTSDA(x) ((x) << SCFGR2_FILTSDA_SHIFT) +#define SCFGR2_FILTSCL(x) ((x) << SCFGR2_FILTSCL_SHIFT) +#define SASR_READ_REQ 0x1 +#define SLAVE_INT_FLAG (SIER_TDIE | SIER_RDIE | SIER_AVIE | \ + SIER_SDIE | SIER_BEIE) #define I2C_CLK_RATIO 2 #define CHUNK_DATA 256 #define I2C_PM_TIMEOUT 10 /* ms */ +#define I2C_DMA_THRESHOLD 8 /* bytes */ enum lpi2c_imx_mode { STANDARD, /* 100+Kbps */ @@ -91,6 +147,24 @@ enum lpi2c_imx_pincfg { FOUR_PIN_PP, }; +struct lpi2c_imx_dma { + bool using_pio_mode; + u8 rx_cmd_buf_len; + u8 *dma_buf; + u16 *rx_cmd_buf; + unsigned int dma_len; + unsigned int tx_burst_num; + unsigned int rx_burst_num; + unsigned long dma_msg_flag; + resource_size_t phy_addr; + dma_addr_t dma_tx_addr; + dma_addr_t dma_addr; + enum dma_data_direction dma_data_dir; + enum dma_transfer_direction dma_transfer_dir; + struct dma_chan *chan_tx; + struct dma_chan *chan_rx; +}; + struct lpi2c_imx_struct { struct i2c_adapter adapter; int num_clks; @@ -108,6 +182,9 @@ struct lpi2c_imx_struct { unsigned int rxfifosize; enum lpi2c_imx_mode mode; struct i2c_bus_recovery_info rinfo; + bool can_use_dma; + struct lpi2c_imx_dma *dma; + struct i2c_client *target; }; static void lpi2c_imx_intctrl(struct lpi2c_imx_struct *lpi2c_imx, @@ -305,7 +382,7 @@ static int lpi2c_imx_master_disable(struct lpi2c_imx_struct *lpi2c_imx) return 0; } -static int lpi2c_imx_msg_complete(struct lpi2c_imx_struct *lpi2c_imx) +static int lpi2c_imx_pio_msg_complete(struct lpi2c_imx_struct *lpi2c_imx) { unsigned long time_left; @@ -451,6 +528,425 @@ static void lpi2c_imx_read(struct lpi2c_imx_struct *lpi2c_imx, lpi2c_imx_intctrl(lpi2c_imx, MIER_RDIE | MIER_NDIE); } +static bool is_use_dma(struct lpi2c_imx_struct *lpi2c_imx, struct i2c_msg *msg) +{ + if (!lpi2c_imx->can_use_dma) + return false; + + /* + * When the length of data is less than I2C_DMA_THRESHOLD, + * cpu mode is used directly to avoid low performance. + */ + return !(msg->len < I2C_DMA_THRESHOLD); +} + +static int lpi2c_imx_pio_xfer(struct lpi2c_imx_struct *lpi2c_imx, + struct i2c_msg *msg) +{ + reinit_completion(&lpi2c_imx->complete); + + if (msg->flags & I2C_M_RD) + lpi2c_imx_read(lpi2c_imx, msg); + else + lpi2c_imx_write(lpi2c_imx, msg); + + return lpi2c_imx_pio_msg_complete(lpi2c_imx); +} + +static int lpi2c_imx_dma_timeout_calculate(struct lpi2c_imx_struct *lpi2c_imx) +{ + unsigned long time = 0; + + time = 8 * lpi2c_imx->dma->dma_len * 1000 / lpi2c_imx->bitrate; + + /* Add extra second for scheduler related activities */ + time += 1; + + /* Double calculated time */ + return msecs_to_jiffies(time * MSEC_PER_SEC); +} + +static int lpi2c_imx_alloc_rx_cmd_buf(struct lpi2c_imx_struct *lpi2c_imx) +{ + struct lpi2c_imx_dma *dma = lpi2c_imx->dma; + u16 rx_remain = dma->dma_len; + int cmd_num; + u16 temp; + + /* + * Calculate the number of rx command words via the DMA TX channel + * writing into command register based on the i2c msg len, and build + * the rx command words buffer. + */ + cmd_num = DIV_ROUND_UP(rx_remain, CHUNK_DATA); + dma->rx_cmd_buf = kcalloc(cmd_num, sizeof(u16), GFP_KERNEL); + dma->rx_cmd_buf_len = cmd_num * sizeof(u16); + + if (!dma->rx_cmd_buf) { + dev_err(&lpi2c_imx->adapter.dev, "Alloc RX cmd buffer failed\n"); + return -ENOMEM; + } + + for (int i = 0; i < cmd_num ; i++) { + temp = rx_remain > CHUNK_DATA ? CHUNK_DATA - 1 : rx_remain - 1; + temp |= (RECV_DATA << 8); + rx_remain -= CHUNK_DATA; + dma->rx_cmd_buf[i] = temp; + } + + return 0; +} + +static int lpi2c_imx_dma_msg_complete(struct lpi2c_imx_struct *lpi2c_imx) +{ + unsigned long time_left, time; + + time = lpi2c_imx_dma_timeout_calculate(lpi2c_imx); + time_left = wait_for_completion_timeout(&lpi2c_imx->complete, time); + if (time_left == 0) { + dev_err(&lpi2c_imx->adapter.dev, "I/O Error in DMA Data Transfer\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static void lpi2c_dma_unmap(struct lpi2c_imx_dma *dma) +{ + struct dma_chan *chan = dma->dma_data_dir == DMA_FROM_DEVICE + ? dma->chan_rx : dma->chan_tx; + + dma_unmap_single(chan->device->dev, dma->dma_addr, + dma->dma_len, dma->dma_data_dir); + + dma->dma_data_dir = DMA_NONE; +} + +static void lpi2c_cleanup_rx_cmd_dma(struct lpi2c_imx_dma *dma) +{ + dmaengine_terminate_sync(dma->chan_tx); + dma_unmap_single(dma->chan_tx->device->dev, dma->dma_tx_addr, + dma->rx_cmd_buf_len, DMA_TO_DEVICE); +} + +static void lpi2c_cleanup_dma(struct lpi2c_imx_dma *dma) +{ + if (dma->dma_data_dir == DMA_FROM_DEVICE) + dmaengine_terminate_sync(dma->chan_rx); + else if (dma->dma_data_dir == DMA_TO_DEVICE) + dmaengine_terminate_sync(dma->chan_tx); + + lpi2c_dma_unmap(dma); +} + +static void lpi2c_dma_callback(void *data) +{ + struct lpi2c_imx_struct *lpi2c_imx = (struct lpi2c_imx_struct *)data; + + complete(&lpi2c_imx->complete); +} + +static int lpi2c_dma_rx_cmd_submit(struct lpi2c_imx_struct *lpi2c_imx) +{ + struct dma_async_tx_descriptor *rx_cmd_desc; + struct lpi2c_imx_dma *dma = lpi2c_imx->dma; + struct dma_chan *txchan = dma->chan_tx; + dma_cookie_t cookie; + + dma->dma_tx_addr = dma_map_single(txchan->device->dev, + dma->rx_cmd_buf, dma->rx_cmd_buf_len, + DMA_TO_DEVICE); + if (dma_mapping_error(txchan->device->dev, dma->dma_tx_addr)) { + dev_err(&lpi2c_imx->adapter.dev, "DMA map failed, use pio\n"); + return -EINVAL; + } + + rx_cmd_desc = dmaengine_prep_slave_single(txchan, dma->dma_tx_addr, + dma->rx_cmd_buf_len, DMA_MEM_TO_DEV, + DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + if (!rx_cmd_desc) { + dev_err(&lpi2c_imx->adapter.dev, "DMA prep slave sg failed, use pio\n"); + goto desc_prepare_err_exit; + } + + cookie = dmaengine_submit(rx_cmd_desc); + if (dma_submit_error(cookie)) { + dev_err(&lpi2c_imx->adapter.dev, "submitting DMA failed, use pio\n"); + goto submit_err_exit; + } + + dma_async_issue_pending(txchan); + + return 0; + +desc_prepare_err_exit: + dma_unmap_single(txchan->device->dev, dma->dma_tx_addr, + dma->rx_cmd_buf_len, DMA_TO_DEVICE); + return -EINVAL; + +submit_err_exit: + dma_unmap_single(txchan->device->dev, dma->dma_tx_addr, + dma->rx_cmd_buf_len, DMA_TO_DEVICE); + dmaengine_desc_free(rx_cmd_desc); + return -EINVAL; +} + +static int lpi2c_dma_submit(struct lpi2c_imx_struct *lpi2c_imx) +{ + struct lpi2c_imx_dma *dma = lpi2c_imx->dma; + struct dma_async_tx_descriptor *desc; + struct dma_chan *chan; + dma_cookie_t cookie; + + if (dma->dma_msg_flag & I2C_M_RD) { + chan = dma->chan_rx; + dma->dma_data_dir = DMA_FROM_DEVICE; + dma->dma_transfer_dir = DMA_DEV_TO_MEM; + } else { + chan = dma->chan_tx; + dma->dma_data_dir = DMA_TO_DEVICE; + dma->dma_transfer_dir = DMA_MEM_TO_DEV; + } + + dma->dma_addr = dma_map_single(chan->device->dev, + dma->dma_buf, dma->dma_len, dma->dma_data_dir); + if (dma_mapping_error(chan->device->dev, dma->dma_addr)) { + dev_err(&lpi2c_imx->adapter.dev, "DMA map failed, use pio\n"); + return -EINVAL; + } + + desc = dmaengine_prep_slave_single(chan, dma->dma_addr, + dma->dma_len, dma->dma_transfer_dir, + DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + if (!desc) { + dev_err(&lpi2c_imx->adapter.dev, "DMA prep slave sg failed, use pio\n"); + goto desc_prepare_err_exit; + } + + reinit_completion(&lpi2c_imx->complete); + desc->callback = lpi2c_dma_callback; + desc->callback_param = lpi2c_imx; + + cookie = dmaengine_submit(desc); + if (dma_submit_error(cookie)) { + dev_err(&lpi2c_imx->adapter.dev, "submitting DMA failed, use pio\n"); + goto submit_err_exit; + } + + /* Can't switch to PIO mode when DMA have started transfer */ + dma->using_pio_mode = false; + + dma_async_issue_pending(chan); + + return 0; + +desc_prepare_err_exit: + lpi2c_dma_unmap(dma); + return -EINVAL; + +submit_err_exit: + lpi2c_dma_unmap(dma); + dmaengine_desc_free(desc); + return -EINVAL; +} + +static int lpi2c_imx_find_max_burst_num(unsigned int fifosize, unsigned int len) +{ + unsigned int i; + + for (i = fifosize / 2; i > 0; i--) + if (!(len % i)) + break; + + return i; +} + +/* + * For a highest DMA efficiency, tx/rx burst number should be calculated according + * to the FIFO depth. + */ +static void lpi2c_imx_dma_burst_num_calculate(struct lpi2c_imx_struct *lpi2c_imx) +{ + struct lpi2c_imx_dma *dma = lpi2c_imx->dma; + unsigned int cmd_num; + + if (dma->dma_msg_flag & I2C_M_RD) { + /* + * One RX cmd word can trigger DMA receive no more than 256 bytes. + * The number of RX cmd words should be calculated based on the data + * length. + */ + cmd_num = DIV_ROUND_UP(dma->dma_len, CHUNK_DATA); + dma->tx_burst_num = lpi2c_imx_find_max_burst_num(lpi2c_imx->txfifosize, + cmd_num); + dma->rx_burst_num = lpi2c_imx_find_max_burst_num(lpi2c_imx->rxfifosize, + dma->dma_len); + } else { + dma->tx_burst_num = lpi2c_imx_find_max_burst_num(lpi2c_imx->txfifosize, + dma->dma_len); + } +} + +static int lpi2c_dma_config(struct lpi2c_imx_struct *lpi2c_imx) +{ + struct lpi2c_imx_dma *dma = lpi2c_imx->dma; + struct dma_slave_config rx = {}, tx = {}; + int ret; + + lpi2c_imx_dma_burst_num_calculate(lpi2c_imx); + + if (dma->dma_msg_flag & I2C_M_RD) { + tx.dst_addr = dma->phy_addr + LPI2C_MTDR; + tx.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; + tx.dst_maxburst = dma->tx_burst_num; + tx.direction = DMA_MEM_TO_DEV; + ret = dmaengine_slave_config(dma->chan_tx, &tx); + if (ret < 0) + return ret; + + rx.src_addr = dma->phy_addr + LPI2C_MRDR; + rx.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; + rx.src_maxburst = dma->rx_burst_num; + rx.direction = DMA_DEV_TO_MEM; + ret = dmaengine_slave_config(dma->chan_rx, &rx); + if (ret < 0) + return ret; + } else { + tx.dst_addr = dma->phy_addr + LPI2C_MTDR; + tx.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; + tx.dst_maxburst = dma->tx_burst_num; + tx.direction = DMA_MEM_TO_DEV; + ret = dmaengine_slave_config(dma->chan_tx, &tx); + if (ret < 0) + return ret; + } + + return 0; +} + +static void lpi2c_dma_enable(struct lpi2c_imx_struct *lpi2c_imx) +{ + struct lpi2c_imx_dma *dma = lpi2c_imx->dma; + /* + * TX interrupt will be triggered when the number of words in + * the transmit FIFO is equal or less than TX watermark. + * RX interrupt will be triggered when the number of words in + * the receive FIFO is greater than RX watermark. + * In order to trigger the DMA interrupt, TX watermark should be + * set equal to the DMA TX burst number but RX watermark should + * be set less than the DMA RX burst number. + */ + if (dma->dma_msg_flag & I2C_M_RD) { + /* Set I2C TX/RX watermark */ + writel(dma->tx_burst_num | (dma->rx_burst_num - 1) << 16, + lpi2c_imx->base + LPI2C_MFCR); + /* Enable I2C DMA TX/RX function */ + writel(MDER_TDDE | MDER_RDDE, lpi2c_imx->base + LPI2C_MDER); + } else { + /* Set I2C TX watermark */ + writel(dma->tx_burst_num, lpi2c_imx->base + LPI2C_MFCR); + /* Enable I2C DMA TX function */ + writel(MDER_TDDE, lpi2c_imx->base + LPI2C_MDER); + } + + /* Enable NACK detected */ + lpi2c_imx_intctrl(lpi2c_imx, MIER_NDIE); +}; + +/* + * When lpi2c is in TX DMA mode we can use one DMA TX channel to write + * data word into TXFIFO, but in RX DMA mode it is different. + * + * The LPI2C MTDR register is a command data and transmit data register. + * Bits 8-10 are the command data field and Bits 0-7 are the transmit + * data field. When the LPI2C master needs to read data, the number of + * bytes to read should be set in the command field and RECV_DATA should + * be set into the command data field to receive (DATA[7:0] + 1) bytes. + * The recv data command word is made of RECV_DATA in the command data + * field and the number of bytes to read in transmit data field. When the + * length of data to be read exceeds 256 bytes, recv data command word + * needs to be written to TXFIFO multiple times. + * + * So when in RX DMA mode, the TX channel also must to be configured to + * send RX command words and the RX command word must be set in advance + * before transmitting. + */ +static int lpi2c_imx_dma_xfer(struct lpi2c_imx_struct *lpi2c_imx, + struct i2c_msg *msg) +{ + struct lpi2c_imx_dma *dma = lpi2c_imx->dma; + int ret; + + /* When DMA mode fails before transferring, CPU mode can be used. */ + dma->using_pio_mode = true; + + dma->dma_len = msg->len; + dma->dma_msg_flag = msg->flags; + dma->dma_buf = i2c_get_dma_safe_msg_buf(msg, I2C_DMA_THRESHOLD); + if (!dma->dma_buf) + return -ENOMEM; + + ret = lpi2c_dma_config(lpi2c_imx); + if (ret) { + dev_err(&lpi2c_imx->adapter.dev, "Failed to configure DMA (%d)\n", ret); + goto disable_dma; + } + + lpi2c_dma_enable(lpi2c_imx); + + ret = lpi2c_dma_submit(lpi2c_imx); + if (ret) { + dev_err(&lpi2c_imx->adapter.dev, "DMA submission failed (%d)\n", ret); + goto disable_dma; + } + + if (dma->dma_msg_flag & I2C_M_RD) { + ret = lpi2c_imx_alloc_rx_cmd_buf(lpi2c_imx); + if (ret) + goto disable_cleanup_data_dma; + + ret = lpi2c_dma_rx_cmd_submit(lpi2c_imx); + if (ret) + goto disable_cleanup_data_dma; + } + + ret = lpi2c_imx_dma_msg_complete(lpi2c_imx); + if (ret) + goto disable_cleanup_all_dma; + + /* When encountering NACK in transfer, clean up all DMA transfers */ + if ((readl(lpi2c_imx->base + LPI2C_MSR) & MSR_NDF) && !ret) { + ret = -EIO; + goto disable_cleanup_all_dma; + } + + if (dma->dma_msg_flag & I2C_M_RD) + dma_unmap_single(dma->chan_tx->device->dev, dma->dma_tx_addr, + dma->rx_cmd_buf_len, DMA_TO_DEVICE); + lpi2c_dma_unmap(dma); + + goto disable_dma; + +disable_cleanup_all_dma: + if (dma->dma_msg_flag & I2C_M_RD) + lpi2c_cleanup_rx_cmd_dma(dma); +disable_cleanup_data_dma: + lpi2c_cleanup_dma(dma); +disable_dma: + /* Disable I2C DMA function */ + writel(0, lpi2c_imx->base + LPI2C_MDER); + + if (dma->dma_msg_flag & I2C_M_RD) + kfree(dma->rx_cmd_buf); + + if (ret) + i2c_put_dma_safe_msg_buf(dma->dma_buf, msg, false); + else + i2c_put_dma_safe_msg_buf(dma->dma_buf, msg, true); + + return ret; +} + static int lpi2c_imx_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num) { @@ -477,12 +973,14 @@ static int lpi2c_imx_xfer(struct i2c_adapter *adapter, lpi2c_imx->msglen = msgs[i].len; init_completion(&lpi2c_imx->complete); - if (msgs[i].flags & I2C_M_RD) - lpi2c_imx_read(lpi2c_imx, &msgs[i]); - else - lpi2c_imx_write(lpi2c_imx, &msgs[i]); + if (is_use_dma(lpi2c_imx, &msgs[i])) { + result = lpi2c_imx_dma_xfer(lpi2c_imx, &msgs[i]); + if (result && lpi2c_imx->dma->using_pio_mode) + result = lpi2c_imx_pio_xfer(lpi2c_imx, &msgs[i]); + } else { + result = lpi2c_imx_pio_xfer(lpi2c_imx, &msgs[i]); + } - result = lpi2c_imx_msg_complete(lpi2c_imx); if (result) goto stop; @@ -510,9 +1008,56 @@ disable: return (result < 0) ? result : num; } -static irqreturn_t lpi2c_imx_isr(int irq, void *dev_id) +static irqreturn_t lpi2c_imx_target_isr(struct lpi2c_imx_struct *lpi2c_imx, + u32 ssr, u32 sier_filter) +{ + u8 value; + u32 sasr; + + /* Arbitration lost */ + if (sier_filter & SSR_BEF) { + writel(0, lpi2c_imx->base + LPI2C_SIER); + return IRQ_HANDLED; + } + + /* Address detected */ + if (sier_filter & SSR_AVF) { + sasr = readl(lpi2c_imx->base + LPI2C_SASR); + if (SASR_READ_REQ & sasr) { + /* Read request */ + i2c_slave_event(lpi2c_imx->target, I2C_SLAVE_READ_REQUESTED, &value); + writel(value, lpi2c_imx->base + LPI2C_STDR); + goto ret; + } else { + /* Write request */ + i2c_slave_event(lpi2c_imx->target, I2C_SLAVE_WRITE_REQUESTED, &value); + } + } + + if (sier_filter & SSR_SDF) + /* STOP */ + i2c_slave_event(lpi2c_imx->target, I2C_SLAVE_STOP, &value); + + if (sier_filter & SSR_TDF) { + /* Target send data */ + i2c_slave_event(lpi2c_imx->target, I2C_SLAVE_READ_PROCESSED, &value); + writel(value, lpi2c_imx->base + LPI2C_STDR); + } + + if (sier_filter & SSR_RDF) { + /* Target receive data */ + value = readl(lpi2c_imx->base + LPI2C_SRDR); + i2c_slave_event(lpi2c_imx->target, I2C_SLAVE_WRITE_RECEIVED, &value); + } + +ret: + /* Clear SSR */ + writel(ssr & SSR_CLEAR_BITS, lpi2c_imx->base + LPI2C_SSR); + return IRQ_HANDLED; +} + +static irqreturn_t lpi2c_imx_master_isr(struct lpi2c_imx_struct *lpi2c_imx) { - struct lpi2c_imx_struct *lpi2c_imx = dev_id; unsigned int enabled; unsigned int temp; @@ -532,6 +1077,124 @@ static irqreturn_t lpi2c_imx_isr(int irq, void *dev_id) return IRQ_HANDLED; } +static irqreturn_t lpi2c_imx_isr(int irq, void *dev_id) +{ + struct lpi2c_imx_struct *lpi2c_imx = dev_id; + + if (lpi2c_imx->target) { + u32 scr = readl(lpi2c_imx->base + LPI2C_SCR); + u32 ssr = readl(lpi2c_imx->base + LPI2C_SSR); + u32 sier_filter = ssr & readl(lpi2c_imx->base + LPI2C_SIER); + + /* + * The target is enabled and an interrupt has been triggered. + * Enter the target's irq handler. + */ + if ((scr & SCR_SEN) && sier_filter) + return lpi2c_imx_target_isr(lpi2c_imx, ssr, sier_filter); + } + + /* + * Otherwise the interrupt has been triggered by the master. + * Enter the master's irq handler. + */ + return lpi2c_imx_master_isr(lpi2c_imx); +} + +static void lpi2c_imx_target_init(struct lpi2c_imx_struct *lpi2c_imx) +{ + u32 temp; + + /* reset target module */ + writel(SCR_RST, lpi2c_imx->base + LPI2C_SCR); + writel(0, lpi2c_imx->base + LPI2C_SCR); + + /* Set target address */ + writel((lpi2c_imx->target->addr << 1), lpi2c_imx->base + LPI2C_SAMR); + + writel(SCFGR1_RXSTALL | SCFGR1_TXDSTALL, lpi2c_imx->base + LPI2C_SCFGR1); + + /* + * set SCFGR2: FILTSDA, FILTSCL and CLKHOLD + * + * FILTSCL/FILTSDA can eliminate signal skew. It should generally be + * set to the same value and should be set >= 50ns. + * + * CLKHOLD is only used when clock stretching is enabled, but it will + * extend the clock stretching to ensure there is an additional delay + * between the target driving SDA and the target releasing the SCL pin. + * + * CLKHOLD setting is crucial for lpi2c target. When master read data + * from target, if there is a delay caused by cpu idle, excessive load, + * or other delays between two bytes in one message transmission, it + * will cause a short interval time between the driving SDA signal and + * releasing SCL signal. The lpi2c master will mistakenly think it is a stop + * signal resulting in an arbitration failure. This issue can be avoided + * by setting CLKHOLD. + * + * In order to ensure lpi2c function normally when the lpi2c speed is as + * low as 100kHz, CLKHOLD should be set to 3 and it is also compatible with + * higher clock frequency like 400kHz and 1MHz. + */ + temp = SCFGR2_FILTSDA(2) | SCFGR2_FILTSCL(2) | SCFGR2_CLKHOLD(3); + writel(temp, lpi2c_imx->base + LPI2C_SCFGR2); + + /* + * Enable module: + * SCR_FILTEN can enable digital filter and output delay counter for LPI2C + * target mode. So SCR_FILTEN need be asserted when enable SDA/SCL FILTER + * and CLKHOLD. + */ + writel(SCR_SEN | SCR_FILTEN, lpi2c_imx->base + LPI2C_SCR); + + /* Enable interrupt from i2c module */ + writel(SLAVE_INT_FLAG, lpi2c_imx->base + LPI2C_SIER); +} + +static int lpi2c_imx_register_target(struct i2c_client *client) +{ + struct lpi2c_imx_struct *lpi2c_imx = i2c_get_adapdata(client->adapter); + int ret; + + if (lpi2c_imx->target) + return -EBUSY; + + lpi2c_imx->target = client; + + ret = pm_runtime_resume_and_get(lpi2c_imx->adapter.dev.parent); + if (ret < 0) { + dev_err(&lpi2c_imx->adapter.dev, "failed to resume i2c controller"); + return ret; + } + + lpi2c_imx_target_init(lpi2c_imx); + + return 0; +} + +static int lpi2c_imx_unregister_target(struct i2c_client *client) +{ + struct lpi2c_imx_struct *lpi2c_imx = i2c_get_adapdata(client->adapter); + int ret; + + if (!lpi2c_imx->target) + return -EINVAL; + + /* Reset target address. */ + writel(0, lpi2c_imx->base + LPI2C_SAMR); + + writel(SCR_RST, lpi2c_imx->base + LPI2C_SCR); + writel(0, lpi2c_imx->base + LPI2C_SCR); + + lpi2c_imx->target = NULL; + + ret = pm_runtime_put_sync(lpi2c_imx->adapter.dev.parent); + if (ret < 0) + dev_err(&lpi2c_imx->adapter.dev, "failed to suspend i2c controller"); + + return ret; +} + static int lpi2c_imx_init_recovery_info(struct lpi2c_imx_struct *lpi2c_imx, struct platform_device *pdev) { @@ -546,6 +1209,58 @@ static int lpi2c_imx_init_recovery_info(struct lpi2c_imx_struct *lpi2c_imx, return 0; } +static void dma_exit(struct device *dev, struct lpi2c_imx_dma *dma) +{ + if (dma->chan_rx) + dma_release_channel(dma->chan_rx); + + if (dma->chan_tx) + dma_release_channel(dma->chan_tx); + + devm_kfree(dev, dma); +} + +static int lpi2c_dma_init(struct device *dev, dma_addr_t phy_addr) +{ + struct lpi2c_imx_struct *lpi2c_imx = dev_get_drvdata(dev); + struct lpi2c_imx_dma *dma; + int ret; + + dma = devm_kzalloc(dev, sizeof(*dma), GFP_KERNEL); + if (!dma) + return -ENOMEM; + + dma->phy_addr = phy_addr; + + /* Prepare for TX DMA: */ + dma->chan_tx = dma_request_chan(dev, "tx"); + if (IS_ERR(dma->chan_tx)) { + ret = PTR_ERR(dma->chan_tx); + if (ret != -ENODEV && ret != -EPROBE_DEFER) + dev_err(dev, "can't request DMA tx channel (%d)\n", ret); + dma->chan_tx = NULL; + goto dma_exit; + } + + /* Prepare for RX DMA: */ + dma->chan_rx = dma_request_chan(dev, "rx"); + if (IS_ERR(dma->chan_rx)) { + ret = PTR_ERR(dma->chan_rx); + if (ret != -ENODEV && ret != -EPROBE_DEFER) + dev_err(dev, "can't request DMA rx channel (%d)\n", ret); + dma->chan_rx = NULL; + goto dma_exit; + } + + lpi2c_imx->can_use_dma = true; + lpi2c_imx->dma = dma; + return 0; + +dma_exit: + dma_exit(dev, dma); + return ret; +} + static u32 lpi2c_imx_func(struct i2c_adapter *adapter) { return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | @@ -555,6 +1270,8 @@ static u32 lpi2c_imx_func(struct i2c_adapter *adapter) static const struct i2c_algorithm lpi2c_imx_algo = { .master_xfer = lpi2c_imx_xfer, .functionality = lpi2c_imx_func, + .reg_target = lpi2c_imx_register_target, + .unreg_target = lpi2c_imx_unregister_target, }; static const struct of_device_id lpi2c_imx_of_match[] = { @@ -566,6 +1283,8 @@ MODULE_DEVICE_TABLE(of, lpi2c_imx_of_match); static int lpi2c_imx_probe(struct platform_device *pdev) { struct lpi2c_imx_struct *lpi2c_imx; + struct resource *res; + dma_addr_t phy_addr; unsigned int temp; int irq, ret; @@ -573,7 +1292,7 @@ static int lpi2c_imx_probe(struct platform_device *pdev) if (!lpi2c_imx) return -ENOMEM; - lpi2c_imx->base = devm_platform_ioremap_resource(pdev, 0); + lpi2c_imx->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(lpi2c_imx->base)) return PTR_ERR(lpi2c_imx->base); @@ -587,6 +1306,7 @@ static int lpi2c_imx_probe(struct platform_device *pdev) lpi2c_imx->adapter.dev.of_node = pdev->dev.of_node; strscpy(lpi2c_imx->adapter.name, pdev->name, sizeof(lpi2c_imx->adapter.name)); + phy_addr = (dma_addr_t)res->start; ret = devm_clk_bulk_get_all(&pdev->dev, &lpi2c_imx->clks); if (ret < 0) @@ -598,7 +1318,7 @@ static int lpi2c_imx_probe(struct platform_device *pdev) if (ret) lpi2c_imx->bitrate = I2C_MAX_STANDARD_MODE_FREQ; - ret = devm_request_irq(&pdev->dev, irq, lpi2c_imx_isr, 0, + ret = devm_request_irq(&pdev->dev, irq, lpi2c_imx_isr, IRQF_NO_SUSPEND, pdev->name, lpi2c_imx); if (ret) return dev_err_probe(&pdev->dev, ret, "can't claim irq %d\n", irq); @@ -640,6 +1360,14 @@ static int lpi2c_imx_probe(struct platform_device *pdev) if (ret == -EPROBE_DEFER) goto rpm_disable; + /* Init DMA */ + ret = lpi2c_dma_init(&pdev->dev, phy_addr); + if (ret) { + if (ret == -EPROBE_DEFER) + goto rpm_disable; + dev_info(&pdev->dev, "use pio mode\n"); + } + ret = i2c_add_adapter(&lpi2c_imx->adapter); if (ret) goto rpm_disable; @@ -694,9 +1422,68 @@ static int __maybe_unused lpi2c_runtime_resume(struct device *dev) return 0; } +static int __maybe_unused lpi2c_suspend_noirq(struct device *dev) +{ + return pm_runtime_force_suspend(dev); +} + +static int __maybe_unused lpi2c_resume_noirq(struct device *dev) +{ + struct lpi2c_imx_struct *lpi2c_imx = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + /* + * If the I2C module powers down during system suspend, + * the register values will be lost. Therefore, reinitialize + * the target when the system resumes. + */ + if (lpi2c_imx->target) + lpi2c_imx_target_init(lpi2c_imx); + + return 0; +} + +static int lpi2c_suspend(struct device *dev) +{ + /* + * Some I2C devices may need the I2C controller to remain active + * during resume_noirq() or suspend_noirq(). If the controller is + * autosuspended, there is no way to wake it up once runtime PM is + * disabled (in suspend_late()). + * + * During system resume, the I2C controller will be available only + * after runtime PM is re-enabled (in resume_early()). However, this + * may be too late for some devices. + * + * Wake up the controller in the suspend() callback while runtime PM + * is still enabled. The I2C controller will remain available until + * the suspend_noirq() callback (pm_runtime_force_suspend()) is + * called. During resume, the I2C controller can be restored by the + * resume_noirq() callback (pm_runtime_force_resume()). + * + * Finally, the resume() callback re-enables autosuspend, ensuring + * the I2C controller remains available until the system enters + * suspend_noirq() and from resume_noirq(). + */ + return pm_runtime_resume_and_get(dev); +} + +static int lpi2c_resume(struct device *dev) +{ + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return 0; +} + static const struct dev_pm_ops lpi2c_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(lpi2c_suspend_noirq, + lpi2c_resume_noirq) + SYSTEM_SLEEP_PM_OPS(lpi2c_suspend, lpi2c_resume) SET_RUNTIME_PM_OPS(lpi2c_runtime_suspend, lpi2c_runtime_resume, NULL) }; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index f751d231ded8..ee0d25b498cb 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -335,6 +335,7 @@ static const struct of_device_id i2c_imx_dt_ids[] = { { .compatible = "fsl,imx6sll-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx6sx-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx6ul-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx7d-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx7s-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx8mm-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx8mn-i2c", .data = &imx6_i2c_hwdata, }, @@ -396,17 +397,16 @@ static void i2c_imx_reset_regs(struct imx_i2c_struct *i2c_imx) } /* Functions for DMA support */ -static void i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, - dma_addr_t phy_addr) +static int i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, dma_addr_t phy_addr) { struct imx_i2c_dma *dma; struct dma_slave_config dma_sconfig; - struct device *dev = &i2c_imx->adapter.dev; + struct device *dev = i2c_imx->adapter.dev.parent; int ret; dma = devm_kzalloc(dev, sizeof(*dma), GFP_KERNEL); if (!dma) - return; + return -ENOMEM; dma->chan_tx = dma_request_chan(dev, "tx"); if (IS_ERR(dma->chan_tx)) { @@ -451,7 +451,7 @@ static void i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, dev_info(dev, "using %s (tx) and %s (rx) for DMA transfers\n", dma_chan_name(dma->chan_tx), dma_chan_name(dma->chan_rx)); - return; + return 0; fail_rx: dma_release_channel(dma->chan_rx); @@ -459,6 +459,8 @@ fail_tx: dma_release_channel(dma->chan_tx); fail_al: devm_kfree(dev, dma); + + return ret; } static void i2c_imx_dma_callback(void *arg) @@ -532,22 +534,20 @@ static void i2c_imx_dma_free(struct imx_i2c_struct *i2c_imx) static int i2c_imx_bus_busy(struct imx_i2c_struct *i2c_imx, int for_busy, bool atomic) { + bool multi_master = i2c_imx->multi_master; unsigned long orig_jiffies = jiffies; unsigned int temp; - if (!i2c_imx->multi_master) - return 0; - while (1) { temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2SR); /* check for arbitration lost */ - if (temp & I2SR_IAL) { + if (multi_master && (temp & I2SR_IAL)) { i2c_imx_clear_irq(i2c_imx, I2SR_IAL); return -EAGAIN; } - if (for_busy && (temp & I2SR_IBB)) { + if (for_busy && (!multi_master || (temp & I2SR_IBB))) { i2c_imx->stopped = 0; break; } @@ -622,8 +622,8 @@ static int i2c_imx_acked(struct imx_i2c_struct *i2c_imx) return 0; } -static void i2c_imx_set_clk(struct imx_i2c_struct *i2c_imx, - unsigned int i2c_clk_rate) +static int i2c_imx_set_clk(struct imx_i2c_struct *i2c_imx, + unsigned int i2c_clk_rate) { struct imx_i2c_clk_pair *i2c_clk_div = i2c_imx->hwdata->clk_div; unsigned int div; @@ -638,7 +638,11 @@ static void i2c_imx_set_clk(struct imx_i2c_struct *i2c_imx, /* Divider value calculation */ if (i2c_imx->cur_clk == i2c_clk_rate) - return; + return 0; + + /* Keep the denominator of the following program always NOT equal to 0. */ + if (!(i2c_clk_rate / 2)) + return -EINVAL; i2c_imx->cur_clk = i2c_clk_rate; @@ -669,6 +673,8 @@ static void i2c_imx_set_clk(struct imx_i2c_struct *i2c_imx, dev_dbg(&i2c_imx->adapter.dev, "IFDR[IC]=0x%x, REAL DIV=%d\n", i2c_clk_div[i].val, i2c_clk_div[i].div); #endif + + return 0; } static int i2c_imx_clk_notifier_call(struct notifier_block *nb, @@ -678,11 +684,12 @@ static int i2c_imx_clk_notifier_call(struct notifier_block *nb, struct imx_i2c_struct *i2c_imx = container_of(nb, struct imx_i2c_struct, clk_change_nb); + int ret = 0; if (action & POST_RATE_CHANGE) - i2c_imx_set_clk(i2c_imx, ndata->new_rate); + ret = i2c_imx_set_clk(i2c_imx, ndata->new_rate); - return NOTIFY_OK; + return notifier_from_errno(ret); } static int i2c_imx_start(struct imx_i2c_struct *i2c_imx, bool atomic) @@ -1761,7 +1768,8 @@ static int i2c_imx_probe(struct platform_device *pdev) goto rpm_disable; /* Request IRQ */ - ret = request_irq(irq, i2c_imx_isr, IRQF_SHARED, pdev->name, i2c_imx); + ret = request_irq(irq, i2c_imx_isr, IRQF_SHARED | IRQF_NO_SUSPEND, + pdev->name, i2c_imx); if (ret) { dev_err(&pdev->dev, "can't claim irq %d\n", irq); goto rpm_disable; @@ -1781,7 +1789,11 @@ static int i2c_imx_probe(struct platform_device *pdev) i2c_imx->bitrate = pdata->bitrate; i2c_imx->clk_change_nb.notifier_call = i2c_imx_clk_notifier_call; clk_notifier_register(i2c_imx->clk, &i2c_imx->clk_change_nb); - i2c_imx_set_clk(i2c_imx, clk_get_rate(i2c_imx->clk)); + ret = i2c_imx_set_clk(i2c_imx, clk_get_rate(i2c_imx->clk)); + if (ret < 0) { + dev_err(&pdev->dev, "can't get I2C clock\n"); + goto clk_notifier_unregister; + } i2c_imx_reset_regs(i2c_imx); @@ -1791,6 +1803,22 @@ static int i2c_imx_probe(struct platform_device *pdev) if (ret == -EPROBE_DEFER) goto clk_notifier_unregister; + /* + * DMA mode should be optional for I2C, when encountering DMA errors, + * no need to exit I2C probe. Only print warning to show DMA error and + * use PIO mode directly to ensure I2C bus available as much as possible. + */ + ret = i2c_imx_dma_request(i2c_imx, phy_addr); + if (ret) { + if (ret == -EPROBE_DEFER) + goto clk_notifier_unregister; + else if (ret == -ENODEV) + dev_dbg(&pdev->dev, "Only use PIO mode\n"); + else + dev_warn(&pdev->dev, "Failed to setup DMA (%pe), only use PIO mode\n", + ERR_PTR(ret)); + } + /* Add I2C adapter */ ret = i2c_add_numbered_adapter(&i2c_imx->adapter); if (ret < 0) @@ -1805,9 +1833,6 @@ static int i2c_imx_probe(struct platform_device *pdev) i2c_imx->adapter.name); dev_info(&i2c_imx->adapter.dev, "IMX I2C adapter registered\n"); - /* Init DMA config if supported */ - i2c_imx_dma_request(i2c_imx, phy_addr); - return 0; /* Return OK */ clk_notifier_unregister: @@ -1859,8 +1884,7 @@ static int i2c_imx_runtime_suspend(struct device *dev) struct imx_i2c_struct *i2c_imx = dev_get_drvdata(dev); clk_disable(i2c_imx->clk); - - return 0; + return pinctrl_pm_select_sleep_state(dev); } static int i2c_imx_runtime_resume(struct device *dev) @@ -1868,6 +1892,10 @@ static int i2c_imx_runtime_resume(struct device *dev) struct imx_i2c_struct *i2c_imx = dev_get_drvdata(dev); int ret; + ret = pinctrl_pm_select_default_state(dev); + if (ret) + return ret; + ret = clk_enable(i2c_imx->clk); if (ret) dev_err(dev, "can't enable I2C clock, ret=%d\n", ret); @@ -1875,7 +1903,43 @@ static int i2c_imx_runtime_resume(struct device *dev) return ret; } +static int i2c_imx_suspend(struct device *dev) +{ + /* + * Some I2C devices may need the I2C controller to remain active + * during resume_noirq() or suspend_noirq(). If the controller is + * autosuspended, there is no way to wake it up once runtime PM is + * disabled (in suspend_late()). + * + * During system resume, the I2C controller will be available only + * after runtime PM is re-enabled (in resume_early()). However, this + * may be too late for some devices. + * + * Wake up the controller in the suspend() callback while runtime PM + * is still enabled. The I2C controller will remain available until + * the suspend_noirq() callback (pm_runtime_force_suspend()) is + * called. During resume, the I2C controller can be restored by the + * resume_noirq() callback (pm_runtime_force_resume()). + * + * Finally, the resume() callback re-enables autosuspend, ensuring + * the I2C controller remains available until the system enters + * suspend_noirq() and from resume_noirq(). + */ + return pm_runtime_resume_and_get(dev); +} + +static int i2c_imx_resume(struct device *dev) +{ + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return 0; +} + static const struct dev_pm_ops i2c_imx_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) + SYSTEM_SLEEP_PM_OPS(i2c_imx_suspend, i2c_imx_resume) RUNTIME_PM_OPS(i2c_imx_runtime_suspend, i2c_imx_runtime_resume, NULL) }; diff --git a/drivers/i2c/busses/i2c-isch.c b/drivers/i2c/busses/i2c-isch.c index 2b3b65ef2900..a2ac992f9cb0 100644 --- a/drivers/i2c/busses/i2c-isch.c +++ b/drivers/i2c/busses/i2c-isch.c @@ -291,9 +291,9 @@ static int smbus_sch_probe(struct platform_device *pdev) /* Set up the sysfs linkage to our parent device */ priv->adapter.dev.parent = dev; - priv->adapter.owner = THIS_MODULE, - priv->adapter.class = I2C_CLASS_HWMON, - priv->adapter.algo = &smbus_algorithm, + priv->adapter.owner = THIS_MODULE; + priv->adapter.class = I2C_CLASS_HWMON; + priv->adapter.algo = &smbus_algorithm; snprintf(priv->adapter.name, sizeof(priv->adapter.name), "SMBus SCH adapter at %04x", (unsigned short)res->start); diff --git a/drivers/i2c/busses/i2c-keba.c b/drivers/i2c/busses/i2c-keba.c index 759732a07ef0..7b9ed2592f5b 100644 --- a/drivers/i2c/busses/i2c-keba.c +++ b/drivers/i2c/busses/i2c-keba.c @@ -464,12 +464,8 @@ static void ki2c_unregister_devices(struct ki2c *ki2c) { int i; - for (i = 0; i < ki2c->client_size; i++) { - struct i2c_client *client = ki2c->client[i]; - - if (client) - i2c_unregister_device(client); - } + for (i = 0; i < ki2c->client_size; i++) + i2c_unregister_device(ki2c->client[i]); } static int ki2c_register_devices(struct ki2c *ki2c) diff --git a/drivers/i2c/busses/i2c-microchip-corei2c.c b/drivers/i2c/busses/i2c-microchip-corei2c.c index d1543e7d8380..5db73429125c 100644 --- a/drivers/i2c/busses/i2c-microchip-corei2c.c +++ b/drivers/i2c/busses/i2c-microchip-corei2c.c @@ -93,27 +93,35 @@ * @base: pointer to register struct * @dev: device reference * @i2c_clk: clock reference for i2c input clock + * @msg_queue: pointer to the messages requiring sending * @buf: pointer to msg buffer for easier use * @msg_complete: xfer completion object * @adapter: core i2c abstraction * @msg_err: error code for completed message * @bus_clk_rate: current i2c bus clock rate * @isr_status: cached copy of local ISR status + * @total_num: total number of messages to be sent/received + * @current_num: index of the current message being sent/received * @msg_len: number of bytes transferred in msg * @addr: address of the current slave + * @restart_needed: whether or not a repeated start is required after current message */ struct mchp_corei2c_dev { void __iomem *base; struct device *dev; struct clk *i2c_clk; + struct i2c_msg *msg_queue; u8 *buf; struct completion msg_complete; struct i2c_adapter adapter; int msg_err; + int total_num; + int current_num; u32 bus_clk_rate; u32 isr_status; u16 msg_len; u8 addr; + bool restart_needed; }; static void mchp_corei2c_core_disable(struct mchp_corei2c_dev *idev) @@ -222,6 +230,47 @@ static int mchp_corei2c_fill_tx(struct mchp_corei2c_dev *idev) return 0; } +static void mchp_corei2c_next_msg(struct mchp_corei2c_dev *idev) +{ + struct i2c_msg *this_msg; + u8 ctrl; + + if (idev->current_num >= idev->total_num) { + complete(&idev->msg_complete); + return; + } + + /* + * If there's been an error, the isr needs to return control + * to the "main" part of the driver, so as not to keep sending + * messages once it completes and clears the SI bit. + */ + if (idev->msg_err) { + complete(&idev->msg_complete); + return; + } + + this_msg = idev->msg_queue++; + + if (idev->current_num < (idev->total_num - 1)) { + struct i2c_msg *next_msg = idev->msg_queue; + + idev->restart_needed = next_msg->flags & I2C_M_RD; + } else { + idev->restart_needed = false; + } + + idev->addr = i2c_8bit_addr_from_msg(this_msg); + idev->msg_len = this_msg->len; + idev->buf = this_msg->buf; + + ctrl = readb(idev->base + CORE_I2C_CTRL); + ctrl |= CTRL_STA; + writeb(ctrl, idev->base + CORE_I2C_CTRL); + + idev->current_num++; +} + static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) { u32 status = idev->isr_status; @@ -238,8 +287,6 @@ static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) ctrl &= ~CTRL_STA; writeb(idev->addr, idev->base + CORE_I2C_DATA); writeb(ctrl, idev->base + CORE_I2C_CTRL); - if (idev->msg_len == 0) - finished = true; break; case STATUS_M_ARB_LOST: idev->msg_err = -EAGAIN; @@ -247,10 +294,14 @@ static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) break; case STATUS_M_SLAW_ACK: case STATUS_M_TX_DATA_ACK: - if (idev->msg_len > 0) + if (idev->msg_len > 0) { mchp_corei2c_fill_tx(idev); - else - last_byte = true; + } else { + if (idev->restart_needed) + finished = true; + else + last_byte = true; + } break; case STATUS_M_TX_DATA_NACK: case STATUS_M_SLAR_NACK: @@ -287,7 +338,7 @@ static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) mchp_corei2c_stop(idev); if (last_byte || finished) - complete(&idev->msg_complete); + mchp_corei2c_next_msg(idev); return IRQ_HANDLED; } @@ -311,21 +362,48 @@ static irqreturn_t mchp_corei2c_isr(int irq, void *_dev) return ret; } -static int mchp_corei2c_xfer_msg(struct mchp_corei2c_dev *idev, - struct i2c_msg *msg) +static int mchp_corei2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, + int num) { - u8 ctrl; + struct mchp_corei2c_dev *idev = i2c_get_adapdata(adap); + struct i2c_msg *this_msg = msgs; unsigned long time_left; - - idev->addr = i2c_8bit_addr_from_msg(msg); - idev->msg_len = msg->len; - idev->buf = msg->buf; - idev->msg_err = 0; - - reinit_completion(&idev->msg_complete); + u8 ctrl; mchp_corei2c_core_enable(idev); + /* + * The isr controls the flow of a transfer, this info needs to be saved + * to a location that it can access the queue information from. + */ + idev->restart_needed = false; + idev->msg_queue = msgs; + idev->total_num = num; + idev->current_num = 0; + + /* + * But the first entry to the isr is triggered by the start in this + * function, so the first message needs to be "dequeued". + */ + idev->addr = i2c_8bit_addr_from_msg(this_msg); + idev->msg_len = this_msg->len; + idev->buf = this_msg->buf; + idev->msg_err = 0; + + if (idev->total_num > 1) { + struct i2c_msg *next_msg = msgs + 1; + + idev->restart_needed = next_msg->flags & I2C_M_RD; + } + + idev->current_num++; + idev->msg_queue++; + + reinit_completion(&idev->msg_complete); + + /* + * Send the first start to pass control to the isr + */ ctrl = readb(idev->base + CORE_I2C_CTRL); ctrl |= CTRL_STA; writeb(ctrl, idev->base + CORE_I2C_CTRL); @@ -335,20 +413,8 @@ static int mchp_corei2c_xfer_msg(struct mchp_corei2c_dev *idev, if (!time_left) return -ETIMEDOUT; - return idev->msg_err; -} - -static int mchp_corei2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, - int num) -{ - struct mchp_corei2c_dev *idev = i2c_get_adapdata(adap); - int i, ret; - - for (i = 0; i < num; i++) { - ret = mchp_corei2c_xfer_msg(idev, msgs++); - if (ret) - return ret; - } + if (idev->msg_err) + return idev->msg_err; return num; } diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index 482a0074d448..3ca08b8ef8af 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -263,6 +263,265 @@ static const int npcm_i2caddr[I2C_NUM_OWN_ADDR] = { #define I2C_FREQ_MIN_HZ 10000 #define I2C_FREQ_MAX_HZ I2C_MAX_FAST_MODE_PLUS_FREQ +struct smb_timing_t { + u32 core_clk; + u8 hldt; + u8 dbcnt; + u16 sclfrq; + u8 scllt; + u8 sclht; + bool fast_mode; +}; + +static struct smb_timing_t smb_timing_100khz[] = { + { + .core_clk = 100000000, .hldt = 0x2A, .dbcnt = 0x4, + .sclfrq = 0xFB, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 62500000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x9D, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 50000000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x7E, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 48000000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x79, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 40000000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x65, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 30000000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x4C, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 29000000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x49, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 26000000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x42, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 25000000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x3F, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 24000000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x3D, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 20000000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x33, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 16180000, .hldt = 0x2A, .dbcnt = 0x1, + .sclfrq = 0x29, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 15000000, .hldt = 0x23, .dbcnt = 0x1, + .sclfrq = 0x26, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 13000000, .hldt = 0x1D, .dbcnt = 0x1, + .sclfrq = 0x21, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 12000000, .hldt = 0x1B, .dbcnt = 0x1, + .sclfrq = 0x1F, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 10000000, .hldt = 0x18, .dbcnt = 0x1, + .sclfrq = 0x1A, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 9000000, .hldt = 0x16, .dbcnt = 0x1, + .sclfrq = 0x17, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 8090000, .hldt = 0x14, .dbcnt = 0x1, + .sclfrq = 0x15, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 7500000, .hldt = 0x7, .dbcnt = 0x1, + .sclfrq = 0x13, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 6500000, .hldt = 0xE, .dbcnt = 0x1, + .sclfrq = 0x11, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, + { + .core_clk = 4000000, .hldt = 0x9, .dbcnt = 0x1, + .sclfrq = 0xB, .scllt = 0x0, .sclht = 0x0, + .fast_mode = false, + }, +}; + +static struct smb_timing_t smb_timing_400khz[] = { + { + .core_clk = 100000000, .hldt = 0x2A, .dbcnt = 0x3, + .sclfrq = 0x0, .scllt = 0x47, .sclht = 0x35, + .fast_mode = true, + }, + { + .core_clk = 62500000, .hldt = 0x2A, .dbcnt = 0x2, + .sclfrq = 0x0, .scllt = 0x2C, .sclht = 0x22, + .fast_mode = true, + }, + { + .core_clk = 50000000, .hldt = 0x21, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x24, .sclht = 0x1B, + .fast_mode = true, + }, + { + .core_clk = 48000000, .hldt = 0x1E, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x24, .sclht = 0x19, + .fast_mode = true, + }, + { + .core_clk = 40000000, .hldt = 0x1B, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x1E, .sclht = 0x14, + .fast_mode = true, + }, + { + .core_clk = 33000000, .hldt = 0x15, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x19, .sclht = 0x11, + .fast_mode = true, + }, + { + .core_clk = 30000000, .hldt = 0x15, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x19, .sclht = 0xD, + .fast_mode = true, + }, + { + .core_clk = 29000000, .hldt = 0x11, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x15, .sclht = 0x10, + .fast_mode = true, + }, + { + .core_clk = 26000000, .hldt = 0x10, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x13, .sclht = 0xE, + .fast_mode = true, + }, + { + .core_clk = 25000000, .hldt = 0xF, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x13, .sclht = 0xD, + .fast_mode = true, + }, + { + .core_clk = 24000000, .hldt = 0xD, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x12, .sclht = 0xD, + .fast_mode = true, + }, + { + .core_clk = 20000000, .hldt = 0xB, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0xF, .sclht = 0xA, + .fast_mode = true, + }, + { + .core_clk = 16180000, .hldt = 0xA, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0xC, .sclht = 0x9, + .fast_mode = true, + }, + { + .core_clk = 15000000, .hldt = 0x9, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0xB, .sclht = 0x8, + .fast_mode = true, + }, + { + .core_clk = 13000000, .hldt = 0x7, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0xA, .sclht = 0x7, + .fast_mode = true, + }, + { + .core_clk = 12000000, .hldt = 0x7, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0xA, .sclht = 0x6, + .fast_mode = true, + }, + { + .core_clk = 10000000, .hldt = 0x6, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x8, .sclht = 0x5, + .fast_mode = true, + }, +}; + +static struct smb_timing_t smb_timing_1000khz[] = { + { + .core_clk = 100000000, .hldt = 0x15, .dbcnt = 0x4, + .sclfrq = 0x0, .scllt = 0x1C, .sclht = 0x15, + .fast_mode = true, + }, + { + .core_clk = 62500000, .hldt = 0xF, .dbcnt = 0x3, + .sclfrq = 0x0, .scllt = 0x11, .sclht = 0xE, + .fast_mode = true, + }, + { + .core_clk = 50000000, .hldt = 0xA, .dbcnt = 0x2, + .sclfrq = 0x0, .scllt = 0xE, .sclht = 0xB, + .fast_mode = true, + }, + { + .core_clk = 48000000, .hldt = 0x9, .dbcnt = 0x2, + .sclfrq = 0x0, .scllt = 0xD, .sclht = 0xB, + .fast_mode = true, + }, + { + .core_clk = 41000000, .hldt = 0x9, .dbcnt = 0x2, + .sclfrq = 0x0, .scllt = 0xC, .sclht = 0x9, + .fast_mode = true, + }, + { + .core_clk = 40000000, .hldt = 0x8, .dbcnt = 0x2, + .sclfrq = 0x0, .scllt = 0xB, .sclht = 0x9, + .fast_mode = true, + }, + { + .core_clk = 33000000, .hldt = 0x7, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0xA, .sclht = 0x7, + .fast_mode = true, + }, + { + .core_clk = 25000000, .hldt = 0x4, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x7, .sclht = 0x6, + .fast_mode = true, + }, + { + .core_clk = 24000000, .hldt = 0x7, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x8, .sclht = 0x5, + .fast_mode = true, + }, + { + .core_clk = 20000000, .hldt = 0x4, .dbcnt = 0x1, + .sclfrq = 0x0, .scllt = 0x6, .sclht = 0x4, + .fast_mode = true, + }, +}; + struct npcm_i2c_data { u8 fifo_size; u32 segctl_init_val; @@ -1666,6 +1925,12 @@ static int npcm_i2c_int_master_handler(struct npcm_i2c *bus) (FIELD_GET(NPCM_I2CCST3_EO_BUSY, ioread8(bus->reg + NPCM_I2CCST3)))) { npcm_i2c_irq_handle_eob(bus); +#if IS_ENABLED(CONFIG_I2C_SLAVE) + /* reenable slave if it was enabled */ + if (bus->slave) + iowrite8(bus->slave->addr | NPCM_I2CADDR_SAEN, + bus->reg + NPCM_I2CADDR1); +#endif return 0; } @@ -1805,102 +2070,45 @@ static void npcm_i2c_recovery_init(struct i2c_adapter *_adap) */ static int npcm_i2c_init_clk(struct npcm_i2c *bus, u32 bus_freq_hz) { - u32 k1 = 0; - u32 k2 = 0; - u8 dbnct = 0; - u32 sclfrq = 0; - u8 hldt = 7; + struct smb_timing_t *smb_timing; + u8 scl_table_cnt = 0, table_size = 0; u8 fast_mode = 0; - u32 src_clk_khz; - u32 bus_freq_khz; - src_clk_khz = bus->apb_clk / 1000; - bus_freq_khz = bus_freq_hz / 1000; bus->bus_freq = bus_freq_hz; - /* 100KHz and below: */ - if (bus_freq_hz <= I2C_MAX_STANDARD_MODE_FREQ) { - sclfrq = src_clk_khz / (bus_freq_khz * 4); - - if (sclfrq < SCLFRQ_MIN || sclfrq > SCLFRQ_MAX) - return -EDOM; - - if (src_clk_khz >= 40000) - hldt = 17; - else if (src_clk_khz >= 12500) - hldt = 15; - else - hldt = 7; - } - - /* 400KHz: */ - else if (bus_freq_hz <= I2C_MAX_FAST_MODE_FREQ) { - sclfrq = 0; + switch (bus_freq_hz) { + case I2C_MAX_STANDARD_MODE_FREQ: + smb_timing = smb_timing_100khz; + table_size = ARRAY_SIZE(smb_timing_100khz); + break; + case I2C_MAX_FAST_MODE_FREQ: + smb_timing = smb_timing_400khz; + table_size = ARRAY_SIZE(smb_timing_400khz); fast_mode = I2CCTL3_400K_MODE; - - if (src_clk_khz < 7500) - /* 400KHZ cannot be supported for core clock < 7.5MHz */ - return -EDOM; - - else if (src_clk_khz >= 50000) { - k1 = 80; - k2 = 48; - hldt = 12; - dbnct = 7; - } - - /* Master or Slave with frequency > 25MHz */ - else if (src_clk_khz > 25000) { - hldt = clk_coef(src_clk_khz, 300) + 7; - k1 = clk_coef(src_clk_khz, 1600); - k2 = clk_coef(src_clk_khz, 900); - } - } - - /* 1MHz: */ - else if (bus_freq_hz <= I2C_MAX_FAST_MODE_PLUS_FREQ) { - sclfrq = 0; + break; + case I2C_MAX_FAST_MODE_PLUS_FREQ: + smb_timing = smb_timing_1000khz; + table_size = ARRAY_SIZE(smb_timing_1000khz); fast_mode = I2CCTL3_400K_MODE; - - /* 1MHZ cannot be supported for core clock < 24 MHz */ - if (src_clk_khz < 24000) - return -EDOM; - - k1 = clk_coef(src_clk_khz, 620); - k2 = clk_coef(src_clk_khz, 380); - - /* Core clk > 40 MHz */ - if (src_clk_khz > 40000) { - /* - * Set HLDT: - * SDA hold time: (HLDT-7) * T(CLK) >= 120 - * HLDT = 120/T(CLK) + 7 = 120 * FREQ(CLK) + 7 - */ - hldt = clk_coef(src_clk_khz, 120) + 7; - } else { - hldt = 7; - dbnct = 2; - } + break; + default: + return -EINVAL; } - /* Frequency larger than 1 MHz is not supported */ - else + for (scl_table_cnt = 0; scl_table_cnt < table_size; scl_table_cnt++) + if (bus->apb_clk >= smb_timing[scl_table_cnt].core_clk) + break; + + if (scl_table_cnt == table_size) return -EINVAL; - if (bus_freq_hz >= I2C_MAX_FAST_MODE_FREQ) { - k1 = round_up(k1, 2); - k2 = round_up(k2 + 1, 2); - if (k1 < SCLFRQ_MIN || k1 > SCLFRQ_MAX || - k2 < SCLFRQ_MIN || k2 > SCLFRQ_MAX) - return -EDOM; - } - /* write sclfrq value. bits [6:0] are in I2CCTL2 reg */ - iowrite8(FIELD_PREP(I2CCTL2_SCLFRQ6_0, sclfrq & 0x7F), + iowrite8(FIELD_PREP(I2CCTL2_SCLFRQ6_0, smb_timing[scl_table_cnt].sclfrq & 0x7F), bus->reg + NPCM_I2CCTL2); /* bits [8:7] are in I2CCTL3 reg */ - iowrite8(fast_mode | FIELD_PREP(I2CCTL3_SCLFRQ8_7, (sclfrq >> 7) & 0x3), + iowrite8(FIELD_PREP(I2CCTL3_SCLFRQ8_7, (smb_timing[scl_table_cnt].sclfrq >> 7) & 0x3) | + fast_mode, bus->reg + NPCM_I2CCTL3); /* Select Bank 0 to access NPCM_I2CCTL4/NPCM_I2CCTL5 */ @@ -1912,13 +2120,13 @@ static int npcm_i2c_init_clk(struct npcm_i2c *bus, u32 bus_freq_hz) * k1 = 2 * SCLLT7-0 -> Low Time = k1 / 2 * k2 = 2 * SCLLT7-0 -> High Time = k2 / 2 */ - iowrite8(k1 / 2, bus->reg + NPCM_I2CSCLLT); - iowrite8(k2 / 2, bus->reg + NPCM_I2CSCLHT); + iowrite8(smb_timing[scl_table_cnt].scllt, bus->reg + NPCM_I2CSCLLT); + iowrite8(smb_timing[scl_table_cnt].sclht, bus->reg + NPCM_I2CSCLHT); - iowrite8(dbnct, bus->reg + NPCM_I2CCTL5); + iowrite8(smb_timing[scl_table_cnt].dbcnt, bus->reg + NPCM_I2CCTL5); } - iowrite8(hldt, bus->reg + NPCM_I2CCTL4); + iowrite8(smb_timing[scl_table_cnt].hldt, bus->reg + NPCM_I2CCTL4); /* Return to Bank 1, and stay there by default: */ npcm_i2c_select_bank(bus, I2C_BANK_1); @@ -2035,7 +2243,7 @@ static irqreturn_t npcm_i2c_bus_irq(int irq, void *dev_id) } static bool npcm_i2c_master_start_xmit(struct npcm_i2c *bus, - u8 slave_addr, u16 nwrite, u16 nread, + u16 nwrite, u16 nread, u8 *write_data, u8 *read_data, bool use_PEC, bool use_read_block) { @@ -2043,7 +2251,6 @@ static bool npcm_i2c_master_start_xmit(struct npcm_i2c *bus, bus->cmd_err = -EBUSY; return false; } - bus->dest_addr = slave_addr << 1; bus->wr_buf = write_data; bus->wr_size = nwrite; bus->wr_ind = 0; @@ -2086,7 +2293,6 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, unsigned long time_left, flags; u16 nwrite, nread; u8 *write_data, *read_data; - u8 slave_addr; unsigned long timeout; bool read_block = false; bool read_PEC = false; @@ -2099,7 +2305,6 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, } msg0 = &msgs[0]; - slave_addr = msg0->addr; if (msg0->flags & I2C_M_RD) { /* read */ nwrite = 0; write_data = NULL; @@ -2132,19 +2337,12 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, } } - /* - * Adaptive TimeOut: estimated time in usec + 100% margin: - * 2: double the timeout for clock stretching case - * 9: bits per transaction (including the ack/nack) - */ - timeout_usec = (2 * 9 * USEC_PER_SEC / bus->bus_freq) * (2 + nread + nwrite); - timeout = max_t(unsigned long, bus->adap.timeout, usecs_to_jiffies(timeout_usec)); if (nwrite >= 32 * 1024 || nread >= 32 * 1024) { dev_err(bus->dev, "i2c%d buffer too big\n", bus->num); return -EINVAL; } - time_left = jiffies + timeout + 1; + time_left = jiffies + bus->adap.timeout / bus->adap.retries + 1; do { /* * we must clear slave address immediately when the bus is not @@ -2162,6 +2360,21 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, } while (time_is_after_jiffies(time_left) && bus_busy); + /* + * Store the address early in a global position to ensure it is + * accessible for a potential call to i2c_recover_bus(). + * + * Since the transfer might be a read operation, remove the I2C_M_RD flag + * from the bus->dest_addr for the i2c_recover_bus() call later. + * + * The i2c_recover_bus() uses the address in a write direction to recover + * the i2c bus if some error condition occurs. + * + * Remove the I2C_M_RD flag from the address since npcm_i2c_master_start_xmit() + * handles the read/write operation internally. + */ + bus->dest_addr = i2c_8bit_addr_from_msg(msg0) & ~I2C_M_RD; + /* * Check the BER (bus error) state, when ber_state is true, it means that the module * detects the bus error which is caused by some factor like that the electricity @@ -2179,7 +2392,6 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, } npcm_i2c_init_params(bus); - bus->dest_addr = slave_addr; bus->msgs = msgs; bus->msgs_num = num; bus->cmd_err = 0; @@ -2189,9 +2401,17 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, npcm_i2c_int_enable(bus, true); - if (npcm_i2c_master_start_xmit(bus, slave_addr, nwrite, nread, + if (npcm_i2c_master_start_xmit(bus, nwrite, nread, write_data, read_data, read_PEC, read_block)) { + /* + * Adaptive TimeOut: estimated time in usec + 100% margin: + * 2: double the timeout for clock stretching case + * 9: bits per transaction (including the ack/nack) + */ + timeout_usec = (2 * 9 * USEC_PER_SEC / bus->bus_freq) * (2 + nread + nwrite); + timeout = max_t(unsigned long, bus->adap.timeout / bus->adap.retries, + usecs_to_jiffies(timeout_usec)); time_left = wait_for_completion_timeout(&bus->cmd_complete, timeout); @@ -2317,7 +2537,12 @@ static int npcm_i2c_probe_bus(struct platform_device *pdev) adap = &bus->adap; adap->owner = THIS_MODULE; adap->retries = 3; - adap->timeout = msecs_to_jiffies(35); + /* + * The users want to connect a lot of masters on the same bus. + * This timeout is used to determine the time it takes to take bus ownership. + * The transactions are very long, so waiting 35ms is not enough. + */ + adap->timeout = 2 * HZ; adap->algo = &npcm_i2c_algo; adap->quirks = &npcm_i2c_quirks; adap->algo_data = bus; diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 7a22e1f46e60..7bbd478171e0 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -823,11 +823,9 @@ static int geni_i2c_probe(struct platform_device *pdev) return gi2c->irq; ret = geni_i2c_clk_map_idx(gi2c); - if (ret) { - dev_err(dev, "Invalid clk frequency %d Hz: %d\n", - gi2c->clk_freq_out, ret); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "Invalid clk frequency %d Hz\n", + gi2c->clk_freq_out); gi2c->adap.algo = &geni_i2c_algo; init_completion(&gi2c->done); @@ -837,11 +835,10 @@ static int geni_i2c_probe(struct platform_device *pdev) /* Keep interrupts disabled initially to allow for low-power modes */ ret = devm_request_irq(dev, gi2c->irq, geni_i2c_irq, IRQF_NO_AUTOEN, dev_name(dev), gi2c); - if (ret) { - dev_err(dev, "Request_irq failed:%d: err:%d\n", - gi2c->irq, ret); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, + "Request_irq failed: %d\n", gi2c->irq); + i2c_set_adapdata(&gi2c->adap, gi2c); gi2c->adap.dev.parent = dev; gi2c->adap.dev.of_node = dev->of_node; @@ -870,16 +867,13 @@ static int geni_i2c_probe(struct platform_device *pdev) ret = geni_se_resources_on(&gi2c->se); if (ret) { - dev_err(dev, "Error turning on resources %d\n", ret); - clk_disable_unprepare(gi2c->core_clk); - return ret; + dev_err_probe(dev, ret, "Error turning on resources\n"); + goto err_clk; } proto = geni_se_read_proto(&gi2c->se); if (proto != GENI_SE_I2C) { - dev_err(dev, "Invalid proto %d\n", proto); - geni_se_resources_off(&gi2c->se); - clk_disable_unprepare(gi2c->core_clk); - return -ENXIO; + ret = dev_err_probe(dev, -ENXIO, "Invalid proto %d\n", proto); + goto err_resources; } if (desc && desc->no_dma_support) @@ -891,11 +885,8 @@ static int geni_i2c_probe(struct platform_device *pdev) /* FIFO is disabled, so we can only use GPI DMA */ gi2c->gpi_mode = true; ret = setup_gpi_dma(gi2c); - if (ret) { - geni_se_resources_off(&gi2c->se); - clk_disable_unprepare(gi2c->core_clk); - return dev_err_probe(dev, ret, "Failed to setup GPI DMA mode\n"); - } + if (ret) + goto err_resources; dev_dbg(dev, "Using GPI DMA mode for I2C\n"); } else { @@ -907,10 +898,9 @@ static int geni_i2c_probe(struct platform_device *pdev) tx_depth = desc->tx_fifo_depth; if (!tx_depth) { - dev_err(dev, "Invalid TX FIFO depth\n"); - geni_se_resources_off(&gi2c->se); - clk_disable_unprepare(gi2c->core_clk); - return -EINVAL; + ret = dev_err_probe(dev, -EINVAL, + "Invalid TX FIFO depth\n"); + goto err_resources; } gi2c->tx_wm = tx_depth - 1; @@ -924,7 +914,7 @@ static int geni_i2c_probe(struct platform_device *pdev) clk_disable_unprepare(gi2c->core_clk); ret = geni_se_resources_off(&gi2c->se); if (ret) { - dev_err(dev, "Error turning off resources %d\n", ret); + dev_err_probe(dev, ret, "Error turning off resources\n"); goto err_dma; } @@ -940,17 +930,25 @@ static int geni_i2c_probe(struct platform_device *pdev) ret = i2c_add_adapter(&gi2c->adap); if (ret) { - dev_err(dev, "Error adding i2c adapter %d\n", ret); + dev_err_probe(dev, ret, "Error adding i2c adapter\n"); pm_runtime_disable(gi2c->se.dev); goto err_dma; } dev_dbg(dev, "Geni-I2C adaptor successfully added\n"); - return 0; + return ret; + +err_resources: + geni_se_resources_off(&gi2c->se); +err_clk: + clk_disable_unprepare(gi2c->core_clk); + + return ret; err_dma: release_gpi_dma(gi2c); + return ret; } diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index a7b77d14ee86..5693a38da7b5 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -130,6 +130,8 @@ #define ID_P_PM_BLOCKED BIT(31) #define ID_P_MASK GENMASK(31, 27) +#define ID_SLAVE_NACK BIT(0) + enum rcar_i2c_type { I2C_RCAR_GEN1, I2C_RCAR_GEN2, @@ -166,6 +168,7 @@ struct rcar_i2c_priv { int irq; struct i2c_client *host_notify_client; + u8 slave_flags; }; #define rcar_i2c_priv_to_dev(p) ((p)->adap.dev.parent) @@ -655,6 +658,7 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv) { u32 ssr_raw, ssr_filtered; u8 value; + int ret; ssr_raw = rcar_i2c_read(priv, ICSSR) & 0xff; ssr_filtered = ssr_raw & rcar_i2c_read(priv, ICSIER); @@ -670,7 +674,10 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv) rcar_i2c_write(priv, ICRXTX, value); rcar_i2c_write(priv, ICSIER, SDE | SSR | SAR); } else { - i2c_slave_event(priv->slave, I2C_SLAVE_WRITE_REQUESTED, &value); + ret = i2c_slave_event(priv->slave, I2C_SLAVE_WRITE_REQUESTED, &value); + if (ret) + priv->slave_flags |= ID_SLAVE_NACK; + rcar_i2c_read(priv, ICRXTX); /* dummy read */ rcar_i2c_write(priv, ICSIER, SDR | SSR | SAR); } @@ -683,18 +690,21 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv) if (ssr_filtered & SSR) { i2c_slave_event(priv->slave, I2C_SLAVE_STOP, &value); rcar_i2c_write(priv, ICSCR, SIE | SDBS); /* clear our NACK */ + priv->slave_flags &= ~ID_SLAVE_NACK; rcar_i2c_write(priv, ICSIER, SAR); rcar_i2c_write(priv, ICSSR, ~SSR & 0xff); } /* master wants to write to us */ if (ssr_filtered & SDR) { - int ret; - value = rcar_i2c_read(priv, ICRXTX); ret = i2c_slave_event(priv->slave, I2C_SLAVE_WRITE_RECEIVED, &value); - /* Send NACK in case of error */ - rcar_i2c_write(priv, ICSCR, SIE | SDBS | (ret < 0 ? FNA : 0)); + if (ret) + priv->slave_flags |= ID_SLAVE_NACK; + + /* Send NACK in case of error, but it will come 1 byte late :( */ + rcar_i2c_write(priv, ICSCR, SIE | SDBS | + (priv->slave_flags & ID_SLAVE_NACK ? FNA : 0)); rcar_i2c_write(priv, ICSSR, ~SDR & 0xff); } diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c index 9264adc97ca9..d7dddd6c296a 100644 --- a/drivers/i2c/busses/i2c-riic.c +++ b/drivers/i2c/busses/i2c-riic.c @@ -34,46 +34,51 @@ * Also check the comments in the interrupt routines for some gory details. */ +#include #include #include #include #include #include #include +#include #include #include #include #include #include +#include -#define ICCR1_ICE 0x80 -#define ICCR1_IICRST 0x40 -#define ICCR1_SOWP 0x10 +#define ICCR1_ICE BIT(7) +#define ICCR1_IICRST BIT(6) +#define ICCR1_SOWP BIT(4) +#define ICCR1_SCLI BIT(1) +#define ICCR1_SDAI BIT(0) -#define ICCR2_BBSY 0x80 -#define ICCR2_SP 0x08 -#define ICCR2_RS 0x04 -#define ICCR2_ST 0x02 +#define ICCR2_BBSY BIT(7) +#define ICCR2_SP BIT(3) +#define ICCR2_RS BIT(2) +#define ICCR2_ST BIT(1) -#define ICMR1_CKS_MASK 0x70 -#define ICMR1_BCWP 0x08 +#define ICMR1_CKS_MASK GENMASK(6, 4) +#define ICMR1_BCWP BIT(3) #define ICMR1_CKS(_x) ((((_x) << 4) & ICMR1_CKS_MASK) | ICMR1_BCWP) -#define ICMR3_RDRFS 0x20 -#define ICMR3_ACKWP 0x10 -#define ICMR3_ACKBT 0x08 +#define ICMR3_RDRFS BIT(5) +#define ICMR3_ACKWP BIT(4) +#define ICMR3_ACKBT BIT(3) -#define ICFER_FMPE 0x80 +#define ICFER_FMPE BIT(7) -#define ICIER_TIE 0x80 -#define ICIER_TEIE 0x40 -#define ICIER_RIE 0x20 -#define ICIER_NAKIE 0x10 -#define ICIER_SPIE 0x08 +#define ICIER_TIE BIT(7) +#define ICIER_TEIE BIT(6) +#define ICIER_RIE BIT(5) +#define ICIER_NAKIE BIT(4) +#define ICIER_SPIE BIT(3) -#define ICSR2_NACKF 0x10 +#define ICSR2_NACKF BIT(4) -#define ICBR_RESERVED 0xe0 /* Should be 1 on writes */ +#define ICBR_RESERVED GENMASK(7, 5) /* Should be 1 on writes */ #define RIIC_INIT_MSG -1 @@ -134,6 +139,27 @@ static inline void riic_clear_set_bit(struct riic_dev *riic, u8 clear, u8 set, u riic_writeb(riic, (riic_readb(riic, reg) & ~clear) | set, reg); } +static int riic_bus_barrier(struct riic_dev *riic) +{ + int ret; + u8 val; + + /* + * The SDA line can still be low even when BBSY = 0. Therefore, after checking + * the BBSY flag, also verify that the SDA and SCL lines are not being held low. + */ + ret = readb_poll_timeout(riic->base + riic->info->regs[RIIC_ICCR2], val, + !(val & ICCR2_BBSY), 10, riic->adapter.timeout); + if (ret) + return ret; + + if ((riic_readb(riic, RIIC_ICCR1) & (ICCR1_SDAI | ICCR1_SCLI)) != + (ICCR1_SDAI | ICCR1_SCLI)) + return -EBUSY; + + return 0; +} + static int riic_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) { struct riic_dev *riic = i2c_get_adapdata(adap); @@ -146,13 +172,11 @@ static int riic_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) if (ret) return ret; - if (riic_readb(riic, RIIC_ICCR2) & ICCR2_BBSY) { - riic->err = -EBUSY; + riic->err = riic_bus_barrier(riic); + if (riic->err) goto out; - } reinit_completion(&riic->msg_done); - riic->err = 0; riic_writeb(riic, 0, RIIC_ICSR2); @@ -312,6 +336,7 @@ static int riic_init_hw(struct riic_dev *riic) { int ret; unsigned long rate; + unsigned long ns_per_tick; int total_ticks, cks, brl, brh; struct i2c_timings *t = &riic->i2c_t; struct device *dev = riic->adapter.dev.parent; @@ -320,7 +345,7 @@ static int riic_init_hw(struct riic_dev *riic) : I2C_MAX_FAST_MODE_FREQ; if (t->bus_freq_hz > max_freq) - return dev_err_probe(&riic->adapter.dev, -EINVAL, + return dev_err_probe(dev, -EINVAL, "unsupported bus speed %uHz (%u max)\n", t->bus_freq_hz, max_freq); @@ -356,11 +381,9 @@ static int riic_init_hw(struct riic_dev *riic) rate /= 2; } - if (brl > (0x1F + 3)) { - dev_err(&riic->adapter.dev, "invalid speed (%lu). Too slow.\n", - (unsigned long)t->bus_freq_hz); - return -EINVAL; - } + if (brl > (0x1F + 3)) + return dev_err_probe(dev, -EINVAL, "invalid speed (%uHz). Too slow.\n", + t->bus_freq_hz); brh = total_ticks - brl; @@ -377,8 +400,9 @@ static int riic_init_hw(struct riic_dev *riic) * Remove clock ticks for rise and fall times. Convert ns to clock * ticks. */ - brl -= t->scl_fall_ns / (1000000000 / rate); - brh -= t->scl_rise_ns / (1000000000 / rate); + ns_per_tick = NSEC_PER_SEC / rate; + brl -= t->scl_fall_ns / ns_per_tick; + brh -= t->scl_rise_ns / ns_per_tick; /* Adjust for min register values for when SCLE=1 and NFE=1 */ if (brl < 1) @@ -388,8 +412,7 @@ static int riic_init_hw(struct riic_dev *riic) pr_debug("i2c-riic: freq=%lu, duty=%d, fall=%lu, rise=%lu, cks=%d, brl=%d, brh=%d\n", rate / total_ticks, ((brl + 3) * 100) / (brl + brh + 6), - t->scl_fall_ns / (1000000000 / rate), - t->scl_rise_ns / (1000000000 / rate), cks, brl, brh); + t->scl_fall_ns / ns_per_tick, t->scl_rise_ns / ns_per_tick, cks, brl, brh); ret = pm_runtime_resume_and_get(dev); if (ret) @@ -416,7 +439,7 @@ static int riic_init_hw(struct riic_dev *riic) return 0; } -static struct riic_irq_desc riic_irqs[] = { +static const struct riic_irq_desc riic_irqs[] = { { .res_num = 0, .isr = riic_tend_isr, .name = "riic-tend" }, { .res_num = 1, .isr = riic_rdrf_isr, .name = "riic-rdrf" }, { .res_num = 2, .isr = riic_tdre_isr, .name = "riic-tdre" }, @@ -424,11 +447,6 @@ static struct riic_irq_desc riic_irqs[] = { { .res_num = 5, .isr = riic_tend_isr, .name = "riic-nack" }, }; -static void riic_reset_control_assert(void *data) -{ - reset_control_assert(data); -} - static int riic_i2c_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -445,35 +463,27 @@ static int riic_i2c_probe(struct platform_device *pdev) return PTR_ERR(riic->base); riic->clk = devm_clk_get(dev, NULL); - if (IS_ERR(riic->clk)) { - dev_err(dev, "missing controller clock"); - return PTR_ERR(riic->clk); - } + if (IS_ERR(riic->clk)) + return dev_err_probe(dev, PTR_ERR(riic->clk), + "missing controller clock"); - riic->rstc = devm_reset_control_get_optional_exclusive(dev, NULL); + riic->rstc = devm_reset_control_get_optional_exclusive_deasserted(dev, NULL); if (IS_ERR(riic->rstc)) return dev_err_probe(dev, PTR_ERR(riic->rstc), - "Error: missing reset ctrl\n"); - - ret = reset_control_deassert(riic->rstc); - if (ret) - return ret; - - ret = devm_add_action_or_reset(dev, riic_reset_control_assert, riic->rstc); - if (ret) - return ret; + "failed to acquire deasserted reset\n"); for (i = 0; i < ARRAY_SIZE(riic_irqs); i++) { - ret = platform_get_irq(pdev, riic_irqs[i].res_num); - if (ret < 0) - return ret; + int irq; - ret = devm_request_irq(dev, ret, riic_irqs[i].isr, + irq = platform_get_irq(pdev, riic_irqs[i].res_num); + if (irq < 0) + return irq; + + ret = devm_request_irq(dev, irq, riic_irqs[i].isr, 0, riic_irqs[i].name, riic); - if (ret) { - dev_err(dev, "failed to request irq %s\n", riic_irqs[i].name); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "failed to request irq %s\n", + riic_irqs[i].name); } riic->info = of_device_get_match_data(dev); diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index c4d3eb02da09..dc1e46d834dc 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -30,6 +30,8 @@ #include #include #include +#include +#include #define DRIVER_NAME "xiic-i2c" #define DYNAMIC_MODE_READ_BROKEN_BIT BIT(0) @@ -74,6 +76,9 @@ enum i2c_scl_freq { * @smbus_block_read: Flag to handle block read * @input_clk: Input clock to I2C controller * @i2c_clk: I2C SCL frequency + * @atomic: Mode of transfer + * @atomic_lock: Lock for atomic transfer mode + * @atomic_xfer_state: See STATE_ */ struct xiic_i2c { struct device *dev; @@ -96,6 +101,9 @@ struct xiic_i2c { bool smbus_block_read; unsigned long input_clk; unsigned int i2c_clk; + bool atomic; + spinlock_t atomic_lock; /* Lock for atomic transfer mode */ + enum xilinx_i2c_state atomic_xfer_state; }; struct xiic_version_data { @@ -224,6 +232,8 @@ static const struct timing_regs timing_reg_values[] = { #define XIIC_I2C_TIMEOUT (msecs_to_jiffies(1000)) /* timeout waiting for the controller finish transfers */ #define XIIC_XFER_TIMEOUT (msecs_to_jiffies(10000)) +/* timeout waiting for the controller finish transfers in micro seconds */ +#define XIIC_XFER_TIMEOUT_US 10000000 /* * The following constant is used for the device global interrupt enable @@ -238,6 +248,29 @@ static const struct timing_regs timing_reg_values[] = { static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num); static void __xiic_start_xfer(struct xiic_i2c *i2c); +static int xiic_i2c_runtime_suspend(struct device *dev) +{ + struct xiic_i2c *i2c = dev_get_drvdata(dev); + + clk_disable(i2c->clk); + + return 0; +} + +static int xiic_i2c_runtime_resume(struct device *dev) +{ + struct xiic_i2c *i2c = dev_get_drvdata(dev); + int ret; + + ret = clk_enable(i2c->clk); + if (ret) { + dev_err(dev, "Cannot enable clock.\n"); + return ret; + } + + return 0; +} + /* * For the register read and write functions, a little-endian and big-endian * version are necessary. Endianness is detected during the probe function. @@ -374,9 +407,10 @@ static int xiic_setclk(struct xiic_i2c *i2c) unsigned int index = 0; u32 reg_val; - dev_dbg(i2c->adap.dev.parent, - "%s entry, i2c->input_clk: %ld, i2c->i2c_clk: %d\n", - __func__, i2c->input_clk, i2c->i2c_clk); + if (!i2c->atomic) + dev_dbg(i2c->adap.dev.parent, + "%s entry, i2c->input_clk: %ld, i2c->i2c_clk: %d\n", + __func__, i2c->input_clk, i2c->i2c_clk); /* If not specified in DT, do not configure in SW. Rely only on Vivado design */ if (!i2c->i2c_clk || !i2c->input_clk) @@ -467,7 +501,8 @@ static int xiic_reinit(struct xiic_i2c *i2c) return ret; /* Enable interrupts */ - xiic_setreg32(i2c, XIIC_DGIER_OFFSET, XIIC_GINTR_ENABLE_MASK); + if (!i2c->atomic) + xiic_setreg32(i2c, XIIC_DGIER_OFFSET, XIIC_GINTR_ENABLE_MASK); xiic_irq_clr_en(i2c, XIIC_INTR_ARB_LOST_MASK); @@ -549,11 +584,12 @@ static void xiic_read_rx(struct xiic_i2c *i2c) bytes_in_fifo = xiic_getreg8(i2c, XIIC_RFO_REG_OFFSET) + 1; - dev_dbg(i2c->adap.dev.parent, - "%s entry, bytes in fifo: %d, rem: %d, SR: 0x%x, CR: 0x%x\n", - __func__, bytes_in_fifo, xiic_rx_space(i2c), - xiic_getreg8(i2c, XIIC_SR_REG_OFFSET), - xiic_getreg8(i2c, XIIC_CR_REG_OFFSET)); + if (!i2c->atomic) + dev_dbg(i2c->adap.dev.parent, + "%s entry, bytes in fifo: %d, rem: %d, SR: 0x%x, CR: 0x%x\n", + __func__, bytes_in_fifo, xiic_rx_space(i2c), + xiic_getreg8(i2c, XIIC_SR_REG_OFFSET), + xiic_getreg8(i2c, XIIC_CR_REG_OFFSET)); if (bytes_in_fifo > xiic_rx_space(i2c)) bytes_in_fifo = xiic_rx_space(i2c); @@ -612,6 +648,26 @@ static void xiic_read_rx(struct xiic_i2c *i2c) } } +static bool xiic_error_check(struct xiic_i2c *i2c) +{ + bool status = false; + u32 pend, isr, ier; + + isr = xiic_getreg32(i2c, XIIC_IISR_OFFSET); + ier = xiic_getreg32(i2c, XIIC_IIER_OFFSET); + pend = isr & ier; + + if ((pend & XIIC_INTR_ARB_LOST_MASK) || + ((pend & XIIC_INTR_TX_ERROR_MASK) && + !(pend & XIIC_INTR_RX_FULL_MASK))) { + xiic_reinit(i2c); + status = true; + if (i2c->tx_msg || i2c->rx_msg) + i2c->atomic_xfer_state = STATE_ERROR; + } + return status; +} + static int xiic_tx_fifo_space(struct xiic_i2c *i2c) { /* return the actual space left in the FIFO */ @@ -625,8 +681,9 @@ static void xiic_fill_tx_fifo(struct xiic_i2c *i2c) len = (len > fifo_space) ? fifo_space : len; - dev_dbg(i2c->adap.dev.parent, "%s entry, len: %d, fifo space: %d\n", - __func__, len, fifo_space); + if (!i2c->atomic) + dev_dbg(i2c->adap.dev.parent, "%s entry, len: %d, fifo space: %d\n", + __func__, len, fifo_space); while (len--) { u16 data = i2c->tx_msg->buf[i2c->tx_pos++]; @@ -649,9 +706,13 @@ static void xiic_fill_tx_fifo(struct xiic_i2c *i2c) xiic_setreg8(i2c, XIIC_CR_REG_OFFSET, cr & ~XIIC_CR_MSMS_MASK); } - dev_dbg(i2c->adap.dev.parent, "%s TX STOP\n", __func__); + if (!i2c->atomic) + dev_dbg(i2c->adap.dev.parent, "%s TX STOP\n", __func__); } xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, data); + + if (i2c->atomic && xiic_error_check(i2c)) + return; } } @@ -854,22 +915,51 @@ static int xiic_wait_not_busy(struct xiic_i2c *i2c) */ err = xiic_bus_busy(i2c); while (err && tries--) { - msleep(1); + if (i2c->atomic) + udelay(1000); + else + usleep_range(1000, 1100); err = xiic_bus_busy(i2c); } return err; } +static void xiic_recv_atomic(struct xiic_i2c *i2c) +{ + while (xiic_rx_space(i2c)) { + if (xiic_getreg32(i2c, XIIC_IISR_OFFSET) & XIIC_INTR_RX_FULL_MASK) { + xiic_read_rx(i2c); + + /* Clear Rx full and Tx error interrupts. */ + xiic_irq_clr_en(i2c, XIIC_INTR_RX_FULL_MASK | + XIIC_INTR_TX_ERROR_MASK); + } + if (xiic_error_check(i2c)) + return; + } + + i2c->rx_msg = NULL; + xiic_irq_clr_en(i2c, XIIC_INTR_TX_ERROR_MASK); + + /* send next message if this wasn't the last. */ + if (i2c->nmsgs > 1) { + i2c->nmsgs--; + i2c->tx_msg++; + __xiic_start_xfer(i2c); + } +} + static void xiic_start_recv(struct xiic_i2c *i2c) { u16 rx_watermark; u8 cr = 0, rfd_set = 0; struct i2c_msg *msg = i2c->rx_msg = i2c->tx_msg; - dev_dbg(i2c->adap.dev.parent, "%s entry, ISR: 0x%x, CR: 0x%x\n", - __func__, xiic_getreg32(i2c, XIIC_IISR_OFFSET), - xiic_getreg8(i2c, XIIC_CR_REG_OFFSET)); + if (!i2c->atomic) + dev_dbg(i2c->adap.dev.parent, "%s entry, ISR: 0x%x, CR: 0x%x\n", + __func__, xiic_getreg32(i2c, XIIC_IISR_OFFSET), + xiic_getreg8(i2c, XIIC_CR_REG_OFFSET)); /* Disable Tx interrupts */ xiic_irq_dis(i2c, XIIC_INTR_TX_HALF_MASK | XIIC_INTR_TX_EMPTY_MASK); @@ -967,9 +1057,10 @@ static void xiic_start_recv(struct xiic_i2c *i2c) XIIC_CR_MSMS_MASK) & ~(XIIC_CR_DIR_IS_TX_MASK)); } - dev_dbg(i2c->adap.dev.parent, "%s end, ISR: 0x%x, CR: 0x%x\n", - __func__, xiic_getreg32(i2c, XIIC_IISR_OFFSET), - xiic_getreg8(i2c, XIIC_CR_REG_OFFSET)); + if (!i2c->atomic) + dev_dbg(i2c->adap.dev.parent, "%s end, ISR: 0x%x, CR: 0x%x\n", + __func__, xiic_getreg32(i2c, XIIC_IISR_OFFSET), + xiic_getreg8(i2c, XIIC_CR_REG_OFFSET)); } if (i2c->nmsgs == 1) @@ -979,10 +1070,55 @@ static void xiic_start_recv(struct xiic_i2c *i2c) /* the message is tx:ed */ i2c->tx_pos = msg->len; - /* Enable interrupts */ - xiic_setreg32(i2c, XIIC_DGIER_OFFSET, XIIC_GINTR_ENABLE_MASK); - i2c->prev_msg_tx = false; + + /* Enable interrupts */ + if (!i2c->atomic) + xiic_setreg32(i2c, XIIC_DGIER_OFFSET, XIIC_GINTR_ENABLE_MASK); + else + xiic_recv_atomic(i2c); +} + +static void xiic_send_rem_atomic(struct xiic_i2c *i2c) +{ + while (xiic_tx_space(i2c)) { + if (xiic_tx_fifo_space(i2c)) { + u16 data; + + data = i2c->tx_msg->buf[i2c->tx_pos]; + i2c->tx_pos++; + if (!xiic_tx_space(i2c) && i2c->nmsgs == 1) { + /* last message in transfer -> STOP */ + if (i2c->dynamic) { + data |= XIIC_TX_DYN_STOP_MASK; + } else { + u8 cr; + int status; + + /* Wait till FIFO is empty so STOP is sent last */ + status = xiic_wait_tx_empty(i2c); + if (status) + return; + + /* Write to CR to stop */ + cr = xiic_getreg8(i2c, XIIC_CR_REG_OFFSET); + xiic_setreg8(i2c, XIIC_CR_REG_OFFSET, cr & + ~XIIC_CR_MSMS_MASK); + } + } + xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, data); + } + if (xiic_error_check(i2c)) + return; + } + + if (i2c->nmsgs > 1) { + i2c->nmsgs--; + i2c->tx_msg++; + __xiic_start_xfer(i2c); + } else { + xiic_irq_dis(i2c, XIIC_INTR_TX_HALF_MASK); + } } static void xiic_start_send(struct xiic_i2c *i2c) @@ -991,11 +1127,13 @@ static void xiic_start_send(struct xiic_i2c *i2c) u16 data; struct i2c_msg *msg = i2c->tx_msg; - dev_dbg(i2c->adap.dev.parent, "%s entry, msg: %p, len: %d", - __func__, msg, msg->len); - dev_dbg(i2c->adap.dev.parent, "%s entry, ISR: 0x%x, CR: 0x%x\n", - __func__, xiic_getreg32(i2c, XIIC_IISR_OFFSET), - xiic_getreg8(i2c, XIIC_CR_REG_OFFSET)); + if (!i2c->atomic) { + dev_dbg(i2c->adap.dev.parent, "%s entry, msg: %p, len: %d", + __func__, msg, msg->len); + dev_dbg(i2c->adap.dev.parent, "%s entry, ISR: 0x%x, CR: 0x%x\n", + __func__, xiic_getreg32(i2c, XIIC_IISR_OFFSET), + xiic_getreg8(i2c, XIIC_CR_REG_OFFSET)); + } if (i2c->dynamic) { /* write the address */ @@ -1060,19 +1198,27 @@ static void xiic_start_send(struct xiic_i2c *i2c) XIIC_INTR_TX_ERROR_MASK | XIIC_INTR_BNB_MASK); } + i2c->prev_msg_tx = true; + + if (i2c->atomic && !i2c->atomic_xfer_state) + xiic_send_rem_atomic(i2c); } static void __xiic_start_xfer(struct xiic_i2c *i2c) { int fifo_space = xiic_tx_fifo_space(i2c); - dev_dbg(i2c->adap.dev.parent, "%s entry, msg: %p, fifos space: %d\n", - __func__, i2c->tx_msg, fifo_space); + if (!i2c->atomic) + dev_dbg(i2c->adap.dev.parent, "%s entry, msg: %p, fifos space: %d\n", + __func__, i2c->tx_msg, fifo_space); if (!i2c->tx_msg) return; + if (i2c->atomic && xiic_error_check(i2c)) + return; + i2c->rx_pos = 0; i2c->tx_pos = 0; i2c->state = STATE_START; @@ -1089,7 +1235,10 @@ static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num) bool broken_read, max_read_len, smbus_blk_read; int ret, count; - mutex_lock(&i2c->lock); + if (i2c->atomic) + spin_lock(&i2c->atomic_lock); + else + mutex_lock(&i2c->lock); if (i2c->tx_msg || i2c->rx_msg) { dev_err(i2c->adap.dev.parent, @@ -1098,6 +1247,8 @@ static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num) goto out; } + i2c->atomic_xfer_state = STATE_DONE; + /* In single master mode bus can only be busy, when in use by this * driver. If the register indicates bus being busy for some reason we * should ignore it, since bus will never be released and i2c will be @@ -1124,7 +1275,9 @@ static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num) i2c->tx_msg = msgs; i2c->rx_msg = NULL; i2c->nmsgs = num; - init_completion(&i2c->completion); + + if (!i2c->atomic) + init_completion(&i2c->completion); /* Decide standard mode or Dynamic mode */ i2c->dynamic = true; @@ -1159,7 +1312,10 @@ static int xiic_start_xfer(struct xiic_i2c *i2c, struct i2c_msg *msgs, int num) __xiic_start_xfer(i2c); out: - mutex_unlock(&i2c->lock); + if (i2c->atomic) + spin_unlock(&i2c->atomic_lock); + else + mutex_unlock(&i2c->lock); return ret; } @@ -1198,6 +1354,44 @@ out: return err; } +static int xiic_xfer_atomic(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) +{ + struct xiic_i2c *i2c = i2c_get_adapdata(adap); + u32 status_reg; + int err; + + err = xiic_i2c_runtime_resume(i2c->dev); + if (err) + return err; + + i2c->atomic = true; + err = xiic_start_xfer(i2c, msgs, num); + if (err < 0) + return err; + + err = readl_poll_timeout_atomic(i2c->base + XIIC_SR_REG_OFFSET, + status_reg, !(status_reg & XIIC_SR_BUS_BUSY_MASK), + 1, XIIC_XFER_TIMEOUT_US); + + if (err) /* Timeout */ + err = -ETIMEDOUT; + + spin_lock(&i2c->atomic_lock); + if (err || i2c->state) { + i2c->tx_msg = NULL; + i2c->rx_msg = NULL; + i2c->nmsgs = 0; + } + + err = (i2c->atomic_xfer_state == STATE_DONE) ? num : -EIO; + spin_unlock(&i2c->atomic_lock); + + i2c->atomic = false; + xiic_i2c_runtime_suspend(i2c->dev); + + return err; +} + static u32 xiic_func(struct i2c_adapter *adap) { return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_SMBUS_BLOCK_DATA; @@ -1205,6 +1399,7 @@ static u32 xiic_func(struct i2c_adapter *adap) static const struct i2c_algorithm xiic_algorithm = { .master_xfer = xiic_xfer, + .master_xfer_atomic = xiic_xfer_atomic, .functionality = xiic_func, }; @@ -1268,6 +1463,7 @@ static int xiic_i2c_probe(struct platform_device *pdev) DRIVER_NAME " %s", pdev->name); mutex_init(&i2c->lock); + spin_lock_init(&i2c->atomic_lock); i2c->clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(i2c->clk)) @@ -1365,29 +1561,6 @@ static void xiic_i2c_remove(struct platform_device *pdev) pm_runtime_dont_use_autosuspend(&pdev->dev); } -static int __maybe_unused xiic_i2c_runtime_suspend(struct device *dev) -{ - struct xiic_i2c *i2c = dev_get_drvdata(dev); - - clk_disable(i2c->clk); - - return 0; -} - -static int __maybe_unused xiic_i2c_runtime_resume(struct device *dev) -{ - struct xiic_i2c *i2c = dev_get_drvdata(dev); - int ret; - - ret = clk_enable(i2c->clk); - if (ret) { - dev_err(dev, "Cannot enable clock.\n"); - return ret; - } - - return 0; -} - static const struct dev_pm_ops xiic_dev_pm_ops = { SET_RUNTIME_PM_OPS(xiic_i2c_runtime_suspend, xiic_i2c_runtime_resume, NULL) diff --git a/drivers/i2c/i2c-atr.c b/drivers/i2c/i2c-atr.c index b7c10ced5a43..8fe9ddff8e96 100644 --- a/drivers/i2c/i2c-atr.c +++ b/drivers/i2c/i2c-atr.c @@ -412,7 +412,7 @@ static int i2c_atr_bus_notifier_call(struct notifier_block *nb, dev_name(dev), ret); break; - case BUS_NOTIFY_DEL_DEVICE: + case BUS_NOTIFY_REMOVED_DEVICE: i2c_atr_detach_client(client->adapter, client); break; diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 14ae0cfc325e..d2499f302b50 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -355,6 +355,25 @@ static const struct acpi_device_id i2c_acpi_force_400khz_device_ids[] = { {} }; +static const struct acpi_device_id i2c_acpi_force_100khz_device_ids[] = { + /* + * When a 400KHz freq is used on this model of ELAN touchpad in Linux, + * excessive smoothing (similar to when the touchpad's firmware detects + * a noisy signal) is sometimes applied. As some devices' (e.g, Lenovo + * V15 G4) ACPI tables specify a 400KHz frequency for this device and + * some I2C busses (e.g, Designware I2C) default to a 400KHz freq, + * force the speed to 100KHz as a workaround. + * + * For future investigation: This problem may be related to the default + * HCNT/LCNT values given by some busses' drivers, because they are not + * specified in the aforementioned devices' ACPI tables, and because + * the device works without issues on Windows at what is expected to be + * a 400KHz frequency. The root cause of the issue is not known. + */ + { "ELAN06FA", 0 }, + {} +}; + static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level, void *data, void **return_value) { @@ -373,6 +392,9 @@ static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level, if (acpi_match_device_ids(adev, i2c_acpi_force_400khz_device_ids) == 0) lookup->force_speed = I2C_MAX_FAST_MODE_FREQ; + if (acpi_match_device_ids(adev, i2c_acpi_force_100khz_device_ids) == 0) + lookup->force_speed = I2C_MAX_STANDARD_MODE_FREQ; + return AE_OK; } diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 7c810893bfa3..5546184df05f 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -583,6 +583,9 @@ static int i2c_device_probe(struct device *dev) goto err_detach_pm_domain; } + client->debugfs = debugfs_create_dir(dev_name(&client->dev), + client->adapter->debugfs); + if (driver->probe) status = driver->probe(client); else @@ -602,6 +605,7 @@ static int i2c_device_probe(struct device *dev) return 0; err_release_driver_resources: + debugfs_remove_recursive(client->debugfs); devres_release_group(&client->dev, client->devres_group_id); err_detach_pm_domain: dev_pm_domain_detach(&client->dev, do_power_on); @@ -627,6 +631,8 @@ static void i2c_device_remove(struct device *dev) driver->remove(client); } + debugfs_remove_recursive(client->debugfs); + devres_release_group(&client->dev, client->devres_group_id); dev_pm_domain_detach(&client->dev, true); @@ -1058,6 +1064,7 @@ void i2c_unregister_device(struct i2c_client *client) if (ACPI_COMPANION(&client->dev)) acpi_device_clear_enumerated(ACPI_COMPANION(&client->dev)); + device_remove_software_node(&client->dev); device_unregister(&client->dev); } @@ -1293,14 +1300,12 @@ new_device_store(struct device *dev, struct device_attribute *attr, info.flags |= I2C_CLIENT_SLAVE; } + info.flags |= I2C_CLIENT_USER; + client = i2c_new_client_device(adap, &info); if (IS_ERR(client)) return PTR_ERR(client); - /* Keep track of the added device */ - mutex_lock(&adap->userspace_clients_lock); - list_add_tail(&client->detected, &adap->userspace_clients); - mutex_unlock(&adap->userspace_clients_lock); dev_info(dev, "%s: Instantiated device %s at 0x%02hx\n", "new_device", info.type, info.addr); @@ -1308,6 +1313,15 @@ new_device_store(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_WO(new_device); +static int __i2c_find_user_addr(struct device *dev, const void *addrp) +{ + struct i2c_client *client = i2c_verify_client(dev); + unsigned short addr = *(unsigned short *)addrp; + + return client && client->flags & I2C_CLIENT_USER && + i2c_encode_flags_to_addr(client) == addr; +} + /* * And of course let the users delete the devices they instantiated, if * they got it wrong. This interface can only be used to delete devices @@ -1322,7 +1336,7 @@ delete_device_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct i2c_adapter *adap = to_i2c_adapter(dev); - struct i2c_client *client, *next; + struct device *child_dev; unsigned short addr; char end; int res; @@ -1338,28 +1352,19 @@ delete_device_store(struct device *dev, struct device_attribute *attr, return -EINVAL; } + mutex_lock(&core_lock); /* Make sure the device was added through sysfs */ - res = -ENOENT; - mutex_lock_nested(&adap->userspace_clients_lock, - i2c_adapter_depth(adap)); - list_for_each_entry_safe(client, next, &adap->userspace_clients, - detected) { - if (i2c_encode_flags_to_addr(client) == addr) { - dev_info(dev, "%s: Deleting device %s at 0x%02hx\n", - "delete_device", client->name, client->addr); - - list_del(&client->detected); - i2c_unregister_device(client); - res = count; - break; - } + child_dev = device_find_child(&adap->dev, &addr, __i2c_find_user_addr); + if (child_dev) { + i2c_unregister_device(i2c_verify_client(child_dev)); + put_device(child_dev); + } else { + dev_err(dev, "Can't find userspace-created device at %#x\n", addr); + count = -ENOENT; } - mutex_unlock(&adap->userspace_clients_lock); + mutex_unlock(&core_lock); - if (res < 0) - dev_err(dev, "%s: Can't find device in list\n", - "delete_device"); - return res; + return count; } static DEVICE_ATTR_IGNORE_LOCKDEP(delete_device, S_IWUSR, NULL, delete_device_store); @@ -1530,8 +1535,6 @@ static int i2c_register_adapter(struct i2c_adapter *adap) adap->locked_flags = 0; rt_mutex_init(&adap->bus_lock); rt_mutex_init(&adap->mux_lock); - mutex_init(&adap->userspace_clients_lock); - INIT_LIST_HEAD(&adap->userspace_clients); /* Set default timeout to 1 second if not already set */ if (adap->timeout == 0) @@ -1562,6 +1565,7 @@ static int i2c_register_adapter(struct i2c_adapter *adap) res = device_add(&adap->dev); if (res) { pr_err("adapter '%s': can't register device (%d)\n", adap->name, res); + put_device(&adap->dev); goto out_list; } @@ -1696,23 +1700,6 @@ int i2c_add_numbered_adapter(struct i2c_adapter *adap) } EXPORT_SYMBOL_GPL(i2c_add_numbered_adapter); -static void i2c_do_del_adapter(struct i2c_driver *driver, - struct i2c_adapter *adapter) -{ - struct i2c_client *client, *_n; - - /* Remove the devices we created ourselves as the result of hardware - * probing (using a driver's detect method) */ - list_for_each_entry_safe(client, _n, &driver->clients, detected) { - if (client->adapter == adapter) { - dev_dbg(&adapter->dev, "Removing %s at 0x%x\n", - client->name, client->addr); - list_del(&client->detected); - i2c_unregister_device(client); - } - } -} - static int __unregister_client(struct device *dev, void *dummy) { struct i2c_client *client = i2c_verify_client(dev); @@ -1728,12 +1715,6 @@ static int __unregister_dummy(struct device *dev, void *dummy) return 0; } -static int __process_removed_adapter(struct device_driver *d, void *data) -{ - i2c_do_del_adapter(to_i2c_driver(d), data); - return 0; -} - /** * i2c_del_adapter - unregister I2C adapter * @adap: the adapter being unregistered @@ -1745,7 +1726,6 @@ static int __process_removed_adapter(struct device_driver *d, void *data) void i2c_del_adapter(struct i2c_adapter *adap) { struct i2c_adapter *found; - struct i2c_client *client, *next; /* First make sure that this adapter was ever added */ mutex_lock(&core_lock); @@ -1757,31 +1737,16 @@ void i2c_del_adapter(struct i2c_adapter *adap) } i2c_acpi_remove_space_handler(adap); - /* Tell drivers about this removal */ - mutex_lock(&core_lock); - bus_for_each_drv(&i2c_bus_type, NULL, adap, - __process_removed_adapter); - mutex_unlock(&core_lock); - - /* Remove devices instantiated from sysfs */ - mutex_lock_nested(&adap->userspace_clients_lock, - i2c_adapter_depth(adap)); - list_for_each_entry_safe(client, next, &adap->userspace_clients, - detected) { - dev_dbg(&adap->dev, "Removing %s at 0x%x\n", client->name, - client->addr); - list_del(&client->detected); - i2c_unregister_device(client); - } - mutex_unlock(&adap->userspace_clients_lock); /* Detach any active clients. This can't fail, thus we do not * check the returned value. This is a two-pass process, because * we can't remove the dummy devices during the first pass: they * could have been instantiated by real devices wishing to clean * them up properly, so we give them a chance to do that first. */ + mutex_lock(&core_lock); device_for_each_child(&adap->dev, NULL, __unregister_client); device_for_each_child(&adap->dev, NULL, __unregister_dummy); + mutex_unlock(&core_lock); /* device name is gone after device_unregister */ dev_dbg(&adap->dev, "adapter [%s] unregistered\n", adap->name); @@ -2001,7 +1966,6 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver) /* add the driver to the list of i2c drivers in the driver core */ driver->driver.owner = owner; driver->driver.bus = &i2c_bus_type; - INIT_LIST_HEAD(&driver->clients); /* When registration returns, the driver core * will have called probe() for all matching-but-unbound devices. @@ -2019,10 +1983,13 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver) } EXPORT_SYMBOL(i2c_register_driver); -static int __process_removed_driver(struct device *dev, void *data) +static int __i2c_unregister_detected_client(struct device *dev, void *argp) { - if (dev->type == &i2c_adapter_type) - i2c_do_del_adapter(data, to_i2c_adapter(dev)); + struct i2c_client *client = i2c_verify_client(dev); + + if (client && client->flags & I2C_CLIENT_AUTO) + i2c_unregister_device(client); + return 0; } @@ -2033,7 +2000,12 @@ static int __process_removed_driver(struct device *dev, void *data) */ void i2c_del_driver(struct i2c_driver *driver) { - i2c_for_each_dev(driver, __process_removed_driver); + mutex_lock(&core_lock); + /* Satisfy __must_check, function can't fail */ + if (driver_for_each_device(&driver->driver, NULL, NULL, + __i2c_unregister_detected_client)) { + } + mutex_unlock(&core_lock); driver_unregister(&driver->driver); pr_debug("driver [%s] unregistered\n", driver->driver.name); @@ -2460,6 +2432,7 @@ static int i2c_detect_address(struct i2c_client *temp_client, /* Finally call the custom detection function */ memset(&info, 0, sizeof(struct i2c_board_info)); info.addr = addr; + info.flags = I2C_CLIENT_AUTO; err = driver->detect(temp_client, &info); if (err) { /* -ENODEV is returned if the detection fails. We catch it @@ -2486,9 +2459,7 @@ static int i2c_detect_address(struct i2c_client *temp_client, dev_dbg(&adapter->dev, "Creating %s at 0x%02x\n", info.type, info.addr); client = i2c_new_client_device(adapter, &info); - if (!IS_ERR(client)) - list_add_tail(&client->detected, &driver->clients); - else + if (IS_ERR(client)) dev_err(&adapter->dev, "Failed creating %s at 0x%02x\n", info.type, info.addr); } @@ -2498,7 +2469,7 @@ static int i2c_detect_address(struct i2c_client *temp_client, static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver) { const unsigned short *address_list; - struct i2c_client *temp_client; + struct i2c_client temp_client; int i, err = 0; address_list = driver->address_list; @@ -2519,22 +2490,19 @@ static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver) return 0; /* Set up a temporary client to help detect callback */ - temp_client = kzalloc(sizeof(struct i2c_client), GFP_KERNEL); - if (!temp_client) - return -ENOMEM; - temp_client->adapter = adapter; + memset(&temp_client, 0, sizeof(temp_client)); + temp_client.adapter = adapter; for (i = 0; address_list[i] != I2C_CLIENT_END; i += 1) { dev_dbg(&adapter->dev, "found normal entry for adapter %d, addr 0x%02x\n", i2c_adapter_id(adapter), address_list[i]); - temp_client->addr = address_list[i]; - err = i2c_detect_address(temp_client, driver); + temp_client.addr = address_list[i]; + err = i2c_detect_address(&temp_client, driver); if (unlikely(err)) break; } - kfree(temp_client); return err; } diff --git a/drivers/i2c/i2c-slave-eeprom.c b/drivers/i2c/i2c-slave-eeprom.c index 5946c0d0aef9..275d1d0e910f 100644 --- a/drivers/i2c/i2c-slave-eeprom.c +++ b/drivers/i2c/i2c-slave-eeprom.c @@ -91,7 +91,7 @@ static int i2c_slave_eeprom_slave_cb(struct i2c_client *client, } static ssize_t i2c_slave_eeprom_bin_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, size_t count) + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct eeprom_data *eeprom; unsigned long flags; @@ -106,7 +106,7 @@ static ssize_t i2c_slave_eeprom_bin_read(struct file *filp, struct kobject *kobj } static ssize_t i2c_slave_eeprom_bin_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, size_t count) + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct eeprom_data *eeprom; unsigned long flags; @@ -165,8 +165,8 @@ static int i2c_slave_eeprom_probe(struct i2c_client *client) sysfs_bin_attr_init(&eeprom->bin); eeprom->bin.attr.name = "slave-eeprom"; eeprom->bin.attr.mode = S_IRUSR | S_IWUSR; - eeprom->bin.read = i2c_slave_eeprom_bin_read; - eeprom->bin.write = i2c_slave_eeprom_bin_write; + eeprom->bin.read_new = i2c_slave_eeprom_bin_read; + eeprom->bin.write_new = i2c_slave_eeprom_bin_write; eeprom->bin.size = size; ret = sysfs_create_bin_file(&client->dev.kobj, &eeprom->bin); diff --git a/drivers/i2c/i2c-slave-testunit.c b/drivers/i2c/i2c-slave-testunit.c index 0d6fbaa48248..6de4307050dd 100644 --- a/drivers/i2c/i2c-slave-testunit.c +++ b/drivers/i2c/i2c-slave-testunit.c @@ -38,6 +38,7 @@ enum testunit_regs { enum testunit_flags { TU_FLAG_IN_PROCESS, + TU_FLAG_NACK, }; struct testunit_data { @@ -90,8 +91,10 @@ static int i2c_slave_testunit_slave_cb(struct i2c_client *client, switch (event) { case I2C_SLAVE_WRITE_REQUESTED: - if (test_bit(TU_FLAG_IN_PROCESS, &tu->flags)) - return -EBUSY; + if (test_bit(TU_FLAG_IN_PROCESS | TU_FLAG_NACK, &tu->flags)) { + ret = -EBUSY; + break; + } memset(tu->regs, 0, TU_NUM_REGS); tu->reg_idx = 0; @@ -99,8 +102,10 @@ static int i2c_slave_testunit_slave_cb(struct i2c_client *client, break; case I2C_SLAVE_WRITE_RECEIVED: - if (test_bit(TU_FLAG_IN_PROCESS, &tu->flags)) - return -EBUSY; + if (test_bit(TU_FLAG_IN_PROCESS | TU_FLAG_NACK, &tu->flags)) { + ret = -EBUSY; + break; + } if (tu->reg_idx < TU_NUM_REGS) tu->regs[tu->reg_idx] = *val; @@ -129,6 +134,8 @@ static int i2c_slave_testunit_slave_cb(struct i2c_client *client, * here because we still need them in the workqueue! */ tu->reg_idx = 0; + + clear_bit(TU_FLAG_NACK, &tu->flags); break; case I2C_SLAVE_READ_PROCESSED: @@ -151,6 +158,10 @@ static int i2c_slave_testunit_slave_cb(struct i2c_client *client, break; } + /* If an error occurred somewhen, we NACK everything until next STOP */ + if (ret) + set_bit(TU_FLAG_NACK, &tu->flags); + return ret; } diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c index dce18f763a09..77a740561fd7 100644 --- a/drivers/i2c/muxes/i2c-demux-pinctrl.c +++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c @@ -68,7 +68,7 @@ static int i2c_demux_activate_master(struct i2c_demux_pinctrl_priv *priv, u32 ne } /* - * Check if there are pinctrl states at all. Note: we cant' use + * Check if there are pinctrl states at all. Note: we can't use * devm_pinctrl_get_select() because we need to distinguish between * the -ENODEV from devm_pinctrl_get() and pinctrl_lookup_state(). */ @@ -261,7 +261,9 @@ static int i2c_demux_pinctrl_probe(struct platform_device *pdev) pm_runtime_no_callbacks(&pdev->dev); /* switch to first parent as active master */ - i2c_demux_activate_master(priv, 0); + err = i2c_demux_activate_master(priv, 0); + if (err) + goto err_rollback; err = device_create_file(&pdev->dev, &dev_attr_available_masters); if (err) diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 42310c9a00c2..d5dc4180afbc 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1919,7 +1919,7 @@ static int i3c_master_bus_init(struct i3c_master_controller *master) goto err_bus_cleanup; if (master->ops->set_speed) { - master->ops->set_speed(master, I3C_OPEN_DRAIN_NORMAL_SPEED); + ret = master->ops->set_speed(master, I3C_OPEN_DRAIN_NORMAL_SPEED); if (ret) goto err_bus_cleanup; } @@ -2486,7 +2486,7 @@ static int i3c_master_i2c_adapter_init(struct i3c_master_controller *master) struct i2c_adapter *adap = i3c_master_to_i2c_adapter(master); struct i2c_dev_desc *i2cdev; struct i2c_dev_boardinfo *i2cboardinfo; - int ret; + int ret, id = -ENODEV; adap->dev.parent = master->dev.parent; adap->owner = master->dev.parent->driver->owner; @@ -2497,7 +2497,15 @@ static int i3c_master_i2c_adapter_init(struct i3c_master_controller *master) adap->timeout = 1000; adap->retries = 3; - ret = i2c_add_adapter(adap); + if (master->dev.of_node) + id = of_alias_get_id(master->dev.of_node, "i2c"); + + if (id >= 0) { + adap->nr = id; + ret = i2c_add_numbered_adapter(adap); + } else { + ret = i2c_add_adapter(adap); + } if (ret) return ret; diff --git a/drivers/i3c/master/Kconfig b/drivers/i3c/master/Kconfig index 90dee3ec5520..77da199c7413 100644 --- a/drivers/i3c/master/Kconfig +++ b/drivers/i3c/master/Kconfig @@ -57,3 +57,14 @@ config MIPI_I3C_HCI This driver can also be built as a module. If so, the module will be called mipi-i3c-hci. + +config MIPI_I3C_HCI_PCI + tristate "MIPI I3C Host Controller Interface PCI support" + depends on MIPI_I3C_HCI + depends on PCI + help + Support for MIPI I3C Host Controller Interface compatible hardware + on the PCI bus. + + This driver can also be built as a module. If so, the module will be + called mipi-i3c-hci-pci. diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index d4b80eb8cecd..2fbf8b2addd0 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -251,14 +251,6 @@ struct dw_i3c_i2c_dev_data { struct i3c_generic_ibi_pool *ibi_pool; }; -static u8 even_parity(u8 p) -{ - p ^= p >> 4; - p &= 0xf; - - return (0x9669 >> p) & 1; -} - static bool dw_i3c_master_supports_ccc_cmd(struct i3c_master_controller *m, const struct i3c_ccc_cmd *cmd) { @@ -848,7 +840,7 @@ static int dw_i3c_master_daa(struct i3c_master_controller *m) struct dw_i3c_xfer *xfer; struct dw_i3c_cmd *cmd; u32 olddevs, newdevs; - u8 p, last_addr = 0; + u8 last_addr = 0; int ret, pos; ret = pm_runtime_resume_and_get(master->dev); @@ -873,9 +865,9 @@ static int dw_i3c_master_daa(struct i3c_master_controller *m) } master->devs[pos].addr = ret; - p = even_parity(ret); last_addr = ret; - ret |= (p << 7); + + ret |= parity8(ret) ? 0 : BIT(7); writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(ret), master->regs + @@ -1647,6 +1639,7 @@ EXPORT_SYMBOL_GPL(dw_i3c_common_probe); void dw_i3c_common_remove(struct dw_i3c_master *master) { + cancel_work_sync(&master->hj_work); i3c_master_unregister(&master->base); pm_runtime_disable(master->dev); diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c index 06c0592487d3..fedbe6624a1c 100644 --- a/drivers/i3c/master/i3c-master-cdns.c +++ b/drivers/i3c/master/i3c-master-cdns.c @@ -889,8 +889,7 @@ static u32 prepare_rr0_dev_address(u32 addr) ret |= (addr & GENMASK(9, 7)) << 6; /* RR0[0] = ~XOR(addr[6:0]) */ - if (!(hweight8(addr & 0x7f) & 1)) - ret |= 1; + ret |= parity8(addr & 0x7f) ? 0 : BIT(0); return ret; } diff --git a/drivers/i3c/master/mipi-i3c-hci/Makefile b/drivers/i3c/master/mipi-i3c-hci/Makefile index 1f8cd5c48fde..e3d3ef757035 100644 --- a/drivers/i3c/master/mipi-i3c-hci/Makefile +++ b/drivers/i3c/master/mipi-i3c-hci/Makefile @@ -5,3 +5,4 @@ mipi-i3c-hci-y := core.o ext_caps.o pio.o dma.o \ cmd_v1.o cmd_v2.o \ dat_v1.o dct_v1.o \ hci_quirks.o +obj-$(CONFIG_MIPI_I3C_HCI_PCI) += mipi-i3c-hci-pci.o diff --git a/drivers/i3c/master/mipi-i3c-hci/dat_v1.c b/drivers/i3c/master/mipi-i3c-hci/dat_v1.c index 47b9b4d4ed3f..85c4916972e4 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dat_v1.c +++ b/drivers/i3c/master/mipi-i3c-hci/dat_v1.c @@ -40,15 +40,6 @@ #define dat_w0_write(i, v) writel(v, hci->DAT_regs + (i) * 8) #define dat_w1_write(i, v) writel(v, hci->DAT_regs + (i) * 8 + 4) -static inline bool dynaddr_parity(unsigned int addr) -{ - addr |= 1 << 7; - addr += addr >> 4; - addr += addr >> 2; - addr += addr >> 1; - return (addr & 1); -} - static int hci_dat_v1_init(struct i3c_hci *hci) { unsigned int dat_idx; @@ -123,7 +114,7 @@ static void hci_dat_v1_set_dynamic_addr(struct i3c_hci *hci, dat_w0 = dat_w0_read(dat_idx); dat_w0 &= ~(DAT_0_DYNAMIC_ADDRESS | DAT_0_DYNADDR_PARITY); dat_w0 |= FIELD_PREP(DAT_0_DYNAMIC_ADDRESS, address) | - (dynaddr_parity(address) ? DAT_0_DYNADDR_PARITY : 0); + (parity8(address) ? 0 : DAT_0_DYNADDR_PARITY); dat_w0_write(dat_idx, dat_w0); } diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index e8e56a8d2057..491dfe70b660 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -758,9 +758,26 @@ static bool hci_dma_irq_handler(struct i3c_hci *hci) complete(&rh->op_done); if (status & INTR_TRANSFER_ABORT) { + u32 ring_status; + dev_notice_ratelimited(&hci->master.dev, "ring %d: Transfer Aborted\n", i); mipi_i3c_hci_resume(hci); + ring_status = rh_reg_read(RING_STATUS); + if (!(ring_status & RING_STATUS_RUNNING) && + status & INTR_TRANSFER_COMPLETION && + status & INTR_TRANSFER_ERR) { + /* + * Ring stop followed by run is an Intel + * specific required quirk after resuming the + * halted controller. Do it only when the ring + * is not in running state after a transfer + * error. + */ + rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE); + rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | + RING_CTRL_RUN_STOP); + } } if (status & INTR_WARN_INS_STOP_MODE) dev_warn_ratelimited(&hci->master.dev, diff --git a/drivers/i3c/master/mipi-i3c-hci/mipi-i3c-hci-pci.c b/drivers/i3c/master/mipi-i3c-hci/mipi-i3c-hci-pci.c new file mode 100644 index 000000000000..c6c3a3ec11ea --- /dev/null +++ b/drivers/i3c/master/mipi-i3c-hci/mipi-i3c-hci-pci.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCI glue code for MIPI I3C HCI driver + * + * Copyright (C) 2024 Intel Corporation + * + * Author: Jarkko Nikula + */ +#include +#include +#include +#include +#include +#include + +struct mipi_i3c_hci_pci_info { + int (*init)(struct pci_dev *pci); +}; + +#define INTEL_PRIV_OFFSET 0x2b0 +#define INTEL_PRIV_SIZE 0x28 +#define INTEL_PRIV_RESETS 0x04 +#define INTEL_PRIV_RESETS_RESET BIT(0) +#define INTEL_PRIV_RESETS_RESET_DONE BIT(1) + +static DEFINE_IDA(mipi_i3c_hci_pci_ida); + +static int mipi_i3c_hci_pci_intel_init(struct pci_dev *pci) +{ + unsigned long timeout; + void __iomem *priv; + + priv = devm_ioremap(&pci->dev, + pci_resource_start(pci, 0) + INTEL_PRIV_OFFSET, + INTEL_PRIV_SIZE); + if (!priv) + return -ENOMEM; + + /* Assert reset, wait for completion and release reset */ + writel(0, priv + INTEL_PRIV_RESETS); + timeout = jiffies + msecs_to_jiffies(10); + while (!(readl(priv + INTEL_PRIV_RESETS) & + INTEL_PRIV_RESETS_RESET_DONE)) { + if (time_after(jiffies, timeout)) + break; + cpu_relax(); + } + writel(INTEL_PRIV_RESETS_RESET, priv + INTEL_PRIV_RESETS); + + return 0; +} + +static struct mipi_i3c_hci_pci_info intel_info = { + .init = mipi_i3c_hci_pci_intel_init, +}; + +static int mipi_i3c_hci_pci_probe(struct pci_dev *pci, + const struct pci_device_id *id) +{ + struct mipi_i3c_hci_pci_info *info; + struct platform_device *pdev; + struct resource res[2]; + int dev_id, ret; + + ret = pcim_enable_device(pci); + if (ret) + return ret; + + pci_set_master(pci); + + memset(&res, 0, sizeof(res)); + + res[0].flags = IORESOURCE_MEM; + res[0].start = pci_resource_start(pci, 0); + res[0].end = pci_resource_end(pci, 0); + + res[1].flags = IORESOURCE_IRQ; + res[1].start = pci->irq; + res[1].end = pci->irq; + + dev_id = ida_alloc(&mipi_i3c_hci_pci_ida, GFP_KERNEL); + if (dev_id < 0) + return dev_id; + + pdev = platform_device_alloc("mipi-i3c-hci", dev_id); + if (!pdev) + return -ENOMEM; + + pdev->dev.parent = &pci->dev; + device_set_node(&pdev->dev, dev_fwnode(&pci->dev)); + + ret = platform_device_add_resources(pdev, res, ARRAY_SIZE(res)); + if (ret) + goto err; + + info = (struct mipi_i3c_hci_pci_info *)id->driver_data; + if (info && info->init) { + ret = info->init(pci); + if (ret) + goto err; + } + + ret = platform_device_add(pdev); + if (ret) + goto err; + + pci_set_drvdata(pci, pdev); + + return 0; + +err: + platform_device_put(pdev); + ida_free(&mipi_i3c_hci_pci_ida, dev_id); + return ret; +} + +static void mipi_i3c_hci_pci_remove(struct pci_dev *pci) +{ + struct platform_device *pdev = pci_get_drvdata(pci); + int dev_id = pdev->id; + + platform_device_unregister(pdev); + ida_free(&mipi_i3c_hci_pci_ida, dev_id); +} + +static const struct pci_device_id mipi_i3c_hci_pci_devices[] = { + /* Panther Lake-H */ + { PCI_VDEVICE(INTEL, 0xe37c), (kernel_ulong_t)&intel_info}, + { PCI_VDEVICE(INTEL, 0xe36f), (kernel_ulong_t)&intel_info}, + /* Panther Lake-P */ + { PCI_VDEVICE(INTEL, 0xe47c), (kernel_ulong_t)&intel_info}, + { PCI_VDEVICE(INTEL, 0xe46f), (kernel_ulong_t)&intel_info}, + { }, +}; +MODULE_DEVICE_TABLE(pci, mipi_i3c_hci_pci_devices); + +static struct pci_driver mipi_i3c_hci_pci_driver = { + .name = "mipi_i3c_hci_pci", + .id_table = mipi_i3c_hci_pci_devices, + .probe = mipi_i3c_hci_pci_probe, + .remove = mipi_i3c_hci_pci_remove, +}; + +module_pci_driver(mipi_i3c_hci_pci_driver); + +MODULE_AUTHOR("Jarkko Nikula "); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MIPI I3C HCI driver on PCI bus"); diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index ac4d8faa3886..118fe1d37c22 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include #include @@ -1651,6 +1652,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { X86_MATCH_VFM(INTEL_ATOM_TREMONT_D, &idle_cpu_snr), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &idle_cpu_grr), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &idle_cpu_srf), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, &idle_cpu_srf), {} }; @@ -2316,10 +2318,7 @@ static int __init intel_idle_init(void) return -ENODEV; } - if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) - return -ENODEV; - - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &mwait_substates); if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) || !(ecx & CPUID5_ECX_INTERRUPT_BREAK) || diff --git a/drivers/iio/accel/adxl345.h b/drivers/iio/accel/adxl345.h index 3d5c8719db3d..517e494ba555 100644 --- a/drivers/iio/accel/adxl345.h +++ b/drivers/iio/accel/adxl345.h @@ -9,37 +9,93 @@ #define _ADXL345_H_ #define ADXL345_REG_DEVID 0x00 +#define ADXL345_REG_THRESH_TAP 0x1D #define ADXL345_REG_OFSX 0x1E #define ADXL345_REG_OFSY 0x1F #define ADXL345_REG_OFSZ 0x20 #define ADXL345_REG_OFS_AXIS(index) (ADXL345_REG_OFSX + (index)) + +/* Tap duration */ +#define ADXL345_REG_DUR 0x21 +/* Tap latency */ +#define ADXL345_REG_LATENT 0x22 +/* Tap window */ +#define ADXL345_REG_WINDOW 0x23 +/* Activity threshold */ +#define ADXL345_REG_THRESH_ACT 0x24 +/* Inactivity threshold */ +#define ADXL345_REG_THRESH_INACT 0x25 +/* Inactivity time */ +#define ADXL345_REG_TIME_INACT 0x26 +/* Axis enable control for activity and inactivity detection */ +#define ADXL345_REG_ACT_INACT_CTRL 0x27 +/* Free-fall threshold */ +#define ADXL345_REG_THRESH_FF 0x28 +/* Free-fall time */ +#define ADXL345_REG_TIME_FF 0x29 +/* Axis control for single tap or double tap */ +#define ADXL345_REG_TAP_AXIS 0x2A +/* Source of single tap or double tap */ +#define ADXL345_REG_ACT_TAP_STATUS 0x2B +/* Data rate and power mode control */ #define ADXL345_REG_BW_RATE 0x2C #define ADXL345_REG_POWER_CTL 0x2D +#define ADXL345_REG_INT_ENABLE 0x2E +#define ADXL345_REG_INT_MAP 0x2F +#define ADXL345_REG_INT_SOURCE 0x30 +#define ADXL345_REG_INT_SOURCE_MSK 0xFF #define ADXL345_REG_DATA_FORMAT 0x31 -#define ADXL345_REG_DATAX0 0x32 -#define ADXL345_REG_DATAY0 0x34 -#define ADXL345_REG_DATAZ0 0x36 -#define ADXL345_REG_DATA_AXIS(index) \ - (ADXL345_REG_DATAX0 + (index) * sizeof(__le16)) +#define ADXL345_REG_XYZ_BASE 0x32 +#define ADXL345_REG_DATA_AXIS(index) \ + (ADXL345_REG_XYZ_BASE + (index) * sizeof(__le16)) +#define ADXL345_REG_FIFO_CTL 0x38 +#define ADXL345_FIFO_CTL_SAMPLES_MSK GENMASK(4, 0) +/* 0: INT1, 1: INT2 */ +#define ADXL345_FIFO_CTL_TRIGGER_MSK BIT(5) +#define ADXL345_FIFO_CTL_MODE_MSK GENMASK(7, 6) +#define ADXL345_REG_FIFO_STATUS 0x39 +#define ADXL345_REG_FIFO_STATUS_MSK 0x3F + +#define ADXL345_INT_OVERRUN BIT(0) +#define ADXL345_INT_WATERMARK BIT(1) +#define ADXL345_INT_FREE_FALL BIT(2) +#define ADXL345_INT_INACTIVITY BIT(3) +#define ADXL345_INT_ACTIVITY BIT(4) +#define ADXL345_INT_DOUBLE_TAP BIT(5) +#define ADXL345_INT_SINGLE_TAP BIT(6) +#define ADXL345_INT_DATA_READY BIT(7) + +/* + * BW_RATE bits - Bandwidth and output data rate. The default value is + * 0x0A, which translates to a 100 Hz output data rate + */ #define ADXL345_BW_RATE GENMASK(3, 0) +#define ADXL345_BW_LOW_POWER BIT(4) #define ADXL345_BASE_RATE_NANO_HZ 97656250LL -#define ADXL345_POWER_CTL_MEASURE BIT(3) #define ADXL345_POWER_CTL_STANDBY 0x00 +#define ADXL345_POWER_CTL_WAKEUP GENMASK(1, 0) +#define ADXL345_POWER_CTL_SLEEP BIT(2) +#define ADXL345_POWER_CTL_MEASURE BIT(3) +#define ADXL345_POWER_CTL_AUTO_SLEEP BIT(4) +#define ADXL345_POWER_CTL_LINK BIT(5) -#define ADXL345_DATA_FORMAT_RANGE GENMASK(1, 0) /* Set the g range */ -#define ADXL345_DATA_FORMAT_JUSTIFY BIT(2) /* Left-justified (MSB) mode */ -#define ADXL345_DATA_FORMAT_FULL_RES BIT(3) /* Up to 13-bits resolution */ -#define ADXL345_DATA_FORMAT_SPI_3WIRE BIT(6) /* 3-wire SPI mode */ -#define ADXL345_DATA_FORMAT_SELF_TEST BIT(7) /* Enable a self test */ - +/* Set the g range */ +#define ADXL345_DATA_FORMAT_RANGE GENMASK(1, 0) +/* Data is left justified */ +#define ADXL345_DATA_FORMAT_JUSTIFY BIT(2) +/* Up to 13-bits resolution */ +#define ADXL345_DATA_FORMAT_FULL_RES BIT(3) +#define ADXL345_DATA_FORMAT_SPI_3WIRE BIT(6) +#define ADXL345_DATA_FORMAT_SELF_TEST BIT(7) #define ADXL345_DATA_FORMAT_2G 0 #define ADXL345_DATA_FORMAT_4G 1 #define ADXL345_DATA_FORMAT_8G 2 #define ADXL345_DATA_FORMAT_16G 3 #define ADXL345_DEVID 0xE5 +#define ADXL345_FIFO_SIZE 32 /* * In full-resolution mode, scale factor is maintained at ~4 mg/LSB @@ -62,6 +118,7 @@ struct adxl345_chip_info { }; int adxl345_core_probe(struct device *dev, struct regmap *regmap, + bool fifo_delay_default, int (*setup)(struct device*, struct regmap*)); #endif /* _ADXL345_H_ */ diff --git a/drivers/iio/accel/adxl345_core.c b/drivers/iio/accel/adxl345_core.c index b1efab0f6404..d1b2d3985a40 100644 --- a/drivers/iio/accel/adxl345_core.c +++ b/drivers/iio/accel/adxl345_core.c @@ -7,6 +7,8 @@ * Datasheet: https://www.analog.com/media/en/technical-documentation/data-sheets/ADXL345.pdf */ +#include +#include #include #include #include @@ -14,36 +16,92 @@ #include #include +#include +#include #include "adxl345.h" -struct adxl345_data { +#define ADXL345_FIFO_BYPASS 0 +#define ADXL345_FIFO_FIFO 1 +#define ADXL345_FIFO_STREAM 2 + +#define ADXL345_DIRS 3 + +#define ADXL345_INT_NONE 0xff +#define ADXL345_INT1 0 +#define ADXL345_INT2 1 + +struct adxl345_state { const struct adxl345_chip_info *info; struct regmap *regmap; + bool fifo_delay; /* delay: delay is needed for SPI */ + int irq; + u8 intio; + u8 int_map; + u8 watermark; + u8 fifo_mode; + __le16 fifo_buf[ADXL345_DIRS * ADXL345_FIFO_SIZE + 1] __aligned(IIO_DMA_MINALIGN); }; -#define ADXL345_CHANNEL(index, axis) { \ +#define ADXL345_CHANNEL(index, reg, axis) { \ .type = IIO_ACCEL, \ .modified = 1, \ .channel2 = IIO_MOD_##axis, \ - .address = index, \ + .address = (reg), \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ BIT(IIO_CHAN_INFO_CALIBBIAS), \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE) | \ BIT(IIO_CHAN_INFO_SAMP_FREQ), \ + .scan_index = (index), \ + .scan_type = { \ + .sign = 's', \ + .realbits = 13, \ + .storagebits = 16, \ + .endianness = IIO_LE, \ + }, \ } -static const struct iio_chan_spec adxl345_channels[] = { - ADXL345_CHANNEL(0, X), - ADXL345_CHANNEL(1, Y), - ADXL345_CHANNEL(2, Z), +enum adxl345_chans { + chan_x, chan_y, chan_z, }; +static const struct iio_chan_spec adxl345_channels[] = { + ADXL345_CHANNEL(0, chan_x, X), + ADXL345_CHANNEL(1, chan_y, Y), + ADXL345_CHANNEL(2, chan_z, Z), +}; + +static const unsigned long adxl345_scan_masks[] = { + BIT(chan_x) | BIT(chan_y) | BIT(chan_z), + 0 +}; + +static int adxl345_set_interrupts(struct adxl345_state *st) +{ + int ret; + unsigned int int_enable = st->int_map; + unsigned int int_map; + + /* + * Any bits set to 0 in the INT map register send their respective + * interrupts to the INT1 pin, whereas bits set to 1 send their respective + * interrupts to the INT2 pin. The intio shall convert this accordingly. + */ + int_map = FIELD_GET(ADXL345_REG_INT_SOURCE_MSK, + st->intio ? st->int_map : ~st->int_map); + + ret = regmap_write(st->regmap, ADXL345_REG_INT_MAP, int_map); + if (ret) + return ret; + + return regmap_write(st->regmap, ADXL345_REG_INT_ENABLE, int_enable); +} + static int adxl345_read_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val, int *val2, long mask) { - struct adxl345_data *data = iio_priv(indio_dev); + struct adxl345_state *st = iio_priv(indio_dev); __le16 accel; long long samp_freq_nhz; unsigned int regval; @@ -56,7 +114,7 @@ static int adxl345_read_raw(struct iio_dev *indio_dev, * ADXL345_REG_DATA(X0/Y0/Z0) contain the least significant byte * and ADXL345_REG_DATA(X0/Y0/Z0) + 1 the most significant byte */ - ret = regmap_bulk_read(data->regmap, + ret = regmap_bulk_read(st->regmap, ADXL345_REG_DATA_AXIS(chan->address), &accel, sizeof(accel)); if (ret < 0) @@ -66,10 +124,10 @@ static int adxl345_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: *val = 0; - *val2 = data->info->uscale; + *val2 = st->info->uscale; return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_CALIBBIAS: - ret = regmap_read(data->regmap, + ret = regmap_read(st->regmap, ADXL345_REG_OFS_AXIS(chan->address), ®val); if (ret < 0) return ret; @@ -81,7 +139,7 @@ static int adxl345_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; case IIO_CHAN_INFO_SAMP_FREQ: - ret = regmap_read(data->regmap, ADXL345_REG_BW_RATE, ®val); + ret = regmap_read(st->regmap, ADXL345_REG_BW_RATE, ®val); if (ret < 0) return ret; @@ -99,7 +157,7 @@ static int adxl345_write_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int val, int val2, long mask) { - struct adxl345_data *data = iio_priv(indio_dev); + struct adxl345_state *st = iio_priv(indio_dev); s64 n; switch (mask) { @@ -108,14 +166,14 @@ static int adxl345_write_raw(struct iio_dev *indio_dev, * 8-bit resolution at +/- 2g, that is 4x accel data scale * factor */ - return regmap_write(data->regmap, + return regmap_write(st->regmap, ADXL345_REG_OFS_AXIS(chan->address), val / 4); case IIO_CHAN_INFO_SAMP_FREQ: n = div_s64(val * NANOHZ_PER_HZ + val2, ADXL345_BASE_RATE_NANO_HZ); - return regmap_update_bits(data->regmap, ADXL345_REG_BW_RATE, + return regmap_update_bits(st->regmap, ADXL345_REG_BW_RATE, ADXL345_BW_RATE, clamp_val(ilog2(n), 0, ADXL345_BW_RATE)); @@ -124,6 +182,24 @@ static int adxl345_write_raw(struct iio_dev *indio_dev, return -EINVAL; } +static int adxl345_set_watermark(struct iio_dev *indio_dev, unsigned int value) +{ + struct adxl345_state *st = iio_priv(indio_dev); + unsigned int fifo_mask = 0x1F; + int ret; + + value = min(value, ADXL345_FIFO_SIZE - 1); + + ret = regmap_update_bits(st->regmap, ADXL345_REG_FIFO_CTL, fifo_mask, value); + if (ret) + return ret; + + st->watermark = value; + st->int_map |= ADXL345_INT_WATERMARK; + + return 0; +} + static int adxl345_write_raw_get_fmt(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, long mask) @@ -138,6 +214,33 @@ static int adxl345_write_raw_get_fmt(struct iio_dev *indio_dev, } } +/** + * adxl345_set_measure_en() - Enable and disable measuring. + * + * @st: The device data. + * @en: Enable measurements, else standby mode. + * + * For lowest power operation, standby mode can be used. In standby mode, + * current consumption is supposed to be reduced to 0.1uA (typical). In this + * mode no measurements are made. Placing the device into standby mode + * preserves the contents of FIFO. + * + * Return: Returns 0 if successful, or a negative error value. + */ +static int adxl345_set_measure_en(struct adxl345_state *st, bool en) +{ + unsigned int val = en ? ADXL345_POWER_CTL_MEASURE : ADXL345_POWER_CTL_STANDBY; + + return regmap_write(st->regmap, ADXL345_REG_POWER_CTL, val); +} + +static void adxl345_powerdown(void *ptr) +{ + struct adxl345_state *st = ptr; + + adxl345_set_measure_en(st, false); +} + static IIO_CONST_ATTR_SAMP_FREQ_AVAIL( "0.09765625 0.1953125 0.390625 0.78125 1.5625 3.125 6.25 12.5 25 50 100 200 400 800 1600 3200" ); @@ -151,37 +254,244 @@ static const struct attribute_group adxl345_attrs_group = { .attrs = adxl345_attrs, }; +static int adxl345_set_fifo(struct adxl345_state *st) +{ + int ret; + + /* FIFO should only be configured while in standby mode */ + ret = adxl345_set_measure_en(st, false); + if (ret < 0) + return ret; + + ret = regmap_write(st->regmap, ADXL345_REG_FIFO_CTL, + FIELD_PREP(ADXL345_FIFO_CTL_SAMPLES_MSK, + st->watermark) | + FIELD_PREP(ADXL345_FIFO_CTL_TRIGGER_MSK, + st->intio) | + FIELD_PREP(ADXL345_FIFO_CTL_MODE_MSK, + st->fifo_mode)); + if (ret < 0) + return ret; + + return adxl345_set_measure_en(st, true); +} + +/** + * adxl345_get_samples() - Read number of FIFO entries. + * @st: The initialized state instance of this driver. + * + * The sensor does not support treating any axis individually, or exclude them + * from measuring. + * + * Return: negative error, or value. + */ +static int adxl345_get_samples(struct adxl345_state *st) +{ + unsigned int regval = 0; + int ret; + + ret = regmap_read(st->regmap, ADXL345_REG_FIFO_STATUS, ®val); + if (ret < 0) + return ret; + + return FIELD_GET(ADXL345_REG_FIFO_STATUS_MSK, regval); +} + +/** + * adxl345_fifo_transfer() - Read samples number of elements. + * @st: The instance of the state object of this sensor. + * @samples: The number of lines in the FIFO referred to as fifo_entry. + * + * It is recommended that a multiple-byte read of all registers be performed to + * prevent a change in data between reads of sequential registers. That is to + * read out the data registers X0, X1, Y0, Y1, Z0, Z1, i.e. 6 bytes at once. + * + * Return: 0 or error value. + */ +static int adxl345_fifo_transfer(struct adxl345_state *st, int samples) +{ + size_t count; + int i, ret = 0; + + /* count is the 3x the fifo_buf element size, hence 6B */ + count = sizeof(st->fifo_buf[0]) * ADXL345_DIRS; + for (i = 0; i < samples; i++) { + /* read 3x 2 byte elements from base address into next fifo_buf position */ + ret = regmap_bulk_read(st->regmap, ADXL345_REG_XYZ_BASE, + st->fifo_buf + (i * count / 2), count); + if (ret < 0) + return ret; + + /* + * To ensure that the FIFO has completely popped, there must be at least 5 + * us between the end of reading the data registers, signified by the + * transition to register 0x38 from 0x37 or the CS pin going high, and the + * start of new reads of the FIFO or reading the FIFO_STATUS register. For + * SPI operation at 1.5 MHz or lower, the register addressing portion of the + * transmission is sufficient delay to ensure the FIFO has completely + * popped. It is necessary for SPI operation greater than 1.5 MHz to + * de-assert the CS pin to ensure a total of 5 us, which is at most 3.4 us + * at 5 MHz operation. + */ + if (st->fifo_delay && samples > 1) + udelay(3); + } + return ret; +} + +/** + * adxl345_fifo_reset() - Empty the FIFO in error condition. + * @st: The instance to the state object of the sensor. + * + * Read all elements of the FIFO. Reading the interrupt source register + * resets the sensor. + */ +static void adxl345_fifo_reset(struct adxl345_state *st) +{ + int regval; + int samples; + + adxl345_set_measure_en(st, false); + + samples = adxl345_get_samples(st); + if (samples > 0) + adxl345_fifo_transfer(st, samples); + + regmap_read(st->regmap, ADXL345_REG_INT_SOURCE, ®val); + + adxl345_set_measure_en(st, true); +} + +static int adxl345_buffer_postenable(struct iio_dev *indio_dev) +{ + struct adxl345_state *st = iio_priv(indio_dev); + int ret; + + ret = adxl345_set_interrupts(st); + if (ret < 0) + return ret; + + st->fifo_mode = ADXL345_FIFO_STREAM; + return adxl345_set_fifo(st); +} + +static int adxl345_buffer_predisable(struct iio_dev *indio_dev) +{ + struct adxl345_state *st = iio_priv(indio_dev); + int ret; + + st->fifo_mode = ADXL345_FIFO_BYPASS; + ret = adxl345_set_fifo(st); + if (ret < 0) + return ret; + + st->int_map = 0x00; + return adxl345_set_interrupts(st); +} + +static const struct iio_buffer_setup_ops adxl345_buffer_ops = { + .postenable = adxl345_buffer_postenable, + .predisable = adxl345_buffer_predisable, +}; + +static int adxl345_get_status(struct adxl345_state *st) +{ + int ret; + unsigned int regval; + + ret = regmap_read(st->regmap, ADXL345_REG_INT_SOURCE, ®val); + if (ret < 0) + return ret; + + return FIELD_GET(ADXL345_REG_INT_SOURCE_MSK, regval); +} + +static int adxl345_fifo_push(struct iio_dev *indio_dev, + int samples) +{ + struct adxl345_state *st = iio_priv(indio_dev); + int i, ret; + + if (samples <= 0) + return -EINVAL; + + ret = adxl345_fifo_transfer(st, samples); + if (ret) + return ret; + + for (i = 0; i < ADXL345_DIRS * samples; i += ADXL345_DIRS) + iio_push_to_buffers(indio_dev, &st->fifo_buf[i]); + + return 0; +} + +/** + * adxl345_irq_handler() - Handle irqs of the ADXL345. + * @irq: The irq being handled. + * @p: The struct iio_device pointer for the device. + * + * Return: The interrupt was handled. + */ +static irqreturn_t adxl345_irq_handler(int irq, void *p) +{ + struct iio_dev *indio_dev = p; + struct adxl345_state *st = iio_priv(indio_dev); + int int_stat; + int samples; + + int_stat = adxl345_get_status(st); + if (int_stat <= 0) + return IRQ_NONE; + + if (int_stat & ADXL345_INT_OVERRUN) + goto err; + + if (int_stat & ADXL345_INT_WATERMARK) { + samples = adxl345_get_samples(st); + if (samples < 0) + goto err; + + if (adxl345_fifo_push(indio_dev, samples) < 0) + goto err; + } + return IRQ_HANDLED; + +err: + adxl345_fifo_reset(st); + + return IRQ_HANDLED; +} + static const struct iio_info adxl345_info = { .attrs = &adxl345_attrs_group, .read_raw = adxl345_read_raw, .write_raw = adxl345_write_raw, .write_raw_get_fmt = adxl345_write_raw_get_fmt, + .hwfifo_set_watermark = adxl345_set_watermark, }; -static int adxl345_powerup(void *regmap) -{ - return regmap_write(regmap, ADXL345_REG_POWER_CTL, ADXL345_POWER_CTL_MEASURE); -} - -static void adxl345_powerdown(void *regmap) -{ - regmap_write(regmap, ADXL345_REG_POWER_CTL, ADXL345_POWER_CTL_STANDBY); -} - /** - * adxl345_core_probe() - probe and setup for the adxl345 accelerometer, - * also covers the adlx375 accelerometer + * adxl345_core_probe() - Probe and setup for the accelerometer. * @dev: Driver model representation of the device * @regmap: Regmap instance for the device + * @fifo_delay_default: Using FIFO with SPI needs delay * @setup: Setup routine to be executed right before the standard device * setup * + * For SPI operation greater than 1.6 MHz, it is necessary to deassert the CS + * pin to ensure a total delay of 5 us; otherwise, the delay is not sufficient. + * The total delay necessary for 5 MHz operation is at most 3.4 us. This is not + * a concern when using I2C mode because the communication rate is low enough + * to ensure a sufficient delay between FIFO reads. + * Ref: "Retrieving Data from FIFO", p. 21 of 36, Data Sheet ADXL345 Rev. G + * * Return: 0 on success, negative errno on error */ int adxl345_core_probe(struct device *dev, struct regmap *regmap, + bool fifo_delay_default, int (*setup)(struct device*, struct regmap*)) { - struct adxl345_data *data; + struct adxl345_state *st; struct iio_dev *indio_dev; u32 regval; unsigned int data_format_mask = (ADXL345_DATA_FORMAT_RANGE | @@ -190,30 +500,32 @@ int adxl345_core_probe(struct device *dev, struct regmap *regmap, ADXL345_DATA_FORMAT_SELF_TEST); int ret; - indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); + indio_dev = devm_iio_device_alloc(dev, sizeof(*st)); if (!indio_dev) return -ENOMEM; - data = iio_priv(indio_dev); - data->regmap = regmap; - data->info = device_get_match_data(dev); - if (!data->info) + st = iio_priv(indio_dev); + st->regmap = regmap; + st->info = device_get_match_data(dev); + if (!st->info) return -ENODEV; + st->fifo_delay = fifo_delay_default; - indio_dev->name = data->info->name; + indio_dev->name = st->info->name; indio_dev->info = &adxl345_info; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = adxl345_channels; indio_dev->num_channels = ARRAY_SIZE(adxl345_channels); + indio_dev->available_scan_masks = adxl345_scan_masks; if (setup) { /* Perform optional initial bus specific configuration */ - ret = setup(dev, data->regmap); + ret = setup(dev, st->regmap); if (ret) return ret; /* Enable full-resolution mode */ - ret = regmap_update_bits(data->regmap, ADXL345_REG_DATA_FORMAT, + ret = regmap_update_bits(st->regmap, ADXL345_REG_DATA_FORMAT, data_format_mask, ADXL345_DATA_FORMAT_FULL_RES); if (ret) @@ -222,14 +534,14 @@ int adxl345_core_probe(struct device *dev, struct regmap *regmap, } else { /* Enable full-resolution mode (init all data_format bits) */ - ret = regmap_write(data->regmap, ADXL345_REG_DATA_FORMAT, + ret = regmap_write(st->regmap, ADXL345_REG_DATA_FORMAT, ADXL345_DATA_FORMAT_FULL_RES); if (ret) return dev_err_probe(dev, ret, "Failed to set data range\n"); } - ret = regmap_read(data->regmap, ADXL345_REG_DEVID, ®val); + ret = regmap_read(st->regmap, ADXL345_REG_DEVID, ®val); if (ret < 0) return dev_err_probe(dev, ret, "Error reading device ID\n"); @@ -238,14 +550,43 @@ int adxl345_core_probe(struct device *dev, struct regmap *regmap, regval, ADXL345_DEVID); /* Enable measurement mode */ - ret = adxl345_powerup(data->regmap); + ret = adxl345_set_measure_en(st, true); if (ret < 0) return dev_err_probe(dev, ret, "Failed to enable measurement mode\n"); - ret = devm_add_action_or_reset(dev, adxl345_powerdown, data->regmap); + ret = devm_add_action_or_reset(dev, adxl345_powerdown, st); if (ret < 0) return ret; + st->intio = ADXL345_INT1; + st->irq = fwnode_irq_get_byname(dev_fwnode(dev), "INT1"); + if (st->irq < 0) { + st->intio = ADXL345_INT2; + st->irq = fwnode_irq_get_byname(dev_fwnode(dev), "INT2"); + if (st->irq < 0) + st->intio = ADXL345_INT_NONE; + } + + if (st->intio != ADXL345_INT_NONE) { + /* FIFO_STREAM mode is going to be activated later */ + ret = devm_iio_kfifo_buffer_setup(dev, indio_dev, &adxl345_buffer_ops); + if (ret) + return ret; + + ret = devm_request_threaded_irq(dev, st->irq, NULL, + &adxl345_irq_handler, + IRQF_SHARED | IRQF_ONESHOT, + indio_dev->name, indio_dev); + if (ret) + return ret; + } else { + ret = regmap_write(st->regmap, ADXL345_REG_FIFO_CTL, + FIELD_PREP(ADXL345_FIFO_CTL_MODE_MSK, + ADXL345_FIFO_BYPASS)); + if (ret < 0) + return ret; + } + return devm_iio_device_register(dev, indio_dev); } EXPORT_SYMBOL_NS_GPL(adxl345_core_probe, "IIO_ADXL345"); diff --git a/drivers/iio/accel/adxl345_i2c.c b/drivers/iio/accel/adxl345_i2c.c index cb23fb11fcd7..8c385dd6c01d 100644 --- a/drivers/iio/accel/adxl345_i2c.c +++ b/drivers/iio/accel/adxl345_i2c.c @@ -27,7 +27,7 @@ static int adxl345_i2c_probe(struct i2c_client *client) if (IS_ERR(regmap)) return dev_err_probe(&client->dev, PTR_ERR(regmap), "Error initializing regmap\n"); - return adxl345_core_probe(&client->dev, regmap, NULL); + return adxl345_core_probe(&client->dev, regmap, false, NULL); } static const struct adxl345_chip_info adxl345_i2c_info = { diff --git a/drivers/iio/accel/adxl345_spi.c b/drivers/iio/accel/adxl345_spi.c index 968e7b390d4b..7e518aea17bf 100644 --- a/drivers/iio/accel/adxl345_spi.c +++ b/drivers/iio/accel/adxl345_spi.c @@ -12,6 +12,7 @@ #include "adxl345.h" #define ADXL345_MAX_SPI_FREQ_HZ 5000000 +#define ADXL345_MAX_FREQ_NO_FIFO_DELAY 1500000 static const struct regmap_config adxl345_spi_regmap_config = { .reg_bits = 8, @@ -28,6 +29,7 @@ static int adxl345_spi_setup(struct device *dev, struct regmap *regmap) static int adxl345_spi_probe(struct spi_device *spi) { struct regmap *regmap; + bool needs_delay; /* Bail out if max_speed_hz exceeds 5 MHz */ if (spi->max_speed_hz > ADXL345_MAX_SPI_FREQ_HZ) @@ -38,10 +40,11 @@ static int adxl345_spi_probe(struct spi_device *spi) if (IS_ERR(regmap)) return dev_err_probe(&spi->dev, PTR_ERR(regmap), "Error initializing regmap\n"); + needs_delay = spi->max_speed_hz > ADXL345_MAX_FREQ_NO_FIFO_DELAY; if (spi->mode & SPI_3WIRE) - return adxl345_core_probe(&spi->dev, regmap, adxl345_spi_setup); + return adxl345_core_probe(&spi->dev, regmap, needs_delay, adxl345_spi_setup); else - return adxl345_core_probe(&spi->dev, regmap, NULL); + return adxl345_core_probe(&spi->dev, regmap, needs_delay, NULL); } static const struct adxl345_chip_info adxl345_spi_info = { diff --git a/drivers/iio/accel/bma220_spi.c b/drivers/iio/accel/bma220_spi.c index 009e6243c6cb..96ba028157ee 100644 --- a/drivers/iio/accel/bma220_spi.c +++ b/drivers/iio/accel/bma220_spi.c @@ -66,7 +66,7 @@ struct bma220_data { struct { s8 chans[3]; /* Ensure timestamp is naturally aligned. */ - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; u8 tx_buf[2] __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c index 65aac60f1245..987212a7c038 100644 --- a/drivers/iio/accel/fxls8962af-core.c +++ b/drivers/iio/accel/fxls8962af-core.c @@ -129,6 +129,8 @@ #define FXLS8962AF_DEVICE_ID 0x62 #define FXLS8964AF_DEVICE_ID 0x84 +#define FXLS8974CF_DEVICE_ID 0x86 +#define FXLS8967AF_DEVICE_ID 0x87 /* Raw temp channel offset */ #define FXLS8962AF_TEMP_CENTER_VAL 25 @@ -766,6 +768,18 @@ static const struct fxls8962af_chip_info fxls_chip_info_table[] = { .channels = fxls8962af_channels, .num_channels = ARRAY_SIZE(fxls8962af_channels), }, + [fxls8967af] = { + .chip_id = FXLS8967AF_DEVICE_ID, + .name = "fxls8967af", + .channels = fxls8962af_channels, + .num_channels = ARRAY_SIZE(fxls8962af_channels), + }, + [fxls8974cf] = { + .chip_id = FXLS8974CF_DEVICE_ID, + .name = "fxls8974cf", + .channels = fxls8962af_channels, + .num_channels = ARRAY_SIZE(fxls8962af_channels), + }, }; static const struct iio_info fxls8962af_info = { diff --git a/drivers/iio/accel/fxls8962af-i2c.c b/drivers/iio/accel/fxls8962af-i2c.c index 2e1bb43ef2a1..1b9156b6b2e3 100644 --- a/drivers/iio/accel/fxls8962af-i2c.c +++ b/drivers/iio/accel/fxls8962af-i2c.c @@ -30,6 +30,8 @@ static int fxls8962af_probe(struct i2c_client *client) static const struct i2c_device_id fxls8962af_id[] = { { "fxls8962af", fxls8962af }, { "fxls8964af", fxls8964af }, + { "fxls8967af", fxls8967af }, + { "fxls8974cf", fxls8974cf }, {} }; MODULE_DEVICE_TABLE(i2c, fxls8962af_id); diff --git a/drivers/iio/accel/fxls8962af.h b/drivers/iio/accel/fxls8962af.h index 6eaa2803b26f..1c9adfc8c0dc 100644 --- a/drivers/iio/accel/fxls8962af.h +++ b/drivers/iio/accel/fxls8962af.h @@ -11,6 +11,8 @@ struct device; enum { fxls8962af, fxls8964af, + fxls8967af, + fxls8974cf, }; int fxls8962af_core_probe(struct device *dev, struct regmap *regmap, int irq); diff --git a/drivers/iio/accel/kionix-kx022a-i2c.c b/drivers/iio/accel/kionix-kx022a-i2c.c index b39a43ecadff..42388636ca31 100644 --- a/drivers/iio/accel/kionix-kx022a-i2c.c +++ b/drivers/iio/accel/kionix-kx022a-i2c.c @@ -38,7 +38,9 @@ static int kx022a_i2c_probe(struct i2c_client *i2c) static const struct i2c_device_id kx022a_i2c_id[] = { { .name = "kx022a", .driver_data = (kernel_ulong_t)&kx022a_chip_info }, { .name = "kx132-1211", .driver_data = (kernel_ulong_t)&kx132_chip_info }, + { .name = "kx134-1211", .driver_data = (kernel_ulong_t)&kx134_chip_info }, { .name = "kx132acr-lbz", .driver_data = (kernel_ulong_t)&kx132acr_chip_info }, + { .name = "kx134acr-lbz", .driver_data = (kernel_ulong_t)&kx134acr_chip_info }, { } }; MODULE_DEVICE_TABLE(i2c, kx022a_i2c_id); @@ -46,7 +48,9 @@ MODULE_DEVICE_TABLE(i2c, kx022a_i2c_id); static const struct of_device_id kx022a_of_match[] = { { .compatible = "kionix,kx022a", .data = &kx022a_chip_info }, { .compatible = "kionix,kx132-1211", .data = &kx132_chip_info }, + { .compatible = "kionix,kx134-1211", .data = &kx134_chip_info }, { .compatible = "rohm,kx132acr-lbz", .data = &kx132acr_chip_info }, + { .compatible = "rohm,kx134acr-lbz", .data = &kx134acr_chip_info }, { } }; MODULE_DEVICE_TABLE(of, kx022a_of_match); diff --git a/drivers/iio/accel/kionix-kx022a-spi.c b/drivers/iio/accel/kionix-kx022a-spi.c index c38a47806a00..e30d21083dc8 100644 --- a/drivers/iio/accel/kionix-kx022a-spi.c +++ b/drivers/iio/accel/kionix-kx022a-spi.c @@ -38,7 +38,9 @@ static int kx022a_spi_probe(struct spi_device *spi) static const struct spi_device_id kx022a_id[] = { { .name = "kx022a", .driver_data = (kernel_ulong_t)&kx022a_chip_info }, { .name = "kx132-1211", .driver_data = (kernel_ulong_t)&kx132_chip_info }, + { .name = "kx134-1211", .driver_data = (kernel_ulong_t)&kx134_chip_info }, { .name = "kx132acr-lbz", .driver_data = (kernel_ulong_t)&kx132acr_chip_info }, + { .name = "kx134acr-lbz", .driver_data = (kernel_ulong_t)&kx134acr_chip_info }, { } }; MODULE_DEVICE_TABLE(spi, kx022a_id); @@ -46,7 +48,9 @@ MODULE_DEVICE_TABLE(spi, kx022a_id); static const struct of_device_id kx022a_of_match[] = { { .compatible = "kionix,kx022a", .data = &kx022a_chip_info }, { .compatible = "kionix,kx132-1211", .data = &kx132_chip_info }, + { .compatible = "kionix,kx134-1211", .data = &kx134_chip_info }, { .compatible = "rohm,kx132acr-lbz", .data = &kx132acr_chip_info }, + { .compatible = "rohm,kx134acr-lbz", .data = &kx134acr_chip_info }, { } }; MODULE_DEVICE_TABLE(of, kx022a_of_match); diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c index 670bac21965b..5aeb3b951ac5 100644 --- a/drivers/iio/accel/kionix-kx022a.c +++ b/drivers/iio/accel/kionix-kx022a.c @@ -5,6 +5,7 @@ * ROHM/KIONIX accelerometer driver */ +#include #include #include #include @@ -407,11 +408,21 @@ static const int kx022a_scale_table[][2] = { { 0, 4788403 }, }; +/* KX134ACR-LBZ ranges are (+/-) 8, 16, 32, 64 G */ +static const int kx134acr_lbz_scale_table[][2] = { + { 0, 2394202 }, + { 0, 4788403 }, + { 0, 9576807 }, + { 0, 19153613 }, +}; + static int kx022a_read_avail(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, const int **vals, int *type, int *length, long mask) { + struct kx022a_data *data = iio_priv(indio_dev); + switch (mask) { case IIO_CHAN_INFO_SAMP_FREQ: *vals = (const int *)kx022a_accel_samp_freq_table; @@ -420,9 +431,8 @@ static int kx022a_read_avail(struct iio_dev *indio_dev, *type = IIO_VAL_INT_PLUS_MICRO; return IIO_AVAIL_LIST; case IIO_CHAN_INFO_SCALE: - *vals = (const int *)kx022a_scale_table; - *length = ARRAY_SIZE(kx022a_scale_table) * - ARRAY_SIZE(kx022a_scale_table[0]); + *vals = (const int *)data->chip_info->scale_table; + *length = data->chip_info->scale_table_size; *type = IIO_VAL_INT_PLUS_NANO; return IIO_AVAIL_LIST; default: @@ -438,17 +448,17 @@ static void kx022a_reg2freq(unsigned int val, int *val1, int *val2) *val2 = kx022a_accel_samp_freq_table[val & KX022A_MASK_ODR][1]; } -static void kx022a_reg2scale(unsigned int val, unsigned int *val1, - unsigned int *val2) +static void kx022a_reg2scale(struct kx022a_data *data, unsigned int val, + unsigned int *val1, unsigned int *val2) { val &= KX022A_MASK_GSEL; val >>= KX022A_GSEL_SHIFT; - *val1 = kx022a_scale_table[val][0]; - *val2 = kx022a_scale_table[val][1]; + *val1 = data->chip_info->scale_table[val][0]; + *val2 = data->chip_info->scale_table[val][1]; } -static int kx022a_turn_on_off_unlocked(struct kx022a_data *data, bool on) +static int __kx022a_turn_on_off(struct kx022a_data *data, bool on) { int ret; @@ -469,7 +479,7 @@ static int kx022a_turn_off_lock(struct kx022a_data *data) int ret; mutex_lock(&data->mutex); - ret = kx022a_turn_on_off_unlocked(data, false); + ret = __kx022a_turn_on_off(data, false); if (ret) mutex_unlock(&data->mutex); @@ -480,7 +490,7 @@ static int kx022a_turn_on_unlock(struct kx022a_data *data) { int ret; - ret = kx022a_turn_on_off_unlocked(data, true); + ret = __kx022a_turn_on_off(data, true); mutex_unlock(&data->mutex); return ret; @@ -543,11 +553,11 @@ static int kx022a_write_raw(struct iio_dev *idev, kx022a_turn_on_unlock(data); break; case IIO_CHAN_INFO_SCALE: - n = ARRAY_SIZE(kx022a_scale_table); + n = data->chip_info->scale_table_size / 2; while (n-- > 0) - if (val == kx022a_scale_table[n][0] && - val2 == kx022a_scale_table[n][1]) + if (val == data->chip_info->scale_table[n][0] && + val2 == data->chip_info->scale_table[n][1]) break; if (n < 0) { ret = -EINVAL; @@ -642,7 +652,7 @@ static int kx022a_read_raw(struct iio_dev *idev, if (ret < 0) return ret; - kx022a_reg2scale(regval, val, val2); + kx022a_reg2scale(data, regval, val, val2); return IIO_VAL_INT_PLUS_NANO; } @@ -912,18 +922,19 @@ static int kx022a_fifo_disable(struct kx022a_data *data) { int ret = 0; - ret = kx022a_turn_off_lock(data); + guard(mutex)(&data->mutex); + ret = __kx022a_turn_on_off(data, false); if (ret) return ret; ret = regmap_clear_bits(data->regmap, data->ien_reg, KX022A_MASK_WMI); if (ret) - goto unlock_out; + return ret; ret = regmap_clear_bits(data->regmap, data->chip_info->buf_cntl2, KX022A_MASK_BUF_EN); if (ret) - goto unlock_out; + return ret; data->state &= ~KX022A_STATE_FIFO; @@ -931,12 +942,7 @@ static int kx022a_fifo_disable(struct kx022a_data *data) kfree(data->fifo_buffer); - return kx022a_turn_on_unlock(data); - -unlock_out: - mutex_unlock(&data->mutex); - - return ret; + return __kx022a_turn_on_off(data, true); } static int kx022a_buffer_predisable(struct iio_dev *idev) @@ -959,33 +965,29 @@ static int kx022a_fifo_enable(struct kx022a_data *data) if (!data->fifo_buffer) return -ENOMEM; - ret = kx022a_turn_off_lock(data); + guard(mutex)(&data->mutex); + ret = __kx022a_turn_on_off(data, false); if (ret) return ret; /* Update watermark to HW */ ret = kx022a_fifo_set_wmi(data); if (ret) - goto unlock_out; + return ret; /* Enable buffer */ ret = regmap_set_bits(data->regmap, data->chip_info->buf_cntl2, KX022A_MASK_BUF_EN); if (ret) - goto unlock_out; + return ret; data->state |= KX022A_STATE_FIFO; ret = regmap_set_bits(data->regmap, data->ien_reg, KX022A_MASK_WMI); if (ret) - goto unlock_out; + return ret; - return kx022a_turn_on_unlock(data); - -unlock_out: - mutex_unlock(&data->mutex); - - return ret; + return __kx022a_turn_on_off(data, true); } static int kx022a_buffer_postenable(struct iio_dev *idev) @@ -1053,7 +1055,7 @@ static irqreturn_t kx022a_irq_thread_handler(int irq, void *private) struct kx022a_data *data = iio_priv(idev); irqreturn_t ret = IRQ_NONE; - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); if (data->trigger_enabled) { iio_trigger_poll_nested(data->trig); @@ -1068,8 +1070,6 @@ static irqreturn_t kx022a_irq_thread_handler(int irq, void *private) ret = IRQ_HANDLED; } - mutex_unlock(&data->mutex); - return ret; } @@ -1079,32 +1079,26 @@ static int kx022a_trigger_set_state(struct iio_trigger *trig, struct kx022a_data *data = iio_trigger_get_drvdata(trig); int ret = 0; - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); if (data->trigger_enabled == state) - goto unlock_out; + return 0; if (data->state & KX022A_STATE_FIFO) { dev_warn(data->dev, "Can't set trigger when FIFO enabled\n"); - ret = -EBUSY; - goto unlock_out; + return -EBUSY; } - ret = kx022a_turn_on_off_unlocked(data, false); + ret = __kx022a_turn_on_off(data, false); if (ret) - goto unlock_out; + return ret; data->trigger_enabled = state; ret = kx022a_set_drdy_irq(data, state); if (ret) - goto unlock_out; + return ret; - ret = kx022a_turn_on_off_unlocked(data, true); - -unlock_out: - mutex_unlock(&data->mutex); - - return ret; + return __kx022a_turn_on_off(data, true); } static const struct iio_trigger_ops kx022a_trigger_ops = { @@ -1121,10 +1115,15 @@ static int kx022a_chip_init(struct kx022a_data *data) return ret; /* - * I've seen I2C read failures if we poll too fast after the sensor - * reset. Slight delay gives I2C block the time to recover. + * According to the power-on procedure documents, there is (at least) + * 2ms delay required after the software reset. This should be same for + * all, KX022ACR-Z, KX132-1211, KX132ACR-LBZ and KX134ACR-LBZ. + * + * https://fscdn.rohm.com/kionix/en/document/AN010_KX022ACR-Z_Power-on_Procedure_E.pdf + * https://fscdn.rohm.com/kionix/en/document/TN027-Power-On-Procedure.pdf + * https://fscdn.rohm.com/kionix/en/document/AN011_KX134ACR-LBZ_Power-on_Procedure_E.pdf */ - msleep(1); + msleep(2); ret = regmap_read_poll_timeout(data->regmap, data->chip_info->cntl2, val, !(val & KX022A_MASK_SRST), @@ -1158,6 +1157,9 @@ const struct kx022a_chip_info kx022a_chip_info = { .regmap_config = &kx022a_regmap_config, .channels = kx022a_channels, .num_channels = ARRAY_SIZE(kx022a_channels), + .scale_table = kx022a_scale_table, + .scale_table_size = ARRAY_SIZE(kx022a_scale_table) * + ARRAY_SIZE(kx022a_scale_table[0]), .fifo_length = KX022A_FIFO_LENGTH, .who = KX022A_REG_WHO, .id = KX022A_ID, @@ -1183,6 +1185,9 @@ const struct kx022a_chip_info kx132_chip_info = { .regmap_config = &kx132_regmap_config, .channels = kx132_channels, .num_channels = ARRAY_SIZE(kx132_channels), + .scale_table = kx022a_scale_table, + .scale_table_size = ARRAY_SIZE(kx022a_scale_table) * + ARRAY_SIZE(kx022a_scale_table[0]), .fifo_length = KX132_FIFO_LENGTH, .who = KX132_REG_WHO, .id = KX132_ID, @@ -1204,6 +1209,35 @@ const struct kx022a_chip_info kx132_chip_info = { }; EXPORT_SYMBOL_NS_GPL(kx132_chip_info, "IIO_KX022A"); +const struct kx022a_chip_info kx134_chip_info = { + .name = "kx134-1211", + .regmap_config = &kx132_regmap_config, + .channels = kx132_channels, + .num_channels = ARRAY_SIZE(kx132_channels), + .scale_table = kx134acr_lbz_scale_table, + .scale_table_size = ARRAY_SIZE(kx134acr_lbz_scale_table) * + ARRAY_SIZE(kx134acr_lbz_scale_table[0]), + .fifo_length = KX132_FIFO_LENGTH, + .who = KX132_REG_WHO, + .id = KX134_1211_ID, + .cntl = KX132_REG_CNTL, + .cntl2 = KX132_REG_CNTL2, + .odcntl = KX132_REG_ODCNTL, + .buf_cntl1 = KX132_REG_BUF_CNTL1, + .buf_cntl2 = KX132_REG_BUF_CNTL2, + .buf_clear = KX132_REG_BUF_CLEAR, + .buf_status1 = KX132_REG_BUF_STATUS_1, + .buf_smp_lvl_mask = KX132_MASK_BUF_SMP_LVL, + .buf_read = KX132_REG_BUF_READ, + .inc1 = KX132_REG_INC1, + .inc4 = KX132_REG_INC4, + .inc5 = KX132_REG_INC5, + .inc6 = KX132_REG_INC6, + .xout_l = KX132_REG_XOUT_L, + .get_fifo_bytes_available = kx132_get_fifo_bytes_available, +}; +EXPORT_SYMBOL_NS_GPL(kx134_chip_info, "IIO_KX022A"); + /* * Despite the naming, KX132ACR-LBZ is not similar to KX132-1211 but it is * exact subset of KX022A. KX132ACR-LBZ is meant to be used for industrial @@ -1216,6 +1250,9 @@ const struct kx022a_chip_info kx132acr_chip_info = { .regmap_config = &kx022a_regmap_config, .channels = kx022a_channels, .num_channels = ARRAY_SIZE(kx022a_channels), + .scale_table = kx022a_scale_table, + .scale_table_size = ARRAY_SIZE(kx022a_scale_table) * + ARRAY_SIZE(kx022a_scale_table[0]), .fifo_length = KX022A_FIFO_LENGTH, .who = KX022A_REG_WHO, .id = KX132ACR_LBZ_ID, @@ -1236,6 +1273,34 @@ const struct kx022a_chip_info kx132acr_chip_info = { }; EXPORT_SYMBOL_NS_GPL(kx132acr_chip_info, "IIO_KX022A"); +const struct kx022a_chip_info kx134acr_chip_info = { + .name = "kx134acr-lbz", + .regmap_config = &kx022a_regmap_config, + .channels = kx022a_channels, + .num_channels = ARRAY_SIZE(kx022a_channels), + .scale_table = kx134acr_lbz_scale_table, + .scale_table_size = ARRAY_SIZE(kx134acr_lbz_scale_table) * + ARRAY_SIZE(kx134acr_lbz_scale_table[0]), + .fifo_length = KX022A_FIFO_LENGTH, + .who = KX022A_REG_WHO, + .id = KX134ACR_LBZ_ID, + .cntl = KX022A_REG_CNTL, + .cntl2 = KX022A_REG_CNTL2, + .odcntl = KX022A_REG_ODCNTL, + .buf_cntl1 = KX022A_REG_BUF_CNTL1, + .buf_cntl2 = KX022A_REG_BUF_CNTL2, + .buf_clear = KX022A_REG_BUF_CLEAR, + .buf_status1 = KX022A_REG_BUF_STATUS_1, + .buf_read = KX022A_REG_BUF_READ, + .inc1 = KX022A_REG_INC1, + .inc4 = KX022A_REG_INC4, + .inc5 = KX022A_REG_INC5, + .inc6 = KX022A_REG_INC6, + .xout_l = KX022A_REG_XOUT_L, + .get_fifo_bytes_available = kx022a_get_fifo_bytes_available, +}; +EXPORT_SYMBOL_NS_GPL(kx134acr_chip_info, "IIO_KX022A"); + int kx022a_probe_internal(struct device *dev, const struct kx022a_chip_info *chip_info) { static const char * const regulator_names[] = {"io-vdd", "vdd"}; diff --git a/drivers/iio/accel/kionix-kx022a.h b/drivers/iio/accel/kionix-kx022a.h index 7060438ad88c..0ed54f584223 100644 --- a/drivers/iio/accel/kionix-kx022a.h +++ b/drivers/iio/accel/kionix-kx022a.h @@ -14,6 +14,7 @@ #define KX022A_REG_WHO 0x0f #define KX022A_ID 0xc8 #define KX132ACR_LBZ_ID 0xd8 +#define KX134ACR_LBZ_ID 0xcc #define KX022A_REG_CNTL2 0x19 #define KX022A_MASK_SRST BIT(7) @@ -77,6 +78,7 @@ #define KX132_REG_WHO 0x13 #define KX132_ID 0x3d +#define KX134_1211_ID 0x46 #define KX132_FIFO_LENGTH 86 @@ -135,6 +137,14 @@ struct kx022a_data; * * @name: name of the device * @regmap_config: pointer to register map configuration + * @scale_table: An array of tables of scaling factors for + * a supported acceleration measurement range. + * Each table containing a single scaling + * factor consisting of two integers. The first + * value in a table is the integer part, and + * the second value is the fractional part as + * parts per billion. + * @scale_table_size: Amount of values in tables. * @channels: pointer to iio_chan_spec array * @num_channels: number of iio_chan_spec channels * @fifo_length: number of 16-bit samples in a full buffer @@ -161,6 +171,8 @@ struct kx022a_data; struct kx022a_chip_info { const char *name; const struct regmap_config *regmap_config; + const int (*scale_table)[2]; + const int scale_table_size; const struct iio_chan_spec *channels; unsigned int num_channels; unsigned int fifo_length; @@ -187,6 +199,8 @@ int kx022a_probe_internal(struct device *dev, const struct kx022a_chip_info *chi extern const struct kx022a_chip_info kx022a_chip_info; extern const struct kx022a_chip_info kx132_chip_info; +extern const struct kx022a_chip_info kx134_chip_info; extern const struct kx022a_chip_info kx132acr_chip_info; +extern const struct kx022a_chip_info kx134acr_chip_info; #endif diff --git a/drivers/iio/adc/ad4000.c b/drivers/iio/adc/ad4000.c index b3b82535f5c1..1d556a842a68 100644 --- a/drivers/iio/adc/ad4000.c +++ b/drivers/iio/adc/ad4000.c @@ -35,10 +35,6 @@ #define AD4000_SCALE_OPTIONS 2 -#define AD4000_TQUIET1_NS 190 -#define AD4000_TQUIET2_NS 60 -#define AD4000_TCONV_NS 320 - #define __AD4000_DIFF_CHANNEL(_sign, _real_bits, _storage_bits, _reg_access) \ { \ .type = IIO_VOLTAGE, \ @@ -49,6 +45,7 @@ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ BIT(IIO_CHAN_INFO_SCALE), \ .info_mask_separate_available = _reg_access ? BIT(IIO_CHAN_INFO_SCALE) : 0,\ + .scan_index = 0, \ .scan_type = { \ .sign = _sign, \ .realbits = _real_bits, \ @@ -62,6 +59,12 @@ __AD4000_DIFF_CHANNEL((_sign), (_real_bits), \ ((_real_bits) > 16 ? 32 : 16), (_reg_access)) +#define AD4000_DIFF_CHANNELS(_sign, _real_bits, _reg_access) \ +{ \ + AD4000_DIFF_CHANNEL(_sign, _real_bits, _reg_access), \ + IIO_CHAN_SOFT_TIMESTAMP(1), \ +} + #define __AD4000_PSEUDO_DIFF_CHANNEL(_sign, _real_bits, _storage_bits, _reg_access)\ { \ .type = IIO_VOLTAGE, \ @@ -71,6 +74,7 @@ BIT(IIO_CHAN_INFO_SCALE) | \ BIT(IIO_CHAN_INFO_OFFSET), \ .info_mask_separate_available = _reg_access ? BIT(IIO_CHAN_INFO_SCALE) : 0,\ + .scan_index = 0, \ .scan_type = { \ .sign = _sign, \ .realbits = _real_bits, \ @@ -84,6 +88,12 @@ __AD4000_PSEUDO_DIFF_CHANNEL((_sign), (_real_bits), \ ((_real_bits) > 16 ? 32 : 16), (_reg_access)) +#define AD4000_PSEUDO_DIFF_CHANNELS(_sign, _real_bits, _reg_access) \ +{ \ + AD4000_PSEUDO_DIFF_CHANNEL(_sign, _real_bits, _reg_access), \ + IIO_CHAN_SOFT_TIMESTAMP(1), \ +} + static const char * const ad4000_power_supplies[] = { "vdd", "vio" }; @@ -108,111 +118,280 @@ static const int ad4000_gains[] = { 454, 909, 1000, 1900, }; +struct ad4000_time_spec { + int t_conv_ns; + int t_quiet2_ns; +}; + +/* + * Same timing specifications for all of AD4000, AD4001, ..., AD4008, AD4010, + * ADAQ4001, and ADAQ4003. + */ +static const struct ad4000_time_spec ad4000_t_spec = { + .t_conv_ns = 320, + .t_quiet2_ns = 60, +}; + +/* AD4020, AD4021, AD4022 */ +static const struct ad4000_time_spec ad4020_t_spec = { + .t_conv_ns = 350, + .t_quiet2_ns = 60, +}; + +/* AD7983, AD7984 */ +static const struct ad4000_time_spec ad7983_t_spec = { + .t_conv_ns = 500, + .t_quiet2_ns = 0, +}; + +/* AD7980, AD7982 */ +static const struct ad4000_time_spec ad7980_t_spec = { + .t_conv_ns = 800, + .t_quiet2_ns = 0, +}; + +/* AD7946, AD7686, AD7688, AD7988-5, AD7693 */ +static const struct ad4000_time_spec ad7686_t_spec = { + .t_conv_ns = 1600, + .t_quiet2_ns = 0, +}; + +/* AD7690 */ +static const struct ad4000_time_spec ad7690_t_spec = { + .t_conv_ns = 2100, + .t_quiet2_ns = 0, +}; + +/* AD7942, AD7685, AD7687 */ +static const struct ad4000_time_spec ad7687_t_spec = { + .t_conv_ns = 3200, + .t_quiet2_ns = 0, +}; + +/* AD7691 */ +static const struct ad4000_time_spec ad7691_t_spec = { + .t_conv_ns = 3700, + .t_quiet2_ns = 0, +}; + +/* AD7988-1 */ +static const struct ad4000_time_spec ad7988_1_t_spec = { + .t_conv_ns = 9500, + .t_quiet2_ns = 0, +}; + struct ad4000_chip_info { const char *dev_name; - struct iio_chan_spec chan_spec; - struct iio_chan_spec reg_access_chan_spec; + struct iio_chan_spec chan_spec[2]; + struct iio_chan_spec reg_access_chan_spec[2]; + const struct ad4000_time_spec *time_spec; bool has_hardware_gain; }; static const struct ad4000_chip_info ad4000_chip_info = { .dev_name = "ad4000", - .chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 0), - .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 1), + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0), + .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4001_chip_info = { .dev_name = "ad4001", - .chan_spec = AD4000_DIFF_CHANNEL('s', 16, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 16, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 16, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4002_chip_info = { .dev_name = "ad4002", - .chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 0), - .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 1), + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 0), + .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4003_chip_info = { .dev_name = "ad4003", - .chan_spec = AD4000_DIFF_CHANNEL('s', 18, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 18, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 18, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4004_chip_info = { .dev_name = "ad4004", - .chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 0), - .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 1), + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0), + .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4005_chip_info = { .dev_name = "ad4005", - .chan_spec = AD4000_DIFF_CHANNEL('s', 16, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 16, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 16, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4006_chip_info = { .dev_name = "ad4006", - .chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 0), - .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 1), + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 0), + .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4007_chip_info = { .dev_name = "ad4007", - .chan_spec = AD4000_DIFF_CHANNEL('s', 18, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 18, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 18, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4008_chip_info = { .dev_name = "ad4008", - .chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 0), - .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 1), + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0), + .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4010_chip_info = { .dev_name = "ad4010", - .chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 0), - .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 1), + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 0), + .reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4011_chip_info = { .dev_name = "ad4011", - .chan_spec = AD4000_DIFF_CHANNEL('s', 18, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 18, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 18, 1), + .time_spec = &ad4000_t_spec, }; static const struct ad4000_chip_info ad4020_chip_info = { .dev_name = "ad4020", - .chan_spec = AD4000_DIFF_CHANNEL('s', 20, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 20, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 20, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 20, 1), + .time_spec = &ad4020_t_spec, }; static const struct ad4000_chip_info ad4021_chip_info = { .dev_name = "ad4021", - .chan_spec = AD4000_DIFF_CHANNEL('s', 20, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 20, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 20, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 20, 1), + .time_spec = &ad4020_t_spec, }; static const struct ad4000_chip_info ad4022_chip_info = { .dev_name = "ad4022", - .chan_spec = AD4000_DIFF_CHANNEL('s', 20, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 20, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 20, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 20, 1), + .time_spec = &ad4020_t_spec, }; static const struct ad4000_chip_info adaq4001_chip_info = { .dev_name = "adaq4001", - .chan_spec = AD4000_DIFF_CHANNEL('s', 16, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 16, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 16, 1), + .time_spec = &ad4000_t_spec, .has_hardware_gain = true, }; static const struct ad4000_chip_info adaq4003_chip_info = { .dev_name = "adaq4003", - .chan_spec = AD4000_DIFF_CHANNEL('s', 18, 0), - .reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 18, 1), + .chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0), + .reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 18, 1), + .time_spec = &ad4000_t_spec, .has_hardware_gain = true, }; +static const struct ad4000_chip_info ad7685_chip_info = { + .dev_name = "ad7685", + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0), + .time_spec = &ad7687_t_spec, +}; + +static const struct ad4000_chip_info ad7686_chip_info = { + .dev_name = "ad7686", + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0), + .time_spec = &ad7686_t_spec, +}; + +static const struct ad4000_chip_info ad7687_chip_info = { + .dev_name = "ad7687", + .chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0), + .time_spec = &ad7687_t_spec, +}; + +static const struct ad4000_chip_info ad7688_chip_info = { + .dev_name = "ad7688", + .chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0), + .time_spec = &ad7686_t_spec, +}; + +static const struct ad4000_chip_info ad7690_chip_info = { + .dev_name = "ad7690", + .chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0), + .time_spec = &ad7690_t_spec, +}; + +static const struct ad4000_chip_info ad7691_chip_info = { + .dev_name = "ad7691", + .chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0), + .time_spec = &ad7691_t_spec, +}; + +static const struct ad4000_chip_info ad7693_chip_info = { + .dev_name = "ad7693", + .chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0), + .time_spec = &ad7686_t_spec, +}; + +static const struct ad4000_chip_info ad7942_chip_info = { + .dev_name = "ad7942", + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 14, 0), + .time_spec = &ad7687_t_spec, +}; + +static const struct ad4000_chip_info ad7946_chip_info = { + .dev_name = "ad7946", + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 14, 0), + .time_spec = &ad7686_t_spec, +}; + +static const struct ad4000_chip_info ad7980_chip_info = { + .dev_name = "ad7980", + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0), + .time_spec = &ad7980_t_spec, +}; + +static const struct ad4000_chip_info ad7982_chip_info = { + .dev_name = "ad7982", + .chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0), + .time_spec = &ad7980_t_spec, +}; + +static const struct ad4000_chip_info ad7983_chip_info = { + .dev_name = "ad7983", + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0), + .time_spec = &ad7983_t_spec, +}; + +static const struct ad4000_chip_info ad7984_chip_info = { + .dev_name = "ad7984", + .chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0), + .time_spec = &ad7983_t_spec, +}; + +static const struct ad4000_chip_info ad7988_1_chip_info = { + .dev_name = "ad7988-1", + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0), + .time_spec = &ad7988_1_t_spec, +}; + +static const struct ad4000_chip_info ad7988_5_chip_info = { + .dev_name = "ad7988-5", + .chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0), + .time_spec = &ad7686_t_spec, +}; + struct ad4000_state { struct spi_device *spi; struct gpio_desc *cnv_gpio; @@ -224,6 +403,7 @@ struct ad4000_state { bool span_comp; u16 gain_milli; int scale_tbl[AD4000_SCALE_OPTIONS][2]; + const struct ad4000_time_spec *time_spec; /* * DMA (thus cache coherency maintenance) requires the transfer buffers @@ -234,7 +414,7 @@ struct ad4000_state { __be16 sample_buf16; __be32 sample_buf32; } data; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan __aligned(IIO_DMA_MINALIGN); u8 tx_buf[2]; u8 rx_buf[2]; @@ -488,16 +668,15 @@ static const struct iio_info ad4000_info = { static int ad4000_prepare_3wire_mode_message(struct ad4000_state *st, const struct iio_chan_spec *chan) { - unsigned int cnv_pulse_time = AD4000_TCONV_NS; struct spi_transfer *xfers = st->xfers; xfers[0].cs_change = 1; - xfers[0].cs_change_delay.value = cnv_pulse_time; + xfers[0].cs_change_delay.value = st->time_spec->t_conv_ns; xfers[0].cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; xfers[1].rx_buf = &st->scan.data; xfers[1].len = BITS_TO_BYTES(chan->scan_type.storagebits); - xfers[1].delay.value = AD4000_TQUIET2_NS; + xfers[1].delay.value = st->time_spec->t_quiet2_ns; xfers[1].delay.unit = SPI_DELAY_UNIT_NSECS; spi_message_init_with_transfers(&st->msg, st->xfers, 2); @@ -515,7 +694,6 @@ static int ad4000_prepare_3wire_mode_message(struct ad4000_state *st, static int ad4000_prepare_4wire_mode_message(struct ad4000_state *st, const struct iio_chan_spec *chan) { - unsigned int cnv_to_sdi_time = AD4000_TCONV_NS; struct spi_transfer *xfers = st->xfers; /* @@ -523,7 +701,7 @@ static int ad4000_prepare_4wire_mode_message(struct ad4000_state *st, * going low. */ xfers[0].cs_off = 1; - xfers[0].delay.value = cnv_to_sdi_time; + xfers[0].delay.value = st->time_spec->t_conv_ns; xfers[0].delay.unit = SPI_DELAY_UNIT_NSECS; xfers[1].rx_buf = &st->scan.data; @@ -562,6 +740,7 @@ static int ad4000_probe(struct spi_device *spi) st = iio_priv(indio_dev); st->spi = spi; + st->time_spec = chip->time_spec; ret = devm_regulator_bulk_get_enable(dev, ARRAY_SIZE(ad4000_power_supplies), ad4000_power_supplies); @@ -591,7 +770,7 @@ static int ad4000_probe(struct spi_device *spi) switch (st->sdi_pin) { case AD4000_SDI_MOSI: indio_dev->info = &ad4000_reg_access_info; - indio_dev->channels = &chip->reg_access_chan_spec; + indio_dev->channels = chip->reg_access_chan_spec; /* * In "3-wire mode", the ADC SDI line must be kept high when @@ -603,7 +782,7 @@ static int ad4000_probe(struct spi_device *spi) if (ret < 0) return ret; - ret = ad4000_prepare_3wire_mode_message(st, indio_dev->channels); + ret = ad4000_prepare_3wire_mode_message(st, &indio_dev->channels[0]); if (ret) return ret; @@ -614,16 +793,16 @@ static int ad4000_probe(struct spi_device *spi) break; case AD4000_SDI_VIO: indio_dev->info = &ad4000_info; - indio_dev->channels = &chip->chan_spec; - ret = ad4000_prepare_3wire_mode_message(st, indio_dev->channels); + indio_dev->channels = chip->chan_spec; + ret = ad4000_prepare_3wire_mode_message(st, &indio_dev->channels[0]); if (ret) return ret; break; case AD4000_SDI_CS: indio_dev->info = &ad4000_info; - indio_dev->channels = &chip->chan_spec; - ret = ad4000_prepare_4wire_mode_message(st, indio_dev->channels); + indio_dev->channels = chip->chan_spec; + ret = ad4000_prepare_4wire_mode_message(st, &indio_dev->channels[0]); if (ret) return ret; @@ -637,7 +816,7 @@ static int ad4000_probe(struct spi_device *spi) } indio_dev->name = chip->dev_name; - indio_dev->num_channels = 1; + indio_dev->num_channels = 2; ret = devm_mutex_init(dev, &st->lock); if (ret) @@ -658,7 +837,7 @@ static int ad4000_probe(struct spi_device *spi) } } - ad4000_fill_scale_tbl(st, indio_dev->channels); + ad4000_fill_scale_tbl(st, &indio_dev->channels[0]); ret = devm_iio_triggered_buffer_setup(dev, indio_dev, &iio_pollfunc_store_time, @@ -686,6 +865,21 @@ static const struct spi_device_id ad4000_id[] = { { "ad4022", (kernel_ulong_t)&ad4022_chip_info }, { "adaq4001", (kernel_ulong_t)&adaq4001_chip_info }, { "adaq4003", (kernel_ulong_t)&adaq4003_chip_info }, + { "ad7685", (kernel_ulong_t)&ad7685_chip_info }, + { "ad7686", (kernel_ulong_t)&ad7686_chip_info }, + { "ad7687", (kernel_ulong_t)&ad7687_chip_info }, + { "ad7688", (kernel_ulong_t)&ad7688_chip_info }, + { "ad7690", (kernel_ulong_t)&ad7690_chip_info }, + { "ad7691", (kernel_ulong_t)&ad7691_chip_info }, + { "ad7693", (kernel_ulong_t)&ad7693_chip_info }, + { "ad7942", (kernel_ulong_t)&ad7942_chip_info }, + { "ad7946", (kernel_ulong_t)&ad7946_chip_info }, + { "ad7980", (kernel_ulong_t)&ad7980_chip_info }, + { "ad7982", (kernel_ulong_t)&ad7982_chip_info }, + { "ad7983", (kernel_ulong_t)&ad7983_chip_info }, + { "ad7984", (kernel_ulong_t)&ad7984_chip_info }, + { "ad7988-1", (kernel_ulong_t)&ad7988_1_chip_info }, + { "ad7988-5", (kernel_ulong_t)&ad7988_5_chip_info }, { } }; MODULE_DEVICE_TABLE(spi, ad4000_id); @@ -707,6 +901,21 @@ static const struct of_device_id ad4000_of_match[] = { { .compatible = "adi,ad4022", .data = &ad4022_chip_info }, { .compatible = "adi,adaq4001", .data = &adaq4001_chip_info }, { .compatible = "adi,adaq4003", .data = &adaq4003_chip_info }, + { .compatible = "adi,ad7685", .data = &ad7685_chip_info }, + { .compatible = "adi,ad7686", .data = &ad7686_chip_info }, + { .compatible = "adi,ad7687", .data = &ad7687_chip_info }, + { .compatible = "adi,ad7688", .data = &ad7688_chip_info }, + { .compatible = "adi,ad7690", .data = &ad7690_chip_info }, + { .compatible = "adi,ad7691", .data = &ad7691_chip_info }, + { .compatible = "adi,ad7693", .data = &ad7693_chip_info }, + { .compatible = "adi,ad7942", .data = &ad7942_chip_info }, + { .compatible = "adi,ad7946", .data = &ad7946_chip_info }, + { .compatible = "adi,ad7980", .data = &ad7980_chip_info }, + { .compatible = "adi,ad7982", .data = &ad7982_chip_info }, + { .compatible = "adi,ad7983", .data = &ad7983_chip_info }, + { .compatible = "adi,ad7984", .data = &ad7984_chip_info }, + { .compatible = "adi,ad7988-1", .data = &ad7988_1_chip_info }, + { .compatible = "adi,ad7988-5", .data = &ad7988_5_chip_info }, { } }; MODULE_DEVICE_TABLE(of, ad4000_of_match); diff --git a/drivers/iio/adc/ad4695.c b/drivers/iio/adc/ad4695.c index 595ec4158e73..b79d135a5471 100644 --- a/drivers/iio/adc/ad4695.c +++ b/drivers/iio/adc/ad4695.c @@ -30,7 +30,7 @@ #include #include -#include +#include /* AD4695 registers */ #define AD4695_REG_SPI_CONFIG_A 0x0000 @@ -91,6 +91,7 @@ #define AD4695_T_WAKEUP_SW_MS 3 #define AD4695_T_REFBUF_MS 100 #define AD4695_T_REGCONFIG_NS 20 +#define AD4695_T_SCK_CNV_DELAY_NS 80 #define AD4695_REG_ACCESS_SCLK_HZ (10 * MEGA) /* Max number of voltage input channels. */ @@ -132,8 +133,13 @@ struct ad4695_state { unsigned int vref_mv; /* Common mode input pin voltage. */ unsigned int com_mv; - /* 1 per voltage and temperature chan plus 1 xfer to trigger 1st CNV */ - struct spi_transfer buf_read_xfer[AD4695_MAX_CHANNELS + 2]; + /* + * 2 per voltage and temperature chan plus 1 xfer to trigger 1st + * CNV. Excluding the trigger xfer, every 2nd xfer only serves + * to control CS and add a delay between the last SCLK and next + * CNV rising edges. + */ + struct spi_transfer buf_read_xfer[AD4695_MAX_CHANNELS * 2 + 3]; struct spi_message buf_read_msg; /* Raw conversion data received. */ u8 buf[ALIGN((AD4695_MAX_CHANNELS + 2) * AD4695_MAX_CHANNEL_SIZE, @@ -423,7 +429,7 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) u8 temp_chan_bit = st->chip_info->num_voltage_inputs; u32 bit, num_xfer, num_slots; u32 temp_en = 0; - int ret; + int ret, rx_buf_offset = 0; /* * We are using the advanced sequencer since it is the only way to read @@ -449,11 +455,9 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) iio_for_each_active_channel(indio_dev, bit) { xfer = &st->buf_read_xfer[num_xfer]; xfer->bits_per_word = 16; - xfer->rx_buf = &st->buf[(num_xfer - 1) * 2]; + xfer->rx_buf = &st->buf[rx_buf_offset]; xfer->len = 2; - xfer->cs_change = 1; - xfer->cs_change_delay.value = AD4695_T_CONVERT_NS; - xfer->cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; + rx_buf_offset += xfer->len; if (bit == temp_chan_bit) { temp_en = 1; @@ -468,21 +472,44 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) } num_xfer++; + + /* + * We need to add a blank xfer in data reads, to meet the timing + * requirement of a minimum delay between the last SCLK rising + * edge and the CS deassert. + */ + xfer = &st->buf_read_xfer[num_xfer]; + xfer->delay.value = AD4695_T_SCK_CNV_DELAY_NS; + xfer->delay.unit = SPI_DELAY_UNIT_NSECS; + xfer->cs_change = 1; + xfer->cs_change_delay.value = AD4695_T_CONVERT_NS; + xfer->cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; + + num_xfer++; } /* * The advanced sequencer requires that at least 2 slots are enabled. * Since slot 0 is always used for other purposes, we need only 1 - * enabled voltage channel to meet this requirement. If the temperature - * channel is the only enabled channel, we need to add one more slot - * in the sequence but not read from it. + * enabled voltage channel to meet this requirement. If the temperature + * channel is the only enabled channel, we need to add one more slot in + * the sequence but not read from it. This is because the temperature + * sensor is sampled at the end of the channel sequence in advanced + * sequencer mode (see datasheet page 38). + * + * From the iio_for_each_active_channel() block above, we now have an + * xfer with data followed by a blank xfer to allow us to meet the + * timing spec, so move both of those up before adding an extra to + * handle the temperature-only case. */ if (num_slots < 2) { - /* move last xfer so we can insert one more xfer before it */ - st->buf_read_xfer[num_xfer] = *xfer; + /* Move last two xfers */ + st->buf_read_xfer[num_xfer] = st->buf_read_xfer[num_xfer - 1]; + st->buf_read_xfer[num_xfer - 1] = st->buf_read_xfer[num_xfer - 2]; num_xfer++; - /* modify 2nd to last xfer for extra slot */ + /* Modify inserted xfer for extra slot. */ + xfer = &st->buf_read_xfer[num_xfer - 3]; memset(xfer, 0, sizeof(*xfer)); xfer->cs_change = 1; xfer->delay.value = st->chip_info->t_acq_ns; @@ -499,6 +526,12 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) return ret; num_slots++; + + /* + * We still want to point at the last xfer when finished, so + * update the pointer. + */ + xfer = &st->buf_read_xfer[num_xfer - 1]; } /* @@ -583,8 +616,20 @@ out: */ static int ad4695_read_one_sample(struct ad4695_state *st, unsigned int address) { - struct spi_transfer xfer[2] = { }; - int ret, i = 0; + struct spi_transfer xfers[2] = { + { + .speed_hz = AD4695_REG_ACCESS_SCLK_HZ, + .bits_per_word = 16, + .tx_buf = &st->cnv_cmd, + .len = 2, + }, + { + /* Required delay between last SCLK and CNV/CS */ + .delay.value = AD4695_T_SCK_CNV_DELAY_NS, + .delay.unit = SPI_DELAY_UNIT_NSECS, + } + }; + int ret; ret = ad4695_set_single_cycle_mode(st, address); if (ret) @@ -592,29 +637,22 @@ static int ad4695_read_one_sample(struct ad4695_state *st, unsigned int address) /* * Setting the first channel to the temperature channel isn't supported - * in single-cycle mode, so we have to do an extra xfer to read the - * temperature. + * in single-cycle mode, so we have to do an extra conversion to read + * the temperature. */ if (address == AD4695_CMD_TEMP_CHAN) { - /* We aren't reading, so we can make this a short xfer. */ - st->cnv_cmd2 = AD4695_CMD_TEMP_CHAN << 3; - xfer[0].tx_buf = &st->cnv_cmd2; - xfer[0].len = 1; - xfer[0].cs_change = 1; - xfer[0].cs_change_delay.value = AD4695_T_CONVERT_NS; - xfer[0].cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; + st->cnv_cmd = AD4695_CMD_TEMP_CHAN << 11; - i = 1; + ret = spi_sync_transfer(st->spi, xfers, ARRAY_SIZE(xfers)); + if (ret) + return ret; } /* Then read the result and exit conversion mode. */ st->cnv_cmd = AD4695_CMD_EXIT_CNV_MODE << 11; - xfer[i].bits_per_word = 16; - xfer[i].tx_buf = &st->cnv_cmd; - xfer[i].rx_buf = &st->raw_data; - xfer[i].len = 2; + xfers[0].rx_buf = &st->raw_data; - return spi_sync_transfer(st->spi, xfer, i + 1); + return spi_sync_transfer(st->spi, xfers, ARRAY_SIZE(xfers)); } static int ad4695_read_raw(struct iio_dev *indio_dev, diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index 7314fb32bdec..6ae27cdd3250 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -95,6 +95,10 @@ #define AD7124_MAX_CONFIGS 8 #define AD7124_MAX_CHANNELS 16 +/* AD7124 input sources */ +#define AD7124_INPUT_TEMPSENSOR 16 +#define AD7124_INPUT_AVSS 17 + enum ad7124_ids { ID_AD7124_4, ID_AD7124_8, @@ -360,20 +364,21 @@ static int ad7124_find_free_config_slot(struct ad7124_state *st) return free_cfg_slot; } +/* Only called during probe, so dev_err_probe() can be used */ static int ad7124_init_config_vref(struct ad7124_state *st, struct ad7124_channel_config *cfg) { + struct device *dev = &st->sd.spi->dev; unsigned int refsel = cfg->refsel; switch (refsel) { case AD7124_REFIN1: case AD7124_REFIN2: case AD7124_AVDD_REF: - if (IS_ERR(st->vref[refsel])) { - dev_err(&st->sd.spi->dev, - "Error, trying to use external voltage reference without a %s regulator.\n", - ad7124_ref_names[refsel]); - return PTR_ERR(st->vref[refsel]); - } + if (IS_ERR(st->vref[refsel])) + return dev_err_probe(dev, PTR_ERR(st->vref[refsel]), + "Error, trying to use external voltage reference without a %s regulator.\n", + ad7124_ref_names[refsel]); + cfg->vref_mv = regulator_get_voltage(st->vref[refsel]); /* Conversion from uV to mV */ cfg->vref_mv /= 1000; @@ -384,8 +389,7 @@ static int ad7124_init_config_vref(struct ad7124_state *st, struct ad7124_channe st->adc_control |= AD7124_ADC_CTRL_REF_EN(1); return 0; default: - dev_err(&st->sd.spi->dev, "Invalid reference %d\n", refsel); - return -EINVAL; + return dev_err_probe(dev, -EINVAL, "Invalid reference %d\n", refsel); } } @@ -571,6 +575,7 @@ static const struct ad_sigma_delta_info ad7124_sigma_delta_info = { .data_reg = AD7124_DATA, .num_slots = 8, .irq_flags = IRQF_TRIGGER_FALLING, + .num_resetclks = 64, }; static int ad7124_read_raw(struct iio_dev *indio_dev, @@ -588,26 +593,59 @@ static int ad7124_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: - mutex_lock(&st->cfgs_lock); + switch (chan->type) { + case IIO_VOLTAGE: + mutex_lock(&st->cfgs_lock); - idx = st->channels[chan->address].cfg.pga_bits; - *val = st->channels[chan->address].cfg.vref_mv; - if (st->channels[chan->address].cfg.bipolar) - *val2 = chan->scan_type.realbits - 1 + idx; - else - *val2 = chan->scan_type.realbits + idx; + idx = st->channels[chan->address].cfg.pga_bits; + *val = st->channels[chan->address].cfg.vref_mv; + if (st->channels[chan->address].cfg.bipolar) + *val2 = chan->scan_type.realbits - 1 + idx; + else + *val2 = chan->scan_type.realbits + idx; + + mutex_unlock(&st->cfgs_lock); + return IIO_VAL_FRACTIONAL_LOG2; + + case IIO_TEMP: + /* + * According to the data sheet + * Temperature (°C) + * = ((Conversion − 0x800000)/13584) − 272.5 + * = (Conversion − 0x800000 - 13584 * 272.5) / 13584 + * = (Conversion − 12090248) / 13584 + * So scale with 1000/13584 to yield °mC. Reduce by 8 to + * 125/1698. + */ + *val = 125; + *val2 = 1698; + return IIO_VAL_FRACTIONAL; + + default: + return -EINVAL; + } - mutex_unlock(&st->cfgs_lock); - return IIO_VAL_FRACTIONAL_LOG2; case IIO_CHAN_INFO_OFFSET: - mutex_lock(&st->cfgs_lock); - if (st->channels[chan->address].cfg.bipolar) - *val = -(1 << (chan->scan_type.realbits - 1)); - else - *val = 0; + switch (chan->type) { + case IIO_VOLTAGE: + mutex_lock(&st->cfgs_lock); + if (st->channels[chan->address].cfg.bipolar) + *val = -(1 << (chan->scan_type.realbits - 1)); + else + *val = 0; + + mutex_unlock(&st->cfgs_lock); + return IIO_VAL_INT; + + case IIO_TEMP: + /* see calculation above */ + *val = -12090248; + return IIO_VAL_INT; + + default: + return -EINVAL; + } - mutex_unlock(&st->cfgs_lock); - return IIO_VAL_INT; case IIO_CHAN_INFO_SAMP_FREQ: mutex_lock(&st->cfgs_lock); *val = st->channels[chan->address].cfg.odr; @@ -751,12 +789,14 @@ static const struct iio_info ad7124_info = { .attrs = &ad7124_attrs_group, }; +/* Only called during probe, so dev_err_probe() can be used */ static int ad7124_soft_reset(struct ad7124_state *st) { + struct device *dev = &st->sd.spi->dev; unsigned int readval, timeout; int ret; - ret = ad_sd_reset(&st->sd, 64); + ret = ad_sd_reset(&st->sd); if (ret < 0) return ret; @@ -765,7 +805,7 @@ static int ad7124_soft_reset(struct ad7124_state *st) do { ret = ad_sd_read_reg(&st->sd, AD7124_STATUS, 1, &readval); if (ret < 0) - return ret; + return dev_err_probe(dev, ret, "Error reading status register\n"); if (!(readval & AD7124_STATUS_POR_FLAG_MSK)) return 0; @@ -774,39 +814,47 @@ static int ad7124_soft_reset(struct ad7124_state *st) usleep_range(100, 2000); } while (--timeout); - dev_err(&st->sd.spi->dev, "Soft reset failed\n"); - - return -EIO; + return dev_err_probe(dev, -EIO, "Soft reset failed\n"); } static int ad7124_check_chip_id(struct ad7124_state *st) { + struct device *dev = &st->sd.spi->dev; unsigned int readval, chip_id, silicon_rev; int ret; ret = ad_sd_read_reg(&st->sd, AD7124_ID, 1, &readval); if (ret < 0) - return ret; + return dev_err_probe(dev, ret, "Failure to read ID register\n"); chip_id = AD7124_DEVICE_ID_GET(readval); silicon_rev = AD7124_SILICON_REV_GET(readval); - if (chip_id != st->chip_info->chip_id) { - dev_err(&st->sd.spi->dev, - "Chip ID mismatch: expected %u, got %u\n", - st->chip_info->chip_id, chip_id); - return -ENODEV; - } + if (chip_id != st->chip_info->chip_id) + return dev_err_probe(dev, -ENODEV, + "Chip ID mismatch: expected %u, got %u\n", + st->chip_info->chip_id, chip_id); - if (silicon_rev == 0) { - dev_err(&st->sd.spi->dev, - "Silicon revision empty. Chip may not be present\n"); - return -ENODEV; - } + if (silicon_rev == 0) + return dev_err_probe(dev, -ENODEV, + "Silicon revision empty. Chip may not be present\n"); return 0; } +/* + * Input specifiers 8 - 15 are explicitly reserved for ad7124-4 + * while they are fine for ad7124-8. Values above 31 don't fit + * into the register field and so are invalid for sure. + */ +static bool ad7124_valid_input_select(unsigned int ain, const struct ad7124_chip_info *info) +{ + if (ain >= info->num_inputs && ain < 16) + return false; + + return ain <= FIELD_MAX(AD7124_CHANNEL_AINM_MSK); +} + static int ad7124_parse_channel_config(struct iio_dev *indio_dev, struct device *dev) { @@ -815,11 +863,23 @@ static int ad7124_parse_channel_config(struct iio_dev *indio_dev, struct ad7124_channel *channels; struct iio_chan_spec *chan; unsigned int ain[2], channel = 0, tmp; + unsigned int num_channels; int ret; - st->num_channels = device_get_child_node_count(dev); - if (!st->num_channels) - return dev_err_probe(dev, -ENODEV, "no channel children\n"); + num_channels = device_get_child_node_count(dev); + + /* + * The driver assigns each logical channel defined in the device tree + * statically one channel register. So only accept 16 such logical + * channels to not treat CONFIG_0 (i.e. the register following + * CHANNEL_15) as an additional channel register. The driver could be + * improved to lift this limitation. + */ + if (num_channels > AD7124_MAX_CHANNELS) + return dev_err_probe(dev, -EINVAL, "Too many channels defined\n"); + + /* Add one for temperature */ + st->num_channels = min(num_channels + 1, AD7124_MAX_CHANNELS); chan = devm_kcalloc(indio_dev->dev.parent, st->num_channels, sizeof(*chan), GFP_KERNEL); @@ -838,16 +898,23 @@ static int ad7124_parse_channel_config(struct iio_dev *indio_dev, device_for_each_child_node_scoped(dev, child) { ret = fwnode_property_read_u32(child, "reg", &channel); if (ret) - return ret; + return dev_err_probe(dev, ret, + "Failed to parse reg property of %pfwP\n", child); - if (channel >= indio_dev->num_channels) + if (channel >= num_channels) return dev_err_probe(dev, -EINVAL, - "Channel index >= number of channels\n"); + "Channel index >= number of channels in %pfwP\n", child); ret = fwnode_property_read_u32_array(child, "diff-channels", ain, 2); if (ret) - return ret; + return dev_err_probe(dev, ret, + "Failed to parse diff-channels property of %pfwP\n", child); + + if (!ad7124_valid_input_select(ain[0], st->chip_info) || + !ad7124_valid_input_select(ain[1], st->chip_info)) + return dev_err_probe(dev, -EINVAL, + "diff-channels property of %pfwP contains invalid data\n", child); st->channels[channel].nr = channel; st->channels[channel].ain = AD7124_CHANNEL_AINP(ain[0]) | @@ -874,17 +941,49 @@ static int ad7124_parse_channel_config(struct iio_dev *indio_dev, chan[channel].channel2 = ain[1]; } + if (num_channels < AD7124_MAX_CHANNELS) { + st->channels[num_channels] = (struct ad7124_channel) { + .nr = num_channels, + .ain = AD7124_CHANNEL_AINP(AD7124_INPUT_TEMPSENSOR) | + AD7124_CHANNEL_AINM(AD7124_INPUT_AVSS), + .cfg = { + .bipolar = true, + }, + }; + + chan[num_channels] = (struct iio_chan_spec) { + .type = IIO_TEMP, + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | + BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_OFFSET) | + BIT(IIO_CHAN_INFO_SAMP_FREQ), + .scan_type = { + /* + * You might find it strange that a bipolar + * measurement yields an unsigned value, but + * this matches the device's manual. + */ + .sign = 'u', + .realbits = 24, + .storagebits = 32, + .endianness = IIO_BE, + }, + .address = num_channels, + .scan_index = num_channels, + }; + } + return 0; } static int ad7124_setup(struct ad7124_state *st) { + struct device *dev = &st->sd.spi->dev; unsigned int fclk, power_mode; int i, ret; fclk = clk_get_rate(st->mclk); if (!fclk) - return -EINVAL; + return dev_err_probe(dev, -EINVAL, "Failed to get mclk rate\n"); /* The power mode changes the master clock frequency */ power_mode = ad7124_find_closest_match(ad7124_master_clk_freq_hz, @@ -893,7 +992,7 @@ static int ad7124_setup(struct ad7124_state *st) if (fclk != ad7124_master_clk_freq_hz[power_mode]) { ret = clk_set_rate(st->mclk, fclk); if (ret) - return ret; + return dev_err_probe(dev, ret, "Failed to set mclk rate\n"); } /* Set the power mode */ @@ -917,11 +1016,14 @@ static int ad7124_setup(struct ad7124_state *st) * set all channels to this default value. */ ad7124_set_channel_odr(st, i, 10); + + /* Disable all channels to prevent unintended conversions. */ + ad_sd_write_reg(&st->sd, AD7124_CHANNEL(i), 2, 0); } ret = ad_sd_write_reg(&st->sd, AD7124_ADC_CONTROL, 2, st->adc_control); if (ret < 0) - return ret; + return dev_err_probe(dev, ret, "Failed to setup CONTROL register\n"); return ret; } @@ -934,13 +1036,14 @@ static void ad7124_reg_disable(void *r) static int ad7124_probe(struct spi_device *spi) { const struct ad7124_chip_info *info; + struct device *dev = &spi->dev; struct ad7124_state *st; struct iio_dev *indio_dev; int i, ret; info = spi_get_device_match_data(spi); if (!info) - return -ENODEV; + return dev_err_probe(dev, -ENODEV, "Failed to get match data\n"); indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st)); if (!indio_dev) @@ -975,17 +1078,17 @@ static int ad7124_probe(struct spi_device *spi) ret = regulator_enable(st->vref[i]); if (ret) - return ret; + return dev_err_probe(dev, ret, "Failed to enable regulator #%d\n", i); ret = devm_add_action_or_reset(&spi->dev, ad7124_reg_disable, st->vref[i]); if (ret) - return ret; + return dev_err_probe(dev, ret, "Failed to register disable handler for regulator #%d\n", i); } st->mclk = devm_clk_get_enabled(&spi->dev, "mclk"); if (IS_ERR(st->mclk)) - return PTR_ERR(st->mclk); + return dev_err_probe(dev, PTR_ERR(st->mclk), "Failed to get mclk\n"); ret = ad7124_soft_reset(st); if (ret < 0) @@ -1001,10 +1104,13 @@ static int ad7124_probe(struct spi_device *spi) ret = devm_ad_sd_setup_buffer_and_trigger(&spi->dev, indio_dev); if (ret < 0) - return ret; + return dev_err_probe(dev, ret, "Failed to setup triggers\n"); - return devm_iio_device_register(&spi->dev, indio_dev); + ret = devm_iio_device_register(&spi->dev, indio_dev); + if (ret < 0) + return dev_err_probe(dev, ret, "Failed to register iio device\n"); + return 0; } static const struct of_device_id ad7124_of_match[] = { diff --git a/drivers/iio/adc/ad7173.c b/drivers/iio/adc/ad7173.c index 8a0c931ca83a..6c4ed10ae580 100644 --- a/drivers/iio/adc/ad7173.c +++ b/drivers/iio/adc/ad7173.c @@ -150,6 +150,11 @@ #define AD7173_FILTER_ODR0_MASK GENMASK(5, 0) #define AD7173_MAX_CONFIGS 8 +#define AD7173_MODE_CAL_INT_ZERO 0x4 /* Internal Zero-Scale Calibration */ +#define AD7173_MODE_CAL_INT_FULL 0x5 /* Internal Full-Scale Calibration */ +#define AD7173_MODE_CAL_SYS_ZERO 0x6 /* System Zero-Scale Calibration */ +#define AD7173_MODE_CAL_SYS_FULL 0x7 /* System Full-Scale Calibration */ + struct ad7173_device_info { const unsigned int *sinc5_data_rates; unsigned int num_sinc5_data_rates; @@ -175,6 +180,7 @@ struct ad7173_device_info { bool has_input_buf; bool has_int_ref; bool has_ref2; + bool has_internal_fs_calibration; bool higher_gpio_bits; u8 num_gpios; }; @@ -193,13 +199,14 @@ struct ad7173_channel_config { }; struct ad7173_channel { - unsigned int chan_reg; unsigned int ain; struct ad7173_channel_config cfg; + u8 syscalib_mode; }; struct ad7173_state { struct ad_sigma_delta sd; + struct ad_sigma_delta_info sigma_delta_info; const struct ad7173_device_info *info; struct ad7173_channel *channels; struct regulator_bulk_data regulators[3]; @@ -272,6 +279,7 @@ static const struct ad7173_device_info ad4111_device_info = { .has_input_buf = true, .has_current_inputs = true, .has_int_ref = true, + .has_internal_fs_calibration = true, .clock = 2 * HZ_PER_MHZ, .sinc5_data_rates = ad7173_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad7173_sinc5_data_rates), @@ -291,6 +299,7 @@ static const struct ad7173_device_info ad4112_device_info = { .has_input_buf = true, .has_current_inputs = true, .has_int_ref = true, + .has_internal_fs_calibration = true, .clock = 2 * HZ_PER_MHZ, .sinc5_data_rates = ad7173_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad7173_sinc5_data_rates), @@ -326,6 +335,7 @@ static const struct ad7173_device_info ad4114_device_info = { .has_temp = true, .has_input_buf = true, .has_int_ref = true, + .has_internal_fs_calibration = true, .clock = 2 * HZ_PER_MHZ, .sinc5_data_rates = ad7173_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad7173_sinc5_data_rates), @@ -343,6 +353,7 @@ static const struct ad7173_device_info ad4115_device_info = { .has_temp = true, .has_input_buf = true, .has_int_ref = true, + .has_internal_fs_calibration = true, .clock = 8 * HZ_PER_MHZ, .sinc5_data_rates = ad4115_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad4115_sinc5_data_rates), @@ -360,6 +371,7 @@ static const struct ad7173_device_info ad4116_device_info = { .has_temp = true, .has_input_buf = true, .has_int_ref = true, + .has_internal_fs_calibration = true, .clock = 4 * HZ_PER_MHZ, .sinc5_data_rates = ad4116_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad4116_sinc5_data_rates), @@ -505,6 +517,105 @@ static const struct regmap_config ad7173_regmap_config = { .read_flag_mask = BIT(6), }; +enum { + AD7173_SYSCALIB_ZERO_SCALE, + AD7173_SYSCALIB_FULL_SCALE, +}; + +static const char * const ad7173_syscalib_modes[] = { + [AD7173_SYSCALIB_ZERO_SCALE] = "zero_scale", + [AD7173_SYSCALIB_FULL_SCALE] = "full_scale", +}; + +static int ad7173_set_syscalib_mode(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + unsigned int mode) +{ + struct ad7173_state *st = iio_priv(indio_dev); + + st->channels[chan->channel].syscalib_mode = mode; + + return 0; +} + +static int ad7173_get_syscalib_mode(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan) +{ + struct ad7173_state *st = iio_priv(indio_dev); + + return st->channels[chan->channel].syscalib_mode; +} + +static ssize_t ad7173_write_syscalib(struct iio_dev *indio_dev, + uintptr_t private, + const struct iio_chan_spec *chan, + const char *buf, size_t len) +{ + struct ad7173_state *st = iio_priv(indio_dev); + bool sys_calib; + int ret, mode; + + ret = kstrtobool(buf, &sys_calib); + if (ret) + return ret; + + mode = st->channels[chan->channel].syscalib_mode; + if (sys_calib) { + if (mode == AD7173_SYSCALIB_ZERO_SCALE) + ret = ad_sd_calibrate(&st->sd, AD7173_MODE_CAL_SYS_ZERO, + chan->address); + else + ret = ad_sd_calibrate(&st->sd, AD7173_MODE_CAL_SYS_FULL, + chan->address); + } + + return ret ? : len; +} + +static const struct iio_enum ad7173_syscalib_mode_enum = { + .items = ad7173_syscalib_modes, + .num_items = ARRAY_SIZE(ad7173_syscalib_modes), + .set = ad7173_set_syscalib_mode, + .get = ad7173_get_syscalib_mode +}; + +static const struct iio_chan_spec_ext_info ad7173_calibsys_ext_info[] = { + { + .name = "sys_calibration", + .write = ad7173_write_syscalib, + .shared = IIO_SEPARATE, + }, + IIO_ENUM("sys_calibration_mode", IIO_SEPARATE, + &ad7173_syscalib_mode_enum), + IIO_ENUM_AVAILABLE("sys_calibration_mode", IIO_SHARED_BY_TYPE, + &ad7173_syscalib_mode_enum), + { } +}; + +static int ad7173_calibrate_all(struct ad7173_state *st, struct iio_dev *indio_dev) +{ + int ret; + int i; + + for (i = 0; i < st->num_channels; i++) { + if (indio_dev->channels[i].type != IIO_VOLTAGE) + continue; + + ret = ad_sd_calibrate(&st->sd, AD7173_MODE_CAL_INT_ZERO, st->channels[i].ain); + if (ret < 0) + return ret; + + if (st->info->has_internal_fs_calibration) { + ret = ad_sd_calibrate(&st->sd, AD7173_MODE_CAL_INT_FULL, + st->channels[i].ain); + if (ret < 0) + return ret; + } + } + + return 0; +} + static int ad7173_mask_xlate(struct gpio_regmap *gpio, unsigned int base, unsigned int offset, unsigned int *reg, unsigned int *mask) @@ -753,7 +864,7 @@ static int ad7173_disable_one(struct ad_sigma_delta *sd, unsigned int chan) return ad_sd_write_reg(sd, AD7173_REG_CH(chan), 2, 0); } -static struct ad_sigma_delta_info ad7173_sigma_delta_info = { +static const struct ad_sigma_delta_info ad7173_sigma_delta_info = { .set_channel = ad7173_set_channel, .append_status = ad7173_append_status, .disable_all = ad7173_disable_all, @@ -764,6 +875,7 @@ static struct ad_sigma_delta_info ad7173_sigma_delta_info = { .read_mask = BIT(6), .status_ch_mask = GENMASK(3, 0), .data_reg = AD7173_REG_DATA, + .num_resetclks = 64, }; static int ad7173_setup(struct iio_dev *indio_dev) @@ -801,6 +913,10 @@ static int ad7173_setup(struct iio_dev *indio_dev) if (!st->config_cnts) return -ENOMEM; + ret = ad7173_calibrate_all(st, indio_dev); + if (ret) + return ret; + /* All channels are enabled by default after a reset */ return ad7173_disable_all(&st->sd); } @@ -1023,6 +1139,7 @@ static const struct iio_chan_spec ad7173_channel_template = { .storagebits = 32, .endianness = IIO_BE, }, + .ext_info = ad7173_calibsys_ext_info, }; static const struct iio_chan_spec ad7173_temp_iio_channel_template = { @@ -1316,7 +1433,6 @@ static int ad7173_fw_parse_channel_config(struct iio_dev *indio_dev) chan->address = chan_index; chan->scan_index = chan_index; chan->channel = ain[0]; - chan_st_priv->chan_reg = chan_index; chan_st_priv->cfg.input_buf = st->info->has_input_buf; chan_st_priv->cfg.odr = 0; @@ -1403,7 +1519,7 @@ static int ad7173_fw_parse_device_config(struct iio_dev *indio_dev) if (ret < 0) return dev_err_probe(dev, ret, "Interrupt 'rdy' is required\n"); - ad7173_sigma_delta_info.irq_line = ret; + st->sigma_delta_info.irq_line = ret; return ad7173_fw_parse_channel_config(indio_dev); } @@ -1436,8 +1552,9 @@ static int ad7173_probe(struct spi_device *spi) spi->mode = SPI_MODE_3; spi_setup(spi); - ad7173_sigma_delta_info.num_slots = st->info->num_configs; - ret = ad_sd_init(&st->sd, indio_dev, spi, &ad7173_sigma_delta_info); + st->sigma_delta_info = ad7173_sigma_delta_info; + st->sigma_delta_info.num_slots = st->info->num_configs; + ret = ad_sd_init(&st->sd, indio_dev, spi, &st->sigma_delta_info); if (ret) return ret; diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 1c87db0e0460..e96a5ae92375 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -361,6 +361,7 @@ static const struct ad_sigma_delta_info ad7192_sigma_delta_info = { .status_ch_mask = GENMASK(3, 0), .num_slots = 4, .irq_flags = IRQF_TRIGGER_FALLING, + .num_resetclks = 40, }; static const struct ad_sigma_delta_info ad7194_sigma_delta_info = { @@ -373,6 +374,7 @@ static const struct ad_sigma_delta_info ad7194_sigma_delta_info = { .read_mask = BIT(6), .status_ch_mask = GENMASK(3, 0), .irq_flags = IRQF_TRIGGER_FALLING, + .num_resetclks = 40, }; static const struct ad_sd_calib_data ad7192_calib_arr[8] = { @@ -565,7 +567,7 @@ static int ad7192_setup(struct iio_dev *indio_dev, struct device *dev) int i, ret, id; /* reset the serial interface */ - ret = ad_sd_reset(&st->sd, 48); + ret = ad_sd_reset(&st->sd); if (ret < 0) return ret; usleep_range(500, 1000); /* Wait for at least 500us */ diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c index e35d55d03d86..d8e3c7a43678 100644 --- a/drivers/iio/adc/ad7606.c +++ b/drivers/iio/adc/ad7606.c @@ -175,17 +175,17 @@ static const struct iio_chan_spec ad7616_channels[] = { AD7606_CHANNEL(15, 16), }; -static int ad7606c_18bit_chan_scale_setup(struct ad7606_state *st, +static int ad7606c_18bit_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch); -static int ad7606c_16bit_chan_scale_setup(struct ad7606_state *st, +static int ad7606c_16bit_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch); -static int ad7606_16bit_chan_scale_setup(struct ad7606_state *st, +static int ad7606_16bit_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch); -static int ad7607_chan_scale_setup(struct ad7606_state *st, +static int ad7607_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch); -static int ad7608_chan_scale_setup(struct ad7606_state *st, +static int ad7608_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch); -static int ad7609_chan_scale_setup(struct ad7606_state *st, +static int ad7609_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch); const struct ad7606_chip_info ad7605_4_info = { @@ -323,9 +323,10 @@ int ad7606_reset(struct ad7606_state *st) } EXPORT_SYMBOL_NS_GPL(ad7606_reset, "IIO_AD7606"); -static int ad7606_16bit_chan_scale_setup(struct ad7606_state *st, +static int ad7606_16bit_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch) { + struct ad7606_state *st = iio_priv(indio_dev); struct ad7606_chan_scale *cs = &st->chan_scales[ch]; if (!st->sw_mode_en) { @@ -345,10 +346,12 @@ static int ad7606_16bit_chan_scale_setup(struct ad7606_state *st, return 0; } -static int ad7606_get_chan_config(struct ad7606_state *st, int ch, +static int ad7606_get_chan_config(struct iio_dev *indio_dev, int ch, bool *bipolar, bool *differential) { - unsigned int num_channels = st->chip_info->num_channels - 1; + struct ad7606_state *st = iio_priv(indio_dev); + unsigned int num_channels = st->chip_info->num_adc_channels; + unsigned int offset = indio_dev->num_channels - st->chip_info->num_adc_channels; struct device *dev = st->dev; int ret; @@ -364,7 +367,7 @@ static int ad7606_get_chan_config(struct ad7606_state *st, int ch, continue; /* channel number (here) is from 1 to num_channels */ - if (reg == 0 || reg > num_channels) { + if (reg < offset || reg > num_channels) { dev_warn(dev, "Invalid channel number (ignoring): %d\n", reg); continue; @@ -399,9 +402,10 @@ static int ad7606_get_chan_config(struct ad7606_state *st, int ch, return 0; } -static int ad7606c_18bit_chan_scale_setup(struct ad7606_state *st, +static int ad7606c_18bit_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch) { + struct ad7606_state *st = iio_priv(indio_dev); struct ad7606_chan_scale *cs = &st->chan_scales[ch]; bool bipolar, differential; int ret; @@ -413,7 +417,7 @@ static int ad7606c_18bit_chan_scale_setup(struct ad7606_state *st, return 0; } - ret = ad7606_get_chan_config(st, ch, &bipolar, &differential); + ret = ad7606_get_chan_config(indio_dev, ch, &bipolar, &differential); if (ret) return ret; @@ -455,9 +459,10 @@ static int ad7606c_18bit_chan_scale_setup(struct ad7606_state *st, return 0; } -static int ad7606c_16bit_chan_scale_setup(struct ad7606_state *st, +static int ad7606c_16bit_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch) { + struct ad7606_state *st = iio_priv(indio_dev); struct ad7606_chan_scale *cs = &st->chan_scales[ch]; bool bipolar, differential; int ret; @@ -469,7 +474,7 @@ static int ad7606c_16bit_chan_scale_setup(struct ad7606_state *st, return 0; } - ret = ad7606_get_chan_config(st, ch, &bipolar, &differential); + ret = ad7606_get_chan_config(indio_dev, ch, &bipolar, &differential); if (ret) return ret; @@ -512,9 +517,10 @@ static int ad7606c_16bit_chan_scale_setup(struct ad7606_state *st, return 0; } -static int ad7607_chan_scale_setup(struct ad7606_state *st, +static int ad7607_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch) { + struct ad7606_state *st = iio_priv(indio_dev); struct ad7606_chan_scale *cs = &st->chan_scales[ch]; cs->range = 0; @@ -523,9 +529,10 @@ static int ad7607_chan_scale_setup(struct ad7606_state *st, return 0; } -static int ad7608_chan_scale_setup(struct ad7606_state *st, +static int ad7608_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch) { + struct ad7606_state *st = iio_priv(indio_dev); struct ad7606_chan_scale *cs = &st->chan_scales[ch]; cs->range = 0; @@ -534,9 +541,10 @@ static int ad7608_chan_scale_setup(struct ad7606_state *st, return 0; } -static int ad7609_chan_scale_setup(struct ad7606_state *st, +static int ad7609_chan_scale_setup(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch) { + struct ad7606_state *st = iio_priv(indio_dev); struct ad7606_chan_scale *cs = &st->chan_scales[ch]; cs->range = 0; @@ -1146,8 +1154,8 @@ static int ad7606_sw_mode_setup(struct iio_dev *indio_dev) static int ad7606_chan_scales_setup(struct iio_dev *indio_dev) { - unsigned int num_channels = indio_dev->num_channels - 1; struct ad7606_state *st = iio_priv(indio_dev); + unsigned int offset = indio_dev->num_channels - st->chip_info->num_adc_channels; struct iio_chan_spec *chans; size_t size; int ch, ret; @@ -1161,8 +1169,8 @@ static int ad7606_chan_scales_setup(struct iio_dev *indio_dev) memcpy(chans, indio_dev->channels, size); indio_dev->channels = chans; - for (ch = 0; ch < num_channels; ch++) { - ret = st->chip_info->scale_setup_cb(st, &chans[ch + 1], ch); + for (ch = 0; ch < st->chip_info->num_adc_channels; ch++) { + ret = st->chip_info->scale_setup_cb(indio_dev, &chans[ch + offset], ch); if (ret) return ret; } diff --git a/drivers/iio/adc/ad7606.h b/drivers/iio/adc/ad7606.h index 998814a92b82..8778ffe515b3 100644 --- a/drivers/iio/adc/ad7606.h +++ b/drivers/iio/adc/ad7606.h @@ -69,7 +69,7 @@ struct ad7606_state; -typedef int (*ad7606_scale_setup_cb_t)(struct ad7606_state *st, +typedef int (*ad7606_scale_setup_cb_t)(struct iio_dev *indio_dev, struct iio_chan_spec *chan, int ch); /** diff --git a/drivers/iio/adc/ad7625.c b/drivers/iio/adc/ad7625.c index aefe3bf75c91..afa9bf4ddf3c 100644 --- a/drivers/iio/adc/ad7625.c +++ b/drivers/iio/adc/ad7625.c @@ -477,12 +477,12 @@ static int devm_ad7625_pwm_get(struct device *dev, ref_clk = devm_clk_get_enabled(dev, NULL); if (IS_ERR(ref_clk)) return dev_err_probe(dev, PTR_ERR(ref_clk), - "failed to get ref_clk"); + "failed to get ref_clk\n"); ref_clk_rate_hz = clk_get_rate(ref_clk); if (!ref_clk_rate_hz) return dev_err_probe(dev, -EINVAL, - "failed to get ref_clk rate"); + "failed to get ref_clk rate\n"); st->ref_clk_rate_hz = ref_clk_rate_hz; @@ -533,7 +533,7 @@ static int devm_ad7625_regulator_setup(struct device *dev, if (!st->info->has_internal_vref && !st->have_refin && !ref_mv) return dev_err_probe(dev, -EINVAL, - "Need either REFIN or REF"); + "Need either REFIN or REF\n"); if (st->have_refin && ref_mv) return dev_err_probe(dev, -EINVAL, @@ -623,7 +623,7 @@ static int ad7625_probe(struct platform_device *pdev) st->back = devm_iio_backend_get(dev, NULL); if (IS_ERR(st->back)) return dev_err_probe(dev, PTR_ERR(st->back), - "failed to get IIO backend"); + "failed to get IIO backend\n"); ret = devm_iio_backend_request_buffer(dev, st->back, indio_dev); if (ret) diff --git a/drivers/iio/adc/ad7791.c b/drivers/iio/adc/ad7791.c index e1bf13fe2cd7..76118fe22db8 100644 --- a/drivers/iio/adc/ad7791.c +++ b/drivers/iio/adc/ad7791.c @@ -254,6 +254,7 @@ static const struct ad_sigma_delta_info ad7791_sigma_delta_info = { .addr_shift = 4, .read_mask = BIT(3), .irq_flags = IRQF_TRIGGER_FALLING, + .num_resetclks = 32, }; static int ad7791_read_raw(struct iio_dev *indio_dev, diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c index d55c71566707..1b50d9643a63 100644 --- a/drivers/iio/adc/ad7793.c +++ b/drivers/iio/adc/ad7793.c @@ -206,6 +206,7 @@ static const struct ad_sigma_delta_info ad7793_sigma_delta_info = { .addr_shift = 3, .read_mask = BIT(6), .irq_flags = IRQF_TRIGGER_FALLING, + .num_resetclks = 32, }; static const struct ad_sd_calib_data ad7793_calib_arr[6] = { @@ -265,7 +266,7 @@ static int ad7793_setup(struct iio_dev *indio_dev, return ret; /* reset the serial interface */ - ret = ad_sd_reset(&st->sd, 32); + ret = ad_sd_reset(&st->sd); if (ret < 0) goto out; usleep_range(500, 2000); /* Wait for at least 500us */ diff --git a/drivers/iio/adc/ad7944.c b/drivers/iio/adc/ad7944.c index a5aea4e9f1a7..0ec9cda10f5f 100644 --- a/drivers/iio/adc/ad7944.c +++ b/drivers/iio/adc/ad7944.c @@ -75,7 +75,7 @@ struct ad7944_adc { u16 u16; u32 u32; } raw; - u64 timestamp __aligned(8); + aligned_s64 timestamp; } sample __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c index d358958ab310..f30119b42ba0 100644 --- a/drivers/iio/adc/ad9467.c +++ b/drivers/iio/adc/ad9467.c @@ -895,7 +895,7 @@ static int ad9467_update_scan_mode(struct iio_dev *indio_dev, return 0; } -static struct iio_info ad9467_info = { +static const struct iio_info ad9467_info = { .read_raw = ad9467_read_raw, .write_raw = ad9467_write_raw, .update_scan_mode = ad9467_update_scan_mode, @@ -903,6 +903,14 @@ static struct iio_info ad9467_info = { .read_avail = ad9467_read_avail, }; +/* Same as above, but without .read_avail */ +static const struct iio_info ad9467_info_no_read_avail = { + .read_raw = ad9467_read_raw, + .write_raw = ad9467_write_raw, + .update_scan_mode = ad9467_update_scan_mode, + .debugfs_reg_access = ad9467_reg_access, +}; + static int ad9467_scale_fill(struct ad9467_state *st) { const struct ad9467_chip_info *info = st->info; @@ -1214,11 +1222,12 @@ static int ad9467_probe(struct spi_device *spi) } if (st->info->num_scales > 1) - ad9467_info.read_avail = ad9467_read_avail; + indio_dev->info = &ad9467_info; + else + indio_dev->info = &ad9467_info_no_read_avail; indio_dev->name = st->info->name; indio_dev->channels = st->info->channels; indio_dev->num_channels = st->info->num_channels; - indio_dev->info = &ad9467_info; ret = ad9467_iio_backend_get(st); if (ret) diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index 3fd200b34161..d5d81581ab34 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -29,8 +29,11 @@ #define AD_SD_COMM_CHAN_MASK 0x3 #define AD_SD_REG_COMM 0x00 +#define AD_SD_REG_STATUS 0x00 #define AD_SD_REG_DATA 0x03 +#define AD_SD_REG_STATUS_RDY 0x80 + /** * ad_sd_set_comm() - Set communications register * @@ -109,7 +112,7 @@ static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta, }, { .rx_buf = val, .len = size, - .cs_change = sigma_delta->bus_locked, + .cs_change = sigma_delta->keep_cs_asserted, }, }; struct spi_message m; @@ -178,13 +181,12 @@ EXPORT_SYMBOL_NS_GPL(ad_sd_read_reg, "IIO_AD_SIGMA_DELTA"); * ad_sd_reset() - Reset the serial interface * * @sigma_delta: The sigma delta device - * @reset_length: Number of SCLKs with DIN = 1 * * Returns 0 on success, an error code otherwise. **/ -int ad_sd_reset(struct ad_sigma_delta *sigma_delta, - unsigned int reset_length) +int ad_sd_reset(struct ad_sigma_delta *sigma_delta) { + unsigned int reset_length = sigma_delta->info->num_resetclks; uint8_t *buf; unsigned int size; int ret; @@ -202,6 +204,107 @@ int ad_sd_reset(struct ad_sigma_delta *sigma_delta, } EXPORT_SYMBOL_NS_GPL(ad_sd_reset, "IIO_AD_SIGMA_DELTA"); +static bool ad_sd_disable_irq(struct ad_sigma_delta *sigma_delta) +{ + guard(spinlock_irqsave)(&sigma_delta->irq_lock); + + /* It's already off, return false to indicate nothing was changed */ + if (sigma_delta->irq_dis) + return false; + + sigma_delta->irq_dis = true; + disable_irq_nosync(sigma_delta->irq_line); + return true; +} + +static void ad_sd_enable_irq(struct ad_sigma_delta *sigma_delta) +{ + guard(spinlock_irqsave)(&sigma_delta->irq_lock); + + sigma_delta->irq_dis = false; + enable_irq(sigma_delta->irq_line); +} + +#define AD_SD_CLEAR_DATA_BUFLEN 9 + +/* Called with `sigma_delta->bus_locked == true` only. */ +static int ad_sigma_delta_clear_pending_event(struct ad_sigma_delta *sigma_delta) +{ + bool pending_event; + unsigned int data_read_len = BITS_TO_BYTES(sigma_delta->info->num_resetclks); + u8 *data; + struct spi_transfer t[] = { + { + .len = 1, + }, { + .len = data_read_len, + } + }; + struct spi_message m; + int ret; + + /* + * Read R̅D̅Y̅ pin (if possible) or status register to check if there is an + * old event. + */ + if (sigma_delta->rdy_gpiod) { + pending_event = gpiod_get_value(sigma_delta->rdy_gpiod); + } else { + unsigned int status_reg; + + ret = ad_sd_read_reg(sigma_delta, AD_SD_REG_STATUS, 1, &status_reg); + if (ret) + return ret; + + pending_event = !(status_reg & AD_SD_REG_STATUS_RDY); + } + + if (!pending_event) + return 0; + + /* + * In general the size of the data register is unknown. It varies from + * device to device, might be one byte longer if CONTROL.DATA_STATUS is + * set and even varies on some devices depending on which input is + * selected. So send one byte to start reading the data register and + * then just clock for some bytes with DIN (aka MOSI) high to not + * confuse the register access state machine after the data register was + * completely read. Note however that the sequence length must be + * shorter than the reset procedure. + */ + + data = kzalloc(data_read_len + 1, GFP_KERNEL); + if (!data) + return -ENOMEM; + + spi_message_init(&m); + if (sigma_delta->info->has_registers) { + unsigned int data_reg = sigma_delta->info->data_reg ?: AD_SD_REG_DATA; + + data[0] = data_reg << sigma_delta->info->addr_shift; + data[0] |= sigma_delta->info->read_mask; + data[0] |= sigma_delta->comm; + t[0].tx_buf = data; + spi_message_add_tail(&t[0], &m); + } + + /* + * The first transferred byte is part of the real data register, + * so this doesn't need to be 0xff. In the remaining + * `data_read_len - 1` bytes are less than $num_resetclks ones. + */ + t[1].tx_buf = data + 1; + data[1] = 0x00; + memset(data + 2, 0xff, data_read_len - 1); + spi_message_add_tail(&t[1], &m); + + ret = spi_sync_locked(sigma_delta->spi, &m); + + kfree(data); + + return ret; +} + int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta, unsigned int mode, unsigned int channel) { @@ -217,16 +320,18 @@ int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta, sigma_delta->keep_cs_asserted = true; reinit_completion(&sigma_delta->completion); + ret = ad_sigma_delta_clear_pending_event(sigma_delta); + if (ret) + goto out; + ret = ad_sigma_delta_set_mode(sigma_delta, mode); if (ret < 0) goto out; - sigma_delta->irq_dis = false; - enable_irq(sigma_delta->irq_line); + ad_sd_enable_irq(sigma_delta); time_left = wait_for_completion_timeout(&sigma_delta->completion, 2 * HZ); if (time_left == 0) { - sigma_delta->irq_dis = true; - disable_irq_nosync(sigma_delta->irq_line); + ad_sd_disable_irq(sigma_delta); ret = -EIO; } else { ret = 0; @@ -292,10 +397,13 @@ int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, sigma_delta->keep_cs_asserted = true; reinit_completion(&sigma_delta->completion); + ret = ad_sigma_delta_clear_pending_event(sigma_delta); + if (ret) + goto out_unlock; + ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_SINGLE); - sigma_delta->irq_dis = false; - enable_irq(sigma_delta->irq_line); + ad_sd_enable_irq(sigma_delta); ret = wait_for_completion_interruptible_timeout( &sigma_delta->completion, HZ); @@ -314,14 +422,13 @@ int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, &raw_sample); out: - if (!sigma_delta->irq_dis) { - disable_irq_nosync(sigma_delta->irq_line); - sigma_delta->irq_dis = true; - } + ad_sd_disable_irq(sigma_delta); - sigma_delta->keep_cs_asserted = false; ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_IDLE); ad_sigma_delta_disable_one(sigma_delta, chan->address); + +out_unlock: + sigma_delta->keep_cs_asserted = false; sigma_delta->bus_locked = false; spi_bus_unlock(sigma_delta->spi->controller); iio_device_release_direct_mode(indio_dev); @@ -392,12 +499,15 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev) sigma_delta->bus_locked = true; sigma_delta->keep_cs_asserted = true; + ret = ad_sigma_delta_clear_pending_event(sigma_delta); + if (ret) + goto err_unlock; + ret = ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_CONTINUOUS); if (ret) goto err_unlock; - sigma_delta->irq_dis = false; - enable_irq(sigma_delta->irq_line); + ad_sd_enable_irq(sigma_delta); return 0; @@ -414,10 +524,7 @@ static int ad_sd_buffer_postdisable(struct iio_dev *indio_dev) reinit_completion(&sigma_delta->completion); wait_for_completion_timeout(&sigma_delta->completion, HZ); - if (!sigma_delta->irq_dis) { - disable_irq_nosync(sigma_delta->irq_line); - sigma_delta->irq_dis = true; - } + ad_sd_disable_irq(sigma_delta); sigma_delta->keep_cs_asserted = false; ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_IDLE); @@ -516,8 +623,7 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p) irq_handled: iio_trigger_notify_done(indio_dev->trig); - sigma_delta->irq_dis = false; - enable_irq(sigma_delta->irq_line); + ad_sd_enable_irq(sigma_delta); return IRQ_HANDLED; } @@ -539,12 +645,31 @@ static irqreturn_t ad_sd_data_rdy_trig_poll(int irq, void *private) { struct ad_sigma_delta *sigma_delta = private; - complete(&sigma_delta->completion); - disable_irq_nosync(irq); - sigma_delta->irq_dis = true; - iio_trigger_poll(sigma_delta->trig); + /* + * AD7124 and a few others use the same physical line for interrupt + * reporting (R̅D̅Y̅) and MISO. + * As MISO toggles when reading a register, this likely results in a + * pending interrupt. This has two consequences: a) The irq might + * trigger immediately after it's enabled even though the conversion + * isn't done yet; and b) checking the STATUS register's R̅D̅Y̅ flag is + * off-limits as reading that would trigger another irq event. + * + * So read the MOSI line as GPIO (if available) and only trigger the irq + * if the line is active. Without such a GPIO assume this is a valid + * interrupt. + * + * Also as disable_irq_nosync() is used to disable the irq, only act if + * the irq wasn't disabled before. + */ + if ((!sigma_delta->rdy_gpiod || gpiod_get_value(sigma_delta->rdy_gpiod)) && + ad_sd_disable_irq(sigma_delta)) { + complete(&sigma_delta->completion); + iio_trigger_poll(sigma_delta->trig); - return IRQ_HANDLED; + return IRQ_HANDLED; + } + + return IRQ_NONE; } /** @@ -674,11 +799,24 @@ int ad_sd_init(struct ad_sigma_delta *sigma_delta, struct iio_dev *indio_dev, } } + spin_lock_init(&sigma_delta->irq_lock); + if (info->irq_line) sigma_delta->irq_line = info->irq_line; else sigma_delta->irq_line = spi->irq; + sigma_delta->rdy_gpiod = devm_gpiod_get_optional(&spi->dev, "rdy", GPIOD_IN); + if (IS_ERR(sigma_delta->rdy_gpiod)) + return dev_err_probe(&spi->dev, PTR_ERR(sigma_delta->rdy_gpiod), + "Failed to find rdy gpio\n"); + + if (sigma_delta->rdy_gpiod && !sigma_delta->irq_line) { + sigma_delta->irq_line = gpiod_to_irq(sigma_delta->rdy_gpiod); + if (sigma_delta->irq_line < 0) + return sigma_delta->irq_line; + } + iio_device_set_drvdata(indio_dev, sigma_delta); return 0; diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index a3f0a2321666..5927756b749a 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -979,7 +979,7 @@ static int at91_ts_register(struct iio_dev *idev, return ret; err: - input_free_device(st->ts_input); + input_free_device(input); return ret; } diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c index 30328626d9be..221a5fdc1eaa 100644 --- a/drivers/iio/adc/dln2-adc.c +++ b/drivers/iio/adc/dln2-adc.c @@ -66,8 +66,6 @@ struct dln2_adc { /* Demux table */ unsigned int demux_count; struct dln2_adc_demux_table demux[DLN2_ADC_MAX_CHANNELS]; - /* Precomputed timestamp padding offset and length */ - unsigned int ts_pad_offset, ts_pad_length; }; struct dln2_adc_port_chan { @@ -111,8 +109,6 @@ static void dln2_adc_update_demux(struct dln2_adc *dln2) if (iio_get_masklength(indio_dev) && (*indio_dev->active_scan_mask & 0xff) == 0xff) { dln2_adc_add_demux(dln2, 0, 0, 16); - dln2->ts_pad_offset = 0; - dln2->ts_pad_length = 0; return; } @@ -127,16 +123,6 @@ static void dln2_adc_update_demux(struct dln2_adc *dln2) out_loc += 2; in_loc += 2; } - - if (indio_dev->scan_timestamp) { - size_t ts_offset = indio_dev->scan_bytes / sizeof(int64_t) - 1; - - dln2->ts_pad_offset = out_loc; - dln2->ts_pad_length = ts_offset * sizeof(int64_t) - out_loc; - } else { - dln2->ts_pad_offset = 0; - dln2->ts_pad_length = 0; - } } static int dln2_adc_get_chan_count(struct dln2_adc *dln2) @@ -494,6 +480,8 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p) if (ret < 0) goto done; + memset(&data, 0, sizeof(data)); + /* Demux operation */ for (i = 0; i < dln2->demux_count; ++i) { t = &dln2->demux[i]; @@ -501,11 +489,6 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p) (void *)dev_data.values + t->from, t->length); } - /* Zero padding space between values and timestamp */ - if (dln2->ts_pad_length) - memset((void *)data.values + dln2->ts_pad_offset, - 0, dln2->ts_pad_length); - iio_push_to_buffers_with_timestamp(indio_dev, &data, iio_get_time_ns(indio_dev)); diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c index 48c95e12e791..40d14faa71c5 100644 --- a/drivers/iio/adc/ina2xx-adc.c +++ b/drivers/iio/adc/ina2xx-adc.c @@ -150,7 +150,7 @@ struct ina2xx_chip_info { /* data buffer needs space for channel data and timestamp */ struct { u16 chan[4]; - u64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/adc/max1118.c b/drivers/iio/adc/max1118.c index 3d0a7d0eb7ee..565ca2e21c0c 100644 --- a/drivers/iio/adc/max1118.c +++ b/drivers/iio/adc/max1118.c @@ -39,7 +39,7 @@ struct max1118 { /* Ensure natural alignment of buffer elements */ struct { u8 channels[2]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; u8 data __aligned(IIO_DMA_MINALIGN); diff --git a/drivers/iio/adc/max11410.c b/drivers/iio/adc/max11410.c index f0dc4b460903..76abafd47404 100644 --- a/drivers/iio/adc/max11410.c +++ b/drivers/iio/adc/max11410.c @@ -143,7 +143,7 @@ struct max11410_state { int irq; struct { u32 data __aligned(IIO_DMA_MINALIGN); - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c index 9a0baea08ab6..e8d731bc34e0 100644 --- a/drivers/iio/adc/max1363.c +++ b/drivers/iio/adc/max1363.c @@ -161,6 +161,7 @@ struct max1363_chip_info { * @vref_uv: Actual (external or internal) reference voltage * @send: function used to send data to the chip * @recv: function used to receive data from the chip + * @data: buffer to store channel data and timestamp */ struct max1363_state { struct i2c_client *client; @@ -186,6 +187,10 @@ struct max1363_state { const char *buf, int count); int (*recv)(const struct i2c_client *client, char *buf, int count); + struct { + u8 buf[MAX1363_MAX_CHANNELS * 2]; + aligned_s64 ts; + } data; }; #define MAX1363_MODE_SINGLE(_num, _mask) { \ @@ -1462,22 +1467,10 @@ static irqreturn_t max1363_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; struct max1363_state *st = iio_priv(indio_dev); - __u8 *rxbuf; int b_sent; - size_t d_size; unsigned long numvals = bitmap_weight(st->current_mode->modemask, MAX1363_MAX_CHANNELS); - /* Ensure the timestamp is 8 byte aligned */ - if (st->chip_info->bits != 8) - d_size = numvals*2; - else - d_size = numvals; - if (indio_dev->scan_timestamp) { - d_size += sizeof(s64); - if (d_size % sizeof(s64)) - d_size += sizeof(s64) - (d_size % sizeof(s64)); - } /* Monitor mode prevents reading. Whilst not currently implemented * might as well have this test in here in the meantime as it does * no harm. @@ -1485,21 +1478,16 @@ static irqreturn_t max1363_trigger_handler(int irq, void *p) if (numvals == 0) goto done; - rxbuf = kmalloc(d_size, GFP_KERNEL); - if (rxbuf == NULL) - goto done; if (st->chip_info->bits != 8) - b_sent = st->recv(st->client, rxbuf, numvals * 2); + b_sent = st->recv(st->client, st->data.buf, numvals * 2); else - b_sent = st->recv(st->client, rxbuf, numvals); + b_sent = st->recv(st->client, st->data.buf, numvals); if (b_sent < 0) - goto done_free; + goto done; - iio_push_to_buffers_with_timestamp(indio_dev, rxbuf, + iio_push_to_buffers_with_timestamp(indio_dev, &st->data, iio_get_time_ns(indio_dev)); -done_free: - kfree(rxbuf); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/adc/mcp3911.c b/drivers/iio/adc/mcp3911.c index b097f04172c8..6748b44d568d 100644 --- a/drivers/iio/adc/mcp3911.c +++ b/drivers/iio/adc/mcp3911.c @@ -122,7 +122,7 @@ struct mcp3911 { const struct mcp3911_chip_info *chip; struct { u32 channels[MCP39XX_MAX_NUM_CHANNELS]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; u8 tx_buf __aligned(IIO_DMA_MINALIGN); diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c index 2d475b43e717..997def4a4d2f 100644 --- a/drivers/iio/adc/meson_saradc.c +++ b/drivers/iio/adc/meson_saradc.c @@ -155,10 +155,10 @@ */ #define MESON_SAR_ADC_REG11 0x2c #define MESON_SAR_ADC_REG11_BANDGAP_EN BIT(13) - #define MESON_SAR_ADC_REG11_CMV_SEL BIT(6) - #define MESON_SAR_ADC_REG11_VREF_VOLTAGE BIT(5) - #define MESON_SAR_ADC_REG11_EOC BIT(1) - #define MESON_SAR_ADC_REG11_VREF_SEL BIT(0) + #define MESON_SAR_ADC_REG11_CMV_SEL BIT(6) + #define MESON_SAR_ADC_REG11_VREF_VOLTAGE BIT(5) + #define MESON_SAR_ADC_REG11_EOC BIT(1) + #define MESON_SAR_ADC_REG11_VREF_SEL BIT(0) #define MESON_SAR_ADC_REG13 0x34 #define MESON_SAR_ADC_REG13_12BIT_CALIBRATION_MASK GENMASK(13, 8) @@ -315,19 +315,17 @@ static const struct iio_chan_spec meson_sar_adc_and_temp_iio_channels[] = { struct meson_sar_adc_param { bool has_bl30_integration; unsigned long clock_rate; - u32 bandgap_reg; unsigned int resolution; const struct regmap_config *regmap_config; u8 temperature_trimming_bits; unsigned int temperature_multiplier; unsigned int temperature_divider; u8 disable_ring_counter; - bool has_reg11; bool has_vref_select; u8 vref_select; u8 cmv_select; u8 adc_eoc; - enum meson_sar_adc_vref_sel vref_volatge; + enum meson_sar_adc_vref_sel vref_voltage; }; struct meson_sar_adc_data { @@ -976,7 +974,7 @@ static int meson_sar_adc_init(struct iio_dev *indio_dev) MESON_SAR_ADC_REG3_CTRL_CONT_RING_COUNTER_EN, regval); - if (priv->param->has_reg11) { + if (priv->param->regmap_config->max_register >= MESON_SAR_ADC_REG11) { regval = FIELD_PREP(MESON_SAR_ADC_REG11_EOC, priv->param->adc_eoc); regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG11, MESON_SAR_ADC_REG11_EOC, regval); @@ -989,7 +987,7 @@ static int meson_sar_adc_init(struct iio_dev *indio_dev) } regval = FIELD_PREP(MESON_SAR_ADC_REG11_VREF_VOLTAGE, - priv->param->vref_volatge); + priv->param->vref_voltage); regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG11, MESON_SAR_ADC_REG11_VREF_VOLTAGE, regval); @@ -1013,16 +1011,15 @@ static int meson_sar_adc_init(struct iio_dev *indio_dev) static void meson_sar_adc_set_bandgap(struct iio_dev *indio_dev, bool on_off) { struct meson_sar_adc_priv *priv = iio_priv(indio_dev); - const struct meson_sar_adc_param *param = priv->param; - u32 enable_mask; - if (param->bandgap_reg == MESON_SAR_ADC_REG11) - enable_mask = MESON_SAR_ADC_REG11_BANDGAP_EN; + if (priv->param->regmap_config->max_register >= MESON_SAR_ADC_REG11) + regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG11, + MESON_SAR_ADC_REG11_BANDGAP_EN, + on_off ? MESON_SAR_ADC_REG11_BANDGAP_EN : 0); else - enable_mask = MESON_SAR_ADC_DELTA_10_TS_VBG_EN; - - regmap_update_bits(priv->regmap, param->bandgap_reg, enable_mask, - on_off ? enable_mask : 0); + regmap_update_bits(priv->regmap, MESON_SAR_ADC_DELTA_10, + MESON_SAR_ADC_DELTA_10_TS_VBG_EN, + on_off ? MESON_SAR_ADC_DELTA_10_TS_VBG_EN : 0); } static int meson_sar_adc_hw_enable(struct iio_dev *indio_dev) @@ -1186,7 +1183,6 @@ static const struct iio_info meson_sar_adc_iio_info = { static const struct meson_sar_adc_param meson_sar_adc_meson8_param = { .has_bl30_integration = false, .clock_rate = 1150000, - .bandgap_reg = MESON_SAR_ADC_DELTA_10, .regmap_config = &meson_sar_adc_regmap_config_meson8, .resolution = 10, .temperature_trimming_bits = 4, @@ -1197,7 +1193,6 @@ static const struct meson_sar_adc_param meson_sar_adc_meson8_param = { static const struct meson_sar_adc_param meson_sar_adc_meson8b_param = { .has_bl30_integration = false, .clock_rate = 1150000, - .bandgap_reg = MESON_SAR_ADC_DELTA_10, .regmap_config = &meson_sar_adc_regmap_config_meson8, .resolution = 10, .temperature_trimming_bits = 5, @@ -1208,35 +1203,29 @@ static const struct meson_sar_adc_param meson_sar_adc_meson8b_param = { static const struct meson_sar_adc_param meson_sar_adc_gxbb_param = { .has_bl30_integration = true, .clock_rate = 1200000, - .bandgap_reg = MESON_SAR_ADC_REG11, .regmap_config = &meson_sar_adc_regmap_config_gxbb, .resolution = 10, - .has_reg11 = true, - .vref_volatge = 1, + .vref_voltage = 1, .cmv_select = 1, }; static const struct meson_sar_adc_param meson_sar_adc_gxl_param = { .has_bl30_integration = true, .clock_rate = 1200000, - .bandgap_reg = MESON_SAR_ADC_REG11, .regmap_config = &meson_sar_adc_regmap_config_gxbb, .resolution = 12, .disable_ring_counter = 1, - .has_reg11 = true, - .vref_volatge = 1, + .vref_voltage = 1, .cmv_select = 1, }; static const struct meson_sar_adc_param meson_sar_adc_axg_param = { .has_bl30_integration = true, .clock_rate = 1200000, - .bandgap_reg = MESON_SAR_ADC_REG11, .regmap_config = &meson_sar_adc_regmap_config_gxbb, .resolution = 12, .disable_ring_counter = 1, - .has_reg11 = true, - .vref_volatge = 1, + .vref_voltage = 1, .has_vref_select = true, .vref_select = VREF_VDDA, .cmv_select = 1, @@ -1245,11 +1234,9 @@ static const struct meson_sar_adc_param meson_sar_adc_axg_param = { static const struct meson_sar_adc_param meson_sar_adc_g12a_param = { .has_bl30_integration = false, .clock_rate = 1200000, - .bandgap_reg = MESON_SAR_ADC_REG11, .regmap_config = &meson_sar_adc_regmap_config_gxbb, .resolution = 12, .disable_ring_counter = 1, - .has_reg11 = true, .adc_eoc = 1, .has_vref_select = true, .vref_select = VREF_VDDA, diff --git a/drivers/iio/adc/pac1921.c b/drivers/iio/adc/pac1921.c index b0f6727cfe38..90f61c47b1c4 100644 --- a/drivers/iio/adc/pac1921.c +++ b/drivers/iio/adc/pac1921.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -67,6 +68,14 @@ enum pac1921_mxsl { #define PAC1921_DEFAULT_DI_GAIN 0 /* 2^(value): 1x gain (HW default) */ #define PAC1921_DEFAULT_NUM_SAMPLES 0 /* 2^(value): 1 sample (HW default) */ +#define PAC1921_ACPI_GET_uOHMS_VALS 0 +#define PAC1921_ACPI_GET_LABEL 1 + +/* f7bb9932-86ee-4516-a236-7a7a742e55cb */ +static const guid_t pac1921_guid = + GUID_INIT(0xf7bb9932, 0x86ee, 0x4516, 0xa2, + 0x36, 0x7a, 0x7a, 0x74, 0x2e, 0x55, 0xcb); + /* * Pre-computed scale factors for BUS voltage * format: IIO_VAL_INT_PLUS_NANO @@ -200,7 +209,7 @@ struct pac1921_priv { struct { u16 chan[PAC1921_NUM_MEAS_CHANS]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; }; @@ -782,7 +791,7 @@ static ssize_t pac1921_write_shunt_resistor(struct iio_dev *indio_dev, const char *buf, size_t len) { struct pac1921_priv *priv = iio_priv(indio_dev); - u64 rshunt_uohm; + u32 rshunt_uohm; int val, val_fract; int ret; @@ -793,10 +802,17 @@ static ssize_t pac1921_write_shunt_resistor(struct iio_dev *indio_dev, if (ret) return ret; - rshunt_uohm = val * MICRO + val_fract; - if (rshunt_uohm == 0 || rshunt_uohm > INT_MAX) + /* + * This check validates the shunt is not zero and does not surpass + * INT_MAX. The check is done before calculating in order to avoid + * val * MICRO overflowing. + */ + if ((!val && !val_fract) || val > INT_MAX / MICRO || + (val == INT_MAX / MICRO && val_fract > INT_MAX % MICRO)) return -EINVAL; + rshunt_uohm = val * MICRO + val_fract; + guard(mutex)(&priv->lock); priv->rshunt_uohm = rshunt_uohm; @@ -1151,6 +1167,61 @@ static void pac1921_regulator_disable(void *data) regulator_disable(regulator); } +/* + * Documentation related to the ACPI device definition + * https://ww1.microchip.com/downloads/aemDocuments/documents/OTH/ApplicationNotes/ApplicationNotes/PAC193X-Integration-Notes-for-Microsoft-Windows-10-and-Windows-11-Driver-Support-DS00002534.pdf + */ +static int pac1921_match_acpi_device(struct iio_dev *indio_dev) +{ + acpi_handle handle; + union acpi_object *status; + char *label; + struct pac1921_priv *priv = iio_priv(indio_dev); + struct device *dev = &priv->client->dev; + + handle = ACPI_HANDLE(dev); + + status = acpi_evaluate_dsm(handle, &pac1921_guid, 1, + PAC1921_ACPI_GET_uOHMS_VALS, NULL); + if (!status) + return dev_err_probe(dev, -EINVAL, + "Could not read shunt from ACPI table\n"); + + priv->rshunt_uohm = status->package.elements[0].integer.value; + ACPI_FREE(status); + + status = acpi_evaluate_dsm(handle, &pac1921_guid, 1, + PAC1921_ACPI_GET_LABEL, NULL); + if (!status) + return dev_err_probe(dev, -EINVAL, + "Could not read label from ACPI table\n"); + + label = devm_kstrdup(dev, status->package.elements[0].string.pointer, + GFP_KERNEL); + if (!label) + return -ENOMEM; + + indio_dev->label = label; + ACPI_FREE(status); + + return 0; +} + +static int pac1921_parse_of_fw(struct iio_dev *indio_dev) +{ + int ret; + struct pac1921_priv *priv = iio_priv(indio_dev); + struct device *dev = &priv->client->dev; + + ret = device_property_read_u32(dev, "shunt-resistor-micro-ohms", + &priv->rshunt_uohm); + if (ret) + return dev_err_probe(dev, ret, + "Cannot read shunt resistor property\n"); + + return 0; +} + static int pac1921_probe(struct i2c_client *client) { struct device *dev = &client->dev; @@ -1179,11 +1250,14 @@ static int pac1921_probe(struct i2c_client *client) priv->di_gain = PAC1921_DEFAULT_DI_GAIN; priv->n_samples = PAC1921_DEFAULT_NUM_SAMPLES; - ret = device_property_read_u32(dev, "shunt-resistor-micro-ohms", - &priv->rshunt_uohm); + if (is_acpi_device_node(dev->fwnode)) + ret = pac1921_match_acpi_device(indio_dev); + else + ret = pac1921_parse_of_fw(indio_dev); if (ret) return dev_err_probe(dev, ret, - "Cannot read shunt resistor property\n"); + "Parameter parsing error\n"); + if (priv->rshunt_uohm == 0 || priv->rshunt_uohm > INT_MAX) return dev_err_probe(dev, -EINVAL, "Invalid shunt resistor: %u\n", @@ -1246,11 +1320,18 @@ static const struct of_device_id pac1921_of_match[] = { }; MODULE_DEVICE_TABLE(of, pac1921_of_match); +static const struct acpi_device_id pac1921_acpi_match[] = { + { "MCHP1921" }, + { } +}; +MODULE_DEVICE_TABLE(acpi, pac1921_acpi_match); + static struct i2c_driver pac1921_driver = { .driver = { .name = "pac1921", .pm = pm_sleep_ptr(&pac1921_pm_ops), .of_match_table = pac1921_of_match, + .acpi_match_table = pac1921_acpi_match, }, .probe = pac1921_probe, .id_table = pac1921_id, diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c index 240cfa391674..a29e54754c8f 100644 --- a/drivers/iio/adc/rockchip_saradc.c +++ b/drivers/iio/adc/rockchip_saradc.c @@ -363,11 +363,13 @@ static irqreturn_t rockchip_saradc_trigger_handler(int irq, void *p) */ struct { u16 values[SARADC_MAX_CHANNELS]; - int64_t timestamp; + aligned_s64 timestamp; } data; int ret; int i, j = 0; + memset(&data, 0, sizeof(data)); + mutex_lock(&info->lock); iio_for_each_active_channel(i_dev, i) { diff --git a/drivers/iio/adc/rtq6056.c b/drivers/iio/adc/rtq6056.c index 56ed948a8ae1..337bc8b31b2c 100644 --- a/drivers/iio/adc/rtq6056.c +++ b/drivers/iio/adc/rtq6056.c @@ -634,7 +634,7 @@ static irqreturn_t rtq6056_buffer_trigger_handler(int irq, void *p) struct device *dev = priv->dev; struct { u16 vals[RTQ6056_MAX_CHANNEL]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } data; unsigned int raw; int i = 0, bit, ret; diff --git a/drivers/iio/adc/rzg2l_adc.c b/drivers/iio/adc/rzg2l_adc.c index cd3a7e46ea53..883c167c0670 100644 --- a/drivers/iio/adc/rzg2l_adc.c +++ b/drivers/iio/adc/rzg2l_adc.c @@ -8,12 +8,13 @@ */ #include -#include +#include #include #include #include #include #include +#include #include #include #include @@ -32,20 +33,15 @@ #define RZG2L_ADM1_MS BIT(2) #define RZG2L_ADM1_BS BIT(4) #define RZG2L_ADM1_EGA_MASK GENMASK(13, 12) -#define RZG2L_ADM2_CHSEL_MASK GENMASK(7, 0) #define RZG2L_ADM3_ADIL_MASK GENMASK(31, 24) #define RZG2L_ADM3_ADCMP_MASK GENMASK(23, 16) -#define RZG2L_ADM3_ADCMP_E FIELD_PREP(RZG2L_ADM3_ADCMP_MASK, 0xe) -#define RZG2L_ADM3_ADSMP_MASK GENMASK(15, 0) #define RZG2L_ADINT 0x20 -#define RZG2L_ADINT_INTEN_MASK GENMASK(7, 0) #define RZG2L_ADINT_CSEEN BIT(16) #define RZG2L_ADINT_INTS BIT(31) #define RZG2L_ADSTS 0x24 #define RZG2L_ADSTS_CSEST BIT(16) -#define RZG2L_ADSTS_INTST_MASK GENMASK(7, 0) #define RZG2L_ADIVC 0x28 #define RZG2L_ADIVC_DIVADC_MASK GENMASK(8, 0) @@ -56,12 +52,28 @@ #define RZG2L_ADCR(n) (0x30 + ((n) * 0x4)) #define RZG2L_ADCR_AD_MASK GENMASK(11, 0) -#define RZG2L_ADSMP_DEFAULT_SAMPLING 0x578 - -#define RZG2L_ADC_MAX_CHANNELS 8 -#define RZG2L_ADC_CHN_MASK 0x7 +#define RZG2L_ADC_MAX_CHANNELS 9 #define RZG2L_ADC_TIMEOUT usecs_to_jiffies(1 * 4) +/** + * struct rzg2l_adc_hw_params - ADC hardware specific parameters + * @default_adsmp: default ADC sampling period (see ADM3 register); index 0 is + * used for voltage channels, index 1 is used for temperature channel + * @adsmp_mask: ADC sampling period mask (see ADM3 register) + * @adint_inten_mask: conversion end interrupt mask (see ADINT register) + * @default_adcmp: default ADC cmp (see ADM3 register) + * @num_channels: number of supported channels + * @adivc: specifies if ADVIC register is available + */ +struct rzg2l_adc_hw_params { + u16 default_adsmp[2]; + u16 adsmp_mask; + u16 adint_inten_mask; + u8 default_adcmp; + u8 num_channels; + bool adivc; +}; + struct rzg2l_adc_data { const struct iio_chan_spec *channels; u8 num_channels; @@ -69,25 +81,36 @@ struct rzg2l_adc_data { struct rzg2l_adc { void __iomem *base; - struct clk *pclk; - struct clk *adclk; struct reset_control *presetn; struct reset_control *adrstn; - struct completion completion; const struct rzg2l_adc_data *data; + const struct rzg2l_adc_hw_params *hw_params; + struct completion completion; struct mutex lock; u16 last_val[RZG2L_ADC_MAX_CHANNELS]; + bool was_rpm_active; }; -static const char * const rzg2l_adc_channel_name[] = { - "adc0", - "adc1", - "adc2", - "adc3", - "adc4", - "adc5", - "adc6", - "adc7", +/** + * struct rzg2l_adc_channel - ADC channel descriptor + * @name: ADC channel name + * @type: ADC channel type + */ +struct rzg2l_adc_channel { + const char * const name; + enum iio_chan_type type; +}; + +static const struct rzg2l_adc_channel rzg2l_adc_channels[] = { + { "adc0", IIO_VOLTAGE }, + { "adc1", IIO_VOLTAGE }, + { "adc2", IIO_VOLTAGE }, + { "adc3", IIO_VOLTAGE }, + { "adc4", IIO_VOLTAGE }, + { "adc5", IIO_VOLTAGE }, + { "adc6", IIO_VOLTAGE }, + { "adc7", IIO_VOLTAGE }, + { "adc8", IIO_TEMP }, }; static unsigned int rzg2l_adc_readl(struct rzg2l_adc *adc, u32 reg) @@ -115,7 +138,7 @@ static void rzg2l_adc_pwr(struct rzg2l_adc *adc, bool on) static void rzg2l_adc_start_stop(struct rzg2l_adc *adc, bool start) { - int timeout = 5; + int ret; u32 reg; reg = rzg2l_adc_readl(adc, RZG2L_ADM(0)); @@ -128,15 +151,10 @@ static void rzg2l_adc_start_stop(struct rzg2l_adc *adc, bool start) if (start) return; - do { - usleep_range(100, 200); - reg = rzg2l_adc_readl(adc, RZG2L_ADM(0)); - timeout--; - if (!timeout) { - pr_err("%s stopping ADC timed out\n", __func__); - break; - } - } while (((reg & RZG2L_ADM0_ADBSY) || (reg & RZG2L_ADM0_ADCE))); + ret = read_poll_timeout(rzg2l_adc_readl, reg, !(reg & (RZG2L_ADM0_ADBSY | RZG2L_ADM0_ADCE)), + 200, 1000, true, adc, RZG2L_ADM(0)); + if (ret) + pr_err("%s stopping ADC timed out\n", __func__); } static void rzg2l_set_trigger(struct rzg2l_adc *adc) @@ -158,8 +176,18 @@ static void rzg2l_set_trigger(struct rzg2l_adc *adc) rzg2l_adc_writel(adc, RZG2L_ADM(1), reg); } +static u8 rzg2l_adc_ch_to_adsmp_index(u8 ch) +{ + if (rzg2l_adc_channels[ch].type == IIO_VOLTAGE) + return 0; + + return 1; +} + static int rzg2l_adc_conversion_setup(struct rzg2l_adc *adc, u8 ch) { + const struct rzg2l_adc_hw_params *hw_params = adc->hw_params; + u8 index = rzg2l_adc_ch_to_adsmp_index(ch); u32 reg; if (rzg2l_adc_readl(adc, RZG2L_ADM(0)) & RZG2L_ADM0_ADBSY) @@ -169,10 +197,15 @@ static int rzg2l_adc_conversion_setup(struct rzg2l_adc *adc, u8 ch) /* Select analog input channel subjected to conversion. */ reg = rzg2l_adc_readl(adc, RZG2L_ADM(2)); - reg &= ~RZG2L_ADM2_CHSEL_MASK; + reg &= ~GENMASK(hw_params->num_channels - 1, 0); reg |= BIT(ch); rzg2l_adc_writel(adc, RZG2L_ADM(2), reg); + reg = rzg2l_adc_readl(adc, RZG2L_ADM(3)); + reg &= ~hw_params->adsmp_mask; + reg |= hw_params->default_adsmp[index]; + rzg2l_adc_writel(adc, RZG2L_ADM(3), reg); + /* * Setup ADINT * INTS[31] - Select pulse signal @@ -181,36 +214,26 @@ static int rzg2l_adc_conversion_setup(struct rzg2l_adc *adc, u8 ch) */ reg = rzg2l_adc_readl(adc, RZG2L_ADINT); reg &= ~RZG2L_ADINT_INTS; - reg &= ~RZG2L_ADINT_INTEN_MASK; + reg &= ~hw_params->adint_inten_mask; reg |= (RZG2L_ADINT_CSEEN | BIT(ch)); rzg2l_adc_writel(adc, RZG2L_ADINT, reg); return 0; } -static int rzg2l_adc_set_power(struct iio_dev *indio_dev, bool on) -{ - struct device *dev = indio_dev->dev.parent; - - if (on) - return pm_runtime_resume_and_get(dev); - - return pm_runtime_put_sync(dev); -} - static int rzg2l_adc_conversion(struct iio_dev *indio_dev, struct rzg2l_adc *adc, u8 ch) { + const struct rzg2l_adc_hw_params *hw_params = adc->hw_params; + struct device *dev = indio_dev->dev.parent; int ret; - ret = rzg2l_adc_set_power(indio_dev, true); + ret = pm_runtime_resume_and_get(dev); if (ret) return ret; ret = rzg2l_adc_conversion_setup(adc, ch); - if (ret) { - rzg2l_adc_set_power(indio_dev, false); - return ret; - } + if (ret) + goto rpm_put; reinit_completion(&adc->completion); @@ -218,13 +241,16 @@ static int rzg2l_adc_conversion(struct iio_dev *indio_dev, struct rzg2l_adc *adc if (!wait_for_completion_timeout(&adc->completion, RZG2L_ADC_TIMEOUT)) { rzg2l_adc_writel(adc, RZG2L_ADINT, - rzg2l_adc_readl(adc, RZG2L_ADINT) & ~RZG2L_ADINT_INTEN_MASK); - rzg2l_adc_start_stop(adc, false); - rzg2l_adc_set_power(indio_dev, false); - return -ETIMEDOUT; + rzg2l_adc_readl(adc, RZG2L_ADINT) & ~hw_params->adint_inten_mask); + ret = -ETIMEDOUT; } - return rzg2l_adc_set_power(indio_dev, false); + rzg2l_adc_start_stop(adc, false); + +rpm_put: + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + return ret; } static int rzg2l_adc_read_raw(struct iio_dev *indio_dev, @@ -233,24 +259,22 @@ static int rzg2l_adc_read_raw(struct iio_dev *indio_dev, { struct rzg2l_adc *adc = iio_priv(indio_dev); int ret; - u8 ch; switch (mask) { - case IIO_CHAN_INFO_RAW: - if (chan->type != IIO_VOLTAGE) + case IIO_CHAN_INFO_RAW: { + if (chan->type != IIO_VOLTAGE && chan->type != IIO_TEMP) return -EINVAL; - mutex_lock(&adc->lock); - ch = chan->channel & RZG2L_ADC_CHN_MASK; - ret = rzg2l_adc_conversion(indio_dev, adc, ch); - if (ret) { - mutex_unlock(&adc->lock); + guard(mutex)(&adc->lock); + + ret = rzg2l_adc_conversion(indio_dev, adc, chan->channel); + if (ret) return ret; - } - *val = adc->last_val[ch]; - mutex_unlock(&adc->lock); + + *val = adc->last_val[chan->channel]; return IIO_VAL_INT; + } default: return -EINVAL; @@ -261,7 +285,7 @@ static int rzg2l_adc_read_label(struct iio_dev *iio_dev, const struct iio_chan_spec *chan, char *label) { - return sysfs_emit(label, "%s\n", rzg2l_adc_channel_name[chan->channel]); + return sysfs_emit(label, "%s\n", rzg2l_adc_channels[chan->channel].name); } static const struct iio_info rzg2l_adc_iio_info = { @@ -272,6 +296,7 @@ static const struct iio_info rzg2l_adc_iio_info = { static irqreturn_t rzg2l_adc_isr(int irq, void *dev_id) { struct rzg2l_adc *adc = dev_id; + const struct rzg2l_adc_hw_params *hw_params = adc->hw_params; unsigned long intst; u32 reg; int ch; @@ -284,11 +309,11 @@ static irqreturn_t rzg2l_adc_isr(int irq, void *dev_id) return IRQ_HANDLED; } - intst = reg & RZG2L_ADSTS_INTST_MASK; + intst = reg & GENMASK(hw_params->num_channels - 1, 0); if (!intst) return IRQ_NONE; - for_each_set_bit(ch, &intst, RZG2L_ADC_MAX_CHANNELS) + for_each_set_bit(ch, &intst, hw_params->num_channels) adc->last_val[ch] = rzg2l_adc_readl(adc, RZG2L_ADCR(ch)) & RZG2L_ADCR_AD_MASK; /* clear the channel interrupt */ @@ -301,6 +326,7 @@ static irqreturn_t rzg2l_adc_isr(int irq, void *dev_id) static int rzg2l_adc_parse_properties(struct platform_device *pdev, struct rzg2l_adc *adc) { + const struct rzg2l_adc_hw_params *hw_params = adc->hw_params; struct iio_chan_spec *chan_array; struct rzg2l_adc_data *data; unsigned int channel; @@ -313,15 +339,12 @@ static int rzg2l_adc_parse_properties(struct platform_device *pdev, struct rzg2l return -ENOMEM; num_channels = device_get_child_node_count(&pdev->dev); - if (!num_channels) { - dev_err(&pdev->dev, "no channel children\n"); - return -ENODEV; - } + if (!num_channels) + return dev_err_probe(&pdev->dev, -ENODEV, "no channel children\n"); - if (num_channels > RZG2L_ADC_MAX_CHANNELS) { - dev_err(&pdev->dev, "num of channel children out of range\n"); - return -EINVAL; - } + if (num_channels > hw_params->num_channels) + return dev_err_probe(&pdev->dev, -EINVAL, + "num of channel children out of range\n"); chan_array = devm_kcalloc(&pdev->dev, num_channels, sizeof(*chan_array), GFP_KERNEL); @@ -334,14 +357,14 @@ static int rzg2l_adc_parse_properties(struct platform_device *pdev, struct rzg2l if (ret) return ret; - if (channel >= RZG2L_ADC_MAX_CHANNELS) + if (channel >= hw_params->num_channels) return -EINVAL; - chan_array[i].type = IIO_VOLTAGE; + chan_array[i].type = rzg2l_adc_channels[channel].type; chan_array[i].indexed = 1; chan_array[i].channel = channel; chan_array[i].info_mask_separate = BIT(IIO_CHAN_INFO_RAW); - chan_array[i].datasheet_name = rzg2l_adc_channel_name[channel]; + chan_array[i].datasheet_name = rzg2l_adc_channels[channel].name; i++; } @@ -352,13 +375,13 @@ static int rzg2l_adc_parse_properties(struct platform_device *pdev, struct rzg2l return 0; } -static int rzg2l_adc_hw_init(struct rzg2l_adc *adc) +static int rzg2l_adc_hw_init(struct device *dev, struct rzg2l_adc *adc) { - int timeout = 5; + const struct rzg2l_adc_hw_params *hw_params = adc->hw_params; u32 reg; int ret; - ret = clk_prepare_enable(adc->pclk); + ret = pm_runtime_resume_and_get(dev); if (ret) return ret; @@ -367,20 +390,18 @@ static int rzg2l_adc_hw_init(struct rzg2l_adc *adc) reg |= RZG2L_ADM0_SRESB; rzg2l_adc_writel(adc, RZG2L_ADM(0), reg); - while (!(rzg2l_adc_readl(adc, RZG2L_ADM(0)) & RZG2L_ADM0_SRESB)) { - if (!timeout) { - ret = -EBUSY; - goto exit_hw_init; - } - timeout--; - usleep_range(100, 200); - } + ret = read_poll_timeout(rzg2l_adc_readl, reg, reg & RZG2L_ADM0_SRESB, + 200, 1000, false, adc, RZG2L_ADM(0)); + if (ret) + goto exit_hw_init; - /* Only division by 4 can be set */ - reg = rzg2l_adc_readl(adc, RZG2L_ADIVC); - reg &= ~RZG2L_ADIVC_DIVADC_MASK; - reg |= RZG2L_ADIVC_DIVADC_4; - rzg2l_adc_writel(adc, RZG2L_ADIVC, reg); + if (hw_params->adivc) { + /* Only division by 4 can be set */ + reg = rzg2l_adc_readl(adc, RZG2L_ADIVC); + reg &= ~RZG2L_ADIVC_DIVADC_MASK; + reg |= RZG2L_ADIVC_DIVADC_4; + rzg2l_adc_writel(adc, RZG2L_ADIVC, reg); + } /* * Setup AMD3 @@ -391,35 +412,18 @@ static int rzg2l_adc_hw_init(struct rzg2l_adc *adc) reg = rzg2l_adc_readl(adc, RZG2L_ADM(3)); reg &= ~RZG2L_ADM3_ADIL_MASK; reg &= ~RZG2L_ADM3_ADCMP_MASK; - reg &= ~RZG2L_ADM3_ADSMP_MASK; - reg |= (RZG2L_ADM3_ADCMP_E | RZG2L_ADSMP_DEFAULT_SAMPLING); + reg &= ~hw_params->adsmp_mask; + reg |= FIELD_PREP(RZG2L_ADM3_ADCMP_MASK, hw_params->default_adcmp) | + hw_params->default_adsmp[0]; + rzg2l_adc_writel(adc, RZG2L_ADM(3), reg); exit_hw_init: - clk_disable_unprepare(adc->pclk); - + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); return ret; } -static void rzg2l_adc_pm_runtime_disable(void *data) -{ - struct device *dev = data; - - pm_runtime_disable(dev->parent); -} - -static void rzg2l_adc_pm_runtime_set_suspended(void *data) -{ - struct device *dev = data; - - pm_runtime_set_suspended(dev->parent); -} - -static void rzg2l_adc_reset_assert(void *data) -{ - reset_control_assert(data); -} - static int rzg2l_adc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -434,6 +438,10 @@ static int rzg2l_adc_probe(struct platform_device *pdev) adc = iio_priv(indio_dev); + adc->hw_params = device_get_match_data(dev); + if (!adc->hw_params || adc->hw_params->num_channels > RZG2L_ADC_MAX_CHANNELS) + return -EINVAL; + ret = rzg2l_adc_parse_properties(pdev, adc); if (ret) return ret; @@ -444,63 +452,28 @@ static int rzg2l_adc_probe(struct platform_device *pdev) if (IS_ERR(adc->base)) return PTR_ERR(adc->base); - adc->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(adc->pclk)) { - dev_err(dev, "Failed to get pclk"); - return PTR_ERR(adc->pclk); - } + adc->adrstn = devm_reset_control_get_exclusive_deasserted(dev, "adrst-n"); + if (IS_ERR(adc->adrstn)) + return dev_err_probe(dev, PTR_ERR(adc->adrstn), + "failed to get/deassert adrst-n\n"); - adc->adclk = devm_clk_get(dev, "adclk"); - if (IS_ERR(adc->adclk)) { - dev_err(dev, "Failed to get adclk"); - return PTR_ERR(adc->adclk); - } + adc->presetn = devm_reset_control_get_exclusive_deasserted(dev, "presetn"); + if (IS_ERR(adc->presetn)) + return dev_err_probe(dev, PTR_ERR(adc->presetn), + "failed to get/deassert presetn\n"); - adc->adrstn = devm_reset_control_get_exclusive(dev, "adrst-n"); - if (IS_ERR(adc->adrstn)) { - dev_err(dev, "failed to get adrstn\n"); - return PTR_ERR(adc->adrstn); - } - - adc->presetn = devm_reset_control_get_exclusive(dev, "presetn"); - if (IS_ERR(adc->presetn)) { - dev_err(dev, "failed to get presetn\n"); - return PTR_ERR(adc->presetn); - } - - ret = reset_control_deassert(adc->adrstn); - if (ret) { - dev_err(&pdev->dev, "failed to deassert adrstn pin, %d\n", ret); + pm_runtime_set_autosuspend_delay(dev, 300); + pm_runtime_use_autosuspend(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) return ret; - } - ret = devm_add_action_or_reset(&pdev->dev, - rzg2l_adc_reset_assert, adc->adrstn); - if (ret) { - dev_err(&pdev->dev, "failed to register adrstn assert devm action, %d\n", - ret); - return ret; - } + platform_set_drvdata(pdev, indio_dev); - ret = reset_control_deassert(adc->presetn); - if (ret) { - dev_err(&pdev->dev, "failed to deassert presetn pin, %d\n", ret); - return ret; - } - - ret = devm_add_action_or_reset(&pdev->dev, - rzg2l_adc_reset_assert, adc->presetn); - if (ret) { - dev_err(&pdev->dev, "failed to register presetn assert devm action, %d\n", - ret); - return ret; - } - - ret = rzg2l_adc_hw_init(adc); - if (ret) { - dev_err(&pdev->dev, "failed to initialize ADC HW, %d\n", ret); - return ret; - } + ret = rzg2l_adc_hw_init(dev, adc); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "failed to initialize ADC HW\n"); irq = platform_get_irq(pdev, 0); if (irq < 0) @@ -513,72 +486,130 @@ static int rzg2l_adc_probe(struct platform_device *pdev) init_completion(&adc->completion); - platform_set_drvdata(pdev, indio_dev); - indio_dev->name = DRIVER_NAME; indio_dev->info = &rzg2l_adc_iio_info; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = adc->data->channels; indio_dev->num_channels = adc->data->num_channels; - pm_runtime_set_suspended(dev); - ret = devm_add_action_or_reset(&pdev->dev, - rzg2l_adc_pm_runtime_set_suspended, &indio_dev->dev); - if (ret) - return ret; - - pm_runtime_enable(dev); - ret = devm_add_action_or_reset(&pdev->dev, - rzg2l_adc_pm_runtime_disable, &indio_dev->dev); - if (ret) - return ret; - return devm_iio_device_register(dev, indio_dev); } +static const struct rzg2l_adc_hw_params rzg2l_hw_params = { + .num_channels = 8, + .default_adcmp = 0xe, + .default_adsmp = { 0x578 }, + .adsmp_mask = GENMASK(15, 0), + .adint_inten_mask = GENMASK(7, 0), + .adivc = true +}; + +static const struct rzg2l_adc_hw_params rzg3s_hw_params = { + .num_channels = 9, + .default_adcmp = 0x1d, + .default_adsmp = { 0x7f, 0xff }, + .adsmp_mask = GENMASK(7, 0), + .adint_inten_mask = GENMASK(11, 0), +}; + static const struct of_device_id rzg2l_adc_match[] = { - { .compatible = "renesas,rzg2l-adc",}, + { .compatible = "renesas,r9a08g045-adc", .data = &rzg3s_hw_params }, + { .compatible = "renesas,rzg2l-adc", .data = &rzg2l_hw_params }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, rzg2l_adc_match); -static int __maybe_unused rzg2l_adc_pm_runtime_suspend(struct device *dev) +static int rzg2l_adc_pm_runtime_suspend(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct rzg2l_adc *adc = iio_priv(indio_dev); rzg2l_adc_pwr(adc, false); - clk_disable_unprepare(adc->adclk); - clk_disable_unprepare(adc->pclk); return 0; } -static int __maybe_unused rzg2l_adc_pm_runtime_resume(struct device *dev) +static int rzg2l_adc_pm_runtime_resume(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct rzg2l_adc *adc = iio_priv(indio_dev); - int ret; - - ret = clk_prepare_enable(adc->pclk); - if (ret) - return ret; - - ret = clk_prepare_enable(adc->adclk); - if (ret) { - clk_disable_unprepare(adc->pclk); - return ret; - } rzg2l_adc_pwr(adc, true); return 0; } +static int rzg2l_adc_suspend(struct device *dev) +{ + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct rzg2l_adc *adc = iio_priv(indio_dev); + struct reset_control_bulk_data resets[] = { + { .rstc = adc->presetn }, + { .rstc = adc->adrstn }, + }; + int ret; + + if (pm_runtime_suspended(dev)) { + adc->was_rpm_active = false; + } else { + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; + adc->was_rpm_active = true; + } + + ret = reset_control_bulk_assert(ARRAY_SIZE(resets), resets); + if (ret) + goto rpm_restore; + + return 0; + +rpm_restore: + if (adc->was_rpm_active) + pm_runtime_force_resume(dev); + + return ret; +} + +static int rzg2l_adc_resume(struct device *dev) +{ + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct rzg2l_adc *adc = iio_priv(indio_dev); + struct reset_control_bulk_data resets[] = { + { .rstc = adc->adrstn }, + { .rstc = adc->presetn }, + }; + int ret; + + ret = reset_control_bulk_deassert(ARRAY_SIZE(resets), resets); + if (ret) + return ret; + + if (adc->was_rpm_active) { + ret = pm_runtime_force_resume(dev); + if (ret) + goto resets_restore; + } + + ret = rzg2l_adc_hw_init(dev, adc); + if (ret) + goto rpm_restore; + + return 0; + +rpm_restore: + if (adc->was_rpm_active) { + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + } +resets_restore: + reset_control_bulk_assert(ARRAY_SIZE(resets), resets); + return ret; +} + static const struct dev_pm_ops rzg2l_adc_pm_ops = { - SET_RUNTIME_PM_OPS(rzg2l_adc_pm_runtime_suspend, - rzg2l_adc_pm_runtime_resume, - NULL) + RUNTIME_PM_OPS(rzg2l_adc_pm_runtime_suspend, rzg2l_adc_pm_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(rzg2l_adc_suspend, rzg2l_adc_resume) }; static struct platform_driver rzg2l_adc_driver = { @@ -586,7 +617,7 @@ static struct platform_driver rzg2l_adc_driver = { .driver = { .name = DRIVER_NAME, .of_match_table = rzg2l_adc_match, - .pm = &rzg2l_adc_pm_ops, + .pm = pm_ptr(&rzg2l_adc_pm_ops), }, }; diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index 1f9eca2fb2bf..fe11b0d8eab3 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -691,11 +691,14 @@ static int stm32_dfsdm_generic_channel_parse_of(struct stm32_dfsdm *dfsdm, return -EINVAL; } - ret = fwnode_property_read_string(node, "label", &ch->datasheet_name); - if (ret < 0) { - dev_err(&indio_dev->dev, - " Error parsing 'label' for idx %d\n", ch->channel); - return ret; + if (fwnode_property_present(node, "label")) { + /* label is optional */ + ret = fwnode_property_read_string(node, "label", &ch->datasheet_name); + if (ret < 0) { + dev_err(&indio_dev->dev, + " Error parsing 'label' for idx %d\n", ch->channel); + return ret; + } } df_ch = &dfsdm->ch_list[ch->channel]; diff --git a/drivers/iio/adc/ti-adc081c.c b/drivers/iio/adc/ti-adc081c.c index 6c2cb3dabbbf..1af9be071d8d 100644 --- a/drivers/iio/adc/ti-adc081c.c +++ b/drivers/iio/adc/ti-adc081c.c @@ -37,7 +37,7 @@ struct adc081c { /* Ensure natural alignment of buffer elements */ struct { u16 channel; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/adc/ti-adc084s021.c b/drivers/iio/adc/ti-adc084s021.c index bf98f9bf942a..da16876c32ae 100644 --- a/drivers/iio/adc/ti-adc084s021.c +++ b/drivers/iio/adc/ti-adc084s021.c @@ -29,7 +29,7 @@ struct adc084s021 { /* Buffer used to align data */ struct { __be16 channels[4]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; /* * DMA (thus cache coherency maintenance) may require the diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c index 47fe8e16aee4..4355726b373a 100644 --- a/drivers/iio/adc/ti-ads1015.c +++ b/drivers/iio/adc/ti-ads1015.c @@ -448,7 +448,7 @@ static irqreturn_t ads1015_trigger_handler(int irq, void *p) /* Ensure natural alignment of timestamp */ struct { s16 chan; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; int chan, ret, res; diff --git a/drivers/iio/adc/ti-ads1119.c b/drivers/iio/adc/ti-ads1119.c index e9d9d4d46d38..de019b3faa48 100644 --- a/drivers/iio/adc/ti-ads1119.c +++ b/drivers/iio/adc/ti-ads1119.c @@ -500,12 +500,14 @@ static irqreturn_t ads1119_trigger_handler(int irq, void *private) struct iio_dev *indio_dev = pf->indio_dev; struct ads1119_state *st = iio_priv(indio_dev); struct { - unsigned int sample; - s64 timestamp __aligned(8); + s16 sample; + aligned_s64 timestamp; } scan; unsigned int index; int ret; + memset(&scan, 0, sizeof(scan)); + if (!iio_trigger_using_own(indio_dev)) { index = find_first_bit(indio_dev->active_scan_mask, iio_get_masklength(indio_dev)); diff --git a/drivers/iio/adc/ti-ads124s08.c b/drivers/iio/adc/ti-ads124s08.c index 425b48d8986f..f452f57f11c9 100644 --- a/drivers/iio/adc/ti-ads124s08.c +++ b/drivers/iio/adc/ti-ads124s08.c @@ -183,9 +183,9 @@ static int ads124s_reset(struct iio_dev *indio_dev) struct ads124s_private *priv = iio_priv(indio_dev); if (priv->reset_gpio) { - gpiod_set_value(priv->reset_gpio, 0); + gpiod_set_value_cansleep(priv->reset_gpio, 0); udelay(200); - gpiod_set_value(priv->reset_gpio, 1); + gpiod_set_value_cansleep(priv->reset_gpio, 1); } else { return ads124s_write_cmd(indio_dev, ADS124S08_CMD_RESET); } diff --git a/drivers/iio/adc/ti-ads1298.c b/drivers/iio/adc/ti-ads1298.c index 36d43495f603..03f762415fa5 100644 --- a/drivers/iio/adc/ti-ads1298.c +++ b/drivers/iio/adc/ti-ads1298.c @@ -613,6 +613,8 @@ static int ads1298_init(struct iio_dev *indio_dev) } indio_dev->name = devm_kasprintf(dev, GFP_KERNEL, "ads129%u%s", indio_dev->num_channels, suffix); + if (!indio_dev->name) + return -ENOMEM; /* Enable internal test signal, double amplitude, double frequency */ ret = regmap_write(priv->regmap, ADS1298_REG_CONFIG2, diff --git a/drivers/iio/adc/ti-ads131e08.c b/drivers/iio/adc/ti-ads131e08.c index 31f1f229d97a..91a79ebc4bde 100644 --- a/drivers/iio/adc/ti-ads131e08.c +++ b/drivers/iio/adc/ti-ads131e08.c @@ -102,7 +102,7 @@ struct ads131e08_state { struct completion completion; struct { u8 data[ADS131E08_NUM_DATA_BYTES_MAX]; - s64 ts __aligned(8); + aligned_s64 ts; } tmp_buf; u8 tx_buf[3] __aligned(IIO_DMA_MINALIGN); diff --git a/drivers/iio/adc/ti-ads8688.c b/drivers/iio/adc/ti-ads8688.c index 9b1814f1965a..a31658b760a4 100644 --- a/drivers/iio/adc/ti-ads8688.c +++ b/drivers/iio/adc/ti-ads8688.c @@ -381,7 +381,7 @@ static irqreturn_t ads8688_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; /* Ensure naturally aligned timestamp */ - u16 buffer[ADS8688_MAX_CHANNELS + sizeof(s64)/sizeof(u16)] __aligned(8); + u16 buffer[ADS8688_MAX_CHANNELS + sizeof(s64)/sizeof(u16)] __aligned(8) = { }; int i, j = 0; iio_for_each_active_channel(indio_dev, i) { diff --git a/drivers/iio/adc/ti-lmp92064.c b/drivers/iio/adc/ti-lmp92064.c index 169e3591320b..1e4a78677fe5 100644 --- a/drivers/iio/adc/ti-lmp92064.c +++ b/drivers/iio/adc/ti-lmp92064.c @@ -199,7 +199,7 @@ static irqreturn_t lmp92064_trigger_handler(int irq, void *p) struct lmp92064_adc_priv *priv = iio_priv(indio_dev); struct { u16 values[2]; - int64_t timestamp __aligned(8); + aligned_s64 timestamp; } data; int ret; diff --git a/drivers/iio/adc/ti-tsc2046.c b/drivers/iio/adc/ti-tsc2046.c index b56f2503f14c..7dde5713973f 100644 --- a/drivers/iio/adc/ti-tsc2046.c +++ b/drivers/iio/adc/ti-tsc2046.c @@ -157,7 +157,7 @@ struct tsc2046_adc_priv { /* Scan data for each channel */ u16 data[TI_TSC2046_MAX_CHAN]; /* Timestamp */ - s64 ts __aligned(8); + aligned_s64 ts; } scan_buf; /* diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c index 4d83c12975c5..513365d42aa5 100644 --- a/drivers/iio/adc/vf610_adc.c +++ b/drivers/iio/adc/vf610_adc.c @@ -173,10 +173,14 @@ struct vf610_adc { /* Ensure the timestamp is naturally aligned */ struct { u16 chan; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; }; +struct vf610_chip_info { + u8 num_channels; +}; + static const u32 vf610_hw_avgs[] = { 1, 4, 8, 16, 32 }; static const u32 vf610_lst_adder[] = { 3, 5, 7, 9, 13, 17, 21, 25 }; @@ -808,14 +812,31 @@ static const struct iio_info vf610_adc_iio_info = { .attrs = &vf610_attribute_group, }; +static const struct vf610_chip_info vf610_chip_info = { + .num_channels = ARRAY_SIZE(vf610_adc_iio_channels), +}; + +static const struct vf610_chip_info imx6sx_chip_info = { + .num_channels = 4, +}; + static const struct of_device_id vf610_adc_match[] = { - { .compatible = "fsl,vf610-adc", }, + { .compatible = "fsl,imx6sx-adc", .data = &imx6sx_chip_info}, + { .compatible = "fsl,vf610-adc", .data = &vf610_chip_info}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, vf610_adc_match); +static void vf610_adc_action_remove(void *d) +{ + struct vf610_adc *info = d; + + regulator_disable(info->vref); +} + static int vf610_adc_probe(struct platform_device *pdev) { + const struct vf610_chip_info *chip_info; struct device *dev = &pdev->dev; struct vf610_adc *info; struct iio_dev *indio_dev; @@ -823,10 +844,8 @@ static int vf610_adc_probe(struct platform_device *pdev) int ret; indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(struct vf610_adc)); - if (!indio_dev) { - dev_err(&pdev->dev, "Failed allocating iio device\n"); - return -ENOMEM; - } + if (!indio_dev) + return dev_err_probe(&pdev->dev, -ENOMEM, "Failed allocating iio device\n"); info = iio_priv(indio_dev); info->dev = &pdev->dev; @@ -835,6 +854,8 @@ static int vf610_adc_probe(struct platform_device *pdev) if (IS_ERR(info->regs)) return PTR_ERR(info->regs); + chip_info = device_get_match_data(dev); + irq = platform_get_irq(pdev, 0); if (irq < 0) return irq; @@ -842,17 +863,12 @@ static int vf610_adc_probe(struct platform_device *pdev) ret = devm_request_irq(info->dev, irq, vf610_adc_isr, 0, dev_name(&pdev->dev), indio_dev); - if (ret < 0) { - dev_err(&pdev->dev, "failed requesting irq, irq = %d\n", irq); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "failed requesting irq, irq = %d\n", irq); - info->clk = devm_clk_get(&pdev->dev, "adc"); - if (IS_ERR(info->clk)) { - dev_err(&pdev->dev, "failed getting clock, err = %ld\n", - PTR_ERR(info->clk)); - return PTR_ERR(info->clk); - } + info->clk = devm_clk_get_enabled(&pdev->dev, "adc"); + if (IS_ERR(info->clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(info->clk), "failed getting clock\n"); info->vref = devm_regulator_get(&pdev->dev, "vref"); if (IS_ERR(info->vref)) @@ -862,6 +878,10 @@ static int vf610_adc_probe(struct platform_device *pdev) if (ret) return ret; + ret = devm_add_action_or_reset(&pdev->dev, vf610_adc_action_remove, info); + if (ret) + return ret; + info->vref_uv = regulator_get_voltage(info->vref); device_property_read_u32_array(dev, "fsl,adck-max-frequency", info->max_adck_rate, 3); @@ -877,54 +897,23 @@ static int vf610_adc_probe(struct platform_device *pdev) indio_dev->info = &vf610_adc_iio_info; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = vf610_adc_iio_channels; - indio_dev->num_channels = ARRAY_SIZE(vf610_adc_iio_channels); - - ret = clk_prepare_enable(info->clk); - if (ret) { - dev_err(&pdev->dev, - "Could not prepare or enable the clock.\n"); - goto error_adc_clk_enable; - } + indio_dev->num_channels = chip_info->num_channels; vf610_adc_cfg_init(info); vf610_adc_hw_init(info); - ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time, - NULL, &iio_triggered_buffer_setup_ops); - if (ret < 0) { - dev_err(&pdev->dev, "Couldn't initialise the buffer\n"); - goto error_iio_device_register; - } + ret = devm_iio_triggered_buffer_setup(&pdev->dev, indio_dev, &iio_pollfunc_store_time, + NULL, &iio_triggered_buffer_setup_ops); + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "Couldn't initialise the buffer\n"); mutex_init(&info->lock); - ret = iio_device_register(indio_dev); - if (ret) { - dev_err(&pdev->dev, "Couldn't register the device.\n"); - goto error_adc_buffer_init; - } + ret = devm_iio_device_register(&pdev->dev, indio_dev); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Couldn't register the device.\n"); return 0; - -error_adc_buffer_init: - iio_triggered_buffer_cleanup(indio_dev); -error_iio_device_register: - clk_disable_unprepare(info->clk); -error_adc_clk_enable: - regulator_disable(info->vref); - - return ret; -} - -static void vf610_adc_remove(struct platform_device *pdev) -{ - struct iio_dev *indio_dev = platform_get_drvdata(pdev); - struct vf610_adc *info = iio_priv(indio_dev); - - iio_device_unregister(indio_dev); - iio_triggered_buffer_cleanup(indio_dev); - regulator_disable(info->vref); - clk_disable_unprepare(info->clk); } static int vf610_adc_suspend(struct device *dev) @@ -972,7 +961,6 @@ static DEFINE_SIMPLE_DEV_PM_OPS(vf610_adc_pm_ops, vf610_adc_suspend, static struct platform_driver vf610_adc_driver = { .probe = vf610_adc_probe, - .remove = vf610_adc_remove, .driver = { .name = DRIVER_NAME, .of_match_table = vf610_adc_match, diff --git a/drivers/iio/buffer/industrialio-buffer-dmaengine.c b/drivers/iio/buffer/industrialio-buffer-dmaengine.c index d2e1529ad8fd..614e1c4189a9 100644 --- a/drivers/iio/buffer/industrialio-buffer-dmaengine.c +++ b/drivers/iio/buffer/industrialio-buffer-dmaengine.c @@ -206,7 +206,7 @@ static const struct iio_dev_attr *iio_dmaengine_buffer_attrs[] = { /** * iio_dmaengine_buffer_alloc() - Allocate new buffer which uses DMAengine - * @dev: Parent device for the buffer + * @dev: DMA channel consumer device * @channel: DMA channel name, typically "rx". * * This allocates a new IIO buffer which internally uses the DMAengine framework @@ -288,6 +288,21 @@ void iio_dmaengine_buffer_free(struct iio_buffer *buffer) } EXPORT_SYMBOL_NS_GPL(iio_dmaengine_buffer_free, "IIO_DMAENGINE_BUFFER"); +/** + * iio_dmaengine_buffer_setup_ext() - Setup a DMA buffer for an IIO device + * @dev: DMA channel consumer device + * @indio_dev: IIO device to which to attach this buffer. + * @channel: DMA channel name, typically "rx". + * @dir: Direction of buffer (in or out) + * + * This allocates a new IIO buffer with devm_iio_dmaengine_buffer_alloc() + * and attaches it to an IIO device with iio_device_attach_buffer(). + * It also appends the INDIO_BUFFER_HARDWARE mode to the supported modes of the + * IIO device. + * + * Once done using the buffer iio_dmaengine_buffer_free() should be used to + * release it. + */ struct iio_buffer *iio_dmaengine_buffer_setup_ext(struct device *dev, struct iio_dev *indio_dev, const char *channel, @@ -321,7 +336,7 @@ static void __devm_iio_dmaengine_buffer_free(void *buffer) /** * devm_iio_dmaengine_buffer_setup_ext() - Setup a DMA buffer for an IIO device - * @dev: Parent device for the buffer + * @dev: Device for devm ownership and DMA channel consumer device * @indio_dev: IIO device to which to attach this buffer. * @channel: DMA channel name, typically "rx". * @dir: Direction of buffer (in or out) diff --git a/drivers/iio/chemical/bme680.h b/drivers/iio/chemical/bme680.h index 00ab89b3138b..7d86ed8b02e6 100644 --- a/drivers/iio/chemical/bme680.h +++ b/drivers/iio/chemical/bme680.h @@ -2,6 +2,7 @@ #ifndef BME680_H_ #define BME680_H_ +#include #include #define BME680_REG_CHIP_ID 0xD0 @@ -80,6 +81,7 @@ #define BME680_CALIB_RANGE_3_LEN 5 extern const struct regmap_config bme680_regmap_config; +extern const struct dev_pm_ops bme680_dev_pm_ops; int bme680_core_probe(struct device *dev, struct regmap *regmap, const char *name); diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c index d12270409c8a..9d73fd2cf52c 100644 --- a/drivers/iio/chemical/bme680_core.c +++ b/drivers/iio/chemical/bme680_core.c @@ -14,7 +14,10 @@ #include #include #include +#include +#include #include +#include #include #include @@ -111,6 +114,8 @@ enum bme680_scan { BME680_GAS, }; +static const char *const bme680_supply_names[] = { "vdd", "vddio" }; + struct bme680_data { struct regmap *regmap; struct bme680_calib bme680; @@ -817,9 +822,9 @@ static int bme680_read_gas(struct bme680_data *data, int *comp_gas_res) return 0; } -static int bme680_read_raw(struct iio_dev *indio_dev, - struct iio_chan_spec const *chan, - int *val, int *val2, long mask) +static int __bme680_read_raw(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + int *val, int *val2, long mask) { struct bme680_data *data = iio_priv(indio_dev); int chan_val, ret; @@ -874,11 +879,11 @@ static int bme680_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_RAW: switch (chan->type) { case IIO_TEMP: - ret = bme680_read_temp(data, (s16 *)&chan_val); + ret = bme680_read_temp(data, &temp_chan_val); if (ret) return ret; - *val = chan_val; + *val = temp_chan_val; return IIO_VAL_INT; case IIO_PRESSURE: ret = bme680_read_press(data, &chan_val); @@ -932,14 +937,33 @@ static int bme680_read_raw(struct iio_dev *indio_dev, } } +static int bme680_read_raw(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + int *val, int *val2, long mask) +{ + struct bme680_data *data = iio_priv(indio_dev); + struct device *dev = regmap_get_device(data->regmap); + int ret; + + ret = pm_runtime_resume_and_get(dev); + if (ret) + return ret; + + ret = __bme680_read_raw(indio_dev, chan, val, val2, mask); + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return ret; +} + static bool bme680_is_valid_oversampling(int rate) { return (rate > 0 && rate <= 16 && is_power_of_2(rate)); } -static int bme680_write_raw(struct iio_dev *indio_dev, - struct iio_chan_spec const *chan, - int val, int val2, long mask) +static int __bme680_write_raw(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + int val, int val2, long mask) { struct bme680_data *data = iio_priv(indio_dev); @@ -984,6 +1008,25 @@ static int bme680_write_raw(struct iio_dev *indio_dev, } } +static int bme680_write_raw(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + int val, int val2, long mask) +{ + struct bme680_data *data = iio_priv(indio_dev); + struct device *dev = regmap_get_device(data->regmap); + int ret; + + ret = pm_runtime_resume_and_get(dev); + if (ret) + return ret; + + ret = __bme680_write_raw(indio_dev, chan, val, val2, mask); + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return ret; +} + static const char bme680_oversampling_ratio_show[] = "1 2 4 8 16"; static IIO_CONST_ATTR(oversampling_ratio_available, @@ -1084,6 +1127,29 @@ out: return IRQ_HANDLED; } +static int bme680_buffer_preenable(struct iio_dev *indio_dev) +{ + struct bme680_data *data = iio_priv(indio_dev); + struct device *dev = regmap_get_device(data->regmap); + + return pm_runtime_resume_and_get(dev); +} + +static int bme680_buffer_postdisable(struct iio_dev *indio_dev) +{ + struct bme680_data *data = iio_priv(indio_dev); + struct device *dev = regmap_get_device(data->regmap); + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + return 0; +} + +static const struct iio_buffer_setup_ops bme680_buffer_setup_ops = { + .preenable = bme680_buffer_preenable, + .postdisable = bme680_buffer_postdisable, +}; + int bme680_core_probe(struct device *dev, struct regmap *regmap, const char *name) { @@ -1114,6 +1180,14 @@ int bme680_core_probe(struct device *dev, struct regmap *regmap, data->heater_dur = 150; /* milliseconds */ data->preheat_curr_mA = 0; + ret = devm_regulator_bulk_get_enable(dev, ARRAY_SIZE(bme680_supply_names), + bme680_supply_names); + if (ret) + return dev_err_probe(dev, ret, + "failed to get and enable supplies.\n"); + + fsleep(BME680_STARTUP_TIME_US); + ret = regmap_write(regmap, BME680_REG_SOFT_RESET, BME680_CMD_SOFTRESET); if (ret < 0) return dev_err_probe(dev, ret, "Failed to reset chip\n"); @@ -1149,15 +1223,47 @@ int bme680_core_probe(struct device *dev, struct regmap *regmap, ret = devm_iio_triggered_buffer_setup(dev, indio_dev, iio_pollfunc_store_time, bme680_trigger_handler, - NULL); + &bme680_buffer_setup_ops); if (ret) return dev_err_probe(dev, ret, "iio triggered buffer setup failed\n"); + /* Enable runtime PM */ + pm_runtime_set_autosuspend_delay(dev, BME680_STARTUP_TIME_US); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_active(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; + return devm_iio_device_register(dev, indio_dev); } EXPORT_SYMBOL_NS_GPL(bme680_core_probe, "IIO_BME680"); +static int bme680_runtime_suspend(struct device *dev) +{ + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct bme680_data *data = iio_priv(indio_dev); + + return bme680_set_mode(data, BME680_MODE_SLEEP); +} + +static int bme680_runtime_resume(struct device *dev) +{ + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct bme680_data *data = iio_priv(indio_dev); + int ret; + + ret = bme680_chip_config(data); + if (ret) + return ret; + + return bme680_gas_config(data); +} + +EXPORT_RUNTIME_DEV_PM_OPS(bme680_dev_pm_ops, bme680_runtime_suspend, + bme680_runtime_resume, NULL); + MODULE_AUTHOR("Himanshu Jha "); MODULE_DESCRIPTION("Bosch BME680 Driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/chemical/bme680_i2c.c b/drivers/iio/chemical/bme680_i2c.c index 7a949228b4a6..ac7763f98a6a 100644 --- a/drivers/iio/chemical/bme680_i2c.c +++ b/drivers/iio/chemical/bme680_i2c.c @@ -51,6 +51,7 @@ static struct i2c_driver bme680_i2c_driver = { .driver = { .name = "bme680_i2c", .of_match_table = bme680_of_i2c_match, + .pm = pm_ptr(&bme680_dev_pm_ops), }, .probe = bme680_i2c_probe, .id_table = bme680_i2c_id, diff --git a/drivers/iio/chemical/bme680_spi.c b/drivers/iio/chemical/bme680_spi.c index 3916a51ba68e..ecb24ba0ebc9 100644 --- a/drivers/iio/chemical/bme680_spi.c +++ b/drivers/iio/chemical/bme680_spi.c @@ -154,6 +154,7 @@ static struct spi_driver bme680_spi_driver = { .driver = { .name = "bme680_spi", .of_match_table = bme680_of_spi_match, + .pm = pm_ptr(&bme680_dev_pm_ops), }, .probe = bme680_spi_probe, .id_table = bme680_spi_id, diff --git a/drivers/iio/chemical/ccs811.c b/drivers/iio/chemical/ccs811.c index 17d1bc518bf2..451fb65dbe60 100644 --- a/drivers/iio/chemical/ccs811.c +++ b/drivers/iio/chemical/ccs811.c @@ -81,7 +81,7 @@ struct ccs811_data { /* Ensures correct alignment of timestamp if present */ struct { s16 channels[2]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/chemical/ens160_core.c b/drivers/iio/chemical/ens160_core.c index 4a89cd5894d9..48d5ad2075b6 100644 --- a/drivers/iio/chemical/ens160_core.c +++ b/drivers/iio/chemical/ens160_core.c @@ -60,7 +60,7 @@ struct ens160_data { struct mutex mutex; struct { __le16 chans[2]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan __aligned(IIO_DMA_MINALIGN); u8 fw_version[3]; __le16 buf; diff --git a/drivers/iio/chemical/scd30_core.c b/drivers/iio/chemical/scd30_core.c index ac3080929f0b..d613c54cb28d 100644 --- a/drivers/iio/chemical/scd30_core.c +++ b/drivers/iio/chemical/scd30_core.c @@ -594,7 +594,7 @@ static irqreturn_t scd30_trigger_handler(int irq, void *p) struct scd30_state *state = iio_priv(indio_dev); struct { int data[SCD30_MEAS_COUNT]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; int ret; diff --git a/drivers/iio/chemical/scd4x.c b/drivers/iio/chemical/scd4x.c index 52cad54e8572..50e3ac44422b 100644 --- a/drivers/iio/chemical/scd4x.c +++ b/drivers/iio/chemical/scd4x.c @@ -665,7 +665,7 @@ static irqreturn_t scd4x_trigger_handler(int irq, void *p) struct scd4x_state *state = iio_priv(indio_dev); struct { uint16_t data[3]; - int64_t ts __aligned(8); + aligned_s64 ts; } scan; int ret; diff --git a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c index c081b5caa475..97526ba87b93 100644 --- a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c +++ b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c @@ -109,8 +109,8 @@ static bool inv_update_chip_period(struct inv_sensors_timestamp *ts, static void inv_align_timestamp_it(struct inv_sensors_timestamp *ts) { - const int64_t period_min = ts->min_period * ts->mult; - const int64_t period_max = ts->max_period * ts->mult; + const int64_t period_min = (int64_t)ts->min_period * ts->mult; + const int64_t period_max = (int64_t)ts->max_period * ts->mult; int64_t add_max, sub_max; int64_t delta, jitter; int64_t adjust; diff --git a/drivers/iio/common/ssp_sensors/ssp_iio.c b/drivers/iio/common/ssp_sensors/ssp_iio.c index caa404edd9d0..78ac689de2fe 100644 --- a/drivers/iio/common/ssp_sensors/ssp_iio.c +++ b/drivers/iio/common/ssp_sensors/ssp_iio.c @@ -8,6 +8,8 @@ #include #include #include +#include +#include #include "ssp_iio_sensor.h" /** @@ -70,8 +72,7 @@ EXPORT_SYMBOL_NS(ssp_common_buffer_postdisable, "IIO_SSP_SENSORS"); int ssp_common_process_data(struct iio_dev *indio_dev, void *buf, unsigned int len, int64_t timestamp) { - __le32 time; - int64_t calculated_time = 0; + int64_t calculated_time; struct ssp_sensor_data *spd = iio_priv(indio_dev); if (indio_dev->scan_bytes == 0) @@ -82,11 +83,8 @@ int ssp_common_process_data(struct iio_dev *indio_dev, void *buf, */ memcpy(spd->buffer, buf, len); - if (indio_dev->scan_timestamp) { - memcpy(&time, &((char *)buf)[len], SSP_TIME_SIZE); - calculated_time = - timestamp + (int64_t)le32_to_cpu(time) * 1000000; - } + calculated_time = timestamp + + (int64_t)get_unaligned_le32(buf + len) * MEGA; return iio_push_to_buffers_with_timestamp(indio_dev, spd->buffer, calculated_time); diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig index 5d01ba4edbf3..5690a37267d8 100644 --- a/drivers/iio/dac/Kconfig +++ b/drivers/iio/dac/Kconfig @@ -80,7 +80,7 @@ config AD5421 depends on SPI help Say yes here to build support for Analog Devices AD5421 loop-powered - digital-to-analog convertors (DAC). + digital-to-analog converters (DAC). To compile this driver as module choose M here: the module will be called ad5421. @@ -348,6 +348,14 @@ config AD8801 To compile this driver as a module choose M here: the module will be called ad8801. +config BD79703 + tristate "ROHM Semiconductor BD79703 DAC driver" + depends on SPI + select REGMAP_SPI + help + Say yes here to build support for ROHM Semiconductor BD79703 Digital + to Analog Converter (DAC). + config CIO_DAC tristate "Measurement Computing CIO-DAC IIO driver" depends on X86 && (ISA_BUS || PC104) diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile index 414c152be779..8dd6cce81ed1 100644 --- a/drivers/iio/dac/Makefile +++ b/drivers/iio/dac/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_AD8460) += ad8460.o obj-$(CONFIG_AD8801) += ad8801.o obj-$(CONFIG_AD9739A) += ad9739a.o obj-$(CONFIG_ADI_AXI_DAC) += adi-axi-dac.o +obj-$(CONFIG_BD79703) += rohm-bd79703.o obj-$(CONFIG_CIO_DAC) += cio-dac.o obj-$(CONFIG_DPOT_DAC) += dpot-dac.o obj-$(CONFIG_DS4424) += ds4424.o diff --git a/drivers/iio/dac/ad3552r-common.c b/drivers/iio/dac/ad3552r-common.c index 0f495df2e5ce..03e0864f5084 100644 --- a/drivers/iio/dac/ad3552r-common.c +++ b/drivers/iio/dac/ad3552r-common.c @@ -22,11 +22,10 @@ EXPORT_SYMBOL_NS_GPL(ad3552r_ch_ranges, "IIO_AD3552R"); const s32 ad3542r_ch_ranges[AD3542R_MAX_RANGES][2] = { [AD3542R_CH_OUTPUT_RANGE_0__2P5V] = { 0, 2500 }, - [AD3542R_CH_OUTPUT_RANGE_0__3V] = { 0, 3000 }, [AD3542R_CH_OUTPUT_RANGE_0__5V] = { 0, 5000 }, [AD3542R_CH_OUTPUT_RANGE_0__10V] = { 0, 10000 }, - [AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V] = { -2500, 7500 }, - [AD3542R_CH_OUTPUT_RANGE_NEG_5__5V] = { -5000, 5000 } + [AD3542R_CH_OUTPUT_RANGE_NEG_5__5V] = { -5000, 5000 }, + [AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V] = { -2500, 7500 } }; EXPORT_SYMBOL_NS_GPL(ad3542r_ch_ranges, "IIO_AD3552R"); diff --git a/drivers/iio/dac/ad3552r-hs.c b/drivers/iio/dac/ad3552r-hs.c index 216c634f3eaf..8974df625670 100644 --- a/drivers/iio/dac/ad3552r-hs.c +++ b/drivers/iio/dac/ad3552r-hs.c @@ -329,6 +329,12 @@ static int ad3552r_hs_setup(struct ad3552r_hs_state *st) dev_info(st->dev, "Chip ID error. Expected 0x%x, Read 0x%x\n", AD3552R_ID, id); + /* Clear reset error flag, see ad3552r manual, rev B table 38. */ + ret = st->data->bus_reg_write(st->back, AD3552R_REG_ADDR_ERR_STATUS, + AD3552R_MASK_RESET_STATUS, 1); + if (ret) + return ret; + ret = st->data->bus_reg_write(st->back, AD3552R_REG_ADDR_SH_REFERENCE_CONFIG, 0, 1); diff --git a/drivers/iio/dac/ad3552r.h b/drivers/iio/dac/ad3552r.h index fd5a3dfd1d1c..4b5581039ae9 100644 --- a/drivers/iio/dac/ad3552r.h +++ b/drivers/iio/dac/ad3552r.h @@ -131,7 +131,7 @@ #define AD3552R_CH1_ACTIVE BIT(1) #define AD3552R_MAX_RANGES 5 -#define AD3542R_MAX_RANGES 6 +#define AD3542R_MAX_RANGES 5 #define AD3552R_QUAD_SPI 2 extern const s32 ad3552r_ch_ranges[AD3552R_MAX_RANGES][2]; @@ -189,16 +189,14 @@ enum ad3552r_ch_vref_select { enum ad3542r_ch_output_range { /* Range from 0 V to 2.5 V. Requires Rfb1x connection */ AD3542R_CH_OUTPUT_RANGE_0__2P5V, - /* Range from 0 V to 3 V. Requires Rfb1x connection */ - AD3542R_CH_OUTPUT_RANGE_0__3V, /* Range from 0 V to 5 V. Requires Rfb1x connection */ AD3542R_CH_OUTPUT_RANGE_0__5V, /* Range from 0 V to 10 V. Requires Rfb2x connection */ AD3542R_CH_OUTPUT_RANGE_0__10V, - /* Range from -2.5 V to 7.5 V. Requires Rfb2x connection */ - AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V, /* Range from -5 V to 5 V. Requires Rfb2x connection */ AD3542R_CH_OUTPUT_RANGE_NEG_5__5V, + /* Range from -2.5 V to 7.5 V. Requires Rfb2x connection */ + AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V, }; enum ad3552r_ch_output_range { diff --git a/drivers/iio/dac/ad5624r.h b/drivers/iio/dac/ad5624r.h index 14a439b06eb6..098fb5a7683d 100644 --- a/drivers/iio/dac/ad5624r.h +++ b/drivers/iio/dac/ad5624r.h @@ -41,11 +41,9 @@ struct ad5624r_chip_info { }; /** - * struct ad5446_state - driver instance specific data - * @indio_dev: the industrial I/O device + * struct ad5624r_state - driver instance specific data * @us: spi_device * @chip_info: chip model specific constants, available modes etc - * @reg: supply regulator * @vref_mv: actual reference voltage used * @pwr_down_mask power down mask * @pwr_down_mode current power down mode diff --git a/drivers/iio/dac/ad5686-spi.c b/drivers/iio/dac/ad5686-spi.c index 39b5dad0d6a5..9c727aa6ea18 100644 --- a/drivers/iio/dac/ad5686-spi.c +++ b/drivers/iio/dac/ad5686-spi.c @@ -95,11 +95,6 @@ static int ad5686_spi_probe(struct spi_device *spi) ad5686_spi_write, ad5686_spi_read); } -static void ad5686_spi_remove(struct spi_device *spi) -{ - ad5686_remove(&spi->dev); -} - static const struct spi_device_id ad5686_spi_id[] = { {"ad5310r", ID_AD5310R}, {"ad5672r", ID_AD5672R}, @@ -126,7 +121,6 @@ static struct spi_driver ad5686_spi_driver = { .name = "ad5686", }, .probe = ad5686_spi_probe, - .remove = ad5686_spi_remove, .id_table = ad5686_spi_id, }; diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c index 8dc578b08784..763af690c444 100644 --- a/drivers/iio/dac/ad5686.c +++ b/drivers/iio/dac/ad5686.c @@ -455,39 +455,28 @@ int ad5686_probe(struct device *dev, struct ad5686_state *st; struct iio_dev *indio_dev; unsigned int val, ref_bit_msk; + bool has_external_vref; u8 cmd; - int ret, i, voltage_uv = 0; + int ret, i; indio_dev = devm_iio_device_alloc(dev, sizeof(*st)); if (indio_dev == NULL) return -ENOMEM; st = iio_priv(indio_dev); - dev_set_drvdata(dev, indio_dev); st->dev = dev; st->write = write; st->read = read; - st->reg = devm_regulator_get_optional(dev, "vcc"); - if (!IS_ERR(st->reg)) { - ret = regulator_enable(st->reg); - if (ret) - return ret; - - ret = regulator_get_voltage(st->reg); - if (ret < 0) - goto error_disable_reg; - - voltage_uv = ret; - } - st->chip_info = &ad5686_chip_info_tbl[chip_type]; - if (voltage_uv) - st->vref_mv = voltage_uv / 1000; - else - st->vref_mv = st->chip_info->int_vref_mv; + ret = devm_regulator_get_enable_read_voltage(dev, "vcc"); + if (ret < 0 && ret != -ENODEV) + return ret; + + has_external_vref = ret != -ENODEV; + st->vref_mv = has_external_vref ? ret / 1000 : st->chip_info->int_vref_mv; /* Set all the power down mode for all channels to 1K pulldown */ for (i = 0; i < st->chip_info->num_channels; i++) @@ -505,12 +494,12 @@ int ad5686_probe(struct device *dev, case AD5310_REGMAP: cmd = AD5686_CMD_CONTROL_REG; ref_bit_msk = AD5310_REF_BIT_MSK; - st->use_internal_vref = !voltage_uv; + st->use_internal_vref = !has_external_vref; break; case AD5683_REGMAP: cmd = AD5686_CMD_CONTROL_REG; ref_bit_msk = AD5683_REF_BIT_MSK; - st->use_internal_vref = !voltage_uv; + st->use_internal_vref = !has_external_vref; break; case AD5686_REGMAP: cmd = AD5686_CMD_INTERNAL_REFER_SETUP; @@ -519,43 +508,22 @@ int ad5686_probe(struct device *dev, case AD5693_REGMAP: cmd = AD5686_CMD_CONTROL_REG; ref_bit_msk = AD5693_REF_BIT_MSK; - st->use_internal_vref = !voltage_uv; + st->use_internal_vref = !has_external_vref; break; default: - ret = -EINVAL; - goto error_disable_reg; + return -EINVAL; } - val = (voltage_uv | ref_bit_msk); + val = (has_external_vref | ref_bit_msk); ret = st->write(st, cmd, 0, !!val); if (ret) - goto error_disable_reg; + return ret; - ret = iio_device_register(indio_dev); - if (ret) - goto error_disable_reg; - - return 0; - -error_disable_reg: - if (!IS_ERR(st->reg)) - regulator_disable(st->reg); - return ret; + return devm_iio_device_register(dev, indio_dev); } EXPORT_SYMBOL_NS_GPL(ad5686_probe, "IIO_AD5686"); -void ad5686_remove(struct device *dev) -{ - struct iio_dev *indio_dev = dev_get_drvdata(dev); - struct ad5686_state *st = iio_priv(indio_dev); - - iio_device_unregister(indio_dev); - if (!IS_ERR(st->reg)) - regulator_disable(st->reg); -} -EXPORT_SYMBOL_NS_GPL(ad5686_remove, "IIO_AD5686"); - MODULE_AUTHOR("Michael Hennerich "); MODULE_DESCRIPTION("Analog Devices AD5686/85/84 DAC"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h index 760f852911df..e7d36bae3e59 100644 --- a/drivers/iio/dac/ad5686.h +++ b/drivers/iio/dac/ad5686.h @@ -115,10 +115,9 @@ struct ad5686_chip_info { }; /** - * struct ad5446_state - driver instance specific data + * struct ad5686_state - driver instance specific data * @spi: spi_device * @chip_info: chip model specific constants, available modes etc - * @reg: supply regulator * @vref_mv: actual reference voltage used * @pwr_down_mask: power down mask * @pwr_down_mode: current power down mode @@ -130,7 +129,6 @@ struct ad5686_chip_info { struct ad5686_state { struct device *dev; const struct ad5686_chip_info *chip_info; - struct regulator *reg; unsigned short vref_mv; unsigned int pwr_down_mask; unsigned int pwr_down_mode; @@ -157,7 +155,5 @@ int ad5686_probe(struct device *dev, const char *name, ad5686_write_func write, ad5686_read_func read); -void ad5686_remove(struct device *dev); - #endif /* __DRIVERS_IIO_DAC_AD5686_H__ */ diff --git a/drivers/iio/dac/ad5696-i2c.c b/drivers/iio/dac/ad5696-i2c.c index bbcda246c547..0156f32c12c8 100644 --- a/drivers/iio/dac/ad5696-i2c.c +++ b/drivers/iio/dac/ad5696-i2c.c @@ -65,11 +65,6 @@ static int ad5686_i2c_probe(struct i2c_client *i2c) ad5686_i2c_write, ad5686_i2c_read); } -static void ad5686_i2c_remove(struct i2c_client *i2c) -{ - ad5686_remove(&i2c->dev); -} - static const struct i2c_device_id ad5686_i2c_id[] = { {"ad5311r", ID_AD5311R}, {"ad5337r", ID_AD5337R}, @@ -116,7 +111,6 @@ static struct i2c_driver ad5686_i2c_driver = { .of_match_table = ad5686_of_match, }, .probe = ad5686_i2c_probe, - .remove = ad5686_i2c_remove, .id_table = ad5686_i2c_id, }; diff --git a/drivers/iio/dac/ad7293.c b/drivers/iio/dac/ad7293.c index 1d4032670482..d3f49b5337d2 100644 --- a/drivers/iio/dac/ad7293.c +++ b/drivers/iio/dac/ad7293.c @@ -141,8 +141,6 @@ struct ad7293_state { /* Protect against concurrent accesses to the device, page selection and data content */ struct mutex lock; struct gpio_desc *gpio_reset; - struct regulator *reg_avdd; - struct regulator *reg_vdrive; u8 page_select; u8 data[3] __aligned(IIO_DMA_MINALIGN); }; @@ -777,6 +775,15 @@ static int ad7293_reset(struct ad7293_state *st) static int ad7293_properties_parse(struct ad7293_state *st) { struct spi_device *spi = st->spi; + int ret; + + ret = devm_regulator_get_enable(&spi->dev, "avdd"); + if (ret) + return dev_err_probe(&spi->dev, ret, "failed to enable AVDD\n"); + + ret = devm_regulator_get_enable(&spi->dev, "vdrive"); + if (ret) + return dev_err_probe(&spi->dev, ret, "failed to enable VDRIVE\n"); st->gpio_reset = devm_gpiod_get_optional(&st->spi->dev, "reset", GPIOD_OUT_HIGH); @@ -784,24 +791,9 @@ static int ad7293_properties_parse(struct ad7293_state *st) return dev_err_probe(&spi->dev, PTR_ERR(st->gpio_reset), "failed to get the reset GPIO\n"); - st->reg_avdd = devm_regulator_get(&spi->dev, "avdd"); - if (IS_ERR(st->reg_avdd)) - return dev_err_probe(&spi->dev, PTR_ERR(st->reg_avdd), - "failed to get the AVDD voltage\n"); - - st->reg_vdrive = devm_regulator_get(&spi->dev, "vdrive"); - if (IS_ERR(st->reg_vdrive)) - return dev_err_probe(&spi->dev, PTR_ERR(st->reg_vdrive), - "failed to get the VDRIVE voltage\n"); - return 0; } -static void ad7293_reg_disable(void *data) -{ - regulator_disable(data); -} - static int ad7293_init(struct ad7293_state *st) { int ret; @@ -816,48 +808,6 @@ static int ad7293_init(struct ad7293_state *st) if (ret) return ret; - ret = regulator_enable(st->reg_avdd); - if (ret) { - dev_err(&spi->dev, - "Failed to enable specified AVDD Voltage!\n"); - return ret; - } - - ret = devm_add_action_or_reset(&spi->dev, ad7293_reg_disable, - st->reg_avdd); - if (ret) - return ret; - - ret = regulator_enable(st->reg_vdrive); - if (ret) { - dev_err(&spi->dev, - "Failed to enable specified VDRIVE Voltage!\n"); - return ret; - } - - ret = devm_add_action_or_reset(&spi->dev, ad7293_reg_disable, - st->reg_vdrive); - if (ret) - return ret; - - ret = regulator_get_voltage(st->reg_avdd); - if (ret < 0) { - dev_err(&spi->dev, "Failed to read avdd regulator: %d\n", ret); - return ret; - } - - if (ret > 5500000 || ret < 4500000) - return -EINVAL; - - ret = regulator_get_voltage(st->reg_vdrive); - if (ret < 0) { - dev_err(&spi->dev, - "Failed to read vdrive regulator: %d\n", ret); - return ret; - } - if (ret > 5500000 || ret < 1700000) - return -EINVAL; - /* Check Chip ID */ ret = __ad7293_spi_read(st, AD7293_REG_DEVICE_ID, &chip_id); if (ret) diff --git a/drivers/iio/dac/ad8801.c b/drivers/iio/dac/ad8801.c index 919e8c880697..8a362fae2eca 100644 --- a/drivers/iio/dac/ad8801.c +++ b/drivers/iio/dac/ad8801.c @@ -23,8 +23,6 @@ struct ad8801_state { unsigned char dac_cache[8]; /* Value write on each channel */ unsigned int vrefh_mv; unsigned int vrefl_mv; - struct regulator *vrefh_reg; - struct regulator *vrefl_reg; __be16 data __aligned(IIO_DMA_MINALIGN); }; @@ -122,86 +120,34 @@ static int ad8801_probe(struct spi_device *spi) state->spi = spi; id = spi_get_device_id(spi); - state->vrefh_reg = devm_regulator_get(&spi->dev, "vrefh"); - if (IS_ERR(state->vrefh_reg)) - return dev_err_probe(&spi->dev, PTR_ERR(state->vrefh_reg), - "Vrefh regulator not specified\n"); + ret = devm_regulator_get_enable_read_voltage(&spi->dev, "vrefh"); + if (ret < 0) + return dev_err_probe(&spi->dev, ret, + "failed to get Vrefh voltage\n"); - ret = regulator_enable(state->vrefh_reg); - if (ret) { - dev_err(&spi->dev, "Failed to enable vrefh regulator: %d\n", - ret); - return ret; - } - - ret = regulator_get_voltage(state->vrefh_reg); - if (ret < 0) { - dev_err(&spi->dev, "Failed to read vrefh regulator: %d\n", - ret); - goto error_disable_vrefh_reg; - } state->vrefh_mv = ret / 1000; if (id->driver_data == ID_AD8803) { - state->vrefl_reg = devm_regulator_get(&spi->dev, "vrefl"); - if (IS_ERR(state->vrefl_reg)) { - ret = dev_err_probe(&spi->dev, PTR_ERR(state->vrefl_reg), - "Vrefl regulator not specified\n"); - goto error_disable_vrefh_reg; - } + ret = devm_regulator_get_enable_read_voltage(&spi->dev, "vrefl"); + if (ret < 0) + return dev_err_probe(&spi->dev, ret, + "failed to get Vrefl voltage\n"); - ret = regulator_enable(state->vrefl_reg); - if (ret) { - dev_err(&spi->dev, "Failed to enable vrefl regulator: %d\n", - ret); - goto error_disable_vrefh_reg; - } - - ret = regulator_get_voltage(state->vrefl_reg); - if (ret < 0) { - dev_err(&spi->dev, "Failed to read vrefl regulator: %d\n", - ret); - goto error_disable_vrefl_reg; - } state->vrefl_mv = ret / 1000; - } else { - state->vrefl_mv = 0; - state->vrefl_reg = NULL; } - spi_set_drvdata(spi, indio_dev); indio_dev->info = &ad8801_info; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = ad8801_channels; indio_dev->num_channels = ARRAY_SIZE(ad8801_channels); indio_dev->name = id->name; - ret = iio_device_register(indio_dev); - if (ret) { - dev_err(&spi->dev, "Failed to register iio device: %d\n", - ret); - goto error_disable_vrefl_reg; - } + ret = devm_iio_device_register(&spi->dev, indio_dev); + if (ret) + return dev_err_probe(&spi->dev, ret, + "Failed to register iio device\n"); return 0; - -error_disable_vrefl_reg: - if (state->vrefl_reg) - regulator_disable(state->vrefl_reg); -error_disable_vrefh_reg: - regulator_disable(state->vrefh_reg); - return ret; -} - -static void ad8801_remove(struct spi_device *spi) -{ - struct iio_dev *indio_dev = spi_get_drvdata(spi); - struct ad8801_state *state = iio_priv(indio_dev); - - iio_device_unregister(indio_dev); - if (state->vrefl_reg) - regulator_disable(state->vrefl_reg); - regulator_disable(state->vrefh_reg); } static const struct spi_device_id ad8801_ids[] = { @@ -216,7 +162,6 @@ static struct spi_driver ad8801_driver = { .name = "ad8801", }, .probe = ad8801_probe, - .remove = ad8801_remove, .id_table = ad8801_ids, }; module_spi_driver(ad8801_driver); diff --git a/drivers/iio/dac/ltc2632.c b/drivers/iio/dac/ltc2632.c index a4fb2509c950..999348836d87 100644 --- a/drivers/iio/dac/ltc2632.c +++ b/drivers/iio/dac/ltc2632.c @@ -41,13 +41,11 @@ struct ltc2632_chip_info { * @spi_dev: pointer to the spi_device struct * @powerdown_cache_mask: used to show current channel powerdown state * @vref_mv: used reference voltage (internal or external) - * @vref_reg: regulator for the reference voltage */ struct ltc2632_state { struct spi_device *spi_dev; unsigned int powerdown_cache_mask; int vref_mv; - struct regulator *vref_reg; }; enum ltc2632_supported_device_ids { @@ -310,6 +308,7 @@ static int ltc2632_probe(struct spi_device *spi) struct ltc2632_state *st; struct iio_dev *indio_dev; struct ltc2632_chip_info *chip_info; + bool has_external_vref; int ret; indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st)); @@ -318,49 +317,31 @@ static int ltc2632_probe(struct spi_device *spi) st = iio_priv(indio_dev); - spi_set_drvdata(spi, indio_dev); st->spi_dev = spi; chip_info = (struct ltc2632_chip_info *) spi_get_device_id(spi)->driver_data; - st->vref_reg = devm_regulator_get_optional(&spi->dev, "vref"); - if (PTR_ERR(st->vref_reg) == -ENODEV) { - /* use internal reference voltage */ - st->vref_reg = NULL; - st->vref_mv = chip_info->vref_mv; + ret = devm_regulator_get_enable_read_voltage(&spi->dev, "vref"); + if (ret < 0 && ret != -ENODEV) + return dev_err_probe(&spi->dev, ret, + "Failed to get vref regulator voltage\n"); - ret = ltc2632_spi_write(spi, LTC2632_CMD_INTERNAL_REFER, - 0, 0, 0); - if (ret) { - dev_err(&spi->dev, - "Set internal reference command failed, %d\n", - ret); - return ret; - } - } else if (IS_ERR(st->vref_reg)) { - dev_err(&spi->dev, - "Error getting voltage reference regulator\n"); - return PTR_ERR(st->vref_reg); - } else { - /* use external reference voltage */ - ret = regulator_enable(st->vref_reg); - if (ret) { - dev_err(&spi->dev, - "enable reference regulator failed, %d\n", - ret); - return ret; - } - st->vref_mv = regulator_get_voltage(st->vref_reg) / 1000; + has_external_vref = ret != -ENODEV; + st->vref_mv = has_external_vref ? ret / 1000 : chip_info->vref_mv; + if (has_external_vref) { ret = ltc2632_spi_write(spi, LTC2632_CMD_EXTERNAL_REFER, - 0, 0, 0); - if (ret) { - dev_err(&spi->dev, - "Set external reference command failed, %d\n", - ret); - return ret; - } + 0, 0, 0); + if (ret) + return dev_err_probe(&spi->dev, ret, + "Set external reference command failed\n"); + } else { + ret = ltc2632_spi_write(spi, LTC2632_CMD_INTERNAL_REFER, + 0, 0, 0); + if (ret) + return dev_err_probe(&spi->dev, ret, + "Set internal reference command failed\n"); } indio_dev->name = fwnode_get_name(dev_fwnode(&spi->dev)) ?: spi_get_device_id(spi)->name; @@ -369,18 +350,7 @@ static int ltc2632_probe(struct spi_device *spi) indio_dev->channels = chip_info->channels; indio_dev->num_channels = chip_info->num_channels; - return iio_device_register(indio_dev); -} - -static void ltc2632_remove(struct spi_device *spi) -{ - struct iio_dev *indio_dev = spi_get_drvdata(spi); - struct ltc2632_state *st = iio_priv(indio_dev); - - iio_device_unregister(indio_dev); - - if (st->vref_reg) - regulator_disable(st->vref_reg); + return devm_iio_device_register(&spi->dev, indio_dev); } static const struct spi_device_id ltc2632_id[] = { @@ -472,7 +442,6 @@ static struct spi_driver ltc2632_driver = { .of_match_table = ltc2632_of_match, }, .probe = ltc2632_probe, - .remove = ltc2632_remove, .id_table = ltc2632_id, }; module_spi_driver(ltc2632_driver); diff --git a/drivers/iio/dac/ltc2688.c b/drivers/iio/dac/ltc2688.c index 376dca163c91..bdc857c7fa6d 100644 --- a/drivers/iio/dac/ltc2688.c +++ b/drivers/iio/dac/ltc2688.c @@ -842,7 +842,7 @@ static int ltc2688_channel_config(struct ltc2688_state *st) return 0; } -static int ltc2688_setup(struct ltc2688_state *st, struct regulator *vref) +static int ltc2688_setup(struct ltc2688_state *st, bool has_external_vref) { struct device *dev = &st->spi->dev; struct gpio_desc *gpio; @@ -881,18 +881,13 @@ static int ltc2688_setup(struct ltc2688_state *st, struct regulator *vref) if (ret) return ret; - if (!vref) + if (!has_external_vref) return 0; return regmap_set_bits(st->regmap, LTC2688_CMD_CONFIG, LTC2688_CONFIG_EXT_REF); } -static void ltc2688_disable_regulator(void *regulator) -{ - regulator_disable(regulator); -} - static bool ltc2688_reg_readable(struct device *dev, unsigned int reg) { switch (reg) { @@ -947,8 +942,8 @@ static int ltc2688_probe(struct spi_device *spi) static const char * const regulators[] = { "vcc", "iovcc" }; struct ltc2688_state *st; struct iio_dev *indio_dev; - struct regulator *vref_reg; struct device *dev = &spi->dev; + bool has_external_vref; int ret; indio_dev = devm_iio_device_alloc(dev, sizeof(*st)); @@ -973,34 +968,15 @@ static int ltc2688_probe(struct spi_device *spi) if (ret) return dev_err_probe(dev, ret, "Failed to enable regulators\n"); - vref_reg = devm_regulator_get_optional(dev, "vref"); - if (IS_ERR(vref_reg)) { - if (PTR_ERR(vref_reg) != -ENODEV) - return dev_err_probe(dev, PTR_ERR(vref_reg), - "Failed to get vref regulator"); + ret = devm_regulator_get_enable_read_voltage(dev, "vref"); + if (ret < 0 && ret != -ENODEV) + return dev_err_probe(dev, ret, + "Failed to get vref regulator voltage\n"); - vref_reg = NULL; - /* internal reference */ - st->vref = 4096; - } else { - ret = regulator_enable(vref_reg); - if (ret) - return dev_err_probe(dev, ret, - "Failed to enable vref regulators\n"); + has_external_vref = ret != -ENODEV; + st->vref = has_external_vref ? ret / 1000 : 0; - ret = devm_add_action_or_reset(dev, ltc2688_disable_regulator, - vref_reg); - if (ret) - return ret; - - ret = regulator_get_voltage(vref_reg); - if (ret < 0) - return dev_err_probe(dev, ret, "Failed to get vref\n"); - - st->vref = ret / 1000; - } - - ret = ltc2688_setup(st, vref_reg); + ret = ltc2688_setup(st, has_external_vref); if (ret) return ret; diff --git a/drivers/iio/dac/max5821.c b/drivers/iio/dac/max5821.c index 18ba3eaaad75..b062a18be5e7 100644 --- a/drivers/iio/dac/max5821.c +++ b/drivers/iio/dac/max5821.c @@ -32,7 +32,6 @@ enum max5821_device_ids { struct max5821_data { struct i2c_client *client; - struct regulator *vref_reg; unsigned short vref_mv; bool powerdown[MAX5821_MAX_DAC_CHANNELS]; u8 powerdown_mode[MAX5821_MAX_DAC_CHANNELS]; @@ -295,11 +294,6 @@ static const struct iio_info max5821_info = { .write_raw = max5821_write_raw, }; -static void max5821_regulator_disable(void *reg) -{ - regulator_disable(reg); -} - static int max5821_probe(struct i2c_client *client) { const struct i2c_device_id *id = i2c_client_get_device_id(client); @@ -321,32 +315,10 @@ static int max5821_probe(struct i2c_client *client) data->powerdown_mode[tmp] = MAX5821_100KOHM_TO_GND; } - data->vref_reg = devm_regulator_get(&client->dev, "vref"); - if (IS_ERR(data->vref_reg)) - return dev_err_probe(&client->dev, PTR_ERR(data->vref_reg), - "Failed to get vref regulator\n"); - - ret = regulator_enable(data->vref_reg); - if (ret) { - dev_err(&client->dev, - "Failed to enable vref regulator: %d\n", ret); - return ret; - } - - ret = devm_add_action_or_reset(&client->dev, max5821_regulator_disable, - data->vref_reg); - if (ret) { - dev_err(&client->dev, - "Failed to add action to managed regulator: %d\n", ret); - return ret; - } - - ret = regulator_get_voltage(data->vref_reg); - if (ret < 0) { - dev_err(&client->dev, - "Failed to get voltage on regulator: %d\n", ret); - return ret; - } + ret = devm_regulator_get_enable_read_voltage(&client->dev, "vref"); + if (ret) + return dev_err_probe(&client->dev, ret, + "Failed to get vref regulator voltage\n"); data->vref_mv = ret / 1000; diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 25bb1c0490af..1337fb02ccf5 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -379,7 +379,7 @@ static int mcp4725_probe_dt(struct device *dev, struct mcp4725_platform_data *pdata) { /* check if is the vref-supply defined */ - pdata->use_vref = device_property_read_bool(dev, "vref-supply"); + pdata->use_vref = device_property_present(dev, "vref-supply"); pdata->vref_buffered = device_property_read_bool(dev, "microchip,vref-buffered"); diff --git a/drivers/iio/dac/rohm-bd79703.c b/drivers/iio/dac/rohm-bd79703.c new file mode 100644 index 000000000000..e998ab51052e --- /dev/null +++ b/drivers/iio/dac/rohm-bd79703.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * BD79703 ROHM Digital to Analog converter + * + * Copyright (c) 2024, ROHM Semiconductor. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define BD79703_MAX_REGISTER 0xf +#define BD79703_DAC_BITS 8 +#define BD79703_REG_OUT_ALL GENMASK(2, 0) + +/* + * The BD79703 uses 12-bit SPI commands. First four bits (high bits) define + * channel(s) which are operated on, and also the mode. The mode can be to set + * a DAC word only, or set DAC word and output. The data-sheet is not very + * specific on how a previously set DAC word can be 'taken in to use'. Thus + * this driver only uses the 'set DAC and output it' -mode. + * + * The BD79703 latches last 12-bits when the chip-select is toggled. Thus we + * can use 16-bit transfers which should be widely supported. To simplify this + * further, we treat the last 8 bits as a value, and first 8 bits as an + * address. This allows us to separate channels/mode by address and treat the + * 8-bit register value as DAC word. The highest 4 bits of address will be + * discarded when the transfer is latched. + */ +static const struct regmap_config bd79703_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = BD79703_MAX_REGISTER, + .cache_type = REGCACHE_RBTREE, +}; + +struct bd79703_data { + struct regmap *regmap; + int vfs; +}; + +static int bd79703_read_raw(struct iio_dev *idev, + struct iio_chan_spec const *chan, int *val, + int *val2, long mask) +{ + struct bd79703_data *data = iio_priv(idev); + + if (mask != IIO_CHAN_INFO_SCALE) + return -EINVAL; + + *val = data->vfs / 1000; + *val2 = BD79703_DAC_BITS; + + return IIO_VAL_FRACTIONAL_LOG2; +} + +static int bd79703_write_raw(struct iio_dev *idev, + struct iio_chan_spec const *chan, int val, + int val2, long mask) +{ + struct bd79703_data *data = iio_priv(idev); + + if (val < 0 || val >= 1 << BD79703_DAC_BITS) + return -EINVAL; + + return regmap_write(data->regmap, chan->channel + 1, val); +}; + +static const struct iio_info bd79703_info = { + .read_raw = bd79703_read_raw, + .write_raw = bd79703_write_raw, +}; + +#define BD79703_CHAN(_chan) { \ + .type = IIO_VOLTAGE, \ + .indexed = 1, \ + .output = 1, \ + .channel = (_chan), \ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \ + .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ + .address = (_chan), \ +} + +static const struct iio_chan_spec bd79703_channels[] = { + BD79703_CHAN(0), + BD79703_CHAN(1), + BD79703_CHAN(2), + BD79703_CHAN(3), + BD79703_CHAN(4), + BD79703_CHAN(5), +}; + +static int bd79703_probe(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct bd79703_data *data; + struct iio_dev *idev; + int ret; + + idev = devm_iio_device_alloc(dev, sizeof(*data)); + if (!idev) + return -ENOMEM; + + data = iio_priv(idev); + + data->regmap = devm_regmap_init_spi(spi, &bd79703_regmap_config); + if (IS_ERR(data->regmap)) + return dev_err_probe(dev, PTR_ERR(data->regmap), + "Failed to initialize Regmap\n"); + + ret = devm_regulator_get_enable(dev, "vcc"); + if (ret) + return dev_err_probe(dev, ret, "Failed to enable VCC\n"); + + ret = devm_regulator_get_enable_read_voltage(dev, "vfs"); + if (ret < 0) + return dev_err_probe(dev, ret, "Failed to get Vfs\n"); + + data->vfs = ret; + idev->channels = bd79703_channels; + idev->num_channels = ARRAY_SIZE(bd79703_channels); + idev->modes = INDIO_DIRECT_MODE; + idev->info = &bd79703_info; + idev->name = "bd79703"; + + /* Initialize all to output zero */ + ret = regmap_write(data->regmap, BD79703_REG_OUT_ALL, 0); + if (ret) + return ret; + + return devm_iio_device_register(dev, idev); +} + +static const struct spi_device_id bd79703_id[] = { + { "bd79703", }, + { } +}; +MODULE_DEVICE_TABLE(spi, bd79703_id); + +static const struct of_device_id bd79703_of_match[] = { + { .compatible = "rohm,bd79703", }, + { } +}; +MODULE_DEVICE_TABLE(of, bd79703_of_match); + +static struct spi_driver bd79703_driver = { + .driver = { + .name = "bd79703", + .of_match_table = bd79703_of_match, + }, + .probe = bd79703_probe, + .id_table = bd79703_id, +}; +module_spi_driver(bd79703_driver); + +MODULE_AUTHOR("Matti Vaittinen "); +MODULE_DESCRIPTION("ROHM BD79703 DAC driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/iio/dummy/iio_simple_dummy_buffer.c b/drivers/iio/dummy/iio_simple_dummy_buffer.c index 4ca3f1aaff99..288880346707 100644 --- a/drivers/iio/dummy/iio_simple_dummy_buffer.c +++ b/drivers/iio/dummy/iio_simple_dummy_buffer.c @@ -48,7 +48,7 @@ static irqreturn_t iio_simple_dummy_trigger_h(int irq, void *p) int i = 0, j; u16 *data; - data = kmalloc(indio_dev->scan_bytes, GFP_KERNEL); + data = kzalloc(indio_dev->scan_bytes, GFP_KERNEL); if (!data) goto done; diff --git a/drivers/iio/gyro/adxrs290.c b/drivers/iio/gyro/adxrs290.c index 600e9725da78..223fc181109c 100644 --- a/drivers/iio/gyro/adxrs290.c +++ b/drivers/iio/gyro/adxrs290.c @@ -75,7 +75,7 @@ struct adxrs290_state { /* Ensure correct alignment of timestamp when present */ struct { s16 channels[3]; - s64 ts __aligned(8); + aligned_s64 ts; } buffer; }; diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c index ba877d067afb..deb3c6459dde 100644 --- a/drivers/iio/gyro/bmg160_core.c +++ b/drivers/iio/gyro/bmg160_core.c @@ -99,7 +99,7 @@ struct bmg160_data { /* Ensure naturally aligned timestamp */ struct { s16 chans[3]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; u32 dps_range; int ev_enable_state; diff --git a/drivers/iio/gyro/fxas21002c_core.c b/drivers/iio/gyro/fxas21002c_core.c index 0391c78c2f18..754c8a564ba4 100644 --- a/drivers/iio/gyro/fxas21002c_core.c +++ b/drivers/iio/gyro/fxas21002c_core.c @@ -730,14 +730,21 @@ static irqreturn_t fxas21002c_trigger_handler(int irq, void *p) int ret; mutex_lock(&data->lock); - ret = regmap_bulk_read(data->regmap, FXAS21002C_REG_OUT_X_MSB, - data->buffer, CHANNEL_SCAN_MAX * sizeof(s16)); + ret = fxas21002c_pm_get(data); if (ret < 0) goto out_unlock; + ret = regmap_bulk_read(data->regmap, FXAS21002C_REG_OUT_X_MSB, + data->buffer, CHANNEL_SCAN_MAX * sizeof(s16)); + if (ret < 0) + goto out_pm_put; + iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, data->timestamp); +out_pm_put: + fxas21002c_pm_put(data); + out_unlock: mutex_unlock(&data->lock); diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c index 4cfa0d439560..a624400a239c 100644 --- a/drivers/iio/gyro/itg3200_buffer.c +++ b/drivers/iio/gyro/itg3200_buffer.c @@ -52,7 +52,7 @@ static irqreturn_t itg3200_trigger_handler(int irq, void *p) */ struct { __be16 buf[ITG3200_SCAN_ELEMENTS]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; int ret = itg3200_read_all_channels(st->i2c, scan.buf); diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index b6883e8b2a8b..d66224bed8e3 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -474,7 +474,7 @@ static irqreturn_t mpu3050_trigger_handler(int irq, void *p) int ret; struct { __be16 chans[4]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; s64 timestamp; unsigned int datums_from_fifo = 0; diff --git a/drivers/iio/humidity/am2315.c b/drivers/iio/humidity/am2315.c index 6b0aa3a3f025..2323974b805c 100644 --- a/drivers/iio/humidity/am2315.c +++ b/drivers/iio/humidity/am2315.c @@ -35,7 +35,7 @@ struct am2315_data { /* Ensure timestamp is naturally aligned */ struct { s16 chans[2]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; }; diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c index 9b355380c9bf..a303f704b7ed 100644 --- a/drivers/iio/humidity/hdc100x.c +++ b/drivers/iio/humidity/hdc100x.c @@ -44,7 +44,7 @@ struct hdc100x_data { /* Ensure natural alignment of timestamp */ struct { __be16 channels[2]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/humidity/hts221.h b/drivers/iio/humidity/hts221.h index 721359e226cb..0215f11fc35e 100644 --- a/drivers/iio/humidity/hts221.h +++ b/drivers/iio/humidity/hts221.h @@ -40,7 +40,7 @@ struct hts221_hw { /* Ensure natural alignment of timestamp */ struct { __le16 channels[2]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c index 0a5d13d2240e..727e0a11eac1 100644 --- a/drivers/iio/imu/adis16480.c +++ b/drivers/iio/imu/adis16480.c @@ -878,11 +878,32 @@ static const struct iio_chan_spec adis16545_channels[] = { IIO_CHAN_SOFT_TIMESTAMP(17), }; +static const struct iio_chan_spec adis16489_channels[] = { + ADIS16480_GYRO_CHANNEL(X), + ADIS16480_GYRO_CHANNEL(Y), + ADIS16480_GYRO_CHANNEL(Z), + ADIS16480_ACCEL_CHANNEL(X), + ADIS16480_ACCEL_CHANNEL(Y), + ADIS16480_ACCEL_CHANNEL(Z), + ADIS16480_PRESSURE_CHANNEL(), + ADIS16480_TEMP_CHANNEL(), + IIO_CHAN_SOFT_TIMESTAMP(8), + ADIS16480_DELTANG_CHANNEL_NO_SCAN(X), + ADIS16480_DELTANG_CHANNEL_NO_SCAN(Y), + ADIS16480_DELTANG_CHANNEL_NO_SCAN(Z), + ADIS16480_DELTVEL_CHANNEL_NO_SCAN(X), + ADIS16480_DELTVEL_CHANNEL_NO_SCAN(Y), + ADIS16480_DELTVEL_CHANNEL_NO_SCAN(Z), +}; + enum adis16480_variant { ADIS16375, ADIS16480, ADIS16485, + ADIS16486, + ADIS16487, ADIS16488, + ADIS16489, ADIS16490, ADIS16495_1, ADIS16495_2, @@ -1038,6 +1059,38 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { .filter_freqs = adis16480_def_filter_freqs, .adis_data = ADIS16480_DATA(16485, &adis16485_timeouts, 0, 0), }, + [ADIS16486] = { + .channels = adis16485_channels, + .num_channels = ARRAY_SIZE(adis16485_channels), + .gyro_max_val = 22500 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(450), + .accel_max_val = IIO_M_S_2_TO_G(20000 << 16), + .accel_max_scale = 18, + .temp_scale = 5650, /* 5.65 milli degree Celsius */ + .deltang_max_val = IIO_DEGREE_TO_RAD(720), + .deltvel_max_val = 200, + .int_clk = 2460000, + .max_dec_rate = 2048, + .has_sleep_cnt = true, + .filter_freqs = adis16480_def_filter_freqs, + .adis_data = ADIS16480_DATA(16486, &adis16480_timeouts, 0, 0), + }, + [ADIS16487] = { + .channels = adis16485_channels, + .num_channels = ARRAY_SIZE(adis16485_channels), + .gyro_max_val = 22500 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(450), + .accel_max_val = IIO_M_S_2_TO_G(20000 << 16), + .accel_max_scale = 5, + .temp_scale = 5650, /* 5.65 milli degree Celsius */ + .deltang_max_val = IIO_DEGREE_TO_RAD(720), + .deltvel_max_val = 50, + .int_clk = 2460000, + .max_dec_rate = 2048, + .has_sleep_cnt = true, + .filter_freqs = adis16480_def_filter_freqs, + .adis_data = ADIS16480_DATA(16487, &adis16485_timeouts, 0, 0), + }, [ADIS16488] = { .channels = adis16480_channels, .num_channels = ARRAY_SIZE(adis16480_channels), @@ -1054,6 +1107,22 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { .filter_freqs = adis16480_def_filter_freqs, .adis_data = ADIS16480_DATA(16488, &adis16485_timeouts, 0, 0), }, + [ADIS16489] = { + .channels = adis16489_channels, + .num_channels = ARRAY_SIZE(adis16489_channels), + .gyro_max_val = 22500 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(450), + .accel_max_val = IIO_M_S_2_TO_G(20000 << 16), + .accel_max_scale = 18, + .temp_scale = 5650, /* 5.65 milli degree Celsius */ + .deltang_max_val = IIO_DEGREE_TO_RAD(720), + .deltvel_max_val = 200, + .int_clk = 2460000, + .max_dec_rate = 2048, + .has_sleep_cnt = true, + .filter_freqs = adis16480_def_filter_freqs, + .adis_data = ADIS16480_DATA(16489, &adis16480_timeouts, 0, 0), + }, [ADIS16490] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), @@ -1741,7 +1810,10 @@ static const struct spi_device_id adis16480_ids[] = { { "adis16375", ADIS16375 }, { "adis16480", ADIS16480 }, { "adis16485", ADIS16485 }, + { "adis16486", ADIS16486 }, + { "adis16487", ADIS16487 }, { "adis16488", ADIS16488 }, + { "adis16489", ADIS16489 }, { "adis16490", ADIS16490 }, { "adis16495-1", ADIS16495_1 }, { "adis16495-2", ADIS16495_2 }, @@ -1763,7 +1835,10 @@ static const struct of_device_id adis16480_of_match[] = { { .compatible = "adi,adis16375" }, { .compatible = "adi,adis16480" }, { .compatible = "adi,adis16485" }, + { .compatible = "adi,adis16486" }, + { .compatible = "adi,adis16487" }, { .compatible = "adi,adis16488" }, + { .compatible = "adi,adis16489" }, { .compatible = "adi,adis16490" }, { .compatible = "adi,adis16495-1" }, { .compatible = "adi,adis16495-2" }, diff --git a/drivers/iio/imu/bmi323/bmi323_core.c b/drivers/iio/imu/bmi323/bmi323_core.c index f7d7f4442e65..7f386c5e58b4 100644 --- a/drivers/iio/imu/bmi323/bmi323_core.c +++ b/drivers/iio/imu/bmi323/bmi323_core.c @@ -174,7 +174,7 @@ struct bmi323_data { __le16 fifo_buff[BMI323_FIFO_FULL_IN_WORDS] __aligned(IIO_DMA_MINALIGN); struct { __le16 channels[BMI323_CHAN_MAX]; - s64 ts __aligned(8); + aligned_s64 ts; } buffer; __le16 steps_count[BMI323_STEP_LEN]; }; diff --git a/drivers/iio/imu/bno055/bno055.c b/drivers/iio/imu/bno055/bno055.c index 0728d38260a1..597c402b98de 100644 --- a/drivers/iio/imu/bno055/bno055.c +++ b/drivers/iio/imu/bno055/bno055.c @@ -207,7 +207,7 @@ struct bno055_priv { bool sw_reset; struct { __le16 chans[BNO055_SCAN_CH_COUNT]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } buf; struct dentry *debugfs; }; @@ -1193,7 +1193,7 @@ static ssize_t serialnumber_show(struct device *dev, } static ssize_t calibration_data_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct bno055_priv *priv = iio_priv(dev_to_iio_dev(kobj_to_dev(kobj))); @@ -1348,16 +1348,16 @@ static struct attribute *bno055_attrs[] = { NULL }; -static BIN_ATTR_RO(calibration_data, BNO055_CALDATA_LEN); +static const BIN_ATTR_RO(calibration_data, BNO055_CALDATA_LEN); -static struct bin_attribute *bno055_bin_attrs[] = { +static const struct bin_attribute *const bno055_bin_attrs[] = { &bin_attr_calibration_data, NULL }; static const struct attribute_group bno055_attrs_group = { .attrs = bno055_attrs, - .bin_attrs = bno055_bin_attrs, + .bin_attrs_new = bno055_bin_attrs, }; static const struct iio_info bno055_info = { diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600.h b/drivers/iio/imu/inv_icm42600/inv_icm42600.h index 3a07e43e4cf1..18787a43477b 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600.h +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600.h @@ -403,6 +403,7 @@ struct inv_icm42600_sensor_state { typedef int (*inv_icm42600_bus_setup)(struct inv_icm42600_state *); extern const struct regmap_config inv_icm42600_regmap_config; +extern const struct regmap_config inv_icm42600_spi_regmap_config; extern const struct dev_pm_ops inv_icm42600_pm_ops; const struct iio_mount_matrix * diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c index 7968aa27f9fd..388520ec60b5 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c @@ -178,7 +178,7 @@ static const struct iio_chan_spec inv_icm42600_accel_channels[] = { struct inv_icm42600_accel_buffer { struct inv_icm42600_fifo_sensor_data accel; int16_t temp; - int64_t timestamp __aligned(8); + aligned_s64 timestamp; }; #define INV_ICM42600_SCAN_MASK_ACCEL_3AXIS \ diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c index 561d245c1d64..ef9875d3b79d 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c @@ -87,6 +87,21 @@ const struct regmap_config inv_icm42600_regmap_config = { }; EXPORT_SYMBOL_NS_GPL(inv_icm42600_regmap_config, "IIO_ICM42600"); +/* define specific regmap for SPI not supporting burst write */ +const struct regmap_config inv_icm42600_spi_regmap_config = { + .name = "inv_icm42600", + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x4FFF, + .ranges = inv_icm42600_regmap_ranges, + .num_ranges = ARRAY_SIZE(inv_icm42600_regmap_ranges), + .volatile_table = inv_icm42600_regmap_volatile_accesses, + .rd_noinc_table = inv_icm42600_regmap_rd_noinc_accesses, + .cache_type = REGCACHE_RBTREE, + .use_single_write = true, +}; +EXPORT_SYMBOL_NS_GPL(inv_icm42600_spi_regmap_config, "IIO_ICM42600"); + struct inv_icm42600_hw { uint8_t whoami; const char *name; @@ -814,6 +829,8 @@ out_unlock: static int inv_icm42600_resume(struct device *dev) { struct inv_icm42600_state *st = dev_get_drvdata(dev); + struct inv_icm42600_sensor_state *gyro_st = iio_priv(st->indio_gyro); + struct inv_icm42600_sensor_state *accel_st = iio_priv(st->indio_accel); int ret; mutex_lock(&st->lock); @@ -834,9 +851,12 @@ static int inv_icm42600_resume(struct device *dev) goto out_unlock; /* restore FIFO data streaming */ - if (st->fifo.on) + if (st->fifo.on) { + inv_sensors_timestamp_reset(&gyro_st->ts); + inv_sensors_timestamp_reset(&accel_st->ts); ret = regmap_write(st->map, INV_ICM42600_REG_FIFO_CONFIG, INV_ICM42600_FIFO_CONFIG_STREAM); + } out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c index c6bb68bf5e14..591ed78a55bb 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c @@ -78,7 +78,7 @@ static const struct iio_chan_spec inv_icm42600_gyro_channels[] = { struct inv_icm42600_gyro_buffer { struct inv_icm42600_fifo_sensor_data gyro; int16_t temp; - int64_t timestamp __aligned(8); + aligned_s64 timestamp; }; #define INV_ICM42600_SCAN_MASK_GYRO_3AXIS \ diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c index c55d8e672183..2bd2c4c8e50c 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c @@ -59,7 +59,8 @@ static int inv_icm42600_probe(struct spi_device *spi) return -EINVAL; chip = (uintptr_t)match; - regmap = devm_regmap_init_spi(spi, &inv_icm42600_regmap_config); + /* use SPI specific regmap */ + regmap = devm_regmap_init_spi(spi, &inv_icm42600_spi_regmap_config); if (IS_ERR(regmap)) return PTR_ERR(regmap); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index 844b611b825a..5bcd5e797046 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -277,6 +277,14 @@ static const struct inv_mpu6050_hw hw_info[] = { .temp = {INV_ICM20608_TEMP_OFFSET, INV_ICM20608_TEMP_SCALE}, .startup_time = {INV_ICM20690_GYRO_STARTUP_TIME, INV_ICM20690_ACCEL_STARTUP_TIME}, }, + { .whoami = INV_IAM20380_WHOAMI_VALUE, + .name = "IAM20380", + .reg = ®_set_6500, + .config = &chip_config_6500, + .fifo_size = 512, + .temp = {INV_ICM20608_TEMP_OFFSET, INV_ICM20608_TEMP_SCALE}, + .startup_time = {INV_MPU6500_GYRO_STARTUP_TIME, INV_MPU6500_ACCEL_STARTUP_TIME}, + }, { .whoami = INV_IAM20680_WHOAMI_VALUE, .name = "IAM20680", @@ -1519,6 +1527,14 @@ static const struct iio_chan_spec inv_mpu6050_channels[] = { INV_MPU6050_CHAN(IIO_ACCEL, IIO_MOD_Z, INV_MPU6050_SCAN_ACCL_Z), }; +static const struct iio_chan_spec inv_iam20380_channels[] = { + IIO_CHAN_SOFT_TIMESTAMP(INV_MPU6050_SCAN_TIMESTAMP), + + INV_MPU6050_CHAN(IIO_ANGL_VEL, IIO_MOD_X, INV_MPU6050_SCAN_GYRO_X), + INV_MPU6050_CHAN(IIO_ANGL_VEL, IIO_MOD_Y, INV_MPU6050_SCAN_GYRO_Y), + INV_MPU6050_CHAN(IIO_ANGL_VEL, IIO_MOD_Z, INV_MPU6050_SCAN_GYRO_Z), +}; + static const struct iio_chan_spec inv_mpu6500_channels[] = { IIO_CHAN_SOFT_TIMESTAMP(INV_MPU6050_SCAN_TIMESTAMP), @@ -1623,6 +1639,10 @@ static const struct iio_chan_spec inv_mpu9250_channels[] = { | BIT(INV_MPU9X50_SCAN_MAGN_Y) \ | BIT(INV_MPU9X50_SCAN_MAGN_Z)) +static const unsigned long inv_iam20380_scan_masks[] = { + INV_MPU6050_SCAN_MASK_3AXIS_GYRO, +}; + static const unsigned long inv_mpu9x50_scan_masks[] = { /* 3-axis accel */ INV_MPU6050_SCAN_MASK_3AXIS_ACCEL, @@ -2026,6 +2046,11 @@ int inv_mpu_core_probe(struct regmap *regmap, int irq, const char *name, indio_dev->num_channels = ARRAY_SIZE(inv_mpu9250_channels); indio_dev->available_scan_masks = inv_mpu9x50_scan_masks; break; + case INV_IAM20380: + indio_dev->channels = inv_iam20380_channels; + indio_dev->num_channels = ARRAY_SIZE(inv_iam20380_channels); + indio_dev->available_scan_masks = inv_iam20380_scan_masks; + break; case INV_ICM20600: case INV_ICM20602: indio_dev->channels = inv_mpu6500_channels; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c index 307a06f4df2e..91d77f94d204 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c @@ -34,6 +34,7 @@ static bool inv_mpu_i2c_aux_bus(struct device *dev) case INV_ICM20689: case INV_ICM20600: case INV_ICM20602: + case INV_IAM20380: case INV_IAM20680: /* no i2c auxiliary bus on the chip */ return false; @@ -187,6 +188,7 @@ static const struct i2c_device_id inv_mpu_id[] = { {"icm20600", INV_ICM20600}, {"icm20602", INV_ICM20602}, {"icm20690", INV_ICM20690}, + {"iam20380", INV_IAM20380}, {"iam20680", INV_IAM20680}, {"iam20680hp", INV_IAM20680HP}, {"iam20680ht", INV_IAM20680HT}, @@ -252,6 +254,10 @@ static const struct of_device_id inv_of_match[] = { .compatible = "invensense,icm20690", .data = (void *)INV_ICM20690 }, + { + .compatible = "invensense,iam20380", + .data = (void *)INV_IAM20380 + }, { .compatible = "invensense,iam20680", .data = (void *)INV_IAM20680 diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h index a6862cf42639..211901f8b8eb 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h @@ -84,6 +84,7 @@ enum inv_devices { INV_ICM20600, INV_ICM20602, INV_ICM20690, + INV_IAM20380, INV_IAM20680, INV_IAM20680HP, INV_IAM20680HT, @@ -425,6 +426,7 @@ struct inv_mpu6050_state { #define INV_ICM20600_WHOAMI_VALUE 0x11 #define INV_ICM20602_WHOAMI_VALUE 0x12 #define INV_ICM20690_WHOAMI_VALUE 0x20 +#define INV_IAM20380_WHOAMI_VALUE 0xB5 #define INV_IAM20680_WHOAMI_VALUE 0xA9 #define INV_IAM20680HP_WHOAMI_VALUE 0xF8 #define INV_IAM20680HT_WHOAMI_VALUE 0xFA diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c index ab415874d699..20de6eb5cd35 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c @@ -79,6 +79,7 @@ static const struct spi_device_id inv_mpu_id[] = { {"icm20600", INV_ICM20600}, {"icm20602", INV_ICM20602}, {"icm20690", INV_ICM20690}, + {"iam20380", INV_IAM20380}, {"iam20680", INV_IAM20680}, {"iam20680hp", INV_IAM20680HP}, {"iam20680ht", INV_IAM20680HT}, @@ -140,6 +141,10 @@ static const struct of_device_id inv_of_match[] = { .compatible = "invensense,icm20690", .data = (void *)INV_ICM20690 }, + { + .compatible = "invensense,iam20380", + .data = (void *)INV_IAM20380 + }, { .compatible = "invensense,iam20680", .data = (void *)INV_IAM20680 diff --git a/drivers/iio/imu/kmx61.c b/drivers/iio/imu/kmx61.c index 324c38764656..e19c5d3137c6 100644 --- a/drivers/iio/imu/kmx61.c +++ b/drivers/iio/imu/kmx61.c @@ -1193,7 +1193,7 @@ static irqreturn_t kmx61_trigger_handler(int irq, void *p) struct kmx61_data *data = kmx61_get_data(indio_dev); int bit, ret, i = 0; u8 base; - s16 buffer[8]; + s16 buffer[8] = { }; if (indio_dev == data->acc_indio_dev) base = KMX61_ACC_XOUT_L; diff --git a/drivers/iio/imu/st_lsm6dsx/Kconfig b/drivers/iio/imu/st_lsm6dsx/Kconfig index 89d687ec3099..3cabec3b152d 100644 --- a/drivers/iio/imu/st_lsm6dsx/Kconfig +++ b/drivers/iio/imu/st_lsm6dsx/Kconfig @@ -6,9 +6,6 @@ config IIO_ST_LSM6DSX select IIO_BUFFER select IIO_TRIGGERED_BUFFER select IIO_KFIFO_BUF - select IIO_ST_LSM6DSX_I2C if (I2C) - select IIO_ST_LSM6DSX_SPI if (SPI_MASTER) - select IIO_ST_LSM6DSX_I3C if (I3C) help Say yes here to build support for STMicroelectronics LSM6DSx imu sensor. @@ -42,16 +39,19 @@ config IIO_ST_LSM6DSX will be called st_lsm6dsx. config IIO_ST_LSM6DSX_I2C - tristate - depends on IIO_ST_LSM6DSX + tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors I2C Interface" + depends on I2C && IIO_ST_LSM6DSX + default I2C && IIO_ST_LSM6DSX select REGMAP_I2C config IIO_ST_LSM6DSX_SPI - tristate - depends on IIO_ST_LSM6DSX + tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors SPI Interface" + depends on SPI_MASTER && IIO_ST_LSM6DSX + default SPI_MASTER && IIO_ST_LSM6DSX select REGMAP_SPI config IIO_ST_LSM6DSX_I3C - tristate - depends on IIO_ST_LSM6DSX + tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors I3C Interface" + depends on I3C && IIO_ST_LSM6DSX + default I3C && IIO_ST_LSM6DSX select REGMAP_I3C diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i3c.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i3c.c index 6952d901316f..f968f32890d1 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i3c.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i3c.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include @@ -30,15 +29,16 @@ static int st_lsm6dsx_i3c_probe(struct i3c_device *i3cdev) }; const struct i3c_device_id *id = i3c_device_match_id(i3cdev, st_lsm6dsx_i3c_ids); + struct device *dev = i3cdev_to_dev(i3cdev); struct regmap *regmap; regmap = devm_regmap_init_i3c(i3cdev, &st_lsm6dsx_i3c_regmap_config); if (IS_ERR(regmap)) { - dev_err(&i3cdev->dev, "Failed to register i3c regmap %ld\n", PTR_ERR(regmap)); + dev_err(dev, "Failed to register i3c regmap %ld\n", PTR_ERR(regmap)); return PTR_ERR(regmap); } - return st_lsm6dsx_probe(&i3cdev->dev, 0, (uintptr_t)id->data, regmap); + return st_lsm6dsx_probe(dev, 0, (uintptr_t)id->data, regmap); } static struct i3c_driver st_lsm6dsx_driver = { diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 2708f87df719..a80f7cc25a27 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -1137,7 +1137,7 @@ static int iio_enable_buffers(struct iio_dev *indio_dev, int ret; indio_dev->active_scan_mask = config->scan_mask; - indio_dev->scan_timestamp = config->scan_timestamp; + ACCESS_PRIVATE(indio_dev, scan_timestamp) = config->scan_timestamp; indio_dev->scan_bytes = config->scan_bytes; iio_dev_opaque->currentmode = config->mode; diff --git a/drivers/iio/industrialio-gts-helper.c b/drivers/iio/industrialio-gts-helper.c index 3b5a99815062..d70ebe3bf774 100644 --- a/drivers/iio/industrialio-gts-helper.c +++ b/drivers/iio/industrialio-gts-helper.c @@ -915,6 +915,41 @@ int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel } EXPORT_SYMBOL_NS_GPL(iio_gts_find_gain_sel_for_scale_using_time, "IIO_GTS_HELPER"); +/** + * iio_gts_find_gain_time_sel_for_scale - Fetch gain and time selectors for scale + * @gts: Gain time scale descriptor + * @scale_int: Integral part of the scale (typically val1) + * @scale_nano: Fractional part of the scale (nano or ppb) + * @gain_sel: Pointer to value where gain selector is stored. + * @time_sel: Pointer to value where time selector is stored. + * + * Wrapper around iio_gts_find_gain_for_scale_using_time() to fetch the + * gain and time selectors for a given scale. + * + * Return: 0 on success and -EINVAL on error. + */ +int iio_gts_find_gain_time_sel_for_scale(struct iio_gts *gts, int scale_int, + int scale_nano, int *gain_sel, + int *time_sel) +{ + int i, ret; + + for (i = 0; i < gts->num_itime; i++) { + *time_sel = gts->itime_table[i].sel; + ret = iio_gts_find_gain_sel_for_scale_using_time(gts, *time_sel, + scale_int, + scale_nano, + gain_sel); + if (ret) + continue; + + return 0; + } + + return -EINVAL; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_find_gain_time_sel_for_scale, "IIO_GTS_HELPER"); + static int iio_gts_get_total_gain(struct iio_gts *gts, int gain, int time) { const struct iio_itime_sel_mul *itime; @@ -1086,6 +1121,48 @@ int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain, } EXPORT_SYMBOL_NS_GPL(iio_gts_find_new_gain_by_old_gain_time, "IIO_GTS_HELPER"); +/** + * iio_gts_find_new_gain_by_gain_time_min - compensate for time change + * @gts: Gain time scale descriptor + * @old_gain: Previously set gain + * @old_time: Selector corresponding previously set time + * @new_time: Selector corresponding new time to be set + * @new_gain: Pointer to value where new gain is to be written + * @in_range: Indicate if the @new_gain was in the range of + * supported gains. + * + * Wrapper around iio_gts_find_new_gain_by_old_gain_time() that tries to + * set an optimal value if no exact match was found, defaulting to the + * minimum gain to avoid saturations if the optimal value is not in the + * range of supported gains. + * + * Return: 0 on success and a negative value if no gain was found. + */ +int iio_gts_find_new_gain_by_gain_time_min(struct iio_gts *gts, int old_gain, + int old_time, int new_time, + int *new_gain, bool *in_range) +{ + int ret; + + *in_range = true; + ret = iio_gts_find_new_gain_by_old_gain_time(gts, old_gain, old_time, + new_time, new_gain); + if (*new_gain < 0) + return -EINVAL; + + if (ret) { + *new_gain = iio_find_closest_gain_low(gts, *new_gain, in_range); + if (*new_gain < 0) { + *new_gain = iio_gts_get_min_gain(gts); + if (*new_gain < 0) + return -EINVAL; + } + } + + return 0; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_find_new_gain_by_gain_time_min, "IIO_GTS_HELPER"); + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Matti Vaittinen "); MODULE_DESCRIPTION("IIO light sensor gain-time-scale helpers"); diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 136b225b6bc8..c174ebb7d5e6 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -500,7 +501,7 @@ struct iio_channel *iio_channel_get_all(struct device *dev) return_ptr(chans); error_free_chans: - for (i = 0; i < nummaps; i++) + for (i = 0; i < mapind; i++) iio_device_put(chans[i].indio_dev); return ERR_PTR(ret); } @@ -989,6 +990,11 @@ ssize_t iio_read_channel_ext_info(struct iio_channel *chan, { const struct iio_chan_spec_ext_info *ext_info; + if (!buf || offset_in_page(buf)) { + pr_err("iio: invalid ext_info read buffer\n"); + return -EINVAL; + } + ext_info = iio_lookup_ext_info(chan, attr); if (!ext_info) return -EINVAL; @@ -1014,6 +1020,11 @@ EXPORT_SYMBOL_GPL(iio_write_channel_ext_info); ssize_t iio_read_channel_label(struct iio_channel *chan, char *buf) { + if (!buf || offset_in_page(buf)) { + pr_err("iio: invalid label read buffer\n"); + return -EINVAL; + } + return do_iio_read_channel_label(chan->indio_dev, chan->channel, buf); } EXPORT_SYMBOL_GPL(iio_read_channel_label); diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index 29ffa8491927..e34e551eef3e 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -329,22 +329,6 @@ config JSA1212 To compile this driver as a module, choose M here: the module will be called jsa1212. -config ROHM_BU27008 - tristate "ROHM BU27008 color (RGB+C/IR) sensor" - depends on I2C - select REGMAP_I2C - select IIO_GTS_HELPER - select IIO_BUFFER - select IIO_TRIGGERED_BUFFER - help - Enable support for the ROHM BU27008 color sensor. - The ROHM BU27008 is a sensor with 5 photodiodes (red, green, - blue, clear and IR) with four configurable channels. Red and - green being always available and two out of the rest three - (blue, clear, IR) can be selected to be simultaneously measured. - Typical application is adjusting LCD backlight of TVs, - mobile phones and tablet PCs. - config ROHM_BU27034 tristate "ROHM BU27034 ambient light sensor" depends on I2C @@ -491,6 +475,19 @@ config OPT4001 If built as a dynamically linked module, it will be called opt4001. +config OPT4060 + tristate "Texas Instruments OPT4060 RGBW Color Sensor" + depends on I2C + select REGMAP_I2C + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER + help + If you say Y or M here, you get support for Texas Instruments + OPT4060 RGBW Color Sensor. + + If built as a dynamically linked module, it will be called + opt4060. + config PA12203001 tristate "TXC PA12203001 light and proximity sensor" depends on I2C @@ -672,6 +669,7 @@ config VCNL4035 config VEML3235 tristate "VEML3235 ambient light sensor" select REGMAP_I2C + select IIO_GTS_HELPER depends on I2C help Say Y here if you want to build a driver for the Vishay VEML3235 @@ -683,6 +681,8 @@ config VEML3235 config VEML6030 tristate "VEML6030 and VEML6035 ambient light sensors" select REGMAP_I2C + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER depends on I2C help Say Y here if you want to build a driver for the Vishay VEML6030 diff --git a/drivers/iio/light/Makefile b/drivers/iio/light/Makefile index f14a37442712..11a4041b918a 100644 --- a/drivers/iio/light/Makefile +++ b/drivers/iio/light/Makefile @@ -42,8 +42,8 @@ obj-$(CONFIG_MAX44009) += max44009.o obj-$(CONFIG_NOA1305) += noa1305.o obj-$(CONFIG_OPT3001) += opt3001.o obj-$(CONFIG_OPT4001) += opt4001.o +obj-$(CONFIG_OPT4060) += opt4060.o obj-$(CONFIG_PA12203001) += pa12203001.o -obj-$(CONFIG_ROHM_BU27008) += rohm-bu27008.o obj-$(CONFIG_ROHM_BU27034) += rohm-bu27034.o obj-$(CONFIG_RPR0521) += rpr0521.o obj-$(CONFIG_SI1133) += si1133.o diff --git a/drivers/iio/light/adjd_s311.c b/drivers/iio/light/adjd_s311.c index c1b43053fbc7..cf96e3dd8bc6 100644 --- a/drivers/iio/light/adjd_s311.c +++ b/drivers/iio/light/adjd_s311.c @@ -56,7 +56,7 @@ struct adjd_s311_data { struct i2c_client *client; struct { s16 chans[4]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/light/as73211.c b/drivers/iio/light/as73211.c index be0068081ebb..37fffce35dd1 100644 --- a/drivers/iio/light/as73211.c +++ b/drivers/iio/light/as73211.c @@ -177,6 +177,12 @@ struct as73211_data { BIT(AS73211_SCAN_INDEX_TEMP) | \ AS73211_SCAN_MASK_COLOR) +static const unsigned long as73211_scan_masks[] = { + AS73211_SCAN_MASK_COLOR, + AS73211_SCAN_MASK_ALL, + 0 +}; + static const struct iio_chan_spec as73211_channels[] = { { .type = IIO_TEMP, @@ -636,7 +642,7 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p) struct as73211_data *data = iio_priv(indio_dev); struct { __le16 chan[4]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; int data_result, ret; @@ -672,9 +678,12 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p) /* AS73211 starts reading at address 2 */ ret = i2c_master_recv(data->client, - (char *)&scan.chan[1], 3 * sizeof(scan.chan[1])); + (char *)&scan.chan[0], 3 * sizeof(scan.chan[0])); if (ret < 0) goto done; + + /* Avoid pushing uninitialized data */ + scan.chan[3] = 0; } if (data_result) { @@ -682,9 +691,15 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p) * Saturate all channels (in case of overflows). Temperature channel * is not affected by overflows. */ - scan.chan[1] = cpu_to_le16(U16_MAX); - scan.chan[2] = cpu_to_le16(U16_MAX); - scan.chan[3] = cpu_to_le16(U16_MAX); + if (*indio_dev->active_scan_mask == AS73211_SCAN_MASK_ALL) { + scan.chan[1] = cpu_to_le16(U16_MAX); + scan.chan[2] = cpu_to_le16(U16_MAX); + scan.chan[3] = cpu_to_le16(U16_MAX); + } else { + scan.chan[0] = cpu_to_le16(U16_MAX); + scan.chan[1] = cpu_to_le16(U16_MAX); + scan.chan[2] = cpu_to_le16(U16_MAX); + } } iio_push_to_buffers_with_timestamp(indio_dev, &scan, iio_get_time_ns(indio_dev)); @@ -758,6 +773,7 @@ static int as73211_probe(struct i2c_client *client) indio_dev->channels = data->spec_dev->channels; indio_dev->num_channels = data->spec_dev->num_channels; indio_dev->modes = INDIO_DIRECT_MODE; + indio_dev->available_scan_masks = as73211_scan_masks; ret = i2c_smbus_read_byte_data(data->client, AS73211_REG_OSR); if (ret < 0) diff --git a/drivers/iio/light/bh1745.c b/drivers/iio/light/bh1745.c index 56e32689bb97..3b4056be54a0 100644 --- a/drivers/iio/light/bh1745.c +++ b/drivers/iio/light/bh1745.c @@ -739,13 +739,15 @@ static irqreturn_t bh1745_trigger_handler(int interrupt, void *p) struct bh1745_data *data = iio_priv(indio_dev); struct { u16 chans[4]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; u16 value; int ret; int i; int j = 0; + memset(&scan, 0, sizeof(scan)); + iio_for_each_active_channel(indio_dev, i) { ret = regmap_bulk_read(data->regmap, BH1745_RED_LSB + 2 * i, &value, 2); diff --git a/drivers/iio/light/cm3232.c b/drivers/iio/light/cm3232.c index b6288dd25bbf..5b00ad2a014e 100644 --- a/drivers/iio/light/cm3232.c +++ b/drivers/iio/light/cm3232.c @@ -89,6 +89,15 @@ static int cm3232_reg_init(struct cm3232_chip *chip) chip->als_info = &cm3232_als_info_default; + /* Disable and reset device */ + chip->regs_cmd = CM3232_CMD_ALS_DISABLE | CM3232_CMD_ALS_RESET; + ret = i2c_smbus_write_byte_data(client, CM3232_REG_ADDR_CMD, + chip->regs_cmd); + if (ret < 0) { + dev_err(&chip->client->dev, "Error writing reg_cmd\n"); + return ret; + } + /* Identify device */ ret = i2c_smbus_read_word_data(client, CM3232_REG_ADDR_ID); if (ret < 0) { @@ -99,15 +108,6 @@ static int cm3232_reg_init(struct cm3232_chip *chip) if ((ret & 0xFF) != chip->als_info->hw_id) return -ENODEV; - /* Disable and reset device */ - chip->regs_cmd = CM3232_CMD_ALS_DISABLE | CM3232_CMD_ALS_RESET; - ret = i2c_smbus_write_byte_data(client, CM3232_REG_ADDR_CMD, - chip->regs_cmd); - if (ret < 0) { - dev_err(&chip->client->dev, "Error writing reg_cmd\n"); - return ret; - } - /* Register default value */ chip->regs_cmd = chip->als_info->regs_cmd_default; diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c index c83acbd78275..7ab64f5c623c 100644 --- a/drivers/iio/light/hid-sensor-prox.c +++ b/drivers/iio/light/hid-sensor-prox.c @@ -94,6 +94,7 @@ static int prox_read_raw(struct iio_dev *indio_dev, *val2 = 0; switch (mask) { case IIO_CHAN_INFO_RAW: + case IIO_CHAN_INFO_PROCESSED: if (chan->scan_index >= prox_state->num_channels) return -EINVAL; address = prox_state->channel2usage[chan->scan_index]; diff --git a/drivers/iio/light/isl29125.c b/drivers/iio/light/isl29125.c index b176bf4c884b..326dc39e7929 100644 --- a/drivers/iio/light/isl29125.c +++ b/drivers/iio/light/isl29125.c @@ -54,7 +54,7 @@ struct isl29125_data { /* Ensure timestamp is naturally aligned */ struct { u16 chans[3]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; }; diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c index 604f5f900a2e..669da0840eba 100644 --- a/drivers/iio/light/ltr501.c +++ b/drivers/iio/light/ltr501.c @@ -1280,7 +1280,7 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p) struct ltr501_data *data = iio_priv(indio_dev); struct { u16 channels[3]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; __le16 als_buf[2]; u8 mask = 0; diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c index b935976871a6..e8b767680133 100644 --- a/drivers/iio/light/max44000.c +++ b/drivers/iio/light/max44000.c @@ -78,7 +78,7 @@ struct max44000_data { /* Ensure naturally aligned timestamp */ struct { u16 channels[2]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/light/opt4060.c b/drivers/iio/light/opt4060.c new file mode 100644 index 000000000000..ab55f8d2ea0c --- /dev/null +++ b/drivers/iio/light/opt4060.c @@ -0,0 +1,1343 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Axis Communications AB + * + * Datasheet: https://www.ti.com/lit/gpn/opt4060 + * + * Device driver for the Texas Instruments OPT4060 RGBW Color Sensor. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* OPT4060 register set */ +#define OPT4060_RED_MSB 0x00 +#define OPT4060_RED_LSB 0x01 +#define OPT4060_GREEN_MSB 0x02 +#define OPT4060_GREEN_LSB 0x03 +#define OPT4060_BLUE_MSB 0x04 +#define OPT4060_BLUE_LSB 0x05 +#define OPT4060_CLEAR_MSB 0x06 +#define OPT4060_CLEAR_LSB 0x07 +#define OPT4060_THRESHOLD_LOW 0x08 +#define OPT4060_THRESHOLD_HIGH 0x09 +#define OPT4060_CTRL 0x0a +#define OPT4060_INT_CTRL 0x0b +#define OPT4060_RES_CTRL 0x0c +#define OPT4060_DEVICE_ID 0x11 + +/* OPT4060 register mask */ +#define OPT4060_EXPONENT_MASK GENMASK(15, 12) +#define OPT4060_MSB_MASK GENMASK(11, 0) +#define OPT4060_LSB_MASK GENMASK(15, 8) +#define OPT4060_COUNTER_MASK GENMASK(7, 4) +#define OPT4060_CRC_MASK GENMASK(3, 0) + +/* OPT4060 device id mask */ +#define OPT4060_DEVICE_ID_MASK GENMASK(11, 0) + +/* OPT4060 control register masks */ +#define OPT4060_CTRL_QWAKE_MASK BIT(15) +#define OPT4060_CTRL_RANGE_MASK GENMASK(13, 10) +#define OPT4060_CTRL_CONV_TIME_MASK GENMASK(9, 6) +#define OPT4060_CTRL_OPER_MODE_MASK GENMASK(5, 4) +#define OPT4060_CTRL_LATCH_MASK BIT(3) +#define OPT4060_CTRL_INT_POL_MASK BIT(2) +#define OPT4060_CTRL_FAULT_COUNT_MASK GENMASK(1, 0) + +/* OPT4060 interrupt control register masks */ +#define OPT4060_INT_CTRL_THRESH_SEL GENMASK(6, 5) +#define OPT4060_INT_CTRL_OUTPUT BIT(4) +#define OPT4060_INT_CTRL_INT_CFG GENMASK(3, 2) +#define OPT4060_INT_CTRL_THRESHOLD 0x0 +#define OPT4060_INT_CTRL_NEXT_CH 0x1 +#define OPT4060_INT_CTRL_ALL_CH 0x3 + +/* OPT4060 result control register masks */ +#define OPT4060_RES_CTRL_OVERLOAD BIT(3) +#define OPT4060_RES_CTRL_CONV_READY BIT(2) +#define OPT4060_RES_CTRL_FLAG_H BIT(1) +#define OPT4060_RES_CTRL_FLAG_L BIT(0) + +/* OPT4060 constants */ +#define OPT4060_DEVICE_ID_VAL 0x821 + +/* OPT4060 operating modes */ +#define OPT4060_CTRL_OPER_MODE_OFF 0x0 +#define OPT4060_CTRL_OPER_MODE_FORCED 0x1 +#define OPT4060_CTRL_OPER_MODE_ONE_SHOT 0x2 +#define OPT4060_CTRL_OPER_MODE_CONTINUOUS 0x3 + +/* OPT4060 conversion control register definitions */ +#define OPT4060_CTRL_CONVERSION_0_6MS 0x0 +#define OPT4060_CTRL_CONVERSION_1MS 0x1 +#define OPT4060_CTRL_CONVERSION_1_8MS 0x2 +#define OPT4060_CTRL_CONVERSION_3_4MS 0x3 +#define OPT4060_CTRL_CONVERSION_6_5MS 0x4 +#define OPT4060_CTRL_CONVERSION_12_7MS 0x5 +#define OPT4060_CTRL_CONVERSION_25MS 0x6 +#define OPT4060_CTRL_CONVERSION_50MS 0x7 +#define OPT4060_CTRL_CONVERSION_100MS 0x8 +#define OPT4060_CTRL_CONVERSION_200MS 0x9 +#define OPT4060_CTRL_CONVERSION_400MS 0xa +#define OPT4060_CTRL_CONVERSION_800MS 0xb + +/* OPT4060 fault count control register definitions */ +#define OPT4060_CTRL_FAULT_COUNT_1 0x0 +#define OPT4060_CTRL_FAULT_COUNT_2 0x1 +#define OPT4060_CTRL_FAULT_COUNT_4 0x2 +#define OPT4060_CTRL_FAULT_COUNT_8 0x3 + +/* OPT4060 scale light level range definitions */ +#define OPT4060_CTRL_LIGHT_SCALE_AUTO 12 + +/* OPT4060 default values */ +#define OPT4060_DEFAULT_CONVERSION_TIME OPT4060_CTRL_CONVERSION_50MS + +/* + * enum opt4060_chan_type - OPT4060 channel types + * @OPT4060_RED: Red channel. + * @OPT4060_GREEN: Green channel. + * @OPT4060_BLUE: Blue channel. + * @OPT4060_CLEAR: Clear (white) channel. + * @OPT4060_ILLUM: Calculated illuminance channel. + * @OPT4060_NUM_CHANS: Number of channel types. + */ +enum opt4060_chan_type { + OPT4060_RED, + OPT4060_GREEN, + OPT4060_BLUE, + OPT4060_CLEAR, + OPT4060_ILLUM, + OPT4060_NUM_CHANS +}; + +struct opt4060_chip { + struct regmap *regmap; + struct device *dev; + struct iio_trigger *trig; + u8 int_time; + int irq; + /* + * Mutex for protecting sensor irq settings. Switching between interrupt + * on each sample and on thresholds needs to be synchronized. + */ + struct mutex irq_setting_lock; + /* + * Mutex for protecting event enabling. + */ + struct mutex event_enabling_lock; + struct completion completion; + bool thresh_event_lo_active; + bool thresh_event_hi_active; +}; + +struct opt4060_channel_factor { + u32 mul; + u32 div; +}; + +static const int opt4060_int_time_available[][2] = { + { 0, 600 }, + { 0, 1000 }, + { 0, 1800 }, + { 0, 3400 }, + { 0, 6500 }, + { 0, 12700 }, + { 0, 25000 }, + { 0, 50000 }, + { 0, 100000 }, + { 0, 200000 }, + { 0, 400000 }, + { 0, 800000 }, +}; + +/* + * Conversion time is integration time + time to set register + * this is used as integration time. + */ +static const int opt4060_int_time_reg[][2] = { + { 600, OPT4060_CTRL_CONVERSION_0_6MS }, + { 1000, OPT4060_CTRL_CONVERSION_1MS }, + { 1800, OPT4060_CTRL_CONVERSION_1_8MS }, + { 3400, OPT4060_CTRL_CONVERSION_3_4MS }, + { 6500, OPT4060_CTRL_CONVERSION_6_5MS }, + { 12700, OPT4060_CTRL_CONVERSION_12_7MS }, + { 25000, OPT4060_CTRL_CONVERSION_25MS }, + { 50000, OPT4060_CTRL_CONVERSION_50MS }, + { 100000, OPT4060_CTRL_CONVERSION_100MS }, + { 200000, OPT4060_CTRL_CONVERSION_200MS }, + { 400000, OPT4060_CTRL_CONVERSION_400MS }, + { 800000, OPT4060_CTRL_CONVERSION_800MS }, +}; + +static int opt4060_als_time_to_index(const u32 als_integration_time) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(opt4060_int_time_available); i++) { + if (als_integration_time == opt4060_int_time_available[i][1]) + return i; + } + + return -EINVAL; +} + +static u8 opt4060_calculate_crc(u8 exp, u32 mantissa, u8 count) +{ + u8 crc; + + /* + * Calculates a 4-bit CRC from a 20-bit mantissa, 4-bit exponent and a 4-bit counter. + * crc[0] = XOR(mantissa[19:0], exp[3:0], count[3:0]) + * crc[1] = XOR(mantissa[1,3,5,7,9,11,13,15,17,19], exp[1,3], count[1,3]) + * crc[2] = XOR(mantissa[3,7,11,15,19], exp[3], count[3]) + * crc[3] = XOR(mantissa[3,11,19]) + */ + crc = (hweight32(mantissa) + hweight32(exp) + hweight32(count)) % 2; + crc |= ((hweight32(mantissa & 0xAAAAA) + hweight32(exp & 0xA) + + hweight32(count & 0xA)) % 2) << 1; + crc |= ((hweight32(mantissa & 0x88888) + hweight32(exp & 0x8) + + hweight32(count & 0x8)) % 2) << 2; + crc |= (hweight32(mantissa & 0x80808) % 2) << 3; + + return crc; +} + +static int opt4060_set_int_state(struct opt4060_chip *chip, u32 state) +{ + int ret; + unsigned int regval; + + guard(mutex)(&chip->irq_setting_lock); + + regval = FIELD_PREP(OPT4060_INT_CTRL_INT_CFG, state); + ret = regmap_update_bits(chip->regmap, OPT4060_INT_CTRL, + OPT4060_INT_CTRL_INT_CFG, regval); + if (ret) + dev_err(chip->dev, "Failed to set interrupt config\n"); + return ret; +} + +static int opt4060_set_sampling_mode(struct opt4060_chip *chip, + bool continuous) +{ + unsigned int reg; + int ret; + + ret = regmap_read(chip->regmap, OPT4060_CTRL, ®); + if (ret < 0) { + dev_err(chip->dev, "Failed to read ctrl register\n"); + return ret; + } + reg &= ~OPT4060_CTRL_OPER_MODE_MASK; + if (continuous) + reg |= FIELD_PREP(OPT4060_CTRL_OPER_MODE_MASK, + OPT4060_CTRL_OPER_MODE_CONTINUOUS); + else + reg |= FIELD_PREP(OPT4060_CTRL_OPER_MODE_MASK, + OPT4060_CTRL_OPER_MODE_ONE_SHOT); + + /* + * Trigger a new conversions by writing to CRTL register. It is not + * possible to use regmap_update_bits() since that will only write when + * data is modified. + */ + ret = regmap_write(chip->regmap, OPT4060_CTRL, reg); + if (ret) + dev_err(chip->dev, "Failed to set ctrl register\n"); + return ret; +} + +static bool opt4060_event_active(struct opt4060_chip *chip) +{ + return chip->thresh_event_lo_active || chip->thresh_event_hi_active; +} + +static int opt4060_set_state_common(struct opt4060_chip *chip, + bool continuous_sampling, + bool continuous_irq) +{ + int ret = 0; + + /* It is important to setup irq before sampling to avoid missing samples. */ + if (continuous_irq) + ret = opt4060_set_int_state(chip, OPT4060_INT_CTRL_ALL_CH); + else + ret = opt4060_set_int_state(chip, OPT4060_INT_CTRL_THRESHOLD); + if (ret) { + dev_err(chip->dev, "Failed to set irq state.\n"); + return ret; + } + + if (continuous_sampling || opt4060_event_active(chip)) + ret = opt4060_set_sampling_mode(chip, true); + else + ret = opt4060_set_sampling_mode(chip, false); + if (ret) + dev_err(chip->dev, "Failed to set sampling state.\n"); + return ret; +} + +/* + * Function for setting the driver state for sampling and irq. Either direct + * mode of buffer mode will be claimed during the transition to prevent races + * between sysfs read, buffer or events. + */ +static int opt4060_set_driver_state(struct iio_dev *indio_dev, + bool continuous_sampling, + bool continuous_irq) +{ + struct opt4060_chip *chip = iio_priv(indio_dev); + int ret = 0; +any_mode_retry: + if (iio_device_claim_buffer_mode(indio_dev)) { + /* + * This one is a *bit* hacky. If we cannot claim buffer mode, + * then try direct mode so that we make sure things cannot + * concurrently change. And we just keep trying until we get one + * of the modes... + */ + if (iio_device_claim_direct_mode(indio_dev)) + goto any_mode_retry; + /* + * This path means that we managed to claim direct mode. In + * this case the buffer isn't enabled and it's okay to leave + * continuous mode for sampling and/or irq. + */ + ret = opt4060_set_state_common(chip, continuous_sampling, + continuous_irq); + iio_device_release_direct_mode(indio_dev); + } else { + /* + * This path means that we managed to claim buffer mode. In + * this case the buffer is enabled and irq and sampling must go + * to or remain continuous, but only if the trigger is from this + * device. + */ + if (!iio_trigger_validate_own_device(indio_dev->trig, indio_dev)) + ret = opt4060_set_state_common(chip, true, true); + else + ret = opt4060_set_state_common(chip, continuous_sampling, + continuous_irq); + iio_device_release_buffer_mode(indio_dev); + } + return ret; +} + +/* + * This function is called with framework mutex locked. + */ +static int opt4060_trigger_set_state(struct iio_trigger *trig, bool state) +{ + struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig); + struct opt4060_chip *chip = iio_priv(indio_dev); + + return opt4060_set_state_common(chip, state, state); +} + +static int opt4060_read_raw_value(struct opt4060_chip *chip, + unsigned long address, u32 *raw) +{ + int ret; + u16 result[2]; + u32 mantissa_raw; + u16 msb, lsb; + u8 exp, count, crc, calc_crc; + + ret = regmap_bulk_read(chip->regmap, address, result, 2); + if (ret) { + dev_err(chip->dev, "Reading channel data failed\n"); + return ret; + } + exp = FIELD_GET(OPT4060_EXPONENT_MASK, result[0]); + msb = FIELD_GET(OPT4060_MSB_MASK, result[0]); + count = FIELD_GET(OPT4060_COUNTER_MASK, result[1]); + crc = FIELD_GET(OPT4060_CRC_MASK, result[1]); + lsb = FIELD_GET(OPT4060_LSB_MASK, result[1]); + mantissa_raw = (msb << 8) + lsb; + calc_crc = opt4060_calculate_crc(exp, mantissa_raw, count); + if (calc_crc != crc) + return -EIO; + *raw = mantissa_raw << exp; + return 0; +} + +static int opt4060_trigger_new_samples(struct iio_dev *indio_dev) +{ + struct opt4060_chip *chip = iio_priv(indio_dev); + int ret; + + /* + * The conversion time should be 500us startup time plus the integration time + * times the number of channels. An exact timeout isn't critical, it's better + * not to get incorrect errors in the log. Setting the timeout to double the + * theoretical time plus and extra 100ms margin. + */ + unsigned int timeout_us = (500 + OPT4060_NUM_CHANS * + opt4060_int_time_reg[chip->int_time][0]) * 2 + 100000; + + /* Setting the state in one shot mode with irq on each sample. */ + ret = opt4060_set_driver_state(indio_dev, false, true); + if (ret) + return ret; + + if (chip->irq) { + guard(mutex)(&chip->irq_setting_lock); + reinit_completion(&chip->completion); + if (wait_for_completion_timeout(&chip->completion, + usecs_to_jiffies(timeout_us)) == 0) { + dev_err(chip->dev, "Completion timed out.\n"); + return -ETIME; + } + } else { + unsigned int ready; + + ret = regmap_read_poll_timeout(chip->regmap, OPT4060_RES_CTRL, + ready, (ready & OPT4060_RES_CTRL_CONV_READY), + 1000, timeout_us); + if (ret) + dev_err(chip->dev, "Conversion ready did not finish within timeout.\n"); + } + /* Setting the state in one shot mode with irq on thresholds. */ + return opt4060_set_driver_state(indio_dev, false, false); +} + +static int opt4060_read_chan_raw(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, int *val) +{ + struct opt4060_chip *chip = iio_priv(indio_dev); + u32 adc_raw; + int ret; + + ret = opt4060_trigger_new_samples(indio_dev); + if (ret) { + dev_err(chip->dev, "Failed to trigger new samples.\n"); + return ret; + } + + ret = opt4060_read_raw_value(chip, chan->address, &adc_raw); + if (ret) { + dev_err(chip->dev, "Reading raw channel data failed.\n"); + return ret; + } + *val = adc_raw; + return IIO_VAL_INT; +} + +/* + * Returns the scale values used for red, green and blue. Scales the raw value + * so that for a particular test light source, typically white, the measurement + * intensity is the same across different color channels. + */ +static int opt4060_get_chan_scale(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + int *val, int *val2) +{ + struct opt4060_chip *chip = iio_priv(indio_dev); + + switch (chan->scan_index) { + case OPT4060_RED: + /* 2.4 */ + *val = 2; + *val2 = 400000; + break; + case OPT4060_GREEN: + /* 1.0 */ + *val = 1; + *val2 = 0; + break; + case OPT4060_BLUE: + /* 1.3 */ + *val = 1; + *val2 = 300000; + break; + default: + dev_err(chip->dev, "Unexpected channel index.\n"); + return -EINVAL; + } + return IIO_VAL_INT_PLUS_MICRO; +} + +static int opt4060_calc_illuminance(struct opt4060_chip *chip, int *val) +{ + u32 lux_raw; + int ret; + + /* The green wide spectral channel is used for illuminance. */ + ret = opt4060_read_raw_value(chip, OPT4060_GREEN_MSB, &lux_raw); + if (ret) { + dev_err(chip->dev, "Reading raw channel data failed\n"); + return ret; + } + + /* Illuminance is calculated by ADC_RAW * 2.15e-3. */ + *val = DIV_U64_ROUND_CLOSEST((u64)(lux_raw * 215), 1000); + return ret; +} + +static int opt4060_read_illuminance(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + int *val) +{ + struct opt4060_chip *chip = iio_priv(indio_dev); + int ret; + + ret = opt4060_trigger_new_samples(indio_dev); + if (ret) { + dev_err(chip->dev, "Failed to trigger new samples.\n"); + return ret; + } + ret = opt4060_calc_illuminance(chip, val); + if (ret) { + dev_err(chip->dev, "Failed to calculate illuminance.\n"); + return ret; + } + + return IIO_VAL_INT; +} + +static int opt4060_set_int_time(struct opt4060_chip *chip) +{ + unsigned int regval; + int ret; + + regval = FIELD_PREP(OPT4060_CTRL_CONV_TIME_MASK, chip->int_time); + ret = regmap_update_bits(chip->regmap, OPT4060_CTRL, + OPT4060_CTRL_CONV_TIME_MASK, regval); + if (ret) + dev_err(chip->dev, "Failed to set integration time.\n"); + + return ret; +} + +static int opt4060_power_down(struct opt4060_chip *chip) +{ + int ret; + + ret = regmap_clear_bits(chip->regmap, OPT4060_CTRL, OPT4060_CTRL_OPER_MODE_MASK); + if (ret) + dev_err(chip->dev, "Failed to power down\n"); + + return ret; +} + +static void opt4060_chip_off_action(void *chip) +{ + opt4060_power_down(chip); +} + +#define _OPT4060_COLOR_CHANNEL(_color, _mask, _ev_spec, _num_ev_spec) \ +{ \ + .type = IIO_INTENSITY, \ + .modified = 1, \ + .channel2 = IIO_MOD_LIGHT_##_color, \ + .info_mask_separate = _mask, \ + .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME), \ + .info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME), \ + .address = OPT4060_##_color##_MSB, \ + .scan_index = OPT4060_##_color, \ + .scan_type = { \ + .sign = 'u', \ + .realbits = 32, \ + .storagebits = 32, \ + .endianness = IIO_CPU, \ + }, \ + .event_spec = _ev_spec, \ + .num_event_specs = _num_ev_spec, \ +} + +#define OPT4060_COLOR_CHANNEL(_color, _mask) \ + _OPT4060_COLOR_CHANNEL(_color, _mask, opt4060_event_spec, \ + ARRAY_SIZE(opt4060_event_spec)) \ + +#define OPT4060_COLOR_CHANNEL_NO_EVENTS(_color, _mask) \ + _OPT4060_COLOR_CHANNEL(_color, _mask, NULL, 0) \ + +#define OPT4060_LIGHT_CHANNEL(_channel) \ +{ \ + .type = IIO_LIGHT, \ + .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED), \ + .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME), \ + .info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME), \ + .scan_index = OPT4060_##_channel, \ + .scan_type = { \ + .sign = 'u', \ + .realbits = 32, \ + .storagebits = 32, \ + .endianness = IIO_CPU, \ + }, \ +} + +static const struct iio_event_spec opt4060_event_spec[] = { + { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_RISING, + .mask_separate = BIT(IIO_EV_INFO_VALUE) | + BIT(IIO_EV_INFO_ENABLE), + }, { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_FALLING, + .mask_separate = BIT(IIO_EV_INFO_VALUE) | + BIT(IIO_EV_INFO_ENABLE), + }, { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_EITHER, + .mask_separate = BIT(IIO_EV_INFO_PERIOD), + }, +}; + +static const struct iio_chan_spec opt4060_channels[] = { + OPT4060_COLOR_CHANNEL(RED, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)), + OPT4060_COLOR_CHANNEL(GREEN, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)), + OPT4060_COLOR_CHANNEL(BLUE, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)), + OPT4060_COLOR_CHANNEL(CLEAR, BIT(IIO_CHAN_INFO_RAW)), + OPT4060_LIGHT_CHANNEL(ILLUM), + IIO_CHAN_SOFT_TIMESTAMP(OPT4060_NUM_CHANS), +}; + +static const struct iio_chan_spec opt4060_channels_no_events[] = { + OPT4060_COLOR_CHANNEL_NO_EVENTS(RED, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)), + OPT4060_COLOR_CHANNEL_NO_EVENTS(GREEN, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)), + OPT4060_COLOR_CHANNEL_NO_EVENTS(BLUE, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)), + OPT4060_COLOR_CHANNEL_NO_EVENTS(CLEAR, BIT(IIO_CHAN_INFO_RAW)), + OPT4060_LIGHT_CHANNEL(ILLUM), + IIO_CHAN_SOFT_TIMESTAMP(OPT4060_NUM_CHANS), +}; + +static int opt4060_read_raw(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + int *val, int *val2, long mask) +{ + struct opt4060_chip *chip = iio_priv(indio_dev); + + switch (mask) { + case IIO_CHAN_INFO_RAW: + return opt4060_read_chan_raw(indio_dev, chan, val); + case IIO_CHAN_INFO_SCALE: + return opt4060_get_chan_scale(indio_dev, chan, val, val2); + case IIO_CHAN_INFO_PROCESSED: + return opt4060_read_illuminance(indio_dev, chan, val); + case IIO_CHAN_INFO_INT_TIME: + *val = 0; + *val2 = opt4060_int_time_reg[chip->int_time][0]; + return IIO_VAL_INT_PLUS_MICRO; + default: + return -EINVAL; + } +} + +static int opt4060_write_raw(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + int val, int val2, long mask) +{ + struct opt4060_chip *chip = iio_priv(indio_dev); + int int_time; + + switch (mask) { + case IIO_CHAN_INFO_INT_TIME: + int_time = opt4060_als_time_to_index(val2); + if (int_time < 0) + return int_time; + chip->int_time = int_time; + return opt4060_set_int_time(chip); + default: + return -EINVAL; + } +} + +static int opt4060_write_raw_get_fmt(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + long mask) +{ + switch (mask) { + case IIO_CHAN_INFO_INT_TIME: + return IIO_VAL_INT_PLUS_MICRO; + default: + return -EINVAL; + } +} + +static u32 opt4060_calc_th_reg(u32 adc_val) +{ + u32 th_val, th_exp, bits; + /* + * The threshold registers take 4 bits of exponent and 12 bits of data + * ADC = TH_VAL << (8 + TH_EXP) + */ + bits = fls(adc_val); + + if (bits > 31) + th_exp = 11; /* Maximum exponent */ + else if (bits > 20) + th_exp = bits - 20; + else + th_exp = 0; + th_val = (adc_val >> (8 + th_exp)) & 0xfff; + + return (th_exp << 12) + th_val; +} + +static u32 opt4060_calc_val_from_th_reg(u32 th_reg) +{ + /* + * The threshold registers take 4 bits of exponent and 12 bits of data + * ADC = TH_VAL << (8 + TH_EXP) + */ + u32 th_val, th_exp; + + th_exp = (th_reg >> 12) & 0xf; + th_val = th_reg & 0xfff; + + return th_val << (8 + th_exp); +} + +static int opt4060_read_available(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + const int **vals, int *type, int *length, + long mask) +{ + switch (mask) { + case IIO_CHAN_INFO_INT_TIME: + *length = ARRAY_SIZE(opt4060_int_time_available) * 2; + *vals = (const int *)opt4060_int_time_available; + *type = IIO_VAL_INT_PLUS_MICRO; + return IIO_AVAIL_LIST; + + default: + return -EINVAL; + } +} + +static ssize_t opt4060_read_ev_period(struct opt4060_chip *chip, int *val, + int *val2) +{ + int ret, pers, fault_count, int_time; + u64 uval; + + int_time = opt4060_int_time_reg[chip->int_time][0]; + + ret = regmap_read(chip->regmap, OPT4060_CTRL, &fault_count); + if (ret < 0) + return ret; + + fault_count = fault_count & OPT4060_CTRL_FAULT_COUNT_MASK; + switch (fault_count) { + case OPT4060_CTRL_FAULT_COUNT_2: + pers = 2; + break; + case OPT4060_CTRL_FAULT_COUNT_4: + pers = 4; + break; + case OPT4060_CTRL_FAULT_COUNT_8: + pers = 8; + break; + + default: + pers = 1; + break; + } + + uval = mul_u32_u32(int_time, pers); + *val = div_u64_rem(uval, MICRO, val2); + + return IIO_VAL_INT_PLUS_MICRO; +} + +static ssize_t opt4060_write_ev_period(struct opt4060_chip *chip, int val, + int val2) +{ + u64 uval, int_time; + unsigned int regval, fault_count_val; + + uval = mul_u32_u32(val, MICRO) + val2; + int_time = opt4060_int_time_reg[chip->int_time][0]; + + /* Check if the period is closest to 1, 2, 4 or 8 times integration time.*/ + if (uval <= int_time) + fault_count_val = OPT4060_CTRL_FAULT_COUNT_1; + else if (uval <= int_time * 2) + fault_count_val = OPT4060_CTRL_FAULT_COUNT_2; + else if (uval <= int_time * 4) + fault_count_val = OPT4060_CTRL_FAULT_COUNT_4; + else + fault_count_val = OPT4060_CTRL_FAULT_COUNT_8; + + regval = FIELD_PREP(OPT4060_CTRL_FAULT_COUNT_MASK, fault_count_val); + return regmap_update_bits(chip->regmap, OPT4060_CTRL, + OPT4060_CTRL_FAULT_COUNT_MASK, regval); +} + +static int opt4060_get_channel_sel(struct opt4060_chip *chip, int *ch_sel) +{ + int ret; + u32 regval; + + ret = regmap_read(chip->regmap, OPT4060_INT_CTRL, ®val); + if (ret) { + dev_err(chip->dev, "Failed to get channel selection.\n"); + return ret; + } + *ch_sel = FIELD_GET(OPT4060_INT_CTRL_THRESH_SEL, regval); + return ret; +} + +static int opt4060_set_channel_sel(struct opt4060_chip *chip, int ch_sel) +{ + int ret; + u32 regval; + + regval = FIELD_PREP(OPT4060_INT_CTRL_THRESH_SEL, ch_sel); + ret = regmap_update_bits(chip->regmap, OPT4060_INT_CTRL, + OPT4060_INT_CTRL_THRESH_SEL, regval); + if (ret) + dev_err(chip->dev, "Failed to set channel selection.\n"); + return ret; +} + +static int opt4060_get_thresholds(struct opt4060_chip *chip, u32 *th_lo, u32 *th_hi) +{ + int ret; + u32 regval; + + ret = regmap_read(chip->regmap, OPT4060_THRESHOLD_LOW, ®val); + if (ret) { + dev_err(chip->dev, "Failed to read THRESHOLD_LOW.\n"); + return ret; + } + *th_lo = opt4060_calc_val_from_th_reg(regval); + + ret = regmap_read(chip->regmap, OPT4060_THRESHOLD_HIGH, ®val); + if (ret) { + dev_err(chip->dev, "Failed to read THRESHOLD_LOW.\n"); + return ret; + } + *th_hi = opt4060_calc_val_from_th_reg(regval); + + return ret; +} + +static int opt4060_set_thresholds(struct opt4060_chip *chip, u32 th_lo, u32 th_hi) +{ + int ret; + + ret = regmap_write(chip->regmap, OPT4060_THRESHOLD_LOW, opt4060_calc_th_reg(th_lo)); + if (ret) { + dev_err(chip->dev, "Failed to write THRESHOLD_LOW.\n"); + return ret; + } + + ret = regmap_write(chip->regmap, OPT4060_THRESHOLD_HIGH, opt4060_calc_th_reg(th_hi)); + if (ret) + dev_err(chip->dev, "Failed to write THRESHOLD_HIGH.\n"); + + return ret; +} + +static int opt4060_read_event(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, + enum iio_event_info info, + int *val, int *val2) +{ + struct opt4060_chip *chip = iio_priv(indio_dev); + u32 th_lo, th_hi; + int ret; + + if (chan->type != IIO_INTENSITY) + return -EINVAL; + if (type != IIO_EV_TYPE_THRESH) + return -EINVAL; + + switch (info) { + case IIO_EV_INFO_VALUE: + ret = opt4060_get_thresholds(chip, &th_lo, &th_hi); + if (ret) + return ret; + if (dir == IIO_EV_DIR_FALLING) { + *val = th_lo; + ret = IIO_VAL_INT; + } else if (dir == IIO_EV_DIR_RISING) { + *val = th_hi; + ret = IIO_VAL_INT; + } + return ret; + case IIO_EV_INFO_PERIOD: + return opt4060_read_ev_period(chip, val, val2); + default: + return -EINVAL; + } +} + +static int opt4060_write_event(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, + enum iio_event_info info, + int val, int val2) +{ + struct opt4060_chip *chip = iio_priv(indio_dev); + u32 th_lo, th_hi; + int ret; + + if (chan->type != IIO_INTENSITY) + return -EINVAL; + if (type != IIO_EV_TYPE_THRESH) + return -EINVAL; + + switch (info) { + case IIO_EV_INFO_VALUE: + ret = opt4060_get_thresholds(chip, &th_lo, &th_hi); + if (ret) + return ret; + if (dir == IIO_EV_DIR_FALLING) + th_lo = val; + else if (dir == IIO_EV_DIR_RISING) + th_hi = val; + return opt4060_set_thresholds(chip, th_lo, th_hi); + case IIO_EV_INFO_PERIOD: + return opt4060_write_ev_period(chip, val, val2); + default: + return -EINVAL; + } +} + +static int opt4060_read_event_config(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir) +{ + int ch_sel, ch_idx = chan->scan_index; + struct opt4060_chip *chip = iio_priv(indio_dev); + int ret; + + if (chan->type != IIO_INTENSITY) + return -EINVAL; + if (type != IIO_EV_TYPE_THRESH) + return -EINVAL; + + ret = opt4060_get_channel_sel(chip, &ch_sel); + if (ret) + return ret; + + if (((dir == IIO_EV_DIR_FALLING) && chip->thresh_event_lo_active) || + ((dir == IIO_EV_DIR_RISING) && chip->thresh_event_hi_active)) + return ch_sel == ch_idx; + + return ret; +} + +static int opt4060_write_event_config(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, bool state) +{ + int ch_sel, ch_idx = chan->scan_index; + struct opt4060_chip *chip = iio_priv(indio_dev); + int ret; + + guard(mutex)(&chip->event_enabling_lock); + + if (chan->type != IIO_INTENSITY) + return -EINVAL; + if (type != IIO_EV_TYPE_THRESH) + return -EINVAL; + + ret = opt4060_get_channel_sel(chip, &ch_sel); + if (ret) + return ret; + + if (state) { + /* Only one channel can be active at the same time */ + if ((chip->thresh_event_lo_active || chip->thresh_event_hi_active) && + (ch_idx != ch_sel)) + return -EBUSY; + if (dir == IIO_EV_DIR_FALLING) + chip->thresh_event_lo_active = true; + else if (dir == IIO_EV_DIR_RISING) + chip->thresh_event_hi_active = true; + ret = opt4060_set_channel_sel(chip, ch_idx); + if (ret) + return ret; + } else { + if (ch_idx == ch_sel) { + if (dir == IIO_EV_DIR_FALLING) + chip->thresh_event_lo_active = false; + else if (dir == IIO_EV_DIR_RISING) + chip->thresh_event_hi_active = false; + } + } + + return opt4060_set_driver_state(indio_dev, + chip->thresh_event_hi_active | + chip->thresh_event_lo_active, + false); +} + +static const struct iio_info opt4060_info = { + .read_raw = opt4060_read_raw, + .write_raw = opt4060_write_raw, + .write_raw_get_fmt = opt4060_write_raw_get_fmt, + .read_avail = opt4060_read_available, + .read_event_value = opt4060_read_event, + .write_event_value = opt4060_write_event, + .read_event_config = opt4060_read_event_config, + .write_event_config = opt4060_write_event_config, +}; + +static const struct iio_info opt4060_info_no_irq = { + .read_raw = opt4060_read_raw, + .write_raw = opt4060_write_raw, + .write_raw_get_fmt = opt4060_write_raw_get_fmt, + .read_avail = opt4060_read_available, +}; + +static int opt4060_load_defaults(struct opt4060_chip *chip) +{ + u16 reg; + int ret; + + chip->int_time = OPT4060_DEFAULT_CONVERSION_TIME; + + /* Set initial MIN/MAX thresholds */ + ret = opt4060_set_thresholds(chip, 0, UINT_MAX); + if (ret) + return ret; + + /* + * Setting auto-range, latched window for thresholds, one-shot conversion + * and quick wake-up mode as default. + */ + reg = FIELD_PREP(OPT4060_CTRL_RANGE_MASK, + OPT4060_CTRL_LIGHT_SCALE_AUTO); + reg |= FIELD_PREP(OPT4060_CTRL_CONV_TIME_MASK, chip->int_time); + reg |= FIELD_PREP(OPT4060_CTRL_OPER_MODE_MASK, + OPT4060_CTRL_OPER_MODE_ONE_SHOT); + reg |= OPT4060_CTRL_QWAKE_MASK | OPT4060_CTRL_LATCH_MASK; + + ret = regmap_write(chip->regmap, OPT4060_CTRL, reg); + if (ret) + dev_err(chip->dev, "Failed to set configuration\n"); + + return ret; +} + +static bool opt4060_volatile_reg(struct device *dev, unsigned int reg) +{ + return reg <= OPT4060_CLEAR_LSB || reg == OPT4060_RES_CTRL; +} + +static bool opt4060_writable_reg(struct device *dev, unsigned int reg) +{ + return reg >= OPT4060_THRESHOLD_LOW || reg >= OPT4060_INT_CTRL; +} + +static bool opt4060_readonly_reg(struct device *dev, unsigned int reg) +{ + return reg == OPT4060_DEVICE_ID; +} + +static bool opt4060_readable_reg(struct device *dev, unsigned int reg) +{ + /* Volatile, writable and read-only registers are readable. */ + return opt4060_volatile_reg(dev, reg) || opt4060_writable_reg(dev, reg) || + opt4060_readonly_reg(dev, reg); +} + +static const struct regmap_config opt4060_regmap_config = { + .name = "opt4060", + .reg_bits = 8, + .val_bits = 16, + .cache_type = REGCACHE_RBTREE, + .max_register = OPT4060_DEVICE_ID, + .readable_reg = opt4060_readable_reg, + .writeable_reg = opt4060_writable_reg, + .volatile_reg = opt4060_volatile_reg, + .val_format_endian = REGMAP_ENDIAN_BIG, +}; + +static const struct iio_trigger_ops opt4060_trigger_ops = { + .set_trigger_state = opt4060_trigger_set_state, +}; + +static irqreturn_t opt4060_trigger_handler(int irq, void *p) +{ + struct iio_poll_func *pf = p; + struct iio_dev *idev = pf->indio_dev; + struct opt4060_chip *chip = iio_priv(idev); + struct { + u32 chan[OPT4060_NUM_CHANS]; + aligned_s64 ts; + } raw; + int i = 0; + int chan, ret; + + /* If the trigger is not from this driver, a new sample is needed.*/ + if (iio_trigger_validate_own_device(idev->trig, idev)) + opt4060_trigger_new_samples(idev); + + memset(&raw, 0, sizeof(raw)); + + iio_for_each_active_channel(idev, chan) { + if (chan == OPT4060_ILLUM) + ret = opt4060_calc_illuminance(chip, &raw.chan[i++]); + else + ret = opt4060_read_raw_value(chip, + idev->channels[chan].address, + &raw.chan[i++]); + if (ret) { + dev_err(chip->dev, "Reading channel data failed\n"); + goto err_read; + } + } + + iio_push_to_buffers_with_timestamp(idev, &raw, pf->timestamp); +err_read: + iio_trigger_notify_done(idev->trig); + return IRQ_HANDLED; +} + +static irqreturn_t opt4060_irq_thread(int irq, void *private) +{ + struct iio_dev *idev = private; + struct opt4060_chip *chip = iio_priv(idev); + int ret, dummy; + unsigned int int_res; + + ret = regmap_read(chip->regmap, OPT4060_RES_CTRL, &int_res); + if (ret < 0) { + dev_err(chip->dev, "Failed to read interrupt reasons.\n"); + return IRQ_NONE; + } + + /* Read OPT4060_CTRL to clear interrupt */ + ret = regmap_read(chip->regmap, OPT4060_CTRL, &dummy); + if (ret < 0) { + dev_err(chip->dev, "Failed to clear interrupt\n"); + return IRQ_NONE; + } + + /* Handle events */ + if (int_res & (OPT4060_RES_CTRL_FLAG_H | OPT4060_RES_CTRL_FLAG_L)) { + u64 code; + int chan = 0; + + ret = opt4060_get_channel_sel(chip, &chan); + if (ret) { + dev_err(chip->dev, "Failed to read threshold channel.\n"); + return IRQ_NONE; + } + + /* Check if the interrupt is from the lower threshold */ + if (int_res & OPT4060_RES_CTRL_FLAG_L) { + code = IIO_MOD_EVENT_CODE(IIO_INTENSITY, + chan, + idev->channels[chan].channel2, + IIO_EV_TYPE_THRESH, + IIO_EV_DIR_FALLING); + iio_push_event(idev, code, iio_get_time_ns(idev)); + } + /* Check if the interrupt is from the upper threshold */ + if (int_res & OPT4060_RES_CTRL_FLAG_H) { + code = IIO_MOD_EVENT_CODE(IIO_INTENSITY, + chan, + idev->channels[chan].channel2, + IIO_EV_TYPE_THRESH, + IIO_EV_DIR_RISING); + iio_push_event(idev, code, iio_get_time_ns(idev)); + } + } + + /* Handle conversion ready */ + if (int_res & OPT4060_RES_CTRL_CONV_READY) { + /* Signal completion for potentially waiting reads */ + complete(&chip->completion); + + /* Handle data ready triggers */ + if (iio_buffer_enabled(idev)) + iio_trigger_poll_nested(chip->trig); + } + return IRQ_HANDLED; +} + +static int opt4060_setup_buffer(struct opt4060_chip *chip, struct iio_dev *idev) +{ + int ret; + + ret = devm_iio_triggered_buffer_setup(chip->dev, idev, + &iio_pollfunc_store_time, + opt4060_trigger_handler, NULL); + if (ret) + return dev_err_probe(chip->dev, ret, + "Buffer setup failed.\n"); + return ret; +} + +static int opt4060_setup_trigger(struct opt4060_chip *chip, struct iio_dev *idev) +{ + struct iio_trigger *data_trigger; + char *name; + int ret; + + data_trigger = devm_iio_trigger_alloc(chip->dev, "%s-data-ready-dev%d", + idev->name, iio_device_id(idev)); + if (!data_trigger) + return -ENOMEM; + + /* + * The data trigger allows for sample capture on each new conversion + * ready interrupt. + */ + chip->trig = data_trigger; + data_trigger->ops = &opt4060_trigger_ops; + iio_trigger_set_drvdata(data_trigger, idev); + ret = devm_iio_trigger_register(chip->dev, data_trigger); + if (ret) + return dev_err_probe(chip->dev, ret, + "Data ready trigger registration failed\n"); + + name = devm_kasprintf(chip->dev, GFP_KERNEL, "%s-opt4060", + dev_name(chip->dev)); + if (!name) + return dev_err_probe(chip->dev, -ENOMEM, "Failed to alloc chip name\n"); + + ret = devm_request_threaded_irq(chip->dev, chip->irq, NULL, opt4060_irq_thread, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + name, idev); + if (ret) + return dev_err_probe(chip->dev, ret, "Could not request IRQ\n"); + + init_completion(&chip->completion); + + ret = devm_mutex_init(chip->dev, &chip->irq_setting_lock); + if (ret) + return ret; + + ret = devm_mutex_init(chip->dev, &chip->event_enabling_lock); + if (ret) + return ret; + + ret = regmap_write_bits(chip->regmap, OPT4060_INT_CTRL, + OPT4060_INT_CTRL_OUTPUT, + OPT4060_INT_CTRL_OUTPUT); + if (ret) + return dev_err_probe(chip->dev, ret, + "Failed to set interrupt as output\n"); + + return 0; +} + +static int opt4060_probe(struct i2c_client *client) +{ + struct device *dev = &client->dev; + struct opt4060_chip *chip; + struct iio_dev *indio_dev; + int ret; + unsigned int regval, dev_id; + + indio_dev = devm_iio_device_alloc(dev, sizeof(*chip)); + if (!indio_dev) + return -ENOMEM; + + chip = iio_priv(indio_dev); + + ret = devm_regulator_get_enable(dev, "vdd"); + if (ret) + return dev_err_probe(dev, ret, "Failed to enable vdd supply\n"); + + chip->regmap = devm_regmap_init_i2c(client, &opt4060_regmap_config); + if (IS_ERR(chip->regmap)) + return dev_err_probe(dev, PTR_ERR(chip->regmap), + "regmap initialization failed\n"); + + chip->dev = dev; + chip->irq = client->irq; + + ret = regmap_reinit_cache(chip->regmap, &opt4060_regmap_config); + if (ret) + return dev_err_probe(dev, ret, + "failed to reinit regmap cache\n"); + + ret = regmap_read(chip->regmap, OPT4060_DEVICE_ID, ®val); + if (ret < 0) + return dev_err_probe(dev, ret, + "Failed to read the device ID register\n"); + + dev_id = FIELD_GET(OPT4060_DEVICE_ID_MASK, regval); + if (dev_id != OPT4060_DEVICE_ID_VAL) + dev_info(dev, "Device ID: %#04x unknown\n", dev_id); + + if (chip->irq) { + indio_dev->info = &opt4060_info; + indio_dev->channels = opt4060_channels; + indio_dev->num_channels = ARRAY_SIZE(opt4060_channels); + } else { + indio_dev->info = &opt4060_info_no_irq; + indio_dev->channels = opt4060_channels_no_events; + indio_dev->num_channels = ARRAY_SIZE(opt4060_channels_no_events); + } + indio_dev->modes = INDIO_DIRECT_MODE; + indio_dev->name = "opt4060"; + + ret = opt4060_load_defaults(chip); + if (ret < 0) + return dev_err_probe(dev, ret, + "Failed to set sensor defaults\n"); + + ret = devm_add_action_or_reset(dev, opt4060_chip_off_action, chip); + if (ret < 0) + return dev_err_probe(dev, ret, + "Failed to setup power off action\n"); + + ret = opt4060_setup_buffer(chip, indio_dev); + if (ret) + return ret; + + if (chip->irq) { + ret = opt4060_setup_trigger(chip, indio_dev); + if (ret) + return ret; + } + + return devm_iio_device_register(dev, indio_dev); +} + +static const struct i2c_device_id opt4060_id[] = { + { "opt4060", }, + { } +}; +MODULE_DEVICE_TABLE(i2c, opt4060_id); + +static const struct of_device_id opt4060_of_match[] = { + { .compatible = "ti,opt4060" }, + { } +}; +MODULE_DEVICE_TABLE(of, opt4060_of_match); + +static struct i2c_driver opt4060_driver = { + .driver = { + .name = "opt4060", + .of_match_table = opt4060_of_match, + }, + .probe = opt4060_probe, + .id_table = opt4060_id, +}; +module_i2c_driver(opt4060_driver); + +MODULE_AUTHOR("Per-Daniel Olsson "); +MODULE_DESCRIPTION("Texas Instruments OPT4060 RGBW color sensor driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/iio/light/rohm-bu27008.c b/drivers/iio/light/rohm-bu27008.c deleted file mode 100644 index fa35dd32700c..000000000000 --- a/drivers/iio/light/rohm-bu27008.c +++ /dev/null @@ -1,1635 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * ROHM Colour Sensor driver for - * - BU27008 RGBC sensor - * - BU27010 RGBC + Flickering sensor - * - * Copyright (c) 2023, ROHM Semiconductor. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -/* - * A word about register address and mask definitions. - * - * At a quick glance to the data-sheet register tables, the BU27010 has all the - * registers that the BU27008 has. On top of that the BU27010 adds couple of new - * ones. - * - * So, all definitions BU27008_REG_* are there also for BU27010 but none of the - * BU27010_REG_* are present on BU27008. This makes sense as BU27010 just adds - * some features (Flicker FIFO, more power control) on top of the BU27008. - * - * Unfortunately, some of the wheel has been re-invented. Even though the names - * of the registers have stayed the same, pretty much all of the functionality - * provided by the registers has changed place. Contents of all MODE_CONTROL - * registers on BU27008 and BU27010 are different. - * - * Chip-specific mapping from register addresses/bits to functionality is done - * in bu27_chip_data structures. - */ -#define BU27008_REG_SYSTEM_CONTROL 0x40 -#define BU27008_MASK_SW_RESET BIT(7) -#define BU27008_MASK_PART_ID GENMASK(5, 0) -#define BU27008_ID 0x1a -#define BU27008_REG_MODE_CONTROL1 0x41 -#define BU27008_MASK_MEAS_MODE GENMASK(2, 0) -#define BU27008_MASK_CHAN_SEL GENMASK(3, 2) - -#define BU27008_REG_MODE_CONTROL2 0x42 -#define BU27008_MASK_RGBC_GAIN GENMASK(7, 3) -#define BU27008_MASK_IR_GAIN_LO GENMASK(2, 0) -#define BU27008_SHIFT_IR_GAIN 3 - -#define BU27008_REG_MODE_CONTROL3 0x43 -#define BU27008_MASK_VALID BIT(7) -#define BU27008_MASK_INT_EN BIT(1) -#define BU27008_INT_EN BU27008_MASK_INT_EN -#define BU27008_INT_DIS 0 -#define BU27008_MASK_MEAS_EN BIT(0) -#define BU27008_MEAS_EN BIT(0) -#define BU27008_MEAS_DIS 0 - -#define BU27008_REG_DATA0_LO 0x50 -#define BU27008_REG_DATA1_LO 0x52 -#define BU27008_REG_DATA2_LO 0x54 -#define BU27008_REG_DATA3_LO 0x56 -#define BU27008_REG_DATA3_HI 0x57 -#define BU27008_REG_MANUFACTURER_ID 0x92 -#define BU27008_REG_MAX BU27008_REG_MANUFACTURER_ID - -/* BU27010 specific definitions */ - -#define BU27010_MASK_SW_RESET BIT(7) -#define BU27010_ID 0x1b -#define BU27010_REG_POWER 0x3e -#define BU27010_MASK_POWER BIT(0) - -#define BU27010_REG_RESET 0x3f -#define BU27010_MASK_RESET BIT(0) -#define BU27010_RESET_RELEASE BU27010_MASK_RESET - -#define BU27010_MASK_MEAS_EN BIT(1) - -#define BU27010_MASK_CHAN_SEL GENMASK(7, 6) -#define BU27010_MASK_MEAS_MODE GENMASK(5, 4) -#define BU27010_MASK_RGBC_GAIN GENMASK(3, 0) - -#define BU27010_MASK_DATA3_GAIN GENMASK(7, 6) -#define BU27010_MASK_DATA2_GAIN GENMASK(5, 4) -#define BU27010_MASK_DATA1_GAIN GENMASK(3, 2) -#define BU27010_MASK_DATA0_GAIN GENMASK(1, 0) - -#define BU27010_MASK_FLC_MODE BIT(7) -#define BU27010_MASK_FLC_GAIN GENMASK(4, 0) - -#define BU27010_REG_MODE_CONTROL4 0x44 -/* If flicker is ever to be supported the IRQ must be handled as a field */ -#define BU27010_IRQ_DIS_ALL GENMASK(1, 0) -#define BU27010_DRDY_EN BIT(0) -#define BU27010_MASK_INT_SEL GENMASK(1, 0) - -#define BU27010_REG_MODE_CONTROL5 0x45 -#define BU27010_MASK_RGB_VALID BIT(7) -#define BU27010_MASK_FLC_VALID BIT(6) -#define BU27010_MASK_WAIT_EN BIT(3) -#define BU27010_MASK_FIFO_EN BIT(2) -#define BU27010_MASK_RGB_EN BIT(1) -#define BU27010_MASK_FLC_EN BIT(0) - -#define BU27010_REG_DATA_FLICKER_LO 0x56 -#define BU27010_MASK_DATA_FLICKER_HI GENMASK(2, 0) -#define BU27010_REG_FLICKER_COUNT 0x5a -#define BU27010_REG_FIFO_LEVEL_LO 0x5b -#define BU27010_MASK_FIFO_LEVEL_HI BIT(0) -#define BU27010_REG_FIFO_DATA_LO 0x5d -#define BU27010_REG_FIFO_DATA_HI 0x5e -#define BU27010_MASK_FIFO_DATA_HI GENMASK(2, 0) -#define BU27010_REG_MANUFACTURER_ID 0x92 -#define BU27010_REG_MAX BU27010_REG_MANUFACTURER_ID - -/** - * enum bu27008_chan_type - BU27008 channel types - * @BU27008_RED: Red channel. Always via data0. - * @BU27008_GREEN: Green channel. Always via data1. - * @BU27008_BLUE: Blue channel. Via data2 (when used). - * @BU27008_CLEAR: Clear channel. Via data2 or data3 (when used). - * @BU27008_IR: IR channel. Via data3 (when used). - * @BU27008_LUX: Illuminance channel, computed using RGB and IR. - * @BU27008_NUM_CHANS: Number of channel types. - */ -enum bu27008_chan_type { - BU27008_RED, - BU27008_GREEN, - BU27008_BLUE, - BU27008_CLEAR, - BU27008_IR, - BU27008_LUX, - BU27008_NUM_CHANS -}; - -/** - * enum bu27008_chan - BU27008 physical data channel - * @BU27008_DATA0: Always red. - * @BU27008_DATA1: Always green. - * @BU27008_DATA2: Blue or clear. - * @BU27008_DATA3: IR or clear. - * @BU27008_NUM_HW_CHANS: Number of physical channels - */ -enum bu27008_chan { - BU27008_DATA0, - BU27008_DATA1, - BU27008_DATA2, - BU27008_DATA3, - BU27008_NUM_HW_CHANS -}; - -/* We can always measure red and green at same time */ -#define ALWAYS_SCANNABLE (BIT(BU27008_RED) | BIT(BU27008_GREEN)) - -/* We use these data channel configs. Ensure scan_masks below follow them too */ -#define BU27008_BLUE2_CLEAR3 0x0 /* buffer is R, G, B, C */ -#define BU27008_CLEAR2_IR3 0x1 /* buffer is R, G, C, IR */ -#define BU27008_BLUE2_IR3 0x2 /* buffer is R, G, B, IR */ - -static const unsigned long bu27008_scan_masks[] = { - /* buffer is R, G, B, C */ - ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_CLEAR), - /* buffer is R, G, C, IR */ - ALWAYS_SCANNABLE | BIT(BU27008_CLEAR) | BIT(BU27008_IR), - /* buffer is R, G, B, IR */ - ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_IR), - /* buffer is R, G, B, IR, LUX */ - ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_IR) | BIT(BU27008_LUX), - 0 -}; - -/* - * Available scales with gain 1x - 1024x, timings 55, 100, 200, 400 mS - * Time impacts to gain: 1x, 2x, 4x, 8x. - * - * => Max total gain is HWGAIN * gain by integration time (8 * 1024) = 8192 - * - * Max amplification is (HWGAIN * MAX integration-time multiplier) 1024 * 8 - * = 8192. With NANO scale we get rid of accuracy loss when we start with the - * scale 16.0 for HWGAIN1, INT-TIME 55 mS. This way the nano scale for MAX - * total gain 8192 will be 1953125 - */ -#define BU27008_SCALE_1X 16 - -/* - * On BU27010 available scales with gain 1x - 4096x, - * timings 55, 100, 200, 400 mS. Time impacts to gain: 1x, 2x, 4x, 8x. - * - * => Max total gain is HWGAIN * gain by integration time (8 * 4096) - * - * Using NANO precision for scale we must use scale 64x corresponding gain 1x - * to avoid precision loss. - */ -#define BU27010_SCALE_1X 64 - -/* See the data sheet for the "Gain Setting" table */ -#define BU27008_GSEL_1X 0x00 -#define BU27008_GSEL_4X 0x08 -#define BU27008_GSEL_8X 0x09 -#define BU27008_GSEL_16X 0x0a -#define BU27008_GSEL_32X 0x0b -#define BU27008_GSEL_64X 0x0c -#define BU27008_GSEL_256X 0x18 -#define BU27008_GSEL_512X 0x19 -#define BU27008_GSEL_1024X 0x1a - -static const struct iio_gain_sel_pair bu27008_gains[] = { - GAIN_SCALE_GAIN(1, BU27008_GSEL_1X), - GAIN_SCALE_GAIN(4, BU27008_GSEL_4X), - GAIN_SCALE_GAIN(8, BU27008_GSEL_8X), - GAIN_SCALE_GAIN(16, BU27008_GSEL_16X), - GAIN_SCALE_GAIN(32, BU27008_GSEL_32X), - GAIN_SCALE_GAIN(64, BU27008_GSEL_64X), - GAIN_SCALE_GAIN(256, BU27008_GSEL_256X), - GAIN_SCALE_GAIN(512, BU27008_GSEL_512X), - GAIN_SCALE_GAIN(1024, BU27008_GSEL_1024X), -}; - -static const struct iio_gain_sel_pair bu27008_gains_ir[] = { - GAIN_SCALE_GAIN(2, BU27008_GSEL_1X), - GAIN_SCALE_GAIN(4, BU27008_GSEL_4X), - GAIN_SCALE_GAIN(8, BU27008_GSEL_8X), - GAIN_SCALE_GAIN(16, BU27008_GSEL_16X), - GAIN_SCALE_GAIN(32, BU27008_GSEL_32X), - GAIN_SCALE_GAIN(64, BU27008_GSEL_64X), - GAIN_SCALE_GAIN(256, BU27008_GSEL_256X), - GAIN_SCALE_GAIN(512, BU27008_GSEL_512X), - GAIN_SCALE_GAIN(1024, BU27008_GSEL_1024X), -}; - -#define BU27010_GSEL_1X 0x00 /* 000000 */ -#define BU27010_GSEL_4X 0x08 /* 001000 */ -#define BU27010_GSEL_16X 0x09 /* 001001 */ -#define BU27010_GSEL_64X 0x0e /* 001110 */ -#define BU27010_GSEL_256X 0x1e /* 011110 */ -#define BU27010_GSEL_1024X 0x2e /* 101110 */ -#define BU27010_GSEL_4096X 0x3f /* 111111 */ - -static const struct iio_gain_sel_pair bu27010_gains[] = { - GAIN_SCALE_GAIN(1, BU27010_GSEL_1X), - GAIN_SCALE_GAIN(4, BU27010_GSEL_4X), - GAIN_SCALE_GAIN(16, BU27010_GSEL_16X), - GAIN_SCALE_GAIN(64, BU27010_GSEL_64X), - GAIN_SCALE_GAIN(256, BU27010_GSEL_256X), - GAIN_SCALE_GAIN(1024, BU27010_GSEL_1024X), - GAIN_SCALE_GAIN(4096, BU27010_GSEL_4096X), -}; - -static const struct iio_gain_sel_pair bu27010_gains_ir[] = { - GAIN_SCALE_GAIN(2, BU27010_GSEL_1X), - GAIN_SCALE_GAIN(4, BU27010_GSEL_4X), - GAIN_SCALE_GAIN(16, BU27010_GSEL_16X), - GAIN_SCALE_GAIN(64, BU27010_GSEL_64X), - GAIN_SCALE_GAIN(256, BU27010_GSEL_256X), - GAIN_SCALE_GAIN(1024, BU27010_GSEL_1024X), - GAIN_SCALE_GAIN(4096, BU27010_GSEL_4096X), -}; - -#define BU27008_MEAS_MODE_100MS 0x00 -#define BU27008_MEAS_MODE_55MS 0x01 -#define BU27008_MEAS_MODE_200MS 0x02 -#define BU27008_MEAS_MODE_400MS 0x04 - -#define BU27010_MEAS_MODE_100MS 0x00 -#define BU27010_MEAS_MODE_55MS 0x03 -#define BU27010_MEAS_MODE_200MS 0x01 -#define BU27010_MEAS_MODE_400MS 0x02 - -#define BU27008_MEAS_TIME_MAX_MS 400 - -static const struct iio_itime_sel_mul bu27008_itimes[] = { - GAIN_SCALE_ITIME_US(400000, BU27008_MEAS_MODE_400MS, 8), - GAIN_SCALE_ITIME_US(200000, BU27008_MEAS_MODE_200MS, 4), - GAIN_SCALE_ITIME_US(100000, BU27008_MEAS_MODE_100MS, 2), - GAIN_SCALE_ITIME_US(55000, BU27008_MEAS_MODE_55MS, 1), -}; - -static const struct iio_itime_sel_mul bu27010_itimes[] = { - GAIN_SCALE_ITIME_US(400000, BU27010_MEAS_MODE_400MS, 8), - GAIN_SCALE_ITIME_US(200000, BU27010_MEAS_MODE_200MS, 4), - GAIN_SCALE_ITIME_US(100000, BU27010_MEAS_MODE_100MS, 2), - GAIN_SCALE_ITIME_US(55000, BU27010_MEAS_MODE_55MS, 1), -}; - -/* - * All the RGBC channels share the same gain. - * IR gain can be fine-tuned from the gain set for the RGBC by 2 bit, but this - * would yield quite complex gain setting. Especially since not all bit - * compinations are supported. And in any case setting GAIN for RGBC will - * always also change the IR-gain. - * - * On top of this, the selector '0' which corresponds to hw-gain 1X on RGBC, - * corresponds to gain 2X on IR. Rest of the selctors correspond to same gains - * though. This, however, makes it not possible to use shared gain for all - * RGBC and IR settings even though they are all changed at the one go. - */ -#define BU27008_CHAN(color, data, separate_avail) \ -{ \ - .type = IIO_INTENSITY, \ - .modified = 1, \ - .channel2 = IIO_MOD_LIGHT_##color, \ - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ - BIT(IIO_CHAN_INFO_SCALE), \ - .info_mask_separate_available = (separate_avail), \ - .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME), \ - .info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME), \ - .address = BU27008_REG_##data##_LO, \ - .scan_index = BU27008_##color, \ - .scan_type = { \ - .sign = 'u', \ - .realbits = 16, \ - .storagebits = 16, \ - .endianness = IIO_LE, \ - }, \ -} - -/* For raw reads we always configure DATA3 for CLEAR */ -static const struct iio_chan_spec bu27008_channels[] = { - BU27008_CHAN(RED, DATA0, BIT(IIO_CHAN_INFO_SCALE)), - BU27008_CHAN(GREEN, DATA1, BIT(IIO_CHAN_INFO_SCALE)), - BU27008_CHAN(BLUE, DATA2, BIT(IIO_CHAN_INFO_SCALE)), - BU27008_CHAN(CLEAR, DATA2, BIT(IIO_CHAN_INFO_SCALE)), - /* - * We don't allow setting scale for IR (because of shared gain bits). - * Hence we don't advertise available ones either. - */ - BU27008_CHAN(IR, DATA3, 0), - { - .type = IIO_LIGHT, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE), - .channel = BU27008_LUX, - .scan_index = BU27008_LUX, - .scan_type = { - .sign = 'u', - .realbits = 64, - .storagebits = 64, - .endianness = IIO_CPU, - }, - }, - IIO_CHAN_SOFT_TIMESTAMP(BU27008_NUM_CHANS), -}; - -struct bu27008_data; - -struct bu27_chip_data { - const char *name; - int (*chip_init)(struct bu27008_data *data); - int (*get_gain_sel)(struct bu27008_data *data, int *sel); - int (*write_gain_sel)(struct bu27008_data *data, int sel); - const struct regmap_config *regmap_cfg; - const struct iio_gain_sel_pair *gains; - const struct iio_gain_sel_pair *gains_ir; - const struct iio_itime_sel_mul *itimes; - int num_gains; - int num_gains_ir; - int num_itimes; - int scale1x; - - int drdy_en_reg; - int drdy_en_mask; - int meas_en_reg; - int meas_en_mask; - int valid_reg; - int chan_sel_reg; - int chan_sel_mask; - int int_time_mask; - u8 part_id; -}; - -struct bu27008_data { - const struct bu27_chip_data *cd; - struct regmap *regmap; - struct iio_trigger *trig; - struct device *dev; - struct iio_gts gts; - struct iio_gts gts_ir; - int irq; - - /* - * Prevent changing gain/time config when scale is read/written. - * Similarly, protect the integration_time read/change sequence. - * Prevent changing gain/time when data is read. - */ - struct mutex mutex; -}; - -static const struct regmap_range bu27008_volatile_ranges[] = { - { - .range_min = BU27008_REG_SYSTEM_CONTROL, /* SWRESET */ - .range_max = BU27008_REG_SYSTEM_CONTROL, - }, { - .range_min = BU27008_REG_MODE_CONTROL3, /* VALID */ - .range_max = BU27008_REG_MODE_CONTROL3, - }, { - .range_min = BU27008_REG_DATA0_LO, /* DATA */ - .range_max = BU27008_REG_DATA3_HI, - }, -}; - -static const struct regmap_range bu27010_volatile_ranges[] = { - { - .range_min = BU27010_REG_RESET, /* RSTB */ - .range_max = BU27008_REG_SYSTEM_CONTROL, /* RESET */ - }, { - .range_min = BU27010_REG_MODE_CONTROL5, /* VALID bits */ - .range_max = BU27010_REG_MODE_CONTROL5, - }, { - .range_min = BU27008_REG_DATA0_LO, - .range_max = BU27010_REG_FIFO_DATA_HI, - }, -}; - -static const struct regmap_access_table bu27008_volatile_regs = { - .yes_ranges = &bu27008_volatile_ranges[0], - .n_yes_ranges = ARRAY_SIZE(bu27008_volatile_ranges), -}; - -static const struct regmap_access_table bu27010_volatile_regs = { - .yes_ranges = &bu27010_volatile_ranges[0], - .n_yes_ranges = ARRAY_SIZE(bu27010_volatile_ranges), -}; - -static const struct regmap_range bu27008_read_only_ranges[] = { - { - .range_min = BU27008_REG_DATA0_LO, - .range_max = BU27008_REG_DATA3_HI, - }, { - .range_min = BU27008_REG_MANUFACTURER_ID, - .range_max = BU27008_REG_MANUFACTURER_ID, - }, -}; - -static const struct regmap_range bu27010_read_only_ranges[] = { - { - .range_min = BU27008_REG_DATA0_LO, - .range_max = BU27010_REG_FIFO_DATA_HI, - }, { - .range_min = BU27010_REG_MANUFACTURER_ID, - .range_max = BU27010_REG_MANUFACTURER_ID, - } -}; - -static const struct regmap_access_table bu27008_ro_regs = { - .no_ranges = &bu27008_read_only_ranges[0], - .n_no_ranges = ARRAY_SIZE(bu27008_read_only_ranges), -}; - -static const struct regmap_access_table bu27010_ro_regs = { - .no_ranges = &bu27010_read_only_ranges[0], - .n_no_ranges = ARRAY_SIZE(bu27010_read_only_ranges), -}; - -static const struct regmap_config bu27008_regmap = { - .reg_bits = 8, - .val_bits = 8, - .max_register = BU27008_REG_MAX, - .cache_type = REGCACHE_RBTREE, - .volatile_table = &bu27008_volatile_regs, - .wr_table = &bu27008_ro_regs, - /* - * All register writes are serialized by the mutex which protects the - * scale setting/getting. This is needed because scale is combined by - * gain and integration time settings and we need to ensure those are - * not read / written when scale is being computed. - * - * As a result of this serializing, we don't need regmap locking. Note, - * this is not true if we add any configurations which are not - * serialized by the mutex and which may need for example a protected - * read-modify-write cycle (eg. regmap_update_bits()). Please, revise - * this when adding features to the driver. - */ - .disable_locking = true, -}; - -static const struct regmap_config bu27010_regmap = { - .reg_bits = 8, - .val_bits = 8, - - .max_register = BU27010_REG_MAX, - .cache_type = REGCACHE_RBTREE, - .volatile_table = &bu27010_volatile_regs, - .wr_table = &bu27010_ro_regs, - .disable_locking = true, -}; - -static int bu27008_write_gain_sel(struct bu27008_data *data, int sel) -{ - int regval; - - regval = FIELD_PREP(BU27008_MASK_RGBC_GAIN, sel); - - /* - * We do always set also the LOW bits of IR-gain because othervice we - * would risk resulting an invalid GAIN register value. - * - * We could allow setting separate gains for RGBC and IR when the - * values were such that HW could support both gain settings. - * Eg, when the shared bits were same for both gain values. - * - * This, however, has a negligible benefit compared to the increased - * software complexity when we would need to go through the gains - * for both channels separately when the integration time changes. - * This would end up with nasty logic for computing gain values for - * both channels - and rejecting them if shared bits changed. - * - * We should then build the logic by guessing what a user prefers. - * RGBC or IR gains correctly set while other jumps to odd value? - * Maybe look-up a value where both gains are somehow optimized - * . Or maybe user would - * expect us to reject changes when optimal gains can't be set to both - * channels w/given integration time. At best that would result - * solution that works well for a very specific subset of - * configurations but causes unexpected corner-cases. - * - * So, we keep it simple. Always set same selector to IR and RGBC. - * We disallow setting IR (as I expect that most of the users are - * interested in RGBC). This way we can show the user that the scales - * for RGBC and IR channels are different (1X Vs 2X with sel 0) while - * still keeping the operation deterministic. - */ - regval |= FIELD_PREP(BU27008_MASK_IR_GAIN_LO, sel); - - return regmap_update_bits(data->regmap, BU27008_REG_MODE_CONTROL2, - BU27008_MASK_RGBC_GAIN, regval); -} - -static int bu27010_write_gain_sel(struct bu27008_data *data, int sel) -{ - unsigned int regval; - int ret, chan_selector; - - /* - * Gain 'selector' is composed of two registers. Selector is 6bit value, - * 4 high bits being the RGBC gain fieild in MODE_CONTROL1 register and - * two low bits being the channel specific gain in MODE_CONTROL2. - * - * Let's take the 4 high bits of whole 6 bit selector, and prepare - * the MODE_CONTROL1 value (RGBC gain part). - */ - regval = FIELD_PREP(BU27010_MASK_RGBC_GAIN, (sel >> 2)); - - ret = regmap_update_bits(data->regmap, BU27008_REG_MODE_CONTROL1, - BU27010_MASK_RGBC_GAIN, regval); - if (ret) - return ret; - - /* - * Two low two bits of the selector must be written for all 4 - * channels in the MODE_CONTROL2 register. Copy these two bits for - * all channels. - */ - chan_selector = sel & GENMASK(1, 0); - - regval = FIELD_PREP(BU27010_MASK_DATA0_GAIN, chan_selector); - regval |= FIELD_PREP(BU27010_MASK_DATA1_GAIN, chan_selector); - regval |= FIELD_PREP(BU27010_MASK_DATA2_GAIN, chan_selector); - regval |= FIELD_PREP(BU27010_MASK_DATA3_GAIN, chan_selector); - - return regmap_write(data->regmap, BU27008_REG_MODE_CONTROL2, regval); -} - -static int bu27008_get_gain_sel(struct bu27008_data *data, int *sel) -{ - int ret; - - /* - * If we always "lock" the gain selectors for all channels to prevent - * unsupported configs, then it does not matter which channel is used - * we can just return selector from any of them. - * - * This, however is not true if we decide to support only 4X and 16X - * and then individual gains for channels. Currently this is not the - * case. - * - * If we some day decide to support individual gains, then we need to - * have channel information here. - */ - - ret = regmap_read(data->regmap, BU27008_REG_MODE_CONTROL2, sel); - if (ret) - return ret; - - *sel = FIELD_GET(BU27008_MASK_RGBC_GAIN, *sel); - - return 0; -} - -static int bu27010_get_gain_sel(struct bu27008_data *data, int *sel) -{ - int ret, tmp; - - /* - * We always "lock" the gain selectors for all channels to prevent - * unsupported configs. It does not matter which channel is used - * we can just return selector from any of them. - * - * Read the channel0 gain. - */ - ret = regmap_read(data->regmap, BU27008_REG_MODE_CONTROL2, sel); - if (ret) - return ret; - - *sel = FIELD_GET(BU27010_MASK_DATA0_GAIN, *sel); - - /* Read the shared gain */ - ret = regmap_read(data->regmap, BU27008_REG_MODE_CONTROL1, &tmp); - if (ret) - return ret; - - /* - * The gain selector is made as a combination of common RGBC gain and - * the channel specific gain. The channel specific gain forms the low - * bits of selector and RGBC gain is appended right after it. - * - * Compose the selector from channel0 gain and shared RGBC gain. - */ - *sel |= FIELD_GET(BU27010_MASK_RGBC_GAIN, tmp) << fls(BU27010_MASK_DATA0_GAIN); - - return ret; -} - -static int bu27008_chip_init(struct bu27008_data *data) -{ - int ret; - - ret = regmap_write_bits(data->regmap, BU27008_REG_SYSTEM_CONTROL, - BU27008_MASK_SW_RESET, BU27008_MASK_SW_RESET); - if (ret) - return dev_err_probe(data->dev, ret, "Sensor reset failed\n"); - - /* - * The data-sheet does not tell how long performing the IC reset takes. - * However, the data-sheet says the minimum time it takes the IC to be - * able to take inputs after power is applied, is 100 uS. I'd assume - * > 1 mS is enough. - */ - msleep(1); - - ret = regmap_reinit_cache(data->regmap, data->cd->regmap_cfg); - if (ret) - dev_err(data->dev, "Failed to reinit reg cache\n"); - - return ret; -} - -static int bu27010_chip_init(struct bu27008_data *data) -{ - int ret; - - ret = regmap_write_bits(data->regmap, BU27008_REG_SYSTEM_CONTROL, - BU27010_MASK_SW_RESET, BU27010_MASK_SW_RESET); - if (ret) - return dev_err_probe(data->dev, ret, "Sensor reset failed\n"); - - msleep(1); - - /* Power ON*/ - ret = regmap_write_bits(data->regmap, BU27010_REG_POWER, - BU27010_MASK_POWER, BU27010_MASK_POWER); - if (ret) - return dev_err_probe(data->dev, ret, "Sensor power-on failed\n"); - - msleep(1); - - /* Release blocks from reset */ - ret = regmap_write_bits(data->regmap, BU27010_REG_RESET, - BU27010_MASK_RESET, BU27010_RESET_RELEASE); - if (ret) - return dev_err_probe(data->dev, ret, "Sensor powering failed\n"); - - msleep(1); - - /* - * The IRQ enabling on BU27010 is done in a peculiar way. The IRQ - * enabling is not a bit mask where individual IRQs could be enabled but - * a field which values are: - * 00 => IRQs disabled - * 01 => Data-ready (RGBC/IR) - * 10 => Data-ready (flicker) - * 11 => Flicker FIFO - * - * So, only one IRQ can be enabled at a time and enabling for example - * flicker FIFO would automagically disable data-ready IRQ. - * - * Currently the driver does not support the flicker. Hence, we can - * just treat the RGBC data-ready as single bit which can be enabled / - * disabled. This works for as long as the second bit in the field - * stays zero. Here we ensure it gets zeroed. - */ - return regmap_clear_bits(data->regmap, BU27010_REG_MODE_CONTROL4, - BU27010_IRQ_DIS_ALL); -} - -static const struct bu27_chip_data bu27010_chip = { - .name = "bu27010", - .chip_init = bu27010_chip_init, - .get_gain_sel = bu27010_get_gain_sel, - .write_gain_sel = bu27010_write_gain_sel, - .regmap_cfg = &bu27010_regmap, - .gains = &bu27010_gains[0], - .gains_ir = &bu27010_gains_ir[0], - .itimes = &bu27010_itimes[0], - .num_gains = ARRAY_SIZE(bu27010_gains), - .num_gains_ir = ARRAY_SIZE(bu27010_gains_ir), - .num_itimes = ARRAY_SIZE(bu27010_itimes), - .scale1x = BU27010_SCALE_1X, - .drdy_en_reg = BU27010_REG_MODE_CONTROL4, - .drdy_en_mask = BU27010_DRDY_EN, - .meas_en_reg = BU27010_REG_MODE_CONTROL5, - .meas_en_mask = BU27010_MASK_MEAS_EN, - .valid_reg = BU27010_REG_MODE_CONTROL5, - .chan_sel_reg = BU27008_REG_MODE_CONTROL1, - .chan_sel_mask = BU27010_MASK_CHAN_SEL, - .int_time_mask = BU27010_MASK_MEAS_MODE, - .part_id = BU27010_ID, -}; - -static const struct bu27_chip_data bu27008_chip = { - .name = "bu27008", - .chip_init = bu27008_chip_init, - .get_gain_sel = bu27008_get_gain_sel, - .write_gain_sel = bu27008_write_gain_sel, - .regmap_cfg = &bu27008_regmap, - .gains = &bu27008_gains[0], - .gains_ir = &bu27008_gains_ir[0], - .itimes = &bu27008_itimes[0], - .num_gains = ARRAY_SIZE(bu27008_gains), - .num_gains_ir = ARRAY_SIZE(bu27008_gains_ir), - .num_itimes = ARRAY_SIZE(bu27008_itimes), - .scale1x = BU27008_SCALE_1X, - .drdy_en_reg = BU27008_REG_MODE_CONTROL3, - .drdy_en_mask = BU27008_MASK_INT_EN, - .valid_reg = BU27008_REG_MODE_CONTROL3, - .meas_en_reg = BU27008_REG_MODE_CONTROL3, - .meas_en_mask = BU27008_MASK_MEAS_EN, - .chan_sel_reg = BU27008_REG_MODE_CONTROL3, - .chan_sel_mask = BU27008_MASK_CHAN_SEL, - .int_time_mask = BU27008_MASK_MEAS_MODE, - .part_id = BU27008_ID, -}; - -#define BU27008_MAX_VALID_RESULT_WAIT_US 50000 -#define BU27008_VALID_RESULT_WAIT_QUANTA_US 1000 - -static int bu27008_chan_read_data(struct bu27008_data *data, int reg, int *val) -{ - int ret, valid; - __le16 tmp; - - ret = regmap_read_poll_timeout(data->regmap, data->cd->valid_reg, - valid, (valid & BU27008_MASK_VALID), - BU27008_VALID_RESULT_WAIT_QUANTA_US, - BU27008_MAX_VALID_RESULT_WAIT_US); - if (ret) - return ret; - - ret = regmap_bulk_read(data->regmap, reg, &tmp, sizeof(tmp)); - if (ret) - dev_err(data->dev, "Reading channel data failed\n"); - - *val = le16_to_cpu(tmp); - - return ret; -} - -static int bu27008_get_gain(struct bu27008_data *data, struct iio_gts *gts, int *gain) -{ - int ret, sel; - - ret = data->cd->get_gain_sel(data, &sel); - if (ret) - return ret; - - ret = iio_gts_find_gain_by_sel(gts, sel); - if (ret < 0) { - dev_err(data->dev, "unknown gain value 0x%x\n", sel); - return ret; - } - - *gain = ret; - - return 0; -} - -static int bu27008_set_gain(struct bu27008_data *data, int gain) -{ - int ret; - - ret = iio_gts_find_sel_by_gain(&data->gts, gain); - if (ret < 0) - return ret; - - return data->cd->write_gain_sel(data, ret); -} - -static int bu27008_get_int_time_sel(struct bu27008_data *data, int *sel) -{ - int ret, val; - - ret = regmap_read(data->regmap, BU27008_REG_MODE_CONTROL1, &val); - if (ret) - return ret; - - val &= data->cd->int_time_mask; - val >>= ffs(data->cd->int_time_mask) - 1; - - *sel = val; - - return 0; -} - -static int bu27008_set_int_time_sel(struct bu27008_data *data, int sel) -{ - sel <<= ffs(data->cd->int_time_mask) - 1; - - return regmap_update_bits(data->regmap, BU27008_REG_MODE_CONTROL1, - data->cd->int_time_mask, sel); -} - -static int bu27008_get_int_time_us(struct bu27008_data *data) -{ - int ret, sel; - - ret = bu27008_get_int_time_sel(data, &sel); - if (ret) - return ret; - - return iio_gts_find_int_time_by_sel(&data->gts, sel); -} - -static int _bu27008_get_scale(struct bu27008_data *data, bool ir, int *val, - int *val2) -{ - struct iio_gts *gts; - int gain, ret; - - if (ir) - gts = &data->gts_ir; - else - gts = &data->gts; - - ret = bu27008_get_gain(data, gts, &gain); - if (ret) - return ret; - - ret = bu27008_get_int_time_us(data); - if (ret < 0) - return ret; - - return iio_gts_get_scale(gts, gain, ret, val, val2); -} - -static int bu27008_get_scale(struct bu27008_data *data, bool ir, int *val, - int *val2) -{ - int ret; - - mutex_lock(&data->mutex); - ret = _bu27008_get_scale(data, ir, val, val2); - mutex_unlock(&data->mutex); - - return ret; -} - -static int bu27008_set_int_time(struct bu27008_data *data, int time) -{ - int ret; - - ret = iio_gts_find_sel_by_int_time(&data->gts, time); - if (ret < 0) - return ret; - - return bu27008_set_int_time_sel(data, ret); -} - -/* Try to change the time so that the scale is maintained */ -static int bu27008_try_set_int_time(struct bu27008_data *data, int int_time_new) -{ - int ret, old_time_sel, new_time_sel, old_gain, new_gain; - - mutex_lock(&data->mutex); - - ret = bu27008_get_int_time_sel(data, &old_time_sel); - if (ret < 0) - goto unlock_out; - - if (!iio_gts_valid_time(&data->gts, int_time_new)) { - dev_dbg(data->dev, "Unsupported integration time %u\n", - int_time_new); - - ret = -EINVAL; - goto unlock_out; - } - - /* If we already use requested time, then we're done */ - new_time_sel = iio_gts_find_sel_by_int_time(&data->gts, int_time_new); - if (new_time_sel == old_time_sel) - goto unlock_out; - - ret = bu27008_get_gain(data, &data->gts, &old_gain); - if (ret) - goto unlock_out; - - ret = iio_gts_find_new_gain_sel_by_old_gain_time(&data->gts, old_gain, - old_time_sel, new_time_sel, &new_gain); - if (ret) { - int scale1, scale2; - bool ok; - - _bu27008_get_scale(data, false, &scale1, &scale2); - dev_dbg(data->dev, - "Can't support time %u with current scale %u %u\n", - int_time_new, scale1, scale2); - - if (new_gain < 0) - goto unlock_out; - - /* - * If caller requests for integration time change and we - * can't support the scale - then the caller should be - * prepared to 'pick up the pieces and deal with the - * fact that the scale changed'. - */ - ret = iio_find_closest_gain_low(&data->gts, new_gain, &ok); - if (!ok) - dev_dbg(data->dev, "optimal gain out of range\n"); - - if (ret < 0) { - dev_dbg(data->dev, - "Total gain increase. Risk of saturation"); - ret = iio_gts_get_min_gain(&data->gts); - if (ret < 0) - goto unlock_out; - } - new_gain = ret; - dev_dbg(data->dev, "scale changed, new gain %u\n", new_gain); - } - - ret = bu27008_set_gain(data, new_gain); - if (ret) - goto unlock_out; - - ret = bu27008_set_int_time(data, int_time_new); - -unlock_out: - mutex_unlock(&data->mutex); - - return ret; -} - -static int bu27008_meas_set(struct bu27008_data *data, bool enable) -{ - if (enable) - return regmap_set_bits(data->regmap, data->cd->meas_en_reg, - data->cd->meas_en_mask); - return regmap_clear_bits(data->regmap, data->cd->meas_en_reg, - data->cd->meas_en_mask); -} - -static int bu27008_chan_cfg(struct bu27008_data *data, - struct iio_chan_spec const *chan) -{ - int chan_sel; - - if (chan->scan_index == BU27008_BLUE) - chan_sel = BU27008_BLUE2_CLEAR3; - else - chan_sel = BU27008_CLEAR2_IR3; - - /* - * prepare bitfield for channel sel. The FIELD_PREP works only when - * mask is constant. In our case the mask is assigned based on the - * chip type. Hence the open-coded FIELD_PREP here. We don't bother - * zeroing the irrelevant bits though - update_bits takes care of that. - */ - chan_sel <<= ffs(data->cd->chan_sel_mask) - 1; - - return regmap_update_bits(data->regmap, data->cd->chan_sel_reg, - BU27008_MASK_CHAN_SEL, chan_sel); -} - -static int bu27008_read_one(struct bu27008_data *data, struct iio_dev *idev, - struct iio_chan_spec const *chan, int *val, int *val2) -{ - int ret, int_time; - - ret = bu27008_chan_cfg(data, chan); - if (ret) - return ret; - - ret = bu27008_meas_set(data, true); - if (ret) - return ret; - - ret = bu27008_get_int_time_us(data); - if (ret < 0) - int_time = BU27008_MEAS_TIME_MAX_MS; - else - int_time = ret / USEC_PER_MSEC; - - msleep(int_time); - - ret = bu27008_chan_read_data(data, chan->address, val); - if (!ret) - ret = IIO_VAL_INT; - - if (bu27008_meas_set(data, false)) - dev_warn(data->dev, "measurement disabling failed\n"); - - return ret; -} - -#define BU27008_LUX_DATA_RED 0 -#define BU27008_LUX_DATA_GREEN 1 -#define BU27008_LUX_DATA_BLUE 2 -#define BU27008_LUX_DATA_IR 3 -#define LUX_DATA_SIZE (BU27008_NUM_HW_CHANS * sizeof(__le16)) - -static int bu27008_read_lux_chans(struct bu27008_data *data, unsigned int time, - __le16 *chan_data) -{ - int ret, chan_sel, tmpret, valid; - - chan_sel = BU27008_BLUE2_IR3 << (ffs(data->cd->chan_sel_mask) - 1); - - ret = regmap_update_bits(data->regmap, data->cd->chan_sel_reg, - data->cd->chan_sel_mask, chan_sel); - if (ret) - return ret; - - ret = bu27008_meas_set(data, true); - if (ret) - return ret; - - msleep(time / USEC_PER_MSEC); - - ret = regmap_read_poll_timeout(data->regmap, data->cd->valid_reg, - valid, (valid & BU27008_MASK_VALID), - BU27008_VALID_RESULT_WAIT_QUANTA_US, - BU27008_MAX_VALID_RESULT_WAIT_US); - if (ret) - goto out; - - ret = regmap_bulk_read(data->regmap, BU27008_REG_DATA0_LO, chan_data, - LUX_DATA_SIZE); - if (ret) - goto out; -out: - tmpret = bu27008_meas_set(data, false); - if (tmpret) - dev_warn(data->dev, "Stopping measurement failed\n"); - - return ret; -} - -/* - * Following equation for computing lux out of register values was given by - * ROHM HW colleagues; - * - * Red = RedData*1024 / Gain * 20 / meas_mode - * Green = GreenData* 1024 / Gain * 20 / meas_mode - * Blue = BlueData* 1024 / Gain * 20 / meas_mode - * IR = IrData* 1024 / Gain * 20 / meas_mode - * - * where meas_mode is the integration time in mS / 10 - * - * IRratio = (IR > 0.18 * Green) ? 0 : 1 - * - * Lx = max(c1*Red + c2*Green + c3*Blue,0) - * - * for - * IRratio 0: c1 = -0.00002237, c2 = 0.0003219, c3 = -0.000120371 - * IRratio 1: c1 = -0.00001074, c2 = 0.000305415, c3 = -0.000129367 - */ - -/* - * The max chan data is 0xffff. When we multiply it by 1024 * 20, we'll get - * 0x4FFFB000 which still fits in 32-bit integer. This won't overflow. - */ -#define NORM_CHAN_DATA_FOR_LX_CALC(chan, gain, time) (le16_to_cpu(chan) * \ - 1024 * 20 / (gain) / (time)) -static u64 bu27008_calc_nlux(struct bu27008_data *data, __le16 *lux_data, - unsigned int gain, unsigned int gain_ir, unsigned int time) -{ - unsigned int red, green, blue, ir; - s64 c1, c2, c3, nlux; - - time /= 10000; - ir = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_IR], gain_ir, time); - red = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_RED], gain, time); - green = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_GREEN], gain, time); - blue = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_BLUE], gain, time); - - if ((u64)ir * 100LLU > (u64)green * 18LLU) { - c1 = -22370; - c2 = 321900; - c3 = -120371; - } else { - c1 = -10740; - c2 = 305415; - c3 = -129367; - } - nlux = c1 * red + c2 * green + c3 * blue; - - return max_t(s64, 0, nlux); -} - -static int bu27008_get_time_n_gains(struct bu27008_data *data, - unsigned int *gain, unsigned int *gain_ir, unsigned int *time) -{ - int ret; - - ret = bu27008_get_gain(data, &data->gts, gain); - if (ret < 0) - return ret; - - ret = bu27008_get_gain(data, &data->gts_ir, gain_ir); - if (ret < 0) - return ret; - - ret = bu27008_get_int_time_us(data); - if (ret < 0) - return ret; - - /* Max integration time is 400000. Fits in signed int. */ - *time = ret; - - return 0; -} - -struct bu27008_buf { - __le16 chan[BU27008_NUM_HW_CHANS]; - u64 lux __aligned(8); - s64 ts __aligned(8); -}; - -static int bu27008_buffer_fill_lux(struct bu27008_data *data, - struct bu27008_buf *raw) -{ - unsigned int gain, gain_ir, time; - int ret; - - ret = bu27008_get_time_n_gains(data, &gain, &gain_ir, &time); - if (ret) - return ret; - - raw->lux = bu27008_calc_nlux(data, raw->chan, gain, gain_ir, time); - - return 0; -} - -static int bu27008_read_lux(struct bu27008_data *data, struct iio_dev *idev, - struct iio_chan_spec const *chan, - int *val, int *val2) -{ - __le16 lux_data[BU27008_NUM_HW_CHANS]; - unsigned int gain, gain_ir, time; - u64 nlux; - int ret; - - ret = bu27008_get_time_n_gains(data, &gain, &gain_ir, &time); - if (ret) - return ret; - - ret = bu27008_read_lux_chans(data, time, lux_data); - if (ret) - return ret; - - nlux = bu27008_calc_nlux(data, lux_data, gain, gain_ir, time); - *val = (int)nlux; - *val2 = nlux >> 32LLU; - - return IIO_VAL_INT_64; -} - -static int bu27008_read_raw(struct iio_dev *idev, - struct iio_chan_spec const *chan, - int *val, int *val2, long mask) -{ - struct bu27008_data *data = iio_priv(idev); - int busy, ret; - - switch (mask) { - case IIO_CHAN_INFO_RAW: - busy = iio_device_claim_direct_mode(idev); - if (busy) - return -EBUSY; - - mutex_lock(&data->mutex); - if (chan->type == IIO_LIGHT) - ret = bu27008_read_lux(data, idev, chan, val, val2); - else - ret = bu27008_read_one(data, idev, chan, val, val2); - mutex_unlock(&data->mutex); - - iio_device_release_direct_mode(idev); - - return ret; - - case IIO_CHAN_INFO_SCALE: - if (chan->type == IIO_LIGHT) { - *val = 0; - *val2 = 1; - return IIO_VAL_INT_PLUS_NANO; - } - ret = bu27008_get_scale(data, chan->scan_index == BU27008_IR, - val, val2); - if (ret) - return ret; - - return IIO_VAL_INT_PLUS_NANO; - - case IIO_CHAN_INFO_INT_TIME: - ret = bu27008_get_int_time_us(data); - if (ret < 0) - return ret; - - *val = 0; - *val2 = ret; - - return IIO_VAL_INT_PLUS_MICRO; - - default: - return -EINVAL; - } -} - -/* Called if the new scale could not be supported with existing int-time */ -static int bu27008_try_find_new_time_gain(struct bu27008_data *data, int val, - int val2, int *gain_sel) -{ - int i, ret, new_time_sel; - - for (i = 0; i < data->gts.num_itime; i++) { - new_time_sel = data->gts.itime_table[i].sel; - ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, - new_time_sel, val, val2, gain_sel); - if (!ret) - break; - } - if (i == data->gts.num_itime) { - dev_err(data->dev, "Can't support scale %u %u\n", val, val2); - - return -EINVAL; - } - - return bu27008_set_int_time_sel(data, new_time_sel); -} - -static int bu27008_set_scale(struct bu27008_data *data, - struct iio_chan_spec const *chan, - int val, int val2) -{ - int ret, gain_sel, time_sel; - - if (chan->scan_index == BU27008_IR) - return -EINVAL; - - mutex_lock(&data->mutex); - - ret = bu27008_get_int_time_sel(data, &time_sel); - if (ret < 0) - goto unlock_out; - - ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, time_sel, - val, val2, &gain_sel); - if (ret) { - ret = bu27008_try_find_new_time_gain(data, val, val2, &gain_sel); - if (ret) - goto unlock_out; - - } - ret = data->cd->write_gain_sel(data, gain_sel); - -unlock_out: - mutex_unlock(&data->mutex); - - return ret; -} - -static int bu27008_write_raw_get_fmt(struct iio_dev *indio_dev, - struct iio_chan_spec const *chan, - long mask) -{ - - switch (mask) { - case IIO_CHAN_INFO_SCALE: - return IIO_VAL_INT_PLUS_NANO; - case IIO_CHAN_INFO_INT_TIME: - return IIO_VAL_INT_PLUS_MICRO; - default: - return -EINVAL; - } -} - -static int bu27008_write_raw(struct iio_dev *idev, - struct iio_chan_spec const *chan, - int val, int val2, long mask) -{ - struct bu27008_data *data = iio_priv(idev); - int ret; - - /* - * Do not allow changing scale when measurement is ongoing as doing so - * could make values in the buffer inconsistent. - */ - ret = iio_device_claim_direct_mode(idev); - if (ret) - return ret; - - switch (mask) { - case IIO_CHAN_INFO_SCALE: - ret = bu27008_set_scale(data, chan, val, val2); - break; - case IIO_CHAN_INFO_INT_TIME: - if (val) { - ret = -EINVAL; - break; - } - ret = bu27008_try_set_int_time(data, val2); - break; - default: - ret = -EINVAL; - break; - } - iio_device_release_direct_mode(idev); - - return ret; -} - -static int bu27008_read_avail(struct iio_dev *idev, - struct iio_chan_spec const *chan, const int **vals, - int *type, int *length, long mask) -{ - struct bu27008_data *data = iio_priv(idev); - - switch (mask) { - case IIO_CHAN_INFO_INT_TIME: - return iio_gts_avail_times(&data->gts, vals, type, length); - case IIO_CHAN_INFO_SCALE: - if (chan->channel2 == IIO_MOD_LIGHT_IR) - return iio_gts_all_avail_scales(&data->gts_ir, vals, - type, length); - return iio_gts_all_avail_scales(&data->gts, vals, type, length); - default: - return -EINVAL; - } -} - -static int bu27008_update_scan_mode(struct iio_dev *idev, - const unsigned long *scan_mask) -{ - struct bu27008_data *data = iio_priv(idev); - int chan_sel; - - /* Configure channel selection */ - if (test_bit(BU27008_BLUE, idev->active_scan_mask)) { - if (test_bit(BU27008_CLEAR, idev->active_scan_mask)) - chan_sel = BU27008_BLUE2_CLEAR3; - else - chan_sel = BU27008_BLUE2_IR3; - } else { - chan_sel = BU27008_CLEAR2_IR3; - } - - chan_sel <<= ffs(data->cd->chan_sel_mask) - 1; - - return regmap_update_bits(data->regmap, data->cd->chan_sel_reg, - data->cd->chan_sel_mask, chan_sel); -} - -static const struct iio_info bu27008_info = { - .read_raw = &bu27008_read_raw, - .write_raw = &bu27008_write_raw, - .write_raw_get_fmt = &bu27008_write_raw_get_fmt, - .read_avail = &bu27008_read_avail, - .update_scan_mode = bu27008_update_scan_mode, - .validate_trigger = iio_validate_own_trigger, -}; - -static int bu27008_trigger_set_state(struct iio_trigger *trig, bool state) -{ - struct bu27008_data *data = iio_trigger_get_drvdata(trig); - int ret; - - - if (state) - ret = regmap_set_bits(data->regmap, data->cd->drdy_en_reg, - data->cd->drdy_en_mask); - else - ret = regmap_clear_bits(data->regmap, data->cd->drdy_en_reg, - data->cd->drdy_en_mask); - if (ret) - dev_err(data->dev, "Failed to set trigger state\n"); - - return ret; -} - -static void bu27008_trigger_reenable(struct iio_trigger *trig) -{ - struct bu27008_data *data = iio_trigger_get_drvdata(trig); - - enable_irq(data->irq); -} - -static const struct iio_trigger_ops bu27008_trigger_ops = { - .set_trigger_state = bu27008_trigger_set_state, - .reenable = bu27008_trigger_reenable, -}; - -static irqreturn_t bu27008_trigger_handler(int irq, void *p) -{ - struct iio_poll_func *pf = p; - struct iio_dev *idev = pf->indio_dev; - struct bu27008_data *data = iio_priv(idev); - struct bu27008_buf raw; - int ret, dummy; - - memset(&raw, 0, sizeof(raw)); - - /* - * After some measurements, it seems reading the - * BU27008_REG_MODE_CONTROL3 debounces the IRQ line - */ - ret = regmap_read(data->regmap, data->cd->valid_reg, &dummy); - if (ret < 0) - goto err_read; - - ret = regmap_bulk_read(data->regmap, BU27008_REG_DATA0_LO, &raw.chan, - sizeof(raw.chan)); - if (ret < 0) - goto err_read; - - if (test_bit(BU27008_LUX, idev->active_scan_mask)) { - ret = bu27008_buffer_fill_lux(data, &raw); - if (ret) - goto err_read; - } - - iio_push_to_buffers_with_timestamp(idev, &raw, pf->timestamp); -err_read: - iio_trigger_notify_done(idev->trig); - - return IRQ_HANDLED; -} - -static int bu27008_buffer_preenable(struct iio_dev *idev) -{ - struct bu27008_data *data = iio_priv(idev); - - return bu27008_meas_set(data, true); -} - -static int bu27008_buffer_postdisable(struct iio_dev *idev) -{ - struct bu27008_data *data = iio_priv(idev); - - return bu27008_meas_set(data, false); -} - -static const struct iio_buffer_setup_ops bu27008_buffer_ops = { - .preenable = bu27008_buffer_preenable, - .postdisable = bu27008_buffer_postdisable, -}; - -static irqreturn_t bu27008_data_rdy_poll(int irq, void *private) -{ - /* - * The BU27008 keeps IRQ asserted until we read the VALID bit from - * a register. We need to keep the IRQ disabled until then. - */ - disable_irq_nosync(irq); - iio_trigger_poll(private); - - return IRQ_HANDLED; -} - -static int bu27008_setup_trigger(struct bu27008_data *data, struct iio_dev *idev) -{ - struct iio_trigger *itrig; - char *name; - int ret; - - ret = devm_iio_triggered_buffer_setup(data->dev, idev, - &iio_pollfunc_store_time, - bu27008_trigger_handler, - &bu27008_buffer_ops); - if (ret) - return dev_err_probe(data->dev, ret, - "iio_triggered_buffer_setup_ext FAIL\n"); - - itrig = devm_iio_trigger_alloc(data->dev, "%sdata-rdy-dev%d", - idev->name, iio_device_id(idev)); - if (!itrig) - return -ENOMEM; - - data->trig = itrig; - - itrig->ops = &bu27008_trigger_ops; - iio_trigger_set_drvdata(itrig, data); - - name = devm_kasprintf(data->dev, GFP_KERNEL, "%s-bu27008", - dev_name(data->dev)); - - ret = devm_request_irq(data->dev, data->irq, - &bu27008_data_rdy_poll, - 0, name, itrig); - if (ret) - return dev_err_probe(data->dev, ret, "Could not request IRQ\n"); - - ret = devm_iio_trigger_register(data->dev, itrig); - if (ret) - return dev_err_probe(data->dev, ret, - "Trigger registration failed\n"); - - /* set default trigger */ - idev->trig = iio_trigger_get(itrig); - - return 0; -} - -static int bu27008_probe(struct i2c_client *i2c) -{ - struct device *dev = &i2c->dev; - struct bu27008_data *data; - struct regmap *regmap; - unsigned int part_id, reg; - struct iio_dev *idev; - int ret; - - idev = devm_iio_device_alloc(dev, sizeof(*data)); - if (!idev) - return -ENOMEM; - - ret = devm_regulator_get_enable(dev, "vdd"); - if (ret) - return dev_err_probe(dev, ret, "Failed to get regulator\n"); - - data = iio_priv(idev); - - data->cd = device_get_match_data(&i2c->dev); - if (!data->cd) - return -ENODEV; - - regmap = devm_regmap_init_i2c(i2c, data->cd->regmap_cfg); - if (IS_ERR(regmap)) - return dev_err_probe(dev, PTR_ERR(regmap), - "Failed to initialize Regmap\n"); - - - ret = regmap_read(regmap, BU27008_REG_SYSTEM_CONTROL, ®); - if (ret) - return dev_err_probe(dev, ret, "Failed to access sensor\n"); - - part_id = FIELD_GET(BU27008_MASK_PART_ID, reg); - - if (part_id != data->cd->part_id) - dev_warn(dev, "unknown device 0x%x\n", part_id); - - ret = devm_iio_init_iio_gts(dev, data->cd->scale1x, 0, data->cd->gains, - data->cd->num_gains, data->cd->itimes, - data->cd->num_itimes, &data->gts); - if (ret) - return ret; - - ret = devm_iio_init_iio_gts(dev, data->cd->scale1x, 0, data->cd->gains_ir, - data->cd->num_gains_ir, data->cd->itimes, - data->cd->num_itimes, &data->gts_ir); - if (ret) - return ret; - - mutex_init(&data->mutex); - data->regmap = regmap; - data->dev = dev; - data->irq = i2c->irq; - - idev->channels = bu27008_channels; - idev->num_channels = ARRAY_SIZE(bu27008_channels); - idev->name = data->cd->name; - idev->info = &bu27008_info; - idev->modes = INDIO_DIRECT_MODE; - idev->available_scan_masks = bu27008_scan_masks; - - ret = data->cd->chip_init(data); - if (ret) - return ret; - - if (i2c->irq) { - ret = bu27008_setup_trigger(data, idev); - if (ret) - return ret; - } else { - dev_info(dev, "No IRQ, buffered mode disabled\n"); - } - - ret = devm_iio_device_register(dev, idev); - if (ret) - return dev_err_probe(dev, ret, - "Unable to register iio device\n"); - - return 0; -} - -static const struct of_device_id bu27008_of_match[] = { - { .compatible = "rohm,bu27008", .data = &bu27008_chip }, - { .compatible = "rohm,bu27010", .data = &bu27010_chip }, - { } -}; -MODULE_DEVICE_TABLE(of, bu27008_of_match); - -static struct i2c_driver bu27008_i2c_driver = { - .driver = { - .name = "bu27008", - .of_match_table = bu27008_of_match, - .probe_type = PROBE_PREFER_ASYNCHRONOUS, - }, - .probe = bu27008_probe, -}; -module_i2c_driver(bu27008_i2c_driver); - -MODULE_DESCRIPTION("ROHM BU27008 and BU27010 colour sensor driver"); -MODULE_AUTHOR("Matti Vaittinen "); -MODULE_LICENSE("GPL"); -MODULE_IMPORT_NS("IIO_GTS_HELPER"); diff --git a/drivers/iio/light/rohm-bu27034.c b/drivers/iio/light/rohm-bu27034.c index 4f591c2278f2..cc25596cb248 100644 --- a/drivers/iio/light/rohm-bu27034.c +++ b/drivers/iio/light/rohm-bu27034.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -205,7 +206,7 @@ struct bu27034_data { struct { u32 mlux; __le16 channels[BU27034_NUM_HW_DATA_CHANS]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; @@ -395,30 +396,26 @@ static int bu27034_try_set_int_time(struct bu27034_data *data, int time_us) int numg = ARRAY_SIZE(gains); int ret, int_time_old, i; - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); ret = bu27034_get_int_time(data); if (ret < 0) - goto unlock_out; + return ret; int_time_old = ret; if (!iio_gts_valid_time(&data->gts, time_us)) { dev_err(data->dev, "Unsupported integration time %u\n", time_us); - ret = -EINVAL; - - goto unlock_out; + return -EINVAL; } - if (time_us == int_time_old) { - ret = 0; - goto unlock_out; - } + if (time_us == int_time_old) + return 0; for (i = 0; i < numg; i++) { ret = bu27034_get_gain(data, gains[i].chan, &gains[i].old_gain); if (ret) - goto unlock_out; + return 0; ret = iio_gts_find_new_gain_by_old_gain_time(&data->gts, gains[i].old_gain, @@ -434,7 +431,7 @@ static int bu27034_try_set_int_time(struct bu27034_data *data, int time_us) gains[i].chan, time_us, scale1, scale2); if (gains[i].new_gain < 0) - goto unlock_out; + return ret; /* * If caller requests for integration time change and we @@ -455,7 +452,7 @@ static int bu27034_try_set_int_time(struct bu27034_data *data, int time_us) "Total gain increase. Risk of saturation"); ret = iio_gts_get_min_gain(&data->gts); if (ret < 0) - goto unlock_out; + return ret; } dev_dbg(data->dev, "chan %u scale changed\n", gains[i].chan); @@ -468,15 +465,10 @@ static int bu27034_try_set_int_time(struct bu27034_data *data, int time_us) for (i = 0; i < numg; i++) { ret = bu27034_set_gain(data, gains[i].chan, gains[i].new_gain); if (ret) - goto unlock_out; + return ret; } - ret = bu27034_set_int_time(data, time_us); - -unlock_out: - mutex_unlock(&data->mutex); - - return ret; + return bu27034_set_int_time(data, time_us); } static int bu27034_set_scale(struct bu27034_data *data, int chan, @@ -492,10 +484,10 @@ static int bu27034_set_scale(struct bu27034_data *data, int chan, return -EINVAL; } - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); ret = regmap_read(data->regmap, BU27034_REG_MODE_CONTROL1, &time_sel); if (ret) - goto unlock_out; + return ret; ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, time_sel, val, val2, &gain_sel); @@ -518,7 +510,7 @@ static int bu27034_set_scale(struct bu27034_data *data, int chan, ret = bu27034_get_gain(data, gain.chan, &gain.old_gain); if (ret) - goto unlock_out; + return ret; /* * Iterate through all the times to see if we find one which @@ -551,26 +543,20 @@ static int bu27034_set_scale(struct bu27034_data *data, int chan, if (!found) { dev_dbg(data->dev, "Can't set scale maintaining other channel\n"); - ret = -EINVAL; - - goto unlock_out; + return -EINVAL; } ret = bu27034_set_gain(data, gain.chan, gain.new_gain); if (ret) - goto unlock_out; + return ret; ret = regmap_update_bits(data->regmap, BU27034_REG_MODE_CONTROL1, BU27034_MASK_MEAS_MODE, new_time_sel); if (ret) - goto unlock_out; + return ret; } - ret = bu27034_write_gain_sel(data, chan, gain_sel); -unlock_out: - mutex_unlock(&data->mutex); - - return ret; + return bu27034_write_gain_sel(data, chan, gain_sel); } /* @@ -1221,42 +1207,33 @@ static int bu27034_buffer_enable(struct iio_dev *idev) struct task_struct *task; int ret; - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); ret = bu27034_meas_set(data, true); if (ret) - goto unlock_out; + return ret; task = kthread_run(bu27034_buffer_thread, idev, "bu27034-buffering-%u", iio_device_id(idev)); - if (IS_ERR(task)) { - ret = PTR_ERR(task); - goto unlock_out; - } + if (IS_ERR(task)) + return PTR_ERR(task); data->task = task; -unlock_out: - mutex_unlock(&data->mutex); - - return ret; + return 0; } static int bu27034_buffer_disable(struct iio_dev *idev) { struct bu27034_data *data = iio_priv(idev); - int ret; - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); if (data->task) { kthread_stop(data->task); data->task = NULL; } - ret = bu27034_meas_set(data, false); - mutex_unlock(&data->mutex); - - return ret; + return bu27034_meas_set(data, false); } static const struct iio_buffer_setup_ops bu27034_buffer_ops = { diff --git a/drivers/iio/light/rpr0521.c b/drivers/iio/light/rpr0521.c index 56f5fbbf79ac..2ba917c5c138 100644 --- a/drivers/iio/light/rpr0521.c +++ b/drivers/iio/light/rpr0521.c @@ -203,7 +203,7 @@ struct rpr0521_data { struct { __le16 channels[3]; u8 garbage; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/light/st_uvis25.h b/drivers/iio/light/st_uvis25.h index 283086887caf..1f93e3dc45c2 100644 --- a/drivers/iio/light/st_uvis25.h +++ b/drivers/iio/light/st_uvis25.h @@ -30,7 +30,7 @@ struct st_uvis25_hw { /* Ensure timestamp is naturally aligned */ struct { u8 chan; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/light/tcs3414.c b/drivers/iio/light/tcs3414.c index 4fecdf10aeb1..884e43e4cda4 100644 --- a/drivers/iio/light/tcs3414.c +++ b/drivers/iio/light/tcs3414.c @@ -56,7 +56,7 @@ struct tcs3414_data { /* Ensure timestamp is naturally aligned */ struct { u16 chans[4]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; }; diff --git a/drivers/iio/light/tcs3472.c b/drivers/iio/light/tcs3472.c index 4186aac04902..2bd36a344ea5 100644 --- a/drivers/iio/light/tcs3472.c +++ b/drivers/iio/light/tcs3472.c @@ -67,7 +67,7 @@ struct tcs3472_data { /* Ensure timestamp is naturally aligned */ struct { u16 chans[4]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; }; diff --git a/drivers/iio/light/vcnl4035.c b/drivers/iio/light/vcnl4035.c index 337a1332c2c6..67c94be02018 100644 --- a/drivers/iio/light/vcnl4035.c +++ b/drivers/iio/light/vcnl4035.c @@ -105,7 +105,7 @@ static irqreturn_t vcnl4035_trigger_consumer_handler(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct vcnl4035_data *data = iio_priv(indio_dev); /* Ensure naturally aligned timestamp */ - u8 buffer[ALIGN(sizeof(u16), sizeof(s64)) + sizeof(s64)] __aligned(8); + u8 buffer[ALIGN(sizeof(u16), sizeof(s64)) + sizeof(s64)] __aligned(8) = { }; int ret; ret = regmap_read(data->regmap, VCNL4035_ALS_DATA, (int *)buffer); diff --git a/drivers/iio/light/veml3235.c b/drivers/iio/light/veml3235.c index 66361c3012a3..77c9ae17ed47 100644 --- a/drivers/iio/light/veml3235.c +++ b/drivers/iio/light/veml3235.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -35,17 +36,33 @@ struct veml3235_data { struct device *dev; struct regmap *regmap; struct veml3235_rf rf; + struct iio_gts gts; }; -static const int veml3235_it_times[][2] = { - { 0, 50000 }, - { 0, 100000 }, - { 0, 200000 }, - { 0, 400000 }, - { 0, 800000 }, +static const struct iio_itime_sel_mul veml3235_it_sel[] = { + GAIN_SCALE_ITIME_US(50000, 0, 1), + GAIN_SCALE_ITIME_US(100000, 1, 2), + GAIN_SCALE_ITIME_US(200000, 2, 4), + GAIN_SCALE_ITIME_US(400000, 3, 8), + GAIN_SCALE_ITIME_US(800000, 4, 16), }; -static const int veml3235_scale_vals[] = { 1, 2, 4, 8 }; +/* + * The MSB (DG) doubles the value of the rest of the field, which leads to + * two possible combinations to obtain gain = 2 and gain = 4. The gain + * handling can be simplified by restricting DG = 1 to the only gain that + * really requires it, gain = 8. Note that "X10" is a reserved value. + */ +#define VEML3235_SEL_GAIN_X1 0 +#define VEML3235_SEL_GAIN_X2 1 +#define VEML3235_SEL_GAIN_X4 3 +#define VEML3235_SEL_GAIN_X8 7 +static const struct iio_gain_sel_pair veml3235_gain_sel[] = { + GAIN_SCALE_GAIN(1, VEML3235_SEL_GAIN_X1), + GAIN_SCALE_GAIN(2, VEML3235_SEL_GAIN_X2), + GAIN_SCALE_GAIN(4, VEML3235_SEL_GAIN_X4), + GAIN_SCALE_GAIN(8, VEML3235_SEL_GAIN_X8), +}; static int veml3235_power_on(struct veml3235_data *data) { @@ -101,42 +118,58 @@ static const struct iio_chan_spec veml3235_channels[] = { }, }; +static const struct regmap_range veml3235_readable_ranges[] = { + regmap_reg_range(VEML3235_REG_CONF, VEML3235_REG_ID), +}; + +static const struct regmap_access_table veml3235_readable_table = { + .yes_ranges = veml3235_readable_ranges, + .n_yes_ranges = ARRAY_SIZE(veml3235_readable_ranges), +}; + +static const struct regmap_range veml3235_writable_ranges[] = { + regmap_reg_range(VEML3235_REG_CONF, VEML3235_REG_CONF), +}; + +static const struct regmap_access_table veml3235_writable_table = { + .yes_ranges = veml3235_writable_ranges, + .n_yes_ranges = ARRAY_SIZE(veml3235_writable_ranges), +}; + +static const struct regmap_range veml3235_volatile_ranges[] = { + regmap_reg_range(VEML3235_REG_WH_DATA, VEML3235_REG_ALS_DATA), +}; + +static const struct regmap_access_table veml3235_volatile_table = { + .yes_ranges = veml3235_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(veml3235_volatile_ranges), +}; + static const struct regmap_config veml3235_regmap_config = { .name = "veml3235_regmap", .reg_bits = 8, .val_bits = 16, .max_register = VEML3235_REG_ID, .val_format_endian = REGMAP_ENDIAN_LITTLE, + .rd_table = &veml3235_readable_table, + .wr_table = &veml3235_writable_table, + .volatile_table = &veml3235_volatile_table, + .cache_type = REGCACHE_RBTREE, }; static int veml3235_get_it(struct veml3235_data *data, int *val, int *val2) { - int ret, reg; + int ret, it_idx; - ret = regmap_field_read(data->rf.it, ®); + ret = regmap_field_read(data->rf.it, &it_idx); if (ret) return ret; - switch (reg) { - case 0: - *val2 = 50000; - break; - case 1: - *val2 = 100000; - break; - case 2: - *val2 = 200000; - break; - case 3: - *val2 = 400000; - break; - case 4: - *val2 = 800000; - break; - default: - return -EINVAL; - } + ret = iio_gts_find_int_time_by_sel(&data->gts, it_idx); + if (ret < 0) + return ret; + *val2 = ret; *val = 0; return IIO_VAL_INT_PLUS_MICRO; @@ -145,78 +178,78 @@ static int veml3235_get_it(struct veml3235_data *data, int *val, int *val2) static int veml3235_set_it(struct iio_dev *indio_dev, int val, int val2) { struct veml3235_data *data = iio_priv(indio_dev); - int ret, new_it; + int ret, gain_idx, it_idx, new_gain, prev_gain, prev_it; + bool in_range; - if (val) + if (val || !iio_gts_valid_time(&data->gts, val2)) return -EINVAL; - switch (val2) { - case 50000: - new_it = 0x00; - break; - case 100000: - new_it = 0x01; - break; - case 200000: - new_it = 0x02; - break; - case 400000: - new_it = 0x03; - break; - case 800000: - new_it = 0x04; - break; - default: - return -EINVAL; - } - - ret = regmap_field_write(data->rf.it, new_it); - if (ret) { - dev_err(data->dev, - "failed to update integration time: %d\n", ret); + ret = regmap_field_read(data->rf.it, &it_idx); + if (ret) return ret; - } - return 0; + ret = regmap_field_read(data->rf.gain, &gain_idx); + if (ret) + return ret; + + prev_it = iio_gts_find_int_time_by_sel(&data->gts, it_idx); + if (prev_it < 0) + return prev_it; + + if (prev_it == val2) + return 0; + + prev_gain = iio_gts_find_gain_by_sel(&data->gts, gain_idx); + if (prev_gain < 0) + return prev_gain; + + ret = iio_gts_find_new_gain_by_gain_time_min(&data->gts, prev_gain, prev_it, + val2, &new_gain, &in_range); + if (ret) + return ret; + + if (!in_range) + dev_dbg(data->dev, "Optimal gain out of range\n"); + + ret = iio_gts_find_sel_by_int_time(&data->gts, val2); + if (ret < 0) + return ret; + + ret = regmap_field_write(data->rf.it, ret); + if (ret) + return ret; + + ret = iio_gts_find_sel_by_gain(&data->gts, new_gain); + if (ret < 0) + return ret; + + return regmap_field_write(data->rf.gain, ret); } -static int veml3235_set_gain(struct iio_dev *indio_dev, int val, int val2) +static int veml3235_set_scale(struct iio_dev *indio_dev, int val, int val2) { struct veml3235_data *data = iio_priv(indio_dev); - int ret, new_gain; + int ret, it_idx, gain_sel, time_sel; - if (val2 != 0) - return -EINVAL; - - switch (val) { - case 1: - new_gain = 0x00; - break; - case 2: - new_gain = 0x01; - break; - case 4: - new_gain = 0x03; - break; - case 8: - new_gain = 0x07; - break; - default: - return -EINVAL; - } - - ret = regmap_field_write(data->rf.gain, new_gain); - if (ret) { - dev_err(data->dev, "failed to set gain: %d\n", ret); + ret = regmap_field_read(data->rf.it, &it_idx); + if (ret) return ret; - } - return 0; + ret = iio_gts_find_gain_time_sel_for_scale(&data->gts, val, val2, + &gain_sel, &time_sel); + if (ret) + return ret; + + ret = regmap_field_write(data->rf.it, time_sel); + if (ret) + return ret; + + return regmap_field_write(data->rf.gain, gain_sel); } -static int veml3235_get_gain(struct veml3235_data *data, int *val) +static int veml3235_get_scale(struct veml3235_data *data, int *val, int *val2) { - int ret, reg; + int gain, it, reg, ret; ret = regmap_field_read(data->rf.gain, ®); if (ret) { @@ -224,25 +257,25 @@ static int veml3235_get_gain(struct veml3235_data *data, int *val) return ret; } - switch (reg & 0x03) { - case 0: - *val = 1; - break; - case 1: - *val = 2; - break; - case 3: - *val = 4; - break; - default: - return -EINVAL; + gain = iio_gts_find_gain_by_sel(&data->gts, reg); + if (gain < 0) + return gain; + + ret = regmap_field_read(data->rf.it, ®); + if (ret) { + dev_err(data->dev, "failed to read integration time %d\n", ret); + return ret; } - /* Double gain */ - if (reg & 0x04) - *val *= 2; + it = iio_gts_find_int_time_by_sel(&data->gts, reg); + if (it < 0) + return it; - return IIO_VAL_INT; + ret = iio_gts_get_scale(&data->gts, gain, it, val, val2); + if (ret) + return ret; + + return IIO_VAL_INT_PLUS_NANO; } static int veml3235_read_raw(struct iio_dev *indio_dev, @@ -276,7 +309,7 @@ static int veml3235_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_INT_TIME: return veml3235_get_it(data, val, val2); case IIO_CHAN_INFO_SCALE: - return veml3235_get_gain(data, val); + return veml3235_get_scale(data, val, val2); default: return -EINVAL; } @@ -287,17 +320,27 @@ static int veml3235_read_avail(struct iio_dev *indio_dev, const int **vals, int *type, int *length, long mask) { + struct veml3235_data *data = iio_priv(indio_dev); + switch (mask) { case IIO_CHAN_INFO_INT_TIME: - *vals = (int *)&veml3235_it_times; - *length = 2 * ARRAY_SIZE(veml3235_it_times); - *type = IIO_VAL_INT_PLUS_MICRO; - return IIO_AVAIL_LIST; + return iio_gts_avail_times(&data->gts, vals, type, length); case IIO_CHAN_INFO_SCALE: - *vals = (int *)&veml3235_scale_vals; - *length = ARRAY_SIZE(veml3235_scale_vals); - *type = IIO_VAL_INT; - return IIO_AVAIL_LIST; + return iio_gts_all_avail_scales(&data->gts, vals, type, length); + default: + return -EINVAL; + } +} + +static int veml3235_write_raw_get_fmt(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + long mask) +{ + switch (mask) { + case IIO_CHAN_INFO_SCALE: + return IIO_VAL_INT_PLUS_NANO; + case IIO_CHAN_INFO_INT_TIME: + return IIO_VAL_INT_PLUS_MICRO; default: return -EINVAL; } @@ -311,7 +354,7 @@ static int veml3235_write_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_INT_TIME: return veml3235_set_it(indio_dev, val, val2); case IIO_CHAN_INFO_SCALE: - return veml3235_set_gain(indio_dev, val, val2); + return veml3235_set_scale(indio_dev, val, val2); } return -EINVAL; @@ -321,7 +364,7 @@ static void veml3235_read_id(struct veml3235_data *data) { int ret, reg; - ret = regmap_field_read(data->rf.id, ®); + ret = regmap_field_read(data->rf.id, ®); if (ret) { dev_info(data->dev, "failed to read ID\n"); return; @@ -371,6 +414,13 @@ static int veml3235_hw_init(struct iio_dev *indio_dev) struct device *dev = data->dev; int ret; + ret = devm_iio_init_iio_gts(data->dev, 0, 272640000, + veml3235_gain_sel, ARRAY_SIZE(veml3235_gain_sel), + veml3235_it_sel, ARRAY_SIZE(veml3235_it_sel), + &data->gts); + if (ret) + return dev_err_probe(data->dev, ret, "failed to init iio gts\n"); + /* Set gain to 1 and integration time to 100 ms */ ret = regmap_field_write(data->rf.gain, 0x00); if (ret) @@ -389,9 +439,10 @@ static int veml3235_hw_init(struct iio_dev *indio_dev) } static const struct iio_info veml3235_info = { - .read_raw = veml3235_read_raw, - .read_avail = veml3235_read_avail, + .read_raw = veml3235_read_raw, + .read_avail = veml3235_read_avail, .write_raw = veml3235_write_raw, + .write_raw_get_fmt = veml3235_write_raw_get_fmt, }; static int veml3235_probe(struct i2c_client *client) @@ -493,3 +544,4 @@ module_i2c_driver(veml3235_driver); MODULE_AUTHOR("Javier Carrasco "); MODULE_DESCRIPTION("VEML3235 Ambient Light Sensor"); MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS("IIO_GTS_HELPER"); diff --git a/drivers/iio/light/veml6030.c b/drivers/iio/light/veml6030.c index ccb43dfd5cf7..9b71825eea9b 100644 --- a/drivers/iio/light/veml6030.c +++ b/drivers/iio/light/veml6030.c @@ -28,6 +28,8 @@ #include #include #include +#include +#include /* Device registers */ #define VEML6030_REG_ALS_CONF 0x00 @@ -37,6 +39,7 @@ #define VEML6030_REG_ALS_DATA 0x04 #define VEML6030_REG_WH_DATA 0x05 #define VEML6030_REG_ALS_INT 0x06 +#define VEML6030_REG_DATA(ch) (VEML6030_REG_ALS_DATA + (ch)) /* Bit masks for specific functionality */ #define VEML6030_ALS_IT GENMASK(9, 6) @@ -56,6 +59,12 @@ #define VEML6035_INT_CHAN BIT(3) #define VEML6035_CHAN_EN BIT(2) +enum veml6030_scan { + VEML6030_SCAN_ALS, + VEML6030_SCAN_WH, + VEML6030_SCAN_TIMESTAMP, +}; + struct veml603x_chip { const char *name; const int(*scale_vals)[][2]; @@ -242,6 +251,13 @@ static const struct iio_chan_spec veml6030_channels[] = { BIT(IIO_CHAN_INFO_SCALE), .event_spec = veml6030_event_spec, .num_event_specs = ARRAY_SIZE(veml6030_event_spec), + .scan_index = VEML6030_SCAN_ALS, + .scan_type = { + .sign = 'u', + .realbits = 16, + .storagebits = 16, + .endianness = IIO_CPU, + }, }, { .type = IIO_INTENSITY, @@ -253,7 +269,15 @@ static const struct iio_chan_spec veml6030_channels[] = { BIT(IIO_CHAN_INFO_SCALE), .info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME) | BIT(IIO_CHAN_INFO_SCALE), + .scan_index = VEML6030_SCAN_WH, + .scan_type = { + .sign = 'u', + .realbits = 16, + .storagebits = 16, + .endianness = IIO_CPU, + }, }, + IIO_CHAN_SOFT_TIMESTAMP(VEML6030_SCAN_TIMESTAMP), }; static const struct iio_chan_spec veml7700_channels[] = { @@ -266,6 +290,13 @@ static const struct iio_chan_spec veml7700_channels[] = { BIT(IIO_CHAN_INFO_SCALE), .info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME) | BIT(IIO_CHAN_INFO_SCALE), + .scan_index = VEML6030_SCAN_ALS, + .scan_type = { + .sign = 'u', + .realbits = 16, + .storagebits = 16, + .endianness = IIO_CPU, + }, }, { .type = IIO_INTENSITY, @@ -277,7 +308,15 @@ static const struct iio_chan_spec veml7700_channels[] = { BIT(IIO_CHAN_INFO_SCALE), .info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME) | BIT(IIO_CHAN_INFO_SCALE), + .scan_index = VEML6030_SCAN_WH, + .scan_type = { + .sign = 'u', + .realbits = 16, + .storagebits = 16, + .endianness = IIO_CPU, + }, }, + IIO_CHAN_SOFT_TIMESTAMP(VEML6030_SCAN_TIMESTAMP), }; static const struct regmap_config veml6030_regmap_config = { @@ -889,6 +928,37 @@ static irqreturn_t veml6030_event_handler(int irq, void *private) return IRQ_HANDLED; } +static irqreturn_t veml6030_trigger_handler(int irq, void *p) +{ + struct iio_poll_func *pf = p; + struct iio_dev *iio = pf->indio_dev; + struct veml6030_data *data = iio_priv(iio); + unsigned int reg; + int ch, ret, i = 0; + struct { + u16 chans[2]; + aligned_s64 timestamp; + } scan; + + memset(&scan, 0, sizeof(scan)); + + iio_for_each_active_channel(iio, ch) { + ret = regmap_read(data->regmap, VEML6030_REG_DATA(ch), + ®); + if (ret) + goto done; + + scan.chans[i++] = reg; + } + + iio_push_to_buffers_with_timestamp(iio, &scan, pf->timestamp); + +done: + iio_trigger_notify_done(iio->trig); + + return IRQ_HANDLED; +} + static int veml6030_set_info(struct iio_dev *indio_dev) { struct veml6030_data *data = iio_priv(indio_dev); @@ -1077,6 +1147,12 @@ static int veml6030_probe(struct i2c_client *client) if (ret < 0) return ret; + ret = devm_iio_triggered_buffer_setup(&client->dev, indio_dev, NULL, + veml6030_trigger_handler, NULL); + if (ret) + return dev_err_probe(&client->dev, ret, + "Failed to register triggered buffer"); + return devm_iio_device_register(&client->dev, indio_dev); } diff --git a/drivers/iio/magnetometer/af8133j.c b/drivers/iio/magnetometer/af8133j.c index acd291f3e792..a70bf8a3c73b 100644 --- a/drivers/iio/magnetometer/af8133j.c +++ b/drivers/iio/magnetometer/af8133j.c @@ -360,7 +360,7 @@ static irqreturn_t af8133j_trigger_handler(int irq, void *p) s64 timestamp = iio_get_time_ns(indio_dev); struct { __le16 values[3]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } sample; int ret; diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c index 8306a18706ac..08975c60e325 100644 --- a/drivers/iio/magnetometer/ak8974.c +++ b/drivers/iio/magnetometer/ak8974.c @@ -197,7 +197,7 @@ struct ak8974 { /* Ensure timestamp is naturally aligned */ struct { __le16 channels[3]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index 18077fb463a9..ef1363126cc2 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -426,7 +426,7 @@ struct ak8975_data { /* Ensure natural alignment of timestamp */ struct { s16 channels[3]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/magnetometer/bmc150_magn.c b/drivers/iio/magnetometer/bmc150_magn.c index 7f545740178e..88bb673e40d8 100644 --- a/drivers/iio/magnetometer/bmc150_magn.c +++ b/drivers/iio/magnetometer/bmc150_magn.c @@ -140,7 +140,7 @@ struct bmc150_magn_data { /* Ensure timestamp is naturally aligned */ struct { s32 chans[3]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; struct iio_trigger *dready_trig; bool dready_trigger_on; diff --git a/drivers/iio/magnetometer/hmc5843.h b/drivers/iio/magnetometer/hmc5843.h index 60fbb5431c88..ffd669b1ee7c 100644 --- a/drivers/iio/magnetometer/hmc5843.h +++ b/drivers/iio/magnetometer/hmc5843.h @@ -44,7 +44,7 @@ struct hmc5843_data { struct iio_mount_matrix orientation; struct { __be16 chans[3]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; }; diff --git a/drivers/iio/magnetometer/mag3110.c b/drivers/iio/magnetometer/mag3110.c index 5295dc0100e4..2fe8e97f2cf8 100644 --- a/drivers/iio/magnetometer/mag3110.c +++ b/drivers/iio/magnetometer/mag3110.c @@ -60,7 +60,7 @@ struct mag3110_data { struct { __be16 channels[3]; u8 temperature; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/magnetometer/yamaha-yas530.c b/drivers/iio/magnetometer/yamaha-yas530.c index c55a38650c0d..28012b20c64f 100644 --- a/drivers/iio/magnetometer/yamaha-yas530.c +++ b/drivers/iio/magnetometer/yamaha-yas530.c @@ -236,7 +236,7 @@ struct yas5xx { */ struct { s32 channels[4]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/multiplexer/iio-mux.c b/drivers/iio/multiplexer/iio-mux.c index 2953403bef53..c309d991490c 100644 --- a/drivers/iio/multiplexer/iio-mux.c +++ b/drivers/iio/multiplexer/iio-mux.c @@ -7,6 +7,7 @@ * Author: Peter Rosin */ +#include #include #include #include @@ -237,49 +238,18 @@ static ssize_t mux_write_ext_info(struct iio_dev *indio_dev, uintptr_t private, return ret; } -static int mux_configure_channel(struct device *dev, struct mux *mux, - u32 state, const char *label, int idx) +static int mux_configure_chan_ext_info(struct device *dev, struct mux *mux, + int idx, int num_ext_info) { struct mux_child *child = &mux->child[idx]; - struct iio_chan_spec *chan = &mux->chan[idx]; struct iio_chan_spec const *pchan = mux->parent->channel; - char *page = NULL; - int num_ext_info; int i; int ret; - chan->indexed = 1; - chan->output = pchan->output; - chan->datasheet_name = label; - chan->ext_info = mux->ext_info; + char *page __free(kfree) = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!page) + return -ENOMEM; - ret = iio_get_channel_type(mux->parent, &chan->type); - if (ret < 0) { - dev_err(dev, "failed to get parent channel type\n"); - return ret; - } - - if (iio_channel_has_info(pchan, IIO_CHAN_INFO_RAW)) - chan->info_mask_separate |= BIT(IIO_CHAN_INFO_RAW); - if (iio_channel_has_info(pchan, IIO_CHAN_INFO_SCALE)) - chan->info_mask_separate |= BIT(IIO_CHAN_INFO_SCALE); - - if (iio_channel_has_available(pchan, IIO_CHAN_INFO_RAW)) - chan->info_mask_separate_available |= BIT(IIO_CHAN_INFO_RAW); - - if (state >= mux_control_states(mux->control)) { - dev_err(dev, "too many channels\n"); - return -EINVAL; - } - - chan->channel = state; - - num_ext_info = iio_get_channel_ext_info_count(mux->parent); - if (num_ext_info) { - page = devm_kzalloc(dev, PAGE_SIZE, GFP_KERNEL); - if (!page) - return -ENOMEM; - } child->ext_info_cache = devm_kcalloc(dev, num_ext_info, sizeof(*child->ext_info_cache), @@ -318,8 +288,46 @@ static int mux_configure_channel(struct device *dev, struct mux *mux, child->ext_info_cache[i].size = ret; } - if (page) - devm_kfree(dev, page); + return 0; +} + +static int mux_configure_channel(struct device *dev, struct mux *mux, u32 state, + const char *label, int idx) +{ + struct iio_chan_spec *chan = &mux->chan[idx]; + struct iio_chan_spec const *pchan = mux->parent->channel; + int num_ext_info; + int ret; + + chan->indexed = 1; + chan->output = pchan->output; + chan->datasheet_name = label; + chan->ext_info = mux->ext_info; + + ret = iio_get_channel_type(mux->parent, &chan->type); + if (ret < 0) { + dev_err(dev, "failed to get parent channel type\n"); + return ret; + } + + if (iio_channel_has_info(pchan, IIO_CHAN_INFO_RAW)) + chan->info_mask_separate |= BIT(IIO_CHAN_INFO_RAW); + if (iio_channel_has_info(pchan, IIO_CHAN_INFO_SCALE)) + chan->info_mask_separate |= BIT(IIO_CHAN_INFO_SCALE); + + if (iio_channel_has_available(pchan, IIO_CHAN_INFO_RAW)) + chan->info_mask_separate_available |= BIT(IIO_CHAN_INFO_RAW); + + if (state >= mux_control_states(mux->control)) { + dev_err(dev, "too many channels\n"); + return -EINVAL; + } + + chan->channel = state; + + num_ext_info = iio_get_channel_ext_info_count(mux->parent); + if (num_ext_info) + return mux_configure_chan_ext_info(dev, mux, idx, num_ext_info); return 0; } diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 5376605b69b4..d44ab65c94cb 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1002,7 +1002,7 @@ static int bmp280_preinit(struct bmp280_data *data) * after resetting, the device uses the complete power-on sequence so * it needs to wait for the defined start-up time. */ - fsleep(data->start_up_time); + fsleep(data->start_up_time_us); ret = regmap_read(data->regmap, BMP280_REG_STATUS, ®); if (ret) @@ -1161,7 +1161,7 @@ const struct bmp280_chip_info bmp280_chip_info = { .chip_id = bmp280_chip_ids, .num_chip_id = ARRAY_SIZE(bmp280_chip_ids), .regmap_config = &bmp280_regmap_config, - .start_up_time = 2000, + .start_up_time_us = 2000, .channels = bmp280_channels, .num_channels = ARRAY_SIZE(bmp280_channels), .avail_scan_masks = bmp280_avail_scan_masks, @@ -1347,7 +1347,7 @@ const struct bmp280_chip_info bme280_chip_info = { .chip_id = bme280_chip_ids, .num_chip_id = ARRAY_SIZE(bme280_chip_ids), .regmap_config = &bme280_regmap_config, - .start_up_time = 2000, + .start_up_time_us = 2000, .channels = bme280_channels, .num_channels = ARRAY_SIZE(bme280_channels), .avail_scan_masks = bme280_avail_scan_masks, @@ -1414,7 +1414,7 @@ static int bmp380_cmd(struct bmp280_data *data, u8 cmd) return ret; } /* Wait for 2ms for command to be processed */ - usleep_range(data->start_up_time, data->start_up_time + 100); + fsleep(data->start_up_time_us); /* Check for command processing error */ ret = regmap_read(data->regmap, BMP380_REG_ERROR, ®); if (ret) { @@ -1806,7 +1806,7 @@ static int bmp380_chip_config(struct bmp280_data *data) * formula in datasheet section 3.9.2 with an offset of ~+15% * as it seen as well in table 3.9.1. */ - msleep(150); + fsleep(150 * USEC_PER_MSEC); /* Check config error flag */ ret = regmap_read(data->regmap, BMP380_REG_ERROR, &tmp); @@ -1957,7 +1957,7 @@ const struct bmp280_chip_info bmp380_chip_info = { .num_chip_id = ARRAY_SIZE(bmp380_chip_ids), .regmap_config = &bmp380_regmap_config, .spi_read_extra_byte = true, - .start_up_time = 2000, + .start_up_time_us = 2000, .channels = bmp380_channels, .num_channels = ARRAY_SIZE(bmp380_channels), .avail_scan_masks = bmp280_avail_scan_masks, @@ -2006,7 +2006,8 @@ static int bmp580_soft_reset(struct bmp280_data *data) dev_err(data->dev, "failed to send reset command to device\n"); return ret; } - usleep_range(2000, 2500); + /* From datasheet's table 4: electrical characteristics */ + fsleep(2000); /* Dummy read of chip_id */ ret = regmap_read(data->regmap, BMP580_REG_CHIP_ID, ®); @@ -2208,7 +2209,7 @@ static int bmp580_nvmem_read_impl(void *priv, unsigned int offset, void *val, goto exit; } /* Wait standby transition time */ - usleep_range(2500, 3000); + fsleep(2500); while (bytes >= sizeof(*dst)) { addr = bmp580_nvmem_addrs[offset / sizeof(*dst)]; @@ -2274,7 +2275,7 @@ static int bmp580_nvmem_write_impl(void *priv, unsigned int offset, void *val, goto exit; } /* Wait standby transition time */ - usleep_range(2500, 3000); + fsleep(2500); while (bytes >= sizeof(*buf)) { addr = bmp580_nvmem_addrs[offset / sizeof(*buf)]; @@ -2458,7 +2459,7 @@ static int bmp580_chip_config(struct bmp280_data *data) return ret; } /* From datasheet's table 4: electrical characteristics */ - usleep_range(2500, 3000); + fsleep(2500); /* Set default DSP mode settings */ reg_val = FIELD_PREP(BMP580_DSP_COMP_MASK, BMP580_DSP_PRESS_TEMP_COMP_EN) | @@ -2649,7 +2650,7 @@ const struct bmp280_chip_info bmp580_chip_info = { .chip_id = bmp580_chip_ids, .num_chip_id = ARRAY_SIZE(bmp580_chip_ids), .regmap_config = &bmp580_regmap_config, - .start_up_time = 2000, + .start_up_time_us = 2000, .channels = bmp580_channels, .num_channels = ARRAY_SIZE(bmp580_channels), .avail_scan_masks = bmp280_avail_scan_masks, @@ -2720,7 +2721,7 @@ static int bmp180_wait_for_eoc(struct bmp280_data *data, u8 ctrl_meas) delay_us = conversion_time_max[data->oversampling_press]; - usleep_range(delay_us, delay_us + 1000); + fsleep(delay_us); } ret = regmap_read(data->regmap, BMP280_REG_CTRL_MEAS, &ctrl); @@ -2988,7 +2989,7 @@ const struct bmp280_chip_info bmp180_chip_info = { .chip_id = bmp180_chip_ids, .num_chip_id = ARRAY_SIZE(bmp180_chip_ids), .regmap_config = &bmp180_regmap_config, - .start_up_time = 2000, + .start_up_time_us = 2000, .channels = bmp280_channels, .num_channels = ARRAY_SIZE(bmp280_channels), .avail_scan_masks = bmp280_avail_scan_masks, @@ -3066,7 +3067,7 @@ const struct bmp280_chip_info bmp085_chip_info = { .chip_id = bmp180_chip_ids, .num_chip_id = ARRAY_SIZE(bmp180_chip_ids), .regmap_config = &bmp180_regmap_config, - .start_up_time = 2000, + .start_up_time_us = 2000, .channels = bmp280_channels, .num_channels = ARRAY_SIZE(bmp280_channels), .avail_scan_masks = bmp280_avail_scan_masks, @@ -3175,7 +3176,7 @@ int bmp280_common_probe(struct device *dev, data->oversampling_temp = chip_info->oversampling_temp_default; data->iir_filter_coeff = chip_info->iir_filter_coeff_default; data->sampling_freq = chip_info->sampling_freq_default; - data->start_up_time = chip_info->start_up_time; + data->start_up_time_us = chip_info->start_up_time_us; /* Bring up regulators */ regulator_bulk_set_supply_names(data->supplies, @@ -3201,7 +3202,7 @@ int bmp280_common_probe(struct device *dev, return ret; /* Wait to make sure we started up properly */ - usleep_range(data->start_up_time, data->start_up_time + 100); + fsleep(data->start_up_time_us); /* Bring chip out of reset if there is an assigned GPIO line */ gpiod = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); @@ -3287,7 +3288,7 @@ int bmp280_common_probe(struct device *dev, * Set autosuspend to two orders of magnitude larger than the * start-up time. */ - pm_runtime_set_autosuspend_delay(dev, data->start_up_time / 10); + pm_runtime_set_autosuspend_delay(dev, data->start_up_time_us / 10); pm_runtime_use_autosuspend(dev); pm_runtime_put(dev); @@ -3306,7 +3307,7 @@ static int bmp280_runtime_suspend(struct device *dev) data->chip_info->set_mode(data, BMP280_SLEEP); - fsleep(data->start_up_time); + fsleep(data->start_up_time_us); return regulator_bulk_disable(BMP280_NUM_SUPPLIES, data->supplies); } @@ -3320,7 +3321,7 @@ static int bmp280_runtime_resume(struct device *dev) if (ret) return ret; - usleep_range(data->start_up_time, data->start_up_time + 100); + fsleep(data->start_up_time_us); ret = data->chip_info->chip_config(data); if (ret) diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h index 2df1175b6b85..5b2ee1d0ee46 100644 --- a/drivers/iio/pressure/bmp280.h +++ b/drivers/iio/pressure/bmp280.h @@ -434,7 +434,7 @@ struct bmp280_data { struct bmp380_calib bmp380; } calib; struct regulator_bulk_data supplies[BMP280_NUM_SUPPLIES]; - unsigned int start_up_time; /* in microseconds */ + unsigned int start_up_time_us; /* log of base 2 of oversampling rate */ u8 oversampling_press; @@ -470,8 +470,8 @@ struct bmp280_data { /* Sensor data buffer */ u8 buf[BME280_BURST_READ_BYTES]; /* Calibration data buffers */ - __le16 bmp280_cal_buf[BMP280_CONTIGUOUS_CALIB_REGS / 2]; - __be16 bmp180_cal_buf[BMP180_REG_CALIB_COUNT / 2]; + __le16 bmp280_cal_buf[BMP280_CONTIGUOUS_CALIB_REGS / sizeof(__le16)]; + __be16 bmp180_cal_buf[BMP180_REG_CALIB_COUNT / sizeof(__be16)]; u8 bme280_humid_cal_buf[BME280_CONTIGUOUS_CALIB_REGS]; u8 bmp380_cal_buf[BMP380_CALIB_REG_COUNT]; /* Miscellaneous, endianness-aware data buffers */ @@ -490,7 +490,7 @@ struct bmp280_chip_info { const struct iio_chan_spec *channels; int num_channels; - unsigned int start_up_time; + unsigned int start_up_time_us; const unsigned long *avail_scan_masks; const int *oversampling_temp_avail; diff --git a/drivers/iio/pressure/hsc030pa.h b/drivers/iio/pressure/hsc030pa.h index 9b40f46f575f..5db46784f4c6 100644 --- a/drivers/iio/pressure/hsc030pa.h +++ b/drivers/iio/pressure/hsc030pa.h @@ -58,7 +58,7 @@ struct hsc_data { s32 p_offset_dec; struct { __be16 chan[2]; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; u8 buffer[HSC_REG_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/pressure/ms5611_core.c b/drivers/iio/pressure/ms5611_core.c index 056c8271c49d..00c077b2a2a4 100644 --- a/drivers/iio/pressure/ms5611_core.c +++ b/drivers/iio/pressure/ms5611_core.c @@ -213,7 +213,7 @@ static irqreturn_t ms5611_trigger_handler(int irq, void *p) /* Ensure buffer elements are naturally aligned */ struct { s32 channels[2]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; int ret; diff --git a/drivers/iio/pressure/rohm-bm1390.c b/drivers/iio/pressure/rohm-bm1390.c index f24d9f927681..9c1197f0e742 100644 --- a/drivers/iio/pressure/rohm-bm1390.c +++ b/drivers/iio/pressure/rohm-bm1390.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -138,7 +139,7 @@ enum { struct bm1390_data_buf { u32 pressure; __be16 temp; - s64 ts __aligned(8); + aligned_s64 ts; }; /* BM1390 has FIFO for 4 pressure samples */ @@ -263,14 +264,14 @@ static int bm1390_read_data(struct bm1390_data *data, { int ret, warn; - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); /* * We use 'continuous mode' even for raw read because according to the * data-sheet an one-shot mode can't be used with IIR filter. */ ret = bm1390_meas_set(data, BM1390_MEAS_MODE_CONTINUOUS); if (ret) - goto unlock_out; + return ret; switch (chan->type) { case IIO_PRESSURE: @@ -287,10 +288,8 @@ static int bm1390_read_data(struct bm1390_data *data, warn = bm1390_meas_set(data, BM1390_MEAS_MODE_STOP); if (warn) dev_warn(data->dev, "Failed to stop measurement (%d)\n", warn); -unlock_out: - mutex_unlock(&data->mutex); - return ret; + return 0; } static int bm1390_read_raw(struct iio_dev *idev, @@ -543,38 +542,33 @@ static int bm1390_fifo_enable(struct iio_dev *idev) if (data->irq <= 0) return -EINVAL; - mutex_lock(&data->mutex); - if (data->trigger_enabled) { - ret = -EBUSY; - goto unlock_out; - } + guard(mutex)(&data->mutex); + + if (data->trigger_enabled) + return -EBUSY; /* Update watermark to HW */ ret = bm1390_fifo_set_wmi(data); if (ret) - goto unlock_out; + return ret; /* Enable WMI_IRQ */ ret = regmap_set_bits(data->regmap, BM1390_REG_MODE_CTRL, BM1390_MASK_WMI_EN); if (ret) - goto unlock_out; + return ret; /* Enable FIFO */ ret = regmap_set_bits(data->regmap, BM1390_REG_FIFO_CTRL, BM1390_MASK_FIFO_EN); if (ret) - goto unlock_out; + return ret; data->state = BM1390_STATE_FIFO; data->old_timestamp = iio_get_time_ns(idev); - ret = bm1390_meas_set(data, BM1390_MEAS_MODE_CONTINUOUS); -unlock_out: - mutex_unlock(&data->mutex); - - return ret; + return bm1390_meas_set(data, BM1390_MEAS_MODE_CONTINUOUS); } static int bm1390_fifo_disable(struct iio_dev *idev) @@ -584,27 +578,22 @@ static int bm1390_fifo_disable(struct iio_dev *idev) msleep(1); - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); ret = bm1390_meas_set(data, BM1390_MEAS_MODE_STOP); if (ret) - goto unlock_out; + return ret; /* Disable FIFO */ ret = regmap_clear_bits(data->regmap, BM1390_REG_FIFO_CTRL, BM1390_MASK_FIFO_EN); if (ret) - goto unlock_out; + return ret; data->state = BM1390_STATE_SAMPLE; /* Disable WMI_IRQ */ - ret = regmap_clear_bits(data->regmap, BM1390_REG_MODE_CTRL, + return regmap_clear_bits(data->regmap, BM1390_REG_MODE_CTRL, BM1390_MASK_WMI_EN); - -unlock_out: - mutex_unlock(&data->mutex); - - return ret; } static int bm1390_buffer_postenable(struct iio_dev *idev) @@ -688,25 +677,24 @@ static irqreturn_t bm1390_irq_thread_handler(int irq, void *private) { struct iio_dev *idev = private; struct bm1390_data *data = iio_priv(idev); - int ret = IRQ_NONE; - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); if (data->trigger_enabled) { iio_trigger_poll_nested(data->trig); - ret = IRQ_HANDLED; - } else if (data->state == BM1390_STATE_FIFO) { + return IRQ_HANDLED; + } + + if (data->state == BM1390_STATE_FIFO) { int ok; ok = __bm1390_fifo_flush(idev, BM1390_FIFO_LENGTH, data->timestamp); if (ok > 0) - ret = IRQ_HANDLED; + return IRQ_HANDLED; } - mutex_unlock(&data->mutex); - - return ret; + return IRQ_NONE; } static int bm1390_set_drdy_irq(struct bm1390_data *data, bool en) @@ -722,17 +710,16 @@ static int bm1390_trigger_set_state(struct iio_trigger *trig, bool state) { struct bm1390_data *data = iio_trigger_get_drvdata(trig); - int ret = 0; + int ret; - mutex_lock(&data->mutex); + guard(mutex)(&data->mutex); if (data->trigger_enabled == state) - goto unlock_out; + return 0; if (data->state == BM1390_STATE_FIFO) { dev_warn(data->dev, "Can't set trigger when FIFO enabled\n"); - ret = -EBUSY; - goto unlock_out; + return -EBUSY; } data->trigger_enabled = state; @@ -740,13 +727,13 @@ static int bm1390_trigger_set_state(struct iio_trigger *trig, if (state) { ret = bm1390_meas_set(data, BM1390_MEAS_MODE_CONTINUOUS); if (ret) - goto unlock_out; + return ret; } else { int dummy; ret = bm1390_meas_set(data, BM1390_MEAS_MODE_STOP); if (ret) - goto unlock_out; + return ret; /* * We need to read the status register in order to ACK the @@ -758,12 +745,7 @@ static int bm1390_trigger_set_state(struct iio_trigger *trig, dev_warn(data->dev, "status read failed\n"); } - ret = bm1390_set_drdy_irq(data, state); - -unlock_out: - mutex_unlock(&data->mutex); - - return ret; + return bm1390_set_drdy_irq(data, state); } static const struct iio_trigger_ops bm1390_trigger_ops = { diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c index 2adea84f5b4d..9db1c94dfc18 100644 --- a/drivers/iio/pressure/zpa2326.c +++ b/drivers/iio/pressure/zpa2326.c @@ -586,6 +586,8 @@ static int zpa2326_fill_sample_buffer(struct iio_dev *indio_dev, } sample; int err; + memset(&sample, 0, sizeof(sample)); + if (test_bit(0, indio_dev->active_scan_mask)) { /* Get current pressure from hardware FIFO. */ err = zpa2326_dequeue_pressure(indio_dev, &sample.pressure); diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c index 96fa97451cbf..9d3caf2bef18 100644 --- a/drivers/iio/proximity/as3935.c +++ b/drivers/iio/proximity/as3935.c @@ -63,7 +63,7 @@ struct as3935_state { /* Ensure timestamp is naturally aligned */ struct { u8 chan; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; u8 buf[2] __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/proximity/aw96103.c b/drivers/iio/proximity/aw96103.c index cdd254da9e50..3472a2c36e44 100644 --- a/drivers/iio/proximity/aw96103.c +++ b/drivers/iio/proximity/aw96103.c @@ -433,7 +433,7 @@ static int aw96103_write_event_config(struct iio_dev *indio_dev, state ? BIT(chan->channel) : 0); } -static struct iio_info iio_info = { +static const struct iio_info iio_info = { .read_raw = aw96103_read_raw, .read_event_value = aw96103_read_event_val, .write_event_value = aw96103_write_event_val, diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c index 4021feb7a7ac..e092a935dbac 100644 --- a/drivers/iio/proximity/hx9023s.c +++ b/drivers/iio/proximity/hx9023s.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -100,6 +101,17 @@ #define HX9023S_INTERRUPT_MASK GENMASK(9, 0) #define HX9023S_PROX_DEBOUNCE_MASK GENMASK(3, 0) +#define FW_VER_OFFSET 2 +#define FW_REG_CNT_OFFSET 3 +#define FW_DATA_OFFSET 16 + +struct hx9023s_bin { + u16 reg_count; + u16 fw_size; + u8 fw_ver; + u8 data[] __counted_by(fw_size); +}; + struct hx9023s_ch_data { s16 raw; /* Raw Data*/ s16 lp; /* Low Pass Filter Data*/ @@ -134,7 +146,7 @@ struct hx9023s_data { struct { __le16 channels[HX9023S_CH_NUM]; - s64 ts __aligned(8); + aligned_s64 ts; } buffer; /* @@ -998,6 +1010,77 @@ static int hx9023s_id_check(struct iio_dev *indio_dev) return 0; } +static int hx9023s_bin_load(struct hx9023s_data *data, struct hx9023s_bin *bin) +{ + u8 *cfg_start = bin->data + FW_DATA_OFFSET; + u8 addr, val; + u16 i; + int ret; + + for (i = 0; i < bin->reg_count; i++) { + addr = cfg_start[i * 2]; + val = cfg_start[i * 2 + 1]; + ret = regmap_write(data->regmap, addr, val); + if (ret < 0) + return ret; + } + + return 0; +} + +static int hx9023s_send_cfg(const struct firmware *fw, struct hx9023s_data *data) +{ + struct hx9023s_bin *bin __free(kfree) = + kzalloc(fw->size + sizeof(*bin), GFP_KERNEL); + if (!bin) + return -ENOMEM; + + memcpy(bin->data, fw->data, fw->size); + release_firmware(fw); + + bin->fw_size = fw->size; + bin->fw_ver = bin->data[FW_VER_OFFSET]; + bin->reg_count = get_unaligned_le16(bin->data + FW_REG_CNT_OFFSET); + + return hx9023s_bin_load(data, bin); +} + +static void hx9023s_cfg_update(const struct firmware *fw, void *context) +{ + struct hx9023s_data *data = context; + struct device *dev = regmap_get_device(data->regmap); + int ret; + + if (!fw || !fw->data) { + dev_warn(dev, "No firmware\n"); + goto no_fw; + } + + ret = hx9023s_send_cfg(fw, data); + if (ret) { + dev_warn(dev, "Firmware update failed: %d\n", ret); + goto no_fw; + } + + ret = regcache_sync(data->regmap); + if (ret) + dev_err(dev, "regcache sync failed\n"); + + return; + +no_fw: + ret = regmap_multi_reg_write(data->regmap, hx9023s_reg_init_list, + ARRAY_SIZE(hx9023s_reg_init_list)); + if (ret) { + dev_err(dev, "Error loading default configuration\n"); + return; + } + + ret = regcache_sync(data->regmap); + if (ret) + dev_err(dev, "regcache sync failed\n"); +} + static int hx9023s_probe(struct i2c_client *client) { struct device *dev = &client->dev; @@ -1036,18 +1119,14 @@ static int hx9023s_probe(struct i2c_client *client) indio_dev->modes = INDIO_DIRECT_MODE; i2c_set_clientdata(client, indio_dev); - ret = regmap_multi_reg_write(data->regmap, hx9023s_reg_init_list, - ARRAY_SIZE(hx9023s_reg_init_list)); - if (ret) - return dev_err_probe(dev, ret, "device init failed\n"); - ret = hx9023s_ch_cfg(data); if (ret) return dev_err_probe(dev, ret, "channel config failed\n"); - ret = regcache_sync(data->regmap); + ret = request_firmware_nowait(THIS_MODULE, true, "hx9023s.bin", dev, + GFP_KERNEL, data, hx9023s_cfg_update); if (ret) - return dev_err_probe(dev, ret, "regcache sync failed\n"); + return dev_err_probe(dev, ret, "reg config failed\n"); if (client->irq) { ret = devm_request_threaded_irq(dev, client->irq, diff --git a/drivers/iio/proximity/mb1232.c b/drivers/iio/proximity/mb1232.c index 614e65cb9d42..cfc75d001f20 100644 --- a/drivers/iio/proximity/mb1232.c +++ b/drivers/iio/proximity/mb1232.c @@ -45,7 +45,7 @@ struct mb1232_data { /* Ensure correct alignment of data to push to IIO buffer */ struct { s16 distance; - s64 ts __aligned(8); + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c index 5c959730aecd..f3d054b06b4c 100644 --- a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c +++ b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c @@ -47,7 +47,7 @@ struct lidar_data { /* Ensure timestamp is naturally aligned */ struct { u16 chan; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; }; diff --git a/drivers/iio/proximity/srf08.c b/drivers/iio/proximity/srf08.c index a75ea5042876..86cab113ef3d 100644 --- a/drivers/iio/proximity/srf08.c +++ b/drivers/iio/proximity/srf08.c @@ -66,7 +66,7 @@ struct srf08_data { /* Ensure timestamp is naturally aligned */ struct { s16 chan; - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; /* Sensor-Type */ diff --git a/drivers/iio/proximity/sx_common.h b/drivers/iio/proximity/sx_common.h index fb14e6f06a6d..259b5c695233 100644 --- a/drivers/iio/proximity/sx_common.h +++ b/drivers/iio/proximity/sx_common.h @@ -125,7 +125,7 @@ struct sx_common_data { /* Ensure correct alignment of timestamp when present. */ struct { __be16 channels[SX_COMMON_MAX_NUM_CHANNELS]; - s64 ts __aligned(8); + aligned_s64 ts; } buffer; unsigned int suspend_ctrl; diff --git a/drivers/iio/resolver/ad2s1210.c b/drivers/iio/resolver/ad2s1210.c index a414eef12e5e..b681129a99b6 100644 --- a/drivers/iio/resolver/ad2s1210.c +++ b/drivers/iio/resolver/ad2s1210.c @@ -164,7 +164,7 @@ struct ad2s1210_state { struct { __be16 chan[2]; /* Ensure timestamp is naturally aligned. */ - s64 timestamp __aligned(8); + aligned_s64 timestamp; } scan; /** SPI transmit buffer. */ u8 rx[2]; diff --git a/drivers/iio/temperature/tmp006.c b/drivers/iio/temperature/tmp006.c index 0c844137d7aa..1998047a1f24 100644 --- a/drivers/iio/temperature/tmp006.c +++ b/drivers/iio/temperature/tmp006.c @@ -248,10 +248,12 @@ static irqreturn_t tmp006_trigger_handler(int irq, void *p) struct tmp006_data *data = iio_priv(indio_dev); struct { s16 channels[2]; - s64 ts __aligned(8); + aligned_s64 ts; } scan; s32 ret; + memset(&scan, 0, sizeof(scan)); + ret = i2c_smbus_read_word_data(data->client, TMP006_VOBJECT); if (ret < 0) goto err; diff --git a/drivers/iio/test/Kconfig b/drivers/iio/test/Kconfig index 33cca49c8058..7a181cac3cc9 100644 --- a/drivers/iio/test/Kconfig +++ b/drivers/iio/test/Kconfig @@ -5,7 +5,7 @@ # Keep in alphabetical order config IIO_GTS_KUNIT_TEST - tristate "Test IIO formatting functions" if !KUNIT_ALL_TESTS + tristate "Test IIO gain-time-scale helpers" if !KUNIT_ALL_TESTS depends on KUNIT select IIO_GTS_HELPER select TEST_KUNIT_DEVICE_HELPERS diff --git a/drivers/iio/test/iio-test-rescale.c b/drivers/iio/test/iio-test-rescale.c index cbf13337ed1f..bbc6a2e1c2c1 100644 --- a/drivers/iio/test/iio-test-rescale.c +++ b/drivers/iio/test/iio-test-rescale.c @@ -652,6 +652,8 @@ static void iio_rescale_test_scale(struct kunit *test) int rel_ppm; int ret; + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buff); + rescale.numerator = t->numerator; rescale.denominator = t->denominator; rescale.offset = t->offset; @@ -681,6 +683,8 @@ static void iio_rescale_test_offset(struct kunit *test) int values[2]; int ret; + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buff_off); + rescale.numerator = t->numerator; rescale.denominator = t->denominator; rescale.offset = t->offset; diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c index bb60b2d7b2ec..e41cb741253b 100644 --- a/drivers/iio/trigger/stm32-timer-trigger.c +++ b/drivers/iio/trigger/stm32-timer-trigger.c @@ -38,6 +38,9 @@ static const void *triggers_table[][MAX_TRIGGERS] = { { TIM15_TRGO,}, { TIM16_OC1,}, { TIM17_OC1,}, + { }, /* timer 18 */ + { }, /* timer 19 */ + { TIM20_TRGO, TIM20_TRGO2, TIM20_OC1, TIM20_OC2, TIM20_OC3, }, }; /* List the triggers accepted by each timer */ @@ -119,7 +122,7 @@ static int stm32_timer_start(struct stm32_timer_trigger *priv, unsigned int frequency) { unsigned long long prd, div; - int prescaler = 0; + int prescaler = 0, ret; u32 ccer; /* Period and prescaler values depends of clock rate */ @@ -150,10 +153,12 @@ static int stm32_timer_start(struct stm32_timer_trigger *priv, if (ccer & TIM_CCER_CCXE) return -EBUSY; - mutex_lock(&priv->lock); + guard(mutex)(&priv->lock); if (!priv->enabled) { priv->enabled = true; - clk_enable(priv->clk); + ret = clk_enable(priv->clk); + if (ret) + return ret; } regmap_write(priv->regmap, TIM_PSC, prescaler); @@ -173,7 +178,6 @@ static int stm32_timer_start(struct stm32_timer_trigger *priv, /* Enable controller */ regmap_set_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN); - mutex_unlock(&priv->lock); return 0; } @@ -307,7 +311,7 @@ static ssize_t stm32_tt_store_master_mode(struct device *dev, struct stm32_timer_trigger *priv = dev_get_drvdata(dev); struct iio_trigger *trig = to_iio_trigger(dev); u32 mask, shift, master_mode_max; - int i; + int i, ret; if (stm32_timer_is_trgo2_name(trig->name)) { mask = TIM_CR2_MMS2; @@ -322,15 +326,16 @@ static ssize_t stm32_tt_store_master_mode(struct device *dev, for (i = 0; i <= master_mode_max; i++) { if (!strncmp(master_mode_table[i], buf, strlen(master_mode_table[i]))) { - mutex_lock(&priv->lock); + guard(mutex)(&priv->lock); if (!priv->enabled) { /* Clock should be enabled first */ priv->enabled = true; - clk_enable(priv->clk); + ret = clk_enable(priv->clk); + if (ret) + return ret; } regmap_update_bits(priv->regmap, TIM_CR2, mask, i << shift); - mutex_unlock(&priv->lock); return len; } } @@ -482,6 +487,7 @@ static int stm32_counter_write_raw(struct iio_dev *indio_dev, int val, int val2, long mask) { struct stm32_timer_trigger *priv = iio_priv(indio_dev); + int ret; switch (mask) { case IIO_CHAN_INFO_RAW: @@ -491,12 +497,14 @@ static int stm32_counter_write_raw(struct iio_dev *indio_dev, /* fixed scale */ return -EINVAL; - case IIO_CHAN_INFO_ENABLE: - mutex_lock(&priv->lock); + case IIO_CHAN_INFO_ENABLE: { + guard(mutex)(&priv->lock); if (val) { if (!priv->enabled) { priv->enabled = true; - clk_enable(priv->clk); + ret = clk_enable(priv->clk); + if (ret) + return ret; } regmap_set_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN); } else { @@ -506,11 +514,12 @@ static int stm32_counter_write_raw(struct iio_dev *indio_dev, clk_disable(priv->clk); } } - mutex_unlock(&priv->lock); + return 0; } - - return -EINVAL; + default: + return -EINVAL; + } } static int stm32_counter_validate_trigger(struct iio_dev *indio_dev, @@ -602,6 +611,7 @@ static int stm32_set_enable_mode(struct iio_dev *indio_dev, { struct stm32_timer_trigger *priv = iio_priv(indio_dev); int sms = stm32_enable_mode2sms(mode); + int ret; if (sms < 0) return sms; @@ -609,12 +619,15 @@ static int stm32_set_enable_mode(struct iio_dev *indio_dev, * Triggered mode sets CEN bit automatically by hardware. So, first * enable counter clock, so it can use it. Keeps it in sync with CEN. */ - mutex_lock(&priv->lock); - if (sms == 6 && !priv->enabled) { - clk_enable(priv->clk); - priv->enabled = true; + scoped_guard(mutex, &priv->lock) { + if (sms == 6 && !priv->enabled) { + ret = clk_enable(priv->clk); + if (ret) + return ret; + + priv->enabled = true; + } } - mutex_unlock(&priv->lock); regmap_update_bits(priv->regmap, TIM_SMCR, TIM_SMCR_SMS, sms); @@ -781,7 +794,7 @@ static int stm32_timer_trigger_probe(struct platform_device *pdev) return -EINVAL; /* Create an IIO device only if we have triggers to be validated */ - if (*cfg->valids_table[index]) + if (cfg->valids_table && *cfg->valids_table[index]) priv = stm32_setup_counter_device(dev); else priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -794,7 +807,8 @@ static int stm32_timer_trigger_probe(struct platform_device *pdev) priv->clk = ddata->clk; priv->max_arr = ddata->max_arr; priv->triggers = triggers_table[index]; - priv->valids = cfg->valids_table[index]; + if (cfg->valids_table && *cfg->valids_table[index]) + priv->valids = cfg->valids_table[index]; stm32_timer_detect_trgo2(priv); mutex_init(&priv->lock); @@ -886,6 +900,16 @@ static const struct stm32_timer_trigger_cfg stm32h7_timer_trg_cfg = { .num_valids_table = ARRAY_SIZE(stm32h7_valids_table), }; +static const struct stm32_timer_trigger_cfg stm32mp25_timer_trg_cfg = { + /* + * valids_table not used: counter framework is now superseding the deprecated IIO + * counter interface (IIO_COUNT), so don't support it. num_valids_table is only + * kept here to register the IIO HW triggers. valids_table should be moved at some + * point to the stm32-timer-cnt driver instead. + */ + .num_valids_table = ARRAY_SIZE(triggers_table), +}; + static const struct of_device_id stm32_trig_of_match[] = { { .compatible = "st,stm32-timer-trigger", @@ -893,6 +917,9 @@ static const struct of_device_id stm32_trig_of_match[] = { }, { .compatible = "st,stm32h7-timer-trigger", .data = (void *)&stm32h7_timer_trg_cfg, + }, { + .compatible = "st,stm32mp25-timer-trigger", + .data = (void *)&stm32mp25_timer_trg_cfg, }, { /* end node */ }, }; diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index b7c078b7f7cf..f8413f8a9f26 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -1127,41 +1127,6 @@ err: } EXPORT_SYMBOL(ib_find_cached_pkey); -int ib_find_exact_cached_pkey(struct ib_device *device, u32 port_num, - u16 pkey, u16 *index) -{ - struct ib_pkey_cache *cache; - unsigned long flags; - int i; - int ret = -ENOENT; - - if (!rdma_is_port_valid(device, port_num)) - return -EINVAL; - - read_lock_irqsave(&device->cache_lock, flags); - - cache = device->port_data[port_num].cache.pkey; - if (!cache) { - ret = -EINVAL; - goto err; - } - - *index = -1; - - for (i = 0; i < cache->table_len; ++i) - if (cache->table[i] == pkey) { - *index = i; - ret = 0; - break; - } - -err: - read_unlock_irqrestore(&device->cache_lock, flags); - - return ret; -} -EXPORT_SYMBOL(ib_find_exact_cached_pkey); - int ib_get_cached_lmc(struct ib_device *device, u32 port_num, u8 *lmc) { unsigned long flags; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 64ace0b968f0..91db10515d74 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -690,6 +690,7 @@ cma_validate_port(struct ib_device *device, u32 port, int bound_if_index = dev_addr->bound_dev_if; int dev_type = dev_addr->dev_type; struct net_device *ndev = NULL; + struct net_device *pdev = NULL; if (!rdma_dev_access_netns(device, id_priv->id.route.addr.dev_addr.net)) goto out; @@ -714,6 +715,21 @@ cma_validate_port(struct ib_device *device, u32 port, rcu_read_lock(); ndev = rcu_dereference(sgid_attr->ndev); + if (ndev->ifindex != bound_if_index) { + pdev = dev_get_by_index_rcu(dev_addr->net, bound_if_index); + if (pdev) { + if (is_vlan_dev(pdev)) { + pdev = vlan_dev_real_dev(pdev); + if (ndev->ifindex == pdev->ifindex) + bound_if_index = pdev->ifindex; + } + if (is_vlan_dev(ndev)) { + pdev = vlan_dev_real_dev(ndev); + if (bound_if_index == pdev->ifindex) + bound_if_index = ndev->ifindex; + } + } + } if (!net_eq(dev_net(ndev), dev_addr->net) || ndev->ifindex != bound_if_index) { rdma_put_gid_attr(sgid_attr); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index ca9b956c034d..0ded91f056f3 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -209,23 +209,6 @@ static void __ibdev_printk(const char *level, const struct ib_device *ibdev, printk("%s(NULL ib_device): %pV", level, vaf); } -void ibdev_printk(const char *level, const struct ib_device *ibdev, - const char *format, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, format); - - vaf.fmt = format; - vaf.va = &args; - - __ibdev_printk(level, ibdev, &vaf); - - va_end(args); -} -EXPORT_SYMBOL(ibdev_printk); - #define define_ibdev_printk_level(func, level) \ void func(const struct ib_device *ibdev, const char *fmt, ...) \ { \ @@ -2295,6 +2278,33 @@ struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, } EXPORT_SYMBOL(ib_device_get_netdev); +/** + * ib_query_netdev_port - Query the port number of a net_device + * associated with an ibdev + * @ibdev: IB device + * @ndev: Network device + * @port: IB port the net_device is connected to + */ +int ib_query_netdev_port(struct ib_device *ibdev, struct net_device *ndev, + u32 *port) +{ + struct net_device *ib_ndev; + u32 port_num; + + rdma_for_each_port(ibdev, port_num) { + ib_ndev = ib_device_get_netdev(ibdev, port_num); + if (ndev == ib_ndev) { + *port = port_num; + dev_put(ib_ndev); + return 0; + } + dev_put(ib_ndev); + } + + return -ENOENT; +} +EXPORT_SYMBOL(ib_query_netdev_port); + /** * ib_device_get_by_netdev - Find an IB device associated with a netdev * @ndev: netdev to locate @@ -2761,6 +2771,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) SET_DEVICE_OP(dev_ops, set_vf_guid); SET_DEVICE_OP(dev_ops, set_vf_link_state); SET_DEVICE_OP(dev_ops, ufile_hw_cleanup); + SET_DEVICE_OP(dev_ops, report_port_event); SET_OBJ_SIZE(dev_ops, ib_ah); SET_OBJ_SIZE(dev_ops, ib_counters); @@ -2854,11 +2865,62 @@ static const struct rdma_nl_cbs ibnl_ls_cb_table[RDMA_NL_LS_NUM_OPS] = { }, }; +void ib_dispatch_port_state_event(struct ib_device *ibdev, struct net_device *ndev) +{ + enum ib_port_state curr_state; + struct ib_event ibevent = {}; + u32 port; + + if (ib_query_netdev_port(ibdev, ndev, &port)) + return; + + curr_state = ib_get_curr_port_state(ndev); + + write_lock_irq(&ibdev->cache_lock); + if (ibdev->port_data[port].cache.last_port_state == curr_state) { + write_unlock_irq(&ibdev->cache_lock); + return; + } + ibdev->port_data[port].cache.last_port_state = curr_state; + write_unlock_irq(&ibdev->cache_lock); + + ibevent.event = (curr_state == IB_PORT_DOWN) ? + IB_EVENT_PORT_ERR : IB_EVENT_PORT_ACTIVE; + ibevent.device = ibdev; + ibevent.element.port_num = port; + ib_dispatch_event(&ibevent); +} +EXPORT_SYMBOL(ib_dispatch_port_state_event); + +static void handle_port_event(struct net_device *ndev, unsigned long event) +{ + struct ib_device *ibdev; + + /* Currently, link events in bonding scenarios are still + * reported by drivers that support bonding. + */ + if (netif_is_lag_master(ndev) || netif_is_lag_port(ndev)) + return; + + ibdev = ib_device_get_by_netdev(ndev, RDMA_DRIVER_UNKNOWN); + if (!ibdev) + return; + + if (ibdev->ops.report_port_event) { + ibdev->ops.report_port_event(ibdev, ndev, event); + goto put_ibdev; + } + + ib_dispatch_port_state_event(ibdev, ndev); + +put_ibdev: + ib_device_put(ibdev); +}; + static int ib_netdevice_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); - struct net_device *ib_ndev; struct ib_device *ibdev; u32 port; @@ -2868,15 +2930,21 @@ static int ib_netdevice_event(struct notifier_block *this, if (!ibdev) return NOTIFY_DONE; - rdma_for_each_port(ibdev, port) { - ib_ndev = ib_device_get_netdev(ibdev, port); - if (ndev == ib_ndev) - rdma_nl_notify_event(ibdev, port, - RDMA_NETDEV_RENAME_EVENT); - dev_put(ib_ndev); + if (ib_query_netdev_port(ibdev, ndev, &port)) { + ib_device_put(ibdev); + break; } + + rdma_nl_notify_event(ibdev, port, RDMA_NETDEV_RENAME_EVENT); ib_device_put(ibdev); break; + + case NETDEV_UP: + case NETDEV_CHANGE: + case NETDEV_DOWN: + handle_port_event(ndev, event); + break; + default: break; } diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index ff121e59b9c0..cb987ab0177c 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -2833,8 +2833,8 @@ int rdma_nl_notify_event(struct ib_device *device, u32 port_num, enum rdma_nl_notify_event_type type) { struct sk_buff *skb; + int ret = -EMSGSIZE; struct net *net; - int ret = 0; void *nlh; net = read_pnet(&device->coredev.rdma_net); diff --git a/drivers/infiniband/core/ud_header.c b/drivers/infiniband/core/ud_header.c index 64d9c492de64..8d3dfef9ebaa 100644 --- a/drivers/infiniband/core/ud_header.c +++ b/drivers/infiniband/core/ud_header.c @@ -462,86 +462,3 @@ int ib_ud_header_pack(struct ib_ud_header *header, return len; } EXPORT_SYMBOL(ib_ud_header_pack); - -/** - * ib_ud_header_unpack - Unpack UD header struct from wire format - * @header:UD header struct - * @buf:Buffer to pack into - * - * ib_ud_header_pack() unpacks the UD header structure @header from wire - * format in the buffer @buf. - */ -int ib_ud_header_unpack(void *buf, - struct ib_ud_header *header) -{ - ib_unpack(lrh_table, ARRAY_SIZE(lrh_table), - buf, &header->lrh); - buf += IB_LRH_BYTES; - - if (header->lrh.link_version != 0) { - pr_warn("Invalid LRH.link_version %u\n", - header->lrh.link_version); - return -EINVAL; - } - - switch (header->lrh.link_next_header) { - case IB_LNH_IBA_LOCAL: - header->grh_present = 0; - break; - - case IB_LNH_IBA_GLOBAL: - header->grh_present = 1; - ib_unpack(grh_table, ARRAY_SIZE(grh_table), - buf, &header->grh); - buf += IB_GRH_BYTES; - - if (header->grh.ip_version != 6) { - pr_warn("Invalid GRH.ip_version %u\n", - header->grh.ip_version); - return -EINVAL; - } - if (header->grh.next_header != 0x1b) { - pr_warn("Invalid GRH.next_header 0x%02x\n", - header->grh.next_header); - return -EINVAL; - } - break; - - default: - pr_warn("Invalid LRH.link_next_header %u\n", - header->lrh.link_next_header); - return -EINVAL; - } - - ib_unpack(bth_table, ARRAY_SIZE(bth_table), - buf, &header->bth); - buf += IB_BTH_BYTES; - - switch (header->bth.opcode) { - case IB_OPCODE_UD_SEND_ONLY: - header->immediate_present = 0; - break; - case IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE: - header->immediate_present = 1; - break; - default: - pr_warn("Invalid BTH.opcode 0x%02x\n", header->bth.opcode); - return -EINVAL; - } - - if (header->bth.transport_header_version != 0) { - pr_warn("Invalid BTH.transport_header_version %u\n", - header->bth.transport_header_version); - return -EINVAL; - } - - ib_unpack(deth_table, ARRAY_SIZE(deth_table), - buf, &header->deth); - buf += IB_DETH_BYTES; - - if (header->immediate_present) - memcpy(&header->immediate_data, buf, sizeof header->immediate_data); - - return 0; -} -EXPORT_SYMBOL(ib_ud_header_unpack); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 66b02fbf077a..5ad14c39d48c 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -161,7 +161,7 @@ static const void __user *uverbs_request_next_ptr(struct uverbs_req_iter *iter, { const void __user *res = iter->cur; - if (iter->cur + len > iter->end) + if (len > iter->end - iter->cur) return (void __force __user *)ERR_PTR(-ENOSPC); iter->cur += len; return res; @@ -2008,11 +2008,13 @@ static int ib_uverbs_post_send(struct uverbs_attr_bundle *attrs) ret = uverbs_request_start(attrs, &iter, &cmd, sizeof(cmd)); if (ret) return ret; - wqes = uverbs_request_next_ptr(&iter, cmd.wqe_size * cmd.wr_count); + wqes = uverbs_request_next_ptr(&iter, size_mul(cmd.wqe_size, + cmd.wr_count)); if (IS_ERR(wqes)) return PTR_ERR(wqes); - sgls = uverbs_request_next_ptr( - &iter, cmd.sge_count * sizeof(struct ib_uverbs_sge)); + sgls = uverbs_request_next_ptr(&iter, + size_mul(cmd.sge_count, + sizeof(struct ib_uverbs_sge))); if (IS_ERR(sgls)) return PTR_ERR(sgls); ret = uverbs_request_finish(&iter); @@ -2198,11 +2200,11 @@ ib_uverbs_unmarshall_recv(struct uverbs_req_iter *iter, u32 wr_count, if (wqe_size < sizeof(struct ib_uverbs_recv_wr)) return ERR_PTR(-EINVAL); - wqes = uverbs_request_next_ptr(iter, wqe_size * wr_count); + wqes = uverbs_request_next_ptr(iter, size_mul(wqe_size, wr_count)); if (IS_ERR(wqes)) return ERR_CAST(wqes); - sgls = uverbs_request_next_ptr( - iter, sge_count * sizeof(struct ib_uverbs_sge)); + sgls = uverbs_request_next_ptr(iter, size_mul(sge_count, + sizeof(struct ib_uverbs_sge))); if (IS_ERR(sgls)) return ERR_CAST(sgls); ret = uverbs_request_finish(iter); diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index 11a080646916..e803f609ec87 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -171,45 +171,3 @@ void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst, __ib_copy_path_rec_to_user(dst, src); } EXPORT_SYMBOL(ib_copy_path_rec_to_user); - -void ib_copy_path_rec_from_user(struct sa_path_rec *dst, - struct ib_user_path_rec *src) -{ - u32 slid, dlid; - - memset(dst, 0, sizeof(*dst)); - if ((ib_is_opa_gid((union ib_gid *)src->sgid)) || - (ib_is_opa_gid((union ib_gid *)src->dgid))) { - dst->rec_type = SA_PATH_REC_TYPE_OPA; - slid = opa_get_lid_from_gid((union ib_gid *)src->sgid); - dlid = opa_get_lid_from_gid((union ib_gid *)src->dgid); - } else { - dst->rec_type = SA_PATH_REC_TYPE_IB; - slid = ntohs(src->slid); - dlid = ntohs(src->dlid); - } - memcpy(dst->dgid.raw, src->dgid, sizeof dst->dgid); - memcpy(dst->sgid.raw, src->sgid, sizeof dst->sgid); - - sa_path_set_dlid(dst, dlid); - sa_path_set_slid(dst, slid); - sa_path_set_raw_traffic(dst, src->raw_traffic); - dst->flow_label = src->flow_label; - dst->hop_limit = src->hop_limit; - dst->traffic_class = src->traffic_class; - dst->reversible = src->reversible; - dst->numb_path = src->numb_path; - dst->pkey = src->pkey; - dst->sl = src->sl; - dst->mtu_selector = src->mtu_selector; - dst->mtu = src->mtu; - dst->rate_selector = src->rate_selector; - dst->rate = src->rate; - dst->packet_life_time = src->packet_life_time; - dst->preference = src->preference; - dst->packet_life_time_selector = src->packet_life_time_selector; - - /* TODO: No need to set this */ - sa_path_set_dmac_zero(dst); -} -EXPORT_SYMBOL(ib_copy_path_rec_from_user); diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile index 1211f4317a9f..aba96ca9bce5 100644 --- a/drivers/infiniband/hw/Makefile +++ b/drivers/infiniband/hw/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_INFINIBAND_OCRDMA) += ocrdma/ obj-$(CONFIG_INFINIBAND_VMWARE_PVRDMA) += vmw_pvrdma/ obj-$(CONFIG_INFINIBAND_USNIC) += usnic/ obj-$(CONFIG_INFINIBAND_HFI1) += hfi1/ -obj-$(CONFIG_INFINIBAND_HNS) += hns/ +obj-$(CONFIG_INFINIBAND_HNS_HIP08) += hns/ obj-$(CONFIG_INFINIBAND_QEDR) += qedr/ obj-$(CONFIG_INFINIBAND_BNXT_RE) += bnxt_re/ obj-$(CONFIG_INFINIBAND_ERDMA) += erdma/ diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index 2975b11b79bf..b91a85a491d0 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -204,7 +204,7 @@ struct bnxt_re_dev { struct bnxt_re_nq_record *nqr; /* Device Resources */ - struct bnxt_qplib_dev_attr dev_attr; + struct bnxt_qplib_dev_attr *dev_attr; struct bnxt_qplib_ctx qplib_ctx; struct bnxt_qplib_res qplib_res; struct bnxt_qplib_dpi dpi_privileged; @@ -229,6 +229,9 @@ struct bnxt_re_dev { DECLARE_HASHTABLE(srq_hash, MAX_SRQ_HASH_BITS); struct dentry *dbg_root; struct dentry *qp_debugfs; + unsigned long event_bitmap; + struct bnxt_qplib_cc_param cc_param; + struct workqueue_struct *dcb_wq; }; #define to_bnxt_re_dev(ptr, member) \ diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c index 1e63f8091748..3ac47f4e6122 100644 --- a/drivers/infiniband/hw/bnxt_re/hw_counters.c +++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c @@ -37,18 +37,9 @@ * */ -#include #include -#include -#include -#include #include -#include -#include -#include - -#include "bnxt_ulp.h" #include "roce_hsi.h" #include "qplib_res.h" #include "qplib_sp.h" @@ -357,7 +348,7 @@ int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev, goto done; } bnxt_re_copy_err_stats(rdev, stats, err_s); - if (_is_ext_stats_supported(rdev->dev_attr.dev_cap_flags) && + if (_is_ext_stats_supported(rdev->dev_attr->dev_cap_flags) && !rdev->is_virtfn) { rc = bnxt_re_get_ext_stat(rdev, stats); if (rc) { diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 82023394e330..2de101d6e825 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -52,8 +52,6 @@ #include #include -#include "bnxt_ulp.h" - #include "roce_hsi.h" #include "qplib_res.h" #include "qplib_sp.h" @@ -161,7 +159,7 @@ static int __qp_access_flags_to_ib(struct bnxt_qplib_chip_ctx *cctx, u8 qflags) static void bnxt_re_check_and_set_relaxed_ordering(struct bnxt_re_dev *rdev, struct bnxt_qplib_mrw *qplib_mr) { - if (_is_relaxed_ordering_supported(rdev->dev_attr.dev_cap_flags2) && + if (_is_relaxed_ordering_supported(rdev->dev_attr->dev_cap_flags2) && pcie_relaxed_ordering_enabled(rdev->en_dev->pdev)) qplib_mr->flags |= CMDQ_REGISTER_MR_FLAGS_ENABLE_RO; } @@ -186,7 +184,7 @@ int bnxt_re_query_device(struct ib_device *ibdev, struct ib_udata *udata) { struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev); - struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr; + struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr; memset(ib_attr, 0, sizeof(*ib_attr)); memcpy(&ib_attr->fw_ver, dev_attr->fw_ver, @@ -199,7 +197,7 @@ int bnxt_re_query_device(struct ib_device *ibdev, ib_attr->vendor_id = rdev->en_dev->pdev->vendor; ib_attr->vendor_part_id = rdev->en_dev->pdev->device; - ib_attr->hw_ver = rdev->en_dev->pdev->subsystem_device; + ib_attr->hw_ver = rdev->en_dev->pdev->revision; ib_attr->max_qp = dev_attr->max_qp; ib_attr->max_qp_wr = dev_attr->max_qp_wqes; ib_attr->device_cap_flags = @@ -275,7 +273,7 @@ int bnxt_re_query_port(struct ib_device *ibdev, u32 port_num, struct ib_port_attr *port_attr) { struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev); - struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr; + struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr; int rc; memset(port_attr, 0, sizeof(*port_attr)); @@ -333,8 +331,8 @@ void bnxt_re_query_fw_str(struct ib_device *ibdev, char *str) struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev); snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d.%d", - rdev->dev_attr.fw_ver[0], rdev->dev_attr.fw_ver[1], - rdev->dev_attr.fw_ver[2], rdev->dev_attr.fw_ver[3]); + rdev->dev_attr->fw_ver[0], rdev->dev_attr->fw_ver[1], + rdev->dev_attr->fw_ver[2], rdev->dev_attr->fw_ver[3]); } int bnxt_re_query_pkey(struct ib_device *ibdev, u32 port_num, @@ -585,7 +583,7 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd) mr->qplib_mr.pd = &pd->qplib_pd; mr->qplib_mr.type = CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR; mr->qplib_mr.access_flags = __from_ib_access_flags(mr_access_flags); - if (!_is_alloc_mr_unified(rdev->dev_attr.dev_cap_flags)) { + if (!_is_alloc_mr_unified(rdev->dev_attr->dev_cap_flags)) { rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mr->qplib_mr); if (rc) { ibdev_err(&rdev->ibdev, "Failed to alloc fence-HW-MR\n"); @@ -967,13 +965,13 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata) unsigned int flags; int rc; + bnxt_re_debug_rem_qpinfo(rdev, qp); + bnxt_qplib_flush_cqn_wq(&qp->qplib_qp); rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp); - if (rc) { + if (rc) ibdev_err(&rdev->ibdev, "Failed to destroy HW QP"); - return rc; - } if (rdma_is_kernel_res(&qp->ib_qp.res)) { flags = bnxt_re_lock_cqs(qp); @@ -983,11 +981,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata) bnxt_qplib_free_qp_res(&rdev->qplib_res, &qp->qplib_qp); - if (ib_qp->qp_type == IB_QPT_GSI && rdev->gsi_ctx.gsi_sqp) { - rc = bnxt_re_destroy_gsi_sqp(qp); - if (rc) - return rc; - } + if (ib_qp->qp_type == IB_QPT_GSI && rdev->gsi_ctx.gsi_sqp) + bnxt_re_destroy_gsi_sqp(qp); mutex_lock(&rdev->qp_lock); list_del(&qp->list); @@ -998,8 +993,6 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata) else if (qp->qplib_qp.type == CMDQ_CREATE_QP_TYPE_UD) atomic_dec(&rdev->stats.res.ud_qp_count); - bnxt_re_debug_rem_qpinfo(rdev, qp); - ib_umem_release(qp->rumem); ib_umem_release(qp->sumem); @@ -1062,7 +1055,7 @@ static int bnxt_re_setup_swqe_size(struct bnxt_re_qp *qp, rdev = qp->rdev; qplqp = &qp->qplib_qp; sq = &qplqp->sq; - dev_attr = &rdev->dev_attr; + dev_attr = rdev->dev_attr; align = sizeof(struct sq_send_hdr); ilsize = ALIGN(init_attr->cap.max_inline_data, align); @@ -1282,7 +1275,7 @@ static int bnxt_re_init_rq_attr(struct bnxt_re_qp *qp, rdev = qp->rdev; qplqp = &qp->qplib_qp; rq = &qplqp->rq; - dev_attr = &rdev->dev_attr; + dev_attr = rdev->dev_attr; if (init_attr->srq) { struct bnxt_re_srq *srq; @@ -1319,7 +1312,7 @@ static void bnxt_re_adjust_gsi_rq_attr(struct bnxt_re_qp *qp) rdev = qp->rdev; qplqp = &qp->qplib_qp; - dev_attr = &rdev->dev_attr; + dev_attr = rdev->dev_attr; if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) { qplqp->rq.max_sge = dev_attr->max_qp_sges; @@ -1345,7 +1338,7 @@ static int bnxt_re_init_sq_attr(struct bnxt_re_qp *qp, rdev = qp->rdev; qplqp = &qp->qplib_qp; sq = &qplqp->sq; - dev_attr = &rdev->dev_attr; + dev_attr = rdev->dev_attr; sq->max_sge = init_attr->cap.max_send_sge; entries = init_attr->cap.max_send_wr; @@ -1398,7 +1391,7 @@ static void bnxt_re_adjust_gsi_sq_attr(struct bnxt_re_qp *qp, rdev = qp->rdev; qplqp = &qp->qplib_qp; - dev_attr = &rdev->dev_attr; + dev_attr = rdev->dev_attr; if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) { entries = bnxt_re_init_depth(init_attr->cap.max_send_wr + 1, uctx); @@ -1447,7 +1440,7 @@ static int bnxt_re_init_qp_attr(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd, rdev = qp->rdev; qplqp = &qp->qplib_qp; - dev_attr = &rdev->dev_attr; + dev_attr = rdev->dev_attr; /* Setup misc params */ ether_addr_copy(qplqp->smac, rdev->netdev->dev_addr); @@ -1617,7 +1610,7 @@ int bnxt_re_create_qp(struct ib_qp *ib_qp, struct ib_qp_init_attr *qp_init_attr, ib_pd = ib_qp->pd; pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd); rdev = pd->rdev; - dev_attr = &rdev->dev_attr; + dev_attr = rdev->dev_attr; qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp); uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx); @@ -1845,7 +1838,7 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq, ib_pd = ib_srq->pd; pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd); rdev = pd->rdev; - dev_attr = &rdev->dev_attr; + dev_attr = rdev->dev_attr; srq = container_of(ib_srq, struct bnxt_re_srq, ib_srq); if (srq_init_attr->attr.max_wr >= dev_attr->max_srq_wqes) { @@ -2049,7 +2042,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, { struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp); struct bnxt_re_dev *rdev = qp->rdev; - struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr; + struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr; enum ib_qp_state curr_qp_state, new_qp_state; int rc, entries; unsigned int flags; @@ -2167,18 +2160,20 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, } } - if (qp_attr_mask & IB_QP_PATH_MTU) { - qp->qplib_qp.modify_flags |= - CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; - qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu); - qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu); - } else if (qp_attr->qp_state == IB_QPS_RTR) { - qp->qplib_qp.modify_flags |= - CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; - qp->qplib_qp.path_mtu = - __from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu)); - qp->qplib_qp.mtu = - ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu)); + if (qp_attr->qp_state == IB_QPS_RTR) { + enum ib_mtu qpmtu; + + qpmtu = iboe_get_mtu(rdev->netdev->mtu); + if (qp_attr_mask & IB_QP_PATH_MTU) { + if (ib_mtu_enum_to_int(qp_attr->path_mtu) > + ib_mtu_enum_to_int(qpmtu)) + return -EINVAL; + qpmtu = qp_attr->path_mtu; + } + + qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; + qp->qplib_qp.path_mtu = __from_ib_mtu(qpmtu); + qp->qplib_qp.mtu = ib_mtu_enum_to_int(qpmtu); } if (qp_attr_mask & IB_QP_TIMEOUT) { @@ -2328,6 +2323,7 @@ int bnxt_re_query_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, qp_attr->retry_cnt = qplib_qp->retry_cnt; qp_attr->rnr_retry = qplib_qp->rnr_retry; qp_attr->min_rnr_timer = qplib_qp->min_rnr_timer; + qp_attr->port_num = __to_ib_port_num(qplib_qp->port_id); qp_attr->rq_psn = qplib_qp->rq.psn; qp_attr->max_rd_atomic = qplib_qp->max_rd_atomic; qp_attr->sq_psn = qplib_qp->sq.psn; @@ -2824,7 +2820,8 @@ bad: wr = wr->next; } bnxt_qplib_post_send_db(&qp->qplib_qp); - bnxt_ud_qp_hw_stall_workaround(qp); + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx)) + bnxt_ud_qp_hw_stall_workaround(qp); spin_unlock_irqrestore(&qp->sq_lock, flags); return rc; } @@ -2936,7 +2933,8 @@ bad: wr = wr->next; } bnxt_qplib_post_send_db(&qp->qplib_qp); - bnxt_ud_qp_hw_stall_workaround(qp); + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx)) + bnxt_ud_qp_hw_stall_workaround(qp); spin_unlock_irqrestore(&qp->sq_lock, flags); return rc; @@ -3091,7 +3089,7 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata = &attrs->driver_udata; struct bnxt_re_ucontext *uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx); - struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr; + struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr; struct bnxt_qplib_chip_ctx *cctx; int cqe = attr->cqe; int rc, entries; @@ -3226,7 +3224,7 @@ int bnxt_re_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata) cq = container_of(ibcq, struct bnxt_re_cq, ib_cq); rdev = cq->rdev; - dev_attr = &rdev->dev_attr; + dev_attr = rdev->dev_attr; if (!ibcq->uobject) { ibdev_err(&rdev->ibdev, "Kernel CQ Resize not supported"); return -EOPNOTSUPP; @@ -4199,7 +4197,7 @@ static struct ib_mr *__bnxt_re_user_reg_mr(struct ib_pd *ib_pd, u64 length, u64 mr->qplib_mr.access_flags = __from_ib_access_flags(mr_access_flags); mr->qplib_mr.type = CMDQ_ALLOCATE_MRW_MRW_FLAGS_MR; - if (!_is_alloc_mr_unified(rdev->dev_attr.dev_cap_flags)) { + if (!_is_alloc_mr_unified(rdev->dev_attr->dev_cap_flags)) { rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mr->qplib_mr); if (rc) { ibdev_err(&rdev->ibdev, "Failed to allocate MR rc = %d", rc); @@ -4291,7 +4289,7 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata) struct bnxt_re_ucontext *uctx = container_of(ctx, struct bnxt_re_ucontext, ib_uctx); struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev); - struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr; + struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr; struct bnxt_re_user_mmap_entry *entry; struct bnxt_re_uctx_resp resp = {}; struct bnxt_re_uctx_req ureq = {}; @@ -4467,9 +4465,10 @@ int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma) case BNXT_RE_MMAP_TOGGLE_PAGE: /* Driver doesn't expect write access for user space */ if (vma->vm_flags & VM_WRITE) - return -EFAULT; - ret = vm_insert_page(vma, vma->vm_start, - virt_to_page((void *)bnxt_entry->mem_offset)); + ret = -EFAULT; + else + ret = vm_insert_page(vma, vma->vm_start, + virt_to_page((void *)bnxt_entry->mem_offset)); break; default: ret = -EINVAL; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index ac59f1d73b15..fbb16a411d6a 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -268,6 +268,10 @@ void bnxt_re_dealloc_ucontext(struct ib_ucontext *context); int bnxt_re_mmap(struct ib_ucontext *context, struct vm_area_struct *vma); void bnxt_re_mmap_free(struct rdma_user_mmap_entry *rdma_entry); +static inline u32 __to_ib_port_num(u16 port_id) +{ + return (u32)port_id + 1; +} unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp); void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, unsigned long flags); diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index b7af0d5ff3b6..e9e4da4dd576 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -79,17 +79,12 @@ MODULE_LICENSE("Dual BSD/GPL"); /* globals */ static DEFINE_MUTEX(bnxt_re_mutex); -static void bnxt_re_stop_irq(void *handle); -static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev); -static int bnxt_re_netdev_event(struct notifier_block *notifier, - unsigned long event, void *ptr); -static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev); -static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev, u8 op_type); static int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev); static int bnxt_re_hwrm_qcfg(struct bnxt_re_dev *rdev, u32 *db_len, u32 *offset); -static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable); +static void bnxt_re_dispatch_event(struct ib_device *ibdev, struct ib_qp *qp, + u8 port_num, enum ib_event_type event); static void bnxt_re_set_db_offset(struct bnxt_re_dev *rdev) { struct bnxt_qplib_chip_ctx *cctx; @@ -153,6 +148,10 @@ static void bnxt_re_destroy_chip_ctx(struct bnxt_re_dev *rdev) if (!rdev->chip_ctx) return; + + kfree(rdev->dev_attr); + rdev->dev_attr = NULL; + chip_ctx = rdev->chip_ctx; rdev->chip_ctx = NULL; rdev->rcfw.res = NULL; @@ -166,7 +165,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev) { struct bnxt_qplib_chip_ctx *chip_ctx; struct bnxt_en_dev *en_dev; - int rc; + int rc = -ENOMEM; en_dev = rdev->en_dev; @@ -182,7 +181,10 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev) rdev->qplib_res.cctx = rdev->chip_ctx; rdev->rcfw.res = &rdev->qplib_res; - rdev->qplib_res.dattr = &rdev->dev_attr; + rdev->dev_attr = kzalloc(sizeof(*rdev->dev_attr), GFP_KERNEL); + if (!rdev->dev_attr) + goto free_chip_ctx; + rdev->qplib_res.dattr = rdev->dev_attr; rdev->qplib_res.is_vf = BNXT_EN_VF(en_dev); rdev->qplib_res.en_dev = en_dev; @@ -190,16 +192,20 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev) bnxt_re_set_db_offset(rdev); rc = bnxt_qplib_map_db_bar(&rdev->qplib_res); - if (rc) { - kfree(rdev->chip_ctx); - rdev->chip_ctx = NULL; - return rc; - } + if (rc) + goto free_dev_attr; if (bnxt_qplib_determine_atomics(en_dev->pdev)) ibdev_info(&rdev->ibdev, "platform doesn't support global atomics."); return 0; +free_dev_attr: + kfree(rdev->dev_attr); + rdev->dev_attr = NULL; +free_chip_ctx: + kfree(rdev->chip_ctx); + rdev->chip_ctx = NULL; + return rc; } /* SR-IOV helper functions */ @@ -221,7 +227,7 @@ static void bnxt_re_limit_pf_res(struct bnxt_re_dev *rdev) struct bnxt_qplib_ctx *ctx; int i; - attr = &rdev->dev_attr; + attr = rdev->dev_attr; ctx = &rdev->qplib_ctx; ctx->qpc_count = min_t(u32, BNXT_RE_MAX_QPC_COUNT, @@ -235,7 +241,7 @@ static void bnxt_re_limit_pf_res(struct bnxt_re_dev *rdev) if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) for (i = 0; i < MAX_TQM_ALLOC_REQ; i++) rdev->qplib_ctx.tqm_ctx.qcount[i] = - rdev->dev_attr.tqm_alloc_reqs[i]; + rdev->dev_attr->tqm_alloc_reqs[i]; } static void bnxt_re_limit_vf_res(struct bnxt_qplib_ctx *qplib_ctx, u32 num_vf) @@ -302,17 +308,123 @@ static void bnxt_re_vf_res_config(struct bnxt_re_dev *rdev) &rdev->qplib_ctx); } -static void bnxt_re_shutdown(struct auxiliary_device *adev) -{ - struct bnxt_re_en_dev_info *en_info = auxiliary_get_drvdata(adev); +struct bnxt_re_dcb_work { + struct work_struct work; struct bnxt_re_dev *rdev; + struct hwrm_async_event_cmpl cmpl; +}; - rdev = en_info->rdev; - ib_unregister_device(&rdev->ibdev); - bnxt_re_dev_uninit(rdev, BNXT_RE_COMPLETE_REMOVE); +static bool bnxt_re_is_qp1_qp(struct bnxt_re_qp *qp) +{ + return qp->ib_qp.qp_type == IB_QPT_GSI; } -static void bnxt_re_stop_irq(void *handle) +static struct bnxt_re_qp *bnxt_re_get_qp1_qp(struct bnxt_re_dev *rdev) +{ + struct bnxt_re_qp *qp; + + mutex_lock(&rdev->qp_lock); + list_for_each_entry(qp, &rdev->qp_list, list) { + if (bnxt_re_is_qp1_qp(qp)) { + mutex_unlock(&rdev->qp_lock); + return qp; + } + } + mutex_unlock(&rdev->qp_lock); + return NULL; +} + +static int bnxt_re_update_qp1_tos_dscp(struct bnxt_re_dev *rdev) +{ + struct bnxt_re_qp *qp; + + if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return 0; + + qp = bnxt_re_get_qp1_qp(rdev); + if (!qp) + return 0; + + qp->qplib_qp.modify_flags = CMDQ_MODIFY_QP_MODIFY_MASK_TOS_DSCP; + qp->qplib_qp.tos_dscp = rdev->cc_param.qp1_tos_dscp; + + return bnxt_qplib_modify_qp(&rdev->qplib_res, &qp->qplib_qp); +} + +static void bnxt_re_init_dcb_wq(struct bnxt_re_dev *rdev) +{ + rdev->dcb_wq = create_singlethread_workqueue("bnxt_re_dcb_wq"); +} + +static void bnxt_re_uninit_dcb_wq(struct bnxt_re_dev *rdev) +{ + if (!rdev->dcb_wq) + return; + destroy_workqueue(rdev->dcb_wq); +} + +static void bnxt_re_dcb_wq_task(struct work_struct *work) +{ + struct bnxt_re_dcb_work *dcb_work = + container_of(work, struct bnxt_re_dcb_work, work); + struct bnxt_re_dev *rdev = dcb_work->rdev; + struct bnxt_qplib_cc_param *cc_param; + int rc; + + if (!rdev) + goto free_dcb; + + cc_param = &rdev->cc_param; + rc = bnxt_qplib_query_cc_param(&rdev->qplib_res, cc_param); + if (rc) { + ibdev_dbg(&rdev->ibdev, "Failed to query ccparam rc:%d", rc); + goto free_dcb; + } + if (cc_param->qp1_tos_dscp != cc_param->tos_dscp) { + cc_param->qp1_tos_dscp = cc_param->tos_dscp; + rc = bnxt_re_update_qp1_tos_dscp(rdev); + if (rc) { + ibdev_dbg(&rdev->ibdev, "%s: Failed to modify QP1 rc:%d", + __func__, rc); + goto free_dcb; + } + } + +free_dcb: + kfree(dcb_work); +} + +static void bnxt_re_async_notifier(void *handle, struct hwrm_async_event_cmpl *cmpl) +{ + struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle; + struct bnxt_re_dcb_work *dcb_work; + u32 data1, data2; + u16 event_id; + + event_id = le16_to_cpu(cmpl->event_id); + data1 = le32_to_cpu(cmpl->event_data1); + data2 = le32_to_cpu(cmpl->event_data2); + + ibdev_dbg(&rdev->ibdev, "Async event_id = %d data1 = %d data2 = %d", + event_id, data1, data2); + + switch (event_id) { + case ASYNC_EVENT_CMPL_EVENT_ID_DCB_CONFIG_CHANGE: + dcb_work = kzalloc(sizeof(*dcb_work), GFP_ATOMIC); + if (!dcb_work) + break; + + dcb_work->rdev = rdev; + memcpy(&dcb_work->cmpl, cmpl, sizeof(*cmpl)); + INIT_WORK(&dcb_work->work, bnxt_re_dcb_wq_task); + queue_work(rdev->dcb_wq, &dcb_work->work); + break; + default: + break; + } +} + +static void bnxt_re_stop_irq(void *handle, bool reset) { struct bnxt_re_en_dev_info *en_info = auxiliary_get_drvdata(handle); struct bnxt_qplib_rcfw *rcfw; @@ -323,6 +435,14 @@ static void bnxt_re_stop_irq(void *handle) rdev = en_info->rdev; rcfw = &rdev->rcfw; + if (reset) { + set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags); + set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags); + wake_up_all(&rdev->rcfw.cmdq.waitq); + bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, + IB_EVENT_DEVICE_FATAL); + } + for (indx = BNXT_RE_NQ_IDX; indx < rdev->nqr->num_msix; indx++) { nq = &rdev->nqr->nq[indx - 1]; bnxt_qplib_nq_stop_irq(nq, false); @@ -378,6 +498,7 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent) } static struct bnxt_ulp_ops bnxt_re_ulp_ops = { + .ulp_async_notifier = bnxt_re_async_notifier, .ulp_irq_stop = bnxt_re_stop_irq, .ulp_irq_restart = bnxt_re_start_irq }; @@ -839,17 +960,6 @@ static void bnxt_re_disassociate_ucontext(struct ib_ucontext *ibcontext) } /* Device */ - -static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev) -{ - struct ib_device *ibdev = - ib_device_get_by_netdev(netdev, RDMA_DRIVER_BNXT_RE); - if (!ibdev) - return NULL; - - return container_of(ibdev, struct bnxt_re_dev, ibdev); -} - static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { @@ -1627,12 +1737,11 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev) /* Configure and allocate resources for qplib */ rdev->qplib_res.rcfw = &rdev->rcfw; - rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr); + rc = bnxt_qplib_get_dev_attr(&rdev->rcfw); if (rc) goto fail; - rc = bnxt_qplib_alloc_res(&rdev->qplib_res, rdev->en_dev->pdev, - rdev->netdev, &rdev->dev_attr); + rc = bnxt_qplib_alloc_res(&rdev->qplib_res, rdev->netdev); if (rc) goto fail; @@ -1715,11 +1824,8 @@ static bool bnxt_re_is_qp1_or_shadow_qp(struct bnxt_re_dev *rdev, static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev) { - int mask = IB_QP_STATE; - struct ib_qp_attr qp_attr; struct bnxt_re_qp *qp; - qp_attr.qp_state = IB_QPS_ERR; mutex_lock(&rdev->qp_lock); list_for_each_entry(qp, &rdev->qp_list, list) { /* Modify the state of all QPs except QP1/Shadow QP */ @@ -1727,12 +1833,9 @@ static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev) if (qp->qplib_qp.state != CMDQ_MODIFY_QP_NEW_STATE_RESET && qp->qplib_qp.state != - CMDQ_MODIFY_QP_NEW_STATE_ERR) { + CMDQ_MODIFY_QP_NEW_STATE_ERR) bnxt_re_dispatch_event(&rdev->ibdev, &qp->ib_qp, 1, IB_EVENT_QP_FATAL); - bnxt_re_modify_qp(&qp->ib_qp, &qp_attr, mask, - NULL); - } } } mutex_unlock(&rdev->qp_lock); @@ -1813,6 +1916,26 @@ static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev) return 0; } +static void bnxt_re_net_unregister_async_event(struct bnxt_re_dev *rdev) +{ + if (rdev->is_virtfn) + return; + + memset(&rdev->event_bitmap, 0, sizeof(rdev->event_bitmap)); + bnxt_register_async_events(rdev->en_dev, &rdev->event_bitmap, + ASYNC_EVENT_CMPL_EVENT_ID_DCB_CONFIG_CHANGE); +} + +static void bnxt_re_net_register_async_event(struct bnxt_re_dev *rdev) +{ + if (rdev->is_virtfn) + return; + + rdev->event_bitmap |= (1 << ASYNC_EVENT_CMPL_EVENT_ID_DCB_CONFIG_CHANGE); + bnxt_register_async_events(rdev->en_dev, &rdev->event_bitmap, + ASYNC_EVENT_CMPL_EVENT_ID_DCB_CONFIG_CHANGE); +} + static void bnxt_re_query_hwrm_intf_version(struct bnxt_re_dev *rdev) { struct bnxt_en_dev *en_dev = rdev->en_dev; @@ -1892,6 +2015,9 @@ static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev, u8 op_type) bnxt_re_debugfs_rem_pdev(rdev); + bnxt_re_net_unregister_async_event(rdev); + bnxt_re_uninit_dcb_wq(rdev); + if (test_and_clear_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags)) cancel_delayed_work_sync(&rdev->worker); @@ -2038,7 +2164,7 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 op_type) rdev->pacing.dbr_pacing = false; } } - rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr); + rc = bnxt_qplib_get_dev_attr(&rdev->rcfw); if (rc) goto disable_rcfw; @@ -2087,6 +2213,11 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 op_type) set_bit(BNXT_RE_FLAG_RESOURCES_INITIALIZED, &rdev->flags); if (!rdev->is_virtfn) { + /* Query f/w defaults of CC params */ + rc = bnxt_qplib_query_cc_param(&rdev->qplib_res, &rdev->cc_param); + if (rc) + ibdev_warn(&rdev->ibdev, "Failed to query CC defaults\n"); + rc = bnxt_re_setup_qos(rdev); if (rc) ibdev_info(&rdev->ibdev, @@ -2105,6 +2236,9 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 op_type) bnxt_re_debugfs_add_pdev(rdev); + bnxt_re_init_dcb_wq(rdev); + bnxt_re_net_register_async_event(rdev); + return 0; free_sctx: bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id); @@ -2123,6 +2257,30 @@ fail: return rc; } +static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable) +{ + struct bnxt_qplib_cc_param cc_param = {}; + + /* Do not enable congestion control on VFs */ + if (rdev->is_virtfn) + return; + + /* Currently enabling only for GenP5 adapters */ + if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return; + + if (enable) { + cc_param.enable = 1; + cc_param.tos_ecn = 1; + } + + cc_param.mask = (CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_ENABLE_CC | + CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_TOS_ECN); + + if (bnxt_qplib_modify_cc(&rdev->qplib_res, &cc_param)) + ibdev_err(&rdev->ibdev, "Failed to setup CC enable = %d\n", enable); +} + static void bnxt_re_update_en_info_rdev(struct bnxt_re_dev *rdev, struct bnxt_re_en_dev_info *en_info, struct auxiliary_device *adev) @@ -2169,20 +2327,10 @@ static int bnxt_re_add_device(struct auxiliary_device *adev, u8 op_type) goto re_dev_uninit; } - rdev->nb.notifier_call = bnxt_re_netdev_event; - rc = register_netdevice_notifier(&rdev->nb); - if (rc) { - rdev->nb.notifier_call = NULL; - pr_err("%s: Cannot register to netdevice_notifier", - ROCE_DRV_MODULE_NAME); - goto re_dev_unreg; - } bnxt_re_setup_cc(rdev, true); return 0; -re_dev_unreg: - ib_unregister_device(&rdev->ibdev); re_dev_uninit: bnxt_re_update_en_info_rdev(NULL, en_info, adev); bnxt_re_dev_uninit(rdev, BNXT_RE_COMPLETE_REMOVE); @@ -2192,79 +2340,6 @@ exit: return rc; } -static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable) -{ - struct bnxt_qplib_cc_param cc_param = {}; - - /* Do not enable congestion control on VFs */ - if (rdev->is_virtfn) - return; - - /* Currently enabling only for GenP5 adapters */ - if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) - return; - - if (enable) { - cc_param.enable = 1; - cc_param.tos_ecn = 1; - } - - cc_param.mask = (CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_ENABLE_CC | - CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_TOS_ECN); - - if (bnxt_qplib_modify_cc(&rdev->qplib_res, &cc_param)) - ibdev_err(&rdev->ibdev, "Failed to setup CC enable = %d\n", enable); -} - -/* - * "Notifier chain callback can be invoked for the same chain from - * different CPUs at the same time". - * - * For cases when the netdev is already present, our call to the - * register_netdevice_notifier() will actually get the rtnl_lock() - * before sending NETDEV_REGISTER and (if up) NETDEV_UP - * events. - * - * But for cases when the netdev is not already present, the notifier - * chain is subjected to be invoked from different CPUs simultaneously. - * - * This is protected by the netdev_mutex. - */ -static int bnxt_re_netdev_event(struct notifier_block *notifier, - unsigned long event, void *ptr) -{ - struct net_device *real_dev, *netdev = netdev_notifier_info_to_dev(ptr); - struct bnxt_re_dev *rdev; - - real_dev = rdma_vlan_dev_real_dev(netdev); - if (!real_dev) - real_dev = netdev; - - if (real_dev != netdev) - goto exit; - - rdev = bnxt_re_from_netdev(real_dev); - if (!rdev) - return NOTIFY_DONE; - - - switch (event) { - case NETDEV_UP: - case NETDEV_DOWN: - case NETDEV_CHANGE: - bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, - netif_carrier_ok(real_dev) ? - IB_EVENT_PORT_ACTIVE : - IB_EVENT_PORT_ERR); - break; - default: - break; - } - ib_device_put(&rdev->ibdev); -exit: - return NOTIFY_DONE; -} - #define BNXT_ADEV_NAME "bnxt_en" static void bnxt_re_remove_device(struct bnxt_re_dev *rdev, u8 op_type, @@ -2322,13 +2397,9 @@ static int bnxt_re_probe(struct auxiliary_device *adev, rc = bnxt_re_add_device(adev, BNXT_RE_COMPLETE_INIT); if (rc) - goto err; - mutex_unlock(&bnxt_re_mutex); - return 0; + kfree(en_info); -err: mutex_unlock(&bnxt_re_mutex); - kfree(en_info); return rc; } @@ -2381,6 +2452,16 @@ static int bnxt_re_resume(struct auxiliary_device *adev) return 0; } +static void bnxt_re_shutdown(struct auxiliary_device *adev) +{ + struct bnxt_re_en_dev_info *en_info = auxiliary_get_drvdata(adev); + struct bnxt_re_dev *rdev; + + rdev = en_info->rdev; + ib_unregister_device(&rdev->ibdev); + bnxt_re_dev_uninit(rdev, BNXT_RE_COMPLETE_REMOVE); +} + static const struct auxiliary_device_id bnxt_re_id_table[] = { { .name = BNXT_ADEV_NAME ".rdma", }, {}, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index e42abf5be6c0..5336f74297f8 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -659,13 +659,6 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, rc = bnxt_qplib_alloc_init_hwq(&srq->hwq, &hwq_attr); if (rc) return rc; - - srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq), - GFP_KERNEL); - if (!srq->swq) { - rc = -ENOMEM; - goto fail; - } srq->dbinfo.flags = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_CREATE_SRQ, @@ -694,9 +687,17 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, spin_lock_init(&srq->lock); srq->start_idx = 0; srq->last_idx = srq->hwq.max_elements - 1; - for (idx = 0; idx < srq->hwq.max_elements; idx++) - srq->swq[idx].next_idx = idx + 1; - srq->swq[srq->last_idx].next_idx = -1; + if (!srq->hwq.is_user) { + srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq), + GFP_KERNEL); + if (!srq->swq) { + rc = -ENOMEM; + goto fail; + } + for (idx = 0; idx < srq->hwq.max_elements; idx++) + srq->swq[idx].next_idx = idx + 1; + srq->swq[srq->last_idx].next_idx = -1; + } srq->id = le32_to_cpu(resp.xid); srq->dbinfo.hwq = &srq->hwq; @@ -1000,9 +1001,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) u32 tbl_indx; u16 nsge; - if (res->dattr) - qp->is_host_msn_tbl = _is_host_msn_table(res->dattr->dev_cap_flags2); - + qp->is_host_msn_tbl = _is_host_msn_table(res->dattr->dev_cap_flags2); sq->dbinfo.flags = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_CREATE_QP, @@ -1034,7 +1033,12 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) : 0; /* Update msn tbl size */ if (qp->is_host_msn_tbl && psn_sz) { - hwq_attr.aux_depth = roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); + if (qp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC) + hwq_attr.aux_depth = + roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); + else + hwq_attr.aux_depth = + roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)) / 2; qp->msn_tbl_sz = hwq_attr.aux_depth; qp->msn = 0; } @@ -1044,13 +1048,14 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) if (rc) return rc; - rc = bnxt_qplib_alloc_init_swq(sq); - if (rc) - goto fail_sq; - - if (psn_sz) - bnxt_qplib_init_psn_ptr(qp, psn_sz); + if (!sq->hwq.is_user) { + rc = bnxt_qplib_alloc_init_swq(sq); + if (rc) + goto fail_sq; + if (psn_sz) + bnxt_qplib_init_psn_ptr(qp, psn_sz); + } req.sq_size = cpu_to_le32(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); pbl = &sq->hwq.pbl[PBL_LVL_0]; req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]); @@ -1076,9 +1081,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) rc = bnxt_qplib_alloc_init_hwq(&rq->hwq, &hwq_attr); if (rc) goto sq_swq; - rc = bnxt_qplib_alloc_init_swq(rq); - if (rc) - goto fail_rq; + if (!rq->hwq.is_user) { + rc = bnxt_qplib_alloc_init_swq(rq); + if (rc) + goto fail_rq; + } req.rq_size = cpu_to_le32(rq->max_wqe); pbl = &rq->hwq.pbl[PBL_LVL_0]; @@ -1174,9 +1181,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) rq->dbinfo.db = qp->dpi->dbr; rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size); } + spin_lock_bh(&rcfw->tbl_lock); tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw); rcfw->qp_tbl[tbl_indx].qp_id = qp->id; rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp; + spin_unlock_bh(&rcfw->tbl_lock); return 0; fail: @@ -1283,7 +1292,8 @@ static void __filter_modify_flags(struct bnxt_qplib_qp *qp) } } -static void bnxt_set_mandatory_attributes(struct bnxt_qplib_qp *qp, +static void bnxt_set_mandatory_attributes(struct bnxt_qplib_res *res, + struct bnxt_qplib_qp *qp, struct cmdq_modify_qp *req) { u32 mandatory_flags = 0; @@ -1298,6 +1308,14 @@ static void bnxt_set_mandatory_attributes(struct bnxt_qplib_qp *qp, mandatory_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PKEY; } + if (_is_min_rnr_in_rtr_rts_mandatory(res->dattr->dev_cap_flags2) && + (qp->cur_qp_state == CMDQ_MODIFY_QP_NEW_STATE_RTR && + qp->state == CMDQ_MODIFY_QP_NEW_STATE_RTS)) { + if (qp->type == CMDQ_MODIFY_QP_QP_TYPE_RC) + mandatory_flags |= + CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER; + } + if (qp->type == CMDQ_MODIFY_QP_QP_TYPE_UD || qp->type == CMDQ_MODIFY_QP_QP_TYPE_GSI) mandatory_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_QKEY; @@ -1338,7 +1356,7 @@ int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) /* Set mandatory attributes for INIT -> RTR and RTR -> RTS transition */ if (_is_optimize_modify_qp_supported(res->dattr->dev_cap_flags2) && is_optimized_state_transition(qp)) - bnxt_set_mandatory_attributes(qp, &req); + bnxt_set_mandatory_attributes(res, qp, &req); } bmask = qp->modify_flags; req.modify_mask = cpu_to_le32(qp->modify_flags); @@ -1521,6 +1539,7 @@ int bnxt_qplib_query_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) qp->dest_qpn = le32_to_cpu(sb->dest_qp_id); memcpy(qp->smac, sb->src_mac, 6); qp->vlan_id = le16_to_cpu(sb->vlan_pcp_vlan_dei_vlan_id); + qp->port_id = le16_to_cpu(sb->port_id); bail: dma_free_coherent(&rcfw->pdev->dev, sbuf.size, sbuf.sb, sbuf.dma_addr); @@ -2667,10 +2686,12 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq, bnxt_qplib_add_flush_qp(qp); } else { /* Before we complete, do WA 9060 */ - if (do_wa9060(qp, cq, cq_cons, sq->swq_last, - cqe_sq_cons)) { - *lib_qp = qp; - goto out; + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->cctx)) { + if (do_wa9060(qp, cq, cq_cons, sq->swq_last, + cqe_sq_cons)) { + *lib_qp = qp; + goto out; + } } if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) { cqe->status = CQ_REQ_STATUS_OK; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index ef3424c81345..0d9487c889ff 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -114,7 +114,6 @@ struct bnxt_qplib_sge { u32 size; }; -#define BNXT_QPLIB_QP_MAX_SGL 6 struct bnxt_qplib_swq { u64 wr_id; int next_idx; @@ -154,7 +153,7 @@ struct bnxt_qplib_swqe { #define BNXT_QPLIB_SWQE_FLAGS_UC_FENCE BIT(2) #define BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT BIT(3) #define BNXT_QPLIB_SWQE_FLAGS_INLINE BIT(4) - struct bnxt_qplib_sge sg_list[BNXT_QPLIB_QP_MAX_SGL]; + struct bnxt_qplib_sge sg_list[BNXT_VAR_MAX_SGE]; int num_sge; /* Max inline data is 96 bytes */ u32 inline_len; @@ -299,6 +298,7 @@ struct bnxt_qplib_qp { u32 dest_qpn; u8 smac[6]; u16 vlan_id; + u16 port_id; u8 nw_type; struct bnxt_qplib_ah ah; @@ -343,6 +343,7 @@ struct bnxt_qplib_qp { u32 msn; u32 msn_tbl_sz; bool is_host_msn_tbl; + u8 tos_dscp; }; #define BNXT_QPLIB_MAX_CQE_ENTRY_SIZE sizeof(struct cq_base) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 5e90ea232de8..17e62f22683b 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -424,7 +424,8 @@ static int __send_message_basic_sanity(struct bnxt_qplib_rcfw *rcfw, /* Prevent posting if f/w is not in a state to process */ if (test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags)) - return bnxt_qplib_map_rc(opcode); + return -ENXIO; + if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags)) return -ETIMEDOUT; @@ -493,7 +494,7 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, rc = __send_message_basic_sanity(rcfw, msg, opcode); if (rc) - return rc; + return rc == -ENXIO ? bnxt_qplib_map_rc(opcode) : rc; rc = __send_message(rcfw, msg, opcode); if (rc) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 96ceec1e8199..02922a0987ad 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -876,14 +876,13 @@ void bnxt_qplib_free_res(struct bnxt_qplib_res *res) bnxt_qplib_free_dpi_tbl(res, &res->dpi_tbl); } -int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev, - struct net_device *netdev, - struct bnxt_qplib_dev_attr *dev_attr) +int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct net_device *netdev) { + struct bnxt_qplib_dev_attr *dev_attr; int rc; - res->pdev = pdev; res->netdev = netdev; + dev_attr = res->dattr; rc = bnxt_qplib_alloc_sgid_tbl(res, &res->sgid_tbl, dev_attr->max_sgid); if (rc) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index 21fb148713a6..be5d907a036b 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -424,9 +424,7 @@ int bnxt_qplib_dealloc_dpi(struct bnxt_qplib_res *res, void bnxt_qplib_cleanup_res(struct bnxt_qplib_res *res); int bnxt_qplib_init_res(struct bnxt_qplib_res *res); void bnxt_qplib_free_res(struct bnxt_qplib_res *res); -int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev, - struct net_device *netdev, - struct bnxt_qplib_dev_attr *dev_attr); +int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct net_device *netdev); void bnxt_qplib_free_ctx(struct bnxt_qplib_res *res, struct bnxt_qplib_ctx *ctx); int bnxt_qplib_alloc_ctx(struct bnxt_qplib_res *res, @@ -584,6 +582,11 @@ static inline bool _is_optimize_modify_qp_supported(u16 dev_cap_ext_flags2) return dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_OPTIMIZE_MODIFY_QP_SUPPORTED; } +static inline bool _is_min_rnr_in_rtr_rts_mandatory(u16 dev_cap_ext_flags2) +{ + return !!(dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_MIN_RNR_RTR_RTS_OPT_SUPPORTED); +} + static inline bool _is_cq_coalescing_supported(u16 dev_cap_ext_flags2) { return dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_CQ_COALESCING_SUPPORTED; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 7e20ae3d2c4f..4ccd4405355a 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -88,9 +88,9 @@ static void bnxt_qplib_query_version(struct bnxt_qplib_rcfw *rcfw, fw_ver[3] = resp.fw_rsvd; } -int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, - struct bnxt_qplib_dev_attr *attr) +int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw) { + struct bnxt_qplib_dev_attr *attr = rcfw->res->dattr; struct creq_query_func_resp resp = {}; struct bnxt_qplib_cmdqmsg msg = {}; struct creq_query_func_resp_sb *sb; @@ -129,12 +129,18 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->max_qp_init_rd_atom = sb->max_qp_init_rd_atom > BNXT_QPLIB_MAX_OUT_RD_ATOM ? BNXT_QPLIB_MAX_OUT_RD_ATOM : sb->max_qp_init_rd_atom; - attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr); - /* - * 128 WQEs needs to be reserved for the HW (8916). Prevent - * reporting the max number - */ - attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1; + attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr) - 1; + if (!bnxt_qplib_is_chip_gen_p5_p7(rcfw->res->cctx)) { + /* + * 128 WQEs needs to be reserved for the HW (8916). Prevent + * reporting the max number on legacy devices + */ + attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1; + } + + /* Adjust for max_qp_wqes for variable wqe */ + if (cctx->modes.wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE) + attr->max_qp_wqes = BNXT_VAR_MAX_WQE - 1; attr->max_qp_sges = cctx->modes.wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE ? min_t(u32, sb->max_sge_var_wqe, BNXT_VAR_MAX_SGE) : 6; @@ -1016,3 +1022,116 @@ free_mem: dma_free_coherent(&rcfw->pdev->dev, sbuf.size, sbuf.sb, sbuf.dma_addr); return rc; } + +static void bnxt_qplib_read_cc_gen1(struct bnxt_qplib_cc_param_ext *cc_ext, + struct creq_query_roce_cc_gen1_resp_sb_tlv *sb) +{ + cc_ext->inact_th_hi = le16_to_cpu(sb->inactivity_th_hi); + cc_ext->min_delta_cnp = le16_to_cpu(sb->min_time_between_cnps); + cc_ext->init_cp = le16_to_cpu(sb->init_cp); + cc_ext->tr_update_mode = sb->tr_update_mode; + cc_ext->tr_update_cyls = sb->tr_update_cycles; + cc_ext->fr_rtt = sb->fr_num_rtts; + cc_ext->ai_rate_incr = sb->ai_rate_increase; + cc_ext->rr_rtt_th = le16_to_cpu(sb->reduction_relax_rtts_th); + cc_ext->ar_cr_th = le16_to_cpu(sb->additional_relax_cr_th); + cc_ext->cr_min_th = le16_to_cpu(sb->cr_min_th); + cc_ext->bw_avg_weight = sb->bw_avg_weight; + cc_ext->cr_factor = sb->actual_cr_factor; + cc_ext->cr_th_max_cp = le16_to_cpu(sb->max_cp_cr_th); + cc_ext->cp_bias_en = sb->cp_bias_en; + cc_ext->cp_bias = sb->cp_bias; + cc_ext->cnp_ecn = sb->cnp_ecn; + cc_ext->rtt_jitter_en = sb->rtt_jitter_en; + cc_ext->bytes_per_usec = le16_to_cpu(sb->link_bytes_per_usec); + cc_ext->cc_cr_reset_th = le16_to_cpu(sb->reset_cc_cr_th); + cc_ext->cr_width = sb->cr_width; + cc_ext->min_quota = sb->quota_period_min; + cc_ext->max_quota = sb->quota_period_max; + cc_ext->abs_max_quota = sb->quota_period_abs_max; + cc_ext->tr_lb = le16_to_cpu(sb->tr_lower_bound); + cc_ext->cr_prob_fac = sb->cr_prob_factor; + cc_ext->tr_prob_fac = sb->tr_prob_factor; + cc_ext->fair_cr_th = le16_to_cpu(sb->fairness_cr_th); + cc_ext->red_div = sb->red_div; + cc_ext->cnp_ratio_th = sb->cnp_ratio_th; + cc_ext->ai_ext_rtt = le16_to_cpu(sb->exp_ai_rtts); + cc_ext->exp_crcp_ratio = sb->exp_ai_cr_cp_ratio; + cc_ext->low_rate_en = sb->use_rate_table; + cc_ext->cpcr_update_th = le16_to_cpu(sb->cp_exp_update_th); + cc_ext->ai_rtt_th1 = le16_to_cpu(sb->high_exp_ai_rtts_th1); + cc_ext->ai_rtt_th2 = le16_to_cpu(sb->high_exp_ai_rtts_th2); + cc_ext->cf_rtt_th = le16_to_cpu(sb->actual_cr_cong_free_rtts_th); + cc_ext->sc_cr_th1 = le16_to_cpu(sb->severe_cong_cr_th1); + cc_ext->sc_cr_th2 = le16_to_cpu(sb->severe_cong_cr_th2); + cc_ext->l64B_per_rtt = le32_to_cpu(sb->link64B_per_rtt); + cc_ext->cc_ack_bytes = sb->cc_ack_bytes; + cc_ext->reduce_cf_rtt_th = le16_to_cpu(sb->reduce_init_cong_free_rtts_th); +} + +int bnxt_qplib_query_cc_param(struct bnxt_qplib_res *res, + struct bnxt_qplib_cc_param *cc_param) +{ + struct bnxt_qplib_tlv_query_rcc_sb *ext_sb; + struct bnxt_qplib_rcfw *rcfw = res->rcfw; + struct creq_query_roce_cc_resp resp = {}; + struct creq_query_roce_cc_resp_sb *sb; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_query_roce_cc req = {}; + struct bnxt_qplib_rcfw_sbuf sbuf; + size_t resp_size; + int rc; + + /* Query the parameters from chip */ + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_QUERY_ROCE_CC, + sizeof(req)); + if (bnxt_qplib_is_chip_gen_p5_p7(res->cctx)) + resp_size = sizeof(*ext_sb); + else + resp_size = sizeof(*sb); + + sbuf.size = ALIGN(resp_size, BNXT_QPLIB_CMDQE_UNITS); + sbuf.sb = dma_alloc_coherent(&rcfw->pdev->dev, sbuf.size, + &sbuf.dma_addr, GFP_KERNEL); + if (!sbuf.sb) + return -ENOMEM; + + req.resp_size = sbuf.size / BNXT_QPLIB_CMDQE_UNITS; + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, &sbuf, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(res->rcfw, &msg); + if (rc) + goto out; + + ext_sb = sbuf.sb; + sb = bnxt_qplib_is_chip_gen_p5_p7(res->cctx) ? &ext_sb->base_sb : + (struct creq_query_roce_cc_resp_sb *)ext_sb; + + cc_param->enable = sb->enable_cc & CREQ_QUERY_ROCE_CC_RESP_SB_ENABLE_CC; + cc_param->tos_ecn = (sb->tos_dscp_tos_ecn & + CREQ_QUERY_ROCE_CC_RESP_SB_TOS_ECN_MASK) >> + CREQ_QUERY_ROCE_CC_RESP_SB_TOS_ECN_SFT; + cc_param->tos_dscp = (sb->tos_dscp_tos_ecn & + CREQ_QUERY_ROCE_CC_RESP_SB_TOS_DSCP_MASK) >> + CREQ_QUERY_ROCE_CC_RESP_SB_TOS_DSCP_SFT; + cc_param->alt_tos_dscp = sb->alt_tos_dscp; + cc_param->alt_vlan_pcp = sb->alt_vlan_pcp; + + cc_param->g = sb->g; + cc_param->nph_per_state = sb->num_phases_per_state; + cc_param->init_cr = le16_to_cpu(sb->init_cr); + cc_param->init_tr = le16_to_cpu(sb->init_tr); + cc_param->cc_mode = sb->cc_mode; + cc_param->inact_th = le16_to_cpu(sb->inactivity_th); + cc_param->rtt = le16_to_cpu(sb->rtt); + cc_param->tcp_cp = le16_to_cpu(sb->tcp_cp); + cc_param->time_pph = sb->time_per_phase; + cc_param->pkts_pph = sb->pkts_per_phase; + if (bnxt_qplib_is_chip_gen_p5_p7(res->cctx)) { + bnxt_qplib_read_cc_gen1(&cc_param->cc_ext, &ext_sb->gen1_sb); + cc_param->inact_th |= (cc_param->cc_ext.inact_th_hi & 0x3F) << 16; + } +out: + dma_free_coherent(&rcfw->pdev->dev, sbuf.size, sbuf.sb, sbuf.dma_addr); + return rc; +} diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index e6beeb514b7d..e626b05038a1 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -296,6 +296,7 @@ struct bnxt_qplib_cc_param_ext { struct bnxt_qplib_cc_param { u8 alt_vlan_pcp; + u8 qp1_tos_dscp; u16 alt_tos_dscp; u8 cc_mode; u8 enable; @@ -325,8 +326,7 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, struct bnxt_qplib_gid *gid, u16 gid_idx, const u8 *smac); -int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, - struct bnxt_qplib_dev_attr *attr); +int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw); int bnxt_qplib_set_func_resources(struct bnxt_qplib_res *res, struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_ctx *ctx); @@ -355,6 +355,8 @@ int bnxt_qplib_modify_cc(struct bnxt_qplib_res *res, struct bnxt_qplib_cc_param *cc_param); int bnxt_qplib_read_context(struct bnxt_qplib_rcfw *rcfw, u8 type, u32 xid, u32 resp_size, void *resp_va); +int bnxt_qplib_query_cc_param(struct bnxt_qplib_res *res, + struct bnxt_qplib_cc_param *cc_param); #define BNXT_VAR_MAX_WQE 4352 #define BNXT_VAR_MAX_SLOT_ALIGN 256 diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h index a98fc9c2313e..0ee60fdc18b3 100644 --- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h +++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h @@ -2215,6 +2215,7 @@ struct creq_query_func_resp_sb { #define CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_IQM_MSN_TABLE (0x2UL << 4) #define CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_LAST \ CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_IQM_MSN_TABLE + #define CREQ_QUERY_FUNC_RESP_SB_MIN_RNR_RTR_RTS_OPT_SUPPORTED 0x1000UL __le16 max_xp_qp_size; __le16 create_qp_batch_size; __le16 destroy_qp_batch_size; diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index 80970a1738f8..034b85c42255 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -1114,8 +1114,10 @@ static inline struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl, * The math here assumes sizeof cpl_pass_accept_req >= sizeof * cpl_rx_pkt. */ - skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) + - sizeof(struct rss_header) - pktshift, GFP_ATOMIC); + skb = alloc_skb(size_add(gl->tot_len, + sizeof(struct cpl_pass_accept_req) + + sizeof(struct rss_header)) - pktshift, + GFP_ATOMIC); if (unlikely(!skb)) return NULL; diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 7b5c4522b426..955f061a55e9 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1599,6 +1599,7 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp, int count; int rq_flushed = 0, sq_flushed; unsigned long flag; + struct ib_event ev; pr_debug("qhp %p rchp %p schp %p\n", qhp, rchp, schp); @@ -1607,6 +1608,13 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp, if (schp != rchp) spin_lock(&schp->lock); spin_lock(&qhp->lock); + if (qhp->srq && qhp->attr.state == C4IW_QP_STATE_ERROR && + qhp->ibqp.event_handler) { + ev.device = qhp->ibqp.device; + ev.element.qp = &qhp->ibqp; + ev.event = IB_EVENT_QP_LAST_WQE_REACHED; + qhp->ibqp.event_handler(&ev, qhp->ibqp.qp_context); + } if (qhp->wq.flushed) { spin_unlock(&qhp->lock); diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h index d7fc9d5eeefd..838182d0409c 100644 --- a/drivers/infiniband/hw/efa/efa.h +++ b/drivers/infiniband/hw/efa/efa.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ /* - * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2025 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef _EFA_H_ @@ -57,15 +57,15 @@ struct efa_dev { u64 db_bar_addr; u64 db_bar_len; - unsigned int num_irq_vectors; - int admin_msix_vector_idx; + u32 num_irq_vectors; + u32 admin_msix_vector_idx; struct efa_irq admin_irq; struct efa_stats stats; /* Array of completion EQs */ struct efa_eq *eqs; - unsigned int neqs; + u32 neqs; /* Only stores CQs with interrupts enabled */ struct xarray cqs_xa; diff --git a/drivers/infiniband/hw/efa/efa_com.h b/drivers/infiniband/hw/efa/efa_com.h index 77282234ce68..4d9ca97e4296 100644 --- a/drivers/infiniband/hw/efa/efa_com.h +++ b/drivers/infiniband/hw/efa/efa_com.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ /* - * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2025 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef _EFA_COM_H_ @@ -65,7 +65,7 @@ struct efa_com_admin_queue { u16 depth; struct efa_com_admin_cq cq; struct efa_com_admin_sq sq; - u16 msix_vector_idx; + u32 msix_vector_idx; unsigned long state; @@ -89,7 +89,7 @@ struct efa_com_aenq { struct efa_aenq_handlers *aenq_handlers; dma_addr_t dma_addr; u32 cc; /* consumer counter */ - u16 msix_vector_idx; + u32 msix_vector_idx; u16 depth; u8 phase; }; diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c index ad225823e6f2..4f03c0ec819f 100644 --- a/drivers/infiniband/hw/efa/efa_main.c +++ b/drivers/infiniband/hw/efa/efa_main.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause /* - * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2025 Amazon.com, Inc. or its affiliates. All rights reserved. */ #include @@ -141,8 +141,7 @@ static int efa_request_irq(struct efa_dev *dev, struct efa_irq *irq) return 0; } -static void efa_setup_comp_irq(struct efa_dev *dev, struct efa_eq *eq, - int vector) +static void efa_setup_comp_irq(struct efa_dev *dev, struct efa_eq *eq, u32 vector) { u32 cpu; @@ -305,7 +304,7 @@ static void efa_destroy_eq(struct efa_dev *dev, struct efa_eq *eq) efa_free_irq(dev, &eq->irq); } -static int efa_create_eq(struct efa_dev *dev, struct efa_eq *eq, u8 msix_vec) +static int efa_create_eq(struct efa_dev *dev, struct efa_eq *eq, u32 msix_vec) { int err; @@ -328,21 +327,17 @@ err_free_comp_irq: static int efa_create_eqs(struct efa_dev *dev) { - unsigned int neqs = dev->dev_attr.max_eq; - int err; - int i; - - neqs = min_t(unsigned int, neqs, - dev->num_irq_vectors - EFA_COMP_EQS_VEC_BASE); + u32 neqs = dev->dev_attr.max_eq; + int err, i; + neqs = min_t(u32, neqs, dev->num_irq_vectors - EFA_COMP_EQS_VEC_BASE); dev->neqs = neqs; dev->eqs = kcalloc(neqs, sizeof(*dev->eqs), GFP_KERNEL); if (!dev->eqs) return -ENOMEM; for (i = 0; i < neqs; i++) { - err = efa_create_eq(dev, &dev->eqs[i], - i + EFA_COMP_EQS_VEC_BASE); + err = efa_create_eq(dev, &dev->eqs[i], i + EFA_COMP_EQS_VEC_BASE); if (err) goto err_destroy_eqs; } @@ -470,7 +465,6 @@ static void efa_ib_device_remove(struct efa_dev *dev) ibdev_info(&dev->ibdev, "Unregister ib device\n"); ib_unregister_device(&dev->ibdev); efa_destroy_eqs(dev); - efa_com_dev_reset(&dev->edev, EFA_REGS_RESET_NORMAL); efa_release_doorbell_bar(dev); } @@ -643,12 +637,14 @@ err_disable_device: return ERR_PTR(err); } -static void efa_remove_device(struct pci_dev *pdev) +static void efa_remove_device(struct pci_dev *pdev, + enum efa_regs_reset_reason_types reset_reason) { struct efa_dev *dev = pci_get_drvdata(pdev); struct efa_com_dev *edev; edev = &dev->edev; + efa_com_dev_reset(edev, reset_reason); efa_com_admin_destroy(edev); efa_free_irq(dev, &dev->admin_irq); efa_disable_msix(dev); @@ -676,7 +672,7 @@ static int efa_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_remove_device: - efa_remove_device(pdev); + efa_remove_device(pdev, EFA_REGS_RESET_INIT_ERR); return err; } @@ -685,7 +681,7 @@ static void efa_remove(struct pci_dev *pdev) struct efa_dev *dev = pci_get_drvdata(pdev); efa_ib_device_remove(dev); - efa_remove_device(pdev); + efa_remove_device(pdev, EFA_REGS_RESET_NORMAL); } static void efa_shutdown(struct pci_dev *pdev) diff --git a/drivers/infiniband/hw/erdma/Kconfig b/drivers/infiniband/hw/erdma/Kconfig index 169038e3ceb1..267fc1f3c42a 100644 --- a/drivers/infiniband/hw/erdma/Kconfig +++ b/drivers/infiniband/hw/erdma/Kconfig @@ -5,7 +5,7 @@ config INFINIBAND_ERDMA depends on INFINIBAND_ADDR_TRANS depends on INFINIBAND_USER_ACCESS help - This is a RDMA/iWarp driver for Alibaba Elastic RDMA Adapter(ERDMA), + This is a RDMA driver for Alibaba Elastic RDMA Adapter(ERDMA), which supports RDMA features in Alibaba cloud environment. To compile this driver as module, choose M here. The module will be diff --git a/drivers/infiniband/hw/erdma/erdma.h b/drivers/infiniband/hw/erdma/erdma.h index 3c166359448d..2a023b99f992 100644 --- a/drivers/infiniband/hw/erdma/erdma.h +++ b/drivers/infiniband/hw/erdma/erdma.h @@ -16,7 +16,7 @@ #include "erdma_hw.h" #define DRV_MODULE_NAME "erdma" -#define ERDMA_NODE_DESC "Elastic RDMA(iWARP) stack" +#define ERDMA_NODE_DESC "Elastic RDMA Adapter stack" struct erdma_eq { void *qbuf; @@ -101,8 +101,6 @@ struct erdma_cmdq { struct erdma_comp_wait *wait_pool; spinlock_t lock; - bool use_event; - struct erdma_cmdq_sq sq; struct erdma_cmdq_cq cq; struct erdma_eq eq; @@ -148,6 +146,8 @@ struct erdma_devattr { u32 max_mr; u32 max_pd; u32 max_mw; + u32 max_gid; + u32 max_ah; u32 local_dma_key; }; @@ -177,7 +177,8 @@ struct erdma_resource_cb { enum { ERDMA_RES_TYPE_PD = 0, ERDMA_RES_TYPE_STAG_IDX = 1, - ERDMA_RES_CNT = 2, + ERDMA_RES_TYPE_AH = 2, + ERDMA_RES_CNT = 3, }; struct erdma_dev { @@ -192,8 +193,6 @@ struct erdma_dev { u8 __iomem *func_bar; struct erdma_devattr attrs; - /* physical port state (only one port per device) */ - enum ib_port_state state; u32 mtu; /* cmdq and aeq use the same msix vector */ @@ -215,6 +214,7 @@ struct erdma_dev { struct dma_pool *db_pool; struct dma_pool *resp_pool; + enum erdma_proto_type proto; }; static inline void *get_queue_entry(void *qbuf, u32 idx, u32 depth, u32 shift) @@ -265,7 +265,7 @@ void erdma_cmdq_destroy(struct erdma_dev *dev); void erdma_cmdq_build_reqhdr(u64 *hdr, u32 mod, u32 op); int erdma_post_cmd_wait(struct erdma_cmdq *cmdq, void *req, u32 req_size, - u64 *resp0, u64 *resp1); + u64 *resp0, u64 *resp1, bool sleepable); void erdma_cmdq_completion_handler(struct erdma_cmdq *cmdq); int erdma_ceqs_init(struct erdma_dev *dev); diff --git a/drivers/infiniband/hw/erdma/erdma_cm.c b/drivers/infiniband/hw/erdma/erdma_cm.c index 771059a8eb7d..1b23c698ec25 100644 --- a/drivers/infiniband/hw/erdma/erdma_cm.c +++ b/drivers/infiniband/hw/erdma/erdma_cm.c @@ -567,7 +567,8 @@ reject_conn: static int erdma_proc_mpareply(struct erdma_cep *cep) { - struct erdma_qp_attrs qp_attrs; + enum erdma_qpa_mask_iwarp to_modify_attrs = 0; + struct erdma_mod_qp_params_iwarp params; struct erdma_qp *qp = cep->qp; struct mpa_rr *rep; int ret; @@ -597,26 +598,29 @@ static int erdma_proc_mpareply(struct erdma_cep *cep) return -EINVAL; } - memset(&qp_attrs, 0, sizeof(qp_attrs)); - qp_attrs.irq_size = cep->ird; - qp_attrs.orq_size = cep->ord; - qp_attrs.state = ERDMA_QP_STATE_RTS; + memset(¶ms, 0, sizeof(params)); + params.state = ERDMA_QPS_IWARP_RTS; + params.irq_size = cep->ird; + params.orq_size = cep->ord; down_write(&qp->state_lock); - if (qp->attrs.state > ERDMA_QP_STATE_RTR) { + if (qp->attrs.iwarp.state > ERDMA_QPS_IWARP_RTR) { ret = -EINVAL; up_write(&qp->state_lock); goto out_err; } - qp->attrs.qp_type = ERDMA_QP_ACTIVE; - if (__mpa_ext_cc(cep->mpa.ext_data.bits) != qp->attrs.cc) - qp->attrs.cc = COMPROMISE_CC; + to_modify_attrs = ERDMA_QPA_IWARP_STATE | ERDMA_QPA_IWARP_LLP_HANDLE | + ERDMA_QPA_IWARP_MPA | ERDMA_QPA_IWARP_IRD | + ERDMA_QPA_IWARP_ORD; - ret = erdma_modify_qp_internal(qp, &qp_attrs, - ERDMA_QP_ATTR_STATE | - ERDMA_QP_ATTR_LLP_HANDLE | - ERDMA_QP_ATTR_MPA); + params.qp_type = ERDMA_QP_ACTIVE; + if (__mpa_ext_cc(cep->mpa.ext_data.bits) != qp->attrs.cc) { + to_modify_attrs |= ERDMA_QPA_IWARP_CC; + params.cc = COMPROMISE_CC; + } + + ret = erdma_modify_qp_state_iwarp(qp, ¶ms, to_modify_attrs); up_write(&qp->state_lock); @@ -722,7 +726,7 @@ static int erdma_newconn_connected(struct erdma_cep *cep) __mpa_rr_set_revision(&cep->mpa.hdr.params.bits, MPA_REVISION_EXT_1); memcpy(cep->mpa.hdr.key, MPA_KEY_REQ, MPA_KEY_SIZE); - cep->mpa.ext_data.cookie = cpu_to_be32(cep->qp->attrs.cookie); + cep->mpa.ext_data.cookie = cpu_to_be32(cep->qp->attrs.iwarp.cookie); __mpa_ext_set_cc(&cep->mpa.ext_data.bits, cep->qp->attrs.cc); ret = erdma_send_mpareqrep(cep, cep->private_data, cep->pd_len); @@ -1126,10 +1130,11 @@ error_put_qp: int erdma_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params) { - struct erdma_dev *dev = to_edev(id->device); struct erdma_cep *cep = (struct erdma_cep *)id->provider_data; + struct erdma_mod_qp_params_iwarp mod_qp_params; + enum erdma_qpa_mask_iwarp to_modify_attrs = 0; + struct erdma_dev *dev = to_edev(id->device); struct erdma_qp *qp; - struct erdma_qp_attrs qp_attrs; int ret; erdma_cep_set_inuse(cep); @@ -1156,7 +1161,7 @@ int erdma_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params) erdma_qp_get(qp); down_write(&qp->state_lock); - if (qp->attrs.state > ERDMA_QP_STATE_RTR) { + if (qp->attrs.iwarp.state > ERDMA_QPS_IWARP_RTR) { ret = -EINVAL; up_write(&qp->state_lock); goto error; @@ -1181,11 +1186,11 @@ int erdma_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params) cep->cm_id = id; id->add_ref(id); - memset(&qp_attrs, 0, sizeof(qp_attrs)); - qp_attrs.orq_size = params->ord; - qp_attrs.irq_size = params->ird; + memset(&mod_qp_params, 0, sizeof(mod_qp_params)); - qp_attrs.state = ERDMA_QP_STATE_RTS; + mod_qp_params.irq_size = params->ird; + mod_qp_params.orq_size = params->ord; + mod_qp_params.state = ERDMA_QPS_IWARP_RTS; /* Associate QP with CEP */ erdma_cep_get(cep); @@ -1194,19 +1199,21 @@ int erdma_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params) cep->state = ERDMA_EPSTATE_RDMA_MODE; - qp->attrs.qp_type = ERDMA_QP_PASSIVE; - qp->attrs.pd_len = params->private_data_len; + mod_qp_params.qp_type = ERDMA_QP_PASSIVE; + mod_qp_params.pd_len = params->private_data_len; - if (qp->attrs.cc != __mpa_ext_cc(cep->mpa.ext_data.bits)) - qp->attrs.cc = COMPROMISE_CC; + to_modify_attrs = ERDMA_QPA_IWARP_STATE | ERDMA_QPA_IWARP_ORD | + ERDMA_QPA_IWARP_LLP_HANDLE | ERDMA_QPA_IWARP_IRD | + ERDMA_QPA_IWARP_MPA; + + if (qp->attrs.cc != __mpa_ext_cc(cep->mpa.ext_data.bits)) { + to_modify_attrs |= ERDMA_QPA_IWARP_CC; + mod_qp_params.cc = COMPROMISE_CC; + } /* move to rts */ - ret = erdma_modify_qp_internal(qp, &qp_attrs, - ERDMA_QP_ATTR_STATE | - ERDMA_QP_ATTR_ORD | - ERDMA_QP_ATTR_LLP_HANDLE | - ERDMA_QP_ATTR_IRD | - ERDMA_QP_ATTR_MPA); + ret = erdma_modify_qp_state_iwarp(qp, &mod_qp_params, to_modify_attrs); + up_write(&qp->state_lock); if (ret) @@ -1214,7 +1221,7 @@ int erdma_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params) cep->mpa.ext_data.bits = 0; __mpa_ext_set_cc(&cep->mpa.ext_data.bits, qp->attrs.cc); - cep->mpa.ext_data.cookie = cpu_to_be32(cep->qp->attrs.cookie); + cep->mpa.ext_data.cookie = cpu_to_be32(cep->qp->attrs.iwarp.cookie); ret = erdma_send_mpareqrep(cep, params->private_data, params->private_data_len); diff --git a/drivers/infiniband/hw/erdma/erdma_cmdq.c b/drivers/infiniband/hw/erdma/erdma_cmdq.c index a3d8922d1ad1..b867aefe83b2 100644 --- a/drivers/infiniband/hw/erdma/erdma_cmdq.c +++ b/drivers/infiniband/hw/erdma/erdma_cmdq.c @@ -182,7 +182,6 @@ int erdma_cmdq_init(struct erdma_dev *dev) int err; cmdq->max_outstandings = ERDMA_CMDQ_MAX_OUTSTANDING; - cmdq->use_event = false; sema_init(&cmdq->credits, cmdq->max_outstandings); @@ -223,8 +222,6 @@ err_destroy_sq: void erdma_finish_cmdq_init(struct erdma_dev *dev) { - /* after device init successfully, change cmdq to event mode. */ - dev->cmdq.use_event = true; arm_cmdq_cq(&dev->cmdq); } @@ -312,8 +309,7 @@ static int erdma_poll_single_cmd_completion(struct erdma_cmdq *cmdq) /* Copy 16B comp data after cqe hdr to outer */ be32_to_cpu_array(comp_wait->comp_data, cqe + 2, 4); - if (cmdq->use_event) - complete(&comp_wait->wait_event); + complete(&comp_wait->wait_event); return 0; } @@ -332,9 +328,6 @@ static void erdma_polling_cmd_completions(struct erdma_cmdq *cmdq) if (erdma_poll_single_cmd_completion(cmdq)) break; - if (comp_num && cmdq->use_event) - arm_cmdq_cq(cmdq); - spin_unlock_irqrestore(&cmdq->cq.lock, flags); } @@ -342,8 +335,7 @@ void erdma_cmdq_completion_handler(struct erdma_cmdq *cmdq) { int got_event = 0; - if (!test_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state) || - !cmdq->use_event) + if (!test_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state)) return; while (get_next_valid_eqe(&cmdq->eq)) { @@ -354,6 +346,7 @@ void erdma_cmdq_completion_handler(struct erdma_cmdq *cmdq) if (got_event) { cmdq->cq.cmdsn++; erdma_polling_cmd_completions(cmdq); + arm_cmdq_cq(cmdq); } notify_eq(&cmdq->eq); @@ -372,7 +365,7 @@ static int erdma_poll_cmd_completion(struct erdma_comp_wait *comp_ctx, if (time_is_before_jiffies(comp_timeout)) return -ETIME; - msleep(20); + udelay(20); } return 0; @@ -403,7 +396,7 @@ void erdma_cmdq_build_reqhdr(u64 *hdr, u32 mod, u32 op) } int erdma_post_cmd_wait(struct erdma_cmdq *cmdq, void *req, u32 req_size, - u64 *resp0, u64 *resp1) + u64 *resp0, u64 *resp1, bool sleepable) { struct erdma_comp_wait *comp_wait; int ret; @@ -411,7 +404,12 @@ int erdma_post_cmd_wait(struct erdma_cmdq *cmdq, void *req, u32 req_size, if (!test_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state)) return -ENODEV; - down(&cmdq->credits); + if (!sleepable) { + while (down_trylock(&cmdq->credits)) + ; + } else { + down(&cmdq->credits); + } comp_wait = get_comp_wait(cmdq); if (IS_ERR(comp_wait)) { @@ -425,7 +423,7 @@ int erdma_post_cmd_wait(struct erdma_cmdq *cmdq, void *req, u32 req_size, push_cmdq_sqe(cmdq, req, req_size, comp_wait); spin_unlock(&cmdq->sq.lock); - if (cmdq->use_event) + if (sleepable) ret = erdma_wait_cmd_completion(comp_wait, cmdq, ERDMA_CMDQ_TIMEOUT_MS); else diff --git a/drivers/infiniband/hw/erdma/erdma_cq.c b/drivers/infiniband/hw/erdma/erdma_cq.c index 70f89f0162aa..1f456327e63c 100644 --- a/drivers/infiniband/hw/erdma/erdma_cq.c +++ b/drivers/infiniband/hw/erdma/erdma_cq.c @@ -105,6 +105,22 @@ static const struct { { ERDMA_WC_RETRY_EXC_ERR, IB_WC_RETRY_EXC_ERR, ERDMA_WC_VENDOR_NO_ERR }, }; +static void erdma_process_ud_cqe(struct erdma_cqe *cqe, struct ib_wc *wc) +{ + u32 ud_info; + + wc->wc_flags |= (IB_WC_GRH | IB_WC_WITH_NETWORK_HDR_TYPE); + ud_info = be32_to_cpu(cqe->ud.info); + wc->network_hdr_type = FIELD_GET(ERDMA_CQE_NTYPE_MASK, ud_info); + if (wc->network_hdr_type == ERDMA_NETWORK_TYPE_IPV4) + wc->network_hdr_type = RDMA_NETWORK_IPV4; + else + wc->network_hdr_type = RDMA_NETWORK_IPV6; + wc->src_qp = FIELD_GET(ERDMA_CQE_SQPN_MASK, ud_info); + wc->sl = FIELD_GET(ERDMA_CQE_SL_MASK, ud_info); + wc->pkey_index = 0; +} + #define ERDMA_POLLCQ_NO_QP 1 static int erdma_poll_one_cqe(struct erdma_cq *cq, struct ib_wc *wc) @@ -168,6 +184,10 @@ static int erdma_poll_one_cqe(struct erdma_cq *cq, struct ib_wc *wc) wc->wc_flags |= IB_WC_WITH_INVALIDATE; } + if (erdma_device_rocev2(dev) && + (qp->ibqp.qp_type == IB_QPT_UD || qp->ibqp.qp_type == IB_QPT_GSI)) + erdma_process_ud_cqe(cqe, wc); + if (syndrome >= ERDMA_NUM_WC_STATUS) syndrome = ERDMA_WC_GENERAL_ERR; @@ -201,3 +221,48 @@ int erdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) return npolled; } + +void erdma_remove_cqes_of_qp(struct ib_cq *ibcq, u32 qpn) +{ + struct erdma_cq *cq = to_ecq(ibcq); + struct erdma_cqe *cqe, *dst_cqe; + u32 prev_cq_ci, cur_cq_ci; + u32 ncqe = 0, nqp_cqe = 0; + unsigned long flags; + u8 owner; + + spin_lock_irqsave(&cq->kern_cq.lock, flags); + + prev_cq_ci = cq->kern_cq.ci; + + while (ncqe < cq->depth && (cqe = get_next_valid_cqe(cq)) != NULL) { + ++cq->kern_cq.ci; + ++ncqe; + } + + while (ncqe > 0) { + cur_cq_ci = prev_cq_ci + ncqe - 1; + cqe = get_queue_entry(cq->kern_cq.qbuf, cur_cq_ci, cq->depth, + CQE_SHIFT); + + if (be32_to_cpu(cqe->qpn) == qpn) { + ++nqp_cqe; + } else if (nqp_cqe) { + dst_cqe = get_queue_entry(cq->kern_cq.qbuf, + cur_cq_ci + nqp_cqe, + cq->depth, CQE_SHIFT); + owner = FIELD_GET(ERDMA_CQE_HDR_OWNER_MASK, + be32_to_cpu(dst_cqe->hdr)); + cqe->hdr = cpu_to_be32( + (be32_to_cpu(cqe->hdr) & + ~ERDMA_CQE_HDR_OWNER_MASK) | + FIELD_PREP(ERDMA_CQE_HDR_OWNER_MASK, owner)); + memcpy(dst_cqe, cqe, sizeof(*cqe)); + } + + --ncqe; + } + + cq->kern_cq.ci = prev_cq_ci + nqp_cqe; + spin_unlock_irqrestore(&cq->kern_cq.lock, flags); +} diff --git a/drivers/infiniband/hw/erdma/erdma_eq.c b/drivers/infiniband/hw/erdma/erdma_eq.c index 9a72fec6d5cc..6486234a2360 100644 --- a/drivers/infiniband/hw/erdma/erdma_eq.c +++ b/drivers/infiniband/hw/erdma/erdma_eq.c @@ -236,7 +236,8 @@ static int create_eq_cmd(struct erdma_dev *dev, u32 eqn, struct erdma_eq *eq) req.db_dma_addr_l = lower_32_bits(eq->dbrec_dma); req.db_dma_addr_h = upper_32_bits(eq->dbrec_dma); - return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + false); } static int erdma_ceq_init_one(struct erdma_dev *dev, u16 ceqn) @@ -278,7 +279,8 @@ static void erdma_ceq_uninit_one(struct erdma_dev *dev, u16 ceqn) req.qtype = ERDMA_EQ_TYPE_CEQ; req.vector_idx = ceqn + 1; - err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + false); if (err) return; diff --git a/drivers/infiniband/hw/erdma/erdma_hw.h b/drivers/infiniband/hw/erdma/erdma_hw.h index 05978f3b1475..ea4db53901a4 100644 --- a/drivers/infiniband/hw/erdma/erdma_hw.h +++ b/drivers/infiniband/hw/erdma/erdma_hw.h @@ -9,6 +9,7 @@ #include #include +#include /* PCIe device related definition. */ #define ERDMA_PCI_WIDTH 64 @@ -21,8 +22,21 @@ #define ERDMA_NUM_MSIX_VEC 32U #define ERDMA_MSIX_VECTOR_CMDQ 0 +/* RoCEv2 related */ +#define ERDMA_ROCEV2_GID_SIZE 16 +#define ERDMA_MAX_PKEYS 1 +#define ERDMA_DEFAULT_PKEY 0xFFFF + +/* erdma device protocol type */ +enum erdma_proto_type { + ERDMA_PROTO_IWARP = 0, + ERDMA_PROTO_ROCEV2 = 1, + ERDMA_PROTO_COUNT = 2, +}; + /* PCIe Bar0 Registers. */ #define ERDMA_REGS_VERSION_REG 0x0 +#define ERDMA_REGS_DEV_PROTO_REG 0xC #define ERDMA_REGS_DEV_CTRL_REG 0x10 #define ERDMA_REGS_DEV_ST_REG 0x14 #define ERDMA_REGS_NETDEV_MAC_L_REG 0x18 @@ -136,7 +150,11 @@ enum CMDQ_RDMA_OPCODE { CMDQ_OPCODE_DESTROY_CQ = 5, CMDQ_OPCODE_REFLUSH = 6, CMDQ_OPCODE_REG_MR = 8, - CMDQ_OPCODE_DEREG_MR = 9 + CMDQ_OPCODE_DEREG_MR = 9, + CMDQ_OPCODE_SET_GID = 14, + CMDQ_OPCODE_CREATE_AH = 15, + CMDQ_OPCODE_DESTROY_AH = 16, + CMDQ_OPCODE_QUERY_QP = 17, }; enum CMDQ_COMMON_OPCODE { @@ -284,6 +302,36 @@ struct erdma_cmdq_dereg_mr_req { u32 cfg; }; +/* create_av cfg0 */ +#define ERDMA_CMD_CREATE_AV_FL_MASK GENMASK(19, 0) +#define ERDMA_CMD_CREATE_AV_NTYPE_MASK BIT(20) + +struct erdma_av_cfg { + u32 cfg0; + u8 traffic_class; + u8 hop_limit; + u8 sl; + u8 rsvd; + u16 udp_sport; + u16 sgid_index; + u8 dmac[ETH_ALEN]; + u8 padding[2]; + u8 dgid[ERDMA_ROCEV2_GID_SIZE]; +}; + +struct erdma_cmdq_create_ah_req { + u64 hdr; + u32 pdn; + u32 ahn; + struct erdma_av_cfg av_cfg; +}; + +struct erdma_cmdq_destroy_ah_req { + u64 hdr; + u32 pdn; + u32 ahn; +}; + /* modify qp cfg */ #define ERDMA_CMD_MODIFY_QP_STATE_MASK GENMASK(31, 24) #define ERDMA_CMD_MODIFY_QP_CC_MASK GENMASK(23, 20) @@ -301,6 +349,36 @@ struct erdma_cmdq_modify_qp_req { u32 recv_nxt; }; +/* modify qp cfg1 for roce device */ +#define ERDMA_CMD_MODIFY_QP_DQPN_MASK GENMASK(19, 0) + +struct erdma_cmdq_mod_qp_req_rocev2 { + u64 hdr; + u32 cfg0; + u32 cfg1; + u32 attr_mask; + u32 qkey; + u32 rq_psn; + u32 sq_psn; + struct erdma_av_cfg av_cfg; +}; + +/* query qp response mask */ +#define ERDMA_CMD_QUERY_QP_RESP_SQ_PSN_MASK GENMASK_ULL(23, 0) +#define ERDMA_CMD_QUERY_QP_RESP_RQ_PSN_MASK GENMASK_ULL(47, 24) +#define ERDMA_CMD_QUERY_QP_RESP_QP_STATE_MASK GENMASK_ULL(55, 48) +#define ERDMA_CMD_QUERY_QP_RESP_SQ_DRAINING_MASK GENMASK_ULL(56, 56) + +struct erdma_cmdq_query_qp_req_rocev2 { + u64 hdr; + u32 qpn; +}; + +enum erdma_qp_type { + ERDMA_QPT_RC = 0, + ERDMA_QPT_UD = 1, +}; + /* create qp cfg0 */ #define ERDMA_CMD_CREATE_QP_SQ_DEPTH_MASK GENMASK(31, 20) #define ERDMA_CMD_CREATE_QP_QPN_MASK GENMASK(19, 0) @@ -309,6 +387,9 @@ struct erdma_cmdq_modify_qp_req { #define ERDMA_CMD_CREATE_QP_RQ_DEPTH_MASK GENMASK(31, 20) #define ERDMA_CMD_CREATE_QP_PD_MASK GENMASK(19, 0) +/* create qp cfg2 */ +#define ERDMA_CMD_CREATE_QP_TYPE_MASK GENMASK(3, 0) + /* create qp cqn_mtt_cfg */ #define ERDMA_CMD_CREATE_QP_PAGE_SIZE_MASK GENMASK(31, 28) #define ERDMA_CMD_CREATE_QP_DB_CFG_MASK BIT(25) @@ -342,6 +423,7 @@ struct erdma_cmdq_create_qp_req { u64 rq_mtt_entry[3]; u32 db_cfg; + u32 cfg2; }; struct erdma_cmdq_destroy_qp_req { @@ -394,10 +476,33 @@ struct erdma_cmdq_query_stats_resp { u64 rx_pps_meter_drop_packets_cnt; }; +enum erdma_network_type { + ERDMA_NETWORK_TYPE_IPV4 = 0, + ERDMA_NETWORK_TYPE_IPV6 = 1, +}; + +enum erdma_set_gid_op { + ERDMA_SET_GID_OP_ADD = 0, + ERDMA_SET_GID_OP_DEL = 1, +}; + +/* set gid cfg */ +#define ERDMA_CMD_SET_GID_SGID_IDX_MASK GENMASK(15, 0) +#define ERDMA_CMD_SET_GID_NTYPE_MASK BIT(16) +#define ERDMA_CMD_SET_GID_OP_MASK BIT(31) + +struct erdma_cmdq_set_gid_req { + u64 hdr; + u32 cfg; + u8 gid[ERDMA_ROCEV2_GID_SIZE]; +}; + /* cap qword 0 definition */ +#define ERDMA_CMD_DEV_CAP_MAX_GID_MASK GENMASK_ULL(51, 48) #define ERDMA_CMD_DEV_CAP_MAX_CQE_MASK GENMASK_ULL(47, 40) #define ERDMA_CMD_DEV_CAP_FLAGS_MASK GENMASK_ULL(31, 24) #define ERDMA_CMD_DEV_CAP_MAX_RECV_WR_MASK GENMASK_ULL(23, 16) +#define ERDMA_CMD_DEV_CAP_MAX_AH_MASK GENMASK_ULL(15, 8) #define ERDMA_CMD_DEV_CAP_MAX_MR_SIZE_MASK GENMASK_ULL(7, 0) /* cap qword 1 definition */ @@ -426,6 +531,10 @@ enum { #define ERDMA_CQE_QTYPE_RQ 1 #define ERDMA_CQE_QTYPE_CMDQ 2 +#define ERDMA_CQE_NTYPE_MASK BIT(31) +#define ERDMA_CQE_SL_MASK GENMASK(27, 20) +#define ERDMA_CQE_SQPN_MASK GENMASK(19, 0) + struct erdma_cqe { __be32 hdr; __be32 qe_idx; @@ -435,7 +544,16 @@ struct erdma_cqe { __be32 inv_rkey; }; __be32 size; - __be32 rsvd[3]; + union { + struct { + __be32 rsvd[3]; + } rc; + + struct { + __be32 rsvd[2]; + __be32 info; + } ud; + }; }; struct erdma_sge { @@ -487,7 +605,7 @@ struct erdma_write_sqe { struct erdma_sge sgl[]; }; -struct erdma_send_sqe { +struct erdma_send_sqe_rc { __le64 hdr; union { __be32 imm_data; @@ -498,6 +616,17 @@ struct erdma_send_sqe { struct erdma_sge sgl[]; }; +struct erdma_send_sqe_ud { + __le64 hdr; + __be32 imm_data; + __le32 length; + __le32 qkey; + __le32 dst_qpn; + __le32 ahn; + __le32 rsvd; + struct erdma_sge sgl[]; +}; + struct erdma_readreq_sqe { __le64 hdr; __le32 invalid_stag; diff --git a/drivers/infiniband/hw/erdma/erdma_main.c b/drivers/infiniband/hw/erdma/erdma_main.c index 62f497a71004..f35b30235018 100644 --- a/drivers/infiniband/hw/erdma/erdma_main.c +++ b/drivers/infiniband/hw/erdma/erdma_main.c @@ -26,14 +26,6 @@ static int erdma_netdev_event(struct notifier_block *nb, unsigned long event, goto done; switch (event) { - case NETDEV_UP: - dev->state = IB_PORT_ACTIVE; - erdma_port_event(dev, IB_EVENT_PORT_ACTIVE); - break; - case NETDEV_DOWN: - dev->state = IB_PORT_DOWN; - erdma_port_event(dev, IB_EVENT_PORT_ERR); - break; case NETDEV_CHANGEMTU: if (dev->mtu != netdev->mtu) { erdma_set_mtu(dev, netdev->mtu); @@ -172,6 +164,8 @@ static int erdma_device_init(struct erdma_dev *dev, struct pci_dev *pdev) { int ret; + dev->proto = erdma_reg_read32(dev, ERDMA_REGS_DEV_PROTO_REG); + dev->resp_pool = dma_pool_create("erdma_resp_pool", &pdev->dev, ERDMA_HW_RESP_SIZE, ERDMA_HW_RESP_SIZE, 0); @@ -390,7 +384,7 @@ static int erdma_dev_attrs_init(struct erdma_dev *dev) CMDQ_OPCODE_QUERY_DEVICE); err = erdma_post_cmd_wait(&dev->cmdq, &req_hdr, sizeof(req_hdr), &cap0, - &cap1); + &cap1, true); if (err) return err; @@ -398,6 +392,8 @@ static int erdma_dev_attrs_init(struct erdma_dev *dev) dev->attrs.max_mr_size = 1ULL << ERDMA_GET_CAP(MAX_MR_SIZE, cap0); dev->attrs.max_mw = 1 << ERDMA_GET_CAP(MAX_MW, cap1); dev->attrs.max_recv_wr = 1 << ERDMA_GET_CAP(MAX_RECV_WR, cap0); + dev->attrs.max_gid = 1 << ERDMA_GET_CAP(MAX_GID, cap0); + dev->attrs.max_ah = 1 << ERDMA_GET_CAP(MAX_AH, cap0); dev->attrs.local_dma_key = ERDMA_GET_CAP(DMA_LOCAL_KEY, cap1); dev->attrs.cc = ERDMA_GET_CAP(DEFAULT_CC, cap1); dev->attrs.max_qp = ERDMA_NQP_PER_QBLOCK * ERDMA_GET_CAP(QBLOCK, cap1); @@ -415,12 +411,13 @@ static int erdma_dev_attrs_init(struct erdma_dev *dev) dev->res_cb[ERDMA_RES_TYPE_PD].max_cap = ERDMA_MAX_PD; dev->res_cb[ERDMA_RES_TYPE_STAG_IDX].max_cap = dev->attrs.max_mr; + dev->res_cb[ERDMA_RES_TYPE_AH].max_cap = dev->attrs.max_ah; erdma_cmdq_build_reqhdr(&req_hdr, CMDQ_SUBMOD_COMMON, CMDQ_OPCODE_QUERY_FW_INFO); err = erdma_post_cmd_wait(&dev->cmdq, &req_hdr, sizeof(req_hdr), &cap0, - &cap1); + &cap1, true); if (!err) dev->attrs.fw_version = FIELD_GET(ERDMA_CMD_INFO0_FW_VER_MASK, cap0); @@ -441,7 +438,8 @@ static int erdma_device_config(struct erdma_dev *dev) req.cfg = FIELD_PREP(ERDMA_CMD_CONFIG_DEVICE_PGSHIFT_MASK, PAGE_SHIFT) | FIELD_PREP(ERDMA_CMD_CONFIG_DEVICE_PS_EN_MASK, 1); - return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); } static int erdma_res_cb_init(struct erdma_dev *dev) @@ -474,6 +472,29 @@ static void erdma_res_cb_free(struct erdma_dev *dev) bitmap_free(dev->res_cb[i].bitmap); } +static const struct ib_device_ops erdma_device_ops_rocev2 = { + .get_link_layer = erdma_get_link_layer, + .add_gid = erdma_add_gid, + .del_gid = erdma_del_gid, + .query_pkey = erdma_query_pkey, + .create_ah = erdma_create_ah, + .destroy_ah = erdma_destroy_ah, + .query_ah = erdma_query_ah, + + INIT_RDMA_OBJ_SIZE(ib_ah, erdma_ah, ibah), +}; + +static const struct ib_device_ops erdma_device_ops_iwarp = { + .iw_accept = erdma_accept, + .iw_add_ref = erdma_qp_get_ref, + .iw_connect = erdma_connect, + .iw_create_listen = erdma_create_listen, + .iw_destroy_listen = erdma_destroy_listen, + .iw_get_qp = erdma_get_ibqp, + .iw_reject = erdma_reject, + .iw_rem_ref = erdma_qp_put_ref, +}; + static const struct ib_device_ops erdma_device_ops = { .owner = THIS_MODULE, .driver_id = RDMA_DRIVER_ERDMA, @@ -494,18 +515,9 @@ static const struct ib_device_ops erdma_device_ops = { .get_dma_mr = erdma_get_dma_mr, .get_hw_stats = erdma_get_hw_stats, .get_port_immutable = erdma_get_port_immutable, - .iw_accept = erdma_accept, - .iw_add_ref = erdma_qp_get_ref, - .iw_connect = erdma_connect, - .iw_create_listen = erdma_create_listen, - .iw_destroy_listen = erdma_destroy_listen, - .iw_get_qp = erdma_get_ibqp, - .iw_reject = erdma_reject, - .iw_rem_ref = erdma_qp_put_ref, .map_mr_sg = erdma_map_mr_sg, .mmap = erdma_mmap, .mmap_free = erdma_mmap_free, - .modify_qp = erdma_modify_qp, .post_recv = erdma_post_recv, .post_send = erdma_post_send, .poll_cq = erdma_poll_cq, @@ -515,6 +527,7 @@ static const struct ib_device_ops erdma_device_ops = { .query_qp = erdma_query_qp, .req_notify_cq = erdma_req_notify_cq, .reg_user_mr = erdma_reg_user_mr, + .modify_qp = erdma_modify_qp, INIT_RDMA_OBJ_SIZE(ib_cq, erdma_cq, ibcq), INIT_RDMA_OBJ_SIZE(ib_pd, erdma_pd, ibpd), @@ -537,7 +550,14 @@ static int erdma_ib_device_add(struct pci_dev *pdev) if (ret) return ret; - ibdev->node_type = RDMA_NODE_RNIC; + if (erdma_device_iwarp(dev)) { + ibdev->node_type = RDMA_NODE_RNIC; + ib_set_device_ops(ibdev, &erdma_device_ops_iwarp); + } else { + ibdev->node_type = RDMA_NODE_IB_CA; + ib_set_device_ops(ibdev, &erdma_device_ops_rocev2); + } + memcpy(ibdev->node_desc, ERDMA_NODE_DESC, sizeof(ERDMA_NODE_DESC)); /* diff --git a/drivers/infiniband/hw/erdma/erdma_qp.c b/drivers/infiniband/hw/erdma/erdma_qp.c index 4d1f9114cd97..25f6c49aec77 100644 --- a/drivers/infiniband/hw/erdma/erdma_qp.c +++ b/drivers/infiniband/hw/erdma/erdma_qp.c @@ -11,20 +11,20 @@ void erdma_qp_llp_close(struct erdma_qp *qp) { - struct erdma_qp_attrs qp_attrs; + struct erdma_mod_qp_params_iwarp params; down_write(&qp->state_lock); - switch (qp->attrs.state) { - case ERDMA_QP_STATE_RTS: - case ERDMA_QP_STATE_RTR: - case ERDMA_QP_STATE_IDLE: - case ERDMA_QP_STATE_TERMINATE: - qp_attrs.state = ERDMA_QP_STATE_CLOSING; - erdma_modify_qp_internal(qp, &qp_attrs, ERDMA_QP_ATTR_STATE); + switch (qp->attrs.iwarp.state) { + case ERDMA_QPS_IWARP_RTS: + case ERDMA_QPS_IWARP_RTR: + case ERDMA_QPS_IWARP_IDLE: + case ERDMA_QPS_IWARP_TERMINATE: + params.state = ERDMA_QPS_IWARP_CLOSING; + erdma_modify_qp_state_iwarp(qp, ¶ms, ERDMA_QPA_IWARP_STATE); break; - case ERDMA_QP_STATE_CLOSING: - qp->attrs.state = ERDMA_QP_STATE_IDLE; + case ERDMA_QPS_IWARP_CLOSING: + qp->attrs.iwarp.state = ERDMA_QPS_IWARP_IDLE; break; default: break; @@ -48,9 +48,10 @@ struct ib_qp *erdma_get_ibqp(struct ib_device *ibdev, int id) return NULL; } -static int erdma_modify_qp_state_to_rts(struct erdma_qp *qp, - struct erdma_qp_attrs *attrs, - enum erdma_qp_attr_mask mask) +static int +erdma_modify_qp_state_to_rts(struct erdma_qp *qp, + struct erdma_mod_qp_params_iwarp *params, + enum erdma_qpa_mask_iwarp mask) { int ret; struct erdma_dev *dev = qp->dev; @@ -59,12 +60,15 @@ static int erdma_modify_qp_state_to_rts(struct erdma_qp *qp, struct erdma_cep *cep = qp->cep; struct sockaddr_storage local_addr, remote_addr; - if (!(mask & ERDMA_QP_ATTR_LLP_HANDLE)) + if (!(mask & ERDMA_QPA_IWARP_LLP_HANDLE)) return -EINVAL; - if (!(mask & ERDMA_QP_ATTR_MPA)) + if (!(mask & ERDMA_QPA_IWARP_MPA)) return -EINVAL; + if (!(mask & ERDMA_QPA_IWARP_CC)) + params->cc = qp->attrs.cc; + ret = getname_local(cep->sock, &local_addr); if (ret < 0) return ret; @@ -73,18 +77,16 @@ static int erdma_modify_qp_state_to_rts(struct erdma_qp *qp, if (ret < 0) return ret; - qp->attrs.state = ERDMA_QP_STATE_RTS; - tp = tcp_sk(qp->cep->sock->sk); erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA, CMDQ_OPCODE_MODIFY_QP); - req.cfg = FIELD_PREP(ERDMA_CMD_MODIFY_QP_STATE_MASK, qp->attrs.state) | - FIELD_PREP(ERDMA_CMD_MODIFY_QP_CC_MASK, qp->attrs.cc) | + req.cfg = FIELD_PREP(ERDMA_CMD_MODIFY_QP_STATE_MASK, params->state) | + FIELD_PREP(ERDMA_CMD_MODIFY_QP_CC_MASK, params->cc) | FIELD_PREP(ERDMA_CMD_MODIFY_QP_QPN_MASK, QP_ID(qp)); - req.cookie = be32_to_cpu(qp->cep->mpa.ext_data.cookie); + req.cookie = be32_to_cpu(cep->mpa.ext_data.cookie); req.dip = to_sockaddr_in(remote_addr).sin_addr.s_addr; req.sip = to_sockaddr_in(local_addr).sin_addr.s_addr; req.dport = to_sockaddr_in(remote_addr).sin_port; @@ -92,33 +94,57 @@ static int erdma_modify_qp_state_to_rts(struct erdma_qp *qp, req.send_nxt = tp->snd_nxt; /* rsvd tcp seq for mpa-rsp in server. */ - if (qp->attrs.qp_type == ERDMA_QP_PASSIVE) - req.send_nxt += MPA_DEFAULT_HDR_LEN + qp->attrs.pd_len; + if (params->qp_type == ERDMA_QP_PASSIVE) + req.send_nxt += MPA_DEFAULT_HDR_LEN + params->pd_len; req.recv_nxt = tp->rcv_nxt; - return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); + if (ret) + return ret; + + if (mask & ERDMA_QPA_IWARP_IRD) + qp->attrs.irq_size = params->irq_size; + + if (mask & ERDMA_QPA_IWARP_ORD) + qp->attrs.orq_size = params->orq_size; + + if (mask & ERDMA_QPA_IWARP_CC) + qp->attrs.cc = params->cc; + + qp->attrs.iwarp.state = ERDMA_QPS_IWARP_RTS; + + return 0; } -static int erdma_modify_qp_state_to_stop(struct erdma_qp *qp, - struct erdma_qp_attrs *attrs, - enum erdma_qp_attr_mask mask) +static int +erdma_modify_qp_state_to_stop(struct erdma_qp *qp, + struct erdma_mod_qp_params_iwarp *params, + enum erdma_qpa_mask_iwarp mask) { struct erdma_dev *dev = qp->dev; struct erdma_cmdq_modify_qp_req req; - - qp->attrs.state = attrs->state; + int ret; erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA, CMDQ_OPCODE_MODIFY_QP); - req.cfg = FIELD_PREP(ERDMA_CMD_MODIFY_QP_STATE_MASK, attrs->state) | + req.cfg = FIELD_PREP(ERDMA_CMD_MODIFY_QP_STATE_MASK, params->state) | FIELD_PREP(ERDMA_CMD_MODIFY_QP_QPN_MASK, QP_ID(qp)); - return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); + if (ret) + return ret; + + qp->attrs.iwarp.state = params->state; + + return 0; } -int erdma_modify_qp_internal(struct erdma_qp *qp, struct erdma_qp_attrs *attrs, - enum erdma_qp_attr_mask mask) +int erdma_modify_qp_state_iwarp(struct erdma_qp *qp, + struct erdma_mod_qp_params_iwarp *params, + int mask) { bool need_reflush = false; int drop_conn, ret = 0; @@ -126,31 +152,31 @@ int erdma_modify_qp_internal(struct erdma_qp *qp, struct erdma_qp_attrs *attrs, if (!mask) return 0; - if (!(mask & ERDMA_QP_ATTR_STATE)) + if (!(mask & ERDMA_QPA_IWARP_STATE)) return 0; - switch (qp->attrs.state) { - case ERDMA_QP_STATE_IDLE: - case ERDMA_QP_STATE_RTR: - if (attrs->state == ERDMA_QP_STATE_RTS) { - ret = erdma_modify_qp_state_to_rts(qp, attrs, mask); - } else if (attrs->state == ERDMA_QP_STATE_ERROR) { - qp->attrs.state = ERDMA_QP_STATE_ERROR; + switch (qp->attrs.iwarp.state) { + case ERDMA_QPS_IWARP_IDLE: + case ERDMA_QPS_IWARP_RTR: + if (params->state == ERDMA_QPS_IWARP_RTS) { + ret = erdma_modify_qp_state_to_rts(qp, params, mask); + } else if (params->state == ERDMA_QPS_IWARP_ERROR) { + qp->attrs.iwarp.state = ERDMA_QPS_IWARP_ERROR; need_reflush = true; if (qp->cep) { erdma_cep_put(qp->cep); qp->cep = NULL; } - ret = erdma_modify_qp_state_to_stop(qp, attrs, mask); + ret = erdma_modify_qp_state_to_stop(qp, params, mask); } break; - case ERDMA_QP_STATE_RTS: + case ERDMA_QPS_IWARP_RTS: drop_conn = 0; - if (attrs->state == ERDMA_QP_STATE_CLOSING || - attrs->state == ERDMA_QP_STATE_TERMINATE || - attrs->state == ERDMA_QP_STATE_ERROR) { - ret = erdma_modify_qp_state_to_stop(qp, attrs, mask); + if (params->state == ERDMA_QPS_IWARP_CLOSING || + params->state == ERDMA_QPS_IWARP_TERMINATE || + params->state == ERDMA_QPS_IWARP_ERROR) { + ret = erdma_modify_qp_state_to_stop(qp, params, mask); drop_conn = 1; need_reflush = true; } @@ -159,17 +185,17 @@ int erdma_modify_qp_internal(struct erdma_qp *qp, struct erdma_qp_attrs *attrs, erdma_qp_cm_drop(qp); break; - case ERDMA_QP_STATE_TERMINATE: - if (attrs->state == ERDMA_QP_STATE_ERROR) - qp->attrs.state = ERDMA_QP_STATE_ERROR; + case ERDMA_QPS_IWARP_TERMINATE: + if (params->state == ERDMA_QPS_IWARP_ERROR) + qp->attrs.iwarp.state = ERDMA_QPS_IWARP_ERROR; break; - case ERDMA_QP_STATE_CLOSING: - if (attrs->state == ERDMA_QP_STATE_IDLE) { - qp->attrs.state = ERDMA_QP_STATE_IDLE; - } else if (attrs->state == ERDMA_QP_STATE_ERROR) { - ret = erdma_modify_qp_state_to_stop(qp, attrs, mask); - qp->attrs.state = ERDMA_QP_STATE_ERROR; - } else if (attrs->state != ERDMA_QP_STATE_CLOSING) { + case ERDMA_QPS_IWARP_CLOSING: + if (params->state == ERDMA_QPS_IWARP_IDLE) { + qp->attrs.iwarp.state = ERDMA_QPS_IWARP_IDLE; + } else if (params->state == ERDMA_QPS_IWARP_ERROR) { + ret = erdma_modify_qp_state_to_stop(qp, params, mask); + qp->attrs.iwarp.state = ERDMA_QPS_IWARP_ERROR; + } else if (params->state != ERDMA_QPS_IWARP_CLOSING) { return -ECONNABORTED; } break; @@ -186,6 +212,98 @@ int erdma_modify_qp_internal(struct erdma_qp *qp, struct erdma_qp_attrs *attrs, return ret; } +static int modify_qp_cmd_rocev2(struct erdma_qp *qp, + struct erdma_mod_qp_params_rocev2 *params, + enum erdma_qpa_mask_rocev2 attr_mask) +{ + struct erdma_cmdq_mod_qp_req_rocev2 req; + + memset(&req, 0, sizeof(req)); + + erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA, + CMDQ_OPCODE_MODIFY_QP); + + req.cfg0 = FIELD_PREP(ERDMA_CMD_MODIFY_QP_QPN_MASK, QP_ID(qp)); + + if (attr_mask & ERDMA_QPA_ROCEV2_STATE) + req.cfg0 |= FIELD_PREP(ERDMA_CMD_MODIFY_QP_STATE_MASK, + params->state); + + if (attr_mask & ERDMA_QPA_ROCEV2_DST_QPN) + req.cfg1 = FIELD_PREP(ERDMA_CMD_MODIFY_QP_DQPN_MASK, + params->dst_qpn); + + if (attr_mask & ERDMA_QPA_ROCEV2_QKEY) + req.qkey = params->qkey; + + if (attr_mask & ERDMA_QPA_ROCEV2_AV) + erdma_set_av_cfg(&req.av_cfg, ¶ms->av); + + if (attr_mask & ERDMA_QPA_ROCEV2_SQ_PSN) + req.sq_psn = params->sq_psn; + + if (attr_mask & ERDMA_QPA_ROCEV2_RQ_PSN) + req.rq_psn = params->rq_psn; + + req.attr_mask = attr_mask; + + return erdma_post_cmd_wait(&qp->dev->cmdq, &req, sizeof(req), NULL, + NULL, true); +} + +static void erdma_reset_qp(struct erdma_qp *qp) +{ + qp->kern_qp.sq_pi = 0; + qp->kern_qp.sq_ci = 0; + qp->kern_qp.rq_pi = 0; + qp->kern_qp.rq_ci = 0; + memset(qp->kern_qp.swr_tbl, 0, qp->attrs.sq_size * sizeof(u64)); + memset(qp->kern_qp.rwr_tbl, 0, qp->attrs.rq_size * sizeof(u64)); + memset(qp->kern_qp.sq_buf, 0, qp->attrs.sq_size << SQEBB_SHIFT); + memset(qp->kern_qp.rq_buf, 0, qp->attrs.rq_size << RQE_SHIFT); + erdma_remove_cqes_of_qp(&qp->scq->ibcq, QP_ID(qp)); + if (qp->rcq != qp->scq) + erdma_remove_cqes_of_qp(&qp->rcq->ibcq, QP_ID(qp)); +} + +int erdma_modify_qp_state_rocev2(struct erdma_qp *qp, + struct erdma_mod_qp_params_rocev2 *params, + int attr_mask) +{ + struct erdma_dev *dev = to_edev(qp->ibqp.device); + int ret; + + ret = modify_qp_cmd_rocev2(qp, params, attr_mask); + if (ret) + return ret; + + if (attr_mask & ERDMA_QPA_ROCEV2_STATE) + qp->attrs.rocev2.state = params->state; + + if (attr_mask & ERDMA_QPA_ROCEV2_QKEY) + qp->attrs.rocev2.qkey = params->qkey; + + if (attr_mask & ERDMA_QPA_ROCEV2_DST_QPN) + qp->attrs.rocev2.dst_qpn = params->dst_qpn; + + if (attr_mask & ERDMA_QPA_ROCEV2_AV) + memcpy(&qp->attrs.rocev2.av, ¶ms->av, + sizeof(struct erdma_av)); + + if (rdma_is_kernel_res(&qp->ibqp.res) && + params->state == ERDMA_QPS_ROCEV2_RESET) + erdma_reset_qp(qp); + + if (rdma_is_kernel_res(&qp->ibqp.res) && + params->state == ERDMA_QPS_ROCEV2_ERROR) { + qp->flags |= ERDMA_QP_IN_FLUSHING; + mod_delayed_work(dev->reflush_wq, &qp->reflush_dwork, + usecs_to_jiffies(100)); + } + + return 0; +} + static void erdma_qp_safe_free(struct kref *ref) { struct erdma_qp *qp = container_of(ref, struct erdma_qp, ref); @@ -282,17 +400,57 @@ static int fill_sgl(struct erdma_qp *qp, const struct ib_send_wr *send_wr, return 0; } +static void init_send_sqe_rc(struct erdma_qp *qp, struct erdma_send_sqe_rc *sqe, + const struct ib_send_wr *wr, u32 *hw_op) +{ + u32 op = ERDMA_OP_SEND; + + if (wr->opcode == IB_WR_SEND_WITH_IMM) { + op = ERDMA_OP_SEND_WITH_IMM; + sqe->imm_data = wr->ex.imm_data; + } else if (wr->opcode == IB_WR_SEND_WITH_INV) { + op = ERDMA_OP_SEND_WITH_INV; + sqe->invalid_stag = cpu_to_le32(wr->ex.invalidate_rkey); + } + + *hw_op = op; +} + +static void init_send_sqe_ud(struct erdma_qp *qp, struct erdma_send_sqe_ud *sqe, + const struct ib_send_wr *wr, u32 *hw_op) +{ + const struct ib_ud_wr *uwr = ud_wr(wr); + struct erdma_ah *ah = to_eah(uwr->ah); + u32 op = ERDMA_OP_SEND; + + if (wr->opcode == IB_WR_SEND_WITH_IMM) { + op = ERDMA_OP_SEND_WITH_IMM; + sqe->imm_data = wr->ex.imm_data; + } + + *hw_op = op; + + sqe->ahn = cpu_to_le32(ah->ahn); + sqe->dst_qpn = cpu_to_le32(uwr->remote_qpn); + /* Not allowed to send control qkey */ + if (uwr->remote_qkey & 0x80000000) + sqe->qkey = cpu_to_le32(qp->attrs.rocev2.qkey); + else + sqe->qkey = cpu_to_le32(uwr->remote_qkey); +} + static int erdma_push_one_sqe(struct erdma_qp *qp, u16 *pi, const struct ib_send_wr *send_wr) { u32 wqe_size, wqebb_cnt, hw_op, flags, sgl_offset; u32 idx = *pi & (qp->attrs.sq_size - 1); enum ib_wr_opcode op = send_wr->opcode; + struct erdma_send_sqe_rc *rc_send_sqe; + struct erdma_send_sqe_ud *ud_send_sqe; struct erdma_atomic_sqe *atomic_sqe; struct erdma_readreq_sqe *read_sqe; struct erdma_reg_mr_sqe *regmr_sge; struct erdma_write_sqe *write_sqe; - struct erdma_send_sqe *send_sqe; struct ib_rdma_wr *rdma_wr; struct erdma_sge *sge; __le32 *length_field; @@ -301,6 +459,10 @@ static int erdma_push_one_sqe(struct erdma_qp *qp, u16 *pi, u32 attrs; int ret; + if (qp->ibqp.qp_type != IB_QPT_RC && send_wr->opcode != IB_WR_SEND && + send_wr->opcode != IB_WR_SEND_WITH_IMM) + return -EINVAL; + entry = get_queue_entry(qp->kern_qp.sq_buf, idx, qp->attrs.sq_size, SQEBB_SHIFT); @@ -374,21 +536,20 @@ static int erdma_push_one_sqe(struct erdma_qp *qp, u16 *pi, case IB_WR_SEND: case IB_WR_SEND_WITH_IMM: case IB_WR_SEND_WITH_INV: - send_sqe = (struct erdma_send_sqe *)entry; - hw_op = ERDMA_OP_SEND; - if (op == IB_WR_SEND_WITH_IMM) { - hw_op = ERDMA_OP_SEND_WITH_IMM; - send_sqe->imm_data = send_wr->ex.imm_data; - } else if (op == IB_WR_SEND_WITH_INV) { - hw_op = ERDMA_OP_SEND_WITH_INV; - send_sqe->invalid_stag = - cpu_to_le32(send_wr->ex.invalidate_rkey); + if (qp->ibqp.qp_type == IB_QPT_RC) { + rc_send_sqe = (struct erdma_send_sqe_rc *)entry; + init_send_sqe_rc(qp, rc_send_sqe, send_wr, &hw_op); + length_field = &rc_send_sqe->length; + wqe_size = sizeof(struct erdma_send_sqe_rc); + } else { + ud_send_sqe = (struct erdma_send_sqe_ud *)entry; + init_send_sqe_ud(qp, ud_send_sqe, send_wr, &hw_op); + length_field = &ud_send_sqe->length; + wqe_size = sizeof(struct erdma_send_sqe_ud); } - wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK, hw_op); - length_field = &send_sqe->length; - wqe_size = sizeof(struct erdma_send_sqe); - sgl_offset = wqe_size; + sgl_offset = wqe_size; + wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK, hw_op); break; case IB_WR_REG_MR: wqe_hdr |= diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c index 51d619edb6c5..af36a8d2df22 100644 --- a/drivers/infiniband/hw/erdma/erdma_verbs.c +++ b/drivers/infiniband/hw/erdma/erdma_verbs.c @@ -55,6 +55,13 @@ static int create_qp_cmd(struct erdma_ucontext *uctx, struct erdma_qp *qp) ilog2(qp->attrs.rq_size)) | FIELD_PREP(ERDMA_CMD_CREATE_QP_PD_MASK, pd->pdn); + if (qp->ibqp.qp_type == IB_QPT_RC) + req.cfg2 = FIELD_PREP(ERDMA_CMD_CREATE_QP_TYPE_MASK, + ERDMA_QPT_RC); + else + req.cfg2 = FIELD_PREP(ERDMA_CMD_CREATE_QP_TYPE_MASK, + ERDMA_QPT_UD); + if (rdma_is_kernel_res(&qp->ibqp.res)) { u32 pgsz_range = ilog2(SZ_1M) - ERDMA_HW_PAGE_SHIFT; @@ -119,10 +126,10 @@ static int create_qp_cmd(struct erdma_ucontext *uctx, struct erdma_qp *qp) } } - err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), &resp0, - &resp1); - if (!err) - qp->attrs.cookie = + err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), &resp0, &resp1, + true); + if (!err && erdma_device_iwarp(dev)) + qp->attrs.iwarp.cookie = FIELD_GET(ERDMA_CMDQ_CREATE_QP_RESP_COOKIE_MASK, resp0); return err; @@ -178,7 +185,8 @@ static int regmr_cmd(struct erdma_dev *dev, struct erdma_mr *mr) } post_cmd: - return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); } static int create_cq_cmd(struct erdma_ucontext *uctx, struct erdma_cq *cq) @@ -240,7 +248,8 @@ static int create_cq_cmd(struct erdma_ucontext *uctx, struct erdma_cq *cq) } } - return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); } static int erdma_alloc_idx(struct erdma_resource_cb *res_cb) @@ -336,6 +345,11 @@ int erdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr, attr->max_fast_reg_page_list_len = ERDMA_MAX_FRMR_PA; attr->page_size_cap = ERDMA_PAGE_SIZE_SUPPORT; + if (erdma_device_rocev2(dev)) { + attr->max_pkeys = ERDMA_MAX_PKEYS; + attr->max_ah = dev->attrs.max_ah; + } + if (dev->attrs.cap_flags & ERDMA_DEV_CAP_FLAGS_ATOMIC) attr->atomic_cap = IB_ATOMIC_GLOB; @@ -367,7 +381,14 @@ int erdma_query_port(struct ib_device *ibdev, u32 port, memset(attr, 0, sizeof(*attr)); - attr->gid_tbl_len = 1; + if (erdma_device_iwarp(dev)) { + attr->gid_tbl_len = 1; + } else { + attr->gid_tbl_len = dev->attrs.max_gid; + attr->ip_gids = true; + attr->pkey_tbl_len = ERDMA_MAX_PKEYS; + } + attr->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_DEVICE_MGMT_SUP; attr->max_msg_sz = -1; @@ -377,14 +398,10 @@ int erdma_query_port(struct ib_device *ibdev, u32 port, ib_get_eth_speed(ibdev, port, &attr->active_speed, &attr->active_width); attr->max_mtu = ib_mtu_int_to_enum(ndev->mtu); attr->active_mtu = ib_mtu_int_to_enum(ndev->mtu); - if (netif_running(ndev) && netif_carrier_ok(ndev)) - dev->state = IB_PORT_ACTIVE; - else - dev->state = IB_PORT_DOWN; - attr->state = dev->state; + attr->state = ib_get_curr_port_state(ndev); out: - if (dev->state == IB_PORT_ACTIVE) + if (attr->state == IB_PORT_ACTIVE) attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; else attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; @@ -395,8 +412,18 @@ out: int erdma_get_port_immutable(struct ib_device *ibdev, u32 port, struct ib_port_immutable *port_immutable) { - port_immutable->gid_tbl_len = 1; - port_immutable->core_cap_flags = RDMA_CORE_PORT_IWARP; + struct erdma_dev *dev = to_edev(ibdev); + + if (erdma_device_iwarp(dev)) { + port_immutable->core_cap_flags = RDMA_CORE_PORT_IWARP; + port_immutable->gid_tbl_len = 1; + } else { + port_immutable->core_cap_flags = + RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP; + port_immutable->max_mad_size = IB_MGMT_MAD_SIZE; + port_immutable->gid_tbl_len = dev->attrs.max_gid; + port_immutable->pkey_tbl_len = ERDMA_MAX_PKEYS; + } return 0; } @@ -438,7 +465,8 @@ static void erdma_flush_worker(struct work_struct *work) req.qpn = QP_ID(qp); req.sq_pi = qp->kern_qp.sq_pi; req.rq_pi = qp->kern_qp.rq_pi; - erdma_post_cmd_wait(&qp->dev->cmdq, &req, sizeof(req), NULL, NULL); + erdma_post_cmd_wait(&qp->dev->cmdq, &req, sizeof(req), NULL, NULL, + true); } static int erdma_qp_validate_cap(struct erdma_dev *dev, @@ -459,7 +487,11 @@ static int erdma_qp_validate_cap(struct erdma_dev *dev, static int erdma_qp_validate_attr(struct erdma_dev *dev, struct ib_qp_init_attr *attrs) { - if (attrs->qp_type != IB_QPT_RC) + if (erdma_device_iwarp(dev) && attrs->qp_type != IB_QPT_RC) + return -EOPNOTSUPP; + + if (erdma_device_rocev2(dev) && attrs->qp_type != IB_QPT_RC && + attrs->qp_type != IB_QPT_UD && attrs->qp_type != IB_QPT_GSI) return -EOPNOTSUPP; if (attrs->srq) @@ -937,7 +969,8 @@ int erdma_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, udata, struct erdma_ucontext, ibucontext); struct erdma_ureq_create_qp ureq; struct erdma_uresp_create_qp uresp; - int ret; + void *old_entry; + int ret = 0; ret = erdma_qp_validate_cap(dev, attrs); if (ret) @@ -956,9 +989,16 @@ int erdma_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, kref_init(&qp->ref); init_completion(&qp->safe_free); - ret = xa_alloc_cyclic(&dev->qp_xa, &qp->ibqp.qp_num, qp, - XA_LIMIT(1, dev->attrs.max_qp - 1), - &dev->next_alloc_qpn, GFP_KERNEL); + if (qp->ibqp.qp_type == IB_QPT_GSI) { + old_entry = xa_store(&dev->qp_xa, 1, qp, GFP_KERNEL); + if (xa_is_err(old_entry)) + ret = xa_err(old_entry); + } else { + ret = xa_alloc_cyclic(&dev->qp_xa, &qp->ibqp.qp_num, qp, + XA_LIMIT(1, dev->attrs.max_qp - 1), + &dev->next_alloc_qpn, GFP_KERNEL); + } + if (ret < 0) { ret = -ENOMEM; goto err_out; @@ -995,7 +1035,12 @@ int erdma_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, qp->attrs.max_send_sge = attrs->cap.max_send_sge; qp->attrs.max_recv_sge = attrs->cap.max_recv_sge; - qp->attrs.state = ERDMA_QP_STATE_IDLE; + + if (erdma_device_iwarp(qp->dev)) + qp->attrs.iwarp.state = ERDMA_QPS_IWARP_IDLE; + else + qp->attrs.rocev2.state = ERDMA_QPS_ROCEV2_RESET; + INIT_DELAYED_WORK(&qp->reflush_dwork, erdma_flush_worker); ret = create_qp_cmd(uctx, qp); @@ -1219,7 +1264,8 @@ int erdma_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) req.cfg = FIELD_PREP(ERDMA_CMD_MR_MPT_IDX_MASK, ibmr->lkey >> 8) | FIELD_PREP(ERDMA_CMD_MR_KEY_MASK, ibmr->lkey & 0xFF); - ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); if (ret) return ret; @@ -1244,7 +1290,8 @@ int erdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) CMDQ_OPCODE_DESTROY_CQ); req.cqn = cq->cqn; - err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); if (err) return err; @@ -1269,13 +1316,20 @@ int erdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) struct erdma_dev *dev = to_edev(ibqp->device); struct erdma_ucontext *ctx = rdma_udata_to_drv_context( udata, struct erdma_ucontext, ibucontext); - struct erdma_qp_attrs qp_attrs; - int err; struct erdma_cmdq_destroy_qp_req req; + union erdma_mod_qp_params params; + int err; down_write(&qp->state_lock); - qp_attrs.state = ERDMA_QP_STATE_ERROR; - erdma_modify_qp_internal(qp, &qp_attrs, ERDMA_QP_ATTR_STATE); + if (erdma_device_iwarp(dev)) { + params.iwarp.state = ERDMA_QPS_IWARP_ERROR; + erdma_modify_qp_state_iwarp(qp, ¶ms.iwarp, + ERDMA_QPA_IWARP_STATE); + } else { + params.rocev2.state = ERDMA_QPS_ROCEV2_ERROR; + erdma_modify_qp_state_rocev2(qp, ¶ms.rocev2, + ERDMA_QPA_ROCEV2_STATE); + } up_write(&qp->state_lock); cancel_delayed_work_sync(&qp->reflush_dwork); @@ -1284,7 +1338,8 @@ int erdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) CMDQ_OPCODE_DESTROY_QP); req.qpn = QP_ID(qp); - err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); if (err) return err; @@ -1382,7 +1437,8 @@ static int alloc_db_resources(struct erdma_dev *dev, struct erdma_ucontext *ctx, FIELD_PREP(ERDMA_CMD_EXT_DB_RQ_EN_MASK, 1) | FIELD_PREP(ERDMA_CMD_EXT_DB_SQ_EN_MASK, 1); - ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), &val0, &val1); + ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), &val0, &val1, + true); if (ret) return ret; @@ -1417,7 +1473,8 @@ static void free_db_resources(struct erdma_dev *dev, struct erdma_ucontext *ctx) req.rdb_off = ctx->ext_db.rdb_off; req.cdb_off = ctx->ext_db.cdb_off; - ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); if (ret) ibdev_err_ratelimited(&dev->ibdev, "free db resources failed %d", ret); @@ -1506,69 +1563,248 @@ void erdma_dealloc_ucontext(struct ib_ucontext *ibctx) atomic_dec(&dev->num_ctx); } -static int ib_qp_state_to_erdma_qp_state[IB_QPS_ERR + 1] = { - [IB_QPS_RESET] = ERDMA_QP_STATE_IDLE, - [IB_QPS_INIT] = ERDMA_QP_STATE_IDLE, - [IB_QPS_RTR] = ERDMA_QP_STATE_RTR, - [IB_QPS_RTS] = ERDMA_QP_STATE_RTS, - [IB_QPS_SQD] = ERDMA_QP_STATE_CLOSING, - [IB_QPS_SQE] = ERDMA_QP_STATE_TERMINATE, - [IB_QPS_ERR] = ERDMA_QP_STATE_ERROR +static void erdma_attr_to_av(const struct rdma_ah_attr *ah_attr, + struct erdma_av *av, u16 sport) +{ + const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr); + + av->port = rdma_ah_get_port_num(ah_attr); + av->sgid_index = grh->sgid_index; + av->hop_limit = grh->hop_limit; + av->traffic_class = grh->traffic_class; + av->sl = rdma_ah_get_sl(ah_attr); + + av->flow_label = grh->flow_label; + av->udp_sport = sport; + + ether_addr_copy(av->dmac, ah_attr->roce.dmac); + memcpy(av->dgid, grh->dgid.raw, ERDMA_ROCEV2_GID_SIZE); + + if (ipv6_addr_v4mapped((struct in6_addr *)&grh->dgid)) + av->ntype = ERDMA_NETWORK_TYPE_IPV4; + else + av->ntype = ERDMA_NETWORK_TYPE_IPV6; +} + +static void erdma_av_to_attr(struct erdma_av *av, struct rdma_ah_attr *ah_attr) +{ + ah_attr->type = RDMA_AH_ATTR_TYPE_ROCE; + + rdma_ah_set_sl(ah_attr, av->sl); + rdma_ah_set_port_num(ah_attr, av->port); + rdma_ah_set_ah_flags(ah_attr, IB_AH_GRH); + + rdma_ah_set_grh(ah_attr, NULL, av->flow_label, av->sgid_index, + av->hop_limit, av->traffic_class); + rdma_ah_set_dgid_raw(ah_attr, av->dgid); +} + +static int ib_qps_to_erdma_qps[ERDMA_PROTO_COUNT][IB_QPS_ERR + 1] = { + [ERDMA_PROTO_IWARP] = { + [IB_QPS_RESET] = ERDMA_QPS_IWARP_IDLE, + [IB_QPS_INIT] = ERDMA_QPS_IWARP_IDLE, + [IB_QPS_RTR] = ERDMA_QPS_IWARP_RTR, + [IB_QPS_RTS] = ERDMA_QPS_IWARP_RTS, + [IB_QPS_SQD] = ERDMA_QPS_IWARP_CLOSING, + [IB_QPS_SQE] = ERDMA_QPS_IWARP_TERMINATE, + [IB_QPS_ERR] = ERDMA_QPS_IWARP_ERROR, + }, + [ERDMA_PROTO_ROCEV2] = { + [IB_QPS_RESET] = ERDMA_QPS_ROCEV2_RESET, + [IB_QPS_INIT] = ERDMA_QPS_ROCEV2_INIT, + [IB_QPS_RTR] = ERDMA_QPS_ROCEV2_RTR, + [IB_QPS_RTS] = ERDMA_QPS_ROCEV2_RTS, + [IB_QPS_SQD] = ERDMA_QPS_ROCEV2_SQD, + [IB_QPS_SQE] = ERDMA_QPS_ROCEV2_SQE, + [IB_QPS_ERR] = ERDMA_QPS_ROCEV2_ERROR, + }, }; +static int erdma_qps_to_ib_qps[ERDMA_PROTO_COUNT][ERDMA_QPS_ROCEV2_COUNT] = { + [ERDMA_PROTO_IWARP] = { + [ERDMA_QPS_IWARP_IDLE] = IB_QPS_INIT, + [ERDMA_QPS_IWARP_RTR] = IB_QPS_RTR, + [ERDMA_QPS_IWARP_RTS] = IB_QPS_RTS, + [ERDMA_QPS_IWARP_CLOSING] = IB_QPS_ERR, + [ERDMA_QPS_IWARP_TERMINATE] = IB_QPS_ERR, + [ERDMA_QPS_IWARP_ERROR] = IB_QPS_ERR, + }, + [ERDMA_PROTO_ROCEV2] = { + [ERDMA_QPS_ROCEV2_RESET] = IB_QPS_RESET, + [ERDMA_QPS_ROCEV2_INIT] = IB_QPS_INIT, + [ERDMA_QPS_ROCEV2_RTR] = IB_QPS_RTR, + [ERDMA_QPS_ROCEV2_RTS] = IB_QPS_RTS, + [ERDMA_QPS_ROCEV2_SQD] = IB_QPS_SQD, + [ERDMA_QPS_ROCEV2_SQE] = IB_QPS_SQE, + [ERDMA_QPS_ROCEV2_ERROR] = IB_QPS_ERR, + }, +}; + +static inline enum erdma_qps_iwarp ib_to_iwarp_qps(enum ib_qp_state state) +{ + return ib_qps_to_erdma_qps[ERDMA_PROTO_IWARP][state]; +} + +static inline enum erdma_qps_rocev2 ib_to_rocev2_qps(enum ib_qp_state state) +{ + return ib_qps_to_erdma_qps[ERDMA_PROTO_ROCEV2][state]; +} + +static inline enum ib_qp_state iwarp_to_ib_qps(enum erdma_qps_iwarp state) +{ + return erdma_qps_to_ib_qps[ERDMA_PROTO_IWARP][state]; +} + +static inline enum ib_qp_state rocev2_to_ib_qps(enum erdma_qps_rocev2 state) +{ + return erdma_qps_to_ib_qps[ERDMA_PROTO_ROCEV2][state]; +} + +static int erdma_check_qp_attrs(struct erdma_qp *qp, struct ib_qp_attr *attr, + int attr_mask) +{ + enum ib_qp_state cur_state, nxt_state; + struct erdma_dev *dev = qp->dev; + int ret = -EINVAL; + + if (attr_mask & ~IB_QP_ATTR_STANDARD_BITS) { + ret = -EOPNOTSUPP; + goto out; + } + + if ((attr_mask & IB_QP_PORT) && + !rdma_is_port_valid(&dev->ibdev, attr->port_num)) + goto out; + + if (erdma_device_rocev2(dev)) { + cur_state = (attr_mask & IB_QP_CUR_STATE) ? + attr->cur_qp_state : + rocev2_to_ib_qps(qp->attrs.rocev2.state); + + nxt_state = (attr_mask & IB_QP_STATE) ? attr->qp_state : + cur_state; + + if (!ib_modify_qp_is_ok(cur_state, nxt_state, qp->ibqp.qp_type, + attr_mask)) + goto out; + + if ((attr_mask & IB_QP_AV) && + erdma_check_gid_attr( + rdma_ah_read_grh(&attr->ah_attr)->sgid_attr)) + goto out; + + if ((attr_mask & IB_QP_PKEY_INDEX) && + attr->pkey_index >= ERDMA_MAX_PKEYS) + goto out; + } + + return 0; + +out: + return ret; +} + +static void erdma_init_mod_qp_params_rocev2( + struct erdma_qp *qp, struct erdma_mod_qp_params_rocev2 *params, + int *erdma_attr_mask, struct ib_qp_attr *attr, int ib_attr_mask) +{ + enum erdma_qpa_mask_rocev2 to_modify_attrs = 0; + enum erdma_qps_rocev2 cur_state, nxt_state; + u16 udp_sport; + + if (ib_attr_mask & IB_QP_CUR_STATE) + cur_state = ib_to_rocev2_qps(attr->cur_qp_state); + else + cur_state = qp->attrs.rocev2.state; + + if (ib_attr_mask & IB_QP_STATE) + nxt_state = ib_to_rocev2_qps(attr->qp_state); + else + nxt_state = cur_state; + + to_modify_attrs |= ERDMA_QPA_ROCEV2_STATE; + params->state = nxt_state; + + if (ib_attr_mask & IB_QP_QKEY) { + to_modify_attrs |= ERDMA_QPA_ROCEV2_QKEY; + params->qkey = attr->qkey; + } + + if (ib_attr_mask & IB_QP_SQ_PSN) { + to_modify_attrs |= ERDMA_QPA_ROCEV2_SQ_PSN; + params->sq_psn = attr->sq_psn; + } + + if (ib_attr_mask & IB_QP_RQ_PSN) { + to_modify_attrs |= ERDMA_QPA_ROCEV2_RQ_PSN; + params->rq_psn = attr->rq_psn; + } + + if (ib_attr_mask & IB_QP_DEST_QPN) { + to_modify_attrs |= ERDMA_QPA_ROCEV2_DST_QPN; + params->dst_qpn = attr->dest_qp_num; + } + + if (ib_attr_mask & IB_QP_AV) { + to_modify_attrs |= ERDMA_QPA_ROCEV2_AV; + udp_sport = rdma_get_udp_sport(attr->ah_attr.grh.flow_label, + QP_ID(qp), params->dst_qpn); + erdma_attr_to_av(&attr->ah_attr, ¶ms->av, udp_sport); + } + + *erdma_attr_mask = to_modify_attrs; +} + int erdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { - struct erdma_qp_attrs new_attrs; - enum erdma_qp_attr_mask erdma_attr_mask = 0; struct erdma_qp *qp = to_eqp(ibqp); - int ret = 0; - - if (attr_mask & ~IB_QP_ATTR_STANDARD_BITS) - return -EOPNOTSUPP; - - memset(&new_attrs, 0, sizeof(new_attrs)); - - if (attr_mask & IB_QP_STATE) { - new_attrs.state = ib_qp_state_to_erdma_qp_state[attr->qp_state]; - - erdma_attr_mask |= ERDMA_QP_ATTR_STATE; - } + union erdma_mod_qp_params params; + int ret = 0, erdma_attr_mask = 0; down_write(&qp->state_lock); - ret = erdma_modify_qp_internal(qp, &new_attrs, erdma_attr_mask); + ret = erdma_check_qp_attrs(qp, attr, attr_mask); + if (ret) + goto out; + if (erdma_device_iwarp(qp->dev)) { + if (attr_mask & IB_QP_STATE) { + erdma_attr_mask |= ERDMA_QPA_IWARP_STATE; + params.iwarp.state = ib_to_iwarp_qps(attr->qp_state); + } + + ret = erdma_modify_qp_state_iwarp(qp, ¶ms.iwarp, + erdma_attr_mask); + } else { + erdma_init_mod_qp_params_rocev2( + qp, ¶ms.rocev2, &erdma_attr_mask, attr, attr_mask); + + ret = erdma_modify_qp_state_rocev2(qp, ¶ms.rocev2, + erdma_attr_mask); + } + +out: up_write(&qp->state_lock); - return ret; } static enum ib_qp_state query_qp_state(struct erdma_qp *qp) { - switch (qp->attrs.state) { - case ERDMA_QP_STATE_IDLE: - return IB_QPS_INIT; - case ERDMA_QP_STATE_RTR: - return IB_QPS_RTR; - case ERDMA_QP_STATE_RTS: - return IB_QPS_RTS; - case ERDMA_QP_STATE_CLOSING: - return IB_QPS_ERR; - case ERDMA_QP_STATE_TERMINATE: - return IB_QPS_ERR; - case ERDMA_QP_STATE_ERROR: - return IB_QPS_ERR; - default: - return IB_QPS_ERR; - } + if (erdma_device_iwarp(qp->dev)) + return iwarp_to_ib_qps(qp->attrs.iwarp.state); + else + return rocev2_to_ib_qps(qp->attrs.rocev2.state); } int erdma_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) { + struct erdma_cmdq_query_qp_req_rocev2 req; struct erdma_dev *dev; struct erdma_qp *qp; + u64 resp0, resp1; + int ret; if (ibqp && qp_attr && qp_init_attr) { qp = to_eqp(ibqp); @@ -1595,8 +1831,37 @@ int erdma_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_init_attr->cap = qp_attr->cap; - qp_attr->qp_state = query_qp_state(qp); - qp_attr->cur_qp_state = query_qp_state(qp); + if (erdma_device_rocev2(dev)) { + /* Query hardware to get some attributes */ + erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA, + CMDQ_OPCODE_QUERY_QP); + req.qpn = QP_ID(qp); + + ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), &resp0, + &resp1, true); + if (ret) + return ret; + + qp_attr->sq_psn = + FIELD_GET(ERDMA_CMD_QUERY_QP_RESP_SQ_PSN_MASK, resp0); + qp_attr->rq_psn = + FIELD_GET(ERDMA_CMD_QUERY_QP_RESP_RQ_PSN_MASK, resp0); + qp_attr->qp_state = rocev2_to_ib_qps(FIELD_GET( + ERDMA_CMD_QUERY_QP_RESP_QP_STATE_MASK, resp0)); + qp_attr->cur_qp_state = qp_attr->qp_state; + qp_attr->sq_draining = FIELD_GET( + ERDMA_CMD_QUERY_QP_RESP_SQ_DRAINING_MASK, resp0); + + qp_attr->pkey_index = 0; + qp_attr->dest_qp_num = qp->attrs.rocev2.dst_qpn; + + if (qp->ibqp.qp_type == IB_QPT_RC) + erdma_av_to_attr(&qp->attrs.rocev2.av, + &qp_attr->ah_attr); + } else { + qp_attr->qp_state = query_qp_state(qp); + qp_attr->cur_qp_state = qp_attr->qp_state; + } return 0; } @@ -1736,7 +2001,7 @@ void erdma_set_mtu(struct erdma_dev *dev, u32 mtu) CMDQ_OPCODE_CONF_MTU); req.mtu = mtu; - erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, true); } void erdma_port_event(struct erdma_dev *dev, enum ib_event_type reason) @@ -1806,7 +2071,8 @@ static int erdma_query_hw_stats(struct erdma_dev *dev, req.target_addr = dma_addr; req.target_length = ERDMA_HW_RESP_SIZE; - err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL); + err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); if (err) goto out; @@ -1839,3 +2105,159 @@ int erdma_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, return stats->num_counters; } + +enum rdma_link_layer erdma_get_link_layer(struct ib_device *ibdev, u32 port_num) +{ + return IB_LINK_LAYER_ETHERNET; +} + +static int erdma_set_gid(struct erdma_dev *dev, u8 op, u32 idx, + const union ib_gid *gid) +{ + struct erdma_cmdq_set_gid_req req; + u8 ntype; + + req.cfg = FIELD_PREP(ERDMA_CMD_SET_GID_SGID_IDX_MASK, idx) | + FIELD_PREP(ERDMA_CMD_SET_GID_OP_MASK, op); + + if (op == ERDMA_SET_GID_OP_ADD) { + if (ipv6_addr_v4mapped((struct in6_addr *)gid)) + ntype = ERDMA_NETWORK_TYPE_IPV4; + else + ntype = ERDMA_NETWORK_TYPE_IPV6; + + req.cfg |= FIELD_PREP(ERDMA_CMD_SET_GID_NTYPE_MASK, ntype); + + memcpy(&req.gid, gid, ERDMA_ROCEV2_GID_SIZE); + } + + erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA, + CMDQ_OPCODE_SET_GID); + return erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + true); +} + +int erdma_add_gid(const struct ib_gid_attr *attr, void **context) +{ + struct erdma_dev *dev = to_edev(attr->device); + int ret; + + ret = erdma_check_gid_attr(attr); + if (ret) + return ret; + + return erdma_set_gid(dev, ERDMA_SET_GID_OP_ADD, attr->index, + &attr->gid); +} + +int erdma_del_gid(const struct ib_gid_attr *attr, void **context) +{ + return erdma_set_gid(to_edev(attr->device), ERDMA_SET_GID_OP_DEL, + attr->index, NULL); +} + +int erdma_query_pkey(struct ib_device *ibdev, u32 port, u16 index, u16 *pkey) +{ + if (index >= ERDMA_MAX_PKEYS) + return -EINVAL; + + *pkey = ERDMA_DEFAULT_PKEY; + return 0; +} + +void erdma_set_av_cfg(struct erdma_av_cfg *av_cfg, struct erdma_av *av) +{ + av_cfg->cfg0 = FIELD_PREP(ERDMA_CMD_CREATE_AV_FL_MASK, av->flow_label) | + FIELD_PREP(ERDMA_CMD_CREATE_AV_NTYPE_MASK, av->ntype); + + av_cfg->traffic_class = av->traffic_class; + av_cfg->hop_limit = av->hop_limit; + av_cfg->sl = av->sl; + + av_cfg->udp_sport = av->udp_sport; + av_cfg->sgid_index = av->sgid_index; + + ether_addr_copy(av_cfg->dmac, av->dmac); + memcpy(av_cfg->dgid, av->dgid, ERDMA_ROCEV2_GID_SIZE); +} + +int erdma_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) +{ + const struct ib_global_route *grh = + rdma_ah_read_grh(init_attr->ah_attr); + struct erdma_dev *dev = to_edev(ibah->device); + struct erdma_pd *pd = to_epd(ibah->pd); + struct erdma_ah *ah = to_eah(ibah); + struct erdma_cmdq_create_ah_req req; + u32 udp_sport; + int ret; + + ret = erdma_check_gid_attr(grh->sgid_attr); + if (ret) + return ret; + + ret = erdma_alloc_idx(&dev->res_cb[ERDMA_RES_TYPE_AH]); + if (ret < 0) + return ret; + + ah->ahn = ret; + + if (grh->flow_label) + udp_sport = rdma_flow_label_to_udp_sport(grh->flow_label); + else + udp_sport = + IB_ROCE_UDP_ENCAP_VALID_PORT_MIN + (ah->ahn & 0x3FFF); + + erdma_attr_to_av(init_attr->ah_attr, &ah->av, udp_sport); + + erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA, + CMDQ_OPCODE_CREATE_AH); + + req.pdn = pd->pdn; + req.ahn = ah->ahn; + erdma_set_av_cfg(&req.av_cfg, &ah->av); + + ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + init_attr->flags & RDMA_CREATE_AH_SLEEPABLE); + if (ret) { + erdma_free_idx(&dev->res_cb[ERDMA_RES_TYPE_AH], ah->ahn); + return ret; + } + + return 0; +} + +int erdma_destroy_ah(struct ib_ah *ibah, u32 flags) +{ + struct erdma_dev *dev = to_edev(ibah->device); + struct erdma_pd *pd = to_epd(ibah->pd); + struct erdma_ah *ah = to_eah(ibah); + struct erdma_cmdq_destroy_ah_req req; + int ret; + + erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA, + CMDQ_OPCODE_DESTROY_AH); + + req.pdn = pd->pdn; + req.ahn = ah->ahn; + + ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL, + flags & RDMA_DESTROY_AH_SLEEPABLE); + if (ret) + return ret; + + erdma_free_idx(&dev->res_cb[ERDMA_RES_TYPE_AH], ah->ahn); + + return 0; +} + +int erdma_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr) +{ + struct erdma_ah *ah = to_eah(ibah); + + memset(ah_attr, 0, sizeof(*ah_attr)); + erdma_av_to_attr(&ah->av, ah_attr); + + return 0; +} diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.h b/drivers/infiniband/hw/erdma/erdma_verbs.h index c998acd39a78..f9408ccc8bad 100644 --- a/drivers/infiniband/hw/erdma/erdma_verbs.h +++ b/drivers/infiniband/hw/erdma/erdma_verbs.h @@ -136,6 +136,25 @@ struct erdma_user_dbrecords_page { int refcnt; }; +struct erdma_av { + u8 port; + u8 hop_limit; + u8 traffic_class; + u8 sl; + u8 sgid_index; + u16 udp_sport; + u32 flow_label; + u8 dmac[ETH_ALEN]; + u8 dgid[ERDMA_ROCEV2_GID_SIZE]; + enum erdma_network_type ntype; +}; + +struct erdma_ah { + struct ib_ah ibah; + struct erdma_av av; + u32 ahn; +}; + struct erdma_uqp { struct erdma_mem sq_mem; struct erdma_mem rq_mem; @@ -176,33 +195,91 @@ struct erdma_kqp { u8 sig_all; }; -enum erdma_qp_state { - ERDMA_QP_STATE_IDLE = 0, - ERDMA_QP_STATE_RTR = 1, - ERDMA_QP_STATE_RTS = 2, - ERDMA_QP_STATE_CLOSING = 3, - ERDMA_QP_STATE_TERMINATE = 4, - ERDMA_QP_STATE_ERROR = 5, - ERDMA_QP_STATE_UNDEF = 7, - ERDMA_QP_STATE_COUNT = 8 +enum erdma_qps_iwarp { + ERDMA_QPS_IWARP_IDLE = 0, + ERDMA_QPS_IWARP_RTR = 1, + ERDMA_QPS_IWARP_RTS = 2, + ERDMA_QPS_IWARP_CLOSING = 3, + ERDMA_QPS_IWARP_TERMINATE = 4, + ERDMA_QPS_IWARP_ERROR = 5, + ERDMA_QPS_IWARP_UNDEF = 6, + ERDMA_QPS_IWARP_COUNT = 7, }; -enum erdma_qp_attr_mask { - ERDMA_QP_ATTR_STATE = (1 << 0), - ERDMA_QP_ATTR_LLP_HANDLE = (1 << 2), - ERDMA_QP_ATTR_ORD = (1 << 3), - ERDMA_QP_ATTR_IRD = (1 << 4), - ERDMA_QP_ATTR_SQ_SIZE = (1 << 5), - ERDMA_QP_ATTR_RQ_SIZE = (1 << 6), - ERDMA_QP_ATTR_MPA = (1 << 7) +enum erdma_qpa_mask_iwarp { + ERDMA_QPA_IWARP_STATE = (1 << 0), + ERDMA_QPA_IWARP_LLP_HANDLE = (1 << 2), + ERDMA_QPA_IWARP_ORD = (1 << 3), + ERDMA_QPA_IWARP_IRD = (1 << 4), + ERDMA_QPA_IWARP_SQ_SIZE = (1 << 5), + ERDMA_QPA_IWARP_RQ_SIZE = (1 << 6), + ERDMA_QPA_IWARP_MPA = (1 << 7), + ERDMA_QPA_IWARP_CC = (1 << 8), +}; + +enum erdma_qps_rocev2 { + ERDMA_QPS_ROCEV2_RESET = 0, + ERDMA_QPS_ROCEV2_INIT = 1, + ERDMA_QPS_ROCEV2_RTR = 2, + ERDMA_QPS_ROCEV2_RTS = 3, + ERDMA_QPS_ROCEV2_SQD = 4, + ERDMA_QPS_ROCEV2_SQE = 5, + ERDMA_QPS_ROCEV2_ERROR = 6, + ERDMA_QPS_ROCEV2_COUNT = 7, +}; + +enum erdma_qpa_mask_rocev2 { + ERDMA_QPA_ROCEV2_STATE = (1 << 0), + ERDMA_QPA_ROCEV2_QKEY = (1 << 1), + ERDMA_QPA_ROCEV2_AV = (1 << 2), + ERDMA_QPA_ROCEV2_SQ_PSN = (1 << 3), + ERDMA_QPA_ROCEV2_RQ_PSN = (1 << 4), + ERDMA_QPA_ROCEV2_DST_QPN = (1 << 5), }; enum erdma_qp_flags { ERDMA_QP_IN_FLUSHING = (1 << 0), }; +#define ERDMA_QP_ACTIVE 0 +#define ERDMA_QP_PASSIVE 1 + +struct erdma_mod_qp_params_iwarp { + enum erdma_qps_iwarp state; + enum erdma_cc_alg cc; + u8 qp_type; + u8 pd_len; + u32 irq_size; + u32 orq_size; +}; + +struct erdma_qp_attrs_iwarp { + enum erdma_qps_iwarp state; + u32 cookie; +}; + +struct erdma_mod_qp_params_rocev2 { + enum erdma_qps_rocev2 state; + u32 qkey; + u32 sq_psn; + u32 rq_psn; + u32 dst_qpn; + struct erdma_av av; +}; + +union erdma_mod_qp_params { + struct erdma_mod_qp_params_iwarp iwarp; + struct erdma_mod_qp_params_rocev2 rocev2; +}; + +struct erdma_qp_attrs_rocev2 { + enum erdma_qps_rocev2 state; + u32 qkey; + u32 dst_qpn; + struct erdma_av av; +}; + struct erdma_qp_attrs { - enum erdma_qp_state state; enum erdma_cc_alg cc; /* Congestion control algorithm */ u32 sq_size; u32 rq_size; @@ -210,11 +287,10 @@ struct erdma_qp_attrs { u32 irq_size; u32 max_send_sge; u32 max_recv_sge; - u32 cookie; -#define ERDMA_QP_ACTIVE 0 -#define ERDMA_QP_PASSIVE 1 - u8 qp_type; - u8 pd_len; + union { + struct erdma_qp_attrs_iwarp iwarp; + struct erdma_qp_attrs_rocev2 rocev2; + }; }; struct erdma_qp { @@ -286,11 +362,25 @@ static inline struct erdma_cq *find_cq_by_cqn(struct erdma_dev *dev, int id) void erdma_qp_get(struct erdma_qp *qp); void erdma_qp_put(struct erdma_qp *qp); -int erdma_modify_qp_internal(struct erdma_qp *qp, struct erdma_qp_attrs *attrs, - enum erdma_qp_attr_mask mask); +int erdma_modify_qp_state_iwarp(struct erdma_qp *qp, + struct erdma_mod_qp_params_iwarp *params, + int mask); +int erdma_modify_qp_state_rocev2(struct erdma_qp *qp, + struct erdma_mod_qp_params_rocev2 *params, + int attr_mask); void erdma_qp_llp_close(struct erdma_qp *qp); void erdma_qp_cm_drop(struct erdma_qp *qp); +static inline bool erdma_device_iwarp(struct erdma_dev *dev) +{ + return dev->proto == ERDMA_PROTO_IWARP; +} + +static inline bool erdma_device_rocev2(struct erdma_dev *dev) +{ + return dev->proto == ERDMA_PROTO_ROCEV2; +} + static inline struct erdma_ucontext *to_ectx(struct ib_ucontext *ibctx) { return container_of(ibctx, struct erdma_ucontext, ibucontext); @@ -316,6 +406,21 @@ static inline struct erdma_cq *to_ecq(struct ib_cq *ibcq) return container_of(ibcq, struct erdma_cq, ibcq); } +static inline struct erdma_ah *to_eah(struct ib_ah *ibah) +{ + return container_of(ibah, struct erdma_ah, ibah); +} + +static inline int erdma_check_gid_attr(const struct ib_gid_attr *attr) +{ + u8 ntype = rdma_gid_attr_network_type(attr); + + if (ntype != RDMA_NETWORK_IPV4 && ntype != RDMA_NETWORK_IPV6) + return -EINVAL; + + return 0; +} + static inline struct erdma_user_mmap_entry * to_emmap(struct rdma_user_mmap_entry *ibmmap) { @@ -360,6 +465,7 @@ int erdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *send_wr, int erdma_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); int erdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc); +void erdma_remove_cqes_of_qp(struct ib_cq *ibcq, u32 qpn); struct ib_mr *erdma_ib_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type, u32 max_num_sg); int erdma_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, @@ -370,5 +476,15 @@ struct rdma_hw_stats *erdma_alloc_hw_port_stats(struct ib_device *device, u32 port_num); int erdma_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, u32 port, int index); +enum rdma_link_layer erdma_get_link_layer(struct ib_device *ibdev, + u32 port_num); +int erdma_add_gid(const struct ib_gid_attr *attr, void **context); +int erdma_del_gid(const struct ib_gid_attr *attr, void **context); +int erdma_query_pkey(struct ib_device *ibdev, u32 port, u16 index, u16 *pkey); +void erdma_set_av_cfg(struct erdma_av_cfg *av_cfg, struct erdma_av *av); +int erdma_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata); +int erdma_destroy_ah(struct ib_ah *ibah, u32 flags); +int erdma_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr); #endif diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index eb38f81aeeb1..cb630551cf1a 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -2339,20 +2339,6 @@ static inline u64 hfi1_pkt_base_sdma_integrity(struct hfi1_devdata *dd) dev_err(&(dd)->pcidev->dev, "%s: port %u: " fmt, \ rvt_get_ibdev_name(&(dd)->verbs_dev.rdi), (port), ##__VA_ARGS__) -/* - * this is used for formatting hw error messages... - */ -struct hfi1_hwerror_msgs { - u64 mask; - const char *msg; - size_t sz; -}; - -/* in intr.c... */ -void hfi1_format_hwerrors(u64 hwerrs, - const struct hfi1_hwerror_msgs *hwerrmsgs, - size_t nhwerrmsgs, char *msg, size_t lmsg); - #define USER_OPCODE_CHECK_VAL 0xC0 #define USER_OPCODE_CHECK_MASK 0xC0 #define OPCODE_CHECK_VAL_DISABLED 0x0 diff --git a/drivers/infiniband/hw/hfi1/intr.c b/drivers/infiniband/hw/hfi1/intr.c index 3737f632d62a..d8dd1a599631 100644 --- a/drivers/infiniband/hw/hfi1/intr.c +++ b/drivers/infiniband/hw/hfi1/intr.c @@ -47,37 +47,6 @@ static void add_full_mgmt_pkey(struct hfi1_pportdata *ppd) hfi1_event_pkey_change(ppd->dd, ppd->port); } -/** - * format_hwmsg - format a single hwerror message - * @msg: message buffer - * @msgl: length of message buffer - * @hwmsg: message to add to message buffer - */ -static void format_hwmsg(char *msg, size_t msgl, const char *hwmsg) -{ - strlcat(msg, "[", msgl); - strlcat(msg, hwmsg, msgl); - strlcat(msg, "]", msgl); -} - -/** - * hfi1_format_hwerrors - format hardware error messages for display - * @hwerrs: hardware errors bit vector - * @hwerrmsgs: hardware error descriptions - * @nhwerrmsgs: number of hwerrmsgs - * @msg: message buffer - * @msgl: message buffer length - */ -void hfi1_format_hwerrors(u64 hwerrs, const struct hfi1_hwerror_msgs *hwerrmsgs, - size_t nhwerrmsgs, char *msg, size_t msgl) -{ - int i; - - for (i = 0; i < nhwerrmsgs; i++) - if (hwerrs & hwerrmsgs[i].mask) - format_hwmsg(msg, msgl, hwerrmsgs[i].msg); -} - static void signal_ib_event(struct hfi1_pportdata *ppd, enum ib_event_type ev) { struct ib_event event; diff --git a/drivers/infiniband/hw/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h index 49805a24bb0a..7259f4f55700 100644 --- a/drivers/infiniband/hw/hfi1/iowait.h +++ b/drivers/infiniband/hw/hfi1/iowait.h @@ -92,7 +92,7 @@ struct iowait_work { * * The lock field is used by waiters to record * the seqlock_t that guards the list head. - * Waiters explicity know that, but the destroy + * Waiters explicitly know that, but the destroy * code that unwaits QPs does not. */ struct iowait { diff --git a/drivers/infiniband/hw/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c index d62ba5fdd80c..d94216c7d576 100644 --- a/drivers/infiniband/hw/hfi1/sysfs.c +++ b/drivers/infiniband/hw/hfi1/sysfs.c @@ -27,8 +27,8 @@ static struct hfi1_pportdata *hfi1_get_pportdata_kobj(struct kobject *kobj) * Congestion control table size followed by table entries */ static ssize_t cc_table_bin_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t pos, size_t count) + const struct bin_attribute *bin_attr, + char *buf, loff_t pos, size_t count) { int ret; struct hfi1_pportdata *ppd = hfi1_get_pportdata_kobj(kobj); @@ -57,7 +57,7 @@ static ssize_t cc_table_bin_read(struct file *filp, struct kobject *kobj, return count; } -static BIN_ATTR_RO(cc_table_bin, PAGE_SIZE); +static const BIN_ATTR_RO(cc_table_bin, PAGE_SIZE); /* * Congestion settings: port control, control map and an array of 16 @@ -65,7 +65,7 @@ static BIN_ATTR_RO(cc_table_bin, PAGE_SIZE); * trigger threshold and the minimum injection rate delay. */ static ssize_t cc_setting_bin_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct hfi1_pportdata *ppd = hfi1_get_pportdata_kobj(kobj); @@ -93,9 +93,9 @@ static ssize_t cc_setting_bin_read(struct file *filp, struct kobject *kobj, return count; } -static BIN_ATTR_RO(cc_setting_bin, PAGE_SIZE); +static const BIN_ATTR_RO(cc_setting_bin, PAGE_SIZE); -static struct bin_attribute *port_cc_bin_attributes[] = { +static const struct bin_attribute *const port_cc_bin_attributes[] = { &bin_attr_cc_setting_bin, &bin_attr_cc_table_bin, NULL @@ -134,7 +134,7 @@ static struct attribute *port_cc_attributes[] = { static const struct attribute_group port_cc_group = { .name = "CCMgtA", .attrs = port_cc_attributes, - .bin_attrs = port_cc_bin_attributes, + .bin_attrs_new = port_cc_bin_attributes, }; /* Start sc2vl */ diff --git a/drivers/infiniband/hw/hns/Kconfig b/drivers/infiniband/hw/hns/Kconfig index ab3fbba70789..44cdb706fe27 100644 --- a/drivers/infiniband/hw/hns/Kconfig +++ b/drivers/infiniband/hw/hns/Kconfig @@ -1,21 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only -config INFINIBAND_HNS - tristate "HNS RoCE Driver" - depends on NET_VENDOR_HISILICON - depends on ARM64 || (COMPILE_TEST && 64BIT) - depends on (HNS_DSAF && HNS_ENET) || HNS3 - help - This is a RoCE/RDMA driver for the Hisilicon RoCE engine. - - To compile HIP08 driver as module, choose M here. - config INFINIBAND_HNS_HIP08 - bool "Hisilicon Hip08 Family RoCE support" - depends on INFINIBAND_HNS && PCI && HNS3 - depends on INFINIBAND_HNS=m || HNS3=y + tristate "Hisilicon Hip08 Family RoCE support" + depends on ARM64 || (COMPILE_TEST && 64BIT) + depends on PCI && HNS3 help RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip08 SoC. The RoCE engine is a PCI device. - To compile this driver, choose Y here: if INFINIBAND_HNS is m, this - module will be called hns-roce-hw-v2. + To compile this driver, choose M here. This module will be called + hns-roce-hw-v2. diff --git a/drivers/infiniband/hw/hns/Makefile b/drivers/infiniband/hw/hns/Makefile index be1e1cdbcfa8..7917af8e6380 100644 --- a/drivers/infiniband/hw/hns/Makefile +++ b/drivers/infiniband/hw/hns/Makefile @@ -5,12 +5,9 @@ ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3 -hns-roce-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_pd.o \ +hns-roce-hw-v2-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_pd.o \ hns_roce_ah.o hns_roce_hem.o hns_roce_mr.o hns_roce_qp.o \ hns_roce_cq.o hns_roce_alloc.o hns_roce_db.o hns_roce_srq.o hns_roce_restrack.o \ - hns_roce_debugfs.o + hns_roce_debugfs.o hns_roce_hw_v2.o -ifdef CONFIG_INFINIBAND_HNS_HIP08 -hns-roce-hw-v2-objs := hns_roce_hw_v2.o $(hns-roce-objs) -obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v2.o -endif +obj-$(CONFIG_INFINIBAND_HNS_HIP08) += hns-roce-hw-v2.o diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index f84521be3bea..605562122ecc 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -931,6 +931,7 @@ struct hns_roce_hem_item { size_t count; /* max ba numbers */ int start; /* start buf offset in this hem */ int end; /* end buf offset in this hem */ + bool exist_bt; }; /* All HEM items are linked in a tree structure */ @@ -959,6 +960,7 @@ hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count, } } + hem->exist_bt = exist_bt; hem->count = count; hem->start = start; hem->end = end; @@ -969,22 +971,22 @@ hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count, } static void hem_list_free_item(struct hns_roce_dev *hr_dev, - struct hns_roce_hem_item *hem, bool exist_bt) + struct hns_roce_hem_item *hem) { - if (exist_bt) + if (hem->exist_bt) dma_free_coherent(hr_dev->dev, hem->count * BA_BYTE_LEN, hem->addr, hem->dma_addr); kfree(hem); } static void hem_list_free_all(struct hns_roce_dev *hr_dev, - struct list_head *head, bool exist_bt) + struct list_head *head) { struct hns_roce_hem_item *hem, *temp_hem; list_for_each_entry_safe(hem, temp_hem, head, list) { list_del(&hem->list); - hem_list_free_item(hr_dev, hem, exist_bt); + hem_list_free_item(hr_dev, hem); } } @@ -1084,6 +1086,10 @@ int hns_roce_hem_list_calc_root_ba(const struct hns_roce_buf_region *regions, for (i = 0; i < region_cnt; i++) { r = (struct hns_roce_buf_region *)®ions[i]; + /* when r->hopnum = 0, the region should not occupy root_ba. */ + if (!r->hopnum) + continue; + if (r->hopnum > 1) { step = hem_list_calc_ba_range(r->hopnum, 1, unit); if (step > 0) @@ -1177,7 +1183,7 @@ static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev, err_exit: for (level = 1; level < hopnum; level++) - hem_list_free_all(hr_dev, &temp_list[level], true); + hem_list_free_all(hr_dev, &temp_list[level]); return ret; } @@ -1218,16 +1224,26 @@ static int alloc_fake_root_bt(struct hns_roce_dev *hr_dev, void *cpu_base, { struct hns_roce_hem_item *hem; + /* This is on the has_mtt branch, if r->hopnum + * is 0, there is no root_ba to reuse for the + * region's fake hem, so a dma_alloc request is + * necessary here. + */ hem = hem_list_alloc_item(hr_dev, r->offset, r->offset + r->count - 1, - r->count, false); + r->count, !r->hopnum); if (!hem) return -ENOMEM; - hem_list_assign_bt(hem, cpu_base, phy_base); + /* The root_ba can be reused only when r->hopnum > 0. */ + if (r->hopnum) + hem_list_assign_bt(hem, cpu_base, phy_base); list_add(&hem->list, branch_head); list_add(&hem->sibling, leaf_head); - return r->count; + /* If r->hopnum == 0, 0 is returned, + * so that the root_bt entry is not occupied. + */ + return r->hopnum ? r->count : 0; } static int setup_middle_bt(struct hns_roce_dev *hr_dev, void *cpu_base, @@ -1271,7 +1287,7 @@ setup_root_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem_list *hem_list, return -ENOMEM; total = 0; - for (i = 0; i < region_cnt && total < max_ba_num; i++) { + for (i = 0; i < region_cnt && total <= max_ba_num; i++) { r = ®ions[i]; if (!r->count) continue; @@ -1337,9 +1353,9 @@ static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev, region_cnt); if (ret) { for (i = 0; i < region_cnt; i++) - hem_list_free_all(hr_dev, &head.branch[i], false); + hem_list_free_all(hr_dev, &head.branch[i]); - hem_list_free_all(hr_dev, &head.root, true); + hem_list_free_all(hr_dev, &head.root); } return ret; @@ -1402,10 +1418,9 @@ void hns_roce_hem_list_release(struct hns_roce_dev *hr_dev, for (i = 0; i < HNS_ROCE_MAX_BT_REGION; i++) for (j = 0; j < HNS_ROCE_MAX_BT_LEVEL; j++) - hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j], - j != 0); + hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j]); - hem_list_free_all(hr_dev, &hem_list->root_bt, true); + hem_list_free_all(hr_dev, &hem_list->root_bt); INIT_LIST_HEAD(&hem_list->btm_bt); hem_list->root_ba = 0; } diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 697b17cca02e..dded339802b3 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -468,7 +468,7 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp, valid_num_sge = calc_wr_sge_num(wr, &msg_len); ret = set_ud_opcode(ud_sq_wqe, wr); - if (WARN_ON(ret)) + if (WARN_ON_ONCE(ret)) return ret; ud_sq_wqe->msg_len = cpu_to_le32(msg_len); @@ -572,7 +572,7 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp, rc_sq_wqe->msg_len = cpu_to_le32(msg_len); ret = set_rc_opcode(hr_dev, rc_sq_wqe, wr); - if (WARN_ON(ret)) + if (WARN_ON_ONCE(ret)) return ret; hr_reg_write(rc_sq_wqe, RC_SEND_WQE_SO, @@ -670,6 +670,10 @@ static void write_dwqe(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp, #define HNS_ROCE_SL_SHIFT 2 struct hns_roce_v2_rc_send_wqe *rc_sq_wqe = wqe; + if (unlikely(qp->state == IB_QPS_ERR)) { + flush_cqe(hr_dev, qp); + return; + } /* All kinds of DirectWQE have the same header field layout */ hr_reg_enable(rc_sq_wqe, RC_SEND_WQE_FLAG); hr_reg_write(rc_sq_wqe, RC_SEND_WQE_DB_SL_L, qp->sl); @@ -5619,6 +5623,9 @@ static void put_dip_ctx_idx(struct hns_roce_dev *hr_dev, { struct hns_roce_dip *hr_dip = hr_qp->dip; + if (!hr_dip) + return; + xa_lock(&hr_dev->qp_table.dip_xa); hr_dip->qp_cnt--; @@ -7178,9 +7185,22 @@ static int hns_roce_hw_v2_reset_notify(struct hnae3_handle *handle, return ret; } +static void hns_roce_hw_v2_link_status_change(struct hnae3_handle *handle, + bool linkup) +{ + struct hns_roce_dev *hr_dev = (struct hns_roce_dev *)handle->priv; + struct net_device *netdev = handle->rinfo.netdev; + + if (linkup || !hr_dev) + return; + + ib_dispatch_port_state_event(&hr_dev->ib_dev, netdev); +} + static const struct hnae3_client_ops hns_roce_hw_v2_ops = { .init_instance = hns_roce_hw_v2_init_instance, .uninit_instance = hns_roce_hw_v2_uninit_instance, + .link_status_change = hns_roce_hw_v2_link_status_change, .reset_notify = hns_roce_hw_v2_reset_notify, }; diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index bf30b3a65a9b..55b9283bfc6f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -814,11 +814,6 @@ int hns_roce_mtr_map(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, for (i = 0, mapped_cnt = 0; i < mtr->hem_cfg.region_count && mapped_cnt < page_cnt; i++) { r = &mtr->hem_cfg.region[i]; - /* if hopnum is 0, no need to map pages in this region */ - if (!r->hopnum) { - mapped_cnt += r->count; - continue; - } if (r->offset + r->count > page_cnt) { ret = -EINVAL; diff --git a/drivers/infiniband/hw/irdma/osdep.h b/drivers/infiniband/hw/irdma/osdep.h index e1e3d3ae72b7..ddf02a462efa 100644 --- a/drivers/infiniband/hw/irdma/osdep.h +++ b/drivers/infiniband/hw/irdma/osdep.h @@ -59,10 +59,6 @@ int irdma_cqp_sds_cmd(struct irdma_sc_dev *dev, int irdma_cqp_manage_hmc_fcn_cmd(struct irdma_sc_dev *dev, struct irdma_hmc_fcn_info *hmcfcninfo, u16 *pmf_idx); -int irdma_cqp_query_fpm_val_cmd(struct irdma_sc_dev *dev, - struct irdma_dma_mem *val_mem, u8 hmc_fn_id); -int irdma_cqp_commit_fpm_val_cmd(struct irdma_sc_dev *dev, - struct irdma_dma_mem *val_mem, u8 hmc_fn_id); int irdma_alloc_query_fpm_buf(struct irdma_sc_dev *dev, struct irdma_dma_mem *mem); void *irdma_remove_cqp_head(struct irdma_sc_dev *dev); diff --git a/drivers/infiniband/hw/irdma/protos.h b/drivers/infiniband/hw/irdma/protos.h index d7c8ea948bcd..c0c9441885d3 100644 --- a/drivers/infiniband/hw/irdma/protos.h +++ b/drivers/infiniband/hw/irdma/protos.h @@ -85,10 +85,6 @@ int irdma_process_cqp_cmd(struct irdma_sc_dev *dev, int irdma_process_bh(struct irdma_sc_dev *dev); int irdma_cqp_sds_cmd(struct irdma_sc_dev *dev, struct irdma_update_sds_info *info); -int irdma_cqp_query_fpm_val_cmd(struct irdma_sc_dev *dev, - struct irdma_dma_mem *val_mem, u8 hmc_fn_id); -int irdma_cqp_commit_fpm_val_cmd(struct irdma_sc_dev *dev, - struct irdma_dma_mem *val_mem, u8 hmc_fn_id); int irdma_alloc_query_fpm_buf(struct irdma_sc_dev *dev, struct irdma_dma_mem *mem); int irdma_cqp_manage_hmc_fcn_cmd(struct irdma_sc_dev *dev, diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index 0422787592d8..0e594122baa7 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -320,9 +320,6 @@ int irdma_netdevice_event(struct notifier_block *notifier, unsigned long event, case NETDEV_DOWN: iwdev->iw_status = 0; fallthrough; - case NETDEV_UP: - irdma_port_ibevent(iwdev); - break; default: break; } @@ -971,74 +968,6 @@ void irdma_terminate_del_timer(struct irdma_sc_qp *qp) irdma_qp_rem_ref(&iwqp->ibqp); } -/** - * irdma_cqp_query_fpm_val_cmd - send cqp command for fpm - * @dev: function device struct - * @val_mem: buffer for fpm - * @hmc_fn_id: function id for fpm - */ -int irdma_cqp_query_fpm_val_cmd(struct irdma_sc_dev *dev, - struct irdma_dma_mem *val_mem, u8 hmc_fn_id) -{ - struct irdma_cqp_request *cqp_request; - struct cqp_cmds_info *cqp_info; - struct irdma_pci_f *rf = dev_to_rf(dev); - int status; - - cqp_request = irdma_alloc_and_get_cqp_request(&rf->cqp, true); - if (!cqp_request) - return -ENOMEM; - - cqp_info = &cqp_request->info; - cqp_request->param = NULL; - cqp_info->in.u.query_fpm_val.cqp = dev->cqp; - cqp_info->in.u.query_fpm_val.fpm_val_pa = val_mem->pa; - cqp_info->in.u.query_fpm_val.fpm_val_va = val_mem->va; - cqp_info->in.u.query_fpm_val.hmc_fn_id = hmc_fn_id; - cqp_info->cqp_cmd = IRDMA_OP_QUERY_FPM_VAL; - cqp_info->post_sq = 1; - cqp_info->in.u.query_fpm_val.scratch = (uintptr_t)cqp_request; - - status = irdma_handle_cqp_op(rf, cqp_request); - irdma_put_cqp_request(&rf->cqp, cqp_request); - - return status; -} - -/** - * irdma_cqp_commit_fpm_val_cmd - commit fpm values in hw - * @dev: hardware control device structure - * @val_mem: buffer with fpm values - * @hmc_fn_id: function id for fpm - */ -int irdma_cqp_commit_fpm_val_cmd(struct irdma_sc_dev *dev, - struct irdma_dma_mem *val_mem, u8 hmc_fn_id) -{ - struct irdma_cqp_request *cqp_request; - struct cqp_cmds_info *cqp_info; - struct irdma_pci_f *rf = dev_to_rf(dev); - int status; - - cqp_request = irdma_alloc_and_get_cqp_request(&rf->cqp, true); - if (!cqp_request) - return -ENOMEM; - - cqp_info = &cqp_request->info; - cqp_request->param = NULL; - cqp_info->in.u.commit_fpm_val.cqp = dev->cqp; - cqp_info->in.u.commit_fpm_val.fpm_val_pa = val_mem->pa; - cqp_info->in.u.commit_fpm_val.fpm_val_va = val_mem->va; - cqp_info->in.u.commit_fpm_val.hmc_fn_id = hmc_fn_id; - cqp_info->cqp_cmd = IRDMA_OP_COMMIT_FPM_VAL; - cqp_info->post_sq = 1; - cqp_info->in.u.commit_fpm_val.scratch = (uintptr_t)cqp_request; - - status = irdma_handle_cqp_op(rf, cqp_request); - irdma_put_cqp_request(&rf->cqp, cqp_request); - - return status; -} - /** * irdma_cqp_cq_create_cmd - create a cq for the cqp * @dev: device pointer diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index aa9ea6ba26e5..c592374f4a58 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -150,8 +150,12 @@ static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, return PTR_ERR(*umem); shift = mlx4_ib_umem_calc_optimal_mtt_size(*umem, 0, &n); - err = mlx4_mtt_init(dev->dev, n, shift, &buf->mtt); + if (shift < 0) { + err = shift; + goto err_buf; + } + err = mlx4_mtt_init(dev->dev, n, shift, &buf->mtt); if (err) goto err_buf; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 529db874d67c..dd35e03402ab 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -351,7 +351,7 @@ static int mlx4_ib_del_gid(const struct ib_gid_attr *attr, void **context) struct mlx4_port_gid_table *port_gid_table; int ret = 0; int hw_update = 0; - struct gid_entry *gids; + struct gid_entry *gids = NULL; if (!rdma_cap_roce_gid_table(attr->device, attr->port_num)) return -EINVAL; @@ -389,10 +389,10 @@ static int mlx4_ib_del_gid(const struct ib_gid_attr *attr, void **context) } spin_unlock_bh(&iboe->lock); - if (!ret && hw_update) { + if (gids) ret = mlx4_ib_update_gids(gids, ibdev, attr->port_num); - kfree(gids); - } + + kfree(gids); return ret; } @@ -2341,39 +2341,40 @@ static void mlx4_ib_scan_netdev(struct mlx4_ib_dev *ibdev, iboe->netdevs[dev->dev_port] = event != NETDEV_UNREGISTER ? dev : NULL; - if (event == NETDEV_UP || event == NETDEV_DOWN) { - enum ib_port_state port_state; - struct ib_event ibev = { }; - - if (ib_get_cached_port_state(&ibdev->ib_dev, dev->dev_port + 1, - &port_state)) - goto iboe_out; - - if (event == NETDEV_UP && - (port_state != IB_PORT_ACTIVE || - iboe->last_port_state[dev->dev_port] != IB_PORT_DOWN)) - goto iboe_out; - if (event == NETDEV_DOWN && - (port_state != IB_PORT_DOWN || - iboe->last_port_state[dev->dev_port] != IB_PORT_ACTIVE)) - goto iboe_out; - iboe->last_port_state[dev->dev_port] = port_state; - - ibev.device = &ibdev->ib_dev; - ibev.element.port_num = dev->dev_port + 1; - ibev.event = event == NETDEV_UP ? IB_EVENT_PORT_ACTIVE : - IB_EVENT_PORT_ERR; - ib_dispatch_event(&ibev); - } - -iboe_out: spin_unlock_bh(&iboe->lock); - if (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER || - event == NETDEV_UP || event == NETDEV_CHANGE) + if (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER) mlx4_ib_update_qps(ibdev, dev, dev->dev_port + 1); } +static void mlx4_ib_port_event(struct ib_device *ibdev, struct net_device *ndev, + unsigned long event) +{ + struct mlx4_ib_dev *mlx4_ibdev = + container_of(ibdev, struct mlx4_ib_dev, ib_dev); + struct mlx4_ib_iboe *iboe = &mlx4_ibdev->iboe; + + if (!net_eq(dev_net(ndev), &init_net)) + return; + + ASSERT_RTNL(); + + if (ndev->dev.parent != mlx4_ibdev->ib_dev.dev.parent) + return; + + spin_lock_bh(&iboe->lock); + + iboe->netdevs[ndev->dev_port] = event != NETDEV_UNREGISTER ? ndev : NULL; + + if (event == NETDEV_UP || event == NETDEV_DOWN) + ib_dispatch_port_state_event(&mlx4_ibdev->ib_dev, ndev); + + spin_unlock_bh(&iboe->lock); + + if (event == NETDEV_UP || event == NETDEV_CHANGE) + mlx4_ib_update_qps(mlx4_ibdev, ndev, ndev->dev_port + 1); +} + static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -2569,6 +2570,7 @@ static const struct ib_device_ops mlx4_ib_dev_ops = { .req_notify_cq = mlx4_ib_arm_cq, .rereg_user_mr = mlx4_ib_rereg_user_mr, .resize_cq = mlx4_ib_resize_cq, + .report_port_event = mlx4_ib_port_event, INIT_RDMA_OBJ_SIZE(ib_ah, mlx4_ib_ah, ibah), INIT_RDMA_OBJ_SIZE(ib_cq, mlx4_ib_cq, ibcq), diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index b52bceff7d97..f53b1846594c 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -667,6 +667,9 @@ struct mlx4_uverbs_ex_query_device { __u32 reserved; }; +/* 4k - 4G */ +#define MLX4_PAGE_SIZE_SUPPORTED ((unsigned long)GENMASK_ULL(31, 12)) + static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev) { return container_of(ibdev, struct mlx4_ib_dev, ib_dev); @@ -936,8 +939,19 @@ mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table) { return 0; } -int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va, - int *num_of_mtts); +static inline int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, + u64 start, + int *num_of_mtts) +{ + unsigned long pg_sz; + + pg_sz = ib_umem_find_best_pgsz(umem, MLX4_PAGE_SIZE_SUPPORTED, start); + if (!pg_sz) + return -EOPNOTSUPP; + + *num_of_mtts = ib_umem_num_dma_blocks(umem, pg_sz); + return order_base_2(pg_sz); +} int mlx4_ib_cm_init(void); void mlx4_ib_cm_destroy(void); diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index a40bf58bcdd3..e77645a673fb 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -87,286 +87,20 @@ err_free: return ERR_PTR(err); } -enum { - MLX4_MAX_MTT_SHIFT = 31 -}; - -static int mlx4_ib_umem_write_mtt_block(struct mlx4_ib_dev *dev, - struct mlx4_mtt *mtt, - u64 mtt_size, u64 mtt_shift, u64 len, - u64 cur_start_addr, u64 *pages, - int *start_index, int *npages) -{ - u64 cur_end_addr = cur_start_addr + len; - u64 cur_end_addr_aligned = 0; - u64 mtt_entries; - int err = 0; - int k; - - len += (cur_start_addr & (mtt_size - 1ULL)); - cur_end_addr_aligned = round_up(cur_end_addr, mtt_size); - len += (cur_end_addr_aligned - cur_end_addr); - if (len & (mtt_size - 1ULL)) { - pr_warn("write_block: len %llx is not aligned to mtt_size %llx\n", - len, mtt_size); - return -EINVAL; - } - - mtt_entries = (len >> mtt_shift); - - /* - * Align the MTT start address to the mtt_size. - * Required to handle cases when the MR starts in the middle of an MTT - * record. Was not required in old code since the physical addresses - * provided by the dma subsystem were page aligned, which was also the - * MTT size. - */ - cur_start_addr = round_down(cur_start_addr, mtt_size); - /* A new block is started ... */ - for (k = 0; k < mtt_entries; ++k) { - pages[*npages] = cur_start_addr + (mtt_size * k); - (*npages)++; - /* - * Be friendly to mlx4_write_mtt() and pass it chunks of - * appropriate size. - */ - if (*npages == PAGE_SIZE / sizeof(u64)) { - err = mlx4_write_mtt(dev->dev, mtt, *start_index, - *npages, pages); - if (err) - return err; - - (*start_index) += *npages; - *npages = 0; - } - } - - return 0; -} - -static inline u64 alignment_of(u64 ptr) -{ - return ilog2(ptr & (~(ptr - 1))); -} - -static int mlx4_ib_umem_calc_block_mtt(u64 next_block_start, - u64 current_block_end, - u64 block_shift) -{ - /* Check whether the alignment of the new block is aligned as well as - * the previous block. - * Block address must start with zeros till size of entity_size. - */ - if ((next_block_start & ((1ULL << block_shift) - 1ULL)) != 0) - /* - * It is not as well aligned as the previous block-reduce the - * mtt size accordingly. Here we take the last right bit which - * is 1. - */ - block_shift = alignment_of(next_block_start); - - /* - * Check whether the alignment of the end of previous block - is it - * aligned as well as the start of the block - */ - if (((current_block_end) & ((1ULL << block_shift) - 1ULL)) != 0) - /* - * It is not as well aligned as the start of the block - - * reduce the mtt size accordingly. - */ - block_shift = alignment_of(current_block_end); - - return block_shift; -} - int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt, struct ib_umem *umem) { - u64 *pages; - u64 len = 0; - int err = 0; - u64 mtt_size; - u64 cur_start_addr = 0; - u64 mtt_shift; - int start_index = 0; - int npages = 0; - struct scatterlist *sg; - int i; + struct ib_block_iter biter; + int err, i = 0; + u64 addr; - pages = (u64 *) __get_free_page(GFP_KERNEL); - if (!pages) - return -ENOMEM; - - mtt_shift = mtt->page_shift; - mtt_size = 1ULL << mtt_shift; - - for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) { - if (cur_start_addr + len == sg_dma_address(sg)) { - /* still the same block */ - len += sg_dma_len(sg); - continue; - } - /* - * A new block is started ... - * If len is malaligned, write an extra mtt entry to cover the - * misaligned area (round up the division) - */ - err = mlx4_ib_umem_write_mtt_block(dev, mtt, mtt_size, - mtt_shift, len, - cur_start_addr, - pages, &start_index, - &npages); + rdma_umem_for_each_dma_block(umem, &biter, BIT(mtt->page_shift)) { + addr = rdma_block_iter_dma_address(&biter); + err = mlx4_write_mtt(dev->dev, mtt, i++, 1, &addr); if (err) - goto out; - - cur_start_addr = sg_dma_address(sg); - len = sg_dma_len(sg); + return err; } - - /* Handle the last block */ - if (len > 0) { - /* - * If len is malaligned, write an extra mtt entry to cover - * the misaligned area (round up the division) - */ - err = mlx4_ib_umem_write_mtt_block(dev, mtt, mtt_size, - mtt_shift, len, - cur_start_addr, pages, - &start_index, &npages); - if (err) - goto out; - } - - if (npages) - err = mlx4_write_mtt(dev->dev, mtt, start_index, npages, pages); - -out: - free_page((unsigned long) pages); - return err; -} - -/* - * Calculate optimal mtt size based on contiguous pages. - * Function will return also the number of pages that are not aligned to the - * calculated mtt_size to be added to total number of pages. For that we should - * check the first chunk length & last chunk length and if not aligned to - * mtt_size we should increment the non_aligned_pages number. All chunks in the - * middle already handled as part of mtt shift calculation for both their start - * & end addresses. - */ -int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va, - int *num_of_mtts) -{ - u64 block_shift = MLX4_MAX_MTT_SHIFT; - u64 min_shift = PAGE_SHIFT; - u64 last_block_aligned_end = 0; - u64 current_block_start = 0; - u64 first_block_start = 0; - u64 current_block_len = 0; - u64 last_block_end = 0; - struct scatterlist *sg; - u64 current_block_end; - u64 misalignment_bits; - u64 next_block_start; - u64 total_len = 0; - int i; - - *num_of_mtts = ib_umem_num_dma_blocks(umem, PAGE_SIZE); - - for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) { - /* - * Initialization - save the first chunk start as the - * current_block_start - block means contiguous pages. - */ - if (current_block_len == 0 && current_block_start == 0) { - current_block_start = sg_dma_address(sg); - first_block_start = current_block_start; - /* - * Find the bits that are different between the physical - * address and the virtual address for the start of the - * MR. - * umem_get aligned the start_va to a page boundary. - * Therefore, we need to align the start va to the same - * boundary. - * misalignment_bits is needed to handle the case of a - * single memory region. In this case, the rest of the - * logic will not reduce the block size. If we use a - * block size which is bigger than the alignment of the - * misalignment bits, we might use the virtual page - * number instead of the physical page number, resulting - * in access to the wrong data. - */ - misalignment_bits = - (start_va & (~(((u64)(PAGE_SIZE)) - 1ULL))) ^ - current_block_start; - block_shift = min(alignment_of(misalignment_bits), - block_shift); - } - - /* - * Go over the scatter entries and check if they continue the - * previous scatter entry. - */ - next_block_start = sg_dma_address(sg); - current_block_end = current_block_start + current_block_len; - /* If we have a split (non-contig.) between two blocks */ - if (current_block_end != next_block_start) { - block_shift = mlx4_ib_umem_calc_block_mtt - (next_block_start, - current_block_end, - block_shift); - - /* - * If we reached the minimum shift for 4k page we stop - * the loop. - */ - if (block_shift <= min_shift) - goto end; - - /* - * If not saved yet we are in first block - we save the - * length of first block to calculate the - * non_aligned_pages number at the end. - */ - total_len += current_block_len; - - /* Start a new block */ - current_block_start = next_block_start; - current_block_len = sg_dma_len(sg); - continue; - } - /* The scatter entry is another part of the current block, - * increase the block size. - * An entry in the scatter can be larger than 4k (page) as of - * dma mapping which merge some blocks together. - */ - current_block_len += sg_dma_len(sg); - } - - /* Account for the last block in the total len */ - total_len += current_block_len; - /* Add to the first block the misalignment that it suffers from. */ - total_len += (first_block_start & ((1ULL << block_shift) - 1ULL)); - last_block_end = current_block_start + current_block_len; - last_block_aligned_end = round_up(last_block_end, 1ULL << block_shift); - total_len += (last_block_aligned_end - last_block_end); - - if (total_len & ((1ULL << block_shift) - 1ULL)) - pr_warn("misaligned total length detected (%llu, %llu)!", - total_len, block_shift); - - *num_of_mtts = total_len >> block_shift; -end: - if (block_shift < min_shift) { - /* - * If shift is less than the min we set a warning and return the - * min shift. - */ - pr_warn("umem_calc_optimal_mtt_size - unexpected shift %lld\n", block_shift); - - block_shift = min_shift; - } - return block_shift; + return 0; } static struct ib_umem *mlx4_get_umem_mr(struct ib_device *device, u64 start, @@ -424,6 +158,10 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, } shift = mlx4_ib_umem_calc_optimal_mtt_size(mr->umem, start, &n); + if (shift < 0) { + err = shift; + goto err_umem; + } err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, virt_addr, length, convert_access(access_flags), n, shift, &mr->mmr); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 9d08aa99f3cb..50fd407103c7 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -925,8 +925,12 @@ static int create_rq(struct ib_pd *pd, struct ib_qp_init_attr *init_attr, } shift = mlx4_ib_umem_calc_optimal_mtt_size(qp->umem, 0, &n); - err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt); + if (shift < 0) { + err = shift; + goto err_buf; + } + err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt); if (err) goto err_buf; @@ -1108,8 +1112,12 @@ static int create_qp_common(struct ib_pd *pd, struct ib_qp_init_attr *init_attr, } shift = mlx4_ib_umem_calc_optimal_mtt_size(qp->umem, 0, &n); - err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt); + if (shift < 0) { + err = shift; + goto err_buf; + } + err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt); if (err) goto err_buf; diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c index 520034acf73a..162814ae8cb4 100644 --- a/drivers/infiniband/hw/mlx5/fs.c +++ b/drivers/infiniband/hw/mlx5/fs.c @@ -943,7 +943,7 @@ int mlx5_ib_fs_add_op_fc(struct mlx5_ib_dev *dev, u32 port_num, } dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dst.counter_id = mlx5_fc_id(opfc->fc); + dst.counter = opfc->fc; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_COUNT | MLX5_FLOW_CONTEXT_ACTION_ALLOW; @@ -1113,8 +1113,8 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, handler->ibcounters = flow_act.counters; dest_arr[dest_num].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest_arr[dest_num].counter_id = - mlx5_fc_id(mcounters->hw_cntrs_hndl); + dest_arr[dest_num].counter = + mcounters->hw_cntrs_hndl; dest_num++; } @@ -1603,7 +1603,7 @@ static bool raw_fs_is_multicast(struct mlx5_ib_flow_matcher *fs_matcher, static struct mlx5_ib_flow_handler *raw_fs_rule_add( struct mlx5_ib_dev *dev, struct mlx5_ib_flow_matcher *fs_matcher, struct mlx5_flow_context *flow_context, struct mlx5_flow_act *flow_act, - u32 counter_id, void *cmd_in, int inlen, int dest_id, int dest_type) + struct mlx5_fc *counter, void *cmd_in, int inlen, int dest_id, int dest_type) { struct mlx5_flow_destination *dst; struct mlx5_ib_flow_prio *ft_prio; @@ -1652,8 +1652,12 @@ static struct mlx5_ib_flow_handler *raw_fs_rule_add( } if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + if (WARN_ON(!counter)) { + err = -EINVAL; + goto unlock; + } dst[dst_num].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dst[dst_num].counter_id = counter_id; + dst[dst_num].counter = counter; dst_num++; } @@ -1878,7 +1882,8 @@ static int get_dests(struct uverbs_attr_bundle *attrs, return 0; } -static bool is_flow_counter(void *obj, u32 offset, u32 *counter_id) +static bool +is_flow_counter(void *obj, u32 offset, u32 *counter_id, u32 *fc_bulk_size) { struct devx_obj *devx_obj = obj; u16 opcode = MLX5_GET(general_obj_in_cmd_hdr, devx_obj->dinbox, opcode); @@ -1888,6 +1893,7 @@ static bool is_flow_counter(void *obj, u32 offset, u32 *counter_id) if (offset && offset >= devx_obj->flow_counter_bulk_size) return false; + *fc_bulk_size = devx_obj->flow_counter_bulk_size; *counter_id = MLX5_GET(dealloc_flow_counter_in, devx_obj->dinbox, flow_counter_id); @@ -1904,13 +1910,13 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)( { struct mlx5_flow_context flow_context = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG}; - u32 *offset_attr, offset = 0, counter_id = 0; int dest_id, dest_type = -1, inlen, len, ret, i; struct mlx5_ib_flow_handler *flow_handler; struct mlx5_ib_flow_matcher *fs_matcher; struct ib_uobject **arr_flow_actions; struct ib_uflow_resources *uflow_res; struct mlx5_flow_act flow_act = {}; + struct mlx5_fc *counter = NULL; struct ib_qp *qp = NULL; void *devx_obj, *cmd_in; struct ib_uobject *uobj; @@ -1937,6 +1943,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)( len = uverbs_attr_get_uobjs_arr(attrs, MLX5_IB_ATTR_CREATE_FLOW_ARR_COUNTERS_DEVX, &arr_flow_actions); if (len) { + u32 *offset_attr, fc_bulk_size, offset = 0, counter_id = 0; devx_obj = arr_flow_actions[0]->object; if (uverbs_attr_is_valid(attrs, @@ -1956,8 +1963,11 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)( offset = *offset_attr; } - if (!is_flow_counter(devx_obj, offset, &counter_id)) + if (!is_flow_counter(devx_obj, offset, &counter_id, &fc_bulk_size)) return -EINVAL; + counter = mlx5_fc_local_create(counter_id, offset, fc_bulk_size); + if (IS_ERR(counter)) + return PTR_ERR(counter); flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; } @@ -1968,8 +1978,10 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)( MLX5_IB_ATTR_CREATE_FLOW_MATCH_VALUE); uflow_res = flow_resources_alloc(MLX5_IB_CREATE_FLOW_MAX_FLOW_ACTIONS); - if (!uflow_res) - return -ENOMEM; + if (!uflow_res) { + ret = -ENOMEM; + goto destroy_counter; + } len = uverbs_attr_get_uobjs_arr(attrs, MLX5_IB_ATTR_CREATE_FLOW_ARR_FLOW_ACTIONS, &arr_flow_actions); @@ -1996,7 +2008,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)( flow_handler = raw_fs_rule_add(dev, fs_matcher, &flow_context, &flow_act, - counter_id, cmd_in, inlen, dest_id, dest_type); + counter, cmd_in, inlen, dest_id, dest_type); if (IS_ERR(flow_handler)) { ret = PTR_ERR(flow_handler); goto err_out; @@ -2007,6 +2019,9 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)( return 0; err_out: ib_uverbs_flow_resources_free(uflow_res); +destroy_counter: + if (counter) + mlx5_fc_local_destroy(counter); return ret; } diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index bc7930d0c564..81849eb671a1 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -242,6 +242,10 @@ static int mlx5_netdev_event(struct notifier_block *this, case NETDEV_DOWN: { struct net_device *upper = NULL; + if (!netif_is_lag_master(ndev) && !netif_is_lag_port(ndev) && + !mlx5_core_mp_enabled(mdev)) + return NOTIFY_DONE; + if (mlx5_lag_is_roce(mdev) || mlx5_lag_is_sriov(mdev)) { struct net_device *lag_ndev; @@ -2839,7 +2843,7 @@ static int mlx5_ib_get_plane_num(struct mlx5_core_dev *mdev, u8 *num_plane) int err; *num_plane = 0; - if (!MLX5_CAP_GEN(mdev, ib_virt)) + if (!MLX5_CAP_GEN(mdev, ib_virt) || !MLX5_CAP_GEN_2(mdev, multiplane)) return 0; err = mlx5_query_hca_vport_context(mdev, 0, 1, 0, &vport_ctx); @@ -3639,7 +3643,8 @@ static int mlx5_ib_init_multiport_master(struct mlx5_ib_dev *dev) list_for_each_entry(mpi, &mlx5_ib_unaffiliated_port_list, list) { if (dev->sys_image_guid == mpi->sys_image_guid && - (mlx5_core_native_port_num(mpi->mdev) - 1) == i) { + (mlx5_core_native_port_num(mpi->mdev) - 1) == i && + mlx5_core_same_coredev_type(dev->mdev, mpi->mdev)) { bound = mlx5_ib_bind_slave_port(dev, mpi); } @@ -4785,7 +4790,8 @@ static int mlx5r_mp_probe(struct auxiliary_device *adev, mutex_lock(&mlx5_ib_multiport_mutex); list_for_each_entry(dev, &mlx5_ib_dev_list, ib_dev_list) { - if (dev->sys_image_guid == mpi->sys_image_guid) + if (dev->sys_image_guid == mpi->sys_image_guid && + mlx5_core_same_coredev_type(dev->mdev, mpi->mdev)) bound = mlx5_ib_bind_slave_port(dev, mpi); if (bound) { diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index a01b592aa716..974a45c92fbb 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -669,6 +669,12 @@ struct mlx5_ib_mkey { #define mlx5_update_odp_stats(mr, counter_name, value) \ atomic64_add(value, &((mr)->odp_stats.counter_name)) +#define mlx5_update_odp_stats_with_handled(mr, counter_name, value) \ + do { \ + mlx5_update_odp_stats(mr, counter_name, value); \ + atomic64_add(1, &((mr)->odp_stats.counter_name##_handled)); \ + } while (0) + struct mlx5_ib_mr { struct ib_mr ibmr; struct mlx5_ib_mkey mmkey; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 45d9dc9c6c8f..bb02b6adbf2c 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -2021,6 +2021,11 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr) { struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device); struct mlx5_cache_ent *ent = mr->mmkey.cache_ent; + bool is_odp = is_odp_mr(mr); + int ret = 0; + + if (is_odp) + mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex); if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr)) { ent = mr->mmkey.cache_ent; @@ -2032,7 +2037,7 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr) ent->tmp_cleanup_scheduled = true; } spin_unlock_irq(&ent->mkeys_queue.lock); - return 0; + goto out; } if (ent) { @@ -2041,7 +2046,15 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr) mr->mmkey.cache_ent = NULL; spin_unlock_irq(&ent->mkeys_queue.lock); } - return destroy_mkey(dev, mr); + ret = destroy_mkey(dev, mr); +out: + if (is_odp) { + if (!ret) + to_ib_umem_odp(mr->umem)->private = NULL; + mutex_unlock(&to_ib_umem_odp(mr->umem)->umem_mutex); + } + + return ret; } static int __mlx5_ib_dereg_mr(struct ib_mr *ibmr) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 4b37446758fd..f1e23583e6c0 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -228,13 +228,27 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr) unsigned long idx = ib_umem_start(odp) >> MLX5_IMR_MTT_SHIFT; struct mlx5_ib_mr *imr = mr->parent; + /* + * If userspace is racing freeing the parent implicit ODP MR then we can + * loose the race with parent destruction. In this case + * mlx5_ib_free_odp_mr() will free everything in the implicit_children + * xarray so NOP is fine. This child MR cannot be destroyed here because + * we are under its umem_mutex. + */ if (!refcount_inc_not_zero(&imr->mmkey.usecount)) return; - xa_erase(&imr->implicit_children, idx); + xa_lock(&imr->implicit_children); + if (__xa_cmpxchg(&imr->implicit_children, idx, mr, NULL, GFP_KERNEL) != + mr) { + xa_unlock(&imr->implicit_children); + return; + } + if (MLX5_CAP_ODP(mr_to_mdev(mr)->mdev, mem_page_fault)) - xa_erase(&mr_to_mdev(mr)->odp_mkeys, - mlx5_base_mkey(mr->mmkey.key)); + __xa_erase(&mr_to_mdev(mr)->odp_mkeys, + mlx5_base_mkey(mr->mmkey.key)); + xa_unlock(&imr->implicit_children); /* Freeing a MR is a sleeping operation, so bounce to a work queue */ INIT_WORK(&mr->odp_destroy.work, free_implicit_child_mr_work); @@ -268,6 +282,8 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni, if (!umem_odp->npages) goto out; mr = umem_odp->private; + if (!mr) + goto out; start = max_t(u64, ib_umem_start(umem_odp), range->start); end = min_t(u64, ib_umem_end(umem_odp), range->end); @@ -313,7 +329,7 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni, MLX5_IB_UPD_XLT_ZAP | MLX5_IB_UPD_XLT_ATOMIC); - mlx5_update_odp_stats(mr, invalidations, invalidations); + mlx5_update_odp_stats_with_handled(mr, invalidations, invalidations); /* * We are now sure that the device will not access the @@ -500,18 +516,18 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, refcount_inc(&ret->mmkey.usecount); goto out_lock; } - xa_unlock(&imr->implicit_children); if (MLX5_CAP_ODP(dev->mdev, mem_page_fault)) { - ret = xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key), - &mr->mmkey, GFP_KERNEL); + ret = __xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key), + &mr->mmkey, GFP_KERNEL); if (xa_is_err(ret)) { ret = ERR_PTR(xa_err(ret)); - xa_erase(&imr->implicit_children, idx); - goto out_mr; + __xa_erase(&imr->implicit_children, idx); + goto out_lock; } mr->mmkey.type = MLX5_MKEY_IMPLICIT_CHILD; } + xa_unlock(&imr->implicit_children); mlx5_ib_dbg(mr_to_mdev(imr), "key %x mr %p\n", mr->mmkey.key, mr); return mr; @@ -944,8 +960,7 @@ out: /* * Handle a single data segment in a page-fault WQE or RDMA region. * - * Returns number of OS pages retrieved on success. The caller may continue to - * the next data segment. + * Returns zero on success. The caller may continue to the next data segment. * Can return the following error codes: * -EAGAIN to designate a temporary error. The caller will abort handling the * page fault and resolve it. @@ -958,7 +973,7 @@ static int pagefault_single_data_segment(struct mlx5_ib_dev *dev, u32 *bytes_committed, u32 *bytes_mapped) { - int npages = 0, ret, i, outlen, cur_outlen = 0, depth = 0; + int ret, i, outlen, cur_outlen = 0, depth = 0, pages_in_range; struct pf_frame *head = NULL, *frame; struct mlx5_ib_mkey *mmkey; struct mlx5_ib_mr *mr; @@ -993,13 +1008,20 @@ next_mr: case MLX5_MKEY_MR: mr = container_of(mmkey, struct mlx5_ib_mr, mmkey); + pages_in_range = (ALIGN(io_virt + bcnt, PAGE_SIZE) - + (io_virt & PAGE_MASK)) >> + PAGE_SHIFT; ret = pagefault_mr(mr, io_virt, bcnt, bytes_mapped, 0, false); if (ret < 0) goto end; - mlx5_update_odp_stats(mr, faults, ret); + mlx5_update_odp_stats_with_handled(mr, faults, ret); + + if (ret < pages_in_range) { + ret = -EFAULT; + goto end; + } - npages += ret; ret = 0; break; @@ -1090,7 +1112,7 @@ end: kfree(out); *bytes_committed = 0; - return ret ? ret : npages; + return ret; } /* @@ -1109,8 +1131,7 @@ end: * the committed bytes). * @receive_queue: receive WQE end of sg list * - * Returns the number of pages loaded if positive, zero for an empty WQE, or a - * negative error code. + * Returns zero for success or a negative error code. */ static int pagefault_data_segments(struct mlx5_ib_dev *dev, struct mlx5_pagefault *pfault, @@ -1118,7 +1139,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev, void *wqe_end, u32 *bytes_mapped, u32 *total_wqe_bytes, bool receive_queue) { - int ret = 0, npages = 0; + int ret = 0; u64 io_virt; __be32 key; u32 byte_count; @@ -1175,10 +1196,9 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev, bytes_mapped); if (ret < 0) break; - npages += ret; } - return ret < 0 ? ret : npages; + return ret; } /* @@ -1414,12 +1434,6 @@ resolve_page_fault: free_page((unsigned long)wqe_start); } -static int pages_in_range(u64 address, u32 length) -{ - return (ALIGN(address + length, PAGE_SIZE) - - (address & PAGE_MASK)) >> PAGE_SHIFT; -} - static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_dev *dev, struct mlx5_pagefault *pfault) { @@ -1458,7 +1472,7 @@ static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_dev *dev, if (ret == -EAGAIN) { /* We're racing with an invalidation, don't prefetch */ prefetch_activated = 0; - } else if (ret < 0 || pages_in_range(address, length) > ret) { + } else if (ret < 0) { mlx5_ib_page_fault_resume(dev, pfault, 1); if (ret != -ENOENT) mlx5_ib_dbg(dev, "PAGE FAULT error %d. QP 0x%llx, type: 0x%x\n", @@ -1529,7 +1543,7 @@ static void mlx5_ib_mr_memory_pfault_handler(struct mlx5_ib_dev *dev, goto err; } - mlx5_update_odp_stats(mr, faults, ret); + mlx5_update_odp_stats_with_handled(mr, faults, ret); mlx5r_deref_odp_mkey(mmkey); if (pfault->memory.flags & MLX5_MEMORY_PAGE_FAULT_FLAGS_LAST) diff --git a/drivers/infiniband/hw/mlx5/restrack.c b/drivers/infiniband/hw/mlx5/restrack.c index affcf8fe943c..67841922c7b8 100644 --- a/drivers/infiniband/hw/mlx5/restrack.c +++ b/drivers/infiniband/hw/mlx5/restrack.c @@ -95,10 +95,19 @@ static int fill_stat_mr_entry(struct sk_buff *msg, struct ib_mr *ibmr) if (rdma_nl_stat_hwcounter_entry(msg, "page_faults", atomic64_read(&mr->odp_stats.faults))) goto err_table; + if (rdma_nl_stat_hwcounter_entry( + msg, "page_faults_handled", + atomic64_read(&mr->odp_stats.faults_handled))) + goto err_table; if (rdma_nl_stat_hwcounter_entry( msg, "page_invalidations", atomic64_read(&mr->odp_stats.invalidations))) goto err_table; + if (rdma_nl_stat_hwcounter_entry( + msg, "page_invalidations_handled", + atomic64_read(&mr->odp_stats.invalidations_handled))) + goto err_table; + if (rdma_nl_stat_hwcounter_entry(msg, "page_prefetch", atomic64_read(&mr->odp_stats.prefetch))) goto err_table; diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index ba2cd68b53e6..805e37dc7621 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -214,8 +214,8 @@ static const struct attribute_group port_linkcontrol_group = { * Congestion control table size followed by table entries */ static ssize_t cc_table_bin_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t pos, size_t count) + const struct bin_attribute *bin_attr, + char *buf, loff_t pos, size_t count) { struct qib_pportdata *ppd = qib_get_pportdata_kobj(kobj); int ret; @@ -241,7 +241,7 @@ static ssize_t cc_table_bin_read(struct file *filp, struct kobject *kobj, return count; } -static BIN_ATTR_RO(cc_table_bin, PAGE_SIZE); +static const BIN_ATTR_RO(cc_table_bin, PAGE_SIZE); /* * Congestion settings: port control, control map and an array of 16 @@ -249,8 +249,8 @@ static BIN_ATTR_RO(cc_table_bin, PAGE_SIZE); * trigger threshold and the minimum injection rate delay. */ static ssize_t cc_setting_bin_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t pos, size_t count) + const struct bin_attribute *bin_attr, + char *buf, loff_t pos, size_t count) { struct qib_pportdata *ppd = qib_get_pportdata_kobj(kobj); int ret; @@ -274,9 +274,9 @@ static ssize_t cc_setting_bin_read(struct file *filp, struct kobject *kobj, return count; } -static BIN_ATTR_RO(cc_setting_bin, PAGE_SIZE); +static const BIN_ATTR_RO(cc_setting_bin, PAGE_SIZE); -static struct bin_attribute *port_ccmgta_attributes[] = { +static const struct bin_attribute *const port_ccmgta_attributes[] = { &bin_attr_cc_setting_bin, &bin_attr_cc_table_bin, NULL, @@ -295,7 +295,7 @@ static umode_t qib_ccmgta_is_bin_visible(struct kobject *kobj, static const struct attribute_group port_ccmgta_attribute_group = { .name = "CCMgtA", .is_bin_visible = qib_ccmgta_is_bin_visible, - .bin_attrs = port_ccmgta_attributes, + .bin_attrs_new = port_ccmgta_attributes, }; /* Start sl2vl */ diff --git a/drivers/infiniband/hw/usnic/usnic_abi.h b/drivers/infiniband/hw/usnic/usnic_abi.h index 7fe9502ce8d3..86a82a4da0aa 100644 --- a/drivers/infiniband/hw/usnic/usnic_abi.h +++ b/drivers/infiniband/hw/usnic/usnic_abi.h @@ -72,7 +72,7 @@ struct usnic_ib_create_qp_resp { u64 bar_bus_addr; u32 bar_len; /* - * WQ, RQ, CQ are explicity specified bc exposing a generic resources inteface + * WQ, RQ, CQ are explicitly specified bc exposing a generic resources inteface * expands the scope of ABI to many files. */ u32 wq_cnt; diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index 13b654ddd3cc..4ddcd5860e0f 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -151,34 +151,6 @@ static void usnic_ib_handle_usdev_event(struct usnic_ib_dev *us_ibdev, ib_event.element.port_num = 1; ib_dispatch_event(&ib_event); break; - case NETDEV_UP: - case NETDEV_DOWN: - case NETDEV_CHANGE: - if (!us_ibdev->ufdev->link_up && - netif_carrier_ok(netdev)) { - usnic_fwd_carrier_up(us_ibdev->ufdev); - usnic_info("Link UP on %s\n", - dev_name(&us_ibdev->ib_dev.dev)); - ib_event.event = IB_EVENT_PORT_ACTIVE; - ib_event.device = &us_ibdev->ib_dev; - ib_event.element.port_num = 1; - ib_dispatch_event(&ib_event); - } else if (us_ibdev->ufdev->link_up && - !netif_carrier_ok(netdev)) { - usnic_fwd_carrier_down(us_ibdev->ufdev); - usnic_info("Link DOWN on %s\n", - dev_name(&us_ibdev->ib_dev.dev)); - usnic_ib_qp_grp_modify_active_to_err(us_ibdev); - ib_event.event = IB_EVENT_PORT_ERR; - ib_event.device = &us_ibdev->ib_dev; - ib_event.element.port_num = 1; - ib_dispatch_event(&ib_event); - } else { - usnic_dbg("Ignoring %s on %s\n", - netdev_cmd_to_name(event), - dev_name(&us_ibdev->ib_dev.dev)); - } - break; case NETDEV_CHANGEADDR: if (!memcmp(us_ibdev->ufdev->mac, netdev->dev_addr, sizeof(us_ibdev->ufdev->mac))) { @@ -218,6 +190,50 @@ static void usnic_ib_handle_usdev_event(struct usnic_ib_dev *us_ibdev, mutex_unlock(&us_ibdev->usdev_lock); } +static void usnic_ib_handle_port_event(struct ib_device *ibdev, + struct net_device *netdev, + unsigned long event) +{ + struct usnic_ib_dev *us_ibdev = + container_of(ibdev, struct usnic_ib_dev, ib_dev); + struct ib_event ib_event; + + mutex_lock(&us_ibdev->usdev_lock); + switch (event) { + case NETDEV_UP: + case NETDEV_DOWN: + case NETDEV_CHANGE: + if (!us_ibdev->ufdev->link_up && + netif_carrier_ok(netdev)) { + usnic_fwd_carrier_up(us_ibdev->ufdev); + usnic_info("Link UP on %s\n", + dev_name(&us_ibdev->ib_dev.dev)); + ib_event.event = IB_EVENT_PORT_ACTIVE; + ib_event.device = &us_ibdev->ib_dev; + ib_event.element.port_num = 1; + ib_dispatch_event(&ib_event); + } else if (us_ibdev->ufdev->link_up && + !netif_carrier_ok(netdev)) { + usnic_fwd_carrier_down(us_ibdev->ufdev); + usnic_info("Link DOWN on %s\n", + dev_name(&us_ibdev->ib_dev.dev)); + usnic_ib_qp_grp_modify_active_to_err(us_ibdev); + ib_event.event = IB_EVENT_PORT_ERR; + ib_event.device = &us_ibdev->ib_dev; + ib_event.element.port_num = 1; + ib_dispatch_event(&ib_event); + } else { + usnic_dbg("Ignoring %s on %s\n", + netdev_cmd_to_name(event), + dev_name(&us_ibdev->ib_dev.dev)); + } + break; + default: + break; + } + mutex_unlock(&us_ibdev->usdev_lock); +} + static int usnic_ib_netdevice_event(struct notifier_block *notifier, unsigned long event, void *ptr) { @@ -358,6 +374,7 @@ static const struct ib_device_ops usnic_dev_ops = { .query_port = usnic_ib_query_port, .query_qp = usnic_ib_query_qp, .reg_user_mr = usnic_ib_reg_mr, + .report_port_event = usnic_ib_handle_port_event, INIT_RDMA_OBJ_SIZE(ib_pd, usnic_ib_pd, ibpd), INIT_RDMA_OBJ_SIZE(ib_cq, usnic_ib_cq, ibcq), INIT_RDMA_OBJ_SIZE(ib_qp, usnic_ib_qp_grp, ibqp), diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index 768aad364c89..1664d1d7d969 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -143,6 +143,46 @@ static int pvrdma_port_immutable(struct ib_device *ibdev, u32 port_num, return 0; } +static void pvrdma_dispatch_event(struct pvrdma_dev *dev, int port, + enum ib_event_type event) +{ + struct ib_event ib_event; + + memset(&ib_event, 0, sizeof(ib_event)); + ib_event.device = &dev->ib_dev; + ib_event.element.port_num = port; + ib_event.event = event; + ib_dispatch_event(&ib_event); +} + +static void pvrdma_report_event_handle(struct ib_device *ibdev, + struct net_device *ndev, + unsigned long event) +{ + struct pvrdma_dev *dev = container_of(ibdev, struct pvrdma_dev, ib_dev); + + switch (event) { + case NETDEV_DOWN: + pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ERR); + break; + case NETDEV_UP: + pvrdma_write_reg(dev, PVRDMA_REG_CTL, + PVRDMA_DEVICE_CTL_UNQUIESCE); + + mb(); + + if (pvrdma_read_reg(dev, PVRDMA_REG_ERR)) + dev_err(&dev->pdev->dev, + "failed to activate device during link up\n"); + else + pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE); + break; + + default: + break; + } +} + static const struct ib_device_ops pvrdma_dev_ops = { .owner = THIS_MODULE, .driver_id = RDMA_DRIVER_VMW_PVRDMA, @@ -181,6 +221,7 @@ static const struct ib_device_ops pvrdma_dev_ops = { .query_qp = pvrdma_query_qp, .reg_user_mr = pvrdma_reg_user_mr, .req_notify_cq = pvrdma_req_notify_cq, + .report_port_event = pvrdma_report_event_handle, INIT_RDMA_OBJ_SIZE(ib_ah, pvrdma_ah, ibah), INIT_RDMA_OBJ_SIZE(ib_cq, pvrdma_cq, ibcq), @@ -362,18 +403,6 @@ static void pvrdma_srq_event(struct pvrdma_dev *dev, u32 srqn, int type) } } -static void pvrdma_dispatch_event(struct pvrdma_dev *dev, int port, - enum ib_event_type event) -{ - struct ib_event ib_event; - - memset(&ib_event, 0, sizeof(ib_event)); - ib_event.device = &dev->ib_dev; - ib_event.element.port_num = port; - ib_event.event = event; - ib_dispatch_event(&ib_event); -} - static void pvrdma_dev_event(struct pvrdma_dev *dev, u8 port, int type) { if (port < 1 || port > dev->dsr->caps.phys_port_cnt) { @@ -666,21 +695,8 @@ static void pvrdma_netdevice_event_handle(struct pvrdma_dev *dev, switch (event) { case NETDEV_REBOOT: - case NETDEV_DOWN: pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ERR); break; - case NETDEV_UP: - pvrdma_write_reg(dev, PVRDMA_REG_CTL, - PVRDMA_DEVICE_CTL_UNQUIESCE); - - mb(); - - if (pvrdma_read_reg(dev, PVRDMA_REG_ERR)) - dev_err(&dev->pdev->dev, - "failed to activate device during link up\n"); - else - pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE); - break; case NETDEV_UNREGISTER: ib_device_set_netdev(&dev->ib_dev, NULL, 1); dev_put(dev->netdev); diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 255677bc12b2..1ba4a0c8726a 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -40,6 +40,8 @@ void rxe_dealloc(struct ib_device *ib_dev) /* initialize rxe device parameters */ static void rxe_init_device_param(struct rxe_dev *rxe) { + struct net_device *ndev; + rxe->max_inline_data = RXE_MAX_INLINE_DATA; rxe->attr.vendor_id = RXE_VENDOR_ID; @@ -71,8 +73,15 @@ static void rxe_init_device_param(struct rxe_dev *rxe) rxe->attr.max_fast_reg_page_list_len = RXE_MAX_FMR_PAGE_LIST_LEN; rxe->attr.max_pkeys = RXE_MAX_PKEYS; rxe->attr.local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return; + addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid, - rxe->ndev->dev_addr); + ndev->dev_addr); + + dev_put(ndev); rxe->max_ucontext = RXE_MAX_UCONTEXT; } @@ -109,10 +118,15 @@ static void rxe_init_port_param(struct rxe_port *port) static void rxe_init_ports(struct rxe_dev *rxe) { struct rxe_port *port = &rxe->port; + struct net_device *ndev; rxe_init_port_param(port); + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return; addrconf_addr_eui48((unsigned char *)&port->port_guid, - rxe->ndev->dev_addr); + ndev->dev_addr); + dev_put(ndev); spin_lock_init(&port->port_lock); } @@ -167,12 +181,13 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu) /* called by ifc layer to create new rxe device. * The caller should allocate memory for rxe by calling ib_alloc_device. */ -int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name) +int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name, + struct net_device *ndev) { rxe_init(rxe); rxe_set_mtu(rxe, mtu); - return rxe_register_device(rxe, ibdev_name); + return rxe_register_device(rxe, ibdev_name, ndev); } static int rxe_newlink(const char *ibdev_name, struct net_device *ndev) diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index d8fb2c7af30a..fe7f97066732 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -139,7 +139,8 @@ enum resp_states { void rxe_set_mtu(struct rxe_dev *rxe, unsigned int dev_mtu); -int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name); +int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name, + struct net_device *ndev); void rxe_rcv(struct sk_buff *skb); diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c index 86cc2e18a7fd..07ff47bae31d 100644 --- a/drivers/infiniband/sw/rxe/rxe_mcast.c +++ b/drivers/infiniband/sw/rxe/rxe_mcast.c @@ -31,10 +31,19 @@ static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid) { unsigned char ll_addr[ETH_ALEN]; + struct net_device *ndev; + int ret; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return -ENODEV; ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr); - return dev_mc_add(rxe->ndev, ll_addr); + ret = dev_mc_add(ndev, ll_addr); + dev_put(ndev); + + return ret; } /** @@ -47,10 +56,19 @@ static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid) static int rxe_mcast_del(struct rxe_dev *rxe, union ib_gid *mgid) { unsigned char ll_addr[ETH_ALEN]; + struct net_device *ndev; + int ret; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return -ENODEV; ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr); - return dev_mc_del(rxe->ndev, ll_addr); + ret = dev_mc_del(ndev, ll_addr); + dev_put(ndev); + + return ret; } /** diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 75d1407db52d..132a87e52d5c 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -524,7 +524,16 @@ out: */ const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num) { - return rxe->ndev->name; + struct net_device *ndev; + char *ndev_name; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return NULL; + ndev_name = ndev->name; + dev_put(ndev); + + return ndev_name; } int rxe_net_add(const char *ibdev_name, struct net_device *ndev) @@ -536,10 +545,9 @@ int rxe_net_add(const char *ibdev_name, struct net_device *ndev) if (!rxe) return -ENOMEM; - rxe->ndev = ndev; ib_mark_name_assigned_by_user(&rxe->ib_dev); - err = rxe_add(rxe, ndev->mtu, ibdev_name); + err = rxe_add(rxe, ndev->mtu, ibdev_name, ndev); if (err) { ib_dealloc_device(&rxe->ib_dev); return err; @@ -563,11 +571,6 @@ static void rxe_port_event(struct rxe_dev *rxe, /* Caller must hold net_info_lock */ void rxe_port_up(struct rxe_dev *rxe) { - struct rxe_port *port; - - port = &rxe->port; - port->attr.state = IB_PORT_ACTIVE; - rxe_port_event(rxe, IB_EVENT_PORT_ACTIVE); dev_info(&rxe->ib_dev.dev, "set active\n"); } @@ -575,11 +578,6 @@ void rxe_port_up(struct rxe_dev *rxe) /* Caller must hold net_info_lock */ void rxe_port_down(struct rxe_dev *rxe) { - struct rxe_port *port; - - port = &rxe->port; - port->attr.state = IB_PORT_DOWN; - rxe_port_event(rxe, IB_EVENT_PORT_ERR); rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED); dev_info(&rxe->ib_dev.dev, "set down\n"); @@ -587,10 +585,18 @@ void rxe_port_down(struct rxe_dev *rxe) void rxe_set_port_state(struct rxe_dev *rxe) { - if (netif_running(rxe->ndev) && netif_carrier_ok(rxe->ndev)) + struct net_device *ndev; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return; + + if (ib_get_curr_port_state(ndev) == IB_PORT_ACTIVE) rxe_port_up(rxe); else rxe_port_down(rxe); + + dev_put(ndev); } static int rxe_notify(struct notifier_block *not_blk, @@ -607,18 +613,14 @@ static int rxe_notify(struct notifier_block *not_blk, case NETDEV_UNREGISTER: ib_unregister_device_queued(&rxe->ib_dev); break; - case NETDEV_UP: - rxe_port_up(rxe); - break; - case NETDEV_DOWN: - rxe_port_down(rxe); - break; case NETDEV_CHANGEMTU: rxe_dbg_dev(rxe, "%s changed mtu to %d\n", ndev->name, ndev->mtu); rxe_set_mtu(rxe, ndev->mtu); break; + case NETDEV_DOWN: case NETDEV_CHANGE: - rxe_set_port_state(rxe); + if (ib_get_curr_port_state(ndev) == IB_PORT_DOWN) + rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED); break; case NETDEV_REBOOT: case NETDEV_GOING_DOWN: diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h index d2f57ead78ad..003f681e5dc0 100644 --- a/drivers/infiniband/sw/rxe/rxe_param.h +++ b/drivers/infiniband/sw/rxe/rxe_param.h @@ -129,7 +129,7 @@ enum rxe_device_param { enum rxe_port_param { RXE_PORT_GID_TBL_LEN = 1024, RXE_PORT_PORT_CAP_FLAGS = IB_PORT_CM_SUP, - RXE_PORT_MAX_MSG_SZ = 0x800000, + RXE_PORT_MAX_MSG_SZ = (1UL << 31), RXE_PORT_BAD_PKEY_CNTR = 0, RXE_PORT_QKEY_VIOL_CNTR = 0, RXE_PORT_LID = 0, diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c index 67567d62195e..d9cb682fd71f 100644 --- a/drivers/infiniband/sw/rxe/rxe_pool.c +++ b/drivers/infiniband/sw/rxe/rxe_pool.c @@ -178,7 +178,6 @@ int __rxe_cleanup(struct rxe_pool_elem *elem, bool sleepable) { struct rxe_pool *pool = elem->pool; struct xarray *xa = &pool->xa; - static int timeout = RXE_POOL_TIMEOUT; int ret, err = 0; void *xa_ret; @@ -202,19 +201,19 @@ int __rxe_cleanup(struct rxe_pool_elem *elem, bool sleepable) * return to rdma-core */ if (sleepable) { - if (!completion_done(&elem->complete) && timeout) { + if (!completion_done(&elem->complete)) { ret = wait_for_completion_timeout(&elem->complete, - timeout); + msecs_to_jiffies(50000)); /* Shouldn't happen. There are still references to * the object but, rather than deadlock, free the * object or pass back to rdma-core. */ if (WARN_ON(!ret)) - err = -EINVAL; + err = -ETIMEDOUT; } } else { - unsigned long until = jiffies + timeout; + unsigned long until = jiffies + RXE_POOL_TIMEOUT; /* AH objects are unique in that the destroy_ah verb * can be called in atomic context. This delay @@ -226,7 +225,7 @@ int __rxe_cleanup(struct rxe_pool_elem *elem, bool sleepable) mdelay(1); if (WARN_ON(!completion_done(&elem->complete))) - err = -EINVAL; + err = -ETIMEDOUT; } if (pool->cleanup) diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 5c18f7e342f2..6152a0fdfc8c 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -41,6 +41,7 @@ static int rxe_query_port(struct ib_device *ibdev, u32 port_num, struct ib_port_attr *attr) { struct rxe_dev *rxe = to_rdev(ibdev); + struct net_device *ndev; int err, ret; if (port_num != 1) { @@ -49,21 +50,29 @@ static int rxe_query_port(struct ib_device *ibdev, goto err_out; } + ndev = rxe_ib_device_get_netdev(ibdev); + if (!ndev) { + err = -ENODEV; + goto err_out; + } + memcpy(attr, &rxe->port.attr, sizeof(*attr)); mutex_lock(&rxe->usdev_lock); ret = ib_get_eth_speed(ibdev, port_num, &attr->active_speed, &attr->active_width); + attr->state = ib_get_curr_port_state(ndev); if (attr->state == IB_PORT_ACTIVE) attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; - else if (dev_get_flags(rxe->ndev) & IFF_UP) + else if (dev_get_flags(ndev) & IFF_UP) attr->phys_state = IB_PORT_PHYS_STATE_POLLING; else attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; mutex_unlock(&rxe->usdev_lock); + dev_put(ndev); return ret; err_out: @@ -688,7 +697,7 @@ static int validate_send_wr(struct rxe_qp *qp, const struct ib_send_wr *ibwr, for (i = 0; i < ibwr->num_sge; i++) length += ibwr->sg_list[i].length; - if (length > (1UL << 31)) { + if (length > RXE_PORT_MAX_MSG_SZ) { rxe_err_qp(qp, "message length too long\n"); break; } @@ -972,8 +981,7 @@ static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr) for (i = 0; i < num_sge; i++) length += ibwr->sg_list[i].length; - /* IBA max message size is 2^31 */ - if (length >= (1UL<<31)) { + if (length > RXE_PORT_MAX_MSG_SZ) { err = -EINVAL; rxe_dbg("message length too long\n"); goto err_out; @@ -1425,9 +1433,16 @@ static const struct attribute_group rxe_attr_group = { static int rxe_enable_driver(struct ib_device *ib_dev) { struct rxe_dev *rxe = container_of(ib_dev, struct rxe_dev, ib_dev); + struct net_device *ndev; + + ndev = rxe_ib_device_get_netdev(ib_dev); + if (!ndev) + return -ENODEV; rxe_set_port_state(rxe); - dev_info(&rxe->ib_dev.dev, "added %s\n", netdev_name(rxe->ndev)); + dev_info(&rxe->ib_dev.dev, "added %s\n", netdev_name(ndev)); + + dev_put(ndev); return 0; } @@ -1495,7 +1510,8 @@ static const struct ib_device_ops rxe_dev_ops = { INIT_RDMA_OBJ_SIZE(ib_mw, rxe_mw, ibmw), }; -int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) +int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name, + struct net_device *ndev) { int err; struct ib_device *dev = &rxe->ib_dev; @@ -1507,13 +1523,13 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) dev->num_comp_vectors = num_possible_cpus(); dev->local_dma_lkey = 0; addrconf_addr_eui48((unsigned char *)&dev->node_guid, - rxe->ndev->dev_addr); + ndev->dev_addr); dev->uverbs_cmd_mask |= BIT_ULL(IB_USER_VERBS_CMD_POST_SEND) | BIT_ULL(IB_USER_VERBS_CMD_REQ_NOTIFY_CQ); ib_set_device_ops(dev, &rxe_dev_ops); - err = ib_device_set_netdev(&rxe->ib_dev, rxe->ndev, 1); + err = ib_device_set_netdev(&rxe->ib_dev, ndev, 1); if (err) return err; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index 3c1354f82283..6573ceec0ef5 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -370,6 +370,7 @@ struct rxe_port { u32 qp_gsi_index; }; +#define RXE_PORT 1 struct rxe_dev { struct ib_device ib_dev; struct ib_device_attr attr; @@ -377,8 +378,6 @@ struct rxe_dev { int max_inline_data; struct mutex usdev_lock; - struct net_device *ndev; - struct rxe_pool uc_pool; struct rxe_pool pd_pool; struct rxe_pool ah_pool; @@ -406,6 +405,11 @@ struct rxe_dev { struct crypto_shash *tfm; }; +static inline struct net_device *rxe_ib_device_get_netdev(struct ib_device *dev) +{ + return ib_device_get_netdev(dev, RXE_PORT); +} + static inline void rxe_counter_inc(struct rxe_dev *rxe, enum rxe_counters index) { atomic64_inc(&rxe->stats_counters[index]); @@ -471,6 +475,7 @@ static inline struct rxe_pd *rxe_mw_pd(struct rxe_mw *mw) return to_rpd(mw->ibmw.pd); } -int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name); +int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name, + struct net_device *ndev); #endif /* RXE_VERBS_H */ diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h index 86d4d6a2170e..ea5eee50dc39 100644 --- a/drivers/infiniband/sw/siw/siw.h +++ b/drivers/infiniband/sw/siw/siw.h @@ -46,6 +46,9 @@ */ #define SIW_IRQ_MAXBURST_SQ_ACTIVE 4 +/* There is always only a port 1 per siw device */ +#define SIW_PORT 1 + struct siw_dev_cap { int max_qp; int max_qp_wr; @@ -69,16 +72,12 @@ struct siw_pd { struct siw_device { struct ib_device base_dev; - struct net_device *netdev; struct siw_dev_cap attrs; u32 vendor_part_id; int numa_node; char raw_gid[ETH_ALEN]; - /* physical port state (only one port per device) */ - enum ib_port_state state; - spinlock_t lock; struct xarray qp_xa; diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 86323918a570..708b13993fdf 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -1759,6 +1759,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) { struct socket *s; struct siw_cep *cep = NULL; + struct net_device *ndev = NULL; struct siw_device *sdev = to_siw_dev(id->device); int addr_family = id->local_addr.ss_family; int rv = 0; @@ -1779,9 +1780,15 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) struct sockaddr_in *laddr = &to_sockaddr_in(id->local_addr); /* For wildcard addr, limit binding to current device only */ - if (ipv4_is_zeronet(laddr->sin_addr.s_addr)) - s->sk->sk_bound_dev_if = sdev->netdev->ifindex; - + if (ipv4_is_zeronet(laddr->sin_addr.s_addr)) { + ndev = ib_device_get_netdev(id->device, SIW_PORT); + if (ndev) { + s->sk->sk_bound_dev_if = ndev->ifindex; + } else { + rv = -ENODEV; + goto error; + } + } rv = s->ops->bind(s, (struct sockaddr *)laddr, sizeof(struct sockaddr_in)); } else { @@ -1797,9 +1804,15 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) } /* For wildcard addr, limit binding to current device only */ - if (ipv6_addr_any(&laddr->sin6_addr)) - s->sk->sk_bound_dev_if = sdev->netdev->ifindex; - + if (ipv6_addr_any(&laddr->sin6_addr)) { + ndev = ib_device_get_netdev(id->device, SIW_PORT); + if (ndev) { + s->sk->sk_bound_dev_if = ndev->ifindex; + } else { + rv = -ENODEV; + goto error; + } + } rv = s->ops->bind(s, (struct sockaddr *)laddr, sizeof(struct sockaddr_in6)); } @@ -1860,6 +1873,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) } list_add_tail(&cep->listenq, (struct list_head *)id->provider_data); cep->state = SIW_EPSTATE_LISTENING; + dev_put(ndev); siw_dbg(id->device, "Listen at laddr %pISp\n", &id->local_addr); @@ -1879,6 +1893,7 @@ error: siw_cep_set_free_and_put(cep); } sock_release(s); + dev_put(ndev); return rv; } diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index 17abef48abcd..b17752bd1ecc 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -287,7 +287,6 @@ static struct siw_device *siw_device_create(struct net_device *netdev) return NULL; base_dev = &sdev->base_dev; - sdev->netdev = netdev; if (netdev->addr_len) { memcpy(sdev->raw_gid, netdev->dev_addr, @@ -380,16 +379,6 @@ static int siw_netdev_event(struct notifier_block *nb, unsigned long event, sdev = to_siw_dev(base_dev); switch (event) { - case NETDEV_UP: - sdev->state = IB_PORT_ACTIVE; - siw_port_event(sdev, 1, IB_EVENT_PORT_ACTIVE); - break; - - case NETDEV_DOWN: - sdev->state = IB_PORT_DOWN; - siw_port_event(sdev, 1, IB_EVENT_PORT_ERR); - break; - case NETDEV_REGISTER: /* * Device registration now handled only by @@ -407,12 +396,8 @@ static int siw_netdev_event(struct notifier_block *nb, unsigned long event, siw_port_event(sdev, 1, IB_EVENT_LID_CHANGE); break; /* - * Todo: Below netdev events are currently not handled. + * All other events are not handled */ - case NETDEV_CHANGEMTU: - case NETDEV_CHANGE: - break; - default: break; } @@ -442,12 +427,6 @@ static int siw_newlink(const char *basedev_name, struct net_device *netdev) sdev = siw_device_create(netdev); if (sdev) { dev_dbg(&netdev->dev, "siw: new device\n"); - - if (netif_running(netdev) && netif_carrier_ok(netdev)) - sdev->state = IB_PORT_ACTIVE; - else - sdev->state = IB_PORT_DOWN; - ib_mark_name_assigned_by_user(&sdev->base_dev); rv = siw_device_register(sdev, basedev_name); if (rv) diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 986666c19378..5ac8bd450d24 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -171,21 +171,28 @@ int siw_query_device(struct ib_device *base_dev, struct ib_device_attr *attr, int siw_query_port(struct ib_device *base_dev, u32 port, struct ib_port_attr *attr) { - struct siw_device *sdev = to_siw_dev(base_dev); + struct net_device *ndev; int rv; memset(attr, 0, sizeof(*attr)); rv = ib_get_eth_speed(base_dev, port, &attr->active_speed, &attr->active_width); + if (rv) + return rv; + + ndev = ib_device_get_netdev(base_dev, SIW_PORT); + if (!ndev) + return -ENODEV; + attr->gid_tbl_len = 1; attr->max_msg_sz = -1; - attr->max_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); - attr->active_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); - attr->phys_state = sdev->state == IB_PORT_ACTIVE ? + attr->max_mtu = ib_mtu_int_to_enum(ndev->max_mtu); + attr->active_mtu = ib_mtu_int_to_enum(READ_ONCE(ndev->mtu)); + attr->state = ib_get_curr_port_state(ndev); + attr->phys_state = attr->state == IB_PORT_ACTIVE ? IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED; attr->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_DEVICE_MGMT_SUP; - attr->state = sdev->state; /* * All zero * @@ -199,6 +206,7 @@ int siw_query_port(struct ib_device *base_dev, u32 port, * attr->subnet_timeout = 0; * attr->init_type_repy = 0; */ + dev_put(ndev); return rv; } @@ -505,21 +513,24 @@ int siw_query_qp(struct ib_qp *base_qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) { struct siw_qp *qp; - struct siw_device *sdev; + struct net_device *ndev; - if (base_qp && qp_attr && qp_init_attr) { + if (base_qp && qp_attr && qp_init_attr) qp = to_siw_qp(base_qp); - sdev = to_siw_dev(base_qp->device); - } else { + else return -EINVAL; - } + + ndev = ib_device_get_netdev(base_qp->device, SIW_PORT); + if (!ndev) + return -ENODEV; + qp_attr->qp_state = siw_qp_state_to_ib_qp_state[qp->attrs.state]; qp_attr->cap.max_inline_data = SIW_MAX_INLINE; qp_attr->cap.max_send_wr = qp->attrs.sq_size; qp_attr->cap.max_send_sge = qp->attrs.sq_max_sges; qp_attr->cap.max_recv_wr = qp->attrs.rq_size; qp_attr->cap.max_recv_sge = qp->attrs.rq_max_sges; - qp_attr->path_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); + qp_attr->path_mtu = ib_mtu_int_to_enum(READ_ONCE(ndev->mtu)); qp_attr->max_rd_atomic = qp->attrs.irq_size; qp_attr->max_dest_rd_atomic = qp->attrs.orq_size; @@ -534,6 +545,7 @@ int siw_query_qp(struct ib_qp *base_qp, struct ib_qp_attr *qp_attr, qp_init_attr->cap = qp_attr->cap; + dev_put(ndev); return 0; } diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index e83d95647852..ef4abdea3c2d 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -349,6 +349,7 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id, struct rtrs_srv_mr *srv_mr; bool need_inval = false; enum ib_send_flags flags; + struct ib_sge list; u32 imm; int err; @@ -401,7 +402,6 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id, imm = rtrs_to_io_rsp_imm(id->msg_id, errno, need_inval); imm_wr.wr.next = NULL; if (always_invalidate) { - struct ib_sge list; struct rtrs_msg_rkey_rsp *msg; srv_mr = &srv_path->mrs[id->msg_id]; diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c index 4e17d546d4cc..bf38ac6f87c4 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs.c +++ b/drivers/infiniband/ulp/rtrs/rtrs.c @@ -584,6 +584,9 @@ static void dev_free(struct kref *ref) list_del(&dev->entry); mutex_unlock(&pool->mutex); + if (pool->ops && pool->ops->deinit) + pool->ops->deinit(dev); + ib_dealloc_pd(dev->ib_pd); kfree(dev); } diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 2916e77f589b..1378651735f6 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -2844,7 +2844,8 @@ static int srp_target_alloc(struct scsi_target *starget) return 0; } -static int srp_slave_configure(struct scsi_device *sdev) +static int srp_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct Scsi_Host *shost = sdev->host; struct srp_target_port *target = host_to_target(shost); @@ -3067,7 +3068,7 @@ static const struct scsi_host_template srp_template = { .name = "InfiniBand SRP initiator", .proc_name = DRV_NAME, .target_alloc = srp_target_alloc, - .slave_configure = srp_slave_configure, + .sdev_configure = srp_sdev_configure, .info = srp_target_info, .init_cmd_priv = srp_init_cmd_priv, .exit_cmd_priv = srp_exit_cmd_priv, @@ -3978,7 +3979,6 @@ static struct srp_host *srp_add_port(struct srp_device *device, u32 port) return host; put_host: - device_del(&host->dev); put_device(&host->dev); return NULL; } diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig index 3bdbd34314b3..88ecdf5218ee 100644 --- a/drivers/input/Kconfig +++ b/drivers/input/Kconfig @@ -152,20 +152,6 @@ config INPUT_EVDEV To compile this driver as a module, choose M here: the module will be called evdev. -config INPUT_EVBUG - tristate "Event debugging" - help - Say Y here if you have a problem with the input subsystem and - want all events (keypresses, mouse movements), to be output to - the system log. While this is useful for debugging, it's also - a security threat - your keypresses include your passwords, of - course. - - If unsure, say N. - - To compile this driver as a module, choose M here: the - module will be called evbug. - config INPUT_KUNIT_TEST tristate "KUnit tests for Input" if !KUNIT_ALL_TESTS depends on INPUT && KUNIT diff --git a/drivers/input/Makefile b/drivers/input/Makefile index c78753274921..930b64d2115e 100644 --- a/drivers/input/Makefile +++ b/drivers/input/Makefile @@ -18,7 +18,6 @@ obj-$(CONFIG_INPUT_LEDS) += input-leds.o obj-$(CONFIG_INPUT_MOUSEDEV) += mousedev.o obj-$(CONFIG_INPUT_JOYDEV) += joydev.o obj-$(CONFIG_INPUT_EVDEV) += evdev.o -obj-$(CONFIG_INPUT_EVBUG) += evbug.o obj-$(CONFIG_INPUT_KEYBOARD) += keyboard/ obj-$(CONFIG_INPUT_MOUSE) += mouse/ diff --git a/drivers/input/evbug.c b/drivers/input/evbug.c deleted file mode 100644 index e47bdf92088a..000000000000 --- a/drivers/input/evbug.c +++ /dev/null @@ -1,100 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (c) 1999-2001 Vojtech Pavlik - */ - -/* - * Input driver event debug module - dumps all events into syslog - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include - -MODULE_AUTHOR("Vojtech Pavlik "); -MODULE_DESCRIPTION("Input driver event debug module"); -MODULE_LICENSE("GPL"); - -static void evbug_event(struct input_handle *handle, unsigned int type, unsigned int code, int value) -{ - printk(KERN_DEBUG pr_fmt("Event. Dev: %s, Type: %d, Code: %d, Value: %d\n"), - dev_name(&handle->dev->dev), type, code, value); -} - -static int evbug_connect(struct input_handler *handler, struct input_dev *dev, - const struct input_device_id *id) -{ - struct input_handle *handle; - int error; - - handle = kzalloc(sizeof(struct input_handle), GFP_KERNEL); - if (!handle) - return -ENOMEM; - - handle->dev = dev; - handle->handler = handler; - handle->name = "evbug"; - - error = input_register_handle(handle); - if (error) - goto err_free_handle; - - error = input_open_device(handle); - if (error) - goto err_unregister_handle; - - printk(KERN_DEBUG pr_fmt("Connected device: %s (%s at %s)\n"), - dev_name(&dev->dev), - dev->name ?: "unknown", - dev->phys ?: "unknown"); - - return 0; - - err_unregister_handle: - input_unregister_handle(handle); - err_free_handle: - kfree(handle); - return error; -} - -static void evbug_disconnect(struct input_handle *handle) -{ - printk(KERN_DEBUG pr_fmt("Disconnected device: %s\n"), - dev_name(&handle->dev->dev)); - - input_close_device(handle); - input_unregister_handle(handle); - kfree(handle); -} - -static const struct input_device_id evbug_ids[] = { - { .driver_info = 1 }, /* Matches all devices */ - { }, /* Terminating zero entry */ -}; - -MODULE_DEVICE_TABLE(input, evbug_ids); - -static struct input_handler evbug_handler = { - .event = evbug_event, - .connect = evbug_connect, - .disconnect = evbug_disconnect, - .name = "evbug", - .id_table = evbug_ids, -}; - -static int __init evbug_init(void) -{ - return input_register_handler(&evbug_handler); -} - -static void __exit evbug_exit(void) -{ - input_unregister_handler(&evbug_handler); -} - -module_init(evbug_init); -module_exit(evbug_exit); diff --git a/drivers/input/ff-core.c b/drivers/input/ff-core.c index 609a5f01761b..b527308cb52e 100644 --- a/drivers/input/ff-core.c +++ b/drivers/input/ff-core.c @@ -93,7 +93,7 @@ int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, { struct ff_device *ff = dev->ff; struct ff_effect *old; - int ret = 0; + int error; int id; if (!test_bit(EV_FF, dev->evbit)) @@ -114,22 +114,20 @@ int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, } if (!test_bit(effect->type, ff->ffbit)) { - ret = compat_effect(ff, effect); - if (ret) - return ret; + error = compat_effect(ff, effect); + if (error) + return error; } - mutex_lock(&ff->mutex); + guard(mutex)(&ff->mutex); if (effect->id == -1) { for (id = 0; id < ff->max_effects; id++) if (!ff->effect_owners[id]) break; - if (id >= ff->max_effects) { - ret = -ENOSPC; - goto out; - } + if (id >= ff->max_effects) + return -ENOSPC; effect->id = id; old = NULL; @@ -137,30 +135,26 @@ int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, } else { id = effect->id; - ret = check_effect_access(ff, id, file); - if (ret) - goto out; + error = check_effect_access(ff, id, file); + if (error) + return error; old = &ff->effects[id]; - if (!check_effects_compatible(effect, old)) { - ret = -EINVAL; - goto out; - } + if (!check_effects_compatible(effect, old)) + return -EINVAL; } - ret = ff->upload(dev, effect, old); - if (ret) - goto out; + error = ff->upload(dev, effect, old); + if (error) + return error; - spin_lock_irq(&dev->event_lock); - ff->effects[id] = *effect; - ff->effect_owners[id] = file; - spin_unlock_irq(&dev->event_lock); + scoped_guard(spinlock_irq, &dev->event_lock) { + ff->effects[id] = *effect; + ff->effect_owners[id] = file; + } - out: - mutex_unlock(&ff->mutex); - return ret; + return 0; } EXPORT_SYMBOL_GPL(input_ff_upload); @@ -178,17 +172,16 @@ static int erase_effect(struct input_dev *dev, int effect_id, if (error) return error; - spin_lock_irq(&dev->event_lock); - ff->playback(dev, effect_id, 0); - ff->effect_owners[effect_id] = NULL; - spin_unlock_irq(&dev->event_lock); + scoped_guard(spinlock_irq, &dev->event_lock) { + ff->playback(dev, effect_id, 0); + ff->effect_owners[effect_id] = NULL; + } if (ff->erase) { error = ff->erase(dev, effect_id); if (error) { - spin_lock_irq(&dev->event_lock); - ff->effect_owners[effect_id] = file; - spin_unlock_irq(&dev->event_lock); + scoped_guard(spinlock_irq, &dev->event_lock) + ff->effect_owners[effect_id] = file; return error; } @@ -210,16 +203,12 @@ static int erase_effect(struct input_dev *dev, int effect_id, int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file) { struct ff_device *ff = dev->ff; - int ret; if (!test_bit(EV_FF, dev->evbit)) return -ENOSYS; - mutex_lock(&ff->mutex); - ret = erase_effect(dev, effect_id, file); - mutex_unlock(&ff->mutex); - - return ret; + guard(mutex)(&ff->mutex); + return erase_effect(dev, effect_id, file); } EXPORT_SYMBOL_GPL(input_ff_erase); @@ -239,13 +228,11 @@ int input_ff_flush(struct input_dev *dev, struct file *file) dev_dbg(&dev->dev, "flushing now\n"); - mutex_lock(&ff->mutex); + guard(mutex)(&ff->mutex); for (i = 0; i < ff->max_effects; i++) erase_effect(dev, i, file); - mutex_unlock(&ff->mutex); - return 0; } EXPORT_SYMBOL_GPL(input_ff_flush); @@ -303,8 +290,6 @@ EXPORT_SYMBOL_GPL(input_ff_event); */ int input_ff_create(struct input_dev *dev, unsigned int max_effects) { - struct ff_device *ff; - size_t ff_dev_size; int i; if (!max_effects) { @@ -317,25 +302,19 @@ int input_ff_create(struct input_dev *dev, unsigned int max_effects) return -EINVAL; } - ff_dev_size = struct_size(ff, effect_owners, max_effects); - if (ff_dev_size == SIZE_MAX) /* overflow */ - return -EINVAL; - - ff = kzalloc(ff_dev_size, GFP_KERNEL); + struct ff_device *ff __free(kfree) = + kzalloc(struct_size(ff, effect_owners, max_effects), + GFP_KERNEL); if (!ff) return -ENOMEM; - ff->effects = kcalloc(max_effects, sizeof(struct ff_effect), - GFP_KERNEL); - if (!ff->effects) { - kfree(ff); + ff->effects = kcalloc(max_effects, sizeof(*ff->effects), GFP_KERNEL); + if (!ff->effects) return -ENOMEM; - } ff->max_effects = max_effects; mutex_init(&ff->mutex); - dev->ff = ff; dev->flush = input_ff_flush; dev->event = input_ff_event; __set_bit(EV_FF, dev->evbit); @@ -348,6 +327,8 @@ int input_ff_create(struct input_dev *dev, unsigned int max_effects) if (test_bit(FF_PERIODIC, ff->ffbit)) __set_bit(FF_RUMBLE, dev->ffbit); + dev->ff = no_free_ptr(ff); + return 0; } EXPORT_SYMBOL_GPL(input_ff_create); diff --git a/drivers/input/ff-memless.c b/drivers/input/ff-memless.c index c321cdabd214..e9120ba6bae0 100644 --- a/drivers/input/ff-memless.c +++ b/drivers/input/ff-memless.c @@ -401,13 +401,11 @@ static void ml_effect_timer(struct timer_list *t) { struct ml_device *ml = from_timer(ml, t, timer); struct input_dev *dev = ml->dev; - unsigned long flags; pr_debug("timer: updating effects\n"); - spin_lock_irqsave(&dev->event_lock, flags); + guard(spinlock_irqsave)(&dev->event_lock); ml_play_effects(ml); - spin_unlock_irqrestore(&dev->event_lock, flags); } /* @@ -465,7 +463,7 @@ static int ml_ff_upload(struct input_dev *dev, struct ml_device *ml = dev->ff->private; struct ml_effect_state *state = &ml->states[effect->id]; - spin_lock_irq(&dev->event_lock); + guard(spinlock_irq)(&dev->event_lock); if (test_bit(FF_EFFECT_STARTED, &state->flags)) { __clear_bit(FF_EFFECT_PLAYING, &state->flags); @@ -477,8 +475,6 @@ static int ml_ff_upload(struct input_dev *dev, ml_schedule_timer(ml); } - spin_unlock_irq(&dev->event_lock); - return 0; } @@ -507,12 +503,11 @@ static void ml_ff_destroy(struct ff_device *ff) int input_ff_create_memless(struct input_dev *dev, void *data, int (*play_effect)(struct input_dev *, void *, struct ff_effect *)) { - struct ml_device *ml; struct ff_device *ff; int error; int i; - ml = kzalloc(sizeof(struct ml_device), GFP_KERNEL); + struct ml_device *ml __free(kfree) = kzalloc(sizeof(*ml), GFP_KERNEL); if (!ml) return -ENOMEM; @@ -525,13 +520,10 @@ int input_ff_create_memless(struct input_dev *dev, void *data, set_bit(FF_GAIN, dev->ffbit); error = input_ff_create(dev, FF_MEMLESS_EFFECTS); - if (error) { - kfree(ml); + if (error) return error; - } ff = dev->ff; - ff->private = ml; ff->upload = ml_ff_upload; ff->playback = ml_ff_playback; ff->set_gain = ml_ff_set_gain; @@ -548,6 +540,8 @@ int input_ff_create_memless(struct input_dev *dev, void *data, for (i = 0; i < FF_MEMLESS_EFFECTS; i++) ml->states[i].effect = &ff->effects[i]; + ff->private = no_free_ptr(ml); + return 0; } EXPORT_SYMBOL_GPL(input_ff_create_memless); diff --git a/drivers/input/input-mt.c b/drivers/input/input-mt.c index 6b04a674f832..337006dd9dcf 100644 --- a/drivers/input/input-mt.c +++ b/drivers/input/input-mt.c @@ -39,20 +39,20 @@ static void copy_abs(struct input_dev *dev, unsigned int dst, unsigned int src) int input_mt_init_slots(struct input_dev *dev, unsigned int num_slots, unsigned int flags) { - struct input_mt *mt = dev->mt; - int i; - if (!num_slots) return 0; - if (mt) - return mt->num_slots != num_slots ? -EINVAL : 0; + + if (dev->mt) + return dev->mt->num_slots != num_slots ? -EINVAL : 0; + /* Arbitrary limit for avoiding too large memory allocation. */ if (num_slots > 1024) return -EINVAL; - mt = kzalloc(struct_size(mt, slots, num_slots), GFP_KERNEL); + struct input_mt *mt __free(kfree) = + kzalloc(struct_size(mt, slots, num_slots), GFP_KERNEL); if (!mt) - goto err_mem; + return -ENOMEM; mt->num_slots = num_slots; mt->flags = flags; @@ -86,21 +86,18 @@ int input_mt_init_slots(struct input_dev *dev, unsigned int num_slots, unsigned int n2 = num_slots * num_slots; mt->red = kcalloc(n2, sizeof(*mt->red), GFP_KERNEL); if (!mt->red) - goto err_mem; + return -ENOMEM; } /* Mark slots as 'inactive' */ - for (i = 0; i < num_slots; i++) + for (unsigned int i = 0; i < num_slots; i++) input_mt_set_value(&mt->slots[i], ABS_MT_TRACKING_ID, -1); /* Mark slots as 'unused' */ mt->frame = 1; - dev->mt = mt; + dev->mt = no_free_ptr(mt); return 0; -err_mem: - kfree(mt); - return -ENOMEM; } EXPORT_SYMBOL(input_mt_init_slots); @@ -285,14 +282,10 @@ void input_mt_drop_unused(struct input_dev *dev) struct input_mt *mt = dev->mt; if (mt) { - unsigned long flags; - - spin_lock_irqsave(&dev->event_lock, flags); + guard(spinlock_irqsave)(&dev->event_lock); __input_mt_drop_unused(dev, mt); mt->frame++; - - spin_unlock_irqrestore(&dev->event_lock, flags); } } EXPORT_SYMBOL(input_mt_drop_unused); @@ -339,11 +332,8 @@ void input_mt_sync_frame(struct input_dev *dev) return; if (mt->flags & INPUT_MT_DROP_UNUSED) { - unsigned long flags; - - spin_lock_irqsave(&dev->event_lock, flags); + guard(spinlock_irqsave)(&dev->event_lock); __input_mt_drop_unused(dev, mt); - spin_unlock_irqrestore(&dev->event_lock, flags); } if ((mt->flags & INPUT_MT_POINTER) && !(mt->flags & INPUT_MT_SEMI_MT)) diff --git a/drivers/input/input-poller.c b/drivers/input/input-poller.c index 688e3cb1c2a0..9c57713a6151 100644 --- a/drivers/input/input-poller.c +++ b/drivers/input/input-poller.c @@ -162,7 +162,7 @@ static ssize_t input_dev_set_poll_interval(struct device *dev, if (interval > poller->poll_interval_max) return -EINVAL; - mutex_lock(&input->mutex); + guard(mutex)(&input->mutex); poller->poll_interval = interval; @@ -172,8 +172,6 @@ static ssize_t input_dev_set_poll_interval(struct device *dev, input_dev_poller_queue_work(poller); } - mutex_unlock(&input->mutex); - return count; } diff --git a/drivers/input/input.c b/drivers/input/input.c index 7f0477e04ad2..c9e3ac64bcd0 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -115,23 +115,23 @@ static void input_pass_values(struct input_dev *dev, lockdep_assert_held(&dev->event_lock); - rcu_read_lock(); + scoped_guard(rcu) { + handle = rcu_dereference(dev->grab); + if (handle) { + count = handle->handle_events(handle, vals, count); + break; + } - handle = rcu_dereference(dev->grab); - if (handle) { - count = handle->handle_events(handle, vals, count); - } else { - list_for_each_entry_rcu(handle, &dev->h_list, d_node) + list_for_each_entry_rcu(handle, &dev->h_list, d_node) { if (handle->open) { count = handle->handle_events(handle, vals, count); if (!count) break; } + } } - rcu_read_unlock(); - /* trigger auto repeat for key events */ if (test_bit(EV_REP, dev->evbit) && test_bit(EV_KEY, dev->evbit)) { for (v = vals; v != vals + count; v++) { @@ -390,13 +390,9 @@ void input_handle_event(struct input_dev *dev, void input_event(struct input_dev *dev, unsigned int type, unsigned int code, int value) { - unsigned long flags; - if (is_event_supported(type, dev->evbit, EV_MAX)) { - - spin_lock_irqsave(&dev->event_lock, flags); + guard(spinlock_irqsave)(&dev->event_lock); input_handle_event(dev, type, code, value); - spin_unlock_irqrestore(&dev->event_lock, flags); } } EXPORT_SYMBOL(input_event); @@ -417,18 +413,15 @@ void input_inject_event(struct input_handle *handle, { struct input_dev *dev = handle->dev; struct input_handle *grab; - unsigned long flags; if (is_event_supported(type, dev->evbit, EV_MAX)) { - spin_lock_irqsave(&dev->event_lock, flags); + guard(spinlock_irqsave)(&dev->event_lock); + guard(rcu)(); - rcu_read_lock(); grab = rcu_dereference(dev->grab); if (!grab || grab == handle) input_handle_event(dev, type, code, value); - rcu_read_unlock(); - spin_unlock_irqrestore(&dev->event_lock, flags); } } EXPORT_SYMBOL(input_inject_event); @@ -526,22 +519,15 @@ EXPORT_SYMBOL(input_copy_abs); int input_grab_device(struct input_handle *handle) { struct input_dev *dev = handle->dev; - int retval; - retval = mutex_lock_interruptible(&dev->mutex); - if (retval) - return retval; + scoped_cond_guard(mutex_intr, return -EINTR, &dev->mutex) { + if (dev->grab) + return -EBUSY; - if (dev->grab) { - retval = -EBUSY; - goto out; + rcu_assign_pointer(dev->grab, handle); } - rcu_assign_pointer(dev->grab, handle); - - out: - mutex_unlock(&dev->mutex); - return retval; + return 0; } EXPORT_SYMBOL(input_grab_device); @@ -576,9 +562,8 @@ void input_release_device(struct input_handle *handle) { struct input_dev *dev = handle->dev; - mutex_lock(&dev->mutex); + guard(mutex)(&dev->mutex); __input_release_device(handle); - mutex_unlock(&dev->mutex); } EXPORT_SYMBOL(input_release_device); @@ -592,67 +577,57 @@ EXPORT_SYMBOL(input_release_device); int input_open_device(struct input_handle *handle) { struct input_dev *dev = handle->dev; - int retval; + int error; - retval = mutex_lock_interruptible(&dev->mutex); - if (retval) - return retval; + scoped_cond_guard(mutex_intr, return -EINTR, &dev->mutex) { + if (dev->going_away) + return -ENODEV; - if (dev->going_away) { - retval = -ENODEV; - goto out; - } + handle->open++; - handle->open++; + if (handle->handler->passive_observer) + return 0; - if (handle->handler->passive_observer) - goto out; - - if (dev->users++ || dev->inhibited) { - /* - * Device is already opened and/or inhibited, - * so we can exit immediately and report success. - */ - goto out; - } - - if (dev->open) { - retval = dev->open(dev); - if (retval) { - dev->users--; - handle->open--; + if (dev->users++ || dev->inhibited) { /* - * Make sure we are not delivering any more events - * through this handle + * Device is already opened and/or inhibited, + * so we can exit immediately and report success. */ - synchronize_rcu(); - goto out; + return 0; } + + if (dev->open) { + error = dev->open(dev); + if (error) { + dev->users--; + handle->open--; + /* + * Make sure we are not delivering any more + * events through this handle. + */ + synchronize_rcu(); + return error; + } + } + + if (dev->poller) + input_dev_poller_start(dev->poller); } - if (dev->poller) - input_dev_poller_start(dev->poller); - - out: - mutex_unlock(&dev->mutex); - return retval; + return 0; } EXPORT_SYMBOL(input_open_device); int input_flush_device(struct input_handle *handle, struct file *file) { struct input_dev *dev = handle->dev; - int retval; - retval = mutex_lock_interruptible(&dev->mutex); - if (retval) - return retval; + scoped_cond_guard(mutex_intr, return -EINTR, &dev->mutex) { + if (dev->flush) + return dev->flush(dev, file); + } - if (dev->flush) - retval = dev->flush(dev, file); - - mutex_unlock(&dev->mutex); - return retval; + return 0; } EXPORT_SYMBOL(input_flush_device); @@ -667,7 +642,7 @@ void input_close_device(struct input_handle *handle) { struct input_dev *dev = handle->dev; - mutex_lock(&dev->mutex); + guard(mutex)(&dev->mutex); __input_release_device(handle); @@ -688,8 +663,6 @@ void input_close_device(struct input_handle *handle) */ synchronize_rcu(); } - - mutex_unlock(&dev->mutex); } EXPORT_SYMBOL(input_close_device); @@ -726,11 +699,10 @@ static void input_disconnect_device(struct input_dev *dev) * not to protect access to dev->going_away but rather to ensure * that there are no threads in the middle of input_open_device() */ - mutex_lock(&dev->mutex); - dev->going_away = true; - mutex_unlock(&dev->mutex); + scoped_guard(mutex, &dev->mutex) + dev->going_away = true; - spin_lock_irq(&dev->event_lock); + guard(spinlock_irq)(&dev->event_lock); /* * Simulate keyup events for all pressed keys so that handlers @@ -743,8 +715,6 @@ static void input_disconnect_device(struct input_dev *dev) list_for_each_entry(handle, &dev->h_list, d_node) handle->open = 0; - - spin_unlock_irq(&dev->event_lock); } /** @@ -901,14 +871,9 @@ static int input_default_setkeycode(struct input_dev *dev, */ int input_get_keycode(struct input_dev *dev, struct input_keymap_entry *ke) { - unsigned long flags; - int retval; + guard(spinlock_irqsave)(&dev->event_lock); - spin_lock_irqsave(&dev->event_lock, flags); - retval = dev->getkeycode(dev, ke); - spin_unlock_irqrestore(&dev->event_lock, flags); - - return retval; + return dev->getkeycode(dev, ke); } EXPORT_SYMBOL(input_get_keycode); @@ -923,18 +888,17 @@ EXPORT_SYMBOL(input_get_keycode); int input_set_keycode(struct input_dev *dev, const struct input_keymap_entry *ke) { - unsigned long flags; unsigned int old_keycode; - int retval; + int error; if (ke->keycode > KEY_MAX) return -EINVAL; - spin_lock_irqsave(&dev->event_lock, flags); + guard(spinlock_irqsave)(&dev->event_lock); - retval = dev->setkeycode(dev, ke, &old_keycode); - if (retval) - goto out; + error = dev->setkeycode(dev, ke, &old_keycode); + if (error) + return error; /* Make sure KEY_RESERVED did not get enabled. */ __clear_bit(KEY_RESERVED, dev->keybit); @@ -962,10 +926,7 @@ int input_set_keycode(struct input_dev *dev, EV_SYN, SYN_REPORT, 1); } - out: - spin_unlock_irqrestore(&dev->event_lock, flags); - - return retval; + return 0; } EXPORT_SYMBOL(input_set_keycode); @@ -1799,26 +1760,21 @@ static void input_dev_toggle(struct input_dev *dev, bool activate) */ void input_reset_device(struct input_dev *dev) { - unsigned long flags; - - mutex_lock(&dev->mutex); - spin_lock_irqsave(&dev->event_lock, flags); + guard(mutex)(&dev->mutex); + guard(spinlock_irqsave)(&dev->event_lock); input_dev_toggle(dev, true); if (input_dev_release_keys(dev)) input_handle_event(dev, EV_SYN, SYN_REPORT, 1); - - spin_unlock_irqrestore(&dev->event_lock, flags); - mutex_unlock(&dev->mutex); } EXPORT_SYMBOL(input_reset_device); static int input_inhibit_device(struct input_dev *dev) { - mutex_lock(&dev->mutex); + guard(mutex)(&dev->mutex); if (dev->inhibited) - goto out; + return 0; if (dev->users) { if (dev->close) @@ -1827,54 +1783,50 @@ static int input_inhibit_device(struct input_dev *dev) input_dev_poller_stop(dev->poller); } - spin_lock_irq(&dev->event_lock); - input_mt_release_slots(dev); - input_dev_release_keys(dev); - input_handle_event(dev, EV_SYN, SYN_REPORT, 1); - input_dev_toggle(dev, false); - spin_unlock_irq(&dev->event_lock); + scoped_guard(spinlock_irq, &dev->event_lock) { + input_mt_release_slots(dev); + input_dev_release_keys(dev); + input_handle_event(dev, EV_SYN, SYN_REPORT, 1); + input_dev_toggle(dev, false); + } dev->inhibited = true; -out: - mutex_unlock(&dev->mutex); return 0; } static int input_uninhibit_device(struct input_dev *dev) { - int ret = 0; + int error; - mutex_lock(&dev->mutex); + guard(mutex)(&dev->mutex); if (!dev->inhibited) - goto out; + return 0; if (dev->users) { if (dev->open) { - ret = dev->open(dev); - if (ret) - goto out; + error = dev->open(dev); + if (error) + return error; } if (dev->poller) input_dev_poller_start(dev->poller); } dev->inhibited = false; - spin_lock_irq(&dev->event_lock); - input_dev_toggle(dev, true); - spin_unlock_irq(&dev->event_lock); -out: - mutex_unlock(&dev->mutex); - return ret; + scoped_guard(spinlock_irq, &dev->event_lock) + input_dev_toggle(dev, true); + + return 0; } static int input_dev_suspend(struct device *dev) { struct input_dev *input_dev = to_input_dev(dev); - spin_lock_irq(&input_dev->event_lock); + guard(spinlock_irq)(&input_dev->event_lock); /* * Keys that are pressed now are unlikely to be @@ -1886,8 +1838,6 @@ static int input_dev_suspend(struct device *dev) /* Turn off LEDs and sounds, if any are active. */ input_dev_toggle(input_dev, false); - spin_unlock_irq(&input_dev->event_lock); - return 0; } @@ -1895,13 +1845,11 @@ static int input_dev_resume(struct device *dev) { struct input_dev *input_dev = to_input_dev(dev); - spin_lock_irq(&input_dev->event_lock); + guard(spinlock_irq)(&input_dev->event_lock); /* Restore state of LEDs and sounds, if any were active. */ input_dev_toggle(input_dev, true); - spin_unlock_irq(&input_dev->event_lock); - return 0; } @@ -1909,7 +1857,7 @@ static int input_dev_freeze(struct device *dev) { struct input_dev *input_dev = to_input_dev(dev); - spin_lock_irq(&input_dev->event_lock); + guard(spinlock_irq)(&input_dev->event_lock); /* * Keys that are pressed now are unlikely to be @@ -1918,8 +1866,6 @@ static int input_dev_freeze(struct device *dev) if (input_dev_release_keys(input_dev)) input_handle_event(input_dev, EV_SYN, SYN_REPORT, 1); - spin_unlock_irq(&input_dev->event_lock); - return 0; } @@ -1927,13 +1873,11 @@ static int input_dev_poweroff(struct device *dev) { struct input_dev *input_dev = to_input_dev(dev); - spin_lock_irq(&input_dev->event_lock); + guard(spinlock_irq)(&input_dev->event_lock); /* Turn off LEDs and sounds, if any are active. */ input_dev_toggle(input_dev, false); - spin_unlock_irq(&input_dev->event_lock); - return 0; } @@ -2274,18 +2218,16 @@ static void __input_unregister_device(struct input_dev *dev) input_disconnect_device(dev); - mutex_lock(&input_mutex); + scoped_guard(mutex, &input_mutex) { + list_for_each_entry_safe(handle, next, &dev->h_list, d_node) + handle->handler->disconnect(handle); + WARN_ON(!list_empty(&dev->h_list)); - list_for_each_entry_safe(handle, next, &dev->h_list, d_node) - handle->handler->disconnect(handle); - WARN_ON(!list_empty(&dev->h_list)); + del_timer_sync(&dev->timer); + list_del_init(&dev->node); - del_timer_sync(&dev->timer); - list_del_init(&dev->node); - - input_wakeup_procfs_readers(); - - mutex_unlock(&input_mutex); + input_wakeup_procfs_readers(); + } device_del(&dev->dev); } @@ -2308,9 +2250,8 @@ static void devm_input_device_unregister(struct device *dev, void *res) static void input_repeat_key(struct timer_list *t) { struct input_dev *dev = from_timer(dev, t, timer); - unsigned long flags; - spin_lock_irqsave(&dev->event_lock, flags); + guard(spinlock_irqsave)(&dev->event_lock); if (!dev->inhibited && test_bit(dev->repeat_key, dev->key) && @@ -2324,8 +2265,6 @@ static void input_repeat_key(struct timer_list *t) mod_timer(&dev->timer, jiffies + msecs_to_jiffies(dev->rep[REP_PERIOD])); } - - spin_unlock_irqrestore(&dev->event_lock, flags); } /** @@ -2370,10 +2309,10 @@ static int input_device_tune_vals(struct input_dev *dev) if (!vals) return -ENOMEM; - spin_lock_irq(&dev->event_lock); - dev->max_vals = max_vals; - swap(dev->vals, vals); - spin_unlock_irq(&dev->event_lock); + scoped_guard(spinlock_irq, &dev->event_lock) { + dev->max_vals = max_vals; + swap(dev->vals, vals); + } /* Because of swap() above, this frees the old vals memory */ kfree(vals); @@ -2465,18 +2404,15 @@ int input_register_device(struct input_dev *dev) path ? path : "N/A"); kfree(path); - error = mutex_lock_interruptible(&input_mutex); - if (error) - goto err_device_del; + error = -EINTR; + scoped_cond_guard(mutex_intr, goto err_device_del, &input_mutex) { + list_add_tail(&dev->node, &input_dev_list); - list_add_tail(&dev->node, &input_dev_list); + list_for_each_entry(handler, &input_handler_list, node) + input_attach_handler(dev, handler); - list_for_each_entry(handler, &input_handler_list, node) - input_attach_handler(dev, handler); - - input_wakeup_procfs_readers(); - - mutex_unlock(&input_mutex); + input_wakeup_procfs_readers(); + } if (dev->devres_managed) { dev_dbg(dev->dev.parent, "%s: registering %s with devres.\n", @@ -2556,20 +2492,17 @@ int input_register_handler(struct input_handler *handler) if (error) return error; - INIT_LIST_HEAD(&handler->h_list); + scoped_cond_guard(mutex_intr, return -EINTR, &input_mutex) { + INIT_LIST_HEAD(&handler->h_list); - error = mutex_lock_interruptible(&input_mutex); - if (error) - return error; + list_add_tail(&handler->node, &input_handler_list); - list_add_tail(&handler->node, &input_handler_list); + list_for_each_entry(dev, &input_dev_list, node) + input_attach_handler(dev, handler); - list_for_each_entry(dev, &input_dev_list, node) - input_attach_handler(dev, handler); + input_wakeup_procfs_readers(); + } - input_wakeup_procfs_readers(); - - mutex_unlock(&input_mutex); return 0; } EXPORT_SYMBOL(input_register_handler); @@ -2585,7 +2518,7 @@ void input_unregister_handler(struct input_handler *handler) { struct input_handle *handle, *next; - mutex_lock(&input_mutex); + guard(mutex)(&input_mutex); list_for_each_entry_safe(handle, next, &handler->h_list, h_node) handler->disconnect(handle); @@ -2594,8 +2527,6 @@ void input_unregister_handler(struct input_handler *handler) list_del_init(&handler->node); input_wakeup_procfs_readers(); - - mutex_unlock(&input_mutex); } EXPORT_SYMBOL(input_unregister_handler); @@ -2615,19 +2546,17 @@ int input_handler_for_each_handle(struct input_handler *handler, void *data, int (*fn)(struct input_handle *, void *)) { struct input_handle *handle; - int retval = 0; + int retval; - rcu_read_lock(); + guard(rcu)(); list_for_each_entry_rcu(handle, &handler->h_list, h_node) { retval = fn(handle, data); if (retval) - break; + return retval; } - rcu_read_unlock(); - - return retval; + return 0; } EXPORT_SYMBOL(input_handler_for_each_handle); @@ -2715,27 +2644,22 @@ int input_register_handle(struct input_handle *handle) { struct input_handler *handler = handle->handler; struct input_dev *dev = handle->dev; - int error; input_handle_setup_event_handler(handle); /* * We take dev->mutex here to prevent race with * input_release_device(). */ - error = mutex_lock_interruptible(&dev->mutex); - if (error) - return error; - - /* - * Filters go to the head of the list, normal handlers - * to the tail. - */ - if (handler->filter) - list_add_rcu(&handle->d_node, &dev->h_list); - else - list_add_tail_rcu(&handle->d_node, &dev->h_list); - - mutex_unlock(&dev->mutex); + scoped_cond_guard(mutex_intr, return -EINTR, &dev->mutex) { + /* + * Filters go to the head of the list, normal handlers + * to the tail. + */ + if (handler->filter) + list_add_rcu(&handle->d_node, &dev->h_list); + else + list_add_tail_rcu(&handle->d_node, &dev->h_list); + } /* * Since we are supposed to be called from ->connect() @@ -2771,9 +2695,8 @@ void input_unregister_handle(struct input_handle *handle) /* * Take dev->mutex to prevent race with input_release_device(). */ - mutex_lock(&dev->mutex); - list_del_rcu(&handle->d_node); - mutex_unlock(&dev->mutex); + scoped_guard(mutex, &dev->mutex) + list_del_rcu(&handle->d_node); synchronize_rcu(); } diff --git a/drivers/input/joystick/sidewinder.c b/drivers/input/joystick/sidewinder.c index f6e92db4d789..3a5873e5fcb3 100644 --- a/drivers/input/joystick/sidewinder.c +++ b/drivers/input/joystick/sidewinder.c @@ -14,6 +14,7 @@ #include #include #include +#include #define DRIVER_DESC "Microsoft SideWinder joystick family driver" @@ -677,7 +678,7 @@ static int sw_connect(struct gameport *gameport, struct gameport_driver *drv) case 48: /* Ambiguous */ if (j == 14) { /* ID length 14*3 -> FFP */ sw->type = SW_ID_FFP; - sprintf(comment, " [AC %s]", sw_get_bits(idbuf,38,1,3) ? "off" : "on"); + sprintf(comment, " [AC %s]", str_off_on(sw_get_bits(idbuf,38,1,3))); } else sw->type = SW_ID_PP; break; diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index ff9bc87f2f70..8fe2a51df649 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -150,6 +150,7 @@ static const struct xpad_device { { 0x045e, 0x028e, "Microsoft X-Box 360 pad", 0, XTYPE_XBOX360 }, { 0x045e, 0x028f, "Microsoft X-Box 360 pad v2", 0, XTYPE_XBOX360 }, { 0x045e, 0x0291, "Xbox 360 Wireless Receiver (XBOX)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W }, + { 0x045e, 0x02a9, "Xbox 360 Wireless Receiver (Unofficial)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W }, { 0x045e, 0x02d1, "Microsoft X-Box One pad", 0, XTYPE_XBOXONE }, { 0x045e, 0x02dd, "Microsoft X-Box One pad (Firmware 2015)", 0, XTYPE_XBOXONE }, { 0x045e, 0x02e3, "Microsoft X-Box One Elite pad", MAP_PADDLES, XTYPE_XBOXONE }, @@ -305,6 +306,7 @@ static const struct xpad_device { { 0x1689, 0xfe00, "Razer Sabertooth", 0, XTYPE_XBOX360 }, { 0x17ef, 0x6182, "Lenovo Legion Controller for Windows", 0, XTYPE_XBOX360 }, { 0x1949, 0x041a, "Amazon Game Controller", 0, XTYPE_XBOX360 }, + { 0x1a86, 0xe310, "QH Electronics Controller", 0, XTYPE_XBOX360 }, { 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 }, { 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, { 0x1bad, 0x0130, "Ion Drum Rocker", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, @@ -373,16 +375,19 @@ static const struct xpad_device { { 0x294b, 0x3303, "Snakebyte GAMEPAD BASE X", 0, XTYPE_XBOXONE }, { 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE }, { 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE }, - { 0x2dc8, 0x3106, "8BitDo Pro 2 Wired Controller", 0, XTYPE_XBOX360 }, + { 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 }, { 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 }, { 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE }, { 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1200, "Wooting Two", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1210, "Wooting Lekker", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1220, "Wooting Two HE", 0, XTYPE_XBOX360 }, + { 0x31e3, 0x1230, "Wooting Two HE (ARM)", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1300, "Wooting 60HE (AVR)", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1310, "Wooting 60HE (ARM)", 0, XTYPE_XBOX360 }, { 0x3285, 0x0607, "Nacon GC-100", 0, XTYPE_XBOX360 }, + { 0x3285, 0x0646, "Nacon Pro Compact", 0, XTYPE_XBOXONE }, + { 0x3285, 0x0663, "Nacon Evol-X", 0, XTYPE_XBOXONE }, { 0x3537, 0x1004, "GameSir T4 Kaleid", 0, XTYPE_XBOX360 }, { 0x3767, 0x0101, "Fanatec Speedster 3 Forceshock Wheel", 0, XTYPE_XBOX }, { 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX }, @@ -514,6 +519,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */ XPAD_XBOX360_VENDOR(0x17ef), /* Lenovo */ XPAD_XBOX360_VENDOR(0x1949), /* Amazon controllers */ + XPAD_XBOX360_VENDOR(0x1a86), /* QH Electronics */ XPAD_XBOX360_VENDOR(0x1bad), /* Harmonix Rock Band guitar and drums */ XPAD_XBOX360_VENDOR(0x20d6), /* PowerA controllers */ XPAD_XBOXONE_VENDOR(0x20d6), /* PowerA controllers */ @@ -530,6 +536,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x2f24), /* GameSir controllers */ XPAD_XBOX360_VENDOR(0x31e3), /* Wooting Keyboards */ XPAD_XBOX360_VENDOR(0x3285), /* Nacon GC-100 */ + XPAD_XBOXONE_VENDOR(0x3285), /* Nacon Evol-X */ XPAD_XBOX360_VENDOR(0x3537), /* GameSir Controllers */ XPAD_XBOXONE_VENDOR(0x3537), /* GameSir Controllers */ { } diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index ec94fcfa4cde..adf0f311996c 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -89,7 +89,7 @@ static const unsigned short atkbd_set2_keycode[ATKBD_KEYMAP_SIZE] = { 0, 46, 45, 32, 18, 5, 4, 95, 0, 57, 47, 33, 20, 19, 6,183, 0, 49, 48, 35, 34, 21, 7,184, 0, 0, 50, 36, 22, 8, 9,185, 0, 51, 37, 23, 24, 11, 10, 0, 0, 52, 53, 38, 39, 25, 12, 0, - 0, 89, 40, 0, 26, 13, 0, 0, 58, 54, 28, 27, 0, 43, 0, 85, + 0, 89, 40, 0, 26, 13, 0,193, 58, 54, 28, 27, 0, 43, 0, 85, 0, 86, 91, 90, 92, 0, 14, 94, 0, 79,124, 75, 71,121, 0, 0, 82, 83, 80, 76, 77, 72, 1, 69, 87, 78, 81, 74, 55, 73, 70, 99, diff --git a/drivers/input/keyboard/dlink-dir685-touchkeys.c b/drivers/input/keyboard/dlink-dir685-touchkeys.c index 993cdbda509e..4184dd2eaeeb 100644 --- a/drivers/input/keyboard/dlink-dir685-touchkeys.c +++ b/drivers/input/keyboard/dlink-dir685-touchkeys.c @@ -14,6 +14,7 @@ #include #include #include +#include #include struct dir685_touchkeys { @@ -48,7 +49,7 @@ static irqreturn_t dir685_tk_irq_thread(int irq, void *data) changed = tk->cur_key ^ key; for_each_set_bit(i, &changed, num_bits) { dev_dbg(tk->dev, "key %d is %s\n", i, - test_bit(i, &key) ? "down" : "up"); + str_down_up(test_bit(i, &key))); input_report_key(tk->input, tk->codes[i], test_bit(i, &key)); } diff --git a/drivers/input/keyboard/lm8323.c b/drivers/input/keyboard/lm8323.c index e26bf2956344..e19442c6f80f 100644 --- a/drivers/input/keyboard/lm8323.c +++ b/drivers/input/keyboard/lm8323.c @@ -21,6 +21,7 @@ #include #include #include +#include /* Commands to send to the chip. */ #define LM8323_CMD_READ_ID 0x80 /* Read chip ID. */ @@ -269,7 +270,7 @@ static void process_keys(struct lm8323_chip *lm) unsigned short keycode = lm->keymap[key]; dev_vdbg(&lm->client->dev, "key 0x%02x %s\n", - key, isdown ? "down" : "up"); + key, str_down_up(isdown)); if (lm->kp_enabled) { input_event(lm->idev, EV_MSC, MSC_SCAN, key); diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig index 6a852c76331b..13d135257e06 100644 --- a/drivers/input/misc/Kconfig +++ b/drivers/input/misc/Kconfig @@ -917,6 +917,18 @@ config INPUT_HISI_POWERKEY To compile this driver as a module, choose M here: the module will be called hisi_powerkey. +config INPUT_QNAP_MCU + tristate "Input Support for QNAP MCU controllers" + depends on MFD_QNAP_MCU + help + This option enables support for input elements available on + embedded controllers used in QNAP NAS devices. + + This includes a polled power-button as well as a beeper. + + To compile this driver as a module, choose M here: the + module will be called qnap-mcu-input. + config INPUT_RAVE_SP_PWRBUTTON tristate "RAVE SP Power button Driver" depends on RAVE_SP_CORE diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile index 4f7f736831ba..6d91804d0a6f 100644 --- a/drivers/input/misc/Makefile +++ b/drivers/input/misc/Makefile @@ -68,6 +68,7 @@ obj-$(CONFIG_INPUT_PMIC8XXX_PWRKEY) += pmic8xxx-pwrkey.o obj-$(CONFIG_INPUT_POWERMATE) += powermate.o obj-$(CONFIG_INPUT_PWM_BEEPER) += pwm-beeper.o obj-$(CONFIG_INPUT_PWM_VIBRA) += pwm-vibra.o +obj-$(CONFIG_INPUT_QNAP_MCU) += qnap-mcu-input.o obj-$(CONFIG_INPUT_RAVE_SP_PWRBUTTON) += rave-sp-pwrbutton.o obj-$(CONFIG_INPUT_RB532_BUTTON) += rb532_button.o obj-$(CONFIG_INPUT_REGULATOR_HAPTIC) += regulator-haptic.o diff --git a/drivers/input/misc/ideapad_slidebar.c b/drivers/input/misc/ideapad_slidebar.c index f6e5fc807b4d..ab2e0a401904 100644 --- a/drivers/input/misc/ideapad_slidebar.c +++ b/drivers/input/misc/ideapad_slidebar.c @@ -121,7 +121,7 @@ static void slidebar_mode_set(u8 mode) } static bool slidebar_i8042_filter(unsigned char data, unsigned char str, - struct serio *port) + struct serio *port, void *context) { static bool extended = false; @@ -219,7 +219,7 @@ static int __init ideapad_probe(struct platform_device* pdev) input_set_capability(slidebar_input_dev, EV_ABS, ABS_X); input_set_abs_params(slidebar_input_dev, ABS_X, 0, 0xff, 0, 0); - err = i8042_install_filter(slidebar_i8042_filter); + err = i8042_install_filter(slidebar_i8042_filter, NULL); if (err) { dev_err(&pdev->dev, "Failed to install i8042 filter: %d\n", err); diff --git a/drivers/input/misc/max77693-haptic.c b/drivers/input/misc/max77693-haptic.c index 0e646f1b257b..cdb9be737e48 100644 --- a/drivers/input/misc/max77693-haptic.c +++ b/drivers/input/misc/max77693-haptic.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -94,7 +95,7 @@ static int max77843_haptic_bias(struct max77693_haptic *haptic, bool on) on << MAINCTRL1_BIASEN_SHIFT); if (error) { dev_err(haptic->dev, "failed to %s bias: %d\n", - on ? "enable" : "disable", error); + str_enable_disable(on), error); return error; } diff --git a/drivers/input/misc/mma8450.c b/drivers/input/misc/mma8450.c index 08412239b8e6..0c661140fb88 100644 --- a/drivers/input/misc/mma8450.c +++ b/drivers/input/misc/mma8450.c @@ -38,6 +38,8 @@ #define MMA8450_CTRL_REG1 0x38 #define MMA8450_CTRL_REG2 0x39 +#define MMA8450_ID 0xc6 +#define MMA8450_WHO_AM_I 0x0f static int mma8450_read(struct i2c_client *c, unsigned int off) { @@ -148,8 +150,20 @@ static void mma8450_close(struct input_dev *input) */ static int mma8450_probe(struct i2c_client *c) { + struct i2c_adapter *adapter = c->adapter; struct input_dev *input; - int err; + int err, client_id; + + if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE | + I2C_FUNC_SMBUS_BYTE_DATA)) + return dev_err_probe(&c->dev, -EINVAL, + "I2C adapter doesn't support SMBUS BYTE"); + + client_id = i2c_smbus_read_byte_data(c, MMA8450_WHO_AM_I); + if (client_id != MMA8450_ID) + return dev_err_probe(&c->dev, -EINVAL, + "unexpected chip ID 0x%x (vs 0x%x)\n", + client_id, MMA8450_ID); input = devm_input_allocate_device(&c->dev); if (!input) diff --git a/drivers/input/misc/nxp-bbnsm-pwrkey.c b/drivers/input/misc/nxp-bbnsm-pwrkey.c index eb4173f9c820..7ba8d166d68c 100644 --- a/drivers/input/misc/nxp-bbnsm-pwrkey.c +++ b/drivers/input/misc/nxp-bbnsm-pwrkey.c @@ -187,6 +187,12 @@ static int bbnsm_pwrkey_probe(struct platform_device *pdev) return 0; } +static void bbnsm_pwrkey_remove(struct platform_device *pdev) +{ + dev_pm_clear_wake_irq(&pdev->dev); + device_init_wakeup(&pdev->dev, false); +} + static int __maybe_unused bbnsm_pwrkey_suspend(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); @@ -223,6 +229,8 @@ static struct platform_driver bbnsm_pwrkey_driver = { .of_match_table = bbnsm_pwrkey_ids, }, .probe = bbnsm_pwrkey_probe, + .remove = bbnsm_pwrkey_remove, + }; module_platform_driver(bbnsm_pwrkey_driver); diff --git a/drivers/input/misc/qnap-mcu-input.c b/drivers/input/misc/qnap-mcu-input.c new file mode 100644 index 000000000000..76e62f0816c1 --- /dev/null +++ b/drivers/input/misc/qnap-mcu-input.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Driver for input events on QNAP-MCUs + * + * Copyright (C) 2024 Heiko Stuebner + */ + +#include +#include +#include +#include +#include +#include + +/* + * The power-key needs to be pressed for a while to create an event, + * so there is no use for overly frequent polling. + */ +#define POLL_INTERVAL 500 + +struct qnap_mcu_input_dev { + struct input_dev *input; + struct qnap_mcu *mcu; + struct device *dev; + + struct work_struct beep_work; + int beep_type; +}; + +static void qnap_mcu_input_poll(struct input_dev *input) +{ + struct qnap_mcu_input_dev *idev = input_get_drvdata(input); + static const u8 cmd[] = { '@', 'C', 'V' }; + u8 reply[4]; + int state, ret; + + /* poll the power button */ + ret = qnap_mcu_exec(idev->mcu, cmd, sizeof(cmd), reply, sizeof(reply)); + if (ret) + return; + + /* First bytes must mirror the sent command */ + if (memcmp(cmd, reply, sizeof(cmd))) { + dev_err(idev->dev, "malformed data received\n"); + return; + } + + state = reply[3] - 0x30; + input_event(input, EV_KEY, KEY_POWER, state); + input_sync(input); +} + +static void qnap_mcu_input_beeper_work(struct work_struct *work) +{ + struct qnap_mcu_input_dev *idev = + container_of(work, struct qnap_mcu_input_dev, beep_work); + const u8 cmd[] = { '@', 'C', (idev->beep_type == SND_TONE) ? '3' : '2' }; + + qnap_mcu_exec_with_ack(idev->mcu, cmd, sizeof(cmd)); +} + +static int qnap_mcu_input_event(struct input_dev *input, unsigned int type, + unsigned int code, int value) +{ + struct qnap_mcu_input_dev *idev = input_get_drvdata(input); + + if (type != EV_SND || (code != SND_BELL && code != SND_TONE)) + return -EOPNOTSUPP; + + if (value < 0) + return -EINVAL; + + /* beep runtime is determined by the MCU */ + if (value == 0) + return 0; + + /* Schedule work to actually turn the beeper on */ + idev->beep_type = code; + schedule_work(&idev->beep_work); + + return 0; +} + +static void qnap_mcu_input_close(struct input_dev *input) +{ + struct qnap_mcu_input_dev *idev = input_get_drvdata(input); + + cancel_work_sync(&idev->beep_work); +} + +static int qnap_mcu_input_probe(struct platform_device *pdev) +{ + struct qnap_mcu *mcu = dev_get_drvdata(pdev->dev.parent); + struct qnap_mcu_input_dev *idev; + struct device *dev = &pdev->dev; + struct input_dev *input; + int ret; + + idev = devm_kzalloc(dev, sizeof(*idev), GFP_KERNEL); + if (!idev) + return -ENOMEM; + + input = devm_input_allocate_device(dev); + if (!input) + return dev_err_probe(dev, -ENOMEM, "no memory for input device\n"); + + idev->input = input; + idev->dev = dev; + idev->mcu = mcu; + + input_set_drvdata(input, idev); + + input->name = "qnap-mcu"; + input->phys = "qnap-mcu-input/input0"; + input->id.bustype = BUS_HOST; + input->id.vendor = 0x0001; + input->id.product = 0x0001; + input->id.version = 0x0100; + input->event = qnap_mcu_input_event; + input->close = qnap_mcu_input_close; + + input_set_capability(input, EV_KEY, KEY_POWER); + input_set_capability(input, EV_SND, SND_BELL); + input_set_capability(input, EV_SND, SND_TONE); + + INIT_WORK(&idev->beep_work, qnap_mcu_input_beeper_work); + + ret = input_setup_polling(input, qnap_mcu_input_poll); + if (ret) + return dev_err_probe(dev, ret, "unable to set up polling\n"); + + input_set_poll_interval(input, POLL_INTERVAL); + + ret = input_register_device(input); + if (ret) + return dev_err_probe(dev, ret, "unable to register input device\n"); + + return 0; +} + +static struct platform_driver qnap_mcu_input_driver = { + .probe = qnap_mcu_input_probe, + .driver = { + .name = "qnap-mcu-input", + }, +}; +module_platform_driver(qnap_mcu_input_driver); + +MODULE_ALIAS("platform:qnap-mcu-input"); +MODULE_AUTHOR("Heiko Stuebner "); +MODULE_DESCRIPTION("QNAP MCU input driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/input/misc/regulator-haptic.c b/drivers/input/misc/regulator-haptic.c index 3666ba6d1f30..9711f5c7c78a 100644 --- a/drivers/input/misc/regulator-haptic.c +++ b/drivers/input/misc/regulator-haptic.c @@ -14,6 +14,7 @@ #include #include #include +#include #define MAX_MAGNITUDE_SHIFT 16 @@ -44,7 +45,7 @@ static int regulator_haptic_toggle(struct regulator_haptic *haptic, bool on) if (error) { dev_err(haptic->dev, "failed to switch regulator %s: %d\n", - on ? "on" : "off", error); + str_on_off(on), error); return error; } diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index a841883660fb..fee1796da3d0 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -199,7 +200,7 @@ static int elan_set_power(struct elan_tp_data *data, bool on) } while (--repeat > 0); dev_err(&data->client->dev, "failed to set power %s: %d\n", - on ? "on" : "off", error); + str_on_off(on), error); return error; } diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 2735f86c23cc..aba57abe6978 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -665,23 +665,50 @@ static void synaptics_pt_stop(struct serio *serio) priv->pt_port = NULL; } +static int synaptics_pt_open(struct serio *serio) +{ + struct psmouse *parent = psmouse_from_serio(serio->parent); + struct synaptics_data *priv = parent->private; + + guard(serio_pause_rx)(parent->ps2dev.serio); + priv->pt_port_open = true; + + return 0; +} + +static void synaptics_pt_close(struct serio *serio) +{ + struct psmouse *parent = psmouse_from_serio(serio->parent); + struct synaptics_data *priv = parent->private; + + guard(serio_pause_rx)(parent->ps2dev.serio); + priv->pt_port_open = false; +} + static int synaptics_is_pt_packet(u8 *buf) { return (buf[0] & 0xFC) == 0x84 && (buf[3] & 0xCC) == 0xC4; } -static void synaptics_pass_pt_packet(struct serio *ptport, u8 *packet) +static void synaptics_pass_pt_packet(struct synaptics_data *priv, u8 *packet) { - struct psmouse *child = psmouse_from_serio(ptport); + struct serio *ptport; - if (child && child->state == PSMOUSE_ACTIVATED) { - serio_interrupt(ptport, packet[1], 0); - serio_interrupt(ptport, packet[4], 0); - serio_interrupt(ptport, packet[5], 0); - if (child->pktsize == 4) - serio_interrupt(ptport, packet[2], 0); - } else { - serio_interrupt(ptport, packet[1], 0); + ptport = priv->pt_port; + if (!ptport) + return; + + serio_interrupt(ptport, packet[1], 0); + + if (priv->pt_port_open) { + struct psmouse *child = psmouse_from_serio(ptport); + + if (child->state == PSMOUSE_ACTIVATED) { + serio_interrupt(ptport, packet[4], 0); + serio_interrupt(ptport, packet[5], 0); + if (child->pktsize == 4) + serio_interrupt(ptport, packet[2], 0); + } } } @@ -720,6 +747,8 @@ static void synaptics_pt_create(struct psmouse *psmouse) serio->write = synaptics_pt_write; serio->start = synaptics_pt_start; serio->stop = synaptics_pt_stop; + serio->open = synaptics_pt_open; + serio->close = synaptics_pt_close; serio->parent = psmouse->ps2dev.serio; psmouse->pt_activate = synaptics_pt_activate; @@ -1216,11 +1245,10 @@ static psmouse_ret_t synaptics_process_byte(struct psmouse *psmouse) if (SYN_CAP_PASS_THROUGH(priv->info.capabilities) && synaptics_is_pt_packet(psmouse->packet)) { - if (priv->pt_port) - synaptics_pass_pt_packet(priv->pt_port, - psmouse->packet); - } else + synaptics_pass_pt_packet(priv, psmouse->packet); + } else { synaptics_process_packet(psmouse); + } return PSMOUSE_FULL_PACKET; } diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h index 899aee598632..3853165b6b3a 100644 --- a/drivers/input/mouse/synaptics.h +++ b/drivers/input/mouse/synaptics.h @@ -188,6 +188,7 @@ struct synaptics_data { bool disable_gesture; /* disable gestures */ struct serio *pt_port; /* Pass-through serio port */ + bool pt_port_open; /* * Last received Advanced Gesture Mode (AGM) packet. An AGM packet diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 509330a27880..cab5a4c5baf5 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -179,8 +179,8 @@ static struct platform_device *i8042_platform_device; static struct notifier_block i8042_kbd_bind_notifier_block; static bool i8042_handle_data(int irq); -static bool (*i8042_platform_filter)(unsigned char data, unsigned char str, - struct serio *serio); +static i8042_filter_t i8042_platform_filter; +static void *i8042_platform_filter_context; void i8042_lock_chip(void) { @@ -194,8 +194,7 @@ void i8042_unlock_chip(void) } EXPORT_SYMBOL(i8042_unlock_chip); -int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *serio)) +int i8042_install_filter(i8042_filter_t filter, void *context) { guard(spinlock_irqsave)(&i8042_lock); @@ -203,12 +202,12 @@ int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, return -EBUSY; i8042_platform_filter = filter; + i8042_platform_filter_context = context; return 0; } EXPORT_SYMBOL(i8042_install_filter); -int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *port)) +int i8042_remove_filter(i8042_filter_t filter) { guard(spinlock_irqsave)(&i8042_lock); @@ -216,6 +215,7 @@ int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, return -EINVAL; i8042_platform_filter = NULL; + i8042_platform_filter_context = NULL; return 0; } EXPORT_SYMBOL(i8042_remove_filter); @@ -480,7 +480,10 @@ static bool i8042_filter(unsigned char data, unsigned char str, } } - if (i8042_platform_filter && i8042_platform_filter(data, str, serio)) { + if (!i8042_platform_filter) + return false; + + if (i8042_platform_filter(data, str, serio, i8042_platform_filter_context)) { dbg("Filtered out by platform filter\n"); return true; } diff --git a/drivers/input/touchscreen/egalax_ts.c b/drivers/input/touchscreen/egalax_ts.c index f4e950920e84..eb3cc2befcdf 100644 --- a/drivers/input/touchscreen/egalax_ts.c +++ b/drivers/input/touchscreen/egalax_ts.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -102,7 +103,7 @@ static irqreturn_t egalax_ts_interrupt(int irq, void *dev_id) input_mt_report_slot_state(input_dev, MT_TOOL_FINGER, down); dev_dbg(&client->dev, "%s id:%d x:%d y:%d z:%d", - down ? "down" : "up", id, x, y, z); + str_down_up(down), id, x, y, z); if (down) { input_report_abs(input_dev, ABS_MT_POSITION_X, x); diff --git a/drivers/interconnect/icc-clk.c b/drivers/interconnect/icc-clk.c index b956e4050f38..88f311c11020 100644 --- a/drivers/interconnect/icc-clk.c +++ b/drivers/interconnect/icc-clk.c @@ -116,6 +116,11 @@ struct icc_provider *icc_clk_register(struct device *dev, } node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_master", data[i].name); + if (!node->name) { + ret = -ENOMEM; + goto err; + } + node->data = &qp->clocks[i]; icc_node_add(node, provider); /* link to the next node, slave */ @@ -129,6 +134,11 @@ struct icc_provider *icc_clk_register(struct device *dev, } node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_slave", data[i].name); + if (!node->name) { + ret = -ENOMEM; + goto err; + } + /* no data for slave node */ icc_node_add(node, provider); onecell->nodes[j++] = node; diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig index 362fb9b0a198..1219f4f23d40 100644 --- a/drivers/interconnect/qcom/Kconfig +++ b/drivers/interconnect/qcom/Kconfig @@ -337,6 +337,15 @@ config INTERCONNECT_QCOM_SM8650 This is a driver for the Qualcomm Network-on-Chip on SM8650-based platforms. +config INTERCONNECT_QCOM_SM8750 + tristate "Qualcomm SM8750 interconnect driver" + depends on INTERCONNECT_QCOM_RPMH_POSSIBLE + select INTERCONNECT_QCOM_RPMH + select INTERCONNECT_QCOM_BCM_VOTER + help + This is a driver for the Qualcomm Network-on-Chip on SM8750-based + platforms. + config INTERCONNECT_QCOM_X1E80100 tristate "Qualcomm X1E80100 interconnect driver" depends on INTERCONNECT_QCOM_RPMH_POSSIBLE diff --git a/drivers/interconnect/qcom/Makefile b/drivers/interconnect/qcom/Makefile index 9997728c02bf..7887b1e8d69b 100644 --- a/drivers/interconnect/qcom/Makefile +++ b/drivers/interconnect/qcom/Makefile @@ -40,6 +40,7 @@ qnoc-sm8350-objs := sm8350.o qnoc-sm8450-objs := sm8450.o qnoc-sm8550-objs := sm8550.o qnoc-sm8650-objs := sm8650.o +qnoc-sm8750-objs := sm8750.o qnoc-x1e80100-objs := x1e80100.o icc-smd-rpm-objs := smd-rpm.o icc-rpm.o icc-rpm-clocks.o @@ -80,5 +81,6 @@ obj-$(CONFIG_INTERCONNECT_QCOM_SM8350) += qnoc-sm8350.o obj-$(CONFIG_INTERCONNECT_QCOM_SM8450) += qnoc-sm8450.o obj-$(CONFIG_INTERCONNECT_QCOM_SM8550) += qnoc-sm8550.o obj-$(CONFIG_INTERCONNECT_QCOM_SM8650) += qnoc-sm8650.o +obj-$(CONFIG_INTERCONNECT_QCOM_SM8750) += qnoc-sm8750.o obj-$(CONFIG_INTERCONNECT_QCOM_X1E80100) += qnoc-x1e80100.o obj-$(CONFIG_INTERCONNECT_QCOM_SMD_RPM) += icc-smd-rpm.o diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c index a8ed435f696c..ea1042d38128 100644 --- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -503,6 +503,7 @@ int qnoc_probe(struct platform_device *pdev) GFP_KERNEL); if (!data) return -ENOMEM; + data->num_nodes = num_nodes; qp->num_intf_clks = cd_num; for (i = 0; i < cd_num; i++) @@ -597,7 +598,6 @@ regmap_done: data->nodes[i] = node; } - data->num_nodes = num_nodes; clk_bulk_disable_unprepare(qp->num_intf_clks, qp->intf_clks); diff --git a/drivers/interconnect/qcom/sm8750.c b/drivers/interconnect/qcom/sm8750.c new file mode 100644 index 000000000000..69bc22222075 --- /dev/null +++ b/drivers/interconnect/qcom/sm8750.c @@ -0,0 +1,1705 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include + +#include "bcm-voter.h" +#include "icc-rpmh.h" + +#define SM8750_MASTER_GPU_TCU 0 +#define SM8750_MASTER_SYS_TCU 1 +#define SM8750_MASTER_APPSS_PROC 2 +#define SM8750_MASTER_LLCC 3 +#define SM8750_MASTER_QDSS_BAM 4 +#define SM8750_MASTER_QSPI_0 5 +#define SM8750_MASTER_QUP_1 6 +#define SM8750_MASTER_QUP_2 7 +#define SM8750_MASTER_A1NOC_SNOC 8 +#define SM8750_MASTER_A2NOC_SNOC 9 +#define SM8750_MASTER_CAMNOC_HF 10 +#define SM8750_MASTER_CAMNOC_NRT_ICP_SF 11 +#define SM8750_MASTER_CAMNOC_RT_CDM_SF 12 +#define SM8750_MASTER_CAMNOC_SF 13 +#define SM8750_MASTER_GEM_NOC_CNOC 14 +#define SM8750_MASTER_GEM_NOC_PCIE_SNOC 15 +#define SM8750_MASTER_GFX3D 16 +#define SM8750_MASTER_LPASS_GEM_NOC 17 +#define SM8750_MASTER_LPASS_LPINOC 18 +#define SM8750_MASTER_LPIAON_NOC 19 +#define SM8750_MASTER_LPASS_PROC 20 +#define SM8750_MASTER_MDP 21 +#define SM8750_MASTER_MSS_PROC 22 +#define SM8750_MASTER_MNOC_HF_MEM_NOC 23 +#define SM8750_MASTER_MNOC_SF_MEM_NOC 24 +#define SM8750_MASTER_CDSP_PROC 25 +#define SM8750_MASTER_COMPUTE_NOC 26 +#define SM8750_MASTER_ANOC_PCIE_GEM_NOC 27 +#define SM8750_MASTER_SNOC_SF_MEM_NOC 28 +#define SM8750_MASTER_UBWC_P 29 +#define SM8750_MASTER_CDSP_HCP 30 +#define SM8750_MASTER_VIDEO_CV_PROC 31 +#define SM8750_MASTER_VIDEO_EVA 32 +#define SM8750_MASTER_VIDEO_MVP 33 +#define SM8750_MASTER_VIDEO_V_PROC 34 +#define SM8750_MASTER_CNOC_CFG 35 +#define SM8750_MASTER_CNOC_MNOC_CFG 36 +#define SM8750_MASTER_PCIE_ANOC_CFG 37 +#define SM8750_MASTER_QUP_CORE_0 38 +#define SM8750_MASTER_QUP_CORE_1 39 +#define SM8750_MASTER_QUP_CORE_2 40 +#define SM8750_MASTER_CRYPTO 41 +#define SM8750_MASTER_IPA 42 +#define SM8750_MASTER_QUP_3 43 +#define SM8750_MASTER_SOCCP_AGGR_NOC 44 +#define SM8750_MASTER_SP 45 +#define SM8750_MASTER_GIC 46 +#define SM8750_MASTER_PCIE_0 47 +#define SM8750_MASTER_QDSS_ETR 48 +#define SM8750_MASTER_QDSS_ETR_1 49 +#define SM8750_MASTER_SDCC_2 50 +#define SM8750_MASTER_SDCC_4 51 +#define SM8750_MASTER_UFS_MEM 52 +#define SM8750_MASTER_USB3_0 53 +#define SM8750_SLAVE_UBWC_P 54 +#define SM8750_SLAVE_EBI1 55 +#define SM8750_SLAVE_AHB2PHY_SOUTH 56 +#define SM8750_SLAVE_AHB2PHY_NORTH 57 +#define SM8750_SLAVE_AOSS 58 +#define SM8750_SLAVE_CAMERA_CFG 59 +#define SM8750_SLAVE_CLK_CTL 60 +#define SM8750_SLAVE_CRYPTO_0_CFG 61 +#define SM8750_SLAVE_DISPLAY_CFG 62 +#define SM8750_SLAVE_EVA_CFG 63 +#define SM8750_SLAVE_GFX3D_CFG 64 +#define SM8750_SLAVE_I2C 65 +#define SM8750_SLAVE_I3C_IBI0_CFG 66 +#define SM8750_SLAVE_I3C_IBI1_CFG 67 +#define SM8750_SLAVE_IMEM_CFG 68 +#define SM8750_SLAVE_IPA_CFG 69 +#define SM8750_SLAVE_IPC_ROUTER_CFG 70 +#define SM8750_SLAVE_CNOC_MSS 71 +#define SM8750_SLAVE_PCIE_CFG 72 +#define SM8750_SLAVE_PRNG 73 +#define SM8750_SLAVE_QDSS_CFG 74 +#define SM8750_SLAVE_QSPI_0 75 +#define SM8750_SLAVE_QUP_3 76 +#define SM8750_SLAVE_QUP_1 77 +#define SM8750_SLAVE_QUP_2 78 +#define SM8750_SLAVE_SDCC_2 79 +#define SM8750_SLAVE_SDCC_4 80 +#define SM8750_SLAVE_SOCCP 81 +#define SM8750_SLAVE_SPSS_CFG 82 +#define SM8750_SLAVE_TCSR 83 +#define SM8750_SLAVE_TLMM 84 +#define SM8750_SLAVE_TME_CFG 85 +#define SM8750_SLAVE_UFS_MEM_CFG 86 +#define SM8750_SLAVE_USB3_0 87 +#define SM8750_SLAVE_VENUS_CFG 88 +#define SM8750_SLAVE_VSENSE_CTRL_CFG 89 +#define SM8750_SLAVE_A1NOC_SNOC 90 +#define SM8750_SLAVE_A2NOC_SNOC 91 +#define SM8750_SLAVE_APPSS 92 +#define SM8750_SLAVE_GEM_NOC_CNOC 93 +#define SM8750_SLAVE_SNOC_GEM_NOC_SF 94 +#define SM8750_SLAVE_LLCC 95 +#define SM8750_SLAVE_LPASS_GEM_NOC 96 +#define SM8750_SLAVE_LPIAON_NOC_LPASS_AG_NOC 97 +#define SM8750_SLAVE_LPICX_NOC_LPIAON_NOC 98 +#define SM8750_SLAVE_MNOC_HF_MEM_NOC 99 +#define SM8750_SLAVE_MNOC_SF_MEM_NOC 100 +#define SM8750_SLAVE_CDSP_MEM_NOC 101 +#define SM8750_SLAVE_MEM_NOC_PCIE_SNOC 102 +#define SM8750_SLAVE_ANOC_PCIE_GEM_NOC 103 +#define SM8750_SLAVE_CNOC_CFG 104 +#define SM8750_SLAVE_DDRSS_CFG 105 +#define SM8750_SLAVE_CNOC_MNOC_CFG 106 +#define SM8750_SLAVE_PCIE_ANOC_CFG 107 +#define SM8750_SLAVE_QUP_CORE_0 108 +#define SM8750_SLAVE_QUP_CORE_1 109 +#define SM8750_SLAVE_QUP_CORE_2 110 +#define SM8750_SLAVE_BOOT_IMEM 111 +#define SM8750_SLAVE_IMEM 112 +#define SM8750_SLAVE_BOOT_IMEM_2 113 +#define SM8750_SLAVE_SERVICE_CNOC 114 +#define SM8750_SLAVE_SERVICE_MNOC 115 +#define SM8750_SLAVE_SERVICE_PCIE_ANOC 116 +#define SM8750_SLAVE_PCIE_0 117 +#define SM8750_SLAVE_QDSS_STM 118 +#define SM8750_SLAVE_TCU 119 + +static struct qcom_icc_node qhm_qspi = { + .name = "qhm_qspi", + .id = SM8750_MASTER_QSPI_0, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_A1NOC_SNOC }, +}; + +static struct qcom_icc_node qhm_qup1 = { + .name = "qhm_qup1", + .id = SM8750_MASTER_QUP_1, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_A1NOC_SNOC }, +}; + +static struct qcom_icc_node qxm_qup02 = { + .name = "qxm_qup02", + .id = SM8750_MASTER_QUP_3, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A1NOC_SNOC }, +}; + +static struct qcom_icc_node xm_sdc4 = { + .name = "xm_sdc4", + .id = SM8750_MASTER_SDCC_4, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A1NOC_SNOC }, +}; + +static struct qcom_icc_node xm_ufs_mem = { + .name = "xm_ufs_mem", + .id = SM8750_MASTER_UFS_MEM, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_SLAVE_A1NOC_SNOC }, +}; + +static struct qcom_icc_node xm_usb3_0 = { + .name = "xm_usb3_0", + .id = SM8750_MASTER_USB3_0, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A1NOC_SNOC }, +}; + +static struct qcom_icc_node qhm_qdss_bam = { + .name = "qhm_qdss_bam", + .id = SM8750_MASTER_QDSS_BAM, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_A2NOC_SNOC }, +}; + +static struct qcom_icc_node qhm_qup2 = { + .name = "qhm_qup2", + .id = SM8750_MASTER_QUP_2, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_A2NOC_SNOC }, +}; + +static struct qcom_icc_node qxm_crypto = { + .name = "qxm_crypto", + .id = SM8750_MASTER_CRYPTO, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A2NOC_SNOC }, +}; + +static struct qcom_icc_node qxm_ipa = { + .name = "qxm_ipa", + .id = SM8750_MASTER_IPA, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A2NOC_SNOC }, +}; + +static struct qcom_icc_node qxm_soccp = { + .name = "qxm_soccp", + .id = SM8750_MASTER_SOCCP_AGGR_NOC, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A2NOC_SNOC }, +}; + +static struct qcom_icc_node qxm_sp = { + .name = "qxm_sp", + .id = SM8750_MASTER_SP, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A2NOC_SNOC }, +}; + +static struct qcom_icc_node xm_qdss_etr_0 = { + .name = "xm_qdss_etr_0", + .id = SM8750_MASTER_QDSS_ETR, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A2NOC_SNOC }, +}; + +static struct qcom_icc_node xm_qdss_etr_1 = { + .name = "xm_qdss_etr_1", + .id = SM8750_MASTER_QDSS_ETR_1, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A2NOC_SNOC }, +}; + +static struct qcom_icc_node xm_sdc2 = { + .name = "xm_sdc2", + .id = SM8750_MASTER_SDCC_2, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_A2NOC_SNOC }, +}; + +static struct qcom_icc_node qup0_core_master = { + .name = "qup0_core_master", + .id = SM8750_MASTER_QUP_CORE_0, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_QUP_CORE_0 }, +}; + +static struct qcom_icc_node qup1_core_master = { + .name = "qup1_core_master", + .id = SM8750_MASTER_QUP_CORE_1, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_QUP_CORE_1 }, +}; + +static struct qcom_icc_node qup2_core_master = { + .name = "qup2_core_master", + .id = SM8750_MASTER_QUP_CORE_2, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_QUP_CORE_2 }, +}; + +static struct qcom_icc_node qsm_cfg = { + .name = "qsm_cfg", + .id = SM8750_MASTER_CNOC_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 33, + .links = { SM8750_SLAVE_AHB2PHY_SOUTH, SM8750_SLAVE_AHB2PHY_NORTH, + SM8750_SLAVE_CAMERA_CFG, SM8750_SLAVE_CLK_CTL, + SM8750_SLAVE_CRYPTO_0_CFG, SM8750_SLAVE_DISPLAY_CFG, + SM8750_SLAVE_EVA_CFG, SM8750_SLAVE_GFX3D_CFG, + SM8750_SLAVE_I2C, SM8750_SLAVE_I3C_IBI0_CFG, + SM8750_SLAVE_I3C_IBI1_CFG, SM8750_SLAVE_IMEM_CFG, + SM8750_SLAVE_CNOC_MSS, SM8750_SLAVE_PCIE_CFG, + SM8750_SLAVE_PRNG, SM8750_SLAVE_QDSS_CFG, + SM8750_SLAVE_QSPI_0, SM8750_SLAVE_QUP_3, + SM8750_SLAVE_QUP_1, SM8750_SLAVE_QUP_2, + SM8750_SLAVE_SDCC_2, SM8750_SLAVE_SDCC_4, + SM8750_SLAVE_SPSS_CFG, SM8750_SLAVE_TCSR, + SM8750_SLAVE_TLMM, SM8750_SLAVE_UFS_MEM_CFG, + SM8750_SLAVE_USB3_0, SM8750_SLAVE_VENUS_CFG, + SM8750_SLAVE_VSENSE_CTRL_CFG, SM8750_SLAVE_CNOC_MNOC_CFG, + SM8750_SLAVE_PCIE_ANOC_CFG, SM8750_SLAVE_QDSS_STM, + SM8750_SLAVE_TCU }, +}; + +static struct qcom_icc_node qnm_gemnoc_cnoc = { + .name = "qnm_gemnoc_cnoc", + .id = SM8750_MASTER_GEM_NOC_CNOC, + .channels = 1, + .buswidth = 16, + .num_links = 12, + .links = { SM8750_SLAVE_AOSS, SM8750_SLAVE_IPA_CFG, + SM8750_SLAVE_IPC_ROUTER_CFG, SM8750_SLAVE_SOCCP, + SM8750_SLAVE_TME_CFG, SM8750_SLAVE_APPSS, + SM8750_SLAVE_CNOC_CFG, SM8750_SLAVE_DDRSS_CFG, + SM8750_SLAVE_BOOT_IMEM, SM8750_SLAVE_IMEM, + SM8750_SLAVE_BOOT_IMEM_2, SM8750_SLAVE_SERVICE_CNOC }, +}; + +static struct qcom_icc_node qnm_gemnoc_pcie = { + .name = "qnm_gemnoc_pcie", + .id = SM8750_MASTER_GEM_NOC_PCIE_SNOC, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_PCIE_0 }, +}; + +static struct qcom_icc_node alm_gpu_tcu = { + .name = "alm_gpu_tcu", + .id = SM8750_MASTER_GPU_TCU, + .channels = 1, + .buswidth = 8, + .num_links = 2, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC }, +}; + +static struct qcom_icc_node alm_sys_tcu = { + .name = "alm_sys_tcu", + .id = SM8750_MASTER_SYS_TCU, + .channels = 1, + .buswidth = 8, + .num_links = 2, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC }, +}; + +static struct qcom_icc_node chm_apps = { + .name = "chm_apps", + .id = SM8750_MASTER_APPSS_PROC, + .channels = 4, + .buswidth = 32, + .num_links = 4, + .links = { SM8750_SLAVE_UBWC_P, SM8750_SLAVE_GEM_NOC_CNOC, + SM8750_SLAVE_LLCC, SM8750_SLAVE_MEM_NOC_PCIE_SNOC }, +}; + +static struct qcom_icc_node qnm_gpu = { + .name = "qnm_gpu", + .id = SM8750_MASTER_GFX3D, + .channels = 2, + .buswidth = 32, + .num_links = 2, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC }, +}; + +static struct qcom_icc_node qnm_lpass_gemnoc = { + .name = "qnm_lpass_gemnoc", + .id = SM8750_MASTER_LPASS_GEM_NOC, + .channels = 1, + .buswidth = 16, + .num_links = 3, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC, + SM8750_SLAVE_MEM_NOC_PCIE_SNOC }, +}; + +static struct qcom_icc_node qnm_mdsp = { + .name = "qnm_mdsp", + .id = SM8750_MASTER_MSS_PROC, + .channels = 1, + .buswidth = 16, + .num_links = 3, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC, + SM8750_SLAVE_MEM_NOC_PCIE_SNOC }, +}; + +static struct qcom_icc_node qnm_mnoc_hf = { + .name = "qnm_mnoc_hf", + .id = SM8750_MASTER_MNOC_HF_MEM_NOC, + .channels = 2, + .buswidth = 32, + .num_links = 2, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC }, +}; + +static struct qcom_icc_node qnm_mnoc_sf = { + .name = "qnm_mnoc_sf", + .id = SM8750_MASTER_MNOC_SF_MEM_NOC, + .channels = 2, + .buswidth = 32, + .num_links = 2, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC }, +}; + +static struct qcom_icc_node qnm_nsp_gemnoc = { + .name = "qnm_nsp_gemnoc", + .id = SM8750_MASTER_COMPUTE_NOC, + .channels = 2, + .buswidth = 32, + .num_links = 3, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC, + SM8750_SLAVE_MEM_NOC_PCIE_SNOC }, +}; + +static struct qcom_icc_node qnm_pcie = { + .name = "qnm_pcie", + .id = SM8750_MASTER_ANOC_PCIE_GEM_NOC, + .channels = 1, + .buswidth = 8, + .num_links = 2, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC }, +}; + +static struct qcom_icc_node qnm_snoc_sf = { + .name = "qnm_snoc_sf", + .id = SM8750_MASTER_SNOC_SF_MEM_NOC, + .channels = 1, + .buswidth = 16, + .num_links = 3, + .links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC, + SM8750_SLAVE_MEM_NOC_PCIE_SNOC }, +}; + +static struct qcom_icc_node qnm_ubwc_p = { + .name = "qnm_ubwc_p", + .id = SM8750_MASTER_UBWC_P, + .channels = 1, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_SLAVE_LLCC }, +}; + +static struct qcom_icc_node xm_gic = { + .name = "xm_gic", + .id = SM8750_MASTER_GIC, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_LLCC }, +}; + +static struct qcom_icc_node qnm_lpiaon_noc = { + .name = "qnm_lpiaon_noc", + .id = SM8750_MASTER_LPIAON_NOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_SLAVE_LPASS_GEM_NOC }, +}; + +static struct qcom_icc_node qnm_lpass_lpinoc = { + .name = "qnm_lpass_lpinoc", + .id = SM8750_MASTER_LPASS_LPINOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_SLAVE_LPIAON_NOC_LPASS_AG_NOC }, +}; + +static struct qcom_icc_node qnm_lpinoc_dsp_qns4m = { + .name = "qnm_lpinoc_dsp_qns4m", + .id = SM8750_MASTER_LPASS_PROC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_SLAVE_LPICX_NOC_LPIAON_NOC }, +}; + +static struct qcom_icc_node llcc_mc = { + .name = "llcc_mc", + .id = SM8750_MASTER_LLCC, + .channels = 4, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_EBI1 }, +}; + +static struct qcom_icc_node qnm_camnoc_hf = { + .name = "qnm_camnoc_hf", + .id = SM8750_MASTER_CAMNOC_HF, + .channels = 2, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_HF_MEM_NOC }, +}; + +static struct qcom_icc_node qnm_camnoc_nrt_icp_sf = { + .name = "qnm_camnoc_nrt_icp_sf", + .id = SM8750_MASTER_CAMNOC_NRT_ICP_SF, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_node qnm_camnoc_rt_cdm_sf = { + .name = "qnm_camnoc_rt_cdm_sf", + .id = SM8750_MASTER_CAMNOC_RT_CDM_SF, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_node qnm_camnoc_sf = { + .name = "qnm_camnoc_sf", + .id = SM8750_MASTER_CAMNOC_SF, + .channels = 2, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_node qnm_mdp = { + .name = "qnm_mdp", + .id = SM8750_MASTER_MDP, + .channels = 2, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_HF_MEM_NOC }, +}; + +static struct qcom_icc_node qnm_vapss_hcp = { + .name = "qnm_vapss_hcp", + .id = SM8750_MASTER_CDSP_HCP, + .channels = 1, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_node qnm_video_cv_cpu = { + .name = "qnm_video_cv_cpu", + .id = SM8750_MASTER_VIDEO_CV_PROC, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_node qnm_video_eva = { + .name = "qnm_video_eva", + .id = SM8750_MASTER_VIDEO_EVA, + .channels = 2, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_node qnm_video_mvp = { + .name = "qnm_video_mvp", + .id = SM8750_MASTER_VIDEO_MVP, + .channels = 2, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_node qnm_video_v_cpu = { + .name = "qnm_video_v_cpu", + .id = SM8750_MASTER_VIDEO_V_PROC, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_MNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_node qsm_mnoc_cfg = { + .name = "qsm_mnoc_cfg", + .id = SM8750_MASTER_CNOC_MNOC_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_SERVICE_MNOC }, +}; + +static struct qcom_icc_node qnm_nsp = { + .name = "qnm_nsp", + .id = SM8750_MASTER_CDSP_PROC, + .channels = 2, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_SLAVE_CDSP_MEM_NOC }, +}; + +static struct qcom_icc_node qsm_pcie_anoc_cfg = { + .name = "qsm_pcie_anoc_cfg", + .id = SM8750_MASTER_PCIE_ANOC_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_SLAVE_SERVICE_PCIE_ANOC }, +}; + +static struct qcom_icc_node xm_pcie3 = { + .name = "xm_pcie3", + .id = SM8750_MASTER_PCIE_0, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_SLAVE_ANOC_PCIE_GEM_NOC }, +}; + +static struct qcom_icc_node qnm_aggre1_noc = { + .name = "qnm_aggre1_noc", + .id = SM8750_MASTER_A1NOC_SNOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_SLAVE_SNOC_GEM_NOC_SF }, +}; + +static struct qcom_icc_node qnm_aggre2_noc = { + .name = "qnm_aggre2_noc", + .id = SM8750_MASTER_A2NOC_SNOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_SLAVE_SNOC_GEM_NOC_SF }, +}; + +static struct qcom_icc_node qns_a1noc_snoc = { + .name = "qns_a1noc_snoc", + .id = SM8750_SLAVE_A1NOC_SNOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_MASTER_A1NOC_SNOC }, +}; + +static struct qcom_icc_node qns_a2noc_snoc = { + .name = "qns_a2noc_snoc", + .id = SM8750_SLAVE_A2NOC_SNOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_MASTER_A2NOC_SNOC }, +}; + +static struct qcom_icc_node qup0_core_slave = { + .name = "qup0_core_slave", + .id = SM8750_SLAVE_QUP_CORE_0, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qup1_core_slave = { + .name = "qup1_core_slave", + .id = SM8750_SLAVE_QUP_CORE_1, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qup2_core_slave = { + .name = "qup2_core_slave", + .id = SM8750_SLAVE_QUP_CORE_2, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_ahb2phy0 = { + .name = "qhs_ahb2phy0", + .id = SM8750_SLAVE_AHB2PHY_SOUTH, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_ahb2phy1 = { + .name = "qhs_ahb2phy1", + .id = SM8750_SLAVE_AHB2PHY_NORTH, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_camera_cfg = { + .name = "qhs_camera_cfg", + .id = SM8750_SLAVE_CAMERA_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_clk_ctl = { + .name = "qhs_clk_ctl", + .id = SM8750_SLAVE_CLK_CTL, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_crypto0_cfg = { + .name = "qhs_crypto0_cfg", + .id = SM8750_SLAVE_CRYPTO_0_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_display_cfg = { + .name = "qhs_display_cfg", + .id = SM8750_SLAVE_DISPLAY_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_eva_cfg = { + .name = "qhs_eva_cfg", + .id = SM8750_SLAVE_EVA_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_gpuss_cfg = { + .name = "qhs_gpuss_cfg", + .id = SM8750_SLAVE_GFX3D_CFG, + .channels = 1, + .buswidth = 8, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_i2c = { + .name = "qhs_i2c", + .id = SM8750_SLAVE_I2C, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_i3c_ibi0_cfg = { + .name = "qhs_i3c_ibi0_cfg", + .id = SM8750_SLAVE_I3C_IBI0_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_i3c_ibi1_cfg = { + .name = "qhs_i3c_ibi1_cfg", + .id = SM8750_SLAVE_I3C_IBI1_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_imem_cfg = { + .name = "qhs_imem_cfg", + .id = SM8750_SLAVE_IMEM_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_mss_cfg = { + .name = "qhs_mss_cfg", + .id = SM8750_SLAVE_CNOC_MSS, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_pcie_cfg = { + .name = "qhs_pcie_cfg", + .id = SM8750_SLAVE_PCIE_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_prng = { + .name = "qhs_prng", + .id = SM8750_SLAVE_PRNG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_qdss_cfg = { + .name = "qhs_qdss_cfg", + .id = SM8750_SLAVE_QDSS_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_qspi = { + .name = "qhs_qspi", + .id = SM8750_SLAVE_QSPI_0, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_qup02 = { + .name = "qhs_qup02", + .id = SM8750_SLAVE_QUP_3, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_qup1 = { + .name = "qhs_qup1", + .id = SM8750_SLAVE_QUP_1, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_qup2 = { + .name = "qhs_qup2", + .id = SM8750_SLAVE_QUP_2, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_sdc2 = { + .name = "qhs_sdc2", + .id = SM8750_SLAVE_SDCC_2, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_sdc4 = { + .name = "qhs_sdc4", + .id = SM8750_SLAVE_SDCC_4, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_spss_cfg = { + .name = "qhs_spss_cfg", + .id = SM8750_SLAVE_SPSS_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_tcsr = { + .name = "qhs_tcsr", + .id = SM8750_SLAVE_TCSR, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_tlmm = { + .name = "qhs_tlmm", + .id = SM8750_SLAVE_TLMM, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_ufs_mem_cfg = { + .name = "qhs_ufs_mem_cfg", + .id = SM8750_SLAVE_UFS_MEM_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_usb3_0 = { + .name = "qhs_usb3_0", + .id = SM8750_SLAVE_USB3_0, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_venus_cfg = { + .name = "qhs_venus_cfg", + .id = SM8750_SLAVE_VENUS_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_vsense_ctrl_cfg = { + .name = "qhs_vsense_ctrl_cfg", + .id = SM8750_SLAVE_VSENSE_CTRL_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qss_mnoc_cfg = { + .name = "qss_mnoc_cfg", + .id = SM8750_SLAVE_CNOC_MNOC_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_MASTER_CNOC_MNOC_CFG }, +}; + +static struct qcom_icc_node qss_pcie_anoc_cfg = { + .name = "qss_pcie_anoc_cfg", + .id = SM8750_SLAVE_PCIE_ANOC_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_MASTER_PCIE_ANOC_CFG }, +}; + +static struct qcom_icc_node xs_qdss_stm = { + .name = "xs_qdss_stm", + .id = SM8750_SLAVE_QDSS_STM, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node xs_sys_tcu_cfg = { + .name = "xs_sys_tcu_cfg", + .id = SM8750_SLAVE_TCU, + .channels = 1, + .buswidth = 8, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_aoss = { + .name = "qhs_aoss", + .id = SM8750_SLAVE_AOSS, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_ipa = { + .name = "qhs_ipa", + .id = SM8750_SLAVE_IPA_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_ipc_router = { + .name = "qhs_ipc_router", + .id = SM8750_SLAVE_IPC_ROUTER_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_soccp = { + .name = "qhs_soccp", + .id = SM8750_SLAVE_SOCCP, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qhs_tme_cfg = { + .name = "qhs_tme_cfg", + .id = SM8750_SLAVE_TME_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qns_apss = { + .name = "qns_apss", + .id = SM8750_SLAVE_APPSS, + .channels = 1, + .buswidth = 8, + .num_links = 0, +}; + +static struct qcom_icc_node qss_cfg = { + .name = "qss_cfg", + .id = SM8750_SLAVE_CNOC_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 1, + .links = { SM8750_MASTER_CNOC_CFG }, +}; + +static struct qcom_icc_node qss_ddrss_cfg = { + .name = "qss_ddrss_cfg", + .id = SM8750_SLAVE_DDRSS_CFG, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qxs_boot_imem = { + .name = "qxs_boot_imem", + .id = SM8750_SLAVE_BOOT_IMEM, + .channels = 1, + .buswidth = 16, + .num_links = 0, +}; + +static struct qcom_icc_node qxs_imem = { + .name = "qxs_imem", + .id = SM8750_SLAVE_IMEM, + .channels = 1, + .buswidth = 8, + .num_links = 0, +}; + +static struct qcom_icc_node qxs_modem_boot_imem = { + .name = "qxs_modem_boot_imem", + .id = SM8750_SLAVE_BOOT_IMEM_2, + .channels = 1, + .buswidth = 8, + .num_links = 0, +}; + +static struct qcom_icc_node srvc_cnoc_main = { + .name = "srvc_cnoc_main", + .id = SM8750_SLAVE_SERVICE_CNOC, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node xs_pcie = { + .name = "xs_pcie", + .id = SM8750_SLAVE_PCIE_0, + .channels = 1, + .buswidth = 8, + .num_links = 0, +}; + +static struct qcom_icc_node chs_ubwc_p = { + .name = "chs_ubwc_p", + .id = SM8750_SLAVE_UBWC_P, + .channels = 1, + .buswidth = 32, + .num_links = 0, +}; + +static struct qcom_icc_node qns_gem_noc_cnoc = { + .name = "qns_gem_noc_cnoc", + .id = SM8750_SLAVE_GEM_NOC_CNOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_MASTER_GEM_NOC_CNOC }, +}; + +static struct qcom_icc_node qns_llcc = { + .name = "qns_llcc", + .id = SM8750_SLAVE_LLCC, + .channels = 4, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_MASTER_LLCC }, +}; + +static struct qcom_icc_node qns_pcie = { + .name = "qns_pcie", + .id = SM8750_SLAVE_MEM_NOC_PCIE_SNOC, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_MASTER_GEM_NOC_PCIE_SNOC }, +}; + +static struct qcom_icc_node qns_lpass_ag_noc_gemnoc = { + .name = "qns_lpass_ag_noc_gemnoc", + .id = SM8750_SLAVE_LPASS_GEM_NOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_MASTER_LPASS_GEM_NOC }, +}; + +static struct qcom_icc_node qns_lpass_aggnoc = { + .name = "qns_lpass_aggnoc", + .id = SM8750_SLAVE_LPIAON_NOC_LPASS_AG_NOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_MASTER_LPIAON_NOC }, +}; + +static struct qcom_icc_node qns_lpi_aon_noc = { + .name = "qns_lpi_aon_noc", + .id = SM8750_SLAVE_LPICX_NOC_LPIAON_NOC, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_MASTER_LPASS_LPINOC }, +}; + +static struct qcom_icc_node ebi = { + .name = "ebi", + .id = SM8750_SLAVE_EBI1, + .channels = 4, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qns_mem_noc_hf = { + .name = "qns_mem_noc_hf", + .id = SM8750_SLAVE_MNOC_HF_MEM_NOC, + .channels = 2, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_MASTER_MNOC_HF_MEM_NOC }, +}; + +static struct qcom_icc_node qns_mem_noc_sf = { + .name = "qns_mem_noc_sf", + .id = SM8750_SLAVE_MNOC_SF_MEM_NOC, + .channels = 2, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_MASTER_MNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_node srvc_mnoc = { + .name = "srvc_mnoc", + .id = SM8750_SLAVE_SERVICE_MNOC, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qns_nsp_gemnoc = { + .name = "qns_nsp_gemnoc", + .id = SM8750_SLAVE_CDSP_MEM_NOC, + .channels = 2, + .buswidth = 32, + .num_links = 1, + .links = { SM8750_MASTER_COMPUTE_NOC }, +}; + +static struct qcom_icc_node qns_pcie_mem_noc = { + .name = "qns_pcie_mem_noc", + .id = SM8750_SLAVE_ANOC_PCIE_GEM_NOC, + .channels = 1, + .buswidth = 8, + .num_links = 1, + .links = { SM8750_MASTER_ANOC_PCIE_GEM_NOC }, +}; + +static struct qcom_icc_node srvc_pcie_aggre_noc = { + .name = "srvc_pcie_aggre_noc", + .id = SM8750_SLAVE_SERVICE_PCIE_ANOC, + .channels = 1, + .buswidth = 4, + .num_links = 0, +}; + +static struct qcom_icc_node qns_gemnoc_sf = { + .name = "qns_gemnoc_sf", + .id = SM8750_SLAVE_SNOC_GEM_NOC_SF, + .channels = 1, + .buswidth = 16, + .num_links = 1, + .links = { SM8750_MASTER_SNOC_SF_MEM_NOC }, +}; + +static struct qcom_icc_bcm bcm_acv = { + .name = "ACV", + .enable_mask = BIT(0), + .num_nodes = 1, + .nodes = { &ebi }, +}; + +static struct qcom_icc_bcm bcm_ce0 = { + .name = "CE0", + .num_nodes = 1, + .nodes = { &qxm_crypto }, +}; + +static struct qcom_icc_bcm bcm_cn0 = { + .name = "CN0", + .enable_mask = BIT(0), + .keepalive = true, + .num_nodes = 44, + .nodes = { &qsm_cfg, &qhs_ahb2phy0, + &qhs_ahb2phy1, &qhs_camera_cfg, + &qhs_clk_ctl, &qhs_crypto0_cfg, + &qhs_eva_cfg, &qhs_gpuss_cfg, + &qhs_i3c_ibi0_cfg, &qhs_i3c_ibi1_cfg, + &qhs_imem_cfg, &qhs_mss_cfg, + &qhs_pcie_cfg, &qhs_prng, + &qhs_qdss_cfg, &qhs_qspi, + &qhs_sdc2, &qhs_sdc4, + &qhs_spss_cfg, &qhs_tcsr, + &qhs_tlmm, &qhs_ufs_mem_cfg, + &qhs_usb3_0, &qhs_venus_cfg, + &qhs_vsense_ctrl_cfg, &qss_mnoc_cfg, + &qss_pcie_anoc_cfg, &xs_qdss_stm, + &xs_sys_tcu_cfg, &qnm_gemnoc_cnoc, + &qnm_gemnoc_pcie, &qhs_aoss, + &qhs_ipa, &qhs_ipc_router, + &qhs_soccp, &qhs_tme_cfg, + &qns_apss, &qss_cfg, + &qss_ddrss_cfg, &qxs_boot_imem, + &qxs_imem, &qxs_modem_boot_imem, + &srvc_cnoc_main, &xs_pcie }, +}; + +static struct qcom_icc_bcm bcm_cn1 = { + .name = "CN1", + .num_nodes = 5, + .nodes = { &qhs_display_cfg, &qhs_i2c, + &qhs_qup02, &qhs_qup1, + &qhs_qup2 }, +}; + +static struct qcom_icc_bcm bcm_co0 = { + .name = "CO0", + .enable_mask = BIT(0), + .num_nodes = 2, + .nodes = { &qnm_nsp, &qns_nsp_gemnoc }, +}; + +static struct qcom_icc_bcm bcm_lp0 = { + .name = "LP0", + .num_nodes = 2, + .nodes = { &qnm_lpass_lpinoc, &qns_lpass_aggnoc }, +}; + +static struct qcom_icc_bcm bcm_mc0 = { + .name = "MC0", + .keepalive = true, + .num_nodes = 1, + .nodes = { &ebi }, +}; + +static struct qcom_icc_bcm bcm_mm0 = { + .name = "MM0", + .num_nodes = 1, + .nodes = { &qns_mem_noc_hf }, +}; + +static struct qcom_icc_bcm bcm_mm1 = { + .name = "MM1", + .enable_mask = BIT(0), + .num_nodes = 9, + .nodes = { &qnm_camnoc_hf, &qnm_camnoc_nrt_icp_sf, + &qnm_camnoc_rt_cdm_sf, &qnm_camnoc_sf, + &qnm_vapss_hcp, &qnm_video_cv_cpu, + &qnm_video_mvp, &qnm_video_v_cpu, + &qns_mem_noc_sf }, +}; + +static struct qcom_icc_bcm bcm_qup0 = { + .name = "QUP0", + .keepalive = true, + .vote_scale = 1, + .num_nodes = 1, + .nodes = { &qup0_core_slave }, +}; + +static struct qcom_icc_bcm bcm_qup1 = { + .name = "QUP1", + .keepalive = true, + .vote_scale = 1, + .num_nodes = 1, + .nodes = { &qup1_core_slave }, +}; + +static struct qcom_icc_bcm bcm_qup2 = { + .name = "QUP2", + .keepalive = true, + .vote_scale = 1, + .num_nodes = 1, + .nodes = { &qup2_core_slave }, +}; + +static struct qcom_icc_bcm bcm_sh0 = { + .name = "SH0", + .keepalive = true, + .num_nodes = 1, + .nodes = { &qns_llcc }, +}; + +static struct qcom_icc_bcm bcm_sh1 = { + .name = "SH1", + .enable_mask = BIT(0), + .num_nodes = 14, + .nodes = { &alm_gpu_tcu, &alm_sys_tcu, + &chm_apps, &qnm_gpu, + &qnm_mdsp, &qnm_mnoc_hf, + &qnm_mnoc_sf, &qnm_nsp_gemnoc, + &qnm_pcie, &qnm_snoc_sf, + &xm_gic, &chs_ubwc_p, + &qns_gem_noc_cnoc, &qns_pcie }, +}; + +static struct qcom_icc_bcm bcm_sn0 = { + .name = "SN0", + .keepalive = true, + .num_nodes = 1, + .nodes = { &qns_gemnoc_sf }, +}; + +static struct qcom_icc_bcm bcm_sn2 = { + .name = "SN2", + .num_nodes = 1, + .nodes = { &qnm_aggre1_noc }, +}; + +static struct qcom_icc_bcm bcm_sn3 = { + .name = "SN3", + .num_nodes = 1, + .nodes = { &qnm_aggre2_noc }, +}; + +static struct qcom_icc_bcm bcm_sn4 = { + .name = "SN4", + .num_nodes = 1, + .nodes = { &qns_pcie_mem_noc }, +}; + +static struct qcom_icc_bcm bcm_ubw0 = { + .name = "UBW0", + .num_nodes = 1, + .nodes = { &qnm_ubwc_p }, +}; + +static struct qcom_icc_node * const aggre1_noc_nodes[] = { + [MASTER_QSPI_0] = &qhm_qspi, + [MASTER_QUP_1] = &qhm_qup1, + [MASTER_QUP_3] = &qxm_qup02, + [MASTER_SDCC_4] = &xm_sdc4, + [MASTER_UFS_MEM] = &xm_ufs_mem, + [MASTER_USB3_0] = &xm_usb3_0, + [SLAVE_A1NOC_SNOC] = &qns_a1noc_snoc, +}; + +static const struct qcom_icc_desc sm8750_aggre1_noc = { + .nodes = aggre1_noc_nodes, + .num_nodes = ARRAY_SIZE(aggre1_noc_nodes), +}; + +static struct qcom_icc_bcm * const aggre2_noc_bcms[] = { + &bcm_ce0, +}; + +static struct qcom_icc_node * const aggre2_noc_nodes[] = { + [MASTER_QDSS_BAM] = &qhm_qdss_bam, + [MASTER_QUP_2] = &qhm_qup2, + [MASTER_CRYPTO] = &qxm_crypto, + [MASTER_IPA] = &qxm_ipa, + [MASTER_SOCCP_AGGR_NOC] = &qxm_soccp, + [MASTER_SP] = &qxm_sp, + [MASTER_QDSS_ETR] = &xm_qdss_etr_0, + [MASTER_QDSS_ETR_1] = &xm_qdss_etr_1, + [MASTER_SDCC_2] = &xm_sdc2, + [SLAVE_A2NOC_SNOC] = &qns_a2noc_snoc, +}; + +static const struct qcom_icc_desc sm8750_aggre2_noc = { + .nodes = aggre2_noc_nodes, + .num_nodes = ARRAY_SIZE(aggre2_noc_nodes), + .bcms = aggre2_noc_bcms, + .num_bcms = ARRAY_SIZE(aggre2_noc_bcms), +}; + +static struct qcom_icc_bcm * const clk_virt_bcms[] = { + &bcm_qup0, + &bcm_qup1, + &bcm_qup2, +}; + +static struct qcom_icc_node * const clk_virt_nodes[] = { + [MASTER_QUP_CORE_0] = &qup0_core_master, + [MASTER_QUP_CORE_1] = &qup1_core_master, + [MASTER_QUP_CORE_2] = &qup2_core_master, + [SLAVE_QUP_CORE_0] = &qup0_core_slave, + [SLAVE_QUP_CORE_1] = &qup1_core_slave, + [SLAVE_QUP_CORE_2] = &qup2_core_slave, +}; + +static const struct qcom_icc_desc sm8750_clk_virt = { + .nodes = clk_virt_nodes, + .num_nodes = ARRAY_SIZE(clk_virt_nodes), + .bcms = clk_virt_bcms, + .num_bcms = ARRAY_SIZE(clk_virt_bcms), +}; + +static struct qcom_icc_bcm * const config_noc_bcms[] = { + &bcm_cn0, + &bcm_cn1, +}; + +static struct qcom_icc_node * const config_noc_nodes[] = { + [MASTER_CNOC_CFG] = &qsm_cfg, + [SLAVE_AHB2PHY_SOUTH] = &qhs_ahb2phy0, + [SLAVE_AHB2PHY_NORTH] = &qhs_ahb2phy1, + [SLAVE_CAMERA_CFG] = &qhs_camera_cfg, + [SLAVE_CLK_CTL] = &qhs_clk_ctl, + [SLAVE_CRYPTO_0_CFG] = &qhs_crypto0_cfg, + [SLAVE_DISPLAY_CFG] = &qhs_display_cfg, + [SLAVE_EVA_CFG] = &qhs_eva_cfg, + [SLAVE_GFX3D_CFG] = &qhs_gpuss_cfg, + [SLAVE_I2C] = &qhs_i2c, + [SLAVE_I3C_IBI0_CFG] = &qhs_i3c_ibi0_cfg, + [SLAVE_I3C_IBI1_CFG] = &qhs_i3c_ibi1_cfg, + [SLAVE_IMEM_CFG] = &qhs_imem_cfg, + [SLAVE_CNOC_MSS] = &qhs_mss_cfg, + [SLAVE_PCIE_CFG] = &qhs_pcie_cfg, + [SLAVE_PRNG] = &qhs_prng, + [SLAVE_QDSS_CFG] = &qhs_qdss_cfg, + [SLAVE_QSPI_0] = &qhs_qspi, + [SLAVE_QUP_3] = &qhs_qup02, + [SLAVE_QUP_1] = &qhs_qup1, + [SLAVE_QUP_2] = &qhs_qup2, + [SLAVE_SDCC_2] = &qhs_sdc2, + [SLAVE_SDCC_4] = &qhs_sdc4, + [SLAVE_SPSS_CFG] = &qhs_spss_cfg, + [SLAVE_TCSR] = &qhs_tcsr, + [SLAVE_TLMM] = &qhs_tlmm, + [SLAVE_UFS_MEM_CFG] = &qhs_ufs_mem_cfg, + [SLAVE_USB3_0] = &qhs_usb3_0, + [SLAVE_VENUS_CFG] = &qhs_venus_cfg, + [SLAVE_VSENSE_CTRL_CFG] = &qhs_vsense_ctrl_cfg, + [SLAVE_CNOC_MNOC_CFG] = &qss_mnoc_cfg, + [SLAVE_PCIE_ANOC_CFG] = &qss_pcie_anoc_cfg, + [SLAVE_QDSS_STM] = &xs_qdss_stm, + [SLAVE_TCU] = &xs_sys_tcu_cfg, +}; + +static const struct qcom_icc_desc sm8750_config_noc = { + .nodes = config_noc_nodes, + .num_nodes = ARRAY_SIZE(config_noc_nodes), + .bcms = config_noc_bcms, + .num_bcms = ARRAY_SIZE(config_noc_bcms), +}; + +static struct qcom_icc_bcm * const cnoc_main_bcms[] = { + &bcm_cn0, +}; + +static struct qcom_icc_node * const cnoc_main_nodes[] = { + [MASTER_GEM_NOC_CNOC] = &qnm_gemnoc_cnoc, + [MASTER_GEM_NOC_PCIE_SNOC] = &qnm_gemnoc_pcie, + [SLAVE_AOSS] = &qhs_aoss, + [SLAVE_IPA_CFG] = &qhs_ipa, + [SLAVE_IPC_ROUTER_CFG] = &qhs_ipc_router, + [SLAVE_SOCCP] = &qhs_soccp, + [SLAVE_TME_CFG] = &qhs_tme_cfg, + [SLAVE_APPSS] = &qns_apss, + [SLAVE_CNOC_CFG] = &qss_cfg, + [SLAVE_DDRSS_CFG] = &qss_ddrss_cfg, + [SLAVE_BOOT_IMEM] = &qxs_boot_imem, + [SLAVE_IMEM] = &qxs_imem, + [SLAVE_BOOT_IMEM_2] = &qxs_modem_boot_imem, + [SLAVE_SERVICE_CNOC] = &srvc_cnoc_main, + [SLAVE_PCIE_0] = &xs_pcie, +}; + +static const struct qcom_icc_desc sm8750_cnoc_main = { + .nodes = cnoc_main_nodes, + .num_nodes = ARRAY_SIZE(cnoc_main_nodes), + .bcms = cnoc_main_bcms, + .num_bcms = ARRAY_SIZE(cnoc_main_bcms), +}; + +static struct qcom_icc_bcm * const gem_noc_bcms[] = { + &bcm_sh0, + &bcm_sh1, + &bcm_ubw0, +}; + +static struct qcom_icc_node * const gem_noc_nodes[] = { + [MASTER_GPU_TCU] = &alm_gpu_tcu, + [MASTER_SYS_TCU] = &alm_sys_tcu, + [MASTER_APPSS_PROC] = &chm_apps, + [MASTER_GFX3D] = &qnm_gpu, + [MASTER_LPASS_GEM_NOC] = &qnm_lpass_gemnoc, + [MASTER_MSS_PROC] = &qnm_mdsp, + [MASTER_MNOC_HF_MEM_NOC] = &qnm_mnoc_hf, + [MASTER_MNOC_SF_MEM_NOC] = &qnm_mnoc_sf, + [MASTER_COMPUTE_NOC] = &qnm_nsp_gemnoc, + [MASTER_ANOC_PCIE_GEM_NOC] = &qnm_pcie, + [MASTER_SNOC_SF_MEM_NOC] = &qnm_snoc_sf, + [MASTER_UBWC_P] = &qnm_ubwc_p, + [MASTER_GIC] = &xm_gic, + [SLAVE_UBWC_P] = &chs_ubwc_p, + [SLAVE_GEM_NOC_CNOC] = &qns_gem_noc_cnoc, + [SLAVE_LLCC] = &qns_llcc, + [SLAVE_MEM_NOC_PCIE_SNOC] = &qns_pcie, +}; + +static const struct qcom_icc_desc sm8750_gem_noc = { + .nodes = gem_noc_nodes, + .num_nodes = ARRAY_SIZE(gem_noc_nodes), + .bcms = gem_noc_bcms, + .num_bcms = ARRAY_SIZE(gem_noc_bcms), +}; + +static struct qcom_icc_node * const lpass_ag_noc_nodes[] = { + [MASTER_LPIAON_NOC] = &qnm_lpiaon_noc, + [SLAVE_LPASS_GEM_NOC] = &qns_lpass_ag_noc_gemnoc, +}; + +static const struct qcom_icc_desc sm8750_lpass_ag_noc = { + .nodes = lpass_ag_noc_nodes, + .num_nodes = ARRAY_SIZE(lpass_ag_noc_nodes), +}; + +static struct qcom_icc_bcm * const lpass_lpiaon_noc_bcms[] = { + &bcm_lp0, +}; + +static struct qcom_icc_node * const lpass_lpiaon_noc_nodes[] = { + [MASTER_LPASS_LPINOC] = &qnm_lpass_lpinoc, + [SLAVE_LPIAON_NOC_LPASS_AG_NOC] = &qns_lpass_aggnoc, +}; + +static const struct qcom_icc_desc sm8750_lpass_lpiaon_noc = { + .nodes = lpass_lpiaon_noc_nodes, + .num_nodes = ARRAY_SIZE(lpass_lpiaon_noc_nodes), + .bcms = lpass_lpiaon_noc_bcms, + .num_bcms = ARRAY_SIZE(lpass_lpiaon_noc_bcms), +}; + +static struct qcom_icc_node * const lpass_lpicx_noc_nodes[] = { + [MASTER_LPASS_PROC] = &qnm_lpinoc_dsp_qns4m, + [SLAVE_LPICX_NOC_LPIAON_NOC] = &qns_lpi_aon_noc, +}; + +static const struct qcom_icc_desc sm8750_lpass_lpicx_noc = { + .nodes = lpass_lpicx_noc_nodes, + .num_nodes = ARRAY_SIZE(lpass_lpicx_noc_nodes), +}; + +static struct qcom_icc_bcm * const mc_virt_bcms[] = { + &bcm_acv, + &bcm_mc0, +}; + +static struct qcom_icc_node * const mc_virt_nodes[] = { + [MASTER_LLCC] = &llcc_mc, + [SLAVE_EBI1] = &ebi, +}; + +static const struct qcom_icc_desc sm8750_mc_virt = { + .nodes = mc_virt_nodes, + .num_nodes = ARRAY_SIZE(mc_virt_nodes), + .bcms = mc_virt_bcms, + .num_bcms = ARRAY_SIZE(mc_virt_bcms), +}; + +static struct qcom_icc_bcm * const mmss_noc_bcms[] = { + &bcm_mm0, + &bcm_mm1, +}; + +static struct qcom_icc_node * const mmss_noc_nodes[] = { + [MASTER_CAMNOC_HF] = &qnm_camnoc_hf, + [MASTER_CAMNOC_NRT_ICP_SF] = &qnm_camnoc_nrt_icp_sf, + [MASTER_CAMNOC_RT_CDM_SF] = &qnm_camnoc_rt_cdm_sf, + [MASTER_CAMNOC_SF] = &qnm_camnoc_sf, + [MASTER_MDP] = &qnm_mdp, + [MASTER_CDSP_HCP] = &qnm_vapss_hcp, + [MASTER_VIDEO_CV_PROC] = &qnm_video_cv_cpu, + [MASTER_VIDEO_EVA] = &qnm_video_eva, + [MASTER_VIDEO_MVP] = &qnm_video_mvp, + [MASTER_VIDEO_V_PROC] = &qnm_video_v_cpu, + [MASTER_CNOC_MNOC_CFG] = &qsm_mnoc_cfg, + [SLAVE_MNOC_HF_MEM_NOC] = &qns_mem_noc_hf, + [SLAVE_MNOC_SF_MEM_NOC] = &qns_mem_noc_sf, + [SLAVE_SERVICE_MNOC] = &srvc_mnoc, +}; + +static const struct qcom_icc_desc sm8750_mmss_noc = { + .nodes = mmss_noc_nodes, + .num_nodes = ARRAY_SIZE(mmss_noc_nodes), + .bcms = mmss_noc_bcms, + .num_bcms = ARRAY_SIZE(mmss_noc_bcms), +}; + +static struct qcom_icc_bcm * const nsp_noc_bcms[] = { + &bcm_co0, +}; + +static struct qcom_icc_node * const nsp_noc_nodes[] = { + [MASTER_CDSP_PROC] = &qnm_nsp, + [SLAVE_CDSP_MEM_NOC] = &qns_nsp_gemnoc, +}; + +static const struct qcom_icc_desc sm8750_nsp_noc = { + .nodes = nsp_noc_nodes, + .num_nodes = ARRAY_SIZE(nsp_noc_nodes), + .bcms = nsp_noc_bcms, + .num_bcms = ARRAY_SIZE(nsp_noc_bcms), +}; + +static struct qcom_icc_bcm * const pcie_anoc_bcms[] = { + &bcm_sn4, +}; + +static struct qcom_icc_node * const pcie_anoc_nodes[] = { + [MASTER_PCIE_ANOC_CFG] = &qsm_pcie_anoc_cfg, + [MASTER_PCIE_0] = &xm_pcie3, + [SLAVE_ANOC_PCIE_GEM_NOC] = &qns_pcie_mem_noc, + [SLAVE_SERVICE_PCIE_ANOC] = &srvc_pcie_aggre_noc, +}; + +static const struct qcom_icc_desc sm8750_pcie_anoc = { + .nodes = pcie_anoc_nodes, + .num_nodes = ARRAY_SIZE(pcie_anoc_nodes), + .bcms = pcie_anoc_bcms, + .num_bcms = ARRAY_SIZE(pcie_anoc_bcms), +}; + +static struct qcom_icc_bcm * const system_noc_bcms[] = { + &bcm_sn0, + &bcm_sn2, + &bcm_sn3, +}; + +static struct qcom_icc_node * const system_noc_nodes[] = { + [MASTER_A1NOC_SNOC] = &qnm_aggre1_noc, + [MASTER_A2NOC_SNOC] = &qnm_aggre2_noc, + [SLAVE_SNOC_GEM_NOC_SF] = &qns_gemnoc_sf, +}; + +static const struct qcom_icc_desc sm8750_system_noc = { + .nodes = system_noc_nodes, + .num_nodes = ARRAY_SIZE(system_noc_nodes), + .bcms = system_noc_bcms, + .num_bcms = ARRAY_SIZE(system_noc_bcms), +}; + +static const struct of_device_id qnoc_of_match[] = { + { .compatible = "qcom,sm8750-aggre1-noc", .data = &sm8750_aggre1_noc}, + { .compatible = "qcom,sm8750-aggre2-noc", .data = &sm8750_aggre2_noc}, + { .compatible = "qcom,sm8750-clk-virt", .data = &sm8750_clk_virt}, + { .compatible = "qcom,sm8750-config-noc", .data = &sm8750_config_noc}, + { .compatible = "qcom,sm8750-cnoc-main", .data = &sm8750_cnoc_main}, + { .compatible = "qcom,sm8750-gem-noc", .data = &sm8750_gem_noc}, + { .compatible = "qcom,sm8750-lpass-ag-noc", .data = &sm8750_lpass_ag_noc}, + { .compatible = "qcom,sm8750-lpass-lpiaon-noc", .data = &sm8750_lpass_lpiaon_noc}, + { .compatible = "qcom,sm8750-lpass-lpicx-noc", .data = &sm8750_lpass_lpicx_noc}, + { .compatible = "qcom,sm8750-mc-virt", .data = &sm8750_mc_virt}, + { .compatible = "qcom,sm8750-mmss-noc", .data = &sm8750_mmss_noc}, + { .compatible = "qcom,sm8750-nsp-noc", .data = &sm8750_nsp_noc}, + { .compatible = "qcom,sm8750-pcie-anoc", .data = &sm8750_pcie_anoc}, + { .compatible = "qcom,sm8750-system-noc", .data = &sm8750_system_noc}, + { } +}; +MODULE_DEVICE_TABLE(of, qnoc_of_match); + +static struct platform_driver qnoc_driver = { + .probe = qcom_icc_rpmh_probe, + .remove = qcom_icc_rpmh_remove, + .driver = { + .name = "qnoc-sm8750", + .of_match_table = qnoc_of_match, + .sync_state = icc_sync_state, + }, +}; + +static int __init qnoc_driver_init(void) +{ + return platform_driver_register(&qnoc_driver); +} +core_initcall(qnoc_driver_init); + +static void __exit qnoc_driver_exit(void) +{ + platform_driver_unregister(&qnoc_driver); +} +module_exit(qnoc_driver_exit); + +MODULE_DESCRIPTION("SM8750 NoC driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 47c46e4b739e..ec1b5e32b972 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -367,6 +367,18 @@ config ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT 'arm-smmu.disable_bypass' will continue to override this config. +config ARM_SMMU_MMU_500_CPRE_ERRATA + bool "Enable errata workaround for CPRE in SMMU reset path" + depends on ARM_SMMU + default y + help + Say Y here (by default) to apply workaround to disable + MMU-500's next-page prefetcher for sake of 4 known errata. + + Say N here only when it is sure that any errata related to + prefetch enablement are not applicable on the platform. + Refer silicon-errata.rst for info on errata IDs. + config ARM_SMMU_QCOM def_tristate y depends on ARM_SMMU && ARCH_QCOM diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 1bef5d55b2f9..68debf5ee2d7 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -16,7 +16,6 @@ irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data); irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data); irqreturn_t amd_iommu_int_thread_galog(int irq, void *data); irqreturn_t amd_iommu_int_handler(int irq, void *data); -void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid); void amd_iommu_restart_log(struct amd_iommu *iommu, const char *evt_type, u8 cntrl_intr, u8 cntrl_log, u32 status_run_mask, u32 status_overflow_mask); @@ -41,13 +40,13 @@ void amd_iommu_disable(void); int amd_iommu_reenable(int mode); int amd_iommu_enable_faulting(unsigned int cpu); extern int amd_iommu_guest_ir; -extern enum io_pgtable_fmt amd_iommu_pgtable; +extern enum protection_domain_mode amd_iommu_pgtable; extern int amd_iommu_gpt_level; extern unsigned long amd_iommu_pgsize_bitmap; /* Protection domain ops */ void amd_iommu_init_identity_domain(void); -struct protection_domain *protection_domain_alloc(unsigned int type, int nid); +struct protection_domain *protection_domain_alloc(void); void protection_domain_free(struct protection_domain *domain); struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev, struct mm_struct *mm); @@ -89,7 +88,6 @@ int amd_iommu_complete_ppr(struct device *dev, u32 pasid, int status, int tag); */ void amd_iommu_flush_all_caches(struct amd_iommu *iommu); void amd_iommu_update_and_flush_device_table(struct protection_domain *domain); -void amd_iommu_domain_update(struct protection_domain *domain); void amd_iommu_domain_flush_pages(struct protection_domain *domain, u64 address, size_t size); void amd_iommu_dev_flush_pasid_pages(struct iommu_dev_data *dev_data, @@ -184,3 +182,6 @@ void amd_iommu_domain_set_pgtable(struct protection_domain *domain, struct dev_table_entry *get_dev_table(struct amd_iommu *iommu); #endif + +struct dev_table_entry *amd_iommu_get_ivhd_dte_flags(u16 segid, u16 devid); +struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid); diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index fdb0357e0bb9..0bbda60d3cdc 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -220,6 +220,8 @@ #define DEV_ENTRY_EX 0x67 #define DEV_ENTRY_SYSMGT1 0x68 #define DEV_ENTRY_SYSMGT2 0x69 +#define DTE_DATA1_SYSMGT_MASK GENMASK_ULL(41, 40) + #define DEV_ENTRY_IRQ_TBL_EN 0x80 #define DEV_ENTRY_INIT_PASS 0xb8 #define DEV_ENTRY_EINT_PASS 0xb9 @@ -407,8 +409,7 @@ #define DTE_FLAG_HAD (3ULL << 7) #define DTE_FLAG_GIOV BIT_ULL(54) #define DTE_FLAG_GV BIT_ULL(55) -#define DTE_GLX_SHIFT (56) -#define DTE_GLX_MASK (3) +#define DTE_GLX GENMASK_ULL(57, 56) #define DTE_FLAG_IR BIT_ULL(61) #define DTE_FLAG_IW BIT_ULL(62) @@ -416,18 +417,18 @@ #define DTE_FLAG_MASK (0x3ffULL << 32) #define DEV_DOMID_MASK 0xffffULL -#define DTE_GCR3_VAL_A(x) (((x) >> 12) & 0x00007ULL) -#define DTE_GCR3_VAL_B(x) (((x) >> 15) & 0x0ffffULL) -#define DTE_GCR3_VAL_C(x) (((x) >> 31) & 0x1fffffULL) - -#define DTE_GCR3_SHIFT_A 58 -#define DTE_GCR3_SHIFT_B 16 -#define DTE_GCR3_SHIFT_C 43 +#define DTE_GCR3_14_12 GENMASK_ULL(60, 58) +#define DTE_GCR3_30_15 GENMASK_ULL(31, 16) +#define DTE_GCR3_51_31 GENMASK_ULL(63, 43) #define DTE_GPT_LEVEL_SHIFT 54 +#define DTE_GPT_LEVEL_MASK GENMASK_ULL(55, 54) #define GCR3_VALID 0x01ULL +/* DTE[128:179] | DTE[184:191] */ +#define DTE_DATA2_INTR_MASK ~GENMASK_ULL(55, 52) + #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL) #define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_PR) #define IOMMU_PTE_DIRTY(pte) ((pte) & IOMMU_PTE_HD) @@ -468,7 +469,7 @@ extern bool amd_iommu_dump; #define DUMP_printk(format, arg...) \ do { \ if (amd_iommu_dump) \ - pr_info("AMD-Vi: " format, ## arg); \ + pr_info(format, ## arg); \ } while(0); /* global flag if IOMMUs cache non-present entries */ @@ -516,6 +517,9 @@ extern struct kmem_cache *amd_iommu_irq_cache; #define for_each_pdom_dev_data_safe(pdom_dev_data, next, pdom) \ list_for_each_entry_safe((pdom_dev_data), (next), &pdom->dev_data_list, list) +#define for_each_ivhd_dte_flags(entry) \ + list_for_each_entry((entry), &amd_ivhd_dev_flags_list, list) + struct amd_iommu; struct iommu_domain; struct irq_domain; @@ -837,6 +841,7 @@ struct devid_map { struct iommu_dev_data { /*Protect against attach/detach races */ struct mutex mutex; + spinlock_t dte_lock; /* DTE lock for 256-bit access */ struct list_head list; /* For domain->dev_list */ struct llist_node dev_data_list; /* For global dev_data_list */ @@ -881,7 +886,21 @@ extern struct list_head amd_iommu_list; * Structure defining one entry in the device table */ struct dev_table_entry { - u64 data[4]; + union { + u64 data[4]; + u128 data128[2]; + }; +}; + +/* + * Structure to sture persistent DTE flags from IVHD + */ +struct ivhd_dte_flags { + struct list_head list; + u16 segid; + u16 devid_first; + u16 devid_last; + struct dev_table_entry dte; }; /* diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 0e0a531042ac..c5cd92edada0 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -152,7 +152,7 @@ struct ivmd_header { bool amd_iommu_dump; bool amd_iommu_irq_remap __read_mostly; -enum io_pgtable_fmt amd_iommu_pgtable = AMD_IOMMU_V1; +enum protection_domain_mode amd_iommu_pgtable = PD_MODE_V1; /* Guest page table level */ int amd_iommu_gpt_level = PAGE_MODE_4_LEVEL; @@ -174,8 +174,8 @@ bool amd_iommu_snp_en; EXPORT_SYMBOL(amd_iommu_snp_en); LIST_HEAD(amd_iommu_pci_seg_list); /* list of all PCI segments */ -LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the - system */ +LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the system */ +LIST_HEAD(amd_ivhd_dev_flags_list); /* list of all IVHD device entry settings */ /* Number of IOMMUs present in the system */ static int amd_iommus_present; @@ -984,36 +984,12 @@ static void iommu_enable_gt(struct amd_iommu *iommu) } /* sets a specific bit in the device table entry. */ -static void __set_dev_entry_bit(struct dev_table_entry *dev_table, - u16 devid, u8 bit) +static void set_dte_bit(struct dev_table_entry *dte, u8 bit) { int i = (bit >> 6) & 0x03; int _bit = bit & 0x3f; - dev_table[devid].data[i] |= (1UL << _bit); -} - -static void set_dev_entry_bit(struct amd_iommu *iommu, u16 devid, u8 bit) -{ - struct dev_table_entry *dev_table = get_dev_table(iommu); - - return __set_dev_entry_bit(dev_table, devid, bit); -} - -static int __get_dev_entry_bit(struct dev_table_entry *dev_table, - u16 devid, u8 bit) -{ - int i = (bit >> 6) & 0x03; - int _bit = bit & 0x3f; - - return (dev_table[devid].data[i] & (1UL << _bit)) >> _bit; -} - -static int get_dev_entry_bit(struct amd_iommu *iommu, u16 devid, u8 bit) -{ - struct dev_table_entry *dev_table = get_dev_table(iommu); - - return __get_dev_entry_bit(dev_table, devid, bit); + dte->data[i] |= (1UL << _bit); } static bool __copy_device_table(struct amd_iommu *iommu) @@ -1081,11 +1057,9 @@ static bool __copy_device_table(struct amd_iommu *iommu) } /* If gcr3 table existed, mask it out */ if (old_devtb[devid].data[0] & DTE_FLAG_GV) { - tmp = DTE_GCR3_VAL_B(~0ULL) << DTE_GCR3_SHIFT_B; - tmp |= DTE_GCR3_VAL_C(~0ULL) << DTE_GCR3_SHIFT_C; + tmp = (DTE_GCR3_30_15 | DTE_GCR3_51_31); pci_seg->old_dev_tbl_cpy[devid].data[1] &= ~tmp; - tmp = DTE_GCR3_VAL_A(~0ULL) << DTE_GCR3_SHIFT_A; - tmp |= DTE_FLAG_GV; + tmp = (DTE_GCR3_14_12 | DTE_FLAG_GV); pci_seg->old_dev_tbl_cpy[devid].data[0] &= ~tmp; } } @@ -1136,42 +1110,107 @@ static bool copy_device_table(void) return true; } -void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid) +struct dev_table_entry *amd_iommu_get_ivhd_dte_flags(u16 segid, u16 devid) { - int sysmgt; + struct ivhd_dte_flags *e; + unsigned int best_len = UINT_MAX; + struct dev_table_entry *dte = NULL; - sysmgt = get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1) | - (get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2) << 1); + for_each_ivhd_dte_flags(e) { + /* + * Need to go through the whole list to find the smallest range, + * which contains the devid. + */ + if ((e->segid == segid) && + (e->devid_first <= devid) && (devid <= e->devid_last)) { + unsigned int len = e->devid_last - e->devid_first; - if (sysmgt == 0x01) - set_dev_entry_bit(iommu, devid, DEV_ENTRY_IW); + if (len < best_len) { + dte = &(e->dte); + best_len = len; + } + } + } + return dte; +} + +static bool search_ivhd_dte_flags(u16 segid, u16 first, u16 last) +{ + struct ivhd_dte_flags *e; + + for_each_ivhd_dte_flags(e) { + if ((e->segid == segid) && + (e->devid_first == first) && + (e->devid_last == last)) + return true; + } + return false; } /* * This function takes the device specific flags read from the ACPI * table and sets up the device table entry with that information */ +static void __init +set_dev_entry_from_acpi_range(struct amd_iommu *iommu, u16 first, u16 last, + u32 flags, u32 ext_flags) +{ + int i; + struct dev_table_entry dte = {}; + + /* Parse IVHD DTE setting flags and store information */ + if (flags) { + struct ivhd_dte_flags *d; + + if (search_ivhd_dte_flags(iommu->pci_seg->id, first, last)) + return; + + d = kzalloc(sizeof(struct ivhd_dte_flags), GFP_KERNEL); + if (!d) + return; + + pr_debug("%s: devid range %#x:%#x\n", __func__, first, last); + + if (flags & ACPI_DEVFLAG_INITPASS) + set_dte_bit(&dte, DEV_ENTRY_INIT_PASS); + if (flags & ACPI_DEVFLAG_EXTINT) + set_dte_bit(&dte, DEV_ENTRY_EINT_PASS); + if (flags & ACPI_DEVFLAG_NMI) + set_dte_bit(&dte, DEV_ENTRY_NMI_PASS); + if (flags & ACPI_DEVFLAG_SYSMGT1) + set_dte_bit(&dte, DEV_ENTRY_SYSMGT1); + if (flags & ACPI_DEVFLAG_SYSMGT2) + set_dte_bit(&dte, DEV_ENTRY_SYSMGT2); + if (flags & ACPI_DEVFLAG_LINT0) + set_dte_bit(&dte, DEV_ENTRY_LINT0_PASS); + if (flags & ACPI_DEVFLAG_LINT1) + set_dte_bit(&dte, DEV_ENTRY_LINT1_PASS); + + /* Apply erratum 63, which needs info in initial_dte */ + if (FIELD_GET(DTE_DATA1_SYSMGT_MASK, dte.data[1]) == 0x1) + dte.data[0] |= DTE_FLAG_IW; + + memcpy(&d->dte, &dte, sizeof(dte)); + d->segid = iommu->pci_seg->id; + d->devid_first = first; + d->devid_last = last; + list_add_tail(&d->list, &amd_ivhd_dev_flags_list); + } + + for (i = first; i <= last; i++) { + if (flags) { + struct dev_table_entry *dev_table = get_dev_table(iommu); + + memcpy(&dev_table[i], &dte, sizeof(dte)); + } + amd_iommu_set_rlookup_table(iommu, i); + } +} + static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu, u16 devid, u32 flags, u32 ext_flags) { - if (flags & ACPI_DEVFLAG_INITPASS) - set_dev_entry_bit(iommu, devid, DEV_ENTRY_INIT_PASS); - if (flags & ACPI_DEVFLAG_EXTINT) - set_dev_entry_bit(iommu, devid, DEV_ENTRY_EINT_PASS); - if (flags & ACPI_DEVFLAG_NMI) - set_dev_entry_bit(iommu, devid, DEV_ENTRY_NMI_PASS); - if (flags & ACPI_DEVFLAG_SYSMGT1) - set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1); - if (flags & ACPI_DEVFLAG_SYSMGT2) - set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2); - if (flags & ACPI_DEVFLAG_LINT0) - set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT0_PASS); - if (flags & ACPI_DEVFLAG_LINT1) - set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT1_PASS); - - amd_iommu_apply_erratum_63(iommu, devid); - - amd_iommu_set_rlookup_table(iommu, devid); + set_dev_entry_from_acpi_range(iommu, devid, devid, flags, ext_flags); } int __init add_special_device(u8 type, u8 id, u32 *devid, bool cmd_line) @@ -1239,7 +1278,7 @@ static int __init add_acpi_hid_device(u8 *hid, u8 *uid, u32 *devid, entry->cmd_line = cmd_line; entry->root_devid = (entry->devid & (~0x7)); - pr_info("%s, add hid:%s, uid:%s, rdevid:%d\n", + pr_info("%s, add hid:%s, uid:%s, rdevid:%#x\n", entry->cmd_line ? "cmd" : "ivrs", entry->hid, entry->uid, entry->root_devid); @@ -1331,15 +1370,12 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, switch (e->type) { case IVHD_DEV_ALL: - DUMP_printk(" DEV_ALL\t\t\tflags: %02x\n", e->flags); - - for (dev_i = 0; dev_i <= pci_seg->last_bdf; ++dev_i) - set_dev_entry_from_acpi(iommu, dev_i, e->flags, 0); + DUMP_printk(" DEV_ALL\t\t\tsetting: %#02x\n", e->flags); + set_dev_entry_from_acpi_range(iommu, 0, pci_seg->last_bdf, e->flags, 0); break; case IVHD_DEV_SELECT: - DUMP_printk(" DEV_SELECT\t\t\t devid: %04x:%02x:%02x.%x " - "flags: %02x\n", + DUMP_printk(" DEV_SELECT\t\t\tdevid: %04x:%02x:%02x.%x flags: %#02x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1350,8 +1386,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_SELECT_RANGE_START: - DUMP_printk(" DEV_SELECT_RANGE_START\t " - "devid: %04x:%02x:%02x.%x flags: %02x\n", + DUMP_printk(" DEV_SELECT_RANGE_START\tdevid: %04x:%02x:%02x.%x flags: %#02x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1364,8 +1399,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_ALIAS: - DUMP_printk(" DEV_ALIAS\t\t\t devid: %04x:%02x:%02x.%x " - "flags: %02x devid_to: %02x:%02x.%x\n", + DUMP_printk(" DEV_ALIAS\t\t\tdevid: %04x:%02x:%02x.%x flags: %#02x devid_to: %02x:%02x.%x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1382,9 +1416,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_ALIAS_RANGE: - DUMP_printk(" DEV_ALIAS_RANGE\t\t " - "devid: %04x:%02x:%02x.%x flags: %02x " - "devid_to: %04x:%02x:%02x.%x\n", + DUMP_printk(" DEV_ALIAS_RANGE\t\tdevid: %04x:%02x:%02x.%x flags: %#02x devid_to: %04x:%02x:%02x.%x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1401,8 +1433,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_EXT_SELECT: - DUMP_printk(" DEV_EXT_SELECT\t\t devid: %04x:%02x:%02x.%x " - "flags: %02x ext: %08x\n", + DUMP_printk(" DEV_EXT_SELECT\t\tdevid: %04x:%02x:%02x.%x flags: %#02x ext: %08x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1414,8 +1445,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_EXT_SELECT_RANGE: - DUMP_printk(" DEV_EXT_SELECT_RANGE\t devid: " - "%04x:%02x:%02x.%x flags: %02x ext: %08x\n", + DUMP_printk(" DEV_EXT_SELECT_RANGE\tdevid: %04x:%02x:%02x.%x flags: %#02x ext: %08x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid), @@ -1428,21 +1458,18 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; case IVHD_DEV_RANGE_END: - DUMP_printk(" DEV_RANGE_END\t\t devid: %04x:%02x:%02x.%x\n", + DUMP_printk(" DEV_RANGE_END\t\tdevid: %04x:%02x:%02x.%x\n", seg_id, PCI_BUS_NUM(e->devid), PCI_SLOT(e->devid), PCI_FUNC(e->devid)); devid = e->devid; for (dev_i = devid_start; dev_i <= devid; ++dev_i) { - if (alias) { + if (alias) pci_seg->alias_table[dev_i] = devid_to; - set_dev_entry_from_acpi(iommu, - devid_to, flags, ext_flags); - } - set_dev_entry_from_acpi(iommu, dev_i, - flags, ext_flags); } + set_dev_entry_from_acpi_range(iommu, devid_start, devid, flags, ext_flags); + set_dev_entry_from_acpi(iommu, devid_to, flags, ext_flags); break; case IVHD_DEV_SPECIAL: { u8 handle, type; @@ -1461,11 +1488,12 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, else var = "UNKNOWN"; - DUMP_printk(" DEV_SPECIAL(%s[%d])\t\tdevid: %04x:%02x:%02x.%x\n", + DUMP_printk(" DEV_SPECIAL(%s[%d])\t\tdevid: %04x:%02x:%02x.%x, flags: %#02x\n", var, (int)handle, seg_id, PCI_BUS_NUM(devid), PCI_SLOT(devid), - PCI_FUNC(devid)); + PCI_FUNC(devid), + e->flags); ret = add_special_device(type, handle, &devid, false); if (ret) @@ -1525,11 +1553,12 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, } devid = PCI_SEG_DEVID_TO_SBDF(seg_id, e->devid); - DUMP_printk(" DEV_ACPI_HID(%s[%s])\t\tdevid: %04x:%02x:%02x.%x\n", + DUMP_printk(" DEV_ACPI_HID(%s[%s])\t\tdevid: %04x:%02x:%02x.%x, flags: %#02x\n", hid, uid, seg_id, PCI_BUS_NUM(devid), PCI_SLOT(devid), - PCI_FUNC(devid)); + PCI_FUNC(devid), + e->flags); flags = e->flags; @@ -1757,13 +1786,8 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h, else iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET; - /* - * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports. - * GAM also requires GA mode. Therefore, we need to - * check cmpxchg16b support before enabling it. - */ - if (!boot_cpu_has(X86_FEATURE_CX16) || - ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0)) + /* GAM requires GA mode. */ + if ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0) amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; break; case 0x11: @@ -1773,13 +1797,8 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h, else iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET; - /* - * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports. - * XT, GAM also requires GA mode. Therefore, we need to - * check cmpxchg16b support before enabling them. - */ - if (!boot_cpu_has(X86_FEATURE_CX16) || - ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) { + /* XT and GAM require GA mode. */ + if ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0) { amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; break; } @@ -2145,7 +2164,7 @@ static void print_iommu_info(void) if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) pr_info("X2APIC enabled\n"); } - if (amd_iommu_pgtable == AMD_IOMMU_V2) { + if (amd_iommu_pgtable == PD_MODE_V2) { pr_info("V2 page table enabled (Paging mode : %d level)\n", amd_iommu_gpt_level); } @@ -2332,7 +2351,7 @@ static struct irq_chip intcapxt_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_set_affinity = intcapxt_set_affinity, .irq_set_wake = intcapxt_set_wake, - .flags = IRQCHIP_MASK_ON_SUSPEND, + .flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_MOVE_DEFERRED, }; static const struct irq_domain_ops intcapxt_domain_ops = { @@ -2575,9 +2594,9 @@ static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg) return; for (devid = 0; devid <= pci_seg->last_bdf; ++devid) { - __set_dev_entry_bit(dev_table, devid, DEV_ENTRY_VALID); + set_dte_bit(&dev_table[devid], DEV_ENTRY_VALID); if (!amd_iommu_snp_en) - __set_dev_entry_bit(dev_table, devid, DEV_ENTRY_TRANSLATION); + set_dte_bit(&dev_table[devid], DEV_ENTRY_TRANSLATION); } } @@ -2605,8 +2624,7 @@ static void init_device_table(void) for_each_pci_segment(pci_seg) { for (devid = 0; devid <= pci_seg->last_bdf; ++devid) - __set_dev_entry_bit(pci_seg->dev_table, - devid, DEV_ENTRY_IRQ_TBL_EN); + set_dte_bit(&pci_seg->dev_table[devid], DEV_ENTRY_IRQ_TBL_EN); } } @@ -3033,6 +3051,11 @@ static int __init early_amd_iommu_init(void) return -EINVAL; } + if (!boot_cpu_has(X86_FEATURE_CX16)) { + pr_err("Failed to initialize. The CMPXCHG16B feature is required.\n"); + return -EINVAL; + } + /* * Validate checksum here so we don't need to do it when * we actually parse the table @@ -3059,10 +3082,10 @@ static int __init early_amd_iommu_init(void) FIELD_GET(FEATURE_GATS, amd_iommu_efr) == GUEST_PGTABLE_5_LEVEL) amd_iommu_gpt_level = PAGE_MODE_5_LEVEL; - if (amd_iommu_pgtable == AMD_IOMMU_V2) { + if (amd_iommu_pgtable == PD_MODE_V2) { if (!amd_iommu_v2_pgtbl_supported()) { pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n"); - amd_iommu_pgtable = AMD_IOMMU_V1; + amd_iommu_pgtable = PD_MODE_V1; } } @@ -3185,7 +3208,7 @@ static void iommu_snp_enable(void) goto disable_snp; } - if (amd_iommu_pgtable != AMD_IOMMU_V1) { + if (amd_iommu_pgtable != PD_MODE_V1) { pr_warn("SNP: IOMMU is configured with V2 page table mode, SNP cannot be supported.\n"); goto disable_snp; } @@ -3398,25 +3421,23 @@ static bool amd_iommu_sme_check(void) * IOMMUs * ****************************************************************************/ -int __init amd_iommu_detect(void) +void __init amd_iommu_detect(void) { int ret; if (no_iommu || (iommu_detected && !gart_iommu_aperture)) - return -ENODEV; + return; if (!amd_iommu_sme_check()) - return -ENODEV; + return; ret = iommu_go_to_state(IOMMU_IVRS_DETECTED); if (ret) - return ret; + return; amd_iommu_detected = true; iommu_detected = 1; x86_init.iommu.iommu_init = amd_iommu_init; - - return 1; } /**************************************************************************** @@ -3464,9 +3485,9 @@ static int __init parse_amd_iommu_options(char *str) } else if (strncmp(str, "force_isolation", 15) == 0) { amd_iommu_force_isolation = true; } else if (strncmp(str, "pgtbl_v1", 8) == 0) { - amd_iommu_pgtable = AMD_IOMMU_V1; + amd_iommu_pgtable = PD_MODE_V1; } else if (strncmp(str, "pgtbl_v2", 8) == 0) { - amd_iommu_pgtable = AMD_IOMMU_V2; + amd_iommu_pgtable = PD_MODE_V2; } else if (strncmp(str, "irtcachedis", 11) == 0) { amd_iommu_irtcachedis = true; } else if (strncmp(str, "nohugepages", 11) == 0) { diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 16f40b8000d7..b48a72bd7b23 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -83,12 +83,142 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, static void set_dte_entry(struct amd_iommu *iommu, struct iommu_dev_data *dev_data); +static void iommu_flush_dte_sync(struct amd_iommu *iommu, u16 devid); + +static struct iommu_dev_data *find_dev_data(struct amd_iommu *iommu, u16 devid); + /**************************************************************************** * * Helper functions * ****************************************************************************/ +static __always_inline void amd_iommu_atomic128_set(__int128 *ptr, __int128 val) +{ + /* + * Note: + * We use arch_cmpxchg128_local() because: + * - Need cmpxchg16b instruction mainly for 128-bit store to DTE + * (not necessary for cmpxchg since this function is already + * protected by a spin_lock for this DTE). + * - Neither need LOCK_PREFIX nor try loop because of the spin_lock. + */ + arch_cmpxchg128_local(ptr, *ptr, val); +} + +static void write_dte_upper128(struct dev_table_entry *ptr, struct dev_table_entry *new) +{ + struct dev_table_entry old; + + old.data128[1] = ptr->data128[1]; + /* + * Preserve DTE_DATA2_INTR_MASK. This needs to be + * done here since it requires to be inside + * spin_lock(&dev_data->dte_lock) context. + */ + new->data[2] &= ~DTE_DATA2_INTR_MASK; + new->data[2] |= old.data[2] & DTE_DATA2_INTR_MASK; + + amd_iommu_atomic128_set(&ptr->data128[1], new->data128[1]); +} + +static void write_dte_lower128(struct dev_table_entry *ptr, struct dev_table_entry *new) +{ + amd_iommu_atomic128_set(&ptr->data128[0], new->data128[0]); +} + +/* + * Note: + * IOMMU reads the entire Device Table entry in a single 256-bit transaction + * but the driver is programming DTE using 2 128-bit cmpxchg. So, the driver + * need to ensure the following: + * - DTE[V|GV] bit is being written last when setting. + * - DTE[V|GV] bit is being written first when clearing. + * + * This function is used only by code, which updates DMA translation part of the DTE. + * So, only consider control bits related to DMA when updating the entry. + */ +static void update_dte256(struct amd_iommu *iommu, struct iommu_dev_data *dev_data, + struct dev_table_entry *new) +{ + unsigned long flags; + struct dev_table_entry *dev_table = get_dev_table(iommu); + struct dev_table_entry *ptr = &dev_table[dev_data->devid]; + + spin_lock_irqsave(&dev_data->dte_lock, flags); + + if (!(ptr->data[0] & DTE_FLAG_V)) { + /* Existing DTE is not valid. */ + write_dte_upper128(ptr, new); + write_dte_lower128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else if (!(new->data[0] & DTE_FLAG_V)) { + /* Existing DTE is valid. New DTE is not valid. */ + write_dte_lower128(ptr, new); + write_dte_upper128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else if (!FIELD_GET(DTE_FLAG_GV, ptr->data[0])) { + /* + * Both DTEs are valid. + * Existing DTE has no guest page table. + */ + write_dte_upper128(ptr, new); + write_dte_lower128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else if (!FIELD_GET(DTE_FLAG_GV, new->data[0])) { + /* + * Both DTEs are valid. + * Existing DTE has guest page table, + * new DTE has no guest page table, + */ + write_dte_lower128(ptr, new); + write_dte_upper128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else if (FIELD_GET(DTE_GPT_LEVEL_MASK, ptr->data[2]) != + FIELD_GET(DTE_GPT_LEVEL_MASK, new->data[2])) { + /* + * Both DTEs are valid and have guest page table, + * but have different number of levels. So, we need + * to upadte both upper and lower 128-bit value, which + * require disabling and flushing. + */ + struct dev_table_entry clear = {}; + + /* First disable DTE */ + write_dte_lower128(ptr, &clear); + iommu_flush_dte_sync(iommu, dev_data->devid); + + /* Then update DTE */ + write_dte_upper128(ptr, new); + write_dte_lower128(ptr, new); + iommu_flush_dte_sync(iommu, dev_data->devid); + } else { + /* + * Both DTEs are valid and have guest page table, + * and same number of levels. We just need to only + * update the lower 128-bit. So no need to disable DTE. + */ + write_dte_lower128(ptr, new); + } + + spin_unlock_irqrestore(&dev_data->dte_lock, flags); +} + +static void get_dte256(struct amd_iommu *iommu, struct iommu_dev_data *dev_data, + struct dev_table_entry *dte) +{ + unsigned long flags; + struct dev_table_entry *ptr; + struct dev_table_entry *dev_table = get_dev_table(iommu); + + ptr = &dev_table[dev_data->devid]; + + spin_lock_irqsave(&dev_data->dte_lock, flags); + dte->data128[0] = ptr->data128[0]; + dte->data128[1] = ptr->data128[1]; + spin_unlock_irqrestore(&dev_data->dte_lock, flags); +} + static inline bool pdom_is_v2_pgtbl_mode(struct protection_domain *pdom) { return (pdom && (pdom->pd_mode == PD_MODE_V2)); @@ -209,6 +339,7 @@ static struct iommu_dev_data *alloc_dev_data(struct amd_iommu *iommu, u16 devid) return NULL; mutex_init(&dev_data->mutex); + spin_lock_init(&dev_data->dte_lock); dev_data->devid = devid; ratelimit_default_init(&dev_data->rs); @@ -216,7 +347,7 @@ static struct iommu_dev_data *alloc_dev_data(struct amd_iommu *iommu, u16 devid) return dev_data; } -static struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid) +struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid) { struct iommu_dev_data *dev_data; struct llist_node *node; @@ -236,9 +367,11 @@ static struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid static int clone_alias(struct pci_dev *pdev, u16 alias, void *data) { + struct dev_table_entry new; struct amd_iommu *iommu; - struct dev_table_entry *dev_table; + struct iommu_dev_data *dev_data, *alias_data; u16 devid = pci_dev_id(pdev); + int ret = 0; if (devid == alias) return 0; @@ -247,13 +380,27 @@ static int clone_alias(struct pci_dev *pdev, u16 alias, void *data) if (!iommu) return 0; - amd_iommu_set_rlookup_table(iommu, alias); - dev_table = get_dev_table(iommu); - memcpy(dev_table[alias].data, - dev_table[devid].data, - sizeof(dev_table[alias].data)); + /* Copy the data from pdev */ + dev_data = dev_iommu_priv_get(&pdev->dev); + if (!dev_data) { + pr_err("%s : Failed to get dev_data for 0x%x\n", __func__, devid); + ret = -EINVAL; + goto out; + } + get_dte256(iommu, dev_data, &new); - return 0; + /* Setup alias */ + alias_data = find_dev_data(iommu, alias); + if (!alias_data) { + pr_err("%s : Failed to get alias dev_data for 0x%x\n", __func__, alias); + ret = -EINVAL; + goto out; + } + update_dte256(iommu, alias_data, &new); + + amd_iommu_set_rlookup_table(iommu, alias); +out: + return ret; } static void clone_aliases(struct amd_iommu *iommu, struct device *dev) @@ -526,6 +673,12 @@ static int iommu_init_device(struct amd_iommu *iommu, struct device *dev) return -ENOMEM; dev_data->dev = dev; + + /* + * The dev_iommu_priv_set() needes to be called before setup_aliases. + * Otherwise, subsequent call to dev_iommu_priv_get() will fail. + */ + dev_iommu_priv_set(dev, dev_data); setup_aliases(iommu, dev); /* @@ -539,8 +692,6 @@ static int iommu_init_device(struct amd_iommu *iommu, struct device *dev) dev_data->flags = pdev_get_caps(to_pci_dev(dev)); } - dev_iommu_priv_set(dev, dev_data); - return 0; } @@ -571,10 +722,13 @@ static void iommu_ignore_device(struct amd_iommu *iommu, struct device *dev) static void dump_dte_entry(struct amd_iommu *iommu, u16 devid) { int i; - struct dev_table_entry *dev_table = get_dev_table(iommu); + struct dev_table_entry dte; + struct iommu_dev_data *dev_data = find_dev_data(iommu, devid); + + get_dte256(iommu, dev_data, &dte); for (i = 0; i < 4; ++i) - pr_err("DTE[%d]: %016llx\n", i, dev_table[devid].data[i]); + pr_err("DTE[%d]: %016llx\n", i, dte.data[i]); } static void dump_command(unsigned long phys_addr) @@ -1261,6 +1415,15 @@ static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid) return iommu_queue_command(iommu, &cmd); } +static void iommu_flush_dte_sync(struct amd_iommu *iommu, u16 devid) +{ + int ret; + + ret = iommu_flush_dte(iommu, devid); + if (!ret) + iommu_completion_wait(iommu); +} + static void amd_iommu_flush_dte_all(struct amd_iommu *iommu) { u32 devid; @@ -1603,15 +1766,6 @@ void amd_iommu_update_and_flush_device_table(struct protection_domain *domain) domain_flush_complete(domain); } -void amd_iommu_domain_update(struct protection_domain *domain) -{ - /* Update device table */ - amd_iommu_update_and_flush_device_table(domain); - - /* Flush domain TLB(s) and wait for completion */ - amd_iommu_domain_flush_all(domain); -} - int amd_iommu_complete_ppr(struct device *dev, u32 pasid, int status, int tag) { struct iommu_dev_data *dev_data; @@ -1826,90 +1980,109 @@ int amd_iommu_clear_gcr3(struct iommu_dev_data *dev_data, ioasid_t pasid) return ret; } +static void make_clear_dte(struct iommu_dev_data *dev_data, struct dev_table_entry *ptr, + struct dev_table_entry *new) +{ + /* All existing DTE must have V bit set */ + new->data128[0] = DTE_FLAG_V; + new->data128[1] = 0; +} + +/* + * Note: + * The old value for GCR3 table and GPT have been cleared from caller. + */ +static void set_dte_gcr3_table(struct amd_iommu *iommu, + struct iommu_dev_data *dev_data, + struct dev_table_entry *target) +{ + struct gcr3_tbl_info *gcr3_info = &dev_data->gcr3_info; + u64 gcr3; + + if (!gcr3_info->gcr3_tbl) + return; + + pr_debug("%s: devid=%#x, glx=%#x, gcr3_tbl=%#llx\n", + __func__, dev_data->devid, gcr3_info->glx, + (unsigned long long)gcr3_info->gcr3_tbl); + + gcr3 = iommu_virt_to_phys(gcr3_info->gcr3_tbl); + + target->data[0] |= DTE_FLAG_GV | + FIELD_PREP(DTE_GLX, gcr3_info->glx) | + FIELD_PREP(DTE_GCR3_14_12, gcr3 >> 12); + if (pdom_is_v2_pgtbl_mode(dev_data->domain)) + target->data[0] |= DTE_FLAG_GIOV; + + target->data[1] |= FIELD_PREP(DTE_GCR3_30_15, gcr3 >> 15) | + FIELD_PREP(DTE_GCR3_51_31, gcr3 >> 31); + + /* Guest page table can only support 4 and 5 levels */ + if (amd_iommu_gpt_level == PAGE_MODE_5_LEVEL) + target->data[2] |= FIELD_PREP(DTE_GPT_LEVEL_MASK, GUEST_PGTABLE_5_LEVEL); + else + target->data[2] |= FIELD_PREP(DTE_GPT_LEVEL_MASK, GUEST_PGTABLE_4_LEVEL); +} + static void set_dte_entry(struct amd_iommu *iommu, struct iommu_dev_data *dev_data) { - u64 pte_root = 0; - u64 flags = 0; - u32 old_domid; - u16 devid = dev_data->devid; u16 domid; + u32 old_domid; + struct dev_table_entry *initial_dte; + struct dev_table_entry new = {}; struct protection_domain *domain = dev_data->domain; - struct dev_table_entry *dev_table = get_dev_table(iommu); struct gcr3_tbl_info *gcr3_info = &dev_data->gcr3_info; + struct dev_table_entry *dte = &get_dev_table(iommu)[dev_data->devid]; if (gcr3_info && gcr3_info->gcr3_tbl) domid = dev_data->gcr3_info.domid; else domid = domain->id; - if (domain->iop.mode != PAGE_MODE_NONE) - pte_root = iommu_virt_to_phys(domain->iop.root); + make_clear_dte(dev_data, dte, &new); - pte_root |= (domain->iop.mode & DEV_ENTRY_MODE_MASK) + if (domain->iop.mode != PAGE_MODE_NONE) + new.data[0] = iommu_virt_to_phys(domain->iop.root); + + new.data[0] |= (domain->iop.mode & DEV_ENTRY_MODE_MASK) << DEV_ENTRY_MODE_SHIFT; - pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V; + new.data[0] |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V; /* - * When SNP is enabled, Only set TV bit when IOMMU - * page translation is in use. + * When SNP is enabled, we can only support TV=1 with non-zero domain ID. + * This is prevented by the SNP-enable and IOMMU_DOMAIN_IDENTITY check in + * do_iommu_domain_alloc(). */ - if (!amd_iommu_snp_en || (domid != 0)) - pte_root |= DTE_FLAG_TV; - - flags = dev_table[devid].data[1]; - - if (dev_data->ats_enabled) - flags |= DTE_FLAG_IOTLB; + WARN_ON(amd_iommu_snp_en && (domid == 0)); + new.data[0] |= DTE_FLAG_TV; if (dev_data->ppr) - pte_root |= 1ULL << DEV_ENTRY_PPR; + new.data[0] |= 1ULL << DEV_ENTRY_PPR; if (domain->dirty_tracking) - pte_root |= DTE_FLAG_HAD; + new.data[0] |= DTE_FLAG_HAD; - if (gcr3_info && gcr3_info->gcr3_tbl) { - u64 gcr3 = iommu_virt_to_phys(gcr3_info->gcr3_tbl); - u64 glx = gcr3_info->glx; - u64 tmp; + if (dev_data->ats_enabled) + new.data[1] |= DTE_FLAG_IOTLB; - pte_root |= DTE_FLAG_GV; - pte_root |= (glx & DTE_GLX_MASK) << DTE_GLX_SHIFT; + old_domid = READ_ONCE(dte->data[1]) & DEV_DOMID_MASK; + new.data[1] |= domid; - /* First mask out possible old values for GCR3 table */ - tmp = DTE_GCR3_VAL_B(~0ULL) << DTE_GCR3_SHIFT_B; - flags &= ~tmp; - - tmp = DTE_GCR3_VAL_C(~0ULL) << DTE_GCR3_SHIFT_C; - flags &= ~tmp; - - /* Encode GCR3 table into DTE */ - tmp = DTE_GCR3_VAL_A(gcr3) << DTE_GCR3_SHIFT_A; - pte_root |= tmp; - - tmp = DTE_GCR3_VAL_B(gcr3) << DTE_GCR3_SHIFT_B; - flags |= tmp; - - tmp = DTE_GCR3_VAL_C(gcr3) << DTE_GCR3_SHIFT_C; - flags |= tmp; - - if (amd_iommu_gpt_level == PAGE_MODE_5_LEVEL) { - dev_table[devid].data[2] |= - ((u64)GUEST_PGTABLE_5_LEVEL << DTE_GPT_LEVEL_SHIFT); - } - - /* GIOV is supported with V2 page table mode only */ - if (pdom_is_v2_pgtbl_mode(domain)) - pte_root |= DTE_FLAG_GIOV; + /* + * Restore cached persistent DTE bits, which can be set by information + * in IVRS table. See set_dev_entry_from_acpi(). + */ + initial_dte = amd_iommu_get_ivhd_dte_flags(iommu->pci_seg->id, dev_data->devid); + if (initial_dte) { + new.data128[0] |= initial_dte->data128[0]; + new.data128[1] |= initial_dte->data128[1]; } - flags &= ~DEV_DOMID_MASK; - flags |= domid; + set_dte_gcr3_table(iommu, dev_data, &new); - old_domid = dev_table[devid].data[1] & DEV_DOMID_MASK; - dev_table[devid].data[1] = flags; - dev_table[devid].data[0] = pte_root; + update_dte256(iommu, dev_data, &new); /* * A kdump kernel might be replacing a domain ID that was copied from @@ -1921,19 +2094,16 @@ static void set_dte_entry(struct amd_iommu *iommu, } } -static void clear_dte_entry(struct amd_iommu *iommu, u16 devid) +/* + * Clear DMA-remap related flags to block all DMA (blockeded domain) + */ +static void clear_dte_entry(struct amd_iommu *iommu, struct iommu_dev_data *dev_data) { - struct dev_table_entry *dev_table = get_dev_table(iommu); + struct dev_table_entry new = {}; + struct dev_table_entry *dte = &get_dev_table(iommu)[dev_data->devid]; - /* remove entry from the device table seen by the hardware */ - dev_table[devid].data[0] = DTE_FLAG_V; - - if (!amd_iommu_snp_en) - dev_table[devid].data[0] |= DTE_FLAG_TV; - - dev_table[devid].data[1] &= DTE_FLAG_MASK; - - amd_iommu_apply_erratum_63(iommu, devid); + make_clear_dte(dev_data, dte, &new); + update_dte256(iommu, dev_data, &new); } /* Update and flush DTE for the given device */ @@ -1944,7 +2114,7 @@ static void dev_update_dte(struct iommu_dev_data *dev_data, bool set) if (set) set_dte_entry(iommu, dev_data); else - clear_dte_entry(iommu, dev_data->devid); + clear_dte_entry(iommu, dev_data); clone_aliases(iommu, dev_data->dev); device_flush_dte(dev_data); @@ -2007,7 +2177,6 @@ static int pdom_attach_iommu(struct amd_iommu *iommu, struct protection_domain *pdom) { struct pdom_iommu_info *pdom_iommu_info, *curr; - struct io_pgtable_cfg *cfg = &pdom->iop.pgtbl.cfg; unsigned long flags; int ret = 0; @@ -2036,10 +2205,6 @@ static int pdom_attach_iommu(struct amd_iommu *iommu, goto out_unlock; } - /* Update NUMA Node ID */ - if (cfg->amd.nid == NUMA_NO_NODE) - cfg->amd.nid = dev_to_node(&iommu->dev->dev); - out_unlock: spin_unlock_irqrestore(&pdom->lock, flags); return ret; @@ -2276,16 +2441,15 @@ void protection_domain_free(struct protection_domain *domain) kfree(domain); } -static void protection_domain_init(struct protection_domain *domain, int nid) +static void protection_domain_init(struct protection_domain *domain) { spin_lock_init(&domain->lock); INIT_LIST_HEAD(&domain->dev_list); INIT_LIST_HEAD(&domain->dev_data_list); xa_init(&domain->iommu_array); - domain->iop.pgtbl.cfg.amd.nid = nid; } -struct protection_domain *protection_domain_alloc(unsigned int type, int nid) +struct protection_domain *protection_domain_alloc(void) { struct protection_domain *domain; int domid; @@ -2301,42 +2465,37 @@ struct protection_domain *protection_domain_alloc(unsigned int type, int nid) } domain->id = domid; - protection_domain_init(domain, nid); + protection_domain_init(domain); return domain; } static int pdom_setup_pgtable(struct protection_domain *domain, - unsigned int type, int pgtable) + struct device *dev) { struct io_pgtable_ops *pgtbl_ops; + enum io_pgtable_fmt fmt; - /* No need to allocate io pgtable ops in passthrough mode */ - if (!(type & __IOMMU_DOMAIN_PAGING)) - return 0; - - switch (pgtable) { - case AMD_IOMMU_V1: - domain->pd_mode = PD_MODE_V1; + switch (domain->pd_mode) { + case PD_MODE_V1: + fmt = AMD_IOMMU_V1; break; - case AMD_IOMMU_V2: - domain->pd_mode = PD_MODE_V2; + case PD_MODE_V2: + fmt = AMD_IOMMU_V2; break; - default: - return -EINVAL; } - pgtbl_ops = - alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl.cfg, domain); + domain->iop.pgtbl.cfg.amd.nid = dev_to_node(dev); + pgtbl_ops = alloc_io_pgtable_ops(fmt, &domain->iop.pgtbl.cfg, domain); if (!pgtbl_ops) return -ENOMEM; return 0; } -static inline u64 dma_max_address(int pgtable) +static inline u64 dma_max_address(enum protection_domain_mode pgtable) { - if (pgtable == AMD_IOMMU_V1) + if (pgtable == PD_MODE_V1) return ~0ULL; /* V2 with 4/5 level page table */ @@ -2348,31 +2507,21 @@ static bool amd_iommu_hd_support(struct amd_iommu *iommu) return iommu && (iommu->features & FEATURE_HDSUP); } -static struct iommu_domain *do_iommu_domain_alloc(unsigned int type, - struct device *dev, - u32 flags, int pgtable) +static struct iommu_domain * +do_iommu_domain_alloc(struct device *dev, u32 flags, + enum protection_domain_mode pgtable) { bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING; + struct amd_iommu *iommu = get_amd_iommu_from_dev(dev); struct protection_domain *domain; - struct amd_iommu *iommu = NULL; int ret; - if (dev) - iommu = get_amd_iommu_from_dev(dev); - - /* - * Since DTE[Mode]=0 is prohibited on SNP-enabled system, - * default to use IOMMU_DOMAIN_DMA[_FQ]. - */ - if (amd_iommu_snp_en && (type == IOMMU_DOMAIN_IDENTITY)) - return ERR_PTR(-EINVAL); - - domain = protection_domain_alloc(type, - dev ? dev_to_node(dev) : NUMA_NO_NODE); + domain = protection_domain_alloc(); if (!domain) return ERR_PTR(-ENOMEM); - ret = pdom_setup_pgtable(domain, type, pgtable); + domain->pd_mode = pgtable; + ret = pdom_setup_pgtable(domain, dev); if (ret) { pdom_id_free(domain->id); kfree(domain); @@ -2384,72 +2533,45 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type, domain->domain.geometry.force_aperture = true; domain->domain.pgsize_bitmap = domain->iop.pgtbl.cfg.pgsize_bitmap; - if (iommu) { - domain->domain.type = type; - domain->domain.ops = iommu->iommu.ops->default_domain_ops; + domain->domain.type = IOMMU_DOMAIN_UNMANAGED; + domain->domain.ops = iommu->iommu.ops->default_domain_ops; - if (dirty_tracking) - domain->domain.dirty_ops = &amd_dirty_ops; - } + if (dirty_tracking) + domain->domain.dirty_ops = &amd_dirty_ops; return &domain->domain; } -static struct iommu_domain *amd_iommu_domain_alloc(unsigned int type) -{ - struct iommu_domain *domain; - int pgtable = amd_iommu_pgtable; - - /* - * Force IOMMU v1 page table when allocating - * domain for pass-through devices. - */ - if (type == IOMMU_DOMAIN_UNMANAGED) - pgtable = AMD_IOMMU_V1; - - domain = do_iommu_domain_alloc(type, NULL, 0, pgtable); - if (IS_ERR(domain)) - return NULL; - - return domain; -} - static struct iommu_domain * amd_iommu_domain_alloc_paging_flags(struct device *dev, u32 flags, const struct iommu_user_data *user_data) { - unsigned int type = IOMMU_DOMAIN_UNMANAGED; - struct amd_iommu *iommu = NULL; + struct amd_iommu *iommu = get_amd_iommu_from_dev(dev); const u32 supported_flags = IOMMU_HWPT_ALLOC_DIRTY_TRACKING | IOMMU_HWPT_ALLOC_PASID; - if (dev) - iommu = get_amd_iommu_from_dev(dev); - if ((flags & ~supported_flags) || user_data) return ERR_PTR(-EOPNOTSUPP); - /* Allocate domain with v2 page table if IOMMU supports PASID. */ - if (flags & IOMMU_HWPT_ALLOC_PASID) { + switch (flags & supported_flags) { + case IOMMU_HWPT_ALLOC_DIRTY_TRACKING: + /* Allocate domain with v1 page table for dirty tracking */ + if (!amd_iommu_hd_support(iommu)) + break; + return do_iommu_domain_alloc(dev, flags, PD_MODE_V1); + case IOMMU_HWPT_ALLOC_PASID: + /* Allocate domain with v2 page table if IOMMU supports PASID. */ if (!amd_iommu_pasid_supported()) - return ERR_PTR(-EOPNOTSUPP); - - return do_iommu_domain_alloc(type, dev, flags, AMD_IOMMU_V2); + break; + return do_iommu_domain_alloc(dev, flags, PD_MODE_V2); + case 0: + /* If nothing specific is required use the kernel commandline default */ + return do_iommu_domain_alloc(dev, 0, amd_iommu_pgtable); + default: + break; } - - /* Allocate domain with v1 page table for dirty tracking */ - if (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) { - if (iommu && amd_iommu_hd_support(iommu)) { - return do_iommu_domain_alloc(type, dev, - flags, AMD_IOMMU_V1); - } - - return ERR_PTR(-EOPNOTSUPP); - } - - /* If nothing specific is required use the kernel commandline default */ - return do_iommu_domain_alloc(type, dev, 0, amd_iommu_pgtable); + return ERR_PTR(-EOPNOTSUPP); } void amd_iommu_domain_free(struct iommu_domain *dom) @@ -2475,10 +2597,19 @@ static int blocked_domain_attach_device(struct iommu_domain *domain, return 0; } +static int blocked_domain_set_dev_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid, + struct iommu_domain *old) +{ + amd_iommu_remove_dev_pasid(dev, pasid, old); + return 0; +} + static struct iommu_domain blocked_domain = { .type = IOMMU_DOMAIN_BLOCKED, .ops = &(const struct iommu_domain_ops) { .attach_dev = blocked_domain_attach_device, + .set_dev_pasid = blocked_domain_set_dev_pasid, } }; @@ -2498,7 +2629,7 @@ void amd_iommu_init_identity_domain(void) identity_domain.id = pdom_id_alloc(); - protection_domain_init(&identity_domain, NUMA_NO_NODE); + protection_domain_init(&identity_domain); } /* Same as blocked domain except it supports only ops->attach_dev() */ @@ -2666,12 +2797,12 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain, bool enable) { struct protection_domain *pdomain = to_pdomain(domain); - struct dev_table_entry *dev_table; + struct dev_table_entry *dte; struct iommu_dev_data *dev_data; bool domain_flush = false; struct amd_iommu *iommu; unsigned long flags; - u64 pte_root; + u64 new; spin_lock_irqsave(&pdomain->lock, flags); if (!(pdomain->dirty_tracking ^ enable)) { @@ -2680,16 +2811,15 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain, } list_for_each_entry(dev_data, &pdomain->dev_list, list) { + spin_lock(&dev_data->dte_lock); iommu = get_amd_iommu_from_dev_data(dev_data); - - dev_table = get_dev_table(iommu); - pte_root = dev_table[dev_data->devid].data[0]; - - pte_root = (enable ? pte_root | DTE_FLAG_HAD : - pte_root & ~DTE_FLAG_HAD); + dte = &get_dev_table(iommu)[dev_data->devid]; + new = dte->data[0]; + new = (enable ? new | DTE_FLAG_HAD : new & ~DTE_FLAG_HAD); + dte->data[0] = new; + spin_unlock(&dev_data->dte_lock); /* Flush device DTE */ - dev_table[dev_data->devid].data[0] = pte_root; device_flush_dte(dev_data); domain_flush = true; } @@ -2890,7 +3020,6 @@ const struct iommu_ops amd_iommu_ops = { .blocked_domain = &blocked_domain, .release_domain = &release_domain, .identity_domain = &identity_domain.domain, - .domain_alloc = amd_iommu_domain_alloc, .domain_alloc_paging_flags = amd_iommu_domain_alloc_paging_flags, .domain_alloc_sva = amd_iommu_domain_alloc_sva, .probe_device = amd_iommu_probe_device, @@ -2901,7 +3030,6 @@ const struct iommu_ops amd_iommu_ops = { .def_domain_type = amd_iommu_def_domain_type, .dev_enable_feat = amd_iommu_dev_enable_feature, .dev_disable_feat = amd_iommu_dev_disable_feature, - .remove_dev_pasid = amd_iommu_remove_dev_pasid, .page_response = amd_iommu_page_response, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = amd_iommu_attach_device, @@ -2956,17 +3084,23 @@ out: static void set_dte_irq_entry(struct amd_iommu *iommu, u16 devid, struct irq_remap_table *table) { - u64 dte; - struct dev_table_entry *dev_table = get_dev_table(iommu); + u64 new; + struct dev_table_entry *dte = &get_dev_table(iommu)[devid]; + struct iommu_dev_data *dev_data = search_dev_data(iommu, devid); - dte = dev_table[devid].data[2]; - dte &= ~DTE_IRQ_PHYS_ADDR_MASK; - dte |= iommu_virt_to_phys(table->table); - dte |= DTE_IRQ_REMAP_INTCTL; - dte |= DTE_INTTABLEN; - dte |= DTE_IRQ_REMAP_ENABLE; + if (dev_data) + spin_lock(&dev_data->dte_lock); - dev_table[devid].data[2] = dte; + new = READ_ONCE(dte->data[2]); + new &= ~DTE_IRQ_PHYS_ADDR_MASK; + new |= iommu_virt_to_phys(table->table); + new |= DTE_IRQ_REMAP_INTCTL; + new |= DTE_INTTABLEN; + new |= DTE_IRQ_REMAP_ENABLE; + WRITE_ONCE(dte->data[2], new); + + if (dev_data) + spin_unlock(&dev_data->dte_lock); } static struct irq_remap_table *get_irq_table(struct amd_iommu *iommu, u16 devid) @@ -3540,7 +3674,6 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, irq_data->chip_data = data; irq_data->chip = &amd_ir_chip; irq_remapping_prepare_irte(data, cfg, info, devid, index, i); - irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT); } return 0; diff --git a/drivers/iommu/amd/pasid.c b/drivers/iommu/amd/pasid.c index 8c73a30c2800..11150cfd6718 100644 --- a/drivers/iommu/amd/pasid.c +++ b/drivers/iommu/amd/pasid.c @@ -185,12 +185,13 @@ struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev, struct protection_domain *pdom; int ret; - pdom = protection_domain_alloc(IOMMU_DOMAIN_SVA, dev_to_node(dev)); + pdom = protection_domain_alloc(); if (!pdom) return ERR_PTR(-ENOMEM); pdom->domain.ops = &amd_sva_domain_ops; pdom->mn.ops = &sva_mn; + pdom->domain.type = IOMMU_DOMAIN_SVA; ret = mmu_notifier_register(&pdom->mn, mm); if (ret) { diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index c7cc613050d9..5aa2e7af58b4 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -178,18 +178,12 @@ arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, const struct iommu_user_data *user_data) { struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core); - const u32 SUPPORTED_FLAGS = IOMMU_HWPT_FAULT_ID_VALID; struct arm_smmu_nested_domain *nested_domain; struct iommu_hwpt_arm_smmuv3 arg; bool enable_ats = false; int ret; - /* - * Faults delivered to the nested domain are faults that originated by - * the S1 in the domain. The core code will match all PASIDs when - * delivering the fault due to user_pasid_table - */ - if (flags & ~SUPPORTED_FLAGS) + if (flags) return ERR_PTR(-EOPNOTSUPP); ret = iommu_copy_struct_from_user(&arg, user_data, diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 1d3e71569775..9ba596430e7c 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -112,6 +112,15 @@ void arm_smmu_make_sva_cd(struct arm_smmu_cd *target, * from the current CPU register */ target->data[3] = cpu_to_le64(read_sysreg(mair_el1)); + + /* + * Note that we don't bother with S1PIE on the SMMU, we just rely on + * our default encoding scheme matching direct permissions anyway. + * SMMU has no notion of S1POE nor GCS, so make sure that is clear if + * either is enabled for CPUs, just in case anyone imagines otherwise. + */ + if (system_supports_poe() || system_supports_gcs()) + dev_warn_once(master->smmu->dev, "SVA devices ignore permission overlays and GCS\n"); } EXPORT_SYMBOL_IF_KUNIT(arm_smmu_make_sva_cd); @@ -206,8 +215,12 @@ bool arm_smmu_sva_supported(struct arm_smmu_device *smmu) unsigned long asid_bits; u32 feat_mask = ARM_SMMU_FEAT_COHERENCY; - if (vabits_actual == 52) + if (vabits_actual == 52) { + /* We don't support LPA2 */ + if (PAGE_SIZE != SZ_64K) + return false; feat_mask |= ARM_SMMU_FEAT_VAX; + } if ((smmu->features & feat_mask) != feat_mask) return false; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index a5c7002ff75b..358072b4e293 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -83,8 +84,28 @@ static struct arm_smmu_option_prop arm_smmu_options[] = { { 0, NULL}, }; -static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain, - struct arm_smmu_device *smmu, u32 flags); +static const char * const event_str[] = { + [EVT_ID_BAD_STREAMID_CONFIG] = "C_BAD_STREAMID", + [EVT_ID_STE_FETCH_FAULT] = "F_STE_FETCH", + [EVT_ID_BAD_STE_CONFIG] = "C_BAD_STE", + [EVT_ID_STREAM_DISABLED_FAULT] = "F_STREAM_DISABLED", + [EVT_ID_BAD_SUBSTREAMID_CONFIG] = "C_BAD_SUBSTREAMID", + [EVT_ID_CD_FETCH_FAULT] = "F_CD_FETCH", + [EVT_ID_BAD_CD_CONFIG] = "C_BAD_CD", + [EVT_ID_TRANSLATION_FAULT] = "F_TRANSLATION", + [EVT_ID_ADDR_SIZE_FAULT] = "F_ADDR_SIZE", + [EVT_ID_ACCESS_FAULT] = "F_ACCESS", + [EVT_ID_PERMISSION_FAULT] = "F_PERMISSION", + [EVT_ID_VMS_FETCH_FAULT] = "F_VMS_FETCH", +}; + +static const char * const event_class_str[] = { + [0] = "CD fetch", + [1] = "Stage 1 translation table fetch", + [2] = "Input address caused fault", + [3] = "Reserved", +}; + static int arm_smmu_alloc_cd_tables(struct arm_smmu_master *master); static void parse_driver_options(struct arm_smmu_device *smmu) @@ -1759,17 +1780,49 @@ arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid) } /* IRQ and event handlers */ -static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt) +static void arm_smmu_decode_event(struct arm_smmu_device *smmu, u64 *raw, + struct arm_smmu_event *event) +{ + struct arm_smmu_master *master; + + event->id = FIELD_GET(EVTQ_0_ID, raw[0]); + event->sid = FIELD_GET(EVTQ_0_SID, raw[0]); + event->ssv = FIELD_GET(EVTQ_0_SSV, raw[0]); + event->ssid = event->ssv ? FIELD_GET(EVTQ_0_SSID, raw[0]) : IOMMU_NO_PASID; + event->privileged = FIELD_GET(EVTQ_1_PnU, raw[1]); + event->instruction = FIELD_GET(EVTQ_1_InD, raw[1]); + event->s2 = FIELD_GET(EVTQ_1_S2, raw[1]); + event->read = FIELD_GET(EVTQ_1_RnW, raw[1]); + event->stag = FIELD_GET(EVTQ_1_STAG, raw[1]); + event->stall = FIELD_GET(EVTQ_1_STALL, raw[1]); + event->class = FIELD_GET(EVTQ_1_CLASS, raw[1]); + event->iova = FIELD_GET(EVTQ_2_ADDR, raw[2]); + event->ipa = raw[3] & EVTQ_3_IPA; + event->fetch_addr = raw[3] & EVTQ_3_FETCH_ADDR; + event->ttrnw = FIELD_GET(EVTQ_1_TT_READ, raw[1]); + event->class_tt = false; + event->dev = NULL; + + if (event->id == EVT_ID_PERMISSION_FAULT) + event->class_tt = (event->class == EVTQ_1_CLASS_TT); + + mutex_lock(&smmu->streams_mutex); + master = arm_smmu_find_master(smmu, event->sid); + if (master) + event->dev = get_device(master->dev); + mutex_unlock(&smmu->streams_mutex); +} + +static int arm_smmu_handle_event(struct arm_smmu_device *smmu, + struct arm_smmu_event *event) { int ret = 0; u32 perm = 0; struct arm_smmu_master *master; - bool ssid_valid = evt[0] & EVTQ_0_SSV; - u32 sid = FIELD_GET(EVTQ_0_SID, evt[0]); struct iopf_fault fault_evt = { }; struct iommu_fault *flt = &fault_evt.fault; - switch (FIELD_GET(EVTQ_0_ID, evt[0])) { + switch (event->id) { case EVT_ID_TRANSLATION_FAULT: case EVT_ID_ADDR_SIZE_FAULT: case EVT_ID_ACCESS_FAULT: @@ -1779,35 +1832,35 @@ static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt) return -EOPNOTSUPP; } - if (!(evt[1] & EVTQ_1_STALL)) + if (!event->stall) return -EOPNOTSUPP; - if (evt[1] & EVTQ_1_RnW) + if (event->read) perm |= IOMMU_FAULT_PERM_READ; else perm |= IOMMU_FAULT_PERM_WRITE; - if (evt[1] & EVTQ_1_InD) + if (event->instruction) perm |= IOMMU_FAULT_PERM_EXEC; - if (evt[1] & EVTQ_1_PnU) + if (event->privileged) perm |= IOMMU_FAULT_PERM_PRIV; flt->type = IOMMU_FAULT_PAGE_REQ; flt->prm = (struct iommu_fault_page_request) { .flags = IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE, - .grpid = FIELD_GET(EVTQ_1_STAG, evt[1]), + .grpid = event->stag, .perm = perm, - .addr = FIELD_GET(EVTQ_2_ADDR, evt[2]), + .addr = event->iova, }; - if (ssid_valid) { + if (event->ssv) { flt->prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID; - flt->prm.pasid = FIELD_GET(EVTQ_0_SSID, evt[0]); + flt->prm.pasid = event->ssid; } mutex_lock(&smmu->streams_mutex); - master = arm_smmu_find_master(smmu, sid); + master = arm_smmu_find_master(smmu, event->sid); if (!master) { ret = -EINVAL; goto out_unlock; @@ -1819,29 +1872,82 @@ out_unlock: return ret; } +static void arm_smmu_dump_raw_event(struct arm_smmu_device *smmu, u64 *raw, + struct arm_smmu_event *event) +{ + int i; + + dev_err(smmu->dev, "event 0x%02x received:\n", event->id); + + for (i = 0; i < EVTQ_ENT_DWORDS; ++i) + dev_err(smmu->dev, "\t0x%016llx\n", raw[i]); +} + +#define ARM_SMMU_EVT_KNOWN(e) ((e)->id < ARRAY_SIZE(event_str) && event_str[(e)->id]) +#define ARM_SMMU_LOG_EVT_STR(e) ARM_SMMU_EVT_KNOWN(e) ? event_str[(e)->id] : "UNKNOWN" +#define ARM_SMMU_LOG_CLIENT(e) (e)->dev ? dev_name((e)->dev) : "(unassigned sid)" + +static void arm_smmu_dump_event(struct arm_smmu_device *smmu, u64 *raw, + struct arm_smmu_event *evt, + struct ratelimit_state *rs) +{ + if (!__ratelimit(rs)) + return; + + arm_smmu_dump_raw_event(smmu, raw, evt); + + switch (evt->id) { + case EVT_ID_TRANSLATION_FAULT: + case EVT_ID_ADDR_SIZE_FAULT: + case EVT_ID_ACCESS_FAULT: + case EVT_ID_PERMISSION_FAULT: + dev_err(smmu->dev, "event: %s client: %s sid: %#x ssid: %#x iova: %#llx ipa: %#llx", + ARM_SMMU_LOG_EVT_STR(evt), ARM_SMMU_LOG_CLIENT(evt), + evt->sid, evt->ssid, evt->iova, evt->ipa); + + dev_err(smmu->dev, "%s %s %s %s \"%s\"%s%s stag: %#x", + evt->privileged ? "priv" : "unpriv", + evt->instruction ? "inst" : "data", + str_read_write(evt->read), + evt->s2 ? "s2" : "s1", event_class_str[evt->class], + evt->class_tt ? (evt->ttrnw ? " ttd_read" : " ttd_write") : "", + evt->stall ? " stall" : "", evt->stag); + + break; + + case EVT_ID_STE_FETCH_FAULT: + case EVT_ID_CD_FETCH_FAULT: + case EVT_ID_VMS_FETCH_FAULT: + dev_err(smmu->dev, "event: %s client: %s sid: %#x ssid: %#x fetch_addr: %#llx", + ARM_SMMU_LOG_EVT_STR(evt), ARM_SMMU_LOG_CLIENT(evt), + evt->sid, evt->ssid, evt->fetch_addr); + + break; + + default: + dev_err(smmu->dev, "event: %s client: %s sid: %#x ssid: %#x", + ARM_SMMU_LOG_EVT_STR(evt), ARM_SMMU_LOG_CLIENT(evt), + evt->sid, evt->ssid); + } +} + static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev) { - int i, ret; + u64 evt[EVTQ_ENT_DWORDS]; + struct arm_smmu_event event = {0}; struct arm_smmu_device *smmu = dev; struct arm_smmu_queue *q = &smmu->evtq.q; struct arm_smmu_ll_queue *llq = &q->llq; static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - u64 evt[EVTQ_ENT_DWORDS]; do { while (!queue_remove_raw(q, evt)) { - u8 id = FIELD_GET(EVTQ_0_ID, evt[0]); - - ret = arm_smmu_handle_evt(smmu, evt); - if (!ret || !__ratelimit(&rs)) - continue; - - dev_info(smmu->dev, "event 0x%02x received:\n", id); - for (i = 0; i < ARRAY_SIZE(evt); ++i) - dev_info(smmu->dev, "\t0x%016llx\n", - (unsigned long long)evt[i]); + arm_smmu_decode_event(smmu, evt, &event); + if (arm_smmu_handle_event(smmu, &event)) + arm_smmu_dump_event(smmu, evt, &event, &rs); + put_device(event.dev); cond_resched(); } @@ -2353,39 +2459,12 @@ struct arm_smmu_domain *arm_smmu_domain_alloc(void) if (!smmu_domain) return ERR_PTR(-ENOMEM); - mutex_init(&smmu_domain->init_mutex); INIT_LIST_HEAD(&smmu_domain->devices); spin_lock_init(&smmu_domain->devices_lock); return smmu_domain; } -static struct iommu_domain *arm_smmu_domain_alloc_paging(struct device *dev) -{ - struct arm_smmu_domain *smmu_domain; - - /* - * Allocate the domain and initialise some of its data structures. - * We can't really do anything meaningful until we've added a - * master. - */ - smmu_domain = arm_smmu_domain_alloc(); - if (IS_ERR(smmu_domain)) - return ERR_CAST(smmu_domain); - - if (dev) { - struct arm_smmu_master *master = dev_iommu_priv_get(dev); - int ret; - - ret = arm_smmu_domain_finalise(smmu_domain, master->smmu, 0); - if (ret) { - kfree(smmu_domain); - return ERR_PTR(ret); - } - } - return &smmu_domain->domain; -} - static void arm_smmu_domain_free_paging(struct iommu_domain *domain) { struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); @@ -2451,12 +2530,6 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain, struct arm_smmu_domain *smmu_domain); bool enable_dirty = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING; - /* Restrict the stage to what we can actually support */ - if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1)) - smmu_domain->stage = ARM_SMMU_DOMAIN_S2; - if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2)) - smmu_domain->stage = ARM_SMMU_DOMAIN_S1; - pgtbl_cfg = (struct io_pgtable_cfg) { .pgsize_bitmap = smmu->pgsize_bitmap, .coherent_walk = smmu->features & ARM_SMMU_FEAT_COHERENCY, @@ -2745,9 +2818,14 @@ int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, * Translation Requests and Translated transactions are denied * as though ATS is disabled for the stream (STE.EATS == 0b00), * causing F_BAD_ATS_TREQ and F_TRANSL_FORBIDDEN events - * (IHI0070Ea 5.2 Stream Table Entry). Thus ATS can only be - * enabled if we have arm_smmu_domain, those always have page - * tables. + * (IHI0070Ea 5.2 Stream Table Entry). + * + * However, if we have installed a CD table and are using S1DSS + * then ATS will work in S1DSS bypass. See "13.6.4 Full ATS + * skipping stage 1". + * + * Disable ATS if we are going to create a normal 0b100 bypass + * STE. */ state->ats_enabled = !state->disable_ats && arm_smmu_ats_supported(master); @@ -2853,15 +2931,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) state.master = master = dev_iommu_priv_get(dev); smmu = master->smmu; - mutex_lock(&smmu_domain->init_mutex); - - if (!smmu_domain->smmu) { - ret = arm_smmu_domain_finalise(smmu_domain, smmu, 0); - } else if (smmu_domain->smmu != smmu) - ret = -EINVAL; - - mutex_unlock(&smmu_domain->init_mutex); - if (ret) + if (smmu_domain->smmu != smmu) return ret; if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) { @@ -2918,16 +2988,9 @@ static int arm_smmu_s1_set_dev_pasid(struct iommu_domain *domain, struct arm_smmu_master *master = dev_iommu_priv_get(dev); struct arm_smmu_device *smmu = master->smmu; struct arm_smmu_cd target_cd; - int ret = 0; - mutex_lock(&smmu_domain->init_mutex); - if (!smmu_domain->smmu) - ret = arm_smmu_domain_finalise(smmu_domain, smmu, 0); - else if (smmu_domain->smmu != smmu) - ret = -EINVAL; - mutex_unlock(&smmu_domain->init_mutex); - if (ret) - return ret; + if (smmu_domain->smmu != smmu) + return -EINVAL; if (smmu_domain->stage != ARM_SMMU_DOMAIN_S1) return -EINVAL; @@ -3016,13 +3079,12 @@ out_unlock: return ret; } -static void arm_smmu_remove_dev_pasid(struct device *dev, ioasid_t pasid, - struct iommu_domain *domain) +static int arm_smmu_blocking_set_dev_pasid(struct iommu_domain *new_domain, + struct device *dev, ioasid_t pasid, + struct iommu_domain *old_domain) { + struct arm_smmu_domain *smmu_domain = to_smmu_domain(old_domain); struct arm_smmu_master *master = dev_iommu_priv_get(dev); - struct arm_smmu_domain *smmu_domain; - - smmu_domain = to_smmu_domain(domain); mutex_lock(&arm_smmu_asid_lock); arm_smmu_clear_cd(master, pasid); @@ -3043,6 +3105,7 @@ static void arm_smmu_remove_dev_pasid(struct device *dev, ioasid_t pasid, sid_domain->type == IOMMU_DOMAIN_BLOCKED) sid_domain->ops->attach_dev(sid_domain, dev); } + return 0; } static void arm_smmu_attach_dev_ste(struct iommu_domain *domain, @@ -3070,8 +3133,10 @@ static void arm_smmu_attach_dev_ste(struct iommu_domain *domain, if (arm_smmu_ssids_in_use(&master->cd_table)) { /* * If a CD table has to be present then we need to run with ATS - * on even though the RID will fail ATS queries with UR. This is - * because we have no idea what the PASID's need. + * on because we have to assume a PASID is using ATS. For + * IDENTITY this will setup things so that S1DSS=bypass which + * follows the explanation in "13.6.4 Full ATS skipping stage 1" + * and allows for ATS on the RID to work. */ state.cd_needs_ats = true; arm_smmu_attach_prepare(&state, domain); @@ -3124,6 +3189,7 @@ static int arm_smmu_attach_dev_blocked(struct iommu_domain *domain, static const struct iommu_domain_ops arm_smmu_blocked_ops = { .attach_dev = arm_smmu_attach_dev_blocked, + .set_dev_pasid = arm_smmu_blocking_set_dev_pasid, }; static struct iommu_domain arm_smmu_blocked_domain = { @@ -3136,6 +3202,7 @@ arm_smmu_domain_alloc_paging_flags(struct device *dev, u32 flags, const struct iommu_user_data *user_data) { struct arm_smmu_master *master = dev_iommu_priv_get(dev); + struct arm_smmu_device *smmu = master->smmu; const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING | IOMMU_HWPT_ALLOC_PASID | IOMMU_HWPT_ALLOC_NEST_PARENT; @@ -3147,25 +3214,43 @@ arm_smmu_domain_alloc_paging_flags(struct device *dev, u32 flags, if (user_data) return ERR_PTR(-EOPNOTSUPP); - if (flags & IOMMU_HWPT_ALLOC_PASID) - return arm_smmu_domain_alloc_paging(dev); - smmu_domain = arm_smmu_domain_alloc(); if (IS_ERR(smmu_domain)) return ERR_CAST(smmu_domain); - if (flags & IOMMU_HWPT_ALLOC_NEST_PARENT) { - if (!(master->smmu->features & ARM_SMMU_FEAT_NESTING)) { + switch (flags) { + case 0: + /* Prefer S1 if available */ + if (smmu->features & ARM_SMMU_FEAT_TRANS_S1) + smmu_domain->stage = ARM_SMMU_DOMAIN_S1; + else + smmu_domain->stage = ARM_SMMU_DOMAIN_S2; + break; + case IOMMU_HWPT_ALLOC_NEST_PARENT: + if (!(smmu->features & ARM_SMMU_FEAT_NESTING)) { ret = -EOPNOTSUPP; goto err_free; } smmu_domain->stage = ARM_SMMU_DOMAIN_S2; smmu_domain->nest_parent = true; + break; + case IOMMU_HWPT_ALLOC_DIRTY_TRACKING: + case IOMMU_HWPT_ALLOC_DIRTY_TRACKING | IOMMU_HWPT_ALLOC_PASID: + case IOMMU_HWPT_ALLOC_PASID: + if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1)) { + ret = -EOPNOTSUPP; + goto err_free; + } + smmu_domain->stage = ARM_SMMU_DOMAIN_S1; + break; + default: + ret = -EOPNOTSUPP; + goto err_free; } smmu_domain->domain.type = IOMMU_DOMAIN_UNMANAGED; smmu_domain->domain.ops = arm_smmu_ops.default_domain_ops; - ret = arm_smmu_domain_finalise(smmu_domain, master->smmu, flags); + ret = arm_smmu_domain_finalise(smmu_domain, smmu, flags); if (ret) goto err_free; return &smmu_domain->domain; @@ -3237,8 +3322,8 @@ static struct platform_driver arm_smmu_driver; static struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode) { - struct device *dev = driver_find_device_by_fwnode(&arm_smmu_driver.driver, - fwnode); + struct device *dev = bus_find_device_by_fwnode(&platform_bus_type, fwnode); + put_device(dev); return dev ? dev_get_drvdata(dev) : NULL; } @@ -3543,7 +3628,6 @@ static struct iommu_ops arm_smmu_ops = { .blocked_domain = &arm_smmu_blocked_domain, .capable = arm_smmu_capable, .hw_info = arm_smmu_hw_info, - .domain_alloc_paging = arm_smmu_domain_alloc_paging, .domain_alloc_sva = arm_smmu_sva_domain_alloc, .domain_alloc_paging_flags = arm_smmu_domain_alloc_paging_flags, .probe_device = arm_smmu_probe_device, @@ -3551,7 +3635,6 @@ static struct iommu_ops arm_smmu_ops = { .device_group = arm_smmu_device_group, .of_xlate = arm_smmu_of_xlate, .get_resv_regions = arm_smmu_get_resv_regions, - .remove_dev_pasid = arm_smmu_remove_dev_pasid, .dev_enable_feat = arm_smmu_dev_enable_feature, .dev_disable_feat = arm_smmu_dev_disable_feature, .page_response = arm_smmu_page_response, @@ -4239,7 +4322,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) */ if (!!(reg & IDR0_COHACC) != coherent) dev_warn(smmu->dev, "IDR0.COHACC overridden by FW configuration (%s)\n", - coherent ? "true" : "false"); + str_true_false(coherent)); switch (FIELD_GET(IDR0_STALL_MODEL, reg)) { case IDR0_STALL_MODEL_FORCE: @@ -4663,7 +4746,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev) /* Initialise in-memory data structures */ ret = arm_smmu_init_structures(smmu); if (ret) - return ret; + goto err_free_iopf; /* Record our private device structure */ platform_set_drvdata(pdev, smmu); @@ -4674,22 +4757,29 @@ static int arm_smmu_device_probe(struct platform_device *pdev) /* Reset the device */ ret = arm_smmu_device_reset(smmu); if (ret) - return ret; + goto err_disable; /* And we're up. Go go go! */ ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL, "smmu3.%pa", &ioaddr); if (ret) - return ret; + goto err_disable; ret = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev); if (ret) { dev_err(dev, "Failed to register iommu\n"); - iommu_device_sysfs_remove(&smmu->iommu); - return ret; + goto err_free_sysfs; } return 0; + +err_free_sysfs: + iommu_device_sysfs_remove(&smmu->iommu); +err_disable: + arm_smmu_device_disable(smmu); +err_free_iopf: + iopf_queue_free(smmu->evtq.iopf); + return ret; } static void arm_smmu_device_remove(struct platform_device *pdev) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 0107d3f333a1..bd9d7c85576a 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -452,10 +452,18 @@ static inline unsigned int arm_smmu_cdtab_l2_idx(unsigned int ssid) #define EVTQ_0_ID GENMASK_ULL(7, 0) +#define EVT_ID_BAD_STREAMID_CONFIG 0x02 +#define EVT_ID_STE_FETCH_FAULT 0x03 +#define EVT_ID_BAD_STE_CONFIG 0x04 +#define EVT_ID_STREAM_DISABLED_FAULT 0x06 +#define EVT_ID_BAD_SUBSTREAMID_CONFIG 0x08 +#define EVT_ID_CD_FETCH_FAULT 0x09 +#define EVT_ID_BAD_CD_CONFIG 0x0a #define EVT_ID_TRANSLATION_FAULT 0x10 #define EVT_ID_ADDR_SIZE_FAULT 0x11 #define EVT_ID_ACCESS_FAULT 0x12 #define EVT_ID_PERMISSION_FAULT 0x13 +#define EVT_ID_VMS_FETCH_FAULT 0x25 #define EVTQ_0_SSV (1UL << 11) #define EVTQ_0_SSID GENMASK_ULL(31, 12) @@ -467,9 +475,11 @@ static inline unsigned int arm_smmu_cdtab_l2_idx(unsigned int ssid) #define EVTQ_1_RnW (1UL << 35) #define EVTQ_1_S2 (1UL << 39) #define EVTQ_1_CLASS GENMASK_ULL(41, 40) +#define EVTQ_1_CLASS_TT 0x01 #define EVTQ_1_TT_READ (1UL << 44) #define EVTQ_2_ADDR GENMASK_ULL(63, 0) #define EVTQ_3_IPA GENMASK_ULL(51, 12) +#define EVTQ_3_FETCH_ADDR GENMASK_ULL(51, 3) /* PRI queue */ #define PRIQ_ENT_SZ_SHIFT 4 @@ -789,6 +799,26 @@ struct arm_smmu_stream { struct rb_node node; }; +struct arm_smmu_event { + u8 stall : 1, + ssv : 1, + privileged : 1, + instruction : 1, + s2 : 1, + read : 1, + ttrnw : 1, + class_tt : 1; + u8 id; + u8 class; + u16 stag; + u32 sid; + u32 ssid; + u64 iova; + u64 ipa; + u64 fetch_addr; + struct device *dev; +}; + /* SMMU private data for each master */ struct arm_smmu_master { struct arm_smmu_device *smmu; @@ -813,7 +843,6 @@ enum arm_smmu_domain_stage { struct arm_smmu_domain { struct arm_smmu_device *smmu; - struct mutex init_mutex; /* Protects smmu pointer */ struct io_pgtable_ops *pgtbl_ops; atomic_t nr_ats_masters; diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index 6e41ddaa24d6..d525ab43a4ae 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -79,7 +79,6 @@ #define TEGRA241_VCMDQ_PAGE1(q) (TEGRA241_VCMDQ_PAGE1_BASE + 0x80*(q)) #define VCMDQ_ADDR GENMASK(47, 5) #define VCMDQ_LOG2SIZE GENMASK(4, 0) -#define VCMDQ_LOG2SIZE_MAX 19 #define TEGRA241_VCMDQ_BASE 0x00000 #define TEGRA241_VCMDQ_CONS_INDX_BASE 0x00008 @@ -505,12 +504,15 @@ static int tegra241_vcmdq_alloc_smmu_cmdq(struct tegra241_vcmdq *vcmdq) struct arm_smmu_cmdq *cmdq = &vcmdq->cmdq; struct arm_smmu_queue *q = &cmdq->q; char name[16]; + u32 regval; int ret; snprintf(name, 16, "vcmdq%u", vcmdq->idx); - /* Queue size, capped to ensure natural alignment */ - q->llq.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT, VCMDQ_LOG2SIZE_MAX); + /* Cap queue size to SMMU's IDR1.CMDQS and ensure natural alignment */ + regval = readl_relaxed(smmu->base + ARM_SMMU_IDR1); + q->llq.max_n_shift = + min_t(u32, CMDQ_MAX_SZ_SHIFT, FIELD_GET(IDR1_CMDQS, regval)); /* Use the common helper to init the VCMDQ, and then... */ ret = arm_smmu_init_one_queue(smmu, q, vcmdq->page0, diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c index 99030e6b16e7..db9b9a8e139c 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c @@ -110,7 +110,6 @@ static struct arm_smmu_device *cavium_smmu_impl_init(struct arm_smmu_device *smm int arm_mmu500_reset(struct arm_smmu_device *smmu) { u32 reg, major; - int i; /* * On MMU-500 r2p0 onwards we need to clear ACR.CACHE_LOCK before * writes to the context bank ACTLRs will stick. And we just hope that @@ -128,11 +127,12 @@ int arm_mmu500_reset(struct arm_smmu_device *smmu) reg |= ARM_MMU500_ACR_SMTNMB_TLBEN | ARM_MMU500_ACR_S2CRB_TLBEN; arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sACR, reg); +#ifdef CONFIG_ARM_SMMU_MMU_500_CPRE_ERRATA /* * Disable MMU-500's not-particularly-beneficial next-page * prefetcher for the sake of at least 5 known errata. */ - for (i = 0; i < smmu->num_context_banks; ++i) { + for (int i = 0; i < smmu->num_context_banks; ++i) { reg = arm_smmu_cb_read(smmu, i, ARM_SMMU_CB_ACTLR); reg &= ~ARM_MMU500_ACTLR_CPRE; arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_ACTLR, reg); @@ -140,6 +140,7 @@ int arm_mmu500_reset(struct arm_smmu_device *smmu) if (reg & ARM_MMU500_ACTLR_CPRE) dev_warn_once(smmu->dev, "Failed to disable prefetcher for errata workarounds, check SACR.CACHE_LOCK\n"); } +#endif return 0; } diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c index 548783f3f8e8..d03b2239baad 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c @@ -73,7 +73,7 @@ void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu) if (__ratelimit(&rs)) { dev_err(smmu->dev, "TLB sync timed out -- SMMU may be deadlocked\n"); - cfg = qsmmu->cfg; + cfg = qsmmu->data->cfg; if (!cfg) return; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index 6372f3e25c4b..59d02687280e 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -16,6 +16,40 @@ #define QCOM_DUMMY_VAL -1 +/* + * SMMU-500 TRM defines BIT(0) as CMTLB (Enable context caching in the + * macro TLB) and BIT(1) as CPRE (Enable context caching in the prefetch + * buffer). The remaining bits are implementation defined and vary across + * SoCs. + */ + +#define CPRE (1 << 1) +#define CMTLB (1 << 0) +#define PREFETCH_SHIFT 8 +#define PREFETCH_DEFAULT 0 +#define PREFETCH_SHALLOW (1 << PREFETCH_SHIFT) +#define PREFETCH_MODERATE (2 << PREFETCH_SHIFT) +#define PREFETCH_DEEP (3 << PREFETCH_SHIFT) +#define GFX_ACTLR_PRR (1 << 5) + +static const struct of_device_id qcom_smmu_actlr_client_of_match[] = { + { .compatible = "qcom,adreno", + .data = (const void *) (PREFETCH_DEEP | CPRE | CMTLB) }, + { .compatible = "qcom,adreno-gmu", + .data = (const void *) (PREFETCH_DEEP | CPRE | CMTLB) }, + { .compatible = "qcom,adreno-smmu", + .data = (const void *) (PREFETCH_DEEP | CPRE | CMTLB) }, + { .compatible = "qcom,fastrpc", + .data = (const void *) (PREFETCH_DEEP | CPRE | CMTLB) }, + { .compatible = "qcom,sc7280-mdss", + .data = (const void *) (PREFETCH_SHALLOW | CPRE | CMTLB) }, + { .compatible = "qcom,sc7280-venus", + .data = (const void *) (PREFETCH_SHALLOW | CPRE | CMTLB) }, + { .compatible = "qcom,sm8550-mdss", + .data = (const void *) (PREFETCH_DEFAULT | CMTLB) }, + { } +}; + static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu) { return container_of(smmu, struct qcom_smmu, smmu); @@ -99,6 +133,47 @@ static void qcom_adreno_smmu_resume_translation(const void *cookie, bool termina arm_smmu_cb_write(smmu, cfg->cbndx, ARM_SMMU_CB_RESUME, reg); } +static void qcom_adreno_smmu_set_prr_bit(const void *cookie, bool set) +{ + struct arm_smmu_domain *smmu_domain = (void *)cookie; + struct arm_smmu_device *smmu = smmu_domain->smmu; + struct arm_smmu_cfg *cfg = &smmu_domain->cfg; + u32 reg = 0; + int ret; + + ret = pm_runtime_resume_and_get(smmu->dev); + if (ret < 0) { + dev_err(smmu->dev, "failed to get runtime PM: %d\n", ret); + return; + } + + reg = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_ACTLR); + reg &= ~GFX_ACTLR_PRR; + if (set) + reg |= FIELD_PREP(GFX_ACTLR_PRR, 1); + arm_smmu_cb_write(smmu, cfg->cbndx, ARM_SMMU_CB_ACTLR, reg); + pm_runtime_put_autosuspend(smmu->dev); +} + +static void qcom_adreno_smmu_set_prr_addr(const void *cookie, phys_addr_t page_addr) +{ + struct arm_smmu_domain *smmu_domain = (void *)cookie; + struct arm_smmu_device *smmu = smmu_domain->smmu; + int ret; + + ret = pm_runtime_resume_and_get(smmu->dev); + if (ret < 0) { + dev_err(smmu->dev, "failed to get runtime PM: %d\n", ret); + return; + } + + writel_relaxed(lower_32_bits(page_addr), + smmu->base + ARM_SMMU_GFX_PRR_CFG_LADDR); + writel_relaxed(upper_32_bits(page_addr), + smmu->base + ARM_SMMU_GFX_PRR_CFG_UADDR); + pm_runtime_put_autosuspend(smmu->dev); +} + #define QCOM_ADRENO_SMMU_GPU_SID 0 static bool qcom_adreno_smmu_is_gpu_device(struct device *dev) @@ -207,13 +282,37 @@ static bool qcom_adreno_can_do_ttbr1(struct arm_smmu_device *smmu) return true; } +static void qcom_smmu_set_actlr_dev(struct device *dev, struct arm_smmu_device *smmu, int cbndx, + const struct of_device_id *client_match) +{ + const struct of_device_id *match = + of_match_device(client_match, dev); + + if (!match) { + dev_dbg(dev, "no ACTLR settings present\n"); + return; + } + + arm_smmu_cb_write(smmu, cbndx, ARM_SMMU_CB_ACTLR, (unsigned long)match->data); +} + static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain, struct io_pgtable_cfg *pgtbl_cfg, struct device *dev) { + const struct device_node *np = smmu_domain->smmu->dev->of_node; + struct arm_smmu_device *smmu = smmu_domain->smmu; + struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + const struct of_device_id *client_match; + int cbndx = smmu_domain->cfg.cbndx; struct adreno_smmu_priv *priv; smmu_domain->cfg.flush_walk_prefer_tlbiasid = true; + client_match = qsmmu->data->client_match; + + if (client_match) + qcom_smmu_set_actlr_dev(dev, smmu, cbndx, client_match); + /* Only enable split pagetables for the GPU device (SID 0) */ if (!qcom_adreno_smmu_is_gpu_device(dev)) return 0; @@ -239,6 +338,14 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain, priv->get_fault_info = qcom_adreno_smmu_get_fault_info; priv->set_stall = qcom_adreno_smmu_set_stall; priv->resume_translation = qcom_adreno_smmu_resume_translation; + priv->set_prr_bit = NULL; + priv->set_prr_addr = NULL; + + if (of_device_is_compatible(np, "qcom,smmu-500") && + of_device_is_compatible(np, "qcom,adreno-smmu")) { + priv->set_prr_bit = qcom_adreno_smmu_set_prr_bit; + priv->set_prr_addr = qcom_adreno_smmu_set_prr_addr; + } return 0; } @@ -269,8 +376,18 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = { static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain, struct io_pgtable_cfg *pgtbl_cfg, struct device *dev) { + struct arm_smmu_device *smmu = smmu_domain->smmu; + struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + const struct of_device_id *client_match; + int cbndx = smmu_domain->cfg.cbndx; + smmu_domain->cfg.flush_walk_prefer_tlbiasid = true; + client_match = qsmmu->data->client_match; + + if (client_match) + qcom_smmu_set_actlr_dev(dev, smmu, cbndx, client_match); + return 0; } @@ -507,7 +624,7 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu, return ERR_PTR(-ENOMEM); qsmmu->smmu.impl = impl; - qsmmu->cfg = data->cfg; + qsmmu->data = data; return &qsmmu->smmu; } @@ -550,6 +667,7 @@ static const struct qcom_smmu_match_data qcom_smmu_500_impl0_data = { .impl = &qcom_smmu_500_impl, .adreno_impl = &qcom_adreno_smmu_500_impl, .cfg = &qcom_smmu_impl0_cfg, + .client_match = qcom_smmu_actlr_client_of_match, }; /* @@ -567,6 +685,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = { { .compatible = "qcom,sc8180x-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8280xp-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sdm630-smmu-v2", .data = &qcom_smmu_v2_data }, + { .compatible = "qcom,sdm670-smmu-v2", .data = &qcom_smmu_v2_data }, { .compatible = "qcom,sdm845-smmu-v2", .data = &qcom_smmu_v2_data }, { .compatible = "qcom,sdm845-smmu-500", .data = &sdm845_smmu_500_data }, { .compatible = "qcom,sm6115-smmu-500", .data = &qcom_smmu_500_impl0_data}, diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h index 3c134d1a6277..8addd453f5f1 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h @@ -8,7 +8,7 @@ struct qcom_smmu { struct arm_smmu_device smmu; - const struct qcom_smmu_config *cfg; + const struct qcom_smmu_match_data *data; bool bypass_quirk; u8 bypass_cbndx; u32 stall_enabled; @@ -28,6 +28,7 @@ struct qcom_smmu_match_data { const struct qcom_smmu_config *cfg; const struct arm_smmu_impl *impl; const struct arm_smmu_impl *adreno_impl; + const struct of_device_id * const client_match; }; irqreturn_t qcom_smmu_context_fault(int irq, void *dev); diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 650664e0f6e3..de205a34ffc6 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -34,6 +34,7 @@ #include #include #include +#include #include @@ -1411,8 +1412,8 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap) static struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode) { - struct device *dev = driver_find_device_by_fwnode(&arm_smmu_driver.driver, - fwnode); + struct device *dev = bus_find_device_by_fwnode(&platform_bus_type, fwnode); + put_device(dev); return dev ? dev_get_drvdata(dev) : NULL; } @@ -1437,17 +1438,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev) goto out_free; } else { smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode); - - /* - * Defer probe if the relevant SMMU instance hasn't finished - * probing yet. This is a fragile hack and we'd ideally - * avoid this race in the core code. Until that's ironed - * out, however, this is the most pragmatic option on the - * table. - */ - if (!smmu) - return ERR_PTR(dev_err_probe(dev, -EPROBE_DEFER, - "smmu dev has not bound yet\n")); } ret = -EINVAL; @@ -2117,7 +2107,7 @@ static void arm_smmu_rmr_install_bypass_smr(struct arm_smmu_device *smmu) } dev_notice(smmu->dev, "\tpreserved %d boot mapping%s\n", cnt, - cnt == 1 ? "" : "s"); + str_plural(cnt)); iort_put_rmr_sids(dev_fwnode(smmu->dev), &rmr_list); } @@ -2227,21 +2217,6 @@ static int arm_smmu_device_probe(struct platform_device *pdev) i, irq); } - err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL, - "smmu.%pa", &smmu->ioaddr); - if (err) { - dev_err(dev, "Failed to register iommu in sysfs\n"); - return err; - } - - err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, - using_legacy_binding ? NULL : dev); - if (err) { - dev_err(dev, "Failed to register iommu\n"); - iommu_device_sysfs_remove(&smmu->iommu); - return err; - } - platform_set_drvdata(pdev, smmu); /* Check for RMRs and install bypass SMRs if any */ @@ -2250,6 +2225,18 @@ static int arm_smmu_device_probe(struct platform_device *pdev) arm_smmu_device_reset(smmu); arm_smmu_test_smr_masks(smmu); + err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL, + "smmu.%pa", &smmu->ioaddr); + if (err) + return dev_err_probe(dev, err, "Failed to register iommu in sysfs\n"); + + err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, + using_legacy_binding ? NULL : dev); + if (err) { + iommu_device_sysfs_remove(&smmu->iommu); + return dev_err_probe(dev, err, "Failed to register iommu\n"); + } + /* * We want to avoid touching dev->power.lock in fastpaths unless * it's really going to do something useful - pm_runtime_enabled() diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h index e2aeb511ae90..2dbf3243b5ad 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h @@ -154,6 +154,8 @@ enum arm_smmu_cbar_type { #define ARM_SMMU_SCTLR_M BIT(0) #define ARM_SMMU_CB_ACTLR 0x4 +#define ARM_SMMU_GFX_PRR_CFG_LADDR 0x6008 +#define ARM_SMMU_GFX_PRR_CFG_UADDR 0x600C #define ARM_SMMU_CB_RESUME 0x8 #define ARM_SMMU_RESUME_TERMINATE BIT(0) diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index 8a5c17b97310..2a86aa5d54c6 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -164,8 +164,8 @@ static int __init hyperv_prepare_irq_remapping(void) * max cpu affinity for IOAPIC irqs. Scan cpu 0-255 and set cpu * into ioapic_max_cpumask if its APIC ID is less than 256. */ - for (i = min_t(unsigned int, num_possible_cpus() - 1, 255); i >= 0; i--) - if (cpu_physical_id(i) < 256) + for (i = min_t(unsigned int, nr_cpu_ids - 1, 255); i >= 0; i--) + if (cpu_possible(i) && cpu_physical_id(i) < 256) cpumask_set_cpu(i, &ioapic_max_cpumask); return 0; diff --git a/drivers/iommu/intel/Makefile b/drivers/iommu/intel/Makefile index d3bb0798092d..6c7528130cf9 100644 --- a/drivers/iommu/intel/Makefile +++ b/drivers/iommu/intel/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DMAR_TABLE) += dmar.o obj-$(CONFIG_INTEL_IOMMU) += iommu.o pasid.o nested.o cache.o prq.o -obj-$(CONFIG_DMAR_TABLE) += trace.o cap_audit.o +obj-$(CONFIG_DMAR_TABLE) += trace.o obj-$(CONFIG_DMAR_PERF) += perf.o obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o obj-$(CONFIG_INTEL_IOMMU_SVM) += svm.o diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c index 09694cca8752..fc35cba59145 100644 --- a/drivers/iommu/intel/cache.c +++ b/drivers/iommu/intel/cache.c @@ -47,6 +47,7 @@ static int cache_tag_assign(struct dmar_domain *domain, u16 did, struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu = info->iommu; struct cache_tag *tag, *temp; + struct list_head *prev; unsigned long flags; tag = kzalloc(sizeof(*tag), GFP_KERNEL); @@ -65,6 +66,7 @@ static int cache_tag_assign(struct dmar_domain *domain, u16 did, tag->dev = iommu->iommu.dev; spin_lock_irqsave(&domain->cache_lock, flags); + prev = &domain->cache_tags; list_for_each_entry(temp, &domain->cache_tags, node) { if (cache_tage_match(temp, did, iommu, dev, pasid, type)) { temp->users++; @@ -73,8 +75,15 @@ static int cache_tag_assign(struct dmar_domain *domain, u16 did, trace_cache_tag_assign(temp); return 0; } + if (temp->iommu == iommu) + prev = &temp->node; } - list_add_tail(&tag->node, &domain->cache_tags); + /* + * Link cache tags of same iommu unit together, so corresponding + * flush ops can be batched for iommu unit. + */ + list_add(&tag->node, prev); + spin_unlock_irqrestore(&domain->cache_lock, flags); trace_cache_tag_assign(tag); diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c deleted file mode 100644 index 9862dc20b35e..000000000000 --- a/drivers/iommu/intel/cap_audit.c +++ /dev/null @@ -1,217 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * cap_audit.c - audit iommu capabilities for boot time and hot plug - * - * Copyright (C) 2021 Intel Corporation - * - * Author: Kyung Min Park - * Lu Baolu - */ - -#define pr_fmt(fmt) "DMAR: " fmt - -#include "iommu.h" -#include "cap_audit.h" - -static u64 intel_iommu_cap_sanity; -static u64 intel_iommu_ecap_sanity; - -static inline void check_irq_capabilities(struct intel_iommu *a, - struct intel_iommu *b) -{ - CHECK_FEATURE_MISMATCH(a, b, cap, pi_support, CAP_PI_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, eim_support, ECAP_EIM_MASK); -} - -static inline void check_dmar_capabilities(struct intel_iommu *a, - struct intel_iommu *b) -{ - MINIMAL_FEATURE_IOMMU(b, cap, CAP_MAMV_MASK); - MINIMAL_FEATURE_IOMMU(b, cap, CAP_NFR_MASK); - MINIMAL_FEATURE_IOMMU(b, cap, CAP_SLLPS_MASK); - MINIMAL_FEATURE_IOMMU(b, cap, CAP_FRO_MASK); - MINIMAL_FEATURE_IOMMU(b, cap, CAP_MGAW_MASK); - MINIMAL_FEATURE_IOMMU(b, cap, CAP_SAGAW_MASK); - MINIMAL_FEATURE_IOMMU(b, cap, CAP_NDOMS_MASK); - MINIMAL_FEATURE_IOMMU(b, ecap, ECAP_PSS_MASK); - MINIMAL_FEATURE_IOMMU(b, ecap, ECAP_MHMV_MASK); - MINIMAL_FEATURE_IOMMU(b, ecap, ECAP_IRO_MASK); - - CHECK_FEATURE_MISMATCH(a, b, cap, fl5lp_support, CAP_FL5LP_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, fl1gp_support, CAP_FL1GP_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, read_drain, CAP_RD_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, write_drain, CAP_WD_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, pgsel_inv, CAP_PSI_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, zlr, CAP_ZLR_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, caching_mode, CAP_CM_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, phmr, CAP_PHMR_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, plmr, CAP_PLMR_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, rwbf, CAP_RWBF_MASK); - CHECK_FEATURE_MISMATCH(a, b, cap, afl, CAP_AFL_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, rps, ECAP_RPS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, smpwc, ECAP_SMPWC_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, flts, ECAP_FLTS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, slts, ECAP_SLTS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, nwfs, ECAP_NWFS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, slads, ECAP_SLADS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, smts, ECAP_SMTS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, pds, ECAP_PDS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, dit, ECAP_DIT_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, pasid, ECAP_PASID_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, eafs, ECAP_EAFS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, srs, ECAP_SRS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, ers, ECAP_ERS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, prs, ECAP_PRS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, nest, ECAP_NEST_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, mts, ECAP_MTS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, sc_support, ECAP_SC_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, pass_through, ECAP_PT_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, dev_iotlb_support, ECAP_DT_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, qis, ECAP_QI_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, coherent, ECAP_C_MASK); -} - -static int cap_audit_hotplug(struct intel_iommu *iommu, enum cap_audit_type type) -{ - bool mismatch = false; - u64 old_cap = intel_iommu_cap_sanity; - u64 old_ecap = intel_iommu_ecap_sanity; - - if (type == CAP_AUDIT_HOTPLUG_IRQR) { - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, pi_support, CAP_PI_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, eim_support, ECAP_EIM_MASK); - goto out; - } - - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, fl5lp_support, CAP_FL5LP_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, fl1gp_support, CAP_FL1GP_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, read_drain, CAP_RD_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, write_drain, CAP_WD_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, pgsel_inv, CAP_PSI_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, zlr, CAP_ZLR_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, caching_mode, CAP_CM_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, phmr, CAP_PHMR_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, plmr, CAP_PLMR_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, rwbf, CAP_RWBF_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, afl, CAP_AFL_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, rps, ECAP_RPS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, smpwc, ECAP_SMPWC_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, flts, ECAP_FLTS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slts, ECAP_SLTS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, nwfs, ECAP_NWFS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slads, ECAP_SLADS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, smts, ECAP_SMTS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pds, ECAP_PDS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, dit, ECAP_DIT_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pasid, ECAP_PASID_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, eafs, ECAP_EAFS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, srs, ECAP_SRS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, ers, ECAP_ERS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, prs, ECAP_PRS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, nest, ECAP_NEST_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, mts, ECAP_MTS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, sc_support, ECAP_SC_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pass_through, ECAP_PT_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, dev_iotlb_support, ECAP_DT_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, qis, ECAP_QI_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, coherent, ECAP_C_MASK); - - /* Abort hot plug if the hot plug iommu feature is smaller than global */ - MINIMAL_FEATURE_HOTPLUG(iommu, cap, max_amask_val, CAP_MAMV_MASK, mismatch); - MINIMAL_FEATURE_HOTPLUG(iommu, cap, num_fault_regs, CAP_NFR_MASK, mismatch); - MINIMAL_FEATURE_HOTPLUG(iommu, cap, super_page_val, CAP_SLLPS_MASK, mismatch); - MINIMAL_FEATURE_HOTPLUG(iommu, cap, fault_reg_offset, CAP_FRO_MASK, mismatch); - MINIMAL_FEATURE_HOTPLUG(iommu, cap, mgaw, CAP_MGAW_MASK, mismatch); - MINIMAL_FEATURE_HOTPLUG(iommu, cap, sagaw, CAP_SAGAW_MASK, mismatch); - MINIMAL_FEATURE_HOTPLUG(iommu, cap, ndoms, CAP_NDOMS_MASK, mismatch); - MINIMAL_FEATURE_HOTPLUG(iommu, ecap, pss, ECAP_PSS_MASK, mismatch); - MINIMAL_FEATURE_HOTPLUG(iommu, ecap, max_handle_mask, ECAP_MHMV_MASK, mismatch); - MINIMAL_FEATURE_HOTPLUG(iommu, ecap, iotlb_offset, ECAP_IRO_MASK, mismatch); - -out: - if (mismatch) { - intel_iommu_cap_sanity = old_cap; - intel_iommu_ecap_sanity = old_ecap; - return -EFAULT; - } - - return 0; -} - -static int cap_audit_static(struct intel_iommu *iommu, enum cap_audit_type type) -{ - struct dmar_drhd_unit *d; - struct intel_iommu *i; - int rc = 0; - - rcu_read_lock(); - if (list_empty(&dmar_drhd_units)) - goto out; - - for_each_active_iommu(i, d) { - if (!iommu) { - intel_iommu_ecap_sanity = i->ecap; - intel_iommu_cap_sanity = i->cap; - iommu = i; - continue; - } - - if (type == CAP_AUDIT_STATIC_DMAR) - check_dmar_capabilities(iommu, i); - else - check_irq_capabilities(iommu, i); - } - - /* - * If the system is sane to support scalable mode, either SL or FL - * should be sane. - */ - if (intel_cap_smts_sanity() && - !intel_cap_flts_sanity() && !intel_cap_slts_sanity()) - rc = -EOPNOTSUPP; - -out: - rcu_read_unlock(); - return rc; -} - -int intel_cap_audit(enum cap_audit_type type, struct intel_iommu *iommu) -{ - switch (type) { - case CAP_AUDIT_STATIC_DMAR: - case CAP_AUDIT_STATIC_IRQR: - return cap_audit_static(iommu, type); - case CAP_AUDIT_HOTPLUG_DMAR: - case CAP_AUDIT_HOTPLUG_IRQR: - return cap_audit_hotplug(iommu, type); - default: - break; - } - - return -EFAULT; -} - -bool intel_cap_smts_sanity(void) -{ - return ecap_smts(intel_iommu_ecap_sanity); -} - -bool intel_cap_pasid_sanity(void) -{ - return ecap_pasid(intel_iommu_ecap_sanity); -} - -bool intel_cap_nest_sanity(void) -{ - return ecap_nest(intel_iommu_ecap_sanity); -} - -bool intel_cap_flts_sanity(void) -{ - return ecap_flts(intel_iommu_ecap_sanity); -} - -bool intel_cap_slts_sanity(void) -{ - return ecap_slts(intel_iommu_ecap_sanity); -} diff --git a/drivers/iommu/intel/cap_audit.h b/drivers/iommu/intel/cap_audit.h deleted file mode 100644 index d07b75938961..000000000000 --- a/drivers/iommu/intel/cap_audit.h +++ /dev/null @@ -1,131 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * cap_audit.h - audit iommu capabilities header - * - * Copyright (C) 2021 Intel Corporation - * - * Author: Kyung Min Park - */ - -/* - * Capability Register Mask - */ -#define CAP_FL5LP_MASK BIT_ULL(60) -#define CAP_PI_MASK BIT_ULL(59) -#define CAP_FL1GP_MASK BIT_ULL(56) -#define CAP_RD_MASK BIT_ULL(55) -#define CAP_WD_MASK BIT_ULL(54) -#define CAP_MAMV_MASK GENMASK_ULL(53, 48) -#define CAP_NFR_MASK GENMASK_ULL(47, 40) -#define CAP_PSI_MASK BIT_ULL(39) -#define CAP_SLLPS_MASK GENMASK_ULL(37, 34) -#define CAP_FRO_MASK GENMASK_ULL(33, 24) -#define CAP_ZLR_MASK BIT_ULL(22) -#define CAP_MGAW_MASK GENMASK_ULL(21, 16) -#define CAP_SAGAW_MASK GENMASK_ULL(12, 8) -#define CAP_CM_MASK BIT_ULL(7) -#define CAP_PHMR_MASK BIT_ULL(6) -#define CAP_PLMR_MASK BIT_ULL(5) -#define CAP_RWBF_MASK BIT_ULL(4) -#define CAP_AFL_MASK BIT_ULL(3) -#define CAP_NDOMS_MASK GENMASK_ULL(2, 0) - -/* - * Extended Capability Register Mask - */ -#define ECAP_RPS_MASK BIT_ULL(49) -#define ECAP_SMPWC_MASK BIT_ULL(48) -#define ECAP_FLTS_MASK BIT_ULL(47) -#define ECAP_SLTS_MASK BIT_ULL(46) -#define ECAP_SLADS_MASK BIT_ULL(45) -#define ECAP_VCS_MASK BIT_ULL(44) -#define ECAP_SMTS_MASK BIT_ULL(43) -#define ECAP_PDS_MASK BIT_ULL(42) -#define ECAP_DIT_MASK BIT_ULL(41) -#define ECAP_PASID_MASK BIT_ULL(40) -#define ECAP_PSS_MASK GENMASK_ULL(39, 35) -#define ECAP_EAFS_MASK BIT_ULL(34) -#define ECAP_NWFS_MASK BIT_ULL(33) -#define ECAP_SRS_MASK BIT_ULL(31) -#define ECAP_ERS_MASK BIT_ULL(30) -#define ECAP_PRS_MASK BIT_ULL(29) -#define ECAP_NEST_MASK BIT_ULL(26) -#define ECAP_MTS_MASK BIT_ULL(25) -#define ECAP_MHMV_MASK GENMASK_ULL(23, 20) -#define ECAP_IRO_MASK GENMASK_ULL(17, 8) -#define ECAP_SC_MASK BIT_ULL(7) -#define ECAP_PT_MASK BIT_ULL(6) -#define ECAP_EIM_MASK BIT_ULL(4) -#define ECAP_DT_MASK BIT_ULL(2) -#define ECAP_QI_MASK BIT_ULL(1) -#define ECAP_C_MASK BIT_ULL(0) - -/* - * u64 intel_iommu_cap_sanity, intel_iommu_ecap_sanity will be adjusted as each - * IOMMU gets audited. - */ -#define DO_CHECK_FEATURE_MISMATCH(a, b, cap, feature, MASK) \ -do { \ - if (cap##_##feature(a) != cap##_##feature(b)) { \ - intel_iommu_##cap##_sanity &= ~(MASK); \ - pr_info("IOMMU feature %s inconsistent", #feature); \ - } \ -} while (0) - -#define CHECK_FEATURE_MISMATCH(a, b, cap, feature, MASK) \ - DO_CHECK_FEATURE_MISMATCH((a)->cap, (b)->cap, cap, feature, MASK) - -#define CHECK_FEATURE_MISMATCH_HOTPLUG(b, cap, feature, MASK) \ -do { \ - if (cap##_##feature(intel_iommu_##cap##_sanity)) \ - DO_CHECK_FEATURE_MISMATCH(intel_iommu_##cap##_sanity, \ - (b)->cap, cap, feature, MASK); \ -} while (0) - -#define MINIMAL_FEATURE_IOMMU(iommu, cap, MASK) \ -do { \ - u64 min_feature = intel_iommu_##cap##_sanity & (MASK); \ - min_feature = min_t(u64, min_feature, (iommu)->cap & (MASK)); \ - intel_iommu_##cap##_sanity = (intel_iommu_##cap##_sanity & ~(MASK)) | \ - min_feature; \ -} while (0) - -#define MINIMAL_FEATURE_HOTPLUG(iommu, cap, feature, MASK, mismatch) \ -do { \ - if ((intel_iommu_##cap##_sanity & (MASK)) > \ - (cap##_##feature((iommu)->cap))) \ - mismatch = true; \ - else \ - (iommu)->cap = ((iommu)->cap & ~(MASK)) | \ - (intel_iommu_##cap##_sanity & (MASK)); \ -} while (0) - -enum cap_audit_type { - CAP_AUDIT_STATIC_DMAR, - CAP_AUDIT_STATIC_IRQR, - CAP_AUDIT_HOTPLUG_DMAR, - CAP_AUDIT_HOTPLUG_IRQR, -}; - -bool intel_cap_smts_sanity(void); -bool intel_cap_pasid_sanity(void); -bool intel_cap_nest_sanity(void); -bool intel_cap_flts_sanity(void); -bool intel_cap_slts_sanity(void); - -static inline bool scalable_mode_support(void) -{ - return (intel_iommu_sm && intel_cap_smts_sanity()); -} - -static inline bool pasid_mode_support(void) -{ - return scalable_mode_support() && intel_cap_pasid_sanity(); -} - -static inline bool nested_mode_support(void) -{ - return scalable_mode_support() && intel_cap_nest_sanity(); -} - -int intel_cap_audit(enum cap_audit_type type, struct intel_iommu *iommu); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 79e0da9eb626..cc46098f875b 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -29,7 +29,6 @@ #include "../irq_remapping.h" #include "../iommu-pages.h" #include "pasid.h" -#include "cap_audit.h" #include "perfmon.h" #define ROOT_SIZE VTD_PAGE_SIZE @@ -2118,10 +2117,6 @@ static int __init init_dmars(void) struct intel_iommu *iommu; int ret; - ret = intel_cap_audit(CAP_AUDIT_STATIC_DMAR, NULL); - if (ret) - goto free_iommu; - for_each_iommu(iommu, drhd) { if (drhd->ignored) { iommu_disable_translation(iommu); @@ -2617,10 +2612,6 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru) struct intel_iommu *iommu = dmaru->iommu; int ret; - ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_DMAR, iommu); - if (ret) - goto out; - /* * Disable translation if already enabled prior to OS handover. */ @@ -3250,10 +3241,15 @@ static int blocking_domain_attach_dev(struct iommu_domain *domain, return 0; } +static int blocking_domain_set_dev_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid, + struct iommu_domain *old); + static struct iommu_domain blocking_domain = { .type = IOMMU_DOMAIN_BLOCKED, .ops = &(const struct iommu_domain_ops) { .attach_dev = blocking_domain_attach_dev, + .set_dev_pasid = blocking_domain_set_dev_pasid, } }; @@ -3342,8 +3338,7 @@ intel_iommu_domain_alloc_paging_flags(struct device *dev, u32 flags, bool first_stage; if (flags & - (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING - | IOMMU_HWPT_FAULT_ID_VALID))) + (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING))) return ERR_PTR(-EOPNOTSUPP); if (nested_parent && !nested_supported(iommu)) return ERR_PTR(-EOPNOTSUPP); @@ -4090,22 +4085,26 @@ void domain_remove_dev_pasid(struct iommu_domain *domain, break; } } - WARN_ON_ONCE(!dev_pasid); spin_unlock_irqrestore(&dmar_domain->lock, flags); cache_tag_unassign_domain(dmar_domain, dev, pasid); domain_detach_iommu(dmar_domain, iommu); - intel_iommu_debugfs_remove_dev_pasid(dev_pasid); - kfree(dev_pasid); + if (!WARN_ON_ONCE(!dev_pasid)) { + intel_iommu_debugfs_remove_dev_pasid(dev_pasid); + kfree(dev_pasid); + } } -static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid, - struct iommu_domain *domain) +static int blocking_domain_set_dev_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid, + struct iommu_domain *old) { struct device_domain_info *info = dev_iommu_priv_get(dev); intel_pasid_tear_down_entry(info->iommu, dev, pasid, false); - domain_remove_dev_pasid(domain, dev, pasid); + domain_remove_dev_pasid(old, dev, pasid); + + return 0; } struct dev_pasid_info * @@ -4445,21 +4444,6 @@ static struct iommu_domain identity_domain = { }, }; -static struct iommu_domain *intel_iommu_domain_alloc_paging(struct device *dev) -{ - struct device_domain_info *info = dev_iommu_priv_get(dev); - struct intel_iommu *iommu = info->iommu; - struct dmar_domain *dmar_domain; - bool first_stage; - - first_stage = first_level_by_default(iommu); - dmar_domain = paging_domain_alloc(dev, first_stage); - if (IS_ERR(dmar_domain)) - return ERR_CAST(dmar_domain); - - return &dmar_domain->domain; -} - const struct iommu_ops intel_iommu_ops = { .blocked_domain = &blocking_domain, .release_domain = &blocking_domain, @@ -4468,7 +4452,6 @@ const struct iommu_ops intel_iommu_ops = { .hw_info = intel_iommu_hw_info, .domain_alloc_paging_flags = intel_iommu_domain_alloc_paging_flags, .domain_alloc_sva = intel_svm_domain_alloc, - .domain_alloc_paging = intel_iommu_domain_alloc_paging, .domain_alloc_nested = intel_iommu_domain_alloc_nested, .probe_device = intel_iommu_probe_device, .release_device = intel_iommu_release_device, @@ -4478,7 +4461,6 @@ const struct iommu_ops intel_iommu_ops = { .dev_disable_feat = intel_iommu_dev_disable_feat, .is_attach_deferred = intel_iommu_is_attach_deferred, .def_domain_type = device_def_domain_type, - .remove_dev_pasid = intel_iommu_remove_dev_pasid, .pgsize_bitmap = SZ_4K, .page_response = intel_iommu_page_response, .default_domain_ops = &(const struct iommu_domain_ops) { diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 466c1412dd45..ad795c772f21 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -24,7 +24,6 @@ #include "iommu.h" #include "../irq_remapping.h" #include "../iommu-pages.h" -#include "cap_audit.h" enum irq_mode { IRQ_REMAPPING, @@ -727,9 +726,6 @@ static int __init intel_prepare_irq_remapping(void) if (dmar_table_init() < 0) return -ENODEV; - if (intel_cap_audit(CAP_AUDIT_STATIC_IRQR, NULL)) - return -ENODEV; - if (!dmar_ir_support()) return -ENODEV; @@ -1463,7 +1459,6 @@ static int intel_irq_remapping_alloc(struct irq_domain *domain, else irq_data->chip = &intel_ir_chip; intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i); - irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT); } return 0; @@ -1534,10 +1529,6 @@ static int dmar_ir_add(struct dmar_drhd_unit *dmaru, struct intel_iommu *iommu) int ret; int eim = x2apic_enabled(); - ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_IRQR, iommu); - if (ret) - return ret; - if (eim && !ecap_eim_support(iommu->ecap)) { pr_info("DRHD %Lx: EIM not supported by DRHD, ecap %Lx\n", iommu->reg_phys, iommu->ecap); diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 5b7d85f1e143..fb59a7d35958 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -244,11 +244,31 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev, spin_lock(&iommu->lock); pte = intel_pasid_get_entry(dev, pasid); - if (WARN_ON(!pte) || !pasid_pte_is_present(pte)) { + if (WARN_ON(!pte)) { spin_unlock(&iommu->lock); return; } + if (!pasid_pte_is_present(pte)) { + if (!pasid_pte_is_fault_disabled(pte)) { + WARN_ON(READ_ONCE(pte->val[0]) != 0); + spin_unlock(&iommu->lock); + return; + } + + /* + * When a PASID is used for SVA by a device, it's possible + * that the pasid entry is non-present with the Fault + * Processing Disabled bit set. Clear the pasid entry and + * drain the PRQ for the PASID before return. + */ + pasid_clear_entry(pte); + spin_unlock(&iommu->lock); + intel_iommu_drain_pasid_prq(dev, pasid); + + return; + } + did = pasid_get_domain_id(pte); pgtt = pasid_pte_get_pgtt(pte); intel_pasid_clear_entry(dev, pasid, fault_ignore); diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 082f4fe20216..668d8ece6b14 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -73,6 +73,12 @@ static inline bool pasid_pte_is_present(struct pasid_entry *pte) return READ_ONCE(pte->val[0]) & PASID_PTE_PRESENT; } +/* Get FPD(Fault Processing Disable) bit of a PASID table entry */ +static inline bool pasid_pte_is_fault_disabled(struct pasid_entry *pte) +{ + return READ_ONCE(pte->val[0]) & PASID_PTE_FPD; +} + /* Get PGTT field of a PASID table entry */ static inline u16 pasid_pte_get_pgtt(struct pasid_entry *pte) { diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 6b9bb58a414f..7632c80edea6 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -223,6 +223,34 @@ static inline int arm_lpae_max_entries(int i, struct arm_lpae_io_pgtable *data) return ptes_per_table - (i & (ptes_per_table - 1)); } +/* + * Check if concatenated PGDs are mandatory according to Arm DDI0487 (K.a) + * 1) R_DXBSH: For 16KB, and 48-bit input size, use level 1 instead of 0. + * 2) R_SRKBC: After de-ciphering the table for PA size and valid initial lookup + * a) 40 bits PA size with 4K: use level 1 instead of level 0 (2 tables for ias = oas) + * b) 40 bits PA size with 16K: use level 2 instead of level 1 (16 tables for ias = oas) + * c) 42 bits PA size with 4K: use level 1 instead of level 0 (8 tables for ias = oas) + * d) 48 bits PA size with 16K: use level 1 instead of level 0 (2 tables for ias = oas) + */ +static inline bool arm_lpae_concat_mandatory(struct io_pgtable_cfg *cfg, + struct arm_lpae_io_pgtable *data) +{ + unsigned int ias = cfg->ias; + unsigned int oas = cfg->oas; + + /* Covers 1 and 2.d */ + if ((ARM_LPAE_GRANULE(data) == SZ_16K) && (data->start_level == 0)) + return (oas == 48) || (ias == 48); + + /* Covers 2.a and 2.c */ + if ((ARM_LPAE_GRANULE(data) == SZ_4K) && (data->start_level == 0)) + return (oas == 40) || (oas == 42); + + /* Case 2.b */ + return (ARM_LPAE_GRANULE(data) == SZ_16K) && + (data->start_level == 1) && (oas == 40); +} + static bool selftest_running = false; static dma_addr_t __arm_lpae_dma_addr(void *pages) @@ -676,85 +704,107 @@ static size_t arm_lpae_unmap_pages(struct io_pgtable_ops *ops, unsigned long iov data->start_level, ptep); } -static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops, - unsigned long iova) -{ - struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); - arm_lpae_iopte pte, *ptep = data->pgd; - int lvl = data->start_level; - - do { - /* Valid IOPTE pointer? */ - if (!ptep) - return 0; - - /* Grab the IOPTE we're interested in */ - ptep += ARM_LPAE_LVL_IDX(iova, lvl, data); - pte = READ_ONCE(*ptep); - - /* Valid entry? */ - if (!pte) - return 0; - - /* Leaf entry? */ - if (iopte_leaf(pte, lvl, data->iop.fmt)) - goto found_translation; - - /* Take it to the next level */ - ptep = iopte_deref(pte, data); - } while (++lvl < ARM_LPAE_MAX_LEVELS); - - /* Ran out of page tables to walk */ - return 0; - -found_translation: - iova &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1); - return iopte_to_paddr(pte, data) | iova; -} - struct io_pgtable_walk_data { - struct iommu_dirty_bitmap *dirty; + struct io_pgtable *iop; + void *data; + int (*visit)(struct io_pgtable_walk_data *walk_data, int lvl, + arm_lpae_iopte *ptep, size_t size); unsigned long flags; u64 addr; const u64 end; }; -static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data, - struct io_pgtable_walk_data *walk_data, - arm_lpae_iopte *ptep, - int lvl); +static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data, + struct io_pgtable_walk_data *walk_data, + arm_lpae_iopte *ptep, + int lvl); -static int io_pgtable_visit_dirty(struct arm_lpae_io_pgtable *data, - struct io_pgtable_walk_data *walk_data, - arm_lpae_iopte *ptep, int lvl) +struct iova_to_phys_data { + arm_lpae_iopte pte; + int lvl; +}; + +static int visit_iova_to_phys(struct io_pgtable_walk_data *walk_data, int lvl, + arm_lpae_iopte *ptep, size_t size) +{ + struct iova_to_phys_data *data = walk_data->data; + data->pte = *ptep; + data->lvl = lvl; + return 0; +} + +static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops, + unsigned long iova) +{ + struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); + struct iova_to_phys_data d; + struct io_pgtable_walk_data walk_data = { + .data = &d, + .visit = visit_iova_to_phys, + .addr = iova, + .end = iova + 1, + }; + int ret; + + ret = __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level); + if (ret) + return 0; + + iova &= (ARM_LPAE_BLOCK_SIZE(d.lvl, data) - 1); + return iopte_to_paddr(d.pte, data) | iova; +} + +static int visit_pgtable_walk(struct io_pgtable_walk_data *walk_data, int lvl, + arm_lpae_iopte *ptep, size_t size) +{ + struct arm_lpae_io_pgtable_walk_data *data = walk_data->data; + data->ptes[lvl] = *ptep; + return 0; +} + +static int arm_lpae_pgtable_walk(struct io_pgtable_ops *ops, unsigned long iova, + void *wd) +{ + struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); + struct io_pgtable_walk_data walk_data = { + .data = wd, + .visit = visit_pgtable_walk, + .addr = iova, + .end = iova + 1, + }; + + return __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level); +} + +static int io_pgtable_visit(struct arm_lpae_io_pgtable *data, + struct io_pgtable_walk_data *walk_data, + arm_lpae_iopte *ptep, int lvl) { struct io_pgtable *iop = &data->iop; arm_lpae_iopte pte = READ_ONCE(*ptep); - if (iopte_leaf(pte, lvl, iop->fmt)) { - size_t size = ARM_LPAE_BLOCK_SIZE(lvl, data); + size_t size = ARM_LPAE_BLOCK_SIZE(lvl, data); + int ret = walk_data->visit(walk_data, lvl, ptep, size); + if (ret) + return ret; - if (iopte_writeable_dirty(pte)) { - iommu_dirty_bitmap_record(walk_data->dirty, - walk_data->addr, size); - if (!(walk_data->flags & IOMMU_DIRTY_NO_CLEAR)) - iopte_set_writeable_clean(ptep); - } + if (iopte_leaf(pte, lvl, iop->fmt)) { walk_data->addr += size; return 0; } - if (WARN_ON(!iopte_table(pte, lvl))) + if (!iopte_table(pte, lvl)) { return -EINVAL; + } ptep = iopte_deref(pte, data); - return __arm_lpae_iopte_walk_dirty(data, walk_data, ptep, lvl + 1); + return __arm_lpae_iopte_walk(data, walk_data, ptep, lvl + 1); } -static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data, - struct io_pgtable_walk_data *walk_data, - arm_lpae_iopte *ptep, - int lvl) +static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data, + struct io_pgtable_walk_data *walk_data, + arm_lpae_iopte *ptep, + int lvl) { u32 idx; int max_entries, ret; @@ -769,7 +819,7 @@ static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data, for (idx = ARM_LPAE_LVL_IDX(walk_data->addr, lvl, data); (idx < max_entries) && (walk_data->addr < walk_data->end); ++idx) { - ret = io_pgtable_visit_dirty(data, walk_data, ptep + idx, lvl); + ret = io_pgtable_visit(data, walk_data, ptep + idx, lvl); if (ret) return ret; } @@ -777,6 +827,23 @@ static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data, return 0; } +static int visit_dirty(struct io_pgtable_walk_data *walk_data, int lvl, + arm_lpae_iopte *ptep, size_t size) +{ + struct iommu_dirty_bitmap *dirty = walk_data->data; + + if (!iopte_leaf(*ptep, lvl, walk_data->iop->fmt)) + return 0; + + if (iopte_writeable_dirty(*ptep)) { + iommu_dirty_bitmap_record(dirty, walk_data->addr, size); + if (!(walk_data->flags & IOMMU_DIRTY_NO_CLEAR)) + iopte_set_writeable_clean(ptep); + } + + return 0; +} + static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops, unsigned long iova, size_t size, unsigned long flags, @@ -785,7 +852,9 @@ static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops, struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); struct io_pgtable_cfg *cfg = &data->iop.cfg; struct io_pgtable_walk_data walk_data = { - .dirty = dirty, + .iop = &data->iop, + .data = dirty, + .visit = visit_dirty, .flags = flags, .addr = iova, .end = iova + size, @@ -800,7 +869,7 @@ static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops, if (data->iop.fmt != ARM_64_LPAE_S1) return -EINVAL; - return __arm_lpae_iopte_walk_dirty(data, &walk_data, ptep, lvl); + return __arm_lpae_iopte_walk(data, &walk_data, ptep, lvl); } static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) @@ -882,6 +951,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg) .unmap_pages = arm_lpae_unmap_pages, .iova_to_phys = arm_lpae_iova_to_phys, .read_and_clear_dirty = arm_lpae_read_and_clear_dirty, + .pgtable_walk = arm_lpae_pgtable_walk, }; return data; @@ -1006,18 +1076,12 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) if (!data) return NULL; - /* - * Concatenate PGDs at level 1 if possible in order to reduce - * the depth of the stage-2 walk. - */ - if (data->start_level == 0) { - unsigned long pgd_pages; - - pgd_pages = ARM_LPAE_PGD_SIZE(data) / sizeof(arm_lpae_iopte); - if (pgd_pages <= ARM_LPAE_S2_MAX_CONCAT_PAGES) { - data->pgd_bits += data->bits_per_level; - data->start_level++; - } + if (arm_lpae_concat_mandatory(cfg, data)) { + if (WARN_ON((ARM_LPAE_PGD_SIZE(data) / sizeof(arm_lpae_iopte)) > + ARM_LPAE_S2_MAX_CONCAT_PAGES)) + return NULL; + data->pgd_bits += data->bits_per_level; + data->start_level++; } /* VTCR */ @@ -1364,15 +1428,14 @@ static int __init arm_lpae_do_selftests(void) SZ_64K | SZ_512M, }; - static const unsigned int ias[] __initconst = { + static const unsigned int address_size[] __initconst = { 32, 36, 40, 42, 44, 48, }; - int i, j, pass = 0, fail = 0; + int i, j, k, pass = 0, fail = 0; struct device dev; struct io_pgtable_cfg cfg = { .tlb = &dummy_tlb_ops, - .oas = 48, .coherent_walk = true, .iommu_dev = &dev, }; @@ -1381,15 +1444,19 @@ static int __init arm_lpae_do_selftests(void) set_dev_node(&dev, NUMA_NO_NODE); for (i = 0; i < ARRAY_SIZE(pgsize); ++i) { - for (j = 0; j < ARRAY_SIZE(ias); ++j) { - cfg.pgsize_bitmap = pgsize[i]; - cfg.ias = ias[j]; - pr_info("selftest: pgsize_bitmap 0x%08lx, IAS %u\n", - pgsize[i], ias[j]); - if (arm_lpae_run_tests(&cfg)) - fail++; - else - pass++; + for (j = 0; j < ARRAY_SIZE(address_size); ++j) { + /* Don't use ias > oas as it is not valid for stage-2. */ + for (k = 0; k <= j; ++k) { + cfg.pgsize_bitmap = pgsize[i]; + cfg.ias = address_size[k]; + cfg.oas = address_size[j]; + pr_info("selftest: pgsize_bitmap 0x%08lx, IAS %u OAS %u\n", + pgsize[i], cfg.ias, cfg.oas); + if (arm_lpae_run_tests(&cfg)) + fail++; + else + pass++; + } } } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 599030e1e890..870c3cdbd0f6 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2819,7 +2819,7 @@ int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode) struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); if (!ops) - return -EPROBE_DEFER; + return driver_deferred_probe_check_state(dev); if (fwspec) return ops == iommu_fwspec_ops(fwspec) ? 0 : -EINVAL; @@ -3312,6 +3312,16 @@ bool iommu_group_dma_owner_claimed(struct iommu_group *group) } EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed); +static void iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid, + struct iommu_domain *domain) +{ + const struct iommu_ops *ops = dev_iommu_ops(dev); + struct iommu_domain *blocked_domain = ops->blocked_domain; + + WARN_ON(blocked_domain->ops->set_dev_pasid(blocked_domain, + dev, pasid, domain)); +} + static int __iommu_set_group_pasid(struct iommu_domain *domain, struct iommu_group *group, ioasid_t pasid) { @@ -3330,11 +3340,9 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain, err_revert: last_gdev = device; for_each_group_device(group, device) { - const struct iommu_ops *ops = dev_iommu_ops(device->dev); - if (device == last_gdev) break; - ops->remove_dev_pasid(device->dev, pasid, domain); + iommu_remove_dev_pasid(device->dev, pasid, domain); } return ret; } @@ -3344,12 +3352,9 @@ static void __iommu_remove_group_pasid(struct iommu_group *group, struct iommu_domain *domain) { struct group_device *device; - const struct iommu_ops *ops; - for_each_group_device(group, device) { - ops = dev_iommu_ops(device->dev); - ops->remove_dev_pasid(device->dev, pasid, domain); - } + for_each_group_device(group, device) + iommu_remove_dev_pasid(device->dev, pasid, domain); } /* @@ -3368,16 +3373,20 @@ int iommu_attach_device_pasid(struct iommu_domain *domain, /* Caller must be a probed driver on dev */ struct iommu_group *group = dev->iommu_group; struct group_device *device; + const struct iommu_ops *ops; int ret; - if (!domain->ops->set_dev_pasid) - return -EOPNOTSUPP; - if (!group) return -ENODEV; - if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner || - pasid == IOMMU_NO_PASID) + ops = dev_iommu_ops(dev); + + if (!domain->ops->set_dev_pasid || + !ops->blocked_domain || + !ops->blocked_domain->ops->set_dev_pasid) + return -EOPNOTSUPP; + + if (ops != domain->owner || pasid == IOMMU_NO_PASID) return -EINVAL; mutex_lock(&group->mutex); diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c index 1fe804e28a86..d9a937450e55 100644 --- a/drivers/iommu/iommufd/fault.c +++ b/drivers/iommu/iommufd/fault.c @@ -103,15 +103,23 @@ static void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt, { struct iommufd_fault *fault = hwpt->fault; struct iopf_group *group, *next; + struct list_head free_list; unsigned long index; if (!fault) return; + INIT_LIST_HEAD(&free_list); mutex_lock(&fault->mutex); + spin_lock(&fault->lock); list_for_each_entry_safe(group, next, &fault->deliver, node) { if (group->attach_handle != &handle->handle) continue; + list_move(&group->node, &free_list); + } + spin_unlock(&fault->lock); + + list_for_each_entry_safe(group, next, &free_list, node) { list_del(&group->node); iopf_group_response(group, IOMMU_PAGE_RESP_INVALID); iopf_free_group(group); @@ -213,6 +221,7 @@ void iommufd_fault_destroy(struct iommufd_object *obj) { struct iommufd_fault *fault = container_of(obj, struct iommufd_fault, obj); struct iopf_group *group, *next; + unsigned long index; /* * The iommufd object's reference count is zero at this point. @@ -225,6 +234,13 @@ void iommufd_fault_destroy(struct iommufd_object *obj) iopf_group_response(group, IOMMU_PAGE_RESP_INVALID); iopf_free_group(group); } + xa_for_each(&fault->response, index, group) { + xa_erase(&fault->response, index); + iopf_group_response(group, IOMMU_PAGE_RESP_INVALID); + iopf_free_group(group); + } + xa_destroy(&fault->response); + mutex_destroy(&fault->mutex); } static void iommufd_compose_fault_message(struct iommu_fault *fault, @@ -247,7 +263,7 @@ static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf, { size_t fault_size = sizeof(struct iommu_hwpt_pgfault); struct iommufd_fault *fault = filep->private_data; - struct iommu_hwpt_pgfault data; + struct iommu_hwpt_pgfault data = {}; struct iommufd_device *idev; struct iopf_group *group; struct iopf_fault *iopf; @@ -258,17 +274,19 @@ static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf, return -ESPIPE; mutex_lock(&fault->mutex); - while (!list_empty(&fault->deliver) && count > done) { - group = list_first_entry(&fault->deliver, - struct iopf_group, node); - - if (group->fault_count * fault_size > count - done) + while ((group = iommufd_fault_deliver_fetch(fault))) { + if (done >= count || + group->fault_count * fault_size > count - done) { + iommufd_fault_deliver_restore(fault, group); break; + } rc = xa_alloc(&fault->response, &group->cookie, group, xa_limit_32b, GFP_KERNEL); - if (rc) + if (rc) { + iommufd_fault_deliver_restore(fault, group); break; + } idev = to_iommufd_handle(group->attach_handle)->idev; list_for_each_entry(iopf, &group->faults, list) { @@ -277,13 +295,12 @@ static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf, group->cookie); if (copy_to_user(buf + done, &data, fault_size)) { xa_erase(&fault->response, group->cookie); + iommufd_fault_deliver_restore(fault, group); rc = -EFAULT; break; } done += fault_size; } - - list_del(&group->node); } mutex_unlock(&fault->mutex); @@ -341,10 +358,10 @@ static __poll_t iommufd_fault_fops_poll(struct file *filep, __poll_t pollflags = EPOLLOUT; poll_wait(filep, &fault->wait_queue, wait); - mutex_lock(&fault->mutex); + spin_lock(&fault->lock); if (!list_empty(&fault->deliver)) pollflags |= EPOLLIN | EPOLLRDNORM; - mutex_unlock(&fault->mutex); + spin_unlock(&fault->lock); return pollflags; } @@ -386,6 +403,7 @@ int iommufd_fault_alloc(struct iommufd_ucmd *ucmd) INIT_LIST_HEAD(&fault->deliver); xa_init_flags(&fault->response, XA_FLAGS_ALLOC1); mutex_init(&fault->mutex); + spin_lock_init(&fault->lock); init_waitqueue_head(&fault->wait_queue); filep = anon_inode_getfile("[iommufd-pgfault]", &iommufd_fault_fops, @@ -434,9 +452,9 @@ int iommufd_fault_iopf_handler(struct iopf_group *group) hwpt = group->attach_handle->domain->fault_data; fault = hwpt->fault; - mutex_lock(&fault->mutex); + spin_lock(&fault->lock); list_add_tail(&group->node, &fault->deliver); - mutex_unlock(&fault->mutex); + spin_unlock(&fault->lock); wake_up_interruptible(&fault->wait_queue); diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index ce03c3804651..598be26a14e2 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -140,8 +140,8 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, hwpt_paging->nest_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT; if (ops->domain_alloc_paging_flags) { - hwpt->domain = ops->domain_alloc_paging_flags(idev->dev, flags, - user_data); + hwpt->domain = ops->domain_alloc_paging_flags(idev->dev, + flags & ~IOMMU_HWPT_FAULT_ID_VALID, user_data); if (IS_ERR(hwpt->domain)) { rc = PTR_ERR(hwpt->domain); hwpt->domain = NULL; @@ -280,6 +280,8 @@ iommufd_viommu_alloc_hwpt_nested(struct iommufd_viommu *viommu, u32 flags, struct iommufd_hw_pagetable *hwpt; int rc; + if (flags & ~IOMMU_HWPT_FAULT_ID_VALID) + return ERR_PTR(-EOPNOTSUPP); if (!user_data->len) return ERR_PTR(-EOPNOTSUPP); if (!viommu->ops || !viommu->ops->alloc_domain_nested) @@ -296,7 +298,9 @@ iommufd_viommu_alloc_hwpt_nested(struct iommufd_viommu *viommu, u32 flags, hwpt_nested->parent = viommu->hwpt; hwpt->domain = - viommu->ops->alloc_domain_nested(viommu, flags, user_data); + viommu->ops->alloc_domain_nested(viommu, + flags & ~IOMMU_HWPT_FAULT_ID_VALID, + user_data); if (IS_ERR(hwpt->domain)) { rc = PTR_ERR(hwpt->domain); hwpt->domain = NULL; diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index b6d706cf2c66..0b1bafc7fd99 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -443,14 +443,39 @@ struct iommufd_fault { struct iommufd_ctx *ictx; struct file *filep; - /* The lists of outstanding faults protected by below mutex. */ - struct mutex mutex; + spinlock_t lock; /* protects the deliver list */ struct list_head deliver; + struct mutex mutex; /* serializes response flows */ struct xarray response; struct wait_queue_head wait_queue; }; +/* Fetch the first node out of the fault->deliver list */ +static inline struct iopf_group * +iommufd_fault_deliver_fetch(struct iommufd_fault *fault) +{ + struct list_head *list = &fault->deliver; + struct iopf_group *group = NULL; + + spin_lock(&fault->lock); + if (!list_empty(list)) { + group = list_first_entry(list, struct iopf_group, node); + list_del(&group->node); + } + spin_unlock(&fault->lock); + return group; +} + +/* Restore a node back to the head of the fault->deliver list */ +static inline void iommufd_fault_deliver_restore(struct iommufd_fault *fault, + struct iopf_group *group) +{ + spin_lock(&fault->lock); + list_add(&group->node, &fault->deliver); + spin_unlock(&fault->lock); +} + struct iommufd_attach_handle { struct iommu_attach_handle handle; struct iommufd_device *idev; diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c index ab665cf38ef4..39a86a4a1d3a 100644 --- a/drivers/iommu/iommufd/iova_bitmap.c +++ b/drivers/iommu/iommufd/iova_bitmap.c @@ -130,7 +130,7 @@ struct iova_bitmap { static unsigned long iova_bitmap_offset_to_index(struct iova_bitmap *bitmap, unsigned long iova) { - unsigned long pgsize = 1 << bitmap->mapped.pgshift; + unsigned long pgsize = 1UL << bitmap->mapped.pgshift; return iova / (BITS_PER_TYPE(*bitmap->bitmap) * pgsize); } diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 97c5e3567d33..ccf616462a1c 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -104,7 +104,7 @@ static int iommufd_object_dec_wait_shortterm(struct iommufd_ctx *ictx, if (wait_event_timeout(ictx->destroy_wait, refcount_read(&to_destroy->shortterm_users) == 0, - msecs_to_jiffies(10000))) + msecs_to_jiffies(60000))) return 0; pr_crit("Time out waiting for iommufd object to become free\n"); @@ -307,9 +307,9 @@ union ucmd_buffer { struct iommu_ioas_map map; struct iommu_ioas_unmap unmap; struct iommu_option option; + struct iommu_vdevice_alloc vdev; struct iommu_vfio_ioas vfio_ioas; struct iommu_viommu_alloc viommu; - struct iommu_vdevice_alloc vdev; #ifdef CONFIG_IOMMUFD_TEST struct iommu_test_cmd test; #endif @@ -333,8 +333,8 @@ struct iommufd_ioctl_op { } static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { IOCTL_OP(IOMMU_DESTROY, iommufd_destroy, struct iommu_destroy, id), - IOCTL_OP(IOMMU_FAULT_QUEUE_ALLOC, iommufd_fault_alloc, struct iommu_fault_alloc, - out_fault_fd), + IOCTL_OP(IOMMU_FAULT_QUEUE_ALLOC, iommufd_fault_alloc, + struct iommu_fault_alloc, out_fault_fd), IOCTL_OP(IOMMU_GET_HW_INFO, iommufd_get_hw_info, struct iommu_hw_info, __reserved), IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc, @@ -355,20 +355,18 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { src_iova), IOCTL_OP(IOMMU_IOAS_IOVA_RANGES, iommufd_ioas_iova_ranges, struct iommu_ioas_iova_ranges, out_iova_alignment), - IOCTL_OP(IOMMU_IOAS_MAP, iommufd_ioas_map, struct iommu_ioas_map, - iova), + IOCTL_OP(IOMMU_IOAS_MAP, iommufd_ioas_map, struct iommu_ioas_map, iova), IOCTL_OP(IOMMU_IOAS_MAP_FILE, iommufd_ioas_map_file, struct iommu_ioas_map_file, iova), IOCTL_OP(IOMMU_IOAS_UNMAP, iommufd_ioas_unmap, struct iommu_ioas_unmap, length), - IOCTL_OP(IOMMU_OPTION, iommufd_option, struct iommu_option, - val64), + IOCTL_OP(IOMMU_OPTION, iommufd_option, struct iommu_option, val64), + IOCTL_OP(IOMMU_VDEVICE_ALLOC, iommufd_vdevice_alloc_ioctl, + struct iommu_vdevice_alloc, virt_id), IOCTL_OP(IOMMU_VFIO_IOAS, iommufd_vfio_ioas, struct iommu_vfio_ioas, __reserved), IOCTL_OP(IOMMU_VIOMMU_ALLOC, iommufd_viommu_alloc_ioctl, struct iommu_viommu_alloc, out_viommu_id), - IOCTL_OP(IOMMU_VDEVICE_ALLOC, iommufd_vdevice_alloc_ioctl, - struct iommu_vdevice_alloc, virt_id), #ifdef CONFIG_IOMMUFD_TEST IOCTL_OP(IOMMU_TEST_CMD, iommufd_test, struct iommu_test_cmd, last), #endif @@ -490,8 +488,8 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { [IOMMUFD_OBJ_DEVICE] = { .destroy = iommufd_device_destroy, }, - [IOMMUFD_OBJ_IOAS] = { - .destroy = iommufd_ioas_destroy, + [IOMMUFD_OBJ_FAULT] = { + .destroy = iommufd_fault_destroy, }, [IOMMUFD_OBJ_HWPT_PAGING] = { .destroy = iommufd_hwpt_paging_destroy, @@ -501,15 +499,15 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { .destroy = iommufd_hwpt_nested_destroy, .abort = iommufd_hwpt_nested_abort, }, - [IOMMUFD_OBJ_FAULT] = { - .destroy = iommufd_fault_destroy, - }, - [IOMMUFD_OBJ_VIOMMU] = { - .destroy = iommufd_viommu_destroy, + [IOMMUFD_OBJ_IOAS] = { + .destroy = iommufd_ioas_destroy, }, [IOMMUFD_OBJ_VDEVICE] = { .destroy = iommufd_vdevice_destroy, }, + [IOMMUFD_OBJ_VIOMMU] = { + .destroy = iommufd_viommu_destroy, + }, #ifdef CONFIG_IOMMUFD_TEST [IOMMUFD_OBJ_SELFTEST] = { .destroy = iommufd_selftest_destroy, diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index a0de6d6d4e68..d40deb0a4f06 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -311,25 +311,6 @@ static const struct iommu_dirty_ops dirty_ops = { .read_and_clear_dirty = mock_domain_read_and_clear_dirty, }; -static struct iommu_domain *mock_domain_alloc_paging(struct device *dev) -{ - struct mock_dev *mdev = to_mock_dev(dev); - struct mock_iommu_domain *mock; - - mock = kzalloc(sizeof(*mock), GFP_KERNEL); - if (!mock) - return NULL; - mock->domain.geometry.aperture_start = MOCK_APERTURE_START; - mock->domain.geometry.aperture_end = MOCK_APERTURE_LAST; - mock->domain.pgsize_bitmap = MOCK_IO_PAGE_SIZE; - if (dev && mdev->flags & MOCK_FLAGS_DEVICE_HUGE_IOVA) - mock->domain.pgsize_bitmap |= MOCK_HUGE_PAGE_SIZE; - mock->domain.ops = mock_ops.default_domain_ops; - mock->domain.type = IOMMU_DOMAIN_UNMANAGED; - xa_init(&mock->pfns); - return &mock->domain; -} - static struct mock_iommu_domain_nested * __mock_domain_alloc_nested(const struct iommu_user_data *user_data) { @@ -385,21 +366,30 @@ mock_domain_alloc_paging_flags(struct device *dev, u32 flags, bool has_dirty_flag = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING; const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING | IOMMU_HWPT_ALLOC_NEST_PARENT; - bool no_dirty_ops = to_mock_dev(dev)->flags & - MOCK_FLAGS_DEVICE_NO_DIRTY; - struct iommu_domain *domain; + struct mock_dev *mdev = to_mock_dev(dev); + bool no_dirty_ops = mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY; + struct mock_iommu_domain *mock; if (user_data) return ERR_PTR(-EOPNOTSUPP); if ((flags & ~PAGING_FLAGS) || (has_dirty_flag && no_dirty_ops)) return ERR_PTR(-EOPNOTSUPP); - domain = mock_domain_alloc_paging(dev); - if (!domain) + mock = kzalloc(sizeof(*mock), GFP_KERNEL); + if (!mock) return ERR_PTR(-ENOMEM); + mock->domain.geometry.aperture_start = MOCK_APERTURE_START; + mock->domain.geometry.aperture_end = MOCK_APERTURE_LAST; + mock->domain.pgsize_bitmap = MOCK_IO_PAGE_SIZE; + if (dev && mdev->flags & MOCK_FLAGS_DEVICE_HUGE_IOVA) + mock->domain.pgsize_bitmap |= MOCK_HUGE_PAGE_SIZE; + mock->domain.ops = mock_ops.default_domain_ops; + mock->domain.type = IOMMU_DOMAIN_UNMANAGED; + xa_init(&mock->pfns); + if (has_dirty_flag) - domain->dirty_ops = &dirty_ops; - return domain; + mock->domain.dirty_ops = &dirty_ops; + return &mock->domain; } static void mock_domain_free(struct iommu_domain *domain) @@ -595,7 +585,7 @@ mock_viommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, struct mock_viommu *mock_viommu = to_mock_viommu(viommu); struct mock_iommu_domain_nested *mock_nested; - if (flags & ~IOMMU_HWPT_FAULT_ID_VALID) + if (flags) return ERR_PTR(-EOPNOTSUPP); mock_nested = __mock_domain_alloc_nested(user_data); @@ -713,7 +703,6 @@ static const struct iommu_ops mock_ops = { .owner = THIS_MODULE, .pgsize_bitmap = MOCK_IO_PAGE_SIZE, .hw_info = mock_domain_hw_info, - .domain_alloc_paging = mock_domain_alloc_paging, .domain_alloc_paging_flags = mock_domain_alloc_paging_flags, .domain_alloc_nested = mock_domain_alloc_nested, .capable = mock_domain_capable, diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index ce40f0a419ea..2769e4544038 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -725,47 +725,32 @@ static int msm_iommu_probe(struct platform_device *pdev) iommu->dev = &pdev->dev; INIT_LIST_HEAD(&iommu->ctx_list); - iommu->pclk = devm_clk_get(iommu->dev, "smmu_pclk"); + iommu->pclk = devm_clk_get_prepared(iommu->dev, "smmu_pclk"); if (IS_ERR(iommu->pclk)) return dev_err_probe(iommu->dev, PTR_ERR(iommu->pclk), "could not get smmu_pclk\n"); - ret = clk_prepare(iommu->pclk); - if (ret) - return dev_err_probe(iommu->dev, ret, - "could not prepare smmu_pclk\n"); - - iommu->clk = devm_clk_get(iommu->dev, "iommu_clk"); - if (IS_ERR(iommu->clk)) { - clk_unprepare(iommu->pclk); + iommu->clk = devm_clk_get_prepared(iommu->dev, "iommu_clk"); + if (IS_ERR(iommu->clk)) return dev_err_probe(iommu->dev, PTR_ERR(iommu->clk), "could not get iommu_clk\n"); - } - - ret = clk_prepare(iommu->clk); - if (ret) { - clk_unprepare(iommu->pclk); - return dev_err_probe(iommu->dev, ret, "could not prepare iommu_clk\n"); - } r = platform_get_resource(pdev, IORESOURCE_MEM, 0); iommu->base = devm_ioremap_resource(iommu->dev, r); if (IS_ERR(iommu->base)) { ret = dev_err_probe(iommu->dev, PTR_ERR(iommu->base), "could not get iommu base\n"); - goto fail; + return ret; } ioaddr = r->start; iommu->irq = platform_get_irq(pdev, 0); - if (iommu->irq < 0) { - ret = -ENODEV; - goto fail; - } + if (iommu->irq < 0) + return -ENODEV; ret = of_property_read_u32(iommu->dev->of_node, "qcom,ncb", &val); if (ret) { dev_err(iommu->dev, "could not get ncb\n"); - goto fail; + return ret; } iommu->ncb = val; @@ -780,8 +765,7 @@ static int msm_iommu_probe(struct platform_device *pdev) if (!par) { pr_err("Invalid PAR value detected\n"); - ret = -ENODEV; - goto fail; + return -ENODEV; } ret = devm_request_threaded_irq(iommu->dev, iommu->irq, NULL, @@ -791,7 +775,7 @@ static int msm_iommu_probe(struct platform_device *pdev) iommu); if (ret) { pr_err("Request IRQ %d failed with ret=%d\n", iommu->irq, ret); - goto fail; + return ret; } list_add(&iommu->dev_node, &qcom_iommu_devices); @@ -800,23 +784,19 @@ static int msm_iommu_probe(struct platform_device *pdev) "msm-smmu.%pa", &ioaddr); if (ret) { pr_err("Could not add msm-smmu at %pa to sysfs\n", &ioaddr); - goto fail; + return ret; } ret = iommu_device_register(&iommu->iommu, &msm_iommu_ops, &pdev->dev); if (ret) { pr_err("Could not register msm-smmu at %pa\n", &ioaddr); - goto fail; + return ret; } pr_info("device mapped at %p, irq %d with %d ctx banks\n", iommu->base, iommu->irq, iommu->ncb); return ret; -fail: - clk_unprepare(iommu->clk); - clk_unprepare(iommu->pclk); - return ret; } static const struct of_device_id msm_iommu_dt_match[] = { @@ -824,20 +804,11 @@ static const struct of_device_id msm_iommu_dt_match[] = { {} }; -static void msm_iommu_remove(struct platform_device *pdev) -{ - struct msm_iommu_dev *iommu = platform_get_drvdata(pdev); - - clk_unprepare(iommu->clk); - clk_unprepare(iommu->pclk); -} - static struct platform_driver msm_iommu_driver = { .driver = { .name = "msm_iommu", .of_match_table = msm_iommu_dt_match, }, .probe = msm_iommu_probe, - .remove = msm_iommu_remove, }; builtin_platform_driver(msm_iommu_driver); diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index ab60901f8f92..034b0e670384 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -510,7 +511,7 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id) bank->parent_dev, "fault type=0x%x iova=0x%llx pa=0x%llx master=0x%x(larb=%d port=%d) layer=%d %s\n", int_state, fault_iova, fault_pa, regval, fault_larb, fault_port, - layer, write ? "write" : "read"); + layer, str_write_read(write)); } /* Interrupt clear */ @@ -602,7 +603,7 @@ static int mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev, larb_mmu->bank[portid] = upper_32_bits(region->iova_base); dev_dbg(dev, "%s iommu for larb(%s) port 0x%lx region %d rgn-bank %d.\n", - enable ? "enable" : "disable", dev_name(larb_mmu->dev), + str_enable_disable(enable), dev_name(larb_mmu->dev), portid_msk, regionid, upper_32_bits(region->iova_base)); if (enable) @@ -630,8 +631,8 @@ static int mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev, } if (ret) dev_err(dev, "%s iommu(%s) inframaster 0x%lx fail(%d).\n", - enable ? "enable" : "disable", - dev_name(data->dev), portid_msk, ret); + str_enable_disable(enable), dev_name(data->dev), + portid_msk, ret); } return ret; } diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index b6de1ca00cef..a565b9e40f4a 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -243,7 +244,7 @@ static void mtk_iommu_v1_config(struct mtk_iommu_v1_data *data, larb_mmu = &data->larb_imu[larbid]; dev_dbg(dev, "%s iommu port: %d\n", - enable ? "enable" : "disable", portid); + str_enable_disable(enable), portid); if (enable) larb_mmu->mmu |= MTK_SMI_MMU_EN(portid); diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index e7a6a1611d19..97987cd78da9 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -29,8 +29,6 @@ static int of_iommu_xlate(struct device *dev, return -ENODEV; ret = iommu_fwspec_init(dev, of_fwnode_handle(iommu_spec->np)); - if (ret == -EPROBE_DEFER) - return driver_deferred_probe_check_state(dev); if (ret) return ret; diff --git a/drivers/iommu/riscv/iommu-pci.c b/drivers/iommu/riscv/iommu-pci.c index c7a89143014c..d82d2b00904c 100644 --- a/drivers/iommu/riscv/iommu-pci.c +++ b/drivers/iommu/riscv/iommu-pci.c @@ -101,6 +101,13 @@ static void riscv_iommu_pci_remove(struct pci_dev *pdev) riscv_iommu_remove(iommu); } +static void riscv_iommu_pci_shutdown(struct pci_dev *pdev) +{ + struct riscv_iommu_device *iommu = dev_get_drvdata(&pdev->dev); + + riscv_iommu_disable(iommu); +} + static const struct pci_device_id riscv_iommu_pci_tbl[] = { {PCI_VDEVICE(REDHAT, PCI_DEVICE_ID_REDHAT_RISCV_IOMMU), 0}, {PCI_VDEVICE(RIVOS, PCI_DEVICE_ID_RIVOS_RISCV_IOMMU_GA), 0}, @@ -112,6 +119,7 @@ static struct pci_driver riscv_iommu_pci_driver = { .id_table = riscv_iommu_pci_tbl, .probe = riscv_iommu_pci_probe, .remove = riscv_iommu_pci_remove, + .shutdown = riscv_iommu_pci_shutdown, .driver = { .suppress_bind_attrs = true, }, diff --git a/drivers/iommu/riscv/iommu-platform.c b/drivers/iommu/riscv/iommu-platform.c index 382ba2841849..725e919b97ef 100644 --- a/drivers/iommu/riscv/iommu-platform.c +++ b/drivers/iommu/riscv/iommu-platform.c @@ -11,18 +11,43 @@ */ #include +#include +#include #include #include #include "iommu-bits.h" #include "iommu.h" +static void riscv_iommu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) +{ + struct device *dev = msi_desc_to_dev(desc); + struct riscv_iommu_device *iommu = dev_get_drvdata(dev); + u16 idx = desc->msi_index; + u64 addr; + + addr = ((u64)msg->address_hi << 32) | msg->address_lo; + + if (addr != (addr & RISCV_IOMMU_MSI_CFG_TBL_ADDR)) { + dev_err_once(dev, + "uh oh, the IOMMU can't send MSIs to 0x%llx, sending to 0x%llx instead\n", + addr, addr & RISCV_IOMMU_MSI_CFG_TBL_ADDR); + } + + addr &= RISCV_IOMMU_MSI_CFG_TBL_ADDR; + + riscv_iommu_writeq(iommu, RISCV_IOMMU_REG_MSI_CFG_TBL_ADDR(idx), addr); + riscv_iommu_writel(iommu, RISCV_IOMMU_REG_MSI_CFG_TBL_DATA(idx), msg->data); + riscv_iommu_writel(iommu, RISCV_IOMMU_REG_MSI_CFG_TBL_CTRL(idx), 0); +} + static int riscv_iommu_platform_probe(struct platform_device *pdev) { + enum riscv_iommu_igs_settings igs; struct device *dev = &pdev->dev; struct riscv_iommu_device *iommu = NULL; struct resource *res = NULL; - int vec; + int vec, ret; iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL); if (!iommu) @@ -40,16 +65,6 @@ static int riscv_iommu_platform_probe(struct platform_device *pdev) iommu->caps = riscv_iommu_readq(iommu, RISCV_IOMMU_REG_CAPABILITIES); iommu->fctl = riscv_iommu_readl(iommu, RISCV_IOMMU_REG_FCTL); - /* For now we only support WSI */ - switch (FIELD_GET(RISCV_IOMMU_CAPABILITIES_IGS, iommu->caps)) { - case RISCV_IOMMU_CAPABILITIES_IGS_WSI: - case RISCV_IOMMU_CAPABILITIES_IGS_BOTH: - break; - default: - return dev_err_probe(dev, -ENODEV, - "unable to use wire-signaled interrupts\n"); - } - iommu->irqs_count = platform_irq_count(pdev); if (iommu->irqs_count <= 0) return dev_err_probe(dev, -ENODEV, @@ -57,13 +72,58 @@ static int riscv_iommu_platform_probe(struct platform_device *pdev) if (iommu->irqs_count > RISCV_IOMMU_INTR_COUNT) iommu->irqs_count = RISCV_IOMMU_INTR_COUNT; - for (vec = 0; vec < iommu->irqs_count; vec++) - iommu->irqs[vec] = platform_get_irq(pdev, vec); + igs = FIELD_GET(RISCV_IOMMU_CAPABILITIES_IGS, iommu->caps); + switch (igs) { + case RISCV_IOMMU_CAPABILITIES_IGS_BOTH: + case RISCV_IOMMU_CAPABILITIES_IGS_MSI: + if (is_of_node(dev->fwnode)) + of_msi_configure(dev, to_of_node(dev->fwnode)); - /* Enable wire-signaled interrupts, fctl.WSI */ - if (!(iommu->fctl & RISCV_IOMMU_FCTL_WSI)) { - iommu->fctl |= RISCV_IOMMU_FCTL_WSI; - riscv_iommu_writel(iommu, RISCV_IOMMU_REG_FCTL, iommu->fctl); + if (!dev_get_msi_domain(dev)) { + dev_warn(dev, "failed to find an MSI domain\n"); + goto msi_fail; + } + + ret = platform_device_msi_init_and_alloc_irqs(dev, iommu->irqs_count, + riscv_iommu_write_msi_msg); + if (ret) { + dev_warn(dev, "failed to allocate MSIs\n"); + goto msi_fail; + } + + for (vec = 0; vec < iommu->irqs_count; vec++) + iommu->irqs[vec] = msi_get_virq(dev, vec); + + /* Enable message-signaled interrupts, fctl.WSI */ + if (iommu->fctl & RISCV_IOMMU_FCTL_WSI) { + iommu->fctl ^= RISCV_IOMMU_FCTL_WSI; + riscv_iommu_writel(iommu, RISCV_IOMMU_REG_FCTL, iommu->fctl); + } + + dev_info(dev, "using MSIs\n"); + break; + +msi_fail: + if (igs != RISCV_IOMMU_CAPABILITIES_IGS_BOTH) { + return dev_err_probe(dev, -ENODEV, + "unable to use wire-signaled interrupts\n"); + } + + fallthrough; + + case RISCV_IOMMU_CAPABILITIES_IGS_WSI: + for (vec = 0; vec < iommu->irqs_count; vec++) + iommu->irqs[vec] = platform_get_irq(pdev, vec); + + /* Enable wire-signaled interrupts, fctl.WSI */ + if (!(iommu->fctl & RISCV_IOMMU_FCTL_WSI)) { + iommu->fctl |= RISCV_IOMMU_FCTL_WSI; + riscv_iommu_writel(iommu, RISCV_IOMMU_REG_FCTL, iommu->fctl); + } + dev_info(dev, "using wire-signaled interrupts\n"); + break; + default: + return dev_err_probe(dev, -ENODEV, "invalid IGS\n"); } return riscv_iommu_init(iommu); @@ -71,7 +131,18 @@ static int riscv_iommu_platform_probe(struct platform_device *pdev) static void riscv_iommu_platform_remove(struct platform_device *pdev) { - riscv_iommu_remove(dev_get_drvdata(&pdev->dev)); + struct riscv_iommu_device *iommu = dev_get_drvdata(&pdev->dev); + bool msi = !(iommu->fctl & RISCV_IOMMU_FCTL_WSI); + + riscv_iommu_remove(iommu); + + if (msi) + platform_device_msi_free_irqs_all(&pdev->dev); +}; + +static void riscv_iommu_platform_shutdown(struct platform_device *pdev) +{ + riscv_iommu_disable(dev_get_drvdata(&pdev->dev)); }; static const struct of_device_id riscv_iommu_of_match[] = { @@ -82,6 +153,7 @@ static const struct of_device_id riscv_iommu_of_match[] = { static struct platform_driver riscv_iommu_platform_driver = { .probe = riscv_iommu_platform_probe, .remove = riscv_iommu_platform_remove, + .shutdown = riscv_iommu_platform_shutdown, .driver = { .name = "riscv,iommu", .of_match_table = riscv_iommu_of_match, diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index 8a05def774bd..8f049d4a0e2c 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -240,6 +240,12 @@ static int riscv_iommu_queue_enable(struct riscv_iommu_device *iommu, return rc; } + /* Empty queue before enabling it */ + if (queue->qid == RISCV_IOMMU_INTR_CQ) + riscv_iommu_writel(queue->iommu, Q_TAIL(queue), 0); + else + riscv_iommu_writel(queue->iommu, Q_HEAD(queue), 0); + /* * Enable queue with interrupts, clear any memory fault if any. * Wait for the hardware to acknowledge request and activate queue @@ -645,9 +651,11 @@ static struct riscv_iommu_dc *riscv_iommu_get_dc(struct riscv_iommu_device *iomm * This is best effort IOMMU translation shutdown flow. * Disable IOMMU without waiting for hardware response. */ -static void riscv_iommu_disable(struct riscv_iommu_device *iommu) +void riscv_iommu_disable(struct riscv_iommu_device *iommu) { - riscv_iommu_writeq(iommu, RISCV_IOMMU_REG_DDTP, 0); + riscv_iommu_writeq(iommu, RISCV_IOMMU_REG_DDTP, + FIELD_PREP(RISCV_IOMMU_DDTP_IOMMU_MODE, + RISCV_IOMMU_DDTP_IOMMU_MODE_BARE)); riscv_iommu_writel(iommu, RISCV_IOMMU_REG_CQCSR, 0); riscv_iommu_writel(iommu, RISCV_IOMMU_REG_FQCSR, 0); riscv_iommu_writel(iommu, RISCV_IOMMU_REG_PQCSR, 0); @@ -1270,7 +1278,7 @@ static phys_addr_t riscv_iommu_iova_to_phys(struct iommu_domain *iommu_domain, dma_addr_t iova) { struct riscv_iommu_domain *domain = iommu_domain_to_riscv(iommu_domain); - unsigned long pte_size; + size_t pte_size; unsigned long *ptr; ptr = riscv_iommu_pte_fetch(domain, iova, &pte_size); diff --git a/drivers/iommu/riscv/iommu.h b/drivers/iommu/riscv/iommu.h index b1c4664542b4..46df79dd5495 100644 --- a/drivers/iommu/riscv/iommu.h +++ b/drivers/iommu/riscv/iommu.h @@ -64,6 +64,7 @@ struct riscv_iommu_device { int riscv_iommu_init(struct riscv_iommu_device *iommu); void riscv_iommu_remove(struct riscv_iommu_device *iommu); +void riscv_iommu_disable(struct riscv_iommu_device *iommu); #define riscv_iommu_readl(iommu, addr) \ readl_relaxed((iommu)->reg + (addr)) diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 4b369419b32c..323cc665c357 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "iommu-pages.h" @@ -611,7 +612,7 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id) dev_err(iommu->dev, "Page fault at %pad of type %s\n", &iova, - (flags == IOMMU_FAULT_WRITE) ? "write" : "read"); + str_write_read(flags == IOMMU_FAULT_WRITE)); log_iova(iommu, i, iova); diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 9bee02db1643..be063bfb50c4 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -534,8 +534,9 @@ config LS1X_IRQ Support for the Loongson-1 platform Interrupt Controller. config TI_SCI_INTR_IRQCHIP - bool + tristate "TI SCI INTR Interrupt Controller" depends on TI_SCI_PROTOCOL + depends on ARCH_K3 || COMPILE_TEST select IRQ_DOMAIN_HIERARCHY help This enables the irqchip driver support for K3 Interrupt router @@ -544,8 +545,9 @@ config TI_SCI_INTR_IRQCHIP TI System Controller, say Y here. Otherwise, say N. config TI_SCI_INTA_IRQCHIP - bool + tristate "TI SCI INTA Interrupt Controller" depends on TI_SCI_PROTOCOL + depends on ARCH_K3 || (COMPILE_TEST && ARM64) select IRQ_DOMAIN_HIERARCHY select TI_SCI_INTA_MSI_DOMAIN help diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index c988886917f7..db4c9721fcf2 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -61,32 +61,6 @@ struct brcmstb_l2_intc_data { u32 saved_mask; /* for suspend/resume */ }; -/** - * brcmstb_l2_mask_and_ack - Mask and ack pending interrupt - * @d: irq_data - * - * Chip has separate enable/disable registers instead of a single mask - * register and pending interrupt is acknowledged by setting a bit. - * - * Note: This function is generic and could easily be added to the - * generic irqchip implementation if there ever becomes a will to do so. - * Perhaps with a name like irq_gc_mask_disable_and_ack_set(). - * - * e.g.: https://patchwork.kernel.org/patch/9831047/ - */ -static void brcmstb_l2_mask_and_ack(struct irq_data *d) -{ - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); - struct irq_chip_type *ct = irq_data_get_chip_type(d); - u32 mask = d->mask; - - irq_gc_lock(gc); - irq_reg_writel(gc, mask, ct->regs.disable); - *ct->mask_cache &= ~mask; - irq_reg_writel(gc, mask, ct->regs.ack); - irq_gc_unlock(gc); -} - static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc) { struct brcmstb_l2_intc_data *b = irq_desc_get_handler_data(desc); @@ -248,7 +222,7 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np, if (init_params->cpu_clear >= 0) { ct->regs.ack = init_params->cpu_clear; ct->chip.irq_ack = irq_gc_ack_set_bit; - ct->chip.irq_mask_ack = brcmstb_l2_mask_and_ack; + ct->chip.irq_mask_ack = irq_gc_mask_disable_and_ack_set; } else { /* No Ack - but still slightly more efficient to define this */ ct->chip.irq_mask_ack = irq_gc_mask_disable_reg; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 92244cfa0464..8c3ec5734f1e 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2045,7 +2045,7 @@ static int its_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu_info) if (!is_v4(its_dev->its)) return -EINVAL; - guard(raw_spinlock_irq)(&its_dev->event_map.vlpi_lock); + guard(raw_spinlock)(&its_dev->event_map.vlpi_lock); /* Unmap request? */ if (!info) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 79d8cc80693c..76dce0aac246 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -1522,7 +1522,7 @@ static int gic_retrigger(struct irq_data *data) static int gic_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { - if (cmd == CPU_PM_EXIT) { + if (cmd == CPU_PM_EXIT || cmd == CPU_PM_ENTER_FAILED) { if (gic_dist_security_disabled()) gic_enable_redist(true); gic_cpu_sys_reg_enable(); diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c index 808c781e2548..37e1a03fcbb4 100644 --- a/drivers/irqchip/irq-keystone.c +++ b/drivers/irqchip/irq-keystone.c @@ -141,18 +141,11 @@ static int keystone_irq_probe(struct platform_device *pdev) if (!kirq) return -ENOMEM; - kirq->devctrl_regs = - syscon_regmap_lookup_by_phandle(np, "ti,syscon-dev"); + kirq->devctrl_regs = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-dev", + 1, &kirq->devctrl_offset); if (IS_ERR(kirq->devctrl_regs)) return PTR_ERR(kirq->devctrl_regs); - ret = of_property_read_u32_index(np, "ti,syscon-dev", 1, - &kirq->devctrl_offset); - if (ret) { - dev_err(dev, "couldn't read the devctrl_offset offset!\n"); - return ret; - } - kirq->irq = platform_get_irq(pdev, 0); if (kirq->irq < 0) return kirq->irq; diff --git a/drivers/irqchip/irq-loongarch-avec.c b/drivers/irqchip/irq-loongarch-avec.c index 0f6e465dd309..80e55955a29f 100644 --- a/drivers/irqchip/irq-loongarch-avec.c +++ b/drivers/irqchip/irq-loongarch-avec.c @@ -56,6 +56,15 @@ struct avecintc_data { unsigned int moving; }; +static inline void avecintc_enable(void) +{ + u64 value; + + value = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC); + value |= IOCSR_MISC_FUNC_AVEC_EN; + iocsr_write64(value, LOONGARCH_IOCSR_MISC_FUNC); +} + static inline void avecintc_ack_irq(struct irq_data *d) { } @@ -127,6 +136,8 @@ static int avecintc_cpu_online(unsigned int cpu) guard(raw_spinlock)(&loongarch_avec.lock); + avecintc_enable(); + irq_matrix_online(loongarch_avec.vector_matrix); pending_list_init(cpu); @@ -339,7 +350,6 @@ static int __init irq_matrix_init(void) static int __init avecintc_init(struct irq_domain *parent) { int ret, parent_irq; - unsigned long value; raw_spin_lock_init(&loongarch_avec.lock); @@ -378,9 +388,7 @@ static int __init avecintc_init(struct irq_domain *parent) "irqchip/loongarch/avecintc:starting", avecintc_cpu_online, avecintc_cpu_offline); #endif - value = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC); - value |= IOCSR_MISC_FUNC_AVEC_EN; - iocsr_write64(value, LOONGARCH_IOCSR_MISC_FUNC); + avecintc_enable(); return ret; diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c index bb92fd85e975..0b4312152024 100644 --- a/drivers/irqchip/irq-sunxi-nmi.c +++ b/drivers/irqchip/irq-sunxi-nmi.c @@ -186,7 +186,8 @@ static int __init sunxi_sc_nmi_irq_init(struct device_node *node, gc->chip_types[0].chip.irq_unmask = irq_gc_mask_set_bit; gc->chip_types[0].chip.irq_eoi = irq_gc_ack_set_bit; gc->chip_types[0].chip.irq_set_type = sunxi_sc_nmi_set_type; - gc->chip_types[0].chip.flags = IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED; + gc->chip_types[0].chip.flags = IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED | + IRQCHIP_SKIP_SET_WAKE; gc->chip_types[0].regs.ack = reg_offs->pend; gc->chip_types[0].regs.mask = reg_offs->enable; gc->chip_types[0].regs.type = reg_offs->ctrl; diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index b83f5cbab123..a887efba262c 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -743,3 +743,4 @@ module_platform_driver(ti_sci_inta_irq_domain_driver); MODULE_AUTHOR("Lokesh Vutla "); MODULE_DESCRIPTION("K3 Interrupt Aggregator driver over TI SCI protocol"); +MODULE_LICENSE("GPL"); diff --git a/drivers/irqchip/irq-ti-sci-intr.c b/drivers/irqchip/irq-ti-sci-intr.c index c027cd9e4a69..b49a73106c69 100644 --- a/drivers/irqchip/irq-ti-sci-intr.c +++ b/drivers/irqchip/irq-ti-sci-intr.c @@ -303,3 +303,4 @@ module_platform_driver(ti_sci_intr_irq_domain_driver); MODULE_AUTHOR("Lokesh Vutla "); MODULE_DESCRIPTION("K3 Interrupt Router driver over TI SCI protocol"); +MODULE_LICENSE("GPL"); diff --git a/drivers/irqchip/irq-ts4800.c b/drivers/irqchip/irq-ts4800.c index cc219f28d317..960c343d5781 100644 --- a/drivers/irqchip/irq-ts4800.c +++ b/drivers/irqchip/irq-ts4800.c @@ -52,7 +52,7 @@ static void ts4800_irq_print_chip(struct irq_data *d, struct seq_file *p) { struct ts4800_irq_data *data = irq_data_get_irq_chip_data(d); - seq_printf(p, "%s", dev_name(&data->pdev->dev)); + seq_puts(p, dev_name(&data->pdev->dev)); } static const struct irq_chip ts4800_chip = { diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c index 1eeb0d0156ce..0ee7b6b71f5f 100644 --- a/drivers/irqchip/irqchip.c +++ b/drivers/irqchip/irqchip.c @@ -35,11 +35,10 @@ void __init irqchip_init(void) int platform_irqchip_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - struct device_node *par_np = of_irq_find_parent(np); + struct device_node *par_np __free(device_node) = of_irq_find_parent(np); of_irq_init_cb_t irq_init_cb = of_device_get_match_data(&pdev->dev); if (!irq_init_cb) { - of_node_put(par_np); return -EINVAL; } @@ -55,7 +54,6 @@ int platform_irqchip_probe(struct platform_device *pdev) * interrupt controller can check for specific domains as necessary. */ if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY)) { - of_node_put(par_np); return -EPROBE_DEFER; } diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c index e34a7a46754e..8ec2d4d4f135 100644 --- a/drivers/isdn/mISDN/core.c +++ b/drivers/isdn/mISDN/core.c @@ -294,20 +294,6 @@ get_Bprotocol4mask(u_int m) return NULL; } -struct Bprotocol * -get_Bprotocol4id(u_int id) -{ - u_int m; - - if (id < ISDN_P_B_START || id > 63) { - printk(KERN_WARNING "%s id not in range %d\n", - __func__, id); - return NULL; - } - m = 1 << (id & ISDN_P_B_MASK); - return get_Bprotocol4mask(m); -} - int mISDN_register_Bprotocol(struct Bprotocol *bp) { diff --git a/drivers/isdn/mISDN/core.h b/drivers/isdn/mISDN/core.h index 42599f49c189..5617c06de8e4 100644 --- a/drivers/isdn/mISDN/core.h +++ b/drivers/isdn/mISDN/core.h @@ -55,7 +55,6 @@ extern void __add_layer2(struct mISDNchannel *, struct mISDNstack *); extern u_int get_all_Bprotocols(void); struct Bprotocol *get_Bprotocol4mask(u_int); -struct Bprotocol *get_Bprotocol4id(u_int); extern int mISDN_inittimer(u_int *); extern void mISDN_timer_cleanup(void); diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index b784bb74a837..2b27d043921c 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -217,6 +217,8 @@ config LEDS_TURRIS_OMNIA depends on I2C depends on MACH_ARMADA_38X || COMPILE_TEST depends on OF + depends on TURRIS_OMNIA_MCU + depends on TURRIS_OMNIA_MCU_GPIO select LEDS_TRIGGERS help This option enables basic support for the LEDs found on the front @@ -511,6 +513,18 @@ config LEDS_LP8860 on the LP8860 4 channel LED driver using the I2C communication bus. +config LEDS_LP8864 + tristate "LED support for the TI LP8864/LP8866 4/6 channel LED drivers" + depends on LEDS_CLASS && I2C && OF + select REGMAP_I2C + help + If you say yes here you get support for the TI LP8864-Q1, + LP8864S-Q1, LP8866-Q1, LP8866S-Q1 4/6 channel LED backlight + drivers with I2C interface. + + To compile this driver as a module, choose M here: the + module will be called leds-lp8864. + config LEDS_CLEVO_MAIL tristate "Mail LED on Clevo notebook" depends on LEDS_CLASS && BROKEN @@ -580,6 +594,17 @@ config LEDS_PCA995X LED driver chips accessed via the I2C bus. Supported devices include PCA9955BTW, PCA9952TW and PCA9955TW. +config LEDS_QNAP_MCU + tristate "LED Support for QNAP MCU controllers" + depends on LEDS_CLASS + depends on MFD_QNAP_MCU + help + This option enables support for LEDs available on embedded + controllers used in QNAP NAS devices. + + This driver can also be built as a module. If so, the module + will be called qnap-mcu-leds. + config LEDS_WM831X_STATUS tristate "LED support for status LEDs on WM831x PMICs" depends on LEDS_CLASS @@ -815,6 +840,15 @@ config LEDS_SC27XX_BLTC This driver can also be built as a module. If so the module will be called leds-sc27xx-bltc. +config LEDS_UPBOARD + tristate "LED support for the UP board" + depends on LEDS_CLASS && MFD_UPBOARD_FPGA + help + This option enables support for the UP board LEDs. + + This driver can also be built as a module. If so the module will be + called leds-upboard. + comment "LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM)" config LEDS_BLINKM @@ -931,6 +965,16 @@ config LEDS_LM36274 Say Y to enable the LM36274 LED driver for TI LMU devices. This supports the LED device LM36274. +config LEDS_ST1202 + tristate "LED Support for STMicroelectronics LED1202 I2C chips" + depends on LEDS_CLASS + depends on I2C + depends on OF + select LEDS_TRIGGERS + help + Say Y to enable support for LEDs connected to LED1202 + LED driver chips accessed via the I2C bus. + config LEDS_TPS6105X tristate "LED support for TI TPS6105X" depends on LEDS_CLASS diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index 18afbb5a23ee..6ad52e219ec6 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_LEDS_LP55XX_COMMON) += leds-lp55xx-common.o obj-$(CONFIG_LEDS_LP8501) += leds-lp8501.o obj-$(CONFIG_LEDS_LP8788) += leds-lp8788.o obj-$(CONFIG_LEDS_LP8860) += leds-lp8860.o +obj-$(CONFIG_LEDS_LP8864) += leds-lp8864.o obj-$(CONFIG_LEDS_LT3593) += leds-lt3593.o obj-$(CONFIG_LEDS_MAX5970) += leds-max5970.o obj-$(CONFIG_LEDS_MAX77650) += leds-max77650.o @@ -79,8 +80,10 @@ obj-$(CONFIG_LEDS_PCA995X) += leds-pca995x.o obj-$(CONFIG_LEDS_PM8058) += leds-pm8058.o obj-$(CONFIG_LEDS_POWERNV) += leds-powernv.o obj-$(CONFIG_LEDS_PWM) += leds-pwm.o +obj-$(CONFIG_LEDS_QNAP_MCU) += leds-qnap-mcu.o obj-$(CONFIG_LEDS_REGULATOR) += leds-regulator.o obj-$(CONFIG_LEDS_SC27XX_BLTC) += leds-sc27xx-bltc.o +obj-$(CONFIG_LEDS_ST1202) += leds-st1202.o obj-$(CONFIG_LEDS_SUN50I_A100) += leds-sun50i-a100.o obj-$(CONFIG_LEDS_SUNFIRE) += leds-sunfire.o obj-$(CONFIG_LEDS_SYSCON) += leds-syscon.o @@ -89,6 +92,7 @@ obj-$(CONFIG_LEDS_TI_LMU_COMMON) += leds-ti-lmu-common.o obj-$(CONFIG_LEDS_TLC591XX) += leds-tlc591xx.o obj-$(CONFIG_LEDS_TPS6105X) += leds-tps6105x.o obj-$(CONFIG_LEDS_TURRIS_OMNIA) += leds-turris-omnia.o +obj-$(CONFIG_LEDS_UPBOARD) += leds-upboard.o obj-$(CONFIG_LEDS_WM831X_STATUS) += leds-wm831x-status.o obj-$(CONFIG_LEDS_WM8350) += leds-wm8350.o obj-$(CONFIG_LEDS_WRAP) += leds-wrap.o diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 2a04ac61574d..c20ac8ccf52b 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -85,13 +85,13 @@ static ssize_t max_brightness_show(struct device *dev, static DEVICE_ATTR_RO(max_brightness); #ifdef CONFIG_LEDS_TRIGGERS -static BIN_ATTR(trigger, 0644, led_trigger_read, led_trigger_write, 0); -static struct bin_attribute *led_trigger_bin_attrs[] = { +static const BIN_ATTR(trigger, 0644, led_trigger_read, led_trigger_write, 0); +static const struct bin_attribute *const led_trigger_bin_attrs[] = { &bin_attr_trigger, NULL, }; static const struct attribute_group led_trigger_group = { - .bin_attrs = led_trigger_bin_attrs, + .bin_attrs_new = led_trigger_bin_attrs, }; #endif diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c index 78eb20093b2c..b2d40f87a5ff 100644 --- a/drivers/leds/led-triggers.c +++ b/drivers/leds/led-triggers.c @@ -34,7 +34,7 @@ trigger_relevant(struct led_classdev *led_cdev, struct led_trigger *trig) } ssize_t led_trigger_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -123,7 +123,7 @@ static int led_trigger_format(char *buf, size_t size, * copy it. */ ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); diff --git a/drivers/leds/leds-cht-wcove.c b/drivers/leds/leds-cht-wcove.c index 8246f048edcb..9a609dd5acdc 100644 --- a/drivers/leds/leds-cht-wcove.c +++ b/drivers/leds/leds-cht-wcove.c @@ -394,7 +394,7 @@ static int cht_wc_leds_probe(struct platform_device *pdev) led->cdev.pattern_clear = cht_wc_leds_pattern_clear; led->cdev.max_brightness = 255; - ret = led_classdev_register(&pdev->dev, &led->cdev); + ret = devm_led_classdev_register(&pdev->dev, &led->cdev); if (ret < 0) return ret; } @@ -406,10 +406,6 @@ static int cht_wc_leds_probe(struct platform_device *pdev) static void cht_wc_leds_remove(struct platform_device *pdev) { struct cht_wc_leds *leds = platform_get_drvdata(pdev); - int i; - - for (i = 0; i < CHT_WC_LED_COUNT; i++) - led_classdev_unregister(&leds->leds[i].cdev); /* Restore LED1 regs if hw-control was active else leave LED1 off */ if (!(leds->led1_initial_regs.ctrl & CHT_WC_LED1_SWCTL)) diff --git a/drivers/leds/leds-lp8860.c b/drivers/leds/leds-lp8860.c index 7a136fd81720..06196d851ade 100644 --- a/drivers/leds/leds-lp8860.c +++ b/drivers/leds/leds-lp8860.c @@ -265,7 +265,7 @@ static int lp8860_init(struct lp8860_led *led) goto out; } - reg_count = ARRAY_SIZE(lp8860_eeprom_disp_regs) / sizeof(lp8860_eeprom_disp_regs[0]); + reg_count = ARRAY_SIZE(lp8860_eeprom_disp_regs); for (i = 0; i < reg_count; i++) { ret = regmap_write(led->eeprom_regmap, lp8860_eeprom_disp_regs[i].reg, diff --git a/drivers/leds/leds-lp8864.c b/drivers/leds/leds-lp8864.c new file mode 100644 index 000000000000..3afd729d2f8a --- /dev/null +++ b/drivers/leds/leds-lp8864.c @@ -0,0 +1,296 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * TI LP8864/LP8866 4/6 Channel LED Driver + * + * Copyright (C) 2024 Siemens AG + * + * Based on LP8860 driver by Dan Murphy + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define LP8864_BRT_CONTROL 0x00 +#define LP8864_USER_CONFIG1 0x04 +#define LP8864_BRT_MODE_MASK GENMASK(9, 8) +#define LP8864_BRT_MODE_REG BIT(9) /* Brightness control by DISPLAY_BRT reg */ +#define LP8864_SUPPLY_STATUS 0x0e +#define LP8864_BOOST_STATUS 0x10 +#define LP8864_LED_STATUS 0x12 +#define LP8864_LED_STATUS_WR_MASK GENMASK(14, 9) /* Writeable bits in the LED_STATUS reg */ + +/* Textual meaning for status bits, starting from bit 1 */ +static const char *const lp8864_supply_status_msg[] = { + "Vin under-voltage fault", + "Vin over-voltage fault", + "Vdd under-voltage fault", + "Vin over-current fault", + "Missing charge pump fault", + "Charge pump fault", + "Missing boost sync fault", + "CRC error fault ", +}; + +/* Textual meaning for status bits, starting from bit 1 */ +static const char *const lp8864_boost_status_msg[] = { + "Boost OVP low fault", + "Boost OVP high fault", + "Boost over-current fault", + "Missing boost FSET resistor fault", + "Missing MODE SEL resistor fault", + "Missing LED resistor fault", + "ISET resistor short to ground fault", + "Thermal shutdown fault", +}; + +/* Textual meaning for every register bit */ +static const char *const lp8864_led_status_msg[] = { + "LED 1 fault", + "LED 2 fault", + "LED 3 fault", + "LED 4 fault", + "LED 5 fault", + "LED 6 fault", + "LED open fault", + "LED internal short fault", + "LED short to GND fault", + NULL, NULL, NULL, + "Invalid string configuration fault", + NULL, + "I2C time out fault", +}; + +/** + * struct lp8864_led + * @client: Pointer to the I2C client + * @led_dev: led class device pointer + * @regmap: Devices register map + * @led_status_mask: Helps to report LED fault only once + */ +struct lp8864_led { + struct i2c_client *client; + struct led_classdev led_dev; + struct regmap *regmap; + u16 led_status_mask; +}; + +static int lp8864_fault_check(struct lp8864_led *led) +{ + int ret, i; + unsigned int val; + + ret = regmap_read(led->regmap, LP8864_SUPPLY_STATUS, &val); + if (ret) + goto err; + + /* Odd bits are status bits, even bits are clear bits */ + for (i = 0; i < ARRAY_SIZE(lp8864_supply_status_msg); i++) + if (val & BIT(i * 2 + 1)) + dev_warn(&led->client->dev, "%s\n", lp8864_supply_status_msg[i]); + + /* + * Clear bits have an index preceding the corresponding Status bits; + * both have to be written "1" simultaneously to clear the corresponding + * Status bit. + */ + if (val) + ret = regmap_write(led->regmap, LP8864_SUPPLY_STATUS, val >> 1 | val); + if (ret) + goto err; + + ret = regmap_read(led->regmap, LP8864_BOOST_STATUS, &val); + if (ret) + goto err; + + /* Odd bits are status bits, even bits are clear bits */ + for (i = 0; i < ARRAY_SIZE(lp8864_boost_status_msg); i++) + if (val & BIT(i * 2 + 1)) + dev_warn(&led->client->dev, "%s\n", lp8864_boost_status_msg[i]); + + if (val) + ret = regmap_write(led->regmap, LP8864_BOOST_STATUS, val >> 1 | val); + if (ret) + goto err; + + ret = regmap_read(led->regmap, LP8864_LED_STATUS, &val); + if (ret) + goto err; + + /* + * Clear already reported faults that maintain their value until device + * power-down + */ + val &= ~led->led_status_mask; + + for (i = 0; i < ARRAY_SIZE(lp8864_led_status_msg); i++) + if (lp8864_led_status_msg[i] && val & BIT(i)) + dev_warn(&led->client->dev, "%s\n", lp8864_led_status_msg[i]); + + /* + * Mark those which maintain their value until device power-down as + * "already reported" + */ + led->led_status_mask |= val & ~LP8864_LED_STATUS_WR_MASK; + + /* + * Only bits 14, 12, 10 have to be cleared here, but others are RO, + * we don't care what we write to them. + */ + if (val & LP8864_LED_STATUS_WR_MASK) + ret = regmap_write(led->regmap, LP8864_LED_STATUS, val >> 1 | val); + if (ret) + goto err; + + return 0; + +err: + dev_err(&led->client->dev, "Failed to read/clear faults (%pe)\n", ERR_PTR(ret)); + + return ret; +} + +static int lp8864_brightness_set(struct led_classdev *led_cdev, + enum led_brightness brt_val) +{ + struct lp8864_led *led = container_of(led_cdev, struct lp8864_led, led_dev); + /* Scale 0..LED_FULL into 16-bit HW brightness */ + unsigned int val = brt_val * 0xffff / LED_FULL; + int ret; + + ret = lp8864_fault_check(led); + if (ret) + return ret; + + ret = regmap_write(led->regmap, LP8864_BRT_CONTROL, val); + if (ret) + dev_err(&led->client->dev, "Failed to write brightness value\n"); + + return ret; +} + +static enum led_brightness lp8864_brightness_get(struct led_classdev *led_cdev) +{ + struct lp8864_led *led = container_of(led_cdev, struct lp8864_led, led_dev); + unsigned int val; + int ret; + + ret = regmap_read(led->regmap, LP8864_BRT_CONTROL, &val); + if (ret) { + dev_err(&led->client->dev, "Failed to read brightness value\n"); + return ret; + } + + /* Scale 16-bit HW brightness into 0..LED_FULL */ + return val * LED_FULL / 0xffff; +} + +static const struct regmap_config lp8864_regmap_config = { + .reg_bits = 8, + .val_bits = 16, + .val_format_endian = REGMAP_ENDIAN_LITTLE, +}; + +static void lp8864_disable_gpio(void *data) +{ + struct gpio_desc *gpio = data; + + gpiod_set_value(gpio, 0); +} + +static int lp8864_probe(struct i2c_client *client) +{ + int ret; + struct lp8864_led *led; + struct device_node *np = dev_of_node(&client->dev); + struct device_node *child_node; + struct led_init_data init_data = {}; + struct gpio_desc *enable_gpio; + + led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL); + if (!led) + return -ENOMEM; + + child_node = of_get_next_available_child(np, NULL); + if (!child_node) { + dev_err(&client->dev, "No LED function defined\n"); + return -EINVAL; + } + + ret = devm_regulator_get_enable_optional(&client->dev, "vled"); + if (ret && ret != -ENODEV) + return dev_err_probe(&client->dev, ret, "Failed to enable vled regulator\n"); + + enable_gpio = devm_gpiod_get_optional(&client->dev, "enable", GPIOD_OUT_HIGH); + if (IS_ERR(enable_gpio)) + return dev_err_probe(&client->dev, PTR_ERR(enable_gpio), + "Failed to get enable GPIO\n"); + + ret = devm_add_action_or_reset(&client->dev, lp8864_disable_gpio, enable_gpio); + if (ret) + return ret; + + led->client = client; + led->led_dev.brightness_set_blocking = lp8864_brightness_set; + led->led_dev.brightness_get = lp8864_brightness_get; + + led->regmap = devm_regmap_init_i2c(client, &lp8864_regmap_config); + if (IS_ERR(led->regmap)) + return dev_err_probe(&client->dev, PTR_ERR(led->regmap), + "Failed to allocate regmap\n"); + + /* Control brightness by DISPLAY_BRT register */ + ret = regmap_update_bits(led->regmap, LP8864_USER_CONFIG1, LP8864_BRT_MODE_MASK, + LP8864_BRT_MODE_REG); + if (ret) { + dev_err(&led->client->dev, "Failed to set brightness control mode\n"); + return ret; + } + + ret = lp8864_fault_check(led); + if (ret) + return ret; + + init_data.fwnode = of_fwnode_handle(child_node); + init_data.devicename = "lp8864"; + init_data.default_label = ":display_cluster"; + + ret = devm_led_classdev_register_ext(&client->dev, &led->led_dev, &init_data); + if (ret) + dev_err(&client->dev, "Failed to register LED device (%pe)\n", ERR_PTR(ret)); + + return ret; +} + +static const struct i2c_device_id lp8864_id[] = { + { "lp8864" }, + {} +}; +MODULE_DEVICE_TABLE(i2c, lp8864_id); + +static const struct of_device_id of_lp8864_leds_match[] = { + { .compatible = "ti,lp8864" }, + {} +}; +MODULE_DEVICE_TABLE(of, of_lp8864_leds_match); + +static struct i2c_driver lp8864_driver = { + .driver = { + .name = "lp8864", + .of_match_table = of_lp8864_leds_match, + }, + .probe = lp8864_probe, + .id_table = lp8864_id, +}; +module_i2c_driver(lp8864_driver); + +MODULE_DESCRIPTION("Texas Instruments LP8864/LP8866 LED driver"); +MODULE_AUTHOR("Alexander Sverdlin "); +MODULE_LICENSE("GPL"); diff --git a/drivers/leds/leds-netxbig.c b/drivers/leds/leds-netxbig.c index af5a908b8d9e..e95287416ef8 100644 --- a/drivers/leds/leds-netxbig.c +++ b/drivers/leds/leds-netxbig.c @@ -439,6 +439,7 @@ static int netxbig_leds_get_of_pdata(struct device *dev, } gpio_ext_pdev = of_find_device_by_node(gpio_ext_np); if (!gpio_ext_pdev) { + of_node_put(gpio_ext_np); dev_err(dev, "Failed to find platform device for gpio-ext\n"); return -ENODEV; } diff --git a/drivers/leds/leds-qnap-mcu.c b/drivers/leds/leds-qnap-mcu.c new file mode 100644 index 000000000000..4e4709456261 --- /dev/null +++ b/drivers/leds/leds-qnap-mcu.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Driver for LEDs found on QNAP MCU devices + * + * Copyright (C) 2024 Heiko Stuebner + */ + +#include +#include +#include +#include +#include +#include + +enum qnap_mcu_err_led_mode { + QNAP_MCU_ERR_LED_ON = 0, + QNAP_MCU_ERR_LED_OFF = 1, + QNAP_MCU_ERR_LED_BLINK_FAST = 2, + QNAP_MCU_ERR_LED_BLINK_SLOW = 3, +}; + +struct qnap_mcu_err_led { + struct qnap_mcu *mcu; + struct led_classdev cdev; + char name[LED_MAX_NAME_SIZE]; + u8 num; + u8 mode; +}; + +static inline struct qnap_mcu_err_led * + cdev_to_qnap_mcu_err_led(struct led_classdev *led_cdev) +{ + return container_of(led_cdev, struct qnap_mcu_err_led, cdev); +} + +static int qnap_mcu_err_led_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct qnap_mcu_err_led *err_led = cdev_to_qnap_mcu_err_led(led_cdev); + u8 cmd[] = { '@', 'R', '0' + err_led->num, '0' }; + + /* Don't disturb a possible set blink-mode if LED stays on */ + if (brightness != 0 && err_led->mode >= QNAP_MCU_ERR_LED_BLINK_FAST) + return 0; + + err_led->mode = brightness ? QNAP_MCU_ERR_LED_ON : QNAP_MCU_ERR_LED_OFF; + cmd[3] = '0' + err_led->mode; + + return qnap_mcu_exec_with_ack(err_led->mcu, cmd, sizeof(cmd)); +} + +static int qnap_mcu_err_led_blink_set(struct led_classdev *led_cdev, + unsigned long *delay_on, + unsigned long *delay_off) +{ + struct qnap_mcu_err_led *err_led = cdev_to_qnap_mcu_err_led(led_cdev); + u8 cmd[] = { '@', 'R', '0' + err_led->num, '0' }; + + /* LED is off, nothing to do */ + if (err_led->mode == QNAP_MCU_ERR_LED_OFF) + return 0; + + if (*delay_on < 500) { + *delay_on = 100; + *delay_off = 100; + err_led->mode = QNAP_MCU_ERR_LED_BLINK_FAST; + } else { + *delay_on = 500; + *delay_off = 500; + err_led->mode = QNAP_MCU_ERR_LED_BLINK_SLOW; + } + + cmd[3] = '0' + err_led->mode; + + return qnap_mcu_exec_with_ack(err_led->mcu, cmd, sizeof(cmd)); +} + +static int qnap_mcu_register_err_led(struct device *dev, struct qnap_mcu *mcu, int num_err_led) +{ + struct qnap_mcu_err_led *err_led; + int ret; + + err_led = devm_kzalloc(dev, sizeof(*err_led), GFP_KERNEL); + if (!err_led) + return -ENOMEM; + + err_led->mcu = mcu; + err_led->num = num_err_led; + err_led->mode = QNAP_MCU_ERR_LED_OFF; + + scnprintf(err_led->name, LED_MAX_NAME_SIZE, "hdd%d:red:status", num_err_led + 1); + err_led->cdev.name = err_led->name; + + err_led->cdev.brightness_set_blocking = qnap_mcu_err_led_set; + err_led->cdev.blink_set = qnap_mcu_err_led_blink_set; + err_led->cdev.brightness = 0; + err_led->cdev.max_brightness = 1; + + ret = devm_led_classdev_register(dev, &err_led->cdev); + if (ret) + return ret; + + return qnap_mcu_err_led_set(&err_led->cdev, 0); +} + +enum qnap_mcu_usb_led_mode { + QNAP_MCU_USB_LED_ON = 1, + QNAP_MCU_USB_LED_OFF = 3, + QNAP_MCU_USB_LED_BLINK = 2, +}; + +struct qnap_mcu_usb_led { + struct qnap_mcu *mcu; + struct led_classdev cdev; + u8 mode; +}; + +static inline struct qnap_mcu_usb_led * + cdev_to_qnap_mcu_usb_led(struct led_classdev *led_cdev) +{ + return container_of(led_cdev, struct qnap_mcu_usb_led, cdev); +} + +static int qnap_mcu_usb_led_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct qnap_mcu_usb_led *usb_led = cdev_to_qnap_mcu_usb_led(led_cdev); + u8 cmd[] = { '@', 'C', 0 }; + + /* Don't disturb a possible set blink-mode if LED stays on */ + if (brightness != 0 && usb_led->mode == QNAP_MCU_USB_LED_BLINK) + return 0; + + usb_led->mode = brightness ? QNAP_MCU_USB_LED_ON : QNAP_MCU_USB_LED_OFF; + + /* + * Byte 3 is shared between the usb led target on/off/blink + * and also the buzzer control (in the input driver) + */ + cmd[2] = 'D' + usb_led->mode; + + return qnap_mcu_exec_with_ack(usb_led->mcu, cmd, sizeof(cmd)); +} + +static int qnap_mcu_usb_led_blink_set(struct led_classdev *led_cdev, + unsigned long *delay_on, + unsigned long *delay_off) +{ + struct qnap_mcu_usb_led *usb_led = cdev_to_qnap_mcu_usb_led(led_cdev); + u8 cmd[] = { '@', 'C', 0 }; + + /* LED is off, nothing to do */ + if (usb_led->mode == QNAP_MCU_USB_LED_OFF) + return 0; + + *delay_on = 250; + *delay_off = 250; + usb_led->mode = QNAP_MCU_USB_LED_BLINK; + + /* + * Byte 3 is shared between the USB LED target on/off/blink + * and also the buzzer control (in the input driver) + */ + cmd[2] = 'D' + usb_led->mode; + + return qnap_mcu_exec_with_ack(usb_led->mcu, cmd, sizeof(cmd)); +} + +static int qnap_mcu_register_usb_led(struct device *dev, struct qnap_mcu *mcu) +{ + struct qnap_mcu_usb_led *usb_led; + int ret; + + usb_led = devm_kzalloc(dev, sizeof(*usb_led), GFP_KERNEL); + if (!usb_led) + return -ENOMEM; + + usb_led->mcu = mcu; + usb_led->mode = QNAP_MCU_USB_LED_OFF; + usb_led->cdev.name = "usb:blue:disk"; + usb_led->cdev.brightness_set_blocking = qnap_mcu_usb_led_set; + usb_led->cdev.blink_set = qnap_mcu_usb_led_blink_set; + usb_led->cdev.brightness = 0; + usb_led->cdev.max_brightness = 1; + + ret = devm_led_classdev_register(dev, &usb_led->cdev); + if (ret) + return ret; + + return qnap_mcu_usb_led_set(&usb_led->cdev, 0); +} + +static int qnap_mcu_leds_probe(struct platform_device *pdev) +{ + struct qnap_mcu *mcu = dev_get_drvdata(pdev->dev.parent); + const struct qnap_mcu_variant *variant = pdev->dev.platform_data; + int ret; + + for (int i = 0; i < variant->num_drives; i++) { + ret = qnap_mcu_register_err_led(&pdev->dev, mcu, i); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "failed to register error LED %d\n", i); + } + + if (variant->usb_led) { + ret = qnap_mcu_register_usb_led(&pdev->dev, mcu); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "failed to register USB LED\n"); + } + + return 0; +} + +static struct platform_driver qnap_mcu_leds_driver = { + .probe = qnap_mcu_leds_probe, + .driver = { + .name = "qnap-mcu-leds", + }, +}; +module_platform_driver(qnap_mcu_leds_driver); + +MODULE_ALIAS("platform:qnap-mcu-leds"); +MODULE_AUTHOR("Heiko Stuebner "); +MODULE_DESCRIPTION("QNAP MCU LEDs driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/leds/leds-st1202.c b/drivers/leds/leds-st1202.c new file mode 100644 index 000000000000..b691c4886993 --- /dev/null +++ b/drivers/leds/leds-st1202.c @@ -0,0 +1,416 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * LED driver for STMicroelectronics LED1202 chip + * + * Copyright (C) 2024 Remote-Tech Ltd. UK + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ST1202_CHAN_DISABLE_ALL 0x00 +#define ST1202_CHAN_ENABLE_HIGH 0x03 +#define ST1202_CHAN_ENABLE_LOW 0x02 +#define ST1202_CONFIG_REG 0x04 +/* PATS: Pattern sequence feature enable */ +#define ST1202_CONFIG_REG_PATS BIT(7) +/* PATSR: Pattern sequence runs (self-clear when sequence is finished) */ +#define ST1202_CONFIG_REG_PATSR BIT(6) +#define ST1202_CONFIG_REG_SHFT BIT(3) +#define ST1202_DEV_ENABLE 0x01 +#define ST1202_DEV_ENABLE_ON BIT(0) +#define ST1202_DEV_ENABLE_RESET BIT(7) +#define ST1202_DEVICE_ID 0x00 +#define ST1202_ILED_REG0 0x09 +#define ST1202_MAX_LEDS 12 +#define ST1202_MAX_PATTERNS 8 +#define ST1202_MILLIS_PATTERN_DUR_MAX 5660 +#define ST1202_MILLIS_PATTERN_DUR_MIN 22 +#define ST1202_PATTERN_DUR 0x16 +#define ST1202_PATTERN_PWM 0x1E +#define ST1202_PATTERN_REP 0x15 + +struct st1202_led { + struct fwnode_handle *fwnode; + struct led_classdev led_cdev; + struct st1202_chip *chip; + bool is_active; + int led_num; +}; + +struct st1202_chip { + struct i2c_client *client; + struct mutex lock; + struct st1202_led leds[ST1202_MAX_LEDS]; +}; + +static struct st1202_led *cdev_to_st1202_led(struct led_classdev *cdev) +{ + return container_of(cdev, struct st1202_led, led_cdev); +} + +static int st1202_read_reg(struct st1202_chip *chip, int reg, uint8_t *val) +{ + struct device *dev = &chip->client->dev; + int ret; + + ret = i2c_smbus_read_byte_data(chip->client, reg); + if (ret < 0) { + dev_err(dev, "Failed to read register [0x%x]: %d\n", reg, ret); + return ret; + } + + *val = (uint8_t)ret; + return 0; +} + +static int st1202_write_reg(struct st1202_chip *chip, int reg, uint8_t val) +{ + struct device *dev = &chip->client->dev; + int ret; + + ret = i2c_smbus_write_byte_data(chip->client, reg, val); + if (ret != 0) + dev_err(dev, "Failed to write %d to register [0x%x]: %d\n", val, reg, ret); + + return ret; +} + +static uint8_t st1202_prescalar_to_miliseconds(unsigned int value) +{ + return value / ST1202_MILLIS_PATTERN_DUR_MIN - 1; +} + +static int st1202_pwm_pattern_write(struct st1202_chip *chip, int led_num, + int pattern, unsigned int value) +{ + u8 value_l, value_h; + int ret; + + value_l = (u8)value; + value_h = (u8)(value >> 8); + + /* + * Datasheet: Register address low = 1Eh + 2*(xh) + 18h*(yh), + * where x is the channel number (led number) in hexadecimal (x = 00h .. 0Bh) + * and y is the pattern number in hexadecimal (y = 00h .. 07h) + */ + ret = st1202_write_reg(chip, (ST1202_PATTERN_PWM + (led_num * 2) + 0x18 * pattern), + value_l); + if (ret != 0) + return ret; + + /* + * Datasheet: Register address high = 1Eh + 01h + 2(xh) +18h*(yh), + * where x is the channel number in hexadecimal (x = 00h .. 0Bh) + * and y is the pattern number in hexadecimal (y = 00h .. 07h) + */ + ret = st1202_write_reg(chip, (ST1202_PATTERN_PWM + 0x1 + (led_num * 2) + 0x18 * pattern), + value_h); + if (ret != 0) + return ret; + + return 0; +} + +static int st1202_duration_pattern_write(struct st1202_chip *chip, int pattern, + unsigned int value) +{ + return st1202_write_reg(chip, (ST1202_PATTERN_DUR + pattern), + st1202_prescalar_to_miliseconds(value)); +} + +static void st1202_brightness_set(struct led_classdev *led_cdev, + enum led_brightness value) +{ + struct st1202_led *led = cdev_to_st1202_led(led_cdev); + struct st1202_chip *chip = led->chip; + + guard(mutex)(&chip->lock); + + st1202_write_reg(chip, ST1202_ILED_REG0 + led->led_num, value); +} + +static enum led_brightness st1202_brightness_get(struct led_classdev *led_cdev) +{ + struct st1202_led *led = cdev_to_st1202_led(led_cdev); + struct st1202_chip *chip = led->chip; + u8 value = 0; + + guard(mutex)(&chip->lock); + + st1202_read_reg(chip, ST1202_ILED_REG0 + led->led_num, &value); + + return value; +} + +static int st1202_channel_set(struct st1202_chip *chip, int led_num, bool active) +{ + u8 chan_low, chan_high; + int ret; + + guard(mutex)(&chip->lock); + + if (led_num <= 7) { + ret = st1202_read_reg(chip, ST1202_CHAN_ENABLE_LOW, &chan_low); + if (ret < 0) + return ret; + + chan_low = active ? chan_low | BIT(led_num) : chan_low & ~BIT(led_num); + + ret = st1202_write_reg(chip, ST1202_CHAN_ENABLE_LOW, chan_low); + if (ret < 0) + return ret; + + } else { + ret = st1202_read_reg(chip, ST1202_CHAN_ENABLE_HIGH, &chan_high); + if (ret < 0) + return ret; + + chan_high = active ? chan_high | (BIT(led_num) >> 8) : + chan_high & ~(BIT(led_num) >> 8); + + ret = st1202_write_reg(chip, ST1202_CHAN_ENABLE_HIGH, chan_high); + if (ret < 0) + return ret; + } + + return 0; +} + +static int st1202_led_set(struct led_classdev *ldev, enum led_brightness value) +{ + struct st1202_led *led = cdev_to_st1202_led(ldev); + struct st1202_chip *chip = led->chip; + + return st1202_channel_set(chip, led->led_num, value == LED_OFF ? false : true); +} + +static int st1202_led_pattern_clear(struct led_classdev *ldev) +{ + struct st1202_led *led = cdev_to_st1202_led(ldev); + struct st1202_chip *chip = led->chip; + int ret; + + guard(mutex)(&chip->lock); + + for (int patt = 0; patt < ST1202_MAX_PATTERNS; patt++) { + ret = st1202_pwm_pattern_write(chip, led->led_num, patt, LED_OFF); + if (ret != 0) + return ret; + + ret = st1202_duration_pattern_write(chip, patt, ST1202_MILLIS_PATTERN_DUR_MIN); + if (ret != 0) + return ret; + } + + return 0; +} + +static int st1202_led_pattern_set(struct led_classdev *ldev, + struct led_pattern *pattern, + u32 len, int repeat) +{ + struct st1202_led *led = cdev_to_st1202_led(ldev); + struct st1202_chip *chip = led->chip; + int ret; + + if (len > ST1202_MAX_PATTERNS) + return -EINVAL; + + guard(mutex)(&chip->lock); + + for (int patt = 0; patt < len; patt++) { + if (pattern[patt].delta_t < ST1202_MILLIS_PATTERN_DUR_MIN || + pattern[patt].delta_t > ST1202_MILLIS_PATTERN_DUR_MAX) + return -EINVAL; + + ret = st1202_pwm_pattern_write(chip, led->led_num, patt, pattern[patt].brightness); + if (ret != 0) + return ret; + + ret = st1202_duration_pattern_write(chip, patt, pattern[patt].delta_t); + if (ret != 0) + return ret; + } + + ret = st1202_write_reg(chip, ST1202_PATTERN_REP, repeat); + if (ret != 0) + return ret; + + ret = st1202_write_reg(chip, ST1202_CONFIG_REG, (ST1202_CONFIG_REG_PATSR | + ST1202_CONFIG_REG_PATS | ST1202_CONFIG_REG_SHFT)); + if (ret != 0) + return ret; + + return 0; +} + +static int st1202_dt_init(struct st1202_chip *chip) +{ + struct device *dev = &chip->client->dev; + struct st1202_led *led; + int err, reg; + + for_each_available_child_of_node_scoped(dev_of_node(dev), child) { + struct led_init_data init_data = {}; + + err = of_property_read_u32(child, "reg", ®); + if (err) + return dev_err_probe(dev, err, "Invalid register\n"); + + led = &chip->leds[reg]; + led->is_active = true; + led->fwnode = of_fwnode_handle(child); + + led->led_cdev.max_brightness = U8_MAX; + led->led_cdev.brightness_set_blocking = st1202_led_set; + led->led_cdev.pattern_set = st1202_led_pattern_set; + led->led_cdev.pattern_clear = st1202_led_pattern_clear; + led->led_cdev.default_trigger = "pattern"; + + init_data.fwnode = led->fwnode; + init_data.devicename = "st1202"; + init_data.default_label = ":"; + + err = devm_led_classdev_register_ext(dev, &led->led_cdev, &init_data); + if (err < 0) + return dev_err_probe(dev, err, "Failed to register LED class device\n"); + + led->led_cdev.brightness_set = st1202_brightness_set; + led->led_cdev.brightness_get = st1202_brightness_get; + } + + return 0; +} + +static int st1202_setup(struct st1202_chip *chip) +{ + int ret; + + guard(mutex)(&chip->lock); + + /* + * Once the supply voltage is applied, the LED1202 executes some internal checks, + * afterwords it stops the oscillator and puts the internal LDO in quiescent mode. + * To start the device, EN bit must be set inside the “Device Enable” register at + * address 01h. As soon as EN is set, the LED1202 loads the adjustment parameters + * from the internal non-volatile memory and performs an auto-calibration procedure + * in order to increase the output current precision. + * Such initialization lasts about 6.5 ms. + */ + + /* Reset the chip during setup */ + ret = st1202_write_reg(chip, ST1202_DEV_ENABLE, ST1202_DEV_ENABLE_RESET); + if (ret < 0) + return ret; + + /* Enable phase-shift delay feature */ + ret = st1202_write_reg(chip, ST1202_CONFIG_REG, ST1202_CONFIG_REG_SHFT); + if (ret < 0) + return ret; + + /* Enable the device */ + ret = st1202_write_reg(chip, ST1202_DEV_ENABLE, ST1202_DEV_ENABLE_ON); + if (ret < 0) + return ret; + + /* Duration of initialization */ + usleep_range(6500, 10000); + + /* Deactivate all LEDS (channels) and activate only the ones found in Device Tree */ + ret = st1202_write_reg(chip, ST1202_CHAN_ENABLE_LOW, ST1202_CHAN_DISABLE_ALL); + if (ret < 0) + return ret; + + ret = st1202_write_reg(chip, ST1202_CHAN_ENABLE_HIGH, ST1202_CHAN_DISABLE_ALL); + if (ret < 0) + return ret; + + ret = st1202_write_reg(chip, ST1202_CONFIG_REG, + ST1202_CONFIG_REG_PATS | ST1202_CONFIG_REG_PATSR); + if (ret < 0) + return ret; + + return 0; +} + +static int st1202_probe(struct i2c_client *client) +{ + struct st1202_chip *chip; + struct st1202_led *led; + int ret; + + if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA)) + return dev_err_probe(&client->dev, -EIO, "SMBUS Byte Data not Supported\n"); + + chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + devm_mutex_init(&client->dev, &chip->lock); + chip->client = client; + + ret = st1202_dt_init(chip); + if (ret < 0) + return ret; + + ret = st1202_setup(chip); + if (ret < 0) + return ret; + + for (int i = 0; i < ST1202_MAX_LEDS; i++) { + led = &chip->leds[i]; + led->chip = chip; + led->led_num = i; + + if (!led->is_active) + continue; + + ret = st1202_channel_set(led->chip, led->led_num, true); + if (ret < 0) + return dev_err_probe(&client->dev, ret, + "Failed to activate LED channel\n"); + + ret = st1202_led_pattern_clear(&led->led_cdev); + if (ret < 0) + return dev_err_probe(&client->dev, ret, + "Failed to clear LED pattern\n"); + } + + return 0; +} + +static const struct i2c_device_id st1202_id[] = { + { "st1202-i2c" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(i2c, st1202_id); + +static const struct of_device_id st1202_dt_ids[] = { + { .compatible = "st,led1202" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, st1202_dt_ids); + +static struct i2c_driver st1202_driver = { + .driver = { + .name = "leds-st1202", + .of_match_table = of_match_ptr(st1202_dt_ids), + }, + .probe = st1202_probe, + .id_table = st1202_id, +}; +module_i2c_driver(st1202_driver); + +MODULE_AUTHOR("Remote Tech LTD"); +MODULE_DESCRIPTION("STMicroelectronics LED1202 : 12-channel constant current LED driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/leds/leds-turris-omnia.c b/drivers/leds/leds-turris-omnia.c index 2de825ac08b3..4fe1a9c0bc1b 100644 --- a/drivers/leds/leds-turris-omnia.c +++ b/drivers/leds/leds-turris-omnia.c @@ -2,7 +2,7 @@ /* * CZ.NIC's Turris Omnia LEDs driver * - * 2020, 2023 by Marek Behún + * 2020, 2023, 2024 by Marek Behún */ #include @@ -10,35 +10,23 @@ #include #include #include +#include #define OMNIA_BOARD_LEDS 12 #define OMNIA_LED_NUM_CHANNELS 3 -/* MCU controller commands at I2C address 0x2a */ -#define OMNIA_MCU_I2C_ADDR 0x2a - -#define CMD_GET_STATUS_WORD 0x01 -#define STS_FEATURES_SUPPORTED BIT(2) - -#define CMD_GET_FEATURES 0x10 -#define FEAT_LED_GAMMA_CORRECTION BIT(5) - -/* LED controller commands at I2C address 0x2b */ -#define CMD_LED_MODE 0x03 -#define CMD_LED_MODE_LED(l) ((l) & 0x0f) -#define CMD_LED_MODE_USER 0x10 - -#define CMD_LED_STATE 0x04 -#define CMD_LED_STATE_LED(l) ((l) & 0x0f) -#define CMD_LED_STATE_ON 0x10 - -#define CMD_LED_COLOR 0x05 -#define CMD_LED_SET_BRIGHTNESS 0x07 -#define CMD_LED_GET_BRIGHTNESS 0x08 - -#define CMD_SET_GAMMA_CORRECTION 0x30 -#define CMD_GET_GAMMA_CORRECTION 0x31 +/* MCU controller I2C address 0x2a, needed for detecting MCU features */ +#define OMNIA_MCU_I2C_ADDR 0x2a +/** + * struct omnia_led - per-LED part of driver private data structure + * @mc_cdev: multi-color LED class device + * @subled_info: per-channel information + * @cached_channels: cached values of per-channel brightness that was sent to the MCU + * @on: whether the LED was set on + * @hwtrig: whether the LED blinking was offloaded to the MCU + * @reg: LED identifier to the MCU + */ struct omnia_led { struct led_classdev_mc mc_cdev; struct mc_subled subled_info[OMNIA_LED_NUM_CHANNELS]; @@ -49,73 +37,38 @@ struct omnia_led { #define to_omnia_led(l) container_of(l, struct omnia_led, mc_cdev) +/** + * struct omnia_leds - driver private data structure + * @client: I2C client device + * @lock: mutex to protect cached state + * @has_gamma_correction: whether the MCU firmware supports gamma correction + * @brightness_knode: kernel node of the "brightness" device sysfs attribute (this is the + * driver specific global brightness, not the LED classdev brightness) + * @leds: flexible array of per-LED data + */ struct omnia_leds { struct i2c_client *client; struct mutex lock; bool has_gamma_correction; + struct kernfs_node *brightness_knode; struct omnia_led leds[]; }; -static int omnia_cmd_write_u8(const struct i2c_client *client, u8 cmd, u8 val) +static int omnia_cmd_set_color(const struct i2c_client *client, u8 led, u8 r, u8 g, u8 b) { - u8 buf[2] = { cmd, val }; - int ret; + u8 buf[5] = { OMNIA_CMD_LED_COLOR, led, r, g, b }; - ret = i2c_master_send(client, buf, sizeof(buf)); - - return ret < 0 ? ret : 0; -} - -static int omnia_cmd_read_raw(struct i2c_adapter *adapter, u8 addr, u8 cmd, - void *reply, size_t len) -{ - struct i2c_msg msgs[2]; - int ret; - - msgs[0].addr = addr; - msgs[0].flags = 0; - msgs[0].len = 1; - msgs[0].buf = &cmd; - msgs[1].addr = addr; - msgs[1].flags = I2C_M_RD; - msgs[1].len = len; - msgs[1].buf = reply; - - ret = i2c_transfer(adapter, msgs, ARRAY_SIZE(msgs)); - if (likely(ret == ARRAY_SIZE(msgs))) - return 0; - else if (ret < 0) - return ret; - else - return -EIO; -} - -static int omnia_cmd_read_u8(const struct i2c_client *client, u8 cmd) -{ - u8 reply; - int err; - - err = omnia_cmd_read_raw(client->adapter, client->addr, cmd, &reply, 1); - if (err) - return err; - - return reply; + return omnia_cmd_write(client, buf, sizeof(buf)); } static int omnia_led_send_color_cmd(const struct i2c_client *client, struct omnia_led *led) { - char cmd[5]; int ret; - cmd[0] = CMD_LED_COLOR; - cmd[1] = led->reg; - cmd[2] = led->subled_info[0].brightness; - cmd[3] = led->subled_info[1].brightness; - cmd[4] = led->subled_info[2].brightness; - /* Send the color change command */ - ret = i2c_master_send(client, cmd, 5); + ret = omnia_cmd_set_color(client, led->reg, led->subled_info[0].brightness, + led->subled_info[1].brightness, led->subled_info[2].brightness); if (ret < 0) return ret; @@ -170,12 +123,12 @@ static int omnia_led_brightness_set_blocking(struct led_classdev *cdev, * is not being blinked by HW. */ if (!err && !led->hwtrig && !brightness != !led->on) { - u8 state = CMD_LED_STATE_LED(led->reg); + u8 state = OMNIA_CMD_LED_STATE_LED(led->reg); if (brightness) - state |= CMD_LED_STATE_ON; + state |= OMNIA_CMD_LED_STATE_ON; - err = omnia_cmd_write_u8(leds->client, CMD_LED_STATE, state); + err = omnia_cmd_write_u8(leds->client, OMNIA_CMD_LED_STATE, state); if (!err) led->on = !!brightness; } @@ -210,8 +163,8 @@ static int omnia_hwtrig_activate(struct led_classdev *cdev) if (!err) { /* Put the LED into MCU controlled mode */ - err = omnia_cmd_write_u8(leds->client, CMD_LED_MODE, - CMD_LED_MODE_LED(led->reg)); + err = omnia_cmd_write_u8(leds->client, OMNIA_CMD_LED_MODE, + OMNIA_CMD_LED_MODE_LED(led->reg)); if (!err) led->hwtrig = true; } @@ -232,9 +185,8 @@ static void omnia_hwtrig_deactivate(struct led_classdev *cdev) led->hwtrig = false; /* Put the LED into software mode */ - err = omnia_cmd_write_u8(leds->client, CMD_LED_MODE, - CMD_LED_MODE_LED(led->reg) | - CMD_LED_MODE_USER); + err = omnia_cmd_write_u8(leds->client, OMNIA_CMD_LED_MODE, + OMNIA_CMD_LED_MODE_LED(led->reg) | OMNIA_CMD_LED_MODE_USER); mutex_unlock(&leds->lock); @@ -300,38 +252,26 @@ static int omnia_led_register(struct i2c_client *client, struct omnia_led *led, */ cdev->default_trigger = omnia_hw_trigger.name; - /* put the LED into software mode */ - ret = omnia_cmd_write_u8(client, CMD_LED_MODE, - CMD_LED_MODE_LED(led->reg) | - CMD_LED_MODE_USER); - if (ret) { - dev_err(dev, "Cannot set LED %pOF to software mode: %i\n", np, - ret); - return ret; - } + /* Put the LED into software mode */ + ret = omnia_cmd_write_u8(client, OMNIA_CMD_LED_MODE, OMNIA_CMD_LED_MODE_LED(led->reg) | + OMNIA_CMD_LED_MODE_USER); + if (ret) + return dev_err_probe(dev, ret, "Cannot set LED %pOF to software mode\n", np); - /* disable the LED */ - ret = omnia_cmd_write_u8(client, CMD_LED_STATE, - CMD_LED_STATE_LED(led->reg)); - if (ret) { - dev_err(dev, "Cannot set LED %pOF brightness: %i\n", np, ret); - return ret; - } + /* Disable the LED */ + ret = omnia_cmd_write_u8(client, OMNIA_CMD_LED_STATE, OMNIA_CMD_LED_STATE_LED(led->reg)); + if (ret) + return dev_err_probe(dev, ret, "Cannot set LED %pOF brightness\n", np); /* Set initial color and cache it */ ret = omnia_led_send_color_cmd(client, led); - if (ret < 0) { - dev_err(dev, "Cannot set LED %pOF initial color: %i\n", np, - ret); - return ret; - } + if (ret < 0) + return dev_err_probe(dev, ret, "Cannot set LED %pOF initial color\n", np); ret = devm_led_classdev_multicolor_register_ext(dev, &led->mc_cdev, &init_data); - if (ret < 0) { - dev_err(dev, "Cannot register LED %pOF: %i\n", np, ret); - return ret; - } + if (ret < 0) + return dev_err_probe(dev, ret, "Cannot register LED %pOF\n", np); return 1; } @@ -351,14 +291,14 @@ static ssize_t brightness_show(struct device *dev, struct device_attribute *a, char *buf) { struct i2c_client *client = to_i2c_client(dev); - int ret; + u8 reply; + int err; - ret = omnia_cmd_read_u8(client, CMD_LED_GET_BRIGHTNESS); + err = omnia_cmd_read_u8(client, OMNIA_CMD_GET_BRIGHTNESS, &reply); + if (err < 0) + return err; - if (ret < 0) - return ret; - - return sysfs_emit(buf, "%d\n", ret); + return sysfs_emit(buf, "%d\n", reply); } static ssize_t brightness_store(struct device *dev, struct device_attribute *a, @@ -374,7 +314,7 @@ static ssize_t brightness_store(struct device *dev, struct device_attribute *a, if (brightness > 100) return -EINVAL; - err = omnia_cmd_write_u8(client, CMD_LED_SET_BRIGHTNESS, brightness); + err = omnia_cmd_write_u8(client, OMNIA_CMD_SET_BRIGHTNESS, brightness); return err ?: count; } @@ -385,17 +325,16 @@ static ssize_t gamma_correction_show(struct device *dev, { struct i2c_client *client = to_i2c_client(dev); struct omnia_leds *leds = i2c_get_clientdata(client); - int ret; + u8 reply = 0; + int err; if (leds->has_gamma_correction) { - ret = omnia_cmd_read_u8(client, CMD_GET_GAMMA_CORRECTION); - if (ret < 0) - return ret; - } else { - ret = 0; + err = omnia_cmd_read_u8(client, OMNIA_CMD_GET_GAMMA_CORRECTION, &reply); + if (err < 0) + return err; } - return sysfs_emit(buf, "%d\n", !!ret); + return sysfs_emit(buf, "%d\n", !!reply); } static ssize_t gamma_correction_store(struct device *dev, @@ -413,7 +352,7 @@ static ssize_t gamma_correction_store(struct device *dev, if (kstrtobool(buf, &val) < 0) return -EINVAL; - err = omnia_cmd_write_u8(client, CMD_SET_GAMMA_CORRECTION, val); + err = omnia_cmd_write_u8(client, OMNIA_CMD_SET_GAMMA_CORRECTION, val); return err ?: count; } @@ -426,26 +365,104 @@ static struct attribute *omnia_led_controller_attrs[] = { }; ATTRIBUTE_GROUPS(omnia_led_controller); -static int omnia_mcu_get_features(const struct i2c_client *client) +static irqreturn_t omnia_brightness_changed_threaded_fn(int irq, void *data) +{ + struct omnia_leds *leds = data; + + if (unlikely(!leds->brightness_knode)) { + /* + * Note that sysfs_get_dirent() may sleep. This is okay, because we are in threaded + * context. + */ + leds->brightness_knode = sysfs_get_dirent(leds->client->dev.kobj.sd, "brightness"); + if (!leds->brightness_knode) + return IRQ_NONE; + } + + sysfs_notify_dirent(leds->brightness_knode); + + return IRQ_HANDLED; +} + +static void omnia_brightness_knode_put(void *data) +{ + struct omnia_leds *leds = data; + + if (leds->brightness_knode) + sysfs_put(leds->brightness_knode); +} + +static int omnia_request_brightness_irq(struct omnia_leds *leds) +{ + struct device *dev = &leds->client->dev; + int ret; + + if (!leds->client->irq) { + dev_info(dev, + "Brightness change interrupt supported by MCU firmware but not described in device-tree\n"); + + return 0; + } + + /* + * Registering the brightness_knode destructor before requesting the IRQ ensures that on + * removal the brightness_knode sysfs node is put only after the IRQ is freed. + * This is needed because the interrupt handler uses the knode. + */ + ret = devm_add_action(dev, omnia_brightness_knode_put, leds); + if (ret < 0) + return ret; + + return devm_request_threaded_irq(dev, leds->client->irq, NULL, + omnia_brightness_changed_threaded_fn, IRQF_ONESHOT, + "leds-turris-omnia", leds); +} + +static int omnia_mcu_get_features(const struct i2c_client *mcu_client) { u16 reply; int err; - err = omnia_cmd_read_raw(client->adapter, OMNIA_MCU_I2C_ADDR, - CMD_GET_STATUS_WORD, &reply, sizeof(reply)); + err = omnia_cmd_read_u16(mcu_client, OMNIA_CMD_GET_STATUS_WORD, &reply); if (err) return err; - /* Check whether MCU firmware supports the CMD_GET_FEAUTRES command */ - if (!(le16_to_cpu(reply) & STS_FEATURES_SUPPORTED)) + /* Check whether MCU firmware supports the OMNIA_CMD_GET_FEAUTRES command */ + if (!(reply & OMNIA_STS_FEATURES_SUPPORTED)) return 0; - err = omnia_cmd_read_raw(client->adapter, OMNIA_MCU_I2C_ADDR, - CMD_GET_FEATURES, &reply, sizeof(reply)); + err = omnia_cmd_read_u16(mcu_client, OMNIA_CMD_GET_FEATURES, &reply); if (err) return err; - return le16_to_cpu(reply); + return reply; +} + +static int omnia_match_mcu_client(struct device *dev, const void *data) +{ + struct i2c_client *client; + + client = i2c_verify_client(dev); + if (!client) + return 0; + + return client->addr == OMNIA_MCU_I2C_ADDR; +} + +static int omnia_find_mcu_and_get_features(struct device *dev) +{ + struct device *mcu_dev; + int ret; + + mcu_dev = device_find_child(dev->parent, NULL, omnia_match_mcu_client); + if (!mcu_dev) + return -ENODEV; + + ret = omnia_mcu_get_features(i2c_verify_client(mcu_dev)); + + put_device(mcu_dev); + + return ret; } static int omnia_leds_probe(struct i2c_client *client) @@ -457,13 +474,10 @@ static int omnia_leds_probe(struct i2c_client *client) int ret, count; count = of_get_available_child_count(np); - if (!count) { - dev_err(dev, "LEDs are not defined in device tree!\n"); - return -ENODEV; - } else if (count > OMNIA_BOARD_LEDS) { - dev_err(dev, "Too many LEDs defined in device tree!\n"); - return -EINVAL; - } + if (count == 0) + return dev_err_probe(dev, -ENODEV, "LEDs are not defined in device tree!\n"); + if (count > OMNIA_BOARD_LEDS) + return dev_err_probe(dev, -EINVAL, "Too many LEDs defined in device tree!\n"); leds = devm_kzalloc(dev, struct_size(leds, leds, count), GFP_KERNEL); if (!leds) @@ -472,28 +486,23 @@ static int omnia_leds_probe(struct i2c_client *client) leds->client = client; i2c_set_clientdata(client, leds); - ret = omnia_mcu_get_features(client); - if (ret < 0) { - dev_err(dev, "Cannot determine MCU supported features: %d\n", - ret); - return ret; - } + ret = omnia_find_mcu_and_get_features(dev); + if (ret < 0) + return dev_err_probe(dev, ret, "Cannot determine MCU supported features\n"); - leds->has_gamma_correction = ret & FEAT_LED_GAMMA_CORRECTION; - if (!leds->has_gamma_correction) { - dev_info(dev, - "Your board's MCU firmware does not support the LED gamma correction feature.\n"); - dev_info(dev, - "Consider upgrading MCU firmware with the omnia-mcutool utility.\n"); + leds->has_gamma_correction = ret & OMNIA_FEAT_LED_GAMMA_CORRECTION; + + if (ret & OMNIA_FEAT_BRIGHTNESS_INT) { + ret = omnia_request_brightness_irq(leds); + if (ret < 0) + return dev_err_probe(dev, ret, "Cannot request brightness IRQ\n"); } mutex_init(&leds->lock); ret = devm_led_trigger_register(dev, &omnia_hw_trigger); - if (ret < 0) { - dev_err(dev, "Cannot register private LED trigger: %d\n", ret); - return ret; - } + if (ret < 0) + return dev_err_probe(dev, ret, "Cannot register private LED trigger\n"); led = &leds->leds[0]; for_each_available_child_of_node_scoped(np, child) { @@ -509,20 +518,11 @@ static int omnia_leds_probe(struct i2c_client *client) static void omnia_leds_remove(struct i2c_client *client) { - u8 buf[5]; + /* Put all LEDs into default (HW triggered) mode */ + omnia_cmd_write_u8(client, OMNIA_CMD_LED_MODE, OMNIA_CMD_LED_MODE_LED(OMNIA_BOARD_LEDS)); - /* put all LEDs into default (HW triggered) mode */ - omnia_cmd_write_u8(client, CMD_LED_MODE, - CMD_LED_MODE_LED(OMNIA_BOARD_LEDS)); - - /* set all LEDs color to [255, 255, 255] */ - buf[0] = CMD_LED_COLOR; - buf[1] = OMNIA_BOARD_LEDS; - buf[2] = 255; - buf[3] = 255; - buf[4] = 255; - - i2c_master_send(client, buf, 5); + /* Set all LEDs color to [255, 255, 255] */ + omnia_cmd_set_color(client, OMNIA_BOARD_LEDS, 255, 255, 255); } static const struct of_device_id of_omnia_leds_match[] = { diff --git a/drivers/leds/leds-upboard.c b/drivers/leds/leds-upboard.c new file mode 100644 index 000000000000..b350eb294280 --- /dev/null +++ b/drivers/leds/leds-upboard.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * UP board LED driver. + * + * Copyright (c) AAEON. All rights reserved. + * Copyright (C) 2024 Bootlin + * + * Author: Gary Wang + * Author: Thomas Richard + */ + +#include +#include +#include +#include +#include +#include +#include + +#define led_cdev_to_led_upboard(c) container_of(c, struct upboard_led, cdev) + +struct upboard_led { + struct regmap_field *field; + struct led_classdev cdev; +}; + +struct upboard_led_profile { + const char *name; + unsigned int bit; +}; + +static struct upboard_led_profile upboard_up_led_profile[] = { + { "upboard:yellow:" LED_FUNCTION_STATUS, 0 }, + { "upboard:green:" LED_FUNCTION_STATUS, 1 }, + { "upboard:red:" LED_FUNCTION_STATUS, 2 }, +}; + +static struct upboard_led_profile upboard_up2_led_profile[] = { + { "upboard:blue:" LED_FUNCTION_STATUS, 0 }, + { "upboard:yellow:" LED_FUNCTION_STATUS, 1 }, + { "upboard:green:" LED_FUNCTION_STATUS, 2 }, + { "upboard:red:" LED_FUNCTION_STATUS, 3 }, +}; + +static enum led_brightness upboard_led_brightness_get(struct led_classdev *cdev) +{ + struct upboard_led *led = led_cdev_to_led_upboard(cdev); + int brightness, ret; + + ret = regmap_field_read(led->field, &brightness); + + return ret ? LED_OFF : brightness; +}; + +static int upboard_led_brightness_set(struct led_classdev *cdev, enum led_brightness brightness) +{ + struct upboard_led *led = led_cdev_to_led_upboard(cdev); + + return regmap_field_write(led->field, brightness != LED_OFF); +}; + +static int upboard_led_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct upboard_fpga *fpga = dev_get_drvdata(dev->parent); + struct upboard_led_profile *led_profile; + struct upboard_led *led; + int led_instances, ret, i; + + switch (fpga->fpga_data->type) { + case UPBOARD_UP_FPGA: + led_profile = upboard_up_led_profile; + led_instances = ARRAY_SIZE(upboard_up_led_profile); + break; + case UPBOARD_UP2_FPGA: + led_profile = upboard_up2_led_profile; + led_instances = ARRAY_SIZE(upboard_up2_led_profile); + break; + default: + return dev_err_probe(dev, -EINVAL, "Unknown device type %d\n", + fpga->fpga_data->type); + } + + for (i = 0; i < led_instances; i++) { + const struct reg_field fldconf = { + .reg = UPBOARD_REG_FUNC_EN0, + .lsb = led_profile[i].bit, + .msb = led_profile[i].bit, + }; + + led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL); + if (!led) + return -ENOMEM; + + led->field = devm_regmap_field_alloc(&pdev->dev, fpga->regmap, fldconf); + if (IS_ERR(led->field)) + return PTR_ERR(led->field); + + led->cdev.brightness_get = upboard_led_brightness_get; + led->cdev.brightness_set_blocking = upboard_led_brightness_set; + led->cdev.max_brightness = LED_ON; + + led->cdev.name = led_profile[i].name; + + ret = devm_led_classdev_register(dev, &led->cdev); + if (ret) + return ret; + } + + return 0; +} + +static struct platform_driver upboard_led_driver = { + .driver = { + .name = "upboard-leds", + }, + .probe = upboard_led_probe, +}; + +module_platform_driver(upboard_led_driver); + +MODULE_AUTHOR("Gary Wang "); +MODULE_AUTHOR("Thomas Richard "); +MODULE_DESCRIPTION("UP Board LED driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:upboard-led"); diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h index d7999e7372a4..bee46651e068 100644 --- a/drivers/leds/leds.h +++ b/drivers/leds/leds.h @@ -22,10 +22,10 @@ void led_stop_software_blink(struct led_classdev *led_cdev); void led_set_brightness_nopm(struct led_classdev *led_cdev, unsigned int value); void led_set_brightness_nosleep(struct led_classdev *led_cdev, unsigned int value); ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count); ssize_t led_trigger_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count); extern struct rw_semaphore leds_list_lock; diff --git a/drivers/leds/rgb/leds-pwm-multicolor.c b/drivers/leds/rgb/leds-pwm-multicolor.c index e1a81e0109e8..f80a06cc31f8 100644 --- a/drivers/leds/rgb/leds-pwm-multicolor.c +++ b/drivers/leds/rgb/leds-pwm-multicolor.c @@ -50,7 +50,13 @@ static int led_pwm_mc_set(struct led_classdev *cdev, duty = priv->leds[i].state.period - duty; priv->leds[i].state.duty_cycle = duty; - priv->leds[i].state.enabled = duty > 0; + /* + * Disabling a PWM doesn't guarantee that it emits the inactive level. + * So keep it on. Only for suspending the PWM should be disabled because + * otherwise it refuses to suspend. The possible downside is that the + * LED might stay (or even go) on. + */ + priv->leds[i].state.enabled = !(cdev->flags & LED_SUSPENDED); ret = pwm_apply_might_sleep(priv->leds[i].pwm, &priv->leds[i].state); if (ret) diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c index 33cbf8413658..b3ee33aed36e 100644 --- a/drivers/leds/trigger/ledtrig-activity.c +++ b/drivers/leds/trigger/ledtrig-activity.c @@ -156,7 +156,7 @@ static ssize_t led_invert_show(struct device *dev, { struct activity_data *activity_data = led_trigger_get_drvdata(dev); - return sprintf(buf, "%u\n", activity_data->invert); + return sprintf(buf, "%d\n", activity_data->invert); } static ssize_t led_invert_store(struct device *dev, diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index 4b0863db901a..c15efe3e5078 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -605,6 +605,8 @@ static int netdev_trig_notify(struct notifier_block *nb, trigger_data->net_dev = NULL; break; case NETDEV_UP: + trigger_data->hw_control = can_hw_control(trigger_data); + fallthrough; case NETDEV_CHANGE: get_device_state(trigger_data); /* Refresh link_speed visibility */ diff --git a/drivers/macintosh/Kconfig b/drivers/macintosh/Kconfig index fb38f684444f..d00e713c1092 100644 --- a/drivers/macintosh/Kconfig +++ b/drivers/macintosh/Kconfig @@ -120,6 +120,7 @@ config PMAC_MEDIABAY config PMAC_BACKLIGHT bool "Backlight control for LCD screens" depends on PPC_PMAC && ADB_PMU && FB = y && (BROKEN || !PPC64) + depends on BACKLIGHT_CLASS_DEVICE=y select FB_BACKLIGHT help Say Y here to enable Macintosh specific extensions of the generic diff --git a/drivers/macintosh/mac_hid.c b/drivers/macintosh/mac_hid.c index b461b1bed25b..369d72f59b3c 100644 --- a/drivers/macintosh/mac_hid.c +++ b/drivers/macintosh/mac_hid.c @@ -215,7 +215,7 @@ static int mac_hid_toggle_emumouse(const struct ctl_table *table, int write, } /* file(s) in /proc/sys/dev/mac_hid */ -static struct ctl_table mac_hid_files[] = { +static const struct ctl_table mac_hid_files[] = { { .procname = "mouse_button_emulation", .data = &mouse_emulate_buttons, diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index a01bc5090cdf..a1534cc6c641 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -492,11 +492,7 @@ int __init smu_init (void) goto fail_np; } - smu = memblock_alloc(sizeof(struct smu_device), SMP_CACHE_BYTES); - if (!smu) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct smu_device)); - + smu = memblock_alloc_or_panic(sizeof(struct smu_device), SMP_CACHE_BYTES); spin_lock_init(&smu->lock); INIT_LIST_HEAD(&smu->cmd_list); INIT_LIST_HEAD(&smu->cmd_i2c_list); diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig index 8ecba7fb999e..ed52db272f4d 100644 --- a/drivers/mailbox/Kconfig +++ b/drivers/mailbox/Kconfig @@ -36,6 +36,17 @@ config ARM_MHU_V3 that provides different means of transports: supported extensions will be discovered and possibly managed at probe-time. +config EXYNOS_MBOX + tristate "Exynos Mailbox" + depends on ARCH_EXYNOS || COMPILE_TEST + help + Say Y here if you want to build the Samsung Exynos Mailbox controller + driver. The controller has 16 flag bits for hardware interrupt + generation and a shared register for passing mailbox messages. + When the controller is used by the ACPM interface the shared register + is ignored and the mailbox controller acts as a doorbell that raises + the interrupt to the ACPM firmware. + config IMX_MBOX tristate "i.MX Mailbox" depends on ARCH_MXC || COMPILE_TEST @@ -178,6 +189,19 @@ config POLARFIRE_SOC_MAILBOX If unsure, say N. +config MCHP_SBI_IPC_MBOX + tristate "Microchip Inter-processor Communication (IPC) SBI driver" + depends on RISCV_SBI || COMPILE_TEST + depends on ARCH_MICROCHIP + help + Mailbox implementation for Microchip devices with an + Inter-process communication (IPC) controller. + + To compile this driver as a module, choose M here. the + module will be called mailbox-mchp-ipc-sbi. + + If unsure, say N. + config QCOM_APCS_IPC tristate "Qualcomm APCS IPC driver" depends on ARCH_QCOM || COMPILE_TEST diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile index 5f4f5b0ce2cc..9a1542b55539 100644 --- a/drivers/mailbox/Makefile +++ b/drivers/mailbox/Makefile @@ -11,6 +11,8 @@ obj-$(CONFIG_ARM_MHU_V2) += arm_mhuv2.o obj-$(CONFIG_ARM_MHU_V3) += arm_mhuv3.o +obj-$(CONFIG_EXYNOS_MBOX) += exynos-mailbox.o + obj-$(CONFIG_IMX_MBOX) += imx-mailbox.o obj-$(CONFIG_ARMADA_37XX_RWTM_MBOX) += armada-37xx-rwtm-mailbox.o @@ -45,6 +47,8 @@ obj-$(CONFIG_BCM_FLEXRM_MBOX) += bcm-flexrm-mailbox.o obj-$(CONFIG_POLARFIRE_SOC_MAILBOX) += mailbox-mpfs.o +obj-$(CONFIG_MCHP_SBI_IPC_MBOX) += mailbox-mchp-ipc-sbi.o + obj-$(CONFIG_QCOM_APCS_IPC) += qcom-apcs-ipc-mailbox.o obj-$(CONFIG_TEGRA_HSP_MBOX) += tegra-hsp.o diff --git a/drivers/mailbox/exynos-mailbox.c b/drivers/mailbox/exynos-mailbox.c new file mode 100644 index 000000000000..20049f0ec5ff --- /dev/null +++ b/drivers/mailbox/exynos-mailbox.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2020 Samsung Electronics Co., Ltd. + * Copyright 2020 Google LLC. + * Copyright 2024 Linaro Ltd. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define EXYNOS_MBOX_MCUCTRL 0x0 /* Mailbox Control Register */ +#define EXYNOS_MBOX_INTCR0 0x24 /* Interrupt Clear Register 0 */ +#define EXYNOS_MBOX_INTMR0 0x28 /* Interrupt Mask Register 0 */ +#define EXYNOS_MBOX_INTSR0 0x2c /* Interrupt Status Register 0 */ +#define EXYNOS_MBOX_INTMSR0 0x30 /* Interrupt Mask Status Register 0 */ +#define EXYNOS_MBOX_INTGR1 0x40 /* Interrupt Generation Register 1 */ +#define EXYNOS_MBOX_INTMR1 0x48 /* Interrupt Mask Register 1 */ +#define EXYNOS_MBOX_INTSR1 0x4c /* Interrupt Status Register 1 */ +#define EXYNOS_MBOX_INTMSR1 0x50 /* Interrupt Mask Status Register 1 */ + +#define EXYNOS_MBOX_INTMR0_MASK GENMASK(15, 0) +#define EXYNOS_MBOX_INTGR1_MASK GENMASK(15, 0) + +#define EXYNOS_MBOX_CHAN_COUNT HWEIGHT32(EXYNOS_MBOX_INTGR1_MASK) + +/** + * struct exynos_mbox - driver's private data. + * @regs: mailbox registers base address. + * @mbox: pointer to the mailbox controller. + * @pclk: pointer to the mailbox peripheral clock. + */ +struct exynos_mbox { + void __iomem *regs; + struct mbox_controller *mbox; + struct clk *pclk; +}; + +static int exynos_mbox_send_data(struct mbox_chan *chan, void *data) +{ + struct device *dev = chan->mbox->dev; + struct exynos_mbox *exynos_mbox = dev_get_drvdata(dev); + struct exynos_mbox_msg *msg = data; + + if (msg->chan_id >= exynos_mbox->mbox->num_chans) { + dev_err(dev, "Invalid channel ID %d\n", msg->chan_id); + return -EINVAL; + } + + if (msg->chan_type != EXYNOS_MBOX_CHAN_TYPE_DOORBELL) { + dev_err(dev, "Unsupported channel type [%d]\n", msg->chan_type); + return -EINVAL; + }; + + writel(BIT(msg->chan_id), exynos_mbox->regs + EXYNOS_MBOX_INTGR1); + + return 0; +} + +static const struct mbox_chan_ops exynos_mbox_chan_ops = { + .send_data = exynos_mbox_send_data, +}; + +static struct mbox_chan *exynos_mbox_of_xlate(struct mbox_controller *mbox, + const struct of_phandle_args *sp) +{ + int i; + + if (sp->args_count != 0) + return ERR_PTR(-EINVAL); + + /* + * Return the first available channel. When we don't pass the + * channel ID from device tree, each channel populated by the driver is + * just a software construct or a virtual channel. We use 'void *data' + * in send_data() to pass the channel identifiers. + */ + for (i = 0; i < mbox->num_chans; i++) + if (mbox->chans[i].cl == NULL) + return &mbox->chans[i]; + return ERR_PTR(-EINVAL); +} + +static const struct of_device_id exynos_mbox_match[] = { + { .compatible = "google,gs101-mbox" }, + {}, +}; +MODULE_DEVICE_TABLE(of, exynos_mbox_match); + +static int exynos_mbox_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct exynos_mbox *exynos_mbox; + struct mbox_controller *mbox; + struct mbox_chan *chans; + int i; + + exynos_mbox = devm_kzalloc(dev, sizeof(*exynos_mbox), GFP_KERNEL); + if (!exynos_mbox) + return -ENOMEM; + + mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL); + if (!mbox) + return -ENOMEM; + + chans = devm_kcalloc(dev, EXYNOS_MBOX_CHAN_COUNT, sizeof(*chans), + GFP_KERNEL); + if (!chans) + return -ENOMEM; + + exynos_mbox->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(exynos_mbox->regs)) + return PTR_ERR(exynos_mbox->regs); + + exynos_mbox->pclk = devm_clk_get_enabled(dev, "pclk"); + if (IS_ERR(exynos_mbox->pclk)) + return dev_err_probe(dev, PTR_ERR(exynos_mbox->pclk), + "Failed to enable clock.\n"); + + mbox->num_chans = EXYNOS_MBOX_CHAN_COUNT; + mbox->chans = chans; + mbox->dev = dev; + mbox->ops = &exynos_mbox_chan_ops; + mbox->of_xlate = exynos_mbox_of_xlate; + + for (i = 0; i < EXYNOS_MBOX_CHAN_COUNT; i++) + chans[i].mbox = mbox; + + exynos_mbox->mbox = mbox; + + platform_set_drvdata(pdev, exynos_mbox); + + /* Mask out all interrupts. We support just polling channels for now. */ + writel(EXYNOS_MBOX_INTMR0_MASK, exynos_mbox->regs + EXYNOS_MBOX_INTMR0); + + return devm_mbox_controller_register(dev, mbox); +} + +static struct platform_driver exynos_mbox_driver = { + .probe = exynos_mbox_probe, + .driver = { + .name = "exynos-acpm-mbox", + .of_match_table = exynos_mbox_match, + }, +}; +module_platform_driver(exynos_mbox_driver); + +MODULE_AUTHOR("Tudor Ambarus "); +MODULE_DESCRIPTION("Samsung Exynos mailbox driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mailbox/mailbox-mchp-ipc-sbi.c b/drivers/mailbox/mailbox-mchp-ipc-sbi.c new file mode 100644 index 000000000000..a6e52009a424 --- /dev/null +++ b/drivers/mailbox/mailbox-mchp-ipc-sbi.c @@ -0,0 +1,504 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Microchip Inter-Processor communication (IPC) driver + * + * Copyright (c) 2021 - 2024 Microchip Technology Inc. All rights reserved. + * + * Author: Valentina Fernandez + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define IRQ_STATUS_BITS 12 +#define NUM_CHANS_PER_CLUSTER 5 +#define IPC_DMA_BIT_MASK 32 +#define SBI_EXT_MICROCHIP_TECHNOLOGY (SBI_EXT_VENDOR_START | \ + MICROCHIP_VENDOR_ID) + +enum { + SBI_EXT_IPC_PROBE = 0x100, + SBI_EXT_IPC_CH_INIT, + SBI_EXT_IPC_SEND, + SBI_EXT_IPC_RECEIVE, + SBI_EXT_IPC_STATUS, +}; + +enum ipc_hw { + MIV_IHC, +}; + +/** + * struct mchp_ipc_mbox_info - IPC probe message format + * + * @hw_type: IPC implementation available in the hardware + * @num_channels: number of IPC channels available in the hardware + * + * Used to retrieve information on the IPC implementation + * using the SBI_EXT_IPC_PROBE SBI function id. + */ +struct mchp_ipc_mbox_info { + enum ipc_hw hw_type; + u8 num_channels; +}; + +/** + * struct mchp_ipc_init - IPC channel init message format + * + * @max_msg_size: maxmimum message size in bytes of a given channel + * + * struct used by the SBI_EXT_IPC_CH_INIT SBI function id to get + * the max message size in bytes of the initialized channel. + */ +struct mchp_ipc_init { + u16 max_msg_size; +}; + +/** + * struct mchp_ipc_status - IPC status message format + * + * @status: interrupt status for all channels associated to a cluster + * @cluster: specifies the cluster instance that originated an irq + * + * struct used by the SBI_EXT_IPC_STATUS SBI function id to get + * the message present and message clear interrupt status for all the + * channels associated to a cluster. + */ +struct mchp_ipc_status { + u32 status; + u8 cluster; +}; + +/** + * struct mchp_ipc_sbi_msg - IPC SBI payload message + * + * @buf_addr: physical address where the received data should be copied to + * @size: maximum size(in bytes) that can be stored in the buffer pointed to by `buf` + * @irq_type: mask representing the irq types that triggered an irq + * + * struct used by the SBI_EXT_IPC_SEND/SBI_EXT_IPC_RECEIVE SBI function + * ids to send/receive a message from an associated processor using + * the IPC. + */ +struct mchp_ipc_sbi_msg { + u64 buf_addr; + u16 size; + u8 irq_type; +}; + +struct mchp_ipc_cluster_cfg { + void *buf_base; + phys_addr_t buf_base_addr; + int irq; +}; + +struct mchp_ipc_sbi_mbox { + struct device *dev; + struct mbox_chan *chans; + struct mchp_ipc_cluster_cfg *cluster_cfg; + void *buf_base; + unsigned long buf_base_addr; + struct mbox_controller controller; + enum ipc_hw hw_type; +}; + +static int mchp_ipc_sbi_chan_send(u32 command, u32 channel, unsigned long address) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_MICROCHIP_TECHNOLOGY, command, channel, + address, 0, 0, 0, 0); + + if (ret.error) + return sbi_err_map_linux_errno(ret.error); + else + return ret.value; +} + +static int mchp_ipc_sbi_send(u32 command, unsigned long address) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_MICROCHIP_TECHNOLOGY, command, address, + 0, 0, 0, 0, 0); + + if (ret.error) + return sbi_err_map_linux_errno(ret.error); + else + return ret.value; +} + +static struct mchp_ipc_sbi_mbox *to_mchp_ipc_mbox(struct mbox_controller *mbox) +{ + return container_of(mbox, struct mchp_ipc_sbi_mbox, controller); +} + +static inline void mchp_ipc_prepare_receive_req(struct mbox_chan *chan) +{ + struct mchp_ipc_sbi_chan *chan_info = (struct mchp_ipc_sbi_chan *)chan->con_priv; + struct mchp_ipc_sbi_msg request; + + request.buf_addr = chan_info->msg_buf_rx_addr; + request.size = chan_info->max_msg_size; + memcpy(chan_info->buf_base_rx, &request, sizeof(struct mchp_ipc_sbi_msg)); +} + +static inline void mchp_ipc_process_received_data(struct mbox_chan *chan, + struct mchp_ipc_msg *ipc_msg) +{ + struct mchp_ipc_sbi_chan *chan_info = (struct mchp_ipc_sbi_chan *)chan->con_priv; + struct mchp_ipc_sbi_msg sbi_msg; + + memcpy(&sbi_msg, chan_info->buf_base_rx, sizeof(struct mchp_ipc_sbi_msg)); + ipc_msg->buf = (u32 *)chan_info->msg_buf_rx; + ipc_msg->size = sbi_msg.size; +} + +static irqreturn_t mchp_ipc_cluster_aggr_isr(int irq, void *data) +{ + struct mbox_chan *chan; + struct mchp_ipc_sbi_chan *chan_info; + struct mchp_ipc_sbi_mbox *ipc = (struct mchp_ipc_sbi_mbox *)data; + struct mchp_ipc_msg ipc_msg; + struct mchp_ipc_status status_msg; + int ret; + unsigned long hartid; + u32 i, chan_index, chan_id; + + /* Find out the hart that originated the irq */ + for_each_online_cpu(i) { + hartid = cpuid_to_hartid_map(i); + if (irq == ipc->cluster_cfg[hartid].irq) + break; + } + + status_msg.cluster = hartid; + memcpy(ipc->cluster_cfg[hartid].buf_base, &status_msg, sizeof(struct mchp_ipc_status)); + + ret = mchp_ipc_sbi_send(SBI_EXT_IPC_STATUS, ipc->cluster_cfg[hartid].buf_base_addr); + if (ret < 0) { + dev_err_ratelimited(ipc->dev, "could not get IHC irq status ret=%d\n", ret); + return IRQ_HANDLED; + } + + memcpy(&status_msg, ipc->cluster_cfg[hartid].buf_base, sizeof(struct mchp_ipc_status)); + + /* + * Iterate over each bit set in the IHC interrupt status register (IRQ_STATUS) to identify + * the channel(s) that have a message to be processed/acknowledged. + * The bits are organized in alternating format, where each pair of bits represents + * the status of the message present and message clear interrupts for each cluster/hart + * (from hart 0 to hart 5). Each cluster can have up to 5 fixed channels associated. + */ + + for_each_set_bit(i, (unsigned long *)&status_msg.status, IRQ_STATUS_BITS) { + /* Find out the destination hart that triggered the interrupt */ + chan_index = i / 2; + + /* + * The IP has no loopback channels, so we need to decrement the index when + * the target hart has a greater index than our own + */ + if (chan_index >= status_msg.cluster) + chan_index--; + + /* + * Calculate the channel id given the hart and channel index. Channel IDs + * are unique across all clusters of an IPC, and iterate contiguously + * across all clusters. + */ + chan_id = status_msg.cluster * (NUM_CHANS_PER_CLUSTER + chan_index); + + chan = &ipc->chans[chan_id]; + chan_info = (struct mchp_ipc_sbi_chan *)chan->con_priv; + + if (i % 2 == 0) { + mchp_ipc_prepare_receive_req(chan); + ret = mchp_ipc_sbi_chan_send(SBI_EXT_IPC_RECEIVE, chan_id, + chan_info->buf_base_rx_addr); + if (ret < 0) + continue; + + mchp_ipc_process_received_data(chan, &ipc_msg); + mbox_chan_received_data(&ipc->chans[chan_id], (void *)&ipc_msg); + + } else { + ret = mchp_ipc_sbi_chan_send(SBI_EXT_IPC_RECEIVE, chan_id, + chan_info->buf_base_rx_addr); + mbox_chan_txdone(&ipc->chans[chan_id], ret); + } + } + return IRQ_HANDLED; +} + +static int mchp_ipc_send_data(struct mbox_chan *chan, void *data) +{ + struct mchp_ipc_sbi_chan *chan_info = (struct mchp_ipc_sbi_chan *)chan->con_priv; + const struct mchp_ipc_msg *msg = data; + struct mchp_ipc_sbi_msg sbi_payload; + + memcpy(chan_info->msg_buf_tx, msg->buf, msg->size); + sbi_payload.buf_addr = chan_info->msg_buf_tx_addr; + sbi_payload.size = msg->size; + memcpy(chan_info->buf_base_tx, &sbi_payload, sizeof(sbi_payload)); + + return mchp_ipc_sbi_chan_send(SBI_EXT_IPC_SEND, chan_info->id, chan_info->buf_base_tx_addr); +} + +static int mchp_ipc_startup(struct mbox_chan *chan) +{ + struct mchp_ipc_sbi_chan *chan_info = (struct mchp_ipc_sbi_chan *)chan->con_priv; + struct mchp_ipc_sbi_mbox *ipc = to_mchp_ipc_mbox(chan->mbox); + struct mchp_ipc_init ch_init_msg; + int ret; + + /* + * The TX base buffer is used to transmit two types of messages: + * - struct mchp_ipc_init to initialize the channel + * - struct mchp_ipc_sbi_msg to transmit user data/payload + * Ensure the TX buffer size is large enough to accommodate either message type. + */ + size_t max_size = max(sizeof(struct mchp_ipc_init), sizeof(struct mchp_ipc_sbi_msg)); + + chan_info->buf_base_tx = kmalloc(max_size, GFP_KERNEL); + if (!chan_info->buf_base_tx) { + ret = -ENOMEM; + goto fail; + } + + chan_info->buf_base_tx_addr = __pa(chan_info->buf_base_tx); + + chan_info->buf_base_rx = kmalloc(max_size, GFP_KERNEL); + if (!chan_info->buf_base_rx) { + ret = -ENOMEM; + goto fail_free_buf_base_tx; + } + + chan_info->buf_base_rx_addr = __pa(chan_info->buf_base_rx); + + ret = mchp_ipc_sbi_chan_send(SBI_EXT_IPC_CH_INIT, chan_info->id, + chan_info->buf_base_tx_addr); + if (ret < 0) { + dev_err(ipc->dev, "channel %u init failed\n", chan_info->id); + goto fail_free_buf_base_rx; + } + + memcpy(&ch_init_msg, chan_info->buf_base_tx, sizeof(struct mchp_ipc_init)); + chan_info->max_msg_size = ch_init_msg.max_msg_size; + + chan_info->msg_buf_tx = kmalloc(chan_info->max_msg_size, GFP_KERNEL); + if (!chan_info->msg_buf_tx) { + ret = -ENOMEM; + goto fail_free_buf_base_rx; + } + + chan_info->msg_buf_tx_addr = __pa(chan_info->msg_buf_tx); + + chan_info->msg_buf_rx = kmalloc(chan_info->max_msg_size, GFP_KERNEL); + if (!chan_info->msg_buf_rx) { + ret = -ENOMEM; + goto fail_free_buf_msg_tx; + } + + chan_info->msg_buf_rx_addr = __pa(chan_info->msg_buf_rx); + + switch (ipc->hw_type) { + case MIV_IHC: + return 0; + default: + goto fail_free_buf_msg_rx; + } + + if (ret) { + dev_err(ipc->dev, "failed to register interrupt(s)\n"); + goto fail_free_buf_msg_rx; + } + + return ret; + +fail_free_buf_msg_rx: + kfree(chan_info->msg_buf_rx); +fail_free_buf_msg_tx: + kfree(chan_info->msg_buf_tx); +fail_free_buf_base_rx: + kfree(chan_info->buf_base_rx); +fail_free_buf_base_tx: + kfree(chan_info->buf_base_tx); +fail: + return ret; +} + +static void mchp_ipc_shutdown(struct mbox_chan *chan) +{ + struct mchp_ipc_sbi_chan *chan_info = (struct mchp_ipc_sbi_chan *)chan->con_priv; + + kfree(chan_info->buf_base_tx); + kfree(chan_info->buf_base_rx); + kfree(chan_info->msg_buf_tx); + kfree(chan_info->msg_buf_rx); +} + +static const struct mbox_chan_ops mchp_ipc_ops = { + .startup = mchp_ipc_startup, + .send_data = mchp_ipc_send_data, + .shutdown = mchp_ipc_shutdown, +}; + +static struct mbox_chan *mchp_ipc_mbox_xlate(struct mbox_controller *controller, + const struct of_phandle_args *spec) +{ + struct mchp_ipc_sbi_mbox *ipc = to_mchp_ipc_mbox(controller); + unsigned int chan_id = spec->args[0]; + + if (chan_id >= ipc->controller.num_chans) { + dev_err(ipc->dev, "invalid channel id %d\n", chan_id); + return ERR_PTR(-EINVAL); + } + + return &ipc->chans[chan_id]; +} + +static int mchp_ipc_get_cluster_aggr_irq(struct mchp_ipc_sbi_mbox *ipc) +{ + struct platform_device *pdev = to_platform_device(ipc->dev); + char *irq_name; + int cpuid, ret; + unsigned long hartid; + bool irq_found = false; + + for_each_online_cpu(cpuid) { + hartid = cpuid_to_hartid_map(cpuid); + irq_name = devm_kasprintf(ipc->dev, GFP_KERNEL, "hart-%lu", hartid); + ret = platform_get_irq_byname_optional(pdev, irq_name); + if (ret <= 0) + continue; + + ipc->cluster_cfg[hartid].irq = ret; + ret = devm_request_irq(ipc->dev, ipc->cluster_cfg[hartid].irq, + mchp_ipc_cluster_aggr_isr, IRQF_SHARED, + "miv-ihc-irq", ipc); + if (ret) + return ret; + + ipc->cluster_cfg[hartid].buf_base = devm_kmalloc(ipc->dev, + sizeof(struct mchp_ipc_status), + GFP_KERNEL); + + if (!ipc->cluster_cfg[hartid].buf_base) + return -ENOMEM; + + ipc->cluster_cfg[hartid].buf_base_addr = __pa(ipc->cluster_cfg[hartid].buf_base); + + irq_found = true; + } + + return irq_found; +} + +static int mchp_ipc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mchp_ipc_mbox_info ipc_info; + struct mchp_ipc_sbi_mbox *ipc; + struct mchp_ipc_sbi_chan *priv; + bool irq_avail = false; + int ret; + u32 chan_id; + + ret = sbi_probe_extension(SBI_EXT_MICROCHIP_TECHNOLOGY); + if (ret <= 0) + return dev_err_probe(dev, ret, "Microchip SBI extension not detected\n"); + + ipc = devm_kzalloc(dev, sizeof(*ipc), GFP_KERNEL); + if (!ipc) + return -ENOMEM; + + platform_set_drvdata(pdev, ipc); + + ipc->buf_base = devm_kmalloc(dev, sizeof(struct mchp_ipc_mbox_info), GFP_KERNEL); + if (!ipc->buf_base) + return -ENOMEM; + + ipc->buf_base_addr = __pa(ipc->buf_base); + + ret = mchp_ipc_sbi_send(SBI_EXT_IPC_PROBE, ipc->buf_base_addr); + if (ret < 0) + return dev_err_probe(dev, ret, "could not probe IPC SBI service\n"); + + memcpy(&ipc_info, ipc->buf_base, sizeof(struct mchp_ipc_mbox_info)); + ipc->controller.num_chans = ipc_info.num_channels; + ipc->hw_type = ipc_info.hw_type; + + ipc->chans = devm_kcalloc(dev, ipc->controller.num_chans, sizeof(*ipc->chans), GFP_KERNEL); + if (!ipc->chans) + return -ENOMEM; + + ipc->dev = dev; + ipc->controller.txdone_irq = true; + ipc->controller.dev = ipc->dev; + ipc->controller.ops = &mchp_ipc_ops; + ipc->controller.chans = ipc->chans; + ipc->controller.of_xlate = mchp_ipc_mbox_xlate; + + for (chan_id = 0; chan_id < ipc->controller.num_chans; chan_id++) { + priv = devm_kmalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + ipc->chans[chan_id].con_priv = priv; + priv->id = chan_id; + } + + if (ipc->hw_type == MIV_IHC) { + ipc->cluster_cfg = devm_kcalloc(dev, num_online_cpus(), + sizeof(struct mchp_ipc_cluster_cfg), + GFP_KERNEL); + if (!ipc->cluster_cfg) + return -ENOMEM; + + if (mchp_ipc_get_cluster_aggr_irq(ipc)) + irq_avail = true; + } + + if (!irq_avail) + return dev_err_probe(dev, -ENODEV, "missing interrupt property\n"); + + ret = devm_mbox_controller_register(dev, &ipc->controller); + if (ret) + return dev_err_probe(dev, ret, + "Inter-Processor communication (IPC) registration failed\n"); + + return 0; +} + +static const struct of_device_id mchp_ipc_of_match[] = { + {.compatible = "microchip,sbi-ipc", }, + {} +}; +MODULE_DEVICE_TABLE(of, mchp_ipc_of_match); + +static struct platform_driver mchp_ipc_driver = { + .driver = { + .name = "microchip_ipc", + .of_match_table = mchp_ipc_of_match, + }, + .probe = mchp_ipc_probe, +}; + +module_platform_driver(mchp_ipc_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Valentina Fernandez "); +MODULE_DESCRIPTION("Microchip Inter-Processor Communication (IPC) driver"); diff --git a/drivers/mailbox/mailbox-mpfs.c b/drivers/mailbox/mailbox-mpfs.c index 4df546e3b7ea..d5d9effece97 100644 --- a/drivers/mailbox/mailbox-mpfs.c +++ b/drivers/mailbox/mailbox-mpfs.c @@ -251,7 +251,7 @@ static inline int mpfs_mbox_syscon_probe(struct mpfs_mbox *mbox, struct platform return PTR_ERR(mbox->sysreg_scb); mbox->mbox_base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(mbox->ctrl_base)) + if (IS_ERR(mbox->mbox_base)) return PTR_ERR(mbox->mbox_base); return 0; diff --git a/drivers/mailbox/mailbox-th1520.c b/drivers/mailbox/mailbox-th1520.c index 4e84640ac3b8..a6b2aa9ae952 100644 --- a/drivers/mailbox/mailbox-th1520.c +++ b/drivers/mailbox/mailbox-th1520.c @@ -41,7 +41,7 @@ #ifdef CONFIG_PM_SLEEP /* store MBOX context across system-wide suspend/resume transitions */ struct th1520_mbox_context { - u32 intr_mask[TH_1520_MBOX_CHANS - 1]; + u32 intr_mask[TH_1520_MBOX_CHANS]; }; #endif @@ -387,8 +387,10 @@ static void __iomem *th1520_map_mmio(struct platform_device *pdev, mapped = devm_ioremap(&pdev->dev, res->start + offset, resource_size(res) - offset); - if (IS_ERR(mapped)) + if (!mapped) { dev_err(&pdev->dev, "Failed to map resource: %s\n", res_name); + return ERR_PTR(-ENOMEM); + } return mapped; } diff --git a/drivers/mailbox/qcom-apcs-ipc-mailbox.c b/drivers/mailbox/qcom-apcs-ipc-mailbox.c index f0d1fc0fb9ff..11c41e935a36 100644 --- a/drivers/mailbox/qcom-apcs-ipc-mailbox.c +++ b/drivers/mailbox/qcom-apcs-ipc-mailbox.c @@ -157,6 +157,7 @@ static const struct of_device_id qcom_apcs_ipc_of_match[] = { { .compatible = "qcom,sm6125-apcs-hmss-global", .data = &msm8994_apcs_data }, { .compatible = "qcom,sm6115-apcs-hmss-global", .data = &msm8994_apcs_data }, { .compatible = "qcom,ipq5332-apcs-apps-global", .data = &ipq6018_apcs_data }, + { .compatible = "qcom,ipq5424-apcs-apps-global", .data = &msm8994_apcs_data }, { .compatible = "qcom,ipq8074-apcs-apps-global", .data = &ipq6018_apcs_data }, { .compatible = "qcom,sc7180-apss-shared", .data = &apps_shared_apcs_data }, { .compatible = "qcom,sc8180x-apss-shared", .data = &apps_shared_apcs_data }, diff --git a/drivers/mailbox/qcom-ipcc.c b/drivers/mailbox/qcom-ipcc.c index 14c7907c6632..0b17a38ea6bf 100644 --- a/drivers/mailbox/qcom-ipcc.c +++ b/drivers/mailbox/qcom-ipcc.c @@ -14,6 +14,7 @@ #include /* IPCC Register offsets */ +#define IPCC_REG_CONFIG 0x08 #define IPCC_REG_SEND_ID 0x0c #define IPCC_REG_RECV_ID 0x10 #define IPCC_REG_RECV_SIGNAL_ENABLE 0x14 @@ -21,6 +22,7 @@ #define IPCC_REG_RECV_SIGNAL_CLEAR 0x1c #define IPCC_REG_CLIENT_CLEAR 0x38 +#define IPCC_CLEAR_ON_RECV_RD BIT(0) #define IPCC_SIGNAL_ID_MASK GENMASK(15, 0) #define IPCC_CLIENT_ID_MASK GENMASK(31, 16) @@ -274,6 +276,7 @@ static int qcom_ipcc_pm_resume(struct device *dev) static int qcom_ipcc_probe(struct platform_device *pdev) { struct qcom_ipcc *ipcc; + u32 config_value; static int id; char *name; int ret; @@ -288,6 +291,19 @@ static int qcom_ipcc_probe(struct platform_device *pdev) if (IS_ERR(ipcc->base)) return PTR_ERR(ipcc->base); + /* + * It is possible that boot firmware is using the same IPCC instance + * as of the HLOS and it has kept CLEAR_ON_RECV_RD set which basically + * means Interrupt pending registers are cleared when RECV_ID is read. + * The register automatically updates to the next pending interrupt/client + * status based on priority. + */ + config_value = readl(ipcc->base + IPCC_REG_CONFIG); + if (config_value & IPCC_CLEAR_ON_RECV_RD) { + config_value &= ~(IPCC_CLEAR_ON_RECV_RD); + writel(config_value, ipcc->base + IPCC_REG_CONFIG); + } + ipcc->irq = platform_get_irq(pdev, 0); if (ipcc->irq < 0) return ipcc->irq; diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c index 8d5e2d7dc03b..c1981f091bd1 100644 --- a/drivers/mailbox/tegra-hsp.c +++ b/drivers/mailbox/tegra-hsp.c @@ -388,7 +388,6 @@ static void tegra_hsp_sm_recv32(struct tegra_hsp_channel *channel) value = tegra_hsp_channel_readl(channel, HSP_SM_SHRD_MBOX); value &= ~HSP_SM_SHRD_MBOX_FULL; msg = (void *)(unsigned long)value; - mbox_chan_received_data(channel->chan, msg); /* * Need to clear all bits here since some producers, such as TCU, depend @@ -398,6 +397,8 @@ static void tegra_hsp_sm_recv32(struct tegra_hsp_channel *channel) * explicitly, so we have to make sure we cover all possible cases. */ tegra_hsp_channel_writel(channel, 0x0, HSP_SM_SHRD_MBOX); + + mbox_chan_received_data(channel->chan, msg); } static const struct tegra_hsp_sm_ops tegra_hsp_sm_32bit_ops = { @@ -433,7 +434,6 @@ static void tegra_hsp_sm_recv128(struct tegra_hsp_channel *channel) value[3] = tegra_hsp_channel_readl(channel, HSP_SHRD_MBOX_TYPE1_DATA3); msg = (void *)(unsigned long)value; - mbox_chan_received_data(channel->chan, msg); /* * Clear data registers and tag. @@ -443,6 +443,8 @@ static void tegra_hsp_sm_recv128(struct tegra_hsp_channel *channel) tegra_hsp_channel_writel(channel, 0x0, HSP_SHRD_MBOX_TYPE1_DATA2); tegra_hsp_channel_writel(channel, 0x0, HSP_SHRD_MBOX_TYPE1_DATA3); tegra_hsp_channel_writel(channel, 0x0, HSP_SHRD_MBOX_TYPE1_TAG); + + mbox_chan_received_data(channel->chan, msg); } static const struct tegra_hsp_sm_ops tegra_hsp_sm_128bit_ops = { diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c index aa5249da59b2..0c143beaafda 100644 --- a/drivers/mailbox/zynqmp-ipi-mailbox.c +++ b/drivers/mailbox/zynqmp-ipi-mailbox.c @@ -905,7 +905,7 @@ static int zynqmp_ipi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *nc, *np = pdev->dev.of_node; - struct zynqmp_ipi_pdata __percpu *pdata; + struct zynqmp_ipi_pdata *pdata; struct of_phandle_args out_irq; struct zynqmp_ipi_mbox *mbox; int num_mboxes, ret = -EINVAL; diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 1e9db8e4acdf..0b1870a09e1f 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -61,6 +61,19 @@ config MD_BITMAP_FILE various kernel APIs and can only work with files on a file system not actually sitting on the MD device. +config MD_LINEAR + tristate "Linear (append) mode" + depends on BLK_DEV_MD + help + If you say Y here, then your multiple devices driver will be able to + use the so-called linear mode, i.e. it will combine the hard disk + partitions by simply appending one to the other. + + To compile this as a module, choose M here: the module + will be called linear. + + If unsure, say Y. + config MD_RAID0 tristate "RAID-0 (striping) mode" depends on BLK_DEV_MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 476a214e4bdc..87bdfc9fe14c 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -29,12 +29,14 @@ dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o md-mod-y += md.o md-bitmap.o raid456-y += raid5.o raid5-cache.o raid5-ppl.o +linear-y += md-linear.o # Note: link order is important. All raid personalities # and must come before md.o, as they each initialise # themselves, and md.o may use the personalities when it # auto-initialised. +obj-$(CONFIG_MD_LINEAR) += linear.o obj-$(CONFIG_MD_RAID0) += raid0.o obj-$(CONFIG_MD_RAID1) += raid1.o obj-$(CONFIG_MD_RAID10) += raid10.o diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c index ef6abf33f926..45ca134cbf02 100644 --- a/drivers/md/bcache/movinggc.c +++ b/drivers/md/bcache/movinggc.c @@ -82,7 +82,7 @@ static void moving_init(struct moving_io *io) bio_init(bio, NULL, bio->bi_inline_vecs, DIV_ROUND_UP(KEY_SIZE(&io->w->key), PAGE_SECTORS), 0); bio_get(bio); - bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); + bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0); bio->bi_iter.bi_size = KEY_SIZE(&io->w->key) << 9; bio->bi_private = &io->cl; diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index c1d28e365910..453efbbdc8ee 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -334,7 +334,7 @@ static void dirty_init(struct keybuf_key *w) bio_init(bio, NULL, bio->bi_inline_vecs, DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS), 0); if (!io->dc->writeback_percent) - bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); + bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0); bio->bi_iter.bi_size = KEY_SIZE(&w->key) << 9; bio->bi_private = w; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 1ae2c71bb383..02a2919f4e5a 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -59,6 +59,7 @@ struct convert_context { struct bio *bio_out; struct bvec_iter iter_out; atomic_t cc_pending; + unsigned int tag_offset; u64 cc_sector; union { struct skcipher_request *req; @@ -1187,7 +1188,7 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio) tag_len = io->cc->tuple_size * (bio_sectors(bio) >> io->cc->sector_shift); - bip->bip_iter.bi_sector = io->cc->start + io->sector; + bip->bip_iter.bi_sector = bio->bi_iter.bi_sector; ret = bio_integrity_add_page(bio, virt_to_page(io->integrity_metadata), tag_len, offset_in_page(io->integrity_metadata)); @@ -1256,6 +1257,7 @@ static void crypt_convert_init(struct crypt_config *cc, if (bio_out) ctx->iter_out = bio_out->bi_iter; ctx->cc_sector = sector + cc->iv_offset; + ctx->tag_offset = 0; init_completion(&ctx->restart); } @@ -1588,7 +1590,6 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_ static blk_status_t crypt_convert(struct crypt_config *cc, struct convert_context *ctx, bool atomic, bool reset_pending) { - unsigned int tag_offset = 0; unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT; int r; @@ -1611,9 +1612,9 @@ static blk_status_t crypt_convert(struct crypt_config *cc, atomic_inc(&ctx->cc_pending); if (crypt_integrity_aead(cc)) - r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, tag_offset); + r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, ctx->tag_offset); else - r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, tag_offset); + r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, ctx->tag_offset); switch (r) { /* @@ -1633,8 +1634,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc, * exit and continue processing in a workqueue */ ctx->r.req = NULL; + ctx->tag_offset++; ctx->cc_sector += sector_step; - tag_offset++; return BLK_STS_DEV_RESOURCE; } } else { @@ -1648,8 +1649,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc, */ case -EINPROGRESS: ctx->r.req = NULL; + ctx->tag_offset++; ctx->cc_sector += sector_step; - tag_offset++; continue; /* * The request was already processed (synchronously). @@ -1657,7 +1658,7 @@ static blk_status_t crypt_convert(struct crypt_config *cc, case 0: atomic_dec(&ctx->cc_pending); ctx->cc_sector += sector_step; - tag_offset++; + ctx->tag_offset++; if (!atomic) cond_resched(); continue; @@ -1719,6 +1720,7 @@ retry: clone->bi_private = io; clone->bi_end_io = crypt_endio; clone->bi_ioprio = io->base_bio->bi_ioprio; + clone->bi_iter.bi_sector = cc->start + io->sector; remaining_size = size; @@ -1909,7 +1911,6 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) crypt_dec_pending(io); return 1; } - clone->bi_iter.bi_sector = cc->start + io->sector; crypt_convert_init(cc, &io->ctx, clone, clone, io->sector); io->saved_bi_iter = clone->bi_iter; dm_submit_bio_remap(io->base_bio, clone); @@ -1925,13 +1926,13 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) clone = bio_alloc_clone(cc->dev->bdev, io->base_bio, gfp, &cc->bs); if (!clone) return 1; + + clone->bi_iter.bi_sector = cc->start + io->sector; clone->bi_private = io; clone->bi_end_io = crypt_endio; crypt_inc_pending(io); - clone->bi_iter.bi_sector = cc->start + io->sector; - if (dm_crypt_integrity_io_alloc(io, clone)) { crypt_dec_pending(io); bio_put(clone); @@ -2039,8 +2040,6 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async) /* crypt_convert should have filled the clone bio */ BUG_ON(io->ctx.iter_out.bi_size); - clone->bi_iter.bi_sector = cc->start + io->sector; - if ((likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) || test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags)) { dm_submit_bio_remap(io->base_bio, clone); @@ -2092,13 +2091,12 @@ static void kcryptd_crypt_write_continue(struct work_struct *work) struct crypt_config *cc = io->cc; struct convert_context *ctx = &io->ctx; int crypt_finished; - sector_t sector = io->sector; blk_status_t r; wait_for_completion(&ctx->restart); reinit_completion(&ctx->restart); - r = crypt_convert(cc, &io->ctx, true, false); + r = crypt_convert(cc, &io->ctx, false, false); if (r) io->error = r; crypt_finished = atomic_dec_and_test(&ctx->cc_pending); @@ -2109,10 +2107,8 @@ static void kcryptd_crypt_write_continue(struct work_struct *work) } /* Encryption was already finished, submit io now */ - if (crypt_finished) { + if (crypt_finished) kcryptd_crypt_write_io_submit(io, 0); - io->sector = sector; - } crypt_dec_pending(io); } @@ -2123,14 +2119,13 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) struct convert_context *ctx = &io->ctx; struct bio *clone; int crypt_finished; - sector_t sector = io->sector; blk_status_t r; /* * Prevent io from disappearing until this function completes. */ crypt_inc_pending(io); - crypt_convert_init(cc, ctx, NULL, io->base_bio, sector); + crypt_convert_init(cc, ctx, NULL, io->base_bio, io->sector); clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size); if (unlikely(!clone)) { @@ -2147,8 +2142,6 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) io->ctx.iter_in = clone->bi_iter; } - sector += bio_sectors(clone); - crypt_inc_pending(io); r = crypt_convert(cc, ctx, test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true); @@ -2172,10 +2165,8 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) } /* Encryption was already finished, submit io now */ - if (crypt_finished) { + if (crypt_finished) kcryptd_crypt_write_io_submit(io, 0); - io->sector = sector; - } dec: crypt_dec_pending(io); @@ -2203,7 +2194,7 @@ static void kcryptd_crypt_read_continue(struct work_struct *work) wait_for_completion(&io->ctx.restart); reinit_completion(&io->ctx.restart); - r = crypt_convert(cc, &io->ctx, true, false); + r = crypt_convert(cc, &io->ctx, false, false); if (r) io->error = r; @@ -2221,7 +2212,6 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) crypt_inc_pending(io); if (io->ctx.aead_recheck) { - io->ctx.cc_sector = io->sector + cc->iv_offset; r = crypt_convert(cc, &io->ctx, test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); } else { diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index ec5db1478b2f..18ae45dcbfb2 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -442,7 +442,7 @@ static int ebs_iterate_devices(struct dm_target *ti, static struct target_type ebs_target = { .name = "ebs", .version = {1, 0, 1}, - .features = DM_TARGET_PASSES_INTEGRITY, + .features = 0, .module = THIS_MODULE, .ctr = ebs_ctr, .dtr = ebs_dtr, diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index d7a8e2f40db3..c37668790577 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -379,6 +379,7 @@ static void do_region(const blk_opf_t opf, unsigned int region, atomic_inc(&io->count); submit_bio(bio); + WARN_ON_ONCE(opf & REQ_ATOMIC && remaining); } while (remaining); } diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 49fb0f684193..66318aba4bdb 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -199,9 +199,10 @@ static size_t linear_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff, static struct target_type linear_target = { .name = "linear", - .version = {1, 4, 0}, + .version = {1, 5, 0}, .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT | - DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO, + DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO | + DM_TARGET_ATOMIC_WRITES, .report_zones = linear_report_zones, .module = THIS_MODULE, .ctr = linear_ctr, diff --git a/drivers/md/dm-ps-io-affinity.c b/drivers/md/dm-ps-io-affinity.c index 461ee6b2044d..716807e511ee 100644 --- a/drivers/md/dm-ps-io-affinity.c +++ b/drivers/md/dm-ps-io-affinity.c @@ -116,7 +116,7 @@ static int ioa_create(struct path_selector *ps, unsigned int argc, char **argv) if (!s) return -ENOMEM; - s->path_map = kzalloc(nr_cpu_ids * sizeof(struct path_info *), + s->path_map = kcalloc(nr_cpu_ids, sizeof(struct path_info *), GFP_KERNEL); if (!s->path_map) goto free_selector; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 1e0d3b9b75d6..6adc55fd90d3 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3196,7 +3196,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (reshape_sectors || rs_is_raid1(rs)) { /* * We can only prepare for a reshape here, because the - * raid set needs to run to provide the repective reshape + * raid set needs to run to provide the respective reshape * check functions via its MD personality instance. * * So do the reshape check after md_run() succeeded. diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 9511dae5b556..8c6f1f7e6456 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -656,7 +656,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio) unsigned int i; struct dm_io_region io[MAX_NR_MIRRORS], *dest = io; struct mirror *m; - blk_opf_t op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH); + blk_opf_t op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH | REQ_ATOMIC); struct dm_io_request io_req = { .bi_opf = REQ_OP_WRITE | op_flags, .mem.type = DM_IO_BIO, @@ -1483,8 +1483,9 @@ static int mirror_iterate_devices(struct dm_target *ti, static struct target_type mirror_target = { .name = "mirror", - .version = {1, 14, 0}, + .version = {1, 15, 0}, .module = THIS_MODULE, + .features = DM_TARGET_ATOMIC_WRITES, .ctr = mirror_ctr, .dtr = mirror_dtr, .map = mirror_map, diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 499f8cc8a39f..e23076f7ece2 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -547,7 +547,7 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t) md->tag_set->ops = &dm_mq_ops; md->tag_set->queue_depth = dm_get_blk_mq_queue_depth(); md->tag_set->numa_node = md->numa_node_id; - md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING; + md->tag_set->flags = BLK_MQ_F_STACKING; md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues(); md->tag_set->driver_data = md; diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 4112071de0be..3786ac67cefe 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -465,8 +465,9 @@ static void stripe_io_hints(struct dm_target *ti, static struct target_type stripe_target = { .name = "striped", - .version = {1, 6, 0}, - .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT, + .version = {1, 7, 0}, + .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT | + DM_TARGET_ATOMIC_WRITES, .module = THIS_MODULE, .ctr = stripe_ctr, .dtr = stripe_dtr, diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index bd8b796ae683..0ef5203387b2 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1806,6 +1806,32 @@ static bool dm_table_supports_secure_erase(struct dm_table *t) return true; } +static int device_not_atomic_write_capable(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) +{ + return !bdev_can_atomic_write(dev->bdev); +} + +static bool dm_table_supports_atomic_writes(struct dm_table *t) +{ + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + if (!dm_target_supports_atomic_writes(ti->type)) + return false; + + if (!ti->type->iterate_devices) + return false; + + if (ti->type->iterate_devices(ti, + device_not_atomic_write_capable, NULL)) { + return false; + } + } + return true; +} + int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { @@ -1854,6 +1880,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, return r; } + if (dm_table_supports_atomic_writes(t)) + limits->features |= BLK_FEAT_ATOMIC_WRITES; + r = queue_limits_set(q, limits); if (r) return r; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index bf0f9dddd146..05cf4e3f2bbe 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2332,10 +2332,9 @@ static struct thin_c *get_first_thin(struct pool *pool) struct thin_c *tc = NULL; rcu_read_lock(); - if (!list_empty(&pool->active_thins)) { - tc = list_entry_rcu(pool->active_thins.next, struct thin_c, list); + tc = list_first_or_null_rcu(&pool->active_thins, struct thin_c, list); + if (tc) thin_get(tc); - } rcu_read_unlock(); return tc; diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 62b1a44b8dd2..0c41949db784 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -39,36 +39,24 @@ static inline u64 fec_interleave(struct dm_verity *v, u64 offset) return offset + mod * (v->fec->rounds << v->data_dev_block_bits); } -/* - * Decode an RS block using Reed-Solomon. - */ -static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, - u8 *data, u8 *fec, int neras) -{ - int i; - uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; - - for (i = 0; i < v->fec->roots; i++) - par[i] = fec[i]; - - return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras, - fio->erasures, 0, NULL); -} - /* * Read error-correcting codes for the requested RS block. Returns a pointer * to the data block. Caller is responsible for releasing buf. */ static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, - unsigned int *offset, struct dm_buffer **buf, - unsigned short ioprio) + unsigned int *offset, unsigned int par_buf_offset, + struct dm_buffer **buf, unsigned short ioprio) { u64 position, block, rem; u8 *res; + /* We have already part of parity bytes read, skip to the next block */ + if (par_buf_offset) + index++; + position = (index + rsb) * v->fec->roots; block = div64_u64_rem(position, v->fec->io_size, &rem); - *offset = (unsigned int)rem; + *offset = par_buf_offset ? 0 : (unsigned int)rem; res = dm_bufio_read_with_ioprio(v->fec->bufio, block, buf, ioprio); if (IS_ERR(res)) { @@ -128,11 +116,13 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, { int r, corrected = 0, res; struct dm_buffer *buf; - unsigned int n, i, offset; + unsigned int n, i, j, offset, par_buf_offset = 0; + uint16_t par_buf[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; u8 *par, *block; struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio->bi_ioprio); if (IS_ERR(par)) return PTR_ERR(par); @@ -142,7 +132,11 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, */ fec_for_each_buffer_rs_block(fio, n, i) { block = fec_buffer_rs_block(v, fio, n, i); - res = fec_decode_rs8(v, fio, block, &par[offset], neras); + for (j = 0; j < v->fec->roots - par_buf_offset; j++) + par_buf[par_buf_offset + j] = par[offset + j]; + /* Decode an RS block using Reed-Solomon */ + res = decode_rs8(fio->rs, block, par_buf, v->fec->rsn, + NULL, neras, fio->erasures, 0, NULL); if (res < 0) { r = res; goto error; @@ -155,12 +149,22 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, if (block_offset >= 1 << v->data_dev_block_bits) goto done; - /* read the next block when we run out of parity bytes */ - offset += v->fec->roots; + /* Read the next block when we run out of parity bytes */ + offset += (v->fec->roots - par_buf_offset); + /* Check if parity bytes are split between blocks */ + if (offset < v->fec->io_size && (offset + v->fec->roots) > v->fec->io_size) { + par_buf_offset = v->fec->io_size - offset; + for (j = 0; j < par_buf_offset; j++) + par_buf[j] = par[offset + j]; + offset += par_buf_offset; + } else + par_buf_offset = 0; + if (offset >= v->fec->io_size) { dm_bufio_release(buf); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio->bi_ioprio); if (IS_ERR(par)) return PTR_ERR(par); } @@ -250,7 +254,7 @@ static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, bufio = v->bufio; } - bbuf = dm_bufio_read_with_ioprio(bufio, block, &buf, bio_prio(bio)); + bbuf = dm_bufio_read_with_ioprio(bufio, block, &buf, bio->bi_ioprio); if (IS_ERR(bbuf)) { DMWARN_LIMIT("%s: FEC %llu: read failed (%llu): %ld", v->data_dev->name, @@ -724,10 +728,7 @@ int verity_fec_ctr(struct dm_verity *v) return -E2BIG; } - if ((f->roots << SECTOR_SHIFT) & ((1 << v->data_dev_block_bits) - 1)) - f->io_size = 1 << v->data_dev_block_bits; - else - f->io_size = v->fec->roots << SECTOR_SHIFT; + f->io_size = 1 << v->data_dev_block_bits; f->bufio = dm_bufio_client_create(f->dev->bdev, f->io_size, diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 47d595f6a76e..e86c1431b108 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -321,7 +321,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, } } else { data = dm_bufio_read_with_ioprio(v->bufio, hash_block, - &buf, bio_prio(bio)); + &buf, bio->bi_ioprio); } if (IS_ERR(data)) @@ -789,7 +789,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio) verity_fec_init_io(io); - verity_submit_prefetch(v, io, bio_prio(bio)); + verity_submit_prefetch(v, io, bio->bi_ioprio); submit_bio_noacct(bio); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 12ecf07a3841..4d1e42891d24 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1479,12 +1479,12 @@ static void setup_split_accounting(struct clone_info *ci, unsigned int len) static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, struct dm_target *ti, unsigned int num_bios, - unsigned *len, gfp_t gfp_flag) + unsigned *len) { struct bio *bio; - int try = (gfp_flag & GFP_NOWAIT) ? 0 : 1; + int try; - for (; try < 2; try++) { + for (try = 0; try < 2; try++) { int bio_nr; if (try && num_bios > 1) @@ -1508,8 +1508,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, } static unsigned int __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti, - unsigned int num_bios, unsigned int *len, - gfp_t gfp_flag) + unsigned int num_bios, unsigned int *len) { struct bio_list blist = BIO_EMPTY_LIST; struct bio *clone; @@ -1526,7 +1525,7 @@ static unsigned int __send_duplicate_bios(struct clone_info *ci, struct dm_targe * Using alloc_multiple_bios(), even if num_bios is 1, to consistently * support allocating using GFP_NOWAIT with GFP_NOIO fallback. */ - alloc_multiple_bios(&blist, ci, ti, num_bios, len, gfp_flag); + alloc_multiple_bios(&blist, ci, ti, num_bios, len); while ((clone = bio_list_pop(&blist))) { if (num_bios > 1) dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO); @@ -1564,7 +1563,7 @@ static void __send_empty_flush(struct clone_info *ci) atomic_add(ti->num_flush_bios, &ci->io->io_count); bios = __send_duplicate_bios(ci, ti, ti->num_flush_bios, - NULL, GFP_NOWAIT); + NULL); atomic_sub(ti->num_flush_bios - bios, &ci->io->io_count); } } else { @@ -1612,7 +1611,7 @@ static void __send_abnormal_io(struct clone_info *ci, struct dm_target *ti, __max_io_len(ti, ci->sector, max_granularity, max_sectors)); atomic_add(num_bios, &ci->io->io_count); - bios = __send_duplicate_bios(ci, ti, num_bios, &len, GFP_NOIO); + bios = __send_duplicate_bios(ci, ti, num_bios, &len); /* * alloc_io() takes one extra reference for submission, so the * reference won't reach 0 without the following (+1) subtraction @@ -1746,6 +1745,9 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci) ci->submit_as_polled = !!(ci->bio->bi_opf & REQ_POLLED); len = min_t(sector_t, max_io_len(ti, ci->sector), ci->sector_count); + if (ci->bio->bi_opf & REQ_ATOMIC && len != ci->sector_count) + return BLK_STS_IOERR; + setup_split_accounting(ci, len); if (unlikely(ci->bio->bi_opf & REQ_NOWAIT)) { @@ -1849,7 +1851,7 @@ static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci, * not go crazy with the clone allocation. */ alloc_multiple_bios(&blist, ci, ti, min(nr_reset, 32), - NULL, GFP_NOIO); + NULL); } /* Get a clone and change it to a regular reset operation. */ @@ -1881,7 +1883,7 @@ static void __send_zone_reset_all_native(struct clone_info *ci, unsigned int bios; atomic_add(1, &ci->io->io_count); - bios = __send_duplicate_bios(ci, ti, 1, NULL, GFP_NOIO); + bios = __send_duplicate_bios(ci, ti, 1, NULL); atomic_sub(1 - bios, &ci->io->io_count); ci->sector_count = 0; @@ -1969,6 +1971,15 @@ static void dm_split_and_process_bio(struct mapped_device *md, /* Only support nowait for normal IO */ if (unlikely(bio->bi_opf & REQ_NOWAIT) && !is_abnormal) { + /* + * Don't support NOWAIT for FLUSH because it may allocate + * multiple bios and there's no easy way how to undo the + * allocations. + */ + if (bio->bi_opf & REQ_PREFLUSH) { + bio_wouldblock_error(bio); + return; + } io = alloc_io(md, bio, GFP_NOWAIT); if (unlikely(!io)) { /* Unable to do anything without dm_io. */ diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index b2a00f213c2c..4b80165afd23 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -49,6 +49,7 @@ static int md_setup_ents __initdata; * instead of just one. -- KTK * 18May2000: Added support for persistent-superblock arrays: * md=n,0,factor,fault,device-list uses RAID0 for device n + * md=n,-1,factor,fault,device-list uses LINEAR for device n * md=n,device-list reads a RAID superblock from the devices * elements in device-list are read by name_to_kdev_t so can be * a hex number or something like /dev/hda1 /dev/sdb @@ -87,7 +88,7 @@ static int __init md_setup(char *str) md_setup_ents++; switch (get_option(&str, &level)) { /* RAID level */ case 2: /* could be 0 or -1.. */ - if (level == 0) { + if (level == 0 || level == LEVEL_LINEAR) { if (get_option(&str, &factor) != 2 || /* Chunk Size */ get_option(&str, &fault) != 2) { printk(KERN_WARNING "md: Too few arguments supplied to md=.\n"); @@ -95,7 +96,10 @@ static int __init md_setup(char *str) } md_setup_args[ent].level = level; md_setup_args[ent].chunk = 1 << (factor+12); - pername = "raid0"; + if (level == LEVEL_LINEAR) + pername = "linear"; + else + pername = "raid0"; break; } fallthrough; diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index c3a42dd66ce5..23c09d22fcdb 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -682,7 +682,7 @@ static void bitmap_update_sb(void *data) return; if (!bitmap->storage.sb_page) /* no superblock */ return; - sb = kmap_atomic(bitmap->storage.sb_page); + sb = kmap_local_page(bitmap->storage.sb_page); sb->events = cpu_to_le64(bitmap->mddev->events); if (bitmap->mddev->events < bitmap->events_cleared) /* rocking back to read-only */ @@ -702,7 +702,7 @@ static void bitmap_update_sb(void *data) sb->nodes = cpu_to_le32(bitmap->mddev->bitmap_info.nodes); sb->sectors_reserved = cpu_to_le32(bitmap->mddev-> bitmap_info.space); - kunmap_atomic(sb); + kunmap_local(sb); if (bitmap->storage.file) write_file_page(bitmap, bitmap->storage.sb_page, 1); @@ -717,7 +717,7 @@ static void bitmap_print_sb(struct bitmap *bitmap) if (!bitmap || !bitmap->storage.sb_page) return; - sb = kmap_atomic(bitmap->storage.sb_page); + sb = kmap_local_page(bitmap->storage.sb_page); pr_debug("%s: bitmap file superblock:\n", bmname(bitmap)); pr_debug(" magic: %08x\n", le32_to_cpu(sb->magic)); pr_debug(" version: %u\n", le32_to_cpu(sb->version)); @@ -736,7 +736,7 @@ static void bitmap_print_sb(struct bitmap *bitmap) pr_debug(" sync size: %llu KB\n", (unsigned long long)le64_to_cpu(sb->sync_size)/2); pr_debug("max write behind: %u\n", le32_to_cpu(sb->write_behind)); - kunmap_atomic(sb); + kunmap_local(sb); } /* @@ -760,7 +760,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap) return -ENOMEM; bitmap->storage.sb_index = 0; - sb = kmap_atomic(bitmap->storage.sb_page); + sb = kmap_local_page(bitmap->storage.sb_page); sb->magic = cpu_to_le32(BITMAP_MAGIC); sb->version = cpu_to_le32(BITMAP_MAJOR_HI); @@ -768,7 +768,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap) chunksize = bitmap->mddev->bitmap_info.chunksize; BUG_ON(!chunksize); if (!is_power_of_2(chunksize)) { - kunmap_atomic(sb); + kunmap_local(sb); pr_warn("bitmap chunksize not a power of 2\n"); return -EINVAL; } @@ -803,7 +803,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap) sb->events_cleared = cpu_to_le64(bitmap->mddev->events); bitmap->mddev->bitmap_info.nodes = 0; - kunmap_atomic(sb); + kunmap_local(sb); return 0; } @@ -865,7 +865,7 @@ re_read: return err; err = -EINVAL; - sb = kmap_atomic(sb_page); + sb = kmap_local_page(sb_page); chunksize = le32_to_cpu(sb->chunksize); daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ; @@ -932,7 +932,7 @@ re_read: err = 0; out: - kunmap_atomic(sb); + kunmap_local(sb); if (err == 0 && nodes && (bitmap->cluster_slot < 0)) { /* Assigning chunksize is required for "re_read" */ bitmap->mddev->bitmap_info.chunksize = chunksize; @@ -1161,12 +1161,12 @@ static void md_bitmap_file_set_bit(struct bitmap *bitmap, sector_t block) bit = file_page_offset(&bitmap->storage, chunk); /* set the bit */ - kaddr = kmap_atomic(page); + kaddr = kmap_local_page(page); if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) set_bit(bit, kaddr); else set_bit_le(bit, kaddr); - kunmap_atomic(kaddr); + kunmap_local(kaddr); pr_debug("set file bit %lu page %lu\n", bit, index); /* record page number so it gets flushed to disk when unplug occurs */ set_page_attr(bitmap, index - node_offset, BITMAP_PAGE_DIRTY); @@ -1190,12 +1190,12 @@ static void md_bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block) if (!page) return; bit = file_page_offset(&bitmap->storage, chunk); - paddr = kmap_atomic(page); + paddr = kmap_local_page(page); if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) clear_bit(bit, paddr); else clear_bit_le(bit, paddr); - kunmap_atomic(paddr); + kunmap_local(paddr); if (!test_page_attr(bitmap, index - node_offset, BITMAP_PAGE_NEEDWRITE)) { set_page_attr(bitmap, index - node_offset, BITMAP_PAGE_PENDING); bitmap->allclean = 0; @@ -1214,12 +1214,12 @@ static int md_bitmap_file_test_bit(struct bitmap *bitmap, sector_t block) if (!page) return -EINVAL; bit = file_page_offset(&bitmap->storage, chunk); - paddr = kmap_atomic(page); + paddr = kmap_local_page(page); if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) set = test_bit(bit, paddr); else set = test_bit_le(bit, paddr); - kunmap_atomic(paddr); + kunmap_local(paddr); return set; } @@ -1388,9 +1388,9 @@ static int md_bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) * If the bitmap is out of date, dirty the whole page * and write it out */ - paddr = kmap_atomic(page); + paddr = kmap_local_page(page); memset(paddr + offset, 0xff, PAGE_SIZE - offset); - kunmap_atomic(paddr); + kunmap_local(paddr); filemap_write_page(bitmap, i, true); if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) { @@ -1406,12 +1406,12 @@ static int md_bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) void *paddr; bool was_set; - paddr = kmap_atomic(page); + paddr = kmap_local_page(page); if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) was_set = test_bit(bit, paddr); else was_set = test_bit_le(bit, paddr); - kunmap_atomic(paddr); + kunmap_local(paddr); if (was_set) { /* if the disk bit is set, set the memory bit */ @@ -1546,10 +1546,10 @@ static void bitmap_daemon_work(struct mddev *mddev) bitmap_super_t *sb; bitmap->need_sync = 0; if (bitmap->storage.filemap) { - sb = kmap_atomic(bitmap->storage.sb_page); + sb = kmap_local_page(bitmap->storage.sb_page); sb->events_cleared = cpu_to_le64(bitmap->events_cleared); - kunmap_atomic(sb); + kunmap_local(sb); set_page_attr(bitmap, 0, BITMAP_PAGE_NEEDWRITE); } @@ -1671,24 +1671,13 @@ __acquires(bitmap->lock) } static int bitmap_startwrite(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool behind) + unsigned long sectors) { struct bitmap *bitmap = mddev->bitmap; if (!bitmap) return 0; - if (behind) { - int bw; - atomic_inc(&bitmap->behind_writes); - bw = atomic_read(&bitmap->behind_writes); - if (bw > bitmap->behind_writes_used) - bitmap->behind_writes_used = bw; - - pr_debug("inc write-behind count %d/%lu\n", - bw, bitmap->mddev->bitmap_info.max_write_behind); - } - while (sectors) { sector_t blocks; bitmap_counter_t *bmc; @@ -1737,21 +1726,13 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset, } static void bitmap_endwrite(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool success, bool behind) + unsigned long sectors) { struct bitmap *bitmap = mddev->bitmap; if (!bitmap) return; - if (behind) { - if (atomic_dec_and_test(&bitmap->behind_writes)) - wake_up(&bitmap->behind_wait); - pr_debug("dec write-behind count %d/%lu\n", - atomic_read(&bitmap->behind_writes), - bitmap->mddev->bitmap_info.max_write_behind); - } - while (sectors) { sector_t blocks; unsigned long flags; @@ -1764,15 +1745,16 @@ static void bitmap_endwrite(struct mddev *mddev, sector_t offset, return; } - if (success && !bitmap->mddev->degraded && - bitmap->events_cleared < bitmap->mddev->events) { - bitmap->events_cleared = bitmap->mddev->events; - bitmap->need_sync = 1; - sysfs_notify_dirent_safe(bitmap->sysfs_can_clear); - } - - if (!success && !NEEDED(*bmc)) + if (!bitmap->mddev->degraded) { + if (bitmap->events_cleared < bitmap->mddev->events) { + bitmap->events_cleared = bitmap->mddev->events; + bitmap->need_sync = 1; + sysfs_notify_dirent_safe( + bitmap->sysfs_can_clear); + } + } else if (!NEEDED(*bmc)) { *bmc |= NEEDED_MASK; + } if (COUNTER(*bmc) == COUNTER_MAX) wake_up(&bitmap->overflow_wait); @@ -2062,6 +2044,37 @@ static void md_bitmap_free(void *data) kfree(bitmap); } +static void bitmap_start_behind_write(struct mddev *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + int bw; + + if (!bitmap) + return; + + atomic_inc(&bitmap->behind_writes); + bw = atomic_read(&bitmap->behind_writes); + if (bw > bitmap->behind_writes_used) + bitmap->behind_writes_used = bw; + + pr_debug("inc write-behind count %d/%lu\n", + bw, bitmap->mddev->bitmap_info.max_write_behind); +} + +static void bitmap_end_behind_write(struct mddev *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + + if (!bitmap) + return; + + if (atomic_dec_and_test(&bitmap->behind_writes)) + wake_up(&bitmap->behind_wait); + pr_debug("dec write-behind count %d/%lu\n", + atomic_read(&bitmap->behind_writes), + bitmap->mddev->bitmap_info.max_write_behind); +} + static void bitmap_wait_behind_writes(struct mddev *mddev) { struct bitmap *bitmap = mddev->bitmap; @@ -2342,7 +2355,10 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats) if (!bitmap) return -ENOENT; - + if (bitmap->mddev->bitmap_info.external) + return -ENOENT; + if (!bitmap->storage.sb_page) /* no superblock */ + return -EINVAL; sb = kmap_local_page(bitmap->storage.sb_page); stats->sync_size = le64_to_cpu(sb->sync_size); kunmap_local(sb); @@ -2981,6 +2997,9 @@ static struct bitmap_operations bitmap_ops = { .dirty_bits = bitmap_dirty_bits, .unplug = bitmap_unplug, .daemon_work = bitmap_daemon_work, + + .start_behind_write = bitmap_start_behind_write, + .end_behind_write = bitmap_end_behind_write, .wait_behind_writes = bitmap_wait_behind_writes, .startwrite = bitmap_startwrite, diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 662e6fc141a7..31c93019c76b 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -84,12 +84,15 @@ struct bitmap_operations { unsigned long e); void (*unplug)(struct mddev *mddev, bool sync); void (*daemon_work)(struct mddev *mddev); + + void (*start_behind_write)(struct mddev *mddev); + void (*end_behind_write)(struct mddev *mddev); void (*wait_behind_writes)(struct mddev *mddev); int (*startwrite)(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool behind); + unsigned long sectors); void (*endwrite)(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool success, bool behind); + unsigned long sectors); bool (*start_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks, bool degraded); void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks); diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c new file mode 100644 index 000000000000..a382929ce7ba --- /dev/null +++ b/drivers/md/md-linear.c @@ -0,0 +1,354 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * linear.c : Multiple Devices driver for Linux Copyright (C) 1994-96 Marc + * ZYNGIER or + */ + +#include +#include +#include +#include +#include +#include +#include "md.h" + +struct dev_info { + struct md_rdev *rdev; + sector_t end_sector; +}; + +struct linear_conf { + struct rcu_head rcu; + sector_t array_sectors; + /* a copy of mddev->raid_disks */ + int raid_disks; + struct dev_info disks[] __counted_by(raid_disks); +}; + +/* + * find which device holds a particular offset + */ +static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) +{ + int lo, mid, hi; + struct linear_conf *conf; + + lo = 0; + hi = mddev->raid_disks - 1; + conf = mddev->private; + + /* + * Binary Search + */ + + while (hi > lo) { + + mid = (hi + lo) / 2; + if (sector < conf->disks[mid].end_sector) + hi = mid; + else + lo = mid + 1; + } + + return conf->disks + lo; +} + +static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks) +{ + struct linear_conf *conf; + sector_t array_sectors; + + conf = mddev->private; + WARN_ONCE(sectors || raid_disks, + "%s does not support generic reshape\n", __func__); + array_sectors = conf->array_sectors; + + return array_sectors; +} + +static int linear_set_limits(struct mddev *mddev) +{ + struct queue_limits lim; + int err; + + md_init_stacking_limits(&lim); + lim.max_hw_sectors = mddev->chunk_sectors; + lim.max_write_zeroes_sectors = mddev->chunk_sectors; + lim.io_min = mddev->chunk_sectors << 9; + err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); + if (err) { + queue_limits_cancel_update(mddev->gendisk->queue); + return err; + } + + return queue_limits_set(mddev->gendisk->queue, &lim); +} + +static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) +{ + struct linear_conf *conf; + struct md_rdev *rdev; + int ret = -EINVAL; + int cnt; + int i; + + conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL); + if (!conf) + return ERR_PTR(-ENOMEM); + + /* + * conf->raid_disks is copy of mddev->raid_disks. The reason to + * keep a copy of mddev->raid_disks in struct linear_conf is, + * mddev->raid_disks may not be consistent with pointers number of + * conf->disks[] when it is updated in linear_add() and used to + * iterate old conf->disks[] earray in linear_congested(). + * Here conf->raid_disks is always consitent with number of + * pointers in conf->disks[] array, and mddev->private is updated + * with rcu_assign_pointer() in linear_addr(), such race can be + * avoided. + */ + conf->raid_disks = raid_disks; + + cnt = 0; + conf->array_sectors = 0; + + rdev_for_each(rdev, mddev) { + int j = rdev->raid_disk; + struct dev_info *disk = conf->disks + j; + sector_t sectors; + + if (j < 0 || j >= raid_disks || disk->rdev) { + pr_warn("md/linear:%s: disk numbering problem. Aborting!\n", + mdname(mddev)); + goto out; + } + + disk->rdev = rdev; + if (mddev->chunk_sectors) { + sectors = rdev->sectors; + sector_div(sectors, mddev->chunk_sectors); + rdev->sectors = sectors * mddev->chunk_sectors; + } + + conf->array_sectors += rdev->sectors; + cnt++; + } + if (cnt != raid_disks) { + pr_warn("md/linear:%s: not enough drives present. Aborting!\n", + mdname(mddev)); + goto out; + } + + /* + * Here we calculate the device offsets. + */ + conf->disks[0].end_sector = conf->disks[0].rdev->sectors; + + for (i = 1; i < raid_disks; i++) + conf->disks[i].end_sector = + conf->disks[i-1].end_sector + + conf->disks[i].rdev->sectors; + + if (!mddev_is_dm(mddev)) { + ret = linear_set_limits(mddev); + if (ret) + goto out; + } + + return conf; + +out: + kfree(conf); + return ERR_PTR(ret); +} + +static int linear_run(struct mddev *mddev) +{ + struct linear_conf *conf; + int ret; + + if (md_check_no_bitmap(mddev)) + return -EINVAL; + + conf = linear_conf(mddev, mddev->raid_disks); + if (IS_ERR(conf)) + return PTR_ERR(conf); + + mddev->private = conf; + md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); + + ret = md_integrity_register(mddev); + if (ret) { + kfree(conf); + mddev->private = NULL; + } + return ret; +} + +static int linear_add(struct mddev *mddev, struct md_rdev *rdev) +{ + /* Adding a drive to a linear array allows the array to grow. + * It is permitted if the new drive has a matching superblock + * already on it, with raid_disk equal to raid_disks. + * It is achieved by creating a new linear_private_data structure + * and swapping it in in-place of the current one. + * The current one is never freed until the array is stopped. + * This avoids races. + */ + struct linear_conf *newconf, *oldconf; + + if (rdev->saved_raid_disk != mddev->raid_disks) + return -EINVAL; + + rdev->raid_disk = rdev->saved_raid_disk; + rdev->saved_raid_disk = -1; + + newconf = linear_conf(mddev, mddev->raid_disks + 1); + if (IS_ERR(newconf)) + return PTR_ERR(newconf); + + /* newconf->raid_disks already keeps a copy of * the increased + * value of mddev->raid_disks, WARN_ONCE() is just used to make + * sure of this. It is possible that oldconf is still referenced + * in linear_congested(), therefore kfree_rcu() is used to free + * oldconf until no one uses it anymore. + */ + oldconf = rcu_dereference_protected(mddev->private, + lockdep_is_held(&mddev->reconfig_mutex)); + mddev->raid_disks++; + WARN_ONCE(mddev->raid_disks != newconf->raid_disks, + "copied raid_disks doesn't match mddev->raid_disks"); + rcu_assign_pointer(mddev->private, newconf); + md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); + set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); + kfree_rcu(oldconf, rcu); + return 0; +} + +static void linear_free(struct mddev *mddev, void *priv) +{ + struct linear_conf *conf = priv; + + kfree(conf); +} + +static bool linear_make_request(struct mddev *mddev, struct bio *bio) +{ + struct dev_info *tmp_dev; + sector_t start_sector, end_sector, data_offset; + sector_t bio_sector = bio->bi_iter.bi_sector; + + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) + return true; + + tmp_dev = which_dev(mddev, bio_sector); + start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; + end_sector = tmp_dev->end_sector; + data_offset = tmp_dev->rdev->data_offset; + + if (unlikely(bio_sector >= end_sector || + bio_sector < start_sector)) + goto out_of_bounds; + + if (unlikely(is_rdev_broken(tmp_dev->rdev))) { + md_error(mddev, tmp_dev->rdev); + bio_io_error(bio); + return true; + } + + if (unlikely(bio_end_sector(bio) > end_sector)) { + /* This bio crosses a device boundary, so we have to split it */ + struct bio *split = bio_split(bio, end_sector - bio_sector, + GFP_NOIO, &mddev->bio_set); + + if (IS_ERR(split)) { + bio->bi_status = errno_to_blk_status(PTR_ERR(split)); + bio_endio(bio); + return true; + } + + bio_chain(split, bio); + submit_bio_noacct(bio); + bio = split; + } + + md_account_bio(mddev, &bio); + bio_set_dev(bio, tmp_dev->rdev->bdev); + bio->bi_iter.bi_sector = bio->bi_iter.bi_sector - + start_sector + data_offset; + + if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && + !bdev_max_discard_sectors(bio->bi_bdev))) { + /* Just ignore it */ + bio_endio(bio); + } else { + if (mddev->gendisk) + trace_block_bio_remap(bio, disk_devt(mddev->gendisk), + bio_sector); + mddev_check_write_zeroes(mddev, bio); + submit_bio_noacct(bio); + } + return true; + +out_of_bounds: + pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n", + mdname(mddev), + (unsigned long long)bio->bi_iter.bi_sector, + tmp_dev->rdev->bdev, + (unsigned long long)tmp_dev->rdev->sectors, + (unsigned long long)start_sector); + bio_io_error(bio); + return true; +} + +static void linear_status(struct seq_file *seq, struct mddev *mddev) +{ + seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2); +} + +static void linear_error(struct mddev *mddev, struct md_rdev *rdev) +{ + if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) { + char *md_name = mdname(mddev); + + pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n", + md_name, rdev->bdev); + } +} + +static void linear_quiesce(struct mddev *mddev, int state) +{ +} + +static struct md_personality linear_personality = { + .name = "linear", + .level = LEVEL_LINEAR, + .owner = THIS_MODULE, + .make_request = linear_make_request, + .run = linear_run, + .free = linear_free, + .status = linear_status, + .hot_add_disk = linear_add, + .size = linear_size, + .quiesce = linear_quiesce, + .error_handler = linear_error, +}; + +static int __init linear_init(void) +{ + return register_md_personality(&linear_personality); +} + +static void linear_exit(void) +{ + unregister_md_personality(&linear_personality); +} + +module_init(linear_init); +module_exit(linear_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)"); +MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/ +MODULE_ALIAS("md-linear"); +MODULE_ALIAS("md-level--1"); diff --git a/drivers/md/md.c b/drivers/md/md.c index aebe12b0ee27..30b3dbbce2d2 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -294,7 +294,7 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev) static struct ctl_table_header *raid_table_header; -static struct ctl_table raid_table[] = { +static const struct ctl_table raid_table[] = { { .procname = "speed_limit_min", .data = &sysctl_speed_limit_min, @@ -8124,7 +8124,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev) return; mddev->pers->error_handler(mddev, rdev); - if (mddev->pers->level == 0) + if (mddev->pers->level == 0 || mddev->pers->level == LEVEL_LINEAR) return; if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags)) @@ -8376,6 +8376,10 @@ static int md_seq_show(struct seq_file *seq, void *v) return 0; spin_unlock(&all_mddevs_lock); + + /* prevent bitmap to be freed after checking */ + mutex_lock(&mddev->bitmap_info.mutex); + spin_lock(&mddev->lock); if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) { seq_printf(seq, "%s : ", mdname(mddev)); @@ -8451,6 +8455,7 @@ static int md_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } spin_unlock(&mddev->lock); + mutex_unlock(&mddev->bitmap_info.mutex); spin_lock(&all_mddevs_lock); if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs)) @@ -8745,12 +8750,32 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, } EXPORT_SYMBOL_GPL(md_submit_discard_bio); +static void md_bitmap_start(struct mddev *mddev, + struct md_io_clone *md_io_clone) +{ + if (mddev->pers->bitmap_sector) + mddev->pers->bitmap_sector(mddev, &md_io_clone->offset, + &md_io_clone->sectors); + + mddev->bitmap_ops->startwrite(mddev, md_io_clone->offset, + md_io_clone->sectors); +} + +static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone) +{ + mddev->bitmap_ops->endwrite(mddev, md_io_clone->offset, + md_io_clone->sectors); +} + static void md_end_clone_io(struct bio *bio) { struct md_io_clone *md_io_clone = bio->bi_private; struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev; + if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap) + md_bitmap_end(mddev, md_io_clone); + if (bio->bi_status && !orig_bio->bi_status) orig_bio->bi_status = bio->bi_status; @@ -8775,6 +8800,12 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio) if (blk_queue_io_stat(bdev->bd_disk->queue)) md_io_clone->start_time = bio_start_io_acct(*bio); + if (bio_data_dir(*bio) == WRITE && mddev->bitmap) { + md_io_clone->offset = (*bio)->bi_iter.bi_sector; + md_io_clone->sectors = bio_sectors(*bio); + md_bitmap_start(mddev, md_io_clone); + } + clone->bi_end_io = md_end_clone_io; clone->bi_private = md_io_clone; *bio = clone; @@ -8793,6 +8824,9 @@ void md_free_cloned_bio(struct bio *bio) struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev; + if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap) + md_bitmap_end(mddev, md_io_clone); + if (bio->bi_status && !orig_bio->bi_status) orig_bio->bi_status = bio->bi_status; diff --git a/drivers/md/md.h b/drivers/md/md.h index 4ba93af36126..def808064ad8 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -746,6 +746,9 @@ struct md_personality void *(*takeover) (struct mddev *mddev); /* Changes the consistency policy of an active array. */ int (*change_consistency_policy)(struct mddev *mddev, const char *buf); + /* convert io ranges from array to bitmap */ + void (*bitmap_sector)(struct mddev *mddev, sector_t *offset, + unsigned long *sectors); }; struct md_sysfs_entry { @@ -828,6 +831,8 @@ struct md_io_clone { struct mddev *mddev; struct bio *orig_bio; unsigned long start_time; + sector_t offset; + unsigned long sectors; struct bio bio_clone; }; diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c index 157c9bd2fed7..8f8792e55806 100644 --- a/drivers/md/persistent-data/dm-array.c +++ b/drivers/md/persistent-data/dm-array.c @@ -917,23 +917,27 @@ static int load_ablock(struct dm_array_cursor *c) if (c->block) unlock_ablock(c->info, c->block); - c->block = NULL; - c->ab = NULL; c->index = 0; r = dm_btree_cursor_get_value(&c->cursor, &key, &value_le); if (r) { DMERR("dm_btree_cursor_get_value failed"); - dm_btree_cursor_end(&c->cursor); + goto out; } else { r = get_ablock(c->info, le64_to_cpu(value_le), &c->block, &c->ab); if (r) { DMERR("get_ablock failed"); - dm_btree_cursor_end(&c->cursor); + goto out; } } + return 0; + +out: + dm_btree_cursor_end(&c->cursor); + c->block = NULL; + c->ab = NULL; return r; } @@ -956,10 +960,10 @@ EXPORT_SYMBOL_GPL(dm_array_cursor_begin); void dm_array_cursor_end(struct dm_array_cursor *c) { - if (c->block) { + if (c->block) unlock_ablock(c->info, c->block); - dm_btree_cursor_end(&c->cursor); - } + + dm_btree_cursor_end(&c->cursor); } EXPORT_SYMBOL_GPL(dm_array_cursor_end); @@ -999,6 +1003,7 @@ int dm_array_cursor_skip(struct dm_array_cursor *c, uint32_t count) } count -= remaining; + c->index += (remaining - 1); r = dm_array_cursor_next(c); } while (!r); diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c index c7ba4e6cbbc7..98c745d90f48 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.c +++ b/drivers/md/persistent-data/dm-transaction-manager.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -77,7 +78,7 @@ static void prefetch_issue(struct prefetch_set *p, struct dm_block_manager *bm) /*----------------------------------------------------------------*/ struct shadow_info { - struct hlist_node hlist; + struct rb_node node; dm_block_t where; }; @@ -95,7 +96,7 @@ struct dm_transaction_manager { struct dm_space_map *sm; spinlock_t lock; - struct hlist_head buckets[DM_HASH_SIZE]; + struct rb_root buckets[DM_HASH_SIZE]; struct prefetch_set prefetches; }; @@ -106,14 +107,22 @@ static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b) { int r = 0; unsigned int bucket = dm_hash_block(b, DM_HASH_MASK); - struct shadow_info *si; + struct rb_node **node; spin_lock(&tm->lock); - hlist_for_each_entry(si, tm->buckets + bucket, hlist) - if (si->where == b) { + node = &tm->buckets[bucket].rb_node; + while (*node) { + struct shadow_info *si = + rb_entry(*node, struct shadow_info, node); + if (b == si->where) { r = 1; break; } + if (b < si->where) + node = &si->node.rb_left; + else + node = &si->node.rb_right; + } spin_unlock(&tm->lock); return r; @@ -130,30 +139,41 @@ static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b) si = kmalloc(sizeof(*si), GFP_NOIO); if (si) { + struct rb_node **node, *parent; si->where = b; bucket = dm_hash_block(b, DM_HASH_MASK); + spin_lock(&tm->lock); - hlist_add_head(&si->hlist, tm->buckets + bucket); + node = &tm->buckets[bucket].rb_node; + parent = NULL; + while (*node) { + struct shadow_info *si = + rb_entry(*node, struct shadow_info, node); + parent = *node; + if (b < si->where) + node = &si->node.rb_left; + else + node = &si->node.rb_right; + } + rb_link_node(&si->node, parent, node); + rb_insert_color(&si->node, &tm->buckets[bucket]); spin_unlock(&tm->lock); } } static void wipe_shadow_table(struct dm_transaction_manager *tm) { - struct shadow_info *si; - struct hlist_node *tmp; - struct hlist_head *bucket; - int i; + unsigned int i; spin_lock(&tm->lock); for (i = 0; i < DM_HASH_SIZE; i++) { - bucket = tm->buckets + i; - hlist_for_each_entry_safe(si, tmp, bucket, hlist) + while (!RB_EMPTY_ROOT(&tm->buckets[i])) { + struct shadow_info *si = + rb_entry(tm->buckets[i].rb_node, struct shadow_info, node); + rb_erase(&si->node, &tm->buckets[i]); kfree(si); - - INIT_HLIST_HEAD(bucket); + } } - spin_unlock(&tm->lock); } @@ -162,7 +182,7 @@ static void wipe_shadow_table(struct dm_transaction_manager *tm) static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm, struct dm_space_map *sm) { - int i; + unsigned int i; struct dm_transaction_manager *tm; tm = kmalloc(sizeof(*tm), GFP_KERNEL); @@ -176,7 +196,7 @@ static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm, spin_lock_init(&tm->lock); for (i = 0; i < DM_HASH_SIZE; i++) - INIT_HLIST_HEAD(tm->buckets + i); + tm->buckets[i] = RB_ROOT; prefetch_init(&tm->prefetches); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 7049ec7fb8eb..8fc9339b00c7 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -384,7 +384,7 @@ static int raid0_set_limits(struct mddev *mddev) lim.max_write_zeroes_sectors = mddev->chunk_sectors; lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * mddev->raid_disks; - lim.features |= BLK_FEAT_ATOMIC_WRITES_STACKED; + lim.features |= BLK_FEAT_ATOMIC_WRITES; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); if (err) { queue_limits_cancel_update(mddev->gendisk->queue); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 519c56f0ee3d..9d57a88dbd26 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -420,10 +420,8 @@ static void close_write(struct r1bio *r1_bio) r1_bio->behind_master_bio = NULL; } - /* clear the bitmap if all writes complete successfully */ - mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors, - !test_bit(R1BIO_Degraded, &r1_bio->state), - test_bit(R1BIO_BehindIO, &r1_bio->state)); + if (test_bit(R1BIO_BehindIO, &r1_bio->state)) + mddev->bitmap_ops->end_behind_write(mddev); md_write_end(mddev); } @@ -480,8 +478,6 @@ static void raid1_end_write_request(struct bio *bio) if (!test_bit(Faulty, &rdev->flags)) set_bit(R1BIO_WriteError, &r1_bio->state); else { - /* Fail the request */ - set_bit(R1BIO_Degraded, &r1_bio->state); /* Finished with this branch */ r1_bio->bios[mirror] = NULL; to_put = bio; @@ -1535,11 +1531,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, write_behind = true; r1_bio->bios[i] = NULL; - if (!rdev || test_bit(Faulty, &rdev->flags)) { - if (i < conf->raid_disks) - set_bit(R1BIO_Degraded, &r1_bio->state); + if (!rdev || test_bit(Faulty, &rdev->flags)) continue; - } atomic_inc(&rdev->nr_pending); if (test_bit(WriteErrorSeen, &rdev->flags)) { @@ -1558,16 +1551,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, */ max_sectors = bad_sectors; rdev_dec_pending(rdev, mddev); - /* We don't set R1BIO_Degraded as that - * only applies if the disk is - * missing, so it might be re-added, - * and we want to know to recover this - * chunk. - * In this case the device is here, - * and the fact that this chunk is not - * in-sync is recorded in the bad - * block log - */ continue; } if (is_bad) { @@ -1645,9 +1628,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, stats.behind_writes < max_write_behind) alloc_behind_master_bio(r1_bio, bio); - mddev->bitmap_ops->startwrite( - mddev, r1_bio->sector, r1_bio->sectors, - test_bit(R1BIO_BehindIO, &r1_bio->state)); + if (test_bit(R1BIO_BehindIO, &r1_bio->state)) + mddev->bitmap_ops->start_behind_write(mddev); first_clone = 0; } @@ -2614,12 +2596,10 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) * errors. */ fail = true; - if (!narrow_write_error(r1_bio, m)) { + if (!narrow_write_error(r1_bio, m)) md_error(conf->mddev, conf->mirrors[m].rdev); /* an I/O failed, we can't clear the bitmap */ - set_bit(R1BIO_Degraded, &r1_bio->state); - } rdev_dec_pending(conf->mirrors[m].rdev, conf->mddev); } @@ -2710,8 +2690,6 @@ static void raid1d(struct md_thread *thread) list_del(&r1_bio->retry_list); idx = sector_to_idx(r1_bio->sector); atomic_dec(&conf->nr_queued[idx]); - if (mddev->degraded) - set_bit(R1BIO_Degraded, &r1_bio->state); if (test_bit(R1BIO_WriteError, &r1_bio->state)) close_write(r1_bio); raid_end_bio_io(r1_bio); @@ -3239,7 +3217,7 @@ static int raid1_set_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_write_zeroes_sectors = 0; - lim.features |= BLK_FEAT_ATOMIC_WRITES_STACKED; + lim.features |= BLK_FEAT_ATOMIC_WRITES; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); if (err) { queue_limits_cancel_update(mddev->gendisk->queue); diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index 5300cbaa58a4..33f318fcc268 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -188,7 +188,6 @@ struct r1bio { enum r1bio_state { R1BIO_Uptodate, R1BIO_IsSync, - R1BIO_Degraded, R1BIO_BehindIO, /* Set ReadError on bios that experience a readerror so that * raid1d knows what to do with them. diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 7d7a8a2524dc..efe93b979167 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -428,10 +428,6 @@ static void close_write(struct r10bio *r10_bio) { struct mddev *mddev = r10_bio->mddev; - /* clear the bitmap if all writes complete successfully */ - mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors, - !test_bit(R10BIO_Degraded, &r10_bio->state), - false); md_write_end(mddev); } @@ -501,7 +497,6 @@ static void raid10_end_write_request(struct bio *bio) set_bit(R10BIO_WriteError, &r10_bio->state); else { /* Fail the request */ - set_bit(R10BIO_Degraded, &r10_bio->state); r10_bio->devs[slot].bio = NULL; to_put = bio; dec_rdev = 1; @@ -1438,10 +1433,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, r10_bio->devs[i].bio = NULL; r10_bio->devs[i].repl_bio = NULL; - if (!rdev && !rrdev) { - set_bit(R10BIO_Degraded, &r10_bio->state); + if (!rdev && !rrdev) continue; - } if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) { sector_t first_bad; sector_t dev_sector = r10_bio->devs[i].addr; @@ -1458,14 +1451,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, * to other devices yet */ max_sectors = bad_sectors; - /* We don't set R10BIO_Degraded as that - * only applies if the disk is missing, - * so it might be re-added, and we want to - * know to recover this chunk. - * In this case the device is here, and the - * fact that this chunk is not in-sync is - * recorded in the bad block log. - */ continue; } if (is_bad) { @@ -1519,8 +1504,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, md_account_bio(mddev, &bio); r10_bio->master_bio = bio; atomic_set(&r10_bio->remaining, 1); - mddev->bitmap_ops->startwrite(mddev, r10_bio->sector, r10_bio->sectors, - false); for (i = 0; i < conf->copies; i++) { if (r10_bio->devs[i].bio) @@ -2966,11 +2949,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) rdev_dec_pending(rdev, conf->mddev); } else if (bio != NULL && bio->bi_status) { fail = true; - if (!narrow_write_error(r10_bio, m)) { + if (!narrow_write_error(r10_bio, m)) md_error(conf->mddev, rdev); - set_bit(R10BIO_Degraded, - &r10_bio->state); - } rdev_dec_pending(rdev, conf->mddev); } bio = r10_bio->devs[m].repl_bio; @@ -3029,8 +3009,6 @@ static void raid10d(struct md_thread *thread) r10_bio = list_first_entry(&tmp, struct r10bio, retry_list); list_del(&r10_bio->retry_list); - if (mddev->degraded) - set_bit(R10BIO_Degraded, &r10_bio->state); if (test_bit(R10BIO_WriteError, &r10_bio->state)) @@ -4040,7 +4018,7 @@ static int raid10_set_queue_limits(struct mddev *mddev) lim.max_write_zeroes_sectors = 0; lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * raid10_nr_stripes(conf); - lim.features |= BLK_FEAT_ATOMIC_WRITES_STACKED; + lim.features |= BLK_FEAT_ATOMIC_WRITES; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); if (err) { queue_limits_cancel_update(mddev->gendisk->queue); diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 2e75e88d0802..3f16ad6904a9 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -161,7 +161,6 @@ enum r10bio_state { R10BIO_IsSync, R10BIO_IsRecover, R10BIO_IsReshape, - R10BIO_Degraded, /* Set ReadError on bios that experience a read error * so that raid10d knows what to do with them. */ diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index b4f7b79fd187..e530271cb86b 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -313,10 +313,6 @@ void r5c_handle_cached_data_endio(struct r5conf *conf, if (sh->dev[i].written) { set_bit(R5_UPTODATE, &sh->dev[i].flags); r5c_return_dev_pending_writes(conf, &sh->dev[i]); - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - !test_bit(STRIPE_DEGRADED, &sh->state), - false); } } } @@ -1023,10 +1019,10 @@ int r5l_write_stripe(struct r5l_log *log, struct stripe_head *sh) /* checksum is already calculated in last run */ if (test_bit(STRIPE_LOG_TRAPPED, &sh->state)) continue; - addr = kmap_atomic(sh->dev[i].page); + addr = kmap_local_page(sh->dev[i].page); sh->dev[i].log_checksum = crc32c_le(log->uuid_checksum, addr, PAGE_SIZE); - kunmap_atomic(addr); + kunmap_local(addr); } parity_pages = 1 + !!(sh->qd_idx >= 0); data_pages = write_disks - parity_pages; @@ -1979,9 +1975,9 @@ r5l_recovery_verify_data_checksum(struct r5l_log *log, u32 checksum; r5l_recovery_read_page(log, ctx, page, log_offset); - addr = kmap_atomic(page); + addr = kmap_local_page(page); checksum = crc32c_le(log->uuid_checksum, addr, PAGE_SIZE); - kunmap_atomic(addr); + kunmap_local(addr); return (le32_to_cpu(log_checksum) == checksum) ? 0 : -EINVAL; } @@ -2381,11 +2377,11 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, payload->size = cpu_to_le32(BLOCK_SECTORS); payload->location = cpu_to_le64( raid5_compute_blocknr(sh, i, 0)); - addr = kmap_atomic(dev->page); + addr = kmap_local_page(dev->page); payload->checksum[0] = cpu_to_le32( crc32c_le(log->uuid_checksum, addr, PAGE_SIZE)); - kunmap_atomic(addr); + kunmap_local(addr); sync_page_io(log->rdev, write_pos, PAGE_SIZE, dev->page, REQ_OP_WRITE, false); write_pos = r5l_ring_add(log, write_pos, @@ -2888,10 +2884,10 @@ int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh) if (!test_bit(R5_Wantwrite, &sh->dev[i].flags)) continue; - addr = kmap_atomic(sh->dev[i].page); + addr = kmap_local_page(sh->dev[i].page); sh->dev[i].log_checksum = crc32c_le(log->uuid_checksum, addr, PAGE_SIZE); - kunmap_atomic(addr); + kunmap_local(addr); pages++; } WARN_ON(pages == 0); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index f09e7677ee9f..5c79429acc64 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -906,8 +906,7 @@ static bool stripe_can_batch(struct stripe_head *sh) if (raid5_has_log(conf) || raid5_has_ppl(conf)) return false; return test_bit(STRIPE_BATCH_READY, &sh->state) && - !test_bit(STRIPE_BITMAP_PENDING, &sh->state) && - is_full_stripe_write(sh); + is_full_stripe_write(sh); } /* we only do back search */ @@ -1345,8 +1344,6 @@ again: submit_bio_noacct(rbi); } if (!rdev && !rrdev) { - if (op_is_write(op)) - set_bit(STRIPE_DEGRADED, &sh->state); pr_debug("skip op %d on disc %d for sector %llu\n", bi->bi_opf, i, (unsigned long long)sh->sector); clear_bit(R5_LOCKED, &sh->dev[i].flags); @@ -2884,7 +2881,6 @@ static void raid5_end_write_request(struct bio *bi) set_bit(R5_MadeGoodRepl, &sh->dev[i].flags); } else { if (bi->bi_status) { - set_bit(STRIPE_DEGRADED, &sh->state); set_bit(WriteErrorSeen, &rdev->flags); set_bit(R5_WriteError, &sh->dev[i].flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) @@ -3548,29 +3544,9 @@ static void __add_stripe_bio(struct stripe_head *sh, struct bio *bi, (*bip)->bi_iter.bi_sector, sh->sector, dd_idx, sh->dev[dd_idx].sector); - if (conf->mddev->bitmap && firstwrite) { - /* Cannot hold spinlock over bitmap_startwrite, - * but must ensure this isn't added to a batch until - * we have added to the bitmap and set bm_seq. - * So set STRIPE_BITMAP_PENDING to prevent - * batching. - * If multiple __add_stripe_bio() calls race here they - * much all set STRIPE_BITMAP_PENDING. So only the first one - * to complete "bitmap_startwrite" gets to set - * STRIPE_BIT_DELAY. This is important as once a stripe - * is added to a batch, STRIPE_BIT_DELAY cannot be changed - * any more. - */ - set_bit(STRIPE_BITMAP_PENDING, &sh->state); - spin_unlock_irq(&sh->stripe_lock); - conf->mddev->bitmap_ops->startwrite(conf->mddev, sh->sector, - RAID5_STRIPE_SECTORS(conf), false); - spin_lock_irq(&sh->stripe_lock); - clear_bit(STRIPE_BITMAP_PENDING, &sh->state); - if (!sh->batch_head) { - sh->bm_seq = conf->seq_flush+1; - set_bit(STRIPE_BIT_DELAY, &sh->state); - } + if (conf->mddev->bitmap && firstwrite && !sh->batch_head) { + sh->bm_seq = conf->seq_flush+1; + set_bit(STRIPE_BIT_DELAY, &sh->state); } } @@ -3621,7 +3597,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, BUG_ON(sh->batch_head); for (i = disks; i--; ) { struct bio *bi; - int bitmap_end = 0; if (test_bit(R5_ReadError, &sh->dev[i].flags)) { struct md_rdev *rdev = conf->disks[i].rdev; @@ -3646,8 +3621,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, sh->dev[i].towrite = NULL; sh->overwrite_disks = 0; spin_unlock_irq(&sh->stripe_lock); - if (bi) - bitmap_end = 1; log_stripe_write_finished(sh); @@ -3662,11 +3635,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, bio_io_error(bi); bi = nextbi; } - if (bitmap_end) - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - false, false); - bitmap_end = 0; /* and fail all 'written' */ bi = sh->dev[i].written; sh->dev[i].written = NULL; @@ -3675,7 +3643,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, sh->dev[i].page = sh->dev[i].orig_page; } - if (bi) bitmap_end = 1; while (bi && bi->bi_iter.bi_sector < sh->dev[i].sector + RAID5_STRIPE_SECTORS(conf)) { struct bio *bi2 = r5_next_bio(conf, bi, sh->dev[i].sector); @@ -3709,10 +3676,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, bi = nextbi; } } - if (bitmap_end) - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - false, false); /* If we were in the middle of a write the parity block might * still be locked - so just clear all R5_LOCKED flags */ @@ -4061,10 +4024,7 @@ returnbi: bio_endio(wbi); wbi = wbi2; } - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - !test_bit(STRIPE_DEGRADED, &sh->state), - false); + if (head_sh->batch_head) { sh = list_first_entry(&sh->batch_list, struct stripe_head, @@ -4341,7 +4301,6 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, s->locked++; set_bit(R5_Wantwrite, &dev->flags); - clear_bit(STRIPE_DEGRADED, &sh->state); set_bit(STRIPE_INSYNC, &sh->state); break; case check_state_run: @@ -4498,7 +4457,6 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, clear_bit(R5_Wantwrite, &dev->flags); s->locked--; } - clear_bit(STRIPE_DEGRADED, &sh->state); set_bit(STRIPE_INSYNC, &sh->state); break; @@ -4891,8 +4849,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, (1 << STRIPE_COMPUTE_RUN) | (1 << STRIPE_DISCARD) | (1 << STRIPE_BATCH_READY) | - (1 << STRIPE_BATCH_ERR) | - (1 << STRIPE_BITMAP_PENDING)), + (1 << STRIPE_BATCH_ERR)), "stripe state: %lx\n", sh->state); WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) | (1 << STRIPE_REPLACED)), @@ -4900,7 +4857,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS | (1 << STRIPE_PREREAD_ACTIVE) | - (1 << STRIPE_DEGRADED) | (1 << STRIPE_ON_UNPLUG_LIST)), head_sh->state & (1 << STRIPE_INSYNC)); @@ -5784,10 +5740,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) } spin_unlock_irq(&sh->stripe_lock); if (conf->mddev->bitmap) { - for (d = 0; d < conf->raid_disks - conf->max_degraded; - d++) - mddev->bitmap_ops->startwrite(mddev, sh->sector, - RAID5_STRIPE_SECTORS(conf), false); sh->bm_seq = conf->seq_flush + 1; set_bit(STRIPE_BIT_DELAY, &sh->state); } @@ -5928,6 +5880,54 @@ static enum reshape_loc get_reshape_loc(struct mddev *mddev, return LOC_BEHIND_RESHAPE; } +static void raid5_bitmap_sector(struct mddev *mddev, sector_t *offset, + unsigned long *sectors) +{ + struct r5conf *conf = mddev->private; + sector_t start = *offset; + sector_t end = start + *sectors; + sector_t prev_start = start; + sector_t prev_end = end; + int sectors_per_chunk; + enum reshape_loc loc; + int dd_idx; + + sectors_per_chunk = conf->chunk_sectors * + (conf->raid_disks - conf->max_degraded); + start = round_down(start, sectors_per_chunk); + end = round_up(end, sectors_per_chunk); + + start = raid5_compute_sector(conf, start, 0, &dd_idx, NULL); + end = raid5_compute_sector(conf, end, 0, &dd_idx, NULL); + + /* + * For LOC_INSIDE_RESHAPE, this IO will wait for reshape to make + * progress, hence it's the same as LOC_BEHIND_RESHAPE. + */ + loc = get_reshape_loc(mddev, conf, prev_start); + if (likely(loc != LOC_AHEAD_OF_RESHAPE)) { + *offset = start; + *sectors = end - start; + return; + } + + sectors_per_chunk = conf->prev_chunk_sectors * + (conf->previous_raid_disks - conf->max_degraded); + prev_start = round_down(prev_start, sectors_per_chunk); + prev_end = round_down(prev_end, sectors_per_chunk); + + prev_start = raid5_compute_sector(conf, prev_start, 1, &dd_idx, NULL); + prev_end = raid5_compute_sector(conf, prev_end, 1, &dd_idx, NULL); + + /* + * for LOC_AHEAD_OF_RESHAPE, reshape can make progress before this IO + * is handled in make_stripe_request(), we can't know this here hence + * we set bits for both. + */ + *offset = min(start, prev_start); + *sectors = max(end, prev_end) - *offset; +} + static enum stripe_result make_stripe_request(struct mddev *mddev, struct r5conf *conf, struct stripe_request_ctx *ctx, sector_t logical_sector, struct bio *bi) @@ -8976,6 +8976,7 @@ static struct md_personality raid6_personality = .takeover = raid6_takeover, .change_consistency_policy = raid5_change_consistency_policy, .prepare_suspend = raid5_prepare_suspend, + .bitmap_sector = raid5_bitmap_sector, }; static struct md_personality raid5_personality = { @@ -9001,6 +9002,7 @@ static struct md_personality raid5_personality = .takeover = raid5_takeover, .change_consistency_policy = raid5_change_consistency_policy, .prepare_suspend = raid5_prepare_suspend, + .bitmap_sector = raid5_bitmap_sector, }; static struct md_personality raid4_personality = @@ -9027,6 +9029,7 @@ static struct md_personality raid4_personality = .takeover = raid4_takeover, .change_consistency_policy = raid5_change_consistency_policy, .prepare_suspend = raid5_prepare_suspend, + .bitmap_sector = raid5_bitmap_sector, }; static int __init raid5_init(void) diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index d174e586698f..eafc6e9ed6ee 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -358,7 +358,6 @@ enum { STRIPE_REPLACED, STRIPE_PREREAD_ACTIVE, STRIPE_DELAYED, - STRIPE_DEGRADED, STRIPE_BIT_DELAY, STRIPE_EXPANDING, STRIPE_EXPAND_SOURCE, @@ -372,9 +371,6 @@ enum { STRIPE_ON_RELEASE_LIST, STRIPE_BATCH_READY, STRIPE_BATCH_ERR, - STRIPE_BITMAP_PENDING, /* Being added to bitmap, don't add - * to batch yet. - */ STRIPE_LOG_TRAPPED, /* trapped into log (see raid5-cache.c) * this bit is used in two scenarios: * diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index c7d36010c890..ba6828ef540e 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -7,12 +7,13 @@ #include #include -#include #include #include #include -#include #include +#include +#include +#include #include #include diff --git a/drivers/media/cec/core/cec-core.c b/drivers/media/cec/core/cec-core.c index ca0db8d457b4..e10bd588a586 100644 --- a/drivers/media/cec/core/cec-core.c +++ b/drivers/media/cec/core/cec-core.c @@ -5,13 +5,14 @@ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ +#include #include #include -#include #include #include -#include #include +#include +#include #include #include diff --git a/drivers/media/cec/core/cec-pin-error-inj.c b/drivers/media/cec/core/cec-pin-error-inj.c index fc0968b9d40e..6e61a04b8168 100644 --- a/drivers/media/cec/core/cec-pin-error-inj.c +++ b/drivers/media/cec/core/cec-pin-error-inj.c @@ -4,8 +4,9 @@ */ #include -#include #include +#include +#include #include #include "cec-pin-priv.h" diff --git a/drivers/media/cec/core/cec-pin.c b/drivers/media/cec/core/cec-pin.c index 330d5d5d86ab..a70451d99ebc 100644 --- a/drivers/media/cec/core/cec-pin.c +++ b/drivers/media/cec/core/cec-pin.c @@ -4,8 +4,9 @@ */ #include -#include #include +#include +#include #include #include "cec-pin-priv.h" diff --git a/drivers/media/cec/platform/cec-gpio/cec-gpio.c b/drivers/media/cec/platform/cec-gpio/cec-gpio.c index cf64e8871fe5..50cdc557c943 100644 --- a/drivers/media/cec/platform/cec-gpio/cec-gpio.c +++ b/drivers/media/cec/platform/cec-gpio/cec-gpio.c @@ -3,11 +3,12 @@ * Copyright 2017 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ -#include -#include #include -#include #include +#include +#include +#include +#include #include #include diff --git a/drivers/media/common/b2c2/flexcop-common.h b/drivers/media/common/b2c2/flexcop-common.h index f944c59cf495..a468ea7e77a1 100644 --- a/drivers/media/common/b2c2/flexcop-common.h +++ b/drivers/media/common/b2c2/flexcop-common.h @@ -125,8 +125,6 @@ void flexcop_dma_free(struct flexcop_dma *dma); int flexcop_dma_control_timer_irq(struct flexcop_device *fc, flexcop_dma_index_t no, int onoff); -int flexcop_dma_control_size_irq(struct flexcop_device *fc, - flexcop_dma_index_t no, int onoff); int flexcop_dma_config(struct flexcop_device *fc, struct flexcop_dma *dma, flexcop_dma_index_t dma_idx); int flexcop_dma_xfer_control(struct flexcop_device *fc, @@ -170,8 +168,6 @@ int flexcop_sram_init(struct flexcop_device *fc); void flexcop_determine_revision(struct flexcop_device *fc); void flexcop_device_name(struct flexcop_device *fc, const char *prefix, const char *suffix); -void flexcop_dump_reg(struct flexcop_device *fc, - flexcop_ibi_register reg, int num); /* from flexcop-hw-filter.c */ int flexcop_pid_feed_control(struct flexcop_device *fc, diff --git a/drivers/media/common/b2c2/flexcop-misc.c b/drivers/media/common/b2c2/flexcop-misc.c index 83d01d3a81cc..251c4f731ed1 100644 --- a/drivers/media/common/b2c2/flexcop-misc.c +++ b/drivers/media/common/b2c2/flexcop-misc.c @@ -70,16 +70,3 @@ void flexcop_device_name(struct flexcop_device *fc, flexcop_bus_names[fc->bus_type], flexcop_revision_names[fc->rev], suffix); } - -void flexcop_dump_reg(struct flexcop_device *fc, - flexcop_ibi_register reg, int num) -{ - flexcop_ibi_value v; - int i; - for (i = 0; i < num; i++) { - v = fc->read_ibi_reg(fc, reg+4*i); - deb_rdump("0x%03x: %08x, ", reg+4*i, v.raw); - } - deb_rdump("\n"); -} -EXPORT_SYMBOL(flexcop_dump_reg); diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c index 9ce5f010de3f..6063782e937a 100644 --- a/drivers/media/dvb-core/dmxdev.c +++ b/drivers/media/dvb-core/dmxdev.c @@ -731,7 +731,7 @@ static int dvb_dmxdev_filter_start(struct dmxdev_filter *filter) ret = (*secfeed)->allocate_filter(*secfeed, secfilter); if (ret < 0) { dvb_dmxdev_feed_restart(filter); - filter->feed.sec->start_filtering(*secfeed); + *secfeed = NULL; dprintk("could not get filter\n"); return ret; } diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c index d925ca24183b..415f1f91cc30 100644 --- a/drivers/media/dvb-frontends/cxd2841er.c +++ b/drivers/media/dvb-frontends/cxd2841er.c @@ -311,12 +311,8 @@ static int cxd2841er_set_reg_bits(struct cxd2841er_priv *priv, static u32 cxd2841er_calc_iffreq_xtal(enum cxd2841er_xtal xtal, u32 ifhz) { - u64 tmp; - - tmp = (u64) ifhz * 16777216; - do_div(tmp, ((xtal == SONY_XTAL_24000) ? 48000000 : 41000000)); - - return (u32) tmp; + return div_u64(ifhz * 16777216ull, + (xtal == SONY_XTAL_24000) ? 48000000 : 41000000); } static u32 cxd2841er_calc_iffreq(u32 ifhz) diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c index 822639f11c04..63bc7b74bc8b 100644 --- a/drivers/media/dvb-frontends/dib3000mb.c +++ b/drivers/media/dvb-frontends/dib3000mb.c @@ -51,7 +51,7 @@ MODULE_PARM_DESC(debug, "set debugging level (1=info,2=xfer,4=setfe,8=getfe (|-a static int dib3000_read_reg(struct dib3000_state *state, u16 reg) { u8 wb[] = { ((reg >> 8) | 0x80) & 0xff, reg & 0xff }; - u8 rb[2]; + u8 rb[2] = {}; struct i2c_msg msg[] = { { .addr = state->config.demod_address, .flags = 0, .buf = wb, .len = 2 }, { .addr = state->config.demod_address, .flags = I2C_M_RD, .buf = rb, .len = 2 }, diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c index e1ae0f9fad43..2cdab2f3d9dc 100644 --- a/drivers/media/i2c/ccs/ccs-core.c +++ b/drivers/media/i2c/ccs/ccs-core.c @@ -3335,9 +3335,11 @@ static int ccs_probe(struct i2c_client *client) rval = request_firmware(&fw, filename, &client->dev); if (!rval) { - ccs_data_parse(&sensor->sdata, fw->data, fw->size, &client->dev, - true); + rval = ccs_data_parse(&sensor->sdata, fw->data, fw->size, + &client->dev, true); release_firmware(fw); + if (rval) + goto out_power_off; } if (!(ccsdev->flags & CCS_DEVICE_FLAG_IS_SMIA) || @@ -3351,9 +3353,11 @@ static int ccs_probe(struct i2c_client *client) rval = request_firmware(&fw, filename, &client->dev); if (!rval) { - ccs_data_parse(&sensor->mdata, fw->data, fw->size, - &client->dev, true); + rval = ccs_data_parse(&sensor->mdata, fw->data, + fw->size, &client->dev, true); release_firmware(fw); + if (rval) + goto out_release_sdata; } } @@ -3566,15 +3570,15 @@ out_disable_runtime_pm: out_cleanup: ccs_cleanup(sensor); +out_free_ccs_limits: + kfree(sensor->ccs_limits); + out_release_mdata: kvfree(sensor->mdata.backing); out_release_sdata: kvfree(sensor->sdata.backing); -out_free_ccs_limits: - kfree(sensor->ccs_limits); - out_power_off: ccs_power_off(&client->dev); mutex_destroy(&sensor->mutex); diff --git a/drivers/media/i2c/ccs/ccs-data.c b/drivers/media/i2c/ccs/ccs-data.c index 08400edf77ce..f469afcea680 100644 --- a/drivers/media/i2c/ccs/ccs-data.c +++ b/drivers/media/i2c/ccs/ccs-data.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "ccs-data-defs.h" @@ -97,7 +98,7 @@ ccs_data_parse_length_specifier(const struct __ccs_data_length_specifier *__len, plen = ((size_t) (__len3->length[0] & ((1 << CCS_DATA_LENGTH_SPECIFIER_SIZE_SHIFT) - 1)) - << 16) + (__len3->length[0] << 8) + __len3->length[1]; + << 16) + (__len3->length[1] << 8) + __len3->length[2]; break; } default: @@ -948,15 +949,15 @@ int ccs_data_parse(struct ccs_data_container *ccsdata, const void *data, rval = __ccs_data_parse(&bin, ccsdata, data, len, dev, verbose); if (rval) - return rval; + goto out_cleanup; rval = bin_backing_alloc(&bin); if (rval) - return rval; + goto out_cleanup; rval = __ccs_data_parse(&bin, ccsdata, data, len, dev, false); if (rval) - goto out_free; + goto out_cleanup; if (verbose && ccsdata->version) print_ccs_data_version(dev, ccsdata->version); @@ -965,15 +966,17 @@ int ccs_data_parse(struct ccs_data_container *ccsdata, const void *data, rval = -EPROTO; dev_dbg(dev, "parsing mismatch; base %p; now %p; end %p\n", bin.base, bin.now, bin.end); - goto out_free; + goto out_cleanup; } ccsdata->backing = bin.base; return 0; -out_free: +out_cleanup: kvfree(bin.base); + memset(ccsdata, 0, sizeof(*ccsdata)); + dev_warn(dev, "failed to parse CCS static data: %d\n", rval); return rval; } diff --git a/drivers/media/i2c/ds90ub913.c b/drivers/media/i2c/ds90ub913.c index 79bddfee2e2e..fd2d2d5272bf 100644 --- a/drivers/media/i2c/ds90ub913.c +++ b/drivers/media/i2c/ds90ub913.c @@ -8,6 +8,7 @@ * Copyright (c) 2023 Tomi Valkeinen */ +#include #include #include #include @@ -146,6 +147,19 @@ static int ub913_write(const struct ub913_data *priv, u8 reg, u8 val) return ret; } +static int ub913_update_bits(const struct ub913_data *priv, u8 reg, u8 mask, + u8 val) +{ + int ret; + + ret = regmap_update_bits(priv->regmap, reg, mask, val); + if (ret < 0) + dev_err(&priv->client->dev, + "Cannot update register 0x%02x %d!\n", reg, ret); + + return ret; +} + /* * GPIO chip */ @@ -733,10 +747,13 @@ static int ub913_hw_init(struct ub913_data *priv) if (ret) return dev_err_probe(dev, ret, "i2c master init failed\n"); - ub913_read(priv, UB913_REG_GENERAL_CFG, &v); - v &= ~UB913_REG_GENERAL_CFG_PCLK_RISING; - v |= priv->pclk_polarity_rising ? UB913_REG_GENERAL_CFG_PCLK_RISING : 0; - ub913_write(priv, UB913_REG_GENERAL_CFG, v); + ret = ub913_update_bits(priv, UB913_REG_GENERAL_CFG, + UB913_REG_GENERAL_CFG_PCLK_RISING, + FIELD_PREP(UB913_REG_GENERAL_CFG_PCLK_RISING, + priv->pclk_polarity_rising)); + + if (ret) + return ret; return 0; } @@ -793,7 +810,6 @@ static void ub913_subdev_uninit(struct ub913_data *priv) v4l2_async_unregister_subdev(&priv->sd); ub913_v4l2_nf_unregister(priv); v4l2_subdev_cleanup(&priv->sd); - fwnode_handle_put(priv->sd.fwnode); media_entity_cleanup(&priv->sd.entity); } diff --git a/drivers/media/i2c/ds90ub953.c b/drivers/media/i2c/ds90ub953.c index 725589b3e1c5..46569381b332 100644 --- a/drivers/media/i2c/ds90ub953.c +++ b/drivers/media/i2c/ds90ub953.c @@ -65,6 +65,9 @@ #define UB953_REG_GPIO_INPUT_CTRL_OUT_EN(n) BIT(4 + (n)) #define UB953_REG_GPIO_INPUT_CTRL_INPUT_EN(n) BIT(0 + (n)) +#define UB953_REG_BC_CTRL 0x49 +#define UB953_REG_BC_CTRL_CRC_ERR_CLR BIT(3) + #define UB953_REG_REV_MASK_ID 0x50 #define UB953_REG_GENERAL_STATUS 0x52 @@ -397,8 +400,13 @@ static int ub953_gpiochip_probe(struct ub953_data *priv) int ret; /* Set all GPIOs to local input mode */ - ub953_write(priv, UB953_REG_LOCAL_GPIO_DATA, 0); - ub953_write(priv, UB953_REG_GPIO_INPUT_CTRL, 0xf); + ret = ub953_write(priv, UB953_REG_LOCAL_GPIO_DATA, 0); + if (ret) + return ret; + + ret = ub953_write(priv, UB953_REG_GPIO_INPUT_CTRL, 0xf); + if (ret) + return ret; gc->label = dev_name(dev); gc->parent = dev; @@ -618,6 +626,12 @@ static int ub953_log_status(struct v4l2_subdev *sd) ub953_read(priv, UB953_REG_CRC_ERR_CNT2, &v2); dev_info(dev, "CRC error count %u\n", v1 | (v2 << 8)); + /* Clear CRC error counter */ + if (v1 || v2) + regmap_update_bits(priv->regmap, UB953_REG_BC_CTRL, + UB953_REG_BC_CTRL_CRC_ERR_CLR, + UB953_REG_BC_CTRL_CRC_ERR_CLR); + ub953_read(priv, UB953_REG_CSI_ERR_CNT, &v); dev_info(dev, "CSI error count %u\n", v); @@ -958,10 +972,11 @@ static void ub953_calc_clkout_params(struct ub953_data *priv, clkout_data->rate = clkout_rate; } -static void ub953_write_clkout_regs(struct ub953_data *priv, - const struct ub953_clkout_data *clkout_data) +static int ub953_write_clkout_regs(struct ub953_data *priv, + const struct ub953_clkout_data *clkout_data) { u8 clkout_ctrl0, clkout_ctrl1; + int ret; if (priv->hw_data->is_ub971) clkout_ctrl0 = clkout_data->m; @@ -971,8 +986,15 @@ static void ub953_write_clkout_regs(struct ub953_data *priv, clkout_ctrl1 = clkout_data->n; - ub953_write(priv, UB953_REG_CLKOUT_CTRL0, clkout_ctrl0); - ub953_write(priv, UB953_REG_CLKOUT_CTRL1, clkout_ctrl1); + ret = ub953_write(priv, UB953_REG_CLKOUT_CTRL0, clkout_ctrl0); + if (ret) + return ret; + + ret = ub953_write(priv, UB953_REG_CLKOUT_CTRL1, clkout_ctrl1); + if (ret) + return ret; + + return 0; } static unsigned long ub953_clkout_recalc_rate(struct clk_hw *hw, @@ -1052,9 +1074,7 @@ static int ub953_clkout_set_rate(struct clk_hw *hw, unsigned long rate, dev_dbg(&priv->client->dev, "%s %lu (requested %lu)\n", __func__, clkout_data.rate, rate); - ub953_write_clkout_regs(priv, &clkout_data); - - return 0; + return ub953_write_clkout_regs(priv, &clkout_data); } static const struct clk_ops ub953_clkout_ops = { @@ -1079,7 +1099,9 @@ static int ub953_register_clkout(struct ub953_data *priv) /* Initialize clkout to 25MHz by default */ ub953_calc_clkout_params(priv, UB953_DEFAULT_CLKOUT_RATE, &clkout_data); - ub953_write_clkout_regs(priv, &clkout_data); + ret = ub953_write_clkout_regs(priv, &clkout_data); + if (ret) + return ret; priv->clkout_clk_hw.init = &init; @@ -1226,10 +1248,15 @@ static int ub953_hw_init(struct ub953_data *priv) if (ret) return dev_err_probe(dev, ret, "i2c init failed\n"); - ub953_write(priv, UB953_REG_GENERAL_CFG, - (priv->non_continous_clk ? 0 : UB953_REG_GENERAL_CFG_CONT_CLK) | - ((priv->num_data_lanes - 1) << UB953_REG_GENERAL_CFG_CSI_LANE_SEL_SHIFT) | - UB953_REG_GENERAL_CFG_CRC_TX_GEN_ENABLE); + v = 0; + v |= priv->non_continous_clk ? 0 : UB953_REG_GENERAL_CFG_CONT_CLK; + v |= (priv->num_data_lanes - 1) << + UB953_REG_GENERAL_CFG_CSI_LANE_SEL_SHIFT; + v |= UB953_REG_GENERAL_CFG_CRC_TX_GEN_ENABLE; + + ret = ub953_write(priv, UB953_REG_GENERAL_CFG, v); + if (ret) + return ret; return 0; } @@ -1288,7 +1315,6 @@ static void ub953_subdev_uninit(struct ub953_data *priv) v4l2_async_unregister_subdev(&priv->sd); ub953_v4l2_notifier_unregister(priv); v4l2_subdev_cleanup(&priv->sd); - fwnode_handle_put(priv->sd.fwnode); media_entity_cleanup(&priv->sd.entity); } diff --git a/drivers/media/i2c/ds90ub960.c b/drivers/media/i2c/ds90ub960.c index 1b1ff7f7505b..5dde8452739b 100644 --- a/drivers/media/i2c/ds90ub960.c +++ b/drivers/media/i2c/ds90ub960.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -51,7 +52,16 @@ #include #include -#define MHZ(v) ((u32)((v) * 1000000U)) +#define MHZ(v) ((u32)((v) * HZ_PER_MHZ)) + +/* + * If this is defined, the i2c addresses from UB960_DEBUG_I2C_RX_ID to + * UB960_DEBUG_I2C_RX_ID + 3 can be used to access the paged RX port registers + * directly. + * + * Only for debug purposes. + */ +/* #define UB960_DEBUG_I2C_RX_ID 0x40 */ #define UB960_POLL_TIME_MS 500 @@ -349,12 +359,13 @@ #define UB960_SR_FPD3_RX_ID(n) (0xf0 + (n)) #define UB960_SR_FPD3_RX_ID_LEN 6 -#define UB960_SR_I2C_RX_ID(n) (0xf8 + (n)) /* < UB960_FPD_RX_NPORTS */ +#define UB960_SR_I2C_RX_ID(n) (0xf8 + (n)) + +#define UB9702_SR_REFCLK_FREQ 0x3d /* Indirect register blocks */ #define UB960_IND_TARGET_PAT_GEN 0x00 #define UB960_IND_TARGET_RX_ANA(n) (0x01 + (n)) -#define UB960_IND_TARGET_CSI_CSIPLL_REG_1 0x92 /* UB9702 */ #define UB960_IND_TARGET_CSI_ANA 0x07 /* UB960_IR_PGEN_*: Indirect Registers for Test Pattern Generator */ @@ -568,11 +579,23 @@ struct ub960_format_info { }; static const struct ub960_format_info ub960_formats[] = { + { .code = MEDIA_BUS_FMT_RGB888_1X24, .bpp = 24, .datatype = MIPI_CSI2_DT_RGB888, }, + { .code = MEDIA_BUS_FMT_YUYV8_1X16, .bpp = 16, .datatype = MIPI_CSI2_DT_YUV422_8B, }, { .code = MEDIA_BUS_FMT_UYVY8_1X16, .bpp = 16, .datatype = MIPI_CSI2_DT_YUV422_8B, }, { .code = MEDIA_BUS_FMT_VYUY8_1X16, .bpp = 16, .datatype = MIPI_CSI2_DT_YUV422_8B, }, { .code = MEDIA_BUS_FMT_YVYU8_1X16, .bpp = 16, .datatype = MIPI_CSI2_DT_YUV422_8B, }, + { .code = MEDIA_BUS_FMT_SBGGR8_1X8, .bpp = 8, .datatype = MIPI_CSI2_DT_RAW8, }, + { .code = MEDIA_BUS_FMT_SGBRG8_1X8, .bpp = 8, .datatype = MIPI_CSI2_DT_RAW8, }, + { .code = MEDIA_BUS_FMT_SGRBG8_1X8, .bpp = 8, .datatype = MIPI_CSI2_DT_RAW8, }, + { .code = MEDIA_BUS_FMT_SRGGB8_1X8, .bpp = 8, .datatype = MIPI_CSI2_DT_RAW8, }, + + { .code = MEDIA_BUS_FMT_SBGGR10_1X10, .bpp = 10, .datatype = MIPI_CSI2_DT_RAW10, }, + { .code = MEDIA_BUS_FMT_SGBRG10_1X10, .bpp = 10, .datatype = MIPI_CSI2_DT_RAW10, }, + { .code = MEDIA_BUS_FMT_SGRBG10_1X10, .bpp = 10, .datatype = MIPI_CSI2_DT_RAW10, }, + { .code = MEDIA_BUS_FMT_SRGGB10_1X10, .bpp = 10, .datatype = MIPI_CSI2_DT_RAW10, }, + { .code = MEDIA_BUS_FMT_SBGGR12_1X12, .bpp = 12, .datatype = MIPI_CSI2_DT_RAW12, }, { .code = MEDIA_BUS_FMT_SGBRG12_1X12, .bpp = 12, .datatype = MIPI_CSI2_DT_RAW12, }, { .code = MEDIA_BUS_FMT_SGRBG12_1X12, .bpp = 12, .datatype = MIPI_CSI2_DT_RAW12, }, @@ -1552,7 +1575,12 @@ static int ub960_rxport_wait_locks(struct ub960_data *priv, if (missing == 0) break; - msleep(50); + /* + * The sleep time of 10 ms was found by testing to give a lock + * with a few iterations. It can be decreased if on some setups + * the lock can be achieved much faster. + */ + fsleep(10 * USEC_PER_MSEC); } if (lock_mask) @@ -1574,16 +1602,24 @@ static int ub960_rxport_wait_locks(struct ub960_data *priv, ub960_rxport_read16(priv, nport, UB960_RR_RX_FREQ_HIGH, &v); - ret = ub960_rxport_get_strobe_pos(priv, nport, &strobe_pos); - if (ret) - return ret; + if (priv->hw_data->is_ub9702) { + dev_dbg(dev, "\trx%u: locked, freq %llu Hz\n", + nport, ((u64)v * HZ_PER_MHZ) >> 8); + } else { + ret = ub960_rxport_get_strobe_pos(priv, nport, + &strobe_pos); + if (ret) + return ret; - ret = ub960_rxport_get_eq_level(priv, nport, &eq_level); - if (ret) - return ret; + ret = ub960_rxport_get_eq_level(priv, nport, &eq_level); + if (ret) + return ret; - dev_dbg(dev, "\trx%u: locked, SP: %d, EQ: %u, freq %llu Hz\n", - nport, strobe_pos, eq_level, (v * 1000000ULL) >> 8); + dev_dbg(dev, + "\trx%u: locked, SP: %d, EQ: %u, freq %llu Hz\n", + nport, strobe_pos, eq_level, + ((u64)v * HZ_PER_MHZ) >> 8); + } } return 0; @@ -2412,7 +2448,6 @@ static int ub960_configure_ports_for_streaming(struct ub960_data *priv, } rx_data[UB960_MAX_RX_NPORTS] = {}; u8 vc_map[UB960_MAX_RX_NPORTS] = {}; struct v4l2_subdev_route *route; - unsigned int nport; int ret; ret = ub960_validate_stream_vcs(priv); @@ -2482,7 +2517,8 @@ static int ub960_configure_ports_for_streaming(struct ub960_data *priv, */ fwd_ctl = GENMASK(7, 4); - for (nport = 0; nport < priv->hw_data->num_rxports; nport++) { + for (unsigned int nport = 0; nport < priv->hw_data->num_rxports; + nport++) { struct ub960_rxport *rxport = priv->rxports[nport]; u8 vc = vc_map[nport]; @@ -2522,7 +2558,7 @@ static int ub960_configure_ports_for_streaming(struct ub960_data *priv, for (i = 0; i < 8; i++) ub960_rxport_write(priv, nport, UB960_RR_VC_ID_MAP(i), - nport); + (nport << 4) | nport); } break; @@ -2939,20 +2975,78 @@ static const struct v4l2_subdev_pad_ops ub960_pad_ops = { .set_fmt = ub960_set_fmt, }; +static void ub960_log_status_ub960_sp_eq(struct ub960_data *priv, + unsigned int nport) +{ + struct device *dev = &priv->client->dev; + u8 eq_level; + s8 strobe_pos; + int ret; + u8 v; + + /* Strobe */ + + ret = ub960_read(priv, UB960_XR_AEQ_CTL1, &v); + if (ret) + return; + + dev_info(dev, "\t%s strobe\n", + (v & UB960_XR_AEQ_CTL1_AEQ_SFILTER_EN) ? "Adaptive" : + "Manual"); + + if (v & UB960_XR_AEQ_CTL1_AEQ_SFILTER_EN) { + ret = ub960_read(priv, UB960_XR_SFILTER_CFG, &v); + if (ret) + return; + + dev_info(dev, "\tStrobe range [%d, %d]\n", + ((v >> UB960_XR_SFILTER_CFG_SFILTER_MIN_SHIFT) & 0xf) - 7, + ((v >> UB960_XR_SFILTER_CFG_SFILTER_MAX_SHIFT) & 0xf) - 7); + } + + ret = ub960_rxport_get_strobe_pos(priv, nport, &strobe_pos); + if (ret) + return; + + dev_info(dev, "\tStrobe pos %d\n", strobe_pos); + + /* EQ */ + + ret = ub960_rxport_read(priv, nport, UB960_RR_AEQ_BYPASS, &v); + if (ret) + return; + + dev_info(dev, "\t%s EQ\n", + (v & UB960_RR_AEQ_BYPASS_ENABLE) ? "Manual" : + "Adaptive"); + + if (!(v & UB960_RR_AEQ_BYPASS_ENABLE)) { + ret = ub960_rxport_read(priv, nport, UB960_RR_AEQ_MIN_MAX, &v); + if (ret) + return; + + dev_info(dev, "\tEQ range [%u, %u]\n", + (v >> UB960_RR_AEQ_MIN_MAX_AEQ_FLOOR_SHIFT) & 0xf, + (v >> UB960_RR_AEQ_MIN_MAX_AEQ_MAX_SHIFT) & 0xf); + } + + if (ub960_rxport_get_eq_level(priv, nport, &eq_level) == 0) + dev_info(dev, "\tEQ level %u\n", eq_level); +} + static int ub960_log_status(struct v4l2_subdev *sd) { struct ub960_data *priv = sd_to_ub960(sd); struct device *dev = &priv->client->dev; struct v4l2_subdev_state *state; unsigned int nport; - unsigned int i; u16 v16 = 0; u8 v = 0; u8 id[UB960_SR_FPD3_RX_ID_LEN]; state = v4l2_subdev_lock_and_get_active_state(sd); - for (i = 0; i < sizeof(id); i++) + for (unsigned int i = 0; i < sizeof(id); i++) ub960_read(priv, UB960_SR_FPD3_RX_ID(i), &id[i]); dev_info(dev, "ID '%.*s'\n", (int)sizeof(id), id); @@ -2986,9 +3080,6 @@ static int ub960_log_status(struct v4l2_subdev *sd) for (nport = 0; nport < priv->hw_data->num_rxports; nport++) { struct ub960_rxport *rxport = priv->rxports[nport]; - u8 eq_level; - s8 strobe_pos; - unsigned int i; dev_info(dev, "RX %u\n", nport); @@ -3009,7 +3100,7 @@ static int ub960_log_status(struct v4l2_subdev *sd) dev_info(dev, "\trx_port_sts2 %#02x\n", v); ub960_rxport_read16(priv, nport, UB960_RR_RX_FREQ_HIGH, &v16); - dev_info(dev, "\tlink freq %llu Hz\n", (v16 * 1000000ULL) >> 8); + dev_info(dev, "\tlink freq %llu Hz\n", ((u64)v16 * HZ_PER_MHZ) >> 8); ub960_rxport_read16(priv, nport, UB960_RR_RX_PAR_ERR_HI, &v16); dev_info(dev, "\tparity errors %u\n", v16); @@ -3023,47 +3114,11 @@ static int ub960_log_status(struct v4l2_subdev *sd) ub960_rxport_read(priv, nport, UB960_RR_CSI_ERR_COUNTER, &v); dev_info(dev, "\tcsi_err_counter %u\n", v); - /* Strobe */ - - ub960_read(priv, UB960_XR_AEQ_CTL1, &v); - - dev_info(dev, "\t%s strobe\n", - (v & UB960_XR_AEQ_CTL1_AEQ_SFILTER_EN) ? "Adaptive" : - "Manual"); - - if (v & UB960_XR_AEQ_CTL1_AEQ_SFILTER_EN) { - ub960_read(priv, UB960_XR_SFILTER_CFG, &v); - - dev_info(dev, "\tStrobe range [%d, %d]\n", - ((v >> UB960_XR_SFILTER_CFG_SFILTER_MIN_SHIFT) & 0xf) - 7, - ((v >> UB960_XR_SFILTER_CFG_SFILTER_MAX_SHIFT) & 0xf) - 7); - } - - ub960_rxport_get_strobe_pos(priv, nport, &strobe_pos); - - dev_info(dev, "\tStrobe pos %d\n", strobe_pos); - - /* EQ */ - - ub960_rxport_read(priv, nport, UB960_RR_AEQ_BYPASS, &v); - - dev_info(dev, "\t%s EQ\n", - (v & UB960_RR_AEQ_BYPASS_ENABLE) ? "Manual" : - "Adaptive"); - - if (!(v & UB960_RR_AEQ_BYPASS_ENABLE)) { - ub960_rxport_read(priv, nport, UB960_RR_AEQ_MIN_MAX, &v); - - dev_info(dev, "\tEQ range [%u, %u]\n", - (v >> UB960_RR_AEQ_MIN_MAX_AEQ_FLOOR_SHIFT) & 0xf, - (v >> UB960_RR_AEQ_MIN_MAX_AEQ_MAX_SHIFT) & 0xf); - } - - if (ub960_rxport_get_eq_level(priv, nport, &eq_level) == 0) - dev_info(dev, "\tEQ level %u\n", eq_level); + if (!priv->hw_data->is_ub9702) + ub960_log_status_ub960_sp_eq(priv, nport); /* GPIOs */ - for (i = 0; i < UB960_NUM_BC_GPIOS; i++) { + for (unsigned int i = 0; i < UB960_NUM_BC_GPIOS; i++) { u8 ctl_reg; u8 ctl_shift; @@ -3834,13 +3889,16 @@ static int ub960_enable_core_hw(struct ub960_data *priv) if (ret) goto err_pd_gpio; - ret = ub960_read(priv, UB960_XR_REFCLK_FREQ, &refclk_freq); + if (priv->hw_data->is_ub9702) + ret = ub960_read(priv, UB9702_SR_REFCLK_FREQ, &refclk_freq); + else + ret = ub960_read(priv, UB960_XR_REFCLK_FREQ, &refclk_freq); if (ret) goto err_pd_gpio; dev_dbg(dev, "refclk valid %u freq %u MHz (clk fw freq %lu MHz)\n", !!(dev_sts & BIT(4)), refclk_freq, - clk_get_rate(priv->refclk) / 1000000); + clk_get_rate(priv->refclk) / HZ_PER_MHZ); /* Disable all RX ports by default */ ret = ub960_write(priv, UB960_SR_RX_PORT_CTL, 0); @@ -3974,6 +4032,12 @@ static int ub960_probe(struct i2c_client *client) schedule_delayed_work(&priv->poll_work, msecs_to_jiffies(UB960_POLL_TIME_MS)); +#ifdef UB960_DEBUG_I2C_RX_ID + for (unsigned int i = 0; i < priv->hw_data->num_rxports; i++) + ub960_write(priv, UB960_SR_I2C_RX_ID(i), + (UB960_DEBUG_I2C_RX_ID + i) << 1); +#endif + return 0; err_free_sers: diff --git a/drivers/media/i2c/imx208.c b/drivers/media/i2c/imx208.c index 2184c90f7864..2b5a6ce7b1ae 100644 --- a/drivers/media/i2c/imx208.c +++ b/drivers/media/i2c/imx208.c @@ -814,7 +814,7 @@ out_unlock: } static ssize_t otp_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct i2c_client *client = to_i2c_client(kobj_to_dev(kobj)); diff --git a/drivers/media/i2c/imx290.c b/drivers/media/i2c/imx290.c index f5ee6bd3b52d..fbf7eba3d71d 100644 --- a/drivers/media/i2c/imx290.c +++ b/drivers/media/i2c/imx290.c @@ -170,12 +170,15 @@ enum imx290_model { IMX290_MODEL_IMX290LQR, IMX290_MODEL_IMX290LLR, IMX290_MODEL_IMX327LQR, + IMX290_MODEL_IMX462LQR, + IMX290_MODEL_IMX462LLR, }; struct imx290_model_info { enum imx290_colour_variant colour_variant; const struct cci_reg_sequence *init_regs; size_t init_regs_num; + unsigned int max_analog_gain; const char *name; }; @@ -267,7 +270,6 @@ static const struct cci_reg_sequence imx290_global_init_settings[] = { { IMX290_WINWV, 1097 }, { IMX290_XSOUTSEL, IMX290_XSOUTSEL_XVSOUTSEL_VSYNC | IMX290_XSOUTSEL_XHSOUTSEL_HSYNC }, - { CCI_REG8(0x3011), 0x02 }, { CCI_REG8(0x3012), 0x64 }, { CCI_REG8(0x3013), 0x00 }, }; @@ -275,6 +277,51 @@ static const struct cci_reg_sequence imx290_global_init_settings[] = { static const struct cci_reg_sequence imx290_global_init_settings_290[] = { { CCI_REG8(0x300f), 0x00 }, { CCI_REG8(0x3010), 0x21 }, + { CCI_REG8(0x3011), 0x00 }, + { CCI_REG8(0x3016), 0x09 }, + { CCI_REG8(0x3070), 0x02 }, + { CCI_REG8(0x3071), 0x11 }, + { CCI_REG8(0x309b), 0x10 }, + { CCI_REG8(0x309c), 0x22 }, + { CCI_REG8(0x30a2), 0x02 }, + { CCI_REG8(0x30a6), 0x20 }, + { CCI_REG8(0x30a8), 0x20 }, + { CCI_REG8(0x30aa), 0x20 }, + { CCI_REG8(0x30ac), 0x20 }, + { CCI_REG8(0x30b0), 0x43 }, + { CCI_REG8(0x3119), 0x9e }, + { CCI_REG8(0x311c), 0x1e }, + { CCI_REG8(0x311e), 0x08 }, + { CCI_REG8(0x3128), 0x05 }, + { CCI_REG8(0x313d), 0x83 }, + { CCI_REG8(0x3150), 0x03 }, + { CCI_REG8(0x317e), 0x00 }, + { CCI_REG8(0x32b8), 0x50 }, + { CCI_REG8(0x32b9), 0x10 }, + { CCI_REG8(0x32ba), 0x00 }, + { CCI_REG8(0x32bb), 0x04 }, + { CCI_REG8(0x32c8), 0x50 }, + { CCI_REG8(0x32c9), 0x10 }, + { CCI_REG8(0x32ca), 0x00 }, + { CCI_REG8(0x32cb), 0x04 }, + { CCI_REG8(0x332c), 0xd3 }, + { CCI_REG8(0x332d), 0x10 }, + { CCI_REG8(0x332e), 0x0d }, + { CCI_REG8(0x3358), 0x06 }, + { CCI_REG8(0x3359), 0xe1 }, + { CCI_REG8(0x335a), 0x11 }, + { CCI_REG8(0x3360), 0x1e }, + { CCI_REG8(0x3361), 0x61 }, + { CCI_REG8(0x3362), 0x10 }, + { CCI_REG8(0x33b0), 0x50 }, + { CCI_REG8(0x33b2), 0x1a }, + { CCI_REG8(0x33b3), 0x04 }, +}; + +static const struct cci_reg_sequence imx290_global_init_settings_462[] = { + { CCI_REG8(0x300f), 0x00 }, + { CCI_REG8(0x3010), 0x21 }, + { CCI_REG8(0x3011), 0x02 }, { CCI_REG8(0x3016), 0x09 }, { CCI_REG8(0x3070), 0x02 }, { CCI_REG8(0x3071), 0x11 }, @@ -328,6 +375,7 @@ static const struct cci_reg_sequence xclk_regs[][IMX290_NUM_CLK_REGS] = { }; static const struct cci_reg_sequence imx290_global_init_settings_327[] = { + { CCI_REG8(0x3011), 0x02 }, { CCI_REG8(0x309e), 0x4A }, { CCI_REG8(0x309f), 0x4A }, { CCI_REG8(0x313b), 0x61 }, @@ -876,14 +924,10 @@ static int imx290_ctrl_init(struct imx290 *imx290) * up to 72.0dB (240) add further digital gain. Limit the range to * analog gain only, support for digital gain can be added separately * if needed. - * - * The IMX327 and IMX462 are largely compatible with the IMX290, but - * have an analog gain range of 0.0dB to 29.4dB and 42dB of digital - * gain. When support for those sensors gets added to the driver, the - * gain control should be adjusted accordingly. */ v4l2_ctrl_new_std(&imx290->ctrls, &imx290_ctrl_ops, - V4L2_CID_ANALOGUE_GAIN, 0, 100, 1, 0); + V4L2_CID_ANALOGUE_GAIN, 0, + imx290->model->max_analog_gain, 1, 0); /* * Correct range will be determined through imx290_ctrl_update setting @@ -1441,20 +1485,37 @@ static const struct imx290_model_info imx290_models[] = { .colour_variant = IMX290_VARIANT_COLOUR, .init_regs = imx290_global_init_settings_290, .init_regs_num = ARRAY_SIZE(imx290_global_init_settings_290), + .max_analog_gain = 100, .name = "imx290", }, [IMX290_MODEL_IMX290LLR] = { .colour_variant = IMX290_VARIANT_MONO, .init_regs = imx290_global_init_settings_290, .init_regs_num = ARRAY_SIZE(imx290_global_init_settings_290), + .max_analog_gain = 100, .name = "imx290", }, [IMX290_MODEL_IMX327LQR] = { .colour_variant = IMX290_VARIANT_COLOUR, .init_regs = imx290_global_init_settings_327, .init_regs_num = ARRAY_SIZE(imx290_global_init_settings_327), + .max_analog_gain = 98, .name = "imx327", }, + [IMX290_MODEL_IMX462LQR] = { + .colour_variant = IMX290_VARIANT_COLOUR, + .init_regs = imx290_global_init_settings_462, + .init_regs_num = ARRAY_SIZE(imx290_global_init_settings_462), + .max_analog_gain = 98, + .name = "imx462", + }, + [IMX290_MODEL_IMX462LLR] = { + .colour_variant = IMX290_VARIANT_MONO, + .init_regs = imx290_global_init_settings_462, + .init_regs_num = ARRAY_SIZE(imx290_global_init_settings_462), + .max_analog_gain = 98, + .name = "imx462", + }, }; static int imx290_parse_dt(struct imx290 *imx290) @@ -1653,6 +1714,12 @@ static const struct of_device_id imx290_of_match[] = { }, { .compatible = "sony,imx327lqr", .data = &imx290_models[IMX290_MODEL_IMX327LQR], + }, { + .compatible = "sony,imx462lqr", + .data = &imx290_models[IMX290_MODEL_IMX462LQR], + }, { + .compatible = "sony,imx462llr", + .data = &imx290_models[IMX290_MODEL_IMX462LLR], }, { /* sentinel */ }, }; diff --git a/drivers/media/i2c/imx296.c b/drivers/media/i2c/imx296.c index 83149fa729c4..f3bec16b527c 100644 --- a/drivers/media/i2c/imx296.c +++ b/drivers/media/i2c/imx296.c @@ -954,6 +954,8 @@ static int imx296_identify_model(struct imx296 *sensor) return ret; } + usleep_range(2000, 5000); + ret = imx296_read(sensor, IMX296_SENSOR_INFO); if (ret < 0) { dev_err(sensor->dev, "failed to read sensor information (%d)\n", diff --git a/drivers/media/i2c/imx412.c b/drivers/media/i2c/imx412.c index 0bfe3046fcc8..c74097a59c42 100644 --- a/drivers/media/i2c/imx412.c +++ b/drivers/media/i2c/imx412.c @@ -547,7 +547,7 @@ static int imx412_update_exp_gain(struct imx412 *imx412, u32 exposure, u32 gain) lpfr = imx412->vblank + imx412->cur_mode->height; - dev_dbg(imx412->dev, "Set exp %u, analog gain %u, lpfr %u", + dev_dbg(imx412->dev, "Set exp %u, analog gain %u, lpfr %u\n", exposure, gain, lpfr); ret = imx412_write_reg(imx412, IMX412_REG_HOLD, 1, 1); @@ -594,7 +594,7 @@ static int imx412_set_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_VBLANK: imx412->vblank = imx412->vblank_ctrl->val; - dev_dbg(imx412->dev, "Received vblank %u, new lpfr %u", + dev_dbg(imx412->dev, "Received vblank %u, new lpfr %u\n", imx412->vblank, imx412->vblank + imx412->cur_mode->height); @@ -613,7 +613,7 @@ static int imx412_set_ctrl(struct v4l2_ctrl *ctrl) exposure = ctrl->val; analog_gain = imx412->again_ctrl->val; - dev_dbg(imx412->dev, "Received exp %u, analog gain %u", + dev_dbg(imx412->dev, "Received exp %u, analog gain %u\n", exposure, analog_gain); ret = imx412_update_exp_gain(imx412, exposure, analog_gain); @@ -622,7 +622,7 @@ static int imx412_set_ctrl(struct v4l2_ctrl *ctrl) break; default: - dev_err(imx412->dev, "Invalid control %d", ctrl->id); + dev_err(imx412->dev, "Invalid control %d\n", ctrl->id); ret = -EINVAL; } @@ -803,14 +803,14 @@ static int imx412_start_streaming(struct imx412 *imx412) ret = imx412_write_regs(imx412, reg_list->regs, reg_list->num_of_regs); if (ret) { - dev_err(imx412->dev, "fail to write initial registers"); + dev_err(imx412->dev, "fail to write initial registers\n"); return ret; } /* Setup handler will write actual exposure and gain */ ret = __v4l2_ctrl_handler_setup(imx412->sd.ctrl_handler); if (ret) { - dev_err(imx412->dev, "fail to setup handler"); + dev_err(imx412->dev, "fail to setup handler\n"); return ret; } @@ -821,7 +821,7 @@ static int imx412_start_streaming(struct imx412 *imx412) ret = imx412_write_reg(imx412, IMX412_REG_MODE_SELECT, 1, IMX412_MODE_STREAMING); if (ret) { - dev_err(imx412->dev, "fail to start streaming"); + dev_err(imx412->dev, "fail to start streaming\n"); return ret; } @@ -895,7 +895,7 @@ static int imx412_detect(struct imx412 *imx412) return ret; if (val != IMX412_ID) { - dev_err(imx412->dev, "chip id mismatch: %x!=%x", + dev_err(imx412->dev, "chip id mismatch: %x!=%x\n", IMX412_ID, val); return -ENXIO; } @@ -927,7 +927,7 @@ static int imx412_parse_hw_config(struct imx412 *imx412) imx412->reset_gpio = devm_gpiod_get_optional(imx412->dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(imx412->reset_gpio)) { - dev_err(imx412->dev, "failed to get reset gpio %ld", + dev_err(imx412->dev, "failed to get reset gpio %ld\n", PTR_ERR(imx412->reset_gpio)); return PTR_ERR(imx412->reset_gpio); } @@ -935,13 +935,13 @@ static int imx412_parse_hw_config(struct imx412 *imx412) /* Get sensor input clock */ imx412->inclk = devm_clk_get(imx412->dev, NULL); if (IS_ERR(imx412->inclk)) { - dev_err(imx412->dev, "could not get inclk"); + dev_err(imx412->dev, "could not get inclk\n"); return PTR_ERR(imx412->inclk); } rate = clk_get_rate(imx412->inclk); if (rate != IMX412_INCLK_RATE) { - dev_err(imx412->dev, "inclk frequency mismatch"); + dev_err(imx412->dev, "inclk frequency mismatch\n"); return -EINVAL; } @@ -966,14 +966,14 @@ static int imx412_parse_hw_config(struct imx412 *imx412) if (bus_cfg.bus.mipi_csi2.num_data_lanes != IMX412_NUM_DATA_LANES) { dev_err(imx412->dev, - "number of CSI2 data lanes %d is not supported", + "number of CSI2 data lanes %d is not supported\n", bus_cfg.bus.mipi_csi2.num_data_lanes); ret = -EINVAL; goto done_endpoint_free; } if (!bus_cfg.nr_of_link_frequencies) { - dev_err(imx412->dev, "no link frequencies defined"); + dev_err(imx412->dev, "no link frequencies defined\n"); ret = -EINVAL; goto done_endpoint_free; } @@ -1034,7 +1034,7 @@ static int imx412_power_on(struct device *dev) ret = clk_prepare_enable(imx412->inclk); if (ret) { - dev_err(imx412->dev, "fail to enable inclk"); + dev_err(imx412->dev, "fail to enable inclk\n"); goto error_reset; } @@ -1145,7 +1145,7 @@ static int imx412_init_controls(struct imx412 *imx412) imx412->hblank_ctrl->flags |= V4L2_CTRL_FLAG_READ_ONLY; if (ctrl_hdlr->error) { - dev_err(imx412->dev, "control init failed: %d", + dev_err(imx412->dev, "control init failed: %d\n", ctrl_hdlr->error); v4l2_ctrl_handler_free(ctrl_hdlr); return ctrl_hdlr->error; @@ -1183,7 +1183,7 @@ static int imx412_probe(struct i2c_client *client) ret = imx412_parse_hw_config(imx412); if (ret) { - dev_err(imx412->dev, "HW configuration is not supported"); + dev_err(imx412->dev, "HW configuration is not supported\n"); return ret; } @@ -1191,14 +1191,14 @@ static int imx412_probe(struct i2c_client *client) ret = imx412_power_on(imx412->dev); if (ret) { - dev_err(imx412->dev, "failed to power-on the sensor"); + dev_err(imx412->dev, "failed to power-on the sensor\n"); goto error_mutex_destroy; } /* Check module identity */ ret = imx412_detect(imx412); if (ret) { - dev_err(imx412->dev, "failed to find sensor: %d", ret); + dev_err(imx412->dev, "failed to find sensor: %d\n", ret); goto error_power_off; } @@ -1208,7 +1208,7 @@ static int imx412_probe(struct i2c_client *client) ret = imx412_init_controls(imx412); if (ret) { - dev_err(imx412->dev, "failed to init controls: %d", ret); + dev_err(imx412->dev, "failed to init controls: %d\n", ret); goto error_power_off; } @@ -1222,14 +1222,14 @@ static int imx412_probe(struct i2c_client *client) imx412->pad.flags = MEDIA_PAD_FL_SOURCE; ret = media_entity_pads_init(&imx412->sd.entity, 1, &imx412->pad); if (ret) { - dev_err(imx412->dev, "failed to init entity pads: %d", ret); + dev_err(imx412->dev, "failed to init entity pads: %d\n", ret); goto error_handler_free; } ret = v4l2_async_register_subdev_sensor(&imx412->sd); if (ret < 0) { dev_err(imx412->dev, - "failed to register async subdev: %d", ret); + "failed to register async subdev: %d\n", ret); goto error_media_entity; } diff --git a/drivers/media/i2c/ov2740.c b/drivers/media/i2c/ov2740.c index c484b753a718..9a5d118b87b0 100644 --- a/drivers/media/i2c/ov2740.c +++ b/drivers/media/i2c/ov2740.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -76,6 +77,14 @@ /* OTP registers from sensor */ #define OV2740_REG_OTP_CUSTOMER 0x7010 +static const char * const ov2740_supply_name[] = { + "AVDD", + "DOVDD", + "DVDD", +}; + +#define OV2740_NUM_SUPPLIES ARRAY_SIZE(ov2740_supply_name) + struct nvm_data { struct nvmem_device *nvmem; struct regmap *regmap; @@ -523,9 +532,11 @@ struct ov2740 { struct v4l2_ctrl *hblank; struct v4l2_ctrl *exposure; - /* GPIOs, clocks */ + /* GPIOs, clocks, regulators */ struct gpio_desc *reset_gpio; + struct gpio_desc *powerdown_gpio; struct clk *clk; + struct regulator_bulk_data supplies[OV2740_NUM_SUPPLIES]; /* Current mode */ const struct ov2740_mode *cur_mode; @@ -644,6 +655,8 @@ static int ov2740_identify_module(struct ov2740 *ov2740) return -ENXIO; } + dev_dbg(&client->dev, "chip id: %x\n", val); + ov2740->identified = true; return 0; @@ -753,15 +766,17 @@ static const struct v4l2_ctrl_ops ov2740_ctrl_ops = { static int ov2740_init_controls(struct ov2740 *ov2740) { + struct i2c_client *client = v4l2_get_subdevdata(&ov2740->sd); struct v4l2_ctrl_handler *ctrl_hdlr; const struct ov2740_mode *cur_mode; s64 exposure_max, h_blank, pixel_rate; u32 vblank_min, vblank_max, vblank_default; + struct v4l2_fwnode_device_properties props; int size; int ret; ctrl_hdlr = &ov2740->ctrl_handler; - ret = v4l2_ctrl_handler_init(ctrl_hdlr, 8); + ret = v4l2_ctrl_handler_init(ctrl_hdlr, 10); if (ret) return ret; @@ -811,6 +826,13 @@ static int ov2740_init_controls(struct ov2740 *ov2740) V4L2_CID_TEST_PATTERN, ARRAY_SIZE(ov2740_test_pattern_menu) - 1, 0, 0, ov2740_test_pattern_menu); + + ret = v4l2_fwnode_device_parse(&client->dev, &props); + if (ret) + return ret; + + v4l2_ctrl_new_fwnode_properties(ctrl_hdlr, &ov2740_ctrl_ops, &props); + if (ctrl_hdlr->error) { v4l2_ctrl_handler_free(ctrl_hdlr); return ctrl_hdlr->error; @@ -1295,7 +1317,9 @@ static int ov2740_suspend(struct device *dev) struct ov2740 *ov2740 = to_ov2740(sd); gpiod_set_value_cansleep(ov2740->reset_gpio, 1); + gpiod_set_value_cansleep(ov2740->powerdown_gpio, 1); clk_disable_unprepare(ov2740->clk); + regulator_bulk_disable(OV2740_NUM_SUPPLIES, ov2740->supplies); return 0; } @@ -1305,10 +1329,17 @@ static int ov2740_resume(struct device *dev) struct ov2740 *ov2740 = to_ov2740(sd); int ret; - ret = clk_prepare_enable(ov2740->clk); + ret = regulator_bulk_enable(OV2740_NUM_SUPPLIES, ov2740->supplies); if (ret) return ret; + ret = clk_prepare_enable(ov2740->clk); + if (ret) { + regulator_bulk_disable(OV2740_NUM_SUPPLIES, ov2740->supplies); + return ret; + } + + gpiod_set_value_cansleep(ov2740->powerdown_gpio, 0); gpiod_set_value_cansleep(ov2740->reset_gpio, 0); msleep(20); @@ -1320,7 +1351,7 @@ static int ov2740_probe(struct i2c_client *client) struct device *dev = &client->dev; struct ov2740 *ov2740; bool full_power; - int ret; + int i, ret; ov2740 = devm_kzalloc(&client->dev, sizeof(*ov2740), GFP_KERNEL); if (!ov2740) @@ -1337,9 +1368,17 @@ static int ov2740_probe(struct i2c_client *client) if (IS_ERR(ov2740->reset_gpio)) { return dev_err_probe(dev, PTR_ERR(ov2740->reset_gpio), "failed to get reset GPIO\n"); - } else if (ov2740->reset_gpio) { + } + + ov2740->powerdown_gpio = devm_gpiod_get_optional(dev, "powerdown", GPIOD_OUT_HIGH); + if (IS_ERR(ov2740->powerdown_gpio)) { + return dev_err_probe(dev, PTR_ERR(ov2740->powerdown_gpio), + "failed to get powerdown GPIO\n"); + } + + if (ov2740->reset_gpio || ov2740->powerdown_gpio) { /* - * Ensure reset is asserted for at least 20 ms before + * Ensure reset/powerdown is asserted for at least 20 ms before * ov2740_resume() deasserts it. */ msleep(20); @@ -1350,6 +1389,13 @@ static int ov2740_probe(struct i2c_client *client) return dev_err_probe(dev, PTR_ERR(ov2740->clk), "failed to get clock\n"); + for (i = 0; i < OV2740_NUM_SUPPLIES; i++) + ov2740->supplies[i].supply = ov2740_supply_name[i]; + + ret = devm_regulator_bulk_get(dev, OV2740_NUM_SUPPLIES, ov2740->supplies); + if (ret) + return dev_err_probe(dev, ret, "failed to get regulators\n"); + full_power = acpi_dev_state_d0(&client->dev); if (full_power) { /* ACPI does not always clear the reset GPIO / enable the clock */ diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c index da5cb5f45a4f..0dae0438aa80 100644 --- a/drivers/media/i2c/ov5640.c +++ b/drivers/media/i2c/ov5640.c @@ -1982,6 +1982,7 @@ static int ov5640_get_light_freq(struct ov5640_dev *sensor) light_freq = 50; } else { /* 60Hz */ + light_freq = 60; } } diff --git a/drivers/media/i2c/ov9282.c b/drivers/media/i2c/ov9282.c index 9f52af6f047f..87e5d7ce5a47 100644 --- a/drivers/media/i2c/ov9282.c +++ b/drivers/media/i2c/ov9282.c @@ -40,7 +40,7 @@ /* Exposure control */ #define OV9282_REG_EXPOSURE 0x3500 #define OV9282_EXPOSURE_MIN 1 -#define OV9282_EXPOSURE_OFFSET 12 +#define OV9282_EXPOSURE_OFFSET 25 #define OV9282_EXPOSURE_STEP 1 #define OV9282_EXPOSURE_DEFAULT 0x0282 diff --git a/drivers/media/pci/b2c2/flexcop-dma.c b/drivers/media/pci/b2c2/flexcop-dma.c index ff8058568240..2ef97be4dc54 100644 --- a/drivers/media/pci/b2c2/flexcop-dma.c +++ b/drivers/media/pci/b2c2/flexcop-dma.c @@ -123,23 +123,6 @@ static int flexcop_dma_remap(struct flexcop_device *fc, return 0; } -int flexcop_dma_control_size_irq(struct flexcop_device *fc, - flexcop_dma_index_t no, - int onoff) -{ - flexcop_ibi_value v = fc->read_ibi_reg(fc, ctrl_208); - - if (no & FC_DMA_1) - v.ctrl_208.DMA1_IRQ_Enable_sig = onoff; - - if (no & FC_DMA_2) - v.ctrl_208.DMA2_IRQ_Enable_sig = onoff; - - fc->write_ibi_reg(fc, ctrl_208, v); - return 0; -} -EXPORT_SYMBOL(flexcop_dma_control_size_irq); - int flexcop_dma_control_timer_irq(struct flexcop_device *fc, flexcop_dma_index_t no, int onoff) diff --git a/drivers/media/pci/cx18/cx18-gpio.c b/drivers/media/pci/cx18/cx18-gpio.c index c85eb8d25837..485a6cbeb15a 100644 --- a/drivers/media/pci/cx18/cx18-gpio.c +++ b/drivers/media/pci/cx18/cx18-gpio.c @@ -305,21 +305,6 @@ int cx18_gpio_register(struct cx18 *cx, u32 hw) return v4l2_device_register_subdev(&cx->v4l2_dev, sd); } -void cx18_reset_ir_gpio(void *data) -{ - struct cx18 *cx = to_cx18(data); - - if (cx->card->gpio_i2c_slave_reset.ir_reset_mask == 0) - return; - - CX18_DEBUG_INFO("Resetting IR microcontroller\n"); - - v4l2_subdev_call(&cx->sd_resetctrl, - core, reset, CX18_GPIO_RESET_Z8F0811); -} -EXPORT_SYMBOL(cx18_reset_ir_gpio); -/* This symbol is exported for use by lirc_pvr150 for the IR-blaster */ - /* Xceive tuner reset function */ int cx18_reset_tuner_gpio(void *dev, int component, int cmd, int value) { diff --git a/drivers/media/pci/cx18/cx18-gpio.h b/drivers/media/pci/cx18/cx18-gpio.h index 0fa4c7ad2286..8d5797dea7f5 100644 --- a/drivers/media/pci/cx18/cx18-gpio.h +++ b/drivers/media/pci/cx18/cx18-gpio.h @@ -17,5 +17,4 @@ enum cx18_gpio_reset_type { CX18_GPIO_RESET_XC2028 = 2, }; -void cx18_reset_ir_gpio(void *data); int cx18_reset_tuner_gpio(void *dev, int component, int cmd, int value); diff --git a/drivers/media/pci/intel/ipu-bridge.c b/drivers/media/pci/intel/ipu-bridge.c index 1bf249f446a9..1cb745855600 100644 --- a/drivers/media/pci/intel/ipu-bridge.c +++ b/drivers/media/pci/intel/ipu-bridge.c @@ -2,6 +2,7 @@ /* Author: Dan Scally */ #include +#include #include #include #include @@ -107,7 +108,6 @@ static const char * const ipu_vcm_types[] = { "lc898212axb", }; -#if IS_ENABLED(CONFIG_ACPI) /* * Used to figure out IVSC acpi device by ipu_bridge_get_ivsc_acpi_dev() * instead of device and driver match to probe IVSC device. @@ -127,11 +127,11 @@ static struct acpi_device *ipu_bridge_get_ivsc_acpi_dev(struct acpi_device *adev const struct acpi_device_id *acpi_id = &ivsc_acpi_ids[i]; struct acpi_device *consumer, *ivsc_adev; - acpi_handle handle = acpi_device_handle(adev); + acpi_handle handle = acpi_device_handle(ACPI_PTR(adev)); for_each_acpi_dev_match(ivsc_adev, acpi_id->id, NULL, -1) /* camera sensor depends on IVSC in DSDT if exist */ for_each_acpi_consumer_dev(ivsc_adev, consumer) - if (consumer->handle == handle) { + if (ACPI_PTR(consumer->handle) == handle) { acpi_dev_put(consumer); return ivsc_adev; } @@ -139,12 +139,6 @@ static struct acpi_device *ipu_bridge_get_ivsc_acpi_dev(struct acpi_device *adev return NULL; } -#else -static struct acpi_device *ipu_bridge_get_ivsc_acpi_dev(struct acpi_device *adev) -{ - return NULL; -} -#endif static int ipu_bridge_match_ivsc_dev(struct device *dev, const void *adev) { @@ -259,12 +253,8 @@ static enum v4l2_fwnode_orientation ipu_bridge_parse_orientation(struct acpi_dev { enum v4l2_fwnode_orientation orientation; struct acpi_pld_info *pld = NULL; - acpi_status status = AE_ERROR; -#if IS_ENABLED(CONFIG_ACPI) - status = acpi_get_physical_device_location(adev->handle, &pld); -#endif - if (ACPI_FAILURE(status)) { + if (!acpi_get_physical_device_location(ACPI_PTR(adev->handle), &pld)) { dev_warn(ADEV_DEV(adev), "_PLD call failed, using default orientation\n"); return V4L2_FWNODE_ORIENTATION_EXTERNAL; } @@ -498,9 +488,7 @@ static void ipu_bridge_create_connection_swnodes(struct ipu_bridge *bridge, if (sensor->csi_dev) { const char *device_hid = ""; -#if IS_ENABLED(CONFIG_ACPI) device_hid = acpi_device_hid(sensor->ivsc_adev); -#endif snprintf(sensor->ivsc_name, sizeof(sensor->ivsc_name), "%s-%u", device_hid, sensor->link); @@ -671,11 +659,7 @@ static int ipu_bridge_connect_sensor(const struct ipu_sensor_config *cfg, struct acpi_device *adev = NULL; int ret; -#if IS_ENABLED(CONFIG_ACPI) for_each_acpi_dev_match(adev, cfg->hid, NULL, -1) { -#else - while (true) { -#endif if (!ACPI_PTR(adev->status.enabled)) continue; @@ -768,15 +752,10 @@ static int ipu_bridge_ivsc_is_ready(void) unsigned int i; for (i = 0; i < ARRAY_SIZE(ipu_supported_sensors); i++) { -#if IS_ENABLED(CONFIG_ACPI) const struct ipu_sensor_config *cfg = &ipu_supported_sensors[i]; for_each_acpi_dev_match(sensor_adev, cfg->hid, NULL, -1) { -#else - while (true) { - sensor_adev = NULL; -#endif if (!ACPI_PTR(sensor_adev->status.enabled)) continue; diff --git a/drivers/media/pci/intel/ipu6/ipu6-buttress.c b/drivers/media/pci/intel/ipu6/ipu6-buttress.c index e898902e83f3..d8db5aa5d528 100644 --- a/drivers/media/pci/intel/ipu6/ipu6-buttress.c +++ b/drivers/media/pci/intel/ipu6/ipu6-buttress.c @@ -847,10 +847,10 @@ int ipu6_buttress_init(struct ipu6_device *isp) INIT_LIST_HEAD(&b->constraints); isp->secure_mode = ipu6_buttress_get_secure_mode(isp); - dev_info(&isp->pdev->dev, "IPU6 in %s mode touch 0x%x mask 0x%x\n", - isp->secure_mode ? "secure" : "non-secure", - readl(isp->base + BUTTRESS_REG_SECURITY_TOUCH), - readl(isp->base + BUTTRESS_REG_CAMERA_MASK)); + dev_dbg(&isp->pdev->dev, "IPU6 in %s mode touch 0x%x mask 0x%x\n", + isp->secure_mode ? "secure" : "non-secure", + readl(isp->base + BUTTRESS_REG_SECURITY_TOUCH), + readl(isp->base + BUTTRESS_REG_CAMERA_MASK)); b->wdt_cached_value = readl(isp->base + BUTTRESS_REG_WDT); writel(BUTTRESS_IRQS, isp->base + BUTTRESS_REG_ISR_CLEAR); diff --git a/drivers/media/pci/intel/ipu6/ipu6-cpd.c b/drivers/media/pci/intel/ipu6/ipu6-cpd.c index 8b8142bcb2d5..b7013f6524ec 100644 --- a/drivers/media/pci/intel/ipu6/ipu6-cpd.c +++ b/drivers/media/pci/intel/ipu6/ipu6-cpd.c @@ -275,7 +275,7 @@ static int ipu6_cpd_validate_moduledata(struct ipu6_device *isp, return -EINVAL; } - dev_info(&isp->pdev->dev, "FW version: %x\n", mod_hdr->fw_pkg_date); + dev_dbg(&isp->pdev->dev, "FW version: %x\n", mod_hdr->fw_pkg_date); ret = ipu6_cpd_validate_cpd(isp, moduledata + mod_hdr->hdr_len, moduledata_size - mod_hdr->hdr_len, moduledata_size); diff --git a/drivers/media/pci/intel/ipu6/ipu6-isys.c b/drivers/media/pci/intel/ipu6/ipu6-isys.c index 77f9c7319868..8df1d83a74b5 100644 --- a/drivers/media/pci/intel/ipu6/ipu6-isys.c +++ b/drivers/media/pci/intel/ipu6/ipu6-isys.c @@ -1133,6 +1133,7 @@ static int isys_probe(struct auxiliary_device *auxdev, free_fw_msg_bufs: free_fw_msg_bufs(isys); out_remove_pkg_dir_shared_buffer: + cpu_latency_qos_remove_request(&isys->pm_qos); if (!isp->secure_mode) ipu6_cpd_free_pkg_dir(adev); remove_shared_buffer: diff --git a/drivers/media/pci/mgb4/mgb4_core.c b/drivers/media/pci/mgb4/mgb4_core.c index bc63dc81bcae..f90ffc4dad52 100644 --- a/drivers/media/pci/mgb4/mgb4_core.c +++ b/drivers/media/pci/mgb4/mgb4_core.c @@ -40,7 +40,9 @@ #include "mgb4_trigger.h" #include "mgb4_core.h" -#define MGB4_USER_IRQS 16 +#define MGB4_USER_IRQS 16 +#define MGB4_MGB4_BAR_ID 0 +#define MGB4_XDMA_BAR_ID 1 #define DIGITEQ_VID 0x1ed8 #define T100_DID 0x0101 @@ -123,7 +125,7 @@ static const struct hwmon_chip_info temp_chip_info = { }; #endif -static int match_i2c_adap(struct device *dev, void *data) +static int match_i2c_adap(struct device *dev, const void *data) { return i2c_verify_adapter(dev) ? 1 : 0; } @@ -139,7 +141,7 @@ static struct i2c_adapter *get_i2c_adap(struct platform_device *pdev) return dev ? to_i2c_adapter(dev) : NULL; } -static int match_spi_adap(struct device *dev, void *data) +static int match_spi_adap(struct device *dev, const void *data) { return to_spi_device(dev) ? 1 : 0; } diff --git a/drivers/media/pci/mgb4/mgb4_core.h b/drivers/media/pci/mgb4/mgb4_core.h index 9aec62514c0b..e86742d7b6c4 100644 --- a/drivers/media/pci/mgb4/mgb4_core.h +++ b/drivers/media/pci/mgb4/mgb4_core.h @@ -18,9 +18,6 @@ #define MGB4_VIN_DEVICES 2 #define MGB4_VOUT_DEVICES 2 -#define MGB4_MGB4_BAR_ID 0 -#define MGB4_XDMA_BAR_ID 1 - #define MGB4_IS_GMSL(mgbdev) \ ((mgbdev)->module_version >> 4 == 2) #define MGB4_IS_FPDL3(mgbdev) \ diff --git a/drivers/media/pci/mgb4/mgb4_sysfs_in.c b/drivers/media/pci/mgb4/mgb4_sysfs_in.c index 0ba66a2cf145..9626fa59e3d3 100644 --- a/drivers/media/pci/mgb4/mgb4_sysfs_in.c +++ b/drivers/media/pci/mgb4/mgb4_sysfs_in.c @@ -333,7 +333,7 @@ static ssize_t hsync_width_show(struct device *dev, struct video_device *vdev = to_video_device(dev); struct mgb4_vin_dev *vindev = video_get_drvdata(vdev); u32 sig = mgb4_read_reg(&vindev->mgbdev->video, - vindev->config->regs.signal); + vindev->config->regs.hsync); return sprintf(buf, "%u\n", (sig & 0x00FF0000) >> 16); } @@ -344,7 +344,7 @@ static ssize_t vsync_width_show(struct device *dev, struct video_device *vdev = to_video_device(dev); struct mgb4_vin_dev *vindev = video_get_drvdata(vdev); u32 sig = mgb4_read_reg(&vindev->mgbdev->video, - vindev->config->regs.signal2); + vindev->config->regs.vsync); return sprintf(buf, "%u\n", (sig & 0x00FF0000) >> 16); } @@ -355,7 +355,7 @@ static ssize_t hback_porch_show(struct device *dev, struct video_device *vdev = to_video_device(dev); struct mgb4_vin_dev *vindev = video_get_drvdata(vdev); u32 sig = mgb4_read_reg(&vindev->mgbdev->video, - vindev->config->regs.signal); + vindev->config->regs.hsync); return sprintf(buf, "%u\n", (sig & 0x0000FF00) >> 8); } @@ -366,7 +366,7 @@ static ssize_t hfront_porch_show(struct device *dev, struct video_device *vdev = to_video_device(dev); struct mgb4_vin_dev *vindev = video_get_drvdata(vdev); u32 sig = mgb4_read_reg(&vindev->mgbdev->video, - vindev->config->regs.signal); + vindev->config->regs.hsync); return sprintf(buf, "%u\n", (sig & 0x000000FF)); } @@ -377,7 +377,7 @@ static ssize_t vback_porch_show(struct device *dev, struct video_device *vdev = to_video_device(dev); struct mgb4_vin_dev *vindev = video_get_drvdata(vdev); u32 sig = mgb4_read_reg(&vindev->mgbdev->video, - vindev->config->regs.signal2); + vindev->config->regs.vsync); return sprintf(buf, "%u\n", (sig & 0x0000FF00) >> 8); } @@ -388,7 +388,7 @@ static ssize_t vfront_porch_show(struct device *dev, struct video_device *vdev = to_video_device(dev); struct mgb4_vin_dev *vindev = video_get_drvdata(vdev); u32 sig = mgb4_read_reg(&vindev->mgbdev->video, - vindev->config->regs.signal2); + vindev->config->regs.vsync); return sprintf(buf, "%u\n", (sig & 0x000000FF)); } diff --git a/drivers/media/pci/mgb4/mgb4_vin.c b/drivers/media/pci/mgb4/mgb4_vin.c index 3f171c624b40..434eaf0440e2 100644 --- a/drivers/media/pci/mgb4/mgb4_vin.c +++ b/drivers/media/pci/mgb4/mgb4_vin.c @@ -143,8 +143,8 @@ static int get_timings(struct mgb4_vin_dev *vindev, u32 status = mgb4_read_reg(video, regs->status); u32 pclk = mgb4_read_reg(video, regs->pclk); - u32 signal = mgb4_read_reg(video, regs->signal); - u32 signal2 = mgb4_read_reg(video, regs->signal2); + u32 hsync = mgb4_read_reg(video, regs->hsync); + u32 vsync = mgb4_read_reg(video, regs->vsync); u32 resolution = mgb4_read_reg(video, regs->resolution); if (!(status & (1U << 2))) @@ -161,12 +161,12 @@ static int get_timings(struct mgb4_vin_dev *vindev, if (status & (1U << 13)) timings->bt.polarities |= V4L2_DV_VSYNC_POS_POL; timings->bt.pixelclock = pclk * 1000; - timings->bt.hsync = (signal & 0x00FF0000) >> 16; - timings->bt.vsync = (signal2 & 0x00FF0000) >> 16; - timings->bt.hbackporch = (signal & 0x0000FF00) >> 8; - timings->bt.hfrontporch = signal & 0x000000FF; - timings->bt.vbackporch = (signal2 & 0x0000FF00) >> 8; - timings->bt.vfrontporch = signal2 & 0x000000FF; + timings->bt.hsync = (hsync & 0x00FF0000) >> 16; + timings->bt.vsync = (vsync & 0x00FF0000) >> 16; + timings->bt.hbackporch = (hsync & 0x0000FF00) >> 8; + timings->bt.hfrontporch = hsync & 0x000000FF; + timings->bt.vbackporch = (vsync & 0x0000FF00) >> 8; + timings->bt.vfrontporch = vsync & 0x000000FF; return 0; } @@ -864,9 +864,9 @@ static void create_debugfs(struct mgb4_vin_dev *vindev) vindev->regs[5].name = "PCLK_FREQUENCY"; vindev->regs[5].offset = vindev->config->regs.pclk; vindev->regs[6].name = "VIDEO_PARAMS_1"; - vindev->regs[6].offset = vindev->config->regs.signal; + vindev->regs[6].offset = vindev->config->regs.hsync; vindev->regs[7].name = "VIDEO_PARAMS_2"; - vindev->regs[7].offset = vindev->config->regs.signal2; + vindev->regs[7].offset = vindev->config->regs.vsync; vindev->regs[8].name = "PADDING_PIXELS"; vindev->regs[8].offset = vindev->config->regs.padding; if (has_timeperframe(video)) { diff --git a/drivers/media/pci/mgb4/mgb4_vin.h b/drivers/media/pci/mgb4/mgb4_vin.h index 8fd10c0a5554..2a2c829914ce 100644 --- a/drivers/media/pci/mgb4/mgb4_vin.h +++ b/drivers/media/pci/mgb4/mgb4_vin.h @@ -22,8 +22,8 @@ struct mgb4_vin_regs { u32 frame_period; u32 sync; u32 pclk; - u32 signal; - u32 signal2; + u32 hsync; + u32 vsync; u32 padding; u32 timer; }; diff --git a/drivers/media/pci/mgb4/mgb4_vout.c b/drivers/media/pci/mgb4/mgb4_vout.c index 6b2791e29de1..14c5725bd4d8 100644 --- a/drivers/media/pci/mgb4/mgb4_vout.c +++ b/drivers/media/pci/mgb4/mgb4_vout.c @@ -24,10 +24,6 @@ #include "mgb4_cmt.h" #include "mgb4_vout.h" -#define DEFAULT_WIDTH 1280 -#define DEFAULT_HEIGHT 640 -#define DEFAULT_PERIOD (MGB4_HW_FREQ / 60) - ATTRIBUTE_GROUPS(mgb4_fpdl3_out); ATTRIBUTE_GROUPS(mgb4_gmsl_out); @@ -180,7 +176,10 @@ static void stop_streaming(struct vb2_queue *vq) xdma_disable_user_irq(mgbdev->xdev, irq); cancel_work_sync(&voutdev->dma_work); + mgb4_mask_reg(&mgbdev->video, voutdev->config->regs.config, 0x2, 0x0); + mgb4_write_reg(&mgbdev->video, voutdev->config->regs.padding, 0); + return_all_buffers(voutdev, VB2_BUF_STATE_ERROR); } @@ -196,6 +195,7 @@ static int start_streaming(struct vb2_queue *vq, unsigned int count) int rv; u32 addr; + mgb4_write_reg(video, config->regs.padding, voutdev->padding); mgb4_mask_reg(video, config->regs.config, 0x2, 0x2); addr = mgb4_read_reg(video, config->regs.address); @@ -359,7 +359,6 @@ static int vidioc_s_fmt(struct file *file, void *priv, struct v4l2_format *f) voutdev->padding = (f->fmt.pix.bytesperline - (f->fmt.pix.width * pixelsize)) / pixelsize; - mgb4_write_reg(video, voutdev->config->regs.padding, voutdev->padding); return 0; } @@ -661,11 +660,10 @@ static void fpga_init(struct mgb4_vout_dev *voutdev) const struct mgb4_vout_regs *regs = &voutdev->config->regs; mgb4_write_reg(video, regs->config, 0x00000011); - mgb4_write_reg(video, regs->resolution, - (DEFAULT_WIDTH << 16) | DEFAULT_HEIGHT); + mgb4_write_reg(video, regs->resolution, (1280 << 16) | 640); mgb4_write_reg(video, regs->hsync, 0x00283232); mgb4_write_reg(video, regs->vsync, 0x40141F1E); - mgb4_write_reg(video, regs->frame_limit, DEFAULT_PERIOD); + mgb4_write_reg(video, regs->frame_limit, MGB4_HW_FREQ / 60); mgb4_write_reg(video, regs->padding, 0x00000000); voutdev->freq = mgb4_cmt_set_vout_freq(voutdev, 61150 >> 1) << 1; diff --git a/drivers/media/pci/saa7164/saa7164-vbi.c b/drivers/media/pci/saa7164/saa7164-vbi.c index a6738baab688..ac958a5fca78 100644 --- a/drivers/media/pci/saa7164/saa7164-vbi.c +++ b/drivers/media/pci/saa7164/saa7164-vbi.c @@ -77,9 +77,7 @@ static int saa7164_vbi_buffers_alloc(struct saa7164_port *port) /* TODO: NTSC SPECIFIC */ /* Init and establish defaults */ params->samplesperline = 1440; - params->numberoflines = 12; params->numberoflines = 18; - params->pitch = 1600; params->pitch = 1440; params->numpagetables = 2 + ((params->numberoflines * params->pitch) / PAGE_SIZE); diff --git a/drivers/media/pci/solo6x10/solo6x10-core.c b/drivers/media/pci/solo6x10/solo6x10-core.c index 1a9e2bccc413..6ec1480a6d18 100644 --- a/drivers/media/pci/solo6x10/solo6x10-core.c +++ b/drivers/media/pci/solo6x10/solo6x10-core.c @@ -362,7 +362,7 @@ static ssize_t sdram_offsets_show(struct device *dev, } static ssize_t sdram_show(struct file *file, struct kobject *kobj, - struct bin_attribute *a, char *buf, + const struct bin_attribute *a, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -432,7 +432,7 @@ static int solo_sysfs_init(struct solo_dev *solo_dev) sysfs_attr_init(&sdram_attr->attr); sdram_attr->attr.name = "sdram"; sdram_attr->attr.mode = 0440; - sdram_attr->read = sdram_show; + sdram_attr->read_new = sdram_show; sdram_attr->size = solo_dev->sdram_size; if (device_create_bin_file(dev, sdram_attr)) { diff --git a/drivers/media/platform/broadcom/bcm2835-unicam.c b/drivers/media/platform/broadcom/bcm2835-unicam.c index 3aed0e493c81..f10064107d54 100644 --- a/drivers/media/platform/broadcom/bcm2835-unicam.c +++ b/drivers/media/platform/broadcom/bcm2835-unicam.c @@ -199,6 +199,7 @@ struct unicam_device { /* subdevice async notifier */ struct v4l2_async_notifier notifier; unsigned int sequence; + bool frame_started; /* Sensor node */ struct { @@ -546,7 +547,8 @@ unicam_find_format_by_fourcc(u32 fourcc, u32 pad) } for (i = 0; i < num_formats; ++i) { - if (formats[i].fourcc == fourcc) + if (formats[i].fourcc == fourcc || + formats[i].unpacked_fourcc == fourcc) return &formats[i]; } @@ -638,7 +640,14 @@ static inline void unicam_reg_write_field(struct unicam_device *unicam, u32 offs static void unicam_wr_dma_addr(struct unicam_node *node, struct unicam_buffer *buf) { - dma_addr_t endaddr = buf->dma_addr + buf->size; + /* + * Due to a HW bug causing buffer overruns in circular buffer mode under + * certain (not yet fully known) conditions, the dummy buffer allocation + * is set to a a single page size, but the hardware gets programmed with + * a buffer size of 0. + */ + dma_addr_t endaddr = buf->dma_addr + + (buf != &node->dummy_buf ? buf->size : 0); if (node->id == UNICAM_IMAGE_NODE) { unicam_reg_write(node->dev, UNICAM_IBSA0, buf->dma_addr); @@ -742,6 +751,8 @@ static irqreturn_t unicam_isr(int irq, void *dev) * buffer forever. */ if (fe) { + bool inc_seq = unicam->frame_started; + /* * Ensure we have swapped buffers already as we can't * stop the peripheral. If no buffer is available, use a @@ -761,11 +772,24 @@ static irqreturn_t unicam_isr(int irq, void *dev) * + FS + LS). In this case, we cannot signal the buffer * as complete, as the HW will reuse that buffer. */ - if (node->cur_frm && node->cur_frm != node->next_frm) + if (node->cur_frm && node->cur_frm != node->next_frm) { unicam_process_buffer_complete(node, sequence); + inc_seq = true; + } node->cur_frm = node->next_frm; } - unicam->sequence++; + + /* + * Increment the sequence number conditionally on either a FS + * having already occurred, or in the FE + FS condition as + * caught in the FE handler above. This ensures the sequence + * number corresponds to the frames generated by the sensor, not + * the frames dequeued to userland. + */ + if (inc_seq) { + unicam->sequence++; + unicam->frame_started = false; + } } if (ista & UNICAM_FSI) { @@ -795,6 +819,7 @@ static irqreturn_t unicam_isr(int irq, void *dev) } unicam_queue_event_sof(unicam); + unicam->frame_started = true; } /* @@ -816,11 +841,6 @@ static irqreturn_t unicam_isr(int irq, void *dev) } } - if (unicam_reg_read(unicam, UNICAM_ICTL) & UNICAM_FCM) { - /* Switch out of trigger mode if selected */ - unicam_reg_write_field(unicam, UNICAM_ICTL, 1, UNICAM_TFC); - unicam_reg_write_field(unicam, UNICAM_ICTL, 0, UNICAM_FCM); - } return IRQ_HANDLED; } @@ -984,8 +1004,7 @@ static void unicam_start_rx(struct unicam_device *unicam, unicam_reg_write_field(unicam, UNICAM_ANA, 0, UNICAM_DDL); - /* Always start in trigger frame capture mode (UNICAM_FCM set) */ - val = UNICAM_FSIE | UNICAM_FEIE | UNICAM_FCM | UNICAM_IBOB; + val = UNICAM_FSIE | UNICAM_FEIE | UNICAM_IBOB; line_int_freq = max(fmt->height >> 2, 128); unicam_set_field(&val, line_int_freq, UNICAM_LCIE_MASK); unicam_reg_write(unicam, UNICAM_ICTL, val); @@ -1413,6 +1432,7 @@ static int unicam_sd_enable_streams(struct v4l2_subdev *sd, if (unicam->pipe.nodes & BIT(UNICAM_METADATA_NODE)) unicam_start_metadata(unicam); + unicam->frame_started = false; unicam_start_rx(unicam, state); } diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu.c b/drivers/media/platform/chips-media/wave5/wave5-vpu.c index 6b294a2d6717..d1320298a0f7 100644 --- a/drivers/media/platform/chips-media/wave5/wave5-vpu.c +++ b/drivers/media/platform/chips-media/wave5/wave5-vpu.c @@ -271,7 +271,7 @@ static int wave5_vpu_probe(struct platform_device *pdev) dev_err(&pdev->dev, "failed to get irq resource, falling back to polling\n"); hrtimer_init(&dev->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); dev->hrtimer.function = &wave5_vpu_timer_callback; - dev->worker = kthread_create_worker(0, "vpu_irq_thread"); + dev->worker = kthread_run_worker(0, "vpu_irq_thread"); if (IS_ERR(dev->worker)) { dev_err(&pdev->dev, "failed to create vpu irq worker\n"); ret = PTR_ERR(dev->worker); diff --git a/drivers/media/platform/marvell/mcam-core.c b/drivers/media/platform/marvell/mcam-core.c index 9ec01228f907..b8360d37000a 100644 --- a/drivers/media/platform/marvell/mcam-core.c +++ b/drivers/media/platform/marvell/mcam-core.c @@ -935,7 +935,12 @@ static int mclk_enable(struct clk_hw *hw) ret = pm_runtime_resume_and_get(cam->dev); if (ret < 0) return ret; - clk_enable(cam->clk[0]); + ret = clk_enable(cam->clk[0]); + if (ret) { + pm_runtime_put(cam->dev); + return ret; + } + mcam_reg_write(cam, REG_CLKCTRL, (mclk_src << 29) | mclk_div); mcam_ctlr_power_up(cam); diff --git a/drivers/media/platform/marvell/mmp-driver.c b/drivers/media/platform/marvell/mmp-driver.c index 3fd4fc1b9c48..d3da7ebb4a2b 100644 --- a/drivers/media/platform/marvell/mmp-driver.c +++ b/drivers/media/platform/marvell/mmp-driver.c @@ -231,13 +231,23 @@ static int mmpcam_probe(struct platform_device *pdev) mcam_init_clk(mcam); + /* + * Register with V4L. + */ + + ret = v4l2_device_register(mcam->dev, &mcam->v4l2_dev); + if (ret) + return ret; + /* * Create a match of the sensor against its OF node. */ ep = fwnode_graph_get_next_endpoint(of_fwnode_handle(pdev->dev.of_node), NULL); - if (!ep) - return -ENODEV; + if (!ep) { + ret = -ENODEV; + goto out_v4l2_device_unregister; + } v4l2_async_nf_init(&mcam->notifier, &mcam->v4l2_dev); @@ -246,7 +256,7 @@ static int mmpcam_probe(struct platform_device *pdev) fwnode_handle_put(ep); if (IS_ERR(asd)) { ret = PTR_ERR(asd); - goto out; + goto out_v4l2_device_unregister; } /* @@ -254,7 +264,7 @@ static int mmpcam_probe(struct platform_device *pdev) */ ret = mccic_register(mcam); if (ret) - goto out; + goto out_v4l2_device_unregister; /* * Add OF clock provider. @@ -283,6 +293,8 @@ static int mmpcam_probe(struct platform_device *pdev) return 0; out: mccic_shutdown(mcam); +out_v4l2_device_unregister: + v4l2_device_unregister(&mcam->v4l2_dev); return ret; } @@ -293,6 +305,7 @@ static void mmpcam_remove(struct platform_device *pdev) struct mcam_camera *mcam = &cam->mcam; mccic_shutdown(mcam); + v4l2_device_unregister(&mcam->v4l2_dev); pm_runtime_force_suspend(mcam->dev); } diff --git a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-cmdq.c b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-cmdq.c index ea2ea119dd2a..e5ccf673e152 100644 --- a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-cmdq.c +++ b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-cmdq.c @@ -114,19 +114,15 @@ static struct img_config *__get_config_offset(struct mdp_dev *mdp, if (pp_idx >= mdp->mdp_data->pp_used) goto err_param; - if (CFG_CHECK(MT8183, p_id)) + if (CFG_CHECK(MT8183, p_id)) { cfg_c = CFG_OFST(MT8183, param->config, pp_idx); - else if (CFG_CHECK(MT8195, p_id)) - cfg_c = CFG_OFST(MT8195, param->config, pp_idx); - else - goto err_param; - - if (CFG_CHECK(MT8183, p_id)) cfg_n = CFG_OFST(MT8183, param->config, pp_idx + 1); - else if (CFG_CHECK(MT8195, p_id)) + } else if (CFG_CHECK(MT8195, p_id)) { + cfg_c = CFG_OFST(MT8195, param->config, pp_idx); cfg_n = CFG_OFST(MT8195, param->config, pp_idx + 1); - else + } else { goto err_param; + } if ((long)cfg_n - (long)mdp->vpu.config > bound) { dev_err(dev, "config offset %ld OOB %ld\n", (long)cfg_n, bound); @@ -325,8 +321,7 @@ static int mdp_path_config_subfrm(struct mdp_cmdq_cmd *cmd, /* Enable mux settings */ for (index = 0; index < ctrl->num_sets; index++) { set = &ctrl->sets[index]; - cmdq_pkt_write_mask(&cmd->pkt, set->subsys_id, set->reg, - set->value, 0xFFFFFFFF); + cmdq_pkt_write(&cmd->pkt, set->subsys_id, set->reg, set->value); } /* Config sub-frame information */ for (index = (num_comp - 1); index >= 0; index--) { @@ -381,8 +376,7 @@ static int mdp_path_config_subfrm(struct mdp_cmdq_cmd *cmd, /* Disable mux settings */ for (index = 0; index < ctrl->num_sets; index++) { set = &ctrl->sets[index]; - cmdq_pkt_write_mask(&cmd->pkt, set->subsys_id, set->reg, - 0, 0xFFFFFFFF); + cmdq_pkt_write(&cmd->pkt, set->subsys_id, set->reg, 0); } return 0; @@ -471,43 +465,6 @@ static int mdp_path_config(struct mdp_dev *mdp, struct mdp_cmdq_cmd *cmd, return 0; } -static int mdp_cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt, - size_t size) -{ - struct device *dev; - dma_addr_t dma_addr; - - pkt->va_base = kzalloc(size, GFP_KERNEL); - if (!pkt->va_base) - return -ENOMEM; - - pkt->buf_size = size; - pkt->cl = (void *)client; - - dev = client->chan->mbox->dev; - dma_addr = dma_map_single(dev, pkt->va_base, pkt->buf_size, - DMA_TO_DEVICE); - if (dma_mapping_error(dev, dma_addr)) { - dev_err(dev, "dma map failed, size=%u\n", (u32)(u64)size); - kfree(pkt->va_base); - return -ENOMEM; - } - - pkt->pa_base = dma_addr; - - return 0; -} - -static void mdp_cmdq_pkt_destroy(struct cmdq_pkt *pkt) -{ - struct cmdq_client *client = (struct cmdq_client *)pkt->cl; - - dma_unmap_single(client->chan->mbox->dev, pkt->pa_base, pkt->buf_size, - DMA_TO_DEVICE); - kfree(pkt->va_base); - pkt->va_base = NULL; -} - static void mdp_auto_release_work(struct work_struct *work) { struct mdp_cmdq_cmd *cmd; @@ -538,7 +495,7 @@ static void mdp_auto_release_work(struct work_struct *work) wake_up(&mdp->callback_wq); } - mdp_cmdq_pkt_destroy(&cmd->pkt); + cmdq_pkt_destroy(mdp->cmdq_clt[cmd->pp_idx], &cmd->pkt); kfree(cmd->comps); cmd->comps = NULL; kfree(cmd); @@ -578,7 +535,7 @@ static void mdp_handle_cmdq_callback(struct mbox_client *cl, void *mssg) if (refcount_dec_and_test(&mdp->job_count)) wake_up(&mdp->callback_wq); - mdp_cmdq_pkt_destroy(&cmd->pkt); + cmdq_pkt_destroy(mdp->cmdq_clt[cmd->pp_idx], &cmd->pkt); kfree(cmd->comps); cmd->comps = NULL; kfree(cmd); @@ -607,20 +564,13 @@ static struct mdp_cmdq_cmd *mdp_cmdq_prepare(struct mdp_dev *mdp, goto err_uninit; } - if (CFG_CHECK(MT8183, p_id)) - num_comp = CFG_GET(MT8183, config, num_components); - else if (CFG_CHECK(MT8195, p_id)) - num_comp = CFG_GET(MT8195, config, num_components); - else - goto err_uninit; - cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) { ret = -ENOMEM; goto err_uninit; } - ret = mdp_cmdq_pkt_create(mdp->cmdq_clt[pp_idx], &cmd->pkt, SZ_16K); + ret = cmdq_pkt_create(mdp->cmdq_clt[pp_idx], &cmd->pkt, SZ_16K); if (ret) goto err_free_cmd; @@ -632,6 +582,7 @@ static struct mdp_cmdq_cmd *mdp_cmdq_prepare(struct mdp_dev *mdp, ret = -EINVAL; goto err_destroy_pkt; } + comps = kcalloc(num_comp, sizeof(*comps), GFP_KERNEL); if (!comps) { ret = -ENOMEM; @@ -676,7 +627,8 @@ static struct mdp_cmdq_cmd *mdp_cmdq_prepare(struct mdp_dev *mdp, dev_err(dev, "mdp_path_config error %d\n", pp_idx); goto err_free_path; } - cmdq_pkt_finalize(&cmd->pkt); + cmdq_pkt_eoc(&cmd->pkt); + cmdq_pkt_jump_rel(&cmd->pkt, CMDQ_INST_SIZE, mdp->cmdq_shift_pa[pp_idx]); for (i = 0; i < num_comp; i++) { s32 inner_id = MDP_COMP_NONE; @@ -699,6 +651,7 @@ static struct mdp_cmdq_cmd *mdp_cmdq_prepare(struct mdp_dev *mdp, cmd->comps = comps; cmd->num_comps = num_comp; cmd->mdp_ctx = param->mdp_ctx; + cmd->pp_idx = pp_idx; kfree(path); return cmd; @@ -710,7 +663,7 @@ err_free_path: err_free_comps: kfree(comps); err_destroy_pkt: - mdp_cmdq_pkt_destroy(&cmd->pkt); + cmdq_pkt_destroy(mdp->cmdq_clt[pp_idx], &cmd->pkt); err_free_cmd: kfree(cmd); err_uninit: diff --git a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-cmdq.h b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-cmdq.h index 53a30ad7e0b0..935ae9825728 100644 --- a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-cmdq.h +++ b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-cmdq.h @@ -35,6 +35,7 @@ struct mdp_cmdq_cmd { struct mdp_comp *comps; void *mdp_ctx; u8 num_comps; + u8 pp_idx; }; struct mdp_dev; diff --git a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c index 8f62fb167156..683c066ed975 100644 --- a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c +++ b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c @@ -72,14 +72,14 @@ static int init_rdma(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) /* Disable RSZ1 */ if (ctx->comp->inner_id == rdma0 && prz1) - MM_REG_WRITE(cmd, subsys_id, prz1->reg_base, PRZ_ENABLE, - 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, prz1->reg_base, + PRZ_ENABLE, 0x0, BIT(0)); } /* Reset RDMA */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_RESET, BIT(0), BIT(0)); - MM_REG_POLL(cmd, subsys_id, base, MDP_RDMA_MON_STA_1, BIT(8), BIT(8)); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_RESET, 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_RESET, BIT(0), BIT(0)); + MM_REG_POLL_MASK(cmd, subsys_id, base, MDP_RDMA_MON_STA_1, BIT(8), BIT(8)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_RESET, 0x0, BIT(0)); return 0; } @@ -98,26 +98,25 @@ static int config_rdma_frame(struct mdp_comp_ctx *ctx, if (mdp_cfg && mdp_cfg->rdma_support_10bit) { if (block10bit) - MM_REG_WRITE(cmd, subsys_id, base, - MDP_RDMA_RESV_DUMMY_0, 0x7, 0x7); + MM_REG_WRITE_MASK(cmd, subsys_id, base, + MDP_RDMA_RESV_DUMMY_0, 0x7, 0x7); else - MM_REG_WRITE(cmd, subsys_id, base, - MDP_RDMA_RESV_DUMMY_0, 0x0, 0x7); + MM_REG_WRITE_MASK(cmd, subsys_id, base, + MDP_RDMA_RESV_DUMMY_0, 0x0, 0x7); } /* Setup smi control */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_GMCIF_CON, - (7 << 4) + //burst type to 8 - (1 << 16), //enable pre-ultra - 0x00030071); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_GMCIF_CON, + (7 << 4) + //burst type to 8 + (1 << 16), //enable pre-ultra + 0x00030071); /* Setup source frame info */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.src_ctrl); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.src_ctrl); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_CON, reg, - 0x03C8FE0F); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_SRC_CON, reg, 0x03C8FE0F); if (mdp_cfg) if (mdp_cfg->rdma_support_10bit && en_ufo) { @@ -126,17 +125,15 @@ static int config_rdma_frame(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, rdma.ufo_dec_y); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.ufo_dec_y); - MM_REG_WRITE(cmd, subsys_id, - base, MDP_RDMA_UFO_DEC_LENGTH_BASE_Y, - reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, + MDP_RDMA_UFO_DEC_LENGTH_BASE_Y, reg); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.ufo_dec_c); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.ufo_dec_c); - MM_REG_WRITE(cmd, subsys_id, - base, MDP_RDMA_UFO_DEC_LENGTH_BASE_C, - reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, + MDP_RDMA_UFO_DEC_LENGTH_BASE_C, reg); /* Set 10bit source frame pitch */ if (block10bit) { @@ -144,9 +141,9 @@ static int config_rdma_frame(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, rdma.mf_bkgd_in_pxl); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.mf_bkgd_in_pxl); - MM_REG_WRITE(cmd, subsys_id, - base, MDP_RDMA_MF_BKGD_SIZE_IN_PXL, - reg, 0x001FFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, + MDP_RDMA_MF_BKGD_SIZE_IN_PXL, + reg, 0x001FFFFF); } } @@ -157,128 +154,121 @@ static int config_rdma_frame(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8195, ctx->param, rdma.control); rdma_con_mask = 0x1130; } - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_CON, reg, - rdma_con_mask); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_CON, reg, rdma_con_mask); /* Setup source buffer base */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.iova[0]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.iova[0]); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_BASE_0, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_BASE_0, reg); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.iova[1]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.iova[1]); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_BASE_1, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_BASE_1, reg); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.iova[2]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.iova[2]); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_BASE_2, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_BASE_2, reg); /* Setup source buffer end */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.iova_end[0]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.iova_end[0]); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_END_0, - reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_END_0, reg); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.iova_end[1]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.iova_end[1]); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_END_1, - reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_END_1, reg); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.iova_end[2]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.iova_end[2]); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_END_2, - reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_END_2, reg); /* Setup source frame pitch */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.mf_bkgd); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.mf_bkgd); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_MF_BKGD_SIZE_IN_BYTE, - reg, 0x001FFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_MF_BKGD_SIZE_IN_BYTE, + reg, 0x001FFFFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.sf_bkgd); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.sf_bkgd); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SF_BKGD_SIZE_IN_BYTE, - reg, 0x001FFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_SF_BKGD_SIZE_IN_BYTE, + reg, 0x001FFFFF); /* Setup color transform */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.transform); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.transform); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_TRANSFORM_0, - reg, 0x0F110000); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_TRANSFORM_0, + reg, 0x0F110000); if (!mdp_cfg || !mdp_cfg->rdma_esl_setting) goto rdma_config_done; if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.dmabuf_con0); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_DMABUF_CON_0, - reg, 0x0FFF00FF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_DMABUF_CON_0, + reg, 0x0FFF00FF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.ultra_th_high_con0); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_HIGH_CON_0, - reg, 0x3FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_HIGH_CON_0, + reg, 0x3FFFFFFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.ultra_th_low_con0); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_LOW_CON_0, - reg, 0x3FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_LOW_CON_0, + reg, 0x3FFFFFFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.dmabuf_con1); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_DMABUF_CON_1, - reg, 0x0F7F007F); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_DMABUF_CON_1, + reg, 0x0F7F007F); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.ultra_th_high_con1); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_HIGH_CON_1, - reg, 0x3FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_HIGH_CON_1, + reg, 0x3FFFFFFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.ultra_th_low_con1); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_LOW_CON_1, - reg, 0x3FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_LOW_CON_1, + reg, 0x3FFFFFFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.dmabuf_con2); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_DMABUF_CON_2, - reg, 0x0F3F003F); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_DMABUF_CON_2, + reg, 0x0F3F003F); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.ultra_th_high_con2); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_HIGH_CON_2, - reg, 0x3FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_HIGH_CON_2, + reg, 0x3FFFFFFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.ultra_th_low_con2); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_LOW_CON_2, - reg, 0x3FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_ULTRA_TH_LOW_CON_2, + reg, 0x3FFFFFFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.dmabuf_con3); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_DMABUF_CON_3, - reg, 0x0F3F003F); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_DMABUF_CON_3, + reg, 0x0F3F003F); rdma_config_done: return 0; @@ -297,15 +287,14 @@ static int config_rdma_subfrm(struct mdp_comp_ctx *ctx, u32 reg = 0; /* Enable RDMA */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_EN, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_EN, BIT(0), BIT(0)); /* Set Y pixel offset */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.subfrms[index].offset[0]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.subfrms[index].offset[0]); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_OFFSET_0, - reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_OFFSET_0, reg); /* Set 10bit UFO mode */ if (mdp_cfg) { @@ -315,8 +304,7 @@ static int config_rdma_subfrm(struct mdp_comp_ctx *ctx, else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.subfrms[index].offset_0_p); MM_REG_WRITE(cmd, subsys_id, base, - MDP_RDMA_SRC_OFFSET_0_P, - reg, 0xFFFFFFFF); + MDP_RDMA_SRC_OFFSET_0_P, reg); } } @@ -325,40 +313,38 @@ static int config_rdma_subfrm(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, rdma.subfrms[index].offset[1]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.subfrms[index].offset[1]); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_OFFSET_1, - reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_OFFSET_1, reg); /* Set V pixel offset */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.subfrms[index].offset[2]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.subfrms[index].offset[2]); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_OFFSET_2, - reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_SRC_OFFSET_2, reg); /* Set source size */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.subfrms[index].src); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.subfrms[index].src); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_MF_SRC_SIZE, reg, - 0x1FFF1FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_MF_SRC_SIZE, reg, + 0x1FFF1FFF); /* Set target size */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.subfrms[index].clip); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.subfrms[index].clip); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_MF_CLIP_SIZE, - reg, 0x1FFF1FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_MF_CLIP_SIZE, + reg, 0x1FFF1FFF); /* Set crop offset */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rdma.subfrms[index].clip_ofst); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rdma.subfrms[index].clip_ofst); - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_MF_OFFSET_1, - reg, 0x003F001F); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_MF_OFFSET_1, + reg, 0x003F001F); if (CFG_CHECK(MT8183, p_id)) { csf_l = CFG_COMP(MT8183, ctx->param, subfrms[index].in.left); @@ -369,8 +355,8 @@ static int config_rdma_subfrm(struct mdp_comp_ctx *ctx, } if (mdp_cfg && mdp_cfg->rdma_upsample_repeat_only) if ((csf_r - csf_l + 1) > 320) - MM_REG_WRITE(cmd, subsys_id, base, - MDP_RDMA_RESV_DUMMY_0, BIT(2), BIT(2)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, + MDP_RDMA_RESV_DUMMY_0, BIT(2), BIT(2)); return 0; } @@ -393,7 +379,7 @@ static int wait_rdma_event(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) MM_REG_WAIT(cmd, ctx->comp->gce_event[MDP_GCE_EVENT_EOF]); /* Disable RDMA */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_RDMA_EN, 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_RDMA_EN, 0x0, BIT(0)); return 0; } @@ -411,10 +397,10 @@ static int init_rsz(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) u8 subsys_id = ctx->comp->subsys_id; /* Reset RSZ */ - MM_REG_WRITE(cmd, subsys_id, base, PRZ_ENABLE, 0x10000, BIT(16)); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_ENABLE, 0x0, BIT(16)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_ENABLE, 0x10000, BIT(16)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_ENABLE, 0x0, BIT(16)); /* Enable RSZ */ - MM_REG_WRITE(cmd, subsys_id, base, PRZ_ENABLE, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_ENABLE, BIT(0), BIT(0)); if (CFG_CHECK(MT8195, p_id)) { struct device *dev; @@ -437,7 +423,7 @@ static int config_rsz_frame(struct mdp_comp_ctx *ctx, u32 reg = 0; if (mdp_cfg && mdp_cfg->rsz_etc_control) - MM_REG_WRITE(cmd, subsys_id, base, RSZ_ETC_CONTROL, 0x0, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, RSZ_ETC_CONTROL, 0x0); if (CFG_CHECK(MT8183, p_id)) bypass = CFG_COMP(MT8183, ctx->param, frame.bypass); @@ -446,7 +432,7 @@ static int config_rsz_frame(struct mdp_comp_ctx *ctx, if (bypass) { /* Disable RSZ */ - MM_REG_WRITE(cmd, subsys_id, base, PRZ_ENABLE, 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_ENABLE, 0x0, BIT(0)); return 0; } @@ -454,29 +440,27 @@ static int config_rsz_frame(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, rsz.control1); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rsz.control1); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_CONTROL_1, reg, - 0x03FFFDF3); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_CONTROL_1, reg, 0x03FFFDF3); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rsz.control2); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rsz.control2); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_CONTROL_2, reg, - 0x0FFFC290); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_CONTROL_2, reg, 0x0FFFC290); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rsz.coeff_step_x); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rsz.coeff_step_x); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_HORIZONTAL_COEFF_STEP, - reg, 0x007FFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_HORIZONTAL_COEFF_STEP, reg, + 0x007FFFFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rsz.coeff_step_y); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rsz.coeff_step_y); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_VERTICAL_COEFF_STEP, - reg, 0x007FFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_VERTICAL_COEFF_STEP, reg, + 0x007FFFFF); return 0; } @@ -495,15 +479,13 @@ static int config_rsz_subfrm(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, rsz.subfrms[index].control2); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rsz.subfrms[index].control2); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_CONTROL_2, reg, - 0x00003800); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_CONTROL_2, reg, 0x00003800); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rsz.subfrms[index].src); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rsz.subfrms[index].src); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_INPUT_IMAGE, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, PRZ_INPUT_IMAGE, reg); if (CFG_CHECK(MT8183, p_id)) { csf_l = CFG_COMP(MT8183, ctx->param, subfrms[index].in.left); @@ -514,60 +496,56 @@ static int config_rsz_subfrm(struct mdp_comp_ctx *ctx, } if (mdp_cfg && mdp_cfg->rsz_disable_dcm_small_sample) if ((csf_r - csf_l + 1) <= 16) - MM_REG_WRITE(cmd, subsys_id, base, PRZ_CONTROL_1, - BIT(27), BIT(27)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_CONTROL_1, + BIT(27), BIT(27)); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, subfrms[index].luma.left); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, subfrms[index].luma.left); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_LUMA_HORIZONTAL_INTEGER_OFFSET, - reg, 0xFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_LUMA_HORIZONTAL_INTEGER_OFFSET, + reg, 0xFFFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, subfrms[index].luma.left_subpix); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, subfrms[index].luma.left_subpix); - MM_REG_WRITE(cmd, subsys_id, - base, PRZ_LUMA_HORIZONTAL_SUBPIXEL_OFFSET, - reg, 0x1FFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_LUMA_HORIZONTAL_SUBPIXEL_OFFSET, + reg, 0x1FFFFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, subfrms[index].luma.top); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, subfrms[index].luma.top); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_LUMA_VERTICAL_INTEGER_OFFSET, - reg, 0xFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_LUMA_VERTICAL_INTEGER_OFFSET, + reg, 0xFFFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, subfrms[index].luma.top_subpix); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, subfrms[index].luma.top_subpix); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_LUMA_VERTICAL_SUBPIXEL_OFFSET, - reg, 0x1FFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_LUMA_VERTICAL_SUBPIXEL_OFFSET, + reg, 0x1FFFFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, subfrms[index].chroma.left); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, subfrms[index].chroma.left); - MM_REG_WRITE(cmd, subsys_id, - base, PRZ_CHROMA_HORIZONTAL_INTEGER_OFFSET, - reg, 0xFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_CHROMA_HORIZONTAL_INTEGER_OFFSET, + reg, 0xFFFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, subfrms[index].chroma.left_subpix); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, subfrms[index].chroma.left_subpix); - MM_REG_WRITE(cmd, subsys_id, - base, PRZ_CHROMA_HORIZONTAL_SUBPIXEL_OFFSET, - reg, 0x1FFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_CHROMA_HORIZONTAL_SUBPIXEL_OFFSET, + reg, 0x1FFFFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, rsz.subfrms[index].clip); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rsz.subfrms[index].clip); - MM_REG_WRITE(cmd, subsys_id, base, PRZ_OUTPUT_IMAGE, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, PRZ_OUTPUT_IMAGE, reg); if (CFG_CHECK(MT8195, p_id)) { struct device *dev; @@ -596,19 +574,19 @@ static int config_rsz_subfrm(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, rsz.subfrms[index].merge_cfg); MM_REG_WRITE(cmd, merge->subsys_id, merge->reg_base, - MDP_MERGE_CFG_0, reg, 0xFFFFFFFF); + MDP_MERGE_CFG_0, reg); MM_REG_WRITE(cmd, merge->subsys_id, merge->reg_base, - MDP_MERGE_CFG_4, reg, 0xFFFFFFFF); + MDP_MERGE_CFG_4, reg); MM_REG_WRITE(cmd, merge->subsys_id, merge->reg_base, - MDP_MERGE_CFG_24, reg, 0xFFFFFFFF); + MDP_MERGE_CFG_24, reg); MM_REG_WRITE(cmd, merge->subsys_id, merge->reg_base, - MDP_MERGE_CFG_25, reg, 0xFFFFFFFF); + MDP_MERGE_CFG_25, reg); /* Bypass mode */ MM_REG_WRITE(cmd, merge->subsys_id, merge->reg_base, - MDP_MERGE_CFG_12, BIT(0), 0xFFFFFFFF); + MDP_MERGE_CFG_12, BIT(0)); MM_REG_WRITE(cmd, merge->subsys_id, merge->reg_base, - MDP_MERGE_ENABLE, BIT(0), 0xFFFFFFFF); + MDP_MERGE_ENABLE, BIT(0)); } rsz_subfrm_done: @@ -634,8 +612,8 @@ static int advance_rsz_subfrm(struct mdp_comp_ctx *ctx, } if ((csf_r - csf_l + 1) <= 16) - MM_REG_WRITE(cmd, subsys_id, base, PRZ_CONTROL_1, 0x0, - BIT(27)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, PRZ_CONTROL_1, 0x0, + BIT(27)); } return 0; @@ -655,15 +633,15 @@ static int init_wrot(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) u8 subsys_id = ctx->comp->subsys_id; /* Reset WROT */ - MM_REG_WRITE(cmd, subsys_id, base, VIDO_SOFT_RST, BIT(0), BIT(0)); - MM_REG_POLL(cmd, subsys_id, base, VIDO_SOFT_RST_STAT, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_SOFT_RST, BIT(0), BIT(0)); + MM_REG_POLL_MASK(cmd, subsys_id, base, VIDO_SOFT_RST_STAT, BIT(0), BIT(0)); /* Reset setting */ if (CFG_CHECK(MT8195, p_id)) - MM_REG_WRITE(cmd, subsys_id, base, VIDO_CTRL, 0x0, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, VIDO_CTRL, 0x0); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_SOFT_RST, 0x0, BIT(0)); - MM_REG_POLL(cmd, subsys_id, base, VIDO_SOFT_RST_STAT, 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_SOFT_RST, 0x0, BIT(0)); + MM_REG_POLL_MASK(cmd, subsys_id, base, VIDO_SOFT_RST_STAT, 0x0, BIT(0)); return 0; } @@ -681,39 +659,36 @@ static int config_wrot_frame(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, wrot.iova[0]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.iova[0]); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_BASE_ADDR, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, VIDO_BASE_ADDR, reg); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.iova[1]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.iova[1]); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_BASE_ADDR_C, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, VIDO_BASE_ADDR_C, reg); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.iova[2]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.iova[2]); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_BASE_ADDR_V, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, VIDO_BASE_ADDR_V, reg); if (mdp_cfg && mdp_cfg->wrot_support_10bit) { if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.scan_10bit); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_SCAN_10BIT, - reg, 0x0000000F); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_SCAN_10BIT, + reg, 0x0000000F); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.pending_zero); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_PENDING_ZERO, - reg, 0x04000000); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_PENDING_ZERO, + reg, 0x04000000); } if (CFG_CHECK(MT8195, p_id)) { reg = CFG_COMP(MT8195, ctx->param, wrot.bit_number); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_CTRL_2, - reg, 0x00000007); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_CTRL_2, + reg, 0x00000007); } /* Write frame related registers */ @@ -721,14 +696,13 @@ static int config_wrot_frame(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, wrot.control); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.control); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_CTRL, reg, - 0xF131510F); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_CTRL, reg, 0xF131510F); /* Write pre-ultra threshold */ if (CFG_CHECK(MT8195, p_id)) { reg = CFG_COMP(MT8195, ctx->param, wrot.pre_ultra); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_DMA_PREULTRA, reg, - 0x00FFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_DMA_PREULTRA, reg, + 0x00FFFFFF); } /* Write frame Y pitch */ @@ -736,37 +710,34 @@ static int config_wrot_frame(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, wrot.stride[0]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.stride[0]); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_STRIDE, reg, - 0x0000FFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_STRIDE, reg, 0x0000FFFF); /* Write frame UV pitch */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.stride[1]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.stride[1]); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_STRIDE_C, reg, - 0xFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_STRIDE_C, reg, 0xFFFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.stride[2]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.stride[2]); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_STRIDE_V, reg, - 0xFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_STRIDE_V, reg, 0xFFFF); /* Write matrix control */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.mat_ctrl); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.mat_ctrl); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_MAT_CTRL, reg, 0xF3); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_MAT_CTRL, reg, 0xF3); /* Set the fixed ALPHA as 0xFF */ - MM_REG_WRITE(cmd, subsys_id, base, VIDO_DITHER, 0xFF000000, - 0xFF000000); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_DITHER, 0xFF000000, + 0xFF000000); /* Set VIDO_EOL_SEL */ - MM_REG_WRITE(cmd, subsys_id, base, VIDO_RSV_1, BIT(31), BIT(31)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_RSV_1, BIT(31), BIT(31)); /* Set VIDO_FIFO_TEST */ if (CFG_CHECK(MT8183, p_id)) @@ -775,8 +746,8 @@ static int config_wrot_frame(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8195, ctx->param, wrot.fifo_test); if (reg != 0) - MM_REG_WRITE(cmd, subsys_id, base, VIDO_FIFO_TEST, - reg, 0xFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_FIFO_TEST, reg, + 0xFFF); /* Filter enable */ if (mdp_cfg && mdp_cfg->wrot_filter_constraint) { @@ -784,13 +755,13 @@ static int config_wrot_frame(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, wrot.filter); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.filter); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_MAIN_BUF_SIZE, - reg, 0x77); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_MAIN_BUF_SIZE, reg, + 0x77); /* Turn off WROT DMA DCM */ if (CFG_CHECK(MT8195, p_id)) - MM_REG_WRITE(cmd, subsys_id, base, VIDO_ROT_EN, - (0x1 << 23) + (0x1 << 20), 0x900000); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_ROT_EN, + (0x1 << 23) + (0x1 << 20), 0x900000); } return 0; @@ -808,57 +779,52 @@ static int config_wrot_subfrm(struct mdp_comp_ctx *ctx, reg = CFG_COMP(MT8183, ctx->param, wrot.subfrms[index].offset[0]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.subfrms[index].offset[0]); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_OFST_ADDR, - reg, 0x0FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_OFST_ADDR, reg, 0x0FFFFFFF); /* Write U pixel offset */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.subfrms[index].offset[1]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.subfrms[index].offset[1]); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_OFST_ADDR_C, - reg, 0x0FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_OFST_ADDR_C, reg, 0x0FFFFFFF); /* Write V pixel offset */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.subfrms[index].offset[2]); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.subfrms[index].offset[2]); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_OFST_ADDR_V, - reg, 0x0FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_OFST_ADDR_V, reg, + 0x0FFFFFFF); /* Write source size */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.subfrms[index].src); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.subfrms[index].src); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_IN_SIZE, reg, - 0x1FFF1FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_IN_SIZE, reg, 0x1FFF1FFF); /* Write target size */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.subfrms[index].clip); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.subfrms[index].clip); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_TAR_SIZE, reg, - 0x1FFF1FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_TAR_SIZE, reg, 0x1FFF1FFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.subfrms[index].clip_ofst); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.subfrms[index].clip_ofst); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_CROP_OFST, reg, - 0x1FFF1FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_CROP_OFST, reg, 0x1FFF1FFF); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wrot.subfrms[index].main_buf); else if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, wrot.subfrms[index].main_buf); - MM_REG_WRITE(cmd, subsys_id, base, VIDO_MAIN_BUF_SIZE, - reg, 0x1FFF7F00); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_MAIN_BUF_SIZE, reg, + 0x1FFF7F00); /* Enable WROT */ - MM_REG_WRITE(cmd, subsys_id, base, VIDO_ROT_EN, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_ROT_EN, BIT(0), BIT(0)); return 0; } @@ -881,11 +847,11 @@ static int wait_wrot_event(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) MM_REG_WAIT(cmd, ctx->comp->gce_event[MDP_GCE_EVENT_EOF]); if (mdp_cfg && mdp_cfg->wrot_filter_constraint) - MM_REG_WRITE(cmd, subsys_id, base, VIDO_MAIN_BUF_SIZE, 0x0, - 0x77); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_MAIN_BUF_SIZE, 0x0, + 0x77); /* Disable WROT */ - MM_REG_WRITE(cmd, subsys_id, base, VIDO_ROT_EN, 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, VIDO_ROT_EN, 0x0, BIT(0)); return 0; } @@ -904,9 +870,9 @@ static int init_wdma(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) u8 subsys_id = ctx->comp->subsys_id; /* Reset WDMA */ - MM_REG_WRITE(cmd, subsys_id, base, WDMA_RST, BIT(0), BIT(0)); - MM_REG_POLL(cmd, subsys_id, base, WDMA_FLOW_CTRL_DBG, BIT(0), BIT(0)); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_RST, 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_RST, BIT(0), BIT(0)); + MM_REG_POLL_MASK(cmd, subsys_id, base, WDMA_FLOW_CTRL_DBG, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_RST, 0x0, BIT(0)); return 0; } @@ -918,40 +884,35 @@ static int config_wdma_frame(struct mdp_comp_ctx *ctx, u8 subsys_id = ctx->comp->subsys_id; u32 reg = 0; - MM_REG_WRITE(cmd, subsys_id, base, WDMA_BUF_CON2, 0x10101050, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, WDMA_BUF_CON2, 0x10101050); /* Setup frame information */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.wdma_cfg); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_CFG, reg, - 0x0F01B8F0); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_CFG, reg, 0x0F01B8F0); /* Setup frame base address */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.iova[0]); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_ADDR, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_ADDR, reg); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.iova[1]); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_U_ADDR, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_U_ADDR, reg); if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.iova[2]); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_V_ADDR, reg, - 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_V_ADDR, reg); /* Setup Y pitch */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.w_in_byte); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_W_IN_BYTE, - reg, 0x0000FFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_DST_W_IN_BYTE, reg, + 0x0000FFFF); /* Setup UV pitch */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.uv_stride); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_UV_PITCH, - reg, 0x0000FFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_DST_UV_PITCH, reg, + 0x0000FFFF); /* Set the fixed ALPHA as 0xFF */ - MM_REG_WRITE(cmd, subsys_id, base, WDMA_ALPHA, 0x800000FF, - 0x800000FF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_ALPHA, 0x800000FF, + 0x800000FF); return 0; } @@ -966,36 +927,33 @@ static int config_wdma_subfrm(struct mdp_comp_ctx *ctx, /* Write Y pixel offset */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.subfrms[index].offset[0]); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_ADDR_OFFSET, - reg, 0x0FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_DST_ADDR_OFFSET, reg, + 0x0FFFFFFF); /* Write U pixel offset */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.subfrms[index].offset[1]); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_U_ADDR_OFFSET, - reg, 0x0FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_DST_U_ADDR_OFFSET, reg, + 0x0FFFFFFF); /* Write V pixel offset */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.subfrms[index].offset[2]); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_DST_V_ADDR_OFFSET, - reg, 0x0FFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_DST_V_ADDR_OFFSET, reg, + 0x0FFFFFFF); /* Write source size */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.subfrms[index].src); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_SRC_SIZE, reg, - 0x3FFF3FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_SRC_SIZE, reg, 0x3FFF3FFF); /* Write target size */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.subfrms[index].clip); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_CLIP_SIZE, reg, - 0x3FFF3FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_CLIP_SIZE, reg, 0x3FFF3FFF); /* Write clip offset */ if (CFG_CHECK(MT8183, p_id)) reg = CFG_COMP(MT8183, ctx->param, wdma.subfrms[index].clip_ofst); - MM_REG_WRITE(cmd, subsys_id, base, WDMA_CLIP_COORD, reg, - 0x3FFF3FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_CLIP_COORD, reg, 0x3FFF3FFF); /* Enable WDMA */ - MM_REG_WRITE(cmd, subsys_id, base, WDMA_EN, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_EN, BIT(0), BIT(0)); return 0; } @@ -1007,7 +965,7 @@ static int wait_wdma_event(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) MM_REG_WAIT(cmd, ctx->comp->gce_event[MDP_GCE_EVENT_EOF]); /* Disable WDMA */ - MM_REG_WRITE(cmd, subsys_id, base, WDMA_EN, 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, WDMA_EN, 0x0, BIT(0)); return 0; } @@ -1033,19 +991,17 @@ static int reset_luma_hist(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) /* Reset histogram */ for (i = 0; i <= hist_num; i++) - MM_REG_WRITE_MASK(cmd, subsys_id, base, - (MDP_LUMA_HIST_INIT + (i << 2)), - 0, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, + (MDP_LUMA_HIST_INIT + (i << 2)), 0); if (mdp_cfg->tdshp_constrain) MM_REG_WRITE(cmd, subsys_id, base, - MDP_DC_TWO_D_W1_RESULT_INIT, 0, 0xFFFFFFFF); + MDP_DC_TWO_D_W1_RESULT_INIT, 0); if (mdp_cfg->tdshp_contour) for (i = 0; i < hist_num; i++) - MM_REG_WRITE_MASK(cmd, subsys_id, base, - (MDP_CONTOUR_HIST_INIT + (i << 2)), - 0, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, + (MDP_CONTOUR_HIST_INIT + (i << 2)), 0); return 0; } @@ -1055,9 +1011,9 @@ static int init_tdshp(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) phys_addr_t base = ctx->comp->reg_base; u16 subsys_id = ctx->comp->subsys_id; - MM_REG_WRITE(cmd, subsys_id, base, MDP_TDSHP_CTRL, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_TDSHP_CTRL, BIT(0), BIT(0)); /* Enable FIFO */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_TDSHP_CFG, BIT(1), BIT(1)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_TDSHP_CFG, BIT(1), BIT(1)); return reset_luma_hist(ctx, cmd); } @@ -1072,7 +1028,7 @@ static int config_tdshp_frame(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, tdshp.cfg); - MM_REG_WRITE(cmd, subsys_id, base, MDP_TDSHP_CFG, reg, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_TDSHP_CFG, reg, BIT(0)); return 0; } @@ -1086,26 +1042,24 @@ static int config_tdshp_subfrm(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, tdshp.subfrms[index].src); - MM_REG_WRITE(cmd, subsys_id, base, MDP_TDSHP_INPUT_SIZE, - reg, MDP_TDSHP_INPUT_SIZE_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_TDSHP_INPUT_SIZE, reg); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, tdshp.subfrms[index].clip_ofst); - MM_REG_WRITE(cmd, subsys_id, base, MDP_TDSHP_OUTPUT_OFFSET, - reg, 0x00FF00FF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_TDSHP_OUTPUT_OFFSET, reg, + 0x00FF00FF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, tdshp.subfrms[index].clip); - MM_REG_WRITE(cmd, subsys_id, base, MDP_TDSHP_OUTPUT_SIZE, - reg, MDP_TDSHP_OUTPUT_SIZE_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_TDSHP_OUTPUT_SIZE, reg); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, tdshp.subfrms[index].hist_cfg_0); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HIST_CFG_00, reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_HIST_CFG_00, reg); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, tdshp.subfrms[index].hist_cfg_1); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HIST_CFG_01, reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_HIST_CFG_01, reg); return 0; } @@ -1122,21 +1076,19 @@ static int init_color(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) phys_addr_t base = ctx->comp->reg_base; u16 subsys_id = ctx->comp->subsys_id; - MM_REG_WRITE(cmd, subsys_id, base, - MDP_COLOR_START, 0x1, BIT(1) | BIT(0)); - MM_REG_WRITE(cmd, subsys_id, base, - MDP_COLOR_WIN_X_MAIN, 0xFFFF0000, 0xFFFFFFFF); - MM_REG_WRITE(cmd, subsys_id, base, - MDP_COLOR_WIN_Y_MAIN, 0xFFFF0000, 0xFFFFFFFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_COLOR_START, 0x1, + BIT(1) | BIT(0)); + MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_WIN_X_MAIN, 0xFFFF0000); + MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_WIN_Y_MAIN, 0xFFFF0000); /* Reset color matrix */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_CM1_EN, 0x0, BIT(0)); - MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_CM2_EN, 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_COLOR_CM1_EN, 0x0, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_COLOR_CM2_EN, 0x0, BIT(0)); /* Enable interrupt */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_INTEN, 0x7, 0x7); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_COLOR_INTEN, 0x7, 0x7); - MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_OUT_SEL, 0x333, 0x333); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_COLOR_OUT_SEL, 0x333, 0x333); return 0; } @@ -1151,8 +1103,7 @@ static int config_color_frame(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, color.start); - MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_START, - reg, MDP_COLOR_START_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_START, reg); return 0; } @@ -1166,13 +1117,13 @@ static int config_color_subfrm(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, color.subfrms[index].in_hsize); - MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_INTERNAL_IP_WIDTH, - reg, 0x00003FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_COLOR_INTERNAL_IP_WIDTH, + reg, 0x00003FFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, color.subfrms[index].in_vsize); - MM_REG_WRITE(cmd, subsys_id, base, MDP_COLOR_INTERNAL_IP_HEIGHT, - reg, 0x00003FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_COLOR_INTERNAL_IP_HEIGHT, + reg, 0x00003FFF); return 0; } @@ -1190,9 +1141,9 @@ static int init_ccorr(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) u8 subsys_id = ctx->comp->subsys_id; /* CCORR enable */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_CCORR_EN, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_CCORR_EN, BIT(0), BIT(0)); /* Relay mode */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_CCORR_CFG, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_CCORR_CFG, BIT(0), BIT(0)); return 0; } @@ -1214,8 +1165,8 @@ static int config_ccorr_subfrm(struct mdp_comp_ctx *ctx, hsize = csf_r - csf_l + 1; vsize = csf_b - csf_t + 1; - MM_REG_WRITE(cmd, subsys_id, base, MDP_CCORR_SIZE, - (hsize << 16) + (vsize << 0), 0x1FFF1FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_CCORR_SIZE, + (hsize << 16) + (vsize << 0), 0x1FFF1FFF); return 0; } @@ -1231,7 +1182,7 @@ static int init_aal(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) u16 subsys_id = ctx->comp->subsys_id; /* Always set MDP_AAL enable to 1 */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_AAL_EN, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_AAL_EN, BIT(0), BIT(0)); return 0; } @@ -1246,11 +1197,11 @@ static int config_aal_frame(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, aal.cfg_main); - MM_REG_WRITE(cmd, subsys_id, base, MDP_AAL_CFG_MAIN, reg, BIT(7)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_AAL_CFG_MAIN, reg, BIT(7)); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, aal.cfg); - MM_REG_WRITE(cmd, subsys_id, base, MDP_AAL_CFG, reg, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_AAL_CFG, reg, BIT(0)); return 0; } @@ -1264,18 +1215,16 @@ static int config_aal_subfrm(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, aal.subfrms[index].src); - MM_REG_WRITE(cmd, subsys_id, base, MDP_AAL_SIZE, - reg, MDP_AAL_SIZE_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_AAL_SIZE, reg); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, aal.subfrms[index].clip_ofst); - MM_REG_WRITE(cmd, subsys_id, base, MDP_AAL_OUTPUT_OFFSET, - reg, 0x00FF00FF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_AAL_OUTPUT_OFFSET, reg, + 0x00FF00FF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, aal.subfrms[index].clip); - MM_REG_WRITE(cmd, subsys_id, base, MDP_AAL_OUTPUT_SIZE, - reg, MDP_AAL_OUTPUT_SIZE_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_AAL_OUTPUT_SIZE, reg); return 0; } @@ -1293,7 +1242,7 @@ static int init_hdr(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) u16 subsys_id = ctx->comp->subsys_id; /* Always set MDP_HDR enable to 1 */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_TOP, BIT(0), BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_TOP, BIT(0), BIT(0)); return 0; } @@ -1308,11 +1257,11 @@ static int config_hdr_frame(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.top); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_TOP, reg, BIT(29) | BIT(28)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_TOP, reg, BIT(29) | BIT(28)); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.relay); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_RELAY, reg, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_RELAY, reg, BIT(0)); return 0; } @@ -1326,37 +1275,36 @@ static int config_hdr_subfrm(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.subfrms[index].win_size); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_TILE_POS, - reg, MDP_HDR_TILE_POS_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_TILE_POS, reg); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.subfrms[index].src); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_SIZE_0, reg, 0x1FFF1FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_SIZE_0, reg, 0x1FFF1FFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.subfrms[index].clip_ofst0); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_SIZE_1, reg, 0x1FFF1FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_SIZE_1, reg, 0x1FFF1FFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.subfrms[index].clip_ofst1); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_SIZE_2, reg, 0x1FFF1FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_SIZE_2, reg, 0x1FFF1FFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.subfrms[index].hist_ctrl_0); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_HIST_CTRL_0, reg, 0x00003FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_HIST_CTRL_0, reg, 0x00003FFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.subfrms[index].hist_ctrl_1); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_HIST_CTRL_1, reg, 0x00003FFF); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_HIST_CTRL_1, reg, 0x00003FFF); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.subfrms[index].hdr_top); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_TOP, reg, BIT(6) | BIT(5)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_TOP, reg, BIT(6) | BIT(5)); /* Enable histogram */ if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, hdr.subfrms[index].hist_addr); - MM_REG_WRITE(cmd, subsys_id, base, MDP_HDR_HIST_ADDR, reg, BIT(9)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_HDR_HIST_ADDR, reg, BIT(9)); return 0; } @@ -1373,8 +1321,8 @@ static int init_fg(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) phys_addr_t base = ctx->comp->reg_base; u16 subsys_id = ctx->comp->subsys_id; - MM_REG_WRITE(cmd, subsys_id, base, MDP_FG_TRIGGER, BIT(2), BIT(2)); - MM_REG_WRITE(cmd, subsys_id, base, MDP_FG_TRIGGER, 0x0, BIT(2)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_FG_TRIGGER, BIT(2), BIT(2)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_FG_TRIGGER, 0x0, BIT(2)); return 0; } @@ -1389,11 +1337,11 @@ static int config_fg_frame(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, fg.ctrl_0); - MM_REG_WRITE(cmd, subsys_id, base, MDP_FG_FG_CTRL_0, reg, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_FG_FG_CTRL_0, reg, BIT(0)); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, fg.ck_en); - MM_REG_WRITE(cmd, subsys_id, base, MDP_FG_FG_CK_EN, reg, 0x7); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_FG_FG_CK_EN, reg, 0x7); return 0; } @@ -1407,11 +1355,11 @@ static int config_fg_subfrm(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, fg.subfrms[index].info_0); - MM_REG_WRITE(cmd, subsys_id, base, MDP_FG_TILE_INFO_0, reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_FG_TILE_INFO_0, reg); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, fg.subfrms[index].info_1); - MM_REG_WRITE(cmd, subsys_id, base, MDP_FG_TILE_INFO_1, reg, 0xFFFFFFFF); + MM_REG_WRITE(cmd, subsys_id, base, MDP_FG_TILE_INFO_1, reg); return 0; } @@ -1428,14 +1376,11 @@ static int init_ovl(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) phys_addr_t base = ctx->comp->reg_base; u16 subsys_id = ctx->comp->subsys_id; - MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_EN, - BIT(0), MDP_OVL_EN_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_EN, BIT(0)); /* Set to relay mode */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_SRC_CON, - BIT(9), MDP_OVL_SRC_CON_MASK); - MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_DP_CON, - BIT(0), MDP_OVL_DP_CON_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_SRC_CON, BIT(9)); + MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_DP_CON, BIT(0)); return 0; } @@ -1450,11 +1395,11 @@ static int config_ovl_frame(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, ovl.L0_con); - MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_L0_CON, reg, BIT(29) | BIT(28)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_OVL_L0_CON, reg, BIT(29) | BIT(28)); if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, ovl.src_con); - MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_SRC_CON, reg, BIT(0)); + MM_REG_WRITE_MASK(cmd, subsys_id, base, MDP_OVL_SRC_CON, reg, BIT(0)); return 0; } @@ -1468,14 +1413,12 @@ static int config_ovl_subfrm(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, ovl.subfrms[index].L0_src_size); - MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_L0_SRC_SIZE, - reg, MDP_OVL_L0_SRC_SIZE_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_L0_SRC_SIZE, reg); /* Setup output size */ if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, ovl.subfrms[index].roi_size); - MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_ROI_SIZE, - reg, MDP_OVL_ROI_SIZE_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_OVL_ROI_SIZE, reg); return 0; } @@ -1492,13 +1435,10 @@ static int init_pad(struct mdp_comp_ctx *ctx, struct mdp_cmdq_cmd *cmd) phys_addr_t base = ctx->comp->reg_base; u16 subsys_id = ctx->comp->subsys_id; - MM_REG_WRITE(cmd, subsys_id, base, MDP_PAD_CON, - BIT(1), MDP_PAD_CON_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_PAD_CON, BIT(1)); /* Reset */ - MM_REG_WRITE(cmd, subsys_id, base, MDP_PAD_W_SIZE, - 0, MDP_PAD_W_SIZE_MASK); - MM_REG_WRITE(cmd, subsys_id, base, MDP_PAD_H_SIZE, - 0, MDP_PAD_H_SIZE_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_PAD_W_SIZE, 0); + MM_REG_WRITE(cmd, subsys_id, base, MDP_PAD_H_SIZE, 0); return 0; } @@ -1512,8 +1452,7 @@ static int config_pad_subfrm(struct mdp_comp_ctx *ctx, if (CFG_CHECK(MT8195, p_id)) reg = CFG_COMP(MT8195, ctx->param, pad.subfrms[index].pic_size); - MM_REG_WRITE(cmd, subsys_id, base, MDP_PAD_PIC_SIZE, - reg, MDP_PAD_PIC_SIZE_MASK); + MM_REG_WRITE(cmd, subsys_id, base, MDP_PAD_PIC_SIZE, reg); return 0; } diff --git a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.h b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.h index 3e5d2da1c807..681906c16419 100644 --- a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.h +++ b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.h @@ -9,18 +9,18 @@ #include "mtk-mdp3-cmdq.h" -#define MM_REG_WRITE_MASK(cmd, id, base, ofst, val, mask, ...) \ - cmdq_pkt_write_mask(&((cmd)->pkt), id, \ - (base) + (ofst), (val), (mask), ##__VA_ARGS__) - -#define MM_REG_WRITE(cmd, id, base, ofst, val, mask, ...) \ +#define MM_REG_WRITE_MASK(cmd, id, base, ofst, val, mask) \ do { \ typeof(mask) (m) = (mask); \ - MM_REG_WRITE_MASK(cmd, id, base, ofst, val, \ + cmdq_pkt_write_mask(&((cmd)->pkt), id, (base) + (ofst), \ + (val), \ (((m) & (ofst##_MASK)) == (ofst##_MASK)) ? \ - (0xffffffff) : (m), ##__VA_ARGS__); \ + (0xffffffff) : (m)); \ } while (0) +#define MM_REG_WRITE(cmd, id, base, ofst, val) \ + cmdq_pkt_write(&((cmd)->pkt), id, (base) + (ofst), (val)) + #define MM_REG_WAIT(cmd, evt) \ do { \ typeof(cmd) (c) = (cmd); \ @@ -49,20 +49,17 @@ do { \ cmdq_pkt_set_event(&((c)->pkt), (e)); \ } while (0) -#define MM_REG_POLL_MASK(cmd, id, base, ofst, val, _mask, ...) \ +#define MM_REG_POLL_MASK(cmd, id, base, ofst, val, _mask) \ do { \ typeof(_mask) (_m) = (_mask); \ cmdq_pkt_poll_mask(&((cmd)->pkt), id, \ - (base) + (ofst), (val), (_m), ##__VA_ARGS__); \ + (base) + (ofst), (val), \ + (((_m) & (ofst##_MASK)) == (ofst##_MASK)) ? \ + (0xffffffff) : (_m)); \ } while (0) -#define MM_REG_POLL(cmd, id, base, ofst, val, mask, ...) \ -do { \ - typeof(mask) (m) = (mask); \ - MM_REG_POLL_MASK((cmd), id, base, ofst, val, \ - (((m) & (ofst##_MASK)) == (ofst##_MASK)) ? \ - (0xffffffff) : (m), ##__VA_ARGS__); \ -} while (0) +#define MM_REG_POLL(cmd, id, base, ofst, val) \ + cmdq_pkt_poll(&((cmd)->pkt), id, (base) + (ofst), (val)) enum mtk_mdp_comp_id { MDP_COMP_NONE = -1, /* Invalid engine */ diff --git a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.c b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.c index 5e94ff0d0756..f571f561f070 100644 --- a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.c +++ b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.c @@ -312,6 +312,8 @@ static int mdp_probe(struct platform_device *pdev) ret = PTR_ERR(mdp->cmdq_clt[i]); goto err_mbox_destroy; } + + mdp->cmdq_shift_pa[i] = cmdq_get_shift_pa(mdp->cmdq_clt[i]->chan); } init_waitqueue_head(&mdp->callback_wq); diff --git a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.h b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.h index 430251f63754..05cade1d098e 100644 --- a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.h +++ b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.h @@ -126,6 +126,7 @@ struct mdp_dev { u32 id_count; struct ida mdp_ida; struct cmdq_client *cmdq_clt[MDP_PP_MAX]; + u8 cmdq_shift_pa[MDP_PP_MAX]; wait_queue_head_t callback_wq; struct v4l2_device v4l2_dev; diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c index eea709d93820..47c302745c1d 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c @@ -1188,7 +1188,8 @@ err: return ret; } -static +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack void vdec_vp9_slice_map_counts_eob_coef(unsigned int i, unsigned int j, unsigned int k, struct vdec_vp9_slice_frame_counts *counts, struct v4l2_vp9_frame_symbol_counts *counts_helper) diff --git a/drivers/media/platform/nuvoton/npcm-video.c b/drivers/media/platform/nuvoton/npcm-video.c index 4f5d75645b2b..024cd8ee1709 100644 --- a/drivers/media/platform/nuvoton/npcm-video.c +++ b/drivers/media/platform/nuvoton/npcm-video.c @@ -1665,9 +1665,9 @@ static int npcm_video_ece_init(struct npcm_video *video) dev_info(dev, "Support HEXTILE pixel format\n"); ece_pdev = of_find_device_by_node(ece_node); - if (IS_ERR(ece_pdev)) { + if (!ece_pdev) { dev_err(dev, "Failed to find ECE device\n"); - return PTR_ERR(ece_pdev); + return -ENODEV; } of_node_put(ece_node); diff --git a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c index 7f5fe551179b..1221b309a916 100644 --- a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c +++ b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c @@ -2677,11 +2677,12 @@ static void mxc_jpeg_detach_pm_domains(struct mxc_jpeg_dev *jpeg) int i; for (i = 0; i < jpeg->num_domains; i++) { - if (jpeg->pd_dev[i] && !pm_runtime_suspended(jpeg->pd_dev[i])) + if (!IS_ERR_OR_NULL(jpeg->pd_dev[i]) && + !pm_runtime_suspended(jpeg->pd_dev[i])) pm_runtime_force_suspend(jpeg->pd_dev[i]); - if (jpeg->pd_link[i] && !IS_ERR(jpeg->pd_link[i])) + if (!IS_ERR_OR_NULL(jpeg->pd_link[i])) device_link_del(jpeg->pd_link[i]); - if (jpeg->pd_dev[i] && !IS_ERR(jpeg->pd_dev[i])) + if (!IS_ERR_OR_NULL(jpeg->pd_dev[i])) dev_pm_domain_detach(jpeg->pd_dev[i], true); jpeg->pd_dev[i] = NULL; jpeg->pd_link[i] = NULL; diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c index aaf58063677c..1e79b1211b60 100644 --- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c +++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c @@ -307,6 +307,19 @@ static const struct mxc_isi_plat_data mxc_imx8mp_data = { .has_36bit_dma = true, }; +static const struct mxc_isi_plat_data mxc_imx8ulp_data = { + .model = MXC_ISI_IMX8ULP, + .num_ports = 1, + .num_channels = 1, + .reg_offset = 0x0, + .ier_reg = &mxc_imx8_isi_ier_v2, + .set_thd = &mxc_imx8_isi_thd_v1, + .clks = mxc_imx8mn_clks, + .num_clks = ARRAY_SIZE(mxc_imx8mn_clks), + .buf_active_reverse = true, + .has_36bit_dma = false, +}; + static const struct mxc_isi_plat_data mxc_imx93_data = { .model = MXC_ISI_IMX93, .num_ports = 1, @@ -528,6 +541,7 @@ static void mxc_isi_remove(struct platform_device *pdev) static const struct of_device_id mxc_isi_of_match[] = { { .compatible = "fsl,imx8mn-isi", .data = &mxc_imx8mn_data }, { .compatible = "fsl,imx8mp-isi", .data = &mxc_imx8mp_data }, + { .compatible = "fsl,imx8ulp-isi", .data = &mxc_imx8ulp_data }, { .compatible = "fsl,imx93-isi", .data = &mxc_imx93_data }, { /* sentinel */ }, }; diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.h b/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.h index 2810ebe9b5f7..9c7fe9e5f941 100644 --- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.h +++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.h @@ -158,6 +158,7 @@ struct mxc_gasket_ops { enum model { MXC_ISI_IMX8MN, MXC_ISI_IMX8MP, + MXC_ISI_IMX8ULP, MXC_ISI_IMX93, }; diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c index c0ba34ea82fd..8654150728a8 100644 --- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c +++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c @@ -861,6 +861,7 @@ int mxc_isi_video_buffer_prepare(struct mxc_isi_dev *isi, struct vb2_buffer *vb2 const struct mxc_isi_format_info *info, const struct v4l2_pix_format_mplane *pix) { + struct vb2_v4l2_buffer *v4l2_buf = to_vb2_v4l2_buffer(vb2); unsigned int i; for (i = 0; i < info->mem_planes; i++) { @@ -875,6 +876,8 @@ int mxc_isi_video_buffer_prepare(struct mxc_isi_dev *isi, struct vb2_buffer *vb2 vb2_set_plane_payload(vb2, i, size); } + v4l2_buf->field = pix->field; + return 0; } diff --git a/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c index df7e93a5a4f6..f341f7b7fd8a 100644 --- a/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c +++ b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c @@ -505,9 +505,9 @@ static void csiphy_gen2_config_lanes(struct csiphy_device *csiphy, u32 val; switch (csiphy->camss->res->version) { - case CAMSS_845: - r = &lane_regs_sdm845[0][0]; - array_size = ARRAY_SIZE(lane_regs_sdm845[0]); + case CAMSS_7280: + r = &lane_regs_sm8250[0][0]; + array_size = ARRAY_SIZE(lane_regs_sm8250[0]); break; case CAMSS_8250: r = &lane_regs_sm8250[0][0]; @@ -517,6 +517,10 @@ static void csiphy_gen2_config_lanes(struct csiphy_device *csiphy, r = &lane_regs_sc8280xp[0][0]; array_size = ARRAY_SIZE(lane_regs_sc8280xp[0]); break; + case CAMSS_845: + r = &lane_regs_sdm845[0][0]; + array_size = ARRAY_SIZE(lane_regs_sdm845[0]); + break; default: WARN(1, "unknown cspi version\n"); return; @@ -557,9 +561,10 @@ static bool csiphy_is_gen2(u32 version) bool ret = false; switch (version) { - case CAMSS_845: + case CAMSS_7280: case CAMSS_8250: case CAMSS_8280XP: + case CAMSS_845: ret = true; break; } diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c index 5af2b382a843..3791c2d8a6cf 100644 --- a/drivers/media/platform/qcom/camss/camss-csiphy.c +++ b/drivers/media/platform/qcom/camss/camss-csiphy.c @@ -103,6 +103,11 @@ const struct csiphy_formats csiphy_formats_8x96 = { .formats = formats_8x96 }; +const struct csiphy_formats csiphy_formats_sc7280 = { + .nformats = ARRAY_SIZE(formats_sdm845), + .formats = formats_sdm845 +}; + const struct csiphy_formats csiphy_formats_sdm845 = { .nformats = ARRAY_SIZE(formats_sdm845), .formats = formats_sdm845 diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h index eebc1ff1cfab..90cc3f976643 100644 --- a/drivers/media/platform/qcom/camss/camss-csiphy.h +++ b/drivers/media/platform/qcom/camss/camss-csiphy.h @@ -26,6 +26,12 @@ struct csiphy_lane { u8 pol; }; +/** + * struct csiphy_lanes_cfg - CSIPHY lanes configuration + * @num_data: number of data lanes + * @data: data lanes configuration + * @clk: clock lane configuration (only for D-PHY) + */ struct csiphy_lanes_cfg { int num_data; struct csiphy_lane *data; @@ -111,6 +117,7 @@ void msm_csiphy_unregister_entity(struct csiphy_device *csiphy); extern const struct csiphy_formats csiphy_formats_8x16; extern const struct csiphy_formats csiphy_formats_8x96; +extern const struct csiphy_formats csiphy_formats_sc7280; extern const struct csiphy_formats csiphy_formats_sdm845; extern const struct csiphy_hw_ops csiphy_ops_2ph_1_0; diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c index 80a62ba11295..95f6a1ac7eaf 100644 --- a/drivers/media/platform/qcom/camss/camss-vfe.c +++ b/drivers/media/platform/qcom/camss/camss-vfe.c @@ -334,11 +334,12 @@ static u32 vfe_src_pad_code(struct vfe_line *line, u32 sink_code, return sink_code; } break; - case CAMSS_8x96: case CAMSS_660: - case CAMSS_845: + case CAMSS_7280: + case CAMSS_8x96: case CAMSS_8250: case CAMSS_8280XP: + case CAMSS_845: switch (sink_code) { case MEDIA_BUS_FMT_YUYV8_1X16: { @@ -1693,9 +1694,10 @@ static int vfe_bpl_align(struct vfe_device *vfe) int ret = 8; switch (vfe->camss->res->version) { - case CAMSS_845: + case CAMSS_7280: case CAMSS_8250: case CAMSS_8280XP: + case CAMSS_845: ret = 16; break; default: diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c index 9fb31f4c18ad..a85e9df0f301 100644 --- a/drivers/media/platform/qcom/camss/camss.c +++ b/drivers/media/platform/qcom/camss/camss.c @@ -1266,6 +1266,310 @@ static const struct resources_icc icc_res_sm8250[] = { }, }; +static const struct camss_subdev_resources csiphy_res_7280[] = { + /* CSIPHY0 */ + { + .regulators = { "vdda-phy", "vdda-pll" }, + + .clock = { "csiphy0", "csiphy0_timer" }, + .clock_rate = { { 300000000, 400000000 }, + { 300000000 } }, + .reg = { "csiphy0" }, + .interrupt = { "csiphy0" }, + .csiphy = { + .hw_ops = &csiphy_ops_3ph_1_0, + .formats = &csiphy_formats_sc7280 + } + }, + /* CSIPHY1 */ + { + .regulators = { "vdda-phy", "vdda-pll" }, + + .clock = { "csiphy1", "csiphy1_timer" }, + .clock_rate = { { 300000000, 400000000 }, + { 300000000 } }, + .reg = { "csiphy1" }, + .interrupt = { "csiphy1" }, + .csiphy = { + .hw_ops = &csiphy_ops_3ph_1_0, + .formats = &csiphy_formats_sc7280 + } + }, + /* CSIPHY2 */ + { + .regulators = { "vdda-phy", "vdda-pll" }, + + .clock = { "csiphy2", "csiphy2_timer" }, + .clock_rate = { { 300000000, 400000000 }, + { 300000000 } }, + .reg = { "csiphy2" }, + .interrupt = { "csiphy2" }, + .csiphy = { + .hw_ops = &csiphy_ops_3ph_1_0, + .formats = &csiphy_formats_sc7280 + } + }, + /* CSIPHY3 */ + { + .regulators = { "vdda-phy", "vdda-pll" }, + + .clock = { "csiphy3", "csiphy3_timer" }, + .clock_rate = { { 300000000, 400000000 }, + { 300000000 } }, + .reg = { "csiphy3" }, + .interrupt = { "csiphy3" }, + .csiphy = { + .hw_ops = &csiphy_ops_3ph_1_0, + .formats = &csiphy_formats_sc7280 + } + }, + /* CSIPHY4 */ + { + .regulators = { "vdda-phy", "vdda-pll" }, + + .clock = { "csiphy4", "csiphy4_timer" }, + .clock_rate = { { 300000000, 400000000 }, + { 300000000 } }, + .reg = { "csiphy4" }, + .interrupt = { "csiphy4" }, + .csiphy = { + .hw_ops = &csiphy_ops_3ph_1_0, + .formats = &csiphy_formats_sc7280 + } + }, +}; + +static const struct camss_subdev_resources csid_res_7280[] = { + /* CSID0 */ + { + .regulators = {}, + + .clock = { "vfe0_csid", "vfe0_cphy_rx", "vfe0" }, + .clock_rate = { { 300000000, 400000000 }, + { 0 }, + { 380000000, 510000000, 637000000, 760000000 } + }, + + .reg = { "csid0" }, + .interrupt = { "csid0" }, + .csid = { + .is_lite = false, + .hw_ops = &csid_ops_gen2, + .parent_dev_ops = &vfe_parent_dev_ops, + .formats = &csid_formats_gen2 + } + }, + /* CSID1 */ + { + .regulators = {}, + + .clock = { "vfe1_csid", "vfe1_cphy_rx", "vfe1" }, + .clock_rate = { { 300000000, 400000000 }, + { 0 }, + { 380000000, 510000000, 637000000, 760000000 } + }, + + .reg = { "csid1" }, + .interrupt = { "csid1" }, + .csid = { + .is_lite = false, + .hw_ops = &csid_ops_gen2, + .parent_dev_ops = &vfe_parent_dev_ops, + .formats = &csid_formats_gen2 + } + }, + /* CSID2 */ + { + .regulators = {}, + + .clock = { "vfe2_csid", "vfe2_cphy_rx", "vfe2" }, + .clock_rate = { { 300000000, 400000000 }, + { 0 }, + { 380000000, 510000000, 637000000, 760000000 } + }, + + .reg = { "csid2" }, + .interrupt = { "csid2" }, + .csid = { + .is_lite = false, + .hw_ops = &csid_ops_gen2, + .parent_dev_ops = &vfe_parent_dev_ops, + .formats = &csid_formats_gen2 + } + }, + /* CSID3 */ + { + .regulators = {}, + + .clock = { "vfe_lite0_csid", "vfe_lite0_cphy_rx", "vfe_lite0" }, + .clock_rate = { { 300000000, 400000000 }, + { 0 }, + { 320000000, 400000000, 480000000, 600000000 } + }, + + .reg = { "csid_lite0" }, + .interrupt = { "csid_lite0" }, + .csid = { + .is_lite = true, + .hw_ops = &csid_ops_gen2, + .parent_dev_ops = &vfe_parent_dev_ops, + .formats = &csid_formats_gen2 + } + }, + /* CSID4 */ + { + .regulators = {}, + + .clock = { "vfe_lite1_csid", "vfe_lite1_cphy_rx", "vfe_lite1" }, + .clock_rate = { { 300000000, 400000000 }, + { 0 }, + { 320000000, 400000000, 480000000, 600000000 } + }, + + .reg = { "csid_lite1" }, + .interrupt = { "csid_lite1" }, + .csid = { + .is_lite = true, + .hw_ops = &csid_ops_gen2, + .parent_dev_ops = &vfe_parent_dev_ops, + .formats = &csid_formats_gen2 + } + }, +}; + +static const struct camss_subdev_resources vfe_res_7280[] = { + /* VFE0 */ + { + .regulators = {}, + + .clock = { "camnoc_axi", "cpas_ahb", "icp_ahb", "vfe0", + "vfe0_axi", "gcc_cam_hf_axi" }, + .clock_rate = { { 150000000, 240000000, 320000000, 400000000, 480000000 }, + { 80000000 }, + { 0 }, + { 380000000, 510000000, 637000000, 760000000 }, + { 0 }, + { 0 } }, + + .reg = { "vfe0" }, + .interrupt = { "vfe0" }, + .vfe = { + .line_num = 3, + .is_lite = false, + .has_pd = true, + .pd_name = "ife0", + .hw_ops = &vfe_ops_170, + .formats_rdi = &vfe_formats_rdi_845, + .formats_pix = &vfe_formats_pix_845 + } + }, + /* VFE1 */ + { + .regulators = {}, + + .clock = { "camnoc_axi", "cpas_ahb", "icp_ahb", "vfe1", + "vfe1_axi", "gcc_cam_hf_axi" }, + .clock_rate = { { 150000000, 240000000, 320000000, 400000000, 480000000 }, + { 80000000 }, + { 0 }, + { 380000000, 510000000, 637000000, 760000000 }, + { 0 }, + { 0 } }, + + .reg = { "vfe1" }, + .interrupt = { "vfe1" }, + .vfe = { + .line_num = 3, + .is_lite = false, + .has_pd = true, + .pd_name = "ife1", + .hw_ops = &vfe_ops_170, + .formats_rdi = &vfe_formats_rdi_845, + .formats_pix = &vfe_formats_pix_845 + } + }, + /* VFE2 */ + { + .regulators = {}, + + .clock = { "camnoc_axi", "cpas_ahb", "icp_ahb", "vfe2", + "vfe2_axi", "gcc_cam_hf_axi" }, + .clock_rate = { { 150000000, 240000000, 320000000, 400000000, 480000000 }, + { 80000000 }, + { 0 }, + { 380000000, 510000000, 637000000, 760000000 }, + { 0 }, + { 0 } }, + + .reg = { "vfe2" }, + .interrupt = { "vfe2" }, + .vfe = { + .line_num = 3, + .is_lite = false, + .hw_ops = &vfe_ops_170, + .has_pd = true, + .pd_name = "ife2", + .formats_rdi = &vfe_formats_rdi_845, + .formats_pix = &vfe_formats_pix_845 + } + }, + /* VFE3 (lite) */ + { + .clock = { "camnoc_axi", "cpas_ahb", "icp_ahb", + "vfe_lite0", "gcc_cam_hf_axi" }, + .clock_rate = { { 150000000, 240000000, 320000000, 400000000, 480000000 }, + { 80000000 }, + { 0 }, + { 320000000, 400000000, 480000000, 600000000 }, + { 0 } }, + + .regulators = {}, + .reg = { "vfe_lite0" }, + .interrupt = { "vfe_lite0" }, + .vfe = { + .line_num = 4, + .is_lite = true, + .hw_ops = &vfe_ops_170, + .formats_rdi = &vfe_formats_rdi_845, + .formats_pix = &vfe_formats_pix_845 + } + }, + /* VFE4 (lite) */ + { + .clock = { "camnoc_axi", "cpas_ahb", "icp_ahb", + "vfe_lite1", "gcc_cam_hf_axi" }, + .clock_rate = { { 150000000, 240000000, 320000000, 400000000, 480000000 }, + { 80000000 }, + { 0 }, + { 320000000, 400000000, 480000000, 600000000 }, + { 0 } }, + + .regulators = {}, + .reg = { "vfe_lite1" }, + .interrupt = { "vfe_lite1" }, + .vfe = { + .line_num = 4, + .is_lite = true, + .hw_ops = &vfe_ops_170, + .formats_rdi = &vfe_formats_rdi_845, + .formats_pix = &vfe_formats_pix_845 + } + }, +}; + +static const struct resources_icc icc_res_sc7280[] = { + { + .name = "ahb", + .icc_bw_tbl.avg = 38400, + .icc_bw_tbl.peak = 76800, + }, + { + .name = "hf_0", + .icc_bw_tbl.avg = 2097152, + .icc_bw_tbl.peak = 2097152, + }, +}; + static const struct camss_subdev_resources csiphy_res_sc8280xp[] = { /* CSIPHY0 */ { @@ -1993,6 +2297,24 @@ static int camss_init_subdevices(struct camss *camss) return 0; } +/* + * camss_link_entities - Register subdev nodes and create links + * camss_link_err - print error in case link creation fails + * @src_name: name for source of the link + * @sink_name: name for sink of the link + */ +inline void camss_link_err(struct camss *camss, + const char *src_name, + const char *sink_name, + int ret) +{ + dev_err(camss->dev, + "Failed to link %s->%s entities: %d\n", + src_name, + sink_name, + ret); +} + /* * camss_link_entities - Register subdev nodes and create links * @camss: CAMSS device @@ -2012,11 +2334,10 @@ static int camss_link_entities(struct camss *camss) MSM_CSID_PAD_SINK, 0); if (ret < 0) { - dev_err(camss->dev, - "Failed to link %s->%s entities: %d\n", - camss->csiphy[i].subdev.entity.name, - camss->csid[j].subdev.entity.name, - ret); + camss_link_err(camss, + camss->csiphy[i].subdev.entity.name, + camss->csid[j].subdev.entity.name, + ret); return ret; } } @@ -2031,11 +2352,10 @@ static int camss_link_entities(struct camss *camss) MSM_ISPIF_PAD_SINK, 0); if (ret < 0) { - dev_err(camss->dev, - "Failed to link %s->%s entities: %d\n", - camss->csid[i].subdev.entity.name, - camss->ispif->line[j].subdev.entity.name, - ret); + camss_link_err(camss, + camss->csid[i].subdev.entity.name, + camss->ispif->line[j].subdev.entity.name, + ret); return ret; } } @@ -2053,11 +2373,9 @@ static int camss_link_entities(struct camss *camss) MSM_VFE_PAD_SINK, 0); if (ret < 0) { - dev_err(camss->dev, - "Failed to link %s->%s entities: %d\n", - ispif->entity.name, - vfe->entity.name, - ret); + camss_link_err(camss, ispif->entity.name, + vfe->entity.name, + ret); return ret; } } @@ -2074,11 +2392,9 @@ static int camss_link_entities(struct camss *camss) MSM_VFE_PAD_SINK, 0); if (ret < 0) { - dev_err(camss->dev, - "Failed to link %s->%s entities: %d\n", - csid->entity.name, - vfe->entity.name, - ret); + camss_link_err(camss, csid->entity.name, + vfe->entity.name, + ret); return ret; } } @@ -2227,9 +2543,9 @@ static int camss_subdev_notifier_complete(struct v4l2_async_notifier *async) input, MSM_CSIPHY_PAD_SINK, MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED); if (ret < 0) { - dev_err(camss->dev, - "Failed to link %s->%s entities: %d\n", - sensor->name, input->name, ret); + camss_link_err(camss, sensor->name, + input->name, + ret); return ret; } } @@ -2622,14 +2938,29 @@ static const struct camss_resources sc8280xp_resources = { .link_entities = camss_link_entities }; +static const struct camss_resources sc7280_resources = { + .version = CAMSS_7280, + .pd_name = "top", + .csiphy_res = csiphy_res_7280, + .csid_res = csid_res_7280, + .vfe_res = vfe_res_7280, + .icc_res = icc_res_sc7280, + .icc_path_num = ARRAY_SIZE(icc_res_sc7280), + .csiphy_num = ARRAY_SIZE(csiphy_res_7280), + .csid_num = ARRAY_SIZE(csid_res_7280), + .vfe_num = ARRAY_SIZE(vfe_res_7280), + .link_entities = camss_link_entities +}; + static const struct of_device_id camss_dt_match[] = { { .compatible = "qcom,msm8916-camss", .data = &msm8916_resources }, { .compatible = "qcom,msm8953-camss", .data = &msm8953_resources }, { .compatible = "qcom,msm8996-camss", .data = &msm8996_resources }, + { .compatible = "qcom,sc7280-camss", .data = &sc7280_resources }, + { .compatible = "qcom,sc8280xp-camss", .data = &sc8280xp_resources }, { .compatible = "qcom,sdm660-camss", .data = &sdm660_resources }, { .compatible = "qcom,sdm845-camss", .data = &sdm845_resources }, { .compatible = "qcom,sm8250-camss", .data = &sm8250_resources }, - { .compatible = "qcom,sc8280xp-camss", .data = &sc8280xp_resources }, { } }; diff --git a/drivers/media/platform/qcom/camss/camss.h b/drivers/media/platform/qcom/camss/camss.h index 9da7f48f5dd7..9a046eea334f 100644 --- a/drivers/media/platform/qcom/camss/camss.h +++ b/drivers/media/platform/qcom/camss/camss.h @@ -77,13 +77,14 @@ enum pm_domain { }; enum camss_version { + CAMSS_660, + CAMSS_7280, CAMSS_8x16, CAMSS_8x53, CAMSS_8x96, - CAMSS_660, - CAMSS_845, CAMSS_8250, CAMSS_8280XP, + CAMSS_845, }; enum icc_count { diff --git a/drivers/media/platform/qcom/venus/Kconfig b/drivers/media/platform/qcom/venus/Kconfig index bfd50e8f3421..bc2e410b29cb 100644 --- a/drivers/media/platform/qcom/venus/Kconfig +++ b/drivers/media/platform/qcom/venus/Kconfig @@ -3,6 +3,7 @@ config VIDEO_QCOM_VENUS depends on V4L_MEM2MEM_DRIVERS depends on VIDEO_DEV && QCOM_SMEM depends on (ARCH_QCOM && IOMMU_DMA) || COMPILE_TEST + select OF_DYNAMIC if ARCH_QCOM select QCOM_MDT_LOADER if ARCH_QCOM select QCOM_SCM select VIDEOBUF2_DMA_CONTIG diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c index 2d27c5167246..77d48578ecd2 100644 --- a/drivers/media/platform/qcom/venus/core.c +++ b/drivers/media/platform/qcom/venus/core.c @@ -286,6 +286,89 @@ static irqreturn_t venus_isr_thread(int irq, void *dev_id) return ret; } +#if defined(CONFIG_OF_DYNAMIC) +static int venus_add_video_core(struct venus_core *core, const char *node_name, + const char *compat) +{ + struct of_changeset *ocs = core->ocs; + struct device *dev = core->dev; + struct device_node *np, *enp; + int ret; + + if (!node_name) + return 0; + + enp = of_find_node_by_name(dev->of_node, node_name); + if (enp) { + of_node_put(enp); + return 0; + } + + np = of_changeset_create_node(ocs, dev->of_node, node_name); + if (!np) { + dev_err(dev, "Unable to create new node\n"); + return -ENODEV; + } + + ret = of_changeset_add_prop_string(ocs, np, "compatible", compat); + if (ret) + dev_err(dev, "unable to add %s\n", compat); + + of_node_put(np); + + return ret; +} + +static int venus_add_dynamic_nodes(struct venus_core *core) +{ + struct device *dev = core->dev; + int ret; + + core->ocs = kmalloc(sizeof(*core->ocs), GFP_KERNEL); + if (!core->ocs) + return -ENOMEM; + + of_changeset_init(core->ocs); + + ret = venus_add_video_core(core, core->res->dec_nodename, "venus-decoder"); + if (ret) + goto err; + + ret = venus_add_video_core(core, core->res->enc_nodename, "venus-encoder"); + if (ret) + goto err; + + ret = of_changeset_apply(core->ocs); + if (ret) { + dev_err(dev, "applying changeset fail ret %d\n", ret); + goto err; + } + + return 0; +err: + of_changeset_destroy(core->ocs); + kfree(core->ocs); + core->ocs = NULL; + return ret; +} + +static void venus_remove_dynamic_nodes(struct venus_core *core) +{ + if (core->ocs) { + of_changeset_revert(core->ocs); + of_changeset_destroy(core->ocs); + kfree(core->ocs); + } +} +#else +static int venus_add_dynamic_nodes(struct venus_core *core) +{ + return 0; +} + +static void venus_remove_dynamic_nodes(struct venus_core *core) {} +#endif + static int venus_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -365,9 +448,15 @@ static int venus_probe(struct platform_device *pdev) if (ret < 0) goto err_runtime_disable; + if (core->res->dec_nodename || core->res->enc_nodename) { + ret = venus_add_dynamic_nodes(core); + if (ret) + goto err_runtime_disable; + } + ret = of_platform_populate(dev->of_node, NULL, NULL, dev); if (ret) - goto err_runtime_disable; + goto err_remove_dynamic_nodes; ret = venus_firmware_init(core); if (ret) @@ -411,6 +500,8 @@ err_firmware_deinit: venus_firmware_deinit(core); err_of_depopulate: of_platform_depopulate(dev); +err_remove_dynamic_nodes: + venus_remove_dynamic_nodes(core); err_runtime_disable: pm_runtime_put_noidle(dev); pm_runtime_disable(dev); @@ -443,6 +534,8 @@ static void venus_remove(struct platform_device *pdev) venus_firmware_deinit(core); + venus_remove_dynamic_nodes(core); + pm_runtime_put_sync(dev); pm_runtime_disable(dev); @@ -506,18 +599,14 @@ err_cpucfg_path: void venus_close_common(struct venus_inst *inst) { /* - * First, remove the inst from the ->instances list, so that - * to_instance() will return NULL. - */ - hfi_session_destroy(inst); - /* - * Second, make sure we don't have IRQ/IRQ-thread currently running + * Make sure we don't have IRQ/IRQ-thread currently running * or pending execution, which would race with the inst destruction. */ synchronize_irq(inst->core->irq); v4l2_m2m_ctx_release(inst->m2m_ctx); v4l2_m2m_release(inst->m2m_dev); + hfi_session_destroy(inst); v4l2_fh_del(&inst->fh); v4l2_fh_exit(&inst->fh); v4l2_ctrl_handler_free(&inst->ctrl_handler); @@ -582,6 +671,8 @@ static const struct venus_resources msm8916_res = { .vmem_addr = 0, .dma_mask = 0xddc00000 - 1, .fwname = "qcom/venus-1.8/venus.mbn", + .dec_nodename = "video-decoder", + .enc_nodename = "video-encoder", }; static const struct freq_tbl msm8996_freq_table[] = { @@ -791,6 +882,8 @@ static const struct venus_resources sdm845_res_v2 = { .cp_nonpixel_start = 0x1000000, .cp_nonpixel_size = 0x24800000, .fwname = "qcom/venus-5.2/venus.mbn", + .dec_nodename = "video-core0", + .enc_nodename = "video-core1", }; static const struct freq_tbl sc7180_freq_table[] = { @@ -839,6 +932,8 @@ static const struct venus_resources sc7180_res = { .cp_nonpixel_start = 0x1000000, .cp_nonpixel_size = 0x24800000, .fwname = "qcom/venus-5.4/venus.mbn", + .dec_nodename = "video-decoder", + .enc_nodename = "video-encoder", }; static const struct freq_tbl sm8250_freq_table[] = { @@ -894,6 +989,8 @@ static const struct venus_resources sm8250_res = { .vmem_addr = 0, .dma_mask = 0xe0000000 - 1, .fwname = "qcom/vpu-1.0/venus.mbn", + .dec_nodename = "video-decoder", + .enc_nodename = "video-encoder", }; static const struct freq_tbl sc7280_freq_table[] = { @@ -956,6 +1053,8 @@ static const struct venus_resources sc7280_res = { .cp_nonpixel_start = 0x1000000, .cp_nonpixel_size = 0x24800000, .fwname = "qcom/vpu-2.0/venus.mbn", + .dec_nodename = "video-decoder", + .enc_nodename = "video-encoder", }; static const struct of_device_id venus_dt_match[] = { diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h index 44f1c3bc4186..abeeafa86697 100644 --- a/drivers/media/platform/qcom/venus/core.h +++ b/drivers/media/platform/qcom/venus/core.h @@ -90,6 +90,8 @@ struct venus_resources { u32 cp_nonpixel_start; u32 cp_nonpixel_size; const char *fwname; + const char *enc_nodename; + const char *dec_nodename; }; enum venus_fmt { @@ -169,6 +171,7 @@ struct venus_format { * @root: debugfs root directory * @venus_ver: the venus firmware version * @dump_core: a flag indicating that a core dump is required + * @ocs: OF changeset pointer */ struct venus_core { void __iomem *base; @@ -231,6 +234,7 @@ struct venus_core { u32 rev; } venus_ver; unsigned long dump_core; + struct of_changeset *ocs; }; struct vdec_controls { diff --git a/drivers/media/platform/qcom/venus/hfi.c b/drivers/media/platform/qcom/venus/hfi.c index e00aedb41d16..675e6fd1e9fa 100644 --- a/drivers/media/platform/qcom/venus/hfi.c +++ b/drivers/media/platform/qcom/venus/hfi.c @@ -138,29 +138,6 @@ int hfi_core_trigger_ssr(struct venus_core *core, u32 type) return core->ops->core_trigger_ssr(core, type); } -int hfi_core_ping(struct venus_core *core) -{ - int ret; - - mutex_lock(&core->lock); - - ret = core->ops->core_ping(core, 0xbeef); - if (ret) - goto unlock; - - ret = wait_for_completion_timeout(&core->done, TIMEOUT); - if (!ret) { - ret = -ETIMEDOUT; - goto unlock; - } - ret = 0; - if (core->error != HFI_ERR_NONE) - ret = -ENODEV; -unlock: - mutex_unlock(&core->lock); - return ret; -} - static int wait_session_msg(struct venus_inst *inst) { int ret; diff --git a/drivers/media/platform/qcom/venus/hfi.h b/drivers/media/platform/qcom/venus/hfi.h index f25d412d6553..0338841d5992 100644 --- a/drivers/media/platform/qcom/venus/hfi.h +++ b/drivers/media/platform/qcom/venus/hfi.h @@ -108,7 +108,6 @@ struct hfi_inst_ops { struct hfi_ops { int (*core_init)(struct venus_core *core); int (*core_deinit)(struct venus_core *core); - int (*core_ping)(struct venus_core *core, u32 cookie); int (*core_trigger_ssr)(struct venus_core *core, u32 trigger_type); int (*session_init)(struct venus_inst *inst, u32 session_type, @@ -152,7 +151,6 @@ int hfi_core_deinit(struct venus_core *core, bool blocking); int hfi_core_suspend(struct venus_core *core); int hfi_core_resume(struct venus_core *core, bool force); int hfi_core_trigger_ssr(struct venus_core *core, u32 type); -int hfi_core_ping(struct venus_core *core); int hfi_session_create(struct venus_inst *inst, const struct hfi_inst_ops *ops); void hfi_session_destroy(struct venus_inst *inst); int hfi_session_init(struct venus_inst *inst, u32 pixfmt); diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c index f9437b6412b9..a9167867063c 100644 --- a/drivers/media/platform/qcom/venus/hfi_venus.c +++ b/drivers/media/platform/qcom/venus/hfi_venus.c @@ -1178,16 +1178,6 @@ static int venus_core_deinit(struct venus_core *core) return 0; } -static int venus_core_ping(struct venus_core *core, u32 cookie) -{ - struct venus_hfi_device *hdev = to_hfi_priv(core); - struct hfi_sys_ping_pkt pkt; - - pkt_sys_ping(&pkt, cookie); - - return venus_iface_cmdq_write(hdev, &pkt, false); -} - static int venus_core_trigger_ssr(struct venus_core *core, u32 trigger_type) { struct venus_hfi_device *hdev = to_hfi_priv(core); @@ -1639,7 +1629,6 @@ static int venus_suspend(struct venus_core *core) static const struct hfi_ops venus_hfi_ops = { .core_init = venus_core_init, .core_deinit = venus_core_deinit, - .core_ping = venus_core_ping, .core_trigger_ssr = venus_core_trigger_ssr, .session_init = venus_session_init, diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 98c22b9f9372..9f82882b77bc 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -1697,10 +1697,6 @@ static int vdec_open(struct file *file) if (ret) goto err_free; - ret = hfi_session_create(inst, &vdec_hfi_ops); - if (ret) - goto err_ctrl_deinit; - vdec_inst_init(inst); ida_init(&inst->dpb_ids); @@ -1712,15 +1708,19 @@ static int vdec_open(struct file *file) inst->m2m_dev = v4l2_m2m_init(&vdec_m2m_ops); if (IS_ERR(inst->m2m_dev)) { ret = PTR_ERR(inst->m2m_dev); - goto err_session_destroy; + goto err_ctrl_deinit; } inst->m2m_ctx = v4l2_m2m_ctx_init(inst->m2m_dev, inst, m2m_queue_init); if (IS_ERR(inst->m2m_ctx)) { ret = PTR_ERR(inst->m2m_ctx); - goto err_m2m_release; + goto err_m2m_dev_release; } + ret = hfi_session_create(inst, &vdec_hfi_ops); + if (ret) + goto err_m2m_ctx_release; + v4l2_fh_init(&inst->fh, core->vdev_dec); inst->fh.ctrl_handler = &inst->ctrl_handler; @@ -1730,10 +1730,10 @@ static int vdec_open(struct file *file) return 0; -err_m2m_release: +err_m2m_ctx_release: + v4l2_m2m_ctx_release(inst->m2m_ctx); +err_m2m_dev_release: v4l2_m2m_release(inst->m2m_dev); -err_session_destroy: - hfi_session_destroy(inst); err_ctrl_deinit: v4l2_ctrl_handler_free(&inst->ctrl_handler); err_free: diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c index c1c543535aaf..c7f8e37dba9b 100644 --- a/drivers/media/platform/qcom/venus/venc.c +++ b/drivers/media/platform/qcom/venus/venc.c @@ -1492,10 +1492,6 @@ static int venc_open(struct file *file) if (ret) goto err_free; - ret = hfi_session_create(inst, &venc_hfi_ops); - if (ret) - goto err_ctrl_deinit; - venc_inst_init(inst); /* @@ -1505,15 +1501,19 @@ static int venc_open(struct file *file) inst->m2m_dev = v4l2_m2m_init(&venc_m2m_ops); if (IS_ERR(inst->m2m_dev)) { ret = PTR_ERR(inst->m2m_dev); - goto err_session_destroy; + goto err_ctrl_deinit; } inst->m2m_ctx = v4l2_m2m_ctx_init(inst->m2m_dev, inst, m2m_queue_init); if (IS_ERR(inst->m2m_ctx)) { ret = PTR_ERR(inst->m2m_ctx); - goto err_m2m_release; + goto err_m2m_dev_release; } + ret = hfi_session_create(inst, &venc_hfi_ops); + if (ret) + goto err_m2m_ctx_release; + v4l2_fh_init(&inst->fh, core->vdev_enc); inst->fh.ctrl_handler = &inst->ctrl_handler; @@ -1523,10 +1523,10 @@ static int venc_open(struct file *file) return 0; -err_m2m_release: +err_m2m_ctx_release: + v4l2_m2m_ctx_release(inst->m2m_ctx); +err_m2m_dev_release: v4l2_m2m_release(inst->m2m_dev); -err_session_destroy: - hfi_session_destroy(inst); err_ctrl_deinit: v4l2_ctrl_handler_free(&inst->ctrl_handler); err_free: diff --git a/drivers/media/platform/renesas/rcar-csi2.c b/drivers/media/platform/renesas/rcar-csi2.c index 27ffdd28cbf7..0a53dd47d7bf 100644 --- a/drivers/media/platform/renesas/rcar-csi2.c +++ b/drivers/media/platform/renesas/rcar-csi2.c @@ -183,17 +183,19 @@ struct rcar_csi2; #define V4H_CORE_DIG_IOCTRL_RW_AFE_CB_CTRL_2_REG(n) (0x23840 + ((n) * 2)) /* n = 0 - 11 */ #define V4H_CORE_DIG_RW_COMMON_REG(n) (0x23880 + ((n) * 2)) /* n = 0 - 15 */ #define V4H_CORE_DIG_ANACTRL_RW_COMMON_ANACTRL_REG(n) (0x239e0 + ((n) * 2)) /* n = 0 - 3 */ -#define V4H_CORE_DIG_CLANE_1_RW_CFG_0_REG 0x2a400 #define V4H_CORE_DIG_CLANE_1_RW_HS_TX_6_REG 0x2a60c /* V4H C-PHY */ #define V4H_CORE_DIG_RW_TRIO0_REG(n) (0x22100 + ((n) * 2)) /* n = 0 - 3 */ #define V4H_CORE_DIG_RW_TRIO1_REG(n) (0x22500 + ((n) * 2)) /* n = 0 - 3 */ #define V4H_CORE_DIG_RW_TRIO2_REG(n) (0x22900 + ((n) * 2)) /* n = 0 - 3 */ +#define V4H_CORE_DIG_CLANE_0_RW_CFG_0_REG 0x2a000 #define V4H_CORE_DIG_CLANE_0_RW_LP_0_REG 0x2a080 #define V4H_CORE_DIG_CLANE_0_RW_HS_RX_REG(n) (0x2a100 + ((n) * 2)) /* n = 0 - 6 */ +#define V4H_CORE_DIG_CLANE_1_RW_CFG_0_REG 0x2a400 #define V4H_CORE_DIG_CLANE_1_RW_LP_0_REG 0x2a480 #define V4H_CORE_DIG_CLANE_1_RW_HS_RX_REG(n) (0x2a500 + ((n) * 2)) /* n = 0 - 6 */ +#define V4H_CORE_DIG_CLANE_2_RW_CFG_0_REG 0x2a800 #define V4H_CORE_DIG_CLANE_2_RW_LP_0_REG 0x2a880 #define V4H_CORE_DIG_CLANE_2_RW_HS_RX_REG(n) (0x2a900 + ((n) * 2)) /* n = 0 - 6 */ @@ -672,6 +674,21 @@ static const struct rcar_csi2_format *rcsi2_code_to_fmt(unsigned int code) return NULL; } +struct rcsi2_cphy_line_order { + enum v4l2_mbus_csi2_cphy_line_orders_type order; + u16 cfg; + u16 ctrl29; +}; + +static const struct rcsi2_cphy_line_order rcsi2_cphy_line_orders[] = { + { .order = V4L2_MBUS_CSI2_CPHY_LINE_ORDER_ABC, .cfg = 0x0, .ctrl29 = 0x0 }, + { .order = V4L2_MBUS_CSI2_CPHY_LINE_ORDER_ACB, .cfg = 0xa, .ctrl29 = 0x1 }, + { .order = V4L2_MBUS_CSI2_CPHY_LINE_ORDER_BAC, .cfg = 0xc, .ctrl29 = 0x1 }, + { .order = V4L2_MBUS_CSI2_CPHY_LINE_ORDER_BCA, .cfg = 0x5, .ctrl29 = 0x0 }, + { .order = V4L2_MBUS_CSI2_CPHY_LINE_ORDER_CAB, .cfg = 0x3, .ctrl29 = 0x0 }, + { .order = V4L2_MBUS_CSI2_CPHY_LINE_ORDER_CBA, .cfg = 0x9, .ctrl29 = 0x1 } +}; + enum rcar_csi2_pads { RCAR_CSI2_SINK, RCAR_CSI2_SOURCE_VC0, @@ -722,6 +739,7 @@ struct rcar_csi2 { bool cphy; unsigned short lanes; unsigned char lane_swap[4]; + enum v4l2_mbus_csi2_cphy_line_orders_type line_orders[3]; }; static inline struct rcar_csi2 *sd_to_csi2(struct v4l2_subdev *sd) @@ -754,11 +772,24 @@ static void rcsi2_write(struct rcar_csi2 *priv, unsigned int reg, u32 data) iowrite32(data, priv->base + reg); } +static u16 rcsi2_read16(struct rcar_csi2 *priv, unsigned int reg) +{ + return ioread16(priv->base + reg); +} + static void rcsi2_write16(struct rcar_csi2 *priv, unsigned int reg, u16 data) { iowrite16(data, priv->base + reg); } +static void rcsi2_modify16(struct rcar_csi2 *priv, unsigned int reg, u16 data, u16 mask) +{ + u16 val; + + val = rcsi2_read16(priv, reg) & ~mask; + rcsi2_write16(priv, reg, val | data); +} + static int rcsi2_phtw_write(struct rcar_csi2 *priv, u8 data, u8 code) { unsigned int timeout; @@ -1112,6 +1143,26 @@ static int rcsi2_start_receiver_gen3(struct rcar_csi2 *priv, return 0; } +static void rsci2_set_line_order(struct rcar_csi2 *priv, + enum v4l2_mbus_csi2_cphy_line_orders_type order, + unsigned int cfgreg, unsigned int ctrlreg) +{ + const struct rcsi2_cphy_line_order *info = NULL; + + for (unsigned int i = 0; i < ARRAY_SIZE(rcsi2_cphy_line_orders); i++) { + if (rcsi2_cphy_line_orders[i].order == order) { + info = &rcsi2_cphy_line_orders[i]; + break; + } + } + + if (!info) + return; + + rcsi2_modify16(priv, cfgreg, info->cfg, 0x000f); + rcsi2_modify16(priv, ctrlreg, info->ctrl29, 0x0100); +} + static int rcsi2_wait_phy_start_v4h(struct rcar_csi2 *priv, u32 match) { unsigned int timeout; @@ -1189,12 +1240,18 @@ static int rcsi2_c_phy_setting_v4h(struct rcar_csi2 *priv, int msps) rcsi2_write16(priv, V4H_CORE_DIG_RW_TRIO1_REG(1), conf->trio1); rcsi2_write16(priv, V4H_CORE_DIG_RW_TRIO2_REG(1), conf->trio1); - /* - * Configure pin-swap. - * TODO: This registers is not documented yet, the values should depend - * on the 'clock-lanes' and 'data-lanes' devicetree properties. - */ - rcsi2_write16(priv, V4H_CORE_DIG_CLANE_1_RW_CFG_0_REG, 0xf5); + /* Configure data line order. */ + rsci2_set_line_order(priv, priv->line_orders[0], + V4H_CORE_DIG_CLANE_0_RW_CFG_0_REG, + V4H_CORE_DIG_IOCTRL_RW_AFE_LANE0_CTRL_2_REG(9)); + rsci2_set_line_order(priv, priv->line_orders[1], + V4H_CORE_DIG_CLANE_1_RW_CFG_0_REG, + V4H_CORE_DIG_IOCTRL_RW_AFE_LANE1_CTRL_2_REG(9)); + rsci2_set_line_order(priv, priv->line_orders[2], + V4H_CORE_DIG_CLANE_2_RW_CFG_0_REG, + V4H_CORE_DIG_IOCTRL_RW_AFE_LANE2_CTRL_2_REG(9)); + + /* TODO: This registers is not documented. */ rcsi2_write16(priv, V4H_CORE_DIG_CLANE_1_RW_HS_TX_6_REG, 0x5000); /* Leave Shutdown mode */ @@ -1349,15 +1406,15 @@ static int rcsi2_init_common_v4m(struct rcar_csi2 *priv, unsigned int mbps) static const struct phtw_value step2[] = { { .data = 0x00, .code = 0x00 }, { .data = 0x80, .code = 0xe0 }, - { .data = 0x01, .code = 0xe1 }, + { .data = 0x31, .code = 0xe1 }, { .data = 0x06, .code = 0x00 }, - { .data = 0x0f, .code = 0x11 }, + { .data = 0x11, .code = 0x11 }, { .data = 0x08, .code = 0x00 }, - { .data = 0x0f, .code = 0x11 }, + { .data = 0x11, .code = 0x11 }, { .data = 0x0a, .code = 0x00 }, - { .data = 0x0f, .code = 0x11 }, + { .data = 0x11, .code = 0x11 }, { .data = 0x0c, .code = 0x00 }, - { .data = 0x0f, .code = 0x11 }, + { .data = 0x11, .code = 0x11 }, { .data = 0x01, .code = 0x00 }, { .data = 0x31, .code = 0xaa }, { .data = 0x05, .code = 0x00 }, @@ -1370,6 +1427,11 @@ static int rcsi2_init_common_v4m(struct rcar_csi2 *priv, unsigned int mbps) { .data = 0x05, .code = 0x09 }, }; + static const struct phtw_value step3[] = { + { .data = 0x01, .code = 0x00 }, + { .data = 0x06, .code = 0xab }, + }; + if (priv->info->hsfreqrange) { ret = rcsi2_set_phypll(priv, mbps); if (ret) @@ -1400,7 +1462,7 @@ static int rcsi2_init_common_v4m(struct rcar_csi2 *priv, unsigned int mbps) return ret; } - return ret; + return rcsi2_phtw_write_array(priv, step3, ARRAY_SIZE(step3)); } static int rcsi2_start_receiver_v4m(struct rcar_csi2 *priv, @@ -1732,6 +1794,9 @@ static int rcsi2_parse_v4l2(struct rcar_csi2 *priv, } } + for (i = 0; i < ARRAY_SIZE(priv->line_orders); i++) + priv->line_orders[i] = vep->bus.mipi_csi2.line_orders[i]; + return 0; } diff --git a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-video.c b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-video.c index 17a1af507a27..cd69c8a686d3 100644 --- a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-video.c +++ b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-video.c @@ -558,7 +558,7 @@ static int rzg2l_cru_start_streaming_vq(struct vb2_queue *vq, unsigned int count goto assert_aresetn; } - /* Allocate scratch buffer. */ + /* Allocate scratch buffer */ cru->scratch = dma_alloc_coherent(cru->dev, cru->format.sizeimage, &cru->scratch_phys, GFP_KERNEL); if (!cru->scratch) { diff --git a/drivers/media/platform/rockchip/rga/rga-buf.c b/drivers/media/platform/rockchip/rga/rga-buf.c index 8a48e9d91f96..4396348811c8 100644 --- a/drivers/media/platform/rockchip/rga/rga-buf.c +++ b/drivers/media/platform/rockchip/rga/rga-buf.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2017 Fuzhou Rockchip Electronics Co.Ltd + * Copyright (C) 2017 Rockchip Electronics Co., Ltd. * Author: Jacob Chen */ diff --git a/drivers/media/platform/rockchip/rga/rga-hw.c b/drivers/media/platform/rockchip/rga/rga-hw.c index 11c3d7234757..bf55beec0fac 100644 --- a/drivers/media/platform/rockchip/rga/rga-hw.c +++ b/drivers/media/platform/rockchip/rga/rga-hw.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Copyright (C) Rockchip Electronics Co., Ltd. * Author: Jacob Chen */ diff --git a/drivers/media/platform/rockchip/rga/rga-hw.h b/drivers/media/platform/rockchip/rga/rga-hw.h index e8917e5630a4..cc6bd7f5b030 100644 --- a/drivers/media/platform/rockchip/rga/rga-hw.h +++ b/drivers/media/platform/rockchip/rga/rga-hw.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Copyright (C) Rockchip Electronics Co., Ltd. * Author: Jacob Chen */ #ifndef __RGA_HW_H__ diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c index 1739ac0c8e92..3dccab5fa4a1 100644 --- a/drivers/media/platform/rockchip/rga/rga.c +++ b/drivers/media/platform/rockchip/rga/rga.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Copyright (C) Rockchip Electronics Co., Ltd. * Author: Jacob Chen */ diff --git a/drivers/media/platform/rockchip/rga/rga.h b/drivers/media/platform/rockchip/rga/rga.h index 8105bb2efe57..530e12de73c4 100644 --- a/drivers/media/platform/rockchip/rga/rga.h +++ b/drivers/media/platform/rockchip/rga/rga.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Copyright (C) Rockchip Electronics Co., Ltd. * Author: Jacob Chen */ #ifndef __RGA_H__ diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c index 02339cd94486..6dcefd144d5a 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c @@ -35,8 +35,6 @@ #define RKISP1_SP_DEV_NAME RKISP1_DRIVER_NAME "_selfpath" #define RKISP1_MP_DEV_NAME RKISP1_DRIVER_NAME "_mainpath" -#define RKISP1_MIN_BUFFERS_NEEDED 3 - enum rkisp1_plane { RKISP1_PLANE_Y = 0, RKISP1_PLANE_CB = 1, @@ -1561,7 +1559,7 @@ static int rkisp1_register_capture(struct rkisp1_capture *cap) q->ops = &rkisp1_vb2_ops; q->mem_ops = &vb2_dma_contig_memops; q->buf_struct_size = sizeof(struct rkisp1_buffer); - q->min_queued_buffers = RKISP1_MIN_BUFFERS_NEEDED; + q->min_queued_buffers = 1; q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; q->lock = &node->vlock; q->dev = cap->rkisp1->dev; diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c index 0100b9c3edbe..dc65a7924f8a 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c @@ -228,6 +228,9 @@ static int rkisp1_subdev_notifier_register(struct rkisp1_device *rkisp1) break; } + if (ret) + break; + /* Parse the endpoint and validate the bus type. */ ret = v4l2_fwnode_endpoint_parse(ep, &vep); if (ret) { diff --git a/drivers/media/platform/samsung/exynos4-is/fimc-is-errno.c b/drivers/media/platform/samsung/exynos4-is/fimc-is-errno.c index 7a48fad1df16..ac67a04e5eeb 100644 --- a/drivers/media/platform/samsung/exynos4-is/fimc-is-errno.c +++ b/drivers/media/platform/samsung/exynos4-is/fimc-is-errno.c @@ -12,137 +12,6 @@ #include "fimc-is-errno.h" -const char *fimc_is_param_strerr(unsigned int error) -{ - switch (error) { - case ERROR_COMMON_CMD: - return "ERROR_COMMON_CMD: Invalid Command"; - case ERROR_COMMON_PARAMETER: - return "ERROR_COMMON_PARAMETER: Invalid Parameter"; - case ERROR_COMMON_SETFILE_LOAD: - return "ERROR_COMMON_SETFILE_LOAD: Illegal Setfile Loading"; - case ERROR_COMMON_SETFILE_ADJUST: - return "ERROR_COMMON_SETFILE_ADJUST: Setfile isn't adjusted"; - case ERROR_COMMON_SETFILE_INDEX: - return "ERROR_COMMON_SETFILE_INDEX: Invalid setfile index"; - case ERROR_COMMON_INPUT_PATH: - return "ERROR_COMMON_INPUT_PATH: Input path can be changed in ready state"; - case ERROR_COMMON_INPUT_INIT: - return "ERROR_COMMON_INPUT_INIT: IP can not start if input path is not set"; - case ERROR_COMMON_OUTPUT_PATH: - return "ERROR_COMMON_OUTPUT_PATH: Output path can be changed in ready state (stop)"; - case ERROR_COMMON_OUTPUT_INIT: - return "ERROR_COMMON_OUTPUT_INIT: IP can not start if output path is not set"; - case ERROR_CONTROL_BYPASS: - return "ERROR_CONTROL_BYPASS"; - case ERROR_OTF_INPUT_FORMAT: - return "ERROR_OTF_INPUT_FORMAT: Invalid format (DRC: YUV444, FD: YUV444, 422, 420)"; - case ERROR_OTF_INPUT_WIDTH: - return "ERROR_OTF_INPUT_WIDTH: Invalid width (DRC: 128~8192, FD: 32~8190)"; - case ERROR_OTF_INPUT_HEIGHT: - return "ERROR_OTF_INPUT_HEIGHT: Invalid bit-width (DRC: 8~12bits, FD: 8bit)"; - case ERROR_OTF_INPUT_BIT_WIDTH: - return "ERROR_OTF_INPUT_BIT_WIDTH: Invalid bit-width (DRC: 8~12bits, FD: 8bit)"; - case ERROR_DMA_INPUT_WIDTH: - return "ERROR_DMA_INPUT_WIDTH: Invalid width (DRC: 128~8192, FD: 32~8190)"; - case ERROR_DMA_INPUT_HEIGHT: - return "ERROR_DMA_INPUT_HEIGHT: Invalid height (DRC: 64~8192, FD: 16~8190)"; - case ERROR_DMA_INPUT_FORMAT: - return "ERROR_DMA_INPUT_FORMAT: Invalid format (DRC: YUV444 or YUV422, FD: YUV444,422,420)"; - case ERROR_DMA_INPUT_BIT_WIDTH: - return "ERROR_DMA_INPUT_BIT_WIDTH: Invalid bit-width (DRC: 8~12bits, FD: 8bit)"; - case ERROR_DMA_INPUT_ORDER: - return "ERROR_DMA_INPUT_ORDER: Invalid order(DRC: YYCbCr,YCbYCr,FD:NO,YYCbCr,YCbYCr,CbCr,CrCb)"; - case ERROR_DMA_INPUT_PLANE: - return "ERROR_DMA_INPUT_PLANE: Invalid plane (DRC: 3, FD: 1, 2, 3)"; - case ERROR_OTF_OUTPUT_WIDTH: - return "ERROR_OTF_OUTPUT_WIDTH: Invalid width (DRC: 128~8192)"; - case ERROR_OTF_OUTPUT_HEIGHT: - return "ERROR_OTF_OUTPUT_HEIGHT: Invalid height (DRC: 64~8192)"; - case ERROR_OTF_OUTPUT_FORMAT: - return "ERROR_OTF_OUTPUT_FORMAT: Invalid format (DRC: YUV444)"; - case ERROR_OTF_OUTPUT_BIT_WIDTH: - return "ERROR_OTF_OUTPUT_BIT_WIDTH: Invalid bit-width (DRC: 8~12bits, FD: 8bit)"; - case ERROR_DMA_OUTPUT_WIDTH: - return "ERROR_DMA_OUTPUT_WIDTH"; - case ERROR_DMA_OUTPUT_HEIGHT: - return "ERROR_DMA_OUTPUT_HEIGHT"; - case ERROR_DMA_OUTPUT_FORMAT: - return "ERROR_DMA_OUTPUT_FORMAT"; - case ERROR_DMA_OUTPUT_BIT_WIDTH: - return "ERROR_DMA_OUTPUT_BIT_WIDTH"; - case ERROR_DMA_OUTPUT_PLANE: - return "ERROR_DMA_OUTPUT_PLANE"; - case ERROR_DMA_OUTPUT_ORDER: - return "ERROR_DMA_OUTPUT_ORDER"; - - /* Sensor Error(100~199) */ - case ERROR_SENSOR_I2C_FAIL: - return "ERROR_SENSOR_I2C_FAIL"; - case ERROR_SENSOR_INVALID_FRAMERATE: - return "ERROR_SENSOR_INVALID_FRAMERATE"; - case ERROR_SENSOR_INVALID_EXPOSURETIME: - return "ERROR_SENSOR_INVALID_EXPOSURETIME"; - case ERROR_SENSOR_INVALID_SIZE: - return "ERROR_SENSOR_INVALID_SIZE"; - case ERROR_SENSOR_INVALID_SETTING: - return "ERROR_SENSOR_INVALID_SETTING"; - case ERROR_SENSOR_ACTUATOR_INIT_FAIL: - return "ERROR_SENSOR_ACTUATOR_INIT_FAIL"; - case ERROR_SENSOR_INVALID_AF_POS: - return "ERROR_SENSOR_INVALID_AF_POS"; - case ERROR_SENSOR_UNSUPPORT_FUNC: - return "ERROR_SENSOR_UNSUPPORT_FUNC"; - case ERROR_SENSOR_UNSUPPORT_PERI: - return "ERROR_SENSOR_UNSUPPORT_PERI"; - case ERROR_SENSOR_UNSUPPORT_AF: - return "ERROR_SENSOR_UNSUPPORT_AF"; - - /* ISP Error (200~299) */ - case ERROR_ISP_AF_BUSY: - return "ERROR_ISP_AF_BUSY"; - case ERROR_ISP_AF_INVALID_COMMAND: - return "ERROR_ISP_AF_INVALID_COMMAND"; - case ERROR_ISP_AF_INVALID_MODE: - return "ERROR_ISP_AF_INVALID_MODE"; - - /* DRC Error (300~399) */ - /* FD Error (400~499) */ - case ERROR_FD_CONFIG_MAX_NUMBER_STATE: - return "ERROR_FD_CONFIG_MAX_NUMBER_STATE"; - case ERROR_FD_CONFIG_MAX_NUMBER_INVALID: - return "ERROR_FD_CONFIG_MAX_NUMBER_INVALID"; - case ERROR_FD_CONFIG_YAW_ANGLE_STATE: - return "ERROR_FD_CONFIG_YAW_ANGLE_STATE"; - case ERROR_FD_CONFIG_YAW_ANGLE_INVALID: - return "ERROR_FD_CONFIG_YAW_ANGLE_INVALID\n"; - case ERROR_FD_CONFIG_ROLL_ANGLE_STATE: - return "ERROR_FD_CONFIG_ROLL_ANGLE_STATE"; - case ERROR_FD_CONFIG_ROLL_ANGLE_INVALID: - return "ERROR_FD_CONFIG_ROLL_ANGLE_INVALID"; - case ERROR_FD_CONFIG_SMILE_MODE_INVALID: - return "ERROR_FD_CONFIG_SMILE_MODE_INVALID"; - case ERROR_FD_CONFIG_BLINK_MODE_INVALID: - return "ERROR_FD_CONFIG_BLINK_MODE_INVALID"; - case ERROR_FD_CONFIG_EYES_DETECT_INVALID: - return "ERROR_FD_CONFIG_EYES_DETECT_INVALID"; - case ERROR_FD_CONFIG_MOUTH_DETECT_INVALID: - return "ERROR_FD_CONFIG_MOUTH_DETECT_INVALID"; - case ERROR_FD_CONFIG_ORIENTATION_STATE: - return "ERROR_FD_CONFIG_ORIENTATION_STATE"; - case ERROR_FD_CONFIG_ORIENTATION_INVALID: - return "ERROR_FD_CONFIG_ORIENTATION_INVALID"; - case ERROR_FD_CONFIG_ORIENTATION_VALUE_INVALID: - return "ERROR_FD_CONFIG_ORIENTATION_VALUE_INVALID"; - case ERROR_FD_RESULT: - return "ERROR_FD_RESULT"; - case ERROR_FD_MODE: - return "ERROR_FD_MODE"; - default: - return "Unknown"; - } -} - const char *fimc_is_strerr(unsigned int error) { error &= ~IS_ERROR_TIME_OUT_FLAG; diff --git a/drivers/media/platform/samsung/exynos4-is/fimc-is-errno.h b/drivers/media/platform/samsung/exynos4-is/fimc-is-errno.h index 809e117331c0..fa8204ffec7b 100644 --- a/drivers/media/platform/samsung/exynos4-is/fimc-is-errno.h +++ b/drivers/media/platform/samsung/exynos4-is/fimc-is-errno.h @@ -240,6 +240,5 @@ enum fimc_is_error { }; const char *fimc_is_strerr(unsigned int error); -const char *fimc_is_param_strerr(unsigned int error); #endif /* FIMC_IS_ERR_H_ */ diff --git a/drivers/media/platform/samsung/exynos4-is/fimc-is-param.c b/drivers/media/platform/samsung/exynos4-is/fimc-is-param.c index 9c816ae3b3e5..443362da8cc8 100644 --- a/drivers/media/platform/samsung/exynos4-is/fimc-is-param.c +++ b/drivers/media/platform/samsung/exynos4-is/fimc-is-param.c @@ -204,15 +204,6 @@ int __is_hw_update_params(struct fimc_is *is) return ret; } -void __is_get_frame_size(struct fimc_is *is, struct v4l2_mbus_framefmt *mf) -{ - struct isp_param *isp; - - isp = &is->config[is->config_index].isp; - mf->width = isp->otf_input.width; - mf->height = isp->otf_input.height; -} - void __is_set_frame_size(struct fimc_is *is, struct v4l2_mbus_framefmt *mf) { unsigned int index = is->config_index; diff --git a/drivers/media/platform/samsung/exynos4-is/fimc-is-param.h b/drivers/media/platform/samsung/exynos4-is/fimc-is-param.h index 206904674927..10ad02f36fed 100644 --- a/drivers/media/platform/samsung/exynos4-is/fimc-is-param.h +++ b/drivers/media/platform/samsung/exynos4-is/fimc-is-param.h @@ -994,7 +994,6 @@ void fimc_is_set_initial_params(struct fimc_is *is); unsigned int __get_pending_param_count(struct fimc_is *is); int __is_hw_update_params(struct fimc_is *is); -void __is_get_frame_size(struct fimc_is *is, struct v4l2_mbus_framefmt *mf); void __is_set_frame_size(struct fimc_is *is, struct v4l2_mbus_framefmt *mf); void __is_set_sensor(struct fimc_is *is, int fps); void __is_set_isp_aa_ae(struct fimc_is *is); diff --git a/drivers/media/platform/samsung/exynos4-is/mipi-csis.c b/drivers/media/platform/samsung/exynos4-is/mipi-csis.c index 63f3eecdd7e6..452880b5350c 100644 --- a/drivers/media/platform/samsung/exynos4-is/mipi-csis.c +++ b/drivers/media/platform/samsung/exynos4-is/mipi-csis.c @@ -940,13 +940,19 @@ static int s5pcsis_pm_resume(struct device *dev, bool runtime) state->supplies); goto unlock; } - clk_enable(state->clock[CSIS_CLK_GATE]); + ret = clk_enable(state->clock[CSIS_CLK_GATE]); + if (ret) { + phy_power_off(state->phy); + regulator_bulk_disable(CSIS_NUM_SUPPLIES, + state->supplies); + goto unlock; + } } if (state->flags & ST_STREAMING) s5pcsis_start_stream(state); state->flags &= ~ST_SUSPENDED; - unlock: +unlock: mutex_unlock(&state->lock); return ret ? -EAGAIN : 0; } diff --git a/drivers/media/platform/samsung/s3c-camif/camif-core.c b/drivers/media/platform/samsung/s3c-camif/camif-core.c index de6e8f151849..221e3c447f36 100644 --- a/drivers/media/platform/samsung/s3c-camif/camif-core.c +++ b/drivers/media/platform/samsung/s3c-camif/camif-core.c @@ -527,10 +527,19 @@ static void s3c_camif_remove(struct platform_device *pdev) static int s3c_camif_runtime_resume(struct device *dev) { struct camif_dev *camif = dev_get_drvdata(dev); + int ret; + + ret = clk_enable(camif->clock[CLK_GATE]); + if (ret) + return ret; - clk_enable(camif->clock[CLK_GATE]); /* null op on s3c244x */ - clk_enable(camif->clock[CLK_CAM]); + ret = clk_enable(camif->clock[CLK_CAM]); + if (ret) { + clk_disable(camif->clock[CLK_GATE]); + return ret; + } + return 0; } diff --git a/drivers/media/platform/samsung/s5p-mfc/s5p_mfc.c b/drivers/media/platform/samsung/s5p-mfc/s5p_mfc.c index 2fe3c9228ac5..5f80931f056d 100644 --- a/drivers/media/platform/samsung/s5p-mfc/s5p_mfc.c +++ b/drivers/media/platform/samsung/s5p-mfc/s5p_mfc.c @@ -774,8 +774,10 @@ static int s5p_mfc_open(struct file *file) int ret = 0; mfc_debug_enter(); - if (mutex_lock_interruptible(&dev->mfc_mutex)) - return -ERESTARTSYS; + if (mutex_lock_interruptible(&dev->mfc_mutex)) { + ret = -ERESTARTSYS; + goto err_enter; + } dev->num_inst++; /* It is guarded by mfc_mutex in vfd */ /* Allocate memory for context */ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); @@ -946,6 +948,7 @@ err_no_ctx: err_alloc: dev->num_inst--; mutex_unlock(&dev->mfc_mutex); +err_enter: mfc_debug_leave(); return ret; } diff --git a/drivers/media/platform/st/stm32/Kconfig b/drivers/media/platform/st/stm32/Kconfig index 9df9a2a17728..f12e67bcc9bc 100644 --- a/drivers/media/platform/st/stm32/Kconfig +++ b/drivers/media/platform/st/stm32/Kconfig @@ -1,6 +1,20 @@ # SPDX-License-Identifier: GPL-2.0-only # V4L drivers +config VIDEO_STM32_CSI + tristate "STM32 Camera Serial Interface (CSI) support" + depends on V4L_PLATFORM_DRIVERS + depends on VIDEO_DEV && OF + depends on ARCH_STM32 || COMPILE_TEST + select MEDIA_CONTROLLER + select V4L2_FWNODE + help + This module makes the STM32 Camera Serial Interface (CSI) + available as a v4l2 device. + + To compile this driver as a module, choose M here: the module + will be called stm32-csi. + config VIDEO_STM32_DCMI tristate "STM32 Digital Camera Memory Interface (DCMI) support" depends on V4L_PLATFORM_DRIVERS diff --git a/drivers/media/platform/st/stm32/Makefile b/drivers/media/platform/st/stm32/Makefile index 7ed8297b9b19..9ae57897f030 100644 --- a/drivers/media/platform/st/stm32/Makefile +++ b/drivers/media/platform/st/stm32/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_VIDEO_STM32_CSI) += stm32-csi.o obj-$(CONFIG_VIDEO_STM32_DCMI) += stm32-dcmi.o obj-$(CONFIG_VIDEO_STM32_DCMIPP) += stm32-dcmipp/ stm32-dma2d-objs := dma2d/dma2d.o dma2d/dma2d-hw.o diff --git a/drivers/media/platform/st/stm32/stm32-csi.c b/drivers/media/platform/st/stm32/stm32-csi.c new file mode 100644 index 000000000000..48941aae8c9b --- /dev/null +++ b/drivers/media/platform/st/stm32/stm32-csi.c @@ -0,0 +1,1137 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for STM32 Camera Serial Interface + * + * Copyright (C) STMicroelectronics SA 2024 + * Author: Alain Volmat + * for STMicroelectronics. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#define STM32_CSI_CR 0x0000 +#define STM32_CSI_CR_CSIEN BIT(0) +#define STM32_CSI_CR_VCXSTART(x) BIT(2 + ((x) * 4)) +#define STM32_CSI_CR_VCXSTOP(x) BIT(3 + ((x) * 4)) +#define STM32_CSI_PCR 0x0004 +#define STM32_CSI_PCR_DL1EN BIT(3) +#define STM32_CSI_PCR_DL0EN BIT(2) +#define STM32_CSI_PCR_CLEN BIT(1) +#define STM32_CSI_PCR_PWRDOWN BIT(0) +#define STM32_CSI_VCXCFGR1(x) ((((x) + 1) * 0x0010) + 0x0) +#define STM32_CSI_VCXCFGR1_ALLDT BIT(0) +#define STM32_CSI_VCXCFGR1_DT0EN BIT(1) +#define STM32_CSI_VCXCFGR1_DT1EN BIT(2) +#define STM32_CSI_VCXCFGR1_CDTFT_SHIFT 8 +#define STM32_CSI_VCXCFGR1_DT0_SHIFT 16 +#define STM32_CSI_VCXCFGR1_DT0FT_SHIFT 24 +#define STM32_CSI_VCXCFGR2(x) ((((x) + 1) * 0x0010) + 0x4) +#define STM32_CSI_VCXCFGR2_DT1_SHIFT 0 +#define STM32_CSI_VCXCFGR2_DT1FT_SHIFT 8 +#define STM32_CSI_INPUT_BPP8 2 +#define STM32_CSI_INPUT_BPP10 3 +#define STM32_CSI_INPUT_BPP12 4 +#define STM32_CSI_INPUT_BPP14 5 +#define STM32_CSI_LMCFGR 0x0070 +#define STM32_CSI_LMCFGR_LANENB_SHIFT 8 +#define STM32_CSI_LMCFGR_DLMAP_SHIFT 16 +#define STM32_CSI_IER0 0x0080 +#define STM32_CSI_IER1 0x0084 +#define STM32_CSI_SR0 0x0090 +#define STM32_CSI_SR0_SYNCERRF BIT(30) +#define STM32_CSI_SR0_SPKTERRF BIT(28) +#define STM32_CSI_SR0_IDERRF BIT(27) +#define STM32_CSI_SR0_CECCERRF BIT(26) +#define STM32_CSI_SR0_ECCERRF BIT(25) +#define STM32_CSI_SR0_CRCERRF BIT(24) +#define STM32_CSI_SR0_CCFIFOFF BIT(21) +#define STM32_CSI_SR0_VCXSTATEF(x) BIT(17 + (x)) +#define STM32_CSI_SR1 0x0094 +#define STM32_CSI_SR1_ECTRLDL1F BIT(12) +#define STM32_CSI_SR1_ESYNCESCDL1F BIT(11) +#define STM32_CSI_SR1_EESCDL1F BIT(10) +#define STM32_CSI_SR1_ESOTSYNCDL1F BIT(9) +#define STM32_CSI_SR1_ESOTDL1F BIT(8) +#define STM32_CSI_SR1_ECTRLDL0F BIT(4) +#define STM32_CSI_SR1_ESYNCESCDL0F BIT(3) +#define STM32_CSI_SR1_EESCDL0F BIT(2) +#define STM32_CSI_SR1_ESOTSYNCDL0F BIT(1) +#define STM32_CSI_SR1_ESOTDL0F BIT(0) +#define STM32_CSI_FCR0 0x0100 +#define STM32_CSI_FCR1 0x0104 +#define STM32_CSI_SPDFR 0x0110 +#define STM32_CSI_DT_MASK 0x3f +#define STM32_CSI_VC_MASK 0x03 +#define STM32_CSI_ERR1 0x0114 +#define STM32_CSI_ERR1_IDVCERR_SHIFT 22 +#define STM32_CSI_ERR1_IDDTERR_SHIFT 16 +#define STM32_CSI_ERR1_CECCVCERR_SHIFT 14 +#define STM32_CSI_ERR1_CECCDTERR_SHIFT 8 +#define STM32_CSI_ERR1_CRCVCERR_SHIFT 6 +#define STM32_CSI_ERR1_CRCDTERR_SHIFT 0 +#define STM32_CSI_ERR2 0x0118 +#define STM32_CSI_ERR2_SYNCVCERR_SHIFT 18 +#define STM32_CSI_ERR2_SPKTVCERR_SHIFT 6 +#define STM32_CSI_ERR2_SPKTDTERR_SHIFT 0 +#define STM32_CSI_PRCR 0x1000 +#define STM32_CSI_PRCR_PEN BIT(1) +#define STM32_CSI_PMCR 0x1004 +#define STM32_CSI_PFCR 0x1008 +#define STM32_CSI_PFCR_CCFR_MASK GENMASK(5, 0) +#define STM32_CSI_PFCR_CCFR_SHIFT 0 +#define STM32_CSI_PFCR_HSFR_MASK GENMASK(14, 8) +#define STM32_CSI_PFCR_HSFR_SHIFT 8 +#define STM32_CSI_PFCR_DLD BIT(16) +#define STM32_CSI_PTCR0 0x1010 +#define STM32_CSI_PTCR0_TCKEN BIT(0) +#define STM32_CSI_PTCR1 0x1014 +#define STM32_CSI_PTCR1_TWM BIT(16) +#define STM32_CSI_PTCR1_TDI_MASK GENMASK(7, 0) +#define STM32_CSI_PTCR1_TDI_SHIFT 0 +#define STM32_CSI_PTSR 0x1018 + +#define STM32_CSI_LANES_MAX 2 + +#define STM32_CSI_SR0_ERRORS (STM32_CSI_SR0_SYNCERRF | STM32_CSI_SR0_SPKTERRF |\ + STM32_CSI_SR0_IDERRF | STM32_CSI_SR0_CECCERRF |\ + STM32_CSI_SR0_ECCERRF | STM32_CSI_SR0_CRCERRF |\ + STM32_CSI_SR0_CCFIFOFF) +#define STM32_CSI_SR1_DL0_ERRORS (STM32_CSI_SR1_ECTRLDL0F | STM32_CSI_SR1_ESYNCESCDL0F |\ + STM32_CSI_SR1_EESCDL0F | STM32_CSI_SR1_ESOTSYNCDL0F |\ + STM32_CSI_SR1_ESOTDL0F) +#define STM32_CSI_SR1_DL1_ERRORS (STM32_CSI_SR1_ECTRLDL1F | STM32_CSI_SR1_ESYNCESCDL1F |\ + STM32_CSI_SR1_EESCDL1F | STM32_CSI_SR1_ESOTSYNCDL1F |\ + STM32_CSI_SR1_ESOTDL1F) +#define STM32_CSI_SR1_ERRORS (STM32_CSI_SR1_DL0_ERRORS | STM32_CSI_SR1_DL1_ERRORS) + +enum stm32_csi_pads { + STM32_CSI_PAD_SINK, + STM32_CSI_PAD_SOURCE, + STM32_CSI_PAD_MAX, +}; + +struct stm32_csi_event { + u32 mask; + const char * const name; +}; + +static const struct stm32_csi_event stm32_csi_events_sr0[] = { + {STM32_CSI_SR0_SYNCERRF, "Synchronization error"}, + {STM32_CSI_SR0_SPKTERRF, "Short packet error"}, + {STM32_CSI_SR0_IDERRF, "Data type ID error"}, + {STM32_CSI_SR0_CECCERRF, "Corrected ECC error"}, + {STM32_CSI_SR0_ECCERRF, "ECC error"}, + {STM32_CSI_SR0_CRCERRF, "CRC error"}, + {STM32_CSI_SR0_CCFIFOFF, "Clk changer FIFO full error"}, +}; + +#define STM32_CSI_NUM_SR0_EVENTS ARRAY_SIZE(stm32_csi_events_sr0) + +static const struct stm32_csi_event stm32_csi_events_sr1[] = { + {STM32_CSI_SR1_ECTRLDL1F, "L1: D-PHY control error"}, + {STM32_CSI_SR1_ESYNCESCDL1F, + "L1: D-PHY low power data transmission synchro error"}, + {STM32_CSI_SR1_EESCDL1F, "L1: D-PHY escape entry error"}, + {STM32_CSI_SR1_ESOTSYNCDL1F, + "L1: Start of transmission synchro error"}, + {STM32_CSI_SR1_ESOTDL1F, "L1: Start of transmission error"}, + {STM32_CSI_SR1_ECTRLDL0F, "L0: D-PHY control error"}, + {STM32_CSI_SR1_ESYNCESCDL0F, + "L0: D-PHY low power data transmission synchro error"}, + {STM32_CSI_SR1_EESCDL0F, "L0: D-PHY escape entry error"}, + {STM32_CSI_SR1_ESOTSYNCDL0F, + "L0: Start of transmission synchro error"}, + {STM32_CSI_SR1_ESOTDL0F, "L0: Start of transmission error"}, +}; + +#define STM32_CSI_NUM_SR1_EVENTS ARRAY_SIZE(stm32_csi_events_sr1) + +enum stm32_csi_clk { + STM32_CSI_CLK_PCLK, + STM32_CSI_CLK_TXESC, + STM32_CSI_CLK_CSI2PHY, + STM32_CSI_CLK_NB, +}; + +static const char * const stm32_csi_clks_id[] = { + "pclk", + "txesc", + "csi2phy", +}; + +struct stm32_csi_dev { + struct device *dev; + + void __iomem *base; + + struct clk_bulk_data clks[STM32_CSI_CLK_NB]; + struct regulator_bulk_data supplies[2]; + + u8 lanes[STM32_CSI_LANES_MAX]; + u8 num_lanes; + + /* + * spinlock slock is used to protect to srX_counters tables being + * accessed from log_status and interrupt context + */ + spinlock_t slock; + + u32 sr0_counters[STM32_CSI_NUM_SR0_EVENTS]; + u32 sr1_counters[STM32_CSI_NUM_SR1_EVENTS]; + + struct v4l2_subdev sd; + struct v4l2_async_notifier notifier; + struct media_pad pads[STM32_CSI_PAD_MAX]; + + /* Remote source */ + struct v4l2_subdev *s_subdev; + u32 s_subdev_pad_nb; +}; + +struct stm32_csi_fmts { + u32 code; + u32 datatype; + u32 input_fmt; + u8 bpp; +}; + +#define FMT_MBUS_DT_DTFMT_BPP(mbus, dt, input, byteperpixel) \ + { \ + .code = MEDIA_BUS_FMT_##mbus, \ + .datatype = MIPI_CSI2_DT_##dt, \ + .input_fmt = STM32_CSI_INPUT_##input, \ + .bpp = byteperpixel, \ + } +static const struct stm32_csi_fmts stm32_csi_formats[] = { + /* YUV 422 8 bit */ + FMT_MBUS_DT_DTFMT_BPP(UYVY8_1X16, YUV422_8B, BPP8, 8), + FMT_MBUS_DT_DTFMT_BPP(YUYV8_1X16, YUV422_8B, BPP8, 8), + FMT_MBUS_DT_DTFMT_BPP(YVYU8_1X16, YUV422_8B, BPP8, 8), + FMT_MBUS_DT_DTFMT_BPP(VYUY8_1X16, YUV422_8B, BPP8, 8), + + /* Raw Bayer */ + /* 8 bit */ + FMT_MBUS_DT_DTFMT_BPP(SBGGR8_1X8, RAW8, BPP8, 8), + FMT_MBUS_DT_DTFMT_BPP(SGBRG8_1X8, RAW8, BPP8, 8), + FMT_MBUS_DT_DTFMT_BPP(SGRBG8_1X8, RAW8, BPP8, 8), + FMT_MBUS_DT_DTFMT_BPP(SRGGB8_1X8, RAW8, BPP8, 8), + /* 10 bit */ + FMT_MBUS_DT_DTFMT_BPP(SRGGB10_1X10, RAW10, BPP10, 10), + FMT_MBUS_DT_DTFMT_BPP(SGBRG10_1X10, RAW10, BPP10, 10), + FMT_MBUS_DT_DTFMT_BPP(SGRBG10_1X10, RAW10, BPP10, 10), + FMT_MBUS_DT_DTFMT_BPP(SRGGB10_1X10, RAW10, BPP10, 10), + /* 12 bit */ + FMT_MBUS_DT_DTFMT_BPP(SRGGB12_1X12, RAW12, BPP12, 12), + FMT_MBUS_DT_DTFMT_BPP(SGBRG12_1X12, RAW12, BPP12, 12), + FMT_MBUS_DT_DTFMT_BPP(SGRBG12_1X12, RAW12, BPP12, 12), + FMT_MBUS_DT_DTFMT_BPP(SRGGB12_1X12, RAW12, BPP12, 12), + /* 14 bit */ + FMT_MBUS_DT_DTFMT_BPP(SRGGB14_1X14, RAW14, BPP14, 14), + FMT_MBUS_DT_DTFMT_BPP(SGBRG14_1X14, RAW14, BPP14, 14), + FMT_MBUS_DT_DTFMT_BPP(SGRBG14_1X14, RAW14, BPP14, 14), + FMT_MBUS_DT_DTFMT_BPP(SRGGB14_1X14, RAW14, BPP14, 14), + + /* RGB 565 */ + FMT_MBUS_DT_DTFMT_BPP(RGB565_1X16, RGB565, BPP8, 8), + + /* JPEG (datatype isn't used) */ + FMT_MBUS_DT_DTFMT_BPP(JPEG_1X8, NULL, BPP8, 8), +}; + +struct stm32_csi_mbps_phy_reg { + unsigned int mbps; + unsigned int hsfreqrange; + unsigned int osc_freq_target; +}; + +/* + * Table describing configuration of the PHY depending on the + * intended Bit Rate. From table 5-8 Frequency Ranges and Defaults + * of the Synopsis DWC MIPI PHY databook + */ +static const struct stm32_csi_mbps_phy_reg snps_stm32mp25[] = { + { .mbps = 80, .hsfreqrange = 0x00, .osc_freq_target = 460 }, + { .mbps = 90, .hsfreqrange = 0x10, .osc_freq_target = 460 }, + { .mbps = 100, .hsfreqrange = 0x20, .osc_freq_target = 460 }, + { .mbps = 110, .hsfreqrange = 0x30, .osc_freq_target = 460 }, + { .mbps = 120, .hsfreqrange = 0x01, .osc_freq_target = 460 }, + { .mbps = 130, .hsfreqrange = 0x11, .osc_freq_target = 460 }, + { .mbps = 140, .hsfreqrange = 0x21, .osc_freq_target = 460 }, + { .mbps = 150, .hsfreqrange = 0x31, .osc_freq_target = 460 }, + { .mbps = 160, .hsfreqrange = 0x02, .osc_freq_target = 460 }, + { .mbps = 170, .hsfreqrange = 0x12, .osc_freq_target = 460 }, + { .mbps = 180, .hsfreqrange = 0x22, .osc_freq_target = 460 }, + { .mbps = 190, .hsfreqrange = 0x32, .osc_freq_target = 460 }, + { .mbps = 205, .hsfreqrange = 0x03, .osc_freq_target = 460 }, + { .mbps = 220, .hsfreqrange = 0x13, .osc_freq_target = 460 }, + { .mbps = 235, .hsfreqrange = 0x23, .osc_freq_target = 460 }, + { .mbps = 250, .hsfreqrange = 0x33, .osc_freq_target = 460 }, + { .mbps = 275, .hsfreqrange = 0x04, .osc_freq_target = 460 }, + { .mbps = 300, .hsfreqrange = 0x14, .osc_freq_target = 460 }, + { .mbps = 325, .hsfreqrange = 0x25, .osc_freq_target = 460 }, + { .mbps = 350, .hsfreqrange = 0x35, .osc_freq_target = 460 }, + { .mbps = 400, .hsfreqrange = 0x05, .osc_freq_target = 460 }, + { .mbps = 450, .hsfreqrange = 0x16, .osc_freq_target = 460 }, + { .mbps = 500, .hsfreqrange = 0x26, .osc_freq_target = 460 }, + { .mbps = 550, .hsfreqrange = 0x37, .osc_freq_target = 460 }, + { .mbps = 600, .hsfreqrange = 0x07, .osc_freq_target = 460 }, + { .mbps = 650, .hsfreqrange = 0x18, .osc_freq_target = 460 }, + { .mbps = 700, .hsfreqrange = 0x28, .osc_freq_target = 460 }, + { .mbps = 750, .hsfreqrange = 0x39, .osc_freq_target = 460 }, + { .mbps = 800, .hsfreqrange = 0x09, .osc_freq_target = 460 }, + { .mbps = 850, .hsfreqrange = 0x19, .osc_freq_target = 460 }, + { .mbps = 900, .hsfreqrange = 0x29, .osc_freq_target = 460 }, + { .mbps = 950, .hsfreqrange = 0x3a, .osc_freq_target = 460 }, + { .mbps = 1000, .hsfreqrange = 0x0a, .osc_freq_target = 460 }, + { .mbps = 1050, .hsfreqrange = 0x1a, .osc_freq_target = 460 }, + { .mbps = 1100, .hsfreqrange = 0x2a, .osc_freq_target = 460 }, + { .mbps = 1150, .hsfreqrange = 0x3b, .osc_freq_target = 460 }, + { .mbps = 1200, .hsfreqrange = 0x0b, .osc_freq_target = 460 }, + { .mbps = 1250, .hsfreqrange = 0x1b, .osc_freq_target = 460 }, + { .mbps = 1300, .hsfreqrange = 0x2b, .osc_freq_target = 460 }, + { .mbps = 1350, .hsfreqrange = 0x3c, .osc_freq_target = 460 }, + { .mbps = 1400, .hsfreqrange = 0x0c, .osc_freq_target = 460 }, + { .mbps = 1450, .hsfreqrange = 0x1c, .osc_freq_target = 460 }, + { .mbps = 1500, .hsfreqrange = 0x2c, .osc_freq_target = 460 }, + { .mbps = 1550, .hsfreqrange = 0x3d, .osc_freq_target = 285 }, + { .mbps = 1600, .hsfreqrange = 0x0d, .osc_freq_target = 295 }, + { .mbps = 1650, .hsfreqrange = 0x1d, .osc_freq_target = 304 }, + { .mbps = 1700, .hsfreqrange = 0x2e, .osc_freq_target = 313 }, + { .mbps = 1750, .hsfreqrange = 0x3e, .osc_freq_target = 322 }, + { .mbps = 1800, .hsfreqrange = 0x0e, .osc_freq_target = 331 }, + { .mbps = 1850, .hsfreqrange = 0x1e, .osc_freq_target = 341 }, + { .mbps = 1900, .hsfreqrange = 0x2f, .osc_freq_target = 350 }, + { .mbps = 1950, .hsfreqrange = 0x3f, .osc_freq_target = 359 }, + { .mbps = 2000, .hsfreqrange = 0x0f, .osc_freq_target = 368 }, + { .mbps = 2050, .hsfreqrange = 0x40, .osc_freq_target = 377 }, + { .mbps = 2100, .hsfreqrange = 0x41, .osc_freq_target = 387 }, + { .mbps = 2150, .hsfreqrange = 0x42, .osc_freq_target = 396 }, + { .mbps = 2200, .hsfreqrange = 0x43, .osc_freq_target = 405 }, + { .mbps = 2250, .hsfreqrange = 0x44, .osc_freq_target = 414 }, + { .mbps = 2300, .hsfreqrange = 0x45, .osc_freq_target = 423 }, + { .mbps = 2350, .hsfreqrange = 0x46, .osc_freq_target = 432 }, + { .mbps = 2400, .hsfreqrange = 0x47, .osc_freq_target = 442 }, + { .mbps = 2450, .hsfreqrange = 0x48, .osc_freq_target = 451 }, + { .mbps = 2500, .hsfreqrange = 0x49, .osc_freq_target = 460 }, + { /* sentinel */ } +}; + +static const struct v4l2_mbus_framefmt fmt_default = { + .width = 640, + .height = 480, + .code = MEDIA_BUS_FMT_RGB565_1X16, + .field = V4L2_FIELD_NONE, + .colorspace = V4L2_COLORSPACE_REC709, + .ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT, + .quantization = V4L2_QUANTIZATION_DEFAULT, + .xfer_func = V4L2_XFER_FUNC_DEFAULT, +}; + +static const struct stm32_csi_fmts *stm32_csi_code_to_fmt(unsigned int code) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(stm32_csi_formats); i++) + if (stm32_csi_formats[i].code == code) + return &stm32_csi_formats[i]; + + return NULL; +} + +static inline struct stm32_csi_dev *to_csidev(struct v4l2_subdev *sd) +{ + return container_of(sd, struct stm32_csi_dev, sd); +} + +static int stm32_csi_setup_lane_merger(struct stm32_csi_dev *csidev) +{ + u32 lmcfgr = 0; + int i; + + for (i = 0; i < csidev->num_lanes; i++) { + if (!csidev->lanes[i] || csidev->lanes[i] > STM32_CSI_LANES_MAX) { + dev_err(csidev->dev, "Invalid lane id (%d)\n", csidev->lanes[i]); + return -EINVAL; + } + lmcfgr |= (csidev->lanes[i] << ((i * 4) + STM32_CSI_LMCFGR_DLMAP_SHIFT)); + } + + lmcfgr |= (csidev->num_lanes << STM32_CSI_LMCFGR_LANENB_SHIFT); + + writel_relaxed(lmcfgr, csidev->base + STM32_CSI_LMCFGR); + + return 0; +} + +static void stm32_csi_phy_reg_write(struct stm32_csi_dev *csidev, + u32 addr, u32 val) +{ + /* Based on sequence described at section 5.2.3.2 of DesignWave document */ + /* For writing the 4-bit testcode MSBs */ + /* Set testen to high */ + writel_relaxed(STM32_CSI_PTCR1_TWM, csidev->base + STM32_CSI_PTCR1); + + /* Set testclk to high */ + writel_relaxed(STM32_CSI_PTCR0_TCKEN, csidev->base + STM32_CSI_PTCR0); + + /* Place 0x00 in testdin */ + writel_relaxed(STM32_CSI_PTCR1_TWM, csidev->base + STM32_CSI_PTCR1); + + /* + * Set testclk to low (with the falling edge on testclk, the testdin + * signal content is latched internally) + */ + writel_relaxed(0, csidev->base + STM32_CSI_PTCR0); + + /* Set testen to low */ + writel_relaxed(0, csidev->base + STM32_CSI_PTCR1); + + /* Place the 8-bit word corresponding to the testcode MSBs in testdin */ + writel_relaxed(((addr >> 8) & STM32_CSI_PTCR1_TDI_MASK) << STM32_CSI_PTCR1_TDI_SHIFT, + csidev->base + STM32_CSI_PTCR1); + + /* Set testclk to high */ + writel_relaxed(STM32_CSI_PTCR0_TCKEN, csidev->base + STM32_CSI_PTCR0); + + /* For writing the 8-bit testcode LSBs */ + /* Set testclk to low */ + writel_relaxed(0, csidev->base + STM32_CSI_PTCR0); + + /* Set testen to high */ + writel_relaxed(STM32_CSI_PTCR1_TWM, csidev->base + STM32_CSI_PTCR1); + + /* Set testclk to high */ + writel_relaxed(STM32_CSI_PTCR0_TCKEN, csidev->base + STM32_CSI_PTCR0); + + /* Place the 8-bit word test data in testdin */ + writel_relaxed((addr & STM32_CSI_PTCR1_TDI_MASK) << + STM32_CSI_PTCR1_TDI_SHIFT | STM32_CSI_PTCR1_TWM, + csidev->base + STM32_CSI_PTCR1); + + /* + * Set testclk to low (with the falling edge on testclk, the testdin + * signal content is latched internally) + */ + writel_relaxed(0, csidev->base + STM32_CSI_PTCR0); + + /* Set testen to low */ + writel_relaxed(0, csidev->base + STM32_CSI_PTCR1); + + /* For writing the data */ + /* Place the 8-bit word corresponding to the page offset in testdin */ + writel_relaxed((val & STM32_CSI_PTCR1_TDI_MASK) << STM32_CSI_PTCR1_TDI_SHIFT, + csidev->base + STM32_CSI_PTCR1); + + /* Set testclk to high (test data is programmed internally */ + writel_relaxed(STM32_CSI_PTCR0_TCKEN, csidev->base + STM32_CSI_PTCR0); + + /* Finish by setting testclk to low */ + writel_relaxed(0, csidev->base + STM32_CSI_PTCR0); +} + +static int stm32_csi_start(struct stm32_csi_dev *csidev, + struct v4l2_subdev_state *state) +{ + const struct stm32_csi_mbps_phy_reg *phy_regs; + struct v4l2_mbus_framefmt *sink_fmt; + const struct stm32_csi_fmts *fmt; + unsigned long phy_clk_frate; + unsigned int mbps; + u32 lanes_ie = 0; + u32 lanes_en = 0; + s64 link_freq; + int ret; + u32 ccfr; + + dev_dbg(csidev->dev, "Starting the CSI2\n"); + + /* Get the bpp value on pad0 (input of CSI) */ + sink_fmt = v4l2_subdev_state_get_format(state, STM32_CSI_PAD_SINK); + fmt = stm32_csi_code_to_fmt(sink_fmt->code); + + /* Get the remote sensor link frequency */ + if (!csidev->s_subdev) + return -EIO; + + link_freq = v4l2_get_link_freq(csidev->s_subdev->ctrl_handler, + fmt->bpp, 2 * csidev->num_lanes); + if (link_freq < 0) + return link_freq; + + /* MBPS is expressed in Mbps, hence link_freq / 100000 * 2 */ + mbps = div_s64(link_freq, 500000); + dev_dbg(csidev->dev, "Computed Mbps: %u\n", mbps); + + for (phy_regs = snps_stm32mp25; phy_regs->mbps != 0; phy_regs++) + if (phy_regs->mbps >= mbps) + break; + + if (!phy_regs->mbps) { + dev_err(csidev->dev, "Unsupported PHY speed (%u Mbps)", mbps); + return -ERANGE; + } + + dev_dbg(csidev->dev, "PHY settings: (%u Mbps, %u HS FRange, %u OSC Freq)\n", + phy_regs->mbps, phy_regs->hsfreqrange, + phy_regs->osc_freq_target); + + /* Prepare lanes related configuration bits */ + lanes_ie |= STM32_CSI_SR1_DL0_ERRORS; + lanes_en |= STM32_CSI_PCR_DL0EN; + if (csidev->num_lanes == 2) { + lanes_ie |= STM32_CSI_SR1_DL1_ERRORS; + lanes_en |= STM32_CSI_PCR_DL1EN; + } + + ret = pm_runtime_get_sync(csidev->dev); + if (ret < 0) + return ret; + + /* Retrieve CSI2PHY clock rate to compute CCFR value */ + phy_clk_frate = clk_get_rate(csidev->clks[STM32_CSI_CLK_CSI2PHY].clk); + if (!phy_clk_frate) { + pm_runtime_put(csidev->dev); + dev_err(csidev->dev, "CSI2PHY clock rate invalid (0)\n"); + return ret; + } + + ret = stm32_csi_setup_lane_merger(csidev); + if (ret) { + pm_runtime_put(csidev->dev); + return ret; + } + + /* Enable the CSI */ + writel_relaxed(STM32_CSI_CR_CSIEN, csidev->base + STM32_CSI_CR); + + /* Enable some global CSI related interrupts - bits are same as SR0 */ + writel_relaxed(STM32_CSI_SR0_ERRORS, csidev->base + STM32_CSI_IER0); + + /* Enable lanes related error interrupts */ + writel_relaxed(lanes_ie, csidev->base + STM32_CSI_IER1); + + /* Initialization of the D-PHY */ + /* Stop the D-PHY */ + writel_relaxed(0, csidev->base + STM32_CSI_PRCR); + + /* Keep the D-PHY in power down state */ + writel_relaxed(0, csidev->base + STM32_CSI_PCR); + + /* Enable testclr clock during 15ns */ + writel_relaxed(STM32_CSI_PTCR0_TCKEN, csidev->base + STM32_CSI_PTCR0); + udelay(1); + writel_relaxed(0, csidev->base + STM32_CSI_PTCR0); + + /* Set hsfreqrange */ + phy_clk_frate /= 1000000; + ccfr = (phy_clk_frate - 17) * 4; + writel_relaxed((ccfr << STM32_CSI_PFCR_CCFR_SHIFT) | + (phy_regs->hsfreqrange << STM32_CSI_PFCR_HSFR_SHIFT), + csidev->base + STM32_CSI_PFCR); + + /* set reg @08 deskew_polarity_rw 1'b1 */ + stm32_csi_phy_reg_write(csidev, 0x08, 0x38); + + /* set reg @0xE4 counter_for_des_en_config_if_rx 0x10 + DLL prog EN */ + /* This is because 13<= cfgclkfreqrange[5:0]<=38 */ + stm32_csi_phy_reg_write(csidev, 0xe4, 0x11); + + /* set reg @0xe2 & reg @0xe3 value DLL target oscilation freq */ + /* Based on the table page 77, osc_freq_target */ + stm32_csi_phy_reg_write(csidev, 0xe2, phy_regs->osc_freq_target & 0xFF); + stm32_csi_phy_reg_write(csidev, 0xe3, (phy_regs->osc_freq_target >> 8) & 0x0F); + + writel_relaxed(STM32_CSI_PFCR_DLD | readl_relaxed(csidev->base + STM32_CSI_PFCR), + csidev->base + STM32_CSI_PFCR); + + /* Enable Lanes */ + writel_relaxed(lanes_en | STM32_CSI_PCR_CLEN, csidev->base + STM32_CSI_PCR); + writel_relaxed(lanes_en | STM32_CSI_PCR_CLEN | STM32_CSI_PCR_PWRDOWN, + csidev->base + STM32_CSI_PCR); + + writel_relaxed(STM32_CSI_PRCR_PEN, csidev->base + STM32_CSI_PRCR); + + /* Remove the force */ + writel_relaxed(0, csidev->base + STM32_CSI_PMCR); + + return ret; +} + +static void stm32_csi_stop(struct stm32_csi_dev *csidev) +{ + dev_dbg(csidev->dev, "Stopping the CSI2\n"); + + /* Disable the D-PHY */ + writel_relaxed(0, csidev->base + STM32_CSI_PCR); + + /* Disable ITs */ + writel_relaxed(0, csidev->base + STM32_CSI_IER0); + writel_relaxed(0, csidev->base + STM32_CSI_IER1); + + /* Disable the CSI */ + writel_relaxed(0, csidev->base + STM32_CSI_CR); + + pm_runtime_put(csidev->dev); +} + +static int stm32_csi_start_vc(struct stm32_csi_dev *csidev, + struct v4l2_subdev_state *state, u32 vc) +{ + struct v4l2_mbus_framefmt *mbus_fmt; + const struct stm32_csi_fmts *fmt; + u32 cfgr1 = 0; + int ret = 0; + u32 status; + + mbus_fmt = v4l2_subdev_state_get_format(state, STM32_CSI_PAD_SOURCE); + fmt = stm32_csi_code_to_fmt(mbus_fmt->code); + + /* If the mbus code is JPEG, don't enable filtering */ + if (mbus_fmt->code == MEDIA_BUS_FMT_JPEG_1X8) { + cfgr1 |= STM32_CSI_VCXCFGR1_ALLDT; + cfgr1 |= fmt->input_fmt << STM32_CSI_VCXCFGR1_CDTFT_SHIFT; + dev_dbg(csidev->dev, "VC%d: enable AllDT mode\n", vc); + } else { + cfgr1 |= fmt->datatype << STM32_CSI_VCXCFGR1_DT0_SHIFT; + cfgr1 |= fmt->input_fmt << STM32_CSI_VCXCFGR1_DT0FT_SHIFT; + cfgr1 |= STM32_CSI_VCXCFGR1_DT0EN; + dev_dbg(csidev->dev, "VC%d: enable DT0(0x%x)/DT0FT(0x%x)\n", + vc, fmt->datatype, fmt->input_fmt); + } + writel_relaxed(cfgr1, csidev->base + STM32_CSI_VCXCFGR1(vc)); + + /* Enable processing of the virtual-channel and wait for its status */ + writel_relaxed(STM32_CSI_CR_VCXSTART(vc) | STM32_CSI_CR_CSIEN, + csidev->base + STM32_CSI_CR); + + ret = readl_relaxed_poll_timeout(csidev->base + STM32_CSI_SR0, + status, + status & STM32_CSI_SR0_VCXSTATEF(vc), + 1000, 1000000); + if (ret) { + dev_err(csidev->dev, "failed to start VC(%d)\n", vc); + return ret; + } + + return 0; +} + +static int stm32_csi_stop_vc(struct stm32_csi_dev *csidev, u32 vc) +{ + int ret = 0; + u32 status; + + /* Stop the Virtual Channel */ + writel_relaxed(STM32_CSI_CR_VCXSTOP(vc) | STM32_CSI_CR_CSIEN, + csidev->base + STM32_CSI_CR); + + ret = readl_relaxed_poll_timeout(csidev->base + STM32_CSI_SR0, + status, + !(status & STM32_CSI_SR0_VCXSTATEF(vc)), + 1000, 1000000); + if (ret) { + dev_err(csidev->dev, "failed to stop VC(%d)\n", vc); + return ret; + } + + /* Disable all DTs */ + writel_relaxed(0, csidev->base + STM32_CSI_VCXCFGR1(vc)); + writel_relaxed(0, csidev->base + STM32_CSI_VCXCFGR2(vc)); + + return 0; +} + +static int stm32_csi_disable_streams(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state, u32 pad, + u64 streams_mask) +{ + struct stm32_csi_dev *csidev = to_csidev(sd); + int ret; + + ret = v4l2_subdev_disable_streams(csidev->s_subdev, + csidev->s_subdev_pad_nb, BIT_ULL(0)); + if (ret) + return ret; + + /* Stop the VC0 */ + ret = stm32_csi_stop_vc(csidev, 0); + if (ret) + dev_err(csidev->dev, "Failed to stop VC0\n"); + + stm32_csi_stop(csidev); + + return 0; +} + +static int stm32_csi_enable_streams(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state, u32 pad, + u64 streams_mask) +{ + struct stm32_csi_dev *csidev = to_csidev(sd); + int ret; + + ret = stm32_csi_start(csidev, state); + if (ret) + return ret; + + /* Configure & start the VC0 */ + ret = stm32_csi_start_vc(csidev, state, 0); + if (ret) { + dev_err(csidev->dev, "Failed to start VC0\n"); + stm32_csi_stop(csidev); + return ret; + } + + ret = v4l2_subdev_enable_streams(csidev->s_subdev, + csidev->s_subdev_pad_nb, BIT_ULL(0)); + if (ret) { + stm32_csi_stop_vc(csidev, 0); + stm32_csi_stop(csidev); + return ret; + } + + return 0; +} + +static int stm32_csi_init_state(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state) +{ + int i; + + for (i = 0; i < sd->entity.num_pads; i++) + *v4l2_subdev_state_get_format(state, i) = fmt_default; + + return 0; +} + +static int stm32_csi_enum_mbus_code(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state, + struct v4l2_subdev_mbus_code_enum *code) +{ + if (code->index >= ARRAY_SIZE(stm32_csi_formats)) + return -EINVAL; + + code->code = stm32_csi_formats[code->index].code; + return 0; +} + +static int stm32_csi_set_pad_format(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state, + struct v4l2_subdev_format *format) +{ + struct stm32_csi_dev *csidev = to_csidev(sd); + struct v4l2_mbus_framefmt *framefmt; + const struct stm32_csi_fmts *fmt; + + fmt = stm32_csi_code_to_fmt(format->format.code); + if (!fmt) { + dev_dbg(csidev->dev, "Unsupported code %d, use default\n", + format->format.code); + format->format.code = fmt_default.code; + } + + framefmt = v4l2_subdev_state_get_format(state, STM32_CSI_PAD_SINK); + + if (format->pad == STM32_CSI_PAD_SOURCE) + format->format = *framefmt; + else + *framefmt = format->format; + + framefmt = v4l2_subdev_state_get_format(state, STM32_CSI_PAD_SOURCE); + *framefmt = format->format; + + return 0; +} + +static int stm32_csi_log_status(struct v4l2_subdev *sd) +{ + struct stm32_csi_dev *csidev = to_csidev(sd); + unsigned long flags; + unsigned int i; + + spin_lock_irqsave(&csidev->slock, flags); + + for (i = 0; i < STM32_CSI_NUM_SR0_EVENTS; i++) { + if (csidev->sr0_counters[i]) + dev_info(csidev->dev, "%s events: %d\n", + stm32_csi_events_sr0[i].name, + csidev->sr0_counters[i]); + } + + for (i = 0; i < STM32_CSI_NUM_SR1_EVENTS; i++) { + if (csidev->sr1_counters[i]) + dev_info(csidev->dev, "%s events: %d\n", + stm32_csi_events_sr1[i].name, + csidev->sr1_counters[i]); + } + + spin_unlock_irqrestore(&csidev->slock, flags); + + return 0; +} + +static const struct v4l2_subdev_core_ops stm32_csi_core_ops = { + .log_status = stm32_csi_log_status, +}; + +static const struct v4l2_subdev_video_ops stm32_csi_video_ops = { + .s_stream = v4l2_subdev_s_stream_helper, +}; + +static const struct v4l2_subdev_pad_ops stm32_csi_pad_ops = { + .enum_mbus_code = stm32_csi_enum_mbus_code, + .set_fmt = stm32_csi_set_pad_format, + .get_fmt = v4l2_subdev_get_fmt, + .enable_streams = stm32_csi_enable_streams, + .disable_streams = stm32_csi_disable_streams, +}; + +static const struct v4l2_subdev_ops stm32_csi_subdev_ops = { + .core = &stm32_csi_core_ops, + .pad = &stm32_csi_pad_ops, + .video = &stm32_csi_video_ops, +}; + +static const struct v4l2_subdev_internal_ops stm32_csi_subdev_internal_ops = { + .init_state = stm32_csi_init_state, +}; + +static int stm32_csi_async_bound(struct v4l2_async_notifier *notifier, + struct v4l2_subdev *s_subdev, + struct v4l2_async_connection *asd) +{ + struct v4l2_subdev *sd = notifier->sd; + struct stm32_csi_dev *csidev = to_csidev(sd); + int remote_pad; + + remote_pad = media_entity_get_fwnode_pad(&s_subdev->entity, + s_subdev->fwnode, + MEDIA_PAD_FL_SOURCE); + if (remote_pad < 0) { + dev_err(csidev->dev, "Couldn't find output pad for subdev %s\n", + s_subdev->name); + return remote_pad; + } + + csidev->s_subdev = s_subdev; + csidev->s_subdev_pad_nb = remote_pad; + + return media_create_pad_link(&csidev->s_subdev->entity, + remote_pad, &csidev->sd.entity, + STM32_CSI_PAD_SINK, + MEDIA_LNK_FL_ENABLED | + MEDIA_LNK_FL_IMMUTABLE); +} + +static const struct v4l2_async_notifier_operations stm32_csi_notifier_ops = { + .bound = stm32_csi_async_bound, +}; + +static irqreturn_t stm32_csi_irq_thread(int irq, void *arg) +{ + struct stm32_csi_dev *csidev = arg; + unsigned long flags; + u32 sr0, sr1; + int i; + + sr0 = readl_relaxed(csidev->base + STM32_CSI_SR0); + sr1 = readl_relaxed(csidev->base + STM32_CSI_SR1); + + /* Clear interrupt */ + writel_relaxed(sr0 & STM32_CSI_SR0_ERRORS, + csidev->base + STM32_CSI_FCR0); + writel_relaxed(sr1 & STM32_CSI_SR1_ERRORS, + csidev->base + STM32_CSI_FCR1); + + spin_lock_irqsave(&csidev->slock, flags); + + for (i = 0; i < STM32_CSI_NUM_SR0_EVENTS; i++) + if (sr0 & stm32_csi_events_sr0[i].mask) + csidev->sr0_counters[i]++; + + for (i = 0; i < STM32_CSI_NUM_SR1_EVENTS; i++) + if (sr1 & stm32_csi_events_sr1[i].mask) + csidev->sr1_counters[i]++; + + spin_unlock_irqrestore(&csidev->slock, flags); + + return IRQ_HANDLED; +} + +static int stm32_csi_get_resources(struct stm32_csi_dev *csidev, + struct platform_device *pdev) +{ + int irq, ret, i; + + csidev->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); + if (IS_ERR(csidev->base)) + return dev_err_probe(&pdev->dev, PTR_ERR(csidev->base), + "Failed to ioremap resource\n"); + + for (i = 0; i < STM32_CSI_CLK_NB; i++) + csidev->clks[i].id = stm32_csi_clks_id[i]; + + ret = devm_clk_bulk_get(&pdev->dev, STM32_CSI_CLK_NB, + csidev->clks); + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "Couldn't get clks\n"); + + csidev->supplies[0].supply = "vdd"; + csidev->supplies[1].supply = "vdda18"; + ret = devm_regulator_bulk_get(&pdev->dev, ARRAY_SIZE(csidev->supplies), + csidev->supplies); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Failed to request regulator vdd\n"); + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, + stm32_csi_irq_thread, IRQF_ONESHOT, + dev_name(&pdev->dev), csidev); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Unable to request irq"); + + return 0; +} + +static int stm32_csi_parse_dt(struct stm32_csi_dev *csidev) +{ + struct v4l2_fwnode_endpoint v4l2_ep = { .bus_type = V4L2_MBUS_CSI2_DPHY }; + struct v4l2_async_connection *asd; + struct fwnode_handle *ep; + int ret; + + /* Get bus characteristics from devicetree */ + ep = fwnode_graph_get_endpoint_by_id(dev_fwnode(csidev->dev), 0, 0, + FWNODE_GRAPH_ENDPOINT_NEXT); + if (!ep) { + dev_err(csidev->dev, "Could not find the endpoint\n"); + return -ENODEV; + } + + ret = v4l2_fwnode_endpoint_parse(ep, &v4l2_ep); + fwnode_handle_put(ep); + if (ret) { + dev_err(csidev->dev, "Could not parse v4l2 endpoint\n"); + return ret; + } + + csidev->num_lanes = v4l2_ep.bus.mipi_csi2.num_data_lanes; + if (csidev->num_lanes > STM32_CSI_LANES_MAX) { + dev_err(csidev->dev, "Unsupported number of data-lanes: %d\n", + csidev->num_lanes); + return -EINVAL; + } + + memcpy(csidev->lanes, v4l2_ep.bus.mipi_csi2.data_lanes, + sizeof(csidev->lanes)); + + ep = fwnode_graph_get_next_endpoint(dev_fwnode(csidev->dev), NULL); + if (!ep) { + dev_err(csidev->dev, "Failed to get next endpoint\n"); + return -EINVAL; + } + + v4l2_async_subdev_nf_init(&csidev->notifier, &csidev->sd); + + asd = v4l2_async_nf_add_fwnode_remote(&csidev->notifier, ep, + struct v4l2_async_connection); + + fwnode_handle_put(ep); + + if (IS_ERR(asd)) { + dev_err(csidev->dev, "Failed to add fwnode remote subdev\n"); + return PTR_ERR(asd); + } + + csidev->notifier.ops = &stm32_csi_notifier_ops; + + ret = v4l2_async_nf_register(&csidev->notifier); + if (ret) { + dev_err(csidev->dev, "Failed to register notifier\n"); + v4l2_async_nf_cleanup(&csidev->notifier); + return ret; + } + + return ret; +} + +static int stm32_csi_probe(struct platform_device *pdev) +{ + struct stm32_csi_dev *csidev; + struct reset_control *rstc; + int ret; + + csidev = devm_kzalloc(&pdev->dev, sizeof(*csidev), GFP_KERNEL); + if (!csidev) + return -ENOMEM; + + platform_set_drvdata(pdev, csidev); + csidev->dev = &pdev->dev; + + spin_lock_init(&csidev->slock); + + ret = stm32_csi_get_resources(csidev, pdev); + if (ret) + goto err_free_priv; + + ret = stm32_csi_parse_dt(csidev); + if (ret) + goto err_free_priv; + + csidev->sd.owner = THIS_MODULE; + csidev->sd.dev = &pdev->dev; + csidev->sd.internal_ops = &stm32_csi_subdev_internal_ops; + v4l2_subdev_init(&csidev->sd, &stm32_csi_subdev_ops); + v4l2_set_subdevdata(&csidev->sd, &pdev->dev); + snprintf(csidev->sd.name, sizeof(csidev->sd.name), "%s", + dev_name(&pdev->dev)); + + /* Create our media pads */ + csidev->sd.entity.function = MEDIA_ENT_F_VID_IF_BRIDGE; + csidev->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE; + csidev->pads[STM32_CSI_PAD_SINK].flags = MEDIA_PAD_FL_SINK; + csidev->pads[STM32_CSI_PAD_SOURCE].flags = MEDIA_PAD_FL_SOURCE; + + ret = media_entity_pads_init(&csidev->sd.entity, STM32_CSI_PAD_MAX, + csidev->pads); + if (ret) + goto err_cleanup; + + ret = v4l2_subdev_init_finalize(&csidev->sd); + if (ret < 0) + goto err_cleanup; + + ret = v4l2_async_register_subdev(&csidev->sd); + if (ret < 0) + goto err_cleanup; + + /* Reset device */ + rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (IS_ERR(rstc)) { + ret = dev_err_probe(&pdev->dev, PTR_ERR(rstc), + "Couldn't get reset control\n"); + goto err_cleanup; + } + + ret = reset_control_assert(rstc); + if (ret) { + ret = dev_err_probe(&pdev->dev, ret, + "Failed to assert the reset line\n"); + goto err_cleanup; + } + + usleep_range(3000, 5000); + + ret = reset_control_deassert(rstc); + if (ret) { + ret = dev_err_probe(&pdev->dev, ret, + "Failed to deassert the reset line\n"); + goto err_cleanup; + } + + pm_runtime_enable(&pdev->dev); + + dev_info(&pdev->dev, + "Probed CSI with %u lanes\n", csidev->num_lanes); + + return 0; + +err_cleanup: + v4l2_async_nf_cleanup(&csidev->notifier); +err_free_priv: + return ret; +} + +static void stm32_csi_remove(struct platform_device *pdev) +{ + struct stm32_csi_dev *csidev = platform_get_drvdata(pdev); + + v4l2_async_unregister_subdev(&csidev->sd); + + pm_runtime_disable(&pdev->dev); +} + +static int stm32_csi_runtime_suspend(struct device *dev) +{ + struct stm32_csi_dev *csidev = dev_get_drvdata(dev); + int ret; + + clk_bulk_disable_unprepare(STM32_CSI_CLK_NB, csidev->clks); + + ret = regulator_bulk_disable(ARRAY_SIZE(csidev->supplies), + csidev->supplies); + if (ret < 0) + dev_err(dev, "cannot disable regulators %d\n", ret); + + return 0; +} + +static int stm32_csi_runtime_resume(struct device *dev) +{ + struct stm32_csi_dev *csidev = dev_get_drvdata(dev); + int ret; + + ret = regulator_bulk_enable(ARRAY_SIZE(csidev->supplies), + csidev->supplies); + if (ret) + goto error_out; + + ret = clk_bulk_prepare_enable(STM32_CSI_CLK_NB, csidev->clks); + if (ret) + goto error_disable_supplies; + + return 0; + +error_disable_supplies: + ret = regulator_bulk_disable(ARRAY_SIZE(csidev->supplies), csidev->supplies); + if (ret < 0) + dev_err(dev, "cannot disable regulators %d\n", ret); +error_out: + dev_err(csidev->dev, "Failed to resume: %d\n", ret); + + return ret; +} + +static const struct of_device_id stm32_csi_of_table[] = { + { .compatible = "st,stm32mp25-csi", }, + { /* end node */ }, +}; +MODULE_DEVICE_TABLE(of, stm32_csi_of_table); + +static const struct dev_pm_ops stm32_csi_pm_ops = { + RUNTIME_PM_OPS(stm32_csi_runtime_suspend, + stm32_csi_runtime_resume, NULL) +}; + +static struct platform_driver stm32_csi_driver = { + .driver = { + .name = "stm32-csi", + .of_match_table = stm32_csi_of_table, + .pm = pm_ptr(&stm32_csi_pm_ops), + }, + .probe = stm32_csi_probe, + .remove = stm32_csi_remove, +}; + +module_platform_driver(stm32_csi_driver); + +MODULE_AUTHOR("Alain Volmat "); +MODULE_DESCRIPTION("STM32 CSI controller"); +MODULE_LICENSE("GPL"); diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/Makefile b/drivers/media/platform/st/stm32/stm32-dcmipp/Makefile index 8920d9388a21..159105fb40b8 100644 --- a/drivers/media/platform/st/stm32/stm32-dcmipp/Makefile +++ b/drivers/media/platform/st/stm32/stm32-dcmipp/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -stm32-dcmipp-y := dcmipp-core.o dcmipp-common.o dcmipp-parallel.o dcmipp-byteproc.o dcmipp-bytecap.o +stm32-dcmipp-y := dcmipp-core.o dcmipp-common.o dcmipp-input.o dcmipp-byteproc.o dcmipp-bytecap.o obj-$(CONFIG_VIDEO_STM32_DCMIPP) += stm32-dcmipp.o diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c index 7edd49bfe7e5..1c1b6b48918e 100644 --- a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c +++ b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c @@ -56,15 +56,32 @@ struct dcmipp_bytecap_pix_map { static const struct dcmipp_bytecap_pix_map dcmipp_bytecap_pix_map_list[] = { PIXMAP_MBUS_PFMT(RGB565_2X8_LE, RGB565), + PIXMAP_MBUS_PFMT(RGB565_1X16, RGB565), PIXMAP_MBUS_PFMT(YUYV8_2X8, YUYV), + PIXMAP_MBUS_PFMT(YUYV8_1X16, YUYV), PIXMAP_MBUS_PFMT(YVYU8_2X8, YVYU), + PIXMAP_MBUS_PFMT(YVYU8_1X16, YVYU), PIXMAP_MBUS_PFMT(UYVY8_2X8, UYVY), + PIXMAP_MBUS_PFMT(UYVY8_1X16, UYVY), PIXMAP_MBUS_PFMT(VYUY8_2X8, VYUY), + PIXMAP_MBUS_PFMT(VYUY8_1X16, VYUY), PIXMAP_MBUS_PFMT(Y8_1X8, GREY), PIXMAP_MBUS_PFMT(SBGGR8_1X8, SBGGR8), PIXMAP_MBUS_PFMT(SGBRG8_1X8, SGBRG8), PIXMAP_MBUS_PFMT(SGRBG8_1X8, SGRBG8), PIXMAP_MBUS_PFMT(SRGGB8_1X8, SRGGB8), + PIXMAP_MBUS_PFMT(SBGGR10_1X10, SBGGR10), + PIXMAP_MBUS_PFMT(SGBRG10_1X10, SGBRG10), + PIXMAP_MBUS_PFMT(SGRBG10_1X10, SGRBG10), + PIXMAP_MBUS_PFMT(SRGGB10_1X10, SRGGB10), + PIXMAP_MBUS_PFMT(SBGGR12_1X12, SBGGR12), + PIXMAP_MBUS_PFMT(SGBRG12_1X12, SGBRG12), + PIXMAP_MBUS_PFMT(SGRBG12_1X12, SGRBG12), + PIXMAP_MBUS_PFMT(SRGGB12_1X12, SRGGB12), + PIXMAP_MBUS_PFMT(SBGGR14_1X14, SBGGR14), + PIXMAP_MBUS_PFMT(SGBRG14_1X14, SGBRG14), + PIXMAP_MBUS_PFMT(SGRBG14_1X14, SGRBG14), + PIXMAP_MBUS_PFMT(SRGGB14_1X14, SRGGB14), PIXMAP_MBUS_PFMT(JPEG_1X8, JPEG), }; @@ -112,6 +129,7 @@ struct dcmipp_bytecap_device { u32 sequence; struct media_pipeline pipe; struct v4l2_subdev *s_subdev; + u32 s_subdev_pad_nb; enum dcmipp_state state; @@ -250,34 +268,34 @@ static int dcmipp_bytecap_enum_fmt_vid_cap(struct file *file, void *priv, { const struct dcmipp_bytecap_pix_map *vpix; unsigned int index = f->index; - unsigned int i; + unsigned int i, prev_pixelformat = 0; - if (f->mbus_code) { - /* - * If a media bus code is specified, only enumerate formats - * compatible with it. - */ - for (i = 0; i < ARRAY_SIZE(dcmipp_bytecap_pix_map_list); i++) { - vpix = &dcmipp_bytecap_pix_map_list[i]; - if (vpix->code != f->mbus_code) - continue; + /* + * List up all formats (or only ones matching f->mbus_code), taking + * care of removing duplicated entries (due to support of both + * parallel & csi 16 bits formats + */ + for (i = 0; i < ARRAY_SIZE(dcmipp_bytecap_pix_map_list); i++) { + vpix = &dcmipp_bytecap_pix_map_list[i]; + /* Skip formats not matching requested mbus code */ + if (f->mbus_code && vpix->code != f->mbus_code) + continue; - if (index == 0) - break; + /* Skip duplicated pixelformat */ + if (vpix->pixelformat == prev_pixelformat) + continue; - index--; - } + prev_pixelformat = vpix->pixelformat; - if (i == ARRAY_SIZE(dcmipp_bytecap_pix_map_list)) - return -EINVAL; - } else { - /* Otherwise, enumerate all formats. */ - if (f->index >= ARRAY_SIZE(dcmipp_bytecap_pix_map_list)) - return -EINVAL; + if (index == 0) + break; - vpix = &dcmipp_bytecap_pix_map_list[f->index]; + index--; } + if (i == ARRAY_SIZE(dcmipp_bytecap_pix_map_list)) + return -EINVAL; + f->pixelformat = vpix->pixelformat; return 0; @@ -337,33 +355,6 @@ static const struct v4l2_ioctl_ops dcmipp_bytecap_ioctl_ops = { .vidioc_streamoff = vb2_ioctl_streamoff, }; -static int dcmipp_pipeline_s_stream(struct dcmipp_bytecap_device *vcap, - int state) -{ - struct media_pad *pad; - int ret; - - /* - * Get source subdev - since link is IMMUTABLE, pointer is cached - * within the dcmipp_bytecap_device structure - */ - if (!vcap->s_subdev) { - pad = media_pad_remote_pad_first(&vcap->vdev.entity.pads[0]); - if (!pad || !is_media_entity_v4l2_subdev(pad->entity)) - return -EINVAL; - vcap->s_subdev = media_entity_to_v4l2_subdev(pad->entity); - } - - ret = v4l2_subdev_call(vcap->s_subdev, video, s_stream, state); - if (ret < 0) { - dev_err(vcap->dev, "failed to %s streaming (%d)\n", - state ? "start" : "stop", ret); - return ret; - } - - return 0; -} - static void dcmipp_start_capture(struct dcmipp_bytecap_device *vcap, struct dcmipp_buf *buf) { @@ -395,11 +386,24 @@ static int dcmipp_bytecap_start_streaming(struct vb2_queue *vq, struct dcmipp_bytecap_device *vcap = vb2_get_drv_priv(vq); struct media_entity *entity = &vcap->vdev.entity; struct dcmipp_buf *buf; + struct media_pad *pad; int ret; vcap->sequence = 0; memset(&vcap->count, 0, sizeof(vcap->count)); + /* + * Get source subdev - since link is IMMUTABLE, pointer is cached + * within the dcmipp_bytecap_device structure + */ + if (!vcap->s_subdev) { + pad = media_pad_remote_pad_first(&vcap->vdev.entity.pads[0]); + if (!pad || !is_media_entity_v4l2_subdev(pad->entity)) + return -EINVAL; + vcap->s_subdev = media_entity_to_v4l2_subdev(pad->entity); + vcap->s_subdev_pad_nb = pad->index; + } + ret = pm_runtime_resume_and_get(vcap->dev); if (ret < 0) { dev_err(vcap->dev, "%s: Failed to start streaming, cannot get sync (%d)\n", @@ -414,7 +418,8 @@ static int dcmipp_bytecap_start_streaming(struct vb2_queue *vq, goto err_pm_put; } - ret = dcmipp_pipeline_s_stream(vcap, 1); + ret = v4l2_subdev_enable_streams(vcap->s_subdev, + vcap->s_subdev_pad_nb, BIT_ULL(0)); if (ret) goto err_media_pipeline_stop; @@ -482,7 +487,10 @@ static void dcmipp_bytecap_stop_streaming(struct vb2_queue *vq) int ret; u32 status; - dcmipp_pipeline_s_stream(vcap, 0); + ret = v4l2_subdev_disable_streams(vcap->s_subdev, + vcap->s_subdev_pad_nb, BIT_ULL(0)); + if (ret) + dev_warn(vcap->dev, "Failed to disable stream\n"); /* Stop the media pipeline */ media_pipeline_stop(vcap->vdev.entity.pads); @@ -810,8 +818,7 @@ static int dcmipp_bytecap_link_validate(struct media_link *link) .which = V4L2_SUBDEV_FORMAT_ACTIVE, .pad = link->source->index, }; - const struct dcmipp_bytecap_pix_map *vpix; - int ret; + int ret, i; ret = v4l2_subdev_call(source_sd, pad, get_fmt, NULL, &source_fmt); if (ret < 0) @@ -825,10 +832,17 @@ static int dcmipp_bytecap_link_validate(struct media_link *link) return -EINVAL; } - vpix = dcmipp_bytecap_pix_map_by_pixelformat(vcap->format.pixelformat); - if (source_fmt.format.code != vpix->code) { - dev_err(vcap->dev, "Wrong mbus_code 0x%x, (0x%x expected)\n", - vpix->code, source_fmt.format.code); + for (i = 0; i < ARRAY_SIZE(dcmipp_bytecap_pix_map_list); i++) { + if (dcmipp_bytecap_pix_map_list[i].pixelformat == + vcap->format.pixelformat && + dcmipp_bytecap_pix_map_list[i].code == + source_fmt.format.code) + break; + } + + if (i == ARRAY_SIZE(dcmipp_bytecap_pix_map_list)) { + dev_err(vcap->dev, "mbus code 0x%x do not match capture device format (0x%x)\n", + vcap->format.pixelformat, source_fmt.format.code); return -EINVAL; } @@ -887,7 +901,7 @@ struct dcmipp_ent_device *dcmipp_bytecap_ent_init(struct device *dev, q->dev = dev; /* DCMIPP requires 16 bytes aligned buffers */ - ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32) & ~0x0f); + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); if (ret) { dev_err(dev, "Failed to set DMA mask\n"); goto err_mutex_destroy; diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-byteproc.c b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-byteproc.c index 5a361ad6b023..3c742a546441 100644 --- a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-byteproc.c +++ b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-byteproc.c @@ -48,15 +48,32 @@ struct dcmipp_byteproc_pix_map { } static const struct dcmipp_byteproc_pix_map dcmipp_byteproc_pix_map_list[] = { PIXMAP_MBUS_BPP(RGB565_2X8_LE, 2), + PIXMAP_MBUS_BPP(RGB565_1X16, 2), PIXMAP_MBUS_BPP(YUYV8_2X8, 2), + PIXMAP_MBUS_BPP(YUYV8_1X16, 2), PIXMAP_MBUS_BPP(YVYU8_2X8, 2), + PIXMAP_MBUS_BPP(YVYU8_1X16, 2), PIXMAP_MBUS_BPP(UYVY8_2X8, 2), + PIXMAP_MBUS_BPP(UYVY8_1X16, 2), PIXMAP_MBUS_BPP(VYUY8_2X8, 2), + PIXMAP_MBUS_BPP(VYUY8_1X16, 2), PIXMAP_MBUS_BPP(Y8_1X8, 1), PIXMAP_MBUS_BPP(SBGGR8_1X8, 1), PIXMAP_MBUS_BPP(SGBRG8_1X8, 1), PIXMAP_MBUS_BPP(SGRBG8_1X8, 1), PIXMAP_MBUS_BPP(SRGGB8_1X8, 1), + PIXMAP_MBUS_BPP(SBGGR10_1X10, 2), + PIXMAP_MBUS_BPP(SGBRG10_1X10, 2), + PIXMAP_MBUS_BPP(SGRBG10_1X10, 2), + PIXMAP_MBUS_BPP(SRGGB10_1X10, 2), + PIXMAP_MBUS_BPP(SBGGR12_1X12, 2), + PIXMAP_MBUS_BPP(SGBRG12_1X12, 2), + PIXMAP_MBUS_BPP(SGRBG12_1X12, 2), + PIXMAP_MBUS_BPP(SRGGB12_1X12, 2), + PIXMAP_MBUS_BPP(SBGGR14_1X14, 2), + PIXMAP_MBUS_BPP(SGBRG14_1X14, 2), + PIXMAP_MBUS_BPP(SGRBG14_1X14, 2), + PIXMAP_MBUS_BPP(SRGGB14_1X14, 2), PIXMAP_MBUS_BPP(JPEG_1X8, 1), }; @@ -78,7 +95,6 @@ struct dcmipp_byteproc_device { struct v4l2_subdev sd; struct device *dev; void __iomem *regs; - bool streaming; }; static const struct v4l2_mbus_framefmt fmt_default = { @@ -239,11 +255,10 @@ static int dcmipp_byteproc_set_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_format *fmt) { - struct dcmipp_byteproc_device *byteproc = v4l2_get_subdevdata(sd); struct v4l2_mbus_framefmt *mf; struct v4l2_rect *crop, *compose; - if (byteproc->streaming) + if (v4l2_subdev_is_streaming(sd)) return -EBUSY; mf = v4l2_subdev_state_get_format(sd_state, fmt->pad); @@ -382,30 +397,19 @@ static int dcmipp_byteproc_set_selection(struct v4l2_subdev *sd, return 0; } -static const struct v4l2_subdev_pad_ops dcmipp_byteproc_pad_ops = { - .enum_mbus_code = dcmipp_byteproc_enum_mbus_code, - .enum_frame_size = dcmipp_byteproc_enum_frame_size, - .get_fmt = v4l2_subdev_get_fmt, - .set_fmt = dcmipp_byteproc_set_fmt, - .get_selection = dcmipp_byteproc_get_selection, - .set_selection = dcmipp_byteproc_set_selection, -}; - static int dcmipp_byteproc_configure_scale_crop - (struct dcmipp_byteproc_device *byteproc) + (struct dcmipp_byteproc_device *byteproc, + struct v4l2_subdev_state *state) { const struct dcmipp_byteproc_pix_map *vpix; - struct v4l2_subdev_state *state; struct v4l2_mbus_framefmt *sink_fmt; u32 hprediv, vprediv; struct v4l2_rect *compose, *crop; u32 val = 0; - state = v4l2_subdev_lock_and_get_active_state(&byteproc->sd); sink_fmt = v4l2_subdev_state_get_format(state, 0); compose = v4l2_subdev_state_get_compose(state, 0); crop = v4l2_subdev_state_get_crop(state, 1); - v4l2_subdev_unlock_state(state); /* find output format bpp */ vpix = dcmipp_byteproc_pix_map_by_code(sink_fmt->code); @@ -460,48 +464,73 @@ static int dcmipp_byteproc_configure_scale_crop return 0; } -static int dcmipp_byteproc_s_stream(struct v4l2_subdev *sd, int enable) +static int dcmipp_byteproc_enable_streams(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state, + u32 pad, u64 streams_mask) { struct dcmipp_byteproc_device *byteproc = v4l2_get_subdevdata(sd); struct v4l2_subdev *s_subdev; - struct media_pad *pad; - int ret = 0; + struct media_pad *s_pad; + int ret; /* Get source subdev */ - pad = media_pad_remote_pad_first(&sd->entity.pads[0]); - if (!pad || !is_media_entity_v4l2_subdev(pad->entity)) + s_pad = media_pad_remote_pad_first(&sd->entity.pads[0]); + if (!s_pad || !is_media_entity_v4l2_subdev(s_pad->entity)) return -EINVAL; - s_subdev = media_entity_to_v4l2_subdev(pad->entity); + s_subdev = media_entity_to_v4l2_subdev(s_pad->entity); - if (enable) { - ret = dcmipp_byteproc_configure_scale_crop(byteproc); - if (ret) - return ret; + ret = dcmipp_byteproc_configure_scale_crop(byteproc, state); + if (ret) + return ret; - ret = v4l2_subdev_call(s_subdev, video, s_stream, enable); - if (ret < 0) { - dev_err(byteproc->dev, - "failed to start source subdev streaming (%d)\n", - ret); - return ret; - } - } else { - ret = v4l2_subdev_call(s_subdev, video, s_stream, enable); - if (ret < 0) { - dev_err(byteproc->dev, - "failed to stop source subdev streaming (%d)\n", - ret); - return ret; - } + ret = v4l2_subdev_enable_streams(s_subdev, s_pad->index, BIT_ULL(0)); + if (ret < 0) { + dev_err(byteproc->dev, + "failed to start source subdev streaming (%d)\n", ret); + return ret; } - byteproc->streaming = enable; - return 0; } +static int dcmipp_byteproc_disable_streams(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state, + u32 pad, u64 streams_mask) +{ + struct dcmipp_byteproc_device *byteproc = v4l2_get_subdevdata(sd); + struct v4l2_subdev *s_subdev; + struct media_pad *s_pad; + int ret; + + /* Get source subdev */ + s_pad = media_pad_remote_pad_first(&sd->entity.pads[0]); + if (!s_pad || !is_media_entity_v4l2_subdev(s_pad->entity)) + return -EINVAL; + s_subdev = media_entity_to_v4l2_subdev(s_pad->entity); + + ret = v4l2_subdev_disable_streams(s_subdev, s_pad->index, BIT_ULL(0)); + if (ret < 0) { + dev_err(byteproc->dev, + "failed to start source subdev streaming (%d)\n", ret); + return ret; + } + + return 0; +} + +static const struct v4l2_subdev_pad_ops dcmipp_byteproc_pad_ops = { + .enum_mbus_code = dcmipp_byteproc_enum_mbus_code, + .enum_frame_size = dcmipp_byteproc_enum_frame_size, + .get_fmt = v4l2_subdev_get_fmt, + .set_fmt = dcmipp_byteproc_set_fmt, + .get_selection = dcmipp_byteproc_get_selection, + .set_selection = dcmipp_byteproc_set_selection, + .enable_streams = dcmipp_byteproc_enable_streams, + .disable_streams = dcmipp_byteproc_disable_streams, +}; + static const struct v4l2_subdev_video_ops dcmipp_byteproc_video_ops = { - .s_stream = dcmipp_byteproc_s_stream, + .s_stream = v4l2_subdev_s_stream_helper, }; static const struct v4l2_subdev_ops dcmipp_byteproc_ops = { diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-common.h b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-common.h index 7a7cf43baf24..fe5f97233f5e 100644 --- a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-common.h +++ b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-common.h @@ -199,11 +199,11 @@ static inline void __reg_clear(struct device *dev, void __iomem *base, u32 reg, } /* DCMIPP subdev init / release entry points */ -struct dcmipp_ent_device *dcmipp_par_ent_init(struct device *dev, +struct dcmipp_ent_device *dcmipp_inp_ent_init(struct device *dev, const char *entity_name, struct v4l2_device *v4l2_dev, void __iomem *regs); -void dcmipp_par_ent_release(struct dcmipp_ent_device *ved); +void dcmipp_inp_ent_release(struct dcmipp_ent_device *ved); struct dcmipp_ent_device * dcmipp_byteproc_ent_init(struct device *dev, const char *entity_name, struct v4l2_device *v4l2_dev, void __iomem *regs); diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-core.c b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-core.c index 3806f7c6e2fe..71acf539e1f3 100644 --- a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-core.c +++ b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-core.c @@ -40,6 +40,7 @@ struct dcmipp_device { /* Hardware resources */ void __iomem *regs; + struct clk *mclk; struct clk *kclk; /* The pipeline configuration */ @@ -87,6 +88,7 @@ struct dcmipp_pipeline_config { size_t num_ents; const struct dcmipp_ent_link *links; size_t num_links; + u32 hw_revision; }; /* -------------------------------------------------------------------------- @@ -95,9 +97,9 @@ struct dcmipp_pipeline_config { static const struct dcmipp_ent_config stm32mp13_ent_config[] = { { - .name = "dcmipp_parallel", - .init = dcmipp_par_ent_init, - .release = dcmipp_par_ent_release, + .name = "dcmipp_input", + .init = dcmipp_inp_ent_init, + .release = dcmipp_inp_ent_release, }, { .name = "dcmipp_dump_postproc", @@ -111,22 +113,58 @@ static const struct dcmipp_ent_config stm32mp13_ent_config[] = { }, }; -#define ID_PARALLEL 0 +#define ID_INPUT 0 #define ID_DUMP_BYTEPROC 1 #define ID_DUMP_CAPTURE 2 static const struct dcmipp_ent_link stm32mp13_ent_links[] = { - DCMIPP_ENT_LINK(ID_PARALLEL, 1, ID_DUMP_BYTEPROC, 0, + DCMIPP_ENT_LINK(ID_INPUT, 1, ID_DUMP_BYTEPROC, 0, MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE), DCMIPP_ENT_LINK(ID_DUMP_BYTEPROC, 1, ID_DUMP_CAPTURE, 0, MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE), }; +#define DCMIPP_STM32MP13_VERR 0x10 static const struct dcmipp_pipeline_config stm32mp13_pipe_cfg = { .ents = stm32mp13_ent_config, .num_ents = ARRAY_SIZE(stm32mp13_ent_config), .links = stm32mp13_ent_links, - .num_links = ARRAY_SIZE(stm32mp13_ent_links) + .num_links = ARRAY_SIZE(stm32mp13_ent_links), + .hw_revision = DCMIPP_STM32MP13_VERR +}; + +static const struct dcmipp_ent_config stm32mp25_ent_config[] = { + { + .name = "dcmipp_input", + .init = dcmipp_inp_ent_init, + .release = dcmipp_inp_ent_release, + }, + { + .name = "dcmipp_dump_postproc", + .init = dcmipp_byteproc_ent_init, + .release = dcmipp_byteproc_ent_release, + }, + { + .name = "dcmipp_dump_capture", + .init = dcmipp_bytecap_ent_init, + .release = dcmipp_bytecap_ent_release, + }, +}; + +static const struct dcmipp_ent_link stm32mp25_ent_links[] = { + DCMIPP_ENT_LINK(ID_INPUT, 1, ID_DUMP_BYTEPROC, 0, + MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE), + DCMIPP_ENT_LINK(ID_DUMP_BYTEPROC, 1, ID_DUMP_CAPTURE, 0, + MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE), +}; + +#define DCMIPP_STM32MP25_VERR 0x30 +static const struct dcmipp_pipeline_config stm32mp25_pipe_cfg = { + .ents = stm32mp25_ent_config, + .num_ents = ARRAY_SIZE(stm32mp25_ent_config), + .links = stm32mp25_ent_links, + .num_links = ARRAY_SIZE(stm32mp25_ent_links), + .hw_revision = DCMIPP_STM32MP25_VERR }; #define LINK_FLAG_TO_STR(f) ((f) == 0 ? "" :\ @@ -209,6 +247,7 @@ err_init_entity: static const struct of_device_id dcmipp_of_match[] = { { .compatible = "st,stm32mp13-dcmipp", .data = &stm32mp13_pipe_cfg }, + { .compatible = "st,stm32mp25-dcmipp", .data = &stm32mp25_pipe_cfg }, { /* end node */ }, }; MODULE_DEVICE_TABLE(of, dcmipp_of_match); @@ -258,13 +297,22 @@ static int dcmipp_graph_notify_bound(struct v4l2_async_notifier *notifier, { struct dcmipp_device *dcmipp = notifier_to_dcmipp(notifier); unsigned int ret; - int src_pad; + int src_pad, i; struct dcmipp_ent_device *sink; - struct v4l2_fwnode_endpoint vep = { .bus_type = V4L2_MBUS_PARALLEL }; + struct v4l2_fwnode_endpoint vep = { 0 }; struct fwnode_handle *ep; + enum v4l2_mbus_type supported_types[] = { + V4L2_MBUS_PARALLEL, V4L2_MBUS_BT656, V4L2_MBUS_CSI2_DPHY + }; + int supported_types_nb = ARRAY_SIZE(supported_types); dev_dbg(dcmipp->dev, "Subdev \"%s\" bound\n", subdev->name); + /* Only MP25 supports CSI input */ + if (!of_device_is_compatible(dcmipp->dev->of_node, + "st,stm32mp25-dcmipp")) + supported_types_nb--; + /* * Link this sub-device to DCMIPP, it could be * a parallel camera sensor or a CSI-2 to parallel bridge @@ -281,21 +329,23 @@ static int dcmipp_graph_notify_bound(struct v4l2_async_notifier *notifier, return -ENODEV; } - /* Check for parallel bus-type first, then bt656 */ - ret = v4l2_fwnode_endpoint_parse(ep, &vep); - if (ret) { - vep.bus_type = V4L2_MBUS_BT656; + /* Check for supported MBUS type */ + for (i = 0; i < supported_types_nb; i++) { + vep.bus_type = supported_types[i]; ret = v4l2_fwnode_endpoint_parse(ep, &vep); - if (ret) { - dev_err(dcmipp->dev, "Could not parse the endpoint\n"); - fwnode_handle_put(ep); - return ret; - } + if (!ret) + break; } fwnode_handle_put(ep); - if (vep.bus.parallel.bus_width == 0) { + if (ret) { + dev_err(dcmipp->dev, "Could not parse the endpoint\n"); + return ret; + } + + if (vep.bus_type != V4L2_MBUS_CSI2_DPHY && + vep.bus.parallel.bus_width == 0) { dev_err(dcmipp->dev, "Invalid parallel interface bus-width\n"); return -ENODEV; } @@ -308,11 +358,13 @@ static int dcmipp_graph_notify_bound(struct v4l2_async_notifier *notifier, return -ENODEV; } - /* Parallel input device detected, connect it to parallel subdev */ - sink = dcmipp->entity[ID_PARALLEL]; - sink->bus.flags = vep.bus.parallel.flags; - sink->bus.bus_width = vep.bus.parallel.bus_width; - sink->bus.data_shift = vep.bus.parallel.data_shift; + /* Connect input device to the dcmipp_input subdev */ + sink = dcmipp->entity[ID_INPUT]; + if (vep.bus_type != V4L2_MBUS_CSI2_DPHY) { + sink->bus.flags = vep.bus.parallel.flags; + sink->bus.bus_width = vep.bus.parallel.bus_width; + sink->bus.data_shift = vep.bus.parallel.data_shift; + } sink->bus_type = vep.bus_type; ret = media_create_pad_link(&subdev->entity, src_pad, sink->ent, 0, MEDIA_LNK_FL_IMMUTABLE | @@ -411,7 +463,7 @@ static int dcmipp_graph_init(struct dcmipp_device *dcmipp) static int dcmipp_probe(struct platform_device *pdev) { struct dcmipp_device *dcmipp; - struct clk *kclk; + struct clk *kclk, *mclk; const struct dcmipp_pipeline_config *pipe_cfg; struct reset_control *rstc; int irq; @@ -471,12 +523,20 @@ static int dcmipp_probe(struct platform_device *pdev) return ret; } - kclk = devm_clk_get(&pdev->dev, NULL); + kclk = devm_clk_get(&pdev->dev, "kclk"); if (IS_ERR(kclk)) return dev_err_probe(&pdev->dev, PTR_ERR(kclk), "Unable to get kclk\n"); dcmipp->kclk = kclk; + if (!of_device_is_compatible(pdev->dev.of_node, "st,stm32mp13-dcmipp")) { + mclk = devm_clk_get(&pdev->dev, "mclk"); + if (IS_ERR(mclk)) + return dev_err_probe(&pdev->dev, PTR_ERR(mclk), + "Unable to get mclk\n"); + dcmipp->mclk = mclk; + } + dcmipp->entity = devm_kcalloc(&pdev->dev, dcmipp->pipe_cfg->num_ents, sizeof(*dcmipp->entity), GFP_KERNEL); if (!dcmipp->entity) @@ -496,6 +556,7 @@ static int dcmipp_probe(struct platform_device *pdev) /* Initialize media device */ strscpy(dcmipp->mdev.model, DCMIPP_MDEV_MODEL_NAME, sizeof(dcmipp->mdev.model)); + dcmipp->mdev.hw_revision = pipe_cfg->hw_revision; dcmipp->mdev.dev = &pdev->dev; media_device_init(&dcmipp->mdev); @@ -538,6 +599,7 @@ static int dcmipp_runtime_suspend(struct device *dev) struct dcmipp_device *dcmipp = dev_get_drvdata(dev); clk_disable_unprepare(dcmipp->kclk); + clk_disable_unprepare(dcmipp->mclk); return 0; } @@ -547,9 +609,17 @@ static int dcmipp_runtime_resume(struct device *dev) struct dcmipp_device *dcmipp = dev_get_drvdata(dev); int ret; + ret = clk_prepare_enable(dcmipp->mclk); + if (ret) { + dev_err(dev, "%s: Failed to prepare_enable mclk\n", __func__); + return ret; + } + ret = clk_prepare_enable(dcmipp->kclk); - if (ret) + if (ret) { + clk_disable_unprepare(dcmipp->mclk); dev_err(dev, "%s: Failed to prepare_enable kclk\n", __func__); + } return ret; } diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-input.c b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-input.c new file mode 100644 index 000000000000..7e5311b67d7e --- /dev/null +++ b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-input.c @@ -0,0 +1,540 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for STM32 Digital Camera Memory Interface Pixel Processor + * + * Copyright (C) STMicroelectronics SA 2023 + * Authors: Hugues Fruchet + * Alain Volmat + * for STMicroelectronics. + */ + +#include +#include +#include +#include + +#include "dcmipp-common.h" + +#define DCMIPP_PRCR 0x104 +#define DCMIPP_PRCR_FORMAT_SHIFT 16 +#define DCMIPP_PRCR_FORMAT_YUV422 0x1e +#define DCMIPP_PRCR_FORMAT_RGB565 0x22 +#define DCMIPP_PRCR_FORMAT_RAW8 0x2a +#define DCMIPP_PRCR_FORMAT_RAW10 0x2b +#define DCMIPP_PRCR_FORMAT_RAW12 0x2c +#define DCMIPP_PRCR_FORMAT_RAW14 0x2d +#define DCMIPP_PRCR_FORMAT_G8 0x4a +#define DCMIPP_PRCR_FORMAT_BYTE_STREAM 0x5a +#define DCMIPP_PRCR_ESS BIT(4) +#define DCMIPP_PRCR_PCKPOL BIT(5) +#define DCMIPP_PRCR_HSPOL BIT(6) +#define DCMIPP_PRCR_VSPOL BIT(7) +#define DCMIPP_PRCR_ENABLE BIT(14) +#define DCMIPP_PRCR_SWAPCYCLES BIT(25) + +#define DCMIPP_PRESCR 0x108 +#define DCMIPP_PRESUR 0x10c + +#define DCMIPP_CMCR 0x204 +#define DCMIPP_CMCR_INSEL BIT(0) + +#define DCMIPP_P0FSCR 0x404 +#define DCMIPP_P0FSCR_DTMODE_MASK GENMASK(17, 16) +#define DCMIPP_P0FSCR_DTMODE_SHIFT 16 +#define DCMIPP_P0FSCR_DTMODE_DTIDA 0x00 +#define DCMIPP_P0FSCR_DTMODE_ALLDT 0x03 +#define DCMIPP_P0FSCR_DTIDA_MASK GENMASK(5, 0) +#define DCMIPP_P0FSCR_DTIDA_SHIFT 0 + +#define IS_SINK(pad) (!(pad)) +#define IS_SRC(pad) ((pad)) + +struct dcmipp_inp_pix_map { + unsigned int code_sink; + unsigned int code_src; + /* Parallel related information */ + u8 prcr_format; + u8 prcr_swapcycles; + /* CSI related information */ + unsigned int dt; +}; + +#define PIXMAP_SINK_SRC_PRCR_SWAP(sink, src, prcr, swap, data_type) \ + { \ + .code_sink = MEDIA_BUS_FMT_##sink, \ + .code_src = MEDIA_BUS_FMT_##src, \ + .prcr_format = DCMIPP_PRCR_FORMAT_##prcr, \ + .prcr_swapcycles = swap, \ + .dt = data_type, \ + } +static const struct dcmipp_inp_pix_map dcmipp_inp_pix_map_list[] = { + /* RGB565 */ + PIXMAP_SINK_SRC_PRCR_SWAP(RGB565_2X8_LE, RGB565_2X8_LE, RGB565, 1, MIPI_CSI2_DT_RGB565), + PIXMAP_SINK_SRC_PRCR_SWAP(RGB565_2X8_BE, RGB565_2X8_LE, RGB565, 0, MIPI_CSI2_DT_RGB565), + PIXMAP_SINK_SRC_PRCR_SWAP(RGB565_1X16, RGB565_1X16, RGB565, 0, MIPI_CSI2_DT_RGB565), + /* YUV422 */ + PIXMAP_SINK_SRC_PRCR_SWAP(YUYV8_2X8, YUYV8_2X8, YUV422, 1, MIPI_CSI2_DT_YUV422_8B), + PIXMAP_SINK_SRC_PRCR_SWAP(YUYV8_1X16, YUYV8_1X16, YUV422, 0, MIPI_CSI2_DT_YUV422_8B), + PIXMAP_SINK_SRC_PRCR_SWAP(YUYV8_2X8, UYVY8_2X8, YUV422, 0, MIPI_CSI2_DT_YUV422_8B), + PIXMAP_SINK_SRC_PRCR_SWAP(UYVY8_2X8, UYVY8_2X8, YUV422, 1, MIPI_CSI2_DT_YUV422_8B), + PIXMAP_SINK_SRC_PRCR_SWAP(UYVY8_1X16, UYVY8_1X16, YUV422, 0, MIPI_CSI2_DT_YUV422_8B), + PIXMAP_SINK_SRC_PRCR_SWAP(UYVY8_2X8, YUYV8_2X8, YUV422, 0, MIPI_CSI2_DT_YUV422_8B), + PIXMAP_SINK_SRC_PRCR_SWAP(YVYU8_2X8, YVYU8_2X8, YUV422, 1, MIPI_CSI2_DT_YUV422_8B), + PIXMAP_SINK_SRC_PRCR_SWAP(YVYU8_1X16, YVYU8_1X16, YUV422, 0, MIPI_CSI2_DT_YUV422_8B), + PIXMAP_SINK_SRC_PRCR_SWAP(VYUY8_2X8, VYUY8_2X8, YUV422, 1, MIPI_CSI2_DT_YUV422_8B), + PIXMAP_SINK_SRC_PRCR_SWAP(VYUY8_1X16, VYUY8_1X16, YUV422, 0, MIPI_CSI2_DT_YUV422_8B), + /* GREY */ + PIXMAP_SINK_SRC_PRCR_SWAP(Y8_1X8, Y8_1X8, G8, 0, MIPI_CSI2_DT_RAW8), + /* Raw Bayer */ + PIXMAP_SINK_SRC_PRCR_SWAP(SBGGR8_1X8, SBGGR8_1X8, RAW8, 0, MIPI_CSI2_DT_RAW8), + PIXMAP_SINK_SRC_PRCR_SWAP(SGBRG8_1X8, SGBRG8_1X8, RAW8, 0, MIPI_CSI2_DT_RAW8), + PIXMAP_SINK_SRC_PRCR_SWAP(SGRBG8_1X8, SGRBG8_1X8, RAW8, 0, MIPI_CSI2_DT_RAW8), + PIXMAP_SINK_SRC_PRCR_SWAP(SRGGB8_1X8, SRGGB8_1X8, RAW8, 0, MIPI_CSI2_DT_RAW8), + PIXMAP_SINK_SRC_PRCR_SWAP(SBGGR10_1X10, SBGGR10_1X10, RAW10, 0, MIPI_CSI2_DT_RAW10), + PIXMAP_SINK_SRC_PRCR_SWAP(SGBRG10_1X10, SGBRG10_1X10, RAW10, 0, MIPI_CSI2_DT_RAW10), + PIXMAP_SINK_SRC_PRCR_SWAP(SGRBG10_1X10, SGRBG10_1X10, RAW10, 0, MIPI_CSI2_DT_RAW10), + PIXMAP_SINK_SRC_PRCR_SWAP(SRGGB10_1X10, SRGGB10_1X10, RAW10, 0, MIPI_CSI2_DT_RAW10), + PIXMAP_SINK_SRC_PRCR_SWAP(SBGGR12_1X12, SBGGR12_1X12, RAW12, 0, MIPI_CSI2_DT_RAW12), + PIXMAP_SINK_SRC_PRCR_SWAP(SGBRG12_1X12, SGBRG12_1X12, RAW12, 0, MIPI_CSI2_DT_RAW12), + PIXMAP_SINK_SRC_PRCR_SWAP(SGRBG12_1X12, SGRBG12_1X12, RAW12, 0, MIPI_CSI2_DT_RAW12), + PIXMAP_SINK_SRC_PRCR_SWAP(SRGGB12_1X12, SRGGB12_1X12, RAW12, 0, MIPI_CSI2_DT_RAW12), + PIXMAP_SINK_SRC_PRCR_SWAP(SBGGR14_1X14, SBGGR14_1X14, RAW14, 0, MIPI_CSI2_DT_RAW14), + PIXMAP_SINK_SRC_PRCR_SWAP(SGBRG14_1X14, SGBRG14_1X14, RAW14, 0, MIPI_CSI2_DT_RAW14), + PIXMAP_SINK_SRC_PRCR_SWAP(SGRBG14_1X14, SGRBG14_1X14, RAW14, 0, MIPI_CSI2_DT_RAW14), + PIXMAP_SINK_SRC_PRCR_SWAP(SRGGB14_1X14, SRGGB14_1X14, RAW14, 0, MIPI_CSI2_DT_RAW14), + /* JPEG */ + PIXMAP_SINK_SRC_PRCR_SWAP(JPEG_1X8, JPEG_1X8, BYTE_STREAM, 0, 0), +}; + +/* + * Search through the pix_map table, skipping two consecutive entry with the + * same code + */ +static inline const struct dcmipp_inp_pix_map *dcmipp_inp_pix_map_by_index + (unsigned int index, + unsigned int pad) +{ + unsigned int i = 0; + u32 prev_code = 0, cur_code; + + while (i < ARRAY_SIZE(dcmipp_inp_pix_map_list)) { + if (IS_SRC(pad)) + cur_code = dcmipp_inp_pix_map_list[i].code_src; + else + cur_code = dcmipp_inp_pix_map_list[i].code_sink; + + if (cur_code == prev_code) { + i++; + continue; + } + prev_code = cur_code; + + if (index == 0) + break; + i++; + index--; + } + + if (i >= ARRAY_SIZE(dcmipp_inp_pix_map_list)) + return NULL; + + return &dcmipp_inp_pix_map_list[i]; +} + +static inline const struct dcmipp_inp_pix_map *dcmipp_inp_pix_map_by_code + (u32 code_sink, u32 code_src) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(dcmipp_inp_pix_map_list); i++) { + if ((dcmipp_inp_pix_map_list[i].code_sink == code_sink && + dcmipp_inp_pix_map_list[i].code_src == code_src) || + (dcmipp_inp_pix_map_list[i].code_sink == code_src && + dcmipp_inp_pix_map_list[i].code_src == code_sink) || + (dcmipp_inp_pix_map_list[i].code_sink == code_sink && + code_src == 0) || + (code_sink == 0 && + dcmipp_inp_pix_map_list[i].code_src == code_src)) + return &dcmipp_inp_pix_map_list[i]; + } + return NULL; +} + +struct dcmipp_inp_device { + struct dcmipp_ent_device ved; + struct v4l2_subdev sd; + struct device *dev; + void __iomem *regs; +}; + +static const struct v4l2_mbus_framefmt fmt_default = { + .width = DCMIPP_FMT_WIDTH_DEFAULT, + .height = DCMIPP_FMT_HEIGHT_DEFAULT, + .code = MEDIA_BUS_FMT_RGB565_2X8_LE, + .field = V4L2_FIELD_NONE, + .colorspace = DCMIPP_COLORSPACE_DEFAULT, + .ycbcr_enc = DCMIPP_YCBCR_ENC_DEFAULT, + .quantization = DCMIPP_QUANTIZATION_DEFAULT, + .xfer_func = DCMIPP_XFER_FUNC_DEFAULT, +}; + +static int dcmipp_inp_init_state(struct v4l2_subdev *sd, + struct v4l2_subdev_state *sd_state) +{ + unsigned int i; + + for (i = 0; i < sd->entity.num_pads; i++) { + struct v4l2_mbus_framefmt *mf; + + mf = v4l2_subdev_state_get_format(sd_state, i); + *mf = fmt_default; + } + + return 0; +} + +static int dcmipp_inp_enum_mbus_code(struct v4l2_subdev *sd, + struct v4l2_subdev_state *sd_state, + struct v4l2_subdev_mbus_code_enum *code) +{ + const struct dcmipp_inp_pix_map *vpix = + dcmipp_inp_pix_map_by_index(code->index, code->pad); + + if (!vpix) + return -EINVAL; + + code->code = IS_SRC(code->pad) ? vpix->code_src : vpix->code_sink; + + return 0; +} + +static int dcmipp_inp_enum_frame_size(struct v4l2_subdev *sd, + struct v4l2_subdev_state *sd_state, + struct v4l2_subdev_frame_size_enum *fse) +{ + const struct dcmipp_inp_pix_map *vpix; + + if (fse->index) + return -EINVAL; + + /* Only accept code in the pix map table */ + vpix = dcmipp_inp_pix_map_by_code(IS_SINK(fse->pad) ? fse->code : 0, + IS_SRC(fse->pad) ? fse->code : 0); + if (!vpix) + return -EINVAL; + + fse->min_width = DCMIPP_FRAME_MIN_WIDTH; + fse->max_width = DCMIPP_FRAME_MAX_WIDTH; + fse->min_height = DCMIPP_FRAME_MIN_HEIGHT; + fse->max_height = DCMIPP_FRAME_MAX_HEIGHT; + + return 0; +} + +static void dcmipp_inp_adjust_fmt(struct dcmipp_inp_device *inp, + struct v4l2_mbus_framefmt *fmt, __u32 pad) +{ + const struct dcmipp_inp_pix_map *vpix; + + /* Only accept code in the pix map table */ + vpix = dcmipp_inp_pix_map_by_code(IS_SINK(pad) ? fmt->code : 0, + IS_SRC(pad) ? fmt->code : 0); + if (!vpix) + fmt->code = fmt_default.code; + + /* Exclude JPEG if BT656 bus is selected */ + if (vpix && vpix->code_sink == MEDIA_BUS_FMT_JPEG_1X8 && + inp->ved.bus_type == V4L2_MBUS_BT656) + fmt->code = fmt_default.code; + + fmt->width = clamp_t(u32, fmt->width, DCMIPP_FRAME_MIN_WIDTH, + DCMIPP_FRAME_MAX_WIDTH) & ~1; + fmt->height = clamp_t(u32, fmt->height, DCMIPP_FRAME_MIN_HEIGHT, + DCMIPP_FRAME_MAX_HEIGHT) & ~1; + + if (fmt->field == V4L2_FIELD_ANY || fmt->field == V4L2_FIELD_ALTERNATE) + fmt->field = fmt_default.field; + + dcmipp_colorimetry_clamp(fmt); +} + +static int dcmipp_inp_set_fmt(struct v4l2_subdev *sd, + struct v4l2_subdev_state *sd_state, + struct v4l2_subdev_format *fmt) +{ + struct dcmipp_inp_device *inp = v4l2_get_subdevdata(sd); + struct v4l2_mbus_framefmt *mf; + + if (v4l2_subdev_is_streaming(sd)) + return -EBUSY; + + mf = v4l2_subdev_state_get_format(sd_state, fmt->pad); + + /* Set the new format */ + dcmipp_inp_adjust_fmt(inp, &fmt->format, fmt->pad); + + dev_dbg(inp->dev, "%s: format update: old:%dx%d (0x%x, %d, %d, %d, %d) new:%dx%d (0x%x, %d, %d, %d, %d)\n", + inp->sd.name, + /* old */ + mf->width, mf->height, mf->code, + mf->colorspace, mf->quantization, + mf->xfer_func, mf->ycbcr_enc, + /* new */ + fmt->format.width, fmt->format.height, fmt->format.code, + fmt->format.colorspace, fmt->format.quantization, + fmt->format.xfer_func, fmt->format.ycbcr_enc); + + *mf = fmt->format; + + /* When setting the sink format, report that format on the src pad */ + if (IS_SINK(fmt->pad)) { + mf = v4l2_subdev_state_get_format(sd_state, 1); + *mf = fmt->format; + dcmipp_inp_adjust_fmt(inp, mf, 1); + } + + return 0; +} + +static int dcmipp_inp_configure_parallel(struct dcmipp_inp_device *inp, + struct v4l2_subdev_state *state) +{ + u32 val = 0; + const struct dcmipp_inp_pix_map *vpix; + struct v4l2_mbus_framefmt *sink_fmt; + struct v4l2_mbus_framefmt *src_fmt; + + /* Set vertical synchronization polarity */ + if (inp->ved.bus.flags & V4L2_MBUS_VSYNC_ACTIVE_HIGH) + val |= DCMIPP_PRCR_VSPOL; + + /* Set horizontal synchronization polarity */ + if (inp->ved.bus.flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH) + val |= DCMIPP_PRCR_HSPOL; + + /* Set pixel clock polarity */ + if (inp->ved.bus.flags & V4L2_MBUS_PCLK_SAMPLE_RISING) + val |= DCMIPP_PRCR_PCKPOL; + + /* + * BT656 embedded synchronisation bus mode. + * + * Default SAV/EAV mode is supported here with default codes + * SAV=0xff000080 & EAV=0xff00009d. + * With DCMIPP this means LSC=SAV=0x80 & LEC=EAV=0x9d. + */ + if (inp->ved.bus_type == V4L2_MBUS_BT656) { + val |= DCMIPP_PRCR_ESS; + + /* Unmask all codes */ + reg_write(inp, DCMIPP_PRESUR, 0xffffffff);/* FEC:LEC:LSC:FSC */ + + /* Trig on LSC=0x80 & LEC=0x9d codes, ignore FSC and FEC */ + reg_write(inp, DCMIPP_PRESCR, 0xff9d80ff);/* FEC:LEC:LSC:FSC */ + } + + /* Set format */ + sink_fmt = v4l2_subdev_state_get_format(state, 0); + src_fmt = v4l2_subdev_state_get_format(state, 1); + + vpix = dcmipp_inp_pix_map_by_code(sink_fmt->code, src_fmt->code); + if (!vpix) { + dev_err(inp->dev, "Invalid sink/src format configuration\n"); + return -EINVAL; + } + + val |= vpix->prcr_format << DCMIPP_PRCR_FORMAT_SHIFT; + + /* swap cycles */ + if (vpix->prcr_swapcycles) + val |= DCMIPP_PRCR_SWAPCYCLES; + + reg_write(inp, DCMIPP_PRCR, val); + + /* Select the DCMIPP parallel interface */ + reg_write(inp, DCMIPP_CMCR, 0); + + /* Enable parallel interface */ + reg_set(inp, DCMIPP_PRCR, DCMIPP_PRCR_ENABLE); + + return 0; +} + +static int dcmipp_inp_configure_csi(struct dcmipp_inp_device *inp, + struct v4l2_subdev_state *state) +{ + const struct dcmipp_inp_pix_map *vpix; + struct v4l2_mbus_framefmt *sink_fmt; + struct v4l2_mbus_framefmt *src_fmt; + + /* Get format information */ + sink_fmt = v4l2_subdev_state_get_format(state, 0); + src_fmt = v4l2_subdev_state_get_format(state, 1); + + vpix = dcmipp_inp_pix_map_by_code(sink_fmt->code, src_fmt->code); + if (!vpix) { + dev_err(inp->dev, "Invalid sink/src format configuration\n"); + return -EINVAL; + } + + /* Apply configuration on each input pipe */ + reg_clear(inp, DCMIPP_P0FSCR, + DCMIPP_P0FSCR_DTMODE_MASK | DCMIPP_P0FSCR_DTIDA_MASK); + + /* In case of JPEG we don't know the DT so we allow all data */ + /* + * TODO - check instead dt == 0 for the time being to allow other + * unknown data-type + */ + if (!vpix->dt) + reg_set(inp, DCMIPP_P0FSCR, + DCMIPP_P0FSCR_DTMODE_ALLDT << DCMIPP_P0FSCR_DTMODE_SHIFT); + else + reg_set(inp, DCMIPP_P0FSCR, + vpix->dt << DCMIPP_P0FSCR_DTIDA_SHIFT | + DCMIPP_P0FSCR_DTMODE_DTIDA); + + /* Select the DCMIPP CSI interface */ + reg_write(inp, DCMIPP_CMCR, DCMIPP_CMCR_INSEL); + + return 0; +} + +static int dcmipp_inp_enable_streams(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state, + u32 pad, u64 streams_mask) +{ + struct dcmipp_inp_device *inp = + container_of(sd, struct dcmipp_inp_device, sd); + struct v4l2_subdev *s_subdev; + struct media_pad *s_pad; + int ret = 0; + + /* Get source subdev */ + s_pad = media_pad_remote_pad_first(&sd->entity.pads[0]); + if (!s_pad || !is_media_entity_v4l2_subdev(s_pad->entity)) + return -EINVAL; + s_subdev = media_entity_to_v4l2_subdev(s_pad->entity); + + if (inp->ved.bus_type == V4L2_MBUS_PARALLEL || + inp->ved.bus_type == V4L2_MBUS_BT656) + ret = dcmipp_inp_configure_parallel(inp, state); + else if (inp->ved.bus_type == V4L2_MBUS_CSI2_DPHY) + ret = dcmipp_inp_configure_csi(inp, state); + if (ret) + return ret; + + ret = v4l2_subdev_enable_streams(s_subdev, s_pad->index, BIT_ULL(0)); + if (ret < 0) { + dev_err(inp->dev, + "failed to start source subdev streaming (%d)\n", ret); + return ret; + } + + return 0; +} + +static int dcmipp_inp_disable_streams(struct v4l2_subdev *sd, + struct v4l2_subdev_state *state, + u32 pad, u64 streams_mask) +{ + struct dcmipp_inp_device *inp = + container_of(sd, struct dcmipp_inp_device, sd); + struct v4l2_subdev *s_subdev; + struct media_pad *s_pad; + int ret; + + /* Get source subdev */ + s_pad = media_pad_remote_pad_first(&sd->entity.pads[0]); + if (!s_pad || !is_media_entity_v4l2_subdev(s_pad->entity)) + return -EINVAL; + s_subdev = media_entity_to_v4l2_subdev(s_pad->entity); + + ret = v4l2_subdev_disable_streams(s_subdev, s_pad->index, BIT_ULL(0)); + if (ret < 0) { + dev_err(inp->dev, + "failed to stop source subdev streaming (%d)\n", ret); + return ret; + } + + if (inp->ved.bus_type == V4L2_MBUS_PARALLEL || + inp->ved.bus_type == V4L2_MBUS_BT656) { + /* Disable parallel interface */ + reg_clear(inp, DCMIPP_PRCR, DCMIPP_PRCR_ENABLE); + } + + return 0; +} + +static const struct v4l2_subdev_pad_ops dcmipp_inp_pad_ops = { + .enum_mbus_code = dcmipp_inp_enum_mbus_code, + .enum_frame_size = dcmipp_inp_enum_frame_size, + .get_fmt = v4l2_subdev_get_fmt, + .set_fmt = dcmipp_inp_set_fmt, + .enable_streams = dcmipp_inp_enable_streams, + .disable_streams = dcmipp_inp_disable_streams, +}; + +static const struct v4l2_subdev_video_ops dcmipp_inp_video_ops = { + .s_stream = v4l2_subdev_s_stream_helper, +}; + +static const struct v4l2_subdev_ops dcmipp_inp_ops = { + .pad = &dcmipp_inp_pad_ops, + .video = &dcmipp_inp_video_ops, +}; + +static void dcmipp_inp_release(struct v4l2_subdev *sd) +{ + struct dcmipp_inp_device *inp = + container_of(sd, struct dcmipp_inp_device, sd); + + kfree(inp); +} + +static const struct v4l2_subdev_internal_ops dcmipp_inp_int_ops = { + .init_state = dcmipp_inp_init_state, + .release = dcmipp_inp_release, +}; + +void dcmipp_inp_ent_release(struct dcmipp_ent_device *ved) +{ + struct dcmipp_inp_device *inp = + container_of(ved, struct dcmipp_inp_device, ved); + + dcmipp_ent_sd_unregister(ved, &inp->sd); +} + +struct dcmipp_ent_device *dcmipp_inp_ent_init(struct device *dev, + const char *entity_name, + struct v4l2_device *v4l2_dev, + void __iomem *regs) +{ + struct dcmipp_inp_device *inp; + const unsigned long pads_flag[] = { + MEDIA_PAD_FL_SINK, MEDIA_PAD_FL_SOURCE, + }; + int ret; + + /* Allocate the inp struct */ + inp = kzalloc(sizeof(*inp), GFP_KERNEL); + if (!inp) + return ERR_PTR(-ENOMEM); + + inp->regs = regs; + + /* Initialize ved and sd */ + ret = dcmipp_ent_sd_register(&inp->ved, &inp->sd, v4l2_dev, + entity_name, MEDIA_ENT_F_VID_IF_BRIDGE, + ARRAY_SIZE(pads_flag), pads_flag, + &dcmipp_inp_int_ops, &dcmipp_inp_ops, + NULL, NULL); + if (ret) { + kfree(inp); + return ERR_PTR(ret); + } + + inp->dev = dev; + + return &inp->ved; +} diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-parallel.c b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-parallel.c deleted file mode 100644 index 62c5c3331cfe..000000000000 --- a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-parallel.c +++ /dev/null @@ -1,440 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Driver for STM32 Digital Camera Memory Interface Pixel Processor - * - * Copyright (C) STMicroelectronics SA 2023 - * Authors: Hugues Fruchet - * Alain Volmat - * for STMicroelectronics. - */ - -#include -#include -#include - -#include "dcmipp-common.h" - -#define DCMIPP_PRCR 0x104 -#define DCMIPP_PRCR_FORMAT_SHIFT 16 -#define DCMIPP_PRCR_FORMAT_YUV422 0x1e -#define DCMIPP_PRCR_FORMAT_RGB565 0x22 -#define DCMIPP_PRCR_FORMAT_RAW8 0x2a -#define DCMIPP_PRCR_FORMAT_G8 0x4a -#define DCMIPP_PRCR_FORMAT_BYTE_STREAM 0x5a -#define DCMIPP_PRCR_ESS BIT(4) -#define DCMIPP_PRCR_PCKPOL BIT(5) -#define DCMIPP_PRCR_HSPOL BIT(6) -#define DCMIPP_PRCR_VSPOL BIT(7) -#define DCMIPP_PRCR_ENABLE BIT(14) -#define DCMIPP_PRCR_SWAPCYCLES BIT(25) - -#define DCMIPP_PRESCR 0x108 -#define DCMIPP_PRESUR 0x10c - -#define IS_SINK(pad) (!(pad)) -#define IS_SRC(pad) ((pad)) - -struct dcmipp_par_pix_map { - unsigned int code_sink; - unsigned int code_src; - u8 prcr_format; - u8 prcr_swapcycles; -}; - -#define PIXMAP_SINK_SRC_PRCR_SWAP(sink, src, prcr, swap) \ - { \ - .code_sink = MEDIA_BUS_FMT_##sink, \ - .code_src = MEDIA_BUS_FMT_##src, \ - .prcr_format = DCMIPP_PRCR_FORMAT_##prcr, \ - .prcr_swapcycles = swap, \ - } -static const struct dcmipp_par_pix_map dcmipp_par_pix_map_list[] = { - /* RGB565 */ - PIXMAP_SINK_SRC_PRCR_SWAP(RGB565_2X8_LE, RGB565_2X8_LE, RGB565, 1), - PIXMAP_SINK_SRC_PRCR_SWAP(RGB565_2X8_BE, RGB565_2X8_LE, RGB565, 0), - /* YUV422 */ - PIXMAP_SINK_SRC_PRCR_SWAP(YUYV8_2X8, YUYV8_2X8, YUV422, 1), - PIXMAP_SINK_SRC_PRCR_SWAP(YUYV8_2X8, UYVY8_2X8, YUV422, 0), - PIXMAP_SINK_SRC_PRCR_SWAP(UYVY8_2X8, UYVY8_2X8, YUV422, 1), - PIXMAP_SINK_SRC_PRCR_SWAP(UYVY8_2X8, YUYV8_2X8, YUV422, 0), - PIXMAP_SINK_SRC_PRCR_SWAP(YVYU8_2X8, YVYU8_2X8, YUV422, 1), - PIXMAP_SINK_SRC_PRCR_SWAP(VYUY8_2X8, VYUY8_2X8, YUV422, 1), - /* GREY */ - PIXMAP_SINK_SRC_PRCR_SWAP(Y8_1X8, Y8_1X8, G8, 0), - /* Raw Bayer */ - PIXMAP_SINK_SRC_PRCR_SWAP(SBGGR8_1X8, SBGGR8_1X8, RAW8, 0), - PIXMAP_SINK_SRC_PRCR_SWAP(SGBRG8_1X8, SGBRG8_1X8, RAW8, 0), - PIXMAP_SINK_SRC_PRCR_SWAP(SGRBG8_1X8, SGRBG8_1X8, RAW8, 0), - PIXMAP_SINK_SRC_PRCR_SWAP(SRGGB8_1X8, SRGGB8_1X8, RAW8, 0), - /* JPEG */ - PIXMAP_SINK_SRC_PRCR_SWAP(JPEG_1X8, JPEG_1X8, BYTE_STREAM, 0), -}; - -/* - * Search through the pix_map table, skipping two consecutive entry with the - * same code - */ -static inline const struct dcmipp_par_pix_map *dcmipp_par_pix_map_by_index - (unsigned int index, - unsigned int pad) -{ - unsigned int i = 0; - u32 prev_code = 0, cur_code; - - while (i < ARRAY_SIZE(dcmipp_par_pix_map_list)) { - if (IS_SRC(pad)) - cur_code = dcmipp_par_pix_map_list[i].code_src; - else - cur_code = dcmipp_par_pix_map_list[i].code_sink; - - if (cur_code == prev_code) { - i++; - continue; - } - prev_code = cur_code; - - if (index == 0) - break; - i++; - index--; - } - - if (i >= ARRAY_SIZE(dcmipp_par_pix_map_list)) - return NULL; - - return &dcmipp_par_pix_map_list[i]; -} - -static inline const struct dcmipp_par_pix_map *dcmipp_par_pix_map_by_code - (u32 code_sink, u32 code_src) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(dcmipp_par_pix_map_list); i++) { - if ((dcmipp_par_pix_map_list[i].code_sink == code_sink && - dcmipp_par_pix_map_list[i].code_src == code_src) || - (dcmipp_par_pix_map_list[i].code_sink == code_src && - dcmipp_par_pix_map_list[i].code_src == code_sink) || - (dcmipp_par_pix_map_list[i].code_sink == code_sink && - code_src == 0) || - (code_sink == 0 && - dcmipp_par_pix_map_list[i].code_src == code_src)) - return &dcmipp_par_pix_map_list[i]; - } - return NULL; -} - -struct dcmipp_par_device { - struct dcmipp_ent_device ved; - struct v4l2_subdev sd; - struct device *dev; - void __iomem *regs; - bool streaming; -}; - -static const struct v4l2_mbus_framefmt fmt_default = { - .width = DCMIPP_FMT_WIDTH_DEFAULT, - .height = DCMIPP_FMT_HEIGHT_DEFAULT, - .code = MEDIA_BUS_FMT_RGB565_2X8_LE, - .field = V4L2_FIELD_NONE, - .colorspace = DCMIPP_COLORSPACE_DEFAULT, - .ycbcr_enc = DCMIPP_YCBCR_ENC_DEFAULT, - .quantization = DCMIPP_QUANTIZATION_DEFAULT, - .xfer_func = DCMIPP_XFER_FUNC_DEFAULT, -}; - -static int dcmipp_par_init_state(struct v4l2_subdev *sd, - struct v4l2_subdev_state *sd_state) -{ - unsigned int i; - - for (i = 0; i < sd->entity.num_pads; i++) { - struct v4l2_mbus_framefmt *mf; - - mf = v4l2_subdev_state_get_format(sd_state, i); - *mf = fmt_default; - } - - return 0; -} - -static int dcmipp_par_enum_mbus_code(struct v4l2_subdev *sd, - struct v4l2_subdev_state *sd_state, - struct v4l2_subdev_mbus_code_enum *code) -{ - const struct dcmipp_par_pix_map *vpix = - dcmipp_par_pix_map_by_index(code->index, code->pad); - - if (!vpix) - return -EINVAL; - - code->code = IS_SRC(code->pad) ? vpix->code_src : vpix->code_sink; - - return 0; -} - -static int dcmipp_par_enum_frame_size(struct v4l2_subdev *sd, - struct v4l2_subdev_state *sd_state, - struct v4l2_subdev_frame_size_enum *fse) -{ - const struct dcmipp_par_pix_map *vpix; - - if (fse->index) - return -EINVAL; - - /* Only accept code in the pix map table */ - vpix = dcmipp_par_pix_map_by_code(IS_SINK(fse->pad) ? fse->code : 0, - IS_SRC(fse->pad) ? fse->code : 0); - if (!vpix) - return -EINVAL; - - fse->min_width = DCMIPP_FRAME_MIN_WIDTH; - fse->max_width = DCMIPP_FRAME_MAX_WIDTH; - fse->min_height = DCMIPP_FRAME_MIN_HEIGHT; - fse->max_height = DCMIPP_FRAME_MAX_HEIGHT; - - return 0; -} - -static void dcmipp_par_adjust_fmt(struct dcmipp_par_device *par, - struct v4l2_mbus_framefmt *fmt, __u32 pad) -{ - const struct dcmipp_par_pix_map *vpix; - - /* Only accept code in the pix map table */ - vpix = dcmipp_par_pix_map_by_code(IS_SINK(pad) ? fmt->code : 0, - IS_SRC(pad) ? fmt->code : 0); - if (!vpix) - fmt->code = fmt_default.code; - - /* Exclude JPEG if BT656 bus is selected */ - if (vpix && vpix->code_sink == MEDIA_BUS_FMT_JPEG_1X8 && - par->ved.bus_type == V4L2_MBUS_BT656) - fmt->code = fmt_default.code; - - fmt->width = clamp_t(u32, fmt->width, DCMIPP_FRAME_MIN_WIDTH, - DCMIPP_FRAME_MAX_WIDTH) & ~1; - fmt->height = clamp_t(u32, fmt->height, DCMIPP_FRAME_MIN_HEIGHT, - DCMIPP_FRAME_MAX_HEIGHT) & ~1; - - if (fmt->field == V4L2_FIELD_ANY || fmt->field == V4L2_FIELD_ALTERNATE) - fmt->field = fmt_default.field; - - dcmipp_colorimetry_clamp(fmt); -} - -static int dcmipp_par_set_fmt(struct v4l2_subdev *sd, - struct v4l2_subdev_state *sd_state, - struct v4l2_subdev_format *fmt) -{ - struct dcmipp_par_device *par = v4l2_get_subdevdata(sd); - struct v4l2_mbus_framefmt *mf; - - if (par->streaming) - return -EBUSY; - - mf = v4l2_subdev_state_get_format(sd_state, fmt->pad); - - /* Set the new format */ - dcmipp_par_adjust_fmt(par, &fmt->format, fmt->pad); - - dev_dbg(par->dev, "%s: format update: old:%dx%d (0x%x, %d, %d, %d, %d) new:%dx%d (0x%x, %d, %d, %d, %d)\n", - par->sd.name, - /* old */ - mf->width, mf->height, mf->code, - mf->colorspace, mf->quantization, - mf->xfer_func, mf->ycbcr_enc, - /* new */ - fmt->format.width, fmt->format.height, fmt->format.code, - fmt->format.colorspace, fmt->format.quantization, - fmt->format.xfer_func, fmt->format.ycbcr_enc); - - *mf = fmt->format; - - /* When setting the sink format, report that format on the src pad */ - if (IS_SINK(fmt->pad)) { - mf = v4l2_subdev_state_get_format(sd_state, 1); - *mf = fmt->format; - dcmipp_par_adjust_fmt(par, mf, 1); - } - - return 0; -} - -static const struct v4l2_subdev_pad_ops dcmipp_par_pad_ops = { - .enum_mbus_code = dcmipp_par_enum_mbus_code, - .enum_frame_size = dcmipp_par_enum_frame_size, - .get_fmt = v4l2_subdev_get_fmt, - .set_fmt = dcmipp_par_set_fmt, -}; - -static int dcmipp_par_configure(struct dcmipp_par_device *par) -{ - u32 val = 0; - const struct dcmipp_par_pix_map *vpix; - struct v4l2_subdev_state *state; - struct v4l2_mbus_framefmt *sink_fmt; - struct v4l2_mbus_framefmt *src_fmt; - - /* Set vertical synchronization polarity */ - if (par->ved.bus.flags & V4L2_MBUS_VSYNC_ACTIVE_HIGH) - val |= DCMIPP_PRCR_VSPOL; - - /* Set horizontal synchronization polarity */ - if (par->ved.bus.flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH) - val |= DCMIPP_PRCR_HSPOL; - - /* Set pixel clock polarity */ - if (par->ved.bus.flags & V4L2_MBUS_PCLK_SAMPLE_RISING) - val |= DCMIPP_PRCR_PCKPOL; - - /* - * BT656 embedded synchronisation bus mode. - * - * Default SAV/EAV mode is supported here with default codes - * SAV=0xff000080 & EAV=0xff00009d. - * With DCMIPP this means LSC=SAV=0x80 & LEC=EAV=0x9d. - */ - if (par->ved.bus_type == V4L2_MBUS_BT656) { - val |= DCMIPP_PRCR_ESS; - - /* Unmask all codes */ - reg_write(par, DCMIPP_PRESUR, 0xffffffff);/* FEC:LEC:LSC:FSC */ - - /* Trig on LSC=0x80 & LEC=0x9d codes, ignore FSC and FEC */ - reg_write(par, DCMIPP_PRESCR, 0xff9d80ff);/* FEC:LEC:LSC:FSC */ - } - - /* Set format */ - state = v4l2_subdev_lock_and_get_active_state(&par->sd); - sink_fmt = v4l2_subdev_state_get_format(state, 0); - src_fmt = v4l2_subdev_state_get_format(state, 1); - v4l2_subdev_unlock_state(state); - - vpix = dcmipp_par_pix_map_by_code(sink_fmt->code, src_fmt->code); - if (!vpix) { - dev_err(par->dev, "Invalid sink/src format configuration\n"); - return -EINVAL; - } - - val |= vpix->prcr_format << DCMIPP_PRCR_FORMAT_SHIFT; - - /* swap cycles */ - if (vpix->prcr_swapcycles) - val |= DCMIPP_PRCR_SWAPCYCLES; - - reg_write(par, DCMIPP_PRCR, val); - - return 0; -} - -static int dcmipp_par_s_stream(struct v4l2_subdev *sd, int enable) -{ - struct dcmipp_par_device *par = - container_of(sd, struct dcmipp_par_device, sd); - struct v4l2_subdev *s_subdev; - struct media_pad *pad; - int ret = 0; - - /* Get source subdev */ - pad = media_pad_remote_pad_first(&sd->entity.pads[0]); - if (!pad || !is_media_entity_v4l2_subdev(pad->entity)) - return -EINVAL; - s_subdev = media_entity_to_v4l2_subdev(pad->entity); - - if (enable) { - ret = dcmipp_par_configure(par); - if (ret) - return ret; - - /* Enable parallel interface */ - reg_set(par, DCMIPP_PRCR, DCMIPP_PRCR_ENABLE); - - ret = v4l2_subdev_call(s_subdev, video, s_stream, enable); - if (ret < 0) { - dev_err(par->dev, - "failed to start source subdev streaming (%d)\n", - ret); - return ret; - } - } else { - ret = v4l2_subdev_call(s_subdev, video, s_stream, enable); - if (ret < 0) { - dev_err(par->dev, - "failed to stop source subdev streaming (%d)\n", - ret); - return ret; - } - - /* Disable parallel interface */ - reg_clear(par, DCMIPP_PRCR, DCMIPP_PRCR_ENABLE); - } - - par->streaming = enable; - - return ret; -} - -static const struct v4l2_subdev_video_ops dcmipp_par_video_ops = { - .s_stream = dcmipp_par_s_stream, -}; - -static const struct v4l2_subdev_ops dcmipp_par_ops = { - .pad = &dcmipp_par_pad_ops, - .video = &dcmipp_par_video_ops, -}; - -static void dcmipp_par_release(struct v4l2_subdev *sd) -{ - struct dcmipp_par_device *par = - container_of(sd, struct dcmipp_par_device, sd); - - kfree(par); -} - -static const struct v4l2_subdev_internal_ops dcmipp_par_int_ops = { - .init_state = dcmipp_par_init_state, - .release = dcmipp_par_release, -}; - -void dcmipp_par_ent_release(struct dcmipp_ent_device *ved) -{ - struct dcmipp_par_device *par = - container_of(ved, struct dcmipp_par_device, ved); - - dcmipp_ent_sd_unregister(ved, &par->sd); -} - -struct dcmipp_ent_device *dcmipp_par_ent_init(struct device *dev, - const char *entity_name, - struct v4l2_device *v4l2_dev, - void __iomem *regs) -{ - struct dcmipp_par_device *par; - const unsigned long pads_flag[] = { - MEDIA_PAD_FL_SINK, MEDIA_PAD_FL_SOURCE, - }; - int ret; - - /* Allocate the par struct */ - par = kzalloc(sizeof(*par), GFP_KERNEL); - if (!par) - return ERR_PTR(-ENOMEM); - - par->regs = regs; - - /* Initialize ved and sd */ - ret = dcmipp_ent_sd_register(&par->ved, &par->sd, v4l2_dev, - entity_name, MEDIA_ENT_F_VID_IF_BRIDGE, - ARRAY_SIZE(pads_flag), pads_flag, - &dcmipp_par_int_ops, &dcmipp_par_ops, - NULL, NULL); - if (ret) { - kfree(par); - return ERR_PTR(ret); - } - - par->dev = dev; - - return &par->ved; -} diff --git a/drivers/media/platform/verisilicon/hantro.h b/drivers/media/platform/verisilicon/hantro.h index 811260dc3c77..edc217eed293 100644 --- a/drivers/media/platform/verisilicon/hantro.h +++ b/drivers/media/platform/verisilicon/hantro.h @@ -227,6 +227,7 @@ struct hantro_dev { * @src_fmt: V4L2 pixel format of active source format. * @vpu_dst_fmt: Descriptor of active destination format. * @dst_fmt: V4L2 pixel format of active destination format. + * @ref_fmt: V4L2 pixel format of the reference frames format. * * @ctrl_handler: Control handler used to register controls. * @jpeg_quality: User-specified JPEG compression quality. @@ -255,6 +256,7 @@ struct hantro_ctx { struct v4l2_pix_format_mplane src_fmt; const struct hantro_fmt *vpu_dst_fmt; struct v4l2_pix_format_mplane dst_fmt; + struct v4l2_pix_format_mplane ref_fmt; struct v4l2_ctrl_handler ctrl_handler; int jpeg_quality; @@ -332,12 +334,19 @@ struct hantro_vp9_decoded_buffer_info { u32 bit_depth : 4; }; +struct hantro_av1_decoded_buffer_info { + /* Info needed when the decoded frame serves as a reference frame. */ + size_t chroma_offset; + size_t mv_offset; +}; + struct hantro_decoded_buffer { /* Must be the first field in this struct. */ struct v4l2_m2m_buffer base; union { struct hantro_vp9_decoded_buffer_info vp9; + struct hantro_av1_decoded_buffer_info av1; }; }; diff --git a/drivers/media/platform/verisilicon/hantro_g2.c b/drivers/media/platform/verisilicon/hantro_g2.c index 5c1d799d8618..aae0b562fabb 100644 --- a/drivers/media/platform/verisilicon/hantro_g2.c +++ b/drivers/media/platform/verisilicon/hantro_g2.c @@ -47,7 +47,7 @@ irqreturn_t hantro_g2_irq(int irq, void *dev_id) size_t hantro_g2_chroma_offset(struct hantro_ctx *ctx) { - return ctx->dst_fmt.width * ctx->dst_fmt.height * ctx->bit_depth / 8; + return ctx->ref_fmt.plane_fmt[0].bytesperline * ctx->ref_fmt.height; } size_t hantro_g2_motion_vectors_offset(struct hantro_ctx *ctx) diff --git a/drivers/media/platform/verisilicon/hantro_postproc.c b/drivers/media/platform/verisilicon/hantro_postproc.c index 232c93eea7ee..c435a393e0cb 100644 --- a/drivers/media/platform/verisilicon/hantro_postproc.c +++ b/drivers/media/platform/verisilicon/hantro_postproc.c @@ -194,35 +194,25 @@ void hantro_postproc_free(struct hantro_ctx *ctx) static unsigned int hantro_postproc_buffer_size(struct hantro_ctx *ctx) { - struct v4l2_pix_format_mplane pix_mp; - const struct hantro_fmt *fmt; unsigned int buf_size; - /* this should always pick native format */ - fmt = hantro_get_default_fmt(ctx, false, ctx->bit_depth, HANTRO_AUTO_POSTPROC); - if (!fmt) - return 0; - - v4l2_fill_pixfmt_mp(&pix_mp, fmt->fourcc, ctx->src_fmt.width, - ctx->src_fmt.height); - - buf_size = pix_mp.plane_fmt[0].sizeimage; + buf_size = ctx->ref_fmt.plane_fmt[0].sizeimage; if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_H264_SLICE) - buf_size += hantro_h264_mv_size(pix_mp.width, - pix_mp.height); + buf_size += hantro_h264_mv_size(ctx->ref_fmt.width, + ctx->ref_fmt.height); else if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_VP9_FRAME) - buf_size += hantro_vp9_mv_size(pix_mp.width, - pix_mp.height); + buf_size += hantro_vp9_mv_size(ctx->ref_fmt.width, + ctx->ref_fmt.height); else if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_HEVC_SLICE) { - buf_size += hantro_hevc_mv_size(pix_mp.width, - pix_mp.height); + buf_size += hantro_hevc_mv_size(ctx->ref_fmt.width, + ctx->ref_fmt.height); if (ctx->hevc_dec.use_compression) - buf_size += hantro_hevc_compressed_size(pix_mp.width, - pix_mp.height); + buf_size += hantro_hevc_compressed_size(ctx->ref_fmt.width, + ctx->ref_fmt.height); } else if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_AV1_FRAME) - buf_size += hantro_av1_mv_size(pix_mp.width, - pix_mp.height); + buf_size += hantro_av1_mv_size(ctx->ref_fmt.width, + ctx->ref_fmt.height); return buf_size; } diff --git a/drivers/media/platform/verisilicon/hantro_v4l2.c b/drivers/media/platform/verisilicon/hantro_v4l2.c index 2513adfbd825..2bce940a5822 100644 --- a/drivers/media/platform/verisilicon/hantro_v4l2.c +++ b/drivers/media/platform/verisilicon/hantro_v4l2.c @@ -126,6 +126,24 @@ hantro_find_format(const struct hantro_ctx *ctx, u32 fourcc) return NULL; } +static int +hantro_set_reference_frames_format(struct hantro_ctx *ctx) +{ + const struct hantro_fmt *fmt; + int dst_bit_depth = hantro_get_format_depth(ctx->vpu_dst_fmt->fourcc); + + fmt = hantro_get_default_fmt(ctx, false, dst_bit_depth, HANTRO_AUTO_POSTPROC); + if (!fmt) + return -EINVAL; + + ctx->ref_fmt.width = ctx->src_fmt.width; + ctx->ref_fmt.height = ctx->src_fmt.height; + + v4l2_apply_frmsize_constraints(&ctx->ref_fmt.width, &ctx->ref_fmt.height, &fmt->frmsize); + return v4l2_fill_pixfmt_mp(&ctx->ref_fmt, fmt->fourcc, + ctx->ref_fmt.width, ctx->ref_fmt.height); +} + const struct hantro_fmt * hantro_get_default_fmt(const struct hantro_ctx *ctx, bool bitstream, int bit_depth, bool need_postproc) @@ -595,6 +613,9 @@ static int hantro_set_fmt_cap(struct hantro_ctx *ctx, ctx->vpu_dst_fmt = hantro_find_format(ctx, pix_mp->pixelformat); ctx->dst_fmt = *pix_mp; + ret = hantro_set_reference_frames_format(ctx); + if (ret) + return ret; /* * Current raw format might have become invalid with newly diff --git a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c index f850d8bddef6..35799da534ed 100644 --- a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c +++ b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c @@ -187,23 +187,23 @@ static const struct hantro_fmt imx8m_vpu_g2_dec_fmts[] = { .frmsize = { .min_width = FMT_MIN_WIDTH, .max_width = FMT_UHD_WIDTH, - .step_width = TILE_MB_DIM, + .step_width = 8, .min_height = FMT_MIN_HEIGHT, .max_height = FMT_UHD_HEIGHT, - .step_height = TILE_MB_DIM, + .step_height = 32, }, }, { - .fourcc = V4L2_PIX_FMT_P010_4L4, + .fourcc = V4L2_PIX_FMT_NV15_4L4, .codec_mode = HANTRO_MODE_NONE, .match_depth = true, .frmsize = { .min_width = FMT_MIN_WIDTH, .max_width = FMT_UHD_WIDTH, - .step_width = TILE_MB_DIM, + .step_width = 8, .min_height = FMT_MIN_HEIGHT, .max_height = FMT_UHD_HEIGHT, - .step_height = TILE_MB_DIM, + .step_height = 32, }, }, { diff --git a/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c b/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c index e54f5fac325b..69b5d9e12926 100644 --- a/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c +++ b/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c @@ -686,8 +686,6 @@ rockchip_vpu981_av1_dec_set_ref(struct hantro_ctx *ctx, int ref, int idx, struct hantro_dev *vpu = ctx->dev; struct hantro_decoded_buffer *dst; dma_addr_t luma_addr, chroma_addr, mv_addr = 0; - size_t cr_offset = rockchip_vpu981_av1_dec_luma_size(ctx); - size_t mv_offset = rockchip_vpu981_av1_dec_chroma_size(ctx); int cur_width = frame->frame_width_minus_1 + 1; int cur_height = frame->frame_height_minus_1 + 1; int scale_width = @@ -744,8 +742,8 @@ rockchip_vpu981_av1_dec_set_ref(struct hantro_ctx *ctx, int ref, int idx, dst = vb2_to_hantro_decoded_buf(&av1_dec->frame_refs[idx].vb2_ref->vb2_buf); luma_addr = hantro_get_dec_buf_addr(ctx, &dst->base.vb.vb2_buf); - chroma_addr = luma_addr + cr_offset; - mv_addr = luma_addr + mv_offset; + chroma_addr = luma_addr + dst->av1.chroma_offset; + mv_addr = luma_addr + dst->av1.mv_offset; hantro_write_addr(vpu, AV1_REFERENCE_Y(ref), luma_addr); hantro_write_addr(vpu, AV1_REFERENCE_CB(ref), chroma_addr); @@ -2089,6 +2087,9 @@ rockchip_vpu981_av1_dec_set_output_buffer(struct hantro_ctx *ctx) chroma_addr = luma_addr + cr_offset; mv_addr = luma_addr + mv_offset; + dst->av1.chroma_offset = cr_offset; + dst->av1.mv_offset = mv_offset; + hantro_write_addr(vpu, AV1_TILE_OUT_LU, luma_addr); hantro_write_addr(vpu, AV1_TILE_OUT_CH, chroma_addr); hantro_write_addr(vpu, AV1_TILE_OUT_MV, mv_addr); diff --git a/drivers/media/radio/Kconfig b/drivers/media/radio/Kconfig index d52eccdc7eb9..72776d08046a 100644 --- a/drivers/media/radio/Kconfig +++ b/drivers/media/radio/Kconfig @@ -221,10 +221,6 @@ config USB_RAREMONO source "drivers/media/radio/si470x/Kconfig" source "drivers/media/radio/si4713/Kconfig" -# TI's ST based wl128x FM radio - -source "drivers/media/radio/wl128x/Kconfig" - # # ISA drivers configuration # diff --git a/drivers/media/radio/Makefile b/drivers/media/radio/Makefile index cfb6af7d3bc3..1ff46f3a6ed3 100644 --- a/drivers/media/radio/Makefile +++ b/drivers/media/radio/Makefile @@ -31,7 +31,6 @@ obj-$(CONFIG_RADIO_TIMBERDALE) += radio-timb.o obj-$(CONFIG_RADIO_TRUST) += radio-trust.o obj-$(CONFIG_RADIO_TYPHOON) += radio-typhoon.o obj-$(CONFIG_RADIO_WL1273) += radio-wl1273.o -obj-$(CONFIG_RADIO_WL128X) += wl128x/ obj-$(CONFIG_RADIO_ZOLTRIX) += radio-zoltrix.o obj-$(CONFIG_USB_DSBR) += dsbr100.o diff --git a/drivers/media/radio/wl128x/Kconfig b/drivers/media/radio/wl128x/Kconfig deleted file mode 100644 index 3e7713872e3f..000000000000 --- a/drivers/media/radio/wl128x/Kconfig +++ /dev/null @@ -1,15 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# TI's wl128x FM driver based on TI's ST driver. -# -config RADIO_WL128X - tristate "Texas Instruments WL128x FM Radio" - depends on VIDEO_DEV && RFKILL && TTY && TI_ST - depends on GPIOLIB || COMPILE_TEST - help - Choose Y here if you have this FM radio chip. - - In order to control your radio card, you will need to use programs - that are compatible with the Video For Linux 2 API. Information on - this API and pointers to "v4l2" programs may be found at - . diff --git a/drivers/media/radio/wl128x/Makefile b/drivers/media/radio/wl128x/Makefile deleted file mode 100644 index 4396ca416cfa..000000000000 --- a/drivers/media/radio/wl128x/Makefile +++ /dev/null @@ -1,7 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# Makefile for TI's shared transport driver based wl128x -# FM radio. -# -obj-$(CONFIG_RADIO_WL128X) += fm_drv.o -fm_drv-objs := fmdrv_common.o fmdrv_rx.o fmdrv_tx.o fmdrv_v4l2.o diff --git a/drivers/media/radio/wl128x/fmdrv.h b/drivers/media/radio/wl128x/fmdrv.h deleted file mode 100644 index 03117a41dbd4..000000000000 --- a/drivers/media/radio/wl128x/fmdrv.h +++ /dev/null @@ -1,229 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * FM Driver for Connectivity chip of Texas Instruments. - * - * Common header for all FM driver sub-modules. - * - * Copyright (C) 2011 Texas Instruments - */ - -#ifndef _FM_DRV_H -#define _FM_DRV_H - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define FM_DRV_VERSION "0.1.1" -#define FM_DRV_NAME "ti_fmdrv" -#define FM_DRV_CARD_SHORT_NAME "TI FM Radio" -#define FM_DRV_CARD_LONG_NAME "Texas Instruments FM Radio" - -/* Flag info */ -#define FM_INTTASK_RUNNING 0 -#define FM_INTTASK_SCHEDULE_PENDING 1 -#define FM_FW_DW_INPROGRESS 2 -#define FM_CORE_READY 3 -#define FM_CORE_TRANSPORT_READY 4 -#define FM_AF_SWITCH_INPROGRESS 5 -#define FM_CORE_TX_XMITING 6 - -#define FM_TUNE_COMPLETE 0x1 -#define FM_BAND_LIMIT 0x2 - -#define FM_DRV_TX_TIMEOUT (5*HZ) /* 5 seconds */ -#define FM_DRV_RX_SEEK_TIMEOUT (20*HZ) /* 20 seconds */ - -#define fmerr(format, ...) \ - printk(KERN_ERR "fmdrv: " format, ## __VA_ARGS__) -#define fmwarn(format, ...) \ - printk(KERN_WARNING "fmdrv: " format, ##__VA_ARGS__) -#ifdef DEBUG -#define fmdbg(format, ...) \ - printk(KERN_DEBUG "fmdrv: " format, ## __VA_ARGS__) -#else /* DEBUG */ -#define fmdbg(format, ...) do {} while(0) -#endif -enum { - FM_MODE_OFF, - FM_MODE_TX, - FM_MODE_RX, - FM_MODE_ENTRY_MAX -}; - -#define FM_RX_RDS_INFO_FIELD_MAX 8 /* 4 Group * 2 Bytes */ - -/* RX RDS data format */ -struct fm_rdsdata_format { - union { - struct { - u8 buff[FM_RX_RDS_INFO_FIELD_MAX]; - } groupdatabuff; - struct { - u16 pidata; - u8 blk_b[2]; - u8 blk_c[2]; - u8 blk_d[2]; - } groupgeneral; - struct { - u16 pidata; - u8 blk_b[2]; - u8 af[2]; - u8 ps[2]; - } group0A; - struct { - u16 pi[2]; - u8 blk_b[2]; - u8 ps[2]; - } group0B; - } data; -}; - -/* FM region (Europe/US, Japan) info */ -struct region_info { - u32 chanl_space; - u32 bot_freq; - u32 top_freq; - u8 fm_band; -}; -struct fmdev; -typedef void (*int_handler_prototype) (struct fmdev *); - -/* FM Interrupt processing related info */ -struct fm_irq { - u8 stage; - u16 flag; /* FM interrupt flag */ - u16 mask; /* FM interrupt mask */ - /* Interrupt process timeout handler */ - struct timer_list timer; - u8 retry; - int_handler_prototype *handlers; -}; - -/* RDS info */ -struct fm_rds { - u8 flag; /* RX RDS on/off status */ - u8 last_blk_idx; /* Last received RDS block */ - - /* RDS buffer */ - wait_queue_head_t read_queue; - u32 buf_size; /* Size is always multiple of 3 */ - u32 wr_idx; - u32 rd_idx; - u8 *buff; -}; - -#define FM_RDS_MAX_AF_LIST 25 - -/* - * Current RX channel Alternate Frequency cache. - * This info is used to switch to other freq (AF) - * when current channel signal strength is below RSSI threshold. - */ -struct tuned_station_info { - u16 picode; - u32 af_cache[FM_RDS_MAX_AF_LIST]; - u8 afcache_size; - u8 af_list_max; -}; - -/* FM RX mode info */ -struct fm_rx { - struct region_info region; /* Current selected band */ - u32 freq; /* Current RX frquency */ - u8 mute_mode; /* Current mute mode */ - u8 deemphasis_mode; /* Current deemphasis mode */ - /* RF dependent soft mute mode */ - u8 rf_depend_mute; - u16 volume; /* Current volume level */ - u16 rssi_threshold; /* Current RSSI threshold level */ - /* Holds the index of the current AF jump */ - u8 afjump_idx; - /* Will hold the frequency before the jump */ - u32 freq_before_jump; - u8 rds_mode; /* RDS operation mode (RDS/RDBS) */ - u8 af_mode; /* Alternate frequency on/off */ - struct tuned_station_info stat_info; - struct fm_rds rds; -}; - -#define FMTX_RDS_TXT_STR_SIZE 25 -/* - * FM TX RDS data - * - * @ text_type: is the text following PS or RT - * @ text: radio text string which could either be PS or RT - * @ af_freq: alternate frequency for Tx - * TODO: to be declared in application - */ -struct tx_rds { - u8 text_type; - u8 text[FMTX_RDS_TXT_STR_SIZE]; - u8 flag; - u32 af_freq; -}; -/* - * FM TX global data - * - * @ pwr_lvl: Power Level of the Transmission from mixer control - * @ xmit_state: Transmission state = Updated locally upon Start/Stop - * @ audio_io: i2S/Analog - * @ tx_frq: Transmission frequency - */ -struct fmtx_data { - u8 pwr_lvl; - u8 xmit_state; - u8 audio_io; - u8 region; - u16 aud_mode; - u32 preemph; - u32 tx_frq; - struct tx_rds rds; -}; - -/* FM driver operation structure */ -struct fmdev { - struct video_device *radio_dev; /* V4L2 video device pointer */ - struct v4l2_device v4l2_dev; /* V4L2 top level struct */ - struct snd_card *card; /* Card which holds FM mixer controls */ - u16 asci_id; - spinlock_t rds_buff_lock; /* To protect access to RDS buffer */ - spinlock_t resp_skb_lock; /* To protect access to received SKB */ - - long flag; /* FM driver state machine info */ - int streg_cbdata; /* status of ST registration */ - - struct sk_buff_head rx_q; /* RX queue */ - struct work_struct rx_bh_work; /* RX BH Work */ - - struct sk_buff_head tx_q; /* TX queue */ - struct work_struct tx_bh_work; /* TX BH Work */ - unsigned long last_tx_jiffies; /* Timestamp of last pkt sent */ - atomic_t tx_cnt; /* Number of packets can send at a time */ - - struct sk_buff *resp_skb; /* Response from the chip */ - /* Main task completion handler */ - struct completion maintask_comp; - /* Opcode of last command sent to the chip */ - u8 pre_op; - /* Handler used for wakeup when response packet is received */ - struct completion *resp_comp; - struct fm_irq irq_info; - u8 curr_fmmode; /* Current FM chip mode (TX, RX, OFF) */ - struct fm_rx rx; /* FM receiver info */ - struct fmtx_data tx_data; - - /* V4L2 ctrl framework handler*/ - struct v4l2_ctrl_handler ctrl_handler; - - /* For core assisted locking */ - struct mutex mutex; -}; -#endif diff --git a/drivers/media/radio/wl128x/fmdrv_common.c b/drivers/media/radio/wl128x/fmdrv_common.c deleted file mode 100644 index 4d032436691c..000000000000 --- a/drivers/media/radio/wl128x/fmdrv_common.c +++ /dev/null @@ -1,1676 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * FM Driver for Connectivity chip of Texas Instruments. - * - * This sub-module of FM driver is common for FM RX and TX - * functionality. This module is responsible for: - * 1) Forming group of Channel-8 commands to perform particular - * functionality (eg., frequency set require more than - * one Channel-8 command to be sent to the chip). - * 2) Sending each Channel-8 command to the chip and reading - * response back over Shared Transport. - * 3) Managing TX and RX Queues and BH bh Works. - * 4) Handling FM Interrupt packet and taking appropriate action. - * 5) Loading FM firmware to the chip (common, FM TX, and FM RX - * firmware files based on mode selection) - * - * Copyright (C) 2011 Texas Instruments - * Author: Raja Mani - * Author: Manjunatha Halli - */ - -#include -#include -#include -#include -#include - -#include "fmdrv.h" -#include "fmdrv_v4l2.h" -#include "fmdrv_common.h" -#include -#include "fmdrv_rx.h" -#include "fmdrv_tx.h" - -/* Region info */ -static struct region_info region_configs[] = { - /* Europe/US */ - { - .chanl_space = FM_CHANNEL_SPACING_200KHZ * FM_FREQ_MUL, - .bot_freq = 87500, /* 87.5 MHz */ - .top_freq = 108000, /* 108 MHz */ - .fm_band = 0, - }, - /* Japan */ - { - .chanl_space = FM_CHANNEL_SPACING_200KHZ * FM_FREQ_MUL, - .bot_freq = 76000, /* 76 MHz */ - .top_freq = 90000, /* 90 MHz */ - .fm_band = 1, - }, -}; - -/* Band selection */ -static u8 default_radio_region; /* Europe/US */ -module_param(default_radio_region, byte, 0); -MODULE_PARM_DESC(default_radio_region, "Region: 0=Europe/US, 1=Japan"); - -/* RDS buffer blocks */ -static u32 default_rds_buf = 300; -module_param(default_rds_buf, uint, 0444); -MODULE_PARM_DESC(default_rds_buf, "RDS buffer entries"); - -/* Radio Nr */ -static u32 radio_nr = -1; -module_param(radio_nr, int, 0444); -MODULE_PARM_DESC(radio_nr, "Radio Nr"); - -/* FM irq handlers forward declaration */ -static void fm_irq_send_flag_getcmd(struct fmdev *); -static void fm_irq_handle_flag_getcmd_resp(struct fmdev *); -static void fm_irq_handle_hw_malfunction(struct fmdev *); -static void fm_irq_handle_rds_start(struct fmdev *); -static void fm_irq_send_rdsdata_getcmd(struct fmdev *); -static void fm_irq_handle_rdsdata_getcmd_resp(struct fmdev *); -static void fm_irq_handle_rds_finish(struct fmdev *); -static void fm_irq_handle_tune_op_ended(struct fmdev *); -static void fm_irq_handle_power_enb(struct fmdev *); -static void fm_irq_handle_low_rssi_start(struct fmdev *); -static void fm_irq_afjump_set_pi(struct fmdev *); -static void fm_irq_handle_set_pi_resp(struct fmdev *); -static void fm_irq_afjump_set_pimask(struct fmdev *); -static void fm_irq_handle_set_pimask_resp(struct fmdev *); -static void fm_irq_afjump_setfreq(struct fmdev *); -static void fm_irq_handle_setfreq_resp(struct fmdev *); -static void fm_irq_afjump_enableint(struct fmdev *); -static void fm_irq_afjump_enableint_resp(struct fmdev *); -static void fm_irq_start_afjump(struct fmdev *); -static void fm_irq_handle_start_afjump_resp(struct fmdev *); -static void fm_irq_afjump_rd_freq(struct fmdev *); -static void fm_irq_afjump_rd_freq_resp(struct fmdev *); -static void fm_irq_handle_low_rssi_finish(struct fmdev *); -static void fm_irq_send_intmsk_cmd(struct fmdev *); -static void fm_irq_handle_intmsk_cmd_resp(struct fmdev *); - -/* - * When FM common module receives interrupt packet, following handlers - * will be executed one after another to service the interrupt(s) - */ -enum fmc_irq_handler_index { - FM_SEND_FLAG_GETCMD_IDX, - FM_HANDLE_FLAG_GETCMD_RESP_IDX, - - /* HW malfunction irq handler */ - FM_HW_MAL_FUNC_IDX, - - /* RDS threshold reached irq handler */ - FM_RDS_START_IDX, - FM_RDS_SEND_RDS_GETCMD_IDX, - FM_RDS_HANDLE_RDS_GETCMD_RESP_IDX, - FM_RDS_FINISH_IDX, - - /* Tune operation ended irq handler */ - FM_HW_TUNE_OP_ENDED_IDX, - - /* TX power enable irq handler */ - FM_HW_POWER_ENB_IDX, - - /* Low RSSI irq handler */ - FM_LOW_RSSI_START_IDX, - FM_AF_JUMP_SETPI_IDX, - FM_AF_JUMP_HANDLE_SETPI_RESP_IDX, - FM_AF_JUMP_SETPI_MASK_IDX, - FM_AF_JUMP_HANDLE_SETPI_MASK_RESP_IDX, - FM_AF_JUMP_SET_AF_FREQ_IDX, - FM_AF_JUMP_HANDLE_SET_AFFREQ_RESP_IDX, - FM_AF_JUMP_ENABLE_INT_IDX, - FM_AF_JUMP_ENABLE_INT_RESP_IDX, - FM_AF_JUMP_START_AFJUMP_IDX, - FM_AF_JUMP_HANDLE_START_AFJUMP_RESP_IDX, - FM_AF_JUMP_RD_FREQ_IDX, - FM_AF_JUMP_RD_FREQ_RESP_IDX, - FM_LOW_RSSI_FINISH_IDX, - - /* Interrupt process post action */ - FM_SEND_INTMSK_CMD_IDX, - FM_HANDLE_INTMSK_CMD_RESP_IDX, -}; - -/* FM interrupt handler table */ -static int_handler_prototype int_handler_table[] = { - fm_irq_send_flag_getcmd, - fm_irq_handle_flag_getcmd_resp, - fm_irq_handle_hw_malfunction, - fm_irq_handle_rds_start, /* RDS threshold reached irq handler */ - fm_irq_send_rdsdata_getcmd, - fm_irq_handle_rdsdata_getcmd_resp, - fm_irq_handle_rds_finish, - fm_irq_handle_tune_op_ended, - fm_irq_handle_power_enb, /* TX power enable irq handler */ - fm_irq_handle_low_rssi_start, - fm_irq_afjump_set_pi, - fm_irq_handle_set_pi_resp, - fm_irq_afjump_set_pimask, - fm_irq_handle_set_pimask_resp, - fm_irq_afjump_setfreq, - fm_irq_handle_setfreq_resp, - fm_irq_afjump_enableint, - fm_irq_afjump_enableint_resp, - fm_irq_start_afjump, - fm_irq_handle_start_afjump_resp, - fm_irq_afjump_rd_freq, - fm_irq_afjump_rd_freq_resp, - fm_irq_handle_low_rssi_finish, - fm_irq_send_intmsk_cmd, /* Interrupt process post action */ - fm_irq_handle_intmsk_cmd_resp -}; - -static long (*g_st_write) (struct sk_buff *skb); -static struct completion wait_for_fmdrv_reg_comp; - -static inline void fm_irq_call(struct fmdev *fmdev) -{ - fmdev->irq_info.handlers[fmdev->irq_info.stage](fmdev); -} - -/* Continue next function in interrupt handler table */ -static inline void fm_irq_call_stage(struct fmdev *fmdev, u8 stage) -{ - fmdev->irq_info.stage = stage; - fm_irq_call(fmdev); -} - -static inline void fm_irq_timeout_stage(struct fmdev *fmdev, u8 stage) -{ - fmdev->irq_info.stage = stage; - mod_timer(&fmdev->irq_info.timer, jiffies + FM_DRV_TX_TIMEOUT); -} - -#ifdef FM_DUMP_TXRX_PKT - /* To dump outgoing FM Channel-8 packets */ -inline void dump_tx_skb_data(struct sk_buff *skb) -{ - int len, len_org; - u8 index; - struct fm_cmd_msg_hdr *cmd_hdr; - - cmd_hdr = (struct fm_cmd_msg_hdr *)skb->data; - printk(KERN_INFO "<<%shdr:%02x len:%02x opcode:%02x type:%s dlen:%02x", - fm_cb(skb)->completion ? " " : "*", cmd_hdr->hdr, - cmd_hdr->len, cmd_hdr->op, - cmd_hdr->rd_wr ? "RD" : "WR", cmd_hdr->dlen); - - len_org = skb->len - FM_CMD_MSG_HDR_SIZE; - if (len_org > 0) { - printk(KERN_CONT "\n data(%d): ", cmd_hdr->dlen); - len = min(len_org, 14); - for (index = 0; index < len; index++) - printk(KERN_CONT "%x ", - skb->data[FM_CMD_MSG_HDR_SIZE + index]); - printk(KERN_CONT "%s", (len_org > 14) ? ".." : ""); - } - printk(KERN_CONT "\n"); -} - - /* To dump incoming FM Channel-8 packets */ -inline void dump_rx_skb_data(struct sk_buff *skb) -{ - int len, len_org; - u8 index; - struct fm_event_msg_hdr *evt_hdr; - - evt_hdr = (struct fm_event_msg_hdr *)skb->data; - printk(KERN_INFO ">> hdr:%02x len:%02x sts:%02x numhci:%02x opcode:%02x type:%s dlen:%02x", - evt_hdr->hdr, evt_hdr->len, - evt_hdr->status, evt_hdr->num_fm_hci_cmds, evt_hdr->op, - (evt_hdr->rd_wr) ? "RD" : "WR", evt_hdr->dlen); - - len_org = skb->len - FM_EVT_MSG_HDR_SIZE; - if (len_org > 0) { - printk(KERN_CONT "\n data(%d): ", evt_hdr->dlen); - len = min(len_org, 14); - for (index = 0; index < len; index++) - printk(KERN_CONT "%x ", - skb->data[FM_EVT_MSG_HDR_SIZE + index]); - printk(KERN_CONT "%s", (len_org > 14) ? ".." : ""); - } - printk(KERN_CONT "\n"); -} -#endif - -void fmc_update_region_info(struct fmdev *fmdev, u8 region_to_set) -{ - fmdev->rx.region = region_configs[region_to_set]; -} - -/* - * FM common sub-module will queue this bh work whenever it receives - * FM packet from ST driver. - */ -static void recv_bh_work(struct work_struct *t) -{ - struct fmdev *fmdev; - struct fm_irq *irq_info; - struct fm_event_msg_hdr *evt_hdr; - struct sk_buff *skb; - u8 num_fm_hci_cmds; - unsigned long flags; - - fmdev = from_work(fmdev, t, tx_bh_work); - irq_info = &fmdev->irq_info; - /* Process all packets in the RX queue */ - while ((skb = skb_dequeue(&fmdev->rx_q))) { - if (skb->len < sizeof(struct fm_event_msg_hdr)) { - fmerr("skb(%p) has only %d bytes, at least need %zu bytes to decode\n", - skb, - skb->len, sizeof(struct fm_event_msg_hdr)); - kfree_skb(skb); - continue; - } - - evt_hdr = (void *)skb->data; - num_fm_hci_cmds = evt_hdr->num_fm_hci_cmds; - - /* FM interrupt packet? */ - if (evt_hdr->op == FM_INTERRUPT) { - /* FM interrupt handler started already? */ - if (!test_bit(FM_INTTASK_RUNNING, &fmdev->flag)) { - set_bit(FM_INTTASK_RUNNING, &fmdev->flag); - if (irq_info->stage != 0) { - fmerr("Inval stage resetting to zero\n"); - irq_info->stage = 0; - } - - /* - * Execute first function in interrupt handler - * table. - */ - irq_info->handlers[irq_info->stage](fmdev); - } else { - set_bit(FM_INTTASK_SCHEDULE_PENDING, &fmdev->flag); - } - kfree_skb(skb); - } - /* Anyone waiting for this with completion handler? */ - else if (evt_hdr->op == fmdev->pre_op && fmdev->resp_comp != NULL) { - - spin_lock_irqsave(&fmdev->resp_skb_lock, flags); - fmdev->resp_skb = skb; - spin_unlock_irqrestore(&fmdev->resp_skb_lock, flags); - complete(fmdev->resp_comp); - - fmdev->resp_comp = NULL; - atomic_set(&fmdev->tx_cnt, 1); - } - /* Is this for interrupt handler? */ - else if (evt_hdr->op == fmdev->pre_op && fmdev->resp_comp == NULL) { - if (fmdev->resp_skb != NULL) - fmerr("Response SKB ptr not NULL\n"); - - spin_lock_irqsave(&fmdev->resp_skb_lock, flags); - fmdev->resp_skb = skb; - spin_unlock_irqrestore(&fmdev->resp_skb_lock, flags); - - /* Execute interrupt handler where state index points */ - irq_info->handlers[irq_info->stage](fmdev); - - kfree_skb(skb); - atomic_set(&fmdev->tx_cnt, 1); - } else { - fmerr("Nobody claimed SKB(%p),purging\n", skb); - } - - /* - * Check flow control field. If Num_FM_HCI_Commands field is - * not zero, queue FM TX bh work. - */ - if (num_fm_hci_cmds && atomic_read(&fmdev->tx_cnt)) - if (!skb_queue_empty(&fmdev->tx_q)) - queue_work(system_bh_wq, &fmdev->tx_bh_work); - } -} - -/* FM send_bh_work: is scheduled when FM packet has to be sent to chip */ -static void send_bh_work(struct work_struct *t) -{ - struct fmdev *fmdev; - struct sk_buff *skb; - int len; - - fmdev = from_work(fmdev, t, tx_bh_work); - - if (!atomic_read(&fmdev->tx_cnt)) - return; - - /* Check, is there any timeout happened to last transmitted packet */ - if (time_is_before_jiffies(fmdev->last_tx_jiffies + FM_DRV_TX_TIMEOUT)) { - fmerr("TX timeout occurred\n"); - atomic_set(&fmdev->tx_cnt, 1); - } - - /* Send queued FM TX packets */ - skb = skb_dequeue(&fmdev->tx_q); - if (!skb) - return; - - atomic_dec(&fmdev->tx_cnt); - fmdev->pre_op = fm_cb(skb)->fm_op; - - if (fmdev->resp_comp != NULL) - fmerr("Response completion handler is not NULL\n"); - - fmdev->resp_comp = fm_cb(skb)->completion; - - /* Write FM packet to ST driver */ - len = g_st_write(skb); - if (len < 0) { - kfree_skb(skb); - fmdev->resp_comp = NULL; - fmerr("TX bh work failed to send skb(%p)\n", skb); - atomic_set(&fmdev->tx_cnt, 1); - } else { - fmdev->last_tx_jiffies = jiffies; - } -} - -/* - * Queues FM Channel-8 packet to FM TX queue and schedules FM TX bh work for - * transmission - */ -static int fm_send_cmd(struct fmdev *fmdev, u8 fm_op, u16 type, void *payload, - int payload_len, struct completion *wait_completion) -{ - struct sk_buff *skb; - struct fm_cmd_msg_hdr *hdr; - int size; - - if (fm_op >= FM_INTERRUPT) { - fmerr("Invalid fm opcode - %d\n", fm_op); - return -EINVAL; - } - if (test_bit(FM_FW_DW_INPROGRESS, &fmdev->flag) && payload == NULL) { - fmerr("Payload data is NULL during fw download\n"); - return -EINVAL; - } - if (!test_bit(FM_FW_DW_INPROGRESS, &fmdev->flag)) - size = - FM_CMD_MSG_HDR_SIZE + ((payload == NULL) ? 0 : payload_len); - else - size = payload_len; - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) { - fmerr("No memory to create new SKB\n"); - return -ENOMEM; - } - /* - * Don't fill FM header info for the commands which come from - * FM firmware file. - */ - if (!test_bit(FM_FW_DW_INPROGRESS, &fmdev->flag) || - test_bit(FM_INTTASK_RUNNING, &fmdev->flag)) { - /* Fill command header info */ - hdr = skb_put(skb, FM_CMD_MSG_HDR_SIZE); - hdr->hdr = FM_PKT_LOGICAL_CHAN_NUMBER; /* 0x08 */ - - /* 3 (fm_opcode,rd_wr,dlen) + payload len) */ - hdr->len = ((payload == NULL) ? 0 : payload_len) + 3; - - /* FM opcode */ - hdr->op = fm_op; - - /* read/write type */ - hdr->rd_wr = type; - hdr->dlen = payload_len; - fm_cb(skb)->fm_op = fm_op; - - /* - * If firmware download has finished and the command is - * not a read command then payload is != NULL - a write - * command with u16 payload - convert to be16 - */ - if (payload != NULL) - *(__be16 *)payload = cpu_to_be16(*(u16 *)payload); - - } else if (payload != NULL) { - fm_cb(skb)->fm_op = *((u8 *)payload + 2); - } - if (payload != NULL) - skb_put_data(skb, payload, payload_len); - - fm_cb(skb)->completion = wait_completion; - skb_queue_tail(&fmdev->tx_q, skb); - queue_work(system_bh_wq, &fmdev->tx_bh_work); - - return 0; -} - -/* Sends FM Channel-8 command to the chip and waits for the response */ -int fmc_send_cmd(struct fmdev *fmdev, u8 fm_op, u16 type, void *payload, - unsigned int payload_len, void *response, int *response_len) -{ - struct sk_buff *skb; - struct fm_event_msg_hdr *evt_hdr; - unsigned long flags; - int ret; - - init_completion(&fmdev->maintask_comp); - ret = fm_send_cmd(fmdev, fm_op, type, payload, payload_len, - &fmdev->maintask_comp); - if (ret) - return ret; - - if (!wait_for_completion_timeout(&fmdev->maintask_comp, - FM_DRV_TX_TIMEOUT)) { - fmerr("Timeout(%d sec),didn't get regcompletion signal from RX bh work\n", - jiffies_to_msecs(FM_DRV_TX_TIMEOUT) / 1000); - return -ETIMEDOUT; - } - spin_lock_irqsave(&fmdev->resp_skb_lock, flags); - if (!fmdev->resp_skb) { - spin_unlock_irqrestore(&fmdev->resp_skb_lock, flags); - fmerr("Response SKB is missing\n"); - return -EFAULT; - } - skb = fmdev->resp_skb; - fmdev->resp_skb = NULL; - spin_unlock_irqrestore(&fmdev->resp_skb_lock, flags); - - evt_hdr = (void *)skb->data; - if (evt_hdr->status != 0) { - fmerr("Received event pkt status(%d) is not zero\n", - evt_hdr->status); - kfree_skb(skb); - return -EIO; - } - /* Send response data to caller */ - if (response != NULL && response_len != NULL && evt_hdr->dlen && - evt_hdr->dlen <= payload_len) { - /* Skip header info and copy only response data */ - skb_pull(skb, sizeof(struct fm_event_msg_hdr)); - memcpy(response, skb->data, evt_hdr->dlen); - *response_len = evt_hdr->dlen; - } else if (response_len != NULL && evt_hdr->dlen == 0) { - *response_len = 0; - } - kfree_skb(skb); - - return 0; -} - -/* --- Helper functions used in FM interrupt handlers ---*/ -static inline int check_cmdresp_status(struct fmdev *fmdev, - struct sk_buff **skb) -{ - struct fm_event_msg_hdr *fm_evt_hdr; - unsigned long flags; - - del_timer(&fmdev->irq_info.timer); - - spin_lock_irqsave(&fmdev->resp_skb_lock, flags); - *skb = fmdev->resp_skb; - fmdev->resp_skb = NULL; - spin_unlock_irqrestore(&fmdev->resp_skb_lock, flags); - - fm_evt_hdr = (void *)(*skb)->data; - if (fm_evt_hdr->status != 0) { - fmerr("irq: opcode %x response status is not zero Initiating irq recovery process\n", - fm_evt_hdr->op); - - mod_timer(&fmdev->irq_info.timer, jiffies + FM_DRV_TX_TIMEOUT); - return -1; - } - - return 0; -} - -static inline void fm_irq_common_cmd_resp_helper(struct fmdev *fmdev, u8 stage) -{ - struct sk_buff *skb; - - if (!check_cmdresp_status(fmdev, &skb)) - fm_irq_call_stage(fmdev, stage); -} - -/* - * Interrupt process timeout handler. - * One of the irq handler did not get proper response from the chip. So take - * recovery action here. FM interrupts are disabled in the beginning of - * interrupt process. Therefore reset stage index to re-enable default - * interrupts. So that next interrupt will be processed as usual. - */ -static void int_timeout_handler(struct timer_list *t) -{ - struct fmdev *fmdev; - struct fm_irq *fmirq; - - fmdbg("irq: timeout,trying to re-enable fm interrupts\n"); - fmdev = from_timer(fmdev, t, irq_info.timer); - fmirq = &fmdev->irq_info; - fmirq->retry++; - - if (fmirq->retry > FM_IRQ_TIMEOUT_RETRY_MAX) { - /* Stop recovery action (interrupt reenable process) and - * reset stage index & retry count values */ - fmirq->stage = 0; - fmirq->retry = 0; - fmerr("Recovery action failed duringirq processing, max retry reached\n"); - return; - } - fm_irq_call_stage(fmdev, FM_SEND_INTMSK_CMD_IDX); -} - -/* --------- FM interrupt handlers ------------*/ -static void fm_irq_send_flag_getcmd(struct fmdev *fmdev) -{ - u16 flag; - - /* Send FLAG_GET command , to know the source of interrupt */ - if (!fm_send_cmd(fmdev, FLAG_GET, REG_RD, NULL, sizeof(flag), NULL)) - fm_irq_timeout_stage(fmdev, FM_HANDLE_FLAG_GETCMD_RESP_IDX); -} - -static void fm_irq_handle_flag_getcmd_resp(struct fmdev *fmdev) -{ - struct sk_buff *skb; - struct fm_event_msg_hdr *fm_evt_hdr; - - if (check_cmdresp_status(fmdev, &skb)) - return; - - fm_evt_hdr = (void *)skb->data; - if (fm_evt_hdr->dlen > sizeof(fmdev->irq_info.flag)) - return; - - /* Skip header info and copy only response data */ - skb_pull(skb, sizeof(struct fm_event_msg_hdr)); - memcpy(&fmdev->irq_info.flag, skb->data, fm_evt_hdr->dlen); - - fmdev->irq_info.flag = be16_to_cpu((__force __be16)fmdev->irq_info.flag); - fmdbg("irq: flag register(0x%x)\n", fmdev->irq_info.flag); - - /* Continue next function in interrupt handler table */ - fm_irq_call_stage(fmdev, FM_HW_MAL_FUNC_IDX); -} - -static void fm_irq_handle_hw_malfunction(struct fmdev *fmdev) -{ - if (fmdev->irq_info.flag & FM_MAL_EVENT & fmdev->irq_info.mask) - fmerr("irq: HW MAL int received - do nothing\n"); - - /* Continue next function in interrupt handler table */ - fm_irq_call_stage(fmdev, FM_RDS_START_IDX); -} - -static void fm_irq_handle_rds_start(struct fmdev *fmdev) -{ - if (fmdev->irq_info.flag & FM_RDS_EVENT & fmdev->irq_info.mask) { - fmdbg("irq: rds threshold reached\n"); - fmdev->irq_info.stage = FM_RDS_SEND_RDS_GETCMD_IDX; - } else { - /* Continue next function in interrupt handler table */ - fmdev->irq_info.stage = FM_HW_TUNE_OP_ENDED_IDX; - } - - fm_irq_call(fmdev); -} - -static void fm_irq_send_rdsdata_getcmd(struct fmdev *fmdev) -{ - /* Send the command to read RDS data from the chip */ - if (!fm_send_cmd(fmdev, RDS_DATA_GET, REG_RD, NULL, - (FM_RX_RDS_FIFO_THRESHOLD * 3), NULL)) - fm_irq_timeout_stage(fmdev, FM_RDS_HANDLE_RDS_GETCMD_RESP_IDX); -} - -/* Keeps track of current RX channel AF (Alternate Frequency) */ -static void fm_rx_update_af_cache(struct fmdev *fmdev, u8 af) -{ - struct tuned_station_info *stat_info = &fmdev->rx.stat_info; - u8 reg_idx = fmdev->rx.region.fm_band; - u8 index; - u32 freq; - - /* First AF indicates the number of AF follows. Reset the list */ - if ((af >= FM_RDS_1_AF_FOLLOWS) && (af <= FM_RDS_25_AF_FOLLOWS)) { - fmdev->rx.stat_info.af_list_max = (af - FM_RDS_1_AF_FOLLOWS + 1); - fmdev->rx.stat_info.afcache_size = 0; - fmdbg("No of expected AF : %d\n", fmdev->rx.stat_info.af_list_max); - return; - } - - if (af < FM_RDS_MIN_AF) - return; - if (reg_idx == FM_BAND_EUROPE_US && af > FM_RDS_MAX_AF) - return; - if (reg_idx == FM_BAND_JAPAN && af > FM_RDS_MAX_AF_JAPAN) - return; - - freq = fmdev->rx.region.bot_freq + (af * 100); - if (freq == fmdev->rx.freq) { - fmdbg("Current freq(%d) is matching with received AF(%d)\n", - fmdev->rx.freq, freq); - return; - } - /* Do check in AF cache */ - for (index = 0; index < stat_info->afcache_size; index++) { - if (stat_info->af_cache[index] == freq) - break; - } - /* Reached the limit of the list - ignore the next AF */ - if (index == stat_info->af_list_max) { - fmdbg("AF cache is full\n"); - return; - } - /* - * If we reached the end of the list then this AF is not - * in the list - add it. - */ - if (index == stat_info->afcache_size) { - fmdbg("Storing AF %d to cache index %d\n", freq, index); - stat_info->af_cache[index] = freq; - stat_info->afcache_size++; - } -} - -/* - * Converts RDS buffer data from big endian format - * to little endian format. - */ -static void fm_rdsparse_swapbytes(struct fmdev *fmdev, - struct fm_rdsdata_format *rds_format) -{ - u8 index = 0; - u8 *rds_buff; - - /* - * Since in Orca the 2 RDS Data bytes are in little endian and - * in Dolphin they are in big endian, the parsing of the RDS data - * is chip dependent - */ - if (fmdev->asci_id != 0x6350) { - rds_buff = &rds_format->data.groupdatabuff.buff[0]; - while (index + 1 < FM_RX_RDS_INFO_FIELD_MAX) { - swap(rds_buff[index], rds_buff[index + 1]); - index += 2; - } - } -} - -static void fm_irq_handle_rdsdata_getcmd_resp(struct fmdev *fmdev) -{ - struct sk_buff *skb; - struct fm_rdsdata_format rds_fmt; - struct fm_rds *rds = &fmdev->rx.rds; - unsigned long group_idx, flags; - u8 *rds_data, meta_data, tmpbuf[FM_RDS_BLK_SIZE]; - u8 type, blk_idx, idx; - u16 cur_picode; - u32 rds_len; - - if (check_cmdresp_status(fmdev, &skb)) - return; - - /* Skip header info */ - skb_pull(skb, sizeof(struct fm_event_msg_hdr)); - rds_data = skb->data; - rds_len = skb->len; - - /* Parse the RDS data */ - while (rds_len >= FM_RDS_BLK_SIZE) { - meta_data = rds_data[2]; - /* Get the type: 0=A, 1=B, 2=C, 3=C', 4=D, 5=E */ - type = (meta_data & 0x07); - - /* Transform the blk type into index sequence (0, 1, 2, 3, 4) */ - blk_idx = (type <= FM_RDS_BLOCK_C ? type : (type - 1)); - fmdbg("Block index:%d(%s)\n", blk_idx, - (meta_data & FM_RDS_STATUS_ERR_MASK) ? "Bad" : "Ok"); - - if ((meta_data & FM_RDS_STATUS_ERR_MASK) != 0) - break; - - if (blk_idx > FM_RDS_BLK_IDX_D) { - fmdbg("Block sequence mismatch\n"); - rds->last_blk_idx = -1; - break; - } - - /* Skip checkword (control) byte and copy only data byte */ - idx = array_index_nospec(blk_idx * (FM_RDS_BLK_SIZE - 1), - FM_RX_RDS_INFO_FIELD_MAX - (FM_RDS_BLK_SIZE - 1)); - - memcpy(&rds_fmt.data.groupdatabuff.buff[idx], rds_data, - FM_RDS_BLK_SIZE - 1); - - rds->last_blk_idx = blk_idx; - - /* If completed a whole group then handle it */ - if (blk_idx == FM_RDS_BLK_IDX_D) { - fmdbg("Good block received\n"); - fm_rdsparse_swapbytes(fmdev, &rds_fmt); - - /* - * Extract PI code and store in local cache. - * We need this during AF switch processing. - */ - cur_picode = be16_to_cpu((__force __be16)rds_fmt.data.groupgeneral.pidata); - if (fmdev->rx.stat_info.picode != cur_picode) - fmdev->rx.stat_info.picode = cur_picode; - - fmdbg("picode:%d\n", cur_picode); - - group_idx = (rds_fmt.data.groupgeneral.blk_b[0] >> 3); - fmdbg("(fmdrv):Group:%ld%s\n", group_idx/2, - (group_idx % 2) ? "B" : "A"); - - group_idx = 1 << (rds_fmt.data.groupgeneral.blk_b[0] >> 3); - if (group_idx == FM_RDS_GROUP_TYPE_MASK_0A) { - fm_rx_update_af_cache(fmdev, rds_fmt.data.group0A.af[0]); - fm_rx_update_af_cache(fmdev, rds_fmt.data.group0A.af[1]); - } - } - rds_len -= FM_RDS_BLK_SIZE; - rds_data += FM_RDS_BLK_SIZE; - } - - /* Copy raw rds data to internal rds buffer */ - rds_data = skb->data; - rds_len = skb->len; - - spin_lock_irqsave(&fmdev->rds_buff_lock, flags); - while (rds_len > 0) { - /* - * Fill RDS buffer as per V4L2 specification. - * Store control byte - */ - type = (rds_data[2] & 0x07); - blk_idx = (type <= FM_RDS_BLOCK_C ? type : (type - 1)); - tmpbuf[2] = blk_idx; /* Offset name */ - tmpbuf[2] |= blk_idx << 3; /* Received offset */ - - /* Store data byte */ - tmpbuf[0] = rds_data[0]; - tmpbuf[1] = rds_data[1]; - - memcpy(&rds->buff[rds->wr_idx], &tmpbuf, FM_RDS_BLK_SIZE); - rds->wr_idx = (rds->wr_idx + FM_RDS_BLK_SIZE) % rds->buf_size; - - /* Check for overflow & start over */ - if (rds->wr_idx == rds->rd_idx) { - fmdbg("RDS buffer overflow\n"); - rds->wr_idx = 0; - rds->rd_idx = 0; - break; - } - rds_len -= FM_RDS_BLK_SIZE; - rds_data += FM_RDS_BLK_SIZE; - } - spin_unlock_irqrestore(&fmdev->rds_buff_lock, flags); - - /* Wakeup read queue */ - if (rds->wr_idx != rds->rd_idx) - wake_up_interruptible(&rds->read_queue); - - fm_irq_call_stage(fmdev, FM_RDS_FINISH_IDX); -} - -static void fm_irq_handle_rds_finish(struct fmdev *fmdev) -{ - fm_irq_call_stage(fmdev, FM_HW_TUNE_OP_ENDED_IDX); -} - -static void fm_irq_handle_tune_op_ended(struct fmdev *fmdev) -{ - if (fmdev->irq_info.flag & (FM_FR_EVENT | FM_BL_EVENT) & fmdev-> - irq_info.mask) { - fmdbg("irq: tune ended/bandlimit reached\n"); - if (test_and_clear_bit(FM_AF_SWITCH_INPROGRESS, &fmdev->flag)) { - fmdev->irq_info.stage = FM_AF_JUMP_RD_FREQ_IDX; - } else { - complete(&fmdev->maintask_comp); - fmdev->irq_info.stage = FM_HW_POWER_ENB_IDX; - } - } else - fmdev->irq_info.stage = FM_HW_POWER_ENB_IDX; - - fm_irq_call(fmdev); -} - -static void fm_irq_handle_power_enb(struct fmdev *fmdev) -{ - if (fmdev->irq_info.flag & FM_POW_ENB_EVENT) { - fmdbg("irq: Power Enabled/Disabled\n"); - complete(&fmdev->maintask_comp); - } - - fm_irq_call_stage(fmdev, FM_LOW_RSSI_START_IDX); -} - -static void fm_irq_handle_low_rssi_start(struct fmdev *fmdev) -{ - if ((fmdev->rx.af_mode == FM_RX_RDS_AF_SWITCH_MODE_ON) && - (fmdev->irq_info.flag & FM_LEV_EVENT & fmdev->irq_info.mask) && - (fmdev->rx.freq != FM_UNDEFINED_FREQ) && - (fmdev->rx.stat_info.afcache_size != 0)) { - fmdbg("irq: rssi level has fallen below threshold level\n"); - - /* Disable further low RSSI interrupts */ - fmdev->irq_info.mask &= ~FM_LEV_EVENT; - - fmdev->rx.afjump_idx = 0; - fmdev->rx.freq_before_jump = fmdev->rx.freq; - fmdev->irq_info.stage = FM_AF_JUMP_SETPI_IDX; - } else { - /* Continue next function in interrupt handler table */ - fmdev->irq_info.stage = FM_SEND_INTMSK_CMD_IDX; - } - - fm_irq_call(fmdev); -} - -static void fm_irq_afjump_set_pi(struct fmdev *fmdev) -{ - u16 payload; - - /* Set PI code - must be updated if the AF list is not empty */ - payload = fmdev->rx.stat_info.picode; - if (!fm_send_cmd(fmdev, RDS_PI_SET, REG_WR, &payload, sizeof(payload), NULL)) - fm_irq_timeout_stage(fmdev, FM_AF_JUMP_HANDLE_SETPI_RESP_IDX); -} - -static void fm_irq_handle_set_pi_resp(struct fmdev *fmdev) -{ - fm_irq_common_cmd_resp_helper(fmdev, FM_AF_JUMP_SETPI_MASK_IDX); -} - -/* - * Set PI mask. - * 0xFFFF = Enable PI code matching - * 0x0000 = Disable PI code matching - */ -static void fm_irq_afjump_set_pimask(struct fmdev *fmdev) -{ - u16 payload; - - payload = 0x0000; - if (!fm_send_cmd(fmdev, RDS_PI_MASK_SET, REG_WR, &payload, sizeof(payload), NULL)) - fm_irq_timeout_stage(fmdev, FM_AF_JUMP_HANDLE_SETPI_MASK_RESP_IDX); -} - -static void fm_irq_handle_set_pimask_resp(struct fmdev *fmdev) -{ - fm_irq_common_cmd_resp_helper(fmdev, FM_AF_JUMP_SET_AF_FREQ_IDX); -} - -static void fm_irq_afjump_setfreq(struct fmdev *fmdev) -{ - u16 frq_index; - u16 payload; - - fmdbg("Switch to %d KHz\n", fmdev->rx.stat_info.af_cache[fmdev->rx.afjump_idx]); - frq_index = (fmdev->rx.stat_info.af_cache[fmdev->rx.afjump_idx] - - fmdev->rx.region.bot_freq) / FM_FREQ_MUL; - - payload = frq_index; - if (!fm_send_cmd(fmdev, AF_FREQ_SET, REG_WR, &payload, sizeof(payload), NULL)) - fm_irq_timeout_stage(fmdev, FM_AF_JUMP_HANDLE_SET_AFFREQ_RESP_IDX); -} - -static void fm_irq_handle_setfreq_resp(struct fmdev *fmdev) -{ - fm_irq_common_cmd_resp_helper(fmdev, FM_AF_JUMP_ENABLE_INT_IDX); -} - -static void fm_irq_afjump_enableint(struct fmdev *fmdev) -{ - u16 payload; - - /* Enable FR (tuning operation ended) interrupt */ - payload = FM_FR_EVENT; - if (!fm_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, sizeof(payload), NULL)) - fm_irq_timeout_stage(fmdev, FM_AF_JUMP_ENABLE_INT_RESP_IDX); -} - -static void fm_irq_afjump_enableint_resp(struct fmdev *fmdev) -{ - fm_irq_common_cmd_resp_helper(fmdev, FM_AF_JUMP_START_AFJUMP_IDX); -} - -static void fm_irq_start_afjump(struct fmdev *fmdev) -{ - u16 payload; - - payload = FM_TUNER_AF_JUMP_MODE; - if (!fm_send_cmd(fmdev, TUNER_MODE_SET, REG_WR, &payload, - sizeof(payload), NULL)) - fm_irq_timeout_stage(fmdev, FM_AF_JUMP_HANDLE_START_AFJUMP_RESP_IDX); -} - -static void fm_irq_handle_start_afjump_resp(struct fmdev *fmdev) -{ - struct sk_buff *skb; - - if (check_cmdresp_status(fmdev, &skb)) - return; - - fmdev->irq_info.stage = FM_SEND_FLAG_GETCMD_IDX; - set_bit(FM_AF_SWITCH_INPROGRESS, &fmdev->flag); - clear_bit(FM_INTTASK_RUNNING, &fmdev->flag); -} - -static void fm_irq_afjump_rd_freq(struct fmdev *fmdev) -{ - u16 payload; - - if (!fm_send_cmd(fmdev, FREQ_SET, REG_RD, NULL, sizeof(payload), NULL)) - fm_irq_timeout_stage(fmdev, FM_AF_JUMP_RD_FREQ_RESP_IDX); -} - -static void fm_irq_afjump_rd_freq_resp(struct fmdev *fmdev) -{ - struct sk_buff *skb; - u16 read_freq; - u32 curr_freq, jumped_freq; - - if (check_cmdresp_status(fmdev, &skb)) - return; - - /* Skip header info and copy only response data */ - skb_pull(skb, sizeof(struct fm_event_msg_hdr)); - memcpy(&read_freq, skb->data, sizeof(read_freq)); - read_freq = be16_to_cpu((__force __be16)read_freq); - curr_freq = fmdev->rx.region.bot_freq + ((u32)read_freq * FM_FREQ_MUL); - - jumped_freq = fmdev->rx.stat_info.af_cache[fmdev->rx.afjump_idx]; - - /* If the frequency was changed the jump succeeded */ - if ((curr_freq != fmdev->rx.freq_before_jump) && (curr_freq == jumped_freq)) { - fmdbg("Successfully switched to alternate freq %d\n", curr_freq); - fmdev->rx.freq = curr_freq; - fm_rx_reset_rds_cache(fmdev); - - /* AF feature is on, enable low level RSSI interrupt */ - if (fmdev->rx.af_mode == FM_RX_RDS_AF_SWITCH_MODE_ON) - fmdev->irq_info.mask |= FM_LEV_EVENT; - - fmdev->irq_info.stage = FM_LOW_RSSI_FINISH_IDX; - } else { /* jump to the next freq in the AF list */ - fmdev->rx.afjump_idx++; - - /* If we reached the end of the list - stop searching */ - if (fmdev->rx.afjump_idx >= fmdev->rx.stat_info.afcache_size) { - fmdbg("AF switch processing failed\n"); - fmdev->irq_info.stage = FM_LOW_RSSI_FINISH_IDX; - } else { /* AF List is not over - try next one */ - - fmdbg("Trying next freq in AF cache\n"); - fmdev->irq_info.stage = FM_AF_JUMP_SETPI_IDX; - } - } - fm_irq_call(fmdev); -} - -static void fm_irq_handle_low_rssi_finish(struct fmdev *fmdev) -{ - fm_irq_call_stage(fmdev, FM_SEND_INTMSK_CMD_IDX); -} - -static void fm_irq_send_intmsk_cmd(struct fmdev *fmdev) -{ - u16 payload; - - /* Re-enable FM interrupts */ - payload = fmdev->irq_info.mask; - - if (!fm_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, - sizeof(payload), NULL)) - fm_irq_timeout_stage(fmdev, FM_HANDLE_INTMSK_CMD_RESP_IDX); -} - -static void fm_irq_handle_intmsk_cmd_resp(struct fmdev *fmdev) -{ - struct sk_buff *skb; - - if (check_cmdresp_status(fmdev, &skb)) - return; - /* - * This is last function in interrupt table to be executed. - * So, reset stage index to 0. - */ - fmdev->irq_info.stage = FM_SEND_FLAG_GETCMD_IDX; - - /* Start processing any pending interrupt */ - if (test_and_clear_bit(FM_INTTASK_SCHEDULE_PENDING, &fmdev->flag)) - fmdev->irq_info.handlers[fmdev->irq_info.stage](fmdev); - else - clear_bit(FM_INTTASK_RUNNING, &fmdev->flag); -} - -/* Returns availability of RDS data in internal buffer */ -int fmc_is_rds_data_available(struct fmdev *fmdev, struct file *file, - struct poll_table_struct *pts) -{ - poll_wait(file, &fmdev->rx.rds.read_queue, pts); - if (fmdev->rx.rds.rd_idx != fmdev->rx.rds.wr_idx) - return 0; - - return -EAGAIN; -} - -/* Copies RDS data from internal buffer to user buffer */ -int fmc_transfer_rds_from_internal_buff(struct fmdev *fmdev, struct file *file, - u8 __user *buf, size_t count) -{ - u32 block_count; - u8 tmpbuf[FM_RDS_BLK_SIZE]; - unsigned long flags; - int ret; - - if (fmdev->rx.rds.wr_idx == fmdev->rx.rds.rd_idx) { - if (file->f_flags & O_NONBLOCK) - return -EWOULDBLOCK; - - ret = wait_event_interruptible(fmdev->rx.rds.read_queue, - (fmdev->rx.rds.wr_idx != fmdev->rx.rds.rd_idx)); - if (ret) - return -EINTR; - } - - /* Calculate block count from byte count */ - count /= FM_RDS_BLK_SIZE; - block_count = 0; - ret = 0; - - while (block_count < count) { - spin_lock_irqsave(&fmdev->rds_buff_lock, flags); - - if (fmdev->rx.rds.wr_idx == fmdev->rx.rds.rd_idx) { - spin_unlock_irqrestore(&fmdev->rds_buff_lock, flags); - break; - } - memcpy(tmpbuf, &fmdev->rx.rds.buff[fmdev->rx.rds.rd_idx], - FM_RDS_BLK_SIZE); - fmdev->rx.rds.rd_idx += FM_RDS_BLK_SIZE; - if (fmdev->rx.rds.rd_idx >= fmdev->rx.rds.buf_size) - fmdev->rx.rds.rd_idx = 0; - - spin_unlock_irqrestore(&fmdev->rds_buff_lock, flags); - - if (copy_to_user(buf, tmpbuf, FM_RDS_BLK_SIZE)) - break; - - block_count++; - buf += FM_RDS_BLK_SIZE; - ret += FM_RDS_BLK_SIZE; - } - return ret; -} - -int fmc_set_freq(struct fmdev *fmdev, u32 freq_to_set) -{ - switch (fmdev->curr_fmmode) { - case FM_MODE_RX: - return fm_rx_set_freq(fmdev, freq_to_set); - - case FM_MODE_TX: - return fm_tx_set_freq(fmdev, freq_to_set); - - default: - return -EINVAL; - } -} - -int fmc_get_freq(struct fmdev *fmdev, u32 *cur_tuned_frq) -{ - if (fmdev->rx.freq == FM_UNDEFINED_FREQ) { - fmerr("RX frequency is not set\n"); - return -EPERM; - } - if (cur_tuned_frq == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - switch (fmdev->curr_fmmode) { - case FM_MODE_RX: - *cur_tuned_frq = fmdev->rx.freq; - return 0; - - case FM_MODE_TX: - *cur_tuned_frq = 0; /* TODO : Change this later */ - return 0; - - default: - return -EINVAL; - } - -} - -int fmc_set_region(struct fmdev *fmdev, u8 region_to_set) -{ - switch (fmdev->curr_fmmode) { - case FM_MODE_RX: - return fm_rx_set_region(fmdev, region_to_set); - - case FM_MODE_TX: - return fm_tx_set_region(fmdev, region_to_set); - - default: - return -EINVAL; - } -} - -int fmc_set_mute_mode(struct fmdev *fmdev, u8 mute_mode_toset) -{ - switch (fmdev->curr_fmmode) { - case FM_MODE_RX: - return fm_rx_set_mute_mode(fmdev, mute_mode_toset); - - case FM_MODE_TX: - return fm_tx_set_mute_mode(fmdev, mute_mode_toset); - - default: - return -EINVAL; - } -} - -int fmc_set_stereo_mono(struct fmdev *fmdev, u16 mode) -{ - switch (fmdev->curr_fmmode) { - case FM_MODE_RX: - return fm_rx_set_stereo_mono(fmdev, mode); - - case FM_MODE_TX: - return fm_tx_set_stereo_mono(fmdev, mode); - - default: - return -EINVAL; - } -} - -int fmc_set_rds_mode(struct fmdev *fmdev, u8 rds_en_dis) -{ - switch (fmdev->curr_fmmode) { - case FM_MODE_RX: - return fm_rx_set_rds_mode(fmdev, rds_en_dis); - - case FM_MODE_TX: - return fm_tx_set_rds_mode(fmdev, rds_en_dis); - - default: - return -EINVAL; - } -} - -/* Sends power off command to the chip */ -static int fm_power_down(struct fmdev *fmdev) -{ - u16 payload; - int ret; - - if (!test_bit(FM_CORE_READY, &fmdev->flag)) { - fmerr("FM core is not ready\n"); - return -EPERM; - } - if (fmdev->curr_fmmode == FM_MODE_OFF) { - fmdbg("FM chip is already in OFF state\n"); - return 0; - } - - payload = 0x0; - ret = fmc_send_cmd(fmdev, FM_POWER_MODE, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - return fmc_release(fmdev); -} - -/* Reads init command from FM firmware file and loads to the chip */ -static int fm_download_firmware(struct fmdev *fmdev, const u8 *fw_name) -{ - const struct firmware *fw_entry; - struct bts_header *fw_header; - struct bts_action *action; - struct bts_action_delay *delay; - u8 *fw_data; - int ret, fw_len; - - set_bit(FM_FW_DW_INPROGRESS, &fmdev->flag); - - ret = request_firmware(&fw_entry, fw_name, - &fmdev->radio_dev->dev); - if (ret < 0) { - fmerr("Unable to read firmware(%s) content\n", fw_name); - return ret; - } - fmdbg("Firmware(%s) length : %zu bytes\n", fw_name, fw_entry->size); - - fw_data = (void *)fw_entry->data; - fw_len = fw_entry->size; - - fw_header = (struct bts_header *)fw_data; - if (fw_header->magic != FM_FW_FILE_HEADER_MAGIC) { - fmerr("%s not a legal TI firmware file\n", fw_name); - ret = -EINVAL; - goto rel_fw; - } - fmdbg("FW(%s) magic number : 0x%x\n", fw_name, fw_header->magic); - - /* Skip file header info , we already verified it */ - fw_data += sizeof(struct bts_header); - fw_len -= sizeof(struct bts_header); - - while (fw_data && fw_len > 0) { - action = (struct bts_action *)fw_data; - - switch (action->type) { - case ACTION_SEND_COMMAND: /* Send */ - ret = fmc_send_cmd(fmdev, 0, 0, action->data, - action->size, NULL, NULL); - if (ret) - goto rel_fw; - - break; - - case ACTION_DELAY: /* Delay */ - delay = (struct bts_action_delay *)action->data; - mdelay(delay->msec); - break; - } - - fw_data += (sizeof(struct bts_action) + (action->size)); - fw_len -= (sizeof(struct bts_action) + (action->size)); - } - fmdbg("Transferred only %d of %d bytes of the firmware to chip\n", - fw_entry->size - fw_len, fw_entry->size); -rel_fw: - release_firmware(fw_entry); - clear_bit(FM_FW_DW_INPROGRESS, &fmdev->flag); - - return ret; -} - -/* Loads default RX configuration to the chip */ -static int load_default_rx_configuration(struct fmdev *fmdev) -{ - int ret; - - ret = fm_rx_set_volume(fmdev, FM_DEFAULT_RX_VOLUME); - if (ret < 0) - return ret; - - return fm_rx_set_rssi_threshold(fmdev, FM_DEFAULT_RSSI_THRESHOLD); -} - -/* Does FM power on sequence */ -static int fm_power_up(struct fmdev *fmdev, u8 mode) -{ - u16 payload; - __be16 asic_id = 0, asic_ver = 0; - int resp_len, ret; - u8 fw_name[50]; - - if (mode >= FM_MODE_ENTRY_MAX) { - fmerr("Invalid firmware download option\n"); - return -EINVAL; - } - - /* - * Initialize FM common module. FM GPIO toggling is - * taken care in Shared Transport driver. - */ - ret = fmc_prepare(fmdev); - if (ret < 0) { - fmerr("Unable to prepare FM Common\n"); - return ret; - } - - payload = FM_ENABLE; - if (fmc_send_cmd(fmdev, FM_POWER_MODE, REG_WR, &payload, - sizeof(payload), NULL, NULL)) - goto rel; - - /* Allow the chip to settle down in Channel-8 mode */ - msleep(20); - - if (fmc_send_cmd(fmdev, ASIC_ID_GET, REG_RD, NULL, - sizeof(asic_id), &asic_id, &resp_len)) - goto rel; - - if (fmc_send_cmd(fmdev, ASIC_VER_GET, REG_RD, NULL, - sizeof(asic_ver), &asic_ver, &resp_len)) - goto rel; - - fmdbg("ASIC ID: 0x%x , ASIC Version: %d\n", - be16_to_cpu(asic_id), be16_to_cpu(asic_ver)); - - sprintf(fw_name, "%s_%x.%d.bts", FM_FMC_FW_FILE_START, - be16_to_cpu(asic_id), be16_to_cpu(asic_ver)); - - ret = fm_download_firmware(fmdev, fw_name); - if (ret < 0) { - fmdbg("Failed to download firmware file %s\n", fw_name); - goto rel; - } - sprintf(fw_name, "%s_%x.%d.bts", (mode == FM_MODE_RX) ? - FM_RX_FW_FILE_START : FM_TX_FW_FILE_START, - be16_to_cpu(asic_id), be16_to_cpu(asic_ver)); - - ret = fm_download_firmware(fmdev, fw_name); - if (ret < 0) { - fmdbg("Failed to download firmware file %s\n", fw_name); - goto rel; - } else - return ret; -rel: - return fmc_release(fmdev); -} - -/* Set FM Modes(TX, RX, OFF) */ -int fmc_set_mode(struct fmdev *fmdev, u8 fm_mode) -{ - int ret = 0; - - if (fm_mode >= FM_MODE_ENTRY_MAX) { - fmerr("Invalid FM mode\n"); - return -EINVAL; - } - if (fmdev->curr_fmmode == fm_mode) { - fmdbg("Already fm is in mode(%d)\n", fm_mode); - return ret; - } - - switch (fm_mode) { - case FM_MODE_OFF: /* OFF Mode */ - ret = fm_power_down(fmdev); - if (ret < 0) { - fmerr("Failed to set OFF mode\n"); - return ret; - } - break; - - case FM_MODE_TX: /* TX Mode */ - case FM_MODE_RX: /* RX Mode */ - /* Power down before switching to TX or RX mode */ - if (fmdev->curr_fmmode != FM_MODE_OFF) { - ret = fm_power_down(fmdev); - if (ret < 0) { - fmerr("Failed to set OFF mode\n"); - return ret; - } - msleep(30); - } - ret = fm_power_up(fmdev, fm_mode); - if (ret < 0) { - fmerr("Failed to load firmware\n"); - return ret; - } - } - fmdev->curr_fmmode = fm_mode; - - /* Set default configuration */ - if (fmdev->curr_fmmode == FM_MODE_RX) { - fmdbg("Loading default rx configuration..\n"); - ret = load_default_rx_configuration(fmdev); - if (ret < 0) - fmerr("Failed to load default values\n"); - } - - return ret; -} - -/* Returns current FM mode (TX, RX, OFF) */ -int fmc_get_mode(struct fmdev *fmdev, u8 *fmmode) -{ - if (!test_bit(FM_CORE_READY, &fmdev->flag)) { - fmerr("FM core is not ready\n"); - return -EPERM; - } - if (fmmode == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - *fmmode = fmdev->curr_fmmode; - return 0; -} - -/* Called by ST layer when FM packet is available */ -static long fm_st_receive(void *arg, struct sk_buff *skb) -{ - struct fmdev *fmdev; - - fmdev = arg; - - if (skb == NULL) { - fmerr("Invalid SKB received from ST\n"); - return -EFAULT; - } - - if (skb->cb[0] != FM_PKT_LOGICAL_CHAN_NUMBER) { - fmerr("Received SKB (%p) is not FM Channel 8 pkt\n", skb); - return -EINVAL; - } - - memcpy(skb_push(skb, 1), &skb->cb[0], 1); - skb_queue_tail(&fmdev->rx_q, skb); - queue_work(system_bh_wq, &fmdev->rx_bh_work); - - return 0; -} - -/* - * Called by ST layer to indicate protocol registration completion - * status. - */ -static void fm_st_reg_comp_cb(void *arg, int data) -{ - struct fmdev *fmdev; - - fmdev = (struct fmdev *)arg; - fmdev->streg_cbdata = data; - complete(&wait_for_fmdrv_reg_comp); -} - -/* - * This function will be called from FM V4L2 open function. - * Register with ST driver and initialize driver data. - */ -int fmc_prepare(struct fmdev *fmdev) -{ - static struct st_proto_s fm_st_proto; - int ret; - - if (test_bit(FM_CORE_READY, &fmdev->flag)) { - fmdbg("FM Core is already up\n"); - return 0; - } - - memset(&fm_st_proto, 0, sizeof(fm_st_proto)); - fm_st_proto.recv = fm_st_receive; - fm_st_proto.match_packet = NULL; - fm_st_proto.reg_complete_cb = fm_st_reg_comp_cb; - fm_st_proto.write = NULL; /* TI ST driver will fill write pointer */ - fm_st_proto.priv_data = fmdev; - fm_st_proto.chnl_id = 0x08; - fm_st_proto.max_frame_size = 0xff; - fm_st_proto.hdr_len = 1; - fm_st_proto.offset_len_in_hdr = 0; - fm_st_proto.len_size = 1; - fm_st_proto.reserve = 1; - - ret = st_register(&fm_st_proto); - if (ret == -EINPROGRESS) { - init_completion(&wait_for_fmdrv_reg_comp); - fmdev->streg_cbdata = -EINPROGRESS; - fmdbg("%s waiting for ST reg completion signal\n", __func__); - - if (!wait_for_completion_timeout(&wait_for_fmdrv_reg_comp, - FM_ST_REG_TIMEOUT)) { - fmerr("Timeout(%d sec), didn't get reg completion signal from ST\n", - jiffies_to_msecs(FM_ST_REG_TIMEOUT) / 1000); - return -ETIMEDOUT; - } - if (fmdev->streg_cbdata != 0) { - fmerr("ST reg comp CB called with error status %d\n", - fmdev->streg_cbdata); - return -EAGAIN; - } - - ret = 0; - } else if (ret < 0) { - fmerr("st_register failed %d\n", ret); - return -EAGAIN; - } - - if (fm_st_proto.write != NULL) { - g_st_write = fm_st_proto.write; - } else { - fmerr("Failed to get ST write func pointer\n"); - ret = st_unregister(&fm_st_proto); - if (ret < 0) - fmerr("st_unregister failed %d\n", ret); - return -EAGAIN; - } - - spin_lock_init(&fmdev->rds_buff_lock); - spin_lock_init(&fmdev->resp_skb_lock); - - /* Initialize TX queue and TX bh work */ - skb_queue_head_init(&fmdev->tx_q); - INIT_WORK(&fmdev->tx_bh_work, send_bh_work); - - /* Initialize RX Queue and RX bh work */ - skb_queue_head_init(&fmdev->rx_q); - INIT_WORK(&fmdev->rx_bh_work, recv_bh_work); - - fmdev->irq_info.stage = 0; - atomic_set(&fmdev->tx_cnt, 1); - fmdev->resp_comp = NULL; - - timer_setup(&fmdev->irq_info.timer, int_timeout_handler, 0); - /*TODO: add FM_STIC_EVENT later */ - fmdev->irq_info.mask = FM_MAL_EVENT; - - /* Region info */ - fmdev->rx.region = region_configs[default_radio_region]; - - fmdev->rx.mute_mode = FM_MUTE_OFF; - fmdev->rx.rf_depend_mute = FM_RX_RF_DEPENDENT_MUTE_OFF; - fmdev->rx.rds.flag = FM_RDS_DISABLE; - fmdev->rx.freq = FM_UNDEFINED_FREQ; - fmdev->rx.rds_mode = FM_RDS_SYSTEM_RDS; - fmdev->rx.af_mode = FM_RX_RDS_AF_SWITCH_MODE_OFF; - fmdev->irq_info.retry = 0; - - fm_rx_reset_rds_cache(fmdev); - init_waitqueue_head(&fmdev->rx.rds.read_queue); - - fm_rx_reset_station_info(fmdev); - set_bit(FM_CORE_READY, &fmdev->flag); - - return ret; -} - -/* - * This function will be called from FM V4L2 release function. - * Unregister from ST driver. - */ -int fmc_release(struct fmdev *fmdev) -{ - static struct st_proto_s fm_st_proto; - int ret; - - if (!test_bit(FM_CORE_READY, &fmdev->flag)) { - fmdbg("FM Core is already down\n"); - return 0; - } - /* Service pending read */ - wake_up_interruptible(&fmdev->rx.rds.read_queue); - - cancel_work_sync(&fmdev->tx_bh_work); - cancel_work_sync(&fmdev->rx_bh_work); - - skb_queue_purge(&fmdev->tx_q); - skb_queue_purge(&fmdev->rx_q); - - fmdev->resp_comp = NULL; - fmdev->rx.freq = 0; - - memset(&fm_st_proto, 0, sizeof(fm_st_proto)); - fm_st_proto.chnl_id = 0x08; - - ret = st_unregister(&fm_st_proto); - - if (ret < 0) - fmerr("Failed to de-register FM from ST %d\n", ret); - else - fmdbg("Successfully unregistered from ST\n"); - - clear_bit(FM_CORE_READY, &fmdev->flag); - return ret; -} - -/* - * Module init function. Ask FM V4L module to register video device. - * Allocate memory for FM driver context and RX RDS buffer. - */ -static int __init fm_drv_init(void) -{ - struct fmdev *fmdev = NULL; - int ret = -ENOMEM; - - fmdbg("FM driver version %s\n", FM_DRV_VERSION); - - fmdev = kzalloc(sizeof(struct fmdev), GFP_KERNEL); - if (NULL == fmdev) { - fmerr("Can't allocate operation structure memory\n"); - return ret; - } - fmdev->rx.rds.buf_size = default_rds_buf * FM_RDS_BLK_SIZE; - fmdev->rx.rds.buff = kzalloc(fmdev->rx.rds.buf_size, GFP_KERNEL); - if (NULL == fmdev->rx.rds.buff) { - fmerr("Can't allocate rds ring buffer\n"); - goto rel_dev; - } - - ret = fm_v4l2_init_video_device(fmdev, radio_nr); - if (ret < 0) - goto rel_rdsbuf; - - fmdev->irq_info.handlers = int_handler_table; - fmdev->curr_fmmode = FM_MODE_OFF; - fmdev->tx_data.pwr_lvl = FM_PWR_LVL_DEF; - fmdev->tx_data.preemph = FM_TX_PREEMPH_50US; - return ret; - -rel_rdsbuf: - kfree(fmdev->rx.rds.buff); -rel_dev: - kfree(fmdev); - - return ret; -} - -/* Module exit function. Ask FM V4L module to unregister video device */ -static void __exit fm_drv_exit(void) -{ - struct fmdev *fmdev = NULL; - - fmdev = fm_v4l2_deinit_video_device(); - if (fmdev != NULL) { - kfree(fmdev->rx.rds.buff); - kfree(fmdev); - } -} - -module_init(fm_drv_init); -module_exit(fm_drv_exit); - -/* ------------- Module Info ------------- */ -MODULE_AUTHOR("Manjunatha Halli "); -MODULE_DESCRIPTION("FM Driver for TI's Connectivity chip. " FM_DRV_VERSION); -MODULE_VERSION(FM_DRV_VERSION); -MODULE_LICENSE("GPL"); diff --git a/drivers/media/radio/wl128x/fmdrv_common.h b/drivers/media/radio/wl128x/fmdrv_common.h deleted file mode 100644 index 6a287eadae75..000000000000 --- a/drivers/media/radio/wl128x/fmdrv_common.h +++ /dev/null @@ -1,389 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * FM Driver for Connectivity chip of Texas Instruments. - * FM Common module header file - * - * Copyright (C) 2011 Texas Instruments - */ - -#ifndef _FMDRV_COMMON_H -#define _FMDRV_COMMON_H - -#define FM_ST_REG_TIMEOUT msecs_to_jiffies(6000) /* 6 sec */ -#define FM_PKT_LOGICAL_CHAN_NUMBER 0x08 /* Logical channel 8 */ - -#define REG_RD 0x1 -#define REG_WR 0x0 - -struct fm_reg_table { - u8 opcode; - u8 type; - u8 *name; -}; - -#define STEREO_GET 0 -#define RSSI_LVL_GET 1 -#define IF_COUNT_GET 2 -#define FLAG_GET 3 -#define RDS_SYNC_GET 4 -#define RDS_DATA_GET 5 -#define FREQ_SET 10 -#define AF_FREQ_SET 11 -#define MOST_MODE_SET 12 -#define MOST_BLEND_SET 13 -#define DEMPH_MODE_SET 14 -#define SEARCH_LVL_SET 15 -#define BAND_SET 16 -#define MUTE_STATUS_SET 17 -#define RDS_PAUSE_LVL_SET 18 -#define RDS_PAUSE_DUR_SET 19 -#define RDS_MEM_SET 20 -#define RDS_BLK_B_SET 21 -#define RDS_MSK_B_SET 22 -#define RDS_PI_MASK_SET 23 -#define RDS_PI_SET 24 -#define RDS_SYSTEM_SET 25 -#define INT_MASK_SET 26 -#define SEARCH_DIR_SET 27 -#define VOLUME_SET 28 -#define AUDIO_ENABLE_SET 29 -#define PCM_MODE_SET 30 -#define I2S_MODE_CONFIG_SET 31 -#define POWER_SET 32 -#define INTX_CONFIG_SET 33 -#define PULL_EN_SET 34 -#define HILO_SET 35 -#define SWITCH2FREF 36 -#define FREQ_DRIFT_REPORT 37 - -#define PCE_GET 40 -#define FIRM_VER_GET 41 -#define ASIC_VER_GET 42 -#define ASIC_ID_GET 43 -#define MAN_ID_GET 44 -#define TUNER_MODE_SET 45 -#define STOP_SEARCH 46 -#define RDS_CNTRL_SET 47 - -#define WRITE_HARDWARE_REG 100 -#define CODE_DOWNLOAD 101 -#define RESET 102 - -#define FM_POWER_MODE 254 -#define FM_INTERRUPT 255 - -/* Transmitter API */ - -#define CHANL_SET 55 -#define CHANL_BW_SET 56 -#define REF_SET 57 -#define POWER_ENB_SET 90 -#define POWER_ATT_SET 58 -#define POWER_LEV_SET 59 -#define AUDIO_DEV_SET 60 -#define PILOT_DEV_SET 61 -#define RDS_DEV_SET 62 -#define TX_BAND_SET 65 -#define PUPD_SET 91 -#define AUDIO_IO_SET 63 -#define PREMPH_SET 64 -#define MONO_SET 66 -#define MUTE 92 -#define MPX_LMT_ENABLE 67 -#define PI_SET 93 -#define ECC_SET 69 -#define PTY 70 -#define AF 71 -#define DISPLAY_MODE 74 -#define RDS_REP_SET 77 -#define RDS_CONFIG_DATA_SET 98 -#define RDS_DATA_SET 99 -#define RDS_DATA_ENB 94 -#define TA_SET 78 -#define TP_SET 79 -#define DI_SET 80 -#define MS_SET 81 -#define PS_SCROLL_SPEED 82 -#define TX_AUDIO_LEVEL_TEST 96 -#define TX_AUDIO_LEVEL_TEST_THRESHOLD 73 -#define TX_AUDIO_INPUT_LEVEL_RANGE_SET 54 -#define RX_ANTENNA_SELECT 87 -#define I2C_DEV_ADDR_SET 86 -#define REF_ERR_CALIB_PARAM_SET 88 -#define REF_ERR_CALIB_PERIODICITY_SET 89 -#define SOC_INT_TRIGGER 52 -#define SOC_AUDIO_PATH_SET 83 -#define SOC_PCMI_OVERRIDE 84 -#define SOC_I2S_OVERRIDE 85 -#define RSSI_BLOCK_SCAN_FREQ_SET 95 -#define RSSI_BLOCK_SCAN_START 97 -#define RSSI_BLOCK_SCAN_DATA_GET 5 -#define READ_FMANT_TUNE_VALUE 104 - -/* SKB helpers */ -struct fm_skb_cb { - __u8 fm_op; - struct completion *completion; -}; - -#define fm_cb(skb) ((struct fm_skb_cb *)(skb->cb)) - -/* FM Channel-8 command message format */ -struct fm_cmd_msg_hdr { - __u8 hdr; /* Logical Channel-8 */ - __u8 len; /* Number of bytes follows */ - __u8 op; /* FM Opcode */ - __u8 rd_wr; /* Read/Write command */ - __u8 dlen; /* Length of payload */ -} __attribute__ ((packed)); - -#define FM_CMD_MSG_HDR_SIZE 5 /* sizeof(struct fm_cmd_msg_hdr) */ - -/* FM Channel-8 event messgage format */ -struct fm_event_msg_hdr { - __u8 header; /* Logical Channel-8 */ - __u8 len; /* Number of bytes follows */ - __u8 status; /* Event status */ - __u8 num_fm_hci_cmds; /* Number of pkts the host allowed to send */ - __u8 op; /* FM Opcode */ - __u8 rd_wr; /* Read/Write command */ - __u8 dlen; /* Length of payload */ -} __attribute__ ((packed)); - -#define FM_EVT_MSG_HDR_SIZE 7 /* sizeof(struct fm_event_msg_hdr) */ - -/* TI's magic number in firmware file */ -#define FM_FW_FILE_HEADER_MAGIC 0x42535442 - -#define FM_ENABLE 1 -#define FM_DISABLE 0 - -/* FLAG_GET register bits */ -#define FM_FR_EVENT BIT(0) -#define FM_BL_EVENT BIT(1) -#define FM_RDS_EVENT BIT(2) -#define FM_BBLK_EVENT BIT(3) -#define FM_LSYNC_EVENT BIT(4) -#define FM_LEV_EVENT BIT(5) -#define FM_IFFR_EVENT BIT(6) -#define FM_PI_EVENT BIT(7) -#define FM_PD_EVENT BIT(8) -#define FM_STIC_EVENT BIT(9) -#define FM_MAL_EVENT BIT(10) -#define FM_POW_ENB_EVENT BIT(11) - -/* - * Firmware files of FM. ASIC ID and ASIC version will be appened to this, - * later. - */ -#define FM_FMC_FW_FILE_START ("fmc_ch8") -#define FM_RX_FW_FILE_START ("fm_rx_ch8") -#define FM_TX_FW_FILE_START ("fm_tx_ch8") - -#define FM_UNDEFINED_FREQ 0xFFFFFFFF - -/* Band types */ -#define FM_BAND_EUROPE_US 0 -#define FM_BAND_JAPAN 1 - -/* Seek directions */ -#define FM_SEARCH_DIRECTION_DOWN 0 -#define FM_SEARCH_DIRECTION_UP 1 - -/* Tunner modes */ -#define FM_TUNER_STOP_SEARCH_MODE 0 -#define FM_TUNER_PRESET_MODE 1 -#define FM_TUNER_AUTONOMOUS_SEARCH_MODE 2 -#define FM_TUNER_AF_JUMP_MODE 3 - -/* Min and Max volume */ -#define FM_RX_VOLUME_MIN 0 -#define FM_RX_VOLUME_MAX 70 - -/* Volume gain step */ -#define FM_RX_VOLUME_GAIN_STEP 0x370 - -/* Mute modes */ -#define FM_MUTE_ON 0 -#define FM_MUTE_OFF 1 -#define FM_MUTE_ATTENUATE 2 - -#define FM_RX_UNMUTE_MODE 0x00 -#define FM_RX_RF_DEP_MODE 0x01 -#define FM_RX_AC_MUTE_MODE 0x02 -#define FM_RX_HARD_MUTE_LEFT_MODE 0x04 -#define FM_RX_HARD_MUTE_RIGHT_MODE 0x08 -#define FM_RX_SOFT_MUTE_FORCE_MODE 0x10 - -/* RF dependent mute mode */ -#define FM_RX_RF_DEPENDENT_MUTE_ON 1 -#define FM_RX_RF_DEPENDENT_MUTE_OFF 0 - -/* RSSI threshold min and max */ -#define FM_RX_RSSI_THRESHOLD_MIN -128 -#define FM_RX_RSSI_THRESHOLD_MAX 127 - -/* Stereo/Mono mode */ -#define FM_STEREO_MODE 0 -#define FM_MONO_MODE 1 -#define FM_STEREO_SOFT_BLEND 1 - -/* FM RX De-emphasis filter modes */ -#define FM_RX_EMPHASIS_FILTER_50_USEC 0 -#define FM_RX_EMPHASIS_FILTER_75_USEC 1 - -/* FM RDS modes */ -#define FM_RDS_DISABLE 0 -#define FM_RDS_ENABLE 1 - -#define FM_NO_PI_CODE 0 - -/* FM and RX RDS block enable/disable */ -#define FM_RX_PWR_SET_FM_ON_RDS_OFF 0x1 -#define FM_RX_PWR_SET_FM_AND_RDS_BLK_ON 0x3 -#define FM_RX_PWR_SET_FM_AND_RDS_BLK_OFF 0x0 - -/* RX RDS */ -#define FM_RX_RDS_FLUSH_FIFO 0x1 -#define FM_RX_RDS_FIFO_THRESHOLD 64 /* tuples */ -#define FM_RDS_BLK_SIZE 3 /* 3 bytes */ - -/* RDS block types */ -#define FM_RDS_BLOCK_A 0 -#define FM_RDS_BLOCK_B 1 -#define FM_RDS_BLOCK_C 2 -#define FM_RDS_BLOCK_Ctag 3 -#define FM_RDS_BLOCK_D 4 -#define FM_RDS_BLOCK_E 5 - -#define FM_RDS_BLK_IDX_A 0 -#define FM_RDS_BLK_IDX_B 1 -#define FM_RDS_BLK_IDX_C 2 -#define FM_RDS_BLK_IDX_D 3 -#define FM_RDS_BLK_IDX_UNKNOWN 0xF0 - -#define FM_RDS_STATUS_ERR_MASK 0x18 - -/* - * Represents an RDS group type & version. - * There are 15 groups, each group has 2 versions: A and B. - */ -#define FM_RDS_GROUP_TYPE_MASK_0A BIT(0) -#define FM_RDS_GROUP_TYPE_MASK_0B BIT(1) -#define FM_RDS_GROUP_TYPE_MASK_1A BIT(2) -#define FM_RDS_GROUP_TYPE_MASK_1B BIT(3) -#define FM_RDS_GROUP_TYPE_MASK_2A BIT(4) -#define FM_RDS_GROUP_TYPE_MASK_2B BIT(5) -#define FM_RDS_GROUP_TYPE_MASK_3A BIT(6) -#define FM_RDS_GROUP_TYPE_MASK_3B BIT(7) -#define FM_RDS_GROUP_TYPE_MASK_4A BIT(8) -#define FM_RDS_GROUP_TYPE_MASK_4B BIT(9) -#define FM_RDS_GROUP_TYPE_MASK_5A BIT(10) -#define FM_RDS_GROUP_TYPE_MASK_5B BIT(11) -#define FM_RDS_GROUP_TYPE_MASK_6A BIT(12) -#define FM_RDS_GROUP_TYPE_MASK_6B BIT(13) -#define FM_RDS_GROUP_TYPE_MASK_7A BIT(14) -#define FM_RDS_GROUP_TYPE_MASK_7B BIT(15) -#define FM_RDS_GROUP_TYPE_MASK_8A BIT(16) -#define FM_RDS_GROUP_TYPE_MASK_8B BIT(17) -#define FM_RDS_GROUP_TYPE_MASK_9A BIT(18) -#define FM_RDS_GROUP_TYPE_MASK_9B BIT(19) -#define FM_RDS_GROUP_TYPE_MASK_10A BIT(20) -#define FM_RDS_GROUP_TYPE_MASK_10B BIT(21) -#define FM_RDS_GROUP_TYPE_MASK_11A BIT(22) -#define FM_RDS_GROUP_TYPE_MASK_11B BIT(23) -#define FM_RDS_GROUP_TYPE_MASK_12A BIT(24) -#define FM_RDS_GROUP_TYPE_MASK_12B BIT(25) -#define FM_RDS_GROUP_TYPE_MASK_13A BIT(26) -#define FM_RDS_GROUP_TYPE_MASK_13B BIT(27) -#define FM_RDS_GROUP_TYPE_MASK_14A BIT(28) -#define FM_RDS_GROUP_TYPE_MASK_14B BIT(29) -#define FM_RDS_GROUP_TYPE_MASK_15A BIT(30) -#define FM_RDS_GROUP_TYPE_MASK_15B BIT(31) - -/* RX Alternate Frequency info */ -#define FM_RDS_MIN_AF 1 -#define FM_RDS_MAX_AF 204 -#define FM_RDS_MAX_AF_JAPAN 140 -#define FM_RDS_1_AF_FOLLOWS 225 -#define FM_RDS_25_AF_FOLLOWS 249 - -/* RDS system type (RDS/RBDS) */ -#define FM_RDS_SYSTEM_RDS 0 -#define FM_RDS_SYSTEM_RBDS 1 - -/* AF on/off */ -#define FM_RX_RDS_AF_SWITCH_MODE_ON 1 -#define FM_RX_RDS_AF_SWITCH_MODE_OFF 0 - -/* Retry count when interrupt process goes wrong */ -#define FM_IRQ_TIMEOUT_RETRY_MAX 5 /* 5 times */ - -/* Audio IO set values */ -#define FM_RX_AUDIO_ENABLE_I2S 0x01 -#define FM_RX_AUDIO_ENABLE_ANALOG 0x02 -#define FM_RX_AUDIO_ENABLE_I2S_AND_ANALOG 0x03 -#define FM_RX_AUDIO_ENABLE_DISABLE 0x00 - -/* HI/LO set values */ -#define FM_RX_IFFREQ_TO_HI_SIDE 0x0 -#define FM_RX_IFFREQ_TO_LO_SIDE 0x1 -#define FM_RX_IFFREQ_HILO_AUTOMATIC 0x2 - -/* - * Default RX mode configuration. Chip will be configured - * with this default values after loading RX firmware. - */ -#define FM_DEFAULT_RX_VOLUME 10 -#define FM_DEFAULT_RSSI_THRESHOLD 3 - -/* Range for TX power level in units for dB/uV */ -#define FM_PWR_LVL_LOW 91 -#define FM_PWR_LVL_HIGH 122 - -/* Chip specific default TX power level value */ -#define FM_PWR_LVL_DEF 4 - -/* FM TX Pre-emphasis filter values */ -#define FM_TX_PREEMPH_OFF 1 -#define FM_TX_PREEMPH_50US 0 -#define FM_TX_PREEMPH_75US 2 - -/* FM TX antenna impedance values */ -#define FM_TX_ANT_IMP_50 0 -#define FM_TX_ANT_IMP_200 1 -#define FM_TX_ANT_IMP_500 2 - -/* Functions exported by FM common sub-module */ -int fmc_prepare(struct fmdev *); -int fmc_release(struct fmdev *); - -void fmc_update_region_info(struct fmdev *, u8); -int fmc_send_cmd(struct fmdev *, u8, u16, - void *, unsigned int, void *, int *); -int fmc_is_rds_data_available(struct fmdev *, struct file *, - struct poll_table_struct *); -int fmc_transfer_rds_from_internal_buff(struct fmdev *, struct file *, - u8 __user *, size_t); - -int fmc_set_freq(struct fmdev *, u32); -int fmc_set_mode(struct fmdev *, u8); -int fmc_set_region(struct fmdev *, u8); -int fmc_set_mute_mode(struct fmdev *, u8); -int fmc_set_stereo_mono(struct fmdev *, u16); -int fmc_set_rds_mode(struct fmdev *, u8); - -int fmc_get_freq(struct fmdev *, u32 *); -int fmc_get_region(struct fmdev *, u8 *); -int fmc_get_mode(struct fmdev *, u8 *); - -/* - * channel spacing - */ -#define FM_CHANNEL_SPACING_50KHZ 1 -#define FM_CHANNEL_SPACING_100KHZ 2 -#define FM_CHANNEL_SPACING_200KHZ 4 -#define FM_FREQ_MUL 50 - -#endif - diff --git a/drivers/media/radio/wl128x/fmdrv_rx.c b/drivers/media/radio/wl128x/fmdrv_rx.c deleted file mode 100644 index 419cf2e03bcf..000000000000 --- a/drivers/media/radio/wl128x/fmdrv_rx.c +++ /dev/null @@ -1,820 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * FM Driver for Connectivity chip of Texas Instruments. - * This sub-module of FM driver implements FM RX functionality. - * - * Copyright (C) 2011 Texas Instruments - * Author: Raja Mani - * Author: Manjunatha Halli - */ - -#include "fmdrv.h" -#include "fmdrv_common.h" -#include "fmdrv_rx.h" - -void fm_rx_reset_rds_cache(struct fmdev *fmdev) -{ - fmdev->rx.rds.flag = FM_RDS_DISABLE; - fmdev->rx.rds.last_blk_idx = 0; - fmdev->rx.rds.wr_idx = 0; - fmdev->rx.rds.rd_idx = 0; - - if (fmdev->rx.af_mode == FM_RX_RDS_AF_SWITCH_MODE_ON) - fmdev->irq_info.mask |= FM_LEV_EVENT; -} - -void fm_rx_reset_station_info(struct fmdev *fmdev) -{ - fmdev->rx.stat_info.picode = FM_NO_PI_CODE; - fmdev->rx.stat_info.afcache_size = 0; - fmdev->rx.stat_info.af_list_max = 0; -} - -int fm_rx_set_freq(struct fmdev *fmdev, u32 freq) -{ - unsigned long timeleft; - u16 payload, curr_frq, intr_flag; - u32 curr_frq_in_khz; - u32 resp_len; - int ret; - - if (freq < fmdev->rx.region.bot_freq || freq > fmdev->rx.region.top_freq) { - fmerr("Invalid frequency %d\n", freq); - return -EINVAL; - } - - /* Set audio enable */ - payload = FM_RX_AUDIO_ENABLE_I2S_AND_ANALOG; - - ret = fmc_send_cmd(fmdev, AUDIO_ENABLE_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Set hilo to automatic selection */ - payload = FM_RX_IFFREQ_HILO_AUTOMATIC; - ret = fmc_send_cmd(fmdev, HILO_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Calculate frequency index and set*/ - payload = (freq - fmdev->rx.region.bot_freq) / FM_FREQ_MUL; - - ret = fmc_send_cmd(fmdev, FREQ_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Read flags - just to clear any pending interrupts if we had */ - ret = fmc_send_cmd(fmdev, FLAG_GET, REG_RD, NULL, 2, NULL, NULL); - if (ret < 0) - return ret; - - /* Enable FR, BL interrupts */ - intr_flag = fmdev->irq_info.mask; - fmdev->irq_info.mask = (FM_FR_EVENT | FM_BL_EVENT); - payload = fmdev->irq_info.mask; - ret = fmc_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Start tune */ - payload = FM_TUNER_PRESET_MODE; - ret = fmc_send_cmd(fmdev, TUNER_MODE_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - goto exit; - - /* Wait for tune ended interrupt */ - init_completion(&fmdev->maintask_comp); - timeleft = wait_for_completion_timeout(&fmdev->maintask_comp, - FM_DRV_TX_TIMEOUT); - if (!timeleft) { - fmerr("Timeout(%d sec),didn't get tune ended int\n", - jiffies_to_msecs(FM_DRV_TX_TIMEOUT) / 1000); - ret = -ETIMEDOUT; - goto exit; - } - - /* Read freq back to confirm */ - ret = fmc_send_cmd(fmdev, FREQ_SET, REG_RD, NULL, 2, &curr_frq, &resp_len); - if (ret < 0) - goto exit; - - curr_frq = be16_to_cpu((__force __be16)curr_frq); - curr_frq_in_khz = (fmdev->rx.region.bot_freq + ((u32)curr_frq * FM_FREQ_MUL)); - - if (curr_frq_in_khz != freq) { - pr_info("Frequency is set to (%d) but requested freq is (%d)\n", - curr_frq_in_khz, freq); - } - - /* Update local cache */ - fmdev->rx.freq = curr_frq_in_khz; -exit: - /* Re-enable default FM interrupts */ - fmdev->irq_info.mask = intr_flag; - payload = fmdev->irq_info.mask; - ret = fmc_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Reset RDS cache and current station pointers */ - fm_rx_reset_rds_cache(fmdev); - fm_rx_reset_station_info(fmdev); - - return ret; -} - -static int fm_rx_set_channel_spacing(struct fmdev *fmdev, u32 spacing) -{ - u16 payload; - int ret; - - if (spacing > 0 && spacing <= 50000) - spacing = FM_CHANNEL_SPACING_50KHZ; - else if (spacing > 50000 && spacing <= 100000) - spacing = FM_CHANNEL_SPACING_100KHZ; - else - spacing = FM_CHANNEL_SPACING_200KHZ; - - /* set channel spacing */ - payload = spacing; - ret = fmc_send_cmd(fmdev, CHANL_BW_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - fmdev->rx.region.chanl_space = spacing * FM_FREQ_MUL; - - return ret; -} - -int fm_rx_seek(struct fmdev *fmdev, u32 seek_upward, - u32 wrap_around, u32 spacing) -{ - u32 resp_len; - u16 curr_frq, next_frq, last_frq; - u16 payload, int_reason, intr_flag; - u16 offset, space_idx; - unsigned long timeleft; - int ret; - - /* Set channel spacing */ - ret = fm_rx_set_channel_spacing(fmdev, spacing); - if (ret < 0) { - fmerr("Failed to set channel spacing\n"); - return ret; - } - - /* Read the current frequency from chip */ - ret = fmc_send_cmd(fmdev, FREQ_SET, REG_RD, NULL, - sizeof(curr_frq), &curr_frq, &resp_len); - if (ret < 0) - return ret; - - curr_frq = be16_to_cpu((__force __be16)curr_frq); - last_frq = (fmdev->rx.region.top_freq - fmdev->rx.region.bot_freq) / FM_FREQ_MUL; - - /* Check the offset in order to be aligned to the channel spacing*/ - space_idx = fmdev->rx.region.chanl_space / FM_FREQ_MUL; - offset = curr_frq % space_idx; - - next_frq = seek_upward ? curr_frq + space_idx /* Seek Up */ : - curr_frq - space_idx /* Seek Down */ ; - - /* - * Add or subtract offset in order to stay aligned to the channel - * spacing. - */ - if ((short)next_frq < 0) - next_frq = last_frq - offset; - else if (next_frq > last_frq) - next_frq = 0 + offset; - -again: - /* Set calculated next frequency to perform seek */ - payload = next_frq; - ret = fmc_send_cmd(fmdev, FREQ_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Set search direction (0:Seek Down, 1:Seek Up) */ - payload = (seek_upward ? FM_SEARCH_DIRECTION_UP : FM_SEARCH_DIRECTION_DOWN); - ret = fmc_send_cmd(fmdev, SEARCH_DIR_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Read flags - just to clear any pending interrupts if we had */ - ret = fmc_send_cmd(fmdev, FLAG_GET, REG_RD, NULL, 2, NULL, NULL); - if (ret < 0) - return ret; - - /* Enable FR, BL interrupts */ - intr_flag = fmdev->irq_info.mask; - fmdev->irq_info.mask = (FM_FR_EVENT | FM_BL_EVENT); - payload = fmdev->irq_info.mask; - ret = fmc_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Start seek */ - payload = FM_TUNER_AUTONOMOUS_SEARCH_MODE; - ret = fmc_send_cmd(fmdev, TUNER_MODE_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Wait for tune ended/band limit reached interrupt */ - init_completion(&fmdev->maintask_comp); - timeleft = wait_for_completion_timeout(&fmdev->maintask_comp, - FM_DRV_RX_SEEK_TIMEOUT); - if (!timeleft) { - fmerr("Timeout(%d sec),didn't get tune ended int\n", - jiffies_to_msecs(FM_DRV_RX_SEEK_TIMEOUT) / 1000); - return -ENODATA; - } - - int_reason = fmdev->irq_info.flag & (FM_TUNE_COMPLETE | FM_BAND_LIMIT); - - /* Re-enable default FM interrupts */ - fmdev->irq_info.mask = intr_flag; - payload = fmdev->irq_info.mask; - ret = fmc_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - if (int_reason & FM_BL_EVENT) { - if (wrap_around == 0) { - fmdev->rx.freq = seek_upward ? - fmdev->rx.region.top_freq : - fmdev->rx.region.bot_freq; - } else { - fmdev->rx.freq = seek_upward ? - fmdev->rx.region.bot_freq : - fmdev->rx.region.top_freq; - /* Calculate frequency index to write */ - next_frq = (fmdev->rx.freq - - fmdev->rx.region.bot_freq) / FM_FREQ_MUL; - goto again; - } - } else { - /* Read freq to know where operation tune operation stopped */ - ret = fmc_send_cmd(fmdev, FREQ_SET, REG_RD, NULL, 2, - &curr_frq, &resp_len); - if (ret < 0) - return ret; - - curr_frq = be16_to_cpu((__force __be16)curr_frq); - fmdev->rx.freq = (fmdev->rx.region.bot_freq + - ((u32)curr_frq * FM_FREQ_MUL)); - - } - /* Reset RDS cache and current station pointers */ - fm_rx_reset_rds_cache(fmdev); - fm_rx_reset_station_info(fmdev); - - return ret; -} - -int fm_rx_set_volume(struct fmdev *fmdev, u16 vol_to_set) -{ - u16 payload; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (vol_to_set > FM_RX_VOLUME_MAX) { - fmerr("Volume is not within(%d-%d) range\n", - FM_RX_VOLUME_MIN, FM_RX_VOLUME_MAX); - return -EINVAL; - } - vol_to_set *= FM_RX_VOLUME_GAIN_STEP; - - payload = vol_to_set; - ret = fmc_send_cmd(fmdev, VOLUME_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - fmdev->rx.volume = vol_to_set; - return ret; -} - -/* Get volume */ -int fm_rx_get_volume(struct fmdev *fmdev, u16 *curr_vol) -{ - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (curr_vol == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - *curr_vol = fmdev->rx.volume / FM_RX_VOLUME_GAIN_STEP; - - return 0; -} - -/* To get current band's bottom and top frequency */ -int fm_rx_get_band_freq_range(struct fmdev *fmdev, u32 *bot_freq, u32 *top_freq) -{ - if (bot_freq != NULL) - *bot_freq = fmdev->rx.region.bot_freq; - - if (top_freq != NULL) - *top_freq = fmdev->rx.region.top_freq; - - return 0; -} - -/* Returns current band index (0-Europe/US; 1-Japan) */ -void fm_rx_get_region(struct fmdev *fmdev, u8 *region) -{ - *region = fmdev->rx.region.fm_band; -} - -/* Sets band (0-Europe/US; 1-Japan) */ -int fm_rx_set_region(struct fmdev *fmdev, u8 region_to_set) -{ - u16 payload; - u32 new_frq = 0; - int ret; - - if (region_to_set != FM_BAND_EUROPE_US && - region_to_set != FM_BAND_JAPAN) { - fmerr("Invalid band\n"); - return -EINVAL; - } - - if (fmdev->rx.region.fm_band == region_to_set) { - fmerr("Requested band is already configured\n"); - return 0; - } - - /* Send cmd to set the band */ - payload = (u16)region_to_set; - ret = fmc_send_cmd(fmdev, BAND_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - fmc_update_region_info(fmdev, region_to_set); - - /* Check whether current RX frequency is within band boundary */ - if (fmdev->rx.freq < fmdev->rx.region.bot_freq) - new_frq = fmdev->rx.region.bot_freq; - else if (fmdev->rx.freq > fmdev->rx.region.top_freq) - new_frq = fmdev->rx.region.top_freq; - - if (new_frq) { - fmdbg("Current freq is not within band limit boundary,switching to %d KHz\n", - new_frq); - /* Current RX frequency is not in range. So, update it */ - ret = fm_rx_set_freq(fmdev, new_frq); - } - - return ret; -} - -/* Reads current mute mode (Mute Off/On/Attenuate)*/ -int fm_rx_get_mute_mode(struct fmdev *fmdev, u8 *curr_mute_mode) -{ - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (curr_mute_mode == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - *curr_mute_mode = fmdev->rx.mute_mode; - - return 0; -} - -static int fm_config_rx_mute_reg(struct fmdev *fmdev) -{ - u16 payload, muteval; - int ret; - - muteval = 0; - switch (fmdev->rx.mute_mode) { - case FM_MUTE_ON: - muteval = FM_RX_AC_MUTE_MODE; - break; - - case FM_MUTE_OFF: - muteval = FM_RX_UNMUTE_MODE; - break; - - case FM_MUTE_ATTENUATE: - muteval = FM_RX_SOFT_MUTE_FORCE_MODE; - break; - } - if (fmdev->rx.rf_depend_mute == FM_RX_RF_DEPENDENT_MUTE_ON) - muteval |= FM_RX_RF_DEP_MODE; - else - muteval &= ~FM_RX_RF_DEP_MODE; - - payload = muteval; - ret = fmc_send_cmd(fmdev, MUTE_STATUS_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - return 0; -} - -/* Configures mute mode (Mute Off/On/Attenuate) */ -int fm_rx_set_mute_mode(struct fmdev *fmdev, u8 mute_mode_toset) -{ - u8 org_state; - int ret; - - if (fmdev->rx.mute_mode == mute_mode_toset) - return 0; - - org_state = fmdev->rx.mute_mode; - fmdev->rx.mute_mode = mute_mode_toset; - - ret = fm_config_rx_mute_reg(fmdev); - if (ret < 0) { - fmdev->rx.mute_mode = org_state; - return ret; - } - - return 0; -} - -/* Gets RF dependent soft mute mode enable/disable status */ -int fm_rx_get_rfdepend_softmute(struct fmdev *fmdev, u8 *curr_mute_mode) -{ - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (curr_mute_mode == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - *curr_mute_mode = fmdev->rx.rf_depend_mute; - - return 0; -} - -/* Sets RF dependent soft mute mode */ -int fm_rx_set_rfdepend_softmute(struct fmdev *fmdev, u8 rfdepend_mute) -{ - u8 org_state; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (rfdepend_mute != FM_RX_RF_DEPENDENT_MUTE_ON && - rfdepend_mute != FM_RX_RF_DEPENDENT_MUTE_OFF) { - fmerr("Invalid RF dependent soft mute\n"); - return -EINVAL; - } - if (fmdev->rx.rf_depend_mute == rfdepend_mute) - return 0; - - org_state = fmdev->rx.rf_depend_mute; - fmdev->rx.rf_depend_mute = rfdepend_mute; - - ret = fm_config_rx_mute_reg(fmdev); - if (ret < 0) { - fmdev->rx.rf_depend_mute = org_state; - return ret; - } - - return 0; -} - -/* Returns the signal strength level of current channel */ -int fm_rx_get_rssi_level(struct fmdev *fmdev, u16 *rssilvl) -{ - __be16 curr_rssi_lel; - u32 resp_len; - int ret; - - if (rssilvl == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - /* Read current RSSI level */ - ret = fmc_send_cmd(fmdev, RSSI_LVL_GET, REG_RD, NULL, 2, - &curr_rssi_lel, &resp_len); - if (ret < 0) - return ret; - - *rssilvl = be16_to_cpu(curr_rssi_lel); - - return 0; -} - -/* - * Sets the signal strength level that once reached - * will stop the auto search process - */ -int fm_rx_set_rssi_threshold(struct fmdev *fmdev, short rssi_lvl_toset) -{ - u16 payload; - int ret; - - if (rssi_lvl_toset < FM_RX_RSSI_THRESHOLD_MIN || - rssi_lvl_toset > FM_RX_RSSI_THRESHOLD_MAX) { - fmerr("Invalid RSSI threshold level\n"); - return -EINVAL; - } - payload = (u16)rssi_lvl_toset; - ret = fmc_send_cmd(fmdev, SEARCH_LVL_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - fmdev->rx.rssi_threshold = rssi_lvl_toset; - - return 0; -} - -/* Returns current RX RSSI threshold value */ -int fm_rx_get_rssi_threshold(struct fmdev *fmdev, short *curr_rssi_lvl) -{ - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (curr_rssi_lvl == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - *curr_rssi_lvl = fmdev->rx.rssi_threshold; - - return 0; -} - -/* Sets RX stereo/mono modes */ -int fm_rx_set_stereo_mono(struct fmdev *fmdev, u16 mode) -{ - u16 payload; - int ret; - - if (mode != FM_STEREO_MODE && mode != FM_MONO_MODE) { - fmerr("Invalid mode\n"); - return -EINVAL; - } - - /* Set stereo/mono mode */ - payload = (u16)mode; - ret = fmc_send_cmd(fmdev, MOST_MODE_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Set stereo blending mode */ - payload = FM_STEREO_SOFT_BLEND; - ret = fmc_send_cmd(fmdev, MOST_BLEND_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - return 0; -} - -/* Gets current RX stereo/mono mode */ -int fm_rx_get_stereo_mono(struct fmdev *fmdev, u16 *mode) -{ - __be16 curr_mode; - u32 resp_len; - int ret; - - if (mode == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - ret = fmc_send_cmd(fmdev, MOST_MODE_SET, REG_RD, NULL, 2, - &curr_mode, &resp_len); - if (ret < 0) - return ret; - - *mode = be16_to_cpu(curr_mode); - - return 0; -} - -/* Choose RX de-emphasis filter mode (50us/75us) */ -int fm_rx_set_deemphasis_mode(struct fmdev *fmdev, u16 mode) -{ - u16 payload; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (mode != FM_RX_EMPHASIS_FILTER_50_USEC && - mode != FM_RX_EMPHASIS_FILTER_75_USEC) { - fmerr("Invalid rx de-emphasis mode (%d)\n", mode); - return -EINVAL; - } - - payload = mode; - ret = fmc_send_cmd(fmdev, DEMPH_MODE_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - fmdev->rx.deemphasis_mode = mode; - - return 0; -} - -/* Gets current RX de-emphasis filter mode */ -int fm_rx_get_deemph_mode(struct fmdev *fmdev, u16 *curr_deemphasis_mode) -{ - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (curr_deemphasis_mode == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - *curr_deemphasis_mode = fmdev->rx.deemphasis_mode; - - return 0; -} - -/* Enable/Disable RX RDS */ -int fm_rx_set_rds_mode(struct fmdev *fmdev, u8 rds_en_dis) -{ - u16 payload; - int ret; - - if (rds_en_dis != FM_RDS_ENABLE && rds_en_dis != FM_RDS_DISABLE) { - fmerr("Invalid rds option\n"); - return -EINVAL; - } - - if (rds_en_dis == FM_RDS_ENABLE - && fmdev->rx.rds.flag == FM_RDS_DISABLE) { - /* Turn on RX RDS and RDS circuit */ - payload = FM_RX_PWR_SET_FM_AND_RDS_BLK_ON; - ret = fmc_send_cmd(fmdev, POWER_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Clear and reset RDS FIFO */ - payload = FM_RX_RDS_FLUSH_FIFO; - ret = fmc_send_cmd(fmdev, RDS_CNTRL_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Read flags - just to clear any pending interrupts. */ - ret = fmc_send_cmd(fmdev, FLAG_GET, REG_RD, NULL, 2, - NULL, NULL); - if (ret < 0) - return ret; - - /* Set RDS FIFO threshold value */ - payload = FM_RX_RDS_FIFO_THRESHOLD; - ret = fmc_send_cmd(fmdev, RDS_MEM_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Enable RDS interrupt */ - fmdev->irq_info.mask |= FM_RDS_EVENT; - payload = fmdev->irq_info.mask; - ret = fmc_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) { - fmdev->irq_info.mask &= ~FM_RDS_EVENT; - return ret; - } - - /* Update our local flag */ - fmdev->rx.rds.flag = FM_RDS_ENABLE; - } else if (rds_en_dis == FM_RDS_DISABLE - && fmdev->rx.rds.flag == FM_RDS_ENABLE) { - /* Turn off RX RDS */ - payload = FM_RX_PWR_SET_FM_ON_RDS_OFF; - ret = fmc_send_cmd(fmdev, POWER_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Reset RDS pointers */ - fmdev->rx.rds.last_blk_idx = 0; - fmdev->rx.rds.wr_idx = 0; - fmdev->rx.rds.rd_idx = 0; - fm_rx_reset_station_info(fmdev); - - /* Update RDS local cache */ - fmdev->irq_info.mask &= ~(FM_RDS_EVENT); - fmdev->rx.rds.flag = FM_RDS_DISABLE; - } - - return 0; -} - -/* Returns current RX RDS enable/disable status */ -int fm_rx_get_rds_mode(struct fmdev *fmdev, u8 *curr_rds_en_dis) -{ - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (curr_rds_en_dis == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - *curr_rds_en_dis = fmdev->rx.rds.flag; - - return 0; -} - -/* Sets RDS operation mode (RDS/RDBS) */ -int fm_rx_set_rds_system(struct fmdev *fmdev, u8 rds_mode) -{ - u16 payload; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (rds_mode != FM_RDS_SYSTEM_RDS && rds_mode != FM_RDS_SYSTEM_RBDS) { - fmerr("Invalid rds mode\n"); - return -EINVAL; - } - /* Set RDS operation mode */ - payload = (u16)rds_mode; - ret = fmc_send_cmd(fmdev, RDS_SYSTEM_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - fmdev->rx.rds_mode = rds_mode; - - return 0; -} - -/* Configures Alternate Frequency switch mode */ -int fm_rx_set_af_switch(struct fmdev *fmdev, u8 af_mode) -{ - u16 payload; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (af_mode != FM_RX_RDS_AF_SWITCH_MODE_ON && - af_mode != FM_RX_RDS_AF_SWITCH_MODE_OFF) { - fmerr("Invalid af mode\n"); - return -EINVAL; - } - /* Enable/disable low RSSI interrupt based on af_mode */ - if (af_mode == FM_RX_RDS_AF_SWITCH_MODE_ON) - fmdev->irq_info.mask |= FM_LEV_EVENT; - else - fmdev->irq_info.mask &= ~FM_LEV_EVENT; - - payload = fmdev->irq_info.mask; - ret = fmc_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - fmdev->rx.af_mode = af_mode; - - return 0; -} - -/* Returns Alternate Frequency switch status */ -int fm_rx_get_af_switch(struct fmdev *fmdev, u8 *af_mode) -{ - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - if (af_mode == NULL) { - fmerr("Invalid memory\n"); - return -ENOMEM; - } - - *af_mode = fmdev->rx.af_mode; - - return 0; -} diff --git a/drivers/media/radio/wl128x/fmdrv_rx.h b/drivers/media/radio/wl128x/fmdrv_rx.h deleted file mode 100644 index 2748e99662c3..000000000000 --- a/drivers/media/radio/wl128x/fmdrv_rx.h +++ /dev/null @@ -1,45 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * FM Driver for Connectivity chip of Texas Instruments. - * FM RX module header. - * - * Copyright (C) 2011 Texas Instruments - */ - -#ifndef _FMDRV_RX_H -#define _FMDRV_RX_H - -int fm_rx_set_freq(struct fmdev *, u32); -int fm_rx_set_mute_mode(struct fmdev *, u8); -int fm_rx_set_stereo_mono(struct fmdev *, u16); -int fm_rx_set_rds_mode(struct fmdev *, u8); -int fm_rx_set_rds_system(struct fmdev *, u8); -int fm_rx_set_volume(struct fmdev *, u16); -int fm_rx_set_rssi_threshold(struct fmdev *, short); -int fm_rx_set_region(struct fmdev *, u8); -int fm_rx_set_rfdepend_softmute(struct fmdev *, u8); -int fm_rx_set_deemphasis_mode(struct fmdev *, u16); -int fm_rx_set_af_switch(struct fmdev *, u8); - -void fm_rx_reset_rds_cache(struct fmdev *); -void fm_rx_reset_station_info(struct fmdev *); - -int fm_rx_seek(struct fmdev *, u32, u32, u32); - -int fm_rx_get_rds_mode(struct fmdev *, u8 *); -int fm_rx_get_mute_mode(struct fmdev *, u8 *); -int fm_rx_get_volume(struct fmdev *, u16 *); -int fm_rx_get_band_freq_range(struct fmdev *, - u32 *, u32 *); -int fm_rx_get_stereo_mono(struct fmdev *, u16 *); -int fm_rx_get_rssi_level(struct fmdev *, u16 *); -int fm_rx_get_rssi_threshold(struct fmdev *, short *); -int fm_rx_get_rfdepend_softmute(struct fmdev *, u8 *); -int fm_rx_get_deemph_mode(struct fmdev *, u16 *); -int fm_rx_get_af_switch(struct fmdev *, u8 *); -void fm_rx_get_region(struct fmdev *, u8 *); - -int fm_rx_set_chanl_spacing(struct fmdev *, u8); -int fm_rx_get_chanl_spacing(struct fmdev *, u8 *); -#endif - diff --git a/drivers/media/radio/wl128x/fmdrv_tx.c b/drivers/media/radio/wl128x/fmdrv_tx.c deleted file mode 100644 index c589de02f4f5..000000000000 --- a/drivers/media/radio/wl128x/fmdrv_tx.c +++ /dev/null @@ -1,413 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * FM Driver for Connectivity chip of Texas Instruments. - * This sub-module of FM driver implements FM TX functionality. - * - * Copyright (C) 2011 Texas Instruments - */ - -#include -#include "fmdrv.h" -#include "fmdrv_common.h" -#include "fmdrv_tx.h" - -int fm_tx_set_stereo_mono(struct fmdev *fmdev, u16 mode) -{ - u16 payload; - int ret; - - if (fmdev->tx_data.aud_mode == mode) - return 0; - - fmdbg("stereo mode: %d\n", mode); - - /* Set Stereo/Mono mode */ - payload = (1 - mode); - ret = fmc_send_cmd(fmdev, MONO_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - fmdev->tx_data.aud_mode = mode; - - return ret; -} - -static int set_rds_text(struct fmdev *fmdev, u8 *rds_text) -{ - u16 payload; - int ret; - - ret = fmc_send_cmd(fmdev, RDS_DATA_SET, REG_WR, rds_text, - strlen(rds_text), NULL, NULL); - if (ret < 0) - return ret; - - /* Scroll mode */ - payload = (u16)0x1; - ret = fmc_send_cmd(fmdev, DISPLAY_MODE, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - return 0; -} - -static int set_rds_data_mode(struct fmdev *fmdev, u8 mode) -{ - u16 payload; - int ret; - - /* Setting unique PI TODO: how unique? */ - payload = (u16)0xcafe; - ret = fmc_send_cmd(fmdev, PI_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Set decoder id */ - payload = (u16)0xa; - ret = fmc_send_cmd(fmdev, DI_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* TODO: RDS_MODE_GET? */ - return 0; -} - -static int set_rds_len(struct fmdev *fmdev, u8 type, u16 len) -{ - u16 payload; - int ret; - - len |= type << 8; - payload = len; - ret = fmc_send_cmd(fmdev, RDS_CONFIG_DATA_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* TODO: LENGTH_GET? */ - return 0; -} - -int fm_tx_set_rds_mode(struct fmdev *fmdev, u8 rds_en_dis) -{ - u16 payload; - int ret; - u8 rds_text[] = "Zoom2\n"; - - fmdbg("rds_en_dis:%d(E:%d, D:%d)\n", rds_en_dis, - FM_RDS_ENABLE, FM_RDS_DISABLE); - - if (rds_en_dis == FM_RDS_ENABLE) { - /* Set RDS length */ - set_rds_len(fmdev, 0, strlen(rds_text)); - - /* Set RDS text */ - set_rds_text(fmdev, rds_text); - - /* Set RDS mode */ - set_rds_data_mode(fmdev, 0x0); - } - - /* Send command to enable RDS */ - if (rds_en_dis == FM_RDS_ENABLE) - payload = 0x01; - else - payload = 0x00; - - ret = fmc_send_cmd(fmdev, RDS_DATA_ENB, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - if (rds_en_dis == FM_RDS_ENABLE) { - /* Set RDS length */ - set_rds_len(fmdev, 0, strlen(rds_text)); - - /* Set RDS text */ - set_rds_text(fmdev, rds_text); - } - fmdev->tx_data.rds.flag = rds_en_dis; - - return 0; -} - -int fm_tx_set_radio_text(struct fmdev *fmdev, u8 *rds_text, u8 rds_type) -{ - u16 payload; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_TX) - return -EPERM; - - fm_tx_set_rds_mode(fmdev, 0); - - /* Set RDS length */ - set_rds_len(fmdev, rds_type, strlen(rds_text)); - - /* Set RDS text */ - set_rds_text(fmdev, rds_text); - - /* Set RDS mode */ - set_rds_data_mode(fmdev, 0x0); - - payload = 1; - ret = fmc_send_cmd(fmdev, RDS_DATA_ENB, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - return 0; -} - -int fm_tx_set_af(struct fmdev *fmdev, u32 af) -{ - u16 payload; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_TX) - return -EPERM; - - fmdbg("AF: %d\n", af); - - af = (af - 87500) / 100; - payload = (u16)af; - ret = fmc_send_cmd(fmdev, TA_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - return 0; -} - -int fm_tx_set_region(struct fmdev *fmdev, u8 region) -{ - u16 payload; - int ret; - - if (region != FM_BAND_EUROPE_US && region != FM_BAND_JAPAN) { - fmerr("Invalid band\n"); - return -EINVAL; - } - - /* Send command to set the band */ - payload = (u16)region; - ret = fmc_send_cmd(fmdev, TX_BAND_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - return 0; -} - -int fm_tx_set_mute_mode(struct fmdev *fmdev, u8 mute_mode_toset) -{ - u16 payload; - int ret; - - fmdbg("tx: mute mode %d\n", mute_mode_toset); - - payload = mute_mode_toset; - ret = fmc_send_cmd(fmdev, MUTE, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - return 0; -} - -/* Set TX Audio I/O */ -static int set_audio_io(struct fmdev *fmdev) -{ - struct fmtx_data *tx = &fmdev->tx_data; - u16 payload; - int ret; - - /* Set Audio I/O Enable */ - payload = tx->audio_io; - ret = fmc_send_cmd(fmdev, AUDIO_IO_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* TODO: is audio set? */ - return 0; -} - -/* Start TX Transmission */ -static int enable_xmit(struct fmdev *fmdev, u8 new_xmit_state) -{ - struct fmtx_data *tx = &fmdev->tx_data; - unsigned long timeleft; - u16 payload; - int ret; - - /* Enable POWER_ENB interrupts */ - payload = FM_POW_ENB_EVENT; - ret = fmc_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Set Power Enable */ - payload = new_xmit_state; - ret = fmc_send_cmd(fmdev, POWER_ENB_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* Wait for Power Enabled */ - init_completion(&fmdev->maintask_comp); - timeleft = wait_for_completion_timeout(&fmdev->maintask_comp, - FM_DRV_TX_TIMEOUT); - if (!timeleft) { - fmerr("Timeout(%d sec),didn't get tune ended interrupt\n", - jiffies_to_msecs(FM_DRV_TX_TIMEOUT) / 1000); - return -ETIMEDOUT; - } - - set_bit(FM_CORE_TX_XMITING, &fmdev->flag); - tx->xmit_state = new_xmit_state; - - return 0; -} - -/* Set TX power level */ -int fm_tx_set_pwr_lvl(struct fmdev *fmdev, u8 new_pwr_lvl) -{ - u16 payload; - struct fmtx_data *tx = &fmdev->tx_data; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_TX) - return -EPERM; - fmdbg("tx: pwr_level_to_set %ld\n", (long int)new_pwr_lvl); - - /* If the core isn't ready update global variable */ - if (!test_bit(FM_CORE_READY, &fmdev->flag)) { - tx->pwr_lvl = new_pwr_lvl; - return 0; - } - - /* Set power level: Application will specify power level value in - * units of dB/uV, whereas range and step are specific to FM chip. - * For TI's WL chips, convert application specified power level value - * to chip specific value by subtracting 122 from it. Refer to TI FM - * data sheet for details. - * */ - - payload = (FM_PWR_LVL_HIGH - new_pwr_lvl); - ret = fmc_send_cmd(fmdev, POWER_LEV_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - /* TODO: is the power level set? */ - tx->pwr_lvl = new_pwr_lvl; - - return 0; -} - -/* - * Sets FM TX pre-emphasis filter value (OFF, 50us, or 75us) - * Convert V4L2 specified filter values to chip specific filter values. - */ -int fm_tx_set_preemph_filter(struct fmdev *fmdev, u32 preemphasis) -{ - struct fmtx_data *tx = &fmdev->tx_data; - u16 payload; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_TX) - return -EPERM; - - switch (preemphasis) { - case V4L2_PREEMPHASIS_DISABLED: - payload = FM_TX_PREEMPH_OFF; - break; - case V4L2_PREEMPHASIS_50_uS: - payload = FM_TX_PREEMPH_50US; - break; - case V4L2_PREEMPHASIS_75_uS: - payload = FM_TX_PREEMPH_75US; - break; - } - - ret = fmc_send_cmd(fmdev, PREMPH_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - tx->preemph = payload; - - return ret; -} - -/* Get the TX tuning capacitor value.*/ -int fm_tx_get_tune_cap_val(struct fmdev *fmdev) -{ - u16 curr_val; - u32 resp_len; - int ret; - - if (fmdev->curr_fmmode != FM_MODE_TX) - return -EPERM; - - ret = fmc_send_cmd(fmdev, READ_FMANT_TUNE_VALUE, REG_RD, - NULL, sizeof(curr_val), &curr_val, &resp_len); - if (ret < 0) - return ret; - - curr_val = be16_to_cpu((__force __be16)curr_val); - - return curr_val; -} - -/* Set TX Frequency */ -int fm_tx_set_freq(struct fmdev *fmdev, u32 freq_to_set) -{ - struct fmtx_data *tx = &fmdev->tx_data; - u16 payload, chanl_index; - int ret; - - if (test_bit(FM_CORE_TX_XMITING, &fmdev->flag)) { - enable_xmit(fmdev, 0); - clear_bit(FM_CORE_TX_XMITING, &fmdev->flag); - } - - /* Enable FR, BL interrupts */ - payload = (FM_FR_EVENT | FM_BL_EVENT); - ret = fmc_send_cmd(fmdev, INT_MASK_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - tx->tx_frq = (unsigned long)freq_to_set; - fmdbg("tx: freq_to_set %ld\n", (long int)tx->tx_frq); - - chanl_index = freq_to_set / 10; - - /* Set current tuner channel */ - payload = chanl_index; - ret = fmc_send_cmd(fmdev, CHANL_SET, REG_WR, &payload, - sizeof(payload), NULL, NULL); - if (ret < 0) - return ret; - - fm_tx_set_pwr_lvl(fmdev, tx->pwr_lvl); - fm_tx_set_preemph_filter(fmdev, tx->preemph); - - tx->audio_io = 0x01; /* I2S */ - set_audio_io(fmdev); - - enable_xmit(fmdev, 0x01); /* Enable transmission */ - - tx->aud_mode = FM_STEREO_MODE; - tx->rds.flag = FM_RDS_DISABLE; - - return 0; -} - diff --git a/drivers/media/radio/wl128x/fmdrv_tx.h b/drivers/media/radio/wl128x/fmdrv_tx.h deleted file mode 100644 index aebdadf9e99b..000000000000 --- a/drivers/media/radio/wl128x/fmdrv_tx.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * FM Driver for Connectivity chip of Texas Instruments. - * FM TX module header. - * - * Copyright (C) 2011 Texas Instruments - */ - -#ifndef _FMDRV_TX_H -#define _FMDRV_TX_H - -int fm_tx_set_freq(struct fmdev *, u32); -int fm_tx_set_pwr_lvl(struct fmdev *, u8); -int fm_tx_set_region(struct fmdev *, u8); -int fm_tx_set_mute_mode(struct fmdev *, u8); -int fm_tx_set_stereo_mono(struct fmdev *, u16); -int fm_tx_set_rds_mode(struct fmdev *, u8); -int fm_tx_set_radio_text(struct fmdev *, u8 *, u8); -int fm_tx_set_af(struct fmdev *, u32); -int fm_tx_set_preemph_filter(struct fmdev *, u32); -int fm_tx_get_tune_cap_val(struct fmdev *); - -#endif - diff --git a/drivers/media/radio/wl128x/fmdrv_v4l2.c b/drivers/media/radio/wl128x/fmdrv_v4l2.c deleted file mode 100644 index 1c146d14dbbd..000000000000 --- a/drivers/media/radio/wl128x/fmdrv_v4l2.c +++ /dev/null @@ -1,604 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * FM Driver for Connectivity chip of Texas Instruments. - * This file provides interfaces to V4L2 subsystem. - * - * This module registers with V4L2 subsystem as Radio - * data system interface (/dev/radio). During the registration, - * it will expose two set of function pointers. - * - * 1) File operation related API (open, close, read, write, poll...etc). - * 2) Set of V4L2 IOCTL complaint API. - * - * Copyright (C) 2011 Texas Instruments - * Author: Raja Mani - * Author: Manjunatha Halli - */ - -#include - -#include "fmdrv.h" -#include "fmdrv_v4l2.h" -#include "fmdrv_common.h" -#include "fmdrv_rx.h" -#include "fmdrv_tx.h" - -static struct video_device gradio_dev; -static u8 radio_disconnected; - -/* -- V4L2 RADIO (/dev/radioX) device file operation interfaces --- */ - -/* Read RX RDS data */ -static ssize_t fm_v4l2_fops_read(struct file *file, char __user * buf, - size_t count, loff_t *ppos) -{ - u8 rds_mode; - int ret; - struct fmdev *fmdev; - - fmdev = video_drvdata(file); - - if (!radio_disconnected) { - fmerr("FM device is already disconnected\n"); - return -EIO; - } - - if (mutex_lock_interruptible(&fmdev->mutex)) - return -ERESTARTSYS; - - /* Turn on RDS mode if it is disabled */ - ret = fm_rx_get_rds_mode(fmdev, &rds_mode); - if (ret < 0) { - fmerr("Unable to read current rds mode\n"); - goto read_unlock; - } - - if (rds_mode == FM_RDS_DISABLE) { - ret = fmc_set_rds_mode(fmdev, FM_RDS_ENABLE); - if (ret < 0) { - fmerr("Failed to enable rds mode\n"); - goto read_unlock; - } - } - - /* Copy RDS data from internal buffer to user buffer */ - ret = fmc_transfer_rds_from_internal_buff(fmdev, file, buf, count); -read_unlock: - mutex_unlock(&fmdev->mutex); - return ret; -} - -/* Write TX RDS data */ -static ssize_t fm_v4l2_fops_write(struct file *file, const char __user * buf, - size_t count, loff_t *ppos) -{ - struct tx_rds rds; - int ret; - struct fmdev *fmdev; - - ret = copy_from_user(&rds, buf, sizeof(rds)); - rds.text[sizeof(rds.text) - 1] = '\0'; - fmdbg("(%d)type: %d, text %s, af %d\n", - ret, rds.text_type, rds.text, rds.af_freq); - if (ret) - return -EFAULT; - - fmdev = video_drvdata(file); - if (mutex_lock_interruptible(&fmdev->mutex)) - return -ERESTARTSYS; - fm_tx_set_radio_text(fmdev, rds.text, rds.text_type); - fm_tx_set_af(fmdev, rds.af_freq); - mutex_unlock(&fmdev->mutex); - - return sizeof(rds); -} - -static __poll_t fm_v4l2_fops_poll(struct file *file, struct poll_table_struct *pts) -{ - int ret; - struct fmdev *fmdev; - - fmdev = video_drvdata(file); - mutex_lock(&fmdev->mutex); - ret = fmc_is_rds_data_available(fmdev, file, pts); - mutex_unlock(&fmdev->mutex); - if (ret < 0) - return EPOLLIN | EPOLLRDNORM; - - return 0; -} - -/* - * Handle open request for "/dev/radioX" device. - * Start with FM RX mode as default. - */ -static int fm_v4l2_fops_open(struct file *file) -{ - int ret; - struct fmdev *fmdev = NULL; - - /* Don't allow multiple open */ - if (radio_disconnected) { - fmerr("FM device is already opened\n"); - return -EBUSY; - } - - fmdev = video_drvdata(file); - - if (mutex_lock_interruptible(&fmdev->mutex)) - return -ERESTARTSYS; - ret = fmc_prepare(fmdev); - if (ret < 0) { - fmerr("Unable to prepare FM CORE\n"); - goto open_unlock; - } - - fmdbg("Load FM RX firmware..\n"); - - ret = fmc_set_mode(fmdev, FM_MODE_RX); - if (ret < 0) { - fmerr("Unable to load FM RX firmware\n"); - goto open_unlock; - } - radio_disconnected = 1; - -open_unlock: - mutex_unlock(&fmdev->mutex); - return ret; -} - -static int fm_v4l2_fops_release(struct file *file) -{ - int ret; - struct fmdev *fmdev; - - fmdev = video_drvdata(file); - if (!radio_disconnected) { - fmdbg("FM device is already closed\n"); - return 0; - } - - mutex_lock(&fmdev->mutex); - ret = fmc_set_mode(fmdev, FM_MODE_OFF); - if (ret < 0) { - fmerr("Unable to turn off the chip\n"); - goto release_unlock; - } - - ret = fmc_release(fmdev); - if (ret < 0) { - fmerr("FM CORE release failed\n"); - goto release_unlock; - } - radio_disconnected = 0; - -release_unlock: - mutex_unlock(&fmdev->mutex); - return ret; -} - -/* V4L2 RADIO (/dev/radioX) device IOCTL interfaces */ -static int fm_v4l2_vidioc_querycap(struct file *file, void *priv, - struct v4l2_capability *capability) -{ - strscpy(capability->driver, FM_DRV_NAME, sizeof(capability->driver)); - strscpy(capability->card, FM_DRV_CARD_SHORT_NAME, - sizeof(capability->card)); - sprintf(capability->bus_info, "UART"); - return 0; -} - -static int fm_g_volatile_ctrl(struct v4l2_ctrl *ctrl) -{ - struct fmdev *fmdev = container_of(ctrl->handler, - struct fmdev, ctrl_handler); - - switch (ctrl->id) { - case V4L2_CID_TUNE_ANTENNA_CAPACITOR: - ctrl->val = fm_tx_get_tune_cap_val(fmdev); - break; - default: - fmwarn("%s: Unknown IOCTL: %d\n", __func__, ctrl->id); - break; - } - - return 0; -} - -static int fm_v4l2_s_ctrl(struct v4l2_ctrl *ctrl) -{ - struct fmdev *fmdev = container_of(ctrl->handler, - struct fmdev, ctrl_handler); - - switch (ctrl->id) { - case V4L2_CID_AUDIO_VOLUME: /* set volume */ - return fm_rx_set_volume(fmdev, (u16)ctrl->val); - - case V4L2_CID_AUDIO_MUTE: /* set mute */ - return fmc_set_mute_mode(fmdev, (u8)ctrl->val); - - case V4L2_CID_TUNE_POWER_LEVEL: - /* set TX power level - ext control */ - return fm_tx_set_pwr_lvl(fmdev, (u8)ctrl->val); - - case V4L2_CID_TUNE_PREEMPHASIS: - return fm_tx_set_preemph_filter(fmdev, (u8) ctrl->val); - - default: - return -EINVAL; - } -} - -static int fm_v4l2_vidioc_g_audio(struct file *file, void *priv, - struct v4l2_audio *audio) -{ - memset(audio, 0, sizeof(*audio)); - strscpy(audio->name, "Radio", sizeof(audio->name)); - audio->capability = V4L2_AUDCAP_STEREO; - - return 0; -} - -static int fm_v4l2_vidioc_s_audio(struct file *file, void *priv, - const struct v4l2_audio *audio) -{ - if (audio->index != 0) - return -EINVAL; - - return 0; -} - -/* Get tuner attributes. If current mode is NOT RX, return error */ -static int fm_v4l2_vidioc_g_tuner(struct file *file, void *priv, - struct v4l2_tuner *tuner) -{ - struct fmdev *fmdev = video_drvdata(file); - u32 bottom_freq; - u32 top_freq; - u16 stereo_mono_mode; - u16 rssilvl; - int ret; - - if (tuner->index != 0) - return -EINVAL; - - if (fmdev->curr_fmmode != FM_MODE_RX) - return -EPERM; - - ret = fm_rx_get_band_freq_range(fmdev, &bottom_freq, &top_freq); - if (ret != 0) - return ret; - - ret = fm_rx_get_stereo_mono(fmdev, &stereo_mono_mode); - if (ret != 0) - return ret; - - ret = fm_rx_get_rssi_level(fmdev, &rssilvl); - if (ret != 0) - return ret; - - strscpy(tuner->name, "FM", sizeof(tuner->name)); - tuner->type = V4L2_TUNER_RADIO; - /* Store rangelow and rangehigh freq in unit of 62.5 Hz */ - tuner->rangelow = bottom_freq * 16; - tuner->rangehigh = top_freq * 16; - tuner->rxsubchans = V4L2_TUNER_SUB_MONO | V4L2_TUNER_SUB_STEREO | - ((fmdev->rx.rds.flag == FM_RDS_ENABLE) ? V4L2_TUNER_SUB_RDS : 0); - tuner->capability = V4L2_TUNER_CAP_STEREO | V4L2_TUNER_CAP_RDS | - V4L2_TUNER_CAP_LOW | - V4L2_TUNER_CAP_HWSEEK_BOUNDED | - V4L2_TUNER_CAP_HWSEEK_WRAP; - tuner->audmode = (stereo_mono_mode ? - V4L2_TUNER_MODE_MONO : V4L2_TUNER_MODE_STEREO); - - /* - * Actual rssi value lies in between -128 to +127. - * Convert this range from 0 to 255 by adding +128 - */ - rssilvl += 128; - - /* - * Return signal strength value should be within 0 to 65535. - * Find out correct signal radio by multiplying (65535/255) = 257 - */ - tuner->signal = rssilvl * 257; - tuner->afc = 0; - - return ret; -} - -/* - * Set tuner attributes. If current mode is NOT RX, set to RX. - * Currently, we set only audio mode (mono/stereo) and RDS state (on/off). - * Should we set other tuner attributes, too? - */ -static int fm_v4l2_vidioc_s_tuner(struct file *file, void *priv, - const struct v4l2_tuner *tuner) -{ - struct fmdev *fmdev = video_drvdata(file); - u16 aud_mode; - u8 rds_mode; - int ret; - - if (tuner->index != 0) - return -EINVAL; - - aud_mode = (tuner->audmode == V4L2_TUNER_MODE_STEREO) ? - FM_STEREO_MODE : FM_MONO_MODE; - rds_mode = (tuner->rxsubchans & V4L2_TUNER_SUB_RDS) ? - FM_RDS_ENABLE : FM_RDS_DISABLE; - - if (fmdev->curr_fmmode != FM_MODE_RX) { - ret = fmc_set_mode(fmdev, FM_MODE_RX); - if (ret < 0) { - fmerr("Failed to set RX mode\n"); - return ret; - } - } - - ret = fmc_set_stereo_mono(fmdev, aud_mode); - if (ret < 0) { - fmerr("Failed to set RX stereo/mono mode\n"); - return ret; - } - - ret = fmc_set_rds_mode(fmdev, rds_mode); - if (ret < 0) - fmerr("Failed to set RX RDS mode\n"); - - return ret; -} - -/* Get tuner or modulator radio frequency */ -static int fm_v4l2_vidioc_g_freq(struct file *file, void *priv, - struct v4l2_frequency *freq) -{ - struct fmdev *fmdev = video_drvdata(file); - int ret; - - ret = fmc_get_freq(fmdev, &freq->frequency); - if (ret < 0) { - fmerr("Failed to get frequency\n"); - return ret; - } - - /* Frequency unit of 62.5 Hz*/ - freq->frequency = (u32) freq->frequency * 16; - - return 0; -} - -/* Set tuner or modulator radio frequency */ -static int fm_v4l2_vidioc_s_freq(struct file *file, void *priv, - const struct v4l2_frequency *freq) -{ - struct fmdev *fmdev = video_drvdata(file); - - /* - * As V4L2_TUNER_CAP_LOW is set 1 user sends the frequency - * in units of 62.5 Hz. - */ - return fmc_set_freq(fmdev, freq->frequency / 16); -} - -/* Set hardware frequency seek. If current mode is NOT RX, set it RX. */ -static int fm_v4l2_vidioc_s_hw_freq_seek(struct file *file, void *priv, - const struct v4l2_hw_freq_seek *seek) -{ - struct fmdev *fmdev = video_drvdata(file); - int ret; - - if (file->f_flags & O_NONBLOCK) - return -EWOULDBLOCK; - - if (fmdev->curr_fmmode != FM_MODE_RX) { - ret = fmc_set_mode(fmdev, FM_MODE_RX); - if (ret != 0) { - fmerr("Failed to set RX mode\n"); - return ret; - } - } - - ret = fm_rx_seek(fmdev, seek->seek_upward, seek->wrap_around, - seek->spacing); - if (ret < 0) - fmerr("RX seek failed - %d\n", ret); - - return ret; -} -/* Get modulator attributes. If mode is not TX, return no attributes. */ -static int fm_v4l2_vidioc_g_modulator(struct file *file, void *priv, - struct v4l2_modulator *mod) -{ - struct fmdev *fmdev = video_drvdata(file); - - if (mod->index != 0) - return -EINVAL; - - if (fmdev->curr_fmmode != FM_MODE_TX) - return -EPERM; - - mod->txsubchans = ((fmdev->tx_data.aud_mode == FM_STEREO_MODE) ? - V4L2_TUNER_SUB_STEREO : V4L2_TUNER_SUB_MONO) | - ((fmdev->tx_data.rds.flag == FM_RDS_ENABLE) ? - V4L2_TUNER_SUB_RDS : 0); - - mod->capability = V4L2_TUNER_CAP_STEREO | V4L2_TUNER_CAP_RDS | - V4L2_TUNER_CAP_LOW; - - return 0; -} - -/* Set modulator attributes. If mode is not TX, set to TX. */ -static int fm_v4l2_vidioc_s_modulator(struct file *file, void *priv, - const struct v4l2_modulator *mod) -{ - struct fmdev *fmdev = video_drvdata(file); - u8 rds_mode; - u16 aud_mode; - int ret; - - if (mod->index != 0) - return -EINVAL; - - if (fmdev->curr_fmmode != FM_MODE_TX) { - ret = fmc_set_mode(fmdev, FM_MODE_TX); - if (ret != 0) { - fmerr("Failed to set TX mode\n"); - return ret; - } - } - - aud_mode = (mod->txsubchans & V4L2_TUNER_SUB_STEREO) ? - FM_STEREO_MODE : FM_MONO_MODE; - rds_mode = (mod->txsubchans & V4L2_TUNER_SUB_RDS) ? - FM_RDS_ENABLE : FM_RDS_DISABLE; - ret = fm_tx_set_stereo_mono(fmdev, aud_mode); - if (ret < 0) { - fmerr("Failed to set mono/stereo mode for TX\n"); - return ret; - } - ret = fm_tx_set_rds_mode(fmdev, rds_mode); - if (ret < 0) - fmerr("Failed to set rds mode for TX\n"); - - return ret; -} - -static const struct v4l2_file_operations fm_drv_fops = { - .owner = THIS_MODULE, - .read = fm_v4l2_fops_read, - .write = fm_v4l2_fops_write, - .poll = fm_v4l2_fops_poll, - .unlocked_ioctl = video_ioctl2, - .open = fm_v4l2_fops_open, - .release = fm_v4l2_fops_release, -}; - -static const struct v4l2_ctrl_ops fm_ctrl_ops = { - .s_ctrl = fm_v4l2_s_ctrl, - .g_volatile_ctrl = fm_g_volatile_ctrl, -}; -static const struct v4l2_ioctl_ops fm_drv_ioctl_ops = { - .vidioc_querycap = fm_v4l2_vidioc_querycap, - .vidioc_g_audio = fm_v4l2_vidioc_g_audio, - .vidioc_s_audio = fm_v4l2_vidioc_s_audio, - .vidioc_g_tuner = fm_v4l2_vidioc_g_tuner, - .vidioc_s_tuner = fm_v4l2_vidioc_s_tuner, - .vidioc_g_frequency = fm_v4l2_vidioc_g_freq, - .vidioc_s_frequency = fm_v4l2_vidioc_s_freq, - .vidioc_s_hw_freq_seek = fm_v4l2_vidioc_s_hw_freq_seek, - .vidioc_g_modulator = fm_v4l2_vidioc_g_modulator, - .vidioc_s_modulator = fm_v4l2_vidioc_s_modulator -}; - -/* V4L2 RADIO device parent structure */ -static const struct video_device fm_viddev_template = { - .fops = &fm_drv_fops, - .ioctl_ops = &fm_drv_ioctl_ops, - .name = FM_DRV_NAME, - .release = video_device_release_empty, - /* - * To ensure both the tuner and modulator ioctls are accessible we - * set the vfl_dir to M2M to indicate this. - * - * It is not really a mem2mem device of course, but it can both receive - * and transmit using the same radio device. It's the only radio driver - * that does this and it should really be split in two radio devices, - * but that would affect applications using this driver. - */ - .vfl_dir = VFL_DIR_M2M, - .device_caps = V4L2_CAP_HW_FREQ_SEEK | V4L2_CAP_TUNER | V4L2_CAP_RADIO | - V4L2_CAP_MODULATOR | V4L2_CAP_AUDIO | - V4L2_CAP_READWRITE | V4L2_CAP_RDS_CAPTURE, -}; - -int fm_v4l2_init_video_device(struct fmdev *fmdev, int radio_nr) -{ - struct v4l2_ctrl *ctrl; - int ret; - - strscpy(fmdev->v4l2_dev.name, FM_DRV_NAME, - sizeof(fmdev->v4l2_dev.name)); - ret = v4l2_device_register(NULL, &fmdev->v4l2_dev); - if (ret < 0) - return ret; - - /* Init mutex for core locking */ - mutex_init(&fmdev->mutex); - - /* Setup FM driver's V4L2 properties */ - gradio_dev = fm_viddev_template; - - video_set_drvdata(&gradio_dev, fmdev); - - gradio_dev.lock = &fmdev->mutex; - gradio_dev.v4l2_dev = &fmdev->v4l2_dev; - - /* Register with V4L2 subsystem as RADIO device */ - if (video_register_device(&gradio_dev, VFL_TYPE_RADIO, radio_nr)) { - v4l2_device_unregister(&fmdev->v4l2_dev); - fmerr("Could not register video device\n"); - return -ENOMEM; - } - - fmdev->radio_dev = &gradio_dev; - - /* Register to v4l2 ctrl handler framework */ - fmdev->radio_dev->ctrl_handler = &fmdev->ctrl_handler; - - ret = v4l2_ctrl_handler_init(&fmdev->ctrl_handler, 5); - if (ret < 0) { - fmerr("(fmdev): Can't init ctrl handler\n"); - v4l2_ctrl_handler_free(&fmdev->ctrl_handler); - video_unregister_device(fmdev->radio_dev); - v4l2_device_unregister(&fmdev->v4l2_dev); - return -EBUSY; - } - - /* - * Following controls are handled by V4L2 control framework. - * Added in ascending ID order. - */ - v4l2_ctrl_new_std(&fmdev->ctrl_handler, &fm_ctrl_ops, - V4L2_CID_AUDIO_VOLUME, FM_RX_VOLUME_MIN, - FM_RX_VOLUME_MAX, 1, FM_RX_VOLUME_MAX); - - v4l2_ctrl_new_std(&fmdev->ctrl_handler, &fm_ctrl_ops, - V4L2_CID_AUDIO_MUTE, 0, 1, 1, 1); - - v4l2_ctrl_new_std_menu(&fmdev->ctrl_handler, &fm_ctrl_ops, - V4L2_CID_TUNE_PREEMPHASIS, V4L2_PREEMPHASIS_75_uS, - 0, V4L2_PREEMPHASIS_75_uS); - - v4l2_ctrl_new_std(&fmdev->ctrl_handler, &fm_ctrl_ops, - V4L2_CID_TUNE_POWER_LEVEL, FM_PWR_LVL_LOW, - FM_PWR_LVL_HIGH, 1, FM_PWR_LVL_HIGH); - - ctrl = v4l2_ctrl_new_std(&fmdev->ctrl_handler, &fm_ctrl_ops, - V4L2_CID_TUNE_ANTENNA_CAPACITOR, 0, - 255, 1, 255); - - if (ctrl) - ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE; - - return 0; -} - -void *fm_v4l2_deinit_video_device(void) -{ - struct fmdev *fmdev; - - - fmdev = video_get_drvdata(&gradio_dev); - - /* Unregister to v4l2 ctrl handler framework*/ - v4l2_ctrl_handler_free(&fmdev->ctrl_handler); - - /* Unregister RADIO device from V4L2 subsystem */ - video_unregister_device(&gradio_dev); - - v4l2_device_unregister(&fmdev->v4l2_dev); - - return fmdev; -} diff --git a/drivers/media/radio/wl128x/fmdrv_v4l2.h b/drivers/media/radio/wl128x/fmdrv_v4l2.h deleted file mode 100644 index 963214e9d6f2..000000000000 --- a/drivers/media/radio/wl128x/fmdrv_v4l2.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * FM Driver for Connectivity chip of Texas Instruments. - * - * FM V4L2 module header. - * - * Copyright (C) 2011 Texas Instruments - */ - -#ifndef _FMDRV_V4L2_H -#define _FMDRV_V4L2_H - -#include -#include -#include - -int fm_v4l2_init_video_device(struct fmdev *, int); -void *fm_v4l2_deinit_video_device(void); - -#endif diff --git a/drivers/media/rc/iguanair.c b/drivers/media/rc/iguanair.c index 276bf3c8a8cb..8af94246e591 100644 --- a/drivers/media/rc/iguanair.c +++ b/drivers/media/rc/iguanair.c @@ -194,8 +194,10 @@ static int iguanair_send(struct iguanair *ir, unsigned size) if (rc) return rc; - if (wait_for_completion_timeout(&ir->completion, TIMEOUT) == 0) + if (wait_for_completion_timeout(&ir->completion, TIMEOUT) == 0) { + usb_kill_urb(ir->urb_out); return -ETIMEDOUT; + } return rc; } diff --git a/drivers/media/rc/imon_raw.c b/drivers/media/rc/imon_raw.c index b02ded52f19e..3a526dea6532 100644 --- a/drivers/media/rc/imon_raw.c +++ b/drivers/media/rc/imon_raw.c @@ -37,7 +37,7 @@ static void imon_ir_data(struct imon *imon) if (packet_no == 0xff) return; - dev_dbg(imon->dev, "data: %*ph", 8, imon->ir_buf); + dev_dbg(imon->dev, "data: %8ph", imon->ir_buf); /* * Only the first 5 bytes contain IR data. Right shift so we move diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index cd7af4d88b7f..044767eb3a38 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #define DRIVER_VERSION "1.95" @@ -658,8 +657,8 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, u8 *buf, int buf_len, if (len == 2) dev_dbg(dev, "Get hw/sw rev?"); else - dev_dbg(dev, "hw/sw rev %*ph", - 4, &buf[offset + 2]); + dev_dbg(dev, "hw/sw rev %4ph", + &buf[offset + 2]); break; case MCE_CMD_RESUME: dev_dbg(dev, "Device resume requested"); diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c index e1dd8adeba46..438483c62fac 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c @@ -191,10 +191,11 @@ static int vidtv_start_streaming(struct vidtv_dvb *dvb) mux_args.mux_buf_sz = mux_buf_sz; - dvb->streaming = true; dvb->mux = vidtv_mux_init(dvb->fe[0], dev, &mux_args); if (!dvb->mux) return -ENOMEM; + + dvb->streaming = true; vidtv_mux_start_thread(dvb->mux); dev_dbg_ratelimited(dev, "Started streaming\n"); @@ -205,6 +206,11 @@ static int vidtv_stop_streaming(struct vidtv_dvb *dvb) { struct device *dev = &dvb->pdev->dev; + if (!dvb->streaming) { + dev_warn_ratelimited(dev, "No streaming. Skipping.\n"); + return 0; + } + dvb->streaming = false; vidtv_mux_stop_thread(dvb->mux); vidtv_mux_destroy(dvb->mux); diff --git a/drivers/media/tuners/fc0013.c b/drivers/media/tuners/fc0013.c index 1006a2798eef..90d2ef067594 100644 --- a/drivers/media/tuners/fc0013.c +++ b/drivers/media/tuners/fc0013.c @@ -112,70 +112,6 @@ static int fc0013_sleep(struct dvb_frontend *fe) return 0; } -int fc0013_rc_cal_add(struct dvb_frontend *fe, int rc_val) -{ - struct fc0013_priv *priv = fe->tuner_priv; - int ret; - u8 rc_cal; - int val; - - if (fe->ops.i2c_gate_ctrl) - fe->ops.i2c_gate_ctrl(fe, 1); /* open I2C-gate */ - - /* push rc_cal value, get rc_cal value */ - ret = fc0013_writereg(priv, 0x10, 0x00); - if (ret) - goto error_out; - - /* get rc_cal value */ - ret = fc0013_readreg(priv, 0x10, &rc_cal); - if (ret) - goto error_out; - - rc_cal &= 0x0f; - - val = (int)rc_cal + rc_val; - - /* forcing rc_cal */ - ret = fc0013_writereg(priv, 0x0d, 0x11); - if (ret) - goto error_out; - - /* modify rc_cal value */ - if (val > 15) - ret = fc0013_writereg(priv, 0x10, 0x0f); - else if (val < 0) - ret = fc0013_writereg(priv, 0x10, 0x00); - else - ret = fc0013_writereg(priv, 0x10, (u8)val); - -error_out: - if (fe->ops.i2c_gate_ctrl) - fe->ops.i2c_gate_ctrl(fe, 0); /* close I2C-gate */ - - return ret; -} -EXPORT_SYMBOL(fc0013_rc_cal_add); - -int fc0013_rc_cal_reset(struct dvb_frontend *fe) -{ - struct fc0013_priv *priv = fe->tuner_priv; - int ret; - - if (fe->ops.i2c_gate_ctrl) - fe->ops.i2c_gate_ctrl(fe, 1); /* open I2C-gate */ - - ret = fc0013_writereg(priv, 0x0d, 0x01); - if (!ret) - ret = fc0013_writereg(priv, 0x10, 0x00); - - if (fe->ops.i2c_gate_ctrl) - fe->ops.i2c_gate_ctrl(fe, 0); /* close I2C-gate */ - - return ret; -} -EXPORT_SYMBOL(fc0013_rc_cal_reset); - static int fc0013_set_vhf_track(struct fc0013_priv *priv, u32 freq) { int ret; diff --git a/drivers/media/tuners/fc0013.h b/drivers/media/tuners/fc0013.h index 74ce5903f199..47ab36342ee8 100644 --- a/drivers/media/tuners/fc0013.h +++ b/drivers/media/tuners/fc0013.h @@ -16,8 +16,6 @@ extern struct dvb_frontend *fc0013_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, u8 i2c_address, int dual_master, enum fc001x_xtal_freq xtal_freq); -extern int fc0013_rc_cal_add(struct dvb_frontend *fe, int rc_val); -extern int fc0013_rc_cal_reset(struct dvb_frontend *fe); #else static inline struct dvb_frontend *fc0013_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, @@ -28,15 +26,6 @@ static inline struct dvb_frontend *fc0013_attach(struct dvb_frontend *fe, return NULL; } -static inline int fc0013_rc_cal_add(struct dvb_frontend *fe, int rc_val) -{ - return 0; -} - -static inline int fc0013_rc_cal_reset(struct dvb_frontend *fe) -{ - return 0; -} #endif #endif diff --git a/drivers/media/usb/cx231xx/cx231xx-avcore.c b/drivers/media/usb/cx231xx/cx231xx-avcore.c index 6139ef5d891d..1cfec76b72f3 100644 --- a/drivers/media/usb/cx231xx/cx231xx-avcore.c +++ b/drivers/media/usb/cx231xx/cx231xx-avcore.c @@ -2704,7 +2704,6 @@ int cx231xx_set_gpio_value(struct cx231xx *dev, int pin_number, int pin_value) dev->gpio_dir = value; status = cx231xx_set_gpio_bit(dev, dev->gpio_dir, dev->gpio_val); - value = 0; } if (pin_value == 0) diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c index 0d2c42819d39..218f712f56b1 100644 --- a/drivers/media/usb/dvb-usb-v2/af9035.c +++ b/drivers/media/usb/dvb-usb-v2/af9035.c @@ -322,13 +322,16 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap, ret = -EOPNOTSUPP; } else if ((msg[0].addr == state->af9033_i2c_addr[0]) || (msg[0].addr == state->af9033_i2c_addr[1])) { + /* demod access via firmware interface */ + u32 reg; + if (msg[0].len < 3 || msg[1].len < 1) { ret = -EOPNOTSUPP; goto unlock; } - /* demod access via firmware interface */ - u32 reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 | - msg[0].buf[2]; + + reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 | + msg[0].buf[2]; if (msg[0].addr == state->af9033_i2c_addr[1]) reg |= 0x100000; @@ -385,13 +388,16 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap, ret = -EOPNOTSUPP; } else if ((msg[0].addr == state->af9033_i2c_addr[0]) || (msg[0].addr == state->af9033_i2c_addr[1])) { + /* demod access via firmware interface */ + u32 reg; + if (msg[0].len < 3) { ret = -EOPNOTSUPP; goto unlock; } - /* demod access via firmware interface */ - u32 reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 | - msg[0].buf[2]; + + reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 | + msg[0].buf[2]; if (msg[0].addr == state->af9033_i2c_addr[1]) reg |= 0x100000; diff --git a/drivers/media/usb/dvb-usb-v2/lmedm04.c b/drivers/media/usb/dvb-usb-v2/lmedm04.c index 8a34e6c0d6a6..f0537b741d13 100644 --- a/drivers/media/usb/dvb-usb-v2/lmedm04.c +++ b/drivers/media/usb/dvb-usb-v2/lmedm04.c @@ -373,6 +373,7 @@ static int lme2510_int_read(struct dvb_usb_adapter *adap) struct dvb_usb_device *d = adap_to_d(adap); struct lme2510_state *lme_int = adap_to_priv(adap); struct usb_host_endpoint *ep; + int ret; lme_int->lme_urb = usb_alloc_urb(0, GFP_KERNEL); @@ -390,11 +391,20 @@ static int lme2510_int_read(struct dvb_usb_adapter *adap) /* Quirk of pipe reporting PIPE_BULK but behaves as interrupt */ ep = usb_pipe_endpoint(d->udev, lme_int->lme_urb->pipe); + if (!ep) { + usb_free_urb(lme_int->lme_urb); + return -ENODEV; + } if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK) lme_int->lme_urb->pipe = usb_rcvbulkpipe(d->udev, 0xa); - usb_submit_urb(lme_int->lme_urb, GFP_KERNEL); + ret = usb_submit_urb(lme_int->lme_urb, GFP_KERNEL); + if (ret) { + usb_free_urb(lme_int->lme_urb); + return ret; + } + info("INT Interrupt Service Started"); return 0; diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index 4fe26e82e3d1..4e58476d305e 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -1579,6 +1579,40 @@ static void uvc_ctrl_send_slave_event(struct uvc_video_chain *chain, uvc_ctrl_send_event(chain, handle, ctrl, mapping, val, changes); } +static void uvc_ctrl_set_handle(struct uvc_fh *handle, struct uvc_control *ctrl, + struct uvc_fh *new_handle) +{ + lockdep_assert_held(&handle->chain->ctrl_mutex); + + if (new_handle) { + if (ctrl->handle) + dev_warn_ratelimited(&handle->stream->dev->udev->dev, + "UVC non compliance: Setting an async control with a pending operation."); + + if (new_handle == ctrl->handle) + return; + + if (ctrl->handle) { + WARN_ON(!ctrl->handle->pending_async_ctrls); + if (ctrl->handle->pending_async_ctrls) + ctrl->handle->pending_async_ctrls--; + } + + ctrl->handle = new_handle; + handle->pending_async_ctrls++; + return; + } + + /* Cannot clear the handle for a control not owned by us.*/ + if (WARN_ON(ctrl->handle != handle)) + return; + + ctrl->handle = NULL; + if (WARN_ON(!handle->pending_async_ctrls)) + return; + handle->pending_async_ctrls--; +} + void uvc_ctrl_status_event(struct uvc_video_chain *chain, struct uvc_control *ctrl, const u8 *data) { @@ -1588,8 +1622,12 @@ void uvc_ctrl_status_event(struct uvc_video_chain *chain, mutex_lock(&chain->ctrl_mutex); + /* Flush the control cache, the data might have changed. */ + ctrl->loaded = 0; + handle = ctrl->handle; - ctrl->handle = NULL; + if (handle) + uvc_ctrl_set_handle(handle, ctrl, NULL); list_for_each_entry(mapping, &ctrl->info.mappings, list) { s32 value = __uvc_ctrl_get_value(mapping, data); @@ -1640,10 +1678,8 @@ bool uvc_ctrl_status_event_async(struct urb *urb, struct uvc_video_chain *chain, struct uvc_device *dev = chain->dev; struct uvc_ctrl_work *w = &dev->async_ctrl; - if (list_empty(&ctrl->info.mappings)) { - ctrl->handle = NULL; + if (list_empty(&ctrl->info.mappings)) return false; - } w->data = data; w->urb = urb; @@ -1673,13 +1709,13 @@ static void uvc_ctrl_send_events(struct uvc_fh *handle, { struct uvc_control_mapping *mapping; struct uvc_control *ctrl; - u32 changes = V4L2_EVENT_CTRL_CH_VALUE; unsigned int i; unsigned int j; for (i = 0; i < xctrls_count; ++i) { - ctrl = uvc_find_control(handle->chain, xctrls[i].id, &mapping); + u32 changes = V4L2_EVENT_CTRL_CH_VALUE; + ctrl = uvc_find_control(handle->chain, xctrls[i].id, &mapping); if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS) /* Notification will be sent from an Interrupt event. */ continue; @@ -1811,7 +1847,10 @@ int uvc_ctrl_begin(struct uvc_video_chain *chain) } static int uvc_ctrl_commit_entity(struct uvc_device *dev, - struct uvc_entity *entity, int rollback, struct uvc_control **err_ctrl) + struct uvc_fh *handle, + struct uvc_entity *entity, + int rollback, + struct uvc_control **err_ctrl) { struct uvc_control *ctrl; unsigned int i; @@ -1859,6 +1898,10 @@ static int uvc_ctrl_commit_entity(struct uvc_device *dev, *err_ctrl = ctrl; return ret; } + + if (!rollback && handle && + ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS) + uvc_ctrl_set_handle(handle, ctrl, handle); } return 0; @@ -1895,8 +1938,8 @@ int __uvc_ctrl_commit(struct uvc_fh *handle, int rollback, /* Find the control. */ list_for_each_entry(entity, &chain->entities, chain) { - ret = uvc_ctrl_commit_entity(chain->dev, entity, rollback, - &err_ctrl); + ret = uvc_ctrl_commit_entity(chain->dev, handle, entity, + rollback, &err_ctrl); if (ret < 0) { if (ctrls) ctrls->error_idx = @@ -1941,6 +1984,8 @@ int uvc_ctrl_set(struct uvc_fh *handle, s32 max; int ret; + lockdep_assert_held(&chain->ctrl_mutex); + if (__uvc_query_v4l2_class(chain, xctrl->id, 0) >= 0) return -EACCES; @@ -2046,9 +2091,6 @@ int uvc_ctrl_set(struct uvc_fh *handle, mapping->set(mapping, value, uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT)); - if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS) - ctrl->handle = handle; - ctrl->dirty = 1; ctrl->modified = 1; return 0; @@ -2377,7 +2419,7 @@ int uvc_ctrl_restore_values(struct uvc_device *dev) ctrl->dirty = 1; } - ret = uvc_ctrl_commit_entity(dev, entity, 0, NULL); + ret = uvc_ctrl_commit_entity(dev, NULL, entity, 0, NULL); if (ret < 0) return ret; } @@ -2770,6 +2812,26 @@ int uvc_ctrl_init_device(struct uvc_device *dev) return 0; } +void uvc_ctrl_cleanup_fh(struct uvc_fh *handle) +{ + struct uvc_entity *entity; + + guard(mutex)(&handle->chain->ctrl_mutex); + + if (!handle->pending_async_ctrls) + return; + + list_for_each_entry(entity, &handle->chain->dev->entities, list) { + for (unsigned int i = 0; i < entity->ncontrols; ++i) { + if (entity->controls[i].handle != handle) + continue; + uvc_ctrl_set_handle(handle, &entity->controls[i], NULL); + } + } + + WARN_ON(handle->pending_async_ctrls); +} + /* * Cleanup device controls. */ diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index b3c8411dc05c..deadbcea5e22 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -32,7 +32,7 @@ unsigned int uvc_clock_param = CLOCK_MONOTONIC; unsigned int uvc_hw_timestamps_param; -unsigned int uvc_no_drop_param; +unsigned int uvc_no_drop_param = 1; static unsigned int uvc_quirks_param = -1; unsigned int uvc_dbg_param; unsigned int uvc_timeout_param = UVC_CTRL_STREAMING_TIMEOUT; @@ -220,20 +220,127 @@ static struct uvc_streaming *uvc_stream_new(struct uvc_device *dev, * Descriptors parsing */ +static int uvc_parse_frame(struct uvc_device *dev, + struct uvc_streaming *streaming, + struct uvc_format *format, struct uvc_frame *frame, + u32 **intervals, u8 ftype, int width_multiplier, + const unsigned char *buffer, int buflen) +{ + struct usb_host_interface *alts = streaming->intf->cur_altsetting; + unsigned int maxIntervalIndex; + unsigned int interval; + unsigned int i, n; + + if (ftype != UVC_VS_FRAME_FRAME_BASED) + n = buflen > 25 ? buffer[25] : 0; + else + n = buflen > 21 ? buffer[21] : 0; + + n = n ? n : 3; + + if (buflen < 26 + 4 * n) { + uvc_dbg(dev, DESCR, + "device %d videostreaming interface %d FRAME error\n", + dev->udev->devnum, alts->desc.bInterfaceNumber); + return -EINVAL; + } + + frame->bFrameIndex = buffer[3]; + frame->bmCapabilities = buffer[4]; + frame->wWidth = get_unaligned_le16(&buffer[5]) * width_multiplier; + frame->wHeight = get_unaligned_le16(&buffer[7]); + frame->dwMinBitRate = get_unaligned_le32(&buffer[9]); + frame->dwMaxBitRate = get_unaligned_le32(&buffer[13]); + if (ftype != UVC_VS_FRAME_FRAME_BASED) { + frame->dwMaxVideoFrameBufferSize = + get_unaligned_le32(&buffer[17]); + frame->dwDefaultFrameInterval = + get_unaligned_le32(&buffer[21]); + frame->bFrameIntervalType = buffer[25]; + } else { + frame->dwMaxVideoFrameBufferSize = 0; + frame->dwDefaultFrameInterval = + get_unaligned_le32(&buffer[17]); + frame->bFrameIntervalType = buffer[21]; + } + + /* + * Copy the frame intervals. + * + * Some bogus devices report dwMinFrameInterval equal to + * dwMaxFrameInterval and have dwFrameIntervalStep set to zero. Setting + * all null intervals to 1 fixes the problem and some other divisions + * by zero that could happen. + */ + frame->dwFrameInterval = *intervals; + + for (i = 0; i < n; ++i) { + interval = get_unaligned_le32(&buffer[26 + 4 * i]); + (*intervals)[i] = interval ? interval : 1; + } + + /* + * Apply more fixes, quirks and workarounds to handle incorrect or + * broken descriptors. + */ + + /* + * Several UVC chipsets screw up dwMaxVideoFrameBufferSize completely. + * Observed behaviours range from setting the value to 1.1x the actual + * frame size to hardwiring the 16 low bits to 0. This results in a + * higher than necessary memory usage as well as a wrong image size + * information. For uncompressed formats this can be fixed by computing + * the value from the frame size. + */ + if (!(format->flags & UVC_FMT_FLAG_COMPRESSED)) + frame->dwMaxVideoFrameBufferSize = format->bpp * frame->wWidth + * frame->wHeight / 8; + + /* + * Clamp the default frame interval to the boundaries. A zero + * bFrameIntervalType value indicates a continuous frame interval + * range, with dwFrameInterval[0] storing the minimum value and + * dwFrameInterval[1] storing the maximum value. + */ + maxIntervalIndex = frame->bFrameIntervalType ? n - 1 : 1; + frame->dwDefaultFrameInterval = + clamp(frame->dwDefaultFrameInterval, + frame->dwFrameInterval[0], + frame->dwFrameInterval[maxIntervalIndex]); + + /* + * Some devices report frame intervals that are not functional. If the + * corresponding quirk is set, restrict operation to the first interval + * only. + */ + if (dev->quirks & UVC_QUIRK_RESTRICT_FRAME_RATE) { + frame->bFrameIntervalType = 1; + (*intervals)[0] = frame->dwDefaultFrameInterval; + } + + uvc_dbg(dev, DESCR, "- %ux%u (%u.%u fps)\n", + frame->wWidth, frame->wHeight, + 10000000 / frame->dwDefaultFrameInterval, + (100000000 / frame->dwDefaultFrameInterval) % 10); + + *intervals += n; + + return buffer[0]; +} + static int uvc_parse_format(struct uvc_device *dev, struct uvc_streaming *streaming, struct uvc_format *format, struct uvc_frame *frames, u32 **intervals, const unsigned char *buffer, int buflen) { - struct usb_interface *intf = streaming->intf; - struct usb_host_interface *alts = intf->cur_altsetting; + struct usb_host_interface *alts = streaming->intf->cur_altsetting; const struct uvc_format_desc *fmtdesc; struct uvc_frame *frame; const unsigned char *start = buffer; unsigned int width_multiplier = 1; - unsigned int interval; unsigned int i, n; u8 ftype; + int ret; format->type = buffer[2]; format->index = buffer[3]; @@ -371,111 +478,19 @@ static int uvc_parse_format(struct uvc_device *dev, * Parse the frame descriptors. Only uncompressed, MJPEG and frame * based formats have frame descriptors. */ - while (ftype && buflen > 2 && buffer[1] == USB_DT_CS_INTERFACE && - buffer[2] == ftype) { - unsigned int maxIntervalIndex; - - frame = &frames[format->nframes]; - if (ftype != UVC_VS_FRAME_FRAME_BASED) - n = buflen > 25 ? buffer[25] : 0; - else - n = buflen > 21 ? buffer[21] : 0; - - n = n ? n : 3; - - if (buflen < 26 + 4*n) { - uvc_dbg(dev, DESCR, - "device %d videostreaming interface %d FRAME error\n", - dev->udev->devnum, - alts->desc.bInterfaceNumber); - return -EINVAL; + if (ftype) { + while (buflen > 2 && buffer[1] == USB_DT_CS_INTERFACE && + buffer[2] == ftype) { + frame = &frames[format->nframes]; + ret = uvc_parse_frame(dev, streaming, format, frame, + intervals, ftype, width_multiplier, + buffer, buflen); + if (ret < 0) + return ret; + format->nframes++; + buflen -= ret; + buffer += ret; } - - frame->bFrameIndex = buffer[3]; - frame->bmCapabilities = buffer[4]; - frame->wWidth = get_unaligned_le16(&buffer[5]) - * width_multiplier; - frame->wHeight = get_unaligned_le16(&buffer[7]); - frame->dwMinBitRate = get_unaligned_le32(&buffer[9]); - frame->dwMaxBitRate = get_unaligned_le32(&buffer[13]); - if (ftype != UVC_VS_FRAME_FRAME_BASED) { - frame->dwMaxVideoFrameBufferSize = - get_unaligned_le32(&buffer[17]); - frame->dwDefaultFrameInterval = - get_unaligned_le32(&buffer[21]); - frame->bFrameIntervalType = buffer[25]; - } else { - frame->dwMaxVideoFrameBufferSize = 0; - frame->dwDefaultFrameInterval = - get_unaligned_le32(&buffer[17]); - frame->bFrameIntervalType = buffer[21]; - } - - /* - * Copy the frame intervals. - * - * Some bogus devices report dwMinFrameInterval equal to - * dwMaxFrameInterval and have dwFrameIntervalStep set to - * zero. Setting all null intervals to 1 fixes the problem and - * some other divisions by zero that could happen. - */ - frame->dwFrameInterval = *intervals; - - for (i = 0; i < n; ++i) { - interval = get_unaligned_le32(&buffer[26+4*i]); - (*intervals)[i] = interval ? interval : 1; - } - - /* - * Apply more fixes, quirks and workarounds to handle incorrect - * or broken descriptors. - */ - - /* - * Several UVC chipsets screw up dwMaxVideoFrameBufferSize - * completely. Observed behaviours range from setting the - * value to 1.1x the actual frame size to hardwiring the - * 16 low bits to 0. This results in a higher than necessary - * memory usage as well as a wrong image size information. For - * uncompressed formats this can be fixed by computing the - * value from the frame size. - */ - if (!(format->flags & UVC_FMT_FLAG_COMPRESSED)) - frame->dwMaxVideoFrameBufferSize = format->bpp - * frame->wWidth * frame->wHeight / 8; - - /* - * Clamp the default frame interval to the boundaries. A zero - * bFrameIntervalType value indicates a continuous frame - * interval range, with dwFrameInterval[0] storing the minimum - * value and dwFrameInterval[1] storing the maximum value. - */ - maxIntervalIndex = frame->bFrameIntervalType ? n - 1 : 1; - frame->dwDefaultFrameInterval = - clamp(frame->dwDefaultFrameInterval, - frame->dwFrameInterval[0], - frame->dwFrameInterval[maxIntervalIndex]); - - /* - * Some devices report frame intervals that are not functional. - * If the corresponding quirk is set, restrict operation to the - * first interval only. - */ - if (dev->quirks & UVC_QUIRK_RESTRICT_FRAME_RATE) { - frame->bFrameIntervalType = 1; - (*intervals)[0] = frame->dwDefaultFrameInterval; - } - - uvc_dbg(dev, DESCR, "- %ux%u (%u.%u fps)\n", - frame->wWidth, frame->wHeight, - 10000000 / frame->dwDefaultFrameInterval, - (100000000 / frame->dwDefaultFrameInterval) % 10); - - format->nframes++; - *intervals += n; - - buflen -= buffer[0]; - buffer += buffer[0]; } if (buflen > 2 && buffer[1] == USB_DT_CS_INTERFACE && @@ -775,27 +790,14 @@ static const u8 uvc_media_transport_input_guid[16] = UVC_GUID_UVC_MEDIA_TRANSPORT_INPUT; static const u8 uvc_processing_guid[16] = UVC_GUID_UVC_PROCESSING; -static struct uvc_entity *uvc_alloc_new_entity(struct uvc_device *dev, u16 type, - u16 id, unsigned int num_pads, - unsigned int extra_size) +static struct uvc_entity *uvc_alloc_entity(u16 type, u16 id, + unsigned int num_pads, unsigned int extra_size) { struct uvc_entity *entity; unsigned int num_inputs; unsigned int size; unsigned int i; - /* Per UVC 1.1+ spec 3.7.2, the ID should be non-zero. */ - if (id == 0) { - dev_err(&dev->udev->dev, "Found Unit with invalid ID 0.\n"); - return ERR_PTR(-EINVAL); - } - - /* Per UVC 1.1+ spec 3.7.2, the ID is unique. */ - if (uvc_entity_by_id(dev, id)) { - dev_err(&dev->udev->dev, "Found multiple Units with ID %u\n", id); - return ERR_PTR(-EINVAL); - } - extra_size = roundup(extra_size, sizeof(*entity->pads)); if (num_pads) num_inputs = type & UVC_TERM_OUTPUT ? num_pads : num_pads - 1; @@ -805,7 +807,7 @@ static struct uvc_entity *uvc_alloc_new_entity(struct uvc_device *dev, u16 type, + num_inputs; entity = kzalloc(size, GFP_KERNEL); if (entity == NULL) - return ERR_PTR(-ENOMEM); + return NULL; entity->id = id; entity->type = type; @@ -917,10 +919,10 @@ static int uvc_parse_vendor_control(struct uvc_device *dev, break; } - unit = uvc_alloc_new_entity(dev, UVC_VC_EXTENSION_UNIT, - buffer[3], p + 1, 2 * n); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(UVC_VC_EXTENSION_UNIT, buffer[3], + p + 1, 2*n); + if (unit == NULL) + return -ENOMEM; memcpy(unit->guid, &buffer[4], 16); unit->extension.bNumControls = buffer[20]; @@ -1029,10 +1031,10 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return -EINVAL; } - term = uvc_alloc_new_entity(dev, type | UVC_TERM_INPUT, - buffer[3], 1, n + p); - if (IS_ERR(term)) - return PTR_ERR(term); + term = uvc_alloc_entity(type | UVC_TERM_INPUT, buffer[3], + 1, n + p); + if (term == NULL) + return -ENOMEM; if (UVC_ENTITY_TYPE(term) == UVC_ITT_CAMERA) { term->camera.bControlSize = n; @@ -1088,10 +1090,10 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return 0; } - term = uvc_alloc_new_entity(dev, type | UVC_TERM_OUTPUT, - buffer[3], 1, 0); - if (IS_ERR(term)) - return PTR_ERR(term); + term = uvc_alloc_entity(type | UVC_TERM_OUTPUT, buffer[3], + 1, 0); + if (term == NULL) + return -ENOMEM; memcpy(term->baSourceID, &buffer[7], 1); @@ -1110,10 +1112,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return -EINVAL; } - unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3], - p + 1, 0); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(buffer[2], buffer[3], p + 1, 0); + if (unit == NULL) + return -ENOMEM; memcpy(unit->baSourceID, &buffer[5], p); @@ -1133,9 +1134,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return -EINVAL; } - unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3], 2, n); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(buffer[2], buffer[3], 2, n); + if (unit == NULL) + return -ENOMEM; memcpy(unit->baSourceID, &buffer[4], 1); unit->processing.wMaxMultiplier = @@ -1162,10 +1163,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return -EINVAL; } - unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3], - p + 1, n); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(buffer[2], buffer[3], p + 1, n); + if (unit == NULL) + return -ENOMEM; memcpy(unit->guid, &buffer[4], 16); unit->extension.bNumControls = buffer[20]; @@ -1295,20 +1295,19 @@ static int uvc_gpio_parse(struct uvc_device *dev) struct gpio_desc *gpio_privacy; int irq; - gpio_privacy = devm_gpiod_get_optional(&dev->udev->dev, "privacy", + gpio_privacy = devm_gpiod_get_optional(&dev->intf->dev, "privacy", GPIOD_IN); if (IS_ERR_OR_NULL(gpio_privacy)) return PTR_ERR_OR_ZERO(gpio_privacy); irq = gpiod_to_irq(gpio_privacy); if (irq < 0) - return dev_err_probe(&dev->udev->dev, irq, + return dev_err_probe(&dev->intf->dev, irq, "No IRQ for privacy GPIO\n"); - unit = uvc_alloc_new_entity(dev, UVC_EXT_GPIO_UNIT, - UVC_EXT_GPIO_UNIT_ID, 0, 1); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(UVC_EXT_GPIO_UNIT, UVC_EXT_GPIO_UNIT_ID, 0, 1); + if (!unit) + return -ENOMEM; unit->gpio.gpio_privacy = gpio_privacy; unit->gpio.irq = irq; @@ -1329,15 +1328,27 @@ static int uvc_gpio_parse(struct uvc_device *dev) static int uvc_gpio_init_irq(struct uvc_device *dev) { struct uvc_entity *unit = dev->gpio_unit; + int ret; if (!unit || unit->gpio.irq < 0) return 0; - return devm_request_threaded_irq(&dev->udev->dev, unit->gpio.irq, NULL, - uvc_gpio_irq, - IRQF_ONESHOT | IRQF_TRIGGER_FALLING | - IRQF_TRIGGER_RISING, - "uvc_privacy_gpio", dev); + ret = request_threaded_irq(unit->gpio.irq, NULL, uvc_gpio_irq, + IRQF_ONESHOT | IRQF_TRIGGER_FALLING | + IRQF_TRIGGER_RISING, + "uvc_privacy_gpio", dev); + + unit->gpio.initialized = !ret; + + return ret; +} + +static void uvc_gpio_deinit(struct uvc_device *dev) +{ + if (!dev->gpio_unit || !dev->gpio_unit->gpio.initialized) + return; + + free_irq(dev->gpio_unit->gpio.irq, dev); } /* ------------------------------------------------------------------------ @@ -1934,6 +1945,8 @@ static void uvc_unregister_video(struct uvc_device *dev) { struct uvc_streaming *stream; + uvc_gpio_deinit(dev); + list_for_each_entry(stream, &dev->streams, list) { /* Nothing to do here, continue. */ if (!video_is_registered(&stream->vdev)) @@ -1995,7 +2008,7 @@ int uvc_register_video_device(struct uvc_device *dev, int ret; /* Initialize the video buffers queue. */ - ret = uvc_queue_init(queue, type, !uvc_no_drop_param); + ret = uvc_queue_init(queue, type); if (ret) return ret; @@ -2424,8 +2437,25 @@ module_param_call(clock, uvc_clock_param_set, uvc_clock_param_get, MODULE_PARM_DESC(clock, "Video buffers timestamp clock"); module_param_named(hwtimestamps, uvc_hw_timestamps_param, uint, 0644); MODULE_PARM_DESC(hwtimestamps, "Use hardware timestamps"); -module_param_named(nodrop, uvc_no_drop_param, uint, 0644); + +static int param_set_nodrop(const char *val, const struct kernel_param *kp) +{ + pr_warn_once("uvcvideo: " + DEPRECATED + "nodrop parameter will be eventually removed.\n"); + return param_set_bool(val, kp); +} + +static const struct kernel_param_ops param_ops_nodrop = { + .set = param_set_nodrop, + .get = param_get_uint, +}; + +param_check_uint(nodrop, &uvc_no_drop_param); +module_param_cb(nodrop, ¶m_ops_nodrop, &uvc_no_drop_param, 0644); +__MODULE_PARM_TYPE(nodrop, "uint"); MODULE_PARM_DESC(nodrop, "Don't drop incomplete frames"); + module_param_named(quirks, uvc_quirks_param, uint, 0644); MODULE_PARM_DESC(quirks, "Forced device quirks"); module_param_named(trace, uvc_dbg_param, uint, 0644); @@ -2802,6 +2832,15 @@ static const struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = (kernel_ulong_t)&uvc_quirk_probe_minmax }, + /* Sonix Technology Co. Ltd. - 292A IPC AR0330 */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x0c45, + .idProduct = 0x6366, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_MJPEG_NO_EOF) }, /* MT6227 */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, @@ -2830,6 +2869,15 @@ static const struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = (kernel_ulong_t)&uvc_quirk_probe_minmax }, + /* Kurokesu C1 PRO */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x16d0, + .idProduct = 0x0ed1, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_MJPEG_NO_EOF) }, /* Syntek (HP Spartan) */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, diff --git a/drivers/media/usb/uvc/uvc_queue.c b/drivers/media/usb/uvc/uvc_queue.c index 26ee85657fc8..2ee142621042 100644 --- a/drivers/media/usb/uvc/uvc_queue.c +++ b/drivers/media/usb/uvc/uvc_queue.c @@ -208,8 +208,7 @@ static const struct vb2_ops uvc_meta_queue_qops = { .stop_streaming = uvc_stop_streaming, }; -int uvc_queue_init(struct uvc_video_queue *queue, enum v4l2_buf_type type, - int drop_corrupted) +int uvc_queue_init(struct uvc_video_queue *queue, enum v4l2_buf_type type) { int ret; @@ -239,7 +238,6 @@ int uvc_queue_init(struct uvc_video_queue *queue, enum v4l2_buf_type type, mutex_init(&queue->mutex); spin_lock_init(&queue->irqlock); INIT_LIST_HEAD(&queue->irqqueue); - queue->flags = drop_corrupted ? UVC_QUEUE_DROP_CORRUPTED : 0; return 0; } @@ -472,14 +470,15 @@ static void uvc_queue_buffer_complete(struct kref *ref) struct vb2_buffer *vb = &buf->buf.vb2_buf; struct uvc_video_queue *queue = vb2_get_drv_priv(vb->vb2_queue); - if ((queue->flags & UVC_QUEUE_DROP_CORRUPTED) && buf->error) { + if (buf->error && !uvc_no_drop_param) { uvc_queue_buffer_requeue(queue, buf); return; } buf->state = buf->error ? UVC_BUF_STATE_ERROR : UVC_BUF_STATE_DONE; vb2_set_plane_payload(&buf->buf.vb2_buf, 0, buf->bytesused); - vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_DONE); + vb2_buffer_done(&buf->buf.vb2_buf, buf->error ? VB2_BUF_STATE_ERROR : + VB2_BUF_STATE_DONE); } /* diff --git a/drivers/media/usb/uvc/uvc_status.c b/drivers/media/usb/uvc/uvc_status.c index 06c867510c8f..ee01dce4b783 100644 --- a/drivers/media/usb/uvc/uvc_status.c +++ b/drivers/media/usb/uvc/uvc_status.c @@ -262,8 +262,6 @@ int uvc_status_init(struct uvc_device *dev) if (ep == NULL) return 0; - uvc_input_init(dev); - dev->status = kzalloc(sizeof(*dev->status), GFP_KERNEL); if (!dev->status) return -ENOMEM; @@ -271,6 +269,7 @@ int uvc_status_init(struct uvc_device *dev) dev->int_urb = usb_alloc_urb(0, GFP_KERNEL); if (!dev->int_urb) { kfree(dev->status); + dev->status = NULL; return -ENOMEM; } @@ -289,11 +288,16 @@ int uvc_status_init(struct uvc_device *dev) dev->status, sizeof(*dev->status), uvc_status_complete, dev, interval); + uvc_input_init(dev); + return 0; } void uvc_status_unregister(struct uvc_device *dev) { + if (!dev->status) + return; + uvc_status_suspend(dev); uvc_input_unregister(dev); } diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c index 97c5407f6603..93c6cdb23881 100644 --- a/drivers/media/usb/uvc/uvc_v4l2.c +++ b/drivers/media/usb/uvc/uvc_v4l2.c @@ -26,6 +26,8 @@ #include "uvcvideo.h" +static int uvc_acquire_privileges(struct uvc_fh *handle); + static int uvc_control_add_xu_mapping(struct uvc_video_chain *chain, struct uvc_control_mapping *map, const struct uvc_xu_control_mapping *xmap) @@ -361,9 +363,11 @@ static int uvc_v4l2_try_format(struct uvc_streaming *stream, return ret; } -static int uvc_v4l2_get_format(struct uvc_streaming *stream, - struct v4l2_format *fmt) +static int uvc_ioctl_g_fmt(struct file *file, void *fh, + struct v4l2_format *fmt) { + struct uvc_fh *handle = fh; + struct uvc_streaming *stream = handle->stream; const struct uvc_format *format; const struct uvc_frame *frame; int ret = 0; @@ -395,14 +399,20 @@ done: return ret; } -static int uvc_v4l2_set_format(struct uvc_streaming *stream, - struct v4l2_format *fmt) +static int uvc_ioctl_s_fmt(struct file *file, void *fh, + struct v4l2_format *fmt) { + struct uvc_fh *handle = fh; + struct uvc_streaming *stream = handle->stream; struct uvc_streaming_control probe; const struct uvc_format *format; const struct uvc_frame *frame; int ret; + ret = uvc_acquire_privileges(handle); + if (ret < 0) + return ret; + if (fmt->type != stream->type) return -EINVAL; @@ -426,10 +436,12 @@ done: return ret; } -static int uvc_v4l2_get_streamparm(struct uvc_streaming *stream, - struct v4l2_streamparm *parm) +static int uvc_ioctl_g_parm(struct file *file, void *fh, + struct v4l2_streamparm *parm) { u32 numerator, denominator; + struct uvc_fh *handle = fh; + struct uvc_streaming *stream = handle->stream; if (parm->type != stream->type) return -EINVAL; @@ -461,9 +473,11 @@ static int uvc_v4l2_get_streamparm(struct uvc_streaming *stream, return 0; } -static int uvc_v4l2_set_streamparm(struct uvc_streaming *stream, - struct v4l2_streamparm *parm) +static int uvc_ioctl_s_parm(struct file *file, void *fh, + struct v4l2_streamparm *parm) { + struct uvc_fh *handle = fh; + struct uvc_streaming *stream = handle->stream; struct uvc_streaming_control probe; struct v4l2_fract timeperframe; const struct uvc_format *format; @@ -472,6 +486,10 @@ static int uvc_v4l2_set_streamparm(struct uvc_streaming *stream, unsigned int i; int ret; + ret = uvc_acquire_privileges(handle); + if (ret < 0) + return ret; + if (parm->type != stream->type) return -EINVAL; @@ -573,6 +591,7 @@ static int uvc_v4l2_set_streamparm(struct uvc_streaming *stream, * - VIDIOC_S_INPUT * - VIDIOC_S_PARM * - VIDIOC_S_FMT + * - VIDIOC_CREATE_BUFS * - VIDIOC_REQBUFS */ static int uvc_acquire_privileges(struct uvc_fh *handle) @@ -652,6 +671,8 @@ static int uvc_v4l2_release(struct file *file) uvc_dbg(stream->dev, CALLS, "%s\n", __func__); + uvc_ctrl_cleanup_fh(handle); + /* Only free resources if this is a privileged handle. */ if (uvc_has_privileges(handle)) uvc_queue_release(&stream->queue); @@ -685,11 +706,13 @@ static int uvc_ioctl_querycap(struct file *file, void *fh, return 0; } -static int uvc_ioctl_enum_fmt(struct uvc_streaming *stream, +static int uvc_ioctl_enum_fmt(struct file *file, void *fh, struct v4l2_fmtdesc *fmt) { - const struct uvc_format *format; + struct uvc_fh *handle = fh; + struct uvc_streaming *stream = handle->stream; enum v4l2_buf_type type = fmt->type; + const struct uvc_format *format; u32 index = fmt->index; if (fmt->type != stream->type || fmt->index >= stream->nformats) @@ -707,82 +730,8 @@ static int uvc_ioctl_enum_fmt(struct uvc_streaming *stream, return 0; } -static int uvc_ioctl_enum_fmt_vid_cap(struct file *file, void *fh, - struct v4l2_fmtdesc *fmt) -{ - struct uvc_fh *handle = fh; - struct uvc_streaming *stream = handle->stream; - - return uvc_ioctl_enum_fmt(stream, fmt); -} - -static int uvc_ioctl_enum_fmt_vid_out(struct file *file, void *fh, - struct v4l2_fmtdesc *fmt) -{ - struct uvc_fh *handle = fh; - struct uvc_streaming *stream = handle->stream; - - return uvc_ioctl_enum_fmt(stream, fmt); -} - -static int uvc_ioctl_g_fmt_vid_cap(struct file *file, void *fh, - struct v4l2_format *fmt) -{ - struct uvc_fh *handle = fh; - struct uvc_streaming *stream = handle->stream; - - return uvc_v4l2_get_format(stream, fmt); -} - -static int uvc_ioctl_g_fmt_vid_out(struct file *file, void *fh, - struct v4l2_format *fmt) -{ - struct uvc_fh *handle = fh; - struct uvc_streaming *stream = handle->stream; - - return uvc_v4l2_get_format(stream, fmt); -} - -static int uvc_ioctl_s_fmt_vid_cap(struct file *file, void *fh, - struct v4l2_format *fmt) -{ - struct uvc_fh *handle = fh; - struct uvc_streaming *stream = handle->stream; - int ret; - - ret = uvc_acquire_privileges(handle); - if (ret < 0) - return ret; - - return uvc_v4l2_set_format(stream, fmt); -} - -static int uvc_ioctl_s_fmt_vid_out(struct file *file, void *fh, - struct v4l2_format *fmt) -{ - struct uvc_fh *handle = fh; - struct uvc_streaming *stream = handle->stream; - int ret; - - ret = uvc_acquire_privileges(handle); - if (ret < 0) - return ret; - - return uvc_v4l2_set_format(stream, fmt); -} - -static int uvc_ioctl_try_fmt_vid_cap(struct file *file, void *fh, - struct v4l2_format *fmt) -{ - struct uvc_fh *handle = fh; - struct uvc_streaming *stream = handle->stream; - struct uvc_streaming_control probe; - - return uvc_v4l2_try_format(stream, fmt, &probe, NULL, NULL); -} - -static int uvc_ioctl_try_fmt_vid_out(struct file *file, void *fh, - struct v4l2_format *fmt) +static int uvc_ioctl_try_fmt(struct file *file, void *fh, + struct v4l2_format *fmt) { struct uvc_fh *handle = fh; struct uvc_streaming *stream = handle->stream; @@ -1212,29 +1161,6 @@ static int uvc_ioctl_g_selection(struct file *file, void *fh, return 0; } -static int uvc_ioctl_g_parm(struct file *file, void *fh, - struct v4l2_streamparm *parm) -{ - struct uvc_fh *handle = fh; - struct uvc_streaming *stream = handle->stream; - - return uvc_v4l2_get_streamparm(stream, parm); -} - -static int uvc_ioctl_s_parm(struct file *file, void *fh, - struct v4l2_streamparm *parm) -{ - struct uvc_fh *handle = fh; - struct uvc_streaming *stream = handle->stream; - int ret; - - ret = uvc_acquire_privileges(handle); - if (ret < 0) - return ret; - - return uvc_v4l2_set_streamparm(stream, parm); -} - static int uvc_ioctl_enum_framesizes(struct file *file, void *fh, struct v4l2_frmsizeenum *fsize) { @@ -1543,15 +1469,17 @@ static unsigned long uvc_v4l2_get_unmapped_area(struct file *file, #endif const struct v4l2_ioctl_ops uvc_ioctl_ops = { + .vidioc_g_fmt_vid_cap = uvc_ioctl_g_fmt, + .vidioc_g_fmt_vid_out = uvc_ioctl_g_fmt, + .vidioc_s_fmt_vid_cap = uvc_ioctl_s_fmt, + .vidioc_s_fmt_vid_out = uvc_ioctl_s_fmt, + .vidioc_g_parm = uvc_ioctl_g_parm, + .vidioc_s_parm = uvc_ioctl_s_parm, .vidioc_querycap = uvc_ioctl_querycap, - .vidioc_enum_fmt_vid_cap = uvc_ioctl_enum_fmt_vid_cap, - .vidioc_enum_fmt_vid_out = uvc_ioctl_enum_fmt_vid_out, - .vidioc_g_fmt_vid_cap = uvc_ioctl_g_fmt_vid_cap, - .vidioc_g_fmt_vid_out = uvc_ioctl_g_fmt_vid_out, - .vidioc_s_fmt_vid_cap = uvc_ioctl_s_fmt_vid_cap, - .vidioc_s_fmt_vid_out = uvc_ioctl_s_fmt_vid_out, - .vidioc_try_fmt_vid_cap = uvc_ioctl_try_fmt_vid_cap, - .vidioc_try_fmt_vid_out = uvc_ioctl_try_fmt_vid_out, + .vidioc_enum_fmt_vid_cap = uvc_ioctl_enum_fmt, + .vidioc_enum_fmt_vid_out = uvc_ioctl_enum_fmt, + .vidioc_try_fmt_vid_cap = uvc_ioctl_try_fmt, + .vidioc_try_fmt_vid_out = uvc_ioctl_try_fmt, .vidioc_reqbufs = uvc_ioctl_reqbufs, .vidioc_querybuf = uvc_ioctl_querybuf, .vidioc_qbuf = uvc_ioctl_qbuf, @@ -1570,8 +1498,6 @@ const struct v4l2_ioctl_ops uvc_ioctl_ops = { .vidioc_try_ext_ctrls = uvc_ioctl_try_ext_ctrls, .vidioc_querymenu = uvc_ioctl_querymenu, .vidioc_g_selection = uvc_ioctl_g_selection, - .vidioc_g_parm = uvc_ioctl_g_parm, - .vidioc_s_parm = uvc_ioctl_s_parm, .vidioc_enum_framesizes = uvc_ioctl_enum_framesizes, .vidioc_enum_frameintervals = uvc_ioctl_enum_frameintervals, .vidioc_subscribe_event = uvc_ioctl_subscribe_event, diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index e00f38dd07d9..e3567aeb0007 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -20,6 +20,7 @@ #include #include +#include #include #include "uvcvideo.h" @@ -79,6 +80,27 @@ int uvc_query_ctrl(struct uvc_device *dev, u8 query, u8 unit, if (likely(ret == size)) return 0; + /* + * Some devices return shorter USB control packets than expected if the + * returned value can fit in less bytes. Zero all the bytes that the + * device has not written. + * + * This quirk is applied to all controls, regardless of their data type. + * Most controls are little-endian integers, in which case the missing + * bytes become 0 MSBs. For other data types, a different heuristic + * could be implemented if a device is found needing it. + * + * We exclude UVC_GET_INFO from the quirk. UVC_GET_LEN does not need + * to be excluded because its size is always 1. + */ + if (ret > 0 && query != UVC_GET_INFO) { + memset(data + ret, 0, size - ret); + dev_warn_once(&dev->udev->dev, + "UVC non compliance: %s control %u on unit %u returned %d bytes when we expected %u.\n", + uvc_query_name(query), cs, unit, ret, size); + return 0; + } + if (ret != -EPIPE) { dev_err(&dev->udev->dev, "Failed to query (%s) UVC control %u on unit %u: %d (exp. %u).\n", @@ -96,8 +118,12 @@ int uvc_query_ctrl(struct uvc_device *dev, u8 query, u8 unit, error = *(u8 *)data; *(u8 *)data = tmp; - if (ret != 1) + if (ret != 1) { + dev_err_ratelimited(&dev->udev->dev, + "Failed to query (%s) UVC error code control %u on unit %u: %d (exp. 1).\n", + uvc_query_name(query), cs, unit, ret); return ret < 0 ? ret : -EPIPE; + } uvc_dbg(dev, CONTROL, "Control error %u\n", error); @@ -297,8 +323,9 @@ static int uvc_get_video_ctrl(struct uvc_streaming *stream, goto out; } else if (ret != size) { dev_err(&stream->intf->dev, - "Failed to query (%u) UVC %s control : %d (exp. %u).\n", - query, probe ? "probe" : "commit", ret, size); + "Failed to query (%s) UVC %s control : %d (exp. %u).\n", + uvc_query_name(query), probe ? "probe" : "commit", + ret, size); ret = (ret == -EPROTO) ? -EPROTO : -EIO; goto out; } @@ -1116,6 +1143,7 @@ static void uvc_video_stats_stop(struct uvc_streaming *stream) static int uvc_video_decode_start(struct uvc_streaming *stream, struct uvc_buffer *buf, const u8 *data, int len) { + u8 header_len; u8 fid; /* @@ -1129,6 +1157,7 @@ static int uvc_video_decode_start(struct uvc_streaming *stream, return -EINVAL; } + header_len = data[0]; fid = data[1] & UVC_STREAM_FID; /* @@ -1210,9 +1239,31 @@ static int uvc_video_decode_start(struct uvc_streaming *stream, return -EAGAIN; } + /* + * Some cameras, when running two parallel streams (one MJPEG alongside + * another non-MJPEG stream), are known to lose the EOF packet for a frame. + * We can detect the end of a frame by checking for a new SOI marker, as + * the SOI always lies on the packet boundary between two frames for + * these devices. + */ + if (stream->dev->quirks & UVC_QUIRK_MJPEG_NO_EOF && + (stream->cur_format->fcc == V4L2_PIX_FMT_MJPEG || + stream->cur_format->fcc == V4L2_PIX_FMT_JPEG)) { + const u8 *packet = data + header_len; + + if (len >= header_len + 2 && + packet[0] == 0xff && packet[1] == JPEG_MARKER_SOI && + buf->bytesused != 0) { + buf->state = UVC_BUF_STATE_READY; + buf->error = 1; + stream->last_fid ^= UVC_STREAM_FID; + return -EAGAIN; + } + } + stream->last_fid = fid; - return data[0]; + return header_len; } static inline enum dma_data_direction uvc_stream_dir( diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index 07f9921d83f2..5e388f05f3fc 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -76,6 +76,7 @@ #define UVC_QUIRK_NO_RESET_RESUME 0x00004000 #define UVC_QUIRK_DISABLE_AUTOSUSPEND 0x00008000 #define UVC_QUIRK_INVALID_DEVICE_SOF 0x00010000 +#define UVC_QUIRK_MJPEG_NO_EOF 0x00020000 /* Format flags */ #define UVC_FMT_FLAG_COMPRESSED 0x00000001 @@ -234,6 +235,7 @@ struct uvc_entity { u8 *bmControls; struct gpio_desc *gpio_privacy; int irq; + bool initialized; } gpio; }; @@ -316,7 +318,6 @@ struct uvc_buffer { }; #define UVC_QUEUE_DISCONNECTED (1 << 0) -#define UVC_QUEUE_DROP_CORRUPTED (1 << 1) struct uvc_video_queue { struct vb2_queue queue; @@ -337,7 +338,11 @@ struct uvc_video_chain { struct uvc_entity *processing; /* Processing unit */ struct uvc_entity *selector; /* Selector unit */ - struct mutex ctrl_mutex; /* Protects ctrl.info */ + struct mutex ctrl_mutex; /* + * Protects ctrl.info, + * ctrl.handle and + * uvc_fh.pending_async_ctrls + */ struct v4l2_prio_state prio; /* V4L2 priority state */ u32 caps; /* V4L2 chain-wide caps */ @@ -612,6 +617,7 @@ struct uvc_fh { struct uvc_video_chain *chain; struct uvc_streaming *stream; enum uvc_handle_state state; + unsigned int pending_async_ctrls; }; struct uvc_driver { @@ -674,8 +680,7 @@ extern struct uvc_driver uvc_driver; struct uvc_entity *uvc_entity_by_id(struct uvc_device *dev, int id); /* Video buffers queue management. */ -int uvc_queue_init(struct uvc_video_queue *queue, enum v4l2_buf_type type, - int drop_corrupted); +int uvc_queue_init(struct uvc_video_queue *queue, enum v4l2_buf_type type); void uvc_queue_release(struct uvc_video_queue *queue); int uvc_request_buffers(struct uvc_video_queue *queue, struct v4l2_requestbuffers *rb); @@ -797,6 +802,8 @@ int uvc_ctrl_is_accessible(struct uvc_video_chain *chain, u32 v4l2_id, int uvc_xu_ctrl_query(struct uvc_video_chain *chain, struct uvc_xu_control_query *xqry); +void uvc_ctrl_cleanup_fh(struct uvc_fh *handle); + /* Utility functions */ struct usb_host_endpoint *uvc_find_endpoint(struct usb_host_interface *alts, u8 epaddr); diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c index f19c8adf2c61..cb153ce42c45 100644 --- a/drivers/media/v4l2-core/v4l2-fwnode.c +++ b/drivers/media/v4l2-core/v4l2-fwnode.c @@ -127,7 +127,7 @@ static int v4l2_fwnode_endpoint_parse_csi2_bus(struct fwnode_handle *fwnode, { struct v4l2_mbus_config_mipi_csi2 *bus = &vep->bus.mipi_csi2; bool have_clk_lane = false, have_data_lanes = false, - have_lane_polarities = false; + have_lane_polarities = false, have_line_orders = false; unsigned int flags = 0, lanes_used = 0; u32 array[1 + V4L2_MBUS_CSI2_MAX_DATA_LANES]; u32 clock_lane = 0; @@ -197,6 +197,17 @@ static int v4l2_fwnode_endpoint_parse_csi2_bus(struct fwnode_handle *fwnode, have_lane_polarities = true; } + rval = fwnode_property_count_u32(fwnode, "line-orders"); + if (rval > 0) { + if (rval != num_data_lanes) { + pr_warn("invalid number of line-orders entries (need %u, got %u)\n", + num_data_lanes, rval); + return -EINVAL; + } + + have_line_orders = true; + } + if (!fwnode_property_read_u32(fwnode, "clock-lanes", &v)) { clock_lane = v; pr_debug("clock lane position %u\n", v); @@ -250,6 +261,36 @@ static int v4l2_fwnode_endpoint_parse_csi2_bus(struct fwnode_handle *fwnode, } else { pr_debug("no lane polarities defined, assuming not inverted\n"); } + + if (have_line_orders) { + fwnode_property_read_u32_array(fwnode, + "line-orders", array, + num_data_lanes); + + for (i = 0; i < num_data_lanes; i++) { + static const char * const orders[] = { + "ABC", "ACB", "BAC", "BCA", "CAB", "CBA" + }; + + if (array[i] >= ARRAY_SIZE(orders)) { + pr_warn("lane %u invalid line-order assuming ABC (got %u)\n", + i, array[i]); + bus->line_orders[i] = + V4L2_MBUS_CSI2_CPHY_LINE_ORDER_ABC; + continue; + } + + bus->line_orders[i] = array[i]; + pr_debug("lane %u line order %s", i, + orders[array[i]]); + } + } else { + for (i = 0; i < num_data_lanes; i++) + bus->line_orders[i] = + V4L2_MBUS_CSI2_CPHY_LINE_ORDER_ABC; + + pr_debug("no line orders defined, assuming ABC\n"); + } } return 0; diff --git a/drivers/media/v4l2-core/v4l2-mc.c b/drivers/media/v4l2-core/v4l2-mc.c index 4bb91359e3a9..937d358697e1 100644 --- a/drivers/media/v4l2-core/v4l2-mc.c +++ b/drivers/media/v4l2-core/v4l2-mc.c @@ -329,7 +329,7 @@ int v4l2_create_fwnode_links_to_pad(struct v4l2_subdev *src_sd, if (!(sink->flags & MEDIA_PAD_FL_SINK)) return -EINVAL; - fwnode_graph_for_each_endpoint(dev_fwnode(src_sd->dev), endpoint) { + fwnode_graph_for_each_endpoint(src_sd->fwnode, endpoint) { struct fwnode_handle *remote_ep; int src_idx, sink_idx, ret; struct media_pad *src; diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index 50eb9f49512b..e2a75a52563f 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -358,17 +358,6 @@ static unsigned int gpmc_ps_to_ticks(unsigned int time_ps) return (time_ps + tick_ps - 1) / tick_ps; } -static unsigned int gpmc_clk_ticks_to_ns(unsigned int ticks, int cs, - enum gpmc_clk_domain cd) -{ - return ticks * gpmc_get_clk_period(cs, cd) / 1000; -} - -unsigned int gpmc_ticks_to_ns(unsigned int ticks) -{ - return gpmc_clk_ticks_to_ns(ticks, /* any CS */ 0, GPMC_CD_FCLK); -} - static unsigned int gpmc_ticks_to_ps(unsigned int ticks) { return ticks * gpmc_get_fclk_period(); @@ -415,6 +404,13 @@ static void gpmc_cs_bool_timings(int cs, const struct gpmc_bool_timings *p) } #ifdef CONFIG_OMAP_GPMC_DEBUG + +static unsigned int gpmc_clk_ticks_to_ns(unsigned int ticks, int cs, + enum gpmc_clk_domain cd) +{ + return ticks * gpmc_get_clk_period(cs, cd) / 1000; +} + /** * get_gpmc_timing_reg - read a timing parameter and print DTS settings for it. * @cs: Chip Select Region @@ -1295,21 +1291,6 @@ int gpmc_omap_onenand_set_timings(struct device *dev, int cs, int freq, } EXPORT_SYMBOL_GPL(gpmc_omap_onenand_set_timings); -int gpmc_get_client_irq(unsigned int irq_config) -{ - if (!gpmc_irq_domain) { - pr_warn("%s called before GPMC IRQ domain available\n", - __func__); - return 0; - } - - /* we restrict this to NAND IRQs only */ - if (irq_config >= GPMC_NR_NAND_IRQS) - return 0; - - return irq_create_mapping(gpmc_irq_domain, irq_config); -} - static int gpmc_irq_endis(unsigned long hwirq, bool endis) { u32 regval; diff --git a/drivers/memory/tegra/tegra20-emc.c b/drivers/memory/tegra/tegra20-emc.c index 7193f848d17e..9b7d30a21a5b 100644 --- a/drivers/memory/tegra/tegra20-emc.c +++ b/drivers/memory/tegra/tegra20-emc.c @@ -474,14 +474,15 @@ tegra_emc_find_node_by_ram_code(struct tegra_emc *emc) ram_code = tegra_read_ram_code(); - for (np = of_find_node_by_name(dev->of_node, "emc-tables"); np; - np = of_find_node_by_name(np, "emc-tables")) { + for_each_child_of_node(dev->of_node, np) { + if (!of_node_name_eq(np, "emc-tables")) + continue; err = of_property_read_u32(np, "nvidia,ram-code", &value); if (err || value != ram_code) { struct device_node *lpddr2_np; bool cfg_mismatches = false; - lpddr2_np = of_find_node_by_name(np, "lpddr2"); + lpddr2_np = of_get_child_by_name(np, "lpddr2"); if (lpddr2_np) { const struct lpddr2_info *info; @@ -518,7 +519,6 @@ tegra_emc_find_node_by_ram_code(struct tegra_emc *emc) } if (cfg_mismatches) { - of_node_put(np); continue; } } diff --git a/drivers/memory/ti-aemif.c b/drivers/memory/ti-aemif.c index d54dc3cfff73..c8b83c9edbd5 100644 --- a/drivers/memory/ti-aemif.c +++ b/drivers/memory/ti-aemif.c @@ -13,7 +13,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -69,39 +71,27 @@ #define ACR_SSTROBE_MASK BIT(31) #define ASIZE_16BIT 1 -#define CONFIG_MASK (TA(TA_MAX) | \ - RHOLD(RHOLD_MAX) | \ - RSTROBE(RSTROBE_MAX) | \ - RSETUP(RSETUP_MAX) | \ - WHOLD(WHOLD_MAX) | \ - WSTROBE(WSTROBE_MAX) | \ - WSETUP(WSETUP_MAX) | \ - EW(EW_MAX) | SSTROBE(SSTROBE_MAX) | \ - ASIZE_MAX) +#define TIMINGS_MASK (TA(TA_MAX) | \ + RHOLD(RHOLD_MAX) | \ + RSTROBE(RSTROBE_MAX) | \ + RSETUP(RSETUP_MAX) | \ + WHOLD(WHOLD_MAX) | \ + WSTROBE(WSTROBE_MAX) | \ + WSETUP(WSETUP_MAX)) + +#define CONFIG_MASK (EW(EW_MAX) | SSTROBE(SSTROBE_MAX) | ASIZE_MAX) /** - * struct aemif_cs_data: structure to hold cs parameters + * struct aemif_cs_data: structure to hold CS parameters + * @timings: timings configuration * @cs: chip-select number - * @wstrobe: write strobe width, ns - * @rstrobe: read strobe width, ns - * @wsetup: write setup width, ns - * @whold: write hold width, ns - * @rsetup: read setup width, ns - * @rhold: read hold width, ns - * @ta: minimum turn around time, ns * @enable_ss: enable/disable select strobe mode * @enable_ew: enable/disable extended wait mode * @asize: width of the asynchronous device's data bus */ struct aemif_cs_data { + struct aemif_cs_timings timings; u8 cs; - u16 wstrobe; - u16 rstrobe; - u8 wsetup; - u8 whold; - u8 rsetup; - u8 rhold; - u8 ta; u8 enable_ss; u8 enable_ew; u8 asize; @@ -115,6 +105,7 @@ struct aemif_cs_data { * @num_cs: number of assigned chip-selects * @cs_offset: start number of cs nodes * @cs_data: array of chip-select settings + * @config_cs_lock: lock used to access CS configuration */ struct aemif_device { void __iomem *base; @@ -123,20 +114,94 @@ struct aemif_device { u8 num_cs; int cs_offset; struct aemif_cs_data cs_data[NUM_CS]; + struct mutex config_cs_lock; }; +/** + * aemif_check_cs_timings() - Check the validity of a CS timing configuration. + * @timings: timings configuration + * + * @return: 0 if the timing configuration is valid, negative error number otherwise. + */ +int aemif_check_cs_timings(struct aemif_cs_timings *timings) +{ + if (timings->ta > TA_MAX) + return -EINVAL; + + if (timings->rhold > RHOLD_MAX) + return -EINVAL; + + if (timings->rstrobe > RSTROBE_MAX) + return -EINVAL; + + if (timings->rsetup > RSETUP_MAX) + return -EINVAL; + + if (timings->whold > WHOLD_MAX) + return -EINVAL; + + if (timings->wstrobe > WSTROBE_MAX) + return -EINVAL; + + if (timings->wsetup > WSETUP_MAX) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL_GPL(aemif_check_cs_timings); + +/** + * aemif_set_cs_timings() - Set the timing configuration of a given chip select. + * @aemif: aemif device to configure + * @cs: index of the chip select to configure + * @timings: timings configuration to set + * + * @return: 0 on success, else negative errno. + */ +int aemif_set_cs_timings(struct aemif_device *aemif, u8 cs, + struct aemif_cs_timings *timings) +{ + unsigned int offset; + u32 val, set; + int ret; + + if (!timings || !aemif) + return -EINVAL; + + if (cs > aemif->num_cs) + return -EINVAL; + + ret = aemif_check_cs_timings(timings); + if (ret) + return ret; + + set = TA(timings->ta) | RHOLD(timings->rhold) | RSTROBE(timings->rstrobe) | + RSETUP(timings->rsetup) | WHOLD(timings->whold) | + WSTROBE(timings->wstrobe) | WSETUP(timings->wsetup); + + offset = A1CR_OFFSET + cs * 4; + + mutex_lock(&aemif->config_cs_lock); + val = readl(aemif->base + offset); + val &= ~TIMINGS_MASK; + val |= set; + writel(val, aemif->base + offset); + mutex_unlock(&aemif->config_cs_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(aemif_set_cs_timings); + /** * aemif_calc_rate - calculate timing data. * @pdev: platform device to calculate for * @wanted: The cycle time needed in nanoseconds. * @clk: The input clock rate in kHz. - * @max: The maximum divider value that can be programmed. * - * On success, returns the calculated timing value minus 1 for easy - * programming into AEMIF timing registers, else negative errno. + * @return: the calculated timing value minus 1 for easy + * programming into AEMIF timing registers. */ -static int aemif_calc_rate(struct platform_device *pdev, int wanted, - unsigned long clk, int max) +static u32 aemif_calc_rate(struct platform_device *pdev, int wanted, unsigned long clk) { int result; @@ -149,10 +214,6 @@ static int aemif_calc_rate(struct platform_device *pdev, int wanted, if (result < 0) result = 0; - /* ... But configuring tighter timings is not an option. */ - else if (result > max) - result = -EINVAL; - return result; } @@ -174,48 +235,25 @@ static int aemif_config_abus(struct platform_device *pdev, int csnum) { struct aemif_device *aemif = platform_get_drvdata(pdev); struct aemif_cs_data *data = &aemif->cs_data[csnum]; - int ta, rhold, rstrobe, rsetup, whold, wstrobe, wsetup; - unsigned long clk_rate = aemif->clk_rate; unsigned offset; u32 set, val; offset = A1CR_OFFSET + (data->cs - aemif->cs_offset) * 4; - ta = aemif_calc_rate(pdev, data->ta, clk_rate, TA_MAX); - rhold = aemif_calc_rate(pdev, data->rhold, clk_rate, RHOLD_MAX); - rstrobe = aemif_calc_rate(pdev, data->rstrobe, clk_rate, RSTROBE_MAX); - rsetup = aemif_calc_rate(pdev, data->rsetup, clk_rate, RSETUP_MAX); - whold = aemif_calc_rate(pdev, data->whold, clk_rate, WHOLD_MAX); - wstrobe = aemif_calc_rate(pdev, data->wstrobe, clk_rate, WSTROBE_MAX); - wsetup = aemif_calc_rate(pdev, data->wsetup, clk_rate, WSETUP_MAX); - - if (ta < 0 || rhold < 0 || rstrobe < 0 || rsetup < 0 || - whold < 0 || wstrobe < 0 || wsetup < 0) { - dev_err(&pdev->dev, "%s: cannot get suitable timings\n", - __func__); - return -EINVAL; - } - - set = TA(ta) | RHOLD(rhold) | RSTROBE(rstrobe) | RSETUP(rsetup) | - WHOLD(whold) | WSTROBE(wstrobe) | WSETUP(wsetup); - - set |= (data->asize & ACR_ASIZE_MASK); + set = (data->asize & ACR_ASIZE_MASK); if (data->enable_ew) set |= ACR_EW_MASK; if (data->enable_ss) set |= ACR_SSTROBE_MASK; + mutex_lock(&aemif->config_cs_lock); val = readl(aemif->base + offset); val &= ~CONFIG_MASK; val |= set; writel(val, aemif->base + offset); + mutex_unlock(&aemif->config_cs_lock); - return 0; -} - -static inline int aemif_cycles_to_nsec(int val, unsigned long clk_rate) -{ - return ((val + 1) * NSEC_PER_MSEC) / clk_rate; + return aemif_set_cs_timings(aemif, data->cs - aemif->cs_offset, &data->timings); } /** @@ -231,19 +269,18 @@ static void aemif_get_hw_params(struct platform_device *pdev, int csnum) { struct aemif_device *aemif = platform_get_drvdata(pdev); struct aemif_cs_data *data = &aemif->cs_data[csnum]; - unsigned long clk_rate = aemif->clk_rate; u32 val, offset; offset = A1CR_OFFSET + (data->cs - aemif->cs_offset) * 4; val = readl(aemif->base + offset); - data->ta = aemif_cycles_to_nsec(TA_VAL(val), clk_rate); - data->rhold = aemif_cycles_to_nsec(RHOLD_VAL(val), clk_rate); - data->rstrobe = aemif_cycles_to_nsec(RSTROBE_VAL(val), clk_rate); - data->rsetup = aemif_cycles_to_nsec(RSETUP_VAL(val), clk_rate); - data->whold = aemif_cycles_to_nsec(WHOLD_VAL(val), clk_rate); - data->wstrobe = aemif_cycles_to_nsec(WSTROBE_VAL(val), clk_rate); - data->wsetup = aemif_cycles_to_nsec(WSETUP_VAL(val), clk_rate); + data->timings.ta = TA_VAL(val); + data->timings.rhold = RHOLD_VAL(val); + data->timings.rstrobe = RSTROBE_VAL(val); + data->timings.rsetup = RSETUP_VAL(val); + data->timings.whold = WHOLD_VAL(val); + data->timings.wstrobe = WSTROBE_VAL(val); + data->timings.wsetup = WSETUP_VAL(val); data->enable_ew = EW_VAL(val); data->enable_ss = SSTROBE_VAL(val); data->asize = val & ASIZE_MAX; @@ -261,6 +298,7 @@ static int of_aemif_parse_abus_config(struct platform_device *pdev, struct device_node *np) { struct aemif_device *aemif = platform_get_drvdata(pdev); + unsigned long clk_rate = aemif->clk_rate; struct aemif_cs_data *data; u32 cs; u32 val; @@ -288,32 +326,33 @@ static int of_aemif_parse_abus_config(struct platform_device *pdev, /* override the values from device node */ if (!of_property_read_u32(np, "ti,cs-min-turnaround-ns", &val)) - data->ta = val; + data->timings.ta = aemif_calc_rate(pdev, val, clk_rate); if (!of_property_read_u32(np, "ti,cs-read-hold-ns", &val)) - data->rhold = val; + data->timings.rhold = aemif_calc_rate(pdev, val, clk_rate); if (!of_property_read_u32(np, "ti,cs-read-strobe-ns", &val)) - data->rstrobe = val; + data->timings.rstrobe = aemif_calc_rate(pdev, val, clk_rate); if (!of_property_read_u32(np, "ti,cs-read-setup-ns", &val)) - data->rsetup = val; + data->timings.rsetup = aemif_calc_rate(pdev, val, clk_rate); if (!of_property_read_u32(np, "ti,cs-write-hold-ns", &val)) - data->whold = val; + data->timings.whold = aemif_calc_rate(pdev, val, clk_rate); if (!of_property_read_u32(np, "ti,cs-write-strobe-ns", &val)) - data->wstrobe = val; + data->timings.wstrobe = aemif_calc_rate(pdev, val, clk_rate); if (!of_property_read_u32(np, "ti,cs-write-setup-ns", &val)) - data->wsetup = val; + data->timings.wsetup = aemif_calc_rate(pdev, val, clk_rate); if (!of_property_read_u32(np, "ti,cs-bus-width", &val)) if (val == 16) data->asize = 1; data->enable_ew = of_property_read_bool(np, "ti,cs-extended-wait-mode"); data->enable_ss = of_property_read_bool(np, "ti,cs-select-strobe-mode"); - return 0; + + return aemif_check_cs_timings(&data->timings); } static const struct of_device_id aemif_of_match[] = { @@ -351,6 +390,7 @@ static int aemif_probe(struct platform_device *pdev) if (IS_ERR(aemif->base)) return PTR_ERR(aemif->base); + mutex_init(&aemif->config_cs_lock); if (np) { /* * For every controller device node, there is a cs device node diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index ae4e8b8e6eb7..043b9ec756ff 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -200,7 +200,7 @@ static int memstick_dummy_check(struct memstick_dev *card) /** * memstick_detect_change - schedule media detection on memstick host - * @host - host to use + * @host: host to use */ void memstick_detect_change(struct memstick_host *host) { @@ -210,13 +210,15 @@ EXPORT_SYMBOL(memstick_detect_change); /** * memstick_next_req - called by host driver to obtain next request to process - * @host - host to use - * @mrq - pointer to stick the request to + * @host: host to use + * @mrq: pointer to stick the request to * * Host calls this function from idle state (*mrq == NULL) or after finishing * previous request (*mrq should point to it). If previous request was - * unsuccessful, it is retried for predetermined number of times. Return value - * of 0 means that new request was assigned to the host. + * unsuccessful, it is retried for predetermined number of times. + * + * Returns: value of 0 means that new request was assigned to the host. + * Otherwise a negative error code is returned. */ int memstick_next_req(struct memstick_host *host, struct memstick_request **mrq) { @@ -242,7 +244,7 @@ EXPORT_SYMBOL(memstick_next_req); /** * memstick_new_req - notify the host that some requests are pending - * @host - host to use + * @host: host to use */ void memstick_new_req(struct memstick_host *host) { @@ -256,9 +258,9 @@ EXPORT_SYMBOL(memstick_new_req); /** * memstick_init_req_sg - set request fields needed for bulk data transfer - * @mrq - request to use - * @tpc - memstick Transport Protocol Command - * @sg - TPC argument + * @mrq: request to use + * @tpc: memstick Transport Protocol Command + * @sg: TPC argument */ void memstick_init_req_sg(struct memstick_request *mrq, unsigned char tpc, const struct scatterlist *sg) @@ -281,10 +283,10 @@ EXPORT_SYMBOL(memstick_init_req_sg); /** * memstick_init_req - set request fields needed for short data transfer - * @mrq - request to use - * @tpc - memstick Transport Protocol Command - * @buf - TPC argument buffer - * @length - TPC argument size + * @mrq: request to use + * @tpc: memstick Transport Protocol Command + * @buf: TPC argument buffer + * @length: TPC argument size * * The intended use of this function (transfer of data items several bytes * in size) allows us to just copy the value between request structure and @@ -360,7 +362,9 @@ static int h_memstick_set_rw_addr(struct memstick_dev *card, /** * memstick_set_rw_addr - issue SET_RW_REG_ADDR request and wait for it to * complete - * @card - media device to use + * @card: media device to use + * + * Returns: error setting for the current request */ int memstick_set_rw_addr(struct memstick_dev *card) { @@ -487,6 +491,8 @@ out_power_off: * memstick_alloc_host - allocate a memstick_host structure * @extra: size of the user private data to allocate * @dev: parent device of the host + * + * Returns: %NULL on failure or the allocated &memstick_host pointer on success */ struct memstick_host *memstick_alloc_host(unsigned int extra, struct device *dev) @@ -507,7 +513,9 @@ EXPORT_SYMBOL(memstick_alloc_host); /** * memstick_add_host - start request processing on memstick host - * @host - host to use + * @host: host to use + * + * Returns: %0 on success or a negative error code on failure */ int memstick_add_host(struct memstick_host *host) { @@ -543,7 +551,7 @@ EXPORT_SYMBOL(memstick_add_host); /** * memstick_remove_host - stop request processing on memstick host - * @host - host to use + * @host: host to use */ void memstick_remove_host(struct memstick_host *host) { @@ -565,7 +573,7 @@ EXPORT_SYMBOL(memstick_remove_host); /** * memstick_free_host - free memstick host - * @host - host to use + * @host: host to use */ void memstick_free_host(struct memstick_host *host) { @@ -576,7 +584,7 @@ EXPORT_SYMBOL(memstick_free_host); /** * memstick_suspend_host - notify bus driver of host suspension - * @host - host to use + * @host: host to use */ void memstick_suspend_host(struct memstick_host *host) { @@ -588,7 +596,7 @@ EXPORT_SYMBOL(memstick_suspend_host); /** * memstick_resume_host - notify bus driver of host resumption - * @host - host to use + * @host: host to use */ void memstick_resume_host(struct memstick_host *host) { diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c index 20a2466bec23..5b617c1f6789 100644 --- a/drivers/memstick/core/ms_block.c +++ b/drivers/memstick/core/ms_block.c @@ -2094,8 +2094,7 @@ static int msb_init_disk(struct memstick_dev *card) if (msb->disk_id < 0) return msb->disk_id; - rc = blk_mq_alloc_sq_tag_set(&msb->tag_set, &msb_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); + rc = blk_mq_alloc_sq_tag_set(&msb->tag_set, &msb_mq_ops, 2, 0); if (rc) goto out_release_id; diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index 13b317c56069..634d343b6bdb 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -1139,8 +1139,7 @@ static int mspro_block_init_disk(struct memstick_dev *card) if (disk_id < 0) return disk_id; - rc = blk_mq_alloc_sq_tag_set(&msb->tag_set, &mspro_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); + rc = blk_mq_alloc_sq_tag_set(&msb->tag_set, &mspro_mq_ops, 2, 0); if (rc) goto out_release_id; diff --git a/drivers/message/fusion/mptfc.c b/drivers/message/fusion/mptfc.c index ee61b70aa677..8f587c0efd9d 100644 --- a/drivers/message/fusion/mptfc.c +++ b/drivers/message/fusion/mptfc.c @@ -96,7 +96,7 @@ static u8 mptfcTaskCtx = MPT_MAX_PROTOCOL_DRIVERS; static u8 mptfcInternalCtx = MPT_MAX_PROTOCOL_DRIVERS; static int mptfc_target_alloc(struct scsi_target *starget); -static int mptfc_slave_alloc(struct scsi_device *sdev); +static int mptfc_sdev_init(struct scsi_device *sdev); static int mptfc_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *SCpnt); static void mptfc_target_destroy(struct scsi_target *starget); static void mptfc_set_rport_loss_tmo(struct fc_rport *rport, uint32_t timeout); @@ -113,10 +113,10 @@ static const struct scsi_host_template mptfc_driver_template = { .info = mptscsih_info, .queuecommand = mptfc_qcmd, .target_alloc = mptfc_target_alloc, - .slave_alloc = mptfc_slave_alloc, - .slave_configure = mptscsih_slave_configure, + .sdev_init = mptfc_sdev_init, + .sdev_configure = mptscsih_sdev_configure, .target_destroy = mptfc_target_destroy, - .slave_destroy = mptscsih_slave_destroy, + .sdev_destroy = mptscsih_sdev_destroy, .change_queue_depth = mptscsih_change_queue_depth, .eh_timed_out = fc_eh_timed_out, .eh_abort_handler = mptfc_abort, @@ -503,7 +503,7 @@ mptfc_register_dev(MPT_ADAPTER *ioc, int channel, FCDevicePage0_t *pg0) /* * if already mapped, remap here. If not mapped, * target_alloc will allocate vtarget and map, - * slave_alloc will fill in vdevice from vtarget. + * sdev_init will fill in vdevice from vtarget. */ if (ri->starget) { vtarget = ri->starget->hostdata; @@ -631,7 +631,7 @@ mptfc_dump_lun_info(MPT_ADAPTER *ioc, struct fc_rport *rport, struct scsi_device * Init memory once per LUN. */ static int -mptfc_slave_alloc(struct scsi_device *sdev) +mptfc_sdev_init(struct scsi_device *sdev) { MPT_SCSI_HOST *hd; VirtTarget *vtarget; @@ -651,7 +651,7 @@ mptfc_slave_alloc(struct scsi_device *sdev) vdevice = kzalloc(sizeof(VirtDevice), GFP_KERNEL); if (!vdevice) { - printk(MYIOC_s_ERR_FMT "slave_alloc kmalloc(%zd) FAILED!\n", + printk(MYIOC_s_ERR_FMT "sdev_init kmalloc(%zd) FAILED!\n", ioc->name, sizeof(VirtDevice)); return -ENOMEM; } diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c index d0549a4daf76..7e79da9684ed 100644 --- a/drivers/message/fusion/mptsas.c +++ b/drivers/message/fusion/mptsas.c @@ -1710,7 +1710,7 @@ mptsas_firmware_event_work(struct work_struct *work) static int -mptsas_slave_configure(struct scsi_device *sdev) +mptsas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { struct Scsi_Host *host = sdev->host; MPT_SCSI_HOST *hd = shost_priv(host); @@ -1736,7 +1736,7 @@ mptsas_slave_configure(struct scsi_device *sdev) mptsas_add_device_component_starget(ioc, scsi_target(sdev)); out: - return mptscsih_slave_configure(sdev); + return mptscsih_sdev_configure(sdev, lim); } static int @@ -1867,7 +1867,7 @@ mptsas_target_destroy(struct scsi_target *starget) static int -mptsas_slave_alloc(struct scsi_device *sdev) +mptsas_sdev_init(struct scsi_device *sdev) { struct Scsi_Host *host = sdev->host; MPT_SCSI_HOST *hd = shost_priv(host); @@ -1880,7 +1880,7 @@ mptsas_slave_alloc(struct scsi_device *sdev) vdevice = kzalloc(sizeof(VirtDevice), GFP_KERNEL); if (!vdevice) { - printk(MYIOC_s_ERR_FMT "slave_alloc kzalloc(%zd) FAILED!\n", + printk(MYIOC_s_ERR_FMT "sdev_init kzalloc(%zd) FAILED!\n", ioc->name, sizeof(VirtDevice)); return -ENOMEM; } @@ -2005,10 +2005,10 @@ static const struct scsi_host_template mptsas_driver_template = { .info = mptscsih_info, .queuecommand = mptsas_qcmd, .target_alloc = mptsas_target_alloc, - .slave_alloc = mptsas_slave_alloc, - .slave_configure = mptsas_slave_configure, + .sdev_init = mptsas_sdev_init, + .sdev_configure = mptsas_sdev_configure, .target_destroy = mptsas_target_destroy, - .slave_destroy = mptscsih_slave_destroy, + .sdev_destroy = mptscsih_sdev_destroy, .change_queue_depth = mptscsih_change_queue_depth, .eh_timed_out = mptsas_eh_timed_out, .eh_abort_handler = mptscsih_abort, diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c index 6c3f25cc33ff..a9604ba3c805 100644 --- a/drivers/message/fusion/mptscsih.c +++ b/drivers/message/fusion/mptscsih.c @@ -1071,7 +1071,7 @@ EXPORT_SYMBOL(mptscsih_flush_running_cmds); * * Returns: None. * - * Called from slave_destroy. + * Called from sdev_destroy. */ static void mptscsih_search_running_cmds(MPT_SCSI_HOST *hd, VirtDevice *vdevice) @@ -2331,7 +2331,7 @@ EXPORT_SYMBOL(mptscsih_raid_id_to_num); * Called if no device present or device being unloaded */ void -mptscsih_slave_destroy(struct scsi_device *sdev) +mptscsih_sdev_destroy(struct scsi_device *sdev) { struct Scsi_Host *host = sdev->host; MPT_SCSI_HOST *hd = shost_priv(host); @@ -2399,7 +2399,7 @@ mptscsih_change_queue_depth(struct scsi_device *sdev, int qdepth) * Return non-zero if fails. */ int -mptscsih_slave_configure(struct scsi_device *sdev) +mptscsih_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { struct Scsi_Host *sh = sdev->host; VirtTarget *vtarget; @@ -3302,8 +3302,8 @@ EXPORT_SYMBOL(mptscsih_resume); EXPORT_SYMBOL(mptscsih_show_info); EXPORT_SYMBOL(mptscsih_info); EXPORT_SYMBOL(mptscsih_qcmd); -EXPORT_SYMBOL(mptscsih_slave_destroy); -EXPORT_SYMBOL(mptscsih_slave_configure); +EXPORT_SYMBOL(mptscsih_sdev_destroy); +EXPORT_SYMBOL(mptscsih_sdev_configure); EXPORT_SYMBOL(mptscsih_abort); EXPORT_SYMBOL(mptscsih_dev_reset); EXPORT_SYMBOL(mptscsih_target_reset); diff --git a/drivers/message/fusion/mptscsih.h b/drivers/message/fusion/mptscsih.h index e3d92c392673..ece451c575e1 100644 --- a/drivers/message/fusion/mptscsih.h +++ b/drivers/message/fusion/mptscsih.h @@ -116,8 +116,9 @@ extern const char * mptscsih_info(struct Scsi_Host *SChost); extern int mptscsih_qcmd(struct scsi_cmnd *SCpnt); extern int mptscsih_IssueTaskMgmt(MPT_SCSI_HOST *hd, u8 type, u8 channel, u8 id, u64 lun, int ctx2abort, ulong timeout); -extern void mptscsih_slave_destroy(struct scsi_device *device); -extern int mptscsih_slave_configure(struct scsi_device *device); +extern void mptscsih_sdev_destroy(struct scsi_device *device); +extern int mptscsih_sdev_configure(struct scsi_device *device, + struct queue_limits *lim); extern int mptscsih_abort(struct scsi_cmnd * SCpnt); extern int mptscsih_dev_reset(struct scsi_cmnd * SCpnt); extern int mptscsih_target_reset(struct scsi_cmnd * SCpnt); diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c index 4184d0c70ac3..a3901fbfac4f 100644 --- a/drivers/message/fusion/mptspi.c +++ b/drivers/message/fusion/mptspi.c @@ -713,7 +713,7 @@ static void mptspi_dv_device(struct _MPT_SCSI_HOST *hd, mptspi_read_parameters(sdev->sdev_target); } -static int mptspi_slave_alloc(struct scsi_device *sdev) +static int mptspi_sdev_init(struct scsi_device *sdev) { MPT_SCSI_HOST *hd = shost_priv(sdev->host); VirtTarget *vtarget; @@ -727,7 +727,7 @@ static int mptspi_slave_alloc(struct scsi_device *sdev) vdevice = kzalloc(sizeof(VirtDevice), GFP_KERNEL); if (!vdevice) { - printk(MYIOC_s_ERR_FMT "slave_alloc kmalloc(%zd) FAILED!\n", + printk(MYIOC_s_ERR_FMT "sdev_init kmalloc(%zd) FAILED!\n", ioc->name, sizeof(VirtDevice)); return -ENOMEM; } @@ -746,7 +746,8 @@ static int mptspi_slave_alloc(struct scsi_device *sdev) return 0; } -static int mptspi_slave_configure(struct scsi_device *sdev) +static int mptspi_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct _MPT_SCSI_HOST *hd = shost_priv(sdev->host); VirtTarget *vtarget = scsi_target(sdev)->hostdata; @@ -754,7 +755,7 @@ static int mptspi_slave_configure(struct scsi_device *sdev) mptspi_initTarget(hd, vtarget, sdev); - ret = mptscsih_slave_configure(sdev); + ret = mptscsih_sdev_configure(sdev, lim); if (ret) return ret; @@ -799,7 +800,7 @@ mptspi_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *SCpnt) return mptscsih_qcmd(SCpnt); } -static void mptspi_slave_destroy(struct scsi_device *sdev) +static void mptspi_sdev_destroy(struct scsi_device *sdev) { struct scsi_target *starget = scsi_target(sdev); VirtTarget *vtarget = starget->hostdata; @@ -817,7 +818,7 @@ static void mptspi_slave_destroy(struct scsi_device *sdev) mptspi_write_spi_device_pg1(starget, &pg1); } - mptscsih_slave_destroy(sdev); + mptscsih_sdev_destroy(sdev); } static const struct scsi_host_template mptspi_driver_template = { @@ -828,10 +829,10 @@ static const struct scsi_host_template mptspi_driver_template = { .info = mptscsih_info, .queuecommand = mptspi_qcmd, .target_alloc = mptspi_target_alloc, - .slave_alloc = mptspi_slave_alloc, - .slave_configure = mptspi_slave_configure, + .sdev_init = mptspi_sdev_init, + .sdev_configure = mptspi_sdev_configure, .target_destroy = mptspi_target_destroy, - .slave_destroy = mptspi_slave_destroy, + .sdev_destroy = mptspi_sdev_destroy, .change_queue_depth = mptscsih_change_queue_depth, .eh_abort_handler = mptscsih_abort, .eh_device_reset_handler = mptscsih_dev_reset, diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index ae23b317a64e..6b0682af6e32 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -2386,6 +2386,19 @@ config MFD_INTEL_M10_BMC_PMCI additional drivers must be enabled in order to use the functionality of the device. +config MFD_QNAP_MCU + tristate "QNAP microcontroller unit core driver" + depends on SERIAL_DEV_BUS + select MFD_CORE + help + Select this to get support for the QNAP MCU device found in + several devices of QNAP network attached storage products that + implements additional functionality for the device, like fan + and LED control. + + This driver implements the base serial protocol to talk to the + device and provides functions for the other parts to hook into. + config MFD_RSMU_I2C tristate "Renesas Synchronization Management Unit with I2C" depends on I2C && OF @@ -2414,5 +2427,17 @@ config MFD_RSMU_SPI Additional drivers must be enabled in order to use the functionality of the device. +config MFD_UPBOARD_FPGA + tristate "Support for the AAeon UP board FPGA" + depends on (X86 && ACPI) + select MFD_CORE + help + Select this option to enable the AAEON UP and UP^2 onboard FPGA. + This is the core driver of this FPGA, which has a pin controller and a + LED controller. + + To compile this driver as a module, choose M here: the module will be + called upboard-fpga. + endmenu endif diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index e057d6d6faef..9220eaf7cf12 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -288,5 +288,9 @@ obj-$(CONFIG_MFD_INTEL_M10_BMC_PMCI) += intel-m10-bmc-pmci.o obj-$(CONFIG_MFD_ATC260X) += atc260x-core.o obj-$(CONFIG_MFD_ATC260X_I2C) += atc260x-i2c.o +obj-$(CONFIG_MFD_QNAP_MCU) += qnap-mcu.o + obj-$(CONFIG_MFD_RSMU_I2C) += rsmu_i2c.o rsmu_core.o obj-$(CONFIG_MFD_RSMU_SPI) += rsmu_spi.o rsmu_core.o + +obj-$(CONFIG_MFD_UPBOARD_FPGA) += upboard-fpga.o diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c index 251465a656d0..cff56deba24f 100644 --- a/drivers/mfd/axp20x.c +++ b/drivers/mfd/axp20x.c @@ -1445,7 +1445,7 @@ int axp20x_device_probe(struct axp20x_dev *axp20x) } } - ret = mfd_add_devices(axp20x->dev, PLATFORM_DEVID_AUTO, axp20x->cells, + ret = mfd_add_devices(axp20x->dev, PLATFORM_DEVID_NONE, axp20x->cells, axp20x->nr_cells, NULL, 0, NULL); if (ret) { @@ -1455,10 +1455,7 @@ int axp20x_device_probe(struct axp20x_dev *axp20x) } if (axp20x->variant != AXP288_ID) - devm_register_sys_off_handler(axp20x->dev, - SYS_OFF_MODE_POWER_OFF, - SYS_OFF_PRIO_DEFAULT, - axp20x_power_off, axp20x); + devm_register_power_off_handler(axp20x->dev, axp20x_power_off, axp20x); dev_info(axp20x->dev, "AXP20X driver loaded\n"); diff --git a/drivers/mfd/cs42l43-i2c.c b/drivers/mfd/cs42l43-i2c.c index f0ad4002652d..a2ab001a600a 100644 --- a/drivers/mfd/cs42l43-i2c.c +++ b/drivers/mfd/cs42l43-i2c.c @@ -56,13 +56,6 @@ static int cs42l43_i2c_probe(struct i2c_client *i2c) return cs42l43_dev_probe(cs42l43); } -static void cs42l43_i2c_remove(struct i2c_client *i2c) -{ - struct cs42l43 *cs42l43 = dev_get_drvdata(&i2c->dev); - - cs42l43_dev_remove(cs42l43); -} - #if IS_ENABLED(CONFIG_OF) static const struct of_device_id cs42l43_of_match[] = { { .compatible = "cirrus,cs42l43", }, @@ -88,7 +81,6 @@ static struct i2c_driver cs42l43_i2c_driver = { }, .probe = cs42l43_i2c_probe, - .remove = cs42l43_i2c_remove, }; module_i2c_driver(cs42l43_i2c_driver); diff --git a/drivers/mfd/cs42l43-sdw.c b/drivers/mfd/cs42l43-sdw.c index 3938d48039c4..023f7e1a30f8 100644 --- a/drivers/mfd/cs42l43-sdw.c +++ b/drivers/mfd/cs42l43-sdw.c @@ -187,15 +187,6 @@ static int cs42l43_sdw_probe(struct sdw_slave *sdw, const struct sdw_device_id * return cs42l43_dev_probe(cs42l43); } -static int cs42l43_sdw_remove(struct sdw_slave *sdw) -{ - struct cs42l43 *cs42l43 = dev_get_drvdata(&sdw->dev); - - cs42l43_dev_remove(cs42l43); - - return 0; -} - static const struct sdw_device_id cs42l43_sdw_id[] = { SDW_SLAVE_ENTRY(0x01FA, 0x4243, 0), {} @@ -209,7 +200,6 @@ static struct sdw_driver cs42l43_sdw_driver = { }, .probe = cs42l43_sdw_probe, - .remove = cs42l43_sdw_remove, .id_table = cs42l43_sdw_id, .ops = &cs42l43_sdw_ops, }; diff --git a/drivers/mfd/cs42l43.c b/drivers/mfd/cs42l43.c index b5ab5e613db7..103787f37443 100644 --- a/drivers/mfd/cs42l43.c +++ b/drivers/mfd/cs42l43.c @@ -29,7 +29,7 @@ #define CS42L43_RESET_DELAY_MS 20 -#define CS42L43_SDW_ATTACH_TIMEOUT_MS 500 +#define CS42L43_SDW_ATTACH_TIMEOUT_MS 5000 #define CS42L43_SDW_DETACH_TIMEOUT_MS 100 #define CS42L43_MCU_BOOT_STAGE1 1 @@ -48,6 +48,7 @@ #define CS42L43_MCU_SUPPORTED_REV 0x2105 #define CS42L43_MCU_SHADOW_REGS_REQUIRED_REV 0x2200 +#define CS42L43_BIOS_SHADOW_REGS_REQUIRED_REV 0x1002 #define CS42L43_MCU_SUPPORTED_BIOS_REV 0x0001 #define CS42L43_VDDP_DELAY_US 50 @@ -773,7 +774,8 @@ static int cs42l43_mcu_update_step(struct cs42l43 *cs42l43) * Later versions of the firmwware require the driver to access some * features through a set of shadow registers. */ - shadow = mcu_rev >= CS42L43_MCU_SHADOW_REGS_REQUIRED_REV; + shadow = (mcu_rev >= CS42L43_MCU_SHADOW_REGS_REQUIRED_REV) || + (bios_rev >= CS42L43_BIOS_SHADOW_REGS_REQUIRED_REV); ret = regmap_read(cs42l43->regmap, CS42L43_BOOT_CONTROL, &secure_cfg); if (ret) { @@ -982,7 +984,7 @@ static int cs42l43_power_up(struct cs42l43 *cs42l43) /* vdd-p must be on for 50uS before any other supply */ usleep_range(CS42L43_VDDP_DELAY_US, 2 * CS42L43_VDDP_DELAY_US); - gpiod_set_value_cansleep(cs42l43->reset, 1); + gpiod_set_raw_value_cansleep(cs42l43->reset, 1); ret = regulator_bulk_enable(CS42L43_N_SUPPLIES, cs42l43->core_supplies); if (ret) { @@ -1003,7 +1005,7 @@ static int cs42l43_power_up(struct cs42l43 *cs42l43) err_core_supplies: regulator_bulk_disable(CS42L43_N_SUPPLIES, cs42l43->core_supplies); err_reset: - gpiod_set_value_cansleep(cs42l43->reset, 0); + gpiod_set_raw_value_cansleep(cs42l43->reset, 0); regulator_disable(cs42l43->vdd_p); return ret; @@ -1025,7 +1027,7 @@ static int cs42l43_power_down(struct cs42l43 *cs42l43) return ret; } - gpiod_set_value_cansleep(cs42l43->reset, 0); + gpiod_set_raw_value_cansleep(cs42l43->reset, 0); ret = regulator_disable(cs42l43->vdd_p); if (ret) { @@ -1036,6 +1038,15 @@ static int cs42l43_power_down(struct cs42l43 *cs42l43) return 0; } +static void cs42l43_dev_remove(void *data) +{ + struct cs42l43 *cs42l43 = data; + + cancel_work_sync(&cs42l43->boot_work); + + cs42l43_power_down(cs42l43); +} + int cs42l43_dev_probe(struct cs42l43 *cs42l43) { int i, ret; @@ -1050,11 +1061,13 @@ int cs42l43_dev_probe(struct cs42l43 *cs42l43) regcache_cache_only(cs42l43->regmap, true); - cs42l43->reset = devm_gpiod_get_optional(cs42l43->dev, "reset", GPIOD_OUT_LOW); + cs42l43->reset = devm_gpiod_get_optional(cs42l43->dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(cs42l43->reset)) return dev_err_probe(cs42l43->dev, PTR_ERR(cs42l43->reset), "Failed to get reset\n"); + gpiod_set_raw_value_cansleep(cs42l43->reset, 0); + cs42l43->vdd_p = devm_regulator_get(cs42l43->dev, "vdd-p"); if (IS_ERR(cs42l43->vdd_p)) return dev_err_probe(cs42l43->dev, PTR_ERR(cs42l43->vdd_p), @@ -1080,6 +1093,10 @@ int cs42l43_dev_probe(struct cs42l43 *cs42l43) if (ret) return ret; + ret = devm_add_action_or_reset(cs42l43->dev, cs42l43_dev_remove, cs42l43); + if (ret) + return ret; + pm_runtime_set_autosuspend_delay(cs42l43->dev, CS42L43_AUTOSUSPEND_TIME_MS); pm_runtime_use_autosuspend(cs42l43->dev); pm_runtime_set_active(cs42l43->dev); @@ -1098,14 +1115,6 @@ int cs42l43_dev_probe(struct cs42l43 *cs42l43) } EXPORT_SYMBOL_NS_GPL(cs42l43_dev_probe, "MFD_CS42L43"); -void cs42l43_dev_remove(struct cs42l43 *cs42l43) -{ - cancel_work_sync(&cs42l43->boot_work); - - cs42l43_power_down(cs42l43); -} -EXPORT_SYMBOL_NS_GPL(cs42l43_dev_remove, "MFD_CS42L43"); - static int cs42l43_suspend(struct device *dev) { struct cs42l43 *cs42l43 = dev_get_drvdata(dev); diff --git a/drivers/mfd/cs42l43.h b/drivers/mfd/cs42l43.h index 8d1b1b0f5a47..f3da783930f5 100644 --- a/drivers/mfd/cs42l43.h +++ b/drivers/mfd/cs42l43.h @@ -25,6 +25,5 @@ bool cs42l43_precious_register(struct device *dev, unsigned int reg); bool cs42l43_volatile_register(struct device *dev, unsigned int reg); int cs42l43_dev_probe(struct cs42l43 *cs42l43); -void cs42l43_dev_remove(struct cs42l43 *cs42l43); #endif /* CS42L43_CORE_INT_H */ diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c index dc85801b9fa0..b06cd518413b 100644 --- a/drivers/mfd/da9052-core.c +++ b/drivers/mfd/da9052-core.c @@ -585,6 +585,7 @@ static int da9052_clear_fault_log(struct da9052 *da9052) "Cannot reset FAULT_LOG values %d\n", ret); } + da9052->fault_log = fault_log; return ret; } diff --git a/drivers/mfd/intel_soc_pmic_chtdc_ti.c b/drivers/mfd/intel_soc_pmic_chtdc_ti.c index 992855bfda3e..8582ae65a802 100644 --- a/drivers/mfd/intel_soc_pmic_chtdc_ti.c +++ b/drivers/mfd/intel_soc_pmic_chtdc_ti.c @@ -81,7 +81,7 @@ static struct mfd_cell chtdc_ti_dev[] = { static const struct regmap_config chtdc_ti_regmap_config = { .reg_bits = 8, .val_bits = 8, - .max_register = 128, + .max_register = 0xff, .cache_type = REGCACHE_NONE, }; diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c index f14901660147..4b7d0cb9340f 100644 --- a/drivers/mfd/lpc_ich.c +++ b/drivers/mfd/lpc_ich.c @@ -834,8 +834,9 @@ static const struct pci_device_id lpc_ich_ids[] = { { PCI_VDEVICE(INTEL, 0x2917), LPC_ICH9ME}, { PCI_VDEVICE(INTEL, 0x2918), LPC_ICH9}, { PCI_VDEVICE(INTEL, 0x2919), LPC_ICH9M}, - { PCI_VDEVICE(INTEL, 0x3197), LPC_GLK}, { PCI_VDEVICE(INTEL, 0x2b9c), LPC_COUGARMOUNTAIN}, + { PCI_VDEVICE(INTEL, 0x3197), LPC_GLK}, + { PCI_VDEVICE(INTEL, 0x31e8), LPC_GLK}, { PCI_VDEVICE(INTEL, 0x3a14), LPC_ICH10DO}, { PCI_VDEVICE(INTEL, 0x3a16), LPC_ICH10R}, { PCI_VDEVICE(INTEL, 0x3a18), LPC_ICH10}, diff --git a/drivers/mfd/qnap-mcu.c b/drivers/mfd/qnap-mcu.c new file mode 100644 index 000000000000..4be39d8b2905 --- /dev/null +++ b/drivers/mfd/qnap-mcu.c @@ -0,0 +1,338 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Core driver for the microcontroller unit in QNAP NAS devices that is + * connected via a dedicated UART port. + * + * Copyright (C) 2024 Heiko Stuebner + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* The longest command found so far is 5 bytes long */ +#define QNAP_MCU_MAX_CMD_SIZE 5 +#define QNAP_MCU_MAX_DATA_SIZE 36 +#define QNAP_MCU_CHECKSUM_SIZE 1 + +#define QNAP_MCU_RX_BUFFER_SIZE \ + (QNAP_MCU_MAX_DATA_SIZE + QNAP_MCU_CHECKSUM_SIZE) + +#define QNAP_MCU_TX_BUFFER_SIZE \ + (QNAP_MCU_MAX_CMD_SIZE + QNAP_MCU_CHECKSUM_SIZE) + +#define QNAP_MCU_ACK_LEN 2 +#define QNAP_MCU_VERSION_LEN 4 + +#define QNAP_MCU_TIMEOUT_MS 500 + +/** + * struct qnap_mcu_reply - Reply to a command + * + * @data: Buffer to store reply payload in + * @length: Expected reply length, including the checksum + * @received: Received number of bytes, so far + * @done: Triggered when the entire reply has been received + */ +struct qnap_mcu_reply { + u8 *data; + size_t length; + size_t received; + struct completion done; +}; + +/** + * struct qnap_mcu - QNAP NAS embedded controller + * + * @serdev: Pointer to underlying serdev + * @bus_lock: Lock to serialize access to the device + * @reply: Reply data structure + * @variant: Device variant specific information + * @version: MCU firmware version + */ +struct qnap_mcu { + struct serdev_device *serdev; + struct mutex bus_lock; + struct qnap_mcu_reply reply; + const struct qnap_mcu_variant *variant; + u8 version[QNAP_MCU_VERSION_LEN]; +}; + +/* + * The QNAP-MCU uses a basic XOR checksum. + * It is always the last byte and XORs the whole previous message. + */ +static u8 qnap_mcu_csum(const u8 *buf, size_t size) +{ + u8 csum = 0; + + while (size--) + csum ^= *buf++; + + return csum; +} + +static int qnap_mcu_write(struct qnap_mcu *mcu, const u8 *data, u8 data_size) +{ + unsigned char tx[QNAP_MCU_TX_BUFFER_SIZE]; + size_t length = data_size + QNAP_MCU_CHECKSUM_SIZE; + + if (length > sizeof(tx)) { + dev_err(&mcu->serdev->dev, "data too big for transmit buffer"); + return -EINVAL; + } + + memcpy(tx, data, data_size); + tx[data_size] = qnap_mcu_csum(data, data_size); + + serdev_device_write_flush(mcu->serdev); + + return serdev_device_write(mcu->serdev, tx, length, HZ); +} + +static size_t qnap_mcu_receive_buf(struct serdev_device *serdev, const u8 *buf, size_t size) +{ + struct device *dev = &serdev->dev; + struct qnap_mcu *mcu = dev_get_drvdata(dev); + struct qnap_mcu_reply *reply = &mcu->reply; + const u8 *src = buf; + const u8 *end = buf + size; + + if (!reply->length) { + dev_warn(dev, "Received %zu bytes, we were not waiting for\n", size); + return size; + } + + while (src < end) { + reply->data[reply->received] = *src++; + reply->received++; + + if (reply->received == reply->length) { + /* We don't expect any characters from the device now */ + reply->length = 0; + + complete(&reply->done); + + /* + * We report the consumed number of bytes. If there + * are still bytes remaining (though there shouldn't) + * the serdev layer will re-execute this handler with + * the remainder of the Rx bytes. + */ + return src - buf; + } + } + + /* + * The only way to get out of the above loop and end up here + * is through consuming all of the supplied data, so here we + * report that we processed it all. + */ + return size; +} + +static const struct serdev_device_ops qnap_mcu_serdev_device_ops = { + .receive_buf = qnap_mcu_receive_buf, + .write_wakeup = serdev_device_write_wakeup, +}; + +int qnap_mcu_exec(struct qnap_mcu *mcu, + const u8 *cmd_data, size_t cmd_data_size, + u8 *reply_data, size_t reply_data_size) +{ + unsigned char rx[QNAP_MCU_RX_BUFFER_SIZE]; + size_t length = reply_data_size + QNAP_MCU_CHECKSUM_SIZE; + struct qnap_mcu_reply *reply = &mcu->reply; + int ret = 0; + + if (length > sizeof(rx)) { + dev_err(&mcu->serdev->dev, "expected data too big for receive buffer"); + return -EINVAL; + } + + mutex_lock(&mcu->bus_lock); + + reply->data = rx, + reply->length = length, + reply->received = 0, + reinit_completion(&reply->done); + + qnap_mcu_write(mcu, cmd_data, cmd_data_size); + + serdev_device_wait_until_sent(mcu->serdev, msecs_to_jiffies(QNAP_MCU_TIMEOUT_MS)); + + if (!wait_for_completion_timeout(&reply->done, msecs_to_jiffies(QNAP_MCU_TIMEOUT_MS))) { + dev_err(&mcu->serdev->dev, "Command timeout\n"); + ret = -ETIMEDOUT; + } else { + u8 crc = qnap_mcu_csum(rx, reply_data_size); + + if (crc != rx[reply_data_size]) { + dev_err(&mcu->serdev->dev, + "Invalid Checksum received\n"); + ret = -EIO; + } else { + memcpy(reply_data, rx, reply_data_size); + } + } + + mutex_unlock(&mcu->bus_lock); + return ret; +} +EXPORT_SYMBOL_GPL(qnap_mcu_exec); + +int qnap_mcu_exec_with_ack(struct qnap_mcu *mcu, + const u8 *cmd_data, size_t cmd_data_size) +{ + u8 ack[QNAP_MCU_ACK_LEN]; + int ret; + + ret = qnap_mcu_exec(mcu, cmd_data, cmd_data_size, ack, sizeof(ack)); + if (ret) + return ret; + + /* Should return @0 */ + if (ack[0] != '@' || ack[1] != '0') { + dev_err(&mcu->serdev->dev, "Did not receive ack\n"); + return -EIO; + } + + return 0; +} +EXPORT_SYMBOL_GPL(qnap_mcu_exec_with_ack); + +static int qnap_mcu_get_version(struct qnap_mcu *mcu) +{ + const u8 cmd[] = { '%', 'V' }; + u8 rx[14]; + int ret; + + /* Reply is the 2 command-bytes + 4 bytes describing the version */ + ret = qnap_mcu_exec(mcu, cmd, sizeof(cmd), rx, QNAP_MCU_VERSION_LEN + 2); + if (ret) + return ret; + + memcpy(mcu->version, &rx[2], QNAP_MCU_VERSION_LEN); + + return 0; +} + +/* + * The MCU controls power to the peripherals but not the CPU. + * + * So using the PMIC to power off the system keeps the MCU and hard-drives + * running. This also then prevents the system from turning back on until + * the MCU is turned off by unplugging the power cable. + * Turning off the MCU alone on the other hand turns off the hard drives, + * LEDs, etc while the main SoC stays running - including its network ports. + */ +static int qnap_mcu_power_off(struct sys_off_data *data) +{ + const u8 cmd[] = { '@', 'C', '0' }; + struct qnap_mcu *mcu = data->cb_data; + int ret; + + ret = qnap_mcu_exec_with_ack(mcu, cmd, sizeof(cmd)); + if (ret) { + dev_err(&mcu->serdev->dev, "MCU poweroff failed %d\n", ret); + return NOTIFY_STOP; + } + + return NOTIFY_DONE; +} + +static const struct qnap_mcu_variant qnap_ts433_mcu = { + .baud_rate = 115200, + .num_drives = 4, + .fan_pwm_min = 51, /* Specified in original model.conf */ + .fan_pwm_max = 255, + .usb_led = true, +}; + +static struct mfd_cell qnap_mcu_cells[] = { + { .name = "qnap-mcu-input", }, + { .name = "qnap-mcu-leds", }, + { .name = "qnap-mcu-hwmon", } +}; + +static int qnap_mcu_probe(struct serdev_device *serdev) +{ + struct device *dev = &serdev->dev; + struct qnap_mcu *mcu; + int ret; + + mcu = devm_kzalloc(dev, sizeof(*mcu), GFP_KERNEL); + if (!mcu) + return -ENOMEM; + + mcu->serdev = serdev; + dev_set_drvdata(dev, mcu); + + mcu->variant = of_device_get_match_data(dev); + if (!mcu->variant) + return -ENODEV; + + mutex_init(&mcu->bus_lock); + init_completion(&mcu->reply.done); + + serdev_device_set_client_ops(serdev, &qnap_mcu_serdev_device_ops); + ret = devm_serdev_device_open(dev, serdev); + if (ret) + return ret; + + serdev_device_set_baudrate(serdev, mcu->variant->baud_rate); + serdev_device_set_flow_control(serdev, false); + + ret = serdev_device_set_parity(serdev, SERDEV_PARITY_NONE); + if (ret) + return dev_err_probe(dev, ret, "Failed to set parity\n"); + + ret = qnap_mcu_get_version(mcu); + if (ret) + return ret; + + ret = devm_register_sys_off_handler(dev, + SYS_OFF_MODE_POWER_OFF_PREPARE, + SYS_OFF_PRIO_DEFAULT, + &qnap_mcu_power_off, mcu); + if (ret) + return dev_err_probe(dev, ret, + "Failed to register poweroff handler\n"); + + for (int i = 0; i < ARRAY_SIZE(qnap_mcu_cells); i++) { + qnap_mcu_cells[i].platform_data = mcu->variant; + qnap_mcu_cells[i].pdata_size = sizeof(*mcu->variant); + } + + ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, qnap_mcu_cells, + ARRAY_SIZE(qnap_mcu_cells), NULL, 0, NULL); + if (ret) + return dev_err_probe(dev, ret, "Failed to add child devices\n"); + + return 0; +} + +static const struct of_device_id qnap_mcu_dt_ids[] = { + { .compatible = "qnap,ts433-mcu", .data = &qnap_ts433_mcu }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, qnap_mcu_dt_ids); + +static struct serdev_device_driver qnap_mcu_drv = { + .probe = qnap_mcu_probe, + .driver = { + .name = "qnap-mcu", + .of_match_table = qnap_mcu_dt_ids, + }, +}; +module_serdev_device_driver(qnap_mcu_drv); + +MODULE_AUTHOR("Heiko Stuebner "); +MODULE_DESCRIPTION("QNAP MCU core driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mfd/stpmic1.c b/drivers/mfd/stpmic1.c index d8a603d95aa6..081827bc0596 100644 --- a/drivers/mfd/stpmic1.c +++ b/drivers/mfd/stpmic1.c @@ -170,11 +170,7 @@ static int stpmic1_probe(struct i2c_client *i2c) return ret; } - ret = devm_register_sys_off_handler(ddata->dev, - SYS_OFF_MODE_POWER_OFF, - SYS_OFF_PRIO_DEFAULT, - stpmic1_power_off, - ddata); + ret = devm_register_power_off_handler(ddata->dev, stpmic1_power_off, ddata); if (ret) { dev_err(ddata->dev, "failed to register sys-off handler: %d\n", ret); return ret; diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c index 3e1d699ba934..226915ca3c93 100644 --- a/drivers/mfd/syscon.c +++ b/drivers/mfd/syscon.c @@ -12,22 +12,16 @@ #include #include #include -#include -#include #include +#include #include #include -#include -#include -#include #include #include #include #include -static struct platform_driver syscon_driver; - -static DEFINE_SPINLOCK(syscon_list_slock); +static DEFINE_MUTEX(syscon_list_lock); static LIST_HEAD(syscon_list); struct syscon { @@ -54,6 +48,8 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_res) struct resource res; struct reset_control *reset; + WARN_ON(!mutex_is_locked(&syscon_list_lock)); + struct syscon *syscon __free(kfree) = kzalloc(sizeof(*syscon), GFP_KERNEL); if (!syscon) return ERR_PTR(-ENOMEM); @@ -146,9 +142,7 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_res) syscon->regmap = regmap; syscon->np = np; - spin_lock(&syscon_list_slock); list_add_tail(&syscon->list, &syscon_list); - spin_unlock(&syscon_list_slock); return_ptr(syscon); @@ -169,7 +163,7 @@ static struct regmap *device_node_get_regmap(struct device_node *np, { struct syscon *entry, *syscon = NULL; - spin_lock(&syscon_list_slock); + mutex_lock(&syscon_list_lock); list_for_each_entry(entry, &syscon_list, list) if (entry->np == np) { @@ -177,10 +171,13 @@ static struct regmap *device_node_get_regmap(struct device_node *np, break; } - spin_unlock(&syscon_list_slock); - - if (!syscon) - syscon = of_syscon_register(np, check_res); + if (!syscon) { + if (of_device_is_compatible(np, "syscon")) + syscon = of_syscon_register(np, check_res); + else + syscon = ERR_PTR(-EINVAL); + } + mutex_unlock(&syscon_list_lock); if (IS_ERR(syscon)) return ERR_CAST(syscon); @@ -212,7 +209,7 @@ int of_syscon_register_regmap(struct device_node *np, struct regmap *regmap) return -ENOMEM; /* check if syscon entry already exists */ - spin_lock(&syscon_list_slock); + mutex_lock(&syscon_list_lock); list_for_each_entry(entry, &syscon_list, list) if (entry->np == np) { @@ -225,12 +222,12 @@ int of_syscon_register_regmap(struct device_node *np, struct regmap *regmap) /* register the regmap in syscon list */ list_add_tail(&syscon->list, &syscon_list); - spin_unlock(&syscon_list_slock); + mutex_unlock(&syscon_list_lock); return 0; err_unlock: - spin_unlock(&syscon_list_slock); + mutex_unlock(&syscon_list_lock); kfree(syscon); return ret; } @@ -244,9 +241,6 @@ EXPORT_SYMBOL_GPL(device_node_to_regmap); struct regmap *syscon_node_to_regmap(struct device_node *np) { - if (!of_device_is_compatible(np, "syscon")) - return ERR_PTR(-EINVAL); - return device_node_get_regmap(np, true); } EXPORT_SYMBOL_GPL(syscon_node_to_regmap); @@ -336,62 +330,3 @@ struct regmap *syscon_regmap_lookup_by_phandle_optional(struct device_node *np, return regmap; } EXPORT_SYMBOL_GPL(syscon_regmap_lookup_by_phandle_optional); - -static int syscon_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct syscon_platform_data *pdata = dev_get_platdata(dev); - struct syscon *syscon; - struct regmap_config syscon_config = syscon_regmap_config; - struct resource *res; - void __iomem *base; - - syscon = devm_kzalloc(dev, sizeof(*syscon), GFP_KERNEL); - if (!syscon) - return -ENOMEM; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENOENT; - - base = devm_ioremap(dev, res->start, resource_size(res)); - if (!base) - return -ENOMEM; - - syscon_config.max_register = resource_size(res) - 4; - if (!syscon_config.max_register) - syscon_config.max_register_is_0 = true; - - if (pdata) - syscon_config.name = pdata->label; - syscon->regmap = devm_regmap_init_mmio(dev, base, &syscon_config); - if (IS_ERR(syscon->regmap)) { - dev_err(dev, "regmap init failed\n"); - return PTR_ERR(syscon->regmap); - } - - platform_set_drvdata(pdev, syscon); - - dev_dbg(dev, "regmap %pR registered\n", res); - - return 0; -} - -static const struct platform_device_id syscon_ids[] = { - { "syscon", }, - { } -}; - -static struct platform_driver syscon_driver = { - .driver = { - .name = "syscon", - }, - .probe = syscon_probe, - .id_table = syscon_ids, -}; - -static int __init syscon_init(void) -{ - return platform_driver_register(&syscon_driver); -} -postcore_initcall(syscon_init); diff --git a/drivers/mfd/tps65219.c b/drivers/mfd/tps65219.c index 57ff5cb294a6..081c5a30b04a 100644 --- a/drivers/mfd/tps65219.c +++ b/drivers/mfd/tps65219.c @@ -110,19 +110,12 @@ static const struct resource tps65219_regulator_resources[] = { }; static const struct mfd_cell tps65219_cells[] = { - { - .name = "tps65219-regulator", - .resources = tps65219_regulator_resources, - .num_resources = ARRAY_SIZE(tps65219_regulator_resources), - }, - { .name = "tps65219-gpio", }, + MFD_CELL_RES("tps65219-regulator", tps65219_regulator_resources), + MFD_CELL_NAME("tps65219-gpio"), }; -static const struct mfd_cell tps65219_pwrbutton_cell = { - .name = "tps65219-pwrbutton", - .resources = tps65219_pwrbutton_resources, - .num_resources = ARRAY_SIZE(tps65219_pwrbutton_resources), -}; +static const struct mfd_cell tps65219_pwrbutton_cell = + MFD_CELL_RES("tps65219-pwrbutton", tps65219_pwrbutton_resources); static const struct regmap_config tps65219_regmap_config = { .reg_bits = 8, diff --git a/drivers/mfd/upboard-fpga.c b/drivers/mfd/upboard-fpga.c new file mode 100644 index 000000000000..5a330e2f2229 --- /dev/null +++ b/drivers/mfd/upboard-fpga.c @@ -0,0 +1,325 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * UP Board FPGA driver. + * + * FPGA provides more GPIO driving power, LEDS and pin mux function. + * + * Copyright (c) AAEON. All rights reserved. + * Copyright (C) 2024 Bootlin + * + * Author: Gary Wang + * Author: Thomas Richard + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define UPBOARD_AAEON_MANUFACTURER_ID 0x01 +#define UPBOARD_MANUFACTURER_ID_MASK GENMASK(7, 0) + +#define UPBOARD_ADDRESS_SIZE 7 +#define UPBOARD_REGISTER_SIZE 16 + +#define UPBOARD_READ_FLAG BIT(UPBOARD_ADDRESS_SIZE) + +#define UPBOARD_FW_ID_MAJOR_SUPPORTED 0x0 + +#define UPBOARD_FW_ID_BUILD_MASK GENMASK(15, 12) +#define UPBOARD_FW_ID_MAJOR_MASK GENMASK(11, 8) +#define UPBOARD_FW_ID_MINOR_MASK GENMASK(7, 4) +#define UPBOARD_FW_ID_PATCH_MASK GENMASK(3, 0) + +static int upboard_fpga_read(void *context, unsigned int reg, unsigned int *val) +{ + struct upboard_fpga *fpga = context; + int i; + + /* Clear to start new transaction */ + gpiod_set_value(fpga->clear_gpio, 0); + gpiod_set_value(fpga->clear_gpio, 1); + + reg |= UPBOARD_READ_FLAG; + + /* Send clock and addr from strobe & datain pins */ + for (i = UPBOARD_ADDRESS_SIZE; i >= 0; i--) { + gpiod_set_value(fpga->strobe_gpio, 0); + gpiod_set_value(fpga->datain_gpio, !!(reg & BIT(i))); + gpiod_set_value(fpga->strobe_gpio, 1); + } + + gpiod_set_value(fpga->strobe_gpio, 0); + *val = 0; + + /* Read data from dataout pin */ + for (i = UPBOARD_REGISTER_SIZE - 1; i >= 0; i--) { + gpiod_set_value(fpga->strobe_gpio, 1); + gpiod_set_value(fpga->strobe_gpio, 0); + *val |= gpiod_get_value(fpga->dataout_gpio) << i; + } + + gpiod_set_value(fpga->strobe_gpio, 1); + + return 0; +} + +static int upboard_fpga_write(void *context, unsigned int reg, unsigned int val) +{ + struct upboard_fpga *fpga = context; + int i; + + /* Clear to start new transcation */ + gpiod_set_value(fpga->clear_gpio, 0); + gpiod_set_value(fpga->clear_gpio, 1); + + /* Send clock and addr from strobe & datain pins */ + for (i = UPBOARD_ADDRESS_SIZE; i >= 0; i--) { + gpiod_set_value(fpga->strobe_gpio, 0); + gpiod_set_value(fpga->datain_gpio, !!(reg & BIT(i))); + gpiod_set_value(fpga->strobe_gpio, 1); + } + + gpiod_set_value(fpga->strobe_gpio, 0); + + /* Write data to datain pin */ + for (i = UPBOARD_REGISTER_SIZE - 1; i >= 0; i--) { + gpiod_set_value(fpga->datain_gpio, !!(val & BIT(i))); + gpiod_set_value(fpga->strobe_gpio, 1); + gpiod_set_value(fpga->strobe_gpio, 0); + } + + gpiod_set_value(fpga->strobe_gpio, 1); + + return 0; +} + +static const struct regmap_range upboard_up_readable_ranges[] = { + regmap_reg_range(UPBOARD_REG_PLATFORM_ID, UPBOARD_REG_FIRMWARE_ID), + regmap_reg_range(UPBOARD_REG_FUNC_EN0, UPBOARD_REG_FUNC_EN0), + regmap_reg_range(UPBOARD_REG_GPIO_EN0, UPBOARD_REG_GPIO_EN1), + regmap_reg_range(UPBOARD_REG_GPIO_DIR0, UPBOARD_REG_GPIO_DIR1), +}; + +static const struct regmap_range upboard_up_writable_ranges[] = { + regmap_reg_range(UPBOARD_REG_FUNC_EN0, UPBOARD_REG_FUNC_EN0), + regmap_reg_range(UPBOARD_REG_GPIO_EN0, UPBOARD_REG_GPIO_EN1), + regmap_reg_range(UPBOARD_REG_GPIO_DIR0, UPBOARD_REG_GPIO_DIR1), +}; + +static const struct regmap_access_table upboard_up_readable_table = { + .yes_ranges = upboard_up_readable_ranges, + .n_yes_ranges = ARRAY_SIZE(upboard_up_readable_ranges), +}; + +static const struct regmap_access_table upboard_up_writable_table = { + .yes_ranges = upboard_up_writable_ranges, + .n_yes_ranges = ARRAY_SIZE(upboard_up_writable_ranges), +}; + +static const struct regmap_config upboard_up_regmap_config = { + .reg_bits = UPBOARD_ADDRESS_SIZE, + .val_bits = UPBOARD_REGISTER_SIZE, + .max_register = UPBOARD_REG_MAX, + .reg_read = upboard_fpga_read, + .reg_write = upboard_fpga_write, + .fast_io = false, + .cache_type = REGCACHE_NONE, + .rd_table = &upboard_up_readable_table, + .wr_table = &upboard_up_writable_table, +}; + +static const struct regmap_range upboard_up2_readable_ranges[] = { + regmap_reg_range(UPBOARD_REG_PLATFORM_ID, UPBOARD_REG_FIRMWARE_ID), + regmap_reg_range(UPBOARD_REG_FUNC_EN0, UPBOARD_REG_FUNC_EN1), + regmap_reg_range(UPBOARD_REG_GPIO_EN0, UPBOARD_REG_GPIO_EN2), + regmap_reg_range(UPBOARD_REG_GPIO_DIR0, UPBOARD_REG_GPIO_DIR2), +}; + +static const struct regmap_range upboard_up2_writable_ranges[] = { + regmap_reg_range(UPBOARD_REG_FUNC_EN0, UPBOARD_REG_FUNC_EN1), + regmap_reg_range(UPBOARD_REG_GPIO_EN0, UPBOARD_REG_GPIO_EN2), + regmap_reg_range(UPBOARD_REG_GPIO_DIR0, UPBOARD_REG_GPIO_DIR2), +}; + +static const struct regmap_access_table upboard_up2_readable_table = { + .yes_ranges = upboard_up2_readable_ranges, + .n_yes_ranges = ARRAY_SIZE(upboard_up2_readable_ranges), +}; + +static const struct regmap_access_table upboard_up2_writable_table = { + .yes_ranges = upboard_up2_writable_ranges, + .n_yes_ranges = ARRAY_SIZE(upboard_up2_writable_ranges), +}; + +static const struct regmap_config upboard_up2_regmap_config = { + .reg_bits = UPBOARD_ADDRESS_SIZE, + .val_bits = UPBOARD_REGISTER_SIZE, + .max_register = UPBOARD_REG_MAX, + .reg_read = upboard_fpga_read, + .reg_write = upboard_fpga_write, + .fast_io = false, + .cache_type = REGCACHE_NONE, + .rd_table = &upboard_up2_readable_table, + .wr_table = &upboard_up2_writable_table, +}; + +static const struct mfd_cell upboard_up_mfd_cells[] = { + { .name = "upboard-pinctrl" }, + { .name = "upboard-leds" }, +}; + +static const struct upboard_fpga_data upboard_up_fpga_data = { + .type = UPBOARD_UP_FPGA, + .regmap_config = &upboard_up_regmap_config, +}; + +static const struct upboard_fpga_data upboard_up2_fpga_data = { + .type = UPBOARD_UP2_FPGA, + .regmap_config = &upboard_up2_regmap_config, +}; + +static int upboard_fpga_gpio_init(struct upboard_fpga *fpga) +{ + fpga->enable_gpio = devm_gpiod_get(fpga->dev, "enable", GPIOD_ASIS); + if (IS_ERR(fpga->enable_gpio)) + return PTR_ERR(fpga->enable_gpio); + + fpga->clear_gpio = devm_gpiod_get(fpga->dev, "clear", GPIOD_OUT_LOW); + if (IS_ERR(fpga->clear_gpio)) + return PTR_ERR(fpga->clear_gpio); + + fpga->strobe_gpio = devm_gpiod_get(fpga->dev, "strobe", GPIOD_OUT_LOW); + if (IS_ERR(fpga->strobe_gpio)) + return PTR_ERR(fpga->strobe_gpio); + + fpga->datain_gpio = devm_gpiod_get(fpga->dev, "datain", GPIOD_OUT_LOW); + if (IS_ERR(fpga->datain_gpio)) + return PTR_ERR(fpga->datain_gpio); + + fpga->dataout_gpio = devm_gpiod_get(fpga->dev, "dataout", GPIOD_IN); + if (IS_ERR(fpga->dataout_gpio)) + return PTR_ERR(fpga->dataout_gpio); + + gpiod_set_value(fpga->enable_gpio, 1); + + return 0; +} + +static int upboard_fpga_get_firmware_version(struct upboard_fpga *fpga) +{ + unsigned int platform_id, manufacturer_id; + int ret; + + if (!fpga) + return -ENOMEM; + + ret = regmap_read(fpga->regmap, UPBOARD_REG_PLATFORM_ID, &platform_id); + if (ret) + return ret; + + manufacturer_id = platform_id & UPBOARD_MANUFACTURER_ID_MASK; + if (manufacturer_id != UPBOARD_AAEON_MANUFACTURER_ID) + return dev_err_probe(fpga->dev, -ENODEV, + "driver not compatible with custom FPGA FW from manufacturer id %#02x.", + manufacturer_id); + + ret = regmap_read(fpga->regmap, UPBOARD_REG_FIRMWARE_ID, &fpga->firmware_version); + if (ret) + return ret; + + if (FIELD_GET(UPBOARD_FW_ID_MAJOR_MASK, fpga->firmware_version) != + UPBOARD_FW_ID_MAJOR_SUPPORTED) + return dev_err_probe(fpga->dev, -ENODEV, + "unsupported FPGA FW v%lu.%lu.%lu build %#02lx", + FIELD_GET(UPBOARD_FW_ID_MAJOR_MASK, fpga->firmware_version), + FIELD_GET(UPBOARD_FW_ID_MINOR_MASK, fpga->firmware_version), + FIELD_GET(UPBOARD_FW_ID_PATCH_MASK, fpga->firmware_version), + FIELD_GET(UPBOARD_FW_ID_BUILD_MASK, fpga->firmware_version)); + return 0; +} + +static ssize_t upboard_fpga_version_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct upboard_fpga *fpga = dev_get_drvdata(dev); + + return sysfs_emit(buf, "FPGA FW v%lu.%lu.%lu build %#02lx\n", + FIELD_GET(UPBOARD_FW_ID_MAJOR_MASK, fpga->firmware_version), + FIELD_GET(UPBOARD_FW_ID_MINOR_MASK, fpga->firmware_version), + FIELD_GET(UPBOARD_FW_ID_PATCH_MASK, fpga->firmware_version), + FIELD_GET(UPBOARD_FW_ID_BUILD_MASK, fpga->firmware_version)); +} + +static DEVICE_ATTR_RO(upboard_fpga_version); + +static struct attribute *upboard_fpga_attrs[] = { + &dev_attr_upboard_fpga_version.attr, + NULL +}; + +ATTRIBUTE_GROUPS(upboard_fpga); + +static int upboard_fpga_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct upboard_fpga *fpga; + int ret; + + fpga = devm_kzalloc(dev, sizeof(*fpga), GFP_KERNEL); + if (!fpga) + return -ENOMEM; + + fpga->fpga_data = device_get_match_data(dev); + + fpga->dev = dev; + + platform_set_drvdata(pdev, fpga); + + fpga->regmap = devm_regmap_init(dev, NULL, fpga, fpga->fpga_data->regmap_config); + if (IS_ERR(fpga->regmap)) + return PTR_ERR(fpga->regmap); + + ret = upboard_fpga_gpio_init(fpga); + if (ret) + return dev_err_probe(dev, ret, "Failed to initialize FPGA common GPIOs"); + + ret = upboard_fpga_get_firmware_version(fpga); + if (ret) + return ret; + + return devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE, upboard_up_mfd_cells, + ARRAY_SIZE(upboard_up_mfd_cells), NULL, 0, NULL); +} + +static const struct acpi_device_id upboard_fpga_acpi_match[] = { + { "AANT0F01", (kernel_ulong_t)&upboard_up2_fpga_data }, + { "AANT0F04", (kernel_ulong_t)&upboard_up_fpga_data }, + {} +}; +MODULE_DEVICE_TABLE(acpi, upboard_fpga_acpi_match); + +static struct platform_driver upboard_fpga_driver = { + .driver = { + .name = "upboard-fpga", + .acpi_match_table = ACPI_PTR(upboard_fpga_acpi_match), + .dev_groups = upboard_fpga_groups, + }, + .probe = upboard_fpga_probe, +}; + +module_platform_driver(upboard_fpga_driver); + +MODULE_AUTHOR("Gary Wang "); +MODULE_AUTHOR("Thomas Richard "); +MODULE_DESCRIPTION("UP Board FPGA driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mfd/vexpress-sysreg.c b/drivers/mfd/vexpress-sysreg.c index d34d58ce46db..ef03d6cec9ff 100644 --- a/drivers/mfd/vexpress-sysreg.c +++ b/drivers/mfd/vexpress-sysreg.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 09cbe3f0ab1e..56bc72c7ce4a 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -517,7 +517,6 @@ config OPEN_DICE config NTSYNC tristate "NT synchronization primitive emulation" - depends on BROKEN help This module provides kernel support for emulation of Windows NT synchronization primitives. It is not a hardware driver. @@ -613,8 +612,7 @@ config MARVELL_CN10K_DPI config MCHP_LAN966X_PCI tristate "Microchip LAN966x PCIe Support" depends on PCI - select OF - select OF_OVERLAY + depends on OF_OVERLAY select IRQ_DOMAIN help This enables the support for the LAN966x PCIe device. diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 40bf953185c7..545aad06d088 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_SENSORS_BH1770) += bh1770glc.o obj-$(CONFIG_SENSORS_APDS990X) += apds990x.o obj-$(CONFIG_ENCLOSURE_SERVICES) += enclosure.o obj-$(CONFIG_KGDB_TESTS) += kgdbts.o +obj-$(CONFIG_TEST_MISC_MINOR) += misc_minor_kunit.o obj-$(CONFIG_SGI_XP) += sgi-xp/ obj-$(CONFIG_SGI_GRU) += sgi-gru/ obj-$(CONFIG_SMPRO_ERRMON) += smpro-errmon.o diff --git a/drivers/misc/c2port/core.c b/drivers/misc/c2port/core.c index 2bb1dd2511f9..fc64474b8241 100644 --- a/drivers/misc/c2port/core.c +++ b/drivers/misc/c2port/core.c @@ -714,7 +714,7 @@ static ssize_t __c2port_read_flash_data(struct c2port_device *dev, } static ssize_t c2port_read_flash_data(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buffer, loff_t offset, size_t count) { struct c2port_device *c2dev = dev_get_drvdata(kobj_to_dev(kobj)); @@ -829,7 +829,7 @@ static ssize_t __c2port_write_flash_data(struct c2port_device *dev, } static ssize_t c2port_write_flash_data(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buffer, loff_t offset, size_t count) { struct c2port_device *c2dev = dev_get_drvdata(kobj_to_dev(kobj)); @@ -849,8 +849,8 @@ static ssize_t c2port_write_flash_data(struct file *filp, struct kobject *kobj, return ret; } /* size is computed at run-time */ -static BIN_ATTR(flash_data, 0644, c2port_read_flash_data, - c2port_write_flash_data, 0); +static const BIN_ATTR(flash_data, 0644, c2port_read_flash_data, + c2port_write_flash_data, 0); /* * Class attributes @@ -869,14 +869,27 @@ static struct attribute *c2port_attrs[] = { NULL, }; -static struct bin_attribute *c2port_bin_attrs[] = { +static const struct bin_attribute *const c2port_bin_attrs[] = { &bin_attr_flash_data, NULL, }; +static size_t c2port_bin_attr_size(struct kobject *kobj, + const struct bin_attribute *attr, + int i) +{ + struct c2port_device *c2dev = dev_get_drvdata(kobj_to_dev(kobj)); + + if (attr == &bin_attr_flash_data) + return c2dev->ops->blocks_num * c2dev->ops->block_size; + + return attr->size; +} + static const struct attribute_group c2port_group = { .attrs = c2port_attrs, - .bin_attrs = c2port_bin_attrs, + .bin_attrs_new = c2port_bin_attrs, + .bin_size = c2port_bin_attr_size, }; static const struct attribute_group *c2port_groups[] = { @@ -912,8 +925,7 @@ struct c2port_device *c2port_device_register(char *name, if (ret < 0) goto error_idr_alloc; c2dev->id = ret; - - bin_attr_flash_data.size = ops->blocks_num * ops->block_size; + c2dev->ops = ops; c2dev->dev = device_create(c2port_class, NULL, 0, c2dev, "c2port%d", c2dev->id); @@ -924,7 +936,6 @@ struct c2port_device *c2port_device_register(char *name, dev_set_drvdata(c2dev->dev, c2dev); strscpy(c2dev->name, name, sizeof(c2dev->name)); - c2dev->ops = ops; mutex_init(&c2dev->mutex); /* By default C2 port access is off */ diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c index 77b0490a1b38..e0174da5e9fc 100644 --- a/drivers/misc/cardreader/rtsx_usb.c +++ b/drivers/misc/cardreader/rtsx_usb.c @@ -286,6 +286,7 @@ static int rtsx_usb_get_status_with_bulk(struct rtsx_ucr *ucr, u16 *status) int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status) { int ret; + u8 interrupt_val = 0; u16 *buf; if (!status) @@ -308,6 +309,20 @@ int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status) ret = rtsx_usb_get_status_with_bulk(ucr, status); } + rtsx_usb_read_register(ucr, CARD_INT_PEND, &interrupt_val); + /* Cross check presence with interrupts */ + if (*status & XD_CD) + if (!(interrupt_val & XD_INT)) + *status &= ~XD_CD; + + if (*status & SD_CD) + if (!(interrupt_val & SD_INT)) + *status &= ~SD_CD; + + if (*status & MS_CD) + if (!(interrupt_val & MS_INT)) + *status &= ~MS_CD; + /* usb_control_msg may return positive when success */ if (ret < 0) return ret; diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig index 5efc4151bf58..15307f5e4307 100644 --- a/drivers/misc/cxl/Kconfig +++ b/drivers/misc/cxl/Kconfig @@ -9,11 +9,13 @@ config CXL_BASE select PPC_64S_HASH_MMU config CXL - tristate "Support for IBM Coherent Accelerators (CXL)" + tristate "Support for IBM Coherent Accelerators (CXL) (DEPRECATED)" depends on PPC_POWERNV && PCI_MSI && EEH select CXL_BASE - default m help + The cxl driver is deprecated and will be removed in a future + kernel release. + Select this option to enable driver support for IBM Coherent Accelerators (CXL). CXL is otherwise known as Coherent Accelerator Processor Interface (CAPI). CAPI allows accelerators in FPGAs to be diff --git a/drivers/misc/cxl/of.c b/drivers/misc/cxl/of.c index cf6bd8a43056..e26ee85279fa 100644 --- a/drivers/misc/cxl/of.c +++ b/drivers/misc/cxl/of.c @@ -295,6 +295,8 @@ int cxl_of_probe(struct platform_device *pdev) int ret; int slice = 0, slice_ok = 0; + dev_err_once(&pdev->dev, "DEPRECATION: cxl is deprecated and will be removed in a future kernel release\n"); + pr_devel("in %s\n", __func__); np = pdev->dev.of_node; diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 3d52f9b92d0d..92bf7c5c7b35 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -1726,6 +1726,8 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id) int slice; int rc; + dev_err_once(&dev->dev, "DEPRECATED: cxl is deprecated and will be removed in a future kernel release\n"); + if (cxl_pci_is_vphb_device(dev)) { dev_dbg(&dev->dev, "cxl_init_adapter: Ignoring cxl vphb device\n"); return -ENODEV; diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c index 409bd1c39663..b1fc6446bd4b 100644 --- a/drivers/misc/cxl/sysfs.c +++ b/drivers/misc/cxl/sysfs.c @@ -444,7 +444,7 @@ static ssize_t api_version_compatible_show(struct device *device, } static ssize_t afu_eb_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct cxl_afu *afu = to_cxl_afu(kobj_to_dev(kobj)); @@ -538,7 +538,7 @@ static ssize_t class_show(struct kobject *kobj, } static ssize_t afu_read_config(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct afu_config_record *cr = to_cr(kobj); @@ -620,7 +620,7 @@ static struct afu_config_record *cxl_sysfs_afu_new_cr(struct cxl_afu *afu, int c cr->config_attr.attr.name = "config"; cr->config_attr.attr.mode = S_IRUSR; cr->config_attr.size = afu->crs_len; - cr->config_attr.read = afu_read_config; + cr->config_attr.read_new = afu_read_config; rc = kobject_init_and_add(&cr->kobj, &afu_config_record_type, &afu->dev.kobj, "cr%i", cr->cr); @@ -693,7 +693,7 @@ int cxl_sysfs_afu_add(struct cxl_afu *afu) afu->attr_eb.attr.name = "afu_err_buff"; afu->attr_eb.attr.mode = S_IRUGO; afu->attr_eb.size = afu->eb_len; - afu->attr_eb.read = afu_eb_read; + afu->attr_eb.read_new = afu_eb_read; rc = device_create_bin_file(&afu->dev, &afu->attr_eb); if (rc) { diff --git a/drivers/misc/ds1682.c b/drivers/misc/ds1682.c index 4175df7ef011..5d5a70a62e98 100644 --- a/drivers/misc/ds1682.c +++ b/drivers/misc/ds1682.c @@ -154,7 +154,7 @@ static const struct attribute_group ds1682_group = { * User data attribute */ static ssize_t ds1682_eeprom_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct i2c_client *client = kobj_to_i2c_client(kobj); @@ -172,7 +172,7 @@ static ssize_t ds1682_eeprom_read(struct file *filp, struct kobject *kobj, } static ssize_t ds1682_eeprom_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct i2c_client *client = kobj_to_i2c_client(kobj); @@ -194,8 +194,8 @@ static const struct bin_attribute ds1682_eeprom_attr = { .mode = S_IRUGO | S_IWUSR, }, .size = DS1682_EEPROM_SIZE, - .read = ds1682_eeprom_read, - .write = ds1682_eeprom_write, + .read_new = ds1682_eeprom_read, + .write_new = ds1682_eeprom_write, }; static int ds1682_nvmem_read(void *priv, unsigned int offset, void *val, diff --git a/drivers/misc/eeprom/idt_89hpesx.c b/drivers/misc/eeprom/idt_89hpesx.c index 43421fe37d33..1fc632ebf22f 100644 --- a/drivers/misc/eeprom/idt_89hpesx.c +++ b/drivers/misc/eeprom/idt_89hpesx.c @@ -847,7 +847,7 @@ err_mutex_unlock: * @count: Number of bytes to write */ static ssize_t eeprom_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct idt_89hpesx_dev *pdev; @@ -871,7 +871,7 @@ static ssize_t eeprom_write(struct file *filp, struct kobject *kobj, * @count: Number of bytes to write */ static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct idt_89hpesx_dev *pdev; @@ -1017,7 +1017,7 @@ static ssize_t idt_dbgfs_csr_read(struct file *filep, char __user *ubuf, * NOTE Size will be changed in compliance with OF node. EEPROM attribute will * be read-only as well if the corresponding flag is specified in OF node. */ -static BIN_ATTR_RW(eeprom, EEPROM_DEF_SIZE); +static const BIN_ATTR_RW(eeprom, EEPROM_DEF_SIZE); /* * csr_dbgfs_ops - CSR debugfs-node read/write operations diff --git a/drivers/misc/eeprom/max6875.c b/drivers/misc/eeprom/max6875.c index 6fab2ffa736b..1c36ad153e78 100644 --- a/drivers/misc/eeprom/max6875.c +++ b/drivers/misc/eeprom/max6875.c @@ -104,7 +104,7 @@ exit_up: } static ssize_t max6875_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct i2c_client *client = kobj_to_i2c_client(kobj); @@ -127,7 +127,7 @@ static const struct bin_attribute user_eeprom_attr = { .mode = S_IRUGO, }, .size = USER_EEPROM_SIZE, - .read = max6875_read, + .read_new = max6875_read, }; static int max6875_probe(struct i2c_client *client) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 48d08eeb2d20..7b7a22c91fe4 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -139,14 +139,14 @@ struct fastrpc_mmap_rsp_msg { }; struct fastrpc_mmap_req_msg { - s32 pgid; + s32 client_id; u32 flags; u64 vaddr; s32 num; }; struct fastrpc_mem_map_req_msg { - s32 pgid; + s32 client_id; s32 fd; s32 offset; u32 flags; @@ -156,20 +156,20 @@ struct fastrpc_mem_map_req_msg { }; struct fastrpc_munmap_req_msg { - s32 pgid; + s32 client_id; u64 vaddr; u64 size; }; struct fastrpc_mem_unmap_req_msg { - s32 pgid; + s32 client_id; s32 fd; u64 vaddrin; u64 len; }; struct fastrpc_msg { - int pid; /* process group id */ + int client_id; /* process client id */ int tid; /* thread id */ u64 ctx; /* invoke caller context */ u32 handle; /* handle to invoke */ @@ -234,7 +234,7 @@ struct fastrpc_invoke_ctx { int nbufs; int retval; int pid; - int tgid; + int client_id; u32 sc; u32 *crc; u64 ctxid; @@ -299,7 +299,7 @@ struct fastrpc_user { struct fastrpc_session_ctx *sctx; struct fastrpc_buf *init_mem; - int tgid; + int client_id; int pd; bool is_secure_dev; /* Lock for lists */ @@ -614,7 +614,7 @@ static struct fastrpc_invoke_ctx *fastrpc_context_alloc( ctx->sc = sc; ctx->retval = -1; ctx->pid = current->pid; - ctx->tgid = user->tgid; + ctx->client_id = user->client_id; ctx->cctx = cctx; init_completion(&ctx->work); INIT_WORK(&ctx->put_work, fastrpc_context_put_wq); @@ -992,7 +992,7 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) mmap_read_lock(current->mm); vma = find_vma(current->mm, ctx->args[i].ptr); if (vma) - pages[i].addr += ctx->args[i].ptr - + pages[i].addr += (ctx->args[i].ptr & PAGE_MASK) - vma->vm_start; mmap_read_unlock(current->mm); @@ -1019,8 +1019,8 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) (pkt_size - rlen); pages[i].addr = pages[i].addr & PAGE_MASK; - pg_start = (args & PAGE_MASK) >> PAGE_SHIFT; - pg_end = ((args + len - 1) & PAGE_MASK) >> PAGE_SHIFT; + pg_start = (rpra[i].buf.pv & PAGE_MASK) >> PAGE_SHIFT; + pg_end = ((rpra[i].buf.pv + len - 1) & PAGE_MASK) >> PAGE_SHIFT; pages[i].size = (pg_end - pg_start + 1) * PAGE_SIZE; args = args + mlen; rlen -= mlen; @@ -1115,11 +1115,11 @@ static int fastrpc_invoke_send(struct fastrpc_session_ctx *sctx, int ret; cctx = fl->cctx; - msg->pid = fl->tgid; + msg->client_id = fl->client_id; msg->tid = current->pid; if (kernel) - msg->pid = 0; + msg->client_id = 0; msg->ctx = ctx->ctxid | fl->pd; msg->handle = handle; @@ -1244,7 +1244,7 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl, int err; bool scm_done = false; struct { - int pgid; + int client_id; u32 namelen; u32 pageslen; } inbuf; @@ -1293,7 +1293,7 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl, } } - inbuf.pgid = fl->tgid; + inbuf.client_id = fl->client_id; inbuf.namelen = init.namelen; inbuf.pageslen = 0; fl->pd = USER_PD; @@ -1363,7 +1363,7 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl, int memlen; int err; struct { - int pgid; + int client_id; u32 namelen; u32 filelen; u32 pageslen; @@ -1395,7 +1395,7 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl, goto err; } - inbuf.pgid = fl->tgid; + inbuf.client_id = fl->client_id; inbuf.namelen = strlen(current->comm) + 1; inbuf.filelen = init.filelen; inbuf.pageslen = 1; @@ -1469,8 +1469,9 @@ err: } static struct fastrpc_session_ctx *fastrpc_session_alloc( - struct fastrpc_channel_ctx *cctx) + struct fastrpc_user *fl) { + struct fastrpc_channel_ctx *cctx = fl->cctx; struct fastrpc_session_ctx *session = NULL; unsigned long flags; int i; @@ -1480,6 +1481,8 @@ static struct fastrpc_session_ctx *fastrpc_session_alloc( if (!cctx->session[i].used && cctx->session[i].valid) { cctx->session[i].used = true; session = &cctx->session[i]; + /* any non-zero ID will work, session_idx + 1 is the simplest one */ + fl->client_id = i + 1; break; } } @@ -1501,12 +1504,12 @@ static void fastrpc_session_free(struct fastrpc_channel_ctx *cctx, static int fastrpc_release_current_dsp_process(struct fastrpc_user *fl) { struct fastrpc_invoke_args args[1]; - int tgid = 0; + int client_id = 0; u32 sc; - tgid = fl->tgid; - args[0].ptr = (u64)(uintptr_t) &tgid; - args[0].length = sizeof(tgid); + client_id = fl->client_id; + args[0].ptr = (u64)(uintptr_t) &client_id; + args[0].length = sizeof(client_id); args[0].fd = -1; sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_RELEASE, 1, 0); @@ -1579,11 +1582,10 @@ static int fastrpc_device_open(struct inode *inode, struct file *filp) INIT_LIST_HEAD(&fl->maps); INIT_LIST_HEAD(&fl->mmaps); INIT_LIST_HEAD(&fl->user); - fl->tgid = current->tgid; fl->cctx = cctx; fl->is_secure_dev = fdevice->secure; - fl->sctx = fastrpc_session_alloc(cctx); + fl->sctx = fastrpc_session_alloc(fl); if (!fl->sctx) { dev_err(&cctx->rpdev->dev, "No session available\n"); mutex_destroy(&fl->mutex); @@ -1647,11 +1649,11 @@ static int fastrpc_dmabuf_alloc(struct fastrpc_user *fl, char __user *argp) static int fastrpc_init_attach(struct fastrpc_user *fl, int pd) { struct fastrpc_invoke_args args[1]; - int tgid = fl->tgid; + int client_id = fl->client_id; u32 sc; - args[0].ptr = (u64)(uintptr_t) &tgid; - args[0].length = sizeof(tgid); + args[0].ptr = (u64)(uintptr_t) &client_id; + args[0].length = sizeof(client_id); args[0].fd = -1; sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_ATTACH, 1, 0); fl->pd = pd; @@ -1803,7 +1805,7 @@ static int fastrpc_req_munmap_impl(struct fastrpc_user *fl, struct fastrpc_buf * int err; u32 sc; - req_msg.pgid = fl->tgid; + req_msg.client_id = fl->client_id; req_msg.size = buf->size; req_msg.vaddr = buf->raddr; @@ -1889,7 +1891,7 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp) return err; } - req_msg.pgid = fl->tgid; + req_msg.client_id = fl->client_id; req_msg.flags = req.flags; req_msg.vaddr = req.vaddrin; req_msg.num = sizeof(pages); @@ -1978,7 +1980,7 @@ static int fastrpc_req_mem_unmap_impl(struct fastrpc_user *fl, struct fastrpc_me return -EINVAL; } - req_msg.pgid = fl->tgid; + req_msg.client_id = fl->client_id; req_msg.len = map->len; req_msg.vaddrin = map->raddr; req_msg.fd = map->fd; @@ -2031,7 +2033,7 @@ static int fastrpc_req_mem_map(struct fastrpc_user *fl, char __user *argp) return err; } - req_msg.pgid = fl->tgid; + req_msg.client_id = fl->client_id; req_msg.fd = req.fd; req_msg.offset = req.offset; req_msg.vaddrin = req.vaddrin; @@ -2344,7 +2346,7 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev) err = fastrpc_device_register(rdev, data, false, domains[domain_id]); if (err) - goto fdev_error; + goto populate_error; break; default: err = -EINVAL; diff --git a/drivers/misc/keba/cp500.c b/drivers/misc/keba/cp500.c index 255d3022dae8..d0c6113dcff3 100644 --- a/drivers/misc/keba/cp500.c +++ b/drivers/misc/keba/cp500.c @@ -126,8 +126,9 @@ static struct cp500_devs cp520_devices = { }; struct cp500_nvmem { - struct nvmem_device *nvmem; + struct nvmem_device *base_nvmem; unsigned int offset; + struct nvmem_device *nvmem; }; struct cp500 { @@ -581,8 +582,8 @@ static int cp500_nvmem_read(void *priv, unsigned int offset, void *val, struct cp500_nvmem *nvmem = priv; int ret; - ret = nvmem_device_read(nvmem->nvmem, nvmem->offset + offset, bytes, - val); + ret = nvmem_device_read(nvmem->base_nvmem, nvmem->offset + offset, + bytes, val); if (ret != bytes) return ret; @@ -595,15 +596,16 @@ static int cp500_nvmem_write(void *priv, unsigned int offset, void *val, struct cp500_nvmem *nvmem = priv; int ret; - ret = nvmem_device_write(nvmem->nvmem, nvmem->offset + offset, bytes, - val); + ret = nvmem_device_write(nvmem->base_nvmem, nvmem->offset + offset, + bytes, val); if (ret != bytes) return ret; return 0; } -static int cp500_nvmem_register(struct cp500 *cp500, struct nvmem_device *nvmem) +static int cp500_nvmem_register(struct cp500 *cp500, + struct nvmem_device *base_nvmem) { struct device *dev = &cp500->pci_dev->dev; struct nvmem_config nvmem_config = {}; @@ -625,27 +627,52 @@ static int cp500_nvmem_register(struct cp500 *cp500, struct nvmem_device *nvmem) nvmem_config.reg_read = cp500_nvmem_read; nvmem_config.reg_write = cp500_nvmem_write; - cp500->nvmem_cpu.nvmem = nvmem; + cp500->nvmem_cpu.base_nvmem = base_nvmem; cp500->nvmem_cpu.offset = CP500_EEPROM_CPU_OFFSET; nvmem_config.name = CP500_EEPROM_CPU_NAME; nvmem_config.size = CP500_EEPROM_CPU_SIZE; nvmem_config.priv = &cp500->nvmem_cpu; - tmp = devm_nvmem_register(dev, &nvmem_config); + tmp = nvmem_register(&nvmem_config); if (IS_ERR(tmp)) return PTR_ERR(tmp); + cp500->nvmem_cpu.nvmem = tmp; - cp500->nvmem_user.nvmem = nvmem; + cp500->nvmem_user.base_nvmem = base_nvmem; cp500->nvmem_user.offset = CP500_EEPROM_USER_OFFSET; nvmem_config.name = CP500_EEPROM_USER_NAME; nvmem_config.size = CP500_EEPROM_USER_SIZE; nvmem_config.priv = &cp500->nvmem_user; - tmp = devm_nvmem_register(dev, &nvmem_config); - if (IS_ERR(tmp)) + tmp = nvmem_register(&nvmem_config); + if (IS_ERR(tmp)) { + nvmem_unregister(cp500->nvmem_cpu.nvmem); + cp500->nvmem_cpu.nvmem = NULL; + return PTR_ERR(tmp); + } + cp500->nvmem_user.nvmem = tmp; return 0; } +static void cp500_nvmem_unregister(struct cp500 *cp500) +{ + int notified; + + if (cp500->nvmem_user.nvmem) { + nvmem_unregister(cp500->nvmem_user.nvmem); + cp500->nvmem_user.nvmem = NULL; + } + if (cp500->nvmem_cpu.nvmem) { + nvmem_unregister(cp500->nvmem_cpu.nvmem); + cp500->nvmem_cpu.nvmem = NULL; + } + + /* CPU and user nvmem use the same base_nvmem, put only once */ + notified = atomic_read(&cp500->nvmem_notified); + if (notified) + nvmem_device_put(cp500->nvmem_cpu.base_nvmem); +} + static int cp500_nvmem_match(struct device *dev, const void *data) { const struct cp500 *cp500 = data; @@ -663,13 +690,6 @@ static int cp500_nvmem_match(struct device *dev, const void *data) return 0; } -static void cp500_devm_nvmem_put(void *data) -{ - struct nvmem_device *nvmem = data; - - nvmem_device_put(nvmem); -} - static int cp500_nvmem(struct notifier_block *nb, unsigned long action, void *data) { @@ -698,10 +718,6 @@ static int cp500_nvmem(struct notifier_block *nb, unsigned long action, return NOTIFY_DONE; } - ret = devm_add_action_or_reset(dev, cp500_devm_nvmem_put, nvmem); - if (ret) - return ret; - ret = cp500_nvmem_register(cp500, nvmem); if (ret) return ret; @@ -932,12 +948,17 @@ static void cp500_remove(struct pci_dev *pci_dev) { struct cp500 *cp500 = pci_get_drvdata(pci_dev); + /* + * unregister CPU and user nvmem and put base_nvmem before parent + * auxiliary device of base_nvmem is unregistered + */ + nvmem_unregister_notifier(&cp500->nvmem_notifier); + cp500_nvmem_unregister(cp500); + cp500_unregister_auxiliary_devs(cp500); cp500_disable(cp500); - nvmem_unregister_notifier(&cp500->nvmem_notifier); - pci_set_drvdata(pci_dev, 0); pci_free_irq_vectors(pci_dev); diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c index e616e3ec2b42..04756302b878 100644 --- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c +++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c @@ -147,8 +147,11 @@ static int pci1xxxx_gpio_set_config(struct gpio_chip *gpio, unsigned int offset, case PIN_CONFIG_DRIVE_OPEN_DRAIN: pci1xxx_assign_bit(priv->reg_base, OPENDRAIN_OFFSET(offset), (offset % 32), true); break; + case PIN_CONFIG_DRIVE_PUSH_PULL: + pci1xxx_assign_bit(priv->reg_base, OPENDRAIN_OFFSET(offset), (offset % 32), false); + break; default: - ret = -EOPNOTSUPP; + ret = -ENOTSUPP; break; } spin_unlock_irqrestore(&priv->lock, flags); @@ -277,7 +280,7 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id) writel(BIT(bit), priv->reg_base + INTR_STATUS_OFFSET(gpiobank)); spin_unlock_irqrestore(&priv->lock, flags); irq = irq_find_mapping(gc->irq.domain, (bit + (gpiobank * 32))); - generic_handle_irq(irq); + handle_nested_irq(irq); } } spin_lock_irqsave(&priv->lock, flags); diff --git a/drivers/misc/misc_minor_kunit.c b/drivers/misc/misc_minor_kunit.c new file mode 100644 index 000000000000..293e0fb7e43e --- /dev/null +++ b/drivers/misc/misc_minor_kunit.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +/* dynamic minor (2) */ +static struct miscdevice dev_dynamic_minor = { + .minor = 2, + .name = "dev_dynamic_minor", +}; + +/* static minor (LCD_MINOR) */ +static struct miscdevice dev_static_minor = { + .minor = LCD_MINOR, + .name = "dev_static_minor", +}; + +/* misc dynamic minor */ +static struct miscdevice dev_misc_dynamic_minor = { + .minor = MISC_DYNAMIC_MINOR, + .name = "dev_misc_dynamic_minor", +}; + +static void kunit_dynamic_minor(struct kunit *test) +{ + int ret; + + ret = misc_register(&dev_dynamic_minor); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 2, dev_dynamic_minor.minor); + misc_deregister(&dev_dynamic_minor); +} + +static void kunit_static_minor(struct kunit *test) +{ + int ret; + + ret = misc_register(&dev_static_minor); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, LCD_MINOR, dev_static_minor.minor); + misc_deregister(&dev_static_minor); +} + +static void kunit_misc_dynamic_minor(struct kunit *test) +{ + int ret; + + ret = misc_register(&dev_misc_dynamic_minor); + KUNIT_EXPECT_EQ(test, 0, ret); + misc_deregister(&dev_misc_dynamic_minor); +} + +static struct kunit_case test_cases[] = { + KUNIT_CASE(kunit_dynamic_minor), + KUNIT_CASE(kunit_static_minor), + KUNIT_CASE(kunit_misc_dynamic_minor), + {} +}; + +static struct kunit_suite test_suite = { + .name = "misc_minor_test", + .test_cases = test_cases, +}; +kunit_test_suite(test_suite); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Vimal Agrawal"); +MODULE_DESCRIPTION("misc minor testing"); diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index 4954553b7baa..055395cde42b 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -6,11 +6,17 @@ */ #include +#include #include #include +#include +#include #include #include +#include #include +#include +#include #include #include #include @@ -19,6 +25,8 @@ enum ntsync_type { NTSYNC_TYPE_SEM, + NTSYNC_TYPE_MUTEX, + NTSYNC_TYPE_EVENT, }; /* @@ -30,10 +38,13 @@ enum ntsync_type { * * Both rely on struct file for reference counting. Individual * ntsync_obj objects take a reference to the device when created. + * Wait operations take a reference to each object being waited on for + * the duration of the wait. */ struct ntsync_obj { spinlock_t lock; + int dev_locked; enum ntsync_type type; @@ -46,22 +57,344 @@ struct ntsync_obj { __u32 count; __u32 max; } sem; + struct { + __u32 count; + pid_t owner; + bool ownerdead; + } mutex; + struct { + bool manual; + bool signaled; + } event; } u; + + /* + * any_waiters is protected by the object lock, but all_waiters is + * protected by the device wait_all_lock. + */ + struct list_head any_waiters; + struct list_head all_waiters; + + /* + * Hint describing how many tasks are queued on this object in a + * wait-all operation. + * + * Any time we do a wake, we may need to wake "all" waiters as well as + * "any" waiters. In order to atomically wake "all" waiters, we must + * lock all of the objects, and that means grabbing the wait_all_lock + * below (and, due to lock ordering rules, before locking this object). + * However, wait-all is a rare operation, and grabbing the wait-all + * lock for every wake would create unnecessary contention. + * Therefore we first check whether all_hint is zero, and, if it is, + * we skip trying to wake "all" waiters. + * + * Since wait requests must originate from user-space threads, we're + * limited here by PID_MAX_LIMIT, so there's no risk of overflow. + */ + atomic_t all_hint; +}; + +struct ntsync_q_entry { + struct list_head node; + struct ntsync_q *q; + struct ntsync_obj *obj; + __u32 index; +}; + +struct ntsync_q { + struct task_struct *task; + __u32 owner; + + /* + * Protected via atomic_try_cmpxchg(). Only the thread that wins the + * compare-and-swap may actually change object states and wake this + * task. + */ + atomic_t signaled; + + bool all; + bool ownerdead; + __u32 count; + struct ntsync_q_entry entries[]; }; struct ntsync_device { + /* + * Wait-all operations must atomically grab all objects, and be totally + * ordered with respect to each other and wait-any operations. + * If one thread is trying to acquire several objects, another thread + * cannot touch the object at the same time. + * + * This device-wide lock is used to serialize wait-for-all + * operations, and operations on an object that is involved in a + * wait-for-all. + */ + struct mutex wait_all_lock; + struct file *file; }; +/* + * Single objects are locked using obj->lock. + * + * Multiple objects are 'locked' while holding dev->wait_all_lock. + * In this case however, individual objects are not locked by holding + * obj->lock, but by setting obj->dev_locked. + * + * This means that in order to lock a single object, the sequence is slightly + * more complicated than usual. Specifically it needs to check obj->dev_locked + * after acquiring obj->lock, if set, it needs to drop the lock and acquire + * dev->wait_all_lock in order to serialize against the multi-object operation. + */ + +static void dev_lock_obj(struct ntsync_device *dev, struct ntsync_obj *obj) +{ + lockdep_assert_held(&dev->wait_all_lock); + lockdep_assert(obj->dev == dev); + spin_lock(&obj->lock); + /* + * By setting obj->dev_locked inside obj->lock, it is ensured that + * anyone holding obj->lock must see the value. + */ + obj->dev_locked = 1; + spin_unlock(&obj->lock); +} + +static void dev_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj) +{ + lockdep_assert_held(&dev->wait_all_lock); + lockdep_assert(obj->dev == dev); + spin_lock(&obj->lock); + obj->dev_locked = 0; + spin_unlock(&obj->lock); +} + +static void obj_lock(struct ntsync_obj *obj) +{ + struct ntsync_device *dev = obj->dev; + + for (;;) { + spin_lock(&obj->lock); + if (likely(!obj->dev_locked)) + break; + + spin_unlock(&obj->lock); + mutex_lock(&dev->wait_all_lock); + spin_lock(&obj->lock); + /* + * obj->dev_locked should be set and released under the same + * wait_all_lock section, since we now own this lock, it should + * be clear. + */ + lockdep_assert(!obj->dev_locked); + spin_unlock(&obj->lock); + mutex_unlock(&dev->wait_all_lock); + } +} + +static void obj_unlock(struct ntsync_obj *obj) +{ + spin_unlock(&obj->lock); +} + +static bool ntsync_lock_obj(struct ntsync_device *dev, struct ntsync_obj *obj) +{ + bool all; + + obj_lock(obj); + all = atomic_read(&obj->all_hint); + if (unlikely(all)) { + obj_unlock(obj); + mutex_lock(&dev->wait_all_lock); + dev_lock_obj(dev, obj); + } + + return all; +} + +static void ntsync_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj, bool all) +{ + if (all) { + dev_unlock_obj(dev, obj); + mutex_unlock(&dev->wait_all_lock); + } else { + obj_unlock(obj); + } +} + +#define ntsync_assert_held(obj) \ + lockdep_assert((lockdep_is_held(&(obj)->lock) != LOCK_STATE_NOT_HELD) || \ + ((lockdep_is_held(&(obj)->dev->wait_all_lock) != LOCK_STATE_NOT_HELD) && \ + (obj)->dev_locked)) + +static bool is_signaled(struct ntsync_obj *obj, __u32 owner) +{ + ntsync_assert_held(obj); + + switch (obj->type) { + case NTSYNC_TYPE_SEM: + return !!obj->u.sem.count; + case NTSYNC_TYPE_MUTEX: + if (obj->u.mutex.owner && obj->u.mutex.owner != owner) + return false; + return obj->u.mutex.count < UINT_MAX; + case NTSYNC_TYPE_EVENT: + return obj->u.event.signaled; + } + + WARN(1, "bad object type %#x\n", obj->type); + return false; +} + +/* + * "locked_obj" is an optional pointer to an object which is already locked and + * should not be locked again. This is necessary so that changing an object's + * state and waking it can be a single atomic operation. + */ +static void try_wake_all(struct ntsync_device *dev, struct ntsync_q *q, + struct ntsync_obj *locked_obj) +{ + __u32 count = q->count; + bool can_wake = true; + int signaled = -1; + __u32 i; + + lockdep_assert_held(&dev->wait_all_lock); + if (locked_obj) + lockdep_assert(locked_obj->dev_locked); + + for (i = 0; i < count; i++) { + if (q->entries[i].obj != locked_obj) + dev_lock_obj(dev, q->entries[i].obj); + } + + for (i = 0; i < count; i++) { + if (!is_signaled(q->entries[i].obj, q->owner)) { + can_wake = false; + break; + } + } + + if (can_wake && atomic_try_cmpxchg(&q->signaled, &signaled, 0)) { + for (i = 0; i < count; i++) { + struct ntsync_obj *obj = q->entries[i].obj; + + switch (obj->type) { + case NTSYNC_TYPE_SEM: + obj->u.sem.count--; + break; + case NTSYNC_TYPE_MUTEX: + if (obj->u.mutex.ownerdead) + q->ownerdead = true; + obj->u.mutex.ownerdead = false; + obj->u.mutex.count++; + obj->u.mutex.owner = q->owner; + break; + case NTSYNC_TYPE_EVENT: + if (!obj->u.event.manual) + obj->u.event.signaled = false; + break; + } + } + wake_up_process(q->task); + } + + for (i = 0; i < count; i++) { + if (q->entries[i].obj != locked_obj) + dev_unlock_obj(dev, q->entries[i].obj); + } +} + +static void try_wake_all_obj(struct ntsync_device *dev, struct ntsync_obj *obj) +{ + struct ntsync_q_entry *entry; + + lockdep_assert_held(&dev->wait_all_lock); + lockdep_assert(obj->dev_locked); + + list_for_each_entry(entry, &obj->all_waiters, node) + try_wake_all(dev, entry->q, obj); +} + +static void try_wake_any_sem(struct ntsync_obj *sem) +{ + struct ntsync_q_entry *entry; + + ntsync_assert_held(sem); + lockdep_assert(sem->type == NTSYNC_TYPE_SEM); + + list_for_each_entry(entry, &sem->any_waiters, node) { + struct ntsync_q *q = entry->q; + int signaled = -1; + + if (!sem->u.sem.count) + break; + + if (atomic_try_cmpxchg(&q->signaled, &signaled, entry->index)) { + sem->u.sem.count--; + wake_up_process(q->task); + } + } +} + +static void try_wake_any_mutex(struct ntsync_obj *mutex) +{ + struct ntsync_q_entry *entry; + + ntsync_assert_held(mutex); + lockdep_assert(mutex->type == NTSYNC_TYPE_MUTEX); + + list_for_each_entry(entry, &mutex->any_waiters, node) { + struct ntsync_q *q = entry->q; + int signaled = -1; + + if (mutex->u.mutex.count == UINT_MAX) + break; + if (mutex->u.mutex.owner && mutex->u.mutex.owner != q->owner) + continue; + + if (atomic_try_cmpxchg(&q->signaled, &signaled, entry->index)) { + if (mutex->u.mutex.ownerdead) + q->ownerdead = true; + mutex->u.mutex.ownerdead = false; + mutex->u.mutex.count++; + mutex->u.mutex.owner = q->owner; + wake_up_process(q->task); + } + } +} + +static void try_wake_any_event(struct ntsync_obj *event) +{ + struct ntsync_q_entry *entry; + + ntsync_assert_held(event); + lockdep_assert(event->type == NTSYNC_TYPE_EVENT); + + list_for_each_entry(entry, &event->any_waiters, node) { + struct ntsync_q *q = entry->q; + int signaled = -1; + + if (!event->u.event.signaled) + break; + + if (atomic_try_cmpxchg(&q->signaled, &signaled, entry->index)) { + if (!event->u.event.manual) + event->u.event.signaled = false; + wake_up_process(q->task); + } + } +} + /* * Actually change the semaphore state, returning -EOVERFLOW if it is made * invalid. */ -static int post_sem_state(struct ntsync_obj *sem, __u32 count) +static int release_sem_state(struct ntsync_obj *sem, __u32 count) { __u32 sum; - lockdep_assert_held(&sem->lock); + ntsync_assert_held(sem); if (check_add_overflow(sem->u.sem.count, count, &sum) || sum > sem->u.sem.max) @@ -71,11 +404,13 @@ static int post_sem_state(struct ntsync_obj *sem, __u32 count) return 0; } -static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp) +static int ntsync_sem_release(struct ntsync_obj *sem, void __user *argp) { + struct ntsync_device *dev = sem->dev; __u32 __user *user_args = argp; __u32 prev_count; __u32 args; + bool all; int ret; if (copy_from_user(&args, argp, sizeof(args))) @@ -84,12 +419,17 @@ static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp) if (sem->type != NTSYNC_TYPE_SEM) return -EINVAL; - spin_lock(&sem->lock); + all = ntsync_lock_obj(dev, sem); prev_count = sem->u.sem.count; - ret = post_sem_state(sem, args); + ret = release_sem_state(sem, args); + if (!ret) { + if (all) + try_wake_all_obj(dev, sem); + try_wake_any_sem(sem); + } - spin_unlock(&sem->lock); + ntsync_unlock_obj(dev, sem, all); if (!ret && put_user(prev_count, user_args)) ret = -EFAULT; @@ -97,13 +437,229 @@ static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp) return ret; } -static int ntsync_obj_release(struct inode *inode, struct file *file) +/* + * Actually change the mutex state, returning -EPERM if not the owner. + */ +static int unlock_mutex_state(struct ntsync_obj *mutex, + const struct ntsync_mutex_args *args) { - struct ntsync_obj *obj = file->private_data; + ntsync_assert_held(mutex); + if (mutex->u.mutex.owner != args->owner) + return -EPERM; + + if (!--mutex->u.mutex.count) + mutex->u.mutex.owner = 0; + return 0; +} + +static int ntsync_mutex_unlock(struct ntsync_obj *mutex, void __user *argp) +{ + struct ntsync_mutex_args __user *user_args = argp; + struct ntsync_device *dev = mutex->dev; + struct ntsync_mutex_args args; + __u32 prev_count; + bool all; + int ret; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + if (!args.owner) + return -EINVAL; + + if (mutex->type != NTSYNC_TYPE_MUTEX) + return -EINVAL; + + all = ntsync_lock_obj(dev, mutex); + + prev_count = mutex->u.mutex.count; + ret = unlock_mutex_state(mutex, &args); + if (!ret) { + if (all) + try_wake_all_obj(dev, mutex); + try_wake_any_mutex(mutex); + } + + ntsync_unlock_obj(dev, mutex, all); + + if (!ret && put_user(prev_count, &user_args->count)) + ret = -EFAULT; + + return ret; +} + +/* + * Actually change the mutex state to mark its owner as dead, + * returning -EPERM if not the owner. + */ +static int kill_mutex_state(struct ntsync_obj *mutex, __u32 owner) +{ + ntsync_assert_held(mutex); + + if (mutex->u.mutex.owner != owner) + return -EPERM; + + mutex->u.mutex.ownerdead = true; + mutex->u.mutex.owner = 0; + mutex->u.mutex.count = 0; + return 0; +} + +static int ntsync_mutex_kill(struct ntsync_obj *mutex, void __user *argp) +{ + struct ntsync_device *dev = mutex->dev; + __u32 owner; + bool all; + int ret; + + if (get_user(owner, (__u32 __user *)argp)) + return -EFAULT; + if (!owner) + return -EINVAL; + + if (mutex->type != NTSYNC_TYPE_MUTEX) + return -EINVAL; + + all = ntsync_lock_obj(dev, mutex); + + ret = kill_mutex_state(mutex, owner); + if (!ret) { + if (all) + try_wake_all_obj(dev, mutex); + try_wake_any_mutex(mutex); + } + + ntsync_unlock_obj(dev, mutex, all); + + return ret; +} + +static int ntsync_event_set(struct ntsync_obj *event, void __user *argp, bool pulse) +{ + struct ntsync_device *dev = event->dev; + __u32 prev_state; + bool all; + + if (event->type != NTSYNC_TYPE_EVENT) + return -EINVAL; + + all = ntsync_lock_obj(dev, event); + + prev_state = event->u.event.signaled; + event->u.event.signaled = true; + if (all) + try_wake_all_obj(dev, event); + try_wake_any_event(event); + if (pulse) + event->u.event.signaled = false; + + ntsync_unlock_obj(dev, event, all); + + if (put_user(prev_state, (__u32 __user *)argp)) + return -EFAULT; + + return 0; +} + +static int ntsync_event_reset(struct ntsync_obj *event, void __user *argp) +{ + struct ntsync_device *dev = event->dev; + __u32 prev_state; + bool all; + + if (event->type != NTSYNC_TYPE_EVENT) + return -EINVAL; + + all = ntsync_lock_obj(dev, event); + + prev_state = event->u.event.signaled; + event->u.event.signaled = false; + + ntsync_unlock_obj(dev, event, all); + + if (put_user(prev_state, (__u32 __user *)argp)) + return -EFAULT; + + return 0; +} + +static int ntsync_sem_read(struct ntsync_obj *sem, void __user *argp) +{ + struct ntsync_sem_args __user *user_args = argp; + struct ntsync_device *dev = sem->dev; + struct ntsync_sem_args args; + bool all; + + if (sem->type != NTSYNC_TYPE_SEM) + return -EINVAL; + + all = ntsync_lock_obj(dev, sem); + + args.count = sem->u.sem.count; + args.max = sem->u.sem.max; + + ntsync_unlock_obj(dev, sem, all); + + if (copy_to_user(user_args, &args, sizeof(args))) + return -EFAULT; + return 0; +} + +static int ntsync_mutex_read(struct ntsync_obj *mutex, void __user *argp) +{ + struct ntsync_mutex_args __user *user_args = argp; + struct ntsync_device *dev = mutex->dev; + struct ntsync_mutex_args args; + bool all; + int ret; + + if (mutex->type != NTSYNC_TYPE_MUTEX) + return -EINVAL; + + all = ntsync_lock_obj(dev, mutex); + + args.count = mutex->u.mutex.count; + args.owner = mutex->u.mutex.owner; + ret = mutex->u.mutex.ownerdead ? -EOWNERDEAD : 0; + + ntsync_unlock_obj(dev, mutex, all); + + if (copy_to_user(user_args, &args, sizeof(args))) + return -EFAULT; + return ret; +} + +static int ntsync_event_read(struct ntsync_obj *event, void __user *argp) +{ + struct ntsync_event_args __user *user_args = argp; + struct ntsync_device *dev = event->dev; + struct ntsync_event_args args; + bool all; + + if (event->type != NTSYNC_TYPE_EVENT) + return -EINVAL; + + all = ntsync_lock_obj(dev, event); + + args.manual = event->u.event.manual; + args.signaled = event->u.event.signaled; + + ntsync_unlock_obj(dev, event, all); + + if (copy_to_user(user_args, &args, sizeof(args))) + return -EFAULT; + return 0; +} + +static void ntsync_free_obj(struct ntsync_obj *obj) +{ fput(obj->dev->file); kfree(obj); +} +static int ntsync_obj_release(struct inode *inode, struct file *file) +{ + ntsync_free_obj(file->private_data); return 0; } @@ -114,8 +670,24 @@ static long ntsync_obj_ioctl(struct file *file, unsigned int cmd, void __user *argp = (void __user *)parm; switch (cmd) { - case NTSYNC_IOC_SEM_POST: - return ntsync_sem_post(obj, argp); + case NTSYNC_IOC_SEM_RELEASE: + return ntsync_sem_release(obj, argp); + case NTSYNC_IOC_SEM_READ: + return ntsync_sem_read(obj, argp); + case NTSYNC_IOC_MUTEX_UNLOCK: + return ntsync_mutex_unlock(obj, argp); + case NTSYNC_IOC_MUTEX_KILL: + return ntsync_mutex_kill(obj, argp); + case NTSYNC_IOC_MUTEX_READ: + return ntsync_mutex_read(obj, argp); + case NTSYNC_IOC_EVENT_SET: + return ntsync_event_set(obj, argp, false); + case NTSYNC_IOC_EVENT_RESET: + return ntsync_event_reset(obj, argp); + case NTSYNC_IOC_EVENT_PULSE: + return ntsync_event_set(obj, argp, true); + case NTSYNC_IOC_EVENT_READ: + return ntsync_event_read(obj, argp); default: return -ENOIOCTLCMD; } @@ -140,6 +712,9 @@ static struct ntsync_obj *ntsync_alloc_obj(struct ntsync_device *dev, obj->dev = dev; get_file(dev->file); spin_lock_init(&obj->lock); + INIT_LIST_HEAD(&obj->any_waiters); + INIT_LIST_HEAD(&obj->all_waiters); + atomic_set(&obj->all_hint, 0); return obj; } @@ -165,7 +740,6 @@ static int ntsync_obj_get_fd(struct ntsync_obj *obj) static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp) { - struct ntsync_sem_args __user *user_args = argp; struct ntsync_sem_args args; struct ntsync_obj *sem; int fd; @@ -182,12 +756,398 @@ static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp) sem->u.sem.count = args.count; sem->u.sem.max = args.max; fd = ntsync_obj_get_fd(sem); - if (fd < 0) { - kfree(sem); - return fd; + if (fd < 0) + ntsync_free_obj(sem); + + return fd; +} + +static int ntsync_create_mutex(struct ntsync_device *dev, void __user *argp) +{ + struct ntsync_mutex_args args; + struct ntsync_obj *mutex; + int fd; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + if (!args.owner != !args.count) + return -EINVAL; + + mutex = ntsync_alloc_obj(dev, NTSYNC_TYPE_MUTEX); + if (!mutex) + return -ENOMEM; + mutex->u.mutex.count = args.count; + mutex->u.mutex.owner = args.owner; + fd = ntsync_obj_get_fd(mutex); + if (fd < 0) + ntsync_free_obj(mutex); + + return fd; +} + +static int ntsync_create_event(struct ntsync_device *dev, void __user *argp) +{ + struct ntsync_event_args args; + struct ntsync_obj *event; + int fd; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + event = ntsync_alloc_obj(dev, NTSYNC_TYPE_EVENT); + if (!event) + return -ENOMEM; + event->u.event.manual = args.manual; + event->u.event.signaled = args.signaled; + fd = ntsync_obj_get_fd(event); + if (fd < 0) + ntsync_free_obj(event); + + return fd; +} + +static struct ntsync_obj *get_obj(struct ntsync_device *dev, int fd) +{ + struct file *file = fget(fd); + struct ntsync_obj *obj; + + if (!file) + return NULL; + + if (file->f_op != &ntsync_obj_fops) { + fput(file); + return NULL; } - return put_user(fd, &user_args->sem); + obj = file->private_data; + if (obj->dev != dev) { + fput(file); + return NULL; + } + + return obj; +} + +static void put_obj(struct ntsync_obj *obj) +{ + fput(obj->file); +} + +static int ntsync_schedule(const struct ntsync_q *q, const struct ntsync_wait_args *args) +{ + ktime_t timeout = ns_to_ktime(args->timeout); + clockid_t clock = CLOCK_MONOTONIC; + ktime_t *timeout_ptr; + int ret = 0; + + timeout_ptr = (args->timeout == U64_MAX ? NULL : &timeout); + + if (args->flags & NTSYNC_WAIT_REALTIME) + clock = CLOCK_REALTIME; + + do { + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + + set_current_state(TASK_INTERRUPTIBLE); + if (atomic_read(&q->signaled) != -1) { + ret = 0; + break; + } + ret = schedule_hrtimeout_range_clock(timeout_ptr, 0, HRTIMER_MODE_ABS, clock); + } while (ret < 0); + __set_current_state(TASK_RUNNING); + + return ret; +} + +/* + * Allocate and initialize the ntsync_q structure, but do not queue us yet. + */ +static int setup_wait(struct ntsync_device *dev, + const struct ntsync_wait_args *args, bool all, + struct ntsync_q **ret_q) +{ + int fds[NTSYNC_MAX_WAIT_COUNT + 1]; + const __u32 count = args->count; + struct ntsync_q *q; + __u32 total_count; + __u32 i, j; + + if (args->pad || (args->flags & ~NTSYNC_WAIT_REALTIME)) + return -EINVAL; + + if (args->count > NTSYNC_MAX_WAIT_COUNT) + return -EINVAL; + + total_count = count; + if (args->alert) + total_count++; + + if (copy_from_user(fds, u64_to_user_ptr(args->objs), + array_size(count, sizeof(*fds)))) + return -EFAULT; + if (args->alert) + fds[count] = args->alert; + + q = kmalloc(struct_size(q, entries, total_count), GFP_KERNEL); + if (!q) + return -ENOMEM; + q->task = current; + q->owner = args->owner; + atomic_set(&q->signaled, -1); + q->all = all; + q->ownerdead = false; + q->count = count; + + for (i = 0; i < total_count; i++) { + struct ntsync_q_entry *entry = &q->entries[i]; + struct ntsync_obj *obj = get_obj(dev, fds[i]); + + if (!obj) + goto err; + + if (all) { + /* Check that the objects are all distinct. */ + for (j = 0; j < i; j++) { + if (obj == q->entries[j].obj) { + put_obj(obj); + goto err; + } + } + } + + entry->obj = obj; + entry->q = q; + entry->index = i; + } + + *ret_q = q; + return 0; + +err: + for (j = 0; j < i; j++) + put_obj(q->entries[j].obj); + kfree(q); + return -EINVAL; +} + +static void try_wake_any_obj(struct ntsync_obj *obj) +{ + switch (obj->type) { + case NTSYNC_TYPE_SEM: + try_wake_any_sem(obj); + break; + case NTSYNC_TYPE_MUTEX: + try_wake_any_mutex(obj); + break; + case NTSYNC_TYPE_EVENT: + try_wake_any_event(obj); + break; + } +} + +static int ntsync_wait_any(struct ntsync_device *dev, void __user *argp) +{ + struct ntsync_wait_args args; + __u32 i, total_count; + struct ntsync_q *q; + int signaled; + bool all; + int ret; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + ret = setup_wait(dev, &args, false, &q); + if (ret < 0) + return ret; + + total_count = args.count; + if (args.alert) + total_count++; + + /* queue ourselves */ + + for (i = 0; i < total_count; i++) { + struct ntsync_q_entry *entry = &q->entries[i]; + struct ntsync_obj *obj = entry->obj; + + all = ntsync_lock_obj(dev, obj); + list_add_tail(&entry->node, &obj->any_waiters); + ntsync_unlock_obj(dev, obj, all); + } + + /* + * Check if we are already signaled. + * + * Note that the API requires that normal objects are checked before + * the alert event. Hence we queue the alert event last, and check + * objects in order. + */ + + for (i = 0; i < total_count; i++) { + struct ntsync_obj *obj = q->entries[i].obj; + + if (atomic_read(&q->signaled) != -1) + break; + + all = ntsync_lock_obj(dev, obj); + try_wake_any_obj(obj); + ntsync_unlock_obj(dev, obj, all); + } + + /* sleep */ + + ret = ntsync_schedule(q, &args); + + /* and finally, unqueue */ + + for (i = 0; i < total_count; i++) { + struct ntsync_q_entry *entry = &q->entries[i]; + struct ntsync_obj *obj = entry->obj; + + all = ntsync_lock_obj(dev, obj); + list_del(&entry->node); + ntsync_unlock_obj(dev, obj, all); + + put_obj(obj); + } + + signaled = atomic_read(&q->signaled); + if (signaled != -1) { + struct ntsync_wait_args __user *user_args = argp; + + /* even if we caught a signal, we need to communicate success */ + ret = q->ownerdead ? -EOWNERDEAD : 0; + + if (put_user(signaled, &user_args->index)) + ret = -EFAULT; + } else if (!ret) { + ret = -ETIMEDOUT; + } + + kfree(q); + return ret; +} + +static int ntsync_wait_all(struct ntsync_device *dev, void __user *argp) +{ + struct ntsync_wait_args args; + struct ntsync_q *q; + int signaled; + __u32 i; + int ret; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + ret = setup_wait(dev, &args, true, &q); + if (ret < 0) + return ret; + + /* queue ourselves */ + + mutex_lock(&dev->wait_all_lock); + + for (i = 0; i < args.count; i++) { + struct ntsync_q_entry *entry = &q->entries[i]; + struct ntsync_obj *obj = entry->obj; + + atomic_inc(&obj->all_hint); + + /* + * obj->all_waiters is protected by dev->wait_all_lock rather + * than obj->lock, so there is no need to acquire obj->lock + * here. + */ + list_add_tail(&entry->node, &obj->all_waiters); + } + if (args.alert) { + struct ntsync_q_entry *entry = &q->entries[args.count]; + struct ntsync_obj *obj = entry->obj; + + dev_lock_obj(dev, obj); + list_add_tail(&entry->node, &obj->any_waiters); + dev_unlock_obj(dev, obj); + } + + /* check if we are already signaled */ + + try_wake_all(dev, q, NULL); + + mutex_unlock(&dev->wait_all_lock); + + /* + * Check if the alert event is signaled, making sure to do so only + * after checking if the other objects are signaled. + */ + + if (args.alert) { + struct ntsync_obj *obj = q->entries[args.count].obj; + + if (atomic_read(&q->signaled) == -1) { + bool all = ntsync_lock_obj(dev, obj); + try_wake_any_obj(obj); + ntsync_unlock_obj(dev, obj, all); + } + } + + /* sleep */ + + ret = ntsync_schedule(q, &args); + + /* and finally, unqueue */ + + mutex_lock(&dev->wait_all_lock); + + for (i = 0; i < args.count; i++) { + struct ntsync_q_entry *entry = &q->entries[i]; + struct ntsync_obj *obj = entry->obj; + + /* + * obj->all_waiters is protected by dev->wait_all_lock rather + * than obj->lock, so there is no need to acquire it here. + */ + list_del(&entry->node); + + atomic_dec(&obj->all_hint); + + put_obj(obj); + } + + mutex_unlock(&dev->wait_all_lock); + + if (args.alert) { + struct ntsync_q_entry *entry = &q->entries[args.count]; + struct ntsync_obj *obj = entry->obj; + bool all; + + all = ntsync_lock_obj(dev, obj); + list_del(&entry->node); + ntsync_unlock_obj(dev, obj, all); + + put_obj(obj); + } + + signaled = atomic_read(&q->signaled); + if (signaled != -1) { + struct ntsync_wait_args __user *user_args = argp; + + /* even if we caught a signal, we need to communicate success */ + ret = q->ownerdead ? -EOWNERDEAD : 0; + + if (put_user(signaled, &user_args->index)) + ret = -EFAULT; + } else if (!ret) { + ret = -ETIMEDOUT; + } + + kfree(q); + return ret; } static int ntsync_char_open(struct inode *inode, struct file *file) @@ -198,6 +1158,8 @@ static int ntsync_char_open(struct inode *inode, struct file *file) if (!dev) return -ENOMEM; + mutex_init(&dev->wait_all_lock); + file->private_data = dev; dev->file = file; return nonseekable_open(inode, file); @@ -219,8 +1181,16 @@ static long ntsync_char_ioctl(struct file *file, unsigned int cmd, void __user *argp = (void __user *)parm; switch (cmd) { + case NTSYNC_IOC_CREATE_EVENT: + return ntsync_create_event(dev, argp); + case NTSYNC_IOC_CREATE_MUTEX: + return ntsync_create_mutex(dev, argp); case NTSYNC_IOC_CREATE_SEM: return ntsync_create_sem(dev, argp); + case NTSYNC_IOC_WAIT_ALL: + return ntsync_wait_all(dev, argp); + case NTSYNC_IOC_WAIT_ANY: + return ntsync_wait_any(dev, argp); default: return -ENOIOCTLCMD; } diff --git a/drivers/misc/ocxl/sysfs.c b/drivers/misc/ocxl/sysfs.c index 07520d6e6dc5..e849641687a0 100644 --- a/drivers/misc/ocxl/sysfs.c +++ b/drivers/misc/ocxl/sysfs.c @@ -94,7 +94,7 @@ static struct device_attribute afu_attrs[] = { }; static ssize_t global_mmio_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct ocxl_afu *afu = to_afu(kobj_to_dev(kobj)); @@ -155,7 +155,7 @@ int ocxl_sysfs_register_afu(struct ocxl_file_info *info) info->attr_global_mmio.attr.name = "global_mmio_area"; info->attr_global_mmio.attr.mode = 0600; info->attr_global_mmio.size = info->afu->config.global_mmio_size; - info->attr_global_mmio.read = global_mmio_read; + info->attr_global_mmio.read_new = global_mmio_read; info->attr_global_mmio.mmap = global_mmio_mmap; rc = device_create_bin_file(&info->dev, &info->attr_global_mmio); if (rc) { diff --git a/drivers/misc/pch_phub.c b/drivers/misc/pch_phub.c index 8d2b7135738e..6121c0940cd1 100644 --- a/drivers/misc/pch_phub.c +++ b/drivers/misc/pch_phub.c @@ -483,7 +483,7 @@ static int pch_phub_write_gbe_mac_addr(struct pch_phub_reg *chip, u8 *data) } static ssize_t pch_phub_bin_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { unsigned int rom_signature; @@ -553,7 +553,7 @@ return_err_nomutex: } static ssize_t pch_phub_bin_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { int err; @@ -655,8 +655,8 @@ static const struct bin_attribute pch_bin_attr = { .mode = S_IRUGO | S_IWUSR, }, .size = PCH_PHUB_OROM_SIZE + 1, - .read = pch_phub_bin_read, - .write = pch_phub_bin_write, + .read_new = pch_phub_bin_read, + .write_new = pch_phub_bin_write, }; static int pch_phub_probe(struct pci_dev *pdev, diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index 3aaaf47fa4ee..d5ac71a49386 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -69,6 +69,9 @@ #define PCI_ENDPOINT_TEST_FLAGS 0x2c #define FLAG_USE_DMA BIT(0) +#define PCI_ENDPOINT_TEST_CAPS 0x30 +#define CAP_UNALIGNED_ACCESS BIT(0) + #define PCI_DEVICE_ID_TI_AM654 0xb00c #define PCI_DEVICE_ID_TI_J7200 0xb00f #define PCI_DEVICE_ID_TI_AM64 0xb010 @@ -166,43 +169,47 @@ static void pci_endpoint_test_free_irq_vectors(struct pci_endpoint_test *test) test->irq_type = IRQ_TYPE_UNDEFINED; } -static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test, +static int pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test, int type) { - int irq = -1; + int irq; struct pci_dev *pdev = test->pdev; struct device *dev = &pdev->dev; - bool res = true; switch (type) { case IRQ_TYPE_INTX: irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_INTX); - if (irq < 0) + if (irq < 0) { dev_err(dev, "Failed to get Legacy interrupt\n"); + return irq; + } + break; case IRQ_TYPE_MSI: irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI); - if (irq < 0) + if (irq < 0) { dev_err(dev, "Failed to get MSI interrupts\n"); + return irq; + } + break; case IRQ_TYPE_MSIX: irq = pci_alloc_irq_vectors(pdev, 1, 2048, PCI_IRQ_MSIX); - if (irq < 0) + if (irq < 0) { dev_err(dev, "Failed to get MSI-X interrupts\n"); + return irq; + } + break; default: dev_err(dev, "Invalid IRQ type selected\n"); - } - - if (irq < 0) { - irq = 0; - res = false; + return -EINVAL; } test->irq_type = type; test->num_irqs = irq; - return res; + return 0; } static void pci_endpoint_test_release_irq(struct pci_endpoint_test *test) @@ -217,22 +224,22 @@ static void pci_endpoint_test_release_irq(struct pci_endpoint_test *test) test->num_irqs = 0; } -static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test) +static int pci_endpoint_test_request_irq(struct pci_endpoint_test *test) { int i; - int err; + int ret; struct pci_dev *pdev = test->pdev; struct device *dev = &pdev->dev; for (i = 0; i < test->num_irqs; i++) { - err = devm_request_irq(dev, pci_irq_vector(pdev, i), + ret = devm_request_irq(dev, pci_irq_vector(pdev, i), pci_endpoint_test_irqhandler, IRQF_SHARED, test->name, test); - if (err) + if (ret) goto fail; } - return true; + return 0; fail: switch (irq_type) { @@ -252,7 +259,7 @@ fail: break; } - return false; + return ret; } static const u32 bar_test_pattern[] = { @@ -277,16 +284,16 @@ static int pci_endpoint_test_bar_memcmp(struct pci_endpoint_test *test, return memcmp(write_buf, read_buf, size); } -static bool pci_endpoint_test_bar(struct pci_endpoint_test *test, +static int pci_endpoint_test_bar(struct pci_endpoint_test *test, enum pci_barno barno) { - int j, bar_size, buf_size, iters, remain; + int j, bar_size, buf_size, iters; void *write_buf __free(kfree) = NULL; void *read_buf __free(kfree) = NULL; struct pci_dev *pdev = test->pdev; if (!test->bar[barno]) - return false; + return -ENOMEM; bar_size = pci_resource_len(pdev, barno); @@ -301,28 +308,105 @@ static bool pci_endpoint_test_bar(struct pci_endpoint_test *test, write_buf = kmalloc(buf_size, GFP_KERNEL); if (!write_buf) - return false; + return -ENOMEM; read_buf = kmalloc(buf_size, GFP_KERNEL); if (!read_buf) - return false; + return -ENOMEM; iters = bar_size / buf_size; for (j = 0; j < iters; j++) if (pci_endpoint_test_bar_memcmp(test, barno, buf_size * j, write_buf, read_buf, buf_size)) - return false; + return -EIO; - remain = bar_size % buf_size; - if (remain) - if (pci_endpoint_test_bar_memcmp(test, barno, buf_size * iters, - write_buf, read_buf, remain)) - return false; - - return true; + return 0; } -static bool pci_endpoint_test_intx_irq(struct pci_endpoint_test *test) +static u32 bar_test_pattern_with_offset(enum pci_barno barno, int offset) +{ + u32 val; + + /* Keep the BAR pattern in the top byte. */ + val = bar_test_pattern[barno] & 0xff000000; + /* Store the (partial) offset in the remaining bytes. */ + val |= offset & 0x00ffffff; + + return val; +} + +static void pci_endpoint_test_bars_write_bar(struct pci_endpoint_test *test, + enum pci_barno barno) +{ + struct pci_dev *pdev = test->pdev; + int j, size; + + size = pci_resource_len(pdev, barno); + + if (barno == test->test_reg_bar) + size = 0x4; + + for (j = 0; j < size; j += 4) + writel_relaxed(bar_test_pattern_with_offset(barno, j), + test->bar[barno] + j); +} + +static int pci_endpoint_test_bars_read_bar(struct pci_endpoint_test *test, + enum pci_barno barno) +{ + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + int j, size; + u32 val; + + size = pci_resource_len(pdev, barno); + + if (barno == test->test_reg_bar) + size = 0x4; + + for (j = 0; j < size; j += 4) { + u32 expected = bar_test_pattern_with_offset(barno, j); + + val = readl_relaxed(test->bar[barno] + j); + if (val != expected) { + dev_err(dev, + "BAR%d incorrect data at offset: %#x, got: %#x expected: %#x\n", + barno, j, val, expected); + return -EIO; + } + } + + return 0; +} + +static int pci_endpoint_test_bars(struct pci_endpoint_test *test) +{ + enum pci_barno bar; + bool ret; + + /* Write all BARs in order (without reading). */ + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) + if (test->bar[bar]) + pci_endpoint_test_bars_write_bar(test, bar); + + /* + * Read all BARs in order (without writing). + * If there is an address translation issue on the EP, writing one BAR + * might have overwritten another BAR. Ensure that this is not the case. + * (Reading back the BAR directly after writing can not detect this.) + */ + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { + if (test->bar[bar]) { + ret = pci_endpoint_test_bars_read_bar(test, bar); + if (!ret) + return ret; + } + } + + return 0; +} + +static int pci_endpoint_test_intx_irq(struct pci_endpoint_test *test) { u32 val; @@ -334,16 +418,17 @@ static bool pci_endpoint_test_intx_irq(struct pci_endpoint_test *test) val = wait_for_completion_timeout(&test->irq_raised, msecs_to_jiffies(1000)); if (!val) - return false; + return -ETIMEDOUT; - return true; + return 0; } -static bool pci_endpoint_test_msi_irq(struct pci_endpoint_test *test, +static int pci_endpoint_test_msi_irq(struct pci_endpoint_test *test, u16 msi_num, bool msix) { - u32 val; struct pci_dev *pdev = test->pdev; + u32 val; + int ret; pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, msix ? IRQ_TYPE_MSIX : IRQ_TYPE_MSI); @@ -354,9 +439,16 @@ static bool pci_endpoint_test_msi_irq(struct pci_endpoint_test *test, val = wait_for_completion_timeout(&test->irq_raised, msecs_to_jiffies(1000)); if (!val) - return false; + return -ETIMEDOUT; - return pci_irq_vector(pdev, msi_num - 1) == test->last_irq; + ret = pci_irq_vector(pdev, msi_num - 1); + if (ret < 0) + return ret; + + if (ret != test->last_irq) + return -EIO; + + return 0; } static int pci_endpoint_test_validate_xfer_params(struct device *dev, @@ -375,11 +467,10 @@ static int pci_endpoint_test_validate_xfer_params(struct device *dev, return 0; } -static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, +static int pci_endpoint_test_copy(struct pci_endpoint_test *test, unsigned long arg) { struct pci_endpoint_test_xfer_param param; - bool ret = false; void *src_addr; void *dst_addr; u32 flags = 0; @@ -398,17 +489,17 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, int irq_type = test->irq_type; u32 src_crc32; u32 dst_crc32; - int err; + int ret; - err = copy_from_user(¶m, (void __user *)arg, sizeof(param)); - if (err) { + ret = copy_from_user(¶m, (void __user *)arg, sizeof(param)); + if (ret) { dev_err(dev, "Failed to get transfer param\n"); - return false; + return -EFAULT; } - err = pci_endpoint_test_validate_xfer_params(dev, ¶m, alignment); - if (err) - return false; + ret = pci_endpoint_test_validate_xfer_params(dev, ¶m, alignment); + if (ret) + return ret; size = param.size; @@ -418,22 +509,21 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) { dev_err(dev, "Invalid IRQ type option\n"); - goto err; + return -EINVAL; } orig_src_addr = kzalloc(size + alignment, GFP_KERNEL); if (!orig_src_addr) { dev_err(dev, "Failed to allocate source buffer\n"); - ret = false; - goto err; + return -ENOMEM; } get_random_bytes(orig_src_addr, size + alignment); orig_src_phys_addr = dma_map_single(dev, orig_src_addr, size + alignment, DMA_TO_DEVICE); - if (dma_mapping_error(dev, orig_src_phys_addr)) { + ret = dma_mapping_error(dev, orig_src_phys_addr); + if (ret) { dev_err(dev, "failed to map source buffer address\n"); - ret = false; goto err_src_phys_addr; } @@ -457,15 +547,15 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, orig_dst_addr = kzalloc(size + alignment, GFP_KERNEL); if (!orig_dst_addr) { dev_err(dev, "Failed to allocate destination address\n"); - ret = false; + ret = -ENOMEM; goto err_dst_addr; } orig_dst_phys_addr = dma_map_single(dev, orig_dst_addr, size + alignment, DMA_FROM_DEVICE); - if (dma_mapping_error(dev, orig_dst_phys_addr)) { + ret = dma_mapping_error(dev, orig_dst_phys_addr); + if (ret) { dev_err(dev, "failed to map destination buffer address\n"); - ret = false; goto err_dst_phys_addr; } @@ -498,8 +588,8 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, DMA_FROM_DEVICE); dst_crc32 = crc32_le(~0, dst_addr, size); - if (dst_crc32 == src_crc32) - ret = true; + if (dst_crc32 != src_crc32) + ret = -EIO; err_dst_phys_addr: kfree(orig_dst_addr); @@ -510,16 +600,13 @@ err_dst_addr: err_src_phys_addr: kfree(orig_src_addr); - -err: return ret; } -static bool pci_endpoint_test_write(struct pci_endpoint_test *test, +static int pci_endpoint_test_write(struct pci_endpoint_test *test, unsigned long arg) { struct pci_endpoint_test_xfer_param param; - bool ret = false; u32 flags = 0; bool use_dma; u32 reg; @@ -534,17 +621,17 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, int irq_type = test->irq_type; size_t size; u32 crc32; - int err; + int ret; - err = copy_from_user(¶m, (void __user *)arg, sizeof(param)); - if (err != 0) { + ret = copy_from_user(¶m, (void __user *)arg, sizeof(param)); + if (ret) { dev_err(dev, "Failed to get transfer param\n"); - return false; + return -EFAULT; } - err = pci_endpoint_test_validate_xfer_params(dev, ¶m, alignment); - if (err) - return false; + ret = pci_endpoint_test_validate_xfer_params(dev, ¶m, alignment); + if (ret) + return ret; size = param.size; @@ -554,23 +641,22 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) { dev_err(dev, "Invalid IRQ type option\n"); - goto err; + return -EINVAL; } orig_addr = kzalloc(size + alignment, GFP_KERNEL); if (!orig_addr) { dev_err(dev, "Failed to allocate address\n"); - ret = false; - goto err; + return -ENOMEM; } get_random_bytes(orig_addr, size + alignment); orig_phys_addr = dma_map_single(dev, orig_addr, size + alignment, DMA_TO_DEVICE); - if (dma_mapping_error(dev, orig_phys_addr)) { + ret = dma_mapping_error(dev, orig_phys_addr); + if (ret) { dev_err(dev, "failed to map source buffer address\n"); - ret = false; goto err_phys_addr; } @@ -603,24 +689,21 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, wait_for_completion(&test->irq_raised); reg = pci_endpoint_test_readl(test, PCI_ENDPOINT_TEST_STATUS); - if (reg & STATUS_READ_SUCCESS) - ret = true; + if (!(reg & STATUS_READ_SUCCESS)) + ret = -EIO; dma_unmap_single(dev, orig_phys_addr, size + alignment, DMA_TO_DEVICE); err_phys_addr: kfree(orig_addr); - -err: return ret; } -static bool pci_endpoint_test_read(struct pci_endpoint_test *test, +static int pci_endpoint_test_read(struct pci_endpoint_test *test, unsigned long arg) { struct pci_endpoint_test_xfer_param param; - bool ret = false; u32 flags = 0; bool use_dma; size_t size; @@ -634,17 +717,17 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t alignment = test->alignment; int irq_type = test->irq_type; u32 crc32; - int err; + int ret; - err = copy_from_user(¶m, (void __user *)arg, sizeof(param)); - if (err) { + ret = copy_from_user(¶m, (void __user *)arg, sizeof(param)); + if (ret) { dev_err(dev, "Failed to get transfer param\n"); - return false; + return -EFAULT; } - err = pci_endpoint_test_validate_xfer_params(dev, ¶m, alignment); - if (err) - return false; + ret = pci_endpoint_test_validate_xfer_params(dev, ¶m, alignment); + if (ret) + return ret; size = param.size; @@ -654,21 +737,20 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) { dev_err(dev, "Invalid IRQ type option\n"); - goto err; + return -EINVAL; } orig_addr = kzalloc(size + alignment, GFP_KERNEL); if (!orig_addr) { dev_err(dev, "Failed to allocate destination address\n"); - ret = false; - goto err; + return -ENOMEM; } orig_phys_addr = dma_map_single(dev, orig_addr, size + alignment, DMA_FROM_DEVICE); - if (dma_mapping_error(dev, orig_phys_addr)) { + ret = dma_mapping_error(dev, orig_phys_addr); + if (ret) { dev_err(dev, "failed to map source buffer address\n"); - ret = false; goto err_phys_addr; } @@ -700,50 +782,51 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, DMA_FROM_DEVICE); crc32 = crc32_le(~0, addr, size); - if (crc32 == pci_endpoint_test_readl(test, PCI_ENDPOINT_TEST_CHECKSUM)) - ret = true; + if (crc32 != pci_endpoint_test_readl(test, PCI_ENDPOINT_TEST_CHECKSUM)) + ret = -EIO; err_phys_addr: kfree(orig_addr); -err: return ret; } -static bool pci_endpoint_test_clear_irq(struct pci_endpoint_test *test) +static int pci_endpoint_test_clear_irq(struct pci_endpoint_test *test) { pci_endpoint_test_release_irq(test); pci_endpoint_test_free_irq_vectors(test); - return true; + + return 0; } -static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test, +static int pci_endpoint_test_set_irq(struct pci_endpoint_test *test, int req_irq_type) { struct pci_dev *pdev = test->pdev; struct device *dev = &pdev->dev; + int ret; if (req_irq_type < IRQ_TYPE_INTX || req_irq_type > IRQ_TYPE_MSIX) { dev_err(dev, "Invalid IRQ type option\n"); - return false; + return -EINVAL; } if (test->irq_type == req_irq_type) - return true; + return 0; pci_endpoint_test_release_irq(test); pci_endpoint_test_free_irq_vectors(test); - if (!pci_endpoint_test_alloc_irq_vectors(test, req_irq_type)) - goto err; + ret = pci_endpoint_test_alloc_irq_vectors(test, req_irq_type); + if (ret) + return ret; - if (!pci_endpoint_test_request_irq(test)) - goto err; + ret = pci_endpoint_test_request_irq(test); + if (ret) { + pci_endpoint_test_free_irq_vectors(test); + return ret; + } - return true; - -err: - pci_endpoint_test_free_irq_vectors(test); - return false; + return 0; } static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, @@ -768,6 +851,9 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, goto ret; ret = pci_endpoint_test_bar(test, bar); break; + case PCITEST_BARS: + ret = pci_endpoint_test_bars(test); + break; case PCITEST_INTX_IRQ: ret = pci_endpoint_test_intx_irq(test); break; @@ -805,10 +891,24 @@ static const struct file_operations pci_endpoint_test_fops = { .unlocked_ioctl = pci_endpoint_test_ioctl, }; +static void pci_endpoint_test_get_capabilities(struct pci_endpoint_test *test) +{ + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + u32 caps; + + caps = pci_endpoint_test_readl(test, PCI_ENDPOINT_TEST_CAPS); + dev_dbg(dev, "PCI_ENDPOINT_TEST_CAPS: %#x\n", caps); + + /* CAP_UNALIGNED_ACCESS is set if the EP can do unaligned access */ + if (caps & CAP_UNALIGNED_ACCESS) + test->alignment = 0; +} + static int pci_endpoint_test_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - int err; + int ret; int id; char name[24]; enum pci_barno bar; @@ -847,24 +947,23 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48)); - err = pci_enable_device(pdev); - if (err) { + ret = pci_enable_device(pdev); + if (ret) { dev_err(dev, "Cannot enable PCI device\n"); - return err; + return ret; } - err = pci_request_regions(pdev, DRV_MODULE_NAME); - if (err) { + ret = pci_request_regions(pdev, DRV_MODULE_NAME); + if (ret) { dev_err(dev, "Cannot obtain PCI resources\n"); goto err_disable_pdev; } pci_set_master(pdev); - if (!pci_endpoint_test_alloc_irq_vectors(test, irq_type)) { - err = -EINVAL; + ret = pci_endpoint_test_alloc_irq_vectors(test, irq_type); + if (ret) goto err_disable_irq; - } for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) { @@ -879,7 +978,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, test->base = test->bar[test_reg_bar]; if (!test->base) { - err = -ENOMEM; + ret = -ENOMEM; dev_err(dev, "Cannot perform PCI test without BAR%d\n", test_reg_bar); goto err_iounmap; @@ -889,7 +988,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, id = ida_alloc(&pci_endpoint_test_ida, GFP_KERNEL); if (id < 0) { - err = id; + ret = id; dev_err(dev, "Unable to get id\n"); goto err_iounmap; } @@ -897,27 +996,28 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, snprintf(name, sizeof(name), DRV_MODULE_NAME ".%d", id); test->name = kstrdup(name, GFP_KERNEL); if (!test->name) { - err = -ENOMEM; + ret = -ENOMEM; goto err_ida_remove; } - if (!pci_endpoint_test_request_irq(test)) { - err = -EINVAL; + ret = pci_endpoint_test_request_irq(test); + if (ret) goto err_kfree_test_name; - } + + pci_endpoint_test_get_capabilities(test); misc_device = &test->miscdev; misc_device->minor = MISC_DYNAMIC_MINOR; misc_device->name = kstrdup(name, GFP_KERNEL); if (!misc_device->name) { - err = -ENOMEM; + ret = -ENOMEM; goto err_release_irq; } misc_device->parent = &pdev->dev; misc_device->fops = &pci_endpoint_test_fops; - err = misc_register(misc_device); - if (err) { + ret = misc_register(misc_device); + if (ret) { dev_err(dev, "Failed to register device\n"); goto err_kfree_name; } @@ -949,7 +1049,7 @@ err_disable_irq: err_disable_pdev: pci_disable_device(pdev); - return err; + return ret; } static void pci_endpoint_test_remove(struct pci_dev *pdev) diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c index 61b66e318488..7a3c34306de9 100644 --- a/drivers/misc/sgi-xp/xpc_main.c +++ b/drivers/misc/sgi-xp/xpc_main.c @@ -93,7 +93,7 @@ int xpc_disengage_timelimit = XPC_DISENGAGE_DEFAULT_TIMELIMIT; static int xpc_disengage_min_timelimit; /* = 0 */ static int xpc_disengage_max_timelimit = 120; -static struct ctl_table xpc_sys_xpc_hb[] = { +static const struct ctl_table xpc_sys_xpc_hb[] = { { .procname = "hb_interval", .data = &xpc_hb_interval, @@ -111,7 +111,7 @@ static struct ctl_table xpc_sys_xpc_hb[] = { .extra1 = &xpc_hb_check_min_interval, .extra2 = &xpc_hb_check_max_interval}, }; -static struct ctl_table xpc_sys_xpc[] = { +static const struct ctl_table xpc_sys_xpc[] = { { .procname = "disengage_timelimit", .data = &xpc_disengage_timelimit, diff --git a/drivers/misc/sram.c b/drivers/misc/sram.c index e40b027a88e2..e5069882457e 100644 --- a/drivers/misc/sram.c +++ b/drivers/misc/sram.c @@ -23,7 +23,7 @@ #define SRAM_GRANULARITY 32 static ssize_t sram_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct sram_partition *part; @@ -38,7 +38,7 @@ static ssize_t sram_read(struct file *filp, struct kobject *kobj, } static ssize_t sram_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct sram_partition *part; @@ -83,8 +83,8 @@ static int sram_add_export(struct sram_dev *sram, struct sram_reserve *block, return -ENOMEM; part->battr.attr.mode = S_IRUSR | S_IWUSR; - part->battr.read = sram_read; - part->battr.write = sram_write; + part->battr.read_new = sram_read; + part->battr.write_new = sram_write; part->battr.size = block->size; return device_create_bin_file(sram->dev, &part->battr); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index d996d39c0d6f..5241528f8b90 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -557,8 +556,7 @@ int mmc_cqe_recovery(struct mmc_host *host) memset(&cmd, 0, sizeof(cmd)); cmd.opcode = MMC_STOP_TRANSMISSION; - cmd.flags = MMC_RSP_R1B | MMC_CMD_AC; - cmd.flags &= ~MMC_RSP_CRC; /* Ignore CRC */ + cmd.flags = MMC_RSP_R1B_NO_CRC | MMC_CMD_AC; /* Ignore CRC */ cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT; mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES); @@ -567,8 +565,7 @@ int mmc_cqe_recovery(struct mmc_host *host) memset(&cmd, 0, sizeof(cmd)); cmd.opcode = MMC_CMDQ_TASK_MGMT; cmd.arg = 1; /* Discard entire queue */ - cmd.flags = MMC_RSP_R1B | MMC_CMD_AC; - cmd.flags &= ~MMC_RSP_CRC; /* Ignore CRC */ + cmd.flags = MMC_RSP_R1B_NO_CRC | MMC_CMD_AC; /* Ignore CRC */ cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT; err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES); diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 48bda70145ee..bdb22998357e 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 4d6844261912..ab662f502fe7 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -441,7 +441,7 @@ struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, else mq->tag_set.queue_depth = MMC_QUEUE_DEPTH; mq->tag_set.numa_node = NUMA_NO_NODE; - mq->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; + mq->tag_set.flags = BLK_MQ_F_BLOCKING; mq->tag_set.nr_hw_queues = 1; mq->tag_set.cmd_size = sizeof(struct mmc_queue_req); mq->tag_set.driver_data = mq; diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index 9566837c9848..4b19b8a16b09 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -458,6 +458,8 @@ static unsigned mmc_sdio_get_max_clock(struct mmc_card *card) if (mmc_card_sd_combo(card)) max_dtr = min(max_dtr, mmc_sd_get_max_clock(card)); + max_dtr = min_not_zero(max_dtr, card->quirk_max_rate); + return max_dtr; } diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c index 7847f0c8b465..e5f151d092cd 100644 --- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -1343,6 +1343,25 @@ static int bcm2835_add_host(struct bcm2835_host *host) return 0; } +static int bcm2835_suspend(struct device *dev) +{ + struct bcm2835_host *host = dev_get_drvdata(dev); + + clk_disable_unprepare(host->clk); + + return 0; +} + +static int bcm2835_resume(struct device *dev) +{ + struct bcm2835_host *host = dev_get_drvdata(dev); + + return clk_prepare_enable(host->clk); +} + +static DEFINE_SIMPLE_DEV_PM_OPS(bcm2835_pm_ops, bcm2835_suspend, + bcm2835_resume); + static int bcm2835_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1471,6 +1490,7 @@ static struct platform_driver bcm2835_driver = { .name = "sdhost-bcm2835", .probe_type = PROBE_PREFER_ASYNCHRONOUS, .of_match_table = bcm2835_match, + .pm = pm_ptr(&bcm2835_pm_ops), }, }; module_platform_driver(bcm2835_driver); diff --git a/drivers/mmc/host/cqhci-crypto.c b/drivers/mmc/host/cqhci-crypto.c index d5f4b6972f63..cb8044093402 100644 --- a/drivers/mmc/host/cqhci-crypto.c +++ b/drivers/mmc/host/cqhci-crypto.c @@ -25,22 +25,16 @@ static const struct cqhci_crypto_alg_entry { static inline struct cqhci_host * cqhci_host_from_crypto_profile(struct blk_crypto_profile *profile) { - struct mmc_host *mmc = - container_of(profile, struct mmc_host, crypto_profile); - - return mmc->cqe_private; + return mmc_from_crypto_profile(profile)->cqe_private; } -static int cqhci_crypto_program_key(struct cqhci_host *cq_host, - const union cqhci_crypto_cfg_entry *cfg, - int slot) +static void cqhci_crypto_program_key(struct cqhci_host *cq_host, + const union cqhci_crypto_cfg_entry *cfg, + int slot) { u32 slot_offset = cq_host->crypto_cfg_register + slot * sizeof(*cfg); int i; - if (cq_host->ops->program_key) - return cq_host->ops->program_key(cq_host, cfg, slot); - /* Clear CFGE */ cqhci_writel(cq_host, 0, slot_offset + 16 * sizeof(cfg->reg_val[0])); @@ -55,7 +49,6 @@ static int cqhci_crypto_program_key(struct cqhci_host *cq_host, /* Write dword 16, which includes the new value of CFGE */ cqhci_writel(cq_host, le32_to_cpu(cfg->reg_val[16]), slot_offset + 16 * sizeof(cfg->reg_val[0])); - return 0; } static int cqhci_crypto_keyslot_program(struct blk_crypto_profile *profile, @@ -72,7 +65,6 @@ static int cqhci_crypto_keyslot_program(struct blk_crypto_profile *profile, int i; int cap_idx = -1; union cqhci_crypto_cfg_entry cfg = {}; - int err; BUILD_BUG_ON(CQHCI_CRYPTO_KEY_SIZE_INVALID != 0); for (i = 0; i < cq_host->crypto_capabilities.num_crypto_cap; i++) { @@ -99,10 +91,10 @@ static int cqhci_crypto_keyslot_program(struct blk_crypto_profile *profile, memcpy(cfg.crypto_key, key->raw, key->size); } - err = cqhci_crypto_program_key(cq_host, &cfg, slot); + cqhci_crypto_program_key(cq_host, &cfg, slot); memzero_explicit(&cfg, sizeof(cfg)); - return err; + return 0; } static int cqhci_crypto_clear_keyslot(struct cqhci_host *cq_host, int slot) @@ -113,7 +105,8 @@ static int cqhci_crypto_clear_keyslot(struct cqhci_host *cq_host, int slot) */ union cqhci_crypto_cfg_entry cfg = {}; - return cqhci_crypto_program_key(cq_host, &cfg, slot); + cqhci_crypto_program_key(cq_host, &cfg, slot); + return 0; } static int cqhci_crypto_keyslot_evict(struct blk_crypto_profile *profile, @@ -170,7 +163,6 @@ int cqhci_crypto_init(struct cqhci_host *cq_host) struct mmc_host *mmc = cq_host->mmc; struct device *dev = mmc_dev(mmc); struct blk_crypto_profile *profile = &mmc->crypto_profile; - unsigned int num_keyslots; unsigned int cap_idx; enum blk_crypto_mode_num blk_mode_num; unsigned int slot; @@ -180,6 +172,9 @@ int cqhci_crypto_init(struct cqhci_host *cq_host) !(cqhci_readl(cq_host, CQHCI_CAP) & CQHCI_CAP_CS)) goto out; + if (cq_host->ops->uses_custom_crypto_profile) + goto profile_initialized; + cq_host->crypto_capabilities.reg_val = cpu_to_le32(cqhci_readl(cq_host, CQHCI_CCAP)); @@ -198,9 +193,8 @@ int cqhci_crypto_init(struct cqhci_host *cq_host) * CCAP.CFGC is off by one, so the actual number of crypto * configurations (a.k.a. keyslots) is CCAP.CFGC + 1. */ - num_keyslots = cq_host->crypto_capabilities.config_count + 1; - - err = devm_blk_crypto_profile_init(dev, profile, num_keyslots); + err = devm_blk_crypto_profile_init( + dev, profile, cq_host->crypto_capabilities.config_count + 1); if (err) goto out; @@ -228,9 +222,11 @@ int cqhci_crypto_init(struct cqhci_host *cq_host) cq_host->crypto_cap_array[cap_idx].sdus_mask * 512; } +profile_initialized: + /* Clear all the keyslots so that we start in a known state. */ - for (slot = 0; slot < num_keyslots; slot++) - cqhci_crypto_clear_keyslot(cq_host, slot); + for (slot = 0; slot < profile->num_slots; slot++) + profile->ll_ops.keyslot_evict(profile, NULL, slot); /* CQHCI crypto requires the use of 128-bit task descriptors. */ cq_host->caps |= CQHCI_TASK_DESC_SZ_128; diff --git a/drivers/mmc/host/cqhci.h b/drivers/mmc/host/cqhci.h index fab9d74445ba..ce189a1866b9 100644 --- a/drivers/mmc/host/cqhci.h +++ b/drivers/mmc/host/cqhci.h @@ -289,13 +289,11 @@ struct cqhci_host_ops { u64 *data); void (*pre_enable)(struct mmc_host *mmc); void (*post_disable)(struct mmc_host *mmc); -#ifdef CONFIG_MMC_CRYPTO - int (*program_key)(struct cqhci_host *cq_host, - const union cqhci_crypto_cfg_entry *cfg, int slot); -#endif void (*set_tran_desc)(struct cqhci_host *cq_host, u8 **desc, dma_addr_t addr, int len, bool end, bool dma64); - +#ifdef CONFIG_MMC_CRYPTO + bool uses_custom_crypto_profile; +#endif }; static inline void cqhci_writel(struct cqhci_host *host, u32 val, int reg) diff --git a/drivers/mmc/host/dw_mmc-hi3798mv200.c b/drivers/mmc/host/dw_mmc-hi3798mv200.c index cce174b5249b..5791a975a944 100644 --- a/drivers/mmc/host/dw_mmc-hi3798mv200.c +++ b/drivers/mmc/host/dw_mmc-hi3798mv200.c @@ -181,7 +181,6 @@ static int dw_mci_hi3798mv200_init(struct dw_mci *host) { struct dw_mci_hi3798mv200_priv *priv; struct device_node *np = host->dev->of_node; - int ret; priv = devm_kzalloc(host->dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -199,15 +198,12 @@ static int dw_mci_hi3798mv200_init(struct dw_mci *host) return dev_err_probe(host->dev, PTR_ERR(priv->drive_clk), "failed to get enabled ciu-drive clock\n"); - priv->crg_reg = syscon_regmap_lookup_by_phandle(np, "hisilicon,sap-dll-reg"); + priv->crg_reg = syscon_regmap_lookup_by_phandle_args(np, "hisilicon,sap-dll-reg", + 1, &priv->sap_dll_offset); if (IS_ERR(priv->crg_reg)) return dev_err_probe(host->dev, PTR_ERR(priv->crg_reg), "failed to get CRG reg\n"); - ret = of_property_read_u32_index(np, "hisilicon,sap-dll-reg", 1, &priv->sap_dll_offset); - if (ret) - return dev_err_probe(host->dev, ret, "failed to get sample DLL register offset\n"); - host->priv = priv; return 0; } diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index efb0d2d5716b..4b6e91372526 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -414,6 +414,7 @@ struct mtk_mmc_compatible { u8 clk_div_bits; bool recheck_sdio_irq; bool hs400_tune; /* only used for MT8173 */ + bool needs_top_base; u32 pad_tune_reg; bool async_fifo; bool data_tune; @@ -587,6 +588,7 @@ static const struct mtk_mmc_compatible mt7986_compat = { .clk_div_bits = 12, .recheck_sdio_irq = true, .hs400_tune = false, + .needs_top_base = true, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, .data_tune = true, @@ -627,6 +629,7 @@ static const struct mtk_mmc_compatible mt8183_compat = { .clk_div_bits = 12, .recheck_sdio_irq = false, .hs400_tune = false, + .needs_top_base = true, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, .data_tune = true, @@ -653,6 +656,7 @@ static const struct mtk_mmc_compatible mt8196_compat = { .clk_div_bits = 12, .recheck_sdio_irq = false, .hs400_tune = false, + .needs_top_base = true, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, .data_tune = true, @@ -1097,11 +1101,12 @@ static inline u32 msdc_cmd_find_resp(struct msdc_host *host, u32 resp; switch (mmc_resp_type(cmd)) { - /* Actually, R1, R5, R6, R7 are the same */ + /* Actually, R1, R5, R6, R7 are the same */ case MMC_RSP_R1: resp = 0x1; break; case MMC_RSP_R1B: + case MMC_RSP_R1B_NO_CRC: resp = 0x7; break; case MMC_RSP_R2: @@ -1351,7 +1356,8 @@ static bool msdc_cmd_done(struct msdc_host *host, int events, * CRC error. */ msdc_reset_hw(host); - if (events & MSDC_INT_RSPCRCERR) { + if (events & MSDC_INT_RSPCRCERR && + mmc_resp_type(cmd) != MMC_RSP_R1B_NO_CRC) { cmd->error = -EILSEQ; host->error |= REQ_CMD_EIO; } else if (events & MSDC_INT_CMDTMO) { @@ -2885,9 +2891,13 @@ static int msdc_drv_probe(struct platform_device *pdev) if (IS_ERR(host->base)) return PTR_ERR(host->base); - host->top_base = devm_platform_ioremap_resource(pdev, 1); - if (IS_ERR(host->top_base)) - host->top_base = NULL; + host->dev_comp = of_device_get_match_data(&pdev->dev); + + if (host->dev_comp->needs_top_base) { + host->top_base = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(host->top_base)) + return PTR_ERR(host->top_base); + } ret = mmc_regulator_get_supply(mmc); if (ret) @@ -2949,7 +2959,6 @@ static int msdc_drv_probe(struct platform_device *pdev) msdc_of_property_parse(pdev, host); host->dev = &pdev->dev; - host->dev_comp = of_device_get_match_data(&pdev->dev); host->src_clk_freq = clk_get_rate(host->src_clk); /* Set host parameters to mmc */ mmc->ops = &mt_msdc_ops; @@ -3070,6 +3079,7 @@ release_clk: msdc_gate_clock(host); platform_set_drvdata(pdev, NULL); release_mem: + device_init_wakeup(&pdev->dev, false); if (host->dma.gpd) dma_free_coherent(&pdev->dev, 2 * sizeof(struct mt_gpdma_desc), @@ -3103,6 +3113,7 @@ static void msdc_drv_remove(struct platform_device *pdev) host->dma.gpd, host->dma.gpd_addr); dma_free_coherent(&pdev->dev, MAX_BD_NUM * sizeof(struct mt_bdma_desc), host->dma.bd, host->dma.bd_addr); + device_init_wakeup(&pdev->dev, false); } static void msdc_save_reg(struct msdc_host *host) diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c index e7a286c3216f..0a9affd12532 100644 --- a/drivers/mmc/host/mxcmmc.c +++ b/drivers/mmc/host/mxcmmc.c @@ -995,7 +995,7 @@ static int mxcmci_probe(struct platform_device *pdev) struct mxcmci_host *host; struct resource *res; int ret = 0, irq; - bool dat3_card_detect = false; + bool dat3_card_detect; dma_cap_mask_t mask; struct imxmmc_platform_data *pdata = pdev->dev.platform_data; @@ -1048,9 +1048,9 @@ static int mxcmci_probe(struct platform_device *pdev) if (pdata) dat3_card_detect = pdata->dat3_card_detect; - else if (mmc_card_is_removable(mmc) - && !of_property_read_bool(pdev->dev.of_node, "cd-gpios")) - dat3_card_detect = true; + else + dat3_card_detect = mmc_card_is_removable(mmc) && + !of_property_present(pdev->dev.of_node, "cd-gpios"); ret = mmc_regulator_get_supply(mmc); if (ret) diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index 48d3b0aae5a0..0c6eb60a95fd 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -115,8 +115,6 @@ static int sd_response_type(struct mmc_command *cmd) return SD_RSP_TYPE_R0; case MMC_RSP_R1: return SD_RSP_TYPE_R1; - case MMC_RSP_R1_NO_CRC: - return SD_RSP_TYPE_R1 | SD_NO_CHECK_CRC7; case MMC_RSP_R1B: return SD_RSP_TYPE_R1b; case MMC_RSP_R2: diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c index 107c78df53cf..d229c2b83ea9 100644 --- a/drivers/mmc/host/rtsx_usb_sdmmc.c +++ b/drivers/mmc/host/rtsx_usb_sdmmc.c @@ -313,9 +313,6 @@ static void sd_send_cmd_get_rsp(struct rtsx_usb_sdmmc *host, case MMC_RSP_R1: rsp_type = SD_RSP_TYPE_R1; break; - case MMC_RSP_R1_NO_CRC: - rsp_type = SD_RSP_TYPE_R1 | SD_NO_CHECK_CRC7; - break; case MMC_RSP_R1B: rsp_type = SD_RSP_TYPE_R1b; break; diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index d1ce9193ece9..e6c5c82f64fa 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -822,8 +822,6 @@ static int sdhci_acpi_probe(struct platform_device *pdev) struct acpi_device *device; struct sdhci_acpi_host *c; struct sdhci_host *host; - struct resource *iomem; - resource_size_t len; size_t priv_size; int quirks = 0; int err; @@ -844,17 +842,6 @@ static int sdhci_acpi_probe(struct platform_device *pdev) if (sdhci_acpi_byt_defer(dev)) return -EPROBE_DEFER; - iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!iomem) - return -ENOMEM; - - len = resource_size(iomem); - if (len < 0x100) - dev_err(dev, "Invalid iomem size!\n"); - - if (!devm_request_mem_region(dev, iomem->start, len, dev_name(dev))) - return -ENOMEM; - priv_size = slot ? slot->priv_size : 0; host = sdhci_alloc_host(dev, sizeof(struct sdhci_acpi_host) + priv_size); if (IS_ERR(host)) @@ -876,10 +863,9 @@ static int sdhci_acpi_probe(struct platform_device *pdev) goto err_free; } - host->ioaddr = devm_ioremap(dev, iomem->start, - resource_size(iomem)); - if (host->ioaddr == NULL) { - err = -ENOMEM; + host->ioaddr = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(host->ioaddr)) { + err = PTR_ERR(host->ioaddr); goto err_free; } diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index d55d045ef236..ff78a7c6a04c 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -304,6 +304,7 @@ static struct esdhc_soc_data usdhc_s32g2_data = { | ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200 | ESDHC_FLAG_HS400 | ESDHC_FLAG_HS400_ES | ESDHC_FLAG_SKIP_ERR004536 | ESDHC_FLAG_SKIP_CD_WAKE, + .quirks = SDHCI_QUIRK_NO_LED, }; static struct esdhc_soc_data usdhc_imx7ulp_data = { @@ -1647,7 +1648,7 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev, * Retrieving and requesting the actual WP GPIO will happen * in the call to mmc_of_parse(). */ - if (of_property_read_bool(np, "wp-gpios")) + if (of_property_present(np, "wp-gpios")) boarddata->wp_type = ESDHC_WP_GPIO; of_property_read_u32(np, "fsl,tuning-step", &boarddata->tuning_step); diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index e00208535bd1..e3d39311fdc7 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -134,9 +134,18 @@ /* Timeout value to avoid infinite waiting for pwr_irq */ #define MSM_PWR_IRQ_TIMEOUT_MS 5000 +/* Max load for eMMC Vdd supply */ +#define MMC_VMMC_MAX_LOAD_UA 570000 + /* Max load for eMMC Vdd-io supply */ #define MMC_VQMMC_MAX_LOAD_UA 325000 +/* Max load for SD Vdd supply */ +#define SD_VMMC_MAX_LOAD_UA 800000 + +/* Max load for SD Vdd-io supply */ +#define SD_VQMMC_MAX_LOAD_UA 22000 + #define msm_host_readl(msm_host, host, offset) \ msm_host->var_ops->msm_readl_relaxed(host, offset) @@ -1403,11 +1412,48 @@ static int sdhci_msm_set_pincfg(struct sdhci_msm_host *msm_host, bool level) return ret; } -static int sdhci_msm_set_vmmc(struct mmc_host *mmc) +static void msm_config_vmmc_regulator(struct mmc_host *mmc, bool hpm) +{ + int load; + + if (!hpm) + load = 0; + else if (!mmc->card) + load = max(MMC_VMMC_MAX_LOAD_UA, SD_VMMC_MAX_LOAD_UA); + else if (mmc_card_mmc(mmc->card)) + load = MMC_VMMC_MAX_LOAD_UA; + else if (mmc_card_sd(mmc->card)) + load = SD_VMMC_MAX_LOAD_UA; + else + return; + + regulator_set_load(mmc->supply.vmmc, load); +} + +static void msm_config_vqmmc_regulator(struct mmc_host *mmc, bool hpm) +{ + int load; + + if (!hpm) + load = 0; + else if (!mmc->card) + load = max(MMC_VQMMC_MAX_LOAD_UA, SD_VQMMC_MAX_LOAD_UA); + else if (mmc_card_sd(mmc->card)) + load = SD_VQMMC_MAX_LOAD_UA; + else + return; + + regulator_set_load(mmc->supply.vqmmc, load); +} + +static int sdhci_msm_set_vmmc(struct sdhci_msm_host *msm_host, + struct mmc_host *mmc, bool hpm) { if (IS_ERR(mmc->supply.vmmc)) return 0; + msm_config_vmmc_regulator(mmc, hpm); + return mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, mmc->ios.vdd); } @@ -1420,6 +1466,8 @@ static int msm_toggle_vqmmc(struct sdhci_msm_host *msm_host, if (msm_host->vqmmc_enabled == level) return 0; + msm_config_vqmmc_regulator(mmc, level); + if (level) { /* Set the IO voltage regulator to default voltage level */ if (msm_host->caps_0 & CORE_3_0V_SUPPORT) @@ -1642,7 +1690,8 @@ static void sdhci_msm_handle_pwr_irq(struct sdhci_host *host, int irq) } if (pwr_state) { - ret = sdhci_msm_set_vmmc(mmc); + ret = sdhci_msm_set_vmmc(msm_host, mmc, + pwr_state & REQ_BUS_ON); if (!ret) ret = sdhci_msm_set_vqmmc(msm_host, mmc, pwr_state & REQ_BUS_ON); @@ -1807,12 +1856,19 @@ out: #ifdef CONFIG_MMC_CRYPTO +static const struct blk_crypto_ll_ops sdhci_msm_crypto_ops; /* forward decl */ + static int sdhci_msm_ice_init(struct sdhci_msm_host *msm_host, struct cqhci_host *cq_host) { struct mmc_host *mmc = msm_host->mmc; + struct blk_crypto_profile *profile = &mmc->crypto_profile; struct device *dev = mmc_dev(mmc); struct qcom_ice *ice; + union cqhci_crypto_capabilities caps; + union cqhci_crypto_cap_entry cap; + int err; + int i; if (!(cqhci_readl(cq_host, CQHCI_CAP) & CQHCI_CAP_CS)) return 0; @@ -1827,8 +1883,37 @@ static int sdhci_msm_ice_init(struct sdhci_msm_host *msm_host, return PTR_ERR_OR_ZERO(ice); msm_host->ice = ice; - mmc->caps2 |= MMC_CAP2_CRYPTO; + /* Initialize the blk_crypto_profile */ + + caps.reg_val = cpu_to_le32(cqhci_readl(cq_host, CQHCI_CCAP)); + + /* The number of keyslots supported is (CFGC+1) */ + err = devm_blk_crypto_profile_init(dev, profile, caps.config_count + 1); + if (err) + return err; + + profile->ll_ops = sdhci_msm_crypto_ops; + profile->max_dun_bytes_supported = 4; + profile->dev = dev; + + /* + * Currently this driver only supports AES-256-XTS. All known versions + * of ICE support it, but to be safe make sure it is really declared in + * the crypto capability registers. The crypto capability registers + * also give the supported data unit size(s). + */ + for (i = 0; i < caps.num_crypto_cap; i++) { + cap.reg_val = cpu_to_le32(cqhci_readl(cq_host, + CQHCI_CRYPTOCAP + + i * sizeof(__le32))); + if (cap.algorithm_id == CQHCI_CRYPTO_ALG_AES_XTS && + cap.key_size == CQHCI_CRYPTO_KEY_SIZE_256) + profile->modes_supported[BLK_ENCRYPTION_MODE_AES_256_XTS] |= + cap.sdus_mask * 512; + } + + mmc->caps2 |= MMC_CAP2_CRYPTO; return 0; } @@ -1854,35 +1939,55 @@ static __maybe_unused int sdhci_msm_ice_suspend(struct sdhci_msm_host *msm_host) return 0; } -/* - * Program a key into a QC ICE keyslot, or evict a keyslot. QC ICE requires - * vendor-specific SCM calls for this; it doesn't support the standard way. - */ -static int sdhci_msm_program_key(struct cqhci_host *cq_host, - const union cqhci_crypto_cfg_entry *cfg, - int slot) +static inline struct sdhci_msm_host * +sdhci_msm_host_from_crypto_profile(struct blk_crypto_profile *profile) { - struct sdhci_host *host = mmc_priv(cq_host->mmc); + struct mmc_host *mmc = mmc_from_crypto_profile(profile); + struct sdhci_host *host = mmc_priv(mmc); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); - union cqhci_crypto_cap_entry cap; + + return msm_host; +} + +/* + * Program a key into a QC ICE keyslot. QC ICE requires a QC-specific SCM call + * for this; it doesn't support the standard way. + */ +static int sdhci_msm_ice_keyslot_program(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, + unsigned int slot) +{ + struct sdhci_msm_host *msm_host = + sdhci_msm_host_from_crypto_profile(profile); /* Only AES-256-XTS has been tested so far. */ - cap = cq_host->crypto_cap_array[cfg->crypto_cap_idx]; - if (cap.algorithm_id != CQHCI_CRYPTO_ALG_AES_XTS || - cap.key_size != CQHCI_CRYPTO_KEY_SIZE_256) - return -EINVAL; + if (key->crypto_cfg.crypto_mode != BLK_ENCRYPTION_MODE_AES_256_XTS) + return -EOPNOTSUPP; - if (cfg->config_enable & CQHCI_CRYPTO_CONFIGURATION_ENABLE) - return qcom_ice_program_key(msm_host->ice, - QCOM_ICE_CRYPTO_ALG_AES_XTS, - QCOM_ICE_CRYPTO_KEY_SIZE_256, - cfg->crypto_key, - cfg->data_unit_size, slot); - else - return qcom_ice_evict_key(msm_host->ice, slot); + return qcom_ice_program_key(msm_host->ice, + QCOM_ICE_CRYPTO_ALG_AES_XTS, + QCOM_ICE_CRYPTO_KEY_SIZE_256, + key->raw, + key->crypto_cfg.data_unit_size / 512, + slot); } +static int sdhci_msm_ice_keyslot_evict(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, + unsigned int slot) +{ + struct sdhci_msm_host *msm_host = + sdhci_msm_host_from_crypto_profile(profile); + + return qcom_ice_evict_key(msm_host->ice, slot); +} + +static const struct blk_crypto_ll_ops sdhci_msm_crypto_ops = { + .keyslot_program = sdhci_msm_ice_keyslot_program, + .keyslot_evict = sdhci_msm_ice_keyslot_evict, +}; + #else /* CONFIG_MMC_CRYPTO */ static inline int sdhci_msm_ice_init(struct sdhci_msm_host *msm_host, @@ -1988,7 +2093,7 @@ static const struct cqhci_host_ops sdhci_msm_cqhci_ops = { .enable = sdhci_msm_cqe_enable, .disable = sdhci_msm_cqe_disable, #ifdef CONFIG_MMC_CRYPTO - .program_key = sdhci_msm_program_key, + .uses_custom_crypto_profile = true, #endif }; diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 4d402b601883..b2f5c3f8b839 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -1525,7 +1525,6 @@ static const struct sdhci_pltfm_data sdhci_tegra186_pdata = { .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | SDHCI_QUIRK_SINGLE_POWER_WRITE | SDHCI_QUIRK_NO_HISPD_BIT | - SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC | SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | SDHCI_QUIRK2_ISSUE_CMD_DAT_RESET_TOGETHER, diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 45a474ccab1c..04c1c54df791 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -297,7 +297,6 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, switch (mmc_resp_type(cmd)) { case MMC_RSP_NONE: c |= RESP_NONE; break; case MMC_RSP_R1: - case MMC_RSP_R1_NO_CRC: c |= RESP_R1; break; case MMC_RSP_R1B: c |= RESP_R1B; break; case MMC_RSP_R2: c |= RESP_R2; break; diff --git a/drivers/mtd/devices/mchp48l640.c b/drivers/mtd/devices/mchp48l640.c index f576e6a890e8..7584d0ba9396 100644 --- a/drivers/mtd/devices/mchp48l640.c +++ b/drivers/mtd/devices/mchp48l640.c @@ -27,6 +27,7 @@ struct mchp48_caps { unsigned int size; unsigned int page_size; + bool auto_disable_wel; }; struct mchp48l640_flash { @@ -194,9 +195,15 @@ static int mchp48l640_write_page(struct mtd_info *mtd, loff_t to, size_t len, else goto fail; - ret = mchp48l640_waitforbit(flash, MCHP48L640_STATUS_WEL, false); - if (ret) - goto fail; + if (flash->caps->auto_disable_wel) { + ret = mchp48l640_waitforbit(flash, MCHP48L640_STATUS_WEL, false); + if (ret) + goto fail; + } else { + ret = mchp48l640_write_prepare(flash, false); + if (ret) + goto fail; + } kfree(cmd); return 0; @@ -293,6 +300,13 @@ static int mchp48l640_read(struct mtd_info *mtd, loff_t from, size_t len, static const struct mchp48_caps mchp48l640_caps = { .size = SZ_8K, .page_size = 32, + .auto_disable_wel = true, +}; + +static const struct mchp48_caps mb85rs128ty_caps = { + .size = SZ_16K, + .page_size = 256, + .auto_disable_wel = false, }; static int mchp48l640_probe(struct spi_device *spi) @@ -353,6 +367,10 @@ static const struct of_device_id mchp48l640_of_table[] = { .compatible = "microchip,48l640", .data = &mchp48l640_caps, }, + { + .compatible = "fujitsu,mb85rs128ty", + .data = &mb85rs128ty_caps, + }, {} }; MODULE_DEVICE_TABLE(of, mchp48l640_of_table); @@ -362,6 +380,10 @@ static const struct spi_device_id mchp48l640_spi_ids[] = { .name = "48l640", .driver_data = (kernel_ulong_t)&mchp48l640_caps, }, + { + .name = "mb85rs128ty", + .driver_data = (kernel_ulong_t)&mb85rs128ty_caps, + }, {} }; MODULE_DEVICE_TABLE(spi, mchp48l640_spi_ids); diff --git a/drivers/mtd/devices/phram.c b/drivers/mtd/devices/phram.c index f756c60a4931..fd9ec165e61a 100644 --- a/drivers/mtd/devices/phram.c +++ b/drivers/mtd/devices/phram.c @@ -30,6 +30,7 @@ #include #include #include +#include struct phram_mtd_list { struct mtd_info mtd; @@ -410,19 +411,23 @@ static int __init init_phram(void) { int ret; + ret = security_locked_down(LOCKDOWN_DEV_MEM); + if (ret) + return ret; + ret = platform_driver_register(&phram_driver); if (ret) return ret; #ifndef MODULE - if (phram_paramline[0]) + if (phram_paramline[0]) { ret = phram_setup(phram_paramline); + if (ret) + platform_driver_unregister(&phram_driver); + } phram_init_called = 1; #endif - if (ret) - platform_driver_unregister(&phram_driver); - return ret; } diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c index dba584fa2a53..f2266145b821 100644 --- a/drivers/mtd/devices/st_spi_fsm.c +++ b/drivers/mtd/devices/st_spi_fsm.c @@ -2104,7 +2104,6 @@ static void stfsm_remove(struct platform_device *pdev) WARN_ON(mtd_device_unregister(&fsm->mtd)); } -#ifdef CONFIG_PM_SLEEP static int stfsmfsm_suspend(struct device *dev) { struct stfsm *fsm = dev_get_drvdata(dev); @@ -2120,9 +2119,8 @@ static int stfsmfsm_resume(struct device *dev) return clk_prepare_enable(fsm->clk); } -#endif -static SIMPLE_DEV_PM_OPS(stfsm_pm_ops, stfsmfsm_suspend, stfsmfsm_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(stfsm_pm_ops, stfsmfsm_suspend, stfsmfsm_resume); static const struct of_device_id stfsm_match[] = { { .compatible = "st,spi-fsm", }, @@ -2136,7 +2134,7 @@ static struct platform_driver stfsm_driver = { .driver = { .name = "st-spi-fsm", .of_match_table = stfsm_match, - .pm = &stfsm_pm_ops, + .pm = pm_sleep_ptr(&stfsm_pm_ops), }, }; module_platform_driver(stfsm_driver); diff --git a/drivers/mtd/hyperbus/hbmc-am654.c b/drivers/mtd/hyperbus/hbmc-am654.c index 217f4e69233f..82a1e7b7e4d8 100644 --- a/drivers/mtd/hyperbus/hbmc-am654.c +++ b/drivers/mtd/hyperbus/hbmc-am654.c @@ -174,26 +174,30 @@ static int am654_hbmc_probe(struct platform_device *pdev) priv->hbdev.np = of_get_next_child(np, NULL); ret = of_address_to_resource(priv->hbdev.np, 0, &res); if (ret) - return ret; + goto put_node; - if (of_property_read_bool(dev->of_node, "mux-controls")) { + if (of_property_present(dev->of_node, "mux-controls")) { struct mux_control *control = devm_mux_control_get(dev, NULL); - if (IS_ERR(control)) - return PTR_ERR(control); + if (IS_ERR(control)) { + ret = PTR_ERR(control); + goto put_node; + } ret = mux_control_select(control, 1); if (ret) { dev_err(dev, "Failed to select HBMC mux\n"); - return ret; + goto put_node; } priv->mux_ctrl = control; } priv->hbdev.map.size = resource_size(&res); priv->hbdev.map.virt = devm_ioremap_resource(dev, &res); - if (IS_ERR(priv->hbdev.map.virt)) - return PTR_ERR(priv->hbdev.map.virt); + if (IS_ERR(priv->hbdev.map.virt)) { + ret = PTR_ERR(priv->hbdev.map.virt); + goto disable_mux; + } priv->ctlr.dev = dev; priv->ctlr.ops = &am654_hbmc_ops; @@ -226,6 +230,8 @@ release_dma: disable_mux: if (priv->mux_ctrl) mux_control_deselect(priv->mux_ctrl); +put_node: + of_node_put(priv->hbdev.np); return ret; } @@ -241,6 +247,7 @@ static void am654_hbmc_remove(struct platform_device *pdev) if (dev_priv->rx_chan) dma_release_channel(dev_priv->rx_chan); + of_node_put(priv->hbdev.np); } static const struct of_device_id am654_hbmc_dt_ids[] = { diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 47ead84407cd..847c11542f02 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -329,7 +329,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) goto out_list_del; ret = blk_mq_alloc_sq_tag_set(new->tag_set, &mtd_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); + BLK_MQ_F_BLOCKING); if (ret) goto out_kfree_tag_set; @@ -404,6 +404,7 @@ out_list_del: int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old) { unsigned long flags; + unsigned int memflags; lockdep_assert_held(&mtd_table_mutex); @@ -420,10 +421,10 @@ int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old) spin_unlock_irqrestore(&old->queue_lock, flags); /* freeze+quiesce queue to ensure all requests are flushed */ - blk_mq_freeze_queue(old->rq); + memflags = blk_mq_freeze_queue(old->rq); blk_mq_quiesce_queue(old->rq); blk_mq_unquiesce_queue(old->rq); - blk_mq_unfreeze_queue(old->rq); + blk_mq_unfreeze_queue(old->rq, memflags); /* If the device is currently open, tell trans driver to close it, then put mtd device, and don't touch it again */ diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile index 19e1291ac4d5..da1586a36574 100644 --- a/drivers/mtd/nand/Makefile +++ b/drivers/mtd/nand/Makefile @@ -3,7 +3,7 @@ nandcore-objs := core.o bbt.o obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o obj-$(CONFIG_MTD_NAND_ECC_MEDIATEK) += ecc-mtk.o - +obj-$(CONFIG_MTD_NAND_QCOM) += qpic_common.o obj-y += onenand/ obj-y += raw/ obj-y += spi/ diff --git a/drivers/mtd/nand/onenand/onenand_base.c b/drivers/mtd/nand/onenand/onenand_base.c index f66385faf631..0dc2ea4fc857 100644 --- a/drivers/mtd/nand/onenand/onenand_base.c +++ b/drivers/mtd/nand/onenand/onenand_base.c @@ -2923,6 +2923,7 @@ static int do_otp_read(struct mtd_info *mtd, loff_t from, size_t len, ret = ONENAND_IS_4KB_PAGE(this) ? onenand_mlc_read_ops_nolock(mtd, from, &ops) : onenand_read_ops_nolock(mtd, from, &ops); + *retlen = ops.retlen; /* Exit OTP access mode */ this->command(mtd, ONENAND_CMD_RESET, 0, 0); diff --git a/drivers/mtd/nand/qpic_common.c b/drivers/mtd/nand/qpic_common.c new file mode 100644 index 000000000000..e0ed25b5afea --- /dev/null +++ b/drivers/mtd/nand/qpic_common.c @@ -0,0 +1,759 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2016, The Linux Foundation. All rights reserved. + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * qcom_free_bam_transaction() - Frees the BAM transaction memory + * @nandc: qpic nand controller + * + * This function frees the bam transaction memory + */ +void qcom_free_bam_transaction(struct qcom_nand_controller *nandc) +{ + struct bam_transaction *bam_txn = nandc->bam_txn; + + kfree(bam_txn); +} +EXPORT_SYMBOL(qcom_free_bam_transaction); + +/** + * qcom_alloc_bam_transaction() - allocate BAM transaction + * @nandc: qpic nand controller + * + * This function will allocate and initialize the BAM transaction structure + */ +struct bam_transaction * +qcom_alloc_bam_transaction(struct qcom_nand_controller *nandc) +{ + struct bam_transaction *bam_txn; + size_t bam_txn_size; + unsigned int num_cw = nandc->max_cwperpage; + void *bam_txn_buf; + + bam_txn_size = + sizeof(*bam_txn) + num_cw * + ((sizeof(*bam_txn->bam_ce) * QPIC_PER_CW_CMD_ELEMENTS) + + (sizeof(*bam_txn->cmd_sgl) * QPIC_PER_CW_CMD_SGL) + + (sizeof(*bam_txn->data_sgl) * QPIC_PER_CW_DATA_SGL)); + + bam_txn_buf = kzalloc(bam_txn_size, GFP_KERNEL); + if (!bam_txn_buf) + return NULL; + + bam_txn = bam_txn_buf; + bam_txn_buf += sizeof(*bam_txn); + + bam_txn->bam_ce = bam_txn_buf; + bam_txn_buf += + sizeof(*bam_txn->bam_ce) * QPIC_PER_CW_CMD_ELEMENTS * num_cw; + + bam_txn->cmd_sgl = bam_txn_buf; + bam_txn_buf += + sizeof(*bam_txn->cmd_sgl) * QPIC_PER_CW_CMD_SGL * num_cw; + + bam_txn->data_sgl = bam_txn_buf; + + init_completion(&bam_txn->txn_done); + + return bam_txn; +} +EXPORT_SYMBOL(qcom_alloc_bam_transaction); + +/** + * qcom_clear_bam_transaction() - Clears the BAM transaction + * @nandc: qpic nand controller + * + * This function will clear the BAM transaction indexes. + */ +void qcom_clear_bam_transaction(struct qcom_nand_controller *nandc) +{ + struct bam_transaction *bam_txn = nandc->bam_txn; + + if (!nandc->props->supports_bam) + return; + + memset(&bam_txn->bam_positions, 0, sizeof(bam_txn->bam_positions)); + bam_txn->last_data_desc = NULL; + + sg_init_table(bam_txn->cmd_sgl, nandc->max_cwperpage * + QPIC_PER_CW_CMD_SGL); + sg_init_table(bam_txn->data_sgl, nandc->max_cwperpage * + QPIC_PER_CW_DATA_SGL); + + reinit_completion(&bam_txn->txn_done); +} +EXPORT_SYMBOL(qcom_clear_bam_transaction); + +/** + * qcom_qpic_bam_dma_done() - Callback for DMA descriptor completion + * @data: data pointer + * + * This function is a callback for DMA descriptor completion + */ +void qcom_qpic_bam_dma_done(void *data) +{ + struct bam_transaction *bam_txn = data; + + complete(&bam_txn->txn_done); +} +EXPORT_SYMBOL(qcom_qpic_bam_dma_done); + +/** + * qcom_nandc_dev_to_mem() - Check for dma sync for cpu or device + * @nandc: qpic nand controller + * @is_cpu: cpu or Device + * + * This function will check for dma sync for cpu or device + */ +inline void qcom_nandc_dev_to_mem(struct qcom_nand_controller *nandc, bool is_cpu) +{ + if (!nandc->props->supports_bam) + return; + + if (is_cpu) + dma_sync_single_for_cpu(nandc->dev, nandc->reg_read_dma, + MAX_REG_RD * + sizeof(*nandc->reg_read_buf), + DMA_FROM_DEVICE); + else + dma_sync_single_for_device(nandc->dev, nandc->reg_read_dma, + MAX_REG_RD * + sizeof(*nandc->reg_read_buf), + DMA_FROM_DEVICE); +} +EXPORT_SYMBOL(qcom_nandc_dev_to_mem); + +/** + * qcom_prepare_bam_async_desc() - Prepare DMA descriptor + * @nandc: qpic nand controller + * @chan: dma channel + * @flags: flags to control DMA descriptor preparation + * + * This function maps the scatter gather list for DMA transfer and forms the + * DMA descriptor for BAM.This descriptor will be added in the NAND DMA + * descriptor queue which will be submitted to DMA engine. + */ +int qcom_prepare_bam_async_desc(struct qcom_nand_controller *nandc, + struct dma_chan *chan, unsigned long flags) +{ + struct desc_info *desc; + struct scatterlist *sgl; + unsigned int sgl_cnt; + int ret; + struct bam_transaction *bam_txn = nandc->bam_txn; + enum dma_transfer_direction dir_eng; + struct dma_async_tx_descriptor *dma_desc; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + if (chan == nandc->cmd_chan) { + sgl = &bam_txn->cmd_sgl[bam_txn->cmd_sgl_start]; + sgl_cnt = bam_txn->cmd_sgl_pos - bam_txn->cmd_sgl_start; + bam_txn->cmd_sgl_start = bam_txn->cmd_sgl_pos; + dir_eng = DMA_MEM_TO_DEV; + desc->dir = DMA_TO_DEVICE; + } else if (chan == nandc->tx_chan) { + sgl = &bam_txn->data_sgl[bam_txn->tx_sgl_start]; + sgl_cnt = bam_txn->tx_sgl_pos - bam_txn->tx_sgl_start; + bam_txn->tx_sgl_start = bam_txn->tx_sgl_pos; + dir_eng = DMA_MEM_TO_DEV; + desc->dir = DMA_TO_DEVICE; + } else { + sgl = &bam_txn->data_sgl[bam_txn->rx_sgl_start]; + sgl_cnt = bam_txn->rx_sgl_pos - bam_txn->rx_sgl_start; + bam_txn->rx_sgl_start = bam_txn->rx_sgl_pos; + dir_eng = DMA_DEV_TO_MEM; + desc->dir = DMA_FROM_DEVICE; + } + + sg_mark_end(sgl + sgl_cnt - 1); + ret = dma_map_sg(nandc->dev, sgl, sgl_cnt, desc->dir); + if (ret == 0) { + dev_err(nandc->dev, "failure in mapping desc\n"); + kfree(desc); + return -ENOMEM; + } + + desc->sgl_cnt = sgl_cnt; + desc->bam_sgl = sgl; + + dma_desc = dmaengine_prep_slave_sg(chan, sgl, sgl_cnt, dir_eng, + flags); + + if (!dma_desc) { + dev_err(nandc->dev, "failure in prep desc\n"); + dma_unmap_sg(nandc->dev, sgl, sgl_cnt, desc->dir); + kfree(desc); + return -EINVAL; + } + + desc->dma_desc = dma_desc; + + /* update last data/command descriptor */ + if (chan == nandc->cmd_chan) + bam_txn->last_cmd_desc = dma_desc; + else + bam_txn->last_data_desc = dma_desc; + + list_add_tail(&desc->node, &nandc->desc_list); + + return 0; +} +EXPORT_SYMBOL(qcom_prepare_bam_async_desc); + +/** + * qcom_prep_bam_dma_desc_cmd() - Prepares the command descriptor for BAM DMA + * @nandc: qpic nand controller + * @read: read or write type + * @reg_off: offset within the controller's data buffer + * @vaddr: virtual address of the buffer we want to write to + * @size: DMA transaction size in bytes + * @flags: flags to control DMA descriptor preparation + * + * This function will prepares the command descriptor for BAM DMA + * which will be used for NAND register reads and writes. + */ +int qcom_prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read, + int reg_off, const void *vaddr, + int size, unsigned int flags) +{ + int bam_ce_size; + int i, ret; + struct bam_cmd_element *bam_ce_buffer; + struct bam_transaction *bam_txn = nandc->bam_txn; + + bam_ce_buffer = &bam_txn->bam_ce[bam_txn->bam_ce_pos]; + + /* fill the command desc */ + for (i = 0; i < size; i++) { + if (read) + bam_prep_ce(&bam_ce_buffer[i], + nandc_reg_phys(nandc, reg_off + 4 * i), + BAM_READ_COMMAND, + reg_buf_dma_addr(nandc, + (__le32 *)vaddr + i)); + else + bam_prep_ce_le32(&bam_ce_buffer[i], + nandc_reg_phys(nandc, reg_off + 4 * i), + BAM_WRITE_COMMAND, + *((__le32 *)vaddr + i)); + } + + bam_txn->bam_ce_pos += size; + + /* use the separate sgl after this command */ + if (flags & NAND_BAM_NEXT_SGL) { + bam_ce_buffer = &bam_txn->bam_ce[bam_txn->bam_ce_start]; + bam_ce_size = (bam_txn->bam_ce_pos - + bam_txn->bam_ce_start) * + sizeof(struct bam_cmd_element); + sg_set_buf(&bam_txn->cmd_sgl[bam_txn->cmd_sgl_pos], + bam_ce_buffer, bam_ce_size); + bam_txn->cmd_sgl_pos++; + bam_txn->bam_ce_start = bam_txn->bam_ce_pos; + + if (flags & NAND_BAM_NWD) { + ret = qcom_prepare_bam_async_desc(nandc, nandc->cmd_chan, + DMA_PREP_FENCE | DMA_PREP_CMD); + if (ret) + return ret; + } + } + + return 0; +} +EXPORT_SYMBOL(qcom_prep_bam_dma_desc_cmd); + +/** + * qcom_prep_bam_dma_desc_data() - Prepares the data descriptor for BAM DMA + * @nandc: qpic nand controller + * @read: read or write type + * @vaddr: virtual address of the buffer we want to write to + * @size: DMA transaction size in bytes + * @flags: flags to control DMA descriptor preparation + * + * This function will prepares the data descriptor for BAM DMA which + * will be used for NAND data reads and writes. + */ +int qcom_prep_bam_dma_desc_data(struct qcom_nand_controller *nandc, bool read, + const void *vaddr, int size, unsigned int flags) +{ + int ret; + struct bam_transaction *bam_txn = nandc->bam_txn; + + if (read) { + sg_set_buf(&bam_txn->data_sgl[bam_txn->rx_sgl_pos], + vaddr, size); + bam_txn->rx_sgl_pos++; + } else { + sg_set_buf(&bam_txn->data_sgl[bam_txn->tx_sgl_pos], + vaddr, size); + bam_txn->tx_sgl_pos++; + + /* + * BAM will only set EOT for DMA_PREP_INTERRUPT so if this flag + * is not set, form the DMA descriptor + */ + if (!(flags & NAND_BAM_NO_EOT)) { + ret = qcom_prepare_bam_async_desc(nandc, nandc->tx_chan, + DMA_PREP_INTERRUPT); + if (ret) + return ret; + } + } + + return 0; +} +EXPORT_SYMBOL(qcom_prep_bam_dma_desc_data); + +/** + * qcom_prep_adm_dma_desc() - Prepare descriptor for adma + * @nandc: qpic nand controller + * @read: read or write type + * @reg_off: offset within the controller's data buffer + * @vaddr: virtual address of the buffer we want to write to + * @size: adm dma transaction size in bytes + * @flow_control: flow controller + * + * This function will prepare descriptor for adma + */ +int qcom_prep_adm_dma_desc(struct qcom_nand_controller *nandc, bool read, + int reg_off, const void *vaddr, int size, + bool flow_control) +{ + struct qcom_adm_peripheral_config periph_conf = {}; + struct dma_async_tx_descriptor *dma_desc; + struct dma_slave_config slave_conf = {0}; + enum dma_transfer_direction dir_eng; + struct desc_info *desc; + struct scatterlist *sgl; + int ret; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + sgl = &desc->adm_sgl; + + sg_init_one(sgl, vaddr, size); + + if (read) { + dir_eng = DMA_DEV_TO_MEM; + desc->dir = DMA_FROM_DEVICE; + } else { + dir_eng = DMA_MEM_TO_DEV; + desc->dir = DMA_TO_DEVICE; + } + + ret = dma_map_sg(nandc->dev, sgl, 1, desc->dir); + if (!ret) { + ret = -ENOMEM; + goto err; + } + + slave_conf.device_fc = flow_control; + if (read) { + slave_conf.src_maxburst = 16; + slave_conf.src_addr = nandc->base_dma + reg_off; + if (nandc->data_crci) { + periph_conf.crci = nandc->data_crci; + slave_conf.peripheral_config = &periph_conf; + slave_conf.peripheral_size = sizeof(periph_conf); + } + } else { + slave_conf.dst_maxburst = 16; + slave_conf.dst_addr = nandc->base_dma + reg_off; + if (nandc->cmd_crci) { + periph_conf.crci = nandc->cmd_crci; + slave_conf.peripheral_config = &periph_conf; + slave_conf.peripheral_size = sizeof(periph_conf); + } + } + + ret = dmaengine_slave_config(nandc->chan, &slave_conf); + if (ret) { + dev_err(nandc->dev, "failed to configure dma channel\n"); + goto err; + } + + dma_desc = dmaengine_prep_slave_sg(nandc->chan, sgl, 1, dir_eng, 0); + if (!dma_desc) { + dev_err(nandc->dev, "failed to prepare desc\n"); + ret = -EINVAL; + goto err; + } + + desc->dma_desc = dma_desc; + + list_add_tail(&desc->node, &nandc->desc_list); + + return 0; +err: + kfree(desc); + + return ret; +} +EXPORT_SYMBOL(qcom_prep_adm_dma_desc); + +/** + * qcom_read_reg_dma() - read a given number of registers to the reg_read_buf pointer + * @nandc: qpic nand controller + * @first: offset of the first register in the contiguous block + * @num_regs: number of registers to read + * @flags: flags to control DMA descriptor preparation + * + * This function will prepares a descriptor to read a given number of + * contiguous registers to the reg_read_buf pointer. + */ +int qcom_read_reg_dma(struct qcom_nand_controller *nandc, int first, + int num_regs, unsigned int flags) +{ + bool flow_control = false; + void *vaddr; + + vaddr = nandc->reg_read_buf + nandc->reg_read_pos; + nandc->reg_read_pos += num_regs; + + if (first == NAND_DEV_CMD_VLD || first == NAND_DEV_CMD1) + first = dev_cmd_reg_addr(nandc, first); + + if (nandc->props->supports_bam) + return qcom_prep_bam_dma_desc_cmd(nandc, true, first, vaddr, + num_regs, flags); + + if (first == NAND_READ_ID || first == NAND_FLASH_STATUS) + flow_control = true; + + return qcom_prep_adm_dma_desc(nandc, true, first, vaddr, + num_regs * sizeof(u32), flow_control); +} +EXPORT_SYMBOL(qcom_read_reg_dma); + +/** + * qcom_write_reg_dma() - write a given number of registers + * @nandc: qpic nand controller + * @vaddr: contiguous memory from where register value will + * be written + * @first: offset of the first register in the contiguous block + * @num_regs: number of registers to write + * @flags: flags to control DMA descriptor preparation + * + * This function will prepares a descriptor to write a given number of + * contiguous registers + */ +int qcom_write_reg_dma(struct qcom_nand_controller *nandc, __le32 *vaddr, + int first, int num_regs, unsigned int flags) +{ + bool flow_control = false; + + if (first == NAND_EXEC_CMD) + flags |= NAND_BAM_NWD; + + if (first == NAND_DEV_CMD1_RESTORE || first == NAND_DEV_CMD1) + first = dev_cmd_reg_addr(nandc, NAND_DEV_CMD1); + + if (first == NAND_DEV_CMD_VLD_RESTORE || first == NAND_DEV_CMD_VLD) + first = dev_cmd_reg_addr(nandc, NAND_DEV_CMD_VLD); + + if (nandc->props->supports_bam) + return qcom_prep_bam_dma_desc_cmd(nandc, false, first, vaddr, + num_regs, flags); + + if (first == NAND_FLASH_CMD) + flow_control = true; + + return qcom_prep_adm_dma_desc(nandc, false, first, vaddr, + num_regs * sizeof(u32), flow_control); +} +EXPORT_SYMBOL(qcom_write_reg_dma); + +/** + * qcom_read_data_dma() - transfer data + * @nandc: qpic nand controller + * @reg_off: offset within the controller's data buffer + * @vaddr: virtual address of the buffer we want to write to + * @size: DMA transaction size in bytes + * @flags: flags to control DMA descriptor preparation + * + * This function will prepares a DMA descriptor to transfer data from the + * controller's internal buffer to the buffer 'vaddr' + */ +int qcom_read_data_dma(struct qcom_nand_controller *nandc, int reg_off, + const u8 *vaddr, int size, unsigned int flags) +{ + if (nandc->props->supports_bam) + return qcom_prep_bam_dma_desc_data(nandc, true, vaddr, size, flags); + + return qcom_prep_adm_dma_desc(nandc, true, reg_off, vaddr, size, false); +} +EXPORT_SYMBOL(qcom_read_data_dma); + +/** + * qcom_write_data_dma() - transfer data + * @nandc: qpic nand controller + * @reg_off: offset within the controller's data buffer + * @vaddr: virtual address of the buffer we want to read from + * @size: DMA transaction size in bytes + * @flags: flags to control DMA descriptor preparation + * + * This function will prepares a DMA descriptor to transfer data from + * 'vaddr' to the controller's internal buffer + */ +int qcom_write_data_dma(struct qcom_nand_controller *nandc, int reg_off, + const u8 *vaddr, int size, unsigned int flags) +{ + if (nandc->props->supports_bam) + return qcom_prep_bam_dma_desc_data(nandc, false, vaddr, size, flags); + + return qcom_prep_adm_dma_desc(nandc, false, reg_off, vaddr, size, false); +} +EXPORT_SYMBOL(qcom_write_data_dma); + +/** + * qcom_submit_descs() - submit dma descriptor + * @nandc: qpic nand controller + * + * This function will submit all the prepared dma descriptor + * cmd or data descriptor + */ +int qcom_submit_descs(struct qcom_nand_controller *nandc) +{ + struct desc_info *desc, *n; + dma_cookie_t cookie = 0; + struct bam_transaction *bam_txn = nandc->bam_txn; + int ret = 0; + + if (nandc->props->supports_bam) { + if (bam_txn->rx_sgl_pos > bam_txn->rx_sgl_start) { + ret = qcom_prepare_bam_async_desc(nandc, nandc->rx_chan, 0); + if (ret) + goto err_unmap_free_desc; + } + + if (bam_txn->tx_sgl_pos > bam_txn->tx_sgl_start) { + ret = qcom_prepare_bam_async_desc(nandc, nandc->tx_chan, + DMA_PREP_INTERRUPT); + if (ret) + goto err_unmap_free_desc; + } + + if (bam_txn->cmd_sgl_pos > bam_txn->cmd_sgl_start) { + ret = qcom_prepare_bam_async_desc(nandc, nandc->cmd_chan, + DMA_PREP_CMD); + if (ret) + goto err_unmap_free_desc; + } + } + + list_for_each_entry(desc, &nandc->desc_list, node) + cookie = dmaengine_submit(desc->dma_desc); + + if (nandc->props->supports_bam) { + bam_txn->last_cmd_desc->callback = qcom_qpic_bam_dma_done; + bam_txn->last_cmd_desc->callback_param = bam_txn; + + dma_async_issue_pending(nandc->tx_chan); + dma_async_issue_pending(nandc->rx_chan); + dma_async_issue_pending(nandc->cmd_chan); + + if (!wait_for_completion_timeout(&bam_txn->txn_done, + QPIC_NAND_COMPLETION_TIMEOUT)) + ret = -ETIMEDOUT; + } else { + if (dma_sync_wait(nandc->chan, cookie) != DMA_COMPLETE) + ret = -ETIMEDOUT; + } + +err_unmap_free_desc: + /* + * Unmap the dma sg_list and free the desc allocated by both + * qcom_prepare_bam_async_desc() and qcom_prep_adm_dma_desc() functions. + */ + list_for_each_entry_safe(desc, n, &nandc->desc_list, node) { + list_del(&desc->node); + + if (nandc->props->supports_bam) + dma_unmap_sg(nandc->dev, desc->bam_sgl, + desc->sgl_cnt, desc->dir); + else + dma_unmap_sg(nandc->dev, &desc->adm_sgl, 1, + desc->dir); + + kfree(desc); + } + + return ret; +} +EXPORT_SYMBOL(qcom_submit_descs); + +/** + * qcom_clear_read_regs() - reset the read register buffer + * @nandc: qpic nand controller + * + * This function reset the register read buffer for next NAND operation + */ +void qcom_clear_read_regs(struct qcom_nand_controller *nandc) +{ + nandc->reg_read_pos = 0; + qcom_nandc_dev_to_mem(nandc, false); +} +EXPORT_SYMBOL(qcom_clear_read_regs); + +/** + * qcom_nandc_unalloc() - unallocate qpic nand controller + * @nandc: qpic nand controller + * + * This function will unallocate memory alloacted for qpic nand controller + */ +void qcom_nandc_unalloc(struct qcom_nand_controller *nandc) +{ + if (nandc->props->supports_bam) { + if (!dma_mapping_error(nandc->dev, nandc->reg_read_dma)) + dma_unmap_single(nandc->dev, nandc->reg_read_dma, + MAX_REG_RD * + sizeof(*nandc->reg_read_buf), + DMA_FROM_DEVICE); + + if (nandc->tx_chan) + dma_release_channel(nandc->tx_chan); + + if (nandc->rx_chan) + dma_release_channel(nandc->rx_chan); + + if (nandc->cmd_chan) + dma_release_channel(nandc->cmd_chan); + } else { + if (nandc->chan) + dma_release_channel(nandc->chan); + } +} +EXPORT_SYMBOL(qcom_nandc_unalloc); + +/** + * qcom_nandc_alloc() - Allocate qpic nand controller + * @nandc: qpic nand controller + * + * This function will allocate memory for qpic nand controller + */ +int qcom_nandc_alloc(struct qcom_nand_controller *nandc) +{ + int ret; + + ret = dma_set_coherent_mask(nandc->dev, DMA_BIT_MASK(32)); + if (ret) { + dev_err(nandc->dev, "failed to set DMA mask\n"); + return ret; + } + + /* + * we use the internal buffer for reading ONFI params, reading small + * data like ID and status, and preforming read-copy-write operations + * when writing to a codeword partially. 532 is the maximum possible + * size of a codeword for our nand controller + */ + nandc->buf_size = 532; + + nandc->data_buffer = devm_kzalloc(nandc->dev, nandc->buf_size, GFP_KERNEL); + if (!nandc->data_buffer) + return -ENOMEM; + + nandc->regs = devm_kzalloc(nandc->dev, sizeof(*nandc->regs), GFP_KERNEL); + if (!nandc->regs) + return -ENOMEM; + + nandc->reg_read_buf = devm_kcalloc(nandc->dev, MAX_REG_RD, + sizeof(*nandc->reg_read_buf), + GFP_KERNEL); + if (!nandc->reg_read_buf) + return -ENOMEM; + + if (nandc->props->supports_bam) { + nandc->reg_read_dma = + dma_map_single(nandc->dev, nandc->reg_read_buf, + MAX_REG_RD * + sizeof(*nandc->reg_read_buf), + DMA_FROM_DEVICE); + if (dma_mapping_error(nandc->dev, nandc->reg_read_dma)) { + dev_err(nandc->dev, "failed to DMA MAP reg buffer\n"); + return -EIO; + } + + nandc->tx_chan = dma_request_chan(nandc->dev, "tx"); + if (IS_ERR(nandc->tx_chan)) { + ret = PTR_ERR(nandc->tx_chan); + nandc->tx_chan = NULL; + dev_err_probe(nandc->dev, ret, + "tx DMA channel request failed\n"); + goto unalloc; + } + + nandc->rx_chan = dma_request_chan(nandc->dev, "rx"); + if (IS_ERR(nandc->rx_chan)) { + ret = PTR_ERR(nandc->rx_chan); + nandc->rx_chan = NULL; + dev_err_probe(nandc->dev, ret, + "rx DMA channel request failed\n"); + goto unalloc; + } + + nandc->cmd_chan = dma_request_chan(nandc->dev, "cmd"); + if (IS_ERR(nandc->cmd_chan)) { + ret = PTR_ERR(nandc->cmd_chan); + nandc->cmd_chan = NULL; + dev_err_probe(nandc->dev, ret, + "cmd DMA channel request failed\n"); + goto unalloc; + } + + /* + * Initially allocate BAM transaction to read ONFI param page. + * After detecting all the devices, this BAM transaction will + * be freed and the next BAM transaction will be allocated with + * maximum codeword size + */ + nandc->max_cwperpage = 1; + nandc->bam_txn = qcom_alloc_bam_transaction(nandc); + if (!nandc->bam_txn) { + dev_err(nandc->dev, + "failed to allocate bam transaction\n"); + ret = -ENOMEM; + goto unalloc; + } + } else { + nandc->chan = dma_request_chan(nandc->dev, "rxtx"); + if (IS_ERR(nandc->chan)) { + ret = PTR_ERR(nandc->chan); + nandc->chan = NULL; + dev_err_probe(nandc->dev, ret, + "rxtx DMA channel request failed\n"); + return ret; + } + } + + INIT_LIST_HEAD(&nandc->desc_list); + INIT_LIST_HEAD(&nandc->host_list); + + return 0; +unalloc: + qcom_nandc_unalloc(nandc); + return ret; +} +EXPORT_SYMBOL(qcom_nandc_alloc); + +MODULE_DESCRIPTION("QPIC controller common api"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig index d0aaccf72d78..b8035df8f732 100644 --- a/drivers/mtd/nand/raw/Kconfig +++ b/drivers/mtd/nand/raw/Kconfig @@ -279,8 +279,8 @@ config MTD_NAND_SH_FLCTL config MTD_NAND_DAVINCI tristate "DaVinci/Keystone NAND controller" - depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF) || COMPILE_TEST - depends on HAS_IOMEM + depends on COMPILE_TEST || ARCH_DAVINCI || ARCH_KEYSTONE + depends on HAS_IOMEM && TI_AEMIF help Enable the driver for NAND flash chips on Texas Instruments DaVinci/Keystone processors. @@ -454,6 +454,14 @@ config MTD_NAND_TS72XX help Enables support for NAND controller on ts72xx SBCs. +config MTD_NAND_NUVOTON_MA35 + tristate "Nuvoton MA35 SoC NAND controller" + depends on ARCH_MA35 || COMPILE_TEST + depends on OF + help + Enables support for the NAND controller found on + the Nuvoton MA35 series SoCs. + comment "Misc" config MTD_SM_COMMON diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile index d0b0e6b83568..99e79c448847 100644 --- a/drivers/mtd/nand/raw/Makefile +++ b/drivers/mtd/nand/raw/Makefile @@ -58,6 +58,7 @@ obj-$(CONFIG_MTD_NAND_INTEL_LGM) += intel-nand-controller.o obj-$(CONFIG_MTD_NAND_ROCKCHIP) += rockchip-nand-controller.o obj-$(CONFIG_MTD_NAND_PL35X) += pl35x-nand-controller.o obj-$(CONFIG_MTD_NAND_RENESAS) += renesas-nand-controller.o +obj-$(CONFIG_MTD_NAND_NUVOTON_MA35) += nuvoton-ma35d1-nand-controller.o nand-objs := nand_base.o nand_legacy.o nand_bbt.o nand_timings.o nand_ids.o nand-objs += nand_onfi.o diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c index db42aa0c7b6b..865754737f5f 100644 --- a/drivers/mtd/nand/raw/arasan-nand-controller.c +++ b/drivers/mtd/nand/raw/arasan-nand-controller.c @@ -1409,8 +1409,8 @@ static int anfc_parse_cs(struct arasan_nfc *nfc) * case, the "not" chosen CS is assigned to nfc->spare_cs and selected * whenever a GPIO CS must be asserted. */ - if (nfc->cs_array && nfc->ncs > 2) { - if (!nfc->cs_array[0] && !nfc->cs_array[1]) { + if (nfc->cs_array) { + if (nfc->ncs > 2 && !nfc->cs_array[0] && !nfc->cs_array[1]) { dev_err(nfc->dev, "Assign a single native CS when using GPIOs\n"); return -EINVAL; @@ -1478,8 +1478,15 @@ static int anfc_probe(struct platform_device *pdev) static void anfc_remove(struct platform_device *pdev) { + int i; struct arasan_nfc *nfc = platform_get_drvdata(pdev); + for (i = 0; i < nfc->ncs; i++) { + if (nfc->cs_array[i]) { + gpiod_put(nfc->cs_array[i]); + } + } + anfc_chips_cleanup(nfc); } diff --git a/drivers/mtd/nand/raw/atmel/pmecc.c b/drivers/mtd/nand/raw/atmel/pmecc.c index a22aab4ed4e8..3c7dee1be21d 100644 --- a/drivers/mtd/nand/raw/atmel/pmecc.c +++ b/drivers/mtd/nand/raw/atmel/pmecc.c @@ -380,10 +380,8 @@ atmel_pmecc_create_user(struct atmel_pmecc *pmecc, user->delta = user->dmu + req->ecc.strength + 1; gf_tables = atmel_pmecc_get_gf_tables(req); - if (IS_ERR(gf_tables)) { - kfree(user); + if (IS_ERR(gf_tables)) return ERR_CAST(gf_tables); - } user->gf_tables = gf_tables; diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index 9c253a511e45..fea5b6119956 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -2342,6 +2342,11 @@ static int brcmnand_write(struct mtd_info *mtd, struct nand_chip *chip, brcmnand_send_cmd(host, CMD_PROGRAM_PAGE); status = brcmnand_waitfunc(chip); + if (status < 0) { + ret = status; + goto out; + } + if (status & NAND_STATUS_FAIL) { dev_info(ctrl->dev, "program failed at %llx\n", (unsigned long long)addr); diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c index 1f8354acfb50..3986553881d0 100644 --- a/drivers/mtd/nand/raw/davinci_nand.c +++ b/drivers/mtd/nand/raw/davinci_nand.c @@ -10,9 +10,11 @@ * Dirk Behme */ +#include #include #include #include +#include #include #include #include @@ -43,6 +45,9 @@ #define MASK_ALE 0x08 #define MASK_CLE 0x10 +#define MAX_TSU_PS 3000 /* Input setup time in ps */ +#define MAX_TH_PS 1600 /* Input hold time in ps */ + struct davinci_nand_pdata { uint32_t mask_ale; uint32_t mask_cle; @@ -66,6 +71,7 @@ struct davinci_nand_pdata { /* none == NAND_ECC_ENGINE_TYPE_NONE (strongly *not* advised!!) * soft == NAND_ECC_ENGINE_TYPE_SOFT + * on-die == NAND_ECC_ENGINE_TYPE_ON_DIE * else == NAND_ECC_ENGINE_TYPE_ON_HOST, according to ecc_bits * * All DaVinci-family chips support 1-bit hardware ECC. @@ -117,6 +123,9 @@ struct davinci_nand_info { uint32_t mask_cle; uint32_t core_chipsel; + + struct clk *clk; + struct aemif_device *aemif; }; static DEFINE_SPINLOCK(davinci_nand_lock); @@ -479,6 +488,44 @@ static const struct mtd_ooblayout_ops hwecc4_small_ooblayout_ops = { .free = hwecc4_ooblayout_small_free, }; +static int hwecc4_ooblayout_large_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *oobregion) +{ + struct nand_device *nand = mtd_to_nanddev(mtd); + unsigned int total_ecc_bytes = nand->ecc.ctx.total; + int nregions = total_ecc_bytes / 10; /* 10 bytes per chunk */ + + if (section >= nregions) + return -ERANGE; + + oobregion->offset = (section * 16) + 6; + oobregion->length = 10; + + return 0; +} + +static int hwecc4_ooblayout_large_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *oobregion) +{ + struct nand_device *nand = mtd_to_nanddev(mtd); + unsigned int total_ecc_bytes = nand->ecc.ctx.total; + int nregions = total_ecc_bytes / 10; /* 10 bytes per chunk */ + + /* First region is used for BBT */ + if (section >= (nregions - 1)) + return -ERANGE; + + oobregion->offset = ((section + 1) * 16); + oobregion->length = 6; + + return 0; +} + +static const struct mtd_ooblayout_ops hwecc4_large_ooblayout_ops = { + .ecc = hwecc4_ooblayout_large_ecc, + .free = hwecc4_ooblayout_large_free, +}; + #if defined(CONFIG_OF) static const struct of_device_id davinci_nand_of_match[] = { {.compatible = "ti,davinci-nand", }, @@ -525,6 +572,8 @@ nand_davinci_get_pdata(struct platform_device *pdev) pdata->engine_type = NAND_ECC_ENGINE_TYPE_SOFT; if (!strncmp("hw", mode, 2)) pdata->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; + if (!strncmp("on-die", mode, 6)) + pdata->engine_type = NAND_ECC_ENGINE_TYPE_ON_DIE; } if (!device_property_read_u32(&pdev->dev, "ti,davinci-ecc-bits", &prop)) @@ -580,6 +629,7 @@ static int davinci_nand_attach_chip(struct nand_chip *chip) switch (chip->ecc.engine_type) { case NAND_ECC_ENGINE_TYPE_NONE: + case NAND_ECC_ENGINE_TYPE_ON_DIE: pdata->ecc_bits = 0; break; case NAND_ECC_ENGINE_TYPE_SOFT: @@ -638,9 +688,12 @@ static int davinci_nand_attach_chip(struct nand_chip *chip) mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops); } else if (chunks == 4 || chunks == 8) { - mtd_set_ooblayout(mtd, - nand_get_large_page_ooblayout()); chip->ecc.read_page = nand_read_page_hwecc_oob_first; + + if (chip->options & NAND_IS_BOOT_MEDIUM) + mtd_set_ooblayout(mtd, &hwecc4_large_ooblayout_ops); + else + mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout()); } else { return -EIO; } @@ -724,7 +777,7 @@ static int davinci_nand_exec_instr(struct davinci_nand_info *info, case NAND_OP_WAITRDY_INSTR: timeout_us = instr->ctx.waitrdy.timeout_ms * 1000; ret = readl_relaxed_poll_timeout(info->base + NANDFSR_OFFSET, - status, status & BIT(0), 100, + status, status & BIT(0), 5, timeout_us); if (ret) return ret; @@ -764,9 +817,82 @@ static int davinci_nand_exec_op(struct nand_chip *chip, return 0; } +#define TO_CYCLES(ps, period_ns) (DIV_ROUND_UP((ps) / 1000, (period_ns))) + +static int davinci_nand_setup_interface(struct nand_chip *chip, int chipnr, + const struct nand_interface_config *conf) +{ + struct davinci_nand_info *info = to_davinci_nand(nand_to_mtd(chip)); + const struct nand_sdr_timings *sdr; + struct aemif_cs_timings timings; + s32 cfg, min, cyc_ns; + int ret; + + cyc_ns = 1000000000 / clk_get_rate(info->clk); + + sdr = nand_get_sdr_timings(conf); + if (IS_ERR(sdr)) + return PTR_ERR(sdr); + + cfg = TO_CYCLES(sdr->tCLR_min, cyc_ns) - 1; + timings.rsetup = cfg > 0 ? cfg : 0; + + cfg = max_t(s32, TO_CYCLES(sdr->tREA_max + MAX_TSU_PS, cyc_ns), + TO_CYCLES(sdr->tRP_min, cyc_ns)) - 1; + timings.rstrobe = cfg > 0 ? cfg : 0; + + min = TO_CYCLES(sdr->tCEA_max + MAX_TSU_PS, cyc_ns) - 2; + while ((s32)(timings.rsetup + timings.rstrobe) < min) + timings.rstrobe++; + + cfg = TO_CYCLES((s32)(MAX_TH_PS - sdr->tCHZ_max), cyc_ns) - 1; + timings.rhold = cfg > 0 ? cfg : 0; + + min = TO_CYCLES(sdr->tRC_min, cyc_ns) - 3; + while ((s32)(timings.rsetup + timings.rstrobe + timings.rhold) < min) + timings.rhold++; + + cfg = TO_CYCLES((s32)(sdr->tRHZ_max - (timings.rhold + 1) * cyc_ns * 1000), cyc_ns); + cfg = max_t(s32, cfg, TO_CYCLES(sdr->tCHZ_max, cyc_ns)) - 1; + timings.ta = cfg > 0 ? cfg : 0; + + cfg = TO_CYCLES(sdr->tWP_min, cyc_ns) - 1; + timings.wstrobe = cfg > 0 ? cfg : 0; + + cfg = max_t(s32, TO_CYCLES(sdr->tCLS_min, cyc_ns), TO_CYCLES(sdr->tALS_min, cyc_ns)); + cfg = max_t(s32, cfg, TO_CYCLES(sdr->tCS_min, cyc_ns)) - 1; + timings.wsetup = cfg > 0 ? cfg : 0; + + min = TO_CYCLES(sdr->tDS_min, cyc_ns) - 2; + while ((s32)(timings.wsetup + timings.wstrobe) < min) + timings.wstrobe++; + + cfg = max_t(s32, TO_CYCLES(sdr->tCLH_min, cyc_ns), TO_CYCLES(sdr->tALH_min, cyc_ns)); + cfg = max_t(s32, cfg, TO_CYCLES(sdr->tCH_min, cyc_ns)); + cfg = max_t(s32, cfg, TO_CYCLES(sdr->tDH_min, cyc_ns)) - 1; + timings.whold = cfg > 0 ? cfg : 0; + + min = TO_CYCLES(sdr->tWC_min, cyc_ns) - 2; + while ((s32)(timings.wsetup + timings.wstrobe + timings.whold) < min) + timings.whold++; + + dev_dbg(&info->pdev->dev, "RSETUP %x RSTROBE %x RHOLD %x\n", + timings.rsetup, timings.rstrobe, timings.rhold); + dev_dbg(&info->pdev->dev, "TA %x\n", timings.ta); + dev_dbg(&info->pdev->dev, "WSETUP %x WSTROBE %x WHOLD %x\n", + timings.wsetup, timings.wstrobe, timings.whold); + + ret = aemif_check_cs_timings(&timings); + if (ret || chipnr == NAND_DATA_IFACE_CHECK_ONLY) + return ret; + + return aemif_set_cs_timings(info->aemif, info->core_chipsel, &timings); +} + static const struct nand_controller_ops davinci_nand_controller_ops = { .attach_chip = davinci_nand_attach_chip, .exec_op = davinci_nand_exec_op, + .setup_interface = davinci_nand_setup_interface, }; static int nand_davinci_probe(struct platform_device *pdev) @@ -822,9 +948,14 @@ static int nand_davinci_probe(struct platform_device *pdev) return -EADDRNOTAVAIL; } + info->clk = devm_clk_get_enabled(&pdev->dev, "aemif"); + if (IS_ERR(info->clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(info->clk), "failed to get clock"); + info->pdev = pdev; info->base = base; info->vaddr = vaddr; + info->aemif = dev_get_drvdata(pdev->dev.parent); mtd = nand_to_mtd(&info->chip); mtd->dev.parent = &pdev->dev; diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 8db7fc424571..70d6c2250f32 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -1098,7 +1098,7 @@ static inline int __init inftl_partscan(struct mtd_info *mtd, struct mtd_partiti (i == 0) && (ip->firstUnit > 0)) { parts[0].name = " DiskOnChip IPL / Media Header partition"; parts[0].offset = 0; - parts[0].size = mtd->erasesize * ip->firstUnit; + parts[0].size = (uint64_t)mtd->erasesize * ip->firstUnit; numparts = 1; } diff --git a/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c b/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c new file mode 100644 index 000000000000..c23b537948d5 --- /dev/null +++ b/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c @@ -0,0 +1,1029 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Nuvoton Technology Corp. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* NFI Registers */ +#define MA35_NFI_REG_DMACTL 0x400 +#define DMA_EN BIT(0) +#define DMA_RST BIT(1) +#define DMA_BUSY BIT(9) + +#define MA35_NFI_REG_DMASA 0x408 +#define MA35_NFI_REG_GCTL 0x800 +#define GRST BIT(0) +#define NAND_EN BIT(3) + +#define MA35_NFI_REG_NANDCTL 0x8A0 +#define SWRST BIT(0) +#define DMA_R_EN BIT(1) +#define DMA_W_EN BIT(2) +#define ECC_CHK BIT(7) +#define PROT3BEN BIT(8) +#define PSIZE_2K BIT(16) +#define PSIZE_4K BIT(17) +#define PSIZE_8K GENMASK(17, 16) +#define PSIZE_MASK GENMASK(17, 16) +#define BCH_T24 BIT(18) +#define BCH_T8 BIT(20) +#define BCH_T12 BIT(21) +#define BCH_NONE (0x0) +#define BCH_MASK GENMASK(22, 18) +#define ECC_EN BIT(23) +#define DISABLE_CS0 BIT(25) + +#define MA35_NFI_REG_NANDINTEN 0x8A8 +#define MA35_NFI_REG_NANDINTSTS 0x8AC +#define INT_DMA BIT(0) +#define INT_ECC BIT(2) +#define INT_RB0 BIT(10) + +#define MA35_NFI_REG_NANDCMD 0x8B0 +#define MA35_NFI_REG_NANDADDR 0x8B4 +#define ENDADDR BIT(31) + +#define MA35_NFI_REG_NANDDATA 0x8B8 +#define MA35_NFI_REG_NANDRACTL 0x8BC +#define MA35_NFI_REG_NANDECTL 0x8C0 +#define ENABLE_WP 0x0 +#define DISABLE_WP BIT(0) + +#define MA35_NFI_REG_NANDECCES0 0x8D0 +#define ECC_STATUS_MASK GENMASK(1, 0) +#define ECC_ERR_CNT_MASK GENMASK(4, 0) + +#define MA35_NFI_REG_NANDECCEA0 0x900 +#define MA35_NFI_REG_NANDECCED0 0x960 +#define MA35_NFI_REG_NANDRA0 0xA00 + +/* Define for the BCH hardware ECC engine */ +/* define the total padding bytes for 512/1024 data segment */ +#define MA35_BCH_PADDING_512 32 +#define MA35_BCH_PADDING_1024 64 +/* define the BCH parity code length for 512 bytes data pattern */ +#define MA35_PARITY_BCH8 15 +#define MA35_PARITY_BCH12 23 +/* define the BCH parity code length for 1024 bytes data pattern */ +#define MA35_PARITY_BCH24 45 + +#define MA35_MAX_NSELS (2) +#define PREFIX_RA_IS_EMPTY(reg) FIELD_GET(GENMASK(31, 16), (reg)) + +struct ma35_nand_chip { + struct list_head node; + struct nand_chip chip; + + u32 eccstatus; + u8 nsels; + u8 sels[] __counted_by(nsels); +}; + +struct ma35_nand_info { + struct nand_controller controller; + struct device *dev; + void __iomem *regs; + int irq; + struct clk *clk; + struct completion complete; + struct list_head chips; + + u8 *buffer; + unsigned long assigned_cs; +}; + +static inline struct ma35_nand_chip *to_ma35_nand(struct nand_chip *chip) +{ + return container_of(chip, struct ma35_nand_chip, chip); +} + +static int ma35_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *oob_region) +{ + struct nand_chip *chip = mtd_to_nand(mtd); + + if (section) + return -ERANGE; + + oob_region->length = chip->ecc.total; + oob_region->offset = mtd->oobsize - oob_region->length; + + return 0; +} + +static int ma35_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *oob_region) +{ + struct nand_chip *chip = mtd_to_nand(mtd); + + if (section) + return -ERANGE; + + oob_region->length = mtd->oobsize - chip->ecc.total - 2; + oob_region->offset = 2; + + return 0; +} + +static const struct mtd_ooblayout_ops ma35_ooblayout_ops = { + .free = ma35_ooblayout_free, + .ecc = ma35_ooblayout_ecc, +}; + +static inline void ma35_clear_spare(struct nand_chip *chip, int size) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + int i; + + for (i = 0; i < size / 4; i++) + writel(0xff, nand->regs + MA35_NFI_REG_NANDRA0); +} + +static inline void read_remaining_bytes(struct ma35_nand_info *nand, u32 *buf, + u32 offset, int size, int swap) +{ + u32 value = readl(nand->regs + MA35_NFI_REG_NANDRA0 + offset); + u8 *ptr = (u8 *)buf; + int i, shift; + + for (i = 0; i < size; i++) { + shift = (swap ? 3 - i : i) * 8; + ptr[i] = (value >> shift) & 0xff; + } +} + +static inline void ma35_read_spare(struct nand_chip *chip, int size, u32 *buf, u32 offset) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + u32 off = round_down(offset, 4); + int len = offset % 4; + int i; + + if (len) { + read_remaining_bytes(nand, buf, off, 4 - len, 1); + off += 4; + size -= (4 - len); + } + + for (i = 0; i < size / 4; i++) + *buf++ = readl(nand->regs + MA35_NFI_REG_NANDRA0 + off + (i * 4)); + + read_remaining_bytes(nand, buf, off + (size & ~3), size % 4, 0); +} + +static inline void ma35_write_spare(struct nand_chip *chip, int size, u32 *buf) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + u32 value; + int i, j; + u8 *ptr; + + for (i = 0, j = 0; i < size / 4; i++, j += 4) + writel(*buf++, nand->regs + MA35_NFI_REG_NANDRA0 + j); + + ptr = (u8 *)buf; + switch (size % 4) { + case 1: + writel(*ptr, nand->regs + MA35_NFI_REG_NANDRA0 + j); + break; + case 2: + value = *ptr | (*(ptr + 1) << 8); + writel(value, nand->regs + MA35_NFI_REG_NANDRA0 + j); + break; + case 3: + value = *ptr | (*(ptr + 1) << 8) | (*(ptr + 2) << 16); + writel(value, nand->regs + MA35_NFI_REG_NANDRA0 + j); + break; + default: + break; + } +} + +static void ma35_nand_target_enable(struct nand_chip *chip, unsigned int cs) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + u32 reg; + + switch (cs) { + case 0: + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + writel(reg & ~DISABLE_CS0, nand->regs + MA35_NFI_REG_NANDCTL); + + reg = readl(nand->regs + MA35_NFI_REG_NANDINTSTS); + reg |= INT_RB0; + writel(reg, nand->regs + MA35_NFI_REG_NANDINTSTS); + break; + default: + break; + } +} + +static int ma35_nand_hwecc_init(struct nand_chip *chip, struct ma35_nand_info *nand) +{ + struct ma35_nand_chip *nvtnand = to_ma35_nand(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + struct device *dev = mtd->dev.parent; + u32 reg; + + nand->buffer = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL); + if (!nand->buffer) + return -ENOMEM; + + /* Redundant area size */ + writel(mtd->oobsize, nand->regs + MA35_NFI_REG_NANDRACTL); + + /* Protect redundant 3 bytes and disable ECC engine */ + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + reg |= (PROT3BEN | ECC_CHK); + reg &= ~ECC_EN; + + if (chip->ecc.strength != 0) { + chip->ecc.steps = mtd->writesize / chip->ecc.size; + nvtnand->eccstatus = (chip->ecc.steps < 4) ? 1 : chip->ecc.steps / 4; + /* Set BCH algorithm */ + reg &= ~BCH_MASK; + switch (chip->ecc.strength) { + case 8: + chip->ecc.total = chip->ecc.steps * MA35_PARITY_BCH8; + reg |= BCH_T8; + break; + case 12: + chip->ecc.total = chip->ecc.steps * MA35_PARITY_BCH12; + reg |= BCH_T12; + break; + case 24: + chip->ecc.total = chip->ecc.steps * MA35_PARITY_BCH24; + reg |= BCH_T24; + break; + default: + dev_err(nand->dev, "ECC strength unsupported\n"); + return -EINVAL; + } + + chip->ecc.bytes = chip->ecc.total / chip->ecc.steps; + } + writel(reg, nand->regs + MA35_NFI_REG_NANDCTL); + return 0; +} + +/* Correct data by BCH alrogithm */ +static void ma35_nfi_correct(struct nand_chip *chip, u8 index, + u8 err_cnt, u8 *addr) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + u32 temp_data[24], temp_addr[24]; + u32 padding_len, parity_len; + u32 value, offset, remain; + u32 err_data[6]; + u8 i, j; + + /* Configurations */ + if (chip->ecc.strength <= 8) { + parity_len = MA35_PARITY_BCH8; + padding_len = MA35_BCH_PADDING_512; + } else if (chip->ecc.strength <= 12) { + parity_len = MA35_PARITY_BCH12; + padding_len = MA35_BCH_PADDING_512; + } else if (chip->ecc.strength <= 24) { + parity_len = MA35_PARITY_BCH24; + padding_len = MA35_BCH_PADDING_1024; + } else { + dev_err(nand->dev, "Invalid BCH_TSEL = 0x%lx\n", + readl(nand->regs + MA35_NFI_REG_NANDCTL) & BCH_MASK); + return; + } + + /* + * got valid BCH_ECC_DATAx and parse them to temp_data[] + * got the valid register number of BCH_ECC_DATAx since + * one register include 4 error bytes + */ + j = (err_cnt + 3) / 4; + j = (j > 6) ? 6 : j; + for (i = 0; i < j; i++) + err_data[i] = readl(nand->regs + MA35_NFI_REG_NANDECCED0 + i * 4); + + for (i = 0; i < j; i++) { + temp_data[i * 4 + 0] = err_data[i] & 0xff; + temp_data[i * 4 + 1] = (err_data[i] >> 8) & 0xff; + temp_data[i * 4 + 2] = (err_data[i] >> 16) & 0xff; + temp_data[i * 4 + 3] = (err_data[i] >> 24) & 0xff; + } + + /* + * got valid REG_BCH_ECC_ADDRx and parse them to temp_addr[] + * got the valid register number of REG_BCH_ECC_ADDRx since + * one register include 2 error addresses + */ + j = (err_cnt + 1) / 2; + j = (j > 12) ? 12 : j; + for (i = 0; i < j; i++) { + temp_addr[i * 2 + 0] = readl(nand->regs + MA35_NFI_REG_NANDECCEA0 + i * 4) + & 0x07ff; + temp_addr[i * 2 + 1] = (readl(nand->regs + MA35_NFI_REG_NANDECCEA0 + i * 4) + >> 16) & 0x07ff; + } + + /* pointer to begin address of field that with data error */ + addr += index * chip->ecc.size; + + /* correct each error bytes */ + for (i = 0; i < err_cnt; i++) { + u32 corrected_index = temp_addr[i]; + + if (corrected_index < chip->ecc.size) { + /* for wrong data in field */ + *(addr + corrected_index) ^= temp_data[i]; + } else if (corrected_index < (chip->ecc.size + 3)) { + /* for wrong first-3-bytes in redundancy area */ + corrected_index -= chip->ecc.size; + temp_addr[i] += (parity_len * index); /* field offset */ + + value = readl(nand->regs + MA35_NFI_REG_NANDRA0); + value ^= temp_data[i] << (8 * corrected_index); + writel(value, nand->regs + MA35_NFI_REG_NANDRA0); + } else { + /* + * for wrong parity code in redundancy area + * ERR_ADDRx = [data in field] + [3 bytes] + [xx] + [parity code] + * |<-- padding bytes -->| + * The ERR_ADDRx for last parity code always = field size + padding size. + * The first parity code = field size + padding size - parity code length. + * For example, for BCH T12, the first parity code = 512 + 32 - 23 = 521. + * That is, error byte address offset within field is + */ + corrected_index -= (chip->ecc.size + padding_len - parity_len); + + /* + * final address = first parity code of first field + + * offset of fields + + * offset within field + */ + offset = (readl(nand->regs + MA35_NFI_REG_NANDRACTL) & 0x1ff) - + (parity_len * chip->ecc.steps) + + (parity_len * index) + corrected_index; + + remain = offset % 4; + value = readl(nand->regs + MA35_NFI_REG_NANDRA0 + offset - remain); + value ^= temp_data[i] << (8 * remain); + writel(value, nand->regs + MA35_NFI_REG_NANDRA0 + offset - remain); + } + } +} + +static int ma35_nfi_ecc_check(struct nand_chip *chip, u8 *addr) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct ma35_nand_chip *nvtnand = to_ma35_nand(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + int maxbitflips = 0; + int cnt = 0; + u32 status; + int i, j; + + for (j = 0; j < nvtnand->eccstatus; j++) { + status = readl(nand->regs + MA35_NFI_REG_NANDECCES0 + j * 4); + if (!status) + continue; + + for (i = 0; i < 4; i++) { + if ((status & ECC_STATUS_MASK) == 0x01) { + /* Correctable error */ + cnt = (status >> 2) & ECC_ERR_CNT_MASK; + ma35_nfi_correct(chip, j * 4 + i, cnt, addr); + maxbitflips = max_t(u32, maxbitflips, cnt); + mtd->ecc_stats.corrected += cnt; + } else { + /* Uncorrectable error */ + mtd->ecc_stats.failed++; + dev_err(nand->dev, "uncorrectable error! 0x%4x\n", status); + return -EBADMSG; + } + status >>= 8; + } + } + return maxbitflips; +} + +static void ma35_nand_dmac_init(struct ma35_nand_info *nand) +{ + /* DMAC reset and enable */ + writel(DMA_RST | DMA_EN, nand->regs + MA35_NFI_REG_DMACTL); + writel(DMA_EN, nand->regs + MA35_NFI_REG_DMACTL); + + /* Clear DMA finished flag and enable */ + writel(INT_DMA | INT_ECC, nand->regs + MA35_NFI_REG_NANDINTSTS); + writel(INT_DMA, nand->regs + MA35_NFI_REG_NANDINTEN); +} + +static int ma35_nand_do_write(struct nand_chip *chip, const u8 *addr, u32 len) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + dma_addr_t dma_addr; + int ret = 0, i; + u32 reg; + + if (len != mtd->writesize) { + for (i = 0; i < len; i++) + writel(addr[i], nand->regs + MA35_NFI_REG_NANDDATA); + return 0; + } + + ma35_nand_dmac_init(nand); + + /* To mark this page as dirty. */ + reg = readl(nand->regs + MA35_NFI_REG_NANDRA0); + if (reg & 0xffff0000) + writel(reg & 0xffff, nand->regs + MA35_NFI_REG_NANDRA0); + + dma_addr = dma_map_single(nand->dev, (void *)addr, len, DMA_TO_DEVICE); + ret = dma_mapping_error(nand->dev, dma_addr); + if (ret) { + dev_err(nand->dev, "dma mapping error\n"); + return -EINVAL; + } + dma_sync_single_for_device(nand->dev, dma_addr, len, DMA_TO_DEVICE); + + reinit_completion(&nand->complete); + writel(dma_addr, nand->regs + MA35_NFI_REG_DMASA); + writel(readl(nand->regs + MA35_NFI_REG_NANDCTL) | DMA_W_EN, + nand->regs + MA35_NFI_REG_NANDCTL); + ret = wait_for_completion_timeout(&nand->complete, msecs_to_jiffies(1000)); + if (!ret) { + dev_err(nand->dev, "write timeout\n"); + ret = -ETIMEDOUT; + } + + dma_unmap_single(nand->dev, dma_addr, len, DMA_TO_DEVICE); + + return ret; +} + +static int ma35_nand_do_read(struct nand_chip *chip, u8 *addr, u32 len) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + int ret = 0, cnt = 0, i; + dma_addr_t dma_addr; + u32 reg; + + if (len != mtd->writesize) { + for (i = 0; i < len; i++) + addr[i] = readb(nand->regs + MA35_NFI_REG_NANDDATA); + return 0; + } + + ma35_nand_dmac_init(nand); + + /* Setup and start DMA using dma_addr */ + dma_addr = dma_map_single(nand->dev, (void *)addr, len, DMA_FROM_DEVICE); + ret = dma_mapping_error(nand->dev, dma_addr); + if (ret) { + dev_err(nand->dev, "dma mapping error\n"); + return -EINVAL; + } + + reinit_completion(&nand->complete); + writel(dma_addr, nand->regs + MA35_NFI_REG_DMASA); + writel(readl(nand->regs + MA35_NFI_REG_NANDCTL) | DMA_R_EN, + nand->regs + MA35_NFI_REG_NANDCTL); + ret = wait_for_completion_timeout(&nand->complete, msecs_to_jiffies(1000)); + if (!ret) { + dev_err(nand->dev, "read timeout\n"); + ret = -ETIMEDOUT; + } + + dma_unmap_single(nand->dev, dma_addr, len, DMA_FROM_DEVICE); + + reg = readl(nand->regs + MA35_NFI_REG_NANDINTSTS); + if (reg & INT_ECC) { + cnt = ma35_nfi_ecc_check(chip, addr); + if (cnt < 0) { + writel(DMA_RST | DMA_EN, nand->regs + MA35_NFI_REG_DMACTL); + writel(readl(nand->regs + MA35_NFI_REG_NANDCTL) | SWRST, + nand->regs + MA35_NFI_REG_NANDCTL); + } + writel(INT_ECC, nand->regs + MA35_NFI_REG_NANDINTSTS); + } + + ret = ret < 0 ? ret : cnt; + return ret; +} + +static int ma35_nand_format_subpage(struct nand_chip *chip, u32 offset, + u32 len, const u8 *buf) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + u32 page_off = round_down(offset, chip->ecc.size); + u32 end = DIV_ROUND_UP(page_off + len, chip->ecc.size); + u32 start = page_off / chip->ecc.size; + u32 reg; + int i; + + reg = readl(nand->regs + MA35_NFI_REG_NANDRACTL) | 0xffff0000; + memset(nand->buffer, 0xff, mtd->writesize); + for (i = start; i < end; i++) { + memcpy(nand->buffer + i * chip->ecc.size, + buf + i * chip->ecc.size, chip->ecc.size); + reg &= ~(1 << (i + 16)); + } + writel(reg, nand->regs + MA35_NFI_REG_NANDRACTL); + + return 0; +} + +static int ma35_nand_write_subpage_hwecc(struct nand_chip *chip, u32 offset, + u32 data_len, const u8 *buf, + int oob_required, int page) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + u32 reg, oobpoi, index; + int i; + + /* Enable HW ECC engine */ + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + writel(reg | ECC_EN, nand->regs + MA35_NFI_REG_NANDCTL); + + ma35_nand_target_enable(chip, chip->cur_cs); + + ma35_clear_spare(chip, mtd->oobsize); + ma35_write_spare(chip, mtd->oobsize - chip->ecc.total, + (u32 *)chip->oob_poi); + + ma35_nand_format_subpage(chip, offset, data_len, buf); + nand_prog_page_begin_op(chip, page, 0, NULL, 0); + ma35_nand_do_write(chip, nand->buffer, mtd->writesize); + nand_prog_page_end_op(chip); + + oobpoi = mtd->oobsize - chip->ecc.total; + reg = readl(nand->regs + MA35_NFI_REG_NANDRACTL); + for (i = 0; i < chip->ecc.steps; i++) { + index = i * chip->ecc.bytes; + if (!(reg & (1 << (i + 16)))) { + ma35_read_spare(chip, chip->ecc.bytes, + (u32 *)(chip->oob_poi + oobpoi + index), + oobpoi + index); + } + } + + writel(mtd->oobsize, nand->regs + MA35_NFI_REG_NANDRACTL); + /* Disable HW ECC engine */ + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + writel(reg & ~ECC_EN, nand->regs + MA35_NFI_REG_NANDCTL); + + return 0; +} + +static int ma35_nand_write_page_hwecc(struct nand_chip *chip, const u8 *buf, + int oob_required, int page) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + u32 reg; + + /* Enable HW ECC engine */ + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + writel(reg | ECC_EN, nand->regs + MA35_NFI_REG_NANDCTL); + + ma35_nand_target_enable(chip, chip->cur_cs); + + ma35_clear_spare(chip, mtd->oobsize); + ma35_write_spare(chip, mtd->oobsize - chip->ecc.total, + (u32 *)chip->oob_poi); + + nand_prog_page_begin_op(chip, page, 0, NULL, 0); + ma35_nand_do_write(chip, buf, mtd->writesize); + nand_prog_page_end_op(chip); + + ma35_read_spare(chip, chip->ecc.total, + (u32 *)(chip->oob_poi + (mtd->oobsize - chip->ecc.total)), + mtd->oobsize - chip->ecc.total); + + /* Disable HW ECC engine */ + writel(reg & ~ECC_EN, nand->regs + MA35_NFI_REG_NANDCTL); + + return 0; +} + +static int ma35_nand_read_subpage_hwecc(struct nand_chip *chip, u32 offset, + u32 data_len, u8 *buf, int page) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + int bitflips = 0; + u32 reg; + + /* Enable HW ECC engine */ + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + writel(reg | ECC_EN, nand->regs + MA35_NFI_REG_NANDCTL); + + ma35_nand_target_enable(chip, chip->cur_cs); + nand_read_oob_op(chip, page, 0, chip->oob_poi, mtd->oobsize); + ma35_write_spare(chip, mtd->oobsize, (u32 *)chip->oob_poi); + + reg = readl(nand->regs + MA35_NFI_REG_NANDRA0); + if (PREFIX_RA_IS_EMPTY(reg)) { + memset((void *)buf, 0xff, mtd->writesize); + } else { + nand_read_page_op(chip, page, offset, NULL, 0); + bitflips = ma35_nand_do_read(chip, buf + offset, data_len); + ma35_read_spare(chip, mtd->oobsize, (u32 *)chip->oob_poi, 0); + } + + /* Disable HW ECC engine */ + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + writel(reg & ~ECC_EN, nand->regs + MA35_NFI_REG_NANDCTL); + + return bitflips; +} + +static int ma35_nand_read_page_hwecc(struct nand_chip *chip, u8 *buf, + int oob_required, int page) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + int bitflips = 0; + u32 reg; + + /* Enable HW ECC engine */ + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + writel(reg | ECC_EN, nand->regs + MA35_NFI_REG_NANDCTL); + + ma35_nand_target_enable(chip, chip->cur_cs); + nand_read_oob_op(chip, page, 0, chip->oob_poi, mtd->oobsize); + ma35_write_spare(chip, mtd->oobsize, (u32 *)chip->oob_poi); + + reg = readl(nand->regs + MA35_NFI_REG_NANDRA0); + if (PREFIX_RA_IS_EMPTY(reg)) { + memset((void *)buf, 0xff, mtd->writesize); + } else { + nand_read_page_op(chip, page, 0, NULL, 0); + bitflips = ma35_nand_do_read(chip, buf, mtd->writesize); + ma35_read_spare(chip, mtd->oobsize, (u32 *)chip->oob_poi, 0); + } + + /* Disable HW ECC engine */ + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + writel(reg & ~ECC_EN, nand->regs + MA35_NFI_REG_NANDCTL); + + return bitflips; +} + +static int ma35_nand_read_oob_hwecc(struct nand_chip *chip, int page) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + u32 reg; + + ma35_nand_target_enable(chip, chip->cur_cs); + nand_read_oob_op(chip, page, 0, chip->oob_poi, mtd->oobsize); + + /* copy OOB data to controller redundant area for page read */ + ma35_write_spare(chip, mtd->oobsize, (u32 *)chip->oob_poi); + + reg = readl(nand->regs + MA35_NFI_REG_NANDRA0); + if (PREFIX_RA_IS_EMPTY(reg)) + memset((void *)chip->oob_poi, 0xff, mtd->oobsize); + + return 0; +} + +static inline void ma35_hw_init(struct ma35_nand_info *nand) +{ + u32 reg; + + /* Disable flash wp. */ + writel(DISABLE_WP, nand->regs + MA35_NFI_REG_NANDECTL); + + /* resets the internal state machine and counters */ + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL); + reg |= SWRST; + writel(reg, nand->regs + MA35_NFI_REG_NANDCTL); +} + +static irqreturn_t ma35_nand_irq(int irq, void *id) +{ + struct ma35_nand_info *nand = (struct ma35_nand_info *)id; + u32 isr; + + isr = readl(nand->regs + MA35_NFI_REG_NANDINTSTS); + if (isr & INT_DMA) { + writel(INT_DMA, nand->regs + MA35_NFI_REG_NANDINTSTS); + complete(&nand->complete); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + +static int ma35_nand_attach_chip(struct nand_chip *chip) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + struct device *dev = mtd->dev.parent; + u32 reg; + + if (chip->options & NAND_BUSWIDTH_16) { + dev_err(dev, "16 bits bus width not supported"); + return -EINVAL; + } + + reg = readl(nand->regs + MA35_NFI_REG_NANDCTL) & (~PSIZE_MASK); + switch (mtd->writesize) { + case SZ_2K: + writel(reg | PSIZE_2K, nand->regs + MA35_NFI_REG_NANDCTL); + break; + case SZ_4K: + writel(reg | PSIZE_4K, nand->regs + MA35_NFI_REG_NANDCTL); + break; + case SZ_8K: + writel(reg | PSIZE_8K, nand->regs + MA35_NFI_REG_NANDCTL); + break; + default: + dev_err(dev, "Unsupported page size"); + return -EINVAL; + } + + switch (chip->ecc.engine_type) { + case NAND_ECC_ENGINE_TYPE_ON_HOST: + /* Do not store BBT bits in the OOB section as it is not protected */ + if (chip->bbt_options & NAND_BBT_USE_FLASH) + chip->bbt_options |= NAND_BBT_NO_OOB; + chip->options |= NAND_USES_DMA | NAND_SUBPAGE_READ; + chip->ecc.write_subpage = ma35_nand_write_subpage_hwecc; + chip->ecc.write_page = ma35_nand_write_page_hwecc; + chip->ecc.read_subpage = ma35_nand_read_subpage_hwecc; + chip->ecc.read_page = ma35_nand_read_page_hwecc; + chip->ecc.read_oob = ma35_nand_read_oob_hwecc; + return ma35_nand_hwecc_init(chip, nand); + case NAND_ECC_ENGINE_TYPE_NONE: + case NAND_ECC_ENGINE_TYPE_SOFT: + case NAND_ECC_ENGINE_TYPE_ON_DIE: + break; + default: + return -EINVAL; + } + + return 0; +} + +static int ma35_nfc_exec_instr(struct nand_chip *chip, + const struct nand_op_instr *instr) +{ + struct ma35_nand_info *nand = nand_get_controller_data(chip); + unsigned int i; + int ret = 0; + u32 status; + + switch (instr->type) { + case NAND_OP_CMD_INSTR: + writel(instr->ctx.cmd.opcode, nand->regs + MA35_NFI_REG_NANDCMD); + break; + case NAND_OP_ADDR_INSTR: + for (i = 0; i < instr->ctx.addr.naddrs; i++) { + if (i == (instr->ctx.addr.naddrs - 1)) + writel(instr->ctx.addr.addrs[i] | ENDADDR, + nand->regs + MA35_NFI_REG_NANDADDR); + else + writel(instr->ctx.addr.addrs[i], + nand->regs + MA35_NFI_REG_NANDADDR); + } + break; + case NAND_OP_DATA_IN_INSTR: + ret = ma35_nand_do_read(chip, instr->ctx.data.buf.in, instr->ctx.data.len); + break; + case NAND_OP_DATA_OUT_INSTR: + ret = ma35_nand_do_write(chip, instr->ctx.data.buf.out, instr->ctx.data.len); + break; + case NAND_OP_WAITRDY_INSTR: + return readl_poll_timeout(nand->regs + MA35_NFI_REG_NANDINTSTS, status, + status & INT_RB0, 20, + instr->ctx.waitrdy.timeout_ms * MSEC_PER_SEC); + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static int ma35_nfc_exec_op(struct nand_chip *chip, + const struct nand_operation *op, + bool check_only) +{ + int ret = 0; + u32 i; + + if (check_only) + return 0; + + ma35_nand_target_enable(chip, op->cs); + + for (i = 0; i < op->ninstrs; i++) { + ret = ma35_nfc_exec_instr(chip, &op->instrs[i]); + if (ret) + break; + } + + return ret; +} + +static const struct nand_controller_ops ma35_nfc_ops = { + .attach_chip = ma35_nand_attach_chip, + .exec_op = ma35_nfc_exec_op, +}; + +static int ma35_nand_chip_init(struct device *dev, struct ma35_nand_info *nand, + struct device_node *np) +{ + struct ma35_nand_chip *nvtnand; + struct nand_chip *chip; + struct mtd_info *mtd; + int nsels; + int ret; + u32 cs; + int i; + + nsels = of_property_count_elems_of_size(np, "reg", sizeof(u32)); + if (!nsels || nsels > MA35_MAX_NSELS) { + dev_err(dev, "invalid reg property size %d\n", nsels); + return -EINVAL; + } + + nvtnand = devm_kzalloc(dev, struct_size(nvtnand, sels, nsels), + GFP_KERNEL); + if (!nvtnand) + return -ENOMEM; + + nvtnand->nsels = nsels; + for (i = 0; i < nsels; i++) { + ret = of_property_read_u32_index(np, "reg", i, &cs); + if (ret) { + dev_err(dev, "reg property failure : %d\n", ret); + return ret; + } + + if (cs >= MA35_MAX_NSELS) { + dev_err(dev, "invalid CS: %u\n", cs); + return -EINVAL; + } + + if (test_and_set_bit(cs, &nand->assigned_cs)) { + dev_err(dev, "CS %u already assigned\n", cs); + return -EINVAL; + } + + nvtnand->sels[i] = cs; + } + + chip = &nvtnand->chip; + chip->controller = &nand->controller; + + nand_set_flash_node(chip, np); + nand_set_controller_data(chip, nand); + + mtd = nand_to_mtd(chip); + mtd->owner = THIS_MODULE; + mtd->dev.parent = dev; + + mtd_set_ooblayout(mtd, &ma35_ooblayout_ops); + ret = nand_scan(chip, nsels); + if (ret) + return ret; + + ret = mtd_device_register(mtd, NULL, 0); + if (ret) { + nand_cleanup(chip); + return ret; + } + + list_add_tail(&nvtnand->node, &nand->chips); + + return 0; +} + +static void ma35_chips_cleanup(struct ma35_nand_info *nand) +{ + struct ma35_nand_chip *nvtnand, *tmp; + struct nand_chip *chip; + int ret; + + list_for_each_entry_safe(nvtnand, tmp, &nand->chips, node) { + chip = &nvtnand->chip; + ret = mtd_device_unregister(nand_to_mtd(chip)); + WARN_ON(ret); + nand_cleanup(chip); + list_del(&nvtnand->node); + } +} + +static int ma35_nand_chips_init(struct device *dev, struct ma35_nand_info *nand) +{ + struct device_node *np = dev->of_node, *nand_np; + int ret; + + for_each_child_of_node(np, nand_np) { + ret = ma35_nand_chip_init(dev, nand, nand_np); + if (ret) { + ma35_chips_cleanup(nand); + return ret; + } + } + return 0; +} + +static int ma35_nand_probe(struct platform_device *pdev) +{ + struct ma35_nand_info *nand; + int ret = 0; + + nand = devm_kzalloc(&pdev->dev, sizeof(*nand), GFP_KERNEL); + if (!nand) + return -ENOMEM; + + nand_controller_init(&nand->controller); + INIT_LIST_HEAD(&nand->chips); + nand->controller.ops = &ma35_nfc_ops; + + init_completion(&nand->complete); + + nand->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(nand->regs)) + return PTR_ERR(nand->regs); + + nand->dev = &pdev->dev; + + nand->clk = devm_clk_get_enabled(&pdev->dev, "nand_gate"); + if (IS_ERR(nand->clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(nand->clk), + "failed to find NAND clock\n"); + + nand->irq = platform_get_irq(pdev, 0); + if (nand->irq < 0) + return dev_err_probe(&pdev->dev, nand->irq, + "failed to get platform irq\n"); + + ret = devm_request_irq(&pdev->dev, nand->irq, ma35_nand_irq, + IRQF_TRIGGER_HIGH, "ma35d1-nand-controller", nand); + if (ret) { + dev_err(&pdev->dev, "failed to request NAND irq\n"); + return -ENXIO; + } + + platform_set_drvdata(pdev, nand); + + writel(GRST | NAND_EN, nand->regs + MA35_NFI_REG_GCTL); + ma35_hw_init(nand); + ret = ma35_nand_chips_init(&pdev->dev, nand); + if (ret) { + dev_err(&pdev->dev, "failed to init NAND chips\n"); + clk_disable(nand->clk); + return ret; + } + + return ret; +} + +static void ma35_nand_remove(struct platform_device *pdev) +{ + struct ma35_nand_info *nand = platform_get_drvdata(pdev); + + ma35_chips_cleanup(nand); +} + +static const struct of_device_id ma35_nand_of_match[] = { + { .compatible = "nuvoton,ma35d1-nand-controller" }, + {}, +}; +MODULE_DEVICE_TABLE(of, ma35_nand_of_match); + +static struct platform_driver ma35_nand_driver = { + .driver = { + .name = "ma35d1-nand-controller", + .of_match_table = ma35_nand_of_match, + }, + .probe = ma35_nand_probe, + .remove = ma35_nand_remove, +}; + +module_platform_driver(ma35_nand_driver); + +MODULE_DESCRIPTION("Nuvoton ma35 NAND driver"); +MODULE_AUTHOR("Hui-Ping Chen "); +MODULE_LICENSE("GPL"); diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c index d9141f3c0dd1..b8af3a3533fc 100644 --- a/drivers/mtd/nand/raw/omap2.c +++ b/drivers/mtd/nand/raw/omap2.c @@ -254,6 +254,10 @@ static int omap_prefetch_reset(int cs, struct omap_nand_info *info) /** * omap_nand_data_in_pref - NAND data in using prefetch engine + * @chip: NAND chip + * @buf: output buffer where NAND data is placed into + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_in_pref(struct nand_chip *chip, void *buf, unsigned int len, bool force_8bit) @@ -297,6 +301,10 @@ static void omap_nand_data_in_pref(struct nand_chip *chip, void *buf, /** * omap_nand_data_out_pref - NAND data out using Write Posting engine + * @chip: NAND chip + * @buf: input buffer that is sent to NAND + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_out_pref(struct nand_chip *chip, const void *buf, unsigned int len, @@ -440,6 +448,10 @@ out_copy: /** * omap_nand_data_in_dma_pref - NAND data in using DMA and Prefetch + * @chip: NAND chip + * @buf: output buffer where NAND data is placed into + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_in_dma_pref(struct nand_chip *chip, void *buf, unsigned int len, bool force_8bit) @@ -460,6 +472,10 @@ static void omap_nand_data_in_dma_pref(struct nand_chip *chip, void *buf, /** * omap_nand_data_out_dma_pref - NAND data out using DMA and write posting + * @chip: NAND chip + * @buf: input buffer that is sent to NAND + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_out_dma_pref(struct nand_chip *chip, const void *buf, unsigned int len, diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index 636bba2528bf..d2d2aeee42a7 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -15,431 +15,7 @@ #include #include #include - -/* NANDc reg offsets */ -#define NAND_FLASH_CMD 0x00 -#define NAND_ADDR0 0x04 -#define NAND_ADDR1 0x08 -#define NAND_FLASH_CHIP_SELECT 0x0c -#define NAND_EXEC_CMD 0x10 -#define NAND_FLASH_STATUS 0x14 -#define NAND_BUFFER_STATUS 0x18 -#define NAND_DEV0_CFG0 0x20 -#define NAND_DEV0_CFG1 0x24 -#define NAND_DEV0_ECC_CFG 0x28 -#define NAND_AUTO_STATUS_EN 0x2c -#define NAND_DEV1_CFG0 0x30 -#define NAND_DEV1_CFG1 0x34 -#define NAND_READ_ID 0x40 -#define NAND_READ_STATUS 0x44 -#define NAND_DEV_CMD0 0xa0 -#define NAND_DEV_CMD1 0xa4 -#define NAND_DEV_CMD2 0xa8 -#define NAND_DEV_CMD_VLD 0xac -#define SFLASHC_BURST_CFG 0xe0 -#define NAND_ERASED_CW_DETECT_CFG 0xe8 -#define NAND_ERASED_CW_DETECT_STATUS 0xec -#define NAND_EBI2_ECC_BUF_CFG 0xf0 -#define FLASH_BUF_ACC 0x100 - -#define NAND_CTRL 0xf00 -#define NAND_VERSION 0xf08 -#define NAND_READ_LOCATION_0 0xf20 -#define NAND_READ_LOCATION_1 0xf24 -#define NAND_READ_LOCATION_2 0xf28 -#define NAND_READ_LOCATION_3 0xf2c -#define NAND_READ_LOCATION_LAST_CW_0 0xf40 -#define NAND_READ_LOCATION_LAST_CW_1 0xf44 -#define NAND_READ_LOCATION_LAST_CW_2 0xf48 -#define NAND_READ_LOCATION_LAST_CW_3 0xf4c - -/* dummy register offsets, used by write_reg_dma */ -#define NAND_DEV_CMD1_RESTORE 0xdead -#define NAND_DEV_CMD_VLD_RESTORE 0xbeef - -/* NAND_FLASH_CMD bits */ -#define PAGE_ACC BIT(4) -#define LAST_PAGE BIT(5) - -/* NAND_FLASH_CHIP_SELECT bits */ -#define NAND_DEV_SEL 0 -#define DM_EN BIT(2) - -/* NAND_FLASH_STATUS bits */ -#define FS_OP_ERR BIT(4) -#define FS_READY_BSY_N BIT(5) -#define FS_MPU_ERR BIT(8) -#define FS_DEVICE_STS_ERR BIT(16) -#define FS_DEVICE_WP BIT(23) - -/* NAND_BUFFER_STATUS bits */ -#define BS_UNCORRECTABLE_BIT BIT(8) -#define BS_CORRECTABLE_ERR_MSK 0x1f - -/* NAND_DEVn_CFG0 bits */ -#define DISABLE_STATUS_AFTER_WRITE 4 -#define CW_PER_PAGE 6 -#define UD_SIZE_BYTES 9 -#define UD_SIZE_BYTES_MASK GENMASK(18, 9) -#define ECC_PARITY_SIZE_BYTES_RS 19 -#define SPARE_SIZE_BYTES 23 -#define SPARE_SIZE_BYTES_MASK GENMASK(26, 23) -#define NUM_ADDR_CYCLES 27 -#define STATUS_BFR_READ 30 -#define SET_RD_MODE_AFTER_STATUS 31 - -/* NAND_DEVn_CFG0 bits */ -#define DEV0_CFG1_ECC_DISABLE 0 -#define WIDE_FLASH 1 -#define NAND_RECOVERY_CYCLES 2 -#define CS_ACTIVE_BSY 5 -#define BAD_BLOCK_BYTE_NUM 6 -#define BAD_BLOCK_IN_SPARE_AREA 16 -#define WR_RD_BSY_GAP 17 -#define ENABLE_BCH_ECC 27 - -/* NAND_DEV0_ECC_CFG bits */ -#define ECC_CFG_ECC_DISABLE 0 -#define ECC_SW_RESET 1 -#define ECC_MODE 4 -#define ECC_PARITY_SIZE_BYTES_BCH 8 -#define ECC_NUM_DATA_BYTES 16 -#define ECC_NUM_DATA_BYTES_MASK GENMASK(25, 16) -#define ECC_FORCE_CLK_OPEN 30 - -/* NAND_DEV_CMD1 bits */ -#define READ_ADDR 0 - -/* NAND_DEV_CMD_VLD bits */ -#define READ_START_VLD BIT(0) -#define READ_STOP_VLD BIT(1) -#define WRITE_START_VLD BIT(2) -#define ERASE_START_VLD BIT(3) -#define SEQ_READ_START_VLD BIT(4) - -/* NAND_EBI2_ECC_BUF_CFG bits */ -#define NUM_STEPS 0 - -/* NAND_ERASED_CW_DETECT_CFG bits */ -#define ERASED_CW_ECC_MASK 1 -#define AUTO_DETECT_RES 0 -#define MASK_ECC BIT(ERASED_CW_ECC_MASK) -#define RESET_ERASED_DET BIT(AUTO_DETECT_RES) -#define ACTIVE_ERASED_DET (0 << AUTO_DETECT_RES) -#define CLR_ERASED_PAGE_DET (RESET_ERASED_DET | MASK_ECC) -#define SET_ERASED_PAGE_DET (ACTIVE_ERASED_DET | MASK_ECC) - -/* NAND_ERASED_CW_DETECT_STATUS bits */ -#define PAGE_ALL_ERASED BIT(7) -#define CODEWORD_ALL_ERASED BIT(6) -#define PAGE_ERASED BIT(5) -#define CODEWORD_ERASED BIT(4) -#define ERASED_PAGE (PAGE_ALL_ERASED | PAGE_ERASED) -#define ERASED_CW (CODEWORD_ALL_ERASED | CODEWORD_ERASED) - -/* NAND_READ_LOCATION_n bits */ -#define READ_LOCATION_OFFSET 0 -#define READ_LOCATION_SIZE 16 -#define READ_LOCATION_LAST 31 - -/* Version Mask */ -#define NAND_VERSION_MAJOR_MASK 0xf0000000 -#define NAND_VERSION_MAJOR_SHIFT 28 -#define NAND_VERSION_MINOR_MASK 0x0fff0000 -#define NAND_VERSION_MINOR_SHIFT 16 - -/* NAND OP_CMDs */ -#define OP_PAGE_READ 0x2 -#define OP_PAGE_READ_WITH_ECC 0x3 -#define OP_PAGE_READ_WITH_ECC_SPARE 0x4 -#define OP_PAGE_READ_ONFI_READ 0x5 -#define OP_PROGRAM_PAGE 0x6 -#define OP_PAGE_PROGRAM_WITH_ECC 0x7 -#define OP_PROGRAM_PAGE_SPARE 0x9 -#define OP_BLOCK_ERASE 0xa -#define OP_CHECK_STATUS 0xc -#define OP_FETCH_ID 0xb -#define OP_RESET_DEVICE 0xd - -/* Default Value for NAND_DEV_CMD_VLD */ -#define NAND_DEV_CMD_VLD_VAL (READ_START_VLD | WRITE_START_VLD | \ - ERASE_START_VLD | SEQ_READ_START_VLD) - -/* NAND_CTRL bits */ -#define BAM_MODE_EN BIT(0) - -/* - * the NAND controller performs reads/writes with ECC in 516 byte chunks. - * the driver calls the chunks 'step' or 'codeword' interchangeably - */ -#define NANDC_STEP_SIZE 512 - -/* - * the largest page size we support is 8K, this will have 16 steps/codewords - * of 512 bytes each - */ -#define MAX_NUM_STEPS (SZ_8K / NANDC_STEP_SIZE) - -/* we read at most 3 registers per codeword scan */ -#define MAX_REG_RD (3 * MAX_NUM_STEPS) - -/* ECC modes supported by the controller */ -#define ECC_NONE BIT(0) -#define ECC_RS_4BIT BIT(1) -#define ECC_BCH_4BIT BIT(2) -#define ECC_BCH_8BIT BIT(3) - -#define nandc_set_read_loc_first(chip, reg, cw_offset, read_size, is_last_read_loc) \ -nandc_set_reg(chip, reg, \ - ((cw_offset) << READ_LOCATION_OFFSET) | \ - ((read_size) << READ_LOCATION_SIZE) | \ - ((is_last_read_loc) << READ_LOCATION_LAST)) - -#define nandc_set_read_loc_last(chip, reg, cw_offset, read_size, is_last_read_loc) \ -nandc_set_reg(chip, reg, \ - ((cw_offset) << READ_LOCATION_OFFSET) | \ - ((read_size) << READ_LOCATION_SIZE) | \ - ((is_last_read_loc) << READ_LOCATION_LAST)) -/* - * Returns the actual register address for all NAND_DEV_ registers - * (i.e. NAND_DEV_CMD0, NAND_DEV_CMD1, NAND_DEV_CMD2 and NAND_DEV_CMD_VLD) - */ -#define dev_cmd_reg_addr(nandc, reg) ((nandc)->props->dev_cmd_reg_start + (reg)) - -/* Returns the NAND register physical address */ -#define nandc_reg_phys(chip, offset) ((chip)->base_phys + (offset)) - -/* Returns the dma address for reg read buffer */ -#define reg_buf_dma_addr(chip, vaddr) \ - ((chip)->reg_read_dma + \ - ((u8 *)(vaddr) - (u8 *)(chip)->reg_read_buf)) - -#define QPIC_PER_CW_CMD_ELEMENTS 32 -#define QPIC_PER_CW_CMD_SGL 32 -#define QPIC_PER_CW_DATA_SGL 8 - -#define QPIC_NAND_COMPLETION_TIMEOUT msecs_to_jiffies(2000) - -/* - * Flags used in DMA descriptor preparation helper functions - * (i.e. read_reg_dma/write_reg_dma/read_data_dma/write_data_dma) - */ -/* Don't set the EOT in current tx BAM sgl */ -#define NAND_BAM_NO_EOT BIT(0) -/* Set the NWD flag in current BAM sgl */ -#define NAND_BAM_NWD BIT(1) -/* Finish writing in the current BAM sgl and start writing in another BAM sgl */ -#define NAND_BAM_NEXT_SGL BIT(2) -/* - * Erased codeword status is being used two times in single transfer so this - * flag will determine the current value of erased codeword status register - */ -#define NAND_ERASED_CW_SET BIT(4) - -#define MAX_ADDRESS_CYCLE 5 - -/* - * This data type corresponds to the BAM transaction which will be used for all - * NAND transfers. - * @bam_ce - the array of BAM command elements - * @cmd_sgl - sgl for NAND BAM command pipe - * @data_sgl - sgl for NAND BAM consumer/producer pipe - * @last_data_desc - last DMA desc in data channel (tx/rx). - * @last_cmd_desc - last DMA desc in command channel. - * @txn_done - completion for NAND transfer. - * @bam_ce_pos - the index in bam_ce which is available for next sgl - * @bam_ce_start - the index in bam_ce which marks the start position ce - * for current sgl. It will be used for size calculation - * for current sgl - * @cmd_sgl_pos - current index in command sgl. - * @cmd_sgl_start - start index in command sgl. - * @tx_sgl_pos - current index in data sgl for tx. - * @tx_sgl_start - start index in data sgl for tx. - * @rx_sgl_pos - current index in data sgl for rx. - * @rx_sgl_start - start index in data sgl for rx. - * @wait_second_completion - wait for second DMA desc completion before making - * the NAND transfer completion. - */ -struct bam_transaction { - struct bam_cmd_element *bam_ce; - struct scatterlist *cmd_sgl; - struct scatterlist *data_sgl; - struct dma_async_tx_descriptor *last_data_desc; - struct dma_async_tx_descriptor *last_cmd_desc; - struct completion txn_done; - u32 bam_ce_pos; - u32 bam_ce_start; - u32 cmd_sgl_pos; - u32 cmd_sgl_start; - u32 tx_sgl_pos; - u32 tx_sgl_start; - u32 rx_sgl_pos; - u32 rx_sgl_start; - bool wait_second_completion; -}; - -/* - * This data type corresponds to the nand dma descriptor - * @dma_desc - low level DMA engine descriptor - * @list - list for desc_info - * - * @adm_sgl - sgl which will be used for single sgl dma descriptor. Only used by - * ADM - * @bam_sgl - sgl which will be used for dma descriptor. Only used by BAM - * @sgl_cnt - number of SGL in bam_sgl. Only used by BAM - * @dir - DMA transfer direction - */ -struct desc_info { - struct dma_async_tx_descriptor *dma_desc; - struct list_head node; - - union { - struct scatterlist adm_sgl; - struct { - struct scatterlist *bam_sgl; - int sgl_cnt; - }; - }; - enum dma_data_direction dir; -}; - -/* - * holds the current register values that we want to write. acts as a contiguous - * chunk of memory which we use to write the controller registers through DMA. - */ -struct nandc_regs { - __le32 cmd; - __le32 addr0; - __le32 addr1; - __le32 chip_sel; - __le32 exec; - - __le32 cfg0; - __le32 cfg1; - __le32 ecc_bch_cfg; - - __le32 clrflashstatus; - __le32 clrreadstatus; - - __le32 cmd1; - __le32 vld; - - __le32 orig_cmd1; - __le32 orig_vld; - - __le32 ecc_buf_cfg; - __le32 read_location0; - __le32 read_location1; - __le32 read_location2; - __le32 read_location3; - __le32 read_location_last0; - __le32 read_location_last1; - __le32 read_location_last2; - __le32 read_location_last3; - - __le32 erased_cw_detect_cfg_clr; - __le32 erased_cw_detect_cfg_set; -}; - -/* - * NAND controller data struct - * - * @dev: parent device - * - * @base: MMIO base - * - * @core_clk: controller clock - * @aon_clk: another controller clock - * - * @regs: a contiguous chunk of memory for DMA register - * writes. contains the register values to be - * written to controller - * - * @props: properties of current NAND controller, - * initialized via DT match data - * - * @controller: base controller structure - * @host_list: list containing all the chips attached to the - * controller - * - * @chan: dma channel - * @cmd_crci: ADM DMA CRCI for command flow control - * @data_crci: ADM DMA CRCI for data flow control - * - * @desc_list: DMA descriptor list (list of desc_infos) - * - * @data_buffer: our local DMA buffer for page read/writes, - * used when we can't use the buffer provided - * by upper layers directly - * @reg_read_buf: local buffer for reading back registers via DMA - * - * @base_phys: physical base address of controller registers - * @base_dma: dma base address of controller registers - * @reg_read_dma: contains dma address for register read buffer - * - * @buf_size/count/start: markers for chip->legacy.read_buf/write_buf - * functions - * @max_cwperpage: maximum QPIC codewords required. calculated - * from all connected NAND devices pagesize - * - * @reg_read_pos: marker for data read in reg_read_buf - * - * @cmd1/vld: some fixed controller register values - * - * @exec_opwrite: flag to select correct number of code word - * while reading status - */ -struct qcom_nand_controller { - struct device *dev; - - void __iomem *base; - - struct clk *core_clk; - struct clk *aon_clk; - - struct nandc_regs *regs; - struct bam_transaction *bam_txn; - - const struct qcom_nandc_props *props; - - struct nand_controller controller; - struct list_head host_list; - - union { - /* will be used only by QPIC for BAM DMA */ - struct { - struct dma_chan *tx_chan; - struct dma_chan *rx_chan; - struct dma_chan *cmd_chan; - }; - - /* will be used only by EBI2 for ADM DMA */ - struct { - struct dma_chan *chan; - unsigned int cmd_crci; - unsigned int data_crci; - }; - }; - - struct list_head desc_list; - - u8 *data_buffer; - __le32 *reg_read_buf; - - phys_addr_t base_phys; - dma_addr_t base_dma; - dma_addr_t reg_read_dma; - - int buf_size; - int buf_count; - int buf_start; - unsigned int max_cwperpage; - - int reg_read_pos; - - u32 cmd1, vld; - bool exec_opwrite; -}; +#include /* * NAND special boot partitions @@ -471,9 +47,9 @@ struct qcom_op { unsigned int data_instr_idx; unsigned int rdy_timeout_ms; unsigned int rdy_delay_ns; - u32 addr1_reg; - u32 addr2_reg; - u32 cmd_reg; + __le32 addr1_reg; + __le32 addr2_reg; + __le32 cmd_reg; u8 flag; }; @@ -544,243 +120,113 @@ struct qcom_nand_host { bool bch_enabled; }; -/* - * This data type corresponds to the NAND controller properties which varies - * among different NAND controllers. - * @ecc_modes - ecc mode for NAND - * @dev_cmd_reg_start - NAND_DEV_CMD_* registers starting offset - * @is_bam - whether NAND controller is using BAM - * @is_qpic - whether NAND CTRL is part of qpic IP - * @qpic_v2 - flag to indicate QPIC IP version 2 - * @use_codeword_fixup - whether NAND has different layout for boot partitions - */ -struct qcom_nandc_props { - u32 ecc_modes; - u32 dev_cmd_reg_start; - bool is_bam; - bool is_qpic; - bool qpic_v2; - bool use_codeword_fixup; -}; - -/* Frees the BAM transaction memory */ -static void free_bam_transaction(struct qcom_nand_controller *nandc) -{ - struct bam_transaction *bam_txn = nandc->bam_txn; - - devm_kfree(nandc->dev, bam_txn); -} - -/* Allocates and Initializes the BAM transaction */ -static struct bam_transaction * -alloc_bam_transaction(struct qcom_nand_controller *nandc) -{ - struct bam_transaction *bam_txn; - size_t bam_txn_size; - unsigned int num_cw = nandc->max_cwperpage; - void *bam_txn_buf; - - bam_txn_size = - sizeof(*bam_txn) + num_cw * - ((sizeof(*bam_txn->bam_ce) * QPIC_PER_CW_CMD_ELEMENTS) + - (sizeof(*bam_txn->cmd_sgl) * QPIC_PER_CW_CMD_SGL) + - (sizeof(*bam_txn->data_sgl) * QPIC_PER_CW_DATA_SGL)); - - bam_txn_buf = devm_kzalloc(nandc->dev, bam_txn_size, GFP_KERNEL); - if (!bam_txn_buf) - return NULL; - - bam_txn = bam_txn_buf; - bam_txn_buf += sizeof(*bam_txn); - - bam_txn->bam_ce = bam_txn_buf; - bam_txn_buf += - sizeof(*bam_txn->bam_ce) * QPIC_PER_CW_CMD_ELEMENTS * num_cw; - - bam_txn->cmd_sgl = bam_txn_buf; - bam_txn_buf += - sizeof(*bam_txn->cmd_sgl) * QPIC_PER_CW_CMD_SGL * num_cw; - - bam_txn->data_sgl = bam_txn_buf; - - init_completion(&bam_txn->txn_done); - - return bam_txn; -} - -/* Clears the BAM transaction indexes */ -static void clear_bam_transaction(struct qcom_nand_controller *nandc) -{ - struct bam_transaction *bam_txn = nandc->bam_txn; - - if (!nandc->props->is_bam) - return; - - bam_txn->bam_ce_pos = 0; - bam_txn->bam_ce_start = 0; - bam_txn->cmd_sgl_pos = 0; - bam_txn->cmd_sgl_start = 0; - bam_txn->tx_sgl_pos = 0; - bam_txn->tx_sgl_start = 0; - bam_txn->rx_sgl_pos = 0; - bam_txn->rx_sgl_start = 0; - bam_txn->last_data_desc = NULL; - bam_txn->wait_second_completion = false; - - sg_init_table(bam_txn->cmd_sgl, nandc->max_cwperpage * - QPIC_PER_CW_CMD_SGL); - sg_init_table(bam_txn->data_sgl, nandc->max_cwperpage * - QPIC_PER_CW_DATA_SGL); - - reinit_completion(&bam_txn->txn_done); -} - -/* Callback for DMA descriptor completion */ -static void qpic_bam_dma_done(void *data) -{ - struct bam_transaction *bam_txn = data; - - /* - * In case of data transfer with NAND, 2 callbacks will be generated. - * One for command channel and another one for data channel. - * If current transaction has data descriptors - * (i.e. wait_second_completion is true), then set this to false - * and wait for second DMA descriptor completion. - */ - if (bam_txn->wait_second_completion) - bam_txn->wait_second_completion = false; - else - complete(&bam_txn->txn_done); -} - -static inline struct qcom_nand_host *to_qcom_nand_host(struct nand_chip *chip) +static struct qcom_nand_host *to_qcom_nand_host(struct nand_chip *chip) { return container_of(chip, struct qcom_nand_host, chip); } -static inline struct qcom_nand_controller * +static struct qcom_nand_controller * get_qcom_nand_controller(struct nand_chip *chip) { - return container_of(chip->controller, struct qcom_nand_controller, - controller); + return (struct qcom_nand_controller *) + ((u8 *)chip->controller - sizeof(struct qcom_nand_controller)); } -static inline u32 nandc_read(struct qcom_nand_controller *nandc, int offset) +static u32 nandc_read(struct qcom_nand_controller *nandc, int offset) { return ioread32(nandc->base + offset); } -static inline void nandc_write(struct qcom_nand_controller *nandc, int offset, - u32 val) +static void nandc_write(struct qcom_nand_controller *nandc, int offset, + u32 val) { iowrite32(val, nandc->base + offset); } -static inline void nandc_read_buffer_sync(struct qcom_nand_controller *nandc, - bool is_cpu) -{ - if (!nandc->props->is_bam) - return; - - if (is_cpu) - dma_sync_single_for_cpu(nandc->dev, nandc->reg_read_dma, - MAX_REG_RD * - sizeof(*nandc->reg_read_buf), - DMA_FROM_DEVICE); - else - dma_sync_single_for_device(nandc->dev, nandc->reg_read_dma, - MAX_REG_RD * - sizeof(*nandc->reg_read_buf), - DMA_FROM_DEVICE); -} - -static __le32 *offset_to_nandc_reg(struct nandc_regs *regs, int offset) -{ - switch (offset) { - case NAND_FLASH_CMD: - return ®s->cmd; - case NAND_ADDR0: - return ®s->addr0; - case NAND_ADDR1: - return ®s->addr1; - case NAND_FLASH_CHIP_SELECT: - return ®s->chip_sel; - case NAND_EXEC_CMD: - return ®s->exec; - case NAND_FLASH_STATUS: - return ®s->clrflashstatus; - case NAND_DEV0_CFG0: - return ®s->cfg0; - case NAND_DEV0_CFG1: - return ®s->cfg1; - case NAND_DEV0_ECC_CFG: - return ®s->ecc_bch_cfg; - case NAND_READ_STATUS: - return ®s->clrreadstatus; - case NAND_DEV_CMD1: - return ®s->cmd1; - case NAND_DEV_CMD1_RESTORE: - return ®s->orig_cmd1; - case NAND_DEV_CMD_VLD: - return ®s->vld; - case NAND_DEV_CMD_VLD_RESTORE: - return ®s->orig_vld; - case NAND_EBI2_ECC_BUF_CFG: - return ®s->ecc_buf_cfg; - case NAND_READ_LOCATION_0: - return ®s->read_location0; - case NAND_READ_LOCATION_1: - return ®s->read_location1; - case NAND_READ_LOCATION_2: - return ®s->read_location2; - case NAND_READ_LOCATION_3: - return ®s->read_location3; - case NAND_READ_LOCATION_LAST_CW_0: - return ®s->read_location_last0; - case NAND_READ_LOCATION_LAST_CW_1: - return ®s->read_location_last1; - case NAND_READ_LOCATION_LAST_CW_2: - return ®s->read_location_last2; - case NAND_READ_LOCATION_LAST_CW_3: - return ®s->read_location_last3; - default: - return NULL; - } -} - -static void nandc_set_reg(struct nand_chip *chip, int offset, - u32 val) -{ - struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); - struct nandc_regs *regs = nandc->regs; - __le32 *reg; - - reg = offset_to_nandc_reg(regs, offset); - - if (reg) - *reg = cpu_to_le32(val); -} - -/* Helper to check the code word, whether it is last cw or not */ +/* Helper to check whether this is the last CW or not */ static bool qcom_nandc_is_last_cw(struct nand_ecc_ctrl *ecc, int cw) { return cw == (ecc->steps - 1); } +/** + * nandc_set_read_loc_first() - to set read location first register + * @chip: NAND Private Flash Chip Data + * @reg_base: location register base + * @cw_offset: code word offset + * @read_size: code word read length + * @is_last_read_loc: is this the last read location + * + * This function will set location register value + */ +static void nandc_set_read_loc_first(struct nand_chip *chip, + int reg_base, u32 cw_offset, + u32 read_size, u32 is_last_read_loc) +{ + struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); + __le32 locreg_val; + u32 val = (((cw_offset) << READ_LOCATION_OFFSET) | + ((read_size) << READ_LOCATION_SIZE) | + ((is_last_read_loc) << READ_LOCATION_LAST)); + + locreg_val = cpu_to_le32(val); + + if (reg_base == NAND_READ_LOCATION_0) + nandc->regs->read_location0 = locreg_val; + else if (reg_base == NAND_READ_LOCATION_1) + nandc->regs->read_location1 = locreg_val; + else if (reg_base == NAND_READ_LOCATION_2) + nandc->regs->read_location2 = locreg_val; + else if (reg_base == NAND_READ_LOCATION_3) + nandc->regs->read_location3 = locreg_val; +} + +/** + * nandc_set_read_loc_last - to set read location last register + * @chip: NAND Private Flash Chip Data + * @reg_base: location register base + * @cw_offset: code word offset + * @read_size: code word read length + * @is_last_read_loc: is this the last read location + * + * This function will set location last register value + */ +static void nandc_set_read_loc_last(struct nand_chip *chip, + int reg_base, u32 cw_offset, + u32 read_size, u32 is_last_read_loc) +{ + struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); + __le32 locreg_val; + u32 val = (((cw_offset) << READ_LOCATION_OFFSET) | + ((read_size) << READ_LOCATION_SIZE) | + ((is_last_read_loc) << READ_LOCATION_LAST)); + + locreg_val = cpu_to_le32(val); + + if (reg_base == NAND_READ_LOCATION_LAST_CW_0) + nandc->regs->read_location_last0 = locreg_val; + else if (reg_base == NAND_READ_LOCATION_LAST_CW_1) + nandc->regs->read_location_last1 = locreg_val; + else if (reg_base == NAND_READ_LOCATION_LAST_CW_2) + nandc->regs->read_location_last2 = locreg_val; + else if (reg_base == NAND_READ_LOCATION_LAST_CW_3) + nandc->regs->read_location_last3 = locreg_val; +} + /* helper to configure location register values */ static void nandc_set_read_loc(struct nand_chip *chip, int cw, int reg, - int cw_offset, int read_size, int is_last_read_loc) + u32 cw_offset, u32 read_size, u32 is_last_read_loc) { struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); struct nand_ecc_ctrl *ecc = &chip->ecc; int reg_base = NAND_READ_LOCATION_0; - if (nandc->props->qpic_v2 && qcom_nandc_is_last_cw(ecc, cw)) + if (nandc->props->qpic_version2 && qcom_nandc_is_last_cw(ecc, cw)) reg_base = NAND_READ_LOCATION_LAST_CW_0; reg_base += reg * 4; - if (nandc->props->qpic_v2 && qcom_nandc_is_last_cw(ecc, cw)) + if (nandc->props->qpic_version2 && qcom_nandc_is_last_cw(ecc, cw)) return nandc_set_read_loc_last(chip, reg_base, cw_offset, read_size, is_last_read_loc); else @@ -792,12 +238,13 @@ static void nandc_set_read_loc(struct nand_chip *chip, int cw, int reg, static void set_address(struct qcom_nand_host *host, u16 column, int page) { struct nand_chip *chip = &host->chip; + struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); if (chip->options & NAND_BUSWIDTH_16) column >>= 1; - nandc_set_reg(chip, NAND_ADDR0, page << 16 | column); - nandc_set_reg(chip, NAND_ADDR1, page >> 16 & 0xff); + nandc->regs->addr0 = cpu_to_le32(page << 16 | column); + nandc->regs->addr1 = cpu_to_le32(page >> 16 & 0xff); } /* @@ -811,407 +258,49 @@ static void set_address(struct qcom_nand_host *host, u16 column, int page) static void update_rw_regs(struct qcom_nand_host *host, int num_cw, bool read, int cw) { struct nand_chip *chip = &host->chip; - u32 cmd, cfg0, cfg1, ecc_bch_cfg; + __le32 cmd, cfg0, cfg1, ecc_bch_cfg; struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); if (read) { if (host->use_ecc) - cmd = OP_PAGE_READ_WITH_ECC | PAGE_ACC | LAST_PAGE; + cmd = cpu_to_le32(OP_PAGE_READ_WITH_ECC | PAGE_ACC | LAST_PAGE); else - cmd = OP_PAGE_READ | PAGE_ACC | LAST_PAGE; + cmd = cpu_to_le32(OP_PAGE_READ | PAGE_ACC | LAST_PAGE); } else { - cmd = OP_PROGRAM_PAGE | PAGE_ACC | LAST_PAGE; + cmd = cpu_to_le32(OP_PROGRAM_PAGE | PAGE_ACC | LAST_PAGE); } if (host->use_ecc) { - cfg0 = (host->cfg0 & ~(7U << CW_PER_PAGE)) | - (num_cw - 1) << CW_PER_PAGE; + cfg0 = cpu_to_le32((host->cfg0 & ~(7U << CW_PER_PAGE)) | + (num_cw - 1) << CW_PER_PAGE); - cfg1 = host->cfg1; - ecc_bch_cfg = host->ecc_bch_cfg; + cfg1 = cpu_to_le32(host->cfg1); + ecc_bch_cfg = cpu_to_le32(host->ecc_bch_cfg); } else { - cfg0 = (host->cfg0_raw & ~(7U << CW_PER_PAGE)) | - (num_cw - 1) << CW_PER_PAGE; + cfg0 = cpu_to_le32((host->cfg0_raw & ~(7U << CW_PER_PAGE)) | + (num_cw - 1) << CW_PER_PAGE); - cfg1 = host->cfg1_raw; - ecc_bch_cfg = 1 << ECC_CFG_ECC_DISABLE; + cfg1 = cpu_to_le32(host->cfg1_raw); + ecc_bch_cfg = cpu_to_le32(ECC_CFG_ECC_DISABLE); } - nandc_set_reg(chip, NAND_FLASH_CMD, cmd); - nandc_set_reg(chip, NAND_DEV0_CFG0, cfg0); - nandc_set_reg(chip, NAND_DEV0_CFG1, cfg1); - nandc_set_reg(chip, NAND_DEV0_ECC_CFG, ecc_bch_cfg); - if (!nandc->props->qpic_v2) - nandc_set_reg(chip, NAND_EBI2_ECC_BUF_CFG, host->ecc_buf_cfg); - nandc_set_reg(chip, NAND_FLASH_STATUS, host->clrflashstatus); - nandc_set_reg(chip, NAND_READ_STATUS, host->clrreadstatus); - nandc_set_reg(chip, NAND_EXEC_CMD, 1); + nandc->regs->cmd = cmd; + nandc->regs->cfg0 = cfg0; + nandc->regs->cfg1 = cfg1; + nandc->regs->ecc_bch_cfg = ecc_bch_cfg; + + if (!nandc->props->qpic_version2) + nandc->regs->ecc_buf_cfg = cpu_to_le32(host->ecc_buf_cfg); + + nandc->regs->clrflashstatus = cpu_to_le32(host->clrflashstatus); + nandc->regs->clrreadstatus = cpu_to_le32(host->clrreadstatus); + nandc->regs->exec = cpu_to_le32(1); if (read) nandc_set_read_loc(chip, cw, 0, 0, host->use_ecc ? host->cw_data : host->cw_size, 1); } -/* - * Maps the scatter gather list for DMA transfer and forms the DMA descriptor - * for BAM. This descriptor will be added in the NAND DMA descriptor queue - * which will be submitted to DMA engine. - */ -static int prepare_bam_async_desc(struct qcom_nand_controller *nandc, - struct dma_chan *chan, - unsigned long flags) -{ - struct desc_info *desc; - struct scatterlist *sgl; - unsigned int sgl_cnt; - int ret; - struct bam_transaction *bam_txn = nandc->bam_txn; - enum dma_transfer_direction dir_eng; - struct dma_async_tx_descriptor *dma_desc; - - desc = kzalloc(sizeof(*desc), GFP_KERNEL); - if (!desc) - return -ENOMEM; - - if (chan == nandc->cmd_chan) { - sgl = &bam_txn->cmd_sgl[bam_txn->cmd_sgl_start]; - sgl_cnt = bam_txn->cmd_sgl_pos - bam_txn->cmd_sgl_start; - bam_txn->cmd_sgl_start = bam_txn->cmd_sgl_pos; - dir_eng = DMA_MEM_TO_DEV; - desc->dir = DMA_TO_DEVICE; - } else if (chan == nandc->tx_chan) { - sgl = &bam_txn->data_sgl[bam_txn->tx_sgl_start]; - sgl_cnt = bam_txn->tx_sgl_pos - bam_txn->tx_sgl_start; - bam_txn->tx_sgl_start = bam_txn->tx_sgl_pos; - dir_eng = DMA_MEM_TO_DEV; - desc->dir = DMA_TO_DEVICE; - } else { - sgl = &bam_txn->data_sgl[bam_txn->rx_sgl_start]; - sgl_cnt = bam_txn->rx_sgl_pos - bam_txn->rx_sgl_start; - bam_txn->rx_sgl_start = bam_txn->rx_sgl_pos; - dir_eng = DMA_DEV_TO_MEM; - desc->dir = DMA_FROM_DEVICE; - } - - sg_mark_end(sgl + sgl_cnt - 1); - ret = dma_map_sg(nandc->dev, sgl, sgl_cnt, desc->dir); - if (ret == 0) { - dev_err(nandc->dev, "failure in mapping desc\n"); - kfree(desc); - return -ENOMEM; - } - - desc->sgl_cnt = sgl_cnt; - desc->bam_sgl = sgl; - - dma_desc = dmaengine_prep_slave_sg(chan, sgl, sgl_cnt, dir_eng, - flags); - - if (!dma_desc) { - dev_err(nandc->dev, "failure in prep desc\n"); - dma_unmap_sg(nandc->dev, sgl, sgl_cnt, desc->dir); - kfree(desc); - return -EINVAL; - } - - desc->dma_desc = dma_desc; - - /* update last data/command descriptor */ - if (chan == nandc->cmd_chan) - bam_txn->last_cmd_desc = dma_desc; - else - bam_txn->last_data_desc = dma_desc; - - list_add_tail(&desc->node, &nandc->desc_list); - - return 0; -} - -/* - * Prepares the command descriptor for BAM DMA which will be used for NAND - * register reads and writes. The command descriptor requires the command - * to be formed in command element type so this function uses the command - * element from bam transaction ce array and fills the same with required - * data. A single SGL can contain multiple command elements so - * NAND_BAM_NEXT_SGL will be used for starting the separate SGL - * after the current command element. - */ -static int prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read, - int reg_off, const void *vaddr, - int size, unsigned int flags) -{ - int bam_ce_size; - int i, ret; - struct bam_cmd_element *bam_ce_buffer; - struct bam_transaction *bam_txn = nandc->bam_txn; - - bam_ce_buffer = &bam_txn->bam_ce[bam_txn->bam_ce_pos]; - - /* fill the command desc */ - for (i = 0; i < size; i++) { - if (read) - bam_prep_ce(&bam_ce_buffer[i], - nandc_reg_phys(nandc, reg_off + 4 * i), - BAM_READ_COMMAND, - reg_buf_dma_addr(nandc, - (__le32 *)vaddr + i)); - else - bam_prep_ce_le32(&bam_ce_buffer[i], - nandc_reg_phys(nandc, reg_off + 4 * i), - BAM_WRITE_COMMAND, - *((__le32 *)vaddr + i)); - } - - bam_txn->bam_ce_pos += size; - - /* use the separate sgl after this command */ - if (flags & NAND_BAM_NEXT_SGL) { - bam_ce_buffer = &bam_txn->bam_ce[bam_txn->bam_ce_start]; - bam_ce_size = (bam_txn->bam_ce_pos - - bam_txn->bam_ce_start) * - sizeof(struct bam_cmd_element); - sg_set_buf(&bam_txn->cmd_sgl[bam_txn->cmd_sgl_pos], - bam_ce_buffer, bam_ce_size); - bam_txn->cmd_sgl_pos++; - bam_txn->bam_ce_start = bam_txn->bam_ce_pos; - - if (flags & NAND_BAM_NWD) { - ret = prepare_bam_async_desc(nandc, nandc->cmd_chan, - DMA_PREP_FENCE | - DMA_PREP_CMD); - if (ret) - return ret; - } - } - - return 0; -} - -/* - * Prepares the data descriptor for BAM DMA which will be used for NAND - * data reads and writes. - */ -static int prep_bam_dma_desc_data(struct qcom_nand_controller *nandc, bool read, - const void *vaddr, - int size, unsigned int flags) -{ - int ret; - struct bam_transaction *bam_txn = nandc->bam_txn; - - if (read) { - sg_set_buf(&bam_txn->data_sgl[bam_txn->rx_sgl_pos], - vaddr, size); - bam_txn->rx_sgl_pos++; - } else { - sg_set_buf(&bam_txn->data_sgl[bam_txn->tx_sgl_pos], - vaddr, size); - bam_txn->tx_sgl_pos++; - - /* - * BAM will only set EOT for DMA_PREP_INTERRUPT so if this flag - * is not set, form the DMA descriptor - */ - if (!(flags & NAND_BAM_NO_EOT)) { - ret = prepare_bam_async_desc(nandc, nandc->tx_chan, - DMA_PREP_INTERRUPT); - if (ret) - return ret; - } - } - - return 0; -} - -static int prep_adm_dma_desc(struct qcom_nand_controller *nandc, bool read, - int reg_off, const void *vaddr, int size, - bool flow_control) -{ - struct desc_info *desc; - struct dma_async_tx_descriptor *dma_desc; - struct scatterlist *sgl; - struct dma_slave_config slave_conf; - struct qcom_adm_peripheral_config periph_conf = {}; - enum dma_transfer_direction dir_eng; - int ret; - - desc = kzalloc(sizeof(*desc), GFP_KERNEL); - if (!desc) - return -ENOMEM; - - sgl = &desc->adm_sgl; - - sg_init_one(sgl, vaddr, size); - - if (read) { - dir_eng = DMA_DEV_TO_MEM; - desc->dir = DMA_FROM_DEVICE; - } else { - dir_eng = DMA_MEM_TO_DEV; - desc->dir = DMA_TO_DEVICE; - } - - ret = dma_map_sg(nandc->dev, sgl, 1, desc->dir); - if (ret == 0) { - ret = -ENOMEM; - goto err; - } - - memset(&slave_conf, 0x00, sizeof(slave_conf)); - - slave_conf.device_fc = flow_control; - if (read) { - slave_conf.src_maxburst = 16; - slave_conf.src_addr = nandc->base_dma + reg_off; - if (nandc->data_crci) { - periph_conf.crci = nandc->data_crci; - slave_conf.peripheral_config = &periph_conf; - slave_conf.peripheral_size = sizeof(periph_conf); - } - } else { - slave_conf.dst_maxburst = 16; - slave_conf.dst_addr = nandc->base_dma + reg_off; - if (nandc->cmd_crci) { - periph_conf.crci = nandc->cmd_crci; - slave_conf.peripheral_config = &periph_conf; - slave_conf.peripheral_size = sizeof(periph_conf); - } - } - - ret = dmaengine_slave_config(nandc->chan, &slave_conf); - if (ret) { - dev_err(nandc->dev, "failed to configure dma channel\n"); - goto err; - } - - dma_desc = dmaengine_prep_slave_sg(nandc->chan, sgl, 1, dir_eng, 0); - if (!dma_desc) { - dev_err(nandc->dev, "failed to prepare desc\n"); - ret = -EINVAL; - goto err; - } - - desc->dma_desc = dma_desc; - - list_add_tail(&desc->node, &nandc->desc_list); - - return 0; -err: - kfree(desc); - - return ret; -} - -/* - * read_reg_dma: prepares a descriptor to read a given number of - * contiguous registers to the reg_read_buf pointer - * - * @first: offset of the first register in the contiguous block - * @num_regs: number of registers to read - * @flags: flags to control DMA descriptor preparation - */ -static int read_reg_dma(struct qcom_nand_controller *nandc, int first, - int num_regs, unsigned int flags) -{ - bool flow_control = false; - void *vaddr; - - vaddr = nandc->reg_read_buf + nandc->reg_read_pos; - nandc->reg_read_pos += num_regs; - - if (first == NAND_DEV_CMD_VLD || first == NAND_DEV_CMD1) - first = dev_cmd_reg_addr(nandc, first); - - if (nandc->props->is_bam) - return prep_bam_dma_desc_cmd(nandc, true, first, vaddr, - num_regs, flags); - - if (first == NAND_READ_ID || first == NAND_FLASH_STATUS) - flow_control = true; - - return prep_adm_dma_desc(nandc, true, first, vaddr, - num_regs * sizeof(u32), flow_control); -} - -/* - * write_reg_dma: prepares a descriptor to write a given number of - * contiguous registers - * - * @first: offset of the first register in the contiguous block - * @num_regs: number of registers to write - * @flags: flags to control DMA descriptor preparation - */ -static int write_reg_dma(struct qcom_nand_controller *nandc, int first, - int num_regs, unsigned int flags) -{ - bool flow_control = false; - struct nandc_regs *regs = nandc->regs; - void *vaddr; - - vaddr = offset_to_nandc_reg(regs, first); - - if (first == NAND_ERASED_CW_DETECT_CFG) { - if (flags & NAND_ERASED_CW_SET) - vaddr = ®s->erased_cw_detect_cfg_set; - else - vaddr = ®s->erased_cw_detect_cfg_clr; - } - - if (first == NAND_EXEC_CMD) - flags |= NAND_BAM_NWD; - - if (first == NAND_DEV_CMD1_RESTORE || first == NAND_DEV_CMD1) - first = dev_cmd_reg_addr(nandc, NAND_DEV_CMD1); - - if (first == NAND_DEV_CMD_VLD_RESTORE || first == NAND_DEV_CMD_VLD) - first = dev_cmd_reg_addr(nandc, NAND_DEV_CMD_VLD); - - if (nandc->props->is_bam) - return prep_bam_dma_desc_cmd(nandc, false, first, vaddr, - num_regs, flags); - - if (first == NAND_FLASH_CMD) - flow_control = true; - - return prep_adm_dma_desc(nandc, false, first, vaddr, - num_regs * sizeof(u32), flow_control); -} - -/* - * read_data_dma: prepares a DMA descriptor to transfer data from the - * controller's internal buffer to the buffer 'vaddr' - * - * @reg_off: offset within the controller's data buffer - * @vaddr: virtual address of the buffer we want to write to - * @size: DMA transaction size in bytes - * @flags: flags to control DMA descriptor preparation - */ -static int read_data_dma(struct qcom_nand_controller *nandc, int reg_off, - const u8 *vaddr, int size, unsigned int flags) -{ - if (nandc->props->is_bam) - return prep_bam_dma_desc_data(nandc, true, vaddr, size, flags); - - return prep_adm_dma_desc(nandc, true, reg_off, vaddr, size, false); -} - -/* - * write_data_dma: prepares a DMA descriptor to transfer data from - * 'vaddr' to the controller's internal buffer - * - * @reg_off: offset within the controller's data buffer - * @vaddr: virtual address of the buffer we want to read from - * @size: DMA transaction size in bytes - * @flags: flags to control DMA descriptor preparation - */ -static int write_data_dma(struct qcom_nand_controller *nandc, int reg_off, - const u8 *vaddr, int size, unsigned int flags) -{ - if (nandc->props->is_bam) - return prep_bam_dma_desc_data(nandc, false, vaddr, size, flags); - - return prep_adm_dma_desc(nandc, false, reg_off, vaddr, size, false); -} - /* * Helper to prepare DMA descriptors for configuring registers * before reading a NAND page. @@ -1220,13 +309,14 @@ static void config_nand_page_read(struct nand_chip *chip) { struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); - write_reg_dma(nandc, NAND_ADDR0, 2, 0); - write_reg_dma(nandc, NAND_DEV0_CFG0, 3, 0); - if (!nandc->props->qpic_v2) - write_reg_dma(nandc, NAND_EBI2_ECC_BUF_CFG, 1, 0); - write_reg_dma(nandc, NAND_ERASED_CW_DETECT_CFG, 1, 0); - write_reg_dma(nandc, NAND_ERASED_CW_DETECT_CFG, 1, - NAND_ERASED_CW_SET | NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->addr0, NAND_ADDR0, 2, 0); + qcom_write_reg_dma(nandc, &nandc->regs->cfg0, NAND_DEV0_CFG0, 3, 0); + if (!nandc->props->qpic_version2) + qcom_write_reg_dma(nandc, &nandc->regs->ecc_buf_cfg, NAND_EBI2_ECC_BUF_CFG, 1, 0); + qcom_write_reg_dma(nandc, &nandc->regs->erased_cw_detect_cfg_clr, + NAND_ERASED_CW_DETECT_CFG, 1, 0); + qcom_write_reg_dma(nandc, &nandc->regs->erased_cw_detect_cfg_set, + NAND_ERASED_CW_DETECT_CFG, 1, NAND_ERASED_CW_SET | NAND_BAM_NEXT_SGL); } /* @@ -1239,23 +329,23 @@ config_nand_cw_read(struct nand_chip *chip, bool use_ecc, int cw) struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); struct nand_ecc_ctrl *ecc = &chip->ecc; - int reg = NAND_READ_LOCATION_0; + __le32 *reg = &nandc->regs->read_location0; - if (nandc->props->qpic_v2 && qcom_nandc_is_last_cw(ecc, cw)) - reg = NAND_READ_LOCATION_LAST_CW_0; + if (nandc->props->qpic_version2 && qcom_nandc_is_last_cw(ecc, cw)) + reg = &nandc->regs->read_location_last0; - if (nandc->props->is_bam) - write_reg_dma(nandc, reg, 4, NAND_BAM_NEXT_SGL); + if (nandc->props->supports_bam) + qcom_write_reg_dma(nandc, reg, NAND_READ_LOCATION_0, 4, NAND_BAM_NEXT_SGL); - write_reg_dma(nandc, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL); - write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->cmd, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->exec, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); if (use_ecc) { - read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0); - read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1, - NAND_BAM_NEXT_SGL); + qcom_read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0); + qcom_read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1, + NAND_BAM_NEXT_SGL); } else { - read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); + qcom_read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); } } @@ -1279,11 +369,11 @@ static void config_nand_page_write(struct nand_chip *chip) { struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); - write_reg_dma(nandc, NAND_ADDR0, 2, 0); - write_reg_dma(nandc, NAND_DEV0_CFG0, 3, 0); - if (!nandc->props->qpic_v2) - write_reg_dma(nandc, NAND_EBI2_ECC_BUF_CFG, 1, - NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->addr0, NAND_ADDR0, 2, 0); + qcom_write_reg_dma(nandc, &nandc->regs->cfg0, NAND_DEV0_CFG0, 3, 0); + if (!nandc->props->qpic_version2) + qcom_write_reg_dma(nandc, &nandc->regs->ecc_buf_cfg, NAND_EBI2_ECC_BUF_CFG, 1, + NAND_BAM_NEXT_SGL); } /* @@ -1294,95 +384,14 @@ static void config_nand_cw_write(struct nand_chip *chip) { struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); - write_reg_dma(nandc, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL); - write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->cmd, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->exec, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); - read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); + qcom_read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); - write_reg_dma(nandc, NAND_FLASH_STATUS, 1, 0); - write_reg_dma(nandc, NAND_READ_STATUS, 1, NAND_BAM_NEXT_SGL); -} - -/* helpers to submit/free our list of dma descriptors */ -static int submit_descs(struct qcom_nand_controller *nandc) -{ - struct desc_info *desc, *n; - dma_cookie_t cookie = 0; - struct bam_transaction *bam_txn = nandc->bam_txn; - int ret = 0; - - if (nandc->props->is_bam) { - if (bam_txn->rx_sgl_pos > bam_txn->rx_sgl_start) { - ret = prepare_bam_async_desc(nandc, nandc->rx_chan, 0); - if (ret) - goto err_unmap_free_desc; - } - - if (bam_txn->tx_sgl_pos > bam_txn->tx_sgl_start) { - ret = prepare_bam_async_desc(nandc, nandc->tx_chan, - DMA_PREP_INTERRUPT); - if (ret) - goto err_unmap_free_desc; - } - - if (bam_txn->cmd_sgl_pos > bam_txn->cmd_sgl_start) { - ret = prepare_bam_async_desc(nandc, nandc->cmd_chan, - DMA_PREP_CMD); - if (ret) - goto err_unmap_free_desc; - } - } - - list_for_each_entry(desc, &nandc->desc_list, node) - cookie = dmaengine_submit(desc->dma_desc); - - if (nandc->props->is_bam) { - bam_txn->last_cmd_desc->callback = qpic_bam_dma_done; - bam_txn->last_cmd_desc->callback_param = bam_txn; - if (bam_txn->last_data_desc) { - bam_txn->last_data_desc->callback = qpic_bam_dma_done; - bam_txn->last_data_desc->callback_param = bam_txn; - bam_txn->wait_second_completion = true; - } - - dma_async_issue_pending(nandc->tx_chan); - dma_async_issue_pending(nandc->rx_chan); - dma_async_issue_pending(nandc->cmd_chan); - - if (!wait_for_completion_timeout(&bam_txn->txn_done, - QPIC_NAND_COMPLETION_TIMEOUT)) - ret = -ETIMEDOUT; - } else { - if (dma_sync_wait(nandc->chan, cookie) != DMA_COMPLETE) - ret = -ETIMEDOUT; - } - -err_unmap_free_desc: - /* - * Unmap the dma sg_list and free the desc allocated by both - * prepare_bam_async_desc() and prep_adm_dma_desc() functions. - */ - list_for_each_entry_safe(desc, n, &nandc->desc_list, node) { - list_del(&desc->node); - - if (nandc->props->is_bam) - dma_unmap_sg(nandc->dev, desc->bam_sgl, - desc->sgl_cnt, desc->dir); - else - dma_unmap_sg(nandc->dev, &desc->adm_sgl, 1, - desc->dir); - - kfree(desc); - } - - return ret; -} - -/* reset the register read buffer for next NAND operation */ -static void clear_read_regs(struct qcom_nand_controller *nandc) -{ - nandc->reg_read_pos = 0; - nandc_read_buffer_sync(nandc, false); + qcom_write_reg_dma(nandc, &nandc->regs->clrflashstatus, NAND_FLASH_STATUS, 1, 0); + qcom_write_reg_dma(nandc, &nandc->regs->clrreadstatus, NAND_READ_STATUS, 1, + NAND_BAM_NEXT_SGL); } /* @@ -1446,7 +455,7 @@ static int check_flash_errors(struct qcom_nand_host *host, int cw_cnt) struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip); int i; - nandc_read_buffer_sync(nandc, true); + qcom_nandc_dev_to_mem(nandc, true); for (i = 0; i < cw_cnt; i++) { u32 flash = le32_to_cpu(nandc->reg_read_buf[i]); @@ -1473,13 +482,13 @@ qcom_nandc_read_cw_raw(struct mtd_info *mtd, struct nand_chip *chip, nand_read_page_op(chip, page, 0, NULL, 0); nandc->buf_count = 0; nandc->buf_start = 0; - clear_read_regs(nandc); + qcom_clear_read_regs(nandc); host->use_ecc = false; - if (nandc->props->qpic_v2) + if (nandc->props->qpic_version2) raw_cw = ecc->steps - 1; - clear_bam_transaction(nandc); + qcom_clear_bam_transaction(nandc); set_address(host, host->cw_size * cw, page); update_rw_regs(host, 1, true, raw_cw); config_nand_page_read(chip); @@ -1497,7 +506,7 @@ qcom_nandc_read_cw_raw(struct mtd_info *mtd, struct nand_chip *chip, oob_size2 = host->ecc_bytes_hw + host->spare_bytes; } - if (nandc->props->is_bam) { + if (nandc->props->supports_bam) { nandc_set_read_loc(chip, cw, 0, read_loc, data_size1, 0); read_loc += data_size1; @@ -1512,18 +521,18 @@ qcom_nandc_read_cw_raw(struct mtd_info *mtd, struct nand_chip *chip, config_nand_cw_read(chip, false, raw_cw); - read_data_dma(nandc, reg_off, data_buf, data_size1, 0); + qcom_read_data_dma(nandc, reg_off, data_buf, data_size1, 0); reg_off += data_size1; - read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0); + qcom_read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0); reg_off += oob_size1; - read_data_dma(nandc, reg_off, data_buf + data_size1, data_size2, 0); + qcom_read_data_dma(nandc, reg_off, data_buf + data_size1, data_size2, 0); reg_off += data_size2; - read_data_dma(nandc, reg_off, oob_buf + oob_size1, oob_size2, 0); + qcom_read_data_dma(nandc, reg_off, oob_buf + oob_size1, oob_size2, 0); - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure to read raw cw %d\n", cw); return ret; @@ -1621,7 +630,7 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf, u8 *data_buf_start = data_buf, *oob_buf_start = oob_buf; buf = (struct read_stats *)nandc->reg_read_buf; - nandc_read_buffer_sync(nandc, true); + qcom_nandc_dev_to_mem(nandc, true); for (i = 0; i < ecc->steps; i++, buf++) { u32 flash, buffer, erased_cw; @@ -1734,7 +743,7 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf, oob_size = host->ecc_bytes_hw + host->spare_bytes; } - if (nandc->props->is_bam) { + if (nandc->props->supports_bam) { if (data_buf && oob_buf) { nandc_set_read_loc(chip, i, 0, 0, data_size, 0); nandc_set_read_loc(chip, i, 1, data_size, @@ -1750,8 +759,8 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf, config_nand_cw_read(chip, true, i); if (data_buf) - read_data_dma(nandc, FLASH_BUF_ACC, data_buf, - data_size, 0); + qcom_read_data_dma(nandc, FLASH_BUF_ACC, data_buf, + data_size, 0); /* * when ecc is enabled, the controller doesn't read the real @@ -1766,8 +775,8 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf, for (j = 0; j < host->bbm_size; j++) *oob_buf++ = 0xff; - read_data_dma(nandc, FLASH_BUF_ACC + data_size, - oob_buf, oob_size, 0); + qcom_read_data_dma(nandc, FLASH_BUF_ACC + data_size, + oob_buf, oob_size, 0); } if (data_buf) @@ -1776,7 +785,7 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf, oob_buf += oob_size; } - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure to read page/oob\n"); return ret; @@ -1797,7 +806,7 @@ static int copy_last_cw(struct qcom_nand_host *host, int page) int size; int ret; - clear_read_regs(nandc); + qcom_clear_read_regs(nandc); size = host->use_ecc ? host->cw_data : host->cw_size; @@ -1809,9 +818,9 @@ static int copy_last_cw(struct qcom_nand_host *host, int page) config_nand_single_cw_page_read(chip, host->use_ecc, ecc->steps - 1); - read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer, size, 0); + qcom_read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer, size, 0); - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) dev_err(nandc->dev, "failed to copy last codeword\n"); @@ -1897,14 +906,14 @@ static int qcom_nandc_read_page(struct nand_chip *chip, u8 *buf, nandc->buf_count = 0; nandc->buf_start = 0; host->use_ecc = true; - clear_read_regs(nandc); + qcom_clear_read_regs(nandc); set_address(host, 0, page); update_rw_regs(host, ecc->steps, true, 0); data_buf = buf; oob_buf = oob_required ? chip->oob_poi : NULL; - clear_bam_transaction(nandc); + qcom_clear_bam_transaction(nandc); return read_page_ecc(host, data_buf, oob_buf, page); } @@ -1945,8 +954,8 @@ static int qcom_nandc_read_oob(struct nand_chip *chip, int page) if (host->nr_boot_partitions) qcom_nandc_codeword_fixup(host, page); - clear_read_regs(nandc); - clear_bam_transaction(nandc); + qcom_clear_read_regs(nandc); + qcom_clear_bam_transaction(nandc); host->use_ecc = true; set_address(host, 0, page); @@ -1973,8 +982,8 @@ static int qcom_nandc_write_page(struct nand_chip *chip, const u8 *buf, set_address(host, 0, page); nandc->buf_count = 0; nandc->buf_start = 0; - clear_read_regs(nandc); - clear_bam_transaction(nandc); + qcom_clear_read_regs(nandc); + qcom_clear_bam_transaction(nandc); data_buf = (u8 *)buf; oob_buf = chip->oob_poi; @@ -1995,8 +1004,8 @@ static int qcom_nandc_write_page(struct nand_chip *chip, const u8 *buf, oob_size = ecc->bytes; } - write_data_dma(nandc, FLASH_BUF_ACC, data_buf, data_size, - i == (ecc->steps - 1) ? NAND_BAM_NO_EOT : 0); + qcom_write_data_dma(nandc, FLASH_BUF_ACC, data_buf, data_size, + i == (ecc->steps - 1) ? NAND_BAM_NO_EOT : 0); /* * when ECC is enabled, we don't really need to write anything @@ -2008,8 +1017,8 @@ static int qcom_nandc_write_page(struct nand_chip *chip, const u8 *buf, if (qcom_nandc_is_last_cw(ecc, i)) { oob_buf += host->bbm_size; - write_data_dma(nandc, FLASH_BUF_ACC + data_size, - oob_buf, oob_size, 0); + qcom_write_data_dma(nandc, FLASH_BUF_ACC + data_size, + oob_buf, oob_size, 0); } config_nand_cw_write(chip); @@ -2018,7 +1027,7 @@ static int qcom_nandc_write_page(struct nand_chip *chip, const u8 *buf, oob_buf += oob_size; } - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure to write page\n"); return ret; @@ -2043,8 +1052,8 @@ static int qcom_nandc_write_page_raw(struct nand_chip *chip, qcom_nandc_codeword_fixup(host, page); nand_prog_page_begin_op(chip, page, 0, NULL, 0); - clear_read_regs(nandc); - clear_bam_transaction(nandc); + qcom_clear_read_regs(nandc); + qcom_clear_bam_transaction(nandc); data_buf = (u8 *)buf; oob_buf = chip->oob_poi; @@ -2070,28 +1079,28 @@ static int qcom_nandc_write_page_raw(struct nand_chip *chip, oob_size2 = host->ecc_bytes_hw + host->spare_bytes; } - write_data_dma(nandc, reg_off, data_buf, data_size1, - NAND_BAM_NO_EOT); + qcom_write_data_dma(nandc, reg_off, data_buf, data_size1, + NAND_BAM_NO_EOT); reg_off += data_size1; data_buf += data_size1; - write_data_dma(nandc, reg_off, oob_buf, oob_size1, - NAND_BAM_NO_EOT); + qcom_write_data_dma(nandc, reg_off, oob_buf, oob_size1, + NAND_BAM_NO_EOT); reg_off += oob_size1; oob_buf += oob_size1; - write_data_dma(nandc, reg_off, data_buf, data_size2, - NAND_BAM_NO_EOT); + qcom_write_data_dma(nandc, reg_off, data_buf, data_size2, + NAND_BAM_NO_EOT); reg_off += data_size2; data_buf += data_size2; - write_data_dma(nandc, reg_off, oob_buf, oob_size2, 0); + qcom_write_data_dma(nandc, reg_off, oob_buf, oob_size2, 0); oob_buf += oob_size2; config_nand_cw_write(chip); } - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure to write raw page\n"); return ret; @@ -2121,7 +1130,7 @@ static int qcom_nandc_write_oob(struct nand_chip *chip, int page) qcom_nandc_codeword_fixup(host, page); host->use_ecc = true; - clear_bam_transaction(nandc); + qcom_clear_bam_transaction(nandc); /* calculate the data and oob size for the last codeword/step */ data_size = ecc->size - ((ecc->steps - 1) << 2); @@ -2136,11 +1145,11 @@ static int qcom_nandc_write_oob(struct nand_chip *chip, int page) update_rw_regs(host, 1, false, 0); config_nand_page_write(chip); - write_data_dma(nandc, FLASH_BUF_ACC, - nandc->data_buffer, data_size + oob_size, 0); + qcom_write_data_dma(nandc, FLASH_BUF_ACC, + nandc->data_buffer, data_size + oob_size, 0); config_nand_cw_write(chip); - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure to write oob\n"); return ret; @@ -2167,7 +1176,7 @@ static int qcom_nandc_block_bad(struct nand_chip *chip, loff_t ofs) */ host->use_ecc = false; - clear_bam_transaction(nandc); + qcom_clear_bam_transaction(nandc); ret = copy_last_cw(host, page); if (ret) goto err; @@ -2194,8 +1203,8 @@ static int qcom_nandc_block_markbad(struct nand_chip *chip, loff_t ofs) struct nand_ecc_ctrl *ecc = &chip->ecc; int page, ret; - clear_read_regs(nandc); - clear_bam_transaction(nandc); + qcom_clear_read_regs(nandc); + qcom_clear_bam_transaction(nandc); /* * to mark the BBM as bad, we flash the entire last codeword with 0s. @@ -2212,11 +1221,11 @@ static int qcom_nandc_block_markbad(struct nand_chip *chip, loff_t ofs) update_rw_regs(host, 1, false, ecc->steps - 1); config_nand_page_write(chip); - write_data_dma(nandc, FLASH_BUF_ACC, - nandc->data_buffer, host->cw_size, 0); + qcom_write_data_dma(nandc, FLASH_BUF_ACC, + nandc->data_buffer, host->cw_size, 0); config_nand_cw_write(chip); - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure to update BBM\n"); return ret; @@ -2455,15 +1464,15 @@ static int qcom_nand_attach_chip(struct nand_chip *chip) mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops); /* Free the initially allocated BAM transaction for reading the ONFI params */ - if (nandc->props->is_bam) - free_bam_transaction(nandc); + if (nandc->props->supports_bam) + qcom_free_bam_transaction(nandc); nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage, cwperpage); /* Now allocate the BAM transaction based on updated max_cwperpage */ - if (nandc->props->is_bam) { - nandc->bam_txn = alloc_bam_transaction(nandc); + if (nandc->props->supports_bam) { + nandc->bam_txn = qcom_alloc_bam_transaction(nandc); if (!nandc->bam_txn) { dev_err(nandc->dev, "failed to allocate bam transaction\n"); @@ -2485,44 +1494,43 @@ static int qcom_nand_attach_chip(struct nand_chip *chip) host->cw_size = host->cw_data + ecc->bytes; bad_block_byte = mtd->writesize - host->cw_size * (cwperpage - 1) + 1; - host->cfg0 = (cwperpage - 1) << CW_PER_PAGE - | host->cw_data << UD_SIZE_BYTES - | 0 << DISABLE_STATUS_AFTER_WRITE - | 5 << NUM_ADDR_CYCLES - | host->ecc_bytes_hw << ECC_PARITY_SIZE_BYTES_RS - | 0 << STATUS_BFR_READ - | 1 << SET_RD_MODE_AFTER_STATUS - | host->spare_bytes << SPARE_SIZE_BYTES; + host->cfg0 = FIELD_PREP(CW_PER_PAGE_MASK, (cwperpage - 1)) | + FIELD_PREP(UD_SIZE_BYTES_MASK, host->cw_data) | + FIELD_PREP(DISABLE_STATUS_AFTER_WRITE, 0) | + FIELD_PREP(NUM_ADDR_CYCLES_MASK, 5) | + FIELD_PREP(ECC_PARITY_SIZE_BYTES_RS, host->ecc_bytes_hw) | + FIELD_PREP(STATUS_BFR_READ, 0) | + FIELD_PREP(SET_RD_MODE_AFTER_STATUS, 1) | + FIELD_PREP(SPARE_SIZE_BYTES_MASK, host->spare_bytes); - host->cfg1 = 7 << NAND_RECOVERY_CYCLES - | 0 << CS_ACTIVE_BSY - | bad_block_byte << BAD_BLOCK_BYTE_NUM - | 0 << BAD_BLOCK_IN_SPARE_AREA - | 2 << WR_RD_BSY_GAP - | wide_bus << WIDE_FLASH - | host->bch_enabled << ENABLE_BCH_ECC; + host->cfg1 = FIELD_PREP(NAND_RECOVERY_CYCLES_MASK, 7) | + FIELD_PREP(BAD_BLOCK_BYTE_NUM_MASK, bad_block_byte) | + FIELD_PREP(BAD_BLOCK_IN_SPARE_AREA, 0) | + FIELD_PREP(WR_RD_BSY_GAP_MASK, 2) | + FIELD_PREP(WIDE_FLASH, wide_bus) | + FIELD_PREP(ENABLE_BCH_ECC, host->bch_enabled); - host->cfg0_raw = (cwperpage - 1) << CW_PER_PAGE - | host->cw_size << UD_SIZE_BYTES - | 5 << NUM_ADDR_CYCLES - | 0 << SPARE_SIZE_BYTES; + host->cfg0_raw = FIELD_PREP(CW_PER_PAGE_MASK, (cwperpage - 1)) | + FIELD_PREP(UD_SIZE_BYTES_MASK, host->cw_size) | + FIELD_PREP(NUM_ADDR_CYCLES_MASK, 5) | + FIELD_PREP(SPARE_SIZE_BYTES_MASK, 0); - host->cfg1_raw = 7 << NAND_RECOVERY_CYCLES - | 0 << CS_ACTIVE_BSY - | 17 << BAD_BLOCK_BYTE_NUM - | 1 << BAD_BLOCK_IN_SPARE_AREA - | 2 << WR_RD_BSY_GAP - | wide_bus << WIDE_FLASH - | 1 << DEV0_CFG1_ECC_DISABLE; + host->cfg1_raw = FIELD_PREP(NAND_RECOVERY_CYCLES_MASK, 7) | + FIELD_PREP(CS_ACTIVE_BSY, 0) | + FIELD_PREP(BAD_BLOCK_BYTE_NUM_MASK, 17) | + FIELD_PREP(BAD_BLOCK_IN_SPARE_AREA, 1) | + FIELD_PREP(WR_RD_BSY_GAP_MASK, 2) | + FIELD_PREP(WIDE_FLASH, wide_bus) | + FIELD_PREP(DEV0_CFG1_ECC_DISABLE, 1); - host->ecc_bch_cfg = !host->bch_enabled << ECC_CFG_ECC_DISABLE - | 0 << ECC_SW_RESET - | host->cw_data << ECC_NUM_DATA_BYTES - | 1 << ECC_FORCE_CLK_OPEN - | ecc_mode << ECC_MODE - | host->ecc_bytes_hw << ECC_PARITY_SIZE_BYTES_BCH; + host->ecc_bch_cfg = FIELD_PREP(ECC_CFG_ECC_DISABLE, !host->bch_enabled) | + FIELD_PREP(ECC_SW_RESET, 0) | + FIELD_PREP(ECC_NUM_DATA_BYTES_MASK, host->cw_data) | + FIELD_PREP(ECC_FORCE_CLK_OPEN, 1) | + FIELD_PREP(ECC_MODE_MASK, ecc_mode) | + FIELD_PREP(ECC_PARITY_SIZE_BYTES_BCH_MASK, host->ecc_bytes_hw); - if (!nandc->props->qpic_v2) + if (!nandc->props->qpic_version2) host->ecc_buf_cfg = 0x203 << NUM_STEPS; host->clrflashstatus = FS_READY_BSY_N; @@ -2556,7 +1564,7 @@ static int qcom_op_cmd_mapping(struct nand_chip *chip, u8 opcode, cmd = OP_FETCH_ID; break; case NAND_CMD_PARAM: - if (nandc->props->qpic_v2) + if (nandc->props->qpic_version2) cmd = OP_PAGE_READ_ONFI_READ; else cmd = OP_PAGE_READ; @@ -2609,7 +1617,7 @@ static int qcom_parse_instructions(struct nand_chip *chip, if (ret < 0) return ret; - q_op->cmd_reg = ret; + q_op->cmd_reg = cpu_to_le32(ret); q_op->rdy_delay_ns = instr->delay_ns; break; @@ -2619,10 +1627,10 @@ static int qcom_parse_instructions(struct nand_chip *chip, addrs = &instr->ctx.addr.addrs[offset]; for (i = 0; i < min_t(unsigned int, 4, naddrs); i++) - q_op->addr1_reg |= addrs[i] << (i * 8); + q_op->addr1_reg |= cpu_to_le32(addrs[i] << (i * 8)); if (naddrs > 4) - q_op->addr2_reg |= addrs[4]; + q_op->addr2_reg |= cpu_to_le32(addrs[4]); q_op->rdy_delay_ns = instr->delay_ns; break; @@ -2663,7 +1671,7 @@ static int qcom_wait_rdy_poll(struct nand_chip *chip, unsigned int time_ms) unsigned long start = jiffies + msecs_to_jiffies(time_ms); u32 flash; - nandc_read_buffer_sync(nandc, true); + qcom_nandc_dev_to_mem(nandc, true); do { flash = le32_to_cpu(nandc->reg_read_buf[0]); @@ -2703,23 +1711,23 @@ static int qcom_read_status_exec(struct nand_chip *chip, nandc->buf_start = 0; host->use_ecc = false; - clear_read_regs(nandc); - clear_bam_transaction(nandc); + qcom_clear_read_regs(nandc); + qcom_clear_bam_transaction(nandc); - nandc_set_reg(chip, NAND_FLASH_CMD, q_op.cmd_reg); - nandc_set_reg(chip, NAND_EXEC_CMD, 1); + nandc->regs->cmd = q_op.cmd_reg; + nandc->regs->exec = cpu_to_le32(1); - write_reg_dma(nandc, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL); - write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); - read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->cmd, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->exec, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); + qcom_read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure in submitting status descriptor\n"); goto err_out; } - nandc_read_buffer_sync(nandc, true); + qcom_nandc_dev_to_mem(nandc, true); for (i = 0; i < num_cw; i++) { flash_status = le32_to_cpu(nandc->reg_read_buf[i]); @@ -2760,23 +1768,21 @@ static int qcom_read_id_type_exec(struct nand_chip *chip, const struct nand_subo nandc->buf_start = 0; host->use_ecc = false; - clear_read_regs(nandc); - clear_bam_transaction(nandc); + qcom_clear_read_regs(nandc); + qcom_clear_bam_transaction(nandc); - nandc_set_reg(chip, NAND_FLASH_CMD, q_op.cmd_reg); - nandc_set_reg(chip, NAND_ADDR0, q_op.addr1_reg); - nandc_set_reg(chip, NAND_ADDR1, q_op.addr2_reg); - nandc_set_reg(chip, NAND_FLASH_CHIP_SELECT, - nandc->props->is_bam ? 0 : DM_EN); + nandc->regs->cmd = q_op.cmd_reg; + nandc->regs->addr0 = q_op.addr1_reg; + nandc->regs->addr1 = q_op.addr2_reg; + nandc->regs->chip_sel = cpu_to_le32(nandc->props->supports_bam ? 0 : DM_EN); + nandc->regs->exec = cpu_to_le32(1); - nandc_set_reg(chip, NAND_EXEC_CMD, 1); + qcom_write_reg_dma(nandc, &nandc->regs->cmd, NAND_FLASH_CMD, 4, NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->exec, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); - write_reg_dma(nandc, NAND_FLASH_CMD, 4, NAND_BAM_NEXT_SGL); - write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); + qcom_read_reg_dma(nandc, NAND_READ_ID, 1, NAND_BAM_NEXT_SGL); - read_reg_dma(nandc, NAND_READ_ID, 1, NAND_BAM_NEXT_SGL); - - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure in submitting read id descriptor\n"); goto err_out; @@ -2786,7 +1792,7 @@ static int qcom_read_id_type_exec(struct nand_chip *chip, const struct nand_subo op_id = q_op.data_instr_idx; len = nand_subop_get_data_len(subop, op_id); - nandc_read_buffer_sync(nandc, true); + qcom_nandc_dev_to_mem(nandc, true); memcpy(instr->ctx.data.buf.in, nandc->reg_read_buf, len); err_out: @@ -2807,15 +1813,14 @@ static int qcom_misc_cmd_type_exec(struct nand_chip *chip, const struct nand_sub if (q_op.flag == OP_PROGRAM_PAGE) { goto wait_rdy; - } else if (q_op.cmd_reg == OP_BLOCK_ERASE) { - q_op.cmd_reg |= PAGE_ACC | LAST_PAGE; - nandc_set_reg(chip, NAND_ADDR0, q_op.addr1_reg); - nandc_set_reg(chip, NAND_ADDR1, q_op.addr2_reg); - nandc_set_reg(chip, NAND_DEV0_CFG0, - host->cfg0_raw & ~(7 << CW_PER_PAGE)); - nandc_set_reg(chip, NAND_DEV0_CFG1, host->cfg1_raw); + } else if (q_op.cmd_reg == cpu_to_le32(OP_BLOCK_ERASE)) { + q_op.cmd_reg |= cpu_to_le32(PAGE_ACC | LAST_PAGE); + nandc->regs->addr0 = q_op.addr1_reg; + nandc->regs->addr1 = q_op.addr2_reg; + nandc->regs->cfg0 = cpu_to_le32(host->cfg0_raw & ~(7 << CW_PER_PAGE)); + nandc->regs->cfg1 = cpu_to_le32(host->cfg1_raw); instrs = 3; - } else if (q_op.cmd_reg != OP_RESET_DEVICE) { + } else if (q_op.cmd_reg != cpu_to_le32(OP_RESET_DEVICE)) { return 0; } @@ -2823,20 +1828,20 @@ static int qcom_misc_cmd_type_exec(struct nand_chip *chip, const struct nand_sub nandc->buf_start = 0; host->use_ecc = false; - clear_read_regs(nandc); - clear_bam_transaction(nandc); + qcom_clear_read_regs(nandc); + qcom_clear_bam_transaction(nandc); - nandc_set_reg(chip, NAND_FLASH_CMD, q_op.cmd_reg); - nandc_set_reg(chip, NAND_EXEC_CMD, 1); + nandc->regs->cmd = q_op.cmd_reg; + nandc->regs->exec = cpu_to_le32(1); - write_reg_dma(nandc, NAND_FLASH_CMD, instrs, NAND_BAM_NEXT_SGL); - if (q_op.cmd_reg == OP_BLOCK_ERASE) - write_reg_dma(nandc, NAND_DEV0_CFG0, 2, NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->cmd, NAND_FLASH_CMD, instrs, NAND_BAM_NEXT_SGL); + if (q_op.cmd_reg == cpu_to_le32(OP_BLOCK_ERASE)) + qcom_write_reg_dma(nandc, &nandc->regs->cfg0, NAND_DEV0_CFG0, 2, NAND_BAM_NEXT_SGL); - write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); - read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); + qcom_write_reg_dma(nandc, &nandc->regs->exec, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); + qcom_read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure in submitting misc descriptor\n"); goto err_out; @@ -2864,46 +1869,46 @@ static int qcom_param_page_type_exec(struct nand_chip *chip, const struct nand_ if (ret) return ret; - q_op.cmd_reg |= PAGE_ACC | LAST_PAGE; + q_op.cmd_reg |= cpu_to_le32(PAGE_ACC | LAST_PAGE); nandc->buf_count = 0; nandc->buf_start = 0; host->use_ecc = false; - clear_read_regs(nandc); - clear_bam_transaction(nandc); + qcom_clear_read_regs(nandc); + qcom_clear_bam_transaction(nandc); - nandc_set_reg(chip, NAND_FLASH_CMD, q_op.cmd_reg); + nandc->regs->cmd = q_op.cmd_reg; + nandc->regs->addr0 = 0; + nandc->regs->addr1 = 0; - nandc_set_reg(chip, NAND_ADDR0, 0); - nandc_set_reg(chip, NAND_ADDR1, 0); - nandc_set_reg(chip, NAND_DEV0_CFG0, 0 << CW_PER_PAGE - | 512 << UD_SIZE_BYTES - | 5 << NUM_ADDR_CYCLES - | 0 << SPARE_SIZE_BYTES); - nandc_set_reg(chip, NAND_DEV0_CFG1, 7 << NAND_RECOVERY_CYCLES - | 0 << CS_ACTIVE_BSY - | 17 << BAD_BLOCK_BYTE_NUM - | 1 << BAD_BLOCK_IN_SPARE_AREA - | 2 << WR_RD_BSY_GAP - | 0 << WIDE_FLASH - | 1 << DEV0_CFG1_ECC_DISABLE); - if (!nandc->props->qpic_v2) - nandc_set_reg(chip, NAND_EBI2_ECC_BUF_CFG, 1 << ECC_CFG_ECC_DISABLE); + host->cfg0 = FIELD_PREP(CW_PER_PAGE_MASK, 0) | + FIELD_PREP(UD_SIZE_BYTES_MASK, 512) | + FIELD_PREP(NUM_ADDR_CYCLES_MASK, 5) | + FIELD_PREP(SPARE_SIZE_BYTES_MASK, 0); + + host->cfg1 = FIELD_PREP(NAND_RECOVERY_CYCLES_MASK, 7) | + FIELD_PREP(BAD_BLOCK_BYTE_NUM_MASK, 17) | + FIELD_PREP(CS_ACTIVE_BSY, 0) | + FIELD_PREP(BAD_BLOCK_IN_SPARE_AREA, 1) | + FIELD_PREP(WR_RD_BSY_GAP_MASK, 2) | + FIELD_PREP(WIDE_FLASH, 0) | + FIELD_PREP(DEV0_CFG1_ECC_DISABLE, 1); + + if (!nandc->props->qpic_version2) + nandc->regs->ecc_buf_cfg = cpu_to_le32(ECC_CFG_ECC_DISABLE); /* configure CMD1 and VLD for ONFI param probing in QPIC v1 */ - if (!nandc->props->qpic_v2) { - nandc_set_reg(chip, NAND_DEV_CMD_VLD, - (nandc->vld & ~READ_START_VLD)); - nandc_set_reg(chip, NAND_DEV_CMD1, - (nandc->cmd1 & ~(0xFF << READ_ADDR)) - | NAND_CMD_PARAM << READ_ADDR); + if (!nandc->props->qpic_version2) { + nandc->regs->vld = cpu_to_le32((nandc->vld & ~READ_START_VLD)); + nandc->regs->cmd1 = cpu_to_le32((nandc->cmd1 & ~(0xFF << READ_ADDR)) + | NAND_CMD_PARAM << READ_ADDR); } - nandc_set_reg(chip, NAND_EXEC_CMD, 1); + nandc->regs->exec = cpu_to_le32(1); - if (!nandc->props->qpic_v2) { - nandc_set_reg(chip, NAND_DEV_CMD1_RESTORE, nandc->cmd1); - nandc_set_reg(chip, NAND_DEV_CMD_VLD_RESTORE, nandc->vld); + if (!nandc->props->qpic_version2) { + nandc->regs->orig_cmd1 = cpu_to_le32(nandc->cmd1); + nandc->regs->orig_vld = cpu_to_le32(nandc->vld); } instr = q_op.data_instr; @@ -2912,9 +1917,9 @@ static int qcom_param_page_type_exec(struct nand_chip *chip, const struct nand_ nandc_set_read_loc(chip, 0, 0, 0, len, 1); - if (!nandc->props->qpic_v2) { - write_reg_dma(nandc, NAND_DEV_CMD_VLD, 1, 0); - write_reg_dma(nandc, NAND_DEV_CMD1, 1, NAND_BAM_NEXT_SGL); + if (!nandc->props->qpic_version2) { + qcom_write_reg_dma(nandc, &nandc->regs->vld, NAND_DEV_CMD_VLD, 1, 0); + qcom_write_reg_dma(nandc, &nandc->regs->cmd1, NAND_DEV_CMD1, 1, NAND_BAM_NEXT_SGL); } nandc->buf_count = len; @@ -2922,16 +1927,17 @@ static int qcom_param_page_type_exec(struct nand_chip *chip, const struct nand_ config_nand_single_cw_page_read(chip, false, 0); - read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer, - nandc->buf_count, 0); + qcom_read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer, + nandc->buf_count, 0); /* restore CMD1 and VLD regs */ - if (!nandc->props->qpic_v2) { - write_reg_dma(nandc, NAND_DEV_CMD1_RESTORE, 1, 0); - write_reg_dma(nandc, NAND_DEV_CMD_VLD_RESTORE, 1, NAND_BAM_NEXT_SGL); + if (!nandc->props->qpic_version2) { + qcom_write_reg_dma(nandc, &nandc->regs->orig_cmd1, NAND_DEV_CMD1_RESTORE, 1, 0); + qcom_write_reg_dma(nandc, &nandc->regs->orig_vld, NAND_DEV_CMD_VLD_RESTORE, 1, + NAND_BAM_NEXT_SGL); } - ret = submit_descs(nandc); + ret = qcom_submit_descs(nandc); if (ret) { dev_err(nandc->dev, "failure in submitting param page descriptor\n"); goto err_out; @@ -3015,151 +2021,24 @@ static const struct nand_controller_ops qcom_nandc_ops = { .exec_op = qcom_nand_exec_op, }; -static void qcom_nandc_unalloc(struct qcom_nand_controller *nandc) -{ - if (nandc->props->is_bam) { - if (!dma_mapping_error(nandc->dev, nandc->reg_read_dma)) - dma_unmap_single(nandc->dev, nandc->reg_read_dma, - MAX_REG_RD * - sizeof(*nandc->reg_read_buf), - DMA_FROM_DEVICE); - - if (nandc->tx_chan) - dma_release_channel(nandc->tx_chan); - - if (nandc->rx_chan) - dma_release_channel(nandc->rx_chan); - - if (nandc->cmd_chan) - dma_release_channel(nandc->cmd_chan); - } else { - if (nandc->chan) - dma_release_channel(nandc->chan); - } -} - -static int qcom_nandc_alloc(struct qcom_nand_controller *nandc) -{ - int ret; - - ret = dma_set_coherent_mask(nandc->dev, DMA_BIT_MASK(32)); - if (ret) { - dev_err(nandc->dev, "failed to set DMA mask\n"); - return ret; - } - - /* - * we use the internal buffer for reading ONFI params, reading small - * data like ID and status, and preforming read-copy-write operations - * when writing to a codeword partially. 532 is the maximum possible - * size of a codeword for our nand controller - */ - nandc->buf_size = 532; - - nandc->data_buffer = devm_kzalloc(nandc->dev, nandc->buf_size, GFP_KERNEL); - if (!nandc->data_buffer) - return -ENOMEM; - - nandc->regs = devm_kzalloc(nandc->dev, sizeof(*nandc->regs), GFP_KERNEL); - if (!nandc->regs) - return -ENOMEM; - - nandc->reg_read_buf = devm_kcalloc(nandc->dev, MAX_REG_RD, - sizeof(*nandc->reg_read_buf), - GFP_KERNEL); - if (!nandc->reg_read_buf) - return -ENOMEM; - - if (nandc->props->is_bam) { - nandc->reg_read_dma = - dma_map_single(nandc->dev, nandc->reg_read_buf, - MAX_REG_RD * - sizeof(*nandc->reg_read_buf), - DMA_FROM_DEVICE); - if (dma_mapping_error(nandc->dev, nandc->reg_read_dma)) { - dev_err(nandc->dev, "failed to DMA MAP reg buffer\n"); - return -EIO; - } - - nandc->tx_chan = dma_request_chan(nandc->dev, "tx"); - if (IS_ERR(nandc->tx_chan)) { - ret = PTR_ERR(nandc->tx_chan); - nandc->tx_chan = NULL; - dev_err_probe(nandc->dev, ret, - "tx DMA channel request failed\n"); - goto unalloc; - } - - nandc->rx_chan = dma_request_chan(nandc->dev, "rx"); - if (IS_ERR(nandc->rx_chan)) { - ret = PTR_ERR(nandc->rx_chan); - nandc->rx_chan = NULL; - dev_err_probe(nandc->dev, ret, - "rx DMA channel request failed\n"); - goto unalloc; - } - - nandc->cmd_chan = dma_request_chan(nandc->dev, "cmd"); - if (IS_ERR(nandc->cmd_chan)) { - ret = PTR_ERR(nandc->cmd_chan); - nandc->cmd_chan = NULL; - dev_err_probe(nandc->dev, ret, - "cmd DMA channel request failed\n"); - goto unalloc; - } - - /* - * Initially allocate BAM transaction to read ONFI param page. - * After detecting all the devices, this BAM transaction will - * be freed and the next BAM transaction will be allocated with - * maximum codeword size - */ - nandc->max_cwperpage = 1; - nandc->bam_txn = alloc_bam_transaction(nandc); - if (!nandc->bam_txn) { - dev_err(nandc->dev, - "failed to allocate bam transaction\n"); - ret = -ENOMEM; - goto unalloc; - } - } else { - nandc->chan = dma_request_chan(nandc->dev, "rxtx"); - if (IS_ERR(nandc->chan)) { - ret = PTR_ERR(nandc->chan); - nandc->chan = NULL; - dev_err_probe(nandc->dev, ret, - "rxtx DMA channel request failed\n"); - return ret; - } - } - - INIT_LIST_HEAD(&nandc->desc_list); - INIT_LIST_HEAD(&nandc->host_list); - - nand_controller_init(&nandc->controller); - nandc->controller.ops = &qcom_nandc_ops; - - return 0; -unalloc: - qcom_nandc_unalloc(nandc); - return ret; -} - /* one time setup of a few nand controller registers */ static int qcom_nandc_setup(struct qcom_nand_controller *nandc) { u32 nand_ctrl; + nand_controller_init(nandc->controller); + nandc->controller->ops = &qcom_nandc_ops; + /* kill onenand */ - if (!nandc->props->is_qpic) + if (!nandc->props->nandc_part_of_qpic) nandc_write(nandc, SFLASHC_BURST_CFG, 0); - if (!nandc->props->qpic_v2) + if (!nandc->props->qpic_version2) nandc_write(nandc, dev_cmd_reg_addr(nandc, NAND_DEV_CMD_VLD), NAND_DEV_CMD_VLD_VAL); /* enable ADM or BAM DMA */ - if (nandc->props->is_bam) { + if (nandc->props->supports_bam) { nand_ctrl = nandc_read(nandc, NAND_CTRL); /* @@ -3176,7 +2055,7 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc) } /* save the original values of these registers */ - if (!nandc->props->qpic_v2) { + if (!nandc->props->qpic_version2) { nandc->cmd1 = nandc_read(nandc, dev_cmd_reg_addr(nandc, NAND_DEV_CMD1)); nandc->vld = NAND_DEV_CMD_VLD_VAL; } @@ -3288,7 +2167,7 @@ static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc, chip->legacy.block_bad = qcom_nandc_block_bad; chip->legacy.block_markbad = qcom_nandc_block_markbad; - chip->controller = &nandc->controller; + chip->controller = nandc->controller; chip->options |= NAND_NO_SUBPAGE_WRITE | NAND_USES_DMA | NAND_SKIP_BBTSCAN; @@ -3349,7 +2228,7 @@ static int qcom_nandc_parse_dt(struct platform_device *pdev) struct device_node *np = nandc->dev->of_node; int ret; - if (!nandc->props->is_bam) { + if (!nandc->props->supports_bam) { ret = of_property_read_u32(np, "qcom,cmd-crci", &nandc->cmd_crci); if (ret) { @@ -3371,17 +2250,21 @@ static int qcom_nandc_parse_dt(struct platform_device *pdev) static int qcom_nandc_probe(struct platform_device *pdev) { struct qcom_nand_controller *nandc; + struct nand_controller *controller; const void *dev_data; struct device *dev = &pdev->dev; struct resource *res; int ret; - nandc = devm_kzalloc(&pdev->dev, sizeof(*nandc), GFP_KERNEL); + nandc = devm_kzalloc(&pdev->dev, sizeof(*nandc) + sizeof(*controller), + GFP_KERNEL); if (!nandc) return -ENOMEM; + controller = (struct nand_controller *)&nandc[1]; platform_set_drvdata(pdev, nandc); nandc->dev = dev; + nandc->controller = controller; dev_data = of_device_get_match_data(dev); if (!dev_data) { @@ -3474,30 +2357,30 @@ static void qcom_nandc_remove(struct platform_device *pdev) static const struct qcom_nandc_props ipq806x_nandc_props = { .ecc_modes = (ECC_RS_4BIT | ECC_BCH_8BIT), - .is_bam = false, + .supports_bam = false, .use_codeword_fixup = true, .dev_cmd_reg_start = 0x0, }; static const struct qcom_nandc_props ipq4019_nandc_props = { .ecc_modes = (ECC_BCH_4BIT | ECC_BCH_8BIT), - .is_bam = true, - .is_qpic = true, + .supports_bam = true, + .nandc_part_of_qpic = true, .dev_cmd_reg_start = 0x0, }; static const struct qcom_nandc_props ipq8074_nandc_props = { .ecc_modes = (ECC_BCH_4BIT | ECC_BCH_8BIT), - .is_bam = true, - .is_qpic = true, + .supports_bam = true, + .nandc_part_of_qpic = true, .dev_cmd_reg_start = 0x7000, }; static const struct qcom_nandc_props sdx55_nandc_props = { .ecc_modes = (ECC_BCH_4BIT | ECC_BCH_8BIT), - .is_bam = true, - .is_qpic = true, - .qpic_v2 = true, + .supports_bam = true, + .nandc_part_of_qpic = true, + .qpic_version2 = true, .dev_cmd_reg_start = 0x7000, }; diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile index 19cc77288ebb..1e61ab21893a 100644 --- a/drivers/mtd/nand/spi/Makefile +++ b/drivers/mtd/nand/spi/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 spinand-objs := core.o alliancememory.o ato.o esmt.o foresee.o gigadevice.o macronix.o -spinand-objs += micron.o paragon.o toshiba.o winbond.o xtx.o +spinand-objs += micron.o paragon.o skyhigh.o toshiba.o winbond.o xtx.o obj-$(CONFIG_MTD_SPI_NAND) += spinand.o diff --git a/drivers/mtd/nand/spi/alliancememory.c b/drivers/mtd/nand/spi/alliancememory.c index 7936ea546b03..6046c73f8424 100644 --- a/drivers/mtd/nand/spi/alliancememory.c +++ b/drivers/mtd/nand/spi/alliancememory.c @@ -21,8 +21,8 @@ static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), diff --git a/drivers/mtd/nand/spi/ato.c b/drivers/mtd/nand/spi/ato.c index 82b377c06812..bb5298911137 100644 --- a/drivers/mtd/nand/spi/ato.c +++ b/drivers/mtd/nand/spi/ato.c @@ -15,8 +15,8 @@ static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index b1df7f627161..da4713692674 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -294,6 +294,9 @@ static int spinand_ondie_ecc_prepare_io_req(struct nand_device *nand, struct spinand_device *spinand = nand_to_spinand(nand); bool enable = (req->mode != MTD_OPS_RAW); + if (!enable && spinand->flags & SPINAND_NO_RAW_ACCESS) + return -EOPNOTSUPP; + memset(spinand->oobbuf, 0xff, nanddev_per_page_oobsize(nand)); /* Only enable or disable the engine */ @@ -901,9 +904,17 @@ static bool spinand_isbad(struct nand_device *nand, const struct nand_pos *pos) .oobbuf.in = marker, .mode = MTD_OPS_RAW, }; + int ret; spinand_select_target(spinand, pos->target); - spinand_read_page(spinand, &req); + + ret = spinand_read_page(spinand, &req); + if (ret == -EOPNOTSUPP) { + /* Retry with ECC in case raw access is not supported */ + req.mode = MTD_OPS_PLACE_OOB; + spinand_read_page(spinand, &req); + } + if (marker[0] != 0xff || marker[1] != 0xff) return true; @@ -942,11 +953,14 @@ static int spinand_markbad(struct nand_device *nand, const struct nand_pos *pos) if (ret) return ret; - ret = spinand_write_enable_op(spinand); - if (ret) - return ret; + ret = spinand_write_page(spinand, &req); + if (ret == -EOPNOTSUPP) { + /* Retry with ECC in case raw access is not supported */ + req.mode = MTD_OPS_PLACE_OOB; + ret = spinand_write_page(spinand, &req); + } - return spinand_write_page(spinand, &req); + return ret; } static int spinand_mtd_block_markbad(struct mtd_info *mtd, loff_t offs) @@ -1117,6 +1131,7 @@ static const struct spinand_manufacturer *spinand_manufacturers[] = { ¯onix_spinand_manufacturer, µn_spinand_manufacturer, ¶gon_spinand_manufacturer, + &skyhigh_spinand_manufacturer, &toshiba_spinand_manufacturer, &winbond_spinand_manufacturer, &xtx_spinand_manufacturer, @@ -1198,10 +1213,13 @@ spinand_select_op_variant(struct spinand_device *spinand, const struct spinand_op_variants *variants) { struct nand_device *nand = spinand_to_nand(spinand); + const struct spi_mem_op *best_variant = NULL; + u64 best_op_duration_ns = ULLONG_MAX; unsigned int i; for (i = 0; i < variants->nops; i++) { struct spi_mem_op op = variants->ops[i]; + u64 op_duration_ns = 0; unsigned int nbytes; int ret; @@ -1214,17 +1232,23 @@ spinand_select_op_variant(struct spinand_device *spinand, if (ret) break; + spi_mem_adjust_op_freq(spinand->spimem, &op); + if (!spi_mem_supports_op(spinand->spimem, &op)) break; nbytes -= op.data.nbytes; + + op_duration_ns += spi_mem_calc_op_duration(&op); } - if (!nbytes) - return &variants->ops[i]; + if (!nbytes && op_duration_ns < best_op_duration_ns) { + best_op_duration_ns = op_duration_ns; + best_variant = &variants->ops[i]; + } } - return NULL; + return best_variant; } /** diff --git a/drivers/mtd/nand/spi/esmt.c b/drivers/mtd/nand/spi/esmt.c index 4597a82de23a..323a20901fc9 100644 --- a/drivers/mtd/nand/spi/esmt.c +++ b/drivers/mtd/nand/spi/esmt.c @@ -15,8 +15,8 @@ static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), diff --git a/drivers/mtd/nand/spi/foresee.c b/drivers/mtd/nand/spi/foresee.c index e0d2d9257045..ecd5f6bffa33 100644 --- a/drivers/mtd/nand/spi/foresee.c +++ b/drivers/mtd/nand/spi/foresee.c @@ -14,8 +14,8 @@ static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), @@ -81,6 +81,16 @@ static const struct spinand_info foresee_spinand_table[] = { SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&f35sqa002g_ooblayout, f35sqa002g_ecc_get_status)), + SPINAND_INFO("F35SQA001G", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x71, 0x71), + NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), + NAND_ECCREQ(1, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&f35sqa002g_ooblayout, + f35sqa002g_ecc_get_status)), }; static const struct spinand_manufacturer_ops foresee_spinand_manuf_ops = { diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c index 6023cba748bb..d620bb02a20a 100644 --- a/drivers/mtd/nand/spi/gigadevice.c +++ b/drivers/mtd/nand/spi/gigadevice.c @@ -28,32 +28,32 @@ static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(read_cache_variants_f, SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X4_OP_3A(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP_3A(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP_3A(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP_3A(false, 0, 0, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP_3A(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP_3A(0, 0, NULL, 0)); static SPINAND_OP_VARIANTS(read_cache_variants_1gq5, SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(read_cache_variants_2gq5, SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 4, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 2, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c index d277c3220fdc..3dc4d63d6832 100644 --- a/drivers/mtd/nand/spi/macronix.c +++ b/drivers/mtd/nand/spi/macronix.c @@ -28,8 +28,8 @@ struct macronix_priv { static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), diff --git a/drivers/mtd/nand/spi/micron.c b/drivers/mtd/nand/spi/micron.c index 12601bc4227a..ad0bb9755a09 100644 --- a/drivers/mtd/nand/spi/micron.c +++ b/drivers/mtd/nand/spi/micron.c @@ -33,8 +33,8 @@ static SPINAND_OP_VARIANTS(quadio_read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(x4_write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), @@ -48,8 +48,8 @@ static SPINAND_OP_VARIANTS(x4_update_cache_variants, static SPINAND_OP_VARIANTS(x4_read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(x1_write_cache_variants, SPINAND_PROG_LOAD(true, 0, NULL, 0)); diff --git a/drivers/mtd/nand/spi/paragon.c b/drivers/mtd/nand/spi/paragon.c index 519ade513c1f..6e7cc6995380 100644 --- a/drivers/mtd/nand/spi/paragon.c +++ b/drivers/mtd/nand/spi/paragon.c @@ -26,8 +26,8 @@ static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), diff --git a/drivers/mtd/nand/spi/skyhigh.c b/drivers/mtd/nand/spi/skyhigh.c new file mode 100644 index 000000000000..961df0d74984 --- /dev/null +++ b/drivers/mtd/nand/spi/skyhigh.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024 SkyHigh Memory Limited + * + * Author: Takahiro Kuwano + * Co-Author: KR Kim + */ + +#include +#include +#include + +#define SPINAND_MFR_SKYHIGH 0x01 +#define SKYHIGH_STATUS_ECC_1TO2_BITFLIPS (1 << 4) +#define SKYHIGH_STATUS_ECC_3TO6_BITFLIPS (2 << 4) +#define SKYHIGH_STATUS_ECC_UNCOR_ERROR (3 << 4) +#define SKYHIGH_CONFIG_PROTECT_EN BIT(1) + +static SPINAND_OP_VARIANTS(read_cache_variants, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 4, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); + +static SPINAND_OP_VARIANTS(write_cache_variants, + SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), + SPINAND_PROG_LOAD(true, 0, NULL, 0)); + +static SPINAND_OP_VARIANTS(update_cache_variants, + SPINAND_PROG_LOAD_X4(false, 0, NULL, 0), + SPINAND_PROG_LOAD(false, 0, NULL, 0)); + +static int skyhigh_spinand_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + /* ECC bytes are stored in hidden area. */ + return -ERANGE; +} + +static int skyhigh_spinand_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section) + return -ERANGE; + + /* ECC bytes are stored in hidden area. Reserve 2 bytes for the BBM. */ + region->offset = 2; + region->length = mtd->oobsize - 2; + + return 0; +} + +static const struct mtd_ooblayout_ops skyhigh_spinand_ooblayout = { + .ecc = skyhigh_spinand_ooblayout_ecc, + .free = skyhigh_spinand_ooblayout_free, +}; + +static int skyhigh_spinand_ecc_get_status(struct spinand_device *spinand, + u8 status) +{ + switch (status & STATUS_ECC_MASK) { + case STATUS_ECC_NO_BITFLIPS: + return 0; + + case SKYHIGH_STATUS_ECC_UNCOR_ERROR: + return -EBADMSG; + + case SKYHIGH_STATUS_ECC_1TO2_BITFLIPS: + return 2; + + case SKYHIGH_STATUS_ECC_3TO6_BITFLIPS: + return 6; + + default: + break; + } + + return -EINVAL; +} + +static const struct spinand_info skyhigh_spinand_table[] = { + SPINAND_INFO("S35ML01G301", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x15), + NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), + NAND_ECCREQ(6, 32), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_NO_RAW_ACCESS, + SPINAND_ECCINFO(&skyhigh_spinand_ooblayout, + skyhigh_spinand_ecc_get_status)), + SPINAND_INFO("S35ML01G300", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x14), + NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1), + NAND_ECCREQ(6, 32), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_NO_RAW_ACCESS, + SPINAND_ECCINFO(&skyhigh_spinand_ooblayout, + skyhigh_spinand_ecc_get_status)), + SPINAND_INFO("S35ML02G300", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x25), + NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 2, 1, 1), + NAND_ECCREQ(6, 32), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_NO_RAW_ACCESS, + SPINAND_ECCINFO(&skyhigh_spinand_ooblayout, + skyhigh_spinand_ecc_get_status)), + SPINAND_INFO("S35ML04G300", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x35), + NAND_MEMORG(1, 2048, 128, 64, 4096, 80, 2, 1, 1), + NAND_ECCREQ(6, 32), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_NO_RAW_ACCESS, + SPINAND_ECCINFO(&skyhigh_spinand_ooblayout, + skyhigh_spinand_ecc_get_status)), +}; + +static int skyhigh_spinand_init(struct spinand_device *spinand) +{ + /* + * Config_Protect_En (bit 1 in Block Lock register) must be set to 1 + * before writing other bits. Do it here before core unlocks all blocks + * by writing block protection bits. + */ + return spinand_write_reg_op(spinand, REG_BLOCK_LOCK, + SKYHIGH_CONFIG_PROTECT_EN); +} + +static const struct spinand_manufacturer_ops skyhigh_spinand_manuf_ops = { + .init = skyhigh_spinand_init, +}; + +const struct spinand_manufacturer skyhigh_spinand_manufacturer = { + .id = SPINAND_MFR_SKYHIGH, + .name = "SkyHigh", + .chips = skyhigh_spinand_table, + .nchips = ARRAY_SIZE(skyhigh_spinand_table), + .ops = &skyhigh_spinand_manuf_ops, +}; diff --git a/drivers/mtd/nand/spi/toshiba.c b/drivers/mtd/nand/spi/toshiba.c index bbbcaa87c0bc..2e2106b2705f 100644 --- a/drivers/mtd/nand/spi/toshiba.c +++ b/drivers/mtd/nand/spi/toshiba.c @@ -17,8 +17,8 @@ static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_x4_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index 7180e615ac97..8394a1b1fb0c 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -10,6 +10,7 @@ #include #include #include +#include #define SPINAND_MFR_WINBOND 0xEF @@ -17,13 +18,31 @@ #define W25N04KV_STATUS_ECC_5_8_BITFLIPS (3 << 4) +/* + * "X2" in the core is equivalent to "dual output" in the datasheets, + * "X4" in the core is equivalent to "quad output" in the datasheets. + */ + +static SPINAND_OP_VARIANTS(read_cache_dtr_variants, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_DTR_OP(0, 8, NULL, 0, 80 * HZ_PER_MHZ), + SPINAND_PAGE_READ_FROM_CACHE_X4_DTR_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ), + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_DTR_OP(0, 4, NULL, 0, 80 * HZ_PER_MHZ), + SPINAND_PAGE_READ_FROM_CACHE_X2_DTR_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DTR_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ), + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0, 54 * HZ_PER_MHZ)); + static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), @@ -194,7 +213,7 @@ static const struct spinand_info winbond_spinand_table[] = { SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xbc, 0x21), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), NAND_ECCREQ(1, 512), - SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + SPINAND_INFO_OP_VARIANTS(&read_cache_dtr_variants, &write_cache_variants, &update_cache_variants), 0, @@ -223,7 +242,7 @@ static const struct spinand_info winbond_spinand_table[] = { SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xbf, 0x22), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 2, 1), NAND_ECCREQ(1, 512), - SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + SPINAND_INFO_OP_VARIANTS(&read_cache_dtr_variants, &write_cache_variants, &update_cache_variants), 0, diff --git a/drivers/mtd/nand/spi/xtx.c b/drivers/mtd/nand/spi/xtx.c index 66a4255bdf06..3f539ca0de86 100644 --- a/drivers/mtd/nand/spi/xtx.c +++ b/drivers/mtd/nand/spi/xtx.c @@ -27,8 +27,8 @@ static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), - SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), diff --git a/drivers/mtd/spi-nor/atmel.c b/drivers/mtd/spi-nor/atmel.c index 45d1153a04a0..82c592f0a1e1 100644 --- a/drivers/mtd/spi-nor/atmel.c +++ b/drivers/mtd/spi-nor/atmel.c @@ -238,6 +238,10 @@ static const struct flash_info atmel_nor_parts[] = { .flags = SPI_NOR_HAS_LOCK, .no_sfdp_flags = SECT_4K, .fixups = &at25fs_nor_fixups + }, { + .id = SNOR_ID(0x1f, 0x87, 0x01), + .size = SZ_4M, + .no_sfdp_flags = SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ, }, }; diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index 66949d9f0cc5..19eb98bd6821 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -89,7 +90,7 @@ void spi_nor_spimem_setup_op(const struct spi_nor *nor, op->addr.buswidth = spi_nor_get_protocol_addr_nbits(proto); if (op->dummy.nbytes) - op->dummy.buswidth = spi_nor_get_protocol_data_nbits(proto); + op->dummy.buswidth = spi_nor_get_protocol_addr_nbits(proto); if (op->data.nbytes) op->data.buswidth = spi_nor_get_protocol_data_nbits(proto); @@ -3576,7 +3577,8 @@ static int spi_nor_create_write_dirmap(struct spi_nor *nor) static int spi_nor_probe(struct spi_mem *spimem) { struct spi_device *spi = spimem->spi; - struct flash_platform_data *data = dev_get_platdata(&spi->dev); + struct device *dev = &spi->dev; + struct flash_platform_data *data = dev_get_platdata(dev); struct spi_nor *nor; /* * Enable all caps by default. The core will mask them after @@ -3586,13 +3588,17 @@ static int spi_nor_probe(struct spi_mem *spimem) char *flash_name; int ret; - nor = devm_kzalloc(&spi->dev, sizeof(*nor), GFP_KERNEL); + ret = devm_regulator_get_enable(dev, "vcc"); + if (ret) + return ret; + + nor = devm_kzalloc(dev, sizeof(*nor), GFP_KERNEL); if (!nor) return -ENOMEM; nor->spimem = spimem; - nor->dev = &spi->dev; - spi_nor_set_flash_node(nor, spi->dev.of_node); + nor->dev = dev; + spi_nor_set_flash_node(nor, dev->of_node); spi_mem_set_drvdata(spimem, nor); @@ -3628,9 +3634,8 @@ static int spi_nor_probe(struct spi_mem *spimem) */ if (nor->params->page_size > PAGE_SIZE) { nor->bouncebuf_size = nor->params->page_size; - devm_kfree(nor->dev, nor->bouncebuf); - nor->bouncebuf = devm_kmalloc(nor->dev, - nor->bouncebuf_size, + devm_kfree(dev, nor->bouncebuf); + nor->bouncebuf = devm_kmalloc(dev, nor->bouncebuf_size, GFP_KERNEL); if (!nor->bouncebuf) return -ENOMEM; diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h index 5c33740ed7f5..ceff412f7d65 100644 --- a/drivers/mtd/spi-nor/core.h +++ b/drivers/mtd/spi-nor/core.h @@ -448,7 +448,11 @@ struct spi_nor_id { * @id: pointer to struct spi_nor_id or NULL, which means "no ID" (mostly * older chips). * @name: (obsolete) the name of the flash. Do not set it for new additions. - * @size: the size of the flash in bytes. + * @size: the size of the flash in bytes. The flash size is one + * property parsed by the SFDP. We use it as an indicator + * whether we need SFDP parsing for a particular flash. + * I.e. non-legacy flash entries in flash_info will have + * a size of zero iff SFDP should be used. * @sector_size: (optional) the size listed here is what works with * SPINOR_OP_SE, which isn't necessarily called a "sector" by * the vendor. Defaults to 64k. diff --git a/drivers/mtd/spi-nor/macronix.c b/drivers/mtd/spi-nor/macronix.c index 830da21eea08..99936fd25d43 100644 --- a/drivers/mtd/spi-nor/macronix.c +++ b/drivers/mtd/spi-nor/macronix.c @@ -142,12 +142,6 @@ static const struct flash_info macronix_nor_parts[] = { .name = "mx25u12835f", .size = SZ_16M, .no_sfdp_flags = SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ, - }, { - .id = SNOR_ID(0xc2, 0x25, 0x39), - .name = "mx25u25635f", - .size = SZ_32M, - .no_sfdp_flags = SECT_4K, - .fixup_flags = SPI_NOR_4B_OPCODES, }, { .id = SNOR_ID(0xc2, 0x25, 0x3a), .name = "mx25u51245g", @@ -230,7 +224,8 @@ static int macronix_nor_octal_dtr_en(struct spi_nor *nor) return ret; /* Read flash ID to make sure the switch was successful. */ - ret = spi_nor_read_id(nor, 4, 4, buf, SNOR_PROTO_8_8_8_DTR); + ret = spi_nor_read_id(nor, nor->addr_nbytes, 4, buf, + SNOR_PROTO_8_8_8_DTR); if (ret) { dev_dbg(nor->dev, "error %d reading JEDEC ID after enabling 8D-8D-8D mode\n", ret); return ret; diff --git a/drivers/mtd/spi-nor/spansion.c b/drivers/mtd/spi-nor/spansion.c index 5a88a6096ca8..bf08dbf5e742 100644 --- a/drivers/mtd/spi-nor/spansion.c +++ b/drivers/mtd/spi-nor/spansion.c @@ -957,6 +957,11 @@ static const struct flash_info spansion_nor_parts[] = { .name = "s25hs02gt", .mfr_flags = USE_CLPEF, .fixups = &s25hx_t_fixups + }, { + /* S28HL256T */ + .id = SNOR_ID(0x34, 0x5a, 0x19), + .mfr_flags = USE_CLPEF, + .fixups = &s28hx_t_fixups, }, { .id = SNOR_ID(0x34, 0x5a, 0x1a), .name = "s28hl512t", @@ -967,6 +972,11 @@ static const struct flash_info spansion_nor_parts[] = { .name = "s28hl01gt", .mfr_flags = USE_CLPEF, .fixups = &s28hx_t_fixups, + }, { + /* S28HL02GT */ + .id = SNOR_ID(0x34, 0x5a, 0x1c), + .mfr_flags = USE_CLPEF, + .fixups = &s28hx_t_fixups, }, { .id = SNOR_ID(0x34, 0x5b, 0x19), .mfr_flags = USE_CLPEF, diff --git a/drivers/mtd/spi-nor/sysfs.c b/drivers/mtd/spi-nor/sysfs.c index 5e9eb268073d..4f12ff755df0 100644 --- a/drivers/mtd/spi-nor/sysfs.c +++ b/drivers/mtd/spi-nor/sysfs.c @@ -50,7 +50,7 @@ static struct attribute *spi_nor_sysfs_entries[] = { }; static ssize_t sfdp_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct spi_device *spi = to_spi_device(kobj_to_dev(kobj)); @@ -62,9 +62,9 @@ static ssize_t sfdp_read(struct file *filp, struct kobject *kobj, return memory_read_from_buffer(buf, count, &off, nor->sfdp->dwords, sfdp_size); } -static BIN_ATTR_RO(sfdp, 0); +static const BIN_ATTR_RO(sfdp, 0); -static struct bin_attribute *spi_nor_sysfs_bin_entries[] = { +static const struct bin_attribute *const spi_nor_sysfs_bin_entries[] = { &bin_attr_sfdp, NULL }; @@ -104,7 +104,7 @@ static const struct attribute_group spi_nor_sysfs_group = { .is_visible = spi_nor_sysfs_is_visible, .is_bin_visible = spi_nor_sysfs_is_bin_visible, .attrs = spi_nor_sysfs_entries, - .bin_attrs = spi_nor_sysfs_bin_entries, + .bin_attrs_new = spi_nor_sysfs_bin_entries, }; const struct attribute_group *spi_nor_sysfs_groups[] = { diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 60d0155be869..2836905f0152 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -383,7 +383,7 @@ int ubiblock_create(struct ubi_volume_info *vi) dev->tag_set.ops = &ubiblock_mq_ops; dev->tag_set.queue_depth = 64; dev->tag_set.numa_node = NUMA_NO_NODE; - dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; + dev->tag_set.flags = BLK_MQ_F_BLOCKING; dev->tag_set.cmd_size = sizeof(struct ubiblock_pdu); dev->tag_set.driver_data = dev; dev->tag_set.nr_hw_queues = 1; diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 30be4ed68fad..ef6a22f372f9 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -1537,7 +1537,7 @@ static int ubi_mtd_param_parse(const char *val, const struct kernel_param *kp) if (token) { int err = kstrtoint(token, 10, &p->ubi_num); - if (err) { + if (err || p->ubi_num < UBI_DEV_NUM_AUTO) { pr_err("UBI error: bad value for ubi_num parameter: %s\n", token); return -EINVAL; diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index 6bb80d7714bc..b700a0efaa93 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -828,6 +828,70 @@ out_free: return err; } +static int ubi_get_ec_info(struct ubi_device *ubi, struct ubi_ecinfo_req __user *ureq) +{ + struct ubi_ecinfo_req req; + struct ubi_wl_entry *wl; + int read_cnt; + int peb; + int end_peb; + + /* Copy the input arguments */ + if (copy_from_user(&req, ureq, sizeof(struct ubi_ecinfo_req))) + return -EFAULT; + + /* Check input arguments */ + if (req.length <= 0 || req.start < 0 || req.start >= ubi->peb_count) + return -EINVAL; + + if (check_add_overflow(req.start, req.length, &end_peb)) + return -EINVAL; + + if (end_peb > ubi->peb_count) + end_peb = ubi->peb_count; + + /* Check access rights before filling erase_counters array */ + if (!access_ok((void __user *)ureq->erase_counters, + (end_peb-req.start) * sizeof(int32_t))) + return -EFAULT; + + /* Fill erase counter array */ + read_cnt = 0; + for (peb = req.start; peb < end_peb; read_cnt++, peb++) { + int ec; + + if (ubi_io_is_bad(ubi, peb)) { + if (__put_user(UBI_UNKNOWN, ureq->erase_counters+read_cnt)) + return -EFAULT; + + continue; + } + + spin_lock(&ubi->wl_lock); + + wl = ubi->lookuptbl[peb]; + if (wl) + ec = wl->ec; + else + ec = UBI_UNKNOWN; + + spin_unlock(&ubi->wl_lock); + + if (__put_user(ec, ureq->erase_counters+read_cnt)) + return -EFAULT; + + } + + /* Return actual read length */ + req.read_length = read_cnt; + + /* Copy everything except erase counter array */ + if (copy_to_user(ureq, &req, sizeof(struct ubi_ecinfo_req))) + return -EFAULT; + + return 0; +} + static long ubi_cdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -991,6 +1055,12 @@ static long ubi_cdev_ioctl(struct file *file, unsigned int cmd, break; } + case UBI_IOCECNFO: + { + err = ubi_get_ec_info(ubi, argp); + break; + } + default: err = -ENOTTY; break; diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index 26cc53ad34ec..c792b9bcab9b 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -549,7 +549,6 @@ struct ubi_debug_info { * @peb_buf: a buffer of PEB size used for different purposes * @buf_mutex: protects @peb_buf * @ckvol_mutex: serializes static volume checking when opening - * @wl_reboot_notifier: close all wear-leveling work before reboot * * @dbg: debugging information for this UBI device */ @@ -652,7 +651,6 @@ struct ubi_device { void *peb_buf; struct mutex buf_mutex; struct mutex ckvol_mutex; - struct notifier_block wl_reboot_notifier; struct ubi_debug_info dbg; }; diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 4f6f339d8fb8..fbd399cf6503 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -89,7 +89,6 @@ #include #include #include -#include #include "ubi.h" #include "wl.h" @@ -128,8 +127,6 @@ static int self_check_in_wl_tree(const struct ubi_device *ubi, struct ubi_wl_entry *e, struct rb_root *root); static int self_check_in_pq(const struct ubi_device *ubi, struct ubi_wl_entry *e); -static int ubi_wl_reboot_notifier(struct notifier_block *n, - unsigned long state, void *cmd); /** * wl_tree_add - add a wear-leveling entry to a WL RB-tree. @@ -1953,13 +1950,6 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) if (!ubi->ro_mode && !ubi->fm_disabled) ubi_ensure_anchor_pebs(ubi); #endif - - if (!ubi->wl_reboot_notifier.notifier_call) { - ubi->wl_reboot_notifier.notifier_call = ubi_wl_reboot_notifier; - ubi->wl_reboot_notifier.priority = 1; /* Higher than MTD */ - register_reboot_notifier(&ubi->wl_reboot_notifier); - } - return 0; out_free: @@ -2005,17 +1995,6 @@ void ubi_wl_close(struct ubi_device *ubi) kfree(ubi->lookuptbl); } -static int ubi_wl_reboot_notifier(struct notifier_block *n, - unsigned long state, void *cmd) -{ - struct ubi_device *ubi; - - ubi = container_of(n, struct ubi_device, wl_reboot_notifier); - ubi_wl_close(ubi); - - return NOTIFY_DONE; -} - /** * self_check_ec - make sure that the erase counter of a PEB is correct. * @ubi: UBI device description object diff --git a/drivers/mux/core.c b/drivers/mux/core.c index 78c0022697ec..02be4ba37257 100644 --- a/drivers/mux/core.c +++ b/drivers/mux/core.c @@ -42,7 +42,7 @@ struct mux_state { unsigned int state; }; -static struct class mux_class = { +static const struct class mux_class = { .name = "mux", }; diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index a2abfade82dd..70814303aab8 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -84,7 +84,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (skb_copy_bits(skb, BAREUDP_BASE_HLEN, &ipversion, sizeof(ipversion))) { - dev_core_stats_rx_dropped_inc(bareudp->dev); + dev_dstats_rx_dropped(bareudp->dev); goto drop; } ipversion >>= 4; @@ -94,7 +94,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) } else if (ipversion == 6 && bareudp->multi_proto_mode) { proto = htons(ETH_P_IPV6); } else { - dev_core_stats_rx_dropped_inc(bareudp->dev); + dev_dstats_rx_dropped(bareudp->dev); goto drop; } } else if (bareudp->ethertype == htons(ETH_P_MPLS_UC)) { @@ -108,7 +108,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) ipv4_is_multicast(tunnel_hdr->daddr)) { proto = htons(ETH_P_MPLS_MC); } else { - dev_core_stats_rx_dropped_inc(bareudp->dev); + dev_dstats_rx_dropped(bareudp->dev); goto drop; } } else { @@ -124,7 +124,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) (addr_type & IPV6_ADDR_MULTICAST)) { proto = htons(ETH_P_MPLS_MC); } else { - dev_core_stats_rx_dropped_inc(bareudp->dev); + dev_dstats_rx_dropped(bareudp->dev); goto drop; } } @@ -136,7 +136,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) proto, !net_eq(bareudp->net, dev_net(bareudp->dev)))) { - dev_core_stats_rx_dropped_inc(bareudp->dev); + dev_dstats_rx_dropped(bareudp->dev); goto drop; } @@ -144,7 +144,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) tun_dst = udp_tun_rx_dst(skb, family, key, 0, 0); if (!tun_dst) { - dev_core_stats_rx_dropped_inc(bareudp->dev); + dev_dstats_rx_dropped(bareudp->dev); goto drop; } skb_dst_set(skb, &tun_dst->dst); @@ -194,7 +194,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) len = skb->len; err = gro_cells_receive(&bareudp->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) - dev_sw_netstats_rx_add(bareudp->dev, len); + dev_dstats_rx_add(bareudp->dev, len); return 0; drop: @@ -589,7 +589,7 @@ static void bareudp_setup(struct net_device *dev) dev->priv_flags |= IFF_NO_QUEUE; dev->lltx = true; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; - dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int bareudp_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index b19492a7f6ad..8adbec7c5084 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -63,13 +63,8 @@ void bond_debug_unregister(struct bonding *bond) void bond_debug_reregister(struct bonding *bond) { - struct dentry *d; - - d = debugfs_rename(bonding_debug_root, bond->debug_dir, - bonding_debug_root, bond->dev->name); - if (!IS_ERR(d)) { - bond->debug_dir = d; - } else { + int err = debugfs_change_name(bond->debug_dir, "%s", bond->dev->name); + if (err) { netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n"); bond_debug_unregister(bond); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 7b78c2bada81..e45bba240cbc 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1538,17 +1538,20 @@ static netdev_features_t bond_fix_features(struct net_device *dev, NETIF_F_HIGHDMA | NETIF_F_LRO) #define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) + NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \ + NETIF_F_GSO_PARTIAL) #define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_GSO_SOFTWARE) +#define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP) + static void bond_compute_features(struct bonding *bond) { + netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; - netdev_features_t gso_partial_features = NETIF_F_GSO_ESP; netdev_features_t vlan_features = BOND_VLAN_FEATURES; netdev_features_t enc_features = BOND_ENC_FEATURES; #ifdef CONFIG_XFRM_OFFLOAD @@ -1582,8 +1585,9 @@ static void bond_compute_features(struct bonding *bond) BOND_XFRM_FEATURES); #endif /* CONFIG_XFRM_OFFLOAD */ - if (slave->dev->hw_enc_features & NETIF_F_GSO_PARTIAL) - gso_partial_features &= slave->dev->gso_partial_features; + gso_partial_features = netdev_increment_features(gso_partial_features, + slave->dev->gso_partial_features, + BOND_GSO_PARTIAL_FEATURES); mpls_features = netdev_increment_features(mpls_features, slave->dev->mpls_features, @@ -1598,12 +1602,8 @@ static void bond_compute_features(struct bonding *bond) } bond_dev->hard_header_len = max_hard_header_len; - if (gso_partial_features & NETIF_F_GSO_ESP) - bond_dev->gso_partial_features |= NETIF_F_GSO_ESP; - else - bond_dev->gso_partial_features &= ~NETIF_F_GSO_ESP; - done: + bond_dev->gso_partial_features = gso_partial_features; bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | @@ -6046,6 +6046,7 @@ void bond_setup(struct net_device *bond_dev) bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; + bond_dev->features |= NETIF_F_GSO_PARTIAL; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_features |= BOND_XFRM_FEATURES; /* Only enable XFRM features if this is an active-backup config */ diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index 681643ab3780..5ec3170b896a 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -85,8 +85,6 @@ const char *can_get_state_str(const enum can_state state) default: return ""; } - - return ""; } EXPORT_SYMBOL_GPL(can_get_state_str); diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index cdf0ec9fa7f3..21a61b86f67d 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -1073,9 +1073,10 @@ static int grcan_open(struct net_device *dev) if (err) goto exit_close_candev; + napi_enable(&priv->napi); + spin_lock_irqsave(&priv->lock, flags); - napi_enable(&priv->napi); grcan_start(dev); if (!(priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)) netif_start_queue(dev); diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index fee012b57f33..fa04a7ced02b 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -999,7 +999,8 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) can->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO | - CAN_CTRLMODE_CC_LEN8_DLC; + CAN_CTRLMODE_CC_LEN8_DLC | + CAN_CTRLMODE_BERR_REPORTING; status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); if (!(status & KVASER_PCIEFD_KCAN_STAT_FD)) { @@ -1234,11 +1235,15 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie, } static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can, + const struct can_berr_counter *bec, struct can_frame *cf, enum can_state new_state, enum can_state tx_state, enum can_state rx_state) { + enum can_state old_state; + + old_state = can->can.state; can_change_state(can->can.dev, cf, tx_state, rx_state); if (new_state == CAN_STATE_BUS_OFF) { @@ -1254,6 +1259,18 @@ static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can, can_bus_off(ndev); } } + if (old_state == CAN_STATE_BUS_OFF && + new_state == CAN_STATE_ERROR_ACTIVE && + can->can.restart_ms) { + can->can.can_stats.restarts++; + if (cf) + cf->can_id |= CAN_ERR_RESTARTED; + } + if (cf && new_state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; + cf->data[6] = bec->txerr; + cf->data[7] = bec->rxerr; + } } static void kvaser_pciefd_packet_to_state(struct kvaser_pciefd_rx_packet *p, @@ -1288,7 +1305,7 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can, struct can_berr_counter bec; enum can_state old_state, new_state, tx_state, rx_state; struct net_device *ndev = can->can.dev; - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct can_frame *cf = NULL; old_state = can->can.state; @@ -1297,16 +1314,10 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can, bec.rxerr = FIELD_GET(KVASER_PCIEFD_SPACK_RXERR_MASK, p->header[0]); kvaser_pciefd_packet_to_state(p, &bec, &new_state, &tx_state, &rx_state); - skb = alloc_can_err_skb(ndev, &cf); + if (can->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) + skb = alloc_can_err_skb(ndev, &cf); if (new_state != old_state) { - kvaser_pciefd_change_state(can, cf, new_state, tx_state, rx_state); - if (old_state == CAN_STATE_BUS_OFF && - new_state == CAN_STATE_ERROR_ACTIVE && - can->can.restart_ms) { - can->can.can_stats.restarts++; - if (skb) - cf->can_id |= CAN_ERR_RESTARTED; - } + kvaser_pciefd_change_state(can, &bec, cf, new_state, tx_state, rx_state); } can->err_rep_cnt++; @@ -1319,18 +1330,19 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can, can->bec.txerr = bec.txerr; can->bec.rxerr = bec.rxerr; - if (!skb) { - ndev->stats.rx_dropped++; - return -ENOMEM; + if (can->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) { + if (!skb) { + netdev_warn(ndev, "No memory left for err_skb\n"); + ndev->stats.rx_dropped++; + return -ENOMEM; + } + kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp); + cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + netif_rx(skb); } - kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp); - cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT; - cf->data[6] = bec.txerr; - cf->data[7] = bec.rxerr; - - netif_rx(skb); - return 0; } @@ -1359,6 +1371,7 @@ static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can, { struct can_berr_counter bec; enum can_state old_state, new_state, tx_state, rx_state; + int ret = 0; old_state = can->can.state; @@ -1372,25 +1385,15 @@ static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can, struct can_frame *cf; skb = alloc_can_err_skb(ndev, &cf); - if (!skb) { + kvaser_pciefd_change_state(can, &bec, cf, new_state, tx_state, rx_state); + if (skb) { + kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp); + netif_rx(skb); + } else { ndev->stats.rx_dropped++; - return -ENOMEM; + netdev_warn(ndev, "No memory left for err_skb\n"); + ret = -ENOMEM; } - - kvaser_pciefd_change_state(can, cf, new_state, tx_state, rx_state); - if (old_state == CAN_STATE_BUS_OFF && - new_state == CAN_STATE_ERROR_ACTIVE && - can->can.restart_ms) { - can->can.can_stats.restarts++; - cf->can_id |= CAN_ERR_RESTARTED; - } - - kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp); - - cf->data[6] = bec.txerr; - cf->data[7] = bec.rxerr; - - netif_rx(skb); } can->bec.txerr = bec.txerr; can->bec.rxerr = bec.rxerr; @@ -1398,7 +1401,7 @@ static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can, if (bec.txerr || bec.rxerr) mod_timer(&can->bec_poll_timer, KVASER_PCIEFD_BEC_POLL_FREQ); - return 0; + return ret; } static int kvaser_pciefd_handle_status_packet(struct kvaser_pciefd *pcie, diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 533bcb77c9f9..d025d4163fd1 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1220,20 +1220,32 @@ static void m_can_coalescing_update(struct m_can_classdev *cdev, u32 ir) static int m_can_interrupt_handler(struct m_can_classdev *cdev) { struct net_device *dev = cdev->net; - u32 ir; + u32 ir = 0, ir_read; int ret; if (pm_runtime_suspended(cdev->dev)) return IRQ_NONE; - ir = m_can_read(cdev, M_CAN_IR); + /* The m_can controller signals its interrupt status as a level, but + * depending in the integration the CPU may interpret the signal as + * edge-triggered (for example with m_can_pci). For these + * edge-triggered integrations, we must observe that IR is 0 at least + * once to be sure that the next interrupt will generate an edge. + */ + while ((ir_read = m_can_read(cdev, M_CAN_IR)) != 0) { + ir |= ir_read; + + /* ACK all irqs */ + m_can_write(cdev, M_CAN_IR, ir); + + if (!cdev->irq_edge_triggered) + break; + } + m_can_coalescing_update(cdev, ir); if (!ir) return IRQ_NONE; - /* ACK all irqs */ - m_can_write(cdev, M_CAN_IR, ir); - if (cdev->ops->clear_interrupts) cdev->ops->clear_interrupts(cdev); @@ -1695,6 +1707,14 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } + /* Write the INIT bit, in case no hardware reset has happened before + * the probe (for example, it was observed that the Intel Elkhart Lake + * SoCs do not properly reset the CAN controllers on reboot) + */ + err = m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + if (err) + return err; + if (!cdev->is_peripheral) netif_napi_add(dev, &cdev->napi, m_can_poll); @@ -1746,11 +1766,7 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } - /* Forcing standby mode should be redundant, as the chip should be in - * standby after a reset. Write the INIT bit anyways, should the chip - * be configured by previous stage. - */ - return m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + return 0; } static void m_can_stop(struct net_device *dev) @@ -1769,6 +1785,13 @@ static void m_can_stop(struct net_device *dev) /* set the state as STOPPED */ cdev->can.state = CAN_STATE_STOPPED; + + if (cdev->ops->deinit) { + ret = cdev->ops->deinit(cdev); + if (ret) + netdev_err(dev, "failed to deinitialize: %pe\n", + ERR_PTR(ret)); + } } static int m_can_close(struct net_device *dev) @@ -2450,6 +2473,7 @@ int m_can_class_suspend(struct device *dev) { struct m_can_classdev *cdev = dev_get_drvdata(dev); struct net_device *ndev = cdev->net; + int ret = 0; if (netif_running(ndev)) { netif_stop_queue(ndev); @@ -2462,6 +2486,9 @@ int m_can_class_suspend(struct device *dev) if (cdev->pm_wake_source) { hrtimer_cancel(&cdev->hrtimer); m_can_write(cdev, M_CAN_IE, IR_RF0N); + + if (cdev->ops->deinit) + ret = cdev->ops->deinit(cdev); } else { m_can_stop(ndev); } @@ -2473,7 +2500,7 @@ int m_can_class_suspend(struct device *dev) cdev->can.state = CAN_STATE_SLEEPING; - return 0; + return ret; } EXPORT_SYMBOL_GPL(m_can_class_suspend); @@ -2481,14 +2508,13 @@ int m_can_class_resume(struct device *dev) { struct m_can_classdev *cdev = dev_get_drvdata(dev); struct net_device *ndev = cdev->net; + int ret = 0; pinctrl_pm_select_default_state(dev); cdev->can.state = CAN_STATE_ERROR_ACTIVE; if (netif_running(ndev)) { - int ret; - ret = m_can_clk_start(cdev); if (ret) return ret; @@ -2501,6 +2527,10 @@ int m_can_class_resume(struct device *dev) * again. */ cdev->active_interrupts |= IR_RF0N | IR_TEFN; + + if (cdev->ops->init) + ret = cdev->ops->init(cdev); + m_can_write(cdev, M_CAN_IE, cdev->active_interrupts); } else { ret = m_can_start(ndev); @@ -2514,7 +2544,7 @@ int m_can_class_resume(struct device *dev) netif_start_queue(ndev); } - return 0; + return ret; } EXPORT_SYMBOL_GPL(m_can_class_resume); diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 92b2bd8628e6..bd4746c63af3 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -68,6 +68,7 @@ struct m_can_ops { int (*write_fifo)(struct m_can_classdev *cdev, int addr_offset, const void *val, size_t val_count); int (*init)(struct m_can_classdev *cdev); + int (*deinit)(struct m_can_classdev *cdev); }; struct m_can_tx_op { @@ -99,6 +100,7 @@ struct m_can_classdev { int pm_clock_support; int pm_wake_source; int is_peripheral; + bool irq_edge_triggered; // Cached M_CAN_IE register content u32 active_interrupts; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index d72fe771dfc7..9ad7419f88f8 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -127,6 +127,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->pm_clock_support = 1; mcan_class->pm_wake_source = 0; mcan_class->can.clock.freq = id->driver_data; + mcan_class->irq_edge_triggered = true; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class); diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c index 2f73bf3abad8..e5c162f8c589 100644 --- a/drivers/net/can/m_can/tcan4x5x-core.c +++ b/drivers/net/can/m_can/tcan4x5x-core.c @@ -92,6 +92,8 @@ #define TCAN4X5X_MODE_STANDBY BIT(6) #define TCAN4X5X_MODE_NORMAL BIT(7) +#define TCAN4X5X_NWKRQ_VOLTAGE_VIO BIT(19) + #define TCAN4X5X_DISABLE_WAKE_MSK (BIT(31) | BIT(30)) #define TCAN4X5X_DISABLE_INH_MSK BIT(9) @@ -267,9 +269,24 @@ static int tcan4x5x_init(struct m_can_classdev *cdev) if (ret) return ret; + if (tcan4x5x->nwkrq_voltage_vio) { + ret = regmap_set_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG, + TCAN4X5X_NWKRQ_VOLTAGE_VIO); + if (ret) + return ret; + } + return ret; } +static int tcan4x5x_deinit(struct m_can_classdev *cdev) +{ + struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev); + + return regmap_update_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG, + TCAN4X5X_MODE_SEL_MASK, TCAN4X5X_MODE_STANDBY); +}; + static int tcan4x5x_disable_wake(struct m_can_classdev *cdev) { struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev); @@ -318,6 +335,14 @@ static const struct tcan4x5x_version_info return &tcan4x5x_versions[TCAN4X5X]; } +static void tcan4x5x_get_dt_data(struct m_can_classdev *cdev) +{ + struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev); + + tcan4x5x->nwkrq_voltage_vio = + of_property_read_bool(cdev->dev->of_node, "ti,nwkrq-voltage-vio"); +} + static int tcan4x5x_get_gpios(struct m_can_classdev *cdev, const struct tcan4x5x_version_info *version_info) { @@ -359,6 +384,7 @@ static int tcan4x5x_get_gpios(struct m_can_classdev *cdev, static const struct m_can_ops tcan4x5x_ops = { .init = tcan4x5x_init, + .deinit = tcan4x5x_deinit, .read_reg = tcan4x5x_read_reg, .write_reg = tcan4x5x_write_reg, .write_fifo = tcan4x5x_write_fifo, @@ -392,7 +418,7 @@ static int tcan4x5x_can_probe(struct spi_device *spi) priv->power = NULL; } - m_can_class_get_clocks(mcan_class); + mcan_class->cclk = devm_clk_get(mcan_class->dev, "cclk"); if (IS_ERR(mcan_class->cclk)) { dev_err(&spi->dev, "no CAN clock source defined\n"); freq = TCAN4X5X_EXT_CLK_DEF; @@ -453,6 +479,8 @@ static int tcan4x5x_can_probe(struct spi_device *spi) goto out_power; } + tcan4x5x_get_dt_data(mcan_class); + tcan4x5x_check_wake(priv); ret = tcan4x5x_write_tcan_reg(mcan_class, TCAN4X5X_INT_EN, 0); diff --git a/drivers/net/can/m_can/tcan4x5x.h b/drivers/net/can/m_can/tcan4x5x.h index e62c030d3e1e..203399d5e8cc 100644 --- a/drivers/net/can/m_can/tcan4x5x.h +++ b/drivers/net/can/m_can/tcan4x5x.h @@ -42,6 +42,8 @@ struct tcan4x5x_priv { struct tcan4x5x_map_buf map_buf_rx; struct tcan4x5x_map_buf map_buf_tx; + + bool nwkrq_voltage_vio; }; static inline void diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c index c42ebe9da55a..2d555f854008 100644 --- a/drivers/net/can/sja1000/sja1000_platform.c +++ b/drivers/net/can/sja1000/sja1000_platform.c @@ -230,18 +230,9 @@ static int sp_probe(struct platform_device *pdev) return -ENODEV; } - res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res_mem) - return -ENODEV; - - if (!devm_request_mem_region(&pdev->dev, res_mem->start, - resource_size(res_mem), DRV_NAME)) - return -EBUSY; - - addr = devm_ioremap(&pdev->dev, res_mem->start, - resource_size(res_mem)); - if (!addr) - return -ENOMEM; + addr = devm_platform_get_and_ioremap_resource(pdev, 0, &res_mem); + if (IS_ERR(addr)) + return PTR_ERR(addr); if (of) { irq = platform_get_irq(pdev, 0); diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 4311c1f0eafd..6fcb301ef611 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -570,7 +570,7 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status) else state = CAN_STATE_ERROR_ACTIVE; } - if (skb && state != CAN_STATE_BUS_OFF) { + if (likely(skb) && state != CAN_STATE_BUS_OFF) { cf->can_id |= CAN_ERR_CNT; cf->data[6] = txerr; cf->data[7] = rxerr; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 7d12776ab63e..dcb0bcbe0565 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -818,7 +818,8 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel) init_completion(&priv->stop_comp); init_completion(&priv->flush_comp); init_completion(&priv->get_busparams_comp); - priv->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC; + priv->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC | + CAN_CTRLMODE_BERR_REPORTING; priv->dev = dev; priv->netdev = netdev; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 3764b263add3..8e88b5917796 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -926,6 +926,42 @@ kvaser_usb_hydra_bus_status_to_can_state(const struct kvaser_usb_net_priv *priv, } } +static void kvaser_usb_hydra_change_state(struct kvaser_usb_net_priv *priv, + const struct can_berr_counter *bec, + struct can_frame *cf, + enum can_state new_state) +{ + struct net_device *netdev = priv->netdev; + enum can_state old_state = priv->can.state; + enum can_state tx_state, rx_state; + + tx_state = (bec->txerr >= bec->rxerr) ? + new_state : CAN_STATE_ERROR_ACTIVE; + rx_state = (bec->txerr <= bec->rxerr) ? + new_state : CAN_STATE_ERROR_ACTIVE; + can_change_state(netdev, cf, tx_state, rx_state); + + if (new_state == CAN_STATE_BUS_OFF && old_state < CAN_STATE_BUS_OFF) { + if (priv->can.restart_ms == 0) + kvaser_usb_hydra_send_simple_cmd_async(priv, CMD_STOP_CHIP_REQ); + + can_bus_off(netdev); + } + + if (priv->can.restart_ms && + old_state >= CAN_STATE_BUS_OFF && + new_state < CAN_STATE_BUS_OFF) { + priv->can.can_stats.restarts++; + if (cf) + cf->can_id |= CAN_ERR_RESTARTED; + } + if (cf && new_state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; + cf->data[6] = bec->txerr; + cf->data[7] = bec->rxerr; + } +} + static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv, u8 bus_status, const struct can_berr_counter *bec) @@ -951,41 +987,11 @@ static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv, return; skb = alloc_can_err_skb(netdev, &cf); - if (skb) { - enum can_state tx_state, rx_state; - - tx_state = (bec->txerr >= bec->rxerr) ? - new_state : CAN_STATE_ERROR_ACTIVE; - rx_state = (bec->txerr <= bec->rxerr) ? - new_state : CAN_STATE_ERROR_ACTIVE; - can_change_state(netdev, cf, tx_state, rx_state); - } - - if (new_state == CAN_STATE_BUS_OFF && old_state < CAN_STATE_BUS_OFF) { - if (!priv->can.restart_ms) - kvaser_usb_hydra_send_simple_cmd_async - (priv, CMD_STOP_CHIP_REQ); - - can_bus_off(netdev); - } - - if (!skb) { + kvaser_usb_hydra_change_state(priv, bec, cf, new_state); + if (skb) + netif_rx(skb); + else netdev_warn(netdev, "No memory left for err_skb\n"); - return; - } - - if (priv->can.restart_ms && - old_state >= CAN_STATE_BUS_OFF && - new_state < CAN_STATE_BUS_OFF) - priv->can.can_stats.restarts++; - - if (new_state != CAN_STATE_BUS_OFF) { - cf->can_id |= CAN_ERR_CNT; - cf->data[6] = bec->txerr; - cf->data[7] = bec->rxerr; - } - - netif_rx(skb); } static void kvaser_usb_hydra_state_event(const struct kvaser_usb *dev, @@ -1078,9 +1084,8 @@ kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv, { struct net_device *netdev = priv->netdev; struct net_device_stats *stats = &netdev->stats; - struct can_frame *cf; - struct sk_buff *skb; - struct skb_shared_hwtstamps *shhwtstamps; + struct can_frame *cf = NULL; + struct sk_buff *skb = NULL; struct can_berr_counter bec; enum can_state new_state, old_state; u8 bus_status; @@ -1096,52 +1101,26 @@ kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv, kvaser_usb_hydra_bus_status_to_can_state(priv, bus_status, &bec, &new_state); - skb = alloc_can_err_skb(netdev, &cf); + if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) + skb = alloc_can_err_skb(netdev, &cf); + if (new_state != old_state) + kvaser_usb_hydra_change_state(priv, &bec, cf, new_state); - if (new_state != old_state) { + if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) { if (skb) { - enum can_state tx_state, rx_state; + struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); - tx_state = (bec.txerr >= bec.rxerr) ? - new_state : CAN_STATE_ERROR_ACTIVE; - rx_state = (bec.txerr <= bec.rxerr) ? - new_state : CAN_STATE_ERROR_ACTIVE; - - can_change_state(netdev, cf, tx_state, rx_state); - - if (priv->can.restart_ms && - old_state >= CAN_STATE_BUS_OFF && - new_state < CAN_STATE_BUS_OFF) - cf->can_id |= CAN_ERR_RESTARTED; - } - - if (new_state == CAN_STATE_BUS_OFF) { - if (!priv->can.restart_ms) - kvaser_usb_hydra_send_simple_cmd_async - (priv, CMD_STOP_CHIP_REQ); - - can_bus_off(netdev); + shhwtstamps->hwtstamp = hwtstamp; + cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + netif_rx(skb); + } else { + stats->rx_dropped++; + netdev_warn(netdev, "No memory left for err_skb\n"); } } - if (!skb) { - stats->rx_dropped++; - netdev_warn(netdev, "No memory left for err_skb\n"); - return; - } - - shhwtstamps = skb_hwtstamps(skb); - shhwtstamps->hwtstamp = hwtstamp; - - cf->can_id |= CAN_ERR_BUSERROR; - if (new_state != CAN_STATE_BUS_OFF) { - cf->can_id |= CAN_ERR_CNT; - cf->data[6] = bec.txerr; - cf->data[7] = bec.rxerr; - } - - netif_rx(skb); - priv->bec.txerr = bec.txerr; priv->bec.rxerr = bec.rxerr; } diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 6b9122ab1464..6a45adcc45bd 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -1120,10 +1120,8 @@ kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv, static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, const struct kvaser_usb_err_summary *es) { - struct can_frame *cf; - struct can_frame tmp_cf = { .can_id = CAN_ERR_FLAG, - .len = CAN_ERR_DLC }; - struct sk_buff *skb; + struct can_frame *cf = NULL; + struct sk_buff *skb = NULL; struct net_device_stats *stats; struct kvaser_usb_net_priv *priv; struct kvaser_usb_net_leaf_priv *leaf; @@ -1143,18 +1141,10 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, if (!netif_running(priv->netdev)) return; - /* Update all of the CAN interface's state and error counters before - * trying any memory allocation that can actually fail with -ENOMEM. - * - * We send a temporary stack-allocated error CAN frame to - * can_change_state() for the very same reason. - * - * TODO: Split can_change_state() responsibility between updating the - * CAN interface's state and counters, and the setting up of CAN error - * frame ID and data to userspace. Remove stack allocation afterwards. - */ old_state = priv->can.state; - kvaser_usb_leaf_rx_error_update_can_state(priv, es, &tmp_cf); + if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) + skb = alloc_can_err_skb(priv->netdev, &cf); + kvaser_usb_leaf_rx_error_update_can_state(priv, es, cf); new_state = priv->can.state; /* If there are errors, request status updates periodically as we do @@ -1168,13 +1158,6 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, schedule_delayed_work(&leaf->chip_state_req_work, msecs_to_jiffies(500)); - skb = alloc_can_err_skb(priv->netdev, &cf); - if (!skb) { - stats->rx_dropped++; - return; - } - memcpy(cf, &tmp_cf, sizeof(*cf)); - if (new_state != old_state) { if (es->status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) { @@ -1187,11 +1170,20 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, if (priv->can.restart_ms && old_state == CAN_STATE_BUS_OFF && new_state < CAN_STATE_BUS_OFF) { - cf->can_id |= CAN_ERR_RESTARTED; + if (cf) + cf->can_id |= CAN_ERR_RESTARTED; netif_carrier_on(priv->netdev); } } + if (!skb) { + if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) { + stats->rx_dropped++; + netdev_warn(priv->netdev, "No memory left for err_skb\n"); + } + return; + } + switch (dev->driver_info->family) { case KVASER_LEAF: if (es->leaf.error_factor) { diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 285785c942b0..79dc77835681 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -2224,25 +2224,19 @@ int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy) } EXPORT_SYMBOL(b53_eee_init); -int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e) +bool b53_support_eee(struct dsa_switch *ds, int port) { struct b53_device *dev = ds->priv; - if (is5325(dev) || is5365(dev)) - return -EOPNOTSUPP; - - return 0; + return !is5325(dev) && !is5365(dev); } -EXPORT_SYMBOL(b53_get_mac_eee); +EXPORT_SYMBOL(b53_support_eee); int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e) { struct b53_device *dev = ds->priv; struct ethtool_keee *p = &dev->ports[port].eee; - if (is5325(dev) || is5365(dev)) - return -EOPNOTSUPP; - p->eee_enabled = e->eee_enabled; b53_eee_enable_set(ds, port, e->eee_enabled); @@ -2298,7 +2292,7 @@ static const struct dsa_switch_ops b53_switch_ops = { .phylink_get_caps = b53_phylink_get_caps, .port_enable = b53_enable_port, .port_disable = b53_disable_port, - .get_mac_eee = b53_get_mac_eee, + .support_eee = b53_support_eee, .set_mac_eee = b53_set_mac_eee, .port_bridge_join = b53_br_join, .port_bridge_leave = b53_br_leave, diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 05141176daf5..9e9b5bc0c5d6 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -384,7 +384,7 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy); void b53_disable_port(struct dsa_switch *ds, int port); void b53_brcm_hdr_setup(struct dsa_switch *ds, int port); int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy); -int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e); +bool b53_support_eee(struct dsa_switch *ds, int port); int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e); #endif diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c index 3f8a491ce885..4730982b6840 100644 --- a/drivers/net/dsa/b53/b53_serdes.c +++ b/drivers/net/dsa/b53/b53_serdes.c @@ -99,8 +99,8 @@ static void b53_serdes_an_restart(struct phylink_pcs *pcs) SERDES_MII_BLK, reg); } -static void b53_serdes_get_state(struct phylink_pcs *pcs, - struct phylink_link_state *state) +static void b53_serdes_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, + struct phylink_link_state *state) { struct b53_device *dev = pcs_to_b53_pcs(pcs)->dev; u8 lane = pcs_to_b53_pcs(pcs)->lane; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 43bde1f583ff..fa2bf3fa9019 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1232,7 +1232,7 @@ static const struct dsa_switch_ops bcm_sf2_ops = { .set_wol = bcm_sf2_sw_set_wol, .port_enable = bcm_sf2_port_setup, .port_disable = bcm_sf2_port_disable, - .get_mac_eee = b53_get_mac_eee, + .support_eee = b53_support_eee, .set_mac_eee = b53_set_mac_eee, .port_bridge_join = b53_br_join, .port_bridge_leave = b53_br_leave, diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index d16817e0476f..29fe79ea74cd 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -2,7 +2,7 @@ /* * Microchip KSZ9477 switch driver main logic * - * Copyright (C) 2017-2019 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #include @@ -983,26 +983,51 @@ void ksz9477_get_caps(struct ksz_device *dev, int port, int ksz9477_set_ageing_time(struct ksz_device *dev, unsigned int msecs) { u32 secs = msecs / 1000; - u8 value; - u8 data; + u8 data, mult, value; + u32 max_val; int ret; - value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs); +#define MAX_TIMER_VAL ((1 << 8) - 1) - ret = ksz_write8(dev, REG_SW_LUE_CTRL_3, value); - if (ret < 0) - return ret; + /* The aging timer comprises a 3-bit multiplier and an 8-bit second + * value. Either of them cannot be zero. The maximum timer is then + * 7 * 255 = 1785 seconds. + */ + if (!secs) + secs = 1; - data = FIELD_GET(SW_AGE_PERIOD_10_8_M, secs); + /* Return error if too large. */ + else if (secs > 7 * MAX_TIMER_VAL) + return -EINVAL; ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value); if (ret < 0) return ret; - value &= ~SW_AGE_CNT_M; - value |= FIELD_PREP(SW_AGE_CNT_M, data); + /* Check whether there is need to update the multiplier. */ + mult = FIELD_GET(SW_AGE_CNT_M, value); + max_val = MAX_TIMER_VAL; + if (mult > 0) { + /* Try to use the same multiplier already in the register as + * the hardware default uses multiplier 4 and 75 seconds for + * 300 seconds. + */ + max_val = DIV_ROUND_UP(secs, mult); + if (max_val > MAX_TIMER_VAL || max_val * mult != secs) + max_val = MAX_TIMER_VAL; + } - return ksz_write8(dev, REG_SW_LUE_CTRL_0, value); + data = DIV_ROUND_UP(secs, max_val); + if (mult != data) { + value &= ~SW_AGE_CNT_M; + value |= FIELD_PREP(SW_AGE_CNT_M, data); + ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value); + if (ret < 0) + return ret; + } + + value = DIV_ROUND_UP(secs, data); + return ksz_write8(dev, REG_SW_LUE_CTRL_3, value); } void ksz9477_port_queue_split(struct ksz_device *dev, int port) diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index 1c6d7fc16772..a2beb27459f1 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -127,10 +127,14 @@ static const struct of_device_id ksz9477_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, ksz9477_dt_ids); +static DEFINE_SIMPLE_DEV_PM_OPS(ksz_i2c_pm_ops, + ksz_switch_suspend, ksz_switch_resume); + static struct i2c_driver ksz9477_i2c_driver = { .driver = { .name = "ksz9477-switch", .of_match_table = ksz9477_dt_ids, + .pm = &ksz_i2c_pm_ops, }, .probe = ksz9477_i2c_probe, .remove = ksz9477_i2c_remove, diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h index 04235c22bf40..ff579920078e 100644 --- a/drivers/net/dsa/microchip/ksz9477_reg.h +++ b/drivers/net/dsa/microchip/ksz9477_reg.h @@ -2,7 +2,7 @@ /* * Microchip KSZ9477 register definitions * - * Copyright (C) 2017-2018 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #ifndef __KSZ9477_REGS_H @@ -165,8 +165,6 @@ #define SW_VLAN_ENABLE BIT(7) #define SW_DROP_INVALID_VID BIT(6) #define SW_AGE_CNT_M GENMASK(5, 3) -#define SW_AGE_CNT_S 3 -#define SW_AGE_PERIOD_10_8_M GENMASK(10, 8) #define SW_RESV_MCAST_ENABLE BIT(2) #define SW_HASH_OPTION_M 0x03 #define SW_HASH_OPTION_CRC 1 diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 8a03baa6aecc..89f0796894af 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1339,6 +1339,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .supports_rgmii = {false, false, true}, .internal_phy = {true, true, false}, .gbit_capable = {false, false, true}, + .ptp_capable = true, .wr_table = &ksz8563_register_set, .rd_table = &ksz8563_register_set, }, @@ -1550,6 +1551,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .internal_phy = {true, true, true, true, true, false, false}, .gbit_capable = {true, true, true, true, true, true, true}, + .ptp_capable = true, .wr_table = &ksz9477_register_set, .rd_table = &ksz9477_register_set, }, @@ -1677,6 +1679,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .supports_rgmii = {false, false, true}, .internal_phy = {true, true, false}, .gbit_capable = {true, true, true}, + .ptp_capable = true, }, [KSZ8567] = { @@ -1712,6 +1715,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { true, false, false}, .gbit_capable = {false, false, false, false, false, true, true}, + .ptp_capable = true, }, [KSZ9567] = { @@ -1744,6 +1748,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .internal_phy = {true, true, true, true, true, false, false}, .gbit_capable = {true, true, true, true, true, true, true}, + .ptp_capable = true, }, [LAN9370] = { @@ -1773,6 +1778,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .supports_rmii = {false, false, false, false, true}, .supports_rgmii = {false, false, false, false, true}, .internal_phy = {true, true, true, true, false}, + .ptp_capable = true, }, [LAN9371] = { @@ -1802,6 +1808,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .supports_rmii = {false, false, false, false, true, true}, .supports_rgmii = {false, false, false, false, true, true}, .internal_phy = {true, true, true, true, false, false}, + .ptp_capable = true, }, [LAN9372] = { @@ -1835,6 +1842,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { true, true, false, false}, .internal_phy = {true, true, true, true, false, false, true, true}, + .ptp_capable = true, }, [LAN9373] = { @@ -1868,6 +1876,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { true, true, false, false}, .internal_phy = {true, true, true, false, false, false, true, true}, + .ptp_capable = true, }, [LAN9374] = { @@ -1901,6 +1910,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { true, true, false, false}, .internal_phy = {true, true, true, true, false, false, true, true}, + .ptp_capable = true, }, [LAN9646] = { @@ -2544,7 +2554,11 @@ static int ksz_mdio_register(struct ksz_device *dev) bus->read = ksz_sw_mdio_read; bus->write = ksz_sw_mdio_write; bus->name = "ksz user smi"; - snprintf(bus->id, MII_BUS_ID_SIZE, "SMI-%d", ds->index); + if (ds->dst->index != 0) { + snprintf(bus->id, MII_BUS_ID_SIZE, "SMI-%d-%d", ds->dst->index, ds->index); + } else { + snprintf(bus->id, MII_BUS_ID_SIZE, "SMI-%d", ds->index); + } } ret = ksz_parse_dt_phy_config(dev, bus, mdio_np); @@ -2805,16 +2819,21 @@ static int ksz_setup(struct dsa_switch *ds) if (ret) goto out_girq; - ret = ksz_ptp_irq_setup(ds, dp->index); - if (ret) - goto out_pirq; + if (dev->info->ptp_capable) { + ret = ksz_ptp_irq_setup(ds, dp->index); + if (ret) + goto out_pirq; + } } } - ret = ksz_ptp_clock_register(ds); - if (ret) { - dev_err(dev->dev, "Failed to register PTP clock: %d\n", ret); - goto out_ptpirq; + if (dev->info->ptp_capable) { + ret = ksz_ptp_clock_register(ds); + if (ret) { + dev_err(dev->dev, "Failed to register PTP clock: %d\n", + ret); + goto out_ptpirq; + } } ret = ksz_mdio_register(dev); @@ -2834,9 +2853,10 @@ static int ksz_setup(struct dsa_switch *ds) return 0; out_ptp_clock_unregister: - ksz_ptp_clock_unregister(ds); + if (dev->info->ptp_capable) + ksz_ptp_clock_unregister(ds); out_ptpirq: - if (dev->irq > 0) + if (dev->irq > 0 && dev->info->ptp_capable) dsa_switch_for_each_user_port(dp, dev->ds) ksz_ptp_irq_free(ds, dp->index); out_pirq: @@ -2855,11 +2875,13 @@ static void ksz_teardown(struct dsa_switch *ds) struct ksz_device *dev = ds->priv; struct dsa_port *dp; - ksz_ptp_clock_unregister(ds); + if (dev->info->ptp_capable) + ksz_ptp_clock_unregister(ds); if (dev->irq > 0) { dsa_switch_for_each_user_port(dp, dev->ds) { - ksz_ptp_irq_free(ds, dp->index); + if (dev->info->ptp_capable) + ksz_ptp_irq_free(ds, dp->index); ksz_irq_free(&dev->ports[dp->index].pirq); } @@ -3444,12 +3466,12 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port) return -EOPNOTSUPP; } -static int ksz_validate_eee(struct dsa_switch *ds, int port) +static bool ksz_support_eee(struct dsa_switch *ds, int port) { struct ksz_device *dev = ds->priv; if (!dev->info->internal_phy[port]) - return -EOPNOTSUPP; + return false; switch (dev->chip_id) { case KSZ8563_CHIP_ID: @@ -3461,41 +3483,16 @@ static int ksz_validate_eee(struct dsa_switch *ds, int port) case KSZ9896_CHIP_ID: case KSZ9897_CHIP_ID: case LAN9646_CHIP_ID: - return 0; + return true; } - return -EOPNOTSUPP; -} - -static int ksz_get_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_keee *e) -{ - int ret; - - ret = ksz_validate_eee(ds, port); - if (ret) - return ret; - - /* There is no documented control of Tx LPI configuration. */ - e->tx_lpi_enabled = true; - - /* There is no documented control of Tx LPI timer. According to tests - * Tx LPI timer seems to be set by default to minimal value. - */ - e->tx_lpi_timer = 0; - - return 0; + return false; } static int ksz_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e) { struct ksz_device *dev = ds->priv; - int ret; - - ret = ksz_validate_eee(ds, port); - if (ret) - return ret; if (!e->tx_lpi_enabled) { dev_err(dev->dev, "Disabling EEE Tx LPI is not supported\n"); @@ -4593,6 +4590,23 @@ static int ksz_hsr_leave(struct dsa_switch *ds, int port, return 0; } +static int ksz_suspend(struct dsa_switch *ds) +{ + struct ksz_device *dev = ds->priv; + + cancel_delayed_work_sync(&dev->mib_read); + return 0; +} + +static int ksz_resume(struct dsa_switch *ds) +{ + struct ksz_device *dev = ds->priv; + + if (dev->mib_read_interval) + schedule_delayed_work(&dev->mib_read, dev->mib_read_interval); + return 0; +} + static const struct dsa_switch_ops ksz_switch_ops = { .get_tag_protocol = ksz_get_tag_protocol, .connect_tag_protocol = ksz_connect_tag_protocol, @@ -4633,6 +4647,8 @@ static const struct dsa_switch_ops ksz_switch_ops = { .port_max_mtu = ksz_max_mtu, .get_wol = ksz_get_wol, .set_wol = ksz_set_wol, + .suspend = ksz_suspend, + .resume = ksz_resume, .get_ts_info = ksz_get_ts_info, .port_hwtstamp_get = ksz_hwtstamp_get, .port_hwtstamp_set = ksz_hwtstamp_set, @@ -4641,7 +4657,7 @@ static const struct dsa_switch_ops ksz_switch_ops = { .cls_flower_add = ksz_cls_flower_add, .cls_flower_del = ksz_cls_flower_del, .port_setup_tc = ksz_setup_tc, - .get_mac_eee = ksz_get_mac_eee, + .support_eee = ksz_support_eee, .set_mac_eee = ksz_set_mac_eee, .port_get_default_prio = ksz_port_get_default_prio, .port_set_default_prio = ksz_port_set_default_prio, @@ -5132,6 +5148,24 @@ void ksz_switch_remove(struct ksz_device *dev) } EXPORT_SYMBOL(ksz_switch_remove); +#ifdef CONFIG_PM_SLEEP +int ksz_switch_suspend(struct device *dev) +{ + struct ksz_device *priv = dev_get_drvdata(dev); + + return dsa_switch_suspend(priv->ds); +} +EXPORT_SYMBOL(ksz_switch_suspend); + +int ksz_switch_resume(struct device *dev) +{ + struct ksz_device *priv = dev_get_drvdata(dev); + + return dsa_switch_resume(priv->ds); +} +EXPORT_SYMBOL(ksz_switch_resume); +#endif + MODULE_AUTHOR("Woojung Huh "); MODULE_DESCRIPTION("Microchip KSZ Series Switch DSA Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index b3bb75ca0796..af17a9c030d4 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -92,6 +92,7 @@ struct ksz_chip_data { bool supports_rgmii[KSZ_MAX_NUM_PORTS]; bool internal_phy[KSZ_MAX_NUM_PORTS]; bool gbit_capable[KSZ_MAX_NUM_PORTS]; + bool ptp_capable; const struct regmap_access_table *wr_table; const struct regmap_access_table *rd_table; }; @@ -444,6 +445,8 @@ struct ksz_dev_ops { struct ksz_device *ksz_switch_alloc(struct device *base, void *priv); int ksz_switch_register(struct ksz_device *dev); void ksz_switch_remove(struct ksz_device *dev); +int ksz_switch_suspend(struct device *dev); +int ksz_switch_resume(struct device *dev); void ksz_init_mib_timer(struct ksz_device *dev); bool ksz_is_port_mac_global_usable(struct dsa_switch *ds, int port); diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c index 108a958dc356..b633d263098c 100644 --- a/drivers/net/dsa/microchip/ksz_spi.c +++ b/drivers/net/dsa/microchip/ksz_spi.c @@ -239,10 +239,14 @@ static const struct spi_device_id ksz_spi_ids[] = { }; MODULE_DEVICE_TABLE(spi, ksz_spi_ids); +static DEFINE_SIMPLE_DEV_PM_OPS(ksz_spi_pm_ops, + ksz_switch_suspend, ksz_switch_resume); + static struct spi_driver ksz_spi_driver = { .driver = { .name = "ksz-switch", .of_match_table = ksz_dt_ids, + .pm = &ksz_spi_pm_ops, }, .id_table = ksz_spi_ids, .probe = ksz_spi_probe, diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index b7652efd632e..b1ae3b9de3d1 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Microchip LAN937X switch driver main logic - * Copyright (C) 2019-2022 Microchip Technology Inc. + * Copyright (C) 2019-2024 Microchip Technology Inc. */ #include #include @@ -461,10 +461,66 @@ int lan937x_change_mtu(struct ksz_device *dev, int port, int new_mtu) int lan937x_set_ageing_time(struct ksz_device *dev, unsigned int msecs) { - u32 secs = msecs / 1000; - u32 value; + u8 data, mult, value8; + bool in_msec = false; + u32 max_val, value; + u32 secs = msecs; int ret; +#define MAX_TIMER_VAL ((1 << 20) - 1) + + /* The aging timer comprises a 3-bit multiplier and a 20-bit second + * value. Either of them cannot be zero. The maximum timer is then + * 7 * 1048575 = 7340025 seconds. As this value is too large for + * practical use it can be interpreted as microseconds, making the + * maximum timer 7340 seconds with finer control. This allows for + * maximum 122 minutes compared to 29 minutes in KSZ9477 switch. + */ + if (msecs % 1000) + in_msec = true; + else + secs /= 1000; + if (!secs) + secs = 1; + + /* Return error if too large. */ + else if (secs > 7 * MAX_TIMER_VAL) + return -EINVAL; + + /* Configure how to interpret the number value. */ + ret = ksz_rmw8(dev, REG_SW_LUE_CTRL_2, SW_AGE_CNT_IN_MICROSEC, + in_msec ? SW_AGE_CNT_IN_MICROSEC : 0); + if (ret < 0) + return ret; + + ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value8); + if (ret < 0) + return ret; + + /* Check whether there is need to update the multiplier. */ + mult = FIELD_GET(SW_AGE_CNT_M, value8); + max_val = MAX_TIMER_VAL; + if (mult > 0) { + /* Try to use the same multiplier already in the register as + * the hardware default uses multiplier 4 and 75 seconds for + * 300 seconds. + */ + max_val = DIV_ROUND_UP(secs, mult); + if (max_val > MAX_TIMER_VAL || max_val * mult != secs) + max_val = MAX_TIMER_VAL; + } + + data = DIV_ROUND_UP(secs, max_val); + if (mult != data) { + value8 &= ~SW_AGE_CNT_M; + value8 |= FIELD_PREP(SW_AGE_CNT_M, data); + ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value8); + if (ret < 0) + return ret; + } + + secs = DIV_ROUND_UP(secs, data); + value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs); ret = ksz_write8(dev, REG_SW_AGE_PERIOD__1, value); diff --git a/drivers/net/dsa/microchip/lan937x_reg.h b/drivers/net/dsa/microchip/lan937x_reg.h index 4ec93e421da4..72042fd64e5b 100644 --- a/drivers/net/dsa/microchip/lan937x_reg.h +++ b/drivers/net/dsa/microchip/lan937x_reg.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Microchip LAN937X switch register definitions - * Copyright (C) 2019-2021 Microchip Technology Inc. + * Copyright (C) 2019-2024 Microchip Technology Inc. */ #ifndef __LAN937X_REG_H #define __LAN937X_REG_H @@ -56,8 +56,7 @@ #define SW_VLAN_ENABLE BIT(7) #define SW_DROP_INVALID_VID BIT(6) -#define SW_AGE_CNT_M 0x7 -#define SW_AGE_CNT_S 3 +#define SW_AGE_CNT_M GENMASK(5, 3) #define SW_RESV_MCAST_ENABLE BIT(2) #define REG_SW_LUE_CTRL_1 0x0311 @@ -70,6 +69,10 @@ #define SW_FAST_AGING BIT(1) #define SW_LINK_AUTO_AGING BIT(0) +#define REG_SW_LUE_CTRL_2 0x0312 + +#define SW_AGE_CNT_IN_MICROSEC BIT(7) + #define REG_SW_AGE_PERIOD__1 0x0313 #define SW_AGE_PERIOD_7_0_M GENMASK(7, 0) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 086b8b3d5b40..1c83af805209 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2994,7 +2994,7 @@ static int mt753x_pcs_validate(struct phylink_pcs *pcs, return 0; } -static void mt7530_pcs_get_state(struct phylink_pcs *pcs, +static void mt7530_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct mt7530_priv *priv = pcs_to_mt753x_pcs(pcs)->priv; @@ -3085,18 +3085,6 @@ mt753x_setup(struct dsa_switch *ds) return ret; } -static int mt753x_get_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_keee *e) -{ - struct mt7530_priv *priv = ds->priv; - u32 eeecr = mt7530_read(priv, MT753X_PMEEECR_P(port)); - - e->tx_lpi_enabled = !(eeecr & LPI_MODE_EN); - e->tx_lpi_timer = LPI_THRESH_GET(eeecr); - - return 0; -} - static int mt753x_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e) { @@ -3238,7 +3226,7 @@ const struct dsa_switch_ops mt7530_switch_ops = { .port_mirror_add = mt753x_port_mirror_add, .port_mirror_del = mt753x_port_mirror_del, .phylink_get_caps = mt753x_phylink_get_caps, - .get_mac_eee = mt753x_get_mac_eee, + .support_eee = dsa_supports_eee, .set_mac_eee = mt753x_set_mac_eee, .conduit_state_change = mt753x_conduit_state_change, .port_setup_tc = mt753x_setup_tc, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 3a792f79270d..68d1e891752b 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -394,7 +394,7 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip) kthread_init_delayed_work(&chip->irq_poll_work, mv88e6xxx_irq_poll); - chip->kworker = kthread_create_worker(0, "%s", dev_name(chip->dev)); + chip->kworker = kthread_run_worker(0, "%s", dev_name(chip->dev)); if (IS_ERR(chip->kworker)) return PTR_ERR(chip->kworker); @@ -1289,9 +1289,6 @@ static size_t mv88e6095_stats_get_stat(struct mv88e6xxx_chip *chip, int port, const struct mv88e6xxx_hw_stat *stat, uint64_t *data) { - if (!(stat->type & (STATS_TYPE_BANK0 | STATS_TYPE_PORT))) - return 0; - *data = _mv88e6xxx_get_ethtool_stat(chip, stat, port, 0, MV88E6XXX_G1_STATS_OP_HIST_RX); return 1; @@ -1301,9 +1298,6 @@ static size_t mv88e6250_stats_get_stat(struct mv88e6xxx_chip *chip, int port, const struct mv88e6xxx_hw_stat *stat, uint64_t *data) { - if (!(stat->type & STATS_TYPE_BANK0)) - return 0; - *data = _mv88e6xxx_get_ethtool_stat(chip, stat, port, 0, MV88E6XXX_G1_STATS_OP_HIST_RX); return 1; @@ -1313,9 +1307,6 @@ static size_t mv88e6320_stats_get_stat(struct mv88e6xxx_chip *chip, int port, const struct mv88e6xxx_hw_stat *stat, uint64_t *data) { - if (!(stat->type & (STATS_TYPE_BANK0 | STATS_TYPE_BANK1))) - return 0; - *data = _mv88e6xxx_get_ethtool_stat(chip, stat, port, MV88E6XXX_G1_STATS_OP_BANK_1_BIT_9, MV88E6XXX_G1_STATS_OP_HIST_RX); @@ -1326,9 +1317,6 @@ static size_t mv88e6390_stats_get_stat(struct mv88e6xxx_chip *chip, int port, const struct mv88e6xxx_hw_stat *stat, uint64_t *data) { - if (!(stat->type & (STATS_TYPE_BANK0 | STATS_TYPE_BANK1))) - return 0; - *data = _mv88e6xxx_get_ethtool_stat(chip, stat, port, MV88E6XXX_G1_STATS_OP_BANK_1_BIT_10, 0); @@ -1341,6 +1329,9 @@ static size_t mv88e6xxx_stats_get_stat(struct mv88e6xxx_chip *chip, int port, { int ret = 0; + if (!(stat->type & chip->info->stats_type)) + return 0; + if (chip->info->ops->stats_get_stat) { mv88e6xxx_reg_lock(chip); ret = chip->info->ops->stats_get_stat(chip, port, stat, data); @@ -1522,13 +1513,6 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port, mv88e6xxx_reg_unlock(chip); } -static int mv88e6xxx_get_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_keee *e) -{ - /* Nothing to do on the port's MAC */ - return 0; -} - static int mv88e6xxx_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e) { @@ -5645,6 +5629,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 5, + .stats_type = STATS_TYPE_BANK0, .atu_move_port_mask = 0xf, .dual_chip = true, .ops = &mv88e6250_ops, @@ -5665,6 +5650,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 5, + .stats_type = STATS_TYPE_BANK0, .atu_move_port_mask = 0xf, .dual_chip = true, .ops = &mv88e6250_ops, @@ -5687,6 +5673,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 8, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -5708,6 +5695,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global2_addr = 0x1c, .age_time_coeff = 15000, .g1_irqs = 8, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .multi_chip = true, .ops = &mv88e6095_ops, @@ -5730,6 +5718,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 8, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -5754,6 +5743,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -5776,6 +5766,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global2_addr = 0x1c, .age_time_coeff = 15000, .g1_irqs = 9, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .multi_chip = true, .ops = &mv88e6131_ops, @@ -5800,6 +5791,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .atu_move_port_mask = 0x1f, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .pvt = true, .multi_chip = true, .edsa_support = MV88E6XXX_EDSA_SUPPORTED, @@ -5823,6 +5815,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -5848,6 +5841,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -5872,6 +5866,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -5897,6 +5892,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -5921,6 +5917,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -5946,6 +5943,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -5968,6 +5966,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global2_addr = 0x1c, .age_time_coeff = 15000, .g1_irqs = 8, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .multi_chip = true, .edsa_support = MV88E6XXX_EDSA_SUPPORTED, @@ -5992,6 +5991,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 9, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .pvt = true, .multi_chip = true, .atu_move_port_mask = 0x1f, @@ -6016,6 +6016,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 9, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0x1f, .pvt = true, .multi_chip = true, @@ -6039,6 +6040,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 9, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0x1f, .pvt = true, .multi_chip = true, @@ -6063,6 +6065,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 10, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0x1f, .pvt = true, .multi_chip = true, @@ -6087,6 +6090,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 10, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0x1f, .pvt = true, .multi_chip = true, @@ -6114,6 +6118,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0, .atu_move_port_mask = 0xf, .dual_chip = true, .ptp_support = true, @@ -6138,6 +6143,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -6161,6 +6167,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0, .atu_move_port_mask = 0xf, .dual_chip = true, .ptp_support = true, @@ -6184,6 +6191,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 9, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0x1f, .pvt = true, .multi_chip = true, @@ -6208,6 +6216,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 8, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -6233,6 +6242,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 8, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0xf, .multi_chip = true, .edsa_support = MV88E6XXX_EDSA_SUPPORTED, @@ -6259,6 +6269,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .atu_move_port_mask = 0x1f, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .pvt = true, .multi_chip = true, .edsa_support = MV88E6XXX_EDSA_SUPPORTED, @@ -6283,6 +6294,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -6307,6 +6319,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -6332,6 +6345,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 15000, .g1_irqs = 9, .g2_irqs = 10, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_PORT, .atu_move_port_mask = 0xf, .pvt = true, .multi_chip = true, @@ -6359,6 +6373,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 10, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0x1f, .pvt = true, .multi_chip = true, @@ -6383,6 +6398,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 9, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0x1f, .pvt = true, .multi_chip = true, @@ -6408,6 +6424,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 9, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0x1f, .pvt = true, .multi_chip = true, @@ -6433,6 +6450,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .age_time_coeff = 3750, .g1_irqs = 10, .g2_irqs = 14, + .stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1, .atu_move_port_mask = 0x1f, .pvt = true, .multi_chip = true, @@ -7074,7 +7092,7 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .get_sset_count = mv88e6xxx_get_sset_count, .port_max_mtu = mv88e6xxx_get_max_mtu, .port_change_mtu = mv88e6xxx_change_mtu, - .get_mac_eee = mv88e6xxx_get_mac_eee, + .support_eee = dsa_supports_eee, .set_mac_eee = mv88e6xxx_set_mac_eee, .get_eeprom_len = mv88e6xxx_get_eeprom_len, .get_eeprom = mv88e6xxx_get_eeprom, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 9fe8e8a7856b..86bf113c9bfa 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -144,6 +144,7 @@ struct mv88e6xxx_info { unsigned int age_time_coeff; unsigned int g1_irqs; unsigned int g2_irqs; + int stats_type; bool pvt; /* Mark certain ports as invalid. This is required for example for the diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6185.c b/drivers/net/dsa/mv88e6xxx/pcs-6185.c index 5a27d047a38e..75ed1fa500a5 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-6185.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-6185.c @@ -55,6 +55,7 @@ static irqreturn_t mv88e6185_pcs_handle_irq(int irq, void *dev_id) } static void mv88e6185_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mv88e6185_pcs *mpcs = pcs_to_mv88e6185_pcs(pcs); diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6352.c b/drivers/net/dsa/mv88e6xxx/pcs-6352.c index 88f624b65470..143fe21d1834 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-6352.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-6352.c @@ -158,6 +158,7 @@ static void marvell_c22_pcs_disable(struct phylink_pcs *pcs) } static void marvell_c22_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct marvell_c22_pcs *mpcs = pcs_to_marvell_c22_pcs(pcs); diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c index d758a6c1b226..59f63d6beec8 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "chip.h" #include "global2.h" @@ -257,6 +258,7 @@ static int mv88e639x_sgmii_pcs_post_config(struct phylink_pcs *pcs, } static void mv88e639x_sgmii_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs); @@ -395,6 +397,7 @@ static void mv88e639x_xg_pcs_disable(struct mv88e639x_pcs *mpcs) } static void mv88e639x_xg_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs); @@ -748,7 +751,7 @@ static int mv88e6393x_sgmii_apply_2500basex_an(struct mv88e639x_pcs *mpcs, if (err) dev_err(mpcs->mdio.dev.parent, "failed to %s 2500basex fix: %pe\n", - enable ? "enable" : "disable", ERR_PTR(err)); + str_enable_disable(enable), ERR_PTR(err)); return err; } @@ -889,6 +892,7 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs, } static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs); @@ -896,7 +900,7 @@ static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs, int err; if (state->interface != PHY_INTERFACE_MODE_USXGMII) - return mv88e639x_xg_pcs_get_state(pcs, state); + return mv88e639x_xg_pcs_get_state(pcs, neg_mode, state); state->link = false; diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index dc777ddce1f3..66b1b7277281 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "chip.h" #include "global2.h" @@ -176,7 +177,7 @@ int mv88e6xxx_port_set_link(struct mv88e6xxx_chip *chip, int port, int link) dev_dbg(chip->dev, "p%d: %s link %s\n", port, reg & MV88E6XXX_PORT_MAC_CTL_FORCE_LINK ? "Force" : "Unforce", - reg & MV88E6XXX_PORT_MAC_CTL_LINK_UP ? "up" : "down"); + str_up_down(reg & MV88E6XXX_PORT_MAC_CTL_LINK_UP)); return 0; } diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 3aa9c997018a..0a4e682a55ef 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1316,6 +1316,14 @@ static void felix_get_eth_phy_stats(struct dsa_switch *ds, int port, ocelot_port_get_eth_phy_stats(ocelot, port, phy_stats); } +static void felix_get_ts_stats(struct dsa_switch *ds, int port, + struct ethtool_ts_stats *ts_stats) +{ + struct ocelot *ocelot = ds->priv; + + ocelot_port_get_ts_stats(ocelot, port, ts_stats); +} + static void felix_get_strings(struct dsa_switch *ds, int port, u32 stringset, u8 *data) { @@ -2237,6 +2245,7 @@ static const struct dsa_switch_ops felix_switch_ops = { .get_stats64 = felix_get_stats64, .get_pause_stats = felix_get_pause_stats, .get_rmon_stats = felix_get_rmon_stats, + .get_ts_stats = felix_get_ts_stats, .get_eth_ctrl_stats = felix_get_eth_ctrl_stats, .get_eth_mac_stats = felix_get_eth_mac_stats, .get_eth_phy_stats = felix_get_eth_phy_stats, diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 59b4a7240b58..e8cb4da15dbe 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -342,7 +342,7 @@ static int qca8k_read_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) dev_queue_xmit(skb); ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, - msecs_to_jiffies(QCA8K_ETHERNET_TIMEOUT)); + QCA8K_ETHERNET_TIMEOUT); *val = mgmt_eth_data->data[0]; if (len > QCA_HDR_MGMT_DATA1_LEN) @@ -394,7 +394,7 @@ static int qca8k_write_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) dev_queue_xmit(skb); ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, - msecs_to_jiffies(QCA8K_ETHERNET_TIMEOUT)); + QCA8K_ETHERNET_TIMEOUT); ack = mgmt_eth_data->ack; @@ -1019,7 +1019,7 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv) of_get_phy_mode(port, &mode); - if (of_property_read_bool(port, "phy-handle") && + if (of_property_present(port, "phy-handle") && mode != PHY_INTERFACE_MODE_INTERNAL) external_mdio_mask |= BIT(reg); else @@ -1491,7 +1491,7 @@ static struct qca8k_pcs *pcs_to_qca8k_pcs(struct phylink_pcs *pcs) return container_of(pcs, struct qca8k_pcs, pcs); } -static void qca8k_pcs_get_state(struct phylink_pcs *pcs, +static void qca8k_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct qca8k_priv *priv = pcs_to_qca8k_pcs(pcs)->priv; @@ -2016,7 +2016,7 @@ static const struct dsa_switch_ops qca8k_switch_ops = { .get_ethtool_stats = qca8k_get_ethtool_stats, .get_sset_count = qca8k_get_sset_count, .set_ageing_time = qca8k_set_ageing_time, - .get_mac_eee = qca8k_get_mac_eee, + .support_eee = dsa_supports_eee, .set_mac_eee = qca8k_set_mac_eee, .port_enable = qca8k_port_enable, .port_disable = qca8k_port_disable, diff --git a/drivers/net/dsa/qca/qca8k-common.c b/drivers/net/dsa/qca/qca8k-common.c index 560c74c4ac3d..13005f10edb7 100644 --- a/drivers/net/dsa/qca/qca8k-common.c +++ b/drivers/net/dsa/qca/qca8k-common.c @@ -557,13 +557,6 @@ exit: return ret; } -int qca8k_get_mac_eee(struct dsa_switch *ds, int port, - struct ethtool_keee *e) -{ - /* Nothing to do on the port's MAC */ - return 0; -} - static int qca8k_port_configure_learning(struct dsa_switch *ds, int port, bool learning) { diff --git a/drivers/net/dsa/qca/qca8k.h b/drivers/net/dsa/qca/qca8k.h index 3664a2e2f1f6..d046679265fa 100644 --- a/drivers/net/dsa/qca/qca8k.h +++ b/drivers/net/dsa/qca/qca8k.h @@ -16,7 +16,7 @@ #define QCA8K_ETHERNET_MDIO_PRIORITY 7 #define QCA8K_ETHERNET_PHY_PRIORITY 6 -#define QCA8K_ETHERNET_TIMEOUT 5 +#define QCA8K_ETHERNET_TIMEOUT msecs_to_jiffies(5) #define QCA8K_NUM_PORTS 7 #define QCA8K_NUM_CPU_PORTS 2 @@ -520,7 +520,6 @@ int qca8k_get_sset_count(struct dsa_switch *ds, int port, int sset); /* Common eee function */ int qca8k_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *eee); -int qca8k_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* Common bridge function */ void qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state); diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c index 23374178a176..4c4a95d4380c 100644 --- a/drivers/net/dsa/realtek/rtl8366rb.c +++ b/drivers/net/dsa/realtek/rtl8366rb.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "realtek.h" #include "realtek-smi.h" @@ -1522,7 +1523,7 @@ static int rtl8366rb_vlan_filtering(struct dsa_switch *ds, int port, rb = priv->chip_data; dev_dbg(priv->dev, "port %d: %s VLAN filtering\n", port, - vlan_filtering ? "enable" : "disable"); + str_enable_disable(vlan_filtering)); /* If the port is not in the member set, the frame will be dropped */ ret = regmap_update_bits(priv->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, @@ -1884,7 +1885,7 @@ static bool rtl8366rb_is_vlan_valid(struct realtek_priv *priv, unsigned int vlan static int rtl8366rb_enable_vlan(struct realtek_priv *priv, bool enable) { - dev_dbg(priv->dev, "%s VLAN\n", enable ? "enable" : "disable"); + dev_dbg(priv->dev, "%s VLAN\n", str_enable_disable(enable)); return regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN, enable ? RTL8366RB_SGCR_EN_VLAN : 0); @@ -1892,7 +1893,7 @@ static int rtl8366rb_enable_vlan(struct realtek_priv *priv, bool enable) static int rtl8366rb_enable_vlan4k(struct realtek_priv *priv, bool enable) { - dev_dbg(priv->dev, "%s VLAN 4k\n", enable ? "enable" : "disable"); + dev_dbg(priv->dev, "%s VLAN 4k\n", str_enable_disable(enable)); return regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN_4KTB, enable ? RTL8366RB_SGCR_EN_VLAN_4KTB : 0); diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index baba204ad62f..3d790f8c6f4d 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -26,12 +26,8 @@ void sja1105_pack(void *buf, const u64 *val, int start, int end, size_t len) pr_err("Start bit (%d) expected to be larger than end (%d)\n", start, end); } else if (rc == -ERANGE) { - if ((start - end + 1) > 64) - pr_err("Field %d-%d too large for 64 bits!\n", - start, end); - else - pr_err("Cannot store %llx inside bits %d-%d (would truncate)\n", - *val, start, end); + pr_err("Field %d-%d too large for 64 bits!\n", + start, end); } dump_stack(); } diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 9a542e3c9b05..977b42bc1e8c 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -159,7 +159,7 @@ config ETHOC Say Y here if you want to use the OpenCores 10/100 Mbps Ethernet MAC. config OA_TC6 - tristate "OPEN Alliance TC6 10BASE-T1x MAC-PHY support" + tristate "OPEN Alliance TC6 10BASE-T1x MAC-PHY support" if COMPILE_TEST depends on SPI select PHYLIB help diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 63c8a2328142..c1295dfad0d0 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -74,7 +74,7 @@ static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue) if (threshold < time_since_last_napi && napi_scheduled) { netdev_err(dev, "napi handler hasn't been called for a long time but is scheduled\n"); - reset_reason = ENA_REGS_RESET_SUSPECTED_POLL_STARVATION; + reset_reason = ENA_REGS_RESET_SUSPECTED_POLL_STARVATION; } schedule_reset: /* Change the state of the device to trigger reset diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 72db9f9e7bee..c6bd803f5b0c 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -462,7 +462,7 @@ static void pcnet32_netif_start(struct net_device *dev) val = lp->a->read_csr(ioaddr, CSR3); val &= 0x00ff; lp->a->write_csr(ioaddr, CSR3, val); - napi_enable(&lp->napi); + napi_enable_locked(&lp->napi); } /* @@ -889,6 +889,7 @@ static int pcnet32_set_ringparam(struct net_device *dev, if (netif_running(dev)) pcnet32_netif_stop(dev); + netdev_lock(dev); spin_lock_irqsave(&lp->lock, flags); lp->a->write_csr(ioaddr, CSR0, CSR0_STOP); /* stop the chip */ @@ -920,6 +921,7 @@ static int pcnet32_set_ringparam(struct net_device *dev, } spin_unlock_irqrestore(&lp->lock, flags); + netdev_unlock(dev); netif_info(lp, drv, dev, "Ring Param Settings: RX: %d, TX: %d\n", lp->rx_ring_size, lp->tx_ring_size); @@ -985,6 +987,7 @@ static int pcnet32_loopback_test(struct net_device *dev, uint64_t * data1) if (netif_running(dev)) pcnet32_netif_stop(dev); + netdev_lock(dev); spin_lock_irqsave(&lp->lock, flags); lp->a->write_csr(ioaddr, CSR0, CSR0_STOP); /* stop the chip */ @@ -1122,6 +1125,7 @@ clean_up: lp->a->write_bcr(ioaddr, 20, 4); /* return to 16bit mode */ } spin_unlock_irqrestore(&lp->lock, flags); + netdev_unlock(dev); return rc; } /* end pcnet32_loopback_test */ @@ -2101,6 +2105,7 @@ static int pcnet32_open(struct net_device *dev) return -EAGAIN; } + netdev_lock(dev); spin_lock_irqsave(&lp->lock, flags); /* Check for a valid station address */ if (!is_valid_ether_addr(dev->dev_addr)) { @@ -2266,7 +2271,7 @@ static int pcnet32_open(struct net_device *dev) goto err_free_ring; } - napi_enable(&lp->napi); + napi_enable_locked(&lp->napi); /* Re-initialize the PCNET32, and start it when done. */ lp->a->write_csr(ioaddr, 1, (lp->init_dma_addr & 0xffff)); @@ -2300,6 +2305,7 @@ static int pcnet32_open(struct net_device *dev) lp->a->read_csr(ioaddr, CSR0)); spin_unlock_irqrestore(&lp->lock, flags); + netdev_unlock(dev); return 0; /* Always succeed */ @@ -2315,6 +2321,7 @@ err_free_ring: err_free_irq: spin_unlock_irqrestore(&lp->lock, flags); + netdev_unlock(dev); free_irq(dev->irq, dev); return rc; } diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index 2681889162a2..44971e71991f 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -118,7 +118,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, if (err && err != -EIO) return err; - listlen = fw_list.num_fw_slots; + listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names)); for (i = 0; i < listlen; i++) { if (i < ARRAY_SIZE(fw_slotnames)) strscpy(buf, fw_slotnames[i], sizeof(buf)); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index b0a6c96b6ef4..b35808d3d07f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -505,21 +505,6 @@ void xgbe_debugfs_exit(struct xgbe_prv_data *pdata) void xgbe_debugfs_rename(struct xgbe_prv_data *pdata) { - char *buf; - - if (!pdata->xgbe_debugfs) - return; - - buf = kasprintf(GFP_KERNEL, "amd-xgbe-%s", pdata->netdev->name); - if (!buf) - return; - - if (!strcmp(pdata->xgbe_debugfs->d_name.name, buf)) - goto out; - - debugfs_rename(pdata->xgbe_debugfs->d_parent, pdata->xgbe_debugfs, - pdata->xgbe_debugfs->d_parent, buf); - -out: - kfree(buf); + debugfs_change_name(pdata->xgbe_debugfs, + "amd-xgbe-%s", pdata->netdev->name); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 6a716337f48b..268399dfcf22 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -923,7 +923,6 @@ static void xgbe_phy_free_phy_device(struct xgbe_prv_data *pdata) static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, }; struct xgbe_phy_data *phy_data = pdata->phy_data; unsigned int phy_id = phy_data->phydev->phy_id; @@ -945,14 +944,7 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) phy_write(phy_data->phydev, 0x04, 0x0d01); phy_write(phy_data->phydev, 0x00, 0x9140); - linkmode_set_bit_array(phy_10_100_features_array, - ARRAY_SIZE(phy_10_100_features_array), - supported); - linkmode_set_bit_array(phy_gbit_features_array, - ARRAY_SIZE(phy_gbit_features_array), - supported); - - linkmode_copy(phy_data->phydev->supported, supported); + linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES); phy_support_asym_pause(phy_data->phydev); @@ -964,7 +956,6 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, }; struct xgbe_phy_data *phy_data = pdata->phy_data; struct xgbe_sfp_eeprom *sfp_eeprom = &phy_data->sfp_eeprom; unsigned int phy_id = phy_data->phydev->phy_id; @@ -1028,13 +1019,7 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata) reg = phy_read(phy_data->phydev, 0x00); phy_write(phy_data->phydev, 0x00, reg & ~0x00800); - linkmode_set_bit_array(phy_10_100_features_array, - ARRAY_SIZE(phy_10_100_features_array), - supported); - linkmode_set_bit_array(phy_gbit_features_array, - ARRAY_SIZE(phy_gbit_features_array), - supported); - linkmode_copy(phy_data->phydev->supported, supported); + linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES); phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index e641dbbea1e2..b854b6b42d77 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -421,18 +421,12 @@ static void xgene_enet_configure_clock(struct xgene_enet_pdata *pdata) if (dev->of_node) { struct clk *parent = clk_get_parent(pdata->clk); + long rate = rgmii_clock(pdata->phy_speed); - switch (pdata->phy_speed) { - case SPEED_10: - clk_set_rate(parent, 2500000); - break; - case SPEED_100: - clk_set_rate(parent, 25000000); - break; - default: - clk_set_rate(parent, 125000000); - break; - } + if (rate < 0) + rate = 125000000; + + clk_set_rate(parent, rate); } #ifdef CONFIG_ACPI else { diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h index f93cb3da44b0..8fc75bcedb70 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h @@ -348,8 +348,6 @@ struct bcmasp_intf { /* Used if per intf wol irq */ int wol_irq; unsigned int wol_irq_enabled:1; - - struct ethtool_keee eee; }; #define NUM_NET_FILTERS 32 @@ -601,5 +599,4 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs, void bcmasp_netfilt_suspend(struct bcmasp_intf *intf); -void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable); #endif diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c index 9da5ae29a105..a537c121d3e2 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c @@ -348,58 +348,19 @@ static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, return err; } -void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable) -{ - u32 reg; - - reg = umac_rl(intf, UMC_EEE_CTRL); - if (enable) - reg |= EEE_EN; - else - reg &= ~EEE_EN; - umac_wl(intf, reg, UMC_EEE_CTRL); - - intf->eee.eee_enabled = enable; -} - static int bcmasp_get_eee(struct net_device *dev, struct ethtool_keee *e) { - struct bcmasp_intf *intf = netdev_priv(dev); - struct ethtool_keee *p = &intf->eee; - if (!dev->phydev) return -ENODEV; - e->tx_lpi_enabled = p->tx_lpi_enabled; - e->tx_lpi_timer = umac_rl(intf, UMC_EEE_LPI_TIMER); - return phy_ethtool_get_eee(dev->phydev, e); } static int bcmasp_set_eee(struct net_device *dev, struct ethtool_keee *e) { - struct bcmasp_intf *intf = netdev_priv(dev); - struct ethtool_keee *p = &intf->eee; - int ret; - if (!dev->phydev) return -ENODEV; - if (!p->eee_enabled) { - bcmasp_eee_enable_set(intf, false); - } else { - ret = phy_init_eee(dev->phydev, 0); - if (ret) { - netif_err(intf, hw, dev, - "EEE initialization failed: %d\n", ret); - return ret; - } - - umac_wl(intf, e->tx_lpi_timer, UMC_EEE_LPI_TIMER); - intf->eee.tx_lpi_enabled = e->tx_lpi_enabled; - bcmasp_eee_enable_set(intf, true); - } - return phy_ethtool_set_eee(dev->phydev, e); } diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index cfd50efbdbc0..45ec1a9214a2 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -619,7 +619,6 @@ static void bcmasp_adj_link(struct net_device *dev) struct phy_device *phydev = dev->phydev; u32 cmd_bits = 0, reg; int changed = 0; - bool active; if (intf->old_link != phydev->link) { changed = 1; @@ -677,8 +676,13 @@ static void bcmasp_adj_link(struct net_device *dev) } umac_wl(intf, reg, UMC_CMD); - active = phy_init_eee(phydev, 0) >= 0; - bcmasp_eee_enable_set(intf, active); + umac_wl(intf, phydev->eee_cfg.tx_lpi_timer, UMC_EEE_LPI_TIMER); + reg = umac_rl(intf, UMC_EEE_CTRL); + if (phydev->enable_tx_lpi) + reg |= EEE_EN; + else + reg &= ~EEE_EN; + umac_wl(intf, reg, UMC_EEE_CTRL); } reg = rgmii_rl(intf, RGMII_OOB_CNTRL); @@ -1055,6 +1059,9 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect) /* Indicate that the MAC is responsible for PHY PM */ phydev->mac_managed_pm = true; + + /* Set phylib's copy of the LPI timer */ + phydev->eee_cfg.tx_lpi_timer = umac_rl(intf, UMC_EEE_LPI_TIMER); } umac_reset(intf); @@ -1331,7 +1338,8 @@ static void bcmasp_suspend_to_wol(struct bcmasp_intf *intf) ASP_WAKEUP_INTR2_MASK_CLEAR); } - if (intf->eee.eee_enabled && intf->parent->eee_fixup) + if (ndev->phydev && ndev->phydev->eee_cfg.eee_enabled && + intf->parent->eee_fixup) intf->parent->eee_fixup(intf, true); netif_dbg(intf, wol, ndev, "entered WOL mode\n"); @@ -1373,7 +1381,8 @@ static void bcmasp_resume_from_wol(struct bcmasp_intf *intf) { u32 reg; - if (intf->eee.eee_enabled && intf->parent->eee_fixup) + if (intf->ndev->phydev && intf->ndev->phydev->eee_cfg.eee_enabled && + intf->parent->eee_fixup) intf->parent->eee_fixup(intf, false); reg = umac_rl(intf, UMC_MPD_CTRL); @@ -1404,9 +1413,6 @@ int bcmasp_interface_resume(struct bcmasp_intf *intf) bcmasp_resume_from_wol(intf); - if (intf->eee.eee_enabled) - bcmasp_eee_enable_set(intf, true); - netif_device_attach(dev); return 0; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 42672c63f108..bc4e1f3b3752 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1933,7 +1933,11 @@ static int bcm_sysport_open(struct net_device *dev) unsigned int i; int ret; - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) { + netdev_err(dev, "could not enable priv clock\n"); + return ret; + } /* Reset UniMAC */ umac_reset(priv); @@ -2591,7 +2595,11 @@ static int bcm_sysport_probe(struct platform_device *pdev) goto err_deregister_notifier; } - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) { + dev_err(&pdev->dev, "could not enable priv clock\n"); + goto err_deregister_netdev; + } priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK; dev_info(&pdev->dev, @@ -2605,6 +2613,8 @@ static int bcm_sysport_probe(struct platform_device *pdev) return 0; +err_deregister_netdev: + unregister_netdev(dev); err_deregister_notifier: unregister_netdevice_notifier(&priv->netdev_notifier); err_deregister_fixed_link: @@ -2774,7 +2784,12 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) if (!netif_running(dev)) return 0; - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) { + netdev_err(dev, "could not enable priv clock\n"); + return ret; + } + if (priv->wolopts) clk_disable_unprepare(priv->wol_clk); diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index ecce23cecbea..4e266ce41180 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -171,6 +171,7 @@ static int platform_phy_connect(struct bgmac *bgmac) static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; + struct device_node *phy_node; struct bgmac *bgmac; struct resource *regs; int ret; @@ -236,7 +237,9 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->cco_ctl_maskset = platform_bgmac_cco_ctl_maskset; bgmac->get_bus_clock = platform_bgmac_get_bus_clock; bgmac->cmn_maskset32 = platform_bgmac_cmn_maskset32; - if (of_parse_phandle(np, "phy-handle", 0)) { + phy_node = of_parse_phandle(np, "phy-handle", 0); + if (phy_node) { + of_node_put(phy_node); bgmac->phy_connect = platform_phy_connect; } else { bgmac->phy_connect = bgmac_phy_connect_direct; diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index d73ef262991d..6fee9a41839c 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -328,8 +328,7 @@ #define BGMAC_RX_FRAME_OFFSET 30 /* There are 2 unused bytes between header and real data */ #define BGMAC_RX_BUF_OFFSET (NET_SKB_PAD + NET_IP_ALIGN - \ BGMAC_RX_FRAME_OFFSET) -/* Jumbo frame size with FCS */ -#define BGMAC_RX_MAX_FRAME_SIZE 9724 +#define BGMAC_RX_MAX_FRAME_SIZE 1536 #define BGMAC_RX_BUF_SIZE (BGMAC_RX_FRAME_OFFSET + BGMAC_RX_MAX_FRAME_SIZE) #define BGMAC_RX_ALLOC_SIZE (SKB_DATA_ALIGN(BGMAC_RX_BUF_SIZE + BGMAC_RX_BUF_OFFSET) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b86f980fa7ea..7b8b5b39c7bb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -81,7 +81,6 @@ MODULE_DESCRIPTION("Broadcom NetXtreme network driver"); #define BNXT_RX_OFFSET (NET_SKB_PAD + NET_IP_ALIGN) #define BNXT_RX_DMA_OFFSET NET_SKB_PAD -#define BNXT_RX_COPY_THRESH 256 #define BNXT_TX_PUSH_THRESH 164 @@ -1343,13 +1342,13 @@ static struct sk_buff *bnxt_copy_data(struct bnxt_napi *bnapi, u8 *data, if (!skb) return NULL; - dma_sync_single_for_cpu(&pdev->dev, mapping, bp->rx_copy_thresh, + dma_sync_single_for_cpu(&pdev->dev, mapping, bp->rx_copybreak, bp->rx_dir); memcpy(skb->data - NET_IP_ALIGN, data - NET_IP_ALIGN, len + NET_IP_ALIGN); - dma_sync_single_for_device(&pdev->dev, mapping, bp->rx_copy_thresh, + dma_sync_single_for_device(&pdev->dev, mapping, bp->rx_copybreak, bp->rx_dir); skb_put(skb, len); @@ -1842,7 +1841,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, return NULL; } - if (len <= bp->rx_copy_thresh) { + if (len <= bp->rx_copybreak) { skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping); if (!skb) { bnxt_abort_tpa(cpr, idx, agg_bufs); @@ -2176,7 +2175,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } } - if (len <= bp->rx_copy_thresh) { + if (len <= bp->rx_copybreak) { if (!xdp_active) skb = bnxt_copy_skb(bnapi, data_ptr, len, dma_addr); else @@ -2855,6 +2854,7 @@ static int bnxt_async_event_process(struct bnxt *bp, } __bnxt_queue_sp_work(bp); async_event_process_exit: + bnxt_ulp_async_events(bp, cmpl); return 0; } @@ -2897,6 +2897,13 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp) return 0; } +static bool bnxt_vnic_is_active(struct bnxt *bp) +{ + struct bnxt_vnic_info *vnic = &bp->vnic_info[0]; + + return vnic->fw_vnic_id != INVALID_HW_RING_ID && vnic->mru > 0; +} + static irqreturn_t bnxt_msix(int irq, void *dev_instance) { struct bnxt_napi *bnapi = dev_instance; @@ -3164,7 +3171,7 @@ static int bnxt_poll(struct napi_struct *napi, int budget) break; } } - if (bp->flags & BNXT_FLAG_DIM) { + if ((bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) { struct dim_sample dim_sample = {}; dim_update_sample(cpr->event_ctr, @@ -3295,7 +3302,7 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget) poll_done: cpr_rx = &cpr->cp_ring_arr[0]; if (cpr_rx->cp_ring_type == BNXT_NQ_HDL_TYPE_RX && - (bp->flags & BNXT_FLAG_DIM)) { + (bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) { struct dim_sample dim_sample = {}; dim_update_sample(cpr->event_ctr, @@ -4601,6 +4608,17 @@ void bnxt_set_tpa_flags(struct bnxt *bp) bp->flags |= BNXT_FLAG_GRO; } +static void bnxt_init_ring_params(struct bnxt *bp) +{ + unsigned int rx_size; + + bp->rx_copybreak = BNXT_DEFAULT_RX_COPYBREAK; + /* Try to fit 4 chunks into a 4k page */ + rx_size = SZ_1K - + NET_SKB_PAD - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + bp->dev->cfg->hds_thresh = max(BNXT_DEFAULT_RX_COPYBREAK, rx_size); +} + /* bp->rx_ring_size, bp->tx_ring_size, dev->mtu, BNXT_FLAG_{G|L}RO flags must * be set on entry. */ @@ -4615,12 +4633,11 @@ void bnxt_set_ring_params(struct bnxt *bp) rx_space = rx_size + ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - bp->rx_copy_thresh = BNXT_RX_COPY_THRESH; ring_size = bp->rx_ring_size; bp->rx_agg_ring_size = 0; bp->rx_agg_nr_pages = 0; - if (bp->flags & BNXT_FLAG_TPA) + if (bp->flags & BNXT_FLAG_TPA || bp->flags & BNXT_FLAG_HDS) agg_factor = min_t(u32, 4, 65536 / BNXT_RX_PAGE_SIZE); bp->flags &= ~BNXT_FLAG_JUMBO; @@ -4660,7 +4677,10 @@ void bnxt_set_ring_params(struct bnxt *bp) ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); } else { - rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN); + rx_size = max3(BNXT_DEFAULT_RX_COPYBREAK, + bp->rx_copybreak, + bp->dev->cfg_pending->hds_thresh); + rx_size = SKB_DATA_ALIGN(rx_size + NET_IP_ALIGN); rx_space = rx_size + NET_SKB_PAD + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); } @@ -4701,7 +4721,7 @@ void bnxt_set_ring_params(struct bnxt *bp) /* Changing allocation mode of RX rings. * TODO: Update when extending xdp_rxq_info to support allocation modes. */ -int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) +static void __bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) { struct net_device *dev = bp->dev; @@ -4722,15 +4742,30 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) bp->rx_skb_func = bnxt_rx_page_skb; } bp->rx_dir = DMA_BIDIRECTIONAL; - /* Disable LRO or GRO_HW */ - netdev_update_features(dev); } else { dev->max_mtu = bp->max_mtu; bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE; bp->rx_dir = DMA_FROM_DEVICE; bp->rx_skb_func = bnxt_rx_skb; } - return 0; +} + +void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) +{ + __bnxt_set_rx_skb_mode(bp, page_mode); + + if (!page_mode) { + int rx, tx; + + bnxt_get_max_rings(bp, &rx, &tx, true); + if (rx > 1) { + bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS; + bp->dev->hw_features |= NETIF_F_LRO; + } + } + + /* Update LRO and GRO_HW availability */ + netdev_update_features(bp->dev); } static void bnxt_free_vnic_attributes(struct bnxt *bp) @@ -6557,6 +6592,7 @@ static void bnxt_hwrm_update_rss_hash_cfg(struct bnxt *bp) static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic) { + u16 hds_thresh = (u16)bp->dev->cfg_pending->hds_thresh; struct hwrm_vnic_plcmodes_cfg_input *req; int rc; @@ -6566,16 +6602,14 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic) req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT); req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID); + req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size); - if (BNXT_RX_PAGE_MODE(bp)) { - req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size); - } else { + if (!BNXT_RX_PAGE_MODE(bp) && (bp->flags & BNXT_FLAG_AGG_RINGS)) { req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 | VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6); req->enables |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID); - req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh); - req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh); + req->hds_threshold = cpu_to_le16(hds_thresh); } req->vnic_id = cpu_to_le32(vnic->fw_vnic_id); return hwrm_req_send(bp, req); @@ -7266,6 +7300,26 @@ err_out: return rc; } +static void bnxt_cancel_dim(struct bnxt *bp) +{ + int i; + + /* DIM work is initialized in bnxt_enable_napi(). Proceed only + * if NAPI is enabled. + */ + if (!bp->bnapi || test_bit(BNXT_STATE_NAPI_DISABLED, &bp->state)) + return; + + /* Make sure NAPI sees that the VNIC is disabled */ + synchronize_net(); + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct bnxt_napi *bnapi = rxr->bnapi; + + cancel_work_sync(&bnapi->cp_ring.dim.work); + } +} + static int hwrm_ring_free_send_msg(struct bnxt *bp, struct bnxt_ring_struct *ring, u32 ring_type, int cmpl_ring_id) @@ -7366,6 +7420,7 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) } } + bnxt_cancel_dim(bp); for (i = 0; i < bp->rx_nr_rings; i++) { bnxt_hwrm_rx_ring_free(bp, &bp->rx_ring[i], close_path); bnxt_hwrm_rx_agg_ring_free(bp, &bp->rx_ring[i], close_path); @@ -8279,16 +8334,20 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) if (rc) goto func_qcfg_exit; + flags = le16_to_cpu(resp->flags); #ifdef CONFIG_BNXT_SRIOV if (BNXT_VF(bp)) { struct bnxt_vf_info *vf = &bp->vf; vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK; + if (flags & FUNC_QCFG_RESP_FLAGS_TRUSTED_VF) + vf->flags |= BNXT_VF_TRUST; + else + vf->flags &= ~BNXT_VF_TRUST; } else { bp->pf.registered_vfs = le16_to_cpu(resp->registered_vfs); } #endif - flags = le16_to_cpu(resp->flags); if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED | FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED)) { bp->fw_cap |= BNXT_FW_CAP_LLDP_AGENT; @@ -9117,10 +9176,18 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp) ena = 0; if ((bp->flags & BNXT_FLAG_ROCE_CAP) && !is_kdump_kernel()) { pg_lvl = 2; - extra_qps = min_t(u32, 65536, max_qps - l2_qps - qp1_qps); - /* allocate extra qps if fw supports RoCE fast qp destroy feature */ - extra_qps += fast_qpmd_qps; - extra_srqs = min_t(u32, 8192, max_srqs - srqs); + if (BNXT_SW_RES_LMT(bp)) { + extra_qps = max_qps - l2_qps - qp1_qps; + extra_srqs = max_srqs - srqs; + } else { + extra_qps = min_t(u32, 65536, + max_qps - l2_qps - qp1_qps); + /* allocate extra qps if fw supports RoCE fast qp + * destroy feature + */ + extra_qps += fast_qpmd_qps; + extra_srqs = min_t(u32, 8192, max_srqs - srqs); + } if (fast_qpmd_qps) ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD; } @@ -9156,14 +9223,20 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp) goto skip_rdma; ctxm = &ctx->ctx_arr[BNXT_CTX_MRAV]; - /* 128K extra is needed to accommodate static AH context - * allocation by f/w. - */ - num_mr = min_t(u32, ctxm->max_entries / 2, 1024 * 256); - num_ah = min_t(u32, num_mr, 1024 * 128); - ctxm->split_entry_cnt = BNXT_CTX_MRAV_AV_SPLIT_ENTRY + 1; - if (!ctxm->mrav_av_entries || ctxm->mrav_av_entries > num_ah) - ctxm->mrav_av_entries = num_ah; + if (BNXT_SW_RES_LMT(bp) && + ctxm->split_entry_cnt == BNXT_CTX_MRAV_AV_SPLIT_ENTRY + 1) { + num_ah = ctxm->mrav_av_entries; + num_mr = ctxm->max_entries - num_ah; + } else { + /* 128K extra is needed to accommodate static AH context + * allocation by f/w. + */ + num_mr = min_t(u32, ctxm->max_entries / 2, 1024 * 256); + num_ah = min_t(u32, num_mr, 1024 * 128); + ctxm->split_entry_cnt = BNXT_CTX_MRAV_AV_SPLIT_ENTRY + 1; + if (!ctxm->mrav_av_entries || ctxm->mrav_av_entries > num_ah) + ctxm->mrav_av_entries = num_ah; + } rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, num_mr + num_ah, 2); if (rc) @@ -9470,6 +9543,9 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->flags |= BNXT_FLAG_UDP_GSO_CAP; if (flags_ext2 & FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED) bp->fw_cap |= BNXT_FW_CAP_TX_TS_CMP; + if (flags_ext2 & + FUNC_QCAPS_RESP_FLAGS_EXT2_SW_MAX_RESOURCE_LIMITS_SUPPORTED) + bp->fw_cap |= BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS; if (BNXT_PF(bp) && (flags_ext2 & FUNC_QCAPS_RESP_FLAGS_EXT2_ROCE_VF_RESOURCE_MGMT_SUPPORTED)) bp->fw_cap |= BNXT_FW_CAP_ROCE_VF_RESC_MGMT_SUPPORTED; @@ -11309,8 +11385,6 @@ static void bnxt_disable_napi(struct bnxt *bp) if (bnapi->in_reset) cpr->sw_stats->rx.rx_resets++; napi_disable(&bnapi->napi); - if (bnapi->rx_ring) - cancel_work_sync(&cpr->dim.work); } } @@ -11530,6 +11604,26 @@ hwrm_phy_qcaps_exit: return rc; } +static void bnxt_hwrm_mac_qcaps(struct bnxt *bp) +{ + struct hwrm_port_mac_qcaps_output *resp; + struct hwrm_port_mac_qcaps_input *req; + int rc; + + if (bp->hwrm_spec_code < 0x10a03) + return; + + rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_QCAPS); + if (rc) + return; + + resp = hwrm_req_hold(bp, req); + rc = hwrm_req_send_silent(bp, req); + if (!rc) + bp->mac_flags = resp->flags; + hwrm_req_drop(bp, req); +} + static bool bnxt_support_dropped(u16 advertising, u16 supported) { u16 diff = advertising ^ supported; @@ -15572,8 +15666,10 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) bnxt_hwrm_vnic_update(bp, vnic, VNIC_UPDATE_REQ_ENABLES_MRU_VALID); } - + /* Make sure NAPI sees that the VNIC is disabled */ + synchronize_net(); rxr = &bp->rx_ring[idx]; + cancel_work_sync(&rxr->bnapi->cp_ring.dim.work); bnxt_hwrm_rx_ring_free(bp, rxr, false); bnxt_hwrm_rx_agg_ring_free(bp, rxr, false); rxr->rx_next_cons = 0; @@ -15658,6 +15754,10 @@ static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt) bp->dev->priv_flags |= IFF_SUPP_NOFCS; else bp->dev->priv_flags &= ~IFF_SUPP_NOFCS; + + bp->mac_flags = 0; + bnxt_hwrm_mac_qcaps(bp); + if (!fw_dflt) return 0; @@ -16186,8 +16286,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (bp->max_fltr < BNXT_MAX_FLTR) bp->max_fltr = BNXT_MAX_FLTR; bnxt_init_l2_fltr_tbl(bp); - bnxt_set_rx_skb_mode(bp, false); + __bnxt_set_rx_skb_mode(bp, false); bnxt_set_tpa_flags(bp); + bnxt_init_ring_params(bp); bnxt_set_ring_params(bp); bnxt_rdma_aux_device_init(bp); rc = bnxt_set_dflt_rings(bp, true); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 7df7a2233307..2373f423a523 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -34,6 +34,9 @@ #include #endif +#define BNXT_DEFAULT_RX_COPYBREAK 256 +#define BNXT_MAX_RX_COPYBREAK 1024 + extern struct list_head bnxt_block_cb_list; struct page_pool; @@ -2241,8 +2244,6 @@ struct bnxt { #define BNXT_FLAG_TPA (BNXT_FLAG_LRO | BNXT_FLAG_GRO) #define BNXT_FLAG_JUMBO 0x10 #define BNXT_FLAG_STRIP_VLAN 0x20 - #define BNXT_FLAG_AGG_RINGS (BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \ - BNXT_FLAG_LRO) #define BNXT_FLAG_RFS 0x100 #define BNXT_FLAG_SHARED_RINGS 0x200 #define BNXT_FLAG_PORT_STATS 0x400 @@ -2263,6 +2264,9 @@ struct bnxt { #define BNXT_FLAG_ROCE_MIRROR_CAP 0x4000000 #define BNXT_FLAG_TX_COAL_CMPL 0x8000000 #define BNXT_FLAG_PORT_STATS_EXT 0x10000000 + #define BNXT_FLAG_HDS 0x20000000 + #define BNXT_FLAG_AGG_RINGS (BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \ + BNXT_FLAG_LRO | BNXT_FLAG_HDS) #define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \ BNXT_FLAG_RFS | \ @@ -2270,6 +2274,11 @@ struct bnxt { #define BNXT_PF(bp) (!((bp)->flags & BNXT_FLAG_VF)) #define BNXT_VF(bp) ((bp)->flags & BNXT_FLAG_VF) +#ifdef CONFIG_BNXT_SRIOV +#define BNXT_VF_IS_TRUSTED(bp) ((bp)->vf.flags & BNXT_VF_TRUST) +#else +#define BNXT_VF_IS_TRUSTED(bp) 0 +#endif #define BNXT_NPAR(bp) ((bp)->port_partition_type) #define BNXT_MH(bp) ((bp)->flags & BNXT_FLAG_MULTI_HOST) #define BNXT_SINGLE_PF(bp) (BNXT_PF(bp) && !BNXT_NPAR(bp) && !BNXT_MH(bp)) @@ -2342,7 +2351,7 @@ struct bnxt { enum dma_data_direction rx_dir; u32 rx_ring_size; u32 rx_agg_ring_size; - u32 rx_copy_thresh; + u32 rx_copybreak; u32 rx_ring_mask; u32 rx_agg_ring_mask; int rx_nr_pages; @@ -2482,6 +2491,7 @@ struct bnxt { #define BNXT_FW_CAP_CFA_NTUPLE_RX_EXT_IP_PROTO BIT_ULL(38) #define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3 BIT_ULL(39) #define BNXT_FW_CAP_VNIC_RE_FLUSH BIT_ULL(40) + #define BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS BIT_ULL(41) u32 fw_dbg_cap; @@ -2501,6 +2511,8 @@ struct bnxt { ((bp)->fw_cap & BNXT_FW_CAP_ENABLE_RDMA_SRIOV) #define BNXT_ROCE_VF_RESC_CAP(bp) \ ((bp)->fw_cap & BNXT_FW_CAP_ROCE_VF_RESC_MGMT_SUPPORTED) +#define BNXT_SW_RES_LMT(bp) \ + ((bp)->fw_cap & BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS) u32 hwrm_spec_code; u16 hwrm_cmd_seq; @@ -2660,6 +2672,11 @@ struct bnxt { #define BNXT_PHY_FL_BANK_SEL (PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED << 8) #define BNXT_PHY_FL_SPEEDS2 (PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED << 8) + /* copied from flags in hwrm_port_mac_qcaps_output */ + u8 mac_flags; +#define BNXT_MAC_FL_NO_MAC_LPBK \ + PORT_MAC_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED + u8 num_tests; struct bnxt_test_info *test_info; @@ -2762,6 +2779,8 @@ struct bnxt { #define SFF_MODULE_ID_QSFP28 0x11 #define BNXT_MAX_PHY_I2C_RESP_SIZE 64 +#define BNXT_HDS_THRESHOLD_MAX 1023 + static inline u32 bnxt_tx_avail(struct bnxt *bp, const struct bnxt_tx_ring_info *txr) { @@ -2846,7 +2865,7 @@ u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx); bool bnxt_bs_trace_avail(struct bnxt *bp, u16 type); void bnxt_set_tpa_flags(struct bnxt *bp); void bnxt_set_ring_params(struct bnxt *); -int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode); +void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode); void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index d87681d71106..9c5820839514 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include "bnxt_hsi.h" #include "bnxt.h" @@ -833,6 +834,8 @@ static void bnxt_get_ringparam(struct net_device *dev, ering->rx_pending = bp->rx_ring_size; ering->rx_jumbo_pending = bp->rx_agg_ring_size; ering->tx_pending = bp->tx_ring_size; + + kernel_ering->hds_thresh_max = BNXT_HDS_THRESHOLD_MAX; } static int bnxt_set_ringparam(struct net_device *dev, @@ -840,16 +843,35 @@ static int bnxt_set_ringparam(struct net_device *dev, struct kernel_ethtool_ringparam *kernel_ering, struct netlink_ext_ack *extack) { + u8 tcp_data_split = kernel_ering->tcp_data_split; struct bnxt *bp = netdev_priv(dev); + u8 hds_config_mod; if ((ering->rx_pending > BNXT_MAX_RX_DESC_CNT) || (ering->tx_pending > BNXT_MAX_TX_DESC_CNT) || (ering->tx_pending < BNXT_MIN_TX_DESC_CNT)) return -EINVAL; + hds_config_mod = tcp_data_split != dev->cfg->hds_config; + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_DISABLED && hds_config_mod) + return -EINVAL; + + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + hds_config_mod && BNXT_RX_PAGE_MODE(bp)) { + NL_SET_ERR_MSG_MOD(extack, "tcp-data-split is disallowed when XDP is attached"); + return -EINVAL; + } + if (netif_running(dev)) bnxt_close_nic(bp, false, false); + if (hds_config_mod) { + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED) + bp->flags |= BNXT_FLAG_HDS; + else if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN) + bp->flags &= ~BNXT_FLAG_HDS; + } + bp->rx_ring_size = ering->rx_pending; bp->tx_ring_size = ering->tx_pending; bnxt_set_ring_params(bp); @@ -2050,7 +2072,8 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs, int rc; regs->version = 0; - bnxt_dbg_hwrm_rd_reg(bp, 0, BNXT_PXP_REG_LEN / 4, _p); + if (!(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_REG_ACCESS_RESTRICTED)) + bnxt_dbg_hwrm_rd_reg(bp, 0, BNXT_PXP_REG_LEN / 4, _p); if (!(bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED)) return; @@ -4161,7 +4184,7 @@ err: static void bnxt_get_pkgver(struct net_device *dev) { struct bnxt *bp = netdev_priv(dev); - char buf[FW_VER_STR_LEN]; + char buf[FW_VER_STR_LEN - 5]; int len; if (!bnxt_get_pkginfo(dev, buf, sizeof(buf))) { @@ -4327,6 +4350,45 @@ static int bnxt_get_eee(struct net_device *dev, struct ethtool_keee *edata) return 0; } +static int bnxt_set_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, + const void *data) +{ + struct bnxt *bp = netdev_priv(dev); + u32 rx_copybreak; + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + rx_copybreak = *(u32 *)data; + if (rx_copybreak > BNXT_MAX_RX_COPYBREAK) + return -ERANGE; + if (rx_copybreak != bp->rx_copybreak) { + if (netif_running(dev)) + return -EBUSY; + bp->rx_copybreak = rx_copybreak; + } + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int bnxt_get_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, void *data) +{ + struct bnxt *bp = netdev_priv(dev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)data = bp->rx_copybreak; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + static int bnxt_read_sfp_module_eeprom_info(struct bnxt *bp, u16 i2c_addr, u16 page_number, u8 bank, u16 start_addr, u16 data_length, @@ -4375,6 +4437,9 @@ static int bnxt_get_module_info(struct net_device *dev, struct bnxt *bp = netdev_priv(dev); int rc; + if (BNXT_VF(bp) && !BNXT_VF_IS_TRUSTED(bp)) + return -EPERM; + /* No point in going further if phy status indicates * module is not inserted or if it is powered down or * if it is of type 10GBase-T @@ -4426,6 +4491,9 @@ static int bnxt_get_module_eeprom(struct net_device *dev, u16 start = eeprom->offset, length = eeprom->len; int rc = 0; + if (BNXT_VF(bp) && !BNXT_VF_IS_TRUSTED(bp)) + return -EPERM; + memset(data, 0, eeprom->len); /* Read A0 portion of the EEPROM */ @@ -4480,6 +4548,12 @@ static int bnxt_get_module_eeprom_by_page(struct net_device *dev, struct bnxt *bp = netdev_priv(dev); int rc; + if (BNXT_VF(bp) && !BNXT_VF_IS_TRUSTED(bp)) { + NL_SET_ERR_MSG_MOD(extack, + "Module read not permitted on untrusted VF"); + return -EPERM; + } + rc = bnxt_get_module_status(bp, extack); if (rc) return rc; @@ -4777,7 +4851,8 @@ static int bnxt_run_loopback(struct bnxt *bp) cpr = &rxr->bnapi->cp_ring; if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) cpr = rxr->rx_cpr; - pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh); + pkt_size = min(bp->dev->mtu + ETH_HLEN, max(BNXT_DEFAULT_RX_COPYBREAK, + bp->rx_copybreak)); skb = netdev_alloc_skb(bp->dev, pkt_size); if (!skb) return -ENOMEM; @@ -4887,35 +4962,44 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, bnxt_close_nic(bp, true, false); bnxt_run_fw_tests(bp, test_mask, &test_results); - buf[BNXT_MACLPBK_TEST_IDX] = 1; - bnxt_hwrm_mac_loopback(bp, true); - msleep(250); rc = bnxt_half_open_nic(bp); if (rc) { - bnxt_hwrm_mac_loopback(bp, false); etest->flags |= ETH_TEST_FL_FAILED; return; } + buf[BNXT_MACLPBK_TEST_IDX] = 1; + if (bp->mac_flags & BNXT_MAC_FL_NO_MAC_LPBK) + goto skip_mac_loopback; + + bnxt_hwrm_mac_loopback(bp, true); + msleep(250); if (bnxt_run_loopback(bp)) etest->flags |= ETH_TEST_FL_FAILED; else buf[BNXT_MACLPBK_TEST_IDX] = 0; bnxt_hwrm_mac_loopback(bp, false); +skip_mac_loopback: + buf[BNXT_PHYLPBK_TEST_IDX] = 1; + if (bp->phy_flags & BNXT_PHY_FL_NO_PHY_LPBK) + goto skip_phy_loopback; + bnxt_hwrm_phy_loopback(bp, true, false); msleep(1000); - if (bnxt_run_loopback(bp)) { - buf[BNXT_PHYLPBK_TEST_IDX] = 1; + if (bnxt_run_loopback(bp)) etest->flags |= ETH_TEST_FL_FAILED; - } + else + buf[BNXT_PHYLPBK_TEST_IDX] = 0; +skip_phy_loopback: + buf[BNXT_EXTLPBK_TEST_IDX] = 1; if (do_ext_lpbk) { etest->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE; bnxt_hwrm_phy_loopback(bp, true, true); msleep(1000); - if (bnxt_run_loopback(bp)) { - buf[BNXT_EXTLPBK_TEST_IDX] = 1; + if (bnxt_run_loopback(bp)) etest->flags |= ETH_TEST_FL_FAILED; - } + else + buf[BNXT_EXTLPBK_TEST_IDX] = 0; } bnxt_hwrm_phy_loopback(bp, false, false); bnxt_half_close_nic(bp); @@ -5309,6 +5393,8 @@ const struct ethtool_ops bnxt_ethtool_ops = { ETHTOOL_COALESCE_STATS_BLOCK_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX | ETHTOOL_COALESCE_USE_CQE, + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT | + ETHTOOL_RING_USE_HDS_THRS, .get_link_ksettings = bnxt_get_link_ksettings, .set_link_ksettings = bnxt_set_link_ksettings, .get_fec_stats = bnxt_get_fec_stats, @@ -5350,6 +5436,8 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_link_ext_stats = bnxt_get_link_ext_stats, .get_eee = bnxt_get_eee, .set_eee = bnxt_set_eee, + .get_tunable = bnxt_get_tunable, + .set_tunable = bnxt_set_tunable, .get_module_info = bnxt_get_module_info, .get_module_eeprom = bnxt_get_module_eeprom, .get_module_eeprom_by_page = bnxt_get_module_eeprom_by_page, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index b771c84cdd89..e4a7f37036ed 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -208,7 +208,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev, rc = hwrm_req_replace(bp, req, fw_msg->msg, fw_msg->msg_len); if (rc) - return rc; + goto drop_req; hwrm_req_timeout(bp, req, fw_msg->timeout); resp = hwrm_req_hold(bp, req); @@ -220,6 +220,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev, memcpy(fw_msg->resp, resp, resp_len); } +drop_req: hwrm_req_drop(bp, req); return rc; } @@ -297,6 +298,7 @@ void bnxt_ulp_irq_stop(struct bnxt *bp) { struct bnxt_en_dev *edev = bp->edev; struct bnxt_ulp_ops *ops; + bool reset = false; if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) return; @@ -310,7 +312,9 @@ void bnxt_ulp_irq_stop(struct bnxt *bp) ops = rtnl_dereference(ulp->ulp_ops); if (!ops || !ops->ulp_irq_stop) return; - ops->ulp_irq_stop(ulp->handle); + if (test_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) + reset = true; + ops->ulp_irq_stop(ulp->handle, reset); } } @@ -345,9 +349,36 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err) } } -int bnxt_register_async_events(struct bnxt_en_dev *edev, - unsigned long *events_bmap, - u16 max_id) +void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl) +{ + u16 event_id = le16_to_cpu(cmpl->event_id); + struct bnxt_en_dev *edev = bp->edev; + struct bnxt_ulp_ops *ops; + struct bnxt_ulp *ulp; + + if (!bnxt_ulp_registered(edev)) + return; + ulp = edev->ulp_tbl; + + rcu_read_lock(); + + ops = rcu_dereference(ulp->ulp_ops); + if (!ops || !ops->ulp_async_notifier) + goto exit_unlock_rcu; + if (!ulp->async_events_bmap || event_id > ulp->max_async_event_id) + goto exit_unlock_rcu; + + /* Read max_async_event_id first before testing the bitmap. */ + smp_rmb(); + + if (test_bit(event_id, ulp->async_events_bmap)) + ops->ulp_async_notifier(ulp->handle, cmpl); +exit_unlock_rcu: + rcu_read_unlock(); +} + +void bnxt_register_async_events(struct bnxt_en_dev *edev, + unsigned long *events_bmap, u16 max_id) { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); @@ -359,7 +390,6 @@ int bnxt_register_async_events(struct bnxt_en_dev *edev, smp_wmb(); ulp->max_async_event_id = max_id; bnxt_hwrm_func_drv_rgtr(bp, events_bmap, max_id + 1, true); - return 0; } EXPORT_SYMBOL(bnxt_register_async_events); @@ -416,6 +446,8 @@ static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp) edev->flags |= BNXT_EN_FLAG_VF; if (BNXT_ROCE_VF_RESC_CAP(bp)) edev->flags |= BNXT_EN_FLAG_ROCE_VF_RES_MGMT; + if (BNXT_SW_RES_LMT(bp)) + edev->flags |= BNXT_EN_FLAG_SW_RES_LMT; edev->chip_num = bp->chip_num; edev->hw_ring_stats_size = bp->hw_ring_stats_size; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h index 5d6aac60f236..7fa3b8d1ebd2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h @@ -30,7 +30,9 @@ struct bnxt_msix_entry { }; struct bnxt_ulp_ops { - void (*ulp_irq_stop)(void *); + /* async_notifier() cannot sleep (in BH context) */ + void (*ulp_async_notifier)(void *, struct hwrm_async_event_cmpl *); + void (*ulp_irq_stop)(void *, bool); void (*ulp_irq_restart)(void *, struct bnxt_msix_entry *); }; @@ -65,6 +67,8 @@ struct bnxt_en_dev { #define BNXT_EN_FLAG_VF 0x10 #define BNXT_EN_VF(edev) ((edev)->flags & BNXT_EN_FLAG_VF) #define BNXT_EN_FLAG_ROCE_VF_RES_MGMT 0x20 + #define BNXT_EN_FLAG_SW_RES_LMT 0x40 +#define BNXT_EN_SW_RES_LMT(edev) ((edev)->flags & BNXT_EN_FLAG_SW_RES_LMT) struct bnxt_ulp *ulp_tbl; int l2_db_size; /* Doorbell BAR size in @@ -124,6 +128,6 @@ int bnxt_register_dev(struct bnxt_en_dev *edev, struct bnxt_ulp_ops *ulp_ops, void *handle); void bnxt_unregister_dev(struct bnxt_en_dev *edev); int bnxt_send_msg(struct bnxt_en_dev *edev, struct bnxt_fw_msg *fw_msg); -int bnxt_register_async_events(struct bnxt_en_dev *edev, - unsigned long *events_bmap, u16 max_id); +void bnxt_register_async_events(struct bnxt_en_dev *edev, + unsigned long *events_bmap, u16 max_id); #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index f88b641533fc..e6c64e4bd66c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -395,6 +395,10 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) bp->dev->mtu, BNXT_MAX_PAGE_MODE_MTU); return -EOPNOTSUPP; } + if (prog && bp->flags & BNXT_FLAG_HDS) { + netdev_warn(dev, "XDP is disallowed when HDS is enabled.\n"); + return -EOPNOTSUPP; + } if (!(bp->flags & BNXT_FLAG_SHARED_RINGS)) { netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n"); return -EOPNOTSUPP; @@ -422,15 +426,8 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) bnxt_set_rx_skb_mode(bp, true); xdp_features_set_redirect_target(dev, true); } else { - int rx, tx; - xdp_features_clear_redirect_target(dev); bnxt_set_rx_skb_mode(bp, false); - bnxt_get_max_rings(bp, &rx, &tx, true); - if (rx > 1) { - bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS; - bp->dev->hw_features |= NETIF_F_LRO; - } } bp->tx_nr_rings_xdp = tx_xdp; bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 9cc8db10a8d6..1c94bf1db718 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -7424,7 +7424,7 @@ static void tg3_napi_enable(struct tg3 *tp) for (i = 0; i < tp->irq_cnt; i++) { tnapi = &tp->napi[i]; - napi_enable(&tnapi->napi); + napi_enable_locked(&tnapi->napi); if (tnapi->tx_buffers) { netif_queue_set_napi(tp->dev, txq_idx, NETDEV_QUEUE_TYPE_TX, @@ -7445,9 +7445,10 @@ static void tg3_napi_init(struct tg3 *tp) int i; for (i = 0; i < tp->irq_cnt; i++) { - netif_napi_add(tp->dev, &tp->napi[i].napi, - i ? tg3_poll_msix : tg3_poll); - netif_napi_set_irq(&tp->napi[i].napi, tp->napi[i].irq_vec); + netif_napi_add_locked(tp->dev, &tp->napi[i].napi, + i ? tg3_poll_msix : tg3_poll); + netif_napi_set_irq_locked(&tp->napi[i].napi, + tp->napi[i].irq_vec); } } @@ -11259,6 +11260,8 @@ static void tg3_timer_stop(struct tg3 *tp) static int tg3_restart_hw(struct tg3 *tp, bool reset_phy) __releases(tp->lock) __acquires(tp->lock) + __releases(tp->dev->lock) + __acquires(tp->dev->lock) { int err; @@ -11271,7 +11274,9 @@ static int tg3_restart_hw(struct tg3 *tp, bool reset_phy) tg3_timer_stop(tp); tp->irq_sync = 0; tg3_napi_enable(tp); + netdev_unlock(tp->dev); dev_close(tp->dev); + netdev_lock(tp->dev); tg3_full_lock(tp, 0); } return err; @@ -11299,6 +11304,7 @@ static void tg3_reset_task(struct work_struct *work) tg3_netif_stop(tp); + netdev_lock(tp->dev); tg3_full_lock(tp, 1); if (tg3_flag(tp, TX_RECOVERY_PENDING)) { @@ -11318,12 +11324,14 @@ static void tg3_reset_task(struct work_struct *work) * call cancel_work_sync() and wait forever. */ tg3_flag_clear(tp, RESET_TASK_PENDING); + netdev_unlock(tp->dev); dev_close(tp->dev); goto out; } tg3_netif_start(tp); tg3_full_unlock(tp); + netdev_unlock(tp->dev); tg3_phy_start(tp); tg3_flag_clear(tp, RESET_TASK_PENDING); out: @@ -11683,9 +11691,11 @@ static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq, if (err) goto out_ints_fini; + netdev_lock(dev); tg3_napi_init(tp); tg3_napi_enable(tp); + netdev_unlock(dev); for (i = 0; i < tp->irq_cnt; i++) { err = tg3_request_irq(tp, i); @@ -12569,6 +12579,7 @@ static int tg3_set_ringparam(struct net_device *dev, irq_sync = 1; } + netdev_lock(dev); tg3_full_lock(tp, irq_sync); tp->rx_pending = ering->rx_pending; @@ -12597,6 +12608,7 @@ static int tg3_set_ringparam(struct net_device *dev, } tg3_full_unlock(tp); + netdev_unlock(dev); if (irq_sync && !err) tg3_phy_start(tp); @@ -12678,6 +12690,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam irq_sync = 1; } + netdev_lock(dev); tg3_full_lock(tp, irq_sync); if (epause->autoneg) @@ -12707,6 +12720,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam } tg3_full_unlock(tp); + netdev_unlock(dev); } tp->phy_flags |= TG3_PHYFLG_USER_CONFIGURED; @@ -13911,6 +13925,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest, data[TG3_INTERRUPT_TEST] = 1; } + netdev_lock(dev); tg3_full_lock(tp, 0); tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); @@ -13922,6 +13937,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest, } tg3_full_unlock(tp); + netdev_unlock(dev); if (irq_sync && !err2) tg3_phy_start(tp); @@ -14365,6 +14381,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu) tg3_set_mtu(dev, tp, new_mtu); + netdev_lock(dev); tg3_full_lock(tp, 1); tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); @@ -14384,6 +14401,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu) tg3_netif_start(tp); tg3_full_unlock(tp); + netdev_unlock(dev); if (!err) tg3_phy_start(tp); @@ -18164,6 +18182,7 @@ static int tg3_resume(struct device *device) netif_device_attach(dev); + netdev_lock(dev); tg3_full_lock(tp, 0); tg3_ape_driver_state_change(tp, RESET_KIND_INIT); @@ -18180,6 +18199,7 @@ static int tg3_resume(struct device *device) out: tg3_full_unlock(tp); + netdev_unlock(dev); if (!err) tg3_phy_start(tp); @@ -18260,7 +18280,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, done: if (state == pci_channel_io_perm_failure) { if (netdev) { + netdev_lock(netdev); tg3_napi_enable(tp); + netdev_unlock(netdev); dev_close(netdev); } err = PCI_ERS_RESULT_DISCONNECT; @@ -18314,7 +18336,9 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev) done: if (rc != PCI_ERS_RESULT_RECOVERED && netdev && netif_running(netdev)) { + netdev_lock(netdev); tg3_napi_enable(tp); + netdev_unlock(netdev); dev_close(netdev); } rtnl_unlock(); @@ -18340,12 +18364,14 @@ static void tg3_io_resume(struct pci_dev *pdev) if (!netdev || !netif_running(netdev)) goto done; + netdev_lock(netdev); tg3_full_lock(tp, 0); tg3_ape_driver_state_change(tp, RESET_KIND_INIT); tg3_flag_set(tp, INIT_COMPLETE); err = tg3_restart_hw(tp, true); if (err) { tg3_full_unlock(tp); + netdev_unlock(netdev); netdev_err(netdev, "Cannot restart hardware after reset.\n"); goto done; } @@ -18357,6 +18383,7 @@ static void tg3_io_resume(struct pci_dev *pdev) tg3_netif_start(tp); tg3_full_unlock(tp); + netdev_unlock(netdev); tg3_phy_start(tp); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index daa416fb1724..48496209fb16 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -530,19 +530,9 @@ static void macb_set_tx_clk(struct macb *bp, int speed) if (bp->phy_interface == PHY_INTERFACE_MODE_MII) return; - switch (speed) { - case SPEED_10: - rate = 2500000; - break; - case SPEED_100: - rate = 25000000; - break; - case SPEED_1000: - rate = 125000000; - break; - default: + rate = rgmii_clock(speed); + if (rate < 0) return; - } rate_rounded = clk_round_rate(bp->tx_clk, rate); if (rate_rounded < 0) @@ -578,6 +568,7 @@ static void macb_usx_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, } static void macb_usx_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct macb *bp = container_of(pcs, struct macb, phylink_usx_pcs); @@ -608,7 +599,7 @@ static int macb_usx_pcs_config(struct phylink_pcs *pcs, return 0; } -static void macb_pcs_get_state(struct phylink_pcs *pcs, +static void macb_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { state->link = 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index bc3af0054406..2f0b3e389e62 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1799,7 +1799,10 @@ void cxgb4_remove_tid(struct tid_info *t, unsigned int chan, unsigned int tid, struct adapter *adap = container_of(t, struct adapter, tids); struct sk_buff *skb; - WARN_ON(tid_out_of_range(&adap->tids, tid)); + if (tid_out_of_range(&adap->tids, tid)) { + dev_err(adap->pdev_dev, "tid %d out of range\n", tid); + return; + } if (t->tid_tab[tid - adap->tids.tid_base]) { t->tid_tab[tid - adap->tids.tid_base] = NULL; @@ -6559,6 +6562,9 @@ static void cxgb4_advance_esn_state(struct xfrm_state *x) { struct adapter *adap = netdev2adap(x->xso.dev); + if (x->xso.dir != XFRM_DEV_OFFLOAD_IN) + return; + if (!mutex_trylock(&uld_mutex)) { dev_dbg(adap->pdev_dev, "crypto uld critical resource is under use\n"); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c index 96fd31d75dfd..daa1ebaef511 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c @@ -346,8 +346,9 @@ static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl, * driver. Once driver synthesizes cpl_pass_accept_req the skb will go * through the regular cpl_pass_accept_req processing in TOM. */ - skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) - - pktshift, GFP_ATOMIC); + skb = alloc_skb(size_add(gl->tot_len, + sizeof(struct cpl_pass_accept_req)) - + pktshift, GFP_ATOMIC); if (unlikely(!skb)) return NULL; __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 9913952ccb42..49f6cab01ed5 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -109,7 +109,7 @@ static struct enic_intr_mod_table mod_table[ENIC_MAX_COALESCE_TIMERS + 1] = { static struct enic_intr_mod_range mod_range[ENIC_MAX_LINK_SPEEDS] = { {0, 0}, /* 0 - 4 Gbps */ {0, 3}, /* 4 - 10 Gbps */ - {3, 6}, /* 10 - 40 Gbps */ + {3, 6}, /* 10+ Gbps */ }; static void enic_init_affinity_hint(struct enic *enic) @@ -428,6 +428,36 @@ static void enic_mtu_check(struct enic *enic) } } +static void enic_set_rx_coal_setting(struct enic *enic) +{ + unsigned int speed; + int index = -1; + struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting; + + /* 1. Read the link speed from fw + * 2. Pick the default range for the speed + * 3. Update it in enic->rx_coalesce_setting + */ + speed = vnic_dev_port_speed(enic->vdev); + if (speed > ENIC_LINK_SPEED_10G) + index = ENIC_LINK_40G_INDEX; + else if (speed > ENIC_LINK_SPEED_4G) + index = ENIC_LINK_10G_INDEX; + else + index = ENIC_LINK_4G_INDEX; + + rx_coal->small_pkt_range_start = mod_range[index].small_pkt_range_start; + rx_coal->large_pkt_range_start = mod_range[index].large_pkt_range_start; + rx_coal->range_end = ENIC_RX_COALESCE_RANGE_END; + + /* Start with the value provided by UCSM */ + for (index = 0; index < enic->rq_count; index++) + enic->cq[index].cur_rx_coal_timeval = + enic->config.intr_timer_usec; + + rx_coal->use_adaptive_rx_coalesce = 1; +} + static void enic_link_check(struct enic *enic) { int link_status = vnic_dev_link_status(enic->vdev); @@ -436,6 +466,7 @@ static void enic_link_check(struct enic *enic) if (link_status && !carrier_ok) { netdev_info(enic->netdev, "Link UP\n"); netif_carrier_on(enic->netdev); + enic_set_rx_coal_setting(enic); } else if (!link_status && carrier_ok) { netdev_info(enic->netdev, "Link DOWN\n"); netif_carrier_off(enic->netdev); @@ -1901,36 +1932,6 @@ static void enic_synchronize_irqs(struct enic *enic) } } -static void enic_set_rx_coal_setting(struct enic *enic) -{ - unsigned int speed; - int index = -1; - struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting; - - /* 1. Read the link speed from fw - * 2. Pick the default range for the speed - * 3. Update it in enic->rx_coalesce_setting - */ - speed = vnic_dev_port_speed(enic->vdev); - if (ENIC_LINK_SPEED_10G < speed) - index = ENIC_LINK_40G_INDEX; - else if (ENIC_LINK_SPEED_4G < speed) - index = ENIC_LINK_10G_INDEX; - else - index = ENIC_LINK_4G_INDEX; - - rx_coal->small_pkt_range_start = mod_range[index].small_pkt_range_start; - rx_coal->large_pkt_range_start = mod_range[index].large_pkt_range_start; - rx_coal->range_end = ENIC_RX_COALESCE_RANGE_END; - - /* Start with the value provided by UCSM */ - for (index = 0; index < enic->rq_count; index++) - enic->cq[index].cur_rx_coal_timeval = - enic->config.intr_timer_usec; - - rx_coal->use_adaptive_rx_coalesce = 1; -} - static int enic_dev_notify_set(struct enic *enic) { int err; @@ -3063,7 +3064,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) timer_setup(&enic->notify_timer, enic_notify_timer, 0); enic_rfs_flw_tbl_init(enic); - enic_set_rx_coal_setting(enic); INIT_WORK(&enic->reset, enic_reset); INIT_WORK(&enic->tx_hang_reset, enic_tx_hang_reset); INIT_WORK(&enic->change_mtu_work, enic_change_mtu_work); diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 8735e333034c..b87eaf0c250c 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1777,10 +1777,11 @@ static void dm9000_drv_remove(struct platform_device *pdev) unregister_netdev(ndev); dm9000_release_board(pdev, dm); - free_netdev(ndev); /* free device structure */ if (dm->power_supply) regulator_disable(dm->power_supply); + free_netdev(ndev); /* free device structure */ + dev_dbg(&pdev->dev, "released and freed device\n"); } diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 95a5295d0361..0d030cb0b21c 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -1966,23 +1966,41 @@ failed: static void tsnep_queue_enable(struct tsnep_queue *queue) { + struct tsnep_adapter *adapter = queue->adapter; + + netif_napi_set_irq(&queue->napi, queue->irq); napi_enable(&queue->napi); - tsnep_enable_irq(queue->adapter, queue->irq_mask); + tsnep_enable_irq(adapter, queue->irq_mask); - if (queue->tx) + if (queue->tx) { + netif_queue_set_napi(adapter->netdev, queue->tx->queue_index, + NETDEV_QUEUE_TYPE_TX, &queue->napi); tsnep_tx_enable(queue->tx); + } - if (queue->rx) + if (queue->rx) { + netif_queue_set_napi(adapter->netdev, queue->rx->queue_index, + NETDEV_QUEUE_TYPE_RX, &queue->napi); tsnep_rx_enable(queue->rx); + } } static void tsnep_queue_disable(struct tsnep_queue *queue) { - if (queue->tx) + struct tsnep_adapter *adapter = queue->adapter; + + if (queue->rx) + netif_queue_set_napi(adapter->netdev, queue->rx->queue_index, + NETDEV_QUEUE_TYPE_RX, NULL); + + if (queue->tx) { tsnep_tx_disable(queue->tx, &queue->napi); + netif_queue_set_napi(adapter->netdev, queue->tx->queue_index, + NETDEV_QUEUE_TYPE_TX, NULL); + } napi_disable(&queue->napi); - tsnep_disable_irq(queue->adapter, queue->irq_mask); + tsnep_disable_irq(adapter, queue->irq_mask); /* disable RX after NAPI polling has been disabled, because RX can be * enabled during NAPI polling diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index 75401d2a5fb4..a2d7300925a8 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -81,8 +81,7 @@ config UCC_GETH tristate "Freescale QE Gigabit Ethernet" depends on QUICC_ENGINE && PPC32 select FSL_PQ_MDIO - select PHYLIB - select FIXED_PHY + select PHYLINK help This driver supports the Gigabit Ethernet mode of the QUICC Engine, which is available on some Freescale SOCs. diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index bf5baef5c3e0..4948b4906584 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2281,7 +2281,7 @@ static int dpaa_a050385_wa_xdpf(struct dpaa_priv *priv, new_xdpf->len = xdpf->len; new_xdpf->headroom = priv->tx_headroom; new_xdpf->frame_sz = DPAA_BP_RAW_SIZE; - new_xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + new_xdpf->mem_type = MEM_TYPE_PAGE_ORDER0; /* Release the initial buffer */ xdp_return_frame_rx_napi(xdpf); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index a293b08f36d4..147a93bf9fa9 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -780,13 +780,14 @@ struct ethsw_dump_ctx { static int dpaa2_switch_fdb_dump_nl(struct fdb_dump_entry *entry, struct ethsw_dump_ctx *dump) { + struct ndo_fdb_dump_context *ctx = (void *)dump->cb->ctx; int is_dynamic = entry->type & DPSW_FDB_ENTRY_DINAMIC; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; struct ndmsg *ndm; - if (dump->idx < dump->cb->args[2]) + if (dump->idx < ctx->fdb_idx) goto skip; nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 535969fa0fdb..6a6fc819dfde 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -146,6 +146,27 @@ static int enetc_ptp_parse(struct sk_buff *skb, u8 *udp, return 0; } +static bool enetc_tx_csum_offload_check(struct sk_buff *skb) +{ + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + case offsetof(struct udphdr, check): + return true; + default: + return false; + } +} + +static bool enetc_skb_is_ipv6(struct sk_buff *skb) +{ + return vlan_get_protocol(skb) == htons(ETH_P_IPV6); +} + +static bool enetc_skb_is_tcp(struct sk_buff *skb) +{ + return skb->csum_offset == offsetof(struct tcphdr, check); +} + static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) { bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false; @@ -163,6 +184,29 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) dma_addr_t dma; u8 flags = 0; + enetc_clear_tx_bd(&temp_bd); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + /* Can not support TSD and checksum offload at the same time */ + if (priv->active_offloads & ENETC_F_TXCSUM && + enetc_tx_csum_offload_check(skb) && !tx_ring->tsd_enable) { + temp_bd.l3_aux0 = FIELD_PREP(ENETC_TX_BD_L3_START, + skb_network_offset(skb)); + temp_bd.l3_aux1 = FIELD_PREP(ENETC_TX_BD_L3_HDR_LEN, + skb_network_header_len(skb) / 4); + temp_bd.l3_aux1 |= FIELD_PREP(ENETC_TX_BD_L3T, + enetc_skb_is_ipv6(skb)); + if (enetc_skb_is_tcp(skb)) + temp_bd.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T, + ENETC_TXBD_L4T_TCP); + else + temp_bd.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T, + ENETC_TXBD_L4T_UDP); + flags |= ENETC_TXBD_FLAGS_CSUM_LSO | ENETC_TXBD_FLAGS_L4CS; + } else if (skb_checksum_help(skb)) { + return 0; + } + } + i = tx_ring->next_to_use; txbd = ENETC_TXBD(*tx_ring, i); prefetchw(txbd); @@ -173,7 +217,6 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) temp_bd.addr = cpu_to_le64(dma); temp_bd.buf_len = cpu_to_le16(len); - temp_bd.lstatus = 0; tx_swbd = &tx_ring->tx_swbd[i]; tx_swbd->dma = dma; @@ -489,8 +532,233 @@ static void enetc_tso_complete_csum(struct enetc_bdr *tx_ring, struct tso_t *tso } } +static int enetc_lso_count_descs(const struct sk_buff *skb) +{ + /* 4 BDs: 1 BD for LSO header + 1 BD for extended BD + 1 BD + * for linear area data but not include LSO header, namely + * skb_headlen(skb) - lso_hdr_len (it may be 0, but that's + * okay, we only need to consider the worst case). And 1 BD + * for gap. + */ + return skb_shinfo(skb)->nr_frags + 4; +} + +static int enetc_lso_get_hdr_len(const struct sk_buff *skb) +{ + int hdr_len, tlen; + + tlen = skb_is_gso_tcp(skb) ? tcp_hdrlen(skb) : sizeof(struct udphdr); + hdr_len = skb_transport_offset(skb) + tlen; + + return hdr_len; +} + +static void enetc_lso_start(struct sk_buff *skb, struct enetc_lso_t *lso) +{ + lso->lso_seg_size = skb_shinfo(skb)->gso_size; + lso->ipv6 = enetc_skb_is_ipv6(skb); + lso->tcp = skb_is_gso_tcp(skb); + lso->l3_hdr_len = skb_network_header_len(skb); + lso->l3_start = skb_network_offset(skb); + lso->hdr_len = enetc_lso_get_hdr_len(skb); + lso->total_len = skb->len - lso->hdr_len; +} + +static void enetc_lso_map_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, + int *i, struct enetc_lso_t *lso) +{ + union enetc_tx_bd txbd_tmp, *txbd; + struct enetc_tx_swbd *tx_swbd; + u16 frm_len, frm_len_ext; + u8 flags, e_flags = 0; + dma_addr_t addr; + char *hdr; + + /* Get the first BD of the LSO BDs chain */ + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + + /* Prepare LSO header: MAC + IP + TCP/UDP */ + hdr = tx_ring->tso_headers + *i * TSO_HEADER_SIZE; + memcpy(hdr, skb->data, lso->hdr_len); + addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE; + + /* {frm_len_ext, frm_len} indicates the total length of + * large transmit data unit. frm_len contains the 16 least + * significant bits and frm_len_ext contains the 4 most + * significant bits. + */ + frm_len = lso->total_len & 0xffff; + frm_len_ext = (lso->total_len >> 16) & 0xf; + + /* Set the flags of the first BD */ + flags = ENETC_TXBD_FLAGS_EX | ENETC_TXBD_FLAGS_CSUM_LSO | + ENETC_TXBD_FLAGS_LSO | ENETC_TXBD_FLAGS_L4CS; + + enetc_clear_tx_bd(&txbd_tmp); + txbd_tmp.addr = cpu_to_le64(addr); + txbd_tmp.hdr_len = cpu_to_le16(lso->hdr_len); + + /* first BD needs frm_len and offload flags set */ + txbd_tmp.frm_len = cpu_to_le16(frm_len); + txbd_tmp.flags = flags; + + txbd_tmp.l3_aux0 = FIELD_PREP(ENETC_TX_BD_L3_START, lso->l3_start); + /* l3_hdr_size in 32-bits (4 bytes) */ + txbd_tmp.l3_aux1 = FIELD_PREP(ENETC_TX_BD_L3_HDR_LEN, + lso->l3_hdr_len / 4); + if (lso->ipv6) + txbd_tmp.l3_aux1 |= ENETC_TX_BD_L3T; + else + txbd_tmp.l3_aux0 |= ENETC_TX_BD_IPCS; + + txbd_tmp.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T, lso->tcp ? + ENETC_TXBD_L4T_TCP : ENETC_TXBD_L4T_UDP); + + /* For the LSO header we do not set the dma address since + * we do not want it unmapped when we do cleanup. We still + * set len so that we count the bytes sent. + */ + tx_swbd->len = lso->hdr_len; + tx_swbd->do_twostep_tstamp = false; + tx_swbd->check_wb = false; + + /* Actually write the header in the BD */ + *txbd = txbd_tmp; + + /* Get the next BD, and the next BD is extended BD */ + enetc_bdr_idx_inc(tx_ring, i); + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + + enetc_clear_tx_bd(&txbd_tmp); + if (skb_vlan_tag_present(skb)) { + /* Setup the VLAN fields */ + txbd_tmp.ext.vid = cpu_to_le16(skb_vlan_tag_get(skb)); + txbd_tmp.ext.tpid = ENETC_TPID_8021Q; + e_flags = ENETC_TXBD_E_FLAGS_VLAN_INS; + } + + /* Write the BD */ + txbd_tmp.ext.e_flags = e_flags; + txbd_tmp.ext.lso_sg_size = cpu_to_le16(lso->lso_seg_size); + txbd_tmp.ext.frm_len_ext = cpu_to_le16(frm_len_ext); + *txbd = txbd_tmp; +} + +static int enetc_lso_map_data(struct enetc_bdr *tx_ring, struct sk_buff *skb, + int *i, struct enetc_lso_t *lso, int *count) +{ + union enetc_tx_bd txbd_tmp, *txbd = NULL; + struct enetc_tx_swbd *tx_swbd; + skb_frag_t *frag; + dma_addr_t dma; + u8 flags = 0; + int len, f; + + len = skb_headlen(skb) - lso->hdr_len; + if (len > 0) { + dma = dma_map_single(tx_ring->dev, skb->data + lso->hdr_len, + len, DMA_TO_DEVICE); + if (dma_mapping_error(tx_ring->dev, dma)) + return -ENOMEM; + + enetc_bdr_idx_inc(tx_ring, i); + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + *count += 1; + + enetc_clear_tx_bd(&txbd_tmp); + txbd_tmp.addr = cpu_to_le64(dma); + txbd_tmp.buf_len = cpu_to_le16(len); + + tx_swbd->dma = dma; + tx_swbd->len = len; + tx_swbd->is_dma_page = 0; + tx_swbd->dir = DMA_TO_DEVICE; + } + + frag = &skb_shinfo(skb)->frags[0]; + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++, frag++) { + if (txbd) + *txbd = txbd_tmp; + + len = skb_frag_size(frag); + dma = skb_frag_dma_map(tx_ring->dev, frag); + if (dma_mapping_error(tx_ring->dev, dma)) + return -ENOMEM; + + /* Get the next BD */ + enetc_bdr_idx_inc(tx_ring, i); + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + *count += 1; + + enetc_clear_tx_bd(&txbd_tmp); + txbd_tmp.addr = cpu_to_le64(dma); + txbd_tmp.buf_len = cpu_to_le16(len); + + tx_swbd->dma = dma; + tx_swbd->len = len; + tx_swbd->is_dma_page = 1; + tx_swbd->dir = DMA_TO_DEVICE; + } + + /* Last BD needs 'F' bit set */ + flags |= ENETC_TXBD_FLAGS_F; + txbd_tmp.flags = flags; + *txbd = txbd_tmp; + + tx_swbd->is_eof = 1; + tx_swbd->skb = skb; + + return 0; +} + +static int enetc_lso_hw_offload(struct enetc_bdr *tx_ring, struct sk_buff *skb) +{ + struct enetc_tx_swbd *tx_swbd; + struct enetc_lso_t lso = {0}; + int err, i, count = 0; + + /* Initialize the LSO handler */ + enetc_lso_start(skb, &lso); + i = tx_ring->next_to_use; + + enetc_lso_map_hdr(tx_ring, skb, &i, &lso); + /* First BD and an extend BD */ + count += 2; + + err = enetc_lso_map_data(tx_ring, skb, &i, &lso, &count); + if (err) + goto dma_err; + + /* Go to the next BD */ + enetc_bdr_idx_inc(tx_ring, &i); + tx_ring->next_to_use = i; + enetc_update_tx_ring_tail(tx_ring); + + return count; + +dma_err: + do { + tx_swbd = &tx_ring->tx_swbd[i]; + enetc_free_tx_frame(tx_ring, tx_swbd); + if (i == 0) + i = tx_ring->bd_count; + i--; + } while (--count); + + return 0; +} + static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) { + struct enetc_ndev_priv *priv = netdev_priv(tx_ring->ndev); int hdr_len, total_len, data_len; struct enetc_tx_swbd *tx_swbd; union enetc_tx_bd *txbd; @@ -556,7 +824,7 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb bd_data_num++; tso_build_data(skb, &tso, size); - if (unlikely(bd_data_num >= ENETC_MAX_SKB_FRAGS && data_len)) + if (unlikely(bd_data_num >= priv->max_frags && data_len)) goto err_chained_bd; } @@ -594,7 +862,7 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_bdr *tx_ring; - int count, err; + int count; /* Queue one-step Sync packet if already locked */ if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) { @@ -608,16 +876,28 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, tx_ring = priv->tx_ring[skb->queue_mapping]; if (skb_is_gso(skb)) { - if (enetc_bd_unused(tx_ring) < tso_count_descs(skb)) { - netif_stop_subqueue(ndev, tx_ring->index); - return NETDEV_TX_BUSY; - } + /* LSO data unit lengths of up to 256KB are supported */ + if (priv->active_offloads & ENETC_F_LSO && + (skb->len - enetc_lso_get_hdr_len(skb)) <= + ENETC_LSO_MAX_DATA_LEN) { + if (enetc_bd_unused(tx_ring) < enetc_lso_count_descs(skb)) { + netif_stop_subqueue(ndev, tx_ring->index); + return NETDEV_TX_BUSY; + } - enetc_lock_mdio(); - count = enetc_map_tx_tso_buffs(tx_ring, skb); - enetc_unlock_mdio(); + count = enetc_lso_hw_offload(tx_ring, skb); + } else { + if (enetc_bd_unused(tx_ring) < tso_count_descs(skb)) { + netif_stop_subqueue(ndev, tx_ring->index); + return NETDEV_TX_BUSY; + } + + enetc_lock_mdio(); + count = enetc_map_tx_tso_buffs(tx_ring, skb); + enetc_unlock_mdio(); + } } else { - if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS)) + if (unlikely(skb_shinfo(skb)->nr_frags > priv->max_frags)) if (unlikely(skb_linearize(skb))) goto drop_packet_err; @@ -627,11 +907,6 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, return NETDEV_TX_BUSY; } - if (skb->ip_summed == CHECKSUM_PARTIAL) { - err = skb_checksum_help(skb); - if (err) - goto drop_packet_err; - } enetc_lock_mdio(); count = enetc_map_tx_buffs(tx_ring, skb); enetc_unlock_mdio(); @@ -640,7 +915,7 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, if (unlikely(!count)) goto drop_packet_err; - if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED) + if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED(priv->max_frags)) netif_stop_subqueue(ndev, tx_ring->index); return NETDEV_TX_OK; @@ -908,7 +1183,8 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) if (unlikely(tx_frm_cnt && netif_carrier_ok(ndev) && __netif_subqueue_stopped(ndev, tx_ring->index) && !test_bit(ENETC_TX_DOWN, &priv->flags) && - (enetc_bd_unused(tx_ring) >= ENETC_TXBDS_MAX_NEEDED))) { + (enetc_bd_unused(tx_ring) >= + ENETC_TXBDS_MAX_NEEDED(priv->max_frags)))) { netif_wake_subqueue(ndev, tx_ring->index); } @@ -1759,6 +2035,9 @@ void enetc_get_si_caps(struct enetc_si *si) rss = enetc_rd(hw, ENETC_SIRSSCAPR); si->num_rss = ENETC_SIRSSCAPR_GET_NUM_RSS(rss); } + + if (val & ENETC_SIPCAPR0_LSO) + si->hw_features |= ENETC_SI_F_LSO; } EXPORT_SYMBOL_GPL(enetc_get_si_caps); @@ -2055,6 +2334,14 @@ static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups) return 0; } +static void enetc_set_lso_flags_mask(struct enetc_hw *hw) +{ + enetc_wr(hw, ENETC4_SILSOSFMR0, + SILSOSFMR0_VAL_SET(ENETC4_TCP_NL_SEG_FLAGS_DMASK, + ENETC4_TCP_NL_SEG_FLAGS_DMASK)); + enetc_wr(hw, ENETC4_SILSOSFMR1, 0); +} + int enetc_configure_si(struct enetc_ndev_priv *priv) { struct enetc_si *si = priv->si; @@ -2068,6 +2355,9 @@ int enetc_configure_si(struct enetc_ndev_priv *priv) /* enable SI */ enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN); + if (si->hw_features & ENETC_SI_F_LSO) + enetc_set_lso_flags_mask(hw); + /* TODO: RSS support for i.MX95 will be supported later, and the * is_enetc_rev1() condition will be removed */ @@ -3269,17 +3559,21 @@ EXPORT_SYMBOL_GPL(enetc_pci_remove); static const struct enetc_drvdata enetc_pf_data = { .sysclk_freq = ENETC_CLK_400M, .pmac_offset = ENETC_PMAC_OFFSET, + .max_frags = ENETC_MAX_SKB_FRAGS, .eth_ops = &enetc_pf_ethtool_ops, }; static const struct enetc_drvdata enetc4_pf_data = { .sysclk_freq = ENETC_CLK_333M, + .tx_csum = true, + .max_frags = ENETC4_MAX_SKB_FRAGS, .pmac_offset = ENETC4_PMAC_OFFSET, .eth_ops = &enetc4_pf_ethtool_ops, }; static const struct enetc_drvdata enetc_vf_data = { .sysclk_freq = ENETC_CLK_400M, + .max_frags = ENETC_MAX_SKB_FRAGS, .eth_ops = &enetc_vf_ethtool_ops, }; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 72fa03dbc2dd..4ad4eb5c5a74 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -41,6 +41,18 @@ struct enetc_tx_swbd { u8 qbv_en:1; }; +struct enetc_lso_t { + bool ipv6; + bool tcp; + u8 l3_hdr_len; + u8 hdr_len; /* LSO header length */ + u8 l3_start; + u16 lso_seg_size; + int total_len; /* total data length, not include LSO header */ +}; + +#define ENETC_LSO_MAX_DATA_LEN SZ_256K + #define ENETC_RX_MAXFRM_SIZE ENETC_MAC_MAXFRM_SIZE #define ENETC_RXB_TRUESIZE 2048 /* PAGE_SIZE >> 1 */ #define ENETC_RXB_PAD NET_SKB_PAD /* add extra space if needed */ @@ -59,9 +71,16 @@ struct enetc_rx_swbd { /* ENETC overhead: optional extension BD + 1 BD gap */ #define ENETC_TXBDS_NEEDED(val) ((val) + 2) -/* max # of chained Tx BDs is 15, including head and extension BD */ +/* For LS1028A, max # of chained Tx BDs is 15, including head and + * extension BD. + */ #define ENETC_MAX_SKB_FRAGS 13 -#define ENETC_TXBDS_MAX_NEEDED ENETC_TXBDS_NEEDED(ENETC_MAX_SKB_FRAGS + 1) +/* For ENETC v4 and later versions, max # of chained Tx BDs is 63, + * including head and extension BD, but the range of MAX_SKB_FRAGS + * is 17 ~ 45, so set ENETC4_MAX_SKB_FRAGS to MAX_SKB_FRAGS. + */ +#define ENETC4_MAX_SKB_FRAGS MAX_SKB_FRAGS +#define ENETC_TXBDS_MAX_NEEDED(x) ENETC_TXBDS_NEEDED((x) + 1) struct enetc_ring_stats { unsigned int packets; @@ -231,9 +250,12 @@ enum enetc_errata { #define ENETC_SI_F_PSFP BIT(0) #define ENETC_SI_F_QBV BIT(1) #define ENETC_SI_F_QBU BIT(2) +#define ENETC_SI_F_LSO BIT(3) struct enetc_drvdata { u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */ + u8 tx_csum:1; + u8 max_frags; u64 sysclk_freq; const struct ethtool_ops *eth_ops; }; @@ -341,6 +363,8 @@ enum enetc_active_offloads { ENETC_F_QBV = BIT(9), ENETC_F_QCI = BIT(10), ENETC_F_QBU = BIT(11), + ENETC_F_TXCSUM = BIT(12), + ENETC_F_LSO = BIT(13), }; enum enetc_flags_bit { @@ -375,6 +399,7 @@ struct enetc_ndev_priv { u16 msg_enable; u8 preemptible_tcs; + u8 max_frags; /* The maximum number of BDs for fragments */ enum enetc_active_offloads active_offloads; diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h index 26b220677448..695cb07c74bc 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h @@ -12,6 +12,29 @@ #define NXP_ENETC_VENDOR_ID 0x1131 #define NXP_ENETC_PF_DEV_ID 0xe101 +/**********************Station interface registers************************/ +/* Station interface LSO segmentation flag mask register 0/1 */ +#define ENETC4_SILSOSFMR0 0x1300 +#define SILSOSFMR0_TCP_MID_SEG GENMASK(27, 16) +#define SILSOSFMR0_TCP_1ST_SEG GENMASK(11, 0) +#define SILSOSFMR0_VAL_SET(first, mid) (FIELD_PREP(SILSOSFMR0_TCP_MID_SEG, mid) | \ + FIELD_PREP(SILSOSFMR0_TCP_1ST_SEG, first)) + +#define ENETC4_SILSOSFMR1 0x1304 +#define SILSOSFMR1_TCP_LAST_SEG GENMASK(11, 0) +#define ENETC4_TCP_FLAGS_FIN BIT(0) +#define ENETC4_TCP_FLAGS_SYN BIT(1) +#define ENETC4_TCP_FLAGS_RST BIT(2) +#define ENETC4_TCP_FLAGS_PSH BIT(3) +#define ENETC4_TCP_FLAGS_ACK BIT(4) +#define ENETC4_TCP_FLAGS_URG BIT(5) +#define ENETC4_TCP_FLAGS_ECE BIT(6) +#define ENETC4_TCP_FLAGS_CWR BIT(7) +#define ENETC4_TCP_FLAGS_NS BIT(8) +/* According to tso_build_hdr(), clear all special flags for not last packet. */ +#define ENETC4_TCP_NL_SEG_FLAGS_DMASK (ENETC4_TCP_FLAGS_FIN | \ + ENETC4_TCP_FLAGS_RST | ENETC4_TCP_FLAGS_PSH) + /***************************ENETC port registers**************************/ #define ENETC4_ECAPR0 0x0 #define ECAPR0_RFS BIT(2) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 55ba949230ff..4098f01479bc 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -25,6 +25,7 @@ #define ENETC_SIPCAPR0 0x20 #define ENETC_SIPCAPR0_RSS BIT(8) #define ENETC_SIPCAPR0_RFS BIT(2) +#define ENETC_SIPCAPR0_LSO BIT(1) #define ENETC_SIPCAPR1 0x24 #define ENETC_SITGTGR 0x30 #define ENETC_SIRBGCR 0x38 @@ -554,11 +555,23 @@ static inline u64 _enetc_rd_reg64_wa(void __iomem *reg) union enetc_tx_bd { struct { __le64 addr; - __le16 buf_len; + union { + __le16 buf_len; + __le16 hdr_len; /* For LSO, ENETC 4.1 and later */ + }; __le16 frm_len; union { struct { - u8 reserved[3]; + u8 l3_aux0; +#define ENETC_TX_BD_L3_START GENMASK(6, 0) +#define ENETC_TX_BD_IPCS BIT(7) + u8 l3_aux1; +#define ENETC_TX_BD_L3_HDR_LEN GENMASK(6, 0) +#define ENETC_TX_BD_L3T BIT(7) + u8 l4_aux; +#define ENETC_TX_BD_L4T GENMASK(7, 5) +#define ENETC_TXBD_L4T_UDP 1 +#define ENETC_TXBD_L4T_TCP 2 u8 flags; }; /* default layout */ __le32 txstart; @@ -569,23 +582,27 @@ union enetc_tx_bd { __le32 tstamp; __le16 tpid; __le16 vid; - u8 reserved[6]; + __le16 lso_sg_size; /* For ENETC 4.1 and later */ + __le16 frm_len_ext; /* For ENETC 4.1 and later */ + u8 reserved[2]; u8 e_flags; u8 flags; } ext; /* Tx BD extension */ struct { __le32 tstamp; - u8 reserved[10]; + u8 reserved[8]; + __le16 lso_err_count; /* For ENETC 4.1 and later */ u8 status; u8 flags; } wb; /* writeback descriptor */ }; enum enetc_txbd_flags { - ENETC_TXBD_FLAGS_RES0 = BIT(0), /* reserved */ + ENETC_TXBD_FLAGS_L4CS = BIT(0), /* For ENETC 4.1 and later */ ENETC_TXBD_FLAGS_TSE = BIT(1), + ENETC_TXBD_FLAGS_LSO = BIT(1), /* For ENETC 4.1 and later */ ENETC_TXBD_FLAGS_W = BIT(2), - ENETC_TXBD_FLAGS_RES3 = BIT(3), /* reserved */ + ENETC_TXBD_FLAGS_CSUM_LSO = BIT(3), /* For ENETC 4.1 and later */ ENETC_TXBD_FLAGS_TXSTART = BIT(4), ENETC_TXBD_FLAGS_EX = BIT(6), ENETC_TXBD_FLAGS_F = BIT(7) @@ -654,6 +671,8 @@ union enetc_rx_bd { #define ENETC_CBD_FLAGS_SF BIT(7) /* short format */ #define ENETC_CBD_STATUS_MASK 0xf +#define ENETC_TPID_8021Q 0 + struct enetc_cmd_rfse { u8 smac_h[6]; u8 smac_m[6]; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c index 0eecfc833164..3fd9b0727875 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c @@ -101,6 +101,7 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, priv->msg_enable = (NETIF_MSG_WOL << 1) - 1; priv->sysclk_freq = si->drvdata->sysclk_freq; + priv->max_frags = si->drvdata->max_frags; ndev->netdev_ops = ndev_ops; enetc_set_ethtool_ops(ndev); ndev->watchdog_timeo = 5 * HZ; @@ -109,16 +110,24 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK | - NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_L4; ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_L4; ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; ndev->priv_flags |= IFF_UNICAST_FLT; + if (si->drvdata->tx_csum) + priv->active_offloads |= ENETC_F_TXCSUM; + + if (si->hw_features & ENETC_SI_F_LSO) + priv->active_offloads |= ENETC_F_LSO; + /* TODO: currently, i.MX95 ENETC driver does not support advanced features */ if (!is_enetc_rev1(si)) { ndev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index a5f8ce576b6e..3768752b6008 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -136,6 +136,7 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev, priv->msg_enable = (NETIF_MSG_IFUP << 1) - 1; priv->sysclk_freq = si->drvdata->sysclk_freq; + priv->max_frags = si->drvdata->max_frags; ndev->netdev_ops = ndev_ops; enetc_set_ethtool_ops(ndev); ndev->watchdog_timeo = 5 * HZ; @@ -144,11 +145,13 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_L4; ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_L4; ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 1cca0425d493..c81f2ea588f2 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -671,8 +671,6 @@ struct fec_enet_private { unsigned int tx_time_itr; unsigned int itr_clk_rate; - /* tx lpi eee mode */ - struct ethtool_keee eee; unsigned int clk_ref_rate; /* ptp clock period in ns*/ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 1b55047c0237..f7c4ce8e9a26 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -840,6 +840,8 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq, struct fec_enet_private *fep = netdev_priv(ndev); int hdr_len, total_len, data_left; struct bufdesc *bdp = txq->bd.cur; + struct bufdesc *tmp_bdp; + struct bufdesc_ex *ebdp; struct tso_t tso; unsigned int index = 0; int ret; @@ -913,7 +915,34 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq, return 0; err_release: - /* TODO: Release all used data descriptors for TSO */ + /* Release all used data descriptors for TSO */ + tmp_bdp = txq->bd.cur; + + while (tmp_bdp != bdp) { + /* Unmap data buffers */ + if (tmp_bdp->cbd_bufaddr && + !IS_TSO_HEADER(txq, fec32_to_cpu(tmp_bdp->cbd_bufaddr))) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(tmp_bdp->cbd_bufaddr), + fec16_to_cpu(tmp_bdp->cbd_datlen), + DMA_TO_DEVICE); + + /* Clear standard buffer descriptor fields */ + tmp_bdp->cbd_sc = 0; + tmp_bdp->cbd_datlen = 0; + tmp_bdp->cbd_bufaddr = 0; + + /* Handle extended descriptor if enabled */ + if (fep->bufdesc_ex) { + ebdp = (struct bufdesc_ex *)tmp_bdp; + ebdp->cbd_esc = 0; + } + + tmp_bdp = fec_enet_get_nextdesc(tmp_bdp, &txq->bd); + } + + dev_kfree_skb_any(skb); + return ret; } @@ -1591,19 +1620,22 @@ static void fec_enet_tx(struct net_device *ndev, int budget) fec_enet_tx_queue(ndev, i, budget); } -static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq, +static int fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq, struct bufdesc *bdp, int index) { struct page *new_page; dma_addr_t phys_addr; new_page = page_pool_dev_alloc_pages(rxq->page_pool); - WARN_ON(!new_page); - rxq->rx_skb_info[index].page = new_page; + if (unlikely(!new_page)) + return -ENOMEM; + rxq->rx_skb_info[index].page = new_page; rxq->rx_skb_info[index].offset = FEC_ENET_XDP_HEADROOM; phys_addr = page_pool_get_dma_addr(new_page) + FEC_ENET_XDP_HEADROOM; bdp->cbd_bufaddr = cpu_to_fec32(phys_addr); + + return 0; } static u32 @@ -1698,6 +1730,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) int cpu = smp_processor_id(); struct xdp_buff xdp; struct page *page; + __fec32 cbd_bufaddr; u32 sub_len = 4; #if !defined(CONFIG_M5272) @@ -1766,12 +1799,17 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) index = fec_enet_get_bd_index(bdp, &rxq->bd); page = rxq->rx_skb_info[index].page; + cbd_bufaddr = bdp->cbd_bufaddr; + if (fec_enet_update_cbd(rxq, bdp, index)) { + ndev->stats.rx_dropped++; + goto rx_processing_done; + } + dma_sync_single_for_cpu(&fep->pdev->dev, - fec32_to_cpu(bdp->cbd_bufaddr), + fec32_to_cpu(cbd_bufaddr), pkt_len, DMA_FROM_DEVICE); prefetch(page_address(page)); - fec_enet_update_cbd(rxq, bdp, index); if (xdp_prog) { xdp_buff_clear_frags_flag(&xdp); @@ -2045,14 +2083,14 @@ static int fec_enet_us_to_tx_cycle(struct net_device *ndev, int us) return us * (fep->clk_ref_rate / 1000) / 1000; } -static int fec_enet_eee_mode_set(struct net_device *ndev, bool enable) +static int fec_enet_eee_mode_set(struct net_device *ndev, u32 lpi_timer, + bool enable) { struct fec_enet_private *fep = netdev_priv(ndev); - struct ethtool_keee *p = &fep->eee; unsigned int sleep_cycle, wake_cycle; if (enable) { - sleep_cycle = fec_enet_us_to_tx_cycle(ndev, p->tx_lpi_timer); + sleep_cycle = fec_enet_us_to_tx_cycle(ndev, lpi_timer); wake_cycle = sleep_cycle; } else { sleep_cycle = 0; @@ -2105,7 +2143,9 @@ static void fec_enet_adjust_link(struct net_device *ndev) napi_enable(&fep->napi); } if (fep->quirks & FEC_QUIRK_HAS_EEE) - fec_enet_eee_mode_set(ndev, phy_dev->enable_tx_lpi); + fec_enet_eee_mode_set(ndev, + phy_dev->eee_cfg.tx_lpi_timer, + phy_dev->enable_tx_lpi); } else { if (fep->link) { netif_stop_queue(ndev); @@ -3181,7 +3221,6 @@ static int fec_enet_get_eee(struct net_device *ndev, struct ethtool_keee *edata) { struct fec_enet_private *fep = netdev_priv(ndev); - struct ethtool_keee *p = &fep->eee; if (!(fep->quirks & FEC_QUIRK_HAS_EEE)) return -EOPNOTSUPP; @@ -3189,8 +3228,6 @@ fec_enet_get_eee(struct net_device *ndev, struct ethtool_keee *edata) if (!netif_running(ndev)) return -ENETDOWN; - edata->tx_lpi_timer = p->tx_lpi_timer; - return phy_ethtool_get_eee(ndev->phydev, edata); } @@ -3198,7 +3235,6 @@ static int fec_enet_set_eee(struct net_device *ndev, struct ethtool_keee *edata) { struct fec_enet_private *fep = netdev_priv(ndev); - struct ethtool_keee *p = &fep->eee; if (!(fep->quirks & FEC_QUIRK_HAS_EEE)) return -EOPNOTSUPP; @@ -3206,8 +3242,6 @@ fec_enet_set_eee(struct net_device *ndev, struct ethtool_keee *edata) if (!netif_running(ndev)) return -ENETDOWN; - p->tx_lpi_timer = edata->tx_lpi_timer; - return phy_ethtool_set_eee(ndev->phydev, edata); } diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index fb416d60dcd7..11887458f050 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -2690,13 +2690,12 @@ static struct fman *read_dts_node(struct platform_device *of_dev) { struct fman *fman; struct device_node *fm_node, *muram_node; + void __iomem *base_addr; struct resource *res; u32 val, range[2]; int err, irq; struct clk *clk; u32 clk_rate; - phys_addr_t phys_base_addr; - resource_size_t mem_size; fman = kzalloc(sizeof(*fman), GFP_KERNEL); if (!fman) @@ -2724,18 +2723,6 @@ static struct fman *read_dts_node(struct platform_device *of_dev) goto fman_node_put; fman->dts_params.err_irq = err; - /* Get the FM address */ - res = platform_get_resource(of_dev, IORESOURCE_MEM, 0); - if (!res) { - err = -EINVAL; - dev_err(&of_dev->dev, "%s: Can't get FMan memory resource\n", - __func__); - goto fman_node_put; - } - - phys_base_addr = res->start; - mem_size = resource_size(res); - clk = of_clk_get(fm_node, 0); if (IS_ERR(clk)) { err = PTR_ERR(clk); @@ -2803,24 +2790,16 @@ static struct fman *read_dts_node(struct platform_device *of_dev) } } - fman->dts_params.res = - devm_request_mem_region(&of_dev->dev, phys_base_addr, - mem_size, "fman"); - if (!fman->dts_params.res) { - err = -EBUSY; - dev_err(&of_dev->dev, "%s: request_mem_region() failed\n", - __func__); - goto fman_free; - } - - fman->dts_params.base_addr = - devm_ioremap(&of_dev->dev, phys_base_addr, mem_size); - if (!fman->dts_params.base_addr) { - err = -ENOMEM; + base_addr = devm_platform_get_and_ioremap_resource(of_dev, 0, &res); + if (IS_ERR(base_addr)) { + err = PTR_ERR(base_addr); dev_err(&of_dev->dev, "%s: devm_ioremap() failed\n", __func__); goto fman_free; } + fman->dts_params.base_addr = base_addr; + fman->dts_params.res = res; + fman->dev = &of_dev->dev; err = of_platform_populate(fm_node, NULL, NULL, &of_dev->dev); diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index 85617bb94959..b3e2a596ad2c 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -755,12 +755,12 @@ static struct fman_mac *pcs_to_dtsec(struct phylink_pcs *pcs) return container_of(pcs, struct fman_mac, pcs); } -static void dtsec_pcs_get_state(struct phylink_pcs *pcs, +static void dtsec_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct fman_mac *dtsec = pcs_to_dtsec(pcs); - phylink_mii_c22_pcs_get_state(dtsec->tbidev, state); + phylink_mii_c22_pcs_get_state(dtsec->tbidev, neg_mode, state); } static int dtsec_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 6663c1768089..88510f822759 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include #include @@ -34,6 +34,7 @@ #include #include #include +#include #include #include @@ -132,7 +133,6 @@ static const struct ucc_geth_info ugeth_primary_info = { .transmitFlowControl = 1, .maxGroupAddrInHash = 4, .maxIndAddrInHash = 4, - .prel = 7, .maxFrameLength = 1518+16, /* Add extra bytes for VLANs etc. */ .minFrameLength = 64, .maxD1Length = 1520+16, /* Add extra bytes for VLANs etc. */ @@ -1205,34 +1205,6 @@ static int init_mac_station_addr_regs(u8 address_byte_0, return 0; } -static int init_check_frame_length_mode(int length_check, - u32 __iomem *maccfg2_register) -{ - u32 value = 0; - - value = in_be32(maccfg2_register); - - if (length_check) - value |= MACCFG2_LC; - else - value &= ~MACCFG2_LC; - - out_be32(maccfg2_register, value); - return 0; -} - -static int init_preamble_length(u8 preamble_length, - u32 __iomem *maccfg2_register) -{ - if ((preamble_length < 3) || (preamble_length > 7)) - return -EINVAL; - - clrsetbits_be32(maccfg2_register, MACCFG2_PREL_MASK, - preamble_length << MACCFG2_PREL_SHIFT); - - return 0; -} - static int init_rx_parameters(int reject_broadcast, int receive_short_frames, int promiscuous, u32 __iomem *upsmr_register) @@ -1287,94 +1259,11 @@ static int init_min_frame_len(u16 min_frame_length, return 0; } -static int adjust_enet_interface(struct ucc_geth_private *ugeth) +static bool phy_interface_mode_is_reduced(phy_interface_t interface) { - struct ucc_geth_info *ug_info; - struct ucc_geth __iomem *ug_regs; - struct ucc_fast __iomem *uf_regs; - int ret_val; - u32 upsmr, maccfg2; - u16 value; - - ugeth_vdbg("%s: IN", __func__); - - ug_info = ugeth->ug_info; - ug_regs = ugeth->ug_regs; - uf_regs = ugeth->uccf->uf_regs; - - /* Set MACCFG2 */ - maccfg2 = in_be32(&ug_regs->maccfg2); - maccfg2 &= ~MACCFG2_INTERFACE_MODE_MASK; - if ((ugeth->max_speed == SPEED_10) || - (ugeth->max_speed == SPEED_100)) - maccfg2 |= MACCFG2_INTERFACE_MODE_NIBBLE; - else if (ugeth->max_speed == SPEED_1000) - maccfg2 |= MACCFG2_INTERFACE_MODE_BYTE; - maccfg2 |= ug_info->padAndCrc; - out_be32(&ug_regs->maccfg2, maccfg2); - - /* Set UPSMR */ - upsmr = in_be32(&uf_regs->upsmr); - upsmr &= ~(UCC_GETH_UPSMR_RPM | UCC_GETH_UPSMR_R10M | - UCC_GETH_UPSMR_TBIM | UCC_GETH_UPSMR_RMM); - if ((ugeth->phy_interface == PHY_INTERFACE_MODE_RMII) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_ID) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) { - if (ugeth->phy_interface != PHY_INTERFACE_MODE_RMII) - upsmr |= UCC_GETH_UPSMR_RPM; - switch (ugeth->max_speed) { - case SPEED_10: - upsmr |= UCC_GETH_UPSMR_R10M; - fallthrough; - case SPEED_100: - if (ugeth->phy_interface != PHY_INTERFACE_MODE_RTBI) - upsmr |= UCC_GETH_UPSMR_RMM; - } - } - if ((ugeth->phy_interface == PHY_INTERFACE_MODE_TBI) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) { - upsmr |= UCC_GETH_UPSMR_TBIM; - } - if (ugeth->phy_interface == PHY_INTERFACE_MODE_SGMII) - upsmr |= UCC_GETH_UPSMR_SGMM; - - out_be32(&uf_regs->upsmr, upsmr); - - /* Disable autonegotiation in tbi mode, because by default it - comes up in autonegotiation mode. */ - /* Note that this depends on proper setting in utbipar register. */ - if ((ugeth->phy_interface == PHY_INTERFACE_MODE_TBI) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) { - struct ucc_geth_info *ug_info = ugeth->ug_info; - struct phy_device *tbiphy; - - if (!ug_info->tbi_node) - pr_warn("TBI mode requires that the device tree specify a tbi-handle\n"); - - tbiphy = of_phy_find_device(ug_info->tbi_node); - if (!tbiphy) - pr_warn("Could not get TBI device\n"); - - value = phy_read(tbiphy, ENET_TBI_MII_CR); - value &= ~0x1000; /* Turn off autonegotiation */ - phy_write(tbiphy, ENET_TBI_MII_CR, value); - - put_device(&tbiphy->mdio.dev); - } - - init_check_frame_length_mode(ug_info->lengthCheckRx, &ug_regs->maccfg2); - - ret_val = init_preamble_length(ug_info->prel, &ug_regs->maccfg2); - if (ret_val != 0) { - if (netif_msg_probe(ugeth)) - pr_err("Preamble length must be between 3 and 7 inclusive\n"); - return ret_val; - } - - return 0; + return phy_interface_mode_is_rgmii(interface) || + interface == PHY_INTERFACE_MODE_RMII || + interface == PHY_INTERFACE_MODE_RTBI; } static int ugeth_graceful_stop_tx(struct ucc_geth_private *ugeth) @@ -1545,108 +1434,7 @@ static void ugeth_activate(struct ucc_geth_private *ugeth) /* allow to xmit again */ netif_tx_wake_all_queues(ugeth->ndev); - __netdev_watchdog_up(ugeth->ndev); -} - -/* Called every time the controller might need to be made - * aware of new link state. The PHY code conveys this - * information through variables in the ugeth structure, and this - * function converts those variables into the appropriate - * register values, and can bring down the device if needed. - */ - -static void adjust_link(struct net_device *dev) -{ - struct ucc_geth_private *ugeth = netdev_priv(dev); - struct ucc_geth __iomem *ug_regs; - struct ucc_fast __iomem *uf_regs; - struct phy_device *phydev = ugeth->phydev; - int new_state = 0; - - ug_regs = ugeth->ug_regs; - uf_regs = ugeth->uccf->uf_regs; - - if (phydev->link) { - u32 tempval = in_be32(&ug_regs->maccfg2); - u32 upsmr = in_be32(&uf_regs->upsmr); - /* Now we make sure that we can be in full duplex mode. - * If not, we operate in half-duplex mode. */ - if (phydev->duplex != ugeth->oldduplex) { - new_state = 1; - if (!(phydev->duplex)) - tempval &= ~(MACCFG2_FDX); - else - tempval |= MACCFG2_FDX; - ugeth->oldduplex = phydev->duplex; - } - - if (phydev->speed != ugeth->oldspeed) { - new_state = 1; - switch (phydev->speed) { - case SPEED_1000: - tempval = ((tempval & - ~(MACCFG2_INTERFACE_MODE_MASK)) | - MACCFG2_INTERFACE_MODE_BYTE); - break; - case SPEED_100: - case SPEED_10: - tempval = ((tempval & - ~(MACCFG2_INTERFACE_MODE_MASK)) | - MACCFG2_INTERFACE_MODE_NIBBLE); - /* if reduced mode, re-set UPSMR.R10M */ - if ((ugeth->phy_interface == PHY_INTERFACE_MODE_RMII) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_ID) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID) || - (ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) { - if (phydev->speed == SPEED_10) - upsmr |= UCC_GETH_UPSMR_R10M; - else - upsmr &= ~UCC_GETH_UPSMR_R10M; - } - break; - default: - if (netif_msg_link(ugeth)) - pr_warn( - "%s: Ack! Speed (%d) is not 10/100/1000!", - dev->name, phydev->speed); - break; - } - ugeth->oldspeed = phydev->speed; - } - - if (!ugeth->oldlink) { - new_state = 1; - ugeth->oldlink = 1; - } - - if (new_state) { - /* - * To change the MAC configuration we need to disable - * the controller. To do so, we have to either grab - * ugeth->lock, which is a bad idea since 'graceful - * stop' commands might take quite a while, or we can - * quiesce driver's activity. - */ - ugeth_quiesce(ugeth); - ugeth_disable(ugeth, COMM_DIR_RX_AND_TX); - - out_be32(&ug_regs->maccfg2, tempval); - out_be32(&uf_regs->upsmr, upsmr); - - ugeth_enable(ugeth, COMM_DIR_RX_AND_TX); - ugeth_activate(ugeth); - } - } else if (ugeth->oldlink) { - new_state = 1; - ugeth->oldlink = 0; - ugeth->oldspeed = 0; - ugeth->oldduplex = -1; - } - - if (new_state && netif_msg_link(ugeth)) - phy_print_status(phydev); + netdev_watchdog_up(ugeth->ndev); } /* Initialize TBI PHY interface for communicating with the @@ -1664,8 +1452,7 @@ static void uec_configure_serdes(struct net_device *dev) struct phy_device *tbiphy; if (!ug_info->tbi_node) { - dev_warn(&dev->dev, "SGMII mode requires that the device " - "tree specify a tbi-handle\n"); + dev_warn(&dev->dev, "SGMII mode requires that the device tree specify a tbi-handle\n"); return; } @@ -1696,34 +1483,145 @@ static void uec_configure_serdes(struct net_device *dev) put_device(&tbiphy->mdio.dev); } -/* Configure the PHY for dev. - * returns 0 if success. -1 if failure - */ -static int init_phy(struct net_device *dev) +static void ugeth_mac_link_up(struct phylink_config *config, struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause) { - struct ucc_geth_private *priv = netdev_priv(dev); - struct ucc_geth_info *ug_info = priv->ug_info; - struct phy_device *phydev; + struct net_device *ndev = to_net_dev(config->dev); + struct ucc_geth_private *ugeth = netdev_priv(ndev); + struct ucc_geth_info *ug_info = ugeth->ug_info; + struct ucc_geth __iomem *ug_regs = ugeth->ug_regs; + struct ucc_fast __iomem *uf_regs = ugeth->uccf->uf_regs; + u32 old_maccfg2, maccfg2 = in_be32(&ug_regs->maccfg2); + u32 old_upsmr, upsmr = in_be32(&uf_regs->upsmr); - priv->oldlink = 0; - priv->oldspeed = 0; - priv->oldduplex = -1; + old_maccfg2 = maccfg2; + old_upsmr = upsmr; - phydev = of_phy_connect(dev, ug_info->phy_node, &adjust_link, 0, - priv->phy_interface); - if (!phydev) { - dev_err(&dev->dev, "Could not attach to PHY\n"); - return -ENODEV; + /* No length check */ + maccfg2 &= ~MACCFG2_LC; + maccfg2 &= ~MACCFG2_INTERFACE_MODE_MASK; + upsmr &= ~(UCC_GETH_UPSMR_RPM | UCC_GETH_UPSMR_R10M | + UCC_GETH_UPSMR_TBIM | UCC_GETH_UPSMR_RMM); + + if (speed == SPEED_10 || speed == SPEED_100) + maccfg2 |= MACCFG2_INTERFACE_MODE_NIBBLE; + else if (speed == SPEED_1000) + maccfg2 |= MACCFG2_INTERFACE_MODE_BYTE; + + maccfg2 |= ug_info->padAndCrc; + + if (phy_interface_mode_is_reduced(interface)) { + + if (interface != PHY_INTERFACE_MODE_RMII) + upsmr |= UCC_GETH_UPSMR_RPM; + + switch (speed) { + case SPEED_10: + upsmr |= UCC_GETH_UPSMR_R10M; + fallthrough; + case SPEED_100: + if (interface != PHY_INTERFACE_MODE_RTBI) + upsmr |= UCC_GETH_UPSMR_RMM; + } } - if (priv->phy_interface == PHY_INTERFACE_MODE_SGMII) - uec_configure_serdes(dev); + if (interface == PHY_INTERFACE_MODE_TBI || + interface == PHY_INTERFACE_MODE_RTBI) + upsmr |= UCC_GETH_UPSMR_TBIM; - phy_set_max_speed(phydev, priv->max_speed); + if (interface == PHY_INTERFACE_MODE_SGMII) + upsmr |= UCC_GETH_UPSMR_SGMM; - priv->phydev = phydev; + if (duplex == DUPLEX_HALF) + maccfg2 &= ~(MACCFG2_FDX); + else + maccfg2 |= MACCFG2_FDX; - return 0; + if (maccfg2 != old_maccfg2 || upsmr != old_upsmr) { + /* + * To change the MAC configuration we need to disable + * the controller. To do so, we have to either grab + * ugeth->lock, which is a bad idea since 'graceful + * stop' commands might take quite a while, or we can + * quiesce driver's activity. + */ + ugeth_quiesce(ugeth); + ugeth_disable(ugeth, COMM_DIR_RX_AND_TX); + + out_be32(&ug_regs->maccfg2, maccfg2); + out_be32(&uf_regs->upsmr, upsmr); + + ugeth_enable(ugeth, COMM_DIR_RX_AND_TX); + ugeth_activate(ugeth); + } + + if (interface == PHY_INTERFACE_MODE_SGMII) + uec_configure_serdes(ndev); + + if (!phylink_autoneg_inband(mode)) { + ug_info->aufc = 0; + ug_info->receiveFlowControl = rx_pause; + ug_info->transmitFlowControl = tx_pause; + + init_flow_control_params(ug_info->aufc, + ug_info->receiveFlowControl, + ug_info->transmitFlowControl, + ug_info->pausePeriod, + ug_info->extensionField, + &ugeth->uccf->uf_regs->upsmr, + &ugeth->ug_regs->uempr, + &ugeth->ug_regs->maccfg1); + } + + ugeth_enable(ugeth, COMM_DIR_RX_AND_TX); +} + +static void ugeth_mac_link_down(struct phylink_config *config, + unsigned int mode, phy_interface_t interface) +{ + struct net_device *ndev = to_net_dev(config->dev); + struct ucc_geth_private *ugeth = netdev_priv(ndev); + + ugeth_disable(ugeth, COMM_DIR_RX_AND_TX); +} + +static void ugeth_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ + struct net_device *ndev = to_net_dev(config->dev); + struct ucc_geth_private *ugeth = netdev_priv(ndev); + struct ucc_geth_info *ug_info = ugeth->ug_info; + u16 value; + + if (state->interface == PHY_INTERFACE_MODE_TBI || + state->interface == PHY_INTERFACE_MODE_RTBI) { + struct phy_device *tbiphy; + + if (!ug_info->tbi_node) + pr_warn("TBI mode requires that the device tree specify a tbi-handle\n"); + + tbiphy = of_phy_find_device(ug_info->tbi_node); + if (!tbiphy) + pr_warn("Could not get TBI device\n"); + + value = phy_read(tbiphy, ENET_TBI_MII_CR); + value &= ~0x1000; /* Turn off autonegotiation */ + phy_write(tbiphy, ENET_TBI_MII_CR, value); + + put_device(&tbiphy->mdio.dev); + } + + if (phylink_autoneg_inband(mode)) { + ug_info->aufc = 1; + + init_flow_control_params(ug_info->aufc, 1, 1, + ug_info->pausePeriod, + ug_info->extensionField, + &ugeth->uccf->uf_regs->upsmr, + &ugeth->ug_regs->uempr, + &ugeth->ug_regs->maccfg1); + } } static void ugeth_dump_regs(struct ucc_geth_private *ugeth) @@ -1995,7 +1893,6 @@ static void ucc_geth_set_multi(struct net_device *dev) static void ucc_geth_stop(struct ucc_geth_private *ugeth) { struct ucc_geth __iomem *ug_regs = ugeth->ug_regs; - struct phy_device *phydev = ugeth->phydev; ugeth_vdbg("%s: IN", __func__); @@ -2004,7 +1901,7 @@ static void ucc_geth_stop(struct ucc_geth_private *ugeth) * Must be done before disabling the controller * or deadlock may happen. */ - phy_stop(phydev); + phylink_stop(ugeth->phylink); /* Disable the controller */ ugeth_disable(ugeth, COMM_DIR_RX_AND_TX); @@ -3246,12 +3143,6 @@ static int ucc_geth_init_mac(struct ucc_geth_private *ugeth) goto err; } - err = adjust_enet_interface(ugeth); - if (err) { - netif_err(ugeth, ifup, dev, "Cannot configure net device, aborting\n"); - goto err; - } - /* Set MACSTNADDR1, MACSTNADDR2 */ /* For more details see the hardware spec. */ init_mac_station_addr_regs(dev->dev_addr[0], @@ -3263,12 +3154,6 @@ static int ucc_geth_init_mac(struct ucc_geth_private *ugeth) &ugeth->ug_regs->macstnaddr1, &ugeth->ug_regs->macstnaddr2); - err = ugeth_enable(ugeth, COMM_DIR_RX_AND_TX); - if (err) { - netif_err(ugeth, ifup, dev, "Cannot enable net device, aborting\n"); - goto err; - } - return 0; err: ucc_geth_stop(ugeth); @@ -3291,10 +3176,10 @@ static int ucc_geth_open(struct net_device *dev) return -EINVAL; } - err = init_phy(dev); + err = phylink_of_phy_connect(ugeth->phylink, ugeth->dev->of_node, 0); if (err) { - netif_err(ugeth, ifup, dev, "Cannot initialize PHY, aborting\n"); - return err; + dev_err(&dev->dev, "Could not attach to PHY\n"); + return -ENODEV; } err = ucc_geth_init_mac(ugeth); @@ -3310,13 +3195,13 @@ static int ucc_geth_open(struct net_device *dev) goto err; } - phy_start(ugeth->phydev); + phylink_start(ugeth->phylink); napi_enable(&ugeth->napi); netdev_reset_queue(dev); netif_start_queue(dev); device_set_wakeup_capable(&dev->dev, - qe_alive_during_sleep() || ugeth->phydev->irq); + qe_alive_during_sleep() || dev->phydev->irq); device_set_wakeup_enable(&dev->dev, ugeth->wol_en); return err; @@ -3337,8 +3222,7 @@ static int ucc_geth_close(struct net_device *dev) cancel_work_sync(&ugeth->timeout_work); ucc_geth_stop(ugeth); - phy_disconnect(ugeth->phydev); - ugeth->phydev = NULL; + phylink_disconnect_phy(ugeth->phylink); free_irq(ugeth->ug_info->uf_info.irq, ugeth->ndev); @@ -3372,7 +3256,7 @@ static void ucc_geth_timeout_work(struct work_struct *work) ucc_geth_stop(ugeth); ucc_geth_init_mac(ugeth); /* Must start PHY here */ - phy_start(ugeth->phydev); + phylink_start(ugeth->phylink); netif_tx_start_all_queues(dev); } @@ -3397,6 +3281,7 @@ static int ucc_geth_suspend(struct platform_device *ofdev, pm_message_t state) { struct net_device *ndev = platform_get_drvdata(ofdev); struct ucc_geth_private *ugeth = netdev_priv(ndev); + bool mac_wol = false; if (!netif_running(ndev)) return 0; @@ -3410,14 +3295,17 @@ static int ucc_geth_suspend(struct platform_device *ofdev, pm_message_t state) */ ugeth_disable(ugeth, COMM_DIR_RX_AND_TX); - if (ugeth->wol_en & WAKE_MAGIC) { + if (ugeth->wol_en & WAKE_MAGIC && !ugeth->phy_wol_en) { setbits32(ugeth->uccf->p_uccm, UCC_GETH_UCCE_MPD); setbits32(&ugeth->ug_regs->maccfg2, MACCFG2_MPE); ucc_fast_enable(ugeth->uccf, COMM_DIR_RX_AND_TX); - } else if (!(ugeth->wol_en & WAKE_PHY)) { - phy_stop(ugeth->phydev); + mac_wol = true; } + rtnl_lock(); + phylink_suspend(ugeth->phylink, mac_wol); + rtnl_unlock(); + return 0; } @@ -3451,12 +3339,9 @@ static int ucc_geth_resume(struct platform_device *ofdev) } } - ugeth->oldlink = 0; - ugeth->oldspeed = 0; - ugeth->oldduplex = -1; - - phy_stop(ugeth->phydev); - phy_start(ugeth->phydev); + rtnl_lock(); + phylink_resume(ugeth->phylink); + rtnl_unlock(); napi_enable(&ugeth->napi); netif_device_attach(ndev); @@ -3469,32 +3354,6 @@ static int ucc_geth_resume(struct platform_device *ofdev) #define ucc_geth_resume NULL #endif -static phy_interface_t to_phy_interface(const char *phy_connection_type) -{ - if (strcasecmp(phy_connection_type, "mii") == 0) - return PHY_INTERFACE_MODE_MII; - if (strcasecmp(phy_connection_type, "gmii") == 0) - return PHY_INTERFACE_MODE_GMII; - if (strcasecmp(phy_connection_type, "tbi") == 0) - return PHY_INTERFACE_MODE_TBI; - if (strcasecmp(phy_connection_type, "rmii") == 0) - return PHY_INTERFACE_MODE_RMII; - if (strcasecmp(phy_connection_type, "rgmii") == 0) - return PHY_INTERFACE_MODE_RGMII; - if (strcasecmp(phy_connection_type, "rgmii-id") == 0) - return PHY_INTERFACE_MODE_RGMII_ID; - if (strcasecmp(phy_connection_type, "rgmii-txid") == 0) - return PHY_INTERFACE_MODE_RGMII_TXID; - if (strcasecmp(phy_connection_type, "rgmii-rxid") == 0) - return PHY_INTERFACE_MODE_RGMII_RXID; - if (strcasecmp(phy_connection_type, "rtbi") == 0) - return PHY_INTERFACE_MODE_RTBI; - if (strcasecmp(phy_connection_type, "sgmii") == 0) - return PHY_INTERFACE_MODE_SGMII; - - return PHY_INTERFACE_MODE_MII; -} - static int ucc_geth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct ucc_geth_private *ugeth = netdev_priv(dev); @@ -3502,10 +3361,7 @@ static int ucc_geth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) if (!netif_running(dev)) return -EINVAL; - if (!ugeth->phydev) - return -ENODEV; - - return phy_mii_ioctl(ugeth->phydev, rq, cmd); + return phylink_mii_ioctl(ugeth->phylink, rq, cmd); } static const struct net_device_ops ucc_geth_netdev_ops = { @@ -3513,7 +3369,6 @@ static const struct net_device_ops ucc_geth_netdev_ops = { .ndo_stop = ucc_geth_close, .ndo_start_xmit = ucc_geth_start_xmit, .ndo_validate_addr = eth_validate_addr, - .ndo_change_carrier = fixed_phy_change_carrier, .ndo_set_mac_address = ucc_geth_set_mac_addr, .ndo_set_rx_mode = ucc_geth_set_multi, .ndo_tx_timeout = ucc_geth_timeout, @@ -3553,6 +3408,12 @@ static int ucc_geth_parse_clock(struct device_node *np, const char *which, return 0; } +struct phylink_mac_ops ugeth_mac_ops = { + .mac_link_up = ugeth_mac_link_up, + .mac_link_down = ugeth_mac_link_down, + .mac_config = ugeth_mac_config, +}; + static int ucc_geth_probe(struct platform_device* ofdev) { struct device *device = &ofdev->dev; @@ -3560,23 +3421,12 @@ static int ucc_geth_probe(struct platform_device* ofdev) struct net_device *dev = NULL; struct ucc_geth_private *ugeth = NULL; struct ucc_geth_info *ug_info; + struct device_node *phy_node; + struct phylink *phylink; struct resource res; - int err, ucc_num, max_speed = 0; + int err, ucc_num; const unsigned int *prop; phy_interface_t phy_interface; - static const int enet_to_speed[] = { - SPEED_10, SPEED_10, SPEED_10, - SPEED_100, SPEED_100, SPEED_100, - SPEED_1000, SPEED_1000, SPEED_1000, SPEED_1000, - }; - static const phy_interface_t enet_to_phy_interface[] = { - PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_RMII, - PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_MII, - PHY_INTERFACE_MODE_RMII, PHY_INTERFACE_MODE_RGMII, - PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_RGMII, - PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_RTBI, - PHY_INTERFACE_MODE_SGMII, - }; ugeth_vdbg("%s: IN", __func__); @@ -3612,57 +3462,35 @@ static int ucc_geth_probe(struct platform_device* ofdev) ug_info->uf_info.regs = res.start; ug_info->uf_info.irq = irq_of_parse_and_map(np, 0); - ug_info->phy_node = of_parse_phandle(np, "phy-handle", 0); - if (!ug_info->phy_node && of_phy_is_fixed_link(np)) { - /* - * In the case of a fixed PHY, the DT node associated - * to the PHY is the Ethernet MAC DT node. - */ - err = of_phy_register_fixed_link(np); - if (err) - return err; - ug_info->phy_node = of_node_get(np); - } - /* Find the TBI PHY node. If it's not there, we don't support SGMII */ ug_info->tbi_node = of_parse_phandle(np, "tbi-handle", 0); - /* get the phy interface type, or default to MII */ - prop = of_get_property(np, "phy-connection-type", NULL); - if (!prop) { - /* handle interface property present in old trees */ - prop = of_get_property(ug_info->phy_node, "interface", NULL); - if (prop != NULL) { - phy_interface = enet_to_phy_interface[*prop]; - max_speed = enet_to_speed[*prop]; - } else - phy_interface = PHY_INTERFACE_MODE_MII; - } else { - phy_interface = to_phy_interface((const char *)prop); + phy_node = of_parse_phandle(np, "phy-handle", 0); + if (phy_node) { + prop = of_get_property(phy_node, "interface", NULL); + if (prop) { + dev_err(&ofdev->dev, + "Device-tree property 'interface' is no longer supported. Please use 'phy-connection-type' instead."); + of_node_put(phy_node); + err = -EINVAL; + goto err_put_tbi; + } + of_node_put(phy_node); } - /* get speed, or derive from PHY interface */ - if (max_speed == 0) - switch (phy_interface) { - case PHY_INTERFACE_MODE_GMII: - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_TXID: - case PHY_INTERFACE_MODE_TBI: - case PHY_INTERFACE_MODE_RTBI: - case PHY_INTERFACE_MODE_SGMII: - max_speed = SPEED_1000; - break; - default: - max_speed = SPEED_100; - break; - } + err = of_get_phy_mode(np, &phy_interface); + if (err) { + dev_err(&ofdev->dev, "Invalid phy-connection-type"); + goto err_put_tbi; + } - if (max_speed == SPEED_1000) { + if (phy_interface == PHY_INTERFACE_MODE_GMII || + phy_interface_mode_is_rgmii(phy_interface) || + phy_interface == PHY_INTERFACE_MODE_TBI || + phy_interface == PHY_INTERFACE_MODE_RTBI || + phy_interface == PHY_INTERFACE_MODE_SGMII) { unsigned int snums = qe_get_num_of_snums(); - /* configure muram FIFOs for gigabit operation */ ug_info->uf_info.urfs = UCC_GETH_URFS_GIGA_INIT; ug_info->uf_info.urfet = UCC_GETH_URFET_GIGA_INIT; ug_info->uf_info.urfset = UCC_GETH_URFSET_GIGA_INIT; @@ -3691,7 +3519,7 @@ static int ucc_geth_probe(struct platform_device* ofdev) dev = devm_alloc_etherdev(&ofdev->dev, sizeof(*ugeth)); if (!dev) { err = -ENOMEM; - goto err_deregister_fixed_link; + goto err_put_tbi; } ugeth = netdev_priv(dev); @@ -3718,23 +3546,50 @@ static int ucc_geth_probe(struct platform_device* ofdev) dev->max_mtu = 1518; ugeth->msg_enable = netif_msg_init(debug.msg_enable, UGETH_MSG_DEFAULT); - ugeth->phy_interface = phy_interface; - ugeth->max_speed = max_speed; - /* Carrier starts down, phylib will bring it up */ - netif_carrier_off(dev); + ugeth->phylink_config.dev = &dev->dev; + ugeth->phylink_config.type = PHYLINK_NETDEV; + + ugeth->phylink_config.mac_capabilities = + MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD; + + __set_bit(PHY_INTERFACE_MODE_MII, + ugeth->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_RMII, + ugeth->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_GMII, + ugeth->phylink_config.supported_interfaces); + phy_interface_set_rgmii(ugeth->phylink_config.supported_interfaces); + + if (ug_info->tbi_node) { + __set_bit(PHY_INTERFACE_MODE_SGMII, + ugeth->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_TBI, + ugeth->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_RTBI, + ugeth->phylink_config.supported_interfaces); + } + + phylink = phylink_create(&ugeth->phylink_config, dev_fwnode(&dev->dev), + phy_interface, &ugeth_mac_ops); + if (IS_ERR(phylink)) { + err = PTR_ERR(phylink); + goto err_put_tbi; + } + + ugeth->phylink = phylink; err = devm_register_netdev(&ofdev->dev, dev); if (err) { if (netif_msg_probe(ugeth)) pr_err("%s: Cannot register net device, aborting\n", dev->name); - goto err_deregister_fixed_link; + goto err_destroy_phylink; } err = of_get_ethdev_address(np, dev); if (err == -EPROBE_DEFER) - goto err_deregister_fixed_link; + goto err_destroy_phylink; ugeth->ug_info = ug_info; ugeth->dev = device; @@ -3743,11 +3598,11 @@ static int ucc_geth_probe(struct platform_device* ofdev) return 0; -err_deregister_fixed_link: - if (of_phy_is_fixed_link(np)) - of_phy_deregister_fixed_link(np); +err_destroy_phylink: + phylink_destroy(phylink); +err_put_tbi: of_node_put(ug_info->tbi_node); - of_node_put(ug_info->phy_node); + return err; } @@ -3755,13 +3610,10 @@ static void ucc_geth_remove(struct platform_device* ofdev) { struct net_device *dev = platform_get_drvdata(ofdev); struct ucc_geth_private *ugeth = netdev_priv(dev); - struct device_node *np = ofdev->dev.of_node; ucc_geth_memclean(ugeth); - if (of_phy_is_fixed_link(np)) - of_phy_deregister_fixed_link(np); + phylink_destroy(ugeth->phylink); of_node_put(ugeth->ug_info->tbi_node); - of_node_put(ugeth->ug_info->phy_node); } static const struct of_device_id ucc_geth_match[] = { diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h index 4294ed096ebb..38789faae706 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.h +++ b/drivers/net/ethernet/freescale/ucc_geth.h @@ -16,6 +16,7 @@ #include #include +#include #include #include @@ -921,7 +922,8 @@ struct ucc_geth_hardware_statistics { #define UCC_GETH_UPSMR_INIT UCC_GETH_UPSMR_RES1 #define UCC_GETH_MACCFG1_INIT 0 -#define UCC_GETH_MACCFG2_INIT (MACCFG2_RESERVED_1) +#define UCC_GETH_MACCFG2_INIT (MACCFG2_RESERVED_1 | \ + (7 << MACCFG2_PREL_SHIFT)) /* Ethernet Address Type. */ enum enet_addr_type { @@ -1073,6 +1075,9 @@ struct ucc_geth_tad_params { u16 vid; }; +struct phylink; +struct phylink_config; + /* GETH protocol initialization structure */ struct ucc_geth_info { struct ucc_fast_info uf_info; @@ -1088,7 +1093,6 @@ struct ucc_geth_info { u8 miminumInterFrameGapEnforcement; u8 backToBackInterFrameGap; int ipAddressAlignment; - int lengthCheckRx; u32 mblinterval; u16 nortsrbytetime; u8 fracsiz; @@ -1114,7 +1118,6 @@ struct ucc_geth_info { int transmitFlowControl; u8 maxGroupAddrInHash; u8 maxIndAddrInHash; - u8 prel; u16 maxFrameLength; u16 minFrameLength; u16 maxD1Length; @@ -1125,7 +1128,6 @@ struct ucc_geth_info { u32 eventRegMask; u16 pausePeriod; u16 extensionField; - struct device_node *phy_node; struct device_node *tbi_node; u8 weightfactor[NUM_TX_QUEUES]; u8 interruptcoalescingmaxvalue[NUM_RX_QUEUES]; @@ -1210,14 +1212,12 @@ struct ucc_geth_private { u16 skb_dirtytx[NUM_TX_QUEUES]; struct ugeth_mii_info *mii_info; - struct phy_device *phydev; - phy_interface_t phy_interface; - int max_speed; uint32_t msg_enable; - int oldspeed; - int oldduplex; - int oldlink; - int wol_en; + u32 wol_en; + u32 phy_wol_en; + + struct phylink *phylink; + struct phylink_config phylink_config; struct device_node *node; }; diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c index 699f346faf5c..1fb49e5a414a 100644 --- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c +++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c @@ -104,14 +104,8 @@ static int uec_get_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { struct ucc_geth_private *ugeth = netdev_priv(netdev); - struct phy_device *phydev = ugeth->phydev; - if (!phydev) - return -ENODEV; - - phy_ethtool_ksettings_get(phydev, cmd); - - return 0; + return phylink_ethtool_ksettings_get(ugeth->phylink, cmd); } static int @@ -119,12 +113,8 @@ uec_set_ksettings(struct net_device *netdev, const struct ethtool_link_ksettings *cmd) { struct ucc_geth_private *ugeth = netdev_priv(netdev); - struct phy_device *phydev = ugeth->phydev; - if (!phydev) - return -ENODEV; - - return phy_ethtool_ksettings_set(phydev, cmd); + return phylink_ethtool_ksettings_set(ugeth->phylink, cmd); } static void @@ -133,12 +123,7 @@ uec_get_pauseparam(struct net_device *netdev, { struct ucc_geth_private *ugeth = netdev_priv(netdev); - pause->autoneg = ugeth->phydev->autoneg; - - if (ugeth->ug_info->receiveFlowControl) - pause->rx_pause = 1; - if (ugeth->ug_info->transmitFlowControl) - pause->tx_pause = 1; + return phylink_ethtool_get_pauseparam(ugeth->phylink, pause); } static int @@ -146,30 +131,11 @@ uec_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { struct ucc_geth_private *ugeth = netdev_priv(netdev); - int ret = 0; ugeth->ug_info->receiveFlowControl = pause->rx_pause; ugeth->ug_info->transmitFlowControl = pause->tx_pause; - if (ugeth->phydev->autoneg) { - if (netif_running(netdev)) { - /* FIXME: automatically restart */ - netdev_info(netdev, "Please re-open the interface\n"); - } - } else { - struct ucc_geth_info *ug_info = ugeth->ug_info; - - ret = init_flow_control_params(ug_info->aufc, - ug_info->receiveFlowControl, - ug_info->transmitFlowControl, - ug_info->pausePeriod, - ug_info->extensionField, - &ugeth->uccf->uf_regs->upsmr, - &ugeth->ug_regs->uempr, - &ugeth->ug_regs->maccfg1); - } - - return ret; + return phylink_ethtool_set_pauseparam(ugeth->phylink, pause); } static uint32_t @@ -343,28 +309,42 @@ uec_get_drvinfo(struct net_device *netdev, static void uec_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct ucc_geth_private *ugeth = netdev_priv(netdev); - struct phy_device *phydev = ugeth->phydev; - if (phydev && phydev->irq) - wol->supported |= WAKE_PHY; + phylink_ethtool_get_wol(ugeth->phylink, wol); + if (qe_alive_during_sleep()) wol->supported |= WAKE_MAGIC; - wol->wolopts = ugeth->wol_en; + wol->wolopts |= ugeth->wol_en; } static int uec_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct ucc_geth_private *ugeth = netdev_priv(netdev); - struct phy_device *phydev = ugeth->phydev; + int ret = 0; - if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) - return -EINVAL; - else if (wol->wolopts & WAKE_PHY && (!phydev || !phydev->irq)) - return -EINVAL; - else if (wol->wolopts & WAKE_MAGIC && !qe_alive_during_sleep()) + ret = phylink_ethtool_set_wol(ugeth->phylink, wol); + if (ret == -EOPNOTSUPP) { + ugeth->phy_wol_en = 0; + } else if (ret) { + return ret; + } else { + ugeth->phy_wol_en = wol->wolopts; + goto out; + } + + /* If the PHY isn't handling the WoL and the MAC is asked to more than + * WAKE_MAGIC, error-out + */ + if (!ugeth->phy_wol_en && + wol->wolopts & ~WAKE_MAGIC) return -EINVAL; + if (wol->wolopts & WAKE_MAGIC && + !qe_alive_during_sleep()) + return -EINVAL; + +out: ugeth->wol_en = wol->wolopts; device_set_wakeup_enable(&netdev->dev, ugeth->wol_en); diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index dd92949bb214..8167cc5fb0df 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1140,6 +1140,7 @@ int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx, void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid); bool gve_tx_poll(struct gve_notify_block *block, int budget); bool gve_xdp_poll(struct gve_notify_block *block, int budget); +int gve_xsk_tx_poll(struct gve_notify_block *block, int budget); int gve_tx_alloc_rings_gqi(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg); void gve_tx_free_rings_gqi(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 060e0e674938..aa7d723011d0 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -1128,20 +1128,6 @@ int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id) return gve_adminq_execute_cmd(priv, &cmd); } -int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu) -{ - union gve_adminq_command cmd; - - memset(&cmd, 0, sizeof(cmd)); - cmd.opcode = cpu_to_be32(GVE_ADMINQ_SET_DRIVER_PARAMETER); - cmd.set_driver_param = (struct gve_adminq_set_driver_parameter) { - .parameter_type = cpu_to_be32(GVE_SET_PARAM_MTU), - .parameter_value = cpu_to_be64(mtu), - }; - - return gve_adminq_execute_cmd(priv, &cmd); -} - int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len, dma_addr_t stats_report_addr, u64 interval) { diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 863683de9694..228217458275 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -612,7 +612,6 @@ int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 queue_id); int gve_adminq_register_page_list(struct gve_priv *priv, struct gve_queue_page_list *qpl); int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id); -int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu); int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len, dma_addr_t stats_report_addr, u64 interval); int gve_adminq_verify_driver_compatibility(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index e171ca248f9a..533e659b15b3 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -333,6 +333,14 @@ int gve_napi_poll(struct napi_struct *napi, int budget) if (block->rx) { work_done = gve_rx_poll(block, budget); + + /* Poll XSK TX as part of RX NAPI. Setup re-poll based on max of + * TX and RX work done. + */ + if (priv->xdp_prog) + work_done = max_t(int, work_done, + gve_xsk_tx_poll(block, budget)); + reschedule |= work_done == budget; } @@ -922,11 +930,13 @@ static void gve_init_sync_stats(struct gve_priv *priv) static void gve_tx_get_curr_alloc_cfg(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg) { + int num_xdp_queues = priv->xdp_prog ? priv->rx_cfg.num_queues : 0; + cfg->qcfg = &priv->tx_cfg; cfg->raw_addressing = !gve_is_qpl(priv); cfg->ring_size = priv->tx_desc_cnt; cfg->start_idx = 0; - cfg->num_rings = gve_num_tx_queues(priv); + cfg->num_rings = priv->tx_cfg.num_queues + num_xdp_queues; cfg->tx = priv->tx; } @@ -1623,8 +1633,8 @@ static int gve_xsk_pool_enable(struct net_device *dev, if (err) return err; - /* If XDP prog is not installed, return */ - if (!priv->xdp_prog) + /* If XDP prog is not installed or interface is down, return. */ + if (!priv->xdp_prog || !netif_running(dev)) return 0; rx = &priv->rx[qid]; @@ -1669,21 +1679,16 @@ static int gve_xsk_pool_disable(struct net_device *dev, if (qid >= priv->rx_cfg.num_queues) return -EINVAL; - /* If XDP prog is not installed, unmap DMA and return */ - if (!priv->xdp_prog) + /* If XDP prog is not installed or interface is down, unmap DMA and + * return. + */ + if (!priv->xdp_prog || !netif_running(dev)) goto done; - tx_qid = gve_xdp_tx_queue_id(priv, qid); - if (!netif_running(dev)) { - priv->rx[qid].xsk_pool = NULL; - xdp_rxq_info_unreg(&priv->rx[qid].xsk_rxq); - priv->tx[tx_qid].xsk_pool = NULL; - goto done; - } - napi_rx = &priv->ntfy_blocks[priv->rx[qid].ntfy_id].napi; napi_disable(napi_rx); /* make sure current rx poll is done */ + tx_qid = gve_xdp_tx_queue_id(priv, qid); napi_tx = &priv->ntfy_blocks[priv->tx[tx_qid].ntfy_id].napi; napi_disable(napi_tx); /* make sure current tx poll is done */ @@ -1709,24 +1714,20 @@ done: static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct gve_priv *priv = netdev_priv(dev); - int tx_queue_id = gve_xdp_tx_queue_id(priv, queue_id); + struct napi_struct *napi; + + if (!gve_get_napi_enabled(priv)) + return -ENETDOWN; if (queue_id >= priv->rx_cfg.num_queues || !priv->xdp_prog) return -EINVAL; - if (flags & XDP_WAKEUP_TX) { - struct gve_tx_ring *tx = &priv->tx[tx_queue_id]; - struct napi_struct *napi = - &priv->ntfy_blocks[tx->ntfy_id].napi; - - if (!napi_if_scheduled_mark_missed(napi)) { - /* Call local_bh_enable to trigger SoftIRQ processing */ - local_bh_disable(); - napi_schedule(napi); - local_bh_enable(); - } - - tx->xdp_xsk_wakeup++; + napi = &priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_id)].napi; + if (!napi_if_scheduled_mark_missed(napi)) { + /* Call local_bh_enable to trigger SoftIRQ processing */ + local_bh_disable(); + napi_schedule(napi); + local_bh_enable(); } return 0; @@ -1837,6 +1838,7 @@ int gve_adjust_queues(struct gve_priv *priv, { struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; + int num_xdp_queues; int err; gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg); @@ -1847,6 +1849,10 @@ int gve_adjust_queues(struct gve_priv *priv, rx_alloc_cfg.qcfg = &new_rx_config; tx_alloc_cfg.num_rings = new_tx_config.num_queues; + /* Add dedicated XDP TX queues if enabled. */ + num_xdp_queues = priv->xdp_prog ? new_rx_config.num_queues : 0; + tx_alloc_cfg.num_rings += num_xdp_queues; + if (netif_running(priv->dev)) { err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); return err; @@ -1899,6 +1905,9 @@ static void gve_turndown(struct gve_priv *priv) gve_clear_napi_enabled(priv); gve_clear_report_stats(priv); + + /* Make sure that all traffic is finished processing. */ + synchronize_net(); } static void gve_turnup(struct gve_priv *priv) @@ -2232,14 +2241,18 @@ static void gve_service_task(struct work_struct *work) static void gve_set_netdev_xdp_features(struct gve_priv *priv) { + xdp_features_t xdp_features; + if (priv->queue_format == GVE_GQI_QPL_FORMAT) { - priv->dev->xdp_features = NETDEV_XDP_ACT_BASIC; - priv->dev->xdp_features |= NETDEV_XDP_ACT_REDIRECT; - priv->dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; - priv->dev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; + xdp_features = NETDEV_XDP_ACT_BASIC; + xdp_features |= NETDEV_XDP_ACT_REDIRECT; + xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; + xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; } else { - priv->dev->xdp_features = 0; + xdp_features = 0; } + + xdp_set_features_flag(priv->dev, xdp_features); } static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index e7fb7d6d283d..4350ebd9c2bd 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -206,7 +206,10 @@ void gve_tx_stop_ring_gqi(struct gve_priv *priv, int idx) return; gve_remove_napi(priv, ntfy_idx); - gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); + if (tx->q_num < priv->tx_cfg.num_queues) + gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); + else + gve_clean_xdp_done(priv, tx, priv->tx_desc_cnt); netdev_tx_reset_queue(tx->netdev_txq); gve_tx_remove_from_block(priv, idx); } @@ -834,9 +837,12 @@ int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct gve_tx_ring *tx; int i, err = 0, qid; - if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK) || !priv->xdp_prog) return -EINVAL; + if (!gve_get_napi_enabled(priv)) + return -ENETDOWN; + qid = gve_xdp_tx_queue_id(priv, smp_processor_id() % priv->num_xdp_queues); @@ -975,33 +981,41 @@ out: return sent; } +int gve_xsk_tx_poll(struct gve_notify_block *rx_block, int budget) +{ + struct gve_rx_ring *rx = rx_block->rx; + struct gve_priv *priv = rx->gve; + struct gve_tx_ring *tx; + int sent = 0; + + tx = &priv->tx[gve_xdp_tx_queue_id(priv, rx->q_num)]; + if (tx->xsk_pool) { + sent = gve_xsk_tx(priv, tx, budget); + + u64_stats_update_begin(&tx->statss); + tx->xdp_xsk_sent += sent; + u64_stats_update_end(&tx->statss); + if (xsk_uses_need_wakeup(tx->xsk_pool)) + xsk_set_tx_need_wakeup(tx->xsk_pool); + } + + return sent; +} + bool gve_xdp_poll(struct gve_notify_block *block, int budget) { struct gve_priv *priv = block->priv; struct gve_tx_ring *tx = block->tx; u32 nic_done; - bool repoll; u32 to_do; /* Find out how much work there is to be done */ nic_done = gve_tx_load_event_counter(priv, tx); to_do = min_t(u32, (nic_done - tx->done), budget); gve_clean_xdp_done(priv, tx, to_do); - repoll = nic_done != tx->done; - - if (tx->xsk_pool) { - int sent = gve_xsk_tx(priv, tx, budget); - - u64_stats_update_begin(&tx->statss); - tx->xdp_xsk_sent += sent; - u64_stats_update_end(&tx->statss); - repoll |= (sent == budget); - if (xsk_uses_need_wakeup(tx->xsk_pool)) - xsk_set_tx_need_wakeup(tx->xsk_pool); - } /* If we still have work we want to repoll */ - return repoll; + return nic_done != tx->done; } bool gve_tx_poll(struct gve_notify_block *block, int budget) diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index f879426cb552..394debc62268 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -1146,8 +1146,7 @@ static void gve_handle_miss_completion(struct gve_priv *priv, /* jiffies can wraparound but time comparisons can handle overflows. */ pending_packet->timeout_jiffies = jiffies + - msecs_to_jiffies(GVE_REINJECT_COMPL_TIMEOUT * - MSEC_PER_SEC); + secs_to_jiffies(GVE_REINJECT_COMPL_TIMEOUT); add_to_list(tx, &tx->dqo_compl.miss_completions, pending_packet); *bytes += pending_packet->skb->len; @@ -1191,8 +1190,7 @@ static void remove_miss_completions(struct gve_priv *priv, pending_packet->state = GVE_PACKET_STATE_TIMED_OUT_COMPL; pending_packet->timeout_jiffies = jiffies + - msecs_to_jiffies(GVE_DEALLOCATE_COMPL_TIMEOUT * - MSEC_PER_SEC); + secs_to_jiffies(GVE_DEALLOCATE_COMPL_TIMEOUT); /* Maintain pending packet in another list so the packet can be * unallocated at a later time. */ diff --git a/drivers/net/ethernet/hisilicon/hibmcge/Makefile b/drivers/net/ethernet/hisilicon/hibmcge/Makefile index ae58ac38c206..7ea15f9ef849 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/Makefile +++ b/drivers/net/ethernet/hisilicon/hibmcge/Makefile @@ -5,4 +5,5 @@ obj-$(CONFIG_HIBMCGE) += hibmcge.o -hibmcge-objs = hbg_main.o hbg_hw.o hbg_mdio.o hbg_irq.o hbg_txrx.o hbg_ethtool.o +hibmcge-objs = hbg_main.o hbg_hw.o hbg_mdio.o hbg_irq.o hbg_txrx.o hbg_ethtool.o \ + hbg_debugfs.o hbg_err.o diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h index 96daf058d387..b4300d8ea4ad 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h @@ -4,6 +4,7 @@ #ifndef __HBG_COMMON_H #define __HBG_COMMON_H +#include #include #include #include "hbg_reg.h" @@ -33,6 +34,14 @@ enum hbg_tx_state { enum hbg_nic_state { HBG_NIC_STATE_EVENT_HANDLING = 0, + HBG_NIC_STATE_RESETTING, + HBG_NIC_STATE_RESET_FAIL, +}; + +enum hbg_reset_type { + HBG_RESET_TYPE_NONE = 0, + HBG_RESET_TYPE_FLR, + HBG_RESET_TYPE_FUNCTION, }; struct hbg_buffer { @@ -84,6 +93,7 @@ struct hbg_dev_specs { u32 vlan_layers; u32 max_mtu; u32 min_mtu; + u32 uc_mac_num; u32 max_frame_len; u32 rx_buf_size; @@ -114,6 +124,22 @@ struct hbg_mac { u32 duplex; u32 autoneg; u32 link_status; + u32 pause_autoneg; +}; + +struct hbg_mac_table_entry { + u8 addr[ETH_ALEN]; +}; + +struct hbg_mac_filter { + struct hbg_mac_table_entry *mac_table; + u32 table_max_len; + bool enabled; +}; + +/* saved for restore after rest */ +struct hbg_user_def { + struct ethtool_pauseparam pause_param; }; struct hbg_priv { @@ -126,6 +152,9 @@ struct hbg_priv { struct hbg_vector vectors; struct hbg_ring tx_ring; struct hbg_ring rx_ring; + struct hbg_mac_filter filter; + enum hbg_reset_type reset_type; + struct hbg_user_def user_def; }; #endif diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c new file mode 100644 index 000000000000..8473c43d171a --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (c) 2024 Hisilicon Limited. + +#include +#include +#include +#include +#include +#include "hbg_common.h" +#include "hbg_debugfs.h" +#include "hbg_hw.h" +#include "hbg_irq.h" +#include "hbg_txrx.h" + +static struct dentry *hbg_dbgfs_root; + +struct hbg_dbg_info { + const char *name; + int (*read)(struct seq_file *seq, void *data); +}; + +#define state_str_true_false(p, s) str_true_false(test_bit(s, &(p)->state)) + +static void hbg_dbg_ring(struct hbg_priv *priv, struct hbg_ring *ring, + struct seq_file *s) +{ + u32 irq_mask = ring->dir == HBG_DIR_TX ? HBG_INT_MSK_TX_B : + HBG_INT_MSK_RX_B; + + seq_printf(s, "ring used num: %u\n", + hbg_get_queue_used_num(ring)); + seq_printf(s, "ring max num: %u\n", ring->len); + seq_printf(s, "ring head: %u, tail: %u\n", ring->head, ring->tail); + seq_printf(s, "fifo used num: %u\n", + hbg_hw_get_fifo_used_num(priv, ring->dir)); + seq_printf(s, "fifo max num: %u\n", + hbg_get_spec_fifo_max_num(priv, ring->dir)); + seq_printf(s, "irq enabled: %s\n", + str_true_false(hbg_hw_irq_is_enabled(priv, irq_mask))); +} + +static int hbg_dbg_tx_ring(struct seq_file *s, void *unused) +{ + struct net_device *netdev = dev_get_drvdata(s->private); + struct hbg_priv *priv = netdev_priv(netdev); + + hbg_dbg_ring(priv, &priv->tx_ring, s); + return 0; +} + +static int hbg_dbg_rx_ring(struct seq_file *s, void *unused) +{ + struct net_device *netdev = dev_get_drvdata(s->private); + struct hbg_priv *priv = netdev_priv(netdev); + + hbg_dbg_ring(priv, &priv->rx_ring, s); + return 0; +} + +static int hbg_dbg_irq_info(struct seq_file *s, void *unused) +{ + struct net_device *netdev = dev_get_drvdata(s->private); + struct hbg_priv *priv = netdev_priv(netdev); + struct hbg_irq_info *info; + u32 i; + + for (i = 0; i < priv->vectors.info_array_len; i++) { + info = &priv->vectors.info_array[i]; + seq_printf(s, + "%-20s: enabled: %-5s, logged: %-5s, count: %llu\n", + info->name, + str_true_false(hbg_hw_irq_is_enabled(priv, + info->mask)), + str_true_false(info->need_print), + info->count); + } + + return 0; +} + +static int hbg_dbg_mac_table(struct seq_file *s, void *unused) +{ + struct net_device *netdev = dev_get_drvdata(s->private); + struct hbg_priv *priv = netdev_priv(netdev); + struct hbg_mac_filter *filter; + u32 i; + + filter = &priv->filter; + seq_printf(s, "mac addr max count: %u\n", filter->table_max_len); + seq_printf(s, "filter enabled: %s\n", str_true_false(filter->enabled)); + + for (i = 0; i < filter->table_max_len; i++) { + if (is_zero_ether_addr(filter->mac_table[i].addr)) + continue; + + seq_printf(s, "[%u] %pM\n", i, filter->mac_table[i].addr); + } + + return 0; +} + +static const char * const reset_type_str[] = {"None", "FLR", "Function"}; + +static int hbg_dbg_nic_state(struct seq_file *s, void *unused) +{ + struct net_device *netdev = dev_get_drvdata(s->private); + struct hbg_priv *priv = netdev_priv(netdev); + + seq_printf(s, "event handling state: %s\n", + state_str_true_false(priv, HBG_NIC_STATE_EVENT_HANDLING)); + seq_printf(s, "resetting state: %s\n", + state_str_true_false(priv, HBG_NIC_STATE_RESETTING)); + seq_printf(s, "reset fail state: %s\n", + state_str_true_false(priv, HBG_NIC_STATE_RESET_FAIL)); + seq_printf(s, "last reset type: %s\n", + reset_type_str[priv->reset_type]); + + return 0; +} + +static const struct hbg_dbg_info hbg_dbg_infos[] = { + { "tx_ring", hbg_dbg_tx_ring }, + { "rx_ring", hbg_dbg_rx_ring }, + { "irq_info", hbg_dbg_irq_info }, + { "mac_table", hbg_dbg_mac_table }, + { "nic_state", hbg_dbg_nic_state }, +}; + +static void hbg_debugfs_uninit(void *data) +{ + debugfs_remove_recursive((struct dentry *)data); +} + +void hbg_debugfs_init(struct hbg_priv *priv) +{ + const char *name = pci_name(priv->pdev); + struct device *dev = &priv->pdev->dev; + struct dentry *root; + u32 i; + + root = debugfs_create_dir(name, hbg_dbgfs_root); + + for (i = 0; i < ARRAY_SIZE(hbg_dbg_infos); i++) + debugfs_create_devm_seqfile(dev, hbg_dbg_infos[i].name, + root, hbg_dbg_infos[i].read); + + /* Ignore the failure because debugfs is not a key feature. */ + devm_add_action_or_reset(dev, hbg_debugfs_uninit, root); +} + +void hbg_debugfs_register(void) +{ + hbg_dbgfs_root = debugfs_create_dir("hibmcge", NULL); +} + +void hbg_debugfs_unregister(void) +{ + debugfs_remove_recursive(hbg_dbgfs_root); + hbg_dbgfs_root = NULL; +} diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.h new file mode 100644 index 000000000000..80670d66bbeb --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2024 Hisilicon Limited. */ + +#ifndef __HBG_DEBUGFS_H +#define __HBG_DEBUGFS_H + +void hbg_debugfs_register(void); +void hbg_debugfs_unregister(void); + +void hbg_debugfs_init(struct hbg_priv *priv); + +#endif diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c new file mode 100644 index 000000000000..4d1f4a33391a --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (c) 2024 Hisilicon Limited. + +#include +#include +#include +#include +#include "hbg_common.h" +#include "hbg_err.h" +#include "hbg_hw.h" + +static void hbg_restore_mac_table(struct hbg_priv *priv) +{ + struct hbg_mac_filter *filter = &priv->filter; + u64 addr; + u32 i; + + for (i = 0; i < filter->table_max_len; i++) + if (!is_zero_ether_addr(filter->mac_table[i].addr)) { + addr = ether_addr_to_u64(filter->mac_table[i].addr); + hbg_hw_set_uc_addr(priv, addr, i); + } + + hbg_hw_set_mac_filter_enable(priv, priv->filter.enabled); +} + +static void hbg_restore_user_def_settings(struct hbg_priv *priv) +{ + struct ethtool_pauseparam *pause_param = &priv->user_def.pause_param; + + hbg_restore_mac_table(priv); + hbg_hw_set_mtu(priv, priv->netdev->mtu); + hbg_hw_set_pause_enable(priv, pause_param->tx_pause, + pause_param->rx_pause); +} + +int hbg_rebuild(struct hbg_priv *priv) +{ + int ret; + + ret = hbg_hw_init(priv); + if (ret) + return ret; + + hbg_restore_user_def_settings(priv); + return 0; +} + +static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type) +{ + int ret; + + ASSERT_RTNL(); + + if (netif_running(priv->netdev)) { + dev_warn(&priv->pdev->dev, + "failed to reset because port is up\n"); + return -EBUSY; + } + + priv->reset_type = type; + set_bit(HBG_NIC_STATE_RESETTING, &priv->state); + clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); + ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET); + if (ret) { + set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); + } + + return ret; +} + +static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type) +{ + int ret; + + if (!test_bit(HBG_NIC_STATE_RESETTING, &priv->state) || + type != priv->reset_type) + return 0; + + ASSERT_RTNL(); + + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); + ret = hbg_rebuild(priv); + if (ret) { + set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); + dev_err(&priv->pdev->dev, "failed to rebuild after reset\n"); + return ret; + } + + dev_info(&priv->pdev->dev, "reset done\n"); + return ret; +} + +/* must be protected by rtnl lock */ +int hbg_reset(struct hbg_priv *priv) +{ + int ret; + + ASSERT_RTNL(); + ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION); + if (ret) + return ret; + + return hbg_reset_done(priv, HBG_RESET_TYPE_FUNCTION); +} + +static void hbg_pci_err_reset_prepare(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct hbg_priv *priv = netdev_priv(netdev); + + rtnl_lock(); + hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR); +} + +static void hbg_pci_err_reset_done(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct hbg_priv *priv = netdev_priv(netdev); + + hbg_reset_done(priv, HBG_RESET_TYPE_FLR); + rtnl_unlock(); +} + +static const struct pci_error_handlers hbg_pci_err_handler = { + .reset_prepare = hbg_pci_err_reset_prepare, + .reset_done = hbg_pci_err_reset_done, +}; + +void hbg_set_pci_err_handler(struct pci_driver *pdrv) +{ + pdrv->err_handler = &hbg_pci_err_handler; +} diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h new file mode 100644 index 000000000000..d7828e446308 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2024 Hisilicon Limited. */ + +#ifndef __HBG_ERR_H +#define __HBG_ERR_H + +#include + +void hbg_set_pci_err_handler(struct pci_driver *pdrv); +int hbg_reset(struct hbg_priv *priv); +int hbg_rebuild(struct hbg_priv *priv); + +#endif diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c index c3370114aef3..00364a438ec2 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c @@ -3,12 +3,193 @@ #include #include +#include +#include "hbg_common.h" +#include "hbg_err.h" #include "hbg_ethtool.h" +#include "hbg_hw.h" + +enum hbg_reg_dump_type { + HBG_DUMP_REG_TYPE_SPEC = 0, + HBG_DUMP_REG_TYPE_MDIO, + HBG_DUMP_REG_TYPE_GMAC, + HBG_DUMP_REG_TYPE_PCU, +}; + +struct hbg_reg_info { + u32 type; + u32 offset; + u32 val; +}; + +#define HBG_DUMP_SPEC_I(offset) {HBG_DUMP_REG_TYPE_SPEC, offset, 0} +#define HBG_DUMP_MDIO_I(offset) {HBG_DUMP_REG_TYPE_MDIO, offset, 0} +#define HBG_DUMP_GMAC_I(offset) {HBG_DUMP_REG_TYPE_GMAC, offset, 0} +#define HBG_DUMP_PCU_I(offset) {HBG_DUMP_REG_TYPE_PCU, offset, 0} + +static const struct hbg_reg_info hbg_dump_reg_infos[] = { + /* dev specs */ + HBG_DUMP_SPEC_I(HBG_REG_SPEC_VALID_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_EVENT_REQ_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_MAC_ID_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_PHY_ID_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_MAC_ADDR_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_MAC_ADDR_HIGH_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_UC_MAC_NUM_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_MDIO_FREQ_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_MAX_MTU_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_MIN_MTU_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_TX_FIFO_NUM_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_RX_FIFO_NUM_ADDR), + HBG_DUMP_SPEC_I(HBG_REG_VLAN_LAYERS_ADDR), + + /* mdio */ + HBG_DUMP_MDIO_I(HBG_REG_MDIO_COMMAND_ADDR), + HBG_DUMP_MDIO_I(HBG_REG_MDIO_ADDR_ADDR), + HBG_DUMP_MDIO_I(HBG_REG_MDIO_WDATA_ADDR), + HBG_DUMP_MDIO_I(HBG_REG_MDIO_RDATA_ADDR), + HBG_DUMP_MDIO_I(HBG_REG_MDIO_STA_ADDR), + + /* gmac */ + HBG_DUMP_GMAC_I(HBG_REG_DUPLEX_TYPE_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_FD_FC_TYPE_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_FC_TX_TIMER_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_FD_FC_ADDR_LOW_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_FD_FC_ADDR_HIGH_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_MAX_FRAME_SIZE_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_PORT_MODE_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_PORT_ENABLE_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_PAUSE_ENABLE_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_AN_NEG_STATE_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_TRANSMIT_CTRL_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_REC_FILT_CTRL_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_LINE_LOOP_BACK_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_CF_CRC_STRIP_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_MODE_CHANGE_EN_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_LOOP_REG_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_RECV_CTRL_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_VLAN_CODE_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_0_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_0_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_1_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_1_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_2_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_2_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_3_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_3_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_4_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_4_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_5_ADDR), + HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_5_ADDR), + + /* pcu */ + HBG_DUMP_PCU_I(HBG_REG_TX_FIFO_THRSLD_ADDR), + HBG_DUMP_PCU_I(HBG_REG_RX_FIFO_THRSLD_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CFG_FIFO_THRSLD_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_INTRPT_MSK_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_INTRPT_STAT_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_INTRPT_CLR_ADDR), + HBG_DUMP_PCU_I(HBG_REG_TX_BUS_ERR_ADDR_ADDR), + HBG_DUMP_PCU_I(HBG_REG_RX_BUS_ERR_ADDR_ADDR), + HBG_DUMP_PCU_I(HBG_REG_MAX_FRAME_LEN_ADDR), + HBG_DUMP_PCU_I(HBG_REG_DEBUG_ST_MCH_ADDR), + HBG_DUMP_PCU_I(HBG_REG_FIFO_CURR_STATUS_ADDR), + HBG_DUMP_PCU_I(HBG_REG_FIFO_HIST_STATUS_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_CFF_DATA_NUM_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_TX_PAUSE_ADDR), + HBG_DUMP_PCU_I(HBG_REG_RX_CFF_ADDR_ADDR), + HBG_DUMP_PCU_I(HBG_REG_RX_BUF_SIZE_ADDR), + HBG_DUMP_PCU_I(HBG_REG_BUS_CTRL_ADDR), + HBG_DUMP_PCU_I(HBG_REG_RX_CTRL_ADDR), + HBG_DUMP_PCU_I(HBG_REG_RX_PKT_MODE_ADDR), + HBG_DUMP_PCU_I(HBG_REG_DBG_ST0_ADDR), + HBG_DUMP_PCU_I(HBG_REG_DBG_ST1_ADDR), + HBG_DUMP_PCU_I(HBG_REG_DBG_ST2_ADDR), + HBG_DUMP_PCU_I(HBG_REG_BUS_RST_EN_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_IND_TXINT_MSK_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_IND_TXINT_STAT_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_IND_TXINT_CLR_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_IND_RXINT_MSK_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_IND_RXINT_STAT_ADDR), + HBG_DUMP_PCU_I(HBG_REG_CF_IND_RXINT_CLR_ADDR), +}; + +static const u32 hbg_dump_type_base_array[] = { + [HBG_DUMP_REG_TYPE_SPEC] = 0, + [HBG_DUMP_REG_TYPE_MDIO] = HBG_REG_MDIO_BASE, + [HBG_DUMP_REG_TYPE_GMAC] = HBG_REG_SGMII_BASE, + [HBG_DUMP_REG_TYPE_PCU] = HBG_REG_SGMII_BASE, +}; + +static int hbg_ethtool_get_regs_len(struct net_device *netdev) +{ + return ARRAY_SIZE(hbg_dump_reg_infos) * sizeof(struct hbg_reg_info); +} + +static void hbg_ethtool_get_regs(struct net_device *netdev, + struct ethtool_regs *regs, void *data) +{ + struct hbg_priv *priv = netdev_priv(netdev); + struct hbg_reg_info *info; + u32 i, offset = 0; + + regs->version = 0; + for (i = 0; i < ARRAY_SIZE(hbg_dump_reg_infos); i++) { + info = data + offset; + + *info = hbg_dump_reg_infos[i]; + info->val = hbg_reg_read(priv, info->offset); + info->offset -= hbg_dump_type_base_array[info->type]; + + offset += sizeof(*info); + } +} + +static void hbg_ethtool_get_pauseparam(struct net_device *net_dev, + struct ethtool_pauseparam *param) +{ + struct hbg_priv *priv = netdev_priv(net_dev); + + param->autoneg = priv->mac.pause_autoneg; + hbg_hw_get_pause_enable(priv, ¶m->tx_pause, ¶m->rx_pause); +} + +static int hbg_ethtool_set_pauseparam(struct net_device *net_dev, + struct ethtool_pauseparam *param) +{ + struct hbg_priv *priv = netdev_priv(net_dev); + + priv->mac.pause_autoneg = param->autoneg; + phy_set_asym_pause(priv->mac.phydev, param->rx_pause, param->tx_pause); + + if (!param->autoneg) + hbg_hw_set_pause_enable(priv, param->tx_pause, param->rx_pause); + + priv->user_def.pause_param = *param; + return 0; +} + +static int hbg_ethtool_reset(struct net_device *netdev, u32 *flags) +{ + struct hbg_priv *priv = netdev_priv(netdev); + + if (*flags != ETH_RESET_DEDICATED) + return -EOPNOTSUPP; + + *flags = 0; + return hbg_reset(priv); +} static const struct ethtool_ops hbg_ethtool_ops = { .get_link = ethtool_op_get_link, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, + .get_regs_len = hbg_ethtool_get_regs_len, + .get_regs = hbg_ethtool_get_regs, + .get_pauseparam = hbg_ethtool_get_pauseparam, + .set_pauseparam = hbg_ethtool_set_pauseparam, + .reset = hbg_ethtool_reset, + .nway_reset = phy_ethtool_nway_reset, }; void hbg_ethtool_set_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c index 05295c2ad439..e7798f213645 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c @@ -3,6 +3,7 @@ #include #include +#include #include #include #include "hbg_common.h" @@ -67,6 +68,8 @@ static int hbg_hw_dev_specs_init(struct hbg_priv *priv) specs->vlan_layers = hbg_reg_read(priv, HBG_REG_VLAN_LAYERS_ADDR); specs->rx_fifo_num = hbg_reg_read(priv, HBG_REG_RX_FIFO_NUM_ADDR); specs->tx_fifo_num = hbg_reg_read(priv, HBG_REG_TX_FIFO_NUM_ADDR); + specs->uc_mac_num = hbg_reg_read(priv, HBG_REG_UC_MAC_NUM_ADDR); + mac_addr = hbg_reg_read64(priv, HBG_REG_MAC_ADDR_ADDR); u64_to_ether_addr(mac_addr, (u8 *)specs->mac_addr.sa_data); @@ -135,9 +138,13 @@ void hbg_hw_irq_enable(struct hbg_priv *priv, u32 mask, bool enable) hbg_reg_write(priv, HBG_REG_CF_INTRPT_MSK_ADDR, value); } -void hbg_hw_set_uc_addr(struct hbg_priv *priv, u64 mac_addr) +void hbg_hw_set_uc_addr(struct hbg_priv *priv, u64 mac_addr, u32 index) { - hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_2_ADDR, mac_addr); + u32 addr; + + /* mac addr is u64, so the addr offset is 0x8 */ + addr = HBG_REG_STATION_ADDR_LOW_2_ADDR + (index * 0x8); + hbg_reg_write64(priv, addr, mac_addr); } static void hbg_hw_set_pcu_max_frame_len(struct hbg_priv *priv, @@ -161,8 +168,13 @@ static void hbg_hw_set_mac_max_frame_len(struct hbg_priv *priv, void hbg_hw_set_mtu(struct hbg_priv *priv, u16 mtu) { - hbg_hw_set_pcu_max_frame_len(priv, mtu); - hbg_hw_set_mac_max_frame_len(priv, mtu); + u32 frame_len; + + frame_len = mtu + VLAN_HLEN * priv->dev_specs.vlan_layers + + ETH_HLEN + ETH_FCS_LEN; + + hbg_hw_set_pcu_max_frame_len(priv, frame_len); + hbg_hw_set_mac_max_frame_len(priv, frame_len); } void hbg_hw_mac_enable(struct hbg_priv *priv, u32 enable) @@ -207,6 +219,34 @@ void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex) HBG_REG_DUPLEX_B, duplex); } +/* only support uc filter */ +void hbg_hw_set_mac_filter_enable(struct hbg_priv *priv, u32 enable) +{ + hbg_reg_write_field(priv, HBG_REG_REC_FILT_CTRL_ADDR, + HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B, enable); +} + +void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en) +{ + hbg_reg_write_field(priv, HBG_REG_PAUSE_ENABLE_ADDR, + HBG_REG_PAUSE_ENABLE_TX_B, tx_en); + hbg_reg_write_field(priv, HBG_REG_PAUSE_ENABLE_ADDR, + HBG_REG_PAUSE_ENABLE_RX_B, rx_en); +} + +void hbg_hw_get_pause_enable(struct hbg_priv *priv, u32 *tx_en, u32 *rx_en) +{ + *tx_en = hbg_reg_read_field(priv, HBG_REG_PAUSE_ENABLE_ADDR, + HBG_REG_PAUSE_ENABLE_TX_B); + *rx_en = hbg_reg_read_field(priv, HBG_REG_PAUSE_ENABLE_ADDR, + HBG_REG_PAUSE_ENABLE_RX_B); +} + +void hbg_hw_set_rx_pause_mac_addr(struct hbg_priv *priv, u64 mac_addr) +{ + hbg_reg_write64(priv, HBG_REG_FD_FC_ADDR_LOW_ADDR, mac_addr); +} + static void hbg_hw_init_transmit_ctrl(struct hbg_priv *priv) { u32 ctrl = 0; diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.h index 14fb39241c93..a4a049b5121d 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.h @@ -51,9 +51,13 @@ bool hbg_hw_irq_is_enabled(struct hbg_priv *priv, u32 mask); void hbg_hw_irq_enable(struct hbg_priv *priv, u32 mask, bool enable); void hbg_hw_set_mtu(struct hbg_priv *priv, u16 mtu); void hbg_hw_mac_enable(struct hbg_priv *priv, u32 enable); -void hbg_hw_set_uc_addr(struct hbg_priv *priv, u64 mac_addr); +void hbg_hw_set_uc_addr(struct hbg_priv *priv, u64 mac_addr, u32 index); u32 hbg_hw_get_fifo_used_num(struct hbg_priv *priv, enum hbg_dir dir); void hbg_hw_set_tx_desc(struct hbg_priv *priv, struct hbg_tx_desc *tx_desc); void hbg_hw_fill_buffer(struct hbg_priv *priv, u32 buffer_dma_addr); +void hbg_hw_set_mac_filter_enable(struct hbg_priv *priv, u32 enable); +void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en); +void hbg_hw_get_pause_enable(struct hbg_priv *priv, u32 *tx_en, u32 *rx_en); +void hbg_hw_set_rx_pause_mac_addr(struct hbg_priv *priv, u64 mac_addr); #endif diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c index 75505fb5cc4a..bb0f25ac9760 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c @@ -6,13 +6,13 @@ #include #include #include "hbg_common.h" +#include "hbg_err.h" #include "hbg_ethtool.h" #include "hbg_hw.h" #include "hbg_irq.h" #include "hbg_mdio.h" #include "hbg_txrx.h" - -static void hbg_change_mtu(struct hbg_priv *priv, int new_mtu); +#include "hbg_debugfs.h" static void hbg_all_irq_enable(struct hbg_priv *priv, bool enabled) { @@ -55,11 +55,7 @@ static int hbg_hw_txrx_clear(struct hbg_priv *priv) return ret; /* After reset, regs need to be reconfigured */ - hbg_hw_init(priv); - hbg_hw_set_uc_addr(priv, ether_addr_to_u64(priv->netdev->dev_addr)); - hbg_change_mtu(priv, priv->netdev->mtu); - - return 0; + return hbg_rebuild(priv); } static int hbg_net_stop(struct net_device *netdev) @@ -74,31 +70,127 @@ static int hbg_net_stop(struct net_device *netdev) return hbg_hw_txrx_clear(priv); } +static void hbg_update_promisc_mode(struct net_device *netdev, bool overflow) +{ + struct hbg_priv *priv = netdev_priv(netdev); + + /* Only when not table_overflow, and netdev->flags not set IFF_PROMISC, + * The MAC filter will be enabled. + * Otherwise the filter will be disabled. + */ + priv->filter.enabled = !(overflow || (netdev->flags & IFF_PROMISC)); + hbg_hw_set_mac_filter_enable(priv, priv->filter.enabled); +} + +static void hbg_set_mac_to_mac_table(struct hbg_priv *priv, + u32 index, const u8 *addr) +{ + if (addr) { + ether_addr_copy(priv->filter.mac_table[index].addr, addr); + hbg_hw_set_uc_addr(priv, ether_addr_to_u64(addr), index); + } else { + eth_zero_addr(priv->filter.mac_table[index].addr); + hbg_hw_set_uc_addr(priv, 0, index); + } +} + +static int hbg_get_index_from_mac_table(struct hbg_priv *priv, + const u8 *addr, u32 *index) +{ + u32 i; + + for (i = 0; i < priv->filter.table_max_len; i++) + if (ether_addr_equal(priv->filter.mac_table[i].addr, addr)) { + *index = i; + return 0; + } + + return -EINVAL; +} + +static int hbg_add_mac_to_filter(struct hbg_priv *priv, const u8 *addr) +{ + u32 index; + + /* already exists */ + if (!hbg_get_index_from_mac_table(priv, addr, &index)) + return 0; + + for (index = 0; index < priv->filter.table_max_len; index++) + if (is_zero_ether_addr(priv->filter.mac_table[index].addr)) { + hbg_set_mac_to_mac_table(priv, index, addr); + return 0; + } + + return -ENOSPC; +} + +static void hbg_del_mac_from_filter(struct hbg_priv *priv, const u8 *addr) +{ + u32 index; + + /* not exists */ + if (hbg_get_index_from_mac_table(priv, addr, &index)) + return; + + hbg_set_mac_to_mac_table(priv, index, NULL); +} + +static int hbg_uc_sync(struct net_device *netdev, const unsigned char *addr) +{ + struct hbg_priv *priv = netdev_priv(netdev); + + return hbg_add_mac_to_filter(priv, addr); +} + +static int hbg_uc_unsync(struct net_device *netdev, const unsigned char *addr) +{ + struct hbg_priv *priv = netdev_priv(netdev); + + if (ether_addr_equal(netdev->dev_addr, (u8 *)addr)) + return 0; + + hbg_del_mac_from_filter(priv, addr); + return 0; +} + +static void hbg_net_set_rx_mode(struct net_device *netdev) +{ + int ret; + + ret = __dev_uc_sync(netdev, hbg_uc_sync, hbg_uc_unsync); + + /* If ret != 0, overflow has occurred */ + hbg_update_promisc_mode(netdev, !!ret); +} + static int hbg_net_set_mac_address(struct net_device *netdev, void *addr) { struct hbg_priv *priv = netdev_priv(netdev); u8 *mac_addr; + bool exists; + u32 index; mac_addr = ((struct sockaddr *)addr)->sa_data; if (!is_valid_ether_addr(mac_addr)) return -EADDRNOTAVAIL; - hbg_hw_set_uc_addr(priv, ether_addr_to_u64(mac_addr)); + /* The index of host mac is always 0. + * If new mac address already exists, + * delete the existing mac address and + * add it to the position with index 0. + */ + exists = !hbg_get_index_from_mac_table(priv, mac_addr, &index); + hbg_set_mac_to_mac_table(priv, 0, mac_addr); + if (exists) + hbg_set_mac_to_mac_table(priv, index, NULL); + + hbg_hw_set_rx_pause_mac_addr(priv, ether_addr_to_u64(mac_addr)); dev_addr_set(netdev, mac_addr); - return 0; } -static void hbg_change_mtu(struct hbg_priv *priv, int new_mtu) -{ - u32 frame_len; - - frame_len = new_mtu + VLAN_HLEN * priv->dev_specs.vlan_layers + - ETH_HLEN + ETH_FCS_LEN; - hbg_hw_set_mtu(priv, frame_len); -} - static int hbg_net_change_mtu(struct net_device *netdev, int new_mtu) { struct hbg_priv *priv = netdev_priv(netdev); @@ -106,7 +198,7 @@ static int hbg_net_change_mtu(struct net_device *netdev, int new_mtu) if (netif_running(netdev)) return -EBUSY; - hbg_change_mtu(priv, new_mtu); + hbg_hw_set_mtu(priv, new_mtu); WRITE_ONCE(netdev->mtu, new_mtu); dev_dbg(&priv->pdev->dev, @@ -142,8 +234,39 @@ static const struct net_device_ops hbg_netdev_ops = { .ndo_set_mac_address = hbg_net_set_mac_address, .ndo_change_mtu = hbg_net_change_mtu, .ndo_tx_timeout = hbg_net_tx_timeout, + .ndo_set_rx_mode = hbg_net_set_rx_mode, }; +static int hbg_mac_filter_init(struct hbg_priv *priv) +{ + struct hbg_dev_specs *dev_specs = &priv->dev_specs; + struct hbg_mac_filter *filter = &priv->filter; + struct hbg_mac_table_entry *tmp_table; + + tmp_table = devm_kcalloc(&priv->pdev->dev, dev_specs->uc_mac_num, + sizeof(*tmp_table), GFP_KERNEL); + if (!tmp_table) + return -ENOMEM; + + filter->mac_table = tmp_table; + filter->table_max_len = dev_specs->uc_mac_num; + filter->enabled = true; + + hbg_hw_set_mac_filter_enable(priv, filter->enabled); + return 0; +} + +static void hbg_init_user_def(struct hbg_priv *priv) +{ + struct ethtool_pauseparam *pause_param = &priv->user_def.pause_param; + + priv->mac.pause_autoneg = HBG_STATUS_ENABLE; + + pause_param->autoneg = priv->mac.pause_autoneg; + hbg_hw_get_pause_enable(priv, &pause_param->tx_pause, + &pause_param->rx_pause); +} + static int hbg_init(struct hbg_priv *priv) { int ret; @@ -160,7 +283,17 @@ static int hbg_init(struct hbg_priv *priv) if (ret) return ret; - return hbg_mdio_init(priv); + ret = hbg_mdio_init(priv); + if (ret) + return ret; + + ret = hbg_mac_filter_init(priv); + if (ret) + return ret; + + hbg_debugfs_init(priv); + hbg_init_user_def(priv); + return 0; } static int hbg_pci_init(struct pci_dev *pdev) @@ -216,13 +349,15 @@ static int hbg_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) return ret; + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netdev->max_mtu = priv->dev_specs.max_mtu; netdev->min_mtu = priv->dev_specs.min_mtu; netdev->netdev_ops = &hbg_netdev_ops; netdev->watchdog_timeo = 5 * HZ; - hbg_change_mtu(priv, ETH_DATA_LEN); + hbg_hw_set_mtu(priv, ETH_DATA_LEN); hbg_net_set_mac_address(priv->netdev, &priv->dev_specs.mac_addr); hbg_ethtool_set_ops(netdev); @@ -245,7 +380,27 @@ static struct pci_driver hbg_driver = { .id_table = hbg_pci_tbl, .probe = hbg_probe, }; -module_pci_driver(hbg_driver); + +static int __init hbg_module_init(void) +{ + int ret; + + hbg_debugfs_register(); + hbg_set_pci_err_handler(&hbg_driver); + ret = pci_register_driver(&hbg_driver); + if (ret) + hbg_debugfs_unregister(); + + return ret; +} +module_init(hbg_module_init); + +static void __exit hbg_module_exit(void) +{ + pci_unregister_driver(&hbg_driver); + hbg_debugfs_unregister(); +} +module_exit(hbg_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Huawei Tech. Co., Ltd."); diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c index a3479fba8501..db6bc4cfb971 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c @@ -114,6 +114,19 @@ static void hbg_mdio_init_hw(struct hbg_priv *priv) hbg_mdio_set_command(mac, cmd); } +static void hbg_flowctrl_cfg(struct hbg_priv *priv) +{ + struct phy_device *phydev = priv->mac.phydev; + bool rx_pause; + bool tx_pause; + + if (!priv->mac.pause_autoneg) + return; + + phy_get_pause(phydev, &tx_pause, &rx_pause); + hbg_hw_set_pause_enable(priv, tx_pause, rx_pause); +} + static void hbg_phy_adjust_link(struct net_device *netdev) { struct hbg_priv *priv = netdev_priv(netdev); @@ -140,6 +153,7 @@ static void hbg_phy_adjust_link(struct net_device *netdev) priv->mac.duplex = phydev->duplex; priv->mac.autoneg = phydev->autoneg; hbg_hw_adjust_link(priv, speed, phydev->duplex); + hbg_flowctrl_cfg(priv); } priv->mac.link_status = phydev->link; @@ -168,6 +182,7 @@ static int hbg_phy_connect(struct hbg_priv *priv) return ret; phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + phy_support_asym_pause(phydev); phy_attached_info(phydev); return 0; diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h index 57d81c6d7633..f12efc12f3c5 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h @@ -10,6 +10,8 @@ #define HBG_REG_MAC_ID_ADDR 0x0008 #define HBG_REG_PHY_ID_ADDR 0x000C #define HBG_REG_MAC_ADDR_ADDR 0x0010 +#define HBG_REG_MAC_ADDR_HIGH_ADDR 0x0014 +#define HBG_REG_UC_MAC_NUM_ADDR 0x0018 #define HBG_REG_MDIO_FREQ_ADDR 0x0024 #define HBG_REG_MAX_MTU_ADDR 0x0028 #define HBG_REG_MIN_MTU_ADDR 0x002C @@ -28,6 +30,7 @@ #define HBG_REG_MDIO_COMMAND_OP_M GENMASK(11, 10) #define HBG_REG_MDIO_COMMAND_PRTAD_M GENMASK(9, 5) #define HBG_REG_MDIO_COMMAND_DEVAD_M GENMASK(4, 0) +#define HBG_REG_MDIO_ADDR_ADDR (HBG_REG_MDIO_BASE + 0x0004) #define HBG_REG_MDIO_WDATA_ADDR (HBG_REG_MDIO_BASE + 0x0008) #define HBG_REG_MDIO_WDATA_M GENMASK(15, 0) #define HBG_REG_MDIO_RDATA_ADDR (HBG_REG_MDIO_BASE + 0x000C) @@ -36,6 +39,10 @@ /* GMAC */ #define HBG_REG_SGMII_BASE 0x10000 #define HBG_REG_DUPLEX_TYPE_ADDR (HBG_REG_SGMII_BASE + 0x0008) +#define HBG_REG_FD_FC_TYPE_ADDR (HBG_REG_SGMII_BASE + 0x000C) +#define HBG_REG_FC_TX_TIMER_ADDR (HBG_REG_SGMII_BASE + 0x001C) +#define HBG_REG_FD_FC_ADDR_LOW_ADDR (HBG_REG_SGMII_BASE + 0x0020) +#define HBG_REG_FD_FC_ADDR_HIGH_ADDR (HBG_REG_SGMII_BASE + 0x0024) #define HBG_REG_DUPLEX_B BIT(0) #define HBG_REG_MAX_FRAME_SIZE_ADDR (HBG_REG_SGMII_BASE + 0x003C) #define HBG_REG_PORT_MODE_ADDR (HBG_REG_SGMII_BASE + 0x0040) @@ -43,20 +50,42 @@ #define HBG_REG_PORT_ENABLE_ADDR (HBG_REG_SGMII_BASE + 0x0044) #define HBG_REG_PORT_ENABLE_RX_B BIT(1) #define HBG_REG_PORT_ENABLE_TX_B BIT(2) +#define HBG_REG_PAUSE_ENABLE_ADDR (HBG_REG_SGMII_BASE + 0x0048) +#define HBG_REG_PAUSE_ENABLE_RX_B BIT(0) +#define HBG_REG_PAUSE_ENABLE_TX_B BIT(1) +#define HBG_REG_AN_NEG_STATE_ADDR (HBG_REG_SGMII_BASE + 0x0058) #define HBG_REG_TRANSMIT_CTRL_ADDR (HBG_REG_SGMII_BASE + 0x0060) #define HBG_REG_TRANSMIT_CTRL_PAD_EN_B BIT(7) #define HBG_REG_TRANSMIT_CTRL_CRC_ADD_B BIT(6) #define HBG_REG_TRANSMIT_CTRL_AN_EN_B BIT(5) +#define HBG_REG_REC_FILT_CTRL_ADDR (HBG_REG_SGMII_BASE + 0x0064) +#define HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B BIT(0) +#define HBG_REG_LINE_LOOP_BACK_ADDR (HBG_REG_SGMII_BASE + 0x01A8) #define HBG_REG_CF_CRC_STRIP_ADDR (HBG_REG_SGMII_BASE + 0x01B0) #define HBG_REG_CF_CRC_STRIP_B BIT(0) #define HBG_REG_MODE_CHANGE_EN_ADDR (HBG_REG_SGMII_BASE + 0x01B4) #define HBG_REG_MODE_CHANGE_EN_B BIT(0) +#define HBG_REG_LOOP_REG_ADDR (HBG_REG_SGMII_BASE + 0x01DC) #define HBG_REG_RECV_CTRL_ADDR (HBG_REG_SGMII_BASE + 0x01E0) #define HBG_REG_RECV_CTRL_STRIP_PAD_EN_B BIT(3) +#define HBG_REG_VLAN_CODE_ADDR (HBG_REG_SGMII_BASE + 0x01E8) +#define HBG_REG_STATION_ADDR_LOW_0_ADDR (HBG_REG_SGMII_BASE + 0x0200) +#define HBG_REG_STATION_ADDR_HIGH_0_ADDR (HBG_REG_SGMII_BASE + 0x0204) +#define HBG_REG_STATION_ADDR_LOW_1_ADDR (HBG_REG_SGMII_BASE + 0x0208) +#define HBG_REG_STATION_ADDR_HIGH_1_ADDR (HBG_REG_SGMII_BASE + 0x020C) #define HBG_REG_STATION_ADDR_LOW_2_ADDR (HBG_REG_SGMII_BASE + 0x0210) #define HBG_REG_STATION_ADDR_HIGH_2_ADDR (HBG_REG_SGMII_BASE + 0x0214) +#define HBG_REG_STATION_ADDR_LOW_3_ADDR (HBG_REG_SGMII_BASE + 0x0218) +#define HBG_REG_STATION_ADDR_HIGH_3_ADDR (HBG_REG_SGMII_BASE + 0x021C) +#define HBG_REG_STATION_ADDR_LOW_4_ADDR (HBG_REG_SGMII_BASE + 0x0220) +#define HBG_REG_STATION_ADDR_HIGH_4_ADDR (HBG_REG_SGMII_BASE + 0x0224) +#define HBG_REG_STATION_ADDR_LOW_5_ADDR (HBG_REG_SGMII_BASE + 0x0228) +#define HBG_REG_STATION_ADDR_HIGH_5_ADDR (HBG_REG_SGMII_BASE + 0x022C) /* PCU */ +#define HBG_REG_TX_FIFO_THRSLD_ADDR (HBG_REG_SGMII_BASE + 0x0420) +#define HBG_REG_RX_FIFO_THRSLD_ADDR (HBG_REG_SGMII_BASE + 0x0424) +#define HBG_REG_CFG_FIFO_THRSLD_ADDR (HBG_REG_SGMII_BASE + 0x0428) #define HBG_REG_CF_INTRPT_MSK_ADDR (HBG_REG_SGMII_BASE + 0x042C) #define HBG_INT_MSK_WE_ERR_B BIT(31) #define HBG_INT_MSK_RBREQ_ERR_B BIT(30) @@ -78,11 +107,17 @@ #define HBG_INT_MSK_RX_B BIT(0) /* just used in driver */ #define HBG_REG_CF_INTRPT_STAT_ADDR (HBG_REG_SGMII_BASE + 0x0434) #define HBG_REG_CF_INTRPT_CLR_ADDR (HBG_REG_SGMII_BASE + 0x0438) +#define HBG_REG_TX_BUS_ERR_ADDR_ADDR (HBG_REG_SGMII_BASE + 0x043C) +#define HBG_REG_RX_BUS_ERR_ADDR_ADDR (HBG_REG_SGMII_BASE + 0x0440) #define HBG_REG_MAX_FRAME_LEN_ADDR (HBG_REG_SGMII_BASE + 0x0444) #define HBG_REG_MAX_FRAME_LEN_M GENMASK(15, 0) +#define HBG_REG_DEBUG_ST_MCH_ADDR (HBG_REG_SGMII_BASE + 0x0450) +#define HBG_REG_FIFO_CURR_STATUS_ADDR (HBG_REG_SGMII_BASE + 0x0454) +#define HBG_REG_FIFO_HIST_STATUS_ADDR (HBG_REG_SGMII_BASE + 0x0458) #define HBG_REG_CF_CFF_DATA_NUM_ADDR (HBG_REG_SGMII_BASE + 0x045C) #define HBG_REG_CF_CFF_DATA_NUM_ADDR_TX_M GENMASK(8, 0) #define HBG_REG_CF_CFF_DATA_NUM_ADDR_RX_M GENMASK(24, 16) +#define HBG_REG_CF_TX_PAUSE_ADDR (HBG_REG_SGMII_BASE + 0x0470) #define HBG_REG_TX_CFF_ADDR_0_ADDR (HBG_REG_SGMII_BASE + 0x0488) #define HBG_REG_TX_CFF_ADDR_1_ADDR (HBG_REG_SGMII_BASE + 0x048C) #define HBG_REG_TX_CFF_ADDR_2_ADDR (HBG_REG_SGMII_BASE + 0x0490) @@ -101,6 +136,10 @@ #define HBG_REG_RX_CTRL_RXBUF_1ST_SKIP_SIZE2_M GENMASK(3, 0) #define HBG_REG_RX_PKT_MODE_ADDR (HBG_REG_SGMII_BASE + 0x04F4) #define HBG_REG_RX_PKT_MODE_PARSE_MODE_M GENMASK(22, 21) +#define HBG_REG_DBG_ST0_ADDR (HBG_REG_SGMII_BASE + 0x05E4) +#define HBG_REG_DBG_ST1_ADDR (HBG_REG_SGMII_BASE + 0x05E8) +#define HBG_REG_DBG_ST2_ADDR (HBG_REG_SGMII_BASE + 0x05EC) +#define HBG_REG_BUS_RST_EN_ADDR (HBG_REG_SGMII_BASE + 0x0688) #define HBG_REG_CF_IND_TXINT_MSK_ADDR (HBG_REG_SGMII_BASE + 0x0694) #define HBG_REG_IND_INTR_MASK_B BIT(0) #define HBG_REG_CF_IND_TXINT_STAT_ADDR (HBG_REG_SGMII_BASE + 0x0698) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 851490346261..6b6ced37e490 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -3019,115 +3019,6 @@ static struct platform_driver g_dsaf_driver = { module_platform_driver(g_dsaf_driver); -/** - * hns_dsaf_roce_reset - reset dsaf and roce - * @dsaf_fwnode: Pointer to framework node for the dasf - * @dereset: false - request reset , true - drop reset - * return 0 - success , negative -fail - */ -int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) -{ - struct dsaf_device *dsaf_dev; - struct platform_device *pdev; - u32 mp; - u32 sl; - u32 credit; - int i; - static const u32 port_map[DSAF_ROCE_CREDIT_CHN][DSAF_ROCE_CHAN_MODE_NUM] = { - {DSAF_ROCE_PORT_0, DSAF_ROCE_PORT_0, DSAF_ROCE_PORT_0}, - {DSAF_ROCE_PORT_1, DSAF_ROCE_PORT_0, DSAF_ROCE_PORT_0}, - {DSAF_ROCE_PORT_2, DSAF_ROCE_PORT_1, DSAF_ROCE_PORT_0}, - {DSAF_ROCE_PORT_3, DSAF_ROCE_PORT_1, DSAF_ROCE_PORT_0}, - {DSAF_ROCE_PORT_4, DSAF_ROCE_PORT_2, DSAF_ROCE_PORT_1}, - {DSAF_ROCE_PORT_4, DSAF_ROCE_PORT_2, DSAF_ROCE_PORT_1}, - {DSAF_ROCE_PORT_5, DSAF_ROCE_PORT_3, DSAF_ROCE_PORT_1}, - {DSAF_ROCE_PORT_5, DSAF_ROCE_PORT_3, DSAF_ROCE_PORT_1}, - }; - static const u32 sl_map[DSAF_ROCE_CREDIT_CHN][DSAF_ROCE_CHAN_MODE_NUM] = { - {DSAF_ROCE_SL_0, DSAF_ROCE_SL_0, DSAF_ROCE_SL_0}, - {DSAF_ROCE_SL_0, DSAF_ROCE_SL_1, DSAF_ROCE_SL_1}, - {DSAF_ROCE_SL_0, DSAF_ROCE_SL_0, DSAF_ROCE_SL_2}, - {DSAF_ROCE_SL_0, DSAF_ROCE_SL_1, DSAF_ROCE_SL_3}, - {DSAF_ROCE_SL_0, DSAF_ROCE_SL_0, DSAF_ROCE_SL_0}, - {DSAF_ROCE_SL_1, DSAF_ROCE_SL_1, DSAF_ROCE_SL_1}, - {DSAF_ROCE_SL_0, DSAF_ROCE_SL_0, DSAF_ROCE_SL_2}, - {DSAF_ROCE_SL_1, DSAF_ROCE_SL_1, DSAF_ROCE_SL_3}, - }; - - /* find the platform device corresponding to fwnode */ - if (is_of_node(dsaf_fwnode)) { - pdev = of_find_device_by_node(to_of_node(dsaf_fwnode)); - } else if (is_acpi_device_node(dsaf_fwnode)) { - pdev = hns_dsaf_find_platform_device(dsaf_fwnode); - } else { - pr_err("fwnode is neither OF or ACPI type\n"); - return -EINVAL; - } - - /* check if we were a success in fetching pdev */ - if (!pdev) { - pr_err("couldn't find platform device for node\n"); - return -ENODEV; - } - - /* retrieve the dsaf_device from the driver data */ - dsaf_dev = dev_get_drvdata(&pdev->dev); - if (!dsaf_dev) { - dev_err(&pdev->dev, "dsaf_dev is NULL\n"); - put_device(&pdev->dev); - return -ENODEV; - } - - /* now, make sure we are running on compatible SoC */ - if (AE_IS_VER1(dsaf_dev->dsaf_ver)) { - dev_err(dsaf_dev->dev, "%s v1 chip doesn't support RoCE!\n", - dsaf_dev->ae_dev.name); - put_device(&pdev->dev); - return -ENODEV; - } - - /* do reset or de-reset according to the flag */ - if (!dereset) { - /* reset rocee-channels in dsaf and rocee */ - dsaf_dev->misc_op->hns_dsaf_srst_chns(dsaf_dev, DSAF_CHNS_MASK, - false); - dsaf_dev->misc_op->hns_dsaf_roce_srst(dsaf_dev, false); - } else { - /* configure dsaf tx roce correspond to port map and sl map */ - mp = dsaf_read_dev(dsaf_dev, DSAF_ROCE_PORT_MAP_REG); - for (i = 0; i < DSAF_ROCE_CREDIT_CHN; i++) - dsaf_set_field(mp, 7 << i * 3, i * 3, - port_map[i][DSAF_ROCE_6PORT_MODE]); - dsaf_set_field(mp, 3 << i * 3, i * 3, 0); - dsaf_write_dev(dsaf_dev, DSAF_ROCE_PORT_MAP_REG, mp); - - sl = dsaf_read_dev(dsaf_dev, DSAF_ROCE_SL_MAP_REG); - for (i = 0; i < DSAF_ROCE_CREDIT_CHN; i++) - dsaf_set_field(sl, 3 << i * 2, i * 2, - sl_map[i][DSAF_ROCE_6PORT_MODE]); - dsaf_write_dev(dsaf_dev, DSAF_ROCE_SL_MAP_REG, sl); - - /* de-reset rocee-channels in dsaf and rocee */ - dsaf_dev->misc_op->hns_dsaf_srst_chns(dsaf_dev, DSAF_CHNS_MASK, - true); - msleep(SRST_TIME_INTERVAL); - dsaf_dev->misc_op->hns_dsaf_roce_srst(dsaf_dev, true); - - /* enable dsaf channel rocee credit */ - credit = dsaf_read_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG); - dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 0); - dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit); - - dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 1); - dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit); - } - - put_device(&pdev->dev); - - return 0; -} -EXPORT_SYMBOL(hns_dsaf_roce_reset); - MODULE_LICENSE("GPL"); MODULE_AUTHOR("Huawei Tech. Co., Ltd."); MODULE_DESCRIPTION("HNS DSAF driver"); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 0eb03dff1a8b..653dfbb25d1b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -42,29 +42,6 @@ struct hns_mac_cb; #define HNS_MAX_WAIT_CNT 10000 -enum dsaf_roce_port_mode { - DSAF_ROCE_6PORT_MODE, - DSAF_ROCE_4PORT_MODE, - DSAF_ROCE_2PORT_MODE, - DSAF_ROCE_CHAN_MODE_NUM, -}; - -enum dsaf_roce_port_num { - DSAF_ROCE_PORT_0, - DSAF_ROCE_PORT_1, - DSAF_ROCE_PORT_2, - DSAF_ROCE_PORT_3, - DSAF_ROCE_PORT_4, - DSAF_ROCE_PORT_5, -}; - -enum dsaf_roce_qos_sl { - DSAF_ROCE_SL_0, - DSAF_ROCE_SL_1, - DSAF_ROCE_SL_2, - DSAF_ROCE_SL_3, -}; - #define DSAF_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset)))) #define HNS_DSAF_IS_DEBUG(dev) ((dev)->dsaf_mode == DSAF_MODE_DISABLE_SP) @@ -307,9 +284,6 @@ struct dsaf_misc_op { void (*ge_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset); void (*ppe_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset); void (*ppe_comm_srst)(struct dsaf_device *dsaf_dev, bool dereset); - void (*hns_dsaf_srst_chns)(struct dsaf_device *dsaf_dev, u32 msk, - bool dereset); - void (*hns_dsaf_roce_srst)(struct dsaf_device *dsaf_dev, bool dereset); phy_interface_t (*get_phy_if)(struct hns_mac_cb *mac_cb); int (*get_sfp_prsnt)(struct hns_mac_cb *mac_cb, int *sfp_prsnt); @@ -463,6 +437,4 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id, u8 port_num); int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port); -int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset); - #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 5df19c604d09..91391a49fcea 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -326,69 +326,6 @@ static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev, HNS_XGE_RESET_FUNC, port, dereset); } -/** - * hns_dsaf_srst_chns - reset dsaf channels - * @dsaf_dev: dsaf device struct pointer - * @msk: xbar channels mask value: - * @dereset: false - request reset , true - drop reset - * - * bit0-5 for xge0-5 - * bit6-11 for ppe0-5 - * bit12-17 for roce0-5 - * bit18-19 for com/dfx - */ -static void -hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) -{ - u32 reg_addr; - - if (!dereset) - reg_addr = DSAF_SUB_SC_DSAF_RESET_REQ_REG; - else - reg_addr = DSAF_SUB_SC_DSAF_RESET_DREQ_REG; - - dsaf_write_sub(dsaf_dev, reg_addr, msk); -} - -/** - * hns_dsaf_srst_chns_acpi - reset dsaf channels - * @dsaf_dev: dsaf device struct pointer - * @msk: xbar channels mask value: - * @dereset: false - request reset , true - drop reset - * - * bit0-5 for xge0-5 - * bit6-11 for ppe0-5 - * bit12-17 for roce0-5 - * bit18-19 for com/dfx - */ -static void -hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) -{ - hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC, - HNS_DSAF_CHN_RESET_FUNC, - msk, dereset); -} - -static void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset) -{ - if (!dereset) { - dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_ROCEE_RESET_REQ_REG, 1); - } else { - dsaf_write_sub(dsaf_dev, - DSAF_SUB_SC_ROCEE_CLK_DIS_REG, 1); - dsaf_write_sub(dsaf_dev, - DSAF_SUB_SC_ROCEE_RESET_DREQ_REG, 1); - msleep(20); - dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_ROCEE_CLK_EN_REG, 1); - } -} - -static void hns_dsaf_roce_srst_acpi(struct dsaf_device *dsaf_dev, bool dereset) -{ - hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC, - HNS_ROCE_RESET_FUNC, 0, dereset); -} - static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, bool dereset) { @@ -729,8 +666,6 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev) misc_op->ge_srst = hns_dsaf_ge_srst_by_port; misc_op->ppe_srst = hns_ppe_srst_by_port; misc_op->ppe_comm_srst = hns_ppe_com_srst; - misc_op->hns_dsaf_srst_chns = hns_dsaf_srst_chns; - misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst; misc_op->get_phy_if = hns_mac_get_phy_if; misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt; @@ -746,8 +681,6 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev) misc_op->ge_srst = hns_dsaf_ge_srst_by_port_acpi; misc_op->ppe_srst = hns_ppe_srst_by_port_acpi; misc_op->ppe_comm_srst = hns_ppe_com_srst; - misc_op->hns_dsaf_srst_chns = hns_dsaf_srst_chns_acpi; - misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst_acpi; misc_op->get_phy_if = hns_mac_get_phy_if_acpi; misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt_acpi; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 46af467aa596..635b3a95dd82 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -195,11 +195,6 @@ void hns_rcb_ring_enable_hw(struct hnae_queue *q, u32 val) dsaf_write_dev(q, RCB_RING_PREFETCH_EN_REG, !!val); } -void hns_rcb_start(struct hnae_queue *q, u32 val) -{ - hns_rcb_ring_enable_hw(q, val); -} - /** *hns_rcb_common_init_commit_hw - make rcb common init completed *@rcb_common: rcb common device diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h index 0f4cc184ef39..68f81547dfb4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -116,7 +116,6 @@ int hns_rcb_buf_size2type(u32 buf_size); int hns_rcb_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index); void hns_rcb_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index); int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common); -void hns_rcb_start(struct hnae_queue *q, u32 val); int hns_rcb_get_cfg(struct rcb_common_cb *rcb_common); void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode, u16 *max_vfn, u16 *max_q_per_vf); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index 9a63fbc69408..b25fb400f476 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -40,6 +40,21 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare); */ static DEFINE_MUTEX(hnae3_common_lock); +/* ensure the drivers being unloaded one by one */ +static DEFINE_MUTEX(hnae3_unload_lock); + +void hnae3_acquire_unload_lock(void) +{ + mutex_lock(&hnae3_unload_lock); +} +EXPORT_SYMBOL(hnae3_acquire_unload_lock); + +void hnae3_release_unload_lock(void) +{ + mutex_unlock(&hnae3_unload_lock); +} +EXPORT_SYMBOL(hnae3_release_unload_lock); + static bool hnae3_client_match(enum hnae3_client_type client_type) { if (client_type == HNAE3_CLIENT_KNIC || diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 710a8f9f2248..4e44f28288f9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -916,9 +916,6 @@ struct hnae3_handle { u8 netdev_flags; struct dentry *hnae3_dbgfs; - /* protects concurrent contention between debugfs commands */ - struct mutex dbgfs_lock; - char **dbgfs_buf; /* Network interface message level enabled bits */ u32 msg_enable; @@ -966,4 +963,6 @@ int hnae3_register_client(struct hnae3_client *client); void hnae3_set_client_init_flag(struct hnae3_client *client, struct hnae3_ae_dev *ae_dev, unsigned int inited); +void hnae3_acquire_unload_lock(void); +void hnae3_release_unload_lock(void); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 807eb3bbb11c..9bbece25552b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1260,69 +1260,55 @@ static int hns3_dbg_read_cmd(struct hns3_dbg_data *dbg_data, static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { - struct hns3_dbg_data *dbg_data = filp->private_data; + char *buf = filp->private_data; + + return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); +} + +static int hns3_dbg_open(struct inode *inode, struct file *filp) +{ + struct hns3_dbg_data *dbg_data = inode->i_private; struct hnae3_handle *handle = dbg_data->handle; struct hns3_nic_priv *priv = handle->priv; - ssize_t size = 0; - char **save_buf; - char *read_buf; u32 index; + char *buf; int ret; + if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || + test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) + return -EBUSY; + ret = hns3_dbg_get_cmd_index(dbg_data, &index); if (ret) return ret; - mutex_lock(&handle->dbgfs_lock); - save_buf = &handle->dbgfs_buf[index]; + buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL); + if (!buf) + return -ENOMEM; - if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || - test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) { - ret = -EBUSY; - goto out; + ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd, + buf, hns3_dbg_cmd[index].buf_len); + if (ret) { + kvfree(buf); + return ret; } - if (*save_buf) { - read_buf = *save_buf; - } else { - read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL); - if (!read_buf) { - ret = -ENOMEM; - goto out; - } + filp->private_data = buf; + return 0; +} - /* save the buffer addr until the last read operation */ - *save_buf = read_buf; - - /* get data ready for the first time to read */ - ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd, - read_buf, hns3_dbg_cmd[index].buf_len); - if (ret) - goto out; - } - - size = simple_read_from_buffer(buffer, count, ppos, read_buf, - strlen(read_buf)); - if (size > 0) { - mutex_unlock(&handle->dbgfs_lock); - return size; - } - -out: - /* free the buffer for the last read operation */ - if (*save_buf) { - kvfree(*save_buf); - *save_buf = NULL; - } - - mutex_unlock(&handle->dbgfs_lock); - return ret; +static int hns3_dbg_release(struct inode *inode, struct file *filp) +{ + kvfree(filp->private_data); + filp->private_data = NULL; + return 0; } static const struct file_operations hns3_dbg_fops = { .owner = THIS_MODULE, - .open = simple_open, + .open = hns3_dbg_open, .read = hns3_dbg_read, + .release = hns3_dbg_release, }; static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, u32 cmd) @@ -1379,13 +1365,6 @@ int hns3_dbg_init(struct hnae3_handle *handle) int ret; u32 i; - handle->dbgfs_buf = devm_kcalloc(&handle->pdev->dev, - ARRAY_SIZE(hns3_dbg_cmd), - sizeof(*handle->dbgfs_buf), - GFP_KERNEL); - if (!handle->dbgfs_buf) - return -ENOMEM; - hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry = debugfs_create_dir(name, hns3_dbgfs_root); handle->hnae3_dbgfs = hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry; @@ -1395,8 +1374,6 @@ int hns3_dbg_init(struct hnae3_handle *handle) debugfs_create_dir(hns3_dbg_dentry[i].name, handle->hnae3_dbgfs); - mutex_init(&handle->dbgfs_lock); - for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) { if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES && ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) || @@ -1425,24 +1402,13 @@ int hns3_dbg_init(struct hnae3_handle *handle) out: debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; - mutex_destroy(&handle->dbgfs_lock); return ret; } void hns3_dbg_uninit(struct hnae3_handle *handle) { - u32 i; - debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; - - for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) - if (handle->dbgfs_buf[i]) { - kvfree(handle->dbgfs_buf[i]); - handle->dbgfs_buf[i] = NULL; - } - - mutex_destroy(&handle->dbgfs_lock); } void hns3_dbg_register_debugfs(const char *debugfs_dir_name) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 43377a7b2426..9ff797fb36c4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2452,7 +2452,6 @@ static int hns3_nic_set_features(struct net_device *netdev, return ret; } - netdev->features = features; return 0; } @@ -6003,9 +6002,11 @@ module_init(hns3_init_module); */ static void __exit hns3_exit_module(void) { + hnae3_acquire_unload_lock(); pci_unregister_driver(&hns3_driver); hnae3_unregister_client(&client); hns3_dbg_unregister_debugfs(); + hnae3_release_unload_lock(); } module_exit(hns3_exit_module); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 05942fa78b11..3f17b3073e50 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -3574,6 +3575,17 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf, return ret; } +static void hclge_set_reset_pending(struct hclge_dev *hdev, + enum hnae3_reset_type reset_type) +{ + /* When an incorrect reset type is executed, the get_reset_level + * function generates the HNAE3_NONE_RESET flag. As a result, this + * type do not need to pending. + */ + if (reset_type != HNAE3_NONE_RESET) + set_bit(reset_type, &hdev->reset_pending); +} + static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) { u32 cmdq_src_reg, msix_src_reg, hw_err_src_reg; @@ -3594,7 +3606,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) */ if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & msix_src_reg) { dev_info(&hdev->pdev->dev, "IMP reset interrupt\n"); - set_bit(HNAE3_IMP_RESET, &hdev->reset_pending); + hclge_set_reset_pending(hdev, HNAE3_IMP_RESET); set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state); *clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B); hdev->rst_stats.imp_rst_cnt++; @@ -3604,7 +3616,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & msix_src_reg) { dev_info(&hdev->pdev->dev, "global reset interrupt\n"); set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state); - set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending); + hclge_set_reset_pending(hdev, HNAE3_GLOBAL_RESET); *clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B); hdev->rst_stats.global_rst_cnt++; return HCLGE_VECTOR0_EVENT_RST; @@ -3759,7 +3771,7 @@ static int hclge_misc_irq_init(struct hclge_dev *hdev) snprintf(hdev->misc_vector.name, HNAE3_INT_NAME_LEN, "%s-misc-%s", HCLGE_NAME, pci_name(hdev->pdev)); ret = request_irq(hdev->misc_vector.vector_irq, hclge_misc_irq_handle, - 0, hdev->misc_vector.name, hdev); + IRQF_NO_AUTOEN, hdev->misc_vector.name, hdev); if (ret) { hclge_free_vector(hdev, 0); dev_err(&hdev->pdev->dev, "request misc irq(%d) fail\n", @@ -4052,7 +4064,7 @@ static void hclge_do_reset(struct hclge_dev *hdev) case HNAE3_FUNC_RESET: dev_info(&pdev->dev, "PF reset requested\n"); /* schedule again to check later */ - set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending); + hclge_set_reset_pending(hdev, HNAE3_FUNC_RESET); hclge_reset_task_schedule(hdev); break; default: @@ -4086,6 +4098,8 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev, clear_bit(HNAE3_FLR_RESET, addr); } + clear_bit(HNAE3_NONE_RESET, addr); + if (hdev->reset_type != HNAE3_NONE_RESET && rst_level < hdev->reset_type) return HNAE3_NONE_RESET; @@ -4227,7 +4241,7 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev) return false; } else if (hdev->rst_stats.reset_fail_cnt < MAX_RESET_FAIL_CNT) { hdev->rst_stats.reset_fail_cnt++; - set_bit(hdev->reset_type, &hdev->reset_pending); + hclge_set_reset_pending(hdev, hdev->reset_type); dev_info(&hdev->pdev->dev, "re-schedule reset task(%u)\n", hdev->rst_stats.reset_fail_cnt); @@ -4470,8 +4484,20 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle) static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev, enum hnae3_reset_type rst_type) { +#define HCLGE_SUPPORT_RESET_TYPE \ + (BIT(HNAE3_FLR_RESET) | BIT(HNAE3_FUNC_RESET) | \ + BIT(HNAE3_GLOBAL_RESET) | BIT(HNAE3_IMP_RESET)) + struct hclge_dev *hdev = ae_dev->priv; + if (!(BIT(rst_type) & HCLGE_SUPPORT_RESET_TYPE)) { + /* To prevent reset triggered by hclge_reset_event */ + set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request); + dev_warn(&hdev->pdev->dev, "unsupported reset type %d\n", + rst_type); + return; + } + set_bit(rst_type, &hdev->default_reset_request); } @@ -11881,9 +11907,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_init_rxd_adv_layout(hdev); - /* Enable MISC vector(vector0) */ - hclge_enable_vector(&hdev->misc_vector, true); - ret = hclge_init_wol(hdev); if (ret) dev_warn(&pdev->dev, @@ -11896,6 +11919,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_state_init(hdev); hdev->last_reset_time = jiffies; + /* Enable MISC vector(vector0) */ + enable_irq(hdev->misc_vector.vector_irq); + hclge_enable_vector(&hdev->misc_vector, true); + dev_info(&hdev->pdev->dev, "%s driver initialization finished.\n", HCLGE_DRIVER_NAME); @@ -12301,7 +12328,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) /* Disable MISC vector(vector0) */ hclge_enable_vector(&hdev->misc_vector, false); - synchronize_irq(hdev->misc_vector.vector_irq); + disable_irq(hdev->misc_vector.vector_irq); /* Disable all hw interrupts */ hclge_config_mac_tnl_int(hdev, false); @@ -12892,9 +12919,11 @@ static int __init hclge_init(void) static void __exit hclge_exit(void) { + hnae3_acquire_unload_lock(); hnae3_unregister_ae_algo_prepare(&ae_algo); hnae3_unregister_ae_algo(&ae_algo); destroy_workqueue(hclge_wq); + hnae3_release_unload_lock(); } module_init(hclge_init); module_exit(hclge_exit); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index 5505caea88e9..bab16c2191b2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -58,6 +58,9 @@ bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb) struct hclge_dev *hdev = vport->back; struct hclge_ptp *ptp = hdev->ptp; + if (!ptp) + return false; + if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) || test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) { ptp->tx_skipped++; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c index 43c1c18fa81f..8c057192aae6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c @@ -510,9 +510,9 @@ out: static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, struct hnae3_knic_private_info *kinfo) { -#define HCLGE_RING_REG_OFFSET 0x200 #define HCLGE_RING_INT_REG_OFFSET 0x4 + struct hnae3_queue *tqp; int i, j, reg_num; int data_num_sum; u32 *reg = data; @@ -533,10 +533,11 @@ static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, reg_num = ARRAY_SIZE(ring_reg_addr_list); for (j = 0; j < kinfo->num_tqps; j++) { reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RING, reg_num, reg); + tqp = kinfo->tqp[j]; for (i = 0; i < reg_num; i++) - *reg++ = hclge_read_dev(&hdev->hw, - ring_reg_addr_list[i] + - HCLGE_RING_REG_OFFSET * j); + *reg++ = readl_relaxed(tqp->io_base - + HCLGE_TQP_REG_OFFSET + + ring_reg_addr_list[i]); } data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * kinfo->num_tqps; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 2f6ffb88e700..9ba767740a04 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1393,6 +1393,17 @@ static int hclgevf_notify_roce_client(struct hclgevf_dev *hdev, return ret; } +static void hclgevf_set_reset_pending(struct hclgevf_dev *hdev, + enum hnae3_reset_type reset_type) +{ + /* When an incorrect reset type is executed, the get_reset_level + * function generates the HNAE3_NONE_RESET flag. As a result, this + * type do not need to pending. + */ + if (reset_type != HNAE3_NONE_RESET) + set_bit(reset_type, &hdev->reset_pending); +} + static int hclgevf_reset_wait(struct hclgevf_dev *hdev) { #define HCLGEVF_RESET_WAIT_US 20000 @@ -1542,7 +1553,7 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev) hdev->rst_stats.rst_fail_cnt); if (hdev->rst_stats.rst_fail_cnt < HCLGEVF_RESET_MAX_FAIL_CNT) - set_bit(hdev->reset_type, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, hdev->reset_type); if (hclgevf_is_reset_pending(hdev)) { set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); @@ -1662,6 +1673,8 @@ static enum hnae3_reset_type hclgevf_get_reset_level(unsigned long *addr) clear_bit(HNAE3_FLR_RESET, addr); } + clear_bit(HNAE3_NONE_RESET, addr); + return rst_level; } @@ -1671,14 +1684,15 @@ static void hclgevf_reset_event(struct pci_dev *pdev, struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev); struct hclgevf_dev *hdev = ae_dev->priv; - dev_info(&hdev->pdev->dev, "received reset request from VF enet\n"); - if (hdev->default_reset_request) hdev->reset_level = hclgevf_get_reset_level(&hdev->default_reset_request); else hdev->reset_level = HNAE3_VF_FUNC_RESET; + dev_info(&hdev->pdev->dev, "received reset request from VF enet, reset level is %d\n", + hdev->reset_level); + /* reset of this VF requested */ set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state); hclgevf_reset_task_schedule(hdev); @@ -1689,8 +1703,20 @@ static void hclgevf_reset_event(struct pci_dev *pdev, static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev, enum hnae3_reset_type rst_type) { +#define HCLGEVF_SUPPORT_RESET_TYPE \ + (BIT(HNAE3_VF_RESET) | BIT(HNAE3_VF_FUNC_RESET) | \ + BIT(HNAE3_VF_PF_FUNC_RESET) | BIT(HNAE3_VF_FULL_RESET) | \ + BIT(HNAE3_FLR_RESET) | BIT(HNAE3_VF_EXP_RESET)) + struct hclgevf_dev *hdev = ae_dev->priv; + if (!(BIT(rst_type) & HCLGEVF_SUPPORT_RESET_TYPE)) { + /* To prevent reset triggered by hclge_reset_event */ + set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request); + dev_info(&hdev->pdev->dev, "unsupported reset type %d\n", + rst_type); + return; + } set_bit(rst_type, &hdev->default_reset_request); } @@ -1847,14 +1873,14 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev) */ if (hdev->reset_attempts > HCLGEVF_MAX_RESET_ATTEMPTS_CNT) { /* prepare for full reset of stack + pcie interface */ - set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, HNAE3_VF_FULL_RESET); /* "defer" schedule the reset task again */ set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); } else { hdev->reset_attempts++; - set_bit(hdev->reset_level, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, hdev->reset_level); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); } hclgevf_reset_task_schedule(hdev); @@ -1977,7 +2003,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev, rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING); dev_info(&hdev->pdev->dev, "receive reset interrupt 0x%x!\n", rst_ing_reg); - set_bit(HNAE3_VF_RESET, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, HNAE3_VF_RESET); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state); *clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B); @@ -2287,6 +2313,8 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev) clear_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state); INIT_DELAYED_WORK(&hdev->service_task, hclgevf_service_task); + /* timer needs to be initialized before misc irq */ + timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0); mutex_init(&hdev->mbx_resp.mbx_mutex); sema_init(&hdev->reset_sem, 1); @@ -2986,7 +3014,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) HCLGEVF_DRIVER_NAME); hclgevf_task_schedule(hdev, round_jiffies_relative(HZ)); - timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0); return 0; @@ -3383,8 +3410,10 @@ static int __init hclgevf_init(void) static void __exit hclgevf_exit(void) { + hnae3_acquire_unload_lock(); hnae3_unregister_ae_algo(&ae_algovf); destroy_workqueue(hclgevf_wq); + hnae3_release_unload_lock(); } module_init(hclgevf_init); module_exit(hclgevf_exit); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c index 6db415d8b917..7d9d9dbc7560 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c @@ -123,10 +123,10 @@ int hclgevf_get_regs_len(struct hnae3_handle *handle) void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, void *data) { -#define HCLGEVF_RING_REG_OFFSET 0x200 #define HCLGEVF_RING_INT_REG_OFFSET 0x4 struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + struct hnae3_queue *tqp; int i, j, reg_um; u32 *reg = data; @@ -147,10 +147,11 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, reg_um = ARRAY_SIZE(ring_reg_addr_list); for (j = 0; j < hdev->num_tqps; j++) { reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg); + tqp = &hdev->htqp[j].q; for (i = 0; i < reg_um; i++) - *reg++ = hclgevf_read_dev(&hdev->hw, - ring_reg_addr_list[i] + - HCLGEVF_RING_REG_OFFSET * j); + *reg++ = readl_relaxed(tqp->io_base - + HCLGEVF_TQP_REG_OFFSET + + ring_reg_addr_list[i]); } reg_um = ARRAY_SIZE(tqp_intr_reg_addr_list); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 890f213da8d1..ae1f523d6841 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -172,6 +172,7 @@ err_init_txq: hinic_sq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->txqs); + nic_dev->txqs = NULL; return err; } @@ -268,6 +269,7 @@ err_init_rxq: hinic_rq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->rxqs); + nic_dev->rxqs = NULL; return err; } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c index f81a43d2cdfc..486fb0e20bef 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -469,7 +469,7 @@ int hinic_set_vlan_fliter(struct hinic_dev *nic_dev, u32 en) err = HINIC_MGMT_CMD_UNSUPPORTED; } else if (err || !out_size || vlan_filter.status) { dev_err(&pdev->dev, - "Failed to set vlan fliter, err: %d, status: 0x%x, out size: 0x%x\n", + "Failed to set vlan filter, err: %d, status: 0x%x, out size: 0x%x\n", err, vlan_filter.status, out_size); err = -EINVAL; } diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 20bc40eec487..24ec9a4f1ffa 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -292,6 +292,7 @@ config ICE select DIMLIB select LIBIE select NET_DEVLINK + select PACKING select PLDMFW select DPLL help diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 98861cc6df7c..b9dd7b719832 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1179,126 +1179,6 @@ s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid) return vid; } -/** - * fm10k_iov_msg_mac_vlan_pf - Message handler for MAC/VLAN request from VF - * @hw: Pointer to hardware structure - * @results: Pointer array to message, results[0] is pointer to message - * @mbx: Pointer to mailbox information structure - * - * This function is a default handler for MAC/VLAN requests from the VF. - * The assumption is that in this case it is acceptable to just directly - * hand off the message from the VF to the underlying shared code. - **/ -s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) -{ - struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; - u8 mac[ETH_ALEN]; - u32 *result; - int err = 0; - bool set; - u16 vlan; - u32 vid; - - /* we shouldn't be updating rules on a disabled interface */ - if (!FM10K_VF_FLAG_ENABLED(vf_info)) - err = FM10K_ERR_PARAM; - - if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) { - result = results[FM10K_MAC_VLAN_MSG_VLAN]; - - /* record VLAN id requested */ - err = fm10k_tlv_attr_get_u32(result, &vid); - if (err) - return err; - - set = !(vid & FM10K_VLAN_CLEAR); - vid &= ~FM10K_VLAN_CLEAR; - - /* if the length field has been set, this is a multi-bit - * update request. For multi-bit requests, simply disallow - * them when the pf_vid has been set. In this case, the PF - * should have already cleared the VLAN_TABLE, and if we - * allowed them, it could allow a rogue VF to receive traffic - * on a VLAN it was not assigned. In the single-bit case, we - * need to modify requests for VLAN 0 to use the default PF or - * SW vid when assigned. - */ - - if (vid >> 16) { - /* prevent multi-bit requests when PF has - * administratively set the VLAN for this VF - */ - if (vf_info->pf_vid) - return FM10K_ERR_PARAM; - } else { - err = fm10k_iov_select_vid(vf_info, (u16)vid); - if (err < 0) - return err; - - vid = err; - } - - /* update VSI info for VF in regards to VLAN table */ - err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set); - } - - if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) { - result = results[FM10K_MAC_VLAN_MSG_MAC]; - - /* record unicast MAC address requested */ - err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan); - if (err) - return err; - - /* block attempts to set MAC for a locked device */ - if (is_valid_ether_addr(vf_info->mac) && - !ether_addr_equal(mac, vf_info->mac)) - return FM10K_ERR_PARAM; - - set = !(vlan & FM10K_VLAN_CLEAR); - vlan &= ~FM10K_VLAN_CLEAR; - - err = fm10k_iov_select_vid(vf_info, vlan); - if (err < 0) - return err; - - vlan = (u16)err; - - /* notify switch of request for new unicast address */ - err = hw->mac.ops.update_uc_addr(hw, vf_info->glort, - mac, vlan, set, 0); - } - - if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) { - result = results[FM10K_MAC_VLAN_MSG_MULTICAST]; - - /* record multicast MAC address requested */ - err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan); - if (err) - return err; - - /* verify that the VF is allowed to request multicast */ - if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED)) - return FM10K_ERR_PARAM; - - set = !(vlan & FM10K_VLAN_CLEAR); - vlan &= ~FM10K_VLAN_CLEAR; - - err = fm10k_iov_select_vid(vf_info, vlan); - if (err < 0) - return err; - - vlan = (u16)err; - - /* notify switch of request for new multicast address */ - err = hw->mac.ops.update_mc_addr(hw, vf_info->glort, - mac, vlan, set); - } - - return err; -} - /** * fm10k_iov_supported_xcast_mode_pf - Determine best match for xcast mode * @vf_info: VF info structure containing capability flags diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h index 8e814df709d2..ad3696893cb1 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h @@ -99,8 +99,6 @@ extern const struct fm10k_tlv_attr fm10k_err_msg_attr[]; s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid); s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); -s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **, - struct fm10k_mbx_info *); s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index d4255c2706fa..c67963bfe14e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -88,6 +88,7 @@ enum i40e_state { __I40E_SERVICE_SCHED, __I40E_ADMINQ_EVENT_PENDING, __I40E_MDD_EVENT_PENDING, + __I40E_MDD_VF_PRINT_PENDING, __I40E_VFLR_EVENT_PENDING, __I40E_RESET_RECOVERY_PENDING, __I40E_TIMEOUT_RECOVERY_PENDING, @@ -191,6 +192,7 @@ enum i40e_pf_flags { */ I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, I40E_FLAG_VF_VLAN_PRUNING_ENA, + I40E_FLAG_MDD_AUTO_RESET_VF, I40E_PF_FLAGS_NBITS, /* must be last */ }; @@ -572,7 +574,7 @@ struct i40e_pf { int num_alloc_vfs; /* actual number of VFs allocated */ u32 vf_aq_requests; u32 arq_overflows; /* Not fatal, possibly indicative of problems */ - + struct ratelimit_state mdd_message_rate_limit; /* DCBx/DCBNL capability for PF that indicates * whether DCBx is managed by firmware or host * based agent (LLDPAD). Also, indicates what @@ -1189,7 +1191,6 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, struct i40e_fdir_filter *input, bool add); void i40e_fdir_check_and_reenable(struct i40e_pf *pf); u32 i40e_get_current_fd_count(struct i40e_pf *pf); -u32 i40e_get_cur_guaranteed_fd_count(struct i40e_pf *pf); u32 i40e_get_current_atr_cnt(struct i40e_pf *pf); u32 i40e_get_global_fd_count(struct i40e_pf *pf); bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features); @@ -1197,7 +1198,6 @@ void i40e_set_ethtool_ops(struct net_device *netdev); struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan); void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f); -void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan); int i40e_sync_vsi_filters(struct i40e_vsi *vsi); struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, u16 uplink, u32 param1); @@ -1313,7 +1313,6 @@ int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset); int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi); int i40e_get_partition_bw_setting(struct i40e_pf *pf); int i40e_set_partition_bw_setting(struct i40e_pf *pf); -int i40e_commit_partition_bw_setting(struct i40e_pf *pf); void i40e_print_link_message(struct i40e_vsi *vsi, bool isup); void i40e_set_fec_in_flags(u8 fec_cfg, unsigned long *flags); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index f73f5930fc58..175c1320c143 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -1016,16 +1016,6 @@ i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, return status; } -int -i40e_asq_send_command_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ u16 buff_size, - struct i40e_asq_cmd_details *cmd_details, - enum i40e_admin_queue_err *aq_status) -{ - return i40e_asq_send_command_atomic_v2(hw, desc, buff, buff_size, - cmd_details, true, aq_status); -} - /** * i40e_fill_default_direct_cmd_desc - AQ descriptor helper function * @desc: pointer to the temp descriptor (non DMA mem) diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index e8031f1a9b4f..370b4bddee44 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1804,37 +1804,6 @@ int i40e_aq_set_vsi_broadcast(struct i40e_hw *hw, return status; } -/** - * i40e_aq_set_vsi_vlan_promisc - control the VLAN promiscuous setting - * @hw: pointer to the hw struct - * @seid: vsi number - * @enable: set MAC L2 layer unicast promiscuous enable/disable for a given VLAN - * @cmd_details: pointer to command details structure or NULL - **/ -int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, - u16 seid, bool enable, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_set_vsi_promiscuous_modes *cmd = - (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; - u16 flags = 0; - int status; - - i40e_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_set_vsi_promiscuous_modes); - if (enable) - flags |= I40E_AQC_SET_VSI_PROMISC_VLAN; - - cmd->promiscuous_flags = cpu_to_le16(flags); - cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_VLAN); - cmd->seid = cpu_to_le16(seid); - - status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); - - return status; -} - /** * i40e_aq_get_vsi_params - get VSI configuration info * @hw: pointer to the hw struct @@ -2435,136 +2404,6 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, cmd_details, true, aq_status); } -/** - * i40e_mirrorrule_op - Internal helper function to add/delete mirror rule - * @hw: pointer to the hw struct - * @opcode: AQ opcode for add or delete mirror rule - * @sw_seid: Switch SEID (to which rule refers) - * @rule_type: Rule Type (ingress/egress/VLAN) - * @id: Destination VSI SEID or Rule ID - * @count: length of the list - * @mr_list: list of mirrored VSI SEIDs or VLAN IDs - * @cmd_details: pointer to command details structure or NULL - * @rule_id: Rule ID returned from FW - * @rules_used: Number of rules used in internal switch - * @rules_free: Number of rules free in internal switch - * - * Add/Delete a mirror rule to a specific switch. Mirror rules are supported for - * VEBs/VEPA elements only - **/ -static int i40e_mirrorrule_op(struct i40e_hw *hw, - u16 opcode, u16 sw_seid, u16 rule_type, u16 id, - u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rule_id, u16 *rules_used, u16 *rules_free) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_add_delete_mirror_rule *cmd = - (struct i40e_aqc_add_delete_mirror_rule *)&desc.params.raw; - struct i40e_aqc_add_delete_mirror_rule_completion *resp = - (struct i40e_aqc_add_delete_mirror_rule_completion *)&desc.params.raw; - u16 buf_size; - int status; - - buf_size = count * sizeof(*mr_list); - - /* prep the rest of the request */ - i40e_fill_default_direct_cmd_desc(&desc, opcode); - cmd->seid = cpu_to_le16(sw_seid); - cmd->rule_type = cpu_to_le16(rule_type & - I40E_AQC_MIRROR_RULE_TYPE_MASK); - cmd->num_entries = cpu_to_le16(count); - /* Dest VSI for add, rule_id for delete */ - cmd->destination = cpu_to_le16(id); - if (mr_list) { - desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | - I40E_AQ_FLAG_RD)); - if (buf_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - } - - status = i40e_asq_send_command(hw, &desc, mr_list, buf_size, - cmd_details); - if (!status || - hw->aq.asq_last_status == I40E_AQ_RC_ENOSPC) { - if (rule_id) - *rule_id = le16_to_cpu(resp->rule_id); - if (rules_used) - *rules_used = le16_to_cpu(resp->mirror_rules_used); - if (rules_free) - *rules_free = le16_to_cpu(resp->mirror_rules_free); - } - return status; -} - -/** - * i40e_aq_add_mirrorrule - add a mirror rule - * @hw: pointer to the hw struct - * @sw_seid: Switch SEID (to which rule refers) - * @rule_type: Rule Type (ingress/egress/VLAN) - * @dest_vsi: SEID of VSI to which packets will be mirrored - * @count: length of the list - * @mr_list: list of mirrored VSI SEIDs or VLAN IDs - * @cmd_details: pointer to command details structure or NULL - * @rule_id: Rule ID returned from FW - * @rules_used: Number of rules used in internal switch - * @rules_free: Number of rules free in internal switch - * - * Add mirror rule. Mirror rules are supported for VEBs or VEPA elements only - **/ -int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 dest_vsi, u16 count, - __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rule_id, u16 *rules_used, u16 *rules_free) -{ - if (!(rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS || - rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS)) { - if (count == 0 || !mr_list) - return -EINVAL; - } - - return i40e_mirrorrule_op(hw, i40e_aqc_opc_add_mirror_rule, sw_seid, - rule_type, dest_vsi, count, mr_list, - cmd_details, rule_id, rules_used, rules_free); -} - -/** - * i40e_aq_delete_mirrorrule - delete a mirror rule - * @hw: pointer to the hw struct - * @sw_seid: Switch SEID (to which rule refers) - * @rule_type: Rule Type (ingress/egress/VLAN) - * @count: length of the list - * @rule_id: Rule ID that is returned in the receive desc as part of - * add_mirrorrule. - * @mr_list: list of mirrored VLAN IDs to be removed - * @cmd_details: pointer to command details structure or NULL - * @rules_used: Number of rules used in internal switch - * @rules_free: Number of rules free in internal switch - * - * Delete a mirror rule. Mirror rules are supported for VEBs/VEPA elements only - **/ -int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 rule_id, u16 count, - __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rules_used, u16 *rules_free) -{ - /* Rule ID has to be valid except rule_type: INGRESS VLAN mirroring */ - if (rule_type == I40E_AQC_MIRROR_RULE_TYPE_VLAN) { - /* count and mr_list shall be valid for rule_type INGRESS VLAN - * mirroring. For other rule_type, count and rule_type should - * not matter. - */ - if (count == 0 || !mr_list) - return -EINVAL; - } - - return i40e_mirrorrule_op(hw, i40e_aqc_opc_delete_mirror_rule, sw_seid, - rule_type, rule_id, count, mr_list, - cmd_details, NULL, rules_used, rules_free); -} - /** * i40e_aq_send_msg_to_vf * @hw: pointer to the hardware structure @@ -3179,41 +3018,6 @@ i40e_aq_update_nvm_exit: return status; } -/** - * i40e_aq_rearrange_nvm - * @hw: pointer to the hw struct - * @rearrange_nvm: defines direction of rearrangement - * @cmd_details: pointer to command details structure or NULL - * - * Rearrange NVM structure, available only for transition FW - **/ -int i40e_aq_rearrange_nvm(struct i40e_hw *hw, - u8 rearrange_nvm, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aqc_nvm_update *cmd; - struct i40e_aq_desc desc; - int status; - - cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw; - - i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_update); - - rearrange_nvm &= (I40E_AQ_NVM_REARRANGE_TO_FLAT | - I40E_AQ_NVM_REARRANGE_TO_STRUCT); - - if (!rearrange_nvm) { - status = -EINVAL; - goto i40e_aq_rearrange_nvm_exit; - } - - cmd->command_flags |= rearrange_nvm; - status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); - -i40e_aq_rearrange_nvm_exit: - return status; -} - /** * i40e_aq_get_lldp_mib * @hw: pointer to the hw struct @@ -3334,44 +3138,6 @@ int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, return status; } -/** - * i40e_aq_restore_lldp - * @hw: pointer to the hw struct - * @setting: pointer to factory setting variable or NULL - * @restore: True if factory settings should be restored - * @cmd_details: pointer to command details structure or NULL - * - * Restore LLDP Agent factory settings if @restore set to True. In other case - * only returns factory setting in AQ response. - **/ -int -i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_lldp_restore *cmd = - (struct i40e_aqc_lldp_restore *)&desc.params.raw; - int status; - - if (!test_bit(I40E_HW_CAP_FW_LLDP_PERSISTENT, hw->caps)) { - i40e_debug(hw, I40E_DEBUG_ALL, - "Restore LLDP not supported by current FW version.\n"); - return -ENODEV; - } - - i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_restore); - - if (restore) - cmd->command |= I40E_AQ_LLDP_AGENT_RESTORE; - - status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); - - if (setting) - *setting = cmd->command & 1; - - return status; -} - /** * i40e_aq_stop_lldp * @hw: pointer to the hw struct @@ -4569,84 +4335,6 @@ phy_write_end: return status; } -/** - * i40e_write_phy_register - * @hw: pointer to the HW structure - * @page: registers page number - * @reg: register address in the page - * @phy_addr: PHY address on MDIO interface - * @value: PHY register value - * - * Writes value to specified PHY register - **/ -int i40e_write_phy_register(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 value) -{ - int status; - - switch (hw->device_id) { - case I40E_DEV_ID_1G_BASE_T_X722: - status = i40e_write_phy_register_clause22(hw, reg, phy_addr, - value); - break; - case I40E_DEV_ID_1G_BASE_T_BC: - case I40E_DEV_ID_5G_BASE_T_BC: - case I40E_DEV_ID_10G_BASE_T: - case I40E_DEV_ID_10G_BASE_T4: - case I40E_DEV_ID_10G_BASE_T_BC: - case I40E_DEV_ID_10G_BASE_T_X722: - case I40E_DEV_ID_25G_B: - case I40E_DEV_ID_25G_SFP28: - status = i40e_write_phy_register_clause45(hw, page, reg, - phy_addr, value); - break; - default: - status = -EIO; - break; - } - - return status; -} - -/** - * i40e_read_phy_register - * @hw: pointer to the HW structure - * @page: registers page number - * @reg: register address in the page - * @phy_addr: PHY address on MDIO interface - * @value: PHY register value - * - * Reads specified PHY register value - **/ -int i40e_read_phy_register(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 *value) -{ - int status; - - switch (hw->device_id) { - case I40E_DEV_ID_1G_BASE_T_X722: - status = i40e_read_phy_register_clause22(hw, reg, phy_addr, - value); - break; - case I40E_DEV_ID_1G_BASE_T_BC: - case I40E_DEV_ID_5G_BASE_T_BC: - case I40E_DEV_ID_10G_BASE_T: - case I40E_DEV_ID_10G_BASE_T4: - case I40E_DEV_ID_10G_BASE_T_BC: - case I40E_DEV_ID_10G_BASE_T_X722: - case I40E_DEV_ID_25G_B: - case I40E_DEV_ID_25G_SFP28: - status = i40e_read_phy_register_clause45(hw, page, reg, - phy_addr, value); - break; - default: - status = -EIO; - break; - } - - return status; -} - /** * i40e_get_phy_address * @hw: pointer to the HW structure @@ -4662,80 +4350,6 @@ u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num) return (u8)(reg_val >> ((dev_num + 1) * 5)) & 0x1f; } -/** - * i40e_blink_phy_link_led - * @hw: pointer to the HW structure - * @time: time how long led will blinks in secs - * @interval: gap between LED on and off in msecs - * - * Blinks PHY link LED - **/ -int i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval) -{ - u16 led_addr = I40E_PHY_LED_PROV_REG_1; - u16 gpio_led_port; - u8 phy_addr = 0; - int status = 0; - u16 led_ctl; - u8 port_num; - u16 led_reg; - u32 i; - - i = rd32(hw, I40E_PFGEN_PORTNUM); - port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); - phy_addr = i40e_get_phy_address(hw, port_num); - - for (gpio_led_port = 0; gpio_led_port < 3; gpio_led_port++, - led_addr++) { - status = i40e_read_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, - &led_reg); - if (status) - goto phy_blinking_end; - led_ctl = led_reg; - if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) { - led_reg = 0; - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, - led_reg); - if (status) - goto phy_blinking_end; - break; - } - } - - if (time > 0 && interval > 0) { - for (i = 0; i < time * 1000; i += interval) { - status = i40e_read_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, &led_reg); - if (status) - goto restore_config; - if (led_reg & I40E_PHY_LED_MANUAL_ON) - led_reg = 0; - else - led_reg = I40E_PHY_LED_MANUAL_ON; - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_reg); - if (status) - goto restore_config; - msleep(interval); - } - } - -restore_config: - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_ctl); - -phy_blinking_end: - return status; -} - /** * i40e_led_get_reg - read LED register * @hw: pointer to the HW structure @@ -5268,39 +4882,6 @@ i40e_find_segment_in_package(u32 segment_type, #define I40E_SECTION_HEADER(profile, offset) \ (struct i40e_profile_section_header *)((u8 *)(profile) + (offset)) -/** - * i40e_find_section_in_profile - * @section_type: the section type to search for (i.e., SECTION_TYPE_NOTE) - * @profile: pointer to the i40e segment header to be searched - * - * This function searches i40e segment for a particular section type. On - * success it returns a pointer to the section header, otherwise it will - * return NULL. - **/ -struct i40e_profile_section_header * -i40e_find_section_in_profile(u32 section_type, - struct i40e_profile_segment *profile) -{ - struct i40e_profile_section_header *sec; - struct i40e_section_table *sec_tbl; - u32 sec_off; - u32 i; - - if (profile->header.type != SEGMENT_TYPE_I40E) - return NULL; - - I40E_SECTION_TABLE(profile, sec_tbl); - - for (i = 0; i < sec_tbl->section_count; i++) { - sec_off = sec_tbl->section_offset[i]; - sec = I40E_SECTION_HEADER(profile, sec_off); - if (sec->section.type == section_type) - return sec; - } - - return NULL; -} - /** * i40e_ddp_exec_aq_section - Execute generic AQ for DDP * @hw: pointer to the hw struct @@ -5523,45 +5104,6 @@ i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, return status; } -/** - * i40e_add_pinfo_to_list - * @hw: pointer to the hardware structure - * @profile: pointer to the profile segment of the package - * @profile_info_sec: buffer for information section - * @track_id: package tracking id - * - * Register a profile to the list of loaded profiles. - */ -int -i40e_add_pinfo_to_list(struct i40e_hw *hw, - struct i40e_profile_segment *profile, - u8 *profile_info_sec, u32 track_id) -{ - struct i40e_profile_section_header *sec = NULL; - struct i40e_profile_info *pinfo; - u32 offset = 0, info = 0; - int status = 0; - - sec = (struct i40e_profile_section_header *)profile_info_sec; - sec->tbl_size = 1; - sec->data_end = sizeof(struct i40e_profile_section_header) + - sizeof(struct i40e_profile_info); - sec->section.type = SECTION_TYPE_INFO; - sec->section.offset = sizeof(struct i40e_profile_section_header); - sec->section.size = sizeof(struct i40e_profile_info); - pinfo = (struct i40e_profile_info *)(profile_info_sec + - sec->section.offset); - pinfo->track_id = track_id; - pinfo->version = profile->version; - pinfo->op = I40E_DDP_ADD_TRACKID; - memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE); - - status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end, - track_id, &offset, &info, NULL); - - return status; -} - /** * i40e_aq_add_cloud_filters * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 8db1eb0c1768..352e957443fd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -1490,19 +1490,6 @@ void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc) wr32(hw, I40E_PRTDCB_GENC, reg); } -/** - * i40e_dcb_hw_get_num_tc - * @hw: pointer to the hw struct - * - * Returns number of traffic classes configured in HW - **/ -u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw) -{ - u32 reg = rd32(hw, I40E_PRTDCB_GENC); - - return FIELD_GET(I40E_PRTDCB_GENC_NUMTC_MASK, reg); -} - /** * i40e_dcb_hw_rx_ets_bw_config * @hw: pointer to the hw struct diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h index d76497566e40..d5662c639c41 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h @@ -253,7 +253,6 @@ void i40e_dcb_hw_rx_cmd_monitor_config(struct i40e_hw *hw, void i40e_dcb_hw_pfc_config(struct i40e_hw *hw, u8 pfc_en, u8 *prio_tc); void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc); -u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw); void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share, u8 *mode, u8 *prio_type); void i40e_dcb_hw_rx_up2tc_config(struct i40e_hw *hw, u8 *prio_tc); diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 208c2f0857b6..6cd9da662ae1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -722,7 +722,7 @@ static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id) dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n", vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs); dev_info(&pf->pdev->dev, " num MDD=%lld\n", - vf->num_mdd_events); + vf->mdd_tx_events.count + vf->mdd_rx_events.count); } else { dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index bce5b76f1e7a..8a7a83f83ee5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -459,6 +459,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0), I40E_PRIV_FLAG("vf-vlan-pruning", I40E_FLAG_VF_VLAN_PRUNING_ENA, 0), + I40E_PRIV_FLAG("mdd-auto-reset-vf", + I40E_FLAG_MDD_AUTO_RESET_VF, 0), }; #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 0e1d9e2fbf38..65a702668e21 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1666,9 +1666,8 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, * @vsi: VSI to remove from * @f: the filter to remove from the list * - * This function should be called instead of i40e_del_filter only if you know - * the exact filter you will remove already, such as via i40e_find_filter or - * i40e_find_mac. + * This function requires you've found * the exact filter you will remove + * already, such as via i40e_find_filter or i40e_find_mac. * * NOTE: This function is expected to be called with mac_filter_hash_lock * being held. @@ -1697,29 +1696,6 @@ void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f) set_bit(__I40E_MACVLAN_SYNC_PENDING, vsi->back->state); } -/** - * i40e_del_filter - Remove a MAC/VLAN filter from the VSI - * @vsi: the VSI to be searched - * @macaddr: the MAC address - * @vlan: the VLAN - * - * NOTE: This function is expected to be called with mac_filter_hash_lock - * being held. - * ANOTHER NOTE: This function MUST be called from within the context of - * the "safe" variants of any list iterators, e.g. list_for_each_entry_safe() - * instead of list_for_each_entry(). - **/ -void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan) -{ - struct i40e_mac_filter *f; - - if (!vsi || !macaddr) - return; - - f = i40e_find_filter(vsi, macaddr, vlan); - __i40e_del_filter(vsi, f); -} - /** * i40e_add_mac_filter - Add a MAC filter for all active VLANs * @vsi: the VSI to be searched @@ -9628,19 +9604,6 @@ static void i40e_handle_lan_overflow_event(struct i40e_pf *pf, i40e_reset_vf(vf, false); } -/** - * i40e_get_cur_guaranteed_fd_count - Get the consumed guaranteed FD filters - * @pf: board private structure - **/ -u32 i40e_get_cur_guaranteed_fd_count(struct i40e_pf *pf) -{ - u32 val, fcnt_prog; - - val = rd32(&pf->hw, I40E_PFQF_FDSTAT); - fcnt_prog = (val & I40E_PFQF_FDSTAT_GUARANT_CNT_MASK); - return fcnt_prog; -} - /** * i40e_get_current_fd_count - Get total FD filters programmed for this PF * @pf: board private structure @@ -11216,6 +11179,67 @@ static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired) i40e_reset_and_rebuild(pf, false, lock_acquired); } +/** + * i40e_print_vf_mdd_event - print VF Tx/Rx malicious driver detect event + * @pf: board private structure + * @vf: pointer to the VF structure + * @is_tx: true - for Tx event, false - for Rx + */ +static void i40e_print_vf_mdd_event(struct i40e_pf *pf, struct i40e_vf *vf, + bool is_tx) +{ + dev_err(&pf->pdev->dev, is_tx ? + "%lld Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n" : + "%lld Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n", + is_tx ? vf->mdd_tx_events.count : vf->mdd_rx_events.count, + pf->hw.pf_id, + vf->vf_id, + vf->default_lan_addr.addr, + str_on_off(test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags))); +} + +/** + * i40e_print_vfs_mdd_events - print VFs malicious driver detect event + * @pf: pointer to the PF structure + * + * Called from i40e_handle_mdd_event to rate limit and print VFs MDD events. + */ +static void i40e_print_vfs_mdd_events(struct i40e_pf *pf) +{ + unsigned int i; + + /* check that there are pending MDD events to print */ + if (!test_and_clear_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state)) + return; + + if (!__ratelimit(&pf->mdd_message_rate_limit)) + return; + + for (i = 0; i < pf->num_alloc_vfs; i++) { + struct i40e_vf *vf = &pf->vf[i]; + bool is_printed = false; + + /* only print Rx MDD event message if there are new events */ + if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) { + vf->mdd_rx_events.last_printed = vf->mdd_rx_events.count; + i40e_print_vf_mdd_event(pf, vf, false); + is_printed = true; + } + + /* only print Tx MDD event message if there are new events */ + if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) { + vf->mdd_tx_events.last_printed = vf->mdd_tx_events.count; + i40e_print_vf_mdd_event(pf, vf, true); + is_printed = true; + } + + if (is_printed && !test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)) + dev_info(&pf->pdev->dev, + "Use PF Control I/F to re-enable the VF #%d\n", + i); + } +} + /** * i40e_handle_mdd_event * @pf: pointer to the PF structure @@ -11230,8 +11254,13 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) u32 reg; int i; - if (!test_bit(__I40E_MDD_EVENT_PENDING, pf->state)) + if (!test_and_clear_bit(__I40E_MDD_EVENT_PENDING, pf->state)) { + /* Since the VF MDD event logging is rate limited, check if + * there are pending MDD events. + */ + i40e_print_vfs_mdd_events(pf); return; + } /* find what triggered the MDD event */ reg = rd32(hw, I40E_GL_MDET_TX); @@ -11275,36 +11304,48 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) /* see if one of the VFs needs its hand slapped */ for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) { + bool is_mdd_on_tx = false; + bool is_mdd_on_rx = false; + vf = &(pf->vf[i]); reg = rd32(hw, I40E_VP_MDET_TX(i)); if (reg & I40E_VP_MDET_TX_VALID_MASK) { + set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state); wr32(hw, I40E_VP_MDET_TX(i), 0xFFFF); - vf->num_mdd_events++; - dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", - i); - dev_info(&pf->pdev->dev, - "Use PF Control I/F to re-enable the VF\n"); + vf->mdd_tx_events.count++; set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); + is_mdd_on_tx = true; } reg = rd32(hw, I40E_VP_MDET_RX(i)); if (reg & I40E_VP_MDET_RX_VALID_MASK) { + set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state); wr32(hw, I40E_VP_MDET_RX(i), 0xFFFF); - vf->num_mdd_events++; - dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n", - i); - dev_info(&pf->pdev->dev, - "Use PF Control I/F to re-enable the VF\n"); + vf->mdd_rx_events.count++; set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); + is_mdd_on_rx = true; + } + + if ((is_mdd_on_tx || is_mdd_on_rx) && + test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)) { + /* VF MDD event counters will be cleared by + * reset, so print the event prior to reset. + */ + if (is_mdd_on_rx) + i40e_print_vf_mdd_event(pf, vf, false); + if (is_mdd_on_tx) + i40e_print_vf_mdd_event(pf, vf, true); + + i40e_vc_reset_vf(vf, true); } } - /* re-enable mdd interrupt cause */ - clear_bit(__I40E_MDD_EVENT_PENDING, pf->state); reg = rd32(hw, I40E_PFINT_ICR0_ENA); reg |= I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK; wr32(hw, I40E_PFINT_ICR0_ENA, reg); i40e_flush(hw); + + i40e_print_vfs_mdd_events(pf); } /** @@ -12613,89 +12654,6 @@ int i40e_set_partition_bw_setting(struct i40e_pf *pf) return status; } -/** - * i40e_commit_partition_bw_setting - Commit BW settings for this PF partition - * @pf: board private structure - **/ -int i40e_commit_partition_bw_setting(struct i40e_pf *pf) -{ - /* Commit temporary BW setting to permanent NVM image */ - enum i40e_admin_queue_err last_aq_status; - u16 nvm_word; - int ret; - - if (pf->hw.partition_id != 1) { - dev_info(&pf->pdev->dev, - "Commit BW only works on partition 1! This is partition %d", - pf->hw.partition_id); - ret = -EOPNOTSUPP; - goto bw_commit_out; - } - - /* Acquire NVM for read access */ - ret = i40e_acquire_nvm(&pf->hw, I40E_RESOURCE_READ); - last_aq_status = pf->hw.aq.asq_last_status; - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot acquire NVM for read access, err %pe aq_err %s\n", - ERR_PTR(ret), - i40e_aq_str(&pf->hw, last_aq_status)); - goto bw_commit_out; - } - - /* Read word 0x10 of NVM - SW compatibility word 1 */ - ret = i40e_aq_read_nvm(&pf->hw, - I40E_SR_NVM_CONTROL_WORD, - 0x10, sizeof(nvm_word), &nvm_word, - false, NULL); - /* Save off last admin queue command status before releasing - * the NVM - */ - last_aq_status = pf->hw.aq.asq_last_status; - i40e_release_nvm(&pf->hw); - if (ret) { - dev_info(&pf->pdev->dev, "NVM read error, err %pe aq_err %s\n", - ERR_PTR(ret), - i40e_aq_str(&pf->hw, last_aq_status)); - goto bw_commit_out; - } - - /* Wait a bit for NVM release to complete */ - msleep(50); - - /* Acquire NVM for write access */ - ret = i40e_acquire_nvm(&pf->hw, I40E_RESOURCE_WRITE); - last_aq_status = pf->hw.aq.asq_last_status; - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot acquire NVM for write access, err %pe aq_err %s\n", - ERR_PTR(ret), - i40e_aq_str(&pf->hw, last_aq_status)); - goto bw_commit_out; - } - /* Write it back out unchanged to initiate update NVM, - * which will force a write of the shadow (alt) RAM to - * the NVM - thus storing the bandwidth values permanently. - */ - ret = i40e_aq_update_nvm(&pf->hw, - I40E_SR_NVM_CONTROL_WORD, - 0x10, sizeof(nvm_word), - &nvm_word, true, 0, NULL); - /* Save off last admin queue command status before releasing - * the NVM - */ - last_aq_status = pf->hw.aq.asq_last_status; - i40e_release_nvm(&pf->hw); - if (ret) - dev_info(&pf->pdev->dev, - "BW settings NOT SAVED, err %pe aq_err %s\n", - ERR_PTR(ret), - i40e_aq_str(&pf->hw, last_aq_status)); -bw_commit_out: - - return ret; -} - /** * i40e_is_total_port_shutdown_enabled - read NVM and return value * if total port shutdown feature is enabled for this PF @@ -15998,6 +15956,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + /* VF MDD event logs are rate limited to one second intervals */ + ratelimit_state_init(&pf->mdd_message_rate_limit, 1 * HZ, 1); + /* Reconfigure hardware for allowing smaller MSS in the case * of TSO, so that we avoid the MDD being fired and causing * a reset in the case of small MSS+TSO. diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index 5a0699ca7ce5..099bb8ab7d70 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -27,13 +27,6 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details); int -i40e_asq_send_command_v2(struct i40e_hw *hw, - struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ - u16 buff_size, - struct i40e_asq_cmd_details *cmd_details, - enum i40e_admin_queue_err *aq_status); -int i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details, @@ -72,8 +65,6 @@ int i40e_led_set_phy(struct i40e_hw *hw, bool on, u16 led_addr, u32 mode); int i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, u16 *val); -int i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval); /* admin send queue commands */ @@ -141,9 +132,6 @@ int i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw, u16 seid, bool enable, u16 vid, struct i40e_asq_cmd_details *cmd_details); -int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, - u16 seid, bool enable, - struct i40e_asq_cmd_details *cmd_details); int i40e_aq_get_vsi_params(struct i40e_hw *hw, struct i40e_vsi_context *vsi_ctx, struct i40e_asq_cmd_details *cmd_details); @@ -176,14 +164,6 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, struct i40e_aqc_remove_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details, enum i40e_admin_queue_err *aq_status); -int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rule_id, u16 *rules_used, u16 *rules_free); -int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 rule_id, u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rules_used, u16 *rules_free); int i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, @@ -220,9 +200,6 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, u32 offset, u16 length, void *data, bool last_command, u8 preservation_flags, struct i40e_asq_cmd_details *cmd_details); -int i40e_aq_rearrange_nvm(struct i40e_hw *hw, - u8 rearrange_nvm, - struct i40e_asq_cmd_details *cmd_details); int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, u8 mib_type, void *buff, u16 buff_size, u16 *local_len, u16 *remote_len, @@ -234,9 +211,6 @@ i40e_aq_set_lldp_mib(struct i40e_hw *hw, int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, bool enable_update, struct i40e_asq_cmd_details *cmd_details); -int -i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore, - struct i40e_asq_cmd_details *cmd_details); int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent, bool persist, struct i40e_asq_cmd_details *cmd_details); @@ -458,13 +432,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 *value); int i40e_write_phy_register_clause45(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 value); -int i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 *value); -int i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 value); u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); -int i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval); int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff, u16 buff_size, u32 track_id, u32 *error_offset, u32 *error_info, @@ -477,20 +445,12 @@ int i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff, struct i40e_generic_seg_header * i40e_find_segment_in_package(u32 segment_type, struct i40e_package_header *pkg_header); -struct i40e_profile_section_header * -i40e_find_section_in_profile(u32 section_type, - struct i40e_profile_segment *profile); int i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, u32 track_id); int i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, u32 track_id); -int -i40e_add_pinfo_to_list(struct i40e_hw *hw, - struct i40e_profile_segment *profile, - u8 *profile_info_sec, u32 track_id); - /* i40e_ddp */ int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index dfa785e39458..1120f8e4bb67 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -216,7 +216,7 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) * @notify_vf: notify vf about reset or not * Reset VF handler. **/ -static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf) +void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf) { struct i40e_pf *pf = vf->pf; int i; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 66f95e2f3146..5cf74f16f433 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -64,6 +64,12 @@ struct i40evf_channel { u64 max_tx_rate; /* bandwidth rate allocation for VSIs */ }; +struct i40e_mdd_vf_events { + u64 count; /* total count of Rx|Tx events */ + /* count number of the last printed event */ + u64 last_printed; +}; + /* VF information structure */ struct i40e_vf { struct i40e_pf *pf; @@ -92,7 +98,9 @@ struct i40e_vf { u8 num_queue_pairs; /* num of qps assigned to VF vsis */ u8 num_req_queues; /* num of requested qps */ - u64 num_mdd_events; /* num of mdd events detected */ + /* num of mdd tx and rx events detected */ + struct i40e_mdd_vf_events mdd_rx_events; + struct i40e_mdd_vf_events mdd_tx_events; unsigned long vf_caps; /* vf's adv. capabilities */ unsigned long vf_states; /* vf's runtime states */ @@ -120,6 +128,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs); int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen); int i40e_vc_process_vflr_event(struct i40e_pf *pf); +void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf); bool i40e_reset_vf(struct i40e_vf *vf, bool flr); bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr); void i40e_vc_notify_vf_reset(struct i40e_vf *vf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 4e885df789ef..e28f1905a4a0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -395,32 +395,6 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring, WARN_ON_ONCE(1); } -static int -i40e_add_xsk_frag(struct i40e_ring *rx_ring, struct xdp_buff *first, - struct xdp_buff *xdp, const unsigned int size) -{ - struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first); - - if (!xdp_buff_has_frags(first)) { - sinfo->nr_frags = 0; - sinfo->xdp_frags_size = 0; - xdp_buff_set_frags_flag(first); - } - - if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { - xsk_buff_free(first); - return -ENOMEM; - } - - __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, - virt_to_page(xdp->data_hard_start), - XDP_PACKET_HEADROOM, size); - sinfo->xdp_frags_size += size; - xsk_buff_add_frag(xdp); - - return 0; -} - /** * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring * @rx_ring: Rx ring @@ -486,8 +460,10 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) if (!first) first = bi; - else if (i40e_add_xsk_frag(rx_ring, first, bi, size)) + else if (!xsk_buff_add_frag(first, bi)) { + xsk_buff_free(first); break; + } if (++next_to_process == count) next_to_process = 0; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index a9e54866ae6b..2d7a18fcc3be 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -773,6 +773,11 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, f->state = IAVF_VLAN_ADD; adapter->num_vlan_filters++; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); + } else if (f->state == IAVF_VLAN_REMOVE) { + /* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed. + * We can safely only change the state here. + */ + f->state = IAVF_VLAN_ACTIVE; } clearout: @@ -793,8 +798,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { - f->state = IAVF_VLAN_REMOVE; - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); + /* IAVF_ADD_VLAN means that VLAN wasn't even added yet. + * Remove it from the list. + */ + if (f->state == IAVF_VLAN_ADD) { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } else { + f->state = IAVF_VLAN_REMOVE; + iavf_schedule_aq_request(adapter, + IAVF_FLAG_AQ_DEL_VLAN_FILTER); + } } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -1180,7 +1195,7 @@ static void iavf_napi_enable_all(struct iavf_adapter *adapter) q_vector = &adapter->q_vectors[q_idx]; napi = &q_vector->napi; - napi_enable(napi); + napi_enable_locked(napi); } } @@ -1196,7 +1211,7 @@ static void iavf_napi_disable_all(struct iavf_adapter *adapter) for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = &adapter->q_vectors[q_idx]; - napi_disable(&q_vector->napi); + napi_disable_locked(&q_vector->napi); } } @@ -1800,8 +1815,8 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) q_vector->v_idx = q_idx; q_vector->reg_idx = q_idx; cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); - netif_napi_add(adapter->netdev, &q_vector->napi, - iavf_napi_poll); + netif_napi_add_locked(adapter->netdev, &q_vector->napi, + iavf_napi_poll); } return 0; @@ -1827,7 +1842,7 @@ static void iavf_free_q_vectors(struct iavf_adapter *adapter) for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; - netif_napi_del(&q_vector->napi); + netif_napi_del_locked(&q_vector->napi); } kfree(adapter->q_vectors); adapter->q_vectors = NULL; @@ -1968,6 +1983,7 @@ err: static void iavf_finish_config(struct work_struct *work) { struct iavf_adapter *adapter; + bool netdev_released = false; int pairs, err; adapter = container_of(work, struct iavf_adapter, finish_config); @@ -1976,7 +1992,7 @@ static void iavf_finish_config(struct work_struct *work) * The dev->lock is needed to update the queue number */ rtnl_lock(); - mutex_lock(&adapter->netdev->lock); + netdev_lock(adapter->netdev); mutex_lock(&adapter->crit_lock); if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && @@ -1988,7 +2004,16 @@ static void iavf_finish_config(struct work_struct *work) switch (adapter->state) { case __IAVF_DOWN: + /* Set the real number of queues when reset occurs while + * state == __IAVF_DOWN + */ + pairs = adapter->num_active_queues; + netif_set_real_num_rx_queues(adapter->netdev, pairs); + netif_set_real_num_tx_queues(adapter->netdev, pairs); + if (adapter->netdev->reg_state != NETREG_REGISTERED) { + netdev_unlock(adapter->netdev); + netdev_released = true; err = register_netdevice(adapter->netdev); if (err) { dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", @@ -2003,11 +2028,7 @@ static void iavf_finish_config(struct work_struct *work) goto out; } } - - /* Set the real number of queues when reset occurs while - * state == __IAVF_DOWN - */ - fallthrough; + break; case __IAVF_RUNNING: pairs = adapter->num_active_queues; netif_set_real_num_rx_queues(adapter->netdev, pairs); @@ -2020,7 +2041,8 @@ static void iavf_finish_config(struct work_struct *work) out: mutex_unlock(&adapter->crit_lock); - mutex_unlock(&adapter->netdev->lock); + if (!netdev_released) + netdev_unlock(adapter->netdev); rtnl_unlock(); } @@ -2713,12 +2735,16 @@ static void iavf_watchdog_task(struct work_struct *work) struct iavf_adapter *adapter = container_of(work, struct iavf_adapter, watchdog_task.work); + struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; u32 reg_val; + netdev_lock(netdev); if (!mutex_trylock(&adapter->crit_lock)) { - if (adapter->state == __IAVF_REMOVE) + if (adapter->state == __IAVF_REMOVE) { + netdev_unlock(netdev); return; + } goto restart_watchdog; } @@ -2730,30 +2756,35 @@ static void iavf_watchdog_task(struct work_struct *work) case __IAVF_STARTUP: iavf_startup(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_VERSION_CHECK: iavf_init_version_check(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_GET_RESOURCES: iavf_init_get_resources(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_EXTENDED_CAPS: iavf_init_process_extended_caps(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_CONFIG_ADAPTER: iavf_init_config_adapter(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; @@ -2765,6 +2796,7 @@ static void iavf_watchdog_task(struct work_struct *work) * as it can loop forever */ mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { @@ -2773,6 +2805,7 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; iavf_shutdown_adminq(hw); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, (5 * HZ)); return; @@ -2780,6 +2813,7 @@ static void iavf_watchdog_task(struct work_struct *work) /* Try again from failed step*/ iavf_change_state(adapter, adapter->last_state); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ); return; case __IAVF_COMM_FAILED: @@ -2792,6 +2826,7 @@ static void iavf_watchdog_task(struct work_struct *work) iavf_change_state(adapter, __IAVF_INIT_FAILED); adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & @@ -2811,12 +2846,14 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(10)); return; case __IAVF_RESETTING: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); return; @@ -2847,6 +2884,7 @@ static void iavf_watchdog_task(struct work_struct *work) case __IAVF_REMOVE: default: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } @@ -2858,12 +2896,14 @@ static void iavf_watchdog_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); return; } mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); restart_watchdog: if (adapter->state >= __IAVF_DOWN) queue_work(adapter->wq, &adapter->adminq_task); @@ -2990,12 +3030,12 @@ static void iavf_reset_task(struct work_struct *work) /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ - mutex_lock(&netdev->lock); + netdev_lock(netdev); if (!mutex_trylock(&adapter->crit_lock)) { if (adapter->state != __IAVF_REMOVE) queue_work(adapter->wq, &adapter->reset_task); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); return; } @@ -3043,7 +3083,7 @@ static void iavf_reset_task(struct work_struct *work) reg_val); iavf_disable_vf(adapter); mutex_unlock(&adapter->crit_lock); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3184,7 +3224,7 @@ continue_reset: wake_up(&adapter->reset_waitqueue); mutex_unlock(&adapter->crit_lock); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); return; reset_err: @@ -3195,7 +3235,7 @@ reset_err: iavf_disable_vf(adapter); mutex_unlock(&adapter->crit_lock); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); } @@ -3667,10 +3707,10 @@ exit: if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) return 0; - mutex_lock(&netdev->lock); + netdev_lock(netdev); netif_set_real_num_rx_queues(netdev, total_qps); netif_set_real_num_tx_queues(netdev, total_qps); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); return ret; } @@ -4340,14 +4380,17 @@ static int iavf_open(struct net_device *netdev) return -EIO; } + netdev_lock(netdev); while (!mutex_trylock(&adapter->crit_lock)) { /* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock * is already taken and iavf_open is called from an upper * device's notifier reacting on NETDEV_REGISTER event. * We have to leave here to avoid dead lock. */ - if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) + if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) { + netdev_unlock(netdev); return -EBUSY; + } usleep_range(500, 1000); } @@ -4396,6 +4439,7 @@ static int iavf_open(struct net_device *netdev) iavf_irq_enable(adapter, true); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return 0; @@ -4408,6 +4452,7 @@ err_setup_tx: iavf_free_all_tx_resources(adapter); err_unlock: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return err; } @@ -4429,10 +4474,12 @@ static int iavf_close(struct net_device *netdev) u64 aq_to_restore; int status; + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); if (adapter->state <= __IAVF_DOWN_PENDING) { mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return 0; } @@ -4466,6 +4513,7 @@ static int iavf_close(struct net_device *netdev) iavf_free_traffic_irqs(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); /* We explicitly don't free resources here because the hardware is * still active and can DMA into memory. Resources are cleared in @@ -5342,6 +5390,7 @@ static int iavf_suspend(struct device *dev_d) netif_device_detach(netdev); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); if (netif_running(netdev)) { @@ -5353,6 +5402,7 @@ static int iavf_suspend(struct device *dev_d) iavf_reset_interrupt_capability(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return 0; } @@ -5451,6 +5501,7 @@ static void iavf_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); dev_info(&adapter->pdev->dev, "Removing device\n"); iavf_change_state(adapter, __IAVF_REMOVE); @@ -5487,6 +5538,7 @@ static void iavf_remove(struct pci_dev *pdev) mutex_destroy(&hw->aq.asq_mutex); mutex_unlock(&adapter->crit_lock); mutex_destroy(&adapter->crit_lock); + netdev_unlock(netdev); iounmap(hw->hw_addr); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 3307d551f431..9e0d9f710441 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -32,7 +32,8 @@ ice-y := ice_main.o \ ice_parser_rt.o \ ice_idc.o \ devlink/devlink.o \ - devlink/devlink_port.o \ + devlink/health.o \ + devlink/port.o \ ice_sf_eth.o \ ice_sf_vsi_vlan_ops.o \ ice_ddp.o \ diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 415445cefdb2..d116e2b10bce 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -6,7 +6,7 @@ #include "ice.h" #include "ice_lib.h" #include "devlink.h" -#include "devlink_port.h" +#include "port.h" #include "ice_eswitch.h" #include "ice_fw_update.h" #include "ice_dcb_lib.h" @@ -368,14 +368,18 @@ static int ice_devlink_info_get(struct devlink *devlink, } break; case ICE_VERSION_RUNNING: - err = devlink_info_version_running_put(req, key, ctx->buf); + err = devlink_info_version_running_put_ext(req, key, + ctx->buf, + DEVLINK_INFO_VERSION_TYPE_COMPONENT); if (err) { NL_SET_ERR_MSG_MOD(extack, "Unable to set running version"); goto out_free_ctx; } break; case ICE_VERSION_STORED: - err = devlink_info_version_stored_put(req, key, ctx->buf); + err = devlink_info_version_stored_put_ext(req, key, + ctx->buf, + DEVLINK_INFO_VERSION_TYPE_COMPONENT); if (err) { NL_SET_ERR_MSG_MOD(extack, "Unable to set stored version"); goto out_free_ctx; @@ -1207,9 +1211,15 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) struct ice_vsi *vsi = ice_get_main_vsi(pf); int err; + err = ice_init_hw(&pf->hw); + if (err) { + dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err); + return err; + } + err = ice_init_dev(pf); if (err) - return err; + goto unroll_hw_init; vsi->flags = ICE_VSI_FLAG_INIT; @@ -1232,6 +1242,8 @@ err_load: rtnl_unlock(); err_vsi_cfg: ice_deinit_dev(pf); +unroll_hw_init: + ice_deinit_hw(&pf->hw); return err; } diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c new file mode 100644 index 000000000000..ea40f7941259 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/health.c @@ -0,0 +1,550 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Intel Corporation. */ + +#include "ice.h" +#include "ice_adminq_cmd.h" /* for enum ice_aqc_health_status_elem */ +#include "health.h" + +#define ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, obj, name) \ + devlink_fmsg_put(fmsg, #name, (obj)->name) + +#define ICE_HEALTH_STATUS_DATA_SIZE 2 + +struct ice_health_status { + enum ice_aqc_health_status code; + const char *description; + const char *solution; + const char *data_label[ICE_HEALTH_STATUS_DATA_SIZE]; +}; + +/* + * In addition to the health status codes provided below, the firmware might + * generate Health Status Codes that are not pertinent to the end-user. + * For instance, Health Code 0x1002 is triggered when the command fails. + * Such codes should be disregarded by the end-user. + * The below lookup requires to be sorted by code. + */ + +static const char *const ice_common_port_solutions = + "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex."; +static const char *const ice_port_number_label = "Port Number"; +static const char *const ice_update_nvm_solution = "Update to the latest NVM image."; + +static const struct ice_health_status ice_health_status_lookup[] = { + {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE, "Module type is not supported.", + "Change or replace the module or cable.", {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL, "Module is not qualified.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM, + "Device cannot communicate with the module.", + "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT, "Unresolved module conflict.", + "Manually set speed/duplex or change the port option. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT, "Module is not present.", + "Check that the module is inserted correctly. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED, "Underutilized module.", + "Change or replace the module or cable. Change the port option.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT, "An unsupported module was detected.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG, "Invalid link configuration.", + NULL, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS, "Port hardware access error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE, "A port is unreachable.", + "Change the port option. Update to the latest NVM image."}, + {ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED, "Port speed is limited due to module.", + "Change the module or configure the port option to match the current module speed. Change the port option.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT, + "All configured link modes were attempted but failed to establish link. The device will restart the process to establish link.", + "Check link partner connection and configuration.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED, + "Port speed is limited by PHY capabilities.", + "Change the module to align to port option.", {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO, "LOM topology netlist is corrupted.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_NETLIST, "Unrecoverable netlist error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT, "Port topology conflict.", + "Change the port option. Update to the latest NVM image."}, + {ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS, "Unrecoverable hardware access error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME, "Unrecoverable runtime error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT, "Link management engine failed to initialize.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD, + "Failed to load the firmware image in the external PHY.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_RECOVERY, "The device is in firmware recovery mode.", + ice_update_nvm_solution, {"Extended Error"}}, + {ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS, "The flash chip cannot be accessed.", + "If issue persists, call customer support.", {"Access Type"}}, + {ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH, "NVM authentication failed.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH, "Option ROM authentication failed.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH, "DDP package authentication failed.", + "Update to latest base driver and DDP package."}, + {ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT, "NVM image is incompatible.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT, "Option ROM is incompatible.", + ice_update_nvm_solution, {"Expected PCI Device ID", "Expected Module ID"}}, + {ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB, + "Supplied MIB file is invalid. DCB reverted to default configuration.", + "Disable FW-LLDP and check DCBx system configuration.", + {ice_port_number_label, "MIB ID"}}, +}; + +static int ice_health_status_lookup_compare(const void *a, const void *b) +{ + return ((struct ice_health_status *)a)->code - ((struct ice_health_status *)b)->code; +} + +static const struct ice_health_status *ice_get_health_status(u16 code) +{ + struct ice_health_status key = { .code = code }; + + return bsearch(&key, ice_health_status_lookup, ARRAY_SIZE(ice_health_status_lookup), + sizeof(struct ice_health_status), ice_health_status_lookup_compare); +} + +static void ice_describe_status_code(struct devlink_fmsg *fmsg, + struct ice_aqc_health_status_elem *hse) +{ + static const char *const aux_label[] = { "Aux Data 1", "Aux Data 2" }; + const struct ice_health_status *health_code; + u32 internal_data[2]; + u16 status_code; + + status_code = le16_to_cpu(hse->health_status_code); + + devlink_fmsg_put(fmsg, "Syndrome", status_code); + if (status_code) { + internal_data[0] = le32_to_cpu(hse->internal_data1); + internal_data[1] = le32_to_cpu(hse->internal_data2); + + health_code = ice_get_health_status(status_code); + if (!health_code) + return; + + devlink_fmsg_string_pair_put(fmsg, "Description", health_code->description); + if (health_code->solution) + devlink_fmsg_string_pair_put(fmsg, "Possible Solution", + health_code->solution); + + for (size_t i = 0; i < ICE_HEALTH_STATUS_DATA_SIZE; i++) { + if (internal_data[i] != ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA) + devlink_fmsg_u32_pair_put(fmsg, + health_code->data_label[i] ? + health_code->data_label[i] : + aux_label[i], + internal_data[i]); + } + } +} + +static int +ice_port_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.port_status); + return 0; +} + +static int +ice_port_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + void *priv_ctx, struct netlink_ext_ack __always_unused *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.port_status); + return 0; +} + +static int +ice_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.fw_status); + return 0; +} + +static int +ice_fw_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + void *priv_ctx, struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.fw_status); + return 0; +} + +static void ice_config_health_events(struct ice_pf *pf, bool enable) +{ + u8 enable_bits = 0; + int ret; + + if (enable) + enable_bits = ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK | + ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK; + + ret = ice_aq_set_health_status_cfg(&pf->hw, enable_bits); + if (ret) + dev_err(ice_pf_to_dev(pf), "Failed to %s firmware health events, err %d aq_err %s\n", + str_enable_disable(enable), ret, + ice_aq_str(pf->hw.adminq.sq_last_status)); +} + +/** + * ice_process_health_status_event - Process the health status event from FW + * @pf: pointer to the PF structure + * @event: event structure containing the Health Status Event opcode + * + * Decode the Health Status Events and print the associated messages + */ +void ice_process_health_status_event(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + const struct ice_aqc_health_status_elem *health_info; + u16 count; + + health_info = (struct ice_aqc_health_status_elem *)event->msg_buf; + count = le16_to_cpu(event->desc.params.get_health_status.health_status_count); + + if (count > (event->buf_len / sizeof(*health_info))) { + dev_err(ice_pf_to_dev(pf), "Received a health status event with invalid element count\n"); + return; + } + + for (size_t i = 0; i < count; i++) { + const struct ice_health_status *health_code; + u16 status_code; + + status_code = le16_to_cpu(health_info->health_status_code); + health_code = ice_get_health_status(status_code); + + if (health_code) { + switch (le16_to_cpu(health_info->event_source)) { + case ICE_AQC_HEALTH_STATUS_GLOBAL: + pf->health_reporters.fw_status = *health_info; + devlink_health_report(pf->health_reporters.fw, + "FW syndrome reported", NULL); + break; + case ICE_AQC_HEALTH_STATUS_PF: + case ICE_AQC_HEALTH_STATUS_PORT: + pf->health_reporters.port_status = *health_info; + devlink_health_report(pf->health_reporters.port, + "Port syndrome reported", NULL); + break; + default: + dev_err(ice_pf_to_dev(pf), "Health code with unknown source\n"); + } + } else { + u32 data1, data2; + u16 source; + + source = le16_to_cpu(health_info->event_source); + data1 = le32_to_cpu(health_info->internal_data1); + data2 = le32_to_cpu(health_info->internal_data2); + dev_dbg(ice_pf_to_dev(pf), + "Received internal health status code 0x%08x, source: 0x%08x, data1: 0x%08x, data2: 0x%08x", + status_code, source, data1, data2); + } + health_info++; + } +} + +/** + * ice_devlink_health_report - boilerplate to call given @reporter + * + * @reporter: devlink health reporter to call, do nothing on NULL + * @msg: message to pass up, "event name" is fine + * @priv_ctx: typically some event struct + */ +static void ice_devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + if (!reporter) + return; + + /* We do not do auto recovering, so return value of the below function + * will always be 0, thus we do ignore it. + */ + devlink_health_report(reporter, msg, priv_ctx); +} + +struct ice_mdd_event { + enum ice_mdd_src src; + u16 vf_num; + u16 queue; + u8 pf_num; + u8 event; +}; + +static const char *ice_mdd_src_to_str(enum ice_mdd_src src) +{ + switch (src) { + case ICE_MDD_SRC_TX_PQM: + return "tx_pqm"; + case ICE_MDD_SRC_TX_TCLAN: + return "tx_tclan"; + case ICE_MDD_SRC_TX_TDPU: + return "tx_tdpu"; + case ICE_MDD_SRC_RX: + return "rx"; + default: + return "invalid"; + } +} + +static int +ice_mdd_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct ice_mdd_event *mdd_event = priv_ctx; + const char *src; + + if (!mdd_event) + return 0; + + src = ice_mdd_src_to_str(mdd_event->src); + + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_put(fmsg, "src", src); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, pf_num); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, vf_num); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, event); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, queue); + devlink_fmsg_obj_nest_end(fmsg); + + return 0; +} + +/** + * ice_report_mdd_event - Report an MDD event through devlink health + * @pf: the PF device structure + * @src: the HW block that was the source of this MDD event + * @pf_num: the pf_num on which the MDD event occurred + * @vf_num: the vf_num on which the MDD event occurred + * @event: the event type of the MDD event + * @queue: the queue on which the MDD event occurred + * + * Report an MDD event that has occurred on this PF. + */ +void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num, + u16 vf_num, u8 event, u16 queue) +{ + struct ice_mdd_event ev = { + .src = src, + .pf_num = pf_num, + .vf_num = vf_num, + .event = event, + .queue = queue, + }; + + ice_devlink_health_report(pf->health_reporters.mdd, "MDD event", &ev); +} + +/** + * ice_fmsg_put_ptr - put hex value of pointer into fmsg + * + * @fmsg: devlink fmsg under construction + * @name: name to pass + * @ptr: 64 bit value to print as hex and put into fmsg + */ +static void ice_fmsg_put_ptr(struct devlink_fmsg *fmsg, const char *name, + void *ptr) +{ + char buf[sizeof(ptr) * 3]; + + sprintf(buf, "%p", ptr); + devlink_fmsg_put(fmsg, name, buf); +} + +struct ice_tx_hang_event { + u32 head; + u32 intr; + u16 vsi_num; + u16 queue; + u16 next_to_clean; + u16 next_to_use; + struct ice_tx_ring *tx_ring; +}; + +static int ice_tx_hang_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct ice_tx_hang_event *event = priv_ctx; + struct sk_buff *skb; + + if (!event) + return 0; + + skb = event->tx_ring->tx_buf->skb; + devlink_fmsg_obj_nest_start(fmsg); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, head); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, intr); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, vsi_num); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, queue); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_clean); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_use); + devlink_fmsg_put(fmsg, "irq-mapping", event->tx_ring->q_vector->name); + ice_fmsg_put_ptr(fmsg, "desc-ptr", event->tx_ring->desc); + ice_fmsg_put_ptr(fmsg, "dma-ptr", (void *)(long)event->tx_ring->dma); + ice_fmsg_put_ptr(fmsg, "skb-ptr", skb); + devlink_fmsg_binary_pair_put(fmsg, "desc", event->tx_ring->desc, + event->tx_ring->count * sizeof(struct ice_tx_desc)); + devlink_fmsg_dump_skb(fmsg, skb); + devlink_fmsg_obj_nest_end(fmsg); + + return 0; +} + +void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring, + u16 vsi_num, u32 head, u32 intr) +{ + struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf; + + buf->tx_ring = tx_ring; + buf->vsi_num = vsi_num; + buf->head = head; + buf->intr = intr; +} + +void ice_report_tx_hang(struct ice_pf *pf) +{ + struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf; + struct ice_tx_ring *tx_ring = buf->tx_ring; + + struct ice_tx_hang_event ev = { + .head = buf->head, + .intr = buf->intr, + .vsi_num = buf->vsi_num, + .queue = tx_ring->q_index, + .next_to_clean = tx_ring->next_to_clean, + .next_to_use = tx_ring->next_to_use, + .tx_ring = tx_ring, + }; + + ice_devlink_health_report(pf->health_reporters.tx_hang, "Tx hang", &ev); +} + +static struct devlink_health_reporter * +ice_init_devlink_rep(struct ice_pf *pf, + const struct devlink_health_reporter_ops *ops) +{ + struct devlink *devlink = priv_to_devlink(pf); + struct devlink_health_reporter *rep; + const u64 graceful_period = 0; + + rep = devl_health_reporter_create(devlink, ops, graceful_period, pf); + if (IS_ERR(rep)) { + struct device *dev = ice_pf_to_dev(pf); + + dev_err(dev, "failed to create devlink %s health report er", + ops->name); + return NULL; + } + return rep; +} + +#define ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field) \ + ._field = ice_##_name##_reporter_##_field, + +#define ICE_DEFINE_HEALTH_REPORTER_OPS_1(_name, _field1) \ + static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \ + .name = #_name, \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \ + } + +#define ICE_DEFINE_HEALTH_REPORTER_OPS_2(_name, _field1, _field2) \ + static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \ + .name = #_name, \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field2) \ + } + +ICE_DEFINE_HEALTH_REPORTER_OPS_1(mdd, dump); +ICE_DEFINE_HEALTH_REPORTER_OPS_1(tx_hang, dump); +ICE_DEFINE_HEALTH_REPORTER_OPS_2(fw, dump, diagnose); +ICE_DEFINE_HEALTH_REPORTER_OPS_2(port, dump, diagnose); + +/** + * ice_health_init - allocate and init all ice devlink health reporters and + * accompanied data + * + * @pf: PF struct + */ +void ice_health_init(struct ice_pf *pf) +{ + struct ice_health *reps = &pf->health_reporters; + + reps->mdd = ice_init_devlink_rep(pf, &ice_mdd_reporter_ops); + reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops); + + if (ice_is_fw_health_report_supported(&pf->hw)) { + reps->fw = ice_init_devlink_rep(pf, &ice_fw_reporter_ops); + reps->port = ice_init_devlink_rep(pf, &ice_port_reporter_ops); + ice_config_health_events(pf, true); + } +} + +/** + * ice_deinit_devl_reporter - destroy given devlink health reporter + * @reporter: reporter to destroy + */ +static void ice_deinit_devl_reporter(struct devlink_health_reporter *reporter) +{ + if (reporter) + devl_health_reporter_destroy(reporter); +} + +/** + * ice_health_deinit - deallocate all ice devlink health reporters and + * accompanied data + * + * @pf: PF struct + */ +void ice_health_deinit(struct ice_pf *pf) +{ + ice_deinit_devl_reporter(pf->health_reporters.mdd); + ice_deinit_devl_reporter(pf->health_reporters.tx_hang); + if (ice_is_fw_health_report_supported(&pf->hw)) { + ice_deinit_devl_reporter(pf->health_reporters.fw); + ice_deinit_devl_reporter(pf->health_reporters.port); + ice_config_health_events(pf, false); + } +} + +static +void ice_health_assign_healthy_state(struct devlink_health_reporter *reporter) +{ + if (reporter) + devlink_health_reporter_state_update(reporter, + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); +} + +/** + * ice_health_clear - clear devlink health issues after a reset + * @pf: the PF device structure + * + * Mark the PF in healthy state again after a reset has completed. + */ +void ice_health_clear(struct ice_pf *pf) +{ + ice_health_assign_healthy_state(pf->health_reporters.mdd); + ice_health_assign_healthy_state(pf->health_reporters.tx_hang); +} diff --git a/drivers/net/ethernet/intel/ice/devlink/health.h b/drivers/net/ethernet/intel/ice/devlink/health.h new file mode 100644 index 000000000000..5edfc4d2adce --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/health.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024, Intel Corporation. */ + +#ifndef _HEALTH_H_ +#define _HEALTH_H_ + +#include + +/** + * DOC: health.h + * + * This header file stores everything that is needed for broadly understood + * devlink health mechanism for ice driver. + */ + +struct ice_aqc_health_status_elem; +struct ice_pf; +struct ice_tx_ring; +struct ice_rq_event_info; + +enum ice_mdd_src { + ICE_MDD_SRC_TX_PQM, + ICE_MDD_SRC_TX_TCLAN, + ICE_MDD_SRC_TX_TDPU, + ICE_MDD_SRC_RX, +}; + +/** + * struct ice_health - stores ice devlink health reporters and accompanied data + * @fw: devlink health reporter for FW Health Status events + * @mdd: devlink health reporter for MDD detection event + * @port: devlink health reporter for Port Health Status events + * @tx_hang: devlink health reporter for tx_hang event + * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from + * non-sleeping context + * @tx_ring: ring that the hang occurred on + * @head: descriptor head + * @intr: interrupt register value + * @vsi_num: VSI owning the queue that the hang occurred on + * @fw_status: buffer for last received FW Status event + * @port_status: buffer for last received Port Status event + */ +struct ice_health { + struct devlink_health_reporter *fw; + struct devlink_health_reporter *mdd; + struct devlink_health_reporter *port; + struct devlink_health_reporter *tx_hang; + struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf, + struct ice_tx_ring *tx_ring; + u32 head; + u32 intr; + u16 vsi_num; + ); + struct ice_aqc_health_status_elem fw_status; + struct ice_aqc_health_status_elem port_status; +}; + +void ice_process_health_status_event(struct ice_pf *pf, + struct ice_rq_event_info *event); + +void ice_health_init(struct ice_pf *pf); +void ice_health_deinit(struct ice_pf *pf); +void ice_health_clear(struct ice_pf *pf); + +void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring, + u16 vsi_num, u32 head, u32 intr); +void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num, + u16 vf_num, u8 event, u16 queue); +void ice_report_tx_hang(struct ice_pf *pf); + +#endif /* _HEALTH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/port.c similarity index 99% rename from drivers/net/ethernet/intel/ice/devlink/devlink_port.c rename to drivers/net/ethernet/intel/ice/devlink/port.c index c6779d9dffff..767419a67fef 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c +++ b/drivers/net/ethernet/intel/ice/devlink/port.c @@ -5,7 +5,7 @@ #include "ice.h" #include "devlink.h" -#include "devlink_port.h" +#include "port.h" #include "ice_lib.h" #include "ice_fltr.h" diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h b/drivers/net/ethernet/intel/ice/devlink/port.h similarity index 100% rename from drivers/net/ethernet/intel/ice/devlink/devlink_port.h rename to drivers/net/ethernet/intel/ice/devlink/port.h diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2f5d6f974185..71e05d30f0fd 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -78,6 +78,7 @@ #include "ice_irq.h" #include "ice_dpll.h" #include "ice_adapter.h" +#include "devlink/health.h" #define ICE_BAR0 0 #define ICE_REQ_DESC_MULTIPLE 32 @@ -665,6 +666,7 @@ struct ice_pf { struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES]; struct ice_dplls dplls; struct device *hwmon_dev; + struct ice_health health_reporters; u8 num_quanta_prof_used; }; diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 1489a8ceec51..bdee499f991a 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -12,6 +12,13 @@ #define ICE_AQC_TOPO_MAX_LEVEL_NUM 0x9 #define ICE_AQ_SET_MAC_FRAME_SIZE_MAX 9728 +#define ICE_RXQ_CTX_SIZE_DWORDS 8 +#define ICE_RXQ_CTX_SZ (ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32)) +#define ICE_TXQ_CTX_SZ 22 + +typedef struct __packed { u8 buf[ICE_RXQ_CTX_SZ]; } ice_rxq_ctx_buf_t; +typedef struct __packed { u8 buf[ICE_TXQ_CTX_SZ]; } ice_txq_ctx_buf_t; + struct ice_aqc_generic { __le32 param0; __le32 param1; @@ -1491,7 +1498,6 @@ struct ice_aqc_dnl_equa_param { #define ICE_AQC_RX_EQU_POST1 (0x12 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_BFLF (0x13 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_BFHF (0x14 << ICE_AQC_RX_EQU_SHIFT) -#define ICE_AQC_RX_EQU_DRATE (0x15 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_CTLE_GAINHF (0x20 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_CTLE_GAINLF (0x21 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_CTLE_GAINDC (0x22 << ICE_AQC_RX_EQU_SHIFT) @@ -1665,6 +1671,7 @@ struct ice_aqc_get_port_options_elem { #define ICE_AQC_PORT_OPT_MAX_LANE_25G 5 #define ICE_AQC_PORT_OPT_MAX_LANE_50G 6 #define ICE_AQC_PORT_OPT_MAX_LANE_100G 7 +#define ICE_AQC_PORT_OPT_MAX_LANE_200G 8 u8 global_scid[2]; u8 phy_scid[2]; @@ -1807,6 +1814,7 @@ struct ice_aqc_nvm_pass_comp_tbl { #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED 0x0 #define ICE_AQ_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE 0x1 #define ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED 0x2 +#define ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK 0x3 u8 component_response_code; /* Response only */ #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED_CODE 0x0 #define ICE_AQ_NVM_PASS_COMP_STAMP_IDENTICAL_CODE 0x1 @@ -2084,10 +2092,10 @@ struct ice_aqc_add_txqs_perq { __le16 txq_id; u8 rsvd[2]; __le32 q_teid; - u8 txq_ctx[22]; + ice_txq_ctx_buf_t txq_ctx; u8 rsvd2[2]; struct ice_aqc_txsched_elem info; -}; +} __packed; /* The format of the command buffer for Add Tx LAN Queues (0x0C30) * is an array of the following structs. Please note that the length of @@ -2264,6 +2272,8 @@ struct ice_aqc_get_pkg_info_resp { struct ice_aqc_get_pkg_info pkg_info[]; }; +#define ICE_AQC_GET_CGU_MAX_PHASE_ADJ GENMASK(30, 0) + /* Get CGU abilities command response data structure (indirect 0x0C61) */ struct ice_aqc_get_cgu_abilities { u8 num_inputs; @@ -2508,6 +2518,87 @@ enum ice_aqc_fw_logging_mod { ICE_AQC_FW_LOG_ID_MAX, }; +enum ice_aqc_health_status_mask { + ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK = BIT(0), + ICE_AQC_HEALTH_STATUS_SET_ALL_PF_MASK = BIT(1), + ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK = BIT(2), +}; + +/* Set Health Status (direct 0xFF20) */ +struct ice_aqc_set_health_status_cfg { + u8 event_source; + u8 reserved[15]; +}; + +enum ice_aqc_health_status { + ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT = 0x101, + ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE = 0x102, + ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL = 0x103, + ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM = 0x104, + ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT = 0x105, + ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT = 0x106, + ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED = 0x107, + ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT = 0x108, + ICE_AQC_HEALTH_STATUS_ERR_MOD_DIAGNOSTIC_FEATURE = 0x109, + ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG = 0x10B, + ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS = 0x10C, + ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE = 0x10D, + ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED = 0x10F, + ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT = 0x110, + ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED = 0x111, + ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO = 0x112, + ICE_AQC_HEALTH_STATUS_ERR_NETLIST = 0x113, + ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT = 0x114, + ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS = 0x115, + ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME = 0x116, + ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT = 0x117, + ICE_AQC_HEALTH_STATUS_ERR_PHY_NVM_PROG = 0x120, + ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD = 0x121, + ICE_AQC_HEALTH_STATUS_INFO_RECOVERY = 0x500, + ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS = 0x501, + ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH = 0x502, + ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH = 0x503, + ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH = 0x504, + ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT = 0x505, + ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT = 0x506, + ICE_AQC_HEALTH_STATUS_ERR_NVM_SEC_VIOLATION = 0x507, + ICE_AQC_HEALTH_STATUS_ERR_OROM_SEC_VIOLATION = 0x508, + ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB = 0x509, + ICE_AQC_HEALTH_STATUS_ERR_MNG_TIMEOUT = 0x50A, + ICE_AQC_HEALTH_STATUS_ERR_BMC_RESET = 0x50B, + ICE_AQC_HEALTH_STATUS_ERR_LAST_MNG_FAIL = 0x50C, + ICE_AQC_HEALTH_STATUS_ERR_RESOURCE_ALLOC_FAIL = 0x50D, + ICE_AQC_HEALTH_STATUS_ERR_FW_LOOP = 0x1000, + ICE_AQC_HEALTH_STATUS_ERR_FW_PFR_FAIL = 0x1001, + ICE_AQC_HEALTH_STATUS_ERR_LAST_FAIL_AQ = 0x1002, +}; + +/* Get Health Status (indirect 0xFF22) */ +struct ice_aqc_get_health_status { + __le16 health_status_count; + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + +enum ice_aqc_health_status_scope { + ICE_AQC_HEALTH_STATUS_PF = 0x1, + ICE_AQC_HEALTH_STATUS_PORT = 0x2, + ICE_AQC_HEALTH_STATUS_GLOBAL = 0x3, +}; + +#define ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA 0xDEADBEEF + +/* Get Health Status event buffer entry (0xFF22), + * repeated per reported health status. + */ +struct ice_aqc_health_status_elem { + __le16 health_status_code; + __le16 event_source; + __le32 internal_data1; + __le32 internal_data2; +}; + /* Set FW Logging configuration (indirect 0xFF30) * Register for FW Logging (indirect 0xFF31) * Query FW Logging (indirect 0xFF32) @@ -2648,6 +2739,8 @@ struct ice_aq_desc { struct ice_aqc_get_link_status get_link_status; struct ice_aqc_event_lan_overflow lan_overflow; struct ice_aqc_get_link_topo get_link_topo; + struct ice_aqc_set_health_status_cfg set_health_status_cfg; + struct ice_aqc_get_health_status get_health_status; struct ice_aqc_dnl_call_command dnl_call; struct ice_aqc_i2c read_write_i2c; struct ice_aqc_read_i2c_resp read_i2c_resp; @@ -2850,6 +2943,10 @@ enum ice_adminq_opc { /* Standalone Commands/Events */ ice_aqc_opc_event_lan_overflow = 0x1001, + /* System Diagnostic commands */ + ice_aqc_opc_set_health_status_cfg = 0xFF20, + ice_aqc_opc_get_health_status = 0xFF22, + /* FW Logging Commands */ ice_aqc_opc_fw_logs_config = 0xFF30, ice_aqc_opc_fw_logs_register = 0xFF31, diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 82a9cd4ec7ae..b2af8e3586f7 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -454,6 +454,9 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Rx queue threshold in units of 64 */ rlan_ctx.lrxqthresh = 1; + /* Enable descriptor prefetch */ + rlan_ctx.prefena = 1; + /* PF acts as uplink for switchdev; set flex descriptor with src_vsi * metadata and flags to allow redirecting to PR netdev */ @@ -910,8 +913,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, ice_setup_tx_ctx(ring, &tlan_ctx, pf_q); /* copy context contents into the qg_buf */ qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q); - ice_set_ctx(hw, (u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx, - ice_tlan_ctx_info); + ice_pack_txq_ctx(&tlan_ctx, &qg_buf->txqs[0].txq_ctx); /* init queue specific tail reg. It is referred as * transmit comm scheduler queue doorbell. diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 496d86cbd13f..7a2a2e8da8fa 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -6,6 +6,7 @@ #include "ice_adminq_cmd.h" #include "ice_flow.h" #include "ice_ptp_hw.h" +#include #define ICE_PF_RESET_WAIT_COUNT 300 #define ICE_MAX_NETLIST_SIZE 10 @@ -307,6 +308,42 @@ bool ice_is_e825c(struct ice_hw *hw) } } +/** + * ice_is_pf_c827 - check if pf contains c827 phy + * @hw: pointer to the hw struct + * + * Return: true if the device has c827 phy. + */ +static bool ice_is_pf_c827(struct ice_hw *hw) +{ + struct ice_aqc_get_link_topo cmd = {}; + u8 node_part_number; + u16 node_handle; + int status; + + if (hw->mac_type != ICE_MAC_E810) + return false; + + if (hw->device_id != ICE_DEV_ID_E810C_QSFP) + return true; + + cmd.addr.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) | + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT); + cmd.addr.topo_params.index = 0; + + status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, + &node_handle); + + if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) + return false; + + if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) + return true; + + return false; +} + /** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure @@ -1024,6 +1061,33 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw) } } +/** + * ice_wait_for_fw - wait for full FW readiness + * @hw: pointer to the hardware structure + * @timeout: milliseconds that can elapse before timing out + * + * Return: 0 on success, -ETIMEDOUT on timeout. + */ +static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) +{ + int fw_loading; + u32 elapsed = 0; + + while (elapsed <= timeout) { + fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M; + + /* firmware was not yet loaded, we have to wait more */ + if (fw_loading) { + elapsed += 100; + msleep(100); + continue; + } + return 0; + } + + return -ETIMEDOUT; +} + /** * ice_init_hw - main hardware initialization routine * @hw: pointer to the hardware structure @@ -1173,8 +1237,19 @@ int ice_init_hw(struct ice_hw *hw) mutex_init(&hw->tnl_lock); ice_init_chk_recipe_reuse_support(hw); - return 0; + /* Some cards require longer initialization times + * due to necessity of loading FW from an external source. + * This can take even half a minute. + */ + if (ice_is_pf_c827(hw)) { + status = ice_wait_for_fw(hw, 30000); + if (status) { + dev_err(ice_hw_to_dev(hw), "ice_wait_for_fw timed out"); + goto err_unroll_fltr_mgmt_struct; + } + } + return 0; err_unroll_fltr_mgmt_struct: ice_cleanup_fltr_mgmt_struct(hw); err_unroll_sched: @@ -1360,39 +1435,31 @@ int ice_reset(struct ice_hw *hw, enum ice_reset_req req) } /** - * ice_copy_rxq_ctx_to_hw + * ice_copy_rxq_ctx_to_hw - Copy packed Rx queue context to HW registers * @hw: pointer to the hardware structure - * @ice_rxq_ctx: pointer to the rxq context + * @rxq_ctx: pointer to the packed Rx queue context * @rxq_index: the index of the Rx queue - * - * Copies rxq context from dense structure to HW register space */ -static int -ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, u8 *ice_rxq_ctx, u32 rxq_index) +static void ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, + const ice_rxq_ctx_buf_t *rxq_ctx, + u32 rxq_index) { - u8 i; - - if (!ice_rxq_ctx) - return -EINVAL; - - if (rxq_index > QRX_CTRL_MAX_INDEX) - return -EINVAL; - /* Copy each dword separately to HW */ - for (i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) { - wr32(hw, QRX_CONTEXT(i, rxq_index), - *((u32 *)(ice_rxq_ctx + (i * sizeof(u32))))); + for (int i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) { + u32 ctx = ((const u32 *)rxq_ctx)[i]; - ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i, - *((u32 *)(ice_rxq_ctx + (i * sizeof(u32))))); + wr32(hw, QRX_CONTEXT(i, rxq_index), ctx); + + ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i, ctx); } - - return 0; } +#define ICE_CTX_STORE(struct_name, struct_field, width, lsb) \ + PACKED_FIELD((lsb) + (width) - 1, (lsb), struct struct_name, struct_field) + /* LAN Rx Queue Context */ -static const struct ice_ctx_ele ice_rlan_ctx_info[] = { - /* Field Width LSB */ +static const struct packed_field_u8 ice_rlan_ctx_fields[] = { + /* Field Width LSB */ ICE_CTX_STORE(ice_rlan_ctx, head, 13, 0), ICE_CTX_STORE(ice_rlan_ctx, cpuid, 8, 13), ICE_CTX_STORE(ice_rlan_ctx, base, 57, 32), @@ -1413,35 +1480,50 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { ICE_CTX_STORE(ice_rlan_ctx, tphhead_ena, 1, 196), ICE_CTX_STORE(ice_rlan_ctx, lrxqthresh, 3, 198), ICE_CTX_STORE(ice_rlan_ctx, prefena, 1, 201), - { 0 } }; /** - * ice_write_rxq_ctx + * ice_pack_rxq_ctx - Pack Rx queue context into a HW buffer + * @ctx: the Rx queue context to pack + * @buf: the HW buffer to pack into + * + * Pack the Rx queue context from the CPU-friendly unpacked buffer into its + * bit-packed HW layout. + */ +static void ice_pack_rxq_ctx(const struct ice_rlan_ctx *ctx, + ice_rxq_ctx_buf_t *buf) +{ + pack_fields(buf, sizeof(*buf), ctx, ice_rlan_ctx_fields, + QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST); +} + +/** + * ice_write_rxq_ctx - Write Rx Queue context to hardware * @hw: pointer to the hardware structure - * @rlan_ctx: pointer to the rxq context + * @rlan_ctx: pointer to the unpacked Rx queue context * @rxq_index: the index of the Rx queue * - * Converts rxq context from sparse to dense structure and then writes - * it to HW register space and enables the hardware to prefetch descriptors - * instead of only fetching them on demand + * Pack the sparse Rx Queue context into dense hardware format and write it + * into the HW register space. + * + * Return: 0 on success, or -EINVAL if the Rx queue index is invalid. */ int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index) { - u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 }; + ice_rxq_ctx_buf_t buf = {}; - if (!rlan_ctx) + if (rxq_index > QRX_CTRL_MAX_INDEX) return -EINVAL; - rlan_ctx->prefena = 1; + ice_pack_rxq_ctx(rlan_ctx, &buf); + ice_copy_rxq_ctx_to_hw(hw, &buf, rxq_index); - ice_set_ctx(hw, (u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info); - return ice_copy_rxq_ctx_to_hw(hw, ctx_buf, rxq_index); + return 0; } /* LAN Tx Queue Context */ -const struct ice_ctx_ele ice_tlan_ctx_info[] = { +static const struct packed_field_u8 ice_tlan_ctx_fields[] = { /* Field Width LSB */ ICE_CTX_STORE(ice_tlan_ctx, base, 57, 0), ICE_CTX_STORE(ice_tlan_ctx, port_num, 3, 57), @@ -1470,10 +1552,22 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = { ICE_CTX_STORE(ice_tlan_ctx, drop_ena, 1, 165), ICE_CTX_STORE(ice_tlan_ctx, cache_prof_idx, 2, 166), ICE_CTX_STORE(ice_tlan_ctx, pkt_shaper_prof_idx, 3, 168), - ICE_CTX_STORE(ice_tlan_ctx, int_q_state, 122, 171), - { 0 } }; +/** + * ice_pack_txq_ctx - Pack Tx queue context into a HW buffer + * @ctx: the Tx queue context to pack + * @buf: the HW buffer to pack into + * + * Pack the Tx queue context from the CPU-friendly unpacked buffer into its + * bit-packed HW layout. + */ +void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf) +{ + pack_fields(buf, sizeof(*buf), ctx, ice_tlan_ctx_fields, + QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST); +} + /* Sideband Queue command wrappers */ /** @@ -2547,6 +2641,7 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->ts_ll_read = ((number & ICE_TS_LL_TX_TS_READ_M) != 0); info->ts_ll_int_read = ((number & ICE_TS_LL_TX_TS_INT_READ_M) != 0); + info->ll_phy_tmr_update = ((number & ICE_TS_LL_PHY_TMR_UPDATE_M) != 0); info->ena_ports = logical_id; info->tmr_own_map = phys_id; @@ -2569,6 +2664,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->ts_ll_read); ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_int_read = %u\n", info->ts_ll_int_read); + ice_debug(hw, ICE_DBG_INIT, "dev caps: ll_phy_tmr_update = %u\n", + info->ll_phy_tmr_update); ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n", info->ena_ports); ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n", @@ -2708,40 +2805,6 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, ice_recalc_port_limited_caps(hw, &dev_p->common_cap); } -/** - * ice_is_pf_c827 - check if pf contains c827 phy - * @hw: pointer to the hw struct - */ -bool ice_is_pf_c827(struct ice_hw *hw) -{ - struct ice_aqc_get_link_topo cmd = {}; - u8 node_part_number; - u16 node_handle; - int status; - - if (hw->mac_type != ICE_MAC_E810) - return false; - - if (hw->device_id != ICE_DEV_ID_E810C_QSFP) - return true; - - cmd.addr.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) | - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT); - cmd.addr.topo_params.index = 0; - - status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, - &node_handle); - - if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) - return false; - - if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) - return true; - - return false; -} - /** * ice_is_phy_rclk_in_netlist * @hw: pointer to the hw struct @@ -4095,6 +4158,57 @@ ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid, return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); } +/** + * ice_get_phy_lane_number - Get PHY lane number for current adapter + * @hw: pointer to the hw struct + * + * Return: PHY lane number on success, negative error code otherwise. + */ +int ice_get_phy_lane_number(struct ice_hw *hw) +{ + struct ice_aqc_get_port_options_elem *options; + unsigned int lport = 0; + unsigned int lane; + int err; + + options = kcalloc(ICE_AQC_PORT_OPT_MAX, sizeof(*options), GFP_KERNEL); + if (!options) + return -ENOMEM; + + for (lane = 0; lane < ICE_MAX_PORT_PER_PCI_DEV; lane++) { + u8 options_count = ICE_AQC_PORT_OPT_MAX; + u8 speed, active_idx, pending_idx; + bool active_valid, pending_valid; + + err = ice_aq_get_port_options(hw, options, &options_count, lane, + true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (err) + goto err; + + if (!active_valid) + continue; + + speed = options[active_idx].max_lane_speed; + /* If we don't get speed for this lane, it's unoccupied */ + if (speed > ICE_AQC_PORT_OPT_MAX_LANE_200G) + continue; + + if (hw->pf_id == lport) { + kfree(options); + return lane; + } + + lport++; + } + + /* PHY lane not found */ + err = -ENXIO; +err: + kfree(options); + return err; +} + /** * ice_aq_sff_eeprom * @hw: pointer to the HW struct @@ -4557,205 +4671,6 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps, /* End of FW Admin Queue command wrappers */ -/** - * ice_pack_ctx_byte - write a byte to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_byte(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u8 src_byte, dest_byte, mask; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); - - src_byte = *from; - src_byte <<= shift_width; - src_byte &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_byte, dest, sizeof(dest_byte)); - - dest_byte &= ~mask; /* get the bits not changing */ - dest_byte |= src_byte; /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_byte, sizeof(dest_byte)); -} - -/** - * ice_pack_ctx_word - write a word to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_word(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u16 src_word, mask; - __le16 dest_word; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); - - /* don't swizzle the bits until after the mask because the mask bits - * will be in a different bit position on big endian machines - */ - src_word = *(u16 *)from; - src_word <<= shift_width; - src_word &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_word, dest, sizeof(dest_word)); - - dest_word &= ~(cpu_to_le16(mask)); /* get the bits not changing */ - dest_word |= cpu_to_le16(src_word); /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_word, sizeof(dest_word)); -} - -/** - * ice_pack_ctx_dword - write a dword to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_dword(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u32 src_dword, mask; - __le32 dest_dword; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); - - /* don't swizzle the bits until after the mask because the mask bits - * will be in a different bit position on big endian machines - */ - src_dword = *(u32 *)from; - src_dword <<= shift_width; - src_dword &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_dword, dest, sizeof(dest_dword)); - - dest_dword &= ~(cpu_to_le32(mask)); /* get the bits not changing */ - dest_dword |= cpu_to_le32(src_dword); /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_dword, sizeof(dest_dword)); -} - -/** - * ice_pack_ctx_qword - write a qword to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_qword(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u64 src_qword, mask; - __le64 dest_qword; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK_ULL(ce_info->width - 1 + shift_width, shift_width); - - /* don't swizzle the bits until after the mask because the mask bits - * will be in a different bit position on big endian machines - */ - src_qword = *(u64 *)from; - src_qword <<= shift_width; - src_qword &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_qword, dest, sizeof(dest_qword)); - - dest_qword &= ~(cpu_to_le64(mask)); /* get the bits not changing */ - dest_qword |= cpu_to_le64(src_qword); /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_qword, sizeof(dest_qword)); -} - -/** - * ice_set_ctx - set context bits in packed structure - * @hw: pointer to the hardware structure - * @src_ctx: pointer to a generic non-packed context structure - * @dest_ctx: pointer to memory for the packed structure - * @ce_info: List of Rx context elements - */ -int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - int f; - - for (f = 0; ce_info[f].width; f++) { - /* We have to deal with each element of the FW response - * using the correct size so that we are correct regardless - * of the endianness of the machine. - */ - if (ce_info[f].width > (ce_info[f].size_of * BITS_PER_BYTE)) { - ice_debug(hw, ICE_DBG_QCTX, "Field %d width of %d bits larger than size of %d byte(s) ... skipping write\n", - f, ce_info[f].width, ce_info[f].size_of); - continue; - } - switch (ce_info[f].size_of) { - case sizeof(u8): - ice_pack_ctx_byte(src_ctx, dest_ctx, &ce_info[f]); - break; - case sizeof(u16): - ice_pack_ctx_word(src_ctx, dest_ctx, &ce_info[f]); - break; - case sizeof(u32): - ice_pack_ctx_dword(src_ctx, dest_ctx, &ce_info[f]); - break; - case sizeof(u64): - ice_pack_ctx_qword(src_ctx, dest_ctx, &ce_info[f]); - break; - default: - return -EINVAL; - } - } - - return 0; -} - /** * ice_get_lan_q_ctx - get the LAN queue context for the given VSI and TC * @hw: pointer to the HW struct @@ -6031,6 +5946,44 @@ bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps) return false; } +/** + * ice_is_fw_health_report_supported - checks if firmware supports health events + * @hw: pointer to the hardware structure + * + * Return: true if firmware supports health status reports, + * false otherwise + */ +bool ice_is_fw_health_report_supported(struct ice_hw *hw) +{ + return ice_is_fw_api_min_ver(hw, ICE_FW_API_HEALTH_REPORT_MAJ, + ICE_FW_API_HEALTH_REPORT_MIN, + ICE_FW_API_HEALTH_REPORT_PATCH); +} + +/** + * ice_aq_set_health_status_cfg - Configure FW health events + * @hw: pointer to the HW struct + * @event_source: type of diagnostic events to enable + * + * Configure the health status event types that the firmware will send to this + * PF. The supported event types are: PF-specific, all PFs, and global. + * + * Return: 0 on success, negative error code otherwise. + */ +int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source) +{ + struct ice_aqc_set_health_status_cfg *cmd; + struct ice_aq_desc desc; + + cmd = &desc.params.set_health_status_cfg; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_health_status_cfg); + + cmd->event_source = event_source; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + /** * ice_aq_set_lldp_mib - Set the LLDP MIB * @hw: pointer to the HW struct diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 27208a60cece..15ba38543738 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -92,9 +92,8 @@ ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq); int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading); void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode); -extern const struct ice_ctx_ele ice_tlan_ctx_info[]; -int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info); + +void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf); extern struct mutex ice_global_cfg_lock_sw; @@ -113,7 +112,6 @@ int ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *caps, struct ice_sq_cd *cd); -bool ice_is_pf_c827(struct ice_hw *hw); bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw); bool ice_is_clock_mux_in_netlist(struct ice_hw *hw); bool ice_is_cgu_in_netlist(struct ice_hw *hw); @@ -143,6 +141,8 @@ int ice_get_link_default_override(struct ice_link_default_override_tlv *ldo, struct ice_port_info *pi); bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps); +bool ice_is_fw_health_report_supported(struct ice_hw *hw); +int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source); int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code, u8 serdes_num, int *output); int @@ -193,6 +193,7 @@ ice_aq_get_port_options(struct ice_hw *hw, int ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid, u8 new_option); +int ice_get_phy_lane_number(struct ice_hw *hw); int ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length, diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index d5ad6d84007c..8d806d8ad761 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -2053,7 +2053,7 @@ static int ice_dpll_init_worker(struct ice_pf *pf) struct kthread_worker *kworker; kthread_init_delayed_work(&d->work, ice_dpll_periodic_work); - kworker = kthread_create_worker(0, "ice-dplls-%s", + kworker = kthread_run_worker(0, "ice-dplls-%s", dev_name(ice_pf_to_dev(pf))); if (IS_ERR(kworker)) return PTR_ERR(kworker); @@ -2064,6 +2064,18 @@ static int ice_dpll_init_worker(struct ice_pf *pf) return 0; } +/** + * ice_dpll_phase_range_set - initialize phase adjust range helper + * @range: pointer to phase adjust range struct to be initialized + * @phase_adj: a value to be used as min(-)/max(+) boundary + */ +static void ice_dpll_phase_range_set(struct dpll_pin_phase_adjust_range *range, + u32 phase_adj) +{ + range->min = -phase_adj; + range->max = phase_adj; +} + /** * ice_dpll_init_info_pins_generic - initializes generic pins info * @pf: board private structure @@ -2105,8 +2117,8 @@ static int ice_dpll_init_info_pins_generic(struct ice_pf *pf, bool input) for (i = 0; i < pin_num; i++) { pins[i].idx = i; pins[i].prop.board_label = labels[i]; - pins[i].prop.phase_range.min = phase_adj_max; - pins[i].prop.phase_range.max = -phase_adj_max; + ice_dpll_phase_range_set(&pins[i].prop.phase_range, + phase_adj_max); pins[i].prop.capabilities = cap; pins[i].pf = pf; ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); @@ -2152,6 +2164,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, struct ice_hw *hw = &pf->hw; struct ice_dpll_pin *pins; unsigned long caps; + u32 phase_adj_max; u8 freq_supp_num; bool input; @@ -2159,11 +2172,13 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, case ICE_DPLL_PIN_TYPE_INPUT: pins = pf->dplls.inputs; num_pins = pf->dplls.num_inputs; + phase_adj_max = pf->dplls.input_phase_adj_max; input = true; break; case ICE_DPLL_PIN_TYPE_OUTPUT: pins = pf->dplls.outputs; num_pins = pf->dplls.num_outputs; + phase_adj_max = pf->dplls.output_phase_adj_max; input = false; break; default: @@ -2188,19 +2203,13 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, return ret; caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE | DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE); - pins[i].prop.phase_range.min = - pf->dplls.input_phase_adj_max; - pins[i].prop.phase_range.max = - -pf->dplls.input_phase_adj_max; } else { - pins[i].prop.phase_range.min = - pf->dplls.output_phase_adj_max; - pins[i].prop.phase_range.max = - -pf->dplls.output_phase_adj_max; ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps); if (ret) return ret; } + ice_dpll_phase_range_set(&pins[i].prop.phase_range, + phase_adj_max); pins[i].prop.capabilities = caps; ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); if (ret) @@ -2308,8 +2317,10 @@ static int ice_dpll_init_info(struct ice_pf *pf, bool cgu) dp->dpll_idx = abilities.pps_dpll_idx; d->num_inputs = abilities.num_inputs; d->num_outputs = abilities.num_outputs; - d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj); - d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj); + d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj) & + ICE_AQC_GET_CGU_MAX_PHASE_ADJ; + d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj) & + ICE_AQC_GET_CGU_MAX_PHASE_ADJ; alloc_size = sizeof(*d->inputs) * d->num_inputs; d->inputs = kzalloc(alloc_size, GFP_KERNEL); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index ac7db100e2cd..5c7dcf21b222 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -5,7 +5,7 @@ #define _ICE_ESWITCH_H_ #include -#include "devlink/devlink_port.h" +#include "devlink/port.h" #ifdef CONFIG_ICE_SWITCHDEV void ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 3072634bf049..f241493a6ac8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -710,7 +710,6 @@ static int ice_get_tx_rx_equa(struct ice_hw *hw, u8 serdes_num, { ICE_AQC_RX_EQU_POST1, rx, &ptr->rx_equ_post1 }, { ICE_AQC_RX_EQU_BFLF, rx, &ptr->rx_equ_bflf }, { ICE_AQC_RX_EQU_BFHF, rx, &ptr->rx_equ_bfhf }, - { ICE_AQC_RX_EQU_DRATE, rx, &ptr->rx_equ_drate }, { ICE_AQC_RX_EQU_CTLE_GAINHF, rx, &ptr->rx_equ_ctle_gainhf }, { ICE_AQC_RX_EQU_CTLE_GAINLF, rx, &ptr->rx_equ_ctle_gainlf }, { ICE_AQC_RX_EQU_CTLE_GAINDC, rx, &ptr->rx_equ_ctle_gaindc }, diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h index 8f2ad1c172c0..23b2cfbc9684 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.h +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h @@ -15,7 +15,6 @@ struct ice_serdes_equalization_to_ethtool { int rx_equ_post1; int rx_equ_bflf; int rx_equ_bfhf; - int rx_equ_drate; int rx_equ_ctle_gainhf; int rx_equ_ctle_gainlf; int rx_equ_ctle_gaindc; diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 2702a0da5c3e..70c201f569ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -6,6 +6,7 @@ #include #include #include "ice.h" +#include "ice_lib.h" #include "ice_fw_update.h" struct ice_fwu_priv { @@ -125,6 +126,10 @@ ice_check_component_response(struct ice_pf *pf, u16 id, u8 response, u8 code, case ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED: dev_info(dev, "firmware has rejected updating %s\n", component); break; + case ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK: + if (ice_is_recovery_mode(&pf->hw)) + return 0; + break; } switch (code) { @@ -1004,13 +1009,20 @@ int ice_devlink_flash_update(struct devlink *devlink, return -EOPNOTSUPP; } - if (!hw->dev_caps.common_cap.nvm_unified_update) { + if (!hw->dev_caps.common_cap.nvm_unified_update && !ice_is_recovery_mode(hw)) { NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update"); return -EOPNOTSUPP; } memset(&priv, 0, sizeof(priv)); + if (params->component && strcmp(params->component, "fw.mgmt") == 0) { + priv.context.mode = PLDMFW_UPDATE_MODE_SINGLE_COMPONENT; + priv.context.component_identifier = NVM_COMP_ID_NVM; + } else if (params->component) { + return -EOPNOTSUPP; + } + /* the E822 device needs a slightly different ops */ if (hw->mac_type == ICE_MAC_GENERIC) priv.context.ops = &ice_fwu_ops_e822; diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index f02e8ca55375..b2148dbe49b2 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -182,7 +182,7 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf) pf->gnss_serial = gnss; kthread_init_delayed_work(&gnss->read_work, ice_gnss_read); - kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev)); + kworker = kthread_run_worker(0, "ice-gnss-%s", dev_name(dev)); if (IS_ERR(kworker)) { kfree(gnss); return NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 611577ebc29d..1479b45738af 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -371,29 +371,21 @@ enum ice_rx_flex_desc_status_error_1_bits { ICE_RX_FLEX_DESC_STATUS1_LAST /* this entry must be last!!! */ }; -#define ICE_RXQ_CTX_SIZE_DWORDS 8 -#define ICE_RXQ_CTX_SZ (ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32)) #define ICE_TX_CMPLTNQ_CTX_SIZE_DWORDS 22 #define ICE_TX_DRBELL_Q_CTX_SIZE_DWORDS 5 #define GLTCLAN_CQ_CNTX(i, CQ) (GLTCLAN_CQ_CNTX0(CQ) + ((i) * 0x0800)) -/* RLAN Rx queue context data - * - * The sizes of the variables may be larger than needed due to crossing byte - * boundaries. If we do not have the width of the variable set to the correct - * size then we could end up shifting bits off the top of the variable when the - * variable is at the top of a byte and crosses over into the next byte. - */ +/* RLAN Rx queue context data */ struct ice_rlan_ctx { u16 head; - u16 cpuid; /* bigger than needed, see above for reason */ + u8 cpuid; #define ICE_RLAN_BASE_S 7 u64 base; u16 qlen; #define ICE_RLAN_CTX_DBUF_S 7 - u16 dbuf; /* bigger than needed, see above for reason */ + u8 dbuf; #define ICE_RLAN_CTX_HBUF_S 6 - u16 hbuf; /* bigger than needed, see above for reason */ + u8 hbuf; u8 dtype; u8 dsize; u8 crcstrip; @@ -401,29 +393,15 @@ struct ice_rlan_ctx { u8 hsplit_0; u8 hsplit_1; u8 showiv; - u32 rxmax; /* bigger than needed, see above for reason */ + u16 rxmax; u8 tphrdesc_ena; u8 tphwdesc_ena; u8 tphdata_ena; u8 tphhead_ena; - u16 lrxqthresh; /* bigger than needed, see above for reason */ + u8 lrxqthresh; u8 prefena; /* NOTE: normally must be set to 1 at init */ }; -struct ice_ctx_ele { - u16 offset; - u16 size_of; - u16 width; - u16 lsb; -}; - -#define ICE_CTX_STORE(_struct, _ele, _width, _lsb) { \ - .offset = offsetof(struct _struct, _ele), \ - .size_of = sizeof_field(struct _struct, _ele), \ - .width = _width, \ - .lsb = _lsb, \ -} - /* for hsplit_0 field of Rx RLAN context */ enum ice_rlan_ctx_rx_hsplit_0 { ICE_RLAN_RX_HSPLIT_0_NO_SPLIT = 0, @@ -551,18 +529,12 @@ enum ice_tx_ctx_desc_eipt_offload { #define ICE_LAN_TXQ_MAX_QGRPS 127 #define ICE_LAN_TXQ_MAX_QDIS 1023 -/* Tx queue context data - * - * The sizes of the variables may be larger than needed due to crossing byte - * boundaries. If we do not have the width of the variable set to the correct - * size then we could end up shifting bits off the top of the variable when the - * variable is at the top of a byte and crosses over into the next byte. - */ +/* Tx queue context data */ struct ice_tlan_ctx { #define ICE_TLAN_CTX_BASE_S 7 u64 base; /* base is defined in 128-byte units */ u8 port_num; - u16 cgd_num; /* bigger than needed, see above for reason */ + u8 cgd_num; u8 pf_num; u16 vmvf_num; u8 vmvf_type; @@ -573,7 +545,7 @@ struct ice_tlan_ctx { u8 tsyn_ena; u8 internal_usage_flag; u8 alt_vlan; - u16 cpuid; /* bigger than needed, see above for reason */ + u8 cpuid; u8 wb_mode; u8 tphrd_desc; u8 tphrd; @@ -582,7 +554,7 @@ struct ice_tlan_ctx { u16 qnum_in_func; u8 itr_notification_mode; u8 adjust_prof_id; - u32 qlen; /* bigger than needed, see above for reason */ + u16 qlen; u8 quanta_prof_idx; u8 tso_ena; u16 tso_qnum; @@ -590,7 +562,6 @@ struct ice_tlan_ctx { u8 drop_ena; u8 cache_prof_idx; u8 pkt_shaper_prof_idx; - u8 int_q_state; /* width not needed - internal - DO NOT WRITE!!! */ }; #endif /* _ICE_LAN_TX_RX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index a7d45a8ce7ac..38a1c8372180 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1700,6 +1700,12 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf) return true; } +#define ICE_FW_MODE_REC_M BIT(1) +bool ice_is_recovery_mode(struct ice_hw *hw) +{ + return rd32(hw, GL_MNG_FWSM) & ICE_FW_MODE_REC_M; +} + /** * ice_update_eth_stats - Update VSI-specific ethernet statistics counters * @vsi: the VSI to be updated diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 10d6fc479a32..eabb35834a24 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -90,6 +90,7 @@ void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); bool ice_is_safe_mode(struct ice_pf *pf); bool ice_is_rdma_ena(struct ice_pf *pf); +bool ice_is_recovery_mode(struct ice_hw *hw); bool ice_is_dflt_vsi_in_use(struct ice_port_info *pi); bool ice_is_vsi_dflt_vsi(struct ice_vsi *vsi); int ice_set_dflt_vsi(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 0ab35607e5d5..c3a0fb97c5ee 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -14,7 +14,7 @@ #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" #include "devlink/devlink.h" -#include "devlink/devlink_port.h" +#include "devlink/port.h" #include "ice_sf_eth.h" #include "ice_hwmon.h" /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the @@ -1144,7 +1144,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (link_up == old_link && link_speed == old_link_speed) return 0; - ice_ptp_link_change(pf, pf->hw.pf_id, link_up); + ice_ptp_link_change(pf, link_up); if (ice_is_dcb_active(pf)) { if (test_bit(ICE_FLAG_DCB_ENA, pf->flags)) @@ -1567,6 +1567,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) case ice_aqc_opc_lldp_set_mib_change: ice_dcb_process_lldp_set_mib_change(pf, &event); break; + case ice_aqc_opc_get_health_status: + ice_process_health_status_event(pf, &event); + break; default: dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n", qtype, opcode); @@ -1816,6 +1819,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); + ice_report_mdd_event(pf, ICE_MDD_SRC_TX_PQM, pf_num, vf_num, + event, queue); wr32(hw, GL_MDET_TX_PQM, 0xffffffff); } @@ -1829,6 +1834,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); + ice_report_mdd_event(pf, ICE_MDD_SRC_TX_TCLAN, pf_num, vf_num, + event, queue); wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX); } @@ -1842,6 +1849,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_rx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); + ice_report_mdd_event(pf, ICE_MDD_SRC_RX, pf_num, vf_num, event, + queue); wr32(hw, GL_MDET_RX, 0xffffffff); } @@ -2355,6 +2364,18 @@ static void ice_check_media_subtask(struct ice_pf *pf) } } +static void ice_service_task_recovery_mode(struct work_struct *work) +{ + struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); + + set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state); + ice_clean_adminq_subtask(pf); + + ice_service_task_complete(pf); + + mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100)); +} + /** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct @@ -2364,9 +2385,11 @@ static void ice_service_task(struct work_struct *work) struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); unsigned long start_time = jiffies; - /* subtasks */ + if (pf->health_reporters.tx_hang_buf.tx_ring) { + ice_report_tx_hang(pf); + pf->health_reporters.tx_hang_buf.tx_ring = NULL; + } - /* process reset requests first */ ice_reset_subtask(pf); /* bail if a reset/recovery cycle is pending or rebuild failed */ @@ -4741,55 +4764,12 @@ static void ice_decfg_netdev(struct ice_vsi *vsi) vsi->netdev = NULL; } -/** - * ice_wait_for_fw - wait for full FW readiness - * @hw: pointer to the hardware structure - * @timeout: milliseconds that can elapse before timing out - */ -static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) -{ - int fw_loading; - u32 elapsed = 0; - - while (elapsed <= timeout) { - fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M; - - /* firmware was not yet loaded, we have to wait more */ - if (fw_loading) { - elapsed += 100; - msleep(100); - continue; - } - return 0; - } - - return -ETIMEDOUT; -} - int ice_init_dev(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int err; - err = ice_init_hw(hw); - if (err) { - dev_err(dev, "ice_init_hw failed: %d\n", err); - return err; - } - - /* Some cards require longer initialization times - * due to necessity of loading FW from an external source. - * This can take even half a minute. - */ - if (ice_is_pf_c827(hw)) { - err = ice_wait_for_fw(hw, 30000); - if (err) { - dev_err(dev, "ice_wait_for_fw timed out"); - return err; - } - } - ice_init_feature_support(pf); err = ice_init_ddp_config(hw, pf); @@ -4810,7 +4790,7 @@ int ice_init_dev(struct ice_pf *pf) err = ice_init_pf(pf); if (err) { dev_err(dev, "ice_init_pf failed: %d\n", err); - goto err_init_pf; + return err; } pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; @@ -4834,7 +4814,7 @@ int ice_init_dev(struct ice_pf *pf) if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); err = -EIO; - goto err_init_interrupt_scheme; + goto unroll_pf_init; } /* In case of MSIX we are going to setup the misc vector right here @@ -4845,17 +4825,15 @@ int ice_init_dev(struct ice_pf *pf) err = ice_req_irq_msix_misc(pf); if (err) { dev_err(dev, "setup of misc vector failed: %d\n", err); - goto err_req_irq_msix_misc; + goto unroll_irq_scheme_init; } return 0; -err_req_irq_msix_misc: +unroll_irq_scheme_init: ice_clear_interrupt_scheme(pf); -err_init_interrupt_scheme: +unroll_pf_init: ice_deinit_pf(pf); -err_init_pf: - ice_deinit_hw(hw); return err; } @@ -5087,6 +5065,7 @@ static int ice_init_devlink(struct ice_pf *pf) return err; ice_devlink_init_regions(pf); + ice_health_init(pf); ice_devlink_register(pf); return 0; @@ -5095,6 +5074,7 @@ static int ice_init_devlink(struct ice_pf *pf) static void ice_deinit_devlink(struct ice_pf *pf) { ice_devlink_unregister(pf); + ice_health_deinit(pf); ice_devlink_destroy_regions(pf); ice_devlink_unregister_params(pf); } @@ -5249,6 +5229,36 @@ void ice_unload(struct ice_pf *pf) ice_decfg_netdev(vsi); } +static int ice_probe_recovery_mode(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n"); + + INIT_HLIST_HEAD(&pf->aq_wait_list); + spin_lock_init(&pf->aq_wait_lock); + init_waitqueue_head(&pf->aq_wait_queue); + + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode); + clear_bit(ICE_SERVICE_SCHED, pf->state); + err = ice_create_all_ctrlq(&pf->hw); + if (err) + return err; + + scoped_guard(devl, priv_to_devlink(pf)) { + err = ice_init_devlink(pf); + if (err) + return err; + } + + ice_service_task_restart(pf); + + return 0; +} + /** * ice_probe - Device initialization routine * @pdev: PCI device information struct @@ -5312,13 +5322,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) } pci_set_master(pdev); - - adapter = ice_adapter_get(pdev); - if (IS_ERR(adapter)) - return PTR_ERR(adapter); - pf->pdev = pdev; - pf->adapter = adapter; pci_set_drvdata(pdev, pf); set_bit(ICE_DOWN, pf->state); /* Disable service task until DOWN bit is cleared */ @@ -5346,29 +5350,47 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) hw->debug_mask = debug; #endif + if (ice_is_recovery_mode(hw)) + return ice_probe_recovery_mode(pf); + + err = ice_init_hw(hw); + if (err) { + dev_err(dev, "ice_init_hw failed: %d\n", err); + return err; + } + + adapter = ice_adapter_get(pdev); + if (IS_ERR(adapter)) { + err = PTR_ERR(adapter); + goto unroll_hw_init; + } + pf->adapter = adapter; + err = ice_init(pf); if (err) - goto err_init; + goto unroll_adapter; devl_lock(priv_to_devlink(pf)); err = ice_load(pf); if (err) - goto err_load; + goto unroll_init; err = ice_init_devlink(pf); if (err) - goto err_init_devlink; + goto unroll_load; devl_unlock(priv_to_devlink(pf)); return 0; -err_init_devlink: +unroll_load: ice_unload(pf); -err_load: +unroll_init: devl_unlock(priv_to_devlink(pf)); ice_deinit(pf); -err_init: +unroll_adapter: ice_adapter_put(pdev); +unroll_hw_init: + ice_deinit_hw(hw); return err; } @@ -5448,6 +5470,14 @@ static void ice_remove(struct pci_dev *pdev) msleep(100); } + if (ice_is_recovery_mode(&pf->hw)) { + ice_service_task_stop(pf); + scoped_guard(devl, priv_to_devlink(pf)) { + ice_deinit_devlink(pf); + } + return; + } + if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { set_bit(ICE_VF_RESETS_DISABLED, pf->state); ice_free_vfs(pf); @@ -6790,7 +6820,7 @@ static int ice_up_complete(struct ice_vsi *vsi) ice_print_link_msg(vsi, true); netif_tx_start_all_queues(vsi->netdev); netif_carrier_on(vsi->netdev); - ice_ptp_link_change(pf, pf->hw.pf_id, true); + ice_ptp_link_change(pf, true); } /* Perform an initial read of the statistics registers now to @@ -7260,7 +7290,7 @@ int ice_down(struct ice_vsi *vsi) if (vsi->netdev) { vlan_err = ice_vsi_del_vlan_zero(vsi); - ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false); + ice_ptp_link_change(vsi->back, false); netif_carrier_off(vsi->netdev); netif_tx_disable(vsi->netdev); } @@ -7793,6 +7823,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* if we get here, reset flow is successful */ clear_bit(ICE_RESET_FAILED, pf->state); + ice_health_clear(pf); + ice_plug_aux_dev(pf); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) ice_lag_rebuild(pf); @@ -8283,16 +8315,18 @@ void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) if (tx_ring) { struct ice_hw *hw = &pf->hw; - u32 head, val = 0; + u32 head, intr = 0; head = FIELD_GET(QTX_COMM_HEAD_HEAD_M, rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue]))); /* Read interrupt register */ - val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); + intr = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %u, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n", vsi->vsi_num, txqueue, tx_ring->next_to_clean, - head, tx_ring->next_to_use, val); + head, tx_ring->next_to_use, intr); + + ice_prep_tx_hang_report(pf, tx_ring, vsi->vsi_num, head, intr); } pf->tx_timeout_last_recovery = jiffies; diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h index 6509d807627c..4f56d53d56b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.h +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -257,7 +257,6 @@ ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size, /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ #define ICE_BST_TCAM_TABLE_SIZE 256 #define ICE_BST_TCAM_KEY_SIZE 20 -#define ICE_BST_KEY_TCAM_SIZE 19 /* Boost TCAM item */ struct ice_bst_tcam_item { @@ -401,7 +400,6 @@ u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag); #define ICE_PARSER_GPR_NUM 128 #define ICE_PARSER_FLG_NUM 64 #define ICE_PARSER_ERR_NUM 16 -#define ICE_BST_KEY_SIZE 10 #define ICE_MARKER_ID_SIZE 9 #define ICE_MARKER_MAX_SIZE \ (ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1) @@ -431,13 +429,13 @@ struct ice_parser_rt { u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV]; u16 pkt_len; u16 po; - u8 bst_key[ICE_BST_KEY_SIZE]; + u8 bst_key[ICE_BST_TCAM_KEY_SIZE]; struct ice_pg_cam_key pg_key; + u8 pg_prio; struct ice_alu *alu0; struct ice_alu *alu1; struct ice_alu *alu2; struct ice_pg_cam_action *action; - u8 pg_prio; struct ice_gpr_pu pu; u8 markers[ICE_MARKER_ID_SIZE]; bool protocols[ICE_PO_PAIR_SIZE]; diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c index dedf5e854e4b..3995d662e050 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser_rt.c +++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c @@ -125,22 +125,20 @@ static void ice_bst_key_init(struct ice_parser_rt *rt, else key[idd] = imem->b_kb.prio; - idd = ICE_BST_KEY_TCAM_SIZE - 1; + idd = ICE_BST_TCAM_KEY_SIZE - 2; for (i = idd; i >= 0; i--) { int j; j = ho + idd - i; if (j < ICE_PARSER_MAX_PKT_LEN) - key[i] = rt->pkt_buf[ho + idd - i]; + key[i] = rt->pkt_buf[j]; else key[i] = 0; } - ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n"); - ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n", - key[0], key[1], key[2], key[3], key[4], - key[5], key[6], key[7], key[8], key[9]); - ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n"); + ice_debug_array_w_prefix(rt->psr->hw, ICE_DBG_PARSER, + KBUILD_MODNAME ": Generated Boost TCAM Key", + key, ICE_BST_TCAM_KEY_SIZE); } static u16 ice_bit_rev_u16(u16 v, int len) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index a999fface272..e26320ce52ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -16,28 +16,28 @@ static const char ice_pin_names[][64] = { }; static const struct ice_ptp_pin_desc ice_pin_desc_e82x[] = { - /* name, gpio */ - { TIME_SYNC, { 4, -1 }}, - { ONE_PPS, { -1, 5 }}, + /* name, gpio, delay */ + { TIME_SYNC, { 4, -1 }, { 0, 0 }}, + { ONE_PPS, { -1, 5 }, { 0, 11 }}, }; static const struct ice_ptp_pin_desc ice_pin_desc_e825c[] = { - /* name, gpio */ - { SDP0, { 0, 0 }}, - { SDP1, { 1, 1 }}, - { SDP2, { 2, 2 }}, - { SDP3, { 3, 3 }}, - { TIME_SYNC, { 4, -1 }}, - { ONE_PPS, { -1, 5 }}, + /* name, gpio, delay */ + { SDP0, { 0, 0 }, { 15, 14 }}, + { SDP1, { 1, 1 }, { 15, 14 }}, + { SDP2, { 2, 2 }, { 15, 14 }}, + { SDP3, { 3, 3 }, { 15, 14 }}, + { TIME_SYNC, { 4, -1 }, { 11, 0 }}, + { ONE_PPS, { -1, 5 }, { 0, 9 }}, }; static const struct ice_ptp_pin_desc ice_pin_desc_e810[] = { - /* name, gpio */ - { SDP0, { 0, 0 }}, - { SDP1, { 1, 1 }}, - { SDP2, { 2, 2 }}, - { SDP3, { 3, 3 }}, - { ONE_PPS, { -1, 5 }}, + /* name, gpio, delay */ + { SDP0, { 0, 0 }, { 0, 1 }}, + { SDP1, { 1, 1 }, { 0, 1 }}, + { SDP2, { 2, 2 }, { 0, 1 }}, + { SDP3, { 3, 3 }, { 0, 1 }}, + { ONE_PPS, { -1, 5 }, { 0, 1 }}, }; static const char ice_pin_names_nvm[][64] = { @@ -49,12 +49,12 @@ static const char ice_pin_names_nvm[][64] = { }; static const struct ice_ptp_pin_desc ice_pin_desc_e810_sma[] = { - /* name, gpio */ - { GNSS, { 1, -1 }}, - { SMA1, { 1, 0 }}, - { UFL1, { -1, 0 }}, - { SMA2, { 3, 2 }}, - { UFL2, { 3, -1 }}, + /* name, gpio, delay */ + { GNSS, { 1, -1 }, { 0, 0 }}, + { SMA1, { 1, 0 }, { 0, 1 }}, + { UFL1, { -1, 0 }, { 0, 1 }}, + { SMA2, { 3, 2 }, { 0, 1 }}, + { UFL2, { 3, -1 }, { 0, 0 }}, }; static struct ice_pf *ice_get_ctrl_pf(struct ice_pf *pf) @@ -464,7 +464,9 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx) */ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) { + struct ice_e810_params *params; struct ice_ptp_port *ptp_port; + unsigned long flags; struct sk_buff *skb; struct ice_pf *pf; @@ -473,6 +475,7 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); + params = &pf->hw.ptp.phy.e810; /* Drop packets which have waited for more than 2 seconds */ if (time_is_before_jiffies(tx->tstamps[idx].start + 2 * HZ)) { @@ -489,11 +492,17 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx); + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + params->atqbal_flags |= ATQBAL_FLAGS_INTR_IN_PROGRESS; + /* Write TS index to read to the PF register so the FW can read it */ - wr32(&pf->hw, PF_SB_ATQBAL, - TS_LL_READ_TS_INTR | FIELD_PREP(TS_LL_READ_TS_IDX, idx) | - TS_LL_READ_TS); + wr32(&pf->hw, REG_LL_PROXY_H, + REG_LL_PROXY_H_TS_INTR_ENA | FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | + REG_LL_PROXY_H_EXEC); tx->last_ll_ts_idx_read = idx; + + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); } /** @@ -504,35 +513,52 @@ void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) { struct skb_shared_hwtstamps shhwtstamps = {}; u8 idx = tx->last_ll_ts_idx_read; + struct ice_e810_params *params; struct ice_ptp_port *ptp_port; u64 raw_tstamp, tstamp; bool drop_ts = false; struct sk_buff *skb; + unsigned long flags; + struct device *dev; struct ice_pf *pf; - u32 val; + u32 reg_ll_high; if (!tx->init || tx->last_ll_ts_idx_read < 0) return; ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); + dev = ice_pf_to_dev(pf); + params = &pf->hw.ptp.phy.e810; ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx); - val = rd32(&pf->hw, PF_SB_ATQBAL); + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + if (!(params->atqbal_flags & ATQBAL_FLAGS_INTR_IN_PROGRESS)) + dev_dbg(dev, "%s: low latency interrupt request not in progress?\n", + __func__); + + /* Read the low 32 bit value */ + raw_tstamp = rd32(&pf->hw, REG_LL_PROXY_L); + /* Read the status together with high TS part */ + reg_ll_high = rd32(&pf->hw, REG_LL_PROXY_H); + + /* Wake up threads waiting on low latency interface */ + params->atqbal_flags &= ~ATQBAL_FLAGS_INTR_IN_PROGRESS; + + wake_up_locked(¶ms->atqbal_wq); + + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); /* When the bit is cleared, the TS is ready in the register */ - if (val & TS_LL_READ_TS) { + if (reg_ll_high & REG_LL_PROXY_H_EXEC) { dev_err(ice_pf_to_dev(pf), "Failed to get the Tx tstamp - FW not ready"); return; } /* High 8 bit value of the TS is on the bits 16:23 */ - raw_tstamp = FIELD_GET(TS_LL_READ_TS_HIGH, val); - raw_tstamp <<= 32; - - /* Read the low 32 bit value */ - raw_tstamp |= (u64)rd32(&pf->hw, PF_SB_ATQBAH); + raw_tstamp |= ((u64)FIELD_GET(REG_LL_PROXY_H_TS_HIGH, reg_ll_high)) << 32; /* Devices using this interface always verify the timestamp differs * relative to the last cached timestamp value. @@ -1388,10 +1414,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) /** * ice_ptp_link_change - Reconfigure PTP after link status change * @pf: Board private structure - * @port: Port for which the PHY start is set * @linkup: Link is up or down */ -void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) +void ice_ptp_link_change(struct ice_pf *pf, bool linkup) { struct ice_ptp_port *ptp_port; struct ice_hw *hw = &pf->hw; @@ -1399,14 +1424,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) if (pf->ptp.state != ICE_PTP_READY) return; - if (WARN_ON_ONCE(port >= hw->ptp.num_lports)) - return; - ptp_port = &pf->ptp.port; - if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo) - port *= 2; - if (WARN_ON_ONCE(ptp_port->port_num != port)) - return; /* Update cached link status for this port immediately */ ptp_port->link_up = linkup; @@ -1566,18 +1584,29 @@ void ice_ptp_extts_event(struct ice_pf *pf) * Event is defined in GLTSYN_EVNT_0 register */ for (chan = 0; chan < GLTSYN_EVNT_H_IDX_MAX; chan++) { - /* Check if channel is enabled */ - if (pf->ptp.ext_ts_irq & (1 << chan)) { - lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx)); - hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx)); - event.timestamp = (((u64)hi) << 32) | lo; - event.type = PTP_CLOCK_EXTTS; - event.index = chan; + int pin_desc_idx; - /* Fire event */ - ptp_clock_event(pf->ptp.clock, &event); - pf->ptp.ext_ts_irq &= ~(1 << chan); + /* Check if channel is enabled */ + if (!(pf->ptp.ext_ts_irq & (1 << chan))) + continue; + + lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx)); + hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx)); + event.timestamp = (u64)hi << 32 | lo; + + /* Add delay compensation */ + pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_EXTTS, chan); + if (pin_desc_idx >= 0) { + const struct ice_ptp_pin_desc *desc; + + desc = &pf->ptp.ice_pin_desc[pin_desc_idx]; + event.timestamp -= desc->delay[0]; } + + event.type = PTP_CLOCK_EXTTS; + event.index = chan; + pf->ptp.ext_ts_irq &= ~(1 << chan); + ptp_clock_event(pf->ptp.clock, &event); } } @@ -1772,9 +1801,9 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, int on) { + unsigned int gpio_pin, prop_delay_ns; u64 clk, period, start, phase; struct ice_hw *hw = &pf->hw; - unsigned int gpio_pin; int pin_desc_idx; if (rq->flags & ~PTP_PEROUT_PHASE) @@ -1785,6 +1814,7 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, return -EIO; gpio_pin = pf->ptp.ice_pin_desc[pin_desc_idx].gpio[1]; + prop_delay_ns = pf->ptp.ice_pin_desc[pin_desc_idx].delay[1]; period = rq->period.sec * NSEC_PER_SEC + rq->period.nsec; /* If we're disabling the output or period is 0, clear out CLKO and TGT @@ -1816,11 +1846,11 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, * at the next multiple of period, maintaining phase. */ clk = ice_ptp_read_src_clk_reg(pf, NULL); - if (rq->flags & PTP_PEROUT_PHASE || start <= clk - ice_prop_delay(hw)) + if (rq->flags & PTP_PEROUT_PHASE || start <= clk - prop_delay_ns) start = div64_u64(clk + period - 1, period) * period + phase; /* Compensate for propagation delay from the generator to the pin. */ - start -= ice_prop_delay(hw); + start -= prop_delay_ns; return ice_ptp_write_perout(hw, rq->index, gpio_pin, start, period); } @@ -3080,7 +3110,7 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp) /* Allocate a kworker for handling work required for the ports * connected to the PTP hardware clock. */ - kworker = kthread_create_worker(0, "ice-ptp-%s", + kworker = kthread_run_worker(0, "ice-ptp-%s", dev_name(ice_pf_to_dev(pf))); if (IS_ERR(kworker)) return PTR_ERR(kworker); @@ -3164,10 +3194,17 @@ void ice_ptp_init(struct ice_pf *pf) { struct ice_ptp *ptp = &pf->ptp; struct ice_hw *hw = &pf->hw; - int err; + int lane_num, err; ptp->state = ICE_PTP_INITIALIZING; + lane_num = ice_get_phy_lane_number(hw); + if (lane_num < 0) { + err = lane_num; + goto err_exit; + } + + ptp->port.port_num = (u8)lane_num; ice_ptp_init_hw(hw); ice_ptp_init_tx_interrupt_mode(pf); @@ -3188,10 +3225,6 @@ void ice_ptp_init(struct ice_pf *pf) if (err) goto err_exit; - ptp->port.port_num = hw->pf_id; - if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo) - ptp->port.port_num = hw->pf_id * 2; - err = ice_ptp_init_port(pf, &ptp->port); if (err) goto err_exit; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 824e73b677a4..a1d0e988c084 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -211,6 +211,7 @@ enum ice_ptp_pin_nvm { * struct ice_ptp_pin_desc - hardware pin description data * @name_idx: index of the name of pin in ice_pin_names * @gpio: the associated GPIO input and output pins + * @delay: input and output signal delays in nanoseconds * * Structure describing a PTP-capable GPIO pin that extends ptp_pin_desc array * for the device. Device families have separate sets of available pins with @@ -219,6 +220,7 @@ enum ice_ptp_pin_nvm { struct ice_ptp_pin_desc { int name_idx; int gpio[2]; + unsigned int delay[2]; }; /** @@ -310,7 +312,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type); void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); -void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup); +void ice_ptp_link_change(struct ice_pf *pf, bool linkup); #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) { @@ -358,7 +360,7 @@ static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf, } static inline void ice_ptp_init(struct ice_pf *pf) { } static inline void ice_ptp_release(struct ice_pf *pf) { } -static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) +static inline void ice_ptp_link_change(struct ice_pf *pf, bool linkup) { } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h index 585ce200c60f..ac46d1183300 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h @@ -131,7 +131,7 @@ struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = { .rx_offset = { .serdes = 0xffffeb27, /* -10.42424 */ .no_fec = 0xffffcccd, /* -25.6 */ - .fc = 0xfffe0014, /* -255.96 */ + .fc = 0xfffc557b, /* -469.26 */ .sfd = 0x4a4, /* 2.32 */ .bs_ds = 0x32 /* 0.0969697 */ } @@ -341,8 +341,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 823437500, /* 823.4375 MHz PLL */ /* nominal_incval */ 0x136e44fabULL, - /* pps_delay */ - 11, }, /* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */ @@ -351,8 +349,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 783360000, /* 783.36 MHz */ /* nominal_incval */ 0x146cc2177ULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */ @@ -361,8 +357,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 796875000, /* 796.875 MHz */ /* nominal_incval */ 0x141414141ULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */ @@ -371,8 +365,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 816000000, /* 816 MHz */ /* nominal_incval */ 0x139b9b9baULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */ @@ -381,8 +373,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 830078125, /* 830.78125 MHz */ /* nominal_incval */ 0x134679aceULL, - /* pps_delay */ - 11, }, /* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */ @@ -391,8 +381,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 783360000, /* 783.36 MHz */ /* nominal_incval */ 0x146cc2177ULL, - /* pps_delay */ - 12, }, }; @@ -761,9 +749,9 @@ const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD] = { /* rx_desk_rsgb_par */ 644531250, /* 644.53125 MHz Reed Solomon gearbox */ /* tx_desk_rsgb_pcs */ - 644531250, /* 644.53125 MHz Reed Solomon gearbox */ + 390625000, /* 390.625 MHz Reed Solomon gearbox */ /* rx_desk_rsgb_pcs */ - 644531250, /* 644.53125 MHz Reed Solomon gearbox */ + 390625000, /* 390.625 MHz Reed Solomon gearbox */ /* tx_fixed_delay */ 1620, /* pmd_adj_divisor */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 518893f23372..ec91822e9280 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -391,7 +391,7 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw24.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -469,7 +469,7 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw24.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -546,7 +546,7 @@ static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw23.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), ro_lock.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -651,7 +651,7 @@ static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw23.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), ro_lock.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -900,31 +900,46 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) * The following functions operate on devices with the ETH 56G PHY. */ +/** + * ice_ptp_get_dest_dev_e825 - get destination PHY for given port number + * @hw: pointer to the HW struct + * @port: destination port + * + * Return: destination sideband queue PHY device. + */ +static enum ice_sbq_msg_dev ice_ptp_get_dest_dev_e825(struct ice_hw *hw, + u8 port) +{ + /* On a single complex E825, PHY 0 is always destination device phy_0 + * and PHY 1 is phy_0_peer. + */ + if (port >= hw->ptp.ports_per_phy) + return eth56g_phy_1; + else + return eth56g_phy_0; +} + /** * ice_write_phy_eth56g - Write a PHY port register * @hw: pointer to the HW struct - * @phy_idx: PHY index + * @port: destination port * @addr: PHY register address * @val: Value to write * * Return: 0 on success, other error codes when failed to write to PHY */ -static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr, - u32 val) +static int ice_write_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 val) { - struct ice_sbq_msg_input phy_msg; + struct ice_sbq_msg_input msg = { + .dest_dev = ice_ptp_get_dest_dev_e825(hw, port), + .opcode = ice_sbq_msg_wr, + .msg_addr_low = lower_16_bits(addr), + .msg_addr_high = upper_16_bits(addr), + .data = val + }; int err; - phy_msg.opcode = ice_sbq_msg_wr; - - phy_msg.msg_addr_low = lower_16_bits(addr); - phy_msg.msg_addr_high = upper_16_bits(addr); - - phy_msg.data = val; - phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx]; - - err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD); - + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); if (err) ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n", err); @@ -935,41 +950,36 @@ static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr, /** * ice_read_phy_eth56g - Read a PHY port register * @hw: pointer to the HW struct - * @phy_idx: PHY index + * @port: destination port * @addr: PHY register address * @val: Value to write * * Return: 0 on success, other error codes when failed to read from PHY */ -static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr, - u32 *val) +static int ice_read_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 *val) { - struct ice_sbq_msg_input phy_msg; + struct ice_sbq_msg_input msg = { + .dest_dev = ice_ptp_get_dest_dev_e825(hw, port), + .opcode = ice_sbq_msg_rd, + .msg_addr_low = lower_16_bits(addr), + .msg_addr_high = upper_16_bits(addr) + }; int err; - phy_msg.opcode = ice_sbq_msg_rd; - - phy_msg.msg_addr_low = lower_16_bits(addr); - phy_msg.msg_addr_high = upper_16_bits(addr); - - phy_msg.data = 0; - phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx]; - - err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD); - if (err) { + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); + if (err) ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n", err); - return err; - } + else + *val = msg.data; - *val = phy_msg.data; - - return 0; + return err; } /** * ice_phy_res_address_eth56g - Calculate a PHY port register address - * @port: Port number to be written + * @hw: pointer to the HW struct + * @lane: Lane number to be written * @res_type: resource type (register/memory) * @offset: Offset from PHY port register base * @addr: The result address @@ -978,17 +988,19 @@ static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr, * * %0 - success * * %EINVAL - invalid port number or resource type */ -static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type, - u32 offset, u32 *addr) +static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane, + enum eth56g_res_type res_type, + u32 offset, + u32 *addr) { - u8 lane = port % ICE_PORTS_PER_QUAD; - u8 phy = ICE_GET_QUAD_NUM(port); - if (res_type >= NUM_ETH56G_PHY_RES) return -EINVAL; - *addr = eth56g_phy_res[res_type].base[phy] + + /* Lanes 4..7 are in fact 0..3 on a second PHY */ + lane %= hw->ptp.ports_per_phy; + *addr = eth56g_phy_res[res_type].base[0] + lane * eth56g_phy_res[res_type].step + offset; + return 0; } @@ -1008,19 +1020,17 @@ static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type, static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset, u32 val, enum eth56g_res_type res_type) { - u8 phy_port = port % hw->ptp.ports_per_phy; - u8 phy_idx = port / hw->ptp.ports_per_phy; u32 addr; int err; if (port >= hw->ptp.num_lports) return -EINVAL; - err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr); + err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr); if (err) return err; - return ice_write_phy_eth56g(hw, phy_idx, addr, val); + return ice_write_phy_eth56g(hw, port, addr, val); } /** @@ -1039,19 +1049,17 @@ static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset, static int ice_read_port_eth56g(struct ice_hw *hw, u8 port, u32 offset, u32 *val, enum eth56g_res_type res_type) { - u8 phy_port = port % hw->ptp.ports_per_phy; - u8 phy_idx = port / hw->ptp.ports_per_phy; u32 addr; int err; if (port >= hw->ptp.num_lports) return -EINVAL; - err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr); + err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr); if (err) return err; - return ice_read_phy_eth56g(hw, phy_idx, addr, val); + return ice_read_phy_eth56g(hw, port, addr, val); } /** @@ -1200,6 +1208,56 @@ static int ice_write_port_mem_eth56g(struct ice_hw *hw, u8 port, u16 offset, return ice_write_port_eth56g(hw, port, offset, val, ETH56G_PHY_MEM_PTP); } +/** + * ice_write_quad_ptp_reg_eth56g - Write a PHY quad register + * @hw: pointer to the HW struct + * @offset: PHY register offset + * @port: Port number + * @val: Value to write + * + * Return: + * * %0 - success + * * %EIO - invalid port number or resource type + * * %other - failed to write to PHY + */ +static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, + u32 offset, u32 val) +{ + u32 addr; + + if (port >= hw->ptp.num_lports) + return -EIO; + + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + + return ice_write_phy_eth56g(hw, port, addr, val); +} + +/** + * ice_read_quad_ptp_reg_eth56g - Read a PHY quad register + * @hw: pointer to the HW struct + * @offset: PHY register offset + * @port: Port number + * @val: Value to read + * + * Return: + * * %0 - success + * * %EIO - invalid port number or resource type + * * %other - failed to read from PHY + */ +static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, + u32 offset, u32 *val) +{ + u32 addr; + + if (port >= hw->ptp.num_lports) + return -EIO; + + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + + return ice_read_phy_eth56g(hw, port, addr, val); +} + /** * ice_is_64b_phy_reg_eth56g - Check if this is a 64bit PHY register * @low_addr: the low address to check @@ -1919,7 +1977,6 @@ ice_phy_get_speed_eth56g(struct ice_link_status *li) */ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port) { - u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1); u32 val; int err; @@ -1934,8 +1991,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port) switch (ice_phy_get_speed_eth56g(&hw->port_info->phy.link_info)) { case ICE_ETH56G_LNK_SPD_1G: case ICE_ETH56G_LNK_SPD_2_5G: - err = ice_read_ptp_reg_eth56g(hw, port_blk, - PHY_GPCS_CONFIG_REG0, &val); + err = ice_read_quad_ptp_reg_eth56g(hw, port, + PHY_GPCS_CONFIG_REG0, &val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read PHY_GPCS_CONFIG_REG0, status: %d", err); @@ -1946,8 +2003,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port) val |= FIELD_PREP(PHY_GPCS_CONFIG_REG0_TX_THR_M, ICE_ETH56G_NOMINAL_TX_THRESH); - err = ice_write_ptp_reg_eth56g(hw, port_blk, - PHY_GPCS_CONFIG_REG0, val); + err = ice_write_quad_ptp_reg_eth56g(hw, port, + PHY_GPCS_CONFIG_REG0, val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_GPCS_CONFIG_REG0, status: %d", err); @@ -1988,50 +2045,47 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port) */ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port) { - u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1); - u8 blk_port = port & (ICE_PORTS_PER_QUAD - 1); + u8 quad_lane = port % ICE_PORTS_PER_QUAD; + u32 addr, val, peer_delay; bool enable, sfd_ena; - u32 val, peer_delay; int err; enable = hw->ptp.phy.eth56g.onestep_ena; peer_delay = hw->ptp.phy.eth56g.peer_delay; sfd_ena = hw->ptp.phy.eth56g.sfd_ena; - /* PHY_PTP_1STEP_CONFIG */ - err = ice_read_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, &val); + addr = PHY_PTP_1STEP_CONFIG; + err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &val); if (err) return err; if (enable) - val |= blk_port; + val |= BIT(quad_lane); else - val &= ~blk_port; + val &= ~BIT(quad_lane); val &= ~(PHY_PTP_1STEP_T1S_UP64_M | PHY_PTP_1STEP_T1S_DELTA_M); - err = ice_write_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, val); + err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val); if (err) return err; - /* PHY_PTP_1STEP_PEER_DELAY */ + addr = PHY_PTP_1STEP_PEER_DELAY(quad_lane); val = FIELD_PREP(PHY_PTP_1STEP_PD_DELAY_M, peer_delay); if (peer_delay) val |= PHY_PTP_1STEP_PD_ADD_PD_M; val |= PHY_PTP_1STEP_PD_DLY_V_M; - err = ice_write_ptp_reg_eth56g(hw, port_blk, - PHY_PTP_1STEP_PEER_DELAY(blk_port), val); + err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val); if (err) return err; val &= ~PHY_PTP_1STEP_PD_DLY_V_M; - err = ice_write_ptp_reg_eth56g(hw, port_blk, - PHY_PTP_1STEP_PEER_DELAY(blk_port), val); + err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val); if (err) return err; - /* PHY_MAC_XIF_MODE */ - err = ice_read_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, &val); + addr = PHY_MAC_XIF_MODE; + err = ice_read_mac_reg_eth56g(hw, port, addr, &val); if (err) return err; @@ -2051,7 +2105,7 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port) FIELD_PREP(PHY_MAC_XIF_TS_BIN_MODE_M, enable) | FIELD_PREP(PHY_MAC_XIF_TS_SFD_ENA_M, sfd_ena); - return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, val); + return ice_write_mac_reg_eth56g(hw, port, addr, val); } /** @@ -2093,21 +2147,22 @@ static u32 ice_ptp_calc_bitslip_eth56g(struct ice_hw *hw, u8 port, u32 bs, bool fc, bool rs, enum ice_eth56g_link_spd spd) { - u8 port_offset = port & (ICE_PORTS_PER_QUAD - 1); - u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1); u32 bitslip; int err; if (!bs || rs) return 0; - if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G) + if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G) { err = ice_read_gpcs_reg_eth56g(hw, port, PHY_GPCS_BITSLIP, &bitslip); - else - err = ice_read_ptp_reg_eth56g(hw, port_blk, - PHY_REG_SD_BIT_SLIP(port_offset), - &bitslip); + } else { + u8 quad_lane = port % ICE_PORTS_PER_QUAD; + u32 addr; + + addr = PHY_REG_SD_BIT_SLIP(quad_lane); + err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &bitslip); + } if (err) return 0; @@ -2667,59 +2722,29 @@ static int ice_get_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw, u8 port, } /** - * ice_is_muxed_topo - detect breakout 2x50G topology for E825C - * @hw: pointer to the HW struct - * - * Return: true if it's 2x50 breakout topology, false otherwise - */ -static bool ice_is_muxed_topo(struct ice_hw *hw) -{ - u8 link_topo; - bool mux; - u32 val; - - val = rd32(hw, GLGEN_SWITCH_MODE_CONFIG); - mux = FIELD_GET(GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M, val); - val = rd32(hw, GLGEN_MAC_LINK_TOPO); - link_topo = FIELD_GET(GLGEN_MAC_LINK_TOPO_LINK_TOPO_M, val); - - return (mux && link_topo == ICE_LINK_TOPO_UP_TO_2_LINKS); -} - -/** - * ice_ptp_init_phy_e825c - initialize PHY parameters + * ice_ptp_init_phy_e825 - initialize PHY parameters * @hw: pointer to the HW struct */ -static void ice_ptp_init_phy_e825c(struct ice_hw *hw) +static void ice_ptp_init_phy_e825(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; struct ice_eth56g_params *params; - u8 phy; + u32 phy_rev; + int err; ptp->phy_model = ICE_PHY_ETH56G; params = &ptp->phy.eth56g; params->onestep_ena = false; params->peer_delay = 0; params->sfd_ena = false; - params->phy_addr[0] = eth56g_phy_0; - params->phy_addr[1] = eth56g_phy_1; params->num_phys = 2; ptp->ports_per_phy = 4; ptp->num_lports = params->num_phys * ptp->ports_per_phy; ice_sb_access_ena_eth56g(hw, true); - for (phy = 0; phy < params->num_phys; phy++) { - u32 phy_rev; - int err; - - err = ice_read_phy_eth56g(hw, phy, PHY_REG_REVISION, &phy_rev); - if (err || phy_rev != PHY_REVISION_ETH56G) { - ptp->phy_model = ICE_PHY_UNSUP; - return; - } - } - - ptp->is_2x50g_muxed_topo = ice_is_muxed_topo(hw); + err = ice_read_phy_eth56g(hw, hw->pf_id, PHY_REG_REVISION, &phy_rev); + if (err || phy_rev != PHY_REVISION_ETH56G) + ptp->phy_model = ICE_PHY_UNSUP; } /* E822 family functions @@ -2738,10 +2763,9 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw, struct ice_sbq_msg_input *msg, u8 port, u16 offset) { - int phy_port, phy, quadtype; + int phy_port, quadtype; phy_port = port % hw->ptp.ports_per_phy; - phy = port / hw->ptp.ports_per_phy; quadtype = ICE_GET_QUAD_NUM(port) % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy); @@ -2753,12 +2777,7 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw, msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port); } - if (phy == 0) - msg->dest_dev = rmn_0; - else if (phy == 1) - msg->dest_dev = rmn_1; - else - msg->dest_dev = rmn_2; + msg->dest_dev = rmn_0; } /** @@ -4857,33 +4876,46 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val) static int ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) { + struct ice_e810_params *params = &hw->ptp.phy.e810; + unsigned long flags; u32 val; - u8 i; + int err; - /* Write TS index to read to the PF register so the FW can read it */ - val = FIELD_PREP(TS_LL_READ_TS_IDX, idx) | TS_LL_READ_TS; - wr32(hw, PF_SB_ATQBAL, val); + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); - /* Read the register repeatedly until the FW provides us the TS */ - for (i = TS_LL_READ_RETRIES; i > 0; i--) { - val = rd32(hw, PF_SB_ATQBAL); - - /* When the bit is cleared, the TS is ready in the register */ - if (!(FIELD_GET(TS_LL_READ_TS, val))) { - /* High 8 bit value of the TS is on the bits 16:23 */ - *hi = FIELD_GET(TS_LL_READ_TS_HIGH, val); - - /* Read the low 32 bit value and set the TS valid bit */ - *lo = rd32(hw, PF_SB_ATQBAH) | TS_VALID; - return 0; - } - - udelay(10); + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + return err; } - /* FW failed to provide the TS in time */ - ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); - return -EINVAL; + /* Write TS index to read to the PF register so the FW can read it */ + val = FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); + + /* Read the register repeatedly until the FW provides us the TS */ + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), 10, + REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + return err; + } + + /* High 8 bit value of the TS is on the bits 16:23 */ + *hi = FIELD_GET(REG_LL_PROXY_H_TS_HIGH, val); + + /* Read the low 32 bit value and set the TS valid bit */ + *lo = rd32(hw, REG_LL_PROXY_L) | TS_VALID; + + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + + return 0; } /** @@ -5065,6 +5097,55 @@ static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time) return 0; } +/** + * ice_ptp_prep_phy_adj_ll_e810 - Prep PHY ports for a time adjustment + * @hw: pointer to HW struct + * @adj: adjustment value to program + * + * Use the low latency firmware interface to program PHY time adjustment to + * all PHY ports. + * + * Return: 0 on success, -EBUSY on timeout + */ +static int ice_ptp_prep_phy_adj_ll_e810(struct ice_hw *hw, s32 adj) +{ + const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + struct ice_e810_params *params = &hw->ptp.phy.e810; + u32 val; + int err; + + spin_lock_irq(¶ms->atqbal_wq.lock); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + wr32(hw, REG_LL_PROXY_L, adj); + val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_ADJ) | + FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); + + /* Read the register repeatedly until the FW indicates completion */ + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), + 10, REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer adjustment using low latency interface\n"); + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + spin_unlock_irq(¶ms->atqbal_wq.lock); + + return 0; +} + /** * ice_ptp_prep_phy_adj_e810 - Prep PHY port for a time adjustment * @hw: pointer to HW struct @@ -5083,6 +5164,9 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) u8 tmr_idx; int err; + if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update) + return ice_ptp_prep_phy_adj_ll_e810(hw, adj); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Adjustments are represented as signed 2's complement values in @@ -5105,6 +5189,56 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) return 0; } +/** + * ice_ptp_prep_phy_incval_ll_e810 - Prep PHY ports increment value change + * @hw: pointer to HW struct + * @incval: The new 40bit increment value to prepare + * + * Use the low latency firmware interface to program PHY time increment value + * for all PHY ports. + * + * Return: 0 on success, -EBUSY on timeout + */ +static int ice_ptp_prep_phy_incval_ll_e810(struct ice_hw *hw, u64 incval) +{ + const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + struct ice_e810_params *params = &hw->ptp.phy.e810; + u32 val; + int err; + + spin_lock_irq(¶ms->atqbal_wq.lock); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + wr32(hw, REG_LL_PROXY_L, lower_32_bits(incval)); + val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_FREQ) | + FIELD_PREP(REG_LL_PROXY_H_TS_HIGH, (u8)upper_32_bits(incval)) | + FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); + + /* Read the register repeatedly until the FW indicates completion */ + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), + 10, REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer increment using low latency interface\n"); + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + spin_unlock_irq(¶ms->atqbal_wq.lock); + + return 0; +} + /** * ice_ptp_prep_phy_incval_e810 - Prep PHY port increment value change * @hw: pointer to HW struct @@ -5120,6 +5254,9 @@ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval) u8 tmr_idx; int err; + if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update) + return ice_ptp_prep_phy_incval_ll_e810(hw, incval); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; low = lower_32_bits(incval); high = upper_32_bits(incval); @@ -5404,6 +5541,8 @@ static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp) ptp->phy_model = ICE_PHY_E810; ptp->num_lports = 8; ptp->ports_per_phy = 4; + + init_waitqueue_head(&ptp->phy.e810.atqbal_wq); } /* Device agnostic functions @@ -5478,7 +5617,7 @@ void ice_ptp_init_hw(struct ice_hw *hw) else if (ice_is_e810(hw)) ice_ptp_init_phy_e810(ptp); else if (ice_is_e825c(hw)) - ice_ptp_init_phy_e825c(hw); + ice_ptp_init_phy_e825(hw); else ptp->phy_model = ICE_PHY_UNSUP; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 1cee0f1bba2d..6779ce120515 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -80,7 +80,6 @@ struct ice_phy_reg_info_eth56g { * struct ice_time_ref_info_e82x * @pll_freq: Frequency of PLL that drives timer ticks in Hz * @nominal_incval: increment to generate nanoseconds in GLTSYN_TIME_L - * @pps_delay: propagation delay of the PPS output signal * * Characteristic information for the various TIME_REF sources possible in the * E822 devices @@ -88,7 +87,6 @@ struct ice_phy_reg_info_eth56g { struct ice_time_ref_info_e82x { u64 pll_freq; u64 nominal_incval; - u8 pps_delay; }; /** @@ -326,8 +324,6 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD]; */ #define ICE_E810_PLL_FREQ 812500000 #define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL -#define ICE_E810_OUT_PROP_DELAY_NS 1 -#define ICE_E825C_OUT_PROP_DELAY_NS 11 /* Device agnostic functions */ u8 ice_get_ptp_src_clock_index(struct ice_hw *hw); @@ -389,11 +385,6 @@ static inline u64 ice_e82x_nominal_incval(enum ice_time_ref_freq time_ref) return e82x_time_ref[time_ref].nominal_incval; } -static inline u64 ice_e82x_pps_delay(enum ice_time_ref_freq time_ref) -{ - return e82x_time_ref[time_ref].pps_delay; -} - /* E822 Vernier calibration functions */ int ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset); int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port); @@ -432,20 +423,6 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port); #define ICE_ETH56G_NOMINAL_THRESH4 0x7777 #define ICE_ETH56G_NOMINAL_TX_THRESH 0x6 -static inline u64 ice_prop_delay(const struct ice_hw *hw) -{ - switch (hw->ptp.phy_model) { - case ICE_PHY_ETH56G: - return ICE_E825C_OUT_PROP_DELAY_NS; - case ICE_PHY_E810: - return ICE_E810_OUT_PROP_DELAY_NS; - case ICE_PHY_E82X: - return ice_e82x_pps_delay(ice_e82x_time_ref(hw)); - default: - return 0; - } -} - /** * ice_get_base_incval - Get base clock increment value * @hw: pointer to the HW struct @@ -689,11 +666,18 @@ static inline bool ice_is_dual(struct ice_hw *hw) #define BYTES_PER_IDX_ADDR_L 4 /* Tx timestamp low latency read definitions */ -#define TS_LL_READ_RETRIES 200 -#define TS_LL_READ_TS_HIGH GENMASK(23, 16) -#define TS_LL_READ_TS_IDX GENMASK(29, 24) -#define TS_LL_READ_TS_INTR BIT(30) -#define TS_LL_READ_TS BIT(31) +#define REG_LL_PROXY_H_TIMEOUT_US 2000 +#define REG_LL_PROXY_H_PHY_TMR_CMD_M GENMASK(7, 6) +#define REG_LL_PROXY_H_PHY_TMR_CMD_ADJ 0x1 +#define REG_LL_PROXY_H_PHY_TMR_CMD_FREQ 0x2 +#define REG_LL_PROXY_H_TS_HIGH GENMASK(23, 16) +#define REG_LL_PROXY_H_PHY_TMR_IDX_M BIT(24) +#define REG_LL_PROXY_H_TS_IDX GENMASK(29, 24) +#define REG_LL_PROXY_H_TS_INTR_ENA BIT(30) +#define REG_LL_PROXY_H_EXEC BIT(31) + +#define REG_LL_PROXY_L PF_SB_ATQBAH +#define REG_LL_PROXY_H PF_SB_ATQBAL /* Internal PHY timestamp address */ #define TS_L(a, idx) ((a) + ((idx) * BYTES_PER_IDX_ADDR_L_U)) diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index 970a99a52bf1..fb7a1b9a4313 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -4,7 +4,7 @@ #include "ice.h" #include "ice_eswitch.h" #include "devlink/devlink.h" -#include "devlink/devlink_port.h" +#include "devlink/port.h" #include "ice_sriov.h" #include "ice_tc_lib.h" #include "ice_dcb_lib.h" diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c index 75d7147e1c01..1a2c94375ca7 100644 --- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c +++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c @@ -5,8 +5,8 @@ #include "ice_txrx.h" #include "ice_fltr.h" #include "ice_sf_eth.h" -#include "devlink/devlink_port.h" #include "devlink/devlink.h" +#include "devlink/port.h" static const struct net_device_ops ice_sf_netdev_ops = { .ndo_open = ice_open, diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 0e740342e294..4a91e0aaf0a5 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -4784,7 +4784,8 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, */ if (found && recp[i].tun_type == rinfo->tun_type && recp[i].need_pass_l2 == rinfo->need_pass_l2 && - recp[i].allow_pass_l2 == rinfo->allow_pass_l2) + recp[i].allow_pass_l2 == rinfo->allow_pass_l2 && + recp[i].priority == rinfo->priority) return i; /* Return the recipe ID */ } } diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index adb168860711..33a1a5934c0d 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -18,6 +18,7 @@ #include "ice_sbq_cmd.h" #include "ice_vlan_mode.h" #include "ice_fwlog.h" +#include static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { @@ -368,6 +369,7 @@ struct ice_ts_func_info { #define ICE_TS_TMR1_ENA_M BIT(26) #define ICE_TS_LL_TX_TS_READ_M BIT(28) #define ICE_TS_LL_TX_TS_INT_READ_M BIT(29) +#define ICE_TS_LL_PHY_TMR_UPDATE_M BIT(30) struct ice_ts_dev_info { /* Device specific info */ @@ -382,6 +384,7 @@ struct ice_ts_dev_info { u8 tmr1_ena; u8 ts_ll_read; u8 ts_ll_int_read; + u8 ll_phy_tmr_update; }; #define ICE_NAC_TOPO_PRIMARY_M BIT(0) @@ -848,15 +851,23 @@ struct ice_mbx_data { #define ICE_PORTS_PER_QUAD 4 #define ICE_GET_QUAD_NUM(port) ((port) / ICE_PORTS_PER_QUAD) +#define ATQBAL_FLAGS_INTR_IN_PROGRESS BIT(0) + +struct ice_e810_params { + /* The wait queue lock also protects the low latency interface */ + wait_queue_head_t atqbal_wq; + unsigned int atqbal_flags; +}; + struct ice_eth56g_params { u8 num_phys; - u8 phy_addr[2]; bool onestep_ena; bool sfd_ena; u32 peer_delay; }; union ice_phy_params { + struct ice_e810_params e810; struct ice_eth56g_params eth56g; }; @@ -881,7 +892,6 @@ struct ice_ptp_hw { union ice_phy_params phy; u8 num_lports; u8 ports_per_phy; - bool is_2x50g_muxed_topo; }; /* Port hardware description */ @@ -1216,4 +1226,9 @@ struct ice_aq_get_set_rss_lut_params { #define ICE_FW_API_REPORT_DFLT_CFG_MIN 7 #define ICE_FW_API_REPORT_DFLT_CFG_PATCH 3 +/* AQ API version for Health Status support */ +#define ICE_FW_API_HEALTH_REPORT_MAJ 1 +#define ICE_FW_API_HEALTH_REPORT_MIN 7 +#define ICE_FW_API_HEALTH_REPORT_PATCH 6 + #endif /* _ICE_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 334ae945d640..8975d2971bc3 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -801,35 +801,6 @@ out_failure: return result; } -static int -ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, - struct xdp_buff *xdp, const unsigned int size) -{ - struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first); - - if (!size) - return 0; - - if (!xdp_buff_has_frags(first)) { - sinfo->nr_frags = 0; - sinfo->xdp_frags_size = 0; - xdp_buff_set_frags_flag(first); - } - - if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { - xsk_buff_free(first); - return -ENOMEM; - } - - __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, - virt_to_page(xdp->data_hard_start), - XDP_PACKET_HEADROOM, size); - sinfo->xdp_frags_size += size; - xsk_buff_add_frag(xdp); - - return 0; -} - /** * ice_clean_rx_irq_zc - consumes packets from the hardware ring * @rx_ring: AF_XDP Rx ring @@ -895,7 +866,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, if (!first) { first = xdp; - } else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) { + } else if (likely(size) && !xsk_buff_add_frag(first, xdp)) { + xsk_buff_free(first); break; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c index 4849590a5591..b28991dd1870 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c @@ -376,6 +376,9 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count, if (!(le16_to_cpu(desc->flags) & IDPF_CTLQ_FLAG_DD)) break; + /* Ensure no other fields are read until DD flag is checked */ + dma_rmb(); + /* strip off FW internal code */ desc_err = le16_to_cpu(desc->ret_val) & 0xff; @@ -563,6 +566,9 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, if (!(flags & IDPF_CTLQ_FLAG_DD)) break; + /* Ensure no other fields are read until DD flag is checked */ + dma_rmb(); + q_msg[i].vmvf_type = (flags & (IDPF_CTLQ_FLAG_FTYPE_VM | IDPF_CTLQ_FLAG_FTYPE_PF)) >> diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c index 6c913a703df6..41e4bd49402a 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c @@ -101,6 +101,9 @@ static int idpf_intr_reg_init(struct idpf_vport *vport) intr->dyn_ctl_itridx_s = PF_GLINT_DYN_CTL_ITR_INDX_S; intr->dyn_ctl_intrvl_s = PF_GLINT_DYN_CTL_INTERVAL_S; intr->dyn_ctl_wb_on_itr_m = PF_GLINT_DYN_CTL_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = PF_GLINT_DYN_CTL_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_PF_ITR_IDX_SPACING); diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index f71d3182580b..b6c515d14cbf 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -174,7 +174,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); pci_set_drvdata(pdev, adapter); - adapter->init_wq = alloc_workqueue("%s-%s-init", 0, 0, + adapter->init_wq = alloc_workqueue("%s-%s-init", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->init_wq) { @@ -183,7 +184,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_free; } - adapter->serv_wq = alloc_workqueue("%s-%s-service", 0, 0, + adapter->serv_wq = alloc_workqueue("%s-%s-service", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->serv_wq) { @@ -192,7 +194,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_serv_wq_alloc; } - adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", 0, 0, + adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->mbx_wq) { @@ -201,7 +204,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_mbx_wq_alloc; } - adapter->stats_wq = alloc_workqueue("%s-%s-stats", 0, 0, + adapter->stats_wq = alloc_workqueue("%s-%s-stats", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->stats_wq) { @@ -210,7 +214,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_stats_wq_alloc; } - adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", 0, 0, + adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->vc_event_wq) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 34f4118c7bc0..2fa9c36e33c9 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3604,21 +3604,31 @@ static void idpf_vport_intr_dis_irq_all(struct idpf_vport *vport) /** * idpf_vport_intr_buildreg_itr - Enable default interrupt generation settings * @q_vector: pointer to q_vector - * @type: itr index - * @itr: itr value */ -static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector, - const int type, u16 itr) +static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector) { - u32 itr_val; + u32 itr_val = q_vector->intr_reg.dyn_ctl_intena_m; + int type = IDPF_NO_ITR_UPDATE_IDX; + u16 itr = 0; + + if (q_vector->wb_on_itr) { + /* + * Trigger a software interrupt when exiting wb_on_itr, to make + * sure we catch any pending write backs that might have been + * missed due to interrupt state transition. + */ + itr_val |= q_vector->intr_reg.dyn_ctl_swint_trig_m | + q_vector->intr_reg.dyn_ctl_sw_itridx_ena_m; + type = IDPF_SW_ITR_UPDATE_IDX; + itr = IDPF_ITR_20K; + } itr &= IDPF_ITR_MASK; /* Don't clear PBA because that can cause lost interrupts that * came in while we were cleaning/polling */ - itr_val = q_vector->intr_reg.dyn_ctl_intena_m | - (type << q_vector->intr_reg.dyn_ctl_itridx_s) | - (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); + itr_val |= (type << q_vector->intr_reg.dyn_ctl_itridx_s) | + (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); return itr_val; } @@ -3716,9 +3726,8 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector) /* net_dim() updates ITR out-of-band using a work item */ idpf_net_dim(q_vector); + intval = idpf_vport_intr_buildreg_itr(q_vector); q_vector->wb_on_itr = false; - intval = idpf_vport_intr_buildreg_itr(q_vector, - IDPF_NO_ITR_UPDATE_IDX, 0); writel(intval, q_vector->intr_reg.dyn_ctl); } diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 9c1fe84108ed..0f71a6f5557b 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -354,6 +354,8 @@ struct idpf_vec_regs { * @dyn_ctl_itridx_m: Mask for ITR index * @dyn_ctl_intrvl_s: Register bit offset for ITR interval * @dyn_ctl_wb_on_itr_m: Mask for WB on ITR feature + * @dyn_ctl_sw_itridx_ena_m: Mask for SW ITR index + * @dyn_ctl_swint_trig_m: Mask for dyn_ctl SW triggered interrupt enable * @rx_itr: RX ITR register * @tx_itr: TX ITR register * @icr_ena: Interrupt cause register offset @@ -367,6 +369,8 @@ struct idpf_intr_reg { u32 dyn_ctl_itridx_m; u32 dyn_ctl_intrvl_s; u32 dyn_ctl_wb_on_itr_m; + u32 dyn_ctl_sw_itridx_ena_m; + u32 dyn_ctl_swint_trig_m; void __iomem *rx_itr; void __iomem *tx_itr; void __iomem *icr_ena; @@ -437,7 +441,7 @@ struct idpf_q_vector { cpumask_var_t affinity_mask; __cacheline_group_end_aligned(cold); }; -libeth_cacheline_set_assert(struct idpf_q_vector, 112, +libeth_cacheline_set_assert(struct idpf_q_vector, 120, 24 + sizeof(struct napi_struct) + 2 * sizeof(struct dim), 8 + sizeof(cpumask_var_t)); @@ -471,6 +475,8 @@ struct idpf_tx_queue_stats { #define IDPF_ITR_IS_DYNAMIC(itr_mode) (itr_mode) #define IDPF_ITR_TX_DEF IDPF_ITR_20K #define IDPF_ITR_RX_DEF IDPF_ITR_20K +/* Index used for 'SW ITR' update in DYN_CTL register */ +#define IDPF_SW_ITR_UPDATE_IDX 2 /* Index used for 'No ITR' update in DYN_CTL register */ #define IDPF_NO_ITR_UPDATE_IDX 3 #define IDPF_ITR_IDX_SPACING(spacing, dflt) (spacing ? spacing : dflt) diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c index aad62e270ae4..aba828abcb17 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c @@ -101,6 +101,9 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport) intr->dyn_ctl_itridx_s = VF_INT_DYN_CTLN_ITR_INDX_S; intr->dyn_ctl_intrvl_s = VF_INT_DYN_CTLN_INTERVAL_S; intr->dyn_ctl_wb_on_itr_m = VF_INT_DYN_CTLN_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = VF_INT_DYN_CTLN_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_VF_ITR_IDX_SPACING); diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index d46c95f91b0d..3d2413b8684f 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -517,8 +517,10 @@ static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter, retval = -ENXIO; goto only_unlock; case IDPF_VC_XN_WAITING: - dev_notice_ratelimited(&adapter->pdev->dev, "Transaction timed-out (op %d, %dms)\n", - params->vc_op, params->timeout_ms); + dev_notice_ratelimited(&adapter->pdev->dev, + "Transaction timed-out (op:%d cookie:%04x vc_op:%d salt:%02x timeout:%dms)\n", + params->vc_op, cookie, xn->vc_op, + xn->salt, params->timeout_ms); retval = -ETIME; break; case IDPF_VC_XN_COMPLETED_SUCCESS: @@ -612,14 +614,16 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter, return -EINVAL; } xn = &adapter->vcxn_mngr->ring[xn_idx]; + idpf_vc_xn_lock(xn); salt = FIELD_GET(IDPF_VC_XN_SALT_M, msg_info); if (xn->salt != salt) { - dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (%02x != %02x)\n", - xn->salt, salt); + dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (exp:%d@%02x(%d) != got:%d@%02x)\n", + xn->vc_op, xn->salt, xn->state, + ctlq_msg->cookie.mbx.chnl_opcode, salt); + idpf_vc_xn_unlock(xn); return -EINVAL; } - idpf_vc_xn_lock(xn); switch (xn->state) { case IDPF_VC_XN_WAITING: /* success */ @@ -3077,12 +3081,21 @@ init_failed: */ void idpf_vc_core_deinit(struct idpf_adapter *adapter) { + bool remove_in_prog; + if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags)) return; + /* Avoid transaction timeouts when called during reset */ + remove_in_prog = test_bit(IDPF_REMOVE_IN_PROG, adapter->flags); + if (!remove_in_prog) + idpf_vc_xn_shutdown(adapter->vcxn_mngr); + idpf_deinit_task(adapter); idpf_intr_rel(adapter); - idpf_vc_xn_shutdown(adapter->vcxn_mngr); + + if (remove_in_prog) + idpf_vc_xn_shutdown(adapter->vcxn_mngr); cancel_delayed_work_sync(&adapter->serv_task); cancel_delayed_work_sync(&adapter->mbx_task); diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile index 463c0d26b9d4..6c1b702fd992 100644 --- a/drivers/net/ethernet/intel/igb/Makefile +++ b/drivers/net/ethernet/intel/igb/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_IGB) += igb.o igb-y := igb_main.o igb_ethtool.o e1000_82575.o \ e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \ - e1000_i210.o igb_ptp.o igb_hwmon.o + e1000_i210.o igb_ptp.o igb_hwmon.o igb_xsk.o diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 3c2dc7bdebb5..02f340280d20 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -18,8 +18,10 @@ #include #include #include +#include #include +#include struct igb_adapter; @@ -86,6 +88,7 @@ struct igb_adapter; #define IGB_XDP_CONSUMED BIT(0) #define IGB_XDP_TX BIT(1) #define IGB_XDP_REDIR BIT(2) +#define IGB_XDP_EXIT BIT(3) struct vf_data_storage { unsigned char vf_mac_addresses[ETH_ALEN]; @@ -255,6 +258,7 @@ enum igb_tx_flags { enum igb_tx_buf_type { IGB_TYPE_SKB = 0, IGB_TYPE_XDP, + IGB_TYPE_XSK }; /* wrapper around a pointer to a socket buffer, @@ -320,6 +324,7 @@ struct igb_ring { union { /* array of buffer info structs */ struct igb_tx_buffer *tx_buffer_info; struct igb_rx_buffer *rx_buffer_info; + struct xdp_buff **rx_buffer_info_zc; }; void *desc; /* descriptor ring memory */ unsigned long flags; /* ring specific flags */ @@ -357,6 +362,7 @@ struct igb_ring { }; }; struct xdp_rxq_info xdp_rxq; + struct xsk_buff_pool *xsk_pool; } ____cacheline_internodealigned_in_smp; struct igb_q_vector { @@ -384,7 +390,8 @@ enum e1000_ring_flags_t { IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, IGB_RING_FLAG_TX_CTX_IDX, - IGB_RING_FLAG_TX_DETECT_HANG + IGB_RING_FLAG_TX_DETECT_HANG, + IGB_RING_FLAG_TX_DISABLED }; #define ring_uses_large_buffer(ring) \ @@ -731,12 +738,21 @@ int igb_setup_tx_resources(struct igb_ring *); int igb_setup_rx_resources(struct igb_ring *); void igb_free_tx_resources(struct igb_ring *); void igb_free_rx_resources(struct igb_ring *); +void igb_clean_tx_ring(struct igb_ring *tx_ring); +void igb_clean_rx_ring(struct igb_ring *rx_ring); void igb_configure_tx_ring(struct igb_adapter *, struct igb_ring *); void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *); +void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status); +void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets, + unsigned int bytes); void igb_setup_tctl(struct igb_adapter *); void igb_setup_rctl(struct igb_adapter *); void igb_setup_srrctl(struct igb_adapter *, struct igb_ring *); netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *); +int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp); +void igb_process_skb_fields(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb); void igb_alloc_rx_buffers(struct igb_ring *, u16); void igb_update_stats(struct igb_adapter *); bool igb_has_link(struct igb_adapter *adapter); @@ -797,6 +813,33 @@ static inline struct netdev_queue *txring_txq(const struct igb_ring *tx_ring) return netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index); } +/* This function assumes __netif_tx_lock is held by the caller. */ +static inline void igb_xdp_ring_update_tail(struct igb_ring *ring) +{ + lockdep_assert_held(&txring_txq(ring)->_xmit_lock); + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); +} + +static inline struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter) +{ + unsigned int r_idx = smp_processor_id(); + + if (r_idx >= adapter->num_tx_queues) + r_idx = r_idx % adapter->num_tx_queues; + + return adapter->tx_ring[r_idx]; +} + +static inline bool igb_xdp_is_enabled(struct igb_adapter *adapter) +{ + return !!READ_ONCE(adapter->xdp_prog); +} + int igb_add_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input); int igb_erase_filter(struct igb_adapter *adapter, @@ -807,4 +850,17 @@ int igb_add_mac_steering_filter(struct igb_adapter *adapter, int igb_del_mac_steering_filter(struct igb_adapter *adapter, const u8 *addr, u8 queue, u8 flags); +struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter, + struct igb_ring *ring); +int igb_xsk_pool_setup(struct igb_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid); +bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count); +void igb_clean_rx_ring_zc(struct igb_ring *rx_ring); +int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, + struct xsk_buff_pool *xsk_pool, const int budget); +bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool); +int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags); + #endif /* _IGB_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 288a4bb2683a..d368b753a467 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -33,7 +33,6 @@ #include #include #include -#include #ifdef CONFIG_IGB_DCA #include #endif @@ -116,8 +115,6 @@ static void igb_configure_tx(struct igb_adapter *); static void igb_configure_rx(struct igb_adapter *); static void igb_clean_all_tx_rings(struct igb_adapter *); static void igb_clean_all_rx_rings(struct igb_adapter *); -static void igb_clean_tx_ring(struct igb_ring *); -static void igb_clean_rx_ring(struct igb_ring *); static void igb_set_rx_mode(struct net_device *); static void igb_update_phy_info(struct timer_list *); static void igb_watchdog(struct timer_list *); @@ -475,12 +472,17 @@ rx_ring_summary: for (i = 0; i < rx_ring->count; i++) { const char *next_desc; - struct igb_rx_buffer *buffer_info; - buffer_info = &rx_ring->rx_buffer_info[i]; + dma_addr_t dma = (dma_addr_t)0; + struct igb_rx_buffer *buffer_info = NULL; rx_desc = IGB_RX_DESC(rx_ring, i); u0 = (struct my_u0 *)rx_desc; staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + if (!rx_ring->xsk_pool) { + buffer_info = &rx_ring->rx_buffer_info[i]; + dma = buffer_info->dma; + } + if (i == rx_ring->next_to_use) next_desc = " NTU"; else if (i == rx_ring->next_to_clean) @@ -500,11 +502,11 @@ rx_ring_summary: "R ", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - (u64)buffer_info->dma, + (u64)dma, next_desc); if (netif_msg_pktdata(adapter) && - buffer_info->dma && buffer_info->page) { + buffer_info && dma && buffer_info->page) { print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 1, @@ -1990,7 +1992,11 @@ static void igb_configure(struct igb_adapter *adapter) */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = adapter->rx_ring[i]; - igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); + if (ring->xsk_pool) + igb_alloc_rx_buffers_zc(ring, ring->xsk_pool, + igb_desc_unused(ring)); + else + igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); } } @@ -2911,37 +2917,20 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) { + struct igb_adapter *adapter = netdev_priv(dev); + switch (xdp->command) { case XDP_SETUP_PROG: return igb_xdp_setup(dev, xdp); + case XDP_SETUP_XSK_POOL: + return igb_xsk_pool_setup(adapter, xdp->xsk.pool, + xdp->xsk.queue_id); default: return -EINVAL; } } -/* This function assumes __netif_tx_lock is held by the caller. */ -static void igb_xdp_ring_update_tail(struct igb_ring *ring) -{ - lockdep_assert_held(&txring_txq(ring)->_xmit_lock); - - /* Force memory writes to complete before letting h/w know there - * are new descriptors to fetch. - */ - wmb(); - writel(ring->next_to_use, ring->tail); -} - -static struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter) -{ - unsigned int r_idx = smp_processor_id(); - - if (r_idx >= adapter->num_tx_queues) - r_idx = r_idx % adapter->num_tx_queues; - - return adapter->tx_ring[r_idx]; -} - -static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) +int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) { struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); int cpu = smp_processor_id(); @@ -2955,7 +2944,8 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) /* During program transitions its possible adapter->xdp_prog is assigned * but ring has not been configured yet. In this case simply abort xmit. */ - tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + tx_ring = igb_xdp_is_enabled(adapter) ? + igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) return IGB_XDP_CONSUMED; @@ -2988,10 +2978,14 @@ static int igb_xdp_xmit(struct net_device *dev, int n, /* During program transitions its possible adapter->xdp_prog is assigned * but ring has not been configured yet. In this case simply abort xmit. */ - tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + tx_ring = igb_xdp_is_enabled(adapter) ? + igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) return -ENXIO; + if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))) + return -ENXIO; + nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); @@ -3042,6 +3036,7 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_setup_tc = igb_setup_tc, .ndo_bpf = igb_xdp, .ndo_xdp_xmit = igb_xdp_xmit, + .ndo_xsk_wakeup = igb_xsk_wakeup, }; /** @@ -3338,7 +3333,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_SUPP_NOFCS; netdev->priv_flags |= IFF_UNICAST_FLT; - netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; @@ -4364,6 +4360,8 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, u64 tdba = ring->dma; int reg_idx = ring->reg_idx; + WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring)); + wr32(E1000_TDLEN(reg_idx), ring->count * sizeof(union e1000_adv_tx_desc)); wr32(E1000_TDBAL(reg_idx), @@ -4424,7 +4422,8 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index, 0); + rx_ring->queue_index, + rx_ring->q_vector->napi.napi_id); if (res < 0) { dev_err(dev, "Failed to register xdp_rxq index %u\n", rx_ring->queue_index); @@ -4720,12 +4719,17 @@ void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring) struct e1000_hw *hw = &adapter->hw; int reg_idx = ring->reg_idx; u32 srrctl = 0; + u32 buf_size; + + if (ring->xsk_pool) + buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool); + else if (ring_uses_large_buffer(ring)) + buf_size = IGB_RXBUFFER_3072; + else + buf_size = IGB_RXBUFFER_2048; srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; - if (ring_uses_large_buffer(ring)) - srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT; - else - srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + srrctl |= buf_size >> E1000_SRRCTL_BSIZEPKT_SHIFT; srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; @@ -4757,8 +4761,17 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, u32 rxdctl = 0; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL)); + WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring)); + if (ring->xsk_pool) { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, + NULL)); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + } else { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL)); + } /* disable the queue */ wr32(E1000_RXDCTL(reg_idx), 0); @@ -4785,9 +4798,12 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |= IGB_RX_HTHRESH << 8; rxdctl |= IGB_RX_WTHRESH << 16; - /* initialize rx_buffer_info */ - memset(ring->rx_buffer_info, 0, - sizeof(struct igb_rx_buffer) * ring->count); + if (ring->xsk_pool) + memset(ring->rx_buffer_info_zc, 0, + sizeof(*ring->rx_buffer_info_zc) * ring->count); + else + memset(ring->rx_buffer_info, 0, + sizeof(*ring->rx_buffer_info) * ring->count); /* initialize Rx descriptor 0 */ rx_desc = IGB_RX_DESC(ring, 0); @@ -4888,19 +4904,24 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) * igb_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned **/ -static void igb_clean_tx_ring(struct igb_ring *tx_ring) +void igb_clean_tx_ring(struct igb_ring *tx_ring) { u16 i = tx_ring->next_to_clean; struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + u32 xsk_frames = 0; while (i != tx_ring->next_to_use) { union e1000_adv_tx_desc *eop_desc, *tx_desc; /* Free all the Tx ring sk_buffs or xdp frames */ - if (tx_buffer->type == IGB_TYPE_SKB) + if (tx_buffer->type == IGB_TYPE_SKB) { dev_kfree_skb_any(tx_buffer->skb); - else + } else if (tx_buffer->type == IGB_TYPE_XDP) { xdp_return_frame(tx_buffer->xdpf); + } else if (tx_buffer->type == IGB_TYPE_XSK) { + xsk_frames++; + goto skip_for_xsk; + } /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -4931,6 +4952,7 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) DMA_TO_DEVICE); } +skip_for_xsk: tx_buffer->next_to_watch = NULL; /* move us one more past the eop_desc for start of next pkt */ @@ -4945,6 +4967,9 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) /* reset BQL for queue */ netdev_tx_reset_queue(txring_txq(tx_ring)); + if (tx_ring->xsk_pool && xsk_frames) + xsk_tx_completed(tx_ring->xsk_pool, xsk_frames); + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -4975,8 +5000,13 @@ void igb_free_rx_resources(struct igb_ring *rx_ring) rx_ring->xdp_prog = NULL; xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - vfree(rx_ring->rx_buffer_info); - rx_ring->rx_buffer_info = NULL; + if (rx_ring->xsk_pool) { + vfree(rx_ring->rx_buffer_info_zc); + rx_ring->rx_buffer_info_zc = NULL; + } else { + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + } /* if not set, then don't free */ if (!rx_ring->desc) @@ -5007,13 +5037,18 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) * igb_clean_rx_ring - Free Rx Buffers per Queue * @rx_ring: ring to free buffers from **/ -static void igb_clean_rx_ring(struct igb_ring *rx_ring) +void igb_clean_rx_ring(struct igb_ring *rx_ring) { u16 i = rx_ring->next_to_clean; dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; + if (rx_ring->xsk_pool) { + igb_clean_rx_ring_zc(rx_ring); + goto skip_for_xsk; + } + /* Free all the Rx ring sk_buffs */ while (i != rx_ring->next_to_alloc) { struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; @@ -5041,6 +5076,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) i = 0; } +skip_for_xsk: rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -6467,6 +6503,9 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))) + return NETDEV_TX_BUSY; + /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; first->type = IGB_TYPE_SKB; @@ -6622,7 +6661,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) struct igb_adapter *adapter = netdev_priv(netdev); int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD; - if (adapter->xdp_prog) { + if (igb_xdp_is_enabled(adapter)) { int i; for (i = 0; i < adapter->num_rx_queues; i++) { @@ -8195,6 +8234,7 @@ static int igb_poll(struct napi_struct *napi, int budget) struct igb_q_vector *q_vector = container_of(napi, struct igb_q_vector, napi); + struct xsk_buff_pool *xsk_pool; bool clean_complete = true; int work_done = 0; @@ -8206,7 +8246,12 @@ static int igb_poll(struct napi_struct *napi, int budget) clean_complete = igb_clean_tx_irq(q_vector, budget); if (q_vector->rx.ring) { - int cleaned = igb_clean_rx_irq(q_vector, budget); + int cleaned; + + xsk_pool = READ_ONCE(q_vector->rx.ring->xsk_pool); + cleaned = xsk_pool ? + igb_clean_rx_irq_zc(q_vector, xsk_pool, budget) : + igb_clean_rx_irq(q_vector, budget); work_done += cleaned; if (cleaned >= budget) @@ -8235,13 +8280,18 @@ static int igb_poll(struct napi_struct *napi, int budget) **/ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) { - struct igb_adapter *adapter = q_vector->adapter; - struct igb_ring *tx_ring = q_vector->tx.ring; - struct igb_tx_buffer *tx_buffer; - union e1000_adv_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; + struct igb_adapter *adapter = q_vector->adapter; unsigned int budget = q_vector->tx.work_limit; + struct igb_ring *tx_ring = q_vector->tx.ring; unsigned int i = tx_ring->next_to_clean; + union e1000_adv_tx_desc *tx_desc; + struct igb_tx_buffer *tx_buffer; + struct xsk_buff_pool *xsk_pool; + int cpu = smp_processor_id(); + bool xsk_xmit_done = true; + struct netdev_queue *nq; + u32 xsk_frames = 0; if (test_bit(__IGB_DOWN, &adapter->state)) return true; @@ -8272,10 +8322,14 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) total_packets += tx_buffer->gso_segs; /* free the skb */ - if (tx_buffer->type == IGB_TYPE_SKB) + if (tx_buffer->type == IGB_TYPE_SKB) { napi_consume_skb(tx_buffer->skb, napi_budget); - else + } else if (tx_buffer->type == IGB_TYPE_XDP) { xdp_return_frame(tx_buffer->xdpf); + } else if (tx_buffer->type == IGB_TYPE_XSK) { + xsk_frames++; + goto skip_for_xsk; + } /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -8307,6 +8361,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) } } +skip_for_xsk: /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; tx_desc++; @@ -8335,6 +8390,21 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) q_vector->tx.total_bytes += total_bytes; q_vector->tx.total_packets += total_packets; + xsk_pool = READ_ONCE(tx_ring->xsk_pool); + if (xsk_pool) { + if (xsk_frames) + xsk_tx_completed(xsk_pool, xsk_frames); + if (xsk_uses_need_wakeup(xsk_pool)) + xsk_set_tx_need_wakeup(xsk_pool); + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + xsk_xmit_done = igb_xmit_zc(tx_ring, xsk_pool); + __netif_tx_unlock(nq); + } + if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) { struct e1000_hw *hw = &adapter->hw; @@ -8397,7 +8467,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) } } - return !!budget; + return !!budget && xsk_xmit_done; } /** @@ -8588,9 +8658,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, return skb; } -static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, - struct igb_ring *rx_ring, - struct xdp_buff *xdp) +static int igb_run_xdp(struct igb_adapter *adapter, struct igb_ring *rx_ring, + struct xdp_buff *xdp) { int err, result = IGB_XDP_PASS; struct bpf_prog *xdp_prog; @@ -8630,7 +8699,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int igb_rx_frame_truesize(struct igb_ring *rx_ring, @@ -8756,10 +8825,6 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - if (unlikely((igb_test_staterr(rx_desc, E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) { struct net_device *netdev = rx_ring->netdev; @@ -8786,9 +8851,9 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, * order to populate the hash, checksum, VLAN, timestamp, protocol, and * other fields within the skb. **/ -static void igb_process_skb_fields(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) +void igb_process_skb_fields(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) { struct net_device *dev = rx_ring->netdev; @@ -8870,6 +8935,38 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring, rx_buffer->page = NULL; } +void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status) +{ + int cpu = smp_processor_id(); + struct netdev_queue *nq; + + if (status & IGB_XDP_REDIR) + xdp_do_flush(); + + if (status & IGB_XDP_TX) { + struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + igb_xdp_ring_update_tail(tx_ring); + __netif_tx_unlock(nq); + } +} + +void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets, + unsigned int bytes) +{ + struct igb_ring *ring = q_vector->rx.ring; + + u64_stats_update_begin(&ring->rx_syncp); + ring->rx_stats.packets += packets; + ring->rx_stats.bytes += bytes; + u64_stats_update_end(&ring->rx_syncp); + + q_vector->rx.total_packets += packets; + q_vector->rx.total_bytes += bytes; +} + static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { unsigned int total_bytes = 0, total_packets = 0; @@ -8877,12 +8974,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) struct igb_ring *rx_ring = q_vector->rx.ring; u16 cleaned_count = igb_desc_unused(rx_ring); struct sk_buff *skb = rx_ring->skb; - int cpu = smp_processor_id(); unsigned int xdp_xmit = 0; - struct netdev_queue *nq; struct xdp_buff xdp; u32 frame_sz = 0; int rx_buf_pgcnt; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -8940,12 +9036,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size); #endif - skb = igb_run_xdp(adapter, rx_ring, &xdp); + xdp_res = igb_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) { xdp_xmit |= xdp_res; igb_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -8964,7 +9058,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) &xdp, timestamp); /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_failed++; rx_buffer->pagecnt_bias++; break; @@ -8978,7 +9072,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) continue; /* verify the packet layout is correct */ - if (igb_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || igb_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } @@ -9001,24 +9095,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* place incomplete frames back on ring for completion */ rx_ring->skb = skb; - if (xdp_xmit & IGB_XDP_REDIR) - xdp_do_flush(); + if (xdp_xmit) + igb_finalize_xdp(adapter, xdp_xmit); - if (xdp_xmit & IGB_XDP_TX) { - struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); - - nq = txring_txq(tx_ring); - __netif_tx_lock(nq, cpu); - igb_xdp_ring_update_tail(tx_ring); - __netif_tx_unlock(nq); - } - - u64_stats_update_begin(&rx_ring->rx_syncp); - rx_ring->rx_stats.packets += total_packets; - rx_ring->rx_stats.bytes += total_bytes; - u64_stats_update_end(&rx_ring->rx_syncp); - q_vector->rx.total_packets += total_packets; - q_vector->rx.total_bytes += total_bytes; + igb_update_rx_stats(q_vector, total_packets, total_bytes); if (cleaned_count) igb_alloc_rx_buffers(rx_ring, cleaned_count); diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c new file mode 100644 index 000000000000..157d43787fa0 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -0,0 +1,562 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Intel Corporation. */ + +#include +#include +#include + +#include "e1000_hw.h" +#include "igb.h" + +static int igb_realloc_rx_buffer_info(struct igb_ring *ring, bool pool_present) +{ + int size = pool_present ? + sizeof(*ring->rx_buffer_info_zc) * ring->count : + sizeof(*ring->rx_buffer_info) * ring->count; + void *buff_info = vmalloc(size); + + if (!buff_info) + return -ENOMEM; + + if (pool_present) { + vfree(ring->rx_buffer_info); + ring->rx_buffer_info = NULL; + ring->rx_buffer_info_zc = buff_info; + } else { + vfree(ring->rx_buffer_info_zc); + ring->rx_buffer_info_zc = NULL; + ring->rx_buffer_info = buff_info; + } + + return 0; +} + +static void igb_txrx_ring_disable(struct igb_adapter *adapter, u16 qid) +{ + struct igb_ring *tx_ring = adapter->tx_ring[qid]; + struct igb_ring *rx_ring = adapter->rx_ring[qid]; + struct e1000_hw *hw = &adapter->hw; + + set_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags); + + wr32(E1000_TXDCTL(tx_ring->reg_idx), 0); + wr32(E1000_RXDCTL(rx_ring->reg_idx), 0); + + synchronize_net(); + + /* Rx/Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + + igb_clean_tx_ring(tx_ring); + igb_clean_rx_ring(rx_ring); + + memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats)); + memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats)); +} + +static void igb_txrx_ring_enable(struct igb_adapter *adapter, u16 qid) +{ + struct igb_ring *tx_ring = adapter->tx_ring[qid]; + struct igb_ring *rx_ring = adapter->rx_ring[qid]; + + igb_configure_tx_ring(adapter, tx_ring); + igb_configure_rx_ring(adapter, rx_ring); + + synchronize_net(); + + clear_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags); + + /* call igb_desc_unused which always leaves + * at least 1 descriptor unused to make sure + * next_to_use != next_to_clean + */ + if (rx_ring->xsk_pool) + igb_alloc_rx_buffers_zc(rx_ring, rx_ring->xsk_pool, + igb_desc_unused(rx_ring)); + else + igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring)); + + /* Rx/Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); +} + +struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter, + struct igb_ring *ring) +{ + int qid = ring->queue_index; + struct xsk_buff_pool *pool; + + pool = xsk_get_pool_from_qid(adapter->netdev, qid); + + if (!igb_xdp_is_enabled(adapter)) + return NULL; + + return (pool && pool->dev) ? pool : NULL; +} + +static int igb_xsk_pool_enable(struct igb_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid) +{ + struct net_device *netdev = adapter->netdev; + struct igb_ring *rx_ring; + bool if_running; + int err; + + if (qid >= adapter->num_rx_queues) + return -EINVAL; + + if (qid >= netdev->real_num_rx_queues || + qid >= netdev->real_num_tx_queues) + return -EINVAL; + + err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IGB_RX_DMA_ATTR); + if (err) + return err; + + rx_ring = adapter->rx_ring[qid]; + if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter); + if (if_running) + igb_txrx_ring_disable(adapter, qid); + + if (if_running) { + err = igb_realloc_rx_buffer_info(rx_ring, true); + if (!err) { + igb_txrx_ring_enable(adapter, qid); + /* Kick start the NAPI context so that receiving will start */ + err = igb_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX); + } + + if (err) { + xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR); + return err; + } + } + + return 0; +} + +static int igb_xsk_pool_disable(struct igb_adapter *adapter, u16 qid) +{ + struct xsk_buff_pool *pool; + struct igb_ring *rx_ring; + bool if_running; + int err; + + pool = xsk_get_pool_from_qid(adapter->netdev, qid); + if (!pool) + return -EINVAL; + + rx_ring = adapter->rx_ring[qid]; + if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter); + if (if_running) + igb_txrx_ring_disable(adapter, qid); + + xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR); + + if (if_running) { + err = igb_realloc_rx_buffer_info(rx_ring, false); + if (err) + return err; + + igb_txrx_ring_enable(adapter, qid); + } + + return 0; +} + +int igb_xsk_pool_setup(struct igb_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid) +{ + return pool ? igb_xsk_pool_enable(adapter, pool, qid) : + igb_xsk_pool_disable(adapter, qid); +} + +static u16 igb_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, + union e1000_adv_rx_desc *rx_desc, u16 count) +{ + dma_addr_t dma; + u16 buffs; + int i; + + /* nothing to do */ + if (!count) + return 0; + + buffs = xsk_buff_alloc_batch(pool, xdp, count); + for (i = 0; i < buffs; i++) { + dma = xsk_buff_xdp_get_dma(*xdp); + rx_desc->read.pkt_addr = cpu_to_le64(dma); + rx_desc->wb.upper.length = 0; + + rx_desc++; + xdp++; + } + + return buffs; +} + +bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count) +{ + u32 nb_buffs_extra = 0, nb_buffs = 0; + union e1000_adv_rx_desc *rx_desc; + u16 ntu = rx_ring->next_to_use; + u16 total_count = count; + struct xdp_buff **xdp; + + rx_desc = IGB_RX_DESC(rx_ring, ntu); + xdp = &rx_ring->rx_buffer_info_zc[ntu]; + + if (ntu + count >= rx_ring->count) { + nb_buffs_extra = igb_fill_rx_descs(xsk_pool, xdp, rx_desc, + rx_ring->count - ntu); + if (nb_buffs_extra != rx_ring->count - ntu) { + ntu += nb_buffs_extra; + goto exit; + } + rx_desc = IGB_RX_DESC(rx_ring, 0); + xdp = rx_ring->rx_buffer_info_zc; + ntu = 0; + count -= nb_buffs_extra; + } + + nb_buffs = igb_fill_rx_descs(xsk_pool, xdp, rx_desc, count); + ntu += nb_buffs; + if (ntu == rx_ring->count) + ntu = 0; + + /* clear the length for the next_to_use descriptor */ + rx_desc = IGB_RX_DESC(rx_ring, ntu); + rx_desc->wb.upper.length = 0; + +exit: + if (rx_ring->next_to_use != ntu) { + rx_ring->next_to_use = ntu; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(ntu, rx_ring->tail); + } + + return total_count == (nb_buffs + nb_buffs_extra); +} + +void igb_clean_rx_ring_zc(struct igb_ring *rx_ring) +{ + u16 ntc = rx_ring->next_to_clean; + u16 ntu = rx_ring->next_to_use; + + while (ntc != ntu) { + struct xdp_buff *xdp = rx_ring->rx_buffer_info_zc[ntc]; + + xsk_buff_free(xdp); + ntc++; + if (ntc >= rx_ring->count) + ntc = 0; + } +} + +static struct sk_buff *igb_construct_skb_zc(struct igb_ring *rx_ring, + struct xdp_buff *xdp, + ktime_t timestamp) +{ + unsigned int totalsize = xdp->data_end - xdp->data_meta; + unsigned int metasize = xdp->data - xdp->data_meta; + struct sk_buff *skb; + + net_prefetch(xdp->data_meta); + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize); + if (unlikely(!skb)) + return NULL; + + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; + + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { + skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } + + return skb; +} + +static int igb_run_xdp_zc(struct igb_adapter *adapter, struct igb_ring *rx_ring, + struct xdp_buff *xdp, struct xsk_buff_pool *xsk_pool, + struct bpf_prog *xdp_prog) +{ + int err, result = IGB_XDP_PASS; + u32 act; + + prefetchw(xdp->data_hard_start); /* xdp_frame write */ + + act = bpf_prog_run_xdp(xdp_prog, xdp); + + if (likely(act == XDP_REDIRECT)) { + err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); + if (!err) + return IGB_XDP_REDIR; + + if (xsk_uses_need_wakeup(xsk_pool) && + err == -ENOBUFS) + result = IGB_XDP_EXIT; + else + result = IGB_XDP_CONSUMED; + goto out_failure; + } + + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + result = igb_xdp_xmit_back(adapter, xdp); + if (result == IGB_XDP_CONSUMED) + goto out_failure; + break; + default: + bpf_warn_invalid_xdp_action(adapter->netdev, xdp_prog, act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + fallthrough; + case XDP_DROP: + result = IGB_XDP_CONSUMED; + break; + } + + return result; +} + +int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, + struct xsk_buff_pool *xsk_pool, const int budget) +{ + struct igb_adapter *adapter = q_vector->adapter; + unsigned int total_bytes = 0, total_packets = 0; + struct igb_ring *rx_ring = q_vector->rx.ring; + u32 ntc = rx_ring->next_to_clean; + struct bpf_prog *xdp_prog; + unsigned int xdp_xmit = 0; + bool failure = false; + u16 entries_to_alloc; + struct sk_buff *skb; + + /* xdp_prog cannot be NULL in the ZC path */ + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + + while (likely(total_packets < budget)) { + union e1000_adv_rx_desc *rx_desc; + ktime_t timestamp = 0; + struct xdp_buff *xdp; + unsigned int size; + int xdp_res = 0; + + rx_desc = IGB_RX_DESC(rx_ring, ntc); + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + xdp = rx_ring->rx_buffer_info_zc[ntc]; + xsk_buff_set_size(xdp, size); + xsk_buff_dma_sync_for_cpu(xdp); + + /* pull rx packet timestamp if available and valid */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + int ts_hdr_len; + + ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector, + xdp->data, + ×tamp); + + xdp->data += ts_hdr_len; + xdp->data_meta += ts_hdr_len; + size -= ts_hdr_len; + } + + xdp_res = igb_run_xdp_zc(adapter, rx_ring, xdp, xsk_pool, + xdp_prog); + + if (xdp_res) { + if (likely(xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR))) { + xdp_xmit |= xdp_res; + } else if (xdp_res == IGB_XDP_EXIT) { + failure = true; + break; + } else if (xdp_res == IGB_XDP_CONSUMED) { + xsk_buff_free(xdp); + } + + total_packets++; + total_bytes += size; + ntc++; + if (ntc == rx_ring->count) + ntc = 0; + continue; + } + + skb = igb_construct_skb_zc(rx_ring, xdp, timestamp); + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_failed++; + break; + } + + xsk_buff_free(xdp); + ntc++; + if (ntc == rx_ring->count) + ntc = 0; + + if (eth_skb_pad(skb)) + continue; + + /* probably a little skewed due to removing CRC */ + total_bytes += skb->len; + + /* populate checksum, timestamp, VLAN, and protocol */ + igb_process_skb_fields(rx_ring, rx_desc, skb); + + napi_gro_receive(&q_vector->napi, skb); + + /* update budget accounting */ + total_packets++; + } + + rx_ring->next_to_clean = ntc; + + if (xdp_xmit) + igb_finalize_xdp(adapter, xdp_xmit); + + igb_update_rx_stats(q_vector, total_packets, total_bytes); + + entries_to_alloc = igb_desc_unused(rx_ring); + if (entries_to_alloc >= IGB_RX_BUFFER_WRITE) + failure |= !igb_alloc_rx_buffers_zc(rx_ring, xsk_pool, + entries_to_alloc); + + if (xsk_uses_need_wakeup(xsk_pool)) { + if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(xsk_pool); + else + xsk_clear_rx_need_wakeup(xsk_pool); + + return (int)total_packets; + } + return failure ? budget : (int)total_packets; +} + +bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool) +{ + unsigned int budget = igb_desc_unused(tx_ring); + u32 cmd_type, olinfo_status, nb_pkts, i = 0; + struct xdp_desc *descs = xsk_pool->tx_descs; + union e1000_adv_tx_desc *tx_desc = NULL; + struct igb_tx_buffer *tx_buffer_info; + unsigned int total_bytes = 0; + dma_addr_t dma; + + if (!netif_carrier_ok(tx_ring->netdev)) + return true; + + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags)) + return true; + + nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget); + if (!nb_pkts) + return true; + + while (nb_pkts-- > 0) { + dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len); + + tx_buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + tx_buffer_info->bytecount = descs[i].len; + tx_buffer_info->type = IGB_TYPE_XSK; + tx_buffer_info->xdpf = NULL; + tx_buffer_info->gso_segs = 1; + tx_buffer_info->time_stamp = jiffies; + + tx_desc = IGB_TX_DESC(tx_ring, tx_ring->next_to_use); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + /* put descriptor type bits */ + cmd_type = E1000_ADVTXD_DTYP_DATA | E1000_ADVTXD_DCMD_DEXT | + E1000_ADVTXD_DCMD_IFCS; + olinfo_status = descs[i].len << E1000_ADVTXD_PAYLEN_SHIFT; + + /* FIXME: This sets the Report Status (RS) bit for every + * descriptor. One nice to have optimization would be to set it + * only for the last descriptor in the whole batch. See Intel + * ice driver for an example on how to do it. + */ + cmd_type |= descs[i].len | IGB_TXD_DCMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); + + total_bytes += descs[i].len; + + i++; + tx_ring->next_to_use++; + tx_buffer_info->next_to_watch = tx_desc; + if (tx_ring->next_to_use == tx_ring->count) + tx_ring->next_to_use = 0; + } + + netdev_tx_sent_queue(txring_txq(tx_ring), total_bytes); + igb_xdp_ring_update_tail(tx_ring); + + return nb_pkts < budget; +} + +int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) +{ + struct igb_adapter *adapter = netdev_priv(dev); + struct e1000_hw *hw = &adapter->hw; + struct igb_ring *ring; + u32 eics = 0; + + if (test_bit(__IGB_DOWN, &adapter->state)) + return -ENETDOWN; + + if (!igb_xdp_is_enabled(adapter)) + return -EINVAL; + + if (qid >= adapter->num_tx_queues) + return -EINVAL; + + ring = adapter->tx_ring[qid]; + + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) + return -ENETDOWN; + + if (!READ_ONCE(ring->xsk_pool)) + return -EINVAL; + + if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + /* Cause software interrupt */ + if (adapter->flags & IGB_FLAG_HAS_MSIX) { + eics |= ring->q_vector->eims_value; + wr32(E1000_EICS, eics); + } else { + wr32(E1000_ICS, E1000_ICS_RXDMT0); + } + } + + return 0; +} diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index eac0f966e0e4..b8111ad9a9a8 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -337,6 +337,8 @@ struct igc_adapter { struct igc_led_classdev *leds; }; +void igc_set_queue_napi(struct igc_adapter *adapter, int q_idx, + struct napi_struct *napi); void igc_up(struct igc_adapter *adapter); void igc_down(struct igc_adapter *adapter); int igc_open(struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index 9fae8bdec2a7..1613b562d17c 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -68,6 +68,10 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw) u32 eecd = rd32(IGC_EECD); u16 size; + /* failed to read reg and got all F's */ + if (!(~eecd)) + return -ENXIO; + size = FIELD_GET(IGC_EECD_SIZE_EX_MASK, eecd); /* Added to a constant, "size" becomes the left-shift value @@ -221,6 +225,8 @@ static s32 igc_get_invariants_base(struct igc_hw *hw) /* NVM initialization */ ret_val = igc_init_nvm_params_base(hw); + if (ret_val) + goto out; switch (hw->mac.type) { case igc_i225: ret_val = igc_init_nvm_params_i225(hw); diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index d9d1a1a11daf..be8a49a86d09 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -279,9 +279,4 @@ struct net_device *igc_get_hw_dev(struct igc_hw *hw); #define hw_dbg(format, arg...) \ netdev_dbg(igc_get_hw_dev(hw), format, ##arg) -s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value); -s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value); -void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value); -void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value); - #endif /* _IGC_HW_H_ */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 27872bdea9bd..56a35d58e7a6 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2123,10 +2123,6 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring, union igc_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) { struct net_device *netdev = rx_ring->netdev; @@ -2515,8 +2511,7 @@ out_failure: } } -static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, - struct xdp_buff *xdp) +static int igc_xdp_run_prog(struct igc_adapter *adapter, struct xdp_buff *xdp) { struct bpf_prog *prog; int res; @@ -2530,7 +2525,7 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, res = __igc_xdp_run_prog(adapter, prog, xdp); out: - return ERR_PTR(-res); + return res; } /* This function assumes __netif_tx_lock is held by the caller. */ @@ -2585,6 +2580,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = igc_desc_unused(rx_ring); int xdp_status = 0, rx_buffer_pgcnt; + int xdp_res = 0; while (likely(total_packets < budget)) { struct igc_xdp_buff ctx = { .rx_ts = NULL }; @@ -2630,12 +2626,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) xdp_buff_clear_frags_flag(&ctx.xdp); ctx.rx_desc = rx_desc; - skb = igc_xdp_run_prog(adapter, &ctx.xdp); + xdp_res = igc_xdp_run_prog(adapter, &ctx.xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { switch (xdp_res) { case IGC_XDP_CONSUMED: rx_buffer->pagecnt_bias++; @@ -2657,7 +2651,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) skb = igc_construct_skb(rx_ring, rx_buffer, &ctx); /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_failed++; rx_buffer->pagecnt_bias++; set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); @@ -2672,7 +2666,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) continue; /* verify the packet layout is correct */ - if (igc_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || igc_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } @@ -4948,6 +4942,22 @@ static int igc_sw_init(struct igc_adapter *adapter) return 0; } +void igc_set_queue_napi(struct igc_adapter *adapter, int vector, + struct napi_struct *napi) +{ + struct igc_q_vector *q_vector = adapter->q_vector[vector]; + + if (q_vector->rx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->rx.ring->queue_index, + NETDEV_QUEUE_TYPE_RX, napi); + + if (q_vector->tx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->tx.ring->queue_index, + NETDEV_QUEUE_TYPE_TX, napi); +} + /** * igc_up - Open the interface and prepare it to handle traffic * @adapter: board private structure @@ -4955,6 +4965,7 @@ static int igc_sw_init(struct igc_adapter *adapter) void igc_up(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int i = 0; /* hardware has been reset, we need to reload some things */ @@ -4962,8 +4973,11 @@ void igc_up(struct igc_adapter *adapter) clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } if (adapter->msix_entries) igc_configure_msix(adapter); @@ -5192,6 +5206,7 @@ void igc_down(struct igc_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) { if (adapter->q_vector[i]) { napi_synchronize(&adapter->q_vector[i]->napi); + igc_set_queue_napi(adapter, i, NULL); napi_disable(&adapter->q_vector[i]->napi); } } @@ -5576,6 +5591,9 @@ static int igc_request_msix(struct igc_adapter *adapter) q_vector); if (err) goto err_free; + + netif_napi_set_irq(&q_vector->napi, + adapter->msix_entries[vector].vector); } igc_configure_msix(adapter); @@ -6018,6 +6036,7 @@ static int __igc_open(struct net_device *netdev, bool resuming) struct igc_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = adapter->pdev; struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int err = 0; int i = 0; @@ -6053,8 +6072,11 @@ static int __igc_open(struct net_device *netdev, bool resuming) clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } /* Clear any pending interrupts. */ rd32(IGC_ICR); @@ -6779,45 +6801,6 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_get_tstamp = igc_get_tstamp, }; -/* PCIe configuration access */ -void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - pci_read_config_word(adapter->pdev, reg, value); -} - -void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - pci_write_config_word(adapter->pdev, reg, *value); -} - -s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - if (!pci_is_pcie(adapter->pdev)) - return -IGC_ERR_CONFIG; - - pcie_capability_read_word(adapter->pdev, reg, value); - - return IGC_SUCCESS; -} - -s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - if (!pci_is_pcie(adapter->pdev)) - return -IGC_ERR_CONFIG; - - pcie_capability_write_word(adapter->pdev, reg, *value); - - return IGC_SUCCESS; -} - u32 igc_rd32(struct igc_hw *hw, u32 reg) { struct igc_adapter *igc = container_of(hw, struct igc_adapter, hw); @@ -7338,7 +7321,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev) netif_rx(skb); } -static int igc_resume(struct device *dev) +static int __igc_resume(struct device *dev, bool rpm) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7381,7 +7364,11 @@ static int igc_resume(struct device *dev) wr32(IGC_WUS, ~0); if (netif_running(netdev)) { + if (!rpm) + rtnl_lock(); err = __igc_open(netdev, true); + if (!rpm) + rtnl_unlock(); if (!err) netif_device_attach(netdev); } @@ -7389,9 +7376,14 @@ static int igc_resume(struct device *dev) return err; } +static int igc_resume(struct device *dev) +{ + return __igc_resume(dev, false); +} + static int igc_runtime_resume(struct device *dev) { - return igc_resume(dev); + return __igc_resume(dev, true); } static int igc_suspend(struct device *dev) @@ -7436,14 +7428,18 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct igc_adapter *adapter = netdev_priv(netdev); + rtnl_lock(); netif_device_detach(netdev); - if (state == pci_channel_io_perm_failure) + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; + } if (netif_running(netdev)) igc_down(adapter); pci_disable_device(pdev); + rtnl_unlock(); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -7454,7 +7450,7 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, * @pdev: Pointer to PCI device * * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the igc_resume routine. + * resembles the first-half of the __igc_resume routine. **/ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) { @@ -7493,7 +7489,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) * * This callback is called when the error recovery driver tells us that * its OK to resume normal operation. Implementation resembles the - * second-half of the igc_resume routine. + * second-half of the __igc_resume routine. */ static void igc_io_resume(struct pci_dev *pdev) { diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.c b/drivers/net/ethernet/intel/igc/igc_nvm.c index 58f81aba0144..efd121c03967 100644 --- a/drivers/net/ethernet/intel/igc/igc_nvm.c +++ b/drivers/net/ethernet/intel/igc/igc_nvm.c @@ -35,56 +35,6 @@ static s32 igc_poll_eerd_eewr_done(struct igc_hw *hw, int ee_reg) return ret_val; } -/** - * igc_acquire_nvm - Generic request for access to EEPROM - * @hw: pointer to the HW structure - * - * Set the EEPROM access request bit and wait for EEPROM access grant bit. - * Return successful if access grant bit set, else clear the request for - * EEPROM access and return -IGC_ERR_NVM (-1). - */ -s32 igc_acquire_nvm(struct igc_hw *hw) -{ - s32 timeout = IGC_NVM_GRANT_ATTEMPTS; - u32 eecd = rd32(IGC_EECD); - s32 ret_val = 0; - - wr32(IGC_EECD, eecd | IGC_EECD_REQ); - eecd = rd32(IGC_EECD); - - while (timeout) { - if (eecd & IGC_EECD_GNT) - break; - udelay(5); - eecd = rd32(IGC_EECD); - timeout--; - } - - if (!timeout) { - eecd &= ~IGC_EECD_REQ; - wr32(IGC_EECD, eecd); - hw_dbg("Could not acquire NVM grant\n"); - ret_val = -IGC_ERR_NVM; - } - - return ret_val; -} - -/** - * igc_release_nvm - Release exclusive access to EEPROM - * @hw: pointer to the HW structure - * - * Stop any current commands to the EEPROM and clear the EEPROM request bit. - */ -void igc_release_nvm(struct igc_hw *hw) -{ - u32 eecd; - - eecd = rd32(IGC_EECD); - eecd &= ~IGC_EECD_REQ; - wr32(IGC_EECD, eecd); -} - /** * igc_read_nvm_eerd - Reads EEPROM using EERD register * @hw: pointer to the HW structure diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.h b/drivers/net/ethernet/intel/igc/igc_nvm.h index f9fc2e9cfb03..ab78d0c64547 100644 --- a/drivers/net/ethernet/intel/igc/igc_nvm.h +++ b/drivers/net/ethernet/intel/igc/igc_nvm.h @@ -4,8 +4,6 @@ #ifndef _IGC_NVM_H_ #define _IGC_NVM_H_ -s32 igc_acquire_nvm(struct igc_hw *hw); -void igc_release_nvm(struct igc_hw *hw); s32 igc_read_mac_addr(struct igc_hw *hw); s32 igc_read_nvm_eerd(struct igc_hw *hw, u16 offset, u16 words, u16 *data); s32 igc_validate_nvm_checksum(struct igc_hw *hw); diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index e27af72aada8..13bbd3346e01 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -13,6 +13,7 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, struct net_device *dev = adapter->netdev; bool if_running = netif_running(dev); struct bpf_prog *old_prog; + bool need_update; if (dev->mtu > ETH_DATA_LEN) { /* For now, the driver doesn't support XDP functionality with @@ -22,7 +23,8 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, return -EOPNOTSUPP; } - if (if_running) + need_update = !!adapter->xdp_prog != !!prog; + if (if_running && need_update) igc_close(dev); old_prog = xchg(&adapter->xdp_prog, prog); @@ -34,7 +36,7 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, else xdp_features_clear_redirect_target(dev); - if (if_running) + if (if_running && need_update) igc_open(dev); return 0; @@ -84,6 +86,7 @@ static int igc_xdp_enable_pool(struct igc_adapter *adapter, napi_disable(napi); } + igc_set_queue_napi(adapter, queue_id, NULL); set_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); set_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); @@ -133,6 +136,7 @@ static int igc_xdp_disable_pool(struct igc_adapter *adapter, u16 queue_id) xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR); clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); + igc_set_queue_napi(adapter, queue_id, napi); if (needs_reset) { napi_enable(napi); diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index 965e5ce1b326..b456d102655a 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright(c) 1999 - 2018 Intel Corporation. +# Copyright(c) 1999 - 2024 Intel Corporation. # # Makefile for the Intel(R) 10GbE PCI Express ethernet driver # @@ -9,7 +9,7 @@ obj-$(CONFIG_IXGBE) += ixgbe.o ixgbe-y := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \ - ixgbe_xsk.o + ixgbe_xsk.o ixgbe_e610.o ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ ixgbe_dcb_82599.o ixgbe_dcb_nl.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 559b443c409f..e6a380d4929b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef _IXGBE_H_ #define _IXGBE_H_ @@ -20,6 +20,7 @@ #include "ixgbe_type.h" #include "ixgbe_common.h" #include "ixgbe_dcb.h" +#include "ixgbe_e610.h" #if IS_ENABLED(CONFIG_FCOE) #define IXGBE_FCOE #include "ixgbe_fcoe.h" @@ -173,6 +174,7 @@ enum ixgbe_tx_flags { #define VMDQ_P(p) ((p) + adapter->ring_feature[RING_F_VMDQ].offset) #define IXGBE_82599_VF_DEVICE_ID 0x10ED #define IXGBE_X540_VF_DEVICE_ID 0x1515 +#define IXGBE_E610_VF_DEVICE_ID 0x57AD #define UPDATE_VF_COUNTER_32bit(reg, last_counter, counter) \ { \ @@ -654,6 +656,7 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP BIT(9) #define IXGBE_FLAG2_PTP_PPS_ENABLED BIT(10) #define IXGBE_FLAG2_PHY_INTERRUPT BIT(11) +#define IXGBE_FLAG2_FW_ASYNC_EVENT BIT(12) #define IXGBE_FLAG2_VLAN_PROMISC BIT(13) #define IXGBE_FLAG2_EEE_CAPABLE BIT(14) #define IXGBE_FLAG2_EEE_ENABLED BIT(15) @@ -661,6 +664,9 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_IPSEC_ENABLED BIT(17) #define IXGBE_FLAG2_VF_IPSEC_ENABLED BIT(18) #define IXGBE_FLAG2_AUTO_DISABLE_VF BIT(19) +#define IXGBE_FLAG2_PHY_FW_LOAD_FAILED BIT(20) +#define IXGBE_FLAG2_NO_MEDIA BIT(21) +#define IXGBE_FLAG2_MOD_POWER_UNSUPPORTED BIT(22) /* Tx fast path data */ int num_tx_queues; @@ -793,6 +799,7 @@ struct ixgbe_adapter { u32 vferr_refcount; struct ixgbe_mac_addr *mac_table; struct kobject *info_kobj; + u16 lse_mask; #ifdef CONFIG_IXGBE_HWMON struct hwmon_buff *ixgbe_hwmon_buff; #endif /* CONFIG_IXGBE_HWMON */ @@ -849,6 +856,7 @@ static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: return IXGBE_MAX_RSS_INDICES_X550; default: return 0; @@ -874,6 +882,7 @@ enum ixgbe_state_t { __IXGBE_PTP_RUNNING, __IXGBE_PTP_TX_IN_PROGRESS, __IXGBE_RESET_REQUESTED, + __IXGBE_PHY_INIT_COMPLETE, }; struct ixgbe_cb { @@ -896,6 +905,7 @@ enum ixgbe_boards { board_x550em_x_fw, board_x550em_a, board_x550em_a_fw, + board_e610, }; extern const struct ixgbe_info ixgbe_82598_info; @@ -906,6 +916,7 @@ extern const struct ixgbe_info ixgbe_X550EM_x_info; extern const struct ixgbe_info ixgbe_x550em_x_fw_info; extern const struct ixgbe_info ixgbe_x550em_a_info; extern const struct ixgbe_info ixgbe_x550em_a_fw_info; +extern const struct ixgbe_info ixgbe_e610_info; #ifdef CONFIG_IXGBE_DCB extern const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops; #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index cdaf087b4e85..964988b4d58b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include #include @@ -1615,6 +1615,7 @@ int ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(hw, IXGBE_FDIRSCTPM, ~fdirtcpm); break; default: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 3be1bfb16498..7beaf6ea57f9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include #include @@ -58,6 +58,7 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) switch (hw->device_id) { case IXGBE_DEV_ID_X550EM_A_SFP: case IXGBE_DEV_ID_X550EM_A_SFP_N: + case IXGBE_DEV_ID_E610_SFP: supported = false; break; default: @@ -88,6 +89,8 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) case IXGBE_DEV_ID_X550EM_A_10G_T: case IXGBE_DEV_ID_X550EM_A_1G_T: case IXGBE_DEV_ID_X550EM_A_1G_T_L: + case IXGBE_DEV_ID_E610_10G_T: + case IXGBE_DEV_ID_E610_2_5G_T: supported = true; break; default: @@ -469,9 +472,14 @@ int ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw) } } - if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) { + if (hw->mac.type == ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_X540 || + hw->mac.type == ixgbe_mac_e610) { if (hw->phy.id == 0) hw->phy.ops.identify(hw); + } + + if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) { hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECL, MDIO_MMD_PCS, &i); hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECH, MDIO_MMD_PCS, &i); hw->phy.ops.read_reg(hw, IXGBE_LDPCECL, MDIO_MMD_PCS, &i); @@ -660,7 +668,11 @@ int ixgbe_get_bus_info_generic(struct ixgbe_hw *hw) hw->bus.type = ixgbe_bus_type_pci_express; /* Get the negotiated link width and speed from PCI config space */ - link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS); + if (hw->mac.type == ixgbe_mac_e610) + link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS_E610); + else + link_status = ixgbe_read_pci_cfg_word(hw, + IXGBE_PCI_LINK_STATUS); hw->bus.width = ixgbe_convert_bus_width(link_status); hw->bus.speed = ixgbe_convert_bus_speed(link_status); @@ -2918,6 +2930,10 @@ u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw) pcie_offset = IXGBE_PCIE_MSIX_82599_CAPS; max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599; break; + case ixgbe_mac_e610: + pcie_offset = IXGBE_PCIE_MSIX_E610_CAPS; + max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599; + break; default: return 1; } @@ -3366,7 +3382,8 @@ int ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, *speed = IXGBE_LINK_SPEED_1GB_FULL; break; case IXGBE_LINKS_SPEED_100_82599: - if ((hw->mac.type >= ixgbe_mac_X550) && + if ((hw->mac.type >= ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_e610) && (links_reg & IXGBE_LINKS_SPEED_NON_STD)) *speed = IXGBE_LINK_SPEED_5GB_FULL; else diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c index f2709b10c2e5..19d6b6fa8fb3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include "ixgbe.h" #include @@ -154,6 +154,7 @@ static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev, case ixgbe_mac_82599EB: case ixgbe_mac_X540: case ixgbe_mac_X550: + case ixgbe_mac_e610: for (j = 0; j < netdev->addr_len; j++, i++) perm_addr[i] = adapter->hw.mac.san_addr[j]; break; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c new file mode 100644 index 000000000000..683c668672d6 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c @@ -0,0 +1,2658 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2024 Intel Corporation. */ + +#include "ixgbe_common.h" +#include "ixgbe_e610.h" +#include "ixgbe_x550.h" +#include "ixgbe_type.h" +#include "ixgbe_x540.h" +#include "ixgbe_mbx.h" +#include "ixgbe_phy.h" + +/** + * ixgbe_should_retry_aci_send_cmd_execute - decide if ACI command should + * be resent + * @opcode: ACI opcode + * + * Check if ACI command should be sent again depending on the provided opcode. + * It may happen when CSR is busy during link state changes. + * + * Return: true if the sending command routine should be repeated, + * otherwise false. + */ +static bool ixgbe_should_retry_aci_send_cmd_execute(u16 opcode) +{ + switch (opcode) { + case ixgbe_aci_opc_disable_rxen: + case ixgbe_aci_opc_get_phy_caps: + case ixgbe_aci_opc_get_link_status: + case ixgbe_aci_opc_get_link_topo: + return true; + } + + return false; +} + +/** + * ixgbe_aci_send_cmd_execute - execute sending FW Admin Command to FW Admin + * Command Interface + * @hw: pointer to the HW struct + * @desc: descriptor describing the command + * @buf: buffer to use for indirect commands (NULL for direct commands) + * @buf_size: size of buffer for indirect commands (0 for direct commands) + * + * Admin Command is sent using CSR by setting descriptor and buffer in specific + * registers. + * + * Return: the exit code of the operation. + * * - 0 - success. + * * - -EIO - CSR mechanism is not enabled. + * * - -EBUSY - CSR mechanism is busy. + * * - -EINVAL - buf_size is too big or + * invalid argument buf or buf_size. + * * - -ETIME - Admin Command X command timeout. + * * - -EIO - Admin Command X invalid state of HICR register or + * Admin Command failed because of bad opcode was returned or + * Admin Command failed with error Y. + */ +static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw, + struct ixgbe_aci_desc *desc, + void *buf, u16 buf_size) +{ + u16 opcode, buf_tail_size = buf_size % 4; + u32 *raw_desc = (u32 *)desc; + u32 hicr, i, buf_tail = 0; + bool valid_buf = false; + + hw->aci.last_status = IXGBE_ACI_RC_OK; + + /* It's necessary to check if mechanism is enabled */ + hicr = IXGBE_READ_REG(hw, IXGBE_PF_HICR); + + if (!(hicr & IXGBE_PF_HICR_EN)) + return -EIO; + + if (hicr & IXGBE_PF_HICR_C) { + hw->aci.last_status = IXGBE_ACI_RC_EBUSY; + return -EBUSY; + } + + opcode = le16_to_cpu(desc->opcode); + + if (buf_size > IXGBE_ACI_MAX_BUFFER_SIZE) + return -EINVAL; + + if (buf) + desc->flags |= cpu_to_le16(IXGBE_ACI_FLAG_BUF); + + if (desc->flags & cpu_to_le16(IXGBE_ACI_FLAG_BUF)) { + if ((buf && !buf_size) || + (!buf && buf_size)) + return -EINVAL; + if (buf && buf_size) + valid_buf = true; + } + + if (valid_buf) { + if (buf_tail_size) + memcpy(&buf_tail, buf + buf_size - buf_tail_size, + buf_tail_size); + + if (((buf_size + 3) & ~0x3) > IXGBE_ACI_LG_BUF) + desc->flags |= cpu_to_le16(IXGBE_ACI_FLAG_LB); + + desc->datalen = cpu_to_le16(buf_size); + + if (desc->flags & cpu_to_le16(IXGBE_ACI_FLAG_RD)) { + for (i = 0; i < buf_size / 4; i++) + IXGBE_WRITE_REG(hw, IXGBE_PF_HIBA(i), ((u32 *)buf)[i]); + if (buf_tail_size) + IXGBE_WRITE_REG(hw, IXGBE_PF_HIBA(i), buf_tail); + } + } + + /* Descriptor is written to specific registers */ + for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) + IXGBE_WRITE_REG(hw, IXGBE_PF_HIDA(i), raw_desc[i]); + + /* SW has to set PF_HICR.C bit and clear PF_HICR.SV and + * PF_HICR_EV + */ + hicr = (IXGBE_READ_REG(hw, IXGBE_PF_HICR) | IXGBE_PF_HICR_C) & + ~(IXGBE_PF_HICR_SV | IXGBE_PF_HICR_EV); + IXGBE_WRITE_REG(hw, IXGBE_PF_HICR, hicr); + +#define MAX_SLEEP_RESP_US 1000 +#define MAX_TMOUT_RESP_SYNC_US 100000000 + + /* Wait for sync Admin Command response */ + read_poll_timeout(IXGBE_READ_REG, hicr, + (hicr & IXGBE_PF_HICR_SV) || + !(hicr & IXGBE_PF_HICR_C), + MAX_SLEEP_RESP_US, MAX_TMOUT_RESP_SYNC_US, true, hw, + IXGBE_PF_HICR); + +#define MAX_TMOUT_RESP_ASYNC_US 150000000 + + /* Wait for async Admin Command response */ + read_poll_timeout(IXGBE_READ_REG, hicr, + (hicr & IXGBE_PF_HICR_EV) || + !(hicr & IXGBE_PF_HICR_C), + MAX_SLEEP_RESP_US, MAX_TMOUT_RESP_ASYNC_US, true, hw, + IXGBE_PF_HICR); + + /* Read sync Admin Command response */ + if ((hicr & IXGBE_PF_HICR_SV)) { + for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) { + raw_desc[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIDA(i)); + raw_desc[i] = raw_desc[i]; + } + } + + /* Read async Admin Command response */ + if ((hicr & IXGBE_PF_HICR_EV) && !(hicr & IXGBE_PF_HICR_C)) { + for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) { + raw_desc[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIDA_2(i)); + raw_desc[i] = raw_desc[i]; + } + } + + /* Handle timeout and invalid state of HICR register */ + if (hicr & IXGBE_PF_HICR_C) + return -ETIME; + + if (!(hicr & IXGBE_PF_HICR_SV) && !(hicr & IXGBE_PF_HICR_EV)) + return -EIO; + + /* For every command other than 0x0014 treat opcode mismatch + * as an error. Response to 0x0014 command read from HIDA_2 + * is a descriptor of an event which is expected to contain + * different opcode than the command. + */ + if (desc->opcode != cpu_to_le16(opcode) && + opcode != ixgbe_aci_opc_get_fw_event) + return -EIO; + + if (desc->retval) { + hw->aci.last_status = (enum ixgbe_aci_err) + le16_to_cpu(desc->retval); + return -EIO; + } + + /* Write a response values to a buf */ + if (valid_buf) { + for (i = 0; i < buf_size / 4; i++) + ((u32 *)buf)[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIBA(i)); + if (buf_tail_size) { + buf_tail = IXGBE_READ_REG(hw, IXGBE_PF_HIBA(i)); + memcpy(buf + buf_size - buf_tail_size, &buf_tail, + buf_tail_size); + } + } + + return 0; +} + +/** + * ixgbe_aci_send_cmd - send FW Admin Command to FW Admin Command Interface + * @hw: pointer to the HW struct + * @desc: descriptor describing the command + * @buf: buffer to use for indirect commands (NULL for direct commands) + * @buf_size: size of buffer for indirect commands (0 for direct commands) + * + * Helper function to send FW Admin Commands to the FW Admin Command Interface. + * + * Retry sending the FW Admin Command multiple times to the FW ACI + * if the EBUSY Admin Command error is returned. + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct ixgbe_aci_desc *desc, + void *buf, u16 buf_size) +{ + u16 opcode = le16_to_cpu(desc->opcode); + struct ixgbe_aci_desc desc_cpy; + enum ixgbe_aci_err last_status; + u8 idx = 0, *buf_cpy = NULL; + bool is_cmd_for_retry; + unsigned long timeout; + int err; + + is_cmd_for_retry = ixgbe_should_retry_aci_send_cmd_execute(opcode); + if (is_cmd_for_retry) { + if (buf) { + buf_cpy = kmalloc(buf_size, GFP_KERNEL); + if (!buf_cpy) + return -ENOMEM; + *buf_cpy = *(u8 *)buf; + } + desc_cpy = *desc; + } + + timeout = jiffies + msecs_to_jiffies(IXGBE_ACI_SEND_TIMEOUT_MS); + do { + mutex_lock(&hw->aci.lock); + err = ixgbe_aci_send_cmd_execute(hw, desc, buf, buf_size); + last_status = hw->aci.last_status; + mutex_unlock(&hw->aci.lock); + + if (!is_cmd_for_retry || !err || + last_status != IXGBE_ACI_RC_EBUSY) + break; + + if (buf) + memcpy(buf, buf_cpy, buf_size); + *desc = desc_cpy; + + msleep(IXGBE_ACI_SEND_DELAY_TIME_MS); + } while (++idx < IXGBE_ACI_SEND_MAX_EXECUTE && + time_before(jiffies, timeout)); + + kfree(buf_cpy); + + return err; +} + +/** + * ixgbe_aci_check_event_pending - check if there are any pending events + * @hw: pointer to the HW struct + * + * Determine if there are any pending events. + * + * Return: true if there are any currently pending events + * otherwise false. + */ +bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw) +{ + u32 ep_bit_mask = hw->bus.func ? GL_FWSTS_EP_PF1 : GL_FWSTS_EP_PF0; + u32 fwsts = IXGBE_READ_REG(hw, GL_FWSTS); + + return (fwsts & ep_bit_mask) ? true : false; +} + +/** + * ixgbe_aci_get_event - get an event from ACI + * @hw: pointer to the HW struct + * @e: event information structure + * @pending: optional flag signaling that there are more pending events + * + * Obtain an event from ACI and return its content + * through 'e' using ACI command (0x0014). + * Provide information if there are more events + * to retrieve through 'pending'. + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e, + bool *pending) +{ + struct ixgbe_aci_desc desc; + int err; + + if (!e || (!e->msg_buf && e->buf_len)) + return -EINVAL; + + mutex_lock(&hw->aci.lock); + + /* Check if there are any events pending */ + if (!ixgbe_aci_check_event_pending(hw)) { + err = -ENOENT; + goto aci_get_event_exit; + } + + /* Obtain pending event */ + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_fw_event); + err = ixgbe_aci_send_cmd_execute(hw, &desc, e->msg_buf, e->buf_len); + if (err) + goto aci_get_event_exit; + + /* Returned 0x0014 opcode indicates that no event was obtained */ + if (desc.opcode == cpu_to_le16(ixgbe_aci_opc_get_fw_event)) { + err = -ENOENT; + goto aci_get_event_exit; + } + + /* Determine size of event data */ + e->msg_len = min_t(u16, le16_to_cpu(desc.datalen), e->buf_len); + /* Write event descriptor to event info structure */ + memcpy(&e->desc, &desc, sizeof(e->desc)); + + /* Check if there are any further events pending */ + if (pending) + *pending = ixgbe_aci_check_event_pending(hw); + +aci_get_event_exit: + mutex_unlock(&hw->aci.lock); + + return err; +} + +/** + * ixgbe_fill_dflt_direct_cmd_desc - fill ACI descriptor with default values. + * @desc: pointer to the temp descriptor (non DMA mem) + * @opcode: the opcode can be used to decide which flags to turn off or on + * + * Helper function to fill the descriptor desc with default values + * and the provided opcode. + */ +void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode) +{ + /* Zero out the desc. */ + memset(desc, 0, sizeof(*desc)); + desc->opcode = cpu_to_le16(opcode); + desc->flags = cpu_to_le16(IXGBE_ACI_FLAG_SI); +} + +/** + * ixgbe_aci_req_res - request a common resource + * @hw: pointer to the HW struct + * @res: resource ID + * @access: access type + * @sdp_number: resource number + * @timeout: the maximum time in ms that the driver may hold the resource + * + * Requests a common resource using the ACI command (0x0008). + * Specifies the maximum time the driver may hold the resource. + * If the requested resource is currently occupied by some other driver, + * a busy return value is returned and the timeout field value indicates the + * maximum time the current owner has to free it. + * + * Return: the exit code of the operation. + */ +static int ixgbe_aci_req_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res, + enum ixgbe_aci_res_access_type access, + u8 sdp_number, u32 *timeout) +{ + struct ixgbe_aci_cmd_req_res *cmd_resp; + struct ixgbe_aci_desc desc; + int err; + + cmd_resp = &desc.params.res_owner; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_req_res); + + cmd_resp->res_id = cpu_to_le16(res); + cmd_resp->access_type = cpu_to_le16(access); + cmd_resp->res_number = cpu_to_le32(sdp_number); + cmd_resp->timeout = cpu_to_le32(*timeout); + *timeout = 0; + + err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0); + + /* If the resource is held by some other driver, the command completes + * with a busy return value and the timeout field indicates the maximum + * time the current owner of the resource has to free it. + */ + if (!err || hw->aci.last_status == IXGBE_ACI_RC_EBUSY) + *timeout = le32_to_cpu(cmd_resp->timeout); + + return err; +} + +/** + * ixgbe_aci_release_res - release a common resource using ACI + * @hw: pointer to the HW struct + * @res: resource ID + * @sdp_number: resource number + * + * Release a common resource using ACI command (0x0009). + * + * Return: the exit code of the operation. + */ +static int ixgbe_aci_release_res(struct ixgbe_hw *hw, + enum ixgbe_aci_res_ids res, u8 sdp_number) +{ + struct ixgbe_aci_cmd_req_res *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.res_owner; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_release_res); + + cmd->res_id = cpu_to_le16(res); + cmd->res_number = cpu_to_le32(sdp_number); + + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_acquire_res - acquire the ownership of a resource + * @hw: pointer to the HW structure + * @res: resource ID + * @access: access type (read or write) + * @timeout: timeout in milliseconds + * + * Make an attempt to acquire the ownership of a resource using + * the ixgbe_aci_req_res to utilize ACI. + * In case if some other driver has previously acquired the resource and + * performed any necessary updates, the -EALREADY is returned, + * and the caller does not obtain the resource and has no further work to do. + * If needed, the function will poll until the current lock owner timeouts. + * + * Return: the exit code of the operation. + */ +int ixgbe_acquire_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res, + enum ixgbe_aci_res_access_type access, u32 timeout) +{ +#define IXGBE_RES_POLLING_DELAY_MS 10 + u32 delay = IXGBE_RES_POLLING_DELAY_MS; + u32 res_timeout = timeout; + u32 retry_timeout; + int err; + + err = ixgbe_aci_req_res(hw, res, access, 0, &res_timeout); + + /* A return code of -EALREADY means that another driver has + * previously acquired the resource and performed any necessary updates; + * in this case the caller does not obtain the resource and has no + * further work to do. + */ + if (err == -EALREADY) + return err; + + /* If necessary, poll until the current lock owner timeouts. + * Set retry_timeout to the timeout value reported by the FW in the + * response to the "Request Resource Ownership" (0x0008) Admin Command + * as it indicates the maximum time the current owner of the resource + * is allowed to hold it. + */ + retry_timeout = res_timeout; + while (err && retry_timeout && res_timeout) { + msleep(delay); + retry_timeout = (retry_timeout > delay) ? + retry_timeout - delay : 0; + err = ixgbe_aci_req_res(hw, res, access, 0, &res_timeout); + + /* Success - lock acquired. + * -EALREADY - lock free, no work to do. + */ + if (!err || err == -EALREADY) + break; + } + + return err; +} + +/** + * ixgbe_release_res - release a common resource + * @hw: pointer to the HW structure + * @res: resource ID + * + * Release a common resource using ixgbe_aci_release_res. + */ +void ixgbe_release_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res) +{ + u32 total_delay = 0; + int err; + + err = ixgbe_aci_release_res(hw, res, 0); + + /* There are some rare cases when trying to release the resource + * results in an admin command timeout, so handle them correctly. + */ + while (err == -ETIME && + total_delay < IXGBE_ACI_RELEASE_RES_TIMEOUT) { + usleep_range(1000, 1500); + err = ixgbe_aci_release_res(hw, res, 0); + total_delay++; + } +} + +/** + * ixgbe_parse_e610_caps - Parse common device/function capabilities + * @hw: pointer to the HW struct + * @caps: pointer to common capabilities structure + * @elem: the capability element to parse + * @prefix: message prefix for tracing capabilities + * + * Given a capability element, extract relevant details into the common + * capability structure. + * + * Return: true if the capability matches one of the common capability ids, + * false otherwise. + */ +static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_caps *caps, + struct ixgbe_aci_cmd_list_caps_elem *elem, + const char *prefix) +{ + u32 logical_id = le32_to_cpu(elem->logical_id); + u32 phys_id = le32_to_cpu(elem->phys_id); + u32 number = le32_to_cpu(elem->number); + u16 cap = le16_to_cpu(elem->cap); + + switch (cap) { + case IXGBE_ACI_CAPS_VALID_FUNCTIONS: + caps->valid_functions = number; + break; + case IXGBE_ACI_CAPS_SRIOV: + caps->sr_iov_1_1 = (number == 1); + break; + case IXGBE_ACI_CAPS_VMDQ: + caps->vmdq = (number == 1); + break; + case IXGBE_ACI_CAPS_DCB: + caps->dcb = (number == 1); + caps->active_tc_bitmap = logical_id; + caps->maxtc = phys_id; + break; + case IXGBE_ACI_CAPS_RSS: + caps->rss_table_size = number; + caps->rss_table_entry_width = logical_id; + break; + case IXGBE_ACI_CAPS_RXQS: + caps->num_rxq = number; + caps->rxq_first_id = phys_id; + break; + case IXGBE_ACI_CAPS_TXQS: + caps->num_txq = number; + caps->txq_first_id = phys_id; + break; + case IXGBE_ACI_CAPS_MSIX: + caps->num_msix_vectors = number; + caps->msix_vector_first_id = phys_id; + break; + case IXGBE_ACI_CAPS_NVM_VER: + break; + case IXGBE_ACI_CAPS_MAX_MTU: + caps->max_mtu = number; + break; + case IXGBE_ACI_CAPS_PCIE_RESET_AVOIDANCE: + caps->pcie_reset_avoidance = (number > 0); + break; + case IXGBE_ACI_CAPS_POST_UPDATE_RESET_RESTRICT: + caps->reset_restrict_support = (number == 1); + break; + case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0: + case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG1: + case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG2: + case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG3: + { + u8 index = cap - IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0; + + caps->ext_topo_dev_img_ver_high[index] = number; + caps->ext_topo_dev_img_ver_low[index] = logical_id; + caps->ext_topo_dev_img_part_num[index] = + FIELD_GET(IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_M, phys_id); + caps->ext_topo_dev_img_load_en[index] = + (phys_id & IXGBE_EXT_TOPO_DEV_IMG_LOAD_EN) != 0; + caps->ext_topo_dev_img_prog_en[index] = + (phys_id & IXGBE_EXT_TOPO_DEV_IMG_PROG_EN) != 0; + break; + } + default: + /* Not one of the recognized common capabilities */ + return false; + } + + return true; +} + +/** + * ixgbe_parse_valid_functions_cap - Parse IXGBE_ACI_CAPS_VALID_FUNCTIONS caps + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse IXGBE_ACI_CAPS_VALID_FUNCTIONS for device capabilities. + */ +static void +ixgbe_parse_valid_functions_cap(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + dev_p->num_funcs = hweight32(le32_to_cpu(cap->number)); +} + +/** + * ixgbe_parse_vf_dev_caps - Parse IXGBE_ACI_CAPS_VF device caps + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse IXGBE_ACI_CAPS_VF for device capabilities. + */ +static void ixgbe_parse_vf_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + dev_p->num_vfs_exposed = le32_to_cpu(cap->number); +} + +/** + * ixgbe_parse_vsi_dev_caps - Parse IXGBE_ACI_CAPS_VSI device caps + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse IXGBE_ACI_CAPS_VSI for device capabilities. + */ +static void ixgbe_parse_vsi_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + dev_p->num_vsi_allocd_to_host = le32_to_cpu(cap->number); +} + +/** + * ixgbe_parse_fdir_dev_caps - Parse IXGBE_ACI_CAPS_FD device caps + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse IXGBE_ACI_CAPS_FD for device capabilities. + */ +static void ixgbe_parse_fdir_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + dev_p->num_flow_director_fltr = le32_to_cpu(cap->number); +} + +/** + * ixgbe_parse_dev_caps - Parse device capabilities + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @buf: buffer containing the device capability records + * @cap_count: the number of capabilities + * + * Helper device to parse device (0x000B) capabilities list. For + * capabilities shared between device and function, this relies on + * ixgbe_parse_e610_caps. + * + * Loop through the list of provided capabilities and extract the relevant + * data into the device capabilities structured. + */ +static void ixgbe_parse_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + void *buf, u32 cap_count) +{ + struct ixgbe_aci_cmd_list_caps_elem *cap_resp; + u32 i; + + cap_resp = (struct ixgbe_aci_cmd_list_caps_elem *)buf; + + memset(dev_p, 0, sizeof(*dev_p)); + + for (i = 0; i < cap_count; i++) { + u16 cap = le16_to_cpu(cap_resp[i].cap); + + ixgbe_parse_e610_caps(hw, &dev_p->common_cap, &cap_resp[i], + "dev caps"); + + switch (cap) { + case IXGBE_ACI_CAPS_VALID_FUNCTIONS: + ixgbe_parse_valid_functions_cap(hw, dev_p, + &cap_resp[i]); + break; + case IXGBE_ACI_CAPS_VF: + ixgbe_parse_vf_dev_caps(hw, dev_p, &cap_resp[i]); + break; + case IXGBE_ACI_CAPS_VSI: + ixgbe_parse_vsi_dev_caps(hw, dev_p, &cap_resp[i]); + break; + case IXGBE_ACI_CAPS_FD: + ixgbe_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]); + break; + default: + /* Don't list common capabilities as unknown */ + break; + } + } +} + +/** + * ixgbe_parse_vf_func_caps - Parse IXGBE_ACI_CAPS_VF function caps + * @hw: pointer to the HW struct + * @func_p: pointer to function capabilities structure + * @cap: pointer to the capability element to parse + * + * Extract function capabilities for IXGBE_ACI_CAPS_VF. + */ +static void ixgbe_parse_vf_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + func_p->num_allocd_vfs = le32_to_cpu(cap->number); + func_p->vf_base_id = le32_to_cpu(cap->logical_id); +} + +/** + * ixgbe_get_num_per_func - determine number of resources per PF + * @hw: pointer to the HW structure + * @max: value to be evenly split between each PF + * + * Determine the number of valid functions by going through the bitmap returned + * from parsing capabilities and use this to calculate the number of resources + * per PF based on the max value passed in. + * + * Return: the number of resources per PF or 0, if no PH are available. + */ +static u32 ixgbe_get_num_per_func(struct ixgbe_hw *hw, u32 max) +{ +#define IXGBE_CAPS_VALID_FUNCS_M GENMASK(7, 0) + u8 funcs = hweight8(hw->dev_caps.common_cap.valid_functions & + IXGBE_CAPS_VALID_FUNCS_M); + + return funcs ? (max / funcs) : 0; +} + +/** + * ixgbe_parse_vsi_func_caps - Parse IXGBE_ACI_CAPS_VSI function caps + * @hw: pointer to the HW struct + * @func_p: pointer to function capabilities structure + * @cap: pointer to the capability element to parse + * + * Extract function capabilities for IXGBE_ACI_CAPS_VSI. + */ +static void ixgbe_parse_vsi_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + func_p->guar_num_vsi = ixgbe_get_num_per_func(hw, IXGBE_MAX_VSI); +} + +/** + * ixgbe_parse_func_caps - Parse function capabilities + * @hw: pointer to the HW struct + * @func_p: pointer to function capabilities structure + * @buf: buffer containing the function capability records + * @cap_count: the number of capabilities + * + * Helper function to parse function (0x000A) capabilities list. For + * capabilities shared between device and function, this relies on + * ixgbe_parse_e610_caps. + * + * Loop through the list of provided capabilities and extract the relevant + * data into the function capabilities structured. + */ +static void ixgbe_parse_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_p, + void *buf, u32 cap_count) +{ + struct ixgbe_aci_cmd_list_caps_elem *cap_resp; + u32 i; + + cap_resp = (struct ixgbe_aci_cmd_list_caps_elem *)buf; + + memset(func_p, 0, sizeof(*func_p)); + + for (i = 0; i < cap_count; i++) { + u16 cap = le16_to_cpu(cap_resp[i].cap); + + ixgbe_parse_e610_caps(hw, &func_p->common_cap, + &cap_resp[i], "func caps"); + + switch (cap) { + case IXGBE_ACI_CAPS_VF: + ixgbe_parse_vf_func_caps(hw, func_p, &cap_resp[i]); + break; + case IXGBE_ACI_CAPS_VSI: + ixgbe_parse_vsi_func_caps(hw, func_p, &cap_resp[i]); + break; + default: + /* Don't list common capabilities as unknown */ + break; + } + } +} + +/** + * ixgbe_aci_list_caps - query function/device capabilities + * @hw: pointer to the HW struct + * @buf: a buffer to hold the capabilities + * @buf_size: size of the buffer + * @cap_count: if not NULL, set to the number of capabilities reported + * @opc: capabilities type to discover, device or function + * + * Get the function (0x000A) or device (0x000B) capabilities description from + * firmware and store it in the buffer. + * + * If the cap_count pointer is not NULL, then it is set to the number of + * capabilities firmware will report. Note that if the buffer size is too + * small, it is possible the command will return -ENOMEM. The + * cap_count will still be updated in this case. It is recommended that the + * buffer size be set to IXGBE_ACI_MAX_BUFFER_SIZE (the largest possible + * buffer that firmware could return) to avoid this. + * + * Return: the exit code of the operation. + * Exit code of -ENOMEM means the buffer size is too small. + */ +int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size, + u32 *cap_count, enum ixgbe_aci_opc opc) +{ + struct ixgbe_aci_cmd_list_caps *cmd; + struct ixgbe_aci_desc desc; + int err; + + cmd = &desc.params.get_cap; + + if (opc != ixgbe_aci_opc_list_func_caps && + opc != ixgbe_aci_opc_list_dev_caps) + return -EINVAL; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, opc); + err = ixgbe_aci_send_cmd(hw, &desc, buf, buf_size); + + if (cap_count) + *cap_count = le32_to_cpu(cmd->count); + + return err; +} + +/** + * ixgbe_discover_dev_caps - Read and extract device capabilities + * @hw: pointer to the hardware structure + * @dev_caps: pointer to device capabilities structure + * + * Read the device capabilities and extract them into the dev_caps structure + * for later use. + * + * Return: the exit code of the operation. + */ +int ixgbe_discover_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_caps) +{ + u32 cap_count; + u8 *cbuf; + int err; + + cbuf = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL); + if (!cbuf) + return -ENOMEM; + + /* Although the driver doesn't know the number of capabilities the + * device will return, we can simply send a 4KB buffer, the maximum + * possible size that firmware can return. + */ + cap_count = IXGBE_ACI_MAX_BUFFER_SIZE / + sizeof(struct ixgbe_aci_cmd_list_caps_elem); + + err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE, + &cap_count, + ixgbe_aci_opc_list_dev_caps); + if (!err) + ixgbe_parse_dev_caps(hw, dev_caps, cbuf, cap_count); + + kfree(cbuf); + + return 0; +} + +/** + * ixgbe_discover_func_caps - Read and extract function capabilities + * @hw: pointer to the hardware structure + * @func_caps: pointer to function capabilities structure + * + * Read the function capabilities and extract them into the func_caps structure + * for later use. + * + * Return: the exit code of the operation. + */ +int ixgbe_discover_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_caps) +{ + u32 cap_count; + u8 *cbuf; + int err; + + cbuf = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL); + if (!cbuf) + return -ENOMEM; + + /* Although the driver doesn't know the number of capabilities the + * device will return, we can simply send a 4KB buffer, the maximum + * possible size that firmware can return. + */ + cap_count = IXGBE_ACI_MAX_BUFFER_SIZE / + sizeof(struct ixgbe_aci_cmd_list_caps_elem); + + err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE, + &cap_count, + ixgbe_aci_opc_list_func_caps); + if (!err) + ixgbe_parse_func_caps(hw, func_caps, cbuf, cap_count); + + kfree(cbuf); + + return 0; +} + +/** + * ixgbe_get_caps - get info about the HW + * @hw: pointer to the hardware structure + * + * Retrieve both device and function capabilities. + * + * Return: the exit code of the operation. + */ +int ixgbe_get_caps(struct ixgbe_hw *hw) +{ + int err; + + err = ixgbe_discover_dev_caps(hw, &hw->dev_caps); + if (err) + return err; + + return ixgbe_discover_func_caps(hw, &hw->func_caps); +} + +/** + * ixgbe_aci_disable_rxen - disable RX + * @hw: pointer to the HW struct + * + * Request a safe disable of Receive Enable using ACI command (0x000C). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_disable_rxen(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_disable_rxen *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.disable_rxen; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_disable_rxen); + + cmd->lport_num = hw->bus.func; + + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_aci_get_phy_caps - returns PHY capabilities + * @hw: pointer to the HW struct + * @qual_mods: report qualified modules + * @report_mode: report mode capabilities + * @pcaps: structure for PHY capabilities to be filled + * + * Returns the various PHY capabilities supported on the Port + * using ACI command (0x0600). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_get_phy_caps(struct ixgbe_hw *hw, bool qual_mods, u8 report_mode, + struct ixgbe_aci_cmd_get_phy_caps_data *pcaps) +{ + struct ixgbe_aci_cmd_get_phy_caps *cmd; + u16 pcaps_size = sizeof(*pcaps); + struct ixgbe_aci_desc desc; + int err; + + cmd = &desc.params.get_phy; + + if (!pcaps || (report_mode & ~IXGBE_ACI_REPORT_MODE_M)) + return -EINVAL; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_phy_caps); + + if (qual_mods) + cmd->param0 |= cpu_to_le16(IXGBE_ACI_GET_PHY_RQM); + + cmd->param0 |= cpu_to_le16(report_mode); + err = ixgbe_aci_send_cmd(hw, &desc, pcaps, pcaps_size); + if (!err && report_mode == IXGBE_ACI_REPORT_TOPO_CAP_MEDIA) { + hw->phy.phy_type_low = le64_to_cpu(pcaps->phy_type_low); + hw->phy.phy_type_high = le64_to_cpu(pcaps->phy_type_high); + memcpy(hw->link.link_info.module_type, &pcaps->module_type, + sizeof(hw->link.link_info.module_type)); + } + + return err; +} + +/** + * ixgbe_copy_phy_caps_to_cfg - Copy PHY ability data to configuration data + * @caps: PHY ability structure to copy data from + * @cfg: PHY configuration structure to copy data to + * + * Helper function to copy data from PHY capabilities data structure + * to PHY configuration data structure + */ +void ixgbe_copy_phy_caps_to_cfg(struct ixgbe_aci_cmd_get_phy_caps_data *caps, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg) +{ + if (!caps || !cfg) + return; + + memset(cfg, 0, sizeof(*cfg)); + cfg->phy_type_low = caps->phy_type_low; + cfg->phy_type_high = caps->phy_type_high; + cfg->caps = caps->caps; + cfg->low_power_ctrl_an = caps->low_power_ctrl_an; + cfg->eee_cap = caps->eee_cap; + cfg->eeer_value = caps->eeer_value; + cfg->link_fec_opt = caps->link_fec_options; + cfg->module_compliance_enforcement = + caps->module_compliance_enforcement; +} + +/** + * ixgbe_aci_set_phy_cfg - set PHY configuration + * @hw: pointer to the HW struct + * @cfg: structure with PHY configuration data to be set + * + * Set the various PHY configuration parameters supported on the Port + * using ACI command (0x0601). + * One or more of the Set PHY config parameters may be ignored in an MFP + * mode as the PF may not have the privilege to set some of the PHY Config + * parameters. + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg) +{ + struct ixgbe_aci_desc desc; + int err; + + if (!cfg) + return -EINVAL; + + /* Ensure that only valid bits of cfg->caps can be turned on. */ + cfg->caps &= IXGBE_ACI_PHY_ENA_VALID_MASK; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_phy_cfg); + desc.params.set_phy.lport_num = hw->bus.func; + desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD); + + err = ixgbe_aci_send_cmd(hw, &desc, cfg, sizeof(*cfg)); + if (!err) + hw->phy.curr_user_phy_cfg = *cfg; + + return err; +} + +/** + * ixgbe_aci_set_link_restart_an - set up link and restart AN + * @hw: pointer to the HW struct + * @ena_link: if true: enable link, if false: disable link + * + * Function sets up the link and restarts the Auto-Negotiation over the link. + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link) +{ + struct ixgbe_aci_cmd_restart_an *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.restart_an; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_restart_an); + + cmd->cmd_flags = IXGBE_ACI_RESTART_AN_LINK_RESTART; + cmd->lport_num = hw->bus.func; + if (ena_link) + cmd->cmd_flags |= IXGBE_ACI_RESTART_AN_LINK_ENABLE; + else + cmd->cmd_flags &= ~IXGBE_ACI_RESTART_AN_LINK_ENABLE; + + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_is_media_cage_present - check if media cage is present + * @hw: pointer to the HW struct + * + * Identify presence of media cage using the ACI command (0x06E0). + * + * Return: true if media cage is present, else false. If no cage, then + * media type is backplane or BASE-T. + */ +static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_link_topo *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.get_link_topo; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo); + + cmd->addr.topo_params.node_type_ctx = + FIELD_PREP(IXGBE_ACI_LINK_TOPO_NODE_CTX_M, + IXGBE_ACI_LINK_TOPO_NODE_CTX_PORT); + + /* Set node type. */ + cmd->addr.topo_params.node_type_ctx |= + FIELD_PREP(IXGBE_ACI_LINK_TOPO_NODE_TYPE_M, + IXGBE_ACI_LINK_TOPO_NODE_TYPE_CAGE); + + /* Node type cage can be used to determine if cage is present. If AQC + * returns error (ENOENT), then no cage present. If no cage present then + * connection type is backplane or BASE-T. + */ + return ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL); +} + +/** + * ixgbe_get_media_type_from_phy_type - Gets media type based on phy type + * @hw: pointer to the HW struct + * + * Try to identify the media type based on the phy type. + * If more than one media type, the ixgbe_media_type_unknown is returned. + * First, phy_type_low is checked, then phy_type_high. + * If none are identified, the ixgbe_media_type_unknown is returned + * + * Return: type of a media based on phy type in form of enum. + */ +static enum ixgbe_media_type +ixgbe_get_media_type_from_phy_type(struct ixgbe_hw *hw) +{ + struct ixgbe_link_status *hw_link_info; + + if (!hw) + return ixgbe_media_type_unknown; + + hw_link_info = &hw->link.link_info; + if (hw_link_info->phy_type_low && hw_link_info->phy_type_high) + /* If more than one media type is selected, report unknown */ + return ixgbe_media_type_unknown; + + if (hw_link_info->phy_type_low) { + /* 1G SGMII is a special case where some DA cable PHYs + * may show this as an option when it really shouldn't + * be since SGMII is meant to be between a MAC and a PHY + * in a backplane. Try to detect this case and handle it + */ + if (hw_link_info->phy_type_low == IXGBE_PHY_TYPE_LOW_1G_SGMII && + (hw_link_info->module_type[IXGBE_ACI_MOD_TYPE_IDENT] == + IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE || + hw_link_info->module_type[IXGBE_ACI_MOD_TYPE_IDENT] == + IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE)) + return ixgbe_media_type_da; + + switch (hw_link_info->phy_type_low) { + case IXGBE_PHY_TYPE_LOW_1000BASE_SX: + case IXGBE_PHY_TYPE_LOW_1000BASE_LX: + case IXGBE_PHY_TYPE_LOW_10GBASE_SR: + case IXGBE_PHY_TYPE_LOW_10GBASE_LR: + case IXGBE_PHY_TYPE_LOW_25GBASE_SR: + case IXGBE_PHY_TYPE_LOW_25GBASE_LR: + return ixgbe_media_type_fiber; + case IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC: + case IXGBE_PHY_TYPE_LOW_25G_AUI_AOC_ACC: + return ixgbe_media_type_fiber; + case IXGBE_PHY_TYPE_LOW_100BASE_TX: + case IXGBE_PHY_TYPE_LOW_1000BASE_T: + case IXGBE_PHY_TYPE_LOW_2500BASE_T: + case IXGBE_PHY_TYPE_LOW_5GBASE_T: + case IXGBE_PHY_TYPE_LOW_10GBASE_T: + case IXGBE_PHY_TYPE_LOW_25GBASE_T: + return ixgbe_media_type_copper; + case IXGBE_PHY_TYPE_LOW_10G_SFI_DA: + case IXGBE_PHY_TYPE_LOW_25GBASE_CR: + case IXGBE_PHY_TYPE_LOW_25GBASE_CR_S: + case IXGBE_PHY_TYPE_LOW_25GBASE_CR1: + return ixgbe_media_type_da; + case IXGBE_PHY_TYPE_LOW_25G_AUI_C2C: + if (ixgbe_is_media_cage_present(hw)) + return ixgbe_media_type_aui; + fallthrough; + case IXGBE_PHY_TYPE_LOW_1000BASE_KX: + case IXGBE_PHY_TYPE_LOW_2500BASE_KX: + case IXGBE_PHY_TYPE_LOW_2500BASE_X: + case IXGBE_PHY_TYPE_LOW_5GBASE_KR: + case IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1: + case IXGBE_PHY_TYPE_LOW_10G_SFI_C2C: + case IXGBE_PHY_TYPE_LOW_25GBASE_KR: + case IXGBE_PHY_TYPE_LOW_25GBASE_KR1: + case IXGBE_PHY_TYPE_LOW_25GBASE_KR_S: + return ixgbe_media_type_backplane; + } + } else { + switch (hw_link_info->phy_type_high) { + case IXGBE_PHY_TYPE_HIGH_10BASE_T: + return ixgbe_media_type_copper; + } + } + return ixgbe_media_type_unknown; +} + +/** + * ixgbe_update_link_info - update status of the HW network link + * @hw: pointer to the HW struct + * + * Update the status of the HW network link. + * + * Return: the exit code of the operation. + */ +int ixgbe_update_link_info(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data *pcaps; + struct ixgbe_link_status *li; + int err; + + if (!hw) + return -EINVAL; + + li = &hw->link.link_info; + + err = ixgbe_aci_get_link_info(hw, true, NULL); + if (err) + return err; + + if (!(li->link_info & IXGBE_ACI_MEDIA_AVAILABLE)) + return 0; + + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); + if (!pcaps) + return -ENOMEM; + + err = ixgbe_aci_get_phy_caps(hw, false, IXGBE_ACI_REPORT_TOPO_CAP_MEDIA, + pcaps); + + if (!err) + memcpy(li->module_type, &pcaps->module_type, + sizeof(li->module_type)); + + kfree(pcaps); + + return err; +} + +/** + * ixgbe_get_link_status - get status of the HW network link + * @hw: pointer to the HW struct + * @link_up: pointer to bool (true/false = linkup/linkdown) + * + * Variable link_up is true if link is up, false if link is down. + * The variable link_up is invalid if status is non zero. As a + * result of this call, link status reporting becomes enabled + * + * Return: the exit code of the operation. + */ +int ixgbe_get_link_status(struct ixgbe_hw *hw, bool *link_up) +{ + if (!hw || !link_up) + return -EINVAL; + + if (hw->link.get_link_info) { + int err = ixgbe_update_link_info(hw); + + if (err) + return err; + } + + *link_up = hw->link.link_info.link_info & IXGBE_ACI_LINK_UP; + + return 0; +} + +/** + * ixgbe_aci_get_link_info - get the link status + * @hw: pointer to the HW struct + * @ena_lse: enable/disable LinkStatusEvent reporting + * @link: pointer to link status structure - optional + * + * Get the current Link Status using ACI command (0x607). + * The current link can be optionally provided to update + * the status. + * + * Return: the link status of the adapter. + */ +int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse, + struct ixgbe_link_status *link) +{ + struct ixgbe_aci_cmd_get_link_status_data link_data = {}; + struct ixgbe_aci_cmd_get_link_status *resp; + struct ixgbe_link_status *li_old, *li; + struct ixgbe_fc_info *hw_fc_info; + struct ixgbe_aci_desc desc; + bool tx_pause, rx_pause; + u8 cmd_flags; + int err; + + if (!hw) + return -EINVAL; + + li_old = &hw->link.link_info_old; + li = &hw->link.link_info; + hw_fc_info = &hw->fc; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_status); + cmd_flags = (ena_lse) ? IXGBE_ACI_LSE_ENA : IXGBE_ACI_LSE_DIS; + resp = &desc.params.get_link_status; + resp->cmd_flags = cpu_to_le16(cmd_flags); + resp->lport_num = hw->bus.func; + + err = ixgbe_aci_send_cmd(hw, &desc, &link_data, sizeof(link_data)); + if (err) + return err; + + /* Save off old link status information. */ + *li_old = *li; + + /* Update current link status information. */ + li->link_speed = le16_to_cpu(link_data.link_speed); + li->phy_type_low = le64_to_cpu(link_data.phy_type_low); + li->phy_type_high = le64_to_cpu(link_data.phy_type_high); + li->link_info = link_data.link_info; + li->link_cfg_err = link_data.link_cfg_err; + li->an_info = link_data.an_info; + li->ext_info = link_data.ext_info; + li->max_frame_size = le16_to_cpu(link_data.max_frame_size); + li->fec_info = link_data.cfg & IXGBE_ACI_FEC_MASK; + li->topo_media_conflict = link_data.topo_media_conflict; + li->pacing = link_data.cfg & (IXGBE_ACI_CFG_PACING_M | + IXGBE_ACI_CFG_PACING_TYPE_M); + + /* Update fc info. */ + tx_pause = !!(link_data.an_info & IXGBE_ACI_LINK_PAUSE_TX); + rx_pause = !!(link_data.an_info & IXGBE_ACI_LINK_PAUSE_RX); + if (tx_pause && rx_pause) + hw_fc_info->current_mode = ixgbe_fc_full; + else if (tx_pause) + hw_fc_info->current_mode = ixgbe_fc_tx_pause; + else if (rx_pause) + hw_fc_info->current_mode = ixgbe_fc_rx_pause; + else + hw_fc_info->current_mode = ixgbe_fc_none; + + li->lse_ena = !!(le16_to_cpu(resp->cmd_flags) & + IXGBE_ACI_LSE_IS_ENABLED); + + /* Save link status information. */ + if (link) + *link = *li; + + /* Flag cleared so calling functions don't call AQ again. */ + hw->link.get_link_info = false; + + return 0; +} + +/** + * ixgbe_aci_set_event_mask - set event mask + * @hw: pointer to the HW struct + * @port_num: port number of the physical function + * @mask: event mask to be set + * + * Set the event mask using ACI command (0x0613). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask) +{ + struct ixgbe_aci_cmd_set_event_mask *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.set_event_mask; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_event_mask); + + cmd->lport_num = port_num; + + cmd->event_mask = cpu_to_le16(mask); + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_configure_lse - enable/disable link status events + * @hw: pointer to the HW struct + * @activate: true for enable lse, false otherwise + * @mask: event mask to be set; a set bit means deactivation of the + * corresponding event + * + * Set the event mask and then enable or disable link status events + * + * Return: the exit code of the operation. + */ +int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask) +{ + int err; + + err = ixgbe_aci_set_event_mask(hw, (u8)hw->bus.func, mask); + if (err) + return err; + + /* Enabling link status events generation by fw. */ + return ixgbe_aci_get_link_info(hw, activate, NULL); +} + +/** + * ixgbe_get_media_type_e610 - Gets media type + * @hw: pointer to the HW struct + * + * In order to get the media type, the function gets PHY + * capabilities and later on use them to identify the PHY type + * checking phy_type_high and phy_type_low. + * + * Return: the type of media in form of ixgbe_media_type enum + * or ixgbe_media_type_unknown in case of an error. + */ +enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data pcaps; + int rc; + + rc = ixgbe_update_link_info(hw); + if (rc) + return ixgbe_media_type_unknown; + + /* If there is no link but PHY (dongle) is available SW should use + * Get PHY Caps admin command instead of Get Link Status, find most + * significant bit that is set in PHY types reported by the command + * and use it to discover media type. + */ + if (!(hw->link.link_info.link_info & IXGBE_ACI_LINK_UP) && + (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE)) { + int highest_bit; + + /* Get PHY Capabilities */ + rc = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_TOPO_CAP_MEDIA, + &pcaps); + if (rc) + return ixgbe_media_type_unknown; + + highest_bit = fls64(le64_to_cpu(pcaps.phy_type_high)); + if (highest_bit) { + hw->link.link_info.phy_type_high = + BIT_ULL(highest_bit - 1); + hw->link.link_info.phy_type_low = 0; + } else { + highest_bit = fls64(le64_to_cpu(pcaps.phy_type_low)); + if (highest_bit) + hw->link.link_info.phy_type_low = + BIT_ULL(highest_bit - 1); + } + } + + /* Based on link status or search above try to discover media type. */ + hw->phy.media_type = ixgbe_get_media_type_from_phy_type(hw); + + return hw->phy.media_type; +} + +/** + * ixgbe_setup_link_e610 - Set up link + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait: true when waiting for completion is needed + * + * Set up the link with the specified speed. + * + * Return: the exit code of the operation. + */ +int ixgbe_setup_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed speed, + bool autoneg_wait) +{ + /* Simply request FW to perform proper PHY setup */ + return hw->phy.ops.setup_link_speed(hw, speed, autoneg_wait); +} + +/** + * ixgbe_check_link_e610 - Determine link and speed status + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @link_up: true when link is up + * @link_up_wait_to_complete: bool used to wait for link up or not + * + * Determine if the link is up and the current link speed + * using ACI command (0x0607). + * + * Return: the exit code of the operation. + */ +int ixgbe_check_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed *speed, + bool *link_up, bool link_up_wait_to_complete) +{ + int err; + u32 i; + + if (!speed || !link_up) + return -EINVAL; + + /* Set get_link_info flag to ensure that fresh + * link information will be obtained from FW + * by sending Get Link Status admin command. + */ + hw->link.get_link_info = true; + + /* Update link information in adapter context. */ + err = ixgbe_get_link_status(hw, link_up); + if (err) + return err; + + /* Wait for link up if it was requested. */ + if (link_up_wait_to_complete && !(*link_up)) { + for (i = 0; i < hw->mac.max_link_up_time; i++) { + msleep(100); + hw->link.get_link_info = true; + err = ixgbe_get_link_status(hw, link_up); + if (err) + return err; + if (*link_up) + break; + } + } + + /* Use link information in adapter context updated by the call + * to ixgbe_get_link_status() to determine current link speed. + * Link speed information is valid only when link up was + * reported by FW. + */ + if (*link_up) { + switch (hw->link.link_info.link_speed) { + case IXGBE_ACI_LINK_SPEED_10MB: + *speed = IXGBE_LINK_SPEED_10_FULL; + break; + case IXGBE_ACI_LINK_SPEED_100MB: + *speed = IXGBE_LINK_SPEED_100_FULL; + break; + case IXGBE_ACI_LINK_SPEED_1000MB: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + case IXGBE_ACI_LINK_SPEED_2500MB: + *speed = IXGBE_LINK_SPEED_2_5GB_FULL; + break; + case IXGBE_ACI_LINK_SPEED_5GB: + *speed = IXGBE_LINK_SPEED_5GB_FULL; + break; + case IXGBE_ACI_LINK_SPEED_10GB: + *speed = IXGBE_LINK_SPEED_10GB_FULL; + break; + default: + *speed = IXGBE_LINK_SPEED_UNKNOWN; + break; + } + } else { + *speed = IXGBE_LINK_SPEED_UNKNOWN; + } + + return 0; +} + +/** + * ixgbe_get_link_capabilities_e610 - Determine link capabilities + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @autoneg: true when autoneg or autotry is enabled + * + * Determine speed and AN parameters of a link. + * + * Return: the exit code of the operation. + */ +int ixgbe_get_link_capabilities_e610(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg) +{ + if (!speed || !autoneg) + return -EINVAL; + + *autoneg = true; + *speed = hw->phy.speeds_supported; + + return 0; +} + +/** + * ixgbe_cfg_phy_fc - Configure PHY Flow Control (FC) data based on FC mode + * @hw: pointer to hardware structure + * @cfg: PHY configuration data to set FC mode + * @req_mode: FC mode to configure + * + * Configures PHY Flow Control according to the provided configuration. + * + * Return: the exit code of the operation. + */ +int ixgbe_cfg_phy_fc(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg, + enum ixgbe_fc_mode req_mode) +{ + u8 pause_mask = 0x0; + + if (!cfg) + return -EINVAL; + + switch (req_mode) { + case ixgbe_fc_full: + pause_mask |= IXGBE_ACI_PHY_EN_TX_LINK_PAUSE; + pause_mask |= IXGBE_ACI_PHY_EN_RX_LINK_PAUSE; + break; + case ixgbe_fc_rx_pause: + pause_mask |= IXGBE_ACI_PHY_EN_RX_LINK_PAUSE; + break; + case ixgbe_fc_tx_pause: + pause_mask |= IXGBE_ACI_PHY_EN_TX_LINK_PAUSE; + break; + default: + break; + } + + /* Clear the old pause settings. */ + cfg->caps &= ~(IXGBE_ACI_PHY_EN_TX_LINK_PAUSE | + IXGBE_ACI_PHY_EN_RX_LINK_PAUSE); + + /* Set the new capabilities. */ + cfg->caps |= pause_mask; + + return 0; +} + +/** + * ixgbe_setup_fc_e610 - Set up flow control + * @hw: pointer to hardware structure + * + * Set up flow control. This has to be done during init time. + * + * Return: the exit code of the operation. + */ +int ixgbe_setup_fc_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data pcaps = {}; + struct ixgbe_aci_cmd_set_phy_cfg_data cfg = {}; + int err; + + /* Get the current PHY config */ + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_ACTIVE_CFG, &pcaps); + if (err) + return err; + + ixgbe_copy_phy_caps_to_cfg(&pcaps, &cfg); + + /* Configure the set PHY data */ + err = ixgbe_cfg_phy_fc(hw, &cfg, hw->fc.requested_mode); + if (err) + return err; + + /* If the capabilities have changed, then set the new config */ + if (cfg.caps != pcaps.caps) { + cfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT; + + err = ixgbe_aci_set_phy_cfg(hw, &cfg); + if (err) + return err; + } + + return err; +} + +/** + * ixgbe_fc_autoneg_e610 - Configure flow control + * @hw: pointer to hardware structure + * + * Configure Flow Control. + */ +void ixgbe_fc_autoneg_e610(struct ixgbe_hw *hw) +{ + int err; + + /* Get current link err. + * Current FC mode will be stored in the hw context. + */ + err = ixgbe_aci_get_link_info(hw, false, NULL); + if (err) + goto no_autoneg; + + /* Check if the link is up */ + if (!(hw->link.link_info.link_info & IXGBE_ACI_LINK_UP)) + goto no_autoneg; + + /* Check if auto-negotiation has completed */ + if (!(hw->link.link_info.an_info & IXGBE_ACI_AN_COMPLETED)) + goto no_autoneg; + + hw->fc.fc_was_autonegged = true; + return; + +no_autoneg: + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; +} + +/** + * ixgbe_disable_rx_e610 - Disable RX unit + * @hw: pointer to hardware structure + * + * Disable RX DMA unit on E610 with use of ACI command (0x000C). + * + * Return: the exit code of the operation. + */ +void ixgbe_disable_rx_e610(struct ixgbe_hw *hw) +{ + u32 rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + u32 pfdtxgswc; + int err; + + if (!(rxctrl & IXGBE_RXCTRL_RXEN)) + return; + + pfdtxgswc = IXGBE_READ_REG(hw, IXGBE_PFDTXGSWC); + if (pfdtxgswc & IXGBE_PFDTXGSWC_VT_LBEN) { + pfdtxgswc &= ~IXGBE_PFDTXGSWC_VT_LBEN; + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, pfdtxgswc); + hw->mac.set_lben = true; + } else { + hw->mac.set_lben = false; + } + + err = ixgbe_aci_disable_rxen(hw); + + /* If we fail - disable RX using register write */ + if (err) { + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + if (rxctrl & IXGBE_RXCTRL_RXEN) { + rxctrl &= ~IXGBE_RXCTRL_RXEN; + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl); + } + } +} + +/** + * ixgbe_init_phy_ops_e610 - PHY specific init + * @hw: pointer to hardware structure + * + * Initialize any function pointers that were not able to be + * set during init_shared_code because the PHY type was not known. + * + * Return: the exit code of the operation. + */ +int ixgbe_init_phy_ops_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + struct ixgbe_phy_info *phy = &hw->phy; + + if (mac->ops.get_media_type(hw) == ixgbe_media_type_copper) + phy->ops.set_phy_power = ixgbe_set_phy_power_e610; + else + phy->ops.set_phy_power = NULL; + + /* Identify the PHY */ + return phy->ops.identify(hw); +} + +/** + * ixgbe_identify_phy_e610 - Identify PHY + * @hw: pointer to hardware structure + * + * Determine PHY type, supported speeds and PHY ID. + * + * Return: the exit code of the operation. + */ +int ixgbe_identify_phy_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data pcaps; + u64 phy_type_low, phy_type_high; + int err; + + /* Set PHY type */ + hw->phy.type = ixgbe_phy_fw; + + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_TOPO_CAP_MEDIA, &pcaps); + if (err) + return err; + + if (!(pcaps.module_compliance_enforcement & + IXGBE_ACI_MOD_ENFORCE_STRICT_MODE)) { + /* Handle lenient mode */ + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_TOPO_CAP_NO_MEDIA, + &pcaps); + if (err) + return err; + } + + /* Determine supported speeds */ + hw->phy.speeds_supported = IXGBE_LINK_SPEED_UNKNOWN; + phy_type_high = le64_to_cpu(pcaps.phy_type_high); + phy_type_low = le64_to_cpu(pcaps.phy_type_low); + + if (phy_type_high & IXGBE_PHY_TYPE_HIGH_10BASE_T || + phy_type_high & IXGBE_PHY_TYPE_HIGH_10M_SGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_10_FULL; + if (phy_type_low & IXGBE_PHY_TYPE_LOW_100BASE_TX || + phy_type_low & IXGBE_PHY_TYPE_LOW_100M_SGMII || + phy_type_high & IXGBE_PHY_TYPE_HIGH_100M_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_100_FULL; + if (phy_type_low & IXGBE_PHY_TYPE_LOW_1000BASE_T || + phy_type_low & IXGBE_PHY_TYPE_LOW_1000BASE_SX || + phy_type_low & IXGBE_PHY_TYPE_LOW_1000BASE_LX || + phy_type_low & IXGBE_PHY_TYPE_LOW_1000BASE_KX || + phy_type_low & IXGBE_PHY_TYPE_LOW_1G_SGMII || + phy_type_high & IXGBE_PHY_TYPE_HIGH_1G_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_1GB_FULL; + if (phy_type_low & IXGBE_PHY_TYPE_LOW_10GBASE_T || + phy_type_low & IXGBE_PHY_TYPE_LOW_10G_SFI_DA || + phy_type_low & IXGBE_PHY_TYPE_LOW_10GBASE_SR || + phy_type_low & IXGBE_PHY_TYPE_LOW_10GBASE_LR || + phy_type_low & IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1 || + phy_type_low & IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC || + phy_type_low & IXGBE_PHY_TYPE_LOW_10G_SFI_C2C || + phy_type_high & IXGBE_PHY_TYPE_HIGH_10G_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_10GB_FULL; + + /* 2.5 and 5 Gbps link speeds must be excluded from the + * auto-negotiation set used during driver initialization due to + * compatibility issues with certain switches. Those issues do not + * exist in case of E610 2.5G SKU device (0x57b1). + */ + if (!hw->phy.autoneg_advertised && + hw->device_id != IXGBE_DEV_ID_E610_2_5G_T) + hw->phy.autoneg_advertised = hw->phy.speeds_supported; + + if (phy_type_low & IXGBE_PHY_TYPE_LOW_2500BASE_T || + phy_type_low & IXGBE_PHY_TYPE_LOW_2500BASE_X || + phy_type_low & IXGBE_PHY_TYPE_LOW_2500BASE_KX || + phy_type_high & IXGBE_PHY_TYPE_HIGH_2500M_SGMII || + phy_type_high & IXGBE_PHY_TYPE_HIGH_2500M_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_2_5GB_FULL; + + if (!hw->phy.autoneg_advertised && + hw->device_id == IXGBE_DEV_ID_E610_2_5G_T) + hw->phy.autoneg_advertised = hw->phy.speeds_supported; + + if (phy_type_low & IXGBE_PHY_TYPE_LOW_5GBASE_T || + phy_type_low & IXGBE_PHY_TYPE_LOW_5GBASE_KR || + phy_type_high & IXGBE_PHY_TYPE_HIGH_5G_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL; + + /* Set PHY ID */ + memcpy(&hw->phy.id, pcaps.phy_id_oui, sizeof(u32)); + + hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_10_FULL | + IXGBE_LINK_SPEED_100_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + hw->phy.eee_speeds_advertised = hw->phy.eee_speeds_supported; + + return 0; +} + +/** + * ixgbe_identify_module_e610 - Identify SFP module type + * @hw: pointer to hardware structure + * + * Identify the SFP module type. + * + * Return: the exit code of the operation. + */ +int ixgbe_identify_module_e610(struct ixgbe_hw *hw) +{ + bool media_available; + u8 module_type; + int err; + + err = ixgbe_update_link_info(hw); + if (err) + return err; + + media_available = + (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE); + + if (media_available) { + hw->phy.sfp_type = ixgbe_sfp_type_unknown; + + /* Get module type from hw context updated by + * ixgbe_update_link_info() + */ + module_type = hw->link.link_info.module_type[IXGBE_ACI_MOD_TYPE_IDENT]; + + if ((module_type & IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE) || + (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE)) { + hw->phy.sfp_type = ixgbe_sfp_type_da_cu; + } else if (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_SR) { + hw->phy.sfp_type = ixgbe_sfp_type_sr; + } else if ((module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LR) || + (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LRM)) { + hw->phy.sfp_type = ixgbe_sfp_type_lr; + } + } else { + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + return -ENOENT; + } + + return 0; +} + +/** + * ixgbe_setup_phy_link_e610 - Sets up firmware-controlled PHYs + * @hw: pointer to hardware structure + * + * Set the parameters for the firmware-controlled PHYs. + * + * Return: the exit code of the operation. + */ +int ixgbe_setup_phy_link_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data pcaps; + struct ixgbe_aci_cmd_set_phy_cfg_data pcfg; + u8 rmode = IXGBE_ACI_REPORT_TOPO_CAP_MEDIA; + u64 sup_phy_type_low, sup_phy_type_high; + u64 phy_type_low = 0, phy_type_high = 0; + int err; + + err = ixgbe_aci_get_link_info(hw, false, NULL); + if (err) + return err; + + /* If media is not available get default config. */ + if (!(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE)) + rmode = IXGBE_ACI_REPORT_DFLT_CFG; + + err = ixgbe_aci_get_phy_caps(hw, false, rmode, &pcaps); + if (err) + return err; + + sup_phy_type_low = le64_to_cpu(pcaps.phy_type_low); + sup_phy_type_high = le64_to_cpu(pcaps.phy_type_high); + + /* Get Active configuration to avoid unintended changes. */ + err = ixgbe_aci_get_phy_caps(hw, false, IXGBE_ACI_REPORT_ACTIVE_CFG, + &pcaps); + if (err) + return err; + + ixgbe_copy_phy_caps_to_cfg(&pcaps, &pcfg); + + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL) { + phy_type_high |= IXGBE_PHY_TYPE_HIGH_10BASE_T; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_10M_SGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_100BASE_TX; + phy_type_low |= IXGBE_PHY_TYPE_LOW_100M_SGMII; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_100M_USXGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_1000BASE_T; + phy_type_low |= IXGBE_PHY_TYPE_LOW_1000BASE_SX; + phy_type_low |= IXGBE_PHY_TYPE_LOW_1000BASE_LX; + phy_type_low |= IXGBE_PHY_TYPE_LOW_1000BASE_KX; + phy_type_low |= IXGBE_PHY_TYPE_LOW_1G_SGMII; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_1G_USXGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_2500BASE_T; + phy_type_low |= IXGBE_PHY_TYPE_LOW_2500BASE_X; + phy_type_low |= IXGBE_PHY_TYPE_LOW_2500BASE_KX; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_2500M_SGMII; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_2500M_USXGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_5GBASE_T; + phy_type_low |= IXGBE_PHY_TYPE_LOW_5GBASE_KR; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_5G_USXGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_10GBASE_T; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10G_SFI_DA; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10GBASE_SR; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10GBASE_LR; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10G_SFI_C2C; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_10G_USXGMII; + } + + /* Mask the set values to avoid requesting unsupported link types. */ + phy_type_low &= sup_phy_type_low; + pcfg.phy_type_low = cpu_to_le64(phy_type_low); + phy_type_high &= sup_phy_type_high; + pcfg.phy_type_high = cpu_to_le64(phy_type_high); + + if (pcfg.phy_type_high != pcaps.phy_type_high || + pcfg.phy_type_low != pcaps.phy_type_low || + pcfg.caps != pcaps.caps) { + pcfg.caps |= IXGBE_ACI_PHY_ENA_LINK; + pcfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT; + + err = ixgbe_aci_set_phy_cfg(hw, &pcfg); + if (err) + return err; + } + + return 0; +} + +/** + * ixgbe_set_phy_power_e610 - Control power for copper PHY + * @hw: pointer to hardware structure + * @on: true for on, false for off + * + * Set the power on/off of the PHY + * by getting its capabilities and setting the appropriate + * configuration parameters. + * + * Return: the exit code of the operation. + */ +int ixgbe_set_phy_power_e610(struct ixgbe_hw *hw, bool on) +{ + struct ixgbe_aci_cmd_get_phy_caps_data phy_caps = {}; + struct ixgbe_aci_cmd_set_phy_cfg_data phy_cfg = {}; + int err; + + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_ACTIVE_CFG, + &phy_caps); + if (err) + return err; + + ixgbe_copy_phy_caps_to_cfg(&phy_caps, &phy_cfg); + + if (on) + phy_cfg.caps &= ~IXGBE_ACI_PHY_ENA_LOW_POWER; + else + phy_cfg.caps |= IXGBE_ACI_PHY_ENA_LOW_POWER; + + /* PHY is already in requested power mode. */ + if (phy_caps.caps == phy_cfg.caps) + return 0; + + phy_cfg.caps |= IXGBE_ACI_PHY_ENA_LINK; + phy_cfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT; + + return ixgbe_aci_set_phy_cfg(hw, &phy_cfg); +} + +/** + * ixgbe_enter_lplu_e610 - Transition to low power states + * @hw: pointer to hardware structure + * + * Configures Low Power Link Up on transition to low power states + * (from D0 to non-D0). Link is required to enter LPLU so avoid resetting the + * X557 PHY immediately prior to entering LPLU. + * + * Return: the exit code of the operation. + */ +int ixgbe_enter_lplu_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data phy_caps = {}; + struct ixgbe_aci_cmd_set_phy_cfg_data phy_cfg = {}; + int err; + + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_ACTIVE_CFG, + &phy_caps); + if (err) + return err; + + ixgbe_copy_phy_caps_to_cfg(&phy_caps, &phy_cfg); + + phy_cfg.low_power_ctrl_an |= IXGBE_ACI_PHY_EN_D3COLD_LOW_POWER_AUTONEG; + + return ixgbe_aci_set_phy_cfg(hw, &phy_cfg); +} + +/** + * ixgbe_init_eeprom_params_e610 - Initialize EEPROM params + * @hw: pointer to hardware structure + * + * Initialize the EEPROM parameters ixgbe_eeprom_info within the ixgbe_hw + * struct in order to set up EEPROM access. + * + * Return: the operation exit code. + */ +int ixgbe_init_eeprom_params_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_eeprom_info *eeprom = &hw->eeprom; + u32 gens_stat; + u8 sr_size; + + if (eeprom->type != ixgbe_eeprom_uninitialized) + return 0; + + eeprom->type = ixgbe_flash; + + gens_stat = IXGBE_READ_REG(hw, GLNVM_GENS); + sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat); + + /* Switching to words (sr_size contains power of 2). */ + eeprom->word_size = BIT(sr_size) * IXGBE_SR_WORDS_IN_1KB; + + hw_dbg(hw, "Eeprom params: type = %d, size = %d\n", eeprom->type, + eeprom->word_size); + + return 0; +} + +/** + * ixgbe_aci_get_netlist_node - get a node handle + * @hw: pointer to the hw struct + * @cmd: get_link_topo AQ structure + * @node_part_number: output node part number if node found + * @node_handle: output node handle parameter if node found + * + * Get the netlist node and assigns it to + * the provided handle using ACI command (0x06E0). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_get_link_topo *cmd, + u8 *node_part_number, u16 *node_handle) +{ + struct ixgbe_aci_desc desc; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo); + desc.params.get_link_topo = *cmd; + + if (ixgbe_aci_send_cmd(hw, &desc, NULL, 0)) + return -EOPNOTSUPP; + + if (node_handle) + *node_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + if (node_part_number) + *node_part_number = desc.params.get_link_topo.node_part_num; + + return 0; +} + +/** + * ixgbe_acquire_nvm - Generic request for acquiring the NVM ownership + * @hw: pointer to the HW structure + * @access: NVM access type (read or write) + * + * Request NVM ownership. + * + * Return: the exit code of the operation. + */ +int ixgbe_acquire_nvm(struct ixgbe_hw *hw, + enum ixgbe_aci_res_access_type access) +{ + u32 fla; + + /* Skip if we are in blank NVM programming mode */ + fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA); + if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0) + return 0; + + return ixgbe_acquire_res(hw, IXGBE_NVM_RES_ID, access, + IXGBE_NVM_TIMEOUT); +} + +/** + * ixgbe_release_nvm - Generic request for releasing the NVM ownership + * @hw: pointer to the HW structure + * + * Release NVM ownership. + */ +void ixgbe_release_nvm(struct ixgbe_hw *hw) +{ + u32 fla; + + /* Skip if we are in blank NVM programming mode */ + fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA); + if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0) + return; + + ixgbe_release_res(hw, IXGBE_NVM_RES_ID); +} + +/** + * ixgbe_aci_read_nvm - read NVM + * @hw: pointer to the HW struct + * @module_typeid: module pointer location in words from the NVM beginning + * @offset: byte offset from the module beginning + * @length: length of the section to be read (in bytes from the offset) + * @data: command buffer (size [bytes] = length) + * @last_command: tells if this is the last command in a series + * @read_shadow_ram: tell if this is a shadow RAM read + * + * Read the NVM using ACI command (0x0701). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, + bool read_shadow_ram) +{ + struct ixgbe_aci_cmd_nvm *cmd; + struct ixgbe_aci_desc desc; + + if (offset > IXGBE_ACI_NVM_MAX_OFFSET) + return -EINVAL; + + cmd = &desc.params.nvm; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_read); + + if (!read_shadow_ram && module_typeid == IXGBE_ACI_NVM_START_POINT) + cmd->cmd_flags |= IXGBE_ACI_NVM_FLASH_ONLY; + + /* If this is the last command in a series, set the proper flag. */ + if (last_command) + cmd->cmd_flags |= IXGBE_ACI_NVM_LAST_CMD; + cmd->module_typeid = cpu_to_le16(module_typeid); + cmd->offset_low = cpu_to_le16(offset & 0xFFFF); + cmd->offset_high = (offset >> 16) & 0xFF; + cmd->length = cpu_to_le16(length); + + return ixgbe_aci_send_cmd(hw, &desc, data, length); +} + +/** + * ixgbe_nvm_validate_checksum - validate checksum + * @hw: pointer to the HW struct + * + * Verify NVM PFA checksum validity using ACI command (0x0706). + * If the checksum verification failed, IXGBE_ERR_NVM_CHECKSUM is returned. + * The function acquires and then releases the NVM ownership. + * + * Return: the exit code of the operation. + */ +int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_nvm_checksum *cmd; + struct ixgbe_aci_desc desc; + int err; + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + cmd = &desc.params.nvm_checksum; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_checksum); + cmd->flags = IXGBE_ACI_NVM_CHECKSUM_VERIFY; + + err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0); + + ixgbe_release_nvm(hw); + + if (!err && cmd->checksum != + cpu_to_le16(IXGBE_ACI_NVM_CHECKSUM_CORRECT)) { + struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter, + hw); + + err = -EIO; + netdev_err(adapter->netdev, "Invalid Shadow Ram checksum"); + } + + return err; +} + +/** + * ixgbe_read_sr_word_aci - Reads Shadow RAM via ACI + * @hw: pointer to the HW structure + * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF) + * @data: word read from the Shadow RAM + * + * Reads one 16 bit word from the Shadow RAM using ixgbe_read_flat_nvm. + * + * Return: the exit code of the operation. + */ +int ixgbe_read_sr_word_aci(struct ixgbe_hw *hw, u16 offset, u16 *data) +{ + u32 bytes = sizeof(u16); + u16 data_local; + int err; + + err = ixgbe_read_flat_nvm(hw, offset * sizeof(u16), &bytes, + (u8 *)&data_local, true); + if (err) + return err; + + *data = data_local; + return 0; +} + +/** + * ixgbe_read_flat_nvm - Read portion of NVM by flat offset + * @hw: pointer to the HW struct + * @offset: offset from beginning of NVM + * @length: (in) number of bytes to read; (out) number of bytes actually read + * @data: buffer to return data in (sized to fit the specified length) + * @read_shadow_ram: if true, read from shadow RAM instead of NVM + * + * Reads a portion of the NVM, as a flat memory space. This function correctly + * breaks read requests across Shadow RAM sectors, prevents Shadow RAM size + * from being exceeded in case of Shadow RAM read requests and ensures that no + * single read request exceeds the maximum 4KB read for a single admin command. + * + * Returns an error code on failure. Note that the data pointer may be + * partially updated if some reads succeed before a failure. + * + * Return: the exit code of the operation. + */ +int ixgbe_read_flat_nvm(struct ixgbe_hw *hw, u32 offset, u32 *length, + u8 *data, bool read_shadow_ram) +{ + u32 inlen = *length; + u32 bytes_read = 0; + bool last_cmd; + int err; + + /* Verify the length of the read if this is for the Shadow RAM */ + if (read_shadow_ram && ((offset + inlen) > + (hw->eeprom.word_size * 2u))) + return -EINVAL; + + do { + u32 read_size, sector_offset; + + /* ixgbe_aci_read_nvm cannot read more than 4KB at a time. + * Additionally, a read from the Shadow RAM may not cross over + * a sector boundary. Conveniently, the sector size is also 4KB. + */ + sector_offset = offset % IXGBE_ACI_MAX_BUFFER_SIZE; + read_size = min_t(u32, + IXGBE_ACI_MAX_BUFFER_SIZE - sector_offset, + inlen - bytes_read); + + last_cmd = !(bytes_read + read_size < inlen); + + /* ixgbe_aci_read_nvm takes the length as a u16. Our read_size + * is calculated using a u32, but the IXGBE_ACI_MAX_BUFFER_SIZE + * maximum size guarantees that it will fit within the 2 bytes. + */ + err = ixgbe_aci_read_nvm(hw, IXGBE_ACI_NVM_START_POINT, + offset, (u16)read_size, + data + bytes_read, last_cmd, + read_shadow_ram); + if (err) + break; + + bytes_read += read_size; + offset += read_size; + } while (!last_cmd); + + *length = bytes_read; + return err; +} + +/** + * ixgbe_read_sr_buf_aci - Read Shadow RAM buffer via ACI + * @hw: pointer to the HW structure + * @offset: offset of the Shadow RAM words to read (0x000000 - 0x001FFF) + * @words: (in) number of words to read; (out) number of words actually read + * @data: words read from the Shadow RAM + * + * Read 16 bit words (data buf) from the Shadow RAM. Acquire/release the NVM + * ownership. + * + * Return: the operation exit code. + */ +int ixgbe_read_sr_buf_aci(struct ixgbe_hw *hw, u16 offset, u16 *words, + u16 *data) +{ + u32 bytes = *words * 2; + int err; + + err = ixgbe_read_flat_nvm(hw, offset * 2, &bytes, (u8 *)data, true); + if (err) + return err; + + *words = bytes / 2; + + for (int i = 0; i < *words; i++) + data[i] = le16_to_cpu(((__le16 *)data)[i]); + + return 0; +} + +/** + * ixgbe_read_ee_aci_e610 - Read EEPROM word using the admin command. + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM using the ACI. + * If the EEPROM params are not initialized, the function + * initialize them before proceeding with reading. + * The function acquires and then releases the NVM ownership. + * + * Return: the exit code of the operation. + */ +int ixgbe_read_ee_aci_e610(struct ixgbe_hw *hw, u16 offset, u16 *data) +{ + int err; + + if (hw->eeprom.type == ixgbe_eeprom_uninitialized) { + err = hw->eeprom.ops.init_params(hw); + if (err) + return err; + } + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + err = ixgbe_read_sr_word_aci(hw, offset, data); + ixgbe_release_nvm(hw); + + return err; +} + +/** + * ixgbe_read_ee_aci_buffer_e610 - Read EEPROM words via ACI + * @hw: pointer to hardware structure + * @offset: offset of words in the EEPROM to read + * @words: number of words to read + * @data: words to read from the EEPROM + * + * Read 16 bit words from the EEPROM via the ACI. Initialize the EEPROM params + * prior to the read. Acquire/release the NVM ownership. + * + * Return: the operation exit code. + */ +int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data) +{ + int err; + + if (hw->eeprom.type == ixgbe_eeprom_uninitialized) { + err = hw->eeprom.ops.init_params(hw); + if (err) + return err; + } + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + err = ixgbe_read_sr_buf_aci(hw, offset, &words, data); + ixgbe_release_nvm(hw); + + return err; +} + +/** + * ixgbe_validate_eeprom_checksum_e610 - Validate EEPROM checksum + * @hw: pointer to hardware structure + * @checksum_val: calculated checksum + * + * Performs checksum calculation and validates the EEPROM checksum. If the + * caller does not need checksum_val, the value can be NULL. + * If the EEPROM params are not initialized, the function + * initialize them before proceeding. + * The function acquires and then releases the NVM ownership. + * + * Return: the exit code of the operation. + */ +int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val) +{ + int err; + + if (hw->eeprom.type == ixgbe_eeprom_uninitialized) { + err = hw->eeprom.ops.init_params(hw); + if (err) + return err; + } + + err = ixgbe_nvm_validate_checksum(hw); + if (err) + return err; + + if (checksum_val) { + u16 tmp_checksum; + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + err = ixgbe_read_sr_word_aci(hw, E610_SR_SW_CHECKSUM_WORD, + &tmp_checksum); + ixgbe_release_nvm(hw); + + if (!err) + *checksum_val = tmp_checksum; + } + + return err; +} + +/** + * ixgbe_reset_hw_e610 - Perform hardware reset + * @hw: pointer to hardware structure + * + * Resets the hardware by resetting the transmit and receive units, masks + * and clears all interrupts, and performs a reset. + * + * Return: the exit code of the operation. + */ +int ixgbe_reset_hw_e610(struct ixgbe_hw *hw) +{ + u32 swfw_mask = hw->phy.phy_semaphore_mask; + u32 ctrl, i; + int err; + + /* Call adapter stop to disable tx/rx and clear interrupts */ + err = hw->mac.ops.stop_adapter(hw); + if (err) + goto reset_hw_out; + + /* Flush pending Tx transactions. */ + ixgbe_clear_tx_pending(hw); + + hw->phy.ops.init(hw); +mac_reset_top: + err = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (err) + return -EBUSY; + ctrl = IXGBE_CTRL_RST; + ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); + IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl); + IXGBE_WRITE_FLUSH(hw); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + + /* Poll for reset bit to self-clear indicating reset is complete */ + for (i = 0; i < 10; i++) { + udelay(1); + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); + if (!(ctrl & IXGBE_CTRL_RST_MASK)) + break; + } + + if (ctrl & IXGBE_CTRL_RST_MASK) { + struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter, + hw); + + err = -EIO; + netdev_err(adapter->netdev, "Reset polling failed to complete."); + } + + /* Double resets are required for recovery from certain error + * conditions. Between resets, it is necessary to stall to allow time + * for any pending HW events to complete. + */ + msleep(100); + if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) { + hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + goto mac_reset_top; + } + + /* Set the Rx packet buffer size. */ + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(0), GENMASK(18, 17)); + + /* Store the permanent mac address */ + hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr); + + /* Maximum number of Receive Address Registers. */ +#define IXGBE_MAX_NUM_RAR 128 + + /* Store MAC address from RAR0, clear receive address registers, and + * clear the multicast table. Also reset num_rar_entries to the + * maximum number of Receive Address Registers, since we modify this + * value when programming the SAN MAC address. + */ + hw->mac.num_rar_entries = IXGBE_MAX_NUM_RAR; + hw->mac.ops.init_rx_addrs(hw); + + /* Initialize bus function number */ + hw->mac.ops.set_lan_id(hw); + +reset_hw_out: + return err; +} + +static const struct ixgbe_mac_operations mac_ops_e610 = { + .init_hw = ixgbe_init_hw_generic, + .start_hw = ixgbe_start_hw_X540, + .clear_hw_cntrs = ixgbe_clear_hw_cntrs_generic, + .enable_rx_dma = ixgbe_enable_rx_dma_generic, + .get_mac_addr = ixgbe_get_mac_addr_generic, + .get_device_caps = ixgbe_get_device_caps_generic, + .stop_adapter = ixgbe_stop_adapter_generic, + .set_lan_id = ixgbe_set_lan_id_multi_port_pcie, + .set_rxpba = ixgbe_set_rxpba_generic, + .check_link = ixgbe_check_link_e610, + .blink_led_start = ixgbe_blink_led_start_X540, + .blink_led_stop = ixgbe_blink_led_stop_X540, + .set_rar = ixgbe_set_rar_generic, + .clear_rar = ixgbe_clear_rar_generic, + .set_vmdq = ixgbe_set_vmdq_generic, + .set_vmdq_san_mac = ixgbe_set_vmdq_san_mac_generic, + .clear_vmdq = ixgbe_clear_vmdq_generic, + .init_rx_addrs = ixgbe_init_rx_addrs_generic, + .update_mc_addr_list = ixgbe_update_mc_addr_list_generic, + .enable_mc = ixgbe_enable_mc_generic, + .disable_mc = ixgbe_disable_mc_generic, + .clear_vfta = ixgbe_clear_vfta_generic, + .set_vfta = ixgbe_set_vfta_generic, + .fc_enable = ixgbe_fc_enable_generic, + .set_fw_drv_ver = ixgbe_set_fw_drv_ver_x550, + .init_uta_tables = ixgbe_init_uta_tables_generic, + .set_mac_anti_spoofing = ixgbe_set_mac_anti_spoofing, + .set_vlan_anti_spoofing = ixgbe_set_vlan_anti_spoofing, + .set_source_address_pruning = + ixgbe_set_source_address_pruning_x550, + .set_ethertype_anti_spoofing = + ixgbe_set_ethertype_anti_spoofing_x550, + .disable_rx_buff = ixgbe_disable_rx_buff_generic, + .enable_rx_buff = ixgbe_enable_rx_buff_generic, + .enable_rx = ixgbe_enable_rx_generic, + .disable_rx = ixgbe_disable_rx_e610, + .led_on = ixgbe_led_on_generic, + .led_off = ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .reset_hw = ixgbe_reset_hw_e610, + .get_media_type = ixgbe_get_media_type_e610, + .setup_link = ixgbe_setup_link_e610, + .get_link_capabilities = ixgbe_get_link_capabilities_e610, + .get_bus_info = ixgbe_get_bus_info_generic, + .acquire_swfw_sync = ixgbe_acquire_swfw_sync_X540, + .release_swfw_sync = ixgbe_release_swfw_sync_X540, + .init_swfw_sync = ixgbe_init_swfw_sync_X540, + .prot_autoc_read = prot_autoc_read_generic, + .prot_autoc_write = prot_autoc_write_generic, + .setup_fc = ixgbe_setup_fc_e610, + .fc_autoneg = ixgbe_fc_autoneg_e610, +}; + +static const struct ixgbe_phy_operations phy_ops_e610 = { + .init = ixgbe_init_phy_ops_e610, + .identify = ixgbe_identify_phy_e610, + .identify_sfp = ixgbe_identify_module_e610, + .setup_link_speed = ixgbe_setup_phy_link_speed_generic, + .setup_link = ixgbe_setup_phy_link_e610, + .enter_lplu = ixgbe_enter_lplu_e610, +}; + +static const struct ixgbe_eeprom_operations eeprom_ops_e610 = { + .read = ixgbe_read_ee_aci_e610, + .read_buffer = ixgbe_read_ee_aci_buffer_e610, + .validate_checksum = ixgbe_validate_eeprom_checksum_e610, +}; + +const struct ixgbe_info ixgbe_e610_info = { + .mac = ixgbe_mac_e610, + .get_invariants = ixgbe_get_invariants_X540, + .mac_ops = &mac_ops_e610, + .eeprom_ops = &eeprom_ops_e610, + .phy_ops = &phy_ops_e610, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_x550em_a, +}; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h new file mode 100644 index 000000000000..ba8c06b73810 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IXGBE_E610_H_ +#define _IXGBE_E610_H_ + +#include "ixgbe_type.h" + +int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct ixgbe_aci_desc *desc, + void *buf, u16 buf_size); +bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw); +int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e, + bool *pending); +void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode); +int ixgbe_acquire_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res, + enum ixgbe_aci_res_access_type access, u32 timeout); +void ixgbe_release_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res); +int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size, + u32 *cap_count, enum ixgbe_aci_opc opc); +int ixgbe_discover_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_caps); +int ixgbe_discover_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_caps); +int ixgbe_get_caps(struct ixgbe_hw *hw); +int ixgbe_aci_disable_rxen(struct ixgbe_hw *hw); +int ixgbe_aci_get_phy_caps(struct ixgbe_hw *hw, bool qual_mods, u8 report_mode, + struct ixgbe_aci_cmd_get_phy_caps_data *pcaps); +void ixgbe_copy_phy_caps_to_cfg(struct ixgbe_aci_cmd_get_phy_caps_data *caps, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg); +int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg); +int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link); +int ixgbe_update_link_info(struct ixgbe_hw *hw); +int ixgbe_get_link_status(struct ixgbe_hw *hw, bool *link_up); +int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse, + struct ixgbe_link_status *link); +int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask); +int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask); +enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw); +int ixgbe_setup_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed speed, + bool autoneg_wait); +int ixgbe_check_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed *speed, + bool *link_up, bool link_up_wait_to_complete); +int ixgbe_get_link_capabilities_e610(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg); +int ixgbe_cfg_phy_fc(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg, + enum ixgbe_fc_mode req_mode); +int ixgbe_setup_fc_e610(struct ixgbe_hw *hw); +void ixgbe_fc_autoneg_e610(struct ixgbe_hw *hw); +void ixgbe_disable_rx_e610(struct ixgbe_hw *hw); +int ixgbe_init_phy_ops_e610(struct ixgbe_hw *hw); +int ixgbe_identify_phy_e610(struct ixgbe_hw *hw); +int ixgbe_identify_module_e610(struct ixgbe_hw *hw); +int ixgbe_setup_phy_link_e610(struct ixgbe_hw *hw); +int ixgbe_set_phy_power_e610(struct ixgbe_hw *hw, bool on); +int ixgbe_enter_lplu_e610(struct ixgbe_hw *hw); +int ixgbe_init_eeprom_params_e610(struct ixgbe_hw *hw); +int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_get_link_topo *cmd, + u8 *node_part_number, u16 *node_handle); +int ixgbe_acquire_nvm(struct ixgbe_hw *hw, + enum ixgbe_aci_res_access_type access); +void ixgbe_release_nvm(struct ixgbe_hw *hw); +int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, + bool read_shadow_ram); +int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw); +int ixgbe_read_sr_word_aci(struct ixgbe_hw *hw, u16 offset, u16 *data); +int ixgbe_read_flat_nvm(struct ixgbe_hw *hw, u32 offset, u32 *length, + u8 *data, bool read_shadow_ram); +int ixgbe_read_sr_buf_aci(struct ixgbe_hw *hw, u16 offset, u16 *words, + u16 *data); +int ixgbe_read_ee_aci_e610(struct ixgbe_hw *hw, u16 offset, u16 *data); +int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data); +int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val); +int ixgbe_reset_hw_e610(struct ixgbe_hw *hw); + +#endif /* _IXGBE_E610_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 9482e0cca8b7..da91c582d439 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ /* ethtool support for ixgbe */ @@ -690,6 +690,7 @@ static void ixgbe_get_regs(struct net_device *netdev, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL_82599(i)); regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH_82599(i)); break; @@ -1613,6 +1614,7 @@ static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: toggle = 0x7FFFF30F; test = reg_test_82599; break; @@ -1874,6 +1876,7 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_DMATXCTL); reg_data |= IXGBE_DMATXCTL_TE; IXGBE_WRITE_REG(&adapter->hw, IXGBE_DMATXCTL, reg_data); @@ -1935,6 +1938,7 @@ static int ixgbe_setup_loopback_test(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: reg_data = IXGBE_READ_REG(hw, IXGBE_MACC); reg_data |= IXGBE_MACC_FLU; IXGBE_WRITE_REG(hw, IXGBE_MACC, reg_data); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 16fa621ce0ff..336d47ffb95a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include "ixgbe.h" #include "ixgbe_sriov.h" @@ -107,6 +107,7 @@ static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (num_tcs > 4) { /* * TCs : TC0/1 TC2/3 TC4-7 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 2e38e8f6fac1..7236f20c9a30 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include #include @@ -42,6 +42,7 @@ #include "ixgbe.h" #include "ixgbe_common.h" +#include "ixgbe_e610.h" #include "ixgbe_dcb_82599.h" #include "ixgbe_mbx.h" #include "ixgbe_phy.h" @@ -73,6 +74,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = { [board_x550em_x_fw] = &ixgbe_x550em_x_fw_info, [board_x550em_a] = &ixgbe_x550em_a_info, [board_x550em_a_fw] = &ixgbe_x550em_a_fw_info, + [board_e610] = &ixgbe_e610_info, }; /* ixgbe_pci_tbl - PCI Device ID Table @@ -131,6 +133,11 @@ static const struct pci_device_id ixgbe_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP), board_x550em_a }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T), board_x550em_a_fw }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T_L), board_x550em_a_fw }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_BACKPLANE), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SFP), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_10G_T), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_2_5G_T), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SGMII), board_e610}, /* required last entry */ {0, } }; @@ -173,6 +180,8 @@ static struct workqueue_struct *ixgbe_wq; static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev); static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *); +static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *); +static void ixgbe_watchdog_update_link(struct ixgbe_adapter *); static const struct net_device_ops ixgbe_netdev_ops; @@ -236,8 +245,11 @@ static int ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter) * bandwidth details should be gathered from the parent bus instead of from the * device. Used to ensure that various locations all have the correct device ID * checks. + * + * Return: true if information should be collected from the parent bus, false + * otherwise */ -static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw) +static bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw) { switch (hw->device_id) { case IXGBE_DEV_ID_82599_SFP_SF_QP: @@ -876,6 +888,7 @@ static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (direction == -1) { /* other causes */ msix_vector |= IXGBE_IVAR_ALLOC_VAL; @@ -915,6 +928,7 @@ void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: mask = (qmask & 0xFFFFFFFF); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask); mask = (qmask >> 32); @@ -1025,7 +1039,7 @@ static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring) return ((head <= tail) ? tail : tail + ring->count) - head; } -static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring) +static bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring) { u32 tx_done = ixgbe_get_tx_completed(tx_ring); u32 tx_done_old = tx_ring->tx_stats.tx_done_old; @@ -1909,10 +1923,6 @@ bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, { struct net_device *netdev = rx_ring->netdev; - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - /* Verify netdev is present, and that packet does not have any * errors that would be unacceptable to the netdev. */ @@ -2220,9 +2230,9 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, - struct ixgbe_ring *rx_ring, - struct xdp_buff *xdp) +static int ixgbe_run_xdp(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) { int err, result = IXGBE_XDP_PASS; struct bpf_prog *xdp_prog; @@ -2272,7 +2282,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring, @@ -2330,6 +2340,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, unsigned int offset = rx_ring->rx_offset; unsigned int xdp_xmit = 0; struct xdp_buff xdp; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -2375,12 +2386,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, size); #endif - skb = ixgbe_run_xdp(adapter, rx_ring, &xdp); + xdp_res = ixgbe_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { xdp_xmit |= xdp_res; ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -2400,7 +2409,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; rx_buffer->pagecnt_bias++; break; @@ -2414,7 +2423,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, continue; /* verify the packet layout is correct */ - if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) + if (xdp_res || ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) continue; /* probably a little skewed due to removing CRC */ @@ -2515,6 +2524,7 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: ixgbe_set_ivar(adapter, -1, 1, v_idx); break; default: @@ -2528,6 +2538,9 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) IXGBE_EIMS_MAILBOX | IXGBE_EIMS_LSC); + if (adapter->hw.mac.type == ixgbe_mac_e610) + mask &= ~IXGBE_EIMS_FW_EVENT; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask); } @@ -2744,6 +2757,7 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* * set the WDIS bit to not clear the timer bits and cause an * immediate assertion of the interrupt @@ -2966,6 +2980,218 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter) } } +/** + * ixgbe_check_phy_fw_load - check if PHY FW load failed + * @adapter: pointer to adapter structure + * @link_cfg_err: bitmap from the link info structure + * + * Check if external PHY FW load failed and print an error message if it did. + */ +static void ixgbe_check_phy_fw_load(struct ixgbe_adapter *adapter, + u8 link_cfg_err) +{ + if (!(link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE)) { + adapter->flags2 &= ~IXGBE_FLAG2_PHY_FW_LOAD_FAILED; + return; + } + + if (adapter->flags2 & IXGBE_FLAG2_PHY_FW_LOAD_FAILED) + return; + + if (link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE) { + netdev_err(adapter->netdev, "Device failed to load the FW for the external PHY. Please download and install the latest NVM for your device and try again\n"); + adapter->flags2 |= IXGBE_FLAG2_PHY_FW_LOAD_FAILED; + } +} + +/** + * ixgbe_check_module_power - check module power level + * @adapter: pointer to adapter structure + * @link_cfg_err: bitmap from the link info structure + * + * Check module power level returned by a previous call to aci_get_link_info + * and print error messages if module power level is not supported. + */ +static void ixgbe_check_module_power(struct ixgbe_adapter *adapter, + u8 link_cfg_err) +{ + /* If module power level is supported, clear the flag. */ + if (!(link_cfg_err & (IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT | + IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED))) { + adapter->flags2 &= ~IXGBE_FLAG2_MOD_POWER_UNSUPPORTED; + return; + } + + /* If IXGBE_FLAG2_MOD_POWER_UNSUPPORTED was previously set and the + * above block didn't clear this bit, there's nothing to do. + */ + if (adapter->flags2 & IXGBE_FLAG2_MOD_POWER_UNSUPPORTED) + return; + + if (link_cfg_err & IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT) { + netdev_err(adapter->netdev, "The installed module is incompatible with the device's NVM image. Cannot start link.\n"); + adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED; + } else if (link_cfg_err & IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED) { + netdev_err(adapter->netdev, "The module's power requirements exceed the device's power supply. Cannot start link.\n"); + adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED; + } +} + +/** + * ixgbe_check_link_cfg_err - check if link configuration failed + * @adapter: pointer to adapter structure + * @link_cfg_err: bitmap from the link info structure + * + * Print if any link configuration failure happens due to the value in the + * link_cfg_err parameter in the link info structure. + */ +static void ixgbe_check_link_cfg_err(struct ixgbe_adapter *adapter, + u8 link_cfg_err) +{ + ixgbe_check_module_power(adapter, link_cfg_err); + ixgbe_check_phy_fw_load(adapter, link_cfg_err); +} + +/** + * ixgbe_process_link_status_event - process the link event + * @adapter: pointer to adapter structure + * @link_up: true if the physical link is up and false if it is down + * @link_speed: current link speed received from the link event + * + * Return: 0 on success or negative value on failure. + */ +static int +ixgbe_process_link_status_event(struct ixgbe_adapter *adapter, bool link_up, + u16 link_speed) +{ + struct ixgbe_hw *hw = &adapter->hw; + int status; + + /* Update the link info structures and re-enable link events, + * don't bail on failure due to other book keeping needed. + */ + status = ixgbe_update_link_info(hw); + if (status) + e_dev_err("Failed to update link status, err %d aq_err %d\n", + status, hw->aci.last_status); + + ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err); + + /* Check if the link state is up after updating link info, and treat + * this event as an UP event since the link is actually UP now. + */ + if (hw->link.link_info.link_info & IXGBE_ACI_LINK_UP) + link_up = true; + + /* Turn off PHY if media was removed. */ + if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA) && + !(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE)) + adapter->flags2 |= IXGBE_FLAG2_NO_MEDIA; + + if (link_up == adapter->link_up && + link_up == netif_carrier_ok(adapter->netdev) && + link_speed == adapter->link_speed) + return 0; + + adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; + adapter->link_check_timeout = jiffies; + ixgbe_watchdog_update_link(adapter); + + if (link_up) + ixgbe_watchdog_link_is_up(adapter); + else + ixgbe_watchdog_link_is_down(adapter); + + return 0; +} + +/** + * ixgbe_handle_link_status_event - handle link status event via ACI + * @adapter: pointer to adapter structure + * @e: event structure containing link status info + */ +static void +ixgbe_handle_link_status_event(struct ixgbe_adapter *adapter, + struct ixgbe_aci_event *e) +{ + struct ixgbe_aci_cmd_get_link_status_data *link_data; + u16 link_speed; + bool link_up; + + link_data = (struct ixgbe_aci_cmd_get_link_status_data *)e->msg_buf; + + link_up = !!(link_data->link_info & IXGBE_ACI_LINK_UP); + link_speed = le16_to_cpu(link_data->link_speed); + + if (ixgbe_process_link_status_event(adapter, link_up, link_speed)) + e_dev_warn("Could not process link status event"); +} + +/** + * ixgbe_schedule_fw_event - schedule Firmware event + * @adapter: pointer to the adapter structure + * + * If the adapter is not in down, removing or resetting state, + * an event is scheduled. + */ +static void ixgbe_schedule_fw_event(struct ixgbe_adapter *adapter) +{ + if (!test_bit(__IXGBE_DOWN, &adapter->state) && + !test_bit(__IXGBE_REMOVING, &adapter->state) && + !test_bit(__IXGBE_RESETTING, &adapter->state)) { + adapter->flags2 |= IXGBE_FLAG2_FW_ASYNC_EVENT; + ixgbe_service_event_schedule(adapter); + } +} + +/** + * ixgbe_aci_event_cleanup - release msg_buf memory + * @event: pointer to the event holding msg_buf to be released + * + * Clean memory allocated for event's msg_buf. Implements auto memory cleanup. + */ +static void ixgbe_aci_event_cleanup(struct ixgbe_aci_event *event) +{ + kfree(event->msg_buf); +} + +/** + * ixgbe_handle_fw_event - handle Firmware event + * @adapter: pointer to the adapter structure + * + * Obtain an event from the ACI and then and then process it according to the + * type of the event and the opcode. + */ +static void ixgbe_handle_fw_event(struct ixgbe_adapter *adapter) +{ + struct ixgbe_aci_event event __cleanup(ixgbe_aci_event_cleanup); + struct ixgbe_hw *hw = &adapter->hw; + bool pending = false; + int err; + + if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT) + adapter->flags2 &= ~IXGBE_FLAG2_FW_ASYNC_EVENT; + event.buf_len = IXGBE_ACI_MAX_BUFFER_SIZE; + event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); + if (!event.msg_buf) + return; + + do { + err = ixgbe_aci_get_event(hw, &event, &pending); + if (err) + break; + + switch (le16_to_cpu(event.desc.opcode)) { + case ixgbe_aci_opc_get_link_status: + ixgbe_handle_link_status_event(adapter, &event); + break; + default: + e_warn(hw, "unknown FW async event captured\n"); + break; + } + } while (pending); +} + static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, u64 qmask) { @@ -2982,6 +3208,7 @@ static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: mask = (qmask & 0xFFFFFFFF); if (mask) IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); @@ -3035,6 +3262,9 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues, case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: + case ixgbe_mac_e610: + mask |= IXGBE_EIMS_FW_EVENT; + fallthrough; case ixgbe_mac_x550em_a: if (adapter->hw.device_id == IXGBE_DEV_ID_X550EM_X_SFP || adapter->hw.device_id == IXGBE_DEV_ID_X550EM_A_SFP || @@ -3091,12 +3321,16 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data) if (eicr & IXGBE_EICR_MAILBOX) ixgbe_msg_task(adapter); + if (eicr & IXGBE_EICR_FW_EVENT) + ixgbe_schedule_fw_event(adapter); + switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (hw->phy.type == ixgbe_phy_x550em_ext_t && (eicr & IXGBE_EICR_GPI_SDP0_X540)) { adapter->flags2 |= IXGBE_FLAG2_PHY_INTERRUPT; @@ -3334,6 +3568,9 @@ static irqreturn_t ixgbe_intr(int irq, void *data) if (eicr & IXGBE_EICR_LSC) ixgbe_check_lsc(adapter); + if (eicr & IXGBE_EICR_FW_EVENT) + ixgbe_schedule_fw_event(adapter); + switch (hw->mac.type) { case ixgbe_mac_82599EB: ixgbe_check_sfp_event(adapter, eicr); @@ -3342,6 +3579,7 @@ static irqreturn_t ixgbe_intr(int irq, void *data) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (eicr & IXGBE_EICR_ECC) { e_info(link, "Received ECC Err, initiating reset\n"); set_bit(__IXGBE_RESET_REQUESTED, &adapter->state); @@ -3442,6 +3680,7 @@ static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0); @@ -4359,6 +4598,7 @@ static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (adapter->num_vfs) rdrxctl |= IXGBE_RDRXCTL_PSP; fallthrough; @@ -4526,6 +4766,7 @@ static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbe_ring *ring = adapter->rx_ring[i]; @@ -4564,6 +4805,7 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbe_ring *ring = adapter->rx_ring[i]; @@ -5148,6 +5390,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: dv_id = IXGBE_DV_X540(link, tc); break; default: @@ -5208,6 +5451,7 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: dv_id = IXGBE_LOW_DV_X540(tc); break; default: @@ -5509,6 +5753,48 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) ixgbe_configure_dfwd(adapter); } +/** + * ixgbe_enable_link_status_events - enable link status events + * @adapter: pointer to the adapter structure + * @mask: event mask to be set + * + * Enables link status events by invoking ixgbe_configure_lse() + * + * Return: the exit code of the operation. + */ +static int ixgbe_enable_link_status_events(struct ixgbe_adapter *adapter, + u16 mask) +{ + int err; + + err = ixgbe_configure_lse(&adapter->hw, true, mask); + if (err) + return err; + + adapter->lse_mask = mask; + return 0; +} + +/** + * ixgbe_disable_link_status_events - disable link status events + * @adapter: pointer to the adapter structure + * + * Disables link status events by invoking ixgbe_configure_lse() + * + * Return: the exit code of the operation. + */ +static int ixgbe_disable_link_status_events(struct ixgbe_adapter *adapter) +{ + int err; + + err = ixgbe_configure_lse(&adapter->hw, false, adapter->lse_mask); + if (err) + return err; + + adapter->lse_mask = 0; + return 0; +} + /** * ixgbe_sfp_link_config - set up SFP+ link * @adapter: pointer to private adapter struct @@ -5532,13 +5818,21 @@ static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter) * ixgbe_non_sfp_link_config - set up non-SFP+ link * @hw: pointer to private hardware struct * - * Returns 0 on success, negative on failure + * Configure non-SFP link. + * + * Return: 0 on success, negative on failure **/ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) { - u32 speed; + struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter, + hw); + u16 mask = ~((u16)(IXGBE_ACI_LINK_EVENT_UPDOWN | + IXGBE_ACI_LINK_EVENT_MEDIA_NA | + IXGBE_ACI_LINK_EVENT_MODULE_QUAL_FAIL | + IXGBE_ACI_LINK_EVENT_PHY_FW_LOAD_FAIL)); bool autoneg, link_up = false; int ret = -EIO; + u32 speed; if (hw->mac.ops.check_link) ret = hw->mac.ops.check_link(hw, &speed, &link_up, false); @@ -5561,12 +5855,52 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) if (ret) return ret; - if (hw->mac.ops.setup_link) + if (hw->mac.ops.setup_link) { + if (adapter->hw.mac.type == ixgbe_mac_e610) { + ret = ixgbe_enable_link_status_events(adapter, mask); + if (ret) + return ret; + } ret = hw->mac.ops.setup_link(hw, speed, link_up); + } return ret; } +/** + * ixgbe_check_media_subtask - check for media + * @adapter: pointer to adapter structure + * + * If media is available then initialize PHY user configuration. Configure the + * PHY if the interface is up. + */ +static void ixgbe_check_media_subtask(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + /* No need to check for media if it's already present */ + if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA)) + return; + + /* Refresh link info and check if media is present */ + if (ixgbe_update_link_info(hw)) + return; + + ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err); + + if (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE) { + /* PHY settings are reset on media insertion, reconfigure + * PHY to preserve settings. + */ + if (!(ixgbe_non_sfp_link_config(&adapter->hw))) + adapter->flags2 &= ~IXGBE_FLAG2_NO_MEDIA; + + /* A Link Status Event will be generated; the event handler + * will complete bringing the interface up + */ + } +} + /** * ixgbe_clear_vf_stats_counters - Clear out VF stats after reset * @adapter: board private structure @@ -5630,6 +5964,7 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: default: IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF); IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF); @@ -5980,6 +6315,7 @@ dma_engine_disable: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, (IXGBE_READ_REG(hw, IXGBE_DMATXCTL) & ~IXGBE_DMATXCTL_TE)); @@ -6224,6 +6560,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter) ixgbe_clean_all_tx_rings(adapter); ixgbe_clean_all_rx_rings(adapter); + if (adapter->hw.mac.type == ixgbe_mac_e610) + ixgbe_disable_link_status_events(adapter); } /** @@ -6279,6 +6617,7 @@ static void ixgbe_init_dcb(struct ixgbe_adapter *adapter) break; case ixgbe_mac_X540: case ixgbe_mac_X550: + case ixgbe_mac_e610: adapter->dcb_cfg.num_tcs.pg_tcs = X540_TRAFFIC_CLASS; adapter->dcb_cfg.num_tcs.pfc_tcs = X540_TRAFFIC_CLASS; break; @@ -6342,6 +6681,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, hw->subsystem_vendor_id = pdev->subsystem_vendor; hw->subsystem_device_id = pdev->subsystem_device; + hw->mac.max_link_up_time = IXGBE_LINK_UP_TIME; + /* get_invariants needs the device IDs */ ii->get_invariants(hw); @@ -6909,6 +7250,19 @@ int ixgbe_open(struct net_device *netdev) ixgbe_up_complete(adapter); udp_tunnel_nic_reset_ntf(netdev); + if (adapter->hw.mac.type == ixgbe_mac_e610) { + int err = ixgbe_update_link_info(&adapter->hw); + + if (err) + e_dev_err("Failed to update link info, err %d.\n", err); + + ixgbe_check_link_cfg_err(adapter, + adapter->hw.link.link_info.link_cfg_err); + + err = ixgbe_non_sfp_link_config(&adapter->hw); + if (ixgbe_non_sfp_link_config(&adapter->hw)) + e_dev_err("Link setup failed, err %d.\n", err); + } return 0; @@ -7062,6 +7416,7 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: pci_wake_from_d3(pdev, !!wufc); break; default: @@ -7209,6 +7564,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: hwstats->pxonrxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i)); break; @@ -7221,11 +7577,12 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) for (i = 0; i < 16; i++) { hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i)); hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i)); - if ((hw->mac.type == ixgbe_mac_82599EB) || - (hw->mac.type == ixgbe_mac_X540) || - (hw->mac.type == ixgbe_mac_X550) || - (hw->mac.type == ixgbe_mac_X550EM_x) || - (hw->mac.type == ixgbe_mac_x550em_a)) { + if (hw->mac.type == ixgbe_mac_82599EB || + hw->mac.type == ixgbe_mac_X540 || + hw->mac.type == ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_X550EM_x || + hw->mac.type == ixgbe_mac_x550em_a || + hw->mac.type == ixgbe_mac_e610) { hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i)); IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); /* to clear */ hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i)); @@ -7251,6 +7608,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* OS2BMC stats are X540 and later */ hwstats->o2bgptc += IXGBE_READ_REG(hw, IXGBE_O2BGPTC); hwstats->o2bspc += IXGBE_READ_REG(hw, IXGBE_O2BSPC); @@ -7551,6 +7909,7 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: case ixgbe_mac_82599EB: { u32 mflcn = IXGBE_READ_REG(hw, IXGBE_MFLCN); u32 fccfg = IXGBE_READ_REG(hw, IXGBE_FCCFG); @@ -8052,6 +8411,11 @@ static void ixgbe_service_task(struct work_struct *work) ixgbe_service_event_complete(adapter); return; } + if (adapter->hw.mac.type == ixgbe_mac_e610) { + if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT) + ixgbe_handle_fw_event(adapter); + ixgbe_check_media_subtask(adapter); + } ixgbe_reset_subtask(adapter); ixgbe_phy_interrupt_subtask(adapter); ixgbe_sfp_detection_subtask(adapter); @@ -10770,6 +11134,24 @@ bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, return false; } +/** + * ixgbe_set_fw_version_e610 - Set FW version specifically on E610 adapters + * @adapter: the adapter private structure + * + * This function is used by probe and ethtool to determine the FW version to + * format to display. The FW version is taken from the EEPROM/NVM. + * + */ +static void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter) +{ + struct ixgbe_orom_info *orom = &adapter->hw.flash.orom; + struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm; + + snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + "%x.%02x 0x%x %d.%d.%d", nvm->major, nvm->minor, + nvm->eetrack, orom->major, orom->build, orom->patch); +} + /** * ixgbe_set_fw_version - Set FW version * @adapter: the adapter private structure @@ -10782,6 +11164,11 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_nvm_version nvm_ver; + if (adapter->hw.mac.type == ixgbe_mac_e610) { + ixgbe_set_fw_version_e610(adapter); + return; + } + ixgbe_get_oem_prod_version(hw, &nvm_ver); if (nvm_ver.oem_valid) { snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), @@ -10868,6 +11255,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #else indices = IXGBE_MAX_RSS_INDICES; #endif + } else if (ii->mac == ixgbe_mac_e610) { + indices = IXGBE_MAX_RSS_INDICES_X550; } netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices); @@ -10933,12 +11322,19 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_sw_init; + if (adapter->hw.mac.type == ixgbe_mac_e610) { + err = ixgbe_get_caps(&adapter->hw); + if (err) + dev_err(&pdev->dev, "ixgbe_get_caps failed %d\n", err); + } + if (adapter->hw.mac.type == ixgbe_mac_82599EB) adapter->flags2 |= IXGBE_FLAG2_AUTO_DISABLE_VF; switch (adapter->hw.mac.type) { case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: + case ixgbe_mac_e610: netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550; break; case ixgbe_mac_x550em_a: @@ -10959,6 +11355,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0); break; default: @@ -11130,6 +11527,8 @@ skip_sriov: ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); ixgbe_mac_set_default_filter(adapter); + if (hw->mac.type == ixgbe_mac_e610) + mutex_init(&hw->aci.lock); timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); if (ixgbe_removed(hw->hw_addr)) { @@ -11275,6 +11674,8 @@ err_netdev: err_register: ixgbe_release_hw_control(adapter); ixgbe_clear_interrupt_scheme(adapter); + if (hw->mac.type == ixgbe_mac_e610) + mutex_destroy(&adapter->hw.aci.lock); err_sw_init: ixgbe_disable_sriov(adapter); adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; @@ -11321,6 +11722,11 @@ static void ixgbe_remove(struct pci_dev *pdev) set_bit(__IXGBE_REMOVING, &adapter->state); cancel_work_sync(&adapter->service_task); + if (adapter->hw.mac.type == ixgbe_mac_e610) { + ixgbe_disable_link_status_events(adapter); + mutex_destroy(&adapter->hw.aci.lock); + } + if (adapter->mii_bus) mdiobus_unregister(adapter->mii_bus); @@ -11452,6 +11858,9 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, case ixgbe_mac_x550em_a: device_id = IXGBE_DEV_ID_X550EM_A_VF; break; + case ixgbe_mac_e610: + device_id = IXGBE_DEV_ID_E610_VF; + break; default: device_id = 0; break; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c index d67d77e5dacc..788b5af07c70 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include #include @@ -283,6 +283,7 @@ static int ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: vflre = IXGBE_READ_REG(hw, IXGBE_VFLREC(reg_offset)); break; default: @@ -407,6 +408,7 @@ void ixgbe_init_mbx_params_pf(struct ixgbe_hw *hw) hw->mac.type != ixgbe_mac_X550 && hw->mac.type != ixgbe_mac_X550EM_x && hw->mac.type != ixgbe_mac_x550em_a && + hw->mac.type != ixgbe_mac_e610 && hw->mac.type != ixgbe_mac_X540) return; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 07eaa3c3f4d3..0a03a8bb5f88 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include #include @@ -1117,7 +1117,7 @@ int ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw) hw->phy.ops.read_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, MDIO_MMD_AN, &autoneg_reg); - if (hw->mac.type == ixgbe_mac_X550) { + if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_e610) { /* Set or unset auto-negotiation 5G advertisement */ autoneg_reg &= ~IXGBE_MII_5GBASE_T_ADVERTISE; if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) && @@ -1233,6 +1233,7 @@ static int ixgbe_get_copper_speeds_supported(struct ixgbe_hw *hw) switch (hw->mac.type) { case ixgbe_mac_X550: + case ixgbe_mac_e610: hw->phy.speeds_supported |= IXGBE_LINK_SPEED_2_5GB_FULL; hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL; break; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 9baccacd02a1..5fdf32d79d82 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef _IXGBE_TYPE_H_ #define _IXGBE_TYPE_H_ @@ -7,6 +7,7 @@ #include #include #include +#include "ixgbe_type_e610.h" /* Device IDs */ #define IXGBE_DEV_ID_82598 0x10B6 @@ -71,12 +72,19 @@ #define IXGBE_DEV_ID_X550EM_A_1G_T 0x15E4 #define IXGBE_DEV_ID_X550EM_A_1G_T_L 0x15E5 +#define IXGBE_DEV_ID_E610_BACKPLANE 0x57AE +#define IXGBE_DEV_ID_E610_SFP 0x57AF +#define IXGBE_DEV_ID_E610_10G_T 0x57B0 +#define IXGBE_DEV_ID_E610_2_5G_T 0x57B1 +#define IXGBE_DEV_ID_E610_SGMII 0x57B2 + /* VF Device IDs */ #define IXGBE_DEV_ID_82599_VF 0x10ED #define IXGBE_DEV_ID_X540_VF 0x1515 #define IXGBE_DEV_ID_X550_VF 0x1565 #define IXGBE_DEV_ID_X550EM_X_VF 0x15A8 #define IXGBE_DEV_ID_X550EM_A_VF 0x15C5 +#define IXGBE_DEV_ID_E610_VF 0x57AD #define IXGBE_CAT(r, m) IXGBE_##r##_##m @@ -1600,7 +1608,7 @@ enum { #define IXGBE_EICR_PCI 0x00040000 /* PCI Exception */ #define IXGBE_EICR_MAILBOX 0x00080000 /* VF to PF Mailbox Interrupt */ #define IXGBE_EICR_LSC 0x00100000 /* Link Status Change */ -#define IXGBE_EICR_LINKSEC 0x00200000 /* PN Threshold */ +#define IXGBE_EICR_FW_EVENT 0x00200000 /* Async FW event */ #define IXGBE_EICR_MNG 0x00400000 /* Manageability Event Interrupt */ #define IXGBE_EICR_TS 0x00800000 /* Thermal Sensor Event */ #define IXGBE_EICR_TIMESYNC 0x01000000 /* Timesync Event */ @@ -1636,6 +1644,7 @@ enum { #define IXGBE_EICS_PCI IXGBE_EICR_PCI /* PCI Exception */ #define IXGBE_EICS_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ #define IXGBE_EICS_LSC IXGBE_EICR_LSC /* Link Status Change */ +#define IXGBE_EICS_FW_EVENT IXGBE_EICR_FW_EVENT /* Async FW event */ #define IXGBE_EICS_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ #define IXGBE_EICS_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ #define IXGBE_EICS_GPI_SDP0(_hw) IXGBE_EICR_GPI_SDP0(_hw) @@ -1654,6 +1663,7 @@ enum { #define IXGBE_EIMS_PCI IXGBE_EICR_PCI /* PCI Exception */ #define IXGBE_EIMS_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ #define IXGBE_EIMS_LSC IXGBE_EICR_LSC /* Link Status Change */ +#define IXGBE_EIMS_FW_EVENT IXGBE_EICR_FW_EVENT /* Async FW event */ #define IXGBE_EIMS_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ #define IXGBE_EIMS_TS IXGBE_EICR_TS /* Thermel Sensor Event */ #define IXGBE_EIMS_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ @@ -1673,6 +1683,7 @@ enum { #define IXGBE_EIMC_PCI IXGBE_EICR_PCI /* PCI Exception */ #define IXGBE_EIMC_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ #define IXGBE_EIMC_LSC IXGBE_EICR_LSC /* Link Status Change */ +#define IXGBE_EIMC_FW_EVENT IXGBE_EICR_FW_EVENT /* Async FW event */ #define IXGBE_EIMC_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ #define IXGBE_EIMC_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ #define IXGBE_EIMC_GPI_SDP0(_hw) IXGBE_EICR_GPI_SDP0(_hw) @@ -2068,6 +2079,7 @@ enum { #define IXGBE_SAN_MAC_ADDR_PTR 0x28 #define IXGBE_DEVICE_CAPS 0x2C #define IXGBE_SERIAL_NUMBER_MAC_ADDR 0x11 +#define IXGBE_PCIE_MSIX_E610_CAPS 0xB2 #define IXGBE_PCIE_MSIX_82599_CAPS 0x72 #define IXGBE_MAX_MSIX_VECTORS_82599 0x40 #define IXGBE_PCIE_MSIX_82598_CAPS 0x62 @@ -2168,6 +2180,7 @@ enum { #define IXGBE_PCI_DEVICE_STATUS 0xAA #define IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING 0x0020 #define IXGBE_PCI_LINK_STATUS 0xB2 +#define IXGBE_PCI_LINK_STATUS_E610 0x82 #define IXGBE_PCI_DEVICE_CONTROL2 0xC8 #define IXGBE_PCI_LINK_WIDTH 0x3F0 #define IXGBE_PCI_LINK_WIDTH_1 0x10 @@ -2288,6 +2301,7 @@ enum { #define IXGBE_RXMTRL_V2_MGMT_MSG 0x0D00 #define IXGBE_FCTRL_SBP 0x00000002 /* Store Bad Packet */ +#define IXGBE_FCTRL_TPE 0x00000080 /* Tag Promiscuous Ena*/ #define IXGBE_FCTRL_MPE 0x00000100 /* Multicast Promiscuous Ena*/ #define IXGBE_FCTRL_UPE 0x00000200 /* Unicast Promiscuous Ena */ #define IXGBE_FCTRL_BAM 0x00000400 /* Broadcast Accept Mode */ @@ -2351,6 +2365,7 @@ enum { /* Multiple Transmit Queue Command Register */ #define IXGBE_MTQC_RT_ENA 0x1 /* DCB Enable */ #define IXGBE_MTQC_VT_ENA 0x2 /* VMDQ2 Enable */ +#define IXGBE_MTQC_NUM_TC_OR_Q 0xC /* Number of TCs or TxQs per pool */ #define IXGBE_MTQC_64Q_1PB 0x0 /* 64 queues 1 pack buffer */ #define IXGBE_MTQC_32VF 0x8 /* 4 TX Queues per pool w/32VF's */ #define IXGBE_MTQC_64VF 0x4 /* 2 TX Queues per pool w/64VF's */ @@ -2970,6 +2985,29 @@ typedef u32 ixgbe_link_speed; IXGBE_LINK_SPEED_1GB_FULL | \ IXGBE_LINK_SPEED_10GB_FULL) +/* Physical layer type */ +typedef u64 ixgbe_physical_layer; +#define IXGBE_PHYSICAL_LAYER_UNKNOWN 0 +#define IXGBE_PHYSICAL_LAYER_10GBASE_T 0x00001 +#define IXGBE_PHYSICAL_LAYER_1000BASE_T 0x00002 +#define IXGBE_PHYSICAL_LAYER_100BASE_TX 0x00004 +#define IXGBE_PHYSICAL_LAYER_SFP_PLUS_CU 0x00008 +#define IXGBE_PHYSICAL_LAYER_10GBASE_LR 0x00010 +#define IXGBE_PHYSICAL_LAYER_10GBASE_LRM 0x00020 +#define IXGBE_PHYSICAL_LAYER_10GBASE_SR 0x00040 +#define IXGBE_PHYSICAL_LAYER_10GBASE_KX4 0x00080 +#define IXGBE_PHYSICAL_LAYER_10GBASE_CX4 0x00100 +#define IXGBE_PHYSICAL_LAYER_1000BASE_KX 0x00200 +#define IXGBE_PHYSICAL_LAYER_1000BASE_BX 0x00400 +#define IXGBE_PHYSICAL_LAYER_10GBASE_KR 0x00800 +#define IXGBE_PHYSICAL_LAYER_10GBASE_XAUI 0x01000 +#define IXGBE_PHYSICAL_LAYER_SFP_ACTIVE_DA 0x02000 +#define IXGBE_PHYSICAL_LAYER_1000BASE_SX 0x04000 +#define IXGBE_PHYSICAL_LAYER_10BASE_T 0x08000 +#define IXGBE_PHYSICAL_LAYER_2500BASE_KX 0x10000 +#define IXGBE_PHYSICAL_LAYER_2500BASE_T 0x20000 +#define IXGBE_PHYSICAL_LAYER_5000BASE_T 0x40000 + /* Flow Control Data Sheet defined values * Calculation and defines taken from 802.1bb Annex O */ @@ -3145,6 +3183,8 @@ enum ixgbe_mac_type { ixgbe_mac_X550, ixgbe_mac_X550EM_x, ixgbe_mac_x550em_a, + ixgbe_mac_e610, + ixgbe_mac_e610_vf, ixgbe_num_macs }; @@ -3224,7 +3264,9 @@ enum ixgbe_media_type { ixgbe_media_type_copper, ixgbe_media_type_backplane, ixgbe_media_type_cx4, - ixgbe_media_type_virtual + ixgbe_media_type_virtual, + ixgbe_media_type_da, + ixgbe_media_type_aui, }; /* Flow Control Settings */ @@ -3233,7 +3275,8 @@ enum ixgbe_fc_mode { ixgbe_fc_rx_pause, ixgbe_fc_tx_pause, ixgbe_fc_full, - ixgbe_fc_default + ixgbe_fc_default, + ixgbe_fc_pfc, }; /* Smart Speed Settings */ @@ -3533,6 +3576,9 @@ struct ixgbe_link_operations { struct ixgbe_link_info { struct ixgbe_link_operations ops; u8 addr; + struct ixgbe_link_status link_info; + struct ixgbe_link_status link_info_old; + u8 get_link_info; }; struct ixgbe_eeprom_info { @@ -3575,6 +3621,7 @@ struct ixgbe_mac_info { u8 san_mac_rar_index; struct ixgbe_thermal_sensor_data thermal_sensor_data; bool set_lben; + u32 max_link_up_time; u8 led_link_act; }; @@ -3599,6 +3646,10 @@ struct ixgbe_phy_info { bool reset_if_overtemp; bool qsfp_shared_i2c_bus; u32 nw_mng_if_sel; + u64 phy_type_low; + u64 phy_type_high; + u16 curr_user_speed_req; + struct ixgbe_aci_cmd_set_phy_cfg_data curr_user_phy_cfg; }; struct ixgbe_mbx_stats { @@ -3643,6 +3694,19 @@ struct ixgbe_hw { bool allow_unsupported_sfp; bool wol_enabled; bool need_crosstalk_fix; + u8 api_branch; + u8 api_maj_ver; + u8 api_min_ver; + u8 api_patch; + u8 fw_branch; + u8 fw_maj_ver; + u8 fw_min_ver; + u8 fw_patch; + u32 fw_build; + struct ixgbe_aci_info aci; + struct ixgbe_flash_info flash; + struct ixgbe_hw_dev_caps dev_caps; + struct ixgbe_hw_func_caps func_caps; }; struct ixgbe_info { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h new file mode 100644 index 000000000000..8d06ade3c7cd --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h @@ -0,0 +1,1074 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IXGBE_TYPE_E610_H_ +#define _IXGBE_TYPE_E610_H_ + +#define BYTES_PER_DWORD 4 + +/* General E610 defines */ +#define IXGBE_MAX_VSI 768 + +/* Checksum and Shadow RAM pointers */ +#define E610_SR_SW_CHECKSUM_WORD 0x3F + +/* Shadow RAM related */ +#define IXGBE_SR_WORDS_IN_1KB 512 + +/* Firmware Status Register (GL_FWSTS) */ +#define GL_FWSTS 0x00083048 /* Reset Source: POR */ +#define GL_FWSTS_EP_PF0 BIT(24) +#define GL_FWSTS_EP_PF1 BIT(25) + +/* Global NVM General Status Register */ +#define GLNVM_GENS 0x000B6100 /* Reset Source: POR */ +#define GLNVM_GENS_SR_SIZE_M GENMASK(7, 5) + +/* Flash Access Register */ +#define IXGBE_GLNVM_FLA 0x000B6108 /* Reset Source: POR */ +#define IXGBE_GLNVM_FLA_LOCKED_S 6 +#define IXGBE_GLNVM_FLA_LOCKED_M BIT(6) + +/* Admin Command Interface (ACI) registers */ +#define IXGBE_PF_HIDA(_i) (0x00085000 + ((_i) * 4)) +#define IXGBE_PF_HIDA_2(_i) (0x00085020 + ((_i) * 4)) +#define IXGBE_PF_HIBA(_i) (0x00084000 + ((_i) * 4)) +#define IXGBE_PF_HICR 0x00082048 + +#define IXGBE_PF_HICR_EN BIT(0) +#define IXGBE_PF_HICR_C BIT(1) +#define IXGBE_PF_HICR_SV BIT(2) +#define IXGBE_PF_HICR_EV BIT(3) + +#define IXGBE_ACI_DESC_SIZE 32 +#define IXGBE_ACI_DESC_SIZE_IN_DWORDS (IXGBE_ACI_DESC_SIZE / BYTES_PER_DWORD) + +#define IXGBE_ACI_MAX_BUFFER_SIZE 4096 /* Size in bytes */ +#define IXGBE_ACI_SEND_DELAY_TIME_MS 10 +#define IXGBE_ACI_SEND_MAX_EXECUTE 3 +#define IXGBE_ACI_SEND_TIMEOUT_MS \ + (IXGBE_ACI_SEND_MAX_EXECUTE * IXGBE_ACI_SEND_DELAY_TIME_MS) +/* [ms] timeout of waiting for sync response */ +#define IXGBE_ACI_SYNC_RESPONSE_TIMEOUT 100000 +/* [ms] timeout of waiting for async response */ +#define IXGBE_ACI_ASYNC_RESPONSE_TIMEOUT 150000 +/* [ms] timeout of waiting for resource release */ +#define IXGBE_ACI_RELEASE_RES_TIMEOUT 10000 + +/* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */ +#define IXGBE_ACI_LG_BUF 512 + +/* Flags sub-structure + * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 | + * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE | + */ + +#define IXGBE_ACI_FLAG_DD BIT(0) /* 0x1 */ +#define IXGBE_ACI_FLAG_CMP BIT(1) /* 0x2 */ +#define IXGBE_ACI_FLAG_ERR BIT(2) /* 0x4 */ +#define IXGBE_ACI_FLAG_VFE BIT(3) /* 0x8 */ +#define IXGBE_ACI_FLAG_LB BIT(9) /* 0x200 */ +#define IXGBE_ACI_FLAG_RD BIT(10) /* 0x400 */ +#define IXGBE_ACI_FLAG_VFC BIT(11) /* 0x800 */ +#define IXGBE_ACI_FLAG_BUF BIT(12) /* 0x1000 */ +#define IXGBE_ACI_FLAG_SI BIT(13) /* 0x2000 */ +#define IXGBE_ACI_FLAG_EI BIT(14) /* 0x4000 */ +#define IXGBE_ACI_FLAG_FE BIT(15) /* 0x8000 */ + +/* Admin Command Interface (ACI) error codes */ +enum ixgbe_aci_err { + IXGBE_ACI_RC_OK = 0, /* Success */ + IXGBE_ACI_RC_EPERM = 1, /* Operation not permitted */ + IXGBE_ACI_RC_ENOENT = 2, /* No such element */ + IXGBE_ACI_RC_ESRCH = 3, /* Bad opcode */ + IXGBE_ACI_RC_EINTR = 4, /* Operation interrupted */ + IXGBE_ACI_RC_EIO = 5, /* I/O error */ + IXGBE_ACI_RC_ENXIO = 6, /* No such resource */ + IXGBE_ACI_RC_E2BIG = 7, /* Arg too long */ + IXGBE_ACI_RC_EAGAIN = 8, /* Try again */ + IXGBE_ACI_RC_ENOMEM = 9, /* Out of memory */ + IXGBE_ACI_RC_EACCES = 10, /* Permission denied */ + IXGBE_ACI_RC_EFAULT = 11, /* Bad address */ + IXGBE_ACI_RC_EBUSY = 12, /* Device or resource busy */ + IXGBE_ACI_RC_EEXIST = 13, /* Object already exists */ + IXGBE_ACI_RC_EINVAL = 14, /* Invalid argument */ + IXGBE_ACI_RC_ENOTTY = 15, /* Not a typewriter */ + IXGBE_ACI_RC_ENOSPC = 16, /* No space left or alloc failure */ + IXGBE_ACI_RC_ENOSYS = 17, /* Function not implemented */ + IXGBE_ACI_RC_ERANGE = 18, /* Parameter out of range */ + IXGBE_ACI_RC_EFLUSHED = 19, /* Cmd flushed due to prev cmd error */ + IXGBE_ACI_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */ + IXGBE_ACI_RC_EMODE = 21, /* Op not allowed in current dev mode */ + IXGBE_ACI_RC_EFBIG = 22, /* File too big */ + IXGBE_ACI_RC_ESBCOMP = 23, /* SB-IOSF completion unsuccessful */ + IXGBE_ACI_RC_ENOSEC = 24, /* Missing security manifest */ + IXGBE_ACI_RC_EBADSIG = 25, /* Bad RSA signature */ + IXGBE_ACI_RC_ESVN = 26, /* SVN number prohibits this package */ + IXGBE_ACI_RC_EBADMAN = 27, /* Manifest hash mismatch */ + IXGBE_ACI_RC_EBADBUF = 28, /* Buffer hash mismatches manifest */ + IXGBE_ACI_RC_EACCES_BMCU = 29, /* BMC Update in progress */ +}; + +/* Admin Command Interface (ACI) opcodes */ +enum ixgbe_aci_opc { + ixgbe_aci_opc_get_ver = 0x0001, + ixgbe_aci_opc_driver_ver = 0x0002, + ixgbe_aci_opc_get_exp_err = 0x0005, + + /* resource ownership */ + ixgbe_aci_opc_req_res = 0x0008, + ixgbe_aci_opc_release_res = 0x0009, + + /* device/function capabilities */ + ixgbe_aci_opc_list_func_caps = 0x000A, + ixgbe_aci_opc_list_dev_caps = 0x000B, + + /* safe disable of RXEN */ + ixgbe_aci_opc_disable_rxen = 0x000C, + + /* FW events */ + ixgbe_aci_opc_get_fw_event = 0x0014, + + /* PHY commands */ + ixgbe_aci_opc_get_phy_caps = 0x0600, + ixgbe_aci_opc_set_phy_cfg = 0x0601, + ixgbe_aci_opc_restart_an = 0x0605, + ixgbe_aci_opc_get_link_status = 0x0607, + ixgbe_aci_opc_set_event_mask = 0x0613, + ixgbe_aci_opc_get_link_topo = 0x06E0, + ixgbe_aci_opc_get_link_topo_pin = 0x06E1, + ixgbe_aci_opc_read_i2c = 0x06E2, + ixgbe_aci_opc_write_i2c = 0x06E3, + ixgbe_aci_opc_read_mdio = 0x06E4, + ixgbe_aci_opc_write_mdio = 0x06E5, + ixgbe_aci_opc_set_gpio_by_func = 0x06E6, + ixgbe_aci_opc_get_gpio_by_func = 0x06E7, + ixgbe_aci_opc_set_gpio = 0x06EC, + ixgbe_aci_opc_get_gpio = 0x06ED, + ixgbe_aci_opc_sff_eeprom = 0x06EE, + ixgbe_aci_opc_prog_topo_dev_nvm = 0x06F2, + ixgbe_aci_opc_read_topo_dev_nvm = 0x06F3, + + /* NVM commands */ + ixgbe_aci_opc_nvm_read = 0x0701, + ixgbe_aci_opc_nvm_erase = 0x0702, + ixgbe_aci_opc_nvm_write = 0x0703, + ixgbe_aci_opc_nvm_cfg_read = 0x0704, + ixgbe_aci_opc_nvm_cfg_write = 0x0705, + ixgbe_aci_opc_nvm_checksum = 0x0706, + ixgbe_aci_opc_nvm_write_activate = 0x0707, + ixgbe_aci_opc_nvm_sr_dump = 0x0707, + ixgbe_aci_opc_nvm_save_factory_settings = 0x0708, + ixgbe_aci_opc_nvm_update_empr = 0x0709, + ixgbe_aci_opc_nvm_pkg_data = 0x070A, + ixgbe_aci_opc_nvm_pass_component_tbl = 0x070B, + + /* Alternate Structure Commands */ + ixgbe_aci_opc_write_alt_direct = 0x0900, + ixgbe_aci_opc_write_alt_indirect = 0x0901, + ixgbe_aci_opc_read_alt_direct = 0x0902, + ixgbe_aci_opc_read_alt_indirect = 0x0903, + ixgbe_aci_opc_done_alt_write = 0x0904, + ixgbe_aci_opc_clear_port_alt_write = 0x0906, + + /* debug commands */ + ixgbe_aci_opc_debug_dump_internals = 0xFF08, + + /* SystemDiagnostic commands */ + ixgbe_aci_opc_set_health_status_config = 0xFF20, + ixgbe_aci_opc_get_supported_health_status_codes = 0xFF21, + ixgbe_aci_opc_get_health_status = 0xFF22, + ixgbe_aci_opc_clear_health_status = 0xFF23, +}; + +/* Get version (direct 0x0001) */ +struct ixgbe_aci_cmd_get_ver { + __le32 rom_ver; + __le32 fw_build; + u8 fw_branch; + u8 fw_major; + u8 fw_minor; + u8 fw_patch; + u8 api_branch; + u8 api_major; + u8 api_minor; + u8 api_patch; +}; + +#define IXGBE_DRV_VER_STR_LEN_E610 32 + +/* Send driver version (indirect 0x0002) */ +struct ixgbe_aci_cmd_driver_ver { + u8 major_ver; + u8 minor_ver; + u8 build_ver; + u8 subbuild_ver; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +/* Get Expanded Error Code (0x0005, direct) */ +struct ixgbe_aci_cmd_get_exp_err { + __le32 reason; +#define IXGBE_ACI_EXPANDED_ERROR_NOT_PROVIDED 0xFFFFFFFF + __le32 identifier; + u8 rsvd[8]; +}; + +/* FW update timeout definitions are in milliseconds */ +#define IXGBE_NVM_TIMEOUT 180000 + +enum ixgbe_aci_res_access_type { + IXGBE_RES_READ = 1, + IXGBE_RES_WRITE +}; + +enum ixgbe_aci_res_ids { + IXGBE_NVM_RES_ID = 1, + IXGBE_SPD_RES_ID, + IXGBE_CHANGE_LOCK_RES_ID, + IXGBE_GLOBAL_CFG_LOCK_RES_ID +}; + +/* Request resource ownership (direct 0x0008) + * Release resource ownership (direct 0x0009) + */ +struct ixgbe_aci_cmd_req_res { + __le16 res_id; + __le16 access_type; + + /* Upon successful completion, FW writes this value and driver is + * expected to release resource before timeout. This value is provided + * in milliseconds. + */ + __le32 timeout; +#define IXGBE_ACI_RES_NVM_READ_DFLT_TIMEOUT_MS 3000 +#define IXGBE_ACI_RES_NVM_WRITE_DFLT_TIMEOUT_MS 180000 +#define IXGBE_ACI_RES_CHNG_LOCK_DFLT_TIMEOUT_MS 1000 +#define IXGBE_ACI_RES_GLBL_LOCK_DFLT_TIMEOUT_MS 3000 + /* For SDP: pin ID of the SDP */ + __le32 res_number; + __le16 status; +#define IXGBE_ACI_RES_GLBL_SUCCESS 0 +#define IXGBE_ACI_RES_GLBL_IN_PROG 1 +#define IXGBE_ACI_RES_GLBL_DONE 2 + u8 reserved[2]; +}; + +/* Get function capabilities (indirect 0x000A) + * Get device capabilities (indirect 0x000B) + */ +struct ixgbe_aci_cmd_list_caps { + u8 cmd_flags; + u8 pf_index; + u8 reserved[2]; + __le32 count; + __le32 addr_high; + __le32 addr_low; +}; + +/* Device/Function buffer entry, repeated per reported capability */ +struct ixgbe_aci_cmd_list_caps_elem { + __le16 cap; +#define IXGBE_ACI_CAPS_VALID_FUNCTIONS 0x0005 +#define IXGBE_ACI_MAX_VALID_FUNCTIONS 0x8 +#define IXGBE_ACI_CAPS_SRIOV 0x0012 +#define IXGBE_ACI_CAPS_VF 0x0013 +#define IXGBE_ACI_CAPS_VMDQ 0x0014 +#define IXGBE_ACI_CAPS_VSI 0x0017 +#define IXGBE_ACI_CAPS_DCB 0x0018 +#define IXGBE_ACI_CAPS_RSS 0x0040 +#define IXGBE_ACI_CAPS_RXQS 0x0041 +#define IXGBE_ACI_CAPS_TXQS 0x0042 +#define IXGBE_ACI_CAPS_MSIX 0x0043 +#define IXGBE_ACI_CAPS_FD 0x0045 +#define IXGBE_ACI_CAPS_1588 0x0046 +#define IXGBE_ACI_CAPS_MAX_MTU 0x0047 +#define IXGBE_ACI_CAPS_NVM_VER 0x0048 +#define IXGBE_ACI_CAPS_PENDING_NVM_VER 0x0049 +#define IXGBE_ACI_CAPS_OROM_VER 0x004A +#define IXGBE_ACI_CAPS_PENDING_OROM_VER 0x004B +#define IXGBE_ACI_CAPS_PENDING_NET_VER 0x004D +#define IXGBE_ACI_CAPS_INLINE_IPSEC 0x0070 +#define IXGBE_ACI_CAPS_NUM_ENABLED_PORTS 0x0072 +#define IXGBE_ACI_CAPS_PCIE_RESET_AVOIDANCE 0x0076 +#define IXGBE_ACI_CAPS_POST_UPDATE_RESET_RESTRICT 0x0077 +#define IXGBE_ACI_CAPS_NVM_MGMT 0x0080 +#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0 0x0081 +#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG1 0x0082 +#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG2 0x0083 +#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG3 0x0084 + u8 major_ver; + u8 minor_ver; + /* Number of resources described by this capability */ + __le32 number; + /* Only meaningful for some types of resources */ + __le32 logical_id; + /* Only meaningful for some types of resources */ + __le32 phys_id; + __le64 rsvd1; + __le64 rsvd2; +}; + +/* Disable RXEN (direct 0x000C) */ +struct ixgbe_aci_cmd_disable_rxen { + u8 lport_num; + u8 reserved[15]; +}; + +/* Get PHY capabilities (indirect 0x0600) */ +struct ixgbe_aci_cmd_get_phy_caps { + u8 lport_num; + u8 reserved; + __le16 param0; + /* 18.0 - Report qualified modules */ +#define IXGBE_ACI_GET_PHY_RQM BIT(0) + /* 18.1 - 18.3 : Report mode + * 000b - Report topology capabilities, without media + * 001b - Report topology capabilities, with media + * 010b - Report Active configuration + * 011b - Report PHY Type and FEC mode capabilities + * 100b - Report Default capabilities + */ +#define IXGBE_ACI_REPORT_MODE_M GENMASK(3, 1) +#define IXGBE_ACI_REPORT_TOPO_CAP_NO_MEDIA 0 +#define IXGBE_ACI_REPORT_TOPO_CAP_MEDIA BIT(1) +#define IXGBE_ACI_REPORT_ACTIVE_CFG BIT(2) +#define IXGBE_ACI_REPORT_DFLT_CFG BIT(3) + __le32 reserved1; + __le32 addr_high; + __le32 addr_low; +}; + +/* This is #define of PHY type (Extended): + * The first set of defines is for phy_type_low. + */ +#define IXGBE_PHY_TYPE_LOW_100BASE_TX BIT_ULL(0) +#define IXGBE_PHY_TYPE_LOW_100M_SGMII BIT_ULL(1) +#define IXGBE_PHY_TYPE_LOW_1000BASE_T BIT_ULL(2) +#define IXGBE_PHY_TYPE_LOW_1000BASE_SX BIT_ULL(3) +#define IXGBE_PHY_TYPE_LOW_1000BASE_LX BIT_ULL(4) +#define IXGBE_PHY_TYPE_LOW_1000BASE_KX BIT_ULL(5) +#define IXGBE_PHY_TYPE_LOW_1G_SGMII BIT_ULL(6) +#define IXGBE_PHY_TYPE_LOW_2500BASE_T BIT_ULL(7) +#define IXGBE_PHY_TYPE_LOW_2500BASE_X BIT_ULL(8) +#define IXGBE_PHY_TYPE_LOW_2500BASE_KX BIT_ULL(9) +#define IXGBE_PHY_TYPE_LOW_5GBASE_T BIT_ULL(10) +#define IXGBE_PHY_TYPE_LOW_5GBASE_KR BIT_ULL(11) +#define IXGBE_PHY_TYPE_LOW_10GBASE_T BIT_ULL(12) +#define IXGBE_PHY_TYPE_LOW_10G_SFI_DA BIT_ULL(13) +#define IXGBE_PHY_TYPE_LOW_10GBASE_SR BIT_ULL(14) +#define IXGBE_PHY_TYPE_LOW_10GBASE_LR BIT_ULL(15) +#define IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1 BIT_ULL(16) +#define IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC BIT_ULL(17) +#define IXGBE_PHY_TYPE_LOW_10G_SFI_C2C BIT_ULL(18) +#define IXGBE_PHY_TYPE_LOW_25GBASE_T BIT_ULL(19) +#define IXGBE_PHY_TYPE_LOW_25GBASE_CR BIT_ULL(20) +#define IXGBE_PHY_TYPE_LOW_25GBASE_CR_S BIT_ULL(21) +#define IXGBE_PHY_TYPE_LOW_25GBASE_CR1 BIT_ULL(22) +#define IXGBE_PHY_TYPE_LOW_25GBASE_SR BIT_ULL(23) +#define IXGBE_PHY_TYPE_LOW_25GBASE_LR BIT_ULL(24) +#define IXGBE_PHY_TYPE_LOW_25GBASE_KR BIT_ULL(25) +#define IXGBE_PHY_TYPE_LOW_25GBASE_KR_S BIT_ULL(26) +#define IXGBE_PHY_TYPE_LOW_25GBASE_KR1 BIT_ULL(27) +#define IXGBE_PHY_TYPE_LOW_25G_AUI_AOC_ACC BIT_ULL(28) +#define IXGBE_PHY_TYPE_LOW_25G_AUI_C2C BIT_ULL(29) +#define IXGBE_PHY_TYPE_LOW_MAX_INDEX 29 +/* The second set of defines is for phy_type_high. */ +#define IXGBE_PHY_TYPE_HIGH_10BASE_T BIT_ULL(1) +#define IXGBE_PHY_TYPE_HIGH_10M_SGMII BIT_ULL(2) +#define IXGBE_PHY_TYPE_HIGH_2500M_SGMII BIT_ULL(56) +#define IXGBE_PHY_TYPE_HIGH_100M_USXGMII BIT_ULL(57) +#define IXGBE_PHY_TYPE_HIGH_1G_USXGMII BIT_ULL(58) +#define IXGBE_PHY_TYPE_HIGH_2500M_USXGMII BIT_ULL(59) +#define IXGBE_PHY_TYPE_HIGH_5G_USXGMII BIT_ULL(60) +#define IXGBE_PHY_TYPE_HIGH_10G_USXGMII BIT_ULL(61) +#define IXGBE_PHY_TYPE_HIGH_MAX_INDEX 61 + +struct ixgbe_aci_cmd_get_phy_caps_data { + __le64 phy_type_low; /* Use values from IXGBE_PHY_TYPE_LOW_* */ + __le64 phy_type_high; /* Use values from IXGBE_PHY_TYPE_HIGH_* */ + u8 caps; +#define IXGBE_ACI_PHY_EN_TX_LINK_PAUSE BIT(0) +#define IXGBE_ACI_PHY_EN_RX_LINK_PAUSE BIT(1) +#define IXGBE_ACI_PHY_LOW_POWER_MODE BIT(2) +#define IXGBE_ACI_PHY_EN_LINK BIT(3) +#define IXGBE_ACI_PHY_AN_MODE BIT(4) +#define IXGBE_ACI_PHY_EN_MOD_QUAL BIT(5) +#define IXGBE_ACI_PHY_EN_LESM BIT(6) +#define IXGBE_ACI_PHY_EN_AUTO_FEC BIT(7) +#define IXGBE_ACI_PHY_CAPS_MASK GENMASK(7, 0) + u8 low_power_ctrl_an; +#define IXGBE_ACI_PHY_EN_D3COLD_LOW_POWER_AUTONEG BIT(0) +#define IXGBE_ACI_PHY_AN_EN_CLAUSE28 BIT(1) +#define IXGBE_ACI_PHY_AN_EN_CLAUSE73 BIT(2) +#define IXGBE_ACI_PHY_AN_EN_CLAUSE37 BIT(3) + __le16 eee_cap; +#define IXGBE_ACI_PHY_EEE_EN_100BASE_TX BIT(0) +#define IXGBE_ACI_PHY_EEE_EN_1000BASE_T BIT(1) +#define IXGBE_ACI_PHY_EEE_EN_10GBASE_T BIT(2) +#define IXGBE_ACI_PHY_EEE_EN_1000BASE_KX BIT(3) +#define IXGBE_ACI_PHY_EEE_EN_10GBASE_KR BIT(4) +#define IXGBE_ACI_PHY_EEE_EN_25GBASE_KR BIT(5) +#define IXGBE_ACI_PHY_EEE_EN_10BASE_T BIT(11) + __le16 eeer_value; + u8 phy_id_oui[4]; /* PHY/Module ID connected on the port */ + u8 phy_fw_ver[8]; + u8 link_fec_options; +#define IXGBE_ACI_PHY_FEC_10G_KR_40G_KR4_EN BIT(0) +#define IXGBE_ACI_PHY_FEC_10G_KR_40G_KR4_REQ BIT(1) +#define IXGBE_ACI_PHY_FEC_25G_RS_528_REQ BIT(2) +#define IXGBE_ACI_PHY_FEC_25G_KR_REQ BIT(3) +#define IXGBE_ACI_PHY_FEC_25G_RS_544_REQ BIT(4) +#define IXGBE_ACI_PHY_FEC_25G_RS_CLAUSE91_EN BIT(6) +#define IXGBE_ACI_PHY_FEC_25G_KR_CLAUSE74_EN BIT(7) +#define IXGBE_ACI_PHY_FEC_MASK 0xdf + u8 module_compliance_enforcement; +#define IXGBE_ACI_MOD_ENFORCE_STRICT_MODE BIT(0) + u8 extended_compliance_code; +#define IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE 3 + u8 module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE]; +#define IXGBE_ACI_MOD_TYPE_BYTE0_SFP_PLUS 0xA0 +#define IXGBE_ACI_MOD_TYPE_BYTE0_QSFP_PLUS 0x80 +#define IXGBE_ACI_MOD_TYPE_IDENT 1 +#define IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE BIT(0) +#define IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE BIT(1) +#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_SR BIT(4) +#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LR BIT(5) +#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LRM BIT(6) +#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_ER BIT(7) +#define IXGBE_ACI_MOD_TYPE_BYTE2_SFP_PLUS 0xA0 +#define IXGBE_ACI_MOD_TYPE_BYTE2_QSFP_PLUS 0x86 + u8 qualified_module_count; + u8 rsvd2[7]; /* Bytes 47:41 reserved */ +#define IXGBE_ACI_QUAL_MOD_COUNT_MAX 16 + struct { + u8 v_oui[3]; + u8 rsvd3; + u8 v_part[16]; + __le32 v_rev; + __le64 rsvd4; + } qual_modules[IXGBE_ACI_QUAL_MOD_COUNT_MAX]; +}; + +/* Set PHY capabilities (direct 0x0601) + * NOTE: This command must be followed by setup link and restart auto-neg + */ +struct ixgbe_aci_cmd_set_phy_cfg { + u8 lport_num; + u8 reserved[7]; + __le32 addr_high; + __le32 addr_low; +}; + +/* Set PHY config command data structure */ +struct ixgbe_aci_cmd_set_phy_cfg_data { + __le64 phy_type_low; /* Use values from IXGBE_PHY_TYPE_LOW_* */ + __le64 phy_type_high; /* Use values from IXGBE_PHY_TYPE_HIGH_* */ + u8 caps; +#define IXGBE_ACI_PHY_ENA_VALID_MASK 0xef +#define IXGBE_ACI_PHY_ENA_TX_PAUSE_ABILITY BIT(0) +#define IXGBE_ACI_PHY_ENA_RX_PAUSE_ABILITY BIT(1) +#define IXGBE_ACI_PHY_ENA_LOW_POWER BIT(2) +#define IXGBE_ACI_PHY_ENA_LINK BIT(3) +#define IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT BIT(5) +#define IXGBE_ACI_PHY_ENA_LESM BIT(6) +#define IXGBE_ACI_PHY_ENA_AUTO_FEC BIT(7) + u8 low_power_ctrl_an; + __le16 eee_cap; /* Value from ixgbe_aci_get_phy_caps */ + __le16 eeer_value; /* Use defines from ixgbe_aci_get_phy_caps */ + u8 link_fec_opt; /* Use defines from ixgbe_aci_get_phy_caps */ + u8 module_compliance_enforcement; +}; + +/* Restart AN command data structure (direct 0x0605) + * Also used for response, with only the lport_num field present. + */ +struct ixgbe_aci_cmd_restart_an { + u8 lport_num; + u8 reserved; + u8 cmd_flags; +#define IXGBE_ACI_RESTART_AN_LINK_RESTART BIT(1) +#define IXGBE_ACI_RESTART_AN_LINK_ENABLE BIT(2) + u8 reserved2[13]; +}; + +/* Get link status (indirect 0x0607), also used for Link Status Event */ +struct ixgbe_aci_cmd_get_link_status { + u8 lport_num; + u8 reserved; + __le16 cmd_flags; +#define IXGBE_ACI_LSE_M GENMASK(1, 0) +#define IXGBE_ACI_LSE_NOP 0x0 +#define IXGBE_ACI_LSE_DIS 0x2 +#define IXGBE_ACI_LSE_ENA 0x3 + /* only response uses this flag */ +#define IXGBE_ACI_LSE_IS_ENABLED 0x1 + __le32 reserved2; + __le32 addr_high; + __le32 addr_low; +}; + +/* Get link status response data structure, also used for Link Status Event */ +struct ixgbe_aci_cmd_get_link_status_data { + u8 topo_media_conflict; +#define IXGBE_ACI_LINK_TOPO_CONFLICT BIT(0) +#define IXGBE_ACI_LINK_MEDIA_CONFLICT BIT(1) +#define IXGBE_ACI_LINK_TOPO_CORRUPT BIT(2) +#define IXGBE_ACI_LINK_TOPO_UNREACH_PRT BIT(4) +#define IXGBE_ACI_LINK_TOPO_UNDRUTIL_PRT BIT(5) +#define IXGBE_ACI_LINK_TOPO_UNDRUTIL_MEDIA BIT(6) +#define IXGBE_ACI_LINK_TOPO_UNSUPP_MEDIA BIT(7) + u8 link_cfg_err; +#define IXGBE_ACI_LINK_CFG_ERR BIT(0) +#define IXGBE_ACI_LINK_CFG_COMPLETED BIT(1) +#define IXGBE_ACI_LINK_ACT_PORT_OPT_INVAL BIT(2) +#define IXGBE_ACI_LINK_FEAT_ID_OR_CONFIG_ID_INVAL BIT(3) +#define IXGBE_ACI_LINK_TOPO_CRITICAL_SDP_ERR BIT(4) +#define IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED BIT(5) +#define IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE BIT(6) +#define IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT BIT(7) + u8 link_info; +#define IXGBE_ACI_LINK_UP BIT(0) /* Link Status */ +#define IXGBE_ACI_LINK_FAULT BIT(1) +#define IXGBE_ACI_LINK_FAULT_TX BIT(2) +#define IXGBE_ACI_LINK_FAULT_RX BIT(3) +#define IXGBE_ACI_LINK_FAULT_REMOTE BIT(4) +#define IXGBE_ACI_LINK_UP_PORT BIT(5) /* External Port Link Status */ +#define IXGBE_ACI_MEDIA_AVAILABLE BIT(6) +#define IXGBE_ACI_SIGNAL_DETECT BIT(7) + u8 an_info; +#define IXGBE_ACI_AN_COMPLETED BIT(0) +#define IXGBE_ACI_LP_AN_ABILITY BIT(1) +#define IXGBE_ACI_PD_FAULT BIT(2) /* Parallel Detection Fault */ +#define IXGBE_ACI_FEC_EN BIT(3) +#define IXGBE_ACI_PHY_LOW_POWER BIT(4) /* Low Power State */ +#define IXGBE_ACI_LINK_PAUSE_TX BIT(5) +#define IXGBE_ACI_LINK_PAUSE_RX BIT(6) +#define IXGBE_ACI_QUALIFIED_MODULE BIT(7) + u8 ext_info; +#define IXGBE_ACI_LINK_PHY_TEMP_ALARM BIT(0) +#define IXGBE_ACI_LINK_EXCESSIVE_ERRORS BIT(1) /* Excessive Link Errors */ + /* Port Tx Suspended */ +#define IXGBE_ACI_LINK_TX_ACTIVE 0 +#define IXGBE_ACI_LINK_TX_DRAINED 1 +#define IXGBE_ACI_LINK_TX_FLUSHED 3 + u8 lb_status; +#define IXGBE_ACI_LINK_LB_PHY_LCL BIT(0) +#define IXGBE_ACI_LINK_LB_PHY_RMT BIT(1) +#define IXGBE_ACI_LINK_LB_MAC_LCL BIT(2) + __le16 max_frame_size; + u8 cfg; +#define IXGBE_ACI_LINK_25G_KR_FEC_EN BIT(0) +#define IXGBE_ACI_LINK_25G_RS_528_FEC_EN BIT(1) +#define IXGBE_ACI_LINK_25G_RS_544_FEC_EN BIT(2) +#define IXGBE_ACI_FEC_MASK GENMASK(2, 0) + /* Pacing Config */ +#define IXGBE_ACI_CFG_PACING_M GENMASK(6, 3) +#define IXGBE_ACI_CFG_PACING_TYPE_M BIT(7) +#define IXGBE_ACI_CFG_PACING_TYPE_AVG 0 +#define IXGBE_ACI_CFG_PACING_TYPE_FIXED IXGBE_ACI_CFG_PACING_TYPE_M + /* External Device Power Ability */ + u8 power_desc; +#define IXGBE_ACI_PWR_CLASS_M GENMASK(5, 0) +#define IXGBE_ACI_LINK_PWR_BASET_LOW_HIGH 0 +#define IXGBE_ACI_LINK_PWR_BASET_HIGH 1 +#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_1 0 +#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_2 1 +#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_3 2 +#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_4 3 + __le16 link_speed; +#define IXGBE_ACI_LINK_SPEED_M GENMASK(10, 0) +#define IXGBE_ACI_LINK_SPEED_10MB BIT(0) +#define IXGBE_ACI_LINK_SPEED_100MB BIT(1) +#define IXGBE_ACI_LINK_SPEED_1000MB BIT(2) +#define IXGBE_ACI_LINK_SPEED_2500MB BIT(3) +#define IXGBE_ACI_LINK_SPEED_5GB BIT(4) +#define IXGBE_ACI_LINK_SPEED_10GB BIT(5) +#define IXGBE_ACI_LINK_SPEED_20GB BIT(6) +#define IXGBE_ACI_LINK_SPEED_25GB BIT(7) +#define IXGBE_ACI_LINK_SPEED_40GB BIT(8) +#define IXGBE_ACI_LINK_SPEED_50GB BIT(9) +#define IXGBE_ACI_LINK_SPEED_100GB BIT(10) +#define IXGBE_ACI_LINK_SPEED_200GB BIT(11) +#define IXGBE_ACI_LINK_SPEED_UNKNOWN BIT(15) + __le16 reserved3; + u8 ext_fec_status; +#define IXGBE_ACI_LINK_RS_272_FEC_EN BIT(0) /* RS 272 FEC enabled */ + u8 reserved4; + __le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */ + __le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */ + /* Get link status version 2 link partner data */ + __le64 lp_phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */ + __le64 lp_phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */ + u8 lp_fec_adv; +#define IXGBE_ACI_LINK_LP_10G_KR_FEC_CAP BIT(0) +#define IXGBE_ACI_LINK_LP_25G_KR_FEC_CAP BIT(1) +#define IXGBE_ACI_LINK_LP_RS_528_FEC_CAP BIT(2) +#define IXGBE_ACI_LINK_LP_50G_KR_272_FEC_CAP BIT(3) +#define IXGBE_ACI_LINK_LP_100G_KR_272_FEC_CAP BIT(4) +#define IXGBE_ACI_LINK_LP_200G_KR_272_FEC_CAP BIT(5) + u8 lp_fec_req; +#define IXGBE_ACI_LINK_LP_10G_KR_FEC_REQ BIT(0) +#define IXGBE_ACI_LINK_LP_25G_KR_FEC_REQ BIT(1) +#define IXGBE_ACI_LINK_LP_RS_528_FEC_REQ BIT(2) +#define IXGBE_ACI_LINK_LP_KR_272_FEC_REQ BIT(3) + u8 lp_flowcontrol; +#define IXGBE_ACI_LINK_LP_PAUSE_ADV BIT(0) +#define IXGBE_ACI_LINK_LP_ASM_DIR_ADV BIT(1) + u8 reserved5[5]; +} __packed; + +/* Set event mask command (direct 0x0613) */ +struct ixgbe_aci_cmd_set_event_mask { + u8 lport_num; + u8 reserved[7]; + __le16 event_mask; +#define IXGBE_ACI_LINK_EVENT_UPDOWN BIT(1) +#define IXGBE_ACI_LINK_EVENT_MEDIA_NA BIT(2) +#define IXGBE_ACI_LINK_EVENT_LINK_FAULT BIT(3) +#define IXGBE_ACI_LINK_EVENT_PHY_TEMP_ALARM BIT(4) +#define IXGBE_ACI_LINK_EVENT_EXCESSIVE_ERRORS BIT(5) +#define IXGBE_ACI_LINK_EVENT_SIGNAL_DETECT BIT(6) +#define IXGBE_ACI_LINK_EVENT_AN_COMPLETED BIT(7) +#define IXGBE_ACI_LINK_EVENT_MODULE_QUAL_FAIL BIT(8) +#define IXGBE_ACI_LINK_EVENT_PORT_TX_SUSPENDED BIT(9) +#define IXGBE_ACI_LINK_EVENT_TOPO_CONFLICT BIT(10) +#define IXGBE_ACI_LINK_EVENT_MEDIA_CONFLICT BIT(11) +#define IXGBE_ACI_LINK_EVENT_PHY_FW_LOAD_FAIL BIT(12) + u8 reserved1[6]; +}; + +struct ixgbe_aci_cmd_link_topo_params { + u8 lport_num; + u8 lport_num_valid; +#define IXGBE_ACI_LINK_TOPO_PORT_NUM_VALID BIT(0) + u8 node_type_ctx; +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_M GENMASK(3, 0) +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_PHY 0 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_GPIO_CTRL 1 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_MUX_CTRL 2 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_LED_CTRL 3 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_LED 4 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_THERMAL 5 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CAGE 6 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_MEZZ 7 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_ID_EEPROM 8 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CLK_CTRL 9 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CLK_MUX 10 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_GPS 11 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_S 4 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_M GENMASK(7, 4) +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_GLOBAL 0 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_BOARD 1 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_PORT 2 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE 3 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE_HANDLE 4 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_DIRECT_BUS_ACCESS 5 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE_HANDLE_BUS_ADDRESS 6 + u8 index; +}; + +struct ixgbe_aci_cmd_link_topo_addr { + struct ixgbe_aci_cmd_link_topo_params topo_params; + __le16 handle; +/* Used to decode the handle field */ +#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_M BIT(9) +#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_LOM BIT(9) +#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_MEZZ 0 +}; + +/* Get Link Topology Handle (direct, 0x06E0) */ +struct ixgbe_aci_cmd_get_link_topo { + struct ixgbe_aci_cmd_link_topo_addr addr; + u8 node_part_num; +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_PCA9575 0x21 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_ZL30632_80032 0x24 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_SI5384 0x25 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_C827 0x31 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX 0x47 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_GEN_GPS 0x48 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_E610_PTC 0x49 + u8 rsvd[9]; +}; + +/* Get Link Topology Pin (direct, 0x06E1) */ +struct ixgbe_aci_cmd_get_link_topo_pin { + struct ixgbe_aci_cmd_link_topo_addr addr; + u8 input_io_params; +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_GPIO 0 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RESET_N 1 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_INT_N 2 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_PRESENT_N 3 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_TX_DIS 4 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_MODSEL_N 5 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_LPMODE 6 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_TX_FAULT 7 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RX_LOSS 8 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RS0 9 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RS1 10 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_EEPROM_WP 11 +/* 12 repeats intentionally due to two different uses depending on context */ +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_LED 12 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RED_LED 12 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_GREEN_LED 13 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_BLUE_LED 14 +#define IXGBE_ACI_LINK_TOPO_INPUT_IO_TYPE_GPIO 3 +/* Use IXGBE_ACI_LINK_TOPO_NODE_TYPE_* for the type values */ + u8 output_io_params; +/* Use IXGBE_ACI_LINK_TOPO_NODE_TYPE_* for the type values */ + u8 output_io_flags; +#define IXGBE_ACI_LINK_TOPO_OUTPUT_POLARITY BIT(5) +#define IXGBE_ACI_LINK_TOPO_OUTPUT_VALUE BIT(6) +#define IXGBE_ACI_LINK_TOPO_OUTPUT_DRIVEN BIT(7) + u8 rsvd[7]; +}; + +/* Read/Write SFF EEPROM command (indirect 0x06EE) */ +struct ixgbe_aci_cmd_sff_eeprom { + u8 lport_num; + u8 lport_num_valid; +#define IXGBE_ACI_SFF_PORT_NUM_VALID BIT(0) + __le16 i2c_bus_addr; +#define IXGBE_ACI_SFF_I2CBUS_7BIT_M GENMASK(6, 0) +#define IXGBE_ACI_SFF_I2CBUS_10BIT_M GENMASK(9, 0) +#define IXGBE_ACI_SFF_I2CBUS_TYPE_M BIT(10) +#define IXGBE_ACI_SFF_I2CBUS_TYPE_7BIT 0 +#define IXGBE_ACI_SFF_I2CBUS_TYPE_10BIT IXGBE_ACI_SFF_I2CBUS_TYPE_M +#define IXGBE_ACI_SFF_NO_PAGE_BANK_UPDATE 0 +#define IXGBE_ACI_SFF_UPDATE_PAGE 1 +#define IXGBE_ACI_SFF_UPDATE_BANK 2 +#define IXGBE_ACI_SFF_UPDATE_PAGE_BANK 3 +#define IXGBE_ACI_SFF_IS_WRITE BIT(15) + __le16 i2c_offset; + u8 module_bank; + u8 module_page; + __le32 addr_high; + __le32 addr_low; +}; + +/* NVM Read command (indirect 0x0701) + * NVM Erase commands (direct 0x0702) + * NVM Write commands (indirect 0x0703) + * NVM Write Activate commands (direct 0x0707) + * NVM Shadow RAM Dump commands (direct 0x0707) + */ +struct ixgbe_aci_cmd_nvm { +#define IXGBE_ACI_NVM_MAX_OFFSET 0xFFFFFF + __le16 offset_low; + u8 offset_high; /* For Write Activate offset_high is used as flags2 */ + u8 cmd_flags; +#define IXGBE_ACI_NVM_LAST_CMD BIT(0) +#define IXGBE_ACI_NVM_PCIR_REQ BIT(0) /* Used by NVM Write reply */ +#define IXGBE_ACI_NVM_PRESERVE_ALL BIT(1) +#define IXGBE_ACI_NVM_ACTIV_SEL_NVM BIT(3) /* Write Activate/SR Dump only */ +#define IXGBE_ACI_NVM_ACTIV_SEL_OROM BIT(4) +#define IXGBE_ACI_NVM_ACTIV_SEL_NETLIST BIT(5) +#define IXGBE_ACI_NVM_SPECIAL_UPDATE BIT(6) +#define IXGBE_ACI_NVM_REVERT_LAST_ACTIV BIT(6) /* Write Activate only */ +#define IXGBE_ACI_NVM_FLASH_ONLY BIT(7) +#define IXGBE_ACI_NVM_RESET_LVL_M GENMASK(1, 0) /* Write reply only */ +#define IXGBE_ACI_NVM_POR_FLAG 0 +#define IXGBE_ACI_NVM_PERST_FLAG 1 +#define IXGBE_ACI_NVM_EMPR_FLAG 2 +#define IXGBE_ACI_NVM_EMPR_ENA BIT(0) /* Write Activate reply only */ + /* For Write Activate, several flags are sent as part of a separate + * flags2 field using a separate byte. For simplicity of the software + * interface, we pass the flags as a 16 bit value so these flags are + * all offset by 8 bits + */ +#define IXGBE_ACI_NVM_ACTIV_REQ_EMPR BIT(8) /* NVM Write Activate only */ + __le16 module_typeid; + __le16 length; +#define IXGBE_ACI_NVM_ERASE_LEN 0xFFFF + __le32 addr_high; + __le32 addr_low; +}; + +/* NVM Module_Type ID, needed offset and read_len for + * struct ixgbe_aci_cmd_nvm. + */ +#define IXGBE_ACI_NVM_START_POINT 0 + +/* NVM Checksum Command (direct, 0x0706) */ +struct ixgbe_aci_cmd_nvm_checksum { + u8 flags; +#define IXGBE_ACI_NVM_CHECKSUM_VERIFY BIT(0) +#define IXGBE_ACI_NVM_CHECKSUM_RECALC BIT(1) + u8 rsvd; + __le16 checksum; /* Used only by response */ +#define IXGBE_ACI_NVM_CHECKSUM_CORRECT 0xBABA + u8 rsvd2[12]; +}; + +/** + * struct ixgbe_aci_desc - Admin Command (AC) descriptor + * @flags: IXGBE_ACI_FLAG_* flags + * @opcode: Admin command opcode + * @datalen: length in bytes of indirect/external data buffer + * @retval: return value from firmware + * @cookie_high: opaque data high-half + * @cookie_low: opaque data low-half + * @params: command-specific parameters + * + * Descriptor format for commands the driver posts via the + * Admin Command Interface (ACI). + * The firmware writes back onto the command descriptor and returns + * the result of the command. Asynchronous events that are not an immediate + * result of the command are written to the Admin Command Interface (ACI) using + * the same descriptor format. Descriptors are in little-endian notation with + * 32-bit words. + */ +struct ixgbe_aci_desc { + __le16 flags; + __le16 opcode; + __le16 datalen; + __le16 retval; + __le32 cookie_high; + __le32 cookie_low; + union { + u8 raw[16]; + struct ixgbe_aci_cmd_get_ver get_ver; + struct ixgbe_aci_cmd_driver_ver driver_ver; + struct ixgbe_aci_cmd_get_exp_err exp_err; + struct ixgbe_aci_cmd_req_res res_owner; + struct ixgbe_aci_cmd_list_caps get_cap; + struct ixgbe_aci_cmd_disable_rxen disable_rxen; + struct ixgbe_aci_cmd_get_phy_caps get_phy; + struct ixgbe_aci_cmd_set_phy_cfg set_phy; + struct ixgbe_aci_cmd_restart_an restart_an; + struct ixgbe_aci_cmd_get_link_status get_link_status; + struct ixgbe_aci_cmd_set_event_mask set_event_mask; + struct ixgbe_aci_cmd_get_link_topo get_link_topo; + struct ixgbe_aci_cmd_get_link_topo_pin get_link_topo_pin; + struct ixgbe_aci_cmd_sff_eeprom read_write_sff_param; + struct ixgbe_aci_cmd_nvm nvm; + struct ixgbe_aci_cmd_nvm_checksum nvm_checksum; + } params; +}; + +/* E610-specific adapter context structures */ + +struct ixgbe_link_status { + /* Refer to ixgbe_aci_phy_type for bits definition */ + u64 phy_type_low; + u64 phy_type_high; + u16 max_frame_size; + u16 link_speed; + u16 req_speeds; + u8 topo_media_conflict; + u8 link_cfg_err; + u8 lse_ena; /* Link Status Event notification */ + u8 link_info; + u8 an_info; + u8 ext_info; + u8 fec_info; + u8 pacing; + /* Refer to #define from module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE] + * of ixgbe_aci_get_phy_caps structure + */ + u8 module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE]; +}; + +/* Common HW capabilities for SW use */ +struct ixgbe_hw_caps { + /* Write CSR protection */ + u64 wr_csr_prot; + u32 switching_mode; + /* switching mode supported - EVB switching (including cloud) */ +#define IXGBE_NVM_IMAGE_TYPE_EVB 0x0 + + /* Manageability mode & supported protocols over MCTP */ + u32 mgmt_mode; +#define IXGBE_MGMT_MODE_PASS_THRU_MODE_M GENMASK(3, 0) +#define IXGBE_MGMT_MODE_CTL_INTERFACE_M GENMASK(7, 4) +#define IXGBE_MGMT_MODE_REDIR_SB_INTERFACE_M GENMASK(11, 8) + + u32 mgmt_protocols_mctp; +#define IXGBE_MGMT_MODE_PROTO_RSVD BIT(0) +#define IXGBE_MGMT_MODE_PROTO_PLDM BIT(1) +#define IXGBE_MGMT_MODE_PROTO_OEM BIT(2) +#define IXGBE_MGMT_MODE_PROTO_NC_SI BIT(3) + + u32 os2bmc; + u32 valid_functions; + /* DCB capabilities */ + u32 active_tc_bitmap; + u32 maxtc; + + /* RSS related capabilities */ + u32 rss_table_size; /* 512 for PFs and 64 for VFs */ + u32 rss_table_entry_width; /* RSS Entry width in bits */ + + /* Tx/Rx queues */ + u32 num_rxq; /* Number/Total Rx queues */ + u32 rxq_first_id; /* First queue ID for Rx queues */ + u32 num_txq; /* Number/Total Tx queues */ + u32 txq_first_id; /* First queue ID for Tx queues */ + + /* MSI-X vectors */ + u32 num_msix_vectors; + u32 msix_vector_first_id; + + /* Max MTU for function or device */ + u32 max_mtu; + + /* WOL related */ + u32 num_wol_proxy_fltr; + u32 wol_proxy_vsi_seid; + + /* LED/SDP pin count */ + u32 led_pin_num; + u32 sdp_pin_num; + + /* LED/SDP - Supports up to 12 LED pins and 8 SDP signals */ +#define IXGBE_MAX_SUPPORTED_GPIO_LED 12 +#define IXGBE_MAX_SUPPORTED_GPIO_SDP 8 + u8 led[IXGBE_MAX_SUPPORTED_GPIO_LED]; + u8 sdp[IXGBE_MAX_SUPPORTED_GPIO_SDP]; + /* SR-IOV virtualization */ + u8 sr_iov_1_1; /* SR-IOV enabled */ + /* VMDQ */ + u8 vmdq; /* VMDQ supported */ + + /* EVB capabilities */ + u8 evb_802_1_qbg; /* Edge Virtual Bridging */ + u8 evb_802_1_qbh; /* Bridge Port Extension */ + + u8 dcb; + u8 iscsi; + u8 ieee_1588; + u8 mgmt_cem; + + /* WoL and APM support */ +#define IXGBE_WOL_SUPPORT_M BIT(0) +#define IXGBE_ACPI_PROG_MTHD_M BIT(1) +#define IXGBE_PROXY_SUPPORT_M BIT(2) + u8 apm_wol_support; + u8 acpi_prog_mthd; + u8 proxy_support; + bool nvm_update_pending_nvm; + bool nvm_update_pending_orom; + bool nvm_update_pending_netlist; +#define IXGBE_NVM_PENDING_NVM_IMAGE BIT(0) +#define IXGBE_NVM_PENDING_OROM BIT(1) +#define IXGBE_NVM_PENDING_NETLIST BIT(2) + bool sec_rev_disabled; + bool update_disabled; + bool nvm_unified_update; + bool netlist_auth; +#define IXGBE_NVM_MGMT_SEC_REV_DISABLED BIT(0) +#define IXGBE_NVM_MGMT_UPDATE_DISABLED BIT(1) +#define IXGBE_NVM_MGMT_UNIFIED_UPD_SUPPORT BIT(3) +#define IXGBE_NVM_MGMT_NETLIST_AUTH_SUPPORT BIT(5) + bool no_drop_policy_support; + /* PCIe reset avoidance */ + bool pcie_reset_avoidance; /* false: not supported, true: supported */ + /* Post update reset restriction */ + bool reset_restrict_support; /* false: not supported, true: supported */ + + /* External topology device images within the NVM */ +#define IXGBE_EXT_TOPO_DEV_IMG_COUNT 4 + u32 ext_topo_dev_img_ver_high[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; + u32 ext_topo_dev_img_ver_low[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; + u8 ext_topo_dev_img_part_num[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; +#define IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_S 8 +#define IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_M GENMASK(15, 8) + bool ext_topo_dev_img_load_en[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; +#define IXGBE_EXT_TOPO_DEV_IMG_LOAD_EN BIT(0) + bool ext_topo_dev_img_prog_en[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; +#define IXGBE_EXT_TOPO_DEV_IMG_PROG_EN BIT(1) +} __packed; + +/* Function specific capabilities */ +struct ixgbe_hw_func_caps { + u32 num_allocd_vfs; /* Number of allocated VFs */ + u32 vf_base_id; /* Logical ID of the first VF */ + u32 guar_num_vsi; + struct ixgbe_hw_caps common_cap; + bool no_drop_policy_ena; +}; + +/* Device wide capabilities */ +struct ixgbe_hw_dev_caps { + struct ixgbe_hw_caps common_cap; + u32 num_vfs_exposed; /* Total number of VFs exposed */ + u32 num_vsi_allocd_to_host; /* Excluding EMP VSI */ + u32 num_flow_director_fltr; /* Number of FD filters available */ + u32 num_funcs; +}; + +/* ACI event information */ +struct ixgbe_aci_event { + struct ixgbe_aci_desc desc; + u8 *msg_buf; + u16 msg_len; + u16 buf_len; +}; + +struct ixgbe_aci_info { + struct mutex lock; /* admin command interface lock */ + enum ixgbe_aci_err last_status; /* last status of sent admin command */ +}; + +/* Option ROM version information */ +struct ixgbe_orom_info { + u8 major; /* Major version of OROM */ + u8 patch; /* Patch version of OROM */ + u16 build; /* Build version of OROM */ + u32 srev; /* Security revision */ +}; + +/* NVM version information */ +struct ixgbe_nvm_info { + u32 eetrack; + u32 srev; + u8 major; + u8 minor; +} __packed; + +/* netlist version information */ +struct ixgbe_netlist_info { + u32 major; /* major high/low */ + u32 minor; /* minor high/low */ + u32 type; /* type high/low */ + u32 rev; /* revision high/low */ + u32 hash; /* SHA-1 hash word */ + u16 cust_ver; /* customer version */ +} __packed; + +/* Enumeration of possible flash banks for the NVM, OROM, and Netlist modules + * of the flash image. + */ +enum ixgbe_flash_bank { + IXGBE_INVALID_FLASH_BANK, + IXGBE_1ST_FLASH_BANK, + IXGBE_2ND_FLASH_BANK, +}; + +/* information for accessing NVM, OROM, and Netlist flash banks */ +struct ixgbe_bank_info { + u32 nvm_ptr; /* Pointer to 1st NVM bank */ + u32 nvm_size; /* Size of NVM bank */ + u32 orom_ptr; /* Pointer to 1st OROM bank */ + u32 orom_size; /* Size of OROM bank */ + u32 netlist_ptr; /* Ptr to 1st Netlist bank */ + u32 netlist_size; /* Size of Netlist bank */ + enum ixgbe_flash_bank nvm_bank; /* Active NVM bank */ + enum ixgbe_flash_bank orom_bank; /* Active OROM bank */ + enum ixgbe_flash_bank netlist_bank; /* Active Netlist bank */ +}; + +/* Flash Chip Information */ +struct ixgbe_flash_info { + struct ixgbe_orom_info orom; /* Option ROM version info */ + u32 flash_size; /* Available flash size in bytes */ + struct ixgbe_nvm_info nvm; /* NVM version information */ + struct ixgbe_netlist_info netlist; /* Netlist version info */ + struct ixgbe_bank_info banks; /* Flash Bank information */ + u16 sr_words; /* Shadow RAM size in words */ + u8 blank_nvm_mode; /* is NVM empty (no FW present) */ +}; + +#endif /* _IXGBE_TYPE_E610_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 81e1df83f136..1fc821fb351a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include #include @@ -66,7 +66,9 @@ int ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw, ixgbe_link_speed speed, * Resets the hardware by resetting the transmit and receive units, masks * and clears all interrupts, perform a PHY reset, and perform a link (MAC) * reset. - **/ + * + * Return: 0 on success or negative value on failure + */ int ixgbe_reset_hw_X540(struct ixgbe_hw *hw) { u32 swfw_mask = hw->phy.phy_semaphore_mask; @@ -133,10 +135,14 @@ mac_reset_top: hw->mac.num_rar_entries = IXGBE_X540_MAX_TX_QUEUES; hw->mac.ops.init_rx_addrs(hw); + /* The following is not supported by E610. */ + if (hw->mac.type == ixgbe_mac_e610) + return status; + /* Store the permanent SAN mac address */ hw->mac.ops.get_san_mac_addr(hw, hw->mac.san_addr); - /* Add the SAN MAC address to the RAR only if it's a valid address */ + /* Add the SAN MAC address to RAR if it's a valid address */ if (is_valid_ether_addr(hw->mac.san_addr)) { /* Save the SAN MAC RAR index */ hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h index b69a680d3ab5..6ed360c5b605 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h @@ -1,5 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ + +#ifndef _IXGBE_X540_H_ +#define _IXGBE_X540_H_ #include "ixgbe_type.h" @@ -17,3 +20,5 @@ int ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask); void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask); void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw); int ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw); + +#endif /* _IXGBE_X540_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index d9a8cf018d3b..277ceaf8a793 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include "ixgbe_x540.h" +#include "ixgbe_x550.h" #include "ixgbe_type.h" #include "ixgbe_common.h" #include "ixgbe_mbx.h" @@ -2770,9 +2771,9 @@ static int ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) * semaphore, -EIO when command fails or -ENIVAL when incorrect * params passed. **/ -static int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, - u8 build, u8 sub, u16 len, - const char *driver_ver) +int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 sub, u16 len, + const char *driver_ver) { struct ixgbe_hic_drv_info2 fw_cmd; int ret_val; @@ -3505,14 +3506,14 @@ mac_reset_top: return status; } -/** ixgbe_set_ethertype_anti_spoofing_X550 - Enable/Disable Ethertype +/** ixgbe_set_ethertype_anti_spoofing_x550 - Enable/Disable Ethertype * anti-spoofing * @hw: pointer to hardware structure * @enable: enable or disable switch for Ethertype anti-spoofing * @vf: Virtual Function pool - VF Pool to set for Ethertype anti-spoofing **/ -static void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw, - bool enable, int vf) +void ixgbe_set_ethertype_anti_spoofing_x550(struct ixgbe_hw *hw, + bool enable, int vf) { int vf_target_reg = vf >> 3; int vf_target_shift = vf % 8 + IXGBE_SPOOF_ETHERTYPEAS_SHIFT; @@ -3527,14 +3528,14 @@ static void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw, IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), pfvfspoof); } -/** ixgbe_set_source_address_pruning_X550 - Enable/Disbale src address pruning +/** ixgbe_set_source_address_pruning_x550 - Enable/Disable src address pruning * @hw: pointer to hardware structure * @enable: enable or disable source address pruning * @pool: Rx pool to set source address pruning for **/ -static void ixgbe_set_source_address_pruning_X550(struct ixgbe_hw *hw, - bool enable, - unsigned int pool) +void ixgbe_set_source_address_pruning_x550(struct ixgbe_hw *hw, + bool enable, + unsigned int pool) { u64 pfflp; @@ -3831,9 +3832,9 @@ static int ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, .set_mac_anti_spoofing = &ixgbe_set_mac_anti_spoofing, \ .set_vlan_anti_spoofing = &ixgbe_set_vlan_anti_spoofing, \ .set_source_address_pruning = \ - &ixgbe_set_source_address_pruning_X550, \ + &ixgbe_set_source_address_pruning_x550, \ .set_ethertype_anti_spoofing = \ - &ixgbe_set_ethertype_anti_spoofing_X550, \ + &ixgbe_set_ethertype_anti_spoofing_x550, \ .disable_rx_buff = &ixgbe_disable_rx_buff_generic, \ .enable_rx_buff = &ixgbe_enable_rx_buff_generic, \ .get_thermal_sensor_data = NULL, \ @@ -4047,7 +4048,7 @@ static const u32 ixgbe_mvals_X550EM_x[IXGBE_MVALS_IDX_LIMIT] = { IXGBE_MVALS_INIT(X550EM_x) }; -static const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT] = { +const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT] = { IXGBE_MVALS_INIT(X550EM_a) }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h new file mode 100644 index 000000000000..3e4092f8da3e --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IXGBE_X550_H_ +#define _IXGBE_X550_H_ + +#include "ixgbe_type.h" + +extern const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT]; + +int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 sub, u16 len, + const char *driver_ver); +void ixgbe_set_source_address_pruning_x550(struct ixgbe_hw *hw, + bool enable, + unsigned int pool); +void ixgbe_set_ethertype_anti_spoofing_x550(struct ixgbe_hw *hw, + bool enable, int vf); + +#endif /* _IXGBE_X550_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h index 5f08779c0e4e..a9bc96f6399d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/defines.h +++ b/drivers/net/ethernet/intel/ixgbevf/defines.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef _IXGBEVF_DEFINES_H_ #define _IXGBEVF_DEFINES_H_ @@ -16,6 +16,9 @@ #define IXGBE_DEV_ID_X550_VF_HV 0x1564 #define IXGBE_DEV_ID_X550EM_X_VF_HV 0x15A9 +#define IXGBE_DEV_ID_E610_VF 0x57AD +#define IXGBE_SUBDEV_ID_E610_VF_HV 0x00FF + #define IXGBE_VF_IRQ_CLEAR_MASK 7 #define IXGBE_VF_MAX_TX_QUEUES 8 #define IXGBE_VF_MAX_RX_QUEUES 8 diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 130cb868774c..4384e892f967 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef _IXGBEVF_H_ #define _IXGBEVF_H_ @@ -418,6 +418,8 @@ enum ixgbevf_boards { board_X550EM_x_vf, board_X550EM_x_vf_hv, board_x550em_a_vf, + board_e610_vf, + board_e610_vf_hv, }; enum ixgbevf_xcast_modes { @@ -434,12 +436,13 @@ extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_info; extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops; extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops_legacy; extern const struct ixgbevf_info ixgbevf_x550em_a_vf_info; +extern const struct ixgbevf_info ixgbevf_e610_vf_info; extern const struct ixgbevf_info ixgbevf_82599_vf_hv_info; extern const struct ixgbevf_info ixgbevf_X540_vf_hv_info; extern const struct ixgbevf_info ixgbevf_X550_vf_hv_info; extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_hv_info; -extern const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops; +extern const struct ixgbevf_info ixgbevf_e610_vf_hv_info; /* needed by ethtool.c */ extern const char ixgbevf_driver_name[]; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 149911e3002a..6442f115a262 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ /****************************************************************************** Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code @@ -39,7 +39,7 @@ static const char ixgbevf_driver_string[] = "Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver"; static char ixgbevf_copyright[] = - "Copyright (c) 2009 - 2018 Intel Corporation."; + "Copyright (c) 2009 - 2024 Intel Corporation."; static const struct ixgbevf_info *ixgbevf_info_tbl[] = { [board_82599_vf] = &ixgbevf_82599_vf_info, @@ -51,6 +51,8 @@ static const struct ixgbevf_info *ixgbevf_info_tbl[] = { [board_X550EM_x_vf] = &ixgbevf_X550EM_x_vf_info, [board_X550EM_x_vf_hv] = &ixgbevf_X550EM_x_vf_hv_info, [board_x550em_a_vf] = &ixgbevf_x550em_a_vf_info, + [board_e610_vf] = &ixgbevf_e610_vf_info, + [board_e610_vf_hv] = &ixgbevf_e610_vf_hv_info, }; /* ixgbevf_pci_tbl - PCI Device ID Table @@ -71,6 +73,9 @@ static const struct pci_device_id ixgbevf_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF), board_X550EM_x_vf }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF_HV), board_X550EM_x_vf_hv}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_VF), board_x550em_a_vf }, + {PCI_VDEVICE_SUB(INTEL, IXGBE_DEV_ID_E610_VF, PCI_ANY_ID, + IXGBE_SUBDEV_ID_E610_VF_HV), board_e610_vf_hv}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_VF), board_e610_vf}, /* required last entry */ {0, } }; @@ -732,10 +737,6 @@ static bool ixgbevf_cleanup_headers(struct ixgbevf_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - /* verify that the packet does not have any known errors */ if (unlikely(ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FRAME_ERR_MASK))) { @@ -1044,9 +1045,9 @@ static int ixgbevf_xmit_xdp_ring(struct ixgbevf_ring *ring, return IXGBEVF_XDP_TX; } -static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *rx_ring, - struct xdp_buff *xdp) +static int ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *rx_ring, + struct xdp_buff *xdp) { int result = IXGBEVF_XDP_PASS; struct ixgbevf_ring *xdp_ring; @@ -1080,7 +1081,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int ixgbevf_rx_frame_truesize(struct ixgbevf_ring *rx_ring, @@ -1122,6 +1123,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, struct sk_buff *skb = rx_ring->skb; bool xdp_xmit = false; struct xdp_buff xdp; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -1165,11 +1167,11 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = ixgbevf_rx_frame_truesize(rx_ring, size); #endif - skb = ixgbevf_run_xdp(adapter, rx_ring, &xdp); + xdp_res = ixgbevf_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -IXGBEVF_XDP_TX) { + if (xdp_res) { + if (xdp_res == IXGBEVF_XDP_TX) { xdp_xmit = true; ixgbevf_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -1189,7 +1191,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, } /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; rx_buffer->pagecnt_bias++; break; @@ -1203,7 +1205,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, continue; /* verify the packet layout is correct */ - if (ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } @@ -4693,6 +4695,9 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) case ixgbe_mac_X540_vf: dev_info(&pdev->dev, "Intel(R) X540 Virtual Function\n"); break; + case ixgbe_mac_e610_vf: + dev_info(&pdev->dev, "Intel(R) E610 Virtual Function\n"); + break; case ixgbe_mac_82599_vf: default: dev_info(&pdev->dev, "Intel(R) 82599 Virtual Function\n"); diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c index a55dd978f7ca..24d0237e7a99 100644 --- a/drivers/net/ethernet/intel/ixgbevf/mbx.c +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c @@ -505,15 +505,3 @@ const struct ixgbe_mbx_operations ixgbevf_mbx_ops_legacy = { .check_for_ack = ixgbevf_check_for_ack_vf, .check_for_rst = ixgbevf_check_for_rst_vf, }; - -/* Mailbox operations when running on Hyper-V. - * On Hyper-V, PF/VF communication is not through the - * hardware mailbox; this communication is through - * a software mediated path. - * Most mail box operations are noop while running on - * Hyper-V. - */ -const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops = { - .init_params = ixgbevf_init_mbx_params_vf, - .check_for_rst = ixgbevf_check_for_rst_vf, -}; diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 1641d00d8ed3..da7a72ecce7a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include "vf.h" #include "ixgbevf.h" @@ -1076,3 +1076,13 @@ const struct ixgbevf_info ixgbevf_x550em_a_vf_info = { .mac = ixgbe_mac_x550em_a_vf, .mac_ops = &ixgbevf_mac_ops, }; + +const struct ixgbevf_info ixgbevf_e610_vf_info = { + .mac = ixgbe_mac_e610_vf, + .mac_ops = &ixgbevf_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_e610_vf_hv_info = { + .mac = ixgbe_mac_e610_vf, + .mac_ops = &ixgbevf_hv_mac_ops, +}; diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h index b4eef5b6c172..2d791bc26ae4 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.h +++ b/drivers/net/ethernet/intel/ixgbevf/vf.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef __IXGBE_VF_H__ #define __IXGBE_VF_H__ @@ -54,6 +54,8 @@ enum ixgbe_mac_type { ixgbe_mac_X550_vf, ixgbe_mac_X550EM_x_vf, ixgbe_mac_x550em_a_vf, + ixgbe_mac_e610, + ixgbe_mac_e610_vf, ixgbe_num_macs }; diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 660dff5426e7..83ce3bfefa5c 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -90,7 +90,6 @@ struct ltq_etop_priv { struct net_device *netdev; struct platform_device *pdev; struct ltq_eth_data *pldata; - struct resource *res; struct mii_bus *mii_bus; @@ -643,31 +642,14 @@ ltq_etop_probe(struct platform_device *pdev) { struct net_device *dev; struct ltq_etop_priv *priv; - struct resource *res; int err; int i; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - dev_err(&pdev->dev, "failed to get etop resource\n"); - err = -ENOENT; - goto err_out; - } - - res = devm_request_mem_region(&pdev->dev, res->start, - resource_size(res), dev_name(&pdev->dev)); - if (!res) { - dev_err(&pdev->dev, "failed to request etop resource\n"); - err = -EBUSY; - goto err_out; - } - - ltq_etop_membase = devm_ioremap(&pdev->dev, res->start, - resource_size(res)); - if (!ltq_etop_membase) { + ltq_etop_membase = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(ltq_etop_membase)) { dev_err(&pdev->dev, "failed to remap etop engine %d\n", pdev->id); - err = -ENOMEM; + err = PTR_ERR(ltq_etop_membase); goto err_out; } @@ -679,7 +661,6 @@ ltq_etop_probe(struct platform_device *pdev) dev->netdev_ops = <q_eth_netdev_ops; dev->ethtool_ops = <q_etop_ethtool_ops; priv = netdev_priv(dev); - priv->res = res; priv->pdev = pdev; priv->pldata = dev_get_platdata(&pdev->dev); priv->netdev = dev; diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index a06048719e84..67a6ff07c83d 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2704,9 +2704,15 @@ static struct platform_device *port_platdev[3]; static void mv643xx_eth_shared_of_remove(void) { + struct mv643xx_eth_platform_data *pd; int n; for (n = 0; n < 3; n++) { + if (!port_platdev[n]) + continue; + pd = dev_get_platdata(&port_platdev[n]->dev); + if (pd) + of_node_put(pd->phy_node); platform_device_del(port_platdev[n]); port_platdev[n] = NULL; } @@ -2769,8 +2775,10 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, } ppdev = platform_device_alloc(MV643XX_ETH_NAME, dev_num); - if (!ppdev) - return -ENOMEM; + if (!ppdev) { + ret = -ENOMEM; + goto put_err; + } ppdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); ppdev->dev.of_node = pnp; @@ -2792,6 +2800,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, port_err: platform_device_put(ppdev); +put_err: + of_node_put(ppd.phy_node); return ret; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 1fb285fa0bdb..4fe121b9f94b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -284,8 +284,12 @@ MVNETA_TXQ_BUCKET_REFILL_PERIOD)) #define MVNETA_LPI_CTRL_0 0x2cc0 +#define MVNETA_LPI_CTRL_0_TS (0xff << 8) #define MVNETA_LPI_CTRL_1 0x2cc4 -#define MVNETA_LPI_REQUEST_ENABLE BIT(0) +#define MVNETA_LPI_CTRL_1_REQUEST_ENABLE BIT(0) +#define MVNETA_LPI_CTRL_1_REQUEST_FORCE BIT(1) +#define MVNETA_LPI_CTRL_1_MANUAL_MODE BIT(2) +#define MVNETA_LPI_CTRL_1_TW (0xfff << 4) #define MVNETA_LPI_CTRL_2 0x2cc8 #define MVNETA_LPI_STATUS 0x2ccc @@ -541,10 +545,6 @@ struct mvneta_port { struct mvneta_bm_pool *pool_short; int bm_win_id; - bool eee_enabled; - bool eee_active; - bool tx_lpi_enabled; - u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)]; u32 indir[MVNETA_RSS_LU_TABLE_SIZE]; @@ -3960,23 +3960,30 @@ static struct mvneta_port *mvneta_pcs_to_port(struct phylink_pcs *pcs) return container_of(pcs, struct mvneta_port, phylink_pcs); } -static int mvneta_pcs_validate(struct phylink_pcs *pcs, - unsigned long *supported, - const struct phylink_link_state *state) +static unsigned int mvneta_pcs_inband_caps(struct phylink_pcs *pcs, + phy_interface_t interface) { - /* We only support QSGMII, SGMII, 802.3z and RGMII modes. - * When in 802.3z mode, we must have AN enabled: + /* When operating in an 802.3z mode, we must have AN enabled: * "Bit 2 Field InBandAnEn In-band Auto-Negotiation enable. ... * When = 1 (1000BASE-X) this field must be set to 1." + * Therefore, inband is "required". */ - if (phy_interface_mode_is_8023z(state->interface) && - !phylink_test(state->advertising, Autoneg)) - return -EINVAL; + if (phy_interface_mode_is_8023z(interface)) + return LINK_INBAND_ENABLE; - return 0; + /* QSGMII, SGMII and RGMII can be configured to use inband + * signalling of the AN result. Indicate these as "possible". + */ + if (interface == PHY_INTERFACE_MODE_SGMII || + interface == PHY_INTERFACE_MODE_QSGMII || + phy_interface_mode_is_rgmii(interface)) + return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE; + + /* For any other modes, indicate that inband is not supported. */ + return LINK_INBAND_DISABLE; } -static void mvneta_pcs_get_state(struct phylink_pcs *pcs, +static void mvneta_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct mvneta_port *pp = mvneta_pcs_to_port(pcs); @@ -4071,7 +4078,7 @@ static void mvneta_pcs_an_restart(struct phylink_pcs *pcs) } static const struct phylink_pcs_ops mvneta_phylink_pcs_ops = { - .pcs_validate = mvneta_pcs_validate, + .pcs_inband_caps = mvneta_pcs_inband_caps, .pcs_get_state = mvneta_pcs_get_state, .pcs_config = mvneta_pcs_config, .pcs_an_restart = mvneta_pcs_an_restart, @@ -4206,18 +4213,6 @@ static int mvneta_mac_finish(struct phylink_config *config, unsigned int mode, return 0; } -static void mvneta_set_eee(struct mvneta_port *pp, bool enable) -{ - u32 lpi_ctl1; - - lpi_ctl1 = mvreg_read(pp, MVNETA_LPI_CTRL_1); - if (enable) - lpi_ctl1 |= MVNETA_LPI_REQUEST_ENABLE; - else - lpi_ctl1 &= ~MVNETA_LPI_REQUEST_ENABLE; - mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi_ctl1); -} - static void mvneta_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { @@ -4233,9 +4228,6 @@ static void mvneta_mac_link_down(struct phylink_config *config, val |= MVNETA_GMAC_FORCE_LINK_DOWN; mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val); } - - pp->eee_active = false; - mvneta_set_eee(pp, false); } static void mvneta_mac_link_up(struct phylink_config *config, @@ -4284,11 +4276,56 @@ static void mvneta_mac_link_up(struct phylink_config *config, } mvneta_port_up(pp); +} - if (phy && pp->eee_enabled) { - pp->eee_active = phy_init_eee(phy, false) >= 0; - mvneta_set_eee(pp, pp->eee_active && pp->tx_lpi_enabled); +static void mvneta_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct mvneta_port *pp = netdev_priv(to_net_dev(config->dev)); + u32 lpi1; + + lpi1 = mvreg_read(pp, MVNETA_LPI_CTRL_1); + lpi1 &= ~(MVNETA_LPI_CTRL_1_REQUEST_ENABLE | + MVNETA_LPI_CTRL_1_REQUEST_FORCE | + MVNETA_LPI_CTRL_1_MANUAL_MODE); + mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi1); +} + +static int mvneta_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop) +{ + struct mvneta_port *pp = netdev_priv(to_net_dev(config->dev)); + u32 ts, tw, lpi0, lpi1, status; + + status = mvreg_read(pp, MVNETA_GMAC_STATUS); + if (status & MVNETA_GMAC_SPEED_1000) { + /* At 1G speeds, the timer resolution are 1us, and + * 802.3 says tw is 16.5us. Round up to 17us. + */ + tw = 17; + ts = timer; + } else { + /* At 100M speeds, the timer resolutions are 10us, and + * 802.3 says tw is 30us. + */ + tw = 3; + ts = DIV_ROUND_UP(timer, 10); } + + if (ts > 255) + ts = 255; + + /* Configure ts */ + lpi0 = mvreg_read(pp, MVNETA_LPI_CTRL_0); + lpi0 = u32_replace_bits(lpi0, ts, MVNETA_LPI_CTRL_0_TS); + mvreg_write(pp, MVNETA_LPI_CTRL_0, lpi0); + + /* Configure tw and enable LPI generation */ + lpi1 = mvreg_read(pp, MVNETA_LPI_CTRL_1); + lpi1 = u32_replace_bits(lpi1, tw, MVNETA_LPI_CTRL_1_TW); + lpi1 |= MVNETA_LPI_CTRL_1_REQUEST_ENABLE; + mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi1); + + return 0; } static const struct phylink_mac_ops mvneta_phylink_ops = { @@ -4298,6 +4335,8 @@ static const struct phylink_mac_ops mvneta_phylink_ops = { .mac_finish = mvneta_mac_finish, .mac_link_down = mvneta_mac_link_down, .mac_link_up = mvneta_mac_link_up, + .mac_disable_tx_lpi = mvneta_mac_disable_tx_lpi, + .mac_enable_tx_lpi = mvneta_mac_enable_tx_lpi, }; static int mvneta_mdio_probe(struct mvneta_port *pp) @@ -4385,6 +4424,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node) if (pp->neta_armada3700) return 0; + netdev_lock(port->napi.dev); spin_lock(&pp->lock); /* * Configuring the driver for a new CPU while the driver is @@ -4392,6 +4432,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node) */ if (pp->is_stopped) { spin_unlock(&pp->lock); + netdev_unlock(port->napi.dev); return 0; } netif_tx_stop_all_queues(pp->dev); @@ -4411,7 +4452,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node) /* Mask all ethernet port interrupts */ on_each_cpu(mvneta_percpu_mask_interrupt, pp, true); - napi_enable(&port->napi); + napi_enable_locked(&port->napi); /* * Enable per-CPU interrupts on the CPU that is @@ -4432,6 +4473,8 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node) MVNETA_CAUSE_LINK_CHANGE); netif_tx_start_all_queues(pp->dev); spin_unlock(&pp->lock); + netdev_unlock(port->napi.dev); + return 0; } @@ -5099,14 +5142,6 @@ static int mvneta_ethtool_get_eee(struct net_device *dev, struct ethtool_keee *eee) { struct mvneta_port *pp = netdev_priv(dev); - u32 lpi_ctl0; - - lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0); - - eee->eee_enabled = pp->eee_enabled; - eee->eee_active = pp->eee_active; - eee->tx_lpi_enabled = pp->tx_lpi_enabled; - eee->tx_lpi_timer = (lpi_ctl0) >> 8; // * scale; return phylink_ethtool_get_eee(pp->phylink, eee); } @@ -5115,7 +5150,6 @@ static int mvneta_ethtool_set_eee(struct net_device *dev, struct ethtool_keee *eee) { struct mvneta_port *pp = netdev_priv(dev); - u32 lpi_ctl0; /* The Armada 37x documents do not give limits for this other than * it being an 8-bit register. @@ -5123,16 +5157,6 @@ static int mvneta_ethtool_set_eee(struct net_device *dev, if (eee->tx_lpi_enabled && eee->tx_lpi_timer > 255) return -EINVAL; - lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0); - lpi_ctl0 &= ~(0xff << 8); - lpi_ctl0 |= eee->tx_lpi_timer << 8; - mvreg_write(pp, MVNETA_LPI_CTRL_0, lpi_ctl0); - - pp->eee_enabled = eee->eee_enabled; - pp->tx_lpi_enabled = eee->tx_lpi_enabled; - - mvneta_set_eee(pp, eee->tx_lpi_enabled && eee->eee_enabled); - return phylink_ethtool_set_eee(pp->phylink, eee); } @@ -5446,6 +5470,9 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) !phy_interface_mode_is_rgmii(phy_mode)) return -EINVAL; + /* Ensure LPI is disabled */ + mvneta_mac_disable_tx_lpi(&pp->phylink_config); + return 0; } @@ -5537,6 +5564,13 @@ static int mvneta_probe(struct platform_device *pdev) pp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD; + /* Setup EEE. Choose 250us idle. Only supported in SGMII modes. */ + __set_bit(PHY_INTERFACE_MODE_QSGMII, pp->phylink_config.lpi_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, pp->phylink_config.lpi_interfaces); + pp->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD; + pp->phylink_config.lpi_timer_default = 250; + pp->phylink_config.eee_enabled_default = true; + phy_interface_set_rgmii(pp->phylink_config.supported_interfaces); __set_bit(PHY_INTERFACE_MODE_QSGMII, pp->phylink_config.supported_interfaces); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 9e02e4367bec..44fe9b68d1c2 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -481,6 +481,11 @@ #define MVPP22_GMAC_INT_SUM_MASK 0xa4 #define MVPP22_GMAC_INT_SUM_MASK_LINK_STAT BIT(1) #define MVPP22_GMAC_INT_SUM_MASK_PTP BIT(2) +#define MVPP2_GMAC_LPI_CTRL0 0xc0 +#define MVPP2_GMAC_LPI_CTRL0_TS_MASK GENMASK(15, 8) +#define MVPP2_GMAC_LPI_CTRL1 0xc4 +#define MVPP2_GMAC_LPI_CTRL1_REQ_EN BIT(0) +#define MVPP2_GMAC_LPI_CTRL1_TW_MASK GENMASK(15, 4) /* Per-port XGMAC registers. PPv2.2 and PPv2.3, only for GOP port 0, * relative to port->base. diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 571631a30320..dd76c1b7ed3a 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5757,6 +5757,28 @@ static int mvpp2_ethtool_set_rxfh(struct net_device *dev, return mvpp2_modify_rxfh_context(dev, NULL, rxfh, extack); } +static int mvpp2_ethtool_get_eee(struct net_device *dev, + struct ethtool_keee *eee) +{ + struct mvpp2_port *port = netdev_priv(dev); + + if (!port->phylink) + return -EOPNOTSUPP; + + return phylink_ethtool_get_eee(port->phylink, eee); +} + +static int mvpp2_ethtool_set_eee(struct net_device *dev, + struct ethtool_keee *eee) +{ + struct mvpp2_port *port = netdev_priv(dev); + + if (!port->phylink) + return -EOPNOTSUPP; + + return phylink_ethtool_set_eee(port->phylink, eee); +} + /* Device ops */ static const struct net_device_ops mvpp2_netdev_ops = { @@ -5802,6 +5824,8 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { .create_rxfh_context = mvpp2_create_rxfh_context, .modify_rxfh_context = mvpp2_modify_rxfh_context, .remove_rxfh_context = mvpp2_remove_rxfh_context, + .get_eee = mvpp2_ethtool_get_eee, + .set_eee = mvpp2_ethtool_set_eee, }; /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that @@ -6188,6 +6212,7 @@ static struct mvpp2_port *mvpp2_pcs_gmac_to_port(struct phylink_pcs *pcs) } static void mvpp2_xlg_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mvpp2_port *port = mvpp2_pcs_xlg_to_port(pcs); @@ -6224,22 +6249,30 @@ static const struct phylink_pcs_ops mvpp2_phylink_xlg_pcs_ops = { .pcs_config = mvpp2_xlg_pcs_config, }; -static int mvpp2_gmac_pcs_validate(struct phylink_pcs *pcs, - unsigned long *supported, - const struct phylink_link_state *state) +static unsigned int mvpp2_gmac_pcs_inband_caps(struct phylink_pcs *pcs, + phy_interface_t interface) { - /* When in 802.3z mode, we must have AN enabled: + /* When operating in an 802.3z mode, we must have AN enabled: * Bit 2 Field InBandAnEn In-band Auto-Negotiation enable. ... * When = 1 (1000BASE-X) this field must be set to 1. + * Therefore, inband is "required". */ - if (phy_interface_mode_is_8023z(state->interface) && - !phylink_test(state->advertising, Autoneg)) - return -EINVAL; + if (phy_interface_mode_is_8023z(interface)) + return LINK_INBAND_ENABLE; - return 0; + /* SGMII and RGMII can be configured to use inband signalling of the + * AN result. Indicate these as "possible". + */ + if (interface == PHY_INTERFACE_MODE_SGMII || + phy_interface_mode_is_rgmii(interface)) + return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE; + + /* For any other modes, indicate that inband is not supported. */ + return LINK_INBAND_DISABLE; } static void mvpp2_gmac_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mvpp2_port *port = mvpp2_pcs_gmac_to_port(pcs); @@ -6343,7 +6376,7 @@ static void mvpp2_gmac_pcs_an_restart(struct phylink_pcs *pcs) } static const struct phylink_pcs_ops mvpp2_phylink_gmac_pcs_ops = { - .pcs_validate = mvpp2_gmac_pcs_validate, + .pcs_inband_caps = mvpp2_gmac_pcs_inband_caps, .pcs_get_state = mvpp2_gmac_pcs_get_state, .pcs_config = mvpp2_gmac_pcs_config, .pcs_an_restart = mvpp2_gmac_pcs_an_restart, @@ -6665,6 +6698,55 @@ static void mvpp2_mac_link_down(struct phylink_config *config, mvpp2_port_disable(port); } +static void mvpp2_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct mvpp2_port *port = mvpp2_phylink_to_port(config); + + mvpp2_modify(port->base + MVPP2_GMAC_LPI_CTRL1, + MVPP2_GMAC_LPI_CTRL1_REQ_EN, 0); +} + +static int mvpp2_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop) +{ + struct mvpp2_port *port = mvpp2_phylink_to_port(config); + u32 ts, tw, lpi1, status; + + status = readl(port->base + MVPP2_GMAC_STATUS0); + if (status & MVPP2_GMAC_STATUS0_GMII_SPEED) { + /* At 1G speeds, the timer resolution are 1us, and + * 802.3 says tw is 16.5us. Round up to 17us. + */ + tw = 17; + ts = timer; + } else { + /* At 100M speeds, the timer resolutions are 10us, and + * 802.3 says tw is 30us. + */ + tw = 3; + ts = DIV_ROUND_UP(timer, 10); + } + + if (ts > 255) + ts = 255; + + /* Configure ts */ + mvpp2_modify(port->base + MVPP2_GMAC_LPI_CTRL0, + MVPP2_GMAC_LPI_CTRL0_TS_MASK, + FIELD_PREP(MVPP2_GMAC_LPI_CTRL0_TS_MASK, ts)); + + lpi1 = readl(port->base + MVPP2_GMAC_LPI_CTRL1); + + /* Configure tw */ + lpi1 = u32_replace_bits(lpi1, tw, MVPP2_GMAC_LPI_CTRL1_TW_MASK); + + /* Enable LPI generation */ + writel(lpi1 | MVPP2_GMAC_LPI_CTRL1_REQ_EN, + port->base + MVPP2_GMAC_LPI_CTRL1); + + return 0; +} + static const struct phylink_mac_ops mvpp2_phylink_ops = { .mac_select_pcs = mvpp2_select_pcs, .mac_prepare = mvpp2_mac_prepare, @@ -6672,6 +6754,8 @@ static const struct phylink_mac_ops mvpp2_phylink_ops = { .mac_finish = mvpp2_mac_finish, .mac_link_up = mvpp2_mac_link_up, .mac_link_down = mvpp2_mac_link_down, + .mac_enable_tx_lpi = mvpp2_mac_enable_tx_lpi, + .mac_disable_tx_lpi = mvpp2_mac_disable_tx_lpi, }; /* Work-around for ACPI */ @@ -6950,6 +7034,15 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->phylink_config.mac_capabilities = MAC_2500FD | MAC_1000FD | MAC_100 | MAC_10; + __set_bit(PHY_INTERFACE_MODE_SGMII, + port->phylink_config.lpi_interfaces); + + port->phylink_config.lpi_capabilities = MAC_1000FD | MAC_100FD; + + /* Setup EEE. Choose 250us idle. */ + port->phylink_config.lpi_timer_default = 250; + port->phylink_config.eee_enabled_default = true; + if (port->priv->global_tx_fc) port->phylink_config.mac_capabilities |= MAC_SYM_PAUSE | MAC_ASYM_PAUSE; @@ -7024,6 +7117,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, goto err_free_port_pcpu; } port->phylink = phylink; + + mvpp2_mac_disable_tx_lpi(&port->phylink_config); } else { dev_warn(&pdev->dev, "Use link irqs for port#%d. FW update required\n", port->id); port->phylink = NULL; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c index 4f4d58189118..a88c006ea65b 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c @@ -150,17 +150,14 @@ octep_get_ethtool_stats(struct net_device *netdev, iface_rx_stats, iface_tx_stats); - for (q = 0; q < oct->num_oqs; q++) { - struct octep_iq *iq = oct->iq[q]; - struct octep_oq *oq = oct->oq[q]; + for (q = 0; q < OCTEP_MAX_QUEUES; q++) { + tx_packets += oct->stats_iq[q].instr_completed; + tx_bytes += oct->stats_iq[q].bytes_sent; + tx_busy_errors += oct->stats_iq[q].tx_busy; - tx_packets += iq->stats.instr_completed; - tx_bytes += iq->stats.bytes_sent; - tx_busy_errors += iq->stats.tx_busy; - - rx_packets += oq->stats.packets; - rx_bytes += oq->stats.bytes; - rx_alloc_errors += oq->stats.alloc_failures; + rx_packets += oct->stats_oq[q].packets; + rx_bytes += oct->stats_oq[q].bytes; + rx_alloc_errors += oct->stats_oq[q].alloc_failures; } i = 0; data[i++] = rx_packets; @@ -198,22 +195,18 @@ octep_get_ethtool_stats(struct net_device *netdev, data[i++] = iface_rx_stats->err_pkts; /* Per Tx Queue stats */ - for (q = 0; q < oct->num_iqs; q++) { - struct octep_iq *iq = oct->iq[q]; - - data[i++] = iq->stats.instr_posted; - data[i++] = iq->stats.instr_completed; - data[i++] = iq->stats.bytes_sent; - data[i++] = iq->stats.tx_busy; + for (q = 0; q < OCTEP_MAX_QUEUES; q++) { + data[i++] = oct->stats_iq[q].instr_posted; + data[i++] = oct->stats_iq[q].instr_completed; + data[i++] = oct->stats_iq[q].bytes_sent; + data[i++] = oct->stats_iq[q].tx_busy; } /* Per Rx Queue stats */ - for (q = 0; q < oct->num_oqs; q++) { - struct octep_oq *oq = oct->oq[q]; - - data[i++] = oq->stats.packets; - data[i++] = oq->stats.bytes; - data[i++] = oq->stats.alloc_failures; + for (q = 0; q < OCTEP_MAX_QUEUES; q++) { + data[i++] = oct->stats_oq[q].packets; + data[i++] = oct->stats_oq[q].bytes; + data[i++] = oct->stats_oq[q].alloc_failures; } } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 549436efc204..0a679e95196f 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -822,7 +822,7 @@ static inline int octep_iq_full_check(struct octep_iq *iq) if (unlikely(IQ_INSTR_SPACE(iq) > OCTEP_WAKE_QUEUE_THRESHOLD)) { netif_start_subqueue(iq->netdev, iq->q_no); - iq->stats.restart_cnt++; + iq->stats->restart_cnt++; return 0; } @@ -960,7 +960,7 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb, wmb(); /* Ring Doorbell to notify the NIC of new packets */ writel(iq->fill_cnt, iq->doorbell_reg); - iq->stats.instr_posted += iq->fill_cnt; + iq->stats->instr_posted += iq->fill_cnt; iq->fill_cnt = 0; return NETDEV_TX_OK; @@ -991,37 +991,24 @@ dma_map_err: static void octep_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { - u64 tx_packets, tx_bytes, rx_packets, rx_bytes; struct octep_device *oct = netdev_priv(netdev); + u64 tx_packets, tx_bytes, rx_packets, rx_bytes; int q; - if (netif_running(netdev)) - octep_ctrl_net_get_if_stats(oct, - OCTEP_CTRL_NET_INVALID_VFID, - &oct->iface_rx_stats, - &oct->iface_tx_stats); - tx_packets = 0; tx_bytes = 0; rx_packets = 0; rx_bytes = 0; - for (q = 0; q < oct->num_oqs; q++) { - struct octep_iq *iq = oct->iq[q]; - struct octep_oq *oq = oct->oq[q]; - - tx_packets += iq->stats.instr_completed; - tx_bytes += iq->stats.bytes_sent; - rx_packets += oq->stats.packets; - rx_bytes += oq->stats.bytes; + for (q = 0; q < OCTEP_MAX_QUEUES; q++) { + tx_packets += oct->stats_iq[q].instr_completed; + tx_bytes += oct->stats_iq[q].bytes_sent; + rx_packets += oct->stats_oq[q].packets; + rx_bytes += oct->stats_oq[q].bytes; } stats->tx_packets = tx_packets; stats->tx_bytes = tx_bytes; stats->rx_packets = rx_packets; stats->rx_bytes = rx_bytes; - stats->multicast = oct->iface_rx_stats.mcast_pkts; - stats->rx_errors = oct->iface_rx_stats.err_pkts; - stats->collisions = oct->iface_tx_stats.xscol; - stats->tx_fifo_errors = oct->iface_tx_stats.undflw; } /** @@ -1137,6 +1124,43 @@ static int octep_set_features(struct net_device *dev, netdev_features_t features return err; } +static int octep_get_vf_config(struct net_device *dev, int vf, + struct ifla_vf_info *ivi) +{ + struct octep_device *oct = netdev_priv(dev); + + ivi->vf = vf; + ether_addr_copy(ivi->mac, oct->vf_info[vf].mac_addr); + ivi->spoofchk = true; + ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE; + ivi->trusted = false; + + return 0; +} + +static int octep_set_vf_mac(struct net_device *dev, int vf, u8 *mac) +{ + struct octep_device *oct = netdev_priv(dev); + int err; + + if (!is_valid_ether_addr(mac)) { + dev_err(&oct->pdev->dev, "Invalid MAC Address %pM\n", mac); + return -EADDRNOTAVAIL; + } + + dev_dbg(&oct->pdev->dev, "set vf-%d mac to %pM\n", vf, mac); + ether_addr_copy(oct->vf_info[vf].mac_addr, mac); + oct->vf_info[vf].flags |= OCTEON_PFVF_FLAG_MAC_SET_BY_PF; + + err = octep_ctrl_net_set_mac_addr(oct, vf, mac, true); + if (err) + dev_err(&oct->pdev->dev, + "Set VF%d MAC address failed via host control Mbox\n", + vf); + + return err; +} + static const struct net_device_ops octep_netdev_ops = { .ndo_open = octep_open, .ndo_stop = octep_stop, @@ -1146,6 +1170,8 @@ static const struct net_device_ops octep_netdev_ops = { .ndo_set_mac_address = octep_set_mac, .ndo_change_mtu = octep_change_mtu, .ndo_set_features = octep_set_features, + .ndo_get_vf_config = octep_get_vf_config, + .ndo_set_vf_mac = octep_set_vf_mac }; /** diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h index fee59e0e0138..81ac4267811c 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h @@ -220,6 +220,7 @@ struct octep_iface_link_info { /* The Octeon VF device specific info data structure.*/ struct octep_pfvf_info { u8 mac_addr[ETH_ALEN]; + u32 flags; u32 mbox_version; }; @@ -257,11 +258,17 @@ struct octep_device { /* Pointers to Octeon Tx queues */ struct octep_iq *iq[OCTEP_MAX_IQ]; + /* Per iq stats */ + struct octep_iq_stats stats_iq[OCTEP_MAX_IQ]; + /* Rx queues (OQ: Output Queue) */ u16 num_oqs; /* Pointers to Octeon Rx queues */ struct octep_oq *oq[OCTEP_MAX_OQ]; + /* Per oq stats */ + struct octep_oq_stats stats_oq[OCTEP_MAX_OQ]; + /* Hardware port number of the PCIe interface */ u16 pcie_port; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c index e6eb98d70f3c..ebecdd29f3bd 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c @@ -156,12 +156,23 @@ static void octep_pfvf_set_mac_addr(struct octep_device *oct, u32 vf_id, { int err; + if (oct->vf_info[vf_id].flags & OCTEON_PFVF_FLAG_MAC_SET_BY_PF) { + dev_err(&oct->pdev->dev, + "VF%d attempted to override administrative set MAC address\n", + vf_id); + rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK; + return; + } + err = octep_ctrl_net_set_mac_addr(oct, vf_id, cmd.s_set_mac.mac_addr, true); if (err) { rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK; - dev_err(&oct->pdev->dev, "Set VF MAC address failed via host control Mbox\n"); + dev_err(&oct->pdev->dev, "Set VF%d MAC address failed via host control Mbox\n", + vf_id); return; } + + ether_addr_copy(oct->vf_info[vf_id].mac_addr, cmd.s_set_mac.mac_addr); rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK; } @@ -171,10 +182,18 @@ static void octep_pfvf_get_mac_addr(struct octep_device *oct, u32 vf_id, { int err; + if (oct->vf_info[vf_id].flags & OCTEON_PFVF_FLAG_MAC_SET_BY_PF) { + dev_dbg(&oct->pdev->dev, "VF%d MAC address set by PF\n", vf_id); + ether_addr_copy(rsp->s_set_mac.mac_addr, + oct->vf_info[vf_id].mac_addr); + rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK; + return; + } err = octep_ctrl_net_get_mac_addr(oct, vf_id, rsp->s_set_mac.mac_addr); if (err) { rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK; - dev_err(&oct->pdev->dev, "Get VF MAC address failed via host control Mbox\n"); + dev_err(&oct->pdev->dev, "Get VF%d MAC address failed via host control Mbox\n", + vf_id); return; } rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h index 0dc6eead292a..386a095a99bc 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h @@ -8,8 +8,6 @@ #ifndef _OCTEP_PFVF_MBOX_H_ #define _OCTEP_PFVF_MBOX_H_ -/* VF flags */ -#define OCTEON_PFVF_FLAG_MAC_SET_BY_PF BIT_ULL(0) /* PF has set VF MAC address */ #define OCTEON_SDP_16K_HW_FRS 16380UL #define OCTEON_SDP_64K_HW_FRS 65531UL @@ -23,6 +21,10 @@ enum octep_pfvf_mbox_version { #define OCTEP_PFVF_MBOX_VERSION_CURRENT OCTEP_PFVF_MBOX_VERSION_V2 +/* VF flags */ +/* PF has set VF MAC address */ +#define OCTEON_PFVF_FLAG_MAC_SET_BY_PF BIT(0) + enum octep_pfvf_mbox_opcode { OCTEP_PFVF_MBOX_CMD_VERSION, OCTEP_PFVF_MBOX_CMD_SET_MTU, diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c index 8af75cb37c3e..82b6b19e76b4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c @@ -87,7 +87,7 @@ static int octep_oq_refill(struct octep_device *oct, struct octep_oq *oq) page = dev_alloc_page(); if (unlikely(!page)) { dev_err(oq->dev, "refill: rx buffer alloc failed\n"); - oq->stats.alloc_failures++; + oq->stats->alloc_failures++; break; } @@ -98,7 +98,7 @@ static int octep_oq_refill(struct octep_device *oct, struct octep_oq *oq) "OQ-%d buffer refill: DMA mapping error!\n", oq->q_no); put_page(page); - oq->stats.alloc_failures++; + oq->stats->alloc_failures++; break; } oq->buff_info[refill_idx].page = page; @@ -134,6 +134,7 @@ static int octep_setup_oq(struct octep_device *oct, int q_no) oq->netdev = oct->netdev; oq->dev = &oct->pdev->dev; oq->q_no = q_no; + oq->stats = &oct->stats_oq[q_no]; oq->max_count = CFG_GET_OQ_NUM_DESC(oct->conf); oq->ring_size_mask = oq->max_count - 1; oq->buffer_size = CFG_GET_OQ_BUF_SIZE(oct->conf); @@ -443,7 +444,7 @@ static int __octep_oq_process_rx(struct octep_device *oct, if (!skb) { octep_oq_drop_rx(oq, buff_info, &read_idx, &desc_used); - oq->stats.alloc_failures++; + oq->stats->alloc_failures++; continue; } skb_reserve(skb, data_offset); @@ -494,8 +495,8 @@ static int __octep_oq_process_rx(struct octep_device *oct, oq->host_read_idx = read_idx; oq->refill_count += desc_used; - oq->stats.packets += pkt; - oq->stats.bytes += rx_bytes; + oq->stats->packets += pkt; + oq->stats->bytes += rx_bytes; return pkt; } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h index 3b08e2d560dc..b4696c93d0e6 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h @@ -186,8 +186,8 @@ struct octep_oq { */ u8 __iomem *pkts_sent_reg; - /* Statistics for this OQ. */ - struct octep_oq_stats stats; + /* Pointer to statistics for this OQ. */ + struct octep_oq_stats *stats; /* Packets pending to be processed */ u32 pkts_pending; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c index 06851b78aa28..08ee90013fef 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c @@ -81,9 +81,9 @@ int octep_iq_process_completions(struct octep_iq *iq, u16 budget) } iq->pkts_processed += compl_pkts; - iq->stats.instr_completed += compl_pkts; - iq->stats.bytes_sent += compl_bytes; - iq->stats.sgentry_sent += compl_sg; + iq->stats->instr_completed += compl_pkts; + iq->stats->bytes_sent += compl_bytes; + iq->stats->sgentry_sent += compl_sg; iq->flush_index = fi; netdev_tx_completed_queue(iq->netdev_q, compl_pkts, compl_bytes); @@ -187,6 +187,7 @@ static int octep_setup_iq(struct octep_device *oct, int q_no) iq->netdev = oct->netdev; iq->dev = &oct->pdev->dev; iq->q_no = q_no; + iq->stats = &oct->stats_iq[q_no]; iq->max_count = CFG_GET_IQ_NUM_DESC(oct->conf); iq->ring_size_mask = iq->max_count - 1; iq->fill_threshold = CFG_GET_IQ_DB_MIN(oct->conf); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h index 875a2c34091f..58fb39dda977 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h @@ -170,8 +170,8 @@ struct octep_iq { */ u16 flush_index; - /* Statistics for this input queue. */ - struct octep_iq_stats stats; + /* Pointer to statistics for this input queue. */ + struct octep_iq_stats *stats; /* Pointer to the Virtual Base addr of the input ring. */ struct octep_tx_desc_hw *desc_ring; diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c index 7b21439a315f..d60441928ba9 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c @@ -114,12 +114,9 @@ static void octep_vf_get_ethtool_stats(struct net_device *netdev, iface_tx_stats = &oct->iface_tx_stats; iface_rx_stats = &oct->iface_rx_stats; - for (q = 0; q < oct->num_oqs; q++) { - struct octep_vf_iq *iq = oct->iq[q]; - struct octep_vf_oq *oq = oct->oq[q]; - - tx_busy_errors += iq->stats.tx_busy; - rx_alloc_errors += oq->stats.alloc_failures; + for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) { + tx_busy_errors += oct->stats_iq[q].tx_busy; + rx_alloc_errors += oct->stats_oq[q].alloc_failures; } i = 0; data[i++] = rx_alloc_errors; @@ -134,22 +131,18 @@ static void octep_vf_get_ethtool_stats(struct net_device *netdev, data[i++] = iface_rx_stats->dropped_octets_fifo_full; /* Per Tx Queue stats */ - for (q = 0; q < oct->num_iqs; q++) { - struct octep_vf_iq *iq = oct->iq[q]; - - data[i++] = iq->stats.instr_posted; - data[i++] = iq->stats.instr_completed; - data[i++] = iq->stats.bytes_sent; - data[i++] = iq->stats.tx_busy; + for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) { + data[i++] = oct->stats_iq[q].instr_posted; + data[i++] = oct->stats_iq[q].instr_completed; + data[i++] = oct->stats_iq[q].bytes_sent; + data[i++] = oct->stats_iq[q].tx_busy; } /* Per Rx Queue stats */ for (q = 0; q < oct->num_oqs; q++) { - struct octep_vf_oq *oq = oct->oq[q]; - - data[i++] = oq->stats.packets; - data[i++] = oq->stats.bytes; - data[i++] = oq->stats.alloc_failures; + data[i++] = oct->stats_oq[q].packets; + data[i++] = oct->stats_oq[q].bytes; + data[i++] = oct->stats_oq[q].alloc_failures; } } diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c index 7e6771c9cdbb..18c922dd5fc6 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c @@ -574,7 +574,7 @@ static int octep_vf_iq_full_check(struct octep_vf_iq *iq) * caused queues to get re-enabled after * being stopped */ - iq->stats.restart_cnt++; + iq->stats->restart_cnt++; fallthrough; case 1: /* Queue left enabled, since IQ is not yet full*/ return 0; @@ -731,7 +731,7 @@ ring_dbell: /* Flush the hw descriptors before writing to doorbell */ smp_wmb(); writel(iq->fill_cnt, iq->doorbell_reg); - iq->stats.instr_posted += iq->fill_cnt; + iq->stats->instr_posted += iq->fill_cnt; iq->fill_cnt = 0; return NETDEV_TX_OK; } @@ -786,27 +786,16 @@ static void octep_vf_get_stats64(struct net_device *netdev, tx_bytes = 0; rx_packets = 0; rx_bytes = 0; - for (q = 0; q < oct->num_oqs; q++) { - struct octep_vf_iq *iq = oct->iq[q]; - struct octep_vf_oq *oq = oct->oq[q]; - - tx_packets += iq->stats.instr_completed; - tx_bytes += iq->stats.bytes_sent; - rx_packets += oq->stats.packets; - rx_bytes += oq->stats.bytes; + for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) { + tx_packets += oct->stats_iq[q].instr_completed; + tx_bytes += oct->stats_iq[q].bytes_sent; + rx_packets += oct->stats_oq[q].packets; + rx_bytes += oct->stats_oq[q].bytes; } stats->tx_packets = tx_packets; stats->tx_bytes = tx_bytes; stats->rx_packets = rx_packets; stats->rx_bytes = rx_bytes; - if (!octep_vf_get_if_stats(oct)) { - stats->multicast = oct->iface_rx_stats.mcast_pkts; - stats->rx_errors = oct->iface_rx_stats.err_pkts; - stats->rx_dropped = oct->iface_rx_stats.dropped_pkts_fifo_full + - oct->iface_rx_stats.err_pkts; - stats->rx_missed_errors = oct->iface_rx_stats.dropped_pkts_fifo_full; - stats->tx_dropped = oct->iface_tx_stats.dropped; - } } /** diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h index 5769f62545cd..1a352f41f823 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h @@ -246,11 +246,17 @@ struct octep_vf_device { /* Pointers to Octeon Tx queues */ struct octep_vf_iq *iq[OCTEP_VF_MAX_IQ]; + /* Per iq stats */ + struct octep_vf_iq_stats stats_iq[OCTEP_VF_MAX_IQ]; + /* Rx queues (OQ: Output Queue) */ u16 num_oqs; /* Pointers to Octeon Rx queues */ struct octep_vf_oq *oq[OCTEP_VF_MAX_OQ]; + /* Per oq stats */ + struct octep_vf_oq_stats stats_oq[OCTEP_VF_MAX_OQ]; + /* Hardware port number of the PCIe interface */ u16 pcie_port; diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c index 82821bc28634..d70c8be3cfc4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c @@ -87,7 +87,7 @@ static int octep_vf_oq_refill(struct octep_vf_device *oct, struct octep_vf_oq *o page = dev_alloc_page(); if (unlikely(!page)) { dev_err(oq->dev, "refill: rx buffer alloc failed\n"); - oq->stats.alloc_failures++; + oq->stats->alloc_failures++; break; } @@ -98,7 +98,7 @@ static int octep_vf_oq_refill(struct octep_vf_device *oct, struct octep_vf_oq *o "OQ-%d buffer refill: DMA mapping error!\n", oq->q_no); put_page(page); - oq->stats.alloc_failures++; + oq->stats->alloc_failures++; break; } oq->buff_info[refill_idx].page = page; @@ -134,6 +134,7 @@ static int octep_vf_setup_oq(struct octep_vf_device *oct, int q_no) oq->netdev = oct->netdev; oq->dev = &oct->pdev->dev; oq->q_no = q_no; + oq->stats = &oct->stats_oq[q_no]; oq->max_count = CFG_GET_OQ_NUM_DESC(oct->conf); oq->ring_size_mask = oq->max_count - 1; oq->buffer_size = CFG_GET_OQ_BUF_SIZE(oct->conf); @@ -458,8 +459,8 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct, oq->host_read_idx = read_idx; oq->refill_count += desc_used; - oq->stats.packets += pkt; - oq->stats.bytes += rx_bytes; + oq->stats->packets += pkt; + oq->stats->bytes += rx_bytes; return pkt; } diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h index fe46838b5200..9e296b7d7e34 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h @@ -187,7 +187,7 @@ struct octep_vf_oq { u8 __iomem *pkts_sent_reg; /* Statistics for this OQ. */ - struct octep_vf_oq_stats stats; + struct octep_vf_oq_stats *stats; /* Packets pending to be processed */ u32 pkts_pending; diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c index 47a5c054fdb6..8180e5ce3d7e 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c @@ -82,9 +82,9 @@ int octep_vf_iq_process_completions(struct octep_vf_iq *iq, u16 budget) } iq->pkts_processed += compl_pkts; - iq->stats.instr_completed += compl_pkts; - iq->stats.bytes_sent += compl_bytes; - iq->stats.sgentry_sent += compl_sg; + iq->stats->instr_completed += compl_pkts; + iq->stats->bytes_sent += compl_bytes; + iq->stats->sgentry_sent += compl_sg; iq->flush_index = fi; netif_subqueue_completed_wake(iq->netdev, iq->q_no, compl_pkts, @@ -186,6 +186,7 @@ static int octep_vf_setup_iq(struct octep_vf_device *oct, int q_no) iq->netdev = oct->netdev; iq->dev = &oct->pdev->dev; iq->q_no = q_no; + iq->stats = &oct->stats_iq[q_no]; iq->max_count = CFG_GET_IQ_NUM_DESC(oct->conf); iq->ring_size_mask = iq->max_count - 1; iq->fill_threshold = CFG_GET_IQ_DB_MIN(oct->conf); diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h index f338b975103c..1cede90e3a5f 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h @@ -129,7 +129,7 @@ struct octep_vf_iq { u16 flush_index; /* Statistics for this input queue. */ - struct octep_vf_iq_stats stats; + struct octep_vf_iq_stats *stats; /* Pointer to the Virtual Base addr of the input ring. */ struct octep_vf_tx_desc_hw *desc_ring; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 62c07407eb94..005ca8a056c0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -313,6 +313,10 @@ M(NIX_BANDPROF_FREE, 0x801e, nix_bandprof_free, nix_bandprof_free_req, \ msg_rsp) \ M(NIX_BANDPROF_GET_HWINFO, 0x801f, nix_bandprof_get_hwinfo, msg_req, \ nix_bandprof_get_hwinfo_rsp) \ +M(NIX_CPT_BP_ENABLE, 0x8020, nix_cpt_bp_enable, nix_bp_cfg_req, \ + nix_bp_cfg_rsp) \ +M(NIX_CPT_BP_DISABLE, 0x8021, nix_cpt_bp_disable, nix_bp_cfg_req, \ + msg_rsp) \ M(NIX_READ_INLINE_IPSEC_CFG, 0x8023, nix_read_inline_ipsec_cfg, \ msg_req, nix_inline_ipsec_cfg) \ M(NIX_MCAST_GRP_CREATE, 0x802b, nix_mcast_grp_create, nix_mcast_grp_create_req, \ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 148144f5b61d..a1f9ec03c2ce 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -917,19 +917,18 @@ static void print_npa_qsize(struct seq_file *m, struct rvu_pfvf *pfvf) /* The 'qsize' entry dumps current Aura/Pool context Qsize * and each context's current enable/disable status in a bitmap. */ -static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused, +static int rvu_dbg_qsize_display(struct seq_file *s, void *unsused, int blktype) { - void (*print_qsize)(struct seq_file *filp, + void (*print_qsize)(struct seq_file *s, struct rvu_pfvf *pfvf) = NULL; - struct dentry *current_dir; struct rvu_pfvf *pfvf; struct rvu *rvu; int qsize_id; u16 pcifunc; int blkaddr; - rvu = filp->private; + rvu = s->private; switch (blktype) { case BLKTYPE_NPA: qsize_id = rvu->rvu_dbg.npa_qsize_id; @@ -945,32 +944,28 @@ static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused, return -EINVAL; } - if (blktype == BLKTYPE_NPA) { + if (blktype == BLKTYPE_NPA) blkaddr = BLKADDR_NPA; - } else { - current_dir = filp->file->f_path.dentry->d_parent; - blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ? - BLKADDR_NIX1 : BLKADDR_NIX0); - } + else + blkaddr = debugfs_get_aux_num(s->file); if (!rvu_dbg_is_valid_lf(rvu, blkaddr, qsize_id, &pcifunc)) return -EINVAL; pfvf = rvu_get_pfvf(rvu, pcifunc); - print_qsize(filp, pfvf); + print_qsize(s, pfvf); return 0; } -static ssize_t rvu_dbg_qsize_write(struct file *filp, +static ssize_t rvu_dbg_qsize_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos, int blktype) { char *blk_string = (blktype == BLKTYPE_NPA) ? "npa" : "nix"; - struct seq_file *seqfile = filp->private_data; + struct seq_file *seqfile = file->private_data; char *cmd_buf, *cmd_buf_tmp, *subtoken; struct rvu *rvu = seqfile->private; - struct dentry *current_dir; int blkaddr; u16 pcifunc; int ret, lf; @@ -996,13 +991,10 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, goto qsize_write_done; } - if (blktype == BLKTYPE_NPA) { + if (blktype == BLKTYPE_NPA) blkaddr = BLKADDR_NPA; - } else { - current_dir = filp->f_path.dentry->d_parent; - blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ? - BLKADDR_NIX1 : BLKADDR_NIX0); - } + else + blkaddr = debugfs_get_aux_num(file); if (!rvu_dbg_is_valid_lf(rvu, blkaddr, lf, &pcifunc)) { ret = -EINVAL; @@ -2704,8 +2696,8 @@ static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr) &rvu_dbg_nix_ndc_tx_hits_miss_fops); debugfs_create_file("ndc_rx_hits_miss", 0600, rvu->rvu_dbg.nix, nix_hw, &rvu_dbg_nix_ndc_rx_hits_miss_fops); - debugfs_create_file("qsize", 0600, rvu->rvu_dbg.nix, rvu, - &rvu_dbg_nix_qsize_fops); + debugfs_create_file_aux_num("qsize", 0600, rvu->rvu_dbg.nix, rvu, + blkaddr, &rvu_dbg_nix_qsize_fops); debugfs_create_file("ingress_policer_ctx", 0600, rvu->rvu_dbg.nix, nix_hw, &rvu_dbg_nix_band_prof_ctx_fops); debugfs_create_file("ingress_policer_rsrc", 0600, rvu->rvu_dbg.nix, nix_hw, @@ -2854,28 +2846,14 @@ static int cgx_print_stats(struct seq_file *s, int lmac_id) return err; } -static int rvu_dbg_derive_lmacid(struct seq_file *filp, int *lmac_id) +static int rvu_dbg_derive_lmacid(struct seq_file *s) { - struct dentry *current_dir; - char *buf; - - current_dir = filp->file->f_path.dentry->d_parent; - buf = strrchr(current_dir->d_name.name, 'c'); - if (!buf) - return -EINVAL; - - return kstrtoint(buf + 1, 10, lmac_id); + return debugfs_get_aux_num(s->file); } -static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused) +static int rvu_dbg_cgx_stat_display(struct seq_file *s, void *unused) { - int lmac_id, err; - - err = rvu_dbg_derive_lmacid(filp, &lmac_id); - if (!err) - return cgx_print_stats(filp, lmac_id); - - return err; + return cgx_print_stats(s, rvu_dbg_derive_lmacid(s)); } RVU_DEBUG_SEQ_FOPS(cgx_stat, cgx_stat_display, NULL); @@ -2933,15 +2911,9 @@ static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id) return 0; } -static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *filp, void *unused) +static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *s, void *unused) { - int err, lmac_id; - - err = rvu_dbg_derive_lmacid(filp, &lmac_id); - if (!err) - return cgx_print_dmac_flt(filp, lmac_id); - - return err; + return cgx_print_dmac_flt(s, rvu_dbg_derive_lmacid(s)); } RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL); @@ -2980,10 +2952,10 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) rvu->rvu_dbg.lmac = debugfs_create_dir(dname, rvu->rvu_dbg.cgx); - debugfs_create_file("stats", 0600, rvu->rvu_dbg.lmac, - cgx, &rvu_dbg_cgx_stat_fops); - debugfs_create_file("mac_filter", 0600, - rvu->rvu_dbg.lmac, cgx, + debugfs_create_file_aux_num("stats", 0600, rvu->rvu_dbg.lmac, + cgx, lmac_id, &rvu_dbg_cgx_stat_fops); + debugfs_create_file_aux_num("mac_filter", 0600, + rvu->rvu_dbg.lmac, cgx, lmac_id, &rvu_dbg_cgx_dmac_flt_fops); } } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index a5d1e2bddd58..613655fcd34f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -569,9 +569,17 @@ void rvu_nix_flr_free_bpids(struct rvu *rvu, u16 pcifunc) mutex_unlock(&rvu->rsrc_lock); } -int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu, - struct nix_bp_cfg_req *req, - struct msg_rsp *rsp) +static u16 nix_get_channel(u16 chan, bool cpt_link) +{ + /* CPT channel for a given link channel is always + * assumed to be BIT(11) set in link channel. + */ + return cpt_link ? chan | BIT(11) : chan; +} + +static int nix_bp_disable(struct rvu *rvu, + struct nix_bp_cfg_req *req, + struct msg_rsp *rsp, bool cpt_link) { u16 pcifunc = req->hdr.pcifunc; int blkaddr, pf, type, err; @@ -579,6 +587,7 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu, struct rvu_pfvf *pfvf; struct nix_hw *nix_hw; struct nix_bp *bp; + u16 chan_v; u64 cfg; pf = rvu_get_pf(pcifunc); @@ -589,6 +598,9 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu, if (is_sdp_pfvf(pcifunc)) type = NIX_INTF_TYPE_SDP; + if (cpt_link && !rvu->hw->cpt_links) + return 0; + pfvf = rvu_get_pfvf(rvu, pcifunc); err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr); if (err) @@ -597,8 +609,9 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu, bp = &nix_hw->bp; chan_base = pfvf->rx_chan_base + req->chan_base; for (chan = chan_base; chan < (chan_base + req->chan_cnt); chan++) { - cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan)); - rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan), + chan_v = nix_get_channel(chan, cpt_link); + cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan_v)); + rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan_v), cfg & ~BIT_ULL(16)); if (type == NIX_INTF_TYPE_LBK) { @@ -617,6 +630,20 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu, return 0; } +int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu, + struct nix_bp_cfg_req *req, + struct msg_rsp *rsp) +{ + return nix_bp_disable(rvu, req, rsp, false); +} + +int rvu_mbox_handler_nix_cpt_bp_disable(struct rvu *rvu, + struct nix_bp_cfg_req *req, + struct msg_rsp *rsp) +{ + return nix_bp_disable(rvu, req, rsp, true); +} + static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req, int type, int chan_id) { @@ -696,15 +723,17 @@ static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req, return bpid; } -int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu, - struct nix_bp_cfg_req *req, - struct nix_bp_cfg_rsp *rsp) +static int nix_bp_enable(struct rvu *rvu, + struct nix_bp_cfg_req *req, + struct nix_bp_cfg_rsp *rsp, + bool cpt_link) { int blkaddr, pf, type, chan_id = 0; u16 pcifunc = req->hdr.pcifunc; struct rvu_pfvf *pfvf; u16 chan_base, chan; s16 bpid, bpid_base; + u16 chan_v; u64 cfg; pf = rvu_get_pf(pcifunc); @@ -717,6 +746,9 @@ int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu, type != NIX_INTF_TYPE_SDP) return 0; + if (cpt_link && !rvu->hw->cpt_links) + return 0; + pfvf = rvu_get_pfvf(rvu, pcifunc); blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); @@ -730,9 +762,11 @@ int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu, return -EINVAL; } - cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan)); + chan_v = nix_get_channel(chan, cpt_link); + + cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan_v)); cfg &= ~GENMASK_ULL(8, 0); - rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan), + rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan_v), cfg | (bpid & GENMASK_ULL(8, 0)) | BIT_ULL(16)); chan_id++; bpid = rvu_nix_get_bpid(rvu, req, type, chan_id); @@ -750,6 +784,20 @@ int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu, return 0; } +int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu, + struct nix_bp_cfg_req *req, + struct nix_bp_cfg_rsp *rsp) +{ + return nix_bp_enable(rvu, req, rsp, false); +} + +int rvu_mbox_handler_nix_cpt_bp_enable(struct rvu *rvu, + struct nix_bp_cfg_req *req, + struct nix_bp_cfg_rsp *rsp) +{ + return nix_bp_enable(rvu, req, rsp, true); +} + static void nix_setup_lso_tso_l3(struct rvu *rvu, int blkaddr, u64 format, bool v4, u64 *fidx) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index dbc971266865..cb6513ab35e7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -15,5 +15,6 @@ rvu_rep-y := rep.o rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o rvu_nicpf-$(CONFIG_MACSEC) += cn10k_macsec.o +rvu_nicpf-$(CONFIG_XFRM_OFFLOAD) += cn10k_ipsec.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c new file mode 100644 index 000000000000..09a5b5268205 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c @@ -0,0 +1,1056 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell IPSEC offload driver + * + * Copyright (C) 2024 Marvell. + */ + +#include +#include +#include +#include +#include + +#include "otx2_common.h" +#include "otx2_struct.h" +#include "cn10k_ipsec.h" + +static bool is_dev_support_ipsec_offload(struct pci_dev *pdev) +{ + return is_dev_cn10ka_b0(pdev) || is_dev_cn10kb(pdev); +} + +static bool cn10k_cpt_device_set_inuse(struct otx2_nic *pf) +{ + enum cn10k_cpt_hw_state_e state; + + while (true) { + state = atomic_cmpxchg(&pf->ipsec.cpt_state, + CN10K_CPT_HW_AVAILABLE, + CN10K_CPT_HW_IN_USE); + if (state == CN10K_CPT_HW_AVAILABLE) + return true; + if (state == CN10K_CPT_HW_UNAVAILABLE) + return false; + + mdelay(1); + } +} + +static void cn10k_cpt_device_set_available(struct otx2_nic *pf) +{ + atomic_set(&pf->ipsec.cpt_state, CN10K_CPT_HW_AVAILABLE); +} + +static void cn10k_cpt_device_set_unavailable(struct otx2_nic *pf) +{ + atomic_set(&pf->ipsec.cpt_state, CN10K_CPT_HW_UNAVAILABLE); +} + +static int cn10k_outb_cptlf_attach(struct otx2_nic *pf) +{ + struct rsrc_attach *attach; + int ret = -ENOMEM; + + mutex_lock(&pf->mbox.lock); + /* Get memory to put this msg */ + attach = otx2_mbox_alloc_msg_attach_resources(&pf->mbox); + if (!attach) + goto unlock; + + attach->cptlfs = true; + attach->modify = true; + + /* Send attach request to AF */ + ret = otx2_sync_mbox_msg(&pf->mbox); + +unlock: + mutex_unlock(&pf->mbox.lock); + return ret; +} + +static int cn10k_outb_cptlf_detach(struct otx2_nic *pf) +{ + struct rsrc_detach *detach; + int ret = -ENOMEM; + + mutex_lock(&pf->mbox.lock); + detach = otx2_mbox_alloc_msg_detach_resources(&pf->mbox); + if (!detach) + goto unlock; + + detach->partial = true; + detach->cptlfs = true; + + /* Send detach request to AF */ + ret = otx2_sync_mbox_msg(&pf->mbox); + +unlock: + mutex_unlock(&pf->mbox.lock); + return ret; +} + +static int cn10k_outb_cptlf_alloc(struct otx2_nic *pf) +{ + struct cpt_lf_alloc_req_msg *req; + int ret = -ENOMEM; + + mutex_lock(&pf->mbox.lock); + req = otx2_mbox_alloc_msg_cpt_lf_alloc(&pf->mbox); + if (!req) + goto unlock; + + /* PF function */ + req->nix_pf_func = pf->pcifunc; + /* Enable SE-IE Engine Group */ + req->eng_grpmsk = 1 << CN10K_DEF_CPT_IPSEC_EGRP; + + ret = otx2_sync_mbox_msg(&pf->mbox); + +unlock: + mutex_unlock(&pf->mbox.lock); + return ret; +} + +static void cn10k_outb_cptlf_free(struct otx2_nic *pf) +{ + mutex_lock(&pf->mbox.lock); + otx2_mbox_alloc_msg_cpt_lf_free(&pf->mbox); + otx2_sync_mbox_msg(&pf->mbox); + mutex_unlock(&pf->mbox.lock); +} + +static int cn10k_outb_cptlf_config(struct otx2_nic *pf) +{ + struct cpt_inline_ipsec_cfg_msg *req; + int ret = -ENOMEM; + + mutex_lock(&pf->mbox.lock); + req = otx2_mbox_alloc_msg_cpt_inline_ipsec_cfg(&pf->mbox); + if (!req) + goto unlock; + + req->dir = CPT_INLINE_OUTBOUND; + req->enable = 1; + req->nix_pf_func = pf->pcifunc; + ret = otx2_sync_mbox_msg(&pf->mbox); +unlock: + mutex_unlock(&pf->mbox.lock); + return ret; +} + +static void cn10k_outb_cptlf_iq_enable(struct otx2_nic *pf) +{ + u64 reg_val; + + /* Set Execution Enable of instruction queue */ + reg_val = otx2_read64(pf, CN10K_CPT_LF_INPROG); + reg_val |= BIT_ULL(16); + otx2_write64(pf, CN10K_CPT_LF_INPROG, reg_val); + + /* Set iqueue's enqueuing */ + reg_val = otx2_read64(pf, CN10K_CPT_LF_CTL); + reg_val |= BIT_ULL(0); + otx2_write64(pf, CN10K_CPT_LF_CTL, reg_val); +} + +static void cn10k_outb_cptlf_iq_disable(struct otx2_nic *pf) +{ + u32 inflight, grb_cnt, gwb_cnt; + u32 nq_ptr, dq_ptr; + int timeout = 20; + u64 reg_val; + int cnt; + + /* Disable instructions enqueuing */ + otx2_write64(pf, CN10K_CPT_LF_CTL, 0ull); + + /* Wait for instruction queue to become empty. + * CPT_LF_INPROG.INFLIGHT count is zero + */ + do { + reg_val = otx2_read64(pf, CN10K_CPT_LF_INPROG); + inflight = FIELD_GET(CPT_LF_INPROG_INFLIGHT, reg_val); + if (!inflight) + break; + + usleep_range(10000, 20000); + if (timeout-- < 0) { + netdev_err(pf->netdev, "Timeout to cleanup CPT IQ\n"); + break; + } + } while (1); + + /* Disable executions in the LF's queue, + * the queue should be empty at this point + */ + reg_val &= ~BIT_ULL(16); + otx2_write64(pf, CN10K_CPT_LF_INPROG, reg_val); + + /* Wait for instruction queue to become empty */ + cnt = 0; + do { + reg_val = otx2_read64(pf, CN10K_CPT_LF_INPROG); + if (reg_val & BIT_ULL(31)) + cnt = 0; + else + cnt++; + reg_val = otx2_read64(pf, CN10K_CPT_LF_Q_GRP_PTR); + nq_ptr = FIELD_GET(CPT_LF_Q_GRP_PTR_DQ_PTR, reg_val); + dq_ptr = FIELD_GET(CPT_LF_Q_GRP_PTR_DQ_PTR, reg_val); + } while ((cnt < 10) && (nq_ptr != dq_ptr)); + + cnt = 0; + do { + reg_val = otx2_read64(pf, CN10K_CPT_LF_INPROG); + inflight = FIELD_GET(CPT_LF_INPROG_INFLIGHT, reg_val); + grb_cnt = FIELD_GET(CPT_LF_INPROG_GRB_CNT, reg_val); + gwb_cnt = FIELD_GET(CPT_LF_INPROG_GWB_CNT, reg_val); + if (inflight == 0 && gwb_cnt < 40 && + (grb_cnt == 0 || grb_cnt == 40)) + cnt++; + else + cnt = 0; + } while (cnt < 10); +} + +/* Allocate memory for CPT outbound Instruction queue. + * Instruction queue memory format is: + * ----------------------------- + * | Instruction Group memory | + * | (CPT_LF_Q_SIZE[SIZE_DIV40] | + * | x 16 Bytes) | + * | | + * ----------------------------- <-- CPT_LF_Q_BASE[ADDR] + * | Flow Control (128 Bytes) | + * | | + * ----------------------------- + * | Instruction Memory | + * | (CPT_LF_Q_SIZE[SIZE_DIV40] | + * | × 40 × 64 bytes) | + * | | + * ----------------------------- + */ +static int cn10k_outb_cptlf_iq_alloc(struct otx2_nic *pf) +{ + struct cn10k_cpt_inst_queue *iq = &pf->ipsec.iq; + + iq->size = CN10K_CPT_INST_QLEN_BYTES + CN10K_CPT_Q_FC_LEN + + CN10K_CPT_INST_GRP_QLEN_BYTES + OTX2_ALIGN; + + iq->real_vaddr = dma_alloc_coherent(pf->dev, iq->size, + &iq->real_dma_addr, GFP_KERNEL); + if (!iq->real_vaddr) + return -ENOMEM; + + /* iq->vaddr/dma_addr points to Flow Control location */ + iq->vaddr = iq->real_vaddr + CN10K_CPT_INST_GRP_QLEN_BYTES; + iq->dma_addr = iq->real_dma_addr + CN10K_CPT_INST_GRP_QLEN_BYTES; + + /* Align pointers */ + iq->vaddr = PTR_ALIGN(iq->vaddr, OTX2_ALIGN); + iq->dma_addr = PTR_ALIGN(iq->dma_addr, OTX2_ALIGN); + return 0; +} + +static void cn10k_outb_cptlf_iq_free(struct otx2_nic *pf) +{ + struct cn10k_cpt_inst_queue *iq = &pf->ipsec.iq; + + if (iq->real_vaddr) + dma_free_coherent(pf->dev, iq->size, iq->real_vaddr, + iq->real_dma_addr); + + iq->real_vaddr = NULL; + iq->vaddr = NULL; +} + +static int cn10k_outb_cptlf_iq_init(struct otx2_nic *pf) +{ + u64 reg_val; + int ret; + + /* Allocate Memory for CPT IQ */ + ret = cn10k_outb_cptlf_iq_alloc(pf); + if (ret) + return ret; + + /* Disable IQ */ + cn10k_outb_cptlf_iq_disable(pf); + + /* Set IQ base address */ + otx2_write64(pf, CN10K_CPT_LF_Q_BASE, pf->ipsec.iq.dma_addr); + + /* Set IQ size */ + reg_val = FIELD_PREP(CPT_LF_Q_SIZE_DIV40, CN10K_CPT_SIZE_DIV40 + + CN10K_CPT_EXTRA_SIZE_DIV40); + otx2_write64(pf, CN10K_CPT_LF_Q_SIZE, reg_val); + + return 0; +} + +static int cn10k_outb_cptlf_init(struct otx2_nic *pf) +{ + int ret; + + /* Initialize CPTLF Instruction Queue (IQ) */ + ret = cn10k_outb_cptlf_iq_init(pf); + if (ret) + return ret; + + /* Configure CPTLF for outbound ipsec offload */ + ret = cn10k_outb_cptlf_config(pf); + if (ret) + goto iq_clean; + + /* Enable CPTLF IQ */ + cn10k_outb_cptlf_iq_enable(pf); + return 0; +iq_clean: + cn10k_outb_cptlf_iq_free(pf); + return ret; +} + +static int cn10k_outb_cpt_init(struct net_device *netdev) +{ + struct otx2_nic *pf = netdev_priv(netdev); + int ret; + + /* Attach a CPT LF for outbound ipsec offload */ + ret = cn10k_outb_cptlf_attach(pf); + if (ret) + return ret; + + /* Allocate a CPT LF for outbound ipsec offload */ + ret = cn10k_outb_cptlf_alloc(pf); + if (ret) + goto detach; + + /* Initialize the CPTLF for outbound ipsec offload */ + ret = cn10k_outb_cptlf_init(pf); + if (ret) + goto lf_free; + + pf->ipsec.io_addr = (__force u64)otx2_get_regaddr(pf, + CN10K_CPT_LF_NQX(0)); + + /* Set ipsec offload enabled for this device */ + pf->flags |= OTX2_FLAG_IPSEC_OFFLOAD_ENABLED; + + cn10k_cpt_device_set_available(pf); + return 0; + +lf_free: + cn10k_outb_cptlf_free(pf); +detach: + cn10k_outb_cptlf_detach(pf); + return ret; +} + +static int cn10k_outb_cpt_clean(struct otx2_nic *pf) +{ + int ret; + + if (!cn10k_cpt_device_set_inuse(pf)) { + netdev_err(pf->netdev, "CPT LF device unavailable\n"); + return -ENODEV; + } + + /* Set ipsec offload disabled for this device */ + pf->flags &= ~OTX2_FLAG_IPSEC_OFFLOAD_ENABLED; + + /* Disable CPTLF Instruction Queue (IQ) */ + cn10k_outb_cptlf_iq_disable(pf); + + /* Set IQ base address and size to 0 */ + otx2_write64(pf, CN10K_CPT_LF_Q_BASE, 0); + otx2_write64(pf, CN10K_CPT_LF_Q_SIZE, 0); + + /* Free CPTLF IQ */ + cn10k_outb_cptlf_iq_free(pf); + + /* Free and detach CPT LF */ + cn10k_outb_cptlf_free(pf); + ret = cn10k_outb_cptlf_detach(pf); + if (ret) + netdev_err(pf->netdev, "Failed to detach CPT LF\n"); + + cn10k_cpt_device_set_unavailable(pf); + return ret; +} + +static void cn10k_cpt_inst_flush(struct otx2_nic *pf, struct cpt_inst_s *inst, + u64 size) +{ + struct otx2_lmt_info *lmt_info; + u64 val = 0, tar_addr = 0; + + lmt_info = per_cpu_ptr(pf->hw.lmt_info, smp_processor_id()); + /* FIXME: val[0:10] LMT_ID. + * [12:15] no of LMTST - 1 in the burst. + * [19:63] data size of each LMTST in the burst except first. + */ + val = (lmt_info->lmt_id & 0x7FF); + /* Target address for LMTST flush tells HW how many 128bit + * words are present. + * tar_addr[6:4] size of first LMTST - 1 in units of 128b. + */ + tar_addr |= pf->ipsec.io_addr | (((size / 16) - 1) & 0x7) << 4; + dma_wmb(); + memcpy((u64 *)lmt_info->lmt_addr, inst, size); + cn10k_lmt_flush(val, tar_addr); +} + +static int cn10k_wait_for_cpt_respose(struct otx2_nic *pf, + struct cpt_res_s *res) +{ + unsigned long timeout = jiffies + msecs_to_jiffies(100); + u64 *completion_ptr = (u64 *)res; + + do { + if (time_after(jiffies, timeout)) { + netdev_err(pf->netdev, "CPT response timeout\n"); + return -EBUSY; + } + } while ((READ_ONCE(*completion_ptr) & CN10K_CPT_COMP_E_MASK) == + CN10K_CPT_COMP_E_NOTDONE); + + if (!(res->compcode == CN10K_CPT_COMP_E_GOOD || + res->compcode == CN10K_CPT_COMP_E_WARN) || res->uc_compcode) { + netdev_err(pf->netdev, "compcode=%x doneint=%x\n", + res->compcode, res->doneint); + netdev_err(pf->netdev, "uc_compcode=%x uc_info=%llx esn=%llx\n", + res->uc_compcode, (u64)res->uc_info, res->esn); + } + return 0; +} + +static int cn10k_outb_write_sa(struct otx2_nic *pf, struct qmem *sa_info) +{ + dma_addr_t res_iova, dptr_iova, sa_iova; + struct cn10k_tx_sa_s *sa_dptr; + struct cpt_inst_s inst = {}; + struct cpt_res_s *res; + u32 sa_size, off; + u64 *sptr, *dptr; + u64 reg_val; + int ret; + + sa_iova = sa_info->iova; + if (!sa_iova) + return -EINVAL; + + res = dma_alloc_coherent(pf->dev, sizeof(struct cpt_res_s), + &res_iova, GFP_ATOMIC); + if (!res) + return -ENOMEM; + + sa_size = sizeof(struct cn10k_tx_sa_s); + sa_dptr = dma_alloc_coherent(pf->dev, sa_size, &dptr_iova, GFP_ATOMIC); + if (!sa_dptr) { + dma_free_coherent(pf->dev, sizeof(struct cpt_res_s), res, + res_iova); + return -ENOMEM; + } + + sptr = (__force u64 *)sa_info->base; + dptr = (__force u64 *)sa_dptr; + for (off = 0; off < (sa_size / 8); off++) + *(dptr + off) = (__force u64)cpu_to_be64(*(sptr + off)); + + res->compcode = CN10K_CPT_COMP_E_NOTDONE; + inst.res_addr = res_iova; + inst.dptr = (u64)dptr_iova; + inst.param2 = sa_size >> 3; + inst.dlen = sa_size; + inst.opcode_major = CN10K_IPSEC_MAJOR_OP_WRITE_SA; + inst.opcode_minor = CN10K_IPSEC_MINOR_OP_WRITE_SA; + inst.cptr = sa_iova; + inst.ctx_val = 1; + inst.egrp = CN10K_DEF_CPT_IPSEC_EGRP; + + /* Check if CPT-LF available */ + if (!cn10k_cpt_device_set_inuse(pf)) { + ret = -ENODEV; + goto free_mem; + } + + cn10k_cpt_inst_flush(pf, &inst, sizeof(struct cpt_inst_s)); + dma_wmb(); + ret = cn10k_wait_for_cpt_respose(pf, res); + if (ret) + goto set_available; + + /* Trigger CTX flush to write dirty data back to DRAM */ + reg_val = FIELD_PREP(CPT_LF_CTX_FLUSH, sa_iova >> 7); + otx2_write64(pf, CN10K_CPT_LF_CTX_FLUSH, reg_val); + +set_available: + cn10k_cpt_device_set_available(pf); +free_mem: + dma_free_coherent(pf->dev, sa_size, sa_dptr, dptr_iova); + dma_free_coherent(pf->dev, sizeof(struct cpt_res_s), res, res_iova); + return ret; +} + +static int cn10k_ipsec_get_hw_ctx_offset(void) +{ + /* Offset on Hardware-context offset in word */ + return (offsetof(struct cn10k_tx_sa_s, hw_ctx) / sizeof(u64)) & 0x7F; +} + +static int cn10k_ipsec_get_ctx_push_size(void) +{ + /* Context push size is round up and in multiple of 8 Byte */ + return (roundup(offsetof(struct cn10k_tx_sa_s, hw_ctx), 8) / 8) & 0x7F; +} + +static int cn10k_ipsec_get_aes_key_len(int key_len) +{ + /* key_len is aes key length in bytes */ + switch (key_len) { + case 16: + return CN10K_IPSEC_SA_AES_KEY_LEN_128; + case 24: + return CN10K_IPSEC_SA_AES_KEY_LEN_192; + default: + return CN10K_IPSEC_SA_AES_KEY_LEN_256; + } +} + +static void cn10k_outb_prepare_sa(struct xfrm_state *x, + struct cn10k_tx_sa_s *sa_entry) +{ + int key_len = (x->aead->alg_key_len + 7) / 8; + struct net_device *netdev = x->xso.dev; + u8 *key = x->aead->alg_key; + struct otx2_nic *pf; + u32 *tmp_salt; + u64 *tmp_key; + int idx; + + memset(sa_entry, 0, sizeof(struct cn10k_tx_sa_s)); + + /* context size, 128 Byte aligned up */ + pf = netdev_priv(netdev); + sa_entry->ctx_size = (pf->ipsec.sa_size / OTX2_ALIGN) & 0xF; + sa_entry->hw_ctx_off = cn10k_ipsec_get_hw_ctx_offset(); + sa_entry->ctx_push_size = cn10k_ipsec_get_ctx_push_size(); + + /* Ucode to skip two words of CPT_CTX_HW_S */ + sa_entry->ctx_hdr_size = 1; + + /* Allow Atomic operation (AOP) */ + sa_entry->aop_valid = 1; + + /* Outbound, ESP TRANSPORT/TUNNEL Mode, AES-GCM with */ + sa_entry->sa_dir = CN10K_IPSEC_SA_DIR_OUTB; + sa_entry->ipsec_protocol = CN10K_IPSEC_SA_IPSEC_PROTO_ESP; + sa_entry->enc_type = CN10K_IPSEC_SA_ENCAP_TYPE_AES_GCM; + sa_entry->iv_src = CN10K_IPSEC_SA_IV_SRC_PACKET; + if (x->props.mode == XFRM_MODE_TUNNEL) + sa_entry->ipsec_mode = CN10K_IPSEC_SA_IPSEC_MODE_TUNNEL; + else + sa_entry->ipsec_mode = CN10K_IPSEC_SA_IPSEC_MODE_TRANSPORT; + + /* Last 4 bytes are salt */ + key_len -= 4; + sa_entry->aes_key_len = cn10k_ipsec_get_aes_key_len(key_len); + memcpy(sa_entry->cipher_key, key, key_len); + tmp_key = (u64 *)sa_entry->cipher_key; + + for (idx = 0; idx < key_len / 8; idx++) + tmp_key[idx] = (__force u64)cpu_to_be64(tmp_key[idx]); + + memcpy(&sa_entry->iv_gcm_salt, key + key_len, 4); + tmp_salt = (u32 *)&sa_entry->iv_gcm_salt; + *tmp_salt = (__force u32)cpu_to_be32(*tmp_salt); + + /* Write SA context data to memory before enabling */ + wmb(); + + /* Enable SA */ + sa_entry->sa_valid = 1; +} + +static int cn10k_ipsec_validate_state(struct xfrm_state *x, + struct netlink_ext_ack *extack) +{ + if (x->props.aalgo != SADB_AALG_NONE) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload authenticated xfrm states"); + return -EINVAL; + } + if (x->props.ealgo != SADB_X_EALG_AES_GCM_ICV16) { + NL_SET_ERR_MSG_MOD(extack, + "Only AES-GCM-ICV16 xfrm state may be offloaded"); + return -EINVAL; + } + if (x->props.calgo != SADB_X_CALG_NONE) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload compressed xfrm states"); + return -EINVAL; + } + if (x->props.flags & XFRM_STATE_ESN) { + NL_SET_ERR_MSG_MOD(extack, "Cannot offload ESN xfrm states"); + return -EINVAL; + } + if (x->props.family != AF_INET && x->props.family != AF_INET6) { + NL_SET_ERR_MSG_MOD(extack, + "Only IPv4/v6 xfrm states may be offloaded"); + return -EINVAL; + } + if (x->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload other than crypto-mode"); + return -EINVAL; + } + if (x->props.mode != XFRM_MODE_TRANSPORT && + x->props.mode != XFRM_MODE_TUNNEL) { + NL_SET_ERR_MSG_MOD(extack, + "Only tunnel/transport xfrm states may be offloaded"); + return -EINVAL; + } + if (x->id.proto != IPPROTO_ESP) { + NL_SET_ERR_MSG_MOD(extack, + "Only ESP xfrm state may be offloaded"); + return -EINVAL; + } + if (x->encap) { + NL_SET_ERR_MSG_MOD(extack, + "Encapsulated xfrm state may not be offloaded"); + return -EINVAL; + } + if (!x->aead) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload xfrm states without aead"); + return -EINVAL; + } + + if (x->aead->alg_icv_len != 128) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload xfrm states with AEAD ICV length other than 128bit"); + return -EINVAL; + } + if (x->aead->alg_key_len != 128 + 32 && + x->aead->alg_key_len != 192 + 32 && + x->aead->alg_key_len != 256 + 32) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload xfrm states with AEAD key length other than 128/192/256bit"); + return -EINVAL; + } + if (x->tfcpad) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload xfrm states with tfc padding"); + return -EINVAL; + } + if (!x->geniv) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload xfrm states without geniv"); + return -EINVAL; + } + if (strcmp(x->geniv, "seqiv")) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload xfrm states with geniv other than seqiv"); + return -EINVAL; + } + return 0; +} + +static int cn10k_ipsec_inb_add_state(struct xfrm_state *x, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG_MOD(extack, "xfrm inbound offload not supported"); + return -EOPNOTSUPP; +} + +static int cn10k_ipsec_outb_add_state(struct xfrm_state *x, + struct netlink_ext_ack *extack) +{ + struct net_device *netdev = x->xso.dev; + struct cn10k_tx_sa_s *sa_entry; + struct qmem *sa_info; + struct otx2_nic *pf; + int err; + + err = cn10k_ipsec_validate_state(x, extack); + if (err) + return err; + + pf = netdev_priv(netdev); + + err = qmem_alloc(pf->dev, &sa_info, pf->ipsec.sa_size, OTX2_ALIGN); + if (err) + return err; + + sa_entry = (struct cn10k_tx_sa_s *)sa_info->base; + cn10k_outb_prepare_sa(x, sa_entry); + + err = cn10k_outb_write_sa(pf, sa_info); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Error writing outbound SA"); + qmem_free(pf->dev, sa_info); + return err; + } + + x->xso.offload_handle = (unsigned long)sa_info; + /* Enable static branch when first SA setup */ + if (!pf->ipsec.outb_sa_count) + static_branch_enable(&cn10k_ipsec_sa_enabled); + pf->ipsec.outb_sa_count++; + return 0; +} + +static int cn10k_ipsec_add_state(struct xfrm_state *x, + struct netlink_ext_ack *extack) +{ + if (x->xso.dir == XFRM_DEV_OFFLOAD_IN) + return cn10k_ipsec_inb_add_state(x, extack); + else + return cn10k_ipsec_outb_add_state(x, extack); +} + +static void cn10k_ipsec_del_state(struct xfrm_state *x) +{ + struct net_device *netdev = x->xso.dev; + struct cn10k_tx_sa_s *sa_entry; + struct qmem *sa_info; + struct otx2_nic *pf; + int err; + + if (x->xso.dir == XFRM_DEV_OFFLOAD_IN) + return; + + pf = netdev_priv(netdev); + + sa_info = (struct qmem *)x->xso.offload_handle; + sa_entry = (struct cn10k_tx_sa_s *)sa_info->base; + memset(sa_entry, 0, sizeof(struct cn10k_tx_sa_s)); + /* Disable SA in CPT h/w */ + sa_entry->ctx_push_size = cn10k_ipsec_get_ctx_push_size(); + sa_entry->ctx_size = (pf->ipsec.sa_size / OTX2_ALIGN) & 0xF; + sa_entry->aop_valid = 1; + + err = cn10k_outb_write_sa(pf, sa_info); + if (err) + netdev_err(netdev, "Error (%d) deleting SA\n", err); + + x->xso.offload_handle = 0; + qmem_free(pf->dev, sa_info); + + /* If no more SA's then update netdev feature for potential change + * in NETIF_F_HW_ESP. + */ + if (!--pf->ipsec.outb_sa_count) + queue_work(pf->ipsec.sa_workq, &pf->ipsec.sa_work); +} + +static bool cn10k_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x) +{ + if (x->props.family == AF_INET) { + /* Offload with IPv4 options is not supported yet */ + if (ip_hdr(skb)->ihl > 5) + return false; + } else { + /* Offload with IPv6 extension headers is not support yet */ + if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) + return false; + } + return true; +} + +static const struct xfrmdev_ops cn10k_ipsec_xfrmdev_ops = { + .xdo_dev_state_add = cn10k_ipsec_add_state, + .xdo_dev_state_delete = cn10k_ipsec_del_state, + .xdo_dev_offload_ok = cn10k_ipsec_offload_ok, +}; + +static void cn10k_ipsec_sa_wq_handler(struct work_struct *work) +{ + struct cn10k_ipsec *ipsec = container_of(work, struct cn10k_ipsec, + sa_work); + struct otx2_nic *pf = container_of(ipsec, struct otx2_nic, ipsec); + + /* Disable static branch when no more SA enabled */ + static_branch_disable(&cn10k_ipsec_sa_enabled); + rtnl_lock(); + netdev_update_features(pf->netdev); + rtnl_unlock(); +} + +int cn10k_ipsec_ethtool_init(struct net_device *netdev, bool enable) +{ + struct otx2_nic *pf = netdev_priv(netdev); + + /* IPsec offload supported on cn10k */ + if (!is_dev_support_ipsec_offload(pf->pdev)) + return -EOPNOTSUPP; + + /* Initialize CPT for outbound ipsec offload */ + if (enable) + return cn10k_outb_cpt_init(netdev); + + /* Don't do CPT cleanup if SA installed */ + if (pf->ipsec.outb_sa_count) { + netdev_err(pf->netdev, "SA installed on this device\n"); + return -EBUSY; + } + + return cn10k_outb_cpt_clean(pf); +} + +int cn10k_ipsec_init(struct net_device *netdev) +{ + struct otx2_nic *pf = netdev_priv(netdev); + u32 sa_size; + + if (!is_dev_support_ipsec_offload(pf->pdev)) + return 0; + + /* Each SA entry size is 128 Byte round up in size */ + sa_size = sizeof(struct cn10k_tx_sa_s) % OTX2_ALIGN ? + (sizeof(struct cn10k_tx_sa_s) / OTX2_ALIGN + 1) * + OTX2_ALIGN : sizeof(struct cn10k_tx_sa_s); + pf->ipsec.sa_size = sa_size; + + INIT_WORK(&pf->ipsec.sa_work, cn10k_ipsec_sa_wq_handler); + pf->ipsec.sa_workq = alloc_workqueue("cn10k_ipsec_sa_workq", 0, 0); + if (!pf->ipsec.sa_workq) { + netdev_err(pf->netdev, "SA alloc workqueue failed\n"); + return -ENOMEM; + } + + /* Set xfrm device ops */ + netdev->xfrmdev_ops = &cn10k_ipsec_xfrmdev_ops; + netdev->hw_features |= NETIF_F_HW_ESP; + netdev->hw_enc_features |= NETIF_F_HW_ESP; + + cn10k_cpt_device_set_unavailable(pf); + return 0; +} +EXPORT_SYMBOL(cn10k_ipsec_init); + +void cn10k_ipsec_clean(struct otx2_nic *pf) +{ + if (!is_dev_support_ipsec_offload(pf->pdev)) + return; + + if (!(pf->flags & OTX2_FLAG_IPSEC_OFFLOAD_ENABLED)) + return; + + if (pf->ipsec.sa_workq) { + destroy_workqueue(pf->ipsec.sa_workq); + pf->ipsec.sa_workq = NULL; + } + + cn10k_outb_cpt_clean(pf); +} +EXPORT_SYMBOL(cn10k_ipsec_clean); + +static u16 cn10k_ipsec_get_ip_data_len(struct xfrm_state *x, + struct sk_buff *skb) +{ + struct ipv6hdr *ipv6h; + struct iphdr *iph; + u8 *src; + + src = (u8 *)skb->data + ETH_HLEN; + + if (x->props.family == AF_INET) { + iph = (struct iphdr *)src; + return ntohs(iph->tot_len); + } + + ipv6h = (struct ipv6hdr *)src; + return ntohs(ipv6h->payload_len) + sizeof(struct ipv6hdr); +} + +/* Prepare CPT and NIX SQE scatter/gather subdescriptor structure. + * SG of NIX and CPT are same in size. + * Layout of a NIX SQE and CPT SG entry: + * ----------------------------- + * | CPT Scatter Gather | + * | (SQE SIZE) | + * | | + * ----------------------------- + * | NIX SQE | + * | (SQE SIZE) | + * | | + * ----------------------------- + */ +bool otx2_sqe_add_sg_ipsec(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, + struct sk_buff *skb, int num_segs, int *offset) +{ + struct cpt_sg_s *cpt_sg = NULL; + struct nix_sqe_sg_s *sg = NULL; + u64 dma_addr, *iova = NULL; + u64 *cpt_iova = NULL; + u16 *sg_lens = NULL; + int seg, len; + + sq->sg[sq->head].num_segs = 0; + cpt_sg = (struct cpt_sg_s *)(sq->sqe_base - sq->sqe_size); + + for (seg = 0; seg < num_segs; seg++) { + if ((seg % MAX_SEGS_PER_SG) == 0) { + sg = (struct nix_sqe_sg_s *)(sq->sqe_base + *offset); + sg->ld_type = NIX_SEND_LDTYPE_LDD; + sg->subdc = NIX_SUBDC_SG; + sg->segs = 0; + sg_lens = (void *)sg; + iova = (void *)sg + sizeof(*sg); + /* Next subdc always starts at a 16byte boundary. + * So if sg->segs is whether 2 or 3, offset += 16bytes. + */ + if ((num_segs - seg) >= (MAX_SEGS_PER_SG - 1)) + *offset += sizeof(*sg) + (3 * sizeof(u64)); + else + *offset += sizeof(*sg) + sizeof(u64); + + cpt_sg += (seg / MAX_SEGS_PER_SG) * 4; + cpt_iova = (void *)cpt_sg + sizeof(*cpt_sg); + } + dma_addr = otx2_dma_map_skb_frag(pfvf, skb, seg, &len); + if (dma_mapping_error(pfvf->dev, dma_addr)) + return false; + + sg_lens[seg % MAX_SEGS_PER_SG] = len; + sg->segs++; + *iova++ = dma_addr; + *cpt_iova++ = dma_addr; + + /* Save DMA mapping info for later unmapping */ + sq->sg[sq->head].dma_addr[seg] = dma_addr; + sq->sg[sq->head].size[seg] = len; + sq->sg[sq->head].num_segs++; + + *cpt_sg = *(struct cpt_sg_s *)sg; + cpt_sg->rsvd_63_50 = 0; + } + + sq->sg[sq->head].skb = (u64)skb; + return true; +} + +static u16 cn10k_ipsec_get_param1(u8 iv_offset) +{ + u16 param1_val; + + /* Set Crypto mode, disable L3/L4 checksum */ + param1_val = CN10K_IPSEC_INST_PARAM1_DIS_L4_CSUM | + CN10K_IPSEC_INST_PARAM1_DIS_L3_CSUM; + param1_val |= (u16)iv_offset << CN10K_IPSEC_INST_PARAM1_IV_OFFSET_SHIFT; + return param1_val; +} + +bool cn10k_ipsec_transmit(struct otx2_nic *pf, struct netdev_queue *txq, + struct otx2_snd_queue *sq, struct sk_buff *skb, + int num_segs, int size) +{ + struct cpt_inst_s inst; + struct cpt_res_s *res; + struct xfrm_state *x; + struct qmem *sa_info; + dma_addr_t dptr_iova; + struct sec_path *sp; + u8 encap_offset; + u8 auth_offset; + u8 gthr_size; + u8 iv_offset; + u16 dlen; + + /* Check for IPSEC offload enabled */ + if (!(pf->flags & OTX2_FLAG_IPSEC_OFFLOAD_ENABLED)) + goto drop; + + sp = skb_sec_path(skb); + if (unlikely(!sp->len)) + goto drop; + + x = xfrm_input_state(skb); + if (unlikely(!x)) + goto drop; + + if (x->props.mode != XFRM_MODE_TRANSPORT && + x->props.mode != XFRM_MODE_TUNNEL) + goto drop; + + dlen = cn10k_ipsec_get_ip_data_len(x, skb); + if (dlen == 0 && netif_msg_tx_err(pf)) { + netdev_err(pf->netdev, "Invalid IP header, ip-length zero\n"); + goto drop; + } + + /* Check for valid SA context */ + sa_info = (struct qmem *)x->xso.offload_handle; + if (!sa_info) + goto drop; + + memset(&inst, 0, sizeof(struct cpt_inst_s)); + + /* Get authentication offset */ + if (x->props.family == AF_INET) + auth_offset = sizeof(struct iphdr); + else + auth_offset = sizeof(struct ipv6hdr); + + /* IV offset is after ESP header */ + iv_offset = auth_offset + sizeof(struct ip_esp_hdr); + /* Encap will start after IV */ + encap_offset = iv_offset + GCM_RFC4106_IV_SIZE; + + /* CPT Instruction word-1 */ + res = (struct cpt_res_s *)(sq->cpt_resp->base + (64 * sq->head)); + res->compcode = 0; + inst.res_addr = sq->cpt_resp->iova + (64 * sq->head); + + /* CPT Instruction word-2 */ + inst.rvu_pf_func = pf->pcifunc; + + /* CPT Instruction word-3: + * Set QORD to force CPT_RES_S write completion + */ + inst.qord = 1; + + /* CPT Instruction word-4 */ + /* inst.dlen should not include ICV length */ + inst.dlen = dlen + ETH_HLEN - (x->aead->alg_icv_len / 8); + inst.opcode_major = CN10K_IPSEC_MAJOR_OP_OUTB_IPSEC; + inst.param1 = cn10k_ipsec_get_param1(iv_offset); + + inst.param2 = encap_offset << + CN10K_IPSEC_INST_PARAM2_ENC_DATA_OFFSET_SHIFT; + inst.param2 |= (u16)auth_offset << + CN10K_IPSEC_INST_PARAM2_AUTH_DATA_OFFSET_SHIFT; + + /* CPT Instruction word-5 */ + gthr_size = num_segs / MAX_SEGS_PER_SG; + gthr_size = (num_segs % MAX_SEGS_PER_SG) ? gthr_size + 1 : gthr_size; + + gthr_size &= 0xF; + dptr_iova = (sq->sqe_ring->iova + (sq->head * (sq->sqe_size * 2))); + inst.dptr = dptr_iova | ((u64)gthr_size << 60); + + /* CPT Instruction word-6 */ + inst.rptr = inst.dptr; + + /* CPT Instruction word-7 */ + inst.cptr = sa_info->iova; + inst.ctx_val = 1; + inst.egrp = CN10K_DEF_CPT_IPSEC_EGRP; + + /* CPT Instruction word-0 */ + inst.nixtxl = (size / 16) - 1; + inst.dat_offset = ETH_HLEN; + inst.nixtx_offset = sq->sqe_size; + + netdev_tx_sent_queue(txq, skb->len); + + /* Finally Flush the CPT instruction */ + sq->head++; + sq->head &= (sq->sqe_cnt - 1); + cn10k_cpt_inst_flush(pf, &inst, sizeof(struct cpt_inst_s)); + return true; +drop: + dev_kfree_skb_any(skb); + return false; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h new file mode 100644 index 000000000000..9965df0faa3e --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h @@ -0,0 +1,265 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell IPSEC offload driver + * + * Copyright (C) 2024 Marvell. + */ + +#ifndef CN10K_IPSEC_H +#define CN10K_IPSEC_H + +#include + +DECLARE_STATIC_KEY_FALSE(cn10k_ipsec_sa_enabled); + +/* CPT instruction size in bytes */ +#define CN10K_CPT_INST_SIZE 64 + +/* CPT instruction (CPT_INST_S) queue length */ +#define CN10K_CPT_INST_QLEN 8200 + +/* CPT instruction queue size passed to HW is in units of + * 40*CPT_INST_S messages. + */ +#define CN10K_CPT_SIZE_DIV40 (CN10K_CPT_INST_QLEN / 40) + +/* CPT needs 320 free entries */ +#define CN10K_CPT_INST_QLEN_EXTRA_BYTES (320 * CN10K_CPT_INST_SIZE) +#define CN10K_CPT_EXTRA_SIZE_DIV40 (320 / 40) + +/* CPT instruction queue length in bytes */ +#define CN10K_CPT_INST_QLEN_BYTES \ + ((CN10K_CPT_SIZE_DIV40 * 40 * CN10K_CPT_INST_SIZE) + \ + CN10K_CPT_INST_QLEN_EXTRA_BYTES) + +/* CPT instruction group queue length in bytes */ +#define CN10K_CPT_INST_GRP_QLEN_BYTES \ + ((CN10K_CPT_SIZE_DIV40 + CN10K_CPT_EXTRA_SIZE_DIV40) * 16) + +/* CPT FC length in bytes */ +#define CN10K_CPT_Q_FC_LEN 128 + +/* Default CPT engine group for ipsec offload */ +#define CN10K_DEF_CPT_IPSEC_EGRP 1 + +/* CN10K CPT LF registers */ +#define CPT_LFBASE (BLKTYPE_CPT << RVU_FUNC_BLKADDR_SHIFT) +#define CN10K_CPT_LF_CTL (CPT_LFBASE | 0x10) +#define CN10K_CPT_LF_INPROG (CPT_LFBASE | 0x40) +#define CN10K_CPT_LF_Q_BASE (CPT_LFBASE | 0xf0) +#define CN10K_CPT_LF_Q_SIZE (CPT_LFBASE | 0x100) +#define CN10K_CPT_LF_Q_INST_PTR (CPT_LFBASE | 0x110) +#define CN10K_CPT_LF_Q_GRP_PTR (CPT_LFBASE | 0x120) +#define CN10K_CPT_LF_NQX(a) (CPT_LFBASE | 0x400 | (a) << 3) +#define CN10K_CPT_LF_CTX_FLUSH (CPT_LFBASE | 0x510) + +/* IPSEC Instruction opcodes */ +#define CN10K_IPSEC_MAJOR_OP_WRITE_SA 0x01UL +#define CN10K_IPSEC_MINOR_OP_WRITE_SA 0x09UL +#define CN10K_IPSEC_MAJOR_OP_OUTB_IPSEC 0x2AUL + +enum cn10k_cpt_comp_e { + CN10K_CPT_COMP_E_NOTDONE = 0x00, + CN10K_CPT_COMP_E_GOOD = 0x01, + CN10K_CPT_COMP_E_FAULT = 0x02, + CN10K_CPT_COMP_E_HWERR = 0x04, + CN10K_CPT_COMP_E_INSTERR = 0x05, + CN10K_CPT_COMP_E_WARN = 0x06, + CN10K_CPT_COMP_E_MASK = 0x3F +}; + +struct cn10k_cpt_inst_queue { + u8 *vaddr; + u8 *real_vaddr; + dma_addr_t dma_addr; + dma_addr_t real_dma_addr; + u32 size; +}; + +enum cn10k_cpt_hw_state_e { + CN10K_CPT_HW_UNAVAILABLE, + CN10K_CPT_HW_AVAILABLE, + CN10K_CPT_HW_IN_USE +}; + +struct cn10k_ipsec { + /* Outbound CPT */ + u64 io_addr; + atomic_t cpt_state; + struct cn10k_cpt_inst_queue iq; + + /* SA info */ + u32 sa_size; + u32 outb_sa_count; + struct work_struct sa_work; + struct workqueue_struct *sa_workq; +}; + +/* CN10K IPSEC Security Association (SA) */ +/* SA direction */ +#define CN10K_IPSEC_SA_DIR_INB 0 +#define CN10K_IPSEC_SA_DIR_OUTB 1 +/* SA protocol */ +#define CN10K_IPSEC_SA_IPSEC_PROTO_AH 0 +#define CN10K_IPSEC_SA_IPSEC_PROTO_ESP 1 +/* SA Encryption Type */ +#define CN10K_IPSEC_SA_ENCAP_TYPE_AES_GCM 5 +/* SA IPSEC mode Transport/Tunnel */ +#define CN10K_IPSEC_SA_IPSEC_MODE_TRANSPORT 0 +#define CN10K_IPSEC_SA_IPSEC_MODE_TUNNEL 1 +/* SA AES Key Length */ +#define CN10K_IPSEC_SA_AES_KEY_LEN_128 1 +#define CN10K_IPSEC_SA_AES_KEY_LEN_192 2 +#define CN10K_IPSEC_SA_AES_KEY_LEN_256 3 +/* IV Source */ +#define CN10K_IPSEC_SA_IV_SRC_COUNTER 0 +#define CN10K_IPSEC_SA_IV_SRC_PACKET 3 + +struct cn10k_tx_sa_s { + u64 esn_en : 1; /* W0 */ + u64 rsvd_w0_1_8 : 8; + u64 hw_ctx_off : 7; + u64 ctx_id : 16; + u64 rsvd_w0_32_47 : 16; + u64 ctx_push_size : 7; + u64 rsvd_w0_55 : 1; + u64 ctx_hdr_size : 2; + u64 aop_valid : 1; + u64 rsvd_w0_59 : 1; + u64 ctx_size : 4; + u64 w1; /* W1 */ + u64 sa_valid : 1; /* W2 */ + u64 sa_dir : 1; + u64 rsvd_w2_2_3 : 2; + u64 ipsec_mode : 1; + u64 ipsec_protocol : 1; + u64 aes_key_len : 2; + u64 enc_type : 3; + u64 rsvd_w2_11_19 : 9; + u64 iv_src : 2; + u64 rsvd_w2_22_31 : 10; + u64 rsvd_w2_32_63 : 32; + u64 w3; /* W3 */ + u8 cipher_key[32]; /* W4 - W7 */ + u32 rsvd_w8_0_31; /* W8 : IV */ + u32 iv_gcm_salt; + u64 rsvd_w9_w30[22]; /* W9 - W30 */ + u64 hw_ctx[6]; /* W31 - W36 */ +}; + +/* CPT instruction parameter-1 */ +#define CN10K_IPSEC_INST_PARAM1_DIS_L4_CSUM 0x1 +#define CN10K_IPSEC_INST_PARAM1_DIS_L3_CSUM 0x2 +#define CN10K_IPSEC_INST_PARAM1_CRYPTO_MODE 0x20 +#define CN10K_IPSEC_INST_PARAM1_IV_OFFSET_SHIFT 8 + +/* CPT instruction parameter-2 */ +#define CN10K_IPSEC_INST_PARAM2_ENC_DATA_OFFSET_SHIFT 0 +#define CN10K_IPSEC_INST_PARAM2_AUTH_DATA_OFFSET_SHIFT 8 + +/* CPT Instruction Structure */ +struct cpt_inst_s { + u64 nixtxl : 3; /* W0 */ + u64 doneint : 1; + u64 rsvd_w0_4_15 : 12; + u64 dat_offset : 8; + u64 ext_param1 : 8; + u64 nixtx_offset : 20; + u64 rsvd_w0_52_63 : 12; + u64 res_addr; /* W1 */ + u64 tag : 32; /* W2 */ + u64 tt : 2; + u64 grp : 10; + u64 rsvd_w2_44_47 : 4; + u64 rvu_pf_func : 16; + u64 qord : 1; /* W3 */ + u64 rsvd_w3_1_2 : 2; + u64 wqe_ptr : 61; + u64 dlen : 16; /* W4 */ + u64 param2 : 16; + u64 param1 : 16; + u64 opcode_major : 8; + u64 opcode_minor : 8; + u64 dptr; /* W5 */ + u64 rptr; /* W6 */ + u64 cptr : 60; /* W7 */ + u64 ctx_val : 1; + u64 egrp : 3; +}; + +/* CPT Instruction Result Structure */ +struct cpt_res_s { + u64 compcode : 7; /* W0 */ + u64 doneint : 1; + u64 uc_compcode : 8; + u64 uc_info : 48; + u64 esn; /* W1 */ +}; + +/* CPT SG structure */ +struct cpt_sg_s { + u64 seg1_size : 16; + u64 seg2_size : 16; + u64 seg3_size : 16; + u64 segs : 2; + u64 rsvd_63_50 : 14; +}; + +/* CPT LF_INPROG Register */ +#define CPT_LF_INPROG_INFLIGHT GENMASK_ULL(8, 0) +#define CPT_LF_INPROG_GRB_CNT GENMASK_ULL(39, 32) +#define CPT_LF_INPROG_GWB_CNT GENMASK_ULL(47, 40) + +/* CPT LF_Q_GRP_PTR Register */ +#define CPT_LF_Q_GRP_PTR_DQ_PTR GENMASK_ULL(14, 0) +#define CPT_LF_Q_GRP_PTR_NQ_PTR GENMASK_ULL(46, 32) + +/* CPT LF_Q_SIZE Register */ +#define CPT_LF_Q_BASE_ADDR GENMASK_ULL(52, 7) + +/* CPT LF_Q_SIZE Register */ +#define CPT_LF_Q_SIZE_DIV40 GENMASK_ULL(14, 0) + +/* CPT LF CTX Flush Register */ +#define CPT_LF_CTX_FLUSH GENMASK_ULL(45, 0) + +#ifdef CONFIG_XFRM_OFFLOAD +int cn10k_ipsec_init(struct net_device *netdev); +void cn10k_ipsec_clean(struct otx2_nic *pf); +int cn10k_ipsec_ethtool_init(struct net_device *netdev, bool enable); +bool otx2_sqe_add_sg_ipsec(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, + struct sk_buff *skb, int num_segs, int *offset); +bool cn10k_ipsec_transmit(struct otx2_nic *pf, struct netdev_queue *txq, + struct otx2_snd_queue *sq, struct sk_buff *skb, + int num_segs, int size); +#else +static inline __maybe_unused int cn10k_ipsec_init(struct net_device *netdev) +{ + return 0; +} + +static inline __maybe_unused void cn10k_ipsec_clean(struct otx2_nic *pf) +{ +} + +static inline __maybe_unused +int cn10k_ipsec_ethtool_init(struct net_device *netdev, bool enable) +{ + return 0; +} + +static inline bool __maybe_unused +otx2_sqe_add_sg_ipsec(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, + struct sk_buff *skb, int num_segs, int *offset) +{ + return true; +} + +static inline bool __maybe_unused +cn10k_ipsec_transmit(struct otx2_nic *pf, struct netdev_queue *txq, + struct otx2_snd_queue *sq, struct sk_buff *skb, + int num_segs, int size) +{ + return true; +} +#endif +#endif // CN10K_IPSEC_H diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 6cc7a78968fc..f3b9daffaec3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -133,9 +133,7 @@ static const char *rsrc_name(enum mcs_rsrc_type rsrc_type) return "SA"; default: return "Unknown"; - }; - - return "Unknown"; + } } static int cn10k_mcs_alloc_rsrc(struct otx2_nic *pfvf, enum mcs_direction dir, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 523ecb798a7a..2b49bfec7869 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -10,12 +10,19 @@ #include #include #include +#include +#include #include "otx2_reg.h" #include "otx2_common.h" #include "otx2_struct.h" #include "cn10k.h" +static bool otx2_is_pfc_enabled(struct otx2_nic *pfvf) +{ + return IS_ENABLED(CONFIG_DCB) && !!pfvf->pfc_en; +} + static void otx2_nix_rq_op_stats(struct queue_stats *stats, struct otx2_nic *pfvf, int qidx) { @@ -964,6 +971,29 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) if (err) return err; + /* Allocate memory for NIX SQE (which includes NIX SG) and CPT SG. + * SG of NIX and CPT are same in size. Allocate memory for CPT SG + * same as NIX SQE for base address alignment. + * Layout of a NIX SQE and CPT SG entry: + * ----------------------------- + * | CPT Scatter Gather | + * | (SQE SIZE) | + * | | + * ----------------------------- + * | NIX SQE | + * | (SQE SIZE) | + * | | + * ----------------------------- + */ + err = qmem_alloc(pfvf->dev, &sq->sqe_ring, qset->sqe_cnt, + sq->sqe_size * 2); + if (err) + return err; + + err = qmem_alloc(pfvf->dev, &sq->cpt_resp, qset->sqe_cnt, 64); + if (err) + return err; + if (qidx < pfvf->hw.tx_queues) { err = qmem_alloc(pfvf->dev, &sq->tso_hdrs, qset->sqe_cnt, TSO_HEADER_SIZE); @@ -1722,18 +1752,43 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable) return -ENOMEM; req->chan_base = 0; -#ifdef CONFIG_DCB - req->chan_cnt = pfvf->pfc_en ? IEEE_8021QAZ_MAX_TCS : 1; - req->bpid_per_chan = pfvf->pfc_en ? 1 : 0; -#else - req->chan_cnt = 1; - req->bpid_per_chan = 0; -#endif + if (otx2_is_pfc_enabled(pfvf)) { + req->chan_cnt = IEEE_8021QAZ_MAX_TCS; + req->bpid_per_chan = 1; + } else { + req->chan_cnt = 1; + req->bpid_per_chan = 0; + } return otx2_sync_mbox_msg(&pfvf->mbox); } EXPORT_SYMBOL(otx2_nix_config_bp); +int otx2_nix_cpt_config_bp(struct otx2_nic *pfvf, bool enable) +{ + struct nix_bp_cfg_req *req; + + if (enable) + req = otx2_mbox_alloc_msg_nix_cpt_bp_enable(&pfvf->mbox); + else + req = otx2_mbox_alloc_msg_nix_cpt_bp_disable(&pfvf->mbox); + + if (!req) + return -ENOMEM; + + req->chan_base = 0; + if (otx2_is_pfc_enabled(pfvf)) { + req->chan_cnt = IEEE_8021QAZ_MAX_TCS; + req->bpid_per_chan = 1; + } else { + req->chan_cnt = 1; + req->bpid_per_chan = 0; + } + + return otx2_sync_mbox_msg(&pfvf->mbox); +} +EXPORT_SYMBOL(otx2_nix_cpt_config_bp); + /* Mbox message handlers */ void mbox_handler_cgx_stats(struct otx2_nic *pfvf, struct cgx_stats_rsp *rsp) @@ -1947,3 +2002,48 @@ EXPORT_SYMBOL(otx2_mbox_up_handler_ ## _fn_name); MBOX_UP_CGX_MESSAGES MBOX_UP_MCS_MESSAGES #undef M + +dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf, + struct sk_buff *skb, int seg, int *len) +{ + enum dma_data_direction dir = DMA_TO_DEVICE; + const skb_frag_t *frag; + struct page *page; + int offset; + + /* Crypto hardware need write permission for ipsec crypto offload */ + if (unlikely(xfrm_offload(skb))) { + dir = DMA_BIDIRECTIONAL; + skb = skb_unshare(skb, GFP_ATOMIC); + } + + /* First segment is always skb->data */ + if (!seg) { + page = virt_to_page(skb->data); + offset = offset_in_page(skb->data); + *len = skb_headlen(skb); + } else { + frag = &skb_shinfo(skb)->frags[seg - 1]; + page = skb_frag_page(frag); + offset = skb_frag_off(frag); + *len = skb_frag_size(frag); + } + return otx2_dma_map_page(pfvf, page, offset, *len, dir); +} + +void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg) +{ + enum dma_data_direction dir = DMA_TO_DEVICE; + struct sk_buff *skb = NULL; + int seg; + + skb = (struct sk_buff *)sg->skb; + if (unlikely(xfrm_offload(skb))) + dir = DMA_BIDIRECTIONAL; + + for (seg = 0; seg < sg->num_segs; seg++) { + otx2_dma_unmap_page(pfvf, sg->dma_addr[seg], + sg->size[seg], dir); + } + sg->num_segs = 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 566848663fea..65814e3dc93f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -30,6 +30,7 @@ #include #include "qos.h" #include "rep.h" +#include "cn10k_ipsec.h" /* IPv4 flag more fragment bit */ #define IPV4_FLAG_MORE 0x20 @@ -40,6 +41,7 @@ #define PCI_DEVID_OCTEONTX2_RVU_AFVF 0xA0F8 #define PCI_SUBSYS_DEVID_96XX_RVU_PFVF 0xB200 +#define PCI_SUBSYS_DEVID_CN10K_A_RVU_PFVF 0xB900 #define PCI_SUBSYS_DEVID_CN10K_B_RVU_PFVF 0xBD00 #define PCI_DEVID_OCTEONTX2_SDP_REP 0xA0F7 @@ -55,6 +57,9 @@ #define NIX_PF_PFC_PRIO_MAX 8 #endif +/* Number of segments per SG structure */ +#define MAX_SEGS_PER_SG 3 + enum arua_mapped_qtypes { AURA_NIX_RQ, AURA_NIX_SQ, @@ -448,6 +453,7 @@ struct otx2_nic { #define OTX2_FLAG_TC_MARK_ENABLED BIT_ULL(17) #define OTX2_FLAG_REP_MODE_ENABLED BIT_ULL(18) #define OTX2_FLAG_PORT_UP BIT_ULL(19) +#define OTX2_FLAG_IPSEC_OFFLOAD_ENABLED BIT_ULL(20) u64 flags; u64 *cq_op_addr; @@ -499,9 +505,9 @@ struct otx2_nic { /* Devlink */ struct otx2_devlink *dl; -#ifdef CONFIG_DCB /* PFC */ u8 pfc_en; +#ifdef CONFIG_DCB u8 *queue_to_pfc_map; u16 pfc_schq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC]; bool pfc_alloc_status[NIX_PF_PFC_PRIO_MAX]; @@ -522,6 +528,9 @@ struct otx2_nic { u16 rep_pf_map[RVU_MAX_REP]; u16 esw_mode; #endif + + /* Inline ipsec */ + struct cn10k_ipsec ipsec; }; static inline bool is_otx2_lbkvf(struct pci_dev *pdev) @@ -572,6 +581,15 @@ static inline bool is_dev_cn10kb(struct pci_dev *pdev) return pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_B_RVU_PFVF; } +static inline bool is_dev_cn10ka_b0(struct pci_dev *pdev) +{ + if (pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_A_RVU_PFVF && + (pdev->revision & 0xFF) == 0x54) + return true; + + return false; +} + static inline void otx2_setup_dev_hw_settings(struct otx2_nic *pfvf) { struct otx2_hw *hw = &pfvf->hw; @@ -621,6 +639,9 @@ static inline void __iomem *otx2_get_regaddr(struct otx2_nic *nic, u64 offset) case BLKTYPE_NPA: blkaddr = BLKADDR_NPA; break; + case BLKTYPE_CPT: + blkaddr = BLKADDR_CPT0; + break; default: blkaddr = BLKADDR_RVUM; break; @@ -985,6 +1006,7 @@ int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable); void otx2_ctx_disable(struct mbox *mbox, int type, bool npa); int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable); +int otx2_nix_cpt_config_bp(struct otx2_nic *pfvf, bool enable); void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int qidx); void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq); int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura); @@ -1149,4 +1171,8 @@ static inline int mcam_entry_cmp(const void *a, const void *b) { return *(u16 *)a - *(u16 *)b; } + +dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf, + struct sk_buff *skb, int seg, int *len); +void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg); #endif /* OTX2_COMMON_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index 294fba58b670..f110dfa42360 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -435,6 +435,9 @@ process_pfc: return err; } + /* Default disable backpressure on NIX-CPT */ + otx2_nix_cpt_config_bp(pfvf, false); + /* Request Per channel Bpids */ if (pfc->pfc_en) otx2_nix_config_bp(pfvf, true); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index e310f99b1736..e1dde93e8af8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -26,6 +26,7 @@ #include "cn10k.h" #include "qos.h" #include +#include "cn10k_ipsec.h" #define DRV_NAME "rvu_nicpf" #define DRV_STRING "Marvell RVU NIC Physical Function Driver" @@ -1484,6 +1485,8 @@ static void otx2_free_sq_res(struct otx2_nic *pf) if (!sq->sqe) continue; qmem_free(pf->dev, sq->sqe); + qmem_free(pf->dev, sq->sqe_ring); + qmem_free(pf->dev, sq->cpt_resp); qmem_free(pf->dev, sq->tso_hdrs); kfree(sq->sg); kfree(sq->sqb_ptrs); @@ -1551,6 +1554,9 @@ int otx2_init_hw_resources(struct otx2_nic *pf) if (err) goto err_free_npa_lf; + /* Default disable backpressure on NIX-CPT */ + otx2_nix_cpt_config_bp(pf, false); + /* Enable backpressure for CGX mapped PF/VFs */ if (!is_otx2_lbkvf(pf->pdev)) otx2_nix_config_bp(pf, true); @@ -2273,6 +2279,10 @@ static int otx2_set_features(struct net_device *netdev, return otx2_enable_rxvlan(pf, features & NETIF_F_HW_VLAN_CTAG_RX); + if (changed & NETIF_F_HW_ESP) + return cn10k_ipsec_ethtool_init(netdev, + features & NETIF_F_HW_ESP); + return otx2_handle_ntuple_tc_features(netdev, features); } @@ -3162,10 +3172,14 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* reset CGX/RPM MAC stats */ otx2_reset_mac_stats(pf); + err = cn10k_ipsec_init(netdev); + if (err) + goto err_mcs_free; + err = register_netdev(netdev); if (err) { dev_err(dev, "Failed to register netdevice\n"); - goto err_mcs_free; + goto err_ipsec_clean; } err = otx2_wq_init(pf); @@ -3206,6 +3220,8 @@ err_mcam_flow_del: otx2_mcam_flow_del(pf); err_unreg_netdev: unregister_netdev(netdev); +err_ipsec_clean: + cn10k_ipsec_clean(pf); err_mcs_free: cn10k_mcs_free(pf); err_del_mcam_entries: @@ -3403,6 +3419,7 @@ static void otx2_remove(struct pci_dev *pdev) otx2_unregister_dl(pf); unregister_netdev(netdev); + cn10k_ipsec_clean(pf); cn10k_mcs_free(pf); otx2_sriov_disable(pf->pdev); otx2_sriov_vfcfg_cleanup(pf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 04bc06a80e23..224cef938927 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "otx2_reg.h" #include "otx2_common.h" @@ -26,12 +27,25 @@ */ #define PTP_SYNC_SEC_OFFSET 34 +DEFINE_STATIC_KEY_FALSE(cn10k_ipsec_sa_enabled); + static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, struct bpf_prog *prog, struct nix_cqe_rx_s *cqe, struct otx2_cq_queue *cq, bool *need_xdp_flush); +static void otx2_sq_set_sqe_base(struct otx2_snd_queue *sq, + struct sk_buff *skb) +{ + if (static_branch_unlikely(&cn10k_ipsec_sa_enabled) && + (xfrm_offload(skb))) + sq->sqe_base = sq->sqe_ring->base + sq->sqe_size + + (sq->head * (sq->sqe_size * 2)); + else + sq->sqe_base = sq->sqe->base; +} + static int otx2_nix_cq_op_status(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) { @@ -80,38 +94,6 @@ static unsigned int frag_num(unsigned int i) #endif } -static dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf, - struct sk_buff *skb, int seg, int *len) -{ - const skb_frag_t *frag; - struct page *page; - int offset; - - /* First segment is always skb->data */ - if (!seg) { - page = virt_to_page(skb->data); - offset = offset_in_page(skb->data); - *len = skb_headlen(skb); - } else { - frag = &skb_shinfo(skb)->frags[seg - 1]; - page = skb_frag_page(frag); - offset = skb_frag_off(frag); - *len = skb_frag_size(frag); - } - return otx2_dma_map_page(pfvf, page, offset, *len, DMA_TO_DEVICE); -} - -static void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg) -{ - int seg; - - for (seg = 0; seg < sg->num_segs; seg++) { - otx2_dma_unmap_page(pfvf, sg->dma_addr[seg], - sg->size[seg], DMA_TO_DEVICE); - } - sg->num_segs = 0; -} - static void otx2_xdp_snd_pkt_handler(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, struct nix_cqe_tx_s *cqe) @@ -625,7 +607,6 @@ void otx2_sqe_flush(void *dev, struct otx2_snd_queue *sq, sq->head &= (sq->sqe_cnt - 1); } -#define MAX_SEGS_PER_SG 3 /* Add SQE scatter/gather subdescriptor structure */ static bool otx2_sqe_add_sg(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, struct sk_buff *skb, int num_segs, int *offset) @@ -1161,6 +1142,7 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq, int offset, num_segs, free_desc; struct nix_sqe_hdr_s *sqe_hdr; struct otx2_nic *pfvf = dev; + bool ret; /* Check if there is enough room between producer * and consumer index. @@ -1177,6 +1159,7 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq, /* If SKB doesn't fit in a single SQE, linearize it. * TODO: Consider adding JUMP descriptor instead. */ + if (unlikely(num_segs > OTX2_MAX_FRAGS_IN_SQE)) { if (__skb_linearize(skb)) { dev_kfree_skb_any(skb); @@ -1196,6 +1179,9 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq, return true; } + /* Set sqe base address */ + otx2_sq_set_sqe_base(sq, skb); + /* Set SQE's SEND_HDR. * Do not clear the first 64bit as it contains constant info. */ @@ -1208,7 +1194,13 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq, otx2_sqe_add_ext(pfvf, sq, skb, &offset); /* Add SG subdesc with data frags */ - if (!otx2_sqe_add_sg(pfvf, sq, skb, num_segs, &offset)) { + if (static_branch_unlikely(&cn10k_ipsec_sa_enabled) && + (xfrm_offload(skb))) + ret = otx2_sqe_add_sg_ipsec(pfvf, sq, skb, num_segs, &offset); + else + ret = otx2_sqe_add_sg(pfvf, sq, skb, num_segs, &offset); + + if (!ret) { otx2_dma_unmap_skb_frags(pfvf, &sq->sg[sq->head]); return false; } @@ -1217,11 +1209,15 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq, sqe_hdr->sizem1 = (offset / 16) - 1; + if (static_branch_unlikely(&cn10k_ipsec_sa_enabled) && + (xfrm_offload(skb))) + return cn10k_ipsec_transmit(pfvf, txq, sq, skb, num_segs, + offset); + netdev_tx_sent_queue(txq, skb->len); /* Flush SQE to HW */ pfvf->hw_ops->sqe_flush(pfvf, sq, offset, qidx); - return true; } EXPORT_SYMBOL(otx2_sq_append_skb); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index e1db5f961877..d23810963fdb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -101,6 +101,9 @@ struct otx2_snd_queue { struct queue_stats stats; u16 sqb_count; u64 *sqb_ptrs; + /* SQE ring and CPT response queue for Inline IPSEC */ + struct qmem *sqe_ring; + struct qmem *cpt_resp; } ____cacheline_aligned_in_smp; enum cq_type { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 839fc77c11b2..e926c6ce96cf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -14,6 +14,7 @@ #include "otx2_reg.h" #include "otx2_ptp.h" #include "cn10k.h" +#include "cn10k_ipsec.h" #define DRV_NAME "rvu_nicvf" #define DRV_STRING "Marvell RVU NIC Virtual Function Driver" @@ -693,10 +694,14 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) pdev->bus->number, n); } + err = cn10k_ipsec_init(netdev); + if (err) + goto err_ptp_destroy; + err = register_netdev(netdev); if (err) { dev_err(dev, "Failed to register netdevice\n"); - goto err_ptp_destroy; + goto err_ipsec_clean; } err = otx2_vf_wq_init(vf); @@ -730,6 +735,8 @@ err_shutdown_tc: otx2_shutdown_tc(vf); err_unreg_netdev: unregister_netdev(netdev); +err_ipsec_clean: + cn10k_ipsec_clean(vf); err_ptp_destroy: otx2_ptp_destroy(vf); err_detach_rsrc: @@ -782,6 +789,7 @@ static void otx2vf_remove(struct pci_dev *pdev) unregister_netdev(netdev); if (vf->otx2_wq) destroy_workqueue(vf->otx2_wq); + cn10k_ipsec_clean(vf); otx2_ptp_destroy(vf); otx2_mcam_flow_del(vf); otx2_shutdown_tc(vf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c index 232b10740c13..04e08e06f30f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c @@ -680,14 +680,17 @@ int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack) ndev->features |= ndev->hw_features; eth_hw_addr_random(ndev); err = rvu_rep_devlink_port_register(rep); - if (err) + if (err) { + free_netdev(ndev); goto exit; + } SET_NETDEV_DEVLINK_PORT(ndev, &rep->dl_port); err = register_netdev(ndev); if (err) { NL_SET_ERR_MSG_MOD(extack, "PFVF representor registration failed"); + rvu_rep_devlink_port_unregister(rep); free_netdev(ndev); goto exit; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 22ca6ee9665e..440a4c42b405 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -280,6 +280,7 @@ prestera_mac_select_pcs(struct phylink_config *config, } static void prestera_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct prestera_port *port = container_of(pcs, struct prestera_port, diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 25bf6ec44289..a1bada9eaaf6 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -3742,10 +3742,7 @@ static int skge_device_event(struct notifier_block *unused, skge = netdev_priv(dev); switch (event) { case NETDEV_CHANGENAME: - if (skge->debugfs) - skge->debugfs = debugfs_rename(skge_debug, - skge->debugfs, - skge_debug, dev->name); + debugfs_change_name(skge->debugfs, "%s", dev->name); break; case NETDEV_GOING_DOWN: diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 3914cd9210d4..d7121c836508 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -130,6 +130,7 @@ static const struct pci_device_id sky2_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436C) }, /* 88E8072 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436D) }, /* 88E8055 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4370) }, /* 88E8075 */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4373) }, /* 88E8075 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4380) }, /* 88E8057 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4381) }, /* 88E8059 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4382) }, /* 88E8079 */ @@ -4493,10 +4494,7 @@ static int sky2_device_event(struct notifier_block *unused, switch (event) { case NETDEV_CHANGENAME: - if (sky2->debugfs) { - sky2->debugfs = debugfs_rename(sky2_debug, sky2->debugfs, - sky2_debug, dev->name); - } + debugfs_change_name(sky2->debugfs, "%s", dev->name); break; case NETDEV_GOING_DOWN: diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c index 6c683a12d5aa..09f448f29124 100644 --- a/drivers/net/ethernet/mediatek/airoha_eth.c +++ b/drivers/net/ethernet/mediatek/airoha_eth.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #define AIROHA_MAX_NUM_GDM_PORTS 1 @@ -23,8 +24,12 @@ #define AIROHA_MAX_NUM_XSI_RSTS 5 #define AIROHA_MAX_MTU 2000 #define AIROHA_MAX_PACKET_SIZE 2048 +#define AIROHA_NUM_QOS_CHANNELS 4 +#define AIROHA_NUM_QOS_QUEUES 8 #define AIROHA_NUM_TX_RING 32 #define AIROHA_NUM_RX_RING 32 +#define AIROHA_NUM_NETDEV_TX_RINGS (AIROHA_NUM_TX_RING + \ + AIROHA_NUM_QOS_CHANNELS) #define AIROHA_FE_MC_MAX_VLAN_TABLE 64 #define AIROHA_FE_MC_MAX_VLAN_PORT 16 #define AIROHA_NUM_TX_IRQ 2 @@ -40,6 +45,9 @@ #define PSE_RSV_PAGES 128 #define PSE_QUEUE_RSV_PAGES 64 +#define QDMA_METER_IDX(_n) ((_n) & 0xff) +#define QDMA_METER_GROUP(_n) (((_n) >> 8) & 0x3) + /* FE */ #define PSE_BASE 0x0100 #define CSR_IFC_BASE 0x0200 @@ -258,11 +266,11 @@ #define REG_GDM3_FWD_CFG GDM3_BASE #define GDM3_PAD_EN_MASK BIT(28) -#define REG_GDM4_FWD_CFG (GDM4_BASE + 0x100) +#define REG_GDM4_FWD_CFG GDM4_BASE #define GDM4_PAD_EN_MASK BIT(28) #define GDM4_SPORT_OFFSET0_MASK GENMASK(11, 8) -#define REG_GDM4_SRC_PORT_SET (GDM4_BASE + 0x33c) +#define REG_GDM4_SRC_PORT_SET (GDM4_BASE + 0x23c) #define GDM4_SPORT_OFF2_MASK GENMASK(19, 16) #define GDM4_SPORT_OFF1_MASK GENMASK(15, 12) #define GDM4_SPORT_OFF0_MASK GENMASK(11, 8) @@ -541,9 +549,24 @@ #define INGRESS_SLOW_TICK_RATIO_MASK GENMASK(29, 16) #define INGRESS_FAST_TICK_MASK GENMASK(15, 0) +#define REG_QUEUE_CLOSE_CFG(_n) (0x00a0 + ((_n) & 0xfc)) +#define TXQ_DISABLE_CHAN_QUEUE_MASK(_n, _m) BIT((_m) + (((_n) & 0x3) << 3)) + #define REG_TXQ_DIS_CFG_BASE(_n) ((_n) ? 0x20a0 : 0x00a0) #define REG_TXQ_DIS_CFG(_n, _m) (REG_TXQ_DIS_CFG_BASE((_n)) + (_m) << 2) +#define REG_CNTR_CFG(_n) (0x0400 + ((_n) << 3)) +#define CNTR_EN_MASK BIT(31) +#define CNTR_ALL_CHAN_EN_MASK BIT(30) +#define CNTR_ALL_QUEUE_EN_MASK BIT(29) +#define CNTR_ALL_DSCP_RING_EN_MASK BIT(28) +#define CNTR_SRC_MASK GENMASK(27, 24) +#define CNTR_DSCP_RING_MASK GENMASK(20, 16) +#define CNTR_CHAN_MASK GENMASK(7, 3) +#define CNTR_QUEUE_MASK GENMASK(2, 0) + +#define REG_CNTR_VAL(_n) (0x0404 + ((_n) << 3)) + #define REG_LMGR_INIT_CFG 0x1000 #define LMGR_INIT_START BIT(31) #define LMGR_SRAM_MODE_MASK BIT(30) @@ -565,13 +588,34 @@ #define EGRESS_SLOW_TICK_RATIO_MASK GENMASK(29, 16) #define EGRESS_FAST_TICK_MASK GENMASK(15, 0) +#define TRTCM_PARAM_RW_MASK BIT(31) +#define TRTCM_PARAM_RW_DONE_MASK BIT(30) +#define TRTCM_PARAM_TYPE_MASK GENMASK(29, 28) +#define TRTCM_METER_GROUP_MASK GENMASK(27, 26) +#define TRTCM_PARAM_INDEX_MASK GENMASK(23, 17) +#define TRTCM_PARAM_RATE_TYPE_MASK BIT(16) + +#define REG_TRTCM_CFG_PARAM(_n) ((_n) + 0x4) +#define REG_TRTCM_DATA_LOW(_n) ((_n) + 0x8) +#define REG_TRTCM_DATA_HIGH(_n) ((_n) + 0xc) + #define REG_TXWRR_MODE_CFG 0x1020 #define TWRR_WEIGHT_SCALE_MASK BIT(31) #define TWRR_WEIGHT_BASE_MASK BIT(3) +#define REG_TXWRR_WEIGHT_CFG 0x1024 +#define TWRR_RW_CMD_MASK BIT(31) +#define TWRR_RW_CMD_DONE BIT(30) +#define TWRR_CHAN_IDX_MASK GENMASK(23, 19) +#define TWRR_QUEUE_IDX_MASK GENMASK(18, 16) +#define TWRR_VALUE_MASK GENMASK(15, 0) + #define REG_PSE_BUF_USAGE_CFG 0x1028 #define PSE_BUF_ESTIMATE_EN_MASK BIT(29) +#define REG_CHAN_QOS_MODE(_n) (0x1040 + ((_n) << 2)) +#define CHAN_QOS_MODE_MASK(_n) GENMASK(2 + ((_n) << 2), (_n) << 2) + #define REG_GLB_TRTCM_CFG 0x1080 #define GLB_TRTCM_EN_MASK BIT(31) #define GLB_TRTCM_MODE_MASK BIT(30) @@ -720,6 +764,40 @@ enum { FE_PSE_PORT_DROP = 0xf, }; +enum tx_sched_mode { + TC_SCH_WRR8, + TC_SCH_SP, + TC_SCH_WRR7, + TC_SCH_WRR6, + TC_SCH_WRR5, + TC_SCH_WRR4, + TC_SCH_WRR3, + TC_SCH_WRR2, +}; + +enum trtcm_param_type { + TRTCM_MISC_MODE, /* meter_en, pps_mode, tick_sel */ + TRTCM_TOKEN_RATE_MODE, + TRTCM_BUCKETSIZE_SHIFT_MODE, + TRTCM_BUCKET_COUNTER_MODE, +}; + +enum trtcm_mode_type { + TRTCM_COMMIT_MODE, + TRTCM_PEAK_MODE, +}; + +enum trtcm_param { + TRTCM_TICK_SEL = BIT(0), + TRTCM_PKT_MODE = BIT(1), + TRTCM_METER_MODE = BIT(2), +}; + +#define MIN_TOKEN_SIZE 4096 +#define MAX_TOKEN_SIZE_OFFSET 17 +#define TRTCM_TOKEN_RATE_MASK GENMASK(23, 6) +#define TRTCM_TOKEN_RATE_FRACTION_MASK GENMASK(5, 0) + struct airoha_queue_entry { union { void *buf; @@ -810,6 +888,12 @@ struct airoha_gdm_port { int id; struct airoha_hw_stats stats; + + DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS); + + /* qos stats counters */ + u64 cpu_tx_packets; + u64 fwd_tx_packets; }; struct airoha_eth { @@ -1789,6 +1873,10 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q, WRITE_ONCE(q->desc[i].ctrl, cpu_to_le32(val)); } + /* xmit ring drop default setting */ + airoha_qdma_set(qdma, REG_TX_RING_BLOCKING(qid), + TX_RING_IRQ_BLOCKING_TX_DROP_EN_MASK); + airoha_qdma_wr(qdma, REG_TX_RING_BASE(qid), dma_addr); airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head)); @@ -1955,6 +2043,27 @@ static void airoha_qdma_init_qos(struct airoha_qdma *qdma) FIELD_PREP(SLA_SLOW_TICK_RATIO_MASK, 40)); } +static void airoha_qdma_init_qos_stats(struct airoha_qdma *qdma) +{ + int i; + + for (i = 0; i < AIROHA_NUM_QOS_CHANNELS; i++) { + /* Tx-cpu transferred count */ + airoha_qdma_wr(qdma, REG_CNTR_VAL(i << 1), 0); + airoha_qdma_wr(qdma, REG_CNTR_CFG(i << 1), + CNTR_EN_MASK | CNTR_ALL_QUEUE_EN_MASK | + CNTR_ALL_DSCP_RING_EN_MASK | + FIELD_PREP(CNTR_CHAN_MASK, i)); + /* Tx-fwd transferred count */ + airoha_qdma_wr(qdma, REG_CNTR_VAL((i << 1) + 1), 0); + airoha_qdma_wr(qdma, REG_CNTR_CFG(i << 1), + CNTR_EN_MASK | CNTR_ALL_QUEUE_EN_MASK | + CNTR_ALL_DSCP_RING_EN_MASK | + FIELD_PREP(CNTR_SRC_MASK, 1) | + FIELD_PREP(CNTR_CHAN_MASK, i)); + } +} + static int airoha_qdma_hw_init(struct airoha_qdma *qdma) { int i; @@ -2005,6 +2114,7 @@ static int airoha_qdma_hw_init(struct airoha_qdma *qdma) airoha_qdma_set(qdma, REG_TXQ_CNGST_CFG, TXQ_CNGST_DROP_EN | TXQ_CNGST_DEI_DROP_EN); + airoha_qdma_init_qos_stats(qdma); return 0; } @@ -2138,17 +2248,14 @@ static void airoha_hw_cleanup(struct airoha_qdma *qdma) if (!qdma->q_rx[i].ndesc) continue; - napi_disable(&qdma->q_rx[i].napi); netif_napi_del(&qdma->q_rx[i].napi); airoha_qdma_cleanup_rx_queue(&qdma->q_rx[i]); if (qdma->q_rx[i].page_pool) page_pool_destroy(qdma->q_rx[i].page_pool); } - for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) { - napi_disable(&qdma->q_tx_irq[i].napi); + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) netif_napi_del(&qdma->q_tx_irq[i].napi); - } for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { if (!qdma->q_tx[i].ndesc) @@ -2173,6 +2280,21 @@ static void airoha_qdma_start_napi(struct airoha_qdma *qdma) } } +static void airoha_qdma_stop_napi(struct airoha_qdma *qdma) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) + napi_disable(&qdma->q_tx_irq[i].napi); + + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) + continue; + + napi_disable(&qdma->q_rx[i].napi); + } +} + static void airoha_update_hw_stats(struct airoha_gdm_port *port) { struct airoha_eth *eth = port->qdma->eth; @@ -2413,21 +2535,44 @@ static void airoha_dev_get_stats64(struct net_device *dev, } while (u64_stats_fetch_retry(&port->stats.syncp, start)); } +static u16 airoha_dev_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + struct airoha_gdm_port *port = netdev_priv(dev); + int queue, channel; + + /* For dsa device select QoS channel according to the dsa user port + * index, rely on port id otherwise. Select QoS queue based on the + * skb priority. + */ + channel = netdev_uses_dsa(dev) ? skb_get_queue_mapping(skb) : port->id; + channel = channel % AIROHA_NUM_QOS_CHANNELS; + queue = (skb->priority - 1) % AIROHA_NUM_QOS_QUEUES; /* QoS queue */ + queue = channel * AIROHA_NUM_QOS_QUEUES + queue; + + return queue < dev->num_tx_queues ? queue : 0; +} + static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct skb_shared_info *sinfo = skb_shinfo(skb); struct airoha_gdm_port *port = netdev_priv(dev); - u32 msg0 = 0, msg1, len = skb_headlen(skb); - int i, qid = skb_get_queue_mapping(skb); + u32 msg0, msg1, len = skb_headlen(skb); struct airoha_qdma *qdma = port->qdma; u32 nr_frags = 1 + sinfo->nr_frags; struct netdev_queue *txq; struct airoha_queue *q; void *data = skb->data; + int i, qid; u16 index; u8 fport; + qid = skb_get_queue_mapping(skb) % ARRAY_SIZE(qdma->q_tx); + msg0 = FIELD_PREP(QDMA_ETH_TXMSG_CHAN_MASK, + qid / AIROHA_NUM_QOS_QUEUES) | + FIELD_PREP(QDMA_ETH_TXMSG_QUEUE_MASK, + qid % AIROHA_NUM_QOS_QUEUES); if (skb->ip_summed == CHECKSUM_PARTIAL) msg0 |= FIELD_PREP(QDMA_ETH_TXMSG_TCO_MASK, 1) | FIELD_PREP(QDMA_ETH_TXMSG_UCO_MASK, 1) | @@ -2597,13 +2742,399 @@ airoha_ethtool_get_rmon_stats(struct net_device *dev, } while (u64_stats_fetch_retry(&port->stats.syncp, start)); } +static int airoha_qdma_set_chan_tx_sched(struct airoha_gdm_port *port, + int channel, enum tx_sched_mode mode, + const u16 *weights, u8 n_weights) +{ + int i; + + for (i = 0; i < AIROHA_NUM_TX_RING; i++) + airoha_qdma_clear(port->qdma, REG_QUEUE_CLOSE_CFG(channel), + TXQ_DISABLE_CHAN_QUEUE_MASK(channel, i)); + + for (i = 0; i < n_weights; i++) { + u32 status; + int err; + + airoha_qdma_wr(port->qdma, REG_TXWRR_WEIGHT_CFG, + TWRR_RW_CMD_MASK | + FIELD_PREP(TWRR_CHAN_IDX_MASK, channel) | + FIELD_PREP(TWRR_QUEUE_IDX_MASK, i) | + FIELD_PREP(TWRR_VALUE_MASK, weights[i])); + err = read_poll_timeout(airoha_qdma_rr, status, + status & TWRR_RW_CMD_DONE, + USEC_PER_MSEC, 10 * USEC_PER_MSEC, + true, port->qdma, + REG_TXWRR_WEIGHT_CFG); + if (err) + return err; + } + + airoha_qdma_rmw(port->qdma, REG_CHAN_QOS_MODE(channel >> 3), + CHAN_QOS_MODE_MASK(channel), + mode << __ffs(CHAN_QOS_MODE_MASK(channel))); + + return 0; +} + +static int airoha_qdma_set_tx_prio_sched(struct airoha_gdm_port *port, + int channel) +{ + static const u16 w[AIROHA_NUM_QOS_QUEUES] = {}; + + return airoha_qdma_set_chan_tx_sched(port, channel, TC_SCH_SP, w, + ARRAY_SIZE(w)); +} + +static int airoha_qdma_set_tx_ets_sched(struct airoha_gdm_port *port, + int channel, + struct tc_ets_qopt_offload *opt) +{ + struct tc_ets_qopt_offload_replace_params *p = &opt->replace_params; + enum tx_sched_mode mode = TC_SCH_SP; + u16 w[AIROHA_NUM_QOS_QUEUES] = {}; + int i, nstrict = 0, nwrr, qidx; + + if (p->bands > AIROHA_NUM_QOS_QUEUES) + return -EINVAL; + + for (i = 0; i < p->bands; i++) { + if (!p->quanta[i]) + nstrict++; + } + + /* this configuration is not supported by the hw */ + if (nstrict == AIROHA_NUM_QOS_QUEUES - 1) + return -EINVAL; + + /* EN7581 SoC supports fixed QoS band priority where WRR queues have + * lowest priorities with respect to SP ones. + * e.g: WRR0, WRR1, .., WRRm, SP0, SP1, .., SPn + */ + nwrr = p->bands - nstrict; + qidx = nstrict && nwrr ? nstrict : 0; + for (i = 1; i <= p->bands; i++) { + if (p->priomap[i % AIROHA_NUM_QOS_QUEUES] != qidx) + return -EINVAL; + + qidx = i == nwrr ? 0 : qidx + 1; + } + + for (i = 0; i < nwrr; i++) + w[i] = p->weights[nstrict + i]; + + if (!nstrict) + mode = TC_SCH_WRR8; + else if (nstrict < AIROHA_NUM_QOS_QUEUES - 1) + mode = nstrict + 1; + + return airoha_qdma_set_chan_tx_sched(port, channel, mode, w, + ARRAY_SIZE(w)); +} + +static int airoha_qdma_get_tx_ets_stats(struct airoha_gdm_port *port, + int channel, + struct tc_ets_qopt_offload *opt) +{ + u64 cpu_tx_packets = airoha_qdma_rr(port->qdma, + REG_CNTR_VAL(channel << 1)); + u64 fwd_tx_packets = airoha_qdma_rr(port->qdma, + REG_CNTR_VAL((channel << 1) + 1)); + u64 tx_packets = (cpu_tx_packets - port->cpu_tx_packets) + + (fwd_tx_packets - port->fwd_tx_packets); + _bstats_update(opt->stats.bstats, 0, tx_packets); + + port->cpu_tx_packets = cpu_tx_packets; + port->fwd_tx_packets = fwd_tx_packets; + + return 0; +} + +static int airoha_tc_setup_qdisc_ets(struct airoha_gdm_port *port, + struct tc_ets_qopt_offload *opt) +{ + int channel; + + if (opt->parent == TC_H_ROOT) + return -EINVAL; + + channel = TC_H_MAJ(opt->handle) >> 16; + channel = channel % AIROHA_NUM_QOS_CHANNELS; + + switch (opt->command) { + case TC_ETS_REPLACE: + return airoha_qdma_set_tx_ets_sched(port, channel, opt); + case TC_ETS_DESTROY: + /* PRIO is default qdisc scheduler */ + return airoha_qdma_set_tx_prio_sched(port, channel); + case TC_ETS_STATS: + return airoha_qdma_get_tx_ets_stats(port, channel, opt); + default: + return -EOPNOTSUPP; + } +} + +static int airoha_qdma_get_trtcm_param(struct airoha_qdma *qdma, int channel, + u32 addr, enum trtcm_param_type param, + enum trtcm_mode_type mode, + u32 *val_low, u32 *val_high) +{ + u32 idx = QDMA_METER_IDX(channel), group = QDMA_METER_GROUP(channel); + u32 val, config = FIELD_PREP(TRTCM_PARAM_TYPE_MASK, param) | + FIELD_PREP(TRTCM_METER_GROUP_MASK, group) | + FIELD_PREP(TRTCM_PARAM_INDEX_MASK, idx) | + FIELD_PREP(TRTCM_PARAM_RATE_TYPE_MASK, mode); + + airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config); + if (read_poll_timeout(airoha_qdma_rr, val, + val & TRTCM_PARAM_RW_DONE_MASK, + USEC_PER_MSEC, 10 * USEC_PER_MSEC, true, + qdma, REG_TRTCM_CFG_PARAM(addr))) + return -ETIMEDOUT; + + *val_low = airoha_qdma_rr(qdma, REG_TRTCM_DATA_LOW(addr)); + if (val_high) + *val_high = airoha_qdma_rr(qdma, REG_TRTCM_DATA_HIGH(addr)); + + return 0; +} + +static int airoha_qdma_set_trtcm_param(struct airoha_qdma *qdma, int channel, + u32 addr, enum trtcm_param_type param, + enum trtcm_mode_type mode, u32 val) +{ + u32 idx = QDMA_METER_IDX(channel), group = QDMA_METER_GROUP(channel); + u32 config = TRTCM_PARAM_RW_MASK | + FIELD_PREP(TRTCM_PARAM_TYPE_MASK, param) | + FIELD_PREP(TRTCM_METER_GROUP_MASK, group) | + FIELD_PREP(TRTCM_PARAM_INDEX_MASK, idx) | + FIELD_PREP(TRTCM_PARAM_RATE_TYPE_MASK, mode); + + airoha_qdma_wr(qdma, REG_TRTCM_DATA_LOW(addr), val); + airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config); + + return read_poll_timeout(airoha_qdma_rr, val, + val & TRTCM_PARAM_RW_DONE_MASK, + USEC_PER_MSEC, 10 * USEC_PER_MSEC, true, + qdma, REG_TRTCM_CFG_PARAM(addr)); +} + +static int airoha_qdma_set_trtcm_config(struct airoha_qdma *qdma, int channel, + u32 addr, enum trtcm_mode_type mode, + bool enable, u32 enable_mask) +{ + u32 val; + + if (airoha_qdma_get_trtcm_param(qdma, channel, addr, TRTCM_MISC_MODE, + mode, &val, NULL)) + return -EINVAL; + + val = enable ? val | enable_mask : val & ~enable_mask; + + return airoha_qdma_set_trtcm_param(qdma, channel, addr, TRTCM_MISC_MODE, + mode, val); +} + +static int airoha_qdma_set_trtcm_token_bucket(struct airoha_qdma *qdma, + int channel, u32 addr, + enum trtcm_mode_type mode, + u32 rate_val, u32 bucket_size) +{ + u32 val, config, tick, unit, rate, rate_frac; + int err; + + if (airoha_qdma_get_trtcm_param(qdma, channel, addr, TRTCM_MISC_MODE, + mode, &config, NULL)) + return -EINVAL; + + val = airoha_qdma_rr(qdma, addr); + tick = FIELD_GET(INGRESS_FAST_TICK_MASK, val); + if (config & TRTCM_TICK_SEL) + tick *= FIELD_GET(INGRESS_SLOW_TICK_RATIO_MASK, val); + if (!tick) + return -EINVAL; + + unit = (config & TRTCM_PKT_MODE) ? 1000000 / tick : 8000 / tick; + if (!unit) + return -EINVAL; + + rate = rate_val / unit; + rate_frac = rate_val % unit; + rate_frac = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate_frac) / unit; + rate = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate) | + FIELD_PREP(TRTCM_TOKEN_RATE_FRACTION_MASK, rate_frac); + + err = airoha_qdma_set_trtcm_param(qdma, channel, addr, + TRTCM_TOKEN_RATE_MODE, mode, rate); + if (err) + return err; + + val = max_t(u32, bucket_size, MIN_TOKEN_SIZE); + val = min_t(u32, __fls(val), MAX_TOKEN_SIZE_OFFSET); + + return airoha_qdma_set_trtcm_param(qdma, channel, addr, + TRTCM_BUCKETSIZE_SHIFT_MODE, + mode, val); +} + +static int airoha_qdma_set_tx_rate_limit(struct airoha_gdm_port *port, + int channel, u32 rate, + u32 bucket_size) +{ + int i, err; + + for (i = 0; i <= TRTCM_PEAK_MODE; i++) { + err = airoha_qdma_set_trtcm_config(port->qdma, channel, + REG_EGRESS_TRTCM_CFG, i, + !!rate, TRTCM_METER_MODE); + if (err) + return err; + + err = airoha_qdma_set_trtcm_token_bucket(port->qdma, channel, + REG_EGRESS_TRTCM_CFG, + i, rate, bucket_size); + if (err) + return err; + } + + return 0; +} + +static int airoha_tc_htb_alloc_leaf_queue(struct airoha_gdm_port *port, + struct tc_htb_qopt_offload *opt) +{ + u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS; + u32 rate = div_u64(opt->rate, 1000) << 3; /* kbps */ + struct net_device *dev = port->dev; + int num_tx_queues = dev->real_num_tx_queues; + int err; + + if (opt->parent_classid != TC_HTB_CLASSID_ROOT) { + NL_SET_ERR_MSG_MOD(opt->extack, "invalid parent classid"); + return -EINVAL; + } + + err = airoha_qdma_set_tx_rate_limit(port, channel, rate, opt->quantum); + if (err) { + NL_SET_ERR_MSG_MOD(opt->extack, + "failed configuring htb offload"); + return err; + } + + if (opt->command == TC_HTB_NODE_MODIFY) + return 0; + + err = netif_set_real_num_tx_queues(dev, num_tx_queues + 1); + if (err) { + airoha_qdma_set_tx_rate_limit(port, channel, 0, opt->quantum); + NL_SET_ERR_MSG_MOD(opt->extack, + "failed setting real_num_tx_queues"); + return err; + } + + set_bit(channel, port->qos_sq_bmap); + opt->qid = AIROHA_NUM_TX_RING + channel; + + return 0; +} + +static void airoha_tc_remove_htb_queue(struct airoha_gdm_port *port, int queue) +{ + struct net_device *dev = port->dev; + + netif_set_real_num_tx_queues(dev, dev->real_num_tx_queues - 1); + airoha_qdma_set_tx_rate_limit(port, queue + 1, 0, 0); + clear_bit(queue, port->qos_sq_bmap); +} + +static int airoha_tc_htb_delete_leaf_queue(struct airoha_gdm_port *port, + struct tc_htb_qopt_offload *opt) +{ + u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS; + + if (!test_bit(channel, port->qos_sq_bmap)) { + NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id"); + return -EINVAL; + } + + airoha_tc_remove_htb_queue(port, channel); + + return 0; +} + +static int airoha_tc_htb_destroy(struct airoha_gdm_port *port) +{ + int q; + + for_each_set_bit(q, port->qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS) + airoha_tc_remove_htb_queue(port, q); + + return 0; +} + +static int airoha_tc_get_htb_get_leaf_queue(struct airoha_gdm_port *port, + struct tc_htb_qopt_offload *opt) +{ + u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS; + + if (!test_bit(channel, port->qos_sq_bmap)) { + NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id"); + return -EINVAL; + } + + opt->qid = channel; + + return 0; +} + +static int airoha_tc_setup_qdisc_htb(struct airoha_gdm_port *port, + struct tc_htb_qopt_offload *opt) +{ + switch (opt->command) { + case TC_HTB_CREATE: + break; + case TC_HTB_DESTROY: + return airoha_tc_htb_destroy(port); + case TC_HTB_NODE_MODIFY: + case TC_HTB_LEAF_ALLOC_QUEUE: + return airoha_tc_htb_alloc_leaf_queue(port, opt); + case TC_HTB_LEAF_DEL: + case TC_HTB_LEAF_DEL_LAST: + case TC_HTB_LEAF_DEL_LAST_FORCE: + return airoha_tc_htb_delete_leaf_queue(port, opt); + case TC_HTB_LEAF_QUERY_QUEUE: + return airoha_tc_get_htb_get_leaf_queue(port, opt); + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int airoha_dev_tc_setup(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct airoha_gdm_port *port = netdev_priv(dev); + + switch (type) { + case TC_SETUP_QDISC_ETS: + return airoha_tc_setup_qdisc_ets(port, type_data); + case TC_SETUP_QDISC_HTB: + return airoha_tc_setup_qdisc_htb(port, type_data); + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops airoha_netdev_ops = { .ndo_init = airoha_dev_init, .ndo_open = airoha_dev_open, .ndo_stop = airoha_dev_stop, + .ndo_select_queue = airoha_dev_select_queue, .ndo_start_xmit = airoha_dev_xmit, .ndo_get_stats64 = airoha_dev_get_stats64, .ndo_set_mac_address = airoha_dev_set_macaddr, + .ndo_setup_tc = airoha_dev_tc_setup, }; static const struct ethtool_ops airoha_ethtool_ops = { @@ -2640,7 +3171,8 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) } dev = devm_alloc_etherdev_mqs(eth->dev, sizeof(*port), - AIROHA_NUM_TX_RING, AIROHA_NUM_RX_RING); + AIROHA_NUM_NETDEV_TX_RINGS, + AIROHA_NUM_RX_RING); if (!dev) { dev_err(eth->dev, "alloc_etherdev failed\n"); return -ENOMEM; @@ -2653,12 +3185,18 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) dev->watchdog_timeo = 5 * HZ; dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO6 | NETIF_F_IPV6_CSUM | - NETIF_F_SG | NETIF_F_TSO; + NETIF_F_SG | NETIF_F_TSO | + NETIF_F_HW_TC; dev->features |= dev->hw_features; dev->dev.of_node = np; dev->irq = qdma->irq; SET_NETDEV_DEV(dev, eth->dev); + /* reserve hw queues for HTB offloading */ + err = netif_set_real_num_tx_queues(dev, AIROHA_NUM_TX_RING); + if (err) + return err; + err = of_get_ethdev_address(np, dev); if (err) { if (err == -EPROBE_DEFER) @@ -2738,7 +3276,7 @@ static int airoha_probe(struct platform_device *pdev) err = airoha_hw_init(pdev, eth); if (err) - goto error; + goto error_hw_cleanup; for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) airoha_qdma_start_napi(ð->qdma[i]); @@ -2753,13 +3291,16 @@ static int airoha_probe(struct platform_device *pdev) err = airoha_alloc_gdm_port(eth, np); if (err) { of_node_put(np); - goto error; + goto error_napi_stop; } } return 0; -error: +error_napi_stop: + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + airoha_qdma_stop_napi(ð->qdma[i]); +error_hw_cleanup: for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) airoha_hw_cleanup(ð->qdma[i]); @@ -2780,8 +3321,10 @@ static void airoha_remove(struct platform_device *pdev) struct airoha_eth *eth = platform_get_drvdata(pdev); int i; - for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) { + airoha_qdma_stop_napi(ð->qdma[i]); airoha_hw_cleanup(ð->qdma[i]); + } for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index be3d0876c521..568bbe5f83f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -17,7 +17,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ fs_counters.o fs_ft_pool.o rl.o lag/debugfs.o lag/lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o diag/reporter_vnic.o \ - fw_reset.o qos.o lib/tout.o lib/aso.o wc.o + fw_reset.o qos.o lib/tout.o lib/aso.o wc.o fs_pool.o # # Netdev basic @@ -60,6 +60,7 @@ mlx5_core-$(CONFIG_MLX5_CLS_ACT) += en/tc/act/act.o en/tc/act/drop.o en/tc/a ifneq ($(CONFIG_MLX5_TC_CT),) mlx5_core-y += en/tc_ct.o en/tc/ct_fs_dmfs.o mlx5_core-$(CONFIG_MLX5_SW_STEERING) += en/tc/ct_fs_smfs.o + mlx5_core-$(CONFIG_MLX5_HW_STEERING) += en/tc/ct_fs_hmfs.o endif mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += en/tc/sample.o @@ -123,6 +124,7 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/sws/dr_domain.o \ steering/sws/dr_ste_v0.o \ steering/sws/dr_ste_v1.o \ steering/sws/dr_ste_v2.o \ + steering/sws/dr_ste_v3.o \ steering/sws/dr_cmd.o \ steering/sws/dr_fw.o \ steering/sws/dr_action.o \ @@ -150,8 +152,9 @@ mlx5_core-$(CONFIG_MLX5_HW_STEERING) += steering/hws/cmd.o \ steering/hws/bwc.o \ steering/hws/debug.o \ steering/hws/vport.o \ - steering/hws/bwc_complex.o - + steering/hws/bwc_complex.o \ + steering/hws/fs_hws_pools.o \ + steering/hws/fs_hws.o # # SF device diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 6bd8a18e3af3..e733b81e18a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1013,6 +1013,7 @@ static void cmd_work_handler(struct work_struct *work) complete(&ent->done); } up(&cmd->vars.sem); + complete(&ent->slotted); return; } } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h index 9aed29fa4900..d6e736c1fb24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h @@ -292,7 +292,7 @@ TRACE_EVENT(mlx5_fs_add_rule, if (rule->dest_attr.type & MLX5_FLOW_DESTINATION_TYPE_COUNTER) __entry->counter_id = - rule->dest_attr.counter_id; + mlx5_fc_id(rule->dest_attr.counter); ), TP_printk("rule=%p fte=%p index=%u sw_action=<%s> [dst] %s\n", __entry->rule, __entry->fte, __entry->index, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h index 62b3f7ff5562..e5b30801314b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h @@ -48,4 +48,14 @@ mlx5_ct_fs_smfs_ops_get(void) } #endif /* IS_ENABLED(CONFIG_MLX5_SW_STEERING) */ +#if IS_ENABLED(CONFIG_MLX5_HW_STEERING) +struct mlx5_ct_fs_ops *mlx5_ct_fs_hmfs_ops_get(void); +#else +static inline struct mlx5_ct_fs_ops * +mlx5_ct_fs_hmfs_ops_get(void) +{ + return NULL; +} +#endif /* IS_ENABLED(CONFIG_MLX5_SW_STEERING) */ + #endif /* __MLX5_EN_TC_CT_FS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c new file mode 100644 index 000000000000..a4263137fef5 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. */ + +#include "en_tc.h" +#include "en/tc_ct.h" +#include "en/tc_priv.h" +#include "en/tc/ct_fs.h" +#include "fs_core.h" +#include "steering/hws/fs_hws_pools.h" +#include "steering/hws/mlx5hws.h" +#include "steering/hws/table.h" + +struct mlx5_ct_fs_hmfs_matcher { + struct mlx5hws_bwc_matcher *hws_bwc_matcher; + refcount_t ref; +}; + +/* We need {ipv4, ipv6} x {tcp, udp, gre} matchers. */ +#define NUM_MATCHERS (2 * 3) + +struct mlx5_ct_fs_hmfs { + struct mlx5hws_table *ct_tbl; + struct mlx5hws_table *ct_nat_tbl; + struct mlx5_flow_table *ct_nat; + struct mlx5hws_action *fwd_action; + struct mlx5hws_action *last_action; + struct mlx5hws_context *ctx; + struct mutex lock; /* Guards matchers */ + struct mlx5_ct_fs_hmfs_matcher matchers[NUM_MATCHERS]; + struct mlx5_ct_fs_hmfs_matcher matchers_nat[NUM_MATCHERS]; +}; + +struct mlx5_ct_fs_hmfs_rule { + struct mlx5_ct_fs_rule fs_rule; + struct mlx5hws_bwc_rule *hws_bwc_rule; + struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher; + struct mlx5_fc *counter; +}; + +static u32 get_matcher_idx(bool ipv4, bool tcp, bool gre) +{ + return ipv4 * 3 + tcp * 2 + gre; +} + +static int mlx5_ct_fs_hmfs_init(struct mlx5_ct_fs *fs, struct mlx5_flow_table *ct, + struct mlx5_flow_table *ct_nat, struct mlx5_flow_table *post_ct) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5hws_table *ct_tbl, *ct_nat_tbl, *post_ct_tbl; + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + + ct_tbl = ct->fs_hws_table.hws_table; + ct_nat_tbl = ct_nat->fs_hws_table.hws_table; + post_ct_tbl = post_ct->fs_hws_table.hws_table; + fs_hmfs->ct_nat = ct_nat; + + if (!ct_tbl || !ct_nat_tbl || !post_ct_tbl) { + netdev_warn(fs->netdev, "ct_fs_hmfs: failed to init, missing backing hws tables"); + return -EOPNOTSUPP; + } + + netdev_dbg(fs->netdev, "using hmfs steering"); + + fs_hmfs->ct_tbl = ct_tbl; + fs_hmfs->ct_nat_tbl = ct_nat_tbl; + fs_hmfs->ctx = ct_tbl->ctx; + mutex_init(&fs_hmfs->lock); + + fs_hmfs->fwd_action = mlx5hws_action_create_dest_table(ct_tbl->ctx, post_ct_tbl, flags); + if (!fs_hmfs->fwd_action) { + netdev_warn(fs->netdev, "ct_fs_hmfs: failed to create fwd action\n"); + return -EINVAL; + } + fs_hmfs->last_action = mlx5hws_action_create_last(ct_tbl->ctx, flags); + if (!fs_hmfs->last_action) { + netdev_warn(fs->netdev, "ct_fs_hmfs: failed to create last action\n"); + mlx5hws_action_destroy(fs_hmfs->fwd_action); + return -EINVAL; + } + + return 0; +} + +static void mlx5_ct_fs_hmfs_destroy(struct mlx5_ct_fs *fs) +{ + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + + mlx5hws_action_destroy(fs_hmfs->last_action); + mlx5hws_action_destroy(fs_hmfs->fwd_action); +} + +static struct mlx5hws_bwc_matcher * +mlx5_ct_fs_hmfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5hws_table *tbl, + struct mlx5_flow_spec *spec, bool ipv4, bool tcp, bool gre) +{ + u8 match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2 | MLX5_MATCH_OUTER_HEADERS; + struct mlx5hws_match_parameters mask = { + .match_buf = spec->match_criteria, + .match_sz = sizeof(spec->match_criteria), + }; + u32 priority = get_matcher_idx(ipv4, tcp, gre); /* Static priority based on params. */ + struct mlx5hws_bwc_matcher *hws_bwc_matcher; + + hws_bwc_matcher = mlx5hws_bwc_matcher_create(tbl, priority, match_criteria_enable, &mask); + if (!hws_bwc_matcher) + return ERR_PTR(-EINVAL); + + return hws_bwc_matcher; +} + +static struct mlx5_ct_fs_hmfs_matcher * +mlx5_ct_fs_hmfs_matcher_get(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, + bool nat, bool ipv4, bool tcp, bool gre) +{ + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + u32 matcher_idx = get_matcher_idx(ipv4, tcp, gre); + struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher; + struct mlx5hws_bwc_matcher *hws_bwc_matcher; + struct mlx5hws_table *tbl; + + hmfs_matcher = nat ? + (fs_hmfs->matchers_nat + matcher_idx) : + (fs_hmfs->matchers + matcher_idx); + + if (refcount_inc_not_zero(&hmfs_matcher->ref)) + return hmfs_matcher; + + mutex_lock(&fs_hmfs->lock); + + /* Retry with lock, as the matcher might be already created by another cpu. */ + if (refcount_inc_not_zero(&hmfs_matcher->ref)) + goto out_unlock; + + tbl = nat ? fs_hmfs->ct_nat_tbl : fs_hmfs->ct_tbl; + + hws_bwc_matcher = mlx5_ct_fs_hmfs_matcher_create(fs, tbl, spec, ipv4, tcp, gre); + if (IS_ERR(hws_bwc_matcher)) { + netdev_warn(fs->netdev, + "ct_fs_hmfs: failed to create bwc matcher (nat %d, ipv4 %d, tcp %d, gre %d), err: %ld\n", + nat, ipv4, tcp, gre, PTR_ERR(hws_bwc_matcher)); + + hmfs_matcher = ERR_CAST(hws_bwc_matcher); + goto out_unlock; + } + + hmfs_matcher->hws_bwc_matcher = hws_bwc_matcher; + refcount_set(&hmfs_matcher->ref, 1); + +out_unlock: + mutex_unlock(&fs_hmfs->lock); + return hmfs_matcher; +} + +static void +mlx5_ct_fs_hmfs_matcher_put(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher) +{ + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + + if (!refcount_dec_and_mutex_lock(&hmfs_matcher->ref, &fs_hmfs->lock)) + return; + + mlx5hws_bwc_matcher_destroy(hmfs_matcher->hws_bwc_matcher); + mutex_unlock(&fs_hmfs->lock); +} + +#define NUM_CT_HMFS_RULES 4 + +static void mlx5_ct_fs_hmfs_fill_rule_actions(struct mlx5_ct_fs_hmfs *fs_hmfs, + struct mlx5_flow_attr *attr, + struct mlx5hws_rule_action *rule_actions) +{ + struct mlx5_fs_hws_action *mh_action = &attr->modify_hdr->fs_hws_action; + + memset(rule_actions, 0, NUM_CT_HMFS_RULES * sizeof(*rule_actions)); + rule_actions[0].action = mlx5_fc_get_hws_action(fs_hmfs->ctx, attr->counter); + /* Modify header is special, it may require extra arguments outside the action itself. */ + if (mh_action->mh_data) { + rule_actions[1].modify_header.offset = mh_action->mh_data->offset; + rule_actions[1].modify_header.data = mh_action->mh_data->data; + } + rule_actions[1].action = mh_action->hws_action; + rule_actions[2].action = fs_hmfs->fwd_action; + rule_actions[3].action = fs_hmfs->last_action; +} + +static struct mlx5_ct_fs_rule * +mlx5_ct_fs_hmfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr, struct flow_rule *flow_rule) +{ + struct mlx5hws_rule_action rule_actions[NUM_CT_HMFS_RULES]; + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + struct mlx5hws_match_parameters match_params = { + .match_buf = spec->match_value, + .match_sz = ARRAY_SIZE(spec->match_value), + }; + struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher; + struct mlx5_ct_fs_hmfs_rule *hmfs_rule; + bool nat, tcp, ipv4, gre; + int err; + + if (!mlx5e_tc_ct_is_valid_flow_rule(fs->netdev, flow_rule)) + return ERR_PTR(-EOPNOTSUPP); + + hmfs_rule = kzalloc(sizeof(*hmfs_rule), GFP_KERNEL); + if (!hmfs_rule) + return ERR_PTR(-ENOMEM); + + nat = (attr->ft == fs_hmfs->ct_nat); + ipv4 = mlx5e_tc_get_ip_version(spec, true) == 4; + tcp = MLX5_GET(fte_match_param, spec->match_value, + outer_headers.ip_protocol) == IPPROTO_TCP; + gre = MLX5_GET(fte_match_param, spec->match_value, + outer_headers.ip_protocol) == IPPROTO_GRE; + + hmfs_matcher = mlx5_ct_fs_hmfs_matcher_get(fs, spec, nat, ipv4, tcp, gre); + if (IS_ERR(hmfs_matcher)) { + err = PTR_ERR(hmfs_matcher); + goto err_free_rule; + } + hmfs_rule->hmfs_matcher = hmfs_matcher; + + mlx5_ct_fs_hmfs_fill_rule_actions(fs_hmfs, attr, rule_actions); + hmfs_rule->counter = attr->counter; + + hmfs_rule->hws_bwc_rule = + mlx5hws_bwc_rule_create(hmfs_matcher->hws_bwc_matcher, &match_params, + spec->flow_context.flow_source, rule_actions); + if (!hmfs_rule->hws_bwc_rule) { + err = -EINVAL; + goto err_put_matcher; + } + + return &hmfs_rule->fs_rule; + +err_put_matcher: + mlx5_fc_put_hws_action(hmfs_rule->counter); + mlx5_ct_fs_hmfs_matcher_put(fs, hmfs_matcher); +err_free_rule: + kfree(hmfs_rule); + return ERR_PTR(err); +} + +static void mlx5_ct_fs_hmfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule) +{ + struct mlx5_ct_fs_hmfs_rule *hmfs_rule = container_of(fs_rule, + struct mlx5_ct_fs_hmfs_rule, + fs_rule); + mlx5hws_bwc_rule_destroy(hmfs_rule->hws_bwc_rule); + mlx5_fc_put_hws_action(hmfs_rule->counter); + mlx5_ct_fs_hmfs_matcher_put(fs, hmfs_rule->hmfs_matcher); + kfree(hmfs_rule); +} + +static int mlx5_ct_fs_hmfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule, + struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) +{ + struct mlx5_ct_fs_hmfs_rule *hmfs_rule = container_of(fs_rule, + struct mlx5_ct_fs_hmfs_rule, + fs_rule); + struct mlx5hws_rule_action rule_actions[NUM_CT_HMFS_RULES]; + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + int err; + + mlx5_ct_fs_hmfs_fill_rule_actions(fs_hmfs, attr, rule_actions); + + err = mlx5hws_bwc_rule_action_update(hmfs_rule->hws_bwc_rule, rule_actions); + if (err) { + mlx5_fc_put_hws_action(attr->counter); + return err; + } + + mlx5_fc_put_hws_action(hmfs_rule->counter); + hmfs_rule->counter = attr->counter; + + return 0; +} + +static struct mlx5_ct_fs_ops hmfs_ops = { + .ct_rule_add = mlx5_ct_fs_hmfs_ct_rule_add, + .ct_rule_del = mlx5_ct_fs_hmfs_ct_rule_del, + .ct_rule_update = mlx5_ct_fs_hmfs_ct_rule_update, + + .init = mlx5_ct_fs_hmfs_init, + .destroy = mlx5_ct_fs_hmfs_destroy, + + .priv_size = sizeof(struct mlx5_ct_fs_hmfs), +}; + +struct mlx5_ct_fs_ops *mlx5_ct_fs_hmfs_ops_get(void) +{ + return &hmfs_ops; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c index 45737d039252..0c97c5899904 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c @@ -13,7 +13,6 @@ #define INIT_ERR_PREFIX "ct_fs_smfs init failed" #define ct_dbg(fmt, args...)\ netdev_dbg(fs->netdev, "ct_fs_smfs debug: " fmt "\n", ##args) -#define MLX5_CT_TCP_FLAGS_MASK cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16) struct mlx5_ct_fs_smfs_matcher { struct mlx5dr_matcher *dr_matcher; @@ -220,78 +219,6 @@ mlx5_ct_fs_smfs_destroy(struct mlx5_ct_fs *fs) mlx5_smfs_action_destroy(fs_smfs->fwd_action); } -static inline bool -mlx5_tc_ct_valid_used_dissector_keys(const u64 used_keys) -{ -#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name) - const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | - DISS_BIT(META); - const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | - DISS_BIT(PORTS) | DISS_BIT(TCP); - const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | - DISS_BIT(PORTS) | DISS_BIT(TCP); - const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | - DISS_BIT(PORTS); - const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | - DISS_BIT(PORTS); - const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS); - const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS); - - return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp || - used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre); -} - -static bool -mlx5_ct_fs_smfs_ct_validate_flow_rule(struct mlx5_ct_fs *fs, struct flow_rule *flow_rule) -{ - struct flow_match_ipv4_addrs ipv4_addrs; - struct flow_match_ipv6_addrs ipv6_addrs; - struct flow_match_control control; - struct flow_match_basic basic; - struct flow_match_ports ports; - struct flow_match_tcp tcp; - - if (!mlx5_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) { - ct_dbg("rule uses unexpected dissectors (0x%016llx)", - flow_rule->match.dissector->used_keys); - return false; - } - - flow_rule_match_basic(flow_rule, &basic); - flow_rule_match_control(flow_rule, &control); - flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs); - flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs); - if (basic.key->ip_proto != IPPROTO_GRE) - flow_rule_match_ports(flow_rule, &ports); - if (basic.key->ip_proto == IPPROTO_TCP) - flow_rule_match_tcp(flow_rule, &tcp); - - if (basic.mask->n_proto != htons(0xFFFF) || - (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) || - basic.mask->ip_proto != 0xFF || - (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP && - basic.key->ip_proto != IPPROTO_GRE)) { - ct_dbg("rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)", - ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto), - basic.key->ip_proto, basic.mask->ip_proto); - return false; - } - - if (basic.key->ip_proto != IPPROTO_GRE && - (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) { - ct_dbg("rule uses ports match (src 0x%04x, dst 0x%04x)", - ports.mask->src, ports.mask->dst); - return false; - } - - if (basic.key->ip_proto == IPPROTO_TCP && tcp.mask->flags != MLX5_CT_TCP_FLAGS_MASK) { - ct_dbg("rule uses unexpected tcp match (flags 0x%02x)", tcp.mask->flags); - return false; - } - - return true; -} - static struct mlx5_ct_fs_rule * mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr, struct flow_rule *flow_rule) @@ -304,7 +231,7 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, int num_actions = 0, err; bool nat, tcp, ipv4, gre; - if (!mlx5_ct_fs_smfs_ct_validate_flow_rule(fs, flow_rule)) + if (!mlx5e_tc_ct_is_valid_flow_rule(fs->netdev, flow_rule)) return ERR_PTR(-EOPNOTSUPP); smfs_rule = kzalloc(sizeof(*smfs_rule), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index a84ebac2f011..a065e8fafb1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -2065,10 +2065,19 @@ mlx5_tc_ct_fs_init(struct mlx5_tc_ct_priv *ct_priv) struct mlx5_ct_fs_ops *fs_ops = mlx5_ct_fs_dmfs_ops_get(); int err; - if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB && - ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) { - ct_dbg("Using SMFS ct flow steering provider"); - fs_ops = mlx5_ct_fs_smfs_ops_get(); + if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB) { + if (ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_HMFS) { + ct_dbg("Using HMFS ct flow steering provider"); + fs_ops = mlx5_ct_fs_hmfs_ops_get(); + } else if (ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) { + ct_dbg("Using SMFS ct flow steering provider"); + fs_ops = mlx5_ct_fs_smfs_ops_get(); + } + + if (!fs_ops) { + ct_dbg("Requested flow steering mode is not enabled."); + return -EOPNOTSUPP; + } } ct_priv->fs = kzalloc(sizeof(*ct_priv->fs) + fs_ops->priv_size, GFP_KERNEL); @@ -2421,3 +2430,74 @@ out_inc_drop: atomic_inc(&ct_priv->debugfs.stats.rx_dropped); return false; } + +static bool mlx5e_tc_ct_valid_used_dissector_keys(const u64 used_keys) +{ +#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name) + const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | + DISS_BIT(META); + const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | + DISS_BIT(PORTS) | DISS_BIT(TCP); + const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | + DISS_BIT(PORTS) | DISS_BIT(TCP); + const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | + DISS_BIT(PORTS); + const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | + DISS_BIT(PORTS); + const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS); + const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS); + + return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp || + used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre); +} + +bool mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, struct flow_rule *flow_rule) +{ + struct flow_match_ipv4_addrs ipv4_addrs; + struct flow_match_ipv6_addrs ipv6_addrs; + struct flow_match_control control; + struct flow_match_basic basic; + struct flow_match_ports ports; + struct flow_match_tcp tcp; + + if (!mlx5e_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) { + netdev_dbg(dev, "ct_debug: rule uses unexpected dissectors (0x%016llx)", + flow_rule->match.dissector->used_keys); + return false; + } + + flow_rule_match_basic(flow_rule, &basic); + flow_rule_match_control(flow_rule, &control); + flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs); + flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs); + if (basic.key->ip_proto != IPPROTO_GRE) + flow_rule_match_ports(flow_rule, &ports); + if (basic.key->ip_proto == IPPROTO_TCP) + flow_rule_match_tcp(flow_rule, &tcp); + + if (basic.mask->n_proto != htons(0xFFFF) || + (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) || + basic.mask->ip_proto != 0xFF || + (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP && + basic.key->ip_proto != IPPROTO_GRE)) { + netdev_dbg(dev, "ct_debug: rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)", + ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto), + basic.key->ip_proto, basic.mask->ip_proto); + return false; + } + + if (basic.key->ip_proto != IPPROTO_GRE && + (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) { + netdev_dbg(dev, "ct_debug: rule uses ports match (src 0x%04x, dst 0x%04x)", + ports.mask->src, ports.mask->dst); + return false; + } + + if (basic.key->ip_proto == IPPROTO_TCP && tcp.mask->flags != MLX5_CT_TCP_FLAGS_MASK) { + netdev_dbg(dev, "ct_debug: rule uses unexpected tcp match (flags 0x%02x)", + tcp.mask->flags); + return false; + } + + return true; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index b66c5f98067f..5e9dbdd4a5e9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -128,6 +128,9 @@ bool mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv, struct sk_buff *skb, u8 zone_restore_id); +#define MLX5_CT_TCP_FLAGS_MASK cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16) +bool mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, struct flow_rule *flow_rule); + #else /* CONFIG_MLX5_TC_CT */ static inline struct mlx5_tc_ct_priv * @@ -202,5 +205,12 @@ mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv, return false; } +static inline bool +mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, + struct flow_rule *flow_rule) +{ + return false; +} + #endif /* !IS_ENABLED(CONFIG_MLX5_TC_CT) */ #endif /* __MLX5_EN_TC_CT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index ca92e518be76..501709ac310f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -94,25 +94,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) u32 esn, esn_msb; u8 overlap; - switch (x->xso.type) { - case XFRM_DEV_OFFLOAD_PACKET: - switch (x->xso.dir) { - case XFRM_DEV_OFFLOAD_IN: - esn = x->replay_esn->seq; - esn_msb = x->replay_esn->seq_hi; - break; - case XFRM_DEV_OFFLOAD_OUT: - esn = x->replay_esn->oseq; - esn_msb = x->replay_esn->oseq_hi; - break; - default: - WARN_ON(true); - return false; - } - break; - case XFRM_DEV_OFFLOAD_CRYPTO: - /* Already parsed by XFRM core */ + switch (x->xso.dir) { + case XFRM_DEV_OFFLOAD_IN: esn = x->replay_esn->seq; + esn_msb = x->replay_esn->seq_hi; + break; + case XFRM_DEV_OFFLOAD_OUT: + esn = x->replay_esn->oseq; + esn_msb = x->replay_esn->oseq_hi; break; default: WARN_ON(true); @@ -121,11 +110,15 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) overlap = sa_entry->esn_state.overlap; - if (esn >= x->replay_esn->replay_window) - seq_bottom = esn - x->replay_esn->replay_window + 1; + if (!x->replay_esn->replay_window) { + seq_bottom = esn; + } else { + if (esn >= x->replay_esn->replay_window) + seq_bottom = esn - x->replay_esn->replay_window + 1; - if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO) - esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom)); + if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO) + esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom)); + } if (sa_entry->esn_state.esn_msb) sa_entry->esn_state.esn = esn; @@ -724,6 +717,12 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x, /* check esn */ if (x->props.flags & XFRM_STATE_ESN) mlx5e_ipsec_update_esn_state(sa_entry); + else + /* According to RFC4303, section "3.3.3. Sequence Number Generation", + * the first packet sent using a given SA will contain a sequence + * number of 1. + */ + sa_entry->esn_state.esn = 1; mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &sa_entry->attrs); @@ -768,9 +767,12 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x, MLX5_IPSEC_RESCHED); if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && - x->props.mode == XFRM_MODE_TUNNEL) - xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id, - MLX5E_IPSEC_TUNNEL_SA); + x->props.mode == XFRM_MODE_TUNNEL) { + xa_lock_bh(&ipsec->sadb); + __xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id, + MLX5E_IPSEC_TUNNEL_SA); + xa_unlock_bh(&ipsec->sadb); + } out: x->xso.offload_handle = (unsigned long)sa_entry; @@ -797,7 +799,6 @@ err_xfrm: static void mlx5e_xfrm_del_state(struct xfrm_state *x) { struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x); - struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs; struct mlx5e_ipsec *ipsec = sa_entry->ipsec; struct mlx5e_ipsec_sa_entry *old; @@ -806,12 +807,6 @@ static void mlx5e_xfrm_del_state(struct xfrm_state *x) old = xa_erase_bh(&ipsec->sadb, sa_entry->ipsec_obj_id); WARN_ON(old != sa_entry); - - if (attrs->mode == XFRM_MODE_TUNNEL && - attrs->type == XFRM_DEV_OFFLOAD_PACKET) - /* Make sure that no ARP requests are running in parallel */ - flush_workqueue(ipsec->wq); - } static void mlx5e_xfrm_free_state(struct xfrm_state *x) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index e51b03d4c717..e7b64679f121 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -194,7 +194,7 @@ static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry, flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; flow_act.flags = FLOW_ACT_NO_APPEND; dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(flow_counter); + dest.counter = flow_counter; if (rx == ipsec->rx_esw) spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; @@ -223,7 +223,7 @@ static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry, } sa_entry->ipsec_rule.trailer.fc = flow_counter; - dest.counter_id = mlx5_fc_id(flow_counter); + dest.counter = flow_counter; MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 2); rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { @@ -275,7 +275,7 @@ static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; flow_act.flags = FLOW_ACT_NO_APPEND; dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(flow_counter); + dest.counter = flow_counter; if (rx == ipsec->rx_esw) spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; @@ -348,7 +348,7 @@ static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec, flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(flow_counter); + dest.counter = flow_counter; if (rx == ipsec->rx_esw) spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); @@ -686,7 +686,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, rx->ft.status = ft; dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[1].counter_id = mlx5_fc_id(rx->fc->cnt); + dest[1].counter = rx->fc->cnt; err = mlx5_ipsec_rx_status_create(ipsec, rx, dest); if (err) goto err_add; @@ -873,7 +873,7 @@ static int ipsec_counter_rule_tx(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW | MLX5_FLOW_CONTEXT_ACTION_COUNT; dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(tx->fc->cnt); + dest.counter = tx->fc->cnt; fte = mlx5_add_flow_rules(tx->ft.status, spec, &flow_act, &dest, 1); if (IS_ERR(fte)) { err = PTR_ERR(fte); @@ -1649,7 +1649,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[0].ft = rx->ft.status; dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[1].counter_id = mlx5_fc_id(counter); + dest[1].counter = counter; rule = mlx5_add_flow_rules(rx->ft.sa, spec, &flow_act, dest, 2); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -1718,23 +1718,21 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) goto err_alloc; } - if (attrs->family == AF_INET) - setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4); - else - setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); - setup_fte_no_frags(spec); setup_fte_upper_proto_match(spec, &attrs->upspec); switch (attrs->type) { case XFRM_DEV_OFFLOAD_CRYPTO: + if (attrs->family == AF_INET) + setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4); + else + setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); setup_fte_spi(spec, attrs->spi, false); setup_fte_esp(spec); setup_fte_reg_a(spec); break; case XFRM_DEV_OFFLOAD_PACKET: - if (attrs->reqid) - setup_fte_reg_c4(spec, attrs->reqid); + setup_fte_reg_c4(spec, attrs->reqid); err = setup_pkt_reformat(ipsec, attrs, &flow_act); if (err) goto err_pkt_reformat; @@ -1762,7 +1760,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) dest[0].ft = tx->ft.status; dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[1].counter_id = mlx5_fc_id(counter); + dest[1].counter = counter; rule = mlx5_add_flow_rules(tx->ft.sa, spec, &flow_act, dest, 2); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -1835,7 +1833,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[dstn].counter_id = mlx5_fc_id(tx->fc->drop); + dest[dstn].counter = tx->fc->drop; dstn++; break; default: @@ -1913,7 +1911,7 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) case XFRM_POLICY_BLOCK: flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[dstn].counter_id = mlx5_fc_id(rx->fc->drop); + dest[dstn].counter = rx->fc->drop; dstn++; break; default: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 53cfa39188cb..820debf3fbbf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -91,8 +91,9 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) EXPORT_SYMBOL_GPL(mlx5_ipsec_device_caps); static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, - struct mlx5_accel_esp_xfrm_attrs *attrs) + struct mlx5e_ipsec_sa_entry *sa_entry) { + struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs; void *aso_ctx; aso_ctx = MLX5_ADDR_OF(ipsec_obj, obj, ipsec_aso); @@ -120,8 +121,12 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, * active. */ MLX5_SET(ipsec_obj, obj, aso_return_reg, MLX5_IPSEC_ASO_REG_C_4_5); - if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) + if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) { MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_INC_SN); + if (!attrs->replay_esn.trigger) + MLX5_SET(ipsec_aso, aso_ctx, mode_parameter, + sa_entry->esn_state.esn); + } if (attrs->lft.hard_packet_limit != XFRM_INF) { MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt, @@ -175,7 +180,7 @@ static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry) res = &mdev->mlx5e_res.hw_objs; if (attrs->type == XFRM_DEV_OFFLOAD_PACKET) - mlx5e_ipsec_packet_setup(obj, res->pdn, attrs); + mlx5e_ipsec_packet_setup(obj, res->pdn, sa_entry); err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); if (!err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index cc9bcc420032..6ab02f3fc291 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -339,9 +339,13 @@ static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx, { struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs; + const struct macsec_tx_sc *tx_sc = &ctx->secy->tx_sc; struct mlx5_macsec_rule_attrs rule_attrs; union mlx5_macsec_rule *macsec_rule; + if (is_tx && tx_sc->encoding_sa != sa->assoc_num) + return 0; + rule_attrs.macsec_obj_id = sa->macsec_obj_id; rule_attrs.sci = sa->sci; rule_attrs.assoc_num = sa->assoc_num; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dd16d73000c3..a814b63ed97e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2087,7 +2087,7 @@ static struct mlx5e_xdpsq *mlx5e_open_xdpredirect_sq(struct mlx5e_channel *c, struct mlx5e_xdpsq *xdpsq; int err; - xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, c->cpu); + xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, cpu_to_node(c->cpu)); if (!xdpsq) return ERR_PTR(-ENOMEM); @@ -3946,6 +3946,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) } stats->rx_missed_errors = priv->stats.qcnt.rx_out_of_buffer; + stats->rx_dropped = PPORT_2863_GET(pstats, if_in_discards); stats->rx_length_errors = PPORT_802_3_GET(pstats, a_in_range_length_errors) + @@ -6542,8 +6543,23 @@ static void _mlx5e_remove(struct auxiliary_device *adev) mlx5_core_uplink_netdev_set(mdev, NULL); mlx5e_dcbnl_delete_app(priv); - unregister_netdev(priv->netdev); - _mlx5e_suspend(adev, false); + /* When unload driver, the netdev is in registered state + * if it's from legacy mode. If from switchdev mode, it + * is already unregistered before changing to NIC profile. + */ + if (priv->netdev->reg_state == NETREG_REGISTERED) { + unregister_netdev(priv->netdev); + _mlx5e_suspend(adev, false); + } else { + struct mlx5_core_dev *pos; + int i; + + if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) + mlx5_sd_for_each_dev(i, mdev, pos) + mlx5e_destroy_mdev_resources(pos); + else + _mlx5e_suspend(adev, true); + } /* Avoid cleanup if profile rollback failed. */ if (priv->profile) priv->profile->cleanup(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 554f9cb5b53f..fdff9fd8a89e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1509,6 +1509,21 @@ mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv) priv = netdev_priv(netdev); + /* This bit is set when using devlink to change eswitch mode from + * switchdev to legacy. As need to keep uplink netdev ifindex, we + * detach uplink representor profile and attach NIC profile only. + * The netdev will be unregistered later when unload NIC auxiliary + * driver for this case. + * We explicitly block devlink eswitch mode change if any IPSec rules + * offloaded, but can't block other cases, such as driver unload + * and devlink reload. We have to unregister netdev before profile + * change for those cases. This is to avoid resource leak because + * the offloaded rules don't have the chance to be unoffloaded before + * cleanup which is triggered by detach uplink representor profile. + */ + if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_SWITCH_LEGACY)) + unregister_netdev(netdev); + mlx5e_netdev_attach_nic_profile(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 6b3b1afe8312..9ba99609999f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1282,7 +1282,7 @@ mlx5e_add_offloaded_nic_rule(struct mlx5e_priv *priv, if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[dest_ix].counter_id = mlx5_fc_id(attr->counter); + dest[dest_ix].counter = attr->counter; dest_ix++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c index 6b4c9ffad95b..7dd1dc3f77c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c @@ -135,7 +135,7 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw, if (drop_counter) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - drop_ctr_dst.counter_id = mlx5_fc_id(drop_counter); + drop_ctr_dst.counter = drop_counter; dst = &drop_ctr_dst; dest_num++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c index 093ed86a0acd..1c37098e09ea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c @@ -260,7 +260,7 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw, if (counter) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - drop_ctr_dst.counter_id = mlx5_fc_id(counter); + drop_ctr_dst.counter = counter; dst = &drop_ctr_dst; dest_num++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index c5ea1d1d2b03..5f647358a05c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -570,7 +570,8 @@ mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge) static struct mlx5_flow_handle * mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char *addr, - struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, + struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_fc *counter, struct mlx5_esw_bridge *bridge, struct mlx5_eswitch *esw) { @@ -628,7 +629,7 @@ mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char dests[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dests[0].ft = bridge->egress_ft; dests[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dests[1].counter_id = counter_id; + dests[1].counter = counter; handle = mlx5_add_flow_rules(br_offloads->ingress_ft, rule_spec, &flow_act, dests, ARRAY_SIZE(dests)); @@ -639,17 +640,19 @@ mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char static struct mlx5_flow_handle * mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr, - struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, + struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_fc *counter, struct mlx5_esw_bridge *bridge) { - return mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id, + return mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter, bridge, bridge->br_offloads->esw); } static struct mlx5_flow_handle * mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, u16 esw_owner_vhca_id, const unsigned char *addr, - struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, + struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_fc *counter, struct mlx5_esw_bridge *bridge) { struct mlx5_devcom_comp_dev *devcom = bridge->br_offloads->esw->devcom, *pos; @@ -671,7 +674,7 @@ mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, u16 esw_owner_vhca_id, goto out; } - handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id, + handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter, bridge, peer_esw); out: @@ -1385,10 +1388,9 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_ow handle = peer ? mlx5_esw_bridge_ingress_flow_peer_create(vport_num, esw_owner_vhca_id, - addr, vlan, mlx5_fc_id(counter), - bridge) : + addr, vlan, counter, bridge) : mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, - mlx5_fc_id(counter), bridge); + counter, bridge); if (IS_ERR(handle)) { err = PTR_ERR(handle); esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d,peer=%d)\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 5a0047bdcb51..ed977ae75fab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -150,11 +150,11 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) unsigned long i; int err; - xa_for_each(&esw->offloads.vport_reps, i, rep) { - rpriv = rep->rep_data[REP_ETH].priv; - if (!rpriv || !rpriv->netdev) + mlx5_esw_for_each_rep(esw, i, rep) { + if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED) continue; + rpriv = rep->rep_data[REP_ETH].priv; rhashtable_walk_enter(&rpriv->tc_ht, &iter); rhashtable_walk_start(&iter); while ((flow = rhashtable_walk_next(&iter)) != NULL) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index a83d41121db6..8573d36785f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -714,6 +714,9 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw); MLX5_CAP_GEN_2((esw->dev), ec_vf_vport_base) +\ (last) - 1) +#define mlx5_esw_for_each_rep(esw, i, rep) \ + xa_for_each(&((esw)->offloads.vport_reps), i, rep) + struct mlx5_eswitch *__must_check mlx5_devlink_eswitch_get(struct devlink *devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d5b42b3a19fd..20cc01ceee8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -53,9 +53,6 @@ #include "lag/lag.h" #include "en/tc/post_meter.h" -#define mlx5_esw_for_each_rep(esw, i, rep) \ - xa_for_each(&((esw)->offloads.vport_reps), i, rep) - /* There are two match-all miss flows, one for unicast dst mac and * one for multicast. */ @@ -724,7 +721,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[i].counter_id = mlx5_fc_id(attr->counter); + dest[i].counter = attr->counter; i++; } @@ -3780,6 +3777,8 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, esw->eswitch_operation_in_progress = true; up_write(&esw->mode_lock); + if (mode == DEVLINK_ESWITCH_MODE_LEGACY) + esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY; mlx5_eswitch_disable_locked(esw); if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { if (mlx5_devlink_trap_get_num_active(esw->dev)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 676005854dad..ae20c061e0fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -217,7 +217,8 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, int err; if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && - underlay_qpn == 0) + underlay_qpn == 0 && + (ft->type != FS_FT_RDMA_RX && ft->type != FS_FT_RDMA_TX)) return 0; if (ft->type == FS_FT_FDB && @@ -718,7 +719,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, continue; MLX5_SET(flow_counter_list, in_dests, flow_counter_id, - dst->dest_attr.counter_id); + mlx5_fc_id(dst->dest_attr.counter)); in_dests += dst_cnt_size; list_size++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 2eabfcc247c6..22dc23d991d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -658,6 +658,7 @@ static void del_sw_hw_rule(struct fs_node *node) BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) | BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS); fte->act_dests.action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT; + mlx5_fc_local_destroy(rule->dest_attr.counter); goto out; } @@ -820,11 +821,17 @@ static int insert_fte(struct mlx5_flow_group *fg, struct fs_fte *fte) return index; fte->index = index + fg->start_index; +retry_insert: ret = rhashtable_insert_fast(&fg->ftes_hash, &fte->hash, rhash_fte); - if (ret) + if (ret) { + if (ret == -EBUSY) { + cond_resched(); + goto retry_insert; + } goto err_ida_remove; + } tree_add_node(&fte->node, &fg->node); list_add_tail(&fte->node.list, &fg->node.children); @@ -2709,6 +2716,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, break; case MLX5_FLOW_NAMESPACE_RDMA_TX: root_ns = steering->rdma_tx_root_ns; + prio = RDMA_TX_BYPASS_PRIO; break; case MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS: root_ns = steering->rdma_rx_root_ns; @@ -3528,35 +3536,42 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id, { struct mlx5_core_dev *dev = devlink_priv(devlink); char *value = val.vstr; - int err = 0; + u8 eswitch_mode; - if (!strcmp(value, "dmfs")) { + if (!strcmp(value, "dmfs")) return 0; - } else if (!strcmp(value, "smfs")) { - u8 eswitch_mode; - bool smfs_cap; - eswitch_mode = mlx5_eswitch_mode(dev); - smfs_cap = mlx5_fs_dr_is_supported(dev); + if (!strcmp(value, "smfs")) { + bool smfs_cap = mlx5_fs_dr_is_supported(dev); if (!smfs_cap) { - err = -EOPNOTSUPP; NL_SET_ERR_MSG_MOD(extack, "Software managed steering is not supported by current device"); + return -EOPNOTSUPP; } + } else if (!strcmp(value, "hmfs")) { + bool hmfs_cap = mlx5_fs_hws_is_supported(dev); - else if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) { + if (!hmfs_cap) { NL_SET_ERR_MSG_MOD(extack, - "Software managed steering is not supported when eswitch offloads enabled."); - err = -EOPNOTSUPP; + "Hardware steering is not supported by current device"); + return -EOPNOTSUPP; } } else { NL_SET_ERR_MSG_MOD(extack, - "Bad parameter: supported values are [\"dmfs\", \"smfs\"]"); - err = -EINVAL; + "Bad parameter: supported values are [\"dmfs\", \"smfs\", \"hmfs\"]"); + return -EINVAL; } - return err; + eswitch_mode = mlx5_eswitch_mode(dev); + if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Moving to %s is not supported when eswitch offloads enabled.", + value); + return -EOPNOTSUPP; + } + + return 0; } static int mlx5_fs_mode_set(struct devlink *devlink, u32 id, @@ -3568,6 +3583,8 @@ static int mlx5_fs_mode_set(struct devlink *devlink, u32 id, if (!strcmp(ctx->val.vstr, "smfs")) mode = MLX5_FLOW_STEERING_MODE_SMFS; + else if (!strcmp(ctx->val.vstr, "hmfs")) + mode = MLX5_FLOW_STEERING_MODE_HMFS; else mode = MLX5_FLOW_STEERING_MODE_DMFS; dev->priv.steering->mode = mode; @@ -3580,10 +3597,17 @@ static int mlx5_fs_mode_get(struct devlink *devlink, u32 id, { struct mlx5_core_dev *dev = devlink_priv(devlink); - if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) + switch (dev->priv.steering->mode) { + case MLX5_FLOW_STEERING_MODE_SMFS: strscpy(ctx->val.vstr, "smfs", sizeof(ctx->val.vstr)); - else + break; + case MLX5_FLOW_STEERING_MODE_HMFS: + strscpy(ctx->val.vstr, "hmfs", sizeof(ctx->val.vstr)); + break; + default: strscpy(ctx->val.vstr, "dmfs", sizeof(ctx->val.vstr)); + } + return 0; } @@ -3658,8 +3682,7 @@ int mlx5_fs_core_init(struct mlx5_core_dev *dev) goto err; } - if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) && - MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) { + if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support)) { err = init_rdma_rx_root_ns(steering); if (err) goto err; @@ -4003,6 +4026,8 @@ int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, if (mode == MLX5_FLOW_STEERING_MODE_SMFS) cmds = mlx5_fs_cmd_get_dr_cmds(); + else if (mode == MLX5_FLOW_STEERING_MODE_HMFS) + cmds = mlx5_fs_cmd_get_hws_cmds(); else cmds = mlx5_fs_cmd_get_fw_cmds(); if (!cmds) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index bad2df0715ec..20837e526679 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -38,6 +38,7 @@ #include #include #include +#include #define FDB_TC_MAX_CHAIN 3 #define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1) @@ -64,6 +65,7 @@ struct mlx5_modify_hdr { enum mlx5_flow_resource_owner owner; union { struct mlx5_fs_dr_action fs_dr_action; + struct mlx5_fs_hws_action fs_hws_action; u32 id; }; }; @@ -74,6 +76,7 @@ struct mlx5_pkt_reformat { enum mlx5_flow_resource_owner owner; union { struct mlx5_fs_dr_action fs_dr_action; + struct mlx5_fs_hws_action fs_hws_action; u32 id; }; }; @@ -126,7 +129,8 @@ enum fs_fte_status { enum mlx5_flow_steering_mode { MLX5_FLOW_STEERING_MODE_DMFS, - MLX5_FLOW_STEERING_MODE_SMFS + MLX5_FLOW_STEERING_MODE_SMFS, + MLX5_FLOW_STEERING_MODE_HMFS, }; enum mlx5_flow_steering_capabilty { @@ -190,7 +194,10 @@ struct mlx5_flow_handle { /* Type of children is mlx5_flow_group */ struct mlx5_flow_table { struct fs_node node; - struct mlx5_fs_dr_table fs_dr_table; + union { + struct mlx5_fs_dr_table fs_dr_table; + struct mlx5_fs_hws_table fs_hws_table; + }; u32 id; u16 vport; unsigned int max_fte; @@ -247,7 +254,10 @@ struct fs_fte_dup { /* Type of children is mlx5_flow_rule */ struct fs_fte { struct fs_node node; - struct mlx5_fs_dr_rule fs_dr_rule; + union { + struct mlx5_fs_dr_rule fs_dr_rule; + struct mlx5_fs_hws_rule fs_hws_rule; + }; u32 val[MLX5_ST_SZ_DW_MATCH_PARAM]; struct fs_fte_action act_dests; struct fs_fte_dup *dup; @@ -280,7 +290,10 @@ struct mlx5_flow_group_mask { /* Type of children is fs_fte */ struct mlx5_flow_group { struct fs_node node; - struct mlx5_fs_dr_matcher fs_dr_matcher; + union { + struct mlx5_fs_dr_matcher fs_dr_matcher; + struct mlx5_fs_hws_matcher fs_hws_matcher; + }; struct mlx5_flow_group_mask mask; u32 start_index; u32 max_ftes; @@ -293,7 +306,10 @@ struct mlx5_flow_group { struct mlx5_flow_root_namespace { struct mlx5_flow_namespace ns; enum mlx5_flow_steering_mode mode; - struct mlx5_fs_dr_domain fs_dr_domain; + union { + struct mlx5_fs_dr_domain fs_dr_domain; + struct mlx5_fs_hws_context fs_hws_context; + }; enum fs_flow_table_type table_type; struct mlx5_core_dev *dev; struct mlx5_flow_table *root_ft; @@ -303,6 +319,42 @@ struct mlx5_flow_root_namespace { const struct mlx5_flow_cmds *cmds; }; +enum mlx5_fc_type { + MLX5_FC_TYPE_ACQUIRED = 0, + MLX5_FC_TYPE_LOCAL, +}; + +struct mlx5_fc_cache { + u64 packets; + u64 bytes; + u64 lastuse; +}; + +struct mlx5_fc { + u32 id; + bool aging; + enum mlx5_fc_type type; + struct mlx5_fc_bulk *bulk; + struct mlx5_fc_cache cache; + /* last{packets,bytes} are used for calculating deltas since last reading. */ + u64 lastpackets; + u64 lastbytes; +}; + +struct mlx5_fc_bulk_hws_data { + struct mlx5hws_action *hws_action; + struct mutex lock; /* protects hws_action */ + refcount_t hws_action_refcount; +}; + +struct mlx5_fc_bulk { + struct mlx5_fs_bulk fs_bulk; + u32 base_id; + struct mlx5_fc_bulk_hws_data hws_data; + struct mlx5_fc fcs[]; +}; + +u32 mlx5_fc_get_base_id(struct mlx5_fc *counter); int mlx5_init_fc_stats(struct mlx5_core_dev *dev); void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev); void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 62d0c689796b..492775d3d193 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -34,6 +34,7 @@ #include #include "mlx5_core.h" #include "fs_core.h" +#include "fs_pool.h" #include "fs_cmd.h" #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) @@ -43,33 +44,6 @@ #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) #define MLX5_FC_POOL_USED_BUFF_RATIO 10 -struct mlx5_fc_cache { - u64 packets; - u64 bytes; - u64 lastuse; -}; - -struct mlx5_fc { - u32 id; - bool aging; - struct mlx5_fc_bulk *bulk; - struct mlx5_fc_cache cache; - /* last{packets,bytes} are used for calculating deltas since last reading. */ - u64 lastpackets; - u64 lastbytes; -}; - -struct mlx5_fc_pool { - struct mlx5_core_dev *dev; - struct mutex pool_lock; /* protects pool lists */ - struct list_head fully_used; - struct list_head partially_used; - struct list_head unused; - int available_fcs; - int used_fcs; - int threshold; -}; - struct mlx5_fc_stats { struct xarray counters; @@ -80,13 +54,13 @@ struct mlx5_fc_stats { int bulk_query_len; bool bulk_query_alloc_failed; unsigned long next_bulk_query_alloc; - struct mlx5_fc_pool fc_pool; + struct mlx5_fs_pool fc_pool; }; -static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev); -static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool); -static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool); -static void mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc); +static void mlx5_fc_pool_init(struct mlx5_fs_pool *fc_pool, struct mlx5_core_dev *dev); +static void mlx5_fc_pool_cleanup(struct mlx5_fs_pool *fc_pool); +static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fs_pool *fc_pool); +static void mlx5_fc_pool_release_counter(struct mlx5_fs_pool *fc_pool, struct mlx5_fc *fc); static int get_init_bulk_query_len(struct mlx5_core_dev *dev) { @@ -186,6 +160,9 @@ static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter) { struct mlx5_fc_stats *fc_stats = dev->priv.fc_stats; + if (WARN_ON(counter->type == MLX5_FC_TYPE_LOCAL)) + return; + if (counter->bulk) mlx5_fc_pool_release_counter(&fc_stats->fc_pool, counter); else @@ -435,15 +412,7 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, fc_stats->sampling_interval); } -/* Flow counter bluks */ - -struct mlx5_fc_bulk { - struct list_head pool_list; - u32 base_id; - int bulk_len; - unsigned long *bitmask; - struct mlx5_fc fcs[] __counted_by(bulk_len); -}; +/* Flow counter bulks */ static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, u32 id) @@ -452,16 +421,16 @@ static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, counter->id = id; } -static int mlx5_fc_bulk_get_free_fcs_amount(struct mlx5_fc_bulk *bulk) +u32 mlx5_fc_get_base_id(struct mlx5_fc *counter) { - return bitmap_weight(bulk->bitmask, bulk->bulk_len); + return counter->bulk->base_id; } -static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) +static struct mlx5_fs_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev, + void *pool_ctx) { enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask; - struct mlx5_fc_bulk *bulk; - int err = -ENOMEM; + struct mlx5_fc_bulk *fc_bulk; int bulk_len; u32 base_id; int i; @@ -469,207 +438,141 @@ static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) alloc_bitmask = MLX5_CAP_GEN(dev, flow_counter_bulk_alloc); bulk_len = alloc_bitmask > 0 ? MLX5_FC_BULK_NUM_FCS(alloc_bitmask) : 1; - bulk = kvzalloc(struct_size(bulk, fcs, bulk_len), GFP_KERNEL); - if (!bulk) - goto err_alloc_bulk; + fc_bulk = kvzalloc(struct_size(fc_bulk, fcs, bulk_len), GFP_KERNEL); + if (!fc_bulk) + return NULL; - bulk->bitmask = kvcalloc(BITS_TO_LONGS(bulk_len), sizeof(unsigned long), - GFP_KERNEL); - if (!bulk->bitmask) - goto err_alloc_bitmask; + if (mlx5_fs_bulk_init(dev, &fc_bulk->fs_bulk, bulk_len)) + goto fc_bulk_free; - err = mlx5_cmd_fc_bulk_alloc(dev, alloc_bitmask, &base_id); - if (err) - goto err_mlx5_cmd_bulk_alloc; + if (mlx5_cmd_fc_bulk_alloc(dev, alloc_bitmask, &base_id)) + goto fs_bulk_cleanup; + fc_bulk->base_id = base_id; + for (i = 0; i < bulk_len; i++) + mlx5_fc_init(&fc_bulk->fcs[i], fc_bulk, base_id + i); - bulk->base_id = base_id; - bulk->bulk_len = bulk_len; - for (i = 0; i < bulk_len; i++) { - mlx5_fc_init(&bulk->fcs[i], bulk, base_id + i); - set_bit(i, bulk->bitmask); - } + refcount_set(&fc_bulk->hws_data.hws_action_refcount, 0); + mutex_init(&fc_bulk->hws_data.lock); + return &fc_bulk->fs_bulk; - return bulk; - -err_mlx5_cmd_bulk_alloc: - kvfree(bulk->bitmask); -err_alloc_bitmask: - kvfree(bulk); -err_alloc_bulk: - return ERR_PTR(err); +fs_bulk_cleanup: + mlx5_fs_bulk_cleanup(&fc_bulk->fs_bulk); +fc_bulk_free: + kvfree(fc_bulk); + return NULL; } static int -mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fc_bulk *bulk) +mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk) { - if (mlx5_fc_bulk_get_free_fcs_amount(bulk) < bulk->bulk_len) { + struct mlx5_fc_bulk *fc_bulk = container_of(fs_bulk, + struct mlx5_fc_bulk, + fs_bulk); + + if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) { mlx5_core_err(dev, "Freeing bulk before all counters were released\n"); return -EBUSY; } - mlx5_cmd_fc_free(dev, bulk->base_id); - kvfree(bulk->bitmask); - kvfree(bulk); + mlx5_cmd_fc_free(dev, fc_bulk->base_id); + mlx5_fs_bulk_cleanup(fs_bulk); + kvfree(fc_bulk); return 0; } -static struct mlx5_fc *mlx5_fc_bulk_acquire_fc(struct mlx5_fc_bulk *bulk) +static void mlx5_fc_pool_update_threshold(struct mlx5_fs_pool *fc_pool) { - int free_fc_index = find_first_bit(bulk->bitmask, bulk->bulk_len); - - if (free_fc_index >= bulk->bulk_len) - return ERR_PTR(-ENOSPC); - - clear_bit(free_fc_index, bulk->bitmask); - return &bulk->fcs[free_fc_index]; -} - -static int mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc) -{ - int fc_index = fc->id - bulk->base_id; - - if (test_bit(fc_index, bulk->bitmask)) - return -EINVAL; - - set_bit(fc_index, bulk->bitmask); - return 0; + fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD, + fc_pool->used_units / MLX5_FC_POOL_USED_BUFF_RATIO); } /* Flow counters pool API */ -static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev) -{ - fc_pool->dev = dev; - mutex_init(&fc_pool->pool_lock); - INIT_LIST_HEAD(&fc_pool->fully_used); - INIT_LIST_HEAD(&fc_pool->partially_used); - INIT_LIST_HEAD(&fc_pool->unused); - fc_pool->available_fcs = 0; - fc_pool->used_fcs = 0; - fc_pool->threshold = 0; -} - -static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool) -{ - struct mlx5_core_dev *dev = fc_pool->dev; - struct mlx5_fc_bulk *bulk; - struct mlx5_fc_bulk *tmp; - - list_for_each_entry_safe(bulk, tmp, &fc_pool->fully_used, pool_list) - mlx5_fc_bulk_destroy(dev, bulk); - list_for_each_entry_safe(bulk, tmp, &fc_pool->partially_used, pool_list) - mlx5_fc_bulk_destroy(dev, bulk); - list_for_each_entry_safe(bulk, tmp, &fc_pool->unused, pool_list) - mlx5_fc_bulk_destroy(dev, bulk); -} - -static void mlx5_fc_pool_update_threshold(struct mlx5_fc_pool *fc_pool) -{ - fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD, - fc_pool->used_fcs / MLX5_FC_POOL_USED_BUFF_RATIO); -} - -static struct mlx5_fc_bulk * -mlx5_fc_pool_alloc_new_bulk(struct mlx5_fc_pool *fc_pool) -{ - struct mlx5_core_dev *dev = fc_pool->dev; - struct mlx5_fc_bulk *new_bulk; - - new_bulk = mlx5_fc_bulk_create(dev); - if (!IS_ERR(new_bulk)) - fc_pool->available_fcs += new_bulk->bulk_len; - mlx5_fc_pool_update_threshold(fc_pool); - return new_bulk; -} +static const struct mlx5_fs_pool_ops mlx5_fc_pool_ops = { + .bulk_destroy = mlx5_fc_bulk_destroy, + .bulk_create = mlx5_fc_bulk_create, + .update_threshold = mlx5_fc_pool_update_threshold, +}; static void -mlx5_fc_pool_free_bulk(struct mlx5_fc_pool *fc_pool, struct mlx5_fc_bulk *bulk) +mlx5_fc_pool_init(struct mlx5_fs_pool *fc_pool, struct mlx5_core_dev *dev) { - struct mlx5_core_dev *dev = fc_pool->dev; + mlx5_fs_pool_init(fc_pool, dev, &mlx5_fc_pool_ops, NULL); +} - fc_pool->available_fcs -= bulk->bulk_len; - mlx5_fc_bulk_destroy(dev, bulk); - mlx5_fc_pool_update_threshold(fc_pool); +static void mlx5_fc_pool_cleanup(struct mlx5_fs_pool *fc_pool) +{ + mlx5_fs_pool_cleanup(fc_pool); } static struct mlx5_fc * -mlx5_fc_pool_acquire_from_list(struct list_head *src_list, - struct list_head *next_list, - bool move_non_full_bulk) +mlx5_fc_pool_acquire_counter(struct mlx5_fs_pool *fc_pool) { - struct mlx5_fc_bulk *bulk; - struct mlx5_fc *fc; + struct mlx5_fs_pool_index pool_index = {}; + struct mlx5_fc_bulk *fc_bulk; + int err; - if (list_empty(src_list)) - return ERR_PTR(-ENODATA); - - bulk = list_first_entry(src_list, struct mlx5_fc_bulk, pool_list); - fc = mlx5_fc_bulk_acquire_fc(bulk); - if (move_non_full_bulk || mlx5_fc_bulk_get_free_fcs_amount(bulk) == 0) - list_move(&bulk->pool_list, next_list); - return fc; -} - -static struct mlx5_fc * -mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool) -{ - struct mlx5_fc_bulk *new_bulk; - struct mlx5_fc *fc; - - mutex_lock(&fc_pool->pool_lock); - - fc = mlx5_fc_pool_acquire_from_list(&fc_pool->partially_used, - &fc_pool->fully_used, false); - if (IS_ERR(fc)) - fc = mlx5_fc_pool_acquire_from_list(&fc_pool->unused, - &fc_pool->partially_used, - true); - if (IS_ERR(fc)) { - new_bulk = mlx5_fc_pool_alloc_new_bulk(fc_pool); - if (IS_ERR(new_bulk)) { - fc = ERR_CAST(new_bulk); - goto out; - } - fc = mlx5_fc_bulk_acquire_fc(new_bulk); - list_add(&new_bulk->pool_list, &fc_pool->partially_used); - } - fc_pool->available_fcs--; - fc_pool->used_fcs++; - -out: - mutex_unlock(&fc_pool->pool_lock); - return fc; + err = mlx5_fs_pool_acquire_index(fc_pool, &pool_index); + if (err) + return ERR_PTR(err); + fc_bulk = container_of(pool_index.fs_bulk, struct mlx5_fc_bulk, fs_bulk); + return &fc_bulk->fcs[pool_index.index]; } static void -mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc) +mlx5_fc_pool_release_counter(struct mlx5_fs_pool *fc_pool, struct mlx5_fc *fc) { + struct mlx5_fs_bulk *fs_bulk = &fc->bulk->fs_bulk; + struct mlx5_fs_pool_index pool_index = {}; struct mlx5_core_dev *dev = fc_pool->dev; - struct mlx5_fc_bulk *bulk = fc->bulk; - int bulk_free_fcs_amount; - mutex_lock(&fc_pool->pool_lock); - - if (mlx5_fc_bulk_release_fc(bulk, fc)) { + pool_index.fs_bulk = fs_bulk; + pool_index.index = fc->id - fc->bulk->base_id; + if (mlx5_fs_pool_release_index(fc_pool, &pool_index)) mlx5_core_warn(dev, "Attempted to release a counter which is not acquired\n"); - goto unlock; - } - - fc_pool->available_fcs++; - fc_pool->used_fcs--; - - bulk_free_fcs_amount = mlx5_fc_bulk_get_free_fcs_amount(bulk); - if (bulk_free_fcs_amount == 1) - list_move_tail(&bulk->pool_list, &fc_pool->partially_used); - if (bulk_free_fcs_amount == bulk->bulk_len) { - list_del(&bulk->pool_list); - if (fc_pool->available_fcs > fc_pool->threshold) - mlx5_fc_pool_free_bulk(fc_pool, bulk); - else - list_add(&bulk->pool_list, &fc_pool->unused); - } - -unlock: - mutex_unlock(&fc_pool->pool_lock); } + +/** + * mlx5_fc_local_create - Allocate mlx5_fc struct for a counter which + * was already acquired using its counter id and bulk data. + * + * @counter_id: counter acquired counter id + * @offset: counter offset from bulk base + * @bulk_size: counter's bulk size as was allocated + * + * Return: Pointer to mlx5_fc on success, ERR_PTR otherwise. + */ +struct mlx5_fc * +mlx5_fc_local_create(u32 counter_id, u32 offset, u32 bulk_size) +{ + struct mlx5_fc_bulk *fc_bulk; + struct mlx5_fc *counter; + + counter = kzalloc(sizeof(*counter), GFP_KERNEL); + if (!counter) + return ERR_PTR(-ENOMEM); + fc_bulk = kzalloc(sizeof(*fc_bulk), GFP_KERNEL); + if (!fc_bulk) { + kfree(counter); + return ERR_PTR(-ENOMEM); + } + + counter->type = MLX5_FC_TYPE_LOCAL; + counter->id = counter_id; + fc_bulk->base_id = counter_id - offset; + fc_bulk->fs_bulk.bulk_len = bulk_size; + counter->bulk = fc_bulk; + return counter; +} +EXPORT_SYMBOL(mlx5_fc_local_create); + +void mlx5_fc_local_destroy(struct mlx5_fc *counter) +{ + if (!counter || counter->type != MLX5_FC_TYPE_LOCAL) + return; + + kfree(counter->bulk); + kfree(counter); +} +EXPORT_SYMBOL(mlx5_fc_local_destroy); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c new file mode 100644 index 000000000000..f6c226664602 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ + +#include +#include "fs_pool.h" + +int mlx5_fs_bulk_init(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk, + int bulk_len) +{ + int i; + + fs_bulk->bitmask = kvcalloc(BITS_TO_LONGS(bulk_len), sizeof(unsigned long), + GFP_KERNEL); + if (!fs_bulk->bitmask) + return -ENOMEM; + + fs_bulk->bulk_len = bulk_len; + for (i = 0; i < bulk_len; i++) + set_bit(i, fs_bulk->bitmask); + + return 0; +} + +void mlx5_fs_bulk_cleanup(struct mlx5_fs_bulk *fs_bulk) +{ + kvfree(fs_bulk->bitmask); +} + +int mlx5_fs_bulk_get_free_amount(struct mlx5_fs_bulk *bulk) +{ + return bitmap_weight(bulk->bitmask, bulk->bulk_len); +} + +static int mlx5_fs_bulk_acquire_index(struct mlx5_fs_bulk *fs_bulk, + struct mlx5_fs_pool_index *pool_index) +{ + int free_index = find_first_bit(fs_bulk->bitmask, fs_bulk->bulk_len); + + WARN_ON_ONCE(!pool_index || !fs_bulk); + if (free_index >= fs_bulk->bulk_len) + return -ENOSPC; + + clear_bit(free_index, fs_bulk->bitmask); + pool_index->fs_bulk = fs_bulk; + pool_index->index = free_index; + return 0; +} + +static int mlx5_fs_bulk_release_index(struct mlx5_fs_bulk *fs_bulk, int index) +{ + if (test_bit(index, fs_bulk->bitmask)) + return -EINVAL; + + set_bit(index, fs_bulk->bitmask); + return 0; +} + +void mlx5_fs_pool_init(struct mlx5_fs_pool *pool, struct mlx5_core_dev *dev, + const struct mlx5_fs_pool_ops *ops, void *pool_ctx) +{ + WARN_ON_ONCE(!ops || !ops->bulk_destroy || !ops->bulk_create || + !ops->update_threshold); + pool->dev = dev; + pool->pool_ctx = pool_ctx; + mutex_init(&pool->pool_lock); + INIT_LIST_HEAD(&pool->fully_used); + INIT_LIST_HEAD(&pool->partially_used); + INIT_LIST_HEAD(&pool->unused); + pool->available_units = 0; + pool->used_units = 0; + pool->threshold = 0; + pool->ops = ops; +} + +void mlx5_fs_pool_cleanup(struct mlx5_fs_pool *pool) +{ + struct mlx5_core_dev *dev = pool->dev; + struct mlx5_fs_bulk *bulk; + struct mlx5_fs_bulk *tmp; + + list_for_each_entry_safe(bulk, tmp, &pool->fully_used, pool_list) + pool->ops->bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &pool->partially_used, pool_list) + pool->ops->bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &pool->unused, pool_list) + pool->ops->bulk_destroy(dev, bulk); +} + +static struct mlx5_fs_bulk * +mlx5_fs_pool_alloc_new_bulk(struct mlx5_fs_pool *fs_pool) +{ + struct mlx5_core_dev *dev = fs_pool->dev; + struct mlx5_fs_bulk *new_bulk; + + new_bulk = fs_pool->ops->bulk_create(dev, fs_pool->pool_ctx); + if (new_bulk) + fs_pool->available_units += new_bulk->bulk_len; + fs_pool->ops->update_threshold(fs_pool); + return new_bulk; +} + +static void +mlx5_fs_pool_free_bulk(struct mlx5_fs_pool *fs_pool, struct mlx5_fs_bulk *bulk) +{ + struct mlx5_core_dev *dev = fs_pool->dev; + + fs_pool->available_units -= bulk->bulk_len; + fs_pool->ops->bulk_destroy(dev, bulk); + fs_pool->ops->update_threshold(fs_pool); +} + +static int +mlx5_fs_pool_acquire_from_list(struct list_head *src_list, + struct list_head *next_list, + bool move_non_full_bulk, + struct mlx5_fs_pool_index *pool_index) +{ + struct mlx5_fs_bulk *fs_bulk; + int err; + + if (list_empty(src_list)) + return -ENODATA; + + fs_bulk = list_first_entry(src_list, struct mlx5_fs_bulk, pool_list); + err = mlx5_fs_bulk_acquire_index(fs_bulk, pool_index); + if (move_non_full_bulk || mlx5_fs_bulk_get_free_amount(fs_bulk) == 0) + list_move(&fs_bulk->pool_list, next_list); + return err; +} + +int mlx5_fs_pool_acquire_index(struct mlx5_fs_pool *fs_pool, + struct mlx5_fs_pool_index *pool_index) +{ + struct mlx5_fs_bulk *new_bulk; + int err; + + mutex_lock(&fs_pool->pool_lock); + + err = mlx5_fs_pool_acquire_from_list(&fs_pool->partially_used, + &fs_pool->fully_used, false, + pool_index); + if (err) + err = mlx5_fs_pool_acquire_from_list(&fs_pool->unused, + &fs_pool->partially_used, + true, pool_index); + if (err) { + new_bulk = mlx5_fs_pool_alloc_new_bulk(fs_pool); + if (!new_bulk) { + err = -ENOENT; + goto out; + } + err = mlx5_fs_bulk_acquire_index(new_bulk, pool_index); + WARN_ON_ONCE(err); + list_add(&new_bulk->pool_list, &fs_pool->partially_used); + } + fs_pool->available_units--; + fs_pool->used_units++; + +out: + mutex_unlock(&fs_pool->pool_lock); + return err; +} + +int mlx5_fs_pool_release_index(struct mlx5_fs_pool *fs_pool, + struct mlx5_fs_pool_index *pool_index) +{ + struct mlx5_fs_bulk *bulk = pool_index->fs_bulk; + int bulk_free_amount; + int err; + + mutex_lock(&fs_pool->pool_lock); + + /* TBD would rather return void if there was no warn here in original code */ + err = mlx5_fs_bulk_release_index(bulk, pool_index->index); + if (err) + goto unlock; + + fs_pool->available_units++; + fs_pool->used_units--; + + bulk_free_amount = mlx5_fs_bulk_get_free_amount(bulk); + if (bulk_free_amount == 1) + list_move_tail(&bulk->pool_list, &fs_pool->partially_used); + if (bulk_free_amount == bulk->bulk_len) { + list_del(&bulk->pool_list); + if (fs_pool->available_units > fs_pool->threshold) + mlx5_fs_pool_free_bulk(fs_pool, bulk); + else + list_add(&bulk->pool_list, &fs_pool->unused); + } + +unlock: + mutex_unlock(&fs_pool->pool_lock); + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h new file mode 100644 index 000000000000..f04ec3107498 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ + +#ifndef __MLX5_FS_POOL_H__ +#define __MLX5_FS_POOL_H__ + +#include + +struct mlx5_fs_bulk { + struct list_head pool_list; + int bulk_len; + unsigned long *bitmask; +}; + +struct mlx5_fs_pool_index { + struct mlx5_fs_bulk *fs_bulk; + int index; +}; + +struct mlx5_fs_pool; + +struct mlx5_fs_pool_ops { + int (*bulk_destroy)(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *bulk); + struct mlx5_fs_bulk * (*bulk_create)(struct mlx5_core_dev *dev, + void *pool_ctx); + void (*update_threshold)(struct mlx5_fs_pool *pool); +}; + +struct mlx5_fs_pool { + struct mlx5_core_dev *dev; + void *pool_ctx; + const struct mlx5_fs_pool_ops *ops; + struct mutex pool_lock; /* protects pool lists */ + struct list_head fully_used; + struct list_head partially_used; + struct list_head unused; + int available_units; + int used_units; + int threshold; +}; + +int mlx5_fs_bulk_init(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk, + int bulk_len); +void mlx5_fs_bulk_cleanup(struct mlx5_fs_bulk *fs_bulk); +int mlx5_fs_bulk_get_free_amount(struct mlx5_fs_bulk *bulk); + +void mlx5_fs_pool_init(struct mlx5_fs_pool *pool, struct mlx5_core_dev *dev, + const struct mlx5_fs_pool_ops *ops, void *pool_ctx); +void mlx5_fs_pool_cleanup(struct mlx5_fs_pool *pool); +int mlx5_fs_pool_acquire_index(struct mlx5_fs_pool *fs_pool, + struct mlx5_fs_pool_index *pool_index); +int mlx5_fs_pool_release_index(struct mlx5_fs_pool *fs_pool, + struct mlx5_fs_pool_index *pool_index); + +#endif /* __MLX5_FS_POOL_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 76ad46bf477d..b253d1673398 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -281,6 +281,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } + if (MLX5_CAP_GEN(dev, shampo)) { + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_SHAMPO, HCA_CAP_OPMOD_GET_CUR); + if (err) + return err; + } + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c index f4b777d4e108..62b6faa4276a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c @@ -105,20 +105,20 @@ static int mapping_show(struct seq_file *file, void *priv) struct mlx5_lag *ldev; bool hash = false; bool lag_active; + int i, idx = 0; int num_ports; - int i; ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); lag_active = __mlx5_lag_is_active(ldev); if (lag_active) { if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &ldev->mode_flags)) { - mlx5_infer_tx_enabled(&ldev->tracker, ldev->ports, ports, + mlx5_infer_tx_enabled(&ldev->tracker, ldev, ports, &num_ports); hash = true; } else { - for (i = 0; i < ldev->ports; i++) - ports[i] = ldev->v2p_map[i]; + mlx5_ldev_for_each(i, 0, ldev) + ports[idx++] = ldev->v2p_map[i]; num_ports = ldev->ports; } } @@ -144,11 +144,8 @@ static int members_show(struct seq_file *file, void *priv) ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); - for (i = 0; i < ldev->ports; i++) { - if (!ldev->pf[i].dev) - continue; + mlx5_ldev_for_each(i, 0, ldev) seq_printf(file, "%s\n", dev_name(ldev->pf[i].dev->device)); - } mutex_unlock(&ldev->lock); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 7f68468c2e75..cea5aa314f6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -43,10 +43,6 @@ #include "mp.h" #include "mpesw.h" -enum { - MLX5_LAG_EGRESS_PORT_1 = 1, - MLX5_LAG_EGRESS_PORT_2, -}; /* General purpose, use for short periods of time. * Beware of lock dependencies (preferably, no locks should be acquired @@ -72,7 +68,7 @@ static u8 lag_active_port_bits(struct mlx5_lag *ldev) int num_enabled; int idx; - mlx5_infer_tx_enabled(&ldev->tracker, ldev->ports, enabled_ports, + mlx5_infer_tx_enabled(&ldev->tracker, ldev, enabled_ports, &num_enabled); for (idx = 0; idx < num_enabled; idx++) active_port |= BIT_MASK(enabled_ports[idx]); @@ -80,23 +76,30 @@ static u8 lag_active_port_bits(struct mlx5_lag *ldev) return active_port; } -static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 *ports, int mode, - unsigned long flags) +static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, struct mlx5_lag *ldev, + int mode, unsigned long flags) { bool fdb_sel_mode = test_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, &flags); int port_sel_mode = get_port_sel_mode(mode, flags); u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {}; + u8 *ports = ldev->v2p_map; + int idx0, idx1; void *lag_ctx; lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx); MLX5_SET(create_lag_in, in, opcode, MLX5_CMD_OP_CREATE_LAG); MLX5_SET(lagc, lag_ctx, fdb_selection_mode, fdb_sel_mode); + idx0 = mlx5_lag_get_dev_index_by_seq(ldev, 0); + idx1 = mlx5_lag_get_dev_index_by_seq(ldev, 1); + + if (idx0 < 0 || idx1 < 0) + return -EINVAL; switch (port_sel_mode) { case MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY: - MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[0]); - MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[1]); + MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[idx0]); + MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[idx1]); break; case MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT: if (!MLX5_CAP_PORT_SELECTION(dev, port_select_flow_table_bypass)) @@ -113,17 +116,23 @@ static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 *ports, int mode, return mlx5_cmd_exec_in(dev, create_lag, in); } -static int mlx5_cmd_modify_lag(struct mlx5_core_dev *dev, u8 num_ports, +static int mlx5_cmd_modify_lag(struct mlx5_core_dev *dev, struct mlx5_lag *ldev, u8 *ports) { u32 in[MLX5_ST_SZ_DW(modify_lag_in)] = {}; void *lag_ctx = MLX5_ADDR_OF(modify_lag_in, in, ctx); + int idx0, idx1; + + idx0 = mlx5_lag_get_dev_index_by_seq(ldev, 0); + idx1 = mlx5_lag_get_dev_index_by_seq(ldev, 1); + if (idx0 < 0 || idx1 < 0) + return -EINVAL; MLX5_SET(modify_lag_in, in, opcode, MLX5_CMD_OP_MODIFY_LAG); MLX5_SET(modify_lag_in, in, field_select, 0x1); - MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[0]); - MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[1]); + MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[idx0]); + MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[idx1]); return mlx5_cmd_exec_in(dev, modify_lag, in); } @@ -148,33 +157,31 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag); -static void mlx5_infer_tx_disabled(struct lag_tracker *tracker, u8 num_ports, +static void mlx5_infer_tx_disabled(struct lag_tracker *tracker, struct mlx5_lag *ldev, u8 *ports, int *num_disabled) { int i; *num_disabled = 0; - for (i = 0; i < num_ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) if (!tracker->netdev_state[i].tx_enabled || !tracker->netdev_state[i].link_up) ports[(*num_disabled)++] = i; - } } -void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports, +void mlx5_infer_tx_enabled(struct lag_tracker *tracker, struct mlx5_lag *ldev, u8 *ports, int *num_enabled) { int i; *num_enabled = 0; - for (i = 0; i < num_ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) if (tracker->netdev_state[i].tx_enabled && tracker->netdev_state[i].link_up) ports[(*num_enabled)++] = i; - } if (*num_enabled == 0) - mlx5_infer_tx_disabled(tracker, num_ports, ports, num_enabled); + mlx5_infer_tx_disabled(tracker, ldev, ports, num_enabled); } static void mlx5_lag_print_mapping(struct mlx5_core_dev *dev, @@ -192,7 +199,7 @@ static void mlx5_lag_print_mapping(struct mlx5_core_dev *dev, int j; if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) { - mlx5_infer_tx_enabled(tracker, ldev->ports, enabled_ports, + mlx5_infer_tx_enabled(tracker, ldev, enabled_ports, &num_enabled); for (i = 0; i < num_enabled; i++) { err = scnprintf(buf + written, 4, "%d, ", enabled_ports[i] + 1); @@ -203,7 +210,7 @@ static void mlx5_lag_print_mapping(struct mlx5_core_dev *dev, buf[written - 2] = 0; mlx5_core_info(dev, "lag map active ports: %s\n", buf); } else { - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { for (j = 0; j < ldev->buckets; j++) { idx = i * ldev->buckets + j; err = scnprintf(buf + written, 10, @@ -286,13 +293,55 @@ int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev, { int i; - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) if (ldev->pf[i].netdev == ndev) return i; return -ENOENT; } +int mlx5_lag_get_dev_index_by_seq(struct mlx5_lag *ldev, int seq) +{ + int i, num = 0; + + if (!ldev) + return -ENOENT; + + mlx5_ldev_for_each(i, 0, ldev) { + if (num == seq) + return i; + num++; + } + return -ENOENT; +} + +int mlx5_lag_num_devs(struct mlx5_lag *ldev) +{ + int i, num = 0; + + if (!ldev) + return 0; + + mlx5_ldev_for_each(i, 0, ldev) { + (void)i; + num++; + } + return num; +} + +int mlx5_lag_num_netdevs(struct mlx5_lag *ldev) +{ + int i, num = 0; + + if (!ldev) + return 0; + + mlx5_ldev_for_each(i, 0, ldev) + if (ldev->pf[i].netdev) + num++; + return num; +} + static bool __mlx5_lag_is_roce(struct mlx5_lag *ldev) { return ldev->mode == MLX5_LAG_MODE_ROCE; @@ -310,7 +359,7 @@ static bool __mlx5_lag_is_sriov(struct mlx5_lag *ldev) * with mapping that points to active ports. */ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker, - u8 num_ports, + struct mlx5_lag *ldev, u8 buckets, u8 *ports) { @@ -323,7 +372,7 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker, int i; int j; - for (i = 0; i < num_ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { if (tracker->netdev_state[i].tx_enabled && tracker->netdev_state[i].link_up) enabled[enabled_ports_num++] = i; @@ -334,15 +383,16 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker, /* Use native mapping by default where each port's buckets * point the native port: 1 1 1 .. 1 2 2 2 ... 2 3 3 3 ... 3 etc */ - for (i = 0; i < num_ports; i++) + mlx5_ldev_for_each(i, 0, ldev) { for (j = 0; j < buckets; j++) { idx = i * buckets + j; - ports[idx] = MLX5_LAG_EGRESS_PORT_1 + i; + ports[idx] = i + 1; } + } /* If all ports are disabled/enabled keep native mapping */ - if (enabled_ports_num == num_ports || - disabled_ports_num == num_ports) + if (enabled_ports_num == ldev->ports || + disabled_ports_num == ldev->ports) return; /* Go over the disabled ports and for each assign a random active port */ @@ -358,7 +408,7 @@ static bool mlx5_lag_has_drop_rule(struct mlx5_lag *ldev) { int i; - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) if (ldev->pf[i].has_drop) return true; return false; @@ -368,7 +418,7 @@ static void mlx5_lag_drop_rule_cleanup(struct mlx5_lag *ldev) { int i; - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { if (!ldev->pf[i].has_drop) continue; @@ -396,7 +446,7 @@ static void mlx5_lag_drop_rule_setup(struct mlx5_lag *ldev, if (!ldev->tracker.has_inactive) return; - mlx5_infer_tx_disabled(tracker, ldev->ports, disabled_ports, &num_disabled); + mlx5_infer_tx_disabled(tracker, ldev, disabled_ports, &num_disabled); for (i = 0; i < num_disabled; i++) { disabled_index = disabled_ports[i]; @@ -428,10 +478,15 @@ static int mlx5_cmd_modify_active_port(struct mlx5_core_dev *dev, u8 ports) static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports) { - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + struct mlx5_core_dev *dev0; u8 active_ports; int ret; + if (idx < 0) + return -EINVAL; + + dev0 = ldev->pf[idx].dev; if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &ldev->mode_flags)) { ret = mlx5_lag_port_sel_modify(ldev, ports); if (ret || @@ -442,7 +497,7 @@ static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports) return mlx5_cmd_modify_active_port(dev0, active_ports); } - return mlx5_cmd_modify_lag(dev0, ldev->ports, ports); + return mlx5_cmd_modify_lag(dev0, ldev, ports); } static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev *dev) @@ -450,7 +505,7 @@ static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev struct net_device *ndev = NULL; struct mlx5_lag *ldev; unsigned long flags; - int i; + int i, last_idx; spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); @@ -458,11 +513,15 @@ static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev if (!ldev) goto unlock; - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) if (ldev->tracker.netdev_state[i].tx_enabled) ndev = ldev->pf[i].netdev; - if (!ndev) - ndev = ldev->pf[ldev->ports - 1].netdev; + if (!ndev) { + last_idx = mlx5_lag_get_dev_index_by_seq(ldev, ldev->ports - 1); + if (last_idx < 0) + goto unlock; + ndev = ldev->pf[last_idx].netdev; + } if (ndev) dev_hold(ndev); @@ -476,16 +535,21 @@ unlock: void mlx5_modify_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker) { + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); u8 ports[MLX5_MAX_PORTS * MLX5_LAG_MAX_HASH_BUCKETS] = {}; - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev0; int idx; int err; int i; int j; - mlx5_infer_tx_affinity_mapping(tracker, ldev->ports, ldev->buckets, ports); + if (first_idx < 0) + return; - for (i = 0; i < ldev->ports; i++) { + dev0 = ldev->pf[first_idx].dev; + mlx5_infer_tx_affinity_mapping(tracker, ldev, ldev->buckets, ports); + + mlx5_ldev_for_each(i, 0, ldev) { for (j = 0; j < ldev->buckets; j++) { idx = i * ldev->buckets + j; if (ports[idx] == ldev->v2p_map[idx]) @@ -523,8 +587,13 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev, unsigned long *flags) { - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + struct mlx5_core_dev *dev0; + if (first_idx < 0) + return -EINVAL; + + dev0 = ldev->pf[first_idx].dev; if (!MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table)) { if (ldev->ports > 2) return -EINVAL; @@ -544,11 +613,13 @@ static void mlx5_lag_set_port_sel_mode_offloads(struct mlx5_lag *ldev, enum mlx5_lag_mode mode, unsigned long *flags) { - struct lag_func *dev0 = &ldev->pf[MLX5_LAG_P1]; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + struct lag_func *dev0; - if (mode == MLX5_LAG_MODE_MPESW) + if (first_idx < 0 || mode == MLX5_LAG_MODE_MPESW) return; + dev0 = &ldev->pf[first_idx]; if (MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table) && tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH) { if (ldev->ports > 2) @@ -593,12 +664,18 @@ char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags) static int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_eswitch *master_esw = dev0->priv.eswitch; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + struct mlx5_eswitch *master_esw; + struct mlx5_core_dev *dev0; + int i, j; int err; - int i; - for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) { + if (first_idx < 0) + return -EINVAL; + + dev0 = ldev->pf[first_idx].dev; + master_esw = dev0->priv.eswitch; + mlx5_ldev_for_each(i, first_idx + 1, ldev) { struct mlx5_eswitch *slave_esw = ldev->pf[i].dev->priv.eswitch; err = mlx5_eswitch_offloads_single_fdb_add_one(master_esw, @@ -608,9 +685,9 @@ static int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev) } return 0; err: - for (; i > MLX5_LAG_P1; i--) + mlx5_ldev_for_each_reverse(j, i, first_idx + 1, ldev) mlx5_eswitch_offloads_single_fdb_del_one(master_esw, - ldev->pf[i].dev->priv.eswitch); + ldev->pf[j].dev->priv.eswitch); return err; } @@ -620,16 +697,21 @@ static int mlx5_create_lag(struct mlx5_lag *ldev, unsigned long flags) { bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags); - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; + struct mlx5_core_dev *dev0; int err; + if (first_idx < 0) + return -EINVAL; + + dev0 = ldev->pf[first_idx].dev; if (tracker) mlx5_lag_print_mapping(dev0, ldev, tracker, flags); mlx5_core_info(dev0, "shared_fdb:%d mode:%s\n", shared_fdb, mlx5_get_str_port_sel_mode(mode, flags)); - err = mlx5_cmd_create_lag(dev0, ldev->v2p_map, mode, flags); + err = mlx5_cmd_create_lag(dev0, ldev, mode, flags); if (err) { mlx5_core_err(dev0, "Failed to create LAG (%d)\n", @@ -661,17 +743,22 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, enum mlx5_lag_mode mode, bool shared_fdb) { + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); bool roce_lag = mode == MLX5_LAG_MODE_ROCE; - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev0; unsigned long flags = 0; int err; + if (first_idx < 0) + return -EINVAL; + + dev0 = ldev->pf[first_idx].dev; err = mlx5_lag_set_flags(ldev, mode, tracker, shared_fdb, &flags); if (err) return err; if (mode != MLX5_LAG_MODE_MPESW) { - mlx5_infer_tx_affinity_mapping(tracker, ldev->ports, ldev->buckets, ldev->v2p_map); + mlx5_infer_tx_affinity_mapping(tracker, ldev, ldev->buckets, ldev->v2p_map); if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) { err = mlx5_lag_port_sel_create(ldev, tracker->hash_type, ldev->v2p_map); @@ -709,20 +796,26 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, int mlx5_deactivate_lag(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_eswitch *master_esw = dev0->priv.eswitch; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; bool roce_lag = __mlx5_lag_is_roce(ldev); unsigned long flags = ldev->mode_flags; + struct mlx5_eswitch *master_esw; + struct mlx5_core_dev *dev0; int err; int i; + if (first_idx < 0) + return -EINVAL; + + dev0 = ldev->pf[first_idx].dev; + master_esw = dev0->priv.eswitch; ldev->mode = MLX5_LAG_MODE_NONE; ldev->mode_flags = 0; mlx5_lag_mp_reset(ldev); if (test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags)) { - for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) + mlx5_ldev_for_each(i, first_idx + 1, ldev) mlx5_eswitch_offloads_single_fdb_del_one(master_esw, ldev->pf[i].dev->priv.eswitch); clear_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags); @@ -754,6 +847,7 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev) bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) { + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); #ifdef CONFIG_MLX5_ESWITCH struct mlx5_core_dev *dev; u8 mode; @@ -761,30 +855,29 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) bool roce_support; int i; - for (i = 0; i < ldev->ports; i++) - if (!ldev->pf[i].dev) - return false; + if (first_idx < 0 || mlx5_lag_num_devs(ldev) != ldev->ports) + return false; #ifdef CONFIG_MLX5_ESWITCH - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { dev = ldev->pf[i].dev; if (mlx5_eswitch_num_vfs(dev->priv.eswitch) && !is_mdev_switchdev_mode(dev)) return false; } - dev = ldev->pf[MLX5_LAG_P1].dev; + dev = ldev->pf[first_idx].dev; mode = mlx5_eswitch_mode(dev); - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) if (mlx5_eswitch_mode(ldev->pf[i].dev) != mode) return false; #else - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) if (mlx5_sriov_is_enabled(ldev->pf[i].dev)) return false; #endif - roce_support = mlx5_get_roce_state(ldev->pf[MLX5_LAG_P1].dev); - for (i = 1; i < ldev->ports; i++) + roce_support = mlx5_get_roce_state(ldev->pf[first_idx].dev); + mlx5_ldev_for_each(i, first_idx + 1, ldev) if (mlx5_get_roce_state(ldev->pf[i].dev) != roce_support) return false; @@ -795,10 +888,7 @@ void mlx5_lag_add_devices(struct mlx5_lag *ldev) { int i; - for (i = 0; i < ldev->ports; i++) { - if (!ldev->pf[i].dev) - continue; - + mlx5_ldev_for_each(i, 0, ldev) { if (ldev->pf[i].dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) continue; @@ -812,10 +902,7 @@ void mlx5_lag_remove_devices(struct mlx5_lag *ldev) { int i; - for (i = 0; i < ldev->ports; i++) { - if (!ldev->pf[i].dev) - continue; - + mlx5_ldev_for_each(i, 0, ldev) { if (ldev->pf[i].dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) continue; @@ -828,11 +915,16 @@ void mlx5_lag_remove_devices(struct mlx5_lag *ldev) void mlx5_disable_lag(struct mlx5_lag *ldev) { bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + struct mlx5_core_dev *dev0; bool roce_lag; int err; int i; + if (idx < 0) + return; + + dev0 = ldev->pf[idx].dev; roce_lag = __mlx5_lag_is_roce(ldev); if (shared_fdb) { @@ -842,7 +934,7 @@ void mlx5_disable_lag(struct mlx5_lag *ldev) dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); } - for (i = 1; i < ldev->ports; i++) + mlx5_ldev_for_each(i, idx + 1, ldev) mlx5_nic_vport_disable_roce(ldev->pf[i].dev); } @@ -854,17 +946,21 @@ void mlx5_disable_lag(struct mlx5_lag *ldev) mlx5_lag_add_devices(ldev); if (shared_fdb) - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) if (!(ldev->pf[i].dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); } static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) { + int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct mlx5_core_dev *dev; int i; - for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) { + if (idx < 0) + return false; + + mlx5_ldev_for_each(i, idx + 1, ldev) { dev = ldev->pf[i].dev; if (is_mdev_switchdev_mode(dev) && mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) && @@ -876,7 +972,7 @@ static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) return false; } - dev = ldev->pf[MLX5_LAG_P1].dev; + dev = ldev->pf[idx].dev; if (is_mdev_switchdev_mode(dev) && mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) && mlx5_esw_offloads_devcom_is_ready(dev->priv.eswitch) && @@ -892,11 +988,11 @@ static bool mlx5_lag_is_roce_lag(struct mlx5_lag *ldev) bool roce_lag = true; int i; - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) roce_lag = roce_lag && !mlx5_sriov_is_enabled(ldev->pf[i].dev); #ifdef CONFIG_MLX5_ESWITCH - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) roce_lag = roce_lag && is_mdev_legacy_mode(ldev->pf[i].dev); #endif @@ -917,13 +1013,18 @@ static bool mlx5_lag_should_disable_lag(struct mlx5_lag *ldev, bool do_bond) static void mlx5_do_bond(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct lag_tracker tracker = { }; + struct mlx5_core_dev *dev0; struct net_device *ndev; bool do_bond, roce_lag; int err; int i; + if (idx < 0) + return; + + dev0 = ldev->pf[idx].dev; if (!mlx5_lag_is_ready(ldev)) { do_bond = false; } else { @@ -956,7 +1057,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) } else if (roce_lag) { dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); - for (i = 1; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, idx + 1, ldev) { if (mlx5_get_roce_state(ldev->pf[i].dev)) mlx5_nic_vport_enable_roce(ldev->pf[i].dev); } @@ -966,7 +1067,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); if (err) break; @@ -977,7 +1078,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) mlx5_rescan_drivers_locked(dev0); mlx5_deactivate_lag(ldev); mlx5_lag_add_devices(ldev); - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); mlx5_core_err(dev0, "Failed to enable lag\n"); return; @@ -1010,12 +1111,9 @@ struct mlx5_devcom_comp_dev *mlx5_lag_get_devcom_comp(struct mlx5_lag *ldev) int i; mutex_lock(&ldev->lock); - for (i = 0; i < ldev->ports; i++) { - if (ldev->pf[i].dev) { - devcom = ldev->pf[i].dev->priv.hca_devcom_comp; - break; - } - } + i = mlx5_get_next_ldev_func(ldev, 0); + if (i < MLX5_MAX_PORTS) + devcom = ldev->pf[i].dev->priv.hca_devcom_comp; mutex_unlock(&ldev->lock); return devcom; } @@ -1068,7 +1166,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, u8 bond_status = 0; int num_slaves = 0; int changed = 0; - int idx; + int i, idx = -1; if (!netif_is_lag_master(upper)) return 0; @@ -1083,8 +1181,13 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, */ rcu_read_lock(); for_each_netdev_in_bond_rcu(upper, ndev_tmp) { - idx = mlx5_lag_dev_get_netdev_idx(ldev, ndev_tmp); - if (idx >= 0) { + mlx5_ldev_for_each(i, 0, ldev) { + if (ldev->pf[i].netdev == ndev_tmp) { + idx++; + break; + } + } + if (i < MLX5_MAX_PORTS) { slave = bond_slave_get_rcu(ndev_tmp); if (slave) has_inactive |= bond_is_slave_inactive(slave); @@ -1234,15 +1337,12 @@ static int mlx5_lag_netdev_event(struct notifier_block *this, } static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev, - struct mlx5_core_dev *dev, - struct net_device *netdev) + struct mlx5_core_dev *dev, + struct net_device *netdev) { unsigned int fn = mlx5_get_dev_index(dev); unsigned long flags; - if (fn >= ldev->ports) - return; - spin_lock_irqsave(&lag_lock, flags); ldev->pf[fn].netdev = netdev; ldev->tracker.netdev_state[fn].link_up = 0; @@ -1257,7 +1357,7 @@ static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev, int i; spin_lock_irqsave(&lag_lock, flags); - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { if (ldev->pf[i].netdev == netdev) { ldev->pf[i].netdev = NULL; break; @@ -1267,13 +1367,10 @@ static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev, } static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev, - struct mlx5_core_dev *dev) + struct mlx5_core_dev *dev) { unsigned int fn = mlx5_get_dev_index(dev); - if (fn >= ldev->ports) - return; - ldev->pf[fn].dev = dev; dev->priv.lag = ldev; } @@ -1281,16 +1378,13 @@ static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev, static void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev) { - int i; + int fn; - for (i = 0; i < ldev->ports; i++) - if (ldev->pf[i].dev == dev) - break; - - if (i == ldev->ports) + fn = mlx5_get_dev_index(dev); + if (ldev->pf[fn].dev != dev) return; - ldev->pf[i].dev = NULL; + ldev->pf[fn].dev = NULL; dev->priv.lag = NULL; } @@ -1398,7 +1492,7 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, struct net_device *netdev) { struct mlx5_lag *ldev; - int i; + int num = 0; ldev = mlx5_lag_dev(dev); if (!ldev) @@ -1406,17 +1500,33 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, mutex_lock(&ldev->lock); mlx5_ldev_add_netdev(ldev, dev, netdev); - - for (i = 0; i < ldev->ports; i++) - if (!ldev->pf[i].netdev) - break; - - if (i >= ldev->ports) + num = mlx5_lag_num_netdevs(ldev); + if (num >= ldev->ports) set_bit(MLX5_LAG_FLAG_NDEVS_READY, &ldev->state_flags); mutex_unlock(&ldev->lock); mlx5_queue_bond_work(ldev, 0); } +int mlx5_get_pre_ldev_func(struct mlx5_lag *ldev, int start_idx, int end_idx) +{ + int i; + + for (i = start_idx; i >= end_idx; i--) + if (ldev->pf[i].dev) + return i; + return -1; +} + +int mlx5_get_next_ldev_func(struct mlx5_lag *ldev, int start_idx) +{ + int i; + + for (i = start_idx; i < MLX5_MAX_PORTS; i++) + if (ldev->pf[i].dev) + return i; + return MLX5_MAX_PORTS; +} + bool mlx5_lag_is_roce(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; @@ -1467,12 +1577,13 @@ bool mlx5_lag_is_master(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; unsigned long flags; - bool res; + bool res = false; + int idx; spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); - res = ldev && __mlx5_lag_is_active(ldev) && - dev == ldev->pf[MLX5_LAG_P1].dev; + idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + res = ldev && __mlx5_lag_is_active(ldev) && idx >= 0 && dev == ldev->pf[idx].dev; spin_unlock_irqrestore(&lag_lock, flags); return res; @@ -1555,7 +1666,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, if (!(ldev && __mlx5_lag_is_roce(ldev))) goto unlock; - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { if (ldev->pf[i].netdev == slave) { port = i; break; @@ -1594,13 +1705,13 @@ struct mlx5_core_dev *mlx5_lag_get_next_peer_mdev(struct mlx5_core_dev *dev, int if (!ldev) goto unlock; - if (*i == ldev->ports) + if (*i == MLX5_MAX_PORTS) goto unlock; - for (idx = *i; idx < ldev->ports; idx++) + mlx5_ldev_for_each(idx, *i, ldev) if (ldev->pf[idx].dev != dev) break; - if (idx == ldev->ports) { + if (idx == MLX5_MAX_PORTS) { *i = idx; goto unlock; } @@ -1621,10 +1732,10 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, { int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out); struct mlx5_core_dev **mdev; + int ret = 0, i, j, idx = 0; struct mlx5_lag *ldev; unsigned long flags; int num_ports; - int ret, i, j; void *out; out = kvzalloc(outlen, GFP_KERNEL); @@ -1643,8 +1754,8 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, ldev = mlx5_lag_dev(dev); if (ldev && __mlx5_lag_is_active(ldev)) { num_ports = ldev->ports; - for (i = 0; i < ldev->ports; i++) - mdev[i] = ldev->pf[i].dev; + mlx5_ldev_for_each(i, 0, ldev) + mdev[idx++] = ldev->pf[i].dev; } else { num_ports = 1; mdev[MLX5_LAG_P1] = dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index 50fcb1eee574..01cf72366947 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -103,7 +103,7 @@ int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev, struct net_device *ndev); char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags); -void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports, +void mlx5_infer_tx_enabled(struct lag_tracker *tracker, struct mlx5_lag *ldev, u8 *ports, int *num_enabled); void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev); @@ -119,9 +119,24 @@ static inline bool mlx5_lag_is_supported(struct mlx5_core_dev *dev) if (!MLX5_CAP_GEN(dev, vport_group_manager) || !MLX5_CAP_GEN(dev, lag_master) || MLX5_CAP_GEN(dev, num_lag_ports) < 2 || + mlx5_get_dev_index(dev) >= MLX5_MAX_PORTS || MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_MAX_PORTS) return false; return true; } +#define mlx5_ldev_for_each(i, start_index, ldev) \ + for (int tmp = start_index; tmp = mlx5_get_next_ldev_func(ldev, tmp), \ + i = tmp, tmp < MLX5_MAX_PORTS; tmp++) + +#define mlx5_ldev_for_each_reverse(i, start_index, end_index, ldev) \ + for (int tmp = start_index, tmp1 = end_index; \ + tmp = mlx5_get_pre_ldev_func(ldev, tmp, tmp1), \ + i = tmp, tmp >= tmp1; tmp--) + +int mlx5_get_pre_ldev_func(struct mlx5_lag *ldev, int start_idx, int end_idx); +int mlx5_get_next_ldev_func(struct mlx5_lag *ldev, int start_idx); +int mlx5_lag_get_dev_index_by_seq(struct mlx5_lag *ldev, int seq); +int mlx5_lag_num_devs(struct mlx5_lag *ldev); +int mlx5_lag_num_netdevs(struct mlx5_lag *ldev); #endif /* __MLX5_LAG_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index b1aa494c76ba..aee17fcf3b36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -17,7 +17,10 @@ static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev) #define MLX5_LAG_MULTIPATH_OFFLOADS_SUPPORTED_PORTS 2 static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) { - if (!mlx5_lag_is_ready(ldev)) + int idx0 = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + int idx1 = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P2); + + if (idx0 < 0 || idx1 < 0 || !mlx5_lag_is_ready(ldev)) return false; if (__mlx5_lag_is_active(ldev) && !__mlx5_lag_is_multipath(ldev)) @@ -26,8 +29,8 @@ static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) if (ldev->ports > MLX5_LAG_MULTIPATH_OFFLOADS_SUPPORTED_PORTS) return false; - return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev, - ldev->pf[MLX5_LAG_P2].dev); + return mlx5_esw_multipath_prereq(ldev->pf[idx0].dev, + ldev->pf[idx1].dev); } bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) @@ -50,43 +53,45 @@ bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, enum mlx5_lag_port_affinity port) { + int idx0 = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + int idx1 = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P2); struct lag_tracker tracker = {}; - if (!__mlx5_lag_is_multipath(ldev)) + if (idx0 < 0 || idx1 < 0 || !__mlx5_lag_is_multipath(ldev)) return; switch (port) { case MLX5_LAG_NORMAL_AFFINITY: - tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true; - tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true; - tracker.netdev_state[MLX5_LAG_P1].link_up = true; - tracker.netdev_state[MLX5_LAG_P2].link_up = true; + tracker.netdev_state[idx0].tx_enabled = true; + tracker.netdev_state[idx1].tx_enabled = true; + tracker.netdev_state[idx0].link_up = true; + tracker.netdev_state[idx1].link_up = true; break; case MLX5_LAG_P1_AFFINITY: - tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true; - tracker.netdev_state[MLX5_LAG_P1].link_up = true; - tracker.netdev_state[MLX5_LAG_P2].tx_enabled = false; - tracker.netdev_state[MLX5_LAG_P2].link_up = false; + tracker.netdev_state[idx0].tx_enabled = true; + tracker.netdev_state[idx0].link_up = true; + tracker.netdev_state[idx1].tx_enabled = false; + tracker.netdev_state[idx1].link_up = false; break; case MLX5_LAG_P2_AFFINITY: - tracker.netdev_state[MLX5_LAG_P1].tx_enabled = false; - tracker.netdev_state[MLX5_LAG_P1].link_up = false; - tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true; - tracker.netdev_state[MLX5_LAG_P2].link_up = true; + tracker.netdev_state[idx0].tx_enabled = false; + tracker.netdev_state[idx0].link_up = false; + tracker.netdev_state[idx1].tx_enabled = true; + tracker.netdev_state[idx1].link_up = true; break; default: - mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev, + mlx5_core_warn(ldev->pf[idx0].dev, "Invalid affinity port %d", port); return; } - if (tracker.netdev_state[MLX5_LAG_P1].tx_enabled) - mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P1].dev->priv.events, + if (tracker.netdev_state[idx0].tx_enabled) + mlx5_notifier_call_chain(ldev->pf[idx0].dev->priv.events, MLX5_DEV_EVENT_PORT_AFFINITY, (void *)0); - if (tracker.netdev_state[MLX5_LAG_P2].tx_enabled) - mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P2].dev->priv.events, + if (tracker.netdev_state[idx1].tx_enabled) + mlx5_notifier_call_chain(ldev->pf[idx1].dev->priv.events, MLX5_DEV_EVENT_PORT_AFFINITY, (void *)0); @@ -150,9 +155,14 @@ mlx5_lag_get_next_fib_dev(struct mlx5_lag *ldev, static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event, struct fib_entry_notifier_info *fen_info) { + int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct net_device *nh_dev0, *nh_dev1; struct fib_info *fi = fen_info->fi; struct lag_mp *mp = &ldev->lag_mp; + int i, dev_idx = 0; + + if (idx < 0) + return; /* Handle delete event */ if (event == FIB_EVENT_ENTRY_DEL) { @@ -179,17 +189,19 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event, } if (nh_dev0 == nh_dev1) { - mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev, + mlx5_core_warn(ldev->pf[idx].dev, "Multipath offload doesn't support routes with multiple nexthops of the same device"); return; } if (!nh_dev1) { if (__mlx5_lag_is_active(ldev)) { - int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev0); - - i++; - mlx5_lag_set_port_affinity(ldev, i); + mlx5_ldev_for_each(i, 0, ldev) { + dev_idx++; + if (ldev->pf[i].netdev == nh_dev0) + break; + } + mlx5_lag_set_port_affinity(ldev, dev_idx); mlx5_lag_fib_set(mp, fi, fen_info->dst, fen_info->dst_len); } @@ -214,6 +226,7 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev, struct fib_info *fi) { struct lag_mp *mp = &ldev->lag_mp; + int i, dev_idx = 0; /* Check the nh event is related to the route */ if (!mp->fib.mfi || mp->fib.mfi != fi) @@ -221,11 +234,15 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev, /* nh added/removed */ if (event == FIB_EVENT_NH_DEL) { - int i = mlx5_lag_dev_get_netdev_idx(ldev, fib_nh->fib_nh_dev); + mlx5_ldev_for_each(i, 0, ldev) { + if (ldev->pf[i].netdev == fib_nh->fib_nh_dev) + break; + dev_idx++; + } - if (i >= 0) { - i = (i + 1) % 2 + 1; /* peer port */ - mlx5_lag_set_port_affinity(ldev, i); + if (dev_idx >= 0) { + dev_idx = (dev_idx + 1) % 2 + 1; /* peer port */ + mlx5_lag_set_port_affinity(ldev, dev_idx); } } else if (event == FIB_EVENT_NH_ADD && fib_info_num_path(fi) == 2) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index 571ea26edd0c..ffac0bd6c895 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -15,7 +15,7 @@ static void mlx5_mpesw_metadata_cleanup(struct mlx5_lag *ldev) u32 pf_metadata; int i; - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { dev = ldev->pf[i].dev; esw = dev->priv.eswitch; pf_metadata = ldev->lag_mpesw.pf_metadata[i]; @@ -36,7 +36,7 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev) u32 pf_metadata; int i, err; - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { dev = ldev->pf[i].dev; esw = dev->priv.eswitch; pf_metadata = mlx5_esw_match_metadata_alloc(esw); @@ -52,7 +52,7 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev) goto err_metadata; } - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { dev = ldev->pf[i].dev; mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_MULTIPORT_ESW, (void *)0); @@ -68,13 +68,15 @@ err_metadata: #define MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS 4 static int enable_mpesw(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + struct mlx5_core_dev *dev0; int err; int i; - if (ldev->mode != MLX5_LAG_MODE_NONE) + if (idx < 0 || ldev->mode != MLX5_LAG_MODE_NONE) return -EINVAL; + dev0 = ldev->pf[idx].dev; if (ldev->ports > MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS) return -EOPNOTSUPP; @@ -98,7 +100,7 @@ static int enable_mpesw(struct mlx5_lag *ldev) dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); if (err) goto err_rescan_drivers; @@ -112,7 +114,7 @@ err_rescan_drivers: mlx5_deactivate_lag(ldev); err_add_devices: mlx5_lag_add_devices(ldev); - for (i = 0; i < ldev->ports; i++) + mlx5_ldev_for_each(i, 0, ldev) mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); mlx5_mpesw_metadata_cleanup(ldev); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index ab2717012b79..bde79cac33a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -39,15 +39,18 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev, struct mlx5_lag_definer *lag_definer, u8 *ports) { - struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_destination dest = {}; MLX5_DECLARE_FLOW_ACT(flow_act); struct mlx5_flow_namespace *ns; - int err, i; - int idx; - int j; + struct mlx5_core_dev *dev; + int err, i, j, k, idx; + if (first_idx < 0) + return -EINVAL; + + dev = ldev->pf[first_idx].dev; ft_attr.max_fte = ldev->ports * ldev->buckets; ft_attr.level = MLX5_LAG_FT_LEVEL_DEFINER; @@ -74,7 +77,7 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev, dest.type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; flow_act.flags |= FLOW_ACT_NO_APPEND; - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { for (j = 0; j < ldev->buckets; j++) { u8 affinity; @@ -88,13 +91,13 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev, &dest, 1); if (IS_ERR(lag_definer->rules[idx])) { err = PTR_ERR(lag_definer->rules[idx]); - do { + mlx5_ldev_for_each_reverse(k, i, 0, ldev) { while (j--) { - idx = i * ldev->buckets + j; + idx = k * ldev->buckets + j; mlx5_del_flow_rules(lag_definer->rules[idx]); } j = ldev->buckets; - } while (i--); + }; goto destroy_fg; } } @@ -295,11 +298,16 @@ static struct mlx5_lag_definer * mlx5_lag_create_definer(struct mlx5_lag *ldev, enum netdev_lag_hash hash, enum mlx5_traffic_types tt, bool tunnel, u8 *ports) { - struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct mlx5_lag_definer *lag_definer; + struct mlx5_core_dev *dev; u32 *match_definer_mask; int format_id, err; + if (first_idx < 0) + return ERR_PTR(-EINVAL); + + dev = ldev->pf[first_idx].dev; lag_definer = kzalloc(sizeof(*lag_definer), GFP_KERNEL); if (!lag_definer) return ERR_PTR(-ENOMEM); @@ -341,12 +349,15 @@ free_lag_definer: static void mlx5_lag_destroy_definer(struct mlx5_lag *ldev, struct mlx5_lag_definer *lag_definer) { - struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; - int idx; - int i; - int j; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + struct mlx5_core_dev *dev; + int idx, i, j; - for (i = 0; i < ldev->ports; i++) { + if (first_idx < 0) + return; + + dev = ldev->pf[first_idx].dev; + mlx5_ldev_for_each(i, first_idx, ldev) { for (j = 0; j < ldev->buckets; j++) { idx = i * ldev->buckets + j; mlx5_del_flow_rules(lag_definer->rules[idx]); @@ -501,10 +512,15 @@ static void mlx5_lag_set_outer_ttc_params(struct mlx5_lag *ldev, static int mlx5_lag_create_ttc_table(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; struct ttc_params ttc_params = {}; + struct mlx5_core_dev *dev; + if (first_idx < 0) + return -EINVAL; + + dev = ldev->pf[first_idx].dev; mlx5_lag_set_outer_ttc_params(ldev, &ttc_params); port_sel->outer.ttc = mlx5_create_ttc_table(dev, &ttc_params); return PTR_ERR_OR_ZERO(port_sel->outer.ttc); @@ -512,10 +528,15 @@ static int mlx5_lag_create_ttc_table(struct mlx5_lag *ldev) static int mlx5_lag_create_inner_ttc_table(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; struct ttc_params ttc_params = {}; + struct mlx5_core_dev *dev; + if (first_idx < 0) + return -EINVAL; + + dev = ldev->pf[first_idx].dev; mlx5_lag_set_inner_ttc_params(ldev, &ttc_params); port_sel->inner.ttc = mlx5_create_inner_ttc_table(dev, &ttc_params); return PTR_ERR_OR_ZERO(port_sel->inner.ttc); @@ -530,7 +551,7 @@ int mlx5_lag_port_sel_create(struct mlx5_lag *ldev, set_tt_map(port_sel, hash_type); err = mlx5_lag_create_definers(ldev, hash_type, ports); if (err) - return err; + goto clear_port_sel; if (port_sel->tunnel) { err = mlx5_lag_create_inner_ttc_table(ldev); @@ -549,6 +570,8 @@ destroy_inner: mlx5_destroy_ttc_table(port_sel->inner.ttc); destroy_definers: mlx5_lag_destroy_definers(ldev); +clear_port_sel: + memset(port_sel, 0, sizeof(*port_sel)); return err; } @@ -565,7 +588,7 @@ static int __mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev, dest.type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; - for (i = 0; i < ldev->ports; i++) { + mlx5_ldev_for_each(i, 0, ldev) { for (j = 0; j < ldev->buckets; j++) { idx = i * ldev->buckets + j; if (ldev->v2p_map[idx] == ports[idx]) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 4822d01123b4..d61a1a9297c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -322,17 +322,16 @@ static void mlx5_pps_out(struct work_struct *work) } } -static void mlx5_timestamp_overflow(struct work_struct *work) +static long mlx5_timestamp_overflow(struct ptp_clock_info *ptp_info) { - struct delayed_work *dwork = to_delayed_work(work); struct mlx5_core_dev *mdev; struct mlx5_timer *timer; struct mlx5_clock *clock; unsigned long flags; - timer = container_of(dwork, struct mlx5_timer, overflow_work); - clock = container_of(timer, struct mlx5_clock, timer); + clock = container_of(ptp_info, struct mlx5_clock, ptp_info); mdev = container_of(clock, struct mlx5_core_dev, clock); + timer = &clock->timer; if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) goto out; @@ -343,7 +342,7 @@ static void mlx5_timestamp_overflow(struct work_struct *work) write_sequnlock_irqrestore(&clock->lock, flags); out: - schedule_delayed_work(&timer->overflow_work, timer->overflow_period); + return timer->overflow_period; } static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev, @@ -517,6 +516,7 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) timer->cycles.mult = mult; mlx5_update_clock_info_page(mdev); write_sequnlock_irqrestore(&clock->lock, flags); + ptp_schedule_worker(clock->ptp, timer->overflow_period); return 0; } @@ -852,6 +852,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = { .settime64 = mlx5_ptp_settime, .enable = NULL, .verify = NULL, + .do_aux_work = mlx5_timestamp_overflow, }; static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin, @@ -1052,12 +1053,11 @@ static void mlx5_init_overflow_period(struct mlx5_clock *clock) do_div(ns, NSEC_PER_SEC / HZ); timer->overflow_period = ns; - INIT_DELAYED_WORK(&timer->overflow_work, mlx5_timestamp_overflow); - if (timer->overflow_period) - schedule_delayed_work(&timer->overflow_work, 0); - else + if (!timer->overflow_period) { + timer->overflow_period = HZ; mlx5_core_warn(mdev, - "invalid overflow period, overflow_work is not scheduled\n"); + "invalid overflow period, overflow_work is scheduled once per second\n"); + } if (clock_info) clock_info->overflow_period = timer->overflow_period; @@ -1172,6 +1172,9 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev) MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT); mlx5_eq_notifier_register(mdev, &clock->pps_nb); + + if (clock->ptp) + ptp_schedule_worker(clock->ptp, 0); } void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) @@ -1188,7 +1191,6 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) } cancel_work_sync(&clock->pps_info.out_work); - cancel_delayed_work_sync(&clock->timer.overflow_work); if (mdev->clock_info) { free_page((unsigned long)mdev->clock_info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c index 4a078113e292..762d55ba9e51 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c @@ -497,7 +497,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs) memset(&dest, 0, sizeof(struct mlx5_flow_destination)); memset(&flow_act, 0, sizeof(flow_act)); dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(tx_tables->check_miss_rule_counter); + dest.counter = tx_tables->check_miss_rule_counter; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; rule = mlx5_add_flow_rules(tx_tables->ft_check, NULL, &flow_act, &dest, 1); if (IS_ERR(rule)) { @@ -519,7 +519,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs) flow_act.flags = FLOW_ACT_NO_APPEND; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW | MLX5_FLOW_CONTEXT_ACTION_COUNT; dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(tx_tables->check_rule_counter); + dest.counter = tx_tables->check_rule_counter; rule = mlx5_add_flow_rules(tx_tables->ft_check, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -1200,7 +1200,7 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5_macsec_fs *macsec_fs flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | MLX5_FLOW_CONTEXT_ACTION_COUNT; roce_dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - roce_dest[dstn].counter_id = mlx5_fc_id(rx_tables->check_rule_counter); + roce_dest[dstn].counter = rx_tables->check_rule_counter; rule = mlx5_add_flow_rules(rx_tables->ft_check, spec, flow_act, roce_dest, dstn + 1); if (IS_ERR(rule)) { @@ -1592,7 +1592,7 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs) memset(&flow_act, 0, sizeof(flow_act)); dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(rx_tables->check_miss_rule_counter); + dest.counter = rx_tables->check_miss_rule_counter; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; rule = mlx5_add_flow_rules(rx_tables->ft_check, NULL, &flow_act, &dest, 1); if (IS_ERR(rule)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 220a9ac75c8b..ec956c4bcebd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -368,6 +368,10 @@ int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_ty u16 opmod = (cap_type << 1) | (cap_mode & 0x01); int err; + if (WARN_ON(!dev->caps.hca[cap_type])) + /* this cap_type must be added to mlx5_hca_caps_alloc() */ + return -EINVAL; + memset(in, 0, sizeof(in)); out = kzalloc(out_sz, GFP_KERNEL); if (!out) @@ -664,6 +668,10 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_current_uc_list, ilog2(max_uc_list)); + /* enable absolute native port num */ + if (MLX5_CAP_GEN_MAX(dev, abs_native_port_num)) + MLX5_SET(cmd_hca_cap, set_hca_cap, abs_native_port_num, 1); + return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); } @@ -941,9 +949,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, mlx5_pci_vsc_init(dev); - err = pci_enable_ptm(pdev, NULL); - if (err) - mlx5_core_info(dev, "PTM is not supported by PCIe\n"); + pci_enable_ptm(pdev, NULL); return 0; @@ -1788,6 +1794,7 @@ static const int types[] = { MLX5_CAP_MACSEC, MLX5_CAP_ADV_VIRTUALIZATION, MLX5_CAP_CRYPTO, + MLX5_CAP_SHAMPO, }; static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c index e393391966e0..39a209b9b684 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c @@ -56,6 +56,8 @@ bool mlx5_qos_tsar_type_supported(struct mlx5_core_dev *dev, int type, u8 hierar return cap & TSAR_TYPE_CAP_MASK_ROUND_ROBIN; case TSAR_ELEMENT_TSAR_TYPE_ETS: return cap & TSAR_TYPE_CAP_MASK_ETS; + case TSAR_ELEMENT_TSAR_TYPE_TC_ARB: + return cap & TSAR_TYPE_CAP_MASK_TC_ARB; } return false; @@ -87,6 +89,8 @@ bool mlx5_qos_element_type_supported(struct mlx5_core_dev *dev, int type, u8 hie return cap & ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; case SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP: return cap & ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT: + return cap & ELEMENT_TYPE_CAP_MASK_RATE_LIMIT; } return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index a96be98be032..b96909fbeb12 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -257,6 +257,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, return 0; esw_err: + mlx5_sf_function_id_erase(table, sf); mlx5_sf_free(table, sf); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c index a897cdc60fdb..b5332c54d4fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c @@ -11,31 +11,29 @@ /* This is the longest supported action sequence for FDB table: * DECAP, POP_VLAN, MODIFY, CTR, ASO, PUSH_VLAN, MODIFY, ENCAP, Term. */ -static const u32 action_order_arr[MLX5HWS_TABLE_TYPE_MAX][MLX5HWS_ACTION_TYP_MAX] = { - [MLX5HWS_TABLE_TYPE_FDB] = { - BIT(MLX5HWS_ACTION_TYP_REMOVE_HEADER) | - BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2) | - BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2), - BIT(MLX5HWS_ACTION_TYP_POP_VLAN), - BIT(MLX5HWS_ACTION_TYP_POP_VLAN), - BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR), - BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN), - BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN), - BIT(MLX5HWS_ACTION_TYP_INSERT_HEADER) | - BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) | - BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3), - BIT(MLX5HWS_ACTION_TYP_CTR), - BIT(MLX5HWS_ACTION_TYP_TAG), - BIT(MLX5HWS_ACTION_TYP_ASO_METER), - BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR), - BIT(MLX5HWS_ACTION_TYP_TBL) | - BIT(MLX5HWS_ACTION_TYP_VPORT) | - BIT(MLX5HWS_ACTION_TYP_DROP) | - BIT(MLX5HWS_ACTION_TYP_SAMPLER) | - BIT(MLX5HWS_ACTION_TYP_RANGE) | - BIT(MLX5HWS_ACTION_TYP_DEST_ARRAY), - BIT(MLX5HWS_ACTION_TYP_LAST), - }, +static const u32 action_order_arr[MLX5HWS_ACTION_TYP_MAX] = { + BIT(MLX5HWS_ACTION_TYP_REMOVE_HEADER) | + BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2) | + BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2), + BIT(MLX5HWS_ACTION_TYP_POP_VLAN), + BIT(MLX5HWS_ACTION_TYP_POP_VLAN), + BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR), + BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN), + BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN), + BIT(MLX5HWS_ACTION_TYP_INSERT_HEADER) | + BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) | + BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3), + BIT(MLX5HWS_ACTION_TYP_CTR), + BIT(MLX5HWS_ACTION_TYP_TAG), + BIT(MLX5HWS_ACTION_TYP_ASO_METER), + BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR), + BIT(MLX5HWS_ACTION_TYP_TBL) | + BIT(MLX5HWS_ACTION_TYP_VPORT) | + BIT(MLX5HWS_ACTION_TYP_DROP) | + BIT(MLX5HWS_ACTION_TYP_SAMPLER) | + BIT(MLX5HWS_ACTION_TYP_RANGE) | + BIT(MLX5HWS_ACTION_TYP_DEST_ARRAY), + BIT(MLX5HWS_ACTION_TYP_LAST), }; static const char * const mlx5hws_action_type_str[] = { @@ -83,8 +81,8 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx, int ret; mutex_lock(&ctx->ctrl_lock); - if (ctx->common_res[tbl_type].shared_stc[stc_type]) { - ctx->common_res[tbl_type].shared_stc[stc_type]->refcount++; + if (ctx->common_res.shared_stc[stc_type]) { + ctx->common_res.shared_stc[stc_type]->refcount++; mutex_unlock(&ctx->ctrl_lock); return 0; } @@ -124,8 +122,8 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx, goto free_shared_stc; } - ctx->common_res[tbl_type].shared_stc[stc_type] = shared_stc; - ctx->common_res[tbl_type].shared_stc[stc_type]->refcount = 1; + ctx->common_res.shared_stc[stc_type] = shared_stc; + ctx->common_res.shared_stc[stc_type]->refcount = 1; mutex_unlock(&ctx->ctrl_lock); @@ -178,16 +176,16 @@ static void hws_action_put_shared_stc(struct mlx5hws_action *action, } mutex_lock(&ctx->ctrl_lock); - if (--ctx->common_res[tbl_type].shared_stc[stc_type]->refcount) { + if (--ctx->common_res.shared_stc[stc_type]->refcount) { mutex_unlock(&ctx->ctrl_lock); return; } - shared_stc = ctx->common_res[tbl_type].shared_stc[stc_type]; + shared_stc = ctx->common_res.shared_stc[stc_type]; mlx5hws_action_free_single_stc(ctx, tbl_type, &shared_stc->stc_chunk); kfree(shared_stc); - ctx->common_res[tbl_type].shared_stc[stc_type] = NULL; + ctx->common_res.shared_stc[stc_type] = NULL; mutex_unlock(&ctx->ctrl_lock); } @@ -206,10 +204,10 @@ bool mlx5hws_action_check_combo(struct mlx5hws_context *ctx, enum mlx5hws_action_type *user_actions, enum mlx5hws_table_type table_type) { - const u32 *order_arr = action_order_arr[table_type]; + const u32 *order_arr = action_order_arr; + bool valid_combo; u8 order_idx = 0; u8 user_idx = 0; - bool valid_combo; if (table_type >= MLX5HWS_TABLE_TYPE_MAX) { mlx5hws_err(ctx, "Invalid table_type %d", table_type); @@ -321,8 +319,8 @@ int mlx5hws_action_alloc_single_stc(struct mlx5hws_context *ctx, __must_hold(&ctx->ctrl_lock) { struct mlx5hws_cmd_stc_modify_attr cleanup_stc_attr = {0}; - struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type]; struct mlx5hws_cmd_stc_modify_attr fixup_stc_attr = {0}; + struct mlx5hws_pool *stc_pool = ctx->stc_pool; bool use_fixup; u32 obj_0_id; int ret; @@ -387,8 +385,8 @@ void mlx5hws_action_free_single_stc(struct mlx5hws_context *ctx, struct mlx5hws_pool_chunk *stc) __must_hold(&ctx->ctrl_lock) { - struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type]; struct mlx5hws_cmd_stc_modify_attr stc_attr = {0}; + struct mlx5hws_pool *stc_pool = ctx->stc_pool; u32 obj_id; /* Modify the STC not to point to an object */ @@ -473,6 +471,7 @@ static void hws_action_fill_stc_attr(struct mlx5hws_action *action, break; case MLX5HWS_ACTION_TYP_TBL: case MLX5HWS_ACTION_TYP_DEST_ARRAY: + case MLX5HWS_ACTION_TYP_SAMPLER: attr->action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_FT; attr->action_offset = MLX5HWS_ACTION_OFFSET_HIT; attr->dest_table_id = obj_id; @@ -561,7 +560,7 @@ hws_action_create_stcs(struct mlx5hws_action *action, u32 obj_id) if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB) { ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, MLX5HWS_TABLE_TYPE_FDB, - &action->stc[MLX5HWS_TABLE_TYPE_FDB]); + &action->stc); if (ret) goto out_err; } @@ -585,7 +584,7 @@ hws_action_destroy_stcs(struct mlx5hws_action *action) if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB) mlx5hws_action_free_single_stc(ctx, MLX5HWS_TABLE_TYPE_FDB, - &action->stc[MLX5HWS_TABLE_TYPE_FDB]); + &action->stc); mutex_unlock(&ctx->ctrl_lock); } @@ -1639,8 +1638,8 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx, rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, false); /* STC is a single resource (obj_id), use any STC for the ID */ - stc_pool = ctx->stc_pool[MLX5HWS_TABLE_TYPE_FDB]; - default_stc = ctx->common_res[MLX5HWS_TABLE_TYPE_FDB].default_stc; + stc_pool = ctx->stc_pool; + default_stc = ctx->common_res.default_stc; obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit); rtc_attr.stc_base = obj_id; @@ -1731,7 +1730,7 @@ hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx, ste_attr.used_id_rtc_0 = &used_rtc_0_id; ste_attr.used_id_rtc_1 = &used_rtc_1_id; - common_res = &ctx->common_res[MLX5HWS_TABLE_TYPE_FDB]; + common_res = &ctx->common_res; /* init an empty match STE which will always hit */ ste_attr.wqe_ctrl = &wqe_ctrl; @@ -1750,7 +1749,7 @@ hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx, wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_CTRL] |= htonl(MLX5HWS_ACTION_STC_IDX_LAST_COMBO2 << 29); wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_HIT] = - htonl(hit_ft_action->stc[MLX5HWS_TABLE_TYPE_FDB].offset); + htonl(hit_ft_action->stc.offset); wqe_data_arr = (__force __be32 *)&range_wqe_data; @@ -1843,7 +1842,7 @@ mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx, stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer; ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, MLX5HWS_TABLE_TYPE_FDB, - &action->stc[MLX5HWS_TABLE_TYPE_FDB]); + &action->stc); if (ret) goto error_unlock; @@ -1875,7 +1874,50 @@ struct mlx5hws_action * mlx5hws_action_create_flow_sampler(struct mlx5hws_context *ctx, u32 sampler_id, u32 flags) { - mlx5hws_err(ctx, "Flow sampler action - unsupported\n"); + struct mlx5hws_cmd_ft_create_attr ft_attr = {0}; + struct mlx5hws_cmd_set_fte_attr fte_attr = {0}; + struct mlx5hws_cmd_forward_tbl *fw_island; + struct mlx5hws_cmd_set_fte_dest dest; + struct mlx5hws_action *action; + int ret; + + if (flags != (MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED)) { + mlx5hws_err(ctx, "Unsupported flags for flow sampler\n"); + return NULL; + } + + ft_attr.type = FS_FT_FDB; + ft_attr.level = ctx->caps->fdb_ft.max_level - 1; + + dest.destination_type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER; + dest.destination_id = sampler_id; + + fte_attr.dests_num = 1; + fte_attr.dests = &dest; + fte_attr.action_flags = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + fte_attr.ignore_flow_level = 1; + + fw_island = mlx5hws_cmd_forward_tbl_create(ctx->mdev, &ft_attr, &fte_attr); + if (!fw_island) + return NULL; + + action = hws_action_create_generic(ctx, flags, + MLX5HWS_ACTION_TYP_SAMPLER); + if (!action) + goto destroy_fw_island; + + ret = hws_action_create_stcs(action, fw_island->ft_id); + if (ret) + goto free_action; + + action->flow_sampler.fw_island = fw_island; + + return action; + +free_action: + kfree(action); +destroy_fw_island: + mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, fw_island); return NULL; } @@ -1914,6 +1956,11 @@ static void hws_action_destroy_hws(struct mlx5hws_action *action) } kfree(action->dest_array.dest_list); break; + case MLX5HWS_ACTION_TYP_SAMPLER: + hws_action_destroy_stcs(action); + mlx5hws_cmd_forward_tbl_destroy(action->ctx->mdev, + action->flow_sampler.fw_island); + break; case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2: case MLX5HWS_ACTION_TYP_MODIFY_HDR: shared_arg = false; @@ -1970,8 +2017,8 @@ __must_hold(&ctx->ctrl_lock) struct mlx5hws_action_default_stc *default_stc; int ret; - if (ctx->common_res[tbl_type].default_stc) { - ctx->common_res[tbl_type].default_stc->refcount++; + if (ctx->common_res.default_stc) { + ctx->common_res.default_stc->refcount++; return 0; } @@ -2023,8 +2070,8 @@ __must_hold(&ctx->ctrl_lock) goto free_nop_dw7; } - ctx->common_res[tbl_type].default_stc = default_stc; - ctx->common_res[tbl_type].default_stc->refcount++; + ctx->common_res.default_stc = default_stc; + ctx->common_res.default_stc->refcount++; return 0; @@ -2046,9 +2093,7 @@ __must_hold(&ctx->ctrl_lock) { struct mlx5hws_action_default_stc *default_stc; - default_stc = ctx->common_res[tbl_type].default_stc; - - default_stc = ctx->common_res[tbl_type].default_stc; + default_stc = ctx->common_res.default_stc; if (--default_stc->refcount) return; @@ -2058,7 +2103,7 @@ __must_hold(&ctx->ctrl_lock) mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw5); mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_ctr); kfree(default_stc); - ctx->common_res[tbl_type].default_stc = NULL; + ctx->common_res.default_stc = NULL; } static void hws_action_modify_write(struct mlx5hws_send_engine *queue, @@ -2150,8 +2195,7 @@ hws_action_apply_stc(struct mlx5hws_actions_apply_data *apply, { struct mlx5hws_action *action = apply->rule_action[action_idx].action; - apply->wqe_ctrl->stc_ix[stc_idx] = - htonl(action->stc[apply->tbl_type].offset); + apply->wqe_ctrl->stc_ix[stc_idx] = htonl(action->stc.offset); } static void @@ -2181,7 +2225,7 @@ hws_action_setter_modify_header(struct mlx5hws_actions_apply_data *apply, rule_action = &apply->rule_action[setter->idx_double]; action = rule_action->action; - stc_idx = htonl(action->stc[apply->tbl_type].offset); + stc_idx = htonl(action->stc.offset); apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx; apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0; @@ -2240,7 +2284,7 @@ hws_action_setter_insert_ptr(struct mlx5hws_actions_apply_data *apply, apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0; apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx); - stc_idx = htonl(action->stc[apply->tbl_type].offset); + stc_idx = htonl(action->stc.offset); apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx; apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0; @@ -2272,7 +2316,7 @@ hws_action_setter_tnl_l3_to_l2(struct mlx5hws_actions_apply_data *apply, apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0; apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx); - stc_idx = htonl(action->stc[apply->tbl_type].offset); + stc_idx = htonl(action->stc.offset); apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx; apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0; @@ -2434,6 +2478,7 @@ int mlx5hws_action_template_process(struct mlx5hws_action_template *at) case MLX5HWS_ACTION_TYP_DROP: case MLX5HWS_ACTION_TYP_TBL: case MLX5HWS_ACTION_TYP_DEST_ARRAY: + case MLX5HWS_ACTION_TYP_SAMPLER: case MLX5HWS_ACTION_TYP_VPORT: case MLX5HWS_ACTION_TYP_MISS: /* Hit action */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h index e8f562c31826..64b76075f7f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h @@ -70,12 +70,12 @@ struct mlx5hws_action_default_stc { struct mlx5hws_pool_chunk nop_dw6; struct mlx5hws_pool_chunk nop_dw7; struct mlx5hws_pool_chunk default_hit; - u32 refcount; + u32 refcount; /* protected by context ctrl lock */ }; struct mlx5hws_action_shared_stc { struct mlx5hws_pool_chunk stc_chunk; - u32 refcount; + u32 refcount; /* protected by context ctrl lock */ }; struct mlx5hws_actions_apply_data { @@ -124,7 +124,7 @@ struct mlx5hws_action { struct mlx5hws_context *ctx; union { struct { - struct mlx5hws_pool_chunk stc[MLX5HWS_TABLE_TYPE_MAX]; + struct mlx5hws_pool_chunk stc; union { struct { u32 pat_id; @@ -165,6 +165,9 @@ struct mlx5hws_action { size_t num_dest; struct mlx5hws_cmd_set_fte_dest *dest_list; } dest_array; + struct { + struct mlx5hws_cmd_forward_tbl *fw_island; + } flow_sampler; struct { u8 type; u8 start_anchor; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c index baacf662c0ab..3dbd4efa21a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c @@ -152,6 +152,8 @@ mlx5hws_bwc_matcher_create(struct mlx5hws_table *table, if (!bwc_matcher) return NULL; + atomic_set(&bwc_matcher->num_of_rules, 0); + /* Check if the required match params can be all matched * in single STE, otherwise complex matcher is needed. */ @@ -199,10 +201,12 @@ int mlx5hws_bwc_matcher_destroy_simple(struct mlx5hws_bwc_matcher *bwc_matcher) int mlx5hws_bwc_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher) { - if (bwc_matcher->num_of_rules) + u32 num_of_rules = atomic_read(&bwc_matcher->num_of_rules); + + if (num_of_rules) mlx5hws_err(bwc_matcher->matcher->tbl->ctx, "BWC matcher destroy: matcher still has %d rules\n", - bwc_matcher->num_of_rules); + num_of_rules); mlx5hws_bwc_matcher_destroy_simple(bwc_matcher); @@ -215,6 +219,8 @@ static int hws_bwc_queue_poll(struct mlx5hws_context *ctx, u32 *pending_rules, bool drain) { + unsigned long timeout = jiffies + + msecs_to_jiffies(MLX5HWS_BWC_POLLING_TIMEOUT * MSEC_PER_SEC); struct mlx5hws_flow_op_result comp[MLX5HWS_BWC_MATCHER_REHASH_BURST_TH]; u16 burst_th = hws_bwc_get_burst_th(ctx, queue_id); bool got_comp = *pending_rules >= burst_th; @@ -250,6 +256,11 @@ static int hws_bwc_queue_poll(struct mlx5hws_context *ctx, } got_comp = !!ret; + + if (unlikely(!got_comp && time_after(jiffies, timeout))) { + mlx5hws_err(ctx, "BWC poll error: polling queue %d - TIMEOUT\n", queue_id); + return -ETIMEDOUT; + } } return err; @@ -309,7 +320,7 @@ static void hws_bwc_rule_list_add(struct mlx5hws_bwc_rule *bwc_rule, u16 idx) { struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher; - bwc_matcher->num_of_rules++; + atomic_inc(&bwc_matcher->num_of_rules); bwc_rule->bwc_queue_idx = idx; list_add(&bwc_rule->list_node, &bwc_matcher->rules[idx]); } @@ -318,7 +329,7 @@ static void hws_bwc_rule_list_remove(struct mlx5hws_bwc_rule *bwc_rule) { struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher; - bwc_matcher->num_of_rules--; + atomic_dec(&bwc_matcher->num_of_rules); list_del_init(&bwc_rule->list_node); } @@ -334,22 +345,21 @@ hws_bwc_rule_destroy_hws_sync(struct mlx5hws_bwc_rule *bwc_rule, struct mlx5hws_rule_attr *rule_attr) { struct mlx5hws_context *ctx = bwc_rule->bwc_matcher->matcher->tbl->ctx; - struct mlx5hws_flow_op_result completion; + u32 expected_completions = 1; int ret; ret = hws_bwc_rule_destroy_hws_async(bwc_rule, rule_attr); if (unlikely(ret)) return ret; - do { - ret = mlx5hws_send_queue_poll(ctx, rule_attr->queue_id, &completion, 1); - } while (ret != 1); + ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true); + if (unlikely(ret)) + return ret; - if (unlikely(completion.status != MLX5HWS_FLOW_OP_SUCCESS || - (bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETED && - bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETING))) { - mlx5hws_err(ctx, "Failed destroying BWC rule: completion %d, rule status %d\n", - completion.status, bwc_rule->rule->status); + if (unlikely(bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETED && + bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETING)) { + mlx5hws_err(ctx, "Failed destroying BWC rule: rule status %d\n", + bwc_rule->rule->status); return -EINVAL; } @@ -458,8 +468,22 @@ hws_bwc_matcher_size_maxed_out(struct mlx5hws_bwc_matcher *bwc_matcher) { struct mlx5hws_cmd_query_caps *caps = bwc_matcher->matcher->tbl->ctx->caps; - return bwc_matcher->size_log + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH >= - caps->ste_alloc_log_max - 1; + /* check the match RTC size */ + if ((bwc_matcher->size_log + + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH + + MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP) > + (caps->ste_alloc_log_max - 1)) + return true; + + /* check the action RTC size */ + if ((bwc_matcher->size_log + + MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP + + ilog2(roundup_pow_of_two(bwc_matcher->matcher->action_ste.max_stes)) + + MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT) > + (caps->ste_alloc_log_max - 1)) + return true; + + return false; } static bool @@ -615,8 +639,12 @@ static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_match ret = hws_bwc_queue_poll(ctx, rule_attr.queue_id, &pending_rules[i], false); - if (unlikely(ret)) + if (unlikely(ret)) { + mlx5hws_err(ctx, + "Moving BWC rule failed during rehash (%d)\n", + ret); goto free_bwc_rules; + } } } } while (!all_done); @@ -629,8 +657,11 @@ static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_match mlx5hws_send_engine_flush_queue(&ctx->send_queue[queue_id]); ret = hws_bwc_queue_poll(ctx, queue_id, &pending_rules[i], true); - if (unlikely(ret)) + if (unlikely(ret)) { + mlx5hws_err(ctx, + "Moving BWC rule failed during rehash (%d)\n", ret); goto free_bwc_rules; + } } } @@ -704,7 +735,8 @@ hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher) * Need to check again if we really need rehash. * If the reason for rehash was size, but not any more - skip rehash. */ - if (!hws_bwc_matcher_rehash_size_needed(bwc_matcher, bwc_matcher->num_of_rules)) + if (!hws_bwc_matcher_rehash_size_needed(bwc_matcher, + atomic_read(&bwc_matcher->num_of_rules))) return 0; /* Now we're done all the checking - do the rehash: @@ -797,7 +829,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule, } /* check if number of rules require rehash */ - num_of_rules = bwc_matcher->num_of_rules; + num_of_rules = atomic_read(&bwc_matcher->num_of_rules); if (unlikely(hws_bwc_matcher_rehash_size_needed(bwc_matcher, num_of_rules))) { mutex_unlock(queue_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h index 0b745968e21e..f9f569131dde 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h @@ -8,10 +8,18 @@ #define MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP 1 #define MLX5HWS_BWC_MATCHER_REHASH_PERCENT_TH 70 #define MLX5HWS_BWC_MATCHER_REHASH_BURST_TH 32 -#define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 255 + +/* Max number of AT attach operations for the same matcher. + * When the limit is reached, next attempt to attach new AT + * will result in creation of a new matcher and moving all + * the rules to this matcher. + */ +#define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 8 #define MLX5HWS_BWC_MAX_ACTS 16 +#define MLX5HWS_BWC_POLLING_TIMEOUT 60 + struct mlx5hws_bwc_matcher { struct mlx5hws_matcher *matcher; struct mlx5hws_match_template *mt; @@ -19,7 +27,7 @@ struct mlx5hws_bwc_matcher { u8 num_of_at; u16 priority; u8 size_log; - u32 num_of_rules; /* atomically accessed */ + atomic_t num_of_rules; struct list_head *rules; }; @@ -60,9 +68,11 @@ void mlx5hws_bwc_rule_fill_attr(struct mlx5hws_bwc_matcher *bwc_matcher, static inline u16 mlx5hws_bwc_queues(struct mlx5hws_context *ctx) { /* Besides the control queue, half of the queues are - * reguler HWS queues, and the other half are BWC queues. + * regular HWS queues, and the other half are BWC queues. */ - return (ctx->queues - 1) / 2; + if (mlx5hws_context_bwc_supported(ctx)) + return (ctx->queues - 1) / 2; + return 0; } static inline u16 mlx5hws_bwc_get_queue_id(struct mlx5hws_context *ctx, u16 idx) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c index c00c138c3366..487e75476b0a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c @@ -257,6 +257,12 @@ int mlx5hws_cmd_set_fte(struct mlx5_core_dev *mdev, dest->ext_reformat_id); } break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER: + MLX5_SET(dest_format, in_dests, + destination_type, ifc_dest_type); + MLX5_SET(dest_format, in_dests, destination_id, + dest->destination_id); + break; default: ret = -EOPNOTSUPP; goto out; @@ -359,7 +365,7 @@ void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx, ft_attr->type = fw_ft_type; ft_attr->table_miss_action = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL; - default_miss_tbl = ctx->common_res[type].default_miss->ft_id; + default_miss_tbl = ctx->common_res.default_miss->ft_id; if (!default_miss_tbl) { pr_warn("HWS: no flow table ID for default miss\n"); return; @@ -622,12 +628,12 @@ int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev, u32 pd, u32 *arg_id) { + u32 in[MLX5_ST_SZ_DW(create_modify_header_arg_in)] = {0}; u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0}; - u32 in[MLX5_ST_SZ_DW(create_arg_in)] = {0}; void *attr; int ret; - attr = MLX5_ADDR_OF(create_arg_in, in, hdr); + attr = MLX5_ADDR_OF(create_modify_header_arg_in, in, hdr); MLX5_SET(general_obj_in_cmd_hdr, attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT); MLX5_SET(general_obj_in_cmd_hdr, @@ -635,8 +641,8 @@ int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev, MLX5_SET(general_obj_in_cmd_hdr, attr, op_param.create.log_obj_range, log_obj_range); - attr = MLX5_ADDR_OF(create_arg_in, in, arg); - MLX5_SET(arg, attr, access_pd, pd); + attr = MLX5_ADDR_OF(create_modify_header_arg_in, in, arg); + MLX5_SET(modify_header_arg, attr, access_pd, pd); ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); if (ret) { @@ -812,7 +818,7 @@ int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev, struct mlx5hws_cmd_packet_reformat_create_attr *attr, u32 *reformat_id) { - u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_out)] = {0}; + u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)] = {0}; size_t insz, cmd_data_sz, cmd_total_sz; void *prctx; void *pdata; @@ -845,7 +851,7 @@ int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev, goto out; } - *reformat_id = MLX5_GET(alloc_packet_reformat_out, out, packet_reformat_id); + *reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id); out: kfree(in); return ret; @@ -854,13 +860,13 @@ out: int mlx5hws_cmd_packet_reformat_destroy(struct mlx5_core_dev *mdev, u32 reformat_id) { - u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_out)] = {0}; - u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)] = {0}; + u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {0}; int ret; - MLX5_SET(dealloc_packet_reformat_in, in, opcode, + MLX5_SET(dealloc_packet_reformat_context_in, in, opcode, MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT); - MLX5_SET(dealloc_packet_reformat_in, in, + MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id, reformat_id); ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); @@ -889,73 +895,6 @@ int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn) return ret; } -int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev, - struct mlx5hws_cmd_allow_other_vhca_access_attr *attr) -{ - u32 out[MLX5_ST_SZ_DW(allow_other_vhca_access_out)] = {0}; - u32 in[MLX5_ST_SZ_DW(allow_other_vhca_access_in)] = {0}; - void *key; - int ret; - - MLX5_SET(allow_other_vhca_access_in, - in, opcode, MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS); - MLX5_SET(allow_other_vhca_access_in, - in, object_type_to_be_accessed, attr->obj_type); - MLX5_SET(allow_other_vhca_access_in, - in, object_id_to_be_accessed, attr->obj_id); - - key = MLX5_ADDR_OF(allow_other_vhca_access_in, in, access_key); - memcpy(key, attr->access_key, sizeof(attr->access_key)); - - ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); - if (ret) - mlx5_core_err(mdev, "Failed to execute ALLOW_OTHER_VHCA_ACCESS command\n"); - - return ret; -} - -int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev, - struct mlx5hws_cmd_alias_obj_create_attr *alias_attr, - u32 *obj_id) -{ - u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0}; - u32 in[MLX5_ST_SZ_DW(create_alias_obj_in)] = {0}; - void *attr; - void *key; - int ret; - - attr = MLX5_ADDR_OF(create_alias_obj_in, in, hdr); - MLX5_SET(general_obj_in_cmd_hdr, - attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT); - MLX5_SET(general_obj_in_cmd_hdr, - attr, obj_type, alias_attr->obj_type); - MLX5_SET(general_obj_in_cmd_hdr, attr, op_param.create.alias_object, 1); - - attr = MLX5_ADDR_OF(create_alias_obj_in, in, alias_ctx); - MLX5_SET(alias_context, attr, vhca_id_to_be_accessed, alias_attr->vhca_id); - MLX5_SET(alias_context, attr, object_id_to_be_accessed, alias_attr->obj_id); - - key = MLX5_ADDR_OF(alias_context, attr, access_key); - memcpy(key, alias_attr->access_key, sizeof(alias_attr->access_key)); - - ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); - if (ret) { - mlx5_core_err(mdev, "Failed to create ALIAS OBJ\n"); - goto out; - } - - *obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); -out: - return ret; -} - -int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev, - u16 obj_type, - u32 obj_id) -{ - return hws_cmd_general_obj_destroy(mdev, obj_type, obj_id); -} - int mlx5hws_cmd_generate_wqe(struct mlx5_core_dev *mdev, struct mlx5hws_cmd_generate_wqe_attr *attr, struct mlx5_cqe64 *ret_cqe) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h index 434f62b0904e..610c63d81ad9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h @@ -63,7 +63,7 @@ struct mlx5hws_cmd_forward_tbl { u8 type; u32 ft_id; u32 fg_id; - u32 refcount; + u32 refcount; /* protected by context ctrl lock */ }; struct mlx5hws_cmd_rtc_create_attr { @@ -334,14 +334,6 @@ mlx5hws_cmd_forward_tbl_create(struct mlx5_core_dev *mdev, void mlx5hws_cmd_forward_tbl_destroy(struct mlx5_core_dev *mdev, struct mlx5hws_cmd_forward_tbl *tbl); -int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev, - struct mlx5hws_cmd_alias_obj_create_attr *alias_attr, - u32 *obj_id); - -int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev, - u16 obj_type, - u32 obj_id); - int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn); int mlx5hws_cmd_query_caps(struct mlx5_core_dev *mdev, @@ -352,9 +344,6 @@ void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx, enum mlx5hws_table_type type, struct mlx5hws_cmd_ft_modify_attr *ft_attr); -int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev, - struct mlx5hws_cmd_allow_other_vhca_access_attr *attr); - int mlx5hws_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_function, u16 vport_number, u16 *gvmi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c index fd48b05e91e0..9cda2774fd64 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c @@ -23,7 +23,6 @@ static int hws_context_pools_init(struct mlx5hws_context *ctx) struct mlx5hws_pool_attr pool_attr = {0}; u8 max_log_sz; int ret; - int i; ret = mlx5hws_pat_init_pattern_cache(&ctx->pattern_cache); if (ret) @@ -39,23 +38,17 @@ static int hws_context_pools_init(struct mlx5hws_context *ctx) max_log_sz = min(MLX5HWS_POOL_STC_LOG_SZ, ctx->caps->stc_alloc_log_max); pool_attr.alloc_log_sz = max(max_log_sz, ctx->caps->stc_alloc_log_gran); - for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) { - pool_attr.table_type = i; - ctx->stc_pool[i] = mlx5hws_pool_create(ctx, &pool_attr); - if (!ctx->stc_pool[i]) { - mlx5hws_err(ctx, "Failed to allocate STC pool [%d]", i); - ret = -ENOMEM; - goto free_stc_pools; - } + pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB; + ctx->stc_pool = mlx5hws_pool_create(ctx, &pool_attr); + if (!ctx->stc_pool) { + mlx5hws_err(ctx, "Failed to allocate STC pool\n"); + ret = -ENOMEM; + goto uninit_cache; } return 0; -free_stc_pools: - for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) - if (ctx->stc_pool[i]) - mlx5hws_pool_destroy(ctx->stc_pool[i]); - +uninit_cache: mlx5hws_definer_uninit_cache(ctx->definer_cache); uninit_pat_cache: mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache); @@ -64,12 +57,8 @@ uninit_pat_cache: static void hws_context_pools_uninit(struct mlx5hws_context *ctx) { - int i; - - for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) { - if (ctx->stc_pool[i]) - mlx5hws_pool_destroy(ctx->stc_pool[i]); - } + if (ctx->stc_pool) + mlx5hws_pool_destroy(ctx->stc_pool); mlx5hws_definer_uninit_cache(ctx->definer_cache); mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache); @@ -161,8 +150,10 @@ static int hws_context_init_hws(struct mlx5hws_context *ctx, if (ret) goto uninit_pd; - if (attr->bwc) - ctx->flags |= MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT; + /* Context has support for backward compatible API, + * and does not have support for native HWS API. + */ + ctx->flags |= MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT; ret = mlx5hws_send_queues_open(ctx, attr->queues, attr->queue_size); if (ret) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h index 47f5cc8de73f..38c3647444ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h @@ -8,6 +8,7 @@ enum mlx5hws_context_flags { MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT = 1 << 0, MLX5HWS_CONTEXT_FLAG_PRIVATE_PD = 1 << 1, MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT = 1 << 2, + MLX5HWS_CONTEXT_FLAG_NATIVE_SUPPORT = 1 << 3, }; enum mlx5hws_context_shared_stc_type { @@ -37,8 +38,8 @@ struct mlx5hws_context { struct mlx5_core_dev *mdev; struct mlx5hws_cmd_query_caps *caps; u32 pd_num; - struct mlx5hws_pool *stc_pool[MLX5HWS_TABLE_TYPE_MAX]; - struct mlx5hws_context_common_res common_res[MLX5HWS_TABLE_TYPE_MAX]; + struct mlx5hws_pool *stc_pool; + struct mlx5hws_context_common_res common_res; struct mlx5hws_pattern_cache *pattern_cache; struct mlx5hws_definer_cache *definer_cache; struct mutex ctrl_lock; /* control lock to protect the whole context */ @@ -58,6 +59,11 @@ static inline bool mlx5hws_context_bwc_supported(struct mlx5hws_context *ctx) return ctx->flags & MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT; } +static inline bool mlx5hws_context_native_supported(struct mlx5hws_context *ctx) +{ + return ctx->flags & MLX5HWS_CONTEXT_FLAG_NATIVE_SUPPORT; +} + bool mlx5hws_context_cap_dynamic_reparse(struct mlx5hws_context *ctx); u8 mlx5hws_context_get_reparse_mode(struct mlx5hws_context *ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c index 5b200b4bc1a8..696275fd0ce2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c @@ -148,8 +148,8 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma matcher->match_ste.rtc_1_id, (int)ste_1_id); - ste = &matcher->action_ste[0].ste; - ste_pool = matcher->action_ste[0].pool; + ste = &matcher->action_ste.ste; + ste_pool = matcher->action_ste.pool; if (ste_pool) { ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste); if (tbl_type == MLX5HWS_TABLE_TYPE_FDB) @@ -171,10 +171,8 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma return ret; seq_printf(f, ",%d,%d,%d,%d,%d,0x%llx,0x%llx\n", - matcher->action_ste[0].rtc_0_id, - (int)ste_0_id, - matcher->action_ste[0].rtc_1_id, - (int)ste_1_id, + matcher->action_ste.rtc_0_id, (int)ste_0_id, + matcher->action_ste.rtc_1_id, (int)ste_1_id, 0, mlx5hws_debug_icm_to_idx(icm_addr_0), mlx5hws_debug_icm_to_idx(icm_addr_1)); @@ -368,9 +366,10 @@ static int hws_debug_dump_context_info(struct seq_file *f, struct mlx5hws_contex static int hws_debug_dump_context_stc_resource(struct seq_file *f, struct mlx5hws_context *ctx, - u32 tbl_type, struct mlx5hws_pool_resource *resource) { + u32 tbl_type = MLX5HWS_TABLE_TYPE_BASE + MLX5HWS_TABLE_TYPE_FDB; + seq_printf(f, "%d,0x%llx,%u,%u\n", MLX5HWS_DEBUG_RES_TYPE_CONTEXT_STC, HWS_PTR_TO_ID(ctx), @@ -382,31 +381,22 @@ static int hws_debug_dump_context_stc_resource(struct seq_file *f, static int hws_debug_dump_context_stc(struct seq_file *f, struct mlx5hws_context *ctx) { - struct mlx5hws_pool *stc_pool; - u32 table_type; + struct mlx5hws_pool *stc_pool = ctx->stc_pool; int ret; - int i; - for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) { - stc_pool = ctx->stc_pool[i]; - table_type = MLX5HWS_TABLE_TYPE_BASE + i; + if (!stc_pool) + return 0; - if (!stc_pool) - continue; + if (stc_pool->resource[0]) { + ret = hws_debug_dump_context_stc_resource(f, ctx, stc_pool->resource[0]); + if (ret) + return ret; + } - if (stc_pool->resource[0]) { - ret = hws_debug_dump_context_stc_resource(f, ctx, table_type, - stc_pool->resource[0]); - if (ret) - return ret; - } - - if (i == MLX5HWS_TABLE_TYPE_FDB && stc_pool->mirror_resource[0]) { - ret = hws_debug_dump_context_stc_resource(f, ctx, table_type, - stc_pool->mirror_resource[0]); - if (ret) - return ret; - } + if (stc_pool->mirror_resource[0]) { + ret = hws_debug_dump_context_stc_resource(f, ctx, stc_pool->mirror_resource[0]); + if (ret) + return ret; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c index 8fe96eb76baf..10ece7df1cfa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c @@ -70,7 +70,7 @@ u32 second_dw_mask = (mask) & ((1 << _bit_off) - 1); \ _HWS_SET32(p, (v) >> _bit_off, byte_off, 0, (mask) >> _bit_off); \ _HWS_SET32(p, (v) & second_dw_mask, (byte_off) + DW_SIZE, \ - (bit_off) % BITS_IN_DW, second_dw_mask); \ + (bit_off + BITS_IN_DW) % BITS_IN_DW, second_dw_mask); \ } else { \ _HWS_SET32(p, v, byte_off, (bit_off), (mask)); \ } \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h index 9432d5084def..5c1a2086efba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h @@ -785,7 +785,7 @@ struct mlx5hws_definer_cache { struct mlx5hws_definer_cache_item { struct mlx5hws_definer definer; - u32 refcount; + u32 refcount; /* protected by context ctrl lock */ struct list_head list_node; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c new file mode 100644 index 000000000000..f34bbbbba1c2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c @@ -0,0 +1,1377 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */ + +#include +#include +#include +#include +#include "fs_hws_pools.h" +#include "mlx5hws.h" + +#define MLX5HWS_CTX_MAX_NUM_OF_QUEUES 16 +#define MLX5HWS_CTX_QUEUE_SIZE 256 + +static struct mlx5hws_action * +mlx5_fs_create_action_remove_header_vlan(struct mlx5hws_context *ctx); +static void +mlx5_fs_destroy_pr_pool(struct mlx5_fs_pool *pool, struct xarray *pr_pools, + unsigned long index); +static void +mlx5_fs_destroy_mh_pool(struct mlx5_fs_pool *pool, struct xarray *mh_pools, + unsigned long index); + +static int mlx5_fs_init_hws_actions_pool(struct mlx5_core_dev *dev, + struct mlx5_fs_hws_context *fs_ctx) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_fs_hws_actions_pool *hws_pool = &fs_ctx->hws_pool; + struct mlx5hws_action_reformat_header reformat_hdr = {}; + struct mlx5hws_context *ctx = fs_ctx->hws_ctx; + enum mlx5hws_action_type action_type; + int err = -ENOSPC; + + hws_pool->tag_action = mlx5hws_action_create_tag(ctx, flags); + if (!hws_pool->tag_action) + return err; + hws_pool->pop_vlan_action = mlx5hws_action_create_pop_vlan(ctx, flags); + if (!hws_pool->pop_vlan_action) + goto destroy_tag; + hws_pool->push_vlan_action = mlx5hws_action_create_push_vlan(ctx, flags); + if (!hws_pool->push_vlan_action) + goto destroy_pop_vlan; + hws_pool->drop_action = mlx5hws_action_create_dest_drop(ctx, flags); + if (!hws_pool->drop_action) + goto destroy_push_vlan; + action_type = MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2; + hws_pool->decapl2_action = + mlx5hws_action_create_reformat(ctx, action_type, 1, + &reformat_hdr, 0, flags); + if (!hws_pool->decapl2_action) + goto destroy_drop; + hws_pool->remove_hdr_vlan_action = + mlx5_fs_create_action_remove_header_vlan(ctx); + if (!hws_pool->remove_hdr_vlan_action) + goto destroy_decapl2; + err = mlx5_fs_hws_pr_pool_init(&hws_pool->insert_hdr_pool, dev, 0, + MLX5HWS_ACTION_TYP_INSERT_HEADER); + if (err) + goto destroy_remove_hdr; + err = mlx5_fs_hws_pr_pool_init(&hws_pool->dl3tnltol2_pool, dev, 0, + MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2); + if (err) + goto cleanup_insert_hdr; + xa_init(&hws_pool->el2tol3tnl_pools); + xa_init(&hws_pool->el2tol2tnl_pools); + xa_init(&hws_pool->mh_pools); + xa_init(&hws_pool->table_dests); + xa_init(&hws_pool->vport_dests); + xa_init(&hws_pool->vport_vhca_dests); + return 0; + +cleanup_insert_hdr: + mlx5_fs_hws_pr_pool_cleanup(&hws_pool->insert_hdr_pool); +destroy_remove_hdr: + mlx5hws_action_destroy(hws_pool->remove_hdr_vlan_action); +destroy_decapl2: + mlx5hws_action_destroy(hws_pool->decapl2_action); +destroy_drop: + mlx5hws_action_destroy(hws_pool->drop_action); +destroy_push_vlan: + mlx5hws_action_destroy(hws_pool->push_vlan_action); +destroy_pop_vlan: + mlx5hws_action_destroy(hws_pool->pop_vlan_action); +destroy_tag: + mlx5hws_action_destroy(hws_pool->tag_action); + return err; +} + +static void mlx5_fs_cleanup_hws_actions_pool(struct mlx5_fs_hws_context *fs_ctx) +{ + struct mlx5_fs_hws_actions_pool *hws_pool = &fs_ctx->hws_pool; + struct mlx5hws_action *action; + struct mlx5_fs_pool *pool; + unsigned long i; + + xa_for_each(&hws_pool->vport_vhca_dests, i, action) + mlx5hws_action_destroy(action); + xa_destroy(&hws_pool->vport_vhca_dests); + xa_for_each(&hws_pool->vport_dests, i, action) + mlx5hws_action_destroy(action); + xa_destroy(&hws_pool->vport_dests); + xa_destroy(&hws_pool->table_dests); + xa_for_each(&hws_pool->mh_pools, i, pool) + mlx5_fs_destroy_mh_pool(pool, &hws_pool->mh_pools, i); + xa_destroy(&hws_pool->mh_pools); + xa_for_each(&hws_pool->el2tol2tnl_pools, i, pool) + mlx5_fs_destroy_pr_pool(pool, &hws_pool->el2tol2tnl_pools, i); + xa_destroy(&hws_pool->el2tol2tnl_pools); + xa_for_each(&hws_pool->el2tol3tnl_pools, i, pool) + mlx5_fs_destroy_pr_pool(pool, &hws_pool->el2tol3tnl_pools, i); + xa_destroy(&hws_pool->el2tol3tnl_pools); + mlx5_fs_hws_pr_pool_cleanup(&hws_pool->dl3tnltol2_pool); + mlx5_fs_hws_pr_pool_cleanup(&hws_pool->insert_hdr_pool); + mlx5hws_action_destroy(hws_pool->remove_hdr_vlan_action); + mlx5hws_action_destroy(hws_pool->decapl2_action); + mlx5hws_action_destroy(hws_pool->drop_action); + mlx5hws_action_destroy(hws_pool->push_vlan_action); + mlx5hws_action_destroy(hws_pool->pop_vlan_action); + mlx5hws_action_destroy(hws_pool->tag_action); +} + +static int mlx5_cmd_hws_create_ns(struct mlx5_flow_root_namespace *ns) +{ + struct mlx5hws_context_attr hws_ctx_attr = {}; + int err; + + hws_ctx_attr.queues = min_t(int, num_online_cpus(), + MLX5HWS_CTX_MAX_NUM_OF_QUEUES); + hws_ctx_attr.queue_size = MLX5HWS_CTX_QUEUE_SIZE; + + ns->fs_hws_context.hws_ctx = + mlx5hws_context_open(ns->dev, &hws_ctx_attr); + if (!ns->fs_hws_context.hws_ctx) { + mlx5_core_err(ns->dev, "Failed to create hws flow namespace\n"); + return -EINVAL; + } + err = mlx5_fs_init_hws_actions_pool(ns->dev, &ns->fs_hws_context); + if (err) { + mlx5_core_err(ns->dev, "Failed to init hws actions pool\n"); + mlx5hws_context_close(ns->fs_hws_context.hws_ctx); + return err; + } + return 0; +} + +static int mlx5_cmd_hws_destroy_ns(struct mlx5_flow_root_namespace *ns) +{ + mlx5_fs_cleanup_hws_actions_pool(&ns->fs_hws_context); + return mlx5hws_context_close(ns->fs_hws_context.hws_ctx); +} + +static int mlx5_cmd_hws_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns, + u16 peer_vhca_id) +{ + struct mlx5hws_context *peer_ctx = NULL; + + if (peer_ns) + peer_ctx = peer_ns->fs_hws_context.hws_ctx; + mlx5hws_context_set_peer(ns->fs_hws_context.hws_ctx, peer_ctx, + peer_vhca_id); + return 0; +} + +static int mlx5_fs_set_ft_default_miss(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table *next_ft) +{ + struct mlx5hws_table *next_tbl; + int err; + + if (!ns->fs_hws_context.hws_ctx) + return -EINVAL; + + /* if no change required, return */ + if (!next_ft && !ft->fs_hws_table.miss_ft_set) + return 0; + + next_tbl = next_ft ? next_ft->fs_hws_table.hws_table : NULL; + err = mlx5hws_table_set_default_miss(ft->fs_hws_table.hws_table, next_tbl); + if (err) { + mlx5_core_err(ns->dev, "Failed setting FT default miss (%d)\n", err); + return err; + } + ft->fs_hws_table.miss_ft_set = !!next_tbl; + return 0; +} + +static int mlx5_fs_add_flow_table_dest_action(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context; + struct mlx5hws_action *dest_ft_action; + struct xarray *dests_xa; + int err; + + dest_ft_action = mlx5hws_action_create_dest_table_num(fs_ctx->hws_ctx, + ft->id, flags); + if (!dest_ft_action) { + mlx5_core_err(ns->dev, "Failed creating dest table action\n"); + return -ENOMEM; + } + + dests_xa = &fs_ctx->hws_pool.table_dests; + err = xa_insert(dests_xa, ft->id, dest_ft_action, GFP_KERNEL); + if (err) + mlx5hws_action_destroy(dest_ft_action); + return err; +} + +static int mlx5_fs_del_flow_table_dest_action(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft) +{ + struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context; + struct mlx5hws_action *dest_ft_action; + struct xarray *dests_xa; + int err; + + dests_xa = &fs_ctx->hws_pool.table_dests; + dest_ft_action = xa_erase(dests_xa, ft->id); + if (!dest_ft_action) { + mlx5_core_err(ns->dev, "Failed to erase dest ft action\n"); + return -ENOENT; + } + + err = mlx5hws_action_destroy(dest_ft_action); + if (err) + mlx5_core_err(ns->dev, "Failed to destroy dest ft action\n"); + return err; +} + +static int mlx5_cmd_hws_create_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table_attr *ft_attr, + struct mlx5_flow_table *next_ft) +{ + struct mlx5hws_context *ctx = ns->fs_hws_context.hws_ctx; + struct mlx5hws_table_attr tbl_attr = {}; + struct mlx5hws_table *tbl; + int err; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) { + err = mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, ft_attr, + next_ft); + if (err) + return err; + err = mlx5_fs_add_flow_table_dest_action(ns, ft); + if (err) + mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft); + return err; + } + + if (ns->table_type != FS_FT_FDB) { + mlx5_core_err(ns->dev, "Table type %d not supported for HWS\n", + ns->table_type); + return -EOPNOTSUPP; + } + + tbl_attr.type = MLX5HWS_TABLE_TYPE_FDB; + tbl_attr.level = ft_attr->level; + tbl = mlx5hws_table_create(ctx, &tbl_attr); + if (!tbl) { + mlx5_core_err(ns->dev, "Failed creating hws flow_table\n"); + return -EINVAL; + } + + ft->fs_hws_table.hws_table = tbl; + ft->id = mlx5hws_table_get_id(tbl); + + if (next_ft) { + err = mlx5_fs_set_ft_default_miss(ns, ft, next_ft); + if (err) + goto destroy_table; + } + + ft->max_fte = INT_MAX; + + err = mlx5_fs_add_flow_table_dest_action(ns, ft); + if (err) + goto clear_ft_miss; + return 0; + +clear_ft_miss: + mlx5_fs_set_ft_default_miss(ns, ft, NULL); +destroy_table: + mlx5hws_table_destroy(tbl); + ft->fs_hws_table.hws_table = NULL; + return err; +} + +static int mlx5_cmd_hws_destroy_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft) +{ + int err; + + err = mlx5_fs_del_flow_table_dest_action(ns, ft); + if (err) + mlx5_core_err(ns->dev, "Failed to remove dest action (%d)\n", err); + + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft); + + err = mlx5_fs_set_ft_default_miss(ns, ft, NULL); + if (err) + mlx5_core_err(ns->dev, "Failed to disconnect next table (%d)\n", err); + + err = mlx5hws_table_destroy(ft->fs_hws_table.hws_table); + if (err) + mlx5_core_err(ns->dev, "Failed to destroy flow_table (%d)\n", err); + + return err; +} + +static int mlx5_cmd_hws_modify_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table *next_ft) +{ + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->modify_flow_table(ns, ft, next_ft); + + return mlx5_fs_set_ft_default_miss(ns, ft, next_ft); +} + +static int mlx5_cmd_hws_update_root_ft(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + u32 underlay_qpn, + bool disconnect) +{ + return mlx5_fs_cmd_get_fw_cmds()->update_root_ft(ns, ft, underlay_qpn, + disconnect); +} + +static int mlx5_cmd_hws_create_flow_group(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, u32 *in, + struct mlx5_flow_group *fg) +{ + struct mlx5hws_match_parameters mask; + struct mlx5hws_bwc_matcher *matcher; + u8 match_criteria_enable; + u32 priority; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in, fg); + + mask.match_buf = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + mask.match_sz = sizeof(fg->mask.match_criteria); + + match_criteria_enable = MLX5_GET(create_flow_group_in, in, + match_criteria_enable); + priority = MLX5_GET(create_flow_group_in, in, start_flow_index); + matcher = mlx5hws_bwc_matcher_create(ft->fs_hws_table.hws_table, + priority, match_criteria_enable, + &mask); + if (!matcher) { + mlx5_core_err(ns->dev, "Failed creating matcher\n"); + return -EINVAL; + } + + fg->fs_hws_matcher.matcher = matcher; + return 0; +} + +static int mlx5_cmd_hws_destroy_flow_group(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *fg) +{ + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg); + + return mlx5hws_bwc_matcher_destroy(fg->fs_hws_matcher.matcher); +} + +static struct mlx5hws_action * +mlx5_fs_get_dest_action_ft(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_flow_rule *dst) +{ + return xa_load(&fs_ctx->hws_pool.table_dests, dst->dest_attr.ft->id); +} + +static struct mlx5hws_action * +mlx5_fs_get_dest_action_table_num(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_flow_rule *dst) +{ + u32 table_num = dst->dest_attr.ft_num; + + return xa_load(&fs_ctx->hws_pool.table_dests, table_num); +} + +static struct mlx5hws_action * +mlx5_fs_create_dest_action_table_num(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_flow_rule *dst) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5hws_context *ctx = fs_ctx->hws_ctx; + u32 table_num = dst->dest_attr.ft_num; + + return mlx5hws_action_create_dest_table_num(ctx, table_num, flags); +} + +static struct mlx5hws_action * +mlx5_fs_get_dest_action_vport(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_flow_rule *dst, + bool is_dest_type_uplink) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_flow_destination *dest_attr = &dst->dest_attr; + struct mlx5hws_context *ctx = fs_ctx->hws_ctx; + struct mlx5hws_action *dest; + struct xarray *dests_xa; + bool vhca_id_valid; + unsigned long idx; + u16 vport_num; + int err; + + vhca_id_valid = is_dest_type_uplink || + (dest_attr->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID); + vport_num = is_dest_type_uplink ? MLX5_VPORT_UPLINK : dest_attr->vport.num; + if (vhca_id_valid) { + dests_xa = &fs_ctx->hws_pool.vport_vhca_dests; + idx = (unsigned long)dest_attr->vport.vhca_id << 16 | vport_num; + } else { + dests_xa = &fs_ctx->hws_pool.vport_dests; + idx = vport_num; + } +dest_load: + dest = xa_load(dests_xa, idx); + if (dest) + return dest; + + dest = mlx5hws_action_create_dest_vport(ctx, vport_num, vhca_id_valid, + dest_attr->vport.vhca_id, flags); + + err = xa_insert(dests_xa, idx, dest, GFP_KERNEL); + if (err) { + mlx5hws_action_destroy(dest); + dest = NULL; + + if (err == -EBUSY) + /* xarray entry was already stored by another thread */ + goto dest_load; + } + + return dest; +} + +static struct mlx5hws_action * +mlx5_fs_create_dest_action_range(struct mlx5hws_context *ctx, + struct mlx5_flow_rule *dst) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_flow_destination *dest_attr = &dst->dest_attr; + + return mlx5hws_action_create_dest_match_range(ctx, + dest_attr->range.field, + dest_attr->range.hit_ft, + dest_attr->range.miss_ft, + dest_attr->range.min, + dest_attr->range.max, + flags); +} + +static struct mlx5hws_action * +mlx5_fs_create_action_dest_array(struct mlx5hws_context *ctx, + struct mlx5hws_action_dest_attr *dests, + u32 num_of_dests, bool ignore_flow_level, + u32 flow_source) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + + return mlx5hws_action_create_dest_array(ctx, num_of_dests, dests, + ignore_flow_level, + flow_source, flags); +} + +static struct mlx5hws_action * +mlx5_fs_get_action_push_vlan(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.push_vlan_action; +} + +static u32 mlx5_fs_calc_vlan_hdr(struct mlx5_fs_vlan *vlan) +{ + u16 n_ethtype = vlan->ethtype; + u8 prio = vlan->prio; + u16 vid = vlan->vid; + + return (u32)n_ethtype << 16 | (u32)(prio) << 12 | (u32)vid; +} + +static struct mlx5hws_action * +mlx5_fs_get_action_pop_vlan(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.pop_vlan_action; +} + +static struct mlx5hws_action * +mlx5_fs_get_action_decap_tnl_l2_to_l2(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.decapl2_action; +} + +static struct mlx5hws_action * +mlx5_fs_get_dest_action_drop(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.drop_action; +} + +static struct mlx5hws_action * +mlx5_fs_get_action_tag(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.tag_action; +} + +static struct mlx5hws_action * +mlx5_fs_create_action_last(struct mlx5hws_context *ctx) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + + return mlx5hws_action_create_last(ctx, flags); +} + +static void mlx5_fs_destroy_fs_action(struct mlx5_fs_hws_rule_action *fs_action) +{ + switch (mlx5hws_action_get_type(fs_action->action)) { + case MLX5HWS_ACTION_TYP_CTR: + mlx5_fc_put_hws_action(fs_action->counter); + break; + default: + mlx5hws_action_destroy(fs_action->action); + } +} + +static void +mlx5_fs_destroy_fs_actions(struct mlx5_fs_hws_rule_action **fs_actions, + int *num_fs_actions) +{ + int i; + + /* Free in reverse order to handle action dependencies */ + for (i = *num_fs_actions - 1; i >= 0; i--) + mlx5_fs_destroy_fs_action(*fs_actions + i); + *num_fs_actions = 0; + kfree(*fs_actions); + *fs_actions = NULL; +} + +/* Splits FTE's actions into cached, rule and destination actions. + * The cached and destination actions are saved on the fte hws rule. + * The rule actions are returned as a parameter, together with their count. + * We want to support a rule with 32 destinations, which means we need to + * account for 32 destinations plus usually a counter plus one more action + * for a multi-destination flow table. + * 32 is SW limitation for array size, keep. HWS limitation is 16M STEs per matcher + */ +#define MLX5_FLOW_CONTEXT_ACTION_MAX 34 +static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + struct fs_fte *fte, + struct mlx5hws_rule_action **ractions) +{ + struct mlx5_flow_act *fte_action = &fte->act_dests.action; + struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context; + struct mlx5hws_action_dest_attr *dest_actions; + struct mlx5hws_context *ctx = fs_ctx->hws_ctx; + struct mlx5_fs_hws_rule_action *fs_actions; + struct mlx5_core_dev *dev = ns->dev; + struct mlx5hws_action *dest_action; + struct mlx5hws_action *tmp_action; + struct mlx5_fs_hws_pr *pr_data; + struct mlx5_fs_hws_mh *mh_data; + bool delay_encap_set = false; + struct mlx5_flow_rule *dst; + int num_dest_actions = 0; + int num_fs_actions = 0; + int num_actions = 0; + int err; + + *ractions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(**ractions), + GFP_KERNEL); + if (!*ractions) { + err = -ENOMEM; + goto out_err; + } + + fs_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, + sizeof(*fs_actions), GFP_KERNEL); + if (!fs_actions) { + err = -ENOMEM; + goto free_actions_alloc; + } + + dest_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, + sizeof(*dest_actions), GFP_KERNEL); + if (!dest_actions) { + err = -ENOMEM; + goto free_fs_actions_alloc; + } + + /* The order of the actions are must to be kept, only the following + * order is supported by HW steering: + * HWS: decap -> remove_hdr -> pop_vlan -> modify header -> push_vlan + * -> reformat (insert_hdr/encap) -> ctr -> tag -> aso + * -> drop -> FWD:tbl/vport/sampler/tbl_num/range -> dest_array -> last + */ + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + tmp_action = mlx5_fs_get_action_decap_tnl_l2_to_l2(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_dest_actions_alloc; + } + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) { + int reformat_type = fte_action->pkt_reformat->reformat_type; + + if (fte_action->pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_FW) { + mlx5_core_err(dev, "FW-owned reformat can't be used in HWS rule\n"); + err = -EINVAL; + goto free_actions; + } + + if (reformat_type == MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2) { + pr_data = fte_action->pkt_reformat->fs_hws_action.pr_data; + (*ractions)[num_actions].reformat.offset = pr_data->offset; + (*ractions)[num_actions].reformat.hdr_idx = pr_data->hdr_idx; + (*ractions)[num_actions].reformat.data = pr_data->data; + (*ractions)[num_actions++].action = + fte_action->pkt_reformat->fs_hws_action.hws_action; + } else if (reformat_type == MLX5_REFORMAT_TYPE_REMOVE_HDR) { + (*ractions)[num_actions++].action = + fte_action->pkt_reformat->fs_hws_action.hws_action; + } else { + delay_encap_set = true; + } + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) { + tmp_action = mlx5_fs_get_action_pop_vlan(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) { + tmp_action = mlx5_fs_get_action_pop_vlan(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + mh_data = fte_action->modify_hdr->fs_hws_action.mh_data; + (*ractions)[num_actions].modify_header.offset = mh_data->offset; + (*ractions)[num_actions].modify_header.data = mh_data->data; + (*ractions)[num_actions++].action = + fte_action->modify_hdr->fs_hws_action.hws_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { + tmp_action = mlx5_fs_get_action_push_vlan(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions].push_vlan.vlan_hdr = + htonl(mlx5_fs_calc_vlan_hdr(&fte_action->vlan[0])); + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) { + tmp_action = mlx5_fs_get_action_push_vlan(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions].push_vlan.vlan_hdr = + htonl(mlx5_fs_calc_vlan_hdr(&fte_action->vlan[1])); + (*ractions)[num_actions++].action = tmp_action; + } + + if (delay_encap_set) { + pr_data = fte_action->pkt_reformat->fs_hws_action.pr_data; + (*ractions)[num_actions].reformat.offset = pr_data->offset; + (*ractions)[num_actions].reformat.data = pr_data->data; + (*ractions)[num_actions++].action = + fte_action->pkt_reformat->fs_hws_action.hws_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + list_for_each_entry(dst, &fte->node.children, node.list) { + struct mlx5_fc *counter; + + if (dst->dest_attr.type != + MLX5_FLOW_DESTINATION_TYPE_COUNTER) + continue; + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + + counter = dst->dest_attr.counter; + tmp_action = mlx5_fc_get_hws_action(ctx, counter); + if (!tmp_action) { + err = -EINVAL; + goto free_actions; + } + + (*ractions)[num_actions].counter.offset = + mlx5_fc_id(counter) - mlx5_fc_get_base_id(counter); + (*ractions)[num_actions++].action = tmp_action; + fs_actions[num_fs_actions].action = tmp_action; + fs_actions[num_fs_actions++].counter = counter; + } + } + + if (fte->act_dests.flow_context.flow_tag) { + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + tmp_action = mlx5_fs_get_action_tag(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions].tag.value = fte->act_dests.flow_context.flow_tag; + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) { + err = -EOPNOTSUPP; + goto free_actions; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_DROP) { + dest_action = mlx5_fs_get_dest_action_drop(fs_ctx); + if (!dest_action) { + err = -ENOMEM; + goto free_actions; + } + dest_actions[num_dest_actions++].dest = dest_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { + list_for_each_entry(dst, &fte->node.children, node.list) { + struct mlx5_flow_destination *attr = &dst->dest_attr; + bool type_uplink = + attr->type == MLX5_FLOW_DESTINATION_TYPE_UPLINK; + + if (num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || + num_dest_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + if (attr->type == MLX5_FLOW_DESTINATION_TYPE_COUNTER) + continue; + + switch (attr->type) { + case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: + dest_action = mlx5_fs_get_dest_action_ft(fs_ctx, dst); + break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM: + dest_action = mlx5_fs_get_dest_action_table_num(fs_ctx, + dst); + if (dest_action) + break; + dest_action = mlx5_fs_create_dest_action_table_num(fs_ctx, + dst); + fs_actions[num_fs_actions++].action = dest_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_RANGE: + dest_action = mlx5_fs_create_dest_action_range(ctx, dst); + fs_actions[num_fs_actions++].action = dest_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_UPLINK: + case MLX5_FLOW_DESTINATION_TYPE_VPORT: + dest_action = mlx5_fs_get_dest_action_vport(fs_ctx, dst, + type_uplink); + break; + default: + err = -EOPNOTSUPP; + goto free_actions; + } + if (!dest_action) { + err = -ENOMEM; + goto free_actions; + } + dest_actions[num_dest_actions++].dest = dest_action; + } + } + + if (num_dest_actions == 1) { + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + (*ractions)[num_actions++].action = dest_actions->dest; + } else if (num_dest_actions > 1) { + u32 flow_source = fte->act_dests.flow_context.flow_source; + bool ignore_flow_level; + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || + num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + ignore_flow_level = + !!(fte_action->flags & FLOW_ACT_IGNORE_FLOW_LEVEL); + tmp_action = mlx5_fs_create_action_dest_array(ctx, dest_actions, + num_dest_actions, + ignore_flow_level, + flow_source); + if (!tmp_action) { + err = -EOPNOTSUPP; + goto free_actions; + } + fs_actions[num_fs_actions++].action = tmp_action; + (*ractions)[num_actions++].action = tmp_action; + } + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || + num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + + tmp_action = mlx5_fs_create_action_last(ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_actions[num_fs_actions++].action = tmp_action; + (*ractions)[num_actions++].action = tmp_action; + + kfree(dest_actions); + + /* Actions created specifically for this rule will be destroyed + * once rule is deleted. + */ + fte->fs_hws_rule.num_fs_actions = num_fs_actions; + fte->fs_hws_rule.hws_fs_actions = fs_actions; + + return 0; + +free_actions: + mlx5_fs_destroy_fs_actions(&fs_actions, &num_fs_actions); +free_dest_actions_alloc: + kfree(dest_actions); +free_fs_actions_alloc: + kfree(fs_actions); +free_actions_alloc: + kfree(*ractions); + *ractions = NULL; +out_err: + return err; +} + +static int mlx5_cmd_hws_create_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + struct fs_fte *fte) +{ + struct mlx5hws_match_parameters params; + struct mlx5hws_rule_action *ractions; + struct mlx5hws_bwc_rule *rule; + int err = 0; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) { + /* Packet reformat on terminamtion table not supported yet */ + if (fte->act_dests.action.action & + MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) + return -EOPNOTSUPP; + return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte); + } + + err = mlx5_fs_fte_get_hws_actions(ns, ft, group, fte, &ractions); + if (err) + goto out_err; + + params.match_sz = sizeof(fte->val); + params.match_buf = fte->val; + + rule = mlx5hws_bwc_rule_create(group->fs_hws_matcher.matcher, ¶ms, + fte->act_dests.flow_context.flow_source, + ractions); + kfree(ractions); + if (!rule) { + err = -EINVAL; + goto free_actions; + } + + fte->fs_hws_rule.bwc_rule = rule; + return 0; + +free_actions: + mlx5_fs_destroy_fs_actions(&fte->fs_hws_rule.hws_fs_actions, + &fte->fs_hws_rule.num_fs_actions); +out_err: + mlx5_core_err(ns->dev, "Failed to create hws rule err(%d)\n", err); + return err; +} + +static int mlx5_cmd_hws_delete_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct fs_fte *fte) +{ + struct mlx5_fs_hws_rule *rule = &fte->fs_hws_rule; + int err; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte); + + err = mlx5hws_bwc_rule_destroy(rule->bwc_rule); + rule->bwc_rule = NULL; + + mlx5_fs_destroy_fs_actions(&rule->hws_fs_actions, &rule->num_fs_actions); + + return err; +} + +static int mlx5_cmd_hws_update_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + int modify_mask, + struct fs_fte *fte) +{ + int allowed_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) | + BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST) | + BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS); + struct mlx5_fs_hws_rule_action *saved_hws_fs_actions; + struct mlx5hws_rule_action *ractions; + int saved_num_fs_actions; + int ret; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->update_fte(ns, ft, group, + modify_mask, fte); + + if ((modify_mask & ~allowed_mask) != 0) + return -EINVAL; + + saved_hws_fs_actions = fte->fs_hws_rule.hws_fs_actions; + saved_num_fs_actions = fte->fs_hws_rule.num_fs_actions; + + ret = mlx5_fs_fte_get_hws_actions(ns, ft, group, fte, &ractions); + if (ret) + return ret; + + ret = mlx5hws_bwc_rule_action_update(fte->fs_hws_rule.bwc_rule, ractions); + kfree(ractions); + if (ret) + goto restore_actions; + + mlx5_fs_destroy_fs_actions(&saved_hws_fs_actions, &saved_num_fs_actions); + return ret; + +restore_actions: + mlx5_fs_destroy_fs_actions(&fte->fs_hws_rule.hws_fs_actions, + &fte->fs_hws_rule.num_fs_actions); + fte->fs_hws_rule.hws_fs_actions = saved_hws_fs_actions; + fte->fs_hws_rule.num_fs_actions = saved_num_fs_actions; + return ret; +} + +static struct mlx5hws_action * +mlx5_fs_create_action_remove_header_vlan(struct mlx5hws_context *ctx) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5hws_action_remove_header_attr remove_hdr_vlan = {}; + + /* MAC anchor not supported in HWS reformat, use VLAN anchor */ + remove_hdr_vlan.anchor = MLX5_REFORMAT_CONTEXT_ANCHOR_VLAN_START; + remove_hdr_vlan.offset = 0; + remove_hdr_vlan.size = sizeof(struct vlan_hdr); + return mlx5hws_action_create_remove_header(ctx, &remove_hdr_vlan, flags); +} + +static struct mlx5hws_action * +mlx5_fs_get_action_remove_header_vlan(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_pkt_reformat_params *params) +{ + if (!params || + params->param_0 != MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START || + params->param_1 != offsetof(struct vlan_ethhdr, h_vlan_proto) || + params->size != sizeof(struct vlan_hdr)) + return NULL; + + return fs_ctx->hws_pool.remove_hdr_vlan_action; +} + +static int +mlx5_fs_verify_insert_header_params(struct mlx5_core_dev *mdev, + struct mlx5_pkt_reformat_params *params) +{ + if ((!params->data && params->size) || (params->data && !params->size) || + MLX5_CAP_GEN_2(mdev, max_reformat_insert_size) < params->size || + MLX5_CAP_GEN_2(mdev, max_reformat_insert_offset) < params->param_1) { + mlx5_core_err(mdev, "Invalid reformat params for INSERT_HDR\n"); + return -EINVAL; + } + if (params->param_0 != MLX5_FS_INSERT_HDR_VLAN_ANCHOR || + params->param_1 != MLX5_FS_INSERT_HDR_VLAN_OFFSET || + params->size != MLX5_FS_INSERT_HDR_VLAN_SIZE) { + mlx5_core_err(mdev, "Only vlan insert header supported\n"); + return -EOPNOTSUPP; + } + return 0; +} + +static int +mlx5_fs_verify_encap_decap_params(struct mlx5_core_dev *dev, + struct mlx5_pkt_reformat_params *params) +{ + if (params->param_0 || params->param_1) { + mlx5_core_err(dev, "Invalid reformat params\n"); + return -EINVAL; + } + return 0; +} + +static struct mlx5_fs_pool * +mlx5_fs_get_pr_encap_pool(struct mlx5_core_dev *dev, struct xarray *pr_pools, + enum mlx5hws_action_type reformat_type, size_t size) +{ + struct mlx5_fs_pool *pr_pool; + unsigned long index = size; + int err; + + pr_pool = xa_load(pr_pools, index); + if (pr_pool) + return pr_pool; + + pr_pool = kzalloc(sizeof(*pr_pool), GFP_KERNEL); + if (!pr_pool) + return ERR_PTR(-ENOMEM); + err = mlx5_fs_hws_pr_pool_init(pr_pool, dev, size, reformat_type); + if (err) + goto free_pr_pool; + err = xa_insert(pr_pools, index, pr_pool, GFP_KERNEL); + if (err) + goto cleanup_pr_pool; + return pr_pool; + +cleanup_pr_pool: + mlx5_fs_hws_pr_pool_cleanup(pr_pool); +free_pr_pool: + kfree(pr_pool); + return ERR_PTR(err); +} + +static void +mlx5_fs_destroy_pr_pool(struct mlx5_fs_pool *pool, struct xarray *pr_pools, + unsigned long index) +{ + xa_erase(pr_pools, index); + mlx5_fs_hws_pr_pool_cleanup(pool); + kfree(pool); +} + +static int +mlx5_cmd_hws_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat_params *params, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context; + struct mlx5_fs_hws_actions_pool *hws_pool; + struct mlx5hws_action *hws_action = NULL; + struct mlx5_fs_hws_pr *pr_data = NULL; + struct mlx5_fs_pool *pr_pool = NULL; + struct mlx5_core_dev *dev = ns->dev; + u8 hdr_idx = 0; + int err; + + if (!params) + return -EINVAL; + + hws_pool = &fs_ctx->hws_pool; + + switch (params->type) { + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: + case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: + if (mlx5_fs_verify_encap_decap_params(dev, params)) + return -EINVAL; + pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools, + MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2, + params->size); + if (IS_ERR(pr_pool)) + return PTR_ERR(pr_pool); + break; + case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: + if (mlx5_fs_verify_encap_decap_params(dev, params)) + return -EINVAL; + pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol3tnl_pools, + MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3, + params->size); + if (IS_ERR(pr_pool)) + return PTR_ERR(pr_pool); + break; + case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2: + if (mlx5_fs_verify_encap_decap_params(dev, params)) + return -EINVAL; + pr_pool = &hws_pool->dl3tnltol2_pool; + hdr_idx = params->size == ETH_HLEN ? + MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX : + MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX; + break; + case MLX5_REFORMAT_TYPE_INSERT_HDR: + err = mlx5_fs_verify_insert_header_params(dev, params); + if (err) + return err; + pr_pool = &hws_pool->insert_hdr_pool; + break; + case MLX5_REFORMAT_TYPE_REMOVE_HDR: + hws_action = mlx5_fs_get_action_remove_header_vlan(fs_ctx, params); + if (!hws_action) + mlx5_core_err(dev, "Only vlan remove header supported\n"); + break; + default: + mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n", + params->type); + return -EOPNOTSUPP; + } + + if (pr_pool) { + pr_data = mlx5_fs_hws_pr_pool_acquire_pr(pr_pool); + if (IS_ERR_OR_NULL(pr_data)) + return !pr_data ? -EINVAL : PTR_ERR(pr_data); + hws_action = pr_data->bulk->hws_action; + if (!hws_action) { + mlx5_core_err(dev, + "Failed allocating packet-reformat action\n"); + err = -EINVAL; + goto release_pr; + } + pr_data->data = kmemdup(params->data, params->size, GFP_KERNEL); + if (!pr_data->data) { + err = -ENOMEM; + goto release_pr; + } + pr_data->hdr_idx = hdr_idx; + pr_data->data_size = params->size; + pkt_reformat->fs_hws_action.pr_data = pr_data; + } + + pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_SW; + pkt_reformat->fs_hws_action.hws_action = hws_action; + return 0; + +release_pr: + if (pr_pool && pr_data) + mlx5_fs_hws_pr_pool_release_pr(pr_pool, pr_data); + return err; +} + +static void mlx5_cmd_hws_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5_fs_hws_actions_pool *hws_pool = &ns->fs_hws_context.hws_pool; + struct mlx5_core_dev *dev = ns->dev; + struct mlx5_fs_hws_pr *pr_data; + struct mlx5_fs_pool *pr_pool; + + if (pkt_reformat->reformat_type == MLX5_REFORMAT_TYPE_REMOVE_HDR) + return; + + if (!pkt_reformat->fs_hws_action.pr_data) { + mlx5_core_err(ns->dev, "Failed release packet-reformat\n"); + return; + } + pr_data = pkt_reformat->fs_hws_action.pr_data; + + switch (pkt_reformat->reformat_type) { + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: + case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: + pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools, + MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2, + pr_data->data_size); + break; + case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: + pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools, + MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2, + pr_data->data_size); + break; + case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2: + pr_pool = &hws_pool->dl3tnltol2_pool; + break; + case MLX5_REFORMAT_TYPE_INSERT_HDR: + pr_pool = &hws_pool->insert_hdr_pool; + break; + default: + mlx5_core_err(ns->dev, "Unknown packet-reformat type\n"); + return; + } + if (!pkt_reformat->fs_hws_action.pr_data || IS_ERR(pr_pool)) { + mlx5_core_err(ns->dev, "Failed release packet-reformat\n"); + return; + } + kfree(pr_data->data); + mlx5_fs_hws_pr_pool_release_pr(pr_pool, pr_data); + pkt_reformat->fs_hws_action.pr_data = NULL; +} + +static struct mlx5_fs_pool * +mlx5_fs_create_mh_pool(struct mlx5_core_dev *dev, + struct mlx5hws_action_mh_pattern *pattern, + struct xarray *mh_pools, unsigned long index) +{ + struct mlx5_fs_pool *pool; + int err; + + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return ERR_PTR(-ENOMEM); + err = mlx5_fs_hws_mh_pool_init(pool, dev, pattern); + if (err) + goto free_pool; + err = xa_insert(mh_pools, index, pool, GFP_KERNEL); + if (err) + goto cleanup_pool; + return pool; + +cleanup_pool: + mlx5_fs_hws_mh_pool_cleanup(pool); +free_pool: + kfree(pool); + return ERR_PTR(err); +} + +static void +mlx5_fs_destroy_mh_pool(struct mlx5_fs_pool *pool, struct xarray *mh_pools, + unsigned long index) +{ + xa_erase(mh_pools, index); + mlx5_fs_hws_mh_pool_cleanup(pool); + kfree(pool); +} + +static int mlx5_cmd_hws_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) +{ + struct mlx5_fs_hws_actions_pool *hws_pool = &ns->fs_hws_context.hws_pool; + struct mlx5hws_action_mh_pattern pattern = {}; + struct mlx5_fs_hws_mh *mh_data = NULL; + struct mlx5hws_action *hws_action; + struct mlx5_fs_pool *pool; + unsigned long i, cnt = 0; + bool known_pattern; + int err; + + pattern.sz = MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) * num_actions; + pattern.data = modify_actions; + + known_pattern = false; + xa_for_each(&hws_pool->mh_pools, i, pool) { + if (mlx5_fs_hws_mh_pool_match(pool, &pattern)) { + known_pattern = true; + break; + } + cnt++; + } + + if (!known_pattern) { + pool = mlx5_fs_create_mh_pool(ns->dev, &pattern, + &hws_pool->mh_pools, cnt); + if (IS_ERR(pool)) + return PTR_ERR(pool); + } + mh_data = mlx5_fs_hws_mh_pool_acquire_mh(pool); + if (IS_ERR(mh_data)) { + err = PTR_ERR(mh_data); + goto destroy_pool; + } + hws_action = mh_data->bulk->hws_action; + mh_data->data = kmemdup(pattern.data, pattern.sz, GFP_KERNEL); + if (!mh_data->data) { + err = -ENOMEM; + goto release_mh; + } + modify_hdr->fs_hws_action.mh_data = mh_data; + modify_hdr->fs_hws_action.fs_pool = pool; + modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW; + modify_hdr->fs_hws_action.hws_action = hws_action; + + return 0; + +release_mh: + mlx5_fs_hws_mh_pool_release_mh(pool, mh_data); +destroy_pool: + if (!known_pattern) + mlx5_fs_destroy_mh_pool(pool, &hws_pool->mh_pools, cnt); + return err; +} + +static void mlx5_cmd_hws_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) +{ + struct mlx5_fs_hws_mh *mh_data; + struct mlx5_fs_pool *pool; + + if (!modify_hdr->fs_hws_action.fs_pool || !modify_hdr->fs_hws_action.mh_data) { + mlx5_core_err(ns->dev, "Failed release modify-header\n"); + return; + } + + mh_data = modify_hdr->fs_hws_action.mh_data; + kfree(mh_data->data); + pool = modify_hdr->fs_hws_action.fs_pool; + mlx5_fs_hws_mh_pool_release_mh(pool, mh_data); + modify_hdr->fs_hws_action.mh_data = NULL; +} + +static int mlx5_cmd_hws_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + return -EOPNOTSUPP; +} + +static int mlx5_cmd_hws_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + return -EOPNOTSUPP; +} + +static u32 mlx5_cmd_hws_get_capabilities(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type) +{ + if (ft_type != FS_FT_FDB) + return 0; + + return MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX | + MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX | + MLX5_FLOW_STEERING_CAP_MATCH_RANGES; +} + +bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev) +{ + return mlx5hws_is_supported(dev); +} + +static const struct mlx5_flow_cmds mlx5_flow_cmds_hws = { + .create_flow_table = mlx5_cmd_hws_create_flow_table, + .destroy_flow_table = mlx5_cmd_hws_destroy_flow_table, + .modify_flow_table = mlx5_cmd_hws_modify_flow_table, + .update_root_ft = mlx5_cmd_hws_update_root_ft, + .create_flow_group = mlx5_cmd_hws_create_flow_group, + .destroy_flow_group = mlx5_cmd_hws_destroy_flow_group, + .create_fte = mlx5_cmd_hws_create_fte, + .delete_fte = mlx5_cmd_hws_delete_fte, + .update_fte = mlx5_cmd_hws_update_fte, + .packet_reformat_alloc = mlx5_cmd_hws_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_hws_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_hws_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_hws_modify_header_dealloc, + .create_match_definer = mlx5_cmd_hws_create_match_definer, + .destroy_match_definer = mlx5_cmd_hws_destroy_match_definer, + .create_ns = mlx5_cmd_hws_create_ns, + .destroy_ns = mlx5_cmd_hws_destroy_ns, + .set_peer = mlx5_cmd_hws_set_peer, + .get_capabilities = mlx5_cmd_hws_get_capabilities, +}; + +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void) +{ + return &mlx5_flow_cmds_hws; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h new file mode 100644 index 000000000000..cbddb72d4362 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */ + +#ifndef _MLX5_FS_HWS_ +#define _MLX5_FS_HWS_ + +#include "mlx5hws.h" +#include "fs_hws_pools.h" + +struct mlx5_fs_hws_actions_pool { + struct mlx5hws_action *tag_action; + struct mlx5hws_action *pop_vlan_action; + struct mlx5hws_action *push_vlan_action; + struct mlx5hws_action *drop_action; + struct mlx5hws_action *decapl2_action; + struct mlx5hws_action *remove_hdr_vlan_action; + struct mlx5_fs_pool insert_hdr_pool; + struct mlx5_fs_pool dl3tnltol2_pool; + struct xarray el2tol3tnl_pools; + struct xarray el2tol2tnl_pools; + struct xarray mh_pools; + struct xarray table_dests; + struct xarray vport_vhca_dests; + struct xarray vport_dests; +}; + +struct mlx5_fs_hws_context { + struct mlx5hws_context *hws_ctx; + struct mlx5_fs_hws_actions_pool hws_pool; +}; + +struct mlx5_fs_hws_table { + struct mlx5hws_table *hws_table; + bool miss_ft_set; +}; + +struct mlx5_fs_hws_action { + struct mlx5hws_action *hws_action; + struct mlx5_fs_pool *fs_pool; + struct mlx5_fs_hws_pr *pr_data; + struct mlx5_fs_hws_mh *mh_data; +}; + +struct mlx5_fs_hws_matcher { + struct mlx5hws_bwc_matcher *matcher; +}; + +struct mlx5_fs_hws_rule_action { + struct mlx5hws_action *action; + union { + struct mlx5_fc *counter; + }; +}; + +struct mlx5_fs_hws_rule { + struct mlx5hws_bwc_rule *bwc_rule; + struct mlx5_fs_hws_rule_action *hws_fs_actions; + int num_fs_actions; +}; + +#ifdef CONFIG_MLX5_HW_STEERING + +bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev); + +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void); + +#else + +static inline bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev) +{ + return false; +} + +static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void) +{ + return NULL; +} + +#endif /* CONFIG_MLX5_HWS_STEERING */ +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c new file mode 100644 index 000000000000..2ae4ac62b0e2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c @@ -0,0 +1,450 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */ + +#include +#include "fs_hws_pools.h" + +#define MLX5_FS_HWS_DEFAULT_BULK_LEN 65536 +#define MLX5_FS_HWS_POOL_MAX_THRESHOLD BIT(18) +#define MLX5_FS_HWS_POOL_USED_BUFF_RATIO 10 + +static struct mlx5hws_action * +mlx5_fs_dl3tnltol2_bulk_action_create(struct mlx5hws_context *ctx) +{ + struct mlx5hws_action_reformat_header reformat_hdr[2] = {}; + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + enum mlx5hws_action_type reformat_type; + u32 log_bulk_size; + + reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2; + reformat_hdr[MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX].sz = ETH_HLEN; + reformat_hdr[MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX].sz = ETH_HLEN + VLAN_HLEN; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + return mlx5hws_action_create_reformat(ctx, reformat_type, 2, + reformat_hdr, log_bulk_size, flags); +} + +static struct mlx5hws_action * +mlx5_fs_el2tol3tnl_bulk_action_create(struct mlx5hws_context *ctx, size_t data_size) +{ + struct mlx5hws_action_reformat_header reformat_hdr = {}; + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + enum mlx5hws_action_type reformat_type; + u32 log_bulk_size; + + reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3; + reformat_hdr.sz = data_size; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + return mlx5hws_action_create_reformat(ctx, reformat_type, 1, + &reformat_hdr, log_bulk_size, flags); +} + +static struct mlx5hws_action * +mlx5_fs_el2tol2tnl_bulk_action_create(struct mlx5hws_context *ctx, size_t data_size) +{ + struct mlx5hws_action_reformat_header reformat_hdr = {}; + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + enum mlx5hws_action_type reformat_type; + u32 log_bulk_size; + + reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2; + reformat_hdr.sz = data_size; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + return mlx5hws_action_create_reformat(ctx, reformat_type, 1, + &reformat_hdr, log_bulk_size, flags); +} + +static struct mlx5hws_action * +mlx5_fs_insert_hdr_bulk_action_create(struct mlx5hws_context *ctx) +{ + struct mlx5hws_action_insert_header insert_hdr = {}; + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + u32 log_bulk_size; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + insert_hdr.hdr.sz = MLX5_FS_INSERT_HDR_VLAN_SIZE; + insert_hdr.anchor = MLX5_FS_INSERT_HDR_VLAN_ANCHOR; + insert_hdr.offset = MLX5_FS_INSERT_HDR_VLAN_OFFSET; + + return mlx5hws_action_create_insert_header(ctx, 1, &insert_hdr, + log_bulk_size, flags); +} + +static struct mlx5hws_action * +mlx5_fs_pr_bulk_action_create(struct mlx5_core_dev *dev, + struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx) +{ + struct mlx5_flow_root_namespace *root_ns; + struct mlx5hws_context *ctx; + size_t encap_data_size; + + root_ns = mlx5_get_root_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!root_ns || root_ns->mode != MLX5_FLOW_STEERING_MODE_HMFS) + return NULL; + + ctx = root_ns->fs_hws_context.hws_ctx; + if (!ctx) + return NULL; + + encap_data_size = pr_pool_ctx->encap_data_size; + switch (pr_pool_ctx->reformat_type) { + case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2: + return mlx5_fs_dl3tnltol2_bulk_action_create(ctx); + case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3: + return mlx5_fs_el2tol3tnl_bulk_action_create(ctx, encap_data_size); + case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2: + return mlx5_fs_el2tol2tnl_bulk_action_create(ctx, encap_data_size); + case MLX5HWS_ACTION_TYP_INSERT_HEADER: + return mlx5_fs_insert_hdr_bulk_action_create(ctx); + default: + return NULL; + } + return NULL; +} + +static struct mlx5_fs_bulk * +mlx5_fs_hws_pr_bulk_create(struct mlx5_core_dev *dev, void *pool_ctx) +{ + struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx; + struct mlx5_fs_hws_pr_bulk *pr_bulk; + int bulk_len; + int i; + + if (!pool_ctx) + return NULL; + pr_pool_ctx = pool_ctx; + bulk_len = MLX5_FS_HWS_DEFAULT_BULK_LEN; + pr_bulk = kvzalloc(struct_size(pr_bulk, prs_data, bulk_len), GFP_KERNEL); + if (!pr_bulk) + return NULL; + + if (mlx5_fs_bulk_init(dev, &pr_bulk->fs_bulk, bulk_len)) + goto free_pr_bulk; + + for (i = 0; i < bulk_len; i++) { + pr_bulk->prs_data[i].bulk = pr_bulk; + pr_bulk->prs_data[i].offset = i; + } + + pr_bulk->hws_action = mlx5_fs_pr_bulk_action_create(dev, pr_pool_ctx); + if (!pr_bulk->hws_action) + goto cleanup_fs_bulk; + + return &pr_bulk->fs_bulk; + +cleanup_fs_bulk: + mlx5_fs_bulk_cleanup(&pr_bulk->fs_bulk); +free_pr_bulk: + kvfree(pr_bulk); + return NULL; +} + +static int +mlx5_fs_hws_pr_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk) +{ + struct mlx5_fs_hws_pr_bulk *pr_bulk; + + pr_bulk = container_of(fs_bulk, struct mlx5_fs_hws_pr_bulk, fs_bulk); + if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) { + mlx5_core_err(dev, "Freeing bulk before all reformats were released\n"); + return -EBUSY; + } + + mlx5hws_action_destroy(pr_bulk->hws_action); + mlx5_fs_bulk_cleanup(fs_bulk); + kvfree(pr_bulk); + + return 0; +} + +static void mlx5_hws_pool_update_threshold(struct mlx5_fs_pool *hws_pool) +{ + hws_pool->threshold = min_t(int, MLX5_FS_HWS_POOL_MAX_THRESHOLD, + hws_pool->used_units / MLX5_FS_HWS_POOL_USED_BUFF_RATIO); +} + +static const struct mlx5_fs_pool_ops mlx5_fs_hws_pr_pool_ops = { + .bulk_create = mlx5_fs_hws_pr_bulk_create, + .bulk_destroy = mlx5_fs_hws_pr_bulk_destroy, + .update_threshold = mlx5_hws_pool_update_threshold, +}; + +int mlx5_fs_hws_pr_pool_init(struct mlx5_fs_pool *pr_pool, + struct mlx5_core_dev *dev, size_t encap_data_size, + enum mlx5hws_action_type reformat_type) +{ + struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx; + + if (reformat_type != MLX5HWS_ACTION_TYP_INSERT_HEADER && + reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2 && + reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3 && + reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) + return -EOPNOTSUPP; + + pr_pool_ctx = kzalloc(sizeof(*pr_pool_ctx), GFP_KERNEL); + if (!pr_pool_ctx) + return -ENOMEM; + pr_pool_ctx->reformat_type = reformat_type; + pr_pool_ctx->encap_data_size = encap_data_size; + mlx5_fs_pool_init(pr_pool, dev, &mlx5_fs_hws_pr_pool_ops, pr_pool_ctx); + return 0; +} + +void mlx5_fs_hws_pr_pool_cleanup(struct mlx5_fs_pool *pr_pool) +{ + struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx; + + mlx5_fs_pool_cleanup(pr_pool); + pr_pool_ctx = pr_pool->pool_ctx; + if (!pr_pool_ctx) + return; + kfree(pr_pool_ctx); +} + +struct mlx5_fs_hws_pr * +mlx5_fs_hws_pr_pool_acquire_pr(struct mlx5_fs_pool *pr_pool) +{ + struct mlx5_fs_pool_index pool_index = {}; + struct mlx5_fs_hws_pr_bulk *pr_bulk; + int err; + + err = mlx5_fs_pool_acquire_index(pr_pool, &pool_index); + if (err) + return ERR_PTR(err); + pr_bulk = container_of(pool_index.fs_bulk, struct mlx5_fs_hws_pr_bulk, + fs_bulk); + return &pr_bulk->prs_data[pool_index.index]; +} + +void mlx5_fs_hws_pr_pool_release_pr(struct mlx5_fs_pool *pr_pool, + struct mlx5_fs_hws_pr *pr_data) +{ + struct mlx5_fs_bulk *fs_bulk = &pr_data->bulk->fs_bulk; + struct mlx5_fs_pool_index pool_index = {}; + struct mlx5_core_dev *dev = pr_pool->dev; + + pool_index.fs_bulk = fs_bulk; + pool_index.index = pr_data->offset; + if (mlx5_fs_pool_release_index(pr_pool, &pool_index)) + mlx5_core_warn(dev, "Attempted to release packet reformat which is not acquired\n"); +} + +struct mlx5hws_action *mlx5_fs_hws_pr_get_action(struct mlx5_fs_hws_pr *pr_data) +{ + return pr_data->bulk->hws_action; +} + +static struct mlx5hws_action * +mlx5_fs_mh_bulk_action_create(struct mlx5hws_context *ctx, + struct mlx5hws_action_mh_pattern *pattern) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + u32 log_bulk_size; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + return mlx5hws_action_create_modify_header(ctx, 1, pattern, + log_bulk_size, flags); +} + +static struct mlx5_fs_bulk * +mlx5_fs_hws_mh_bulk_create(struct mlx5_core_dev *dev, void *pool_ctx) +{ + struct mlx5hws_action_mh_pattern *pattern; + struct mlx5_flow_root_namespace *root_ns; + struct mlx5_fs_hws_mh_bulk *mh_bulk; + struct mlx5hws_context *ctx; + int bulk_len; + + if (!pool_ctx) + return NULL; + + root_ns = mlx5_get_root_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!root_ns || root_ns->mode != MLX5_FLOW_STEERING_MODE_HMFS) + return NULL; + + ctx = root_ns->fs_hws_context.hws_ctx; + if (!ctx) + return NULL; + + pattern = pool_ctx; + bulk_len = MLX5_FS_HWS_DEFAULT_BULK_LEN; + mh_bulk = kvzalloc(struct_size(mh_bulk, mhs_data, bulk_len), GFP_KERNEL); + if (!mh_bulk) + return NULL; + + if (mlx5_fs_bulk_init(dev, &mh_bulk->fs_bulk, bulk_len)) + goto free_mh_bulk; + + for (int i = 0; i < bulk_len; i++) { + mh_bulk->mhs_data[i].bulk = mh_bulk; + mh_bulk->mhs_data[i].offset = i; + } + + mh_bulk->hws_action = mlx5_fs_mh_bulk_action_create(ctx, pattern); + if (!mh_bulk->hws_action) + goto cleanup_fs_bulk; + + return &mh_bulk->fs_bulk; + +cleanup_fs_bulk: + mlx5_fs_bulk_cleanup(&mh_bulk->fs_bulk); +free_mh_bulk: + kvfree(mh_bulk); + return NULL; +} + +static int +mlx5_fs_hws_mh_bulk_destroy(struct mlx5_core_dev *dev, + struct mlx5_fs_bulk *fs_bulk) +{ + struct mlx5_fs_hws_mh_bulk *mh_bulk; + + mh_bulk = container_of(fs_bulk, struct mlx5_fs_hws_mh_bulk, fs_bulk); + if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) { + mlx5_core_err(dev, "Freeing bulk before all modify header were released\n"); + return -EBUSY; + } + + mlx5hws_action_destroy(mh_bulk->hws_action); + mlx5_fs_bulk_cleanup(fs_bulk); + kvfree(mh_bulk); + + return 0; +} + +static const struct mlx5_fs_pool_ops mlx5_fs_hws_mh_pool_ops = { + .bulk_create = mlx5_fs_hws_mh_bulk_create, + .bulk_destroy = mlx5_fs_hws_mh_bulk_destroy, + .update_threshold = mlx5_hws_pool_update_threshold, +}; + +int mlx5_fs_hws_mh_pool_init(struct mlx5_fs_pool *fs_hws_mh_pool, + struct mlx5_core_dev *dev, + struct mlx5hws_action_mh_pattern *pattern) +{ + struct mlx5hws_action_mh_pattern *pool_pattern; + + pool_pattern = kzalloc(sizeof(*pool_pattern), GFP_KERNEL); + if (!pool_pattern) + return -ENOMEM; + pool_pattern->data = kmemdup(pattern->data, pattern->sz, GFP_KERNEL); + if (!pool_pattern->data) { + kfree(pool_pattern); + return -ENOMEM; + } + pool_pattern->sz = pattern->sz; + mlx5_fs_pool_init(fs_hws_mh_pool, dev, &mlx5_fs_hws_mh_pool_ops, + pool_pattern); + return 0; +} + +void mlx5_fs_hws_mh_pool_cleanup(struct mlx5_fs_pool *fs_hws_mh_pool) +{ + struct mlx5hws_action_mh_pattern *pool_pattern; + + mlx5_fs_pool_cleanup(fs_hws_mh_pool); + pool_pattern = fs_hws_mh_pool->pool_ctx; + if (!pool_pattern) + return; + kfree(pool_pattern->data); + kfree(pool_pattern); +} + +struct mlx5_fs_hws_mh * +mlx5_fs_hws_mh_pool_acquire_mh(struct mlx5_fs_pool *mh_pool) +{ + struct mlx5_fs_pool_index pool_index = {}; + struct mlx5_fs_hws_mh_bulk *mh_bulk; + int err; + + err = mlx5_fs_pool_acquire_index(mh_pool, &pool_index); + if (err) + return ERR_PTR(err); + mh_bulk = container_of(pool_index.fs_bulk, struct mlx5_fs_hws_mh_bulk, + fs_bulk); + return &mh_bulk->mhs_data[pool_index.index]; +} + +void mlx5_fs_hws_mh_pool_release_mh(struct mlx5_fs_pool *mh_pool, + struct mlx5_fs_hws_mh *mh_data) +{ + struct mlx5_fs_bulk *fs_bulk = &mh_data->bulk->fs_bulk; + struct mlx5_fs_pool_index pool_index = {}; + struct mlx5_core_dev *dev = mh_pool->dev; + + pool_index.fs_bulk = fs_bulk; + pool_index.index = mh_data->offset; + if (mlx5_fs_pool_release_index(mh_pool, &pool_index)) + mlx5_core_warn(dev, "Attempted to release modify header which is not acquired\n"); +} + +bool mlx5_fs_hws_mh_pool_match(struct mlx5_fs_pool *mh_pool, + struct mlx5hws_action_mh_pattern *pattern) +{ + struct mlx5hws_action_mh_pattern *pool_pattern; + int num_actions, i; + + pool_pattern = mh_pool->pool_ctx; + if (WARN_ON_ONCE(!pool_pattern)) + return false; + + if (pattern->sz != pool_pattern->sz) + return false; + num_actions = pattern->sz / MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto); + for (i = 0; i < num_actions; i++) { + if ((__force __be32)pattern->data[i] != + (__force __be32)pool_pattern->data[i]) + return false; + } + return true; +} + +struct mlx5hws_action *mlx5_fc_get_hws_action(struct mlx5hws_context *ctx, + struct mlx5_fc *counter) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_fc_bulk *fc_bulk = counter->bulk; + struct mlx5_fc_bulk_hws_data *fc_bulk_hws; + + fc_bulk_hws = &fc_bulk->hws_data; + /* try avoid locking if not necessary */ + if (refcount_inc_not_zero(&fc_bulk_hws->hws_action_refcount)) + return fc_bulk_hws->hws_action; + + mutex_lock(&fc_bulk_hws->lock); + if (refcount_inc_not_zero(&fc_bulk_hws->hws_action_refcount)) { + mutex_unlock(&fc_bulk_hws->lock); + return fc_bulk_hws->hws_action; + } + fc_bulk_hws->hws_action = + mlx5hws_action_create_counter(ctx, fc_bulk->base_id, flags); + if (!fc_bulk_hws->hws_action) { + mutex_unlock(&fc_bulk_hws->lock); + return NULL; + } + refcount_set(&fc_bulk_hws->hws_action_refcount, 1); + mutex_unlock(&fc_bulk_hws->lock); + + return fc_bulk_hws->hws_action; +} + +void mlx5_fc_put_hws_action(struct mlx5_fc *counter) +{ + struct mlx5_fc_bulk_hws_data *fc_bulk_hws = &counter->bulk->hws_data; + + /* try avoid locking if not necessary */ + if (refcount_dec_not_one(&fc_bulk_hws->hws_action_refcount)) + return; + + mutex_lock(&fc_bulk_hws->lock); + if (!refcount_dec_and_test(&fc_bulk_hws->hws_action_refcount)) { + mutex_unlock(&fc_bulk_hws->lock); + return; + } + mlx5hws_action_destroy(fc_bulk_hws->hws_action); + fc_bulk_hws->hws_action = NULL; + mutex_unlock(&fc_bulk_hws->lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h new file mode 100644 index 000000000000..34072551dd21 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */ + +#ifndef __MLX5_FS_HWS_POOLS_H__ +#define __MLX5_FS_HWS_POOLS_H__ + +#include +#include "fs_pool.h" +#include "fs_core.h" + +#define MLX5_FS_INSERT_HDR_VLAN_ANCHOR MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START +#define MLX5_FS_INSERT_HDR_VLAN_OFFSET offsetof(struct vlan_ethhdr, h_vlan_proto) +#define MLX5_FS_INSERT_HDR_VLAN_SIZE sizeof(struct vlan_hdr) + +enum { + MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX = 0, + MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX, +}; + +struct mlx5_fs_hws_pr { + struct mlx5_fs_hws_pr_bulk *bulk; + u32 offset; + u8 hdr_idx; + u8 *data; + size_t data_size; +}; + +struct mlx5_fs_hws_pr_bulk { + struct mlx5_fs_bulk fs_bulk; + struct mlx5hws_action *hws_action; + struct mlx5_fs_hws_pr prs_data[]; +}; + +struct mlx5_fs_hws_pr_pool_ctx { + enum mlx5hws_action_type reformat_type; + size_t encap_data_size; +}; + +struct mlx5_fs_hws_mh { + struct mlx5_fs_hws_mh_bulk *bulk; + u32 offset; + u8 *data; +}; + +struct mlx5_fs_hws_mh_bulk { + struct mlx5_fs_bulk fs_bulk; + struct mlx5_fs_pool *mh_pool; + struct mlx5hws_action *hws_action; + struct mlx5_fs_hws_mh mhs_data[]; +}; + +int mlx5_fs_hws_pr_pool_init(struct mlx5_fs_pool *pr_pool, + struct mlx5_core_dev *dev, size_t encap_data_size, + enum mlx5hws_action_type reformat_type); +void mlx5_fs_hws_pr_pool_cleanup(struct mlx5_fs_pool *pr_pool); + +struct mlx5_fs_hws_pr *mlx5_fs_hws_pr_pool_acquire_pr(struct mlx5_fs_pool *pr_pool); +void mlx5_fs_hws_pr_pool_release_pr(struct mlx5_fs_pool *pr_pool, + struct mlx5_fs_hws_pr *pr_data); +struct mlx5hws_action *mlx5_fs_hws_pr_get_action(struct mlx5_fs_hws_pr *pr_data); +int mlx5_fs_hws_mh_pool_init(struct mlx5_fs_pool *fs_hws_mh_pool, + struct mlx5_core_dev *dev, + struct mlx5hws_action_mh_pattern *pattern); +void mlx5_fs_hws_mh_pool_cleanup(struct mlx5_fs_pool *fs_hws_mh_pool); +struct mlx5_fs_hws_mh *mlx5_fs_hws_mh_pool_acquire_mh(struct mlx5_fs_pool *mh_pool); +void mlx5_fs_hws_mh_pool_release_mh(struct mlx5_fs_pool *mh_pool, + struct mlx5_fs_hws_mh *mh_data); +bool mlx5_fs_hws_mh_pool_match(struct mlx5_fs_pool *mh_pool, + struct mlx5hws_action_mh_pattern *pattern); +struct mlx5hws_action *mlx5_fc_get_hws_action(struct mlx5hws_context *ctx, + struct mlx5_fc *counter); +void mlx5_fc_put_hws_action(struct mlx5_fc *counter); +#endif /* __MLX5_FS_HWS_POOLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h index 3c8635f286ce..30ccd635b505 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h @@ -39,7 +39,6 @@ #define mlx5hws_dbg(ctx, arg...) mlx5_core_dbg((ctx)->mdev, ##arg) #define MLX5HWS_TABLE_TYPE_BASE 2 -#define MLX5HWS_ACTION_STE_IDX_ANY 0 static inline bool is_mem_zero(const u8 *mem, size_t size) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c index 1bb3a6f8c3cd..b61864b32053 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c @@ -165,14 +165,14 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher) next->match_ste.rtc_0_id, next->match_ste.rtc_1_id); if (ret) { - mlx5hws_err(tbl->ctx, "Failed to disconnect matcher\n"); - goto matcher_reconnect; + mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect matcher\n"); + return ret; } } else { ret = mlx5hws_table_connect_to_miss_table(tbl, tbl->default_miss.miss_tbl); if (ret) { - mlx5hws_err(tbl->ctx, "Failed to disconnect last matcher\n"); - goto matcher_reconnect; + mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect last matcher\n"); + return ret; } } @@ -180,27 +180,19 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher) if (prev_ft_id == tbl->ft_id) { ret = mlx5hws_table_update_connected_miss_tables(tbl); if (ret) { - mlx5hws_err(tbl->ctx, "Fatal error, failed to update connected miss table\n"); - goto matcher_reconnect; + mlx5hws_err(tbl->ctx, + "Fatal error, failed to update connected miss table\n"); + return ret; } } ret = mlx5hws_table_ft_set_default_next_ft(tbl, prev_ft_id); if (ret) { mlx5hws_err(tbl->ctx, "Fatal error, failed to restore matcher ft default miss\n"); - goto matcher_reconnect; + return ret; } return 0; - -matcher_reconnect: - if (list_empty(&tbl->matchers_list) || !prev) - list_add(&matcher->list_node, &tbl->matchers_list); - else - /* insert after prev matcher */ - list_add(&matcher->list_node, &prev->list_node); - - return ret; } static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher, @@ -208,7 +200,7 @@ static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher, enum mlx5hws_matcher_rtc_type rtc_type, bool is_mirror) { - struct mlx5hws_pool_chunk *ste = &matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].ste; + struct mlx5hws_pool_chunk *ste = &matcher->action_ste.ste; enum mlx5hws_matcher_flow_src flow_src = matcher->attr.optimize_flow_src; bool is_match_rtc = rtc_type == HWS_MATCHER_RTC_TYPE_MATCH; @@ -225,8 +217,7 @@ static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher, } static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher, - enum mlx5hws_matcher_rtc_type rtc_type, - u8 action_ste_selector) + enum mlx5hws_matcher_rtc_type rtc_type) { struct mlx5hws_matcher_attr *attr = &matcher->attr; struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0}; @@ -286,14 +277,20 @@ static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher, break; case HWS_MATCHER_RTC_TYPE_STE_ARRAY: - action_ste = &matcher->action_ste[action_ste_selector]; + action_ste = &matcher->action_ste; rtc_0_id = &action_ste->rtc_0_id; rtc_1_id = &action_ste->rtc_1_id; ste_pool = action_ste->pool; ste = &action_ste->ste; + /* Action RTC size calculation: + * log((max number of rules in matcher) * + * (max number of action STEs per rule) * + * (2 to support writing new STEs for update rule)) + */ ste->order = ilog2(roundup_pow_of_two(action_ste->max_stes)) + - attr->table.sz_row_log; + attr->table.sz_row_log + + MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT; rtc_attr.log_size = ste->order; rtc_attr.log_depth = 0; rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET; @@ -318,8 +315,8 @@ static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher, hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, false); /* STC is a single resource (obj_id), use any STC for the ID */ - stc_pool = ctx->stc_pool[tbl->type]; - default_stc = ctx->common_res[tbl->type].default_stc; + stc_pool = ctx->stc_pool; + default_stc = ctx->common_res.default_stc; obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit); rtc_attr.stc_base = obj_id; @@ -358,8 +355,7 @@ free_ste: } static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher, - enum mlx5hws_matcher_rtc_type rtc_type, - u8 action_ste_selector) + enum mlx5hws_matcher_rtc_type rtc_type) { struct mlx5hws_matcher_action_ste *action_ste; struct mlx5hws_table *tbl = matcher->tbl; @@ -375,7 +371,7 @@ static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher, ste = &matcher->match_ste.ste; break; case HWS_MATCHER_RTC_TYPE_STE_ARRAY: - action_ste = &matcher->action_ste[action_ste_selector]; + action_ste = &matcher->action_ste; rtc_0_id = action_ste->rtc_0_id; rtc_1_id = action_ste->rtc_1_id; ste_pool = action_ste->pool; @@ -466,20 +462,13 @@ static int hws_matcher_resize_init(struct mlx5hws_matcher *src_matcher) if (!resize_data) return -ENOMEM; - resize_data->max_stes = src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes; + resize_data->max_stes = src_matcher->action_ste.max_stes; - resize_data->action_ste[0].stc = src_matcher->action_ste[0].stc; - resize_data->action_ste[0].rtc_0_id = src_matcher->action_ste[0].rtc_0_id; - resize_data->action_ste[0].rtc_1_id = src_matcher->action_ste[0].rtc_1_id; - resize_data->action_ste[0].pool = src_matcher->action_ste[0].max_stes ? - src_matcher->action_ste[0].pool : - NULL; - resize_data->action_ste[1].stc = src_matcher->action_ste[1].stc; - resize_data->action_ste[1].rtc_0_id = src_matcher->action_ste[1].rtc_0_id; - resize_data->action_ste[1].rtc_1_id = src_matcher->action_ste[1].rtc_1_id; - resize_data->action_ste[1].pool = src_matcher->action_ste[1].max_stes ? - src_matcher->action_ste[1].pool : - NULL; + resize_data->stc = src_matcher->action_ste.stc; + resize_data->rtc_0_id = src_matcher->action_ste.rtc_0_id; + resize_data->rtc_1_id = src_matcher->action_ste.rtc_1_id; + resize_data->pool = src_matcher->action_ste.max_stes ? + src_matcher->action_ste.pool : NULL; /* Place the new resized matcher on the dst matcher's list */ list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data); @@ -512,109 +501,31 @@ static void hws_matcher_resize_uninit(struct mlx5hws_matcher *matcher) if (resize_data->max_stes) { mlx5hws_action_free_single_stc(matcher->tbl->ctx, matcher->tbl->type, - &resize_data->action_ste[1].stc); - mlx5hws_action_free_single_stc(matcher->tbl->ctx, - matcher->tbl->type, - &resize_data->action_ste[0].stc); + &resize_data->stc); - if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB) { + if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB) mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, - resize_data->action_ste[1].rtc_1_id); - mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, - resize_data->action_ste[0].rtc_1_id); - } + resize_data->rtc_1_id); + mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, - resize_data->action_ste[1].rtc_0_id); - mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, - resize_data->action_ste[0].rtc_0_id); - if (resize_data->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].pool) { - mlx5hws_pool_destroy(resize_data->action_ste[1].pool); - mlx5hws_pool_destroy(resize_data->action_ste[0].pool); - } + resize_data->rtc_0_id); + + if (resize_data->pool) + mlx5hws_pool_destroy(resize_data->pool); } kfree(resize_data); } } -static int -hws_matcher_bind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector) +static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher) { + bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt); struct mlx5hws_cmd_stc_modify_attr stc_attr = {0}; struct mlx5hws_matcher_action_ste *action_ste; struct mlx5hws_table *tbl = matcher->tbl; struct mlx5hws_pool_attr pool_attr = {0}; struct mlx5hws_context *ctx = tbl->ctx; - int ret; - - action_ste = &matcher->action_ste[action_ste_selector]; - - /* Allocate action STE mempool */ - pool_attr.table_type = tbl->type; - pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE; - pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL; - pool_attr.alloc_log_sz = ilog2(roundup_pow_of_two(action_ste->max_stes)) + - matcher->attr.table.sz_row_log; - hws_matcher_set_pool_attr(&pool_attr, matcher); - action_ste->pool = mlx5hws_pool_create(ctx, &pool_attr); - if (!action_ste->pool) { - mlx5hws_err(ctx, "Failed to create action ste pool\n"); - return -EINVAL; - } - - /* Allocate action RTC */ - ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector); - if (ret) { - mlx5hws_err(ctx, "Failed to create action RTC\n"); - goto free_ste_pool; - } - - /* Allocate STC for jumps to STE */ - stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT; - stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE; - stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE; - stc_attr.ste_table.ste = action_ste->ste; - stc_attr.ste_table.ste_pool = action_ste->pool; - stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer; - - ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl->type, - &action_ste->stc); - if (ret) { - mlx5hws_err(ctx, "Failed to create action jump to table STC\n"); - goto free_rtc; - } - - return 0; - -free_rtc: - hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector); -free_ste_pool: - mlx5hws_pool_destroy(action_ste->pool); - return ret; -} - -static void hws_matcher_unbind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector) -{ - struct mlx5hws_matcher_action_ste *action_ste; - struct mlx5hws_table *tbl = matcher->tbl; - - action_ste = &matcher->action_ste[action_ste_selector]; - - if (!action_ste->max_stes || - matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION || - mlx5hws_matcher_is_in_resize(matcher)) - return; - - mlx5hws_action_free_single_stc(tbl->ctx, tbl->type, &action_ste->stc); - hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector); - mlx5hws_pool_destroy(action_ste->pool); -} - -static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher) -{ - bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt); - struct mlx5hws_table *tbl = matcher->tbl; - struct mlx5hws_context *ctx = tbl->ctx; u32 required_stes; u8 max_stes = 0; int i, ret; @@ -641,28 +552,71 @@ static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher) if (!max_stes) return 0; - matcher->action_ste[0].max_stes = max_stes; - matcher->action_ste[1].max_stes = max_stes; + matcher->action_ste.max_stes = max_stes; - ret = hws_matcher_bind_at_idx(matcher, 0); - if (ret) - return ret; + action_ste = &matcher->action_ste; - ret = hws_matcher_bind_at_idx(matcher, 1); - if (ret) - goto free_at_0; + /* Allocate action STE mempool */ + pool_attr.table_type = tbl->type; + pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE; + pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL; + /* Pool size is similar to action RTC size */ + pool_attr.alloc_log_sz = ilog2(roundup_pow_of_two(action_ste->max_stes)) + + matcher->attr.table.sz_row_log + + MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT; + hws_matcher_set_pool_attr(&pool_attr, matcher); + action_ste->pool = mlx5hws_pool_create(ctx, &pool_attr); + if (!action_ste->pool) { + mlx5hws_err(ctx, "Failed to create action ste pool\n"); + return -EINVAL; + } + + /* Allocate action RTC */ + ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY); + if (ret) { + mlx5hws_err(ctx, "Failed to create action RTC\n"); + goto free_ste_pool; + } + + /* Allocate STC for jumps to STE */ + stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT; + stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE; + stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE; + stc_attr.ste_table.ste = action_ste->ste; + stc_attr.ste_table.ste_pool = action_ste->pool; + stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer; + + ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl->type, + &action_ste->stc); + if (ret) { + mlx5hws_err(ctx, "Failed to create action jump to table STC\n"); + goto free_rtc; + } return 0; -free_at_0: - hws_matcher_unbind_at_idx(matcher, 0); +free_rtc: + hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY); +free_ste_pool: + mlx5hws_pool_destroy(action_ste->pool); return ret; } static void hws_matcher_unbind_at(struct mlx5hws_matcher *matcher) { - hws_matcher_unbind_at_idx(matcher, 1); - hws_matcher_unbind_at_idx(matcher, 0); + struct mlx5hws_matcher_action_ste *action_ste; + struct mlx5hws_table *tbl = matcher->tbl; + + action_ste = &matcher->action_ste; + + if (!action_ste->max_stes || + matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION || + mlx5hws_matcher_is_in_resize(matcher)) + return; + + mlx5hws_action_free_single_stc(tbl->ctx, tbl->type, &action_ste->stc); + hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY); + mlx5hws_pool_destroy(action_ste->pool); } static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher) @@ -810,7 +764,7 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher) goto unbind_at; /* Allocate the RTC for the new matcher */ - ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0); + ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH); if (ret) goto destroy_end_ft; @@ -822,7 +776,7 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher) return 0; destroy_rtc: - hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0); + hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH); destroy_end_ft: hws_matcher_destroy_end_ft(matcher); unbind_at: @@ -836,7 +790,7 @@ static void hws_matcher_destroy_and_disconnect(struct mlx5hws_matcher *matcher) { hws_matcher_resize_uninit(matcher); hws_matcher_disconnect(matcher); - hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0); + hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH); hws_matcher_destroy_end_ft(matcher); hws_matcher_unbind_at(matcher); hws_matcher_unbind_mt(matcher); @@ -970,10 +924,9 @@ int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher, return ret; required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term); - if (matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes < required_stes) { + if (matcher->action_ste.max_stes < required_stes) { mlx5hws_dbg(ctx, "Required STEs [%d] exceeds initial action template STE [%d]\n", - required_stes, - matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes); + required_stes, matcher->action_ste.max_stes); return -ENOMEM; } @@ -1007,9 +960,9 @@ hws_matcher_set_templates(struct mlx5hws_matcher *matcher, if (!matcher->mt) return -ENOMEM; - matcher->at = kcalloc(num_of_at + matcher->attr.max_num_of_at_attach, - sizeof(*matcher->at), - GFP_KERNEL); + matcher->at = kvcalloc(num_of_at + matcher->attr.max_num_of_at_attach, + sizeof(*matcher->at), + GFP_KERNEL); if (!matcher->at) { mlx5hws_err(ctx, "Failed to allocate action template array\n"); ret = -ENOMEM; @@ -1035,7 +988,7 @@ free_mt: static void hws_matcher_unset_templates(struct mlx5hws_matcher *matcher) { - kfree(matcher->at); + kvfree(matcher->at); kfree(matcher->mt); } @@ -1157,8 +1110,7 @@ static int hws_matcher_resize_precheck(struct mlx5hws_matcher *src_matcher, return -EINVAL; } - if (src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes > - dst_matcher->action_ste[0].max_stes) { + if (src_matcher->action_ste.max_stes > dst_matcher->action_ste.max_stes) { mlx5hws_err(ctx, "Src/dst matcher max STEs mismatch\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h index 81ff487f57be..020de70270c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h @@ -18,6 +18,11 @@ /* Required depth of the main large table */ #define MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH 2 +/* Action RTC size multiplier that is required in order + * to support rule update for rules with action STEs. + */ +#define MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT 1 + enum mlx5hws_matcher_offset { MLX5HWS_MATCHER_OFFSET_TAG_DW1 = 12, MLX5HWS_MATCHER_OFFSET_TAG_DW0 = 13, @@ -52,15 +57,11 @@ struct mlx5hws_matcher_action_ste { u8 max_stes; }; -struct mlx5hws_matcher_resize_data_node { +struct mlx5hws_matcher_resize_data { struct mlx5hws_pool_chunk stc; u32 rtc_0_id; u32 rtc_1_id; struct mlx5hws_pool *pool; -}; - -struct mlx5hws_matcher_resize_data { - struct mlx5hws_matcher_resize_data_node action_ste[2]; u8 max_stes; struct list_head list_node; }; @@ -78,7 +79,7 @@ struct mlx5hws_matcher { struct mlx5hws_matcher *col_matcher; struct mlx5hws_matcher *resize_dst; struct mlx5hws_matcher_match_ste match_ste; - struct mlx5hws_matcher_action_ste action_ste[2]; + struct mlx5hws_matcher_action_ste action_ste; struct list_head list_node; struct list_head resize_data; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h index f39d636ff39a..5121951f2778 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h @@ -70,7 +70,6 @@ enum mlx5hws_send_queue_actions { struct mlx5hws_context_attr { u16 queues; u16 queue_size; - bool bwc; /* add support for backward compatible API*/ }; struct mlx5hws_table_attr { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c index 06db5e4726ae..d9dc4f2d0dc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c @@ -344,7 +344,7 @@ void mlx5hws_arg_write(struct mlx5hws_send_engine *queue, mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_ctrl, &wqe_len); memset(wqe_ctrl, 0, wqe_len); mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_arg, &wqe_len); - memcpy(wqe_arg, arg_data, wqe_len); + memcpy(wqe_arg, arg_data, MLX5HWS_ARG_DATA_SIZE); send_attr.id = arg_idx++; mlx5hws_send_engine_post_end(&ctrl, &send_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h index 27ca93385b08..8ddb51980044 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h @@ -31,7 +31,7 @@ struct mlx5hws_pattern_cache_item { u8 *data; u16 num_of_actions; } mh_data; - u32 refcount; + u32 refcount; /* protected by pattern_cache lock */ struct list_head ptrn_list_node; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c index fed2d913f3b8..50a81d360bb2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c @@ -183,7 +183,7 @@ static int hws_pool_buddy_get_mem_chunk(struct mlx5hws_pool *pool, *seg = -1; /* Find the next free place from the buddy array */ - while (*seg == -1) { + while (*seg < 0) { for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) { buddy = hws_pool_buddy_get_next_buddy(pool, i, order, @@ -194,7 +194,7 @@ static int hws_pool_buddy_get_mem_chunk(struct mlx5hws_pool *pool, } *seg = mlx5hws_buddy_alloc_mem(buddy, order); - if (*seg != -1) + if (*seg >= 0) goto found; if (pool->flags & MLX5HWS_POOL_FLAGS_ONE_RESOURCE) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h index de92cecbeb92..271490a51b96 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h @@ -390,11 +390,6 @@ struct mlx5_ifc_definer_bits { u8 match_mask[0x160]; }; -struct mlx5_ifc_arg_bits { - u8 rsvd0[0x88]; - u8 access_pd[0x18]; -}; - struct mlx5_ifc_header_modify_pattern_in_bits { u8 modify_field_select[0x40]; @@ -428,11 +423,6 @@ struct mlx5_ifc_create_definer_in_bits { struct mlx5_ifc_definer_bits definer; }; -struct mlx5_ifc_create_arg_in_bits { - struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; - struct mlx5_ifc_arg_bits arg; -}; - struct mlx5_ifc_create_header_modify_pattern_in_bits { struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; struct mlx5_ifc_header_modify_pattern_in_bits pattern; @@ -479,36 +469,4 @@ enum { MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL = 1, }; -struct mlx5_ifc_alloc_packet_reformat_out_bits { - u8 status[0x8]; - u8 reserved_at_8[0x18]; - - u8 syndrome[0x20]; - - u8 packet_reformat_id[0x20]; - - u8 reserved_at_60[0x20]; -}; - -struct mlx5_ifc_dealloc_packet_reformat_in_bits { - u8 opcode[0x10]; - u8 reserved_at_10[0x10]; - - u8 reserved_at_20[0x10]; - u8 op_mod[0x10]; - - u8 packet_reformat_id[0x20]; - - u8 reserved_at_60[0x20]; -}; - -struct mlx5_ifc_dealloc_packet_reformat_out_bits { - u8 status[0x8]; - u8 reserved_at_8[0x18]; - - u8 syndrome[0x20]; - - u8 reserved_at_40[0x40]; -}; - #endif /* MLX5_PRM_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c index e20c67a04203..a27a2d5ffc7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c @@ -129,27 +129,18 @@ static void hws_rule_gen_comp(struct mlx5hws_send_engine *queue, static void hws_rule_save_resize_info(struct mlx5hws_rule *rule, - struct mlx5hws_send_ste_attr *ste_attr, - bool is_update) + struct mlx5hws_send_ste_attr *ste_attr) { if (!mlx5hws_matcher_is_resizable(rule->matcher)) return; - if (likely(!is_update)) { + /* resize_info might already exist (if we're in update flow) */ + if (likely(!rule->resize_info)) { rule->resize_info = kzalloc(sizeof(*rule->resize_info), GFP_KERNEL); if (unlikely(!rule->resize_info)) { pr_warn("HWS: resize info isn't allocated for rule\n"); return; } - - rule->resize_info->max_stes = - rule->matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes; - rule->resize_info->action_ste_pool[0] = rule->matcher->action_ste[0].max_stes ? - rule->matcher->action_ste[0].pool : - NULL; - rule->resize_info->action_ste_pool[1] = rule->matcher->action_ste[1].max_stes ? - rule->matcher->action_ste[1].pool : - NULL; } memcpy(rule->resize_info->ctrl_seg, ste_attr->wqe_ctrl, @@ -204,15 +195,14 @@ hws_rule_load_delete_info(struct mlx5hws_rule *rule, } } -static int hws_rule_alloc_action_ste_idx(struct mlx5hws_rule *rule, - u8 action_ste_selector) +static int hws_rule_alloc_action_ste(struct mlx5hws_rule *rule) { struct mlx5hws_matcher *matcher = rule->matcher; struct mlx5hws_matcher_action_ste *action_ste; struct mlx5hws_pool_chunk ste = {0}; int ret; - action_ste = &matcher->action_ste[action_ste_selector]; + action_ste = &matcher->action_ste; ste.order = ilog2(roundup_pow_of_two(action_ste->max_stes)); ret = mlx5hws_pool_chunk_alloc(action_ste->pool, &ste); if (unlikely(ret)) { @@ -220,68 +210,29 @@ static int hws_rule_alloc_action_ste_idx(struct mlx5hws_rule *rule, "Failed to allocate STE for rule actions"); return ret; } - rule->action_ste_idx = ste.offset; + + rule->action_ste.pool = matcher->action_ste.pool; + rule->action_ste.num_stes = matcher->action_ste.max_stes; + rule->action_ste.index = ste.offset; return 0; } -static void hws_rule_free_action_ste_idx(struct mlx5hws_rule *rule, - u8 action_ste_selector) +void mlx5hws_rule_free_action_ste(struct mlx5hws_rule_action_ste_info *action_ste) { - struct mlx5hws_matcher *matcher = rule->matcher; struct mlx5hws_pool_chunk ste = {0}; - struct mlx5hws_pool *pool; - u8 max_stes; - if (mlx5hws_matcher_is_resizable(matcher)) { - /* Free the original action pool if rule was resized */ - max_stes = rule->resize_info->max_stes; - pool = rule->resize_info->action_ste_pool[action_ste_selector]; - } else { - max_stes = matcher->action_ste[action_ste_selector].max_stes; - pool = matcher->action_ste[action_ste_selector].pool; - } + if (!action_ste->num_stes) + return; - /* This release is safe only when the rule match part was deleted */ - ste.order = ilog2(roundup_pow_of_two(max_stes)); - ste.offset = rule->action_ste_idx; + ste.order = ilog2(roundup_pow_of_two(action_ste->num_stes)); + ste.offset = action_ste->index; - mlx5hws_pool_chunk_free(pool, &ste); -} - -static int hws_rule_alloc_action_ste(struct mlx5hws_rule *rule, - struct mlx5hws_rule_attr *attr) -{ - int action_ste_idx; - int ret; - - ret = hws_rule_alloc_action_ste_idx(rule, 0); - if (unlikely(ret)) - return ret; - - action_ste_idx = rule->action_ste_idx; - - ret = hws_rule_alloc_action_ste_idx(rule, 1); - if (unlikely(ret)) { - hws_rule_free_action_ste_idx(rule, 0); - return ret; - } - - /* Both pools have to return the same index */ - if (unlikely(rule->action_ste_idx != action_ste_idx)) { - pr_warn("HWS: allocation of action STE failed - pool indexes mismatch\n"); - return -EINVAL; - } - - return 0; -} - -void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule) -{ - if (rule->action_ste_idx > -1) { - hws_rule_free_action_ste_idx(rule, 1); - hws_rule_free_action_ste_idx(rule, 0); - } + /* This release is safe only when the rule match STE was deleted + * (when the rule is being deleted) or replaced with the new STE that + * isn't pointing to old action STEs (when the rule is being updated). + */ + mlx5hws_pool_chunk_free(action_ste->pool, &ste); } static void hws_rule_create_init(struct mlx5hws_rule *rule, @@ -298,14 +249,24 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule, /* In update we use these rtc's */ rule->rtc_0 = 0; rule->rtc_1 = 0; - rule->action_ste_selector = 0; + + rule->action_ste.pool = NULL; + rule->action_ste.num_stes = 0; + rule->action_ste.index = -1; + + rule->status = MLX5HWS_RULE_STATUS_CREATING; } else { - rule->action_ste_selector = !rule->action_ste_selector; + rule->status = MLX5HWS_RULE_STATUS_UPDATING; } + /* Initialize the old action STE info - shallow-copy action_ste. + * In create flow this will set old_action_ste fields to initial values. + * In update flow this will save the existing action STE info, + * so that we will later use it to free old STEs. + */ + rule->old_action_ste = rule->action_ste; + rule->pending_wqes = 0; - rule->action_ste_idx = -1; - rule->status = MLX5HWS_RULE_STATUS_CREATING; /* Init default send STE attributes */ ste_attr->gta_opcode = MLX5HWS_WQE_GTA_OP_ACTIVATE; @@ -315,8 +276,8 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule, /* Init default action apply */ apply->tbl_type = tbl->type; - apply->common_res = &ctx->common_res[tbl->type]; - apply->jump_to_action_stc = matcher->action_ste[0].stc.offset; + apply->common_res = &ctx->common_res; + apply->jump_to_action_stc = matcher->action_ste.stc.offset; apply->require_dep = 0; } @@ -332,8 +293,6 @@ static void hws_rule_move_init(struct mlx5hws_rule *rule, rule->rtc_1 = 0; rule->pending_wqes = 0; - rule->action_ste_idx = -1; - rule->action_ste_selector = 0; rule->status = MLX5HWS_RULE_STATUS_CREATING; rule->resize_info->state = MLX5HWS_RULE_RESIZE_STATE_WRITING; } @@ -394,21 +353,17 @@ static int hws_rule_create_hws(struct mlx5hws_rule *rule, if (action_stes) { /* Allocate action STEs for rules that need more than match STE */ - if (!is_update) { - ret = hws_rule_alloc_action_ste(rule, attr); - if (ret) { - mlx5hws_err(ctx, "Failed to allocate action memory %d", ret); - mlx5hws_send_abort_new_dep_wqe(queue); - return ret; - } + ret = hws_rule_alloc_action_ste(rule); + if (ret) { + mlx5hws_err(ctx, "Failed to allocate action memory %d", ret); + mlx5hws_send_abort_new_dep_wqe(queue); + return ret; } /* Skip RX/TX based on the dep_wqe init */ - ste_attr.rtc_0 = dep_wqe->rtc_0 ? - matcher->action_ste[rule->action_ste_selector].rtc_0_id : 0; - ste_attr.rtc_1 = dep_wqe->rtc_1 ? - matcher->action_ste[rule->action_ste_selector].rtc_1_id : 0; + ste_attr.rtc_0 = dep_wqe->rtc_0 ? matcher->action_ste.rtc_0_id : 0; + ste_attr.rtc_1 = dep_wqe->rtc_1 ? matcher->action_ste.rtc_1_id : 0; /* Action STEs are written to a specific index last to first */ - ste_attr.direct_index = rule->action_ste_idx + action_stes; + ste_attr.direct_index = rule->action_ste.index + action_stes; apply.next_direct_idx = ste_attr.direct_index; } else { apply.next_direct_idx = 0; @@ -459,7 +414,7 @@ static int hws_rule_create_hws(struct mlx5hws_rule *rule, if (!is_update) hws_rule_save_delete_info(rule, &ste_attr); - hws_rule_save_resize_info(rule, &ste_attr, is_update); + hws_rule_save_resize_info(rule, &ste_attr); mlx5hws_send_engine_inc_rule(queue); if (!attr->burst) @@ -480,7 +435,10 @@ static void hws_rule_destroy_failed_hws(struct mlx5hws_rule *rule, attr->user_data, MLX5HWS_RULE_STATUS_DELETED); /* Rule failed now we can safely release action STEs */ - mlx5hws_rule_free_action_ste(rule); + mlx5hws_rule_free_action_ste(&rule->action_ste); + + /* Perhaps the rule failed updating - release old action STEs as well */ + mlx5hws_rule_free_action_ste(&rule->old_action_ste); /* Clear complex tag */ hws_rule_clear_delete_info(rule); @@ -517,7 +475,8 @@ static int hws_rule_destroy_hws(struct mlx5hws_rule *rule, } /* Rule is not completed yet */ - if (rule->status == MLX5HWS_RULE_STATUS_CREATING) + if (rule->status == MLX5HWS_RULE_STATUS_CREATING || + rule->status == MLX5HWS_RULE_STATUS_UPDATING) return -EBUSY; /* Rule failed and doesn't require cleanup */ @@ -534,7 +493,7 @@ static int hws_rule_destroy_hws(struct mlx5hws_rule *rule, hws_rule_gen_comp(queue, rule, false, attr->user_data, MLX5HWS_RULE_STATUS_DELETED); - mlx5hws_rule_free_action_ste(rule); + mlx5hws_rule_free_action_ste(&rule->action_ste); mlx5hws_rule_clear_resize_info(rule); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h index 495cdd17e9f3..b5ee94ac449b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h @@ -15,6 +15,8 @@ enum mlx5hws_rule_status { MLX5HWS_RULE_STATUS_UNKNOWN, MLX5HWS_RULE_STATUS_CREATING, MLX5HWS_RULE_STATUS_CREATED, + MLX5HWS_RULE_STATUS_UPDATING, + MLX5HWS_RULE_STATUS_UPDATED, MLX5HWS_RULE_STATUS_DELETING, MLX5HWS_RULE_STATUS_DELETED, MLX5HWS_RULE_STATUS_FAILING, @@ -41,13 +43,17 @@ struct mlx5hws_rule_match_tag { }; }; +struct mlx5hws_rule_action_ste_info { + struct mlx5hws_pool *pool; + int index; /* STE array index */ + u8 num_stes; +}; + struct mlx5hws_rule_resize_info { - struct mlx5hws_pool *action_ste_pool[2]; u32 rtc_0; u32 rtc_1; u32 rule_idx; u8 state; - u8 max_stes; u8 ctrl_seg[MLX5HWS_WQE_SZ_GTA_CTRL]; /* Ctrl segment of STE: 48 bytes */ u8 data_seg[MLX5HWS_WQE_SZ_GTA_DATA]; /* Data segment of STE: 64 bytes */ }; @@ -58,18 +64,18 @@ struct mlx5hws_rule { struct mlx5hws_rule_match_tag tag; struct mlx5hws_rule_resize_info *resize_info; }; + struct mlx5hws_rule_action_ste_info action_ste; + struct mlx5hws_rule_action_ste_info old_action_ste; u32 rtc_0; /* The RTC into which the STE was inserted */ u32 rtc_1; /* The RTC into which the STE was inserted */ - int action_ste_idx; /* STE array index */ u8 status; /* enum mlx5hws_rule_status */ - u8 action_ste_selector; /* For rule update - which action STE is in use */ u8 pending_wqes; bool skip_delete; /* For complex rules - another rule with same tag * still exists, so don't actually delete this rule. */ }; -void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule); +void mlx5hws_rule_free_action_ste(struct mlx5hws_rule_action_ste_info *action_ste); int mlx5hws_rule_move_hws_remove(struct mlx5hws_rule *rule, void *queue, void *user_data); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c index 883b4ed30892..cb6abc4ab7df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c @@ -377,17 +377,25 @@ static void hws_send_engine_update_rule(struct mlx5hws_send_engine *queue, *status = MLX5HWS_FLOW_OP_ERROR; } else { - /* Increase the status, this only works on good flow as the enum - * is arrange it away creating -> created -> deleting -> deleted + /* Increase the status, this only works on good flow as + * the enum is arranged this way: + * - creating -> created + * - updating -> updated + * - deleting -> deleted */ priv->rule->status++; *status = MLX5HWS_FLOW_OP_SUCCESS; - /* Rule was deleted now we can safely release action STEs - * and clear resize info - */ if (priv->rule->status == MLX5HWS_RULE_STATUS_DELETED) { - mlx5hws_rule_free_action_ste(priv->rule); + /* Rule was deleted, now we can safely release + * action STEs and clear resize info + */ + mlx5hws_rule_free_action_ste(&priv->rule->action_ste); mlx5hws_rule_clear_resize_info(priv->rule); + } else if (priv->rule->status == MLX5HWS_RULE_STATUS_UPDATED) { + /* Rule was updated, free the old action STEs */ + mlx5hws_rule_free_action_ste(&priv->rule->old_action_ste); + /* Update completed - move the rule back to "created" */ + priv->rule->status = MLX5HWS_RULE_STATUS_CREATED; } } } @@ -633,6 +641,7 @@ static int hws_send_ring_create_sq(struct mlx5_core_dev *mdev, u32 pdn, MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST); MLX5_SET(sqc, sqc, flush_in_error_en, 1); + MLX5_SET(sqc, sqc, non_wire, 1); ts_format = mlx5_is_real_time_sq(mdev) ? MLX5_TIMESTAMP_FORMAT_REAL_TIME : MLX5_TIMESTAMP_FORMAT_FREE_RUNNING; @@ -896,15 +905,18 @@ close_cq: return err; } -void mlx5hws_send_queue_close(struct mlx5hws_send_engine *queue) +static void mlx5hws_send_queue_close(struct mlx5hws_send_engine *queue) { + if (!queue->num_entries) + return; /* this queue wasn't initialized */ + hws_send_ring_close(queue); kfree(queue->completed.entries); } -int mlx5hws_send_queue_open(struct mlx5hws_context *ctx, - struct mlx5hws_send_engine *queue, - u16 queue_size) +static int mlx5hws_send_queue_open(struct mlx5hws_context *ctx, + struct mlx5hws_send_engine *queue, + u16 queue_size) { int err; @@ -1005,7 +1017,7 @@ int mlx5hws_send_queues_open(struct mlx5hws_context *ctx, u16 queue_size) { int err = 0; - u32 i; + int i = 0; /* Open one extra queue for control path */ ctx->queues = queues + 1; @@ -1021,7 +1033,13 @@ int mlx5hws_send_queues_open(struct mlx5hws_context *ctx, goto free_bwc_locks; } - for (i = 0; i < ctx->queues; i++) { + /* If native API isn't supported, skip the unused native queues: + * initialize BWC queues and control queue only. + */ + if (!mlx5hws_context_native_supported(ctx)) + i = mlx5hws_bwc_get_queue_id(ctx, 0); + + for (; i < ctx->queues; i++) { err = mlx5hws_send_queue_open(ctx, &ctx->send_queue[i], queue_size); if (err) goto close_send_queues; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h index b50825d6dc53..f833092235c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h @@ -189,12 +189,6 @@ void mlx5hws_send_abort_new_dep_wqe(struct mlx5hws_send_engine *queue); void mlx5hws_send_all_dep_wqe(struct mlx5hws_send_engine *queue); -void mlx5hws_send_queue_close(struct mlx5hws_send_engine *queue); - -int mlx5hws_send_queue_open(struct mlx5hws_context *ctx, - struct mlx5hws_send_engine *queue, - u16 queue_size); - void mlx5hws_send_queues_close(struct mlx5hws_context *ctx); int mlx5hws_send_queues_open(struct mlx5hws_context *ctx, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c index 9576e02d00c3..ab1297531232 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c @@ -37,6 +37,7 @@ static void hws_table_set_cap_attr(struct mlx5hws_table *tbl, } static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl) +__must_hold(&tbl->ctx->ctrl_lock) { struct mlx5hws_cmd_ft_create_attr ft_attr = {0}; struct mlx5hws_cmd_set_fte_attr fte_attr = {0}; @@ -48,8 +49,8 @@ static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl) if (tbl->type != MLX5HWS_TABLE_TYPE_FDB) return 0; - if (ctx->common_res[tbl_type].default_miss) { - ctx->common_res[tbl_type].default_miss->refcount++; + if (ctx->common_res.default_miss) { + ctx->common_res.default_miss->refcount++; return 0; } @@ -70,29 +71,28 @@ static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl) return -EINVAL; } - /* ctx->ctrl_lock must be held here */ - ctx->common_res[tbl_type].default_miss = default_miss; - ctx->common_res[tbl_type].default_miss->refcount++; + ctx->common_res.default_miss = default_miss; + ctx->common_res.default_miss->refcount++; return 0; } /* Called under ctx->ctrl_lock */ static void hws_table_down_default_fdb_miss_tbl(struct mlx5hws_table *tbl) +__must_hold(&tbl->ctx->ctrl_lock) { struct mlx5hws_cmd_forward_tbl *default_miss; struct mlx5hws_context *ctx = tbl->ctx; - u8 tbl_type = tbl->type; if (tbl->type != MLX5HWS_TABLE_TYPE_FDB) return; - default_miss = ctx->common_res[tbl_type].default_miss; + default_miss = ctx->common_res.default_miss; if (--default_miss->refcount) return; mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, default_miss); - ctx->common_res[tbl_type].default_miss = NULL; + ctx->common_res.default_miss = NULL; } static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32 ft_id) @@ -478,15 +478,9 @@ int mlx5hws_table_set_default_miss(struct mlx5hws_table *tbl, if (old_miss_tbl) list_del_init(&tbl->default_miss.next); - old_miss_tbl = tbl->default_miss.miss_tbl; - if (old_miss_tbl) - list_del_init(&old_miss_tbl->default_miss.head); - if (miss_tbl) list_add(&tbl->default_miss.next, &miss_tbl->default_miss.head); - mutex_unlock(&ctx->ctrl_lock); - return 0; out: mutex_unlock(&ctx->ctrl_lock); return ret; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c index 49f22cad92bf..60cb4527588a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c @@ -8,7 +8,7 @@ #define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type) \ ((dmn)->info.caps.dmn_type##_sw_owner || \ ((dmn)->info.caps.dmn_type##_sw_owner_v2 && \ - (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_7)) + (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_8)) bool mlx5dr_domain_is_support_ptrn_arg(struct mlx5dr_domain *dmn) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c index 6fa06ba2d346..f57c84e5128b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c @@ -1067,7 +1067,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, int inlen, err, eqn; void *cqc, *in; __be64 *pas; - int vector; u32 i; cq = kzalloc(sizeof(*cq), GFP_KERNEL); @@ -1096,8 +1095,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, if (!in) goto err_cqwq; - vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev); - err = mlx5_comp_eqn_get(mdev, vector, &eqn); + err = mlx5_comp_eqn_get(mdev, 0, &eqn); if (err) { kvfree(in); goto err_cqwq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c index e94fbb015efa..c8b8ff80c7c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c @@ -555,7 +555,7 @@ void mlx5dr_ste_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes) { - ste_ctx->set_actions_tx(dmn, action_type_set, ste_ctx->actions_caps, + ste_ctx->set_actions_tx(ste_ctx, dmn, action_type_set, ste_ctx->actions_caps, hw_ste_arr, attr, added_stes); } @@ -566,7 +566,7 @@ void mlx5dr_ste_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes) { - ste_ctx->set_actions_rx(dmn, action_type_set, ste_ctx->actions_caps, + ste_ctx->set_actions_rx(ste_ctx, dmn, action_type_set, ste_ctx->actions_caps, hw_ste_arr, attr, added_stes); } @@ -1458,6 +1458,8 @@ struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx(u8 version) return mlx5dr_ste_get_ctx_v1(); else if (version == MLX5_STEERING_FORMAT_CONNECTX_7) return mlx5dr_ste_get_ctx_v2(); + else if (version == MLX5_STEERING_FORMAT_CONNECTX_8) + return mlx5dr_ste_get_ctx_v3(); return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h index 54a6619c3ecb..5f409dc30aca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h @@ -160,13 +160,15 @@ struct mlx5dr_ste_ctx { /* Actions */ u32 actions_caps; - void (*set_actions_rx)(struct mlx5dr_domain *dmn, + void (*set_actions_rx)(struct mlx5dr_ste_ctx *ste_ctx, + struct mlx5dr_domain *dmn, u8 *action_type_set, u32 actions_caps, u8 *hw_ste_arr, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes); - void (*set_actions_tx)(struct mlx5dr_domain *dmn, + void (*set_actions_tx)(struct mlx5dr_ste_ctx *ste_ctx, + struct mlx5dr_domain *dmn, u8 *action_type_set, u32 actions_caps, u8 *hw_ste_arr, @@ -197,7 +199,17 @@ struct mlx5dr_ste_ctx { u16 *used_hw_action_num); int (*alloc_modify_hdr_chunk)(struct mlx5dr_action *action); void (*dealloc_modify_hdr_chunk)(struct mlx5dr_action *action); - + /* Actions bit set */ + void (*set_encap)(u8 *hw_ste_p, u8 *d_action, + u32 reformat_id, int size); + void (*set_push_vlan)(u8 *ste, u8 *d_action, + u32 vlan_hdr); + void (*set_pop_vlan)(u8 *hw_ste_p, u8 *s_action, + u8 vlans_num); + void (*set_rx_decap)(u8 *hw_ste_p, u8 *s_action); + void (*set_encap_l3)(u8 *hw_ste_p, u8 *frst_s_action, + u8 *scnd_d_action, u32 reformat_id, + int size); /* Send */ void (*prepare_for_postsend)(u8 *hw_ste_p, u32 ste_size); }; @@ -205,5 +217,6 @@ struct mlx5dr_ste_ctx { struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v0(void); struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v1(void); struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v2(void); +struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v3(void); #endif /* _DR_STE_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c index e9f6c7ed7a7b..42536bee55e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c @@ -406,7 +406,8 @@ static void dr_ste_v0_arr_init_next(u8 **last_ste, } static void -dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, +dr_ste_v0_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx, + struct mlx5dr_domain *dmn, u8 *action_type_set, u32 actions_caps, u8 *last_ste, @@ -476,7 +477,8 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, } static void -dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn, +dr_ste_v0_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx, + struct mlx5dr_domain *dmn, u8 *action_type_set, u32 actions_caps, u8 *last_ste, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c index 1d49704b9542..7f83d77c43ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c @@ -5,136 +5,6 @@ #include "mlx5_ifc_dr_ste_v1.h" #include "dr_ste_v1.h" -#define DR_STE_CALC_DFNR_TYPE(lookup_type, inner) \ - ((inner) ? DR_STE_V1_LU_TYPE_##lookup_type##_I : \ - DR_STE_V1_LU_TYPE_##lookup_type##_O) - -enum dr_ste_v1_entry_format { - DR_STE_V1_TYPE_BWC_BYTE = 0x0, - DR_STE_V1_TYPE_BWC_DW = 0x1, - DR_STE_V1_TYPE_MATCH = 0x2, - DR_STE_V1_TYPE_MATCH_RANGES = 0x7, -}; - -/* Lookup type is built from 2B: [ Definer mode 1B ][ Definer index 1B ] */ -enum { - DR_STE_V1_LU_TYPE_NOP = 0x0000, - DR_STE_V1_LU_TYPE_ETHL2_TNL = 0x0002, - DR_STE_V1_LU_TYPE_IBL3_EXT = 0x0102, - DR_STE_V1_LU_TYPE_ETHL2_O = 0x0003, - DR_STE_V1_LU_TYPE_IBL4 = 0x0103, - DR_STE_V1_LU_TYPE_ETHL2_I = 0x0004, - DR_STE_V1_LU_TYPE_SRC_QP_GVMI = 0x0104, - DR_STE_V1_LU_TYPE_ETHL2_SRC_O = 0x0005, - DR_STE_V1_LU_TYPE_ETHL2_HEADERS_O = 0x0105, - DR_STE_V1_LU_TYPE_ETHL2_SRC_I = 0x0006, - DR_STE_V1_LU_TYPE_ETHL2_HEADERS_I = 0x0106, - DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_O = 0x0007, - DR_STE_V1_LU_TYPE_IPV6_DES_O = 0x0107, - DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_I = 0x0008, - DR_STE_V1_LU_TYPE_IPV6_DES_I = 0x0108, - DR_STE_V1_LU_TYPE_ETHL4_O = 0x0009, - DR_STE_V1_LU_TYPE_IPV6_SRC_O = 0x0109, - DR_STE_V1_LU_TYPE_ETHL4_I = 0x000a, - DR_STE_V1_LU_TYPE_IPV6_SRC_I = 0x010a, - DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_O = 0x000b, - DR_STE_V1_LU_TYPE_MPLS_O = 0x010b, - DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_I = 0x000c, - DR_STE_V1_LU_TYPE_MPLS_I = 0x010c, - DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_O = 0x000d, - DR_STE_V1_LU_TYPE_GRE = 0x010d, - DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER = 0x000e, - DR_STE_V1_LU_TYPE_GENERAL_PURPOSE = 0x010e, - DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_I = 0x000f, - DR_STE_V1_LU_TYPE_STEERING_REGISTERS_0 = 0x010f, - DR_STE_V1_LU_TYPE_STEERING_REGISTERS_1 = 0x0110, - DR_STE_V1_LU_TYPE_FLEX_PARSER_OK = 0x0011, - DR_STE_V1_LU_TYPE_FLEX_PARSER_0 = 0x0111, - DR_STE_V1_LU_TYPE_FLEX_PARSER_1 = 0x0112, - DR_STE_V1_LU_TYPE_ETHL4_MISC_O = 0x0113, - DR_STE_V1_LU_TYPE_ETHL4_MISC_I = 0x0114, - DR_STE_V1_LU_TYPE_INVALID = 0x00ff, - DR_STE_V1_LU_TYPE_DONT_CARE = MLX5DR_STE_LU_TYPE_DONT_CARE, -}; - -enum dr_ste_v1_header_anchors { - DR_STE_HEADER_ANCHOR_START_OUTER = 0x00, - DR_STE_HEADER_ANCHOR_1ST_VLAN = 0x02, - DR_STE_HEADER_ANCHOR_IPV6_IPV4 = 0x07, - DR_STE_HEADER_ANCHOR_INNER_MAC = 0x13, - DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4 = 0x19, -}; - -enum dr_ste_v1_action_size { - DR_STE_ACTION_SINGLE_SZ = 4, - DR_STE_ACTION_DOUBLE_SZ = 8, - DR_STE_ACTION_TRIPLE_SZ = 12, -}; - -enum dr_ste_v1_action_insert_ptr_attr { - DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE = 0, /* Regular push header (e.g. push vlan) */ - DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP = 1, /* Encapsulation / Tunneling */ - DR_STE_V1_ACTION_INSERT_PTR_ATTR_ESP = 2, /* IPsec */ -}; - -enum dr_ste_v1_action_id { - DR_STE_V1_ACTION_ID_NOP = 0x00, - DR_STE_V1_ACTION_ID_COPY = 0x05, - DR_STE_V1_ACTION_ID_SET = 0x06, - DR_STE_V1_ACTION_ID_ADD = 0x07, - DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE = 0x08, - DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER = 0x09, - DR_STE_V1_ACTION_ID_INSERT_INLINE = 0x0a, - DR_STE_V1_ACTION_ID_INSERT_POINTER = 0x0b, - DR_STE_V1_ACTION_ID_FLOW_TAG = 0x0c, - DR_STE_V1_ACTION_ID_QUEUE_ID_SEL = 0x0d, - DR_STE_V1_ACTION_ID_ACCELERATED_LIST = 0x0e, - DR_STE_V1_ACTION_ID_MODIFY_LIST = 0x0f, - DR_STE_V1_ACTION_ID_ASO = 0x12, - DR_STE_V1_ACTION_ID_TRAILER = 0x13, - DR_STE_V1_ACTION_ID_COUNTER_ID = 0x14, - DR_STE_V1_ACTION_ID_MAX = 0x21, - /* use for special cases */ - DR_STE_V1_ACTION_ID_SPECIAL_ENCAP_L3 = 0x22, -}; - -enum { - DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_0 = 0x00, - DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_1 = 0x01, - DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2 = 0x02, - DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0 = 0x08, - DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_1 = 0x09, - DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0 = 0x0e, - DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0 = 0x18, - DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_1 = 0x19, - DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_0 = 0x40, - DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_1 = 0x41, - DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_0 = 0x44, - DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_1 = 0x45, - DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_2 = 0x46, - DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_3 = 0x47, - DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_0 = 0x4c, - DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_1 = 0x4d, - DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_2 = 0x4e, - DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3 = 0x4f, - DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0 = 0x5e, - DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1 = 0x5f, - DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0 = 0x6f, - DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1 = 0x70, - DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE = 0x7b, - DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE = 0x7c, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_0 = 0x8c, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_1 = 0x8d, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_0 = 0x8e, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_1 = 0x8f, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_0 = 0x90, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_1 = 0x91, -}; - -enum dr_ste_v1_aso_ctx_type { - DR_STE_V1_ASO_CTX_TYPE_POLICERS = 0x2, -}; - static const struct mlx5dr_ste_action_modify_field dr_ste_v1_action_modify_field_arr[] = { [MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = { .hw_field = DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31, @@ -379,13 +249,12 @@ static void dr_ste_v1_set_counter_id(u8 *hw_ste_p, u32 ctr_id) MLX5_SET(ste_match_bwc_v1, hw_ste_p, counter_id, ctr_id); } -static void dr_ste_v1_set_reparse(u8 *hw_ste_p) +void dr_ste_v1_set_reparse(u8 *hw_ste_p) { MLX5_SET(ste_match_bwc_v1, hw_ste_p, reparse, 1); } -static void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action, - u32 reformat_id, int size) +void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action, u32 reformat_id, int size) { MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER); @@ -432,8 +301,7 @@ static void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action, dr_ste_v1_set_reparse(hw_ste_p); } -static void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action, - u32 vlan_hdr) +void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action, u32 vlan_hdr) { MLX5_SET(ste_double_action_insert_with_inline_v1, d_action, action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE); @@ -446,7 +314,7 @@ static void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action, dr_ste_v1_set_reparse(hw_ste_p); } -static void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num) +void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num) { MLX5_SET(ste_single_action_remove_header_size_v1, s_action, action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); @@ -459,11 +327,8 @@ static void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num) dr_ste_v1_set_reparse(hw_ste_p); } -static void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, - u8 *frst_s_action, - u8 *scnd_d_action, - u32 reformat_id, - int size) +void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, u8 *frst_s_action, u8 *scnd_d_action, + u32 reformat_id, int size) { /* Remove L2 headers */ MLX5_SET(ste_single_action_remove_header_v1, frst_s_action, action_id, @@ -483,7 +348,7 @@ static void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, dr_ste_v1_set_reparse(hw_ste_p); } -static void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action) +void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action) { MLX5_SET(ste_single_action_remove_header_v1, s_action, action_id, DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER); @@ -620,7 +485,8 @@ static void dr_ste_v1_arr_init_next_match_range(u8 **last_ste, dr_ste_v1_set_entry_type(*last_ste, DR_STE_V1_TYPE_MATCH_RANGES); } -void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, +void dr_ste_v1_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx, + struct mlx5dr_domain *dmn, u8 *action_type_set, u32 actions_caps, u8 *last_ste, @@ -640,7 +506,7 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, last_ste, action); action_sz = DR_STE_ACTION_TRIPLE_SZ; } - dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count); + ste_ctx->set_pop_vlan(last_ste, action, attr->vlans.count); action_sz -= DR_STE_ACTION_SINGLE_SZ; action += DR_STE_ACTION_SINGLE_SZ; @@ -677,8 +543,8 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, action_sz = DR_STE_ACTION_TRIPLE_SZ; allow_encap = true; } - dr_ste_v1_set_push_vlan(last_ste, action, - attr->vlans.headers[i]); + ste_ctx->set_push_vlan(last_ste, action, + attr->vlans.headers[i]); action_sz -= DR_STE_ACTION_DOUBLE_SZ; action += DR_STE_ACTION_DOUBLE_SZ; } @@ -691,9 +557,9 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, action_sz = DR_STE_ACTION_TRIPLE_SZ; allow_encap = true; } - dr_ste_v1_set_encap(last_ste, action, - attr->reformat.id, - attr->reformat.size); + ste_ctx->set_encap(last_ste, action, + attr->reformat.id, + attr->reformat.size); action_sz -= DR_STE_ACTION_DOUBLE_SZ; action += DR_STE_ACTION_DOUBLE_SZ; } else if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]) { @@ -706,10 +572,10 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, } d_action = action + DR_STE_ACTION_SINGLE_SZ; - dr_ste_v1_set_encap_l3(last_ste, - action, d_action, - attr->reformat.id, - attr->reformat.size); + ste_ctx->set_encap_l3(last_ste, + action, d_action, + attr->reformat.id, + attr->reformat.size); action_sz -= DR_STE_ACTION_TRIPLE_SZ; action += DR_STE_ACTION_TRIPLE_SZ; } else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) { @@ -776,7 +642,8 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1); } -void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, +void dr_ste_v1_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx, + struct mlx5dr_domain *dmn, u8 *action_type_set, u32 actions_caps, u8 *last_ste, @@ -799,7 +666,7 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, allow_modify_hdr = false; allow_ctr = false; } else if (action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2]) { - dr_ste_v1_set_rx_decap(last_ste, action); + ste_ctx->set_rx_decap(last_ste, action); action_sz -= DR_STE_ACTION_SINGLE_SZ; action += DR_STE_ACTION_SINGLE_SZ; allow_modify_hdr = false; @@ -827,7 +694,7 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, action_sz = DR_STE_ACTION_TRIPLE_SZ; } - dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count); + ste_ctx->set_pop_vlan(last_ste, action, attr->vlans.count); action_sz -= DR_STE_ACTION_SINGLE_SZ; action += DR_STE_ACTION_SINGLE_SZ; allow_ctr = false; @@ -868,8 +735,8 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, last_ste, action); action_sz = DR_STE_ACTION_TRIPLE_SZ; } - dr_ste_v1_set_push_vlan(last_ste, action, - attr->vlans.headers[i]); + ste_ctx->set_push_vlan(last_ste, action, + attr->vlans.headers[i]); action_sz -= DR_STE_ACTION_DOUBLE_SZ; action += DR_STE_ACTION_DOUBLE_SZ; } @@ -895,9 +762,9 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); action_sz = DR_STE_ACTION_TRIPLE_SZ; } - dr_ste_v1_set_encap(last_ste, action, - attr->reformat.id, - attr->reformat.size); + ste_ctx->set_encap(last_ste, action, + attr->reformat.id, + attr->reformat.size); action_sz -= DR_STE_ACTION_DOUBLE_SZ; action += DR_STE_ACTION_DOUBLE_SZ; allow_modify_hdr = false; @@ -912,10 +779,10 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, d_action = action + DR_STE_ACTION_SINGLE_SZ; - dr_ste_v1_set_encap_l3(last_ste, - action, d_action, - attr->reformat.id, - attr->reformat.size); + ste_ctx->set_encap_l3(last_ste, + action, d_action, + attr->reformat.id, + attr->reformat.size); action_sz -= DR_STE_ACTION_TRIPLE_SZ; allow_modify_hdr = false; } else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) { @@ -1027,9 +894,6 @@ void dr_ste_v1_set_action_copy(u8 *d_action, MLX5_SET(ste_double_action_copy_v1, d_action, source_right_shifter, src_shifter); } -#define DR_STE_DECAP_L3_ACTION_NUM 8 -#define DR_STE_L2_HDR_MAX_SZ 20 - int dr_ste_v1_set_action_decap_l3_list(void *data, u32 data_sz, u8 *hw_action, @@ -2330,7 +2194,12 @@ static struct mlx5dr_ste_ctx ste_ctx_v1 = { .set_action_decap_l3_list = &dr_ste_v1_set_action_decap_l3_list, .alloc_modify_hdr_chunk = &dr_ste_v1_alloc_modify_hdr_ptrn_arg, .dealloc_modify_hdr_chunk = &dr_ste_v1_free_modify_hdr_ptrn_arg, - + /* Actions bit set */ + .set_encap = &dr_ste_v1_set_encap, + .set_push_vlan = &dr_ste_v1_set_push_vlan, + .set_pop_vlan = &dr_ste_v1_set_pop_vlan, + .set_rx_decap = &dr_ste_v1_set_rx_decap, + .set_encap_l3 = &dr_ste_v1_set_encap_l3, /* Send */ .prepare_for_postsend = &dr_ste_v1_prepare_for_postsend, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h index e2fc69867088..a8d9e308d339 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h @@ -7,6 +7,138 @@ #include "dr_types.h" #include "dr_ste.h" +#define DR_STE_DECAP_L3_ACTION_NUM 8 +#define DR_STE_L2_HDR_MAX_SZ 20 +#define DR_STE_CALC_DFNR_TYPE(lookup_type, inner) \ + ((inner) ? DR_STE_V1_LU_TYPE_##lookup_type##_I : \ + DR_STE_V1_LU_TYPE_##lookup_type##_O) + +enum dr_ste_v1_entry_format { + DR_STE_V1_TYPE_BWC_BYTE = 0x0, + DR_STE_V1_TYPE_BWC_DW = 0x1, + DR_STE_V1_TYPE_MATCH = 0x2, + DR_STE_V1_TYPE_MATCH_RANGES = 0x7, +}; + +/* Lookup type is built from 2B: [ Definer mode 1B ][ Definer index 1B ] */ +enum { + DR_STE_V1_LU_TYPE_NOP = 0x0000, + DR_STE_V1_LU_TYPE_ETHL2_TNL = 0x0002, + DR_STE_V1_LU_TYPE_IBL3_EXT = 0x0102, + DR_STE_V1_LU_TYPE_ETHL2_O = 0x0003, + DR_STE_V1_LU_TYPE_IBL4 = 0x0103, + DR_STE_V1_LU_TYPE_ETHL2_I = 0x0004, + DR_STE_V1_LU_TYPE_SRC_QP_GVMI = 0x0104, + DR_STE_V1_LU_TYPE_ETHL2_SRC_O = 0x0005, + DR_STE_V1_LU_TYPE_ETHL2_HEADERS_O = 0x0105, + DR_STE_V1_LU_TYPE_ETHL2_SRC_I = 0x0006, + DR_STE_V1_LU_TYPE_ETHL2_HEADERS_I = 0x0106, + DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_O = 0x0007, + DR_STE_V1_LU_TYPE_IPV6_DES_O = 0x0107, + DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_I = 0x0008, + DR_STE_V1_LU_TYPE_IPV6_DES_I = 0x0108, + DR_STE_V1_LU_TYPE_ETHL4_O = 0x0009, + DR_STE_V1_LU_TYPE_IPV6_SRC_O = 0x0109, + DR_STE_V1_LU_TYPE_ETHL4_I = 0x000a, + DR_STE_V1_LU_TYPE_IPV6_SRC_I = 0x010a, + DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_O = 0x000b, + DR_STE_V1_LU_TYPE_MPLS_O = 0x010b, + DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_I = 0x000c, + DR_STE_V1_LU_TYPE_MPLS_I = 0x010c, + DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_O = 0x000d, + DR_STE_V1_LU_TYPE_GRE = 0x010d, + DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER = 0x000e, + DR_STE_V1_LU_TYPE_GENERAL_PURPOSE = 0x010e, + DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_I = 0x000f, + DR_STE_V1_LU_TYPE_STEERING_REGISTERS_0 = 0x010f, + DR_STE_V1_LU_TYPE_STEERING_REGISTERS_1 = 0x0110, + DR_STE_V1_LU_TYPE_FLEX_PARSER_OK = 0x0011, + DR_STE_V1_LU_TYPE_FLEX_PARSER_0 = 0x0111, + DR_STE_V1_LU_TYPE_FLEX_PARSER_1 = 0x0112, + DR_STE_V1_LU_TYPE_ETHL4_MISC_O = 0x0113, + DR_STE_V1_LU_TYPE_ETHL4_MISC_I = 0x0114, + DR_STE_V1_LU_TYPE_INVALID = 0x00ff, + DR_STE_V1_LU_TYPE_DONT_CARE = MLX5DR_STE_LU_TYPE_DONT_CARE, +}; + +enum dr_ste_v1_header_anchors { + DR_STE_HEADER_ANCHOR_START_OUTER = 0x00, + DR_STE_HEADER_ANCHOR_1ST_VLAN = 0x02, + DR_STE_HEADER_ANCHOR_IPV6_IPV4 = 0x07, + DR_STE_HEADER_ANCHOR_INNER_MAC = 0x13, + DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4 = 0x19, +}; + +enum dr_ste_v1_action_size { + DR_STE_ACTION_SINGLE_SZ = 4, + DR_STE_ACTION_DOUBLE_SZ = 8, + DR_STE_ACTION_TRIPLE_SZ = 12, +}; + +enum dr_ste_v1_action_insert_ptr_attr { + DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE = 0, /* Regular push header (e.g. push vlan) */ + DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP = 1, /* Encapsulation / Tunneling */ + DR_STE_V1_ACTION_INSERT_PTR_ATTR_ESP = 2, /* IPsec */ +}; + +enum dr_ste_v1_action_id { + DR_STE_V1_ACTION_ID_NOP = 0x00, + DR_STE_V1_ACTION_ID_COPY = 0x05, + DR_STE_V1_ACTION_ID_SET = 0x06, + DR_STE_V1_ACTION_ID_ADD = 0x07, + DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE = 0x08, + DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER = 0x09, + DR_STE_V1_ACTION_ID_INSERT_INLINE = 0x0a, + DR_STE_V1_ACTION_ID_INSERT_POINTER = 0x0b, + DR_STE_V1_ACTION_ID_FLOW_TAG = 0x0c, + DR_STE_V1_ACTION_ID_QUEUE_ID_SEL = 0x0d, + DR_STE_V1_ACTION_ID_ACCELERATED_LIST = 0x0e, + DR_STE_V1_ACTION_ID_MODIFY_LIST = 0x0f, + DR_STE_V1_ACTION_ID_ASO = 0x12, + DR_STE_V1_ACTION_ID_TRAILER = 0x13, + DR_STE_V1_ACTION_ID_COUNTER_ID = 0x14, + DR_STE_V1_ACTION_ID_MAX = 0x21, + /* use for special cases */ + DR_STE_V1_ACTION_ID_SPECIAL_ENCAP_L3 = 0x22, +}; + +enum { + DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_0 = 0x00, + DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_1 = 0x01, + DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2 = 0x02, + DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0 = 0x08, + DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_1 = 0x09, + DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0 = 0x0e, + DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0 = 0x18, + DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_1 = 0x19, + DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_0 = 0x40, + DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_1 = 0x41, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_0 = 0x44, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_1 = 0x45, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_2 = 0x46, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_3 = 0x47, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_0 = 0x4c, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_1 = 0x4d, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_2 = 0x4e, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3 = 0x4f, + DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0 = 0x5e, + DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1 = 0x5f, + DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0 = 0x6f, + DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1 = 0x70, + DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE = 0x7b, + DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE = 0x7c, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_0 = 0x8c, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_1 = 0x8d, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_0 = 0x8e, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_1 = 0x8f, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_0 = 0x90, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_1 = 0x91, +}; + +enum dr_ste_v1_aso_ctx_type { + DR_STE_V1_ASO_CTX_TYPE_POLICERS = 0x2, +}; + bool dr_ste_v1_is_miss_addr_set(u8 *hw_ste_p); void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr); u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p); @@ -17,11 +149,18 @@ u16 dr_ste_v1_get_next_lu_type(u8 *hw_ste_p); void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size); void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type, bool is_rx, u16 gvmi); void dr_ste_v1_prepare_for_postsend(u8 *hw_ste_p, u32 ste_size); -void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, u8 *action_type_set, - u32 actions_caps, u8 *last_ste, +void dr_ste_v1_set_reparse(u8 *hw_ste_p); +void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action, u32 reformat_id, int size); +void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action, u32 vlan_hdr); +void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num); +void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, u8 *frst_s_action, u8 *scnd_d_action, + u32 reformat_id, int size); +void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action); +void dr_ste_v1_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_domain *dmn, + u8 *action_type_set, u32 actions_caps, u8 *last_ste, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes); -void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, u8 *action_type_set, - u32 actions_caps, u8 *last_ste, +void dr_ste_v1_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_domain *dmn, + u8 *action_type_set, u32 actions_caps, u8 *last_ste, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes); void dr_ste_v1_set_action_set(u8 *d_action, u8 hw_field, u8 shifter, u8 length, u32 data); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c index 808b013cf48c..0882dba0f64b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c @@ -2,167 +2,7 @@ /* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ #include "dr_ste_v1.h" - -enum { - DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0 = 0x00, - DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1 = 0x01, - DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2 = 0x02, - DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0 = 0x08, - DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1 = 0x09, - DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0 = 0x0e, - DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0 = 0x18, - DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1 = 0x19, - DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0 = 0x40, - DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1 = 0x41, - DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0 = 0x44, - DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1 = 0x45, - DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2 = 0x46, - DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3 = 0x47, - DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0 = 0x4c, - DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1 = 0x4d, - DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2 = 0x4e, - DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3 = 0x4f, - DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0 = 0x5e, - DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1 = 0x5f, - DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0 = 0x6f, - DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1 = 0x70, - DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE = 0x7b, - DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE = 0x7c, - DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0 = 0x90, - DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1 = 0x91, - DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0 = 0x92, - DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1 = 0x93, - DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0 = 0x94, - DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1 = 0x95, -}; - -static const struct mlx5dr_ste_action_modify_field dr_ste_v2_action_modify_field_arr[] = { - [MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1, .start = 16, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 0, .end = 15, - }, - [MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 16, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 18, .end = 23, - }, - [MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1, .start = 16, .end = 24, - .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, - }, - [MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31, - .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, - }, - [MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15, - .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, - }, - [MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, - }, - [MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, - }, - [MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31, - .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP, - }, - [MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15, - .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP, - }, - [MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, - }, - [MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, - }, - [MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, - }, - [MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, - }, - [MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, - }, - [MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, - }, - [MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, - }, - [MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, - }, - [MLX5_ACTION_IN_FIELD_OUT_SIPV4] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, - }, - [MLX5_ACTION_IN_FIELD_OUT_DIPV4] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1, .start = 0, .end = 31, - .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, - }, - [MLX5_ACTION_IN_FIELD_METADATA_REG_A] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_METADATA_REG_B] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15, - }, - [MLX5_ACTION_IN_FIELD_OUT_EMD_31_0] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1, .start = 0, .end = 31, - }, - [MLX5_ACTION_IN_FIELD_OUT_EMD_47_32] = { - .hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0, .start = 0, .end = 15, - }, -}; +#include "dr_ste_v2.h" static struct mlx5dr_ste_ctx ste_ctx_v2 = { /* Builders */ @@ -223,7 +63,12 @@ static struct mlx5dr_ste_ctx ste_ctx_v2 = { .set_action_decap_l3_list = &dr_ste_v1_set_action_decap_l3_list, .alloc_modify_hdr_chunk = &dr_ste_v1_alloc_modify_hdr_ptrn_arg, .dealloc_modify_hdr_chunk = &dr_ste_v1_free_modify_hdr_ptrn_arg, - + /* Actions bit set */ + .set_encap = &dr_ste_v1_set_encap, + .set_push_vlan = &dr_ste_v1_set_push_vlan, + .set_pop_vlan = &dr_ste_v1_set_pop_vlan, + .set_rx_decap = &dr_ste_v1_set_rx_decap, + .set_encap_l3 = &dr_ste_v1_set_encap_l3, /* Send */ .prepare_for_postsend = &dr_ste_v1_prepare_for_postsend, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.h new file mode 100644 index 000000000000..d853fde49cfc --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.h @@ -0,0 +1,168 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef _DR_STE_V2_ +#define _DR_STE_V2_ + +enum { + DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0 = 0x00, + DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1 = 0x01, + DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2 = 0x02, + DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0 = 0x08, + DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1 = 0x09, + DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0 = 0x0e, + DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0 = 0x18, + DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1 = 0x19, + DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0 = 0x40, + DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1 = 0x41, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0 = 0x44, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1 = 0x45, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2 = 0x46, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3 = 0x47, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0 = 0x4c, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1 = 0x4d, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2 = 0x4e, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3 = 0x4f, + DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0 = 0x5e, + DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1 = 0x5f, + DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0 = 0x6f, + DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1 = 0x70, + DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE = 0x7b, + DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE = 0x7c, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0 = 0x90, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1 = 0x91, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0 = 0x92, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1 = 0x93, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0 = 0x94, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1 = 0x95, +}; + +static const struct mlx5dr_ste_action_modify_field dr_ste_v2_action_modify_field_arr[] = { + [MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1, .start = 16, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 0, .end = 15, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 16, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 18, .end = 23, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1, .start = 16, .end = 24, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV4] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV4] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_A] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_B] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15, + }, + [MLX5_ACTION_IN_FIELD_OUT_EMD_31_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_EMD_47_32] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0, .start = 0, .end = 15, + }, +}; + +#endif /* _DR_STE_V2_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c new file mode 100644 index 000000000000..cc60ce1d274e --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include "dr_ste_v1.h" +#include "dr_ste_v2.h" + +static void dr_ste_v3_set_encap(u8 *hw_ste_p, u8 *d_action, + u32 reformat_id, int size) +{ + MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, action_id, + DR_STE_V1_ACTION_ID_INSERT_POINTER); + /* The hardware expects here size in words (2 byte) */ + MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, size, size / 2); + MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, pointer, reformat_id); + MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, attributes, + DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP); + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v3_set_push_vlan(u8 *ste, u8 *d_action, + u32 vlan_hdr) +{ + MLX5_SET(ste_double_action_insert_with_inline_v3, d_action, action_id, + DR_STE_V1_ACTION_ID_INSERT_INLINE); + /* The hardware expects here offset to vlan header in words (2 byte) */ + MLX5_SET(ste_double_action_insert_with_inline_v3, d_action, start_offset, + HDR_LEN_L2_MACS >> 1); + MLX5_SET(ste_double_action_insert_with_inline_v3, d_action, inline_data, vlan_hdr); + dr_ste_v1_set_reparse(ste); +} + +static void dr_ste_v3_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, + u8 vlans_num) +{ + MLX5_SET(ste_single_action_remove_header_size_v3, s_action, + action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); + MLX5_SET(ste_single_action_remove_header_size_v3, s_action, + start_anchor, DR_STE_HEADER_ANCHOR_1ST_VLAN); + /* The hardware expects here size in words (2 byte) */ + MLX5_SET(ste_single_action_remove_header_size_v3, s_action, + remove_size, (HDR_LEN_L2_VLAN >> 1) * vlans_num); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v3_set_encap_l3(u8 *hw_ste_p, + u8 *frst_s_action, + u8 *scnd_d_action, + u32 reformat_id, + int size) +{ + /* Remove L2 headers */ + MLX5_SET(ste_single_action_remove_header_v3, frst_s_action, action_id, + DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER); + MLX5_SET(ste_single_action_remove_header_v3, frst_s_action, end_anchor, + DR_STE_HEADER_ANCHOR_IPV6_IPV4); + + /* Encapsulate with given reformat ID */ + MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, action_id, + DR_STE_V1_ACTION_ID_INSERT_POINTER); + /* The hardware expects here size in words (2 byte) */ + MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, size, size / 2); + MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, pointer, reformat_id); + MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, attributes, + DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v3_set_rx_decap(u8 *hw_ste_p, u8 *s_action) +{ + MLX5_SET(ste_single_action_remove_header_v3, s_action, action_id, + DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER); + MLX5_SET(ste_single_action_remove_header_v3, s_action, decap, 1); + MLX5_SET(ste_single_action_remove_header_v3, s_action, vni_to_cqe, 1); + MLX5_SET(ste_single_action_remove_header_v3, s_action, end_anchor, + DR_STE_HEADER_ANCHOR_INNER_MAC); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static int +dr_ste_v3_set_action_decap_l3_list(void *data, u32 data_sz, + u8 *hw_action, u32 hw_action_sz, + uint16_t *used_hw_action_num) +{ + u8 padded_data[DR_STE_L2_HDR_MAX_SZ] = {}; + void *data_ptr = padded_data; + u16 used_actions = 0; + u32 inline_data_sz; + u32 i; + + if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM) + return -EINVAL; + + inline_data_sz = + MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v3, inline_data); + + /* Add an alignment padding */ + memcpy(padded_data + data_sz % inline_data_sz, data, data_sz); + + /* Remove L2L3 outer headers */ + MLX5_SET(ste_single_action_remove_header_v3, hw_action, action_id, + DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER); + MLX5_SET(ste_single_action_remove_header_v3, hw_action, decap, 1); + MLX5_SET(ste_single_action_remove_header_v3, hw_action, vni_to_cqe, 1); + MLX5_SET(ste_single_action_remove_header_v3, hw_action, end_anchor, + DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4); + hw_action += DR_STE_ACTION_DOUBLE_SZ; + used_actions++; /* Remove and NOP are a single double action */ + + /* Point to the last dword of the header */ + data_ptr += (data_sz / inline_data_sz) * inline_data_sz; + + /* Add the new header using inline action 4Byte at a time, the header + * is added in reversed order to the beginning of the packet to avoid + * incorrect parsing by the HW. Since header is 14B or 18B an extra + * two bytes are padded and later removed. + */ + for (i = 0; i < data_sz / inline_data_sz + 1; i++) { + void *addr_inline; + + MLX5_SET(ste_double_action_insert_with_inline_v3, hw_action, action_id, + DR_STE_V1_ACTION_ID_INSERT_INLINE); + /* The hardware expects here offset to words (2 bytes) */ + MLX5_SET(ste_double_action_insert_with_inline_v3, hw_action, start_offset, 0); + + /* Copy bytes one by one to avoid endianness problem */ + addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v3, + hw_action, inline_data); + memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz); + hw_action += DR_STE_ACTION_DOUBLE_SZ; + used_actions++; + } + + /* Remove first 2 extra bytes */ + MLX5_SET(ste_single_action_remove_header_size_v3, hw_action, action_id, + DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); + MLX5_SET(ste_single_action_remove_header_size_v3, hw_action, start_offset, 0); + /* The hardware expects here size in words (2 bytes) */ + MLX5_SET(ste_single_action_remove_header_size_v3, hw_action, remove_size, 1); + used_actions++; + + *used_hw_action_num = used_actions; + + return 0; +} + +static struct mlx5dr_ste_ctx ste_ctx_v3 = { + /* Builders */ + .build_eth_l2_src_dst_init = &dr_ste_v1_build_eth_l2_src_dst_init, + .build_eth_l3_ipv6_src_init = &dr_ste_v1_build_eth_l3_ipv6_src_init, + .build_eth_l3_ipv6_dst_init = &dr_ste_v1_build_eth_l3_ipv6_dst_init, + .build_eth_l3_ipv4_5_tuple_init = &dr_ste_v1_build_eth_l3_ipv4_5_tuple_init, + .build_eth_l2_src_init = &dr_ste_v1_build_eth_l2_src_init, + .build_eth_l2_dst_init = &dr_ste_v1_build_eth_l2_dst_init, + .build_eth_l2_tnl_init = &dr_ste_v1_build_eth_l2_tnl_init, + .build_eth_l3_ipv4_misc_init = &dr_ste_v1_build_eth_l3_ipv4_misc_init, + .build_eth_ipv6_l3_l4_init = &dr_ste_v1_build_eth_ipv6_l3_l4_init, + .build_mpls_init = &dr_ste_v1_build_mpls_init, + .build_tnl_gre_init = &dr_ste_v1_build_tnl_gre_init, + .build_tnl_mpls_init = &dr_ste_v1_build_tnl_mpls_init, + .build_tnl_mpls_over_udp_init = &dr_ste_v1_build_tnl_mpls_over_udp_init, + .build_tnl_mpls_over_gre_init = &dr_ste_v1_build_tnl_mpls_over_gre_init, + .build_icmp_init = &dr_ste_v1_build_icmp_init, + .build_general_purpose_init = &dr_ste_v1_build_general_purpose_init, + .build_eth_l4_misc_init = &dr_ste_v1_build_eth_l4_misc_init, + .build_tnl_vxlan_gpe_init = &dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init, + .build_tnl_geneve_init = &dr_ste_v1_build_flex_parser_tnl_geneve_init, + .build_tnl_geneve_tlv_opt_init = &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init, + .build_tnl_geneve_tlv_opt_exist_init = + &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_init, + .build_register_0_init = &dr_ste_v1_build_register_0_init, + .build_register_1_init = &dr_ste_v1_build_register_1_init, + .build_src_gvmi_qpn_init = &dr_ste_v1_build_src_gvmi_qpn_init, + .build_flex_parser_0_init = &dr_ste_v1_build_flex_parser_0_init, + .build_flex_parser_1_init = &dr_ste_v1_build_flex_parser_1_init, + .build_tnl_gtpu_init = &dr_ste_v1_build_flex_parser_tnl_gtpu_init, + .build_tnl_header_0_1_init = &dr_ste_v1_build_tnl_header_0_1_init, + .build_tnl_gtpu_flex_parser_0_init = &dr_ste_v1_build_tnl_gtpu_flex_parser_0_init, + .build_tnl_gtpu_flex_parser_1_init = &dr_ste_v1_build_tnl_gtpu_flex_parser_1_init, + + /* Getters and Setters */ + .ste_init = &dr_ste_v1_init, + .set_next_lu_type = &dr_ste_v1_set_next_lu_type, + .get_next_lu_type = &dr_ste_v1_get_next_lu_type, + .is_miss_addr_set = &dr_ste_v1_is_miss_addr_set, + .set_miss_addr = &dr_ste_v1_set_miss_addr, + .get_miss_addr = &dr_ste_v1_get_miss_addr, + .set_hit_addr = &dr_ste_v1_set_hit_addr, + .set_byte_mask = &dr_ste_v1_set_byte_mask, + .get_byte_mask = &dr_ste_v1_get_byte_mask, + + /* Actions */ + .actions_caps = DR_STE_CTX_ACTION_CAP_TX_POP | + DR_STE_CTX_ACTION_CAP_RX_PUSH | + DR_STE_CTX_ACTION_CAP_RX_ENCAP, + .set_actions_rx = &dr_ste_v1_set_actions_rx, + .set_actions_tx = &dr_ste_v1_set_actions_tx, + .modify_field_arr_sz = ARRAY_SIZE(dr_ste_v2_action_modify_field_arr), + .modify_field_arr = dr_ste_v2_action_modify_field_arr, + .set_action_set = &dr_ste_v1_set_action_set, + .set_action_add = &dr_ste_v1_set_action_add, + .set_action_copy = &dr_ste_v1_set_action_copy, + .set_action_decap_l3_list = &dr_ste_v3_set_action_decap_l3_list, + .alloc_modify_hdr_chunk = &dr_ste_v1_alloc_modify_hdr_ptrn_arg, + .dealloc_modify_hdr_chunk = &dr_ste_v1_free_modify_hdr_ptrn_arg, + /* Actions bit set */ + .set_encap = &dr_ste_v3_set_encap, + .set_push_vlan = &dr_ste_v3_set_push_vlan, + .set_pop_vlan = &dr_ste_v3_set_pop_vlan, + .set_rx_decap = &dr_ste_v3_set_rx_decap, + .set_encap_l3 = &dr_ste_v3_set_encap_l3, + /* Send */ + .prepare_for_postsend = &dr_ste_v1_prepare_for_postsend, +}; + +struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v3(void) +{ + return &ste_ctx_v3; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c index 4b349d4005e4..8007d3f523c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c @@ -521,7 +521,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, goto free_actions; } - id = dst->dest_attr.counter_id; + id = mlx5_fc_id(dst->dest_attr.counter); tmp_action = mlx5dr_action_create_flow_counter(id); if (!tmp_action) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h index fb078fa0f0cc..898c3618ff26 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h @@ -600,4 +600,44 @@ struct mlx5_ifc_ste_double_action_aso_v1_bits { }; }; +struct mlx5_ifc_ste_single_action_remove_header_v3_bits { + u8 action_id[0x8]; + u8 start_anchor[0x7]; + u8 end_anchor[0x7]; + u8 reserved_at_16[0x1]; + u8 outer_l4_remove[0x1]; + u8 reserved_at_18[0x4]; + u8 decap[0x1]; + u8 vni_to_cqe[0x1]; + u8 qos_profile[0x2]; +}; + +struct mlx5_ifc_ste_single_action_remove_header_size_v3_bits { + u8 action_id[0x8]; + u8 start_anchor[0x7]; + u8 start_offset[0x8]; + u8 outer_l4_remove[0x1]; + u8 reserved_at_18[0x2]; + u8 remove_size[0x6]; +}; + +struct mlx5_ifc_ste_double_action_insert_with_inline_v3_bits { + u8 action_id[0x8]; + u8 start_anchor[0x7]; + u8 start_offset[0x8]; + u8 reserved_at_17[0x9]; + + u8 inline_data[0x20]; +}; + +struct mlx5_ifc_ste_double_action_insert_with_ptr_v3_bits { + u8 action_id[0x8]; + u8 start_anchor[0x7]; + u8 start_offset[0x8]; + u8 size[0x6]; + u8 attributes[0x3]; + + u8 pointer[0x20]; +}; + #endif /* MLX5_IFC_DR_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h index 3ac7dc67509f..0bb3724c10c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h @@ -160,7 +160,7 @@ mlx5dr_is_supported(struct mlx5_core_dev *dev) (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && (MLX5_CAP_GEN(dev, steering_format_version) <= - MLX5_STEERING_FORMAT_CONNECTX_7))); + MLX5_STEERING_FORMAT_CONNECTX_8))); } /* buddy functions & structure */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wc.c b/drivers/net/ethernet/mellanox/mlx5/core/wc.c index 1bed75eca97d..740b719e7072 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wc.c @@ -382,6 +382,7 @@ err_alloc_bfreg: bool mlx5_wc_support_get(struct mlx5_core_dev *mdev) { + struct mutex *wc_state_lock = &mdev->wc_state_lock; struct mlx5_core_dev *parent = NULL; if (!MLX5_CAP_GEN(mdev, bf)) { @@ -400,32 +401,31 @@ bool mlx5_wc_support_get(struct mlx5_core_dev *mdev) */ goto out; - mutex_lock(&mdev->wc_state_lock); +#ifdef CONFIG_MLX5_SF + if (mlx5_core_is_sf(mdev)) { + parent = mdev->priv.parent_mdev; + wc_state_lock = &parent->wc_state_lock; + } +#endif + + mutex_lock(wc_state_lock); if (mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED) goto unlock; -#ifdef CONFIG_MLX5_SF - if (mlx5_core_is_sf(mdev)) - parent = mdev->priv.parent_mdev; -#endif - if (parent) { - mutex_lock(&parent->wc_state_lock); - mlx5_core_test_wc(parent); mlx5_core_dbg(mdev, "parent set wc_state=%d\n", parent->wc_state); mdev->wc_state = parent->wc_state; - mutex_unlock(&parent->wc_state_lock); + } else { + mlx5_core_test_wc(mdev); } - mlx5_core_test_wc(mdev); - unlock: - mutex_unlock(&mdev->wc_state_lock); + mutex_unlock(wc_state_lock); out: mlx5_core_dbg(mdev, "wc_state=%d\n", mdev->wc_state); diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c index 46245e0b2462..43c84900369a 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c @@ -14,7 +14,6 @@ #define MLXFW_FSM_STATE_WAIT_TIMEOUT_MS 30000 #define MLXFW_FSM_STATE_WAIT_ROUNDS \ (MLXFW_FSM_STATE_WAIT_TIMEOUT_MS / MLXFW_FSM_STATE_WAIT_CYCLE_MS) -#define MLXFW_FSM_MAX_COMPONENT_SIZE (10 * (1 << 20)) static const int mlxfw_fsm_state_errno[] = { [MLXFW_FSM_STATE_ERR_ERROR] = -EIO, @@ -229,7 +228,6 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev, return err; } - comp_max_size = min_t(u32, comp_max_size, MLXFW_FSM_MAX_COMPONENT_SIZE); if (comp->data_size > comp_max_size) { MLXFW_ERR_MSG(mlxfw_dev, extack, "Component size is bigger than limit", -EINVAL); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 4a79c0d7e7ad..2bb2b77351bd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -35,6 +35,7 @@ #include "reg.h" #include "resources.h" #include "../mlxfw/mlxfw.h" +#include "txheader.h" static LIST_HEAD(mlxsw_core_driver_list); static DEFINE_SPINLOCK(mlxsw_core_driver_list_lock); @@ -677,7 +678,7 @@ struct mlxsw_reg_trans { struct list_head bulk_list; struct mlxsw_core *core; struct sk_buff *tx_skb; - struct mlxsw_tx_info tx_info; + struct mlxsw_txhdr_info txhdr_info; struct delayed_work timeout_dw; unsigned int retries; u64 tid; @@ -737,12 +738,11 @@ static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, if (!skb) return -ENOMEM; - trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), false, 0, - skb->data + mlxsw_core->driver->txhdr_len, - skb->len - mlxsw_core->driver->txhdr_len); + trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), false, 0, skb->data, + skb->len); atomic_set(&trans->active, 1); - err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->tx_info); + err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->txhdr_info); if (err) { dev_kfree_skb(skb); return err; @@ -944,7 +944,7 @@ static struct sk_buff *mlxsw_emad_alloc(const struct mlxsw_core *mlxsw_core, emad_len = (reg_len + sizeof(u32) + MLXSW_EMAD_ETH_HDR_LEN + (MLXSW_EMAD_OP_TLV_LEN + MLXSW_EMAD_END_TLV_LEN) * - sizeof(u32) + mlxsw_core->driver->txhdr_len); + sizeof(u32) + MLXSW_TXHDR_LEN); if (mlxsw_core->emad.enable_string_tlv) emad_len += MLXSW_EMAD_STRING_TLV_LEN * sizeof(u32); if (mlxsw_core->emad.enable_latency_tlv) @@ -984,8 +984,8 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core, list_add_tail(&trans->bulk_list, bulk_list); trans->core = mlxsw_core; trans->tx_skb = skb; - trans->tx_info.local_port = MLXSW_PORT_CPU_PORT; - trans->tx_info.is_emad = true; + trans->txhdr_info.tx_info.local_port = MLXSW_PORT_CPU_PORT; + trans->txhdr_info.tx_info.is_emad = true; INIT_DELAYED_WORK(&trans->timeout_dw, mlxsw_emad_trans_timeout_work); trans->tid = tid; init_completion(&trans->completion); @@ -995,7 +995,6 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core, trans->type = type; mlxsw_emad_construct(mlxsw_core, skb, reg, payload, type, trans->tid); - mlxsw_core->driver->txhdr_construct(skb, &trans->tx_info); spin_lock_bh(&mlxsw_core->emad.trans_list_lock); list_add_tail_rcu(&trans->list, &mlxsw_core->emad.trans_list); @@ -2330,10 +2329,10 @@ bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core, EXPORT_SYMBOL(mlxsw_core_skb_transmit_busy); int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) + const struct mlxsw_txhdr_info *txhdr_info) { return mlxsw_core->bus->skb_transmit(mlxsw_core->bus_priv, skb, - tx_info); + txhdr_info); } EXPORT_SYMBOL(mlxsw_core_skb_transmit); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 6d11225594dd..1a871397a6df 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -72,7 +72,14 @@ struct mlxsw_tx_info { bool is_emad; }; +struct mlxsw_txhdr_info { + struct mlxsw_tx_info tx_info; + bool data; + u16 max_fid; /* Used for PTP packets which are sent as data. */ +}; + struct mlxsw_rx_md_info { + struct napi_struct *napi; u32 cookie_index; u32 latency; u32 tx_congestion; @@ -94,7 +101,7 @@ struct mlxsw_rx_md_info { bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core, const struct mlxsw_tx_info *tx_info); int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); + const struct mlxsw_txhdr_info *txhdr_info); void mlxsw_core_ptp_transmitted(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, u16 local_port); @@ -425,8 +432,6 @@ struct mlxsw_driver { int (*trap_policer_counter_get)(struct mlxsw_core *mlxsw_core, const struct devlink_trap_policer *policer, u64 *p_drops); - void (*txhdr_construct)(struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); int (*resources_register)(struct mlxsw_core *mlxsw_core); int (*kvd_sizes_get)(struct mlxsw_core *mlxsw_core, const struct mlxsw_config_profile *profile, @@ -439,7 +444,6 @@ struct mlxsw_driver { void (*ptp_transmitted)(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, u16 local_port); - u8 txhdr_len; const struct mlxsw_config_profile *profile; bool sdq_supports_cqe_v2; }; @@ -486,7 +490,7 @@ struct mlxsw_bus { bool (*skb_transmit_busy)(void *bus_priv, const struct mlxsw_tx_info *tx_info); int (*skb_transmit)(void *bus_priv, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); + const struct mlxsw_txhdr_info *txhdr_info); int (*cmd_exec)(void *bus_priv, u16 opcode, u8 opcode_mod, u32 in_mod, bool out_mbox_direct, char *in_mbox, size_t in_mbox_size, diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 1e150ce1c73a..f9f565c1036d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -516,7 +516,7 @@ static bool mlxsw_i2c_skb_transmit_busy(void *bus_priv, } static int mlxsw_i2c_skb_transmit(void *bus_priv, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) + const struct mlxsw_txhdr_info *txhdr_info) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index d6f37456fb31..5b44c931b660 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -21,6 +21,7 @@ #include "cmd.h" #include "port.h" #include "resources.h" +#include "txheader.h" #define mlxsw_pci_write32(mlxsw_pci, reg, val) \ iowrite32be(val, (mlxsw_pci)->hw_addr + (MLXSW_PCI_ ## reg)) @@ -737,6 +738,7 @@ static void mlxsw_pci_cqe_rdq_md_init(struct sk_buff *skb, const char *cqe) } static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, + struct napi_struct *napi, struct mlxsw_pci_queue *q, u16 consumer_counter_limit, enum mlxsw_pci_cqe_v cqe_v, char *cqe) @@ -807,6 +809,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, } mlxsw_pci_skb_cb_ts_set(mlxsw_pci, skb, cqe_v, cqe); + mlxsw_skb_cb(skb)->rx_md_info.napi = napi; mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info); @@ -869,7 +872,7 @@ static int mlxsw_pci_napi_poll_cq_rx(struct napi_struct *napi, int budget) continue; } - mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq, + mlxsw_pci_cqe_rdq_handle(mlxsw_pci, napi, rdq, wqe_counter, q->u.cq.v, cqe); if (++work_done == budget) @@ -2093,6 +2096,39 @@ static void mlxsw_pci_fini(void *bus_priv) mlxsw_pci_free_irq_vectors(mlxsw_pci); } +static int mlxsw_pci_txhdr_construct(struct sk_buff *skb, + const struct mlxsw_txhdr_info *txhdr_info) +{ + const struct mlxsw_tx_info tx_info = txhdr_info->tx_info; + char *txhdr; + + if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) + return -ENOMEM; + + txhdr = skb_push(skb, MLXSW_TXHDR_LEN); + memset(txhdr, 0, MLXSW_TXHDR_LEN); + + mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1); + mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH); + mlxsw_tx_hdr_swid_set(txhdr, 0); + + if (unlikely(txhdr_info->data)) { + u16 fid = txhdr_info->max_fid + tx_info.local_port - 1; + + mlxsw_tx_hdr_rx_is_router_set(txhdr, true); + mlxsw_tx_hdr_fid_valid_set(txhdr, true); + mlxsw_tx_hdr_fid_set(txhdr, fid); + mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_DATA); + } else { + mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL); + mlxsw_tx_hdr_control_tclass_set(txhdr, 1); + mlxsw_tx_hdr_port_mid_set(txhdr, tx_info.local_port); + mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL); + } + + return 0; +} + static struct mlxsw_pci_queue * mlxsw_pci_sdq_pick(struct mlxsw_pci *mlxsw_pci, const struct mlxsw_tx_info *tx_info) @@ -2120,7 +2156,7 @@ static bool mlxsw_pci_skb_transmit_busy(void *bus_priv, } static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) + const struct mlxsw_txhdr_info *txhdr_info) { struct mlxsw_pci *mlxsw_pci = bus_priv; struct mlxsw_pci_queue *q; @@ -2129,13 +2165,17 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb, int i; int err; + err = mlxsw_pci_txhdr_construct(skb, txhdr_info); + if (err) + return err; + if (skb_shinfo(skb)->nr_frags > MLXSW_PCI_WQE_SG_ENTRIES - 1) { err = skb_linearize(skb); if (err) return err; } - q = mlxsw_pci_sdq_pick(mlxsw_pci, tx_info); + q = mlxsw_pci_sdq_pick(mlxsw_pci, &txhdr_info->tx_info); spin_lock_bh(&q->lock); elem_info = mlxsw_pci_queue_elem_info_producer_get(q); if (!elem_info) { @@ -2143,7 +2183,7 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb, err = -EAGAIN; goto unlock; } - mlxsw_skb_cb(skb)->tx_info = *tx_info; + mlxsw_skb_cb(skb)->tx_info = txhdr_info->tx_info; elem_info->sdq.skb = skb; wqe = elem_info->elem; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3f5e5d99251b..d714311fd884 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -107,74 +107,6 @@ static const unsigned char mlxsw_sp2_mac_mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xf0, 0x00 }; -/* tx_hdr_version - * Tx header version. - * Must be set to 1. - */ -MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4); - -/* tx_hdr_ctl - * Packet control type. - * 0 - Ethernet control (e.g. EMADs, LACP) - * 1 - Ethernet data - */ -MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2); - -/* tx_hdr_proto - * Packet protocol type. Must be set to 1 (Ethernet). - */ -MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3); - -/* tx_hdr_rx_is_router - * Packet is sent from the router. Valid for data packets only. - */ -MLXSW_ITEM32(tx, hdr, rx_is_router, 0x00, 19, 1); - -/* tx_hdr_fid_valid - * Indicates if the 'fid' field is valid and should be used for - * forwarding lookup. Valid for data packets only. - */ -MLXSW_ITEM32(tx, hdr, fid_valid, 0x00, 16, 1); - -/* tx_hdr_swid - * Switch partition ID. Must be set to 0. - */ -MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3); - -/* tx_hdr_control_tclass - * Indicates if the packet should use the control TClass and not one - * of the data TClasses. - */ -MLXSW_ITEM32(tx, hdr, control_tclass, 0x00, 6, 1); - -/* tx_hdr_etclass - * Egress TClass to be used on the egress device on the egress port. - */ -MLXSW_ITEM32(tx, hdr, etclass, 0x00, 0, 4); - -/* tx_hdr_port_mid - * Destination local port for unicast packets. - * Destination multicast ID for multicast packets. - * - * Control packets are directed to a specific egress port, while data - * packets are transmitted through the CPU port (0) into the switch partition, - * where forwarding rules are applied. - */ -MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16); - -/* tx_hdr_fid - * Forwarding ID used for L2 forwarding lookup. Valid only if 'fid_valid' is - * set, otherwise calculated based on the packet's VID using VID to FID mapping. - * Valid for data packets only. - */ -MLXSW_ITEM32(tx, hdr, fid, 0x08, 16, 16); - -/* tx_hdr_type - * 0 - Data packets - * 6 - Control packets - */ -MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); - int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, unsigned int counter_index, bool clear, u64 *packets, u64 *bytes) @@ -233,61 +165,6 @@ void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, counter_index); } -void mlxsw_sp_txhdr_construct(struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN); - - memset(txhdr, 0, MLXSW_TXHDR_LEN); - - mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1); - mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL); - mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH); - mlxsw_tx_hdr_swid_set(txhdr, 0); - mlxsw_tx_hdr_control_tclass_set(txhdr, 1); - mlxsw_tx_hdr_port_mid_set(txhdr, tx_info->local_port); - mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL); -} - -int -mlxsw_sp_txhdr_ptp_data_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - char *txhdr; - u16 max_fid; - int err; - - if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) { - err = -ENOMEM; - goto err_skb_cow_head; - } - - if (!MLXSW_CORE_RES_VALID(mlxsw_core, FID)) { - err = -EIO; - goto err_res_valid; - } - max_fid = MLXSW_CORE_RES_GET(mlxsw_core, FID); - - txhdr = skb_push(skb, MLXSW_TXHDR_LEN); - memset(txhdr, 0, MLXSW_TXHDR_LEN); - - mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1); - mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH); - mlxsw_tx_hdr_rx_is_router_set(txhdr, true); - mlxsw_tx_hdr_fid_valid_set(txhdr, true); - mlxsw_tx_hdr_fid_set(txhdr, max_fid + tx_info->local_port - 1); - mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_DATA); - return 0; - -err_res_valid: -err_skb_cow_head: - this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); - dev_kfree_skb_any(skb); - return err; -} - static bool mlxsw_sp_skb_requires_ts(struct sk_buff *skb) { unsigned int type; @@ -299,30 +176,49 @@ static bool mlxsw_sp_skb_requires_ts(struct sk_buff *skb) return !!ptp_parse_header(skb, type); } -static int mlxsw_sp_txhdr_handle(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) +static void mlxsw_sp_txhdr_info_data_init(struct mlxsw_core *mlxsw_core, + struct sk_buff *skb, + struct mlxsw_txhdr_info *txhdr_info) { - struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + /* Resource validation was done as part of PTP init. */ + u16 max_fid = MLXSW_CORE_RES_GET(mlxsw_core, FID); - /* In Spectrum-2 and Spectrum-3, PTP events that require a time stamp - * need special handling and cannot be transmitted as regular control - * packets. + txhdr_info->data = true; + txhdr_info->max_fid = max_fid; +} + +static struct sk_buff * +mlxsw_sp_vlan_tag_push(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb) +{ + /* In some Spectrum ASICs, in order for PTP event packets to have their + * correction field correctly set on the egress port they must be + * transmitted as data packets. Such packets ingress the ASIC via the + * CPU port and must have a VLAN tag, as the CPU port is not configured + * with a PVID. Push the default VLAN (4095), which is configured as + * egress untagged on all the ports. */ - if (unlikely(mlxsw_sp_skb_requires_ts(skb))) - return mlxsw_sp->ptp_ops->txhdr_construct(mlxsw_core, - mlxsw_sp_port, skb, - tx_info); + if (skb_vlan_tagged(skb)) + return skb; - if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) { - this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); - dev_kfree_skb_any(skb); - return -ENOMEM; - } + return vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q), + MLXSW_SP_DEFAULT_VID); +} - mlxsw_sp_txhdr_construct(skb, tx_info); - return 0; +static struct sk_buff * +mlxsw_sp_txhdr_preparations(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, + struct mlxsw_txhdr_info *txhdr_info) +{ + if (likely(!mlxsw_sp_skb_requires_ts(skb))) + return skb; + + if (!mlxsw_sp->ptp_ops->tx_as_data) + return skb; + + /* Special handling for PTP events that require a time stamp and cannot + * be transmitted as regular control packets. + */ + mlxsw_sp_txhdr_info_data_init(mlxsw_sp->core, skb, txhdr_info); + return mlxsw_sp_vlan_tag_push(mlxsw_sp, skb); } enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 state) @@ -721,16 +617,16 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_port_pcpu_stats *pcpu_stats; - const struct mlxsw_tx_info tx_info = { - .local_port = mlxsw_sp_port->local_port, - .is_emad = false, + struct mlxsw_txhdr_info txhdr_info = { + .tx_info.local_port = mlxsw_sp_port->local_port, + .tx_info.is_emad = false, }; u64 len; int err; memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb)); - if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info)) + if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &txhdr_info.tx_info)) return NETDEV_TX_BUSY; if (eth_skb_pad(skb)) { @@ -738,10 +634,11 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } - err = mlxsw_sp_txhdr_handle(mlxsw_sp->core, mlxsw_sp_port, skb, - &tx_info); - if (err) + skb = mlxsw_sp_txhdr_preparations(mlxsw_sp, skb, &txhdr_info); + if (!skb) { + this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); return NETDEV_TX_OK; + } /* TX header is consumed by HW on the way so we shouldn't count its * bytes as being sent. @@ -751,7 +648,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, /* Due to a race we might fail here because of a full queue. In that * unlikely case we simply drop the packet. */ - err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &tx_info); + err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &txhdr_info); if (!err) { pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); @@ -2449,7 +2346,7 @@ void mlxsw_sp_rx_listener_no_mark_func(struct sk_buff *skb, u64_stats_update_end(&pcpu_stats->syncp); skb->protocol = eth_type_trans(skb, skb->dev); - netif_receive_skb(skb); + napi_gro_receive(mlxsw_skb_cb(skb)->rx_md_info.napi, skb); } static void mlxsw_sp_rx_listener_mark_func(struct sk_buff *skb, u16 local_port, @@ -2792,7 +2689,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = { .get_stats_count = mlxsw_sp1_get_stats_count, .get_stats_strings = mlxsw_sp1_get_stats_strings, .get_stats = mlxsw_sp1_get_stats, - .txhdr_construct = mlxsw_sp_ptp_txhdr_construct, }; static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = { @@ -2811,7 +2707,7 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = { .get_stats_count = mlxsw_sp2_get_stats_count, .get_stats_strings = mlxsw_sp2_get_stats_strings, .get_stats = mlxsw_sp2_get_stats, - .txhdr_construct = mlxsw_sp2_ptp_txhdr_construct, + .tx_as_data = true, }; static const struct mlxsw_sp_ptp_ops mlxsw_sp4_ptp_ops = { @@ -2830,7 +2726,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp4_ptp_ops = { .get_stats_count = mlxsw_sp2_get_stats_count, .get_stats_strings = mlxsw_sp2_get_stats_strings, .get_stats = mlxsw_sp2_get_stats, - .txhdr_construct = mlxsw_sp_ptp_txhdr_construct, }; struct mlxsw_sp_sample_trigger_node { @@ -3992,11 +3887,9 @@ static struct mlxsw_driver mlxsw_sp1_driver = { .trap_policer_fini = mlxsw_sp_trap_policer_fini, .trap_policer_set = mlxsw_sp_trap_policer_set, .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, - .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp1_resources_register, .kvd_sizes_get = mlxsw_sp_kvd_sizes_get, .ptp_transmitted = mlxsw_sp_ptp_transmitted, - .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp1_config_profile, .sdq_supports_cqe_v2 = false, }; @@ -4030,10 +3923,8 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .trap_policer_fini = mlxsw_sp_trap_policer_fini, .trap_policer_set = mlxsw_sp_trap_policer_set, .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, - .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, .ptp_transmitted = mlxsw_sp_ptp_transmitted, - .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, .sdq_supports_cqe_v2 = true, }; @@ -4067,10 +3958,8 @@ static struct mlxsw_driver mlxsw_sp3_driver = { .trap_policer_fini = mlxsw_sp_trap_policer_fini, .trap_policer_set = mlxsw_sp_trap_policer_set, .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, - .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, .ptp_transmitted = mlxsw_sp_ptp_transmitted, - .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, .sdq_supports_cqe_v2 = true, }; @@ -4102,10 +3991,8 @@ static struct mlxsw_driver mlxsw_sp4_driver = { .trap_policer_fini = mlxsw_sp_trap_policer_fini, .trap_policer_set = mlxsw_sp_trap_policer_set, .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, - .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, .ptp_transmitted = mlxsw_sp_ptp_transmitted, - .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp4_config_profile, .sdq_supports_cqe_v2 = true, }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 8d3c61287696..b10f80fc651b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -243,10 +243,7 @@ struct mlxsw_sp_ptp_ops { void (*get_stats_strings)(u8 **p); void (*get_stats)(struct mlxsw_sp_port *mlxsw_sp_port, u64 *data, int data_index); - int (*txhdr_construct)(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); + bool tx_as_data; }; struct mlxsw_sp_fid_core_ops { @@ -711,12 +708,6 @@ int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int *p_counter_index); void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, unsigned int counter_index); -void mlxsw_sp_txhdr_construct(struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); -int mlxsw_sp_txhdr_ptp_data_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); bool mlxsw_sp_port_dev_check(const struct net_device *dev); struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev); struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index f07955b5439f..6a4a81c63451 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -192,6 +192,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return -EOPNOTSUPP; } + if (sample_act_count) { + NL_SET_ERR_MSG_MOD(extack, "Mirror action after sample action is not supported"); + return -EOPNOTSUPP; + } + err = mlxsw_sp_acl_rulei_act_mirror(mlxsw_sp, rulei, block, out_dev, extack); @@ -265,6 +270,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return -EOPNOTSUPP; } + if (mirror_act_count) { + NL_SET_ERR_MSG_MOD(extack, "Sample action after mirror action is not supported"); + return -EOPNOTSUPP; + } + err = mlxsw_sp_acl_rulei_act_sample(mlxsw_sp, rulei, block, act->sample.psample_group, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 69cd689dbc83..5afe6b155ef0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -1003,10 +1003,10 @@ static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp, mr->mr_ops->route_stats(mlxsw_sp, mr_route->route_priv, &packets, &bytes); - if (mr_route->mfc->mfc_un.res.pkt != packets) - mr_route->mfc->mfc_un.res.lastuse = jiffies; - mr_route->mfc->mfc_un.res.pkt = packets; - mr_route->mfc->mfc_un.res.bytes = bytes; + if (atomic_long_read(&mr_route->mfc->mfc_un.res.pkt) != packets) + WRITE_ONCE(mr_route->mfc->mfc_un.res.lastuse, jiffies); + atomic_long_set(&mr_route->mfc->mfc_un.res.pkt, packets); + atomic_long_set(&mr_route->mfc->mfc_un.res.bytes, bytes); } static void mlxsw_sp_mr_stats_update(struct work_struct *work) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index d94081c7658e..ca8b9d18fbb9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -1353,6 +1353,10 @@ struct mlxsw_sp_ptp_state *mlxsw_sp2_ptp_init(struct mlxsw_sp *mlxsw_sp) struct mlxsw_sp2_ptp_state *ptp_state; int err; + /* Max FID will be used in data path, check validity as part of init. */ + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, FID)) + return ERR_PTR(-EIO); + ptp_state = kzalloc(sizeof(*ptp_state), GFP_KERNEL); if (!ptp_state) return ERR_PTR(-ENOMEM); @@ -1679,43 +1683,3 @@ int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp, return 0; } - -int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) { - this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); - dev_kfree_skb_any(skb); - return -ENOMEM; - } - - mlxsw_sp_txhdr_construct(skb, tx_info); - return 0; -} - -int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - /* In Spectrum-2 and Spectrum-3, in order for PTP event packets to have - * their correction field correctly set on the egress port they must be - * transmitted as data packets. Such packets ingress the ASIC via the - * CPU port and must have a VLAN tag, as the CPU port is not configured - * with a PVID. Push the default VLAN (4095), which is configured as - * egress untagged on all the ports. - */ - if (!skb_vlan_tagged(skb)) { - skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q), - MLXSW_SP_DEFAULT_VID); - if (!skb) { - this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); - return -ENOMEM; - } - } - - return mlxsw_sp_txhdr_ptp_data_construct(mlxsw_core, mlxsw_sp_port, skb, - tx_info); -} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h index c8aa1452fbb9..102db9060135 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h @@ -49,11 +49,6 @@ void mlxsw_sp1_get_stats_strings(u8 **p); void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port, u64 *data, int data_index); -int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); - struct mlxsw_sp_ptp_clock * mlxsw_sp2_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev); @@ -78,11 +73,6 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port, int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp, struct kernel_ethtool_ts_info *info); -int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); - #else static inline struct mlxsw_sp_ptp_clock * @@ -157,15 +147,6 @@ static inline void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port, { } -static inline int -mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - return -EOPNOTSUPP; -} - static inline struct mlxsw_sp_ptp_clock * mlxsw_sp2_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev) { @@ -211,15 +192,6 @@ mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port, { return -EOPNOTSUPP; } - -static inline int -mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - return -EOPNOTSUPP; -} #endif static inline void mlxsw_sp2_ptp_shaper_work(struct work_struct *work) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 4b5fd71c897d..32d2e61f2b82 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -423,8 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, parms = mlxsw_sp_ipip_netdev_parms4(to_dev); ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, - 0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0, - 0); + 0, 0, tun->net, parms.link, tun->fwmark, 0, 0); rt = ip_route_output_key(tun->net, &fl4); if (IS_ERR(rt)) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 899c954e0e5f..1f9c1c86839f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -173,7 +173,7 @@ static void mlxsw_sp_rx_no_mark_listener(struct sk_buff *skb, u16 local_port, if (err) return; - netif_receive_skb(skb); + napi_gro_receive(mlxsw_skb_cb(skb)->rx_md_info.napi, skb); } static void mlxsw_sp_rx_mark_listener(struct sk_buff *skb, u16 local_port, diff --git a/drivers/net/ethernet/mellanox/mlxsw/txheader.h b/drivers/net/ethernet/mellanox/mlxsw/txheader.h index da51dd9d5e44..e78cba5821b6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/txheader.h +++ b/drivers/net/ethernet/mellanox/mlxsw/txheader.h @@ -4,6 +4,69 @@ #ifndef _MLXSW_TXHEADER_H #define _MLXSW_TXHEADER_H +/* tx_hdr_version + * Tx header version. + * Must be set to 1. + */ +MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4); + +/* tx_hdr_ctl + * Packet control type. + * 0 - Ethernet control (e.g. EMADs, LACP) + * 1 - Ethernet data + */ +MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2); + +/* tx_hdr_proto + * Packet protocol type. Must be set to 1 (Ethernet). + */ +MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3); + +/* tx_hdr_rx_is_router + * Packet is sent from the router. Valid for data packets only. + */ +MLXSW_ITEM32(tx, hdr, rx_is_router, 0x00, 19, 1); + +/* tx_hdr_fid_valid + * Indicates if the 'fid' field is valid and should be used for + * forwarding lookup. Valid for data packets only. + */ +MLXSW_ITEM32(tx, hdr, fid_valid, 0x00, 16, 1); + +/* tx_hdr_swid + * Switch partition ID. Must be set to 0. + */ +MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3); + +/* tx_hdr_control_tclass + * Indicates if the packet should use the control TClass and not one + * of the data TClasses. + */ +MLXSW_ITEM32(tx, hdr, control_tclass, 0x00, 6, 1); + +/* tx_hdr_port_mid + * Destination local port for unicast packets. + * Destination multicast ID for multicast packets. + * + * Control packets are directed to a specific egress port, while data + * packets are transmitted through the CPU port (0) into the switch partition, + * where forwarding rules are applied. + */ +MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16); + +/* tx_hdr_fid + * Forwarding ID used for L2 forwarding lookup. Valid only if 'fid_valid' is + * set, otherwise calculated based on the packet's VID using VID to FID mapping. + * Valid for data packets only. + */ +MLXSW_ITEM32(tx, hdr, fid, 0x08, 16, 16); + +/* tx_hdr_type + * 0 - Data packets + * 6 - Control packets + */ +MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); + #define MLXSW_TXHDR_LEN 0x10 #define MLXSW_TXHDR_VERSION_0 0 #define MLXSW_TXHDR_VERSION_1 1 diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index 706ae6104c8e..14751f16e125 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -16,6 +16,10 @@ #include "fbnic_mac.h" #include "fbnic_rpc.h" +struct fbnic_napi_vector; + +#define FBNIC_MAX_NAPI_VECTORS 128u + struct fbnic_dev { struct device *dev; struct net_device *netdev; @@ -29,6 +33,11 @@ struct fbnic_dev { unsigned int pcs_msix_vector; unsigned short num_irqs; + struct { + u8 users; + char name[IFNAMSIZ + 9]; + } napi_irq[FBNIC_MAX_NAPI_VECTORS]; + struct delayed_work service_task; struct fbnic_fw_mbx mbx[FBNIC_IPC_MBX_INDICES]; @@ -148,6 +157,12 @@ void fbnic_hwmon_unregister(struct fbnic_dev *fbd); int fbnic_pcs_irq_enable(struct fbnic_dev *fbd); void fbnic_pcs_irq_disable(struct fbnic_dev *fbd); +void fbnic_napi_name_irqs(struct fbnic_dev *fbd); +int fbnic_napi_request_irq(struct fbnic_dev *fbd, + struct fbnic_napi_vector *nv); +void fbnic_napi_free_irq(struct fbnic_dev *fbd, + struct fbnic_napi_vector *nv); +void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr); int fbnic_request_irq(struct fbnic_dev *dev, int nr, irq_handler_t handler, unsigned long flags, const char *name, void *data); void fbnic_free_irq(struct fbnic_dev *dev, int nr, void *data); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c index 2118901b25e9..aeb9f333f4c7 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c @@ -64,7 +64,7 @@ static void fbnic_csr_get_regs_rpc_ram(struct fbnic_dev *fbd, u32 **data_p) u32 i, j; *(data++) = start; - *(data++) = end - 1; + *(data++) = end; /* FBNIC_RPC_TCAM_ACT */ for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) { diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c index cc8ca94529ca..20cd9f5f89e2 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c @@ -40,6 +40,451 @@ static const struct fbnic_stat fbnic_gstrings_hw_stats[] = { #define FBNIC_HW_FIXED_STATS_LEN ARRAY_SIZE(fbnic_gstrings_hw_stats) #define FBNIC_HW_STATS_LEN FBNIC_HW_FIXED_STATS_LEN +static void +fbnic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + struct fbnic_dev *fbd = fbn->fbd; + + fbnic_get_fw_ver_commit_str(fbd, drvinfo->fw_version, + sizeof(drvinfo->fw_version)); +} + +static int fbnic_get_regs_len(struct net_device *netdev) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + + return fbnic_csr_regs_len(fbn->fbd) * sizeof(u32); +} + +static void fbnic_get_regs(struct net_device *netdev, + struct ethtool_regs *regs, void *data) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + + fbnic_csr_get_regs(fbn->fbd, data, ®s->version); +} + +static struct fbnic_net *fbnic_clone_create(struct fbnic_net *orig) +{ + struct fbnic_net *clone; + + clone = kmemdup(orig, sizeof(*orig), GFP_KERNEL); + if (!clone) + return NULL; + + memset(clone->tx, 0, sizeof(clone->tx)); + memset(clone->rx, 0, sizeof(clone->rx)); + memset(clone->napi, 0, sizeof(clone->napi)); + return clone; +} + +static void fbnic_clone_swap_cfg(struct fbnic_net *orig, + struct fbnic_net *clone) +{ + swap(clone->rcq_size, orig->rcq_size); + swap(clone->hpq_size, orig->hpq_size); + swap(clone->ppq_size, orig->ppq_size); + swap(clone->txq_size, orig->txq_size); + swap(clone->num_rx_queues, orig->num_rx_queues); + swap(clone->num_tx_queues, orig->num_tx_queues); + swap(clone->num_napi, orig->num_napi); +} + +static void fbnic_aggregate_vector_counters(struct fbnic_net *fbn, + struct fbnic_napi_vector *nv) +{ + int i, j; + + for (i = 0; i < nv->txt_count; i++) { + fbnic_aggregate_ring_tx_counters(fbn, &nv->qt[i].sub0); + fbnic_aggregate_ring_tx_counters(fbn, &nv->qt[i].sub1); + fbnic_aggregate_ring_tx_counters(fbn, &nv->qt[i].cmpl); + } + + for (j = 0; j < nv->rxt_count; j++, i++) { + fbnic_aggregate_ring_rx_counters(fbn, &nv->qt[i].sub0); + fbnic_aggregate_ring_rx_counters(fbn, &nv->qt[i].sub1); + fbnic_aggregate_ring_rx_counters(fbn, &nv->qt[i].cmpl); + } +} + +static void fbnic_clone_swap(struct fbnic_net *orig, + struct fbnic_net *clone) +{ + struct fbnic_dev *fbd = orig->fbd; + unsigned int i; + + for (i = 0; i < max(clone->num_napi, orig->num_napi); i++) + fbnic_synchronize_irq(fbd, FBNIC_NON_NAPI_VECTORS + i); + for (i = 0; i < orig->num_napi; i++) + fbnic_aggregate_vector_counters(orig, orig->napi[i]); + + fbnic_clone_swap_cfg(orig, clone); + + for (i = 0; i < ARRAY_SIZE(orig->napi); i++) + swap(clone->napi[i], orig->napi[i]); + for (i = 0; i < ARRAY_SIZE(orig->tx); i++) + swap(clone->tx[i], orig->tx[i]); + for (i = 0; i < ARRAY_SIZE(orig->rx); i++) + swap(clone->rx[i], orig->rx[i]); +} + +static void fbnic_clone_free(struct fbnic_net *clone) +{ + kfree(clone); +} + +static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data) +{ + int i; + + switch (sset) { + case ETH_SS_STATS: + for (i = 0; i < FBNIC_HW_STATS_LEN; i++) + ethtool_puts(&data, fbnic_gstrings_hw_stats[i].string); + break; + } +} + +static void fbnic_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct fbnic_net *fbn = netdev_priv(dev); + const struct fbnic_stat *stat; + int i; + + fbnic_get_hw_stats(fbn->fbd); + + for (i = 0; i < FBNIC_HW_STATS_LEN; i++) { + stat = &fbnic_gstrings_hw_stats[i]; + data[i] = *(u64 *)((u8 *)&fbn->fbd->hw_stats + stat->offset); + } +} + +static int fbnic_get_sset_count(struct net_device *dev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return FBNIC_HW_STATS_LEN; + default: + return -EOPNOTSUPP; + } +} + +static int fbnic_get_rss_hash_idx(u32 flow_type) +{ + switch (flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) { + case TCP_V4_FLOW: + return FBNIC_TCP4_HASH_OPT; + case TCP_V6_FLOW: + return FBNIC_TCP6_HASH_OPT; + case UDP_V4_FLOW: + return FBNIC_UDP4_HASH_OPT; + case UDP_V6_FLOW: + return FBNIC_UDP6_HASH_OPT; + case AH_V4_FLOW: + case ESP_V4_FLOW: + case AH_ESP_V4_FLOW: + case SCTP_V4_FLOW: + case IPV4_FLOW: + case IPV4_USER_FLOW: + return FBNIC_IPV4_HASH_OPT; + case AH_V6_FLOW: + case ESP_V6_FLOW: + case AH_ESP_V6_FLOW: + case SCTP_V6_FLOW: + case IPV6_FLOW: + case IPV6_USER_FLOW: + return FBNIC_IPV6_HASH_OPT; + case ETHER_FLOW: + return FBNIC_ETHER_HASH_OPT; + } + + return -1; +} + +static int +fbnic_get_rss_hash_opts(struct fbnic_net *fbn, struct ethtool_rxnfc *cmd) +{ + int hash_opt_idx = fbnic_get_rss_hash_idx(cmd->flow_type); + + if (hash_opt_idx < 0) + return -EINVAL; + + /* Report options from rss_en table in fbn */ + cmd->data = fbn->rss_flow_hash[hash_opt_idx]; + + return 0; +} + +static int fbnic_get_rxnfc(struct net_device *netdev, + struct ethtool_rxnfc *cmd, u32 *rule_locs) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = fbn->num_rx_queues; + ret = 0; + break; + case ETHTOOL_GRXFH: + ret = fbnic_get_rss_hash_opts(fbn, cmd); + break; + } + + return ret; +} + +#define FBNIC_L2_HASH_OPTIONS \ + (RXH_L2DA | RXH_DISCARD) +#define FBNIC_L3_HASH_OPTIONS \ + (FBNIC_L2_HASH_OPTIONS | RXH_IP_SRC | RXH_IP_DST) +#define FBNIC_L4_HASH_OPTIONS \ + (FBNIC_L3_HASH_OPTIONS | RXH_L4_B_0_1 | RXH_L4_B_2_3) + +static int +fbnic_set_rss_hash_opts(struct fbnic_net *fbn, const struct ethtool_rxnfc *cmd) +{ + int hash_opt_idx; + + /* Verify the type requested is correct */ + hash_opt_idx = fbnic_get_rss_hash_idx(cmd->flow_type); + if (hash_opt_idx < 0) + return -EINVAL; + + /* Verify the fields asked for can actually be assigned based on type */ + if (cmd->data & ~FBNIC_L4_HASH_OPTIONS || + (hash_opt_idx > FBNIC_L4_HASH_OPT && + cmd->data & ~FBNIC_L3_HASH_OPTIONS) || + (hash_opt_idx > FBNIC_IP_HASH_OPT && + cmd->data & ~FBNIC_L2_HASH_OPTIONS)) + return -EINVAL; + + fbn->rss_flow_hash[hash_opt_idx] = cmd->data; + + if (netif_running(fbn->netdev)) { + fbnic_rss_reinit(fbn->fbd, fbn); + fbnic_write_rules(fbn->fbd); + } + + return 0; +} + +static int fbnic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXFH: + ret = fbnic_set_rss_hash_opts(fbn, cmd); + break; + } + + return ret; +} + +static u32 fbnic_get_rxfh_key_size(struct net_device *netdev) +{ + return FBNIC_RPC_RSS_KEY_BYTE_LEN; +} + +static u32 fbnic_get_rxfh_indir_size(struct net_device *netdev) +{ + return FBNIC_RPC_RSS_TBL_SIZE; +} + +static int +fbnic_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + unsigned int i; + + rxfh->hfunc = ETH_RSS_HASH_TOP; + + if (rxfh->key) { + for (i = 0; i < FBNIC_RPC_RSS_KEY_BYTE_LEN; i++) { + u32 rss_key = fbn->rss_key[i / 4] << ((i % 4) * 8); + + rxfh->key[i] = rss_key >> 24; + } + } + + if (rxfh->indir) { + for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++) + rxfh->indir[i] = fbn->indir_tbl[0][i]; + } + + return 0; +} + +static unsigned int +fbnic_set_indir(struct fbnic_net *fbn, unsigned int idx, const u32 *indir) +{ + unsigned int i, changes = 0; + + for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++) { + if (fbn->indir_tbl[idx][i] == indir[i]) + continue; + + fbn->indir_tbl[idx][i] = indir[i]; + changes++; + } + + return changes; +} + +static int +fbnic_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + unsigned int i, changes = 0; + + if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && + rxfh->hfunc != ETH_RSS_HASH_TOP) + return -EINVAL; + + if (rxfh->key) { + u32 rss_key = 0; + + for (i = FBNIC_RPC_RSS_KEY_BYTE_LEN; i--;) { + rss_key >>= 8; + rss_key |= (u32)(rxfh->key[i]) << 24; + + if (i % 4) + continue; + + if (fbn->rss_key[i / 4] == rss_key) + continue; + + fbn->rss_key[i / 4] = rss_key; + changes++; + } + } + + if (rxfh->indir) + changes += fbnic_set_indir(fbn, 0, rxfh->indir); + + if (changes && netif_running(netdev)) + fbnic_rss_reinit_hw(fbn->fbd, fbn); + + return 0; +} + +static void fbnic_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + struct fbnic_dev *fbd = fbn->fbd; + + ch->max_rx = fbd->max_num_queues; + ch->max_tx = fbd->max_num_queues; + ch->max_combined = min(ch->max_rx, ch->max_tx); + ch->max_other = FBNIC_NON_NAPI_VECTORS; + + if (fbn->num_rx_queues > fbn->num_napi || + fbn->num_tx_queues > fbn->num_napi) + ch->combined_count = min(fbn->num_rx_queues, + fbn->num_tx_queues); + else + ch->combined_count = + fbn->num_rx_queues + fbn->num_tx_queues - fbn->num_napi; + ch->rx_count = fbn->num_rx_queues - ch->combined_count; + ch->tx_count = fbn->num_tx_queues - ch->combined_count; + ch->other_count = FBNIC_NON_NAPI_VECTORS; +} + +static void fbnic_set_queues(struct fbnic_net *fbn, struct ethtool_channels *ch, + unsigned int max_napis) +{ + fbn->num_rx_queues = ch->rx_count + ch->combined_count; + fbn->num_tx_queues = ch->tx_count + ch->combined_count; + fbn->num_napi = min(ch->rx_count + ch->tx_count + ch->combined_count, + max_napis); +} + +static int fbnic_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + unsigned int max_napis, standalone; + struct fbnic_dev *fbd = fbn->fbd; + struct fbnic_net *clone; + int err; + + max_napis = fbd->num_irqs - FBNIC_NON_NAPI_VECTORS; + standalone = ch->rx_count + ch->tx_count; + + /* Limits for standalone queues: + * - each queue has it's own NAPI (num_napi >= rx + tx + combined) + * - combining queues (combined not 0, rx or tx must be 0) + */ + if ((ch->rx_count && ch->tx_count && ch->combined_count) || + (standalone && standalone + ch->combined_count > max_napis) || + ch->rx_count + ch->combined_count > fbd->max_num_queues || + ch->tx_count + ch->combined_count > fbd->max_num_queues || + ch->other_count != FBNIC_NON_NAPI_VECTORS) + return -EINVAL; + + if (!netif_running(netdev)) { + fbnic_set_queues(fbn, ch, max_napis); + fbnic_reset_indir_tbl(fbn); + return 0; + } + + clone = fbnic_clone_create(fbn); + if (!clone) + return -ENOMEM; + + fbnic_set_queues(clone, ch, max_napis); + + err = fbnic_alloc_napi_vectors(clone); + if (err) + goto err_free_clone; + + err = fbnic_alloc_resources(clone); + if (err) + goto err_free_napis; + + fbnic_down_noidle(fbn); + err = fbnic_wait_all_queues_idle(fbn->fbd, true); + if (err) + goto err_start_stack; + + err = fbnic_set_netif_queues(clone); + if (err) + goto err_start_stack; + + /* Nothing can fail past this point */ + fbnic_flush(fbn); + + fbnic_clone_swap(fbn, clone); + + /* Reset RSS indirection table */ + fbnic_reset_indir_tbl(fbn); + + fbnic_up(fbn); + + fbnic_free_resources(clone); + fbnic_free_napi_vectors(clone); + fbnic_clone_free(clone); + + return 0; + +err_start_stack: + fbnic_flush(fbn); + fbnic_up(fbn); + fbnic_free_resources(clone); +err_free_napis: + fbnic_free_napi_vectors(clone); +err_free_clone: + fbnic_clone_free(clone); + return err; +} + static int fbnic_get_ts_info(struct net_device *netdev, struct kernel_ethtool_ts_info *tsinfo) @@ -69,14 +514,27 @@ fbnic_get_ts_info(struct net_device *netdev, return 0; } -static void -fbnic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) +static void fbnic_get_ts_stats(struct net_device *netdev, + struct ethtool_ts_stats *ts_stats) { struct fbnic_net *fbn = netdev_priv(netdev); - struct fbnic_dev *fbd = fbn->fbd; + u64 ts_packets, ts_lost; + struct fbnic_ring *ring; + unsigned int start; + int i; - fbnic_get_fw_ver_commit_str(fbd, drvinfo->fw_version, - sizeof(drvinfo->fw_version)); + ts_stats->pkts = fbn->tx_stats.ts_packets; + ts_stats->lost = fbn->tx_stats.ts_lost; + for (i = 0; i < fbn->num_tx_queues; i++) { + ring = fbn->tx[i]; + do { + start = u64_stats_fetch_begin(&ring->stats.syncp); + ts_packets = ring->stats.ts_packets; + ts_lost = ring->stats.ts_lost; + } while (u64_stats_fetch_retry(&ring->stats.syncp, start)); + ts_stats->pkts += ts_packets; + ts_stats->lost += ts_lost; + } } static void fbnic_set_counter(u64 *stat, struct fbnic_stat_counter *counter) @@ -85,43 +543,6 @@ static void fbnic_set_counter(u64 *stat, struct fbnic_stat_counter *counter) *stat = counter->value; } -static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data) -{ - int i; - - switch (sset) { - case ETH_SS_STATS: - for (i = 0; i < FBNIC_HW_STATS_LEN; i++) - ethtool_puts(&data, fbnic_gstrings_hw_stats[i].string); - break; - } -} - -static int fbnic_get_sset_count(struct net_device *dev, int sset) -{ - switch (sset) { - case ETH_SS_STATS: - return FBNIC_HW_STATS_LEN; - default: - return -EOPNOTSUPP; - } -} - -static void fbnic_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) -{ - struct fbnic_net *fbn = netdev_priv(dev); - const struct fbnic_stat *stat; - int i; - - fbnic_get_hw_stats(fbn->fbd); - - for (i = 0; i < FBNIC_HW_STATS_LEN; i++) { - stat = &fbnic_gstrings_hw_stats[i]; - data[i] = *(u64 *)((u8 *)&fbn->fbd->hw_stats + stat->offset); - } -} - static void fbnic_get_eth_mac_stats(struct net_device *netdev, struct ethtool_eth_mac_stats *eth_mac_stats) @@ -164,44 +585,6 @@ fbnic_get_eth_mac_stats(struct net_device *netdev, &mac_stats->eth_mac.FrameTooLongErrors); } -static void fbnic_get_ts_stats(struct net_device *netdev, - struct ethtool_ts_stats *ts_stats) -{ - struct fbnic_net *fbn = netdev_priv(netdev); - u64 ts_packets, ts_lost; - struct fbnic_ring *ring; - unsigned int start; - int i; - - ts_stats->pkts = fbn->tx_stats.ts_packets; - ts_stats->lost = fbn->tx_stats.ts_lost; - for (i = 0; i < fbn->num_tx_queues; i++) { - ring = fbn->tx[i]; - do { - start = u64_stats_fetch_begin(&ring->stats.syncp); - ts_packets = ring->stats.ts_packets; - ts_lost = ring->stats.ts_lost; - } while (u64_stats_fetch_retry(&ring->stats.syncp, start)); - ts_stats->pkts += ts_packets; - ts_stats->lost += ts_lost; - } -} - -static void fbnic_get_regs(struct net_device *netdev, - struct ethtool_regs *regs, void *data) -{ - struct fbnic_net *fbn = netdev_priv(netdev); - - fbnic_csr_get_regs(fbn->fbd, data, ®s->version); -} - -static int fbnic_get_regs_len(struct net_device *netdev) -{ - struct fbnic_net *fbn = netdev_priv(netdev); - - return fbnic_csr_regs_len(fbn->fbd) * sizeof(u32); -} - static const struct ethtool_ops fbnic_ethtool_ops = { .get_drvinfo = fbnic_get_drvinfo, .get_regs_len = fbnic_get_regs_len, @@ -209,6 +592,14 @@ static const struct ethtool_ops fbnic_ethtool_ops = { .get_strings = fbnic_get_strings, .get_ethtool_stats = fbnic_get_ethtool_stats, .get_sset_count = fbnic_get_sset_count, + .get_rxnfc = fbnic_get_rxnfc, + .set_rxnfc = fbnic_set_rxnfc, + .get_rxfh_key_size = fbnic_get_rxfh_key_size, + .get_rxfh_indir_size = fbnic_get_rxfh_indir_size, + .get_rxfh = fbnic_get_rxfh, + .set_rxfh = fbnic_set_rxfh, + .get_channels = fbnic_get_channels, + .set_channels = fbnic_set_channels, .get_ts_info = fbnic_get_ts_info, .get_ts_stats = fbnic_get_ts_stats, .get_eth_mac_stats = fbnic_get_eth_mac_stats, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c index 8f7a2a19ddf8..bbc7c1c0c37e 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c @@ -228,6 +228,63 @@ static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd) tx_mbx->head = head; } +static int fbnic_mbx_map_req_w_cmpl(struct fbnic_dev *fbd, + struct fbnic_tlv_msg *msg, + struct fbnic_fw_completion *cmpl_data) +{ + unsigned long flags; + int err; + + spin_lock_irqsave(&fbd->fw_tx_lock, flags); + + /* If we are already waiting on a completion then abort */ + if (cmpl_data && fbd->cmpl_data) { + err = -EBUSY; + goto unlock_mbx; + } + + /* Record completion location and submit request */ + if (cmpl_data) + fbd->cmpl_data = cmpl_data; + + err = fbnic_mbx_map_msg(fbd, FBNIC_IPC_MBX_TX_IDX, msg, + le16_to_cpu(msg->hdr.len) * sizeof(u32), 1); + + /* If msg failed then clear completion data for next caller */ + if (err && cmpl_data) + fbd->cmpl_data = NULL; + +unlock_mbx: + spin_unlock_irqrestore(&fbd->fw_tx_lock, flags); + + return err; +} + +static void fbnic_fw_release_cmpl_data(struct kref *kref) +{ + struct fbnic_fw_completion *cmpl_data; + + cmpl_data = container_of(kref, struct fbnic_fw_completion, + ref_count); + kfree(cmpl_data); +} + +static struct fbnic_fw_completion * +fbnic_fw_get_cmpl_by_type(struct fbnic_dev *fbd, u32 msg_type) +{ + struct fbnic_fw_completion *cmpl_data = NULL; + unsigned long flags; + + spin_lock_irqsave(&fbd->fw_tx_lock, flags); + if (fbd->cmpl_data && fbd->cmpl_data->msg_type == msg_type) { + cmpl_data = fbd->cmpl_data; + kref_get(&fbd->cmpl_data->ref_count); + } + spin_unlock_irqrestore(&fbd->fw_tx_lock, flags); + + return cmpl_data; +} + /** * fbnic_fw_xmit_simple_msg - Transmit a simple single TLV message w/o data * @fbd: FBNIC device structure @@ -651,6 +708,84 @@ void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd) dev_warn(fbd->dev, "Failed to send heartbeat message\n"); } +/** + * fbnic_fw_xmit_tsene_read_msg - Create and transmit a sensor read request + * @fbd: FBNIC device structure + * @cmpl_data: Completion data structure to store sensor response + * + * Asks the firmware to provide an update with the latest sensor data. + * The response will contain temperature and voltage readings. + * + * Return: 0 on success, negative error value on failure + */ +int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd, + struct fbnic_fw_completion *cmpl_data) +{ + struct fbnic_tlv_msg *msg; + int err; + + if (!fbnic_fw_present(fbd)) + return -ENODEV; + + msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_TSENE_READ_REQ); + if (!msg) + return -ENOMEM; + + err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data); + if (err) + goto free_message; + + return 0; + +free_message: + free_page((unsigned long)msg); + return err; +} + +static const struct fbnic_tlv_index fbnic_tsene_read_resp_index[] = { + FBNIC_TLV_ATTR_S32(FBNIC_TSENE_THERM), + FBNIC_TLV_ATTR_S32(FBNIC_TSENE_VOLT), + FBNIC_TLV_ATTR_S32(FBNIC_TSENE_ERROR), + FBNIC_TLV_ATTR_LAST +}; + +static int fbnic_fw_parse_tsene_read_resp(void *opaque, + struct fbnic_tlv_msg **results) +{ + struct fbnic_fw_completion *cmpl_data; + struct fbnic_dev *fbd = opaque; + int err = 0; + + /* Verify we have a completion pointer to provide with data */ + cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, + FBNIC_TLV_MSG_ID_TSENE_READ_RESP); + if (!cmpl_data) + return -EINVAL; + + if (results[FBNIC_TSENE_ERROR]) { + err = fbnic_tlv_attr_get_unsigned(results[FBNIC_TSENE_ERROR]); + if (err) + goto exit_complete; + } + + if (!results[FBNIC_TSENE_THERM] || !results[FBNIC_TSENE_VOLT]) { + err = -EINVAL; + goto exit_complete; + } + + cmpl_data->u.tsene.millidegrees = + fbnic_tlv_attr_get_signed(results[FBNIC_TSENE_THERM]); + cmpl_data->u.tsene.millivolts = + fbnic_tlv_attr_get_signed(results[FBNIC_TSENE_VOLT]); + +exit_complete: + cmpl_data->result = err; + complete(&cmpl_data->done); + fbnic_fw_put_cmpl(cmpl_data); + + return err; +} + static const struct fbnic_tlv_parser fbnic_fw_tlv_parser[] = { FBNIC_TLV_PARSER(FW_CAP_RESP, fbnic_fw_cap_resp_index, fbnic_fw_parse_cap_resp), @@ -658,6 +793,9 @@ static const struct fbnic_tlv_parser fbnic_fw_tlv_parser[] = { fbnic_fw_parse_ownership_resp), FBNIC_TLV_PARSER(HEARTBEAT_RESP, fbnic_heartbeat_resp_index, fbnic_fw_parse_heartbeat_resp), + FBNIC_TLV_PARSER(TSENE_READ_RESP, + fbnic_tsene_read_resp_index, + fbnic_fw_parse_tsene_read_resp), FBNIC_TLV_MSG_ERROR }; @@ -802,3 +940,25 @@ void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version, fbnic_mk_full_fw_ver_str(mgmt->version, delim, mgmt->commit, fw_version, str_sz); } + +void fbnic_fw_init_cmpl(struct fbnic_fw_completion *fw_cmpl, + u32 msg_type) +{ + fw_cmpl->msg_type = msg_type; + init_completion(&fw_cmpl->done); + kref_init(&fw_cmpl->ref_count); +} + +void fbnic_fw_clear_compl(struct fbnic_dev *fbd) +{ + unsigned long flags; + + spin_lock_irqsave(&fbd->fw_tx_lock, flags); + fbd->cmpl_data = NULL; + spin_unlock_irqrestore(&fbd->fw_tx_lock, flags); +} + +void fbnic_fw_put_cmpl(struct fbnic_fw_completion *fw_cmpl) +{ + kref_put(&fw_cmpl->ref_count, fbnic_fw_release_cmpl_data); +} diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h index 7cd8841920e4..fe68333d51b1 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h @@ -45,10 +45,16 @@ struct fbnic_fw_cap { }; struct fbnic_fw_completion { - struct { - s32 millivolts; - s32 millidegrees; - } tsene; + u32 msg_type; + struct completion done; + struct kref ref_count; + int result; + union { + struct { + s32 millivolts; + s32 millidegrees; + } tsene; + } u; }; void fbnic_mbx_init(struct fbnic_dev *fbd); @@ -59,6 +65,12 @@ void fbnic_mbx_flush_tx(struct fbnic_dev *fbd); int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership); int fbnic_fw_init_heartbeat(struct fbnic_dev *fbd, bool poll); void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd); +int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd, + struct fbnic_fw_completion *cmpl_data); +void fbnic_fw_init_cmpl(struct fbnic_fw_completion *cmpl_data, + u32 msg_type); +void fbnic_fw_clear_compl(struct fbnic_dev *fbd); +void fbnic_fw_put_cmpl(struct fbnic_fw_completion *cmpl_data); #define fbnic_mk_full_fw_ver_str(_rev_id, _delim, _commit, _str, _str_sz) \ do { \ @@ -83,6 +95,8 @@ enum { FBNIC_TLV_MSG_ID_OWNERSHIP_RESP = 0x13, FBNIC_TLV_MSG_ID_HEARTBEAT_REQ = 0x14, FBNIC_TLV_MSG_ID_HEARTBEAT_RESP = 0x15, + FBNIC_TLV_MSG_ID_TSENE_READ_REQ = 0x3C, + FBNIC_TLV_MSG_ID_TSENE_READ_RESP = 0x3D, }; #define FBNIC_FW_CAP_RESP_VERSION_MAJOR CSR_GENMASK(31, 24) @@ -124,6 +138,13 @@ enum { FBNIC_FW_LINK_FEC_BASER = 3, }; +enum { + FBNIC_TSENE_THERM = 0x0, + FBNIC_TSENE_VOLT = 0x1, + FBNIC_TSENE_ERROR = 0x2, + FBNIC_TSENE_MSG_MAX +}; + enum { FBNIC_FW_OWNERSHIP_FLAG = 0x0, FBNIC_FW_OWNERSHIP_MSG_MAX diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c index bcd1086e3768..def8598aceec 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c @@ -66,7 +66,7 @@ void fbnic_hwmon_register(struct fbnic_dev *fbd) if (IS_ERR(fbd->hwmon)) { dev_notice(fbd->dev, "Failed to register hwmon device %pe\n", - fbd->hwmon); + fbd->hwmon); fbd->hwmon = NULL; } } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c index 914362195920..1bbc0e56f3a0 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c @@ -146,6 +146,17 @@ void fbnic_pcs_irq_disable(struct fbnic_dev *fbd) free_irq(fbd->pcs_msix_vector, fbd); } +void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr) +{ + struct pci_dev *pdev = to_pci_dev(fbd->dev); + int irq = pci_irq_vector(pdev, nr); + + if (irq < 0) + return; + + synchronize_irq(irq); +} + int fbnic_request_irq(struct fbnic_dev *fbd, int nr, irq_handler_t handler, unsigned long flags, const char *name, void *data) { @@ -169,6 +180,48 @@ void fbnic_free_irq(struct fbnic_dev *fbd, int nr, void *data) free_irq(irq, data); } +void fbnic_napi_name_irqs(struct fbnic_dev *fbd) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(fbd->napi_irq); i++) + snprintf(fbd->napi_irq[i].name, + sizeof(fbd->napi_irq[i].name), + "%s-TxRx-%u", fbd->netdev->name, i); +} + +int fbnic_napi_request_irq(struct fbnic_dev *fbd, + struct fbnic_napi_vector *nv) +{ + struct fbnic_net *fbn = netdev_priv(fbd->netdev); + int i = fbnic_napi_idx(nv); + int err; + + if (!fbd->napi_irq[i].users) { + err = fbnic_request_irq(fbd, nv->v_idx, + fbnic_msix_clean_rings, 0, + fbd->napi_irq[i].name, + &fbn->napi[i]); + if (err) + return err; + } + + fbd->napi_irq[i].users++; + return 0; +} + +void fbnic_napi_free_irq(struct fbnic_dev *fbd, + struct fbnic_napi_vector *nv) +{ + struct fbnic_net *fbn = netdev_priv(fbd->netdev); + int i = fbnic_napi_idx(nv); + + if (--fbd->napi_irq[i].users) + return; + + fbnic_free_irq(fbd, nv->v_idx, &fbn->napi[i]); +} + void fbnic_free_irqs(struct fbnic_dev *fbd) { struct pci_dev *pdev = to_pci_dev(fbd->dev); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c index 80b82ff12c4d..14291401f463 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c @@ -686,25 +686,75 @@ fbnic_mac_get_eth_mac_stats(struct fbnic_dev *fbd, bool reset, MAC_STAT_TX_BROADCAST); } -static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id, long *val) +static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id, + long *val) { - struct fbnic_fw_completion fw_cmpl; + struct fbnic_fw_completion *fw_cmpl; + int err = 0, retries = 5; s32 *sensor; + fw_cmpl = kzalloc(sizeof(*fw_cmpl), GFP_KERNEL); + if (!fw_cmpl) + return -ENOMEM; + + /* Initialize completion and queue it for FW to process */ + fbnic_fw_init_cmpl(fw_cmpl, FBNIC_TLV_MSG_ID_TSENE_READ_RESP); + switch (id) { case FBNIC_SENSOR_TEMP: - sensor = &fw_cmpl.tsene.millidegrees; + sensor = &fw_cmpl->u.tsene.millidegrees; break; case FBNIC_SENSOR_VOLTAGE: - sensor = &fw_cmpl.tsene.millivolts; + sensor = &fw_cmpl->u.tsene.millivolts; break; default: - return -EINVAL; + err = -EINVAL; + goto exit_free; + } + + err = fbnic_fw_xmit_tsene_read_msg(fbd, fw_cmpl); + if (err) { + dev_err(fbd->dev, + "Failed to transmit TSENE read msg, err %d\n", + err); + goto exit_free; + } + + /* Allow 2 seconds for reply, resend and try up to 5 times */ + while (!wait_for_completion_timeout(&fw_cmpl->done, 2 * HZ)) { + retries--; + + if (retries == 0) { + dev_err(fbd->dev, + "Timed out waiting for TSENE read\n"); + err = -ETIMEDOUT; + goto exit_cleanup; + } + + err = fbnic_fw_xmit_tsene_read_msg(fbd, NULL); + if (err) { + dev_err(fbd->dev, + "Failed to transmit TSENE read msg, err %d\n", + err); + goto exit_cleanup; + } + } + + /* Handle error returned by firmware */ + if (fw_cmpl->result) { + err = fw_cmpl->result; + dev_err(fbd->dev, "%s: Firmware returned error %d\n", + __func__, err); + goto exit_cleanup; } *val = *sensor; +exit_cleanup: + fbnic_fw_clear_compl(fbd); +exit_free: + fbnic_fw_put_cmpl(fw_cmpl); - return 0; + return err; } static const struct fbnic_mac fbnic_mac_asic = { diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index fc7d80db5fa6..7a96b6ee773f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -23,13 +23,7 @@ int __fbnic_open(struct fbnic_net *fbn) if (err) goto free_napi_vectors; - err = netif_set_real_num_tx_queues(fbn->netdev, - fbn->num_tx_queues); - if (err) - goto free_resources; - - err = netif_set_real_num_rx_queues(fbn->netdev, - fbn->num_rx_queues); + err = fbnic_set_netif_queues(fbn); if (err) goto free_resources; @@ -74,6 +68,8 @@ static int fbnic_open(struct net_device *netdev) struct fbnic_net *fbn = netdev_priv(netdev); int err; + fbnic_napi_name_irqs(fbn->fbd); + err = __fbnic_open(fbn); if (!err) fbnic_up(fbn); @@ -91,6 +87,7 @@ static int fbnic_stop(struct net_device *netdev) fbnic_time_stop(fbn); fbnic_fw_xmit_ownership_msg(fbn->fbd, false); + fbnic_reset_netif_queues(fbn); fbnic_free_resources(fbn); fbnic_free_napi_vectors(fbn); @@ -615,7 +612,6 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) fbn->netdev = netdev; fbn->fbd = fbd; - INIT_LIST_HEAD(&fbn->napis); fbn->txq_size = FBNIC_TXQ_SIZE_DEFAULT; fbn->hpq_size = FBNIC_HPQ_SIZE_DEFAULT; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h index b8417b300778..a392ac1cc4f2 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h @@ -11,10 +11,14 @@ #include "fbnic_rpc.h" #include "fbnic_txrx.h" +#define FBNIC_MAX_NAPI_VECTORS 128u + struct fbnic_net { struct fbnic_ring *tx[FBNIC_MAX_TXQS]; struct fbnic_ring *rx[FBNIC_MAX_RXQS]; + struct fbnic_napi_vector *napi[FBNIC_MAX_NAPI_VECTORS]; + struct net_device *netdev; struct fbnic_dev *fbd; @@ -56,13 +60,12 @@ struct fbnic_net { /* Time stampinn filter config */ struct kernel_hwtstamp_config hwtstamp_config; - - struct list_head napis; }; int __fbnic_open(struct fbnic_net *fbn); void fbnic_up(struct fbnic_net *fbn); void fbnic_down(struct fbnic_net *fbn); +void fbnic_down_noidle(struct fbnic_net *fbn); struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd); void fbnic_netdev_free(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index 32702dc4a066..6cbbc2ee3e1f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -145,7 +145,7 @@ void fbnic_up(struct fbnic_net *fbn) fbnic_service_task_start(fbn); } -static void fbnic_down_noidle(struct fbnic_net *fbn) +void fbnic_down_noidle(struct fbnic_net *fbn) { fbnic_service_task_stop(fbn); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c index 1a5e1e719b30..bb11fc83367d 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c @@ -15,7 +15,7 @@ fbnic_pcs_to_net(struct phylink_pcs *pcs) } static void -fbnic_phylink_pcs_get_state(struct phylink_pcs *pcs, +fbnic_phylink_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct fbnic_net *fbn = fbnic_pcs_to_net(pcs); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c index 908c098cd59e..c25bd300b902 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c @@ -13,10 +13,11 @@ void fbnic_reset_indir_tbl(struct fbnic_net *fbn) unsigned int num_rx = fbn->num_rx_queues; unsigned int i; - for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++) { + if (netif_is_rxfh_configured(fbn->netdev)) + return; + + for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++) fbn->indir_tbl[0][i] = ethtool_rxfh_indir_default(i, num_rx); - fbn->indir_tbl[1][i] = ethtool_rxfh_indir_default(i, num_rx); - } } void fbnic_rss_key_fill(u32 *buffer) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index b5050fabe8fe..d4d7027df9a0 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -1033,20 +1033,20 @@ static int fbnic_poll(struct napi_struct *napi, int budget) if (likely(napi_complete_done(napi, work_done))) fbnic_nv_irq_rearm(nv); - return 0; + return work_done; } -static irqreturn_t fbnic_msix_clean_rings(int __always_unused irq, void *data) +irqreturn_t fbnic_msix_clean_rings(int __always_unused irq, void *data) { - struct fbnic_napi_vector *nv = data; + struct fbnic_napi_vector *nv = *(void **)data; napi_schedule_irqoff(&nv->napi); return IRQ_HANDLED; } -static void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn, - struct fbnic_ring *rxr) +void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn, + struct fbnic_ring *rxr) { struct fbnic_queue_stats *stats = &rxr->stats; @@ -1056,8 +1056,8 @@ static void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn, fbn->rx_stats.dropped += stats->dropped; } -static void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn, - struct fbnic_ring *txr) +void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn, + struct fbnic_ring *txr) { struct fbnic_queue_stats *stats = &txr->stats; @@ -1099,7 +1099,6 @@ static void fbnic_free_napi_vector(struct fbnic_net *fbn, struct fbnic_napi_vector *nv) { struct fbnic_dev *fbd = nv->fbd; - u32 v_idx = nv->v_idx; int i, j; for (i = 0; i < nv->txt_count; i++) { @@ -1113,31 +1112,20 @@ static void fbnic_free_napi_vector(struct fbnic_net *fbn, fbnic_remove_rx_ring(fbn, &nv->qt[i].cmpl); } - fbnic_free_irq(fbd, v_idx, nv); + fbnic_napi_free_irq(fbd, nv); page_pool_destroy(nv->page_pool); netif_napi_del(&nv->napi); - list_del(&nv->napis); + fbn->napi[fbnic_napi_idx(nv)] = NULL; kfree(nv); } void fbnic_free_napi_vectors(struct fbnic_net *fbn) { - struct fbnic_napi_vector *nv, *temp; + int i; - list_for_each_entry_safe(nv, temp, &fbn->napis, napis) - fbnic_free_napi_vector(fbn, nv); -} - -static void fbnic_name_napi_vector(struct fbnic_napi_vector *nv) -{ - unsigned char *dev_name = nv->napi.dev->name; - - if (!nv->rxt_count) - snprintf(nv->name, sizeof(nv->name), "%s-Tx-%u", dev_name, - nv->v_idx - FBNIC_NON_NAPI_VECTORS); - else - snprintf(nv->name, sizeof(nv->name), "%s-TxRx-%u", dev_name, - nv->v_idx - FBNIC_NON_NAPI_VECTORS); + for (i = 0; i < fbn->num_napi; i++) + if (fbn->napi[i]) + fbnic_free_napi_vector(fbn, fbn->napi[i]); } #define FBNIC_PAGE_POOL_FLAGS \ @@ -1222,7 +1210,7 @@ static int fbnic_alloc_napi_vector(struct fbnic_dev *fbd, struct fbnic_net *fbn, nv->v_idx = v_idx; /* Tie napi to netdev */ - list_add(&nv->napis, &fbn->napis); + fbn->napi[fbnic_napi_idx(nv)] = nv; netif_napi_add(fbn->netdev, &nv->napi, fbnic_poll); /* Record IRQ to NAPI struct */ @@ -1239,12 +1227,8 @@ static int fbnic_alloc_napi_vector(struct fbnic_dev *fbd, struct fbnic_net *fbn, goto napi_del; } - /* Initialize vector name */ - fbnic_name_napi_vector(nv); - /* Request the IRQ for napi vector */ - err = fbnic_request_irq(fbd, v_idx, &fbnic_msix_clean_rings, - IRQF_SHARED, nv->name, nv); + err = fbnic_napi_request_irq(fbd, nv); if (err) goto pp_destroy; @@ -1307,7 +1291,7 @@ pp_destroy: page_pool_destroy(nv->page_pool); napi_del: netif_napi_del(&nv->napi); - list_del(&nv->napis); + fbn->napi[fbnic_napi_idx(nv)] = NULL; kfree(nv); return err; } @@ -1612,19 +1596,18 @@ free_resources: void fbnic_free_resources(struct fbnic_net *fbn) { - struct fbnic_napi_vector *nv; + int i; - list_for_each_entry(nv, &fbn->napis, napis) - fbnic_free_nv_resources(fbn, nv); + for (i = 0; i < fbn->num_napi; i++) + fbnic_free_nv_resources(fbn, fbn->napi[i]); } int fbnic_alloc_resources(struct fbnic_net *fbn) { - struct fbnic_napi_vector *nv; - int err = -ENODEV; + int i, err = -ENODEV; - list_for_each_entry(nv, &fbn->napis, napis) { - err = fbnic_alloc_nv_resources(fbn, nv); + for (i = 0; i < fbn->num_napi; i++) { + err = fbnic_alloc_nv_resources(fbn, fbn->napi[i]); if (err) goto free_resources; } @@ -1632,12 +1615,77 @@ int fbnic_alloc_resources(struct fbnic_net *fbn) return 0; free_resources: - list_for_each_entry_continue_reverse(nv, &fbn->napis, napis) - fbnic_free_nv_resources(fbn, nv); + while (i--) + fbnic_free_nv_resources(fbn, fbn->napi[i]); return err; } +static void fbnic_set_netif_napi(struct fbnic_napi_vector *nv) +{ + int i, j; + + /* Associate Tx queue with NAPI */ + for (i = 0; i < nv->txt_count; i++) { + struct fbnic_q_triad *qt = &nv->qt[i]; + + netif_queue_set_napi(nv->napi.dev, qt->sub0.q_idx, + NETDEV_QUEUE_TYPE_TX, &nv->napi); + } + + /* Associate Rx queue with NAPI */ + for (j = 0; j < nv->rxt_count; j++, i++) { + struct fbnic_q_triad *qt = &nv->qt[i]; + + netif_queue_set_napi(nv->napi.dev, qt->cmpl.q_idx, + NETDEV_QUEUE_TYPE_RX, &nv->napi); + } +} + +static void fbnic_reset_netif_napi(struct fbnic_napi_vector *nv) +{ + int i, j; + + /* Disassociate Tx queue from NAPI */ + for (i = 0; i < nv->txt_count; i++) { + struct fbnic_q_triad *qt = &nv->qt[i]; + + netif_queue_set_napi(nv->napi.dev, qt->sub0.q_idx, + NETDEV_QUEUE_TYPE_TX, NULL); + } + + /* Disassociate Rx queue from NAPI */ + for (j = 0; j < nv->rxt_count; j++, i++) { + struct fbnic_q_triad *qt = &nv->qt[i]; + + netif_queue_set_napi(nv->napi.dev, qt->cmpl.q_idx, + NETDEV_QUEUE_TYPE_RX, NULL); + } +} + +int fbnic_set_netif_queues(struct fbnic_net *fbn) +{ + int i, err; + + err = netif_set_real_num_queues(fbn->netdev, fbn->num_tx_queues, + fbn->num_rx_queues); + if (err) + return err; + + for (i = 0; i < fbn->num_napi; i++) + fbnic_set_netif_napi(fbn->napi[i]); + + return 0; +} + +void fbnic_reset_netif_queues(struct fbnic_net *fbn) +{ + int i; + + for (i = 0; i < fbn->num_napi; i++) + fbnic_reset_netif_napi(fbn->napi[i]); +} + static void fbnic_disable_twq0(struct fbnic_ring *txr) { u32 twq_ctl = fbnic_ring_rd32(txr, FBNIC_QUEUE_TWQ0_CTL); @@ -1670,33 +1718,34 @@ static void fbnic_disable_rcq(struct fbnic_ring *rxr) void fbnic_napi_disable(struct fbnic_net *fbn) { - struct fbnic_napi_vector *nv; + int i; - list_for_each_entry(nv, &fbn->napis, napis) { - napi_disable(&nv->napi); + for (i = 0; i < fbn->num_napi; i++) { + napi_disable(&fbn->napi[i]->napi); - fbnic_nv_irq_disable(nv); + fbnic_nv_irq_disable(fbn->napi[i]); } } void fbnic_disable(struct fbnic_net *fbn) { struct fbnic_dev *fbd = fbn->fbd; - struct fbnic_napi_vector *nv; - int i, j; + int i, j, t; + + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; - list_for_each_entry(nv, &fbn->napis, napis) { /* Disable Tx queue triads */ - for (i = 0; i < nv->txt_count; i++) { - struct fbnic_q_triad *qt = &nv->qt[i]; + for (t = 0; t < nv->txt_count; t++) { + struct fbnic_q_triad *qt = &nv->qt[t]; fbnic_disable_twq0(&qt->sub0); fbnic_disable_tcq(&qt->cmpl); } /* Disable Rx queue triads */ - for (j = 0; j < nv->rxt_count; j++, i++) { - struct fbnic_q_triad *qt = &nv->qt[i]; + for (j = 0; j < nv->rxt_count; j++, t++) { + struct fbnic_q_triad *qt = &nv->qt[t]; fbnic_disable_bdq(&qt->sub0, &qt->sub1); fbnic_disable_rcq(&qt->cmpl); @@ -1792,14 +1841,15 @@ int fbnic_wait_all_queues_idle(struct fbnic_dev *fbd, bool may_fail) void fbnic_flush(struct fbnic_net *fbn) { - struct fbnic_napi_vector *nv; + int i; - list_for_each_entry(nv, &fbn->napis, napis) { - int i, j; + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; + int j, t; /* Flush any processed Tx Queue Triads and drop the rest */ - for (i = 0; i < nv->txt_count; i++) { - struct fbnic_q_triad *qt = &nv->qt[i]; + for (t = 0; t < nv->txt_count; t++) { + struct fbnic_q_triad *qt = &nv->qt[t]; struct netdev_queue *tx_queue; /* Clean the work queues of unprocessed work */ @@ -1816,15 +1866,11 @@ void fbnic_flush(struct fbnic_net *fbn) tx_queue = netdev_get_tx_queue(nv->napi.dev, qt->sub0.q_idx); netdev_tx_reset_queue(tx_queue); - - /* Disassociate Tx queue from NAPI */ - netif_queue_set_napi(nv->napi.dev, qt->sub0.q_idx, - NETDEV_QUEUE_TYPE_TX, NULL); } /* Flush any processed Rx Queue Triads and drop the rest */ - for (j = 0; j < nv->rxt_count; j++, i++) { - struct fbnic_q_triad *qt = &nv->qt[i]; + for (j = 0; j < nv->rxt_count; j++, t++) { + struct fbnic_q_triad *qt = &nv->qt[t]; /* Clean the work queues of unprocessed work */ fbnic_clean_bdq(nv, 0, &qt->sub0, qt->sub0.tail); @@ -1835,43 +1881,23 @@ void fbnic_flush(struct fbnic_net *fbn) fbnic_put_pkt_buff(nv, qt->cmpl.pkt, 0); qt->cmpl.pkt->buff.data_hard_start = NULL; - - /* Disassociate Rx queue from NAPI */ - netif_queue_set_napi(nv->napi.dev, qt->cmpl.q_idx, - NETDEV_QUEUE_TYPE_RX, NULL); } } } void fbnic_fill(struct fbnic_net *fbn) { - struct fbnic_napi_vector *nv; + int i; - list_for_each_entry(nv, &fbn->napis, napis) { - int i, j; - - /* Configure NAPI mapping for Tx */ - for (i = 0; i < nv->txt_count; i++) { - struct fbnic_q_triad *qt = &nv->qt[i]; - - /* Nothing to do if Tx queue is disabled */ - if (qt->sub0.flags & FBNIC_RING_F_DISABLED) - continue; - - /* Associate Tx queue with NAPI */ - netif_queue_set_napi(nv->napi.dev, qt->sub0.q_idx, - NETDEV_QUEUE_TYPE_TX, &nv->napi); - } + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; + int j, t; /* Configure NAPI mapping and populate pages * in the BDQ rings to use for Rx */ - for (j = 0; j < nv->rxt_count; j++, i++) { - struct fbnic_q_triad *qt = &nv->qt[i]; - - /* Associate Rx queue with NAPI */ - netif_queue_set_napi(nv->napi.dev, qt->cmpl.q_idx, - NETDEV_QUEUE_TYPE_RX, &nv->napi); + for (j = 0, t = nv->txt_count; j < nv->rxt_count; j++, t++) { + struct fbnic_q_triad *qt = &nv->qt[t]; /* Populate the header and payload BDQs */ fbnic_fill_bdq(nv, &qt->sub0); @@ -2025,21 +2051,23 @@ static void fbnic_enable_rcq(struct fbnic_napi_vector *nv, void fbnic_enable(struct fbnic_net *fbn) { struct fbnic_dev *fbd = fbn->fbd; - struct fbnic_napi_vector *nv; - int i, j; + int i; + + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; + int j, t; - list_for_each_entry(nv, &fbn->napis, napis) { /* Setup Tx Queue Triads */ - for (i = 0; i < nv->txt_count; i++) { - struct fbnic_q_triad *qt = &nv->qt[i]; + for (t = 0; t < nv->txt_count; t++) { + struct fbnic_q_triad *qt = &nv->qt[t]; fbnic_enable_twq0(&qt->sub0); fbnic_enable_tcq(nv, &qt->cmpl); } /* Setup Rx Queue Triads */ - for (j = 0; j < nv->rxt_count; j++, i++) { - struct fbnic_q_triad *qt = &nv->qt[i]; + for (j = 0; j < nv->rxt_count; j++, t++) { + struct fbnic_q_triad *qt = &nv->qt[t]; fbnic_enable_bdq(&qt->sub0, &qt->sub1); fbnic_config_drop_mode_rcq(nv, &qt->cmpl); @@ -2064,10 +2092,11 @@ void fbnic_napi_enable(struct fbnic_net *fbn) { u32 irqs[FBNIC_MAX_MSIX_VECS / 32] = {}; struct fbnic_dev *fbd = fbn->fbd; - struct fbnic_napi_vector *nv; int i; - list_for_each_entry(nv, &fbn->napis, napis) { + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; + napi_enable(&nv->napi); fbnic_nv_irq_enable(nv); @@ -2096,17 +2125,18 @@ void fbnic_napi_depletion_check(struct net_device *netdev) struct fbnic_net *fbn = netdev_priv(netdev); u32 irqs[FBNIC_MAX_MSIX_VECS / 32] = {}; struct fbnic_dev *fbd = fbn->fbd; - struct fbnic_napi_vector *nv; - int i, j; + int i, j, t; + + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; - list_for_each_entry(nv, &fbn->napis, napis) { /* Find RQs which are completely out of pages */ - for (i = nv->txt_count, j = 0; j < nv->rxt_count; j++, i++) { + for (t = nv->txt_count, j = 0; j < nv->rxt_count; j++, t++) { /* Assume 4 pages is always enough to fit a packet * and therefore generate a completion and an IRQ. */ - if (fbnic_desc_used(&nv->qt[i].sub0) < 4 || - fbnic_desc_used(&nv->qt[i].sub1) < 4) + if (fbnic_desc_used(&nv->qt[t].sub0) < 4 || + fbnic_desc_used(&nv->qt[t].sub1) < 4) irqs[nv->v_idx / 32] |= BIT(nv->v_idx % 32); } } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h index 8d626287c3f4..c2a94f31f71b 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h @@ -104,14 +104,11 @@ struct fbnic_napi_vector { struct device *dev; /* Device for DMA unmapping */ struct page_pool *page_pool; struct fbnic_dev *fbd; - char name[IFNAMSIZ + 9]; u16 v_idx; u8 txt_count; u8 rxt_count; - struct list_head napis; - struct fbnic_q_triad qt[]; }; @@ -123,10 +120,18 @@ netdev_features_t fbnic_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); +void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn, + struct fbnic_ring *rxr); +void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn, + struct fbnic_ring *txr); + int fbnic_alloc_napi_vectors(struct fbnic_net *fbn); void fbnic_free_napi_vectors(struct fbnic_net *fbn); int fbnic_alloc_resources(struct fbnic_net *fbn); void fbnic_free_resources(struct fbnic_net *fbn); +int fbnic_set_netif_queues(struct fbnic_net *fbn); +void fbnic_reset_netif_queues(struct fbnic_net *fbn); +irqreturn_t fbnic_msix_clean_rings(int irq, void *data); void fbnic_napi_enable(struct fbnic_net *fbn); void fbnic_napi_disable(struct fbnic_net *fbn); void fbnic_enable(struct fbnic_net *fbn); @@ -137,4 +142,9 @@ void fbnic_fill(struct fbnic_net *fbn); void fbnic_napi_depletion_check(struct net_device *netdev); int fbnic_wait_all_queues_idle(struct fbnic_dev *fbd, bool may_fail); +static inline int fbnic_napi_idx(const struct fbnic_napi_vector *nv) +{ + return nv->v_idx - FBNIC_NON_NAPI_VECTORS; +} + #endif /* _FBNIC_TXRX_H_ */ diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index 1a1cbd034eda..1459acfb1e61 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -1055,9 +1055,6 @@ static int lan743x_ethtool_get_eee(struct net_device *netdev, { struct lan743x_adapter *adapter = netdev_priv(netdev); - eee->tx_lpi_timer = lan743x_csr_read(adapter, - MAC_EEE_TX_LPI_REQ_DLY_CNT); - return phylink_ethtool_get_eee(adapter->phylink, eee); } @@ -1065,24 +1062,6 @@ static int lan743x_ethtool_set_eee(struct net_device *netdev, struct ethtool_keee *eee) { struct lan743x_adapter *adapter = netdev_priv(netdev); - u32 tx_lpi_timer; - - tx_lpi_timer = lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT); - if (tx_lpi_timer != eee->tx_lpi_timer) { - u32 mac_cr = lan743x_csr_read(adapter, MAC_CR); - - /* Software should only change this field when Energy Efficient - * Ethernet Enable (EEEEN) is cleared. - * This function will trigger an autonegotiation restart and - * eee will be reenabled during link up if eee was negotiated. - */ - lan743x_mac_eee_enable(adapter, false); - lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT, - eee->tx_lpi_timer); - - if (mac_cr & MAC_CR_EEE_EN_) - lan743x_mac_eee_enable(adapter, true); - } return phylink_ethtool_set_eee(adapter->phylink, eee); } diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 4dc5adcda6a3..23760b613d3e 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -2966,7 +2966,7 @@ static int lan743x_phylink_2500basex_config(struct lan743x_adapter *adapter) return lan743x_pcs_power_reset(adapter); } -void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable) +static void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable) { u32 mac_cr; @@ -3027,10 +3027,8 @@ static void lan743x_phylink_mac_link_down(struct phylink_config *config, phy_interface_t interface) { struct net_device *netdev = to_net_dev(config->dev); - struct lan743x_adapter *adapter = netdev_priv(netdev); - netif_tx_stop_all_queues(to_net_dev(config->dev)); - lan743x_mac_eee_enable(adapter, false); + netif_tx_stop_all_queues(netdev); } static void lan743x_phylink_mac_link_up(struct phylink_config *config, @@ -3072,16 +3070,40 @@ static void lan743x_phylink_mac_link_up(struct phylink_config *config, cap & FLOW_CTRL_TX, cap & FLOW_CTRL_RX); - if (phydev) - lan743x_mac_eee_enable(adapter, phydev->enable_tx_lpi); - netif_tx_wake_all_queues(netdev); } +static void lan743x_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct net_device *netdev = to_net_dev(config->dev); + struct lan743x_adapter *adapter = netdev_priv(netdev); + + lan743x_mac_eee_enable(adapter, false); +} + +static int lan743x_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop) +{ + struct net_device *netdev = to_net_dev(config->dev); + struct lan743x_adapter *adapter = netdev_priv(netdev); + + /* Software should only change this field when Energy Efficient + * Ethernet Enable (EEEEN) is cleared. We ensure that by clearing + * EEEEN during probe, and phylink itself guarantees that + * mac_disable_tx_lpi() will have been previously called. + */ + lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT, timer); + lan743x_mac_eee_enable(adapter, true); + + return 0; +} + static const struct phylink_mac_ops lan743x_phylink_mac_ops = { .mac_config = lan743x_phylink_mac_config, .mac_link_down = lan743x_phylink_mac_link_down, .mac_link_up = lan743x_phylink_mac_link_up, + .mac_disable_tx_lpi = lan743x_mac_disable_tx_lpi, + .mac_enable_tx_lpi = lan743x_mac_enable_tx_lpi, }; static int lan743x_phylink_create(struct lan743x_adapter *adapter) @@ -3095,6 +3117,9 @@ static int lan743x_phylink_create(struct lan743x_adapter *adapter) adapter->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD; + adapter->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD; + adapter->phylink_config.lpi_timer_default = + lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT); lan743x_phy_interface_select(adapter); @@ -3120,6 +3145,10 @@ static int lan743x_phylink_create(struct lan743x_adapter *adapter) phy_interface_set_rgmii(adapter->phylink_config.supported_interfaces); } + memcpy(adapter->phylink_config.lpi_interfaces, + adapter->phylink_config.supported_interfaces, + sizeof(adapter->phylink_config.lpi_interfaces)); + pl = phylink_create(&adapter->phylink_config, NULL, adapter->phy_interface, &lan743x_phylink_mac_ops); @@ -3517,6 +3546,9 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, spin_lock_init(&tx->ring_lock); } + /* Ensure EEEEN is clear */ + lan743x_mac_eee_enable(adapter, false); + return 0; } diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 8ef897c114d3..7f73d66854be 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -1206,6 +1206,5 @@ void lan743x_hs_syslock_release(struct lan743x_adapter *adapter); void lan743x_mac_flow_ctrl_set_enables(struct lan743x_adapter *adapter, bool tx_enable, bool rx_enable); int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr); -void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable); #endif /* _LAN743X_H */ diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 25cb2f61986f..1efa584e7107 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -443,7 +443,7 @@ int lan966x_stats_init(struct lan966x *lan966x); void lan966x_port_config_down(struct lan966x_port *port); void lan966x_port_config_up(struct lan966x_port *port); -void lan966x_port_status_get(struct lan966x_port *port, +void lan966x_port_status_get(struct lan966x_port *port, unsigned int neg_mode, struct phylink_link_state *state); int lan966x_port_pcs_set(struct lan966x_port *port, struct lan966x_port_config *config); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c index 1d63903f9006..75188b99e4e7 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c @@ -88,11 +88,12 @@ static struct lan966x_port *lan966x_pcs_to_port(struct phylink_pcs *pcs) } static void lan966x_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct lan966x_port *port = lan966x_pcs_to_port(pcs); - lan966x_port_status_get(port, state); + lan966x_port_status_get(port, neg_mode, state); } static int lan966x_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c index fdfa4040d9ee..cf7de0267c32 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c @@ -284,7 +284,7 @@ void lan966x_port_config_up(struct lan966x_port *port) lan966x_port_link_up(port); } -void lan966x_port_status_get(struct lan966x_port *port, +void lan966x_port_status_get(struct lan966x_port *port, unsigned int neg_mode, struct phylink_link_state *state) { struct lan966x *lan966x = port->lan966x; @@ -314,7 +314,7 @@ void lan966x_port_status_get(struct lan966x_port *port, bmsr |= BMSR_ANEGCOMPLETE; lp_adv = DEV_PCS1G_ANEG_STATUS_LP_ADV_GET(val); - phylink_mii_c22_pcs_decode_state(state, bmsr, lp_adv); + phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lp_adv); } else { if (!state->link) return; diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig index 35b057c9d0cb..35e1c0cf345e 100644 --- a/drivers/net/ethernet/microchip/sparx5/Kconfig +++ b/drivers/net/ethernet/microchip/sparx5/Kconfig @@ -28,5 +28,6 @@ config SPARX5_DCB config LAN969X_SWITCH bool "Lan969x switch driver" depends on SPARX5_SWITCH + select PAGE_POOL help This driver supports the lan969x family of network switch devices. diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile index 4bf2a885a9da..d447f9e84d92 100644 --- a/drivers/net/ethernet/microchip/sparx5/Makefile +++ b/drivers/net/ethernet/microchip/sparx5/Makefile @@ -20,7 +20,9 @@ sparx5-switch-$(CONFIG_LAN969X_SWITCH) += lan969x/lan969x_regs.o \ lan969x/lan969x.o \ lan969x/lan969x_calendar.o \ lan969x/lan969x_vcap_ag_api.o \ - lan969x/lan969x_vcap_impl.o + lan969x/lan969x_vcap_impl.o \ + lan969x/lan969x_rgmii.o \ + lan969x/lan969x_fdma.o # Provide include files ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c index c2afa2176b08..f3a9c71bea36 100644 --- a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c +++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c @@ -90,9 +90,12 @@ static const struct sparx5_main_io_resource lan969x_main_iomap[] = { { TARGET_DEV2G5 + 27, 0x30d8000, 1 }, /* 0xe30d8000 */ { TARGET_DEV10G + 9, 0x30dc000, 1 }, /* 0xe30dc000 */ { TARGET_PCS10G_BR + 9, 0x30e0000, 1 }, /* 0xe30e0000 */ + { TARGET_DEVRGMII, 0x30e4000, 1 }, /* 0xe30e4000 */ + { TARGET_DEVRGMII + 1, 0x30e8000, 1 }, /* 0xe30e8000 */ { TARGET_DSM, 0x30ec000, 1 }, /* 0xe30ec000 */ { TARGET_PORT_CONF, 0x30f0000, 1 }, /* 0xe30f0000 */ { TARGET_ASM, 0x3200000, 1 }, /* 0xe3200000 */ + { TARGET_HSIO_WRAP, 0x3408000, 1 }, /* 0xe3408000 */ }; static struct sparx5_sdlb_group lan969x_sdlb_groups[LAN969X_SDLB_GRP_CNT] = { @@ -329,6 +332,7 @@ static const struct sparx5_ops lan969x_ops = { .is_port_5g = &lan969x_port_is_5g, .is_port_10g = &lan969x_port_is_10g, .is_port_25g = &lan969x_port_is_25g, + .is_port_rgmii = &lan969x_port_is_rgmii, .get_port_dev_index = &lan969x_port_dev_mapping, .get_port_dev_bit = &lan969x_get_dev_mode_bit, .get_hsch_max_group_rate = &lan969x_get_hsch_max_group_rate, @@ -336,6 +340,11 @@ static const struct sparx5_ops lan969x_ops = { .set_port_mux = &lan969x_port_mux_set, .ptp_irq_handler = &lan969x_ptp_irq_handler, .dsm_calendar_calc = &lan969x_dsm_calendar_calc, + .port_config_rgmii = &lan969x_port_config_rgmii, + .fdma_init = &lan969x_fdma_init, + .fdma_deinit = &lan969x_fdma_deinit, + .fdma_poll = &lan969x_fdma_napi_poll, + .fdma_xmit = &lan969x_fdma_xmit, }; const struct sparx5_match_data lan969x_desc = { diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h index 2489d0d32dfd..529fde3d4deb 100644 --- a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h +++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h @@ -59,7 +59,24 @@ static inline bool lan969x_port_is_25g(int portno) return false; } +static inline bool lan969x_port_is_rgmii(int portno) +{ + return portno == 28 || portno == 29; +} + /* lan969x_calendar.c */ int lan969x_dsm_calendar_calc(struct sparx5 *sparx5, u32 taxi, struct sparx5_calendar_data *data); + +/* lan969x_rgmii.c */ +int lan969x_port_config_rgmii(struct sparx5_port *port, + struct sparx5_port_config *conf); + +/* lan969x_fdma.c */ +int lan969x_fdma_init(struct sparx5 *sparx5); +int lan969x_fdma_deinit(struct sparx5 *sparx5); +int lan969x_fdma_napi_poll(struct napi_struct *napi, int weight); +int lan969x_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev); + #endif diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_fdma.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_fdma.c new file mode 100644 index 000000000000..1282f5c3ee6d --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_fdma.c @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip lan969x Switch driver + * + * Copyright (c) 2025 Microchip Technology Inc. and its subsidiaries. + */ +#include + +#include "../sparx5_main.h" +#include "../sparx5_main_regs.h" +#include "../sparx5_port.h" + +#include "fdma_api.h" +#include "lan969x.h" + +#define FDMA_PRIV(fdma) ((struct sparx5 *)((fdma)->priv)) + +static int lan969x_fdma_tx_dataptr_cb(struct fdma *fdma, int dcb, int db, + u64 *dataptr) +{ + *dataptr = FDMA_PRIV(fdma)->tx.dbs[dcb].dma_addr; + + return 0; +} + +static int lan969x_fdma_rx_dataptr_cb(struct fdma *fdma, int dcb, int db, + u64 *dataptr) +{ + struct sparx5_rx *rx = &FDMA_PRIV(fdma)->rx; + struct page *page; + + page = page_pool_dev_alloc_pages(rx->page_pool); + if (unlikely(!page)) + return -ENOMEM; + + rx->page[dcb][db] = page; + + *dataptr = page_pool_get_dma_addr(page); + + return 0; +} + +static int lan969x_fdma_get_next_dcb(struct sparx5_tx *tx) +{ + struct fdma *fdma = &tx->fdma; + + for (int i = 0; i < fdma->n_dcbs; ++i) + if (!tx->dbs[i].used && !fdma_is_last(fdma, &fdma->dcbs[i])) + return i; + + return -ENOSPC; +} + +static void lan969x_fdma_tx_clear_buf(struct sparx5 *sparx5, int weight) +{ + struct fdma *fdma = &sparx5->tx.fdma; + struct sparx5_tx_buf *db; + unsigned long flags; + int i; + + spin_lock_irqsave(&sparx5->tx_lock, flags); + + for (i = 0; i < fdma->n_dcbs; ++i) { + db = &sparx5->tx.dbs[i]; + + if (!db->used) + continue; + + if (!fdma_db_is_done(fdma_db_get(fdma, i, 0))) + continue; + + db->dev->stats.tx_bytes += db->skb->len; + db->dev->stats.tx_packets++; + sparx5->tx.packets++; + + dma_unmap_single(sparx5->dev, + db->dma_addr, + db->skb->len, + DMA_TO_DEVICE); + + if (!db->ptp) + napi_consume_skb(db->skb, weight); + + db->used = false; + } + + spin_unlock_irqrestore(&sparx5->tx_lock, flags); +} + +static void lan969x_fdma_free_pages(struct sparx5_rx *rx) +{ + struct fdma *fdma = &rx->fdma; + + for (int i = 0; i < fdma->n_dcbs; ++i) { + for (int j = 0; j < fdma->n_dbs; ++j) + page_pool_put_full_page(rx->page_pool, + rx->page[i][j], false); + } +} + +static struct sk_buff *lan969x_fdma_rx_get_frame(struct sparx5 *sparx5, + struct sparx5_rx *rx) +{ + const struct sparx5_consts *consts = sparx5->data->consts; + struct fdma *fdma = &rx->fdma; + struct sparx5_port *port; + struct frame_info fi; + struct sk_buff *skb; + struct fdma_db *db; + struct page *page; + + db = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index]; + page = rx->page[fdma->dcb_index][fdma->db_index]; + + sparx5_ifh_parse(sparx5, page_address(page), &fi); + port = fi.src_port < consts->n_ports ? sparx5->ports[fi.src_port] : + NULL; + if (WARN_ON(!port)) + goto free_page; + + skb = build_skb(page_address(page), fdma->db_size); + if (unlikely(!skb)) + goto free_page; + + skb_mark_for_recycle(skb); + skb_put(skb, fdma_db_len_get(db)); + skb_pull(skb, IFH_LEN * sizeof(u32)); + + skb->dev = port->ndev; + + if (likely(!(skb->dev->features & NETIF_F_RXFCS))) + skb_trim(skb, skb->len - ETH_FCS_LEN); + + sparx5_ptp_rxtstamp(sparx5, skb, fi.timestamp); + skb->protocol = eth_type_trans(skb, skb->dev); + + if (test_bit(port->portno, sparx5->bridge_mask)) + skb->offload_fwd_mark = 1; + + skb->dev->stats.rx_bytes += skb->len; + skb->dev->stats.rx_packets++; + + return skb; + +free_page: + page_pool_recycle_direct(rx->page_pool, page); + + return NULL; +} + +static int lan969x_fdma_rx_alloc(struct sparx5 *sparx5) +{ + struct sparx5_rx *rx = &sparx5->rx; + struct fdma *fdma = &rx->fdma; + int err; + + struct page_pool_params pp_params = { + .order = 0, + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .pool_size = fdma->n_dcbs * fdma->n_dbs, + .nid = NUMA_NO_NODE, + .dev = sparx5->dev, + .dma_dir = DMA_FROM_DEVICE, + .offset = 0, + .max_len = fdma->db_size - + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + }; + + rx->page_pool = page_pool_create(&pp_params); + if (IS_ERR(rx->page_pool)) + return PTR_ERR(rx->page_pool); + + err = fdma_alloc_coherent(sparx5->dev, fdma); + if (err) + return err; + + fdma_dcbs_init(fdma, + FDMA_DCB_INFO_DATAL(fdma->db_size), + FDMA_DCB_STATUS_INTR); + + return 0; +} + +static int lan969x_fdma_tx_alloc(struct sparx5 *sparx5) +{ + struct sparx5_tx *tx = &sparx5->tx; + struct fdma *fdma = &tx->fdma; + int err; + + tx->dbs = kcalloc(fdma->n_dcbs, + sizeof(struct sparx5_tx_buf), + GFP_KERNEL); + if (!tx->dbs) + return -ENOMEM; + + err = fdma_alloc_coherent(sparx5->dev, fdma); + if (err) { + kfree(tx->dbs); + return err; + } + + fdma_dcbs_init(fdma, + FDMA_DCB_INFO_DATAL(fdma->db_size), + FDMA_DCB_STATUS_DONE); + + return 0; +} + +static void lan969x_fdma_rx_init(struct sparx5 *sparx5) +{ + struct fdma *fdma = &sparx5->rx.fdma; + + fdma->channel_id = FDMA_XTR_CHANNEL; + fdma->n_dcbs = FDMA_DCB_MAX; + fdma->n_dbs = 1; + fdma->priv = sparx5; + fdma->size = fdma_get_size(fdma); + fdma->db_size = PAGE_SIZE; + fdma->ops.dataptr_cb = &lan969x_fdma_rx_dataptr_cb; + fdma->ops.nextptr_cb = &fdma_nextptr_cb; + + /* Fetch a netdev for SKB and NAPI use, any will do */ + for (int idx = 0; idx < sparx5->data->consts->n_ports; ++idx) { + struct sparx5_port *port = sparx5->ports[idx]; + + if (port && port->ndev) { + sparx5->rx.ndev = port->ndev; + break; + } + } +} + +static void lan969x_fdma_tx_init(struct sparx5 *sparx5) +{ + struct fdma *fdma = &sparx5->tx.fdma; + + fdma->channel_id = FDMA_INJ_CHANNEL; + fdma->n_dcbs = FDMA_DCB_MAX; + fdma->n_dbs = 1; + fdma->priv = sparx5; + fdma->size = fdma_get_size(fdma); + fdma->db_size = PAGE_SIZE; + fdma->ops.dataptr_cb = &lan969x_fdma_tx_dataptr_cb; + fdma->ops.nextptr_cb = &fdma_nextptr_cb; +} + +int lan969x_fdma_napi_poll(struct napi_struct *napi, int weight) +{ + struct sparx5_rx *rx = container_of(napi, struct sparx5_rx, napi); + struct sparx5 *sparx5 = container_of(rx, struct sparx5, rx); + int old_dcb, dcb_reload, counter = 0; + struct fdma *fdma = &rx->fdma; + struct sk_buff *skb; + + dcb_reload = fdma->dcb_index; + + lan969x_fdma_tx_clear_buf(sparx5, weight); + + /* Process RX data */ + while (counter < weight) { + if (!fdma_has_frames(fdma)) + break; + + skb = lan969x_fdma_rx_get_frame(sparx5, rx); + if (!skb) + break; + + napi_gro_receive(&rx->napi, skb); + + fdma_db_advance(fdma); + counter++; + /* Check if the DCB can be reused */ + if (fdma_dcb_is_reusable(fdma)) + continue; + + fdma_db_reset(fdma); + fdma_dcb_advance(fdma); + } + + /* Allocate new pages and map them */ + while (dcb_reload != fdma->dcb_index) { + old_dcb = dcb_reload; + dcb_reload++; + /* n_dcbs must be a power of 2 */ + dcb_reload &= fdma->n_dcbs - 1; + + fdma_dcb_add(fdma, + old_dcb, + FDMA_DCB_INFO_DATAL(fdma->db_size), + FDMA_DCB_STATUS_INTR); + + sparx5_fdma_reload(sparx5, fdma); + } + + if (counter < weight && napi_complete_done(napi, counter)) + spx5_wr(0xff, sparx5, FDMA_INTR_DB_ENA); + + return counter; +} + +int lan969x_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev) +{ + int next_dcb, needed_headroom, needed_tailroom, err; + struct sparx5_tx *tx = &sparx5->tx; + struct fdma *fdma = &tx->fdma; + struct sparx5_tx_buf *db_buf; + u64 status; + + next_dcb = lan969x_fdma_get_next_dcb(tx); + if (next_dcb < 0) + return -EBUSY; + + needed_headroom = max_t(int, IFH_LEN * 4 - skb_headroom(skb), 0); + needed_tailroom = max_t(int, ETH_FCS_LEN - skb_tailroom(skb), 0); + if (needed_headroom || needed_tailroom || skb_header_cloned(skb)) { + err = pskb_expand_head(skb, needed_headroom, needed_tailroom, + GFP_ATOMIC); + if (unlikely(err)) + return err; + } + + skb_push(skb, IFH_LEN * 4); + memcpy(skb->data, ifh, IFH_LEN * 4); + skb_put(skb, ETH_FCS_LEN); + + db_buf = &tx->dbs[next_dcb]; + db_buf->dma_addr = dma_map_single(sparx5->dev, + skb->data, + skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(sparx5->dev, db_buf->dma_addr)) + return -ENOMEM; + + db_buf->dev = dev; + db_buf->skb = skb; + db_buf->ptp = false; + db_buf->used = true; + + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + db_buf->ptp = true; + + status = FDMA_DCB_STATUS_SOF | + FDMA_DCB_STATUS_EOF | + FDMA_DCB_STATUS_BLOCKO(0) | + FDMA_DCB_STATUS_BLOCKL(skb->len) | + FDMA_DCB_STATUS_INTR; + + fdma_dcb_advance(fdma); + fdma_dcb_add(fdma, next_dcb, 0, status); + + sparx5_fdma_reload(sparx5, fdma); + + return NETDEV_TX_OK; +} + +int lan969x_fdma_init(struct sparx5 *sparx5) +{ + struct sparx5_rx *rx = &sparx5->rx; + int err; + + lan969x_fdma_rx_init(sparx5); + lan969x_fdma_tx_init(sparx5); + sparx5_fdma_injection_mode(sparx5); + + err = dma_set_mask_and_coherent(sparx5->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(sparx5->dev, "Failed to set 64-bit FDMA mask"); + return err; + } + + err = lan969x_fdma_rx_alloc(sparx5); + if (err) { + dev_err(sparx5->dev, "Failed to allocate RX buffers: %d\n", + err); + return err; + } + + err = lan969x_fdma_tx_alloc(sparx5); + if (err) { + fdma_free_coherent(sparx5->dev, &rx->fdma); + dev_err(sparx5->dev, "Failed to allocate TX buffers: %d\n", + err); + return err; + } + + /* Reset FDMA state */ + spx5_wr(FDMA_CTRL_NRESET_SET(0), sparx5, FDMA_CTRL); + spx5_wr(FDMA_CTRL_NRESET_SET(1), sparx5, FDMA_CTRL); + + return err; +} + +int lan969x_fdma_deinit(struct sparx5 *sparx5) +{ + struct sparx5_rx *rx = &sparx5->rx; + struct sparx5_tx *tx = &sparx5->tx; + + sparx5_fdma_stop(sparx5); + fdma_free_coherent(sparx5->dev, &tx->fdma); + fdma_free_coherent(sparx5->dev, &rx->fdma); + lan969x_fdma_free_pages(rx); + page_pool_destroy(rx->page_pool); + + return 0; +} diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_rgmii.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_rgmii.c new file mode 100644 index 000000000000..4e422ca50828 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_rgmii.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip lan969x Switch driver + * + * Copyright (c) 2024 Microchip Technology Inc. and its subsidiaries. + */ + +#include "lan969x.h" + +/* Tx clock selectors */ +#define LAN969X_RGMII_TX_CLK_SEL_125MHZ 1 /* 1000Mbps */ +#define LAN969X_RGMII_TX_CLK_SEL_25MHZ 2 /* 100Mbps */ +#define LAN969X_RGMII_TX_CLK_SEL_2M5MHZ 3 /* 10Mbps */ + +/* Port speed selectors */ +#define LAN969X_RGMII_SPEED_SEL_10 0 /* Select 10Mbps speed */ +#define LAN969X_RGMII_SPEED_SEL_100 1 /* Select 100Mbps speed */ +#define LAN969X_RGMII_SPEED_SEL_1000 2 /* Select 1000Mbps speed */ + +/* Clock delay selectors */ +#define LAN969X_RGMII_CLK_DELAY_SEL_1_0_NS 2 /* Phase shift 45deg */ +#define LAN969X_RGMII_CLK_DELAY_SEL_1_7_NS 3 /* Phase shift 77deg */ +#define LAN969X_RGMII_CLK_DELAY_SEL_2_0_NS 4 /* Phase shift 90deg */ +#define LAN969X_RGMII_CLK_DELAY_SEL_2_5_NS 5 /* Phase shift 112deg */ +#define LAN969X_RGMII_CLK_DELAY_SEL_3_0_NS 6 /* Phase shift 135deg */ +#define LAN969X_RGMII_CLK_DELAY_SEL_3_3_NS 7 /* Phase shift 147deg */ + +#define LAN969X_RGMII_PORT_START_IDX 28 /* Index of the first RGMII port */ +#define LAN969X_RGMII_IFG_TX 4 /* TX Inter Frame Gap value */ +#define LAN969X_RGMII_IFG_RX1 5 /* RX1 Inter Frame Gap value */ +#define LAN969X_RGMII_IFG_RX2 1 /* RX2 Inter Frame Gap value */ + +#define RGMII_PORT_IDX(port) ((port)->portno - LAN969X_RGMII_PORT_START_IDX) + +/* Get the tx clock selector based on the port speed. */ +static int lan969x_rgmii_get_clk_sel(int speed) +{ + return (speed == SPEED_10 ? LAN969X_RGMII_TX_CLK_SEL_2M5MHZ : + speed == SPEED_100 ? LAN969X_RGMII_TX_CLK_SEL_25MHZ : + LAN969X_RGMII_TX_CLK_SEL_125MHZ); +} + +/* Get the port speed selector based on the port speed. */ +static int lan969x_rgmii_get_speed_sel(int speed) +{ + return (speed == SPEED_10 ? LAN969X_RGMII_SPEED_SEL_10 : + speed == SPEED_100 ? LAN969X_RGMII_SPEED_SEL_100 : + LAN969X_RGMII_SPEED_SEL_1000); +} + +/* Get the clock delay selector based on the clock delay in picoseconds. */ +static int lan969x_rgmii_get_clk_delay_sel(struct sparx5_port *port, + u32 delay_ps, u32 *clk_delay_sel) +{ + switch (delay_ps) { + case 0: + /* Hardware default selector. */ + *clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_2_5_NS; + break; + case 1000: + *clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_1_0_NS; + break; + case 1700: + *clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_1_7_NS; + break; + case 2000: + *clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_2_0_NS; + break; + case 2500: + *clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_2_5_NS; + break; + case 3000: + *clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_3_0_NS; + break; + case 3300: + *clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_3_3_NS; + break; + default: + dev_err(port->sparx5->dev, "Invalid RGMII delay: %u", delay_ps); + return -EINVAL; + } + + return 0; +} + +/* Configure the RGMII tx clock frequency. */ +static void lan969x_rgmii_tx_clk_config(struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + u32 clk_sel = lan969x_rgmii_get_clk_sel(conf->speed); + u32 idx = RGMII_PORT_IDX(port); + + /* Take the RGMII clock domain out of reset and set tx clock + * frequency. + */ + spx5_rmw(HSIO_WRAP_RGMII_CFG_TX_CLK_CFG_SET(clk_sel) | + HSIO_WRAP_RGMII_CFG_RGMII_TX_RST_SET(0) | + HSIO_WRAP_RGMII_CFG_RGMII_RX_RST_SET(0), + HSIO_WRAP_RGMII_CFG_TX_CLK_CFG | + HSIO_WRAP_RGMII_CFG_RGMII_TX_RST | + HSIO_WRAP_RGMII_CFG_RGMII_RX_RST, + port->sparx5, HSIO_WRAP_RGMII_CFG(idx)); +} + +/* Configure the RGMII port device. */ +static void lan969x_rgmii_port_device_config(struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + u32 dtag, dotag, etype, speed_sel, idx = RGMII_PORT_IDX(port); + + speed_sel = lan969x_rgmii_get_speed_sel(conf->speed); + + etype = (port->vlan_type == SPX5_VLAN_PORT_TYPE_S_CUSTOM ? + port->custom_etype : + port->vlan_type == SPX5_VLAN_PORT_TYPE_C ? + ETH_P_8021Q : ETH_P_8021AD); + + dtag = port->max_vlan_tags == SPX5_PORT_MAX_TAGS_TWO; + dotag = port->max_vlan_tags != SPX5_PORT_MAX_TAGS_NONE; + + /* Enable the MAC. */ + spx5_wr(DEVRGMII_MAC_ENA_CFG_RX_ENA_SET(1) | + DEVRGMII_MAC_ENA_CFG_TX_ENA_SET(1), + port->sparx5, DEVRGMII_MAC_ENA_CFG(idx)); + + /* Configure the Inter Frame Gap. */ + spx5_wr(DEVRGMII_MAC_IFG_CFG_TX_IFG_SET(LAN969X_RGMII_IFG_TX) | + DEVRGMII_MAC_IFG_CFG_RX_IFG1_SET(LAN969X_RGMII_IFG_RX1) | + DEVRGMII_MAC_IFG_CFG_RX_IFG2_SET(LAN969X_RGMII_IFG_RX2), + port->sparx5, DEVRGMII_MAC_IFG_CFG(idx)); + + /* Configure port data rate. */ + spx5_wr(DEVRGMII_DEV_RST_CTRL_SPEED_SEL_SET(speed_sel), + port->sparx5, DEVRGMII_DEV_RST_CTRL(idx)); + + /* Configure VLAN awareness. */ + spx5_wr(DEVRGMII_MAC_TAGS_CFG_TAG_ID_SET(etype) | + DEVRGMII_MAC_TAGS_CFG_PB_ENA_SET(dtag) | + DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(dotag) | + DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA_SET(dotag), + port->sparx5, + DEVRGMII_MAC_TAGS_CFG(idx)); +} + +/* Configure the RGMII delay lines in the MAC. + * + * We use the rx-internal-delay-ps" and "tx-internal-delay-ps" properties to + * configure the rx and tx delays for the MAC. If these properties are missing + * or set to zero, the MAC will not apply any delay. + * + * The PHY side delays are determined by the PHY mode + * (e.g. PHY_INTERFACE_MODE_RGMII_{ID, RXID, TXID}), and ignored by the MAC side + * entirely. + */ +static int lan969x_rgmii_delay_config(struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + u32 tx_clk_sel, rx_clk_sel, tx_delay_ps = 0, rx_delay_ps = 0; + u32 idx = RGMII_PORT_IDX(port); + int err; + + of_property_read_u32(port->of_node, "rx-internal-delay-ps", + &rx_delay_ps); + + of_property_read_u32(port->of_node, "tx-internal-delay-ps", + &tx_delay_ps); + + err = lan969x_rgmii_get_clk_delay_sel(port, rx_delay_ps, &rx_clk_sel); + if (err) + return err; + + err = lan969x_rgmii_get_clk_delay_sel(port, tx_delay_ps, &tx_clk_sel); + if (err) + return err; + + /* Configure rx delay. */ + spx5_rmw(HSIO_WRAP_DLL_CFG_DLL_RST_SET(0) | + HSIO_WRAP_DLL_CFG_DLL_ENA_SET(1) | + HSIO_WRAP_DLL_CFG_DLL_CLK_ENA_SET(!!rx_delay_ps) | + HSIO_WRAP_DLL_CFG_DLL_CLK_SEL_SET(rx_clk_sel), + HSIO_WRAP_DLL_CFG_DLL_RST | + HSIO_WRAP_DLL_CFG_DLL_ENA | + HSIO_WRAP_DLL_CFG_DLL_CLK_ENA | + HSIO_WRAP_DLL_CFG_DLL_CLK_SEL, + port->sparx5, HSIO_WRAP_DLL_CFG(idx, 0)); + + /* Configure tx delay. */ + spx5_rmw(HSIO_WRAP_DLL_CFG_DLL_RST_SET(0) | + HSIO_WRAP_DLL_CFG_DLL_ENA_SET(1) | + HSIO_WRAP_DLL_CFG_DLL_CLK_ENA_SET(!!tx_delay_ps) | + HSIO_WRAP_DLL_CFG_DLL_CLK_SEL_SET(tx_clk_sel), + HSIO_WRAP_DLL_CFG_DLL_RST | + HSIO_WRAP_DLL_CFG_DLL_ENA | + HSIO_WRAP_DLL_CFG_DLL_CLK_ENA | + HSIO_WRAP_DLL_CFG_DLL_CLK_SEL, + port->sparx5, HSIO_WRAP_DLL_CFG(idx, 1)); + + return 0; +} + +/* Configure GPIO's to be used as RGMII interface. */ +static void lan969x_rgmii_gpio_config(struct sparx5_port *port) +{ + u32 idx = RGMII_PORT_IDX(port); + + /* Enable the RGMII on the GPIOs. */ + spx5_wr(HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG_SET(1), port->sparx5, + HSIO_WRAP_XMII_CFG(!idx)); +} + +int lan969x_port_config_rgmii(struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + int err; + + err = lan969x_rgmii_delay_config(port, conf); + if (err) + return err; + + lan969x_rgmii_tx_clk_config(port, conf); + lan969x_rgmii_gpio_config(port); + lan969x_rgmii_port_device_config(port, conf); + + return 0; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c index 0027144a2af2..dbe86f937b21 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c @@ -18,9 +18,6 @@ #include "sparx5_main.h" #include "sparx5_port.h" -#define FDMA_XTR_CHANNEL 6 -#define FDMA_INJ_CHANNEL 0 - #define FDMA_XTR_BUFFER_SIZE 2048 #define FDMA_WEIGHT 4 @@ -133,7 +130,7 @@ static void sparx5_fdma_tx_deactivate(struct sparx5 *sparx5, struct sparx5_tx *t sparx5, FDMA_CH_ACTIVATE); } -static void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma) +void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma) { /* Reload the RX channel */ spx5_wr(BIT(fdma->channel_id), sparx5, FDMA_CH_RELOAD); @@ -183,7 +180,7 @@ static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx return true; } -static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight) +int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight) { struct sparx5_rx *rx = container_of(napi, struct sparx5_rx, napi); struct sparx5 *sparx5 = container_of(rx, struct sparx5, rx); @@ -213,11 +210,11 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight) return counter; } -int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb) +int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev) { struct sparx5_tx *tx = &sparx5->tx; struct fdma *fdma = &tx->fdma; - static bool first_time = true; void *virt_addr; fdma_dcb_advance(fdma); @@ -238,12 +235,8 @@ int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb) FDMA_DCB_STATUS_BLOCKO(0) | FDMA_DCB_STATUS_BLOCKL(skb->len + IFH_LEN * 4 + 4)); - if (first_time) { - sparx5_fdma_tx_activate(sparx5, tx); - first_time = false; - } else { - sparx5_fdma_reload(sparx5, fdma); - } + sparx5_fdma_reload(sparx5, fdma); + return NETDEV_TX_OK; } @@ -260,10 +253,6 @@ static int sparx5_fdma_rx_alloc(struct sparx5 *sparx5) fdma_dcbs_init(fdma, FDMA_DCB_INFO_DATAL(fdma->db_size), FDMA_DCB_STATUS_INTR); - netif_napi_add_weight(rx->ndev, &rx->napi, sparx5_fdma_napi_callback, - FDMA_WEIGHT); - napi_enable(&rx->napi); - sparx5_fdma_rx_activate(sparx5, rx); return 0; } @@ -348,7 +337,7 @@ irqreturn_t sparx5_fdma_handler(int irq, void *args) return IRQ_HANDLED; } -static void sparx5_fdma_injection_mode(struct sparx5 *sparx5) +void sparx5_fdma_injection_mode(struct sparx5 *sparx5) { const int byte_swap = 1; int portno; @@ -410,7 +399,7 @@ static void sparx5_fdma_injection_mode(struct sparx5 *sparx5) } } -int sparx5_fdma_start(struct sparx5 *sparx5) +int sparx5_fdma_init(struct sparx5 *sparx5) { int err; @@ -443,24 +432,55 @@ int sparx5_fdma_start(struct sparx5 *sparx5) return err; } +int sparx5_fdma_deinit(struct sparx5 *sparx5) +{ + sparx5_fdma_stop(sparx5); + fdma_free_phys(&sparx5->rx.fdma); + fdma_free_phys(&sparx5->tx.fdma); + + return 0; +} + static u32 sparx5_fdma_port_ctrl(struct sparx5 *sparx5) { return spx5_rd(sparx5, FDMA_PORT_CTRL(0)); } +int sparx5_fdma_start(struct sparx5 *sparx5) +{ + const struct sparx5_ops *ops = sparx5->data->ops; + struct sparx5_rx *rx = &sparx5->rx; + struct sparx5_tx *tx = &sparx5->tx; + + netif_napi_add_weight(rx->ndev, + &rx->napi, + ops->fdma_poll, + FDMA_WEIGHT); + + napi_enable(&rx->napi); + + sparx5_fdma_rx_activate(sparx5, rx); + sparx5_fdma_tx_activate(sparx5, tx); + + return 0; +} + int sparx5_fdma_stop(struct sparx5 *sparx5) { + struct sparx5_rx *rx = &sparx5->rx; + struct sparx5_tx *tx = &sparx5->tx; u32 val; - napi_disable(&sparx5->rx.napi); + napi_disable(&rx->napi); + /* Stop the fdma and channel interrupts */ - sparx5_fdma_rx_deactivate(sparx5, &sparx5->rx); - sparx5_fdma_tx_deactivate(sparx5, &sparx5->tx); + sparx5_fdma_rx_deactivate(sparx5, rx); + sparx5_fdma_tx_deactivate(sparx5, tx); + /* Wait for the RX channel to stop */ read_poll_timeout(sparx5_fdma_port_ctrl, val, FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY_GET(val) == 0, 500, 10000, 0, sparx5); - fdma_free_phys(&sparx5->rx.fdma); - fdma_free_phys(&sparx5->tx.fdma); + return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index f61aa15beab7..6a0e5b83ecd0 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -313,10 +313,13 @@ static int sparx5_create_port(struct sparx5 *sparx5, struct initial_port_config *config) { struct sparx5_port *spx5_port; + const struct sparx5_ops *ops; struct net_device *ndev; struct phylink *phylink; int err; + ops = sparx5->data->ops; + ndev = sparx5_create_netdev(sparx5, config->portno); if (IS_ERR(ndev)) { dev_err(sparx5->dev, "Could not create net device: %02u\n", @@ -357,6 +360,9 @@ static int sparx5_create_port(struct sparx5 *sparx5, MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD | MAC_5000FD | MAC_10000FD | MAC_25000FD; + if (ops->is_port_rgmii(spx5_port->portno)) + phy_interface_set_rgmii(spx5_port->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, spx5_port->phylink_config.supported_interfaces); __set_bit(PHY_INTERFACE_MODE_QSGMII, @@ -778,15 +784,19 @@ static int sparx5_start(struct sparx5 *sparx5) /* Start Frame DMA with fallback to register based INJ/XTR */ err = -ENXIO; - if (sparx5->fdma_irq >= 0 && is_sparx5(sparx5)) { - if (GCB_CHIP_ID_REV_ID_GET(sparx5->chip_id) > 0) + if (sparx5->fdma_irq >= 0) { + if (GCB_CHIP_ID_REV_ID_GET(sparx5->chip_id) > 0 || + !is_sparx5(sparx5)) err = devm_request_irq(sparx5->dev, sparx5->fdma_irq, sparx5_fdma_handler, 0, "sparx5-fdma", sparx5); - if (!err) - err = sparx5_fdma_start(sparx5); + if (!err) { + err = ops->fdma_init(sparx5); + if (!err) + sparx5_fdma_start(sparx5); + } if (err) sparx5->fdma_irq = -ENXIO; } else { @@ -830,6 +840,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev) struct initial_port_config *configs, *config; struct device_node *np = pdev->dev.of_node; struct device_node *ports, *portnp; + const struct sparx5_ops *ops; struct reset_control *reset; struct sparx5 *sparx5; int idx = 0, err = 0; @@ -851,6 +862,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev) return -EINVAL; regs = sparx5->data->regs; + ops = sparx5->data->ops; /* Do switch core reset if available */ reset = devm_reset_control_get_optional_shared(&pdev->dev, "switch"); @@ -880,7 +892,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev) for_each_available_child_of_node(ports, portnp) { struct sparx5_port_config *conf; - struct phy *serdes; + struct phy *serdes = NULL; u32 portno; err = of_property_read_u32(portnp, "reg", &portno); @@ -910,13 +922,17 @@ static int mchp_sparx5_probe(struct platform_device *pdev) conf->sd_sgpio = ~0; else sparx5->sd_sgpio_remapping = true; - serdes = devm_of_phy_get(sparx5->dev, portnp, NULL); - if (IS_ERR(serdes)) { - err = dev_err_probe(sparx5->dev, PTR_ERR(serdes), - "port %u: missing serdes\n", - portno); - of_node_put(portnp); - goto cleanup_config; + /* There is no SerDes node for RGMII ports. */ + if (!ops->is_port_rgmii(portno)) { + serdes = devm_of_phy_get(sparx5->dev, portnp, NULL); + if (IS_ERR(serdes)) { + err = dev_err_probe(sparx5->dev, + PTR_ERR(serdes), + "port %u: missing serdes\n", + portno); + of_node_put(portnp); + goto cleanup_config; + } } config->portno = portno; config->node = portnp; @@ -1014,6 +1030,7 @@ cleanup_pnode: static void mchp_sparx5_remove(struct platform_device *pdev) { struct sparx5 *sparx5 = platform_get_drvdata(pdev); + const struct sparx5_ops *ops = sparx5->data->ops; debugfs_remove_recursive(sparx5->debugfs_root); if (sparx5->xtr_irq) { @@ -1025,7 +1042,7 @@ static void mchp_sparx5_remove(struct platform_device *pdev) sparx5->fdma_irq = -ENXIO; } sparx5_ptp_deinit(sparx5); - sparx5_fdma_stop(sparx5); + ops->fdma_deinit(sparx5); sparx5_cleanup_ports(sparx5); sparx5_vcap_destroy(sparx5); /* Unregister netdevs */ @@ -1072,6 +1089,7 @@ static const struct sparx5_ops sparx5_ops = { .is_port_5g = &sparx5_port_is_5g, .is_port_10g = &sparx5_port_is_10g, .is_port_25g = &sparx5_port_is_25g, + .is_port_rgmii = &sparx5_port_is_rgmii, .get_port_dev_index = &sparx5_port_dev_mapping, .get_port_dev_bit = &sparx5_port_dev_mapping, .get_hsch_max_group_rate = &sparx5_get_hsch_max_group_rate, @@ -1079,6 +1097,10 @@ static const struct sparx5_ops sparx5_ops = { .set_port_mux = &sparx5_port_mux_set, .ptp_irq_handler = &sparx5_ptp_irq_handler, .dsm_calendar_calc = &sparx5_dsm_calendar_calc, + .fdma_init = &sparx5_fdma_init, + .fdma_deinit = &sparx5_fdma_deinit, + .fdma_poll = &sparx5_fdma_napi_callback, + .fdma_xmit = &sparx5_fdma_xmit, }; static const struct sparx5_match_data sparx5_desc = { diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index d5dd953b0a71..fe7d8bcc0cd9 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -112,6 +112,8 @@ enum sparx5_feature { #define XTR_QUEUE 0 #define INJ_QUEUE 0 +#define FDMA_XTR_CHANNEL 6 +#define FDMA_INJ_CHANNEL 0 #define FDMA_DCB_MAX 64 #define FDMA_RX_DCB_MAX_DBS 15 #define FDMA_TX_DCB_MAX_DBS 1 @@ -157,11 +159,25 @@ struct sparx5_calendar_data { */ struct sparx5_rx { struct fdma fdma; - struct sk_buff *skb[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS]; + struct page_pool *page_pool; + union { + struct sk_buff *skb[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS]; + struct page *page[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS]; + }; dma_addr_t dma; struct napi_struct napi; struct net_device *ndev; u64 packets; + u8 page_order; +}; + +/* Used to store information about TX buffers. */ +struct sparx5_tx_buf { + struct net_device *dev; + struct sk_buff *skb; + dma_addr_t dma_addr; + bool used; + bool ptp; }; /* Frame DMA transmit state: @@ -169,6 +185,7 @@ struct sparx5_rx { */ struct sparx5_tx { struct fdma fdma; + struct sparx5_tx_buf *dbs; u64 packets; u64 dropped; }; @@ -313,6 +330,7 @@ struct sparx5_ops { bool (*is_port_5g)(int portno); bool (*is_port_10g)(int portno); bool (*is_port_25g)(int portno); + bool (*is_port_rgmii)(int portno); u32 (*get_port_dev_index)(struct sparx5 *sparx5, int port); u32 (*get_port_dev_bit)(struct sparx5 *sparx5, int port); u32 (*get_hsch_max_group_rate)(int grp); @@ -323,6 +341,13 @@ struct sparx5_ops { irqreturn_t (*ptp_irq_handler)(int irq, void *args); int (*dsm_calendar_calc)(struct sparx5 *sparx5, u32 taxi, struct sparx5_calendar_data *data); + int (*port_config_rgmii)(struct sparx5_port *port, + struct sparx5_port_config *conf); + int (*fdma_init)(struct sparx5 *sparx5); + int (*fdma_deinit)(struct sparx5 *sparx5); + int (*fdma_poll)(struct napi_struct *napi, int weight); + int (*fdma_xmit)(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev); }; struct sparx5_main_io_resource { @@ -433,10 +458,16 @@ int sparx5_manual_injection_mode(struct sparx5 *sparx5); void sparx5_port_inj_timer_setup(struct sparx5_port *port); /* sparx5_fdma.c */ +int sparx5_fdma_init(struct sparx5 *sparx5); +int sparx5_fdma_deinit(struct sparx5 *sparx5); int sparx5_fdma_start(struct sparx5 *sparx5); int sparx5_fdma_stop(struct sparx5 *sparx5); -int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb); +int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight); +int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev); irqreturn_t sparx5_fdma_handler(int irq, void *args); +void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma); +void sparx5_fdma_injection_mode(struct sparx5 *sparx5); /* sparx5_mactable.c */ void sparx5_mact_pull_work(struct work_struct *work); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h index 561344f19062..d9ef4ef137b8 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h @@ -37,6 +37,7 @@ enum sparx5_target { TARGET_FDMA = 117, TARGET_GCB = 118, TARGET_HSCH = 119, + TARGET_HSIO_WRAP = 120, TARGET_LRN = 122, TARGET_PCEP = 129, TARGET_PCS10G_BR = 132, @@ -54,6 +55,7 @@ enum sparx5_target { TARGET_VCAP_SUPER = 326, TARGET_VOP = 327, TARGET_XQS = 331, + TARGET_DEVRGMII = 392, NUM_TARGETS = 517 }; @@ -5367,6 +5369,69 @@ extern const struct sparx5_regs *regs; #define HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY_GET(x)\ FIELD_GET(HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY, x) +/* LAN969X ONLY */ +/* HSIOWRAP:XMII_CFG:XMII_CFG */ +#define HSIO_WRAP_XMII_CFG(g) \ + __REG(TARGET_HSIO_WRAP, 0, 1, 116, g, 2, 20, 0, 0, 1, 4) + +#define HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG GENMASK(2, 1) +#define HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG_SET(x)\ + FIELD_PREP(HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG, x) +#define HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG_GET(x)\ + FIELD_GET(HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG, x) + +/* LAN969X ONLY */ +/* HSIOWRAP:XMII_CFG:RGMII_CFG */ +#define HSIO_WRAP_RGMII_CFG(g) \ + __REG(TARGET_HSIO_WRAP, 0, 1, 116, g, 2, 20, 4, 0, 1, 4) + +#define HSIO_WRAP_RGMII_CFG_TX_CLK_CFG GENMASK(4, 2) +#define HSIO_WRAP_RGMII_CFG_TX_CLK_CFG_SET(x)\ + FIELD_PREP(HSIO_WRAP_RGMII_CFG_TX_CLK_CFG, x) +#define HSIO_WRAP_RGMII_CFG_TX_CLK_CFG_GET(x)\ + FIELD_GET(HSIO_WRAP_RGMII_CFG_TX_CLK_CFG, x) + +#define HSIO_WRAP_RGMII_CFG_RGMII_TX_RST BIT(1) +#define HSIO_WRAP_RGMII_CFG_RGMII_TX_RST_SET(x)\ + FIELD_PREP(HSIO_WRAP_RGMII_CFG_RGMII_TX_RST, x) +#define HSIO_WRAP_RGMII_CFG_RGMII_TX_RST_GET(x)\ + FIELD_GET(HSIO_WRAP_RGMII_CFG_RGMII_TX_RST, x) + +#define HSIO_WRAP_RGMII_CFG_RGMII_RX_RST BIT(0) +#define HSIO_WRAP_RGMII_CFG_RGMII_RX_RST_SET(x)\ + FIELD_PREP(HSIO_WRAP_RGMII_CFG_RGMII_RX_RST, x) +#define HSIO_WRAP_RGMII_CFG_RGMII_RX_RST_GET(x)\ + FIELD_GET(HSIO_WRAP_RGMII_CFG_RGMII_RX_RST, x) + +/* LAN969X ONLY */ +/* HSIOWRAP:XMII_CFG:DLL_CFG */ +#define HSIO_WRAP_DLL_CFG(g, r) \ + __REG(TARGET_HSIO_WRAP, 0, 1, 116, g, 2, 20, 12, r, 2, 4) + +#define HSIO_WRAP_DLL_CFG_DLL_ENA BIT(19) +#define HSIO_WRAP_DLL_CFG_DLL_ENA_SET(x)\ + FIELD_PREP(HSIO_WRAP_DLL_CFG_DLL_ENA, x) +#define HSIO_WRAP_DLL_CFG_DLL_ENA_GET(x)\ + FIELD_GET(HSIO_WRAP_DLL_CFG_DLL_ENA, x) + +#define HSIO_WRAP_DLL_CFG_DLL_CLK_ENA BIT(18) +#define HSIO_WRAP_DLL_CFG_DLL_CLK_ENA_SET(x)\ + FIELD_PREP(HSIO_WRAP_DLL_CFG_DLL_CLK_ENA, x) +#define HSIO_WRAP_DLL_CFG_DLL_CLK_ENA_GET(x)\ + FIELD_GET(HSIO_WRAP_DLL_CFG_DLL_CLK_ENA, x) + +#define HSIO_WRAP_DLL_CFG_DLL_CLK_SEL GENMASK(17, 15) +#define HSIO_WRAP_DLL_CFG_DLL_CLK_SEL_SET(x)\ + FIELD_PREP(HSIO_WRAP_DLL_CFG_DLL_CLK_SEL, x) +#define HSIO_WRAP_DLL_CFG_DLL_CLK_SEL_GET(x)\ + FIELD_GET(HSIO_WRAP_DLL_CFG_DLL_CLK_SEL, x) + +#define HSIO_WRAP_DLL_CFG_DLL_RST BIT(0) +#define HSIO_WRAP_DLL_CFG_DLL_RST_SET(x)\ + FIELD_PREP(HSIO_WRAP_DLL_CFG_DLL_RST, x) +#define HSIO_WRAP_DLL_CFG_DLL_RST_GET(x)\ + FIELD_GET(HSIO_WRAP_DLL_CFG_DLL_RST, x) + /* LRN:COMMON:COMMON_ACCESS_CTRL */ #define LRN_COMMON_ACCESS_CTRL \ __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 0, 0, 1, 4) @@ -8110,4 +8175,84 @@ extern const struct sparx5_regs *regs; #define XQS_CNT(g) \ __REG(TARGET_XQS, 0, 1, 0, g, 1024, 4, 0, 0, 1, 4) +/* LAN969X ONLY */ +/* DEV1G:DEV_CFG_STATUS:DEV_RST_CTRL */ +#define DEVRGMII_DEV_RST_CTRL(t) \ + __REG(TARGET_DEVRGMII, t, 2, 0, 0, 1, 36, 0, 0, 1, 4) + +#define DEVRGMII_DEV_RST_CTRL_SPEED_SEL GENMASK(22, 20) +#define DEVRGMII_DEV_RST_CTRL_SPEED_SEL_SET(x)\ + FIELD_PREP(DEVRGMII_DEV_RST_CTRL_SPEED_SEL, x) +#define DEVRGMII_DEV_RST_CTRL_SPEED_SEL_GET(x)\ + FIELD_GET(DEVRGMII_DEV_RST_CTRL_SPEED_SEL, x) + +/* LAN969X ONLY */ +/* DEV1G:MAC_CFG_STATUS:MAC_ENA_CFG */ +#define DEVRGMII_MAC_ENA_CFG(t) \ + __REG(TARGET_DEVRGMII, t, 2, 36, 0, 1, 36, 0, 0, 1, 4) + +#define DEVRGMII_MAC_ENA_CFG_RX_ENA BIT(4) +#define DEVRGMII_MAC_ENA_CFG_RX_ENA_SET(x)\ + FIELD_PREP(DEVRGMII_MAC_ENA_CFG_RX_ENA, x) +#define DEVRGMII_MAC_ENA_CFG_RX_ENA_GET(x)\ + FIELD_GET(DEVRGMII_MAC_ENA_CFG_RX_ENA, x) + +#define DEVRGMII_MAC_ENA_CFG_TX_ENA BIT(0) +#define DEVRGMII_MAC_ENA_CFG_TX_ENA_SET(x)\ + FIELD_PREP(DEVRGMII_MAC_ENA_CFG_TX_ENA, x) +#define DEVRGMII_MAC_ENA_CFG_TX_ENA_GET(x)\ + FIELD_GET(DEVRGMII_MAC_ENA_CFG_TX_ENA, x) + +/* LAN969X ONLY */ +/* DEV1G:MAC_CFG_STATUS:MAC_TAGS_CFG */ +#define DEVRGMII_MAC_TAGS_CFG(t) \ + __REG(TARGET_DEVRGMII, t, 2, 36, 0, 1, 36, 12, 0, 1, 4) + +#define DEVRGMII_MAC_TAGS_CFG_TAG_ID GENMASK(31, 16) +#define DEVRGMII_MAC_TAGS_CFG_TAG_ID_SET(x)\ + FIELD_PREP(DEVRGMII_MAC_TAGS_CFG_TAG_ID, x) +#define DEVRGMII_MAC_TAGS_CFG_TAG_ID_GET(x)\ + FIELD_GET(DEVRGMII_MAC_TAGS_CFG_TAG_ID, x) + +#define DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA BIT(3) +#define DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA_SET(x)\ + FIELD_PREP(DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA, x) +#define DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA_GET(x)\ + FIELD_GET(DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA, x) + +#define DEVRGMII_MAC_TAGS_CFG_PB_ENA GENMASK(2, 1) +#define DEVRGMII_MAC_TAGS_CFG_PB_ENA_SET(x)\ + FIELD_PREP(DEVRGMII_MAC_TAGS_CFG_PB_ENA, x) +#define DEVRGMII_MAC_TAGS_CFG_PB_ENA_GET(x)\ + FIELD_GET(DEVRGMII_MAC_TAGS_CFG_PB_ENA, x) + +#define DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0) +#define DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(x)\ + FIELD_PREP(DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA, x) +#define DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA_GET(x)\ + FIELD_GET(DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA, x) + +/* LAN969X ONLY */ +/* DEV1G:MAC_CFG_STATUS:MAC_IFG_CFG */ +#define DEVRGMII_MAC_IFG_CFG(t) \ + __REG(TARGET_DEVRGMII, t, 2, 36, 0, 1, 36, 24, 0, 1, 4) + +#define DEVRGMII_MAC_IFG_CFG_TX_IFG GENMASK(12, 8) +#define DEVRGMII_MAC_IFG_CFG_TX_IFG_SET(x)\ + FIELD_PREP(DEVRGMII_MAC_IFG_CFG_TX_IFG, x) +#define DEVRGMII_MAC_IFG_CFG_TX_IFG_GET(x)\ + FIELD_GET(DEVRGMII_MAC_IFG_CFG_TX_IFG, x) + +#define DEVRGMII_MAC_IFG_CFG_RX_IFG2 GENMASK(7, 4) +#define DEVRGMII_MAC_IFG_CFG_RX_IFG2_SET(x)\ + FIELD_PREP(DEVRGMII_MAC_IFG_CFG_RX_IFG2, x) +#define DEVRGMII_MAC_IFG_CFG_RX_IFG2_GET(x)\ + FIELD_GET(DEVRGMII_MAC_IFG_CFG_RX_IFG2, x) + +#define DEVRGMII_MAC_IFG_CFG_RX_IFG1 GENMASK(3, 0) +#define DEVRGMII_MAC_IFG_CFG_RX_IFG1_SET(x)\ + FIELD_PREP(DEVRGMII_MAC_IFG_CFG_RX_IFG1, x) +#define DEVRGMII_MAC_IFG_CFG_RX_IFG1_GET(x)\ + FIELD_GET(DEVRGMII_MAC_IFG_CFG_RX_IFG1, x) + #endif /* _SPARX5_MAIN_REGS_H_ */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index b6f635d85820..138ac58fae51 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -232,9 +232,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) struct net_device_stats *stats = &dev->stats; struct sparx5_port *port = netdev_priv(dev); struct sparx5 *sparx5 = port->sparx5; + const struct sparx5_ops *ops; u32 ifh[IFH_LEN]; netdev_tx_t ret; + ops = sparx5->data->ops; + memset(ifh, 0, IFH_LEN * 4); sparx5_set_port_ifh(sparx5, ifh, port->portno); @@ -254,7 +257,7 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); spin_lock(&sparx5->tx_lock); if (sparx5->fdma_irq > 0) - ret = sparx5_fdma_xmit(sparx5, ifh, skb); + ret = ops->fdma_xmit(sparx5, ifh, skb, dev); else ret = sparx5_inject(sparx5, ifh, skb, dev); spin_unlock(&sparx5->tx_lock); @@ -264,6 +267,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) if (ret < 0) goto drop; + if (!is_sparx5(sparx5)) + /* When lan969x and TX_OK, stats and SKB consumption is handled + * in the TX completion loop, so dont go any further. + */ + return NETDEV_TX_OK; + stats->tx_bytes += skb->len; stats->tx_packets++; sparx5->tx.packets++; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c index f8562c1a894d..cfb4b2e17ace 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c @@ -32,7 +32,19 @@ sparx5_phylink_mac_select_pcs(struct phylink_config *config, { struct sparx5_port *port = netdev_priv(to_net_dev(config->dev)); - return &port->phylink_pcs; + /* Return the PCS for all the modes that require it. */ + switch (interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + case PHY_INTERFACE_MODE_5GBASER: + case PHY_INTERFACE_MODE_10GBASER: + case PHY_INTERFACE_MODE_25GBASER: + return &port->phylink_pcs; + default: + return NULL; + } } static void sparx5_phylink_mac_config(struct phylink_config *config, @@ -77,7 +89,7 @@ static struct sparx5_port *sparx5_pcs_to_port(struct phylink_pcs *pcs) return container_of(pcs, struct sparx5_port, phylink_pcs); } -static void sparx5_pcs_get_state(struct phylink_pcs *pcs, +static void sparx5_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct sparx5_port *port = sparx5_pcs_to_port(pcs); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index f9d1a6bb9bff..04bc8fffaf96 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -257,6 +257,15 @@ static int sparx5_port_verify_speed(struct sparx5 *sparx5, conf->speed != SPEED_25000)) return sparx5_port_error(port, conf, SPX5_PERR_SPEED); break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: + if (conf->speed != SPEED_1000 && + conf->speed != SPEED_100 && + conf->speed != SPEED_10) + return sparx5_port_error(port, conf, SPX5_PERR_SPEED); + break; default: return sparx5_port_error(port, conf, SPX5_PERR_IFTYPE); } @@ -994,6 +1003,7 @@ int sparx5_port_config(struct sparx5 *sparx5, struct sparx5_port *port, struct sparx5_port_config *conf) { + bool rgmii = phy_interface_mode_is_rgmii(conf->phy_mode); bool high_speed_dev = sparx5_is_baser(conf->portmode); const struct sparx5_ops *ops = sparx5->data->ops; int err, urgency, stop_wm; @@ -1002,8 +1012,14 @@ int sparx5_port_config(struct sparx5 *sparx5, if (err) return err; + if (rgmii) { + err = ops->port_config_rgmii(port, conf); + if (err) + return err; + } + /* high speed device is already configured */ - if (!high_speed_dev) + if (!rgmii && !high_speed_dev) sparx5_port_config_low_set(sparx5, port, conf); /* Configure flow control */ @@ -1067,24 +1083,6 @@ int sparx5_port_init(struct sparx5 *sparx5, if (err) return err; - /* Configure MAC vlan awareness */ - err = sparx5_port_max_tags_set(sparx5, port); - if (err) - return err; - - /* Set Max Length */ - spx5_rmw(DEV2G5_MAC_MAXLEN_CFG_MAX_LEN_SET(ETH_MAXLEN), - DEV2G5_MAC_MAXLEN_CFG_MAX_LEN, - sparx5, - DEV2G5_MAC_MAXLEN_CFG(port->portno)); - - /* 1G/2G5: Signal Detect configuration */ - spx5_wr(DEV2G5_PCS1G_SD_CFG_SD_POL_SET(sd_pol) | - DEV2G5_PCS1G_SD_CFG_SD_SEL_SET(sd_sel) | - DEV2G5_PCS1G_SD_CFG_SD_ENA_SET(sd_ena), - sparx5, - DEV2G5_PCS1G_SD_CFG(port->portno)); - /* Set Pause WM hysteresis */ spx5_rmw(QSYS_PAUSE_CFG_PAUSE_START_SET(pause_start) | QSYS_PAUSE_CFG_PAUSE_STOP_SET(pause_stop) | @@ -1108,6 +1106,27 @@ int sparx5_port_init(struct sparx5 *sparx5, ANA_CL_FILTER_CTRL_FILTER_SMAC_MC_DIS, sparx5, ANA_CL_FILTER_CTRL(port->portno)); + if (ops->is_port_rgmii(port->portno)) + return 0; /* RGMII device - nothing more to configure */ + + /* Configure MAC vlan awareness */ + err = sparx5_port_max_tags_set(sparx5, port); + if (err) + return err; + + /* Set Max Length */ + spx5_rmw(DEV2G5_MAC_MAXLEN_CFG_MAX_LEN_SET(ETH_MAXLEN), + DEV2G5_MAC_MAXLEN_CFG_MAX_LEN, + sparx5, + DEV2G5_MAC_MAXLEN_CFG(port->portno)); + + /* 1G/2G5: Signal Detect configuration */ + spx5_wr(DEV2G5_PCS1G_SD_CFG_SD_POL_SET(sd_pol) | + DEV2G5_PCS1G_SD_CFG_SD_SEL_SET(sd_sel) | + DEV2G5_PCS1G_SD_CFG_SD_ENA_SET(sd_ena), + sparx5, + DEV2G5_PCS1G_SD_CFG(port->portno)); + if (conf->portmode == PHY_INTERFACE_MODE_QSGMII || conf->portmode == PHY_INTERFACE_MODE_SGMII) { err = sparx5_serdes_set(sparx5, port, conf); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h index 9b9bcc6834bc..c8a37468a3d1 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h @@ -40,6 +40,11 @@ static inline bool sparx5_port_is_25g(int portno) return portno >= 56 && portno <= 63; } +static inline bool sparx5_port_is_rgmii(int portno) +{ + return false; +} + static inline u32 sparx5_to_high_dev(struct sparx5 *sparx5, int port) { const struct sparx5_ops *ops = sparx5->data->ops; diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 2dc0c6ad54be..be95336ce089 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1656,9 +1656,9 @@ static int __init mana_driver_init(void) static void __exit mana_driver_exit(void) { - debugfs_remove(mana_debugfs_root); - pci_unregister_driver(&mana_driver); + + debugfs_remove(mana_debugfs_root); } module_init(mana_driver_init); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 3d72aa7b1305..ef93df520887 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1432,7 +1432,7 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_bypass(ifh, 1); - ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports)); + ocelot_ifh_set_src(ifh, ocelot->num_phys_ports); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); ocelot_ifh_set_qos_class(ifh, qos_class); ocelot_ifh_set_tag_type(ifh, tag_type); diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 558e03301aa8..7663d196eaf8 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -758,12 +758,13 @@ static int ocelot_port_fdb_do_dump(const unsigned char *addr, u16 vid, bool is_static, void *data) { struct ocelot_dump_ctx *dump = data; + struct ndo_fdb_dump_context *ctx = (void *)dump->cb->ctx; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; struct ndmsg *ndm; - if (dump->idx < dump->cb->args[2]) + if (dump->idx < ctx->fdb_idx) goto skip; nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, @@ -992,6 +993,16 @@ static int ocelot_port_get_ts_info(struct net_device *dev, return ocelot_get_ts_info(ocelot, port, info); } +static void ocelot_port_ts_stats(struct net_device *dev, + struct ethtool_ts_stats *ts_stats) +{ + struct ocelot_port_private *priv = netdev_priv(dev); + struct ocelot *ocelot = priv->port.ocelot; + int port = priv->port.index; + + ocelot_port_get_ts_stats(ocelot, port, ts_stats); +} + static const struct ethtool_ops ocelot_ethtool_ops = { .get_strings = ocelot_port_get_strings, .get_ethtool_stats = ocelot_port_get_ethtool_stats, @@ -999,6 +1010,7 @@ static const struct ethtool_ops ocelot_ethtool_ops = { .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_ts_info = ocelot_port_get_ts_info, + .get_ts_stats = ocelot_port_ts_stats, }; static void ocelot_port_attr_stp_state_set(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c index 808ce8e68d39..cc1088988da0 100644 --- a/drivers/net/ethernet/mscc/ocelot_ptp.c +++ b/drivers/net/ethernet/mscc/ocelot_ptp.c @@ -680,9 +680,14 @@ static int ocelot_port_queue_ptp_tx_skb(struct ocelot *ocelot, int port, skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) { if (time_before(OCELOT_SKB_CB(skb)->ptp_tx_time + OCELOT_PTP_TX_TSTAMP_TIMEOUT, jiffies)) { - dev_warn_ratelimited(ocelot->dev, - "port %d invalidating stale timestamp ID %u which seems lost\n", - port, OCELOT_SKB_CB(skb)->ts_id); + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->lost++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + + dev_dbg_ratelimited(ocelot->dev, + "port %d invalidating stale timestamp ID %u which seems lost\n", + port, OCELOT_SKB_CB(skb)->ts_id); + __skb_unlink(skb, &ocelot_port->tx_skbs); kfree_skb(skb); ocelot->ptp_skbs_in_flight--; @@ -748,13 +753,20 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, return 0; ptp_class = ptp_classify_raw(skb); - if (ptp_class == PTP_CLASS_NONE) - return -EINVAL; + if (ptp_class == PTP_CLASS_NONE) { + err = -EINVAL; + goto error; + } /* Store ptp_cmd in OCELOT_SKB_CB(skb)->ptp_cmd */ if (ptp_cmd == IFH_REW_OP_ORIGIN_PTP) { if (ocelot_ptp_is_onestep_sync(skb, ptp_class)) { OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd; + + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->onestep_pkts_unconfirmed++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + return 0; } @@ -764,14 +776,16 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, if (ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) { *clone = skb_clone_sk(skb); - if (!(*clone)) - return -ENOMEM; + if (!(*clone)) { + err = -ENOMEM; + goto error; + } /* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */ err = ocelot_port_queue_ptp_tx_skb(ocelot, port, *clone); if (err) { kfree_skb(*clone); - return err; + goto error; } skb_shinfo(*clone)->tx_flags |= SKBTX_IN_PROGRESS; @@ -780,6 +794,12 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, } return 0; + +error: + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->err++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + return err; } EXPORT_SYMBOL(ocelot_port_txtstamp_request); @@ -816,6 +836,7 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) while (budget--) { struct skb_shared_hwtstamps shhwtstamps; + struct ocelot_port *ocelot_port; u32 val, id, seqid, txport; struct sk_buff *skb_match; struct timespec64 ts; @@ -832,17 +853,27 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) id = SYS_PTP_STATUS_PTP_MESS_ID_X(val); txport = SYS_PTP_STATUS_PTP_MESS_TXPORT_X(val); seqid = SYS_PTP_STATUS_PTP_MESS_SEQ_ID(val); + ocelot_port = ocelot->ports[txport]; /* Retrieve its associated skb */ skb_match = ocelot_port_dequeue_ptp_tx_skb(ocelot, txport, id, seqid); if (!skb_match) { - dev_warn_ratelimited(ocelot->dev, - "port %d received TX timestamp (seqid %d, ts id %u) for packet previously declared stale\n", - txport, seqid, id); + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->err++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + + dev_dbg_ratelimited(ocelot->dev, + "port %d received TX timestamp (seqid %d, ts id %u) for packet previously declared stale\n", + txport, seqid, id); + goto next_ts; } + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->pkts++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + /* Get the h/w timestamp */ ocelot_get_hwtimestamp(ocelot, &ts); diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c index c018783757fb..545710dadcf5 100644 --- a/drivers/net/ethernet/mscc/ocelot_stats.c +++ b/drivers/net/ethernet/mscc/ocelot_stats.c @@ -821,6 +821,26 @@ void ocelot_port_get_eth_phy_stats(struct ocelot *ocelot, int port, } EXPORT_SYMBOL_GPL(ocelot_port_get_eth_phy_stats); +void ocelot_port_get_ts_stats(struct ocelot *ocelot, int port, + struct ethtool_ts_stats *ts_stats) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct ocelot_ts_stats *stats = ocelot_port->ts_stats; + unsigned int start; + + if (!ocelot->ptp) + return; + + do { + start = u64_stats_fetch_begin(&stats->syncp); + ts_stats->pkts = stats->pkts; + ts_stats->onestep_pkts_unconfirmed = stats->onestep_pkts_unconfirmed; + ts_stats->lost = stats->lost; + ts_stats->err = stats->err; + } while (u64_stats_fetch_retry(&stats->syncp, start)); +} +EXPORT_SYMBOL_GPL(ocelot_port_get_ts_stats); + void ocelot_port_get_stats64(struct ocelot *ocelot, int port, struct rtnl_link_stats64 *stats) { @@ -960,6 +980,23 @@ int ocelot_stats_init(struct ocelot *ocelot) if (!ocelot->stats) return -ENOMEM; + if (ocelot->ptp) { + for (int port = 0; port < ocelot->num_phys_ports; port++) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + + if (!ocelot_port) + continue; + + ocelot_port->ts_stats = devm_kzalloc(ocelot->dev, + sizeof(*ocelot_port->ts_stats), + GFP_KERNEL); + if (!ocelot_port->ts_stats) + return -ENOMEM; + + u64_stats_init(&ocelot_port->ts_stats->syncp); + } + } + snprintf(queue_name, sizeof(queue_name), "%s-stats", dev_name(ocelot->dev)); ocelot->stats_queue = create_singlethread_workqueue(queue_name); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 9d97cd281f18..c03558adda91 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -458,7 +458,8 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data, map_id_full = be64_to_cpu(cbe->map_ptr); map_id = map_id_full; - if (len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size) + if (size_add(pkt_size, data_size) > INT_MAX || + len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size) return -EINVAL; if (cbe->hdr.ver != NFP_CCM_ABI_VERSION) return -EINVAL; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 98e098c09c03..abba165738a3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2779,7 +2779,7 @@ static void nfp_net_netdev_init(struct nfp_net *nn) break; } - netdev->watchdog_timeo = msecs_to_jiffies(5 * 1000); + netdev->watchdog_timeo = secs_to_jiffies(5); /* MTU range: 68 - hw-specific max */ netdev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 720f577929db..499e5e39d513 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -1120,20 +1120,6 @@ static void nv_disable_hw_interrupts(struct net_device *dev, u32 mask) } } -static void nv_napi_enable(struct net_device *dev) -{ - struct fe_priv *np = get_nvpriv(dev); - - napi_enable(&np->napi); -} - -static void nv_napi_disable(struct net_device *dev) -{ - struct fe_priv *np = get_nvpriv(dev); - - napi_disable(&np->napi); -} - #define MII_READ (-1) /* mii_rw: read/write a register on the PHY. * @@ -3114,7 +3100,7 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu) * Changing the MTU is a rare event, it shouldn't matter. */ nv_disable_irq(dev); - nv_napi_disable(dev); + napi_disable(&np->napi); netif_tx_lock_bh(dev); netif_addr_lock(dev); spin_lock(&np->lock); @@ -3143,7 +3129,7 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu) spin_unlock(&np->lock); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); - nv_napi_enable(dev); + napi_enable(&np->napi); nv_enable_irq(dev); } return 0; @@ -4731,7 +4717,7 @@ static int nv_set_ringparam(struct net_device *dev, if (netif_running(dev)) { nv_disable_irq(dev); - nv_napi_disable(dev); + napi_disable(&np->napi); netif_tx_lock_bh(dev); netif_addr_lock(dev); spin_lock(&np->lock); @@ -4784,7 +4770,7 @@ static int nv_set_ringparam(struct net_device *dev, spin_unlock(&np->lock); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); - nv_napi_enable(dev); + napi_enable(&np->napi); nv_enable_irq(dev); } return 0; @@ -5277,7 +5263,7 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64 if (test->flags & ETH_TEST_FL_OFFLINE) { if (netif_running(dev)) { netif_stop_queue(dev); - nv_napi_disable(dev); + napi_disable(&np->napi); netif_tx_lock_bh(dev); netif_addr_lock(dev); spin_lock_irq(&np->lock); @@ -5334,7 +5320,7 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64 /* restart rx engine */ nv_start_rxtx(dev); netif_start_queue(dev); - nv_napi_enable(dev); + napi_enable(&np->napi); nv_enable_hw_interrupts(dev, np->irqmask); } } @@ -5576,6 +5562,7 @@ static int nv_open(struct net_device *dev) /* ask for interrupts */ nv_enable_hw_interrupts(dev, np->irqmask); + netdev_lock(dev); spin_lock_irq(&np->lock); writel(NVREG_MCASTADDRA_FORCE, base + NvRegMulticastAddrA); writel(0, base + NvRegMulticastAddrB); @@ -5594,7 +5581,7 @@ static int nv_open(struct net_device *dev) ret = nv_update_linkspeed(dev); nv_start_rxtx(dev); netif_start_queue(dev); - nv_napi_enable(dev); + napi_enable_locked(&np->napi); if (ret) { netif_carrier_on(dev); @@ -5611,6 +5598,7 @@ static int nv_open(struct net_device *dev) round_jiffies(jiffies + STATS_INTERVAL)); spin_unlock_irq(&np->lock); + netdev_unlock(dev); /* If the loopback feature was set while the device was down, make sure * that it's set correctly now. @@ -5632,7 +5620,7 @@ static int nv_close(struct net_device *dev) spin_lock_irq(&np->lock); np->in_shutdown = 1; spin_unlock_irq(&np->lock); - nv_napi_disable(dev); + napi_disable(&np->napi); synchronize_irq(np->pci_dev->irq); del_timer_sync(&np->oom_kick); diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index f9c0dcd965c2..db200e4ec284 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -113,6 +113,7 @@ struct oa_tc6 { struct mii_bus *mdiobus; struct spi_device *spi; struct mutex spi_ctrl_lock; /* Protects spi control transfer */ + spinlock_t tx_skb_lock; /* Protects tx skb handling */ void *spi_ctrl_tx_buf; void *spi_ctrl_rx_buf; void *spi_data_tx_buf; @@ -1004,8 +1005,10 @@ static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6) for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits; used_tx_credits++) { if (!tc6->ongoing_tx_skb) { + spin_lock_bh(&tc6->tx_skb_lock); tc6->ongoing_tx_skb = tc6->waiting_tx_skb; tc6->waiting_tx_skb = NULL; + spin_unlock_bh(&tc6->tx_skb_lock); } if (!tc6->ongoing_tx_skb) break; @@ -1111,8 +1114,9 @@ static int oa_tc6_spi_thread_handler(void *data) /* This kthread will be waken up if there is a tx skb or mac-phy * interrupt to perform spi transfer with tx chunks. */ - wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb || - tc6->int_flag || + wait_event_interruptible(tc6->spi_wq, tc6->int_flag || + (tc6->waiting_tx_skb && + tc6->tx_credits) || kthread_should_stop()); if (kthread_should_stop()) @@ -1209,7 +1213,9 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) return NETDEV_TX_OK; } + spin_lock_bh(&tc6->tx_skb_lock); tc6->waiting_tx_skb = skb; + spin_unlock_bh(&tc6->tx_skb_lock); /* Wake spi kthread to perform spi transfer */ wake_up_interruptible(&tc6->spi_wq); @@ -1239,6 +1245,7 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) tc6->netdev = netdev; SET_NETDEV_DEV(netdev, &spi->dev); mutex_init(&tc6->spi_ctrl_lock); + spin_lock_init(&tc6->tx_skb_lock); /* Set the SPI controller to pump at realtime priority */ tc6->spi->rt = true; diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h index 1c61390677f7..04f00ea94230 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic.h +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -18,8 +18,6 @@ struct ionic_lif; #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF 0x1002 #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003 -#define IONIC_ASIC_TYPE_ELBA 2 - #define DEVCMD_TIMEOUT 5 #define IONIC_ADMINQ_TIME_SLICE msecs_to_jiffies(100) @@ -59,7 +57,6 @@ struct ionic { DECLARE_BITMAP(intrs, IONIC_INTR_CTRL_REGS_MAX); cpumask_var_t *affinity_masks; struct delayed_work doorbell_check_dwork; - struct work_struct nb_work; struct notifier_block nb; struct rw_semaphore vf_op_lock; /* lock for VF operations */ struct ionic_vf *vfs; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 9e42d599840d..57edcde9e6f8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -277,7 +277,10 @@ void ionic_dev_teardown(struct ionic *ionic) idev->phy_cmb_pages = 0; idev->cmb_npages = 0; - destroy_workqueue(ionic->wq); + if (ionic->wq) { + destroy_workqueue(ionic->wq); + ionic->wq = NULL; + } mutex_destroy(&idev->cmb_inuse_lock); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index dda22fa4448c..a2d4336d2766 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -158,6 +158,20 @@ static int ionic_get_link_ksettings(struct net_device *netdev, 25000baseCR_Full); copper_seen++; break; + case IONIC_XCVR_PID_QSFP_50G_CR2_FC: + case IONIC_XCVR_PID_QSFP_50G_CR2: + ethtool_link_ksettings_add_link_mode(ks, supported, + 50000baseCR2_Full); + copper_seen++; + break; + case IONIC_XCVR_PID_QSFP_200G_CR4: + ethtool_link_ksettings_add_link_mode(ks, supported, 200000baseCR4_Full); + copper_seen++; + break; + case IONIC_XCVR_PID_QSFP_400G_CR4: + ethtool_link_ksettings_add_link_mode(ks, supported, 400000baseCR4_Full); + copper_seen++; + break; case IONIC_XCVR_PID_SFP_10GBASE_AOC: case IONIC_XCVR_PID_SFP_10GBASE_CU: ethtool_link_ksettings_add_link_mode(ks, supported, @@ -196,6 +210,31 @@ static int ionic_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_add_link_mode(ks, supported, 25000baseSR_Full); break; + case IONIC_XCVR_PID_QSFP_200G_AOC: + case IONIC_XCVR_PID_QSFP_200G_SR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 200000baseSR4_Full); + break; + case IONIC_XCVR_PID_QSFP_200G_FR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 200000baseLR4_ER4_FR4_Full); + break; + case IONIC_XCVR_PID_QSFP_200G_DR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 200000baseDR4_Full); + break; + case IONIC_XCVR_PID_QSFP_400G_FR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 400000baseLR4_ER4_FR4_Full); + break; + case IONIC_XCVR_PID_QSFP_400G_DR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 400000baseDR4_Full); + break; + case IONIC_XCVR_PID_QSFP_400G_SR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 400000baseSR4_Full); + break; case IONIC_XCVR_PID_SFP_10GBASE_SR: ethtool_link_ksettings_add_link_mode(ks, supported, 10000baseSR_Full); @@ -929,6 +968,7 @@ static int ionic_get_module_info(struct net_device *netdev, break; case SFF8024_ID_QSFP_8436_8636: case SFF8024_ID_QSFP28_8636: + case SFF8024_ID_QSFP_PLUS_CMIS: modinfo->type = ETH_MODULE_SFF_8436; modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; break; @@ -961,8 +1001,8 @@ static int ionic_get_module_eeprom(struct net_device *netdev, len = min_t(u32, sizeof(xcvr->sprom), ee->len); do { - memcpy(data, xcvr->sprom, len); - memcpy(tbuf, xcvr->sprom, len); + memcpy(data, &xcvr->sprom[ee->offset], len); + memcpy(tbuf, &xcvr->sprom[ee->offset], len); /* Let's make sure we got a consistent copy */ if (!memcmp(data, tbuf, len)) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h index 9c85c0706c6e..830c8adbfbee 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_if.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h @@ -1277,7 +1277,10 @@ enum ionic_xcvr_pid { IONIC_XCVR_PID_SFP_25GBASE_CR_S = 3, IONIC_XCVR_PID_SFP_25GBASE_CR_L = 4, IONIC_XCVR_PID_SFP_25GBASE_CR_N = 5, - + IONIC_XCVR_PID_QSFP_50G_CR2_FC = 6, + IONIC_XCVR_PID_QSFP_50G_CR2 = 7, + IONIC_XCVR_PID_QSFP_200G_CR4 = 8, + IONIC_XCVR_PID_QSFP_400G_CR4 = 9, /* Fiber */ IONIC_XCVR_PID_QSFP_100G_AOC = 50, IONIC_XCVR_PID_QSFP_100G_ACC = 51, @@ -1303,6 +1306,15 @@ enum ionic_xcvr_pid { IONIC_XCVR_PID_SFP_25GBASE_ACC = 71, IONIC_XCVR_PID_SFP_10GBASE_T = 72, IONIC_XCVR_PID_SFP_1000BASE_T = 73, + IONIC_XCVR_PID_QSFP_200G_AOC = 74, + IONIC_XCVR_PID_QSFP_200G_FR4 = 75, + IONIC_XCVR_PID_QSFP_200G_DR4 = 76, + IONIC_XCVR_PID_QSFP_200G_SR4 = 77, + IONIC_XCVR_PID_QSFP_200G_ACC = 78, + IONIC_XCVR_PID_QSFP_400G_FR4 = 79, + IONIC_XCVR_PID_QSFP_400G_DR4 = 80, + IONIC_XCVR_PID_QSFP_400G_SR4 = 81, + IONIC_XCVR_PID_QSFP_400G_VR4 = 82, }; /** @@ -1404,6 +1416,8 @@ struct ionic_xcvr_status { */ union ionic_port_config { struct { +#define IONIC_SPEED_400G 400000 /* 400G in Mbps */ +#define IONIC_SPEED_200G 200000 /* 200G in Mbps */ #define IONIC_SPEED_100G 100000 /* 100G in Mbps */ #define IONIC_SPEED_50G 50000 /* 50G in Mbps */ #define IONIC_SPEED_40G 40000 /* 40G in Mbps */ @@ -3209,7 +3223,11 @@ union ionic_adminq_comp { #define IONIC_BAR0_INTR_CTRL_OFFSET 0x2000 #define IONIC_DEV_CMD_DONE 0x00000001 -#define IONIC_ASIC_TYPE_CAPRI 0 +#define IONIC_ASIC_TYPE_NONE 0 +#define IONIC_ASIC_TYPE_CAPRI 1 +#define IONIC_ASIC_TYPE_ELBA 2 +#define IONIC_ASIC_TYPE_GIGLIO 3 +#define IONIC_ASIC_TYPE_SALINA 4 /** * struct ionic_doorbell - Doorbell register layout diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 40496587b2b3..7707a9e53c43 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3265,7 +3265,7 @@ int ionic_lif_alloc(struct ionic *ionic) lif->netdev->min_mtu = max_t(unsigned int, ETH_MIN_MTU, le32_to_cpu(lif->identity->eth.min_frame_size)); lif->netdev->max_mtu = - le32_to_cpu(lif->identity->eth.max_frame_size) - ETH_HLEN - VLAN_HLEN; + le32_to_cpu(lif->identity->eth.max_frame_size) - VLAN_ETH_HLEN; lif->neqs = ionic->neqs_per_lif; lif->nxqs = ionic->ntxqs_per_lif; @@ -3804,10 +3804,6 @@ err_out_adminq_deinit: return err; } -static void ionic_lif_notify_work(struct work_struct *ws) -{ -} - static void ionic_lif_set_netdev_info(struct ionic_lif *lif) { struct ionic_admin_ctx ctx = { @@ -3858,8 +3854,6 @@ int ionic_lif_register(struct ionic_lif *lif) ionic_lif_register_phc(lif); - INIT_WORK(&lif->ionic->nb_work, ionic_lif_notify_work); - lif->ionic->nb.notifier_call = ionic_lif_notify; err = register_netdevice_notifier(&lif->ionic->nb); @@ -3869,8 +3863,8 @@ int ionic_lif_register(struct ionic_lif *lif) /* only register LIF0 for now */ err = register_netdev(lif->netdev); if (err) { - dev_err(lif->ionic->dev, "Cannot register net device, aborting\n"); - ionic_lif_unregister_phc(lif); + dev_err(lif->ionic->dev, "Cannot register net device: %d, aborting\n", err); + ionic_lif_unregister(lif); return err; } @@ -3885,7 +3879,6 @@ void ionic_lif_unregister(struct ionic_lif *lif) { if (lif->ionic->nb.notifier_call) { unregister_netdevice_notifier(&lif->ionic->nb); - cancel_work_sync(&lif->ionic->nb_work); lif->ionic->nb.notifier_call = NULL; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 0f817c3f92d8..daf1e82cb76b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -81,8 +81,9 @@ static int ionic_error_to_errno(enum ionic_status_code code) case IONIC_RC_EQTYPE: case IONIC_RC_EQID: case IONIC_RC_EINVAL: - case IONIC_RC_ENOSUPP: return -EINVAL; + case IONIC_RC_ENOSUPP: + return -EOPNOTSUPP; case IONIC_RC_EPERM: return -EPERM; case IONIC_RC_ENOENT: diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 9cff0a8ffb2c..3383ee1dad14 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -2832,7 +2832,7 @@ netxen_sysfs_validate_crb(struct netxen_adapter *adapter, static ssize_t netxen_sysfs_read_crb(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = kobj_to_dev(kobj); @@ -2860,7 +2860,7 @@ netxen_sysfs_read_crb(struct file *filp, struct kobject *kobj, static ssize_t netxen_sysfs_write_crb(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = kobj_to_dev(kobj); @@ -2901,7 +2901,7 @@ netxen_sysfs_validate_mem(struct netxen_adapter *adapter, static ssize_t netxen_sysfs_read_mem(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = kobj_to_dev(kobj); @@ -2922,7 +2922,7 @@ netxen_sysfs_read_mem(struct file *filp, struct kobject *kobj, } static ssize_t netxen_sysfs_write_mem(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = kobj_to_dev(kobj); @@ -2946,20 +2946,20 @@ static ssize_t netxen_sysfs_write_mem(struct file *filp, struct kobject *kobj, static const struct bin_attribute bin_attr_crb = { .attr = { .name = "crb", .mode = 0644 }, .size = 0, - .read = netxen_sysfs_read_crb, - .write = netxen_sysfs_write_crb, + .read_new = netxen_sysfs_read_crb, + .write_new = netxen_sysfs_write_crb, }; static const struct bin_attribute bin_attr_mem = { .attr = { .name = "mem", .mode = 0644 }, .size = 0, - .read = netxen_sysfs_read_mem, - .write = netxen_sysfs_write_mem, + .read_new = netxen_sysfs_read_mem, + .write_new = netxen_sysfs_write_mem, }; static ssize_t netxen_sysfs_read_dimm(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = kobj_to_dev(kobj); @@ -3082,7 +3082,7 @@ out: static const struct bin_attribute bin_attr_dimm = { .attr = { .name = "dimm", .mode = 0644 }, .size = sizeof(struct netxen_dimm_cfg), - .read = netxen_sysfs_read_dimm, + .read_new = netxen_sysfs_read_dimm, }; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index b45efc272fdb..c7f497c36f66 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3358,6 +3358,7 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) p_ptt, &nvm_info.num_images); if (rc == -EOPNOTSUPP) { DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n"); + nvm_info.num_images = 0; goto out; } else if (rc || !nvm_info.num_images) { DP_ERR(p_hwfn, "Failed getting number of images\n"); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index 74125188beb8..c0f20464fd1e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -264,7 +264,7 @@ static int qlcnic_sysfs_validate_crb(struct qlcnic_adapter *adapter, } static ssize_t qlcnic_sysfs_read_crb(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = kobj_to_dev(kobj); @@ -281,7 +281,7 @@ static ssize_t qlcnic_sysfs_read_crb(struct file *filp, struct kobject *kobj, } static ssize_t qlcnic_sysfs_write_crb(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = kobj_to_dev(kobj); @@ -310,7 +310,7 @@ static int qlcnic_sysfs_validate_mem(struct qlcnic_adapter *adapter, } static ssize_t qlcnic_sysfs_read_mem(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = kobj_to_dev(kobj); @@ -332,7 +332,7 @@ static ssize_t qlcnic_sysfs_read_mem(struct file *filp, struct kobject *kobj, } static ssize_t qlcnic_sysfs_write_mem(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = kobj_to_dev(kobj); @@ -396,7 +396,7 @@ static int validate_pm_config(struct qlcnic_adapter *adapter, static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -446,7 +446,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp, static ssize_t qlcnic_sysfs_read_pm_config(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -539,7 +539,7 @@ static int validate_esw_config(struct qlcnic_adapter *adapter, static ssize_t qlcnic_sysfs_write_esw_config(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -623,7 +623,7 @@ out: static ssize_t qlcnic_sysfs_read_esw_config(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -675,7 +675,7 @@ static int validate_npar_config(struct qlcnic_adapter *adapter, static ssize_t qlcnic_sysfs_write_npar_config(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -722,7 +722,7 @@ static ssize_t qlcnic_sysfs_write_npar_config(struct file *file, static ssize_t qlcnic_sysfs_read_npar_config(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -769,7 +769,7 @@ static ssize_t qlcnic_sysfs_read_npar_config(struct file *file, static ssize_t qlcnic_sysfs_get_port_stats(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -804,7 +804,7 @@ static ssize_t qlcnic_sysfs_get_port_stats(struct file *file, static ssize_t qlcnic_sysfs_get_esw_stats(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -839,7 +839,7 @@ static ssize_t qlcnic_sysfs_get_esw_stats(struct file *file, static ssize_t qlcnic_sysfs_clear_esw_stats(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -868,7 +868,7 @@ static ssize_t qlcnic_sysfs_clear_esw_stats(struct file *file, static ssize_t qlcnic_sysfs_clear_port_stats(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -898,7 +898,7 @@ static ssize_t qlcnic_sysfs_clear_port_stats(struct file *file, static ssize_t qlcnic_sysfs_read_pci_config(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -938,7 +938,7 @@ static ssize_t qlcnic_sysfs_read_pci_config(struct file *file, static ssize_t qlcnic_83xx_sysfs_flash_read_handler(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -1115,7 +1115,7 @@ static int qlcnic_83xx_sysfs_flash_write(struct qlcnic_adapter *adapter, static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { @@ -1195,64 +1195,63 @@ static const struct device_attribute dev_attr_beacon = { static const struct bin_attribute bin_attr_crb = { .attr = { .name = "crb", .mode = 0644 }, .size = 0, - .read = qlcnic_sysfs_read_crb, - .write = qlcnic_sysfs_write_crb, + .read_new = qlcnic_sysfs_read_crb, + .write_new = qlcnic_sysfs_write_crb, }; static const struct bin_attribute bin_attr_mem = { .attr = { .name = "mem", .mode = 0644 }, .size = 0, - .read = qlcnic_sysfs_read_mem, - .write = qlcnic_sysfs_write_mem, + .read_new = qlcnic_sysfs_read_mem, + .write_new = qlcnic_sysfs_write_mem, }; static const struct bin_attribute bin_attr_npar_config = { .attr = { .name = "npar_config", .mode = 0644 }, .size = 0, - .read = qlcnic_sysfs_read_npar_config, - .write = qlcnic_sysfs_write_npar_config, + .read_new = qlcnic_sysfs_read_npar_config, + .write_new = qlcnic_sysfs_write_npar_config, }; static const struct bin_attribute bin_attr_pci_config = { .attr = { .name = "pci_config", .mode = 0644 }, .size = 0, - .read = qlcnic_sysfs_read_pci_config, - .write = NULL, + .read_new = qlcnic_sysfs_read_pci_config, }; static const struct bin_attribute bin_attr_port_stats = { .attr = { .name = "port_stats", .mode = 0644 }, .size = 0, - .read = qlcnic_sysfs_get_port_stats, - .write = qlcnic_sysfs_clear_port_stats, + .read_new = qlcnic_sysfs_get_port_stats, + .write_new = qlcnic_sysfs_clear_port_stats, }; static const struct bin_attribute bin_attr_esw_stats = { .attr = { .name = "esw_stats", .mode = 0644 }, .size = 0, - .read = qlcnic_sysfs_get_esw_stats, - .write = qlcnic_sysfs_clear_esw_stats, + .read_new = qlcnic_sysfs_get_esw_stats, + .write_new = qlcnic_sysfs_clear_esw_stats, }; static const struct bin_attribute bin_attr_esw_config = { .attr = { .name = "esw_config", .mode = 0644 }, .size = 0, - .read = qlcnic_sysfs_read_esw_config, - .write = qlcnic_sysfs_write_esw_config, + .read_new = qlcnic_sysfs_read_esw_config, + .write_new = qlcnic_sysfs_write_esw_config, }; static const struct bin_attribute bin_attr_pm_config = { .attr = { .name = "pm_config", .mode = 0644 }, .size = 0, - .read = qlcnic_sysfs_read_pm_config, - .write = qlcnic_sysfs_write_pm_config, + .read_new = qlcnic_sysfs_read_pm_config, + .write_new = qlcnic_sysfs_write_pm_config, }; static const struct bin_attribute bin_attr_flash = { .attr = { .name = "flash", .mode = 0644 }, .size = 0, - .read = qlcnic_83xx_sysfs_flash_read_handler, - .write = qlcnic_83xx_sysfs_flash_write_handler, + .read_new = qlcnic_83xx_sysfs_flash_read_handler, + .write_new = qlcnic_83xx_sysfs_flash_write_handler, }; #ifdef CONFIG_QLCNIC_HWMON diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 9ce0e8a64ba8..a73dcaffa8c5 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -1684,6 +1684,7 @@ static void rtl8139_tx_timeout_task (struct work_struct *work) if (tmp8 & CmdTxEnb) RTL_W8 (ChipCmd, CmdRxEnb); + netdev_lock(dev); spin_lock_bh(&tp->rx_lock); /* Disable interrupts by clearing the interrupt mask. */ RTL_W16 (IntrMask, 0x0000); @@ -1694,11 +1695,12 @@ static void rtl8139_tx_timeout_task (struct work_struct *work) spin_unlock_irq(&tp->lock); /* ...and finally, reset everything */ - napi_enable(&tp->napi); + napi_enable_locked(&tp->napi); rtl8139_hw_start(dev); netif_wake_queue(dev); spin_unlock_bh(&tp->rx_lock); + netdev_unlock(dev); } static void rtl8139_tx_timeout(struct net_device *dev, unsigned int txqueue) diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h index be4c9622618d..7a194a8ab989 100644 --- a/drivers/net/ethernet/realtek/r8169.h +++ b/drivers/net/ethernet/realtek/r8169.h @@ -23,7 +23,7 @@ enum mac_version { RTL_GIGA_MAC_VER_08, RTL_GIGA_MAC_VER_09, RTL_GIGA_MAC_VER_10, - RTL_GIGA_MAC_VER_11, + /* support for RTL_GIGA_MAC_VER_11 has been removed */ /* RTL_GIGA_MAC_VER_12 was handled the same as VER_17 */ /* RTL_GIGA_MAC_VER_13 was merged with VER_10 */ RTL_GIGA_MAC_VER_14, @@ -71,6 +71,8 @@ enum mac_version { RTL_GIGA_MAC_VER_64, RTL_GIGA_MAC_VER_65, RTL_GIGA_MAC_VER_66, + RTL_GIGA_MAC_VER_70, + RTL_GIGA_MAC_VER_71, RTL_GIGA_MAC_NONE }; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 739707a7b40f..5a5eba49c651 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -57,6 +56,8 @@ #define FIRMWARE_8125A_3 "rtl_nic/rtl8125a-3.fw" #define FIRMWARE_8125B_2 "rtl_nic/rtl8125b-2.fw" #define FIRMWARE_8125D_1 "rtl_nic/rtl8125d-1.fw" +#define FIRMWARE_8125D_2 "rtl_nic/rtl8125d-2.fw" +#define FIRMWARE_8125BP_2 "rtl_nic/rtl8125bp-2.fw" #define FIRMWARE_8126A_2 "rtl_nic/rtl8126a-2.fw" #define FIRMWARE_8126A_3 "rtl_nic/rtl8126a-3.fw" @@ -104,7 +105,6 @@ static const struct { [RTL_GIGA_MAC_VER_08] = {"RTL8102e" }, [RTL_GIGA_MAC_VER_09] = {"RTL8102e/RTL8103e" }, [RTL_GIGA_MAC_VER_10] = {"RTL8101e/RTL8100e" }, - [RTL_GIGA_MAC_VER_11] = {"RTL8168b/8111b" }, [RTL_GIGA_MAC_VER_14] = {"RTL8401" }, [RTL_GIGA_MAC_VER_17] = {"RTL8168b/8111b" }, [RTL_GIGA_MAC_VER_18] = {"RTL8168cp/8111cp" }, @@ -141,8 +141,10 @@ static const struct { /* reserve 62 for CFG_METHOD_4 in the vendor driver */ [RTL_GIGA_MAC_VER_63] = {"RTL8125B", FIRMWARE_8125B_2}, [RTL_GIGA_MAC_VER_64] = {"RTL8125D", FIRMWARE_8125D_1}, - [RTL_GIGA_MAC_VER_65] = {"RTL8126A", FIRMWARE_8126A_2}, - [RTL_GIGA_MAC_VER_66] = {"RTL8126A", FIRMWARE_8126A_3}, + [RTL_GIGA_MAC_VER_65] = {"RTL8125D", FIRMWARE_8125D_2}, + [RTL_GIGA_MAC_VER_66] = {"RTL8125BP", FIRMWARE_8125BP_2}, + [RTL_GIGA_MAC_VER_70] = {"RTL8126A", FIRMWARE_8126A_2}, + [RTL_GIGA_MAC_VER_71] = {"RTL8126A", FIRMWARE_8126A_3}, }; static const struct pci_device_id rtl8169_pci_tbl[] = { @@ -623,7 +625,6 @@ struct rtl8169_tc_offsets { enum rtl_flag { RTL_FLAG_TASK_RESET_PENDING, - RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE, RTL_FLAG_TASK_TX_TIMEOUT, RTL_FLAG_MAX }; @@ -632,6 +633,7 @@ enum rtl_dash_type { RTL_DASH_NONE, RTL_DASH_DP, RTL_DASH_EP, + RTL_DASH_25_BP, }; struct rtl8169_private { @@ -708,6 +710,8 @@ MODULE_FIRMWARE(FIRMWARE_8107E_2); MODULE_FIRMWARE(FIRMWARE_8125A_3); MODULE_FIRMWARE(FIRMWARE_8125B_2); MODULE_FIRMWARE(FIRMWARE_8125D_1); +MODULE_FIRMWARE(FIRMWARE_8125D_2); +MODULE_FIRMWARE(FIRMWARE_8125BP_2); MODULE_FIRMWARE(FIRMWARE_8126A_2); MODULE_FIRMWARE(FIRMWARE_8126A_3); @@ -1230,7 +1234,7 @@ static void rtl_writephy(struct rtl8169_private *tp, int location, int val) case RTL_GIGA_MAC_VER_31: r8168dp_2_mdio_write(tp, location, val); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: r8168g_mdio_write(tp, location, val); break; default: @@ -1245,7 +1249,7 @@ static int rtl_readphy(struct rtl8169_private *tp, int location) case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: return r8168dp_2_mdio_read(tp, location); - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: return r8168g_mdio_read(tp, location); default: return r8169_mdio_read(tp, location); @@ -1360,10 +1364,19 @@ static void rtl8168ep_driver_start(struct rtl8169_private *tp) rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); } +static void rtl8125bp_driver_start(struct rtl8169_private *tp) +{ + r8168ep_ocp_write(tp, 0x01, 0x14, OOB_CMD_DRIVER_START); + r8168ep_ocp_write(tp, 0x01, 0x18, 0x00); + r8168ep_ocp_write(tp, 0x01, 0x10, 0x01); +} + static void rtl8168_driver_start(struct rtl8169_private *tp) { if (tp->dash_type == RTL_DASH_DP) rtl8168dp_driver_start(tp); + else if (tp->dash_type == RTL_DASH_25_BP) + rtl8125bp_driver_start(tp); else rtl8168ep_driver_start(tp); } @@ -1384,10 +1397,19 @@ static void rtl8168ep_driver_stop(struct rtl8169_private *tp) rtl_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10); } +static void rtl8125bp_driver_stop(struct rtl8169_private *tp) +{ + r8168ep_ocp_write(tp, 0x01, 0x14, OOB_CMD_DRIVER_STOP); + r8168ep_ocp_write(tp, 0x01, 0x18, 0x00); + r8168ep_ocp_write(tp, 0x01, 0x10, 0x01); +} + static void rtl8168_driver_stop(struct rtl8169_private *tp) { if (tp->dash_type == RTL_DASH_DP) rtl8168dp_driver_stop(tp); + else if (tp->dash_type == RTL_DASH_25_BP) + rtl8125bp_driver_stop(tp); else rtl8168ep_driver_stop(tp); } @@ -1410,6 +1432,7 @@ static bool rtl_dash_is_enabled(struct rtl8169_private *tp) case RTL_DASH_DP: return r8168dp_check_dash(tp); case RTL_DASH_EP: + case RTL_DASH_25_BP: return r8168ep_check_dash(tp); default: return false; @@ -1424,6 +1447,8 @@ static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp) return RTL_DASH_DP; case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53: return RTL_DASH_EP; + case RTL_GIGA_MAC_VER_66: + return RTL_DASH_25_BP; default: return RTL_DASH_NONE; } @@ -1576,7 +1601,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) break; case RTL_GIGA_MAC_VER_34: case RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_71: r8169_mod_reg8_cond(tp, Config2, PME_SIGNAL, wolopts); break; default: @@ -2049,7 +2074,7 @@ static void rtl_set_eee_txidle_timer(struct rtl8169_private *tp) tp->tx_lpi_timer = timer_val; r8168_mac_ocp_write(tp, 0xe048, timer_val); break; - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: tp->tx_lpi_timer = timer_val; RTL_W16(tp, EEE_TXIDLE_TIMER_8125, timer_val); break; @@ -2257,10 +2282,14 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) enum mac_version ver; } mac_info[] = { /* 8126A family. */ - { 0x7cf, 0x64a, RTL_GIGA_MAC_VER_66 }, - { 0x7cf, 0x649, RTL_GIGA_MAC_VER_65 }, + { 0x7cf, 0x64a, RTL_GIGA_MAC_VER_71 }, + { 0x7cf, 0x649, RTL_GIGA_MAC_VER_70 }, + + /* 8125BP family. */ + { 0x7cf, 0x681, RTL_GIGA_MAC_VER_66 }, /* 8125D family. */ + { 0x7cf, 0x689, RTL_GIGA_MAC_VER_65 }, { 0x7cf, 0x688, RTL_GIGA_MAC_VER_64 }, /* 8125B family. */ @@ -2336,7 +2365,7 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) /* 8168B family. */ { 0x7c8, 0x380, RTL_GIGA_MAC_VER_17 }, - /* This one is very old and rare, let's see if anybody complains. + /* This one is very old and rare, support has been removed. * { 0x7c8, 0x300, RTL_GIGA_MAC_VER_11 }, */ @@ -2528,7 +2557,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_61: RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST); break; - case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_71: RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST | RX_PAUSE_SLOT_ON); break; @@ -2660,7 +2689,7 @@ static void rtl_wait_txrx_fifo_empty(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_61: rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42); break; - case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_71: RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq); rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42); rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond_2, 100, 42); @@ -2903,7 +2932,7 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_38: rtl_eri_set_bits(tp, 0xd4, 0x0c00); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80); break; default: @@ -2917,7 +2946,7 @@ static void rtl_disable_exit_l1(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38: rtl_eri_clear_bits(tp, 0xd4, 0x1f00); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: r8168_mac_ocp_modify(tp, 0xc0ac, 0x1f80, 0); break; default: @@ -2943,8 +2972,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) rtl_mod_config5(tp, 0, ASPM_en); switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_65: - case RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_70: + case RTL_GIGA_MAC_VER_71: val8 = RTL_R8(tp, INT_CFG0_8125) | INT_CFG0_CLKREQEN; RTL_W8(tp, INT_CFG0_8125, val8); break; @@ -2955,7 +2984,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) switch (tp->mac_version) { case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: /* reset ephy tx/rx disable timer */ r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0); /* chip can trigger L1.2 */ @@ -2967,7 +2996,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) } else { switch (tp->mac_version) { case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0); break; default: @@ -2975,8 +3004,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) } switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_65: - case RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_70: + case RTL_GIGA_MAC_VER_71: val8 = RTL_R8(tp, INT_CFG0_8125) & ~INT_CFG0_CLKREQEN; RTL_W8(tp, INT_CFG0_8125, val8); break; @@ -3696,12 +3725,12 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp) /* disable new tx descriptor format */ r8168_mac_ocp_modify(tp, 0xeb58, 0x0001, 0x0000); - if (tp->mac_version == RTL_GIGA_MAC_VER_65 || - tp->mac_version == RTL_GIGA_MAC_VER_66) + if (tp->mac_version == RTL_GIGA_MAC_VER_70 || + tp->mac_version == RTL_GIGA_MAC_VER_71) RTL_W8(tp, 0xD8, RTL_R8(tp, 0xD8) & ~0x02); - if (tp->mac_version == RTL_GIGA_MAC_VER_65 || - tp->mac_version == RTL_GIGA_MAC_VER_66) + if (tp->mac_version == RTL_GIGA_MAC_VER_70 || + tp->mac_version == RTL_GIGA_MAC_VER_71) r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0400); else if (tp->mac_version == RTL_GIGA_MAC_VER_63) r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0200); @@ -3719,8 +3748,8 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp) r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0030); r8168_mac_ocp_modify(tp, 0xe040, 0x1000, 0x0000); r8168_mac_ocp_modify(tp, 0xea1c, 0x0003, 0x0001); - if (tp->mac_version == RTL_GIGA_MAC_VER_65 || - tp->mac_version == RTL_GIGA_MAC_VER_66) + if (tp->mac_version == RTL_GIGA_MAC_VER_70 || + tp->mac_version == RTL_GIGA_MAC_VER_71) r8168_mac_ocp_modify(tp, 0xea1c, 0x0300, 0x0000); else r8168_mac_ocp_modify(tp, 0xea1c, 0x0004, 0x0000); @@ -3804,7 +3833,6 @@ static void rtl_hw_config(struct rtl8169_private *tp) [RTL_GIGA_MAC_VER_08] = rtl_hw_start_8102e_3, [RTL_GIGA_MAC_VER_09] = rtl_hw_start_8102e_2, [RTL_GIGA_MAC_VER_10] = NULL, - [RTL_GIGA_MAC_VER_11] = rtl_hw_start_8168b, [RTL_GIGA_MAC_VER_14] = rtl_hw_start_8401, [RTL_GIGA_MAC_VER_17] = rtl_hw_start_8168b, [RTL_GIGA_MAC_VER_18] = rtl_hw_start_8168cp_1, @@ -3840,8 +3868,10 @@ static void rtl_hw_config(struct rtl8169_private *tp) [RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2, [RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b, [RTL_GIGA_MAC_VER_64] = rtl_hw_start_8125d, - [RTL_GIGA_MAC_VER_65] = rtl_hw_start_8126a, - [RTL_GIGA_MAC_VER_66] = rtl_hw_start_8126a, + [RTL_GIGA_MAC_VER_65] = rtl_hw_start_8125d, + [RTL_GIGA_MAC_VER_66] = rtl_hw_start_8125d, + [RTL_GIGA_MAC_VER_70] = rtl_hw_start_8126a, + [RTL_GIGA_MAC_VER_71] = rtl_hw_start_8126a, }; if (hw_configs[tp->mac_version]) @@ -3858,12 +3888,14 @@ static void rtl_hw_start_8125(struct rtl8169_private *tp) switch (tp->mac_version) { case RTL_GIGA_MAC_VER_61: case RTL_GIGA_MAC_VER_64: + case RTL_GIGA_MAC_VER_65: + case RTL_GIGA_MAC_VER_66: for (i = 0xa00; i < 0xb00; i += 4) RTL_W32(tp, i, 0); break; case RTL_GIGA_MAC_VER_63: - case RTL_GIGA_MAC_VER_65: - case RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_70: + case RTL_GIGA_MAC_VER_71: for (i = 0xa00; i < 0xa80; i += 4) RTL_W32(tp, i, 0); RTL_W16(tp, INT_CFG1_8125, 0x0000); @@ -4095,7 +4127,7 @@ static void rtl8169_cleanup(struct rtl8169_private *tp) RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq); rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: rtl_enable_rxdvgate(tp); fsleep(2000); break; @@ -4252,7 +4284,7 @@ static unsigned int rtl_quirk_packet_padto(struct rtl8169_private *tp, switch (tp->mac_version) { case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: padto = max_t(unsigned int, padto, ETH_ZLEN); break; default: @@ -4680,12 +4712,6 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) if (status & LinkChg) phy_mac_interrupt(tp->phydev); - if (unlikely(status & RxFIFOOver && - tp->mac_version == RTL_GIGA_MAC_VER_11)) { - netif_stop_queue(tp->dev); - rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING); - } - rtl_irq_disable(tp); napi_schedule(&tp->napi); out: @@ -4723,8 +4749,6 @@ static void rtl_task(struct work_struct *work) reset: rtl_reset_work(tp); netif_wake_queue(tp->dev); - } else if (test_and_clear_bit(RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE, tp->wk.flags)) { - rtl_reset_work(tp); } } @@ -5103,9 +5127,6 @@ static void rtl_set_irq_mask(struct rtl8169_private *tp) if (tp->mac_version <= RTL_GIGA_MAC_VER_06) tp->irq_mask |= SYSErr | RxFIFOOver; - else if (tp->mac_version == RTL_GIGA_MAC_VER_11) - /* special workaround needed */ - tp->irq_mask |= RxFIFOOver; } static int rtl_alloc_irq(struct rtl8169_private *tp) @@ -5281,7 +5302,7 @@ static void rtl_hw_initialize(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48: rtl_hw_init_8168g(tp); break; - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: rtl_hw_init_8125(tp); break; default: @@ -5300,7 +5321,6 @@ static int rtl_jumbo_max(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: return JUMBO_7K; /* RTL8168b */ - case RTL_GIGA_MAC_VER_11: case RTL_GIGA_MAC_VER_17: return JUMBO_4K; /* RTL8168c */ @@ -5347,43 +5367,6 @@ static bool rtl_aspm_is_safe(struct rtl8169_private *tp) return false; } -static umode_t r8169_hwmon_is_visible(const void *drvdata, - enum hwmon_sensor_types type, - u32 attr, int channel) -{ - return 0444; -} - -static int r8169_hwmon_read(struct device *dev, enum hwmon_sensor_types type, - u32 attr, int channel, long *val) -{ - struct rtl8169_private *tp = dev_get_drvdata(dev); - int val_raw; - - val_raw = phy_read_paged(tp->phydev, 0xbd8, 0x12) & 0x3ff; - if (val_raw >= 512) - val_raw -= 1024; - - *val = 1000 * val_raw / 2; - - return 0; -} - -static const struct hwmon_ops r8169_hwmon_ops = { - .is_visible = r8169_hwmon_is_visible, - .read = r8169_hwmon_read, -}; - -static const struct hwmon_channel_info * const r8169_hwmon_info[] = { - HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), - NULL -}; - -static const struct hwmon_chip_info r8169_hwmon_chip_info = { - .ops = &r8169_hwmon_ops, - .info = r8169_hwmon_info, -}; - static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { struct rtl8169_private *tp; @@ -5563,12 +5546,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) return rc; - /* The temperature sensor is available from RTl8125B */ - if (IS_REACHABLE(CONFIG_HWMON) && tp->mac_version >= RTL_GIGA_MAC_VER_63) - /* ignore errors */ - devm_hwmon_device_register_with_info(&pdev->dev, "nic_temp", tp, - &r8169_hwmon_chip_info, - NULL); rc = register_netdev(dev); if (rc) return rc; diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index 5307c6ff4e25..cf95e579c65d 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -276,15 +276,6 @@ static void rtl8169sce_hw_phy_config(struct rtl8169_private *tp, rtl_writephy_batch(phydev, phy_reg_init); } -static void rtl8168bb_hw_phy_config(struct rtl8169_private *tp, - struct phy_device *phydev) -{ - phy_write(phydev, 0x1f, 0x0001); - phy_set_bits(phydev, 0x16, BIT(0)); - phy_write(phydev, 0x10, 0xf41b); - phy_write(phydev, 0x1f, 0x0000); -} - static void rtl8168bef_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev) { @@ -1111,6 +1102,28 @@ static void rtl8125d_hw_phy_config(struct rtl8169_private *tp, rtl8125_config_eee_phy(phydev); } +static void rtl8125bp_hw_phy_config(struct rtl8169_private *tp, + struct phy_device *phydev) +{ + r8169_apply_firmware(tp); + rtl8168g_enable_gphy_10m(phydev); + + r8168g_phy_param(phydev, 0x8010, 0x0800, 0x0000); + + phy_write(phydev, 0x1f, 0x0b87); + phy_write(phydev, 0x16, 0x8088); + phy_modify(phydev, 0x17, 0xff00, 0x9000); + phy_write(phydev, 0x16, 0x808f); + phy_modify(phydev, 0x17, 0xff00, 0x9000); + phy_write(phydev, 0x1f, 0x0000); + + r8168g_phy_param(phydev, 0x8174, 0x2000, 0x1800); + + rtl8125_legacy_force_mode(phydev); + rtl8168g_disable_aldps(phydev); + rtl8125_config_eee_phy(phydev); +} + static void rtl8126a_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev) { @@ -1136,7 +1149,6 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev, [RTL_GIGA_MAC_VER_08] = rtl8102e_hw_phy_config, [RTL_GIGA_MAC_VER_09] = rtl8102e_hw_phy_config, [RTL_GIGA_MAC_VER_10] = NULL, - [RTL_GIGA_MAC_VER_11] = rtl8168bb_hw_phy_config, [RTL_GIGA_MAC_VER_14] = rtl8401_hw_phy_config, [RTL_GIGA_MAC_VER_17] = rtl8168bef_hw_phy_config, [RTL_GIGA_MAC_VER_18] = rtl8168cp_1_hw_phy_config, @@ -1172,8 +1184,10 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev, [RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config, [RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config, [RTL_GIGA_MAC_VER_64] = rtl8125d_hw_phy_config, - [RTL_GIGA_MAC_VER_65] = rtl8126a_hw_phy_config, - [RTL_GIGA_MAC_VER_66] = rtl8126a_hw_phy_config, + [RTL_GIGA_MAC_VER_65] = rtl8125d_hw_phy_config, + [RTL_GIGA_MAC_VER_66] = rtl8125bp_hw_phy_config, + [RTL_GIGA_MAC_VER_70] = rtl8126a_hw_phy_config, + [RTL_GIGA_MAC_VER_71] = rtl8126a_hw_phy_config, }; if (phy_configs[ver]) diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h index dbc3f92eebc4..2bbfcad613ab 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase.h +++ b/drivers/net/ethernet/realtek/rtase/rtase.h @@ -13,6 +13,7 @@ #define RTASE_HW_VER_906X_7XA 0x00800000 #define RTASE_HW_VER_906X_7XC 0x04000000 #define RTASE_HW_VER_907XD_V1 0x04800000 +#define RTASE_HW_VER_907XD_VA 0x08000000 #define RTASE_RX_DMA_BURST_256 4 #define RTASE_TX_DMA_BURST_UNLIMITED 7 diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index de7f11232593..3bd11cb56294 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -1725,6 +1725,7 @@ static int rtase_get_settings(struct net_device *dev, cmd->base.speed = SPEED_5000; break; case RTASE_HW_VER_907XD_V1: + case RTASE_HW_VER_907XD_VA: cmd->base.speed = SPEED_10000; break; } @@ -1827,7 +1828,7 @@ static int rtase_alloc_msix(struct pci_dev *pdev, struct rtase_private *tp) for (i = 0; i < tp->int_nums; i++) { irq = pci_irq_vector(pdev, i); - if (!irq) { + if (irq < 0) { pci_disable_msix(pdev); return irq; } @@ -1993,6 +1994,7 @@ static int rtase_check_mac_version_valid(struct rtase_private *tp) case RTASE_HW_VER_906X_7XA: case RTASE_HW_VER_906X_7XC: case RTASE_HW_VER_907XD_V1: + case RTASE_HW_VER_907XD_VA: ret = 0; break; } @@ -2016,7 +2018,7 @@ static int rtase_init_board(struct pci_dev *pdev, struct net_device **dev_out, SET_NETDEV_DEV(dev, &pdev->dev); ret = pci_enable_device(pdev); - if (ret < 0) + if (ret) goto err_out_free_dev; /* make sure PCI base addr 1 is MMIO */ @@ -2032,7 +2034,7 @@ static int rtase_init_board(struct pci_dev *pdev, struct net_device **dev_out, } ret = pci_request_regions(pdev, KBUILD_MODNAME); - if (ret < 0) + if (ret) goto err_out_disable; ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); @@ -2108,7 +2110,7 @@ static int rtase_init_one(struct pci_dev *pdev, dev_dbg(&pdev->dev, "Automotive Switch Ethernet driver loaded\n"); ret = rtase_init_board(pdev, &dev, &ioaddr); - if (ret != 0) + if (ret) return ret; tp = netdev_priv(dev); @@ -2118,7 +2120,7 @@ static int rtase_init_one(struct pci_dev *pdev, /* identify chip attached to board */ ret = rtase_check_mac_version_valid(tp); - if (ret != 0) { + if (ret) { dev_err(&pdev->dev, "unknown chip version: 0x%08x, contact rtase maintainers (see MAINTAINERS file)\n", tp->hw_ver); @@ -2129,7 +2131,7 @@ static int rtase_init_one(struct pci_dev *pdev, rtase_init_hardware(tp); ret = rtase_alloc_interrupt(pdev, tp); - if (ret < 0) { + if (ret) { dev_err(&pdev->dev, "unable to alloc MSIX/MSI\n"); goto err_out_del_napi; } @@ -2174,7 +2176,7 @@ static int rtase_init_one(struct pci_dev *pdev, netif_carrier_off(dev); ret = register_netdev(dev); - if (ret != 0) + if (ret) goto err_out_free_dma; netdev_dbg(dev, "%pM, IRQ %d\n", dev->dev_addr, dev->irq); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ac0f093f647a..c9f4976a3527 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2763,6 +2763,7 @@ static const struct ravb_hw_info ravb_rzv2m_hw_info = { .net_features = NETIF_F_RXCSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .tx_max_frame_size = SZ_2K, .rx_max_frame_size = SZ_2K, .rx_buffer_size = SZ_2K + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), @@ -3216,10 +3217,15 @@ static int ravb_suspend(struct device *dev) netif_device_detach(ndev); - if (priv->wol_enabled) - return ravb_wol_setup(ndev); + rtnl_lock(); + if (priv->wol_enabled) { + ret = ravb_wol_setup(ndev); + rtnl_unlock(); + return ret; + } ret = ravb_close(ndev); + rtnl_unlock(); if (ret) return ret; @@ -3244,19 +3250,20 @@ static int ravb_resume(struct device *dev) if (!netif_running(ndev)) return 0; + rtnl_lock(); /* If WoL is enabled restore the interface. */ - if (priv->wol_enabled) { + if (priv->wol_enabled) ret = ravb_wol_restore(ndev); - if (ret) - return ret; - } else { + else ret = pm_runtime_force_resume(dev); - if (ret) - return ret; + if (ret) { + rtnl_unlock(); + return ret; } /* Reopening the interface will restore the device to the working state. */ ret = ravb_open(ndev); + rtnl_unlock(); if (ret < 0) goto out_rpm_put; diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index dbbbf024e7ab..84d09a8973b7 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -111,25 +111,35 @@ static void rswitch_top_init(struct rswitch_private *priv) /* Forwarding engine block (MFWD) */ static void rswitch_fwd_init(struct rswitch_private *priv) { + u32 all_ports_mask = GENMASK(RSWITCH_NUM_AGENTS - 1, 0); unsigned int i; - /* For ETHA */ - for (i = 0; i < RSWITCH_NUM_PORTS; i++) { - iowrite32(FWPC0_DEFAULT, priv->addr + FWPC0(i)); + /* Start with empty configuration */ + for (i = 0; i < RSWITCH_NUM_AGENTS; i++) { + /* Disable all port features */ + iowrite32(0, priv->addr + FWPC0(i)); + /* Disallow L3 forwarding and direct descriptor forwarding */ + iowrite32(FIELD_PREP(FWCP1_LTHFW, all_ports_mask), + priv->addr + FWPC1(i)); + /* Disallow L2 forwarding */ + iowrite32(FIELD_PREP(FWCP2_LTWFW, all_ports_mask), + priv->addr + FWPC2(i)); + /* Disallow port based forwarding */ iowrite32(0, priv->addr + FWPBFC(i)); } - for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + /* For enabled ETHA ports, setup port based forwarding */ + rswitch_for_each_enabled_port(priv, i) { + /* Port based forwarding from port i to GWCA port */ + rswitch_modify(priv->addr, FWPBFC(i), FWPBFC_PBDV, + FIELD_PREP(FWPBFC_PBDV, BIT(priv->gwca.index))); + /* Within GWCA port, forward to Rx queue for port i */ iowrite32(priv->rdev[i]->rx_queue->index, priv->addr + FWPBFCSDC(GWCA_INDEX, i)); - iowrite32(BIT(priv->gwca.index), priv->addr + FWPBFC(i)); } - /* For GWCA */ - iowrite32(FWPC0_DEFAULT, priv->addr + FWPC0(priv->gwca.index)); - iowrite32(FWPC1_DDE, priv->addr + FWPC1(priv->gwca.index)); - iowrite32(0, priv->addr + FWPBFC(priv->gwca.index)); - iowrite32(GENMASK(RSWITCH_NUM_PORTS - 1, 0), priv->addr + FWPBFC(priv->gwca.index)); + /* For GWCA port, allow direct descriptor forwarding */ + rswitch_modify(priv->addr, FWPC1(priv->gwca.index), FWPC1_DDE, FWPC1_DDE); } /* Gateway CPU agent block (GWCA) */ @@ -547,7 +557,6 @@ static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv) desc = &gq->ts_ring[gq->ring_size]; desc->desc.die_dt = DT_LINKFIX; rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); - INIT_LIST_HEAD(&priv->gwca.ts_info_list); return 0; } @@ -1003,9 +1012,10 @@ static int rswitch_gwca_request_irqs(struct rswitch_private *priv) static void rswitch_ts(struct rswitch_private *priv) { struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; - struct rswitch_gwca_ts_info *ts_info, *ts_info2; struct skb_shared_hwtstamps shhwtstamps; struct rswitch_ts_desc *desc; + struct rswitch_device *rdev; + struct sk_buff *ts_skb; struct timespec64 ts; unsigned int num; u32 tag, port; @@ -1015,23 +1025,28 @@ static void rswitch_ts(struct rswitch_private *priv) dma_rmb(); port = TS_DESC_DPN(__le32_to_cpu(desc->desc.dptrl)); + if (unlikely(port >= RSWITCH_NUM_PORTS)) + goto next; + rdev = priv->rdev[port]; + tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); + if (unlikely(tag >= TS_TAGS_PER_PORT)) + goto next; + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + smp_mb(); /* order rdev->ts_skb[] read before bitmap update */ + clear_bit(tag, rdev->ts_skb_used); - list_for_each_entry_safe(ts_info, ts_info2, &priv->gwca.ts_info_list, list) { - if (!(ts_info->port == port && ts_info->tag == tag)) - continue; + if (unlikely(!ts_skb)) + goto next; - memset(&shhwtstamps, 0, sizeof(shhwtstamps)); - ts.tv_sec = __le32_to_cpu(desc->ts_sec); - ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); - shhwtstamps.hwtstamp = timespec64_to_ktime(ts); - skb_tstamp_tx(ts_info->skb, &shhwtstamps); - dev_consume_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); - break; - } + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + ts.tv_sec = __le32_to_cpu(desc->ts_sec); + ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); + shhwtstamps.hwtstamp = timespec64_to_ktime(ts); + skb_tstamp_tx(ts_skb, &shhwtstamps); + dev_consume_skb_irq(ts_skb); +next: gq->cur = rswitch_next_queue_index(gq, true, 1); desc = &gq->ts_ring[gq->cur]; } @@ -1154,9 +1169,9 @@ static void rswitch_rmac_setting(struct rswitch_etha *etha, const u8 *mac) static void rswitch_etha_enable_mii(struct rswitch_etha *etha) { - rswitch_modify(etha->addr, MPIC, MPIC_PSMCS_MASK | MPIC_PSMHT_MASK, - MPIC_PSMCS(etha->psmcs) | MPIC_PSMHT(0x06)); - rswitch_modify(etha->addr, MPSM, 0, MPSM_MFF_C45); + rswitch_modify(etha->addr, MPIC, MPIC_PSMCS | MPIC_PSMHT, + FIELD_PREP(MPIC_PSMCS, etha->psmcs) | + FIELD_PREP(MPIC_PSMHT, 0x06)); } static int rswitch_etha_hw_init(struct rswitch_etha *etha, const u8 *mac) @@ -1185,42 +1200,29 @@ static int rswitch_etha_hw_init(struct rswitch_etha *etha, const u8 *mac) return rswitch_etha_change_mode(etha, EAMC_OPC_OPERATION); } -static int rswitch_etha_set_access(struct rswitch_etha *etha, bool read, - int phyad, int devad, int regad, int data) +static int rswitch_etha_mpsm_op(struct rswitch_etha *etha, bool read, + unsigned int mmf, unsigned int pda, + unsigned int pra, unsigned int pop, + unsigned int prd) { - int pop = read ? MDIO_READ_C45 : MDIO_WRITE_C45; u32 val; int ret; - if (devad == 0xffffffff) - return -ENODEV; + val = MPSM_PSME | + FIELD_PREP(MPSM_MFF, mmf) | + FIELD_PREP(MPSM_PDA, pda) | + FIELD_PREP(MPSM_PRA, pra) | + FIELD_PREP(MPSM_POP, pop) | + FIELD_PREP(MPSM_PRD, prd); + iowrite32(val, etha->addr + MPSM); - writel(MMIS1_CLEAR_FLAGS, etha->addr + MMIS1); - - val = MPSM_PSME | MPSM_MFF_C45; - iowrite32((regad << 16) | (devad << 8) | (phyad << 3) | val, etha->addr + MPSM); - - ret = rswitch_reg_wait(etha->addr, MMIS1, MMIS1_PAACS, MMIS1_PAACS); + ret = rswitch_reg_wait(etha->addr, MPSM, MPSM_PSME, 0); if (ret) return ret; - rswitch_modify(etha->addr, MMIS1, MMIS1_PAACS, MMIS1_PAACS); - if (read) { - writel((pop << 13) | (devad << 8) | (phyad << 3) | val, etha->addr + MPSM); - - ret = rswitch_reg_wait(etha->addr, MMIS1, MMIS1_PRACS, MMIS1_PRACS); - if (ret) - return ret; - - ret = (ioread32(etha->addr + MPSM) & MPSM_PRD_MASK) >> 16; - - rswitch_modify(etha->addr, MMIS1, MMIS1_PRACS, MMIS1_PRACS); - } else { - iowrite32((data << 16) | (pop << 13) | (devad << 8) | (phyad << 3) | val, - etha->addr + MPSM); - - ret = rswitch_reg_wait(etha->addr, MMIS1, MMIS1_PWACS, MMIS1_PWACS); + val = ioread32(etha->addr + MPSM); + ret = FIELD_GET(MPSM_PRD, val); } return ret; @@ -1230,16 +1232,47 @@ static int rswitch_etha_mii_read_c45(struct mii_bus *bus, int addr, int devad, int regad) { struct rswitch_etha *etha = bus->priv; + int ret; - return rswitch_etha_set_access(etha, true, addr, devad, regad, 0); + ret = rswitch_etha_mpsm_op(etha, false, MPSM_MMF_C45, addr, devad, + MPSM_POP_ADDRESS, regad); + if (ret) + return ret; + + return rswitch_etha_mpsm_op(etha, true, MPSM_MMF_C45, addr, devad, + MPSM_POP_READ_C45, 0); } static int rswitch_etha_mii_write_c45(struct mii_bus *bus, int addr, int devad, int regad, u16 val) { struct rswitch_etha *etha = bus->priv; + int ret; - return rswitch_etha_set_access(etha, false, addr, devad, regad, val); + ret = rswitch_etha_mpsm_op(etha, false, MPSM_MMF_C45, addr, devad, + MPSM_POP_ADDRESS, regad); + if (ret) + return ret; + + return rswitch_etha_mpsm_op(etha, false, MPSM_MMF_C45, addr, devad, + MPSM_POP_WRITE, val); +} + +static int rswitch_etha_mii_read_c22(struct mii_bus *bus, int phyad, int regad) +{ + struct rswitch_etha *etha = bus->priv; + + return rswitch_etha_mpsm_op(etha, true, MPSM_MMF_C22, phyad, regad, + MPSM_POP_READ_C22, 0); +} + +static int rswitch_etha_mii_write_c22(struct mii_bus *bus, int phyad, + int regad, u16 val) +{ + struct rswitch_etha *etha = bus->priv; + + return rswitch_etha_mpsm_op(etha, false, MPSM_MMF_C22, phyad, regad, + MPSM_POP_WRITE, val); } /* Call of_node_put(port) after done */ @@ -1324,6 +1357,8 @@ static int rswitch_mii_register(struct rswitch_device *rdev) mii_bus->priv = rdev->etha; mii_bus->read_c45 = rswitch_etha_mii_read_c45; mii_bus->write_c45 = rswitch_etha_mii_write_c45; + mii_bus->read = rswitch_etha_mii_read_c22; + mii_bus->write = rswitch_etha_mii_write_c22; mii_bus->parent = &rdev->priv->pdev->dev; mdio_np = of_get_child_by_name(rdev->np_port, "mdio"); @@ -1544,7 +1579,7 @@ static void rswitch_ether_port_deinit_all(struct rswitch_private *priv) { unsigned int i; - for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + rswitch_for_each_enabled_port(priv, i) { phy_exit(priv->rdev[i]->serdes); rswitch_ether_port_deinit_one(priv->rdev[i]); } @@ -1576,8 +1611,9 @@ static int rswitch_open(struct net_device *ndev) static int rswitch_stop(struct net_device *ndev) { struct rswitch_device *rdev = netdev_priv(ndev); - struct rswitch_gwca_ts_info *ts_info, *ts_info2; + struct sk_buff *ts_skb; unsigned long flags; + unsigned int tag; netif_tx_stop_all_queues(ndev); @@ -1594,12 +1630,13 @@ static int rswitch_stop(struct net_device *ndev) if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID); - list_for_each_entry_safe(ts_info, ts_info2, &rdev->priv->gwca.ts_info_list, list) { - if (ts_info->port != rdev->port) - continue; - dev_kfree_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); + for (tag = find_first_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + tag < TS_TAGS_PER_PORT; + tag = find_next_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT, tag + 1)) { + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + clear_bit(tag, rdev->ts_skb_used); + if (ts_skb) + dev_kfree_skb(ts_skb); } return 0; @@ -1612,20 +1649,17 @@ static bool rswitch_ext_desc_set_info1(struct rswitch_device *rdev, desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) | INFO1_IPV(GWCA_IPV_NUM) | INFO1_FMT); if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { - struct rswitch_gwca_ts_info *ts_info; + unsigned int tag; - ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC); - if (!ts_info) + tag = find_first_zero_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + if (tag == TS_TAGS_PER_PORT) return false; + smp_mb(); /* order bitmap read before rdev->ts_skb[] write */ + rdev->ts_skb[tag] = skb_get(skb); + set_bit(tag, rdev->ts_skb_used); skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - rdev->ts_tag++; - desc->info1 |= cpu_to_le64(INFO1_TSUN(rdev->ts_tag) | INFO1_TXC); - - ts_info->skb = skb_get(skb); - ts_info->port = rdev->port; - ts_info->tag = rdev->ts_tag; - list_add_tail(&ts_info->list, &rdev->priv->gwca.ts_info_list); + desc->info1 |= cpu_to_le64(INFO1_TSUN(tag) | INFO1_TXC); skb_tx_timestamp(skb); } @@ -1920,9 +1954,6 @@ static int rswitch_device_alloc(struct rswitch_private *priv, unsigned int index if (err < 0) goto out_get_params; - if (rdev->priv->gwca.speed < rdev->etha->speed) - rdev->priv->gwca.speed = rdev->etha->speed; - err = rswitch_rxdmac_alloc(ndev); if (err < 0) goto out_rxdmac; diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index e020800dcc57..532192cbca4b 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -12,6 +12,7 @@ #define RSWITCH_MAX_NUM_QUEUES 128 +#define RSWITCH_NUM_AGENTS 5 #define RSWITCH_NUM_PORTS 3 #define rswitch_for_each_enabled_port(priv, i) \ for (i = 0; i < RSWITCH_NUM_PORTS; i++) \ @@ -731,28 +732,21 @@ enum rswitch_etha_mode { #define MPIC_LSC_100M 1 #define MPIC_LSC_1G 2 #define MPIC_LSC_2_5G 3 - -#define MDIO_READ_C45 0x03 -#define MDIO_WRITE_C45 0x01 +#define MPIC_PSMCS GENMASK(22, 16) +#define MPIC_PSMHT GENMASK(26, 24) #define MPSM_PSME BIT(0) -#define MPSM_MFF_C45 BIT(2) -#define MPSM_PRD_SHIFT 16 -#define MPSM_PRD_MASK GENMASK(31, MPSM_PRD_SHIFT) - -/* Completion flags */ -#define MMIS1_PAACS BIT(2) /* Address */ -#define MMIS1_PWACS BIT(1) /* Write */ -#define MMIS1_PRACS BIT(0) /* Read */ -#define MMIS1_CLEAR_FLAGS 0xf - -#define MPIC_PSMCS_SHIFT 16 -#define MPIC_PSMCS_MASK GENMASK(22, MPIC_PSMCS_SHIFT) -#define MPIC_PSMCS(val) ((val) << MPIC_PSMCS_SHIFT) - -#define MPIC_PSMHT_SHIFT 24 -#define MPIC_PSMHT_MASK GENMASK(26, MPIC_PSMHT_SHIFT) -#define MPIC_PSMHT(val) ((val) << MPIC_PSMHT_SHIFT) +#define MPSM_MFF BIT(2) +#define MPSM_MMF_C22 0 +#define MPSM_MMF_C45 1 +#define MPSM_PDA GENMASK(7, 3) +#define MPSM_PRA GENMASK(12, 8) +#define MPSM_POP GENMASK(14, 13) +#define MPSM_POP_ADDRESS 0 +#define MPSM_POP_WRITE 1 +#define MPSM_POP_READ_C22 2 +#define MPSM_POP_READ_C45 3 +#define MPSM_PRD GENMASK(31, 16) #define MLVC_PLV BIT(16) @@ -806,6 +800,7 @@ enum rswitch_gwca_mode { #define CABPPFLC_INIT_VALUE 0x00800080 /* MFWD */ +#define FWPC0(i) (FWPC00 + (i) * 0x10) #define FWPC0_LTHTA BIT(0) #define FWPC0_IP4UE BIT(3) #define FWPC0_IP4TE BIT(4) @@ -819,15 +814,15 @@ enum rswitch_gwca_mode { #define FWPC0_MACHMA BIT(27) #define FWPC0_VLANSA BIT(28) -#define FWPC0(i) (FWPC00 + (i) * 0x10) -#define FWPC0_DEFAULT (FWPC0_LTHTA | FWPC0_IP4UE | FWPC0_IP4TE | \ - FWPC0_IP4OE | FWPC0_L2SE | FWPC0_IP4EA | \ - FWPC0_IPDSA | FWPC0_IPHLA | FWPC0_MACSDA | \ - FWPC0_MACHLA | FWPC0_MACHMA | FWPC0_VLANSA) #define FWPC1(i) (FWPC10 + (i) * 0x10) +#define FWCP1_LTHFW GENMASK(16 + (RSWITCH_NUM_AGENTS - 1), 16) #define FWPC1_DDE BIT(0) -#define FWPBFC(i) (FWPBFC0 + (i) * 0x10) +#define FWPC2(i) (FWPC20 + (i) * 0x10) +#define FWCP2_LTWFW GENMASK(16 + (RSWITCH_NUM_AGENTS - 1), 16) + +#define FWPBFC(i) (FWPBFC0 + (i) * 0x10) +#define FWPBFC_PBDV GENMASK(RSWITCH_NUM_AGENTS - 1, 0) #define FWPBFCSDC(j, i) (FWPBFCSDC00 + (i) * 0x10 + (j) * 0x04) @@ -972,14 +967,6 @@ struct rswitch_gwca_queue { }; }; -struct rswitch_gwca_ts_info { - struct sk_buff *skb; - struct list_head list; - - int port; - u8 tag; -}; - #define RSWITCH_NUM_IRQ_REGS (RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32)) struct rswitch_gwca { unsigned int index; @@ -989,14 +976,13 @@ struct rswitch_gwca { struct rswitch_gwca_queue *queues; int num_queues; struct rswitch_gwca_queue ts_queue; - struct list_head ts_info_list; DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES); u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS]; u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS]; - int speed; }; #define NUM_QUEUES_PER_NDEV 2 +#define TS_TAGS_PER_PORT 256 struct rswitch_device { struct rswitch_private *priv; struct net_device *ndev; @@ -1004,7 +990,8 @@ struct rswitch_device { void __iomem *addr; struct rswitch_gwca_queue *tx_queue; struct rswitch_gwca_queue *rx_queue; - u8 ts_tag; + struct sk_buff *ts_skb[TS_TAGS_PER_PORT]; + DECLARE_BITMAP(ts_skb_used, TS_TAGS_PER_PORT); bool disabled; int port; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 8887b8921009..5fc8027c92c7 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3494,10 +3494,12 @@ static int sh_eth_suspend(struct device *dev) netif_device_detach(ndev); + rtnl_lock(); if (mdp->wol_enabled) ret = sh_eth_wol_setup(ndev); else ret = sh_eth_close(ndev); + rtnl_unlock(); return ret; } @@ -3511,10 +3513,12 @@ static int sh_eth_resume(struct device *dev) if (!netif_running(ndev)) return 0; + rtnl_lock(); if (mdp->wol_enabled) ret = sh_eth_wol_restore(ndev); else ret = sh_eth_open(ndev); + rtnl_unlock(); if (ret < 0) return ret; diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h index 4cc7b501135f..ef374a8e05c3 100644 --- a/drivers/net/ethernet/sfc/io.h +++ b/drivers/net/ethernet/sfc/io.h @@ -217,28 +217,4 @@ _efx_writed_page(struct efx_nic *efx, const efx_dword_t *value, (reg) != 0xa1c), \ page) -/* Write TIMER_COMMAND. This is a page-mapped 32-bit CSR, but a bug - * in the BIU means that writes to TIMER_COMMAND[0] invalidate the - * collector register. - */ -static inline void _efx_writed_page_locked(struct efx_nic *efx, - const efx_dword_t *value, - unsigned int reg, - unsigned int page) -{ - unsigned long flags __attribute__ ((unused)); - - if (page == 0) { - spin_lock_irqsave(&efx->biu_lock, flags); - efx_writed(efx, value, efx_paged_reg(efx, page, reg)); - spin_unlock_irqrestore(&efx->biu_lock, flags); - } else { - efx_writed(efx, value, efx_paged_reg(efx, page, reg)); - } -} -#define efx_writed_page_locked(efx, value, reg, page) \ - _efx_writed_page_locked(efx, value, \ - reg + BUILD_BUG_ON_ZERO((reg) != 0x420), \ - page) - #endif /* EFX_IO_H */ diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 620ba6ef3514..f70a7b7d6345 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -831,6 +831,7 @@ struct efx_arfs_rule { /** * struct efx_async_filter_insertion - Request to asynchronously insert a filter * @net_dev: Reference to the netdevice + * @net_dev_tracker: reference tracker entry for @net_dev * @spec: The filter to insert * @work: Workitem for this request * @rxq_index: Identifies the channel for which this request was made @@ -838,6 +839,7 @@ struct efx_arfs_rule { */ struct efx_async_filter_insertion { struct net_device *net_dev; + netdevice_tracker net_dev_tracker; struct efx_filter_spec spec; struct work_struct work; u16 rxq_index; diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index ab358fe13e1d..4cc83203e188 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -897,7 +897,7 @@ static void efx_filter_rfs_work(struct work_struct *data) /* Release references */ clear_bit(slot_idx, &efx->rps_slot_map); - dev_put(req->net_dev); + netdev_put(req->net_dev, &req->net_dev_tracker); } int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, @@ -989,7 +989,8 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, } /* Queue the request */ - dev_hold(req->net_dev = net_dev); + req->net_dev = net_dev; + netdev_hold(req->net_dev, &req->net_dev_tracker, GFP_ATOMIC); INIT_WORK(&req->work, efx_filter_rfs_work); req->rxq_index = rxq_index; req->flow_id = flow_id; diff --git a/drivers/net/ethernet/sfc/siena/net_driver.h b/drivers/net/ethernet/sfc/siena/net_driver.h index 9785eff10607..2be3bad3c993 100644 --- a/drivers/net/ethernet/sfc/siena/net_driver.h +++ b/drivers/net/ethernet/sfc/siena/net_driver.h @@ -753,6 +753,7 @@ struct efx_arfs_rule { /** * struct efx_async_filter_insertion - Request to asynchronously insert a filter * @net_dev: Reference to the netdevice + * @net_dev_tracker: reference tracker entry for @net_dev * @spec: The filter to insert * @work: Workitem for this request * @rxq_index: Identifies the channel for which this request was made @@ -760,6 +761,7 @@ struct efx_arfs_rule { */ struct efx_async_filter_insertion { struct net_device *net_dev; + netdevice_tracker net_dev_tracker; struct efx_filter_spec spec; struct work_struct work; u16 rxq_index; diff --git a/drivers/net/ethernet/sfc/siena/rx_common.c b/drivers/net/ethernet/sfc/siena/rx_common.c index 082e35c6caaa..2839d0e0a9c1 100644 --- a/drivers/net/ethernet/sfc/siena/rx_common.c +++ b/drivers/net/ethernet/sfc/siena/rx_common.c @@ -888,7 +888,7 @@ static void efx_filter_rfs_work(struct work_struct *data) /* Release references */ clear_bit(slot_idx, &efx->rps_slot_map); - dev_put(req->net_dev); + netdev_put(req->net_dev, &req->net_dev_tracker); } int efx_siena_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, @@ -980,7 +980,8 @@ int efx_siena_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, } /* Queue the request */ - dev_hold(req->net_dev = net_dev); + req->net_dev = net_dev; + netdev_hold(req->net_dev, &req->net_dev_tracker, GFP_ATOMIC); INIT_WORK(&req->work, efx_filter_rfs_work); req->rxq_index = rxq_index; req->flow_id = flow_id; diff --git a/drivers/net/ethernet/sfc/tc_conntrack.c b/drivers/net/ethernet/sfc/tc_conntrack.c index d90206f27161..c0603f54cec3 100644 --- a/drivers/net/ethernet/sfc/tc_conntrack.c +++ b/drivers/net/ethernet/sfc/tc_conntrack.c @@ -16,7 +16,7 @@ static int efx_tc_flow_block(enum tc_setup_type type, void *type_data, void *cb_priv); static const struct rhashtable_params efx_tc_ct_zone_ht_params = { - .key_len = offsetof(struct efx_tc_ct_zone, linkage), + .key_len = sizeof_field(struct efx_tc_ct_zone, zone), .key_offset = 0, .head_offset = offsetof(struct efx_tc_ct_zone, linkage), }; diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 6658536a4e17..4cc85a36a1ab 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -154,6 +154,18 @@ config DWMAC_RZN1 the stmmac device driver. This support can make use of a custom MII converter PCS device. +config DWMAC_S32 + tristate "NXP S32G/S32R GMAC support" + default ARCH_S32 + depends on OF && (ARCH_S32 || COMPILE_TEST) + help + Support for ethernet controller on NXP S32CC SOCs. + + This selects NXP SoC glue layer support for the stmmac + device driver. This driver is used for the S32CC series + SOCs GMAC ethernet controller, ie. S32G2xx, S32G3xx and + S32R45. + config DWMAC_SOCFPGA tristate "SOCFPGA dwmac support" default ARCH_INTEL_SOCFPGA diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index 2389fd261344..b26f0e79c2b3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_DWMAC_MESON) += dwmac-meson.o dwmac-meson8b.o obj-$(CONFIG_DWMAC_QCOM_ETHQOS) += dwmac-qcom-ethqos.o obj-$(CONFIG_DWMAC_ROCKCHIP) += dwmac-rk.o obj-$(CONFIG_DWMAC_RZN1) += dwmac-rzn1.o +obj-$(CONFIG_DWMAC_S32) += dwmac-s32.o obj-$(CONFIG_DWMAC_SOCFPGA) += dwmac-altr-socfpga.o obj-$(CONFIG_DWMAC_STARFIVE) += dwmac-starfive.o obj-$(CONFIG_DWMAC_STI) += dwmac-sti.o diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 1367fa5c9b8e..e25db747a81a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -257,6 +257,8 @@ struct stmmac_safety_stats { #define CSR_F_150M 150000000 #define CSR_F_250M 250000000 #define CSR_F_300M 300000000 +#define CSR_F_500M 500000000 +#define CSR_F_800M 800000000 #define MAC_CSR_H_FRQ_MASK 0x20 @@ -543,18 +545,8 @@ struct dma_features { #define STMMAC_VLAN_INSERT 0x2 #define STMMAC_VLAN_REPLACE 0x3 -extern const struct stmmac_desc_ops enh_desc_ops; -extern const struct stmmac_desc_ops ndesc_ops; - struct mac_device_info; -extern const struct stmmac_hwtimestamp stmmac_ptp; -extern const struct stmmac_hwtimestamp dwmac1000_ptp; -extern const struct stmmac_mode_ops dwmac4_ring_mode_ops; - -extern const struct ptp_clock_info stmmac_ptp_clock_ops; -extern const struct ptp_clock_info dwmac1000_ptp_clock_ops; - struct mac_link { u32 caps; u32 speed_mask; @@ -641,8 +633,4 @@ void stmmac_dwmac4_set_mac(void __iomem *ioaddr, bool enable); void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr); -extern const struct stmmac_mode_ops ring_mode_ops; -extern const struct stmmac_mode_ops chain_mode_ops; -extern const struct stmmac_desc_ops dwmac4_desc_ops; - #endif /* __COMMON_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 83290e707df5..bd4eb187f8c6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -181,24 +181,19 @@ static void dwc_qos_remove(struct platform_device *pdev) static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mode) { struct tegra_eqos *eqos = priv; - unsigned long rate = 125000000; bool needs_calibration = false; + long rate = 125000000; u32 value; int err; switch (speed) { case SPEED_1000: - needs_calibration = true; - rate = 125000000; - break; - case SPEED_100: needs_calibration = true; - rate = 25000000; - break; + fallthrough; case SPEED_10: - rate = 2500000; + rate = rgmii_clock(speed); break; default: diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 641f3cd019a3..20d3a202bb8d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -36,6 +36,8 @@ #define MX93_GPR_ENET_QOS_INTF_SEL_RMII (0x4 << 1) #define MX93_GPR_ENET_QOS_INTF_SEL_RGMII (0x1 << 1) #define MX93_GPR_ENET_QOS_CLK_GEN_EN (0x1 << 0) +#define MX93_GPR_ENET_QOS_CLK_SEL_MASK BIT_MASK(0) +#define MX93_GPR_CLK_SEL_OFFSET (4) #define DMA_BUS_MODE 0x00001000 #define DMA_BUS_MODE_SFT_RESET (0x1 << 0) @@ -108,13 +110,21 @@ imx8dxl_set_intf_mode(struct plat_stmmacenet_data *plat_dat) static int imx93_set_intf_mode(struct plat_stmmacenet_data *plat_dat) { struct imx_priv_data *dwmac = plat_dat->bsp_priv; - int val; + int val, ret; switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_MII: val = MX93_GPR_ENET_QOS_INTF_SEL_MII; break; case PHY_INTERFACE_MODE_RMII: + if (dwmac->rmii_refclk_ext) { + ret = regmap_clear_bits(dwmac->intf_regmap, + dwmac->intf_reg_off + + MX93_GPR_CLK_SEL_OFFSET, + MX93_GPR_ENET_QOS_CLK_SEL_MASK); + if (ret) + return ret; + } val = MX93_GPR_ENET_QOS_INTF_SEL_RMII; break; case PHY_INTERFACE_MODE_RGMII: @@ -186,7 +196,7 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod { struct plat_stmmacenet_data *plat_dat; struct imx_priv_data *dwmac = priv; - unsigned long rate; + long rate; int err; plat_dat = dwmac->plat_dat; @@ -196,17 +206,8 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod (plat_dat->mac_interface == PHY_INTERFACE_MODE_MII)) return; - switch (speed) { - case SPEED_1000: - rate = 125000000; - break; - case SPEED_100: - rate = 25000000; - break; - case SPEED_10: - rate = 2500000; - break; - default: + rate = rgmii_clock(speed); + if (rate < 0) { dev_err(dwmac->dev, "invalid speed %u\n", speed); return; } @@ -301,15 +302,11 @@ imx_dwmac_parse_dt(struct imx_priv_data *dwmac, struct device *dev) * is required by i.MX8MP, i.MX93. * is optinoal for i.MX8DXL. */ - dwmac->intf_regmap = syscon_regmap_lookup_by_phandle(np, "intf_mode"); + dwmac->intf_regmap = + syscon_regmap_lookup_by_phandle_args(np, "intf_mode", 1, + &dwmac->intf_reg_off); if (IS_ERR(dwmac->intf_regmap)) return PTR_ERR(dwmac->intf_regmap); - - err = of_property_read_u32_index(np, "intf_mode", 1, &dwmac->intf_reg_off); - if (err) { - dev_err(dev, "Can't get intf mode reg offset (%d)\n", err); - return err; - } } return err; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index d94f0a150e93..ddee6154d40b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -31,27 +31,13 @@ struct intel_dwmac_data { static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct intel_dwmac *dwmac = priv; - unsigned long rate; + long rate; int ret; - rate = clk_get_rate(dwmac->tx_clk); - - switch (speed) { - case SPEED_1000: - rate = 125000000; - break; - - case SPEED_100: - rate = 25000000; - break; - - case SPEED_10: - rate = 2500000; - break; - - default: + rate = rgmii_clock(speed); + if (rate < 0) { dev_err(dwmac->dev, "Invalid speed\n"); - break; + return; } ret = clk_set_rate(dwmac->tx_clk, rate); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 901a3c1959fa..2a5b38723635 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -777,7 +777,7 @@ static void ethqos_ptp_clk_freq_config(struct stmmac_priv *priv) netdev_err(priv->dev, "Failed to max out clk_ptp_ref: %d\n", err); plat_dat->clk_ptp_rate = clk_get_rate(plat_dat->clk_ptp_ref); - netdev_dbg(priv->dev, "PTP rate %d\n", plat_dat->clk_ptp_rate); + netdev_dbg(priv->dev, "PTP rate %lu\n", plat_dat->clk_ptp_rate); } static int qcom_ethqos_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 8cb374668b74..a4dc89e23a68 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1079,20 +1079,11 @@ static void rk3568_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed) { struct clk *clk_mac_speed = bsp_priv->clks[RK_CLK_MAC_SPEED].clk; struct device *dev = &bsp_priv->pdev->dev; - unsigned long rate; + long rate; int ret; - switch (speed) { - case 10: - rate = 2500000; - break; - case 100: - rate = 25000000; - break; - case 1000: - rate = 125000000; - break; - default: + rate = rgmii_clock(speed); + if (rate < 0) { dev_err(dev, "unknown speed value for GMAC speed=%d", speed); return; } @@ -1540,20 +1531,11 @@ static void rv1126_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) { struct clk *clk_mac_speed = bsp_priv->clks[RK_CLK_MAC_SPEED].clk; struct device *dev = &bsp_priv->pdev->dev; - unsigned long rate; + long rate; int ret; - switch (speed) { - case 10: - rate = 2500000; - break; - case 100: - rate = 25000000; - break; - case 1000: - rate = 125000000; - break; - default: + rate = rgmii_clock(speed); + if (rate < 0) { dev_err(dev, "unknown speed value for RGMII speed=%d", speed); return; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c new file mode 100644 index 000000000000..9cc0e5817416 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NXP S32G/R GMAC glue layer + * + * Copyright 2019-2024 NXP + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "stmmac_platform.h" + +#define GMAC_INTF_RATE_125M 125000000 /* 125MHz */ + +/* SoC PHY interface control register */ +#define PHY_INTF_SEL_MII 0x00 +#define PHY_INTF_SEL_SGMII 0x01 +#define PHY_INTF_SEL_RGMII 0x02 +#define PHY_INTF_SEL_RMII 0x08 + +struct s32_priv_data { + void __iomem *ioaddr; + void __iomem *ctrl_sts; + struct device *dev; + phy_interface_t *intf_mode; + struct clk *tx_clk; + struct clk *rx_clk; +}; + +static int s32_gmac_write_phy_intf_select(struct s32_priv_data *gmac) +{ + writel(PHY_INTF_SEL_RGMII, gmac->ctrl_sts); + + dev_dbg(gmac->dev, "PHY mode set to %s\n", phy_modes(*gmac->intf_mode)); + + return 0; +} + +static int s32_gmac_init(struct platform_device *pdev, void *priv) +{ + struct s32_priv_data *gmac = priv; + int ret; + + /* Set initial TX interface clock */ + ret = clk_prepare_enable(gmac->tx_clk); + if (ret) { + dev_err(&pdev->dev, "Can't enable tx clock\n"); + return ret; + } + ret = clk_set_rate(gmac->tx_clk, GMAC_INTF_RATE_125M); + if (ret) { + dev_err(&pdev->dev, "Can't set tx clock\n"); + goto err_tx_disable; + } + + /* Set initial RX interface clock */ + ret = clk_prepare_enable(gmac->rx_clk); + if (ret) { + dev_err(&pdev->dev, "Can't enable rx clock\n"); + goto err_tx_disable; + } + ret = clk_set_rate(gmac->rx_clk, GMAC_INTF_RATE_125M); + if (ret) { + dev_err(&pdev->dev, "Can't set rx clock\n"); + goto err_txrx_disable; + } + + /* Set interface mode */ + ret = s32_gmac_write_phy_intf_select(gmac); + if (ret) { + dev_err(&pdev->dev, "Can't set PHY interface mode\n"); + goto err_txrx_disable; + } + + return 0; + +err_txrx_disable: + clk_disable_unprepare(gmac->rx_clk); +err_tx_disable: + clk_disable_unprepare(gmac->tx_clk); + return ret; +} + +static void s32_gmac_exit(struct platform_device *pdev, void *priv) +{ + struct s32_priv_data *gmac = priv; + + clk_disable_unprepare(gmac->tx_clk); + clk_disable_unprepare(gmac->rx_clk); +} + +static void s32_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) +{ + struct s32_priv_data *gmac = priv; + long tx_clk_rate; + int ret; + + tx_clk_rate = rgmii_clock(speed); + if (tx_clk_rate < 0) { + dev_err(gmac->dev, "Unsupported/Invalid speed: %d\n", speed); + return; + } + + dev_dbg(gmac->dev, "Set tx clock to %ld Hz\n", tx_clk_rate); + ret = clk_set_rate(gmac->tx_clk, tx_clk_rate); + if (ret) + dev_err(gmac->dev, "Can't set tx clock\n"); +} + +static int s32_dwmac_probe(struct platform_device *pdev) +{ + struct plat_stmmacenet_data *plat; + struct device *dev = &pdev->dev; + struct stmmac_resources res; + struct s32_priv_data *gmac; + int ret; + + gmac = devm_kzalloc(&pdev->dev, sizeof(*gmac), GFP_KERNEL); + if (!gmac) + return -ENOMEM; + + gmac->dev = &pdev->dev; + + ret = stmmac_get_platform_resources(pdev, &res); + if (ret) + return dev_err_probe(dev, ret, + "Failed to get platform resources\n"); + + plat = devm_stmmac_probe_config_dt(pdev, res.mac); + if (IS_ERR(plat)) + return dev_err_probe(dev, PTR_ERR(plat), + "dt configuration failed\n"); + + /* PHY interface mode control reg */ + gmac->ctrl_sts = devm_platform_get_and_ioremap_resource(pdev, 1, NULL); + if (IS_ERR(gmac->ctrl_sts)) + return dev_err_probe(dev, PTR_ERR(gmac->ctrl_sts), + "S32CC config region is missing\n"); + + /* tx clock */ + gmac->tx_clk = devm_clk_get(&pdev->dev, "tx"); + if (IS_ERR(gmac->tx_clk)) + return dev_err_probe(dev, PTR_ERR(gmac->tx_clk), + "tx clock not found\n"); + + /* rx clock */ + gmac->rx_clk = devm_clk_get(&pdev->dev, "rx"); + if (IS_ERR(gmac->rx_clk)) + return dev_err_probe(dev, PTR_ERR(gmac->rx_clk), + "rx clock not found\n"); + + gmac->intf_mode = &plat->phy_interface; + gmac->ioaddr = res.addr; + + /* S32CC core feature set */ + plat->has_gmac4 = true; + plat->pmt = 1; + plat->flags |= STMMAC_FLAG_SPH_DISABLE; + plat->rx_fifo_size = 20480; + plat->tx_fifo_size = 20480; + + plat->init = s32_gmac_init; + plat->exit = s32_gmac_exit; + plat->fix_mac_speed = s32_fix_mac_speed; + + plat->bsp_priv = gmac; + + return stmmac_pltfr_probe(pdev, plat, &res); +} + +static const struct of_device_id s32_dwmac_match[] = { + { .compatible = "nxp,s32g2-dwmac" }, + { } +}; +MODULE_DEVICE_TABLE(of, s32_dwmac_match); + +static struct platform_driver s32_dwmac_driver = { + .probe = s32_dwmac_probe, + .remove = stmmac_pltfr_remove, + .driver = { + .name = "s32-dwmac", + .pm = &stmmac_pltfr_pm_ops, + .of_match_table = s32_dwmac_match, + }, +}; +module_platform_driver(s32_dwmac_driver); + +MODULE_AUTHOR("Jan Petrous (OSS) "); +MODULE_DESCRIPTION("NXP S32G/R common chassis GMAC driver"); +MODULE_LICENSE("GPL"); + diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c index 421666279dd3..0a0a363d3730 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c @@ -34,24 +34,13 @@ struct starfive_dwmac { static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct starfive_dwmac *dwmac = priv; - unsigned long rate; + long rate; int err; - rate = clk_get_rate(dwmac->clk_tx); - - switch (speed) { - case SPEED_1000: - rate = 125000000; - break; - case SPEED_100: - rate = 25000000; - break; - case SPEED_10: - rate = 2500000; - break; - default: + rate = rgmii_clock(speed); + if (rate < 0) { dev_err(dwmac->dev, "invalid speed %u\n", speed); - break; + return; } err = clk_set_rate(dwmac->clk_tx, rate); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index a6ff02d905a9..f25461c292fe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -21,10 +21,7 @@ #include "stmmac_platform.h" -#define DWMAC_125MHZ 125000000 #define DWMAC_50MHZ 50000000 -#define DWMAC_25MHZ 25000000 -#define DWMAC_2_5MHZ 2500000 #define IS_PHY_IF_MODE_RGMII(iface) (iface == PHY_INTERFACE_MODE_RGMII || \ iface == PHY_INTERFACE_MODE_RGMII_ID || \ @@ -140,7 +137,7 @@ static void stih4xx_fix_retime_src(void *priv, u32 spd, unsigned int mode) struct sti_dwmac *dwmac = priv; u32 src = dwmac->tx_retime_src; u32 reg = dwmac->ctrl_reg; - u32 freq = 0; + long freq = 0; if (dwmac->interface == PHY_INTERFACE_MODE_MII) { src = TX_RETIME_SRC_TXCLK; @@ -153,19 +150,14 @@ static void stih4xx_fix_retime_src(void *priv, u32 spd, unsigned int mode) } } else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) { /* On GiGa clk source can be either ext or from clkgen */ - if (spd == SPEED_1000) { - freq = DWMAC_125MHZ; - } else { + freq = rgmii_clock(spd); + + if (spd != SPEED_1000 && freq > 0) /* Switch to clkgen for these speeds */ src = TX_RETIME_SRC_CLKGEN; - if (spd == SPEED_100) - freq = DWMAC_25MHZ; - else if (spd == SPEED_10) - freq = DWMAC_2_5MHZ; - } } - if (src == TX_RETIME_SRC_CLKGEN && freq) + if (src == TX_RETIME_SRC_CLKGEN && freq > 0) clk_set_rate(dwmac->clk, freq); regmap_update_bits(dwmac->regmap, reg, STIH4XX_RETIME_SRC_MASK, @@ -207,16 +199,11 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac, if (res) dwmac->clk_sel_reg = res->start; - regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon"); + regmap = syscon_regmap_lookup_by_phandle_args(np, "st,syscon", + 1, &dwmac->ctrl_reg); if (IS_ERR(regmap)) return PTR_ERR(regmap); - err = of_property_read_u32_index(np, "st,syscon", 1, &dwmac->ctrl_reg); - if (err) { - dev_err(dev, "Can't get sysconfig ctrl offset (%d)\n", err); - return err; - } - err = of_get_phy_mode(np, &dwmac->interface); if (err && err != -ENODEV) { dev_err(dev, "Can't get phy-mode\n"); @@ -321,7 +308,6 @@ static void sti_dwmac_remove(struct platform_device *pdev) clk_disable_unprepare(dwmac->clk); } -#ifdef CONFIG_PM_SLEEP static int sti_dwmac_suspend(struct device *dev) { struct sti_dwmac *dwmac = get_stmmac_bsp_priv(dev); @@ -341,10 +327,9 @@ static int sti_dwmac_resume(struct device *dev) return stmmac_resume(dev); } -#endif /* CONFIG_PM_SLEEP */ -static SIMPLE_DEV_PM_OPS(sti_dwmac_pm_ops, sti_dwmac_suspend, - sti_dwmac_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(sti_dwmac_pm_ops, sti_dwmac_suspend, + sti_dwmac_resume); static const struct sti_dwmac_of_data stih4xx_dwmac_data = { .fix_retime_src = stih4xx_fix_retime_src, @@ -361,7 +346,7 @@ static struct platform_driver sti_dwmac_driver = { .remove = sti_dwmac_remove, .driver = { .name = "sti-dwmac", - .pm = &sti_dwmac_pm_ops, + .pm = pm_sleep_ptr(&sti_dwmac_pm_ops), .of_match_table = sti_dwmac_match, }, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index 1e8bac665cc9..1fcb74e9e3ff 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -419,16 +419,11 @@ static int stm32_dwmac_parse_data(struct stm32_dwmac *dwmac, } /* Get mode register */ - dwmac->regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon"); + dwmac->regmap = syscon_regmap_lookup_by_phandle_args(np, "st,syscon", + 1, &dwmac->mode_reg); if (IS_ERR(dwmac->regmap)) return PTR_ERR(dwmac->regmap); - err = of_property_read_u32_index(np, "st,syscon", 1, &dwmac->mode_reg); - if (err) { - dev_err(dev, "Can't get sysconfig mode offset (%d)\n", err); - return err; - } - if (dwmac->ops->is_mp2) return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c index 3827997d2132..dc903b846b1b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include #include #include @@ -19,6 +20,8 @@ struct tegra_mgbe { struct reset_control *rst_mac; struct reset_control *rst_pcs; + u32 iommu_sid; + void __iomem *hv; void __iomem *regs; void __iomem *xpcs; @@ -50,7 +53,6 @@ struct tegra_mgbe { #define MGBE_WRAP_COMMON_INTR_ENABLE 0x8704 #define MAC_SBD_INTR BIT(2) #define MGBE_WRAP_AXI_ASID0_CTRL 0x8400 -#define MGBE_SID 0x6 static int __maybe_unused tegra_mgbe_suspend(struct device *dev) { @@ -84,7 +86,7 @@ static int __maybe_unused tegra_mgbe_resume(struct device *dev) writel(MAC_SBD_INTR, mgbe->regs + MGBE_WRAP_COMMON_INTR_ENABLE); /* Program SID */ - writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); + writel(mgbe->iommu_sid, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_STATUS); if ((value & XPCS_WRAP_UPHY_STATUS_TX_P_UP) == 0) { @@ -241,6 +243,12 @@ static int tegra_mgbe_probe(struct platform_device *pdev) if (IS_ERR(mgbe->xpcs)) return PTR_ERR(mgbe->xpcs); + /* get controller's stream id from iommu property in device tree */ + if (!tegra_dev_iommu_get_stream_id(mgbe->dev, &mgbe->iommu_sid)) { + dev_err(mgbe->dev, "failed to get iommu stream id\n"); + return -EINVAL; + } + res.addr = mgbe->regs; res.irq = irq; @@ -346,7 +354,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev) writel(MAC_SBD_INTR, mgbe->regs + MGBE_WRAP_COMMON_INTR_ENABLE); /* Program SID */ - writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); + writel(mgbe->iommu_sid, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); plat->flags |= STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index c25781874aa7..9ed8620580a8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -27,7 +27,7 @@ static void dwmac4_core_init(struct mac_device_info *hw, struct stmmac_priv *priv = netdev_priv(dev); void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONFIG); - u32 clk_rate; + unsigned long clk_rate; value |= GMAC_CORE_INIT; @@ -420,10 +420,10 @@ static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link) writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS); } -static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, int et) +static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, u32 et) { void __iomem *ioaddr = hw->pcsr; - int value = et & STMMAC_ET_MAX; + u32 value = et & STMMAC_ET_MAX; int regval; /* Program LPI entry timer value into register */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h index 1ce6f43d545a..806555976496 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h @@ -144,4 +144,7 @@ /* TDS3 use for both format (read and write back) */ #define RDES3_OWN BIT(31) +extern const struct stmmac_mode_ops dwmac4_ring_mode_ops; +extern const struct stmmac_desc_ops dwmac4_desc_ops; + #endif /* __DWMAC4_DESCS_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index a04a79003692..20027d3c25a7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -493,4 +493,9 @@ #define XGMAC_RDES3_TSD BIT(6) #define XGMAC_RDES3_TSA BIT(4) +extern const struct stmmac_ops dwxgmac210_ops; +extern const struct stmmac_ops dwxlgmac2_ops; +extern const struct stmmac_dma_ops dwxgmac210_dma_ops; +extern const struct stmmac_desc_ops dwxgmac210_desc_ops; + #endif /* __STMMAC_DWXGMAC2_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index a72d336a8350..31bdbab9a46c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -9,6 +9,8 @@ #include "stmmac_fpe.h" #include "stmmac_ptp.h" #include "stmmac_est.h" +#include "dwmac4_descs.h" +#include "dwxgmac2.h" static u32 stmmac_get_id(struct stmmac_priv *priv, u32 id_reg) { @@ -265,7 +267,7 @@ static const struct stmmac_hwif_entry { .hwtimestamp = &stmmac_ptp, .ptp = &stmmac_ptp_clock_ops, .mode = NULL, - .tc = &dwxgmac_tc_ops, + .tc = &dwmac510_tc_ops, .mmc = &dwxgmac_mmc_ops, .est = &dwmac510_est_ops, .setup = dwxgmac2_setup, @@ -288,7 +290,7 @@ static const struct stmmac_hwif_entry { .hwtimestamp = &stmmac_ptp, .ptp = &stmmac_ptp_clock_ops, .mode = NULL, - .tc = &dwxgmac_tc_ops, + .tc = &dwmac510_tc_ops, .mmc = &dwxgmac_mmc_ops, .est = &dwmac510_est_ops, .setup = dwxlgmac2_setup, diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 64f8ed67dcc4..0f200b72c225 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -363,7 +363,7 @@ struct stmmac_ops { void (*set_eee_mode)(struct mac_device_info *hw, bool en_tx_lpi_clockgating); void (*reset_eee_mode)(struct mac_device_info *hw); - void (*set_eee_lpi_entry_timer)(struct mac_device_info *hw, int et); + void (*set_eee_lpi_entry_timer)(struct mac_device_info *hw, u32 et); void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw); void (*set_eee_pls)(struct mac_device_info *hw, int link); void (*debug)(struct stmmac_priv *priv, void __iomem *ioaddr, @@ -665,6 +665,15 @@ struct stmmac_regs_off { u32 est_off; }; +extern const struct stmmac_desc_ops enh_desc_ops; +extern const struct stmmac_desc_ops ndesc_ops; + +extern const struct stmmac_hwtimestamp stmmac_ptp; +extern const struct stmmac_hwtimestamp dwmac1000_ptp; + +extern const struct stmmac_mode_ops ring_mode_ops; +extern const struct stmmac_mode_ops chain_mode_ops; + extern const struct stmmac_ops dwmac100_ops; extern const struct stmmac_dma_ops dwmac100_dma_ops; extern const struct stmmac_ops dwmac1000_ops; @@ -676,14 +685,6 @@ extern const struct stmmac_dma_ops dwmac410_dma_ops; extern const struct stmmac_ops dwmac510_ops; extern const struct stmmac_tc_ops dwmac4_tc_ops; extern const struct stmmac_tc_ops dwmac510_tc_ops; -extern const struct stmmac_tc_ops dwxgmac_tc_ops; -extern const struct stmmac_ops dwxgmac210_ops; -extern const struct stmmac_ops dwxlgmac2_ops; -extern const struct stmmac_dma_ops dwxgmac210_dma_ops; -extern const struct stmmac_desc_ops dwxgmac210_desc_ops; -extern const struct stmmac_mmc_ops dwmac_mmc_ops; -extern const struct stmmac_mmc_ops dwxgmac_mmc_ops; -extern const struct stmmac_est_ops dwmac510_est_ops; #define GMAC_VERSION 0x00000020 /* GMAC CORE Version */ #define GMAC4_VERSION 0x00000110 /* GMAC4+ CORE Version */ diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h index 5d1ea3e07459..1cba39fb2c44 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc.h +++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h @@ -139,4 +139,7 @@ struct stmmac_counters { unsigned int mmc_rx_fpe_fragment_cntr; }; +extern const struct stmmac_mmc_ops dwmac_mmc_ops; +extern const struct stmmac_mmc_ops dwxgmac_mmc_ops; + #endif /* __MMC_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 1d86439b8a14..f05cae103d83 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -126,7 +126,7 @@ struct stmmac_rx_queue { unsigned int cur_rx; unsigned int dirty_rx; unsigned int buf_alloc_num; - u32 rx_zeroc_thresh; + unsigned int napi_skb_frag_size; dma_addr_t dma_rx_phy; u32 rx_tail_addr; unsigned int state_saved; @@ -266,7 +266,6 @@ struct stmmac_priv { int sph_cap; u32 sarc_type; - unsigned int rx_copybreak; u32 rx_riwt[MTL_MAX_TX_QUEUES]; int hwts_rx_en; @@ -307,11 +306,9 @@ struct stmmac_priv { int clk_csr; struct timer_list eee_ctrl_timer; int lpi_irq; - int eee_enabled; - int eee_active; - int tx_lpi_timer; - int tx_lpi_enabled; - int eee_tw_timer; + u32 tx_lpi_timer; + bool eee_enabled; + bool eee_active; bool eee_sw_timer_en; unsigned int mode; unsigned int chain_mode; @@ -407,8 +404,6 @@ void stmmac_dvr_remove(struct device *dev); int stmmac_dvr_probe(struct device *device, struct plat_stmmacenet_data *plat_dat, struct stmmac_resources *res); -void stmmac_disable_eee_mode(struct stmmac_priv *priv); -bool stmmac_eee_init(struct stmmac_priv *priv); int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt); int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size); int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled); @@ -418,14 +413,6 @@ static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv) return !!priv->xdp_prog; } -static inline unsigned int stmmac_rx_offset(struct stmmac_priv *priv) -{ - if (stmmac_xdp_is_enabled(priv)) - return XDP_PACKET_HEADROOM; - - return 0; -} - void stmmac_disable_rx_queue(struct stmmac_priv *priv, u32 queue); void stmmac_enable_rx_queue(struct stmmac_priv *priv, u32 queue); void stmmac_disable_tx_queue(struct stmmac_priv *priv, u32 queue); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h index 7a858c566e7e..d247fa383a6e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h @@ -62,3 +62,5 @@ #define EST_SRWO BIT(0) #define EST_GCL_DATA 0x00000034 + +extern const struct stmmac_est_ops dwmac510_est_ops; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 1d77389ce953..918a32f8fda8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -654,7 +654,7 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, (*(u32 *)p); } } - if (priv->eee_enabled) { + if (priv->dma_cap.eee) { int val = phylink_get_eee_err(priv->phylink); if (val) priv->xstats.phy_eee_wakeup_error_n = val; @@ -898,9 +898,6 @@ static int stmmac_ethtool_op_get_eee(struct net_device *dev, if (!priv->dma_cap.eee) return -EOPNOTSUPP; - edata->tx_lpi_timer = priv->tx_lpi_timer; - edata->tx_lpi_enabled = priv->tx_lpi_enabled; - return phylink_ethtool_get_eee(priv->phylink, edata); } @@ -908,29 +905,11 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct ethtool_keee *edata) { struct stmmac_priv *priv = netdev_priv(dev); - int ret; if (!priv->dma_cap.eee) return -EOPNOTSUPP; - if (priv->tx_lpi_enabled != edata->tx_lpi_enabled) - netdev_warn(priv->dev, - "Setting EEE tx-lpi is not supported\n"); - - if (!edata->eee_enabled) - stmmac_disable_eee_mode(priv); - - ret = phylink_ethtool_set_eee(priv->phylink, edata); - if (ret) - return ret; - - if (edata->eee_enabled && - priv->tx_lpi_timer != edata->tx_lpi_timer) { - priv->tx_lpi_timer = edata->tx_lpi_timer; - stmmac_eee_init(priv); - } - - return 0; + return phylink_ethtool_set_eee(priv->phylink, edata); } static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) @@ -1227,43 +1206,6 @@ static int stmmac_get_ts_info(struct net_device *dev, return ethtool_op_get_ts_info(dev, info); } -static int stmmac_get_tunable(struct net_device *dev, - const struct ethtool_tunable *tuna, void *data) -{ - struct stmmac_priv *priv = netdev_priv(dev); - int ret = 0; - - switch (tuna->id) { - case ETHTOOL_RX_COPYBREAK: - *(u32 *)data = priv->rx_copybreak; - break; - default: - ret = -EINVAL; - break; - } - - return ret; -} - -static int stmmac_set_tunable(struct net_device *dev, - const struct ethtool_tunable *tuna, - const void *data) -{ - struct stmmac_priv *priv = netdev_priv(dev); - int ret = 0; - - switch (tuna->id) { - case ETHTOOL_RX_COPYBREAK: - priv->rx_copybreak = *(u32 *)data; - break; - default: - ret = -EINVAL; - break; - } - - return ret; -} - static int stmmac_get_mm(struct net_device *ndev, struct ethtool_mm_state *state) { @@ -1390,8 +1332,6 @@ static const struct ethtool_ops stmmac_ethtool_ops = { .set_per_queue_coalesce = stmmac_set_per_queue_coalesce, .get_channels = stmmac_get_channels, .set_channels = stmmac_set_channels, - .get_tunable = stmmac_get_tunable, - .set_tunable = stmmac_set_tunable, .get_link_ksettings = stmmac_ethtool_get_link_ksettings, .set_link_ksettings = stmmac_ethtool_set_link_ksettings, .get_mm = stmmac_get_mm, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c81ea8cdfe6e..d04543e5697b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -77,7 +77,6 @@ module_param(phyaddr, int, 0444); MODULE_PARM_DESC(phyaddr, "Physical device address"); #define STMMAC_TX_THRESH(x) ((x)->dma_conf.dma_tx_size / 4) -#define STMMAC_RX_THRESH(x) ((x)->dma_conf.dma_rx_size / 4) /* Limit to make sure XDP TX and slow path can coexist */ #define STMMAC_XSK_TX_BUDGET_MAX 256 @@ -107,15 +106,13 @@ static int buf_sz = DEFAULT_BUFSIZE; module_param(buf_sz, int, 0644); MODULE_PARM_DESC(buf_sz, "DMA buffer size"); -#define STMMAC_RX_COPYBREAK 256 - static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN | NETIF_MSG_TIMER); #define STMMAC_DEFAULT_LPI_TIMER 1000 -static int eee_timer = STMMAC_DEFAULT_LPI_TIMER; -module_param(eee_timer, int, 0644); +static unsigned int eee_timer = STMMAC_DEFAULT_LPI_TIMER; +module_param(eee_timer, uint, 0644); MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec"); #define STMMAC_LPI_T(x) (jiffies + usecs_to_jiffies(x)) @@ -197,8 +194,6 @@ static void stmmac_verify_args(void) flow_ctrl = FLOW_OFF; if (unlikely((pause < 0) || (pause > 0xffff))) pause = PAUSE_TIME; - if (eee_timer < 0) - eee_timer = STMMAC_DEFAULT_LPI_TIMER; } static void __stmmac_disable_all_queues(struct stmmac_priv *priv) @@ -301,7 +296,7 @@ static void stmmac_global_err(struct stmmac_priv *priv) */ static void stmmac_clk_csr_set(struct stmmac_priv *priv) { - u32 clk_rate; + unsigned long clk_rate; clk_rate = clk_get_rate(priv->plat->stmmac_clk); @@ -325,6 +320,10 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv) priv->clk_csr = STMMAC_CSR_150_250M; else if ((clk_rate >= CSR_F_250M) && (clk_rate <= CSR_F_300M)) priv->clk_csr = STMMAC_CSR_250_300M; + else if ((clk_rate >= CSR_F_300M) && (clk_rate < CSR_F_500M)) + priv->clk_csr = STMMAC_CSR_300_500M; + else if ((clk_rate >= CSR_F_500M) && (clk_rate < CSR_F_800M)) + priv->clk_csr = STMMAC_CSR_500_800M; } if (priv->plat->flags & STMMAC_FLAG_HAS_SUN8I) { @@ -391,23 +390,17 @@ static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue) return dirty; } -static void stmmac_lpi_entry_timer_config(struct stmmac_priv *priv, bool en) +static void stmmac_disable_hw_lpi_timer(struct stmmac_priv *priv) { - int tx_lpi_timer; - - /* Clear/set the SW EEE timer flag based on LPI ET enablement */ - priv->eee_sw_timer_en = en ? 0 : 1; - tx_lpi_timer = en ? priv->tx_lpi_timer : 0; - stmmac_set_eee_lpi_timer(priv, priv->hw, tx_lpi_timer); + stmmac_set_eee_lpi_timer(priv, priv->hw, 0); } -/** - * stmmac_enable_eee_mode - check and enter in LPI mode - * @priv: driver private structure - * Description: this function is to verify and enter in LPI mode in case of - * EEE. - */ -static int stmmac_enable_eee_mode(struct stmmac_priv *priv) +static void stmmac_enable_hw_lpi_timer(struct stmmac_priv *priv) +{ + stmmac_set_eee_lpi_timer(priv, priv->hw, priv->tx_lpi_timer); +} + +static bool stmmac_eee_tx_busy(struct stmmac_priv *priv) { u32 tx_cnt = priv->plat->tx_queues_to_use; u32 queue; @@ -417,29 +410,43 @@ static int stmmac_enable_eee_mode(struct stmmac_priv *priv) struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; if (tx_q->dirty_tx != tx_q->cur_tx) - return -EBUSY; /* still unfinished work */ + return true; /* still unfinished work */ + } + + return false; +} + +static void stmmac_restart_sw_lpi_timer(struct stmmac_priv *priv) +{ + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); +} + +/** + * stmmac_try_to_start_sw_lpi - check and enter in LPI mode + * @priv: driver private structure + * Description: this function is to verify and enter in LPI mode in case of + * EEE. + */ +static void stmmac_try_to_start_sw_lpi(struct stmmac_priv *priv) +{ + if (stmmac_eee_tx_busy(priv)) { + stmmac_restart_sw_lpi_timer(priv); + return; } /* Check and enter in LPI mode */ if (!priv->tx_path_in_lpi_mode) stmmac_set_eee_mode(priv, priv->hw, priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING); - return 0; } /** - * stmmac_disable_eee_mode - disable and exit from LPI mode + * stmmac_stop_sw_lpi - stop transmitting LPI * @priv: driver private structure - * Description: this function is to exit and disable EEE in case of - * LPI state is true. This is called by the xmit. + * Description: When using software-controlled LPI, stop transmitting LPI state. */ -void stmmac_disable_eee_mode(struct stmmac_priv *priv) +static void stmmac_stop_sw_lpi(struct stmmac_priv *priv) { - if (!priv->eee_sw_timer_en) { - stmmac_lpi_entry_timer_config(priv, 0); - return; - } - stmmac_reset_eee_mode(priv, priv->hw); del_timer_sync(&priv->eee_ctrl_timer); priv->tx_path_in_lpi_mode = false; @@ -456,25 +463,27 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t) { struct stmmac_priv *priv = from_timer(priv, t, eee_ctrl_timer); - if (stmmac_enable_eee_mode(priv)) - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); + stmmac_try_to_start_sw_lpi(priv); } /** * stmmac_eee_init - init EEE * @priv: driver private structure + * @active: indicates whether EEE should be enabled. * Description: * if the GMAC supports the EEE (from the HW cap reg) and the phy device * can also manage EEE, this function enable the LPI state and start related * timer. */ -bool stmmac_eee_init(struct stmmac_priv *priv) +static void stmmac_eee_init(struct stmmac_priv *priv, bool active) { - int eee_tw_timer = priv->eee_tw_timer; + priv->eee_active = active; /* Check if MAC core supports the EEE feature. */ - if (!priv->dma_cap.eee) - return false; + if (!priv->dma_cap.eee) { + priv->eee_enabled = false; + return; + } mutex_lock(&priv->lock); @@ -482,22 +491,24 @@ bool stmmac_eee_init(struct stmmac_priv *priv) if (!priv->eee_active) { if (priv->eee_enabled) { netdev_dbg(priv->dev, "disable EEE\n"); - stmmac_lpi_entry_timer_config(priv, 0); + priv->eee_sw_timer_en = false; + stmmac_disable_hw_lpi_timer(priv); del_timer_sync(&priv->eee_ctrl_timer); - stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer); + stmmac_set_eee_timer(priv, priv->hw, 0, + STMMAC_DEFAULT_TWT_LS); if (priv->hw->xpcs) xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns, false); } + priv->eee_enabled = false; mutex_unlock(&priv->lock); - return false; + return; } if (priv->eee_active && !priv->eee_enabled) { - timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0); stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS, - eee_tw_timer); + STMMAC_DEFAULT_TWT_LS); if (priv->hw->xpcs) xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns, @@ -505,18 +516,22 @@ bool stmmac_eee_init(struct stmmac_priv *priv) } if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) { + /* Use hardware LPI mode */ del_timer_sync(&priv->eee_ctrl_timer); priv->tx_path_in_lpi_mode = false; - stmmac_lpi_entry_timer_config(priv, 1); + priv->eee_sw_timer_en = false; + stmmac_enable_hw_lpi_timer(priv); } else { - stmmac_lpi_entry_timer_config(priv, 0); - mod_timer(&priv->eee_ctrl_timer, - STMMAC_LPI_T(priv->tx_lpi_timer)); + /* Use software LPI mode */ + priv->eee_sw_timer_en = true; + stmmac_disable_hw_lpi_timer(priv); + stmmac_restart_sw_lpi_timer(priv); } + priv->eee_enabled = true; + mutex_unlock(&priv->lock); netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n"); - return true; } /* stmmac_get_tx_hwtstamp - get HW TX timestamps @@ -973,10 +988,8 @@ static void stmmac_mac_link_down(struct phylink_config *config, struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); stmmac_mac_set(priv, priv->ioaddr, false); - priv->eee_active = false; - priv->tx_lpi_enabled = false; - priv->eee_enabled = stmmac_eee_init(priv); - stmmac_set_eee_pls(priv, priv->hw, false); + if (priv->dma_cap.eee) + stmmac_set_eee_pls(priv, priv->hw, false); if (stmmac_fpe_supported(priv)) stmmac_fpe_link_state_handle(priv, false); @@ -1083,14 +1096,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, writel(ctrl, priv->ioaddr + MAC_CTRL_REG); stmmac_mac_set(priv, priv->ioaddr, true); - if (phy && priv->dma_cap.eee) { - priv->eee_active = - phy_init_eee(phy, !(priv->plat->flags & - STMMAC_FLAG_RX_CLK_RUNS_IN_LPI)) >= 0; - priv->eee_enabled = stmmac_eee_init(priv); - priv->tx_lpi_enabled = priv->eee_enabled; + if (priv->dma_cap.eee) stmmac_set_eee_pls(priv, priv->hw, true); - } if (stmmac_fpe_supported(priv)) stmmac_fpe_link_state_handle(priv, true); @@ -1099,12 +1106,32 @@ static void stmmac_mac_link_up(struct phylink_config *config, stmmac_hwtstamp_correct_latency(priv, priv); } +static void stmmac_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); + + stmmac_eee_init(priv, false); +} + +static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop) +{ + struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); + + priv->tx_lpi_timer = timer; + stmmac_eee_init(priv, true); + + return 0; +} + static const struct phylink_mac_ops stmmac_phylink_mac_ops = { .mac_get_caps = stmmac_mac_get_caps, .mac_select_pcs = stmmac_mac_select_pcs, .mac_config = stmmac_mac_config, .mac_link_down = stmmac_mac_link_down, .mac_link_up = stmmac_mac_link_up, + .mac_disable_tx_lpi = stmmac_mac_disable_tx_lpi, + .mac_enable_tx_lpi = stmmac_mac_enable_tx_lpi, }; /** @@ -1177,15 +1204,27 @@ static int stmmac_init_phy(struct net_device *dev) return -ENODEV; } - if (priv->dma_cap.eee) - phy_support_eee(phydev); - ret = phylink_connect_phy(priv->phylink, phydev); } else { fwnode_handle_put(phy_fwnode); ret = phylink_fwnode_phy_connect(priv->phylink, fwnode, 0); } + if (ret == 0) { + struct ethtool_keee eee; + + /* Configure phylib's copy of the LPI timer. Normally, + * phylink_config.lpi_timer_default would do this, but there is + * a chance that userspace could change the eee_timer setting + * via sysfs before the first open. Thus, preserve existing + * behaviour. + */ + if (!phylink_ethtool_get_eee(priv->phylink, &eee)) { + eee.tx_lpi_timer = priv->tx_lpi_timer; + phylink_ethtool_set_eee(priv->phylink, &eee); + } + } + if (!priv->plat->pmt) { struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; @@ -1202,6 +1241,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) struct stmmac_mdio_bus_data *mdio_bus_data; int mode = priv->plat->phy_interface; struct fwnode_handle *fwnode; + struct phylink_pcs *pcs; struct phylink *phylink; priv->phylink_config.dev = &priv->dev->dev; @@ -1211,6 +1251,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) /* Stmmac always requires an RX clock for hardware initialization */ priv->phylink_config.mac_requires_rxc = true; + if (!(priv->plat->flags & STMMAC_FLAG_RX_CLK_RUNS_IN_LPI)) + priv->phylink_config.eee_rx_clk_stop_enable = true; + mdio_bus_data = priv->plat->mdio_bus_data; if (mdio_bus_data) priv->phylink_config.default_an_inband = @@ -1223,8 +1266,27 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) /* If we have an xpcs, it defines which PHY interfaces are supported. */ if (priv->hw->xpcs) - xpcs_get_interfaces(priv->hw->xpcs, - priv->phylink_config.supported_interfaces); + pcs = xpcs_to_phylink_pcs(priv->hw->xpcs); + else + pcs = priv->hw->phylink_pcs; + + if (pcs) + phy_interface_or(priv->phylink_config.supported_interfaces, + priv->phylink_config.supported_interfaces, + pcs->supported_interfaces); + + if (priv->dma_cap.eee) { + /* Assume all supported interfaces also support LPI */ + memcpy(priv->phylink_config.lpi_interfaces, + priv->phylink_config.supported_interfaces, + sizeof(priv->phylink_config.lpi_interfaces)); + + /* All full duplex speeds above 100Mbps are supported */ + priv->phylink_config.lpi_capabilities = ~(MAC_1000FD - 1) | + MAC_100FD; + priv->phylink_config.lpi_timer_default = eee_timer * 1000; + priv->phylink_config.eee_enabled_default = true; + } fwnode = priv->plat->port_node; if (!fwnode) @@ -1307,6 +1369,14 @@ static void stmmac_display_rings(struct stmmac_priv *priv, stmmac_display_tx_rings(priv, dma_conf); } +static unsigned int stmmac_rx_offset(struct stmmac_priv *priv) +{ + if (stmmac_xdp_is_enabled(priv)) + return XDP_PACKET_HEADROOM; + + return NET_SKB_PAD; +} + static int stmmac_set_bfsize(int mtu, int bufsize) { int ret = bufsize; @@ -2003,22 +2073,26 @@ static int __alloc_dma_rx_desc_resources(struct stmmac_priv *priv, struct stmmac_channel *ch = &priv->channel[queue]; bool xdp_prog = stmmac_xdp_is_enabled(priv); struct page_pool_params pp_params = { 0 }; - unsigned int num_pages; + unsigned int dma_buf_sz_pad, num_pages; unsigned int napi_id; int ret; + dma_buf_sz_pad = stmmac_rx_offset(priv) + dma_conf->dma_buf_sz + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + num_pages = DIV_ROUND_UP(dma_buf_sz_pad, PAGE_SIZE); + rx_q->queue_index = queue; rx_q->priv_data = priv; + rx_q->napi_skb_frag_size = num_pages * PAGE_SIZE; pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; pp_params.pool_size = dma_conf->dma_rx_size; - num_pages = DIV_ROUND_UP(dma_conf->dma_buf_sz, PAGE_SIZE); - pp_params.order = ilog2(num_pages); + pp_params.order = order_base_2(num_pages); pp_params.nid = dev_to_node(priv->device); pp_params.dev = priv->device; pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; pp_params.offset = stmmac_rx_offset(priv); - pp_params.max_len = STMMAC_MAX_RX_BUF_SIZE(num_pages); + pp_params.max_len = dma_conf->dma_buf_sz; rx_q->page_pool = page_pool_create(&pp_params); if (IS_ERR(rx_q->page_pool)) { @@ -2350,11 +2424,6 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) u32 chan = 0; u8 qmode = 0; - if (rxfifosz == 0) - rxfifosz = priv->dma_cap.rx_fifo_size; - if (txfifosz == 0) - txfifosz = priv->dma_cap.tx_fifo_size; - /* Split up the shared Tx/Rx FIFO memory on DW QoS Eth and DW XGMAC */ if (priv->plat->has_gmac4 || priv->plat->has_xgmac) { rxfifosz /= rx_channels_count; @@ -2757,11 +2826,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue, xmits = budget; } - if (priv->eee_enabled && !priv->tx_path_in_lpi_mode && - priv->eee_sw_timer_en) { - if (stmmac_enable_eee_mode(priv)) - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); - } + if (priv->eee_sw_timer_en && !priv->tx_path_in_lpi_mode) + stmmac_restart_sw_lpi_timer(priv); /* We still have pending packets, let's call for a new scheduling */ if (tx_q->dirty_tx != tx_q->cur_tx) @@ -2826,11 +2892,6 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, int rxfifosz = priv->plat->rx_fifo_size; int txfifosz = priv->plat->tx_fifo_size; - if (rxfifosz == 0) - rxfifosz = priv->dma_cap.rx_fifo_size; - if (txfifosz == 0) - txfifosz = priv->dma_cap.tx_fifo_size; - /* Adjust for real per queue fifo size */ rxfifosz /= rx_channels_count; txfifosz /= tx_channels_count; @@ -3436,12 +3497,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) else if (ptp_register) stmmac_ptp_register(priv); - priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS; - - /* Convert the timer from msec to usec */ - if (!priv->tx_lpi_timer) - priv->tx_lpi_timer = eee_timer * 1000; - if (priv->use_riwt) { u32 queue; @@ -3908,6 +3963,10 @@ static int __stmmac_open(struct net_device *dev, u32 chan; int ret; + /* Initialise the tx lpi timer, converting from msec to usec */ + if (!priv->tx_lpi_timer) + priv->tx_lpi_timer = eee_timer * 1000; + ret = pm_runtime_resume_and_get(priv->device); if (ret < 0) return ret; @@ -3923,8 +3982,6 @@ static int __stmmac_open(struct net_device *dev, } } - priv->rx_copybreak = STMMAC_RX_COPYBREAK; - buf_sz = dma_conf->dma_buf_sz; for (int i = 0; i < MTL_MAX_TX_QUEUES; i++) if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN) @@ -4024,11 +4081,6 @@ static int stmmac_release(struct net_device *dev) /* Free the IRQ lines */ stmmac_free_irq(dev, REQ_IRQ_ERR_ALL, 0); - if (priv->eee_enabled) { - priv->tx_path_in_lpi_mode = false; - del_timer_sync(&priv->eee_ctrl_timer); - } - /* Stop TX/RX DMA and clear the descriptors */ stmmac_stop_all_dma(priv); @@ -4117,11 +4169,7 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des, desc = &tx_q->dma_tx[tx_q->cur_tx]; curr_addr = des + (total_len - tmp_len); - if (priv->dma_cap.addr64 <= 32) - desc->des0 = cpu_to_le32(curr_addr); - else - stmmac_set_desc_addr(priv, desc, curr_addr); - + stmmac_set_desc_addr(priv, desc, curr_addr); buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ? TSO_MAX_BUFF_SIZE : tmp_len; @@ -4167,17 +4215,27 @@ static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue) * First Descriptor * -------- * | DES0 |---> buffer1 = L2/L3/L4 header - * | DES1 |---> TCP Payload (can continue on next descr...) - * | DES2 |---> buffer 1 and 2 len + * | DES1 |---> can be used as buffer2 for TCP Payload if the DMA AXI address + * | | width is 32-bit, but we never use it. + * | | Also can be used as the most-significant 8-bits or 16-bits of + * | | buffer1 address pointer if the DMA AXI address width is 40-bit + * | | or 48-bit, and we always use it. + * | DES2 |---> buffer1 len * | DES3 |---> must set TSE, TCP hdr len-> [22:19]. TCP payload len [17:0] * -------- + * -------- + * | DES0 |---> buffer1 = TCP Payload (can continue on next descr...) + * | DES1 |---> same as the First Descriptor + * | DES2 |---> buffer1 len + * | DES3 | + * -------- * | * ... * | * -------- - * | DES0 | --| Split TCP Payload on Buffers 1 and 2 - * | DES1 | --| - * | DES2 | --> buffer 1 and 2 len + * | DES0 |---> buffer1 = Split TCP Payload + * | DES1 |---> same as the First Descriptor + * | DES2 |---> buffer1 len * | DES3 | * -------- * @@ -4187,15 +4245,14 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) { struct dma_desc *desc, *first, *mss_desc = NULL; struct stmmac_priv *priv = netdev_priv(dev); - int tmp_pay_len = 0, first_tx, nfrags; unsigned int first_entry, tx_packets; struct stmmac_txq_stats *txq_stats; struct stmmac_tx_queue *tx_q; u32 pay_len, mss, queue; - dma_addr_t tso_des, des; + int i, first_tx, nfrags; u8 proto_hdr_len, hdr; + dma_addr_t des; bool set_ic; - int i; /* Always insert VLAN tag to SKB payload for TSO frames. * @@ -4280,24 +4337,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) if (dma_mapping_error(priv->device, des)) goto dma_map_err; - if (priv->dma_cap.addr64 <= 32) { - first->des0 = cpu_to_le32(des); - - /* Fill start of payload in buff2 of first descriptor */ - if (pay_len) - first->des1 = cpu_to_le32(des + proto_hdr_len); - - /* If needed take extra descriptors to fill the remaining payload */ - tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE; - tso_des = des; - } else { - stmmac_set_desc_addr(priv, first, des); - tmp_pay_len = pay_len; - tso_des = des + proto_hdr_len; - pay_len = 0; - } - - stmmac_tso_allocator(priv, tso_des, tmp_pay_len, (nfrags == 0), queue); + stmmac_set_desc_addr(priv, first, des); + stmmac_tso_allocator(priv, des + proto_hdr_len, pay_len, + (nfrags == 0), queue); /* In case two or more DMA transmit descriptors are allocated for this * non-paged SKB data, the DMA buffer address should be saved to @@ -4401,11 +4443,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) } /* Complete the first descriptor before granting the DMA */ - stmmac_prepare_tso_tx_desc(priv, first, 1, - proto_hdr_len, - pay_len, - 1, tx_q->tx_skbuff_dma[first_entry].last_segment, - hdr / 4, (skb->len - proto_hdr_len)); + stmmac_prepare_tso_tx_desc(priv, first, 1, proto_hdr_len, 0, 1, + tx_q->tx_skbuff_dma[first_entry].last_segment, + hdr / 4, (skb->len - proto_hdr_len)); /* If context desc is used to change MSS */ if (mss_desc) { @@ -4492,7 +4532,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) first_tx = tx_q->cur_tx; if (priv->tx_path_in_lpi_mode && priv->eee_sw_timer_en) - stmmac_disable_eee_mode(priv); + stmmac_stop_sw_lpi(priv); /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { @@ -5473,7 +5513,7 @@ read_again: if (priv->extend_desc) stmmac_rx_extended_status(priv, &priv->xstats, rx_q->dma_erx + entry); if (unlikely(status == discard_frame)) { - page_pool_recycle_direct(rx_q->page_pool, buf->page); + page_pool_put_page(rx_q->page_pool, buf->page, 0, true); buf->page = NULL; error = 1; if (!priv->hwts_rx_en) @@ -5491,10 +5531,6 @@ read_again: /* Buffer is good. Go on. */ - prefetch(page_address(buf->page) + buf->page_offset); - if (buf->sec_page) - prefetch(page_address(buf->sec_page)); - buf1_len = stmmac_rx_buf1_len(priv, p, status, len); len += buf1_len; buf2_len = stmmac_rx_buf2_len(priv, p, status, len); @@ -5516,6 +5552,8 @@ read_again: dma_sync_single_for_cpu(priv->device, buf->addr, buf1_len, dma_dir); + net_prefetch(page_address(buf->page) + + buf->page_offset); xdp_init_buff(&ctx.xdp, buf_sz, &rx_q->xdp_rxq); xdp_prepare_buff(&ctx.xdp, page_address(buf->page), @@ -5569,22 +5607,26 @@ read_again: } if (!skb) { + unsigned int head_pad_len; + /* XDP program may expand or reduce tail */ buf1_len = ctx.xdp.data_end - ctx.xdp.data; - skb = napi_alloc_skb(&ch->rx_napi, buf1_len); + skb = napi_build_skb(page_address(buf->page), + rx_q->napi_skb_frag_size); if (!skb) { + page_pool_recycle_direct(rx_q->page_pool, + buf->page); rx_dropped++; count++; goto drain_data; } /* XDP program may adjust header */ - skb_copy_to_linear_data(skb, ctx.xdp.data, buf1_len); + head_pad_len = ctx.xdp.data - ctx.xdp.data_hard_start; + skb_reserve(skb, head_pad_len); skb_put(skb, buf1_len); - - /* Data payload copied into SKB, page ready for recycle */ - page_pool_recycle_direct(rx_q->page_pool, buf->page); + skb_mark_for_recycle(skb); buf->page = NULL; } else if (buf1_len) { dma_sync_single_for_cpu(priv->device, buf->addr, @@ -5592,9 +5634,6 @@ read_again: skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, buf->page, buf->page_offset, buf1_len, priv->dma_conf.dma_buf_sz); - - /* Data payload appended into SKB */ - skb_mark_for_recycle(skb); buf->page = NULL; } @@ -5604,9 +5643,6 @@ read_again: skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, buf->sec_page, 0, buf2_len, priv->dma_conf.dma_buf_sz); - - /* Data payload appended into SKB */ - skb_mark_for_recycle(skb); buf->sec_page = NULL; } @@ -5832,9 +5868,6 @@ static int stmmac_change_mtu(struct net_device *dev, int new_mtu) const int mtu = new_mtu; int ret; - if (txfifosz == 0) - txfifosz = priv->dma_cap.tx_fifo_size; - txfifosz /= priv->plat->tx_queues_to_use; if (stmmac_xdp_is_enabled(priv) && new_mtu > ETH_DATA_LEN) { @@ -6489,11 +6522,7 @@ static int stmmac_device_event(struct notifier_block *unused, switch (event) { case NETDEV_CHANGENAME: - if (priv->dbgfs_dir) - priv->dbgfs_dir = debugfs_rename(stmmac_fs_dir, - priv->dbgfs_dir, - stmmac_fs_dir, - dev->name); + debugfs_change_name(priv->dbgfs_dir, "%s", dev->name); break; } done: @@ -7175,6 +7204,50 @@ static int stmmac_hw_init(struct stmmac_priv *priv) if (priv->dma_cap.tsoen) dev_info(priv->device, "TSO supported\n"); + if (priv->dma_cap.number_rx_queues && + priv->plat->rx_queues_to_use > priv->dma_cap.number_rx_queues) { + dev_warn(priv->device, + "Number of Rx queues (%u) exceeds dma capability\n", + priv->plat->rx_queues_to_use); + priv->plat->rx_queues_to_use = priv->dma_cap.number_rx_queues; + } + if (priv->dma_cap.number_tx_queues && + priv->plat->tx_queues_to_use > priv->dma_cap.number_tx_queues) { + dev_warn(priv->device, + "Number of Tx queues (%u) exceeds dma capability\n", + priv->plat->tx_queues_to_use); + priv->plat->tx_queues_to_use = priv->dma_cap.number_tx_queues; + } + + if (!priv->plat->rx_fifo_size) { + if (priv->dma_cap.rx_fifo_size) { + priv->plat->rx_fifo_size = priv->dma_cap.rx_fifo_size; + } else { + dev_err(priv->device, "Can't specify Rx FIFO size\n"); + return -ENODEV; + } + } else if (priv->dma_cap.rx_fifo_size && + priv->plat->rx_fifo_size > priv->dma_cap.rx_fifo_size) { + dev_warn(priv->device, + "Rx FIFO size (%u) exceeds dma capability\n", + priv->plat->rx_fifo_size); + priv->plat->rx_fifo_size = priv->dma_cap.rx_fifo_size; + } + if (!priv->plat->tx_fifo_size) { + if (priv->dma_cap.tx_fifo_size) { + priv->plat->tx_fifo_size = priv->dma_cap.tx_fifo_size; + } else { + dev_err(priv->device, "Can't specify Tx FIFO size\n"); + return -ENODEV; + } + } else if (priv->dma_cap.tx_fifo_size && + priv->plat->tx_fifo_size > priv->dma_cap.tx_fifo_size) { + dev_warn(priv->device, + "Tx FIFO size (%u) exceeds dma capability\n", + priv->plat->tx_fifo_size); + priv->plat->tx_fifo_size = priv->dma_cap.tx_fifo_size; + } + priv->hw->vlan_fail_q_en = (priv->plat->flags & STMMAC_FLAG_VLAN_FAIL_Q_EN); priv->hw->vlan_fail_q = priv->plat->vlan_fail_q; @@ -7407,6 +7480,8 @@ int stmmac_dvr_probe(struct device *device, INIT_WORK(&priv->service_task, stmmac_service_task); + timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0); + /* Override with kernel parameters if supplied XXX CRS XXX * this needs to have multiple instances */ @@ -7714,7 +7789,7 @@ int stmmac_suspend(struct device *dev) for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) hrtimer_cancel(&priv->dma_conf.tx_queue[chan].txtimer); - if (priv->eee_enabled) { + if (priv->eee_sw_timer_en) { priv->tx_path_in_lpi_mode = false; del_timer_sync(&priv->eee_ctrl_timer); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 3ac32444e492..d0e61aa1a495 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -405,22 +405,6 @@ static int stmmac_of_get_mac_mode(struct device_node *np) return -ENODEV; } -/** - * stmmac_remove_config_dt - undo the effects of stmmac_probe_config_dt() - * @pdev: platform_device structure - * @plat: driver data platform structure - * - * Release resources claimed by stmmac_probe_config_dt(). - */ -static void stmmac_remove_config_dt(struct platform_device *pdev, - struct plat_stmmacenet_data *plat) -{ - clk_disable_unprepare(plat->stmmac_clk); - clk_disable_unprepare(plat->pclk); - of_node_put(plat->phy_node); - of_node_put(plat->mdio_node); -} - /** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure @@ -490,8 +474,10 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); rc = stmmac_mdio_setup(plat, np, &pdev->dev); - if (rc) - return ERR_PTR(rc); + if (rc) { + ret = ERR_PTR(rc); + goto error_put_phy; + } of_property_read_u32(np, "tx-fifo-depth", &plat->tx_fifo_size); @@ -581,8 +567,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL); if (!dma_cfg) { - stmmac_remove_config_dt(pdev, plat); - return ERR_PTR(-ENOMEM); + ret = ERR_PTR(-ENOMEM); + goto error_put_mdio; } plat->dma_cfg = dma_cfg; @@ -610,8 +596,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) rc = stmmac_mtl_setup(pdev, plat); if (rc) { - stmmac_remove_config_dt(pdev, plat); - return ERR_PTR(rc); + ret = ERR_PTR(rc); + goto error_put_mdio; } /* clock setup */ @@ -640,7 +626,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dev_info(&pdev->dev, "PTP uses main clock\n"); } else { plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref); - dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate); + dev_dbg(&pdev->dev, "PTP rate %lu\n", plat->clk_ptp_rate); } plat->stmmac_rst = devm_reset_control_get_optional(&pdev->dev, @@ -663,6 +649,10 @@ error_hw_init: clk_disable_unprepare(plat->pclk); error_pclk_get: clk_disable_unprepare(plat->stmmac_clk); +error_put_mdio: + of_node_put(plat->mdio_node); +error_put_phy: + of_node_put(plat->phy_node); return ret; } @@ -671,16 +661,17 @@ static void devm_stmmac_remove_config_dt(void *data) { struct plat_stmmacenet_data *plat = data; - /* Platform data argument is unused */ - stmmac_remove_config_dt(NULL, plat); + clk_disable_unprepare(plat->stmmac_clk); + clk_disable_unprepare(plat->pclk); + of_node_put(plat->mdio_node); + of_node_put(plat->phy_node); } /** * devm_stmmac_probe_config_dt * @pdev: platform_device structure * @mac: MAC address to use - * Description: Devres variant of stmmac_probe_config_dt(). Does not require - * the user to call stmmac_remove_config_dt() at driver detach. + * Description: Devres variant of stmmac_probe_config_dt(). */ struct plat_stmmacenet_data * devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h index 4cc70480ce0f..3fe0e3a80e80 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h @@ -104,4 +104,7 @@ int dwmac1000_ptp_enable(struct ptp_clock_info *ptp, void dwmac1000_get_ptptime(void __iomem *ptpaddr, u64 *ptp_time); void dwmac1000_timestamp_interrupt(struct stmmac_priv *priv); +extern const struct ptp_clock_info stmmac_ptp_clock_ops; +extern const struct ptp_clock_info dwmac1000_ptp_clock_ops; + #endif /* __STMMAC_PTP_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 6a79e6a111ed..694d6ee14381 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -1284,14 +1284,3 @@ const struct stmmac_tc_ops dwmac510_tc_ops = { .query_caps = tc_query_caps, .setup_mqprio = tc_setup_dwmac510_mqprio, }; - -const struct stmmac_tc_ops dwxgmac_tc_ops = { - .init = tc_init, - .setup_cls_u32 = tc_setup_cls_u32, - .setup_cbs = tc_setup_cbs, - .setup_cls = tc_setup_cls, - .setup_taprio = tc_setup_taprio, - .setup_etf = tc_setup_etf, - .query_caps = tc_query_caps, - .setup_mqprio = tc_setup_dwmac510_mqprio, -}; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h index 896dc987d4ef..77ce8cfbe976 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h @@ -4,7 +4,6 @@ #ifndef _STMMAC_XDP_H_ #define _STMMAC_XDP_H_ -#define STMMAC_MAX_RX_BUF_SIZE(num) (((num) * PAGE_SIZE) - XDP_PACKET_HEADROOM) #define STMMAC_RX_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) int stmmac_xdp_setup_pool(struct stmmac_priv *priv, struct xsk_buff_pool *pool, diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index df6d35d41b97..72177fea1cfb 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -3303,7 +3303,7 @@ static struct page *niu_find_rxpage(struct rx_ring_info *rp, u64 addr, addr &= PAGE_MASK; pp = &rp->rxhash[h]; for (; (p = *pp) != NULL; pp = &niu_next_page(p)) { - if (p->index == addr) { + if (p->private == addr) { *link = pp; goto found; } @@ -3318,7 +3318,7 @@ static void niu_hash_page(struct rx_ring_info *rp, struct page *page, u64 base) { unsigned int h = niu_hash_rxaddr(rp, base); - page->index = base; + page->private = base; niu_next_page(page) = rp->rxhash[h]; rp->rxhash[h] = page; } @@ -3400,11 +3400,11 @@ static int niu_rx_pkt_ignore(struct niu *np, struct rx_ring_info *rp) rcr_size = rp->rbr_sizes[(val & RCR_ENTRY_PKTBUFSZ) >> RCR_ENTRY_PKTBUFSZ_SHIFT]; - if ((page->index + PAGE_SIZE) - rcr_size == addr) { + if ((page->private + PAGE_SIZE) - rcr_size == addr) { *link = niu_next_page(page); - np->ops->unmap_page(np->device, page->index, + np->ops->unmap_page(np->device, page->private, PAGE_SIZE, DMA_FROM_DEVICE); - page->index = 0; + page->private = 0; niu_next_page(page) = NULL; __free_page(page); rp->rbr_refill_pending++; @@ -3469,11 +3469,11 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np, append_size = append_size - skb->len; niu_rx_skb_append(skb, page, off, append_size, rcr_size); - if ((page->index + rp->rbr_block_size) - rcr_size == addr) { + if ((page->private + rp->rbr_block_size) - rcr_size == addr) { *link = niu_next_page(page); - np->ops->unmap_page(np->device, page->index, + np->ops->unmap_page(np->device, page->private, PAGE_SIZE, DMA_FROM_DEVICE); - page->index = 0; + page->private = 0; niu_next_page(page) = NULL; rp->rbr_refill_pending++; } else @@ -3538,11 +3538,11 @@ static void niu_rbr_free(struct niu *np, struct rx_ring_info *rp) page = rp->rxhash[i]; while (page) { struct page *next = niu_next_page(page); - u64 base = page->index; + u64 base = page->private; np->ops->unmap_page(np->device, base, PAGE_SIZE, DMA_FROM_DEVICE); - page->index = 0; + page->private = 0; niu_next_page(page) = NULL; __free_page(page); @@ -6086,7 +6086,7 @@ static void niu_enable_napi(struct niu *np) int i; for (i = 0; i < np->num_ldg; i++) - napi_enable(&np->ldg[i].napi); + napi_enable_locked(&np->ldg[i].napi); } static void niu_disable_napi(struct niu *np) @@ -6116,7 +6116,9 @@ static int niu_open(struct net_device *dev) if (err) goto out_free_channels; + netdev_lock(dev); niu_enable_napi(np); + netdev_unlock(dev); spin_lock_irq(&np->lock); @@ -6460,7 +6462,7 @@ static void niu_reset_buffers(struct niu *np) page = rp->rxhash[j]; while (page) { struct page *next = niu_next_page(page); - u64 base = page->index; + u64 base = page->private; base = base >> RBR_DESCR_ADDR_SHIFT; rp->rbr[k++] = cpu_to_le32(base); page = next; @@ -6521,6 +6523,7 @@ static void niu_reset_task(struct work_struct *work) niu_reset_buffers(np); + netdev_lock(np->dev); spin_lock_irqsave(&np->lock, flags); err = niu_init_hw(np); @@ -6531,6 +6534,7 @@ static void niu_reset_task(struct work_struct *work) } spin_unlock_irqrestore(&np->lock, flags); + netdev_unlock(np->dev); } static void niu_tx_timeout(struct net_device *dev, unsigned int txqueue) @@ -6761,7 +6765,9 @@ static int niu_change_mtu(struct net_device *dev, int new_mtu) niu_free_channels(np); + netdev_lock(dev); niu_enable_napi(np); + netdev_unlock(dev); err = niu_alloc_channels(np); if (err) @@ -9937,6 +9943,7 @@ static int __maybe_unused niu_resume(struct device *dev_d) spin_lock_irqsave(&np->lock, flags); + netdev_lock(dev); err = niu_init_hw(np); if (!err) { np->timer.expires = jiffies + HZ; @@ -9945,6 +9952,7 @@ static int __maybe_unused niu_resume(struct device *dev_d) } spin_unlock_irqrestore(&np->lock, flags); + netdev_unlock(dev); return err; } diff --git a/drivers/net/ethernet/sunplus/spl2sw_driver.c b/drivers/net/ethernet/sunplus/spl2sw_driver.c index 721d8ed3f302..5e0e4c9ecbb0 100644 --- a/drivers/net/ethernet/sunplus/spl2sw_driver.c +++ b/drivers/net/ethernet/sunplus/spl2sw_driver.c @@ -199,7 +199,7 @@ static const struct net_device_ops netdev_ops = { .ndo_start_xmit = spl2sw_ethernet_start_xmit, .ndo_set_rx_mode = spl2sw_ethernet_set_rx_mode, .ndo_set_mac_address = spl2sw_ethernet_set_mac_address, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_tx_timeout = spl2sw_ethernet_tx_timeout, }; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 14e1df721f2e..b663271e79f7 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include "cpsw_ale.h" @@ -497,35 +498,62 @@ static void am65_cpsw_init_host_port_switch(struct am65_cpsw_common *common); static void am65_cpsw_init_host_port_emac(struct am65_cpsw_common *common); static void am65_cpsw_init_port_switch_ale(struct am65_cpsw_port *port); static void am65_cpsw_init_port_emac_ale(struct am65_cpsw_port *port); +static inline void am65_cpsw_put_page(struct am65_cpsw_rx_flow *flow, + struct page *page, + bool allow_direct); +static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma); +static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma); -static void am65_cpsw_destroy_xdp_rxqs(struct am65_cpsw_common *common) +static void am65_cpsw_destroy_rxq(struct am65_cpsw_common *common, int id) { struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; struct am65_cpsw_rx_flow *flow; struct xdp_rxq_info *rxq; - int id, port; + int port; - for (id = 0; id < common->rx_ch_num_flows; id++) { - flow = &rx_chn->flows[id]; + flow = &rx_chn->flows[id]; + napi_disable(&flow->napi_rx); + hrtimer_cancel(&flow->rx_hrtimer); + k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, id, rx_chn, + am65_cpsw_nuss_rx_cleanup, !!id); - for (port = 0; port < common->port_num; port++) { - if (!common->ports[port].ndev) - continue; + for (port = 0; port < common->port_num; port++) { + if (!common->ports[port].ndev) + continue; - rxq = &common->ports[port].xdp_rxq[id]; + rxq = &common->ports[port].xdp_rxq[id]; - if (xdp_rxq_info_is_reg(rxq)) - xdp_rxq_info_unreg(rxq); - } + if (xdp_rxq_info_is_reg(rxq)) + xdp_rxq_info_unreg(rxq); + } - if (flow->page_pool) { - page_pool_destroy(flow->page_pool); - flow->page_pool = NULL; - } + if (flow->page_pool) { + page_pool_destroy(flow->page_pool); + flow->page_pool = NULL; } } -static int am65_cpsw_create_xdp_rxqs(struct am65_cpsw_common *common) +static void am65_cpsw_destroy_rxqs(struct am65_cpsw_common *common) +{ + struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; + int id; + + reinit_completion(&common->tdown_complete); + k3_udma_glue_tdown_rx_chn(rx_chn->rx_chn, true); + + if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ) { + id = wait_for_completion_timeout(&common->tdown_complete, msecs_to_jiffies(1000)); + if (!id) + dev_err(common->dev, "rx teardown timeout\n"); + } + + for (id = common->rx_ch_num_flows - 1; id >= 0; id--) + am65_cpsw_destroy_rxq(common, id); + + k3_udma_glue_disable_rx_chn(common->rx_chns.rx_chn); +} + +static int am65_cpsw_create_rxq(struct am65_cpsw_common *common, int id) { struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; struct page_pool_params pp_params = { @@ -540,45 +568,162 @@ static int am65_cpsw_create_xdp_rxqs(struct am65_cpsw_common *common) struct am65_cpsw_rx_flow *flow; struct xdp_rxq_info *rxq; struct page_pool *pool; - int id, port, ret; + struct page *page; + int port, ret, i; - for (id = 0; id < common->rx_ch_num_flows; id++) { - flow = &rx_chn->flows[id]; - pp_params.napi = &flow->napi_rx; - pool = page_pool_create(&pp_params); - if (IS_ERR(pool)) { - ret = PTR_ERR(pool); + flow = &rx_chn->flows[id]; + pp_params.napi = &flow->napi_rx; + pool = page_pool_create(&pp_params); + if (IS_ERR(pool)) { + ret = PTR_ERR(pool); + return ret; + } + + flow->page_pool = pool; + + /* using same page pool is allowed as no running rx handlers + * simultaneously for both ndevs + */ + for (port = 0; port < common->port_num; port++) { + if (!common->ports[port].ndev) + /* FIXME should we BUG here? */ + continue; + + rxq = &common->ports[port].xdp_rxq[id]; + ret = xdp_rxq_info_reg(rxq, common->ports[port].ndev, + id, flow->napi_rx.napi_id); + if (ret) + goto err; + + ret = xdp_rxq_info_reg_mem_model(rxq, + MEM_TYPE_PAGE_POOL, + pool); + if (ret) + goto err; + } + + for (i = 0; i < AM65_CPSW_MAX_RX_DESC; i++) { + page = page_pool_dev_alloc_pages(flow->page_pool); + if (!page) { + dev_err(common->dev, "cannot allocate page in flow %d\n", + id); + ret = -ENOMEM; goto err; } - flow->page_pool = pool; + ret = am65_cpsw_nuss_rx_push(common, page, id); + if (ret < 0) { + dev_err(common->dev, + "cannot submit page to rx channel flow %d, error %d\n", + id, ret); + am65_cpsw_put_page(flow, page, false); + goto err; + } + } - /* using same page pool is allowed as no running rx handlers - * simultaneously for both ndevs - */ - for (port = 0; port < common->port_num; port++) { - if (!common->ports[port].ndev) - continue; + napi_enable(&flow->napi_rx); + return 0; - rxq = &common->ports[port].xdp_rxq[id]; +err: + am65_cpsw_destroy_rxq(common, id); + return ret; +} - ret = xdp_rxq_info_reg(rxq, common->ports[port].ndev, - id, flow->napi_rx.napi_id); - if (ret) - goto err; +static int am65_cpsw_create_rxqs(struct am65_cpsw_common *common) +{ + int id, ret; - ret = xdp_rxq_info_reg_mem_model(rxq, - MEM_TYPE_PAGE_POOL, - pool); - if (ret) - goto err; + for (id = 0; id < common->rx_ch_num_flows; id++) { + ret = am65_cpsw_create_rxq(common, id); + if (ret) { + dev_err(common->dev, "couldn't create rxq %d: %d\n", + id, ret); + goto err; + } + } + + ret = k3_udma_glue_enable_rx_chn(common->rx_chns.rx_chn); + if (ret) { + dev_err(common->dev, "couldn't enable rx chn: %d\n", ret); + goto err; + } + + return 0; + +err: + for (--id; id >= 0; id--) + am65_cpsw_destroy_rxq(common, id); + + return ret; +} + +static void am65_cpsw_destroy_txq(struct am65_cpsw_common *common, int id) +{ + struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[id]; + + napi_disable(&tx_chn->napi_tx); + hrtimer_cancel(&tx_chn->tx_hrtimer); + k3_udma_glue_reset_tx_chn(tx_chn->tx_chn, tx_chn, + am65_cpsw_nuss_tx_cleanup); + k3_udma_glue_disable_tx_chn(tx_chn->tx_chn); +} + +static void am65_cpsw_destroy_txqs(struct am65_cpsw_common *common) +{ + struct am65_cpsw_tx_chn *tx_chn = common->tx_chns; + int id; + + /* shutdown tx channels */ + atomic_set(&common->tdown_cnt, common->tx_ch_num); + /* ensure new tdown_cnt value is visible */ + smp_mb__after_atomic(); + reinit_completion(&common->tdown_complete); + + for (id = 0; id < common->tx_ch_num; id++) + k3_udma_glue_tdown_tx_chn(tx_chn[id].tx_chn, false); + + id = wait_for_completion_timeout(&common->tdown_complete, + msecs_to_jiffies(1000)); + if (!id) + dev_err(common->dev, "tx teardown timeout\n"); + + for (id = common->tx_ch_num - 1; id >= 0; id--) + am65_cpsw_destroy_txq(common, id); +} + +static int am65_cpsw_create_txq(struct am65_cpsw_common *common, int id) +{ + struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[id]; + int ret; + + ret = k3_udma_glue_enable_tx_chn(tx_chn->tx_chn); + if (ret) + return ret; + + napi_enable(&tx_chn->napi_tx); + + return 0; +} + +static int am65_cpsw_create_txqs(struct am65_cpsw_common *common) +{ + int id, ret; + + for (id = 0; id < common->tx_ch_num; id++) { + ret = am65_cpsw_create_txq(common, id); + if (ret) { + dev_err(common->dev, "couldn't create txq %d: %d\n", + id, ret); + goto err; } } return 0; err: - am65_cpsw_destroy_xdp_rxqs(common); + for (--id; id >= 0; id--) + am65_cpsw_destroy_txq(common, id); + return ret; } @@ -642,7 +787,6 @@ static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma) k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE); k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - am65_cpsw_put_page(&rx_chn->flows[flow_id], page, false); } @@ -717,12 +861,8 @@ static struct sk_buff *am65_cpsw_build_skb(void *page_addr, static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) { struct am65_cpsw_host *host_p = am65_common_get_host(common); - struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; - struct am65_cpsw_tx_chn *tx_chn = common->tx_chns; - int port_idx, i, ret, tx, flow_idx; - struct am65_cpsw_rx_flow *flow; u32 val, port_mask; - struct page *page; + int port_idx, ret; if (common->usage_count) return 0; @@ -762,7 +902,7 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) ALE_DEFAULT_THREAD_ID, 0); cpsw_ale_control_set(common->ale, HOST_PORT_NUM, ALE_DEFAULT_THREAD_ENABLE, 1); - /* switch to vlan unaware mode */ + /* switch to vlan aware mode */ cpsw_ale_control_set(common->ale, HOST_PORT_NUM, ALE_VLAN_AWARE, 1); cpsw_ale_control_set(common->ale, HOST_PORT_NUM, ALE_PORT_STATE, ALE_PORT_STATE_FORWARD); @@ -782,151 +922,38 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) am65_cpsw_qos_tx_p0_rate_init(common); - ret = am65_cpsw_create_xdp_rxqs(common); - if (ret) { - dev_err(common->dev, "Failed to create XDP rx queues\n"); + ret = am65_cpsw_create_rxqs(common); + if (ret) return ret; - } - for (flow_idx = 0; flow_idx < common->rx_ch_num_flows; flow_idx++) { - flow = &rx_chn->flows[flow_idx]; - for (i = 0; i < AM65_CPSW_MAX_RX_DESC; i++) { - page = page_pool_dev_alloc_pages(flow->page_pool); - if (!page) { - dev_err(common->dev, "cannot allocate page in flow %d\n", - flow_idx); - ret = -ENOMEM; - goto fail_rx; - } - - ret = am65_cpsw_nuss_rx_push(common, page, flow_idx); - if (ret < 0) { - dev_err(common->dev, - "cannot submit page to rx channel flow %d, error %d\n", - flow_idx, ret); - am65_cpsw_put_page(flow, page, false); - goto fail_rx; - } - } - } - - ret = k3_udma_glue_enable_rx_chn(rx_chn->rx_chn); - if (ret) { - dev_err(common->dev, "couldn't enable rx chn: %d\n", ret); - goto fail_rx; - } - - for (i = 0; i < common->rx_ch_num_flows ; i++) { - napi_enable(&rx_chn->flows[i].napi_rx); - if (rx_chn->flows[i].irq_disabled) { - rx_chn->flows[i].irq_disabled = false; - enable_irq(rx_chn->flows[i].irq); - } - } - - for (tx = 0; tx < common->tx_ch_num; tx++) { - ret = k3_udma_glue_enable_tx_chn(tx_chn[tx].tx_chn); - if (ret) { - dev_err(common->dev, "couldn't enable tx chn %d: %d\n", - tx, ret); - tx--; - goto fail_tx; - } - napi_enable(&tx_chn[tx].napi_tx); - } + ret = am65_cpsw_create_txqs(common); + if (ret) + goto cleanup_rx; dev_dbg(common->dev, "cpsw_nuss started\n"); return 0; -fail_tx: - while (tx >= 0) { - napi_disable(&tx_chn[tx].napi_tx); - k3_udma_glue_disable_tx_chn(tx_chn[tx].tx_chn); - tx--; - } - - for (flow_idx = 0; i < common->rx_ch_num_flows; flow_idx++) { - flow = &rx_chn->flows[flow_idx]; - if (!flow->irq_disabled) { - disable_irq(flow->irq); - flow->irq_disabled = true; - } - napi_disable(&flow->napi_rx); - } - - k3_udma_glue_disable_rx_chn(rx_chn->rx_chn); - -fail_rx: - for (i = 0; i < common->rx_ch_num_flows; i++) - k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, rx_chn, - am65_cpsw_nuss_rx_cleanup, !!i); - - am65_cpsw_destroy_xdp_rxqs(common); +cleanup_rx: + am65_cpsw_destroy_rxqs(common); return ret; } static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common) { - struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; - struct am65_cpsw_tx_chn *tx_chn = common->tx_chns; - int i; - if (common->usage_count != 1) return 0; cpsw_ale_control_set(common->ale, HOST_PORT_NUM, ALE_PORT_STATE, ALE_PORT_STATE_DISABLE); - /* shutdown tx channels */ - atomic_set(&common->tdown_cnt, common->tx_ch_num); - /* ensure new tdown_cnt value is visible */ - smp_mb__after_atomic(); - reinit_completion(&common->tdown_complete); - - for (i = 0; i < common->tx_ch_num; i++) - k3_udma_glue_tdown_tx_chn(tx_chn[i].tx_chn, false); - - i = wait_for_completion_timeout(&common->tdown_complete, - msecs_to_jiffies(1000)); - if (!i) - dev_err(common->dev, "tx timeout\n"); - for (i = 0; i < common->tx_ch_num; i++) { - napi_disable(&tx_chn[i].napi_tx); - hrtimer_cancel(&tx_chn[i].tx_hrtimer); - } - - for (i = 0; i < common->tx_ch_num; i++) { - k3_udma_glue_reset_tx_chn(tx_chn[i].tx_chn, &tx_chn[i], - am65_cpsw_nuss_tx_cleanup); - k3_udma_glue_disable_tx_chn(tx_chn[i].tx_chn); - } - - reinit_completion(&common->tdown_complete); - k3_udma_glue_tdown_rx_chn(rx_chn->rx_chn, true); - - if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ) { - i = wait_for_completion_timeout(&common->tdown_complete, msecs_to_jiffies(1000)); - if (!i) - dev_err(common->dev, "rx teardown timeout\n"); - } - - for (i = common->rx_ch_num_flows - 1; i >= 0; i--) { - napi_disable(&rx_chn->flows[i].napi_rx); - hrtimer_cancel(&rx_chn->flows[i].rx_hrtimer); - k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, rx_chn, - am65_cpsw_nuss_rx_cleanup, !!i); - } - - k3_udma_glue_disable_rx_chn(rx_chn->rx_chn); - + am65_cpsw_destroy_txqs(common); + am65_cpsw_destroy_rxqs(common); cpsw_ale_stop(common->ale); writel(0, common->cpsw_base + AM65_CPSW_REG_CTL); writel(0, common->cpsw_base + AM65_CPSW_REG_STAT_PORT_EN); - am65_cpsw_destroy_xdp_rxqs(common); - dev_dbg(common->dev, "cpsw_nuss stopped\n"); return 0; } @@ -1014,6 +1041,15 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev) common->usage_count++; + /* VLAN aware CPSW mode is incompatible with some DSA tagging schemes. + * Therefore disable VLAN_AWARE mode if any of the ports is a DSA Port. + */ + if (netdev_uses_dsa(ndev)) { + reg = readl(common->cpsw_base + AM65_CPSW_REG_CTL); + reg &= ~AM65_CPSW_CTL_VLAN_AWARE; + writel(reg, common->cpsw_base + AM65_CPSW_REG_CTL); + } + am65_cpsw_port_set_sl_mac(port, ndev->dev_addr); am65_cpsw_port_enable_dscp_map(port); @@ -2242,13 +2278,11 @@ static void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common) struct device *dev = common->dev; int i; - devm_remove_action(dev, am65_cpsw_nuss_free_tx_chns, common); - common->tx_ch_rate_msk = 0; for (i = 0; i < common->tx_ch_num; i++) { struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; - if (tx_chn->irq) + if (tx_chn->irq > 0) devm_free_irq(dev, tx_chn->irq, tx_chn); netif_napi_del(&tx_chn->napi_tx); @@ -2265,8 +2299,6 @@ static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common) for (i = 0; i < common->tx_ch_num; i++) { struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; - netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx, - am65_cpsw_nuss_tx_poll); hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); tx_chn->tx_hrtimer.function = &am65_cpsw_nuss_tx_timer_callback; @@ -2279,9 +2311,21 @@ static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common) tx_chn->id, tx_chn->irq, ret); goto err; } + + netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx, + am65_cpsw_nuss_tx_poll); } + return 0; + err: + for (--i ; i >= 0 ; i--) { + struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; + + netif_napi_del(&tx_chn->napi_tx); + devm_free_irq(dev, tx_chn->irq, tx_chn); + } + return ret; } @@ -2362,12 +2406,10 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) goto err; } + return 0; + err: - i = devm_add_action(dev, am65_cpsw_nuss_free_tx_chns, common); - if (i) { - dev_err(dev, "Failed to add free_tx_chns action %d\n", i); - return i; - } + am65_cpsw_nuss_free_tx_chns(common); return ret; } @@ -2395,7 +2437,6 @@ static void am65_cpsw_nuss_remove_rx_chns(struct am65_cpsw_common *common) rx_chn = &common->rx_chns; flows = rx_chn->flows; - devm_remove_action(dev, am65_cpsw_nuss_free_rx_chns, common); for (i = 0; i < common->rx_ch_num_flows; i++) { if (!(flows[i].irq < 0)) @@ -2494,7 +2535,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) i, &rx_flow_cfg); if (ret) { dev_err(dev, "Failed to init rx flow%d %d\n", i, ret); - goto err; + goto err_flow; } if (!i) fdqring_id = @@ -2506,14 +2547,12 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) dev_err(dev, "Failed to get rx dma irq %d\n", flow->irq); ret = flow->irq; - goto err; + goto err_flow; } snprintf(flow->name, sizeof(flow->name), "%s-rx%d", dev_name(dev), i); - netif_napi_add(common->dma_ndev, &flow->napi_rx, - am65_cpsw_nuss_rx_poll); hrtimer_init(&flow->rx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); flow->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback; @@ -2526,20 +2565,28 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) dev_err(dev, "failure requesting rx %d irq %u, %d\n", i, flow->irq, ret); flow->irq = -EINVAL; - goto err; + goto err_flow; } + + netif_napi_add(common->dma_ndev, &flow->napi_rx, + am65_cpsw_nuss_rx_poll); } /* setup classifier to route priorities to flows */ cpsw_ale_classifier_setup_default(common->ale, common->rx_ch_num_flows); -err: - i = devm_add_action(dev, am65_cpsw_nuss_free_rx_chns, common); - if (i) { - dev_err(dev, "Failed to add free_rx_chns action %d\n", i); - return i; + return 0; + +err_flow: + for (--i; i >= 0 ; i--) { + flow = &rx_chn->flows[i]; + netif_napi_del(&flow->napi_rx); + devm_free_irq(dev, flow->irq, flow); } +err: + am65_cpsw_nuss_free_rx_chns(common); + return ret; } @@ -2559,20 +2606,15 @@ static int am65_cpsw_am654_get_efuse_macid(struct device_node *of_node, { u32 mac_lo, mac_hi, offset; struct regmap *syscon; - int ret; - syscon = syscon_regmap_lookup_by_phandle(of_node, "ti,syscon-efuse"); + syscon = syscon_regmap_lookup_by_phandle_args(of_node, "ti,syscon-efuse", + 1, &offset); if (IS_ERR(syscon)) { if (PTR_ERR(syscon) == -ENODEV) return 0; return PTR_ERR(syscon); } - ret = of_property_read_u32_index(of_node, "ti,syscon-efuse", 1, - &offset); - if (ret) - return ret; - regmap_read(syscon, offset, &mac_lo); regmap_read(syscon, offset + 4, &mac_hi); @@ -3349,7 +3391,7 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) return ret; ret = am65_cpsw_nuss_init_rx_chns(common); if (ret) - return ret; + goto err_remove_tx; /* The DMA Channels are not guaranteed to be in a clean state. * Reset and disable them to ensure that they are back to the @@ -3370,7 +3412,7 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) ret = am65_cpsw_nuss_register_devlink(common); if (ret) - return ret; + goto err_remove_rx; for (i = 0; i < common->port_num; i++) { port = &common->ports[i]; @@ -3401,6 +3443,10 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) err_cleanup_ndev: am65_cpsw_nuss_cleanup_ndev(common); am65_cpsw_unregister_devlink(common); +err_remove_rx: + am65_cpsw_nuss_remove_rx_chns(common); +err_remove_tx: + am65_cpsw_nuss_remove_tx_chns(common); return ret; } @@ -3420,6 +3466,8 @@ int am65_cpsw_nuss_update_tx_rx_chns(struct am65_cpsw_common *common, return ret; ret = am65_cpsw_nuss_init_rx_chns(common); + if (ret) + am65_cpsw_nuss_remove_tx_chns(common); return ret; } @@ -3551,7 +3599,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) init_completion(&common->tdown_complete); common->tx_ch_num = AM65_CPSW_DEFAULT_TX_CHNS; common->rx_ch_num_flows = AM65_CPSW_DEFAULT_RX_CHN_FLOWS; - common->pf_p0_rx_ptype_rrobin = false; + common->pf_p0_rx_ptype_rrobin = true; common->default_vlan = 1; common->ports = devm_kcalloc(dev, common->port_num, @@ -3678,6 +3726,8 @@ static void am65_cpsw_nuss_remove(struct platform_device *pdev) */ am65_cpsw_nuss_cleanup_ndev(common); am65_cpsw_unregister_devlink(common); + am65_cpsw_nuss_remove_rx_chns(common); + am65_cpsw_nuss_remove_tx_chns(common); am65_cpsw_nuss_phylink_cleanup(common); am65_cpts_release(common->cpts); am65_cpsw_disable_serdes_phy(common); @@ -3739,8 +3789,10 @@ static int am65_cpsw_nuss_resume(struct device *dev) if (ret) return ret; ret = am65_cpsw_nuss_init_rx_chns(common); - if (ret) + if (ret) { + am65_cpsw_nuss_remove_tx_chns(common); return ret; + } /* If RX IRQ was disabled before suspend, keep it disabled */ for (i = 0; i < common->rx_ch_num_flows; i++) { diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 4ef8cf6ea135..0cb6fa6e5b7d 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -635,6 +635,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) slave->phy = phy; + phy_disable_eee(slave->phy); + phy_attached_info(slave->phy); phy_start(slave->phy); @@ -684,7 +686,7 @@ static void cpsw_init_host_port(struct cpsw_priv *priv) soft_reset("cpsw", &cpsw->regs->soft_reset); cpsw_ale_start(cpsw->ale); - /* switch to vlan unaware mode */ + /* switch to vlan aware mode */ cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_VLAN_AWARE, CPSW_ALE_VLAN_AWARE); control_reg = readl(&cpsw->regs->control); @@ -1225,7 +1227,6 @@ static const struct ethtool_ops cpsw_ethtool_ops = { .get_link_ksettings = cpsw_get_link_ksettings, .set_link_ksettings = cpsw_set_link_ksettings, .get_eee = cpsw_get_eee, - .set_eee = cpsw_set_eee, .nway_reset = cpsw_nway_reset, .get_ringparam = cpsw_get_ringparam, .set_ringparam = cpsw_set_ringparam, diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 52e4e350b734..5cc72a91f220 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -127,15 +127,15 @@ struct cpsw_ale_dev_id { static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits) { - int idx, idx2; + int idx, idx2, index; u32 hi_val = 0; idx = start / 32; idx2 = (start + bits - 1) / 32; /* Check if bits to be fetched exceed a word */ if (idx != idx2) { - idx2 = 2 - idx2; /* flip */ - hi_val = ale_entry[idx2] << ((idx2 * 32) - start); + index = 2 - idx2; /* flip */ + hi_val = ale_entry[index] << ((idx2 * 32) - start); } start -= idx * 32; idx = 2 - idx; /* flip */ @@ -145,16 +145,16 @@ static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits) static inline void cpsw_ale_set_field(u32 *ale_entry, u32 start, u32 bits, u32 value) { - int idx, idx2; + int idx, idx2, index; value &= BITMASK(bits); idx = start / 32; idx2 = (start + bits - 1) / 32; /* Check if bits to be set exceed a word */ if (idx != idx2) { - idx2 = 2 - idx2; /* flip */ - ale_entry[idx2] &= ~(BITMASK(bits + start - (idx2 * 32))); - ale_entry[idx2] |= (value >> ((idx2 * 32) - start)); + index = 2 - idx2; /* flip */ + ale_entry[index] &= ~(BITMASK(bits + start - (idx2 * 32))); + ale_entry[index] |= (value >> ((idx2 * 32) - start)); } start -= idx * 32; idx = 2 - idx; /* flip */ diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c index 21d55a180ef6..bdc4db0d169c 100644 --- a/drivers/net/ethernet/ti/cpsw_ethtool.c +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c @@ -434,18 +434,6 @@ int cpsw_get_eee(struct net_device *ndev, struct ethtool_keee *edata) return -EOPNOTSUPP; } -int cpsw_set_eee(struct net_device *ndev, struct ethtool_keee *edata) -{ - struct cpsw_priv *priv = netdev_priv(ndev); - struct cpsw_common *cpsw = priv->cpsw; - int slave_no = cpsw_slave_index(cpsw, priv); - - if (cpsw->slaves[slave_no].phy) - return phy_ethtool_set_eee(cpsw->slaves[slave_no].phy, edata); - else - return -EOPNOTSUPP; -} - int cpsw_nway_reset(struct net_device *ndev) { struct cpsw_priv *priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index a98bcc5eb566..cec0a90659d9 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -554,7 +554,7 @@ static void cpsw_init_host_port(struct cpsw_priv *priv) soft_reset("cpsw", &cpsw->regs->soft_reset); cpsw_ale_start(cpsw->ale); - /* switch to vlan unaware mode */ + /* switch to vlan aware mode */ cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_VLAN_AWARE, CPSW_ALE_VLAN_AWARE); control_reg = readl(&cpsw->regs->control); @@ -778,6 +778,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) slave->phy = phy; + phy_disable_eee(slave->phy); + phy_attached_info(slave->phy); phy_start(slave->phy); @@ -1209,7 +1211,6 @@ static const struct ethtool_ops cpsw_ethtool_ops = { .get_link_ksettings = cpsw_get_link_ksettings, .set_link_ksettings = cpsw_set_link_ksettings, .get_eee = cpsw_get_eee, - .set_eee = cpsw_set_eee, .nway_reset = cpsw_nway_reset, .get_ringparam = cpsw_get_ringparam, .set_ringparam = cpsw_set_ringparam, diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index 1f448290b9f4..f2fc55d9295d 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -497,7 +497,6 @@ int cpsw_get_link_ksettings(struct net_device *ndev, int cpsw_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *ecmd); int cpsw_get_eee(struct net_device *ndev, struct ethtool_keee *edata); -int cpsw_set_eee(struct net_device *ndev, struct ethtool_keee *edata); int cpsw_nway_reset(struct net_device *ndev); void cpsw_get_ringparam(struct net_device *ndev, struct ethtool_ringparam *ering, diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c index 5d6d1cf78e93..768578c0d958 100644 --- a/drivers/net/ethernet/ti/icssg/icss_iep.c +++ b/drivers/net/ethernet/ti/icssg/icss_iep.c @@ -215,6 +215,9 @@ static void icss_iep_enable_shadow_mode(struct icss_iep *iep) for (cmp = IEP_MIN_CMP; cmp < IEP_MAX_CMP; cmp++) { regmap_update_bits(iep->map, ICSS_IEP_CMP_STAT_REG, IEP_CMP_STATUS(cmp), IEP_CMP_STATUS(cmp)); + + regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG, + IEP_CMP_CFG_CMP_EN(cmp), 0); } /* enable reset counter on CMP0 event */ @@ -780,6 +783,11 @@ int icss_iep_exit(struct icss_iep *iep) } icss_iep_disable(iep); + if (iep->pps_enabled) + icss_iep_pps_enable(iep, false); + else if (iep->perout_enabled) + icss_iep_perout_enable(iep, NULL, false); + return 0; } EXPORT_SYMBOL_GPL(icss_iep_exit); diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index fdebeb2f84e0..74f0f200a89d 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -855,31 +855,6 @@ irqreturn_t prueth_rx_irq(int irq, void *dev_id) } EXPORT_SYMBOL_GPL(prueth_rx_irq); -void prueth_emac_stop(struct prueth_emac *emac) -{ - struct prueth *prueth = emac->prueth; - int slice; - - switch (emac->port_id) { - case PRUETH_PORT_MII0: - slice = ICSS_SLICE0; - break; - case PRUETH_PORT_MII1: - slice = ICSS_SLICE1; - break; - default: - netdev_err(emac->ndev, "invalid port\n"); - return; - } - - emac->fw_running = 0; - if (!emac->is_sr1) - rproc_shutdown(prueth->txpru[slice]); - rproc_shutdown(prueth->rtu[slice]); - rproc_shutdown(prueth->pru[slice]); -} -EXPORT_SYMBOL_GPL(prueth_emac_stop); - void prueth_cleanup_tx_ts(struct prueth_emac *emac) { int i; diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index 5d2491c2943a..ddfd1c02a885 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -397,7 +397,7 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac) return 0; } -static void icssg_init_emac_mode(struct prueth *prueth) +void icssg_init_emac_mode(struct prueth *prueth) { /* When the device is configured as a bridge and it is being brought * back to the emac mode, the host mac address has to be set as 0. @@ -406,9 +406,6 @@ static void icssg_init_emac_mode(struct prueth *prueth) int i; u8 mac[ETH_ALEN] = { 0 }; - if (prueth->emacs_initialized) - return; - /* Set VLAN TABLE address base */ regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, addr << SMEM_VLAN_OFFSET); @@ -423,15 +420,13 @@ static void icssg_init_emac_mode(struct prueth *prueth) /* Clear host MAC address */ icssg_class_set_host_mac_addr(prueth->miig_rt, mac); } +EXPORT_SYMBOL_GPL(icssg_init_emac_mode); -static void icssg_init_fw_offload_mode(struct prueth *prueth) +void icssg_init_fw_offload_mode(struct prueth *prueth) { u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET; int i; - if (prueth->emacs_initialized) - return; - /* Set VLAN TABLE address base */ regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, addr << SMEM_VLAN_OFFSET); @@ -448,6 +443,7 @@ static void icssg_init_fw_offload_mode(struct prueth *prueth) icssg_class_set_host_mac_addr(prueth->miig_rt, prueth->hw_bridge_dev->dev_addr); icssg_set_pvid(prueth, prueth->default_vlan, PRUETH_PORT_HOST); } +EXPORT_SYMBOL_GPL(icssg_init_fw_offload_mode); int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) { @@ -455,11 +451,6 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) struct icssg_flow_cfg __iomem *flow_cfg; int ret; - if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) - icssg_init_fw_offload_mode(prueth); - else - icssg_init_emac_mode(prueth); - memset_io(config, 0, TAS_GATE_MASK_LIST0); icssg_miig_queues_init(prueth, slice); @@ -786,3 +777,27 @@ void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port) writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT0_DEFAULT_VLAN_OFFSET); } EXPORT_SYMBOL_GPL(icssg_set_pvid); + +int emac_fdb_flow_id_updated(struct prueth_emac *emac) +{ + struct mgmt_cmd_rsp fdb_cmd_rsp = { 0 }; + int slice = prueth_emac_slice(emac); + struct mgmt_cmd fdb_cmd = { 0 }; + int ret; + + fdb_cmd.header = ICSSG_FW_MGMT_CMD_HEADER; + fdb_cmd.type = ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW; + fdb_cmd.seqnum = ++(emac->prueth->icssg_hwcmdseq); + fdb_cmd.param = 0; + + fdb_cmd.param |= (slice << 4); + fdb_cmd.cmd_args[0] = 0; + + ret = icssg_send_fdb_msg(emac, &fdb_cmd, &fdb_cmd_rsp); + if (ret) + return ret; + + WARN_ON(fdb_cmd.seqnum != fdb_cmd_rsp.seqnum); + return fdb_cmd_rsp.status == 1 ? 0 : -EINVAL; +} +EXPORT_SYMBOL_GPL(emac_fdb_flow_id_updated); diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h index 92c2deaa3068..c884e9fa099e 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.h +++ b/drivers/net/ethernet/ti/icssg/icssg_config.h @@ -55,6 +55,7 @@ struct icssg_rxq_ctx { #define ICSSG_FW_MGMT_FDB_CMD_TYPE 0x03 #define ICSSG_FW_MGMT_CMD_TYPE 0x04 #define ICSSG_FW_MGMT_PKT 0x80000000 +#define ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW 0x05 struct icssg_r30_cmd { u32 cmd[4]; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index c568c84a032b..00ed97860547 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -164,11 +164,26 @@ static struct icssg_firmwares icssg_emac_firmwares[] = { } }; -static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) +static int prueth_start(struct rproc *rproc, const char *fw_name) +{ + int ret; + + ret = rproc_set_firmware(rproc, fw_name); + if (ret) + return ret; + return rproc_boot(rproc); +} + +static void prueth_shutdown(struct rproc *rproc) +{ + rproc_shutdown(rproc); +} + +static int prueth_emac_start(struct prueth *prueth) { struct icssg_firmwares *firmwares; struct device *dev = prueth->dev; - int slice, ret; + int ret, slice; if (prueth->is_switch_mode) firmwares = icssg_switch_firmwares; @@ -177,49 +192,126 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) else firmwares = icssg_emac_firmwares; - slice = prueth_emac_slice(emac); - if (slice < 0) { - netdev_err(emac->ndev, "invalid port\n"); - return -EINVAL; + for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { + ret = prueth_start(prueth->pru[slice], firmwares[slice].pru); + if (ret) { + dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret); + goto unwind_slices; + } + + ret = prueth_start(prueth->rtu[slice], firmwares[slice].rtu); + if (ret) { + dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret); + rproc_shutdown(prueth->pru[slice]); + goto unwind_slices; + } + + ret = prueth_start(prueth->txpru[slice], firmwares[slice].txpru); + if (ret) { + dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret); + rproc_shutdown(prueth->rtu[slice]); + rproc_shutdown(prueth->pru[slice]); + goto unwind_slices; + } } - ret = icssg_config(prueth, emac, slice); - if (ret) - return ret; - - ret = rproc_set_firmware(prueth->pru[slice], firmwares[slice].pru); - ret = rproc_boot(prueth->pru[slice]); - if (ret) { - dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret); - return -EINVAL; - } - - ret = rproc_set_firmware(prueth->rtu[slice], firmwares[slice].rtu); - ret = rproc_boot(prueth->rtu[slice]); - if (ret) { - dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret); - goto halt_pru; - } - - ret = rproc_set_firmware(prueth->txpru[slice], firmwares[slice].txpru); - ret = rproc_boot(prueth->txpru[slice]); - if (ret) { - dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret); - goto halt_rtu; - } - - emac->fw_running = 1; return 0; -halt_rtu: - rproc_shutdown(prueth->rtu[slice]); - -halt_pru: - rproc_shutdown(prueth->pru[slice]); +unwind_slices: + while (--slice >= 0) { + prueth_shutdown(prueth->txpru[slice]); + prueth_shutdown(prueth->rtu[slice]); + prueth_shutdown(prueth->pru[slice]); + } return ret; } +static void prueth_emac_stop(struct prueth *prueth) +{ + int slice; + + for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { + prueth_shutdown(prueth->txpru[slice]); + prueth_shutdown(prueth->rtu[slice]); + prueth_shutdown(prueth->pru[slice]); + } +} + +static int prueth_emac_common_start(struct prueth *prueth) +{ + struct prueth_emac *emac; + int ret = 0; + int slice; + + if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1]) + return -EINVAL; + + /* clear SMEM and MSMC settings for all slices */ + memset_io(prueth->msmcram.va, 0, prueth->msmcram.size); + memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS); + + icssg_class_default(prueth->miig_rt, ICSS_SLICE0, 0, false); + icssg_class_default(prueth->miig_rt, ICSS_SLICE1, 0, false); + + if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) + icssg_init_fw_offload_mode(prueth); + else + icssg_init_emac_mode(prueth); + + for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { + emac = prueth->emac[slice]; + if (!emac) + continue; + ret = icssg_config(prueth, emac, slice); + if (ret) + goto disable_class; + } + + ret = prueth_emac_start(prueth); + if (ret) + goto disable_class; + + emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] : + prueth->emac[ICSS_SLICE1]; + ret = icss_iep_init(emac->iep, &prueth_iep_clockops, + emac, IEP_DEFAULT_CYCLE_TIME_NS); + if (ret) { + dev_err(prueth->dev, "Failed to initialize IEP module\n"); + goto stop_pruss; + } + + return 0; + +stop_pruss: + prueth_emac_stop(prueth); + +disable_class: + icssg_class_disable(prueth->miig_rt, ICSS_SLICE0); + icssg_class_disable(prueth->miig_rt, ICSS_SLICE1); + + return ret; +} + +static int prueth_emac_common_stop(struct prueth *prueth) +{ + struct prueth_emac *emac; + + if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1]) + return -EINVAL; + + icssg_class_disable(prueth->miig_rt, ICSS_SLICE0); + icssg_class_disable(prueth->miig_rt, ICSS_SLICE1); + + prueth_emac_stop(prueth); + + emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] : + prueth->emac[ICSS_SLICE1]; + icss_iep_exit(emac->iep); + + return 0; +} + /* called back by PHY layer if there is change in link state of hw port*/ static void emac_adjust_link(struct net_device *ndev) { @@ -374,9 +466,6 @@ static void prueth_iep_settime(void *clockops_data, u64 ns) u32 cycletime; int timeout; - if (!emac->fw_running) - return; - sc_descp = emac->prueth->shram.va + TIMESYNC_FW_WC_SETCLOCK_DESC_OFFSET; cycletime = IEP_DEFAULT_CYCLE_TIME_NS; @@ -472,61 +561,134 @@ const struct icss_iep_clockops prueth_iep_clockops = { static int icssg_prueth_add_mcast(struct net_device *ndev, const u8 *addr) { - struct prueth_emac *emac = netdev_priv(ndev); - int port_mask = BIT(emac->port_id); + struct net_device *real_dev; + struct prueth_emac *emac; + int port_mask; + u8 vlan_id; - port_mask |= icssg_fdb_lookup(emac, addr, 0); - icssg_fdb_add_del(emac, addr, 0, port_mask, true); - icssg_vtbl_modify(emac, 0, port_mask, port_mask, true); + vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_MAC; + real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev; + emac = netdev_priv(real_dev); + + port_mask = BIT(emac->port_id) | icssg_fdb_lookup(emac, addr, vlan_id); + icssg_fdb_add_del(emac, addr, vlan_id, port_mask, true); + icssg_vtbl_modify(emac, vlan_id, port_mask, port_mask, true); return 0; } static int icssg_prueth_del_mcast(struct net_device *ndev, const u8 *addr) { - struct prueth_emac *emac = netdev_priv(ndev); - int port_mask = BIT(emac->port_id); + struct net_device *real_dev; + struct prueth_emac *emac; int other_port_mask; + int port_mask; + u8 vlan_id; - other_port_mask = port_mask ^ icssg_fdb_lookup(emac, addr, 0); + vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_MAC; + real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev; + emac = netdev_priv(real_dev); - icssg_fdb_add_del(emac, addr, 0, port_mask, false); - icssg_vtbl_modify(emac, 0, port_mask, port_mask, false); + port_mask = BIT(emac->port_id); + other_port_mask = port_mask ^ icssg_fdb_lookup(emac, addr, vlan_id); + + icssg_fdb_add_del(emac, addr, vlan_id, port_mask, false); + icssg_vtbl_modify(emac, vlan_id, port_mask, port_mask, false); if (other_port_mask) { - icssg_fdb_add_del(emac, addr, 0, other_port_mask, true); - icssg_vtbl_modify(emac, 0, other_port_mask, other_port_mask, true); + icssg_fdb_add_del(emac, addr, vlan_id, other_port_mask, true); + icssg_vtbl_modify(emac, vlan_id, other_port_mask, + other_port_mask, true); } return 0; } -static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) +static void icssg_prueth_hsr_fdb_add_del(struct prueth_emac *emac, + const u8 *addr, u8 vid, bool add) { - struct prueth_emac *emac = netdev_priv(ndev); - struct prueth *prueth = emac->prueth; - - icssg_fdb_add_del(emac, addr, prueth->default_vlan, + icssg_fdb_add_del(emac, addr, vid, ICSSG_FDB_ENTRY_P0_MEMBERSHIP | ICSSG_FDB_ENTRY_P1_MEMBERSHIP | ICSSG_FDB_ENTRY_P2_MEMBERSHIP | - ICSSG_FDB_ENTRY_BLOCK, true); + ICSSG_FDB_ENTRY_BLOCK, add); + + if (add) + icssg_vtbl_modify(emac, vid, BIT(emac->port_id), + BIT(emac->port_id), add); +} + +static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) +{ + struct net_device *real_dev; + struct prueth_emac *emac; + u8 vlan_id, i; + + vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_HSR; + real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev; + + if (is_hsr_master(real_dev)) { + for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) { + emac = netdev_priv(hsr_get_port_ndev(real_dev, i)); + if (!emac) + return -EINVAL; + icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, + true); + } + } else { + emac = netdev_priv(real_dev); + icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, true); + } - icssg_vtbl_modify(emac, emac->port_vlan, BIT(emac->port_id), - BIT(emac->port_id), true); return 0; } static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr) { - struct prueth_emac *emac = netdev_priv(ndev); - struct prueth *prueth = emac->prueth; + struct net_device *real_dev; + struct prueth_emac *emac; + u8 vlan_id, i; - icssg_fdb_add_del(emac, addr, prueth->default_vlan, - ICSSG_FDB_ENTRY_P0_MEMBERSHIP | - ICSSG_FDB_ENTRY_P1_MEMBERSHIP | - ICSSG_FDB_ENTRY_P2_MEMBERSHIP | - ICSSG_FDB_ENTRY_BLOCK, false); + vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_HSR; + real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev; + + if (is_hsr_master(real_dev)) { + for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) { + emac = netdev_priv(hsr_get_port_ndev(real_dev, i)); + if (!emac) + return -EINVAL; + icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, + false); + } + } else { + emac = netdev_priv(real_dev); + icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, false); + } + + return 0; +} + +static int icssg_update_vlan_mcast(struct net_device *vdev, int vid, + void *args) +{ + struct prueth_emac *emac = args; + + if (!vdev || !vid) + return 0; + + netif_addr_lock_bh(vdev); + __hw_addr_sync_multiple(&emac->vlan_mcast_list[vid], &vdev->mc, + vdev->addr_len); + netif_addr_unlock_bh(vdev); + + if (emac->prueth->is_hsr_offload_mode) + __hw_addr_sync_dev(&emac->vlan_mcast_list[vid], vdev, + icssg_prueth_hsr_add_mcast, + icssg_prueth_hsr_del_mcast); + else + __hw_addr_sync_dev(&emac->vlan_mcast_list[vid], vdev, + icssg_prueth_add_mcast, + icssg_prueth_del_mcast); return 0; } @@ -543,23 +705,17 @@ static int emac_ndo_open(struct net_device *ndev) { struct prueth_emac *emac = netdev_priv(ndev); int ret, i, num_data_chn = emac->tx_ch_num; + struct icssg_flow_cfg __iomem *flow_cfg; struct prueth *prueth = emac->prueth; int slice = prueth_emac_slice(emac); struct device *dev = prueth->dev; int max_rx_flows; int rx_flow; - /* clear SMEM and MSMC settings for all slices */ - if (!prueth->emacs_initialized) { - memset_io(prueth->msmcram.va, 0, prueth->msmcram.size); - memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS); - } - /* set h/w MAC as user might have re-configured */ ether_addr_copy(emac->mac_addr, ndev->dev_addr); icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); - icssg_class_default(prueth->miig_rt, slice, 0, false); icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); /* Notify the stack of the actual queue counts. */ @@ -597,18 +753,23 @@ static int emac_ndo_open(struct net_device *ndev) goto cleanup_napi; } - /* reset and start PRU firmware */ - ret = prueth_emac_start(prueth, emac); - if (ret) - goto free_rx_irq; + if (!prueth->emacs_initialized) { + ret = prueth_emac_common_start(prueth); + if (ret) + goto free_rx_irq; + } + + flow_cfg = emac->dram.va + ICSSG_CONFIG_OFFSET + PSI_L_REGULAR_FLOW_ID_BASE_OFFSET; + writew(emac->rx_flow_id_base, &flow_cfg->rx_base_flow); + ret = emac_fdb_flow_id_updated(emac); + + if (ret) { + netdev_err(ndev, "Failed to update Rx Flow ID %d", ret); + goto stop; + } icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu); - if (!prueth->emacs_initialized) { - ret = icss_iep_init(emac->iep, &prueth_iep_clockops, - emac, IEP_DEFAULT_CYCLE_TIME_NS); - } - ret = request_threaded_irq(emac->tx_ts_irq, NULL, prueth_tx_ts_irq, IRQF_ONESHOT, dev_name(dev), emac); if (ret) @@ -653,7 +814,8 @@ reset_rx_chn: free_tx_ts_irq: free_irq(emac->tx_ts_irq, emac); stop: - prueth_emac_stop(emac); + if (!prueth->emacs_initialized) + prueth_emac_common_stop(prueth); free_rx_irq: free_irq(emac->rx_chns.irq[rx_flow], emac); cleanup_napi: @@ -689,8 +851,6 @@ static int emac_ndo_stop(struct net_device *ndev) if (ndev->phydev) phy_stop(ndev->phydev); - icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac)); - if (emac->prueth->is_hsr_offload_mode) __dev_mc_unsync(ndev, icssg_prueth_hsr_del_mcast); else @@ -728,11 +888,9 @@ static int emac_ndo_stop(struct net_device *ndev) /* Destroying the queued work in ndo_stop() */ cancel_delayed_work_sync(&emac->stats_work); - if (prueth->emacs_initialized == 1) - icss_iep_exit(emac->iep); - /* stop PRUs */ - prueth_emac_stop(emac); + if (prueth->emacs_initialized == 1) + prueth_emac_common_stop(prueth); free_irq(emac->tx_ts_irq, emac); @@ -772,12 +930,22 @@ static void emac_ndo_set_rx_mode_work(struct work_struct *work) return; } - if (emac->prueth->is_hsr_offload_mode) + if (emac->prueth->is_hsr_offload_mode) { __dev_mc_sync(ndev, icssg_prueth_hsr_add_mcast, icssg_prueth_hsr_del_mcast); - else + if (rtnl_trylock()) { + vlan_for_each(emac->prueth->hsr_dev, + icssg_update_vlan_mcast, emac); + rtnl_unlock(); + } + } else { __dev_mc_sync(ndev, icssg_prueth_add_mcast, icssg_prueth_del_mcast); + if (rtnl_trylock()) { + vlan_for_each(ndev, icssg_update_vlan_mcast, emac); + rtnl_unlock(); + } + } } /** @@ -822,19 +990,19 @@ static int emac_ndo_vlan_rx_add_vid(struct net_device *ndev, { struct prueth_emac *emac = netdev_priv(ndev); struct prueth *prueth = emac->prueth; + int port_mask = BIT(emac->port_id); int untag_mask = 0; - int port_mask; - if (prueth->is_hsr_offload_mode) { - port_mask = BIT(PRUETH_PORT_HOST) | BIT(emac->port_id); - untag_mask = 0; + if (prueth->is_hsr_offload_mode) + port_mask |= BIT(PRUETH_PORT_HOST); - netdev_dbg(emac->ndev, "VID add vid:%u port_mask:%X untag_mask %X\n", - vid, port_mask, untag_mask); + __hw_addr_init(&emac->vlan_mcast_list[vid]); + netdev_dbg(emac->ndev, "VID add vid:%u port_mask:%X untag_mask %X\n", + vid, port_mask, untag_mask); + + icssg_vtbl_modify(emac, vid, port_mask, untag_mask, true); + icssg_set_pvid(emac->prueth, vid, emac->port_id); - icssg_vtbl_modify(emac, vid, port_mask, untag_mask, true); - icssg_set_pvid(emac->prueth, vid, emac->port_id); - } return 0; } @@ -843,18 +1011,16 @@ static int emac_ndo_vlan_rx_del_vid(struct net_device *ndev, { struct prueth_emac *emac = netdev_priv(ndev); struct prueth *prueth = emac->prueth; + int port_mask = BIT(emac->port_id); int untag_mask = 0; - int port_mask; - if (prueth->is_hsr_offload_mode) { + if (prueth->is_hsr_offload_mode) port_mask = BIT(PRUETH_PORT_HOST); - untag_mask = 0; - netdev_dbg(emac->ndev, "VID del vid:%u port_mask:%X untag_mask %X\n", - vid, port_mask, untag_mask); + netdev_dbg(emac->ndev, "VID del vid:%u port_mask:%X untag_mask %X\n", + vid, port_mask, untag_mask); + icssg_vtbl_modify(emac, vid, port_mask, untag_mask, false); - icssg_vtbl_modify(emac, vid, port_mask, untag_mask, false); - } return 0; } @@ -1053,10 +1219,11 @@ static void prueth_offload_fwd_mark_update(struct prueth *prueth) } } -static void prueth_emac_restart(struct prueth *prueth) +static int prueth_emac_restart(struct prueth *prueth) { struct prueth_emac *emac0 = prueth->emac[PRUETH_MAC0]; struct prueth_emac *emac1 = prueth->emac[PRUETH_MAC1]; + int ret; /* Detach the net_device for both PRUeth ports*/ if (netif_running(emac0->ndev)) @@ -1065,36 +1232,46 @@ static void prueth_emac_restart(struct prueth *prueth) netif_device_detach(emac1->ndev); /* Disable both PRUeth ports */ - icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE); - icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE); + ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE); + ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE); + if (ret) + return ret; /* Stop both pru cores for both PRUeth ports*/ - prueth_emac_stop(emac0); - prueth->emacs_initialized--; - prueth_emac_stop(emac1); - prueth->emacs_initialized--; + ret = prueth_emac_common_stop(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to stop the firmwares"); + return ret; + } /* Start both pru cores for both PRUeth ports */ - prueth_emac_start(prueth, emac0); - prueth->emacs_initialized++; - prueth_emac_start(prueth, emac1); - prueth->emacs_initialized++; + ret = prueth_emac_common_start(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to start the firmwares"); + return ret; + } /* Enable forwarding for both PRUeth ports */ - icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD); - icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD); + ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD); + ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD); /* Attache net_device for both PRUeth ports */ netif_device_attach(emac0->ndev); netif_device_attach(emac1->ndev); + + return ret; } static void icssg_change_mode(struct prueth *prueth) { struct prueth_emac *emac; - int mac; + int mac, ret; - prueth_emac_restart(prueth); + ret = prueth_emac_restart(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process"); + return; + } for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) { emac = prueth->emac[mac]; @@ -1158,7 +1335,7 @@ static int prueth_netdevice_port_link(struct net_device *ndev, if (prueth->br_members & BIT(PRUETH_PORT_MII0) && prueth->br_members & BIT(PRUETH_PORT_MII1)) { prueth->is_switch_mode = true; - prueth->default_vlan = 1; + prueth->default_vlan = PRUETH_DFLT_VLAN_SW; emac->port_vlan = prueth->default_vlan; icssg_change_mode(prueth); } @@ -1173,13 +1350,18 @@ static void prueth_netdevice_port_unlink(struct net_device *ndev) { struct prueth_emac *emac = netdev_priv(ndev); struct prueth *prueth = emac->prueth; + int ret; prueth->br_members &= ~BIT(emac->port_id); if (prueth->is_switch_mode) { prueth->is_switch_mode = false; emac->port_vlan = 0; - prueth_emac_restart(prueth); + ret = prueth_emac_restart(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process"); + return; + } } prueth_offload_fwd_mark_update(prueth); @@ -1211,7 +1393,7 @@ static int prueth_hsr_port_link(struct net_device *ndev) NETIF_PRUETH_HSR_OFFLOAD_FEATURES)) return -EOPNOTSUPP; prueth->is_hsr_offload_mode = true; - prueth->default_vlan = 1; + prueth->default_vlan = PRUETH_DFLT_VLAN_HSR; emac0->port_vlan = prueth->default_vlan; emac1->port_vlan = prueth->default_vlan; icssg_change_mode(prueth); @@ -1228,6 +1410,7 @@ static void prueth_hsr_port_unlink(struct net_device *ndev) struct prueth *prueth = emac->prueth; struct prueth_emac *emac0; struct prueth_emac *emac1; + int ret; emac0 = prueth->emac[PRUETH_MAC0]; emac1 = prueth->emac[PRUETH_MAC1]; @@ -1238,7 +1421,11 @@ static void prueth_hsr_port_unlink(struct net_device *ndev) emac0->port_vlan = 0; emac1->port_vlan = 0; prueth->hsr_dev = NULL; - prueth_emac_restart(prueth); + ret = prueth_emac_restart(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process"); + return; + } netdev_dbg(ndev, "Disabling HSR Offload mode\n"); } } @@ -1413,13 +1600,10 @@ static int prueth_probe(struct platform_device *pdev) prueth->pa_stats = NULL; } - if (eth0_node) { + if (eth0_node || eth1_node) { ret = prueth_get_cores(prueth, ICSS_SLICE0, false); if (ret) goto put_cores; - } - - if (eth1_node) { ret = prueth_get_cores(prueth, ICSS_SLICE1, false); if (ret) goto put_cores; @@ -1618,14 +1802,12 @@ put_pruss: pruss_put(prueth->pruss); put_cores: - if (eth1_node) { - prueth_put_cores(prueth, ICSS_SLICE1); - of_node_put(eth1_node); - } - - if (eth0_node) { + if (eth0_node || eth1_node) { prueth_put_cores(prueth, ICSS_SLICE0); of_node_put(eth0_node); + + prueth_put_cores(prueth, ICSS_SLICE1); + of_node_put(eth1_node); } return ret; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index f5c1d473e9f9..329b46e9ee53 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -83,6 +83,12 @@ #define ICSS_CMD_ADD_FILTER 0x7 #define ICSS_CMD_ADD_MAC 0x8 +/* VLAN Filtering Related MACROs */ +#define PRUETH_DFLT_VLAN_HSR 1 +#define PRUETH_DFLT_VLAN_SW 1 +#define PRUETH_DFLT_VLAN_MAC 0 +#define MAX_VLAN_ID 256 + /* In switch mode there are 3 real ports i.e. 3 mac addrs. * however Linux sees only the host side port. The other 2 ports * are the switch ports. @@ -140,7 +146,6 @@ struct prueth_rx_chn { /* data for each emac port */ struct prueth_emac { bool is_sr1; - bool fw_running; struct prueth *prueth; struct net_device *ndev; u8 mac_addr[6]; @@ -201,6 +206,8 @@ struct prueth_emac { /* RX IRQ Coalescing Related */ struct hrtimer rx_hrtimer; unsigned long rx_pace_timeout_ns; + + struct netdev_hw_addr_list vlan_mcast_list[MAX_VLAN_ID]; }; /** @@ -361,6 +368,8 @@ int icssg_set_port_state(struct prueth_emac *emac, enum icssg_port_state_cmd state); void icssg_config_set_speed(struct prueth_emac *emac); void icssg_config_half_duplex(struct prueth_emac *emac); +void icssg_init_emac_mode(struct prueth *prueth); +void icssg_init_fw_offload_mode(struct prueth *prueth); /* Buffer queue helpers */ int icssg_queue_pop(struct prueth *prueth, u8 queue); @@ -377,6 +386,7 @@ void icssg_vtbl_modify(struct prueth_emac *emac, u8 vid, u8 port_mask, u8 untag_mask, bool add); u16 icssg_get_pvid(struct prueth_emac *emac); void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port); +int emac_fdb_flow_id_updated(struct prueth_emac *emac); #define prueth_napi_to_tx_chn(pnapi) \ container_of(pnapi, struct prueth_tx_chn, napi_tx) @@ -407,7 +417,6 @@ void emac_rx_timestamp(struct prueth_emac *emac, struct sk_buff *skb, u32 *psdata); enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev); irqreturn_t prueth_rx_irq(int irq, void *dev_id); -void prueth_emac_stop(struct prueth_emac *emac); void prueth_cleanup_tx_ts(struct prueth_emac *emac); int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget); int prueth_prepare_rx_chan(struct prueth_emac *emac, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index 5024f0647a0d..64a19ff39562 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -440,7 +440,6 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) goto halt_pru; } - emac->fw_running = 1; return 0; halt_pru: @@ -449,6 +448,29 @@ halt_pru: return ret; } +static void prueth_emac_stop(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + int slice; + + switch (emac->port_id) { + case PRUETH_PORT_MII0: + slice = ICSS_SLICE0; + break; + case PRUETH_PORT_MII1: + slice = ICSS_SLICE1; + break; + default: + netdev_err(emac->ndev, "invalid port\n"); + return; + } + + if (!emac->is_sr1) + rproc_shutdown(prueth->txpru[slice]); + rproc_shutdown(prueth->rtu[slice]); + rproc_shutdown(prueth->pru[slice]); +} + /** * emac_ndo_open - EMAC device open * @ndev: network adapter device @@ -1009,8 +1031,6 @@ static int prueth_probe(struct platform_device *pdev) (unsigned long)prueth->msmcram.va); prueth->msmcram.size = msmc_ram_size; memset_io(prueth->msmcram.va, 0, msmc_ram_size); - dev_dbg(dev, "sram: pa %llx va %p size %zx\n", prueth->msmcram.pa, - prueth->msmcram.va, prueth->msmcram.size); prueth->iep0 = icss_iep_get_idx(np, 0); if (IS_ERR(prueth->iep0)) { diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 894911f3d560..e56ebbdd428d 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -1568,7 +1568,7 @@ static void init_registers(struct net_device *dev) if (rp->quirks & rqMgmt) rhine_init_cam_filter(dev); - napi_enable(&rp->napi); + napi_enable_locked(&rp->napi); iowrite16(RHINE_EVENT & 0xffff, ioaddr + IntrEnable); @@ -1696,7 +1696,10 @@ static int rhine_open(struct net_device *dev) rhine_power_init(dev); rhine_chip_reset(dev); rhine_task_enable(rp); + + netdev_lock(dev); init_registers(dev); + netdev_unlock(dev); netif_dbg(rp, ifup, dev, "%s() Done - status %04x MII status: %04x\n", __func__, ioread16(ioaddr + ChipCmd), @@ -1727,6 +1730,8 @@ static void rhine_reset_task(struct work_struct *work) napi_disable(&rp->napi); netif_tx_disable(dev); + + netdev_lock(dev); spin_lock_bh(&rp->lock); /* clear all descriptors */ @@ -1740,6 +1745,7 @@ static void rhine_reset_task(struct work_struct *work) init_registers(dev); spin_unlock_bh(&rp->lock); + netdev_unlock(dev); netif_trans_update(dev); /* prevent tx timeout */ dev->stats.tx_errors++; @@ -2541,9 +2547,12 @@ static int rhine_resume(struct device *device) alloc_tbufs(dev); rhine_reset_rbufs(rp); rhine_task_enable(rp); + + netdev_lock(dev); spin_lock_bh(&rp->lock); init_registers(dev); spin_unlock_bh(&rp->lock); + netdev_unlock(dev); netif_device_attach(dev); diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index dd4a07c97eee..5aa93144a4f5 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -2320,7 +2320,8 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu) if (ret < 0) goto out_free_tmp_vptr_1; - napi_disable(&vptr->napi); + netdev_lock(dev); + napi_disable_locked(&vptr->napi); spin_lock_irqsave(&vptr->lock, flags); @@ -2342,12 +2343,13 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu) velocity_give_many_rx_descs(vptr); - napi_enable(&vptr->napi); + napi_enable_locked(&vptr->napi); mac_enable_int(vptr->mac_regs); netif_start_queue(dev); spin_unlock_irqrestore(&vptr->lock, flags); + netdev_unlock(dev); velocity_free_rings(tmp_vptr); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 1bf9c38e4125..deaf670c160e 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -334,27 +334,25 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer, status = read_poll_timeout(rd32, hicr, hicr & WX_MNG_MBOX_CTL_FWRDY, 1000, timeout * 1000, false, wx, WX_MNG_MBOX_CTL); + buf[0] = rd32(wx, WX_MNG_MBOX); + if ((buf[0] & 0xff0000) >> 16 == 0x80) { + wx_err(wx, "Unknown FW command: 0x%x\n", buffer[0] & 0xff); + status = -EINVAL; + goto rel_out; + } + /* Check command completion */ if (status) { - wx_dbg(wx, "Command has failed with no status valid.\n"); - - buf[0] = rd32(wx, WX_MNG_MBOX); - if ((buffer[0] & 0xff) != (~buf[0] >> 24)) { - status = -EINVAL; - goto rel_out; - } - if ((buf[0] & 0xff0000) >> 16 == 0x80) { - wx_dbg(wx, "It's unknown cmd.\n"); - status = -EINVAL; - goto rel_out; - } - + wx_err(wx, "Command has failed with no status valid.\n"); wx_dbg(wx, "write value:\n"); for (i = 0; i < dword_len; i++) wx_dbg(wx, "%x ", buffer[i]); wx_dbg(wx, "read value:\n"); for (i = 0; i < dword_len; i++) wx_dbg(wx, "%x ", buf[i]); + wx_dbg(wx, "\ncheck: %x %x\n", buffer[0] & 0xff, ~buf[0] >> 24); + + goto rel_out; } if (!return_data) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index d64b8abcf018..a3f4f3e42587 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -120,6 +120,9 @@ #define XAXIDMA_IRQ_ERROR_MASK 0x00004000 /* Error interrupt */ #define XAXIDMA_IRQ_ALL_MASK 0x00007000 /* All interrupts */ +/* Constant to convert delay counts to microseconds */ +#define XAXIDMA_DELAY_SCALE (125ULL * USEC_PER_SEC) + /* Default TX/RX Threshold and delay timer values for SGDMA mode */ #define XAXIDMA_DFT_TX_THRESHOLD 24 #define XAXIDMA_DFT_TX_USEC 50 diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 0f4b02fe6f85..9e7fa012e4fa 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -238,11 +238,8 @@ static u32 axienet_usec_to_timer(struct axienet_local *lp, u32 coalesce_usec) /* 1 Timeout Interval = 125 * (clock period of SG clock) */ result = DIV64_U64_ROUND_CLOSEST((u64)coalesce_usec * clk_rate, - (u64)125000000); - if (result > 255) - result = 255; - - return result; + XAXIDMA_DELAY_SCALE); + return min(result, FIELD_MAX(XAXIDMA_DELAY_MASK)); } /** @@ -2056,14 +2053,31 @@ axienet_ethtools_set_coalesce(struct net_device *ndev, return -EBUSY; } - if (ecoalesce->rx_max_coalesced_frames) - lp->coalesce_count_rx = ecoalesce->rx_max_coalesced_frames; - if (ecoalesce->rx_coalesce_usecs) - lp->coalesce_usec_rx = ecoalesce->rx_coalesce_usecs; - if (ecoalesce->tx_max_coalesced_frames) - lp->coalesce_count_tx = ecoalesce->tx_max_coalesced_frames; - if (ecoalesce->tx_coalesce_usecs) - lp->coalesce_usec_tx = ecoalesce->tx_coalesce_usecs; + if (ecoalesce->rx_max_coalesced_frames > 255 || + ecoalesce->tx_max_coalesced_frames > 255) { + NL_SET_ERR_MSG(extack, "frames must be less than 256"); + return -EINVAL; + } + + if (!ecoalesce->rx_max_coalesced_frames || + !ecoalesce->tx_max_coalesced_frames) { + NL_SET_ERR_MSG(extack, "frames must be non-zero"); + return -EINVAL; + } + + if ((ecoalesce->rx_max_coalesced_frames > 1 && + !ecoalesce->rx_coalesce_usecs) || + (ecoalesce->tx_max_coalesced_frames > 1 && + !ecoalesce->tx_coalesce_usecs)) { + NL_SET_ERR_MSG(extack, + "usecs must be non-zero when frames is greater than one"); + return -EINVAL; + } + + lp->coalesce_count_rx = ecoalesce->rx_max_coalesced_frames; + lp->coalesce_usec_rx = ecoalesce->rx_coalesce_usecs; + lp->coalesce_count_tx = ecoalesce->tx_max_coalesced_frames; + lp->coalesce_usec_tx = ecoalesce->tx_coalesce_usecs; return 0; } @@ -2331,11 +2345,12 @@ static struct axienet_local *pcs_to_axienet_local(struct phylink_pcs *pcs) } static void axienet_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy; - phylink_mii_c22_pcs_get_state(pcs_phy, state); + phylink_mii_c22_pcs_get_state(pcs_phy, neg_mode, state); } static void axienet_pcs_an_restart(struct phylink_pcs *pcs) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index bc658bc60885..642155cb8315 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -235,7 +235,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, vni_to_tunnel_id(gnvh->vni), gnvh->opt_len * 4); if (!tun_dst) { - DEV_STATS_INC(geneve->dev, rx_dropped); + dev_dstats_rx_dropped(geneve->dev); goto drop; } /* Update tunnel dst according to Geneve options. */ @@ -322,7 +322,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, len = skb->len; err = gro_cells_receive(&geneve->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) - dev_sw_netstats_rx_add(geneve->dev, len); + dev_dstats_rx_add(geneve->dev, len); return; drop: @@ -387,14 +387,14 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (unlikely((!geneve->cfg.inner_proto_inherit && inner_proto != htons(ETH_P_TEB)))) { - DEV_STATS_INC(geneve->dev, rx_dropped); + dev_dstats_rx_dropped(geneve->dev); goto drop; } opts_len = geneveh->opt_len * 4; if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, inner_proto, !net_eq(geneve->net, dev_net(geneve->dev)))) { - DEV_STATS_INC(geneve->dev, rx_dropped); + dev_dstats_rx_dropped(geneve->dev); goto drop; } @@ -1023,7 +1023,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { netdev_dbg(dev, "no tunnel metadata\n"); dev_kfree_skb(skb); - DEV_STATS_INC(dev, tx_dropped); + dev_dstats_tx_dropped(dev); return NETDEV_TX_OK; } } else { @@ -1202,7 +1202,7 @@ static void geneve_setup(struct net_device *dev) dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; - dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; /* MTU range: 68 - (something less than 65535) */ dev->min_mtu = ETH_MIN_MTU; /* The max_mtu calculation does not take account of GENEVE diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 89a996ad8cd0..d64740bf44ed 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -23,6 +23,8 @@ #include #include +#include +#include #include #include #include @@ -350,7 +352,7 @@ static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, fl4->flowi4_oif = sk->sk_bound_dev_if; fl4->daddr = daddr; fl4->saddr = saddr; - fl4->flowi4_tos = ip_sock_rt_tos(sk); + fl4->flowi4_tos = inet_dscp_to_dsfield(inet_sk_dscp(inet_sk(sk))); fl4->flowi4_scope = ip_sock_rt_scope(sk); fl4->flowi4_proto = sk->sk_protocol; @@ -1524,8 +1526,8 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, goto out_encap; } - gn = net_generic(dev_net(dev), gtp_net_id); - list_add_rcu(>p->list, &gn->gtp_dev_list); + gn = net_generic(src_net, gtp_net_id); + list_add(>p->list, &gn->gtp_dev_list); dev->priv_destructor = gtp_destructor; netdev_dbg(dev, "registered new GTP interface\n"); @@ -1551,7 +1553,7 @@ static void gtp_dellink(struct net_device *dev, struct list_head *head) hlist_for_each_entry_safe(pctx, next, >p->tid_hash[i], hlist_tid) pdp_context_delete(pctx); - list_del_rcu(>p->list); + list_del(>p->list); unregister_netdevice_queue(dev, head); } @@ -2271,16 +2273,19 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb, struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp; int i, j, bucket = cb->args[0], skip = cb->args[1]; struct net *net = sock_net(skb->sk); + struct net_device *dev; struct pdp_ctx *pctx; - struct gtp_net *gn; - - gn = net_generic(net, gtp_net_id); if (cb->args[4]) return 0; rcu_read_lock(); - list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) { + for_each_netdev_rcu(net, dev) { + if (dev->rtnl_link_ops != >p_link_ops) + continue; + + gtp = netdev_priv(dev); + if (last_gtp && last_gtp != gtp) continue; else @@ -2475,9 +2480,14 @@ static void __net_exit gtp_net_exit_batch_rtnl(struct list_head *net_list, list_for_each_entry(net, net_list, exit_list) { struct gtp_net *gn = net_generic(net, gtp_net_id); - struct gtp_dev *gtp; + struct gtp_dev *gtp, *gtp_next; + struct net_device *dev; - list_for_each_entry(gtp, &gn->gtp_dev_list, list) + for_each_netdev(net, dev) + if (dev->rtnl_link_ops == >p_link_ops) + gtp_dellink(dev, dev_to_kill); + + list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list) gtp_dellink(gtp->dev, dev_to_kill); } } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index e690b95b1bbb..234db693cefa 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -464,7 +464,7 @@ struct nvsp_1_message_send_receive_buffer_complete { * LargeOffset SmallOffset */ - struct nvsp_1_receive_buffer_section sections[1]; + struct nvsp_1_receive_buffer_section sections[]; } __packed; /* diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 9afb08dbc350..d6f5b9ea3109 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -866,7 +866,8 @@ static void netvsc_send_completion(struct net_device *ndev, case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE: if (msglen < sizeof(struct nvsp_message_header) + - sizeof(struct nvsp_1_message_send_receive_buffer_complete)) { + struct_size_t(struct nvsp_1_message_send_receive_buffer_complete, + sections, 1)) { netdev_err(ndev, "nvsp_msg1 length too small: %u\n", msglen); return; diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index e685a7f946f0..753215ebc67c 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -3072,7 +3072,11 @@ static int ca8210_probe(struct spi_device *spi_device) spi_set_drvdata(priv->spi, priv); if (IS_ENABLED(CONFIG_IEEE802154_CA8210_DEBUGFS)) { cascoda_api_upstream = ca8210_test_int_driver_write; - ca8210_test_interface_init(priv); + ret = ca8210_test_interface_init(priv); + if (ret) { + dev_crit(&spi_device->dev, "ca8210_test_interface_init failed\n"); + goto error; + } } else { cascoda_api_upstream = NULL; } diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index ee2c3cf4df36..da3a97a65507 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -799,6 +799,12 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; + + case NETDEV_NOTIFY_PEERS: + case NETDEV_BONDING_FAILOVER: + case NETDEV_RESEND_IGMP: + list_for_each_entry(ipvlan, &port->ipvlans, pnode) + call_netdevice_notifiers(event, ipvlan->dev); } return NOTIFY_DONE; } diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 1993b90b1a5f..c8840c3b9a1b 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -264,13 +264,12 @@ static int __init blackhole_netdev_init(void) if (!blackhole_netdev) return -ENOMEM; - rtnl_lock(); + rtnl_net_lock(&init_net); dev_init_scheduler(blackhole_netdev); dev_activate(blackhole_netdev); - rtnl_unlock(); + rtnl_net_unlock(&init_net); blackhole_netdev->flags |= IFF_UP | IFF_RUNNING; - dev_net_set(blackhole_netdev, &init_net); return 0; } diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index d2b3f5a59141..e3dcdeacc12c 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -177,8 +177,7 @@ static struct mctp_i2c_client *mctp_i2c_new_client(struct i2c_client *client) return mcli; err: if (mcli) { - if (mcli->client) - i2c_unregister_device(mcli->client); + i2c_unregister_device(mcli->client); kfree(mcli); } return ERR_PTR(rc); diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c index 9adad59b8676..d247fe483c58 100644 --- a/drivers/net/mctp/mctp-i3c.c +++ b/drivers/net/mctp/mctp-i3c.c @@ -125,6 +125,8 @@ static int mctp_i3c_read(struct mctp_i3c_device *mi) xfer.data.in = skb_put(skb, mi->mrl); + /* Make sure netif_rx() is read in the same order as i3c. */ + mutex_lock(&mi->lock); rc = i3c_device_do_priv_xfers(mi->i3c, &xfer, 1); if (rc < 0) goto err; @@ -166,8 +168,10 @@ static int mctp_i3c_read(struct mctp_i3c_device *mi) stats->rx_dropped++; } + mutex_unlock(&mi->lock); return 0; err: + mutex_unlock(&mi->lock); kfree_skb(skb); return rc; } diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index b156493d7084..aea0f0357568 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -40,6 +40,7 @@ fwnode_find_pse_control(struct fwnode_handle *fwnode) static struct mii_timestamper * fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) { + struct mii_timestamper *mii_ts; struct of_phandle_args arg; int err; @@ -53,10 +54,16 @@ fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) else if (err) return ERR_PTR(err); - if (arg.args_count != 1) - return ERR_PTR(-EINVAL); + if (arg.args_count != 1) { + mii_ts = ERR_PTR(-EINVAL); + goto put_node; + } - return register_mii_timestamper(arg.np, arg.args[0]); + mii_ts = register_mii_timestamper(arg.np, arg.args[0]); + +put_node: + of_node_put(arg.np); + return mii_ts; } int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, diff --git a/drivers/net/mdio/mdio-octeon.c b/drivers/net/mdio/mdio-octeon.c index 2beb83154d39..cb53dccbde1a 100644 --- a/drivers/net/mdio/mdio-octeon.c +++ b/drivers/net/mdio/mdio-octeon.c @@ -17,37 +17,20 @@ static int octeon_mdiobus_probe(struct platform_device *pdev) { struct cavium_mdiobus *bus; struct mii_bus *mii_bus; - struct resource *res_mem; - resource_size_t mdio_phys; - resource_size_t regsize; union cvmx_smix_en smi_en; - int err = -ENOENT; + int err; mii_bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*bus)); if (!mii_bus) return -ENOMEM; - res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res_mem == NULL) { - dev_err(&pdev->dev, "found no memory resource\n"); - return -ENXIO; - } - bus = mii_bus->priv; bus->mii_bus = mii_bus; - mdio_phys = res_mem->start; - regsize = resource_size(res_mem); - if (!devm_request_mem_region(&pdev->dev, mdio_phys, regsize, - res_mem->name)) { - dev_err(&pdev->dev, "request_mem_region failed\n"); - return -ENXIO; - } - - bus->register_base = devm_ioremap(&pdev->dev, mdio_phys, regsize); - if (!bus->register_base) { + bus->register_base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(bus->register_base)) { dev_err(&pdev->dev, "dev_ioremap failed\n"); - return -ENOMEM; + return PTR_ERR(bus->register_base); } smi_en.u64 = 0; diff --git a/drivers/net/mii.c b/drivers/net/mii.c index 22680f47385d..37bc3131d31a 100644 --- a/drivers/net/mii.c +++ b/drivers/net/mii.c @@ -213,6 +213,9 @@ void mii_ethtool_get_link_ksettings(struct mii_if_info *mii, lp_advertising = 0; } + if (!(bmsr & BMSR_LSTATUS)) + cmd->base.speed = SPEED_UNKNOWN; + mii->full_duplex = cmd->base.duplex; ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 4ea44a2f48f7..86ab4a42769a 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include @@ -90,6 +91,12 @@ static DEFINE_MUTEX(target_cleanup_list_lock); */ static struct console netconsole_ext; +struct netconsole_target_stats { + u64_stats_t xmit_drop_count; + u64_stats_t enomem_count; + struct u64_stats_sync syncp; +}; + /** * struct netconsole_target - Represents a configured netconsole target. * @list: Links this target into the target_list. @@ -97,6 +104,7 @@ static struct console netconsole_ext; * @userdata_group: Links to the userdata configfs hierarchy * @userdata_complete: Cached, formatted string of append * @userdata_length: String length of userdata_complete + * @stats: Packet send stats for the target. Used for debugging. * @enabled: On / off knob to enable / disable target. * Visible from userspace (read-write). * We maintain a strict 1:1 correspondence between this and @@ -124,6 +132,7 @@ struct netconsole_target { char userdata_complete[MAX_USERDATA_ENTRY_LENGTH * MAX_USERDATA_ITEMS]; size_t userdata_length; #endif + struct netconsole_target_stats stats; bool enabled; bool extended; bool release; @@ -262,6 +271,7 @@ static void netconsole_process_cleanups_core(void) * | remote_ip * | local_mac * | remote_mac + * | transmit_errors * | userdata/ * | / * | value @@ -371,6 +381,21 @@ static ssize_t remote_mac_show(struct config_item *item, char *buf) return sysfs_emit(buf, "%pM\n", to_target(item)->np.remote_mac); } +static ssize_t transmit_errors_show(struct config_item *item, char *buf) +{ + struct netconsole_target *nt = to_target(item); + u64 xmit_drop_count, enomem_count; + unsigned int start; + + do { + start = u64_stats_fetch_begin(&nt->stats.syncp); + xmit_drop_count = u64_stats_read(&nt->stats.xmit_drop_count); + enomem_count = u64_stats_read(&nt->stats.enomem_count); + } while (u64_stats_fetch_retry(&nt->stats.syncp, start)); + + return sysfs_emit(buf, "%llu\n", xmit_drop_count + enomem_count); +} + /* * This one is special -- targets created through the configfs interface * are not enabled (and the corresponding netpoll activated) by default. @@ -705,7 +730,7 @@ static void update_userdata(struct netconsole_target *nt) struct userdatum *udm_item; struct config_item *item; - if (child_count >= MAX_USERDATA_ITEMS) + if (WARN_ON_ONCE(child_count >= MAX_USERDATA_ITEMS)) break; child_count++; @@ -842,6 +867,7 @@ CONFIGFS_ATTR(, remote_ip); CONFIGFS_ATTR_RO(, local_mac); CONFIGFS_ATTR(, remote_mac); CONFIGFS_ATTR(, release); +CONFIGFS_ATTR_RO(, transmit_errors); static struct configfs_attribute *netconsole_target_attrs[] = { &attr_enabled, @@ -854,6 +880,7 @@ static struct configfs_attribute *netconsole_target_attrs[] = { &attr_remote_ip, &attr_local_mac, &attr_remote_mac, + &attr_transmit_errors, NULL, }; @@ -1058,6 +1085,33 @@ static struct notifier_block netconsole_netdev_notifier = { .notifier_call = netconsole_netdev_event, }; +/** + * send_udp - Wrapper for netpoll_send_udp that counts errors + * @nt: target to send message to + * @msg: message to send + * @len: length of message + * + * Calls netpoll_send_udp and classifies the return value. If an error + * occurred it increments statistics in nt->stats accordingly. + * Only calls netpoll_send_udp if CONFIG_NETCONSOLE_DYNAMIC is disabled. + */ +static void send_udp(struct netconsole_target *nt, const char *msg, int len) +{ + int result = netpoll_send_udp(&nt->np, msg, len); + + if (IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) { + if (result == NET_XMIT_DROP) { + u64_stats_update_begin(&nt->stats.syncp); + u64_stats_inc(&nt->stats.xmit_drop_count); + u64_stats_update_end(&nt->stats.syncp); + } else if (result == -ENOMEM) { + u64_stats_update_begin(&nt->stats.syncp); + u64_stats_inc(&nt->stats.enomem_count); + u64_stats_update_end(&nt->stats.syncp); + } + } +} + static void send_msg_no_fragmentation(struct netconsole_target *nt, const char *msg, int msg_len, @@ -1085,7 +1139,7 @@ static void send_msg_no_fragmentation(struct netconsole_target *nt, MAX_PRINT_CHUNK - msg_len, "%s", userdata); - netpoll_send_udp(&nt->np, buf, msg_len); + send_udp(nt, buf, msg_len); } static void append_release(char *buf) @@ -1178,7 +1232,7 @@ static void send_fragmented_body(struct netconsole_target *nt, char *buf, this_offset += this_chunk; } - netpoll_send_udp(&nt->np, buf, this_header + this_offset); + send_udp(nt, buf, this_header + this_offset); offset += this_offset; } } @@ -1288,7 +1342,7 @@ static void write_msg(struct console *con, const char *msg, unsigned int len) tmp = msg; for (left = len; left;) { frag = min(left, MAX_PRINT_CHUNK); - netpoll_send_udp(&nt->np, tmp, frag); + send_udp(nt, tmp, frag); tmp += frag; left -= frag; } diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index 5fe1eaef99b5..5c80fbee7913 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -2,8 +2,8 @@ // Copyright (c) 2020 Facebook #include -#include #include +#include #include "netdevsim.h" @@ -72,6 +72,10 @@ static void nsim_get_ringparam(struct net_device *dev, struct netdevsim *ns = netdev_priv(dev); memcpy(ring, &ns->ethtool.ring, sizeof(ns->ethtool.ring)); + kernel_ring->hds_thresh_max = NSIM_HDS_THRESHOLD_MAX; + + if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN) + kernel_ring->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED; } static int nsim_set_ringparam(struct net_device *dev, @@ -103,10 +107,10 @@ nsim_set_channels(struct net_device *dev, struct ethtool_channels *ch) struct netdevsim *ns = netdev_priv(dev); int err; - mutex_lock(&dev->lock); + netdev_lock(dev); err = netif_set_real_num_queues(dev, ch->combined_count, ch->combined_count); - mutex_unlock(&dev->lock); + netdev_unlock(dev); if (err) return err; @@ -161,6 +165,8 @@ static int nsim_get_ts_info(struct net_device *dev, static const struct ethtool_ops nsim_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_ALL_PARAMS, + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT | + ETHTOOL_RING_USE_HDS_THRS, .get_pause_stats = nsim_get_pause_stats, .get_pauseparam = nsim_get_pauseparam, .set_pauseparam = nsim_set_pauseparam, diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index 70e8bdf34be9..688f05316b5e 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -149,6 +149,8 @@ static ssize_t nsim_dev_health_break_write(struct file *file, char *break_msg; int err; + if (count == 0 || count > PAGE_SIZE) + return -EINVAL; break_msg = memdup_user_nul(data, count); if (IS_ERR(break_msg)) return PTR_ERR(break_msg); diff --git a/drivers/net/netdevsim/hwstats.c b/drivers/net/netdevsim/hwstats.c index 0e58aa7f0374..66b3215db3ac 100644 --- a/drivers/net/netdevsim/hwstats.c +++ b/drivers/net/netdevsim/hwstats.c @@ -331,7 +331,6 @@ enum nsim_dev_hwstats_do { }; struct nsim_dev_hwstats_fops { - const struct file_operations fops; enum nsim_dev_hwstats_do action; enum netdev_offload_xstats_type type; }; @@ -342,13 +341,12 @@ nsim_dev_hwstats_do_write(struct file *file, size_t count, loff_t *ppos) { struct nsim_dev_hwstats *hwstats = file->private_data; - struct nsim_dev_hwstats_fops *hwsfops; + const struct nsim_dev_hwstats_fops *hwsfops; struct list_head *hwsdev_list; int ifindex; int err; - hwsfops = container_of(debugfs_real_fops(file), - struct nsim_dev_hwstats_fops, fops); + hwsfops = debugfs_get_aux(file); err = kstrtoint_from_user(data, count, 0, &ifindex); if (err) @@ -381,14 +379,13 @@ nsim_dev_hwstats_do_write(struct file *file, return count; } +static struct debugfs_short_fops debugfs_ops = { + .write = nsim_dev_hwstats_do_write, + .llseek = generic_file_llseek, +}; + #define NSIM_DEV_HWSTATS_FOPS(ACTION, TYPE) \ { \ - .fops = { \ - .open = simple_open, \ - .write = nsim_dev_hwstats_do_write, \ - .llseek = generic_file_llseek, \ - .owner = THIS_MODULE, \ - }, \ .action = ACTION, \ .type = TYPE, \ } @@ -433,12 +430,12 @@ int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev) goto err_remove_hwstats_recursive; } - debugfs_create_file("enable_ifindex", 0200, hwstats->l3_ddir, hwstats, - &nsim_dev_hwstats_l3_enable_fops.fops); - debugfs_create_file("disable_ifindex", 0200, hwstats->l3_ddir, hwstats, - &nsim_dev_hwstats_l3_disable_fops.fops); - debugfs_create_file("fail_next_enable", 0200, hwstats->l3_ddir, hwstats, - &nsim_dev_hwstats_l3_fail_fops.fops); + debugfs_create_file_aux("enable_ifindex", 0200, hwstats->l3_ddir, hwstats, + &nsim_dev_hwstats_l3_enable_fops, &debugfs_ops); + debugfs_create_file_aux("disable_ifindex", 0200, hwstats->l3_ddir, hwstats, + &nsim_dev_hwstats_l3_disable_fops, &debugfs_ops); + debugfs_create_file_aux("fail_next_enable", 0200, hwstats->l3_ddir, hwstats, + &nsim_dev_hwstats_l3_fail_fops, &debugfs_ops); INIT_DELAYED_WORK(&hwstats->traffic_dw, &nsim_dev_hwstats_traffic_work); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 0be47fed4efc..42f247cbdcee 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -15,11 +15,13 @@ #include #include +#include #include #include #include #include #include +#include #include #include #include @@ -29,6 +31,8 @@ #include "netdevsim.h" +MODULE_IMPORT_NS("NETDEV_INTERNAL"); + #define NSIM_RING_SIZE 256 static int nsim_napi_rx(struct nsim_rq *rq, struct sk_buff *skb) @@ -54,6 +58,7 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev) struct net_device *peer_dev; unsigned int len = skb->len; struct netdevsim *peer_ns; + struct netdev_config *cfg; struct nsim_rq *rq; int rxq; @@ -69,7 +74,14 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev) rxq = skb_get_queue_mapping(skb); if (rxq >= peer_dev->num_rx_queues) rxq = rxq % peer_dev->num_rx_queues; - rq = &peer_ns->rq[rxq]; + rq = peer_ns->rq[rxq]; + + cfg = peer_dev->cfg; + if (skb_is_nonlinear(skb) && + (cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED || + (cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + cfg->hds_thresh > len))) + skb_linearize(skb); skb_tx_timestamp(skb); if (unlikely(nsim_forward_skb(peer_dev, skb, rq) == NET_RX_DROP)) @@ -359,25 +371,24 @@ static int nsim_poll(struct napi_struct *napi, int budget) return done; } -static int nsim_create_page_pool(struct nsim_rq *rq) +static int nsim_create_page_pool(struct page_pool **p, struct napi_struct *napi) { - struct page_pool_params p = { + struct page_pool_params params = { .order = 0, .pool_size = NSIM_RING_SIZE, .nid = NUMA_NO_NODE, - .dev = &rq->napi.dev->dev, - .napi = &rq->napi, + .dev = &napi->dev->dev, + .napi = napi, .dma_dir = DMA_BIDIRECTIONAL, - .netdev = rq->napi.dev, + .netdev = napi->dev, }; + struct page_pool *pool; - rq->page_pool = page_pool_create(&p); - if (IS_ERR(rq->page_pool)) { - int err = PTR_ERR(rq->page_pool); + pool = page_pool_create(¶ms); + if (IS_ERR(pool)) + return PTR_ERR(pool); - rq->page_pool = NULL; - return err; - } + *p = pool; return 0; } @@ -388,15 +399,15 @@ static int nsim_init_napi(struct netdevsim *ns) int err, i; for (i = 0; i < dev->num_rx_queues; i++) { - rq = &ns->rq[i]; + rq = ns->rq[i]; - netif_napi_add(dev, &rq->napi, nsim_poll); + netif_napi_add_config(dev, &rq->napi, nsim_poll, i); } for (i = 0; i < dev->num_rx_queues; i++) { - rq = &ns->rq[i]; + rq = ns->rq[i]; - err = nsim_create_page_pool(rq); + err = nsim_create_page_pool(&rq->page_pool, &rq->napi); if (err) goto err_pp_destroy; } @@ -405,12 +416,12 @@ static int nsim_init_napi(struct netdevsim *ns) err_pp_destroy: while (i--) { - page_pool_destroy(ns->rq[i].page_pool); - ns->rq[i].page_pool = NULL; + page_pool_destroy(ns->rq[i]->page_pool); + ns->rq[i]->page_pool = NULL; } for (i = 0; i < dev->num_rx_queues; i++) - __netif_napi_del(&ns->rq[i].napi); + __netif_napi_del(&ns->rq[i]->napi); return err; } @@ -421,7 +432,7 @@ static void nsim_enable_napi(struct netdevsim *ns) int i; for (i = 0; i < dev->num_rx_queues; i++) { - struct nsim_rq *rq = &ns->rq[i]; + struct nsim_rq *rq = ns->rq[i]; netif_queue_set_napi(dev, i, NETDEV_QUEUE_TYPE_RX, &rq->napi); napi_enable(&rq->napi); @@ -448,7 +459,7 @@ static void nsim_del_napi(struct netdevsim *ns) int i; for (i = 0; i < dev->num_rx_queues; i++) { - struct nsim_rq *rq = &ns->rq[i]; + struct nsim_rq *rq = ns->rq[i]; napi_disable(&rq->napi); __netif_napi_del(&rq->napi); @@ -456,8 +467,8 @@ static void nsim_del_napi(struct netdevsim *ns) synchronize_net(); for (i = 0; i < dev->num_rx_queues; i++) { - page_pool_destroy(ns->rq[i].page_pool); - ns->rq[i].page_pool = NULL; + page_pool_destroy(ns->rq[i]->page_pool); + ns->rq[i]->page_pool = NULL; } } @@ -595,6 +606,182 @@ static const struct netdev_stat_ops nsim_stat_ops = { .get_base_stats = nsim_get_base_stats, }; +static struct nsim_rq *nsim_queue_alloc(void) +{ + struct nsim_rq *rq; + + rq = kzalloc(sizeof(*rq), GFP_KERNEL_ACCOUNT); + if (!rq) + return NULL; + + skb_queue_head_init(&rq->skb_queue); + return rq; +} + +static void nsim_queue_free(struct nsim_rq *rq) +{ + skb_queue_purge_reason(&rq->skb_queue, SKB_DROP_REASON_QUEUE_PURGE); + kfree(rq); +} + +/* Queue reset mode is controlled by ns->rq_reset_mode. + * - normal - new NAPI new pool (old NAPI enabled when new added) + * - mode 1 - allocate new pool (NAPI is only disabled / enabled) + * - mode 2 - new NAPI new pool (old NAPI removed before new added) + * - mode 3 - new NAPI new pool (old NAPI disabled when new added) + */ +struct nsim_queue_mem { + struct nsim_rq *rq; + struct page_pool *pp; +}; + +static int +nsim_queue_mem_alloc(struct net_device *dev, void *per_queue_mem, int idx) +{ + struct nsim_queue_mem *qmem = per_queue_mem; + struct netdevsim *ns = netdev_priv(dev); + int err; + + if (ns->rq_reset_mode > 3) + return -EINVAL; + + if (ns->rq_reset_mode == 1) + return nsim_create_page_pool(&qmem->pp, &ns->rq[idx]->napi); + + qmem->rq = nsim_queue_alloc(); + if (!qmem->rq) + return -ENOMEM; + + err = nsim_create_page_pool(&qmem->rq->page_pool, &qmem->rq->napi); + if (err) + goto err_free; + + if (!ns->rq_reset_mode) + netif_napi_add_config(dev, &qmem->rq->napi, nsim_poll, idx); + + return 0; + +err_free: + nsim_queue_free(qmem->rq); + return err; +} + +static void nsim_queue_mem_free(struct net_device *dev, void *per_queue_mem) +{ + struct nsim_queue_mem *qmem = per_queue_mem; + struct netdevsim *ns = netdev_priv(dev); + + page_pool_destroy(qmem->pp); + if (qmem->rq) { + if (!ns->rq_reset_mode) + netif_napi_del(&qmem->rq->napi); + page_pool_destroy(qmem->rq->page_pool); + nsim_queue_free(qmem->rq); + } +} + +static int +nsim_queue_start(struct net_device *dev, void *per_queue_mem, int idx) +{ + struct nsim_queue_mem *qmem = per_queue_mem; + struct netdevsim *ns = netdev_priv(dev); + + if (ns->rq_reset_mode == 1) { + ns->rq[idx]->page_pool = qmem->pp; + napi_enable(&ns->rq[idx]->napi); + return 0; + } + + /* netif_napi_add()/_del() should normally be called from alloc/free, + * here we want to test various call orders. + */ + if (ns->rq_reset_mode == 2) { + netif_napi_del(&ns->rq[idx]->napi); + netif_napi_add_config(dev, &qmem->rq->napi, nsim_poll, idx); + } else if (ns->rq_reset_mode == 3) { + netif_napi_add_config(dev, &qmem->rq->napi, nsim_poll, idx); + netif_napi_del(&ns->rq[idx]->napi); + } + + ns->rq[idx] = qmem->rq; + napi_enable(&ns->rq[idx]->napi); + + return 0; +} + +static int nsim_queue_stop(struct net_device *dev, void *per_queue_mem, int idx) +{ + struct nsim_queue_mem *qmem = per_queue_mem; + struct netdevsim *ns = netdev_priv(dev); + + napi_disable(&ns->rq[idx]->napi); + + if (ns->rq_reset_mode == 1) { + qmem->pp = ns->rq[idx]->page_pool; + page_pool_disable_direct_recycling(qmem->pp); + } else { + qmem->rq = ns->rq[idx]; + } + + return 0; +} + +static const struct netdev_queue_mgmt_ops nsim_queue_mgmt_ops = { + .ndo_queue_mem_size = sizeof(struct nsim_queue_mem), + .ndo_queue_mem_alloc = nsim_queue_mem_alloc, + .ndo_queue_mem_free = nsim_queue_mem_free, + .ndo_queue_start = nsim_queue_start, + .ndo_queue_stop = nsim_queue_stop, +}; + +static ssize_t +nsim_qreset_write(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + struct netdevsim *ns = file->private_data; + unsigned int queue, mode; + char buf[32]; + ssize_t ret; + + if (count >= sizeof(buf)) + return -EINVAL; + if (copy_from_user(buf, data, count)) + return -EFAULT; + buf[count] = '\0'; + + ret = sscanf(buf, "%u %u", &queue, &mode); + if (ret != 2) + return -EINVAL; + + rtnl_lock(); + if (!netif_running(ns->netdev)) { + ret = -ENETDOWN; + goto exit_unlock; + } + + if (queue >= ns->netdev->real_num_rx_queues) { + ret = -EINVAL; + goto exit_unlock; + } + + ns->rq_reset_mode = mode; + ret = netdev_rx_queue_restart(ns->netdev, queue); + ns->rq_reset_mode = 0; + if (ret) + goto exit_unlock; + + ret = count; +exit_unlock: + rtnl_unlock(); + return ret; +} + +static const struct file_operations nsim_qreset_fops = { + .open = simple_open, + .write = nsim_qreset_write, + .owner = THIS_MODULE, +}; + static ssize_t nsim_pp_hold_read(struct file *file, char __user *data, size_t count, loff_t *ppos) @@ -628,17 +815,17 @@ nsim_pp_hold_write(struct file *file, const char __user *data, if (!netif_running(ns->netdev) && val) { ret = -ENETDOWN; } else if (val) { - ns->page = page_pool_dev_alloc_pages(ns->rq[0].page_pool); + ns->page = page_pool_dev_alloc_pages(ns->rq[0]->page_pool); if (!ns->page) ret = -ENOMEM; } else { page_pool_put_full_page(ns->page->pp, ns->page, false); ns->page = NULL; } - rtnl_unlock(); exit: - return count; + rtnl_unlock(); + return ret; } static const struct file_operations nsim_pp_hold_fops = { @@ -677,27 +864,35 @@ static int nsim_queue_init(struct netdevsim *ns) struct net_device *dev = ns->netdev; int i; - ns->rq = kvcalloc(dev->num_rx_queues, sizeof(*ns->rq), - GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); + ns->rq = kcalloc(dev->num_rx_queues, sizeof(*ns->rq), + GFP_KERNEL_ACCOUNT); if (!ns->rq) return -ENOMEM; - for (i = 0; i < dev->num_rx_queues; i++) - skb_queue_head_init(&ns->rq[i].skb_queue); + for (i = 0; i < dev->num_rx_queues; i++) { + ns->rq[i] = nsim_queue_alloc(); + if (!ns->rq[i]) + goto err_free_prev; + } return 0; + +err_free_prev: + while (i--) + kfree(ns->rq[i]); + kfree(ns->rq); + return -ENOMEM; } -static void nsim_queue_free(struct netdevsim *ns) +static void nsim_queue_uninit(struct netdevsim *ns) { struct net_device *dev = ns->netdev; int i; for (i = 0; i < dev->num_rx_queues; i++) - skb_queue_purge_reason(&ns->rq[i].skb_queue, - SKB_DROP_REASON_QUEUE_PURGE); + nsim_queue_free(ns->rq[i]); - kvfree(ns->rq); + kfree(ns->rq); ns->rq = NULL; } @@ -713,6 +908,7 @@ static int nsim_init_netdevsim(struct netdevsim *ns) ns->phc = phc; ns->netdev->netdev_ops = &nsim_netdev_ops; ns->netdev->stat_ops = &nsim_stat_ops; + ns->netdev->queue_mgmt_ops = &nsim_queue_mgmt_ops; err = nsim_udp_tunnels_info_create(ns->nsim_dev, ns->netdev); if (err) @@ -741,7 +937,7 @@ err_ipsec_teardown: nsim_macsec_teardown(ns); nsim_bpf_uninit(ns); err_rq_destroy: - nsim_queue_free(ns); + nsim_queue_uninit(ns); err_utn_destroy: rtnl_unlock(); nsim_udp_tunnels_info_destroy(ns->netdev); @@ -798,6 +994,9 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) ns->pp_dfs = debugfs_create_file("pp_hold", 0600, nsim_dev_port->ddir, ns, &nsim_pp_hold_fops); + ns->qr_dfs = debugfs_create_file("queue_reset", 0200, + nsim_dev_port->ddir, ns, + &nsim_qreset_fops); return ns; @@ -811,6 +1010,7 @@ void nsim_destroy(struct netdevsim *ns) struct net_device *dev = ns->netdev; struct netdevsim *peer; + debugfs_remove(ns->qr_dfs); debugfs_remove(ns->pp_dfs); rtnl_lock(); @@ -823,7 +1023,7 @@ void nsim_destroy(struct netdevsim *ns) nsim_macsec_teardown(ns); nsim_ipsec_teardown(ns); nsim_bpf_uninit(ns); - nsim_queue_free(ns); + nsim_queue_uninit(ns); } rtnl_unlock(); if (nsim_dev_port_is_pf(ns->nsim_dev_port)) diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index bf02efa10956..96d54c08043d 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -36,6 +37,8 @@ #define NSIM_IPSEC_VALID BIT(31) #define NSIM_UDP_TUNNEL_N_PORTS 4 +#define NSIM_HDS_THRESHOLD_MAX 1024 + struct nsim_sa { struct xfrm_state *xs; __be32 ipaddr[4]; @@ -101,7 +104,9 @@ struct netdevsim { struct nsim_dev *nsim_dev; struct nsim_dev_port *nsim_dev_port; struct mock_phc *phc; - struct nsim_rq *rq; + struct nsim_rq **rq; + + int rq_reset_mode; u64 tx_packets; u64 tx_bytes; @@ -129,11 +134,13 @@ struct netdevsim { u32 sleep; u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS]; u32 (*ports)[NSIM_UDP_TUNNEL_N_PORTS]; + struct dentry *ddir; struct debugfs_u32_array dfs_ports[2]; } udp_ports; struct page *page; struct dentry *pp_dfs; + struct dentry *qr_dfs; struct nsim_ethtool ethtool; struct netdevsim __rcu *peer; diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c index 02dc3123eb6c..640b4983a9a0 100644 --- a/drivers/net/netdevsim/udp_tunnels.c +++ b/drivers/net/netdevsim/udp_tunnels.c @@ -112,9 +112,11 @@ nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data, struct net_device *dev = file->private_data; struct netdevsim *ns = netdev_priv(dev); - memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports)); rtnl_lock(); - udp_tunnel_nic_reset_ntf(dev); + if (dev->reg_state == NETREG_REGISTERED) { + memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports)); + udp_tunnel_nic_reset_ntf(dev); + } rtnl_unlock(); return count; @@ -144,23 +146,23 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, else ns->udp_ports.ports = nsim_dev->udp_ports.__ports; - debugfs_create_u32("udp_ports_inject_error", 0600, - ns->nsim_dev_port->ddir, + ns->udp_ports.ddir = debugfs_create_dir("udp_ports", + ns->nsim_dev_port->ddir); + + debugfs_create_u32("inject_error", 0600, ns->udp_ports.ddir, &ns->udp_ports.inject_error); ns->udp_ports.dfs_ports[0].array = ns->udp_ports.ports[0]; ns->udp_ports.dfs_ports[0].n_elements = NSIM_UDP_TUNNEL_N_PORTS; - debugfs_create_u32_array("udp_ports_table0", 0400, - ns->nsim_dev_port->ddir, + debugfs_create_u32_array("table0", 0400, ns->udp_ports.ddir, &ns->udp_ports.dfs_ports[0]); ns->udp_ports.dfs_ports[1].array = ns->udp_ports.ports[1]; ns->udp_ports.dfs_ports[1].n_elements = NSIM_UDP_TUNNEL_N_PORTS; - debugfs_create_u32_array("udp_ports_table1", 0400, - ns->nsim_dev_port->ddir, + debugfs_create_u32_array("table1", 0400, ns->udp_ports.ddir, &ns->udp_ports.dfs_ports[1]); - debugfs_create_file("udp_ports_reset", 0200, ns->nsim_dev_port->ddir, + debugfs_create_file("reset", 0200, ns->udp_ports.ddir, dev, &nsim_udp_tunnels_info_reset_fops); /* Note: it's not normal to allocate the info struct like this! @@ -196,6 +198,9 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, void nsim_udp_tunnels_info_destroy(struct net_device *dev) { + struct netdevsim *ns = netdev_priv(dev); + + debugfs_remove_recursive(ns->udp_ports.ddir); kfree(dev->udp_tunnel_nic_info); dev->udp_tunnel_nic_info = NULL; } diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index c1d881dc6409..1e1b00756be7 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -338,6 +338,7 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev, enum netkit_scrub scrub_peer = NETKIT_SCRUB_DEFAULT; enum netkit_mode mode = NETKIT_L3; unsigned char ifname_assign_type; + u16 headroom = 0, tailroom = 0; struct ifinfomsg *ifmp = NULL; struct net_device *peer; char ifname[IFNAMSIZ]; @@ -371,6 +372,10 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev, if (err < 0) return err; } + if (data[IFLA_NETKIT_HEADROOM]) + headroom = nla_get_u16(data[IFLA_NETKIT_HEADROOM]); + if (data[IFLA_NETKIT_TAILROOM]) + tailroom = nla_get_u16(data[IFLA_NETKIT_TAILROOM]); } if (ifmp && tbp[IFLA_IFNAME]) { @@ -390,6 +395,14 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev, return PTR_ERR(peer); netif_inherit_tso_max(peer, dev); + if (headroom) { + peer->needed_headroom = headroom; + dev->needed_headroom = headroom; + } + if (tailroom) { + peer->needed_tailroom = tailroom; + dev->needed_tailroom = tailroom; + } if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS])) eth_hw_addr_random(peer); @@ -401,6 +414,7 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev, nk->policy = policy_peer; nk->scrub = scrub_peer; nk->mode = mode; + nk->headroom = headroom; bpf_mprog_bundle_init(&nk->bundle); err = register_netdevice(peer); @@ -426,6 +440,7 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev, nk->policy = policy_prim; nk->scrub = scrub_prim; nk->mode = mode; + nk->headroom = headroom; bpf_mprog_bundle_init(&nk->bundle); err = register_netdevice(dev); @@ -850,7 +865,18 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[], struct net_device *peer = rtnl_dereference(nk->peer); enum netkit_action policy; struct nlattr *attr; - int err; + int err, i; + static const struct { + u32 attr; + char *name; + } fixed_params[] = { + { IFLA_NETKIT_MODE, "operating mode" }, + { IFLA_NETKIT_SCRUB, "scrubbing" }, + { IFLA_NETKIT_PEER_SCRUB, "peer scrubbing" }, + { IFLA_NETKIT_PEER_INFO, "peer info" }, + { IFLA_NETKIT_HEADROOM, "headroom" }, + { IFLA_NETKIT_TAILROOM, "tailroom" }, + }; if (!nk->primary) { NL_SET_ERR_MSG(extack, @@ -858,28 +884,14 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[], return -EACCES; } - if (data[IFLA_NETKIT_MODE]) { - NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_MODE], - "netkit link operating mode cannot be changed after device creation"); - return -EACCES; - } - - if (data[IFLA_NETKIT_SCRUB]) { - NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_SCRUB], - "netkit scrubbing cannot be changed after device creation"); - return -EACCES; - } - - if (data[IFLA_NETKIT_PEER_SCRUB]) { - NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_PEER_SCRUB], - "netkit scrubbing cannot be changed after device creation"); - return -EACCES; - } - - if (data[IFLA_NETKIT_PEER_INFO]) { - NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_PEER_INFO], - "netkit peer info cannot be changed after device creation"); - return -EINVAL; + for (i = 0; i < ARRAY_SIZE(fixed_params); i++) { + attr = data[fixed_params[i].attr]; + if (attr) { + NL_SET_ERR_MSG_ATTR_FMT(extack, attr, + "netkit link %s cannot be changed after device creation", + fixed_params[i].name); + return -EACCES; + } } if (data[IFLA_NETKIT_POLICY]) { @@ -914,6 +926,8 @@ static size_t netkit_get_size(const struct net_device *dev) nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_SCRUB */ nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_MODE */ nla_total_size(sizeof(u8)) + /* IFLA_NETKIT_PRIMARY */ + nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_HEADROOM */ + nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_TAILROOM */ 0; } @@ -930,6 +944,10 @@ static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev) return -EMSGSIZE; if (nla_put_u32(skb, IFLA_NETKIT_SCRUB, nk->scrub)) return -EMSGSIZE; + if (nla_put_u16(skb, IFLA_NETKIT_HEADROOM, dev->needed_headroom)) + return -EMSGSIZE; + if (nla_put_u16(skb, IFLA_NETKIT_TAILROOM, dev->needed_tailroom)) + return -EMSGSIZE; if (peer) { nk = netkit_priv(peer); @@ -947,6 +965,8 @@ static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = { [IFLA_NETKIT_MODE] = NLA_POLICY_MAX(NLA_U32, NETKIT_L3), [IFLA_NETKIT_POLICY] = { .type = NLA_U32 }, [IFLA_NETKIT_PEER_POLICY] = { .type = NLA_U32 }, + [IFLA_NETKIT_HEADROOM] = { .type = NLA_U16 }, + [IFLA_NETKIT_TAILROOM] = { .type = NLA_U16 }, [IFLA_NETKIT_SCRUB] = NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT), [IFLA_NETKIT_PEER_SCRUB] = NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT), [IFLA_NETKIT_PRIMARY] = { .type = NLA_REJECT, diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c index b79aedad855b..e46f588cae7d 100644 --- a/drivers/net/pcs/pcs-lynx.c +++ b/drivers/net/pcs/pcs-lynx.c @@ -35,6 +35,27 @@ enum sgmii_speed { #define phylink_pcs_to_lynx(pl_pcs) container_of((pl_pcs), struct lynx_pcs, pcs) #define lynx_to_phylink_pcs(lynx) (&(lynx)->pcs) +static unsigned int lynx_pcs_inband_caps(struct phylink_pcs *pcs, + phy_interface_t interface) +{ + switch (interface) { + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE; + + case PHY_INTERFACE_MODE_10GBASER: + case PHY_INTERFACE_MODE_2500BASEX: + return LINK_INBAND_DISABLE; + + case PHY_INTERFACE_MODE_USXGMII: + return LINK_INBAND_ENABLE; + + default: + return 0; + } +} + static void lynx_pcs_get_state_usxgmii(struct mdio_device *pcs, struct phylink_link_state *state) { @@ -79,7 +100,7 @@ static void lynx_pcs_get_state_2500basex(struct mdio_device *pcs, state->duplex = DUPLEX_FULL; } -static void lynx_pcs_get_state(struct phylink_pcs *pcs, +static void lynx_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); @@ -88,7 +109,7 @@ static void lynx_pcs_get_state(struct phylink_pcs *pcs, case PHY_INTERFACE_MODE_1000BASEX: case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_QSGMII: - phylink_mii_c22_pcs_get_state(lynx->mdio, state); + phylink_mii_c22_pcs_get_state(lynx->mdio, neg_mode, state); break; case PHY_INTERFACE_MODE_2500BASEX: lynx_pcs_get_state_2500basex(lynx->mdio, state); @@ -306,15 +327,26 @@ static void lynx_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, } static const struct phylink_pcs_ops lynx_pcs_phylink_ops = { + .pcs_inband_caps = lynx_pcs_inband_caps, .pcs_get_state = lynx_pcs_get_state, .pcs_config = lynx_pcs_config, .pcs_an_restart = lynx_pcs_an_restart, .pcs_link_up = lynx_pcs_link_up, }; +static const phy_interface_t lynx_interfaces[] = { + PHY_INTERFACE_MODE_SGMII, + PHY_INTERFACE_MODE_QSGMII, + PHY_INTERFACE_MODE_1000BASEX, + PHY_INTERFACE_MODE_2500BASEX, + PHY_INTERFACE_MODE_10GBASER, + PHY_INTERFACE_MODE_USXGMII, +}; + static struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio) { struct lynx_pcs *lynx; + int i; lynx = kzalloc(sizeof(*lynx), GFP_KERNEL); if (!lynx) @@ -326,6 +358,9 @@ static struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio) lynx->pcs.neg_mode = true; lynx->pcs.poll = true; + for (i = 0; i < ARRAY_SIZE(lynx_interfaces); i++) + __set_bit(lynx_interfaces[i], lynx->pcs.supported_interfaces); + return lynx_to_phylink_pcs(lynx); } diff --git a/drivers/net/pcs/pcs-mtk-lynxi.c b/drivers/net/pcs/pcs-mtk-lynxi.c index 4f63abe638c4..7d6261dee534 100644 --- a/drivers/net/pcs/pcs-mtk-lynxi.c +++ b/drivers/net/pcs/pcs-mtk-lynxi.c @@ -88,7 +88,24 @@ static struct mtk_pcs_lynxi *pcs_to_mtk_pcs_lynxi(struct phylink_pcs *pcs) return container_of(pcs, struct mtk_pcs_lynxi, pcs); } +static unsigned int mtk_pcs_lynxi_inband_caps(struct phylink_pcs *pcs, + phy_interface_t interface) +{ + switch (interface) { + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_SGMII: + return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE; + + case PHY_INTERFACE_MODE_2500BASEX: + return LINK_INBAND_DISABLE; + + default: + return 0; + } +} + static void mtk_pcs_lynxi_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mtk_pcs_lynxi *mpcs = pcs_to_mtk_pcs_lynxi(pcs); @@ -98,7 +115,8 @@ static void mtk_pcs_lynxi_get_state(struct phylink_pcs *pcs, regmap_read(mpcs->regmap, SGMSYS_PCS_CONTROL_1, &bm); regmap_read(mpcs->regmap, SGMSYS_PCS_ADVERTISE, &adv); - phylink_mii_c22_pcs_decode_state(state, FIELD_GET(SGMII_BMSR, bm), + phylink_mii_c22_pcs_decode_state(state, neg_mode, + FIELD_GET(SGMII_BMSR, bm), FIELD_GET(SGMII_LPA, adv)); } @@ -241,6 +259,7 @@ static void mtk_pcs_lynxi_disable(struct phylink_pcs *pcs) } static const struct phylink_pcs_ops mtk_pcs_lynxi_ops = { + .pcs_inband_caps = mtk_pcs_lynxi_inband_caps, .pcs_get_state = mtk_pcs_lynxi_get_state, .pcs_config = mtk_pcs_lynxi_config, .pcs_an_restart = mtk_pcs_lynxi_restart_an, @@ -290,6 +309,10 @@ struct phylink_pcs *mtk_pcs_lynxi_create(struct device *dev, mpcs->pcs.poll = true; mpcs->interface = PHY_INTERFACE_MODE_NA; + __set_bit(PHY_INTERFACE_MODE_SGMII, mpcs->pcs.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, mpcs->pcs.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_2500BASEX, mpcs->pcs.supported_interfaces); + return &mpcs->pcs; } EXPORT_SYMBOL(mtk_pcs_lynxi_create); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 7246a910728d..1faa37f0e7b9 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -567,14 +567,40 @@ static int xpcs_validate(struct phylink_pcs *pcs, unsigned long *supported, return 0; } -void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces) +static unsigned int xpcs_inband_caps(struct phylink_pcs *pcs, + phy_interface_t interface) +{ + struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); + const struct dw_xpcs_compat *compat; + + compat = xpcs_find_compat(xpcs, interface); + if (!compat) + return 0; + + switch (compat->an_mode) { + case DW_AN_C73: + return LINK_INBAND_ENABLE; + + case DW_AN_C37_SGMII: + case DW_AN_C37_1000BASEX: + return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE; + + case DW_10GBASER: + case DW_2500BASEX: + return LINK_INBAND_DISABLE; + + default: + return 0; + } +} + +static void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces) { const struct dw_xpcs_compat *compat; for (compat = xpcs->desc->compat; compat->supported; compat++) __set_bit(compat->interface, interfaces); } -EXPORT_SYMBOL_GPL(xpcs_get_interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable) { @@ -684,7 +710,9 @@ static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs, if (ret < 0) return ret; - mask = DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; + val = 0; + mask = DW_VR_MII_DIG_CTRL1_2G5_EN | DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) val = DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; @@ -1004,6 +1032,7 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs, } static int xpcs_get_state_c37_1000basex(struct dw_xpcs *xpcs, + unsigned int neg_mode, struct phylink_link_state *state) { int lpa, bmsr; @@ -1032,7 +1061,7 @@ static int xpcs_get_state_c37_1000basex(struct dw_xpcs *xpcs, } } - phylink_mii_c22_pcs_decode_state(state, bmsr, lpa); + phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lpa); } return 0; @@ -1060,7 +1089,7 @@ static int xpcs_get_state_2500basex(struct dw_xpcs *xpcs, return 0; } -static void xpcs_get_state(struct phylink_pcs *pcs, +static void xpcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); @@ -1088,7 +1117,7 @@ static void xpcs_get_state(struct phylink_pcs *pcs, "xpcs_get_state_c37_sgmii", ERR_PTR(ret)); break; case DW_AN_C37_1000BASEX: - ret = xpcs_get_state_c37_1000basex(xpcs, state); + ret = xpcs_get_state_c37_1000basex(xpcs, neg_mode, state); if (ret) dev_err(&xpcs->mdiodev->dev, "%s returned %pe\n", "xpcs_get_state_c37_1000basex", ERR_PTR(ret)); @@ -1306,6 +1335,7 @@ static const struct dw_xpcs_desc xpcs_desc_list[] = { static const struct phylink_pcs_ops xpcs_phylink_ops = { .pcs_validate = xpcs_validate, + .pcs_inband_caps = xpcs_inband_caps, .pcs_pre_config = xpcs_pre_config, .pcs_config = xpcs_config, .pcs_get_state = xpcs_get_state, @@ -1418,6 +1448,8 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev) if (ret) goto out_clear_clks; + xpcs_get_interfaces(xpcs, xpcs->pcs.supported_interfaces); + if (xpcs->info.pma == WX_TXGBE_XPCS_PMA_10G_ID) xpcs->pcs.poll = false; else diff --git a/drivers/net/pfcp.c b/drivers/net/pfcp.c index 69434fd13f96..68d0d9e92a22 100644 --- a/drivers/net/pfcp.c +++ b/drivers/net/pfcp.c @@ -206,8 +206,8 @@ static int pfcp_newlink(struct net *net, struct net_device *dev, goto exit_del_pfcp_sock; } - pn = net_generic(dev_net(dev), pfcp_net_id); - list_add_rcu(&pfcp->list, &pn->pfcp_dev_list); + pn = net_generic(net, pfcp_net_id); + list_add(&pfcp->list, &pn->pfcp_dev_list); netdev_dbg(dev, "registered new PFCP interface\n"); @@ -224,7 +224,7 @@ static void pfcp_dellink(struct net_device *dev, struct list_head *head) { struct pfcp_dev *pfcp = netdev_priv(dev); - list_del_rcu(&pfcp->list); + list_del(&pfcp->list); unregister_netdevice_queue(dev, head); } @@ -247,11 +247,16 @@ static int __net_init pfcp_net_init(struct net *net) static void __net_exit pfcp_net_exit(struct net *net) { struct pfcp_net *pn = net_generic(net, pfcp_net_id); - struct pfcp_dev *pfcp; + struct pfcp_dev *pfcp, *pfcp_next; + struct net_device *dev; LIST_HEAD(list); rtnl_lock(); - list_for_each_entry(pfcp, &pn->pfcp_dev_list, list) + for_each_netdev(net, dev) + if (dev->rtnl_link_ops == &pfcp_link_ops) + pfcp_dellink(dev, &list); + + list_for_each_entry_safe(pfcp, pfcp_next, &pn->pfcp_dev_list, list) pfcp_dellink(pfcp->dev, &list); unregister_netdevice_many(&list); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 15828f4710a9..41c15a2c2037 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -287,8 +287,15 @@ config MICROCHIP_PHY config MICROCHIP_T1_PHY tristate "Microchip T1 PHYs" + select MICROCHIP_PHY_RDS_PTP if NETWORK_PHY_TIMESTAMPING + depends on PTP_1588_CLOCK_OPTIONAL help - Supports the LAN87XX PHYs. + Supports the LAN8XXX PHYs. + +config MICROCHIP_PHY_RDS_PTP + tristate + help + Currently supports LAN887X T1 PHY config MICROSEMI_PHY tristate "Microsemi PHYs" @@ -343,10 +350,7 @@ config QSEMI_PHY help Currently supports the qs6612 -config REALTEK_PHY - tristate "Realtek PHYs" - help - Supports the Realtek 821x PHY. +source "drivers/net/phy/realtek/Kconfig" config RENESAS_PHY tristate "Renesas PHYs" diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index e6145153e837..c8dac6e92278 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -79,6 +79,7 @@ obj-$(CONFIG_MESON_GXL_PHY) += meson-gxl.o obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o obj-$(CONFIG_MICREL_PHY) += micrel.o obj-$(CONFIG_MICROCHIP_PHY) += microchip.o +obj-$(CONFIG_MICROCHIP_PHY_RDS_PTP) += microchip_rds_ptp.o obj-$(CONFIG_MICROCHIP_T1_PHY) += microchip_t1.o obj-$(CONFIG_MICROCHIP_T1S_PHY) += microchip_t1s.o obj-$(CONFIG_MICROSEMI_PHY) += mscc/ @@ -94,7 +95,7 @@ obj-$(CONFIG_NXP_CBTX_PHY) += nxp-cbtx.o obj-$(CONFIG_NXP_TJA11XX_PHY) += nxp-tja11xx.o obj-y += qcom/ obj-$(CONFIG_QSEMI_PHY) += qsemi.o -obj-$(CONFIG_REALTEK_PHY) += realtek.o +obj-$(CONFIG_REALTEK_PHY) += realtek/ obj-$(CONFIG_RENESAS_PHY) += uPD60620.o obj-$(CONFIG_ROCKCHIP_PHY) += rockchip.o obj-$(CONFIG_SMSC_PHY) += smsc.o diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c index a2a862bae2ed..7fa713ca8d45 100644 --- a/drivers/net/phy/adin.c +++ b/drivers/net/phy/adin.c @@ -1038,7 +1038,7 @@ static struct phy_driver adin_driver[] = { module_phy_driver(adin_driver); -static struct mdio_device_id __maybe_unused adin_tbl[] = { +static const struct mdio_device_id __maybe_unused adin_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200) }, { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300) }, { } diff --git a/drivers/net/phy/adin1100.c b/drivers/net/phy/adin1100.c index 85f910e2d4fb..6bb469429b9d 100644 --- a/drivers/net/phy/adin1100.c +++ b/drivers/net/phy/adin1100.c @@ -340,7 +340,7 @@ static struct phy_driver adin_driver[] = { module_phy_driver(adin_driver); -static struct mdio_device_id __maybe_unused adin_tbl[] = { +static const struct mdio_device_id __maybe_unused adin_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1100) }, { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1110) }, { PHY_ID_MATCH_MODEL(PHY_ID_ADIN2111) }, diff --git a/drivers/net/phy/air_en8811h.c b/drivers/net/phy/air_en8811h.c index 8d076b9609fd..e9fd24cb7270 100644 --- a/drivers/net/phy/air_en8811h.c +++ b/drivers/net/phy/air_en8811h.c @@ -1075,7 +1075,7 @@ static struct phy_driver en8811h_driver[] = { module_phy_driver(en8811h_driver); -static struct mdio_device_id __maybe_unused en8811h_tbl[] = { +static const struct mdio_device_id __maybe_unused en8811h_tbl[] = { { PHY_ID_MATCH_MODEL(EN8811H_PHY_ID) }, { } }; diff --git a/drivers/net/phy/amd.c b/drivers/net/phy/amd.c index 930b15fa6ce9..75b5fe65500a 100644 --- a/drivers/net/phy/amd.c +++ b/drivers/net/phy/amd.c @@ -111,7 +111,7 @@ static struct phy_driver am79c_drivers[] = { module_phy_driver(am79c_drivers); -static struct mdio_device_id __maybe_unused amd_tbl[] = { +static const struct mdio_device_id __maybe_unused amd_tbl[] = { { PHY_ID_AC101L, 0xfffffff0 }, { PHY_ID_AM79C874, 0xfffffff0 }, { } diff --git a/drivers/net/phy/aquantia/aquantia_leds.c b/drivers/net/phy/aquantia/aquantia_leds.c index 00ad2313fed3..951f46104eff 100644 --- a/drivers/net/phy/aquantia/aquantia_leds.c +++ b/drivers/net/phy/aquantia/aquantia_leds.c @@ -156,5 +156,5 @@ int aqr_phy_led_polarity_set(struct phy_device *phydev, int index, unsigned long if (force_active_high || force_active_low) return aqr_phy_led_active_low_set(phydev, index, force_active_low); - unreachable(); + return -EINVAL; } diff --git a/drivers/net/phy/aquantia/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c index bb56a66d2a48..e42ace4e682a 100644 --- a/drivers/net/phy/aquantia/aquantia_main.c +++ b/drivers/net/phy/aquantia/aquantia_main.c @@ -1200,7 +1200,7 @@ static struct phy_driver aqr_driver[] = { module_phy_driver(aqr_driver); -static struct mdio_device_id __maybe_unused aqr_tbl[] = { +static const struct mdio_device_id __maybe_unused aqr_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_AQ1202) }, { PHY_ID_MATCH_MODEL(PHY_ID_AQ2104) }, { PHY_ID_MATCH_MODEL(PHY_ID_AQR105) }, diff --git a/drivers/net/phy/ax88796b.c b/drivers/net/phy/ax88796b.c index eb74a8cf8df1..694df1401aa2 100644 --- a/drivers/net/phy/ax88796b.c +++ b/drivers/net/phy/ax88796b.c @@ -121,7 +121,7 @@ static struct phy_driver asix_driver[] = { module_phy_driver(asix_driver); -static struct mdio_device_id __maybe_unused asix_tbl[] = { +static const struct mdio_device_id __maybe_unused asix_tbl[] = { { PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772A) }, { PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772C) }, { PHY_ID_ASIX_AX88796B, 0xfffffff0 }, diff --git a/drivers/net/phy/bcm-cygnus.c b/drivers/net/phy/bcm-cygnus.c index da8f7cb41b44..15cbef8202bc 100644 --- a/drivers/net/phy/bcm-cygnus.c +++ b/drivers/net/phy/bcm-cygnus.c @@ -278,7 +278,7 @@ static struct phy_driver bcm_cygnus_phy_driver[] = { } }; -static struct mdio_device_id __maybe_unused bcm_cygnus_phy_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm_cygnus_phy_tbl[] = { { PHY_ID_BCM_CYGNUS, 0xfffffff0, }, { PHY_ID_BCM_OMEGA, 0xfffffff0, }, { } diff --git a/drivers/net/phy/bcm54140.c b/drivers/net/phy/bcm54140.c index 2eea3d09b1e6..7969345f6b35 100644 --- a/drivers/net/phy/bcm54140.c +++ b/drivers/net/phy/bcm54140.c @@ -883,7 +883,7 @@ static struct phy_driver bcm54140_drivers[] = { }; module_phy_driver(bcm54140_drivers); -static struct mdio_device_id __maybe_unused bcm54140_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm54140_tbl[] = { { PHY_ID_BCM54140, BCM54140_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index 0eb33be824f1..b46a736a3130 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -93,7 +93,7 @@ static struct phy_driver bcm63xx_driver[] = { module_phy_driver(bcm63xx_driver); -static struct mdio_device_id __maybe_unused bcm63xx_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm63xx_tbl[] = { { 0x00406000, 0xfffffc00 }, { 0x002bdc00, 0xfffffc00 }, { } diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 97638ba7ae85..00e8fa14aa77 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -929,7 +929,7 @@ static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_16NM_EPHY(PHY_ID_BCM7712, "Broadcom BCM7712"), }; -static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM72113, 0xfffffff0 }, { PHY_ID_BCM72116, 0xfffffff0, }, { PHY_ID_BCM72165, 0xfffffff0, }, diff --git a/drivers/net/phy/bcm84881.c b/drivers/net/phy/bcm84881.c index 97da3aee4942..d7f7cc44c532 100644 --- a/drivers/net/phy/bcm84881.c +++ b/drivers/net/phy/bcm84881.c @@ -235,11 +235,21 @@ static int bcm84881_read_status(struct phy_device *phydev) return genphy_c45_read_mdix(phydev); } +/* The Broadcom BCM84881 in the Methode DM7052 is unable to provide a SGMII + * or 802.3z control word, so inband will not work. + */ +static unsigned int bcm84881_inband_caps(struct phy_device *phydev, + phy_interface_t interface) +{ + return LINK_INBAND_DISABLE; +} + static struct phy_driver bcm84881_drivers[] = { { .phy_id = 0xae025150, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM84881", + .inband_caps = bcm84881_inband_caps, .config_init = bcm84881_config_init, .probe = bcm84881_probe, .get_features = bcm84881_get_features, @@ -252,7 +262,7 @@ static struct phy_driver bcm84881_drivers[] = { module_phy_driver(bcm84881_drivers); /* FIXME: module auto-loading for Clause 45 PHYs seems non-functional */ -static struct mdio_device_id __maybe_unused bcm84881_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm84881_tbl[] = { { 0xae025150, 0xfffffff0 }, { }, }; diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index ddded162c44c..22edb7e4c1a1 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -1717,7 +1717,7 @@ static struct phy_driver broadcom_drivers[] = { module_phy_driver(broadcom_drivers); -static struct mdio_device_id __maybe_unused broadcom_tbl[] = { +static const struct mdio_device_id __maybe_unused broadcom_tbl[] = { { PHY_ID_BCM5411, 0xfffffff0 }, { PHY_ID_BCM5421, 0xfffffff0 }, { PHY_ID_BCM54210E, 0xfffffff0 }, diff --git a/drivers/net/phy/cicada.c b/drivers/net/phy/cicada.c index ef5f412e101f..d87cf8b94cf8 100644 --- a/drivers/net/phy/cicada.c +++ b/drivers/net/phy/cicada.c @@ -145,7 +145,7 @@ static struct phy_driver cis820x_driver[] = { module_phy_driver(cis820x_driver); -static struct mdio_device_id __maybe_unused cicada_tbl[] = { +static const struct mdio_device_id __maybe_unused cicada_tbl[] = { { 0x000fc410, 0x000ffff0 }, { 0x000fc440, 0x000fffc0 }, { } diff --git a/drivers/net/phy/cortina.c b/drivers/net/phy/cortina.c index 40514a94e6ff..3b65f37f1c57 100644 --- a/drivers/net/phy/cortina.c +++ b/drivers/net/phy/cortina.c @@ -87,7 +87,7 @@ static struct phy_driver cortina_driver[] = { module_phy_driver(cortina_driver); -static struct mdio_device_id __maybe_unused cortina_tbl[] = { +static const struct mdio_device_id __maybe_unused cortina_tbl[] = { { PHY_ID_CS4340, 0xffffffff}, {}, }; diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c index 4ac4bce1bf32..fa3692508f16 100644 --- a/drivers/net/phy/davicom.c +++ b/drivers/net/phy/davicom.c @@ -209,7 +209,7 @@ static struct phy_driver dm91xx_driver[] = { module_phy_driver(dm91xx_driver); -static struct mdio_device_id __maybe_unused davicom_tbl[] = { +static const struct mdio_device_id __maybe_unused davicom_tbl[] = { { 0x0181b880, 0x0ffffff0 }, { 0x0181b8b0, 0x0ffffff0 }, { 0x0181b8a0, 0x0ffffff0 }, diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 075d2beea716..85e231451093 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1548,7 +1548,7 @@ MODULE_LICENSE("GPL"); module_init(dp83640_init); module_exit(dp83640_exit); -static struct mdio_device_id __maybe_unused dp83640_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83640_tbl[] = { { DP83640_PHY_ID, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index cf8b6d0bfaa9..6599feca1967 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -22,8 +22,6 @@ #define DP83826C_PHY_ID 0x2000a130 #define DP83826NC_PHY_ID 0x2000a110 -#define DP83822_DEVADDR 0x1f - #define MII_DP83822_CTRL_2 0x0a #define MII_DP83822_PHYSTS 0x10 #define MII_DP83822_PHYSCR 0x11 @@ -32,6 +30,10 @@ #define MII_DP83822_FCSCR 0x14 #define MII_DP83822_RCSR 0x17 #define MII_DP83822_RESET_CTRL 0x1f +#define MII_DP83822_MLEDCR 0x25 +#define MII_DP83822_LEDCFG1 0x460 +#define MII_DP83822_IOCTRL1 0x462 +#define MII_DP83822_IOCTRL2 0x463 #define MII_DP83822_GENCFG 0x465 #define MII_DP83822_SOR1 0x467 @@ -106,6 +108,50 @@ #define DP83822_RX_CLK_SHIFT BIT(12) #define DP83822_TX_CLK_SHIFT BIT(11) +/* MLEDCR bits */ +#define DP83822_MLEDCR_CFG GENMASK(6, 3) +#define DP83822_MLEDCR_ROUTE GENMASK(1, 0) +#define DP83822_MLEDCR_ROUTE_LED_0 DP83822_MLEDCR_ROUTE + +/* LEDCFG1 bits */ +#define DP83822_LEDCFG1_LED1_CTRL GENMASK(11, 8) +#define DP83822_LEDCFG1_LED3_CTRL GENMASK(7, 4) + +/* IOCTRL1 bits */ +#define DP83822_IOCTRL1_GPIO3_CTRL GENMASK(10, 8) +#define DP83822_IOCTRL1_GPIO3_CTRL_LED3 BIT(0) +#define DP83822_IOCTRL1_GPIO1_CTRL GENMASK(2, 0) +#define DP83822_IOCTRL1_GPIO1_CTRL_LED_1 BIT(0) + +/* IOCTRL2 bits */ +#define DP83822_IOCTRL2_GPIO2_CLK_SRC GENMASK(6, 4) +#define DP83822_IOCTRL2_GPIO2_CTRL GENMASK(2, 0) +#define DP83822_IOCTRL2_GPIO2_CTRL_CLK_REF GENMASK(1, 0) +#define DP83822_IOCTRL2_GPIO2_CTRL_MLED BIT(0) + +#define DP83822_CLK_SRC_MAC_IF 0x0 +#define DP83822_CLK_SRC_XI 0x1 +#define DP83822_CLK_SRC_INT_REF 0x2 +#define DP83822_CLK_SRC_RMII_MASTER_MODE_REF 0x4 +#define DP83822_CLK_SRC_FREE_RUNNING 0x6 +#define DP83822_CLK_SRC_RECOVERED 0x7 + +#define DP83822_LED_FN_LINK 0x0 /* Link established */ +#define DP83822_LED_FN_RX_TX 0x1 /* Receive or Transmit activity */ +#define DP83822_LED_FN_TX 0x2 /* Transmit activity */ +#define DP83822_LED_FN_RX 0x3 /* Receive activity */ +#define DP83822_LED_FN_COLLISION 0x4 /* Collision detected */ +#define DP83822_LED_FN_LINK_100_BTX 0x5 /* 100 BTX link established */ +#define DP83822_LED_FN_LINK_10_BT 0x6 /* 10BT link established */ +#define DP83822_LED_FN_FULL_DUPLEX 0x7 /* Full duplex */ +#define DP83822_LED_FN_LINK_RX_TX 0x8 /* Link established, blink for rx or tx activity */ +#define DP83822_LED_FN_ACTIVE_STRETCH 0x9 /* Active Stretch Signal */ +#define DP83822_LED_FN_MII_LINK 0xa /* MII LINK (100BT+FD) */ +#define DP83822_LED_FN_LPI_MODE 0xb /* LPI Mode (EEE) */ +#define DP83822_LED_FN_RX_TX_ERR 0xc /* TX/RX MII Error */ +#define DP83822_LED_FN_LINK_LOST 0xd /* Link Lost */ +#define DP83822_LED_FN_PRBS_ERR 0xe /* Blink for PRBS error */ + /* SOR1 mode */ #define DP83822_STRAP_MODE1 0 #define DP83822_STRAP_MODE2 BIT(0) @@ -134,6 +180,13 @@ ADVERTISED_FIBRE | \ ADVERTISED_Pause | ADVERTISED_Asym_Pause) +#define DP83822_MAX_LED_PINS 4 + +#define DP83822_LED_INDEX_LED_0 0 +#define DP83822_LED_INDEX_LED_1_GPIO1 1 +#define DP83822_LED_INDEX_COL_GPIO2 2 +#define DP83822_LED_INDEX_RX_D3_GPIO3 3 + struct dp83822_private { bool fx_signal_det_low; int fx_enabled; @@ -141,6 +194,9 @@ struct dp83822_private { u8 cfg_dac_minus; u8 cfg_dac_plus; struct ethtool_wolinfo wol; + bool set_gpio2_clk_out; + u32 gpio2_clk_out; + bool led_pin_enable[DP83822_MAX_LED_PINS]; }; static int dp83822_config_wol(struct phy_device *phydev, @@ -159,14 +215,14 @@ static int dp83822_config_wol(struct phy_device *phydev, /* MAC addresses start with byte 5, but stored in mac[0]. * 822 PHYs store bytes 4|5, 2|3, 0|1 */ - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA1, + phy_write_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_DA1, (mac[1] << 8) | mac[0]); - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA2, + phy_write_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_DA2, (mac[3] << 8) | mac[2]); - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA3, + phy_write_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_DA3, (mac[5] << 8) | mac[4]); - value = phy_read_mmd(phydev, DP83822_DEVADDR, + value = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_CFG); if (wol->wolopts & WAKE_MAGIC) value |= DP83822_WOL_MAGIC_EN; @@ -174,13 +230,13 @@ static int dp83822_config_wol(struct phy_device *phydev, value &= ~DP83822_WOL_MAGIC_EN; if (wol->wolopts & WAKE_MAGICSECURE) { - phy_write_mmd(phydev, DP83822_DEVADDR, + phy_write_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RXSOP1, (wol->sopass[1] << 8) | wol->sopass[0]); - phy_write_mmd(phydev, DP83822_DEVADDR, + phy_write_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RXSOP2, (wol->sopass[3] << 8) | wol->sopass[2]); - phy_write_mmd(phydev, DP83822_DEVADDR, + phy_write_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RXSOP3, (wol->sopass[5] << 8) | wol->sopass[4]); value |= DP83822_WOL_SECURE_ON; @@ -194,10 +250,10 @@ static int dp83822_config_wol(struct phy_device *phydev, value |= DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL | DP83822_WOL_CLR_INDICATION; - return phy_write_mmd(phydev, DP83822_DEVADDR, + return phy_write_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_CFG, value); } else { - return phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_CFG, DP83822_WOL_EN | DP83822_WOL_MAGIC_EN | @@ -226,23 +282,23 @@ static void dp83822_get_wol(struct phy_device *phydev, wol->supported = (WAKE_MAGIC | WAKE_MAGICSECURE); wol->wolopts = 0; - value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG); + value = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_CFG); if (value & DP83822_WOL_MAGIC_EN) wol->wolopts |= WAKE_MAGIC; if (value & DP83822_WOL_SECURE_ON) { - sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR, + sopass_val = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RXSOP1); wol->sopass[0] = (sopass_val & 0xff); wol->sopass[1] = (sopass_val >> 8); - sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR, + sopass_val = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RXSOP2); wol->sopass[2] = (sopass_val & 0xff); wol->sopass[3] = (sopass_val >> 8); - sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR, + sopass_val = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RXSOP3); wol->sopass[4] = (sopass_val & 0xff); wol->sopass[5] = (sopass_val >> 8); @@ -405,6 +461,48 @@ static int dp83822_read_status(struct phy_device *phydev) return 0; } +static int dp83822_config_init_leds(struct phy_device *phydev) +{ + struct dp83822_private *dp83822 = phydev->priv; + int ret; + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_LED_0]) { + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_MLEDCR, + DP83822_MLEDCR_ROUTE, + FIELD_PREP(DP83822_MLEDCR_ROUTE, + DP83822_MLEDCR_ROUTE_LED_0)); + if (ret) + return ret; + } else if (dp83822->led_pin_enable[DP83822_LED_INDEX_COL_GPIO2]) { + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_IOCTRL2, + DP83822_IOCTRL2_GPIO2_CTRL, + FIELD_PREP(DP83822_IOCTRL2_GPIO2_CTRL, + DP83822_IOCTRL2_GPIO2_CTRL_MLED)); + if (ret) + return ret; + } + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_LED_1_GPIO1]) { + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_IOCTRL1, + DP83822_IOCTRL1_GPIO1_CTRL, + FIELD_PREP(DP83822_IOCTRL1_GPIO1_CTRL, + DP83822_IOCTRL1_GPIO1_CTRL_LED_1)); + if (ret) + return ret; + } + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_RX_D3_GPIO3]) { + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_IOCTRL1, + DP83822_IOCTRL1_GPIO3_CTRL, + FIELD_PREP(DP83822_IOCTRL1_GPIO3_CTRL, + DP83822_IOCTRL1_GPIO3_CTRL_LED3)); + if (ret) + return ret; + } + + return 0; +} + static int dp83822_config_init(struct phy_device *phydev) { struct dp83822_private *dp83822 = phydev->priv; @@ -415,6 +513,19 @@ static int dp83822_config_init(struct phy_device *phydev) int err = 0; int bmcr; + if (dp83822->set_gpio2_clk_out) + phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_IOCTRL2, + DP83822_IOCTRL2_GPIO2_CTRL | + DP83822_IOCTRL2_GPIO2_CLK_SRC, + FIELD_PREP(DP83822_IOCTRL2_GPIO2_CTRL, + DP83822_IOCTRL2_GPIO2_CTRL_CLK_REF) | + FIELD_PREP(DP83822_IOCTRL2_GPIO2_CLK_SRC, + dp83822->gpio2_clk_out)); + + err = dp83822_config_init_leds(phydev); + if (err) + return err; + if (phy_interface_is_rgmii(phydev)) { rx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, true); @@ -430,18 +541,18 @@ static int dp83822_config_init(struct phy_device *phydev) if (tx_int_delay <= 0) rgmii_delay |= DP83822_TX_CLK_SHIFT; - err = phy_modify_mmd(phydev, DP83822_DEVADDR, MII_DP83822_RCSR, + err = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RCSR, DP83822_RX_CLK_SHIFT | DP83822_TX_CLK_SHIFT, rgmii_delay); if (err) return err; - err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, + err = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); if (err) return err; } else { - err = phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + err = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); if (err) @@ -496,7 +607,7 @@ static int dp83822_config_init(struct phy_device *phydev) return err; if (dp83822->fx_signal_det_low) { - err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, + err = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_GENCFG, DP83822_SIG_DET_LOW); if (err) @@ -514,10 +625,10 @@ static int dp8382x_config_rmii_mode(struct phy_device *phydev) if (!device_property_read_string(dev, "ti,rmii-mode", &of_val)) { if (strcmp(of_val, "master") == 0) { - ret = phy_clear_bits_mmd(phydev, DP83822_DEVADDR, MII_DP83822_RCSR, + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RCSR, DP83822_RMII_MODE_SEL); } else if (strcmp(of_val, "slave") == 0) { - ret = phy_set_bits_mmd(phydev, DP83822_DEVADDR, MII_DP83822_RCSR, + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RCSR, DP83822_RMII_MODE_SEL); } else { phydev_err(phydev, "Invalid value for ti,rmii-mode property (%s)\n", @@ -539,7 +650,7 @@ static int dp83826_config_init(struct phy_device *phydev) int ret; if (phydev->interface == PHY_INTERFACE_MODE_RMII) { - ret = phy_set_bits_mmd(phydev, DP83822_DEVADDR, MII_DP83822_RCSR, + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RCSR, DP83822_RMII_MODE_EN); if (ret) return ret; @@ -548,7 +659,7 @@ static int dp83826_config_init(struct phy_device *phydev) if (ret) return ret; } else { - ret = phy_clear_bits_mmd(phydev, DP83822_DEVADDR, MII_DP83822_RCSR, + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_RCSR, DP83822_RMII_MODE_EN); if (ret) return ret; @@ -560,7 +671,7 @@ static int dp83826_config_init(struct phy_device *phydev) FIELD_GET(DP83826_CFG_DAC_MINUS_MDIX_5_TO_4, dp83822->cfg_dac_minus)); mask = DP83826_VOD_CFG1_MINUS_MDIX_MASK | DP83826_VOD_CFG1_MINUS_MDI_MASK; - ret = phy_modify_mmd(phydev, DP83822_DEVADDR, MII_DP83826_VOD_CFG1, mask, val); + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83826_VOD_CFG1, mask, val); if (ret) return ret; @@ -568,7 +679,7 @@ static int dp83826_config_init(struct phy_device *phydev) FIELD_GET(DP83826_CFG_DAC_MINUS_MDIX_3_TO_0, dp83822->cfg_dac_minus)); mask = DP83826_VOD_CFG2_MINUS_MDIX_MASK; - ret = phy_modify_mmd(phydev, DP83822_DEVADDR, MII_DP83826_VOD_CFG2, mask, val); + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83826_VOD_CFG2, mask, val); if (ret) return ret; } @@ -577,7 +688,7 @@ static int dp83826_config_init(struct phy_device *phydev) val = FIELD_PREP(DP83826_VOD_CFG2_PLUS_MDIX_MASK, dp83822->cfg_dac_plus) | FIELD_PREP(DP83826_VOD_CFG2_PLUS_MDI_MASK, dp83822->cfg_dac_plus); mask = DP83826_VOD_CFG2_PLUS_MDIX_MASK | DP83826_VOD_CFG2_PLUS_MDI_MASK; - ret = phy_modify_mmd(phydev, DP83822_DEVADDR, MII_DP83826_VOD_CFG2, mask, val); + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83826_VOD_CFG2, mask, val); if (ret) return ret; } @@ -609,10 +720,66 @@ static int dp83822_phy_reset(struct phy_device *phydev) } #ifdef CONFIG_OF_MDIO +static int dp83822_of_init_leds(struct phy_device *phydev) +{ + struct device_node *node = phydev->mdio.dev.of_node; + struct dp83822_private *dp83822 = phydev->priv; + struct device_node *leds; + u32 index; + int err; + + if (!node) + return 0; + + leds = of_get_child_by_name(node, "leds"); + if (!leds) + return 0; + + for_each_available_child_of_node_scoped(leds, led) { + err = of_property_read_u32(led, "reg", &index); + if (err) { + of_node_put(leds); + return err; + } + + if (index <= DP83822_LED_INDEX_RX_D3_GPIO3) { + dp83822->led_pin_enable[index] = true; + } else { + of_node_put(leds); + return -EINVAL; + } + } + + of_node_put(leds); + /* LED_0 and COL(GPIO2) use the MLED function. MLED can be routed to + * only one of these two pins at a time. + */ + if (dp83822->led_pin_enable[DP83822_LED_INDEX_LED_0] && + dp83822->led_pin_enable[DP83822_LED_INDEX_COL_GPIO2]) { + phydev_err(phydev, "LED_0 and COL(GPIO2) cannot be used as LED output at the same time\n"); + return -EINVAL; + } + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_COL_GPIO2] && + dp83822->set_gpio2_clk_out) { + phydev_err(phydev, "COL(GPIO2) cannot be used as LED output, already used as clock output\n"); + return -EINVAL; + } + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_RX_D3_GPIO3] && + phydev->interface != PHY_INTERFACE_MODE_RMII) { + phydev_err(phydev, "RX_D3 can only be used as LED output when in RMII mode\n"); + return -EINVAL; + } + + return 0; +} + static int dp83822_of_init(struct phy_device *phydev) { struct dp83822_private *dp83822 = phydev->priv; struct device *dev = &phydev->mdio.dev; + const char *of_val; /* Signal detection for the PHY is only enabled if the FX_EN and the * SD_EN pins are strapped. Signal detection can only enabled if FX_EN @@ -625,7 +792,30 @@ static int dp83822_of_init(struct phy_device *phydev) dp83822->fx_enabled = device_property_present(dev, "ti,fiber-mode"); - return 0; + if (!device_property_read_string(dev, "ti,gpio2-clk-out", &of_val)) { + if (strcmp(of_val, "mac-if") == 0) { + dp83822->gpio2_clk_out = DP83822_CLK_SRC_MAC_IF; + } else if (strcmp(of_val, "xi") == 0) { + dp83822->gpio2_clk_out = DP83822_CLK_SRC_XI; + } else if (strcmp(of_val, "int-ref") == 0) { + dp83822->gpio2_clk_out = DP83822_CLK_SRC_INT_REF; + } else if (strcmp(of_val, "rmii-master-mode-ref") == 0) { + dp83822->gpio2_clk_out = DP83822_CLK_SRC_RMII_MASTER_MODE_REF; + } else if (strcmp(of_val, "free-running") == 0) { + dp83822->gpio2_clk_out = DP83822_CLK_SRC_FREE_RUNNING; + } else if (strcmp(of_val, "recovered") == 0) { + dp83822->gpio2_clk_out = DP83822_CLK_SRC_RECOVERED; + } else { + phydev_err(phydev, + "Invalid value for ti,gpio2-clk-out property (%s)\n", + of_val); + return -EINVAL; + } + + dp83822->set_gpio2_clk_out = true; + } + + return dp83822_of_init_leds(phydev); } static int dp83826_to_dac_minus_one_regval(int percent) @@ -673,7 +863,7 @@ static int dp83822_read_straps(struct phy_device *phydev) int fx_enabled, fx_sd_enable; int val; - val = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_SOR1); + val = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_SOR1); if (val < 0) return val; @@ -723,7 +913,9 @@ static int dp83822_probe(struct phy_device *phydev) if (ret) return ret; - dp83822_of_init(phydev); + ret = dp83822_of_init(phydev); + if (ret) + return ret; if (dp83822->fx_enabled) phydev->port = PORT_FIBRE; @@ -748,7 +940,7 @@ static int dp83822_suspend(struct phy_device *phydev) { int value; - value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG); + value = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_CFG); if (!(value & DP83822_WOL_EN)) genphy_suspend(phydev); @@ -762,14 +954,138 @@ static int dp83822_resume(struct phy_device *phydev) genphy_resume(phydev); - value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG); + value = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_CFG); - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, value | + phy_write_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_WOL_CFG, value | DP83822_WOL_CLR_INDICATION); return 0; } +static int dp83822_led_mode(u8 index, unsigned long rules) +{ + switch (rules) { + case BIT(TRIGGER_NETDEV_LINK): + return DP83822_LED_FN_LINK; + case BIT(TRIGGER_NETDEV_LINK_10): + return DP83822_LED_FN_LINK_10_BT; + case BIT(TRIGGER_NETDEV_LINK_100): + return DP83822_LED_FN_LINK_100_BTX; + case BIT(TRIGGER_NETDEV_FULL_DUPLEX): + return DP83822_LED_FN_FULL_DUPLEX; + case BIT(TRIGGER_NETDEV_TX): + return DP83822_LED_FN_TX; + case BIT(TRIGGER_NETDEV_RX): + return DP83822_LED_FN_RX; + case BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX): + return DP83822_LED_FN_RX_TX; + case BIT(TRIGGER_NETDEV_TX_ERR) | BIT(TRIGGER_NETDEV_RX_ERR): + return DP83822_LED_FN_RX_TX_ERR; + case BIT(TRIGGER_NETDEV_LINK) | BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX): + return DP83822_LED_FN_LINK_RX_TX; + default: + return -EOPNOTSUPP; + } +} + +static int dp83822_led_hw_is_supported(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + int mode; + + mode = dp83822_led_mode(index, rules); + if (mode < 0) + return mode; + + return 0; +} + +static int dp83822_led_hw_control_set(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + int mode; + + mode = dp83822_led_mode(index, rules); + if (mode < 0) + return mode; + + if (index == DP83822_LED_INDEX_LED_0 || index == DP83822_LED_INDEX_COL_GPIO2) + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, + MII_DP83822_MLEDCR, DP83822_MLEDCR_CFG, + FIELD_PREP(DP83822_MLEDCR_CFG, mode)); + else if (index == DP83822_LED_INDEX_LED_1_GPIO1) + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, + MII_DP83822_LEDCFG1, + DP83822_LEDCFG1_LED1_CTRL, + FIELD_PREP(DP83822_LEDCFG1_LED1_CTRL, + mode)); + else + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, + MII_DP83822_LEDCFG1, + DP83822_LEDCFG1_LED3_CTRL, + FIELD_PREP(DP83822_LEDCFG1_LED3_CTRL, + mode)); +} + +static int dp83822_led_hw_control_get(struct phy_device *phydev, u8 index, + unsigned long *rules) +{ + int val; + + if (index == DP83822_LED_INDEX_LED_0 || index == DP83822_LED_INDEX_COL_GPIO2) { + val = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_MLEDCR); + if (val < 0) + return val; + + val = FIELD_GET(DP83822_MLEDCR_CFG, val); + } else { + val = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_LEDCFG1); + if (val < 0) + return val; + + if (index == DP83822_LED_INDEX_LED_1_GPIO1) + val = FIELD_GET(DP83822_LEDCFG1_LED1_CTRL, val); + else + val = FIELD_GET(DP83822_LEDCFG1_LED3_CTRL, val); + } + + switch (val) { + case DP83822_LED_FN_LINK: + *rules = BIT(TRIGGER_NETDEV_LINK); + break; + case DP83822_LED_FN_LINK_10_BT: + *rules = BIT(TRIGGER_NETDEV_LINK_10); + break; + case DP83822_LED_FN_LINK_100_BTX: + *rules = BIT(TRIGGER_NETDEV_LINK_100); + break; + case DP83822_LED_FN_FULL_DUPLEX: + *rules = BIT(TRIGGER_NETDEV_FULL_DUPLEX); + break; + case DP83822_LED_FN_TX: + *rules = BIT(TRIGGER_NETDEV_TX); + break; + case DP83822_LED_FN_RX: + *rules = BIT(TRIGGER_NETDEV_RX); + break; + case DP83822_LED_FN_RX_TX: + *rules = BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX); + break; + case DP83822_LED_FN_RX_TX_ERR: + *rules = BIT(TRIGGER_NETDEV_TX_ERR) | BIT(TRIGGER_NETDEV_RX_ERR); + break; + case DP83822_LED_FN_LINK_RX_TX: + *rules = BIT(TRIGGER_NETDEV_LINK) | BIT(TRIGGER_NETDEV_TX) | + BIT(TRIGGER_NETDEV_RX); + break; + default: + *rules = 0; + break; + } + + return 0; +} + #define DP83822_PHY_DRIVER(_id, _name) \ { \ PHY_ID_MATCH_MODEL(_id), \ @@ -785,6 +1101,9 @@ static int dp83822_resume(struct phy_device *phydev) .handle_interrupt = dp83822_handle_interrupt, \ .suspend = dp83822_suspend, \ .resume = dp83822_resume, \ + .led_hw_is_supported = dp83822_led_hw_is_supported, \ + .led_hw_control_set = dp83822_led_hw_control_set, \ + .led_hw_control_get = dp83822_led_hw_control_get, \ } #define DP83825_PHY_DRIVER(_id, _name) \ @@ -830,7 +1149,7 @@ static struct phy_driver dp83822_driver[] = { }; module_phy_driver(dp83822_driver); -static struct mdio_device_id __maybe_unused dp83822_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83822_tbl[] = { { DP83822_PHY_ID, 0xfffffff0 }, { DP83825I_PHY_ID, 0xfffffff0 }, { DP83826C_PHY_ID, 0xfffffff0 }, diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c index 351411f0aa6f..d88b1999d596 100644 --- a/drivers/net/phy/dp83848.c +++ b/drivers/net/phy/dp83848.c @@ -123,7 +123,7 @@ static int dp83848_config_init(struct phy_device *phydev) return 0; } -static struct mdio_device_id __maybe_unused dp83848_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83848_tbl[] = { { TI_DP83848C_PHY_ID, 0xfffffff0 }, { NS_DP83848C_PHY_ID, 0xfffffff0 }, { TI_DP83620_PHY_ID, 0xfffffff0 }, diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 4120385c5a79..c1451df430ac 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -1210,7 +1210,7 @@ static struct phy_driver dp83867_driver[] = { }; module_phy_driver(dp83867_driver); -static struct mdio_device_id __maybe_unused dp83867_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83867_tbl[] = { { DP83867_PHY_ID, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index b6b38caf9c0e..a62cd838a9ea 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -928,7 +928,7 @@ static struct phy_driver dp83869_driver[] = { }; module_phy_driver(dp83869_driver); -static struct mdio_device_id __maybe_unused dp83869_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83869_tbl[] = { { PHY_ID_MATCH_MODEL(DP83869_PHY_ID) }, { PHY_ID_MATCH_MODEL(DP83561_PHY_ID) }, { } diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index 7ea32fb77190..e480c2a07450 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -403,7 +403,7 @@ static struct phy_driver dp83811_driver[] = { }; module_phy_driver(dp83811_driver); -static struct mdio_device_id __maybe_unused dp83811_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83811_tbl[] = { { DP83TC811_PHY_ID, 0xfffffff0 }, { }, }; diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c index 92aa3a2b9744..a42af9c168ec 100644 --- a/drivers/net/phy/dp83td510.c +++ b/drivers/net/phy/dp83td510.c @@ -34,6 +34,29 @@ #define DP83TD510E_CTRL_HW_RESET BIT(15) #define DP83TD510E_CTRL_SW_RESET BIT(14) +/* + * DP83TD510E_PKT_STAT_x registers correspond to similarly named registers + * in the datasheet (PKT_STAT_1 through PKT_STAT_6). These registers store + * 32-bit or 16-bit counters for TX and RX statistics and must be read in + * sequence to ensure the counters are cleared correctly. + * + * - DP83TD510E_PKT_STAT_1: Contains TX packet count bits [15:0]. + * - DP83TD510E_PKT_STAT_2: Contains TX packet count bits [31:16]. + * - DP83TD510E_PKT_STAT_3: Contains TX error packet count. + * - DP83TD510E_PKT_STAT_4: Contains RX packet count bits [15:0]. + * - DP83TD510E_PKT_STAT_5: Contains RX packet count bits [31:16]. + * - DP83TD510E_PKT_STAT_6: Contains RX error packet count. + * + * Keeping the register names as defined in the datasheet helps maintain + * clarity and alignment with the documentation. + */ +#define DP83TD510E_PKT_STAT_1 0x12b +#define DP83TD510E_PKT_STAT_2 0x12c +#define DP83TD510E_PKT_STAT_3 0x12d +#define DP83TD510E_PKT_STAT_4 0x12e +#define DP83TD510E_PKT_STAT_5 0x12f +#define DP83TD510E_PKT_STAT_6 0x130 + #define DP83TD510E_AN_STAT_1 0x60c #define DP83TD510E_MASTER_SLAVE_RESOL_FAIL BIT(15) @@ -58,8 +81,16 @@ static const u16 dp83td510_mse_sqi_map[] = { 0x0000 /* 24dB =< SNR */ }; +struct dp83td510_stats { + u64 tx_pkt_cnt; + u64 tx_err_pkt_cnt; + u64 rx_pkt_cnt; + u64 rx_err_pkt_cnt; +}; + struct dp83td510_priv { bool alcd_test_active; + struct dp83td510_stats stats; }; /* Time Domain Reflectometry (TDR) Functionality of DP83TD510 PHY @@ -177,6 +208,85 @@ struct dp83td510_priv { #define DP83TD510E_ALCD_COMPLETE BIT(15) #define DP83TD510E_ALCD_CABLE_LENGTH GENMASK(10, 0) +/** + * dp83td510_update_stats - Update the PHY statistics for the DP83TD510 PHY. + * @phydev: Pointer to the phy_device structure. + * + * The function reads the PHY statistics registers and updates the statistics + * structure. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83td510_update_stats(struct phy_device *phydev) +{ + struct dp83td510_priv *priv = phydev->priv; + u32 count; + int ret; + + /* The DP83TD510E_PKT_STAT registers are divided into two groups: + * - Group 1 (TX stats): DP83TD510E_PKT_STAT_1 to DP83TD510E_PKT_STAT_3 + * - Group 2 (RX stats): DP83TD510E_PKT_STAT_4 to DP83TD510E_PKT_STAT_6 + * + * Registers in each group are cleared only after reading them in a + * plain sequence (e.g., 1, 2, 3 for Group 1 or 4, 5, 6 for Group 2). + * Any deviation from the sequence, such as reading 1, 2, 1, 2, 3, will + * prevent the group from being cleared. Additionally, the counters + * for a group are frozen as soon as the first register in that group + * is accessed. + */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_1); + if (ret < 0) + return ret; + /* tx_pkt_cnt_15_0 */ + count = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_2); + if (ret < 0) + return ret; + /* tx_pkt_cnt_31_16 */ + count |= ret << 16; + priv->stats.tx_pkt_cnt += count; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_3); + if (ret < 0) + return ret; + /* tx_err_pkt_cnt */ + priv->stats.tx_err_pkt_cnt += ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_4); + if (ret < 0) + return ret; + /* rx_pkt_cnt_15_0 */ + count = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_5); + if (ret < 0) + return ret; + /* rx_pkt_cnt_31_16 */ + count |= ret << 16; + priv->stats.rx_pkt_cnt += count; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_6); + if (ret < 0) + return ret; + /* rx_err_pkt_cnt */ + priv->stats.rx_err_pkt_cnt += ret; + + return 0; +} + +static void dp83td510_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *eth_stats, + struct ethtool_phy_stats *stats) +{ + struct dp83td510_priv *priv = phydev->priv; + + stats->tx_packets = priv->stats.tx_pkt_cnt; + stats->tx_errors = priv->stats.tx_err_pkt_cnt; + stats->rx_packets = priv->stats.rx_pkt_cnt; + stats->rx_errors = priv->stats.rx_err_pkt_cnt; +} + static int dp83td510_config_intr(struct phy_device *phydev) { int ret; @@ -599,13 +709,15 @@ static struct phy_driver dp83td510_driver[] = { .get_sqi_max = dp83td510_get_sqi_max, .cable_test_start = dp83td510_cable_test_start, .cable_test_get_status = dp83td510_cable_test_get_status, + .get_phy_stats = dp83td510_get_phy_stats, + .update_stats = dp83td510_update_stats, .suspend = genphy_suspend, .resume = genphy_resume, } }; module_phy_driver(dp83td510_driver); -static struct mdio_device_id __maybe_unused dp83td510_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83td510_tbl[] = { { PHY_ID_MATCH_MODEL(DP83TD510E_PHY_ID) }, { } }; diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c index 0ef4d7dba065..050f4537d140 100644 --- a/drivers/net/phy/dp83tg720.c +++ b/drivers/net/phy/dp83tg720.c @@ -51,6 +51,9 @@ /* Register 0x0405: Unknown Register */ #define DP83TG720S_UNKNOWN_0405 0x405 +#define DP83TG720S_LINK_QUAL_3 0x547 +#define DP83TG720S_LINK_LOSS_CNT_MASK GENMASK(15, 10) + /* Register 0x0576: TDR Master Link Down Control */ #define DP83TG720S_TDR_MASTER_LINK_DOWN 0x576 @@ -60,6 +63,29 @@ /* In RGMII mode, Enable or disable the internal delay for TXD */ #define DP83TG720S_RGMII_TX_CLK_SEL BIT(0) +/* + * DP83TG720S_PKT_STAT_x registers correspond to similarly named registers + * in the datasheet (PKT_STAT_1 through PKT_STAT_6). These registers store + * 32-bit or 16-bit counters for TX and RX statistics and must be read in + * sequence to ensure the counters are cleared correctly. + * + * - DP83TG720S_PKT_STAT_1: Contains TX packet count bits [15:0]. + * - DP83TG720S_PKT_STAT_2: Contains TX packet count bits [31:16]. + * - DP83TG720S_PKT_STAT_3: Contains TX error packet count. + * - DP83TG720S_PKT_STAT_4: Contains RX packet count bits [15:0]. + * - DP83TG720S_PKT_STAT_5: Contains RX packet count bits [31:16]. + * - DP83TG720S_PKT_STAT_6: Contains RX error packet count. + * + * Keeping the register names as defined in the datasheet helps maintain + * clarity and alignment with the documentation. + */ +#define DP83TG720S_PKT_STAT_1 0x639 +#define DP83TG720S_PKT_STAT_2 0x63a +#define DP83TG720S_PKT_STAT_3 0x63b +#define DP83TG720S_PKT_STAT_4 0x63c +#define DP83TG720S_PKT_STAT_5 0x63d +#define DP83TG720S_PKT_STAT_6 0x63e + /* Register 0x083F: Unknown Register */ #define DP83TG720S_UNKNOWN_083F 0x83f @@ -69,6 +95,113 @@ #define DP83TG720_SQI_MAX 7 +struct dp83tg720_stats { + u64 link_loss_cnt; + u64 tx_pkt_cnt; + u64 tx_err_pkt_cnt; + u64 rx_pkt_cnt; + u64 rx_err_pkt_cnt; +}; + +struct dp83tg720_priv { + struct dp83tg720_stats stats; +}; + +/** + * dp83tg720_update_stats - Update the PHY statistics for the DP83TD510 PHY. + * @phydev: Pointer to the phy_device structure. + * + * The function reads the PHY statistics registers and updates the statistics + * structure. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83tg720_update_stats(struct phy_device *phydev) +{ + struct dp83tg720_priv *priv = phydev->priv; + u32 count; + int ret; + + /* Read the link loss count */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_LINK_QUAL_3); + if (ret < 0) + return ret; + /* link_loss_cnt */ + count = FIELD_GET(DP83TG720S_LINK_LOSS_CNT_MASK, ret); + priv->stats.link_loss_cnt += count; + + /* The DP83TG720S_PKT_STAT registers are divided into two groups: + * - Group 1 (TX stats): DP83TG720S_PKT_STAT_1 to DP83TG720S_PKT_STAT_3 + * - Group 2 (RX stats): DP83TG720S_PKT_STAT_4 to DP83TG720S_PKT_STAT_6 + * + * Registers in each group are cleared only after reading them in a + * plain sequence (e.g., 1, 2, 3 for Group 1 or 4, 5, 6 for Group 2). + * Any deviation from the sequence, such as reading 1, 2, 1, 2, 3, will + * prevent the group from being cleared. Additionally, the counters + * for a group are frozen as soon as the first register in that group + * is accessed. + */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_1); + if (ret < 0) + return ret; + /* tx_pkt_cnt_15_0 */ + count = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_2); + if (ret < 0) + return ret; + /* tx_pkt_cnt_31_16 */ + count |= ret << 16; + priv->stats.tx_pkt_cnt += count; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_3); + if (ret < 0) + return ret; + /* tx_err_pkt_cnt */ + priv->stats.tx_err_pkt_cnt += ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_4); + if (ret < 0) + return ret; + /* rx_pkt_cnt_15_0 */ + count = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_5); + if (ret < 0) + return ret; + /* rx_pkt_cnt_31_16 */ + count |= ret << 16; + priv->stats.rx_pkt_cnt += count; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_6); + if (ret < 0) + return ret; + /* rx_err_pkt_cnt */ + priv->stats.rx_err_pkt_cnt += ret; + + return 0; +} + +static void dp83tg720_get_link_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ + struct dp83tg720_priv *priv = phydev->priv; + + link_stats->link_down_events = priv->stats.link_loss_cnt; +} + +static void dp83tg720_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *eth_stats, + struct ethtool_phy_stats *stats) +{ + struct dp83tg720_priv *priv = phydev->priv; + + stats->tx_packets = priv->stats.tx_pkt_cnt; + stats->tx_errors = priv->stats.tx_err_pkt_cnt; + stats->rx_packets = priv->stats.rx_pkt_cnt; + stats->rx_errors = priv->stats.rx_err_pkt_cnt; +} + /** * dp83tg720_cable_test_start - Start the cable test for the DP83TG720 PHY. * @phydev: Pointer to the phy_device structure. @@ -182,6 +315,11 @@ static int dp83tg720_cable_test_get_status(struct phy_device *phydev, ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A, stat); + /* save the current stats before resetting the PHY */ + ret = dp83tg720_update_stats(phydev); + if (ret) + return ret; + return phy_init_hw(phydev); } @@ -217,6 +355,11 @@ static int dp83tg720_read_status(struct phy_device *phydev) phy_sts = phy_read(phydev, DP83TG720S_MII_REG_10); phydev->link = !!(phy_sts & DP83TG720S_LINK_STATUS); if (!phydev->link) { + /* save the current stats before resetting the PHY */ + ret = dp83tg720_update_stats(phydev); + if (ret) + return ret; + /* According to the "DP83TC81x, DP83TG72x Software * Implementation Guide", the PHY needs to be reset after a * link loss or if no link is created after at least 100ms. @@ -341,12 +484,27 @@ static int dp83tg720_config_init(struct phy_device *phydev) return genphy_c45_pma_baset1_read_master_slave(phydev); } +static int dp83tg720_probe(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + struct dp83tg720_priv *priv; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + return 0; +} + static struct phy_driver dp83tg720_driver[] = { { PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID), .name = "TI DP83TG720S", .flags = PHY_POLL_CABLE_TEST, + .probe = dp83tg720_probe, .config_aneg = dp83tg720_config_aneg, .read_status = dp83tg720_read_status, .get_features = genphy_c45_pma_read_ext_abilities, @@ -355,13 +513,16 @@ static struct phy_driver dp83tg720_driver[] = { .get_sqi_max = dp83tg720_get_sqi_max, .cable_test_start = dp83tg720_cable_test_start, .cable_test_get_status = dp83tg720_cable_test_get_status, + .get_link_stats = dp83tg720_get_link_stats, + .get_phy_stats = dp83tg720_get_phy_stats, + .update_stats = dp83tg720_update_stats, .suspend = genphy_suspend, .resume = genphy_resume, } }; module_phy_driver(dp83tg720_driver); -static struct mdio_device_id __maybe_unused dp83tg720_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83tg720_tbl[] = { { PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID) }, { } }; diff --git a/drivers/net/phy/et1011c.c b/drivers/net/phy/et1011c.c index be1b71d7cab7..6cd8d77586fd 100644 --- a/drivers/net/phy/et1011c.c +++ b/drivers/net/phy/et1011c.c @@ -94,7 +94,7 @@ static struct phy_driver et1011c_driver[] = { { module_phy_driver(et1011c_driver); -static struct mdio_device_id __maybe_unused et1011c_tbl[] = { +static const struct mdio_device_id __maybe_unused et1011c_tbl[] = { { 0x0282f014, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c index ee438b71a0b4..bbcc7d2b54cd 100644 --- a/drivers/net/phy/icplus.c +++ b/drivers/net/phy/icplus.c @@ -623,7 +623,7 @@ static struct phy_driver icplus_driver[] = { module_phy_driver(icplus_driver); -static struct mdio_device_id __maybe_unused icplus_tbl[] = { +static const struct mdio_device_id __maybe_unused icplus_tbl[] = { { PHY_ID_MATCH_MODEL(IP175C_PHY_ID) }, { PHY_ID_MATCH_MODEL(IP1001_PHY_ID) }, { PHY_ID_MATCH_EXACT(IP101A_PHY_ID) }, diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c index b672c55a7a4e..a44771e8acdc 100644 --- a/drivers/net/phy/intel-xway.c +++ b/drivers/net/phy/intel-xway.c @@ -529,7 +529,7 @@ static int xway_gphy_led_polarity_set(struct phy_device *phydev, int index, if (force_active_high) return phy_clear_bits(phydev, XWAY_MDIO_LED, XWAY_GPHY_LED_INV(index)); - unreachable(); + return -EINVAL; } static struct phy_driver xway_gphy[] = { @@ -691,7 +691,7 @@ static struct phy_driver xway_gphy[] = { }; module_phy_driver(xway_gphy); -static struct mdio_device_id __maybe_unused xway_gphy_tbl[] = { +static const struct mdio_device_id __maybe_unused xway_gphy_tbl[] = { { PHY_ID_PHY11G_1_3, 0xffffffff }, { PHY_ID_PHY22F_1_3, 0xffffffff }, { PHY_ID_PHY11G_1_4, 0xffffffff }, diff --git a/drivers/net/phy/lxt.c b/drivers/net/phy/lxt.c index e3bf827b7959..5251a61c8b0f 100644 --- a/drivers/net/phy/lxt.c +++ b/drivers/net/phy/lxt.c @@ -348,7 +348,7 @@ static struct phy_driver lxt97x_driver[] = { module_phy_driver(lxt97x_driver); -static struct mdio_device_id __maybe_unused lxt_tbl[] = { +static const struct mdio_device_id __maybe_unused lxt_tbl[] = { { 0x78100000, 0xfffffff0 }, { 0x001378e0, 0xfffffff0 }, { 0x00137a10, 0xfffffff0 }, diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c index 5107f58338af..a3996471a1c9 100644 --- a/drivers/net/phy/marvell-88q2xxx.c +++ b/drivers/net/phy/marvell-88q2xxx.c @@ -95,6 +95,10 @@ #define MDIO_MMD_PCS_MV_TDR_OFF_CUTOFF 65246 +struct mv88q2xxx_priv { + bool enable_temp; +}; + struct mmd_val { int devad; u32 regnum; @@ -710,17 +714,12 @@ static const struct hwmon_chip_info mv88q2xxx_hwmon_chip_info = { static int mv88q2xxx_hwmon_probe(struct phy_device *phydev) { + struct mv88q2xxx_priv *priv = phydev->priv; struct device *dev = &phydev->mdio.dev; struct device *hwmon; char *hwmon_name; - int ret; - - /* Enable temperature sense */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_TEMP_SENSOR2, - MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0); - if (ret < 0) - return ret; + priv->enable_temp = true; hwmon_name = devm_hwmon_sanitize_name(dev, dev_name(dev)); if (IS_ERR(hwmon_name)) return PTR_ERR(hwmon_name); @@ -743,6 +742,14 @@ static int mv88q2xxx_hwmon_probe(struct phy_device *phydev) static int mv88q2xxx_probe(struct phy_device *phydev) { + struct mv88q2xxx_priv *priv; + + priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + return mv88q2xxx_hwmon_probe(phydev); } @@ -810,6 +817,18 @@ static int mv88q222x_revb1_revb2_config_init(struct phy_device *phydev) static int mv88q222x_config_init(struct phy_device *phydev) { + struct mv88q2xxx_priv *priv = phydev->priv; + int ret; + + /* Enable temperature sense */ + if (priv->enable_temp) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + MDIO_MMD_PCS_MV_TEMP_SENSOR2, + MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0); + if (ret < 0) + return ret; + } + if (phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] == PHY_ID_88Q2220_REVB0) return mv88q222x_revb0_config_init(phydev); else @@ -939,7 +958,7 @@ static struct phy_driver mv88q2xxx_driver[] = { module_phy_driver(mv88q2xxx_driver); -static struct mdio_device_id __maybe_unused mv88q2xxx_tbl[] = { +static const struct mdio_device_id __maybe_unused mv88q2xxx_tbl[] = { { MARVELL_PHY_ID_88Q2110, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88Q2220, MARVELL_PHY_ID_MASK }, { /*sentinel*/ } diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index 0b777cdd7078..fad2f54c1eac 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -613,7 +613,7 @@ static struct phy_driver mv2222_drivers[] = { }; module_phy_driver(mv2222_drivers); -static struct mdio_device_id __maybe_unused mv2222_tbl[] = { +static const struct mdio_device_id __maybe_unused mv2222_tbl[] = { { MARVELL_PHY_ID_88X2222, MARVELL_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index cd50cd6a7f75..44e1927de499 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -717,6 +717,48 @@ static int marvell_config_aneg_fiber(struct phy_device *phydev) return genphy_check_and_restart_aneg(phydev, changed); } +static unsigned int m88e1111_inband_caps(struct phy_device *phydev, + phy_interface_t interface) +{ + /* In 1000base-X and SGMII modes, the inband mode can be changed + * through the Fibre page BMCR ANENABLE bit. + */ + if (interface == PHY_INTERFACE_MODE_1000BASEX || + interface == PHY_INTERFACE_MODE_SGMII) + return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE | + LINK_INBAND_BYPASS; + + return 0; +} + +static int m88e1111_config_inband(struct phy_device *phydev, unsigned int modes) +{ + u16 extsr, bmcr; + int err; + + if (phydev->interface != PHY_INTERFACE_MODE_1000BASEX && + phydev->interface != PHY_INTERFACE_MODE_SGMII) + return -EINVAL; + + if (modes == LINK_INBAND_BYPASS) + extsr = MII_M1111_HWCFG_SERIAL_AN_BYPASS; + else + extsr = 0; + + if (modes == LINK_INBAND_DISABLE) + bmcr = 0; + else + bmcr = BMCR_ANENABLE; + + err = phy_modify(phydev, MII_M1111_PHY_EXT_SR, + MII_M1111_HWCFG_SERIAL_AN_BYPASS, extsr); + if (err < 0) + return extsr; + + return phy_modify_paged(phydev, MII_MARVELL_FIBER_PAGE, MII_BMCR, + BMCR_ANENABLE, bmcr); +} + static int m88e1111_config_aneg(struct phy_device *phydev) { int extsr = phy_read(phydev, MII_M1111_PHY_EXT_SR); @@ -1508,7 +1550,6 @@ static int m88e1540_get_fld(struct phy_device *phydev, u8 *msecs) static int m88e1540_set_fld(struct phy_device *phydev, const u8 *msecs) { - struct ethtool_keee eee; int val, ret; if (*msecs == ETHTOOL_PHY_FAST_LINK_DOWN_OFF) @@ -1518,8 +1559,7 @@ static int m88e1540_set_fld(struct phy_device *phydev, const u8 *msecs) /* According to the Marvell data sheet EEE must be disabled for * Fast Link Down detection to work properly */ - ret = genphy_c45_ethtool_get_eee(phydev, &eee); - if (!ret && eee.eee_enabled) { + if (phydev->eee_cfg.eee_enabled) { phydev_warn(phydev, "Fast Link Down detection requires EEE to be disabled!\n"); return -EBUSY; } @@ -3677,6 +3717,8 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1112", /* PHY_GBIT_FEATURES */ .probe = marvell_probe, + .inband_caps = m88e1111_inband_caps, + .config_inband = m88e1111_config_inband, .config_init = m88e1112_config_init, .config_aneg = marvell_config_aneg, .config_intr = marvell_config_intr, @@ -3698,6 +3740,8 @@ static struct phy_driver marvell_drivers[] = { /* PHY_GBIT_FEATURES */ .flags = PHY_POLL_CABLE_TEST, .probe = marvell_probe, + .inband_caps = m88e1111_inband_caps, + .config_inband = m88e1111_config_inband, .config_init = m88e1111gbe_config_init, .config_aneg = m88e1111_config_aneg, .read_status = marvell_read_status, @@ -3721,6 +3765,8 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1111 (Finisar)", /* PHY_GBIT_FEATURES */ .probe = marvell_probe, + .inband_caps = m88e1111_inband_caps, + .config_inband = m88e1111_config_inband, .config_init = m88e1111gbe_config_init, .config_aneg = m88e1111_config_aneg, .read_status = marvell_read_status, @@ -4143,7 +4189,7 @@ static struct phy_driver marvell_drivers[] = { module_phy_driver(marvell_drivers); -static struct mdio_device_id __maybe_unused marvell_tbl[] = { +static const struct mdio_device_id __maybe_unused marvell_tbl[] = { { MARVELL_PHY_ID_88E1101, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E3082, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1112, MARVELL_PHY_ID_MASK }, diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 6642eb642d4b..623bdb8466b8 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -1484,7 +1484,7 @@ static struct phy_driver mv3310_drivers[] = { module_phy_driver(mv3310_drivers); -static struct mdio_device_id __maybe_unused mv3310_tbl[] = { +static const struct mdio_device_id __maybe_unused mv3310_tbl[] = { { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E2110, MARVELL_PHY_ID_MASK }, { }, diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c index 38dc898eaf7b..bdf99b327029 100644 --- a/drivers/net/phy/mediatek/mtk-ge-soc.c +++ b/drivers/net/phy/mediatek/mtk-ge-soc.c @@ -1356,7 +1356,7 @@ static struct phy_driver mtk_socphy_driver[] = { module_phy_driver(mtk_socphy_driver); -static struct mdio_device_id __maybe_unused mtk_socphy_tbl[] = { +static const struct mdio_device_id __maybe_unused mtk_socphy_tbl[] = { { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7981) }, { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7988) }, { } diff --git a/drivers/net/phy/mediatek/mtk-ge.c b/drivers/net/phy/mediatek/mtk-ge.c index ed2617bc20f4..b517ca8573e7 100644 --- a/drivers/net/phy/mediatek/mtk-ge.c +++ b/drivers/net/phy/mediatek/mtk-ge.c @@ -93,7 +93,7 @@ static struct phy_driver mtk_gephy_driver[] = { module_phy_driver(mtk_gephy_driver); -static struct mdio_device_id __maybe_unused mtk_gephy_tbl[] = { +static const struct mdio_device_id __maybe_unused mtk_gephy_tbl[] = { { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7530) }, { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7531) }, { } diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index bb9b33b6bce2..962ebbbc1348 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -221,7 +221,7 @@ static struct phy_driver meson_gxl_phy[] = { }, }; -static struct mdio_device_id __maybe_unused meson_gxl_tbl[] = { +static const struct mdio_device_id __maybe_unused meson_gxl_tbl[] = { { PHY_ID_MATCH_VENDOR(0x01814400) }, { PHY_ID_MATCH_VENDOR(0x01803301) }, { } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 3ef508840674..9c0b1c229af6 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -432,10 +432,12 @@ struct kszphy_ptp_priv { struct kszphy_priv { struct kszphy_ptp_priv ptp_priv; const struct kszphy_type *type; + struct clk *clk; int led_mode; u16 vct_ctrl1000; bool rmii_ref_clk_sel; bool rmii_ref_clk_sel_val; + bool clk_enable; u64 stats[ARRAY_SIZE(kszphy_hw_stats)]; }; @@ -2004,7 +2006,7 @@ static int ksz9477_config_init(struct phy_device *phydev) * in this switch shall be regarded as broken. */ if (phydev->dev_flags & MICREL_NO_EEE) - linkmode_fill(phydev->eee_broken_modes); + phy_disable_eee(phydev); return kszphy_config_init(phydev); } @@ -2050,6 +2052,46 @@ static void kszphy_get_stats(struct phy_device *phydev, data[i] = kszphy_get_stat(phydev, i); } +static void kszphy_enable_clk(struct phy_device *phydev) +{ + struct kszphy_priv *priv = phydev->priv; + + if (!priv->clk_enable && priv->clk) { + clk_prepare_enable(priv->clk); + priv->clk_enable = true; + } +} + +static void kszphy_disable_clk(struct phy_device *phydev) +{ + struct kszphy_priv *priv = phydev->priv; + + if (priv->clk_enable && priv->clk) { + clk_disable_unprepare(priv->clk); + priv->clk_enable = false; + } +} + +static int kszphy_generic_resume(struct phy_device *phydev) +{ + kszphy_enable_clk(phydev); + + return genphy_resume(phydev); +} + +static int kszphy_generic_suspend(struct phy_device *phydev) +{ + int ret; + + ret = genphy_suspend(phydev); + if (ret) + return ret; + + kszphy_disable_clk(phydev); + + return 0; +} + static int kszphy_suspend(struct phy_device *phydev) { /* Disable PHY Interrupts */ @@ -2059,7 +2101,7 @@ static int kszphy_suspend(struct phy_device *phydev) phydev->drv->config_intr(phydev); } - return genphy_suspend(phydev); + return kszphy_generic_suspend(phydev); } static void kszphy_parse_led_mode(struct phy_device *phydev) @@ -2090,7 +2132,9 @@ static int kszphy_resume(struct phy_device *phydev) { int ret; - genphy_resume(phydev); + ret = kszphy_generic_resume(phydev); + if (ret) + return ret; /* After switching from power-down to normal mode, an internal global * reset is automatically generated. Wait a minimum of 1 ms before @@ -2112,6 +2156,24 @@ static int kszphy_resume(struct phy_device *phydev) return 0; } +/* Because of errata DS80000700A, receiver error following software + * power down. Suspend and resume callbacks only disable and enable + * external rmii reference clock. + */ +static int ksz8041_resume(struct phy_device *phydev) +{ + kszphy_enable_clk(phydev); + + return 0; +} + +static int ksz8041_suspend(struct phy_device *phydev) +{ + kszphy_disable_clk(phydev); + + return 0; +} + static int ksz9477_resume(struct phy_device *phydev) { int ret; @@ -2159,7 +2221,10 @@ static int ksz8061_resume(struct phy_device *phydev) if (!(ret & BMCR_PDOWN)) return 0; - genphy_resume(phydev); + ret = kszphy_generic_resume(phydev); + if (ret) + return ret; + usleep_range(1000, 2000); /* Re-program the value after chip is reset. */ @@ -2177,6 +2242,11 @@ static int ksz8061_resume(struct phy_device *phydev) return 0; } +static int ksz8061_suspend(struct phy_device *phydev) +{ + return kszphy_suspend(phydev); +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -2217,10 +2287,14 @@ static int kszphy_probe(struct phy_device *phydev) } else if (!clk) { /* unnamed clock from the generic ethernet-phy binding */ clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, NULL); - if (IS_ERR(clk)) - return PTR_ERR(clk); } + if (IS_ERR(clk)) + return PTR_ERR(clk); + + clk_disable_unprepare(clk); + priv->clk = clk; + if (ksz8041_fiber_mode(phydev)) phydev->port = PORT_FIBRE; @@ -5290,6 +5364,21 @@ static int lan8841_probe(struct phy_device *phydev) return 0; } +static int lan8804_resume(struct phy_device *phydev) +{ + return kszphy_resume(phydev); +} + +static int lan8804_suspend(struct phy_device *phydev) +{ + return kszphy_generic_suspend(phydev); +} + +static int lan8841_resume(struct phy_device *phydev) +{ + return kszphy_generic_resume(phydev); +} + static int lan8841_suspend(struct phy_device *phydev) { struct kszphy_priv *priv = phydev->priv; @@ -5298,7 +5387,7 @@ static int lan8841_suspend(struct phy_device *phydev) if (ptp_priv->ptp_clock) ptp_cancel_worker_sync(ptp_priv->ptp_clock); - return genphy_suspend(phydev); + return kszphy_generic_suspend(phydev); } static struct phy_driver ksphy_driver[] = { @@ -5358,9 +5447,8 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, - /* No suspend/resume callbacks because of errata DS80000700A, - * receiver error following software power down. - */ + .suspend = ksz8041_suspend, + .resume = ksz8041_resume, }, { .phy_id = PHY_ID_KSZ8041RNLI, .phy_id_mask = MICREL_PHY_ID_MASK, @@ -5436,7 +5524,7 @@ static struct phy_driver ksphy_driver[] = { .soft_reset = genphy_soft_reset, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, - .suspend = kszphy_suspend, + .suspend = ksz8061_suspend, .resume = ksz8061_resume, }, { .phy_id = PHY_ID_KSZ9021, @@ -5507,8 +5595,8 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, - .suspend = genphy_suspend, - .resume = kszphy_resume, + .suspend = lan8804_suspend, + .resume = lan8804_resume, .config_intr = lan8804_config_intr, .handle_interrupt = lan8804_handle_interrupt, }, { @@ -5526,7 +5614,7 @@ static struct phy_driver ksphy_driver[] = { .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, .suspend = lan8841_suspend, - .resume = genphy_resume, + .resume = lan8841_resume, .cable_test_start = lan8814_cable_test_start, .cable_test_get_status = ksz886x_cable_test_get_status, }, { @@ -5601,7 +5689,7 @@ MODULE_DESCRIPTION("Micrel PHY driver"); MODULE_AUTHOR("David J. Choi"); MODULE_LICENSE("GPL"); -static struct mdio_device_id __maybe_unused micrel_tbl[] = { +static const struct mdio_device_id __maybe_unused micrel_tbl[] = { { PHY_ID_KSZ9021, 0x000ffffe }, { PHY_ID_KSZ9031, MICREL_PHY_ID_MASK }, { PHY_ID_KSZ9131, MICREL_PHY_ID_MASK }, diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index 691969a4910f..0e17cc458efd 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -548,7 +548,7 @@ static struct phy_driver microchip_phy_driver[] = { module_phy_driver(microchip_phy_driver); -static struct mdio_device_id __maybe_unused microchip_tbl[] = { +static const struct mdio_device_id __maybe_unused microchip_tbl[] = { { 0x0007c132, 0xfffffff2 }, { PHY_ID_MATCH_MODEL(PHY_ID_LAN937X_TX) }, { } diff --git a/drivers/net/phy/microchip_rds_ptp.c b/drivers/net/phy/microchip_rds_ptp.c new file mode 100644 index 000000000000..3e6bf10cdeed --- /dev/null +++ b/drivers/net/phy/microchip_rds_ptp.c @@ -0,0 +1,1309 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2024 Microchip Technology + +#include "microchip_rds_ptp.h" + +static int mchp_rds_phy_read_mmd(struct mchp_rds_ptp_clock *clock, + u32 offset, enum mchp_rds_ptp_base base) +{ + struct phy_device *phydev = clock->phydev; + u32 addr; + + addr = (offset + ((base == MCHP_RDS_PTP_PORT) ? BASE_PORT(clock) : + BASE_CLK(clock))); + + return phy_read_mmd(phydev, PTP_MMD(clock), addr); +} + +static int mchp_rds_phy_write_mmd(struct mchp_rds_ptp_clock *clock, + u32 offset, enum mchp_rds_ptp_base base, + u16 val) +{ + struct phy_device *phydev = clock->phydev; + u32 addr; + + addr = (offset + ((base == MCHP_RDS_PTP_PORT) ? BASE_PORT(clock) : + BASE_CLK(clock))); + + return phy_write_mmd(phydev, PTP_MMD(clock), addr, val); +} + +static int mchp_rds_phy_modify_mmd(struct mchp_rds_ptp_clock *clock, + u32 offset, enum mchp_rds_ptp_base base, + u16 mask, u16 val) +{ + struct phy_device *phydev = clock->phydev; + u32 addr; + + addr = (offset + ((base == MCHP_RDS_PTP_PORT) ? BASE_PORT(clock) : + BASE_CLK(clock))); + + return phy_modify_mmd(phydev, PTP_MMD(clock), addr, mask, val); +} + +static int mchp_rds_phy_set_bits_mmd(struct mchp_rds_ptp_clock *clock, + u32 offset, enum mchp_rds_ptp_base base, + u16 val) +{ + struct phy_device *phydev = clock->phydev; + u32 addr; + + addr = (offset + ((base == MCHP_RDS_PTP_PORT) ? BASE_PORT(clock) : + BASE_CLK(clock))); + + return phy_set_bits_mmd(phydev, PTP_MMD(clock), addr, val); +} + +static int mchp_get_pulsewidth(struct phy_device *phydev, + struct ptp_perout_request *perout_request, + int *pulse_width) +{ + struct timespec64 ts_period; + s64 ts_on_nsec, period_nsec; + struct timespec64 ts_on; + static const s64 sup_on_necs[] = { + 100, /* 100ns */ + 500, /* 500ns */ + 1000, /* 1us */ + 5000, /* 5us */ + 10000, /* 10us */ + 50000, /* 50us */ + 100000, /* 100us */ + 500000, /* 500us */ + 1000000, /* 1ms */ + 5000000, /* 5ms */ + 10000000, /* 10ms */ + 50000000, /* 50ms */ + 100000000, /* 100ms */ + 200000000, /* 200ms */ + }; + + ts_period.tv_sec = perout_request->period.sec; + ts_period.tv_nsec = perout_request->period.nsec; + + ts_on.tv_sec = perout_request->on.sec; + ts_on.tv_nsec = perout_request->on.nsec; + ts_on_nsec = timespec64_to_ns(&ts_on); + period_nsec = timespec64_to_ns(&ts_period); + + if (period_nsec < 200) { + phydev_warn(phydev, "perout period small, minimum is 200ns\n"); + return -EOPNOTSUPP; + } + + for (int i = 0; i < ARRAY_SIZE(sup_on_necs); i++) { + if (ts_on_nsec <= sup_on_necs[i]) { + *pulse_width = i; + break; + } + } + + phydev_info(phydev, "pulse width is %d\n", *pulse_width); + return 0; +} + +static int mchp_general_event_config(struct mchp_rds_ptp_clock *clock, + int pulse_width) +{ + int general_config; + + general_config = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_GEN_CFG, + MCHP_RDS_PTP_CLOCK); + if (general_config < 0) + return general_config; + + general_config &= ~MCHP_RDS_PTP_GEN_CFG_LTC_EVT_MASK; + general_config |= MCHP_RDS_PTP_GEN_CFG_LTC_EVT_SET(pulse_width); + general_config &= ~MCHP_RDS_PTP_GEN_CFG_RELOAD_ADD; + general_config |= MCHP_RDS_PTP_GEN_CFG_POLARITY; + + return mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_GEN_CFG, + MCHP_RDS_PTP_CLOCK, general_config); +} + +static int mchp_set_clock_reload(struct mchp_rds_ptp_clock *clock, + s64 period_sec, u32 period_nsec) +{ + int rc; + + rc = mchp_rds_phy_write_mmd(clock, + MCHP_RDS_PTP_CLK_TRGT_RELOAD_SEC_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(period_sec)); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, + MCHP_RDS_PTP_CLK_TRGT_RELOAD_SEC_HI, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(period_sec)); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, + MCHP_RDS_PTP_CLK_TRGT_RELOAD_NS_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(period_nsec)); + if (rc < 0) + return rc; + + return mchp_rds_phy_write_mmd(clock, + MCHP_RDS_PTP_CLK_TRGT_RELOAD_NS_HI, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(period_nsec) & 0x3fff); +} + +static int mchp_set_clock_target(struct mchp_rds_ptp_clock *clock, + s64 start_sec, u32 start_nsec) +{ + int rc; + + /* Set the start time */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CLK_TRGT_SEC_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(start_sec)); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CLK_TRGT_SEC_HI, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(start_sec)); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CLK_TRGT_NS_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(start_nsec)); + if (rc < 0) + return rc; + + return mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CLK_TRGT_NS_HI, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(start_nsec) & 0x3fff); +} + +static int mchp_rds_ptp_perout_off(struct mchp_rds_ptp_clock *clock) +{ + u16 general_config; + int rc; + + /* Set target to too far in the future, effectively disabling it */ + rc = mchp_set_clock_target(clock, 0xFFFFFFFF, 0); + if (rc < 0) + return rc; + + general_config = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_GEN_CFG, + MCHP_RDS_PTP_CLOCK); + general_config |= MCHP_RDS_PTP_GEN_CFG_RELOAD_ADD; + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_GEN_CFG, + MCHP_RDS_PTP_CLOCK, general_config); + if (rc < 0) + return rc; + + clock->mchp_rds_ptp_event = -1; + + return 0; +} + +static bool mchp_get_event(struct mchp_rds_ptp_clock *clock, int pin) +{ + if (clock->mchp_rds_ptp_event < 0 && pin == clock->event_pin) { + clock->mchp_rds_ptp_event = pin; + return true; + } + + return false; +} + +static int mchp_rds_ptp_perout(struct ptp_clock_info *ptpci, + struct ptp_perout_request *perout, int on) +{ + struct mchp_rds_ptp_clock *clock = container_of(ptpci, + struct mchp_rds_ptp_clock, + caps); + struct phy_device *phydev = clock->phydev; + int ret, event_pin, pulsewidth; + + /* Reject requests with unsupported flags */ + if (perout->flags & ~PTP_PEROUT_DUTY_CYCLE) + return -EOPNOTSUPP; + + event_pin = ptp_find_pin(clock->ptp_clock, PTP_PF_PEROUT, + perout->index); + if (event_pin != clock->event_pin) + return -EINVAL; + + if (!on) { + ret = mchp_rds_ptp_perout_off(clock); + return ret; + } + + if (!mchp_get_event(clock, event_pin)) + return -EINVAL; + + ret = mchp_get_pulsewidth(phydev, perout, &pulsewidth); + if (ret < 0) + return ret; + + /* Configure to pulse every period */ + ret = mchp_general_event_config(clock, pulsewidth); + if (ret < 0) + return ret; + + ret = mchp_set_clock_target(clock, perout->start.sec, + perout->start.nsec); + if (ret < 0) + return ret; + + return mchp_set_clock_reload(clock, perout->period.sec, + perout->period.nsec); +} + +static int mchp_rds_ptpci_enable(struct ptp_clock_info *ptpci, + struct ptp_clock_request *request, int on) +{ + switch (request->type) { + case PTP_CLK_REQ_PEROUT: + return mchp_rds_ptp_perout(ptpci, &request->perout, on); + default: + return -EINVAL; + } +} + +static int mchp_rds_ptpci_verify(struct ptp_clock_info *ptpci, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + struct mchp_rds_ptp_clock *clock = container_of(ptpci, + struct mchp_rds_ptp_clock, + caps); + + if (!(pin == clock->event_pin && chan == 0)) + return -1; + + switch (func) { + case PTP_PF_NONE: + case PTP_PF_PEROUT: + break; + default: + return -1; + } + + return 0; +} + +static int mchp_rds_ptp_flush_fifo(struct mchp_rds_ptp_clock *clock, + enum mchp_rds_ptp_fifo_dir dir) +{ + int rc; + + if (dir == MCHP_RDS_PTP_EGRESS_FIFO) + skb_queue_purge(&clock->tx_queue); + else + skb_queue_purge(&clock->rx_queue); + + for (int i = 0; i < MCHP_RDS_PTP_FIFO_SIZE; ++i) { + rc = mchp_rds_phy_read_mmd(clock, + dir == MCHP_RDS_PTP_EGRESS_FIFO ? + MCHP_RDS_PTP_TX_MSG_HDR2 : + MCHP_RDS_PTP_RX_MSG_HDR2, + MCHP_RDS_PTP_PORT); + if (rc < 0) + return rc; + } + return mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_INT_STS, + MCHP_RDS_PTP_PORT); +} + +static int mchp_rds_ptp_config_intr(struct mchp_rds_ptp_clock *clock, + bool enable) +{ + /* Enable or disable ptp interrupts */ + return mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_INT_EN, + MCHP_RDS_PTP_PORT, + enable ? MCHP_RDS_PTP_INT_ALL_MSK : 0); +} + +static void mchp_rds_ptp_txtstamp(struct mii_timestamper *mii_ts, + struct sk_buff *skb, int type) +{ + struct mchp_rds_ptp_clock *clock = container_of(mii_ts, + struct mchp_rds_ptp_clock, + mii_ts); + + switch (clock->hwts_tx_type) { + case HWTSTAMP_TX_ONESTEP_SYNC: + if (ptp_msg_is_sync(skb, type)) { + kfree_skb(skb); + return; + } + fallthrough; + case HWTSTAMP_TX_ON: + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + skb_queue_tail(&clock->tx_queue, skb); + break; + case HWTSTAMP_TX_OFF: + default: + kfree_skb(skb); + break; + } +} + +static bool mchp_rds_ptp_get_sig_rx(struct sk_buff *skb, u16 *sig) +{ + struct ptp_header *ptp_header; + int type; + + skb_push(skb, ETH_HLEN); + type = ptp_classify_raw(skb); + if (type == PTP_CLASS_NONE) + return false; + + ptp_header = ptp_parse_header(skb, type); + if (!ptp_header) + return false; + + skb_pull_inline(skb, ETH_HLEN); + + *sig = (__force u16)(ntohs(ptp_header->sequence_id)); + + return true; +} + +static bool mchp_rds_ptp_match_skb(struct mchp_rds_ptp_clock *clock, + struct mchp_rds_ptp_rx_ts *rx_ts) +{ + struct skb_shared_hwtstamps *shhwtstamps; + struct sk_buff *skb, *skb_tmp; + unsigned long flags; + bool rc = false; + u16 skb_sig; + + spin_lock_irqsave(&clock->rx_queue.lock, flags); + skb_queue_walk_safe(&clock->rx_queue, skb, skb_tmp) { + if (!mchp_rds_ptp_get_sig_rx(skb, &skb_sig)) + continue; + + if (skb_sig != rx_ts->seq_id) + continue; + + __skb_unlink(skb, &clock->rx_queue); + + rc = true; + break; + } + spin_unlock_irqrestore(&clock->rx_queue.lock, flags); + + if (rc) { + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = ktime_set(rx_ts->seconds, rx_ts->nsec); + netif_rx(skb); + } + + return rc; +} + +static void mchp_rds_ptp_match_rx_ts(struct mchp_rds_ptp_clock *clock, + struct mchp_rds_ptp_rx_ts *rx_ts) +{ + unsigned long flags; + + /* If we failed to match the skb add it to the queue for when + * the frame will come + */ + if (!mchp_rds_ptp_match_skb(clock, rx_ts)) { + spin_lock_irqsave(&clock->rx_ts_lock, flags); + list_add(&rx_ts->list, &clock->rx_ts_list); + spin_unlock_irqrestore(&clock->rx_ts_lock, flags); + } else { + kfree(rx_ts); + } +} + +static void mchp_rds_ptp_match_rx_skb(struct mchp_rds_ptp_clock *clock, + struct sk_buff *skb) +{ + struct mchp_rds_ptp_rx_ts *rx_ts, *tmp, *rx_ts_var = NULL; + struct skb_shared_hwtstamps *shhwtstamps; + unsigned long flags; + u16 skb_sig; + + if (!mchp_rds_ptp_get_sig_rx(skb, &skb_sig)) + return; + + /* Iterate over all RX timestamps and match it with the received skbs */ + spin_lock_irqsave(&clock->rx_ts_lock, flags); + list_for_each_entry_safe(rx_ts, tmp, &clock->rx_ts_list, list) { + /* Check if we found the signature we were looking for. */ + if (skb_sig != rx_ts->seq_id) + continue; + + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = ktime_set(rx_ts->seconds, rx_ts->nsec); + netif_rx(skb); + + rx_ts_var = rx_ts; + + break; + } + spin_unlock_irqrestore(&clock->rx_ts_lock, flags); + + if (rx_ts_var) { + list_del(&rx_ts_var->list); + kfree(rx_ts_var); + } else { + skb_queue_tail(&clock->rx_queue, skb); + } +} + +static bool mchp_rds_ptp_rxtstamp(struct mii_timestamper *mii_ts, + struct sk_buff *skb, int type) +{ + struct mchp_rds_ptp_clock *clock = container_of(mii_ts, + struct mchp_rds_ptp_clock, + mii_ts); + + if (clock->rx_filter == HWTSTAMP_FILTER_NONE || + type == PTP_CLASS_NONE) + return false; + + if ((type & clock->version) == 0 || (type & clock->layer) == 0) + return false; + + /* Here if match occurs skb is sent to application, If not skb is added + * to queue and sending skb to application will get handled when + * interrupt occurs i.e., it get handles in interrupt handler. By + * any means skb will reach the application so we should not return + * false here if skb doesn't matches. + */ + mchp_rds_ptp_match_rx_skb(clock, skb); + + return true; +} + +static int mchp_rds_ptp_hwtstamp(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct mchp_rds_ptp_clock *clock = + container_of(mii_ts, struct mchp_rds_ptp_clock, + mii_ts); + struct mchp_rds_ptp_rx_ts *rx_ts, *tmp; + int txcfg = 0, rxcfg = 0; + unsigned long flags; + int rc; + + clock->hwts_tx_type = config->tx_type; + clock->rx_filter = config->rx_filter; + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + clock->layer = 0; + clock->version = 0; + break; + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + clock->layer = PTP_CLASS_L4; + clock->version = PTP_CLASS_V2; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + clock->layer = PTP_CLASS_L2; + clock->version = PTP_CLASS_V2; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + clock->layer = PTP_CLASS_L4 | PTP_CLASS_L2; + clock->version = PTP_CLASS_V2; + break; + default: + return -ERANGE; + } + + /* Setup parsing of the frames and enable the timestamping for ptp + * frames + */ + if (clock->layer & PTP_CLASS_L2) { + rxcfg = MCHP_RDS_PTP_PARSE_CONFIG_LAYER2_EN; + txcfg = MCHP_RDS_PTP_PARSE_CONFIG_LAYER2_EN; + } + if (clock->layer & PTP_CLASS_L4) { + rxcfg |= MCHP_RDS_PTP_PARSE_CONFIG_IPV4_EN | + MCHP_RDS_PTP_PARSE_CONFIG_IPV6_EN; + txcfg |= MCHP_RDS_PTP_PARSE_CONFIG_IPV4_EN | + MCHP_RDS_PTP_PARSE_CONFIG_IPV6_EN; + } + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_RX_PARSE_CONFIG, + MCHP_RDS_PTP_PORT, rxcfg); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_TX_PARSE_CONFIG, + MCHP_RDS_PTP_PORT, txcfg); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_RX_TIMESTAMP_EN, + MCHP_RDS_PTP_PORT, + MCHP_RDS_PTP_TIMESTAMP_EN_ALL); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_TX_TIMESTAMP_EN, + MCHP_RDS_PTP_PORT, + MCHP_RDS_PTP_TIMESTAMP_EN_ALL); + if (rc < 0) + return rc; + + if (clock->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC) + /* Enable / disable of the TX timestamp in the SYNC frames */ + rc = mchp_rds_phy_modify_mmd(clock, MCHP_RDS_PTP_TX_MOD, + MCHP_RDS_PTP_PORT, + MCHP_RDS_TX_MOD_PTP_SYNC_TS_INSERT, + MCHP_RDS_TX_MOD_PTP_SYNC_TS_INSERT); + else + rc = mchp_rds_phy_modify_mmd(clock, MCHP_RDS_PTP_TX_MOD, + MCHP_RDS_PTP_PORT, + MCHP_RDS_TX_MOD_PTP_SYNC_TS_INSERT, + (u16)~MCHP_RDS_TX_MOD_PTP_SYNC_TS_INSERT); + + if (rc < 0) + return rc; + + /* In case of multiple starts and stops, these needs to be cleared */ + spin_lock_irqsave(&clock->rx_ts_lock, flags); + list_for_each_entry_safe(rx_ts, tmp, &clock->rx_ts_list, list) { + list_del(&rx_ts->list); + kfree(rx_ts); + } + spin_unlock_irqrestore(&clock->rx_ts_lock, flags); + + rc = mchp_rds_ptp_flush_fifo(clock, MCHP_RDS_PTP_INGRESS_FIFO); + if (rc < 0) + return rc; + + rc = mchp_rds_ptp_flush_fifo(clock, MCHP_RDS_PTP_EGRESS_FIFO); + if (rc < 0) + return rc; + + /* Now enable the timestamping interrupts */ + rc = mchp_rds_ptp_config_intr(clock, + config->rx_filter != HWTSTAMP_FILTER_NONE); + + return rc < 0 ? rc : 0; +} + +static int mchp_rds_ptp_ts_info(struct mii_timestamper *mii_ts, + struct kernel_ethtool_ts_info *info) +{ + struct mchp_rds_ptp_clock *clock = container_of(mii_ts, + struct mchp_rds_ptp_clock, + mii_ts); + + info->phc_index = ptp_clock_index(clock->ptp_clock); + + info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) | + BIT(HWTSTAMP_TX_ONESTEP_SYNC); + + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT); + + return 0; +} + +static int mchp_rds_ptp_ltc_adjtime(struct ptp_clock_info *info, s64 delta) +{ + struct mchp_rds_ptp_clock *clock = container_of(info, + struct mchp_rds_ptp_clock, + caps); + struct timespec64 ts; + bool add = true; + int rc = 0; + u32 nsec; + s32 sec; + + /* The HW allows up to 15 sec to adjust the time, but here we limit to + * 10 sec the adjustment. The reason is, in case the adjustment is 14 + * sec and 999999999 nsec, then we add 8ns to compensate the actual + * increment so the value can be bigger than 15 sec. Therefore limit the + * possible adjustments so we will not have these corner cases + */ + if (delta > 10000000000LL || delta < -10000000000LL) { + /* The timeadjustment is too big, so fall back using set time */ + u64 now; + + info->gettime64(info, &ts); + + now = ktime_to_ns(timespec64_to_ktime(ts)); + ts = ns_to_timespec64(now + delta); + + info->settime64(info, &ts); + return 0; + } + sec = div_u64_rem(abs(delta), NSEC_PER_SEC, &nsec); + if (delta < 0 && nsec != 0) { + /* It is not allowed to adjust low the nsec part, therefore + * subtract more from second part and add to nanosecond such + * that would roll over, so the second part will increase + */ + sec--; + nsec = NSEC_PER_SEC - nsec; + } + + /* Calculate the adjustments and the direction */ + if (delta < 0) + add = false; + + if (nsec > 0) { + /* add 8 ns to cover the likely normal increment */ + nsec += 8; + + if (nsec >= NSEC_PER_SEC) { + /* carry into seconds */ + sec++; + nsec -= NSEC_PER_SEC; + } + } + + mutex_lock(&clock->ptp_lock); + if (sec) { + sec = abs(sec); + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_STEP_ADJ_LO, + MCHP_RDS_PTP_CLOCK, sec); + if (rc < 0) + goto out_unlock; + + rc = mchp_rds_phy_set_bits_mmd(clock, MCHP_RDS_PTP_STEP_ADJ_HI, + MCHP_RDS_PTP_CLOCK, + ((add ? + MCHP_RDS_PTP_STEP_ADJ_HI_DIR : + 0) | ((sec >> 16) & + GENMASK(13, 0)))); + if (rc < 0) + goto out_unlock; + + rc = mchp_rds_phy_set_bits_mmd(clock, MCHP_RDS_PTP_CMD_CTL, + MCHP_RDS_PTP_CLOCK, + MCHP_RDS_PTP_CMD_CTL_LTC_STEP_SEC); + if (rc < 0) + goto out_unlock; + } + + if (nsec) { + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_STEP_ADJ_LO, + MCHP_RDS_PTP_CLOCK, + nsec & GENMASK(15, 0)); + if (rc < 0) + goto out_unlock; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_STEP_ADJ_HI, + MCHP_RDS_PTP_CLOCK, + (nsec >> 16) & GENMASK(13, 0)); + if (rc < 0) + goto out_unlock; + + rc = mchp_rds_phy_set_bits_mmd(clock, MCHP_RDS_PTP_CMD_CTL, + MCHP_RDS_PTP_CLOCK, + MCHP_RDS_PTP_CMD_CTL_LTC_STEP_NSEC); + } + + mutex_unlock(&clock->ptp_lock); + info->gettime64(info, &ts); + mutex_lock(&clock->ptp_lock); + + /* Target update is required for pulse generation on events that + * are enabled + */ + if (clock->mchp_rds_ptp_event >= 0) + mchp_set_clock_target(clock, + ts.tv_sec + MCHP_RDS_PTP_BUFFER_TIME, 0); +out_unlock: + mutex_unlock(&clock->ptp_lock); + + return rc; +} + +static int mchp_rds_ptp_ltc_adjfine(struct ptp_clock_info *info, + long scaled_ppm) +{ + struct mchp_rds_ptp_clock *clock = container_of(info, + struct mchp_rds_ptp_clock, + caps); + u16 rate_lo, rate_hi; + bool faster = true; + u32 rate; + int rc; + + if (!scaled_ppm) + return 0; + + if (scaled_ppm < 0) { + scaled_ppm = -scaled_ppm; + faster = false; + } + + rate = MCHP_RDS_PTP_1PPM_FORMAT * (upper_16_bits(scaled_ppm)); + rate += (MCHP_RDS_PTP_1PPM_FORMAT * (lower_16_bits(scaled_ppm))) >> 16; + + rate_lo = rate & GENMASK(15, 0); + rate_hi = (rate >> 16) & GENMASK(13, 0); + + if (faster) + rate_hi |= MCHP_RDS_PTP_LTC_RATE_ADJ_HI_DIR; + + mutex_lock(&clock->ptp_lock); + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_LTC_RATE_ADJ_HI, + MCHP_RDS_PTP_CLOCK, rate_hi); + if (rc < 0) + goto error; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_LTC_RATE_ADJ_LO, + MCHP_RDS_PTP_CLOCK, rate_lo); + if (rc > 0) + rc = 0; +error: + mutex_unlock(&clock->ptp_lock); + + return rc; +} + +static int mchp_rds_ptp_ltc_gettime64(struct ptp_clock_info *info, + struct timespec64 *ts) +{ + struct mchp_rds_ptp_clock *clock = container_of(info, + struct mchp_rds_ptp_clock, + caps); + time64_t secs; + int rc = 0; + s64 nsecs; + + mutex_lock(&clock->ptp_lock); + /* Set read bit to 1 to save current values of 1588 local time counter + * into PTP LTC seconds and nanoseconds registers. + */ + rc = mchp_rds_phy_set_bits_mmd(clock, MCHP_RDS_PTP_CMD_CTL, + MCHP_RDS_PTP_CLOCK, + MCHP_RDS_PTP_CMD_CTL_CLOCK_READ); + if (rc < 0) + goto out_unlock; + + /* Get LTC clock values */ + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_LTC_READ_SEC_HI, + MCHP_RDS_PTP_CLOCK); + if (rc < 0) + goto out_unlock; + secs = rc << 16; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_LTC_READ_SEC_MID, + MCHP_RDS_PTP_CLOCK); + if (rc < 0) + goto out_unlock; + secs |= rc; + secs <<= 16; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_LTC_READ_SEC_LO, + MCHP_RDS_PTP_CLOCK); + if (rc < 0) + goto out_unlock; + secs |= rc; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_LTC_READ_NS_HI, + MCHP_RDS_PTP_CLOCK); + if (rc < 0) + goto out_unlock; + nsecs = (rc & GENMASK(13, 0)); + nsecs <<= 16; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_LTC_READ_NS_LO, + MCHP_RDS_PTP_CLOCK); + if (rc < 0) + goto out_unlock; + nsecs |= rc; + + set_normalized_timespec64(ts, secs, nsecs); + + if (rc > 0) + rc = 0; +out_unlock: + mutex_unlock(&clock->ptp_lock); + + return rc; +} + +static int mchp_rds_ptp_ltc_settime64(struct ptp_clock_info *info, + const struct timespec64 *ts) +{ + struct mchp_rds_ptp_clock *clock = container_of(info, + struct mchp_rds_ptp_clock, + caps); + int rc; + + mutex_lock(&clock->ptp_lock); + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_LTC_SEC_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(ts->tv_sec)); + if (rc < 0) + goto out_unlock; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_LTC_SEC_MID, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(ts->tv_sec)); + if (rc < 0) + goto out_unlock; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_LTC_SEC_HI, + MCHP_RDS_PTP_CLOCK, + upper_32_bits(ts->tv_sec) & GENMASK(15, 0)); + if (rc < 0) + goto out_unlock; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_LTC_NS_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(ts->tv_nsec)); + if (rc < 0) + goto out_unlock; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_LTC_NS_HI, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(ts->tv_nsec) & GENMASK(13, 0)); + if (rc < 0) + goto out_unlock; + + /* Set load bit to 1 to write PTP LTC seconds and nanoseconds + * registers to 1588 local time counter. + */ + rc = mchp_rds_phy_set_bits_mmd(clock, MCHP_RDS_PTP_CMD_CTL, + MCHP_RDS_PTP_CLOCK, + MCHP_RDS_PTP_CMD_CTL_CLOCK_LOAD); + if (rc > 0) + rc = 0; +out_unlock: + mutex_unlock(&clock->ptp_lock); + + return rc; +} + +static bool mchp_rds_ptp_get_sig_tx(struct sk_buff *skb, u16 *sig) +{ + struct ptp_header *ptp_header; + int type; + + type = ptp_classify_raw(skb); + if (type == PTP_CLASS_NONE) + return false; + + ptp_header = ptp_parse_header(skb, type); + if (!ptp_header) + return false; + + *sig = (__force u16)(ntohs(ptp_header->sequence_id)); + + return true; +} + +static void mchp_rds_ptp_match_tx_skb(struct mchp_rds_ptp_clock *clock, + u32 seconds, u32 nsec, u16 seq_id) +{ + struct skb_shared_hwtstamps shhwtstamps; + struct sk_buff *skb, *skb_tmp; + unsigned long flags; + bool rc = false; + u16 skb_sig; + + spin_lock_irqsave(&clock->tx_queue.lock, flags); + skb_queue_walk_safe(&clock->tx_queue, skb, skb_tmp) { + if (!mchp_rds_ptp_get_sig_tx(skb, &skb_sig)) + continue; + + if (skb_sig != seq_id) + continue; + + __skb_unlink(skb, &clock->tx_queue); + rc = true; + break; + } + spin_unlock_irqrestore(&clock->tx_queue.lock, flags); + + if (rc) { + shhwtstamps.hwtstamp = ktime_set(seconds, nsec); + skb_complete_tx_timestamp(skb, &shhwtstamps); + } +} + +static struct mchp_rds_ptp_rx_ts + *mchp_rds_ptp_get_rx_ts(struct mchp_rds_ptp_clock *clock) +{ + struct phy_device *phydev = clock->phydev; + struct mchp_rds_ptp_rx_ts *rx_ts = NULL; + u32 sec, nsec; + int rc; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_RX_INGRESS_NS_HI, + MCHP_RDS_PTP_PORT); + if (rc < 0) + goto error; + if (!(rc & MCHP_RDS_PTP_RX_INGRESS_NS_HI_TS_VALID)) { + phydev_err(phydev, "RX Timestamp is not valid!\n"); + goto error; + } + nsec = (rc & GENMASK(13, 0)) << 16; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_RX_INGRESS_NS_LO, + MCHP_RDS_PTP_PORT); + if (rc < 0) + goto error; + nsec |= rc; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_RX_INGRESS_SEC_HI, + MCHP_RDS_PTP_PORT); + if (rc < 0) + goto error; + sec = rc << 16; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_RX_INGRESS_SEC_LO, + MCHP_RDS_PTP_PORT); + if (rc < 0) + goto error; + sec |= rc; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_RX_MSG_HDR2, + MCHP_RDS_PTP_PORT); + if (rc < 0) + goto error; + + rx_ts = kmalloc(sizeof(*rx_ts), GFP_KERNEL); + if (!rx_ts) + return NULL; + + rx_ts->seconds = sec; + rx_ts->nsec = nsec; + rx_ts->seq_id = rc; + +error: + return rx_ts; +} + +static void mchp_rds_ptp_process_rx_ts(struct mchp_rds_ptp_clock *clock) +{ + int caps; + + do { + struct mchp_rds_ptp_rx_ts *rx_ts; + + rx_ts = mchp_rds_ptp_get_rx_ts(clock); + if (rx_ts) + mchp_rds_ptp_match_rx_ts(clock, rx_ts); + + caps = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_CAP_INFO, + MCHP_RDS_PTP_PORT); + if (caps < 0) + return; + } while (MCHP_RDS_PTP_RX_TS_CNT(caps) > 0); +} + +static bool mchp_rds_ptp_get_tx_ts(struct mchp_rds_ptp_clock *clock, + u32 *sec, u32 *nsec, u16 *seq) +{ + int rc; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_TX_EGRESS_NS_HI, + MCHP_RDS_PTP_PORT); + if (rc < 0) + return false; + if (!(rc & MCHP_RDS_PTP_TX_EGRESS_NS_HI_TS_VALID)) + return false; + *nsec = (rc & GENMASK(13, 0)) << 16; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_TX_EGRESS_NS_LO, + MCHP_RDS_PTP_PORT); + if (rc < 0) + return false; + *nsec = *nsec | rc; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_TX_EGRESS_SEC_HI, + MCHP_RDS_PTP_PORT); + if (rc < 0) + return false; + *sec = rc << 16; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_TX_EGRESS_SEC_LO, + MCHP_RDS_PTP_PORT); + if (rc < 0) + return false; + *sec = *sec | rc; + + rc = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_TX_MSG_HDR2, + MCHP_RDS_PTP_PORT); + if (rc < 0) + return false; + + *seq = rc; + + return true; +} + +static void mchp_rds_ptp_process_tx_ts(struct mchp_rds_ptp_clock *clock) +{ + int caps; + + do { + u32 sec, nsec; + u16 seq; + + if (mchp_rds_ptp_get_tx_ts(clock, &sec, &nsec, &seq)) + mchp_rds_ptp_match_tx_skb(clock, sec, nsec, seq); + + caps = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_CAP_INFO, + MCHP_RDS_PTP_PORT); + if (caps < 0) + return; + } while (MCHP_RDS_PTP_TX_TS_CNT(caps) > 0); +} + +int mchp_rds_ptp_top_config_intr(struct mchp_rds_ptp_clock *clock, + u16 reg, u16 val, bool clear) +{ + if (clear) + return phy_clear_bits_mmd(clock->phydev, PTP_MMD(clock), reg, + val); + else + return phy_set_bits_mmd(clock->phydev, PTP_MMD(clock), reg, + val); +} +EXPORT_SYMBOL_GPL(mchp_rds_ptp_top_config_intr); + +irqreturn_t mchp_rds_ptp_handle_interrupt(struct mchp_rds_ptp_clock *clock) +{ + int irq_sts; + + /* To handle rogue interrupt scenarios */ + if (!clock) + return IRQ_NONE; + + do { + irq_sts = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_INT_STS, + MCHP_RDS_PTP_PORT); + if (irq_sts < 0) + return IRQ_NONE; + + if (irq_sts & MCHP_RDS_PTP_INT_RX_TS_EN) + mchp_rds_ptp_process_rx_ts(clock); + + if (irq_sts & MCHP_RDS_PTP_INT_TX_TS_EN) + mchp_rds_ptp_process_tx_ts(clock); + + if (irq_sts & MCHP_RDS_PTP_INT_TX_TS_OVRFL_EN) + mchp_rds_ptp_flush_fifo(clock, + MCHP_RDS_PTP_EGRESS_FIFO); + + if (irq_sts & MCHP_RDS_PTP_INT_RX_TS_OVRFL_EN) + mchp_rds_ptp_flush_fifo(clock, + MCHP_RDS_PTP_INGRESS_FIFO); + } while (irq_sts & (MCHP_RDS_PTP_INT_RX_TS_EN | + MCHP_RDS_PTP_INT_TX_TS_EN | + MCHP_RDS_PTP_INT_TX_TS_OVRFL_EN | + MCHP_RDS_PTP_INT_RX_TS_OVRFL_EN)); + + return IRQ_HANDLED; +} +EXPORT_SYMBOL_GPL(mchp_rds_ptp_handle_interrupt); + +static int mchp_rds_ptp_init(struct mchp_rds_ptp_clock *clock) +{ + int rc; + + /* Disable PTP */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CMD_CTL, + MCHP_RDS_PTP_CLOCK, + MCHP_RDS_PTP_CMD_CTL_DIS); + if (rc < 0) + return rc; + + /* Disable TSU */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_TSU_GEN_CONFIG, + MCHP_RDS_PTP_PORT, 0); + if (rc < 0) + return rc; + + /* Clear PTP interrupt status registers */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_TSU_HARD_RESET, + MCHP_RDS_PTP_PORT, + MCHP_RDS_PTP_TSU_HARDRESET); + if (rc < 0) + return rc; + + /* Predictor enable */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_LATENCY_CORRECTION_CTL, + MCHP_RDS_PTP_CLOCK, + MCHP_RDS_PTP_LATENCY_SETTING); + if (rc < 0) + return rc; + + /* Configure PTP operational mode */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_OP_MODE, + MCHP_RDS_PTP_CLOCK, + MCHP_RDS_PTP_OP_MODE_STANDALONE); + if (rc < 0) + return rc; + + /* Reference clock configuration */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_REF_CLK_CFG, + MCHP_RDS_PTP_CLOCK, + MCHP_RDS_PTP_REF_CLK_CFG_SET); + if (rc < 0) + return rc; + + /* Classifier configurations */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_RX_PARSE_CONFIG, + MCHP_RDS_PTP_PORT, 0); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_TX_PARSE_CONFIG, + MCHP_RDS_PTP_PORT, 0); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_TX_PARSE_L2_ADDR_EN, + MCHP_RDS_PTP_PORT, 0); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_RX_PARSE_L2_ADDR_EN, + MCHP_RDS_PTP_PORT, 0); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_RX_PARSE_IPV4_ADDR_EN, + MCHP_RDS_PTP_PORT, 0); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_TX_PARSE_IPV4_ADDR_EN, + MCHP_RDS_PTP_PORT, 0); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_RX_VERSION, + MCHP_RDS_PTP_PORT, + MCHP_RDS_PTP_MAX_VERSION(0xff) | + MCHP_RDS_PTP_MIN_VERSION(0x0)); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_TX_VERSION, + MCHP_RDS_PTP_PORT, + MCHP_RDS_PTP_MAX_VERSION(0xff) | + MCHP_RDS_PTP_MIN_VERSION(0x0)); + if (rc < 0) + return rc; + + /* Enable TSU */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_TSU_GEN_CONFIG, + MCHP_RDS_PTP_PORT, + MCHP_RDS_PTP_TSU_GEN_CFG_TSU_EN); + if (rc < 0) + return rc; + + /* Enable PTP */ + return mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CMD_CTL, + MCHP_RDS_PTP_CLOCK, + MCHP_RDS_PTP_CMD_CTL_EN); +} + +struct mchp_rds_ptp_clock *mchp_rds_ptp_probe(struct phy_device *phydev, u8 mmd, + u16 clk_base_addr, + u16 port_base_addr) +{ + struct mchp_rds_ptp_clock *clock; + int rc; + + clock = devm_kzalloc(&phydev->mdio.dev, sizeof(*clock), GFP_KERNEL); + if (!clock) + return ERR_PTR(-ENOMEM); + + clock->port_base_addr = port_base_addr; + clock->clk_base_addr = clk_base_addr; + clock->mmd = mmd; + + mutex_init(&clock->ptp_lock); + clock->pin_config = devm_kmalloc_array(&phydev->mdio.dev, + MCHP_RDS_PTP_N_PIN, + sizeof(*clock->pin_config), + GFP_KERNEL); + if (!clock->pin_config) + return ERR_PTR(-ENOMEM); + + for (int i = 0; i < MCHP_RDS_PTP_N_PIN; ++i) { + struct ptp_pin_desc *p = &clock->pin_config[i]; + + memset(p, 0, sizeof(*p)); + snprintf(p->name, sizeof(p->name), "pin%d", i); + p->index = i; + p->func = PTP_PF_NONE; + } + /* Register PTP clock */ + clock->caps.owner = THIS_MODULE; + snprintf(clock->caps.name, 30, "%s", phydev->drv->name); + clock->caps.max_adj = MCHP_RDS_PTP_MAX_ADJ; + clock->caps.n_ext_ts = 0; + clock->caps.pps = 0; + clock->caps.n_pins = MCHP_RDS_PTP_N_PIN; + clock->caps.n_per_out = MCHP_RDS_PTP_N_PEROUT; + clock->caps.pin_config = clock->pin_config; + clock->caps.adjfine = mchp_rds_ptp_ltc_adjfine; + clock->caps.adjtime = mchp_rds_ptp_ltc_adjtime; + clock->caps.gettime64 = mchp_rds_ptp_ltc_gettime64; + clock->caps.settime64 = mchp_rds_ptp_ltc_settime64; + clock->caps.enable = mchp_rds_ptpci_enable; + clock->caps.verify = mchp_rds_ptpci_verify; + clock->caps.getcrosststamp = NULL; + clock->ptp_clock = ptp_clock_register(&clock->caps, + &phydev->mdio.dev); + if (IS_ERR(clock->ptp_clock)) + return ERR_PTR(-EINVAL); + + /* Check if PHC support is missing at the configuration level */ + if (!clock->ptp_clock) + return NULL; + + /* Initialize the SW */ + skb_queue_head_init(&clock->tx_queue); + skb_queue_head_init(&clock->rx_queue); + INIT_LIST_HEAD(&clock->rx_ts_list); + spin_lock_init(&clock->rx_ts_lock); + + clock->mii_ts.rxtstamp = mchp_rds_ptp_rxtstamp; + clock->mii_ts.txtstamp = mchp_rds_ptp_txtstamp; + clock->mii_ts.hwtstamp = mchp_rds_ptp_hwtstamp; + clock->mii_ts.ts_info = mchp_rds_ptp_ts_info; + + phydev->mii_ts = &clock->mii_ts; + + clock->mchp_rds_ptp_event = -1; + + /* Timestamp selected by default to keep legacy API */ + phydev->default_timestamp = true; + + clock->phydev = phydev; + + rc = mchp_rds_ptp_init(clock); + if (rc < 0) + return ERR_PTR(rc); + + return clock; +} +EXPORT_SYMBOL_GPL(mchp_rds_ptp_probe); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MICROCHIP PHY RDS PTP driver"); +MODULE_AUTHOR("Divya Koppera"); diff --git a/drivers/net/phy/microchip_rds_ptp.h b/drivers/net/phy/microchip_rds_ptp.h new file mode 100644 index 000000000000..25af68337b94 --- /dev/null +++ b/drivers/net/phy/microchip_rds_ptp.h @@ -0,0 +1,247 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (C) 2024 Microchip Technology + */ + +#ifndef _MICROCHIP_RDS_PTP_H +#define _MICROCHIP_RDS_PTP_H + +#include +#include +#include +#include +#include +#include + +#define MCHP_RDS_PTP_CMD_CTL 0x0 +#define MCHP_RDS_PTP_CMD_CTL_LTC_STEP_NSEC BIT(6) +#define MCHP_RDS_PTP_CMD_CTL_LTC_STEP_SEC BIT(5) +#define MCHP_RDS_PTP_CMD_CTL_CLOCK_LOAD BIT(4) +#define MCHP_RDS_PTP_CMD_CTL_CLOCK_READ BIT(3) +#define MCHP_RDS_PTP_CMD_CTL_EN BIT(1) +#define MCHP_RDS_PTP_CMD_CTL_DIS BIT(0) + +#define MCHP_RDS_PTP_REF_CLK_CFG 0x2 +#define MCHP_RDS_PTP_REF_CLK_SRC_250MHZ 0x0 +#define MCHP_RDS_PTP_REF_CLK_PERIOD_OVERRIDE BIT(9) +#define MCHP_RDS_PTP_REF_CLK_PERIOD 4 +#define MCHP_RDS_PTP_REF_CLK_CFG_SET (MCHP_RDS_PTP_REF_CLK_SRC_250MHZ |\ + MCHP_RDS_PTP_REF_CLK_PERIOD_OVERRIDE |\ + MCHP_RDS_PTP_REF_CLK_PERIOD) + +#define MCHP_RDS_PTP_LTC_SEC_HI 0x5 +#define MCHP_RDS_PTP_LTC_SEC_MID 0x6 +#define MCHP_RDS_PTP_LTC_SEC_LO 0x7 +#define MCHP_RDS_PTP_LTC_NS_HI 0x8 +#define MCHP_RDS_PTP_LTC_NS_LO 0x9 +#define MCHP_RDS_PTP_LTC_RATE_ADJ_HI 0xc +#define MCHP_RDS_PTP_LTC_RATE_ADJ_HI_DIR BIT(15) +#define MCHP_RDS_PTP_LTC_RATE_ADJ_LO 0xd +#define MCHP_RDS_PTP_STEP_ADJ_HI 0x12 +#define MCHP_RDS_PTP_STEP_ADJ_HI_DIR BIT(15) +#define MCHP_RDS_PTP_STEP_ADJ_LO 0x13 +#define MCHP_RDS_PTP_LTC_READ_SEC_HI 0x29 +#define MCHP_RDS_PTP_LTC_READ_SEC_MID 0x2a +#define MCHP_RDS_PTP_LTC_READ_SEC_LO 0x2b +#define MCHP_RDS_PTP_LTC_READ_NS_HI 0x2c +#define MCHP_RDS_PTP_LTC_READ_NS_LO 0x2d +#define MCHP_RDS_PTP_OP_MODE 0x41 +#define MCHP_RDS_PTP_OP_MODE_DIS 0 +#define MCHP_RDS_PTP_OP_MODE_STANDALONE 1 +#define MCHP_RDS_PTP_LATENCY_CORRECTION_CTL 0x44 +#define MCHP_RDS_PTP_PREDICTOR_EN BIT(6) +#define MCHP_RDS_PTP_TX_PRED_DIS BIT(1) +#define MCHP_RDS_PTP_RX_PRED_DIS BIT(0) +#define MCHP_RDS_PTP_LATENCY_SETTING (MCHP_RDS_PTP_PREDICTOR_EN | \ + MCHP_RDS_PTP_TX_PRED_DIS | \ + MCHP_RDS_PTP_RX_PRED_DIS) + +#define MCHP_RDS_PTP_INT_EN 0x0 +#define MCHP_RDS_PTP_INT_STS 0x01 +#define MCHP_RDS_PTP_INT_TX_TS_OVRFL_EN BIT(3) +#define MCHP_RDS_PTP_INT_TX_TS_EN BIT(2) +#define MCHP_RDS_PTP_INT_RX_TS_OVRFL_EN BIT(1) +#define MCHP_RDS_PTP_INT_RX_TS_EN BIT(0) +#define MCHP_RDS_PTP_INT_ALL_MSK (MCHP_RDS_PTP_INT_TX_TS_OVRFL_EN | \ + MCHP_RDS_PTP_INT_TX_TS_EN | \ + MCHP_RDS_PTP_INT_RX_TS_OVRFL_EN |\ + MCHP_RDS_PTP_INT_RX_TS_EN) + +#define MCHP_RDS_PTP_CAP_INFO 0x2e +#define MCHP_RDS_PTP_TX_TS_CNT(v) (((v) & GENMASK(11, 8)) >> 8) +#define MCHP_RDS_PTP_RX_TS_CNT(v) ((v) & GENMASK(3, 0)) + +#define MCHP_RDS_PTP_RX_PARSE_CONFIG 0x42 +#define MCHP_RDS_PTP_RX_PARSE_L2_ADDR_EN 0x44 +#define MCHP_RDS_PTP_RX_PARSE_IPV4_ADDR_EN 0x45 + +#define MCHP_RDS_PTP_RX_TIMESTAMP_CONFIG 0x4e +#define MCHP_RDS_PTP_RX_TIMESTAMP_CONFIG_PTP_FCS_DIS BIT(0) + +#define MCHP_RDS_PTP_RX_VERSION 0x48 +#define MCHP_RDS_PTP_RX_TIMESTAMP_EN 0x4d + +#define MCHP_RDS_PTP_RX_INGRESS_NS_HI 0x54 +#define MCHP_RDS_PTP_RX_INGRESS_NS_HI_TS_VALID BIT(15) + +#define MCHP_RDS_PTP_RX_INGRESS_NS_LO 0x55 +#define MCHP_RDS_PTP_RX_INGRESS_SEC_HI 0x56 +#define MCHP_RDS_PTP_RX_INGRESS_SEC_LO 0x57 +#define MCHP_RDS_PTP_RX_MSG_HDR2 0x59 + +#define MCHP_RDS_PTP_TX_PARSE_CONFIG 0x82 +#define MCHP_RDS_PTP_PARSE_CONFIG_LAYER2_EN BIT(0) +#define MCHP_RDS_PTP_PARSE_CONFIG_IPV4_EN BIT(1) +#define MCHP_RDS_PTP_PARSE_CONFIG_IPV6_EN BIT(2) + +#define MCHP_RDS_PTP_TX_PARSE_L2_ADDR_EN 0x84 +#define MCHP_RDS_PTP_TX_PARSE_IPV4_ADDR_EN 0x85 + +#define MCHP_RDS_PTP_TX_VERSION 0x88 +#define MCHP_RDS_PTP_MAX_VERSION(x) (((x) & GENMASK(7, 0)) << 8) +#define MCHP_RDS_PTP_MIN_VERSION(x) ((x) & GENMASK(7, 0)) + +#define MCHP_RDS_PTP_TX_TIMESTAMP_EN 0x8d +#define MCHP_RDS_PTP_TIMESTAMP_EN_SYNC BIT(0) +#define MCHP_RDS_PTP_TIMESTAMP_EN_DREQ BIT(1) +#define MCHP_RDS_PTP_TIMESTAMP_EN_PDREQ BIT(2) +#define MCHP_RDS_PTP_TIMESTAMP_EN_PDRES BIT(3) +#define MCHP_RDS_PTP_TIMESTAMP_EN_ALL (MCHP_RDS_PTP_TIMESTAMP_EN_SYNC |\ + MCHP_RDS_PTP_TIMESTAMP_EN_DREQ |\ + MCHP_RDS_PTP_TIMESTAMP_EN_PDREQ |\ + MCHP_RDS_PTP_TIMESTAMP_EN_PDRES) + +#define MCHP_RDS_PTP_TX_TIMESTAMP_CONFIG 0x8e +#define MCHP_RDS_PTP_TX_TIMESTAMP_CONFIG_PTP_FCS_DIS BIT(0) + +#define MCHP_RDS_PTP_TX_MOD 0x8f +#define MCHP_RDS_TX_MOD_PTP_SYNC_TS_INSERT BIT(12) + +#define MCHP_RDS_PTP_TX_EGRESS_NS_HI 0x94 +#define MCHP_RDS_PTP_TX_EGRESS_NS_HI_TS_VALID BIT(15) + +#define MCHP_RDS_PTP_TX_EGRESS_NS_LO 0x95 +#define MCHP_RDS_PTP_TX_EGRESS_SEC_HI 0x96 +#define MCHP_RDS_PTP_TX_EGRESS_SEC_LO 0x97 +#define MCHP_RDS_PTP_TX_MSG_HDR2 0x99 + +#define MCHP_RDS_PTP_TSU_GEN_CONFIG 0xc0 +#define MCHP_RDS_PTP_TSU_GEN_CFG_TSU_EN BIT(0) + +#define MCHP_RDS_PTP_TSU_HARD_RESET 0xc1 +#define MCHP_RDS_PTP_TSU_HARDRESET BIT(0) + +#define MCHP_RDS_PTP_CLK_TRGT_SEC_HI 0x15 +#define MCHP_RDS_PTP_CLK_TRGT_SEC_LO 0x16 +#define MCHP_RDS_PTP_CLK_TRGT_NS_HI 0x17 +#define MCHP_RDS_PTP_CLK_TRGT_NS_LO 0x18 + +#define MCHP_RDS_PTP_CLK_TRGT_RELOAD_SEC_HI 0x19 +#define MCHP_RDS_PTP_CLK_TRGT_RELOAD_SEC_LO 0x1a +#define MCHP_RDS_PTP_CLK_TRGT_RELOAD_NS_HI 0x1b +#define MCHP_RDS_PTP_CLK_TRGT_RELOAD_NS_LO 0x1c + +#define MCHP_RDS_PTP_GEN_CFG 0x01 +#define MCHP_RDS_PTP_GEN_CFG_LTC_EVT_MASK GENMASK(11, 8) + +#define MCHP_RDS_PTP_GEN_CFG_LTC_EVT_SET(value) (((value) & 0xF) << 4) +#define MCHP_RDS_PTP_GEN_CFG_RELOAD_ADD BIT(0) +#define MCHP_RDS_PTP_GEN_CFG_POLARITY BIT(1) + +/* Represents 1ppm adjustment in 2^32 format with + * each nsec contains 4 clock cycles in 250MHz. + * The value is calculated as following: (1/1000000)/((2^-32)/4) + */ +#define MCHP_RDS_PTP_1PPM_FORMAT 17179 +#define MCHP_RDS_PTP_FIFO_SIZE 8 +#define MCHP_RDS_PTP_MAX_ADJ 31249999 + +#define MCHP_RDS_PTP_BUFFER_TIME 2 +#define MCHP_RDS_PTP_N_PIN 4 +#define MCHP_RDS_PTP_N_PEROUT 1 + +#define BASE_CLK(p) ((p)->clk_base_addr) +#define BASE_PORT(p) ((p)->port_base_addr) +#define PTP_MMD(p) ((p)->mmd) + +enum mchp_rds_ptp_base { + MCHP_RDS_PTP_PORT, + MCHP_RDS_PTP_CLOCK +}; + +enum mchp_rds_ptp_fifo_dir { + MCHP_RDS_PTP_INGRESS_FIFO, + MCHP_RDS_PTP_EGRESS_FIFO +}; + +struct mchp_rds_ptp_clock { + struct mii_timestamper mii_ts; + struct phy_device *phydev; + struct ptp_clock *ptp_clock; + + struct sk_buff_head tx_queue; + struct sk_buff_head rx_queue; + struct list_head rx_ts_list; + + struct ptp_clock_info caps; + + /* Lock for Rx ts fifo */ + spinlock_t rx_ts_lock; + int hwts_tx_type; + + enum hwtstamp_rx_filters rx_filter; + int layer; + int version; + u16 port_base_addr; + u16 clk_base_addr; + + /* Lock for phc */ + struct mutex ptp_lock; + u8 mmd; + int mchp_rds_ptp_event; + int event_pin; + struct ptp_pin_desc *pin_config; +}; + +struct mchp_rds_ptp_rx_ts { + struct list_head list; + u32 seconds; + u32 nsec; + u16 seq_id; +}; + +#if IS_ENABLED(CONFIG_MICROCHIP_PHY_RDS_PTP) + +struct mchp_rds_ptp_clock *mchp_rds_ptp_probe(struct phy_device *phydev, u8 mmd, + u16 clk_base, u16 port_base); + +int mchp_rds_ptp_top_config_intr(struct mchp_rds_ptp_clock *clock, + u16 reg, u16 val, bool enable); + +irqreturn_t mchp_rds_ptp_handle_interrupt(struct mchp_rds_ptp_clock *clock); + +#else + +static inline struct mchp_rds_ptp_clock *mchp_rds_ptp_probe(struct phy_device + *phydev, u8 mmd, + u16 clk_base, + u16 port_base) +{ + return NULL; +} + +static inline int mchp_rds_ptp_top_config_intr(struct mchp_rds_ptp_clock *clock, + u16 reg, u16 val, bool enable) +{ + return 0; +} + +static inline irqreturn_t mchp_rds_ptp_handle_interrupt(struct + mchp_rds_ptp_clock + * clock) +{ + return IRQ_NONE; +} + +#endif //CONFIG_MICROCHIP_PHY_RDS_PTP + +#endif //_MICROCHIP_RDS_PTP_H diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index b17bf6708003..62b36a318100 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -10,11 +10,15 @@ #include #include #include +#include "microchip_rds_ptp.h" #define PHY_ID_LAN87XX 0x0007c150 #define PHY_ID_LAN937X 0x0007c180 #define PHY_ID_LAN887X 0x0007c1f0 +#define MCHP_RDS_PTP_LTC_BASE_ADDR 0xe000 +#define MCHP_RDS_PTP_PORT_BASE_ADDR (MCHP_RDS_PTP_LTC_BASE_ADDR + 0x800) + /* External Register Control Register */ #define LAN87XX_EXT_REG_CTL (0x14) #define LAN87XX_EXT_REG_CTL_RD_CTL (0x1000) @@ -229,10 +233,14 @@ #define LAN887X_INT_STS 0xf000 #define LAN887X_INT_MSK 0xf001 +#define LAN887X_INT_MSK_P1588_MOD_INT_MSK BIT(3) #define LAN887X_INT_MSK_T1_PHY_INT_MSK BIT(2) #define LAN887X_INT_MSK_LINK_UP_MSK BIT(1) #define LAN887X_INT_MSK_LINK_DOWN_MSK BIT(0) +#define LAN887X_MX_CHIP_TOP_REG_CONTROL1 0xF002 +#define LAN887X_MX_CHIP_TOP_REG_CONTROL1_EVT_EN BIT(8) + #define LAN887X_MX_CHIP_TOP_LINK_MSK (LAN887X_INT_MSK_LINK_UP_MSK |\ LAN887X_INT_MSK_LINK_DOWN_MSK) @@ -319,6 +327,8 @@ struct lan887x_regwr_map { struct lan887x_priv { u64 stats[ARRAY_SIZE(lan887x_hw_stats)]; + struct mchp_rds_ptp_clock *clock; + bool init_done; }; static int lan937x_dsp_workaround(struct phy_device *phydev, u16 ereg, u8 bank) @@ -1269,8 +1279,28 @@ static int lan887x_get_features(struct phy_device *phydev) static int lan887x_phy_init(struct phy_device *phydev) { + struct lan887x_priv *priv = phydev->priv; int ret; + if (!priv->init_done && phy_interrupt_is_valid(phydev)) { + priv->clock = mchp_rds_ptp_probe(phydev, MDIO_MMD_VEND1, + MCHP_RDS_PTP_LTC_BASE_ADDR, + MCHP_RDS_PTP_PORT_BASE_ADDR); + if (IS_ERR(priv->clock)) + return PTR_ERR(priv->clock); + + /* Enable pin mux for EVT */ + phy_modify_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_MX_CHIP_TOP_REG_CONTROL1, + LAN887X_MX_CHIP_TOP_REG_CONTROL1_EVT_EN, + LAN887X_MX_CHIP_TOP_REG_CONTROL1_EVT_EN); + + /* Initialize pin numbers specific to PEROUT */ + priv->clock->event_pin = 3; + + priv->init_done = true; + } + /* Clear loopback */ ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG2, @@ -1470,6 +1500,7 @@ static int lan887x_probe(struct phy_device *phydev) if (!priv) return -ENOMEM; + priv->init_done = false; phydev->priv = priv; return lan887x_phy_setup(phydev); @@ -1518,6 +1549,7 @@ static void lan887x_get_strings(struct phy_device *phydev, u8 *data) static int lan887x_config_intr(struct phy_device *phydev) { + struct lan887x_priv *priv = phydev->priv; int rc; if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { @@ -1537,12 +1569,24 @@ static int lan887x_config_intr(struct phy_device *phydev) rc = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_INT_STS); } + if (rc < 0) + return rc; - return rc < 0 ? rc : 0; + if (phy_is_default_hwtstamp(phydev)) { + return mchp_rds_ptp_top_config_intr(priv->clock, + LAN887X_INT_MSK, + LAN887X_INT_MSK_P1588_MOD_INT_MSK, + (phydev->interrupts == + PHY_INTERRUPT_ENABLED)); + } + + return 0; } static irqreturn_t lan887x_handle_interrupt(struct phy_device *phydev) { + struct lan887x_priv *priv = phydev->priv; + int rc = IRQ_NONE; int irq_status; irq_status = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_INT_STS); @@ -1553,10 +1597,13 @@ static irqreturn_t lan887x_handle_interrupt(struct phy_device *phydev) if (irq_status & LAN887X_MX_CHIP_TOP_LINK_MSK) { phy_trigger_machine(phydev); - return IRQ_HANDLED; + rc = IRQ_HANDLED; } - return IRQ_NONE; + if (irq_status & LAN887X_INT_MSK_P1588_MOD_INT_MSK) + rc = mchp_rds_ptp_handle_interrupt(priv->clock); + + return rc; } static int lan887x_cd_reset(struct phy_device *phydev, diff --git a/drivers/net/phy/microchip_t1s.c b/drivers/net/phy/microchip_t1s.c index 75d291154b4c..e50a0c102a86 100644 --- a/drivers/net/phy/microchip_t1s.c +++ b/drivers/net/phy/microchip_t1s.c @@ -497,7 +497,7 @@ static struct phy_driver microchip_t1s_driver[] = { module_phy_driver(microchip_t1s_driver); -static struct mdio_device_id __maybe_unused tbl[] = { +static const struct mdio_device_id __maybe_unused tbl[] = { { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVB1) }, { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVC1) }, { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVC2) }, diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index bee381200ab8..19cf12ee8990 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -2699,7 +2699,7 @@ static struct phy_driver vsc85xx_driver[] = { module_phy_driver(vsc85xx_driver); -static struct mdio_device_id __maybe_unused vsc85xx_tbl[] = { +static const struct mdio_device_id __maybe_unused vsc85xx_tbl[] = { { PHY_ID_MATCH_VENDOR(PHY_VENDOR_MSCC) }, { } }; diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index db3c1f72b407..94d9cb727121 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -1014,7 +1014,7 @@ static int gpy_led_polarity_set(struct phy_device *phydev, int index, if (force_active_high) return phy_clear_bits(phydev, PHY_LED, PHY_LED_POLARITY(index)); - unreachable(); + return -EINVAL; } static struct phy_driver gpy_drivers[] = { @@ -1274,7 +1274,7 @@ static struct phy_driver gpy_drivers[] = { }; module_phy_driver(gpy_drivers); -static struct mdio_device_id __maybe_unused gpy_tbl[] = { +static const struct mdio_device_id __maybe_unused gpy_tbl[] = { {PHY_ID_MATCH_MODEL(PHY_ID_GPY2xx)}, {PHY_ID_GPY115B, PHY_ID_GPYx15B_MASK}, {PHY_ID_MATCH_MODEL(PHY_ID_GPY115C)}, diff --git a/drivers/net/phy/national.c b/drivers/net/phy/national.c index 9ae9cc6b23c2..7f3ff322892e 100644 --- a/drivers/net/phy/national.c +++ b/drivers/net/phy/national.c @@ -173,7 +173,7 @@ MODULE_DESCRIPTION("NatSemi PHY driver"); MODULE_AUTHOR("Stuart Menefy"); MODULE_LICENSE("GPL"); -static struct mdio_device_id __maybe_unused ns_tbl[] = { +static const struct mdio_device_id __maybe_unused ns_tbl[] = { { DP83865_PHY_ID, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/ncn26000.c b/drivers/net/phy/ncn26000.c index 5680584f659e..cabdd83c614f 100644 --- a/drivers/net/phy/ncn26000.c +++ b/drivers/net/phy/ncn26000.c @@ -159,7 +159,7 @@ static struct phy_driver ncn26000_driver[] = { module_phy_driver(ncn26000_driver); -static struct mdio_device_id __maybe_unused ncn26000_tbl[] = { +static const struct mdio_device_id __maybe_unused ncn26000_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_NCN26000) }, { } }; diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index ade544bc007d..34231b5b9175 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1297,6 +1297,8 @@ static int nxp_c45_soft_reset(struct phy_device *phydev) if (ret) return ret; + usleep_range(2000, 2050); + return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, VEND1_DEVICE_CONTROL, ret, !(ret & DEVICE_CONTROL_RESET), 20000, @@ -2008,7 +2010,7 @@ static struct phy_driver nxp_c45_driver[] = { module_phy_driver(nxp_c45_driver); -static struct mdio_device_id __maybe_unused nxp_c45_tbl[] = { +static const struct mdio_device_id __maybe_unused nxp_c45_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103) }, { PHY_ID_MATCH_MODEL(PHY_ID_TJA_1120) }, { /*sentinel*/ }, diff --git a/drivers/net/phy/nxp-cbtx.c b/drivers/net/phy/nxp-cbtx.c index 3d25491043a3..3286fcb4f47e 100644 --- a/drivers/net/phy/nxp-cbtx.c +++ b/drivers/net/phy/nxp-cbtx.c @@ -215,7 +215,7 @@ static struct phy_driver cbtx_driver[] = { module_phy_driver(cbtx_driver); -static struct mdio_device_id __maybe_unused cbtx_tbl[] = { +static const struct mdio_device_id __maybe_unused cbtx_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_CBTX_SJA1110) }, { }, }; diff --git a/drivers/net/phy/nxp-tja11xx.c b/drivers/net/phy/nxp-tja11xx.c index 2c263ae44b4f..ed7fa26bac8e 100644 --- a/drivers/net/phy/nxp-tja11xx.c +++ b/drivers/net/phy/nxp-tja11xx.c @@ -888,7 +888,7 @@ static struct phy_driver tja11xx_driver[] = { module_phy_driver(tja11xx_driver); -static struct mdio_device_id __maybe_unused tja11xx_tbl[] = { +static const struct mdio_device_id __maybe_unused tja11xx_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA1100) }, { PHY_ID_MATCH_MODEL(PHY_ID_TJA1101) }, { PHY_ID_MATCH_MODEL(PHY_ID_TJA1102) }, diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 944ae98ad110..0dac08e85304 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -1469,18 +1469,17 @@ EXPORT_SYMBOL_GPL(genphy_c45_plca_get_status); * @phydev: target phy_device struct * @adv: variable to store advertised linkmodes * @lp: variable to store LP advertised linkmodes - * @is_enabled: variable to store EEE enabled/disabled configuration value * * Description: this function will read local and link partner PHY * advertisements. Compare them return current EEE state. */ int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, - unsigned long *lp, bool *is_enabled) + unsigned long *lp) { __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp_adv) = {}; __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp_lp) = {}; __ETHTOOL_DECLARE_LINK_MODE_MASK(common); - bool eee_enabled, eee_active; + bool eee_active; int ret; ret = genphy_c45_read_eee_adv(phydev, tmp_adv); @@ -1491,9 +1490,8 @@ int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, if (ret) return ret; - eee_enabled = !linkmode_empty(tmp_adv); linkmode_and(common, tmp_adv, tmp_lp); - if (eee_enabled && !linkmode_empty(common)) + if (!linkmode_empty(tmp_adv) && !linkmode_empty(common)) eee_active = phy_check_valid(phydev->speed, phydev->duplex, common); else @@ -1503,8 +1501,6 @@ int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, linkmode_copy(adv, tmp_adv); if (lp) linkmode_copy(lp, tmp_lp); - if (is_enabled) - *is_enabled = eee_enabled; return eee_active; } @@ -1521,15 +1517,13 @@ EXPORT_SYMBOL(genphy_c45_eee_is_active); int genphy_c45_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data) { - bool is_enabled; int ret; ret = genphy_c45_eee_is_active(phydev, data->advertised, - data->lp_advertised, &is_enabled); + data->lp_advertised); if (ret < 0) return ret; - data->eee_enabled = is_enabled; data->eee_active = phydev->eee_active; linkmode_copy(data->supported, phydev->supported_eee); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 0d20b534122b..d0c1718e2b16 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -615,6 +615,49 @@ int phy_ethtool_get_stats(struct phy_device *phydev, } EXPORT_SYMBOL(phy_ethtool_get_stats); +/** + * __phy_ethtool_get_phy_stats - Retrieve standardized PHY statistics + * @phydev: Pointer to the PHY device + * @phy_stats: Pointer to ethtool_eth_phy_stats structure + * @phydev_stats: Pointer to ethtool_phy_stats structure + * + * Fetches PHY statistics using a kernel-defined interface for consistent + * diagnostics. Unlike phy_ethtool_get_stats(), which allows custom stats, + * this function enforces a standardized format for better interoperability. + */ +void __phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats) +{ + if (!phydev->drv || !phydev->drv->get_phy_stats) + return; + + mutex_lock(&phydev->lock); + phydev->drv->get_phy_stats(phydev, phy_stats, phydev_stats); + mutex_unlock(&phydev->lock); +} + +/** + * __phy_ethtool_get_link_ext_stats - Retrieve extended link statistics for a PHY + * @phydev: Pointer to the PHY device + * @link_stats: Pointer to the structure to store extended link statistics + * + * Populates the ethtool_link_ext_stats structure with link down event counts + * and additional driver-specific link statistics, if available. + */ +void __phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ + link_stats->link_down_events = READ_ONCE(phydev->link_down_events); + + if (!phydev->drv || !phydev->drv->get_link_stats) + return; + + mutex_lock(&phydev->lock); + phydev->drv->get_link_stats(phydev, link_stats); + mutex_unlock(&phydev->lock); +} + /** * phy_ethtool_get_plca_cfg - Get PLCA RS configuration * @phydev: the phy_device struct @@ -988,8 +1031,7 @@ static int phy_check_link_status(struct phy_device *phydev) if (phydev->link && phydev->state != PHY_RUNNING) { phy_check_downshift(phydev); phydev->state = PHY_RUNNING; - err = genphy_c45_eee_is_active(phydev, - NULL, NULL, NULL); + err = genphy_c45_eee_is_active(phydev, NULL, NULL); phydev->eee_active = err > 0; phydev->enable_tx_lpi = phydev->eee_cfg.tx_lpi_enabled && phydev->eee_active; @@ -1005,6 +1047,59 @@ static int phy_check_link_status(struct phy_device *phydev) return 0; } +/** + * phy_inband_caps - query which in-band signalling modes are supported + * @phydev: a pointer to a &struct phy_device + * @interface: the interface mode for the PHY + * + * Returns zero if it is unknown what in-band signalling is supported by the + * PHY (e.g. because the PHY driver doesn't implement the method.) Otherwise, + * returns a bit mask of the LINK_INBAND_* values from + * &enum link_inband_signalling to describe which inband modes are supported + * by the PHY for this interface mode. + */ +unsigned int phy_inband_caps(struct phy_device *phydev, + phy_interface_t interface) +{ + if (phydev->drv && phydev->drv->inband_caps) + return phydev->drv->inband_caps(phydev, interface); + + return 0; +} +EXPORT_SYMBOL_GPL(phy_inband_caps); + +/** + * phy_config_inband - configure the desired PHY in-band mode + * @phydev: the phy_device struct + * @modes: in-band modes to configure + * + * Description: disables, enables or enables-with-bypass in-band signalling + * between the PHY and host system. + * + * Returns: zero on success, or negative errno value. + */ +int phy_config_inband(struct phy_device *phydev, unsigned int modes) +{ + int err; + + if (!!(modes & LINK_INBAND_DISABLE) + + !!(modes & LINK_INBAND_ENABLE) + + !!(modes & LINK_INBAND_BYPASS) != 1) + return -EINVAL; + + mutex_lock(&phydev->lock); + if (!phydev->drv) + err = -EIO; + else if (!phydev->drv->config_inband) + err = -EOPNOTSUPP; + else + err = phydev->drv->config_inband(phydev, modes); + mutex_unlock(&phydev->lock); + + return err; +} +EXPORT_SYMBOL(phy_config_inband); + /** * _phy_start_aneg - start auto-negotiation for this PHY device * @phydev: the phy_device struct @@ -1346,6 +1441,23 @@ static int phy_enable_interrupts(struct phy_device *phydev) return phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED); } +/** + * phy_update_stats - Update PHY device statistics if supported. + * @phydev: Pointer to the PHY device structure. + * + * If the PHY driver provides an update_stats callback, this function + * invokes it to update the PHY statistics. If not, it returns 0. + * + * Return: 0 on success, or a negative error code if the callback fails. + */ +static int phy_update_stats(struct phy_device *phydev) +{ + if (!phydev->drv->update_stats) + return 0; + + return phydev->drv->update_stats(phydev); +} + /** * phy_request_interrupt - request and enable interrupt for a PHY device * @phydev: target phy_device struct @@ -1415,6 +1527,9 @@ static enum phy_state_work _phy_state_machine(struct phy_device *phydev) case PHY_RUNNING: err = phy_check_link_status(phydev); func = &phy_check_link_status; + + if (!err) + err = phy_update_stats(phydev); break; case PHY_CABLETEST: err = phydev->drv->cable_test_get_status(phydev, &finished); @@ -1588,6 +1703,47 @@ void phy_mac_interrupt(struct phy_device *phydev) } EXPORT_SYMBOL(phy_mac_interrupt); +/** + * phy_eee_tx_clock_stop_capable() - indicate whether the MAC can stop tx clock + * @phydev: target phy_device struct + * + * Indicate whether the MAC can disable the transmit xMII clock while in LPI + * state. Returns 1 if the MAC may stop the transmit clock, 0 if the MAC must + * not stop the transmit clock, or negative error. + */ +int phy_eee_tx_clock_stop_capable(struct phy_device *phydev) +{ + int stat1; + + stat1 = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_STAT1); + if (stat1 < 0) + return stat1; + + return !!(stat1 & MDIO_PCS_STAT1_CLKSTOP_CAP); +} +EXPORT_SYMBOL_GPL(phy_eee_tx_clock_stop_capable); + +/** + * phy_eee_rx_clock_stop() - configure PHY receive clock in LPI + * @phydev: target phy_device struct + * @clk_stop_enable: flag to indicate whether the clock can be stopped + * + * Configure whether the PHY can disable its receive clock during LPI mode, + * See IEEE 802.3 sections 22.2.2.2, 35.2.2.10, and 45.2.3.1.4. + * + * Returns: 0 or negative error. + */ +int phy_eee_rx_clock_stop(struct phy_device *phydev, bool clk_stop_enable) +{ + /* Configure the PHY to stop receiving xMII + * clock while it is signaling LPI. + */ + return phy_modify_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, + MDIO_PCS_CTRL1_CLKSTOP_EN, + clk_stop_enable ? MDIO_PCS_CTRL1_CLKSTOP_EN : 0); +} +EXPORT_SYMBOL_GPL(phy_eee_rx_clock_stop); + /** * phy_init_eee - init and check the EEE feature * @phydev: target phy_device struct @@ -1605,18 +1761,14 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) if (!phydev->drv) return -EIO; - ret = genphy_c45_eee_is_active(phydev, NULL, NULL, NULL); + ret = genphy_c45_eee_is_active(phydev, NULL, NULL); if (ret < 0) return ret; if (!ret) return -EPROTONOSUPPORT; if (clk_stop_enable) - /* Configure the PHY to stop receiving xMII - * clock while it is signaling LPI. - */ - ret = phy_set_bits_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, - MDIO_PCS_CTRL1_CLKSTOP_EN); + ret = phy_eee_rx_clock_stop(phydev, true); return ret < 0 ? ret : 0; } @@ -1649,8 +1801,8 @@ EXPORT_SYMBOL(phy_get_eee_err); * @phydev: target phy_device struct * @data: ethtool_keee data * - * Description: reports the Supported/Advertisement/LP Advertisement - * capabilities, etc. + * Description: get the current EEE settings, filling in all members of + * @data. */ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data) { diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index b26bb33cd1d4..46713d27412b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -59,15 +60,9 @@ EXPORT_SYMBOL_GPL(phy_gbit_features); __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_gbit_fibre_features); -__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; -EXPORT_SYMBOL_GPL(phy_gbit_all_ports_features); - __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_10gbit_features); -__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; -EXPORT_SYMBOL_GPL(phy_10gbit_fec_features); - const int phy_basic_ports_array[3] = { ETHTOOL_LINK_MODE_Autoneg_BIT, ETHTOOL_LINK_MODE_TP_BIT, @@ -75,12 +70,7 @@ const int phy_basic_ports_array[3] = { }; EXPORT_SYMBOL_GPL(phy_basic_ports_array); -const int phy_fibre_port_array[1] = { - ETHTOOL_LINK_MODE_FIBRE_BIT, -}; -EXPORT_SYMBOL_GPL(phy_fibre_port_array); - -const int phy_all_ports_features_array[7] = { +static const int phy_all_ports_features_array[7] = { ETHTOOL_LINK_MODE_Autoneg_BIT, ETHTOOL_LINK_MODE_TP_BIT, ETHTOOL_LINK_MODE_MII_BIT, @@ -89,7 +79,6 @@ const int phy_all_ports_features_array[7] = { ETHTOOL_LINK_MODE_BNC_BIT, ETHTOOL_LINK_MODE_Backplane_BIT, }; -EXPORT_SYMBOL_GPL(phy_all_ports_features_array); const int phy_10_100_features_array[4] = { ETHTOOL_LINK_MODE_10baseT_Half_BIT, @@ -123,20 +112,6 @@ const int phy_10gbit_features_array[1] = { }; EXPORT_SYMBOL_GPL(phy_10gbit_features_array); -static const int phy_10gbit_fec_features_array[1] = { - ETHTOOL_LINK_MODE_10000baseR_FEC_BIT, -}; - -__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; -EXPORT_SYMBOL_GPL(phy_10gbit_full_features); - -static const int phy_10gbit_full_features_array[] = { - ETHTOOL_LINK_MODE_10baseT_Full_BIT, - ETHTOOL_LINK_MODE_100baseT_Full_BIT, - ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - ETHTOOL_LINK_MODE_10000baseT_Full_BIT, -}; - static const int phy_eee_cap1_features_array[] = { ETHTOOL_LINK_MODE_100baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT, @@ -198,20 +173,7 @@ static void features_init(void) linkmode_set_bit_array(phy_gbit_features_array, ARRAY_SIZE(phy_gbit_features_array), phy_gbit_fibre_features); - linkmode_set_bit_array(phy_fibre_port_array, - ARRAY_SIZE(phy_fibre_port_array), - phy_gbit_fibre_features); - - /* 10/100 half/full + 1000 half/full + TP/MII/FIBRE/AUI/BNC/Backplane*/ - linkmode_set_bit_array(phy_all_ports_features_array, - ARRAY_SIZE(phy_all_ports_features_array), - phy_gbit_all_ports_features); - linkmode_set_bit_array(phy_10_100_features_array, - ARRAY_SIZE(phy_10_100_features_array), - phy_gbit_all_ports_features); - linkmode_set_bit_array(phy_gbit_features_array, - ARRAY_SIZE(phy_gbit_features_array), - phy_gbit_all_ports_features); + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phy_gbit_fibre_features); /* 10/100 half/full + 1000 half/full + 10G full*/ linkmode_set_bit_array(phy_all_ports_features_array, @@ -227,17 +189,6 @@ static void features_init(void) ARRAY_SIZE(phy_10gbit_features_array), phy_10gbit_features); - /* 10/100/1000/10G full */ - linkmode_set_bit_array(phy_all_ports_features_array, - ARRAY_SIZE(phy_all_ports_features_array), - phy_10gbit_full_features); - linkmode_set_bit_array(phy_10gbit_full_features_array, - ARRAY_SIZE(phy_10gbit_full_features_array), - phy_10gbit_full_features); - /* 10G FEC only */ - linkmode_set_bit_array(phy_10gbit_fec_features_array, - ARRAY_SIZE(phy_10gbit_fec_features_array), - phy_10gbit_fec_features); linkmode_set_bit_array(phy_eee_cap1_features_array, ARRAY_SIZE(phy_eee_cap1_features_array), phy_eee_cap1_features); @@ -1998,6 +1949,15 @@ void phy_detach(struct phy_device *phydev) phy_suspend(phydev); if (dev) { + struct hwtstamp_provider *hwprov; + + hwprov = rtnl_dereference(dev->hwprov); + /* Disable timestamp if it is the one selected */ + if (hwprov && hwprov->phydev == phydev) { + rcu_assign_pointer(dev->hwprov, NULL); + kfree_rcu(hwprov, rcu_head); + } + phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; phy_link_topo_del_phy(dev, phydev); @@ -2993,6 +2953,23 @@ void phy_support_eee(struct phy_device *phydev) } EXPORT_SYMBOL(phy_support_eee); +/** + * phy_disable_eee - Disable EEE for the PHY + * @phydev: Target phy_device struct + * + * This function is used by MAC drivers for MAC's which don't support EEE. + * It disables EEE on the PHY layer. + */ +void phy_disable_eee(struct phy_device *phydev) +{ + linkmode_zero(phydev->advertising_eee); + phydev->eee_cfg.tx_lpi_enabled = false; + phydev->eee_cfg.eee_enabled = false; + /* don't let userspace re-enable EEE advertisement */ + linkmode_fill(phydev->eee_broken_modes); +} +EXPORT_SYMBOL_GPL(phy_disable_eee); + /** * phy_support_sym_pause - Enable support of symmetrical pause * @phydev: target phy_device struct @@ -3773,6 +3750,8 @@ static const struct ethtool_phy_ops phy_ethtool_phy_ops = { static const struct phylib_stubs __phylib_stubs = { .hwtstamp_get = __phy_hwtstamp_get, .hwtstamp_set = __phy_hwtstamp_set, + .get_phy_stats = __phy_ethtool_get_phy_stats, + .get_link_ext_stats = __phy_ethtool_get_link_ext_stats, }; static void phylib_register_stubs(void) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 30a654e98352..214b62fba991 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -56,9 +56,11 @@ struct phylink { struct phy_device *phydev; phy_interface_t link_interface; /* PHY_INTERFACE_xxx */ u8 cfg_link_an_mode; /* MLO_AN_xxx */ - u8 cur_link_an_mode; + u8 req_link_an_mode; /* Requested MLO_AN_xxx mode */ + u8 act_link_an_mode; /* Active MLO_AN_xxx mode */ u8 link_port; /* The current non-phy ethtool port */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_lpi); /* The link configuration settings */ struct phylink_link_state link_config; @@ -74,17 +76,26 @@ struct phylink { struct mutex state_mutex; struct phylink_link_state phy_state; + unsigned int phy_ib_mode; struct work_struct resolve; unsigned int pcs_neg_mode; unsigned int pcs_state; bool link_failed; + bool mac_supports_eee_ops; + bool mac_supports_eee; + bool phy_enable_tx_lpi; + bool mac_enable_tx_lpi; + bool mac_tx_clk_stop; + u32 mac_tx_lpi_timer; struct sfp_bus *sfp_bus; bool sfp_may_have_phy; DECLARE_PHY_INTERFACE_MASK(sfp_interfaces); __ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support); u8 sfp_port; + + struct eee_config eee_cfg; }; #define phylink_printk(level, pl, fmt, ...) \ @@ -174,6 +185,24 @@ static const char *phylink_an_mode_str(unsigned int mode) return mode < ARRAY_SIZE(modestr) ? modestr[mode] : "unknown"; } +static const char *phylink_pcs_mode_str(unsigned int mode) +{ + if (!mode) + return "none"; + + if (mode & PHYLINK_PCS_NEG_OUTBAND) + return "outband"; + + if (mode & PHYLINK_PCS_NEG_INBAND) { + if (mode & PHYLINK_PCS_NEG_ENABLED) + return "inband,an-enabled"; + else + return "inband,an-disabled"; + } + + return "unknown"; +} + static unsigned int phylink_interface_signal_rate(phy_interface_t interface) { switch (interface) { @@ -671,6 +700,17 @@ static int phylink_validate_mac_and_pcs(struct phylink *pl, return -EINVAL; } + /* Ensure that this PCS supports the interface which the MAC + * returned it for. It is an error for the MAC to return a PCS + * that does not support the interface mode. + */ + if (!phy_interface_empty(pcs->supported_interfaces) && + !test_bit(state->interface, pcs->supported_interfaces)) { + phylink_err(pl, "MAC returned PCS which does not support %s\n", + phy_modes(state->interface)); + return -EINVAL; + } + /* Validate the link parameters with the PCS */ if (pcs->ops->pcs_validate) { ret = pcs->ops->pcs_validate(pcs, supported, state); @@ -971,6 +1011,15 @@ static void phylink_resolve_an_pause(struct phylink_link_state *state) } } +static unsigned int phylink_pcs_inband_caps(struct phylink_pcs *pcs, + phy_interface_t interface) +{ + if (pcs && pcs->ops->pcs_inband_caps) + return pcs->ops->pcs_inband_caps(pcs, interface); + + return 0; +} + static void phylink_pcs_pre_config(struct phylink_pcs *pcs, phy_interface_t interface) { @@ -1024,6 +1073,24 @@ static void phylink_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, pcs->ops->pcs_link_up(pcs, neg_mode, interface, speed, duplex); } +/* Query inband for a specific interface mode, asking the MAC for the + * PCS which will be used to handle the interface mode. + */ +static unsigned int phylink_inband_caps(struct phylink *pl, + phy_interface_t interface) +{ + struct phylink_pcs *pcs; + + if (!pl->mac_ops->mac_select_pcs) + return 0; + + pcs = pl->mac_ops->mac_select_pcs(pl->config, interface); + if (!pcs) + return 0; + + return phylink_pcs_inband_caps(pcs, interface); +} + static void phylink_pcs_poll_stop(struct phylink *pl) { if (pl->cfg_link_an_mode == MLO_AN_INBAND) @@ -1065,13 +1132,13 @@ static void phylink_mac_config(struct phylink *pl, phylink_dbg(pl, "%s: mode=%s/%s/%s adv=%*pb pause=%02x\n", - __func__, phylink_an_mode_str(pl->cur_link_an_mode), + __func__, phylink_an_mode_str(pl->act_link_an_mode), phy_modes(st.interface), phy_rate_matching_to_str(st.rate_matching), __ETHTOOL_LINK_MODE_MASK_NBITS, st.advertising, st.pause); - pl->mac_ops->mac_config(pl->config, pl->cur_link_an_mode, &st); + pl->mac_ops->mac_config(pl->config, pl->act_link_an_mode, &st); } static void phylink_pcs_an_restart(struct phylink *pl) @@ -1079,13 +1146,14 @@ static void phylink_pcs_an_restart(struct phylink *pl) if (pl->pcs && linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, pl->link_config.advertising) && phy_interface_mode_is_8023z(pl->link_config.interface) && - phylink_autoneg_inband(pl->cur_link_an_mode)) + phylink_autoneg_inband(pl->act_link_an_mode)) pl->pcs->ops->pcs_an_restart(pl->pcs); } /** * phylink_pcs_neg_mode() - helper to determine PCS inband mode - * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @pcs: a pointer to &struct phylink_pcs * @interface: interface mode to be used * @advertising: adertisement ethtool link mode mask * @@ -1102,11 +1170,21 @@ static void phylink_pcs_an_restart(struct phylink *pl) * Note: this is for cases where the PCS itself is involved in negotiation * (e.g. Clause 37, SGMII and similar) not Clause 73. */ -static unsigned int phylink_pcs_neg_mode(unsigned int mode, - phy_interface_t interface, - const unsigned long *advertising) +static void phylink_pcs_neg_mode(struct phylink *pl, struct phylink_pcs *pcs, + phy_interface_t interface, + const unsigned long *advertising) { - unsigned int neg_mode; + unsigned int pcs_ib_caps = 0; + unsigned int phy_ib_caps = 0; + unsigned int neg_mode, mode; + enum { + INBAND_CISCO_SGMII, + INBAND_BASEX, + } type; + + mode = pl->req_link_an_mode; + + pl->phy_ib_mode = 0; switch (interface) { case PHY_INTERFACE_MODE_SGMII: @@ -1119,10 +1197,7 @@ static unsigned int phylink_pcs_neg_mode(unsigned int mode, * inband communication. Note: there exist PHYs that run * with SGMII but do not send the inband data. */ - if (!phylink_autoneg_inband(mode)) - neg_mode = PHYLINK_PCS_NEG_OUTBAND; - else - neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED; + type = INBAND_CISCO_SGMII; break; case PHY_INTERFACE_MODE_1000BASEX: @@ -1133,21 +1208,143 @@ static unsigned int phylink_pcs_neg_mode(unsigned int mode, * as well, but drivers may not support this, so may * need to override this. */ - if (!phylink_autoneg_inband(mode)) + type = INBAND_BASEX; + break; + + default: + pl->pcs_neg_mode = PHYLINK_PCS_NEG_NONE; + pl->act_link_an_mode = mode; + return; + } + + if (pcs) + pcs_ib_caps = phylink_pcs_inband_caps(pcs, interface); + + if (pl->phydev) + phy_ib_caps = phy_inband_caps(pl->phydev, interface); + + phylink_dbg(pl, "interface %s inband modes: pcs=%02x phy=%02x\n", + phy_modes(interface), pcs_ib_caps, phy_ib_caps); + + if (!phylink_autoneg_inband(mode)) { + bool pcs_ib_only = false; + bool phy_ib_only = false; + + if (pcs_ib_caps && pcs_ib_caps != LINK_INBAND_DISABLE) { + /* PCS supports reporting in-band capabilities, and + * supports more than disable mode. + */ + if (pcs_ib_caps & LINK_INBAND_DISABLE) + neg_mode = PHYLINK_PCS_NEG_OUTBAND; + else if (pcs_ib_caps & LINK_INBAND_ENABLE) + pcs_ib_only = true; + } + + if (phy_ib_caps && phy_ib_caps != LINK_INBAND_DISABLE) { + /* PHY supports in-band capabilities, and supports + * more than disable mode. + */ + if (phy_ib_caps & LINK_INBAND_DISABLE) + pl->phy_ib_mode = LINK_INBAND_DISABLE; + else if (phy_ib_caps & LINK_INBAND_BYPASS) + pl->phy_ib_mode = LINK_INBAND_BYPASS; + else if (phy_ib_caps & LINK_INBAND_ENABLE) + phy_ib_only = true; + } + + /* If either the PCS or PHY requires inband to be enabled, + * this is an invalid configuration. Provide a diagnostic + * message for this case, but don't try to force the issue. + */ + if (pcs_ib_only || phy_ib_only) + phylink_warn(pl, + "firmware wants %s mode, but %s%s%s requires inband\n", + phylink_an_mode_str(mode), + pcs_ib_only ? "PCS" : "", + pcs_ib_only && phy_ib_only ? " and " : "", + phy_ib_only ? "PHY" : ""); + + neg_mode = PHYLINK_PCS_NEG_OUTBAND; + } else if (type == INBAND_CISCO_SGMII || pl->phydev) { + /* For SGMII modes which are designed to be used with PHYs, or + * Base-X with a PHY, we try to use in-band mode where-ever + * possible. However, there are some PHYs e.g. BCM84881 which + * do not support in-band. + */ + const unsigned int inband_ok = LINK_INBAND_ENABLE | + LINK_INBAND_BYPASS; + const unsigned int outband_ok = LINK_INBAND_DISABLE | + LINK_INBAND_BYPASS; + /* PCS PHY + * D E D E + * 0 0 0 0 no information inband enabled + * 1 0 0 0 pcs doesn't support outband + * 0 1 0 0 pcs required inband enabled + * 1 1 0 0 pcs optional inband enabled + * 0 0 1 0 phy doesn't support outband + * 1 0 1 0 pcs+phy doesn't support outband + * 0 1 1 0 pcs required, phy doesn't support, invalid + * 1 1 1 0 pcs optional, phy doesn't support, outband + * 0 0 0 1 phy required inband enabled + * 1 0 0 1 pcs doesn't support, phy required, invalid + * 0 1 0 1 pcs+phy required inband enabled + * 1 1 0 1 pcs optional, phy required inband enabled + * 0 0 1 1 phy optional inband enabled + * 1 0 1 1 pcs doesn't support, phy optional, outband + * 0 1 1 1 pcs required, phy optional inband enabled + * 1 1 1 1 pcs+phy optional inband enabled + */ + if ((!pcs_ib_caps || pcs_ib_caps & inband_ok) && + (!phy_ib_caps || phy_ib_caps & inband_ok)) { + /* In-band supported or unknown at both ends. Enable + * in-band mode with or without bypass at the PHY. + */ + if (phy_ib_caps & LINK_INBAND_ENABLE) + pl->phy_ib_mode = LINK_INBAND_ENABLE; + else if (phy_ib_caps & LINK_INBAND_BYPASS) + pl->phy_ib_mode = LINK_INBAND_BYPASS; + + neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED; + } else if ((!pcs_ib_caps || pcs_ib_caps & outband_ok) && + (!phy_ib_caps || phy_ib_caps & outband_ok)) { + /* Either in-band not supported at at least one end. + * In-band bypass at the other end is possible. + */ + if (phy_ib_caps & LINK_INBAND_DISABLE) + pl->phy_ib_mode = LINK_INBAND_DISABLE; + else if (phy_ib_caps & LINK_INBAND_BYPASS) + pl->phy_ib_mode = LINK_INBAND_BYPASS; + neg_mode = PHYLINK_PCS_NEG_OUTBAND; + if (pl->phydev) + mode = MLO_AN_PHY; + } else { + /* invalid */ + phylink_warn(pl, "%s: incompatible in-band capabilities, trying in-band", + phy_modes(interface)); + neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED; + } + } else { + /* For Base-X without a PHY */ + if (pcs_ib_caps == LINK_INBAND_DISABLE) + /* If the PCS doesn't support inband, then inband must + * be disabled. + */ + neg_mode = PHYLINK_PCS_NEG_INBAND_DISABLED; + else if (pcs_ib_caps == LINK_INBAND_ENABLE) + /* If the PCS requires inband, then inband must always + * be enabled. + */ + neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED; else if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, advertising)) neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED; else neg_mode = PHYLINK_PCS_NEG_INBAND_DISABLED; - break; - - default: - neg_mode = PHYLINK_PCS_NEG_NONE; - break; } - return neg_mode; + pl->pcs_neg_mode = neg_mode; + pl->act_link_an_mode = mode; } static void phylink_major_config(struct phylink *pl, bool restart, @@ -1159,11 +1356,9 @@ static void phylink_major_config(struct phylink *pl, bool restart, unsigned int neg_mode; int err; - phylink_dbg(pl, "major config %s\n", phy_modes(state->interface)); - - pl->pcs_neg_mode = phylink_pcs_neg_mode(pl->cur_link_an_mode, - state->interface, - state->advertising); + phylink_dbg(pl, "major config, requested %s/%s\n", + phylink_an_mode_str(pl->req_link_an_mode), + phy_modes(state->interface)); if (pl->mac_ops->mac_select_pcs) { pcs = pl->mac_ops->mac_select_pcs(pl->config, state->interface); @@ -1177,10 +1372,17 @@ static void phylink_major_config(struct phylink *pl, bool restart, pcs_changed = pl->pcs != pcs; } + phylink_pcs_neg_mode(pl, pcs, state->interface, state->advertising); + + phylink_dbg(pl, "major config, active %s/%s/%s\n", + phylink_an_mode_str(pl->act_link_an_mode), + phylink_pcs_mode_str(pl->pcs_neg_mode), + phy_modes(state->interface)); + phylink_pcs_poll_stop(pl); if (pl->mac_ops->mac_prepare) { - err = pl->mac_ops->mac_prepare(pl->config, pl->cur_link_an_mode, + err = pl->mac_ops->mac_prepare(pl->config, pl->act_link_an_mode, state->interface); if (err < 0) { phylink_err(pl, "mac_prepare failed: %pe\n", @@ -1214,7 +1416,7 @@ static void phylink_major_config(struct phylink *pl, bool restart, if (pl->pcs_state == PCS_STATE_STARTING || pcs_changed) phylink_pcs_enable(pl->pcs); - neg_mode = pl->cur_link_an_mode; + neg_mode = pl->act_link_an_mode; if (pl->pcs && pl->pcs->neg_mode) neg_mode = pl->pcs_neg_mode; @@ -1230,13 +1432,20 @@ static void phylink_major_config(struct phylink *pl, bool restart, phylink_pcs_an_restart(pl); if (pl->mac_ops->mac_finish) { - err = pl->mac_ops->mac_finish(pl->config, pl->cur_link_an_mode, + err = pl->mac_ops->mac_finish(pl->config, pl->act_link_an_mode, state->interface); if (err < 0) phylink_err(pl, "mac_finish failed: %pe\n", ERR_PTR(err)); } + if (pl->phydev && pl->phy_ib_mode) { + err = phy_config_inband(pl->phydev, pl->phy_ib_mode); + if (err < 0) + phylink_err(pl, "phy_config_inband: %pe\n", + ERR_PTR(err)); + } + if (pl->sfp_bus) { rate_kbd = phylink_interface_signal_rate(state->interface); if (rate_kbd) @@ -1261,17 +1470,16 @@ static int phylink_change_inband_advert(struct phylink *pl) return 0; phylink_dbg(pl, "%s: mode=%s/%s adv=%*pb pause=%02x\n", __func__, - phylink_an_mode_str(pl->cur_link_an_mode), + phylink_an_mode_str(pl->req_link_an_mode), phy_modes(pl->link_config.interface), __ETHTOOL_LINK_MODE_MASK_NBITS, pl->link_config.advertising, pl->link_config.pause); /* Recompute the PCS neg mode */ - pl->pcs_neg_mode = phylink_pcs_neg_mode(pl->cur_link_an_mode, - pl->link_config.interface, - pl->link_config.advertising); + phylink_pcs_neg_mode(pl, pl->pcs, pl->link_config.interface, + pl->link_config.advertising); - neg_mode = pl->cur_link_an_mode; + neg_mode = pl->act_link_an_mode; if (pl->pcs->neg_mode) neg_mode = pl->pcs_neg_mode; @@ -1293,12 +1501,24 @@ static int phylink_change_inband_advert(struct phylink *pl) static void phylink_mac_pcs_get_state(struct phylink *pl, struct phylink_link_state *state) { + struct phylink_pcs *pcs; + bool autoneg; + linkmode_copy(state->advertising, pl->link_config.advertising); linkmode_zero(state->lp_advertising); state->interface = pl->link_config.interface; state->rate_matching = pl->link_config.rate_matching; - if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - state->advertising)) { + state->an_complete = 0; + state->link = 1; + + pcs = pl->pcs; + if (!pcs || pcs->neg_mode) + autoneg = pl->pcs_neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED; + else + autoneg = linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + state->advertising); + + if (autoneg) { state->speed = SPEED_UNKNOWN; state->duplex = DUPLEX_UNKNOWN; state->pause = MLO_PAUSE_NONE; @@ -1307,11 +1527,9 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, state->duplex = pl->link_config.duplex; state->pause = pl->link_config.pause; } - state->an_complete = 0; - state->link = 1; - if (pl->pcs) - pl->pcs->ops->pcs_get_state(pl->pcs, state); + if (pcs) + pcs->ops->pcs_get_state(pcs, pl->pcs_neg_mode, state); else state->link = 0; } @@ -1336,7 +1554,7 @@ static void phylink_mac_initial_config(struct phylink *pl, bool force_restart) { struct phylink_link_state link_state; - switch (pl->cur_link_an_mode) { + switch (pl->req_link_an_mode) { case MLO_AN_PHY: link_state = pl->phy_state; break; @@ -1375,6 +1593,39 @@ static const char *phylink_pause_to_str(int pause) } } +static void phylink_deactivate_lpi(struct phylink *pl) +{ + if (pl->mac_enable_tx_lpi) { + pl->mac_enable_tx_lpi = false; + + phylink_dbg(pl, "disabling LPI\n"); + + pl->mac_ops->mac_disable_tx_lpi(pl->config); + } +} + +static void phylink_activate_lpi(struct phylink *pl) +{ + int err; + + if (!test_bit(pl->cur_interface, pl->config->lpi_interfaces)) { + phylink_dbg(pl, "MAC does not support LPI with %s\n", + phy_modes(pl->cur_interface)); + return; + } + + phylink_dbg(pl, "LPI timer %uus, tx clock stop %u\n", + pl->mac_tx_lpi_timer, pl->mac_tx_clk_stop); + + err = pl->mac_ops->mac_enable_tx_lpi(pl->config, pl->mac_tx_lpi_timer, + pl->mac_tx_clk_stop); + if (!err) + pl->mac_enable_tx_lpi = true; + else + phylink_err(pl, "%ps() failed: %pe\n", + pl->mac_ops->mac_enable_tx_lpi, ERR_PTR(err)); +} + static void phylink_link_up(struct phylink *pl, struct phylink_link_state link_state) { @@ -1410,17 +1661,20 @@ static void phylink_link_up(struct phylink *pl, pl->cur_interface = link_state.interface; - neg_mode = pl->cur_link_an_mode; + neg_mode = pl->act_link_an_mode; if (pl->pcs && pl->pcs->neg_mode) neg_mode = pl->pcs_neg_mode; phylink_pcs_link_up(pl->pcs, neg_mode, pl->cur_interface, speed, duplex); - pl->mac_ops->mac_link_up(pl->config, pl->phydev, pl->cur_link_an_mode, + pl->mac_ops->mac_link_up(pl->config, pl->phydev, pl->act_link_an_mode, pl->cur_interface, speed, duplex, !!(link_state.pause & MLO_PAUSE_TX), rx_pause); + if (pl->mac_supports_eee && pl->phy_enable_tx_lpi) + phylink_activate_lpi(pl); + if (ndev) netif_carrier_on(ndev); @@ -1437,25 +1691,29 @@ static void phylink_link_down(struct phylink *pl) if (ndev) netif_carrier_off(ndev); - pl->mac_ops->mac_link_down(pl->config, pl->cur_link_an_mode, + + phylink_deactivate_lpi(pl); + + pl->mac_ops->mac_link_down(pl->config, pl->act_link_an_mode, pl->cur_interface); phylink_info(pl, "Link is Down\n"); } +static bool phylink_link_is_up(struct phylink *pl) +{ + return pl->netdev ? netif_carrier_ok(pl->netdev) : pl->old_link_state; +} + static void phylink_resolve(struct work_struct *w) { struct phylink *pl = container_of(w, struct phylink, resolve); struct phylink_link_state link_state; - struct net_device *ndev = pl->netdev; bool mac_config = false; bool retrigger = false; bool cur_link_state; mutex_lock(&pl->state_mutex); - if (pl->netdev) - cur_link_state = netif_carrier_ok(ndev); - else - cur_link_state = pl->old_link_state; + cur_link_state = phylink_link_is_up(pl); if (pl->phylink_disable_state) { pl->link_failed = false; @@ -1463,10 +1721,10 @@ static void phylink_resolve(struct work_struct *w) } else if (pl->link_failed) { link_state.link = false; retrigger = true; - } else if (pl->cur_link_an_mode == MLO_AN_FIXED) { + } else if (pl->act_link_an_mode == MLO_AN_FIXED) { phylink_get_fixed_state(pl, &link_state); mac_config = link_state.link; - } else if (pl->cur_link_an_mode == MLO_AN_PHY) { + } else if (pl->act_link_an_mode == MLO_AN_PHY) { link_state = pl->phy_state; mac_config = link_state.link; } else { @@ -1520,7 +1778,7 @@ static void phylink_resolve(struct work_struct *w) } } - if (pl->cur_link_an_mode != MLO_AN_FIXED) + if (pl->act_link_an_mode != MLO_AN_FIXED) phylink_apply_manual_flow(pl, &link_state); if (mac_config) { @@ -1644,7 +1902,7 @@ int phylink_set_fixed_link(struct phylink *pl, pl->link_config.an_complete = 1; pl->cfg_link_an_mode = MLO_AN_FIXED; - pl->cur_link_an_mode = pl->cfg_link_an_mode; + pl->req_link_an_mode = pl->cfg_link_an_mode; return 0; } @@ -1699,6 +1957,17 @@ struct phylink *phylink_create(struct phylink_config *config, return ERR_PTR(-EINVAL); } + pl->mac_supports_eee_ops = mac_ops->mac_disable_tx_lpi && + mac_ops->mac_enable_tx_lpi; + pl->mac_supports_eee = pl->mac_supports_eee_ops && + pl->config->lpi_capabilities && + !phy_interface_empty(pl->config->lpi_interfaces); + + /* Set the default EEE configuration */ + pl->eee_cfg.eee_enabled = pl->config->eee_enabled_default; + pl->eee_cfg.tx_lpi_enabled = pl->eee_cfg.eee_enabled; + pl->eee_cfg.tx_lpi_timer = pl->config->lpi_timer_default; + pl->phy_state.interface = iface; pl->link_interface = iface; if (iface == PHY_INTERFACE_MODE_MOCA) @@ -1732,7 +2001,7 @@ struct phylink *phylink_create(struct phylink_config *config, } } - pl->cur_link_an_mode = pl->cfg_link_an_mode; + pl->req_link_an_mode = pl->cfg_link_an_mode; ret = phylink_register_sfp(pl, fwnode); if (ret < 0) { @@ -1803,16 +2072,22 @@ static void phylink_phy_change(struct phy_device *phydev, bool up) pl->phy_state.link = up; if (!up) pl->link_failed = true; + + /* Get the LPI state from phylib */ + pl->phy_enable_tx_lpi = phydev->enable_tx_lpi; + pl->mac_tx_lpi_timer = phydev->eee_cfg.tx_lpi_timer; mutex_unlock(&pl->state_mutex); phylink_run_resolve(pl); - phylink_dbg(pl, "phy link %s %s/%s/%s/%s/%s\n", up ? "up" : "down", + phylink_dbg(pl, "phy link %s %s/%s/%s/%s/%s/%slpi\n", + up ? "up" : "down", phy_modes(phydev->interface), phy_speed_to_str(phydev->speed), phy_duplex_to_str(phydev->duplex), phy_rate_matching_to_str(phydev->rate_matching), - phylink_pause_to_str(pl->phy_state.pause)); + phylink_pause_to_str(pl->phy_state.pause), + phydev->enable_tx_lpi ? "" : "no"); } static int phylink_validate_phy(struct phylink *pl, struct phy_device *phy, @@ -1942,6 +2217,36 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, /* Restrict the phy advertisement according to the MAC support. */ linkmode_copy(phy->advertising, config.advertising); + + /* If the MAC supports phylink managed EEE, restrict the EEE + * advertisement according to the MAC's LPI capabilities. + */ + if (pl->mac_supports_eee) { + /* If EEE is enabled, then we need to call phy_support_eee() + * to ensure that the advertising mask is appropriately set. + * This also enables EEE at the PHY. + */ + if (pl->eee_cfg.eee_enabled) + phy_support_eee(phy); + + phy->eee_cfg.tx_lpi_enabled = pl->eee_cfg.tx_lpi_enabled; + phy->eee_cfg.tx_lpi_timer = pl->eee_cfg.tx_lpi_timer; + + /* Convert the MAC's LPI capabilities to linkmodes */ + linkmode_zero(pl->supported_lpi); + phylink_caps_to_linkmodes(pl->supported_lpi, + pl->config->lpi_capabilities); + + /* Restrict the PHYs EEE support/advertisement to the modes + * that the MAC supports. + */ + linkmode_and(phy->advertising_eee, phy->advertising_eee, + pl->supported_lpi); + } else if (pl->mac_supports_eee_ops) { + /* MAC supports phylink EEE, but wants EEE always disabled. */ + phy_disable_eee(phy); + } + mutex_unlock(&pl->state_mutex); mutex_unlock(&phy->lock); @@ -1957,7 +2262,17 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, if (pl->config->mac_managed_pm) phy->mac_managed_pm = true; - return 0; + /* Allow the MAC to stop its clock if the PHY has the capability */ + pl->mac_tx_clk_stop = phy_eee_tx_clock_stop_capable(phy) > 0; + + /* Explicitly configure whether the PHY is allowed to stop it's + * receive clock. + */ + ret = phy_eee_rx_clock_stop(phy, pl->config->eee_rx_clk_stop_enable); + if (ret == -EOPNOTSUPP) + ret = 0; + + return ret; } static int phylink_attach_phy(struct phylink *pl, struct phy_device *phy, @@ -2114,6 +2429,8 @@ void phylink_disconnect_phy(struct phylink *pl) mutex_lock(&phy->lock); mutex_lock(&pl->state_mutex); pl->phydev = NULL; + pl->phy_enable_tx_lpi = false; + pl->mac_tx_clk_stop = false; mutex_unlock(&pl->state_mutex); mutex_unlock(&phy->lock); flush_work(&pl->resolve); @@ -2189,7 +2506,7 @@ void phylink_start(struct phylink *pl) ASSERT_RTNL(); phylink_info(pl, "configuring for %s/%s link mode\n", - phylink_an_mode_str(pl->cur_link_an_mode), + phylink_an_mode_str(pl->req_link_an_mode), phy_modes(pl->link_config.interface)); /* Always set the carrier off */ @@ -2474,7 +2791,7 @@ int phylink_ethtool_ksettings_get(struct phylink *pl, linkmode_copy(kset->link_modes.supported, pl->supported); - switch (pl->cur_link_an_mode) { + switch (pl->act_link_an_mode) { case MLO_AN_FIXED: /* We are using fixed settings. Report these as the * current link settings - and note that these also @@ -2505,6 +2822,26 @@ int phylink_ethtool_ksettings_get(struct phylink *pl, } EXPORT_SYMBOL_GPL(phylink_ethtool_ksettings_get); +static bool phylink_validate_pcs_inband_autoneg(struct phylink *pl, + phy_interface_t interface, + unsigned long *adv) +{ + unsigned int inband = phylink_inband_caps(pl, interface); + unsigned int mask; + + /* If the PCS doesn't implement inband support, be permissive. */ + if (!inband) + return true; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, adv)) + mask = LINK_INBAND_ENABLE; + else + mask = LINK_INBAND_DISABLE; + + /* Check whether the PCS implements the required mode */ + return !!(inband & mask); +} + /** * phylink_ethtool_ksettings_set() - set the link settings * @pl: a pointer to a &struct phylink returned from phylink_create() @@ -2566,7 +2903,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, /* If we have a fixed link, refuse to change link parameters. * If the link parameters match, accept them but do nothing. */ - if (pl->cur_link_an_mode == MLO_AN_FIXED) { + if (pl->req_link_an_mode == MLO_AN_FIXED) { if (s->speed != pl->link_config.speed || s->duplex != pl->link_config.duplex) return -EINVAL; @@ -2582,7 +2919,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, * is our default case) but do not allow the advertisement to * be changed. If the advertisement matches, simply return. */ - if (pl->cur_link_an_mode == MLO_AN_FIXED) { + if (pl->req_link_an_mode == MLO_AN_FIXED) { if (!linkmode_equal(config.advertising, pl->link_config.advertising)) return -EINVAL; @@ -2617,7 +2954,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, linkmode_copy(support, pl->supported); if (phylink_validate(pl, support, &config)) { phylink_err(pl, "validation of %s/%s with support %*pb failed\n", - phylink_an_mode_str(pl->cur_link_an_mode), + phylink_an_mode_str(pl->req_link_an_mode), phy_modes(config.interface), __ETHTOOL_LINK_MODE_MASK_NBITS, support); return -EINVAL; @@ -2635,6 +2972,13 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, phylink_is_empty_linkmode(config.advertising)) return -EINVAL; + /* Validate the autonegotiation state. We don't have a PHY in this + * situation, so the PCS is the media-facing entity. + */ + if (!phylink_validate_pcs_inband_autoneg(pl, config.interface, + config.advertising)) + return -EINVAL; + mutex_lock(&pl->state_mutex); pl->link_config.speed = config.speed; pl->link_config.duplex = config.duplex; @@ -2717,7 +3061,7 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, ASSERT_RTNL(); - if (pl->cur_link_an_mode == MLO_AN_FIXED) + if (pl->req_link_an_mode == MLO_AN_FIXED) return -EOPNOTSUPP; if (!phylink_test(pl->supported, Pause) && @@ -2841,8 +3185,16 @@ int phylink_ethtool_get_eee(struct phylink *pl, struct ethtool_keee *eee) ASSERT_RTNL(); - if (pl->phydev) + if (pl->mac_supports_eee_ops && !pl->mac_supports_eee) + return ret; + + if (pl->phydev) { ret = phy_ethtool_get_eee(pl->phydev, eee); + /* Restrict supported linkmode mask */ + if (ret == 0 && pl->mac_supports_eee_ops) + linkmode_and(eee->supported, eee->supported, + pl->supported_lpi); + } return ret; } @@ -2855,12 +3207,29 @@ EXPORT_SYMBOL_GPL(phylink_ethtool_get_eee); */ int phylink_ethtool_set_eee(struct phylink *pl, struct ethtool_keee *eee) { + bool mac_eee = pl->mac_supports_eee; int ret = -EOPNOTSUPP; ASSERT_RTNL(); - if (pl->phydev) + phylink_dbg(pl, "mac %s phylink EEE%s, adv %*pbl, LPI%s timer %uus\n", + mac_eee ? "supports" : "does not support", + eee->eee_enabled ? ", enabled" : "", + __ETHTOOL_LINK_MODE_MASK_NBITS, eee->advertised, + eee->tx_lpi_enabled ? " enabled" : "", eee->tx_lpi_timer); + + if (pl->mac_supports_eee_ops && !mac_eee) + return ret; + + if (pl->phydev) { + /* Restrict advertisement mask */ + if (pl->mac_supports_eee_ops) + linkmode_and(eee->advertised, eee->advertised, + pl->supported_lpi); ret = phy_ethtool_set_eee(pl->phydev, eee); + if (ret == 0) + eee_to_eeecfg(&pl->eee_cfg, eee); + } return ret; } @@ -2981,7 +3350,7 @@ static int phylink_mii_read(struct phylink *pl, unsigned int phy_id, struct phylink_link_state state; int val = 0xffff; - switch (pl->cur_link_an_mode) { + switch (pl->act_link_an_mode) { case MLO_AN_FIXED: if (phy_id == 0) { phylink_get_fixed_state(pl, &state); @@ -3006,7 +3375,7 @@ static int phylink_mii_read(struct phylink *pl, unsigned int phy_id, static int phylink_mii_write(struct phylink *pl, unsigned int phy_id, unsigned int reg, unsigned int val) { - switch (pl->cur_link_an_mode) { + switch (pl->act_link_an_mode) { case MLO_AN_FIXED: break; @@ -3176,11 +3545,11 @@ static phy_interface_t phylink_choose_sfp_interface(struct phylink *pl, return interface; } -static void phylink_sfp_set_config(struct phylink *pl, u8 mode, - unsigned long *supported, - struct phylink_link_state *state) +static void phylink_sfp_set_config(struct phylink *pl, unsigned long *supported, + struct phylink_link_state *state, + bool changed) { - bool changed = false; + u8 mode = MLO_AN_INBAND; phylink_dbg(pl, "requesting link mode %s/%s with support %*pb\n", phylink_an_mode_str(mode), phy_modes(state->interface), @@ -3196,9 +3565,9 @@ static void phylink_sfp_set_config(struct phylink *pl, u8 mode, changed = true; } - if (pl->cur_link_an_mode != mode || + if (pl->req_link_an_mode != mode || pl->link_config.interface != state->interface) { - pl->cur_link_an_mode = mode; + pl->req_link_an_mode = mode; pl->link_config.interface = state->interface; changed = true; @@ -3213,8 +3582,7 @@ static void phylink_sfp_set_config(struct phylink *pl, u8 mode, phylink_mac_initial_config(pl, false); } -static int phylink_sfp_config_phy(struct phylink *pl, u8 mode, - struct phy_device *phy) +static int phylink_sfp_config_phy(struct phylink *pl, struct phy_device *phy) { __ETHTOOL_DECLARE_LINK_MODE_MASK(support); struct phylink_link_state config; @@ -3258,7 +3626,7 @@ static int phylink_sfp_config_phy(struct phylink *pl, u8 mode, pl->link_port = pl->sfp_port; - phylink_sfp_set_config(pl, mode, support, &config); + phylink_sfp_set_config(pl, support, &config, true); return 0; } @@ -3314,6 +3682,12 @@ static int phylink_sfp_config_optical(struct phylink *pl) phylink_dbg(pl, "optical SFP: chosen %s interface\n", phy_modes(interface)); + if (!phylink_validate_pcs_inband_autoneg(pl, interface, + config.advertising)) { + phylink_err(pl, "autoneg setting not compatible with PCS"); + return -EINVAL; + } + config.interface = interface; /* Ignore errors if we're expecting a PHY to attach later */ @@ -3327,7 +3701,7 @@ static int phylink_sfp_config_optical(struct phylink *pl) pl->link_port = pl->sfp_port; - phylink_sfp_set_config(pl, MLO_AN_INBAND, pl->sfp_support, &config); + phylink_sfp_set_config(pl, pl->sfp_support, &config, false); return 0; } @@ -3398,19 +3772,16 @@ static void phylink_sfp_link_up(void *upstream) phylink_enable_and_run_resolve(pl, PHYLINK_DISABLE_LINK); } -/* The Broadcom BCM84881 in the Methode DM7052 is unable to provide a SGMII - * or 802.3z control word, so inband will not work. - */ -static bool phylink_phy_no_inband(struct phy_device *phy) -{ - return phy->is_c45 && phy_id_compare(phy->c45_ids.device_ids[1], - 0xae025150, 0xfffffff0); -} - static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) { struct phylink *pl = upstream; - u8 mode; + + if (!phy->drv) { + phylink_err(pl, "PHY %s (id 0x%.8lx) has no driver loaded\n", + phydev_name(phy), (unsigned long)phy->phy_id); + phylink_err(pl, "Drivers which handle known common cases: CONFIG_BCM84881_PHY, CONFIG_MARVELL_PHY\n"); + return -EINVAL; + } /* * This is the new way of dealing with flow control for PHYs, @@ -3421,17 +3792,12 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) */ phy_support_asym_pause(phy); - if (phylink_phy_no_inband(phy)) - mode = MLO_AN_PHY; - else - mode = MLO_AN_INBAND; - /* Set the PHY's host supported interfaces */ phy_interface_and(phy->host_interfaces, phylink_sfp_interfaces, pl->config->supported_interfaces); /* Do the initial configuration */ - return phylink_sfp_config_phy(pl, mode, phy); + return phylink_sfp_config_phy(pl, phy); } static void phylink_sfp_disconnect_phy(void *upstream, @@ -3626,6 +3992,7 @@ static void phylink_decode_usgmii_word(struct phylink_link_state *state, /** * phylink_mii_c22_pcs_decode_state() - Decode MAC PCS state from MII registers * @state: a pointer to a &struct phylink_link_state. + * @neg_mode: link negotiation mode (PHYLINK_PCS_NEG_xxx) * @bmsr: The value of the %MII_BMSR register * @lpa: The value of the %MII_LPA register * @@ -3638,32 +4005,45 @@ static void phylink_decode_usgmii_word(struct phylink_link_state *state, * accessing @bmsr and @lpa cannot be done with MDIO directly. */ void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, - u16 bmsr, u16 lpa) + unsigned int neg_mode, u16 bmsr, u16 lpa) { state->link = !!(bmsr & BMSR_LSTATUS); state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE); - /* If there is no link or autonegotiation is disabled, the LP advertisement - * data is not meaningful, so don't go any further. - */ - if (!state->link || !linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - state->advertising)) + + /* If the link is down, the advertisement data is undefined. */ + if (!state->link) return; switch (state->interface) { case PHY_INTERFACE_MODE_1000BASEX: - phylink_decode_c37_word(state, lpa, SPEED_1000); + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) { + phylink_decode_c37_word(state, lpa, SPEED_1000); + } else { + state->speed = SPEED_1000; + state->duplex = DUPLEX_FULL; + state->pause |= MLO_PAUSE_TX | MLO_PAUSE_RX; + } break; case PHY_INTERFACE_MODE_2500BASEX: - phylink_decode_c37_word(state, lpa, SPEED_2500); + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) { + phylink_decode_c37_word(state, lpa, SPEED_2500); + } else { + state->speed = SPEED_2500; + state->duplex = DUPLEX_FULL; + state->pause |= MLO_PAUSE_TX | MLO_PAUSE_RX; + } break; case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_QSGMII: - phylink_decode_sgmii_word(state, lpa); + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) + phylink_decode_sgmii_word(state, lpa); break; + case PHY_INTERFACE_MODE_QUSGMII: - phylink_decode_usgmii_word(state, lpa); + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) + phylink_decode_usgmii_word(state, lpa); break; default: @@ -3676,6 +4056,7 @@ EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_decode_state); /** * phylink_mii_c22_pcs_get_state() - read the MAC PCS state * @pcs: a pointer to a &struct mdio_device. + * @neg_mode: link negotiation mode (PHYLINK_PCS_NEG_xxx) * @state: a pointer to a &struct phylink_link_state. * * Helper for MAC PCS supporting the 802.3 clause 22 register set for @@ -3688,6 +4069,7 @@ EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_decode_state); * structure. */ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { int bmsr, lpa; @@ -3699,7 +4081,7 @@ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, return; } - phylink_mii_c22_pcs_decode_state(state, bmsr, lpa); + phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lpa); } EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_get_state); diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index 105602581a03..26350b962890 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -1098,7 +1098,7 @@ static struct phy_driver at803x_driver[] = { module_phy_driver(at803x_driver); -static struct mdio_device_id __maybe_unused atheros_tbl[] = { +static const struct mdio_device_id __maybe_unused atheros_tbl[] = { { ATH8030_PHY_ID, AT8030_PHY_ID_MASK }, { PHY_ID_MATCH_EXACT(ATH8031_PHY_ID) }, { PHY_ID_MATCH_EXACT(ATH8032_PHY_ID) }, diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index bd8a51ec0ecd..3279de857b47 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -828,7 +828,7 @@ static struct phy_driver qca807x_drivers[] = { }; module_phy_driver(qca807x_drivers); -static struct mdio_device_id __maybe_unused qca807x_tbl[] = { +static const struct mdio_device_id __maybe_unused qca807x_tbl[] = { { PHY_ID_MATCH_EXACT(PHY_ID_QCA8072) }, { PHY_ID_MATCH_EXACT(PHY_ID_QCA8075) }, { } diff --git a/drivers/net/phy/qcom/qca808x.c b/drivers/net/phy/qcom/qca808x.c index 5048304ccc9e..71498c518f0f 100644 --- a/drivers/net/phy/qcom/qca808x.c +++ b/drivers/net/phy/qcom/qca808x.c @@ -655,7 +655,7 @@ static struct phy_driver qca808x_driver[] = { module_phy_driver(qca808x_driver); -static struct mdio_device_id __maybe_unused qca808x_tbl[] = { +static const struct mdio_device_id __maybe_unused qca808x_tbl[] = { { PHY_ID_MATCH_EXACT(QCA8081_PHY_ID) }, { } }; diff --git a/drivers/net/phy/qcom/qca83xx.c b/drivers/net/phy/qcom/qca83xx.c index 7a5039920b9f..bc70ed8efd86 100644 --- a/drivers/net/phy/qcom/qca83xx.c +++ b/drivers/net/phy/qcom/qca83xx.c @@ -259,7 +259,7 @@ static struct phy_driver qca83xx_driver[] = { module_phy_driver(qca83xx_driver); -static struct mdio_device_id __maybe_unused qca83xx_tbl[] = { +static const struct mdio_device_id __maybe_unused qca83xx_tbl[] = { { PHY_ID_MATCH_EXACT(QCA8337_PHY_ID) }, { PHY_ID_MATCH_EXACT(QCA8327_A_PHY_ID) }, { PHY_ID_MATCH_EXACT(QCA8327_B_PHY_ID) }, diff --git a/drivers/net/phy/qsemi.c b/drivers/net/phy/qsemi.c index 30d15f7c9b03..7b70ba6cab66 100644 --- a/drivers/net/phy/qsemi.c +++ b/drivers/net/phy/qsemi.c @@ -155,7 +155,7 @@ static struct phy_driver qs6612_driver[] = { { module_phy_driver(qs6612_driver); -static struct mdio_device_id __maybe_unused qs6612_tbl[] = { +static const struct mdio_device_id __maybe_unused qs6612_tbl[] = { { 0x00181440, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/realtek/Kconfig b/drivers/net/phy/realtek/Kconfig new file mode 100644 index 000000000000..31935f147d87 --- /dev/null +++ b/drivers/net/phy/realtek/Kconfig @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-only +config REALTEK_PHY + tristate "Realtek PHYs" + help + Currently supports RTL821x/RTL822x and fast ethernet PHYs + +config REALTEK_PHY_HWMON + def_bool REALTEK_PHY && HWMON + depends on !(REALTEK_PHY=y && HWMON=m) + help + Optional hwmon support for the temperature sensor diff --git a/drivers/net/phy/realtek/Makefile b/drivers/net/phy/realtek/Makefile new file mode 100644 index 000000000000..dd21cf87f2f1 --- /dev/null +++ b/drivers/net/phy/realtek/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +realtek-y += realtek_main.o +realtek-$(CONFIG_REALTEK_PHY_HWMON) += realtek_hwmon.o +obj-$(CONFIG_REALTEK_PHY) += realtek.o diff --git a/drivers/net/phy/realtek/realtek.h b/drivers/net/phy/realtek/realtek.h new file mode 100644 index 000000000000..a39b44fa18a0 --- /dev/null +++ b/drivers/net/phy/realtek/realtek.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef REALTEK_H +#define REALTEK_H + +#include + +int rtl822x_hwmon_init(struct phy_device *phydev); + +#endif /* REALTEK_H */ diff --git a/drivers/net/phy/realtek/realtek_hwmon.c b/drivers/net/phy/realtek/realtek_hwmon.c new file mode 100644 index 000000000000..1ecb410bb941 --- /dev/null +++ b/drivers/net/phy/realtek/realtek_hwmon.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * HWMON support for Realtek PHY's + * + * Author: Heiner Kallweit + */ + +#include +#include + +#include "realtek.h" + +#define RTL822X_VND2_TSALRM 0xa662 +#define RTL822X_VND2_TSRR 0xbd84 +#define RTL822X_VND2_TSSR 0xb54c + +static int rtl822x_hwmon_get_temp(int raw) +{ + if (raw >= 512) + raw -= 1024; + + return 1000 * raw / 2; +} + +static int rtl822x_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + struct phy_device *phydev = dev_get_drvdata(dev); + int raw; + + switch (attr) { + case hwmon_temp_input: + raw = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL822X_VND2_TSRR) & 0x3ff; + *val = rtl822x_hwmon_get_temp(raw); + break; + case hwmon_temp_max: + /* Chip reduces speed to 1G if threshold is exceeded */ + raw = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL822X_VND2_TSSR) >> 6; + *val = rtl822x_hwmon_get_temp(raw); + break; + default: + return -EINVAL; + } + + return 0; +} + +static const struct hwmon_ops rtl822x_hwmon_ops = { + .visible = 0444, + .read = rtl822x_hwmon_read, +}; + +static const struct hwmon_channel_info * const rtl822x_hwmon_info[] = { + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_MAX), + NULL +}; + +static const struct hwmon_chip_info rtl822x_hwmon_chip_info = { + .ops = &rtl822x_hwmon_ops, + .info = rtl822x_hwmon_info, +}; + +int rtl822x_hwmon_init(struct phy_device *phydev) +{ + struct device *hwdev, *dev = &phydev->mdio.dev; + const char *name; + + /* Ensure over-temp alarm is reset. */ + phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, RTL822X_VND2_TSALRM, 3); + + name = devm_hwmon_sanitize_name(dev, dev_name(dev)); + if (IS_ERR(name)) + return PTR_ERR(name); + + hwdev = devm_hwmon_device_register_with_info(dev, name, phydev, + &rtl822x_hwmon_chip_info, + NULL); + return PTR_ERR_OR_ZERO(hwdev); +} diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek/realtek_main.c similarity index 97% rename from drivers/net/phy/realtek.c rename to drivers/net/phy/realtek/realtek_main.c index f65d7f1f348e..572a933636b0 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek/realtek_main.c @@ -14,6 +14,8 @@ #include #include +#include "realtek.h" + #define RTL821x_PHYSR 0x11 #define RTL821x_PHYSR_DUPLEX BIT(13) #define RTL821x_PHYSR_SPEED GENMASK(15, 14) @@ -736,7 +738,11 @@ static int rtlgen_read_mmd(struct phy_device *phydev, int devnum, u16 regnum) { int ret; - if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE) { + if (devnum == MDIO_MMD_VEND2) { + rtl821x_write_page(phydev, regnum >> 4); + ret = __phy_read(phydev, 0x10 + ((regnum & 0xf) >> 1)); + rtl821x_write_page(phydev, 0); + } else if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE) { rtl821x_write_page(phydev, 0xa5c); ret = __phy_read(phydev, 0x12); rtl821x_write_page(phydev, 0); @@ -760,7 +766,11 @@ static int rtlgen_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, { int ret; - if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) { + if (devnum == MDIO_MMD_VEND2) { + rtl821x_write_page(phydev, regnum >> 4); + ret = __phy_write(phydev, 0x10 + ((regnum & 0xf) >> 1), val); + rtl821x_write_page(phydev, 0); + } else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) { rtl821x_write_page(phydev, 0xa5d); ret = __phy_write(phydev, 0x10, val); rtl821x_write_page(phydev, 0); @@ -812,6 +822,15 @@ static int rtl822x_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, return ret; } +static int rtl822x_probe(struct phy_device *phydev) +{ + if (IS_ENABLED(CONFIG_REALTEK_PHY_HWMON) && + phydev->phy_id != RTL_GENERIC_PHYID) + return rtl822x_hwmon_init(phydev); + + return 0; +} + static int rtl822xb_config_init(struct phy_device *phydev) { bool has_2500, has_sgmii; @@ -952,15 +971,15 @@ static int rtl822x_read_status(struct phy_device *phydev) { int lpadv, ret; + mii_10gbt_stat_mod_linkmode_lpa_t(phydev->lp_advertising, 0); + ret = rtlgen_read_status(phydev); if (ret < 0) return ret; if (phydev->autoneg == AUTONEG_DISABLE || - !phydev->autoneg_complete) { - mii_10gbt_stat_mod_linkmode_lpa_t(phydev->lp_advertising, 0); + !phydev->autoneg_complete) return 0; - } lpadv = phy_read_paged(phydev, 0xa5d, 0x13); if (lpadv < 0) @@ -1023,26 +1042,25 @@ static int rtl822x_c45_read_status(struct phy_device *phydev) { int ret, val; - ret = genphy_c45_read_status(phydev); - if (ret < 0) - return ret; - - if (phydev->autoneg == AUTONEG_DISABLE || - !genphy_c45_aneg_done(phydev)) - mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, 0); - /* Vendor register as C45 has no standardized support for 1000BaseT */ - if (phydev->autoneg == AUTONEG_ENABLE) { + if (phydev->autoneg == AUTONEG_ENABLE && genphy_c45_aneg_done(phydev)) { val = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL822X_VND2_GANLPAR); if (val < 0) return val; - - mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, val); + } else { + val = 0; } + mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, val); - if (!phydev->link) + ret = genphy_c45_read_status(phydev); + if (ret < 0) + return ret; + + if (!phydev->link) { + phydev->master_slave_state = MASTER_SLAVE_STATE_UNKNOWN; return 0; + } /* Read actual speed from vendor register. */ val = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL_VND2_PHYSR); @@ -1456,6 +1474,7 @@ static struct phy_driver realtek_drvs[] = { }, { .match_phy_device = rtl8221b_vb_cg_c22_match_phy_device, .name = "RTL8221B-VB-CG 2.5Gbps PHY (C22)", + .probe = rtl822x_probe, .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .config_init = rtl822xb_config_init, @@ -1468,6 +1487,7 @@ static struct phy_driver realtek_drvs[] = { }, { .match_phy_device = rtl8221b_vb_cg_c45_match_phy_device, .name = "RTL8221B-VB-CG 2.5Gbps PHY (C45)", + .probe = rtl822x_probe, .config_init = rtl822xb_config_init, .get_rate_matching = rtl822xb_get_rate_matching, .get_features = rtl822x_c45_get_features, @@ -1478,6 +1498,7 @@ static struct phy_driver realtek_drvs[] = { }, { .match_phy_device = rtl8221b_vn_cg_c22_match_phy_device, .name = "RTL8221B-VM-CG 2.5Gbps PHY (C22)", + .probe = rtl822x_probe, .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .config_init = rtl822xb_config_init, @@ -1490,6 +1511,7 @@ static struct phy_driver realtek_drvs[] = { }, { .match_phy_device = rtl8221b_vn_cg_c45_match_phy_device, .name = "RTL8221B-VN-CG 2.5Gbps PHY (C45)", + .probe = rtl822x_probe, .config_init = rtl822xb_config_init, .get_rate_matching = rtl822xb_get_rate_matching, .get_features = rtl822x_c45_get_features, @@ -1500,6 +1522,7 @@ static struct phy_driver realtek_drvs[] = { }, { .match_phy_device = rtl8251b_c45_match_phy_device, .name = "RTL8251B 5Gbps PHY", + .probe = rtl822x_probe, .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .read_status = rtl822x_read_status, @@ -1511,6 +1534,7 @@ static struct phy_driver realtek_drvs[] = { .match_phy_device = rtl_internal_nbaset_match_phy_device, .name = "Realtek Internal NBASE-T PHY", .flags = PHY_IS_INTERNAL, + .probe = rtl822x_probe, .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .read_status = rtl822x_read_status, diff --git a/drivers/net/phy/rockchip.c b/drivers/net/phy/rockchip.c index bb13e75183ee..b338f385e15a 100644 --- a/drivers/net/phy/rockchip.c +++ b/drivers/net/phy/rockchip.c @@ -188,7 +188,7 @@ static struct phy_driver rockchip_phy_driver[] = { module_phy_driver(rockchip_phy_driver); -static struct mdio_device_id __maybe_unused rockchip_phy_tbl[] = { +static const struct mdio_device_id __maybe_unused rockchip_phy_tbl[] = { { INTERNAL_EPHY_ID, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index e1853599d9ba..31463b9e5697 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -838,7 +838,7 @@ MODULE_DESCRIPTION("SMSC PHY driver"); MODULE_AUTHOR("Herbert Valerio Riedel"); MODULE_LICENSE("GPL"); -static struct mdio_device_id __maybe_unused smsc_tbl[] = { +static const struct mdio_device_id __maybe_unused smsc_tbl[] = { { 0x0007c0a0, 0xfffffff0 }, { 0x0007c0b0, 0xfffffff0 }, { 0x0007c0c0, 0xfffffff0 }, diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c index 7196e927c2cd..076a370be849 100644 --- a/drivers/net/phy/spi_ks8995.c +++ b/drivers/net/phy/spi_ks8995.c @@ -289,7 +289,7 @@ static int ks8995_reset(struct ks8995_switch *ks) } static ssize_t ks8995_registers_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev; struct ks8995_switch *ks8995; @@ -301,7 +301,7 @@ static ssize_t ks8995_registers_read(struct file *filp, struct kobject *kobj, } static ssize_t ks8995_registers_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev; struct ks8995_switch *ks8995; @@ -401,8 +401,8 @@ static const struct bin_attribute ks8995_registers_attr = { .mode = 0600, }, .size = KS8995_REGS_SIZE, - .read = ks8995_registers_read, - .write = ks8995_registers_write, + .read_new = ks8995_registers_read, + .write_new = ks8995_registers_write, }; /* ------------------------------------------------------------------------ */ diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c index 309e4c3496c4..d4835d4c50e0 100644 --- a/drivers/net/phy/ste10Xp.c +++ b/drivers/net/phy/ste10Xp.c @@ -124,7 +124,7 @@ static struct phy_driver ste10xp_pdriver[] = { module_phy_driver(ste10xp_pdriver); -static struct mdio_device_id __maybe_unused ste10Xp_tbl[] = { +static const struct mdio_device_id __maybe_unused ste10Xp_tbl[] = { { STE101P_PHY_ID, 0xfffffff0 }, { STE100P_PHY_ID, 0xffffffff }, { } diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c index 8057ea8dbc21..752d4bf7bb99 100644 --- a/drivers/net/phy/teranetics.c +++ b/drivers/net/phy/teranetics.c @@ -87,7 +87,7 @@ static struct phy_driver teranetics_driver[] = { module_phy_driver(teranetics_driver); -static struct mdio_device_id __maybe_unused teranetics_tbl[] = { +static const struct mdio_device_id __maybe_unused teranetics_tbl[] = { { PHY_ID_TN2020, 0xffffffff }, { } }; diff --git a/drivers/net/phy/uPD60620.c b/drivers/net/phy/uPD60620.c index 38834347a427..900cb756c366 100644 --- a/drivers/net/phy/uPD60620.c +++ b/drivers/net/phy/uPD60620.c @@ -90,7 +90,7 @@ static struct phy_driver upd60620_driver[1] = { { module_phy_driver(upd60620_driver); -static struct mdio_device_id __maybe_unused upd60620_tbl[] = { +static const struct mdio_device_id __maybe_unused upd60620_tbl[] = { { UPD60620_PHY_ID, 0xfffffffe }, { } }; diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 2377179de017..b1b7bbba284e 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -674,7 +674,7 @@ static struct phy_driver vsc82xx_driver[] = { module_phy_driver(vsc82xx_driver); -static struct mdio_device_id __maybe_unused vitesse_tbl[] = { +static const struct mdio_device_id __maybe_unused vitesse_tbl[] = { { PHY_ID_VSC8234, 0x000ffff0 }, { PHY_ID_VSC8244, 0x000fffc0 }, { PHY_ID_VSC8572, 0x000ffff0 }, diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index 0af7db80b2f8..fc9e23927b3b 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -431,31 +431,6 @@ static int pd692x0_pi_disable(struct pse_controller_dev *pcdev, int id) return 0; } -static int pd692x0_pi_is_enabled(struct pse_controller_dev *pcdev, int id) -{ - struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); - struct pd692x0_msg msg, buf = {0}; - int ret; - - ret = pd692x0_fw_unavailable(priv); - if (ret) - return ret; - - msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_STATUS]; - msg.sub[2] = id; - ret = pd692x0_sendrecv_msg(priv, &msg, &buf); - if (ret < 0) - return ret; - - if (buf.sub[1]) { - priv->admin_state[id] = ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; - return 1; - } else { - priv->admin_state[id] = ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; - return 0; - } -} - struct pd692x0_pse_ext_state_mapping { u32 status_code; enum ethtool_c33_pse_ext_state pse_ext_state; @@ -517,21 +492,38 @@ pd692x0_pse_ext_state_map[] = { { /* sentinel */ } }; -static void -pd692x0_get_ext_state(struct ethtool_c33_pse_ext_state_info *c33_ext_state_info, - u32 status_code) +static int +pd692x0_pi_get_ext_state(struct pse_controller_dev *pcdev, int id, + struct pse_ext_state_info *ext_state_info) { + struct ethtool_c33_pse_ext_state_info *c33_ext_state_info; const struct pd692x0_pse_ext_state_mapping *ext_state_map; + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + int ret; + ret = pd692x0_fw_unavailable(priv); + if (ret) + return ret; + + msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_STATUS]; + msg.sub[2] = id; + ret = pd692x0_sendrecv_msg(priv, &msg, &buf); + if (ret < 0) + return ret; + + c33_ext_state_info = &ext_state_info->c33_ext_state_info; ext_state_map = pd692x0_pse_ext_state_map; while (ext_state_map->status_code) { - if (ext_state_map->status_code == status_code) { + if (ext_state_map->status_code == buf.sub[0]) { c33_ext_state_info->c33_pse_ext_state = ext_state_map->pse_ext_state; c33_ext_state_info->__c33_pse_ext_substate = ext_state_map->pse_ext_substate; - return; + return 0; } ext_state_map++; } + + return 0; } struct pd692x0_class_pw { @@ -613,35 +605,66 @@ static int pd692x0_pi_set_pw_from_table(struct device *dev, } static int -pd692x0_pi_get_pw_ranges(struct pse_control_status *st) +pd692x0_pi_get_pw_limit_ranges(struct pse_controller_dev *pcdev, int id, + struct pse_pw_limit_ranges *pw_limit_ranges) { + struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; const struct pd692x0_class_pw *pw_table; int i; pw_table = pd692x0_class_pw_table; - st->c33_pw_limit_ranges = kcalloc(PD692X0_CLASS_PW_TABLE_SIZE, - sizeof(struct ethtool_c33_pse_pw_limit_range), - GFP_KERNEL); - if (!st->c33_pw_limit_ranges) + c33_pw_limit_ranges = kcalloc(PD692X0_CLASS_PW_TABLE_SIZE, + sizeof(*c33_pw_limit_ranges), + GFP_KERNEL); + if (!c33_pw_limit_ranges) return -ENOMEM; for (i = 0; i < PD692X0_CLASS_PW_TABLE_SIZE; i++, pw_table++) { - st->c33_pw_limit_ranges[i].min = pw_table->class_pw; - st->c33_pw_limit_ranges[i].max = pw_table->class_pw + pw_table->max_added_class_pw; + c33_pw_limit_ranges[i].min = pw_table->class_pw; + c33_pw_limit_ranges[i].max = pw_table->class_pw + + pw_table->max_added_class_pw; } - st->c33_pw_limit_nb_ranges = i; - return 0; + pw_limit_ranges->c33_pw_limit_ranges = c33_pw_limit_ranges; + return i; } -static int pd692x0_ethtool_get_status(struct pse_controller_dev *pcdev, - unsigned long id, - struct netlink_ext_ack *extack, - struct pse_control_status *status) +static int +pd692x0_pi_get_admin_state(struct pse_controller_dev *pcdev, int id, + struct pse_admin_state *admin_state) +{ + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + int ret; + + ret = pd692x0_fw_unavailable(priv); + if (ret) + return ret; + + msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_STATUS]; + msg.sub[2] = id; + ret = pd692x0_sendrecv_msg(priv, &msg, &buf); + if (ret < 0) + return ret; + + if (buf.sub[1]) + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; + else + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; + + priv->admin_state[id] = admin_state->c33_admin_state; + + return 0; +} + +static int +pd692x0_pi_get_pw_status(struct pse_controller_dev *pcdev, int id, + struct pse_pw_status *pw_status) { struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); struct pd692x0_msg msg, buf = {0}; - u32 class; int ret; ret = pd692x0_fw_unavailable(priv); @@ -656,37 +679,33 @@ static int pd692x0_ethtool_get_status(struct pse_controller_dev *pcdev, /* Compare Port Status (Communication Protocol Document par. 7.1) */ if ((buf.sub[0] & 0xf0) == 0x80 || (buf.sub[0] & 0xf0) == 0x90) - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING; + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING; else if (buf.sub[0] == 0x1b || buf.sub[0] == 0x22) - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING; + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING; else if (buf.sub[0] == 0x12) - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_FAULT; + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_FAULT; else - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED; + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED; - if (buf.sub[1]) - status->c33_admin_state = ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; - else - status->c33_admin_state = ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; + return 0; +} - priv->admin_state[id] = status->c33_admin_state; +static int +pd692x0_pi_get_pw_class(struct pse_controller_dev *pcdev, int id) +{ + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + u32 class; + int ret; - pd692x0_get_ext_state(&status->c33_ext_state_info, buf.sub[0]); - status->c33_actual_pw = (buf.data[0] << 4 | buf.data[1]) * 100; - - msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_PARAM]; - msg.sub[2] = id; - memset(&buf, 0, sizeof(buf)); - ret = pd692x0_sendrecv_msg(priv, &msg, &buf); - if (ret < 0) + ret = pd692x0_fw_unavailable(priv); + if (ret) return ret; - ret = pd692x0_pi_get_pw_from_table(buf.data[0], buf.data[1]); - if (ret < 0) - return ret; - status->c33_avail_pw_limit = ret; - - memset(&buf, 0, sizeof(buf)); msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_CLASS]; msg.sub[2] = id; ret = pd692x0_sendrecv_msg(priv, &msg, &buf); @@ -695,13 +714,29 @@ static int pd692x0_ethtool_get_status(struct pse_controller_dev *pcdev, class = buf.data[3] >> 4; if (class <= 8) - status->c33_pw_class = class; + return class; - ret = pd692x0_pi_get_pw_ranges(status); + return 0; +} + +static int +pd692x0_pi_get_actual_pw(struct pse_controller_dev *pcdev, int id) +{ + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + int ret; + + ret = pd692x0_fw_unavailable(priv); + if (ret) + return ret; + + msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_STATUS]; + msg.sub[2] = id; + ret = pd692x0_sendrecv_msg(priv, &msg, &buf); if (ret < 0) return ret; - return 0; + return (buf.data[0] << 4 | buf.data[1]) * 100; } static struct pd692x0_msg_ver pd692x0_get_sw_version(struct pd692x0_priv *priv) @@ -999,13 +1034,12 @@ static int pd692x0_pi_get_voltage(struct pse_controller_dev *pcdev, int id) return (buf.sub[0] << 8 | buf.sub[1]) * 100000; } -static int pd692x0_pi_get_current_limit(struct pse_controller_dev *pcdev, - int id) +static int pd692x0_pi_get_pw_limit(struct pse_controller_dev *pcdev, + int id) { struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); struct pd692x0_msg msg, buf = {0}; - int mW, uV, uA, ret; - s64 tmp_64; + int ret; msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_PARAM]; msg.sub[2] = id; @@ -1013,48 +1047,24 @@ static int pd692x0_pi_get_current_limit(struct pse_controller_dev *pcdev, if (ret < 0) return ret; - ret = pd692x0_pi_get_pw_from_table(buf.data[2], buf.data[3]); - if (ret < 0) - return ret; - mW = ret; - - ret = pd692x0_pi_get_voltage(pcdev, id); - if (ret < 0) - return ret; - uV = ret; - - tmp_64 = mW; - tmp_64 *= 1000000000ull; - /* uA = mW * 1000000000 / uV */ - uA = DIV_ROUND_CLOSEST_ULL(tmp_64, uV); - return uA; + return pd692x0_pi_get_pw_from_table(buf.data[2], buf.data[3]); } -static int pd692x0_pi_set_current_limit(struct pse_controller_dev *pcdev, - int id, int max_uA) +static int pd692x0_pi_set_pw_limit(struct pse_controller_dev *pcdev, + int id, int max_mW) { struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); struct device *dev = &priv->client->dev; struct pd692x0_msg msg, buf = {0}; - int uV, ret, mW; - s64 tmp_64; + int ret; ret = pd692x0_fw_unavailable(priv); if (ret) return ret; - ret = pd692x0_pi_get_voltage(pcdev, id); - if (ret < 0) - return ret; - uV = ret; - msg = pd692x0_msg_template_list[PD692X0_MSG_SET_PORT_PARAM]; msg.sub[2] = id; - tmp_64 = uV; - tmp_64 *= max_uA; - /* mW = uV * uA / 1000000000 */ - mW = DIV_ROUND_CLOSEST_ULL(tmp_64, 1000000000); - ret = pd692x0_pi_set_pw_from_table(dev, &msg, mW); + ret = pd692x0_pi_set_pw_from_table(dev, &msg, max_mW); if (ret) return ret; @@ -1063,13 +1073,17 @@ static int pd692x0_pi_set_current_limit(struct pse_controller_dev *pcdev, static const struct pse_controller_ops pd692x0_ops = { .setup_pi_matrix = pd692x0_setup_pi_matrix, - .ethtool_get_status = pd692x0_ethtool_get_status, + .pi_get_admin_state = pd692x0_pi_get_admin_state, + .pi_get_pw_status = pd692x0_pi_get_pw_status, + .pi_get_ext_state = pd692x0_pi_get_ext_state, + .pi_get_pw_class = pd692x0_pi_get_pw_class, + .pi_get_actual_pw = pd692x0_pi_get_actual_pw, .pi_enable = pd692x0_pi_enable, .pi_disable = pd692x0_pi_disable, - .pi_is_enabled = pd692x0_pi_is_enabled, .pi_get_voltage = pd692x0_pi_get_voltage, - .pi_get_current_limit = pd692x0_pi_get_current_limit, - .pi_set_current_limit = pd692x0_pi_set_current_limit, + .pi_get_pw_limit = pd692x0_pi_get_pw_limit, + .pi_set_pw_limit = pd692x0_pi_set_pw_limit, + .pi_get_pw_limit_ranges = pd692x0_pi_get_pw_limit_ranges, }; #define PD692X0_FW_LINE_MAX_SZ 0xff diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c index 2906ce173f66..4f2a54afc4d0 100644 --- a/drivers/net/pse-pd/pse_core.c +++ b/drivers/net/pse-pd/pse_core.c @@ -6,6 +6,7 @@ // #include +#include #include #include #include @@ -210,16 +211,25 @@ out: static int pse_pi_is_enabled(struct regulator_dev *rdev) { struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev); + struct pse_admin_state admin_state = {0}; const struct pse_controller_ops *ops; int id, ret; ops = pcdev->ops; - if (!ops->pi_is_enabled) + if (!ops->pi_get_admin_state) return -EOPNOTSUPP; id = rdev_get_id(rdev); mutex_lock(&pcdev->lock); - ret = ops->pi_is_enabled(pcdev, id); + ret = ops->pi_get_admin_state(pcdev, id, &admin_state); + if (ret) + goto out; + + if (admin_state.podl_admin_state == ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED || + admin_state.c33_admin_state == ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED) + ret = 1; + +out: mutex_unlock(&pcdev->lock); return ret; @@ -291,33 +301,25 @@ static int pse_pi_get_voltage(struct regulator_dev *rdev) return ret; } -static int _pse_ethtool_get_status(struct pse_controller_dev *pcdev, - int id, - struct netlink_ext_ack *extack, - struct pse_control_status *status); - static int pse_pi_get_current_limit(struct regulator_dev *rdev) { struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev); const struct pse_controller_ops *ops; - struct netlink_ext_ack extack = {}; - struct pse_control_status st = {}; - int id, uV, ret; + int id, uV, mW, ret; s64 tmp_64; ops = pcdev->ops; id = rdev_get_id(rdev); - mutex_lock(&pcdev->lock); - if (ops->pi_get_current_limit) { - ret = ops->pi_get_current_limit(pcdev, id); - goto out; - } + if (!ops->pi_get_pw_limit || !ops->pi_get_voltage) + return -EOPNOTSUPP; - /* If pi_get_current_limit() callback not populated get voltage - * from pi_get_voltage() and power limit from ethtool_get_status() - * to calculate current limit. - */ - ret = _pse_pi_get_voltage(rdev); + mutex_lock(&pcdev->lock); + ret = ops->pi_get_pw_limit(pcdev, id); + if (ret < 0) + goto out; + mW = ret; + + ret = pse_pi_get_voltage(rdev); if (!ret) { dev_err(pcdev->dev, "Voltage null\n"); ret = -ERANGE; @@ -327,16 +329,7 @@ static int pse_pi_get_current_limit(struct regulator_dev *rdev) goto out; uV = ret; - ret = _pse_ethtool_get_status(pcdev, id, &extack, &st); - if (ret) - goto out; - - if (!st.c33_avail_pw_limit) { - ret = -ENODATA; - goto out; - } - - tmp_64 = st.c33_avail_pw_limit; + tmp_64 = mW; tmp_64 *= 1000000000ull; /* uA = mW * 1000000000 / uV */ ret = DIV_ROUND_CLOSEST_ULL(tmp_64, uV); @@ -351,15 +344,33 @@ static int pse_pi_set_current_limit(struct regulator_dev *rdev, int min_uA, { struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev); const struct pse_controller_ops *ops; - int id, ret; + int id, mW, ret; + s64 tmp_64; ops = pcdev->ops; - if (!ops->pi_set_current_limit) + if (!ops->pi_set_pw_limit || !ops->pi_get_voltage) return -EOPNOTSUPP; + if (max_uA > MAX_PI_CURRENT) + return -ERANGE; + id = rdev_get_id(rdev); mutex_lock(&pcdev->lock); - ret = ops->pi_set_current_limit(pcdev, id, max_uA); + ret = pse_pi_get_voltage(rdev); + if (!ret) { + dev_err(pcdev->dev, "Voltage null\n"); + ret = -ERANGE; + goto out; + } + if (ret < 0) + goto out; + + tmp_64 = ret; + tmp_64 *= max_uA; + /* mW = uA * uV / 1000000000 */ + mW = DIV_ROUND_CLOSEST_ULL(tmp_64, 1000000000); + ret = ops->pi_set_pw_limit(pcdev, id, mW); +out: mutex_unlock(&pcdev->lock); return ret; @@ -403,17 +414,16 @@ devm_pse_pi_regulator_register(struct pse_controller_dev *pcdev, rinit_data->constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS; - if (pcdev->ops->pi_set_current_limit) { + if (pcdev->ops->pi_set_pw_limit) rinit_data->constraints.valid_ops_mask |= REGULATOR_CHANGE_CURRENT; - rinit_data->constraints.max_uA = MAX_PI_CURRENT; - } rinit_data->supply_regulator = "vpwr"; rconfig.dev = pcdev->dev; rconfig.driver_data = pcdev; rconfig.init_data = rinit_data; + rconfig.of_node = pcdev->pi[id].np; rdev = devm_regulator_register(pcdev->dev, rdesc, &rconfig); if (IS_ERR(rdev)) { @@ -444,6 +454,13 @@ int pse_controller_register(struct pse_controller_dev *pcdev) if (!pcdev->nr_lines) pcdev->nr_lines = 1; + if (!pcdev->ops->pi_get_admin_state || + !pcdev->ops->pi_get_pw_status) { + dev_err(pcdev->dev, + "Mandatory status report callbacks are missing"); + return -EINVAL; + } + ret = of_load_pse_pis(pcdev); if (ret) return ret; @@ -736,23 +753,6 @@ out: } EXPORT_SYMBOL_GPL(of_pse_control_get); -static int _pse_ethtool_get_status(struct pse_controller_dev *pcdev, - int id, - struct netlink_ext_ack *extack, - struct pse_control_status *status) -{ - const struct pse_controller_ops *ops; - - ops = pcdev->ops; - if (!ops->ethtool_get_status) { - NL_SET_ERR_MSG(extack, - "PSE driver does not support status report"); - return -EOPNOTSUPP; - } - - return ops->ethtool_get_status(pcdev, id, extack, status); -} - /** * pse_ethtool_get_status - get status of PSE control * @psec: PSE control pointer @@ -763,15 +763,81 @@ static int _pse_ethtool_get_status(struct pse_controller_dev *pcdev, */ int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, - struct pse_control_status *status) + struct ethtool_pse_control_status *status) { - int err; + struct pse_admin_state admin_state = {0}; + struct pse_pw_status pw_status = {0}; + const struct pse_controller_ops *ops; + struct pse_controller_dev *pcdev; + int ret; - mutex_lock(&psec->pcdev->lock); - err = _pse_ethtool_get_status(psec->pcdev, psec->id, extack, status); + pcdev = psec->pcdev; + ops = pcdev->ops; + mutex_lock(&pcdev->lock); + ret = ops->pi_get_admin_state(pcdev, psec->id, &admin_state); + if (ret) + goto out; + status->podl_admin_state = admin_state.podl_admin_state; + status->c33_admin_state = admin_state.c33_admin_state; + + ret = ops->pi_get_pw_status(pcdev, psec->id, &pw_status); + if (ret) + goto out; + status->podl_pw_status = pw_status.podl_pw_status; + status->c33_pw_status = pw_status.c33_pw_status; + + if (ops->pi_get_ext_state) { + struct pse_ext_state_info ext_state_info = {0}; + + ret = ops->pi_get_ext_state(pcdev, psec->id, + &ext_state_info); + if (ret) + goto out; + + memcpy(&status->c33_ext_state_info, + &ext_state_info.c33_ext_state_info, + sizeof(status->c33_ext_state_info)); + } + + if (ops->pi_get_pw_class) { + ret = ops->pi_get_pw_class(pcdev, psec->id); + if (ret < 0) + goto out; + + status->c33_pw_class = ret; + } + + if (ops->pi_get_actual_pw) { + ret = ops->pi_get_actual_pw(pcdev, psec->id); + if (ret < 0) + goto out; + + status->c33_actual_pw = ret; + } + + if (ops->pi_get_pw_limit) { + ret = ops->pi_get_pw_limit(pcdev, psec->id); + if (ret < 0) + goto out; + + status->c33_avail_pw_limit = ret; + } + + if (ops->pi_get_pw_limit_ranges) { + struct pse_pw_limit_ranges pw_limit_ranges = {0}; + + ret = ops->pi_get_pw_limit_ranges(pcdev, psec->id, + &pw_limit_ranges); + if (ret < 0) + goto out; + + status->c33_pw_limit_ranges = + pw_limit_ranges.c33_pw_limit_ranges; + status->c33_pw_limit_nb_ranges = ret; + } +out: mutex_unlock(&psec->pcdev->lock); - - return err; + return ret; } EXPORT_SYMBOL_GPL(pse_ethtool_get_status); @@ -876,6 +942,9 @@ int pse_ethtool_set_pw_limit(struct pse_control *psec, int uV, uA, ret; s64 tmp_64; + if (pw_limit > MAX_PI_PW) + return -ERANGE; + ret = regulator_get_voltage(psec->ps); if (!ret) { NL_SET_ERR_MSG(extack, diff --git a/drivers/net/pse-pd/pse_regulator.c b/drivers/net/pse-pd/pse_regulator.c index 64ab36974fe0..6ce6773fff31 100644 --- a/drivers/net/pse-pd/pse_regulator.c +++ b/drivers/net/pse-pd/pse_regulator.c @@ -52,17 +52,19 @@ pse_reg_pi_disable(struct pse_controller_dev *pcdev, int id) } static int -pse_reg_pi_is_enabled(struct pse_controller_dev *pcdev, int id) +pse_reg_pi_get_admin_state(struct pse_controller_dev *pcdev, int id, + struct pse_admin_state *admin_state) { struct pse_reg_priv *priv = to_pse_reg(pcdev); - return regulator_is_enabled(priv->ps); + admin_state->podl_admin_state = priv->admin_state; + + return 0; } static int -pse_reg_ethtool_get_status(struct pse_controller_dev *pcdev, unsigned long id, - struct netlink_ext_ack *extack, - struct pse_control_status *status) +pse_reg_pi_get_pw_status(struct pse_controller_dev *pcdev, int id, + struct pse_pw_status *pw_status) { struct pse_reg_priv *priv = to_pse_reg(pcdev); int ret; @@ -72,20 +74,19 @@ pse_reg_ethtool_get_status(struct pse_controller_dev *pcdev, unsigned long id, return ret; if (!ret) - status->podl_pw_status = ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED; + pw_status->podl_pw_status = + ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED; else - status->podl_pw_status = + pw_status->podl_pw_status = ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING; - status->podl_admin_state = priv->admin_state; - return 0; } static const struct pse_controller_ops pse_reg_ops = { - .ethtool_get_status = pse_reg_ethtool_get_status, + .pi_get_admin_state = pse_reg_pi_get_admin_state, + .pi_get_pw_status = pse_reg_pi_get_pw_status, .pi_enable = pse_reg_pi_enable, - .pi_is_enabled = pse_reg_pi_is_enabled, .pi_disable = pse_reg_pi_disable, }; diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index 5c4e88be46ee..5e9dda2c0eac 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -25,20 +25,32 @@ #define TPS23881_REG_GEN_MASK 0x17 #define TPS23881_REG_NBITACC BIT(5) #define TPS23881_REG_PW_EN 0x19 +#define TPS23881_REG_2PAIR_POL1 0x1e #define TPS23881_REG_PORT_MAP 0x26 #define TPS23881_REG_PORT_POWER 0x29 -#define TPS23881_REG_POEPLUS 0x40 +#define TPS23881_REG_4PAIR_POL1 0x2a +#define TPS23881_REG_INPUT_V 0x2e +#define TPS23881_REG_CHAN1_A 0x30 +#define TPS23881_REG_CHAN1_V 0x32 +#define TPS23881_REG_FOLDBACK 0x40 #define TPS23881_REG_TPON BIT(0) #define TPS23881_REG_FWREV 0x41 #define TPS23881_REG_DEVID 0x43 #define TPS23881_REG_DEVID_MASK 0xF0 #define TPS23881_DEVICE_ID 0x02 +#define TPS23881_REG_CHAN1_CLASS 0x4c #define TPS23881_REG_SRAM_CTRL 0x60 #define TPS23881_REG_SRAM_DATA 0x61 +#define TPS23881_UV_STEP 3662 +#define TPS23881_NA_STEP 70190 +#define TPS23881_MW_STEP 500 +#define TPS23881_MIN_PI_PW_LIMIT_MW 2000 + struct tps23881_port_desc { u8 chan[2]; bool is_4p; + int pw_pol; }; struct tps23881_priv { @@ -53,40 +65,123 @@ static struct tps23881_priv *to_tps23881_priv(struct pse_controller_dev *pcdev) return container_of(pcdev, struct tps23881_priv, pcdev); } +/* + * Helper to extract a value from a u16 register value, which is made of two + * u8 registers. The function calculates the bit offset based on the channel + * and extracts the relevant bits using a provided field mask. + * + * @param reg_val: The u16 register value (composed of two u8 registers). + * @param chan: The channel number (0-7). + * @param field_offset: The base bit offset to apply (e.g., 0 or 4). + * @param field_mask: The mask to apply to extract the required bits. + * @return: The extracted value for the specific channel. + */ +static u16 tps23881_calc_val(u16 reg_val, u8 chan, u8 field_offset, + u16 field_mask) +{ + if (chan >= 4) + reg_val >>= 8; + + return (reg_val >> field_offset) & field_mask; +} + +/* + * Helper to combine individual channel values into a u16 register value. + * The function sets the value for a specific channel in the appropriate + * position. + * + * @param reg_val: The current u16 register value. + * @param chan: The channel number (0-7). + * @param field_offset: The base bit offset to apply (e.g., 0 or 4). + * @param field_mask: The mask to apply for the field (e.g., 0x0F). + * @param field_val: The value to set for the specific channel (masked by + * field_mask). + * @return: The updated u16 register value with the channel value set. + */ +static u16 tps23881_set_val(u16 reg_val, u8 chan, u8 field_offset, + u16 field_mask, u16 field_val) +{ + field_val &= field_mask; + + if (chan < 4) { + reg_val &= ~(field_mask << field_offset); + reg_val |= (field_val << field_offset); + } else { + reg_val &= ~(field_mask << (field_offset + 8)); + reg_val |= (field_val << (field_offset + 8)); + } + + return reg_val; +} + +static int +tps23881_pi_set_pw_pol_limit(struct tps23881_priv *priv, int id, u8 pw_pol, + bool is_4p) +{ + struct i2c_client *client = priv->client; + int ret, reg; + u16 val; + u8 chan; + + chan = priv->port[id].chan[0]; + if (!is_4p) { + reg = TPS23881_REG_2PAIR_POL1 + (chan % 4); + } else { + /* One chan is enough to configure the 4p PI power limit */ + if ((chan % 4) < 2) + reg = TPS23881_REG_4PAIR_POL1; + else + reg = TPS23881_REG_4PAIR_POL1 + 1; + } + + ret = i2c_smbus_read_word_data(client, reg); + if (ret < 0) + return ret; + + val = tps23881_set_val(ret, chan, 0, 0xff, pw_pol); + return i2c_smbus_write_word_data(client, reg, val); +} + +static int tps23881_pi_enable_manual_pol(struct tps23881_priv *priv, int id) +{ + struct i2c_client *client = priv->client; + int ret; + u8 chan; + u16 val; + + ret = i2c_smbus_read_byte_data(client, TPS23881_REG_FOLDBACK); + if (ret < 0) + return ret; + + /* No need to test if the chan is PoE4 as setting either bit for a + * 4P configured port disables the automatic configuration on both + * channels. + */ + chan = priv->port[id].chan[0]; + val = tps23881_set_val(ret, chan, 0, BIT(chan % 4), BIT(chan % 4)); + return i2c_smbus_write_byte_data(client, TPS23881_REG_FOLDBACK, val); +} + static int tps23881_pi_enable(struct pse_controller_dev *pcdev, int id) { struct tps23881_priv *priv = to_tps23881_priv(pcdev); struct i2c_client *client = priv->client; u8 chan; u16 val; - int ret; if (id >= TPS23881_MAX_CHANS) return -ERANGE; - ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); - if (ret < 0) - return ret; - chan = priv->port[id].chan[0]; - if (chan < 4) - val = (u16)(ret | BIT(chan)); - else - val = (u16)(ret | BIT(chan + 4)); + val = tps23881_set_val(0, chan, 0, BIT(chan % 4), BIT(chan % 4)); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; - if (chan < 4) - val |= BIT(chan); - else - val |= BIT(chan + 4); + val = tps23881_set_val(val, chan, 0, BIT(chan % 4), + BIT(chan % 4)); } - ret = i2c_smbus_write_word_data(client, TPS23881_REG_PW_EN, val); - if (ret) - return ret; - - return 0; + return i2c_smbus_write_word_data(client, TPS23881_REG_PW_EN, val); } static int tps23881_pi_disable(struct pse_controller_dev *pcdev, int id) @@ -100,37 +195,68 @@ static int tps23881_pi_disable(struct pse_controller_dev *pcdev, int id) if (id >= TPS23881_MAX_CHANS) return -ERANGE; - ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); - if (ret < 0) - return ret; - chan = priv->port[id].chan[0]; - if (chan < 4) - val = (u16)(ret | BIT(chan + 4)); - else - val = (u16)(ret | BIT(chan + 8)); + val = tps23881_set_val(0, chan, 4, BIT(chan % 4), BIT(chan % 4)); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; - if (chan < 4) - val |= BIT(chan + 4); - else - val |= BIT(chan + 8); + val = tps23881_set_val(val, chan, 4, BIT(chan % 4), + BIT(chan % 4)); } ret = i2c_smbus_write_word_data(client, TPS23881_REG_PW_EN, val); if (ret) return ret; - return 0; + /* PWOFF command resets lots of register which need to be + * configured again. According to the datasheet "It may take upwards + * of 5ms after PWOFFn command for all register values to be updated" + */ + mdelay(5); + + /* Enable detection and classification */ + ret = i2c_smbus_read_word_data(client, TPS23881_REG_DET_CLA_EN); + if (ret < 0) + return ret; + + chan = priv->port[id].chan[0]; + val = tps23881_set_val(ret, chan, 0, BIT(chan % 4), BIT(chan % 4)); + val = tps23881_set_val(val, chan, 4, BIT(chan % 4), BIT(chan % 4)); + + if (priv->port[id].is_4p) { + chan = priv->port[id].chan[1]; + val = tps23881_set_val(ret, chan, 0, BIT(chan % 4), + BIT(chan % 4)); + val = tps23881_set_val(val, chan, 4, BIT(chan % 4), + BIT(chan % 4)); + } + + ret = i2c_smbus_write_word_data(client, TPS23881_REG_DET_CLA_EN, val); + if (ret) + return ret; + + /* No power policy */ + if (priv->port[id].pw_pol < 0) + return 0; + + ret = tps23881_pi_enable_manual_pol(priv, id); + if (ret < 0) + return ret; + + /* Set power policy */ + return tps23881_pi_set_pw_pol_limit(priv, id, priv->port[id].pw_pol, + priv->port[id].is_4p); } -static int tps23881_pi_is_enabled(struct pse_controller_dev *pcdev, int id) +static int +tps23881_pi_get_admin_state(struct pse_controller_dev *pcdev, int id, + struct pse_admin_state *admin_state) { struct tps23881_priv *priv = to_tps23881_priv(pcdev); struct i2c_client *client = priv->client; bool enabled; u8 chan; + u16 val; int ret; ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); @@ -138,32 +264,35 @@ static int tps23881_pi_is_enabled(struct pse_controller_dev *pcdev, int id) return ret; chan = priv->port[id].chan[0]; - if (chan < 4) - enabled = ret & BIT(chan); - else - enabled = ret & BIT(chan + 4); + val = tps23881_calc_val(ret, chan, 0, BIT(chan % 4)); + enabled = !!(val); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; - if (chan < 4) - enabled &= !!(ret & BIT(chan)); - else - enabled &= !!(ret & BIT(chan + 4)); + val = tps23881_calc_val(ret, chan, 0, BIT(chan % 4)); + enabled &= !!(val); } /* Return enabled status only if both channel are on this state */ - return enabled; + if (enabled) + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; + else + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; + + return 0; } -static int tps23881_ethtool_get_status(struct pse_controller_dev *pcdev, - unsigned long id, - struct netlink_ext_ack *extack, - struct pse_control_status *status) +static int +tps23881_pi_get_pw_status(struct pse_controller_dev *pcdev, int id, + struct pse_pw_status *pw_status) { struct tps23881_priv *priv = to_tps23881_priv(pcdev); struct i2c_client *client = priv->client; - bool enabled, delivering; + bool delivering; u8 chan; + u16 val; int ret; ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); @@ -171,40 +300,197 @@ static int tps23881_ethtool_get_status(struct pse_controller_dev *pcdev, return ret; chan = priv->port[id].chan[0]; - if (chan < 4) { - enabled = ret & BIT(chan); - delivering = ret & BIT(chan + 4); - } else { - enabled = ret & BIT(chan + 4); - delivering = ret & BIT(chan + 8); - } + val = tps23881_calc_val(ret, chan, 4, BIT(chan % 4)); + delivering = !!(val); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; - if (chan < 4) { - enabled &= !!(ret & BIT(chan)); - delivering &= !!(ret & BIT(chan + 4)); - } else { - enabled &= !!(ret & BIT(chan + 4)); - delivering &= !!(ret & BIT(chan + 8)); - } + val = tps23881_calc_val(ret, chan, 4, BIT(chan % 4)); + delivering &= !!(val); } /* Return delivering status only if both channel are on this state */ if (delivering) - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING; + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING; else - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED; - - /* Return enabled status only if both channel are on this state */ - if (enabled) - status->c33_admin_state = ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; - else - status->c33_admin_state = ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED; return 0; } +static int tps23881_pi_get_voltage(struct pse_controller_dev *pcdev, int id) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + struct i2c_client *client = priv->client; + int ret; + u64 uV; + + ret = i2c_smbus_read_word_data(client, TPS23881_REG_INPUT_V); + if (ret < 0) + return ret; + + uV = ret & 0x3fff; + uV *= TPS23881_UV_STEP; + + return (int)uV; +} + +static int +tps23881_pi_get_chan_current(struct tps23881_priv *priv, u8 chan) +{ + struct i2c_client *client = priv->client; + int reg, ret; + u64 tmp_64; + + /* Registers 0x30 to 0x3d */ + reg = TPS23881_REG_CHAN1_A + (chan % 4) * 4 + (chan >= 4); + ret = i2c_smbus_read_word_data(client, reg); + if (ret < 0) + return ret; + + tmp_64 = ret & 0x3fff; + tmp_64 *= TPS23881_NA_STEP; + /* uA = nA / 1000 */ + tmp_64 = DIV_ROUND_CLOSEST_ULL(tmp_64, 1000); + return (int)tmp_64; +} + +static int tps23881_pi_get_pw_class(struct pse_controller_dev *pcdev, + int id) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + struct i2c_client *client = priv->client; + int ret, reg; + u8 chan; + + chan = priv->port[id].chan[0]; + reg = TPS23881_REG_CHAN1_CLASS + (chan % 4); + ret = i2c_smbus_read_word_data(client, reg); + if (ret < 0) + return ret; + + return tps23881_calc_val(ret, chan, 4, 0x0f); +} + +static int +tps23881_pi_get_actual_pw(struct pse_controller_dev *pcdev, int id) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + int ret, uV, uA; + u64 tmp_64; + u8 chan; + + ret = tps23881_pi_get_voltage(&priv->pcdev, id); + if (ret < 0) + return ret; + uV = ret; + + chan = priv->port[id].chan[0]; + ret = tps23881_pi_get_chan_current(priv, chan); + if (ret < 0) + return ret; + uA = ret; + + if (priv->port[id].is_4p) { + chan = priv->port[id].chan[1]; + ret = tps23881_pi_get_chan_current(priv, chan); + if (ret < 0) + return ret; + uA += ret; + } + + tmp_64 = uV; + tmp_64 *= uA; + /* mW = uV * uA / 1000000000 */ + return DIV_ROUND_CLOSEST_ULL(tmp_64, 1000000000); +} + +static int +tps23881_pi_get_pw_limit_chan(struct tps23881_priv *priv, u8 chan) +{ + struct i2c_client *client = priv->client; + int ret, reg; + u16 val; + + reg = TPS23881_REG_2PAIR_POL1 + (chan % 4); + ret = i2c_smbus_read_word_data(client, reg); + if (ret < 0) + return ret; + + val = tps23881_calc_val(ret, chan, 0, 0xff); + return val * TPS23881_MW_STEP; +} + +static int tps23881_pi_get_pw_limit(struct pse_controller_dev *pcdev, int id) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + int ret, mW; + u8 chan; + + chan = priv->port[id].chan[0]; + ret = tps23881_pi_get_pw_limit_chan(priv, chan); + if (ret < 0) + return ret; + + mW = ret; + if (priv->port[id].is_4p) { + chan = priv->port[id].chan[1]; + ret = tps23881_pi_get_pw_limit_chan(priv, chan); + if (ret < 0) + return ret; + mW += ret; + } + + return mW; +} + +static int tps23881_pi_set_pw_limit(struct pse_controller_dev *pcdev, + int id, int max_mW) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + u8 pw_pol; + int ret; + + if (max_mW < TPS23881_MIN_PI_PW_LIMIT_MW || MAX_PI_PW < max_mW) { + dev_err(&priv->client->dev, + "power limit %d out of ranges [%d,%d]", + max_mW, TPS23881_MIN_PI_PW_LIMIT_MW, MAX_PI_PW); + return -ERANGE; + } + + ret = tps23881_pi_enable_manual_pol(priv, id); + if (ret < 0) + return ret; + + pw_pol = DIV_ROUND_CLOSEST_ULL(max_mW, TPS23881_MW_STEP); + + /* Save power policy to reconfigure it after a disabled call */ + priv->port[id].pw_pol = pw_pol; + return tps23881_pi_set_pw_pol_limit(priv, id, pw_pol, + priv->port[id].is_4p); +} + +static int +tps23881_pi_get_pw_limit_ranges(struct pse_controller_dev *pcdev, int id, + struct pse_pw_limit_ranges *pw_limit_ranges) +{ + struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; + + c33_pw_limit_ranges = kzalloc(sizeof(*c33_pw_limit_ranges), + GFP_KERNEL); + if (!c33_pw_limit_ranges) + return -ENOMEM; + + c33_pw_limit_ranges->min = TPS23881_MIN_PI_PW_LIMIT_MW; + c33_pw_limit_ranges->max = MAX_PI_PW; + pw_limit_ranges->c33_pw_limit_ranges = c33_pw_limit_ranges; + + /* Return the number of ranges */ + return 1; +} + /* Parse managers subnode into a array of device node */ static int tps23881_get_of_channels(struct tps23881_priv *priv, @@ -488,7 +774,7 @@ tps23881_write_port_matrix(struct tps23881_priv *priv, struct i2c_client *client = priv->client; u8 pi_id, lgcl_chan, hw_chan; u16 val = 0; - int i, ret; + int i; for (i = 0; i < port_cnt; i++) { pi_id = port_matrix[i].pi_id; @@ -499,6 +785,9 @@ tps23881_write_port_matrix(struct tps23881_priv *priv, if (port_matrix[i].exist) priv->port[pi_id].chan[0] = lgcl_chan; + /* Initialize power policy internal value */ + priv->port[pi_id].pw_pol = -1; + /* Set hardware port matrix for all ports */ val |= hw_chan << (lgcl_chan * 2); @@ -519,11 +808,7 @@ tps23881_write_port_matrix(struct tps23881_priv *priv, } /* Write hardware ports matrix */ - ret = i2c_smbus_write_word_data(client, TPS23881_REG_PORT_MAP, val); - if (ret) - return ret; - - return 0; + return i2c_smbus_write_word_data(client, TPS23881_REG_PORT_MAP, val); } static int @@ -572,11 +857,7 @@ tps23881_set_ports_conf(struct tps23881_priv *priv, val |= BIT(port_matrix[i].lgcl_chan[1]) | BIT(port_matrix[i].lgcl_chan[1] + 4); } - ret = i2c_smbus_write_word_data(client, TPS23881_REG_DET_CLA_EN, val); - if (ret) - return ret; - - return 0; + return i2c_smbus_write_word_data(client, TPS23881_REG_DET_CLA_EN, val); } static int @@ -602,11 +883,7 @@ tps23881_set_ports_matrix(struct tps23881_priv *priv, if (ret) return ret; - ret = tps23881_set_ports_conf(priv, port_matrix); - if (ret) - return ret; - - return 0; + return tps23881_set_ports_conf(priv, port_matrix); } static int tps23881_setup_pi_matrix(struct pse_controller_dev *pcdev) @@ -634,8 +911,14 @@ static const struct pse_controller_ops tps23881_ops = { .setup_pi_matrix = tps23881_setup_pi_matrix, .pi_enable = tps23881_pi_enable, .pi_disable = tps23881_pi_disable, - .pi_is_enabled = tps23881_pi_is_enabled, - .ethtool_get_status = tps23881_ethtool_get_status, + .pi_get_admin_state = tps23881_pi_get_admin_state, + .pi_get_pw_status = tps23881_pi_get_pw_status, + .pi_get_pw_class = tps23881_pi_get_pw_class, + .pi_get_actual_pw = tps23881_pi_get_actual_pw, + .pi_get_voltage = tps23881_pi_get_voltage, + .pi_get_pw_limit = tps23881_pi_get_pw_limit, + .pi_set_pw_limit = tps23881_pi_set_pw_limit, + .pi_get_pw_limit_ranges = tps23881_pi_get_pw_limit_ranges, }; static const char fw_parity_name[] = "ti/tps23881/tps23881-parity-14.bin"; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 5aa41d5f7765..5ca6ecf0ce5f 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1329,9 +1329,9 @@ int tap_queue_resize(struct tap_dev *tap) list_for_each_entry(q, &tap->queue_list, next) rings[i++] = &q->ring; - ret = ptr_ring_resize_multiple(rings, n, - dev->tx_queue_len, GFP_KERNEL, - __skb_array_destroy_skb); + ret = ptr_ring_resize_multiple_bh(rings, n, + dev->tx_queue_len, GFP_KERNEL, + __skb_array_destroy_skb); kfree(rings); return ret; diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 69ea2c3c76bf..dc7cbd6a9798 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -998,9 +998,13 @@ static void __team_compute_features(struct team *team) unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; - vlan_features = netdev_base_features(vlan_features); - rcu_read_lock(); + if (list_empty(&team->port_list)) + goto done; + + vlan_features = netdev_base_features(vlan_features); + enc_features = netdev_base_features(enc_features); + list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, @@ -1010,11 +1014,11 @@ static void __team_compute_features(struct team *team) port->dev->hw_enc_features, TEAM_ENC_FEATURES); - dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } +done: rcu_read_unlock(); team->dev->vlan_features = vlan_features; @@ -1171,6 +1175,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return -EBUSY; } + if (netdev_has_upper_dev(port_dev, dev)) { + NL_SET_ERR_MSG(extack, "Device is already a lower device of the team interface"); + netdev_err(dev, "Device %s is already a lower device of the team interface\n", + portname); + return -EBUSY; + } + if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d7a865ef370b..28624cca91f8 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -574,14 +574,18 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, return ret; } -static inline bool tun_not_capable(struct tun_struct *tun) +static inline bool tun_capable(struct tun_struct *tun) { const struct cred *cred = current_cred(); struct net *net = dev_net(tun->dev); - return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || - (gid_valid(tun->group) && !in_egroup_p(tun->group))) && - !ns_capable(net->user_ns, CAP_NET_ADMIN); + if (ns_capable(net->user_ns, CAP_NET_ADMIN)) + return 1; + if (uid_valid(tun->owner) && uid_eq(cred->euid, tun->owner)) + return 1; + if (gid_valid(tun->group) && in_egroup_p(tun->group)) + return 1; + return 0; } static void tun_set_real_num_queues(struct tun_struct *tun) @@ -1481,7 +1485,7 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { - const struct iovec *iov = iter_iov(it); + const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; @@ -2778,7 +2782,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) !!(tun->flags & IFF_MULTI_QUEUE)) return -EINVAL; - if (tun_not_capable(tun)) + if (!tun_capable(tun)) return -EPERM; err = security_tun_dev_open(tun->security); if (err < 0) @@ -3697,9 +3701,9 @@ static int tun_queue_resize(struct tun_struct *tun) list_for_each_entry(tfile, &tun->disabled, next) rings[i++] = &tfile->tx_ring; - ret = ptr_ring_resize_multiple(rings, n, - dev->tx_queue_len, GFP_KERNEL, - tun_ptr_free); + ret = ptr_ring_resize_multiple_bh(rings, n, + dev->tx_queue_len, GFP_KERNEL, + tun_ptr_free); kfree(rings); return ret; diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 46afb95ffabe..a19789b57190 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -61,7 +61,18 @@ #define IPHETH_USBINTF_PROTO 1 #define IPHETH_IP_ALIGN 2 /* padding at front of URB */ -#define IPHETH_NCM_HEADER_SIZE (12 + 96) /* NCMH + NCM0 */ +/* On iOS devices, NCM headers in RX have a fixed size regardless of DPE count: + * - NTH16 (NCMH): 12 bytes, as per CDC NCM 1.0 spec + * - NDP16 (NCM0): 96 bytes, of which + * - NDP16 fixed header: 8 bytes + * - maximum of 22 DPEs (21 datagrams + trailer), 4 bytes each + */ +#define IPHETH_NDP16_MAX_DPE 22 +#define IPHETH_NDP16_HEADER_SIZE (sizeof(struct usb_cdc_ncm_ndp16) + \ + IPHETH_NDP16_MAX_DPE * \ + sizeof(struct usb_cdc_ncm_dpe16)) +#define IPHETH_NCM_HEADER_SIZE (sizeof(struct usb_cdc_ncm_nth16) + \ + IPHETH_NDP16_HEADER_SIZE) #define IPHETH_TX_BUF_SIZE ETH_FRAME_LEN #define IPHETH_RX_BUF_SIZE_LEGACY (IPHETH_IP_ALIGN + ETH_FRAME_LEN) #define IPHETH_RX_BUF_SIZE_NCM 65536 @@ -207,15 +218,23 @@ static int ipheth_rcvbulk_callback_legacy(struct urb *urb) return ipheth_consume_skb(buf, len, dev); } +/* In "NCM mode", the iOS device encapsulates RX (phone->computer) traffic + * in NCM Transfer Blocks (similarly to CDC NCM). However, unlike reverse + * tethering (handled by the `cdc_ncm` driver), regular tethering is not + * compliant with the CDC NCM spec, as the device is missing the necessary + * descriptors, and TX (computer->phone) traffic is not encapsulated + * at all. Thus `ipheth` implements a very limited subset of the spec with + * the sole purpose of parsing RX URBs. + */ static int ipheth_rcvbulk_callback_ncm(struct urb *urb) { struct usb_cdc_ncm_nth16 *ncmh; struct usb_cdc_ncm_ndp16 *ncm0; struct usb_cdc_ncm_dpe16 *dpe; struct ipheth_device *dev; + u16 dg_idx, dg_len; int retval = -EINVAL; char *buf; - int len; dev = urb->context; @@ -226,40 +245,42 @@ static int ipheth_rcvbulk_callback_ncm(struct urb *urb) ncmh = urb->transfer_buffer; if (ncmh->dwSignature != cpu_to_le32(USB_CDC_NCM_NTH16_SIGN) || - le16_to_cpu(ncmh->wNdpIndex) >= urb->actual_length) { - dev->net->stats.rx_errors++; - return retval; - } + /* On iOS, NDP16 directly follows NTH16 */ + ncmh->wNdpIndex != cpu_to_le16(sizeof(struct usb_cdc_ncm_nth16))) + goto rx_error; - ncm0 = urb->transfer_buffer + le16_to_cpu(ncmh->wNdpIndex); - if (ncm0->dwSignature != cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN) || - le16_to_cpu(ncmh->wHeaderLength) + le16_to_cpu(ncm0->wLength) >= - urb->actual_length) { - dev->net->stats.rx_errors++; - return retval; - } + ncm0 = urb->transfer_buffer + sizeof(struct usb_cdc_ncm_nth16); + if (ncm0->dwSignature != cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN)) + goto rx_error; dpe = ncm0->dpe16; - while (le16_to_cpu(dpe->wDatagramIndex) != 0 && - le16_to_cpu(dpe->wDatagramLength) != 0) { - if (le16_to_cpu(dpe->wDatagramIndex) >= urb->actual_length || - le16_to_cpu(dpe->wDatagramIndex) + - le16_to_cpu(dpe->wDatagramLength) > urb->actual_length) { + for (int dpe_i = 0; dpe_i < IPHETH_NDP16_MAX_DPE; ++dpe_i, ++dpe) { + dg_idx = le16_to_cpu(dpe->wDatagramIndex); + dg_len = le16_to_cpu(dpe->wDatagramLength); + + /* Null DPE must be present after last datagram pointer entry + * (3.3.1 USB CDC NCM spec v1.0) + */ + if (dg_idx == 0 && dg_len == 0) + return 0; + + if (dg_idx < IPHETH_NCM_HEADER_SIZE || + dg_idx >= urb->actual_length || + dg_len > urb->actual_length - dg_idx) { dev->net->stats.rx_length_errors++; return retval; } - buf = urb->transfer_buffer + le16_to_cpu(dpe->wDatagramIndex); - len = le16_to_cpu(dpe->wDatagramLength); + buf = urb->transfer_buffer + dg_idx; - retval = ipheth_consume_skb(buf, len, dev); + retval = ipheth_consume_skb(buf, dg_len, dev); if (retval != 0) return retval; - - dpe++; } - return 0; +rx_error: + dev->net->stats.rx_errors++; + return retval; } static void ipheth_rcvbulk_callback(struct urb *urb) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 531b1b6a37d1..a91bf9c7e31d 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -439,7 +439,7 @@ struct lan78xx_net { struct usb_anchor deferred; struct mutex dev_mutex; /* serialise open/stop wrt suspend/resume */ - struct mutex phy_mutex; /* for phy access */ + struct mutex mdiobus_mutex; /* for MDIO bus access */ unsigned int pipe_in, pipe_out, pipe_intr; unsigned int bulk_in_delay; @@ -472,10 +472,6 @@ struct lan78xx_net { struct irq_domain_data domain_data; }; -/* define external phy id */ -#define PHY_LAN8835 (0x0007C130) -#define PHY_KSZ9031RNX (0x00221620) - /* use ethtool to change the level for any given device */ static int msg_level = -1; module_param(msg_level, int, 0); @@ -625,8 +621,8 @@ static int lan78xx_read_reg(struct lan78xx_net *dev, u32 index, u32 *data) *data = *buf; } else if (net_ratelimit()) { netdev_warn(dev->net, - "Failed to read register index 0x%08x. ret = %d", - index, ret); + "Failed to read register index 0x%08x. ret = %pe", + index, ERR_PTR(ret)); } kfree(buf); @@ -656,8 +652,8 @@ static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data) if (unlikely(ret < 0) && net_ratelimit()) { netdev_warn(dev->net, - "Failed to write register index 0x%08x. ret = %d", - index, ret); + "Failed to write register index 0x%08x. ret = %pe", + index, ERR_PTR(ret)); } kfree(buf); @@ -678,11 +674,7 @@ static int lan78xx_update_reg(struct lan78xx_net *dev, u32 reg, u32 mask, buf &= ~mask; buf |= (mask & data); - ret = lan78xx_write_reg(dev, reg, buf); - if (ret < 0) - return ret; - - return 0; + return lan78xx_write_reg(dev, reg, buf); } static int lan78xx_read_stats(struct lan78xx_net *dev, @@ -812,8 +804,156 @@ static void lan78xx_update_stats(struct lan78xx_net *dev) usb_autopm_put_interface(dev->intf); } -/* Loop until the read is completed with timeout called with phy_mutex held */ -static int lan78xx_phy_wait_not_busy(struct lan78xx_net *dev) +static int lan78xx_start_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enable) +{ + return lan78xx_update_reg(dev, reg, hw_enable, hw_enable); +} + +static int lan78xx_stop_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enabled, + u32 hw_disabled) +{ + unsigned long timeout; + bool stopped = true; + int ret; + u32 buf; + + /* Stop the h/w block (if not already stopped) */ + + ret = lan78xx_read_reg(dev, reg, &buf); + if (ret < 0) + return ret; + + if (buf & hw_enabled) { + buf &= ~hw_enabled; + + ret = lan78xx_write_reg(dev, reg, buf); + if (ret < 0) + return ret; + + stopped = false; + timeout = jiffies + HW_DISABLE_TIMEOUT; + do { + ret = lan78xx_read_reg(dev, reg, &buf); + if (ret < 0) + return ret; + + if (buf & hw_disabled) + stopped = true; + else + msleep(HW_DISABLE_DELAY_MS); + } while (!stopped && !time_after(jiffies, timeout)); + } + + return stopped ? 0 : -ETIMEDOUT; +} + +static int lan78xx_flush_fifo(struct lan78xx_net *dev, u32 reg, u32 fifo_flush) +{ + return lan78xx_update_reg(dev, reg, fifo_flush, fifo_flush); +} + +static int lan78xx_start_tx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "start tx path"); + + /* Start the MAC transmitter */ + + ret = lan78xx_start_hw(dev, MAC_TX, MAC_TX_TXEN_); + if (ret < 0) + return ret; + + /* Start the Tx FIFO */ + + ret = lan78xx_start_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_); + if (ret < 0) + return ret; + + return 0; +} + +static int lan78xx_stop_tx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "stop tx path"); + + /* Stop the Tx FIFO */ + + ret = lan78xx_stop_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_, FCT_TX_CTL_DIS_); + if (ret < 0) + return ret; + + /* Stop the MAC transmitter */ + + ret = lan78xx_stop_hw(dev, MAC_TX, MAC_TX_TXEN_, MAC_TX_TXD_); + if (ret < 0) + return ret; + + return 0; +} + +/* The caller must ensure the Tx path is stopped before calling + * lan78xx_flush_tx_fifo(). + */ +static int lan78xx_flush_tx_fifo(struct lan78xx_net *dev) +{ + return lan78xx_flush_fifo(dev, FCT_TX_CTL, FCT_TX_CTL_RST_); +} + +static int lan78xx_start_rx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "start rx path"); + + /* Start the Rx FIFO */ + + ret = lan78xx_start_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_); + if (ret < 0) + return ret; + + /* Start the MAC receiver*/ + + ret = lan78xx_start_hw(dev, MAC_RX, MAC_RX_RXEN_); + if (ret < 0) + return ret; + + return 0; +} + +static int lan78xx_stop_rx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "stop rx path"); + + /* Stop the MAC receiver */ + + ret = lan78xx_stop_hw(dev, MAC_RX, MAC_RX_RXEN_, MAC_RX_RXD_); + if (ret < 0) + return ret; + + /* Stop the Rx FIFO */ + + ret = lan78xx_stop_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_, FCT_RX_CTL_DIS_); + if (ret < 0) + return ret; + + return 0; +} + +/* The caller must ensure the Rx path is stopped before calling + * lan78xx_flush_rx_fifo(). + */ +static int lan78xx_flush_rx_fifo(struct lan78xx_net *dev) +{ + return lan78xx_flush_fifo(dev, FCT_RX_CTL, FCT_RX_CTL_RST_); +} + +/* Loop until the read is completed with timeout called with mdiobus_mutex held */ +static int lan78xx_mdiobus_wait_not_busy(struct lan78xx_net *dev) { unsigned long start_time = jiffies; u32 val; @@ -821,14 +961,14 @@ static int lan78xx_phy_wait_not_busy(struct lan78xx_net *dev) do { ret = lan78xx_read_reg(dev, MII_ACC, &val); - if (unlikely(ret < 0)) - return -EIO; + if (ret < 0) + return ret; if (!(val & MII_ACC_MII_BUSY_)) return 0; } while (!time_after(jiffies, start_time + HZ)); - return -EIO; + return -ETIMEDOUT; } static inline u32 mii_access(int id, int index, int read) @@ -854,8 +994,8 @@ static int lan78xx_wait_eeprom(struct lan78xx_net *dev) do { ret = lan78xx_read_reg(dev, E2P_CMD, &val); - if (unlikely(ret < 0)) - return -EIO; + if (ret < 0) + return ret; if (!(val & E2P_CMD_EPC_BUSY_) || (val & E2P_CMD_EPC_TIMEOUT_)) @@ -865,7 +1005,7 @@ static int lan78xx_wait_eeprom(struct lan78xx_net *dev) if (val & (E2P_CMD_EPC_TIMEOUT_ | E2P_CMD_EPC_BUSY_)) { netdev_warn(dev->net, "EEPROM read operation timeout"); - return -EIO; + return -ETIMEDOUT; } return 0; @@ -879,8 +1019,8 @@ static int lan78xx_eeprom_confirm_not_busy(struct lan78xx_net *dev) do { ret = lan78xx_read_reg(dev, E2P_CMD, &val); - if (unlikely(ret < 0)) - return -EIO; + if (ret < 0) + return ret; if (!(val & E2P_CMD_EPC_BUSY_)) return 0; @@ -889,75 +1029,81 @@ static int lan78xx_eeprom_confirm_not_busy(struct lan78xx_net *dev) } while (!time_after(jiffies, start_time + HZ)); netdev_warn(dev->net, "EEPROM is busy"); - return -EIO; + return -ETIMEDOUT; } static int lan78xx_read_raw_eeprom(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { - u32 val; - u32 saved; + u32 val, saved; int i, ret; - int retval; /* depends on chip, some EEPROM pins are muxed with LED function. * disable & restore LED function to access EEPROM. */ ret = lan78xx_read_reg(dev, HW_CFG, &val); + if (ret < 0) + return ret; + saved = val; if (dev->chipid == ID_REV_CHIP_ID_7800_) { val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_); ret = lan78xx_write_reg(dev, HW_CFG, val); + if (ret < 0) + return ret; } - retval = lan78xx_eeprom_confirm_not_busy(dev); - if (retval) - return retval; + ret = lan78xx_eeprom_confirm_not_busy(dev); + if (ret == -ETIMEDOUT) + goto read_raw_eeprom_done; + /* If USB fails, there is nothing to do */ + if (ret < 0) + return ret; for (i = 0; i < length; i++) { val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_READ_; val |= (offset & E2P_CMD_EPC_ADDR_MASK_); ret = lan78xx_write_reg(dev, E2P_CMD, val); - if (unlikely(ret < 0)) { - retval = -EIO; - goto exit; - } + if (ret < 0) + return ret; - retval = lan78xx_wait_eeprom(dev); - if (retval < 0) - goto exit; + ret = lan78xx_wait_eeprom(dev); + /* Looks like not USB specific error, try to recover */ + if (ret == -ETIMEDOUT) + goto read_raw_eeprom_done; + /* If USB fails, there is nothing to do */ + if (ret < 0) + return ret; ret = lan78xx_read_reg(dev, E2P_DATA, &val); - if (unlikely(ret < 0)) { - retval = -EIO; - goto exit; - } + if (ret < 0) + return ret; data[i] = val & 0xFF; offset++; } - retval = 0; -exit: +read_raw_eeprom_done: if (dev->chipid == ID_REV_CHIP_ID_7800_) - ret = lan78xx_write_reg(dev, HW_CFG, saved); + return lan78xx_write_reg(dev, HW_CFG, saved); - return retval; + return 0; } static int lan78xx_read_eeprom(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { - u8 sig; int ret; + u8 sig; ret = lan78xx_read_raw_eeprom(dev, 0, 1, &sig); - if ((ret == 0) && (sig == EEPROM_INDICATOR)) - ret = lan78xx_read_raw_eeprom(dev, offset, length, data); - else - ret = -EINVAL; + if (ret < 0) + return ret; - return ret; + if (sig != EEPROM_INDICATOR) + return -ENODATA; + + return lan78xx_read_raw_eeprom(dev, offset, length, data); } static int lan78xx_write_raw_eeprom(struct lan78xx_net *dev, u32 offset, @@ -966,113 +1112,144 @@ static int lan78xx_write_raw_eeprom(struct lan78xx_net *dev, u32 offset, u32 val; u32 saved; int i, ret; - int retval; /* depends on chip, some EEPROM pins are muxed with LED function. * disable & restore LED function to access EEPROM. */ ret = lan78xx_read_reg(dev, HW_CFG, &val); + if (ret < 0) + return ret; + saved = val; if (dev->chipid == ID_REV_CHIP_ID_7800_) { val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_); ret = lan78xx_write_reg(dev, HW_CFG, val); + if (ret < 0) + return ret; } - retval = lan78xx_eeprom_confirm_not_busy(dev); - if (retval) - goto exit; + ret = lan78xx_eeprom_confirm_not_busy(dev); + /* Looks like not USB specific error, try to recover */ + if (ret == -ETIMEDOUT) + goto write_raw_eeprom_done; + /* If USB fails, there is nothing to do */ + if (ret < 0) + return ret; /* Issue write/erase enable command */ val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_EWEN_; ret = lan78xx_write_reg(dev, E2P_CMD, val); - if (unlikely(ret < 0)) { - retval = -EIO; - goto exit; - } + if (ret < 0) + return ret; - retval = lan78xx_wait_eeprom(dev); - if (retval < 0) - goto exit; + ret = lan78xx_wait_eeprom(dev); + /* Looks like not USB specific error, try to recover */ + if (ret == -ETIMEDOUT) + goto write_raw_eeprom_done; + /* If USB fails, there is nothing to do */ + if (ret < 0) + return ret; for (i = 0; i < length; i++) { /* Fill data register */ val = data[i]; ret = lan78xx_write_reg(dev, E2P_DATA, val); - if (ret < 0) { - retval = -EIO; - goto exit; - } + if (ret < 0) + return ret; /* Send "write" command */ val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_WRITE_; val |= (offset & E2P_CMD_EPC_ADDR_MASK_); ret = lan78xx_write_reg(dev, E2P_CMD, val); - if (ret < 0) { - retval = -EIO; - goto exit; - } + if (ret < 0) + return ret; - retval = lan78xx_wait_eeprom(dev); - if (retval < 0) - goto exit; + ret = lan78xx_wait_eeprom(dev); + /* Looks like not USB specific error, try to recover */ + if (ret == -ETIMEDOUT) + goto write_raw_eeprom_done; + /* If USB fails, there is nothing to do */ + if (ret < 0) + return ret; offset++; } - retval = 0; -exit: +write_raw_eeprom_done: if (dev->chipid == ID_REV_CHIP_ID_7800_) - ret = lan78xx_write_reg(dev, HW_CFG, saved); + return lan78xx_write_reg(dev, HW_CFG, saved); - return retval; + return 0; } static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { - int i; - u32 buf; unsigned long timeout; + int ret, i; + u32 buf; - lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + if (ret < 0) + return ret; if (buf & OTP_PWR_DN_PWRDN_N_) { /* clear it and wait to be cleared */ - lan78xx_write_reg(dev, OTP_PWR_DN, 0); + ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0); + if (ret < 0) + return ret; timeout = jiffies + HZ; do { usleep_range(1, 10); - lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + if (ret < 0) + return ret; + if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_PWR_DN"); - return -EIO; + return -ETIMEDOUT; } } while (buf & OTP_PWR_DN_PWRDN_N_); } for (i = 0; i < length; i++) { - lan78xx_write_reg(dev, OTP_ADDR1, - ((offset + i) >> 8) & OTP_ADDR1_15_11); - lan78xx_write_reg(dev, OTP_ADDR2, - ((offset + i) & OTP_ADDR2_10_3)); + ret = lan78xx_write_reg(dev, OTP_ADDR1, + ((offset + i) >> 8) & OTP_ADDR1_15_11); + if (ret < 0) + return ret; - lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_); - lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); + ret = lan78xx_write_reg(dev, OTP_ADDR2, + ((offset + i) & OTP_ADDR2_10_3)); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); + if (ret < 0) + return ret; timeout = jiffies + HZ; do { udelay(1); - lan78xx_read_reg(dev, OTP_STATUS, &buf); + ret = lan78xx_read_reg(dev, OTP_STATUS, &buf); + if (ret < 0) + return ret; + if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_STATUS"); - return -EIO; + return -ETIMEDOUT; } } while (buf & OTP_STATUS_BUSY_); - lan78xx_read_reg(dev, OTP_RD_DATA, &buf); + ret = lan78xx_read_reg(dev, OTP_RD_DATA, &buf); + if (ret < 0) + return ret; data[i] = (u8)(buf & 0xFF); } @@ -1086,45 +1263,72 @@ static int lan78xx_write_raw_otp(struct lan78xx_net *dev, u32 offset, int i; u32 buf; unsigned long timeout; + int ret; - lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + if (ret < 0) + return ret; if (buf & OTP_PWR_DN_PWRDN_N_) { /* clear it and wait to be cleared */ - lan78xx_write_reg(dev, OTP_PWR_DN, 0); + ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0); + if (ret < 0) + return ret; timeout = jiffies + HZ; do { udelay(1); - lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + if (ret < 0) + return ret; + if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_PWR_DN completion"); - return -EIO; + return -ETIMEDOUT; } } while (buf & OTP_PWR_DN_PWRDN_N_); } /* set to BYTE program mode */ - lan78xx_write_reg(dev, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_); + ret = lan78xx_write_reg(dev, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_); + if (ret < 0) + return ret; for (i = 0; i < length; i++) { - lan78xx_write_reg(dev, OTP_ADDR1, - ((offset + i) >> 8) & OTP_ADDR1_15_11); - lan78xx_write_reg(dev, OTP_ADDR2, - ((offset + i) & OTP_ADDR2_10_3)); - lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]); - lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_); - lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); + ret = lan78xx_write_reg(dev, OTP_ADDR1, + ((offset + i) >> 8) & OTP_ADDR1_15_11); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, OTP_ADDR2, + ((offset + i) & OTP_ADDR2_10_3)); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); + if (ret < 0) + return ret; timeout = jiffies + HZ; do { udelay(1); - lan78xx_read_reg(dev, OTP_STATUS, &buf); + ret = lan78xx_read_reg(dev, OTP_STATUS, &buf); + if (ret < 0) + return ret; + if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "Timeout on OTP_STATUS completion"); - return -EIO; + return -ETIMEDOUT; } } while (buf & OTP_STATUS_BUSY_); } @@ -1161,7 +1365,7 @@ static int lan78xx_dataport_wait_not_busy(struct lan78xx_net *dev) ret = lan78xx_read_reg(dev, DP_SEL, &dp_sel); if (unlikely(ret < 0)) - return -EIO; + return ret; if (dp_sel & DP_SEL_DPRDY_) return 0; @@ -1171,44 +1375,51 @@ static int lan78xx_dataport_wait_not_busy(struct lan78xx_net *dev) netdev_warn(dev->net, "%s timed out", __func__); - return -EIO; + return -ETIMEDOUT; } static int lan78xx_dataport_write(struct lan78xx_net *dev, u32 ram_select, u32 addr, u32 length, u32 *buf) { struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); - u32 dp_sel; int i, ret; - if (usb_autopm_get_interface(dev->intf) < 0) - return 0; + ret = usb_autopm_get_interface(dev->intf); + if (ret < 0) + return ret; mutex_lock(&pdata->dataport_mutex); ret = lan78xx_dataport_wait_not_busy(dev); if (ret < 0) - goto done; + goto dataport_write; - ret = lan78xx_read_reg(dev, DP_SEL, &dp_sel); - - dp_sel &= ~DP_SEL_RSEL_MASK_; - dp_sel |= ram_select; - ret = lan78xx_write_reg(dev, DP_SEL, dp_sel); + ret = lan78xx_update_reg(dev, DP_SEL, DP_SEL_RSEL_MASK_, ram_select); + if (ret < 0) + goto dataport_write; for (i = 0; i < length; i++) { ret = lan78xx_write_reg(dev, DP_ADDR, addr + i); + if (ret < 0) + goto dataport_write; ret = lan78xx_write_reg(dev, DP_DATA, buf[i]); + if (ret < 0) + goto dataport_write; ret = lan78xx_write_reg(dev, DP_CMD, DP_CMD_WRITE_); + if (ret < 0) + goto dataport_write; ret = lan78xx_dataport_wait_not_busy(dev); if (ret < 0) - goto done; + goto dataport_write; } -done: +dataport_write: + if (ret < 0) + netdev_warn(dev->net, "dataport write failed %pe", ERR_PTR(ret)); + mutex_unlock(&pdata->dataport_mutex); usb_autopm_put_interface(dev->intf); @@ -1244,23 +1455,39 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param) struct lan78xx_priv *pdata = container_of(param, struct lan78xx_priv, set_multicast); struct lan78xx_net *dev = pdata->dev; - int i; + int i, ret; netif_dbg(dev, drv, dev->net, "deferred multicast write 0x%08x\n", pdata->rfe_ctl); - lan78xx_dataport_write(dev, DP_SEL_RSEL_VLAN_DA_, DP_SEL_VHF_VLAN_LEN, - DP_SEL_VHF_HASH_LEN, pdata->mchash_table); + ret = lan78xx_dataport_write(dev, DP_SEL_RSEL_VLAN_DA_, + DP_SEL_VHF_VLAN_LEN, + DP_SEL_VHF_HASH_LEN, pdata->mchash_table); + if (ret < 0) + goto multicast_write_done; for (i = 1; i < NUM_OF_MAF; i++) { - lan78xx_write_reg(dev, MAF_HI(i), 0); - lan78xx_write_reg(dev, MAF_LO(i), - pdata->pfilter_table[i][1]); - lan78xx_write_reg(dev, MAF_HI(i), - pdata->pfilter_table[i][0]); + ret = lan78xx_write_reg(dev, MAF_HI(i), 0); + if (ret < 0) + goto multicast_write_done; + + ret = lan78xx_write_reg(dev, MAF_LO(i), + pdata->pfilter_table[i][1]); + if (ret < 0) + goto multicast_write_done; + + ret = lan78xx_write_reg(dev, MAF_HI(i), + pdata->pfilter_table[i][0]); + if (ret < 0) + goto multicast_write_done; } - lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); + ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); + +multicast_write_done: + if (ret < 0) + netdev_warn(dev->net, "multicast write failed %pe", ERR_PTR(ret)); + return; } static void lan78xx_set_multicast(struct net_device *netdev) @@ -1369,24 +1596,24 @@ static int lan78xx_mac_reset(struct lan78xx_net *dev) u32 val; int ret; - mutex_lock(&dev->phy_mutex); + mutex_lock(&dev->mdiobus_mutex); /* Resetting the device while there is activity on the MDIO * bus can result in the MAC interface locking up and not * completing register access transactions. */ - ret = lan78xx_phy_wait_not_busy(dev); + ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) - goto done; + goto exit_unlock; ret = lan78xx_read_reg(dev, MAC_CR, &val); if (ret < 0) - goto done; + goto exit_unlock; val |= MAC_CR_RST_; ret = lan78xx_write_reg(dev, MAC_CR, val); if (ret < 0) - goto done; + goto exit_unlock; /* Wait for the reset to complete before allowing any further * MAC register accesses otherwise the MAC may lock up. @@ -1394,17 +1621,17 @@ static int lan78xx_mac_reset(struct lan78xx_net *dev) do { ret = lan78xx_read_reg(dev, MAC_CR, &val); if (ret < 0) - goto done; + goto exit_unlock; if (!(val & MAC_CR_RST_)) { ret = 0; - goto done; + goto exit_unlock; } } while (!time_after(jiffies, start_time + HZ)); ret = -ETIMEDOUT; -done: - mutex_unlock(&dev->phy_mutex); +exit_unlock: + mutex_unlock(&dev->mdiobus_mutex); return ret; } @@ -1630,6 +1857,7 @@ static void lan78xx_get_wol(struct net_device *netdev, ret = lan78xx_read_reg(dev, USB_CFG0, &buf); if (unlikely(ret < 0)) { + netdev_warn(dev->net, "failed to get WoL %pe", ERR_PTR(ret)); wol->supported = 0; wol->wolopts = 0; } else { @@ -1661,10 +1889,13 @@ static int lan78xx_set_wol(struct net_device *netdev, pdata->wol = wol->wolopts; - device_set_wakeup_enable(&dev->udev->dev, (bool)wol->wolopts); + ret = device_set_wakeup_enable(&dev->udev->dev, (bool)wol->wolopts); + if (ret < 0) + goto exit_pm_put; - phy_ethtool_set_wol(netdev->phydev, wol); + ret = phy_ethtool_set_wol(netdev->phydev, wol); +exit_pm_put: usb_autopm_put_interface(dev->intf); return ret; @@ -1869,30 +2100,35 @@ exit: static int lan78xx_get_regs_len(struct net_device *netdev) { - if (!netdev->phydev) - return (sizeof(lan78xx_regs)); - else - return (sizeof(lan78xx_regs) + PHY_REG_SIZE); + return sizeof(lan78xx_regs); } static void lan78xx_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *buf) { - u32 *data = buf; - int i, j; struct lan78xx_net *dev = netdev_priv(netdev); + unsigned int data_count = 0; + u32 *data = buf; + int i, ret; /* Read Device/MAC registers */ - for (i = 0; i < ARRAY_SIZE(lan78xx_regs); i++) - lan78xx_read_reg(dev, lan78xx_regs[i], &data[i]); + for (i = 0; i < ARRAY_SIZE(lan78xx_regs); i++) { + ret = lan78xx_read_reg(dev, lan78xx_regs[i], &data[i]); + if (ret < 0) { + netdev_warn(dev->net, + "failed to read register 0x%08x\n", + lan78xx_regs[i]); + goto clean_data; + } - if (!netdev->phydev) - return; + data_count++; + } - /* Read PHY registers */ - for (j = 0; j < 32; i++, j++) - data[i] = phy_read(netdev->phydev, j); + return; + +clean_data: + memset(data, 0, data_count * sizeof(u32)); } static const struct ethtool_ops lan78xx_ethtool_ops = { @@ -1920,13 +2156,19 @@ static const struct ethtool_ops lan78xx_ethtool_ops = { .get_regs = lan78xx_get_regs, }; -static void lan78xx_init_mac_address(struct lan78xx_net *dev) +static int lan78xx_init_mac_address(struct lan78xx_net *dev) { u32 addr_lo, addr_hi; u8 addr[6]; + int ret; - lan78xx_read_reg(dev, RX_ADDRL, &addr_lo); - lan78xx_read_reg(dev, RX_ADDRH, &addr_hi); + ret = lan78xx_read_reg(dev, RX_ADDRL, &addr_lo); + if (ret < 0) + return ret; + + ret = lan78xx_read_reg(dev, RX_ADDRH, &addr_hi); + if (ret < 0) + return ret; addr[0] = addr_lo & 0xFF; addr[1] = (addr_lo >> 8) & 0xFF; @@ -1959,14 +2201,26 @@ static void lan78xx_init_mac_address(struct lan78xx_net *dev) (addr[2] << 16) | (addr[3] << 24); addr_hi = addr[4] | (addr[5] << 8); - lan78xx_write_reg(dev, RX_ADDRL, addr_lo); - lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + if (ret < 0) + return ret; } - lan78xx_write_reg(dev, MAF_LO(0), addr_lo); - lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); + ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); + if (ret < 0) + return ret; eth_hw_addr_set(dev->net, addr); + + return 0; } /* MDIO read and write wrappers for phylib */ @@ -1980,27 +2234,31 @@ static int lan78xx_mdiobus_read(struct mii_bus *bus, int phy_id, int idx) if (ret < 0) return ret; - mutex_lock(&dev->phy_mutex); + mutex_lock(&dev->mdiobus_mutex); /* confirm MII not busy */ - ret = lan78xx_phy_wait_not_busy(dev); + ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) goto done; /* set the address, index & direction (read from PHY) */ addr = mii_access(phy_id, idx, MII_READ); ret = lan78xx_write_reg(dev, MII_ACC, addr); + if (ret < 0) + goto done; - ret = lan78xx_phy_wait_not_busy(dev); + ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) goto done; ret = lan78xx_read_reg(dev, MII_DATA, &val); + if (ret < 0) + goto done; ret = (int)(val & 0xFFFF); done: - mutex_unlock(&dev->phy_mutex); + mutex_unlock(&dev->mdiobus_mutex); usb_autopm_put_interface(dev->intf); return ret; @@ -2017,28 +2275,32 @@ static int lan78xx_mdiobus_write(struct mii_bus *bus, int phy_id, int idx, if (ret < 0) return ret; - mutex_lock(&dev->phy_mutex); + mutex_lock(&dev->mdiobus_mutex); /* confirm MII not busy */ - ret = lan78xx_phy_wait_not_busy(dev); + ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) goto done; val = (u32)regval; ret = lan78xx_write_reg(dev, MII_DATA, val); + if (ret < 0) + goto done; /* set the address, index & direction (write to PHY) */ addr = mii_access(phy_id, idx, MII_WRITE); ret = lan78xx_write_reg(dev, MII_ACC, addr); + if (ret < 0) + goto done; - ret = lan78xx_phy_wait_not_busy(dev); + ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) goto done; done: - mutex_unlock(&dev->phy_mutex); + mutex_unlock(&dev->mdiobus_mutex); usb_autopm_put_interface(dev->intf); - return 0; + return ret; } static int lan78xx_mdio_init(struct lan78xx_net *dev) @@ -2164,13 +2426,22 @@ static void lan78xx_irq_bus_sync_unlock(struct irq_data *irqd) struct lan78xx_net *dev = container_of(data, struct lan78xx_net, domain_data); u32 buf; + int ret; /* call register access here because irq_bus_lock & irq_bus_sync_unlock * are only two callbacks executed in non-atomic contex. */ - lan78xx_read_reg(dev, INT_EP_CTL, &buf); + ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf); + if (ret < 0) + goto irq_bus_sync_unlock; + if (buf != data->irqenable) - lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable); + ret = lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable); + +irq_bus_sync_unlock: + if (ret < 0) + netdev_err(dev->net, "Failed to sync IRQ enable register: %pe\n", + ERR_PTR(ret)); mutex_unlock(&data->irq_lock); } @@ -2195,7 +2466,10 @@ static int lan78xx_setup_irq_domain(struct lan78xx_net *dev) mutex_init(&dev->domain_data.irq_lock); - lan78xx_read_reg(dev, INT_EP_CTL, &buf); + ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf); + if (ret < 0) + return ret; + dev->domain_data.irqenable = buf; dev->domain_data.irqchip = &lan78xx_irqchip; @@ -2234,46 +2508,6 @@ static void lan78xx_remove_irq_domain(struct lan78xx_net *dev) dev->domain_data.irqdomain = NULL; } -static int lan8835_fixup(struct phy_device *phydev) -{ - int buf; - struct lan78xx_net *dev = netdev_priv(phydev->attached_dev); - - /* LED2/PME_N/IRQ_N/RGMII_ID pin to IRQ_N mode */ - buf = phy_read_mmd(phydev, MDIO_MMD_PCS, 0x8010); - buf &= ~0x1800; - buf |= 0x0800; - phy_write_mmd(phydev, MDIO_MMD_PCS, 0x8010, buf); - - /* RGMII MAC TXC Delay Enable */ - lan78xx_write_reg(dev, MAC_RGMII_ID, - MAC_RGMII_ID_TXC_DELAY_EN_); - - /* RGMII TX DLL Tune Adjust */ - lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00); - - dev->interface = PHY_INTERFACE_MODE_RGMII_TXID; - - return 1; -} - -static int ksz9031rnx_fixup(struct phy_device *phydev) -{ - struct lan78xx_net *dev = netdev_priv(phydev->attached_dev); - - /* Micrel9301RNX PHY configuration */ - /* RGMII Control Signal Pad Skew */ - phy_write_mmd(phydev, MDIO_MMD_WIS, 4, 0x0077); - /* RGMII RX Data Pad Skew */ - phy_write_mmd(phydev, MDIO_MMD_WIS, 5, 0x7777); - /* RGMII RX Clock Pad Skew */ - phy_write_mmd(phydev, MDIO_MMD_WIS, 8, 0x1FF); - - dev->interface = PHY_INTERFACE_MODE_RGMII_RXID; - - return 1; -} - static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev) { u32 buf; @@ -2307,22 +2541,11 @@ static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev) netdev_err(dev->net, "no PHY driver found\n"); return NULL; } - dev->interface = PHY_INTERFACE_MODE_RGMII; - /* external PHY fixup for KSZ9031RNX */ - ret = phy_register_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0, - ksz9031rnx_fixup); - if (ret < 0) { - netdev_err(dev->net, "Failed to register fixup for PHY_KSZ9031RNX\n"); - return NULL; - } - /* external PHY fixup for LAN8835 */ - ret = phy_register_fixup_for_uid(PHY_LAN8835, 0xfffffff0, - lan8835_fixup); - if (ret < 0) { - netdev_err(dev->net, "Failed to register fixup for PHY_LAN8835\n"); - return NULL; - } - /* add more external PHY fixup here if needed */ + dev->interface = PHY_INTERFACE_MODE_RGMII_ID; + /* The PHY driver is responsible to configure proper RGMII + * interface delays. Disable RGMII delays on MAC side. + */ + lan78xx_write_reg(dev, MAC_RGMII_ID, 0); phydev->is_internal = false; } @@ -2381,11 +2604,6 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) if (phy_is_pseudo_fixed_link(phydev)) { fixed_phy_unregister(phydev); phy_device_free(phydev); - } else { - phy_unregister_fixup_for_uid(PHY_KSZ9031RNX, - 0xfffffff0); - phy_unregister_fixup_for_uid(PHY_LAN8835, - 0xfffffff0); } } return -EIO; @@ -2437,27 +2655,36 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) static int lan78xx_set_rx_max_frame_length(struct lan78xx_net *dev, int size) { - u32 buf; bool rxenabled; + u32 buf; + int ret; - lan78xx_read_reg(dev, MAC_RX, &buf); + ret = lan78xx_read_reg(dev, MAC_RX, &buf); + if (ret < 0) + return ret; rxenabled = ((buf & MAC_RX_RXEN_) != 0); if (rxenabled) { buf &= ~MAC_RX_RXEN_; - lan78xx_write_reg(dev, MAC_RX, buf); + ret = lan78xx_write_reg(dev, MAC_RX, buf); + if (ret < 0) + return ret; } /* add 4 to size for FCS */ buf &= ~MAC_RX_MAX_SIZE_MASK_; buf |= (((size + 4) << MAC_RX_MAX_SIZE_SHIFT_) & MAC_RX_MAX_SIZE_MASK_); - lan78xx_write_reg(dev, MAC_RX, buf); + ret = lan78xx_write_reg(dev, MAC_RX, buf); + if (ret < 0) + return ret; if (rxenabled) { buf |= MAC_RX_RXEN_; - lan78xx_write_reg(dev, MAC_RX, buf); + ret = lan78xx_write_reg(dev, MAC_RX, buf); + if (ret < 0) + return ret; } return 0; @@ -2523,7 +2750,10 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) return ret; ret = lan78xx_set_rx_max_frame_length(dev, max_frame_len); - if (!ret) + if (ret < 0) + netdev_err(dev->net, "MTU changed to %d from %d failed with %pe\n", + new_mtu, netdev->mtu, ERR_PTR(ret)); + else WRITE_ONCE(netdev->mtu, new_mtu); usb_autopm_put_interface(dev->intf); @@ -2536,6 +2766,7 @@ static int lan78xx_set_mac_addr(struct net_device *netdev, void *p) struct lan78xx_net *dev = netdev_priv(netdev); struct sockaddr *addr = p; u32 addr_lo, addr_hi; + int ret; if (netif_running(netdev)) return -EBUSY; @@ -2552,14 +2783,20 @@ static int lan78xx_set_mac_addr(struct net_device *netdev, void *p) addr_hi = netdev->dev_addr[4] | netdev->dev_addr[5] << 8; - lan78xx_write_reg(dev, RX_ADDRL, addr_lo); - lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + if (ret < 0) + return ret; /* Added to support MAC address changes */ - lan78xx_write_reg(dev, MAF_LO(0), addr_lo); - lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); + ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); + if (ret < 0) + return ret; - return 0; + return lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); } /* Enable or disable Rx checksum offload engine */ @@ -2592,9 +2829,7 @@ static int lan78xx_set_features(struct net_device *netdev, spin_unlock_irqrestore(&pdata->rfe_ctl_lock, flags); - lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); - - return 0; + return lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); } static void lan78xx_deferred_vlan_write(struct work_struct *param) @@ -2645,13 +2880,16 @@ static int lan78xx_vlan_rx_kill_vid(struct net_device *netdev, return 0; } -static void lan78xx_init_ltm(struct lan78xx_net *dev) +static int lan78xx_init_ltm(struct lan78xx_net *dev) { + u32 regs[6] = { 0 }; int ret; u32 buf; - u32 regs[6] = { 0 }; ret = lan78xx_read_reg(dev, USB_CFG1, &buf); + if (ret < 0) + goto init_ltm_failed; + if (buf & USB_CFG1_LTM_ENABLE_) { u8 temp[2]; /* Get values from EEPROM first */ @@ -2662,7 +2900,7 @@ static void lan78xx_init_ltm(struct lan78xx_net *dev) 24, (u8 *)regs); if (ret < 0) - return; + return ret; } } else if (lan78xx_read_otp(dev, 0x3F, 2, temp) == 0) { if (temp[0] == 24) { @@ -2671,17 +2909,40 @@ static void lan78xx_init_ltm(struct lan78xx_net *dev) 24, (u8 *)regs); if (ret < 0) - return; + return ret; } } } - lan78xx_write_reg(dev, LTM_BELT_IDLE0, regs[0]); - lan78xx_write_reg(dev, LTM_BELT_IDLE1, regs[1]); - lan78xx_write_reg(dev, LTM_BELT_ACT0, regs[2]); - lan78xx_write_reg(dev, LTM_BELT_ACT1, regs[3]); - lan78xx_write_reg(dev, LTM_INACTIVE0, regs[4]); - lan78xx_write_reg(dev, LTM_INACTIVE1, regs[5]); + ret = lan78xx_write_reg(dev, LTM_BELT_IDLE0, regs[0]); + if (ret < 0) + goto init_ltm_failed; + + ret = lan78xx_write_reg(dev, LTM_BELT_IDLE1, regs[1]); + if (ret < 0) + goto init_ltm_failed; + + ret = lan78xx_write_reg(dev, LTM_BELT_ACT0, regs[2]); + if (ret < 0) + goto init_ltm_failed; + + ret = lan78xx_write_reg(dev, LTM_BELT_ACT1, regs[3]); + if (ret < 0) + goto init_ltm_failed; + + ret = lan78xx_write_reg(dev, LTM_INACTIVE0, regs[4]); + if (ret < 0) + goto init_ltm_failed; + + ret = lan78xx_write_reg(dev, LTM_INACTIVE1, regs[5]); + if (ret < 0) + goto init_ltm_failed; + + return 0; + +init_ltm_failed: + netdev_err(dev->net, "Failed to init LTM with error %pe\n", ERR_PTR(ret)); + return ret; } static int lan78xx_urb_config_init(struct lan78xx_net *dev) @@ -2722,156 +2983,6 @@ static int lan78xx_urb_config_init(struct lan78xx_net *dev) return result; } -static int lan78xx_start_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enable) -{ - return lan78xx_update_reg(dev, reg, hw_enable, hw_enable); -} - -static int lan78xx_stop_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enabled, - u32 hw_disabled) -{ - unsigned long timeout; - bool stopped = true; - int ret; - u32 buf; - - /* Stop the h/w block (if not already stopped) */ - - ret = lan78xx_read_reg(dev, reg, &buf); - if (ret < 0) - return ret; - - if (buf & hw_enabled) { - buf &= ~hw_enabled; - - ret = lan78xx_write_reg(dev, reg, buf); - if (ret < 0) - return ret; - - stopped = false; - timeout = jiffies + HW_DISABLE_TIMEOUT; - do { - ret = lan78xx_read_reg(dev, reg, &buf); - if (ret < 0) - return ret; - - if (buf & hw_disabled) - stopped = true; - else - msleep(HW_DISABLE_DELAY_MS); - } while (!stopped && !time_after(jiffies, timeout)); - } - - ret = stopped ? 0 : -ETIME; - - return ret; -} - -static int lan78xx_flush_fifo(struct lan78xx_net *dev, u32 reg, u32 fifo_flush) -{ - return lan78xx_update_reg(dev, reg, fifo_flush, fifo_flush); -} - -static int lan78xx_start_tx_path(struct lan78xx_net *dev) -{ - int ret; - - netif_dbg(dev, drv, dev->net, "start tx path"); - - /* Start the MAC transmitter */ - - ret = lan78xx_start_hw(dev, MAC_TX, MAC_TX_TXEN_); - if (ret < 0) - return ret; - - /* Start the Tx FIFO */ - - ret = lan78xx_start_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_); - if (ret < 0) - return ret; - - return 0; -} - -static int lan78xx_stop_tx_path(struct lan78xx_net *dev) -{ - int ret; - - netif_dbg(dev, drv, dev->net, "stop tx path"); - - /* Stop the Tx FIFO */ - - ret = lan78xx_stop_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_, FCT_TX_CTL_DIS_); - if (ret < 0) - return ret; - - /* Stop the MAC transmitter */ - - ret = lan78xx_stop_hw(dev, MAC_TX, MAC_TX_TXEN_, MAC_TX_TXD_); - if (ret < 0) - return ret; - - return 0; -} - -/* The caller must ensure the Tx path is stopped before calling - * lan78xx_flush_tx_fifo(). - */ -static int lan78xx_flush_tx_fifo(struct lan78xx_net *dev) -{ - return lan78xx_flush_fifo(dev, FCT_TX_CTL, FCT_TX_CTL_RST_); -} - -static int lan78xx_start_rx_path(struct lan78xx_net *dev) -{ - int ret; - - netif_dbg(dev, drv, dev->net, "start rx path"); - - /* Start the Rx FIFO */ - - ret = lan78xx_start_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_); - if (ret < 0) - return ret; - - /* Start the MAC receiver*/ - - ret = lan78xx_start_hw(dev, MAC_RX, MAC_RX_RXEN_); - if (ret < 0) - return ret; - - return 0; -} - -static int lan78xx_stop_rx_path(struct lan78xx_net *dev) -{ - int ret; - - netif_dbg(dev, drv, dev->net, "stop rx path"); - - /* Stop the MAC receiver */ - - ret = lan78xx_stop_hw(dev, MAC_RX, MAC_RX_RXEN_, MAC_RX_RXD_); - if (ret < 0) - return ret; - - /* Stop the Rx FIFO */ - - ret = lan78xx_stop_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_, FCT_RX_CTL_DIS_); - if (ret < 0) - return ret; - - return 0; -} - -/* The caller must ensure the Rx path is stopped before calling - * lan78xx_flush_rx_fifo(). - */ -static int lan78xx_flush_rx_fifo(struct lan78xx_net *dev) -{ - return lan78xx_flush_fifo(dev, FCT_RX_CTL, FCT_RX_CTL_RST_); -} - static int lan78xx_reset(struct lan78xx_net *dev) { struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); @@ -2905,7 +3016,9 @@ static int lan78xx_reset(struct lan78xx_net *dev) } } while (buf & HW_CFG_LRST_); - lan78xx_init_mac_address(dev); + ret = lan78xx_init_mac_address(dev); + if (ret < 0) + return ret; /* save DEVID for later usage */ ret = lan78xx_read_reg(dev, ID_REV, &buf); @@ -2927,7 +3040,9 @@ static int lan78xx_reset(struct lan78xx_net *dev) return ret; /* Init LTM */ - lan78xx_init_ltm(dev); + ret = lan78xx_init_ltm(dev); + if (ret < 0) + return ret; ret = lan78xx_write_reg(dev, BURST_CAP, dev->burst_cap); if (ret < 0) @@ -4242,9 +4357,6 @@ static void lan78xx_disconnect(struct usb_interface *intf) phydev = net->phydev; - phy_unregister_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0); - phy_unregister_fixup_for_uid(PHY_LAN8835, 0xfffffff0); - phy_disconnect(net->phydev); if (phy_is_pseudo_fixed_link(phydev)) { @@ -4349,7 +4461,7 @@ static int lan78xx_probe(struct usb_interface *intf, skb_queue_head_init(&dev->rxq_done); skb_queue_head_init(&dev->txq_pend); skb_queue_head_init(&dev->rxq_overflow); - mutex_init(&dev->phy_mutex); + mutex_init(&dev->mdiobus_mutex); mutex_init(&dev->dev_mutex); ret = lan78xx_urb_config_init(dev); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 9fe7f704a2f7..e9208a8d2bfa 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1429,6 +1429,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x030e, 4)}, /* Quectel EM05GV2 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0316, 3)}, /* Quectel RG255C */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0112, 0)}, /* Fibocom FG132 */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 01a3b2417a54..ddff6f19ff98 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -71,6 +71,14 @@ #define MSR_SPEED (1<<3) #define MSR_LINK (1<<2) +/* USB endpoints */ +enum rtl8150_usb_ep { + RTL8150_USB_EP_CONTROL = 0, + RTL8150_USB_EP_BULK_IN = 1, + RTL8150_USB_EP_BULK_OUT = 2, + RTL8150_USB_EP_INT_IN = 3, +}; + /* Interrupt pipe data */ #define INT_TSR 0x00 #define INT_RSR 0x01 @@ -867,6 +875,13 @@ static int rtl8150_probe(struct usb_interface *intf, struct usb_device *udev = interface_to_usbdev(intf); rtl8150_t *dev; struct net_device *netdev; + static const u8 bulk_ep_addr[] = { + RTL8150_USB_EP_BULK_IN | USB_DIR_IN, + RTL8150_USB_EP_BULK_OUT | USB_DIR_OUT, + 0}; + static const u8 int_ep_addr[] = { + RTL8150_USB_EP_INT_IN | USB_DIR_IN, + 0}; netdev = alloc_etherdev(sizeof(rtl8150_t)); if (!netdev) @@ -880,6 +895,13 @@ static int rtl8150_probe(struct usb_interface *intf, return -ENOMEM; } + /* Verify that all required endpoints are present */ + if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) || + !usb_check_int_endpoints(intf, int_ep_addr)) { + dev_err(&intf->dev, "couldn't find required endpoints\n"); + goto out; + } + tasklet_setup(&dev->tl, rx_fixup); spin_lock_init(&dev->rx_pool_lock); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 07ebb800edf1..01251868a9c2 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -634,7 +634,7 @@ static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq, break; case XDP_TX: orig_frame = *frame; - xdp->rxq->mem = frame->mem; + xdp->rxq->mem.type = frame->mem_type; if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) { trace_xdp_exception(rq->dev, xdp_prog, act); frame = &orig_frame; @@ -646,7 +646,7 @@ static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq, goto xdp_xmit; case XDP_REDIRECT: orig_frame = *frame; - xdp->rxq->mem = frame->mem; + xdp->rxq->mem.type = frame->mem_type; if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) { frame = &orig_frame; stats->rx_drops++; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 67d25f4f94ef..ca81b212a246 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -122,16 +122,6 @@ struct net_vrf { int ifindex; }; -static void vrf_rx_stats(struct net_device *dev, int len) -{ - struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); - - u64_stats_update_begin(&dstats->syncp); - u64_stats_inc(&dstats->rx_packets); - u64_stats_add(&dstats->rx_bytes, len); - u64_stats_update_end(&dstats->syncp); -} - static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb) { vrf_dev->stats.tx_errors++; @@ -369,7 +359,7 @@ static bool qdisc_tx_is_default(const struct net_device *dev) static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, struct dst_entry *dst) { - int len = skb->len; + unsigned int len = skb->len; skb_orphan(skb); @@ -382,15 +372,10 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, skb->protocol = eth_type_trans(skb, dev); - if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { - vrf_rx_stats(dev, len); - } else { - struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); - - u64_stats_update_begin(&dstats->syncp); - u64_stats_inc(&dstats->rx_drops); - u64_stats_update_end(&dstats->syncp); - } + if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) + dev_dstats_rx_add(dev, len); + else + dev_dstats_rx_dropped(dev); return NETDEV_TX_OK; } @@ -578,20 +563,14 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { - struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + unsigned int len = skb->len; + netdev_tx_t ret; - int len = skb->len; - netdev_tx_t ret = is_ip_tx_frame(skb, dev); - - u64_stats_update_begin(&dstats->syncp); - if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { - - u64_stats_inc(&dstats->tx_packets); - u64_stats_add(&dstats->tx_bytes, len); - } else { - u64_stats_inc(&dstats->tx_drops); - } - u64_stats_update_end(&dstats->syncp); + ret = is_ip_tx_frame(skb, dev); + if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) + dev_dstats_tx_add(dev, len); + else + dev_dstats_tx_dropped(dev); return ret; } @@ -1364,7 +1343,7 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, if (!is_ndisc) { struct net_device *orig_dev = skb->dev; - vrf_rx_stats(vrf_dev, skb->len); + dev_dstats_rx_add(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; @@ -1420,7 +1399,7 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, goto out; } - vrf_rx_stats(vrf_dev, skb->len); + dev_dstats_rx_add(vrf_dev, skb->len); if (!list_empty(&vrf_dev->ptype_all)) { int err; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 9ea63059d52d..05c10acb2a57 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -622,9 +622,9 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, return 1; } -static bool vxlan_parse_gpe_proto(struct vxlanhdr *hdr, __be16 *protocol) +static bool vxlan_parse_gpe_proto(const struct vxlanhdr *hdr, __be16 *protocol) { - struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)hdr; + const struct vxlanhdr_gpe *gpe = (const struct vxlanhdr_gpe *)hdr; /* Need to have Next Protocol set for interfaces in GPE mode. */ if (!gpe->np_applied) @@ -1352,6 +1352,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { + struct ndo_fdb_dump_context *ctx = (void *)cb->ctx; struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; int err = 0; @@ -1364,7 +1365,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct vxlan_rdst *rd; if (rcu_access_pointer(f->nh)) { - if (*idx < cb->args[2]) + if (*idx < ctx->fdb_idx) goto skip_nh; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, @@ -1381,7 +1382,7 @@ skip_nh: } list_for_each_entry_rcu(rd, &f->remotes, list) { - if (*idx < cb->args[2]) + if (*idx < ctx->fdb_idx) goto skip; err = vxlan_fdb_info(skb, vxlan, f, @@ -1554,18 +1555,17 @@ static void vxlan_sock_release(struct vxlan_dev *vxlan) #endif } -static enum skb_drop_reason vxlan_remcsum(struct vxlanhdr *unparsed, - struct sk_buff *skb, - u32 vxflags) +static enum skb_drop_reason vxlan_remcsum(struct sk_buff *skb, u32 vxflags) { + const struct vxlanhdr *vh = vxlan_hdr(skb); enum skb_drop_reason reason; size_t start, offset; - if (!(unparsed->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload) - goto out; + if (!(vh->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload) + return SKB_NOT_DROPPED_YET; - start = vxlan_rco_start(unparsed->vx_vni); - offset = start + vxlan_rco_offset(unparsed->vx_vni); + start = vxlan_rco_start(vh->vx_vni); + offset = start + vxlan_rco_offset(vh->vx_vni); reason = pskb_may_pull_reason(skb, offset + sizeof(u16)); if (reason) @@ -1573,22 +1573,20 @@ static enum skb_drop_reason vxlan_remcsum(struct vxlanhdr *unparsed, skb_remcsum_process(skb, (void *)(vxlan_hdr(skb) + 1), start, offset, !!(vxflags & VXLAN_F_REMCSUM_NOPARTIAL)); -out: - unparsed->vx_flags &= ~VXLAN_HF_RCO; - unparsed->vx_vni &= VXLAN_VNI_MASK; - return SKB_NOT_DROPPED_YET; } -static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed, - struct sk_buff *skb, u32 vxflags, +static void vxlan_parse_gbp_hdr(struct sk_buff *skb, u32 vxflags, struct vxlan_metadata *md) { - struct vxlanhdr_gbp *gbp = (struct vxlanhdr_gbp *)unparsed; + const struct vxlanhdr *vh = vxlan_hdr(skb); + const struct vxlanhdr_gbp *gbp; struct metadata_dst *tun_dst; - if (!(unparsed->vx_flags & VXLAN_HF_GBP)) - goto out; + gbp = (const struct vxlanhdr_gbp *)vh; + + if (!(vh->vx_flags & VXLAN_HF_GBP)) + return; md->gbp = ntohs(gbp->policy_id); @@ -1607,8 +1605,6 @@ static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed, /* In flow-based mode, GBP is carried in dst_metadata */ if (!(vxflags & VXLAN_F_COLLECT_METADATA)) skb->mark = md->gbp; -out: - unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS; } static enum skb_drop_reason vxlan_set_mac(struct vxlan_dev *vxlan, @@ -1672,9 +1668,9 @@ static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph, static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) { struct vxlan_vni_node *vninode = NULL; + const struct vxlanhdr *vh; struct vxlan_dev *vxlan; struct vxlan_sock *vs; - struct vxlanhdr unparsed; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 protocol = htons(ETH_P_TEB); @@ -1689,24 +1685,21 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) if (reason) goto drop; - unparsed = *vxlan_hdr(skb); + vh = vxlan_hdr(skb); /* VNI flag always required to be set */ - if (!(unparsed.vx_flags & VXLAN_HF_VNI)) { + if (!(vh->vx_flags & VXLAN_HF_VNI)) { netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n", - ntohl(vxlan_hdr(skb)->vx_flags), - ntohl(vxlan_hdr(skb)->vx_vni)); + ntohl(vh->vx_flags), ntohl(vh->vx_vni)); reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; /* Return non vxlan pkt */ goto drop; } - unparsed.vx_flags &= ~VXLAN_HF_VNI; - unparsed.vx_vni &= ~VXLAN_VNI_MASK; vs = rcu_dereference_sk_user_data(sk); if (!vs) goto drop; - vni = vxlan_vni(vxlan_hdr(skb)->vx_vni); + vni = vxlan_vni(vh->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, &vninode); if (!vxlan) { @@ -1714,13 +1707,27 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) goto drop; } - /* For backwards compatibility, only allow reserved fields to be - * used by VXLAN extensions if explicitly requested. - */ - if (vs->flags & VXLAN_F_GPE) { - if (!vxlan_parse_gpe_proto(&unparsed, &protocol)) + if (vh->vx_flags & vxlan->cfg.reserved_bits.vx_flags || + vh->vx_vni & vxlan->cfg.reserved_bits.vx_vni) { + /* If the header uses bits besides those enabled by the + * netdevice configuration, treat this as a malformed packet. + * This behavior diverges from VXLAN RFC (RFC7348) which + * stipulates that bits in reserved in reserved fields are to be + * ignored. The approach here maintains compatibility with + * previous stack code, and also is more robust and provides a + * little more security in adding extensions to VXLAN. + */ + reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; + DEV_STATS_INC(vxlan->dev, rx_frame_errors); + DEV_STATS_INC(vxlan->dev, rx_errors); + vxlan_vnifilter_count(vxlan, vni, vninode, + VXLAN_VNI_STATS_RX_ERRORS, 0); + goto drop; + } + + if (vxlan->cfg.flags & VXLAN_F_GPE) { + if (!vxlan_parse_gpe_proto(vh, &protocol)) goto drop; - unparsed.vx_flags &= ~VXLAN_GPE_USED_BITS; raw_proto = true; } @@ -1730,8 +1737,8 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) goto drop; } - if (vs->flags & VXLAN_F_REMCSUM_RX) { - reason = vxlan_remcsum(&unparsed, skb, vs->flags); + if (vxlan->cfg.flags & VXLAN_F_REMCSUM_RX) { + reason = vxlan_remcsum(skb, vxlan->cfg.flags); if (unlikely(reason)) goto drop; } @@ -1756,25 +1763,12 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) memset(md, 0, sizeof(*md)); } - if (vs->flags & VXLAN_F_GBP) - vxlan_parse_gbp_hdr(&unparsed, skb, vs->flags, md); + if (vxlan->cfg.flags & VXLAN_F_GBP) + vxlan_parse_gbp_hdr(skb, vxlan->cfg.flags, md); /* Note that GBP and GPE can never be active together. This is * ensured in vxlan_dev_configure. */ - if (unparsed.vx_flags || unparsed.vx_vni) { - /* If there are any unprocessed flags remaining treat - * this as a malformed packet. This behavior diverges from - * VXLAN RFC (RFC7348) which stipulates that bits in reserved - * in reserved fields are to be ignored. The approach here - * maintains compatibility with previous stack code, and also - * is more robust and provides a little more security in - * adding extensions to VXLAN. - */ - reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; - goto drop; - } - if (!raw_proto) { reason = vxlan_set_mac(vxlan, vs, skb, vni); if (reason) @@ -1818,14 +1812,14 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) if (unlikely(!(vxlan->dev->flags & IFF_UP))) { rcu_read_unlock(); - dev_core_stats_rx_dropped_inc(vxlan->dev); + dev_dstats_rx_dropped(vxlan->dev); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_DROPS, 0); reason = SKB_DROP_REASON_DEV_READY; goto drop; } - dev_sw_netstats_rx_add(vxlan->dev, skb->len); + dev_dstats_rx_add(vxlan->dev, skb->len); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX, skb->len); gro_cells_receive(&vxlan->gro_cells, skb); @@ -1880,7 +1874,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) goto out; if (!pskb_may_pull(skb, arp_hdr_len(dev))) { - dev_core_stats_tx_dropped_inc(dev); + dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); goto out; @@ -1938,7 +1932,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) reply->pkt_type = PACKET_HOST; if (netif_rx(reply) == NET_RX_DROP) { - dev_core_stats_rx_dropped_inc(dev); + dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } @@ -2097,7 +2091,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) goto out; if (netif_rx(reply) == NET_RX_DROP) { - dev_core_stats_rx_dropped_inc(dev); + dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } @@ -2271,8 +2265,8 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, { union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; + unsigned int len = skb->len; struct net_device *dev; - int len = skb->len; skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; @@ -2299,16 +2293,16 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop) vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); - dev_sw_netstats_tx_add(src_vxlan->dev, 1, len); + dev_dstats_tx_add(src_vxlan->dev, len); vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len); if (__netif_rx(skb) == NET_RX_SUCCESS) { - dev_sw_netstats_rx_add(dst_vxlan->dev, len); + dev_dstats_rx_add(dst_vxlan->dev, len); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, len); } else { drop: - dev_core_stats_rx_dropped_inc(dev); + dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } @@ -2621,7 +2615,7 @@ out_unlock: return; drop: - dev_core_stats_tx_dropped_inc(dev); + dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, reason); return; @@ -2666,7 +2660,7 @@ static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, return; drop: - dev_core_stats_tx_dropped_inc(dev); + dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); @@ -2704,7 +2698,7 @@ static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, return NETDEV_TX_OK; drop: - dev_core_stats_tx_dropped_inc(dev); + dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); @@ -2801,10 +2795,10 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) !is_multicast_ether_addr(eth->h_dest)) vxlan_fdb_miss(vxlan, eth->h_dest); - dev_core_stats_tx_dropped_inc(dev); + dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); - kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE); + kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); return NETDEV_TX_OK; } } @@ -2827,7 +2821,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) if (fdst) vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); else - kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE); + kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); } return NETDEV_TX_OK; @@ -3371,7 +3365,7 @@ static void vxlan_setup(struct net_device *dev) dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_MAX_MTU; - dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; INIT_LIST_HEAD(&vxlan->next); timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE); @@ -3435,6 +3429,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), + [IFLA_VXLAN_RESERVED_BITS] = NLA_POLICY_EXACT_LEN(sizeof(struct vxlanhdr)), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], @@ -4070,6 +4065,10 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], struct net_device *dev, struct vxlan_config *conf, bool changelink, struct netlink_ext_ack *extack) { + struct vxlanhdr used_bits = { + .vx_flags = VXLAN_HF_VNI, + .vx_vni = VXLAN_VNI_MASK, + }; struct vxlan_dev *vxlan = netdev_priv(dev); int err = 0; @@ -4296,6 +4295,8 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], extack); if (err) return err; + used_bits.vx_flags |= VXLAN_HF_RCO; + used_bits.vx_vni |= ~VXLAN_VNI_MASK; } if (data[IFLA_VXLAN_GBP]) { @@ -4303,6 +4304,7 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], VXLAN_F_GBP, changelink, false, extack); if (err) return err; + used_bits.vx_flags |= VXLAN_GBP_USED_BITS; } if (data[IFLA_VXLAN_GPE]) { @@ -4311,6 +4313,46 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], extack); if (err) return err; + + used_bits.vx_flags |= VXLAN_GPE_USED_BITS; + } + + if (data[IFLA_VXLAN_RESERVED_BITS]) { + struct vxlanhdr reserved_bits; + + if (changelink) { + NL_SET_ERR_MSG_ATTR(extack, + data[IFLA_VXLAN_RESERVED_BITS], + "Cannot change reserved_bits"); + return -EOPNOTSUPP; + } + + nla_memcpy(&reserved_bits, data[IFLA_VXLAN_RESERVED_BITS], + sizeof(reserved_bits)); + if (used_bits.vx_flags & reserved_bits.vx_flags || + used_bits.vx_vni & reserved_bits.vx_vni) { + __be64 ub_be64, rb_be64; + + memcpy(&ub_be64, &used_bits, sizeof(ub_be64)); + memcpy(&rb_be64, &reserved_bits, sizeof(rb_be64)); + + NL_SET_ERR_MSG_ATTR_FMT(extack, + data[IFLA_VXLAN_RESERVED_BITS], + "Used bits %#018llx cannot overlap reserved bits %#018llx", + be64_to_cpu(ub_be64), + be64_to_cpu(rb_be64)); + return -EINVAL; + } + + conf->reserved_bits = reserved_bits; + } else { + /* For backwards compatibility, only allow reserved fields to be + * used by VXLAN extensions if explicitly requested. + */ + conf->reserved_bits = (struct vxlanhdr) { + .vx_flags = ~used_bits.vx_flags, + .vx_vni = ~used_bits.vx_vni, + }; } if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) { @@ -4497,6 +4539,8 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(0) + /* IFLA_VXLAN_GPE */ nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ + /* IFLA_VXLAN_RESERVED_BITS */ + nla_total_size(sizeof(struct vxlanhdr)) + 0; } @@ -4599,6 +4643,11 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) !!(vxlan->cfg.flags & VXLAN_F_VNIFILTER))) goto nla_put_failure; + if (nla_put(skb, IFLA_VXLAN_RESERVED_BITS, + sizeof(vxlan->cfg.reserved_bits), + &vxlan->cfg.reserved_bits)) + goto nla_put_failure; + return 0; nla_put_failure: diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c index 8735891ee128..816ab1aa0526 100644 --- a/drivers/net/vxlan/vxlan_mdb.c +++ b/drivers/net/vxlan/vxlan_mdb.c @@ -1712,7 +1712,7 @@ netdev_tx_t vxlan_mdb_xmit(struct vxlan_dev *vxlan, vxlan_xmit_one(skb, vxlan->dev, src_vni, rcu_dereference(fremote->rd), false); else - kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE); + kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); return NETDEV_TX_OK; } diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index d2023e7131bd..6e6e9f05509a 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -411,6 +411,11 @@ static int vxlan_vnifilter_dump(struct sk_buff *skb, struct netlink_callback *cb struct tunnel_msg *tmsg; struct net_device *dev; + if (cb->nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct tunnel_msg))) { + NL_SET_ERR_MSG(cb->extack, "Invalid msg length"); + return -EINVAL; + } + tmsg = nlmsg_data(cb->nlh); if (tmsg->flags & ~TUNNEL_MSG_VALID_USER_FLAGS) { diff --git a/drivers/net/wan/framer/framer-core.c b/drivers/net/wan/framer/framer-core.c index f547c22e26ac..58f5143359df 100644 --- a/drivers/net/wan/framer/framer-core.c +++ b/drivers/net/wan/framer/framer-core.c @@ -732,8 +732,8 @@ EXPORT_SYMBOL_GPL(devm_framer_create); /** * framer_provider_simple_of_xlate() - returns the framer instance from framer provider - * @dev: the framer provider device - * @args: of_phandle_args (not used here) + * @dev: the framer provider device (not used here) + * @args: of_phandle_args * * Intended to be used by framer provider for the common case where #framer-cells is * 0. For other cases where #framer-cells is greater than '0', the framer provider @@ -743,21 +743,14 @@ EXPORT_SYMBOL_GPL(devm_framer_create); struct framer *framer_provider_simple_of_xlate(struct device *dev, const struct of_phandle_args *args) { - struct class_dev_iter iter; - struct framer *framer; + struct device *target_dev; - class_dev_iter_init(&iter, &framer_class, NULL, NULL); - while ((dev = class_dev_iter_next(&iter))) { - framer = dev_to_framer(dev); - if (args->np != framer->dev.of_node) - continue; + target_dev = class_find_device_by_of_node(&framer_class, args->np); + if (!target_dev) + return ERR_PTR(-ENODEV); - class_dev_iter_exit(&iter); - return framer; - } - - class_dev_iter_exit(&iter); - return ERR_PTR(-ENODEV); + put_device(target_dev); + return dev_to_framer(target_dev); } EXPORT_SYMBOL_GPL(framer_provider_simple_of_xlate); diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index be67382c00f6..c576bbba52bf 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -123,6 +123,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .tx_ring_size = DP_TCL_DATA_RING_SIZE, .smp2p_wow_exit = false, .support_dual_stations = false, + .pdev_suspend = false, }, { .hw_rev = ATH11K_HW_IPQ6018_HW10, @@ -207,6 +208,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .smp2p_wow_exit = false, .support_fw_mac_sequence = false, .support_dual_stations = false, + .pdev_suspend = false, }, { .name = "qca6390 hw2.0", @@ -296,6 +298,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .smp2p_wow_exit = false, .support_fw_mac_sequence = true, .support_dual_stations = true, + .pdev_suspend = false, }, { .name = "qcn9074 hw1.0", @@ -379,6 +382,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .smp2p_wow_exit = false, .support_fw_mac_sequence = false, .support_dual_stations = false, + .pdev_suspend = false, }, { .name = "wcn6855 hw2.0", @@ -468,6 +472,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .smp2p_wow_exit = false, .support_fw_mac_sequence = true, .support_dual_stations = true, + .pdev_suspend = false, }, { .name = "wcn6855 hw2.1", @@ -555,6 +560,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .smp2p_wow_exit = false, .support_fw_mac_sequence = true, .support_dual_stations = true, + .pdev_suspend = false, }, { .name = "wcn6750 hw1.0", @@ -637,6 +643,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .smp2p_wow_exit = true, .support_fw_mac_sequence = true, .support_dual_stations = false, + .pdev_suspend = true, }, { .hw_rev = ATH11K_HW_IPQ5018_HW10, @@ -719,6 +726,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .smp2p_wow_exit = false, .support_fw_mac_sequence = false, .support_dual_stations = false, + .pdev_suspend = false, }, { .name = "qca2066 hw2.1", @@ -809,6 +817,94 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .support_fw_mac_sequence = true, .support_dual_stations = true, }, + { + .name = "qca6698aq hw2.1", + .hw_rev = ATH11K_HW_QCA6698AQ_HW21, + .fw = { + .dir = "QCA6698AQ/hw2.1", + .board_size = 256 * 1024, + .cal_offset = 128 * 1024, + }, + .max_radios = 3, + .bdf_addr = 0x4B0C0000, + .hw_ops = &wcn6855_ops, + .ring_mask = &ath11k_hw_ring_mask_qca6390, + .internal_sleep_clock = true, + .regs = &wcn6855_regs, + .qmi_service_ins_id = ATH11K_QMI_WLFW_SERVICE_INS_ID_V01_QCA6390, + .host_ce_config = ath11k_host_ce_config_qca6390, + .ce_count = 9, + .target_ce_config = ath11k_target_ce_config_wlan_qca6390, + .target_ce_count = 9, + .svc_to_ce_map = ath11k_target_service_to_ce_map_wlan_qca6390, + .svc_to_ce_map_len = 14, + .single_pdev_only = true, + .rxdma1_enable = false, + .num_rxdma_per_pdev = 2, + .rx_mac_buf_ring = true, + .vdev_start_delay = true, + .htt_peer_map_v2 = false, + + .spectral = { + .fft_sz = 0, + .fft_pad_sz = 0, + .summary_pad_sz = 0, + .fft_hdr_len = 0, + .max_fft_bins = 0, + .fragment_160mhz = false, + }, + + .interface_modes = BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_AP) | + BIT(NL80211_IFTYPE_P2P_DEVICE) | + BIT(NL80211_IFTYPE_P2P_CLIENT) | + BIT(NL80211_IFTYPE_P2P_GO), + .supports_monitor = false, + .supports_shadow_regs = true, + .idle_ps = true, + .supports_sta_ps = true, + .coldboot_cal_mm = false, + .coldboot_cal_ftm = false, + .cbcal_restart_fw = false, + .fw_mem_mode = 0, + .num_vdevs = 2 + 1, + .num_peers = 512, + .supports_suspend = true, + .hal_desc_sz = sizeof(struct hal_rx_desc_wcn6855), + .supports_regdb = true, + .fix_l1ss = false, + .credit_flow = true, + .max_tx_ring = DP_TCL_NUM_RING_MAX_QCA6390, + .hal_params = &ath11k_hw_hal_params_qca6390, + .supports_dynamic_smps_6ghz = false, + .alloc_cacheable_memory = false, + .supports_rssi_stats = true, + .fw_wmi_diag_event = true, + .current_cc_support = true, + .dbr_debug_support = false, + .global_reset = true, + .bios_sar_capa = &ath11k_hw_sar_capa_wcn6855, + .m3_fw_support = true, + .fixed_bdf_addr = false, + .fixed_mem_region = false, + .static_window_map = false, + .hybrid_bus_type = false, + .fixed_fw_mem = false, + .support_off_channel_tx = true, + .supports_multi_bssid = true, + + .sram_dump = { + .start = 0x01400000, + .end = 0x0177ffff, + }, + + .tcl_ring_retry = true, + .tx_ring_size = DP_TCL_DATA_RING_SIZE, + .smp2p_wow_exit = false, + .support_fw_mac_sequence = true, + .support_dual_stations = true, + .pdev_suspend = false, + }, }; static inline struct ath11k_pdev *ath11k_core_get_single_pdev(struct ath11k_base *ab) @@ -1669,11 +1765,47 @@ err_pdev_debug: return ret; } +static void ath11k_core_pdev_suspend_target(struct ath11k_base *ab) +{ + struct ath11k *ar; + struct ath11k_pdev *pdev; + unsigned long time_left; + int ret; + int i; + + if (!ab->hw_params.pdev_suspend) + return; + + for (i = 0; i < ab->num_radios; i++) { + pdev = &ab->pdevs[i]; + ar = pdev->ar; + + reinit_completion(&ab->htc_suspend); + + ret = ath11k_wmi_pdev_suspend(ar, WMI_PDEV_SUSPEND_AND_DISABLE_INTR, + pdev->pdev_id); + if (ret) { + ath11k_warn(ab, "could not suspend target :%d\n", ret); + /* pointless to try other pdevs */ + return; + } + + time_left = wait_for_completion_timeout(&ab->htc_suspend, 3 * HZ); + + if (!time_left) { + ath11k_warn(ab, "suspend timed out - target pause event never came\n"); + /* pointless to try other pdevs */ + return; + } + } +} + static void ath11k_core_pdev_destroy(struct ath11k_base *ab) { ath11k_spectral_deinit(ab); ath11k_thermal_unregister(ab); ath11k_mac_unregister(ab); + ath11k_core_pdev_suspend_target(ab); ath11k_hif_irq_disable(ab); ath11k_dp_pdev_free(ab); ath11k_debugfs_pdev_destroy(ab); diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index 09c37e19a168..a9dc7fe7765a 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -148,6 +148,7 @@ enum ath11k_hw_rev { ATH11K_HW_WCN6750_HW10, ATH11K_HW_IPQ5018_HW10, ATH11K_HW_QCA2066_HW21, + ATH11K_HW_QCA6698AQ_HW21, }; enum ath11k_firmware_mode { @@ -340,7 +341,6 @@ struct ath11k_chan_power_info { * @ap_power_type: type of power (SP/LPI/VLP) * @num_pwr_levels: number of power levels * @reg_max: Array of maximum TX power (dBm) per PSD value - * @ap_constraint_power: AP constraint power (dBm) * @tpe: TPE values processed from TPE IE * @chan_power_info: power info to send to firmware */ @@ -350,7 +350,6 @@ struct ath11k_reg_tpc_power_info { enum wmi_reg_6ghz_ap_type ap_power_type; u8 num_pwr_levels; u8 reg_max[ATH11K_NUM_PWR_LEVELS]; - u8 ap_constraint_power; s8 tpe[ATH11K_NUM_PWR_LEVELS]; struct ath11k_chan_power_info chan_power_info[ATH11K_NUM_PWR_LEVELS]; }; @@ -370,7 +369,6 @@ struct ath11k_vif { struct ath11k *ar; struct ieee80211_vif *vif; - u16 tx_seq_no; struct wmi_wmm_params_all_arg wmm_params; struct list_head list; union { diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c index 57281a135dd7..bf192529e3fe 100644 --- a/drivers/net/wireless/ath/ath11k/debugfs.c +++ b/drivers/net/wireless/ath/ath11k/debugfs.c @@ -178,7 +178,7 @@ static int ath11k_debugfs_fw_stats_request(struct ath11k *ar, * received 'update stats' event, we keep a 3 seconds timeout in case, * fw_stats_done is not marked yet */ - timeout = jiffies + msecs_to_jiffies(3 * 1000); + timeout = jiffies + secs_to_jiffies(3); ath11k_debugfs_fw_stats_reset(ar); diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h index 65d2bc0687c8..f777314db8b3 100644 --- a/drivers/net/wireless/ath/ath11k/dp.h +++ b/drivers/net/wireless/ath/ath11k/dp.h @@ -165,7 +165,6 @@ struct ath11k_mon_data { struct ath11k_pdev_mon_stats rx_mon_stats; /* lock for monitor data */ spinlock_t mon_lock; - struct sk_buff_head rx_status_q; }; struct ath11k_pdev_dp { diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 40088e62572e..029ecf51c9ef 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -3872,6 +3872,7 @@ int ath11k_dp_process_rx_err(struct ath11k_base *ab, struct napi_struct *napi, ath11k_hal_rx_msdu_link_info_get(link_desc_va, &num_msdus, msdu_cookies, &rbm); if (rbm != HAL_RX_BUF_RBM_WBM_IDLE_DESC_LIST && + rbm != HAL_RX_BUF_RBM_SW1_BM && rbm != HAL_RX_BUF_RBM_SW3_BM) { ab->soc_stats.invalid_rbm++; ath11k_warn(ab, "invalid return buffer manager %d\n", rbm); @@ -4690,11 +4691,12 @@ static void ath11k_dp_mon_get_buf_len(struct hal_rx_msdu_desc_info *info, } } -static u32 -ath11k_dp_rx_mon_mpdu_pop(struct ath11k *ar, int mac_id, - void *ring_entry, struct sk_buff **head_msdu, - struct sk_buff **tail_msdu, u32 *npackets, - u32 *ppdu_id) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +u32 ath11k_dp_rx_mon_mpdu_pop(struct ath11k *ar, int mac_id, + void *ring_entry, struct sk_buff **head_msdu, + struct sk_buff **tail_msdu, u32 *npackets, + u32 *ppdu_id) { struct ath11k_pdev_dp *dp = &ar->dp; struct ath11k_mon_data *pmon = (struct ath11k_mon_data *)&dp->mon_data; @@ -5705,8 +5707,6 @@ static int ath11k_dp_rx_pdev_mon_status_attach(struct ath11k *ar) struct ath11k_pdev_dp *dp = &ar->dp; struct ath11k_mon_data *pmon = (struct ath11k_mon_data *)&dp->mon_data; - skb_queue_head_init(&pmon->rx_status_q); - pmon->mon_ppdu_status = DP_PPDU_STATUS_START; memset(&pmon->rx_mon_stats, 0, diff --git a/drivers/net/wireless/ath/ath11k/hal.h b/drivers/net/wireless/ath/ath11k/hal.h index dc8bbe073017..601542410c75 100644 --- a/drivers/net/wireless/ath/ath11k/hal.h +++ b/drivers/net/wireless/ath/ath11k/hal.h @@ -700,7 +700,7 @@ enum hal_rx_buf_return_buf_manager { #define HAL_REO_CMD_FLG_UNBLK_RESOURCE BIT(7) #define HAL_REO_CMD_FLG_UNBLK_CACHE BIT(8) -/* Should be matching with HAL_REO_UPD_RX_QUEUE_INFO0_UPD_* feilds */ +/* Should be matching with HAL_REO_UPD_RX_QUEUE_INFO0_UPD_* fields */ #define HAL_REO_CMD_UPD0_RX_QUEUE_NUM BIT(8) #define HAL_REO_CMD_UPD0_VLD BIT(9) #define HAL_REO_CMD_UPD0_ALDC BIT(10) @@ -725,7 +725,7 @@ enum hal_rx_buf_return_buf_manager { #define HAL_REO_CMD_UPD0_PN_VALID BIT(29) #define HAL_REO_CMD_UPD0_PN BIT(30) -/* Should be matching with HAL_REO_UPD_RX_QUEUE_INFO1_* feilds */ +/* Should be matching with HAL_REO_UPD_RX_QUEUE_INFO1_* fields */ #define HAL_REO_CMD_UPD1_VLD BIT(16) #define HAL_REO_CMD_UPD1_ALDC GENMASK(18, 17) #define HAL_REO_CMD_UPD1_DIS_DUP_DETECTION BIT(19) @@ -741,7 +741,7 @@ enum hal_rx_buf_return_buf_manager { #define HAL_REO_CMD_UPD1_PN_HANDLE_ENABLE BIT(30) #define HAL_REO_CMD_UPD1_IGNORE_AMPDU_FLG BIT(31) -/* Should be matching with HAL_REO_UPD_RX_QUEUE_INFO2_* feilds */ +/* Should be matching with HAL_REO_UPD_RX_QUEUE_INFO2_* fields */ #define HAL_REO_CMD_UPD2_SVLD BIT(10) #define HAL_REO_CMD_UPD2_SSN GENMASK(22, 11) #define HAL_REO_CMD_UPD2_SEQ_2K_ERR BIT(23) diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.c b/drivers/net/wireless/ath/ath11k/hal_rx.c index 8f7dd43dc1bd..753bd93f0212 100644 --- a/drivers/net/wireless/ath/ath11k/hal_rx.c +++ b/drivers/net/wireless/ath/ath11k/hal_rx.c @@ -372,7 +372,8 @@ int ath11k_hal_wbm_desc_parse_err(struct ath11k_base *ab, void *desc, ret_buf_mgr = FIELD_GET(BUFFER_ADDR_INFO1_RET_BUF_MGR, wbm_desc->buf_addr_info.info1); - if (ret_buf_mgr != HAL_RX_BUF_RBM_SW3_BM) { + if (ret_buf_mgr != HAL_RX_BUF_RBM_SW1_BM && + ret_buf_mgr != HAL_RX_BUF_RBM_SW3_BM) { ab->soc_stats.invalid_rbm++; return -EINVAL; } diff --git a/drivers/net/wireless/ath/ath11k/hw.h b/drivers/net/wireless/ath/ath11k/hw.h index 300322535766..52d9f4c13b13 100644 --- a/drivers/net/wireless/ath/ath11k/hw.h +++ b/drivers/net/wireless/ath/ath11k/hw.h @@ -227,6 +227,7 @@ struct ath11k_hw_params { bool smp2p_wow_exit; bool support_fw_mac_sequence; bool support_dual_stations; + bool pdev_suspend; }; struct ath11k_hw_ops { diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index e6acbff06749..1556392f7ad4 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -1697,8 +1697,6 @@ static void ath11k_control_beaconing(struct ath11k_vif *arvif, return; } - arvif->tx_seq_no = 0x1000; - arvif->aid = 0; ether_addr_copy(arvif->bssid, info->bssid); @@ -2230,7 +2228,7 @@ static void ath11k_peer_assoc_h_vht(struct ath11k *ar, __le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map), vht_mcs_mask); /* In IPQ8074 platform, VHT mcs rate 10 and 11 is enabled by default. - * VHT mcs rate 10 and 11 is not suppoerted in 11ac standard. + * VHT mcs rate 10 and 11 is not supported in 11ac standard. * so explicitly disable the VHT MCS rate 10 and 11 in 11ac mode. */ arg->tx_mcs_set &= ~IEEE80211_VHT_MCS_SUPPORT_0_11_MASK; @@ -6952,7 +6950,7 @@ err_vdev_del: /* Recalc txpower for remaining vdev */ ath11k_mac_txpower_recalc(ar); - /* TODO: recal traffic pause state based on the available vdevs */ + /* TODO: recalc traffic pause state based on the available vdevs */ mutex_unlock(&ar->conf_mutex); } @@ -9356,6 +9354,7 @@ static int ath11k_fw_stats_request(struct ath11k *ar, static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id, int *dbm) { struct ath11k *ar = hw->priv; diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index 6974a551883f..6e45f464a429 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -398,6 +398,7 @@ int ath11k_mhi_register(struct ath11k_pci *ab_pci) case ATH11K_HW_WCN6855_HW20: case ATH11K_HW_WCN6855_HW21: case ATH11K_HW_QCA2066_HW21: + case ATH11K_HW_QCA6698AQ_HW21: ath11k_mhi_config = &ath11k_mhi_config_qca6390; break; default: diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c index be9d2c69cc41..b93f04973ad7 100644 --- a/drivers/net/wireless/ath/ath11k/pci.c +++ b/drivers/net/wireless/ath/ath11k/pci.c @@ -846,6 +846,9 @@ static int ath11k_pci_probe(struct pci_dev *pdev, case 0x1019D0E1: ab->hw_rev = ATH11K_HW_QCA2066_HW21; break; + case 0x001e60e1: + ab->hw_rev = ATH11K_HW_QCA6698AQ_HW21; + break; default: ab->hw_rev = ATH11K_HW_WCN6855_HW21; } diff --git a/drivers/net/wireless/ath/ath11k/pcic.c b/drivers/net/wireless/ath/ath11k/pcic.c index debe7c5919ef..3fe77310c71f 100644 --- a/drivers/net/wireless/ath/ath11k/pcic.c +++ b/drivers/net/wireless/ath/ath11k/pcic.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include "core.h" @@ -126,6 +126,17 @@ static const struct ath11k_msi_config ath11k_msi_config[] = { }, .hw_rev = ATH11K_HW_QCA2066_HW21, }, + { + .total_vectors = 32, + .total_users = 4, + .users = (struct ath11k_msi_user[]) { + { .name = "MHI", .num_vectors = 3, .base_vector = 0 }, + { .name = "CE", .num_vectors = 10, .base_vector = 3 }, + { .name = "WAKE", .num_vectors = 1, .base_vector = 13 }, + { .name = "DP", .num_vectors = 18, .base_vector = 14 }, + }, + .hw_rev = ATH11K_HW_QCA6698AQ_HW21, + }, }; int ath11k_pcic_init_msi_config(struct ath11k_base *ab) diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c index 7a22483b35cd..5759fc521316 100644 --- a/drivers/net/wireless/ath/ath11k/qmi.c +++ b/drivers/net/wireless/ath/ath11k/qmi.c @@ -1704,7 +1704,9 @@ static const struct qmi_elem_info qmi_wlfw_fw_init_done_ind_msg_v01_ei[] = { }, }; -static int ath11k_qmi_host_cap_send(struct ath11k_base *ab) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath11k_qmi_host_cap_send(struct ath11k_base *ab) { struct qmi_wlanfw_host_cap_req_msg_v01 req; struct qmi_wlanfw_host_cap_resp_msg_v01 resp; @@ -2570,7 +2572,9 @@ static void ath11k_qmi_m3_free(struct ath11k_base *ab) m3_mem->size = 0; } -static int ath11k_qmi_wlanfw_m3_info_send(struct ath11k_base *ab) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath11k_qmi_wlanfw_m3_info_send(struct ath11k_base *ab) { struct m3_mem_region *m3_mem = &ab->qmi.m3_mem; struct qmi_wlanfw_m3_info_req_msg_v01 req; diff --git a/drivers/net/wireless/ath/ath11k/wow.c b/drivers/net/wireless/ath/ath11k/wow.c index 827085a926b2..b6f08755129f 100644 --- a/drivers/net/wireless/ath/ath11k/wow.c +++ b/drivers/net/wireless/ath/ath11k/wow.c @@ -148,8 +148,10 @@ static int ath11k_wow_cleanup(struct ath11k *ar) * 802.11: |4B|dest mac(6B)| 6B |src mac(6B)| 8B |type(2B)| body... | * +--+------------+----+-----------+---------------+-----------+ */ -static void ath11k_wow_convert_8023_to_80211(struct cfg80211_pkt_pattern *new, - const struct cfg80211_pkt_pattern *old) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +void ath11k_wow_convert_8023_to_80211(struct cfg80211_pkt_pattern *new, + const struct cfg80211_pkt_pattern *old) { u8 hdr_8023_pattern[ETH_HLEN] = {}; u8 hdr_8023_bit_mask[ETH_HLEN] = {}; diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c index c57322221e1d..0606116d6b9c 100644 --- a/drivers/net/wireless/ath/ath12k/core.c +++ b/drivers/net/wireless/ath/ath12k/core.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. */ #include @@ -9,6 +9,7 @@ #include #include #include +#include #include "core.h" #include "dp_tx.h" #include "dp_rx.h" @@ -22,6 +23,11 @@ unsigned int ath12k_debug_mask; module_param_named(debug_mask, ath12k_debug_mask, uint, 0644); MODULE_PARM_DESC(debug_mask, "Debugging mask"); +/* protected with ath12k_hw_group_mutex */ +static struct list_head ath12k_hw_group_list = LIST_HEAD_INIT(ath12k_hw_group_list); + +static DEFINE_MUTEX(ath12k_hw_group_mutex); + static int ath12k_core_rfkill_config(struct ath12k_base *ab) { struct ath12k *ar; @@ -79,11 +85,17 @@ int ath12k_core_suspend(struct ath12k_base *ab) ar = ab->pdevs[i].ar; if (!ar) continue; + + wiphy_lock(ath12k_ar_to_hw(ar)->wiphy); + ret = ath12k_mac_wait_tx_complete(ar); if (ret) { + wiphy_unlock(ath12k_ar_to_hw(ar)->wiphy); ath12k_warn(ab, "failed to wait tx complete: %d\n", ret); return ret; } + + wiphy_unlock(ath12k_ar_to_hw(ar)->wiphy); } /* PM framework skips suspend_late/resume_early callbacks @@ -593,14 +605,17 @@ u32 ath12k_core_get_max_num_tids(struct ath12k_base *ab) static void ath12k_core_stop(struct ath12k_base *ab) { + ath12k_core_stopped(ab); + if (!test_bit(ATH12K_FLAG_CRASH_FLUSH, &ab->dev_flags)) ath12k_qmi_firmware_stop(ab); ath12k_acpi_stop(ab); + ath12k_dp_rx_pdev_reo_cleanup(ab); ath12k_hif_stop(ab); ath12k_wmi_detach(ab); - ath12k_dp_rx_pdev_reo_cleanup(ab); + ath12k_dp_free(ab); /* De-Init of components as needed */ } @@ -702,7 +717,7 @@ err_qmi_deinit: static void ath12k_core_soc_destroy(struct ath12k_base *ab) { - ath12k_dp_free(ab); + ath12k_hif_power_down(ab, false); ath12k_reg_free(ab); ath12k_debugfs_soc_destroy(ab); ath12k_qmi_deinit_service(ab); @@ -712,30 +727,17 @@ static int ath12k_core_pdev_create(struct ath12k_base *ab) { int ret; - ret = ath12k_mac_register(ab); - if (ret) { - ath12k_err(ab, "failed register the radio with mac80211: %d\n", ret); - return ret; - } - ret = ath12k_dp_pdev_alloc(ab); if (ret) { ath12k_err(ab, "failed to attach DP pdev: %d\n", ret); - goto err_mac_unregister; + return ret; } return 0; - -err_mac_unregister: - ath12k_mac_unregister(ab); - - return ret; } static void ath12k_core_pdev_destroy(struct ath12k_base *ab) { - ath12k_mac_unregister(ab); - ath12k_hif_irq_disable(ab); ath12k_dp_pdev_free(ab); } @@ -744,6 +746,8 @@ static int ath12k_core_start(struct ath12k_base *ab, { int ret; + lockdep_assert_held(&ab->core_lock); + ret = ath12k_wmi_attach(ab); if (ret) { ath12k_err(ab, "failed to attach wmi: %d\n", ret); @@ -793,19 +797,12 @@ static int ath12k_core_start(struct ath12k_base *ab, goto err_hif_stop; } - ret = ath12k_mac_allocate(ab); - if (ret) { - ath12k_err(ab, "failed to create new hw device with mac80211 :%d\n", - ret); - goto err_hif_stop; - } - ath12k_dp_cc_config(ab); ret = ath12k_dp_rx_pdev_reo_setup(ab); if (ret) { ath12k_err(ab, "failed to initialize reo destination rings: %d\n", ret); - goto err_mac_destroy; + goto err_hif_stop; } ath12k_dp_hal_rx_desc_init(ab); @@ -844,12 +841,14 @@ static int ath12k_core_start(struct ath12k_base *ab, /* ACPI is optional so continue in case of an error */ ath12k_dbg(ab, ATH12K_DBG_BOOT, "acpi failed: %d\n", ret); + if (!test_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags)) + /* Indicate the core start in the appropriate group */ + ath12k_core_started(ab); + return 0; err_reo_cleanup: ath12k_dp_rx_pdev_reo_cleanup(ab); -err_mac_destroy: - ath12k_mac_destroy(ab); err_hif_stop: ath12k_hif_stop(ab); err_wmi_detach: @@ -857,6 +856,169 @@ err_wmi_detach: return ret; } +static void ath12k_core_device_cleanup(struct ath12k_base *ab) +{ + mutex_lock(&ab->core_lock); + + ath12k_hif_irq_disable(ab); + ath12k_core_pdev_destroy(ab); + + mutex_unlock(&ab->core_lock); +} + +static void ath12k_core_hw_group_stop(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab; + int i; + + lockdep_assert_held(&ag->mutex); + + clear_bit(ATH12K_GROUP_FLAG_REGISTERED, &ag->flags); + + ath12k_mac_unregister(ag); + + for (i = ag->num_devices - 1; i >= 0; i--) { + ab = ag->ab[i]; + if (!ab) + continue; + ath12k_core_device_cleanup(ab); + } + + ath12k_mac_destroy(ag); +} + +static int __ath12k_mac_mlo_ready(struct ath12k *ar) +{ + int ret; + + ret = ath12k_wmi_mlo_ready(ar); + if (ret) { + ath12k_err(ar->ab, "MLO ready failed for pdev %d: %d\n", + ar->pdev_idx, ret); + return ret; + } + + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mlo ready done for pdev %d\n", + ar->pdev_idx); + + return 0; +} + +int ath12k_mac_mlo_ready(struct ath12k_hw_group *ag) +{ + struct ath12k_hw *ah; + struct ath12k *ar; + int ret; + int i, j; + + for (i = 0; i < ag->num_hw; i++) { + ah = ag->ah[i]; + if (!ah) + continue; + + for_each_ar(ah, ar, j) { + ar = &ah->radio[j]; + ret = __ath12k_mac_mlo_ready(ar); + if (ret) + goto out; + } + } + +out: + return ret; +} + +static int ath12k_core_mlo_setup(struct ath12k_hw_group *ag) +{ + int ret, i; + + if (!ag->mlo_capable || ag->num_devices == 1) + return 0; + + ret = ath12k_mac_mlo_setup(ag); + if (ret) + return ret; + + for (i = 0; i < ag->num_devices; i++) + ath12k_dp_partner_cc_init(ag->ab[i]); + + ret = ath12k_mac_mlo_ready(ag); + if (ret) + goto err_mlo_teardown; + + return 0; + +err_mlo_teardown: + ath12k_mac_mlo_teardown(ag); + + return ret; +} + +static int ath12k_core_hw_group_start(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab; + int ret, i; + + lockdep_assert_held(&ag->mutex); + + if (test_bit(ATH12K_GROUP_FLAG_REGISTERED, &ag->flags)) + goto core_pdev_create; + + ret = ath12k_mac_allocate(ag); + if (WARN_ON(ret)) + return ret; + + ret = ath12k_core_mlo_setup(ag); + if (WARN_ON(ret)) + goto err_mac_destroy; + + ret = ath12k_mac_register(ag); + if (WARN_ON(ret)) + goto err_mlo_teardown; + + set_bit(ATH12K_GROUP_FLAG_REGISTERED, &ag->flags); + +core_pdev_create: + for (i = 0; i < ag->num_devices; i++) { + ab = ag->ab[i]; + if (!ab) + continue; + + mutex_lock(&ab->core_lock); + + ret = ath12k_core_pdev_create(ab); + if (ret) { + ath12k_err(ab, "failed to create pdev core %d\n", ret); + mutex_unlock(&ab->core_lock); + goto err; + } + + ath12k_hif_irq_enable(ab); + + ret = ath12k_core_rfkill_config(ab); + if (ret && ret != -EOPNOTSUPP) { + mutex_unlock(&ab->core_lock); + goto err; + } + + mutex_unlock(&ab->core_lock); + } + + return 0; + +err: + ath12k_core_hw_group_stop(ag); + return ret; + +err_mlo_teardown: + ath12k_mac_mlo_teardown(ag); + +err_mac_destroy: + ath12k_mac_destroy(ag); + + return ret; +} + static int ath12k_core_start_firmware(struct ath12k_base *ab, enum ath12k_firmware_mode mode) { @@ -874,9 +1036,37 @@ static int ath12k_core_start_firmware(struct ath12k_base *ab, return ret; } +static inline +bool ath12k_core_hw_group_start_ready(struct ath12k_hw_group *ag) +{ + lockdep_assert_held(&ag->mutex); + + return (ag->num_started == ag->num_devices); +} + +static void ath12k_core_trigger_partner(struct ath12k_base *ab) +{ + struct ath12k_hw_group *ag = ab->ag; + struct ath12k_base *partner_ab; + bool found = false; + int i; + + for (i = 0; i < ag->num_devices; i++) { + partner_ab = ag->ab[i]; + if (!partner_ab) + continue; + + if (found) + ath12k_qmi_trigger_host_cap(partner_ab); + + found = (partner_ab == ab); + } +} + int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab) { - int ret; + struct ath12k_hw_group *ag = ath12k_ab_to_ag(ab); + int ret, i; ret = ath12k_core_start_firmware(ab, ATH12K_FIRMWARE_MODE_NORMAL); if (ret) { @@ -896,41 +1086,52 @@ int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab) goto err_firmware_stop; } + mutex_lock(&ag->mutex); mutex_lock(&ab->core_lock); + ret = ath12k_core_start(ab, ATH12K_FIRMWARE_MODE_NORMAL); if (ret) { ath12k_err(ab, "failed to start core: %d\n", ret); goto err_dp_free; } - ret = ath12k_core_pdev_create(ab); - if (ret) { - ath12k_err(ab, "failed to create pdev core: %d\n", ret); - goto err_core_stop; - } - ath12k_hif_irq_enable(ab); - - ret = ath12k_core_rfkill_config(ab); - if (ret && ret != -EOPNOTSUPP) { - ath12k_err(ab, "failed to config rfkill: %d\n", ret); - goto err_core_pdev_destroy; - } - mutex_unlock(&ab->core_lock); + if (ath12k_core_hw_group_start_ready(ag)) { + ret = ath12k_core_hw_group_start(ag); + if (ret) { + ath12k_warn(ab, "unable to start hw group\n"); + goto err_core_stop; + } + ath12k_dbg(ab, ATH12K_DBG_BOOT, "group %d started\n", ag->id); + } else { + ath12k_core_trigger_partner(ab); + } + + mutex_unlock(&ag->mutex); + return 0; -err_core_pdev_destroy: - ath12k_core_pdev_destroy(ab); err_core_stop: - ath12k_core_stop(ab); - ath12k_mac_destroy(ab); + for (i = ag->num_devices - 1; i >= 0; i--) { + ab = ag->ab[i]; + if (!ab) + continue; + + mutex_lock(&ab->core_lock); + ath12k_core_stop(ab); + mutex_unlock(&ab->core_lock); + } + goto exit; + err_dp_free: ath12k_dp_free(ab); mutex_unlock(&ab->core_lock); err_firmware_stop: ath12k_qmi_firmware_stop(ab); +exit: + mutex_unlock(&ag->mutex); return ret; } @@ -972,6 +1173,7 @@ err_hal_srng_deinit: static void ath12k_rfkill_work(struct work_struct *work) { struct ath12k_base *ab = container_of(work, struct ath12k_base, rfkill_work); + struct ath12k_hw_group *ag = ab->ag; struct ath12k *ar; struct ath12k_hw *ah; struct ieee80211_hw *hw; @@ -982,8 +1184,8 @@ static void ath12k_rfkill_work(struct work_struct *work) rfkill_radio_on = ab->rfkill_radio_on; spin_unlock_bh(&ab->base_lock); - for (i = 0; i < ab->num_hw; i++) { - ah = ab->ah[i]; + for (i = 0; i < ag->num_hw; i++) { + ah = ath12k_ag_to_ah(ag, i); if (!ah) continue; @@ -1023,6 +1225,7 @@ void ath12k_core_halt(struct ath12k *ar) static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab) { + struct ath12k_hw_group *ag = ab->ag; struct ath12k *ar; struct ath12k_hw *ah; int i, j; @@ -1034,8 +1237,8 @@ static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab) if (ab->is_reset) set_bit(ATH12K_FLAG_CRASH_FLUSH, &ab->dev_flags); - for (i = 0; i < ab->num_hw; i++) { - ah = ab->ah[i]; + for (i = 0; i < ag->num_hw; i++) { + ah = ath12k_ag_to_ah(ag, i); if (!ah || ah->state == ATH12K_HW_STATE_OFF) continue; @@ -1069,12 +1272,13 @@ static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab) static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab) { + struct ath12k_hw_group *ag = ab->ag; struct ath12k_hw *ah; struct ath12k *ar; int i, j; - for (i = 0; i < ab->num_hw; i++) { - ah = ab->ah[i]; + for (i = 0; i < ag->num_hw; i++) { + ah = ath12k_ag_to_ah(ag, i); if (!ah || ah->state == ATH12K_HW_STATE_OFF) continue; @@ -1117,6 +1321,7 @@ static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab) static void ath12k_core_restart(struct work_struct *work) { struct ath12k_base *ab = container_of(work, struct ath12k_base, restart_work); + struct ath12k_hw_group *ag = ab->ag; struct ath12k_hw *ah; int ret, i; @@ -1127,8 +1332,16 @@ static void ath12k_core_restart(struct work_struct *work) } if (ab->is_reset) { - for (i = 0; i < ab->num_hw; i++) { - ah = ab->ah[i]; + if (!test_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags)) { + atomic_dec(&ab->reset_count); + complete(&ab->reset_complete); + ab->is_reset = false; + atomic_set(&ab->fail_cont_count, 0); + ath12k_dbg(ab, ATH12K_DBG_BOOT, "reset success\n"); + } + + for (i = 0; i < ag->num_hw; i++) { + ah = ath12k_ag_to_ah(ab->ag, i); ieee80211_restart_hw(ah->hw); } } @@ -1142,7 +1355,7 @@ static void ath12k_core_reset(struct work_struct *work) int reset_count, fail_cont_count; long time_left; - if (!(test_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags))) { + if (!(test_bit(ATH12K_FLAG_QMI_FW_READY_COMPLETE, &ab->dev_flags))) { ath12k_warn(ab, "ignore reset dev flags 0x%lx\n", ab->dev_flags); return; } @@ -1241,38 +1454,430 @@ static void ath12k_core_panic_notifier_unregister(struct ath12k_base *ab) &ab->panic_nb); } +static inline +bool ath12k_core_hw_group_create_ready(struct ath12k_hw_group *ag) +{ + lockdep_assert_held(&ag->mutex); + + return (ag->num_probed == ag->num_devices); +} + +static struct ath12k_hw_group *ath12k_core_hw_group_alloc(struct ath12k_base *ab) +{ + struct ath12k_hw_group *ag; + int count = 0; + + lockdep_assert_held(&ath12k_hw_group_mutex); + + list_for_each_entry(ag, &ath12k_hw_group_list, list) + count++; + + ag = kzalloc(sizeof(*ag), GFP_KERNEL); + if (!ag) + return NULL; + + ag->id = count; + list_add(&ag->list, &ath12k_hw_group_list); + mutex_init(&ag->mutex); + ag->mlo_capable = false; + + return ag; +} + +static void ath12k_core_hw_group_free(struct ath12k_hw_group *ag) +{ + mutex_lock(&ath12k_hw_group_mutex); + + list_del(&ag->list); + kfree(ag); + + mutex_unlock(&ath12k_hw_group_mutex); +} + +static struct ath12k_hw_group *ath12k_core_hw_group_find_by_dt(struct ath12k_base *ab) +{ + struct ath12k_hw_group *ag; + int i; + + if (!ab->dev->of_node) + return NULL; + + list_for_each_entry(ag, &ath12k_hw_group_list, list) + for (i = 0; i < ag->num_devices; i++) + if (ag->wsi_node[i] == ab->dev->of_node) + return ag; + + return NULL; +} + +static int ath12k_core_get_wsi_info(struct ath12k_hw_group *ag, + struct ath12k_base *ab) +{ + struct device_node *wsi_dev = ab->dev->of_node, *next_wsi_dev; + struct device_node *tx_endpoint, *next_rx_endpoint; + int device_count = 0; + + next_wsi_dev = wsi_dev; + + if (!next_wsi_dev) + return -ENODEV; + + do { + ag->wsi_node[device_count] = next_wsi_dev; + + tx_endpoint = of_graph_get_endpoint_by_regs(next_wsi_dev, 0, -1); + if (!tx_endpoint) { + of_node_put(next_wsi_dev); + return -ENODEV; + } + + next_rx_endpoint = of_graph_get_remote_endpoint(tx_endpoint); + if (!next_rx_endpoint) { + of_node_put(next_wsi_dev); + of_node_put(tx_endpoint); + return -ENODEV; + } + + of_node_put(tx_endpoint); + of_node_put(next_wsi_dev); + + next_wsi_dev = of_graph_get_port_parent(next_rx_endpoint); + if (!next_wsi_dev) { + of_node_put(next_rx_endpoint); + return -ENODEV; + } + + of_node_put(next_rx_endpoint); + + device_count++; + if (device_count > ATH12K_MAX_SOCS) { + ath12k_warn(ab, "device count in DT %d is more than limit %d\n", + device_count, ATH12K_MAX_SOCS); + of_node_put(next_wsi_dev); + return -EINVAL; + } + } while (wsi_dev != next_wsi_dev); + + of_node_put(next_wsi_dev); + ag->num_devices = device_count; + + return 0; +} + +static int ath12k_core_get_wsi_index(struct ath12k_hw_group *ag, + struct ath12k_base *ab) +{ + int i, wsi_controller_index = -1, node_index = -1; + bool control; + + for (i = 0; i < ag->num_devices; i++) { + control = of_property_read_bool(ag->wsi_node[i], "qcom,wsi-controller"); + if (control) + wsi_controller_index = i; + + if (ag->wsi_node[i] == ab->dev->of_node) + node_index = i; + } + + if (wsi_controller_index == -1) { + ath12k_dbg(ab, ATH12K_DBG_BOOT, "wsi controller is not defined in dt"); + return -EINVAL; + } + + if (node_index == -1) { + ath12k_dbg(ab, ATH12K_DBG_BOOT, "unable to get WSI node index"); + return -EINVAL; + } + + ab->wsi_info.index = (ag->num_devices + node_index - wsi_controller_index) % + ag->num_devices; + + return 0; +} + +static struct ath12k_hw_group *ath12k_core_hw_group_assign(struct ath12k_base *ab) +{ + struct ath12k_wsi_info *wsi = &ab->wsi_info; + struct ath12k_hw_group *ag; + + lockdep_assert_held(&ath12k_hw_group_mutex); + + /* The grouping of multiple devices will be done based on device tree file. + * The platforms that do not have any valid group information would have + * each device to be part of its own invalid group. + * + * We use group id ATH12K_INVALID_GROUP_ID for single device group + * which didn't have dt entry or wrong dt entry, there could be many + * groups with same group id, i.e ATH12K_INVALID_GROUP_ID. So + * default group id of ATH12K_INVALID_GROUP_ID combined with + * num devices in ath12k_hw_group determines if the group is + * multi device or single device group + */ + + ag = ath12k_core_hw_group_find_by_dt(ab); + if (!ag) { + ag = ath12k_core_hw_group_alloc(ab); + if (!ag) { + ath12k_warn(ab, "unable to create new hw group\n"); + return NULL; + } + + if (ath12k_core_get_wsi_info(ag, ab) || + ath12k_core_get_wsi_index(ag, ab)) { + ath12k_dbg(ab, ATH12K_DBG_BOOT, + "unable to get wsi info from dt, grouping single device"); + ag->id = ATH12K_INVALID_GROUP_ID; + ag->num_devices = 1; + memset(ag->wsi_node, 0, sizeof(ag->wsi_node)); + wsi->index = 0; + } + + goto exit; + } else if (test_bit(ATH12K_GROUP_FLAG_UNREGISTER, &ag->flags)) { + ath12k_dbg(ab, ATH12K_DBG_BOOT, "group id %d in unregister state\n", + ag->id); + goto invalid_group; + } else { + if (ath12k_core_get_wsi_index(ag, ab)) + goto invalid_group; + goto exit; + } + +invalid_group: + ag = ath12k_core_hw_group_alloc(ab); + if (!ag) { + ath12k_warn(ab, "unable to create new hw group\n"); + return NULL; + } + + ag->id = ATH12K_INVALID_GROUP_ID; + ag->num_devices = 1; + wsi->index = 0; + + ath12k_dbg(ab, ATH12K_DBG_BOOT, "single device added to hardware group\n"); + +exit: + if (ag->num_probed >= ag->num_devices) { + ath12k_warn(ab, "unable to add new device to group, max limit reached\n"); + goto invalid_group; + } + + ab->device_id = ag->num_probed++; + ag->ab[ab->device_id] = ab; + ab->ag = ag; + + ath12k_dbg(ab, ATH12K_DBG_BOOT, "wsi group-id %d num-devices %d index %d", + ag->id, ag->num_devices, wsi->index); + + return ag; +} + +void ath12k_core_hw_group_unassign(struct ath12k_base *ab) +{ + struct ath12k_hw_group *ag = ath12k_ab_to_ag(ab); + u8 device_id = ab->device_id; + int num_probed; + + if (!ag) + return; + + mutex_lock(&ag->mutex); + + if (WARN_ON(device_id >= ag->num_devices)) { + mutex_unlock(&ag->mutex); + return; + } + + if (WARN_ON(ag->ab[device_id] != ab)) { + mutex_unlock(&ag->mutex); + return; + } + + ag->ab[device_id] = NULL; + ab->ag = NULL; + ab->device_id = ATH12K_INVALID_DEVICE_ID; + + if (ag->num_probed) + ag->num_probed--; + + num_probed = ag->num_probed; + + mutex_unlock(&ag->mutex); + + if (!num_probed) + ath12k_core_hw_group_free(ag); +} + +static void ath12k_core_hw_group_destroy(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab; + int i; + + if (WARN_ON(!ag)) + return; + + for (i = 0; i < ag->num_devices; i++) { + ab = ag->ab[i]; + if (!ab) + continue; + + ath12k_core_soc_destroy(ab); + } +} + +static void ath12k_core_hw_group_cleanup(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab; + int i; + + if (!ag) + return; + + mutex_lock(&ag->mutex); + + if (test_bit(ATH12K_GROUP_FLAG_UNREGISTER, &ag->flags)) { + mutex_unlock(&ag->mutex); + return; + } + + set_bit(ATH12K_GROUP_FLAG_UNREGISTER, &ag->flags); + + ath12k_core_hw_group_stop(ag); + + for (i = 0; i < ag->num_devices; i++) { + ab = ag->ab[i]; + if (!ab) + continue; + + mutex_lock(&ab->core_lock); + ath12k_core_stop(ab); + mutex_unlock(&ab->core_lock); + } + + mutex_unlock(&ag->mutex); +} + +static int ath12k_core_hw_group_create(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab; + int i, ret; + + lockdep_assert_held(&ag->mutex); + + for (i = 0; i < ag->num_devices; i++) { + ab = ag->ab[i]; + if (!ab) + continue; + + mutex_lock(&ab->core_lock); + + ret = ath12k_core_soc_create(ab); + if (ret) { + mutex_unlock(&ab->core_lock); + ath12k_err(ab, "failed to create soc core: %d\n", ret); + return ret; + } + + mutex_unlock(&ab->core_lock); + } + + return 0; +} + +void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab; + int i; + + lockdep_assert_held(&ag->mutex); + + /* If more than one devices are grouped, then inter MLO + * functionality can work still independent of whether internally + * each device supports single_chip_mlo or not. + * Only when there is one device, then it depends whether the + * device can support intra chip MLO or not + */ + if (ag->num_devices > 1) { + ag->mlo_capable = true; + } else { + ab = ag->ab[0]; + ag->mlo_capable = ab->single_chip_mlo_supp; + + /* WCN chipsets does not advertise in firmware features + * hence skip checking + */ + if (ab->hw_params->def_num_link) + return; + } + + if (!ag->mlo_capable) + return; + + for (i = 0; i < ag->num_devices; i++) { + ab = ag->ab[i]; + if (!ab) + continue; + + /* even if 1 device's firmware feature indicates MLO + * unsupported, make MLO unsupported for the whole group + */ + if (!test_bit(ATH12K_FW_FEATURE_MLO, ab->fw.fw_features)) { + ag->mlo_capable = false; + return; + } + } +} + int ath12k_core_init(struct ath12k_base *ab) { + struct ath12k_hw_group *ag; int ret; - ret = ath12k_core_soc_create(ab); - if (ret) { - ath12k_err(ab, "failed to create soc core: %d\n", ret); - return ret; - } - ret = ath12k_core_panic_notifier_register(ab); if (ret) ath12k_warn(ab, "failed to register panic handler: %d\n", ret); + mutex_lock(&ath12k_hw_group_mutex); + + ag = ath12k_core_hw_group_assign(ab); + if (!ag) { + mutex_unlock(&ath12k_hw_group_mutex); + ath12k_warn(ab, "unable to get hw group\n"); + return -ENODEV; + } + + mutex_unlock(&ath12k_hw_group_mutex); + + mutex_lock(&ag->mutex); + + ath12k_dbg(ab, ATH12K_DBG_BOOT, "num devices %d num probed %d\n", + ag->num_devices, ag->num_probed); + + if (ath12k_core_hw_group_create_ready(ag)) { + ret = ath12k_core_hw_group_create(ag); + if (ret) { + mutex_unlock(&ag->mutex); + ath12k_warn(ab, "unable to create hw group\n"); + goto err; + } + } + + mutex_unlock(&ag->mutex); + return 0; + +err: + ath12k_core_hw_group_destroy(ab->ag); + ath12k_core_hw_group_unassign(ab); + return ret; } void ath12k_core_deinit(struct ath12k_base *ab) { ath12k_core_panic_notifier_unregister(ab); - - mutex_lock(&ab->core_lock); - - ath12k_core_pdev_destroy(ab); - ath12k_core_stop(ab); - - mutex_unlock(&ab->core_lock); - - ath12k_hif_power_down(ab, false); - ath12k_mac_destroy(ab); - ath12k_core_soc_destroy(ab); - ath12k_fw_unmap(ab); + ath12k_core_hw_group_cleanup(ab->ag); + ath12k_core_hw_group_destroy(ab->ag); + ath12k_core_hw_group_unassign(ab); } void ath12k_core_free(struct ath12k_base *ab) @@ -1322,7 +1927,7 @@ struct ath12k_base *ath12k_core_alloc(struct device *dev, size_t priv_size, ab->dev = dev; ab->hif.bus = bus; ab->qmi.num_radios = U8_MAX; - ab->mlo_capable_flags = ATH12K_INTRA_DEVICE_MLO_SUPPORT; + ab->single_chip_mlo_supp = false; /* Device index used to identify the devices in a group. * diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h index 3bf31ee5b9fa..ee595794a7ae 100644 --- a/drivers/net/wireless/ath/ath12k/core.h +++ b/drivers/net/wireless/ath/ath12k/core.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. */ #ifndef ATH12K_CORE_H @@ -63,6 +63,14 @@ #define ATH12K_RECONFIGURE_TIMEOUT_HZ (10 * HZ) #define ATH12K_RECOVER_START_TIMEOUT_HZ (20 * HZ) +#define ATH12K_MAX_SOCS 3 +#define ATH12K_GROUP_MAX_RADIO (ATH12K_MAX_SOCS * MAX_RADIOS) +#define ATH12K_INVALID_GROUP_ID 0xFF +#define ATH12K_INVALID_DEVICE_ID 0xFF + +#define ATH12K_MAX_MLO_PEERS 256 +#define ATH12K_MLO_PEER_ID_INVALID 0xFFFF + enum ath12k_bdf_search { ATH12K_BDF_SEARCH_DEFAULT, ATH12K_BDF_SEARCH_BUS_AND_BOARD, @@ -115,6 +123,7 @@ struct ath12k_skb_cb { dma_addr_t paddr_ext_desc; u32 cipher; u8 flags; + u8 link_id; }; struct ath12k_skb_rxcb { @@ -127,7 +136,7 @@ struct ath12k_skb_rxcb { struct hal_rx_desc *rx_desc; u8 err_rel_src; u8 err_code; - u8 mac_id; + u8 hw_link_id; u8 unmapped; u8 is_frag; u8 tid; @@ -208,8 +217,13 @@ enum ath12k_scan_state { ATH12K_SCAN_ABORTING, }; +enum ath12k_hw_group_flags { + ATH12K_GROUP_FLAG_REGISTERED, + ATH12K_GROUP_FLAG_UNREGISTER, +}; + enum ath12k_dev_flags { - ATH12K_CAC_RUNNING, + ATH12K_FLAG_CAC_RUNNING, ATH12K_FLAG_CRASH_FLUSH, ATH12K_FLAG_RAW_MODE, ATH12K_FLAG_HW_CRYPTO_DISABLED, @@ -220,6 +234,7 @@ enum ath12k_dev_flags { ATH12K_FLAG_HTC_SUSPEND_COMPLETE, ATH12K_FLAG_CE_IRQ_ENABLED, ATH12K_FLAG_EXT_IRQ_ENABLED, + ATH12K_FLAG_QMI_FW_READY_COMPLETE, }; struct ath12k_tx_conf { @@ -314,10 +329,11 @@ struct ath12k_vif { bool ps; struct ath12k_link_vif deflink; - struct ath12k_link_vif __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; + struct ath12k_link_vif __rcu *link[ATH12K_NUM_MAX_LINKS]; struct ath12k_vif_cache *cache[IEEE80211_MLD_MAX_NUM_LINKS]; /* indicates bitmap of link vif created in FW */ u16 links_map; + u8 last_scan_link; /* Must be last - ends in a flexible-array member. * @@ -365,10 +381,6 @@ struct ath12k_rx_peer_stats { u64 non_ampdu_msdu_count; u64 stbc_count; u64 beamformed_count; - u64 mcs_count[HAL_RX_MAX_MCS + 1]; - u64 nss_count[HAL_RX_MAX_NSS]; - u64 bw_count[HAL_RX_BW_MAX]; - u64 gi_count[HAL_RX_GI_MAX]; u64 coding_count[HAL_RX_SU_MU_CODING_MAX]; u64 tid_count[IEEE80211_NUM_TIDS + 1]; u64 pream_cnt[HAL_RX_PREAMBLE_MAX]; @@ -469,6 +481,9 @@ struct ath12k_link_sta { struct ath12k_link_vif *arvif; struct ath12k_sta *ahsta; + /* link address similar to ieee80211_link_sta */ + u8 addr[ETH_ALEN]; + /* the following are protected by ar->data_lock */ u32 changed; /* IEEE80211_RC_* */ u32 bw; @@ -485,14 +500,26 @@ struct ath12k_link_sta { struct ath12k_rx_peer_stats *rx_stats; struct ath12k_wbm_tx_stats *wbm_tx_stats; u32 bw_prev; + + /* For now the assoc link will be considered primary */ + bool is_assoc_link; + + /* for firmware use only */ + u8 link_idx; }; struct ath12k_sta { + struct ath12k_vif *ahvif; enum hal_pn_type pn_type; struct ath12k_link_sta deflink; struct ath12k_link_sta __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; /* indicates bitmap of link sta created in FW */ u16 links_map; + u8 assoc_link_id; + u16 ml_peer_id; + u8 num_peer; + + enum ieee80211_sta_state state; }; #define ATH12K_MIN_5G_FREQ 4150 @@ -572,9 +599,10 @@ struct ath12k { struct delayed_work timeout; enum ath12k_scan_state state; bool is_roc; - int vdev_id; int roc_freq; bool roc_notify; + struct wiphy_work vdev_clean_wk; + struct ath12k_link_vif *arvif; } scan; struct { @@ -657,7 +685,7 @@ struct ath12k { struct work_struct regd_update_work; - struct work_struct wmi_mgmt_tx_work; + struct wiphy_work wmi_mgmt_tx_work; struct sk_buff_head wmi_mgmt_tx_queue; struct ath12k_wow wow; @@ -680,14 +708,18 @@ struct ath12k { bool monitor_started; int monitor_vdev_id; - u32 freq_low; - u32 freq_high; + struct wiphy_radio_freq_range freq_range; bool nlo_enabled; + + struct completion mlo_setup_done; + u32 mlo_setup_status; }; struct ath12k_hw { struct ieee80211_hw *hw; + struct device *dev; + /* Protect the write operation of the hardware state ath12k_hw::state * between hardware start<=>reconfigure<=>stop transitions. */ @@ -698,6 +730,11 @@ struct ath12k_hw { u8 num_radio; + DECLARE_BITMAP(free_ml_peer_id_map, ATH12K_MAX_MLO_PEERS); + + /* protected by wiphy_lock() */ + struct list_head ml_peers; + /* Keep last */ struct ath12k radio[] __aligned(sizeof(void *)); }; @@ -732,6 +769,8 @@ struct ath12k_pdev_cap { u32 tx_chain_mask_shift; u32 rx_chain_mask_shift; struct ath12k_band_cap band[NUM_NL80211_BANDS]; + u32 eml_cap; + u32 mld_cap; }; struct mlo_timestamp { @@ -784,19 +823,51 @@ struct ath12k_soc_dp_stats { struct ath12k_soc_dp_tx_err_stats tx_err; }; -/** - * enum ath12k_link_capable_flags - link capable flags - * - * Single/Multi link capability information - * - * @ATH12K_INTRA_DEVICE_MLO_SUPPORT: SLO/MLO form between the radio, where all - * the links (radios) present within a device. - * @ATH12K_INTER_DEVICE_MLO_SUPPORT: SLO/MLO form between the radio, where all - * the links (radios) present across the devices. +struct ath12k_mlo_memory { + struct target_mem_chunk chunk[ATH12K_QMI_WLANFW_MAX_NUM_MEM_SEG_V01]; + int mlo_mem_size; + bool init_done; +}; + +struct ath12k_hw_link { + u8 device_id; + u8 pdev_idx; +}; + +/* Holds info on the group of devices that are registered as a single + * wiphy, protected with struct ath12k_hw_group::mutex. */ -enum ath12k_link_capable_flags { - ATH12K_INTRA_DEVICE_MLO_SUPPORT = BIT(0), - ATH12K_INTER_DEVICE_MLO_SUPPORT = BIT(1), +struct ath12k_hw_group { + struct list_head list; + u8 id; + u8 num_devices; + u8 num_probed; + u8 num_started; + unsigned long flags; + struct ath12k_base *ab[ATH12K_MAX_SOCS]; + + /* protects access to this struct */ + struct mutex mutex; + + /* Holds information of wiphy (hw) registration. + * + * In Multi/Single Link Operation case, all pdevs are registered as + * a single wiphy. In other (legacy/Non-MLO) cases, each pdev is + * registered as separate wiphys. + */ + struct ath12k_hw *ah[ATH12K_GROUP_MAX_RADIO]; + u8 num_hw; + bool mlo_capable; + struct device_node *wsi_node[ATH12K_MAX_SOCS]; + struct ath12k_mlo_memory mlo_mem; + struct ath12k_hw_link hw_links[ATH12K_GROUP_MAX_RADIO]; + bool hw_link_id_init_done; +}; + +/* Holds WSI info specific to each device, excluding WSI group info */ +struct ath12k_wsi_info { + u32 index; + u32 hw_link_id_base; }; /* Master structure to hold the hw data which may be used in core module */ @@ -862,15 +933,6 @@ struct ath12k_base { struct ath12k_pdev __rcu *pdevs_active[MAX_RADIOS]; - /* Holds information of wiphy (hw) registration. - * - * In Multi/Single Link Operation case, all pdevs are registered as - * a single wiphy. In other (legacy/Non-MLO) cases, each pdev is - * registered as separate wiphys. - */ - struct ath12k_hw *ah[MAX_RADIOS]; - u8 num_hw; - struct ath12k_wmi_hal_reg_capabilities_ext_arg hal_reg_cap[MAX_RADIOS]; unsigned long long free_vdev_map; unsigned long long free_vdev_stats_id_map; @@ -964,12 +1026,8 @@ struct ath12k_base { const struct hal_rx_ops *hal_rx_ops; - /* mlo_capable_flags denotes the single/multi link operation - * capabilities of the Device. - * - * See enum ath12k_link_capable_flags - */ - u8 mlo_capable_flags; + /* Denotes the whether MLO is possible within the chip */ + bool single_chip_mlo_supp; struct completion restart_completed; @@ -992,6 +1050,9 @@ struct ath12k_base { struct notifier_block panic_nb; + struct ath12k_hw_group *ag; + struct ath12k_wsi_info wsi_info; + /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; @@ -1022,6 +1083,7 @@ int ath12k_core_resume_early(struct ath12k_base *ab); int ath12k_core_resume(struct ath12k_base *ab); int ath12k_core_suspend(struct ath12k_base *ab); int ath12k_core_suspend_late(struct ath12k_base *ab); +void ath12k_core_hw_group_unassign(struct ath12k_base *ab); const struct firmware *ath12k_core_firmware_request(struct ath12k_base *ab, const char *filename); @@ -1029,6 +1091,8 @@ u32 ath12k_core_get_max_station_per_radio(struct ath12k_base *ab); u32 ath12k_core_get_max_peers_per_radio(struct ath12k_base *ab); u32 ath12k_core_get_max_num_tids(struct ath12k_base *ab); +void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag); + static inline const char *ath12k_scan_state_str(enum ath12k_scan_state state) { switch (state) { @@ -1129,4 +1193,41 @@ static inline struct ieee80211_hw *ath12k_ar_to_hw(struct ath12k *ar) #define for_each_ar(ah, ar, index) \ for ((index) = 0; ((index) < (ah)->num_radio && \ ((ar) = &(ah)->radio[(index)])); (index)++) + +static inline struct ath12k_hw *ath12k_ag_to_ah(struct ath12k_hw_group *ag, int idx) +{ + return ag->ah[idx]; +} + +static inline void ath12k_ag_set_ah(struct ath12k_hw_group *ag, int idx, + struct ath12k_hw *ah) +{ + ag->ah[idx] = ah; +} + +static inline struct ath12k_hw_group *ath12k_ab_to_ag(struct ath12k_base *ab) +{ + return ab->ag; +} + +static inline void ath12k_core_started(struct ath12k_base *ab) +{ + lockdep_assert_held(&ab->ag->mutex); + + ab->ag->num_started++; +} + +static inline void ath12k_core_stopped(struct ath12k_base *ab) +{ + lockdep_assert_held(&ab->ag->mutex); + + ab->ag->num_started--; +} + +static inline struct ath12k_base *ath12k_ag_to_ab(struct ath12k_hw_group *ag, + u8 device_id) +{ + return ag->ab[device_id]; +} + #endif /* _CORE_H_ */ diff --git a/drivers/net/wireless/ath/ath12k/coredump.c b/drivers/net/wireless/ath/ath12k/coredump.c index 72d675d15e64..ce1beeb54836 100644 --- a/drivers/net/wireless/ath/ath12k/coredump.c +++ b/drivers/net/wireless/ath/ath12k/coredump.c @@ -27,6 +27,9 @@ ath12k_fw_crash_dump_type ath12k_coredump_get_dump_type(enum ath12k_qmi_target_m case CALDB_MEM_REGION_TYPE: dump_type = FW_CRASH_DUMP_NONE; break; + case MLO_GLOBAL_MEM_REGION_TYPE: + dump_type = FW_CRASH_DUMP_MLO_GLOBAL_DATA; + break; default: dump_type = FW_CRASH_DUMP_TYPE_MAX; break; diff --git a/drivers/net/wireless/ath/ath12k/coredump.h b/drivers/net/wireless/ath/ath12k/coredump.h index 5d6003b1c12d..13f46a605113 100644 --- a/drivers/net/wireless/ath/ath12k/coredump.h +++ b/drivers/net/wireless/ath/ath12k/coredump.h @@ -15,6 +15,7 @@ enum ath12k_fw_crash_dump_type { FW_CRASH_DUMP_PAGEABLE_DATA, FW_CRASH_DUMP_M3_DUMP, FW_CRASH_DUMP_NONE, + FW_CRASH_DUMP_MLO_GLOBAL_DATA, /* keep last */ FW_CRASH_DUMP_TYPE_MAX, diff --git a/drivers/net/wireless/ath/ath12k/debug.c b/drivers/net/wireless/ath/ath12k/debug.c index fe5a732ba9ec..ff6eaeafa092 100644 --- a/drivers/net/wireless/ath/ath12k/debug.c +++ b/drivers/net/wireless/ath/ath12k/debug.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include @@ -36,7 +36,7 @@ void ath12k_err(struct ath12k_base *ab, const char *fmt, ...) va_end(args); } -void ath12k_warn(struct ath12k_base *ab, const char *fmt, ...) +void __ath12k_warn(struct device *dev, const char *fmt, ...) { struct va_format vaf = { .fmt = fmt, @@ -45,7 +45,7 @@ void ath12k_warn(struct ath12k_base *ab, const char *fmt, ...) va_start(args, fmt); vaf.va = &args; - dev_warn_ratelimited(ab->dev, "%pV", &vaf); + dev_warn_ratelimited(dev, "%pV", &vaf); /* TODO: Trace the log */ va_end(args); } diff --git a/drivers/net/wireless/ath/ath12k/debug.h b/drivers/net/wireless/ath/ath12k/debug.h index f7005917362c..90e801136bc6 100644 --- a/drivers/net/wireless/ath/ath12k/debug.h +++ b/drivers/net/wireless/ath/ath12k/debug.h @@ -31,7 +31,10 @@ enum ath12k_debug_mask { __printf(2, 3) void ath12k_info(struct ath12k_base *ab, const char *fmt, ...); __printf(2, 3) void ath12k_err(struct ath12k_base *ab, const char *fmt, ...); -__printf(2, 3) void ath12k_warn(struct ath12k_base *ab, const char *fmt, ...); +__printf(2, 3) void __ath12k_warn(struct device *dev, const char *fmt, ...); + +#define ath12k_warn(ab, fmt, ...) __ath12k_warn((ab)->dev, fmt, ##__VA_ARGS__) +#define ath12k_hw_warn(ah, fmt, ...) __ath12k_warn((ah)->dev, fmt, ##__VA_ARGS__) extern unsigned int ath12k_debug_mask; diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c index c9980c0193d1..41e4ef2ef3af 100644 --- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c +++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c @@ -48,6 +48,28 @@ print_array_to_buf(u8 *buf, u32 offset, const char *header, footer); } +static const char *ath12k_htt_ax_tx_rx_ru_size_to_str(u8 ru_size) +{ + switch (ru_size) { + case ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_26: + return "26"; + case ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_52: + return "52"; + case ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_106: + return "106"; + case ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_242: + return "242"; + case ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_484: + return "484"; + case ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_996: + return "996"; + case ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_996x2: + return "996x2"; + default: + return "unknown"; + } +} + static const char *ath12k_htt_be_tx_rx_ru_size_to_str(u8 ru_size) { switch (ru_size) { @@ -88,6 +110,17 @@ static const char *ath12k_htt_be_tx_rx_ru_size_to_str(u8 ru_size) } } +static const char* +ath12k_tx_ru_size_to_str(enum ath12k_htt_stats_ru_type ru_type, u8 ru_size) +{ + if (ru_type == ATH12K_HTT_STATS_RU_TYPE_SINGLE_RU_ONLY) + return ath12k_htt_ax_tx_rx_ru_size_to_str(ru_size); + else if (ru_type == ATH12K_HTT_STATS_RU_TYPE_SINGLE_AND_MULTI_RU) + return ath12k_htt_be_tx_rx_ru_size_to_str(ru_size); + else + return "unknown"; +} + static void htt_print_tx_pdev_stats_cmn_tlv(const void *tag_buf, u16 tag_len, struct debug_htt_stats_req *stats_req) @@ -1562,7 +1595,8 @@ ath12k_htt_print_tx_selfgen_ac_stats_tlv(const void *tag_buf, u16 tag_len, le32_to_cpu(htt_stats_buf->ac_mu_mimo_ndp)); len += print_array_to_buf_index(buf, len, "ac_mu_mimo_brpollX_tried = ", 1, htt_stats_buf->ac_mu_mimo_brpoll, - ATH12K_HTT_TX_NUM_AC_MUMIMO_USER_STATS, "\n\n"); + ATH12K_HTT_TX_NUM_AC_MUMIMO_USER_STATS - 1, + "\n\n"); stats_req->buf_len = len; } @@ -1590,7 +1624,7 @@ ath12k_htt_print_tx_selfgen_ax_stats_tlv(const void *tag_buf, u16 tag_len, le32_to_cpu(htt_stats_buf->ax_mu_mimo_ndp)); len += print_array_to_buf_index(buf, len, "ax_mu_mimo_brpollX_tried = ", 1, htt_stats_buf->ax_mu_mimo_brpoll, - ATH12K_HTT_TX_NUM_AX_MUMIMO_USER_STATS, "\n"); + ATH12K_HTT_TX_NUM_AX_MUMIMO_USER_STATS - 1, "\n"); len += scnprintf(buf + len, buf_len - len, "ax_basic_trigger = %u\n", le32_to_cpu(htt_stats_buf->ax_basic_trigger)); len += scnprintf(buf + len, buf_len - len, "ax_ulmumimo_total_trigger = %u\n", @@ -2276,9 +2310,9 @@ ath12k_htt_print_tx_pdev_mumimo_grp_stats_tlv(const void *tag_buf, u16 tag_len, len += print_array_to_buf(buf, len, "ul_mumimo_grp_best_grp_size", htt_stats_buf->ul_mumimo_grp_best_grp_size, ATH12K_HTT_STATS_NUM_MAX_MUMIMO_SZ, "\n"); - len += print_array_to_buf_index(buf, len, "ul_mumimo_grp_best_num_usrs = ", 1, - htt_stats_buf->ul_mumimo_grp_best_usrs, - ATH12K_HTT_TX_NUM_AX_MUMIMO_USER_STATS, "\n"); + len += print_array_to_buf(buf, len, "ul_mumimo_grp_best_num_usrs = ", + htt_stats_buf->ul_mumimo_grp_best_usrs, + ATH12K_HTT_TX_NUM_AX_MUMIMO_USER_STATS, "\n"); len += print_array_to_buf(buf, len, "ul_mumimo_grp_tputs_observed (per bin = 300 mbps)", htt_stats_buf->ul_mumimo_grp_tputs, @@ -2542,6 +2576,1050 @@ ath12k_htt_print_pdev_obss_pd_stats_tlv(const void *tag_buf, u16 tag_len, stats_req->buf_len = len; } +static void +ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_pdev_txrate_txbf_stats_tlv *htt_stats_buf = tag_buf; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 len = stats_req->buf_len; + u8 *buf = stats_req->buf; + u8 i; + + if (tag_len < sizeof(*htt_stats_buf)) + return; + + len += scnprintf(buf + len, buf_len - len, + "HTT_STATS_PDEV_TX_RATE_TXBF_STATS:\n"); + len += scnprintf(buf + len, buf_len - len, "Legacy OFDM Rates: 6 Mbps: %u, ", + le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[0])); + len += scnprintf(buf + len, buf_len - len, "9 Mbps: %u, 12 Mbps: %u, ", + le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[1]), + le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[2])); + len += scnprintf(buf + len, buf_len - len, "18 Mbps: %u\n", + le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[3])); + len += scnprintf(buf + len, buf_len - len, "24 Mbps: %u, 36 Mbps: %u, ", + le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[4]), + le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[5])); + len += scnprintf(buf + len, buf_len - len, "48 Mbps: %u, 54 Mbps: %u\n", + le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[6]), + le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[7])); + + len += print_array_to_buf(buf, len, "tx_ol_mcs", htt_stats_buf->tx_su_ol_mcs, + ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS, "\n"); + len += print_array_to_buf(buf, len, "tx_ibf_mcs", htt_stats_buf->tx_su_ibf_mcs, + ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS, "\n"); + len += print_array_to_buf(buf, len, "tx_txbf_mcs", htt_stats_buf->tx_su_txbf_mcs, + ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS, "\n"); + len += print_array_to_buf_index(buf, len, "tx_ol_nss", 1, + htt_stats_buf->tx_su_ol_nss, + ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS, + "\n"); + len += print_array_to_buf_index(buf, len, "tx_ibf_nss", 1, + htt_stats_buf->tx_su_ibf_nss, + ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS, + "\n"); + len += print_array_to_buf_index(buf, len, "tx_txbf_nss", 1, + htt_stats_buf->tx_su_txbf_nss, + ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS, + "\n"); + len += print_array_to_buf(buf, len, "tx_ol_bw", htt_stats_buf->tx_su_ol_bw, + ATH12K_HTT_TXBF_NUM_BW_CNTRS, "\n"); + for (i = 0; i < ATH12K_HTT_TXBF_NUM_REDUCED_CHAN_TYPES; i++) + len += print_array_to_buf(buf, len, i ? "quarter_tx_ol_bw" : + "half_tx_ol_bw", + htt_stats_buf->ol[i], + ATH12K_HTT_TXBF_NUM_BW_CNTRS, + "\n"); + + len += print_array_to_buf(buf, len, "tx_ibf_bw", htt_stats_buf->tx_su_ibf_bw, + ATH12K_HTT_TXBF_NUM_BW_CNTRS, "\n"); + for (i = 0; i < ATH12K_HTT_TXBF_NUM_REDUCED_CHAN_TYPES; i++) + len += print_array_to_buf(buf, len, i ? "quarter_tx_ibf_bw" : + "half_tx_ibf_bw", + htt_stats_buf->ibf[i], + ATH12K_HTT_TXBF_NUM_BW_CNTRS, + "\n"); + + len += print_array_to_buf(buf, len, "tx_txbf_bw", htt_stats_buf->tx_su_txbf_bw, + ATH12K_HTT_TXBF_NUM_BW_CNTRS, "\n"); + for (i = 0; i < ATH12K_HTT_TXBF_NUM_REDUCED_CHAN_TYPES; i++) + len += print_array_to_buf(buf, len, i ? "quarter_tx_txbf_bw" : + "half_tx_txbf_bw", + htt_stats_buf->txbf[i], + ATH12K_HTT_TXBF_NUM_BW_CNTRS, + "\n"); + len += scnprintf(buf + len, buf_len - len, "\n"); + + len += scnprintf(buf + len, buf_len - len, + "HTT_STATS_PDEV_TXBF_FLAG_RETURN_STATS:\n"); + len += scnprintf(buf + len, buf_len - len, "TXBF_reason_code_stats: 0:%u, 1:%u,", + le32_to_cpu(htt_stats_buf->txbf_flag_set_mu_mode), + le32_to_cpu(htt_stats_buf->txbf_flag_set_final_status)); + len += scnprintf(buf + len, buf_len - len, " 2:%u, 3:%u, 4:%u, 5:%u, ", + le32_to_cpu(htt_stats_buf->txbf_flag_not_set_verified_txbf_mode), + le32_to_cpu(htt_stats_buf->txbf_flag_not_set_disable_p2p_access), + le32_to_cpu(htt_stats_buf->txbf_flag_not_set_max_nss_in_he160), + le32_to_cpu(htt_stats_buf->txbf_flag_not_set_disable_uldlofdma)); + len += scnprintf(buf + len, buf_len - len, "6:%u, 7:%u\n\n", + le32_to_cpu(htt_stats_buf->txbf_flag_not_set_mcs_threshold_val), + le32_to_cpu(htt_stats_buf->txbf_flag_not_set_final_status)); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_txbf_ofdma_ax_ndpa_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_txbf_ofdma_ax_ndpa_stats_tlv *stats_buf = tag_buf; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 len = stats_req->buf_len; + u8 *buf = stats_req->buf; + u32 num_elements; + u8 i; + + if (tag_len < sizeof(*stats_buf)) + return; + + num_elements = le32_to_cpu(stats_buf->num_elems_ax_ndpa_arr); + + len += scnprintf(buf + len, buf_len - len, "HTT_TXBF_OFDMA_AX_NDPA_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "ax_ofdma_ndpa_queued ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_ndpa[i].ax_ofdma_ndpa_queued)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_ndpa_tried ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_ndpa[i].ax_ofdma_ndpa_tried)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_ndpa_flushed ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_ndpa[i].ax_ofdma_ndpa_flush)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_ndpa_err ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_ndpa[i].ax_ofdma_ndpa_err)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\n\n"); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_txbf_ofdma_ax_ndp_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_txbf_ofdma_ax_ndp_stats_tlv *stats_buf = tag_buf; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 len = stats_req->buf_len; + u8 *buf = stats_req->buf; + u32 num_elements; + u8 i; + + if (tag_len < sizeof(*stats_buf)) + return; + + num_elements = le32_to_cpu(stats_buf->num_elems_ax_ndp_arr); + + len += scnprintf(buf + len, buf_len - len, "HTT_TXBF_OFDMA_AX_NDP_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "ax_ofdma_ndp_queued ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_ndp[i].ax_ofdma_ndp_queued)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_ndp_tried ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_ndp[i].ax_ofdma_ndp_tried)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_ndp_flushed ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_ndp[i].ax_ofdma_ndp_flush)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_ndp_err ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_ndp[i].ax_ofdma_ndp_err)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\n\n"); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_txbf_ofdma_ax_brp_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_txbf_ofdma_ax_brp_stats_tlv *stats_buf = tag_buf; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 len = stats_req->buf_len; + u8 *buf = stats_req->buf; + u32 num_elements; + u8 i; + + if (tag_len < sizeof(*stats_buf)) + return; + + num_elements = le32_to_cpu(stats_buf->num_elems_ax_brp_arr); + + len += scnprintf(buf + len, buf_len - len, "HTT_TXBF_OFDMA_AX_BRP_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "ax_ofdma_brpoll_queued ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_brp[i].ax_ofdma_brp_queued)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_brpoll_tied ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_brp[i].ax_ofdma_brp_tried)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_brpoll_flushed ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_brp[i].ax_ofdma_brp_flushed)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_brp_err ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_brp[i].ax_ofdma_brp_err)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_brp_err_num_cbf_rcvd ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_brp[i].ax_ofdma_num_cbf_rcvd)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\n\n"); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_txbf_ofdma_ax_steer_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_txbf_ofdma_ax_steer_stats_tlv *stats_buf = tag_buf; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 len = stats_req->buf_len; + u8 *buf = stats_req->buf; + u32 num_elements; + u8 i; + + if (tag_len < sizeof(*stats_buf)) + return; + + num_elements = le32_to_cpu(stats_buf->num_elems_ax_steer_arr); + + len += scnprintf(buf + len, buf_len - len, + "HTT_TXBF_OFDMA_AX_STEER_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "ax_ofdma_num_ppdu_steer ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_steer[i].num_ppdu_steer)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_num_usrs_prefetch ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_steer[i].num_usr_prefetch)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_num_usrs_sound ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_steer[i].num_usr_sound)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\nax_ofdma_num_usrs_force_sound ="); + for (i = 0; i < num_elements; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u,", i + 1, + le32_to_cpu(stats_buf->ax_steer[i].num_usr_force_sound)); + len--; + *(buf + len) = '\0'; + + len += scnprintf(buf + len, buf_len - len, "\n\n"); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_txbf_ofdma_ax_steer_mpdu_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_txbf_ofdma_ax_steer_mpdu_stats_tlv *stats_buf = tag_buf; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 len = stats_req->buf_len; + u8 *buf = stats_req->buf; + + if (tag_len < sizeof(*stats_buf)) + return; + + len += scnprintf(buf + len, buf_len - len, + "HTT_TXBF_OFDMA_AX_STEER_MPDU_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "rbo_steer_mpdus_tried = %u\n", + le32_to_cpu(stats_buf->ax_ofdma_rbo_steer_mpdus_tried)); + len += scnprintf(buf + len, buf_len - len, "rbo_steer_mpdus_failed = %u\n", + le32_to_cpu(stats_buf->ax_ofdma_rbo_steer_mpdus_failed)); + len += scnprintf(buf + len, buf_len - len, "sifs_steer_mpdus_tried = %u\n", + le32_to_cpu(stats_buf->ax_ofdma_sifs_steer_mpdus_tried)); + len += scnprintf(buf + len, buf_len - len, "sifs_steer_mpdus_failed = %u\n\n", + le32_to_cpu(stats_buf->ax_ofdma_sifs_steer_mpdus_failed)); + + stats_req->buf_len = len; +} + +static void ath12k_htt_print_dlpager_entry(const struct ath12k_htt_pgs_info *pg_info, + int idx, char *str_buf) +{ + u64 page_timestamp; + u16 index = 0; + + page_timestamp = ath12k_le32hilo_to_u64(pg_info->ts_msb, pg_info->ts_lsb); + + index += snprintf(&str_buf[index], ATH12K_HTT_MAX_STRING_LEN - index, + "Index - %u ; Page Number - %u ; ", + idx, le32_to_cpu(pg_info->page_num)); + index += snprintf(&str_buf[index], ATH12K_HTT_MAX_STRING_LEN - index, + "Num of pages - %u ; Timestamp - %lluus\n", + le32_to_cpu(pg_info->num_pgs), page_timestamp); +} + +static void +ath12k_htt_print_dlpager_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_dl_pager_stats_tlv *stat_buf = tag_buf; + u32 len = stats_req->buf_len; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 dword_lock, dword_unlock; + int i; + u8 *buf = stats_req->buf; + u8 pg_locked; + u8 pg_unlock; + char str_buf[ATH12K_HTT_MAX_STRING_LEN] = {0}; + + if (tag_len < sizeof(*stat_buf)) + return; + + dword_lock = le32_get_bits(stat_buf->info2, + ATH12K_HTT_DLPAGER_TOTAL_LOCK_PAGES_INFO2); + dword_unlock = le32_get_bits(stat_buf->info2, + ATH12K_HTT_DLPAGER_TOTAL_FREE_PAGES_INFO2); + + pg_locked = ATH12K_HTT_STATS_PAGE_LOCKED; + pg_unlock = ATH12K_HTT_STATS_PAGE_UNLOCKED; + + len += scnprintf(buf + len, buf_len - len, "HTT_DLPAGER_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "ASYNC locked pages = %u\n", + le32_get_bits(stat_buf->info0, + ATH12K_HTT_DLPAGER_ASYNC_LOCK_PG_CNT_INFO0)); + len += scnprintf(buf + len, buf_len - len, "SYNC locked pages = %u\n", + le32_get_bits(stat_buf->info0, + ATH12K_HTT_DLPAGER_SYNC_LOCK_PG_CNT_INFO0)); + len += scnprintf(buf + len, buf_len - len, "Total locked pages = %u\n", + le32_get_bits(stat_buf->info1, + ATH12K_HTT_DLPAGER_TOTAL_LOCK_PAGES_INFO1)); + len += scnprintf(buf + len, buf_len - len, "Total free pages = %u\n", + le32_get_bits(stat_buf->info1, + ATH12K_HTT_DLPAGER_TOTAL_FREE_PAGES_INFO1)); + + len += scnprintf(buf + len, buf_len - len, "\nLOCKED PAGES HISTORY\n"); + len += scnprintf(buf + len, buf_len - len, "last_locked_page_idx = %u\n", + dword_lock ? dword_lock - 1 : (ATH12K_PAGER_MAX - 1)); + + for (i = 0; i < ATH12K_PAGER_MAX; i++) { + memset(str_buf, 0x0, ATH12K_HTT_MAX_STRING_LEN); + ath12k_htt_print_dlpager_entry(&stat_buf->pgs_info[pg_locked][i], + i, str_buf); + len += scnprintf(buf + len, buf_len - len, "%s", str_buf); + } + + len += scnprintf(buf + len, buf_len - len, "\nUNLOCKED PAGES HISTORY\n"); + len += scnprintf(buf + len, buf_len - len, "last_unlocked_page_idx = %u\n", + dword_unlock ? dword_unlock - 1 : ATH12K_PAGER_MAX - 1); + + for (i = 0; i < ATH12K_PAGER_MAX; i++) { + memset(str_buf, 0x0, ATH12K_HTT_MAX_STRING_LEN); + ath12k_htt_print_dlpager_entry(&stat_buf->pgs_info[pg_unlock][i], + i, str_buf); + len += scnprintf(buf + len, buf_len - len, "%s", str_buf); + } + + len += scnprintf(buf + len, buf_len - len, "\n"); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_phy_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_phy_stats_tlv *htt_stats_buf = tag_buf; + u32 len = stats_req->buf_len; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u8 *buf = stats_req->buf, i; + + if (tag_len < sizeof(*htt_stats_buf)) + return; + + len += scnprintf(buf + len, buf_len - len, "HTT_PHY_STATS_TLV:\n"); + for (i = 0; i < ATH12K_HTT_STATS_MAX_CHAINS; i++) + len += scnprintf(buf + len, buf_len - len, "bdf_nf_chain[%d] = %d\n", + i, a_sle32_to_cpu(htt_stats_buf->nf_chain[i])); + for (i = 0; i < ATH12K_HTT_STATS_MAX_CHAINS; i++) + len += scnprintf(buf + len, buf_len - len, "runtime_nf_chain[%d] = %d\n", + i, a_sle32_to_cpu(htt_stats_buf->runtime_nf_chain[i])); + len += scnprintf(buf + len, buf_len - len, "false_radar_cnt = %u / %u (mins)\n", + le32_to_cpu(htt_stats_buf->false_radar_cnt), + le32_to_cpu(htt_stats_buf->fw_run_time)); + len += scnprintf(buf + len, buf_len - len, "radar_cs_cnt = %u\n", + le32_to_cpu(htt_stats_buf->radar_cs_cnt)); + len += scnprintf(buf + len, buf_len - len, "ani_level = %d\n\n", + a_sle32_to_cpu(htt_stats_buf->ani_level)); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_phy_counters_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_phy_counters_tlv *htt_stats_buf = tag_buf; + u32 len = stats_req->buf_len; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u8 *buf = stats_req->buf; + + if (tag_len < sizeof(*htt_stats_buf)) + return; + + len += scnprintf(buf + len, buf_len - len, "HTT_PHY_COUNTERS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "rx_ofdma_timing_err_cnt = %u\n", + le32_to_cpu(htt_stats_buf->rx_ofdma_timing_err_cnt)); + len += scnprintf(buf + len, buf_len - len, "rx_cck_fail_cnt = %u\n", + le32_to_cpu(htt_stats_buf->rx_cck_fail_cnt)); + len += scnprintf(buf + len, buf_len - len, "mactx_abort_cnt = %u\n", + le32_to_cpu(htt_stats_buf->mactx_abort_cnt)); + len += scnprintf(buf + len, buf_len - len, "macrx_abort_cnt = %u\n", + le32_to_cpu(htt_stats_buf->macrx_abort_cnt)); + len += scnprintf(buf + len, buf_len - len, "phytx_abort_cnt = %u\n", + le32_to_cpu(htt_stats_buf->phytx_abort_cnt)); + len += scnprintf(buf + len, buf_len - len, "phyrx_abort_cnt = %u\n", + le32_to_cpu(htt_stats_buf->phyrx_abort_cnt)); + len += scnprintf(buf + len, buf_len - len, "phyrx_defer_abort_cnt = %u\n", + le32_to_cpu(htt_stats_buf->phyrx_defer_abort_cnt)); + len += scnprintf(buf + len, buf_len - len, "rx_gain_adj_lstf_event_cnt = %u\n", + le32_to_cpu(htt_stats_buf->rx_gain_adj_lstf_event_cnt)); + len += scnprintf(buf + len, buf_len - len, "rx_gain_adj_non_legacy_cnt = %u\n", + le32_to_cpu(htt_stats_buf->rx_gain_adj_non_legacy_cnt)); + len += print_array_to_buf(buf, len, "rx_pkt_cnt", htt_stats_buf->rx_pkt_cnt, + ATH12K_HTT_MAX_RX_PKT_CNT, "\n"); + len += print_array_to_buf(buf, len, "rx_pkt_crc_pass_cnt", + htt_stats_buf->rx_pkt_crc_pass_cnt, + ATH12K_HTT_MAX_RX_PKT_CRC_PASS_CNT, "\n"); + len += print_array_to_buf(buf, len, "per_blk_err_cnt", + htt_stats_buf->per_blk_err_cnt, + ATH12K_HTT_MAX_PER_BLK_ERR_CNT, "\n"); + len += print_array_to_buf(buf, len, "rx_ota_err_cnt", + htt_stats_buf->rx_ota_err_cnt, + ATH12K_HTT_MAX_RX_OTA_ERR_CNT, "\n\n"); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_phy_reset_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_phy_reset_stats_tlv *htt_stats_buf = tag_buf; + u32 len = stats_req->buf_len; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u8 *buf = stats_req->buf; + + if (tag_len < sizeof(*htt_stats_buf)) + return; + + len += scnprintf(buf + len, buf_len - len, "HTT_PHY_RESET_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "pdev_id = %u\n", + le32_to_cpu(htt_stats_buf->pdev_id)); + len += scnprintf(buf + len, buf_len - len, "chan_mhz = %u\n", + le32_to_cpu(htt_stats_buf->chan_mhz)); + len += scnprintf(buf + len, buf_len - len, "chan_band_center_freq1 = %u\n", + le32_to_cpu(htt_stats_buf->chan_band_center_freq1)); + len += scnprintf(buf + len, buf_len - len, "chan_band_center_freq2 = %u\n", + le32_to_cpu(htt_stats_buf->chan_band_center_freq2)); + len += scnprintf(buf + len, buf_len - len, "chan_phy_mode = %u\n", + le32_to_cpu(htt_stats_buf->chan_phy_mode)); + len += scnprintf(buf + len, buf_len - len, "chan_flags = 0x%0x\n", + le32_to_cpu(htt_stats_buf->chan_flags)); + len += scnprintf(buf + len, buf_len - len, "chan_num = %u\n", + le32_to_cpu(htt_stats_buf->chan_num)); + len += scnprintf(buf + len, buf_len - len, "reset_cause = 0x%0x\n", + le32_to_cpu(htt_stats_buf->reset_cause)); + len += scnprintf(buf + len, buf_len - len, "prev_reset_cause = 0x%0x\n", + le32_to_cpu(htt_stats_buf->prev_reset_cause)); + len += scnprintf(buf + len, buf_len - len, "phy_warm_reset_src = 0x%0x\n", + le32_to_cpu(htt_stats_buf->phy_warm_reset_src)); + len += scnprintf(buf + len, buf_len - len, "rx_gain_tbl_mode = %d\n", + le32_to_cpu(htt_stats_buf->rx_gain_tbl_mode)); + len += scnprintf(buf + len, buf_len - len, "xbar_val = 0x%0x\n", + le32_to_cpu(htt_stats_buf->xbar_val)); + len += scnprintf(buf + len, buf_len - len, "force_calibration = %u\n", + le32_to_cpu(htt_stats_buf->force_calibration)); + len += scnprintf(buf + len, buf_len - len, "phyrf_mode = %u\n", + le32_to_cpu(htt_stats_buf->phyrf_mode)); + len += scnprintf(buf + len, buf_len - len, "phy_homechan = %u\n", + le32_to_cpu(htt_stats_buf->phy_homechan)); + len += scnprintf(buf + len, buf_len - len, "phy_tx_ch_mask = 0x%0x\n", + le32_to_cpu(htt_stats_buf->phy_tx_ch_mask)); + len += scnprintf(buf + len, buf_len - len, "phy_rx_ch_mask = 0x%0x\n", + le32_to_cpu(htt_stats_buf->phy_rx_ch_mask)); + len += scnprintf(buf + len, buf_len - len, "phybb_ini_mask = 0x%0x\n", + le32_to_cpu(htt_stats_buf->phybb_ini_mask)); + len += scnprintf(buf + len, buf_len - len, "phyrf_ini_mask = 0x%0x\n", + le32_to_cpu(htt_stats_buf->phyrf_ini_mask)); + len += scnprintf(buf + len, buf_len - len, "phy_dfs_en_mask = 0x%0x\n", + le32_to_cpu(htt_stats_buf->phy_dfs_en_mask)); + len += scnprintf(buf + len, buf_len - len, "phy_sscan_en_mask = 0x%0x\n", + le32_to_cpu(htt_stats_buf->phy_sscan_en_mask)); + len += scnprintf(buf + len, buf_len - len, "phy_synth_sel_mask = 0x%0x\n", + le32_to_cpu(htt_stats_buf->phy_synth_sel_mask)); + len += scnprintf(buf + len, buf_len - len, "phy_adfs_freq = %u\n", + le32_to_cpu(htt_stats_buf->phy_adfs_freq)); + len += scnprintf(buf + len, buf_len - len, "cck_fir_settings = 0x%0x\n", + le32_to_cpu(htt_stats_buf->cck_fir_settings)); + len += scnprintf(buf + len, buf_len - len, "phy_dyn_pri_chan = %u\n", + le32_to_cpu(htt_stats_buf->phy_dyn_pri_chan)); + len += scnprintf(buf + len, buf_len - len, "cca_thresh = 0x%0x\n", + le32_to_cpu(htt_stats_buf->cca_thresh)); + len += scnprintf(buf + len, buf_len - len, "dyn_cca_status = %u\n", + le32_to_cpu(htt_stats_buf->dyn_cca_status)); + len += scnprintf(buf + len, buf_len - len, "rxdesense_thresh_hw = 0x%x\n", + le32_to_cpu(htt_stats_buf->rxdesense_thresh_hw)); + len += scnprintf(buf + len, buf_len - len, "rxdesense_thresh_sw = 0x%x\n\n", + le32_to_cpu(htt_stats_buf->rxdesense_thresh_sw)); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_phy_reset_counters_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_phy_reset_counters_tlv *htt_stats_buf = tag_buf; + u32 len = stats_req->buf_len; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u8 *buf = stats_req->buf; + + if (tag_len < sizeof(*htt_stats_buf)) + return; + + len += scnprintf(buf + len, buf_len - len, "HTT_PHY_RESET_COUNTERS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "pdev_id = %u\n", + le32_to_cpu(htt_stats_buf->pdev_id)); + len += scnprintf(buf + len, buf_len - len, "cf_active_low_fail_cnt = %u\n", + le32_to_cpu(htt_stats_buf->cf_active_low_fail_cnt)); + len += scnprintf(buf + len, buf_len - len, "cf_active_low_pass_cnt = %u\n", + le32_to_cpu(htt_stats_buf->cf_active_low_pass_cnt)); + len += scnprintf(buf + len, buf_len - len, "phy_off_through_vreg_cnt = %u\n", + le32_to_cpu(htt_stats_buf->phy_off_through_vreg_cnt)); + len += scnprintf(buf + len, buf_len - len, "force_calibration_cnt = %u\n", + le32_to_cpu(htt_stats_buf->force_calibration_cnt)); + len += scnprintf(buf + len, buf_len - len, "rf_mode_switch_phy_off_cnt = %u\n", + le32_to_cpu(htt_stats_buf->rf_mode_switch_phy_off_cnt)); + len += scnprintf(buf + len, buf_len - len, "temperature_recal_cnt = %u\n\n", + le32_to_cpu(htt_stats_buf->temperature_recal_cnt)); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_phy_tpc_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_phy_tpc_stats_tlv *htt_stats_buf = tag_buf; + u32 len = stats_req->buf_len; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u8 *buf = stats_req->buf; + + if (tag_len < sizeof(*htt_stats_buf)) + return; + + len += scnprintf(buf + len, buf_len - len, "HTT_PHY_TPC_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "pdev_id = %u\n", + le32_to_cpu(htt_stats_buf->pdev_id)); + len += scnprintf(buf + len, buf_len - len, "tx_power_scale = %u\n", + le32_to_cpu(htt_stats_buf->tx_power_scale)); + len += scnprintf(buf + len, buf_len - len, "tx_power_scale_db = %u\n", + le32_to_cpu(htt_stats_buf->tx_power_scale_db)); + len += scnprintf(buf + len, buf_len - len, "min_negative_tx_power = %d\n", + le32_to_cpu(htt_stats_buf->min_negative_tx_power)); + len += scnprintf(buf + len, buf_len - len, "reg_ctl_domain = %u\n", + le32_to_cpu(htt_stats_buf->reg_ctl_domain)); + len += scnprintf(buf + len, buf_len - len, "twice_max_rd_power = %u\n", + le32_to_cpu(htt_stats_buf->twice_max_rd_power)); + len += scnprintf(buf + len, buf_len - len, "max_tx_power = %u\n", + le32_to_cpu(htt_stats_buf->max_tx_power)); + len += scnprintf(buf + len, buf_len - len, "home_max_tx_power = %u\n", + le32_to_cpu(htt_stats_buf->home_max_tx_power)); + len += scnprintf(buf + len, buf_len - len, "psd_power = %d\n", + le32_to_cpu(htt_stats_buf->psd_power)); + len += scnprintf(buf + len, buf_len - len, "eirp_power = %u\n", + le32_to_cpu(htt_stats_buf->eirp_power)); + len += scnprintf(buf + len, buf_len - len, "power_type_6ghz = %u\n", + le32_to_cpu(htt_stats_buf->power_type_6ghz)); + len += print_array_to_buf(buf, len, "max_reg_allowed_power", + htt_stats_buf->max_reg_allowed_power, + ATH12K_HTT_STATS_MAX_CHAINS, "\n"); + len += print_array_to_buf(buf, len, "max_reg_allowed_power_6ghz", + htt_stats_buf->max_reg_allowed_power_6ghz, + ATH12K_HTT_STATS_MAX_CHAINS, "\n"); + len += print_array_to_buf(buf, len, "sub_band_cfreq", + htt_stats_buf->sub_band_cfreq, + ATH12K_HTT_MAX_CH_PWR_INFO_SIZE, "\n"); + len += print_array_to_buf(buf, len, "sub_band_txpower", + htt_stats_buf->sub_band_txpower, + ATH12K_HTT_MAX_CH_PWR_INFO_SIZE, "\n\n"); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_soc_txrx_stats_common_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_t2h_soc_txrx_stats_common_tlv *htt_stats_buf = tag_buf; + u64 drop_count; + u32 len = stats_req->buf_len; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u8 *buf = stats_req->buf; + + if (tag_len < sizeof(*htt_stats_buf)) + return; + + drop_count = ath12k_le32hilo_to_u64(htt_stats_buf->inv_peers_msdu_drop_count_hi, + htt_stats_buf->inv_peers_msdu_drop_count_lo); + + len += scnprintf(buf + len, buf_len - len, "HTT_SOC_COMMON_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "soc_drop_count = %llu\n\n", + drop_count); + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_tx_per_rate_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_tx_per_rate_stats_tlv *stats_buf = tag_buf; + u32 len = stats_req->buf_len; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 ru_size_cnt = 0; + u32 rc_mode, ru_type; + u8 *buf = stats_req->buf, i; + const char *mode_prefix; + + if (tag_len < sizeof(*stats_buf)) + return; + + rc_mode = le32_to_cpu(stats_buf->rc_mode); + ru_type = le32_to_cpu(stats_buf->ru_type); + + switch (rc_mode) { + case ATH12K_HTT_STATS_RC_MODE_DLSU: + len += scnprintf(buf + len, buf_len - len, "HTT_TX_PER_STATS:\n"); + len += scnprintf(buf + len, buf_len - len, "\nPER_STATS_SU:\n"); + mode_prefix = "su"; + break; + case ATH12K_HTT_STATS_RC_MODE_DLMUMIMO: + len += scnprintf(buf + len, buf_len - len, "\nPER_STATS_DL_MUMIMO:\n"); + mode_prefix = "mu"; + break; + case ATH12K_HTT_STATS_RC_MODE_DLOFDMA: + len += scnprintf(buf + len, buf_len - len, "\nPER_STATS_DL_OFDMA:\n"); + mode_prefix = "ofdma"; + if (ru_type == ATH12K_HTT_STATS_RU_TYPE_SINGLE_RU_ONLY) + ru_size_cnt = ATH12K_HTT_TX_RX_PDEV_STATS_NUM_AX_RU_SIZE_CNTRS; + else if (ru_type == ATH12K_HTT_STATS_RU_TYPE_SINGLE_AND_MULTI_RU) + ru_size_cnt = ATH12K_HTT_TX_RX_PDEV_NUM_BE_RU_SIZE_CNTRS; + break; + case ATH12K_HTT_STATS_RC_MODE_ULMUMIMO: + len += scnprintf(buf + len, buf_len - len, "HTT_RX_PER_STATS:\n"); + len += scnprintf(buf + len, buf_len - len, "\nPER_STATS_UL_MUMIMO:\n"); + mode_prefix = "ulmu"; + break; + case ATH12K_HTT_STATS_RC_MODE_ULOFDMA: + len += scnprintf(buf + len, buf_len - len, "\nPER_STATS_UL_OFDMA:\n"); + mode_prefix = "ulofdma"; + if (ru_type == ATH12K_HTT_STATS_RU_TYPE_SINGLE_RU_ONLY) + ru_size_cnt = ATH12K_HTT_TX_RX_PDEV_STATS_NUM_AX_RU_SIZE_CNTRS; + else if (ru_type == ATH12K_HTT_STATS_RU_TYPE_SINGLE_AND_MULTI_RU) + ru_size_cnt = ATH12K_HTT_TX_RX_PDEV_NUM_BE_RU_SIZE_CNTRS; + break; + default: + return; + } + + len += scnprintf(buf + len, buf_len - len, "\nPER per BW:\n"); + if (rc_mode == ATH12K_HTT_STATS_RC_MODE_ULOFDMA || + rc_mode == ATH12K_HTT_STATS_RC_MODE_ULMUMIMO) + len += scnprintf(buf + len, buf_len - len, "data_ppdus_%s = ", + mode_prefix); + else + len += scnprintf(buf + len, buf_len - len, "ppdus_tried_%s = ", + mode_prefix); + for (i = 0; i < ATH12K_HTT_TX_PDEV_STATS_NUM_BW_CNTRS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i, + le32_to_cpu(stats_buf->per_bw[i].ppdus_tried)); + len += scnprintf(buf + len, buf_len - len, " %u:%u\n", i, + le32_to_cpu(stats_buf->per_bw320.ppdus_tried)); + + if (rc_mode == ATH12K_HTT_STATS_RC_MODE_ULOFDMA || + rc_mode == ATH12K_HTT_STATS_RC_MODE_ULMUMIMO) + len += scnprintf(buf + len, buf_len - len, "non_data_ppdus_%s = ", + mode_prefix); + else + len += scnprintf(buf + len, buf_len - len, "ppdus_ack_failed_%s = ", + mode_prefix); + for (i = 0; i < ATH12K_HTT_TX_PDEV_STATS_NUM_BW_CNTRS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i, + le32_to_cpu(stats_buf->per_bw[i].ppdus_ack_failed)); + len += scnprintf(buf + len, buf_len - len, " %u:%u\n", i, + le32_to_cpu(stats_buf->per_bw320.ppdus_ack_failed)); + + len += scnprintf(buf + len, buf_len - len, "mpdus_tried_%s = ", mode_prefix); + for (i = 0; i < ATH12K_HTT_TX_PDEV_STATS_NUM_BW_CNTRS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i, + le32_to_cpu(stats_buf->per_bw[i].mpdus_tried)); + len += scnprintf(buf + len, buf_len - len, " %u:%u\n", i, + le32_to_cpu(stats_buf->per_bw320.mpdus_tried)); + + len += scnprintf(buf + len, buf_len - len, "mpdus_failed_%s = ", mode_prefix); + for (i = 0; i < ATH12K_HTT_TX_PDEV_STATS_NUM_BW_CNTRS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u", i, + le32_to_cpu(stats_buf->per_bw[i].mpdus_failed)); + len += scnprintf(buf + len, buf_len - len, " %u:%u\n", i, + le32_to_cpu(stats_buf->per_bw320.mpdus_failed)); + + len += scnprintf(buf + len, buf_len - len, "\nPER per NSS:\n"); + if (rc_mode == ATH12K_HTT_STATS_RC_MODE_ULOFDMA || + rc_mode == ATH12K_HTT_STATS_RC_MODE_ULMUMIMO) + len += scnprintf(buf + len, buf_len - len, "data_ppdus_%s = ", + mode_prefix); + else + len += scnprintf(buf + len, buf_len - len, "ppdus_tried_%s = ", + mode_prefix); + for (i = 0; i < ATH12K_HTT_PDEV_STAT_NUM_SPATIAL_STREAMS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i + 1, + le32_to_cpu(stats_buf->per_nss[i].ppdus_tried)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + if (rc_mode == ATH12K_HTT_STATS_RC_MODE_ULOFDMA || + rc_mode == ATH12K_HTT_STATS_RC_MODE_ULMUMIMO) + len += scnprintf(buf + len, buf_len - len, "non_data_ppdus_%s = ", + mode_prefix); + else + len += scnprintf(buf + len, buf_len - len, "ppdus_ack_failed_%s = ", + mode_prefix); + for (i = 0; i < ATH12K_HTT_PDEV_STAT_NUM_SPATIAL_STREAMS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i + 1, + le32_to_cpu(stats_buf->per_nss[i].ppdus_ack_failed)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + len += scnprintf(buf + len, buf_len - len, "mpdus_tried_%s = ", mode_prefix); + for (i = 0; i < ATH12K_HTT_PDEV_STAT_NUM_SPATIAL_STREAMS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i + 1, + le32_to_cpu(stats_buf->per_nss[i].mpdus_tried)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + len += scnprintf(buf + len, buf_len - len, "mpdus_failed_%s = ", mode_prefix); + for (i = 0; i < ATH12K_HTT_PDEV_STAT_NUM_SPATIAL_STREAMS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i + 1, + le32_to_cpu(stats_buf->per_nss[i].mpdus_failed)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + len += scnprintf(buf + len, buf_len - len, "\nPER per MCS:\n"); + if (rc_mode == ATH12K_HTT_STATS_RC_MODE_ULOFDMA || + rc_mode == ATH12K_HTT_STATS_RC_MODE_ULMUMIMO) + len += scnprintf(buf + len, buf_len - len, "data_ppdus_%s = ", + mode_prefix); + else + len += scnprintf(buf + len, buf_len - len, "ppdus_tried_%s = ", + mode_prefix); + for (i = 0; i < ATH12K_HTT_TXBF_RATE_STAT_NUM_MCS_CNTRS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i, + le32_to_cpu(stats_buf->per_mcs[i].ppdus_tried)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + if (rc_mode == ATH12K_HTT_STATS_RC_MODE_ULOFDMA || + rc_mode == ATH12K_HTT_STATS_RC_MODE_ULMUMIMO) + len += scnprintf(buf + len, buf_len - len, "non_data_ppdus_%s = ", + mode_prefix); + else + len += scnprintf(buf + len, buf_len - len, "ppdus_ack_failed_%s = ", + mode_prefix); + for (i = 0; i < ATH12K_HTT_TXBF_RATE_STAT_NUM_MCS_CNTRS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i, + le32_to_cpu(stats_buf->per_mcs[i].ppdus_ack_failed)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + len += scnprintf(buf + len, buf_len - len, "mpdus_tried_%s = ", mode_prefix); + for (i = 0; i < ATH12K_HTT_TXBF_RATE_STAT_NUM_MCS_CNTRS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i, + le32_to_cpu(stats_buf->per_mcs[i].mpdus_tried)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + len += scnprintf(buf + len, buf_len - len, "mpdus_failed_%s = ", mode_prefix); + for (i = 0; i < ATH12K_HTT_TXBF_RATE_STAT_NUM_MCS_CNTRS; i++) + len += scnprintf(buf + len, buf_len - len, " %u:%u ", i, + le32_to_cpu(stats_buf->per_mcs[i].mpdus_failed)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + if ((rc_mode == ATH12K_HTT_STATS_RC_MODE_DLOFDMA || + rc_mode == ATH12K_HTT_STATS_RC_MODE_ULOFDMA) && + ru_type != ATH12K_HTT_STATS_RU_TYPE_INVALID) { + len += scnprintf(buf + len, buf_len - len, "\nPER per RU:\n"); + + if (rc_mode == ATH12K_HTT_STATS_RC_MODE_ULOFDMA) + len += scnprintf(buf + len, buf_len - len, "data_ppdus_%s = ", + mode_prefix); + else + len += scnprintf(buf + len, buf_len - len, "ppdus_tried_%s = ", + mode_prefix); + for (i = 0; i < ru_size_cnt; i++) + len += scnprintf(buf + len, buf_len - len, " %s:%u ", + ath12k_tx_ru_size_to_str(ru_type, i), + le32_to_cpu(stats_buf->ru[i].ppdus_tried)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + if (rc_mode == ATH12K_HTT_STATS_RC_MODE_ULOFDMA) + len += scnprintf(buf + len, buf_len - len, + "non_data_ppdus_%s = ", mode_prefix); + else + len += scnprintf(buf + len, buf_len - len, + "ppdus_ack_failed_%s = ", mode_prefix); + for (i = 0; i < ru_size_cnt; i++) + len += scnprintf(buf + len, buf_len - len, " %s:%u ", + ath12k_tx_ru_size_to_str(ru_type, i), + le32_to_cpu(stats_buf->ru[i].ppdus_ack_failed)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + len += scnprintf(buf + len, buf_len - len, "mpdus_tried_%s = ", + mode_prefix); + for (i = 0; i < ru_size_cnt; i++) + len += scnprintf(buf + len, buf_len - len, " %s:%u ", + ath12k_tx_ru_size_to_str(ru_type, i), + le32_to_cpu(stats_buf->ru[i].mpdus_tried)); + len += scnprintf(buf + len, buf_len - len, "\n"); + + len += scnprintf(buf + len, buf_len - len, "mpdus_failed_%s = ", + mode_prefix); + for (i = 0; i < ru_size_cnt; i++) + len += scnprintf(buf + len, buf_len - len, " %s:%u ", + ath12k_tx_ru_size_to_str(ru_type, i), + le32_to_cpu(stats_buf->ru[i].mpdus_failed)); + len += scnprintf(buf + len, buf_len - len, "\n\n"); + } + + if (rc_mode == ATH12K_HTT_STATS_RC_MODE_DLMUMIMO) { + len += scnprintf(buf + len, buf_len - len, "\nlast_probed_bw = %u\n", + le32_to_cpu(stats_buf->last_probed_bw)); + len += scnprintf(buf + len, buf_len - len, "last_probed_nss = %u\n", + le32_to_cpu(stats_buf->last_probed_nss)); + len += scnprintf(buf + len, buf_len - len, "last_probed_mcs = %u\n", + le32_to_cpu(stats_buf->last_probed_mcs)); + len += print_array_to_buf(buf, len, "MU Probe count per RC MODE", + stats_buf->probe_cnt, + ATH12K_HTT_RC_MODE_2D_COUNT, "\n\n"); + } + + stats_req->buf_len = len; +} + +static void +ath12k_htt_print_ast_entry_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_ast_entry_tlv *htt_stats_buf = tag_buf; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 len = stats_req->buf_len; + u8 *buf = stats_req->buf; + u32 mac_addr_l32; + u32 mac_addr_h16; + u32 ast_info; + + if (tag_len < sizeof(*htt_stats_buf)) + return; + + mac_addr_l32 = le32_to_cpu(htt_stats_buf->mac_addr.mac_addr_l32); + mac_addr_h16 = le32_to_cpu(htt_stats_buf->mac_addr.mac_addr_h16); + ast_info = le32_to_cpu(htt_stats_buf->info); + + len += scnprintf(buf + len, buf_len - len, "HTT_AST_ENTRY_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "ast_index = %u\n", + le32_to_cpu(htt_stats_buf->ast_index)); + len += scnprintf(buf + len, buf_len - len, + "mac_addr = %02x:%02x:%02x:%02x:%02x:%02x\n", + u32_get_bits(mac_addr_l32, ATH12K_HTT_MAC_ADDR_L32_0), + u32_get_bits(mac_addr_l32, ATH12K_HTT_MAC_ADDR_L32_1), + u32_get_bits(mac_addr_l32, ATH12K_HTT_MAC_ADDR_L32_2), + u32_get_bits(mac_addr_l32, ATH12K_HTT_MAC_ADDR_L32_3), + u32_get_bits(mac_addr_h16, ATH12K_HTT_MAC_ADDR_H16_0), + u32_get_bits(mac_addr_h16, ATH12K_HTT_MAC_ADDR_H16_1)); + + len += scnprintf(buf + len, buf_len - len, "sw_peer_id = %u\n", + le32_to_cpu(htt_stats_buf->sw_peer_id)); + len += scnprintf(buf + len, buf_len - len, "pdev_id = %u\n", + u32_get_bits(ast_info, ATH12K_HTT_AST_PDEV_ID_INFO)); + len += scnprintf(buf + len, buf_len - len, "vdev_id = %u\n", + u32_get_bits(ast_info, ATH12K_HTT_AST_VDEV_ID_INFO)); + len += scnprintf(buf + len, buf_len - len, "next_hop = %u\n", + u32_get_bits(ast_info, ATH12K_HTT_AST_NEXT_HOP_INFO)); + len += scnprintf(buf + len, buf_len - len, "mcast = %u\n", + u32_get_bits(ast_info, ATH12K_HTT_AST_MCAST_INFO)); + len += scnprintf(buf + len, buf_len - len, "monitor_direct = %u\n", + u32_get_bits(ast_info, ATH12K_HTT_AST_MONITOR_DIRECT_INFO)); + len += scnprintf(buf + len, buf_len - len, "mesh_sta = %u\n", + u32_get_bits(ast_info, ATH12K_HTT_AST_MESH_STA_INFO)); + len += scnprintf(buf + len, buf_len - len, "mec = %u\n", + u32_get_bits(ast_info, ATH12K_HTT_AST_MEC_INFO)); + len += scnprintf(buf + len, buf_len - len, "intra_bss = %u\n\n", + u32_get_bits(ast_info, ATH12K_HTT_AST_INTRA_BSS_INFO)); + + stats_req->buf_len = len; +} + +static const char* +ath12k_htt_get_punct_dir_type_str(enum ath12k_htt_stats_direction direction) +{ + switch (direction) { + case ATH12K_HTT_STATS_DIRECTION_TX: + return "tx"; + case ATH12K_HTT_STATS_DIRECTION_RX: + return "rx"; + default: + return "unknown"; + } +} + +static const char* +ath12k_htt_get_punct_ppdu_type_str(enum ath12k_htt_stats_ppdu_type ppdu_type) +{ + switch (ppdu_type) { + case ATH12K_HTT_STATS_PPDU_TYPE_MODE_SU: + return "su"; + case ATH12K_HTT_STATS_PPDU_TYPE_DL_MU_MIMO: + return "dl_mu_mimo"; + case ATH12K_HTT_STATS_PPDU_TYPE_UL_MU_MIMO: + return "ul_mu_mimo"; + case ATH12K_HTT_STATS_PPDU_TYPE_DL_MU_OFDMA: + return "dl_mu_ofdma"; + case ATH12K_HTT_STATS_PPDU_TYPE_UL_MU_OFDMA: + return "ul_mu_ofdma"; + default: + return "unknown"; + } +} + +static const char* +ath12k_htt_get_punct_pream_type_str(enum ath12k_htt_stats_param_type pream_type) +{ + switch (pream_type) { + case ATH12K_HTT_STATS_PREAM_OFDM: + return "ofdm"; + case ATH12K_HTT_STATS_PREAM_CCK: + return "cck"; + case ATH12K_HTT_STATS_PREAM_HT: + return "ht"; + case ATH12K_HTT_STATS_PREAM_VHT: + return "ac"; + case ATH12K_HTT_STATS_PREAM_HE: + return "ax"; + case ATH12K_HTT_STATS_PREAM_EHT: + return "be"; + default: + return "unknown"; + } +} + +static void +ath12k_htt_print_puncture_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_pdev_puncture_stats_tlv *stats_buf = tag_buf; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 len = stats_req->buf_len; + u8 *buf = stats_req->buf; + const char *direction; + const char *ppdu_type; + const char *preamble; + u32 mac_id__word; + u32 subband_limit; + u8 i; + + if (tag_len < sizeof(*stats_buf)) + return; + + mac_id__word = le32_to_cpu(stats_buf->mac_id__word); + subband_limit = min(le32_to_cpu(stats_buf->subband_cnt), + ATH12K_HTT_PUNCT_STATS_MAX_SUBBAND_CNT); + + direction = ath12k_htt_get_punct_dir_type_str(le32_to_cpu(stats_buf->direction)); + ppdu_type = ath12k_htt_get_punct_ppdu_type_str(le32_to_cpu(stats_buf->ppdu_type)); + preamble = ath12k_htt_get_punct_pream_type_str(le32_to_cpu(stats_buf->preamble)); + + len += scnprintf(buf + len, buf_len - len, "HTT_PDEV_PUNCTURE_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "mac_id = %u\n", + u32_get_bits(mac_id__word, ATH12K_HTT_STATS_MAC_ID)); + len += scnprintf(buf + len, buf_len - len, + "%s_%s_%s_last_used_pattern_mask = 0x%08x\n", + direction, preamble, ppdu_type, + le32_to_cpu(stats_buf->last_used_pattern_mask)); + + for (i = 0; i < subband_limit; i++) { + len += scnprintf(buf + len, buf_len - len, + "%s_%s_%s_num_subbands_used_cnt_%02d = %u\n", + direction, preamble, ppdu_type, i + 1, + le32_to_cpu(stats_buf->num_subbands_used_cnt[i])); + } + len += scnprintf(buf + len, buf_len - len, "\n"); + + stats_req->buf_len = len; +} + static void ath12k_htt_print_dmac_reset_stats_tlv(const void *tag_buf, u16 tag_len, struct debug_htt_stats_req *stats_req) @@ -2561,7 +3639,6 @@ ath12k_htt_print_dmac_reset_stats_tlv(const void *tag_buf, u16 tag_len, time = ath12k_le32hilo_to_u64(htt_stats_buf->reset_time_hi_ms, htt_stats_buf->reset_time_lo_ms); len += scnprintf(buf + len, buf_len - len, "reset_time_ms = %llu\n", time); - time = ath12k_le32hilo_to_u64(htt_stats_buf->disengage_time_hi_ms, htt_stats_buf->disengage_time_lo_ms); len += scnprintf(buf + len, buf_len - len, "disengage_time_ms = %llu\n", time); @@ -2680,7 +3757,7 @@ ath12k_htt_print_tx_pdev_rate_stats_be_ofdma_tlv(const void *tag_buf, u16 tag_le len += scnprintf(buf + len, buf_len - len, "\n"); len += print_array_to_buf_index(buf, len, "be_ofdma_tx_nss = ", 1, htt_stats_buf->be_ofdma_tx_nss, - ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS, + ATH12K_HTT_PDEV_STAT_NUM_SPATIAL_STREAMS, "\n"); len += print_array_to_buf(buf, len, "be_ofdma_tx_bw", htt_stats_buf->be_ofdma_tx_bw, @@ -2696,6 +3773,45 @@ ath12k_htt_print_tx_pdev_rate_stats_be_ofdma_tlv(const void *tag_buf, u16 tag_le stats_req->buf_len = len; } +static void +ath12k_htt_print_pdev_mbssid_ctrl_frame_stats_tlv(const void *tag_buf, u16 tag_len, + struct debug_htt_stats_req *stats_req) +{ + const struct ath12k_htt_pdev_mbssid_ctrl_frame_tlv *htt_stats_buf = tag_buf; + u8 *buf = stats_req->buf; + u32 len = stats_req->buf_len; + u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE; + u32 mac_id_word; + + if (tag_len < sizeof(*htt_stats_buf)) + return; + + mac_id_word = le32_to_cpu(htt_stats_buf->mac_id__word); + + len += scnprintf(buf + len, buf_len - len, "HTT_MBSSID_CTRL_FRAME_STATS_TLV:\n"); + len += scnprintf(buf + len, buf_len - len, "mac_id = %u\n", + u32_get_bits(mac_id_word, ATH12K_HTT_STATS_MAC_ID)); + len += scnprintf(buf + len, buf_len - len, "basic_trigger_across_bss = %u\n", + le32_to_cpu(htt_stats_buf->basic_trigger_across_bss)); + len += scnprintf(buf + len, buf_len - len, "basic_trigger_within_bss = %u\n", + le32_to_cpu(htt_stats_buf->basic_trigger_within_bss)); + len += scnprintf(buf + len, buf_len - len, "bsr_trigger_across_bss = %u\n", + le32_to_cpu(htt_stats_buf->bsr_trigger_across_bss)); + len += scnprintf(buf + len, buf_len - len, "bsr_trigger_within_bss = %u\n", + le32_to_cpu(htt_stats_buf->bsr_trigger_within_bss)); + len += scnprintf(buf + len, buf_len - len, "mu_rts_across_bss = %u\n", + le32_to_cpu(htt_stats_buf->mu_rts_across_bss)); + len += scnprintf(buf + len, buf_len - len, "mu_rts_within_bss = %u\n", + le32_to_cpu(htt_stats_buf->mu_rts_within_bss)); + len += scnprintf(buf + len, buf_len - len, "ul_mumimo_trigger_across_bss = %u\n", + le32_to_cpu(htt_stats_buf->ul_mumimo_trigger_across_bss)); + len += scnprintf(buf + len, buf_len - len, + "ul_mumimo_trigger_within_bss = %u\n\n", + le32_to_cpu(htt_stats_buf->ul_mumimo_trigger_within_bss)); + + stats_req->buf_len = len; +} + static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab, u16 tag, u16 len, const void *tag_buf, void *user_data) @@ -2869,6 +3985,55 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab, case HTT_STATS_PDEV_OBSS_PD_TAG: ath12k_htt_print_pdev_obss_pd_stats_tlv(tag_buf, len, stats_req); break; + case HTT_STATS_PDEV_TX_RATE_TXBF_STATS_TAG: + ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_TXBF_OFDMA_AX_NDPA_STATS_TAG: + ath12k_htt_print_txbf_ofdma_ax_ndpa_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_TXBF_OFDMA_AX_NDP_STATS_TAG: + ath12k_htt_print_txbf_ofdma_ax_ndp_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_TXBF_OFDMA_AX_BRP_STATS_TAG: + ath12k_htt_print_txbf_ofdma_ax_brp_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_TXBF_OFDMA_AX_STEER_STATS_TAG: + ath12k_htt_print_txbf_ofdma_ax_steer_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_TXBF_OFDMA_AX_STEER_MPDU_STATS_TAG: + ath12k_htt_print_txbf_ofdma_ax_steer_mpdu_stats_tlv(tag_buf, len, + stats_req); + break; + case HTT_STATS_DLPAGER_STATS_TAG: + ath12k_htt_print_dlpager_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_PHY_STATS_TAG: + ath12k_htt_print_phy_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_PHY_COUNTERS_TAG: + ath12k_htt_print_phy_counters_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_PHY_RESET_STATS_TAG: + ath12k_htt_print_phy_reset_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_PHY_RESET_COUNTERS_TAG: + ath12k_htt_print_phy_reset_counters_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_PHY_TPC_STATS_TAG: + ath12k_htt_print_phy_tpc_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_SOC_TXRX_STATS_COMMON_TAG: + ath12k_htt_print_soc_txrx_stats_common_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_PER_RATE_STATS_TAG: + ath12k_htt_print_tx_per_rate_stats_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_AST_ENTRY_TAG: + ath12k_htt_print_ast_entry_tlv(tag_buf, len, stats_req); + break; + case HTT_STATS_PDEV_PUNCTURE_STATS_TAG: + ath12k_htt_print_puncture_stats_tlv(tag_buf, len, stats_req); + break; case HTT_STATS_DMAC_RESET_STATS_TAG: ath12k_htt_print_dmac_reset_stats_tlv(tag_buf, len, stats_req); break; @@ -2878,6 +4043,10 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab, case HTT_STATS_TX_PDEV_RATE_STATS_BE_OFDMA_TAG: ath12k_htt_print_tx_pdev_rate_stats_be_ofdma_tlv(tag_buf, len, stats_req); break; + case HTT_STATS_PDEV_MBSSID_CTRL_FRAME_STATS_TAG: + ath12k_htt_print_pdev_mbssid_ctrl_frame_stats_tlv(tag_buf, len, + stats_req); + break; default: break; } diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h index ac86cab234ec..4b59976fbc35 100644 --- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h +++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h @@ -135,9 +135,18 @@ enum ath12k_dbg_htt_ext_stats_type { ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_MU = 17, ATH12K_DBG_HTT_EXT_STATS_PDEV_CCA_STATS = 19, ATH12K_DBG_HTT_EXT_STATS_PDEV_OBSS_PD_STATS = 23, + ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE_TXBF = 31, + ATH12K_DBG_HTT_EXT_STATS_TXBF_OFDMA = 32, + ATH12K_DBG_HTT_EXT_STATS_DLPAGER_STATS = 36, + ATH12K_DBG_HTT_EXT_PHY_COUNTERS_AND_PHY_STATS = 37, + ATH12K_DBG_HTT_EXT_VDEVS_TXRX_STATS = 38, + ATH12K_DBG_HTT_EXT_PDEV_PER_STATS = 40, + ATH12K_DBG_HTT_EXT_AST_ENTRIES = 41, ATH12K_DBG_HTT_EXT_STATS_SOC_ERROR = 45, + ATH12K_DBG_HTT_DBG_PDEV_PUNCTURE_STATS = 46, ATH12K_DBG_HTT_EXT_STATS_PDEV_SCHED_ALGO = 49, ATH12K_DBG_HTT_EXT_STATS_MANDATORY_MUOFDMA = 51, + ATH12K_DGB_HTT_EXT_STATS_PDEV_MBSSID_CTRL_FRAME = 54, /* keep this last */ ATH12K_DBG_HTT_NUM_EXT_STATS, @@ -192,16 +201,33 @@ enum ath12k_dbg_htt_tlv_tag { HTT_STATS_HW_WAR_TAG = 89, HTT_STATS_SCHED_TXQ_SUPERCYCLE_TRIGGER_TAG = 100, HTT_STATS_PDEV_CTRL_PATH_TX_STATS_TAG = 102, + HTT_STATS_PDEV_TX_RATE_TXBF_STATS_TAG = 108, HTT_STATS_TX_SELFGEN_AC_SCHED_STATUS_STATS_TAG = 111, HTT_STATS_TX_SELFGEN_AX_SCHED_STATUS_STATS_TAG = 112, + HTT_STATS_DLPAGER_STATS_TAG = 120, + HTT_STATS_PHY_COUNTERS_TAG = 121, + HTT_STATS_PHY_STATS_TAG = 122, + HTT_STATS_PHY_RESET_COUNTERS_TAG = 123, + HTT_STATS_PHY_RESET_STATS_TAG = 124, + HTT_STATS_SOC_TXRX_STATS_COMMON_TAG = 125, + HTT_STATS_PER_RATE_STATS_TAG = 128, HTT_STATS_MU_PPDU_DIST_TAG = 129, HTT_STATS_TX_PDEV_MUMIMO_GRP_STATS_TAG = 130, + HTT_STATS_AST_ENTRY_TAG = 132, HTT_STATS_TX_PDEV_RATE_STATS_BE_OFDMA_TAG = 135, HTT_STATS_TX_SELFGEN_BE_ERR_STATS_TAG = 137, HTT_STATS_TX_SELFGEN_BE_STATS_TAG = 138, HTT_STATS_TX_SELFGEN_BE_SCHED_STATUS_STATS_TAG = 139, + HTT_STATS_TXBF_OFDMA_AX_NDPA_STATS_TAG = 147, + HTT_STATS_TXBF_OFDMA_AX_NDP_STATS_TAG = 148, + HTT_STATS_TXBF_OFDMA_AX_BRP_STATS_TAG = 149, + HTT_STATS_TXBF_OFDMA_AX_STEER_STATS_TAG = 150, HTT_STATS_DMAC_RESET_STATS_TAG = 155, + HTT_STATS_PHY_TPC_STATS_TAG = 157, + HTT_STATS_PDEV_PUNCTURE_STATS_TAG = 158, HTT_STATS_PDEV_SCHED_ALGO_OFDMA_STATS_TAG = 165, + HTT_STATS_TXBF_OFDMA_AX_STEER_MPDU_STATS_TAG = 172, + HTT_STATS_PDEV_MBSSID_CTRL_FRAME_STATS_TAG = 176, HTT_STATS_MAX_TAG, }; @@ -1054,6 +1080,275 @@ struct ath12k_htt_pdev_obss_pd_stats_tlv { __le32 num_sr_ppdu_abort_flush_cnt; } __packed; +#define ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS 14 +#define ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_OFDM_STATS 8 +#define ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS 8 +#define ATH12K_HTT_TXBF_NUM_BW_CNTRS 5 +#define ATH12K_HTT_TXBF_NUM_REDUCED_CHAN_TYPES 2 + +struct ath12k_htt_pdev_txrate_txbf_stats_tlv { + __le32 tx_su_txbf_mcs[ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS]; + __le32 tx_su_ibf_mcs[ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS]; + __le32 tx_su_ol_mcs[ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS]; + __le32 tx_su_txbf_nss[ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS]; + __le32 tx_su_ibf_nss[ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS]; + __le32 tx_su_ol_nss[ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS]; + __le32 tx_su_txbf_bw[ATH12K_HTT_TXBF_NUM_BW_CNTRS]; + __le32 tx_su_ibf_bw[ATH12K_HTT_TXBF_NUM_BW_CNTRS]; + __le32 tx_su_ol_bw[ATH12K_HTT_TXBF_NUM_BW_CNTRS]; + __le32 tx_legacy_ofdm_rate[ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_OFDM_STATS]; + __le32 txbf[ATH12K_HTT_TXBF_NUM_REDUCED_CHAN_TYPES][ATH12K_HTT_TXBF_NUM_BW_CNTRS]; + __le32 ibf[ATH12K_HTT_TXBF_NUM_REDUCED_CHAN_TYPES][ATH12K_HTT_TXBF_NUM_BW_CNTRS]; + __le32 ol[ATH12K_HTT_TXBF_NUM_REDUCED_CHAN_TYPES][ATH12K_HTT_TXBF_NUM_BW_CNTRS]; + __le32 txbf_flag_set_mu_mode; + __le32 txbf_flag_set_final_status; + __le32 txbf_flag_not_set_verified_txbf_mode; + __le32 txbf_flag_not_set_disable_p2p_access; + __le32 txbf_flag_not_set_max_nss_in_he160; + __le32 txbf_flag_not_set_disable_uldlofdma; + __le32 txbf_flag_not_set_mcs_threshold_val; + __le32 txbf_flag_not_set_final_status; +} __packed; + +struct ath12k_htt_txbf_ofdma_ax_ndpa_stats_elem_t { + __le32 ax_ofdma_ndpa_queued; + __le32 ax_ofdma_ndpa_tried; + __le32 ax_ofdma_ndpa_flush; + __le32 ax_ofdma_ndpa_err; +} __packed; + +struct ath12k_htt_txbf_ofdma_ax_ndpa_stats_tlv { + __le32 num_elems_ax_ndpa_arr; + __le32 arr_elem_size_ax_ndpa; + DECLARE_FLEX_ARRAY(struct ath12k_htt_txbf_ofdma_ax_ndpa_stats_elem_t, ax_ndpa); +} __packed; + +struct ath12k_htt_txbf_ofdma_ax_ndp_stats_elem_t { + __le32 ax_ofdma_ndp_queued; + __le32 ax_ofdma_ndp_tried; + __le32 ax_ofdma_ndp_flush; + __le32 ax_ofdma_ndp_err; +} __packed; + +struct ath12k_htt_txbf_ofdma_ax_ndp_stats_tlv { + __le32 num_elems_ax_ndp_arr; + __le32 arr_elem_size_ax_ndp; + DECLARE_FLEX_ARRAY(struct ath12k_htt_txbf_ofdma_ax_ndp_stats_elem_t, ax_ndp); +} __packed; + +struct ath12k_htt_txbf_ofdma_ax_brp_stats_elem_t { + __le32 ax_ofdma_brp_queued; + __le32 ax_ofdma_brp_tried; + __le32 ax_ofdma_brp_flushed; + __le32 ax_ofdma_brp_err; + __le32 ax_ofdma_num_cbf_rcvd; +} __packed; + +struct ath12k_htt_txbf_ofdma_ax_brp_stats_tlv { + __le32 num_elems_ax_brp_arr; + __le32 arr_elem_size_ax_brp; + DECLARE_FLEX_ARRAY(struct ath12k_htt_txbf_ofdma_ax_brp_stats_elem_t, ax_brp); +} __packed; + +struct ath12k_htt_txbf_ofdma_ax_steer_stats_elem_t { + __le32 num_ppdu_steer; + __le32 num_ppdu_ol; + __le32 num_usr_prefetch; + __le32 num_usr_sound; + __le32 num_usr_force_sound; +} __packed; + +struct ath12k_htt_txbf_ofdma_ax_steer_stats_tlv { + __le32 num_elems_ax_steer_arr; + __le32 arr_elem_size_ax_steer; + DECLARE_FLEX_ARRAY(struct ath12k_htt_txbf_ofdma_ax_steer_stats_elem_t, ax_steer); +} __packed; + +struct ath12k_htt_txbf_ofdma_ax_steer_mpdu_stats_tlv { + __le32 ax_ofdma_rbo_steer_mpdus_tried; + __le32 ax_ofdma_rbo_steer_mpdus_failed; + __le32 ax_ofdma_sifs_steer_mpdus_tried; + __le32 ax_ofdma_sifs_steer_mpdus_failed; +} __packed; + +enum ath12k_htt_stats_page_lock_state { + ATH12K_HTT_STATS_PAGE_LOCKED = 0, + ATH12K_HTT_STATS_PAGE_UNLOCKED = 1, + ATH12K_NUM_PG_LOCK_STATE +}; + +#define ATH12K_PAGER_MAX 10 + +#define ATH12K_HTT_DLPAGER_ASYNC_LOCK_PG_CNT_INFO0 GENMASK(7, 0) +#define ATH12K_HTT_DLPAGER_SYNC_LOCK_PG_CNT_INFO0 GENMASK(15, 8) +#define ATH12K_HTT_DLPAGER_TOTAL_LOCK_PAGES_INFO1 GENMASK(15, 0) +#define ATH12K_HTT_DLPAGER_TOTAL_FREE_PAGES_INFO1 GENMASK(31, 16) +#define ATH12K_HTT_DLPAGER_TOTAL_LOCK_PAGES_INFO2 GENMASK(15, 0) +#define ATH12K_HTT_DLPAGER_TOTAL_FREE_PAGES_INFO2 GENMASK(31, 16) + +struct ath12k_htt_pgs_info { + __le32 page_num; + __le32 num_pgs; + __le32 ts_lsb; + __le32 ts_msb; +} __packed; + +struct ath12k_htt_dl_pager_stats_tlv { + __le32 info0; + __le32 info1; + __le32 info2; + struct ath12k_htt_pgs_info pgs_info[ATH12K_NUM_PG_LOCK_STATE][ATH12K_PAGER_MAX]; +} __packed; + +#define ATH12K_HTT_STATS_MAX_CHAINS 8 +#define ATH12K_HTT_MAX_RX_PKT_CNT 8 +#define ATH12K_HTT_MAX_RX_PKT_CRC_PASS_CNT 8 +#define ATH12K_HTT_MAX_PER_BLK_ERR_CNT 20 +#define ATH12K_HTT_MAX_RX_OTA_ERR_CNT 14 +#define ATH12K_HTT_MAX_CH_PWR_INFO_SIZE 16 + +struct ath12k_htt_phy_stats_tlv { + a_sle32 nf_chain[ATH12K_HTT_STATS_MAX_CHAINS]; + __le32 false_radar_cnt; + __le32 radar_cs_cnt; + a_sle32 ani_level; + __le32 fw_run_time; + a_sle32 runtime_nf_chain[ATH12K_HTT_STATS_MAX_CHAINS]; +} __packed; + +struct ath12k_htt_phy_counters_tlv { + __le32 rx_ofdma_timing_err_cnt; + __le32 rx_cck_fail_cnt; + __le32 mactx_abort_cnt; + __le32 macrx_abort_cnt; + __le32 phytx_abort_cnt; + __le32 phyrx_abort_cnt; + __le32 phyrx_defer_abort_cnt; + __le32 rx_gain_adj_lstf_event_cnt; + __le32 rx_gain_adj_non_legacy_cnt; + __le32 rx_pkt_cnt[ATH12K_HTT_MAX_RX_PKT_CNT]; + __le32 rx_pkt_crc_pass_cnt[ATH12K_HTT_MAX_RX_PKT_CRC_PASS_CNT]; + __le32 per_blk_err_cnt[ATH12K_HTT_MAX_PER_BLK_ERR_CNT]; + __le32 rx_ota_err_cnt[ATH12K_HTT_MAX_RX_OTA_ERR_CNT]; +} __packed; + +struct ath12k_htt_phy_reset_stats_tlv { + __le32 pdev_id; + __le32 chan_mhz; + __le32 chan_band_center_freq1; + __le32 chan_band_center_freq2; + __le32 chan_phy_mode; + __le32 chan_flags; + __le32 chan_num; + __le32 reset_cause; + __le32 prev_reset_cause; + __le32 phy_warm_reset_src; + __le32 rx_gain_tbl_mode; + __le32 xbar_val; + __le32 force_calibration; + __le32 phyrf_mode; + __le32 phy_homechan; + __le32 phy_tx_ch_mask; + __le32 phy_rx_ch_mask; + __le32 phybb_ini_mask; + __le32 phyrf_ini_mask; + __le32 phy_dfs_en_mask; + __le32 phy_sscan_en_mask; + __le32 phy_synth_sel_mask; + __le32 phy_adfs_freq; + __le32 cck_fir_settings; + __le32 phy_dyn_pri_chan; + __le32 cca_thresh; + __le32 dyn_cca_status; + __le32 rxdesense_thresh_hw; + __le32 rxdesense_thresh_sw; +} __packed; + +struct ath12k_htt_phy_reset_counters_tlv { + __le32 pdev_id; + __le32 cf_active_low_fail_cnt; + __le32 cf_active_low_pass_cnt; + __le32 phy_off_through_vreg_cnt; + __le32 force_calibration_cnt; + __le32 rf_mode_switch_phy_off_cnt; + __le32 temperature_recal_cnt; +} __packed; + +struct ath12k_htt_phy_tpc_stats_tlv { + __le32 pdev_id; + __le32 tx_power_scale; + __le32 tx_power_scale_db; + __le32 min_negative_tx_power; + __le32 reg_ctl_domain; + __le32 max_reg_allowed_power[ATH12K_HTT_STATS_MAX_CHAINS]; + __le32 max_reg_allowed_power_6ghz[ATH12K_HTT_STATS_MAX_CHAINS]; + __le32 twice_max_rd_power; + __le32 max_tx_power; + __le32 home_max_tx_power; + __le32 psd_power; + __le32 eirp_power; + __le32 power_type_6ghz; + __le32 sub_band_cfreq[ATH12K_HTT_MAX_CH_PWR_INFO_SIZE]; + __le32 sub_band_txpower[ATH12K_HTT_MAX_CH_PWR_INFO_SIZE]; +} __packed; + +struct ath12k_htt_t2h_soc_txrx_stats_common_tlv { + __le32 inv_peers_msdu_drop_count_hi; + __le32 inv_peers_msdu_drop_count_lo; +} __packed; + +#define ATH12K_HTT_AST_PDEV_ID_INFO GENMASK(1, 0) +#define ATH12K_HTT_AST_VDEV_ID_INFO GENMASK(9, 2) +#define ATH12K_HTT_AST_NEXT_HOP_INFO BIT(10) +#define ATH12K_HTT_AST_MCAST_INFO BIT(11) +#define ATH12K_HTT_AST_MONITOR_DIRECT_INFO BIT(12) +#define ATH12K_HTT_AST_MESH_STA_INFO BIT(13) +#define ATH12K_HTT_AST_MEC_INFO BIT(14) +#define ATH12K_HTT_AST_INTRA_BSS_INFO BIT(15) + +struct ath12k_htt_ast_entry_tlv { + __le32 sw_peer_id; + __le32 ast_index; + struct htt_mac_addr mac_addr; + __le32 info; +} __packed; + +enum ath12k_htt_stats_direction { + ATH12K_HTT_STATS_DIRECTION_TX, + ATH12K_HTT_STATS_DIRECTION_RX +}; + +enum ath12k_htt_stats_ppdu_type { + ATH12K_HTT_STATS_PPDU_TYPE_MODE_SU, + ATH12K_HTT_STATS_PPDU_TYPE_DL_MU_MIMO, + ATH12K_HTT_STATS_PPDU_TYPE_UL_MU_MIMO, + ATH12K_HTT_STATS_PPDU_TYPE_DL_MU_OFDMA, + ATH12K_HTT_STATS_PPDU_TYPE_UL_MU_OFDMA +}; + +enum ath12k_htt_stats_param_type { + ATH12K_HTT_STATS_PREAM_OFDM, + ATH12K_HTT_STATS_PREAM_CCK, + ATH12K_HTT_STATS_PREAM_HT, + ATH12K_HTT_STATS_PREAM_VHT, + ATH12K_HTT_STATS_PREAM_HE, + ATH12K_HTT_STATS_PREAM_EHT, + ATH12K_HTT_STATS_PREAM_RSVD1, + ATH12K_HTT_STATS_PREAM_COUNT, +}; + +#define ATH12K_HTT_PUNCT_STATS_MAX_SUBBAND_CNT 32 + +struct ath12k_htt_pdev_puncture_stats_tlv { + __le32 mac_id__word; + __le32 direction; + __le32 preamble; + __le32 ppdu_type; + __le32 subband_cnt; + __le32 last_used_pattern_mask; + __le32 num_subbands_used_cnt[ATH12K_HTT_PUNCT_STATS_MAX_SUBBAND_CNT]; +} __packed; + struct ath12k_htt_dmac_reset_stats_tlv { __le32 reset_count; __le32 reset_time_lo_ms; @@ -1085,6 +1380,10 @@ struct ath12k_htt_pdev_sched_algo_ofdma_stats_tlv { __le32 dlofdma_disabled_consec_no_mpdus_success[ATH12K_HTT_NUM_AC_WMM]; } __packed; +#define ATH12K_HTT_TX_PDEV_STATS_NUM_BW_CNTRS 4 +#define ATH12K_HTT_PDEV_STAT_NUM_SPATIAL_STREAMS 8 +#define ATH12K_HTT_TXBF_RATE_STAT_NUM_MCS_CNTRS 14 + enum ATH12K_HTT_TX_RX_PDEV_STATS_BE_RU_SIZE { ATH12K_HTT_TX_RX_PDEV_STATS_BE_RU_SIZE_26, ATH12K_HTT_TX_RX_PDEV_STATS_BE_RU_SIZE_52, @@ -1105,7 +1404,65 @@ enum ATH12K_HTT_TX_RX_PDEV_STATS_BE_RU_SIZE { ATH12K_HTT_TX_RX_PDEV_NUM_BE_RU_SIZE_CNTRS, }; -#define ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS 8 +enum ATH12K_HTT_RC_MODE { + ATH12K_HTT_RC_MODE_SU_OL, + ATH12K_HTT_RC_MODE_SU_BF, + ATH12K_HTT_RC_MODE_MU1_INTF, + ATH12K_HTT_RC_MODE_MU2_INTF, + ATH12K_HTT_RC_MODE_MU3_INTF, + ATH12K_HTT_RC_MODE_MU4_INTF, + ATH12K_HTT_RC_MODE_MU5_INTF, + ATH12K_HTT_RC_MODE_MU6_INTF, + ATH12K_HTT_RC_MODE_MU7_INTF, + ATH12K_HTT_RC_MODE_2D_COUNT +}; + +enum ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE { + ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_26, + ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_52, + ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_106, + ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_242, + ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_484, + ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_996, + ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_996x2, + ATH12K_HTT_TX_RX_PDEV_STATS_NUM_AX_RU_SIZE_CNTRS +}; + +enum ath12k_htt_stats_rc_mode { + ATH12K_HTT_STATS_RC_MODE_DLSU = 0, + ATH12K_HTT_STATS_RC_MODE_DLMUMIMO = 1, + ATH12K_HTT_STATS_RC_MODE_DLOFDMA = 2, + ATH12K_HTT_STATS_RC_MODE_ULMUMIMO = 3, + ATH12K_HTT_STATS_RC_MODE_ULOFDMA = 4, +}; + +enum ath12k_htt_stats_ru_type { + ATH12K_HTT_STATS_RU_TYPE_INVALID, + ATH12K_HTT_STATS_RU_TYPE_SINGLE_RU_ONLY, + ATH12K_HTT_STATS_RU_TYPE_SINGLE_AND_MULTI_RU, +}; + +struct ath12k_htt_tx_rate_stats { + __le32 ppdus_tried; + __le32 ppdus_ack_failed; + __le32 mpdus_tried; + __le32 mpdus_failed; +} __packed; + +struct ath12k_htt_tx_per_rate_stats_tlv { + __le32 rc_mode; + __le32 last_probed_mcs; + __le32 last_probed_nss; + __le32 last_probed_bw; + struct ath12k_htt_tx_rate_stats per_bw[ATH12K_HTT_TX_PDEV_STATS_NUM_BW_CNTRS]; + struct ath12k_htt_tx_rate_stats per_nss[ATH12K_HTT_PDEV_STAT_NUM_SPATIAL_STREAMS]; + struct ath12k_htt_tx_rate_stats per_mcs[ATH12K_HTT_TXBF_RATE_STAT_NUM_MCS_CNTRS]; + struct ath12k_htt_tx_rate_stats per_bw320; + __le32 probe_cnt[ATH12K_HTT_RC_MODE_2D_COUNT]; + __le32 ru_type; + struct ath12k_htt_tx_rate_stats ru[ATH12K_HTT_TX_RX_PDEV_NUM_BE_RU_SIZE_CNTRS]; +} __packed; + #define ATH12K_HTT_TX_PDEV_NUM_BE_MCS_CNTRS 16 #define ATH12K_HTT_TX_PDEV_NUM_BE_BW_CNTRS 5 #define ATH12K_HTT_TX_PDEV_NUM_EHT_SIG_MCS_CNTRS 4 @@ -1115,11 +1472,23 @@ struct ath12k_htt_tx_pdev_rate_stats_be_ofdma_tlv { __le32 mac_id__word; __le32 be_ofdma_tx_ldpc; __le32 be_ofdma_tx_mcs[ATH12K_HTT_TX_PDEV_NUM_BE_MCS_CNTRS]; - __le32 be_ofdma_tx_nss[ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS]; + __le32 be_ofdma_tx_nss[ATH12K_HTT_PDEV_STAT_NUM_SPATIAL_STREAMS]; __le32 be_ofdma_tx_bw[ATH12K_HTT_TX_PDEV_NUM_BE_BW_CNTRS]; __le32 gi[ATH12K_HTT_TX_PDEV_NUM_GI_CNTRS][ATH12K_HTT_TX_PDEV_NUM_BE_MCS_CNTRS]; __le32 be_ofdma_tx_ru_size[ATH12K_HTT_TX_RX_PDEV_NUM_BE_RU_SIZE_CNTRS]; __le32 be_ofdma_eht_sig_mcs[ATH12K_HTT_TX_PDEV_NUM_EHT_SIG_MCS_CNTRS]; } __packed; +struct ath12k_htt_pdev_mbssid_ctrl_frame_tlv { + __le32 mac_id__word; + __le32 basic_trigger_across_bss; + __le32 basic_trigger_within_bss; + __le32 bsr_trigger_across_bss; + __le32 bsr_trigger_within_bss; + __le32 mu_rts_across_bss; + __le32 mu_rts_within_bss; + __le32 ul_mumimo_trigger_across_bss; + __le32 ul_mumimo_trigger_within_bss; +} __packed; + #endif diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c index c99e9ceb1a6e..9e5a4e75f2f6 100644 --- a/drivers/net/wireless/ath/ath12k/dp.c +++ b/drivers/net/wireless/ath/ath12k/dp.c @@ -41,6 +41,11 @@ void ath12k_dp_peer_cleanup(struct ath12k *ar, int vdev_id, const u8 *addr) return; } + if (!peer->primary_link) { + spin_unlock_bh(&ab->base_lock); + return; + } + ath12k_dp_rx_peer_tid_cleanup(ar, peer); crypto_free_shash(peer->tfm_mmic); peer->dp_setup_done = false; @@ -977,27 +982,23 @@ void ath12k_dp_pdev_free(struct ath12k_base *ab) { int i; + if (!ab->mon_reap_timer.function) + return; + del_timer_sync(&ab->mon_reap_timer); for (i = 0; i < ab->num_radios; i++) ath12k_dp_rx_pdev_free(ab, i); } -void ath12k_dp_pdev_pre_alloc(struct ath12k_base *ab) +void ath12k_dp_pdev_pre_alloc(struct ath12k *ar) { - struct ath12k *ar; - struct ath12k_pdev_dp *dp; - int i; + struct ath12k_pdev_dp *dp = &ar->dp; - for (i = 0; i < ab->num_radios; i++) { - ar = ab->pdevs[i].ar; - dp = &ar->dp; - dp->mac_id = i; - atomic_set(&dp->num_tx_pending, 0); - init_waitqueue_head(&dp->tx_empty_waitq); - - /* TODO: Add any RXDMA setup required per pdev */ - } + dp->mac_id = ar->pdev_idx; + atomic_set(&dp->num_tx_pending, 0); + init_waitqueue_head(&dp->tx_empty_waitq); + /* TODO: Add any RXDMA setup required per pdev */ } bool ath12k_dp_wmask_compaction_rx_tlv_supported(struct ath12k_base *ab) @@ -1260,15 +1261,23 @@ static void ath12k_dp_reoq_lut_cleanup(struct ath12k_base *ab) if (!ab->hw_params->reoq_lut_support) return; - if (!dp->reoq_lut.vaddr) - return; + if (dp->reoq_lut.vaddr) { + ath12k_hif_write32(ab, + HAL_SEQ_WCSS_UMAC_REO_REG + + HAL_REO1_QDESC_LUT_BASE0(ab), 0); + dma_free_coherent(ab->dev, DP_REOQ_LUT_SIZE, + dp->reoq_lut.vaddr, dp->reoq_lut.paddr); + dp->reoq_lut.vaddr = NULL; + } - dma_free_coherent(ab->dev, DP_REOQ_LUT_SIZE, - dp->reoq_lut.vaddr, dp->reoq_lut.paddr); - dp->reoq_lut.vaddr = NULL; - - ath12k_hif_write32(ab, - HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO1_QDESC_LUT_BASE0(ab), 0); + if (dp->ml_reoq_lut.vaddr) { + ath12k_hif_write32(ab, + HAL_SEQ_WCSS_UMAC_REO_REG + + HAL_REO1_QDESC_LUT_BASE1(ab), 0); + dma_free_coherent(ab->dev, DP_REOQ_LUT_SIZE, + dp->ml_reoq_lut.vaddr, dp->ml_reoq_lut.paddr); + dp->ml_reoq_lut.vaddr = NULL; + } } void ath12k_dp_free(struct ath12k_base *ab) @@ -1276,6 +1285,9 @@ void ath12k_dp_free(struct ath12k_base *ab) struct ath12k_dp *dp = &ab->dp; int i; + if (!dp->ab) + return; + ath12k_dp_link_desc_cleanup(ab, dp->link_desc_banks, HAL_WBM_IDLE_LINK, &dp->wbm_idle_ring); @@ -1293,6 +1305,7 @@ void ath12k_dp_free(struct ath12k_base *ab) ath12k_dp_rx_free(ab); /* Deinit any SOC level resource */ + dp->ab = NULL; } void ath12k_dp_cc_config(struct ath12k_base *ab) @@ -1432,6 +1445,7 @@ static int ath12k_dp_cc_desc_init(struct ath12k_base *ab) for (j = 0; j < ATH12K_MAX_SPT_ENTRIES; j++) { rx_descs[j].cookie = ath12k_dp_cc_cookie_gen(cookie_ppt_idx, j); rx_descs[j].magic = ATH12K_DP_RX_DESC_MAGIC; + rx_descs[j].device_id = ab->device_id; list_add_tail(&rx_descs[j].list, &dp->rx_desc_free_list); /* Update descriptor VA in SPT */ @@ -1508,6 +1522,19 @@ static int ath12k_dp_cmem_init(struct ath12k_base *ab, return 0; } +void ath12k_dp_partner_cc_init(struct ath12k_base *ab) +{ + struct ath12k_hw_group *ag = ab->ag; + int i; + + for (i = 0; i < ag->num_devices; i++) { + if (ag->ab[i] == ab) + continue; + + ath12k_dp_cmem_init(ab, &ag->ab[i]->dp, ATH12K_DP_RX_DESC); + } +} + static int ath12k_dp_cc_init(struct ath12k_base *ab) { struct ath12k_dp *dp = &ab->dp; @@ -1594,8 +1621,23 @@ static int ath12k_dp_reoq_lut_setup(struct ath12k_base *ab) return -ENOMEM; } + dp->ml_reoq_lut.vaddr = dma_alloc_coherent(ab->dev, + DP_REOQ_LUT_SIZE, + &dp->ml_reoq_lut.paddr, + GFP_KERNEL | __GFP_ZERO); + if (!dp->ml_reoq_lut.vaddr) { + ath12k_warn(ab, "failed to allocate memory for ML reoq table"); + dma_free_coherent(ab->dev, DP_REOQ_LUT_SIZE, + dp->reoq_lut.vaddr, dp->reoq_lut.paddr); + dp->reoq_lut.vaddr = NULL; + return -ENOMEM; + } + ath12k_hif_write32(ab, HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO1_QDESC_LUT_BASE0(ab), dp->reoq_lut.paddr); + ath12k_hif_write32(ab, HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO1_QDESC_LUT_BASE1(ab), + dp->ml_reoq_lut.paddr >> 8); + return 0; } diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h index 2e05fc19410e..7ac3143de016 100644 --- a/drivers/net/wireless/ath/ath12k/dp.h +++ b/drivers/net/wireless/ath/ath12k/dp.h @@ -287,7 +287,8 @@ struct ath12k_rx_desc_info { u32 cookie; u32 magic; u8 in_use : 1, - reserved : 7; + device_id : 3, + reserved : 4; }; struct ath12k_tx_desc_info { @@ -368,6 +369,7 @@ struct ath12k_dp { struct dp_rxdma_mon_ring rxdma_mon_buf_ring; struct dp_rxdma_mon_ring tx_mon_buf_ring; struct ath12k_reo_q_addr_lut reoq_lut; + struct ath12k_reo_q_addr_lut ml_reoq_lut; }; /* HTT definitions */ @@ -694,9 +696,9 @@ enum htt_stats_internal_ppdu_frametype { * * The message would appear as follows: * - * |31 26|25|24|23 16|15 8|7 0| - * |-----------------+----------------+----------------+---------------| - * | rsvd1 |PS|SS| ring_id | pdev_id | msg_type | + * |31 29|28|27|26|25|24|23 16|15 8|7 0| + * |-------+--+--+--+--+--+-----------+----------------+---------------| + * | rsvd1 |ED|DT|OV|PS|SS| ring_id | pdev_id | msg_type | * |-------------------------------------------------------------------| * | rsvd2 | ring_buffer_size | * |-------------------------------------------------------------------| @@ -723,7 +725,13 @@ enum htt_stats_internal_ppdu_frametype { * More details can be got from enum htt_srng_ring_id * b'24 - status_swap: 1 is to swap status TLV * b'25 - pkt_swap: 1 is to swap packet TLV - * b'26:31 - rsvd1: reserved for future use + * b'26 - rx_offset_valid (OV): flag to indicate rx offsets + * configuration fields are valid + * b'27 - drop_thresh_valid (DT): flag to indicate if the + * rx_drop_threshold field is valid + * b'28 - rx_mon_global_en: Enable/Disable global register + * configuration in Rx monitor module. + * b'29:31 - rsvd1: reserved for future use * dword1 - b'0:16 - ring_buffer_size: size of buffers referenced by rx ring, * in byte units. * Valid only for HW_TO_SW_RING and SW_TO_HW_RING @@ -1790,6 +1798,18 @@ enum vdev_stats_offload_timer_duration { ATH12K_STATS_TIMER_DUR_2SEC = 3, }; +#define ATH12K_HTT_MAC_ADDR_L32_0 GENMASK(7, 0) +#define ATH12K_HTT_MAC_ADDR_L32_1 GENMASK(15, 8) +#define ATH12K_HTT_MAC_ADDR_L32_2 GENMASK(23, 16) +#define ATH12K_HTT_MAC_ADDR_L32_3 GENMASK(31, 24) +#define ATH12K_HTT_MAC_ADDR_H16_0 GENMASK(7, 0) +#define ATH12K_HTT_MAC_ADDR_H16_1 GENMASK(15, 8) + +struct htt_mac_addr { + __le32 mac_addr_l32; + __le32 mac_addr_h16; +} __packed; + static inline void ath12k_dp_get_mac_addr(u32 addr_l32, u16 addr_h16, u8 *addr) { memcpy(addr, &addr_l32, 4); @@ -1804,8 +1824,9 @@ void ath12k_dp_vdev_tx_attach(struct ath12k *ar, struct ath12k_link_vif *arvif); void ath12k_dp_free(struct ath12k_base *ab); int ath12k_dp_alloc(struct ath12k_base *ab); void ath12k_dp_cc_config(struct ath12k_base *ab); +void ath12k_dp_partner_cc_init(struct ath12k_base *ab); int ath12k_dp_pdev_alloc(struct ath12k_base *ab); -void ath12k_dp_pdev_pre_alloc(struct ath12k_base *ab); +void ath12k_dp_pdev_pre_alloc(struct ath12k *ar); void ath12k_dp_pdev_free(struct ath12k_base *ab); int ath12k_dp_tx_htt_srng_setup(struct ath12k_base *ab, u32 ring_id, int mac_id, enum hal_ring_type ring_type); diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c index 494984133a91..5a21961cfd46 100644 --- a/drivers/net/wireless/ath/ath12k/dp_mon.c +++ b/drivers/net/wireless/ath/ath12k/dp_mon.c @@ -10,11 +10,10 @@ #include "dp_tx.h" #include "peer.h" -static void ath12k_dp_mon_rx_handle_ofdma_info(void *rx_tlv, - struct hal_rx_user_status *rx_user_status) +static void +ath12k_dp_mon_rx_handle_ofdma_info(const struct hal_rx_ppdu_end_user_stats *ppdu_end_user, + struct hal_rx_user_status *rx_user_status) { - struct hal_rx_ppdu_end_user_stats *ppdu_end_user = rx_tlv; - rx_user_status->ul_ofdma_user_v0_word0 = __le32_to_cpu(ppdu_end_user->usr_resp_ref); rx_user_status->ul_ofdma_user_v0_word1 = @@ -35,7 +34,7 @@ ath12k_dp_mon_rx_populate_byte_count(const struct hal_rx_ppdu_end_user_stats *st } static void -ath12k_dp_mon_rx_populate_mu_user_info(void *rx_tlv, +ath12k_dp_mon_rx_populate_mu_user_info(const struct hal_rx_ppdu_end_user_stats *rx_tlv, struct hal_rx_mon_ppdu_info *ppdu_info, struct hal_rx_user_status *rx_user_status) { @@ -73,11 +72,9 @@ ath12k_dp_mon_rx_populate_mu_user_info(void *rx_tlv, ath12k_dp_mon_rx_populate_byte_count(rx_tlv, ppdu_info, rx_user_status); } -static void ath12k_dp_mon_parse_vht_sig_a(u8 *tlv_data, +static void ath12k_dp_mon_parse_vht_sig_a(const struct hal_rx_vht_sig_a_info *vht_sig, struct hal_rx_mon_ppdu_info *ppdu_info) { - struct hal_rx_vht_sig_a_info *vht_sig = - (struct hal_rx_vht_sig_a_info *)tlv_data; u32 nsts, group_id, info0, info1; u8 gi_setting; @@ -119,11 +116,9 @@ static void ath12k_dp_mon_parse_vht_sig_a(u8 *tlv_data, u32_get_bits(info1, HAL_RX_VHT_SIG_A_INFO_INFO1_SU_MU_CODING); } -static void ath12k_dp_mon_parse_ht_sig(u8 *tlv_data, +static void ath12k_dp_mon_parse_ht_sig(const struct hal_rx_ht_sig_info *ht_sig, struct hal_rx_mon_ppdu_info *ppdu_info) { - struct hal_rx_ht_sig_info *ht_sig = - (struct hal_rx_ht_sig_info *)tlv_data; u32 info0 = __le32_to_cpu(ht_sig->info0); u32 info1 = __le32_to_cpu(ht_sig->info1); @@ -136,11 +131,9 @@ static void ath12k_dp_mon_parse_ht_sig(u8 *tlv_data, ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU; } -static void ath12k_dp_mon_parse_l_sig_b(u8 *tlv_data, +static void ath12k_dp_mon_parse_l_sig_b(const struct hal_rx_lsig_b_info *lsigb, struct hal_rx_mon_ppdu_info *ppdu_info) { - struct hal_rx_lsig_b_info *lsigb = - (struct hal_rx_lsig_b_info *)tlv_data; u32 info0 = __le32_to_cpu(lsigb->info0); u8 rate; @@ -170,11 +163,9 @@ static void ath12k_dp_mon_parse_l_sig_b(u8 *tlv_data, ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU; } -static void ath12k_dp_mon_parse_l_sig_a(u8 *tlv_data, +static void ath12k_dp_mon_parse_l_sig_a(const struct hal_rx_lsig_a_info *lsiga, struct hal_rx_mon_ppdu_info *ppdu_info) { - struct hal_rx_lsig_a_info *lsiga = - (struct hal_rx_lsig_a_info *)tlv_data; u32 info0 = __le32_to_cpu(lsiga->info0); u8 rate; @@ -212,14 +203,13 @@ static void ath12k_dp_mon_parse_l_sig_a(u8 *tlv_data, ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU; } -static void ath12k_dp_mon_parse_he_sig_b2_ofdma(u8 *tlv_data, - struct hal_rx_mon_ppdu_info *ppdu_info) +static void +ath12k_dp_mon_parse_he_sig_b2_ofdma(const struct hal_rx_he_sig_b2_ofdma_info *ofdma, + struct hal_rx_mon_ppdu_info *ppdu_info) { - struct hal_rx_he_sig_b2_ofdma_info *he_sig_b2_ofdma = - (struct hal_rx_he_sig_b2_ofdma_info *)tlv_data; u32 info0, value; - info0 = __le32_to_cpu(he_sig_b2_ofdma->info0); + info0 = __le32_to_cpu(ofdma->info0); ppdu_info->he_data1 |= HE_MCS_KNOWN | HE_DCM_KNOWN | HE_CODING_KNOWN; @@ -250,11 +240,10 @@ static void ath12k_dp_mon_parse_he_sig_b2_ofdma(u8 *tlv_data, ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_OFDMA; } -static void ath12k_dp_mon_parse_he_sig_b2_mu(u8 *tlv_data, - struct hal_rx_mon_ppdu_info *ppdu_info) +static void +ath12k_dp_mon_parse_he_sig_b2_mu(const struct hal_rx_he_sig_b2_mu_info *he_sig_b2_mu, + struct hal_rx_mon_ppdu_info *ppdu_info) { - struct hal_rx_he_sig_b2_mu_info *he_sig_b2_mu = - (struct hal_rx_he_sig_b2_mu_info *)tlv_data; u32 info0, value; info0 = __le32_to_cpu(he_sig_b2_mu->info0); @@ -277,11 +266,10 @@ static void ath12k_dp_mon_parse_he_sig_b2_mu(u8 *tlv_data, ppdu_info->nss = u32_get_bits(info0, HAL_RX_HE_SIG_B2_MU_INFO_INFO0_STA_NSTS); } -static void ath12k_dp_mon_parse_he_sig_b1_mu(u8 *tlv_data, - struct hal_rx_mon_ppdu_info *ppdu_info) +static void +ath12k_dp_mon_parse_he_sig_b1_mu(const struct hal_rx_he_sig_b1_mu_info *he_sig_b1_mu, + struct hal_rx_mon_ppdu_info *ppdu_info) { - struct hal_rx_he_sig_b1_mu_info *he_sig_b1_mu = - (struct hal_rx_he_sig_b1_mu_info *)tlv_data; u32 info0 = __le32_to_cpu(he_sig_b1_mu->info0); u16 ru_tones; @@ -292,11 +280,10 @@ static void ath12k_dp_mon_parse_he_sig_b1_mu(u8 *tlv_data, ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_MIMO; } -static void ath12k_dp_mon_parse_he_sig_mu(u8 *tlv_data, - struct hal_rx_mon_ppdu_info *ppdu_info) +static void +ath12k_dp_mon_parse_he_sig_mu(const struct hal_rx_he_sig_a_mu_dl_info *he_sig_a_mu_dl, + struct hal_rx_mon_ppdu_info *ppdu_info) { - struct hal_rx_he_sig_a_mu_dl_info *he_sig_a_mu_dl = - (struct hal_rx_he_sig_a_mu_dl_info *)tlv_data; u32 info0, info1, value; u16 he_gi = 0, he_ltf = 0; @@ -427,11 +414,9 @@ static void ath12k_dp_mon_parse_he_sig_mu(u8 *tlv_data, ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_MIMO; } -static void ath12k_dp_mon_parse_he_sig_su(u8 *tlv_data, +static void ath12k_dp_mon_parse_he_sig_su(const struct hal_rx_he_sig_a_su_info *he_sig_a, struct hal_rx_mon_ppdu_info *ppdu_info) { - struct hal_rx_he_sig_a_su_info *he_sig_a = - (struct hal_rx_he_sig_a_su_info *)tlv_data; u32 info0, info1, value; u32 dcm; u8 he_dcm = 0, he_stbc = 0; @@ -580,15 +565,15 @@ static void ath12k_dp_mon_parse_he_sig_su(u8 *tlv_data, static enum hal_rx_mon_status ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, struct ath12k_mon_data *pmon, - u32 tlv_tag, u8 *tlv_data, u32 userid) + u32 tlv_tag, const void *tlv_data, + u32 userid) { struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info; u32 info[7]; switch (tlv_tag) { case HAL_RX_PPDU_START: { - struct hal_rx_ppdu_start *ppdu_start = - (struct hal_rx_ppdu_start *)tlv_data; + const struct hal_rx_ppdu_start *ppdu_start = tlv_data; u64 ppdu_ts = ath12k_le32hilo_to_u64(ppdu_start->ppdu_start_ts_63_32, ppdu_start->ppdu_start_ts_31_0); @@ -615,8 +600,8 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, break; } case HAL_RX_PPDU_END_USER_STATS: { - struct hal_rx_ppdu_end_user_stats *eu_stats = - (struct hal_rx_ppdu_end_user_stats *)tlv_data; + const struct hal_rx_ppdu_end_user_stats *eu_stats = tlv_data; + u32 tid_bitmap; info[0] = __le32_to_cpu(eu_stats->info0); info[1] = __le32_to_cpu(eu_stats->info1); @@ -629,10 +614,9 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, u32_get_bits(info[2], HAL_RX_PPDU_END_USER_STATS_INFO2_AST_INDEX); ppdu_info->fc_valid = u32_get_bits(info[1], HAL_RX_PPDU_END_USER_STATS_INFO1_FC_VALID); - ppdu_info->tid = - ffs(u32_get_bits(info[6], - HAL_RX_PPDU_END_USER_STATS_INFO6_TID_BITMAP) - - 1); + tid_bitmap = u32_get_bits(info[6], + HAL_RX_PPDU_END_USER_STATS_INFO6_TID_BITMAP); + ppdu_info->tid = ffs(tid_bitmap) - 1; ppdu_info->tcp_msdu_count = u32_get_bits(info[4], HAL_RX_PPDU_END_USER_STATS_INFO4_TCP_MSDU_CNT); @@ -673,8 +657,8 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, &ppdu_info->userstats[userid]; ppdu_info->num_users += 1; - ath12k_dp_mon_rx_handle_ofdma_info(tlv_data, rxuser_stats); - ath12k_dp_mon_rx_populate_mu_user_info(tlv_data, ppdu_info, + ath12k_dp_mon_rx_handle_ofdma_info(eu_stats, rxuser_stats); + ath12k_dp_mon_rx_populate_mu_user_info(eu_stats, ppdu_info, rxuser_stats); } ppdu_info->mpdu_fcs_ok_bitmap[0] = __le32_to_cpu(eu_stats->rsvd1[0]); @@ -682,8 +666,8 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, break; } case HAL_RX_PPDU_END_USER_STATS_EXT: { - struct hal_rx_ppdu_end_user_stats_ext *eu_stats = - (struct hal_rx_ppdu_end_user_stats_ext *)tlv_data; + const struct hal_rx_ppdu_end_user_stats_ext *eu_stats = tlv_data; + ppdu_info->mpdu_fcs_ok_bitmap[2] = __le32_to_cpu(eu_stats->info1); ppdu_info->mpdu_fcs_ok_bitmap[3] = __le32_to_cpu(eu_stats->info2); ppdu_info->mpdu_fcs_ok_bitmap[4] = __le32_to_cpu(eu_stats->info3); @@ -729,8 +713,7 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, break; case HAL_PHYRX_RSSI_LEGACY: { - struct hal_rx_phyrx_rssi_legacy_info *rssi = - (struct hal_rx_phyrx_rssi_legacy_info *)tlv_data; + const struct hal_rx_phyrx_rssi_legacy_info *rssi = tlv_data; info[0] = __le32_to_cpu(rssi->info0); info[1] = __le32_to_cpu(rssi->info1); @@ -748,8 +731,7 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, break; } case HAL_RXPCU_PPDU_END_INFO: { - struct hal_rx_ppdu_end_duration *ppdu_rx_duration = - (struct hal_rx_ppdu_end_duration *)tlv_data; + const struct hal_rx_ppdu_end_duration *ppdu_rx_duration = tlv_data; info[0] = __le32_to_cpu(ppdu_rx_duration->info0); ppdu_info->rx_duration = @@ -760,8 +742,7 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, break; } case HAL_RX_MPDU_START: { - struct hal_rx_mpdu_start *mpdu_start = - (struct hal_rx_mpdu_start *)tlv_data; + const struct hal_rx_mpdu_start *mpdu_start = tlv_data; struct dp_mon_mpdu *mon_mpdu = pmon->mon_mpdu; u16 peer_id; @@ -790,8 +771,7 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, break; case HAL_MON_BUF_ADDR: { struct dp_rxdma_mon_ring *buf_ring = &ab->dp.rxdma_mon_buf_ring; - struct dp_mon_packet_info *packet_info = - (struct dp_mon_packet_info *)tlv_data; + const struct dp_mon_packet_info *packet_info = tlv_data; int buf_id = u32_get_bits(packet_info->cookie, DP_RXDMA_BUF_COOKIE_BUF_ID); struct sk_buff *msdu; @@ -823,8 +803,7 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab, break; } case HAL_RX_MSDU_END: { - struct rx_msdu_end_qcn9274 *msdu_end = - (struct rx_msdu_end_qcn9274 *)tlv_data; + const struct rx_msdu_end_qcn9274 *msdu_end = tlv_data; bool is_first_msdu_in_mpdu; u16 msdu_end_info; @@ -1093,8 +1072,14 @@ static void ath12k_dp_mon_rx_deliver_msdu(struct ath12k *ar, struct napi_struct decap = ath12k_dp_rx_h_decap_type(ar->ab, rxcb->rx_desc); spin_lock_bh(&ar->ab->base_lock); peer = ath12k_dp_rx_h_find_peer(ar->ab, msdu); - if (peer && peer->sta) + if (peer && peer->sta) { pubsta = peer->sta; + if (pubsta->valid_links) { + status->link_valid = 1; + status->link_id = peer->link_id; + } + } + spin_unlock_bh(&ar->ab->base_lock); ath12k_dbg(ar->ab, ATH12K_DBG_DATA, @@ -1199,19 +1184,19 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k_base *ab, struct ath12k_mon_data *pmon struct sk_buff *skb) { struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info; - struct hal_tlv_hdr *tlv; + struct hal_tlv_64_hdr *tlv; enum hal_rx_mon_status hal_status; - u32 tlv_userid = 0; + u32 tlv_userid; u16 tlv_tag, tlv_len; u8 *ptr = skb->data; memset(ppdu_info, 0, sizeof(struct hal_rx_mon_ppdu_info)); do { - tlv = (struct hal_tlv_hdr *)ptr; - tlv_tag = le32_get_bits(tlv->tl, HAL_TLV_HDR_TAG); - tlv_len = le32_get_bits(tlv->tl, HAL_TLV_HDR_LEN); - tlv_userid = le32_get_bits(tlv->tl, HAL_TLV_USR_ID); + tlv = (struct hal_tlv_64_hdr *)ptr; + tlv_tag = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_TAG); + tlv_len = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_LEN); + tlv_userid = le64_get_bits(tlv->tl, HAL_TLV_64_USR_ID); ptr += sizeof(*tlv); /* The actual length of PPDU_END is the combined length of many PHY @@ -1226,7 +1211,7 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k_base *ab, struct ath12k_mon_data *pmon hal_status = ath12k_dp_mon_rx_parse_status_tlv(ab, pmon, tlv_tag, ptr, tlv_userid); ptr += tlv_len; - ptr = PTR_ALIGN(ptr, HAL_TLV_ALIGN); + ptr = PTR_ALIGN(ptr, HAL_TLV_64_ALIGN); if ((ptr - skb->data) >= DP_RX_BUFFER_SIZE) break; @@ -1603,7 +1588,7 @@ ath12k_dp_mon_tx_gen_prot_frame(struct dp_mon_tx_ppdu_info *tx_ppdu_info) static enum dp_mon_tx_tlv_status ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, struct ath12k_mon_data *pmon, - u16 tlv_tag, u8 *tlv_data, u32 userid) + u16 tlv_tag, const void *tlv_data, u32 userid) { struct dp_mon_tx_ppdu_info *tx_ppdu_info; enum dp_mon_tx_tlv_status status = DP_MON_TX_STATUS_PPDU_NOT_DONE; @@ -1613,8 +1598,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, switch (tlv_tag) { case HAL_TX_FES_SETUP: { - struct hal_tx_fes_setup *tx_fes_setup = - (struct hal_tx_fes_setup *)tlv_data; + const struct hal_tx_fes_setup *tx_fes_setup = tlv_data; info[0] = __le32_to_cpu(tx_fes_setup->info0); tx_ppdu_info->ppdu_id = __le32_to_cpu(tx_fes_setup->schedule_id); @@ -1625,8 +1609,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, } case HAL_TX_FES_STATUS_END: { - struct hal_tx_fes_status_end *tx_fes_status_end = - (struct hal_tx_fes_status_end *)tlv_data; + const struct hal_tx_fes_status_end *tx_fes_status_end = tlv_data; u32 tst_15_0, tst_31_16; info[0] = __le32_to_cpu(tx_fes_status_end->info0); @@ -1643,8 +1626,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, } case HAL_RX_RESPONSE_REQUIRED_INFO: { - struct hal_rx_resp_req_info *rx_resp_req_info = - (struct hal_rx_resp_req_info *)tlv_data; + const struct hal_rx_resp_req_info *rx_resp_req_info = tlv_data; u32 addr_32; u16 addr_16; @@ -1689,8 +1671,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, } case HAL_PCU_PPDU_SETUP_INIT: { - struct hal_tx_pcu_ppdu_setup_init *ppdu_setup = - (struct hal_tx_pcu_ppdu_setup_init *)tlv_data; + const struct hal_tx_pcu_ppdu_setup_init *ppdu_setup = tlv_data; u32 addr_32; u16 addr_16; @@ -1736,8 +1717,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, } case HAL_TX_QUEUE_EXTENSION: { - struct hal_tx_queue_exten *tx_q_exten = - (struct hal_tx_queue_exten *)tlv_data; + const struct hal_tx_queue_exten *tx_q_exten = tlv_data; info[0] = __le32_to_cpu(tx_q_exten->info0); @@ -1749,8 +1729,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, } case HAL_TX_FES_STATUS_START: { - struct hal_tx_fes_status_start *tx_fes_start = - (struct hal_tx_fes_status_start *)tlv_data; + const struct hal_tx_fes_status_start *tx_fes_start = tlv_data; info[0] = __le32_to_cpu(tx_fes_start->info0); @@ -1761,8 +1740,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, } case HAL_TX_FES_STATUS_PROT: { - struct hal_tx_fes_status_prot *tx_fes_status = - (struct hal_tx_fes_status_prot *)tlv_data; + const struct hal_tx_fes_status_prot *tx_fes_status = tlv_data; u32 start_timestamp; u32 end_timestamp; @@ -1789,8 +1767,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, case HAL_TX_FES_STATUS_START_PPDU: case HAL_TX_FES_STATUS_START_PROT: { - struct hal_tx_fes_status_start_prot *tx_fes_stat_start = - (struct hal_tx_fes_status_start_prot *)tlv_data; + const struct hal_tx_fes_status_start_prot *tx_fes_stat_start = tlv_data; u64 ppdu_ts; info[0] = __le32_to_cpu(tx_fes_stat_start->info0); @@ -1805,8 +1782,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, } case HAL_TX_FES_STATUS_USER_PPDU: { - struct hal_tx_fes_status_user_ppdu *tx_fes_usr_ppdu = - (struct hal_tx_fes_status_user_ppdu *)tlv_data; + const struct hal_tx_fes_status_user_ppdu *tx_fes_usr_ppdu = tlv_data; info[0] = __le32_to_cpu(tx_fes_usr_ppdu->info0); @@ -1849,8 +1825,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, break; case HAL_RX_FRAME_BITMAP_ACK: { - struct hal_rx_frame_bitmap_ack *fbm_ack = - (struct hal_rx_frame_bitmap_ack *)tlv_data; + const struct hal_rx_frame_bitmap_ack *fbm_ack = tlv_data; u32 addr_32; u16 addr_16; @@ -1868,8 +1843,7 @@ ath12k_dp_mon_tx_parse_status_tlv(struct ath12k_base *ab, } case HAL_MACTX_PHY_DESC: { - struct hal_tx_phy_desc *tx_phy_desc = - (struct hal_tx_phy_desc *)tlv_data; + const struct hal_tx_phy_desc *tx_phy_desc = tlv_data; info[0] = __le32_to_cpu(tx_phy_desc->info0); info[1] = __le32_to_cpu(tx_phy_desc->info1); diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c index 9ae579e50557..dad35bfd83f6 100644 --- a/drivers/net/wireless/ath/ath12k/dp_rx.c +++ b/drivers/net/wireless/ath/ath12k/dp_rx.c @@ -740,15 +740,22 @@ static void ath12k_peer_rx_tid_qref_setup(struct ath12k_base *ab, u16 peer_id, u { struct ath12k_reo_queue_ref *qref; struct ath12k_dp *dp = &ab->dp; + bool ml_peer = false; if (!ab->hw_params->reoq_lut_support) return; - /* TODO: based on ML peer or not, select the LUT. below assumes non - * ML peer - */ - qref = (struct ath12k_reo_queue_ref *)dp->reoq_lut.vaddr + - (peer_id * (IEEE80211_NUM_TIDS + 1) + tid); + if (peer_id & ATH12K_PEER_ML_ID_VALID) { + peer_id &= ~ATH12K_PEER_ML_ID_VALID; + ml_peer = true; + } + + if (ml_peer) + qref = (struct ath12k_reo_queue_ref *)dp->ml_reoq_lut.vaddr + + (peer_id * (IEEE80211_NUM_TIDS + 1) + tid); + else + qref = (struct ath12k_reo_queue_ref *)dp->reoq_lut.vaddr + + (peer_id * (IEEE80211_NUM_TIDS + 1) + tid); qref->info0 = u32_encode_bits(lower_32_bits(paddr), BUFFER_ADDR_INFO0_ADDR); @@ -761,15 +768,22 @@ static void ath12k_peer_rx_tid_qref_reset(struct ath12k_base *ab, u16 peer_id, u { struct ath12k_reo_queue_ref *qref; struct ath12k_dp *dp = &ab->dp; + bool ml_peer = false; if (!ab->hw_params->reoq_lut_support) return; - /* TODO: based on ML peer or not, select the LUT. below assumes non - * ML peer - */ - qref = (struct ath12k_reo_queue_ref *)dp->reoq_lut.vaddr + - (peer_id * (IEEE80211_NUM_TIDS + 1) + tid); + if (peer_id & ATH12K_PEER_ML_ID_VALID) { + peer_id &= ~ATH12K_PEER_ML_ID_VALID; + ml_peer = true; + } + + if (ml_peer) + qref = (struct ath12k_reo_queue_ref *)dp->ml_reoq_lut.vaddr + + (peer_id * (IEEE80211_NUM_TIDS + 1) + tid); + else + qref = (struct ath12k_reo_queue_ref *)dp->reoq_lut.vaddr + + (peer_id * (IEEE80211_NUM_TIDS + 1) + tid); qref->info0 = u32_encode_bits(0, BUFFER_ADDR_INFO0_ADDR); qref->info1 = u32_encode_bits(0, BUFFER_ADDR_INFO1_ADDR) | @@ -802,7 +816,10 @@ void ath12k_dp_rx_peer_tid_delete(struct ath12k *ar, rx_tid->vaddr = NULL; } - ath12k_peer_rx_tid_qref_reset(ar->ab, peer->peer_id, tid); + if (peer->mlo) + ath12k_peer_rx_tid_qref_reset(ar->ab, peer->ml_id, tid); + else + ath12k_peer_rx_tid_qref_reset(ar->ab, peer->peer_id, tid); rx_tid->active = false; } @@ -940,7 +957,13 @@ int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_ return -ENOENT; } - if (ab->hw_params->reoq_lut_support && !dp->reoq_lut.vaddr) { + if (!peer->primary_link) { + spin_unlock_bh(&ab->base_lock); + return 0; + } + + if (ab->hw_params->reoq_lut_support && + (!dp->reoq_lut.vaddr || !dp->ml_reoq_lut.vaddr)) { spin_unlock_bh(&ab->base_lock); ath12k_warn(ab, "reo qref table is not setup\n"); return -EINVAL; @@ -1021,7 +1044,11 @@ int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_ /* Update the REO queue LUT at the corresponding peer id * and tid with qaddr. */ - ath12k_peer_rx_tid_qref_setup(ab, peer->peer_id, tid, paddr); + if (peer->mlo) + ath12k_peer_rx_tid_qref_setup(ab, peer->ml_id, tid, paddr); + else + ath12k_peer_rx_tid_qref_setup(ab, peer->peer_id, tid, paddr); + spin_unlock_bh(&ab->base_lock); } else { spin_unlock_bh(&ab->base_lock); @@ -1038,15 +1065,25 @@ err_mem_free: } int ath12k_dp_rx_ampdu_start(struct ath12k *ar, - struct ieee80211_ampdu_params *params) + struct ieee80211_ampdu_params *params, + u8 link_id) { struct ath12k_base *ab = ar->ab; struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(params->sta); - struct ath12k_link_sta *arsta = &ahsta->deflink; - int vdev_id = arsta->arvif->vdev_id; + struct ath12k_link_sta *arsta; + int vdev_id; int ret; - ret = ath12k_dp_rx_peer_tid_setup(ar, params->sta->addr, vdev_id, + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + arsta = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy, + ahsta->link[link_id]); + if (!arsta) + return -ENOLINK; + + vdev_id = arsta->arvif->vdev_id; + + ret = ath12k_dp_rx_peer_tid_setup(ar, arsta->addr, vdev_id, params->tid, params->buf_size, params->ssn, arsta->ahsta->pn_type); if (ret) @@ -1056,19 +1093,29 @@ int ath12k_dp_rx_ampdu_start(struct ath12k *ar, } int ath12k_dp_rx_ampdu_stop(struct ath12k *ar, - struct ieee80211_ampdu_params *params) + struct ieee80211_ampdu_params *params, + u8 link_id) { struct ath12k_base *ab = ar->ab; struct ath12k_peer *peer; struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(params->sta); - struct ath12k_link_sta *arsta = &ahsta->deflink; - int vdev_id = arsta->arvif->vdev_id; + struct ath12k_link_sta *arsta; + int vdev_id; bool active; int ret; + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + arsta = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy, + ahsta->link[link_id]); + if (!arsta) + return -ENOLINK; + + vdev_id = arsta->arvif->vdev_id; + spin_lock_bh(&ab->base_lock); - peer = ath12k_peer_find(ab, vdev_id, params->sta->addr); + peer = ath12k_peer_find(ab, vdev_id, arsta->addr); if (!peer) { spin_unlock_bh(&ab->base_lock); ath12k_warn(ab, "failed to find the peer to stop rx aggregation\n"); @@ -1650,7 +1697,11 @@ static void ath12k_htt_mlo_offset_event_handler(struct ath12k_base *ab, rcu_read_lock(); ar = ath12k_mac_get_ar_by_pdev_id(ab, pdev_id); if (!ar) { - ath12k_warn(ab, "invalid pdev id %d on htt mlo offset\n", pdev_id); + /* It is possible that the ar is not yet active (started). + * The above function will only look for the active pdev + * and hence %NULL return is possible. Just silently + * discard this message + */ goto exit; } @@ -2427,6 +2478,11 @@ static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *nap pubsta = peer ? peer->sta : NULL; + if (pubsta && pubsta->valid_links) { + status->link_valid = 1; + status->link_id = peer->link_id; + } + spin_unlock_bh(&ab->base_lock); ath12k_dbg(ab, ATH12K_DBG_DATA, @@ -2548,11 +2604,14 @@ static void ath12k_dp_rx_process_received_packets(struct ath12k_base *ab, struct sk_buff_head *msdu_list, int ring_id) { + struct ath12k_hw_group *ag = ab->ag; struct ieee80211_rx_status rx_status = {0}; struct ath12k_skb_rxcb *rxcb; struct sk_buff *msdu; struct ath12k *ar; - u8 mac_id, pdev_id; + struct ath12k_hw_link *hw_links = ag->hw_links; + struct ath12k_base *partner_ab; + u8 hw_link_id, pdev_id; int ret; if (skb_queue_empty(msdu_list)) @@ -2562,15 +2621,18 @@ static void ath12k_dp_rx_process_received_packets(struct ath12k_base *ab, while ((msdu = __skb_dequeue(msdu_list))) { rxcb = ATH12K_SKB_RXCB(msdu); - mac_id = rxcb->mac_id; - pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id); - ar = ab->pdevs[pdev_id].ar; - if (!rcu_dereference(ab->pdevs_active[pdev_id])) { + hw_link_id = rxcb->hw_link_id; + partner_ab = ath12k_ag_to_ab(ag, + hw_links[hw_link_id].device_id); + pdev_id = ath12k_hw_mac_id_to_pdev_id(partner_ab->hw_params, + hw_links[hw_link_id].pdev_idx); + ar = partner_ab->pdevs[pdev_id].ar; + if (!rcu_dereference(partner_ab->pdevs_active[pdev_id])) { dev_kfree_skb_any(msdu); continue; } - if (test_bit(ATH12K_CAC_RUNNING, &ar->dev_flags)) { + if (test_bit(ATH12K_FLAG_CAC_RUNNING, &ar->dev_flags)) { dev_kfree_skb_any(msdu); continue; } @@ -2615,23 +2677,29 @@ static u16 ath12k_dp_rx_get_peer_id(struct ath12k_base *ab, int ath12k_dp_rx_process(struct ath12k_base *ab, int ring_id, struct napi_struct *napi, int budget) { - LIST_HEAD(rx_desc_used_list); + struct ath12k_hw_group *ag = ab->ag; + struct list_head rx_desc_used_list[ATH12K_MAX_SOCS]; + struct ath12k_hw_link *hw_links = ag->hw_links; + int num_buffs_reaped[ATH12K_MAX_SOCS] = {}; struct ath12k_rx_desc_info *desc_info; struct ath12k_dp *dp = &ab->dp; struct dp_rxdma_ring *rx_ring = &dp->rx_refill_buf_ring; struct hal_reo_dest_ring *desc; - int num_buffs_reaped = 0; + struct ath12k_base *partner_ab; struct sk_buff_head msdu_list; struct ath12k_skb_rxcb *rxcb; int total_msdu_reaped = 0; + u8 hw_link_id, device_id; struct hal_srng *srng; struct sk_buff *msdu; bool done = false; - int mac_id; u64 desc_va; __skb_queue_head_init(&msdu_list); + for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++) + INIT_LIST_HEAD(&rx_desc_used_list[device_id]); + srng = &ab->hal.srng_list[dp->reo_dst_ring[ring_id].ring_id]; spin_lock_bh(&srng->lock); @@ -2648,18 +2716,29 @@ try_again: cookie = le32_get_bits(desc->buf_addr_info.info1, BUFFER_ADDR_INFO1_SW_COOKIE); - mac_id = le32_get_bits(desc->info0, - HAL_REO_DEST_RING_INFO0_SRC_LINK_ID); + hw_link_id = le32_get_bits(desc->info0, + HAL_REO_DEST_RING_INFO0_SRC_LINK_ID); desc_va = ((u64)le32_to_cpu(desc->buf_va_hi) << 32 | le32_to_cpu(desc->buf_va_lo)); desc_info = (struct ath12k_rx_desc_info *)((unsigned long)desc_va); + device_id = hw_links[hw_link_id].device_id; + partner_ab = ath12k_ag_to_ab(ag, device_id); + if (unlikely(!partner_ab)) { + if (desc_info->skb) { + dev_kfree_skb_any(desc_info->skb); + desc_info->skb = NULL; + } + + continue; + } + /* retry manual desc retrieval */ if (!desc_info) { - desc_info = ath12k_dp_get_rx_desc(ab, cookie); + desc_info = ath12k_dp_get_rx_desc(partner_ab, cookie); if (!desc_info) { - ath12k_warn(ab, "Invalid cookie in manual descriptor retrieval: 0x%x\n", + ath12k_warn(partner_ab, "Invalid cookie in manual descriptor retrieval: 0x%x\n", cookie); continue; } @@ -2671,14 +2750,14 @@ try_again: msdu = desc_info->skb; desc_info->skb = NULL; - list_add_tail(&desc_info->list, &rx_desc_used_list); + list_add_tail(&desc_info->list, &rx_desc_used_list[device_id]); rxcb = ATH12K_SKB_RXCB(msdu); - dma_unmap_single(ab->dev, rxcb->paddr, + dma_unmap_single(partner_ab->dev, rxcb->paddr, msdu->len + skb_tailroom(msdu), DMA_FROM_DEVICE); - num_buffs_reaped++; + num_buffs_reaped[device_id]++; push_reason = le32_get_bits(desc->info0, HAL_REO_DEST_RING_INFO0_PUSH_REASON); @@ -2698,7 +2777,7 @@ try_again: RX_MSDU_DESC_INFO0_LAST_MSDU_IN_MPDU); rxcb->is_continuation = !!(le32_to_cpu(msdu_info->info0) & RX_MSDU_DESC_INFO0_MSDU_CONTINUATION); - rxcb->mac_id = mac_id; + rxcb->hw_link_id = hw_link_id; rxcb->peer_id = ath12k_dp_rx_get_peer_id(ab, dp->peer_metadata_ver, mpdu_info->peer_meta_data); rxcb->tid = le32_get_bits(mpdu_info->info0, @@ -2735,8 +2814,17 @@ try_again: if (!total_msdu_reaped) goto exit; - ath12k_dp_rx_bufs_replenish(ab, rx_ring, &rx_desc_used_list, - num_buffs_reaped); + for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++) { + if (!num_buffs_reaped[device_id]) + continue; + + partner_ab = ath12k_ag_to_ab(ag, device_id); + rx_ring = &partner_ab->dp.rx_refill_buf_ring; + + ath12k_dp_rx_bufs_replenish(partner_ab, rx_ring, + &rx_desc_used_list[device_id], + num_buffs_reaped[device_id]); + } ath12k_dp_rx_process_received_packets(ab, napi, &msdu_list, ring_id); @@ -2781,6 +2869,12 @@ int ath12k_dp_rx_peer_frag_setup(struct ath12k *ar, const u8 *peer_mac, int vdev return -ENOENT; } + if (!peer->primary_link) { + spin_unlock_bh(&ab->base_lock); + crypto_free_shash(tfm); + return 0; + } + for (i = 0; i <= IEEE80211_NUM_TIDS; i++) { rx_tid = &peer->rx_tid[i]; rx_tid->ab = ab; @@ -3390,7 +3484,7 @@ ath12k_dp_process_rx_err_buf(struct ath12k *ar, struct hal_reo_dest_ring *desc, goto exit; } - if (test_bit(ATH12K_CAC_RUNNING, &ar->dev_flags)) { + if (test_bit(ATH12K_FLAG_CAC_RUNNING, &ar->dev_flags)) { dev_kfree_skb_any(msdu); goto exit; } @@ -3420,7 +3514,10 @@ exit: int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, int budget) { + struct ath12k_hw_group *ag = ab->ag; + struct list_head rx_desc_used_list[ATH12K_MAX_SOCS]; u32 msdu_cookies[HAL_NUM_RX_MSDUS_PER_LINK_DESC]; + int num_buffs_reaped[ATH12K_MAX_SOCS] = {}; struct dp_link_desc_bank *link_desc_banks; enum hal_rx_buf_return_buf_manager rbm; struct hal_rx_msdu_link *link_desc_va; @@ -3428,11 +3525,11 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, struct hal_reo_dest_ring *reo_desc; struct dp_rxdma_ring *rx_ring; struct dp_srng *reo_except; - LIST_HEAD(rx_desc_used_list); + struct ath12k_hw_link *hw_links = ag->hw_links; + struct ath12k_base *partner_ab; + u8 hw_link_id, device_id; u32 desc_bank, num_msdus; struct hal_srng *srng; - struct ath12k_dp *dp; - int mac_id; struct ath12k *ar; dma_addr_t paddr; bool is_frag; @@ -3442,9 +3539,10 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, tot_n_bufs_reaped = 0; quota = budget; - dp = &ab->dp; - reo_except = &dp->reo_except_ring; - link_desc_banks = dp->link_desc_banks; + for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++) + INIT_LIST_HEAD(&rx_desc_used_list[device_id]); + + reo_except = &ab->dp.reo_except_ring; srng = &ab->hal.srng_list[reo_except->ring_id]; @@ -3464,16 +3562,27 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, ret); continue; } + + hw_link_id = le32_get_bits(reo_desc->info0, + HAL_REO_DEST_RING_INFO0_SRC_LINK_ID); + device_id = hw_links[hw_link_id].device_id; + partner_ab = ath12k_ag_to_ab(ag, device_id); + + pdev_id = ath12k_hw_mac_id_to_pdev_id(partner_ab->hw_params, + hw_links[hw_link_id].pdev_idx); + ar = partner_ab->pdevs[pdev_id].ar; + + link_desc_banks = partner_ab->dp.link_desc_banks; link_desc_va = link_desc_banks[desc_bank].vaddr + (paddr - link_desc_banks[desc_bank].paddr); ath12k_hal_rx_msdu_link_info_get(link_desc_va, &num_msdus, msdu_cookies, &rbm); - if (rbm != dp->idle_link_rbm && + if (rbm != partner_ab->dp.idle_link_rbm && rbm != HAL_RX_BUF_RBM_SW3_BM && - rbm != ab->hw_params->hal_params->rx_buf_rbm) { + rbm != partner_ab->hw_params->hal_params->rx_buf_rbm) { ab->soc_stats.invalid_rbm++; ath12k_warn(ab, "invalid return buffer manager %d\n", rbm); - ath12k_dp_rx_link_desc_return(ab, reo_desc, + ath12k_dp_rx_link_desc_return(partner_ab, reo_desc, HAL_WBM_REL_BM_ACT_REL_MSDU); continue; } @@ -3483,26 +3592,26 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, /* Process only rx fragments with one msdu per link desc below, and drop * msdu's indicated due to error reasons. + * Dynamic fragmentation not supported in Multi-link client, so drop the + * partner device buffers. */ - if (!is_frag || num_msdus > 1) { + if (!is_frag || num_msdus > 1 || + partner_ab->device_id != ab->device_id) { drop = true; + /* Return the link desc back to wbm idle list */ - ath12k_dp_rx_link_desc_return(ab, reo_desc, + ath12k_dp_rx_link_desc_return(partner_ab, reo_desc, HAL_WBM_REL_BM_ACT_PUT_IN_IDLE); } for (i = 0; i < num_msdus; i++) { - mac_id = le32_get_bits(reo_desc->info0, - HAL_REO_DEST_RING_INFO0_SRC_LINK_ID); - - pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id); - ar = ab->pdevs[pdev_id].ar; - if (!ath12k_dp_process_rx_err_buf(ar, reo_desc, - &rx_desc_used_list, + &rx_desc_used_list[device_id], drop, - msdu_cookies[i])) + msdu_cookies[i])) { + num_buffs_reaped[device_id]++; tot_n_bufs_reaped++; + } } if (tot_n_bufs_reaped >= quota) { @@ -3518,10 +3627,17 @@ exit: spin_unlock_bh(&srng->lock); - rx_ring = &dp->rx_refill_buf_ring; + for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++) { + if (!num_buffs_reaped[device_id]) + continue; - ath12k_dp_rx_bufs_replenish(ab, rx_ring, &rx_desc_used_list, - tot_n_bufs_reaped); + partner_ab = ath12k_ag_to_ab(ag, device_id); + rx_ring = &partner_ab->dp.rx_refill_buf_ring; + + ath12k_dp_rx_bufs_replenish(partner_ab, rx_ring, + &rx_desc_used_list[device_id], + num_buffs_reaped[device_id]); + } return tot_n_bufs_reaped; } @@ -3738,7 +3854,8 @@ static void ath12k_dp_rx_wbm_err(struct ath12k *ar, int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab, struct napi_struct *napi, int budget) { - LIST_HEAD(rx_desc_used_list); + struct list_head rx_desc_used_list[ATH12K_MAX_SOCS]; + struct ath12k_hw_group *ag = ab->ag; struct ath12k *ar; struct ath12k_dp *dp = &ab->dp; struct dp_rxdma_ring *rx_ring; @@ -3748,17 +3865,22 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab, struct sk_buff_head msdu_list, scatter_msdu_list; struct ath12k_skb_rxcb *rxcb; void *rx_desc; - u8 mac_id; - int num_buffs_reaped = 0; + int num_buffs_reaped[ATH12K_MAX_SOCS] = {}; + int total_num_buffs_reaped = 0; struct ath12k_rx_desc_info *desc_info; + struct ath12k_hw_link *hw_links = ag->hw_links; + struct ath12k_base *partner_ab; + u8 hw_link_id, device_id; int ret, pdev_id; struct hal_rx_desc *msdu_data; __skb_queue_head_init(&msdu_list); __skb_queue_head_init(&scatter_msdu_list); + for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++) + INIT_LIST_HEAD(&rx_desc_used_list[device_id]); + srng = &ab->hal.srng_list[dp->rx_rel_ring.ring_id]; - rx_ring = &dp->rx_refill_buf_ring; spin_lock_bh(&srng->lock); ath12k_hal_srng_access_begin(ab, srng); @@ -3794,14 +3916,27 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab, msdu = desc_info->skb; desc_info->skb = NULL; - list_add_tail(&desc_info->list, &rx_desc_used_list); + device_id = desc_info->device_id; + partner_ab = ath12k_ag_to_ab(ag, device_id); + if (unlikely(!partner_ab)) { + dev_kfree_skb_any(msdu); + + /* In any case continuation bit is set + * in the previous record, cleanup scatter_msdu_list + */ + ath12k_dp_clean_up_skb_list(&scatter_msdu_list); + continue; + } + + list_add_tail(&desc_info->list, &rx_desc_used_list[device_id]); rxcb = ATH12K_SKB_RXCB(msdu); - dma_unmap_single(ab->dev, rxcb->paddr, + dma_unmap_single(partner_ab->dev, rxcb->paddr, msdu->len + skb_tailroom(msdu), DMA_FROM_DEVICE); - num_buffs_reaped++; + num_buffs_reaped[device_id]++; + total_num_buffs_reaped++; if (!err_info.continuation) budget--; @@ -3825,9 +3960,9 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab, continue; } - mac_id = ath12k_dp_rx_get_msdu_src_link(ab, - msdu_data); - if (mac_id >= MAX_RADIOS) { + hw_link_id = ath12k_dp_rx_get_msdu_src_link(partner_ab, + msdu_data); + if (hw_link_id >= ATH12K_GROUP_MAX_RADIO) { dev_kfree_skb_any(msdu); /* In any case continuation bit is set @@ -3842,7 +3977,7 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab, skb_queue_walk(&scatter_msdu_list, msdu) { rxcb = ATH12K_SKB_RXCB(msdu); - rxcb->mac_id = mac_id; + rxcb->hw_link_id = hw_link_id; } skb_queue_splice_tail_init(&scatter_msdu_list, @@ -3850,7 +3985,7 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab, } rxcb = ATH12K_SKB_RXCB(msdu); - rxcb->mac_id = mac_id; + rxcb->hw_link_id = hw_link_id; __skb_queue_tail(&msdu_list, msdu); } @@ -3863,26 +3998,46 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab, spin_unlock_bh(&srng->lock); - if (!num_buffs_reaped) + if (!total_num_buffs_reaped) goto done; - ath12k_dp_rx_bufs_replenish(ab, rx_ring, &rx_desc_used_list, - num_buffs_reaped); + for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++) { + if (!num_buffs_reaped[device_id]) + continue; + + partner_ab = ath12k_ag_to_ab(ag, device_id); + rx_ring = &partner_ab->dp.rx_refill_buf_ring; + + ath12k_dp_rx_bufs_replenish(ab, rx_ring, + &rx_desc_used_list[device_id], + num_buffs_reaped[device_id]); + } rcu_read_lock(); while ((msdu = __skb_dequeue(&msdu_list))) { rxcb = ATH12K_SKB_RXCB(msdu); - mac_id = rxcb->mac_id; + hw_link_id = rxcb->hw_link_id; - pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id); - ar = ab->pdevs[pdev_id].ar; - - if (!ar || !rcu_dereference(ar->ab->pdevs_active[mac_id])) { + device_id = hw_links[hw_link_id].device_id; + partner_ab = ath12k_ag_to_ab(ag, device_id); + if (unlikely(!partner_ab)) { + ath12k_dbg(ab, ATH12K_DBG_DATA, + "Unable to process WBM error msdu due to invalid hw link id %d device id %d\n", + hw_link_id, device_id); dev_kfree_skb_any(msdu); continue; } - if (test_bit(ATH12K_CAC_RUNNING, &ar->dev_flags)) { + pdev_id = ath12k_hw_mac_id_to_pdev_id(partner_ab->hw_params, + hw_links[hw_link_id].pdev_idx); + ar = partner_ab->pdevs[pdev_id].ar; + + if (!ar || !rcu_dereference(ar->ab->pdevs_active[hw_link_id])) { + dev_kfree_skb_any(msdu); + continue; + } + + if (test_bit(ATH12K_FLAG_CAC_RUNNING, &ar->dev_flags)) { dev_kfree_skb_any(msdu); continue; } @@ -3890,7 +4045,7 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab, } rcu_read_unlock(); done: - return num_buffs_reaped; + return total_num_buffs_reaped; } void ath12k_dp_rx_process_reo_status(struct ath12k_base *ab) @@ -3912,7 +4067,7 @@ void ath12k_dp_rx_process_reo_status(struct ath12k_base *ab) ath12k_hal_srng_access_begin(ab, srng); while ((hdr = ath12k_hal_srng_dst_get_next_entry(ab, srng))) { - tag = u64_get_bits(hdr->tl, HAL_SRNG_TLV_HDR_TAG); + tag = le64_get_bits(hdr->tl, HAL_SRNG_TLV_HDR_TAG); switch (tag) { case HAL_REO_GET_QUEUE_STATS_STATUS: diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.h b/drivers/net/wireless/ath/ath12k/dp_rx.h index bfd4f814553e..1ce82088c954 100644 --- a/drivers/net/wireless/ath/ath12k/dp_rx.h +++ b/drivers/net/wireless/ath/ath12k/dp_rx.h @@ -85,9 +85,11 @@ static inline u32 ath12k_he_gi_to_nl80211_he_gi(u8 sgi) } int ath12k_dp_rx_ampdu_start(struct ath12k *ar, - struct ieee80211_ampdu_params *params); + struct ieee80211_ampdu_params *params, + u8 link_id); int ath12k_dp_rx_ampdu_stop(struct ath12k *ar, - struct ieee80211_ampdu_params *params); + struct ieee80211_ampdu_params *params, + u8 link_id); int ath12k_dp_rx_peer_pn_replay_config(struct ath12k_link_vif *arvif, const u8 *peer_addr, enum set_key_cmd key_cmd, diff --git a/drivers/net/wireless/ath/ath12k/fw.h b/drivers/net/wireless/ath/ath12k/fw.h index 3ff041f15fa0..273c003eff3b 100644 --- a/drivers/net/wireless/ath/ath12k/fw.h +++ b/drivers/net/wireless/ath/ath12k/fw.h @@ -23,6 +23,9 @@ enum ath12k_fw_features { */ ATH12K_FW_FEATURE_MULTI_QRTR_ID = 0, + /* The firmware supports MLO capability */ + ATH12K_FW_FEATURE_MLO, + /* keep last */ ATH12K_FW_FEATURE_COUNT, }; diff --git a/drivers/net/wireless/ath/ath12k/hal.c b/drivers/net/wireless/ath/ath12k/hal.c index fd98fac16dd5..cd59ff8e6c7b 100644 --- a/drivers/net/wireless/ath/ath12k/hal.c +++ b/drivers/net/wireless/ath/ath12k/hal.c @@ -181,7 +181,7 @@ static const struct hal_srng_config hw_srng_config_template[] = { .max_size = HAL_WBM2PPE_RELEASE_RING_BASE_MSB_RING_SIZE, }, [HAL_TX_MONITOR_BUF] = { - .start_ring_id = HAL_SRNG_SW2TXMON_BUF0, + .start_ring_id = HAL_SRNG_RING_ID_WMAC1_SW2TXMON_BUF0, .max_rings = 1, .entry_size = sizeof(struct hal_mon_buf_ring) >> 2, .mac_type = ATH12K_HAL_SRNG_PMAC, diff --git a/drivers/net/wireless/ath/ath12k/hal.h b/drivers/net/wireless/ath/ath12k/hal.h index 8a78bb9a10bc..94e2e8735958 100644 --- a/drivers/net/wireless/ath/ath12k/hal.h +++ b/drivers/net/wireless/ath/ath12k/hal.h @@ -485,8 +485,8 @@ enum hal_srng_ring_id { HAL_SRNG_RING_ID_WMAC1_RXMON2SW0 = HAL_SRNG_RING_ID_WMAC1_RXDMA2SW1, HAL_SRNG_RING_ID_WMAC1_SW2RXDMA1_DESC, HAL_SRNG_RING_ID_RXDMA_DIR_BUF, - HAL_SRNG_RING_ID_WMAC1_SW2TXMON_BUF0, HAL_SRNG_RING_ID_WMAC1_TXMON2SW0_BUF0, + HAL_SRNG_RING_ID_WMAC1_SW2TXMON_BUF0, HAL_SRNG_RING_ID_PMAC1_ID_END, }; diff --git a/drivers/net/wireless/ath/ath12k/hal_desc.h b/drivers/net/wireless/ath/ath12k/hal_desc.h index 739f73370015..7b0403d245e5 100644 --- a/drivers/net/wireless/ath/ath12k/hal_desc.h +++ b/drivers/net/wireless/ath/ath12k/hal_desc.h @@ -522,7 +522,7 @@ enum hal_tlv_tag { HAL_PHYRXHT_SIG_USR_SU = 468 /* 0x1d4 */, HAL_PHYRXHT_SIG_USR_MU_MIMO = 469 /* 0x1d5 */, HAL_PHYRX_GENERIC_U_SIG = 470 /* 0x1d6 */, - HAL_PHYRX_GENERICHT_SIG = 471 /* 0x1d7 */, + HAL_PHYRX_GENERIC_EHT_SIG = 471 /* 0x1d7 */, HAL_OVERWRITE_RESP_START = 472 /* 0x1d8 */, HAL_OVERWRITE_RESP_PREAMBLE_INFO = 473 /* 0x1d9 */, HAL_OVERWRITE_RESP_FRAME_INFO = 474 /* 0x1da */, @@ -579,9 +579,11 @@ struct hal_tlv_hdr { #define HAL_TLV_64_HDR_TAG GENMASK(9, 1) #define HAL_TLV_64_HDR_LEN GENMASK(21, 10) +#define HAL_TLV_64_USR_ID GENMASK(31, 26) +#define HAL_TLV_64_ALIGN 8 struct hal_tlv_64_hdr { - u64 tl; + __le64 tl; u8 value[]; } __packed; diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.c b/drivers/net/wireless/ath/ath12k/hal_rx.c index f7c1aaa3b5d4..ac17d6223fa7 100644 --- a/drivers/net/wireless/ath/ath12k/hal_rx.c +++ b/drivers/net/wireless/ath/ath12k/hal_rx.c @@ -26,8 +26,8 @@ static int ath12k_hal_reo_cmd_queue_stats(struct hal_tlv_64_hdr *tlv, { struct hal_reo_get_queue_stats *desc; - tlv->tl = u32_encode_bits(HAL_REO_GET_QUEUE_STATS, HAL_TLV_HDR_TAG) | - u32_encode_bits(sizeof(*desc), HAL_TLV_HDR_LEN); + tlv->tl = le64_encode_bits(HAL_REO_GET_QUEUE_STATS, HAL_TLV_HDR_TAG) | + le64_encode_bits(sizeof(*desc), HAL_TLV_HDR_LEN); desc = (struct hal_reo_get_queue_stats *)tlv->value; memset_startat(desc, 0, queue_addr_lo); @@ -59,8 +59,8 @@ static int ath12k_hal_reo_cmd_flush_cache(struct ath12k_hal *hal, hal->current_blk_index = avail_slot; } - tlv->tl = u32_encode_bits(HAL_REO_FLUSH_CACHE, HAL_TLV_HDR_TAG) | - u32_encode_bits(sizeof(*desc), HAL_TLV_HDR_LEN); + tlv->tl = le64_encode_bits(HAL_REO_FLUSH_CACHE, HAL_TLV_HDR_TAG) | + le64_encode_bits(sizeof(*desc), HAL_TLV_HDR_LEN); desc = (struct hal_reo_flush_cache *)tlv->value; memset_startat(desc, 0, cache_addr_lo); @@ -97,8 +97,8 @@ static int ath12k_hal_reo_cmd_update_rx_queue(struct hal_tlv_64_hdr *tlv, { struct hal_reo_update_rx_queue *desc; - tlv->tl = u32_encode_bits(HAL_REO_UPDATE_RX_REO_QUEUE, HAL_TLV_HDR_TAG) | - u32_encode_bits(sizeof(*desc), HAL_TLV_HDR_LEN); + tlv->tl = le64_encode_bits(HAL_REO_UPDATE_RX_REO_QUEUE, HAL_TLV_HDR_TAG) | + le64_encode_bits(sizeof(*desc), HAL_TLV_HDR_LEN); desc = (struct hal_reo_update_rx_queue *)tlv->value; memset_startat(desc, 0, queue_addr_lo); diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h index 2de7b0eba9f2..b08aa2e79f41 100644 --- a/drivers/net/wireless/ath/ath12k/hal_rx.h +++ b/drivers/net/wireless/ath/ath12k/hal_rx.h @@ -19,7 +19,7 @@ struct hal_rx_wbm_rel_info { bool hw_cc_done; }; -#define HAL_INVALID_PEERID 0xffff +#define HAL_INVALID_PEERID 0x3fff #define VHT_SIG_SU_NSS_MASK 0x7 #define HAL_RX_MAX_MCS 12 @@ -245,6 +245,8 @@ struct hal_rx_ppdu_start { __le32 rsvd[2]; } __packed; +#define HAL_RX_PPDU_END_USER_STATS_INFO0_PEER_ID GENMASK(13, 0) +#define HAL_RX_PPDU_END_USER_STATS_INFO0_DEVICE_ID GENMASK(15, 14) #define HAL_RX_PPDU_END_USER_STATS_INFO0_MPDU_CNT_FCS_ERR GENMASK(26, 16) #define HAL_RX_PPDU_END_USER_STATS_INFO1_MPDU_CNT_FCS_OK GENMASK(10, 0) @@ -299,6 +301,7 @@ struct hal_rx_ppdu_end_user_stats_ext { __le32 info4; __le32 info5; __le32 info6; + __le32 rsvd; } __packed; #define HAL_RX_HT_SIG_INFO_INFO0_MCS GENMASK(6, 0) @@ -395,11 +398,9 @@ struct hal_rx_he_sig_a_su_info { #define HAL_RX_HE_SIG_A_MU_DL_INFO0_DOPPLER_INDICATION BIT(25) #define HAL_RX_HE_SIG_A_MU_DL_INFO1_TXOP_DURATION GENMASK(6, 0) -#define HAL_RX_HE_SIG_A_MU_DL_INFO1_CODING BIT(7) #define HAL_RX_HE_SIG_A_MU_DL_INFO1_NUM_LTF_SYMB GENMASK(10, 8) #define HAL_RX_HE_SIG_A_MU_DL_INFO1_LDPC_EXTRA BIT(11) #define HAL_RX_HE_SIG_A_MU_DL_INFO1_STBC BIT(12) -#define HAL_RX_HE_SIG_A_MU_DL_INFO1_TXBF BIT(10) #define HAL_RX_HE_SIG_A_MU_DL_INFO1_PKT_EXT_FACTOR GENMASK(14, 13) #define HAL_RX_HE_SIG_A_MU_DL_INFO1_PKT_EXT_PE_DISAM BIT(15) @@ -425,7 +426,7 @@ struct hal_rx_he_sig_b2_mu_info { #define HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_ID GENMASK(10, 0) #define HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_NSTS GENMASK(13, 11) -#define HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_TXBF BIT(19) +#define HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_TXBF BIT(14) #define HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_MCS GENMASK(18, 15) #define HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_DCM BIT(19) #define HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_CODING BIT(20) @@ -453,7 +454,8 @@ struct hal_rx_phyrx_rssi_legacy_info { } __packed; #define HAL_RX_MPDU_START_INFO0_PPDU_ID GENMASK(31, 16) -#define HAL_RX_MPDU_START_INFO1_PEERID GENMASK(31, 16) +#define HAL_RX_MPDU_START_INFO1_PEERID GENMASK(29, 16) +#define HAL_RX_MPDU_START_INFO1_DEVICE_ID GENMASK(31, 30) #define HAL_RX_MPDU_START_INFO2_MPDU_LEN GENMASK(13, 0) struct hal_rx_mpdu_start { __le32 rsvd0[9]; @@ -468,7 +470,7 @@ struct hal_rx_mpdu_start { struct hal_rx_ppdu_end_duration { __le32 rsvd0[9]; __le32 info0; - __le32 rsvd1[4]; + __le32 rsvd1[18]; } __packed; struct hal_rx_rxpcu_classification_overview { diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index d493ec812055..2d062b5904a8 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -1,10 +1,11 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. */ #include +#include #include #include "mac.h" @@ -501,6 +502,41 @@ static int ath12k_mac_vif_link_chan(struct ieee80211_vif *vif, u8 link_id, return 0; } +static struct ieee80211_bss_conf * +ath12k_mac_get_link_bss_conf(struct ath12k_link_vif *arvif) +{ + struct ieee80211_vif *vif = arvif->ahvif->vif; + struct ieee80211_bss_conf *link_conf; + struct ath12k *ar = arvif->ar; + + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + if (arvif->link_id >= IEEE80211_MLD_MAX_NUM_LINKS) + return NULL; + + link_conf = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy, + vif->link_conf[arvif->link_id]); + + return link_conf; +} + +static struct ieee80211_link_sta *ath12k_mac_get_link_sta(struct ath12k_link_sta *arsta) +{ + struct ath12k_sta *ahsta = arsta->ahsta; + struct ieee80211_sta *sta = ath12k_ahsta_to_sta(ahsta); + struct ieee80211_link_sta *link_sta; + + lockdep_assert_wiphy(ahsta->ahvif->ah->hw->wiphy); + + if (arsta->link_id >= IEEE80211_MLD_MAX_NUM_LINKS) + return NULL; + + link_sta = wiphy_dereference(ahsta->ahvif->ah->hw->wiphy, + sta->link[arsta->link_id]); + + return link_sta; +} + static bool ath12k_mac_bitrate_is_cck(int bitrate) { switch (bitrate) { @@ -648,6 +684,18 @@ struct ath12k *ath12k_mac_get_ar_by_pdev_id(struct ath12k_base *ab, u32 pdev_id) return NULL; } +static bool ath12k_mac_is_ml_arvif(struct ath12k_link_vif *arvif) +{ + struct ath12k_vif *ahvif = arvif->ahvif; + + lockdep_assert_wiphy(ahvif->ah->hw->wiphy); + + if (ahvif->vif->valid_links & BIT(arvif->link_id)) + return true; + + return false; +} + static struct ath12k *ath12k_mac_get_ar_by_chan(struct ieee80211_hw *hw, struct ieee80211_channel *channel) { @@ -661,8 +709,8 @@ static struct ath12k *ath12k_mac_get_ar_by_chan(struct ieee80211_hw *hw, return ar; for_each_ar(ah, ar, i) { - if (channel->center_freq >= ar->freq_low && - channel->center_freq <= ar->freq_high) + if (channel->center_freq >= KHZ_TO_MHZ(ar->freq_range.start_freq) && + channel->center_freq <= KHZ_TO_MHZ(ar->freq_range.end_freq)) return ar; } return NULL; @@ -678,11 +726,14 @@ static struct ath12k *ath12k_get_ar_by_ctx(struct ieee80211_hw *hw, } static struct ath12k *ath12k_get_ar_by_vif(struct ieee80211_hw *hw, - struct ieee80211_vif *vif) + struct ieee80211_vif *vif, + u8 link_id) { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); - struct ath12k_link_vif *arvif = &ahvif->deflink; struct ath12k_hw *ah = ath12k_hw_to_ah(hw); + struct ath12k_link_vif *arvif; + + lockdep_assert_wiphy(hw->wiphy); /* If there is one pdev within ah, then we return * ar directly. @@ -690,12 +741,27 @@ static struct ath12k *ath12k_get_ar_by_vif(struct ieee80211_hw *hw, if (ah->num_radio == 1) return ah->radio; - if (arvif->is_created) + if (!(ahvif->links_map & BIT(link_id))) + return NULL; + + arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); + if (arvif && arvif->is_created) return arvif->ar; return NULL; } +void ath12k_mac_get_any_chanctx_conf_iter(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *conf, + void *data) +{ + struct ath12k_mac_get_any_chanctx_conf_arg *arg = data; + struct ath12k *ctx_ar = ath12k_get_ar_by_ctx(hw, conf); + + if (ctx_ar == arg->ar) + arg->chanctx_conf = conf; +} + static struct ath12k_link_vif *ath12k_mac_get_vif_up(struct ath12k *ar) { struct ath12k_link_vif *arvif; @@ -1239,7 +1305,7 @@ static int ath12k_mac_monitor_stop(struct ath12k *ar) return ret; } -static int ath12k_mac_vdev_stop(struct ath12k_link_vif *arvif) +int ath12k_mac_vdev_stop(struct ath12k_link_vif *arvif) { struct ath12k_vif *ahvif = arvif->ahvif; struct ath12k *ar = arvif->ar; @@ -1269,8 +1335,8 @@ static int ath12k_mac_vdev_stop(struct ath12k_link_vif *arvif) ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "vdev %pM stopped, vdev_id %d\n", ahvif->vif->addr, arvif->vdev_id); - if (test_bit(ATH12K_CAC_RUNNING, &ar->dev_flags)) { - clear_bit(ATH12K_CAC_RUNNING, &ar->dev_flags); + if (test_bit(ATH12K_FLAG_CAC_RUNNING, &ar->dev_flags)) { + clear_bit(ATH12K_FLAG_CAC_RUNNING, &ar->dev_flags); ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "CAC Stopped for vdev %d\n", arvif->vdev_id); } @@ -1486,7 +1552,7 @@ static void ath12k_mac_set_arvif_ies(struct ath12k_link_vif *arvif, struct sk_bu static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif) { struct ath12k_vif *ahvif = arvif->ahvif; - struct ieee80211_bss_conf *bss_conf = &ahvif->vif->bss_conf; + struct ieee80211_bss_conf *bss_conf; struct ath12k_wmi_bcn_tmpl_ema_arg ema_args; struct ieee80211_ema_beacons *beacons; struct ath12k_link_vif *tx_arvif; @@ -1495,10 +1561,19 @@ static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif) int ret = 0; u8 i; + bss_conf = ath12k_mac_get_link_bss_conf(arvif); + if (!bss_conf) { + ath12k_warn(arvif->ar->ab, + "failed to get link bss conf to update bcn tmpl for vif %pM link %u\n", + ahvif->vif->addr, arvif->link_id); + return -ENOLINK; + } + tx_ahvif = ath12k_vif_to_ahvif(ahvif->vif->mbssid_tx_vif); tx_arvif = &tx_ahvif->deflink; beacons = ieee80211_beacon_get_template_ema_list(ath12k_ar_to_hw(tx_arvif->ar), - tx_ahvif->vif, 0); + tx_ahvif->vif, + tx_arvif->link_id); if (!beacons || !beacons->cnt) { ath12k_warn(arvif->ar->ab, "failed to get ema beacon templates from mac80211\n"); @@ -1540,6 +1615,7 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_link_vif *arvif) { struct ath12k_vif *ahvif = arvif->ahvif; struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif); + struct ieee80211_bss_conf *link_conf; struct ath12k_link_vif *tx_arvif = arvif; struct ath12k *ar = arvif->ar; struct ath12k_base *ab = ar->ab; @@ -1552,18 +1628,25 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_link_vif *arvif) if (ahvif->vdev_type != WMI_VDEV_TYPE_AP) return 0; + link_conf = ath12k_mac_get_link_bss_conf(arvif); + if (!link_conf) { + ath12k_warn(ar->ab, "unable to access bss link conf to set bcn tmpl for vif %pM link %u\n", + vif->addr, arvif->link_id); + return -ENOLINK; + } + if (vif->mbssid_tx_vif) { tx_ahvif = ath12k_vif_to_ahvif(vif->mbssid_tx_vif); tx_arvif = &tx_ahvif->deflink; if (tx_arvif != arvif && arvif->is_up) return 0; - if (vif->bss_conf.ema_ap) + if (link_conf->ema_ap) return ath12k_mac_setup_bcn_tmpl_ema(arvif); } bcn = ieee80211_beacon_get_template(ath12k_ar_to_hw(tx_arvif->ar), tx_ahvif->vif, - &offs, 0); + &offs, tx_arvif->link_id); if (!bcn) { ath12k_warn(ab, "failed to get beacon template from mac80211\n"); return -EPERM; @@ -1573,7 +1656,7 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_link_vif *arvif) ath12k_mac_set_arvif_ies(arvif, bcn, 0, NULL); } else { ath12k_mac_set_arvif_ies(arvif, bcn, - ahvif->vif->bss_conf.bssid_index, + link_conf->bssid_index, &nontx_profile_found); if (!nontx_profile_found) ath12k_warn(ab, @@ -1644,7 +1727,7 @@ static void ath12k_control_beaconing(struct ath12k_link_vif *arvif, ahvif->aid = 0; - ether_addr_copy(arvif->bssid, info->bssid); + ether_addr_copy(arvif->bssid, info->addr); params.vdev_id = arvif->vdev_id; params.aid = ahvif->aid; @@ -1749,6 +1832,7 @@ static void ath12k_peer_assoc_h_basic(struct ath12k *ar, struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); struct ieee80211_hw *hw = ath12k_ar_to_hw(ar); + struct ieee80211_bss_conf *bss_conf; u32 aid; lockdep_assert_wiphy(hw->wiphy); @@ -1758,14 +1842,22 @@ static void ath12k_peer_assoc_h_basic(struct ath12k *ar, else aid = sta->aid; - ether_addr_copy(arg->peer_mac, sta->addr); + ether_addr_copy(arg->peer_mac, arsta->addr); arg->vdev_id = arvif->vdev_id; arg->peer_associd = aid; arg->auth_flag = true; /* TODO: STA WAR in ath10k for listen interval required? */ arg->peer_listen_intval = hw->conf.listen_interval; arg->peer_nss = 1; - arg->peer_caps = vif->bss_conf.assoc_capability; + + bss_conf = ath12k_mac_get_link_bss_conf(arvif); + if (!bss_conf) { + ath12k_warn(ar->ab, "unable to access bss link conf in peer assoc for vif %pM link %u\n", + vif->addr, arvif->link_id); + return; + } + + arg->peer_caps = bss_conf->assoc_capability; } static void ath12k_peer_assoc_h_crypto(struct ath12k *ar, @@ -1775,7 +1867,7 @@ static void ath12k_peer_assoc_h_crypto(struct ath12k *ar, { struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - struct ieee80211_bss_conf *info = &vif->bss_conf; + struct ieee80211_bss_conf *info; struct cfg80211_chan_def def; struct cfg80211_bss *bss; struct ieee80211_hw *hw = ath12k_ar_to_hw(ar); @@ -1784,6 +1876,13 @@ static void ath12k_peer_assoc_h_crypto(struct ath12k *ar, lockdep_assert_wiphy(hw->wiphy); + info = ath12k_mac_get_link_bss_conf(arvif); + if (!info) { + ath12k_warn(ar->ab, "unable to access bss link conf for peer assoc crypto for vif %pM link %u\n", + vif->addr, arvif->link_id); + return; + } + if (WARN_ON(ath12k_mac_vif_link_chan(vif, arvif->link_id, &def))) return; @@ -1839,6 +1938,7 @@ static void ath12k_peer_assoc_h_rates(struct ath12k *ar, struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); struct wmi_rate_set_arg *rateset = &arg->peer_legacy_rates; + struct ieee80211_link_sta *link_sta; struct cfg80211_chan_def def; const struct ieee80211_supported_band *sband; const struct ieee80211_rate *rates; @@ -1853,9 +1953,16 @@ static void ath12k_peer_assoc_h_rates(struct ath12k *ar, if (WARN_ON(ath12k_mac_vif_link_chan(vif, arvif->link_id, &def))) return; + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in peer assoc rates for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + band = def.chan->band; sband = hw->wiphy->bands[band]; - ratemask = sta->deflink.supp_rates[band]; + ratemask = link_sta->supp_rates[band]; ratemask &= arvif->bitrate_mask.control[band].legacy; rates = sband->bitrates; @@ -1902,7 +2009,8 @@ static void ath12k_peer_assoc_h_ht(struct ath12k *ar, { struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - const struct ieee80211_sta_ht_cap *ht_cap = &sta->deflink.ht_cap; + const struct ieee80211_sta_ht_cap *ht_cap; + struct ieee80211_link_sta *link_sta; struct cfg80211_chan_def def; enum nl80211_band band; const u8 *ht_mcs_mask; @@ -1915,6 +2023,14 @@ static void ath12k_peer_assoc_h_ht(struct ath12k *ar, if (WARN_ON(ath12k_mac_vif_link_chan(vif, arvif->link_id, &def))) return; + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in peer assoc ht for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + + ht_cap = &link_sta->ht_cap; if (!ht_cap->ht_supported) return; @@ -1938,7 +2054,7 @@ static void ath12k_peer_assoc_h_ht(struct ath12k *ar, if (ht_cap->cap & IEEE80211_HT_CAP_LDPC_CODING) arg->ldpc_flag = true; - if (sta->deflink.bandwidth >= IEEE80211_STA_RX_BW_40) { + if (link_sta->bandwidth >= IEEE80211_STA_RX_BW_40) { arg->bw_40 = true; arg->peer_rate_caps |= WMI_HOST_RC_CW40_FLAG; } @@ -1988,7 +2104,7 @@ static void ath12k_peer_assoc_h_ht(struct ath12k *ar, arg->peer_ht_rates.rates[i] = i; } else { arg->peer_ht_rates.num_rates = n; - arg->peer_nss = min(sta->deflink.rx_nss, max_nss); + arg->peer_nss = min(link_sta->rx_nss, max_nss); } ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac ht peer %pM mcs cnt %d nss %d\n", @@ -2064,7 +2180,8 @@ static void ath12k_peer_assoc_h_vht(struct ath12k *ar, { struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - const struct ieee80211_sta_vht_cap *vht_cap = &sta->deflink.vht_cap; + const struct ieee80211_sta_vht_cap *vht_cap; + struct ieee80211_link_sta *link_sta; struct cfg80211_chan_def def; enum nl80211_band band; const u16 *vht_mcs_mask; @@ -2078,6 +2195,14 @@ static void ath12k_peer_assoc_h_vht(struct ath12k *ar, if (WARN_ON(ath12k_mac_vif_link_chan(vif, arvif->link_id, &def))) return; + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in peer assoc vht for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + + vht_cap = &link_sta->vht_cap; if (!vht_cap->vht_supported) return; @@ -2110,10 +2235,10 @@ static void ath12k_peer_assoc_h_vht(struct ath12k *ar, (1U << (IEEE80211_HT_MAX_AMPDU_FACTOR + ampdu_factor)) - 1); - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_80) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_80) arg->bw_80 = true; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_160) arg->bw_160 = true; /* Calculate peer NSS capability from VHT capabilities if STA @@ -2127,7 +2252,7 @@ static void ath12k_peer_assoc_h_vht(struct ath12k *ar, vht_mcs_mask[i]) max_nss = i + 1; } - arg->peer_nss = min(sta->deflink.rx_nss, max_nss); + arg->peer_nss = min(link_sta->rx_nss, max_nss); arg->rx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.rx_highest); arg->rx_mcs_set = __le16_to_cpu(vht_cap->vht_mcs.rx_mcs_map); arg->tx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.tx_highest); @@ -2150,7 +2275,7 @@ static void ath12k_peer_assoc_h_vht(struct ath12k *ar, arg->tx_max_mcs_nss = 0xFF; ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vht peer %pM max_mpdu %d flags 0x%x\n", - sta->addr, arg->peer_max_mpdu, arg->peer_flags); + arsta->addr, arg->peer_max_mpdu, arg->peer_flags); /* TODO: rxnss_override */ } @@ -2162,7 +2287,9 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar, { struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - const struct ieee80211_sta_he_cap *he_cap = &sta->deflink.he_cap; + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_bss_conf *link_conf; + struct ieee80211_link_sta *link_sta; int i; u8 ampdu_factor, max_nss; u8 rx_mcs_80 = IEEE80211_HE_MCS_NOT_SUPPORTED; @@ -2171,6 +2298,21 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar, bool support_160; u16 v; + link_conf = ath12k_mac_get_link_bss_conf(arvif); + if (!link_conf) { + ath12k_warn(ar->ab, "unable to access bss link conf in peer assoc he for vif %pM link %u", + vif->addr, arvif->link_id); + return; + } + + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in peer assoc he for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + + he_cap = &link_sta->he_cap; if (!he_cap->has_he) return; @@ -2208,13 +2350,13 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar, else max_nss = rx_mcs_80; - arg->peer_nss = min(sta->deflink.rx_nss, max_nss); + arg->peer_nss = min(link_sta->rx_nss, max_nss); memcpy(&arg->peer_he_cap_macinfo, he_cap->he_cap_elem.mac_cap_info, sizeof(he_cap->he_cap_elem.mac_cap_info)); memcpy(&arg->peer_he_cap_phyinfo, he_cap->he_cap_elem.phy_cap_info, sizeof(he_cap->he_cap_elem.phy_cap_info)); - arg->peer_he_ops = vif->bss_conf.he_oper.params; + arg->peer_he_ops = link_conf->he_oper.params; /* the top most byte is used to indicate BSS color info */ arg->peer_he_ops &= 0xffffff; @@ -2235,10 +2377,10 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar, IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK); if (ampdu_factor) { - if (sta->deflink.vht_cap.vht_supported) + if (link_sta->vht_cap.vht_supported) arg->peer_max_mpdu = (1 << (IEEE80211_HE_VHT_MAX_AMPDU_FACTOR + ampdu_factor)) - 1; - else if (sta->deflink.ht_cap.ht_supported) + else if (link_sta->ht_cap.ht_supported) arg->peer_max_mpdu = (1 << (IEEE80211_HE_HT_MAX_AMPDU_FACTOR + ampdu_factor)) - 1; } @@ -2279,7 +2421,7 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar, if (he_cap->he_cap_elem.mac_cap_info[0] & IEEE80211_HE_MAC_CAP0_TWT_REQ) arg->twt_requester = true; - switch (sta->deflink.bandwidth) { + switch (link_sta->bandwidth) { case IEEE80211_STA_RX_BW_160: if (he_cap->he_cap_elem.phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) { @@ -2319,7 +2461,8 @@ static void ath12k_peer_assoc_h_he_6ghz(struct ath12k *ar, { struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - const struct ieee80211_sta_he_cap *he_cap = &sta->deflink.he_cap; + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_link_sta *link_sta; struct cfg80211_chan_def def; enum nl80211_band band; u8 ampdu_factor, mpdu_density; @@ -2329,22 +2472,31 @@ static void ath12k_peer_assoc_h_he_6ghz(struct ath12k *ar, band = def.chan->band; - if (!arg->he_flag || band != NL80211_BAND_6GHZ || !sta->deflink.he_6ghz_capa.capa) + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in peer assoc he 6ghz for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + + he_cap = &link_sta->he_cap; + + if (!arg->he_flag || band != NL80211_BAND_6GHZ || !link_sta->he_6ghz_capa.capa) return; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_40) arg->bw_40 = true; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_80) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_80) arg->bw_80 = true; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_160) arg->bw_160 = true; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_320) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_320) arg->bw_320 = true; - arg->peer_he_caps_6ghz = le16_to_cpu(sta->deflink.he_6ghz_capa.capa); + arg->peer_he_caps_6ghz = le16_to_cpu(link_sta->he_6ghz_capa.capa); mpdu_density = u32_get_bits(arg->peer_he_caps_6ghz, IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START); @@ -2388,10 +2540,23 @@ static void ath12k_peer_assoc_h_smps(struct ath12k_link_sta *arsta, struct ath12k_wmi_peer_assoc_arg *arg) { struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - const struct ieee80211_he_6ghz_capa *he_6ghz_capa = &sta->deflink.he_6ghz_capa; - const struct ieee80211_sta_ht_cap *ht_cap = &sta->deflink.ht_cap; + const struct ieee80211_he_6ghz_capa *he_6ghz_capa; + struct ath12k_link_vif *arvif = arsta->arvif; + const struct ieee80211_sta_ht_cap *ht_cap; + struct ieee80211_link_sta *link_sta; + struct ath12k *ar = arvif->ar; int smps; + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in peer assoc he for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + + he_6ghz_capa = &link_sta->he_6ghz_capa; + ht_cap = &link_sta->ht_cap; + if (!ht_cap->ht_supported && !he_6ghz_capa->capa) return; @@ -2446,7 +2611,7 @@ static void ath12k_peer_assoc_h_qos(struct ath12k *ar, } ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac peer %pM qos %d\n", - sta->addr, arg->qos_flag); + arsta->addr, arg->qos_flag); } static int ath12k_peer_assoc_qos_ap(struct ath12k *ar, @@ -2486,26 +2651,26 @@ static int ath12k_peer_assoc_qos_ap(struct ath12k *ar, arg.param = WMI_AP_PS_PEER_PARAM_UAPSD; arg.value = uapsd; - ret = ath12k_wmi_send_set_ap_ps_param_cmd(ar, sta->addr, &arg); + ret = ath12k_wmi_send_set_ap_ps_param_cmd(ar, arsta->addr, &arg); if (ret) goto err; arg.param = WMI_AP_PS_PEER_PARAM_MAX_SP; arg.value = max_sp; - ret = ath12k_wmi_send_set_ap_ps_param_cmd(ar, sta->addr, &arg); + ret = ath12k_wmi_send_set_ap_ps_param_cmd(ar, arsta->addr, &arg); if (ret) goto err; /* TODO: revisit during testing */ arg.param = WMI_AP_PS_PEER_PARAM_SIFS_RESP_FRMTYPE; arg.value = DISABLE_SIFS_RESPONSE_TRIGGER; - ret = ath12k_wmi_send_set_ap_ps_param_cmd(ar, sta->addr, &arg); + ret = ath12k_wmi_send_set_ap_ps_param_cmd(ar, arsta->addr, &arg); if (ret) goto err; arg.param = WMI_AP_PS_PEER_PARAM_SIFS_RESP_UAPSD; arg.value = DISABLE_SIFS_RESPONSE_TRIGGER; - ret = ath12k_wmi_send_set_ap_ps_param_cmd(ar, sta->addr, &arg); + ret = ath12k_wmi_send_set_ap_ps_param_cmd(ar, arsta->addr, &arg); if (ret) goto err; @@ -2517,17 +2682,17 @@ err: return ret; } -static bool ath12k_mac_sta_has_ofdm_only(struct ieee80211_sta *sta) +static bool ath12k_mac_sta_has_ofdm_only(struct ieee80211_link_sta *sta) { - return sta->deflink.supp_rates[NL80211_BAND_2GHZ] >> + return sta->supp_rates[NL80211_BAND_2GHZ] >> ATH12K_MAC_FIRST_OFDM_RATE_IDX; } static enum wmi_phy_mode ath12k_mac_get_phymode_vht(struct ath12k *ar, - struct ieee80211_sta *sta) + struct ieee80211_link_sta *link_sta) { - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160) { - switch (sta->deflink.vht_cap.cap & + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_160) { + switch (link_sta->vht_cap.cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: return MODE_11AC_VHT160; @@ -2539,74 +2704,74 @@ static enum wmi_phy_mode ath12k_mac_get_phymode_vht(struct ath12k *ar, } } - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_80) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_80) return MODE_11AC_VHT80; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_40) return MODE_11AC_VHT40; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_20) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_20) return MODE_11AC_VHT20; return MODE_UNKNOWN; } static enum wmi_phy_mode ath12k_mac_get_phymode_he(struct ath12k *ar, - struct ieee80211_sta *sta) + struct ieee80211_link_sta *link_sta) { - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160) { - if (sta->deflink.he_cap.he_cap_elem.phy_cap_info[0] & + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_160) { + if (link_sta->he_cap.he_cap_elem.phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) return MODE_11AX_HE160; - else if (sta->deflink.he_cap.he_cap_elem.phy_cap_info[0] & + else if (link_sta->he_cap.he_cap_elem.phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) return MODE_11AX_HE80_80; /* not sure if this is a valid case? */ return MODE_11AX_HE160; } - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_80) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_80) return MODE_11AX_HE80; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_40) return MODE_11AX_HE40; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_20) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_20) return MODE_11AX_HE20; return MODE_UNKNOWN; } static enum wmi_phy_mode ath12k_mac_get_phymode_eht(struct ath12k *ar, - struct ieee80211_sta *sta) + struct ieee80211_link_sta *link_sta) { - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_320) - if (sta->deflink.eht_cap.eht_cap_elem.phy_cap_info[0] & + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_320) + if (link_sta->eht_cap.eht_cap_elem.phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) return MODE_11BE_EHT320; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160) { - if (sta->deflink.he_cap.he_cap_elem.phy_cap_info[0] & + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_160) { + if (link_sta->he_cap.he_cap_elem.phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) return MODE_11BE_EHT160; - if (sta->deflink.he_cap.he_cap_elem.phy_cap_info[0] & + if (link_sta->he_cap.he_cap_elem.phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) return MODE_11BE_EHT80_80; ath12k_warn(ar->ab, "invalid EHT PHY capability info for 160 Mhz: %d\n", - sta->deflink.he_cap.he_cap_elem.phy_cap_info[0]); + link_sta->he_cap.he_cap_elem.phy_cap_info[0]); return MODE_11BE_EHT160; } - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_80) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_80) return MODE_11BE_EHT80; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_40) return MODE_11BE_EHT40; - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_20) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_20) return MODE_11BE_EHT20; return MODE_UNKNOWN; @@ -2617,6 +2782,7 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar, struct ath12k_link_sta *arsta, struct ath12k_wmi_peer_assoc_arg *arg) { + struct ieee80211_link_sta *link_sta; struct cfg80211_chan_def def; enum nl80211_band band; const u8 *ht_mcs_mask; @@ -2635,33 +2801,40 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar, ht_mcs_mask = arvif->bitrate_mask.control[band].ht_mcs; vht_mcs_mask = arvif->bitrate_mask.control[band].vht_mcs; + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in peer assoc he for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + switch (band) { case NL80211_BAND_2GHZ: - if (sta->deflink.eht_cap.has_eht) { - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40) + if (link_sta->eht_cap.has_eht) { + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_40) phymode = MODE_11BE_EHT40_2G; else phymode = MODE_11BE_EHT20_2G; - } else if (sta->deflink.he_cap.has_he) { - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_80) + } else if (link_sta->he_cap.has_he) { + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_80) phymode = MODE_11AX_HE80_2G; - else if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40) + else if (link_sta->bandwidth == IEEE80211_STA_RX_BW_40) phymode = MODE_11AX_HE40_2G; else phymode = MODE_11AX_HE20_2G; - } else if (sta->deflink.vht_cap.vht_supported && + } else if (link_sta->vht_cap.vht_supported && !ath12k_peer_assoc_h_vht_masked(vht_mcs_mask)) { - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_40) phymode = MODE_11AC_VHT40; else phymode = MODE_11AC_VHT20; - } else if (sta->deflink.ht_cap.ht_supported && + } else if (link_sta->ht_cap.ht_supported && !ath12k_peer_assoc_h_ht_masked(ht_mcs_mask)) { - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_40) + if (link_sta->bandwidth == IEEE80211_STA_RX_BW_40) phymode = MODE_11NG_HT40; else phymode = MODE_11NG_HT20; - } else if (ath12k_mac_sta_has_ofdm_only(sta)) { + } else if (ath12k_mac_sta_has_ofdm_only(link_sta)) { phymode = MODE_11G; } else { phymode = MODE_11B; @@ -2670,16 +2843,16 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar, case NL80211_BAND_5GHZ: case NL80211_BAND_6GHZ: /* Check EHT first */ - if (sta->deflink.eht_cap.has_eht) { - phymode = ath12k_mac_get_phymode_eht(ar, sta); - } else if (sta->deflink.he_cap.has_he) { - phymode = ath12k_mac_get_phymode_he(ar, sta); - } else if (sta->deflink.vht_cap.vht_supported && + if (link_sta->eht_cap.has_eht) { + phymode = ath12k_mac_get_phymode_eht(ar, link_sta); + } else if (link_sta->he_cap.has_he) { + phymode = ath12k_mac_get_phymode_he(ar, link_sta); + } else if (link_sta->vht_cap.vht_supported && !ath12k_peer_assoc_h_vht_masked(vht_mcs_mask)) { - phymode = ath12k_mac_get_phymode_vht(ar, sta); - } else if (sta->deflink.ht_cap.ht_supported && + phymode = ath12k_mac_get_phymode_vht(ar, link_sta); + } else if (link_sta->ht_cap.ht_supported && !ath12k_peer_assoc_h_ht_masked(ht_mcs_mask)) { - if (sta->deflink.bandwidth >= IEEE80211_STA_RX_BW_40) + if (link_sta->bandwidth >= IEEE80211_STA_RX_BW_40) phymode = MODE_11NA_HT40; else phymode = MODE_11NA_HT20; @@ -2692,7 +2865,7 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar, } ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac peer %pM phymode %s\n", - sta->addr, ath12k_mac_phymode_str(phymode)); + arsta->addr, ath12k_mac_phymode_str(phymode)); arg->peer_phymode = phymode; WARN_ON(phymode == MODE_UNKNOWN); @@ -2767,15 +2940,25 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, struct ath12k_wmi_peer_assoc_arg *arg) { struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - const struct ieee80211_sta_eht_cap *eht_cap = &sta->deflink.eht_cap; - const struct ieee80211_sta_he_cap *he_cap = &sta->deflink.he_cap; const struct ieee80211_eht_mcs_nss_supp_20mhz_only *bw_20; const struct ieee80211_eht_mcs_nss_supp_bw *bw; + const struct ieee80211_sta_eht_cap *eht_cap; + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_link_sta *link_sta; u32 *rx_mcs, *tx_mcs; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); - if (!sta->deflink.he_cap.has_he || !eht_cap->has_eht) + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in peer assoc eht for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + + eht_cap = &link_sta->eht_cap; + he_cap = &link_sta->he_cap; + if (!he_cap->has_he || !eht_cap->has_eht) return; arg->eht_flag = true; @@ -2794,7 +2977,7 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, rx_mcs = arg->peer_eht_rx_mcs_set; tx_mcs = arg->peer_eht_tx_mcs_set; - switch (sta->deflink.bandwidth) { + switch (link_sta->bandwidth) { case IEEE80211_STA_RX_BW_320: bw = &eht_cap->eht_mcs_nss_supp.bw._320; ath12k_mac_set_eht_mcs(bw->rx_tx_mcs9_max_nss, @@ -2846,6 +3029,67 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, arg->punct_bitmap = ~arvif->punct_bitmap; } +static void ath12k_peer_assoc_h_mlo(struct ath12k_link_sta *arsta, + struct ath12k_wmi_peer_assoc_arg *arg) +{ + struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); + struct peer_assoc_mlo_params *ml = &arg->ml; + struct ath12k_sta *ahsta = arsta->ahsta; + struct ath12k_link_sta *arsta_p; + struct ath12k_link_vif *arvif; + unsigned long links; + u8 link_id; + int i; + + if (!sta->mlo || ahsta->ml_peer_id == ATH12K_MLO_PEER_ID_INVALID) + return; + + ml->enabled = true; + ml->assoc_link = arsta->is_assoc_link; + + /* For now considering the primary umac based on assoc link */ + ml->primary_umac = arsta->is_assoc_link; + ml->peer_id_valid = true; + ml->logical_link_idx_valid = true; + + ether_addr_copy(ml->mld_addr, sta->addr); + ml->logical_link_idx = arsta->link_idx; + ml->ml_peer_id = ahsta->ml_peer_id; + ml->ieee_link_id = arsta->link_id; + ml->num_partner_links = 0; + links = ahsta->links_map; + + rcu_read_lock(); + + i = 0; + + for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { + if (i >= ATH12K_WMI_MLO_MAX_LINKS) + break; + + arsta_p = rcu_dereference(ahsta->link[link_id]); + arvif = rcu_dereference(ahsta->ahvif->link[link_id]); + + if (arsta_p == arsta) + continue; + + if (!arvif->is_started) + continue; + + ml->partner_info[i].vdev_id = arvif->vdev_id; + ml->partner_info[i].hw_link_id = arvif->ar->pdev->hw_link_id; + ml->partner_info[i].assoc_link = arsta_p->is_assoc_link; + ml->partner_info[i].primary_umac = arsta_p->is_assoc_link; + ml->partner_info[i].logical_link_idx_valid = true; + ml->partner_info[i].logical_link_idx = arsta_p->link_idx; + ml->num_partner_links++; + + i++; + } + + rcu_read_unlock(); +} + static void ath12k_peer_assoc_prepare(struct ath12k *ar, struct ath12k_link_vif *arvif, struct ath12k_link_sta *arsta, @@ -2870,6 +3114,7 @@ static void ath12k_peer_assoc_prepare(struct ath12k *ar, ath12k_peer_assoc_h_qos(ar, arvif, arsta, arg); ath12k_peer_assoc_h_phymode(ar, arvif, arsta, arg); ath12k_peer_assoc_h_smps(arsta, arg); + ath12k_peer_assoc_h_mlo(arsta, arg); /* TODO: amsdu_disable req? */ } @@ -2900,7 +3145,8 @@ static void ath12k_bss_assoc(struct ath12k *ar, struct ath12k_vif *ahvif = arvif->ahvif; struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif); struct ath12k_wmi_vdev_up_params params = {}; - struct ath12k_wmi_peer_assoc_arg peer_arg; + struct ieee80211_link_sta *link_sta; + u8 link_id = bss_conf->link_id; struct ath12k_link_sta *arsta; struct ieee80211_sta *ap_sta; struct ath12k_sta *ahsta; @@ -2910,32 +3156,48 @@ static void ath12k_bss_assoc(struct ath12k *ar, lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); - ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %i assoc bssid %pM aid %d\n", - arvif->vdev_id, arvif->bssid, ahvif->aid); + struct ath12k_wmi_peer_assoc_arg *peer_arg __free(kfree) = + kzalloc(sizeof(*peer_arg), GFP_KERNEL); + if (!peer_arg) + return; + + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, + "mac vdev %i link id %u assoc bssid %pM aid %d\n", + arvif->vdev_id, link_id, arvif->bssid, ahvif->aid); rcu_read_lock(); - ap_sta = ieee80211_find_sta(vif, bss_conf->bssid); + /* During ML connection, cfg.ap_addr has the MLD address. For + * non-ML connection, it has the BSSID. + */ + ap_sta = ieee80211_find_sta(vif, vif->cfg.ap_addr); if (!ap_sta) { ath12k_warn(ar->ab, "failed to find station entry for bss %pM vdev %i\n", - bss_conf->bssid, arvif->vdev_id); + vif->cfg.ap_addr, arvif->vdev_id); rcu_read_unlock(); return; } ahsta = ath12k_sta_to_ahsta(ap_sta); - arsta = &ahsta->deflink; + arsta = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy, + ahsta->link[link_id]); if (WARN_ON(!arsta)) { rcu_read_unlock(); return; } - ath12k_peer_assoc_prepare(ar, arvif, arsta, &peer_arg, false); + link_sta = ath12k_mac_get_link_sta(arsta); + if (WARN_ON(!link_sta)) { + rcu_read_unlock(); + return; + } + + ath12k_peer_assoc_prepare(ar, arvif, arsta, peer_arg, false); rcu_read_unlock(); - ret = ath12k_wmi_send_peer_assoc_cmd(ar, &peer_arg); + ret = ath12k_wmi_send_peer_assoc_cmd(ar, peer_arg); if (ret) { ath12k_warn(ar->ab, "failed to run peer assoc for %pM vdev %i: %d\n", bss_conf->bssid, arvif->vdev_id, ret); @@ -2949,8 +3211,7 @@ static void ath12k_bss_assoc(struct ath12k *ar, } ret = ath12k_setup_peer_smps(ar, arvif, bss_conf->bssid, - &ap_sta->deflink.ht_cap, - &ap_sta->deflink.he_6ghz_capa); + &link_sta->ht_cap, &link_sta->he_6ghz_capa); if (ret) { ath12k_warn(ar->ab, "failed to setup peer SMPS for vdev %d: %d\n", arvif->vdev_id, ret); @@ -3058,6 +3319,7 @@ static void ath12k_recalculate_mgmt_rate(struct ath12k *ar, struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_hw *hw = ath12k_ar_to_hw(ar); const struct ieee80211_supported_band *sband; + struct ieee80211_bss_conf *bss_conf; u8 basic_rate_idx; int hw_rate_code; u32 vdev_param; @@ -3066,8 +3328,15 @@ static void ath12k_recalculate_mgmt_rate(struct ath12k *ar, lockdep_assert_wiphy(hw->wiphy); + bss_conf = ath12k_mac_get_link_bss_conf(arvif); + if (!bss_conf) { + ath12k_warn(ar->ab, "unable to access bss link conf in mgmt rate calc for vif %pM link %u\n", + vif->addr, arvif->link_id); + return; + } + sband = hw->wiphy->bands[def->chan->band]; - basic_rate_idx = ffs(vif->bss_conf.basic_rates) - 1; + basic_rate_idx = ffs(bss_conf->basic_rates) - 1; bitrate = sband->bitrates[basic_rate_idx].bitrate; hw_rate_code = ath12k_mac_get_rate_hw_value(bitrate); @@ -3151,6 +3420,7 @@ static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw, { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); unsigned long links = ahvif->links_map; + struct ieee80211_bss_conf *info; struct ath12k_link_vif *arvif; struct ath12k *ar; u8 link_id; @@ -3171,10 +3441,15 @@ static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw, ar = arvif->ar; - if (vif->cfg.assoc) - ath12k_bss_assoc(ar, arvif, &vif->bss_conf); - else + if (vif->cfg.assoc) { + info = ath12k_mac_get_link_bss_conf(arvif); + if (!info) + continue; + + ath12k_bss_assoc(ar, arvif, info); + } else { ath12k_bss_disassoc(ar, arvif); + } } } } @@ -3185,6 +3460,7 @@ static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif) struct ieee80211_vif *vif = arvif->ahvif->vif; struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf; enum wmi_sta_powersave_param param; + struct ieee80211_bss_conf *info; enum wmi_sta_ps_mode psmode; int ret; int timeout; @@ -3202,8 +3478,15 @@ static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif) timeout = conf->dynamic_ps_timeout; if (timeout == 0) { + info = ath12k_mac_get_link_bss_conf(arvif); + if (!info) { + ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n", + vif->addr, arvif->link_id); + return; + } + /* firmware doesn't like 0 */ - timeout = ieee80211_tu_to_usec(vif->bss_conf.beacon_int) / 1000; + timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000; } ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param, @@ -3314,8 +3597,8 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, if (changed & BSS_CHANGED_BEACON_ENABLED) { ath12k_control_beaconing(arvif, info); - if (arvif->is_up && vif->bss_conf.he_support && - vif->bss_conf.he_oper.params) { + if (arvif->is_up && info->he_support && + info->he_oper.params) { /* TODO: Extend to support 1024 BA Bitmap size */ ret = ath12k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, WMI_VDEV_PARAM_BA_MODE, @@ -3326,7 +3609,7 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, arvif->vdev_id); param_id = WMI_VDEV_PARAM_HEOPS_0_31; - param_value = vif->bss_conf.he_oper.params; + param_value = info->he_oper.params; ret = ath12k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, param_id, param_value); ath12k_dbg(ar->ab, ATH12K_DBG_MAC, @@ -3418,12 +3701,12 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, if (changed & BSS_CHANGED_MCAST_RATE && !ath12k_mac_vif_link_chan(vif, arvif->link_id, &def)) { band = def.chan->band; - mcast_rate = vif->bss_conf.mcast_rate[band]; + mcast_rate = info->mcast_rate[band]; if (mcast_rate > 0) rateidx = mcast_rate - 1; else - rateidx = ffs(vif->bss_conf.basic_rates) - 1; + rateidx = ffs(info->basic_rates) - 1; if (ar->pdev->cap.supported_bands & WMI_HOST_WLAN_5G_CAP) rateidx += ATH12K_MAC_FIRST_OFDM_RATE_IDX; @@ -3537,6 +3820,9 @@ static void ath12k_ahvif_put_link_key_cache(struct ath12k_vif_cache *cache) static void ath12k_ahvif_put_link_cache(struct ath12k_vif *ahvif, u8 link_id) { + if (link_id >= IEEE80211_MLD_MAX_NUM_LINKS) + return; + ath12k_ahvif_put_link_key_cache(ahvif->cache[link_id]); kfree(ahvif->cache[link_id]); ahvif->cache[link_id] = NULL; @@ -3597,9 +3883,9 @@ static struct ath12k_link_vif *ath12k_mac_assign_link_vif(struct ath12k_hw *ah, arvif = &ahvif->deflink; } else { /* If this is the first link arvif being created for an ML VIF - * use the preallocated deflink memory + * use the preallocated deflink memory except for scan arvifs */ - if (!ahvif->links_map) { + if (!ahvif->links_map && link_id != ATH12K_DEFAULT_SCAN_LINK) { arvif = &ahvif->deflink; } else { arvif = (struct ath12k_link_vif *) @@ -3730,22 +4016,9 @@ void __ath12k_mac_scan_finish(struct ath12k *ar) ieee80211_remain_on_channel_expired(hw); fallthrough; case ATH12K_SCAN_STARTING: - if (!ar->scan.is_roc) { - struct cfg80211_scan_info info = { - .aborted = ((ar->scan.state == - ATH12K_SCAN_ABORTING) || - (ar->scan.state == - ATH12K_SCAN_STARTING)), - }; - - ieee80211_scan_completed(hw, &info); - } - - ar->scan.state = ATH12K_SCAN_IDLE; - ar->scan_channel = NULL; - ar->scan.roc_freq = 0; cancel_delayed_work(&ar->scan.timeout); complete(&ar->scan.completed); + wiphy_work_queue(ar->ah->hw->wiphy, &ar->scan.vdev_clean_wk); break; } } @@ -3786,15 +4059,15 @@ static int ath12k_scan_stop(struct ath12k *ar) } out: - /* Scan state should be updated upon scan completion but in case - * firmware fails to deliver the event (for whatever reason) it is - * desired to clean up scan state anyway. Firmware may have just - * dropped the scan completion event delivery due to transport pipe - * being overflown with data and/or it can recover on its own before - * next scan request is submitted. + /* Scan state should be updated in scan completion worker but in + * case firmware fails to deliver the event (for whatever reason) + * it is desired to clean up scan state anyway. Firmware may have + * just dropped the scan completion event delivery due to transport + * pipe being overflown with data and/or it can recover on its own + * before next scan request is submitted. */ spin_lock_bh(&ar->data_lock); - if (ar->scan.state != ATH12K_SCAN_IDLE) + if (ret) __ath12k_mac_scan_finish(ar); spin_unlock_bh(&ar->data_lock); @@ -3845,6 +4118,53 @@ static void ath12k_scan_timeout_work(struct work_struct *work) wiphy_unlock(ath12k_ar_to_hw(ar)->wiphy); } +static void ath12k_scan_vdev_clean_work(struct wiphy *wiphy, struct wiphy_work *work) +{ + struct ath12k *ar = container_of(work, struct ath12k, + scan.vdev_clean_wk); + struct ath12k_hw *ah = ar->ah; + struct ath12k_link_vif *arvif; + + lockdep_assert_wiphy(wiphy); + + arvif = ar->scan.arvif; + + /* The scan vdev has already been deleted. This can occur when a + * new scan request is made on the same vif with a different + * frequency, causing the scan arvif to move from one radio to + * another. Or, scan was abrupted and via remove interface, the + * arvif is already deleted. Alternatively, if the scan vdev is not + * being used as an actual vdev, then do not delete it. + */ + if (!arvif || arvif->is_started) + goto work_complete; + + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac clean scan vdev (link id %u)", + arvif->link_id); + + ath12k_mac_remove_link_interface(ah->hw, arvif); + ath12k_mac_unassign_link_vif(arvif); + +work_complete: + spin_lock_bh(&ar->data_lock); + ar->scan.arvif = NULL; + if (!ar->scan.is_roc) { + struct cfg80211_scan_info info = { + .aborted = ((ar->scan.state == + ATH12K_SCAN_ABORTING) || + (ar->scan.state == + ATH12K_SCAN_STARTING)), + }; + + ieee80211_scan_completed(ar->ah->hw, &info); + } + + ar->scan.state = ATH12K_SCAN_IDLE; + ar->scan_channel = NULL; + ar->scan.roc_freq = 0; + spin_unlock_bh(&ar->data_lock); +} + static int ath12k_start_scan(struct ath12k *ar, struct ath12k_wmi_scan_req_arg *arg) { @@ -3899,10 +4219,10 @@ ath12k_mac_find_link_id_by_ar(struct ath12k_vif *ahvif, struct ath12k *ar) return link_id; } - /* input ar is not assigned to any of the links, use link id - * 0 for scan vdev creation. + /* input ar is not assigned to any of the links of ML VIF, use scan + * link (15) for scan vdev creation. */ - return 0; + return ATH12K_DEFAULT_SCAN_LINK; } static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw, @@ -3933,11 +4253,14 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw, /* check if any of the links of ML VIF is already started on * radio(ar) correpsondig to given scan frequency and use it, - * if not use deflink(link 0) for scan purpose. + * if not use scan link (link 15) for scan purpose. */ link_id = ath12k_mac_find_link_id_by_ar(ahvif, ar); arvif = ath12k_mac_assign_link_vif(ah, vif, link_id); + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac link ID %d selected for scan", + arvif->link_id); + /* If the vif is already assigned to a specific vdev of an ar, * check whether its already started, vdev which is started * are not allowed to switch to a new radio. @@ -3961,6 +4284,7 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw, create = false; } } + if (create) { /* Previous arvif would've been cleared in radio switch block * above, assign arvif again for create. @@ -3981,7 +4305,7 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw, reinit_completion(&ar->scan.completed); ar->scan.state = ATH12K_SCAN_STARTING; ar->scan.is_roc = false; - ar->scan.vdev_id = arvif->vdev_id; + ar->scan.arvif = arvif; ret = 0; break; case ATH12K_SCAN_STARTING: @@ -4043,6 +4367,15 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw, spin_unlock_bh(&ar->data_lock); } + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac scan started"); + + /* As per cfg80211/mac80211 scan design, it allows only one + * scan at a time. Hence last_scan link id is used for + * tracking the link id on which the scan is been done on + * this vif. + */ + ahvif->last_scan_link = arvif->link_id; + /* Add a margin to account for event/command processing */ ieee80211_queue_delayed_work(ath12k_ar_to_hw(ar), &ar->scan.timeout, msecs_to_jiffies(arg->max_scan_time + @@ -4062,14 +4395,14 @@ static void ath12k_mac_op_cancel_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); + u16 link_id = ahvif->last_scan_link; struct ath12k_link_vif *arvif; struct ath12k *ar; lockdep_assert_wiphy(hw->wiphy); - arvif = &ahvif->deflink; - - if (!arvif->is_created) + arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); + if (!arvif || arvif->is_started) return; ar = arvif->ar; @@ -4203,6 +4536,7 @@ static int ath12k_mac_set_key(struct ath12k *ar, enum set_key_cmd cmd, { struct ath12k_vif *ahvif = arvif->ahvif; struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif); + struct ieee80211_bss_conf *link_conf; struct ieee80211_sta *sta = NULL; struct ath12k_base *ab = ar->ab; struct ath12k_peer *peer; @@ -4219,12 +4553,19 @@ static int ath12k_mac_set_key(struct ath12k *ar, enum set_key_cmd cmd, if (test_bit(ATH12K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags)) return 1; + link_conf = ath12k_mac_get_link_bss_conf(arvif); + if (!link_conf) { + ath12k_warn(ab, "unable to access bss link conf in set key for vif %pM link %u\n", + vif->addr, arvif->link_id); + return -ENOLINK; + } + if (sta) - peer_addr = sta->addr; + peer_addr = arsta->addr; else if (ahvif->vdev_type == WMI_VDEV_TYPE_STA) - peer_addr = vif->bss_conf.bssid; + peer_addr = link_conf->bssid; else - peer_addr = vif->addr; + peer_addr = link_conf->addr; key->hw_key_idx = key->keyidx; @@ -4316,7 +4657,23 @@ static int ath12k_mac_update_key_cache(struct ath12k_vif_cache *cache, struct ieee80211_sta *sta, struct ieee80211_key_conf *key) { - struct ath12k_key_conf *key_conf = NULL, *tmp; + struct ath12k_key_conf *key_conf, *tmp; + + list_for_each_entry_safe(key_conf, tmp, &cache->key_conf.list, list) { + if (key_conf->key != key) + continue; + + /* If SET key entry is already present in cache, nothing to do, + * just return + */ + if (cmd == SET_KEY) + return 0; + + /* DEL key for an old SET key which driver hasn't flushed yet. + */ + list_del(&key_conf->list); + kfree(key_conf); + } if (cmd == SET_KEY) { key_conf = kzalloc(sizeof(*key_conf), GFP_KERNEL); @@ -4330,17 +4687,7 @@ static int ath12k_mac_update_key_cache(struct ath12k_vif_cache *cache, list_add_tail(&key_conf->list, &cache->key_conf.list); } - if (list_empty(&cache->key_conf.list)) - return 0; - list_for_each_entry_safe(key_conf, tmp, &cache->key_conf.list, list) { - if (key_conf->key == key) { - /* DEL key for an old SET key which driver hasn't flushed yet. - */ - list_del(&key_conf->list); - kfree(key_conf); - break; - } - } + return 0; } @@ -4372,6 +4719,7 @@ static int ath12k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, if (sta) { ahsta = ath12k_sta_to_ahsta(sta); + /* For an ML STA Pairwise key is same for all associated link Stations, * hence do set key for all link STAs which are active. */ @@ -4394,41 +4742,47 @@ static int ath12k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, if (ret) break; } - } else { - arsta = &ahsta->deflink; - arvif = arsta->arvif; - if (WARN_ON(!arvif)) { - ret = -EINVAL; - goto out; - } - ret = ath12k_mac_set_key(arvif->ar, cmd, arvif, arsta, key); - } - } else { - if (key->link_id >= 0 && key->link_id < IEEE80211_MLD_MAX_NUM_LINKS) { - link_id = key->link_id; - arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); - } else { - link_id = 0; - arvif = &ahvif->deflink; + return 0; } - if (!arvif || !arvif->is_created) { - cache = ath12k_ahvif_get_link_cache(ahvif, link_id); - if (!cache) - return -ENOSPC; - - ret = ath12k_mac_update_key_cache(cache, cmd, sta, key); + arsta = &ahsta->deflink; + arvif = arsta->arvif; + if (WARN_ON(!arvif)) + return -EINVAL; + ret = ath12k_mac_set_key(arvif->ar, cmd, arvif, arsta, key); + if (ret) return ret; - } - ret = ath12k_mac_set_key(arvif->ar, cmd, arvif, NULL, key); + return 0; } -out: + if (key->link_id >= 0 && key->link_id < IEEE80211_MLD_MAX_NUM_LINKS) { + link_id = key->link_id; + arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); + } else { + link_id = 0; + arvif = &ahvif->deflink; + } - return ret; + if (!arvif || !arvif->is_created) { + cache = ath12k_ahvif_get_link_cache(ahvif, link_id); + if (!cache) + return -ENOSPC; + + ret = ath12k_mac_update_key_cache(cache, cmd, sta, key); + if (ret) + return ret; + + return 0; + } + + ret = ath12k_mac_set_key(arvif->ar, cmd, arvif, NULL, key); + if (ret) + return ret; + + return 0; } static int @@ -4451,7 +4805,6 @@ ath12k_mac_set_peer_vht_fixed_rate(struct ath12k_link_vif *arvif, const struct cfg80211_bitrate_mask *mask, enum nl80211_band band) { - struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); struct ath12k *ar = arvif->ar; u8 vht_rate, nss; u32 rate_code; @@ -4470,67 +4823,76 @@ ath12k_mac_set_peer_vht_fixed_rate(struct ath12k_link_vif *arvif, if (!nss) { ath12k_warn(ar->ab, "No single VHT Fixed rate found to set for %pM", - sta->addr); + arsta->addr); return -EINVAL; } ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "Setting Fixed VHT Rate for peer %pM. Device will not switch to any other selected rates", - sta->addr); + arsta->addr); rate_code = ATH12K_HW_RATE_CODE(vht_rate, nss - 1, WMI_RATE_PREAMBLE_VHT); - ret = ath12k_wmi_set_peer_param(ar, sta->addr, + ret = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_PARAM_FIXED_RATE, rate_code); if (ret) ath12k_warn(ar->ab, "failed to update STA %pM Fixed Rate %d: %d\n", - sta->addr, rate_code, ret); + arsta->addr, rate_code, ret); return ret; } -static int ath12k_station_assoc(struct ath12k *ar, - struct ath12k_link_vif *arvif, - struct ath12k_link_sta *arsta, - bool reassoc) +static int ath12k_mac_station_assoc(struct ath12k *ar, + struct ath12k_link_vif *arvif, + struct ath12k_link_sta *arsta, + bool reassoc) { struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - struct ath12k_wmi_peer_assoc_arg peer_arg; + struct ieee80211_link_sta *link_sta; int ret; struct cfg80211_chan_def def; enum nl80211_band band; struct cfg80211_bitrate_mask *mask; u8 num_vht_rates; + u8 link_id = arvif->link_id; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); if (WARN_ON(ath12k_mac_vif_link_chan(vif, arvif->link_id, &def))) return -EPERM; + if (WARN_ON(!rcu_access_pointer(sta->link[link_id]))) + return -EINVAL; + band = def.chan->band; mask = &arvif->bitrate_mask; - ath12k_peer_assoc_prepare(ar, arvif, arsta, &peer_arg, reassoc); + struct ath12k_wmi_peer_assoc_arg *peer_arg __free(kfree) = + kzalloc(sizeof(*peer_arg), GFP_KERNEL); + if (!peer_arg) + return -ENOMEM; - if (peer_arg.peer_nss < 1) { + ath12k_peer_assoc_prepare(ar, arvif, arsta, peer_arg, reassoc); + + if (peer_arg->peer_nss < 1) { ath12k_warn(ar->ab, - "invalid peer NSS %d\n", peer_arg.peer_nss); + "invalid peer NSS %d\n", peer_arg->peer_nss); return -EINVAL; } - ret = ath12k_wmi_send_peer_assoc_cmd(ar, &peer_arg); + ret = ath12k_wmi_send_peer_assoc_cmd(ar, peer_arg); if (ret) { ath12k_warn(ar->ab, "failed to run peer assoc for STA %pM vdev %i: %d\n", - sta->addr, arvif->vdev_id, ret); + arsta->addr, arvif->vdev_id, ret); return ret; } if (!wait_for_completion_timeout(&ar->peer_assoc_done, 1 * HZ)) { ath12k_warn(ar->ab, "failed to get peer assoc conf event for %pM vdev %i\n", - sta->addr, arvif->vdev_id); + arsta->addr, arvif->vdev_id); return -ETIMEDOUT; } @@ -4541,7 +4903,13 @@ static int ath12k_station_assoc(struct ath12k *ar, * fixed param. * Note that all other rates and NSS will be disabled for this peer. */ - if (sta->deflink.vht_cap.vht_supported && num_vht_rates == 1) { + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in station assoc\n"); + return -EINVAL; + } + + if (link_sta->vht_cap.vht_supported && num_vht_rates == 1) { ret = ath12k_mac_set_peer_vht_fixed_rate(arvif, arsta, mask, band); if (ret) @@ -4554,9 +4922,8 @@ static int ath12k_station_assoc(struct ath12k *ar, if (reassoc) return 0; - ret = ath12k_setup_peer_smps(ar, arvif, sta->addr, - &sta->deflink.ht_cap, - &sta->deflink.he_6ghz_capa); + ret = ath12k_setup_peer_smps(ar, arvif, arsta->addr, + &link_sta->ht_cap, &link_sta->he_6ghz_capa); if (ret) { ath12k_warn(ar->ab, "failed to setup peer SMPS for vdev %d: %d\n", arvif->vdev_id, ret); @@ -4574,7 +4941,7 @@ static int ath12k_station_assoc(struct ath12k *ar, ret = ath12k_peer_assoc_qos_ap(ar, arvif, arsta); if (ret) { ath12k_warn(ar->ab, "failed to set qos params for STA %pM for vdev %i: %d\n", - sta->addr, arvif->vdev_id, ret); + arsta->addr, arvif->vdev_id, ret); return ret; } } @@ -4582,33 +4949,25 @@ static int ath12k_station_assoc(struct ath12k *ar, return 0; } -static int ath12k_station_disassoc(struct ath12k *ar, - struct ath12k_link_vif *arvif, - struct ath12k_link_sta *arsta) +static int ath12k_mac_station_disassoc(struct ath12k *ar, + struct ath12k_link_vif *arvif, + struct ath12k_link_sta *arsta) { struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - int ret; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); if (!sta->wme) { arvif->num_legacy_stations--; - ret = ath12k_recalc_rtscts_prot(arvif); - if (ret) - return ret; + return ath12k_recalc_rtscts_prot(arvif); } - ret = ath12k_clear_peer_keys(arvif, sta->addr); - if (ret) { - ath12k_warn(ar->ab, "failed to clear all peer keys for vdev %i: %d\n", - arvif->vdev_id, ret); - return ret; - } return 0; } static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) { + struct ieee80211_link_sta *link_sta; struct ath12k *ar; struct ath12k_link_vif *arvif; struct ieee80211_sta *sta; @@ -4619,7 +4978,6 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) u32 changed, bw, nss, smps, bw_prev; int err, num_vht_rates; const struct cfg80211_bitrate_mask *mask; - struct ath12k_wmi_peer_assoc_arg peer_arg; enum wmi_phy_mode peer_phymode; struct ath12k_link_sta *arsta; struct ieee80211_vif *vif; @@ -4655,9 +5013,14 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) nss = min(nss, max(ath12k_mac_max_ht_nss(ht_mcs_mask), ath12k_mac_max_vht_nss(vht_mcs_mask))); + struct ath12k_wmi_peer_assoc_arg *peer_arg __free(kfree) = + kzalloc(sizeof(*peer_arg), GFP_KERNEL); + if (!peer_arg) + return; + if (changed & IEEE80211_RC_BW_CHANGED) { - ath12k_peer_assoc_h_phymode(ar, arvif, arsta, &peer_arg); - peer_phymode = peer_arg.peer_phymode; + ath12k_peer_assoc_h_phymode(ar, arvif, arsta, peer_arg); + peer_phymode = peer_arg->peer_phymode; if (bw > bw_prev) { /* Phymode shows maximum supported channel width, if we @@ -4666,65 +5029,65 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) * WMI_PEER_CHWIDTH */ ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac bandwidth upgrade for sta %pM new %d old %d\n", - sta->addr, bw, bw_prev); - err = ath12k_wmi_set_peer_param(ar, sta->addr, + arsta->addr, bw, bw_prev); + err = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_PHYMODE, peer_phymode); if (err) { ath12k_warn(ar->ab, "failed to update STA %pM to peer phymode %d: %d\n", - sta->addr, peer_phymode, err); + arsta->addr, peer_phymode, err); return; } - err = ath12k_wmi_set_peer_param(ar, sta->addr, + err = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_CHWIDTH, bw); if (err) ath12k_warn(ar->ab, "failed to update STA %pM to peer bandwidth %d: %d\n", - sta->addr, bw, err); + arsta->addr, bw, err); } else { /* When we downgrade bandwidth this will conflict with phymode * and cause to trigger firmware crash. In this case we send * WMI_PEER_CHWIDTH followed by WMI_PEER_PHYMODE */ ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac bandwidth downgrade for sta %pM new %d old %d\n", - sta->addr, bw, bw_prev); - err = ath12k_wmi_set_peer_param(ar, sta->addr, + arsta->addr, bw, bw_prev); + err = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_CHWIDTH, bw); if (err) { ath12k_warn(ar->ab, "failed to update STA %pM peer to bandwidth %d: %d\n", - sta->addr, bw, err); + arsta->addr, bw, err); return; } - err = ath12k_wmi_set_peer_param(ar, sta->addr, + err = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_PHYMODE, peer_phymode); if (err) ath12k_warn(ar->ab, "failed to update STA %pM to peer phymode %d: %d\n", - sta->addr, peer_phymode, err); + arsta->addr, peer_phymode, err); } } if (changed & IEEE80211_RC_NSS_CHANGED) { ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac update sta %pM nss %d\n", - sta->addr, nss); + arsta->addr, nss); - err = ath12k_wmi_set_peer_param(ar, sta->addr, arvif->vdev_id, + err = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_NSS, nss); if (err) ath12k_warn(ar->ab, "failed to update STA %pM nss %d: %d\n", - sta->addr, nss, err); + arsta->addr, nss, err); } if (changed & IEEE80211_RC_SMPS_CHANGED) { ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac update sta %pM smps %d\n", - sta->addr, smps); + arsta->addr, smps); - err = ath12k_wmi_set_peer_param(ar, sta->addr, arvif->vdev_id, + err = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_MIMO_PS_STATE, smps); if (err) ath12k_warn(ar->ab, "failed to update STA %pM smps %d: %d\n", - sta->addr, smps, err); + arsta->addr, smps, err); } if (changed & IEEE80211_RC_SUPP_RATES_CHANGED) { @@ -4743,7 +5106,14 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) * TODO: Check RATEMASK_CMDID to support auto rates selection * across HT/VHT and for multiple VHT MCS support. */ - if (sta->deflink.vht_cap.vht_supported && num_vht_rates == 1) { + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta) { + ath12k_warn(ar->ab, "unable to access link sta in peer assoc he for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + + if (link_sta->vht_cap.vht_supported && num_vht_rates == 1) { ath12k_mac_set_peer_vht_fixed_rate(arvif, arsta, mask, band); } else { @@ -4752,20 +5122,49 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) * other rates using peer_assoc command. */ ath12k_peer_assoc_prepare(ar, arvif, arsta, - &peer_arg, true); + peer_arg, true); - err = ath12k_wmi_send_peer_assoc_cmd(ar, &peer_arg); + err = ath12k_wmi_send_peer_assoc_cmd(ar, peer_arg); if (err) ath12k_warn(ar->ab, "failed to run peer assoc for STA %pM vdev %i: %d\n", - sta->addr, arvif->vdev_id, err); + arsta->addr, arvif->vdev_id, err); if (!wait_for_completion_timeout(&ar->peer_assoc_done, 1 * HZ)) ath12k_warn(ar->ab, "failed to get peer assoc conf event for %pM vdev %i\n", - sta->addr, arvif->vdev_id); + arsta->addr, arvif->vdev_id); } } } +static void ath12k_mac_free_unassign_link_sta(struct ath12k_hw *ah, + struct ath12k_sta *ahsta, + u8 link_id) +{ + struct ath12k_link_sta *arsta; + + lockdep_assert_wiphy(ah->hw->wiphy); + + if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) + return; + + arsta = wiphy_dereference(ah->hw->wiphy, ahsta->link[link_id]); + if (WARN_ON(!arsta)) + return; + + ahsta->links_map &= ~BIT(link_id); + rcu_assign_pointer(ahsta->link[link_id], NULL); + synchronize_rcu(); + + if (arsta == &ahsta->deflink) { + arsta->link_id = ATH12K_INVALID_LINK_ID; + arsta->ahsta = NULL; + arsta->arvif = NULL; + return; + } + + kfree(arsta); +} + static int ath12k_mac_inc_num_stations(struct ath12k_link_vif *arvif, struct ath12k_link_sta *arsta) { @@ -4799,6 +5198,144 @@ static void ath12k_mac_dec_num_stations(struct ath12k_link_vif *arvif, ar->num_stations--; } +static void ath12k_mac_station_post_remove(struct ath12k *ar, + struct ath12k_link_vif *arvif, + struct ath12k_link_sta *arsta) +{ + struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); + struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); + struct ath12k_peer *peer; + + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + ath12k_mac_dec_num_stations(arvif, arsta); + + spin_lock_bh(&ar->ab->base_lock); + + peer = ath12k_peer_find(ar->ab, arvif->vdev_id, arsta->addr); + if (peer && peer->sta == sta) { + ath12k_warn(ar->ab, "Found peer entry %pM n vdev %i after it was supposedly removed\n", + vif->addr, arvif->vdev_id); + peer->sta = NULL; + list_del(&peer->list); + kfree(peer); + ar->num_peers--; + } + + spin_unlock_bh(&ar->ab->base_lock); + + kfree(arsta->rx_stats); + arsta->rx_stats = NULL; +} + +static int ath12k_mac_station_unauthorize(struct ath12k *ar, + struct ath12k_link_vif *arvif, + struct ath12k_link_sta *arsta) +{ + struct ath12k_peer *peer; + int ret; + + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + spin_lock_bh(&ar->ab->base_lock); + + peer = ath12k_peer_find(ar->ab, arvif->vdev_id, arsta->addr); + if (peer) + peer->is_authorized = false; + + spin_unlock_bh(&ar->ab->base_lock); + + /* Driver must clear the keys during the state change from + * IEEE80211_STA_AUTHORIZED to IEEE80211_STA_ASSOC, since after + * returning from here, mac80211 is going to delete the keys + * in __sta_info_destroy_part2(). This will ensure that the driver does + * not retain stale key references after mac80211 deletes the keys. + */ + ret = ath12k_clear_peer_keys(arvif, arsta->addr); + if (ret) { + ath12k_warn(ar->ab, "failed to clear all peer keys for vdev %i: %d\n", + arvif->vdev_id, ret); + return ret; + } + + return 0; +} + +static int ath12k_mac_station_authorize(struct ath12k *ar, + struct ath12k_link_vif *arvif, + struct ath12k_link_sta *arsta) +{ + struct ath12k_peer *peer; + struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); + int ret; + + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + spin_lock_bh(&ar->ab->base_lock); + + peer = ath12k_peer_find(ar->ab, arvif->vdev_id, arsta->addr); + if (peer) + peer->is_authorized = true; + + spin_unlock_bh(&ar->ab->base_lock); + + if (vif->type == NL80211_IFTYPE_STATION && arvif->is_up) { + ret = ath12k_wmi_set_peer_param(ar, arsta->addr, + arvif->vdev_id, + WMI_PEER_AUTHORIZE, + 1); + if (ret) { + ath12k_warn(ar->ab, "Unable to authorize peer %pM vdev %d: %d\n", + arsta->addr, arvif->vdev_id, ret); + return ret; + } + } + + return 0; +} + +static int ath12k_mac_station_remove(struct ath12k *ar, + struct ath12k_link_vif *arvif, + struct ath12k_link_sta *arsta) +{ + struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); + struct ath12k_vif *ahvif = arvif->ahvif; + int ret = 0; + + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + wiphy_work_cancel(ar->ah->hw->wiphy, &arsta->update_wk); + + if (ahvif->vdev_type == WMI_VDEV_TYPE_STA) { + ath12k_bss_disassoc(ar, arvif); + ret = ath12k_mac_vdev_stop(arvif); + if (ret) + ath12k_warn(ar->ab, "failed to stop vdev %i: %d\n", + arvif->vdev_id, ret); + } + + if (sta->mlo) + return ret; + + ath12k_dp_peer_cleanup(ar, arvif->vdev_id, arsta->addr); + + ret = ath12k_peer_delete(ar, arvif->vdev_id, arsta->addr); + if (ret) + ath12k_warn(ar->ab, "Failed to delete peer: %pM for VDEV: %d\n", + arsta->addr, arvif->vdev_id); + else + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "Removed peer: %pM for VDEV: %d\n", + arsta->addr, arvif->vdev_id); + + ath12k_mac_station_post_remove(ar, arvif, arsta); + + if (sta->valid_links) + ath12k_mac_free_unassign_link_sta(ahvif->ah, + arsta->ahsta, arsta->link_id); + + return ret; +} + static int ath12k_mac_station_add(struct ath12k *ar, struct ath12k_link_vif *arvif, struct ath12k_link_sta *arsta) @@ -4806,7 +5343,7 @@ static int ath12k_mac_station_add(struct ath12k *ar, struct ath12k_base *ab = ar->ab; struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); - struct ath12k_wmi_peer_create_arg peer_param; + struct ath12k_wmi_peer_create_arg peer_param = {0}; int ret; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); @@ -4824,34 +5361,35 @@ static int ath12k_mac_station_add(struct ath12k *ar, } peer_param.vdev_id = arvif->vdev_id; - peer_param.peer_addr = sta->addr; + peer_param.peer_addr = arsta->addr; peer_param.peer_type = WMI_PEER_TYPE_DEFAULT; + peer_param.ml_enabled = sta->mlo; ret = ath12k_peer_create(ar, arvif, sta, &peer_param); if (ret) { ath12k_warn(ab, "Failed to add peer: %pM for VDEV: %d\n", - sta->addr, arvif->vdev_id); + arsta->addr, arvif->vdev_id); goto free_peer; } ath12k_dbg(ab, ATH12K_DBG_MAC, "Added peer: %pM for VDEV: %d\n", - sta->addr, arvif->vdev_id); + arsta->addr, arvif->vdev_id); if (ieee80211_vif_is_mesh(vif)) { - ret = ath12k_wmi_set_peer_param(ar, sta->addr, + ret = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_USE_4ADDR, 1); if (ret) { ath12k_warn(ab, "failed to STA %pM 4addr capability: %d\n", - sta->addr, ret); + arsta->addr, ret); goto free_peer; } } - ret = ath12k_dp_peer_setup(ar, arvif->vdev_id, sta->addr); + ret = ath12k_dp_peer_setup(ar, arvif->vdev_id, arsta->addr); if (ret) { ath12k_warn(ab, "failed to setup dp for peer %pM on vdev %i (%d)\n", - sta->addr, arvif->vdev_id, ret); + arsta->addr, arvif->vdev_id, ret); goto free_peer; } @@ -4868,7 +5406,9 @@ static int ath12k_mac_station_add(struct ath12k *ar, return 0; free_peer: - ath12k_peer_delete(ar, arvif->vdev_id, sta->addr); + ath12k_peer_delete(ar, arvif->vdev_id, arsta->addr); + kfree(arsta->rx_stats); + arsta->rx_stats = NULL; dec_num_station: ath12k_mac_dec_num_stations(arvif, arsta); exit: @@ -4906,6 +5446,174 @@ static u32 ath12k_mac_ieee80211_sta_bw_to_wmi(struct ath12k *ar, return bw; } +static int ath12k_mac_assign_link_sta(struct ath12k_hw *ah, + struct ath12k_sta *ahsta, + struct ath12k_link_sta *arsta, + struct ath12k_vif *ahvif, + u8 link_id) +{ + struct ieee80211_sta *sta = ath12k_ahsta_to_sta(ahsta); + struct ieee80211_link_sta *link_sta; + struct ath12k_link_vif *arvif; + + lockdep_assert_wiphy(ah->hw->wiphy); + + if (!arsta || link_id >= IEEE80211_MLD_MAX_NUM_LINKS) + return -EINVAL; + + arvif = wiphy_dereference(ah->hw->wiphy, ahvif->link[link_id]); + if (!arvif) + return -EINVAL; + + memset(arsta, 0, sizeof(*arsta)); + + link_sta = wiphy_dereference(ah->hw->wiphy, sta->link[link_id]); + if (!link_sta) + return -EINVAL; + + ether_addr_copy(arsta->addr, link_sta->addr); + + /* logical index of the link sta in order of creation */ + arsta->link_idx = ahsta->num_peer++; + + arsta->link_id = link_id; + ahsta->links_map |= BIT(arsta->link_id); + arsta->arvif = arvif; + arsta->ahsta = ahsta; + ahsta->ahvif = ahvif; + + wiphy_work_init(&arsta->update_wk, ath12k_sta_rc_update_wk); + + rcu_assign_pointer(ahsta->link[link_id], arsta); + + return 0; +} + +static void ath12k_mac_ml_station_remove(struct ath12k_vif *ahvif, + struct ath12k_sta *ahsta) +{ + struct ieee80211_sta *sta = ath12k_ahsta_to_sta(ahsta); + struct ath12k_hw *ah = ahvif->ah; + struct ath12k_link_vif *arvif; + struct ath12k_link_sta *arsta; + unsigned long links; + struct ath12k *ar; + u8 link_id; + + lockdep_assert_wiphy(ah->hw->wiphy); + + ath12k_peer_mlo_link_peers_delete(ahvif, ahsta); + + /* validate link station removal and clear arsta links */ + links = ahsta->links_map; + for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif = wiphy_dereference(ah->hw->wiphy, ahvif->link[link_id]); + arsta = wiphy_dereference(ah->hw->wiphy, ahsta->link[link_id]); + if (!arvif || !arsta) + continue; + + ar = arvif->ar; + + ath12k_mac_station_post_remove(ar, arvif, arsta); + + ath12k_mac_free_unassign_link_sta(ah, ahsta, link_id); + } + + ath12k_peer_ml_delete(ah, sta); +} + +static int ath12k_mac_handle_link_sta_state(struct ieee80211_hw *hw, + struct ath12k_link_vif *arvif, + struct ath12k_link_sta *arsta, + enum ieee80211_sta_state old_state, + enum ieee80211_sta_state new_state) +{ + struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); + struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); + struct ath12k *ar = arvif->ar; + int ret = 0; + + lockdep_assert_wiphy(hw->wiphy); + + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac handle link %u sta %pM state %d -> %d\n", + arsta->link_id, arsta->addr, old_state, new_state); + + /* IEEE80211_STA_NONE -> IEEE80211_STA_NOTEXIST: Remove the station + * from driver + */ + if ((old_state == IEEE80211_STA_NONE && + new_state == IEEE80211_STA_NOTEXIST)) { + ret = ath12k_mac_station_remove(ar, arvif, arsta); + if (ret) { + ath12k_warn(ar->ab, "Failed to remove station: %pM for VDEV: %d\n", + arsta->addr, arvif->vdev_id); + goto exit; + } + } + + /* IEEE80211_STA_NOTEXIST -> IEEE80211_STA_NONE: Add new station to driver */ + if (old_state == IEEE80211_STA_NOTEXIST && + new_state == IEEE80211_STA_NONE) { + ret = ath12k_mac_station_add(ar, arvif, arsta); + if (ret) + ath12k_warn(ar->ab, "Failed to add station: %pM for VDEV: %d\n", + arsta->addr, arvif->vdev_id); + + /* IEEE80211_STA_AUTH -> IEEE80211_STA_ASSOC: Send station assoc command for + * peer associated to AP/Mesh/ADHOC vif type. + */ + } else if (old_state == IEEE80211_STA_AUTH && + new_state == IEEE80211_STA_ASSOC && + (vif->type == NL80211_IFTYPE_AP || + vif->type == NL80211_IFTYPE_MESH_POINT || + vif->type == NL80211_IFTYPE_ADHOC)) { + ret = ath12k_mac_station_assoc(ar, arvif, arsta, false); + if (ret) + ath12k_warn(ar->ab, "Failed to associate station: %pM\n", + arsta->addr); + + spin_lock_bh(&ar->data_lock); + + arsta->bw = ath12k_mac_ieee80211_sta_bw_to_wmi(ar, sta); + arsta->bw_prev = sta->deflink.bandwidth; + + spin_unlock_bh(&ar->data_lock); + + /* IEEE80211_STA_ASSOC -> IEEE80211_STA_AUTHORIZED: set peer status as + * authorized + */ + } else if (old_state == IEEE80211_STA_ASSOC && + new_state == IEEE80211_STA_AUTHORIZED) { + ret = ath12k_mac_station_authorize(ar, arvif, arsta); + if (ret) + ath12k_warn(ar->ab, "Failed to authorize station: %pM\n", + arsta->addr); + + /* IEEE80211_STA_AUTHORIZED -> IEEE80211_STA_ASSOC: station may be in removal, + * deauthorize it. + */ + } else if (old_state == IEEE80211_STA_AUTHORIZED && + new_state == IEEE80211_STA_ASSOC) { + ath12k_mac_station_unauthorize(ar, arvif, arsta); + + /* IEEE80211_STA_ASSOC -> IEEE80211_STA_AUTH: disassoc peer connected to + * AP/mesh/ADHOC vif type. + */ + } else if (old_state == IEEE80211_STA_ASSOC && + new_state == IEEE80211_STA_AUTH && + (vif->type == NL80211_IFTYPE_AP || + vif->type == NL80211_IFTYPE_MESH_POINT || + vif->type == NL80211_IFTYPE_ADHOC)) { + ret = ath12k_mac_station_disassoc(ar, arvif, arsta); + if (ret) + ath12k_warn(ar->ab, "Failed to disassociate station: %pM\n", + arsta->addr); + } + +exit: + return ret; +} + static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, @@ -4914,139 +5622,110 @@ static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw, { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta); - struct ath12k *ar; + struct ath12k_hw *ah = ath12k_hw_to_ah(hw); struct ath12k_link_vif *arvif; struct ath12k_link_sta *arsta; - struct ath12k_peer *peer; - int ret = 0; + unsigned long valid_links; + u8 link_id = 0; + int ret; lockdep_assert_wiphy(hw->wiphy); - arvif = &ahvif->deflink; - arsta = &ahsta->deflink; - - ar = ath12k_get_ar_by_vif(hw, vif); - if (!ar) { - WARN_ON_ONCE(1); - return -EINVAL; + if (ieee80211_vif_is_mld(vif) && sta->valid_links) { + WARN_ON(!sta->mlo && hweight16(sta->valid_links) != 1); + link_id = ffs(sta->valid_links) - 1; } + /* IEEE80211_STA_NOTEXIST -> IEEE80211_STA_NONE: + * New station add received. If this is a ML station then + * ahsta->links_map will be zero and sta->valid_links will be 1. + * Assign default link to the first link sta. + */ if (old_state == IEEE80211_STA_NOTEXIST && new_state == IEEE80211_STA_NONE) { - memset(arsta, 0, sizeof(*arsta)); - rcu_assign_pointer(ahsta->link[0], arsta); - /* TODO use appropriate link id once MLO support is added */ - arsta->link_id = ATH12K_DEFAULT_LINK_ID; - ahsta->links_map = BIT(arsta->link_id); - arsta->ahsta = ahsta; - arsta->arvif = arvif; - wiphy_work_init(&arsta->update_wk, ath12k_sta_rc_update_wk); + memset(ahsta, 0, sizeof(*ahsta)); - synchronize_rcu(); + arsta = &ahsta->deflink; - ret = ath12k_mac_station_add(ar, arvif, arsta); - if (ret) - ath12k_warn(ar->ab, "Failed to add station: %pM for VDEV: %d\n", - sta->addr, arvif->vdev_id); - } else if ((old_state == IEEE80211_STA_NONE && - new_state == IEEE80211_STA_NOTEXIST)) { - wiphy_work_cancel(hw->wiphy, &arsta->update_wk); - - if (ahvif->vdev_type == WMI_VDEV_TYPE_STA) { - ath12k_bss_disassoc(ar, arvif); - ret = ath12k_mac_vdev_stop(arvif); - if (ret) - ath12k_warn(ar->ab, "failed to stop vdev %i: %d\n", - arvif->vdev_id, ret); + /* ML sta */ + if (sta->mlo && !ahsta->links_map && + (hweight16(sta->valid_links) == 1)) { + ret = ath12k_peer_ml_create(ah, sta); + if (ret) { + ath12k_hw_warn(ah, "unable to create ML peer for sta %pM", + sta->addr); + goto exit; + } } - ath12k_dp_peer_cleanup(ar, arvif->vdev_id, sta->addr); - ret = ath12k_peer_delete(ar, arvif->vdev_id, sta->addr); - if (ret) - ath12k_warn(ar->ab, "Failed to delete peer: %pM for VDEV: %d\n", - sta->addr, arvif->vdev_id); - else - ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "Removed peer: %pM for VDEV: %d\n", - sta->addr, arvif->vdev_id); - - ath12k_mac_dec_num_stations(arvif, arsta); - spin_lock_bh(&ar->ab->base_lock); - peer = ath12k_peer_find(ar->ab, arvif->vdev_id, sta->addr); - if (peer && peer->sta == sta) { - ath12k_warn(ar->ab, "Found peer entry %pM n vdev %i after it was supposedly removed\n", - vif->addr, arvif->vdev_id); - peer->sta = NULL; - list_del(&peer->list); - kfree(peer); - ar->num_peers--; + ret = ath12k_mac_assign_link_sta(ah, ahsta, arsta, ahvif, + link_id); + if (ret) { + ath12k_hw_warn(ah, "unable assign link %d for sta %pM", + link_id, sta->addr); + goto exit; } - spin_unlock_bh(&ar->ab->base_lock); - kfree(arsta->rx_stats); - arsta->rx_stats = NULL; - - if (arsta->link_id < IEEE80211_MLD_MAX_NUM_LINKS) { - rcu_assign_pointer(ahsta->link[arsta->link_id], NULL); - synchronize_rcu(); - ahsta->links_map &= ~(BIT(arsta->link_id)); - arsta->link_id = ATH12K_INVALID_LINK_ID; - arsta->ahsta = NULL; + /* above arsta will get memset, hence do this after assign + * link sta + */ + if (sta->mlo) { + arsta->is_assoc_link = true; + ahsta->assoc_link_id = link_id; } - } else if (old_state == IEEE80211_STA_AUTH && - new_state == IEEE80211_STA_ASSOC && - (vif->type == NL80211_IFTYPE_AP || - vif->type == NL80211_IFTYPE_MESH_POINT || - vif->type == NL80211_IFTYPE_ADHOC)) { - ret = ath12k_station_assoc(ar, arvif, arsta, false); - if (ret) - ath12k_warn(ar->ab, "Failed to associate station: %pM\n", - sta->addr); - - spin_lock_bh(&ar->data_lock); - - arsta->bw = ath12k_mac_ieee80211_sta_bw_to_wmi(ar, sta); - arsta->bw_prev = sta->deflink.bandwidth; - - spin_unlock_bh(&ar->data_lock); - } else if (old_state == IEEE80211_STA_ASSOC && - new_state == IEEE80211_STA_AUTHORIZED) { - spin_lock_bh(&ar->ab->base_lock); - - peer = ath12k_peer_find(ar->ab, arvif->vdev_id, sta->addr); - if (peer) - peer->is_authorized = true; - - spin_unlock_bh(&ar->ab->base_lock); - - if (vif->type == NL80211_IFTYPE_STATION && arvif->is_up) { - ret = ath12k_wmi_set_peer_param(ar, sta->addr, - arvif->vdev_id, - WMI_PEER_AUTHORIZE, - 1); - if (ret) - ath12k_warn(ar->ab, "Unable to authorize peer %pM vdev %d: %d\n", - sta->addr, arvif->vdev_id, ret); - } - } else if (old_state == IEEE80211_STA_AUTHORIZED && - new_state == IEEE80211_STA_ASSOC) { - spin_lock_bh(&ar->ab->base_lock); - - peer = ath12k_peer_find(ar->ab, arvif->vdev_id, sta->addr); - if (peer) - peer->is_authorized = false; - - spin_unlock_bh(&ar->ab->base_lock); - } else if (old_state == IEEE80211_STA_ASSOC && - new_state == IEEE80211_STA_AUTH && - (vif->type == NL80211_IFTYPE_AP || - vif->type == NL80211_IFTYPE_MESH_POINT || - vif->type == NL80211_IFTYPE_ADHOC)) { - ret = ath12k_station_disassoc(ar, arvif, arsta); - if (ret) - ath12k_warn(ar->ab, "Failed to disassociate station: %pM\n", - sta->addr); } + /* In the ML station scenario, activate all partner links once the + * client is transitioning to the associated state. + * + * FIXME: Ideally, this activation should occur when the client + * transitions to the authorized state. However, there are some + * issues with handling this in the firmware. Until the firmware + * can manage it properly, activate the links when the client is + * about to move to the associated state. + */ + if (ieee80211_vif_is_mld(vif) && vif->type == NL80211_IFTYPE_STATION && + old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC) + ieee80211_set_active_links(vif, ieee80211_vif_usable_links(vif)); + + /* Handle all the other state transitions in generic way */ + valid_links = ahsta->links_map; + for_each_set_bit(link_id, &valid_links, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); + arsta = wiphy_dereference(hw->wiphy, ahsta->link[link_id]); + /* some assumptions went wrong! */ + if (WARN_ON(!arvif || !arsta)) + continue; + + /* vdev might be in deleted */ + if (WARN_ON(!arvif->ar)) + continue; + + ret = ath12k_mac_handle_link_sta_state(hw, arvif, arsta, + old_state, new_state); + if (ret) { + ath12k_hw_warn(ah, "unable to move link sta %d of sta %pM from state %d to %d", + link_id, arsta->addr, old_state, new_state); + goto exit; + } + } + + /* IEEE80211_STA_NONE -> IEEE80211_STA_NOTEXIST: + * Remove the station from driver (handle ML sta here since that + * needs special handling. Normal sta will be handled in generic + * handler below + */ + if (old_state == IEEE80211_STA_NONE && + new_state == IEEE80211_STA_NOTEXIST && sta->mlo) + ath12k_mac_ml_station_remove(ahvif, ahsta); + + ret = 0; + +exit: + /* update the state if everything went well */ + if (!ret) + ahsta->state = new_state; + return ret; } @@ -5054,16 +5733,22 @@ static int ath12k_mac_op_sta_set_txpwr(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - struct ath12k_hw *ah = ath12k_hw_to_ah(hw); + struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta); struct ath12k *ar; struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); struct ath12k_link_vif *arvif; + struct ath12k_link_sta *arsta; + u8 link_id; int ret; s16 txpwr; lockdep_assert_wiphy(hw->wiphy); - arvif = &ahvif->deflink; + /* TODO: use link id from mac80211 once that's implemented */ + link_id = 0; + + arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); + arsta = wiphy_dereference(hw->wiphy, ahsta->link[link_id]); if (sta->deflink.txpwr.type == NL80211_TX_POWER_AUTOMATIC) { txpwr = 0; @@ -5080,9 +5765,9 @@ static int ath12k_mac_op_sta_set_txpwr(struct ieee80211_hw *hw, goto out; } - ar = ath12k_ah_to_ar(ah, 0); + ar = arvif->ar; - ret = ath12k_wmi_set_peer_param(ar, sta->addr, arvif->vdev_id, + ret = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_USE_FIXED_PWR, txpwr); if (ret) { ath12k_warn(ar->ab, "failed to set tx power for station ret: %d\n", @@ -5094,62 +5779,69 @@ out: return ret; } -static void ath12k_mac_op_sta_rc_update(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct ieee80211_link_sta *link_sta, - u32 changed) +static void ath12k_mac_op_link_sta_rc_update(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_link_sta *link_sta, + u32 changed) { struct ieee80211_sta *sta = link_sta->sta; struct ath12k *ar; struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta); struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); + struct ath12k_hw *ah = ath12k_hw_to_ah(hw); struct ath12k_link_sta *arsta; struct ath12k_link_vif *arvif; struct ath12k_peer *peer; u32 bw, smps; - /* TODO: use proper link id once link sta specific rc update support is - * available in mac80211. - */ - u8 link_id = ATH12K_DEFAULT_LINK_ID; - - ar = ath12k_get_ar_by_vif(hw, vif); - if (!ar) { - WARN_ON_ONCE(1); - return; - } rcu_read_lock(); - arvif = rcu_dereference(ahvif->link[link_id]); + arvif = rcu_dereference(ahvif->link[link_sta->link_id]); if (!arvif) { - ath12k_warn(ar->ab, "mac sta rc update failed to fetch link vif on link id %u for peer %pM\n", - link_id, sta->addr); + ath12k_hw_warn(ah, "mac sta rc update failed to fetch link vif on link id %u for peer %pM\n", + link_sta->link_id, sta->addr); rcu_read_unlock(); return; } - arsta = rcu_dereference(ahsta->link[link_id]); + + ar = arvif->ar; + + arsta = rcu_dereference(ahsta->link[link_sta->link_id]); if (!arsta) { rcu_read_unlock(); ath12k_warn(ar->ab, "mac sta rc update failed to fetch link sta on link id %u for peer %pM\n", - link_id, sta->addr); + link_sta->link_id, sta->addr); return; } spin_lock_bh(&ar->ab->base_lock); - peer = ath12k_peer_find(ar->ab, arvif->vdev_id, sta->addr); + peer = ath12k_peer_find(ar->ab, arvif->vdev_id, arsta->addr); if (!peer) { spin_unlock_bh(&ar->ab->base_lock); rcu_read_unlock(); ath12k_warn(ar->ab, "mac sta rc update failed to find peer %pM on vdev %i\n", - sta->addr, arvif->vdev_id); + arsta->addr, arvif->vdev_id); return; } spin_unlock_bh(&ar->ab->base_lock); + if (arsta->link_id >= IEEE80211_MLD_MAX_NUM_LINKS) { + rcu_read_unlock(); + return; + } + + link_sta = rcu_dereference(sta->link[arsta->link_id]); + if (!link_sta) { + rcu_read_unlock(); + ath12k_warn(ar->ab, "unable to access link sta in rc update for sta %pM link %u\n", + sta->addr, arsta->link_id); + return; + } + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac sta rc update for %pM changed %08x bw %d nss %d smps %d\n", - sta->addr, changed, sta->deflink.bandwidth, sta->deflink.rx_nss, - sta->deflink.smps_mode); + arsta->addr, changed, link_sta->bandwidth, link_sta->rx_nss, + link_sta->smps_mode); spin_lock_bh(&ar->data_lock); @@ -5160,12 +5852,12 @@ static void ath12k_mac_op_sta_rc_update(struct ieee80211_hw *hw, } if (changed & IEEE80211_RC_NSS_CHANGED) - arsta->nss = sta->deflink.rx_nss; + arsta->nss = link_sta->rx_nss; if (changed & IEEE80211_RC_SMPS_CHANGED) { smps = WMI_PEER_SMPS_PS_NONE; - switch (sta->deflink.smps_mode) { + switch (link_sta->smps_mode) { case IEEE80211_SMPS_AUTOMATIC: case IEEE80211_SMPS_OFF: smps = WMI_PEER_SMPS_PS_NONE; @@ -5177,8 +5869,8 @@ static void ath12k_mac_op_sta_rc_update(struct ieee80211_hw *hw, smps = WMI_PEER_SMPS_DYNAMIC; break; default: - ath12k_warn(ar->ab, "Invalid smps %d in sta rc update for %pM\n", - sta->deflink.smps_mode, sta->addr); + ath12k_warn(ar->ab, "Invalid smps %d in sta rc update for %pM link %u\n", + link_sta->smps_mode, arsta->addr, link_sta->link_id); smps = WMI_PEER_SMPS_PS_NONE; break; } @@ -5195,6 +5887,110 @@ static void ath12k_mac_op_sta_rc_update(struct ieee80211_hw *hw, rcu_read_unlock(); } +static struct ath12k_link_sta *ath12k_mac_alloc_assign_link_sta(struct ath12k_hw *ah, + struct ath12k_sta *ahsta, + struct ath12k_vif *ahvif, + u8 link_id) +{ + struct ath12k_link_sta *arsta; + int ret; + + lockdep_assert_wiphy(ah->hw->wiphy); + + if (link_id >= IEEE80211_MLD_MAX_NUM_LINKS) + return NULL; + + arsta = wiphy_dereference(ah->hw->wiphy, ahsta->link[link_id]); + if (arsta) + return NULL; + + arsta = kmalloc(sizeof(*arsta), GFP_KERNEL); + if (!arsta) + return NULL; + + ret = ath12k_mac_assign_link_sta(ah, ahsta, arsta, ahvif, link_id); + if (ret) { + kfree(arsta); + return NULL; + } + + return arsta; +} + +static int ath12k_mac_op_change_sta_links(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + u16 old_links, u16 new_links) +{ + struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); + struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta); + struct ath12k_hw *ah = hw->priv; + struct ath12k_link_vif *arvif; + struct ath12k_link_sta *arsta; + unsigned long valid_links; + struct ath12k *ar; + u8 link_id; + int ret; + + lockdep_assert_wiphy(hw->wiphy); + + if (!sta->valid_links) + return -EINVAL; + + /* Firmware does not support removal of one of link stas. All sta + * would be removed during ML STA delete in sta_state(), hence link + * sta removal is not handled here. + */ + if (new_links < old_links) + return 0; + + if (ahsta->ml_peer_id == ATH12K_MLO_PEER_ID_INVALID) { + ath12k_hw_warn(ah, "unable to add link for ml sta %pM", sta->addr); + return -EINVAL; + } + + /* this op is expected only after initial sta insertion with default link */ + if (WARN_ON(ahsta->links_map == 0)) + return -EINVAL; + + valid_links = new_links; + for_each_set_bit(link_id, &valid_links, IEEE80211_MLD_MAX_NUM_LINKS) { + if (ahsta->links_map & BIT(link_id)) + continue; + + arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); + arsta = ath12k_mac_alloc_assign_link_sta(ah, ahsta, ahvif, link_id); + + if (!arvif || !arsta) { + ath12k_hw_warn(ah, "Failed to alloc/assign link sta"); + continue; + } + + ar = arvif->ar; + if (!ar) + continue; + + ret = ath12k_mac_station_add(ar, arvif, arsta); + if (ret) { + ath12k_warn(ar->ab, "Failed to add station: %pM for VDEV: %d\n", + arsta->addr, arvif->vdev_id); + ath12k_mac_free_unassign_link_sta(ah, ahsta, link_id); + return ret; + } + } + + return 0; +} + +static bool ath12k_mac_op_can_activate_links(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u16 active_links) +{ + /* TODO: Handle recovery case */ + + return true; +} + static int ath12k_conf_tx_uapsd(struct ath12k_link_vif *arvif, u16 ac, bool enable) { @@ -6054,6 +6850,8 @@ static void ath12k_mgmt_over_wmi_tx_drop(struct ath12k *ar, struct sk_buff *skb) { int num_mgmt; + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + ieee80211_free_txskb(ath12k_ar_to_hw(ar), skb); num_mgmt = atomic_dec_if_positive(&ar->num_pending_mgmt_tx); @@ -6115,6 +6913,8 @@ static int ath12k_mac_mgmt_tx_wmi(struct ath12k *ar, struct ath12k_link_vif *arv int buf_id; int ret; + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + ATH12K_SKB_CB(skb)->ar = ar; spin_lock_bh(&ar->txmgmt_idr_lock); buf_id = idr_alloc(&ar->txmgmt_idr, skb, 0, @@ -6169,15 +6969,18 @@ static void ath12k_mgmt_over_wmi_tx_purge(struct ath12k *ar) ath12k_mgmt_over_wmi_tx_drop(ar, skb); } -static void ath12k_mgmt_over_wmi_tx_work(struct work_struct *work) +static void ath12k_mgmt_over_wmi_tx_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ath12k *ar = container_of(work, struct ath12k, wmi_mgmt_tx_work); + struct ath12k_hw *ah = ar->ah; struct ath12k_skb_cb *skb_cb; struct ath12k_vif *ahvif; struct ath12k_link_vif *arvif; struct sk_buff *skb; int ret; + lockdep_assert_wiphy(wiphy); + while ((skb = skb_dequeue(&ar->wmi_mgmt_tx_queue)) != NULL) { skb_cb = ATH12K_SKB_CB(skb); if (!skb_cb->vif) { @@ -6187,7 +6990,15 @@ static void ath12k_mgmt_over_wmi_tx_work(struct work_struct *work) } ahvif = ath12k_vif_to_ahvif(skb_cb->vif); - arvif = &ahvif->deflink; + if (!(ahvif->links_map & BIT(skb_cb->link_id))) { + ath12k_warn(ar->ab, + "invalid linkid %u in mgmt over wmi tx with linkmap 0x%x\n", + skb_cb->link_id, ahvif->links_map); + ath12k_mgmt_over_wmi_tx_drop(ar, skb); + continue; + } + + arvif = wiphy_dereference(ah->hw->wiphy, ahvif->link[skb_cb->link_id]); if (ar->allocated_vdev_map & (1LL << arvif->vdev_id)) { ret = ath12k_mac_mgmt_tx_wmi(ar, arvif, skb); if (ret) { @@ -6197,8 +7008,9 @@ static void ath12k_mgmt_over_wmi_tx_work(struct work_struct *work) } } else { ath12k_warn(ar->ab, - "dropping mgmt frame for vdev %d, is_started %d\n", + "dropping mgmt frame for vdev %d link %u is_started %d\n", arvif->vdev_id, + skb_cb->link_id, arvif->is_started); ath12k_mgmt_over_wmi_tx_drop(ar, skb); } @@ -6232,7 +7044,7 @@ static int ath12k_mac_mgmt_tx(struct ath12k *ar, struct sk_buff *skb, skb_queue_tail(q, skb); atomic_inc(&ar->num_pending_mgmt_tx); - ieee80211_queue_work(ath12k_ar_to_hw(ar), &ar->wmi_mgmt_tx_work); + wiphy_work_queue(ath12k_ar_to_hw(ar)->wiphy, &ar->wmi_mgmt_tx_work); return 0; } @@ -6258,6 +7070,105 @@ static void ath12k_mac_add_p2p_noa_ie(struct ath12k *ar, spin_unlock_bh(&ar->data_lock); } +/* Note: called under rcu_read_lock() */ +static u8 ath12k_mac_get_tx_link(struct ieee80211_sta *sta, struct ieee80211_vif *vif, + u8 link, struct sk_buff *skb, u32 info_flags) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); + struct ieee80211_link_sta *link_sta; + struct ieee80211_bss_conf *bss_conf; + struct ath12k_sta *ahsta; + + /* Use the link id passed or the default vif link */ + if (!sta) { + if (link != IEEE80211_LINK_UNSPECIFIED) + return link; + + return ahvif->deflink.link_id; + } + + ahsta = ath12k_sta_to_ahsta(sta); + + /* Below translation ensures we pass proper A2 & A3 for non ML clients. + * Also it assumes for now support only for MLO AP in this path + */ + if (!sta->mlo) { + link = ahsta->deflink.link_id; + + if (info_flags & IEEE80211_TX_CTL_HW_80211_ENCAP) + return link; + + bss_conf = rcu_dereference(vif->link_conf[link]); + if (bss_conf) { + ether_addr_copy(hdr->addr2, bss_conf->addr); + if (!ieee80211_has_tods(hdr->frame_control) && + !ieee80211_has_fromds(hdr->frame_control)) + ether_addr_copy(hdr->addr3, bss_conf->addr); + } + + return link; + } + + /* enqueue eth enacap & data frames on primary link, FW does link + * selection and address translation. + */ + if (info_flags & IEEE80211_TX_CTL_HW_80211_ENCAP || + ieee80211_is_data(hdr->frame_control)) + return ahsta->assoc_link_id; + + /* 802.11 frame cases */ + if (link == IEEE80211_LINK_UNSPECIFIED) + link = ahsta->deflink.link_id; + + if (!ieee80211_is_mgmt(hdr->frame_control)) + return link; + + /* Perform address conversion for ML STA Tx */ + bss_conf = rcu_dereference(vif->link_conf[link]); + link_sta = rcu_dereference(sta->link[link]); + + if (bss_conf && link_sta) { + ether_addr_copy(hdr->addr1, link_sta->addr); + ether_addr_copy(hdr->addr2, bss_conf->addr); + + if (vif->type == NL80211_IFTYPE_STATION && bss_conf->bssid) + ether_addr_copy(hdr->addr3, bss_conf->bssid); + else if (vif->type == NL80211_IFTYPE_AP) + ether_addr_copy(hdr->addr3, bss_conf->addr); + + return link; + } + + if (bss_conf) { + /* In certain cases where a ML sta associated and added subset of + * links on which the ML AP is active, but now sends some frame + * (ex. Probe request) on a different link which is active in our + * MLD but was not added during previous association, we can + * still honor the Tx to that ML STA via the requested link. + * The control would reach here in such case only when that link + * address is same as the MLD address or in worst case clients + * used MLD address at TA wrongly which would have helped + * identify the ML sta object and pass it here. + * If the link address of that STA is different from MLD address, + * then the sta object would be NULL and control won't reach + * here but return at the start of the function itself with !sta + * check. Also this would not need any translation at hdr->addr1 + * from MLD to link address since the RA is the MLD address + * (same as that link address ideally) already. + */ + ether_addr_copy(hdr->addr2, bss_conf->addr); + + if (vif->type == NL80211_IFTYPE_STATION && bss_conf->bssid) + ether_addr_copy(hdr->addr3, bss_conf->bssid); + else if (vif->type == NL80211_IFTYPE_AP) + ether_addr_copy(hdr->addr3, bss_conf->addr); + } + + return link; +} + +/* Note: called under rcu_read_lock() */ static void ath12k_mac_op_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct sk_buff *skb) @@ -6267,13 +7178,16 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif = info->control.vif; struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); struct ath12k_link_vif *arvif = &ahvif->deflink; - struct ath12k *ar = arvif->ar; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct ieee80211_key_conf *key = info->control.hw_key; + struct ieee80211_sta *sta = control->sta; u32 info_flags = info->flags; + struct ath12k *ar; bool is_prb_rsp; + u8 link_id; int ret; + link_id = u32_get_bits(info->control.flags, IEEE80211_TX_CTRL_MLO_LINK); memset(skb_cb, 0, sizeof(*skb_cb)); skb_cb->vif = vif; @@ -6282,6 +7196,27 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw, skb_cb->flags |= ATH12K_SKB_CIPHER_SET; } + /* handle only for MLO case, use deflink for non MLO case */ + if (ieee80211_vif_is_mld(vif)) { + link_id = ath12k_mac_get_tx_link(sta, vif, link_id, skb, info_flags); + if (link_id >= IEEE80211_MLD_MAX_NUM_LINKS) { + ieee80211_free_txskb(hw, skb); + return; + } + } else { + link_id = 0; + } + + arvif = rcu_dereference(ahvif->link[link_id]); + if (!arvif || !arvif->ar) { + ath12k_warn(ahvif->ah, "failed to find arvif link id %u for frame transmission", + link_id); + ieee80211_free_txskb(hw, skb); + return; + } + + ar = arvif->ar; + skb_cb->link_id = link_id; is_prb_rsp = ieee80211_is_probe_resp(hdr->frame_control); if (info_flags & IEEE80211_TX_CTL_HW_80211_ENCAP) { @@ -6309,10 +7244,12 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw, void ath12k_mac_drain_tx(struct ath12k *ar) { + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + /* make sure rcu-protected mac80211 tx path itself is drained */ synchronize_net(); - cancel_work_sync(&ar->wmi_mgmt_tx_work); + wiphy_work_cancel(ath12k_ar_to_hw(ar)->wiphy, &ar->wmi_mgmt_tx_work); ath12k_mgmt_over_wmi_tx_purge(ar); } @@ -6429,6 +7366,8 @@ static void ath12k_drain_tx(struct ath12k_hw *ah) struct ath12k *ar; int i; + lockdep_assert_wiphy(ah->hw->wiphy); + for_each_ar(ah, ar, i) ath12k_mac_drain_tx(ar); } @@ -6554,9 +7493,10 @@ static void ath12k_mac_stop(struct ath12k *ar) ath12k_err(ar->ab, "failed to clear rx_filter for monitor status ring: (%d)\n", ret); - clear_bit(ATH12K_CAC_RUNNING, &ar->dev_flags); + clear_bit(ATH12K_FLAG_CAC_RUNNING, &ar->dev_flags); cancel_delayed_work_sync(&ar->scan.timeout); + wiphy_work_cancel(ath12k_ar_to_hw(ar)->wiphy, &ar->scan.vdev_clean_wk); cancel_work_sync(&ar->regd_update_work); cancel_work_sync(&ar->ab->rfkill_work); @@ -6622,6 +7562,7 @@ static int ath12k_mac_setup_vdev_params_mbssid(struct ath12k_link_vif *arvif, { struct ath12k_vif *ahvif = arvif->ahvif; struct ieee80211_vif *tx_vif = ahvif->vif->mbssid_tx_vif; + struct ieee80211_bss_conf *link_conf; struct ath12k *ar = arvif->ar; struct ath12k_link_vif *tx_arvif; struct ath12k_vif *tx_ahvif; @@ -6629,10 +7570,17 @@ static int ath12k_mac_setup_vdev_params_mbssid(struct ath12k_link_vif *arvif, if (!tx_vif) return 0; + link_conf = ath12k_mac_get_link_bss_conf(arvif); + if (!link_conf) { + ath12k_warn(ar->ab, "unable to access bss link conf in set mbssid params for vif %pM link %u\n", + ahvif->vif->addr, arvif->link_id); + return -ENOLINK; + } + tx_ahvif = ath12k_vif_to_ahvif(tx_vif); tx_arvif = &tx_ahvif->deflink; - if (ahvif->vif->bss_conf.nontransmitted) { + if (link_conf->nontransmitted) { if (ar->ah->hw->wiphy != ieee80211_vif_to_wdev(tx_vif)->wiphy) return -EINVAL; @@ -6644,7 +7592,7 @@ static int ath12k_mac_setup_vdev_params_mbssid(struct ath12k_link_vif *arvif, return -EINVAL; } - if (ahvif->vif->bss_conf.ema_ap) + if (link_conf->ema_ap) *flags |= WMI_VDEV_MBSSID_FLAGS_EMA_MODE; return 0; @@ -6658,6 +7606,8 @@ static int ath12k_mac_setup_vdev_create_arg(struct ath12k_link_vif *arvif, struct ath12k_vif *ahvif = arvif->ahvif; int ret; + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + arg->if_id = arvif->vdev_id; arg->type = ahvif->vdev_type; arg->subtype = ahvif->vdev_subtype; @@ -6689,6 +7639,17 @@ static int ath12k_mac_setup_vdev_create_arg(struct ath12k_link_vif *arvif, } arg->if_stats_id = ath12k_mac_get_vdev_stats_id(arvif); + + if (ath12k_mac_is_ml_arvif(arvif)) { + if (hweight16(ahvif->vif->valid_links) > ATH12K_WMI_MLO_MAX_LINKS) { + ath12k_warn(ar->ab, "too many MLO links during setting up vdev: %d", + ahvif->vif->valid_links); + return -EINVAL; + } + + ether_addr_copy(arg->mld_addr, ahvif->vif->addr); + } + return 0; } @@ -6839,16 +7800,25 @@ int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif) struct ath12k_vif *ahvif = arvif->ahvif; struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif); struct ath12k_wmi_vdev_create_arg vdev_arg = {0}; - struct ath12k_wmi_peer_create_arg peer_param; + struct ath12k_wmi_peer_create_arg peer_param = {0}; struct ieee80211_bss_conf *link_conf; u32 param_id, param_value; u16 nss; int i; int ret, vdev_id; + u8 link_id; lockdep_assert_wiphy(hw->wiphy); - link_conf = wiphy_dereference(hw->wiphy, vif->link_conf[arvif->link_id]); + /* If no link is active and scan vdev is requested + * use a default link conf for scan address purpose. + */ + if (arvif->link_id == ATH12K_DEFAULT_SCAN_LINK && vif->valid_links) + link_id = ffs(vif->valid_links) - 1; + else + link_id = arvif->link_id; + + link_conf = wiphy_dereference(hw->wiphy, vif->link_conf[link_id]); if (!link_conf) { ath12k_warn(ar->ab, "unable to access bss link conf in vdev create for vif %pM link %u\n", vif->addr, arvif->link_id); @@ -6999,7 +7969,7 @@ int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif) break; } - arvif->txpower = vif->bss_conf.txpower; + arvif->txpower = link_conf->txpower; ret = ath12k_mac_txpower_recalc(ar); if (ret) goto err_peer_del; @@ -7034,8 +8004,7 @@ err_peer_del: ret = ath12k_wait_for_peer_delete_done(ar, arvif->vdev_id, arvif->bssid); if (ret) - /* KVALO: why not goto err? */ - return ret; + goto err_vdev_del; ar->num_peers--; } @@ -7129,7 +8098,9 @@ static struct ath12k *ath12k_mac_assign_vif_to_vdev(struct ieee80211_hw *hw, struct ath12k_link_vif *arvif, struct ieee80211_chanctx_conf *ctx) { - struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); + struct ath12k_vif *ahvif = arvif->ahvif; + struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif); + struct ath12k_link_vif *scan_arvif; struct ath12k_hw *ah = hw->priv; struct ath12k *ar; struct ath12k_base *ab; @@ -7148,6 +8119,19 @@ static struct ath12k *ath12k_mac_assign_vif_to_vdev(struct ieee80211_hw *hw, if (!ar) return NULL; + /* cleanup the scan vdev if we are done scan on that ar + * and now we want to create for actual usage. + */ + if (ieee80211_vif_is_mld(vif)) { + scan_arvif = wiphy_dereference(hw->wiphy, + ahvif->link[ATH12K_DEFAULT_SCAN_LINK]); + if (scan_arvif && scan_arvif->ar == ar) { + ar->scan.arvif = NULL; + ath12k_mac_remove_link_interface(hw, scan_arvif); + ath12k_mac_unassign_link_vif(scan_arvif); + } + } + if (arvif->ar) { /* This is not expected really */ if (WARN_ON(!arvif->is_created)) { @@ -7173,9 +8157,6 @@ static struct ath12k *ath12k_mac_assign_vif_to_vdev(struct ieee80211_hw *hw, ab = ar->ab; - if (arvif->is_created) - goto flush; - /* Assign arvif again here since previous radio switch block * would've unassigned and cleared it. */ @@ -7186,6 +8167,9 @@ static struct ath12k *ath12k_mac_assign_vif_to_vdev(struct ieee80211_hw *hw, goto unlock; } + if (arvif->is_created) + goto flush; + if (ar->num_created_vdevs > (TARGET_NUM_VDEVS - 1)) { ath12k_warn(ab, "failed to create vdev, reached max vdev limit %d\n", TARGET_NUM_VDEVS); @@ -7243,14 +8227,9 @@ static int ath12k_mac_op_add_interface(struct ieee80211_hw *hw, vif->hw_queue[i] = ATH12K_HW_DEFAULT_QUEUE; vif->driver_flags |= IEEE80211_VIF_SUPPORTS_UAPSD; - /* For non-ml vifs, vif->addr is the actual vdev address but for - * ML vif link(link BSSID) address is the vdev address and it can be a - * different one from vif->addr (i.e ML address). - * Defer vdev creation until assign_chanctx or hw_scan is initiated as driver + /* Defer vdev creation until assign_chanctx or hw_scan is initiated as driver * will not know if this interface is an ML vif at this point. */ - ath12k_mac_assign_vif_to_vdev(hw, arvif, NULL); - return 0; } @@ -7348,11 +8327,12 @@ static void ath12k_mac_op_remove_interface(struct ieee80211_hw *hw, { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); struct ath12k_link_vif *arvif; + struct ath12k *ar; u8 link_id; lockdep_assert_wiphy(hw->wiphy); - for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + for (link_id = 0; link_id < ATH12K_NUM_MAX_LINKS; link_id++) { /* if we cached some config but never received assign chanctx, * free the allocated cache. */ @@ -7361,6 +8341,31 @@ static void ath12k_mac_op_remove_interface(struct ieee80211_hw *hw, if (!arvif || !arvif->is_created) continue; + ar = arvif->ar; + + /* Scan abortion is in progress since before this, cancel_hw_scan() + * is expected to be executed. Since link is anyways going to be removed + * now, just cancel the worker and send the scan aborted to user space + */ + if (ar->scan.arvif == arvif) { + wiphy_work_cancel(hw->wiphy, &ar->scan.vdev_clean_wk); + + spin_lock_bh(&ar->data_lock); + ar->scan.arvif = NULL; + if (!ar->scan.is_roc) { + struct cfg80211_scan_info info = { + .aborted = true, + }; + + ieee80211_scan_completed(ar->ah->hw, &info); + } + + ar->scan.state = ATH12K_SCAN_IDLE; + ar->scan_channel = NULL; + ar->scan.roc_freq = 0; + spin_unlock_bh(&ar->data_lock); + } + ath12k_mac_remove_link_interface(hw, arvif); ath12k_mac_unassign_link_vif(arvif); } @@ -7453,20 +8458,26 @@ static int ath12k_mac_op_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx return ret; } -static int ath12k_mac_ampdu_action(struct ath12k_link_vif *arvif, - struct ieee80211_ampdu_params *params) +static int ath12k_mac_ampdu_action(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_ampdu_params *params, + u8 link_id) { - struct ath12k *ar = arvif->ar; + struct ath12k *ar; int ret = -EINVAL; - lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + lockdep_assert_wiphy(hw->wiphy); + + ar = ath12k_get_ar_by_vif(hw, vif, link_id); + if (!ar) + return -EINVAL; switch (params->action) { case IEEE80211_AMPDU_RX_START: - ret = ath12k_dp_rx_ampdu_start(ar, params); + ret = ath12k_dp_rx_ampdu_start(ar, params, link_id); break; case IEEE80211_AMPDU_RX_STOP: - ret = ath12k_dp_rx_ampdu_stop(ar, params); + ret = ath12k_dp_rx_ampdu_stop(ar, params, link_id); break; case IEEE80211_AMPDU_TX_START: case IEEE80211_AMPDU_TX_STOP_CONT: @@ -7480,6 +8491,10 @@ static int ath12k_mac_ampdu_action(struct ath12k_link_vif *arvif, break; } + if (ret) + ath12k_warn(ar->ab, "unable to perform ampdu action %d for vif %pM link %u ret %d\n", + params->action, vif->addr, link_id, ret); + return ret; } @@ -7487,27 +8502,24 @@ static int ath12k_mac_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params) { - struct ath12k_hw *ah = ath12k_hw_to_ah(hw); - struct ath12k *ar; - struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); - struct ath12k_link_vif *arvif; + struct ieee80211_sta *sta = params->sta; + struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta); + unsigned long links_map = ahsta->links_map; int ret = -EINVAL; + u8 link_id; lockdep_assert_wiphy(hw->wiphy); - ar = ath12k_get_ar_by_vif(hw, vif); - if (!ar) - return -EINVAL; + if (WARN_ON(!links_map)) + return ret; - ar = ath12k_ah_to_ar(ah, 0); - arvif = &ahvif->deflink; + for_each_set_bit(link_id, &links_map, IEEE80211_MLD_MAX_NUM_LINKS) { + ret = ath12k_mac_ampdu_action(hw, vif, params, link_id); + if (ret) + return ret; + } - ret = ath12k_mac_ampdu_action(arvif, params); - if (ret) - ath12k_warn(ar->ab, "pdev idx %d unable to perform ampdu action %d ret %d\n", - ar->pdev_idx, params->action, ret); - - return ret; + return 0; } static int ath12k_mac_op_add_chanctx(struct ieee80211_hw *hw, @@ -7627,6 +8639,58 @@ ath12k_mac_check_down_grade_phy_mode(struct ath12k *ar, return down_mode; } +static void +ath12k_mac_mlo_get_vdev_args(struct ath12k_link_vif *arvif, + struct wmi_ml_arg *ml_arg) +{ + struct ath12k_vif *ahvif = arvif->ahvif; + struct wmi_ml_partner_info *partner_info; + struct ieee80211_bss_conf *link_conf; + struct ath12k_link_vif *arvif_p; + unsigned long links; + u8 link_id; + + lockdep_assert_wiphy(ahvif->ah->hw->wiphy); + + if (!ath12k_mac_is_ml_arvif(arvif)) + return; + + if (hweight16(ahvif->vif->valid_links) > ATH12K_WMI_MLO_MAX_LINKS) + return; + + ml_arg->enabled = true; + + /* Driver always add a new link via VDEV START, FW takes + * care of internally adding this link to existing + * link vdevs which are advertised as partners below + */ + ml_arg->link_add = true; + partner_info = ml_arg->partner_info; + + links = ahvif->links_map; + for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif_p = wiphy_dereference(ahvif->ah->hw->wiphy, ahvif->link[link_id]); + + if (WARN_ON(!arvif_p)) + continue; + + if (arvif == arvif_p) + continue; + + link_conf = wiphy_dereference(ahvif->ah->hw->wiphy, + ahvif->vif->link_conf[arvif_p->link_id]); + + if (!link_conf) + continue; + + partner_info->vdev_id = arvif_p->vdev_id; + partner_info->hw_link_id = arvif_p->ar->pdev->hw_link_id; + ether_addr_copy(partner_info->addr, link_conf->addr); + ml_arg->num_partner_links++; + partner_info++; + } +} + static int ath12k_mac_vdev_start_restart(struct ath12k_link_vif *arvif, struct ieee80211_chanctx_conf *ctx, @@ -7636,11 +8700,20 @@ ath12k_mac_vdev_start_restart(struct ath12k_link_vif *arvif, struct ath12k_base *ab = ar->ab; struct wmi_vdev_start_req_arg arg = {}; const struct cfg80211_chan_def *chandef = &ctx->def; + struct ieee80211_hw *hw = ath12k_ar_to_hw(ar); struct ath12k_vif *ahvif = arvif->ahvif; - int he_support = ahvif->vif->bss_conf.he_support; + struct ieee80211_bss_conf *link_conf; + unsigned int dfs_cac_time; int ret; - lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + lockdep_assert_wiphy(hw->wiphy); + + link_conf = ath12k_mac_get_link_bss_conf(arvif); + if (!link_conf) { + ath12k_warn(ar->ab, "unable to access bss link conf in vdev start for vif %pM link %u\n", + ahvif->vif->addr, arvif->link_id); + return -ENOLINK; + } reinit_completion(&ar->vdev_setup_done); @@ -7658,9 +8731,9 @@ ath12k_mac_vdev_start_restart(struct ath12k_link_vif *arvif, chandef->chan->band, ahvif->vif->type); arg.min_power = 0; - arg.max_power = chandef->chan->max_power * 2; - arg.max_reg_power = chandef->chan->max_reg_power * 2; - arg.max_antenna_gain = chandef->chan->max_antenna_gain * 2; + arg.max_power = chandef->chan->max_power; + arg.max_reg_power = chandef->chan->max_reg_power; + arg.max_antenna_gain = chandef->chan->max_antenna_gain; arg.pref_tx_streams = ar->num_tx_chains; arg.pref_rx_streams = ar->num_rx_chains; @@ -7693,7 +8766,7 @@ ath12k_mac_vdev_start_restart(struct ath12k_link_vif *arvif, spin_unlock_bh(&ab->base_lock); /* TODO: Notify if secondary 80Mhz also needs radar detection */ - if (he_support) { + if (link_conf->he_support) { ret = ath12k_set_he_mu_sounding_mode(ar, arvif); if (ret) { ath12k_warn(ar->ab, "failed to set he mode vdev %i\n", @@ -7705,6 +8778,9 @@ ath12k_mac_vdev_start_restart(struct ath12k_link_vif *arvif, arg.passive |= !!(chandef->chan->flags & IEEE80211_CHAN_NO_IR); + if (!restart) + ath12k_mac_mlo_get_vdev_args(arvif, &arg.ml); + ath12k_dbg(ab, ATH12K_DBG_MAC, "mac vdev %d start center_freq %d phymode %s punct_bitmap 0x%x\n", arg.vdev_id, arg.freq, @@ -7728,20 +8804,20 @@ ath12k_mac_vdev_start_restart(struct ath12k_link_vif *arvif, ath12k_dbg(ab, ATH12K_DBG_MAC, "vdev %pM started, vdev_id %d\n", ahvif->vif->addr, arvif->vdev_id); - /* Enable CAC Flag in the driver by checking the channel DFS cac time, - * i.e dfs_cac_ms value which will be valid only for radar channels - * and state as NL80211_DFS_USABLE which indicates CAC needs to be - * done before channel usage. This flags is used to drop rx packets. + /* Enable CAC Running Flag in the driver by checking all sub-channel's DFS + * state as NL80211_DFS_USABLE which indicates CAC needs to be + * done before channel usage. This flag is used to drop rx packets. * during CAC. */ /* TODO: Set the flag for other interface types as required */ - if (arvif->ahvif->vdev_type == WMI_VDEV_TYPE_AP && - chandef->chan->dfs_cac_ms && - chandef->chan->dfs_state == NL80211_DFS_USABLE) { - set_bit(ATH12K_CAC_RUNNING, &ar->dev_flags); + if (arvif->ahvif->vdev_type == WMI_VDEV_TYPE_AP && ctx->radar_enabled && + cfg80211_chandef_dfs_usable(hw->wiphy, chandef)) { + set_bit(ATH12K_FLAG_CAC_RUNNING, &ar->dev_flags); + dfs_cac_time = cfg80211_chandef_dfs_cac_time(hw->wiphy, chandef); + ath12k_dbg(ab, ATH12K_DBG_MAC, - "CAC Started in chan_freq %d for vdev %d\n", - arg.freq, arg.vdev_id); + "CAC started dfs_cac_time %u center_freq %d center_freq1 %d for vdev %d\n", + dfs_cac_time, arg.freq, arg.band_center_freq1, arg.vdev_id); } ret = ath12k_mac_set_txbf_conf(arvif); @@ -7778,19 +8854,32 @@ ath12k_mac_change_chanctx_cnt_iter(void *data, u8 *mac, { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); struct ath12k_mac_change_chanctx_arg *arg = data; + struct ieee80211_bss_conf *link_conf; struct ath12k_link_vif *arvif; + unsigned long links_map; + u8 link_id; lockdep_assert_wiphy(ahvif->ah->hw->wiphy); - arvif = &ahvif->deflink; + links_map = ahvif->links_map; + for_each_set_bit(link_id, &links_map, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif = wiphy_dereference(ahvif->ah->hw->wiphy, ahvif->link[link_id]); + if (WARN_ON(!arvif)) + continue; - if (arvif->ar != arg->ar) - return; + if (arvif->ar != arg->ar) + continue; - if (rcu_access_pointer(vif->bss_conf.chanctx_conf) != arg->ctx) - return; + link_conf = wiphy_dereference(ahvif->ah->hw->wiphy, + vif->link_conf[link_id]); + if (WARN_ON(!link_conf)) + continue; - arg->n_vifs++; + if (rcu_access_pointer(link_conf->chanctx_conf) != arg->ctx) + continue; + + arg->n_vifs++; + } } static void @@ -7799,27 +8888,41 @@ ath12k_mac_change_chanctx_fill_iter(void *data, u8 *mac, { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); struct ath12k_mac_change_chanctx_arg *arg = data; + struct ieee80211_bss_conf *link_conf; struct ieee80211_chanctx_conf *ctx; struct ath12k_link_vif *arvif; + unsigned long links_map; + u8 link_id; lockdep_assert_wiphy(ahvif->ah->hw->wiphy); - arvif = &ahvif->deflink; + links_map = ahvif->links_map; + for_each_set_bit(link_id, &links_map, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif = wiphy_dereference(ahvif->ah->hw->wiphy, ahvif->link[link_id]); + if (WARN_ON(!arvif)) + continue; - if (arvif->ar != arg->ar) - return; + if (arvif->ar != arg->ar) + continue; - ctx = rcu_access_pointer(vif->bss_conf.chanctx_conf); - if (ctx != arg->ctx) - return; + link_conf = wiphy_dereference(ahvif->ah->hw->wiphy, + vif->link_conf[arvif->link_id]); + if (WARN_ON(!link_conf)) + continue; - if (WARN_ON(arg->next_vif == arg->n_vifs)) - return; + ctx = rcu_access_pointer(link_conf->chanctx_conf); + if (ctx != arg->ctx) + continue; - arg->vifs[arg->next_vif].vif = vif; - arg->vifs[arg->next_vif].old_ctx = ctx; - arg->vifs[arg->next_vif].new_ctx = ctx; - arg->next_vif++; + if (WARN_ON(arg->next_vif == arg->n_vifs)) + return; + + arg->vifs[arg->next_vif].vif = vif; + arg->vifs[arg->next_vif].old_ctx = ctx; + arg->vifs[arg->next_vif].new_ctx = ctx; + arg->vifs[arg->next_vif].link_conf = link_conf; + arg->next_vif++; + } } static u32 ath12k_mac_nlwidth_to_wmiwidth(enum nl80211_chan_width width) @@ -7879,10 +8982,12 @@ ath12k_mac_update_vif_chan(struct ath12k *ar, int n_vifs) { struct ath12k_wmi_vdev_up_params params = {}; + struct ieee80211_bss_conf *link_conf; struct ath12k_base *ab = ar->ab; struct ath12k_link_vif *arvif; struct ieee80211_vif *vif; struct ath12k_vif *ahvif; + u8 link_id; int ret; int i; bool monitor_vif = false; @@ -7892,7 +8997,10 @@ ath12k_mac_update_vif_chan(struct ath12k *ar, for (i = 0; i < n_vifs; i++) { vif = vifs[i].vif; ahvif = ath12k_vif_to_ahvif(vif); - arvif = &ahvif->deflink; + link_conf = vifs[i].link_conf; + link_id = link_conf->link_id; + arvif = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy, + ahvif->link[link_id]); if (vif->type == NL80211_IFTYPE_MONITOR) monitor_vif = true; @@ -7945,13 +9053,13 @@ ath12k_mac_update_vif_chan(struct ath12k *ar, params.aid = ahvif->aid; params.bssid = arvif->bssid; if (vif->mbssid_tx_vif) { - struct ath12k_vif *ahvif = + struct ath12k_vif *tx_ahvif = ath12k_vif_to_ahvif(vif->mbssid_tx_vif); - struct ath12k_link_vif *arvif = &ahvif->deflink; + struct ath12k_link_vif *tx_arvif = &tx_ahvif->deflink; - params.tx_bssid = arvif->bssid; - params.nontx_profile_idx = vif->bss_conf.bssid_index; - params.nontx_profile_cnt = 1 << vif->bss_conf.bssid_indicator; + params.tx_bssid = tx_arvif->bssid; + params.nontx_profile_idx = link_conf->bssid_index; + params.nontx_profile_cnt = 1 << link_conf->bssid_indicator; } ret = ath12k_wmi_vdev_up(arvif->ar, ¶ms); if (ret) { @@ -8099,11 +9207,8 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw, return -ENOMEM; } - if (!arvif->is_started) { - ar = ath12k_mac_assign_vif_to_vdev(hw, arvif, ctx); - if (!ar) - return -EINVAL; - } else { + ar = ath12k_mac_assign_vif_to_vdev(hw, arvif, ctx); + if (!ar) { ath12k_warn(arvif->ar->ab, "failed to assign chanctx for vif %pM link id %u link vif is already started", vif->addr, link_id); return -EINVAL; @@ -8348,6 +9453,8 @@ static int ath12k_mac_flush(struct ath12k *ar) int ath12k_mac_wait_tx_complete(struct ath12k *ar) { + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + ath12k_mac_drain_tx(ar); return ath12k_mac_flush(ar); } @@ -8356,7 +9463,11 @@ static void ath12k_mac_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *v u32 queues, bool drop) { struct ath12k_hw *ah = ath12k_hw_to_ah(hw); + struct ath12k_link_vif *arvif; + struct ath12k_vif *ahvif; + unsigned long links; struct ath12k *ar; + u8 link_id; int i; lockdep_assert_wiphy(hw->wiphy); @@ -8371,12 +9482,18 @@ static void ath12k_mac_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *v return; } - ar = ath12k_get_ar_by_vif(hw, vif); + for_each_ar(ah, ar, i) + wiphy_work_flush(hw->wiphy, &ar->wmi_mgmt_tx_work); - if (!ar) - return; + ahvif = ath12k_vif_to_ahvif(vif); + links = ahvif->links_map; + for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); + if (!(arvif && arvif->ar)) + continue; - ath12k_mac_flush(ar); + ath12k_mac_flush(arvif->ar); + } } static int @@ -8575,10 +9692,11 @@ static void ath12k_mac_set_bitrate_mask_iter(void *data, { struct ath12k_link_vif *arvif = data; struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta); - struct ath12k_link_sta *arsta = &ahsta->deflink; + struct ath12k_link_sta *arsta; struct ath12k *ar = arvif->ar; - if (arsta->arvif != arvif) + arsta = rcu_dereference(ahsta->link[arvif->link_id]); + if (!arsta || arsta->arvif != arvif) return; spin_lock_bh(&ar->data_lock); @@ -8593,21 +9711,26 @@ static void ath12k_mac_disable_peer_fixed_rate(void *data, { struct ath12k_link_vif *arvif = data; struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta); - struct ath12k_link_sta *arsta = &ahsta->deflink; + struct ath12k_link_sta *arsta; struct ath12k *ar = arvif->ar; int ret; - if (arsta->arvif != arvif) + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + arsta = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy, + ahsta->link[arvif->link_id]); + + if (!arsta || arsta->arvif != arvif) return; - ret = ath12k_wmi_set_peer_param(ar, sta->addr, + ret = ath12k_wmi_set_peer_param(ar, arsta->addr, arvif->vdev_id, WMI_PEER_PARAM_FIXED_RATE, WMI_FIXED_RATE_NONE); if (ret) ath12k_warn(ar->ab, "failed to disable peer fixed rate for STA %pM ret %d\n", - sta->addr, ret); + arsta->addr, ret); } static int @@ -8950,6 +10073,7 @@ static int ath12k_mac_op_cancel_remain_on_channel(struct ieee80211_hw *hw, ath12k_scan_abort(ar); cancel_delayed_work_sync(&ar->scan.timeout); + wiphy_work_cancel(hw->wiphy, &ar->scan.vdev_clean_wk); return 0; } @@ -8962,7 +10086,6 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw, { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); struct ath12k_hw *ah = ath12k_hw_to_ah(hw); - struct ath12k_wmi_scan_req_arg arg; struct ath12k_link_vif *arvif; struct ath12k *ar; u32 scan_time_msec; @@ -8973,10 +10096,8 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw, lockdep_assert_wiphy(hw->wiphy); ar = ath12k_mac_select_scan_device(hw, vif, chan->center_freq); - if (!ar) { - ret = -EINVAL; - goto exit; - } + if (!ar) + return -EINVAL; /* check if any of the links of ML VIF is already started on * radio(ar) correpsondig to given scan frequency and use it, @@ -8995,15 +10116,11 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw, * always on the same band for the vif */ if (arvif->is_created) { - if (WARN_ON(!arvif->ar)) { - ret = -EINVAL; - goto exit; - } + if (WARN_ON(!arvif->ar)) + return -EINVAL; - if (ar != arvif->ar && arvif->is_started) { - ret = -EBUSY; - goto exit; - } + if (ar != arvif->ar && arvif->is_started) + return -EBUSY; if (ar != arvif->ar) { ath12k_mac_remove_link_interface(hw, arvif); @@ -9020,7 +10137,7 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw, if (ret) { ath12k_warn(ar->ab, "unable to create scan vdev for roc: %d\n", ret); - goto exit; + return ret; } } @@ -9033,7 +10150,7 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw, reinit_completion(&ar->scan.on_channel); ar->scan.state = ATH12K_SCAN_STARTING; ar->scan.is_roc = true; - ar->scan.vdev_id = arvif->vdev_id; + ar->scan.arvif = arvif; ar->scan.roc_freq = chan->center_freq; ar->scan.roc_notify = true; ret = 0; @@ -9048,37 +10165,41 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw, spin_unlock_bh(&ar->data_lock); if (ret) - goto exit; + return ret; scan_time_msec = hw->wiphy->max_remain_on_channel_duration * 2; - memset(&arg, 0, sizeof(arg)); - ath12k_wmi_start_scan_init(ar, &arg); - arg.num_chan = 1; - arg.chan_list = kcalloc(arg.num_chan, sizeof(*arg.chan_list), - GFP_KERNEL); - if (!arg.chan_list) { - ret = -ENOMEM; - goto exit; - } + struct ath12k_wmi_scan_req_arg *arg __free(kfree) = + kzalloc(sizeof(*arg), GFP_KERNEL); + if (!arg) + return -ENOMEM; - arg.vdev_id = arvif->vdev_id; - arg.scan_id = ATH12K_SCAN_ID; - arg.chan_list[0] = chan->center_freq; - arg.dwell_time_active = scan_time_msec; - arg.dwell_time_passive = scan_time_msec; - arg.max_scan_time = scan_time_msec; - arg.scan_f_passive = 1; - arg.burst_duration = duration; + ath12k_wmi_start_scan_init(ar, arg); + arg->num_chan = 1; - ret = ath12k_start_scan(ar, &arg); + u32 *chan_list __free(kfree) = kcalloc(arg->num_chan, sizeof(*chan_list), + GFP_KERNEL); + if (!chan_list) + return -ENOMEM; + + arg->chan_list = chan_list; + arg->vdev_id = arvif->vdev_id; + arg->scan_id = ATH12K_SCAN_ID; + arg->chan_list[0] = chan->center_freq; + arg->dwell_time_active = scan_time_msec; + arg->dwell_time_passive = scan_time_msec; + arg->max_scan_time = scan_time_msec; + arg->scan_f_passive = 1; + arg->burst_duration = duration; + + ret = ath12k_start_scan(ar, arg); if (ret) { ath12k_warn(ar->ab, "failed to start roc scan: %d\n", ret); spin_lock_bh(&ar->data_lock); ar->scan.state = ATH12K_SCAN_IDLE; spin_unlock_bh(&ar->data_lock); - goto free_chan_list; + return ret; } ret = wait_for_completion_timeout(&ar->scan.on_channel, 3 * HZ); @@ -9087,20 +10208,13 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw, ret = ath12k_scan_stop(ar); if (ret) ath12k_warn(ar->ab, "failed to stop scan: %d\n", ret); - ret = -ETIMEDOUT; - goto free_chan_list; + return -ETIMEDOUT; } ieee80211_queue_delayed_work(hw, &ar->scan.timeout, msecs_to_jiffies(duration)); - ret = 0; - -free_chan_list: - kfree(arg.chan_list); - -exit: - return ret; + return 0; } static void ath12k_mac_op_set_rekey_data(struct ieee80211_hw *hw, @@ -9159,7 +10273,7 @@ static const struct ieee80211_ops ath12k_ops = { .set_rekey_data = ath12k_mac_op_set_rekey_data, .sta_state = ath12k_mac_op_sta_state, .sta_set_txpwr = ath12k_mac_op_sta_set_txpwr, - .link_sta_rc_update = ath12k_mac_op_sta_rc_update, + .link_sta_rc_update = ath12k_mac_op_link_sta_rc_update, .conf_tx = ath12k_mac_op_conf_tx, .set_antenna = ath12k_mac_op_set_antenna, .get_antenna = ath12k_mac_op_get_antenna, @@ -9178,7 +10292,8 @@ static const struct ieee80211_ops ath12k_ops = { .sta_statistics = ath12k_mac_op_sta_statistics, .remain_on_channel = ath12k_mac_op_remain_on_channel, .cancel_remain_on_channel = ath12k_mac_op_cancel_remain_on_channel, - + .change_sta_links = ath12k_mac_op_change_sta_links, + .can_activate_links = ath12k_mac_op_can_activate_links, #ifdef CONFIG_PM .suspend = ath12k_wow_op_suspend, .resume = ath12k_wow_op_resume, @@ -9201,8 +10316,8 @@ static void ath12k_mac_update_ch_list(struct ath12k *ar, band->channels[i].flags |= IEEE80211_CHAN_DISABLED; } - ar->freq_low = freq_low; - ar->freq_high = freq_high; + ar->freq_range.start_freq = MHZ_TO_KHZ(freq_low); + ar->freq_range.end_freq = MHZ_TO_KHZ(freq_high); } static u32 ath12k_get_phy_id(struct ath12k *ar, u32 band) @@ -9334,14 +10449,20 @@ static bool ath12k_mac_is_iface_mode_enable(struct ath12k_hw *ah, { struct ath12k *ar; int i; - u16 interface_modes, mode; - bool is_enable = true; + u16 interface_modes, mode = 0; + bool is_enable = false; + + if (type == NL80211_IFTYPE_MESH_POINT) { + if (IS_ENABLED(CONFIG_MAC80211_MESH)) + mode = BIT(type); + } else { + mode = BIT(type); + } - mode = BIT(type); for_each_ar(ah, ar, i) { interface_modes = ar->ab->hw_params->interface_modes; - if (!(interface_modes & mode)) { - is_enable = false; + if (interface_modes & mode) { + is_enable = true; break; } } @@ -9349,23 +10470,20 @@ static bool ath12k_mac_is_iface_mode_enable(struct ath12k_hw *ah, return is_enable; } -static int ath12k_mac_setup_iface_combinations(struct ath12k_hw *ah) +static int +ath12k_mac_setup_radio_iface_comb(struct ath12k *ar, + struct ieee80211_iface_combination *comb) { - struct wiphy *wiphy = ah->hw->wiphy; - struct ieee80211_iface_combination *combinations; + u16 interface_modes = ar->ab->hw_params->interface_modes; struct ieee80211_iface_limit *limits; int n_limits, max_interfaces; bool ap, mesh, p2p; - ap = ath12k_mac_is_iface_mode_enable(ah, NL80211_IFTYPE_AP); - p2p = ath12k_mac_is_iface_mode_enable(ah, NL80211_IFTYPE_P2P_DEVICE); + ap = interface_modes & BIT(NL80211_IFTYPE_AP); + p2p = interface_modes & BIT(NL80211_IFTYPE_P2P_DEVICE); mesh = IS_ENABLED(CONFIG_MAC80211_MESH) && - ath12k_mac_is_iface_mode_enable(ah, NL80211_IFTYPE_MESH_POINT); - - combinations = kzalloc(sizeof(*combinations), GFP_KERNEL); - if (!combinations) - return -ENOMEM; + (interface_modes & BIT(NL80211_IFTYPE_MESH_POINT)); if ((ap || mesh) && !p2p) { n_limits = 2; @@ -9382,10 +10500,8 @@ static int ath12k_mac_setup_iface_combinations(struct ath12k_hw *ah) } limits = kcalloc(n_limits, sizeof(*limits), GFP_KERNEL); - if (!limits) { - kfree(combinations); + if (!limits) return -ENOMEM; - } limits[0].max = 1; limits[0].types |= BIT(NL80211_IFTYPE_STATION); @@ -9401,26 +10517,181 @@ static int ath12k_mac_setup_iface_combinations(struct ath12k_hw *ah) if (p2p) { limits[1].types |= BIT(NL80211_IFTYPE_P2P_CLIENT) | - BIT(NL80211_IFTYPE_P2P_GO); + BIT(NL80211_IFTYPE_P2P_GO); limits[2].max = 1; limits[2].types |= BIT(NL80211_IFTYPE_P2P_DEVICE); } - combinations[0].limits = limits; - combinations[0].n_limits = n_limits; - combinations[0].max_interfaces = max_interfaces; - combinations[0].num_different_channels = 1; - combinations[0].beacon_int_infra_match = true; - combinations[0].beacon_int_min_gcd = 100; - combinations[0].radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) | - BIT(NL80211_CHAN_WIDTH_20) | - BIT(NL80211_CHAN_WIDTH_40) | - BIT(NL80211_CHAN_WIDTH_80); + comb[0].limits = limits; + comb[0].n_limits = n_limits; + comb[0].max_interfaces = max_interfaces; + comb[0].num_different_channels = 1; + comb[0].beacon_int_infra_match = true; + comb[0].beacon_int_min_gcd = 100; + comb[0].radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) | + BIT(NL80211_CHAN_WIDTH_20) | + BIT(NL80211_CHAN_WIDTH_40) | + BIT(NL80211_CHAN_WIDTH_80); + return 0; +} + +static int +ath12k_mac_setup_global_iface_comb(struct ath12k_hw *ah, + struct wiphy_radio *radio, + u8 n_radio, + struct ieee80211_iface_combination *comb) +{ + const struct ieee80211_iface_combination *iter_comb; + struct ieee80211_iface_limit *limits; + int i, j, n_limits; + bool ap, mesh, p2p; + + if (!n_radio) + return 0; + + ap = ath12k_mac_is_iface_mode_enable(ah, NL80211_IFTYPE_AP); + p2p = ath12k_mac_is_iface_mode_enable(ah, NL80211_IFTYPE_P2P_DEVICE); + mesh = ath12k_mac_is_iface_mode_enable(ah, NL80211_IFTYPE_MESH_POINT); + + if ((ap || mesh) && !p2p) + n_limits = 2; + else if (p2p) + n_limits = 3; + else + n_limits = 1; + + limits = kcalloc(n_limits, sizeof(*limits), GFP_KERNEL); + if (!limits) + return -ENOMEM; + + for (i = 0; i < n_radio; i++) { + iter_comb = radio[i].iface_combinations; + for (j = 0; j < iter_comb->n_limits && j < n_limits; j++) { + limits[j].types |= iter_comb->limits[j].types; + limits[j].max += iter_comb->limits[j].max; + } + + comb->max_interfaces += iter_comb->max_interfaces; + comb->num_different_channels += iter_comb->num_different_channels; + comb->radar_detect_widths |= iter_comb->radar_detect_widths; + } + + comb->limits = limits; + comb->n_limits = n_limits; + comb->beacon_int_infra_match = true; + comb->beacon_int_min_gcd = 100; + + return 0; +} + +static +void ath12k_mac_cleanup_iface_comb(const struct ieee80211_iface_combination *iface_comb) +{ + kfree(iface_comb[0].limits); + kfree(iface_comb); +} + +static void ath12k_mac_cleanup_iface_combinations(struct ath12k_hw *ah) +{ + struct wiphy *wiphy = ah->hw->wiphy; + const struct wiphy_radio *radio; + int i; + + if (wiphy->n_radio > 0) { + radio = wiphy->radio; + for (i = 0; i < wiphy->n_radio; i++) + ath12k_mac_cleanup_iface_comb(radio[i].iface_combinations); + + kfree(wiphy->radio); + } + + ath12k_mac_cleanup_iface_comb(wiphy->iface_combinations); +} + +static int ath12k_mac_setup_iface_combinations(struct ath12k_hw *ah) +{ + struct ieee80211_iface_combination *combinations, *comb; + struct wiphy *wiphy = ah->hw->wiphy; + struct wiphy_radio *radio; + struct ath12k *ar; + int i, ret; + + combinations = kzalloc(sizeof(*combinations), GFP_KERNEL); + if (!combinations) + return -ENOMEM; + + if (ah->num_radio == 1) { + ret = ath12k_mac_setup_radio_iface_comb(&ah->radio[0], + combinations); + if (ret) { + ath12k_hw_warn(ah, "failed to setup radio interface combinations for one radio: %d", + ret); + goto err_free_combinations; + } + + goto out; + } + + /* there are multiple radios */ + + radio = kcalloc(ah->num_radio, sizeof(*radio), GFP_KERNEL); + if (!radio) { + ret = -ENOMEM; + goto err_free_combinations; + } + + for_each_ar(ah, ar, i) { + comb = kzalloc(sizeof(*comb), GFP_KERNEL); + if (!comb) { + ret = -ENOMEM; + goto err_free_radios; + } + + ret = ath12k_mac_setup_radio_iface_comb(ar, comb); + if (ret) { + ath12k_hw_warn(ah, "failed to setup radio interface combinations for radio %d: %d", + i, ret); + kfree(comb); + goto err_free_radios; + } + + radio[i].freq_range = &ar->freq_range; + radio[i].n_freq_range = 1; + + radio[i].iface_combinations = comb; + radio[i].n_iface_combinations = 1; + } + + ret = ath12k_mac_setup_global_iface_comb(ah, radio, ah->num_radio, combinations); + if (ret) { + ath12k_hw_warn(ah, "failed to setup global interface combinations: %d", + ret); + goto err_free_all_radios; + } + + wiphy->radio = radio; + wiphy->n_radio = ah->num_radio; + +out: wiphy->iface_combinations = combinations; wiphy->n_iface_combinations = 1; return 0; + +err_free_all_radios: + i = ah->num_radio; + +err_free_radios: + while (i--) + ath12k_mac_cleanup_iface_comb(radio[i].iface_combinations); + + kfree(radio); + +err_free_combinations: + kfree(combinations); + + return ret; } static const u8 ath12k_if_types_ext_capa[] = { @@ -9444,7 +10715,7 @@ static const u8 ath12k_if_types_ext_capa_ap[] = { [10] = WLAN_EXT_CAPA11_EMA_SUPPORT, }; -static const struct wiphy_iftype_ext_capab ath12k_iftypes_ext_capa[] = { +static struct wiphy_iftype_ext_capab ath12k_iftypes_ext_capa[] = { { .extended_capabilities = ath12k_if_types_ext_capa, .extended_capabilities_mask = ath12k_if_types_ext_capa, @@ -9461,6 +10732,8 @@ static const struct wiphy_iftype_ext_capab ath12k_iftypes_ext_capa[] = { .extended_capabilities_mask = ath12k_if_types_ext_capa_ap, .extended_capabilities_len = sizeof(ath12k_if_types_ext_capa_ap), + .eml_capabilities = 0, + .mld_capa_and_ops = 0, }, }; @@ -9477,7 +10750,6 @@ static void ath12k_mac_cleanup_unregister(struct ath12k *ar) static void ath12k_mac_hw_unregister(struct ath12k_hw *ah) { struct ieee80211_hw *hw = ah->hw; - struct wiphy *wiphy = hw->wiphy; struct ath12k *ar; int i; @@ -9491,8 +10763,7 @@ static void ath12k_mac_hw_unregister(struct ath12k_hw *ah) for_each_ar(ah, ar, i) ath12k_mac_cleanup_unregister(ar); - kfree(wiphy->iface_combinations[0].limits); - kfree(wiphy->iface_combinations); + ath12k_mac_cleanup_iface_combinations(ah); SET_IEEE80211_DEV(hw, NULL); } @@ -9567,7 +10838,10 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah) if (ret) goto err_cleanup_unregister; - ht_cap &= ht_cap_info; + /* 6 GHz does not support HT Cap, hence do not consider it */ + if (!ar->supports_6ghz) + ht_cap &= ht_cap_info; + wiphy->max_ap_assoc_sta += ar->max_num_stations; /* Advertise the max antenna support of all radios, driver can handle @@ -9631,7 +10905,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah) ieee80211_hw_set(hw, SUPPORTS_TX_FRAG); ieee80211_hw_set(hw, REPORTS_LOW_ACK); - if ((ht_cap & WMI_HT_CAP_ENABLED) || ar->supports_6ghz) { + if ((ht_cap & WMI_HT_CAP_ENABLED) || is_6ghz) { ieee80211_hw_set(hw, AMPDU_AGGREGATION); ieee80211_hw_set(hw, TX_AMPDU_SETUP_IN_HW); ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER); @@ -9647,7 +10921,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah) * handle it when the ht capability different for each band. */ if (ht_cap & WMI_HT_CAP_DYNAMIC_SMPS || - (ar->supports_6ghz && ab->hw_params->supports_dynamic_smps_6ghz)) + (is_6ghz && ab->hw_params->supports_dynamic_smps_6ghz)) wiphy->features |= NL80211_FEATURE_DYNAMIC_SMPS; wiphy->max_scan_ssids = WLAN_SCAN_PARAMS_MAX_SSID; @@ -9669,6 +10943,15 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah) */ wiphy->flags |= WIPHY_FLAG_DISABLE_WEXT; + /* Copy over MLO related capabilities received from + * WMI_SERVICE_READY_EXT2_EVENT if single_chip_mlo_supp is set. + */ + if (ab->ag->mlo_capable) { + ath12k_iftypes_ext_capa[2].eml_capabilities = cap->eml_cap; + ath12k_iftypes_ext_capa[2].mld_capa_and_ops = cap->mld_cap; + wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO; + } + hw->queues = ATH12K_HW_MAX_QUEUES; wiphy->tx_queue_len = ATH12K_QUEUE_LEN; hw->offchannel_tx_hw_queue = ATH12K_HW_MAX_QUEUES - 1; @@ -9722,13 +11005,13 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah) ret = ath12k_wow_init(ar); if (ret) { ath12k_warn(ar->ab, "failed to init wow: %d\n", ret); - goto err_free_if_combs; + goto err_cleanup_if_combs; } ret = ieee80211_register_hw(hw); if (ret) { ath12k_err(ab, "ieee80211 registration failed: %d\n", ret); - goto err_free_if_combs; + goto err_cleanup_if_combs; } if (is_monitor_disable) @@ -9758,9 +11041,8 @@ err_unregister_hw: ieee80211_unregister_hw(hw); -err_free_if_combs: - kfree(wiphy->iface_combinations[0].limits); - kfree(wiphy->iface_combinations); +err_cleanup_if_combs: + ath12k_mac_cleanup_iface_combinations(ah); err_complete_cleanup_unregister: i = ah->num_radio; @@ -9794,6 +11076,7 @@ static void ath12k_mac_setup(struct ath12k *ar) ar->cfg_rx_chainmask = pdev->cap.rx_chain_mask; ar->num_tx_chains = hweight32(pdev->cap.tx_chain_mask); ar->num_rx_chains = hweight32(pdev->cap.rx_chain_mask); + ar->scan.arvif = NULL; spin_lock_init(&ar->data_lock); INIT_LIST_HEAD(&ar->arvifs); @@ -9808,40 +11091,179 @@ static void ath12k_mac_setup(struct ath12k *ar) init_completion(&ar->scan.started); init_completion(&ar->scan.completed); init_completion(&ar->scan.on_channel); + init_completion(&ar->mlo_setup_done); INIT_DELAYED_WORK(&ar->scan.timeout, ath12k_scan_timeout_work); + wiphy_work_init(&ar->scan.vdev_clean_wk, ath12k_scan_vdev_clean_work); INIT_WORK(&ar->regd_update_work, ath12k_regd_update_work); - INIT_WORK(&ar->wmi_mgmt_tx_work, ath12k_mgmt_over_wmi_tx_work); + wiphy_work_init(&ar->wmi_mgmt_tx_work, ath12k_mgmt_over_wmi_tx_work); skb_queue_head_init(&ar->wmi_mgmt_tx_queue); } -int ath12k_mac_register(struct ath12k_base *ab) +static int __ath12k_mac_mlo_setup(struct ath12k *ar) { + u8 num_link = 0, partner_link_id[ATH12K_GROUP_MAX_RADIO] = {}; + struct ath12k_base *partner_ab, *ab = ar->ab; + struct ath12k_hw_group *ag = ab->ag; + struct wmi_mlo_setup_arg mlo = {}; + struct ath12k_pdev *pdev; + unsigned long time_left; + int i, j, ret; + + lockdep_assert_held(&ag->mutex); + + reinit_completion(&ar->mlo_setup_done); + + for (i = 0; i < ag->num_devices; i++) { + partner_ab = ag->ab[i]; + + for (j = 0; j < partner_ab->num_radios; j++) { + pdev = &partner_ab->pdevs[j]; + + /* Avoid the self link */ + if (ar == pdev->ar) + continue; + + partner_link_id[num_link] = pdev->hw_link_id; + num_link++; + + ath12k_dbg(ab, ATH12K_DBG_MAC, "device %d pdev %d hw_link_id %d num_link %d\n", + i, j, pdev->hw_link_id, num_link); + } + } + + mlo.group_id = cpu_to_le32(ag->id); + mlo.partner_link_id = partner_link_id; + mlo.num_partner_links = num_link; + ar->mlo_setup_status = 0; + + ath12k_dbg(ab, ATH12K_DBG_MAC, "group id %d num_link %d\n", ag->id, num_link); + + ret = ath12k_wmi_mlo_setup(ar, &mlo); + if (ret) { + ath12k_err(ab, "failed to send setup MLO WMI command for pdev %d: %d\n", + ar->pdev_idx, ret); + return ret; + } + + time_left = wait_for_completion_timeout(&ar->mlo_setup_done, + WMI_MLO_CMD_TIMEOUT_HZ); + + if (!time_left || ar->mlo_setup_status) + return ar->mlo_setup_status ? : -ETIMEDOUT; + + ath12k_dbg(ab, ATH12K_DBG_MAC, "mlo setup done for pdev %d\n", ar->pdev_idx); + + return 0; +} + +static int __ath12k_mac_mlo_teardown(struct ath12k *ar) +{ + struct ath12k_base *ab = ar->ab; + int ret; + + if (test_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags)) + return 0; + + ret = ath12k_wmi_mlo_teardown(ar); + if (ret) { + ath12k_warn(ab, "failed to send MLO teardown WMI command for pdev %d: %d\n", + ar->pdev_idx, ret); + return ret; + } + + ath12k_dbg(ab, ATH12K_DBG_MAC, "mlo teardown for pdev %d\n", ar->pdev_idx); + + return 0; +} + +int ath12k_mac_mlo_setup(struct ath12k_hw_group *ag) +{ + struct ath12k_hw *ah; + struct ath12k *ar; + int ret; + int i, j; + + for (i = 0; i < ag->num_hw; i++) { + ah = ag->ah[i]; + if (!ah) + continue; + + for_each_ar(ah, ar, j) { + ar = &ah->radio[j]; + ret = __ath12k_mac_mlo_setup(ar); + if (ret) { + ath12k_err(ar->ab, "failed to setup MLO: %d\n", ret); + goto err_setup; + } + } + } + + return 0; + +err_setup: + for (i = i - 1; i >= 0; i--) { + ah = ag->ah[i]; + if (!ah) + continue; + + for (j = j - 1; j >= 0; j--) { + ar = &ah->radio[j]; + if (!ar) + continue; + + __ath12k_mac_mlo_teardown(ar); + } + } + + return ret; +} + +void ath12k_mac_mlo_teardown(struct ath12k_hw_group *ag) +{ + struct ath12k_hw *ah; + struct ath12k *ar; + int ret, i, j; + + for (i = 0; i < ag->num_hw; i++) { + ah = ag->ah[i]; + if (!ah) + continue; + + for_each_ar(ah, ar, j) { + ar = &ah->radio[j]; + ret = __ath12k_mac_mlo_teardown(ar); + if (ret) { + ath12k_err(ar->ab, "failed to teardown MLO: %d\n", ret); + break; + } + } + } +} + +int ath12k_mac_register(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab = ag->ab[0]; struct ath12k_hw *ah; int i; int ret; - if (test_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags)) - return 0; - - /* Initialize channel counters frequency value in hertz */ - ab->cc_freq_hz = 320000; - ab->free_vdev_map = (1LL << (ab->num_radios * TARGET_NUM_VDEVS)) - 1; - - for (i = 0; i < ab->num_hw; i++) { - ah = ab->ah[i]; + for (i = 0; i < ag->num_hw; i++) { + ah = ath12k_ag_to_ah(ag, i); ret = ath12k_mac_hw_register(ah); if (ret) goto err; } + set_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags); + return 0; err: for (i = i - 1; i >= 0; i--) { - ah = ab->ah[i]; + ah = ath12k_ag_to_ah(ag, i); if (!ah) continue; @@ -9851,13 +11273,16 @@ err: return ret; } -void ath12k_mac_unregister(struct ath12k_base *ab) +void ath12k_mac_unregister(struct ath12k_hw_group *ag) { + struct ath12k_base *ab = ag->ab[0]; struct ath12k_hw *ah; int i; - for (i = ab->num_hw - 1; i >= 0; i--) { - ah = ab->ah[i]; + clear_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags); + + for (i = ag->num_hw - 1; i >= 0; i--) { + ah = ath12k_ag_to_ah(ag, i); if (!ah) continue; @@ -9870,12 +11295,13 @@ static void ath12k_mac_hw_destroy(struct ath12k_hw *ah) ieee80211_free_hw(ah->hw); } -static struct ath12k_hw *ath12k_mac_hw_allocate(struct ath12k_base *ab, +static struct ath12k_hw *ath12k_mac_hw_allocate(struct ath12k_hw_group *ag, struct ath12k_pdev_map *pdev_map, u8 num_pdev_map) { struct ieee80211_hw *hw; struct ath12k *ar; + struct ath12k_base *ab; struct ath12k_pdev *pdev; struct ath12k_hw *ah; int i; @@ -9891,6 +11317,7 @@ static struct ath12k_hw *ath12k_mac_hw_allocate(struct ath12k_base *ab, ah->num_radio = num_pdev_map; mutex_init(&ah->hw_mutex); + INIT_LIST_HEAD(&ah->ml_peers); for (i = 0; i < num_pdev_map; i++) { ab = pdev_map[i].ab; @@ -9905,54 +11332,116 @@ static struct ath12k_hw *ath12k_mac_hw_allocate(struct ath12k_base *ab, ar->pdev_idx = pdev_idx; pdev->ar = ar; + ag->hw_links[ar->hw_link_id].device_id = ab->device_id; + ag->hw_links[ar->hw_link_id].pdev_idx = pdev_idx; + ath12k_mac_setup(ar); + ath12k_dp_pdev_pre_alloc(ar); } return ah; } -void ath12k_mac_destroy(struct ath12k_base *ab) +void ath12k_mac_destroy(struct ath12k_hw_group *ag) { struct ath12k_pdev *pdev; - int i; + struct ath12k_base *ab = ag->ab[0]; + int i, j; + struct ath12k_hw *ah; - for (i = 0; i < ab->num_radios; i++) { - pdev = &ab->pdevs[i]; - if (!pdev->ar) + for (i = 0; i < ag->num_devices; i++) { + ab = ag->ab[i]; + if (!ab) continue; - pdev->ar = NULL; + for (j = 0; j < ab->num_radios; j++) { + pdev = &ab->pdevs[j]; + if (!pdev->ar) + continue; + pdev->ar = NULL; + } } - for (i = 0; i < ab->num_hw; i++) { - if (!ab->ah[i]) + for (i = 0; i < ag->num_hw; i++) { + ah = ath12k_ag_to_ah(ag, i); + if (!ah) continue; - ath12k_mac_hw_destroy(ab->ah[i]); - ab->ah[i] = NULL; + ath12k_mac_hw_destroy(ah); + ath12k_ag_set_ah(ag, i, NULL); } } -int ath12k_mac_allocate(struct ath12k_base *ab) +static void ath12k_mac_set_device_defaults(struct ath12k_base *ab) { + /* Initialize channel counters frequency value in hertz */ + ab->cc_freq_hz = 320000; + ab->free_vdev_map = (1LL << (ab->num_radios * TARGET_NUM_VDEVS)) - 1; +} + +int ath12k_mac_allocate(struct ath12k_hw_group *ag) +{ + struct ath12k_pdev_map pdev_map[ATH12K_GROUP_MAX_RADIO]; + int mac_id, device_id, total_radio, num_hw; + struct ath12k_base *ab; struct ath12k_hw *ah; - struct ath12k_pdev_map pdev_map[MAX_RADIOS]; int ret, i, j; u8 radio_per_hw; - if (test_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags)) - return 0; + total_radio = 0; + for (i = 0; i < ag->num_devices; i++) { + ab = ag->ab[i]; + if (!ab) + continue; - ab->num_hw = ab->num_radios; - radio_per_hw = 1; + ath12k_mac_set_device_defaults(ab); + total_radio += ab->num_radios; + } - for (i = 0; i < ab->num_hw; i++) { + if (!total_radio) + return -EINVAL; + + if (WARN_ON(total_radio > ATH12K_GROUP_MAX_RADIO)) + return -ENOSPC; + + /* All pdev get combined and register as single wiphy based on + * hardware group which participate in multi-link operation else + * each pdev get register separately. + */ + if (ag->mlo_capable) + radio_per_hw = total_radio; + else + radio_per_hw = 1; + + num_hw = total_radio / radio_per_hw; + + ag->num_hw = 0; + device_id = 0; + mac_id = 0; + for (i = 0; i < num_hw; i++) { for (j = 0; j < radio_per_hw; j++) { + if (device_id >= ag->num_devices || !ag->ab[device_id]) { + ret = -ENOSPC; + goto err; + } + + ab = ag->ab[device_id]; pdev_map[j].ab = ab; - pdev_map[j].pdev_idx = (i * radio_per_hw) + j; + pdev_map[j].pdev_idx = mac_id; + mac_id++; + + /* If mac_id falls beyond the current device MACs then + * move to next device + */ + if (mac_id >= ab->num_radios) { + mac_id = 0; + device_id++; + } } - ah = ath12k_mac_hw_allocate(ab, pdev_map, radio_per_hw); + ab = pdev_map->ab; + + ah = ath12k_mac_hw_allocate(ag, pdev_map, radio_per_hw); if (!ah) { ath12k_warn(ab, "failed to allocate mac80211 hw device for hw_idx %d\n", i); @@ -9960,20 +11449,22 @@ int ath12k_mac_allocate(struct ath12k_base *ab) goto err; } - ab->ah[i] = ah; - } + ah->dev = ab->dev; - ath12k_dp_pdev_pre_alloc(ab); + ag->ah[i] = ah; + ag->num_hw++; + } return 0; err: for (i = i - 1; i >= 0; i--) { - if (!ab->ah[i]) + ah = ath12k_ag_to_ah(ag, i); + if (!ah) continue; - ath12k_mac_hw_destroy(ab->ah[i]); - ab->ah[i] = NULL; + ath12k_mac_hw_destroy(ah); + ath12k_ag_set_ah(ag, i, NULL); } return ret; diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h index d382337ba649..3594729b6397 100644 --- a/drivers/net/wireless/ath/ath12k/mac.h +++ b/drivers/net/wireless/ath/ath12k/mac.h @@ -14,6 +14,7 @@ struct ath12k; struct ath12k_base; struct ath12k_hw; +struct ath12k_hw_group; struct ath12k_pdev_map; struct ath12k_generic_iter { @@ -44,6 +45,12 @@ struct ath12k_generic_iter { #define ATH12K_DEFAULT_LINK_ID 0 #define ATH12K_INVALID_LINK_ID 255 +/* Default link after the IEEE802.11 defined Max link id limit + * for driver usage purpose. + */ +#define ATH12K_DEFAULT_SCAN_LINK IEEE80211_MLD_MAX_NUM_LINKS +#define ATH12K_NUM_MAX_LINKS (IEEE80211_MLD_MAX_NUM_LINKS + 1) + enum ath12k_supported_bw { ATH12K_BW_20 = 0, ATH12K_BW_40 = 1, @@ -52,12 +59,17 @@ enum ath12k_supported_bw { ATH12K_BW_320 = 4, }; +struct ath12k_mac_get_any_chanctx_conf_arg { + struct ath12k *ar; + struct ieee80211_chanctx_conf *chanctx_conf; +}; + extern const struct htt_rx_ring_tlv_filter ath12k_mac_mon_status_filter_default; -void ath12k_mac_destroy(struct ath12k_base *ab); -void ath12k_mac_unregister(struct ath12k_base *ab); -int ath12k_mac_register(struct ath12k_base *ab); -int ath12k_mac_allocate(struct ath12k_base *ab); +void ath12k_mac_destroy(struct ath12k_hw_group *ag); +void ath12k_mac_unregister(struct ath12k_hw_group *ag); +int ath12k_mac_register(struct ath12k_hw_group *ag); +int ath12k_mac_allocate(struct ath12k_hw_group *ag); int ath12k_mac_hw_ratecode_to_legacy_rate(u8 hw_rc, u8 preamble, u8 *rateidx, u16 *rate); u8 ath12k_mac_bitrate_to_idx(const struct ieee80211_supported_band *sband, @@ -89,5 +101,12 @@ int ath12k_mac_vif_set_keepalive(struct ath12k_link_vif *arvif, enum wmi_sta_keepalive_method method, u32 interval); u8 ath12k_mac_get_target_pdev_id(struct ath12k *ar); +int ath12k_mac_mlo_setup(struct ath12k_hw_group *ag); +int ath12k_mac_mlo_ready(struct ath12k_hw_group *ag); +void ath12k_mac_mlo_teardown(struct ath12k_hw_group *ag); +int ath12k_mac_vdev_stop(struct ath12k_link_vif *arvif); +void ath12k_mac_get_any_chanctx_conf_iter(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *conf, + void *data); #endif diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c index cf907550e6a4..06cff3849ab8 100644 --- a/drivers/net/wireless/ath/ath12k/pci.c +++ b/drivers/net/wireless/ath/ath12k/pci.c @@ -1123,6 +1123,9 @@ void ath12k_pci_ext_irq_enable(struct ath12k_base *ab) void ath12k_pci_ext_irq_disable(struct ath12k_base *ab) { + if (!test_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags)) + return; + __ath12k_pci_ext_irq_disable(ab); ath12k_pci_sync_ext_irqs(ab); } @@ -1147,6 +1150,11 @@ int ath12k_pci_hif_resume(struct ath12k_base *ab) void ath12k_pci_stop(struct ath12k_base *ab) { + struct ath12k_pci *ab_pci = ath12k_pci_priv(ab); + + if (!test_bit(ATH12K_PCI_FLAG_INIT_DONE, &ab_pci->flags)) + return; + ath12k_pci_ce_irq_disable_sync(ab); ath12k_ce_cleanup_pipes(ab); } @@ -1717,6 +1725,7 @@ static void ath12k_pci_remove(struct pci_dev *pdev) if (test_bit(ATH12K_FLAG_QMI_FAIL, &ab->dev_flags)) { ath12k_pci_power_down(ab, false); ath12k_qmi_deinit_service(ab); + ath12k_core_hw_group_unassign(ab); goto qmi_fail; } @@ -1725,6 +1734,7 @@ static void ath12k_pci_remove(struct pci_dev *pdev) cancel_work_sync(&ab->reset_work); cancel_work_sync(&ab->dump_work); ath12k_core_deinit(ab); + ath12k_fw_unmap(ab); qmi_fail: ath12k_mhi_unregister(ab_pci); diff --git a/drivers/net/wireless/ath/ath12k/peer.c b/drivers/net/wireless/ath/ath12k/peer.c index 7a62665b8af9..792cca8a3fb1 100644 --- a/drivers/net/wireless/ath/ath12k/peer.c +++ b/drivers/net/wireless/ath/ath12k/peer.c @@ -8,6 +8,22 @@ #include "peer.h" #include "debug.h" +static struct ath12k_ml_peer *ath12k_peer_ml_find(struct ath12k_hw *ah, const u8 *addr) +{ + struct ath12k_ml_peer *ml_peer; + + lockdep_assert_wiphy(ah->hw->wiphy); + + list_for_each_entry(ml_peer, &ah->ml_peers, list) { + if (!ether_addr_equal(ml_peer->addr, addr)) + continue; + + return ml_peer; + } + + return NULL; +} + struct ath12k_peer *ath12k_peer_find(struct ath12k_base *ab, int vdev_id, const u8 *addr) { @@ -63,6 +79,20 @@ struct ath12k_peer *ath12k_peer_find_by_addr(struct ath12k_base *ab, return NULL; } +static struct ath12k_peer *ath12k_peer_find_by_ml_id(struct ath12k_base *ab, + int ml_peer_id) +{ + struct ath12k_peer *peer; + + lockdep_assert_held(&ab->base_lock); + + list_for_each_entry(peer, &ab->peers, list) + if (ml_peer_id == peer->ml_id) + return peer; + + return NULL; +} + struct ath12k_peer *ath12k_peer_find_by_id(struct ath12k_base *ab, int peer_id) { @@ -70,6 +100,9 @@ struct ath12k_peer *ath12k_peer_find_by_id(struct ath12k_base *ab, lockdep_assert_held(&ab->base_lock); + if (peer_id & ATH12K_PEER_ML_ID_VALID) + return ath12k_peer_find_by_ml_id(ab, peer_id); + list_for_each_entry(peer, &ab->peers, list) if (peer_id == peer->peer_id) return peer; @@ -231,8 +264,9 @@ int ath12k_wait_for_peer_delete_done(struct ath12k *ar, u32 vdev_id, return 0; } -int ath12k_peer_delete(struct ath12k *ar, u32 vdev_id, u8 *addr) +static int ath12k_peer_delete_send(struct ath12k *ar, u32 vdev_id, const u8 *addr) { + struct ath12k_base *ab = ar->ab; int ret; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); @@ -241,12 +275,25 @@ int ath12k_peer_delete(struct ath12k *ar, u32 vdev_id, u8 *addr) ret = ath12k_wmi_send_peer_delete_cmd(ar, addr, vdev_id); if (ret) { - ath12k_warn(ar->ab, + ath12k_warn(ab, "failed to delete peer vdev_id %d addr %pM ret %d\n", vdev_id, addr, ret); return ret; } + return 0; +} + +int ath12k_peer_delete(struct ath12k *ar, u32 vdev_id, u8 *addr) +{ + int ret; + + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + ret = ath12k_peer_delete_send(ar, vdev_id, addr); + if (ret) + return ret; + ret = ath12k_wait_for_peer_delete_done(ar, vdev_id, addr); if (ret) return ret; @@ -266,7 +313,11 @@ int ath12k_peer_create(struct ath12k *ar, struct ath12k_link_vif *arvif, struct ath12k_wmi_peer_create_arg *arg) { struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); + struct ath12k_link_sta *arsta; + u8 link_id = arvif->link_id; struct ath12k_peer *peer; + struct ath12k_sta *ahsta; + u16 ml_peer_id; int ret; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); @@ -332,6 +383,29 @@ int ath12k_peer_create(struct ath12k *ar, struct ath12k_link_vif *arvif, arvif->ast_idx = peer->hw_peer_id; } + if (sta) { + ahsta = ath12k_sta_to_ahsta(sta); + arsta = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy, + ahsta->link[link_id]); + + peer->link_id = arsta->link_id; + + /* Fill ML info into created peer */ + if (sta->mlo) { + ml_peer_id = ahsta->ml_peer_id; + peer->ml_id = ml_peer_id | ATH12K_PEER_ML_ID_VALID; + ether_addr_copy(peer->ml_addr, sta->addr); + + /* the assoc link is considered primary for now */ + peer->primary_link = arsta->is_assoc_link; + peer->mlo = true; + } else { + peer->ml_id = ATH12K_MLO_PEER_ID_INVALID; + peer->primary_link = true; + peer->mlo = false; + } + } + peer->sec_type = HAL_ENCRYPT_TYPE_OPEN; peer->sec_type_grp = HAL_ENCRYPT_TYPE_OPEN; @@ -341,3 +415,150 @@ int ath12k_peer_create(struct ath12k *ar, struct ath12k_link_vif *arvif, return 0; } + +static u16 ath12k_peer_ml_alloc(struct ath12k_hw *ah) +{ + u16 ml_peer_id; + + lockdep_assert_wiphy(ah->hw->wiphy); + + for (ml_peer_id = 0; ml_peer_id < ATH12K_MAX_MLO_PEERS; ml_peer_id++) { + if (test_bit(ml_peer_id, ah->free_ml_peer_id_map)) + continue; + + set_bit(ml_peer_id, ah->free_ml_peer_id_map); + break; + } + + if (ml_peer_id == ATH12K_MAX_MLO_PEERS) + ml_peer_id = ATH12K_MLO_PEER_ID_INVALID; + + return ml_peer_id; +} + +int ath12k_peer_ml_create(struct ath12k_hw *ah, struct ieee80211_sta *sta) +{ + struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta); + struct ath12k_ml_peer *ml_peer; + + lockdep_assert_wiphy(ah->hw->wiphy); + + if (!sta->mlo) + return -EINVAL; + + ml_peer = ath12k_peer_ml_find(ah, sta->addr); + if (ml_peer) { + ath12k_hw_warn(ah, "ML peer %d exists already, unable to add new entry for %pM", + ml_peer->id, sta->addr); + return -EEXIST; + } + + ml_peer = kzalloc(sizeof(*ml_peer), GFP_ATOMIC); + if (!ml_peer) + return -ENOMEM; + + ahsta->ml_peer_id = ath12k_peer_ml_alloc(ah); + + if (ahsta->ml_peer_id == ATH12K_MLO_PEER_ID_INVALID) { + ath12k_hw_warn(ah, "unable to allocate ML peer id for sta %pM", + sta->addr); + kfree(ml_peer); + return -ENOMEM; + } + + ether_addr_copy(ml_peer->addr, sta->addr); + ml_peer->id = ahsta->ml_peer_id; + list_add(&ml_peer->list, &ah->ml_peers); + + return 0; +} + +int ath12k_peer_ml_delete(struct ath12k_hw *ah, struct ieee80211_sta *sta) +{ + struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta); + struct ath12k_ml_peer *ml_peer; + + lockdep_assert_wiphy(ah->hw->wiphy); + + if (!sta->mlo) + return -EINVAL; + + clear_bit(ahsta->ml_peer_id, ah->free_ml_peer_id_map); + ahsta->ml_peer_id = ATH12K_MLO_PEER_ID_INVALID; + + ml_peer = ath12k_peer_ml_find(ah, sta->addr); + if (!ml_peer) { + ath12k_hw_warn(ah, "ML peer for %pM not found", sta->addr); + return -EINVAL; + } + + list_del(&ml_peer->list); + kfree(ml_peer); + + return 0; +} + +int ath12k_peer_mlo_link_peers_delete(struct ath12k_vif *ahvif, struct ath12k_sta *ahsta) +{ + struct ieee80211_sta *sta = ath12k_ahsta_to_sta(ahsta); + struct ath12k_hw *ah = ahvif->ah; + struct ath12k_link_vif *arvif; + struct ath12k_link_sta *arsta; + unsigned long links; + struct ath12k *ar; + int ret, err_ret = 0; + u8 link_id; + + lockdep_assert_wiphy(ah->hw->wiphy); + + if (!sta->mlo) + return -EINVAL; + + /* FW expects delete of all link peers at once before waiting for reception + * of peer unmap or delete responses + */ + links = ahsta->links_map; + for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif = wiphy_dereference(ah->hw->wiphy, ahvif->link[link_id]); + arsta = wiphy_dereference(ah->hw->wiphy, ahsta->link[link_id]); + if (!arvif || !arsta) + continue; + + ar = arvif->ar; + if (!ar) + continue; + + ath12k_dp_peer_cleanup(ar, arvif->vdev_id, arsta->addr); + + ret = ath12k_peer_delete_send(ar, arvif->vdev_id, arsta->addr); + if (ret) { + ath12k_warn(ar->ab, + "failed to delete peer vdev_id %d addr %pM ret %d\n", + arvif->vdev_id, arsta->addr, ret); + err_ret = ret; + continue; + } + } + + /* Ensure all link peers are deleted and unmapped */ + links = ahsta->links_map; + for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif = wiphy_dereference(ah->hw->wiphy, ahvif->link[link_id]); + arsta = wiphy_dereference(ah->hw->wiphy, ahsta->link[link_id]); + if (!arvif || !arsta) + continue; + + ar = arvif->ar; + if (!ar) + continue; + + ret = ath12k_wait_for_peer_delete_done(ar, arvif->vdev_id, arsta->addr); + if (ret) { + err_ret = ret; + continue; + } + ar->num_peers--; + } + + return err_ret; +} diff --git a/drivers/net/wireless/ath/ath12k/peer.h b/drivers/net/wireless/ath/ath12k/peer.h index b955f0cdf598..5870ee11a8c7 100644 --- a/drivers/net/wireless/ath/ath12k/peer.h +++ b/drivers/net/wireless/ath/ath12k/peer.h @@ -19,6 +19,8 @@ struct ppdu_user_delayba { u32 resp_rate_flags; }; +#define ATH12K_PEER_ML_ID_VALID BIT(13) + struct ath12k_peer { struct list_head list; struct ieee80211_sta *sta; @@ -44,9 +46,28 @@ struct ath12k_peer { struct ppdu_user_delayba ppdu_stats_delayba; bool delayba_flag; bool is_authorized; - + bool mlo; /* protected by ab->data_lock */ bool dp_setup_done; + + u16 ml_id; + + /* any other ML info common for all partners can be added + * here and would be same for all partner peers. + */ + u8 ml_addr[ETH_ALEN]; + + /* To ensure only certain work related to dp is done once */ + bool primary_link; + + /* for reference to ath12k_link_sta */ + u8 link_id; +}; + +struct ath12k_ml_peer { + struct list_head list; + u8 addr[ETH_ALEN]; + u16 id; }; void ath12k_peer_unmap_event(struct ath12k_base *ab, u16 peer_id); @@ -66,5 +87,8 @@ int ath12k_wait_for_peer_delete_done(struct ath12k *ar, u32 vdev_id, const u8 *addr); bool ath12k_peer_exist_by_vdev_id(struct ath12k_base *ab, int vdev_id); struct ath12k_peer *ath12k_peer_find_by_ast(struct ath12k_base *ab, int ast_hash); +int ath12k_peer_ml_create(struct ath12k_hw *ah, struct ieee80211_sta *sta); +int ath12k_peer_ml_delete(struct ath12k_hw *ah, struct ieee80211_sta *sta); +int ath12k_peer_mlo_link_peers_delete(struct ath12k_vif *ahvif, struct ath12k_sta *ahsta); #endif /* _PEER_H_ */ diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c index b93ce9f87f61..5c3563383fab 100644 --- a/drivers/net/wireless/ath/ath12k/qmi.c +++ b/drivers/net/wireless/ath/ath12k/qmi.c @@ -2016,26 +2016,57 @@ static const struct qmi_elem_info qmi_wlanfw_wlan_ini_resp_msg_v01_ei[] = { }, }; -static void ath12k_host_cap_parse_mlo(struct ath12k_base *ab, - struct qmi_wlanfw_host_cap_req_msg_v01 *req) +static void ath12k_host_cap_hw_link_id_init(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab, *partner_ab; + int i, j, hw_id_base; + + for (i = 0; i < ag->num_devices; i++) { + hw_id_base = 0; + ab = ag->ab[i]; + + for (j = 0; j < ag->num_devices; j++) { + partner_ab = ag->ab[j]; + + if (partner_ab->wsi_info.index >= ab->wsi_info.index) + continue; + + hw_id_base += partner_ab->qmi.num_radios; + } + + ab->wsi_info.hw_link_id_base = hw_id_base; + } + + ag->hw_link_id_init_done = true; +} + +static int ath12k_host_cap_parse_mlo(struct ath12k_base *ab, + struct qmi_wlanfw_host_cap_req_msg_v01 *req) { struct wlfw_host_mlo_chip_info_s_v01 *info; + struct ath12k_hw_group *ag = ab->ag; + struct ath12k_base *partner_ab; u8 hw_link_id = 0; - int i; + int i, j, ret; - if (!(ab->mlo_capable_flags & ATH12K_INTRA_DEVICE_MLO_SUPPORT)) { + if (!ag->mlo_capable) { ath12k_dbg(ab, ATH12K_DBG_QMI, - "intra device MLO is disabled hence skip QMI MLO cap"); - return; + "MLO is disabled hence skip QMI MLO cap"); + return 0; } if (!ab->qmi.num_radios || ab->qmi.num_radios == U8_MAX) { - ab->mlo_capable_flags = 0; + ab->single_chip_mlo_supp = false; ath12k_dbg(ab, ATH12K_DBG_QMI, "skip QMI MLO cap due to invalid num_radio %d\n", ab->qmi.num_radios); - return; + return 0; + } + + if (ab->device_id == ATH12K_INVALID_DEVICE_ID) { + ath12k_err(ab, "failed to send MLO cap due to invalid device id\n"); + return -EINVAL; } req->mlo_capable_valid = 1; @@ -2043,30 +2074,88 @@ static void ath12k_host_cap_parse_mlo(struct ath12k_base *ab, req->mlo_chip_id_valid = 1; req->mlo_chip_id = ab->device_id; req->mlo_group_id_valid = 1; - req->mlo_group_id = 0; + req->mlo_group_id = ag->id; req->max_mlo_peer_valid = 1; /* Max peer number generally won't change for the same device * but needs to be synced with host driver. */ req->max_mlo_peer = ab->hw_params->max_mlo_peer; req->mlo_num_chips_valid = 1; - req->mlo_num_chips = 1; + req->mlo_num_chips = ag->num_devices; - info = &req->mlo_chip_info[0]; - info->chip_id = ab->device_id; - info->num_local_links = ab->qmi.num_radios; + ath12k_dbg(ab, ATH12K_DBG_QMI, "mlo capability advertisement device_id %d group_id %d num_devices %d", + req->mlo_chip_id, req->mlo_group_id, req->mlo_num_chips); - for (i = 0; i < info->num_local_links; i++) { - info->hw_link_id[i] = hw_link_id; - info->valid_mlo_link_id[i] = 1; + mutex_lock(&ag->mutex); - hw_link_id++; + if (!ag->hw_link_id_init_done) + ath12k_host_cap_hw_link_id_init(ag); + + for (i = 0; i < ag->num_devices; i++) { + info = &req->mlo_chip_info[i]; + partner_ab = ag->ab[i]; + + if (partner_ab->device_id == ATH12K_INVALID_DEVICE_ID) { + ath12k_err(ab, "failed to send MLO cap due to invalid partner device id\n"); + ret = -EINVAL; + goto device_cleanup; + } + + info->chip_id = partner_ab->device_id; + info->num_local_links = partner_ab->qmi.num_radios; + + ath12k_dbg(ab, ATH12K_DBG_QMI, "mlo device id %d num_link %d\n", + info->chip_id, info->num_local_links); + + for (j = 0; j < info->num_local_links; j++) { + info->hw_link_id[j] = partner_ab->wsi_info.hw_link_id_base + j; + info->valid_mlo_link_id[j] = 1; + + ath12k_dbg(ab, ATH12K_DBG_QMI, "mlo hw_link_id %d\n", + info->hw_link_id[j]); + + hw_link_id++; + } } + if (hw_link_id <= 0) + ag->mlo_capable = false; + req->mlo_chip_info_valid = 1; + + mutex_unlock(&ag->mutex); + + return 0; + +device_cleanup: + for (i = i - 1; i >= 0; i--) { + info = &req->mlo_chip_info[i]; + + memset(info, 0, sizeof(*info)); + } + + req->mlo_num_chips = 0; + req->mlo_num_chips_valid = 0; + + req->max_mlo_peer = 0; + req->max_mlo_peer_valid = 0; + req->mlo_group_id = 0; + req->mlo_group_id_valid = 0; + req->mlo_chip_id = 0; + req->mlo_chip_id_valid = 0; + req->mlo_capable = 0; + req->mlo_capable_valid = 0; + + ag->mlo_capable = false; + + mutex_unlock(&ag->mutex); + + return ret; } -static int ath12k_qmi_host_cap_send(struct ath12k_base *ab) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath12k_qmi_host_cap_send(struct ath12k_base *ab) { struct qmi_wlanfw_host_cap_req_msg_v01 req = {}; struct qmi_wlanfw_host_cap_resp_msg_v01 resp = {}; @@ -2111,7 +2200,9 @@ static int ath12k_qmi_host_cap_send(struct ath12k_base *ab) req.nm_modem |= PLATFORM_CAP_PCIE_GLOBAL_RESET; } - ath12k_host_cap_parse_mlo(ab, &req); + ret = ath12k_host_cap_parse_mlo(ab, &req); + if (ret < 0) + goto out; ret = qmi_txn_init(&ab->qmi.handle, &txn, qmi_wlanfw_host_cap_resp_msg_v01_ei, &resp); @@ -2174,12 +2265,9 @@ static void ath12k_qmi_phy_cap_send(struct ath12k_base *ab) goto out; } - if (resp.single_chip_mlo_support_valid) { - if (resp.single_chip_mlo_support) - ab->mlo_capable_flags |= ATH12K_INTRA_DEVICE_MLO_SUPPORT; - else - ab->mlo_capable_flags &= ~ATH12K_INTRA_DEVICE_MLO_SUPPORT; - } + if (resp.single_chip_mlo_support_valid && + resp.single_chip_mlo_support) + ab->single_chip_mlo_supp = true; if (!resp.num_phy_valid) { ret = -ENODATA; @@ -2275,7 +2363,9 @@ resp_out: return ret; } -static int ath12k_qmi_respond_fw_mem_request(struct ath12k_base *ab) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath12k_qmi_respond_fw_mem_request(struct ath12k_base *ab) { struct qmi_wlanfw_respond_mem_req_msg_v01 *req; struct qmi_wlanfw_respond_mem_resp_msg_v01 resp = {}; @@ -2350,30 +2440,125 @@ out: return ret; } +static void ath12k_qmi_free_mlo_mem_chunk(struct ath12k_base *ab, + struct target_mem_chunk *chunk, + int idx) +{ + struct ath12k_hw_group *ag = ab->ag; + struct target_mem_chunk *mlo_chunk; + + lockdep_assert_held(&ag->mutex); + + if (!ag->mlo_mem.init_done || ag->num_started) + return; + + if (idx >= ARRAY_SIZE(ag->mlo_mem.chunk)) { + ath12k_warn(ab, "invalid index for MLO memory chunk free: %d\n", idx); + return; + } + + mlo_chunk = &ag->mlo_mem.chunk[idx]; + if (mlo_chunk->v.addr) { + dma_free_coherent(ab->dev, + mlo_chunk->size, + mlo_chunk->v.addr, + mlo_chunk->paddr); + mlo_chunk->v.addr = NULL; + } + + mlo_chunk->paddr = 0; + mlo_chunk->size = 0; + chunk->v.addr = NULL; + chunk->paddr = 0; + chunk->size = 0; +} + static void ath12k_qmi_free_target_mem_chunk(struct ath12k_base *ab) { - int i; + struct ath12k_hw_group *ag = ab->ag; + int i, mlo_idx; - for (i = 0; i < ab->qmi.mem_seg_count; i++) { + for (i = 0, mlo_idx = 0; i < ab->qmi.mem_seg_count; i++) { if (!ab->qmi.target_mem[i].v.addr) continue; - dma_free_coherent(ab->dev, - ab->qmi.target_mem[i].prev_size, - ab->qmi.target_mem[i].v.addr, - ab->qmi.target_mem[i].paddr); - ab->qmi.target_mem[i].v.addr = NULL; + if (ab->qmi.target_mem[i].type == MLO_GLOBAL_MEM_REGION_TYPE) { + ath12k_qmi_free_mlo_mem_chunk(ab, + &ab->qmi.target_mem[i], + mlo_idx++); + } else { + dma_free_coherent(ab->dev, + ab->qmi.target_mem[i].prev_size, + ab->qmi.target_mem[i].v.addr, + ab->qmi.target_mem[i].paddr); + ab->qmi.target_mem[i].v.addr = NULL; + } } + + if (!ag->num_started && ag->mlo_mem.init_done) { + ag->mlo_mem.init_done = false; + ag->mlo_mem.mlo_mem_size = 0; + } +} + +static int ath12k_qmi_alloc_chunk(struct ath12k_base *ab, + struct target_mem_chunk *chunk) +{ + /* Firmware reloads in recovery/resume. + * In such cases, no need to allocate memory for FW again. + */ + if (chunk->v.addr) { + if (chunk->prev_type == chunk->type && + chunk->prev_size == chunk->size) + goto this_chunk_done; + + /* cannot reuse the existing chunk */ + dma_free_coherent(ab->dev, chunk->prev_size, + chunk->v.addr, chunk->paddr); + chunk->v.addr = NULL; + } + + chunk->v.addr = dma_alloc_coherent(ab->dev, + chunk->size, + &chunk->paddr, + GFP_KERNEL | __GFP_NOWARN); + if (!chunk->v.addr) { + if (chunk->size > ATH12K_QMI_MAX_CHUNK_SIZE) { + ab->qmi.target_mem_delayed = true; + ath12k_warn(ab, + "qmi dma allocation failed (%d B type %u), will try later with small size\n", + chunk->size, + chunk->type); + ath12k_qmi_free_target_mem_chunk(ab); + return -EAGAIN; + } + ath12k_warn(ab, "memory allocation failure for %u size: %d\n", + chunk->type, chunk->size); + return -ENOMEM; + } + chunk->prev_type = chunk->type; + chunk->prev_size = chunk->size; +this_chunk_done: + return 0; } static int ath12k_qmi_alloc_target_mem_chunk(struct ath12k_base *ab) { - int i; - struct target_mem_chunk *chunk; + struct target_mem_chunk *chunk, *mlo_chunk; + struct ath12k_hw_group *ag = ab->ag; + int i, mlo_idx, ret; + int mlo_size = 0; + + mutex_lock(&ag->mutex); + + if (!ag->mlo_mem.init_done) { + memset(ag->mlo_mem.chunk, 0, sizeof(ag->mlo_mem.chunk)); + ag->mlo_mem.init_done = true; + } ab->qmi.target_mem_delayed = false; - for (i = 0; i < ab->qmi.mem_seg_count; i++) { + for (i = 0, mlo_idx = 0; i < ab->qmi.mem_seg_count; i++) { chunk = &ab->qmi.target_mem[i]; /* Allocate memory for the region and the functionality supported @@ -2385,42 +2570,41 @@ static int ath12k_qmi_alloc_target_mem_chunk(struct ath12k_base *ab) case M3_DUMP_REGION_TYPE: case PAGEABLE_MEM_REGION_TYPE: case CALDB_MEM_REGION_TYPE: - /* Firmware reloads in recovery/resume. - * In such cases, no need to allocate memory for FW again. - */ - if (chunk->v.addr) { - if (chunk->prev_type == chunk->type && - chunk->prev_size == chunk->size) - goto this_chunk_done; - - /* cannot reuse the existing chunk */ - dma_free_coherent(ab->dev, chunk->prev_size, - chunk->v.addr, chunk->paddr); - chunk->v.addr = NULL; + ret = ath12k_qmi_alloc_chunk(ab, chunk); + if (ret) + goto err; + break; + case MLO_GLOBAL_MEM_REGION_TYPE: + mlo_size += chunk->size; + if (ag->mlo_mem.mlo_mem_size && + mlo_size > ag->mlo_mem.mlo_mem_size) { + ath12k_err(ab, "QMI MLO memory allocation failure, requested size %d is more than allocated size %d", + mlo_size, ag->mlo_mem.mlo_mem_size); + ret = -EINVAL; + goto err; } - chunk->v.addr = dma_alloc_coherent(ab->dev, - chunk->size, - &chunk->paddr, - GFP_KERNEL | __GFP_NOWARN); - if (!chunk->v.addr) { - if (chunk->size > ATH12K_QMI_MAX_CHUNK_SIZE) { - ab->qmi.target_mem_delayed = true; - ath12k_warn(ab, - "qmi dma allocation failed (%d B type %u), will try later with small size\n", - chunk->size, - chunk->type); - ath12k_qmi_free_target_mem_chunk(ab); - return 0; + mlo_chunk = &ag->mlo_mem.chunk[mlo_idx]; + if (mlo_chunk->paddr) { + if (chunk->size != mlo_chunk->size) { + ath12k_err(ab, "QMI MLO chunk memory allocation failure for index %d, requested size %d is more than allocated size %d", + mlo_idx, chunk->size, mlo_chunk->size); + ret = -EINVAL; + goto err; } - ath12k_warn(ab, "memory allocation failure for %u size: %d\n", - chunk->type, chunk->size); - return -ENOMEM; + } else { + mlo_chunk->size = chunk->size; + mlo_chunk->type = chunk->type; + ret = ath12k_qmi_alloc_chunk(ab, mlo_chunk); + if (ret) + goto err; + memset(mlo_chunk->v.addr, 0, mlo_chunk->size); } - chunk->prev_type = chunk->type; - chunk->prev_size = chunk->size; -this_chunk_done: + chunk->paddr = mlo_chunk->paddr; + chunk->v.addr = mlo_chunk->v.addr; + mlo_idx++; + break; default: ath12k_warn(ab, "memory type %u not supported\n", @@ -2430,10 +2614,39 @@ this_chunk_done: break; } } + + if (!ag->mlo_mem.mlo_mem_size) { + ag->mlo_mem.mlo_mem_size = mlo_size; + } else if (ag->mlo_mem.mlo_mem_size != mlo_size) { + ath12k_err(ab, "QMI MLO memory size error, expected size is %d but requested size is %d", + ag->mlo_mem.mlo_mem_size, mlo_size); + ret = -EINVAL; + goto err; + } + + mutex_unlock(&ag->mutex); + return 0; + +err: + ath12k_qmi_free_target_mem_chunk(ab); + + mutex_unlock(&ag->mutex); + + /* The firmware will attempt to request memory in smaller chunks + * on the next try. However, the current caller should be notified + * that this instance of request parsing was successful. + * Therefore, return 0 only. + */ + if (ret == -EAGAIN) + ret = 0; + + return ret; } -static int ath12k_qmi_request_target_cap(struct ath12k_base *ab) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath12k_qmi_request_target_cap(struct ath12k_base *ab) { struct qmi_wlanfw_cap_req_msg_v01 req = {}; struct qmi_wlanfw_cap_resp_msg_v01 resp = {}; @@ -2619,8 +2832,10 @@ out: return ret; } -static int ath12k_qmi_load_bdf_qmi(struct ath12k_base *ab, - enum ath12k_qmi_bdf_type type) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath12k_qmi_load_bdf_qmi(struct ath12k_base *ab, + enum ath12k_qmi_bdf_type type) { struct device *dev = ab->dev; char filename[ATH12K_QMI_MAX_BDF_FILE_NAME_SIZE]; @@ -2791,7 +3006,9 @@ out: return ret; } -static int ath12k_qmi_wlanfw_m3_info_send(struct ath12k_base *ab) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath12k_qmi_wlanfw_m3_info_send(struct ath12k_base *ab) { struct m3_mem_region *m3_mem = &ab->qmi.m3_mem; struct qmi_wlanfw_m3_info_req_msg_v01 req = {}; @@ -3023,6 +3240,8 @@ void ath12k_qmi_firmware_stop(struct ath12k_base *ab) { int ret; + clear_bit(ATH12K_FLAG_QMI_FW_READY_COMPLETE, &ab->dev_flags); + ret = ath12k_qmi_wlanfw_mode_send(ab, ATH12K_FIRMWARE_MODE_OFF); if (ret < 0) { ath12k_warn(ab, "qmi failed to send wlan mode off\n"); @@ -3079,9 +3298,69 @@ ath12k_qmi_driver_event_post(struct ath12k_qmi *qmi, return 0; } -static int ath12k_qmi_event_server_arrive(struct ath12k_qmi *qmi) +void ath12k_qmi_trigger_host_cap(struct ath12k_base *ab) { - struct ath12k_base *ab = qmi->ab; + struct ath12k_qmi *qmi = &ab->qmi; + + spin_lock(&qmi->event_lock); + + if (ath12k_qmi_get_event_block(qmi)) + ath12k_qmi_set_event_block(qmi, false); + + spin_unlock(&qmi->event_lock); + + ath12k_dbg(ab, ATH12K_DBG_QMI, "trigger host cap for device id %d\n", + ab->device_id); + + ath12k_qmi_driver_event_post(qmi, ATH12K_QMI_EVENT_HOST_CAP, NULL); +} + +static bool ath12k_qmi_hw_group_host_cap_ready(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab; + int i; + + for (i = 0; i < ag->num_devices; i++) { + ab = ag->ab[i]; + + if (!(ab && ab->qmi.num_radios != U8_MAX)) + return false; + } + + return true; +} + +static struct ath12k_base *ath12k_qmi_hw_group_find_blocked(struct ath12k_hw_group *ag) +{ + struct ath12k_base *ab; + int i; + + lockdep_assert_held(&ag->mutex); + + for (i = 0; i < ag->num_devices; i++) { + ab = ag->ab[i]; + if (!ab) + continue; + + spin_lock(&ab->qmi.event_lock); + + if (ath12k_qmi_get_event_block(&ab->qmi)) { + spin_unlock(&ab->qmi.event_lock); + return ab; + } + + spin_unlock(&ab->qmi.event_lock); + } + + return NULL; +} + +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath12k_qmi_event_server_arrive(struct ath12k_qmi *qmi) +{ + struct ath12k_base *ab = qmi->ab, *block_ab; + struct ath12k_hw_group *ag = ab->ag; int ret; ath12k_qmi_phy_cap_send(ab); @@ -3092,16 +3371,30 @@ static int ath12k_qmi_event_server_arrive(struct ath12k_qmi *qmi) return ret; } - ret = ath12k_qmi_host_cap_send(ab); - if (ret < 0) { - ath12k_warn(ab, "qmi failed to send host cap QMI:%d\n", ret); - return ret; + spin_lock(&qmi->event_lock); + + ath12k_qmi_set_event_block(qmi, true); + + spin_unlock(&qmi->event_lock); + + mutex_lock(&ag->mutex); + + if (ath12k_qmi_hw_group_host_cap_ready(ag)) { + ath12k_core_hw_group_set_mlo_capable(ag); + + block_ab = ath12k_qmi_hw_group_find_blocked(ag); + if (block_ab) + ath12k_qmi_trigger_host_cap(block_ab); } + mutex_unlock(&ag->mutex); + return ret; } -static int ath12k_qmi_event_mem_request(struct ath12k_qmi *qmi) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath12k_qmi_event_mem_request(struct ath12k_qmi *qmi) { struct ath12k_base *ab = qmi->ab; int ret; @@ -3115,7 +3408,9 @@ static int ath12k_qmi_event_mem_request(struct ath12k_qmi *qmi) return ret; } -static int ath12k_qmi_event_load_bdf(struct ath12k_qmi *qmi) +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack +int ath12k_qmi_event_load_bdf(struct ath12k_qmi *qmi) { struct ath12k_base *ab = qmi->ab; int ret; @@ -3280,6 +3575,21 @@ static const struct qmi_ops ath12k_qmi_ops = { .del_server = ath12k_qmi_ops_del_server, }; +static int ath12k_qmi_event_host_cap(struct ath12k_qmi *qmi) +{ + struct ath12k_base *ab = qmi->ab; + int ret; + + ret = ath12k_qmi_host_cap_send(ab); + if (ret < 0) { + ath12k_warn(ab, "failed to send qmi host cap for device id %d: %d\n", + ab->device_id, ret); + return ret; + } + + return ret; +} + static void ath12k_qmi_driver_event_work(struct work_struct *work) { struct ath12k_qmi *qmi = container_of(work, struct ath12k_qmi, @@ -3306,7 +3616,6 @@ static void ath12k_qmi_driver_event_work(struct work_struct *work) break; case ATH12K_QMI_EVENT_SERVER_EXIT: set_bit(ATH12K_FLAG_CRASH_FLUSH, &ab->dev_flags); - set_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags); break; case ATH12K_QMI_EVENT_REQUEST_MEM: ret = ath12k_qmi_event_mem_request(qmi); @@ -3320,20 +3629,28 @@ static void ath12k_qmi_driver_event_work(struct work_struct *work) break; case ATH12K_QMI_EVENT_FW_READY: clear_bit(ATH12K_FLAG_QMI_FAIL, &ab->dev_flags); - if (test_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags)) { + if (test_bit(ATH12K_FLAG_QMI_FW_READY_COMPLETE, &ab->dev_flags)) { if (ab->is_reset) ath12k_hal_dump_srng_stats(ab); + + set_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags); queue_work(ab->workqueue, &ab->restart_work); break; } clear_bit(ATH12K_FLAG_CRASH_FLUSH, &ab->dev_flags); - clear_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags); - ath12k_core_qmi_firmware_ready(ab); - set_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags); + ret = ath12k_core_qmi_firmware_ready(ab); + if (!ret) + set_bit(ATH12K_FLAG_QMI_FW_READY_COMPLETE, + &ab->dev_flags); break; + case ATH12K_QMI_EVENT_HOST_CAP: + ret = ath12k_qmi_event_host_cap(qmi); + if (ret < 0) + set_bit(ATH12K_FLAG_QMI_FAIL, &ab->dev_flags); + break; default: ath12k_warn(ab, "invalid event type: %d", event->type); break; @@ -3386,11 +3703,15 @@ int ath12k_qmi_init_service(struct ath12k_base *ab) void ath12k_qmi_deinit_service(struct ath12k_base *ab) { + if (!ab->qmi.ab) + return; + qmi_handle_release(&ab->qmi.handle); cancel_work_sync(&ab->qmi.event_work); destroy_workqueue(ab->qmi.event_wq); ath12k_qmi_m3_free(ab); ath12k_qmi_free_target_mem_chunk(ab); + ab->qmi.ab = NULL; } void ath12k_qmi_free_resource(struct ath12k_base *ab) diff --git a/drivers/net/wireless/ath/ath12k/qmi.h b/drivers/net/wireless/ath/ath12k/qmi.h index 0dfcbd8cb59b..45d7c3fcafdd 100644 --- a/drivers/net/wireless/ath/ath12k/qmi.h +++ b/drivers/net/wireless/ath/ath12k/qmi.h @@ -68,6 +68,7 @@ enum ath12k_qmi_event_type { ATH12K_QMI_EVENT_FORCE_FW_ASSERT, ATH12K_QMI_EVENT_POWER_UP, ATH12K_QMI_EVENT_POWER_DOWN, + ATH12K_QMI_EVENT_HOST_CAP, ATH12K_QMI_EVENT_MAX, }; @@ -142,6 +143,10 @@ struct ath12k_qmi { u32 target_mem_mode; bool target_mem_delayed; u8 cal_done; + + /* protected with struct ath12k_qmi::event_lock */ + bool block_event; + u8 num_radios; struct target_info target; struct m3_mem_region m3_mem; @@ -167,6 +172,7 @@ enum ath12k_qmi_target_mem { BDF_MEM_REGION_TYPE = 0x2, M3_DUMP_REGION_TYPE = 0x3, CALDB_MEM_REGION_TYPE = 0x4, + MLO_GLOBAL_MEM_REGION_TYPE = 0x8, PAGEABLE_MEM_REGION_TYPE = 0x9, }; @@ -594,11 +600,26 @@ struct qmi_wlanfw_wlan_ini_resp_msg_v01 { struct qmi_response_type_v01 resp; }; +static inline void ath12k_qmi_set_event_block(struct ath12k_qmi *qmi, bool block) +{ + lockdep_assert_held(&qmi->event_lock); + + qmi->block_event = block; +} + +static inline bool ath12k_qmi_get_event_block(struct ath12k_qmi *qmi) +{ + lockdep_assert_held(&qmi->event_lock); + + return qmi->block_event; +} + int ath12k_qmi_firmware_start(struct ath12k_base *ab, u32 mode); void ath12k_qmi_firmware_stop(struct ath12k_base *ab); void ath12k_qmi_deinit_service(struct ath12k_base *ab); int ath12k_qmi_init_service(struct ath12k_base *ab); void ath12k_qmi_free_resource(struct ath12k_base *ab); +void ath12k_qmi_trigger_host_cap(struct ath12k_base *ab); #endif diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index dced2aa9ba1a..4dd6cdf84571 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -821,6 +821,8 @@ int ath12k_wmi_vdev_create(struct ath12k *ar, u8 *macaddr, struct wmi_vdev_create_cmd *cmd; struct sk_buff *skb; struct ath12k_wmi_vdev_txrx_streams_params *txrx_streams; + bool is_ml_vdev = is_valid_ether_addr(args->mld_addr); + struct wmi_vdev_create_mlo_params *ml_params; struct wmi_tlv *tlv; int ret, len; void *ptr; @@ -830,7 +832,8 @@ int ath12k_wmi_vdev_create(struct ath12k *ar, u8 *macaddr, * both the bands. */ len = sizeof(*cmd) + TLV_HDR_SIZE + - (WMI_NUM_SUPPORTED_BAND_MAX * sizeof(*txrx_streams)); + (WMI_NUM_SUPPORTED_BAND_MAX * sizeof(*txrx_streams)) + + (is_ml_vdev ? TLV_HDR_SIZE + sizeof(*ml_params) : 0); skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len); if (!skb) @@ -879,6 +882,21 @@ int ath12k_wmi_vdev_create(struct ath12k *ar, u8 *macaddr, txrx_streams->supported_rx_streams = cpu_to_le32(args->chains[NL80211_BAND_5GHZ].rx); + ptr += WMI_NUM_SUPPORTED_BAND_MAX * sizeof(*txrx_streams); + + if (is_ml_vdev) { + tlv = ptr; + tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, + sizeof(*ml_params)); + ptr += TLV_HDR_SIZE; + ml_params = ptr; + + ml_params->tlv_header = + ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_VDEV_CREATE_PARAMS, + sizeof(*ml_params)); + ether_addr_copy(ml_params->mld_macaddr.addr, args->mld_addr); + } + ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "WMI vdev create: id %d type %d subtype %d macaddr %pM pdevid %d\n", args->if_id, args->type, args->subtype, @@ -1020,19 +1038,27 @@ static void ath12k_wmi_put_wmi_channel(struct ath12k_wmi_channel_params *chan, int ath12k_wmi_vdev_start(struct ath12k *ar, struct wmi_vdev_start_req_arg *arg, bool restart) { + struct wmi_vdev_start_mlo_params *ml_params; + struct wmi_partner_link_info *partner_info; struct ath12k_wmi_pdev *wmi = ar->wmi; struct wmi_vdev_start_request_cmd *cmd; struct sk_buff *skb; struct ath12k_wmi_channel_params *chan; struct wmi_tlv *tlv; void *ptr; - int ret, len; + int ret, len, i, ml_arg_size = 0; if (WARN_ON(arg->ssid_len > sizeof(cmd->ssid.ssid))) return -EINVAL; len = sizeof(*cmd) + sizeof(*chan) + TLV_HDR_SIZE; + if (!restart && arg->ml.enabled) { + ml_arg_size = TLV_HDR_SIZE + sizeof(*ml_params) + + TLV_HDR_SIZE + (arg->ml.num_partner_links * + sizeof(*partner_info)); + len += ml_arg_size; + } skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len); if (!skb) return -ENOMEM; @@ -1085,6 +1111,61 @@ int ath12k_wmi_vdev_start(struct ath12k *ar, struct wmi_vdev_start_req_arg *arg, ptr += sizeof(*tlv); + if (ml_arg_size) { + tlv = ptr; + tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, + sizeof(*ml_params)); + ptr += TLV_HDR_SIZE; + + ml_params = ptr; + + ml_params->tlv_header = + ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_VDEV_START_PARAMS, + sizeof(*ml_params)); + + ml_params->flags = le32_encode_bits(arg->ml.enabled, + ATH12K_WMI_FLAG_MLO_ENABLED) | + le32_encode_bits(arg->ml.assoc_link, + ATH12K_WMI_FLAG_MLO_ASSOC_LINK) | + le32_encode_bits(arg->ml.mcast_link, + ATH12K_WMI_FLAG_MLO_MCAST_VDEV) | + le32_encode_bits(arg->ml.link_add, + ATH12K_WMI_FLAG_MLO_LINK_ADD); + + ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "vdev %d start ml flags 0x%x\n", + arg->vdev_id, ml_params->flags); + + ptr += sizeof(*ml_params); + + tlv = ptr; + tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, + arg->ml.num_partner_links * + sizeof(*partner_info)); + ptr += TLV_HDR_SIZE; + + partner_info = ptr; + + for (i = 0; i < arg->ml.num_partner_links; i++) { + partner_info->tlv_header = + ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_PARTNER_LINK_PARAMS, + sizeof(*partner_info)); + partner_info->vdev_id = + cpu_to_le32(arg->ml.partner_info[i].vdev_id); + partner_info->hw_link_id = + cpu_to_le32(arg->ml.partner_info[i].hw_link_id); + ether_addr_copy(partner_info->vdev_addr.addr, + arg->ml.partner_info[i].addr); + + ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "partner vdev %d hw_link_id %d macaddr%pM\n", + partner_info->vdev_id, partner_info->hw_link_id, + partner_info->vdev_addr.addr); + + partner_info++; + } + + ptr = partner_info; + } + ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "vdev %s id 0x%x freq 0x%x mode 0x%x\n", restart ? "restart" : "start", arg->vdev_id, arg->freq, arg->mode); @@ -1149,9 +1230,14 @@ int ath12k_wmi_send_peer_create_cmd(struct ath12k *ar, struct ath12k_wmi_pdev *wmi = ar->wmi; struct wmi_peer_create_cmd *cmd; struct sk_buff *skb; - int ret; + int ret, len; + struct wmi_peer_create_mlo_params *ml_param; + void *ptr; + struct wmi_tlv *tlv; - skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, sizeof(*cmd)); + len = sizeof(*cmd) + TLV_HDR_SIZE + sizeof(*ml_param); + + skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len); if (!skb) return -ENOMEM; @@ -1163,9 +1249,23 @@ int ath12k_wmi_send_peer_create_cmd(struct ath12k *ar, cmd->peer_type = cpu_to_le32(arg->peer_type); cmd->vdev_id = cpu_to_le32(arg->vdev_id); + ptr = skb->data + sizeof(*cmd); + tlv = ptr; + tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, + sizeof(*ml_param)); + ptr += TLV_HDR_SIZE; + ml_param = ptr; + ml_param->tlv_header = + ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_PEER_CREATE_PARAMS, + sizeof(*ml_param)); + if (arg->ml_enabled) + ml_param->flags = cpu_to_le32(ATH12K_WMI_FLAG_MLO_ENABLED); + + ptr += sizeof(*ml_param); + ath12k_dbg(ar->ab, ATH12K_DBG_WMI, - "WMI peer create vdev_id %d peer_addr %pM\n", - arg->vdev_id, arg->peer_addr); + "WMI peer create vdev_id %d peer_addr %pM ml_flags 0x%x\n", + arg->vdev_id, arg->peer_addr, ml_param->flags); ret = ath12k_wmi_cmd_send(wmi, skb, WMI_PEER_CREATE_CMDID); if (ret) { @@ -2001,12 +2101,15 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar, struct ath12k_wmi_vht_rate_set_params *mcs; struct ath12k_wmi_he_rate_set_params *he_mcs; struct ath12k_wmi_eht_rate_set_params *eht_mcs; + struct wmi_peer_assoc_mlo_params *ml_params; + struct wmi_peer_assoc_mlo_partner_info_params *partner_info; struct sk_buff *skb; struct wmi_tlv *tlv; void *ptr; u32 peer_legacy_rates_align; u32 peer_ht_rates_align; int i, ret, len; + __le32 v; peer_legacy_rates_align = roundup(arg->peer_legacy_rates.num_rates, sizeof(u32)); @@ -2018,8 +2121,13 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar, TLV_HDR_SIZE + (peer_ht_rates_align * sizeof(u8)) + sizeof(*mcs) + TLV_HDR_SIZE + (sizeof(*he_mcs) * arg->peer_he_mcs_count) + - TLV_HDR_SIZE + (sizeof(*eht_mcs) * arg->peer_eht_mcs_count) + - TLV_HDR_SIZE + TLV_HDR_SIZE; + TLV_HDR_SIZE + (sizeof(*eht_mcs) * arg->peer_eht_mcs_count); + + if (arg->ml.enabled) + len += TLV_HDR_SIZE + sizeof(*ml_params) + + TLV_HDR_SIZE + (arg->ml.num_partner_links * sizeof(*partner_info)); + else + len += (2 * TLV_HDR_SIZE); skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len); if (!skb) @@ -2143,12 +2251,38 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar, ptr += sizeof(*he_mcs); } - /* MLO header tag with 0 length */ - len = 0; tlv = ptr; + len = arg->ml.enabled ? sizeof(*ml_params) : 0; tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, len); ptr += TLV_HDR_SIZE; + if (!len) + goto skip_ml_params; + ml_params = ptr; + ml_params->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_PEER_ASSOC_PARAMS, + len); + ml_params->flags = cpu_to_le32(ATH12K_WMI_FLAG_MLO_ENABLED); + + if (arg->ml.assoc_link) + ml_params->flags |= cpu_to_le32(ATH12K_WMI_FLAG_MLO_ASSOC_LINK); + + if (arg->ml.primary_umac) + ml_params->flags |= cpu_to_le32(ATH12K_WMI_FLAG_MLO_PRIMARY_UMAC); + + if (arg->ml.logical_link_idx_valid) + ml_params->flags |= + cpu_to_le32(ATH12K_WMI_FLAG_MLO_LOGICAL_LINK_IDX_VALID); + + if (arg->ml.peer_id_valid) + ml_params->flags |= cpu_to_le32(ATH12K_WMI_FLAG_MLO_PEER_ID_VALID); + + ether_addr_copy(ml_params->mld_addr.addr, arg->ml.mld_addr); + ml_params->logical_link_idx = cpu_to_le32(arg->ml.logical_link_idx); + ml_params->ml_peer_id = cpu_to_le32(arg->ml.ml_peer_id); + ml_params->ieee_link_id = cpu_to_le32(arg->ml.ieee_link_id); + ptr += sizeof(*ml_params); + +skip_ml_params: /* Loop through the EHT rate set */ len = arg->peer_eht_mcs_count * sizeof(*eht_mcs); tlv = ptr; @@ -2165,12 +2299,45 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar, ptr += sizeof(*eht_mcs); } - /* ML partner links tag with 0 length */ - len = 0; tlv = ptr; + len = arg->ml.enabled ? arg->ml.num_partner_links * sizeof(*partner_info) : 0; + /* fill ML Partner links */ tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, len); ptr += TLV_HDR_SIZE; + if (len == 0) + goto send; + + for (i = 0; i < arg->ml.num_partner_links; i++) { + u32 cmd = WMI_TAG_MLO_PARTNER_LINK_PARAMS_PEER_ASSOC; + + partner_info = ptr; + partner_info->tlv_header = ath12k_wmi_tlv_cmd_hdr(cmd, + sizeof(*partner_info)); + partner_info->vdev_id = cpu_to_le32(arg->ml.partner_info[i].vdev_id); + partner_info->hw_link_id = + cpu_to_le32(arg->ml.partner_info[i].hw_link_id); + partner_info->flags = cpu_to_le32(ATH12K_WMI_FLAG_MLO_ENABLED); + + if (arg->ml.partner_info[i].assoc_link) + partner_info->flags |= + cpu_to_le32(ATH12K_WMI_FLAG_MLO_ASSOC_LINK); + + if (arg->ml.partner_info[i].primary_umac) + partner_info->flags |= + cpu_to_le32(ATH12K_WMI_FLAG_MLO_PRIMARY_UMAC); + + if (arg->ml.partner_info[i].logical_link_idx_valid) { + v = cpu_to_le32(ATH12K_WMI_FLAG_MLO_LINK_ID_VALID); + partner_info->flags |= v; + } + + partner_info->logical_link_idx = + cpu_to_le32(arg->ml.partner_info[i].logical_link_idx); + ptr += sizeof(*partner_info); + } + +send: ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "wmi peer assoc vdev id %d assoc id %d peer mac %pM peer_flags %x rate_caps %x peer_caps %x listen_intval %d ht_caps %x max_mpdu %d nss %d phymode %d peer_mpdu_density %d vht_caps %x he cap_info %x he ops %x he cap_info_ext %x he phy %x %x %x peer_bw_rxnss_override %x peer_flags_ext %x eht mac_cap %x %x eht phy_cap %x %x %x\n", cmd->vdev_id, cmd->peer_associd, arg->peer_mac, @@ -4495,6 +4662,9 @@ ath12k_wmi_tlv_mac_phy_caps_ext_parse(struct ath12k_base *ab, caps->eht_cap_info_internal); } + pdev->cap.eml_cap = le32_to_cpu(caps->eml_capability); + pdev->cap.mld_cap = le32_to_cpu(caps->mld_capability); + return 0; } @@ -5192,6 +5362,9 @@ static int wmi_process_mgmt_tx_comp(struct ath12k *ar, u32 desc_id, if ((!(info->flags & IEEE80211_TX_CTL_NO_ACK)) && !status) info->flags |= IEEE80211_TX_STAT_ACK; + if ((info->flags & IEEE80211_TX_CTL_NO_ACK) && !status) + info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED; + ieee80211_tx_status_irqsafe(ath12k_ar_to_hw(ar), msdu); num_mgmt = atomic_dec_if_positive(&ar->num_pending_mgmt_tx); @@ -6042,7 +6215,7 @@ static void ath12k_mgmt_rx_event(struct ath12k_base *ab, struct sk_buff *skb) goto exit; } - if ((test_bit(ATH12K_CAC_RUNNING, &ar->dev_flags)) || + if ((test_bit(ATH12K_FLAG_CAC_RUNNING, &ar->dev_flags)) || (rx_ev.status & (WMI_RX_STATUS_ERR_DECRYPT | WMI_RX_STATUS_ERR_KEY_CACHE_MISS | WMI_RX_STATUS_ERR_CRC))) { @@ -6171,7 +6344,8 @@ static struct ath12k *ath12k_get_ar_on_scan_state(struct ath12k_base *ab, spin_lock_bh(&ar->data_lock); if (ar->scan.state == state && - ar->scan.vdev_id == vdev_id) { + ar->scan.arvif && + ar->scan.arvif->vdev_id == vdev_id) { spin_unlock_bh(&ar->data_lock); return ar; } @@ -6687,6 +6861,7 @@ ath12k_wmi_process_csa_switch_count_event(struct ath12k_base *ab, const u32 *vdev_ids) { int i; + struct ieee80211_bss_conf *conf; struct ath12k_link_vif *arvif; struct ath12k_vif *ahvif; @@ -6705,7 +6880,20 @@ ath12k_wmi_process_csa_switch_count_event(struct ath12k_base *ab, } ahvif = arvif->ahvif; - if (arvif->is_up && ahvif->vif->bss_conf.csa_active) + if (arvif->link_id >= IEEE80211_MLD_MAX_NUM_LINKS) { + ath12k_warn(ab, "Invalid CSA switch count even link id: %d\n", + arvif->link_id); + continue; + } + + conf = rcu_dereference(ahvif->vif->link_conf[arvif->link_id]); + if (!conf) { + ath12k_warn(ab, "unable to access bss link conf in process csa for vif %pM link %u\n", + ahvif->vif->addr, arvif->link_id); + continue; + } + + if (arvif->is_up && conf->csa_active) ieee80211_csa_finish(ahvif->vif, 0); } rcu_read_unlock(); @@ -6750,6 +6938,7 @@ static void ath12k_wmi_pdev_dfs_radar_detected_event(struct ath12k_base *ab, struct sk_buff *skb) { const void **tb; + struct ath12k_mac_get_any_chanctx_conf_arg arg; const struct ath12k_wmi_pdev_radar_event *ev; struct ath12k *ar; int ret; @@ -6785,13 +6974,22 @@ ath12k_wmi_pdev_dfs_radar_detected_event(struct ath12k_base *ab, struct sk_buff goto exit; } + arg.ar = ar; + arg.chanctx_conf = NULL; + ieee80211_iter_chan_contexts_atomic(ath12k_ar_to_hw(ar), + ath12k_mac_get_any_chanctx_conf_iter, &arg); + if (!arg.chanctx_conf) { + ath12k_warn(ab, "failed to find valid chanctx_conf in radar detected event\n"); + goto exit; + } + ath12k_dbg(ar->ab, ATH12K_DBG_REG, "DFS Radar Detected in pdev %d\n", ev->pdev_id); if (ar->dfs_block_radar_events) ath12k_info(ab, "DFS Radar detected, but ignored as requested\n"); else - ieee80211_radar_detected(ath12k_ar_to_hw(ar), NULL); + ieee80211_radar_detected(ath12k_ar_to_hw(ar), arg.chanctx_conf); exit: rcu_read_unlock(); @@ -7146,6 +7344,79 @@ static void ath12k_wmi_gtk_offload_status_event(struct ath12k_base *ab, kfree(tb); } +static void ath12k_wmi_event_mlo_setup_complete(struct ath12k_base *ab, + struct sk_buff *skb) +{ + const struct wmi_mlo_setup_complete_event *ev; + struct ath12k *ar = NULL; + struct ath12k_pdev *pdev; + const void **tb; + int ret, i; + + tb = ath12k_wmi_tlv_parse_alloc(ab, skb, GFP_ATOMIC); + if (IS_ERR(tb)) { + ret = PTR_ERR(tb); + ath12k_warn(ab, "failed to parse mlo setup complete event tlv: %d\n", + ret); + return; + } + + ev = tb[WMI_TAG_MLO_SETUP_COMPLETE_EVENT]; + if (!ev) { + ath12k_warn(ab, "failed to fetch mlo setup complete event\n"); + kfree(tb); + return; + } + + if (le32_to_cpu(ev->pdev_id) > ab->num_radios) + goto skip_lookup; + + for (i = 0; i < ab->num_radios; i++) { + pdev = &ab->pdevs[i]; + if (pdev && pdev->pdev_id == le32_to_cpu(ev->pdev_id)) { + ar = pdev->ar; + break; + } + } + +skip_lookup: + if (!ar) { + ath12k_warn(ab, "invalid pdev_id %d status %u in setup complete event\n", + ev->pdev_id, ev->status); + goto out; + } + + ar->mlo_setup_status = le32_to_cpu(ev->status); + complete(&ar->mlo_setup_done); + +out: + kfree(tb); +} + +static void ath12k_wmi_event_teardown_complete(struct ath12k_base *ab, + struct sk_buff *skb) +{ + const struct wmi_mlo_teardown_complete_event *ev; + const void **tb; + int ret; + + tb = ath12k_wmi_tlv_parse_alloc(ab, skb, GFP_ATOMIC); + if (IS_ERR(tb)) { + ret = PTR_ERR(tb); + ath12k_warn(ab, "failed to parse teardown complete event tlv: %d\n", ret); + return; + } + + ev = tb[WMI_TAG_MLO_TEARDOWN_COMPLETE]; + if (!ev) { + ath12k_warn(ab, "failed to fetch teardown complete event\n"); + kfree(tb); + return; + } + + kfree(tb); +} + static void ath12k_wmi_op_rx(struct ath12k_base *ab, struct sk_buff *skb) { struct wmi_cmd_hdr *cmd_hdr; @@ -7250,13 +7521,6 @@ static void ath12k_wmi_op_rx(struct ath12k_base *ab, struct sk_buff *skb) case WMI_P2P_NOA_EVENTID: ath12k_wmi_p2p_noa_event(ab, skb); break; - /* add Unsupported events here */ - case WMI_TBTTOFFSET_EXT_UPDATE_EVENTID: - case WMI_PEER_OPER_MODE_CHANGE_EVENTID: - case WMI_PDEV_DMA_RING_CFG_RSP_EVENTID: - ath12k_dbg(ab, ATH12K_DBG_WMI, - "ignoring unsupported event 0x%x\n", id); - break; case WMI_PDEV_DFS_RADAR_DETECTION_EVENTID: ath12k_wmi_pdev_dfs_radar_detected_event(ab, skb); break; @@ -7272,6 +7536,25 @@ static void ath12k_wmi_op_rx(struct ath12k_base *ab, struct sk_buff *skb) case WMI_GTK_OFFLOAD_STATUS_EVENTID: ath12k_wmi_gtk_offload_status_event(ab, skb); break; + case WMI_MLO_SETUP_COMPLETE_EVENTID: + ath12k_wmi_event_mlo_setup_complete(ab, skb); + break; + case WMI_MLO_TEARDOWN_COMPLETE_EVENTID: + ath12k_wmi_event_teardown_complete(ab, skb); + break; + /* add Unsupported events (rare) here */ + case WMI_TBTTOFFSET_EXT_UPDATE_EVENTID: + case WMI_PEER_OPER_MODE_CHANGE_EVENTID: + case WMI_PDEV_DMA_RING_CFG_RSP_EVENTID: + ath12k_dbg(ab, ATH12K_DBG_WMI, + "ignoring unsupported event 0x%x\n", id); + break; + /* add Unsupported events (frequent) here */ + case WMI_PDEV_GET_HALPHY_CAL_STATUS_EVENTID: + case WMI_MGMT_RX_FW_CONSUMED_EVENTID: + case WMI_OBSS_COLOR_COLLISION_DETECTION_EVENTID: + /* debug might flood hence silently ignore (no-op) */ + break; /* TODO: Add remaining events */ default: ath12k_dbg(ab, ATH12K_DBG_WMI, "Unknown eventid: 0x%x\n", id); @@ -8088,3 +8371,104 @@ int ath12k_wmi_sta_keepalive(struct ath12k *ar, return ath12k_wmi_cmd_send(wmi, skb, WMI_STA_KEEPALIVE_CMDID); } + +int ath12k_wmi_mlo_setup(struct ath12k *ar, struct wmi_mlo_setup_arg *mlo_params) +{ + struct wmi_mlo_setup_cmd *cmd; + struct ath12k_wmi_pdev *wmi = ar->wmi; + u32 *partner_links, num_links; + int i, ret, buf_len, arg_len; + struct sk_buff *skb; + struct wmi_tlv *tlv; + void *ptr; + + num_links = mlo_params->num_partner_links; + arg_len = num_links * sizeof(u32); + buf_len = sizeof(*cmd) + TLV_HDR_SIZE + arg_len; + + skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, buf_len); + if (!skb) + return -ENOMEM; + + cmd = (struct wmi_mlo_setup_cmd *)skb->data; + cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_SETUP_CMD, + sizeof(*cmd)); + cmd->mld_group_id = mlo_params->group_id; + cmd->pdev_id = cpu_to_le32(ar->pdev->pdev_id); + ptr = skb->data + sizeof(*cmd); + + tlv = ptr; + tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, arg_len); + ptr += TLV_HDR_SIZE; + + partner_links = ptr; + for (i = 0; i < num_links; i++) + partner_links[i] = mlo_params->partner_link_id[i]; + + ret = ath12k_wmi_cmd_send(wmi, skb, WMI_MLO_SETUP_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to submit WMI_MLO_SETUP_CMDID command: %d\n", + ret); + dev_kfree_skb(skb); + return ret; + } + + return 0; +} + +int ath12k_wmi_mlo_ready(struct ath12k *ar) +{ + struct wmi_mlo_ready_cmd *cmd; + struct ath12k_wmi_pdev *wmi = ar->wmi; + struct sk_buff *skb; + int ret, len; + + len = sizeof(*cmd); + skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len); + if (!skb) + return -ENOMEM; + + cmd = (struct wmi_mlo_ready_cmd *)skb->data; + cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_READY_CMD, + sizeof(*cmd)); + cmd->pdev_id = cpu_to_le32(ar->pdev->pdev_id); + + ret = ath12k_wmi_cmd_send(wmi, skb, WMI_MLO_READY_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to submit WMI_MLO_READY_CMDID command: %d\n", + ret); + dev_kfree_skb(skb); + return ret; + } + + return 0; +} + +int ath12k_wmi_mlo_teardown(struct ath12k *ar) +{ + struct wmi_mlo_teardown_cmd *cmd; + struct ath12k_wmi_pdev *wmi = ar->wmi; + struct sk_buff *skb; + int ret, len; + + len = sizeof(*cmd); + skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len); + if (!skb) + return -ENOMEM; + + cmd = (struct wmi_mlo_teardown_cmd *)skb->data; + cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_TEARDOWN_CMD, + sizeof(*cmd)); + cmd->pdev_id = cpu_to_le32(ar->pdev->pdev_id); + cmd->reason_code = WMI_MLO_TEARDOWN_SSR_REASON; + + ret = ath12k_wmi_cmd_send(wmi, skb, WMI_MLO_TEARDOWN_CMDID); + if (ret) { + ath12k_warn(ar->ab, "failed to submit WMI MLO teardown command: %d\n", + ret); + dev_kfree_skb(skb); + return ret; + } + + return 0; +} diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h index 6f55dbdf629d..b6a197389277 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.h +++ b/drivers/net/wireless/ath/ath12k/wmi.h @@ -285,6 +285,7 @@ enum wmi_cmd_group { WMI_GRP_TWT = 0x3e, WMI_GRP_MOTION_DET = 0x3f, WMI_GRP_SPATIAL_REUSE = 0x40, + WMI_GRP_MLO = 0x48, }; #define WMI_CMD_GRP(grp_id) (((grp_id) << 12) | 0x1) @@ -665,6 +666,10 @@ enum wmi_tlv_cmd_id { WMI_PDEV_OBSS_PD_SPATIAL_REUSE_CMDID = WMI_TLV_CMD(WMI_GRP_SPATIAL_REUSE), WMI_PDEV_OBSS_PD_SPATIAL_REUSE_SET_DEF_OBSS_THRESH_CMDID, + WMI_MLO_LINK_SET_ACTIVE_CMDID = WMI_TLV_CMD(WMI_GRP_MLO), + WMI_MLO_SETUP_CMDID, + WMI_MLO_READY_CMDID, + WMI_MLO_TEARDOWN_CMDID, }; enum wmi_tlv_event_id { @@ -706,6 +711,8 @@ enum wmi_tlv_event_id { WMI_PDEV_RAP_INFO_EVENTID, WMI_CHAN_RF_CHARACTERIZATION_INFO_EVENTID, WMI_SERVICE_READY_EXT2_EVENTID, + WMI_PDEV_GET_HALPHY_CAL_STATUS_EVENTID = + WMI_SERVICE_READY_EXT2_EVENTID + 4, WMI_VDEV_START_RESP_EVENTID = WMI_TLV_CMD(WMI_GRP_VDEV), WMI_VDEV_STOPPED_EVENTID, WMI_VDEV_INSTALL_KEY_COMPLETE_EVENTID, @@ -747,6 +754,7 @@ enum wmi_tlv_event_id { WMI_TBTTOFFSET_EXT_UPDATE_EVENTID, WMI_OFFCHAN_DATA_TX_COMPLETION_EVENTID, WMI_HOST_FILS_DISCOVERY_EVENTID, + WMI_MGMT_RX_FW_CONSUMED_EVENTID = WMI_HOST_FILS_DISCOVERY_EVENTID + 3, WMI_TX_DELBA_COMPLETE_EVENTID = WMI_TLV_CMD(WMI_GRP_BA_NEG), WMI_TX_ADDBA_COMPLETE_EVENTID, WMI_BA_RSP_SSN_EVENTID, @@ -845,6 +853,8 @@ enum wmi_tlv_event_id { WMI_MDNS_STATS_EVENTID = WMI_TLV_CMD(WMI_GRP_MDNS_OFL), WMI_SAP_OFL_ADD_STA_EVENTID = WMI_TLV_CMD(WMI_GRP_SAP_OFL), WMI_SAP_OFL_DEL_STA_EVENTID, + WMI_OBSS_COLOR_COLLISION_DETECTION_EVENTID = + WMI_EVT_GRP_START_ID(WMI_GRP_OBSS_OFL), WMI_OCB_SET_CONFIG_RESP_EVENTID = WMI_TLV_CMD(WMI_GRP_OCB), WMI_OCB_GET_TSF_TIMER_RESP_EVENTID, WMI_DCC_GET_STATS_RESP_EVENTID, @@ -874,6 +884,9 @@ enum wmi_tlv_event_id { WMI_TWT_DEL_DIALOG_EVENTID, WMI_TWT_PAUSE_DIALOG_EVENTID, WMI_TWT_RESUME_DIALOG_EVENTID, + WMI_MLO_LINK_SET_ACTIVE_RESP_EVENTID = WMI_EVT_GRP_START_ID(WMI_GRP_MLO), + WMI_MLO_SETUP_COMPLETE_EVENTID, + WMI_MLO_TEARDOWN_COMPLETE_EVENTID, }; enum wmi_tlv_pdev_param { @@ -1929,6 +1942,19 @@ enum wmi_tlv_tag { WMI_TAG_REGULATORY_RULE_EXT_STRUCT = 0x3A9, WMI_TAG_REG_CHAN_LIST_CC_EXT_EVENT, WMI_TAG_EHT_RATE_SET = 0x3C4, + WMI_TAG_DCS_AWGN_INT_TYPE = 0x3C5, + WMI_TAG_MLO_TX_SEND_PARAMS, + WMI_TAG_MLO_PARTNER_LINK_PARAMS, + WMI_TAG_MLO_PARTNER_LINK_PARAMS_PEER_ASSOC, + WMI_TAG_MLO_SETUP_CMD = 0x3C9, + WMI_TAG_MLO_SETUP_COMPLETE_EVENT, + WMI_TAG_MLO_READY_CMD, + WMI_TAG_MLO_TEARDOWN_CMD, + WMI_TAG_MLO_TEARDOWN_COMPLETE, + WMI_TAG_MLO_PEER_ASSOC_PARAMS = 0x3D0, + WMI_TAG_MLO_PEER_CREATE_PARAMS = 0x3D5, + WMI_TAG_MLO_VDEV_START_PARAMS = 0x3D6, + WMI_TAG_MLO_VDEV_CREATE_PARAMS = 0x3D7, WMI_TAG_PDEV_SET_BIOS_SAR_TABLE_CMD = 0x3D8, WMI_TAG_PDEV_SET_BIOS_GEO_TABLE_CMD = 0x3D9, WMI_TAG_PDEV_SET_BIOS_INTERFACE_CMD = 0x3FB, @@ -2690,6 +2716,8 @@ struct ath12k_wmi_caps_ext_params { __le32 eht_cap_info_internal; __le32 eht_supp_mcs_ext_2ghz[WMI_MAX_EHT_SUPP_MCS_2G_SIZE]; __le32 eht_supp_mcs_ext_5ghz[WMI_MAX_EHT_SUPP_MCS_5G_SIZE]; + __le32 eml_capability; + __le32 mld_capability; } __packed; /* 2 word representation of MAC addr */ @@ -2740,6 +2768,7 @@ struct ath12k_wmi_vdev_create_arg { u8 if_stats_id; u32 mbssid_flags; u32 mbssid_tx_vdev_id; + u8 mld_addr[ETH_ALEN]; }; #define ATH12K_MAX_VDEV_STATS_ID 0x30 @@ -2766,6 +2795,33 @@ struct ath12k_wmi_vdev_txrx_streams_params { __le32 supported_rx_streams; } __packed; +struct wmi_vdev_create_mlo_params { + __le32 tlv_header; + struct ath12k_wmi_mac_addr_params mld_macaddr; +} __packed; + +#define ATH12K_WMI_FLAG_MLO_ENABLED BIT(0) +#define ATH12K_WMI_FLAG_MLO_ASSOC_LINK BIT(1) +#define ATH12K_WMI_FLAG_MLO_PRIMARY_UMAC BIT(2) +#define ATH12K_WMI_FLAG_MLO_LOGICAL_LINK_IDX_VALID BIT(3) +#define ATH12K_WMI_FLAG_MLO_PEER_ID_VALID BIT(4) +#define ATH12K_WMI_FLAG_MLO_MCAST_VDEV BIT(5) +#define ATH12K_WMI_FLAG_MLO_EMLSR_SUPPORT BIT(6) +#define ATH12K_WMI_FLAG_MLO_FORCED_INACTIVE BIT(7) +#define ATH12K_WMI_FLAG_MLO_LINK_ADD BIT(8) + +struct wmi_vdev_start_mlo_params { + __le32 tlv_header; + __le32 flags; +} __packed; + +struct wmi_partner_link_info { + __le32 tlv_header; + __le32 vdev_id; + __le32 hw_link_id; + struct ath12k_wmi_mac_addr_params vdev_addr; +} __packed; + struct wmi_vdev_delete_cmd { __le32 tlv_header; __le32 vdev_id; @@ -2909,6 +2965,27 @@ enum wmi_phy_mode { MODE_MAX = 33, }; +#define ATH12K_WMI_MLO_MAX_LINKS 4 + +struct wmi_ml_partner_info { + u32 vdev_id; + u32 hw_link_id; + u8 addr[ETH_ALEN]; + bool assoc_link; + bool primary_umac; + bool logical_link_idx_valid; + u32 logical_link_idx; +}; + +struct wmi_ml_arg { + bool enabled; + bool assoc_link; + bool mcast_link; + bool link_add; + u8 num_partner_links; + struct wmi_ml_partner_info partner_info[ATH12K_WMI_MLO_MAX_LINKS]; +}; + struct wmi_vdev_start_req_arg { u32 vdev_id; u32 freq; @@ -2946,12 +3023,19 @@ struct wmi_vdev_start_req_arg { u32 mbssid_flags; u32 mbssid_tx_vdev_id; u32 punct_bitmap; + struct wmi_ml_arg ml; }; struct ath12k_wmi_peer_create_arg { const u8 *peer_addr; u32 peer_type; u32 vdev_id; + bool ml_enabled; +}; + +struct wmi_peer_create_mlo_params { + __le32 tlv_header; + __le32 flags; }; struct ath12k_wmi_pdev_set_regdomain_arg { @@ -3618,6 +3702,24 @@ struct wmi_vdev_install_key_arg { #define WMI_HECAP_TXRX_MCS_NSS_IDX_160 1 #define WMI_HECAP_TXRX_MCS_NSS_IDX_80_80 2 +#define ATH12K_WMI_MLO_MAX_PARTNER_LINKS \ + (ATH12K_WMI_MLO_MAX_LINKS + ATH12K_MAX_NUM_BRIDGE_LINKS - 1) + +struct peer_assoc_mlo_params { + bool enabled; + bool assoc_link; + bool primary_umac; + bool peer_id_valid; + bool logical_link_idx_valid; + bool bridge_peer; + u8 mld_addr[ETH_ALEN]; + u32 logical_link_idx; + u32 ml_peer_id; + u32 ieee_link_id; + u8 num_partner_links; + struct wmi_ml_partner_info partner_info[ATH12K_WMI_MLO_MAX_LINKS]; +}; + struct wmi_rate_set_arg { u32 num_rates; u8 rates[WMI_MAX_SUPPORTED_RATES]; @@ -3692,8 +3794,36 @@ struct ath12k_wmi_peer_assoc_arg { u32 peer_eht_tx_mcs_set[WMI_MAX_EHTCAP_RATE_SET]; struct ath12k_wmi_ppe_threshold_arg peer_eht_ppet; u32 punct_bitmap; + bool is_assoc; + struct peer_assoc_mlo_params ml; }; +#define ATH12K_WMI_FLAG_MLO_ENABLED BIT(0) +#define ATH12K_WMI_FLAG_MLO_ASSOC_LINK BIT(1) +#define ATH12K_WMI_FLAG_MLO_PRIMARY_UMAC BIT(2) +#define ATH12K_WMI_FLAG_MLO_LINK_ID_VALID BIT(3) +#define ATH12K_WMI_FLAG_MLO_PEER_ID_VALID BIT(4) + +struct wmi_peer_assoc_mlo_partner_info_params { + __le32 tlv_header; + __le32 vdev_id; + __le32 hw_link_id; + __le32 flags; + __le32 logical_link_idx; +} __packed; + +struct wmi_peer_assoc_mlo_params { + __le32 tlv_header; + __le32 flags; + struct ath12k_wmi_mac_addr_params mld_addr; + __le32 logical_link_idx; + __le32 ml_peer_id; + __le32 ieee_link_id; + __le32 emlsr_trans_timeout_us; + __le32 emlsr_trans_delay_us; + __le32 emlsr_padding_delay_us; +} __packed; + struct wmi_peer_assoc_complete_cmd { __le32 tlv_header; struct ath12k_wmi_mac_addr_params peer_macaddr; @@ -4815,6 +4945,7 @@ struct wmi_probe_tmpl_cmd { #define MAX_RADIOS 2 +#define WMI_MLO_CMD_TIMEOUT_HZ (5 * HZ) #define WMI_SERVICE_READY_TIMEOUT_HZ (5 * HZ) #define WMI_SEND_TIMEOUT_HZ (3 * HZ) @@ -4911,6 +5042,43 @@ struct wmi_twt_disable_event { __le32 status; } __packed; +struct wmi_mlo_setup_cmd { + __le32 tlv_header; + __le32 mld_group_id; + __le32 pdev_id; +} __packed; + +struct wmi_mlo_setup_arg { + __le32 group_id; + u8 num_partner_links; + u8 *partner_link_id; +}; + +struct wmi_mlo_ready_cmd { + __le32 tlv_header; + __le32 pdev_id; +} __packed; + +enum wmi_mlo_tear_down_reason_code_type { + WMI_MLO_TEARDOWN_SSR_REASON, +}; + +struct wmi_mlo_teardown_cmd { + __le32 tlv_header; + __le32 pdev_id; + __le32 reason_code; +} __packed; + +struct wmi_mlo_setup_complete_event { + __le32 pdev_id; + __le32 status; +} __packed; + +struct wmi_mlo_teardown_complete_event { + __le32 pdev_id; + __le32 status; +} __packed; + /* WOW structures */ enum wmi_wow_wakeup_event { WOW_BMISS_EVENT = 0, @@ -5636,5 +5804,8 @@ int ath12k_wmi_gtk_rekey_getinfo(struct ath12k *ar, struct ath12k_link_vif *arvif); int ath12k_wmi_sta_keepalive(struct ath12k *ar, const struct wmi_sta_keepalive_arg *arg); +int ath12k_wmi_mlo_setup(struct ath12k *ar, struct wmi_mlo_setup_arg *mlo_params); +int ath12k_wmi_mlo_ready(struct ath12k *ar); +int ath12k_wmi_mlo_teardown(struct ath12k *ar); #endif diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index 61b2e3f15f0e..72ce321f2a77 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -1441,6 +1441,7 @@ static int ath6kl_cfg80211_set_txpower(struct wiphy *wiphy, static int ath6kl_cfg80211_get_txpower(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id, int *dbm) { struct ath6kl *ar = (struct ath6kl *)wiphy_priv(wiphy); diff --git a/drivers/net/wireless/ath/ath9k/antenna.c b/drivers/net/wireless/ath/ath9k/antenna.c index acc84e6711b0..e5e274bc9e68 100644 --- a/drivers/net/wireless/ath/ath9k/antenna.c +++ b/drivers/net/wireless/ath/ath9k/antenna.c @@ -193,7 +193,7 @@ static void ath_lnaconf_alt_good_scan(struct ath_ant_comb *antcomb, static void ath_ant_set_alt_ratio(struct ath_ant_comb *antcomb, struct ath_hw_antcomb_conf *conf) { - /* set alt to the conf with maximun ratio */ + /* set alt to the conf with maximum ratio */ if (antcomb->first_ratio && antcomb->second_ratio) { if (antcomb->rssi_second > antcomb->rssi_third) { /* first alt*/ diff --git a/drivers/net/wireless/ath/ath9k/ar9002_hw.c b/drivers/net/wireless/ath/ath9k/ar9002_hw.c index d08ea0b28530..b26224480041 100644 --- a/drivers/net/wireless/ath/ath9k/ar9002_hw.c +++ b/drivers/net/wireless/ath/ath9k/ar9002_hw.c @@ -395,7 +395,7 @@ static void ar9002_hw_init_hang_checks(struct ath_hw *ah) ah->config.hw_hang_checks |= HW_MAC_HANG; } -/* Sets up the AR5008/AR9001/AR9002 hardware familiy callbacks */ +/* Sets up the AR5008/AR9001/AR9002 hardware family callbacks */ int ar9002_hw_attach_ops(struct ath_hw *ah) { struct ath_hw_private_ops *priv_ops = ath9k_hw_private_ops(ah); diff --git a/drivers/net/wireless/ath/ath9k/ar9003_hw.c b/drivers/net/wireless/ath/ath9k/ar9003_hw.c index e9bd13eeee92..6595eca74997 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_hw.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_hw.c @@ -1170,7 +1170,7 @@ exit: return false; } -/* Sets up the AR9003 hardware familiy callbacks */ +/* Sets up the AR9003 hardware family callbacks */ void ar9003_hw_attach_ops(struct ath_hw *ah) { struct ath_hw_private_ops *priv_ops = ath9k_hw_private_ops(ah); diff --git a/drivers/net/wireless/ath/ath9k/ar9003_mci.c b/drivers/net/wireless/ath/ath9k/ar9003_mci.c index 2b9c07961cd7..3f0543e55d9b 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_mci.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_mci.c @@ -637,7 +637,7 @@ static u32 ar9003_mci_wait_for_gpm(struct ath_hw *ah, u8 gpm_type, * same time. Since BT's calibration doesn't happen * that often, we'll let BT completes calibration then * we continue to wait for cal_grant from BT. - * Orginal: Wait BT_CAL_GRANT. + * Original: Wait BT_CAL_GRANT. * New: Receive BT_CAL_REQ -> send WLAN_CAL_GRANT->wait * BT_CAL_DONE -> Wait BT_CAL_GRANT. */ @@ -747,7 +747,7 @@ int ar9003_mci_end_reset(struct ath_hw *ah, struct ath9k_channel *chan, * BT is sleeping. Check if BT wakes up during * WLAN calibration. If BT wakes up during * WLAN calibration, need to go through all - * message exchanges again and recal. + * message exchanges again and recalibrate. */ REG_WRITE(ah, AR_MCI_INTERRUPT_RX_MSG_RAW, (AR_MCI_INTERRUPT_RX_MSG_REMOTE_RESET | diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.h b/drivers/net/wireless/ath/ath9k/ar9003_phy.h index ad72a30b67c3..e13873fb8e2f 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_phy.h +++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.h @@ -246,7 +246,7 @@ /* - * MRC Feild Definitions + * MRC Field Definitions */ #define AR_PHY_SGI_DSC_MAN 0x0007FFF0 #define AR_PHY_SGI_DSC_MAN_S 4 diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h index 29ca65a732a6..a728cc0387df 100644 --- a/drivers/net/wireless/ath/ath9k/ath9k.h +++ b/drivers/net/wireless/ath/ath9k/ath9k.h @@ -338,7 +338,7 @@ struct ath_chanctx { struct ath_beacon_config beacon; struct ath9k_hw_cal_data caldata; - struct timespec64 tsf_ts; + ktime_t tsf_ts; u64 tsf_val; u32 last_beacon; @@ -592,8 +592,8 @@ void ath_txq_schedule_all(struct ath_softc *sc); int ath_tx_init(struct ath_softc *sc, int nbufs); int ath_txq_update(struct ath_softc *sc, int qnum, struct ath9k_tx_queue_info *q); -u32 ath_pkt_duration(struct ath_softc *sc, u8 rix, int pktlen, - int width, int half_gi, bool shortPreamble); +u32 ath_pkt_duration(u8 rix, int pktlen, int width, + int half_gi, bool shortPreamble); void ath_update_max_aggr_framelen(struct ath_softc *sc, int queue, int txop); void ath_assign_seq(struct ath_common *common, struct sk_buff *skb); int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb, @@ -1011,13 +1011,15 @@ struct ath_softc { struct ath_offchannel offchannel; struct ath_chanctx *next_chan; struct completion go_beacon; - struct timespec64 last_event_time; + ktime_t last_event_time; #endif unsigned long driver_data; u8 gtt_cnt; u32 intrstatus; + u32 rx_active_check_time; + u32 rx_active_count; u16 ps_flags; /* PS_* */ bool ps_enabled; bool ps_idle; diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c index b399a7926ef5..4a27e3753c03 100644 --- a/drivers/net/wireless/ath/ath9k/beacon.c +++ b/drivers/net/wireless/ath/ath9k/beacon.c @@ -293,7 +293,7 @@ void ath9k_beacon_ensure_primary_slot(struct ath_softc *sc) /* Modify TSF as required and update the HW. */ avp->chanctx->tsf_val += tsfadjust; if (sc->cur_chan == avp->chanctx) { - offset = ath9k_hw_get_tsf_offset(&avp->chanctx->tsf_ts, NULL); + offset = ath9k_hw_get_tsf_offset(avp->chanctx->tsf_ts, 0); ath9k_hw_settsf64(sc->sc_ah, avp->chanctx->tsf_val + offset); } diff --git a/drivers/net/wireless/ath/ath9k/calib.c b/drivers/net/wireless/ath/ath9k/calib.c index 4b331c85509c..b4ab85bd7895 100644 --- a/drivers/net/wireless/ath/ath9k/calib.c +++ b/drivers/net/wireless/ath/ath9k/calib.c @@ -16,29 +16,25 @@ #include "hw.h" #include "hw-ops.h" +#include #include /* Common calibration code */ +static int rcmp_i16(const void *x, const void *y) +{ + /* Sort in reverse order. */ + return *(int16_t *)y - *(int16_t *)x; +} static int16_t ath9k_hw_get_nf_hist_mid(int16_t *nfCalBuffer) { - int16_t nfval; - int16_t sort[ATH9K_NF_CAL_HIST_MAX]; - int i, j; + int16_t nfcal[ATH9K_NF_CAL_HIST_MAX]; - for (i = 0; i < ATH9K_NF_CAL_HIST_MAX; i++) - sort[i] = nfCalBuffer[i]; + memcpy(nfcal, nfCalBuffer, sizeof(nfcal)); + sort(nfcal, ATH9K_NF_CAL_HIST_MAX, sizeof(int16_t), rcmp_i16, NULL); - for (i = 0; i < ATH9K_NF_CAL_HIST_MAX - 1; i++) { - for (j = 1; j < ATH9K_NF_CAL_HIST_MAX - i; j++) { - if (sort[j] > sort[j - 1]) - swap(sort[j], sort[j - 1]); - } - } - nfval = sort[(ATH9K_NF_CAL_HIST_MAX - 1) >> 1]; - - return nfval; + return nfcal[(ATH9K_NF_CAL_HIST_MAX - 1) >> 1]; } static struct ath_nf_limits *ath9k_hw_get_nf_limits(struct ath_hw *ah, diff --git a/drivers/net/wireless/ath/ath9k/channel.c b/drivers/net/wireless/ath/ath9k/channel.c index 571062f2e82a..bae24e3d3168 100644 --- a/drivers/net/wireless/ath/ath9k/channel.c +++ b/drivers/net/wireless/ath/ath9k/channel.c @@ -17,7 +17,7 @@ #include "ath9k.h" /* Set/change channels. If the channel is really being changed, it's done - * by reseting the chip. To accomplish this we must first cleanup any pending + * by resetting the chip. To accomplish this we must first cleanup any pending * DMA, then restart stuff. */ static int ath_set_channel(struct ath_softc *sc) @@ -232,16 +232,11 @@ static const char *chanctx_state_string(enum ath_chanctx_state state) static u32 chanctx_event_delta(struct ath_softc *sc) { - u64 ms; - struct timespec64 ts, *old; + ktime_t ts = ktime_get_raw(); + s64 ms = ktime_ms_delta(ts, sc->last_event_time); - ktime_get_raw_ts64(&ts); - old = &sc->last_event_time; - ms = ts.tv_sec * 1000 + ts.tv_nsec / 1000000; - ms -= old->tv_sec * 1000 + old->tv_nsec / 1000000; sc->last_event_time = ts; - - return (u32)ms; + return ms; } void ath_chanctx_check_active(struct ath_softc *sc, struct ath_chanctx *ctx) @@ -334,8 +329,8 @@ ath_chanctx_get_next(struct ath_softc *sc, struct ath_chanctx *ctx) static void ath_chanctx_adjust_tbtt_delta(struct ath_softc *sc) { struct ath_chanctx *prev, *cur; - struct timespec64 ts; u32 cur_tsf, prev_tsf, beacon_int; + ktime_t ts; s32 offset; beacon_int = TU_TO_USEC(sc->cur_chan->beacon.beacon_interval); @@ -346,12 +341,12 @@ static void ath_chanctx_adjust_tbtt_delta(struct ath_softc *sc) if (!prev->switch_after_beacon) return; - ktime_get_raw_ts64(&ts); + ts = ktime_get_raw(); cur_tsf = (u32) cur->tsf_val + - ath9k_hw_get_tsf_offset(&cur->tsf_ts, &ts); + ath9k_hw_get_tsf_offset(cur->tsf_ts, ts); prev_tsf = prev->last_beacon - (u32) prev->tsf_val + cur_tsf; - prev_tsf -= ath9k_hw_get_tsf_offset(&prev->tsf_ts, &ts); + prev_tsf -= ath9k_hw_get_tsf_offset(prev->tsf_ts, ts); /* Adjust the TSF time of the AP chanctx to keep its beacons * at half beacon interval offset relative to the STA chanctx. @@ -691,7 +686,7 @@ void ath_chanctx_event(struct ath_softc *sc, struct ieee80211_vif *vif, */ tsf_time = sc->sched.switch_start_time; tsf_time -= (u32) sc->cur_chan->tsf_val + - ath9k_hw_get_tsf_offset(&sc->cur_chan->tsf_ts, NULL); + ath9k_hw_get_tsf_offset(sc->cur_chan->tsf_ts, 0); tsf_time += ath9k_hw_gettsf32(ah); sc->sched.beacon_adjust = false; @@ -1230,10 +1225,10 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force) { struct ath_common *common = ath9k_hw_common(sc->sc_ah); struct ath_chanctx *old_ctx; - struct timespec64 ts; bool measure_time = false; bool send_ps = false; bool queues_stopped = false; + ktime_t ts; spin_lock_bh(&sc->chan_lock); if (!sc->next_chan) { @@ -1260,7 +1255,7 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force) spin_unlock_bh(&sc->chan_lock); if (sc->next_chan == &sc->offchannel.chan) { - ktime_get_raw_ts64(&ts); + ts = ktime_get_raw(); measure_time = true; } @@ -1277,7 +1272,7 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force) spin_lock_bh(&sc->chan_lock); if (sc->cur_chan != &sc->offchannel.chan) { - ktime_get_raw_ts64(&sc->cur_chan->tsf_ts); + sc->cur_chan->tsf_ts = ktime_get_raw(); sc->cur_chan->tsf_val = ath9k_hw_gettsf64(sc->sc_ah); } } @@ -1303,7 +1298,7 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force) ath_set_channel(sc); if (measure_time) sc->sched.channel_switch_time = - ath9k_hw_get_tsf_offset(&ts, NULL); + ath9k_hw_get_tsf_offset(ts, 0); /* * A reset will ensure that all queues are woken up, * so there is no need to awaken them again. diff --git a/drivers/net/wireless/ath/ath9k/common-spectral.c b/drivers/net/wireless/ath/ath9k/common-spectral.c index 4b27445a5fb8..628eeec4b82f 100644 --- a/drivers/net/wireless/ath/ath9k/common-spectral.c +++ b/drivers/net/wireless/ath/ath9k/common-spectral.c @@ -734,7 +734,7 @@ void ath9k_cmn_spectral_scan_trigger(struct ath_common *common, ATH9K_RX_FILTER_PHYRADAR | ATH9K_RX_FILTER_PHYERR); - /* TODO: usually this should not be neccesary, but for some reason + /* TODO: usually this should not be necessary, but for some reason * (or in some mode?) the trigger must be called after the * configuration, otherwise the register will have its values reset * (on my ar9220 to value 0x01002310) diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c index eff894958a73..74a0134075cf 100644 --- a/drivers/net/wireless/ath/ath9k/debug.c +++ b/drivers/net/wireless/ath/ath9k/debug.c @@ -750,6 +750,7 @@ static int read_file_reset(struct seq_file *file, void *data) [RESET_TYPE_CALIBRATION] = "Calibration error", [RESET_TX_DMA_ERROR] = "Tx DMA stop error", [RESET_RX_DMA_ERROR] = "Rx DMA stop error", + [RESET_TYPE_RX_INACTIVE] = "Rx path inactive", }; int i; diff --git a/drivers/net/wireless/ath/ath9k/debug.h b/drivers/net/wireless/ath/ath9k/debug.h index 389459c04d14..cb3e75969875 100644 --- a/drivers/net/wireless/ath/ath9k/debug.h +++ b/drivers/net/wireless/ath/ath9k/debug.h @@ -53,6 +53,7 @@ enum ath_reset_type { RESET_TYPE_CALIBRATION, RESET_TX_DMA_ERROR, RESET_RX_DMA_ERROR, + RESET_TYPE_RX_INACTIVE, __RESET_TYPE_MAX }; diff --git a/drivers/net/wireless/ath/ath9k/dfs.c b/drivers/net/wireless/ath/ath9k/dfs.c index 3689e12db9f7..2fb73a5e1d51 100644 --- a/drivers/net/wireless/ath/ath9k/dfs.c +++ b/drivers/net/wireless/ath/ath9k/dfs.c @@ -79,7 +79,7 @@ static int ath9k_get_max_index_ht40(struct ath9k_dfs_fft_40 *fft, const int DFS_UPPER_BIN_OFFSET = 64; /* if detected radar on both channels, select the significant one */ if (is_ctl && is_ext) { - /* first check wether channels have 'strong' bins */ + /* first check whether channels have 'strong' bins */ is_ctl = fft_bitmap_weight(fft->lower_bins) != 0; is_ext = fft_bitmap_weight(fft->upper_bins) != 0; diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 7265766cddbd..fe9abe8cd268 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -1198,7 +1198,7 @@ static int ath9k_hif_request_firmware(struct hif_device_usb *hif_dev, filename = FIRMWARE_AR9271; /* expected fw locations: - * - htc_9271.fw (stable version 1.3, depricated) + * - htc_9271.fw (stable version 1.3, deprecated) */ snprintf(hif_dev->fw_name, sizeof(hif_dev->fw_name), "%s", filename); diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index e2bef099adb3..f9a774bd0e13 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -1847,20 +1847,11 @@ fail: return -EINVAL; } -u32 ath9k_hw_get_tsf_offset(struct timespec64 *last, struct timespec64 *cur) +u32 ath9k_hw_get_tsf_offset(ktime_t last, ktime_t cur) { - struct timespec64 ts; - s64 usec; - - if (!cur) { - ktime_get_raw_ts64(&ts); - cur = &ts; - } - - usec = cur->tv_sec * 1000000ULL + cur->tv_nsec / 1000; - usec -= last->tv_sec * 1000000ULL + last->tv_nsec / 1000; - - return (u32) usec; + if (cur == 0) + cur = ktime_get_raw(); + return ktime_us_delta(cur, last); } EXPORT_SYMBOL(ath9k_hw_get_tsf_offset); @@ -1871,7 +1862,7 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan, u32 saveLedState; u32 saveDefAntenna; u32 macStaId1; - struct timespec64 tsf_ts; + ktime_t tsf_ts; u32 tsf_offset; u64 tsf = 0; int r; @@ -1917,7 +1908,7 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan, macStaId1 = REG_READ(ah, AR_STA_ID1) & AR_STA_ID1_BASE_RATE_11B; /* Save TSF before chip reset, a cold reset clears it */ - ktime_get_raw_ts64(&tsf_ts); + tsf_ts = ktime_get_raw(); tsf = ath9k_hw_gettsf64(ah); saveLedState = REG_READ(ah, AR_CFG_LED) & @@ -1951,7 +1942,7 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan, } /* Restore TSF */ - tsf_offset = ath9k_hw_get_tsf_offset(&tsf_ts, NULL); + tsf_offset = ath9k_hw_get_tsf_offset(tsf_ts, 0); ath9k_hw_settsf64(ah, tsf + tsf_offset); if (AR_SREV_9280_20_OR_LATER(ah)) @@ -1975,7 +1966,7 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan, * value after the initvals have been applied. */ if (AR_SREV_9100(ah) && (ath9k_hw_gettsf64(ah) < tsf)) { - tsf_offset = ath9k_hw_get_tsf_offset(&tsf_ts, NULL); + tsf_offset = ath9k_hw_get_tsf_offset(tsf_ts, 0); ath9k_hw_settsf64(ah, tsf + tsf_offset); } @@ -2149,7 +2140,7 @@ static void ath9k_set_power_network_sleep(struct ath_hw *ah) /* When chip goes into network sleep, it could be waken * up by MCI_INT interrupt caused by BT's HW messages - * (LNA_xxx, CONT_xxx) which chould be in a very fast + * (LNA_xxx, CONT_xxx) which could be in a very fast * rate (~100us). This will cause chip to leave and * re-enter network sleep mode frequently, which in * consequence will have WLAN MCI HW to generate lots of @@ -2544,7 +2535,7 @@ int ath9k_hw_fill_cap_info(struct ath_hw *ah) pCap->tx_chainmask = ah->eep_ops->get_eeprom(ah, EEP_TX_MASK); /* - * For AR9271 we will temporarilly uses the rx chainmax as read from + * For AR9271 we will temporarily use the rx chainmax as read from * the EEPROM. */ if ((ah->hw_version.devid == AR5416_DEVID_PCI) && diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index 450ab19b1d4e..eaa07d6dbde0 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -282,7 +282,7 @@ enum ath9k_hw_caps { * an exact user defined pattern or de-authentication/disassoc pattern. * @ATH9K_HW_WOW_PATTERN_MATCH_DWORD: device requires the first four * bytes of the pattern for user defined pattern, de-authentication and - * disassociation patterns for all types of possible frames recieved + * disassociation patterns for all types of possible frames received * of those types. */ @@ -1066,7 +1066,7 @@ u32 ath9k_hw_gettsf32(struct ath_hw *ah); u64 ath9k_hw_gettsf64(struct ath_hw *ah); void ath9k_hw_settsf64(struct ath_hw *ah, u64 tsf64); void ath9k_hw_reset_tsf(struct ath_hw *ah); -u32 ath9k_hw_get_tsf_offset(struct timespec64 *last, struct timespec64 *cur); +u32 ath9k_hw_get_tsf_offset(ktime_t last, ktime_t cur); void ath9k_hw_set_tsfadjust(struct ath_hw *ah, bool set); void ath9k_hw_init_global_settings(struct ath_hw *ah); u32 ar9003_get_pll_sqsum_dvc(struct ath_hw *ah); diff --git a/drivers/net/wireless/ath/ath9k/link.c b/drivers/net/wireless/ath/ath9k/link.c index d1e5767aab3c..d078a59d7d3c 100644 --- a/drivers/net/wireless/ath/ath9k/link.c +++ b/drivers/net/wireless/ath/ath9k/link.c @@ -50,7 +50,36 @@ reset: "tx hung, resetting the chip\n"); ath9k_queue_reset(sc, RESET_TYPE_TX_HANG); return false; +} +#define RX_INACTIVE_CHECK_INTERVAL (4 * MSEC_PER_SEC) + +static bool ath_hw_rx_inactive_check(struct ath_softc *sc) +{ + struct ath_common *common = ath9k_hw_common(sc->sc_ah); + u32 interval, count; + + interval = jiffies_to_msecs(jiffies - sc->rx_active_check_time); + count = sc->rx_active_count; + + if (interval < RX_INACTIVE_CHECK_INTERVAL) + return true; /* too soon to check */ + + sc->rx_active_count = 0; + sc->rx_active_check_time = jiffies; + + /* Need at least one interrupt per second, and we should only react if + * we are within a factor two of the expected interval + */ + if (interval > RX_INACTIVE_CHECK_INTERVAL * 2 || + count >= interval / MSEC_PER_SEC) + return true; + + ath_dbg(common, RESET, + "RX inactivity detected. Schedule chip reset\n"); + ath9k_queue_reset(sc, RESET_TYPE_RX_INACTIVE); + + return false; } void ath_hw_check_work(struct work_struct *work) @@ -58,8 +87,8 @@ void ath_hw_check_work(struct work_struct *work) struct ath_softc *sc = container_of(work, struct ath_softc, hw_check_work.work); - if (!ath_hw_check(sc) || - !ath_tx_complete_check(sc)) + if (!ath_hw_check(sc) || !ath_tx_complete_check(sc) || + !ath_hw_rx_inactive_check(sc)) return; ieee80211_queue_delayed_work(sc->hw, &sc->hw_check_work, diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h index f03d792732da..16203e7ecf29 100644 --- a/drivers/net/wireless/ath/ath9k/mac.h +++ b/drivers/net/wireless/ath/ath9k/mac.h @@ -251,7 +251,7 @@ struct ath_desc { * when the descriptor is specifically marked to generate * an interrupt with this flag. Descriptors should be * marked periodically to insure timely replenishing of the - * supply needed for sending frames. Defering interrupts + * supply needed for sending frames. Deferring interrupts * reduces system load and potentially allows more concurrent * work to be done but if done to aggressively can cause * senders to backup. When the hardware queue is left too diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index b92c89dad8de..a70c94564814 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -249,8 +249,7 @@ static bool ath_complete_reset(struct ath_softc *sc, bool start) if (sc->cur_chan->tsf_val) { u32 offset; - offset = ath9k_hw_get_tsf_offset(&sc->cur_chan->tsf_ts, - NULL); + offset = ath9k_hw_get_tsf_offset(sc->cur_chan->tsf_ts, 0); ath9k_hw_settsf64(ah, sc->cur_chan->tsf_val + offset); } @@ -453,6 +452,7 @@ void ath9k_tasklet(struct tasklet_struct *t) ath_rx_tasklet(sc, 0, true); ath_rx_tasklet(sc, 0, false); + sc->rx_active_count++; } if (status & ATH9K_INT_TX) { @@ -1001,7 +1001,7 @@ static bool ath9k_uses_beacons(int type) static void ath9k_vif_iter_set_beacon(struct ath9k_vif_iter_data *iter_data, struct ieee80211_vif *vif) { - /* Use the first (configured) interface, but prefering AP interfaces. */ + /* Use the first (configured) interface, but preferring AP interfaces. */ if (!iter_data->primary_beacon_vif) { iter_data->primary_beacon_vif = vif; } else { @@ -1955,7 +1955,7 @@ static u64 ath9k_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) tsf = ath9k_hw_gettsf64(sc->sc_ah); } else { tsf = sc->cur_chan->tsf_val + - ath9k_hw_get_tsf_offset(&sc->cur_chan->tsf_ts, NULL); + ath9k_hw_get_tsf_offset(sc->cur_chan->tsf_ts, 0); } tsf += le64_to_cpu(avp->tsf_adjust); ath9k_ps_restore(sc); @@ -1974,7 +1974,7 @@ static void ath9k_set_tsf(struct ieee80211_hw *hw, mutex_lock(&sc->mutex); ath9k_ps_wakeup(sc); tsf -= le64_to_cpu(avp->tsf_adjust); - ktime_get_raw_ts64(&avp->chanctx->tsf_ts); + avp->chanctx->tsf_ts = ktime_get_raw(); if (sc->cur_chan == avp->chanctx) ath9k_hw_settsf64(sc->sc_ah, tsf); avp->chanctx->tsf_val = tsf; @@ -1990,7 +1990,7 @@ static void ath9k_reset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) mutex_lock(&sc->mutex); ath9k_ps_wakeup(sc); - ktime_get_raw_ts64(&avp->chanctx->tsf_ts); + avp->chanctx->tsf_ts = ktime_get_raw(); if (sc->cur_chan == avp->chanctx) ath9k_hw_reset_tsf(sc->sc_ah); avp->chanctx->tsf_val = 0; @@ -2767,7 +2767,7 @@ void ath9k_fill_chanctx_ops(void) #endif static int ath9k_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - int *dbm) + unsigned int link_id, int *dbm) { struct ath_softc *sc = hw->priv; struct ath_vif *avp = (void *)vif->drv_priv; diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c index 0c0624a3b40d..34c74ed99b7b 100644 --- a/drivers/net/wireless/ath/ath9k/recv.c +++ b/drivers/net/wireless/ath/ath9k/recv.c @@ -1042,8 +1042,8 @@ static void ath_rx_count_airtime(struct ath_softc *sc, if (!!(rxs->encoding == RX_ENC_HT)) { /* MCS rates */ - airtime += ath_pkt_duration(sc, rxs->rate_idx, len, - is_40, is_sgi, is_sp); + airtime += ath_pkt_duration(rxs->rate_idx, len, + is_40, is_sgi, is_sp); } else { phy = IS_CCK_RATE(rs->rs_rate) ? WLAN_RC_PHY_CCK : WLAN_RC_PHY_OFDM; diff --git a/drivers/net/wireless/ath/ath9k/wow.c b/drivers/net/wireless/ath/ath9k/wow.c index 8d0b1730a9d5..ed4152cd44f0 100644 --- a/drivers/net/wireless/ath/ath9k/wow.c +++ b/drivers/net/wireless/ath/ath9k/wow.c @@ -60,7 +60,7 @@ static int ath9k_wow_add_disassoc_deauth_pattern(struct ath_softc *sc) memset(dis_deauth_mask, 0, MAX_PATTERN_SIZE); /* - * Create Dissassociate / Deauthenticate packet filter + * Create Disassociate / Deauthenticate packet filter * * 2 bytes 2 byte 6 bytes 6 bytes 6 bytes * +--------------+----------+---------+--------+--------+---- @@ -70,7 +70,7 @@ static int ath9k_wow_add_disassoc_deauth_pattern(struct ath_softc *sc) * The above is the management frame format for disassociate/ * deauthenticate pattern, from this we need to match the first byte * of 'Frame Control' and DA, SA, and BSSID fields - * (skipping 2nd byte of FC and Duration feild. + * (skipping 2nd byte of FC and Duration field. * * Disassociate pattern * -------------------- @@ -225,7 +225,7 @@ int ath9k_suspend(struct ieee80211_hw *hw, ath9k_stop_btcoex(sc); /* - * Enable wake up on recieving disassoc/deauth + * Enable wake up on receiving disassoc/deauth * frame by default. */ ret = ath9k_wow_add_disassoc_deauth_pattern(sc); diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 35aa47a9db90..db07ce6dbc08 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -67,8 +67,7 @@ static void ath_tx_txqaddbuf(struct ath_softc *sc, struct ath_txq *txq, static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, struct ath_tx_status *ts, int nframes, int nbad, int txok); -static void ath_tx_update_baw(struct ath_softc *sc, struct ath_atx_tid *tid, - struct ath_buf *bf); +static void ath_tx_update_baw(struct ath_atx_tid *tid, struct ath_buf *bf); static struct ath_buf *ath_tx_setup_buffer(struct ath_softc *sc, struct ath_txq *txq, struct ath_atx_tid *tid, @@ -208,10 +207,10 @@ static void ath_set_rates(struct ieee80211_vif *vif, struct ieee80211_sta *sta, ARRAY_SIZE(bf->rates)); } -static void ath_txq_skb_done(struct ath_softc *sc, struct ath_txq *txq, - struct sk_buff *skb) +static void ath_txq_skb_done(struct ath_softc *sc, struct sk_buff *skb) { struct ath_frame_info *fi = get_frame_info(skb); + struct ath_txq *txq; int q = fi->txq; if (q < 0) @@ -224,7 +223,7 @@ static void ath_txq_skb_done(struct ath_softc *sc, struct ath_txq *txq, } static struct ath_atx_tid * -ath_get_skb_tid(struct ath_softc *sc, struct ath_node *an, struct sk_buff *skb) +ath_get_skb_tid(struct ath_node *an, struct sk_buff *skb) { u8 tidno = skb->priority & IEEE80211_QOS_CTL_TID_MASK; return ATH_AN_2_TID(an, tidno); @@ -294,13 +293,13 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid) fi = get_frame_info(skb); bf = fi->bf; if (!bf) { - ath_txq_skb_done(sc, txq, skb); + ath_txq_skb_done(sc, skb); ieee80211_free_txskb(sc->hw, skb); continue; } if (fi->baw_tracked) { - ath_tx_update_baw(sc, tid, bf); + ath_tx_update_baw(tid, bf); sendbar = true; } @@ -315,8 +314,7 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid) } } -static void ath_tx_update_baw(struct ath_softc *sc, struct ath_atx_tid *tid, - struct ath_buf *bf) +static void ath_tx_update_baw(struct ath_atx_tid *tid, struct ath_buf *bf) { struct ath_frame_info *fi = get_frame_info(bf->bf_mpdu); u16 seqno = bf->bf_state.seqno; @@ -338,8 +336,7 @@ static void ath_tx_update_baw(struct ath_softc *sc, struct ath_atx_tid *tid, } } -static void ath_tx_addto_baw(struct ath_softc *sc, struct ath_atx_tid *tid, - struct ath_buf *bf) +static void ath_tx_addto_baw(struct ath_atx_tid *tid, struct ath_buf *bf) { struct ath_frame_info *fi = get_frame_info(bf->bf_mpdu); u16 seqno = bf->bf_state.seqno; @@ -452,9 +449,8 @@ static struct ath_buf* ath_clone_txbuf(struct ath_softc *sc, struct ath_buf *bf) return tbf; } -static void ath_tx_count_frames(struct ath_softc *sc, struct ath_buf *bf, - struct ath_tx_status *ts, int txok, - int *nframes, int *nbad) +static void ath_tx_count_frames(struct ath_buf *bf, struct ath_tx_status *ts, + int txok, int *nframes, int *nbad) { u16 seq_st = 0; u32 ba[WME_BA_BMP_SIZE >> 5]; @@ -557,7 +553,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, /* * AR5416 can become deaf/mute when BA * issue happens. Chip needs to be reset. - * But AP code may have sychronization issues + * But AP code may have synchronization issues * when perform internal reset in this routine. * Only enable reset in STA mode for now. */ @@ -568,7 +564,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, __skb_queue_head_init(&bf_pending); - ath_tx_count_frames(sc, bf, ts, txok, &nframes, &nbad); + ath_tx_count_frames(bf, ts, txok, &nframes, &nbad); while (bf) { u16 seqno = bf->bf_state.seqno; @@ -621,7 +617,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, * complete the acked-ones/xretried ones; update * block-ack window */ - ath_tx_update_baw(sc, tid, bf); + ath_tx_update_baw(tid, bf); if (rc_update && (acked_cnt == 1 || txfail_cnt == 1)) { memcpy(tx_info->control.rates, rates, sizeof(rates)); @@ -651,7 +647,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, * run out of tx buf. */ if (!tbf) { - ath_tx_update_baw(sc, tid, bf); + ath_tx_update_baw(tid, bf); ath_tx_complete_buf(sc, bf, txq, &bf_head, NULL, ts, @@ -752,7 +748,7 @@ static void ath_tx_process_buffer(struct ath_softc *sc, struct ath_txq *txq, sta = ieee80211_find_sta_by_ifaddr(hw, hdr->addr1, hdr->addr2); if (sta) { struct ath_node *an = (struct ath_node *)sta->drv_priv; - tid = ath_get_skb_tid(sc, an, bf->bf_mpdu); + tid = ath_get_skb_tid(an, bf->bf_mpdu); ath_tx_count_airtime(sc, sta, bf, ts, tid->tidno); if (ts->ts_status & (ATH9K_TXERR_FILT | ATH9K_TXERR_XRETRY)) tid->clear_ps_filter = true; @@ -962,7 +958,7 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq, bf->bf_state.stale = false; if (!bf) { - ath_txq_skb_done(sc, txq, skb); + ath_txq_skb_done(sc, skb); ieee80211_free_txskb(sc->hw, skb); continue; } @@ -1012,13 +1008,13 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq, INIT_LIST_HEAD(&bf_head); list_add(&bf->list, &bf_head); - ath_tx_update_baw(sc, tid, bf); + ath_tx_update_baw(tid, bf); ath_tx_complete_buf(sc, bf, txq, &bf_head, NULL, &ts, 0); continue; } if (bf_isampdu(bf)) - ath_tx_addto_baw(sc, tid, bf); + ath_tx_addto_baw(tid, bf); break; } @@ -1114,8 +1110,8 @@ finish: * width - 0 for 20 MHz, 1 for 40 MHz * half_gi - to use 4us v/s 3.6 us for symbol time */ -u32 ath_pkt_duration(struct ath_softc *sc, u8 rix, int pktlen, - int width, int half_gi, bool shortPreamble) +u32 ath_pkt_duration(u8 rix, int pktlen, int width, + int half_gi, bool shortPreamble) { u32 nbits, nsymbits, duration, nsymbols; int streams; @@ -1327,7 +1323,7 @@ static void ath_buf_set_rate(struct ath_softc *sc, struct ath_buf *bf, info->rates[i].Rate = rix | 0x80; info->rates[i].ChSel = ath_txchainmask_reduction(sc, ah->txchainmask, info->rates[i].Rate); - info->rates[i].PktDuration = ath_pkt_duration(sc, rix, len, + info->rates[i].PktDuration = ath_pkt_duration(rix, len, is_40, is_sgi, is_sp); if (rix < 8 && (tx_info->flags & IEEE80211_TX_CTL_STBC)) info->rates[i].RateFlags |= ATH9K_RATESERIES_STBC; @@ -2122,7 +2118,7 @@ static void ath_tx_send_normal(struct ath_softc *sc, struct ath_txq *txq, bf->bf_state.bf_type = 0; if (tid && (tx_info->flags & IEEE80211_TX_CTL_AMPDU)) { bf->bf_state.bf_type = BUF_AMPDU; - ath_tx_addto_baw(sc, tid, bf); + ath_tx_addto_baw(tid, bf); } bf->bf_next = NULL; @@ -2368,7 +2364,7 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb, if (txctl->sta) { an = (struct ath_node *) sta->drv_priv; - tid = ath_get_skb_tid(sc, an, skb); + tid = ath_get_skb_tid(an, skb); } ath_txq_lock(sc, txq); @@ -2379,7 +2375,7 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb, bf = ath_tx_setup_buffer(sc, txq, tid, skb); if (!bf) { - ath_txq_skb_done(sc, txq, skb); + ath_txq_skb_done(sc, skb); if (txctl->paprd) dev_kfree_skb_any(skb); else @@ -2514,7 +2510,7 @@ static void ath_tx_complete(struct ath_softc *sc, struct sk_buff *skb, } spin_unlock_irqrestore(&sc->sc_pm_lock, flags); - ath_txq_skb_done(sc, txq, skb); + ath_txq_skb_done(sc, skb); tx_info->status.status_driver_data[0] = sta; __skb_queue_tail(&txq->complete_q, skb); } diff --git a/drivers/net/wireless/ath/carl9170/debug.c b/drivers/net/wireless/ath/carl9170/debug.c index bb40889d7c72..2d734567000a 100644 --- a/drivers/net/wireless/ath/carl9170/debug.c +++ b/drivers/net/wireless/ath/carl9170/debug.c @@ -54,7 +54,6 @@ struct carl9170_debugfs_fops { char *(*read)(struct ar9170 *ar, char *buf, size_t bufsize, ssize_t *len); ssize_t (*write)(struct ar9170 *aru, const char *buf, size_t size); - const struct file_operations fops; enum carl9170_device_state req_dev_state; }; @@ -62,7 +61,7 @@ struct carl9170_debugfs_fops { static ssize_t carl9170_debugfs_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - struct carl9170_debugfs_fops *dfops; + const struct carl9170_debugfs_fops *dfops; struct ar9170 *ar; char *buf = NULL, *res_buf = NULL; ssize_t ret = 0; @@ -75,8 +74,7 @@ static ssize_t carl9170_debugfs_read(struct file *file, char __user *userbuf, if (!ar) return -ENODEV; - dfops = container_of(debugfs_real_fops(file), - struct carl9170_debugfs_fops, fops); + dfops = debugfs_get_aux(file); if (!dfops->read) return -ENOSYS; @@ -113,7 +111,7 @@ out_free: static ssize_t carl9170_debugfs_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { - struct carl9170_debugfs_fops *dfops; + const struct carl9170_debugfs_fops *dfops; struct ar9170 *ar; char *buf = NULL; int err = 0; @@ -128,8 +126,7 @@ static ssize_t carl9170_debugfs_write(struct file *file, if (!ar) return -ENODEV; - dfops = container_of(debugfs_real_fops(file), - struct carl9170_debugfs_fops, fops); + dfops = debugfs_get_aux(file); if (!dfops->write) return -ENOSYS; @@ -165,6 +162,11 @@ out_free: return err; } +static struct debugfs_short_fops debugfs_fops = { + .read = carl9170_debugfs_read, + .write = carl9170_debugfs_write, +}; + #define __DEBUGFS_DECLARE_FILE(name, _read, _write, _read_bufsize, \ _attr, _dstate) \ static const struct carl9170_debugfs_fops carl_debugfs_##name ##_ops = {\ @@ -173,12 +175,6 @@ static const struct carl9170_debugfs_fops carl_debugfs_##name ##_ops = {\ .write = _write, \ .attr = _attr, \ .req_dev_state = _dstate, \ - .fops = { \ - .open = simple_open, \ - .read = carl9170_debugfs_read, \ - .write = carl9170_debugfs_write, \ - .owner = THIS_MODULE \ - }, \ } #define DEBUGFS_DECLARE_FILE(name, _read, _write, _read_bufsize, _attr) \ @@ -816,9 +812,9 @@ void carl9170_debugfs_register(struct ar9170 *ar) ar->hw->wiphy->debugfsdir); #define DEBUGFS_ADD(name) \ - debugfs_create_file(#name, carl_debugfs_##name ##_ops.attr, \ - ar->debug_dir, ar, \ - &carl_debugfs_##name ## _ops.fops) + debugfs_create_file_aux(#name, carl_debugfs_##name ##_ops.attr, \ + ar->debug_dir, ar, &carl_debugfs_##name ## _ops, \ + &debugfs_fops) DEBUGFS_ADD(usb_tx_anch_urbs); DEBUGFS_ADD(usb_rx_pool_urbs); diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c index 8557d4826a46..94d08d6ae1a3 100644 --- a/drivers/net/wireless/ath/wcn36xx/main.c +++ b/drivers/net/wireless/ath/wcn36xx/main.c @@ -1590,7 +1590,10 @@ static int wcn36xx_probe(struct platform_device *pdev) } n_channels = wcn_band_2ghz.n_channels + wcn_band_5ghz.n_channels; - wcn->chan_survey = devm_kmalloc(wcn->dev, n_channels, GFP_KERNEL); + wcn->chan_survey = devm_kcalloc(wcn->dev, + n_channels, + sizeof(struct wcn36xx_chan_survey), + GFP_KERNEL); if (!wcn->chan_survey) { ret = -ENOMEM; goto out_wq; diff --git a/drivers/net/wireless/broadcom/b43/debugfs.c b/drivers/net/wireless/broadcom/b43/debugfs.c index efa98444e3fb..5a49970afc8c 100644 --- a/drivers/net/wireless/broadcom/b43/debugfs.c +++ b/drivers/net/wireless/broadcom/b43/debugfs.c @@ -30,7 +30,6 @@ static struct dentry *rootdir; struct b43_debugfs_fops { ssize_t (*read)(struct b43_wldev *dev, char *buf, size_t bufsize); int (*write)(struct b43_wldev *dev, const char *buf, size_t count); - struct file_operations fops; /* Offset of struct b43_dfs_file in struct b43_dfsentry */ size_t file_struct_offset; }; @@ -491,7 +490,7 @@ static ssize_t b43_debugfs_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct b43_wldev *dev; - struct b43_debugfs_fops *dfops; + const struct b43_debugfs_fops *dfops; struct b43_dfs_file *dfile; ssize_t ret; char *buf; @@ -511,8 +510,7 @@ static ssize_t b43_debugfs_read(struct file *file, char __user *userbuf, goto out_unlock; } - dfops = container_of(debugfs_real_fops(file), - struct b43_debugfs_fops, fops); + dfops = debugfs_get_aux(file); if (!dfops->read) { err = -ENOSYS; goto out_unlock; @@ -555,7 +553,7 @@ static ssize_t b43_debugfs_write(struct file *file, size_t count, loff_t *ppos) { struct b43_wldev *dev; - struct b43_debugfs_fops *dfops; + const struct b43_debugfs_fops *dfops; char *buf; int err = 0; @@ -573,8 +571,7 @@ static ssize_t b43_debugfs_write(struct file *file, goto out_unlock; } - dfops = container_of(debugfs_real_fops(file), - struct b43_debugfs_fops, fops); + dfops = debugfs_get_aux(file); if (!dfops->write) { err = -ENOSYS; goto out_unlock; @@ -602,16 +599,16 @@ out_unlock: } +static struct debugfs_short_fops debugfs_ops = { + .read = b43_debugfs_read, + .write = b43_debugfs_write, + .llseek = generic_file_llseek, +}; + #define B43_DEBUGFS_FOPS(name, _read, _write) \ static struct b43_debugfs_fops fops_##name = { \ .read = _read, \ .write = _write, \ - .fops = { \ - .open = simple_open, \ - .read = b43_debugfs_read, \ - .write = b43_debugfs_write, \ - .llseek = generic_file_llseek, \ - }, \ .file_struct_offset = offsetof(struct b43_dfsentry, \ file_##name), \ } @@ -703,9 +700,9 @@ void b43_debugfs_add_device(struct b43_wldev *dev) #define ADD_FILE(name, mode) \ do { \ - debugfs_create_file(__stringify(name), \ + debugfs_create_file_aux(__stringify(name), \ mode, e->subdir, dev, \ - &fops_##name.fops); \ + &fops_##name, &debugfs_ops); \ } while (0) diff --git a/drivers/net/wireless/broadcom/b43legacy/debugfs.c b/drivers/net/wireless/broadcom/b43legacy/debugfs.c index 6b0e8d117061..5d04bcc216e5 100644 --- a/drivers/net/wireless/broadcom/b43legacy/debugfs.c +++ b/drivers/net/wireless/broadcom/b43legacy/debugfs.c @@ -31,7 +31,6 @@ static struct dentry *rootdir; struct b43legacy_debugfs_fops { ssize_t (*read)(struct b43legacy_wldev *dev, char *buf, size_t bufsize); int (*write)(struct b43legacy_wldev *dev, const char *buf, size_t count); - struct file_operations fops; /* Offset of struct b43legacy_dfs_file in struct b43legacy_dfsentry */ size_t file_struct_offset; /* Take wl->irq_lock before calling read/write? */ @@ -188,7 +187,7 @@ static ssize_t b43legacy_debugfs_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct b43legacy_wldev *dev; - struct b43legacy_debugfs_fops *dfops; + const struct b43legacy_debugfs_fops *dfops; struct b43legacy_dfs_file *dfile; ssize_t ret; char *buf; @@ -208,8 +207,7 @@ static ssize_t b43legacy_debugfs_read(struct file *file, char __user *userbuf, goto out_unlock; } - dfops = container_of(debugfs_real_fops(file), - struct b43legacy_debugfs_fops, fops); + dfops = debugfs_get_aux(file); if (!dfops->read) { err = -ENOSYS; goto out_unlock; @@ -257,7 +255,7 @@ static ssize_t b43legacy_debugfs_write(struct file *file, size_t count, loff_t *ppos) { struct b43legacy_wldev *dev; - struct b43legacy_debugfs_fops *dfops; + const struct b43legacy_debugfs_fops *dfops; char *buf; int err = 0; @@ -275,8 +273,7 @@ static ssize_t b43legacy_debugfs_write(struct file *file, goto out_unlock; } - dfops = container_of(debugfs_real_fops(file), - struct b43legacy_debugfs_fops, fops); + dfops = debugfs_get_aux(file); if (!dfops->write) { err = -ENOSYS; goto out_unlock; @@ -308,17 +305,16 @@ out_unlock: return err ? err : count; } +static struct debugfs_short_fops debugfs_ops = { + .read = b43legacy_debugfs_read, + .write = b43legacy_debugfs_write, + .llseek = generic_file_llseek +}; #define B43legacy_DEBUGFS_FOPS(name, _read, _write, _take_irqlock) \ static struct b43legacy_debugfs_fops fops_##name = { \ .read = _read, \ .write = _write, \ - .fops = { \ - .open = simple_open, \ - .read = b43legacy_debugfs_read, \ - .write = b43legacy_debugfs_write, \ - .llseek = generic_file_llseek, \ - }, \ .file_struct_offset = offsetof(struct b43legacy_dfsentry, \ file_##name), \ .take_irqlock = _take_irqlock, \ @@ -386,9 +382,9 @@ void b43legacy_debugfs_add_device(struct b43legacy_wldev *dev) #define ADD_FILE(name, mode) \ do { \ - debugfs_create_file(__stringify(name), mode, \ + debugfs_create_file_aux(__stringify(name), mode, \ e->subdir, dev, \ - &fops_##name.fops); \ + &fops_##name, &debugfs_ops); \ } while (0) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index 42d991d9f8cb..60eb95fc19a5 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -455,6 +455,11 @@ static int brcmf_sdiod_sglist_rw(struct brcmf_sdio_dev *sdiodev, if (sg_data_sz > max_req_sz - req_sz) sg_data_sz = max_req_sz - req_sz; + if (!sgl) { + /* out of (pre-allocated) scatterlist entries */ + ret = -ENOMEM; + goto exit; + } sg_set_buf(sgl, pkt_data, sg_data_sz); sg_cnt++; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 297a7c738c01..4b70845e1a26 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -814,6 +814,8 @@ static int brcmf_cfg80211_request_ap_if(struct brcmf_if *ifp) * @name: name of the new interface. * @params: contains mac address for AP or STA device. * @type: interface type. + * + * Return: pointer to new vif on success, ERR_PTR(-errno) if not */ static struct wireless_dev *brcmf_apsta_add_vif(struct wiphy *wiphy, const char *name, @@ -900,6 +902,8 @@ static bool brcmf_is_ibssmode(struct brcmf_cfg80211_vif *vif) * * @wiphy: wiphy device of new interface. * @name: name of the new interface. + * + * Return: pointer to new vif on success, ERR_PTR(-errno) if not */ static struct wireless_dev *brcmf_mon_add_vif(struct wiphy *wiphy, const char *name) @@ -2676,7 +2680,7 @@ done: static s32 brcmf_cfg80211_get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, - s32 *dbm) + unsigned int link_id, s32 *dbm) { struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy); struct brcmf_cfg80211_vif *vif = wdev_to_vif(wdev); @@ -4999,12 +5003,16 @@ exit: s32 brcmf_vif_clear_mgmt_ies(struct brcmf_cfg80211_vif *vif) { static const s32 pktflags[] = { - BRCMF_VNDR_IE_PRBREQ_FLAG, BRCMF_VNDR_IE_PRBRSP_FLAG, BRCMF_VNDR_IE_BEACON_FLAG }; int i; + if (vif->wdev.iftype == NL80211_IFTYPE_AP) + brcmf_vif_set_mgmt_ie(vif, BRCMF_VNDR_IE_ASSOCRSP_FLAG, NULL, 0); + else + brcmf_vif_set_mgmt_ie(vif, BRCMF_VNDR_IE_PRBREQ_FLAG, NULL, 0); + for (i = 0; i < ARRAY_SIZE(pktflags); i++) brcmf_vif_set_mgmt_ie(vif, pktflags[i], NULL, 0); @@ -7408,6 +7416,8 @@ brcmf_txrx_stypes[NUM_NL80211_IFTYPES] = { * p2p, rsdb, and no mbss: * #STA <= 1, #P2P-DEV <= 1, #{P2P-CL, P2P-GO} <= 2, AP <= 2, * channels = 2, 4 total + * + * Return: 0 on success, negative errno on failure */ static int brcmf_setup_ifmodes(struct wiphy *wiphy, struct brcmf_if *ifp) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index da72fd2d541f..3d63010ae079 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -327,8 +327,8 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb, if (skb_headroom(skb) < drvr->hdrlen || skb_header_cloned(skb)) { head_delta = max_t(int, drvr->hdrlen - skb_headroom(skb), 0); - brcmf_dbg(INFO, "%s: insufficient headroom (%d)\n", - brcmf_ifname(ifp), head_delta); + brcmf_dbg(INFO, "%s: %s headroom\n", brcmf_ifname(ifp), + head_delta ? "insufficient" : "unmodifiable"); atomic_inc(&drvr->bus_if->stats.pktcowed); ret = pskb_expand_head(skb, ALIGN(head_delta, NET_SKB_PAD), 0, GFP_ATOMIC); @@ -540,6 +540,11 @@ void brcmf_txfinalize(struct brcmf_if *ifp, struct sk_buff *txp, bool success) struct ethhdr *eh; u16 type; + if (!ifp) { + brcmu_pkt_buf_free_skb(txp); + return; + } + eh = (struct ethhdr *)(txp->data); type = ntohs(eh->h_proto); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h index 31e080e4da66..ab3d6cfcb02b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h @@ -6,6 +6,8 @@ #ifndef _fwil_h_ #define _fwil_h_ +#include "debug.h" + /******************************************************************************* * Dongle command codes that are interpreted by firmware ******************************************************************************/ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c index 0949e7975ff1..b70d20128f98 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c @@ -1810,7 +1810,7 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt) rfi->cur_idx = cur_idx; } } else { - /* explicity window move updating the expected index */ + /* explicitly window move updating the expected index */ exp_idx = reorder_data[BRCMF_RXREORDER_EXPIDX_OFFSET]; brcmf_dbg(DATA, "flow-%d (0x%x): change expected: %d -> %d\n", diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c index c1f18e2fe540..1681ad00f82e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c @@ -99,13 +99,13 @@ int brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type, /* Set board-type to the first string of the machine compatible prop */ root = of_find_node_by_path("/"); if (root && err) { - char *board_type; + char *board_type = NULL; const char *tmp; - of_property_read_string_index(root, "compatible", 0, &tmp); - /* get rid of '/' in the compatible string to be able to find the FW */ - board_type = devm_kstrdup(dev, tmp, GFP_KERNEL); + if (!of_property_read_string_index(root, "compatible", 0, &tmp)) + board_type = devm_kstrdup(dev, tmp, GFP_KERNEL); + if (!board_type) { of_node_put(root); return 0; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c index d69879e1bd87..d362c4337616 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c @@ -23423,6 +23423,9 @@ wlc_phy_iqcal_gainparams_nphy(struct brcms_phy *pi, u16 core_no, break; } + if (WARN_ON(k == NPHY_IQCAL_NUMGAINS)) + return; + params->txgm = tbl_iqcal_gainparams_nphy[band_idx][k][1]; params->pga = tbl_iqcal_gainparams_nphy[band_idx][k][2]; params->pad = tbl_iqcal_gainparams_nphy[band_idx][k][3]; diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c index 74fc76c00ebc..4013443698a2 100644 --- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c @@ -1127,44 +1127,6 @@ il3945_rx_queue_free(struct il_priv *il, struct il_rx_queue *rxq) rxq->rb_stts = NULL; } -/* Convert linear signal-to-noise ratio into dB */ -static u8 ratio2dB[100] = { -/* 0 1 2 3 4 5 6 7 8 9 */ - 0, 0, 6, 10, 12, 14, 16, 17, 18, 19, /* 00 - 09 */ - 20, 21, 22, 22, 23, 23, 24, 25, 26, 26, /* 10 - 19 */ - 26, 26, 26, 27, 27, 28, 28, 28, 29, 29, /* 20 - 29 */ - 29, 30, 30, 30, 31, 31, 31, 31, 32, 32, /* 30 - 39 */ - 32, 32, 32, 33, 33, 33, 33, 33, 34, 34, /* 40 - 49 */ - 34, 34, 34, 34, 35, 35, 35, 35, 35, 35, /* 50 - 59 */ - 36, 36, 36, 36, 36, 36, 36, 37, 37, 37, /* 60 - 69 */ - 37, 37, 37, 37, 37, 38, 38, 38, 38, 38, /* 70 - 79 */ - 38, 38, 38, 38, 38, 39, 39, 39, 39, 39, /* 80 - 89 */ - 39, 39, 39, 39, 39, 40, 40, 40, 40, 40 /* 90 - 99 */ -}; - -/* Calculates a relative dB value from a ratio of linear - * (i.e. not dB) signal levels. - * Conversion assumes that levels are voltages (20*log), not powers (10*log). */ -int -il3945_calc_db_from_ratio(int sig_ratio) -{ - /* 1000:1 or higher just report as 60 dB */ - if (sig_ratio >= 1000) - return 60; - - /* 100:1 or higher, divide by 10 and use table, - * add 20 dB to make up for divide by 10 */ - if (sig_ratio >= 100) - return 20 + (int)ratio2dB[sig_ratio / 10]; - - /* We shouldn't see this */ - if (sig_ratio < 1) - return 0; - - /* Use table for ratios 1:1 - 99:1 */ - return (int)ratio2dB[sig_ratio]; -} - /* * il3945_rx_handle - Main entry function for receiving responses from uCode * diff --git a/drivers/net/wireless/intel/iwlegacy/3945.h b/drivers/net/wireless/intel/iwlegacy/3945.h index ffbe11902628..fb1e33c89d0e 100644 --- a/drivers/net/wireless/intel/iwlegacy/3945.h +++ b/drivers/net/wireless/intel/iwlegacy/3945.h @@ -173,7 +173,6 @@ struct il3945_ibss_seq { * for use by iwl-*.c * *****************************************************************************/ -int il3945_calc_db_from_ratio(int sig_ratio); void il3945_rx_replenish(void *data); void il3945_rx_queue_reset(struct il_priv *il, struct il_rx_queue *rxq); unsigned int il3945_fill_beacon_frame(struct il_priv *il, diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c index 958dd4f9bc69..af4f42534ea0 100644 --- a/drivers/net/wireless/intel/iwlegacy/common.c +++ b/drivers/net/wireless/intel/iwlegacy/common.c @@ -3915,37 +3915,6 @@ il_set_rxon_ht(struct il_priv *il, struct il_ht_config *ht_conf) } EXPORT_SYMBOL(il_set_rxon_ht); -/* Return valid, unused, channel for a passive scan to reset the RF */ -u8 -il_get_single_channel_number(struct il_priv *il, enum nl80211_band band) -{ - const struct il_channel_info *ch_info; - int i; - u8 channel = 0; - u8 min, max; - - if (band == NL80211_BAND_5GHZ) { - min = 14; - max = il->channel_count; - } else { - min = 0; - max = 14; - } - - for (i = min; i < max; i++) { - channel = il->channel_info[i].channel; - if (channel == le16_to_cpu(il->staging.channel)) - continue; - - ch_info = il_get_channel_info(il, band, channel); - if (il_is_channel_valid(ch_info)) - break; - } - - return channel; -} -EXPORT_SYMBOL(il_get_single_channel_number); - /* * il_set_rxon_channel - Set the band and channel values in staging RXON * @ch: requested channel as a pointer to struct ieee80211_channel diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h index 725c2a88ddb7..92285412ab10 100644 --- a/drivers/net/wireless/intel/iwlegacy/common.h +++ b/drivers/net/wireless/intel/iwlegacy/common.h @@ -1705,7 +1705,6 @@ int il_full_rxon_required(struct il_priv *il); int il_set_rxon_channel(struct il_priv *il, struct ieee80211_channel *ch); void il_set_flags_for_band(struct il_priv *il, enum nl80211_band band, struct ieee80211_vif *vif); -u8 il_get_single_channel_number(struct il_priv *il, enum nl80211_band band); void il_set_rxon_ht(struct il_priv *il, struct il_ht_config *ht_conf); bool il_is_ht40_tx_allowed(struct il_priv *il, struct ieee80211_sta_ht_cap *ht_cap); diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile index 64c123314245..19c4ce6f2465 100644 --- a/drivers/net/wireless/intel/iwlwifi/Makefile +++ b/drivers/net/wireless/intel/iwlwifi/Makefile @@ -5,13 +5,14 @@ iwlwifi-objs += iwl-io.o iwlwifi-objs += iwl-drv.o iwlwifi-objs += iwl-debug.o iwlwifi-objs += iwl-nvm-utils.o +iwlwifi-objs += iwl-utils.o iwlwifi-objs += iwl-phy-db.o iwl-nvm-parse.o iwlwifi-objs += pcie/drv.o pcie/rx.o pcie/tx.o pcie/trans.o iwlwifi-objs += pcie/ctxt-info.o pcie/ctxt-info-gen3.o iwlwifi-objs += pcie/trans-gen2.o pcie/tx-gen2.o iwlwifi-$(CONFIG_IWLDVM) += cfg/1000.o cfg/2000.o cfg/5000.o cfg/6000.o iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o cfg/9000.o cfg/22000.o -iwlwifi-$(CONFIG_IWLMVM) += cfg/ax210.o cfg/bz.o cfg/sc.o +iwlwifi-$(CONFIG_IWLMVM) += cfg/ax210.o cfg/bz.o cfg/sc.o cfg/dr.o iwlwifi-objs += iwl-dbg-tlv.o iwlwifi-objs += iwl-trans.o diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c index 975e8aed1526..dcba1a5d793b 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c @@ -31,40 +31,21 @@ #define IWL_SO_A_GF_A_FW_PRE "iwlwifi-so-a0-gf-a0" #define IWL_TY_A_GF_A_FW_PRE "iwlwifi-ty-a0-gf-a0" #define IWL_SO_A_GF4_A_FW_PRE "iwlwifi-so-a0-gf4-a0" -#define IWL_SO_A_MR_A_FW_PRE "iwlwifi-so-a0-mr-a0" #define IWL_MA_A_HR_B_FW_PRE "iwlwifi-ma-a0-hr-b0" #define IWL_MA_A_GF_A_FW_PRE "iwlwifi-ma-a0-gf-a0" #define IWL_MA_A_GF4_A_FW_PRE "iwlwifi-ma-a0-gf4-a0" -#define IWL_MA_A_MR_A_FW_PRE "iwlwifi-ma-a0-mr-a0" #define IWL_MA_B_HR_B_FW_PRE "iwlwifi-ma-b0-hr-b0" #define IWL_MA_B_GF_A_FW_PRE "iwlwifi-ma-b0-gf-a0" #define IWL_MA_B_GF4_A_FW_PRE "iwlwifi-ma-b0-gf4-a0" -#define IWL_MA_B_MR_A_FW_PRE "iwlwifi-ma-b0-mr-a0" #define IWL_SO_A_JF_B_MODULE_FIRMWARE(api) \ IWL_SO_A_JF_B_FW_PRE "-" __stringify(api) ".ucode" #define IWL_SO_A_HR_B_MODULE_FIRMWARE(api) \ IWL_SO_A_HR_B_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_SO_A_GF_A_MODULE_FIRMWARE(api) \ - IWL_SO_A_GF_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_TY_A_GF_A_MODULE_FIRMWARE(api) \ - IWL_TY_A_GF_A_FW_PRE "-" __stringify(api) ".ucode" #define IWL_MA_A_HR_B_FW_MODULE_FIRMWARE(api) \ IWL_MA_A_HR_B_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_MA_A_GF_A_FW_MODULE_FIRMWARE(api) \ - IWL_MA_A_GF_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_MA_A_GF4_A_FW_MODULE_FIRMWARE(api) \ - IWL_MA_A_GF4_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_MA_A_MR_A_FW_MODULE_FIRMWARE(api) \ - IWL_MA_A_MR_A_FW_PRE "-" __stringify(api) ".ucode" #define IWL_MA_B_HR_B_FW_MODULE_FIRMWARE(api) \ IWL_MA_B_HR_B_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_MA_B_GF_A_FW_MODULE_FIRMWARE(api) \ - IWL_MA_B_GF_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_MA_B_GF4_A_FW_MODULE_FIRMWARE(api) \ - IWL_MA_B_GF4_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_MA_B_MR_A_FW_MODULE_FIRMWARE(api) \ - IWL_MA_B_MR_A_FW_PRE "-" __stringify(api) ".ucode" static const struct iwl_base_params iwl_ax210_base_params = { .eeprom_size = OTP_LOW_IMAGE_SIZE_32K, @@ -267,13 +248,6 @@ const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0_long = { .trans.low_latency_xtal = true, }; -const struct iwl_cfg iwl_cfg_so_a0_ms_a0 = { - .fw_name_pre = IWL_SO_A_MR_A_FW_PRE, - .uhb_supported = false, - IWL_DEVICE_AX210, - .num_rbds = IWL_NUM_RBDS_AX210_HE, -}; - const struct iwl_cfg iwl_cfg_ma = { .fw_name_mac = "ma", .uhb_supported = true, @@ -289,19 +263,11 @@ const struct iwl_cfg iwl_cfg_so_a0_hr_a0 = { MODULE_FIRMWARE(IWL_SO_A_JF_B_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_SO_A_HR_B_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_SO_A_GF_A_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_TY_A_GF_A_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); +IWL_FW_AND_PNVM(IWL_SO_A_GF_A_FW_PRE, IWL_AX210_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_TY_A_GF_A_FW_PRE, IWL_AX210_UCODE_API_MAX); MODULE_FIRMWARE(IWL_MA_A_HR_B_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_MA_A_GF_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_MA_A_GF4_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_MA_A_MR_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); +IWL_FW_AND_PNVM(IWL_MA_A_GF_A_FW_PRE, IWL_AX210_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_MA_A_GF4_A_FW_PRE, IWL_AX210_UCODE_API_MAX); MODULE_FIRMWARE(IWL_MA_B_HR_B_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_MA_B_GF_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_MA_B_GF4_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_MA_B_MR_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); - -MODULE_FIRMWARE("iwlwifi-so-a0-gf-a0.pnvm"); -MODULE_FIRMWARE("iwlwifi-so-a0-gf4-a0.pnvm"); -MODULE_FIRMWARE("iwlwifi-ty-a0-gf-a0.pnvm"); -MODULE_FIRMWARE("iwlwifi-ma-b0-gf-a0.pnvm"); -MODULE_FIRMWARE("iwlwifi-ma-b0-gf4-a0.pnvm"); +IWL_FW_AND_PNVM(IWL_MA_B_GF_A_FW_PRE, IWL_AX210_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_MA_B_GF4_A_FW_PRE, IWL_AX210_UCODE_API_MAX); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c index cd1fe8490ae5..efa3e0e35f79 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c @@ -10,7 +10,7 @@ #include "fw/api/txq.h" /* Highest firmware API version supported */ -#define IWL_BZ_UCODE_API_MAX 94 +#define IWL_BZ_UCODE_API_MAX 96 /* Lowest firmware API version supported */ #define IWL_BZ_UCODE_API_MIN 92 @@ -37,20 +37,6 @@ #define IWL_BZ_A_HR_B_MODULE_FIRMWARE(api) \ IWL_BZ_A_HR_B_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_BZ_A_GF_A_MODULE_FIRMWARE(api) \ - IWL_BZ_A_GF_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_BZ_A_GF4_A_MODULE_FIRMWARE(api) \ - IWL_BZ_A_GF4_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_BZ_A_FM_B_MODULE_FIRMWARE(api) \ - IWL_BZ_A_FM_B_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_BZ_A_FM_C_MODULE_FIRMWARE(api) \ - IWL_BZ_A_FM_C_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_BZ_A_FM4_B_MODULE_FIRMWARE(api) \ - IWL_BZ_A_FM4_B_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_GL_B_FM_B_MODULE_FIRMWARE(api) \ - IWL_GL_B_FM_B_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_GL_C_FM_C_MODULE_FIRMWARE(api) \ - IWL_GL_C_FM_C_FW_PRE "-" __stringify(api) ".ucode" static const struct iwl_base_params iwl_bz_base_params = { .eeprom_size = OTP_LOW_IMAGE_SIZE_32K, @@ -161,6 +147,7 @@ const struct iwl_cfg_trans_params iwl_gl_trans_cfg = { const char iwl_bz_name[] = "Intel(R) TBD Bz device"; const char iwl_fm_name[] = "Intel(R) Wi-Fi 7 BE201 320MHz"; +const char iwl_wh_name[] = "Intel(R) Wi-Fi 7 BE211 320MHz"; const char iwl_gl_name[] = "Intel(R) Wi-Fi 7 BE200 320MHz"; const char iwl_mtp_name[] = "Intel(R) Wi-Fi 7 BE202 160MHz"; @@ -180,14 +167,11 @@ const struct iwl_cfg iwl_cfg_gl = { .num_rbds = IWL_NUM_RBDS_BZ_EHT, }; - MODULE_FIRMWARE(IWL_BZ_A_HR_B_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_BZ_A_GF_A_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_BZ_A_GF4_A_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_BZ_A_FM_B_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_BZ_A_FM_C_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_BZ_A_FM4_B_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_GL_B_FM_B_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_GL_C_FM_C_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); - -MODULE_FIRMWARE("iwlwifi-gl-c0-fm-c0.pnvm"); +IWL_FW_AND_PNVM(IWL_BZ_A_GF_A_FW_PRE, IWL_BZ_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_BZ_A_GF4_A_FW_PRE, IWL_BZ_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_BZ_A_FM_B_FW_PRE, IWL_BZ_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_BZ_A_FM_C_FW_PRE, IWL_BZ_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_BZ_A_FM4_B_FW_PRE, IWL_BZ_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_GL_B_FM_B_FW_PRE, IWL_BZ_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_GL_C_FM_C_FW_PRE, IWL_BZ_UCODE_API_MAX); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c new file mode 100644 index 000000000000..ab7c0f8d54f4 --- /dev/null +++ b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Copyright (C) 2024 Intel Corporation + */ +#include +#include +#include "iwl-config.h" +#include "iwl-prph.h" +#include "fw/api/txq.h" + +/* Highest firmware API version supported */ +#define IWL_DR_UCODE_API_MAX 96 + +/* Lowest firmware API version supported */ +#define IWL_DR_UCODE_API_MIN 96 + +/* NVM versions */ +#define IWL_DR_NVM_VERSION 0x0a1d + +/* Memory offsets and lengths */ +#define IWL_DR_DCCM_OFFSET 0x800000 /* LMAC1 */ +#define IWL_DR_DCCM_LEN 0x10000 /* LMAC1 */ +#define IWL_DR_DCCM2_OFFSET 0x880000 +#define IWL_DR_DCCM2_LEN 0x8000 +#define IWL_DR_SMEM_OFFSET 0x400000 +#define IWL_DR_SMEM_LEN 0xD0000 + +#define IWL_DR_A_PE_A_FW_PRE "iwlwifi-dr-a0-pe-a0" +#define IWL_BR_A_PET_A_FW_PRE "iwlwifi-br-a0-petc-a0" +#define IWL_BR_A_PE_A_FW_PRE "iwlwifi-br-a0-pe-a0" + +#define IWL_DR_A_PE_A_FW_MODULE_FIRMWARE(api) \ + IWL_DR_A_PE_A_FW_PRE "-" __stringify(api) ".ucode" +#define IWL_BR_A_PET_A_FW_MODULE_FIRMWARE(api) \ + IWL_BR_A_PET_A_FW_PRE "-" __stringify(api) ".ucode" +#define IWL_BR_A_PE_A_FW_MODULE_FIRMWARE(api) \ + IWL_BR_A_PE_A_FW_PRE "-" __stringify(api) ".ucode" + +static const struct iwl_base_params iwl_dr_base_params = { + .eeprom_size = OTP_LOW_IMAGE_SIZE_32K, + .num_of_queues = 512, + .max_tfd_queue_size = 65536, + .shadow_ram_support = true, + .led_compensation = 57, + .wd_timeout = IWL_LONG_WD_TIMEOUT, + .max_event_log_size = 512, + .shadow_reg_enable = true, + .pcie_l1_allowed = true, +}; + +#define IWL_DEVICE_DR_COMMON \ + .ucode_api_max = IWL_DR_UCODE_API_MAX, \ + .ucode_api_min = IWL_DR_UCODE_API_MIN, \ + .led_mode = IWL_LED_RF_STATE, \ + .nvm_hw_section_num = 10, \ + .non_shared_ant = ANT_B, \ + .dccm_offset = IWL_DR_DCCM_OFFSET, \ + .dccm_len = IWL_DR_DCCM_LEN, \ + .dccm2_offset = IWL_DR_DCCM2_OFFSET, \ + .dccm2_len = IWL_DR_DCCM2_LEN, \ + .smem_offset = IWL_DR_SMEM_OFFSET, \ + .smem_len = IWL_DR_SMEM_LEN, \ + .apmg_not_supported = true, \ + .trans.mq_rx_supported = true, \ + .vht_mu_mimo_supported = true, \ + .mac_addr_from_csr = 0x30, \ + .nvm_ver = IWL_DR_NVM_VERSION, \ + .trans.rf_id = true, \ + .trans.gen2 = true, \ + .nvm_type = IWL_NVM_EXT, \ + .dbgc_supported = true, \ + .min_umac_error_event_table = 0xD0000, \ + .d3_debug_data_base_addr = 0x401000, \ + .d3_debug_data_length = 60 * 1024, \ + .mon_smem_regs = { \ + .write_ptr = { \ + .addr = LDBG_M2S_BUF_WPTR, \ + .mask = LDBG_M2S_BUF_WPTR_VAL_MSK, \ + }, \ + .cycle_cnt = { \ + .addr = LDBG_M2S_BUF_WRAP_CNT, \ + .mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK, \ + }, \ + }, \ + .trans.umac_prph_offset = 0x300000, \ + .trans.device_family = IWL_DEVICE_FAMILY_DR, \ + .trans.base_params = &iwl_dr_base_params, \ + .min_txq_size = 128, \ + .gp2_reg_addr = 0xd02c68, \ + .min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_EHT, \ + .mon_dram_regs = { \ + .write_ptr = { \ + .addr = DBGC_CUR_DBGBUF_STATUS, \ + .mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK, \ + }, \ + .cycle_cnt = { \ + .addr = DBGC_DBGBUF_WRAP_AROUND, \ + .mask = 0xffffffff, \ + }, \ + .cur_frag = { \ + .addr = DBGC_CUR_DBGBUF_STATUS, \ + .mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK, \ + }, \ + }, \ + .mon_dbgi_regs = { \ + .write_ptr = { \ + .addr = DBGI_SRAM_FIFO_POINTERS, \ + .mask = DBGI_SRAM_FIFO_POINTERS_WR_PTR_MSK, \ + }, \ + } + +#define IWL_DEVICE_DR \ + IWL_DEVICE_DR_COMMON, \ + .uhb_supported = true, \ + .features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM, \ + .num_rbds = IWL_NUM_RBDS_DR_EHT, \ + .ht_params = &iwl_22000_ht_params + +/* + * This size was picked according to 8 MSDUs inside 512 A-MSDUs in an + * A-MPDU, with additional overhead to account for processing time. + */ +#define IWL_NUM_RBDS_DR_EHT (512 * 16) + +const struct iwl_cfg_trans_params iwl_dr_trans_cfg = { + .device_family = IWL_DEVICE_FAMILY_DR, + .base_params = &iwl_dr_base_params, + .mq_rx_supported = true, + .rf_id = true, + .gen2 = true, + .integrated = true, + .umac_prph_offset = 0x300000, + .xtal_latency = 12000, + .low_latency_xtal = true, + .ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US, +}; + +const char iwl_dr_name[] = "Intel(R) TBD Dr device"; + +const struct iwl_cfg iwl_cfg_dr = { + .fw_name_mac = "dr", + IWL_DEVICE_DR, +}; + +const struct iwl_cfg_trans_params iwl_br_trans_cfg = { + .device_family = IWL_DEVICE_FAMILY_DR, + .base_params = &iwl_dr_base_params, + .mq_rx_supported = true, + .rf_id = true, + .gen2 = true, + .integrated = true, + .umac_prph_offset = 0x300000, + .xtal_latency = 12000, + .low_latency_xtal = true, + .ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US, +}; + +const char iwl_br_name[] = "Intel(R) TBD Br device"; + +const struct iwl_cfg iwl_cfg_br = { + .fw_name_mac = "br", + IWL_DEVICE_DR, +}; + +MODULE_FIRMWARE(IWL_DR_A_PE_A_FW_MODULE_FIRMWARE(IWL_DR_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_BR_A_PET_A_FW_MODULE_FIRMWARE(IWL_DR_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_BR_A_PE_A_FW_MODULE_FIRMWARE(IWL_DR_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c index fc5e6e44c6aa..c9eeb3f6704e 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c @@ -10,7 +10,7 @@ #include "fw/api/txq.h" /* Highest firmware API version supported */ -#define IWL_SC_UCODE_API_MAX 94 +#define IWL_SC_UCODE_API_MAX 96 /* Lowest firmware API version supported */ #define IWL_SC_UCODE_API_MIN 92 @@ -38,28 +38,10 @@ #define IWL_SC2F_A_FM_C_FW_PRE "iwlwifi-sc2f-a0-fm-c0" #define IWL_SC2F_A_WH_A_FW_PRE "iwlwifi-sc2f-a0-wh-a0" -#define IWL_SC_A_FM_B_FW_MODULE_FIRMWARE(api) \ - IWL_SC_A_FM_B_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_SC_A_FM_C_FW_MODULE_FIRMWARE(api) \ - IWL_SC_A_FM_C_FW_PRE "-" __stringify(api) ".ucode" #define IWL_SC_A_HR_A_FW_MODULE_FIRMWARE(api) \ IWL_SC_A_HR_A_FW_PRE "-" __stringify(api) ".ucode" #define IWL_SC_A_HR_B_FW_MODULE_FIRMWARE(api) \ IWL_SC_A_HR_B_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_SC_A_GF_A_FW_MODULE_FIRMWARE(api) \ - IWL_SC_A_GF_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_SC_A_GF4_A_FW_MODULE_FIRMWARE(api) \ - IWL_SC_A_GF4_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_SC_A_WH_A_FW_MODULE_FIRMWARE(api) \ - IWL_SC_A_WH_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_SC2_A_FM_C_FW_MODULE_FIRMWARE(api) \ - IWL_SC2_A_FM_C_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_SC2_A_WH_A_FW_MODULE_FIRMWARE(api) \ - IWL_SC2_A_WH_A_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_SC2F_A_FM_C_FW_MODULE_FIRMWARE(api) \ - IWL_SC2F_A_FM_C_FW_PRE "-" __stringify(api) ".ucode" -#define IWL_SC2F_A_WH_A_FW_MODULE_FIRMWARE(api) \ - IWL_SC2F_A_WH_A_FW_PRE "-" __stringify(api) ".ucode" static const struct iwl_base_params iwl_sc_base_params = { .eeprom_size = OTP_LOW_IMAGE_SIZE_32K, @@ -181,14 +163,14 @@ const struct iwl_cfg iwl_cfg_sc2f = { IWL_DEVICE_SC, }; -MODULE_FIRMWARE(IWL_SC_A_FM_B_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_SC_A_FM_C_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); +IWL_FW_AND_PNVM(IWL_SC_A_FM_B_FW_PRE, IWL_SC_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_SC_A_FM_C_FW_PRE, IWL_SC_UCODE_API_MAX); MODULE_FIRMWARE(IWL_SC_A_HR_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_SC_A_HR_B_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_SC_A_GF_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_SC_A_GF4_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_SC_A_WH_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_SC2_A_FM_C_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_SC2_A_WH_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_SC2F_A_FM_C_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL_SC2F_A_WH_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); +IWL_FW_AND_PNVM(IWL_SC_A_GF_A_FW_PRE, IWL_SC_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_SC_A_GF4_A_FW_PRE, IWL_SC_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_SC_A_WH_A_FW_PRE, IWL_SC_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_SC2_A_FM_C_FW_PRE, IWL_SC_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_SC2_A_WH_A_FW_PRE, IWL_SC_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_SC2F_A_FM_C_FW_PRE, IWL_SC_UCODE_API_MAX); +IWL_FW_AND_PNVM(IWL_SC2F_A_WH_A_FW_PRE, IWL_SC_UCODE_API_MAX); diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c b/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c index 931aa3f5798d..cdc05f7e75a6 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c @@ -676,12 +676,12 @@ static int iwl_eeprom_acquire_semaphore(struct iwl_trans *trans) for (count = 0; count < IWL_EEPROM_SEM_RETRY_LIMIT; count++) { /* Request semaphore */ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_BIT_EEPROM_OWN_SEM); + CSR_HW_IF_CONFIG_REG_EEPROM_OWN_SEM); /* See if we got it */ ret = iwl_poll_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_BIT_EEPROM_OWN_SEM, - CSR_HW_IF_CONFIG_REG_BIT_EEPROM_OWN_SEM, + CSR_HW_IF_CONFIG_REG_EEPROM_OWN_SEM, + CSR_HW_IF_CONFIG_REG_EEPROM_OWN_SEM, IWL_EEPROM_SEM_TIMEOUT); if (ret >= 0) { IWL_DEBUG_EEPROM(trans->dev, @@ -697,7 +697,7 @@ static int iwl_eeprom_acquire_semaphore(struct iwl_trans *trans) static void iwl_eeprom_release_semaphore(struct iwl_trans *trans) { iwl_clear_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_BIT_EEPROM_OWN_SEM); + CSR_HW_IF_CONFIG_REG_EEPROM_OWN_SEM); } static int iwl_eeprom_verify_signature(struct iwl_trans *trans, bool nvm_is_otp) diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c index 74d163e56511..56d19a034c24 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c @@ -1565,6 +1565,16 @@ static void iwlagn_mac_sta_notify(struct ieee80211_hw *hw, IWL_DEBUG_MAC80211(priv, "leave\n"); } +static void +iwlagn_mac_reconfig_complete(struct ieee80211_hw *hw, + enum ieee80211_reconfig_type reconfig_type) +{ + struct iwl_priv *priv = IWL_MAC80211_GET_DVM(hw); + + if (reconfig_type == IEEE80211_RECONFIG_TYPE_RESTART) + iwl_trans_finish_sw_reset(priv->trans); +} + const struct ieee80211_ops iwlagn_hw_ops = { .add_chanctx = ieee80211_emulate_add_chanctx, .remove_chanctx = ieee80211_emulate_remove_chanctx, @@ -1598,6 +1608,7 @@ const struct ieee80211_ops iwlagn_hw_ops = { .tx_last_beacon = iwlagn_mac_tx_last_beacon, .event_callback = iwlagn_mac_event_callback, .set_tim = iwlagn_mac_set_tim, + .reconfig_complete = iwlagn_mac_reconfig_complete, }; /* This function both allocates and initializes hw and priv. */ diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c index 769b75c3fa5b..30789ba06d9d 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c @@ -1241,7 +1241,7 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans, STATISTICS_NOTIFICATION, REPLY_TX, }; - int i; + int i, err; /************************ * 1. Allocating HW data @@ -1249,6 +1249,7 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans, hw = iwl_alloc_all(); if (!hw) { pr_err("%s: Cannot allocate network device\n", trans->name); + err = -ENOMEM; goto out; } @@ -1299,8 +1300,10 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans, break; } - if (WARN_ON(!priv->lib)) + if (WARN_ON(!priv->lib)) { + err = -ENODEV; goto out_free_hw; + } /* * Populate the state variables that the transport layer needs @@ -1377,12 +1380,14 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans, IWL_INFO(priv, "Detected %s, REV=0x%X\n", priv->trans->name, priv->trans->hw_rev); - if (iwl_trans_start_hw(priv->trans)) + err = iwl_trans_start_hw(priv->trans); + if (err) goto out_free_hw; /* Read the EEPROM */ - if (iwl_read_eeprom(priv->trans, &priv->eeprom_blob, - &priv->eeprom_blob_size)) { + err = iwl_read_eeprom(priv->trans, &priv->eeprom_blob, + &priv->eeprom_blob_size); + if (err) { IWL_ERR(priv, "Unable to init EEPROM\n"); goto out_free_hw; } @@ -1393,13 +1398,17 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans, priv->nvm_data = iwl_parse_eeprom_data(priv->trans, priv->cfg, priv->eeprom_blob, priv->eeprom_blob_size); - if (!priv->nvm_data) + if (!priv->nvm_data) { + err = -ENOMEM; goto out_free_eeprom_blob; + } - if (iwl_nvm_check_version(priv->nvm_data, priv->trans)) + err = iwl_nvm_check_version(priv->nvm_data, priv->trans); + if (err) goto out_free_eeprom; - if (iwl_eeprom_init_hw_params(priv)) + err = iwl_eeprom_init_hw_params(priv); + if (err) goto out_free_eeprom; /* extract MAC Address */ @@ -1446,7 +1455,8 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans, atomic_set(&priv->queue_stop_count[i], 0); } - if (iwl_init_drv(priv)) + err = iwl_init_drv(priv); + if (err) goto out_free_eeprom; /* At this point both hw and priv are initialized. */ @@ -1480,7 +1490,8 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans, * * 7. Setup and register with mac80211 and debugfs **************************************************/ - if (iwlagn_mac_setup_register(priv, &fw->ucode_capa)) + err = iwlagn_mac_setup_register(priv, &fw->ucode_capa); + if (err) goto out_destroy_workqueue; iwl_dbgfs_register(priv, dbgfs_dir); @@ -1500,8 +1511,7 @@ out_free_eeprom: out_free_hw: ieee80211_free_hw(priv->hw); out: - op_mode = NULL; - return op_mode; + return ERR_PTR(err); } static void iwl_op_mode_dvm_stop(struct iwl_op_mode *op_mode) @@ -1895,17 +1905,9 @@ static void iwlagn_fw_error(struct iwl_priv *priv, bool ondemand) unsigned int reload_msec; unsigned long reload_jiffies; - if (iwl_have_debug_level(IWL_DL_FW)) - iwl_print_rx_config_cmd(priv, IWL_RXON_CTX_BSS); - /* uCode is no longer loaded. */ priv->ucode_loaded = false; - /* Set the FW error flag -- cleared on iwl_down */ - set_bit(STATUS_FW_ERROR, &priv->status); - - iwl_abort_notification_waits(&priv->notif_wait); - /* Keep the restart process from trying to send host * commands by clearing the ready bit */ clear_bit(STATUS_READY, &priv->status); @@ -1942,27 +1944,43 @@ static void iwlagn_fw_error(struct iwl_priv *priv, bool ondemand) } } -static void iwl_nic_error(struct iwl_op_mode *op_mode, bool sync) +static void iwl_nic_error(struct iwl_op_mode *op_mode, + enum iwl_fw_error_type type) { struct iwl_priv *priv = IWL_OP_MODE_GET_DVM(op_mode); + /* Set the FW error flag -- cleared on iwl_down */ + set_bit(STATUS_FW_ERROR, &priv->status); + + iwl_abort_notification_waits(&priv->notif_wait); + + if (type == IWL_ERR_TYPE_CMD_QUEUE_FULL && iwl_check_for_ct_kill(priv)) + return; + IWL_ERR(priv, "Loaded firmware version: %s\n", priv->fw->fw_version); - iwl_dump_nic_error_log(priv); - iwl_dump_nic_event_log(priv, false, NULL); + if (type == IWL_ERR_TYPE_CMD_QUEUE_FULL) { + IWL_ERR(priv, "Command queue full!\n"); + } else { + iwl_dump_nic_error_log(priv); + iwl_dump_nic_event_log(priv, false, NULL); + } - iwlagn_fw_error(priv, false); + if (iwl_have_debug_level(IWL_DL_FW)) + iwl_print_rx_config_cmd(priv, IWL_RXON_CTX_BSS); } -static void iwl_cmd_queue_full(struct iwl_op_mode *op_mode) +static bool iwlagn_sw_reset(struct iwl_op_mode *op_mode, + enum iwl_fw_error_type type) { struct iwl_priv *priv = IWL_OP_MODE_GET_DVM(op_mode); - if (!iwl_check_for_ct_kill(priv)) { - IWL_ERR(priv, "Restarting adapter queue is full\n"); - iwlagn_fw_error(priv, false); - } + if (type == IWL_ERR_TYPE_CMD_QUEUE_FULL && iwl_check_for_ct_kill(priv)) + return false; + + iwlagn_fw_error(priv, false); + return true; } #define EEPROM_RF_CONFIG_TYPE_MAX 0x3 @@ -2117,7 +2135,7 @@ static const struct iwl_op_mode_ops iwl_dvm_ops = { .hw_rf_kill = iwl_set_hw_rfkill_state, .free_skb = iwl_free_skb, .nic_error = iwl_nic_error, - .cmd_queue_full = iwl_cmd_queue_full, + .sw_reset = iwlagn_sw_reset, .nic_config = iwl_nic_config, .wimax_active = iwl_wimax_active, }; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 0bc32291815e..efa7b673ebc7 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -79,9 +79,9 @@ static void *iwl_acpi_get_object(struct device *dev, acpi_string method) * method (DSM) interface. The returned acpi object must be freed by calling * function. */ -static void *iwl_acpi_get_dsm_object(struct device *dev, int rev, int func, - union acpi_object *args, - const guid_t *guid) +union acpi_object *iwl_acpi_get_dsm_object(struct device *dev, int rev, + int func, union acpi_object *args, + const guid_t *guid) { union acpi_object *obj; @@ -108,7 +108,7 @@ static int iwl_acpi_get_dsm_integer(struct device *dev, int rev, int func, size_t expected_size) { union acpi_object *obj; - int ret = 0; + int ret; obj = iwl_acpi_get_dsm_object(dev, rev, func, NULL, guid); if (IS_ERR(obj)) { @@ -123,8 +123,10 @@ static int iwl_acpi_get_dsm_integer(struct device *dev, int rev, int func, } else if (obj->type == ACPI_TYPE_BUFFER) { __le64 le_value = 0; - if (WARN_ON_ONCE(expected_size > sizeof(le_value))) - return -EINVAL; + if (WARN_ON_ONCE(expected_size > sizeof(le_value))) { + ret = -EINVAL; + goto out; + } /* if the buffer size doesn't match the expected size */ if (obj->buffer.length != expected_size) @@ -145,8 +147,9 @@ static int iwl_acpi_get_dsm_integer(struct device *dev, int rev, int func, } IWL_DEBUG_DEV_RADIO(dev, - "ACPI: DSM method evaluated: func=%d, ret=%d\n", - func, ret); + "ACPI: DSM method evaluated: func=%d, value=%lld\n", + func, *value); + ret = 0; out: ACPI_FREE(obj); return ret; @@ -259,13 +262,14 @@ int iwl_acpi_get_tas_table(struct iwl_fw_runtime *fwrt, struct iwl_tas_data *tas_data) { union acpi_object *wifi_pkg, *data; - int ret, tbl_rev, i, block_list_size, enabled; + int ret, tbl_rev, block_list_size, enabled; + u32 tas_selection; data = iwl_acpi_get_object(fwrt->dev, ACPI_WTAS_METHOD); if (IS_ERR(data)) return PTR_ERR(data); - /* try to read wtas table revision 1 or revision 0*/ + /* try to read wtas table */ wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data, ACPI_WTAS_WIFI_DATA_SIZE, &tbl_rev); @@ -274,27 +278,23 @@ int iwl_acpi_get_tas_table(struct iwl_fw_runtime *fwrt, goto out_free; } - if (tbl_rev == 1 && wifi_pkg->package.elements[1].type == - ACPI_TYPE_INTEGER) { - u32 tas_selection = - (u32)wifi_pkg->package.elements[1].integer.value; - - enabled = iwl_parse_tas_selection(fwrt, tas_data, - tas_selection); - - } else if (tbl_rev == 0 && - wifi_pkg->package.elements[1].type == ACPI_TYPE_INTEGER) { - enabled = !!wifi_pkg->package.elements[1].integer.value; - } else { + if (tbl_rev < 0 || tbl_rev > 2 || + wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) { ret = -EINVAL; goto out_free; } - if (!enabled) { - IWL_DEBUG_RADIO(fwrt, "TAS not enabled\n"); - ret = 0; - goto out_free; - } + tas_selection = (u32)wifi_pkg->package.elements[1].integer.value; + enabled = tas_selection & IWL_WTAS_ENABLED_MSK; + + IWL_DEBUG_RADIO(fwrt, "TAS selection as read from BIOS: 0x%x\n", + tas_selection); + tas_data->table_source = BIOS_SOURCE_ACPI; + tas_data->table_revision = tbl_rev; + tas_data->tas_selection = tas_selection; + + IWL_DEBUG_RADIO(fwrt, "TAS %s enabled\n", + enabled ? "is" : "not"); IWL_DEBUG_RADIO(fwrt, "Reading TAS table revision %d\n", tbl_rev); if (wifi_pkg->package.elements[2].type != ACPI_TYPE_INTEGER || @@ -305,13 +305,14 @@ int iwl_acpi_get_tas_table(struct iwl_fw_runtime *fwrt, ret = -EINVAL; goto out_free; } + block_list_size = wifi_pkg->package.elements[2].integer.value; - tas_data->block_list_size = cpu_to_le32(block_list_size); + tas_data->block_list_size = block_list_size; IWL_DEBUG_RADIO(fwrt, "TAS array size %u\n", block_list_size); - for (i = 0; i < block_list_size; i++) { - u32 country; + for (int i = 0; i < block_list_size; i++) { + u16 country; if (wifi_pkg->package.elements[3 + i].type != ACPI_TYPE_INTEGER) { @@ -322,11 +323,11 @@ int iwl_acpi_get_tas_table(struct iwl_fw_runtime *fwrt, } country = wifi_pkg->package.elements[3 + i].integer.value; - tas_data->block_list_array[i] = cpu_to_le32(country); + tas_data->block_list_array[i] = country; IWL_DEBUG_RADIO(fwrt, "TAS block list country %d\n", country); } - ret = 1; + ret = enabled; out_free: kfree(data); return ret; @@ -1023,3 +1024,37 @@ out_free: kfree(data); return ret; } + +int iwl_acpi_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value) +{ + union acpi_object *wifi_pkg, *data; + int ret = -ENOENT; + int tbl_rev; + + data = iwl_acpi_get_object(fwrt->dev, ACPI_DSBR_METHOD); + if (IS_ERR(data)) + return ret; + + wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data, + ACPI_DSBR_WIFI_DATA_SIZE, + &tbl_rev); + if (IS_ERR(wifi_pkg)) + goto out_free; + + if (tbl_rev != ACPI_DSBR_WIFI_DATA_REV) { + IWL_DEBUG_RADIO(fwrt, "Unsupported ACPI DSBR revision:%d\n", + tbl_rev); + goto out_free; + } + + if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) + goto out_free; + + *value = wifi_pkg->package.elements[1].integer.value; + IWL_DEBUG_RADIO(fwrt, "Loaded DSBR config from ACPI value: 0x%x\n", + *value); + ret = 0; +out_free: + kfree(data); + return ret; +} diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h index bb88398a6987..e50b93472dd2 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h @@ -28,6 +28,7 @@ #define ACPI_WPFC_METHOD "WPFC" #define ACPI_GLAI_METHOD "GLAI" #define ACPI_WBEM_METHOD "WBEM" +#define ACPI_DSBR_METHOD "DSBR" #define ACPI_WIFI_DOMAIN (0x07) @@ -74,6 +75,13 @@ * and one for enablement of Wi-Fi 320MHz per MCC */ #define ACPI_WBEM_WIFI_DATA_SIZE 2 +/* + * One element for domain type, + * and one for DSBR response data + */ +#define ACPI_DSBR_WIFI_DATA_SIZE 2 +#define ACPI_DSBR_WIFI_DATA_REV 1 + /* * One element for domain type, * and one for the status @@ -101,6 +109,30 @@ #define ACPI_DSM_REV 0 +#define DSM_INTERNAL_FUNC_GET_PLAT_INFO 1 +/* TBD: VPRO is BIT(0) in the result, but what's the result? */ + +#define DSM_INTERNAL_FUNC_PRODUCT_RESET 2 + +/* DSM_INTERNAL_FUNC_PRODUCT_RESET - product reset (aka "PLDR") */ +enum iwl_dsm_internal_product_reset_cmds { + DSM_INTERNAL_PLDR_CMD_GET_MODE = 1, + DSM_INTERNAL_PLDR_CMD_SET_MODE = 2, + DSM_INTERNAL_PLDR_CMD_GET_STATUS = 3, +}; + +enum iwl_dsm_internal_product_reset_mode { + DSM_INTERNAL_PLDR_MODE_EN_PROD_RESET = BIT(0), + DSM_INTERNAL_PLDR_MODE_EN_WIFI_FLR = BIT(1), + DSM_INTERNAL_PLDR_MODE_EN_BT_OFF_ON = BIT(2), +}; + +struct iwl_dsm_internal_product_reset_cmd { + /* cmd is from enum iwl_dsm_internal_product_reset_cmds */ + u16 cmd; + u16 value; +} __packed; + #define IWL_ACPI_WBEM_REV0_MASK (BIT(0) | BIT(1)) #define IWL_ACPI_WBEM_REVISION 0 @@ -110,6 +142,10 @@ struct iwl_fw_runtime; extern const guid_t iwl_guid; +union acpi_object *iwl_acpi_get_dsm_object(struct device *dev, int rev, + int func, union acpi_object *args, + const guid_t *guid); + /** * iwl_acpi_get_mcc - read MCC from ACPI, if available * @@ -153,10 +189,14 @@ int iwl_acpi_get_dsm(struct iwl_fw_runtime *fwrt, enum iwl_dsm_funcs func, u32 *value); int iwl_acpi_get_wbem(struct iwl_fw_runtime *fwrt, u32 *value); + +int iwl_acpi_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value); + #else /* CONFIG_ACPI */ -static inline void *iwl_acpi_get_dsm_object(struct device *dev, int rev, - int func, union acpi_object *args) +static inline union acpi_object * +iwl_acpi_get_dsm_object(struct device *dev, int rev, int func, + union acpi_object *args, const guid_t *guid) { return ERR_PTR(-ENOENT); } @@ -221,6 +261,11 @@ static inline int iwl_acpi_get_wbem(struct iwl_fw_runtime *fwrt, u32 *value) { return -ENOENT; } + +static inline int iwl_acpi_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value) +{ + return -ENOENT; +} #endif /* CONFIG_ACPI */ #endif /* __iwl_fw_acpi__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h index 2f40e69db318..34a1f97653c0 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h @@ -447,7 +447,7 @@ enum iwl_legacy_cmds { /** * @BA_NOTIF: - * BlockAck notification, uses &struct iwl_mvm_compressed_ba_notif + * BlockAck notification, uses &struct iwl_compressed_ba_notif * or &struct iwl_mvm_ba_notif depending on the HW */ BA_NOTIF = 0xc5, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h index 2ab38eaeb290..570a3f722510 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h @@ -391,7 +391,7 @@ enum iwl_datapath_monitor_notif_type { struct iwl_datapath_monitor_notif { __le32 type; - u8 mac_id; + u8 link_id; u8 reserved[3]; } __packed; /* MONITOR_NTF_API_S_VER_1 */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h index bea0f4668cc8..aa88e91d117e 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h @@ -477,6 +477,9 @@ struct iwl_mvm_tas_status_per_mac { * @tas_status_mac: TAS status per lmac, uses * &struct iwl_mvm_tas_status_per_mac * @in_dual_radio: is TAS in dual radio? - TRUE/FALSE + * @uhb_allowed_flags: see &enum iwl_tas_uhb_allowed_flags. + * This member is valid only when fw has + * %IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT capability. * @reserved: reserved */ struct iwl_mvm_tas_status_resp { @@ -486,7 +489,8 @@ struct iwl_mvm_tas_status_resp { __le16 block_list[16]; struct iwl_mvm_tas_status_per_mac tas_status_mac[2]; u8 in_dual_radio; - u8 reserved[3]; + u8 uhb_allowed_flags; + u8 reserved[2]; } __packed; /*DEBUG_GET_TAS_STATUS_RSP_API_S_VER_3*/ /** diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h index b23d5fc4bbe6..37bb7002c1c9 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h @@ -74,7 +74,7 @@ enum iwl_mac_conf_subcmd_ids { */ ROC_NOTIF = 0xF8, /** - * @SESSION_PROTECTION_NOTIF: &struct iwl_mvm_session_prot_notif + * @SESSION_PROTECTION_NOTIF: &struct iwl_session_prot_notif */ SESSION_PROTECTION_NOTIF = 0xFB, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h index d424d0126367..5cdc09d465d4 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h @@ -463,22 +463,31 @@ struct iwl_tas_config_cmd_v3 { __le16 enable_tas_iec; } __packed; /* TAS_CONFIG_CMD_API_S_VER_3 */ +/** + * enum iwl_tas_uhb_allowed_flags - per country TAS UHB allowed flags. + * @TAS_UHB_ALLOWED_CANADA: TAS UHB is allowed in Canada. This flag is valid + * only when fw has %IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT capability. + */ +enum iwl_tas_uhb_allowed_flags { + TAS_UHB_ALLOWED_CANADA = BIT(0), +}; + /** * struct iwl_tas_config_cmd_v4 - configures the TAS * @override_tas_iec: indicates whether to override default value of IEC regulatory * @enable_tas_iec: in case override_tas_iec is set - * indicates whether IEC regulatory is enabled or disabled * @usa_tas_uhb_allowed: if set, allow TAS UHB in the USA - * @reserved: reserved -*/ + * @uhb_allowed_flags: see &enum iwl_tas_uhb_allowed_flags. + */ struct iwl_tas_config_cmd_v4 { u8 override_tas_iec; u8 enable_tas_iec; u8 usa_tas_uhb_allowed; - u8 reserved; + u8 uhb_allowed_flags; } __packed; /* TAS_CONFIG_CMD_API_S_VER_4 */ -struct iwl_tas_config_cmd { +struct iwl_tas_config_cmd_v2_v4 { struct iwl_tas_config_cmd_common common; union { struct iwl_tas_config_cmd_v3 v3; @@ -486,6 +495,46 @@ struct iwl_tas_config_cmd { }; }; +/** + * enum bios_source - source of bios data + * @BIOS_SOURCE_NONE: BIOS source is not defined + * @BIOS_SOURCE_ACPI: BIOS source is ACPI + * @BIOS_SOURCE_UEFI: BIOS source is UEFI + */ +enum bios_source { + BIOS_SOURCE_NONE, + BIOS_SOURCE_ACPI, + BIOS_SOURCE_UEFI, +}; + +/** + * struct bios_value_u32 - BIOS configuration. + * @table_source: see &enum bios_source + * @table_revision: table revision. + * @reserved: reserved + * @value: value in bios. + */ +struct bios_value_u32 { + u8 table_source; + u8 table_revision; + u8 reserved[2]; + __le32 value; +} __packed; /* BIOS_TABLE_SOURCE_U32_S_VER_1 */ + +/** + * struct iwl_tas_config_cmd - configures the TAS. + * @block_list_size: size of relevant field in block_list_array + * @block_list_array: list of countries where TAS must be disabled + * @reserved: reserved + * @tas_config_info: see @struct bios_value_u32 + */ +struct iwl_tas_config_cmd { + __le16 block_list_size; + __le16 block_list_array[IWL_WTAS_BLACK_LIST_MAX]; + u8 reserved[2]; + struct bios_value_u32 tas_config_info; +} __packed; /* TAS_CONFIG_CMD_API_S_VER_5 */ + /** * enum iwl_lari_config_masks - bit masks for the various LARI config operations * @LARI_CONFIG_DISABLE_11AC_UKRAINE_MSK: disable 11ac in ukraine diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/offload.h b/drivers/net/wireless/intel/iwlwifi/fw/api/offload.h index 6a7bbfd6b2b7..9b09b835560b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/offload.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/offload.h @@ -31,7 +31,7 @@ enum iwl_prot_offload_subcmd_ids { /** * @STORED_BEACON_NTF: &struct iwl_stored_beacon_notif_v2 or - * &struct iwl_stored_beacon_notif_v3 + * &struct iwl_stored_beacon_notif */ STORED_BEACON_NTF = 0xFF, }; @@ -71,18 +71,18 @@ struct iwl_stored_beacon_notif_v2 { } __packed; /* WOWLAN_STROED_BEACON_INFO_S_VER_2 */ /** - * struct iwl_stored_beacon_notif_v3 - Stored beacon notification + * struct iwl_stored_beacon_notif - Stored beacon notification * * @common: fields common for all versions * @sta_id: station for which the beacon was received * @reserved: reserved for alignment * @data: beacon data, length in @byte_count */ -struct iwl_stored_beacon_notif_v3 { +struct iwl_stored_beacon_notif { struct iwl_stored_beacon_notif_common common; u8 sta_id; u8 reserved[3]; u8 data[MAX_STORED_BEACON_SIZE]; -} __packed; /* WOWLAN_STROED_BEACON_INFO_S_VER_3 */ +} __packed; /* WOWLAN_STROED_BEACON_INFO_S_VER_3, _VER_4 */ #endif /* __iwl_fw_api_offload_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h index df0680eae30c..37ec26596ee7 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h @@ -266,7 +266,7 @@ struct iwl_reduce_tx_power_cmd { } __packed; /* TX_REDUCED_POWER_API_S_VER_1 */ enum iwl_dev_tx_power_cmd_mode { - IWL_TX_POWER_MODE_SET_MAC = 0, + IWL_TX_POWER_MODE_SET_LINK = 0, IWL_TX_POWER_MODE_SET_DEVICE = 1, IWL_TX_POWER_MODE_SET_CHAINS = 2, IWL_TX_POWER_MODE_SET_ACK = 3, @@ -283,12 +283,14 @@ enum iwl_dev_tx_power_cmd_mode { /** * struct iwl_dev_tx_power_common - Common part of the TX power reduction cmd * @set_mode: see &enum iwl_dev_tx_power_cmd_mode - * @mac_context_id: id of the mac ctx for which we are reducing TX power. + * @link_id: id of the link ctx for which we are reducing TX power. + * For version 9 / 10, this is the link id. For earlier versions, it is + * the mac id. * @pwr_restriction: TX power restriction in 1/8 dBms. */ struct iwl_dev_tx_power_common { __le32 set_mode; - __le32 mac_context_id; + __le32 link_id; __le16 pwr_restriction; } __packed; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h index 893438aadab0..cfa6532a3cdd 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2012-2014, 2018 Intel Corporation + * Copyright (C) 2012-2014, 2018, 2024 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -10,7 +10,7 @@ #include "fw/api/tx.h" #include "fw/api/phy-ctxt.h" -#define IWL_MVM_TDLS_STA_COUNT 4 +#define IWL_TDLS_STA_COUNT 4 /* Type of TDLS request */ enum iwl_tdls_channel_switch_type { @@ -128,7 +128,7 @@ struct iwl_tdls_config_cmd { u8 tdls_peer_count; u8 tx_to_ap_tid; __le16 tx_to_ap_ssn; - struct iwl_tdls_sta_info sta_info[IWL_MVM_TDLS_STA_COUNT]; + struct iwl_tdls_sta_info sta_info[IWL_TDLS_STA_COUNT]; __le32 pti_req_data_offset; struct iwl_tx_cmd pti_req_tx_cmd; @@ -155,7 +155,7 @@ struct iwl_tdls_config_sta_info_res { */ struct iwl_tdls_config_res { __le32 tx_to_ap_last_seq; - struct iwl_tdls_config_sta_info_res sta_info[IWL_MVM_TDLS_STA_COUNT]; + struct iwl_tdls_config_sta_info_res sta_info[IWL_TDLS_STA_COUNT]; } __packed; /* TDLS_CONFIG_RSP_API_S_VER_1 */ #endif /* __iwl_fw_api_tdls_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h index f4b827b58bd3..18d030334a6a 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h @@ -395,7 +395,7 @@ struct iwl_roc_notif { } __packed; /* ROC_NOTIF_API_S_VER_1 */ /** - * enum iwl_mvm_session_prot_conf_id - session protection's configurations + * enum iwl_session_prot_conf_id - session protection's configurations * @SESSION_PROTECT_CONF_ASSOC: Start a session protection for association. * The firmware will allocate two events. * Valid for BSS_STA and P2P_STA. @@ -424,7 +424,7 @@ struct iwl_roc_notif { * be taken into account. * @SESSION_PROTECT_CONF_MAX_ID: not used */ -enum iwl_mvm_session_prot_conf_id { +enum iwl_session_prot_conf_id { SESSION_PROTECT_CONF_ASSOC, SESSION_PROTECT_CONF_GO_CLIENT_ASSOC, SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV, @@ -433,12 +433,12 @@ enum iwl_mvm_session_prot_conf_id { }; /* SESSION_PROTECTION_CONF_ID_E_VER_1 */ /** - * struct iwl_mvm_session_prot_cmd - configure a session protection + * struct iwl_session_prot_cmd - configure a session protection * @id_and_color: the id and color of the link (or mac, for command version 1) * for which this session protection is sent * @action: can be either FW_CTXT_ACTION_ADD or FW_CTXT_ACTION_REMOVE, * see &enum iwl_ctxt_action - * @conf_id: see &enum iwl_mvm_session_prot_conf_id + * @conf_id: see &enum iwl_session_prot_conf_id * @duration_tu: the duration of the whole protection in TUs. * @repetition_count: not used * @interval: not used @@ -448,7 +448,7 @@ enum iwl_mvm_session_prot_conf_id { * The firmware supports only one concurrent session protection per vif. * Adding a new session protection will remove any currently running session. */ -struct iwl_mvm_session_prot_cmd { +struct iwl_session_prot_cmd { /* COMMON_INDEX_HDR_API_S_VER_1 hdr */ __le32 id_and_color; __le32 action; @@ -462,17 +462,17 @@ struct iwl_mvm_session_prot_cmd { */ /** - * struct iwl_mvm_session_prot_notif - session protection started / ended + * struct iwl_session_prot_notif - session protection started / ended * @mac_link_id: the mac id (or link id, for notif ver > 2) for which the * session protection started / ended * @status: 1 means success, 0 means failure * @start: 1 means the session protection started, 0 means it ended - * @conf_id: see &enum iwl_mvm_session_prot_conf_id + * @conf_id: see &enum iwl_session_prot_conf_id * * Note that any session protection will always get two notifications: start * and end even the firmware could not schedule it. */ -struct iwl_mvm_session_prot_notif { +struct iwl_session_prot_notif { __le32 mac_link_id; __le32 status; __le32 start; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h index f3bf2e087a40..0a39e4b6eb62 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h @@ -191,7 +191,7 @@ enum iwl_tx_offload_assist_flags_pos { * cleared. Combination of RATE_MCS_* * @sta_id: index of destination station in FW station table * @sec_ctl: security control, TX_CMD_SEC_* - * @initial_rate_index: index into the the rate table for initial TX attempt. + * @initial_rate_index: index into the rate table for initial TX attempt. * Applied if TX_CMD_FLG_STA_RATE_MSK is set, normally 0 for data frames. * @reserved2: reserved * @key: security key @@ -298,8 +298,7 @@ struct iwl_tx_cmd_gen3 { __le32 rate_n_flags; u8 reserved[8]; struct ieee80211_hdr hdr[]; -} __packed; /* TX_CMD_API_S_VER_8, - TX_CMD_API_S_VER_10 */ +} __packed; /* TX_CMD_API_S_VER_8, TX_CMD_API_S_VER_10 */ /* * TX response related data @@ -482,8 +481,8 @@ struct agg_tx_status { #define TX_RES_RATE_TABLE_COL_GET(_f) (((_f) & TX_RES_RATE_TABLE_COLOR_MSK) >>\ TX_RES_RATE_TABLE_COLOR_POS) -#define IWL_MVM_TX_RES_GET_TID(_ra_tid) ((_ra_tid) & 0x0f) -#define IWL_MVM_TX_RES_GET_RA(_ra_tid) ((_ra_tid) >> 4) +#define IWL_TX_RES_GET_TID(_ra_tid) ((_ra_tid) & 0x0f) +#define IWL_TX_RES_GET_RA(_ra_tid) ((_ra_tid) >> 4) /** * struct iwl_tx_resp_v3 - notifies that fw is TXing a packet @@ -601,7 +600,8 @@ struct iwl_tx_resp { __le16 reserved2; struct agg_tx_status status; } __packed; /* TX_RSP_API_S_VER_6, - TX_RSP_API_S_VER_7 */ + TX_RSP_API_S_VER_7, + TX_RSP_API_S_VER_8 */ /** * struct iwl_mvm_ba_notif - notifies about reception of BA @@ -638,14 +638,14 @@ struct iwl_mvm_ba_notif { } __packed; /** - * struct iwl_mvm_compressed_ba_tfd - progress of a TFD queue + * struct iwl_compressed_ba_tfd - progress of a TFD queue * @q_num: TFD queue number * @tfd_index: Index of first un-acked frame in the TFD queue * @scd_queue: For debug only - the physical queue the TFD queue is bound to * @tid: TID of the queue (0-7) * @reserved: reserved for alignment */ -struct iwl_mvm_compressed_ba_tfd { +struct iwl_compressed_ba_tfd { __le16 q_num; __le16 tfd_index; u8 scd_queue; @@ -654,12 +654,12 @@ struct iwl_mvm_compressed_ba_tfd { } __packed; /* COMPRESSED_BA_TFD_API_S_VER_1 */ /** - * struct iwl_mvm_compressed_ba_ratid - progress of a RA TID queue + * struct iwl_compressed_ba_ratid - progress of a RA TID queue * @q_num: RA TID queue number * @tid: TID of the queue * @ssn: BA window current SSN */ -struct iwl_mvm_compressed_ba_ratid { +struct iwl_compressed_ba_ratid { u8 q_num; u8 tid; __le16 ssn; @@ -685,7 +685,7 @@ enum iwl_mvm_ba_resp_flags { }; /** - * struct iwl_mvm_compressed_ba_notif - notifies about reception of BA + * struct iwl_compressed_ba_notif - notifies about reception of BA * ( BA_NOTIF = 0xc5 ) * @flags: status flag, see the &iwl_mvm_ba_resp_flags * @sta_id: Index of recipient (BA-sending) station in fw's station table @@ -704,12 +704,12 @@ enum iwl_mvm_ba_resp_flags { * @tx_rate: the rate the aggregation was sent at * @tfd_cnt: number of TFD-Q elements * @ra_tid_cnt: number of RATID-Q elements - * @tfd: array of TFD queue status updates. See &iwl_mvm_compressed_ba_tfd + * @tfd: array of TFD queue status updates. See &iwl_compressed_ba_tfd * for details. Length in @tfd_cnt. * @ra_tid: array of RA-TID queue status updates. For debug purposes only. See - * &iwl_mvm_compressed_ba_ratid for more details. Length in @ra_tid_cnt. + * &iwl_compressed_ba_ratid for more details. Length in @ra_tid_cnt. */ -struct iwl_mvm_compressed_ba_notif { +struct iwl_compressed_ba_notif { __le32 flags; u8 sta_id; u8 reduced_txp; @@ -726,8 +726,8 @@ struct iwl_mvm_compressed_ba_notif { __le16 tfd_cnt; __le16 ra_tid_cnt; union { - DECLARE_FLEX_ARRAY(struct iwl_mvm_compressed_ba_ratid, ra_tid); - DECLARE_FLEX_ARRAY(struct iwl_mvm_compressed_ba_tfd, tfd); + DECLARE_FLEX_ARRAY(struct iwl_compressed_ba_ratid, ra_tid); + DECLARE_FLEX_ARRAY(struct iwl_compressed_ba_tfd, tfd); }; } __packed; /* COMPRESSED_BA_RES_API_S_VER_4, COMPRESSED_BA_RES_API_S_VER_5 */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h index f4803b55adb9..87998374f459 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h @@ -287,7 +287,7 @@ static inline void iwl_fw_umac_set_alive_err_table(struct iwl_trans *trans, trans->dbg.umac_error_event_table = umac_error_event_table; } -static inline void iwl_fw_error_collect(struct iwl_fw_runtime *fwrt, bool sync) +static inline void iwl_fw_error_collect(struct iwl_fw_runtime *fwrt) { enum iwl_fw_ini_time_point tp_id; @@ -303,7 +303,7 @@ static inline void iwl_fw_error_collect(struct iwl_fw_runtime *fwrt, bool sync) tp_id = IWL_FW_INI_TIME_POINT_FW_ASSERT; } - _iwl_dbg_tlv_time_point(fwrt, tp_id, NULL, sync); + iwl_dbg_tlv_time_point_sync(fwrt, tp_id, NULL); } static inline void iwl_fwrt_update_fw_versions(struct iwl_fw_runtime *fwrt, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c index 893b21fcaf87..f0c813d675f4 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2023 Intel Corporation + * Copyright (C) 2012-2014, 2018-2024 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -123,6 +123,24 @@ static const struct file_operations iwl_dbgfs_##name##_ops = { \ #define FWRT_DEBUGFS_ADD_FILE(name, parent, mode) \ FWRT_DEBUGFS_ADD_FILE_ALIAS(#name, name, parent, mode) +static ssize_t iwl_dbgfs_fw_dbg_collect_write(struct iwl_fw_runtime *fwrt, + char *buf, size_t count) +{ + if (count == 0) + return 0; + + if (!iwl_trans_fw_running(fwrt->trans)) + return count; + + iwl_dbg_tlv_time_point(fwrt, IWL_FW_INI_TIME_POINT_USER_TRIGGER, NULL); + + iwl_fw_dbg_collect(fwrt, FW_DBG_TRIGGER_USER, buf, (count - 1), NULL); + + return count; +} + +FWRT_DEBUGFS_WRITE_FILE_OPS(fw_dbg_collect, 16); + static int iwl_dbgfs_enabled_severities_write(struct iwl_fw_runtime *fwrt, char *buf, size_t count) { @@ -282,6 +300,26 @@ static ssize_t iwl_dbgfs_fw_dbg_domain_read(struct iwl_fw_runtime *fwrt, FWRT_DEBUGFS_READ_FILE_OPS(fw_dbg_domain, 20); +static ssize_t iwl_dbgfs_fw_ver_read(struct iwl_fw_runtime *fwrt, + size_t size, char *buf) +{ + char *pos = buf; + char *endpos = buf + size; + + pos += scnprintf(pos, endpos - pos, "FW id: %s\n", + fwrt->fw->fw_version); + pos += scnprintf(pos, endpos - pos, "FW: %s\n", + fwrt->fw->human_readable); + pos += scnprintf(pos, endpos - pos, "Device: %s\n", + fwrt->trans->name); + pos += scnprintf(pos, endpos - pos, "Bus: %s\n", + fwrt->dev->bus->name); + + return pos - buf; +} + +FWRT_DEBUGFS_READ_FILE_OPS(fw_ver, 1024); + struct iwl_dbgfs_fw_info_priv { struct iwl_fw_runtime *fwrt; }; @@ -403,5 +441,7 @@ void iwl_fwrt_dbgfs_register(struct iwl_fw_runtime *fwrt, FWRT_DEBUGFS_ADD_FILE(fw_info, dbgfs_dir, 0200); FWRT_DEBUGFS_ADD_FILE(send_hcmd, dbgfs_dir, 0200); FWRT_DEBUGFS_ADD_FILE(enabled_severities, dbgfs_dir, 0200); + FWRT_DEBUGFS_ADD_FILE(fw_dbg_collect, dbgfs_dir, 0200); FWRT_DEBUGFS_ADD_FILE(fw_dbg_domain, dbgfs_dir, 0400); + FWRT_DEBUGFS_ADD_FILE(fw_ver, dbgfs_dir, 0400); } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h index e63b08b7d336..3af275133da0 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h @@ -169,7 +169,7 @@ struct iwl_fw_error_dump_info { * @fw_mon_wr_ptr: the position of the write pointer in the cyclic buffer * @fw_mon_base_ptr: base pointer of the data * @fw_mon_cycle_cnt: number of wraparounds - * @fw_mon_base_high_ptr: used in AX210 devices, the base adderss is 64 bit + * @fw_mon_base_high_ptr: used in AX210 devices, the base address is 64 bit * so fw_mon_base_ptr holds LSB 32 bits and fw_mon_base_high_ptr hold * MSB 32 bits * @reserved: for future use diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h index ae05227b6153..9860903ecd3f 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/file.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h @@ -104,6 +104,7 @@ enum iwl_ucode_tlv_type { IWL_UCODE_TLV_CURRENT_PC = 68, IWL_UCODE_TLV_FW_NUM_STATIONS = IWL_UCODE_TLV_CONST_BASE + 0, + IWL_UCODE_TLV_FW_NUM_LINKS = IWL_UCODE_TLV_CONST_BASE + 1, IWL_UCODE_TLV_FW_NUM_BEACONS = IWL_UCODE_TLV_CONST_BASE + 2, IWL_UCODE_TLV_TYPE_DEBUG_INFO = IWL_UCODE_TLV_DEBUG_BASE + 0, @@ -384,7 +385,8 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * to report the CSI information with (certain) RX frames * @IWL_UCODE_TLV_CAPA_FTM_CALIBRATED: has FTM calibrated and thus supports both * initiator and responder - * @IWL_UCODE_TLV_CAPA_MLME_OFFLOAD: supports MLME offload + * @IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_UNII4_US_CA: supports (de)activating UNII-4 + * for US/CA/WW from BIOS * @IWL_UCODE_TLV_CAPA_PROTECTED_TWT: Supports protection of TWT action frames * @IWL_UCODE_TLV_CAPA_FW_RESET_HANDSHAKE: Supports the firmware handshake in * reset flow @@ -397,6 +399,9 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * @IWL_UCODE_TLV_CAPA_SECURE_LTF_SUPPORT: Support secure LTF measurement. * @IWL_UCODE_TLV_CAPA_MONITOR_PASSIVE_CHANS: Support monitor mode on otherwise * passive channels + * @IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_5G9_FOR_CA: supports (de)activating 5G9 + * for CA from BIOS. + * @IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT: supports %TAS_UHB_ALLOWED_CANADA * * @NUM_IWL_UCODE_TLV_CAPA: number of bits used */ @@ -474,7 +479,7 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_DBG_BUF_ALLOC_CMD_SUPP = (__force iwl_ucode_tlv_capa_t)93, /* set 3 */ - IWL_UCODE_TLV_CAPA_MLME_OFFLOAD = (__force iwl_ucode_tlv_capa_t)96, + IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_UNII4_US_CA = (__force iwl_ucode_tlv_capa_t)96, /* * @IWL_UCODE_TLV_CAPA_PSC_CHAN_SUPPORT: supports PSC channels @@ -497,6 +502,8 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_CHINA_22_REG_SUPPORT = (__force iwl_ucode_tlv_capa_t)117, IWL_UCODE_TLV_CAPA_SECURE_LTF_SUPPORT = (__force iwl_ucode_tlv_capa_t)121, IWL_UCODE_TLV_CAPA_MONITOR_PASSIVE_CHANS = (__force iwl_ucode_tlv_capa_t)122, + IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_5G9_FOR_CA = (__force iwl_ucode_tlv_capa_t)123, + IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT = (__force iwl_ucode_tlv_capa_t)124, NUM_IWL_UCODE_TLV_CAPA /* * This construction make both sparse (which cannot increment the previous diff --git a/drivers/net/wireless/intel/iwlwifi/fw/img.c b/drivers/net/wireless/intel/iwlwifi/fw/img.c index b7deca05a953..c2f4fc83a22c 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/img.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/img.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Copyright(c) 2019 - 2021 Intel Corporation + * Copyright(c) 2024 Intel Corporation */ #include #include "img.h" @@ -75,6 +76,7 @@ static const struct { { "NMI_INTERRUPT_ACTION_PT", 0x7C }, { "NMI_INTERRUPT_UNKNOWN", 0x84 }, { "NMI_INTERRUPT_INST_ACTION_PT", 0x86 }, + { "NMI_INTERRUPT_PREG", 0x88 }, { "PNVM_MISSING", FW_SYSASSERT_PNVM_MISSING }, { "ADVANCED_SYSASSERT", 0 }, }; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/img.h b/drivers/net/wireless/intel/iwlwifi/fw/img.h index 96bda80632f3..f9de139561a0 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/img.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/img.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2005-2014, 2018-2023 Intel Corporation + * Copyright (C) 2005-2014, 2018-2024 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016 Intel Deutschland GmbH */ @@ -51,6 +51,7 @@ struct iwl_ucode_capabilities { u32 error_log_addr; u32 error_log_size; u32 num_stations; + u32 num_links; u32 num_beacons; unsigned long _api[BITS_TO_LONGS(NUM_IWL_UCODE_TLV_API)]; unsigned long _capa[BITS_TO_LONGS(NUM_IWL_UCODE_TLV_CAPA)]; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/paging.c b/drivers/net/wireless/intel/iwlwifi/fw/paging.c index 945bc4160cc9..a7b7cae874a2 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/paging.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/paging.c @@ -249,7 +249,7 @@ static int iwl_send_paging_cmd(struct iwl_fw_runtime *fwrt, }; int blk_idx; - /* loop for for all paging blocks + CSS block */ + /* loop for all paging blocks + CSS block */ for (blk_idx = 0; blk_idx < fwrt->num_of_paging_blk + 1; blk_idx++) { dma_addr_t addr = fwrt->fw_paging_db[blk_idx].fw_paging_phys; __le32 phy_addr; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c index 4d9a1f83ef8c..ea435ee94312 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c @@ -39,6 +39,7 @@ IWL_BIOS_TABLE_LOADER_DATA(pwr_limit, u64); IWL_BIOS_TABLE_LOADER_DATA(mcc, char); IWL_BIOS_TABLE_LOADER_DATA(eckv, u32); IWL_BIOS_TABLE_LOADER_DATA(wbem, u32); +IWL_BIOS_TABLE_LOADER_DATA(dsbr, u32); static const struct dmi_system_id dmi_ppag_approved_list[] = { @@ -100,6 +101,11 @@ static const struct dmi_system_id dmi_ppag_approved_list[] = { DMI_MATCH(DMI_SYS_VENDOR, "HONOR"), }, }, + { .ident = "WIKO", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "WIKO"), + }, + }, {} }; @@ -424,25 +430,31 @@ bool iwl_is_tas_approved(void) } IWL_EXPORT_SYMBOL(iwl_is_tas_approved); -int iwl_parse_tas_selection(struct iwl_fw_runtime *fwrt, - struct iwl_tas_data *tas_data, - const u32 tas_selection) +struct iwl_tas_selection_data +iwl_parse_tas_selection(const u32 tas_selection_in, const u8 tbl_rev) { - u8 override_iec = u32_get_bits(tas_selection, + struct iwl_tas_selection_data tas_selection_out = {}; + u8 override_iec = u32_get_bits(tas_selection_in, IWL_WTAS_OVERRIDE_IEC_MSK); - u8 enabled_iec = u32_get_bits(tas_selection, IWL_WTAS_ENABLE_IEC_MSK); - u8 usa_tas_uhb = u32_get_bits(tas_selection, IWL_WTAS_USA_UHB_MSK); - int enabled = tas_selection & IWL_WTAS_ENABLED_MSK; + u8 canada_tas_uhb = u32_get_bits(tas_selection_in, + IWL_WTAS_CANADA_UHB_MSK); + u8 enabled_iec = u32_get_bits(tas_selection_in, + IWL_WTAS_ENABLE_IEC_MSK); + u8 usa_tas_uhb = u32_get_bits(tas_selection_in, + IWL_WTAS_USA_UHB_MSK); - IWL_DEBUG_RADIO(fwrt, "TAS selection as read from BIOS: 0x%x\n", - tas_selection); + if (tbl_rev > 0) { + tas_selection_out.usa_tas_uhb_allowed = usa_tas_uhb; + tas_selection_out.override_tas_iec = override_iec; + tas_selection_out.enable_tas_iec = enabled_iec; + } - tas_data->usa_tas_uhb_allowed = usa_tas_uhb; - tas_data->override_tas_iec = override_iec; - tas_data->enable_tas_iec = enabled_iec; + if (tbl_rev > 1) + tas_selection_out.canada_tas_uhb_allowed = canada_tas_uhb; - return enabled; + return tas_selection_out; } +IWL_EXPORT_SYMBOL(iwl_parse_tas_selection); static __le32 iwl_get_lari_config_bitmap(struct iwl_fw_runtime *fwrt) { @@ -552,10 +564,16 @@ int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt, ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ENABLE_UNII4_CHAN, &value); if (!ret) { - if (cmd_ver < 9) - value &= DSM_UNII4_ALLOW_BITMAP_CMD_V8; - else - value &= DSM_UNII4_ALLOW_BITMAP; + value &= DSM_UNII4_ALLOW_BITMAP; + + /* Since version 9, bits 4 and 5 are supported + * regardless of this capability. + */ + if (cmd_ver < 9 && + !fw_has_capa(&fwrt->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_5G9_FOR_CA)) + value &= ~(DSM_VALUE_UNII4_CANADA_OVERRIDE_MSK | + DSM_VALUE_UNII4_CANADA_EN_MSK); cmd->oem_unii4_allow_bitmap = cpu_to_le32(value); } @@ -564,7 +582,13 @@ int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt, if (!ret) { if (cmd_ver < 8) value &= ~ACTIVATE_5G2_IN_WW_MASK; - if (cmd_ver < 12) + + /* Since version 12, bits 5 and 6 are supported + * regardless of this capability. + */ + if (cmd_ver < 12 && + !fw_has_capa(&fwrt->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_UNII4_US_CA)) value &= CHAN_STATE_ACTIVE_BITMAP_CMD_V11; cmd->chan_state_active_bitmap = cpu_to_le32(value); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h index 81787501d4a4..b355d7bef14c 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h @@ -40,11 +40,19 @@ #define IWL_PPAG_ETSI_CHINA_MASK 3 #define IWL_PPAG_REV3_MASK 0x7FF -#define IWL_WTAS_ENABLED_MSK 0x1 -#define IWL_WTAS_OVERRIDE_IEC_MSK 0x2 -#define IWL_WTAS_ENABLE_IEC_MSK 0x4 +#define IWL_WTAS_ENABLED_MSK BIT(0) +#define IWL_WTAS_OVERRIDE_IEC_MSK BIT(1) +#define IWL_WTAS_ENABLE_IEC_MSK BIT(2) +#define IWL_WTAS_CANADA_UHB_MSK BIT(15) #define IWL_WTAS_USA_UHB_MSK BIT(16) +struct iwl_tas_selection_data { + u8 override_tas_iec:1, + enable_tas_iec:1, + usa_tas_uhb_allowed:1, + canada_tas_uhb_allowed:1; +}; + #define BIOS_MCC_CHINA 0x434e /* @@ -97,11 +105,11 @@ struct iwl_ppag_chain { }; struct iwl_tas_data { - __le32 block_list_size; - __le32 block_list_array[IWL_WTAS_BLACK_LIST_MAX]; - u8 override_tas_iec; - u8 enable_tas_iec; - u8 usa_tas_uhb_allowed; + u8 block_list_size; + u16 block_list_array[IWL_WTAS_BLACK_LIST_MAX]; + u8 table_source; + u8 table_revision; + u32 tas_selection; }; /* For DSM revision 0 and 4 */ @@ -144,12 +152,11 @@ enum iwl_dsm_unii4_bitmap { DSM_VALUE_UNII4_CANADA_EN_MSK = BIT(5), }; -#define DSM_UNII4_ALLOW_BITMAP_CMD_V8 (DSM_VALUE_UNII4_US_OVERRIDE_MSK | \ - DSM_VALUE_UNII4_US_EN_MSK | \ - DSM_VALUE_UNII4_ETSI_OVERRIDE_MSK | \ - DSM_VALUE_UNII4_ETSI_EN_MSK) -#define DSM_UNII4_ALLOW_BITMAP (DSM_UNII4_ALLOW_BITMAP_CMD_V8 | \ - DSM_VALUE_UNII4_CANADA_OVERRIDE_MSK | \ +#define DSM_UNII4_ALLOW_BITMAP (DSM_VALUE_UNII4_US_OVERRIDE_MSK |\ + DSM_VALUE_UNII4_US_EN_MSK |\ + DSM_VALUE_UNII4_ETSI_OVERRIDE_MSK |\ + DSM_VALUE_UNII4_ETSI_EN_MSK |\ + DSM_VALUE_UNII4_CANADA_OVERRIDE_MSK |\ DSM_VALUE_UNII4_CANADA_EN_MSK) enum iwl_dsm_values_rfi { @@ -184,9 +191,8 @@ bool iwl_is_ppag_approved(struct iwl_fw_runtime *fwrt); bool iwl_is_tas_approved(void); -int iwl_parse_tas_selection(struct iwl_fw_runtime *fwrt, - struct iwl_tas_data *tas_data, - const u32 tas_selection); +struct iwl_tas_selection_data +iwl_parse_tas_selection(const u32 tas_selection, const u8 tbl_rev); int iwl_bios_get_wrds_table(struct iwl_fw_runtime *fwrt); @@ -221,4 +227,27 @@ static inline u32 iwl_bios_get_ppag_flags(const u32 ppag_modes, } bool iwl_puncturing_is_allowed_in_bios(u32 puncturing, u16 mcc); + +#define IWL_DSBR_FW_MODIFIED_URM_MASK BIT(8) +#define IWL_DSBR_PERMANENT_URM_MASK BIT(9) + +int iwl_bios_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value); + +static inline void iwl_bios_setup_step(struct iwl_trans *trans, + struct iwl_fw_runtime *fwrt) +{ + u32 dsbr; + + if (!trans->trans_cfg->integrated) + return; + + if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ) + return; + + if (iwl_bios_get_dsbr(fwrt, &dsbr)) + dsbr = 0; + + trans->dsbr_urm_fw_dependent = !!(dsbr & IWL_DSBR_FW_MODIFIED_URM_MASK); + trans->dsbr_urm_permanent = !!(dsbr & IWL_DSBR_PERMANENT_URM_MASK); +} #endif /* __fw_regulatory_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c index 091fb6fd7c78..434eed4130b9 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c @@ -13,9 +13,12 @@ #include #include "fw/runtime.h" -#define IWL_EFI_VAR_GUID EFI_GUID(0x92daaf2f, 0xc02b, 0x455b, \ - 0xb2, 0xec, 0xf5, 0xa3, \ - 0x59, 0x4f, 0x4a, 0xea) +#define IWL_EFI_WIFI_GUID EFI_GUID(0x92daaf2f, 0xc02b, 0x455b, \ + 0xb2, 0xec, 0xf5, 0xa3, \ + 0x59, 0x4f, 0x4a, 0xea) +#define IWL_EFI_WIFI_BT_GUID EFI_GUID(0xe65d8884, 0xd4af, 0x4b20, \ + 0x8d, 0x03, 0x77, 0x2e, \ + 0xcc, 0x3d, 0xa5, 0x31) struct iwl_uefi_pnvm_mem_desc { __le32 addr; @@ -61,7 +64,7 @@ void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len) *len = 0; - data = iwl_uefi_get_variable(IWL_UEFI_OEM_PNVM_NAME, &IWL_EFI_VAR_GUID, + data = iwl_uefi_get_variable(IWL_UEFI_OEM_PNVM_NAME, &IWL_EFI_WIFI_GUID, &package_size); if (IS_ERR(data)) { IWL_DEBUG_FW(trans, @@ -76,18 +79,18 @@ void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len) return data; } -static -void *iwl_uefi_get_verified_variable(struct iwl_trans *trans, - efi_char16_t *uefi_var_name, - char *var_name, - unsigned int expected_size, - unsigned long *size) +static void * +iwl_uefi_get_verified_variable_guid(struct iwl_trans *trans, + efi_guid_t *guid, + efi_char16_t *uefi_var_name, + char *var_name, + unsigned int expected_size, + unsigned long *size) { void *var; unsigned long var_size; - var = iwl_uefi_get_variable(uefi_var_name, &IWL_EFI_VAR_GUID, - &var_size); + var = iwl_uefi_get_variable(uefi_var_name, guid, &var_size); if (IS_ERR(var)) { IWL_DEBUG_RADIO(trans, @@ -112,6 +115,18 @@ void *iwl_uefi_get_verified_variable(struct iwl_trans *trans, return var; } +static void * +iwl_uefi_get_verified_variable(struct iwl_trans *trans, + efi_char16_t *uefi_var_name, + char *var_name, + unsigned int expected_size, + unsigned long *size) +{ + return iwl_uefi_get_verified_variable_guid(trans, &IWL_EFI_WIFI_GUID, + uefi_var_name, var_name, + expected_size, size); +} + int iwl_uefi_handle_tlv_mem_desc(struct iwl_trans *trans, const u8 *data, u32 tlv_len, struct iwl_pnvm_image *pnvm_data) { @@ -311,8 +326,9 @@ void iwl_uefi_get_step_table(struct iwl_trans *trans) if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210) return; - data = iwl_uefi_get_verified_variable(trans, IWL_UEFI_STEP_NAME, - "STEP", sizeof(*data), NULL); + data = iwl_uefi_get_verified_variable_guid(trans, &IWL_EFI_WIFI_BT_GUID, + IWL_UEFI_STEP_NAME, + "STEP", sizeof(*data), NULL); if (IS_ERR(data)) return; @@ -554,27 +570,31 @@ int iwl_uefi_get_tas_table(struct iwl_fw_runtime *fwrt, struct iwl_tas_data *tas_data) { struct uefi_cnv_var_wtas *uefi_tas; - int ret = 0, enabled, i; + int ret, enabled; uefi_tas = iwl_uefi_get_verified_variable(fwrt->trans, IWL_UEFI_WTAS_NAME, "WTAS", sizeof(*uefi_tas), NULL); if (IS_ERR(uefi_tas)) return -EINVAL; - if (uefi_tas->revision != IWL_UEFI_WTAS_REVISION) { + if (uefi_tas->revision < IWL_UEFI_MIN_WTAS_REVISION || + uefi_tas->revision > IWL_UEFI_MAX_WTAS_REVISION) { ret = -EINVAL; IWL_DEBUG_RADIO(fwrt, "Unsupported UEFI WTAS revision:%d\n", uefi_tas->revision); goto out; } - enabled = iwl_parse_tas_selection(fwrt, tas_data, - uefi_tas->tas_selection); - if (!enabled) { - IWL_DEBUG_RADIO(fwrt, "TAS not enabled\n"); - ret = 0; - goto out; - } + IWL_DEBUG_RADIO(fwrt, "TAS selection as read from BIOS: 0x%x\n", + uefi_tas->tas_selection); + + enabled = uefi_tas->tas_selection & IWL_WTAS_ENABLED_MSK; + tas_data->table_source = BIOS_SOURCE_UEFI; + tas_data->table_revision = uefi_tas->revision; + tas_data->tas_selection = uefi_tas->tas_selection; + + IWL_DEBUG_RADIO(fwrt, "TAS %s enabled\n", + enabled ? "is" : "not"); IWL_DEBUG_RADIO(fwrt, "Reading TAS table revision %d\n", uefi_tas->revision); @@ -584,15 +604,16 @@ int iwl_uefi_get_tas_table(struct iwl_fw_runtime *fwrt, ret = -EINVAL; goto out; } - tas_data->block_list_size = cpu_to_le32(uefi_tas->black_list_size); + + tas_data->block_list_size = uefi_tas->black_list_size; IWL_DEBUG_RADIO(fwrt, "TAS array size %u\n", uefi_tas->black_list_size); - for (i = 0; i < uefi_tas->black_list_size; i++) { - tas_data->block_list_array[i] = - cpu_to_le32(uefi_tas->black_list[i]); + for (u8 i = 0; i < uefi_tas->black_list_size; i++) { + tas_data->block_list_array[i] = uefi_tas->black_list[i]; IWL_DEBUG_RADIO(fwrt, "TAS block list country %d\n", uefi_tas->black_list[i]); } + ret = enabled; out: kfree(uefi_tas); return ret; @@ -758,3 +779,29 @@ int iwl_uefi_get_puncturing(struct iwl_fw_runtime *fwrt) return puncturing; } IWL_EXPORT_SYMBOL(iwl_uefi_get_puncturing); + +int iwl_uefi_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value) +{ + struct uefi_cnv_wlan_dsbr_data *data; + int ret = 0; + + data = iwl_uefi_get_verified_variable_guid(fwrt->trans, + &IWL_EFI_WIFI_BT_GUID, + IWL_UEFI_DSBR_NAME, "DSBR", + sizeof(*data), NULL); + if (IS_ERR(data)) + return -EINVAL; + + if (data->revision != IWL_UEFI_DSBR_REVISION) { + ret = -EINVAL; + IWL_DEBUG_RADIO(fwrt, "Unsupported UEFI DSBR revision:%d\n", + data->revision); + goto out; + } + *value = data->config; + IWL_DEBUG_RADIO(fwrt, "Loaded DSBR config from UEFI value: 0x%x\n", + *value); +out: + kfree(data); + return ret; +} diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h index e525d449e656..0c8943a8bd01 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h @@ -23,6 +23,7 @@ #define IWL_UEFI_DSM_NAME L"UefiCnvWlanGeneralCfg" #define IWL_UEFI_WBEM_NAME L"UefiCnvWlanWBEM" #define IWL_UEFI_PUNCTURING_NAME L"UefiCnvWlanPuncturing" +#define IWL_UEFI_DSBR_NAME L"UefiCnvCommonDSBR" #define IWL_SGOM_MAP_SIZE 339 @@ -33,13 +34,15 @@ #define IWL_UEFI_WGDS_REVISION 3 #define IWL_UEFI_MIN_PPAG_REV 1 #define IWL_UEFI_MAX_PPAG_REV 3 -#define IWL_UEFI_WTAS_REVISION 1 +#define IWL_UEFI_MIN_WTAS_REVISION 1 +#define IWL_UEFI_MAX_WTAS_REVISION 2 #define IWL_UEFI_SPLC_REVISION 0 #define IWL_UEFI_WRDD_REVISION 0 #define IWL_UEFI_ECKV_REVISION 0 #define IWL_UEFI_WBEM_REVISION 0 #define IWL_UEFI_DSM_REVISION 4 #define IWL_UEFI_PUNCTURING_REVISION 0 +#define IWL_UEFI_DSBR_REVISION 1 struct pnvm_sku_package { u8 rev; @@ -213,6 +216,20 @@ struct uefi_cnv_var_puncturing_data { u32 puncturing; } __packed; +/** + * struct uefi_cnv_wlan_dsbr_data - BIOS STEP configuration information + * @revision: the revision of the table + * @config: STEP configuration flags: + * bit 8, switch to URM depending on FW setting + * bit 9, switch to URM + * + * Platform information for STEP configuration/workarounds. + */ +struct uefi_cnv_wlan_dsbr_data { + u8 revision; + u32 config; +} __packed; + /* * This is known to be broken on v4.19 and to work on v5.4. Until we * figure out why this is the case and how to make it work, simply @@ -244,6 +261,7 @@ void iwl_uefi_get_sgom_table(struct iwl_trans *trans, struct iwl_fw_runtime *fwr int iwl_uefi_get_uats_table(struct iwl_trans *trans, struct iwl_fw_runtime *fwrt); int iwl_uefi_get_puncturing(struct iwl_fw_runtime *fwrt); +int iwl_uefi_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value); #else /* CONFIG_EFI */ static inline void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len) { @@ -346,5 +364,11 @@ int iwl_uefi_get_puncturing(struct iwl_fw_runtime *fwrt) { return 0; } + +static inline +int iwl_uefi_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value) +{ + return -ENOENT; +} #endif /* CONFIG_EFI */ #endif /* __iwl_fw_uefi__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 34c91deca57b..2b6a80142aba 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -38,6 +38,7 @@ enum iwl_device_family { IWL_DEVICE_FAMILY_AX210, IWL_DEVICE_FAMILY_BZ, IWL_DEVICE_FAMILY_SC, + IWL_DEVICE_FAMILY_DR, }; /* @@ -102,6 +103,10 @@ enum iwl_nvm_type { #define ANT_ABC (ANT_A | ANT_B | ANT_C) +#define IWL_FW_AND_PNVM(pfx, api) \ + MODULE_FIRMWARE(pfx "-" __stringify(api) ".ucode"); \ + MODULE_FIRMWARE(pfx ".pnvm") + static inline u8 num_of_ant(u8 mask) { return !!((mask) & ANT_A) + @@ -424,6 +429,8 @@ struct iwl_cfg { #define IWL_CFG_MAC_TYPE_SC2 0x49 #define IWL_CFG_MAC_TYPE_SC2F 0x4A #define IWL_CFG_MAC_TYPE_BZ_W 0x4B +#define IWL_CFG_MAC_TYPE_BR 0x4C +#define IWL_CFG_MAC_TYPE_DR 0x4D #define IWL_CFG_RF_TYPE_TH 0x105 #define IWL_CFG_RF_TYPE_TH1 0x108 @@ -434,6 +441,7 @@ struct iwl_cfg { #define IWL_CFG_RF_TYPE_GF 0x10D #define IWL_CFG_RF_TYPE_FM 0x112 #define IWL_CFG_RF_TYPE_WH 0x113 +#define IWL_CFG_RF_TYPE_PE 0x114 #define IWL_CFG_RF_ID_TH 0x1 #define IWL_CFG_RF_ID_TH1 0x1 @@ -506,6 +514,8 @@ extern const struct iwl_cfg_trans_params iwl_ma_trans_cfg; extern const struct iwl_cfg_trans_params iwl_bz_trans_cfg; extern const struct iwl_cfg_trans_params iwl_gl_trans_cfg; extern const struct iwl_cfg_trans_params iwl_sc_trans_cfg; +extern const struct iwl_cfg_trans_params iwl_dr_trans_cfg; +extern const struct iwl_cfg_trans_params iwl_br_trans_cfg; extern const char iwl9162_name[]; extern const char iwl9260_name[]; extern const char iwl9260_1_name[]; @@ -545,11 +555,14 @@ extern const char iwl_ax231_name[]; extern const char iwl_ax411_name[]; extern const char iwl_bz_name[]; extern const char iwl_fm_name[]; +extern const char iwl_wh_name[]; extern const char iwl_gl_name[]; extern const char iwl_mtp_name[]; extern const char iwl_sc_name[]; extern const char iwl_sc2_name[]; extern const char iwl_sc2f_name[]; +extern const char iwl_dr_name[]; +extern const char iwl_br_name[]; #if IS_ENABLED(CONFIG_IWLDVM) extern const struct iwl_cfg iwl5300_agn_cfg; extern const struct iwl_cfg iwl5100_agn_cfg; @@ -648,7 +661,6 @@ extern const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0_long; extern const struct iwl_cfg iwl_cfg_ma; extern const struct iwl_cfg iwl_cfg_so_a0_hr_a0; -extern const struct iwl_cfg iwl_cfg_so_a0_ms_a0; extern const struct iwl_cfg iwl_cfg_quz_a0_hr_b0; extern const struct iwl_cfg iwl_cfg_bz; @@ -657,6 +669,8 @@ extern const struct iwl_cfg iwl_cfg_gl; extern const struct iwl_cfg iwl_cfg_sc; extern const struct iwl_cfg iwl_cfg_sc2; extern const struct iwl_cfg iwl_cfg_sc2f; +extern const struct iwl_cfg iwl_cfg_dr; +extern const struct iwl_cfg iwl_cfg_br; #endif /* CONFIG_IWLMVM */ #endif /* __IWL_CONFIG_H__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h index 5b62933134cf..cd25a1b9f2ff 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h @@ -76,7 +76,17 @@ enum iwl_prph_scratch_flags { IWL_PRPH_SCRATCH_SCU_FORCE_ACTIVE = BIT(29), }; -/* +/** + * enum iwl_prph_scratch_ext_flags - PRPH scratch control ext flags + * @IWL_PRPH_SCRATCH_EXT_URM_FW: switch to URM mode based on fw setting + * @IWL_PRPH_SCRATCH_EXT_URM_PERM: switch to permanent URM mode + */ +enum iwl_prph_scratch_ext_flags { + IWL_PRPH_SCRATCH_EXT_URM_FW = BIT(4), + IWL_PRPH_SCRATCH_EXT_URM_PERM = BIT(5), +}; + +/** * struct iwl_prph_scratch_version - version structure * @mac_id: SKU and revision id * @version: prph scratch information version id @@ -90,17 +100,18 @@ struct iwl_prph_scratch_version { __le16 reserved; } __packed; /* PERIPH_SCRATCH_VERSION_S */ -/* +/** * struct iwl_prph_scratch_control - control structure * @control_flags: context information flags see &enum iwl_prph_scratch_flags - * @reserved: reserved + * @control_flags_ext: context information for extended flags, + * see &enum iwl_prph_scratch_ext_flags */ struct iwl_prph_scratch_control { __le32 control_flags; - __le32 reserved; + __le32 control_flags_ext; } __packed; /* PERIPH_SCRATCH_CONTROL_S */ -/* +/** * struct iwl_prph_scratch_pnvm_cfg - PNVM scratch * @pnvm_base_addr: PNVM start address * @pnvm_size: the size of the PNVM image in bytes @@ -120,7 +131,8 @@ struct iwl_prph_scratch_pnvm_cfg { struct iwl_prph_scrath_mem_desc_addr_array { __le64 mem_descs[IPC_DRAM_MAP_ENTRY_NUM_MAX]; } __packed; /* PERIPH_SCRATCH_MEM_DESC_ADDR_ARRAY_S_VER_1 */ -/* + +/** * struct iwl_prph_scratch_hwm_cfg - hwm config * @hwm_base_addr: hwm start address * @hwm_size: hwm size in DWs @@ -132,7 +144,7 @@ struct iwl_prph_scratch_hwm_cfg { __le32 debug_token_config; } __packed; /* PERIPH_SCRATCH_HWM_CFG_S */ -/* +/** * struct iwl_prph_scratch_rbd_cfg - RBDs configuration * @free_rbd_addr: default queue free RB CB base address * @reserved: reserved @@ -142,10 +154,11 @@ struct iwl_prph_scratch_rbd_cfg { __le32 reserved; } __packed; /* PERIPH_SCRATCH_RBD_CFG_S */ -/* +/** * struct iwl_prph_scratch_uefi_cfg - prph scratch reduce power table * @base_addr: reduce power table address * @size: the size of the entire power table image + * @reserved: (reserved) */ struct iwl_prph_scratch_uefi_cfg { __le64 base_addr; @@ -153,7 +166,7 @@ struct iwl_prph_scratch_uefi_cfg { __le32 reserved; } __packed; /* PERIPH_SCRATCH_UEFI_CFG_S */ -/* +/** * struct iwl_prph_scratch_step_cfg - prph scratch step configuration * @mbx_addr_0: [0:7] revision, * [8:15] cnvi_to_cnvr length, @@ -167,13 +180,14 @@ struct iwl_prph_scratch_step_cfg { __le32 mbx_addr_1; } __packed; -/* +/** * struct iwl_prph_scratch_ctrl_cfg - prph scratch ctrl and config * @version: version information of context info and HW * @control: control flags of FH configurations * @pnvm_cfg: ror configuration * @hwm_cfg: hwm configuration * @rbd_cfg: default RX queue configuration + * @reduce_power_cfg: UEFI power reduction table * @step_cfg: step configuration */ struct iwl_prph_scratch_ctrl_cfg { @@ -186,7 +200,7 @@ struct iwl_prph_scratch_ctrl_cfg { struct iwl_prph_scratch_step_cfg step_cfg; } __packed; /* PERIPH_SCRATCH_CTRL_CFG_S */ -/* +/** * struct iwl_prph_scratch - peripheral scratch mapping * @ctrl_cfg: control and configuration of prph scratch * @dram: firmware images addresses in DRAM @@ -202,7 +216,7 @@ struct iwl_prph_scratch { struct iwl_context_info_dram dram; } __packed; /* PERIPH_SCRATCH_S */ -/* +/** * struct iwl_prph_info - peripheral information * @boot_stage_mirror: reflects the value in the Boot Stage CSR register * @ipc_status_mirror: reflects the value in the IPC Status CSR register @@ -216,7 +230,7 @@ struct iwl_prph_info { __le32 reserved; } __packed; /* PERIPH_INFO_S */ -/* +/** * struct iwl_context_info_gen3 - device INIT configuration * @version: version of the context information * @size: size of context information in DWs diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h index 1a1321db137c..dfd44fabf237 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* * Copyright (C) 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020, 2022 Intel Corporation + * Copyright (C) 2018-2020, 2022, 2024 Intel Corporation */ #ifndef __iwl_context_info_file_h__ #define __iwl_context_info_file_h__ -/* maximmum number of DRAM map entries supported by FW */ +/* maximum number of DRAM map entries supported by FW */ #define IWL_MAX_DRAM_ENTRY 64 #define CSR_CTXT_INFO_BA 0x40 @@ -53,11 +53,12 @@ enum iwl_context_info_flags { IWL_CTXT_INFO_RB_SIZE_32K = 0xe, }; -/* +/** * struct iwl_context_info_version - version structure * @mac_id: SKU and revision id * @version: context information version id * @size: the size of the context information in DWs + * @reserved: (reserved) */ struct iwl_context_info_version { __le16 mac_id; @@ -66,16 +67,17 @@ struct iwl_context_info_version { __le16 reserved; } __packed; -/* +/** * struct iwl_context_info_control - version structure * @control_flags: context information flags see &enum iwl_context_info_flags + * @reserved: (reserved) */ struct iwl_context_info_control { __le32 control_flags; __le32 reserved; } __packed; -/* +/** * struct iwl_context_info_dram - images DRAM map * each entry in the map represents a DRAM chunk of up to 32 KB * @umac_img: UMAC image DRAM map @@ -88,7 +90,7 @@ struct iwl_context_info_dram { __le64 virtual_img[IWL_MAX_DRAM_ENTRY]; } __packed; -/* +/** * struct iwl_context_info_rbd_cfg - RBDs configuration * @free_rbd_addr: default queue free RB CB base address * @used_rbd_addr: default queue used RB CB base address @@ -100,10 +102,11 @@ struct iwl_context_info_rbd_cfg { __le64 status_wr_ptr; } __packed; -/* +/** * struct iwl_context_info_hcmd_cfg - command queue configuration * @cmd_queue_addr: address of command queue * @cmd_queue_size: number of entries + * @reserved: (reserved) */ struct iwl_context_info_hcmd_cfg { __le64 cmd_queue_addr; @@ -111,10 +114,11 @@ struct iwl_context_info_hcmd_cfg { u8 reserved[7]; } __packed; -/* +/** * struct iwl_context_info_dump_cfg - Core Dump configuration * @core_dump_addr: core dump (debug DRAM address) start address * @core_dump_size: size, in DWs + * @reserved: (reserved) */ struct iwl_context_info_dump_cfg { __le64 core_dump_addr; @@ -122,10 +126,11 @@ struct iwl_context_info_dump_cfg { __le32 reserved; } __packed; -/* +/** * struct iwl_context_info_pnvm_cfg - platform NVM data configuration * @platform_nvm_addr: Platform NVM data start address * @platform_nvm_size: size in DWs + * @reserved: (reserved) */ struct iwl_context_info_pnvm_cfg { __le64 platform_nvm_addr; @@ -133,11 +138,12 @@ struct iwl_context_info_pnvm_cfg { __le32 reserved; } __packed; -/* +/** * struct iwl_context_info_early_dbg_cfg - early debug configuration for * dumping DRAM addresses * @early_debug_addr: early debug start address * @early_debug_size: size in DWs + * @reserved: (reserved) */ struct iwl_context_info_early_dbg_cfg { __le64 early_debug_addr; @@ -145,16 +151,20 @@ struct iwl_context_info_early_dbg_cfg { __le32 reserved; } __packed; -/* +/** * struct iwl_context_info - device INIT configuration * @version: version information of context info and HW * @control: control flags of FH configurations + * @reserved0: (reserved) * @rbd_cfg: default RX queue configuration * @hcmd_cfg: command queue configuration + * @reserved1: (reserved) * @dump_cfg: core dump data * @edbg_cfg: early debug configuration * @pnvm_cfg: platform nvm configuration + * @reserved2: (reserved) * @dram: firmware image addresses in DRAM + * @reserved3: (reserved) */ struct iwl_context_info { struct iwl_context_info_version version; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h index 98563757ce2c..be9e464c9b7b 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h @@ -167,13 +167,15 @@ #define CSR_HW_IF_CONFIG_REG_POS_PHY_DASH (12) #define CSR_HW_IF_CONFIG_REG_POS_PHY_STEP (14) -#define CSR_HW_IF_CONFIG_REG_BIT_HAP_WAKE_L1A (0x00080000) -#define CSR_HW_IF_CONFIG_REG_BIT_EEPROM_OWN_SEM (0x00200000) -#define CSR_HW_IF_CONFIG_REG_BIT_NIC_READY (0x00400000) /* PCI_OWN_SEM */ -#define CSR_HW_IF_CONFIG_REG_BIT_NIC_PREPARE_DONE (0x02000000) /* ME_OWN */ -#define CSR_HW_IF_CONFIG_REG_PREPARE (0x08000000) /* WAKE_ME */ -#define CSR_HW_IF_CONFIG_REG_ENABLE_PME (0x10000000) -#define CSR_HW_IF_CONFIG_REG_PERSIST_MODE (0x40000000) /* PERSISTENCE */ +#define CSR_HW_IF_CONFIG_REG_HAP_WAKE 0x00080000 +/* NOTE: EEPROM_OWN_SEM is no longer defined for new HW */ +#define CSR_HW_IF_CONFIG_REG_EEPROM_OWN_SEM 0x00200000 +#define CSR_HW_IF_CONFIG_REG_PCI_OWN_SET 0x00400000 +#define CSR_HW_IF_CONFIG_REG_IAMT_UP 0x01000000 +#define CSR_HW_IF_CONFIG_REG_ME_OWN 0x02000000 +#define CSR_HW_IF_CONFIG_REG_WAKE_ME 0x08000000 +#define CSR_HW_IF_CONFIG_REG_WAKE_ME_PCIE_OWNER_EN 0x10000000 +#define CSR_HW_IF_CONFIG_REG_PERSISTENCE 0x40000000 #define CSR_MBOX_SET_REG_OS_ALIVE BIT(5) @@ -351,7 +353,6 @@ enum { #define CSR_HW_RF_ID_TYPE_HRCDB (0x00109F00) #define CSR_HW_RF_ID_TYPE_GF (0x0010D000) #define CSR_HW_RF_ID_TYPE_GF4 (0x0010E000) -#define CSR_HW_RF_ID_TYPE_MS (0x00111000) #define CSR_HW_RF_ID_TYPE_FM (0x00112000) #define CSR_HW_RF_ID_TYPE_WP (0x00113000) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h index 1b9f16a31b54..bf52c2edaad1 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h @@ -2,7 +2,7 @@ /****************************************************************************** * * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. - * Copyright(c) 2018 - 2021 Intel Corporation + * Copyright(c) 2018 - 2021, 2024 Intel Corporation * * Portions of this file are derived from the ipw3945 project. *****************************************************************************/ @@ -209,6 +209,7 @@ do { \ #define IWL_DEBUG_RADIO(p, f, a...) IWL_DEBUG(p, IWL_DL_RADIO, f, ## a) #define IWL_DEBUG_DEV_RADIO(p, f, a...) IWL_DEBUG_DEV(p, IWL_DL_RADIO, f, ## a) #define IWL_DEBUG_POWER(p, f, a...) IWL_DEBUG(p, IWL_DL_POWER, f, ## a) +#define IWL_DEBUG_DEV_POWER(p, f, a...) IWL_DEBUG_DEV(p, IWL_DL_POWER, f, ## a) #define IWL_DEBUG_11H(p, f, a...) IWL_DEBUG(p, IWL_DL_11H, f, ## a) #define IWL_DEBUG_TPT(p, f, a...) IWL_DEBUG(p, IWL_DL_TPT, f, ## a) #define IWL_DEBUG_WOWLAN(p, f, a...) IWL_DEBUG(p, IWL_DL_WOWLAN, f, ## a) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index c620911a1193..d3a65f33097c 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -22,6 +22,7 @@ #include "iwl-modparams.h" #include "fw/api/alive.h" #include "fw/api/mac.h" +#include "fw/api/mac-cfg.h" /****************************************************************************** * @@ -137,8 +138,7 @@ static void iwl_dealloc_ucode(struct iwl_drv *drv) memset(&drv->fw, 0, sizeof(drv->fw)); } -static int iwl_alloc_fw_desc(struct iwl_drv *drv, struct fw_desc *desc, - struct fw_sec *sec) +static int iwl_alloc_fw_desc(struct fw_desc *desc, struct fw_sec *sec) { void *data; @@ -318,17 +318,6 @@ struct iwl_firmware_pieces { size_t n_mem_tlv; }; -/* - * These functions are just to extract uCode section data from the pieces - * structure. - */ -static struct fw_sec *get_sec(struct iwl_firmware_pieces *pieces, - enum iwl_ucode_type type, - int sec) -{ - return &pieces->img[type].sec[sec]; -} - static void alloc_sec_data(struct iwl_firmware_pieces *pieces, enum iwl_ucode_type type, int sec) @@ -389,22 +378,18 @@ static void set_sec_offset(struct iwl_firmware_pieces *pieces, /* * Gets uCode section from tlv. */ -static int iwl_store_ucode_sec(struct iwl_firmware_pieces *pieces, - const void *data, enum iwl_ucode_type type, - int size) +static int iwl_store_ucode_sec(struct fw_img_parsing *img, + const void *data, int size) { - struct fw_img_parsing *img; struct fw_sec *sec; const struct fw_sec_parsing *sec_parse; size_t alloc_size; - if (WARN_ON(!pieces || !data || type >= IWL_UCODE_TYPE_MAX)) - return -1; + if (WARN_ON(!img || !data)) + return -EINVAL; sec_parse = (const struct fw_sec_parsing *)data; - img = &pieces->img[type]; - alloc_size = sizeof(*img->sec) * (img->sec_counter + 1); sec = krealloc(img->sec, alloc_size, GFP_KERNEL); if (!sec) @@ -900,18 +885,18 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, le32_to_cpup((const __le32 *)tlv_data); break; case IWL_UCODE_TLV_SEC_RT: - iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_REGULAR, - tlv_len); + iwl_store_ucode_sec(&pieces->img[IWL_UCODE_REGULAR], + tlv_data, tlv_len); drv->fw.type = IWL_FW_MVM; break; case IWL_UCODE_TLV_SEC_INIT: - iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_INIT, - tlv_len); + iwl_store_ucode_sec(&pieces->img[IWL_UCODE_INIT], + tlv_data, tlv_len); drv->fw.type = IWL_FW_MVM; break; case IWL_UCODE_TLV_SEC_WOWLAN: - iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_WOWLAN, - tlv_len); + iwl_store_ucode_sec(&pieces->img[IWL_UCODE_WOWLAN], + tlv_data, tlv_len); drv->fw.type = IWL_FW_MVM; break; case IWL_UCODE_TLV_DEF_CALIB: @@ -932,18 +917,18 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, FW_PHY_CFG_RX_CHAIN_POS; break; case IWL_UCODE_TLV_SECURE_SEC_RT: - iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_REGULAR, - tlv_len); + iwl_store_ucode_sec(&pieces->img[IWL_UCODE_REGULAR], + tlv_data, tlv_len); drv->fw.type = IWL_FW_MVM; break; case IWL_UCODE_TLV_SECURE_SEC_INIT: - iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_INIT, - tlv_len); + iwl_store_ucode_sec(&pieces->img[IWL_UCODE_INIT], + tlv_data, tlv_len); drv->fw.type = IWL_FW_MVM; break; case IWL_UCODE_TLV_SECURE_SEC_WOWLAN: - iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_WOWLAN, - tlv_len); + iwl_store_ucode_sec(&pieces->img[IWL_UCODE_WOWLAN], + tlv_data, tlv_len); drv->fw.type = IWL_FW_MVM; break; case IWL_UCODE_TLV_NUM_OF_CPU: @@ -1110,9 +1095,8 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, } case IWL_UCODE_TLV_SEC_RT_USNIFFER: *usniffer_images = true; - iwl_store_ucode_sec(pieces, tlv_data, - IWL_UCODE_REGULAR_USNIFFER, - tlv_len); + iwl_store_ucode_sec(&pieces->img[IWL_UCODE_REGULAR_USNIFFER], + tlv_data, tlv_len); break; case IWL_UCODE_TLV_PAGING: if (tlv_len != sizeof(u32)) @@ -1214,6 +1198,19 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, capa->num_stations = le32_to_cpup((const __le32 *)tlv_data); break; + case IWL_UCODE_TLV_FW_NUM_LINKS: + if (tlv_len != sizeof(u32)) + goto invalid_tlv_len; + if (le32_to_cpup((const __le32 *)tlv_data) > + IWL_FW_MAX_LINK_ID + 1) { + IWL_ERR(drv, + "%d is an invalid number of links\n", + le32_to_cpup((const __le32 *)tlv_data)); + goto tlv_error; + } + capa->num_links = + le32_to_cpup((const __le32 *)tlv_data); + break; case IWL_UCODE_TLV_FW_NUM_BEACONS: if (tlv_len != sizeof(u32)) goto invalid_tlv_len; @@ -1337,24 +1334,29 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, return -EINVAL; } +static int iwl_alloc_ucode_mem(struct fw_img *out, struct fw_img_parsing *img) +{ + struct fw_desc *sec; + + sec = kcalloc(img->sec_counter, sizeof(*sec), GFP_KERNEL); + if (!sec) + return -ENOMEM; + + out->sec = sec; + out->num_sec = img->sec_counter; + + for (int i = 0; i < out->num_sec; i++) + if (iwl_alloc_fw_desc(&sec[i], &img->sec[i])) + return -ENOMEM; + + return 0; +} + static int iwl_alloc_ucode(struct iwl_drv *drv, struct iwl_firmware_pieces *pieces, enum iwl_ucode_type type) { - int i; - struct fw_desc *sec; - - sec = kcalloc(pieces->img[type].sec_counter, sizeof(*sec), GFP_KERNEL); - if (!sec) - return -ENOMEM; - drv->fw.img[type].sec = sec; - drv->fw.img[type].num_sec = pieces->img[type].sec_counter; - - for (i = 0; i < pieces->img[type].sec_counter; i++) - if (iwl_alloc_fw_desc(drv, &sec[i], get_sec(pieces, type, i))) - return -ENOMEM; - - return 0; + return iwl_alloc_ucode_mem(&drv->fw.img[type], &pieces->img[type]); } static int validate_sec_sizes(struct iwl_drv *drv, @@ -1429,18 +1431,21 @@ _iwl_op_mode_start(struct iwl_drv *drv, struct iwlwifi_opmode_table *op) op_mode = ops->start(drv->trans, drv->trans->cfg, &drv->fw, dbgfs_dir); - if (op_mode) + if (!IS_ERR(op_mode)) return op_mode; if (test_bit(STATUS_TRANS_DEAD, &drv->trans->status)) break; - IWL_ERR(drv, "retry init count %d\n", retry); - #ifdef CONFIG_IWLWIFI_DEBUGFS debugfs_remove_recursive(drv->dbgfs_op_mode); drv->dbgfs_op_mode = NULL; #endif + + if (PTR_ERR(op_mode) != -ETIMEDOUT) + break; + + IWL_ERR(drv, "retry init count %d\n", retry); } return NULL; @@ -1944,6 +1949,7 @@ module_init(iwl_drv_init); static void __exit iwl_drv_exit(void) { iwl_pci_unregister_driver(); + iwl_trans_free_restart_list(); #ifdef CONFIG_IWLWIFI_DEBUGFS debugfs_remove_recursive(iwl_dbgfs_root); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.c b/drivers/net/wireless/intel/iwlwifi/iwl-io.c index 060becfd64f3..0653ca8b974a 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-io.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.c @@ -526,5 +526,5 @@ void iwl_trans_sync_nmi_with_addr(struct iwl_trans *trans, u32 inta_addr, if (interrupts_enabled) iwl_trans_interrupts(trans, true); - iwl_trans_fw_error(trans, false); + iwl_trans_fw_error(trans, IWL_ERR_TYPE_NMI_FORCED); } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index d902121da009..9f7e013252fe 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -141,8 +141,10 @@ static struct ieee80211_rate iwl_cfg80211_rates[] = { /** * enum iwl_nvm_channel_flags - channel flags in NVM * @NVM_CHANNEL_VALID: channel is usable for this SKU/geo - * @NVM_CHANNEL_IBSS: usable as an IBSS channel - * @NVM_CHANNEL_ACTIVE: active scanning allowed + * @NVM_CHANNEL_IBSS: usable as an IBSS channel and deprecated + * when %IWL_NVM_SBANDS_FLAGS_LAR enabled. + * @NVM_CHANNEL_ACTIVE: active scanning allowed and allows IBSS + * when %IWL_NVM_SBANDS_FLAGS_LAR enabled. * @NVM_CHANNEL_RADAR: radar detection required * @NVM_CHANNEL_INDOOR_ONLY: only indoor use is allowed * @NVM_CHANNEL_GO_CONCURRENT: GO operation is allowed when connected to BSS diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h index 8ef5ed2db051..34eca1a568ea 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h @@ -44,6 +44,55 @@ struct iwl_cfg; * 5) The driver layer stops the op_mode */ +/** + * enum iwl_fw_error_type - FW error types/sources + * @IWL_ERR_TYPE_IRQ: "normal" FW error through an IRQ + * @IWL_ERR_TYPE_NMI_FORCED: NMI was forced by driver + * @IWL_ERR_TYPE_RESET_HS_TIMEOUT: reset handshake timed out, + * any debug collection must happen synchronously as + * the device will be shut down + * @IWL_ERR_TYPE_CMD_QUEUE_FULL: command queue was full + */ +enum iwl_fw_error_type { + IWL_ERR_TYPE_IRQ, + IWL_ERR_TYPE_NMI_FORCED, + IWL_ERR_TYPE_RESET_HS_TIMEOUT, + IWL_ERR_TYPE_CMD_QUEUE_FULL, +}; + +/** + * enum iwl_fw_error_context - error dump context + * @IWL_ERR_CONTEXT_WORKER: regular from worker context, + * opmode must acquire locks and must also check + * for @IWL_ERR_CONTEXT_ABORT after acquiring locks + * @IWL_ERR_CONTEXT_FROM_OPMODE: context is in a call + * originating from the opmode, e.g. while resetting + * or stopping the device, so opmode must not acquire + * any locks + * @IWL_ERR_CONTEXT_ABORT: after lock acquisition, indicates + * that the dump already happened via another callback + * (currently only while stopping the device) via the + * @IWL_ERR_CONTEXT_FROM_OPMODE context, and this call + * must be aborted + */ +enum iwl_fw_error_context { + IWL_ERR_CONTEXT_WORKER, + IWL_ERR_CONTEXT_FROM_OPMODE, + IWL_ERR_CONTEXT_ABORT, +}; + +/** + * struct iwl_fw_error_dump_mode - error dump mode for callback + * @type: The reason for the dump, per &enum iwl_fw_error_type. + * @context: The context for the dump, may also indicate this + * call needs to be skipped. This MUST be checked before + * and after acquiring any locks in the op-mode! + */ +struct iwl_fw_error_dump_mode { + enum iwl_fw_error_type type; + enum iwl_fw_error_context context; +}; + /** * struct iwl_op_mode_ops - op_mode specific operations * @@ -77,10 +126,11 @@ struct iwl_cfg; * reclaimed by the op_mode. This can happen when the driver is freed and * there are Tx packets pending in the transport layer. * Must be atomic - * @nic_error: error notification. Must be atomic and must be called with BH - * disabled, unless the sync parameter is true. - * @cmd_queue_full: Called when the command queue gets full. Must be atomic and - * called with BH disabled. + * @nic_error: error notification. Must be atomic, the op mode should handle + * the error (e.g. abort notification waiters) and print the error if + * applicable + * @dump_error: NIC error dump collection (can sleep, synchronous) + * @sw_reset: (maybe) initiate a software reset, return %true if started * @nic_config: configure NIC, called before firmware is started. * May sleep * @wimax_active: invoked when WiMax becomes active. May sleep @@ -104,8 +154,12 @@ struct iwl_op_mode_ops { void (*queue_not_full)(struct iwl_op_mode *op_mode, int queue); bool (*hw_rf_kill)(struct iwl_op_mode *op_mode, bool state); void (*free_skb)(struct iwl_op_mode *op_mode, struct sk_buff *skb); - void (*nic_error)(struct iwl_op_mode *op_mode, bool sync); - void (*cmd_queue_full)(struct iwl_op_mode *op_mode); + void (*nic_error)(struct iwl_op_mode *op_mode, + enum iwl_fw_error_type type); + void (*dump_error)(struct iwl_op_mode *op_mode, + struct iwl_fw_error_dump_mode *mode); + bool (*sw_reset)(struct iwl_op_mode *op_mode, + enum iwl_fw_error_type type); void (*nic_config)(struct iwl_op_mode *op_mode); void (*wimax_active)(struct iwl_op_mode *op_mode); void (*time_point)(struct iwl_op_mode *op_mode, @@ -177,14 +231,19 @@ static inline void iwl_op_mode_free_skb(struct iwl_op_mode *op_mode, op_mode->ops->free_skb(op_mode, skb); } -static inline void iwl_op_mode_nic_error(struct iwl_op_mode *op_mode, bool sync) +static inline void iwl_op_mode_nic_error(struct iwl_op_mode *op_mode, + enum iwl_fw_error_type type) { - op_mode->ops->nic_error(op_mode, sync); + op_mode->ops->nic_error(op_mode, type); } -static inline void iwl_op_mode_cmd_queue_full(struct iwl_op_mode *op_mode) +static inline void iwl_op_mode_dump_error(struct iwl_op_mode *op_mode, + struct iwl_fw_error_dump_mode *mode) { - op_mode->ops->cmd_queue_full(op_mode); + might_sleep(); + + if (op_mode->ops->dump_error) + op_mode->ops->dump_error(op_mode, mode); } static inline void iwl_op_mode_nic_config(struct iwl_op_mode *op_mode) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h index dc171c29eb7b..23b2009fbb28 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h @@ -381,6 +381,10 @@ enum { #define CNVR_SCU_SD_REGS_SD_REG_ACTIVE_VDIG_MIRROR 0xA29938 #define CNVI_SCU_SEQ_DATA_DW9 0xA27488 +#define CNVI_SCU_REG_FOR_ECO_1 0xA26EF8 +#define CNVI_SCU_REG_FOR_ECO_1_WIAMT_KNOWN BIT(4) +#define CNVI_SCU_REG_FOR_ECO_1_WIAMT_PRESENT BIT(5) + #define CNVI_PMU_STEP_FLOW 0xA2D588 #define CNVI_PMU_STEP_FLOW_FORCE_URM BIT(2) @@ -458,6 +462,7 @@ enum { #define REG_CRF_ID_TYPE_GF 0x410 #define REG_CRF_ID_TYPE_FM 0x910 #define REG_CRF_ID_TYPE_WHP 0xA10 +#define REG_CRF_ID_TYPE_PE 0xA30 #define HPM_DEBUG 0xA03440 #define PERSISTENCE_BIT BIT(12) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c index 3c9d91496c82..49c8507d1a6b 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c @@ -6,6 +6,7 @@ */ #include #include +#include #include "fw/api/tx.h" #include "iwl-trans.h" @@ -16,13 +17,200 @@ #include "pcie/internal.h" #include "iwl-context-info-gen3.h" +struct iwl_trans_dev_restart_data { + struct list_head list; + unsigned int restart_count; + time64_t last_error; + char name[]; +}; + +static LIST_HEAD(restart_data_list); +static DEFINE_SPINLOCK(restart_data_lock); + +static struct iwl_trans_dev_restart_data * +iwl_trans_get_restart_data(struct device *dev) +{ + struct iwl_trans_dev_restart_data *tmp, *data = NULL; + const char *name = dev_name(dev); + + spin_lock(&restart_data_lock); + list_for_each_entry(tmp, &restart_data_list, list) { + if (strcmp(tmp->name, name)) + continue; + data = tmp; + break; + } + spin_unlock(&restart_data_lock); + + if (data) + return data; + + data = kzalloc(struct_size(data, name, strlen(name) + 1), GFP_ATOMIC); + if (!data) + return NULL; + + strcpy(data->name, name); + spin_lock(&restart_data_lock); + list_add_tail(&data->list, &restart_data_list); + spin_unlock(&restart_data_lock); + + return data; +} + +static void iwl_trans_inc_restart_count(struct device *dev) +{ + struct iwl_trans_dev_restart_data *data; + + data = iwl_trans_get_restart_data(dev); + if (data) { + data->last_error = ktime_get_boottime_seconds(); + data->restart_count++; + } +} + +void iwl_trans_free_restart_list(void) +{ + struct iwl_trans_dev_restart_data *tmp; + + while ((tmp = list_first_entry_or_null(&restart_data_list, + typeof(*tmp), list))) { + list_del(&tmp->list); + kfree(tmp); + } +} + +struct iwl_trans_reprobe { + struct device *dev; + struct work_struct work; +}; + +static void iwl_trans_reprobe_wk(struct work_struct *wk) +{ + struct iwl_trans_reprobe *reprobe; + + reprobe = container_of(wk, typeof(*reprobe), work); + + if (device_reprobe(reprobe->dev)) + dev_err(reprobe->dev, "reprobe failed!\n"); + put_device(reprobe->dev); + kfree(reprobe); + module_put(THIS_MODULE); +} + +#define IWL_TRANS_RESET_OK_TIME 180 /* seconds */ + +static enum iwl_reset_mode +iwl_trans_determine_restart_mode(struct iwl_trans *trans) +{ + struct iwl_trans_dev_restart_data *data; + enum iwl_reset_mode at_least = 0; + unsigned int index; + static const enum iwl_reset_mode escalation_list[] = { + IWL_RESET_MODE_SW_RESET, + IWL_RESET_MODE_REPROBE, + IWL_RESET_MODE_REPROBE, + IWL_RESET_MODE_FUNC_RESET, + /* FIXME: add TOP reset */ + IWL_RESET_MODE_PROD_RESET, + /* FIXME: add TOP reset */ + IWL_RESET_MODE_PROD_RESET, + /* FIXME: add TOP reset */ + IWL_RESET_MODE_PROD_RESET, + }; + + if (trans->restart.during_reset) + at_least = IWL_RESET_MODE_REPROBE; + + data = iwl_trans_get_restart_data(trans->dev); + if (!data) + return at_least; + + if (ktime_get_boottime_seconds() - data->last_error >= + IWL_TRANS_RESET_OK_TIME) + data->restart_count = 0; + + index = data->restart_count; + if (index >= ARRAY_SIZE(escalation_list)) + index = ARRAY_SIZE(escalation_list) - 1; + + return max(at_least, escalation_list[index]); +} + +#define IWL_TRANS_RESET_DELAY (HZ * 60) + +static void iwl_trans_restart_wk(struct work_struct *wk) +{ + struct iwl_trans *trans = container_of(wk, typeof(*trans), restart.wk); + struct iwl_trans_reprobe *reprobe; + enum iwl_reset_mode mode; + + if (!trans->op_mode) + return; + + /* might have been scheduled before marked as dead, re-check */ + if (test_bit(STATUS_TRANS_DEAD, &trans->status)) + return; + + iwl_op_mode_dump_error(trans->op_mode, &trans->restart.mode); + + /* + * If the opmode stopped the device while we were trying to dump and + * reset, then we'll have done the dump already (synchronized by the + * opmode lock that it will acquire in iwl_op_mode_dump_error()) and + * managed that via trans->restart.mode. + * Additionally, make sure that in such a case we won't attempt to do + * any resets now, since it's no longer requested. + */ + if (!test_and_clear_bit(STATUS_RESET_PENDING, &trans->status)) + return; + + if (!iwlwifi_mod_params.fw_restart) + return; + + mode = iwl_trans_determine_restart_mode(trans); + + iwl_trans_inc_restart_count(trans->dev); + + switch (mode) { + case IWL_RESET_MODE_SW_RESET: + IWL_ERR(trans, "Device error - SW reset\n"); + iwl_trans_opmode_sw_reset(trans, trans->restart.mode.type); + break; + case IWL_RESET_MODE_REPROBE: + IWL_ERR(trans, "Device error - reprobe!\n"); + + /* + * get a module reference to avoid doing this while unloading + * anyway and to avoid scheduling a work with code that's + * being removed. + */ + if (!try_module_get(THIS_MODULE)) { + IWL_ERR(trans, "Module is being unloaded - abort\n"); + return; + } + + reprobe = kzalloc(sizeof(*reprobe), GFP_KERNEL); + if (!reprobe) { + module_put(THIS_MODULE); + return; + } + reprobe->dev = get_device(trans->dev); + INIT_WORK(&reprobe->work, iwl_trans_reprobe_wk); + schedule_work(&reprobe->work); + break; + default: + iwl_trans_pcie_reset(trans, mode); + break; + } +} + struct iwl_trans *iwl_trans_alloc(unsigned int priv_size, struct device *dev, const struct iwl_cfg_trans_params *cfg_trans) { struct iwl_trans *trans; #ifdef CONFIG_LOCKDEP - static struct lock_class_key __key; + static struct lock_class_key __sync_cmd_key; #endif trans = devm_kzalloc(dev, sizeof(*trans) + priv_size, GFP_KERNEL); @@ -33,12 +221,14 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size, #ifdef CONFIG_LOCKDEP lockdep_init_map(&trans->sync_cmd_lockdep_map, "sync_cmd_lockdep_map", - &__key, 0); + &__sync_cmd_key, 0); #endif trans->dev = dev; trans->num_rx_queues = 1; + INIT_WORK(&trans->restart.wk, iwl_trans_restart_wk); + return trans; } @@ -81,6 +271,7 @@ int iwl_trans_init(struct iwl_trans *trans) void iwl_trans_free(struct iwl_trans *trans) { + cancel_work_sync(&trans->restart.wk); kmem_cache_destroy(trans->dev_cmd_pool); } @@ -391,6 +582,34 @@ void iwl_trans_stop_device(struct iwl_trans *trans) { might_sleep(); + /* + * See also the comment in iwl_trans_restart_wk(). + * + * When the opmode stops the device while a reset is pending, the + * worker (iwl_trans_restart_wk) might not have run yet or, more + * likely, will be blocked on the opmode lock. Due to the locking, + * we can't just flush the worker. + * + * If this is the case, then the test_and_clear_bit() ensures that + * the worker won't attempt to do anything after the stop. + * + * The trans->restart.mode is a handshake with the opmode, we set + * the context there to ABORT so that when the worker can finally + * acquire the lock in the opmode, the code there won't attempt to + * do any dumps. Since we'd really like to have the dump though, + * also do it inline here (with the opmode locks already held), + * but use a separate mode struct to avoid races. + */ + if (test_and_clear_bit(STATUS_RESET_PENDING, &trans->status)) { + struct iwl_fw_error_dump_mode mode; + + mode = trans->restart.mode; + mode.context = IWL_ERR_CONTEXT_FROM_OPMODE; + trans->restart.mode.context = IWL_ERR_CONTEXT_ABORT; + + iwl_op_mode_dump_error(trans->op_mode, &mode); + } + if (trans->trans_cfg->gen2) iwl_trans_pcie_gen2_stop_device(trans); else diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h index c70da7281551..f6234065dbdd 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h @@ -300,6 +300,10 @@ enum iwl_d3_status { * @STATUS_TRANS_DEAD: trans is dead - avoid any read/write operation * @STATUS_SUPPRESS_CMD_ERROR_ONCE: suppress "FW error in SYNC CMD" once, * e.g. for testing + * @STATUS_IN_SW_RESET: device is undergoing reset, cleared by opmode + * via iwl_trans_finish_sw_reset() + * @STATUS_RESET_PENDING: reset worker was scheduled, but didn't dump + * the firmware state yet */ enum iwl_trans_status { STATUS_SYNC_HCMD_ACTIVE, @@ -311,6 +315,8 @@ enum iwl_trans_status { STATUS_FW_ERROR, STATUS_TRANS_DEAD, STATUS_SUPPRESS_CMD_ERROR_ONCE, + STATUS_IN_SW_RESET, + STATUS_RESET_PENDING, }; static inline int @@ -322,7 +328,6 @@ iwl_trans_get_rb_size_order(enum iwl_amsdu_size rb_size) case IWL_AMSDU_4K: return get_order(4 * 1024); case IWL_AMSDU_8K: - return get_order(8 * 1024); case IWL_AMSDU_12K: return get_order(16 * 1024); default: @@ -628,8 +633,6 @@ struct iwl_pc_data { * @n_dest_reg: num of reg_ops in %dbg_dest_tlv * @rec_on: true iff there is a fw debug recording currently active * @dest_tlv: points to the destination TLV for debug - * @conf_tlv: array of pointers to configuration TLVs for debug - * @trigger_tlv: array of pointers to triggers TLVs for debug * @lmac_error_event_table: addrs of lmacs error tables * @umac_error_event_table: addr of umac error table * @tcm_error_event_table: address(es) of TCM error table(s) @@ -664,8 +667,6 @@ struct iwl_trans_debug { bool rec_on; const struct iwl_fw_dbg_dest_tlv_v1 *dest_tlv; - const struct iwl_fw_dbg_conf_tlv *conf_tlv[FW_DBG_CONF_MAX]; - struct iwl_fw_dbg_trigger_tlv * const *trigger_tlv; u32 lmac_error_event_table[2]; u32 umac_error_event_table; @@ -877,7 +878,16 @@ struct iwl_txq { * @reduced_cap_sku: reduced capability supported SKU * @no_160: device not supporting 160 MHz * @step_urm: STEP is in URM, no support for MCS>9 in 320 MHz + * @restart: restart worker data + * @restart.wk: restart worker + * @restart.mode: reset/restart error mode information + * @restart.during_reset: error occurred during previous software reset + * @me_recheck_wk: worker to recheck WiAMT/CSME presence + * @me_present: WiAMT/CSME is detected as present (1), not present (0) + * or unknown (-1, so can still use it as a boolean safely) * @trans_specific: data for the specific transport this is allocated for/with + * @dsbr_urm_fw_dependent: switch to URM based on fw settings + * @dsbr_urm_permanent: switch to URM permanently */ struct iwl_trans { bool csme_own; @@ -902,6 +912,9 @@ struct iwl_trans { bool reduced_cap_sku; u8 no_160:1, step_urm:1; + u8 dsbr_urm_fw_dependent:1, + dsbr_urm_permanent:1; + u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size; bool pm_support; @@ -944,6 +957,15 @@ struct iwl_trans { struct iwl_dma_ptr invalid_tx_cmd; + struct { + struct work_struct wk; + struct iwl_fw_error_dump_mode mode; + bool during_reset; + } restart; + + struct delayed_work me_recheck_wk; + s8 me_present; + /* pointer to trans specific struct */ /*Ensure that this pointer will always be aligned to sizeof pointer */ char trans_specific[] __aligned(sizeof(void *)); @@ -1120,7 +1142,28 @@ bool _iwl_trans_grab_nic_access(struct iwl_trans *trans); void __releases(nic_access) iwl_trans_release_nic_access(struct iwl_trans *trans); -static inline void iwl_trans_fw_error(struct iwl_trans *trans, bool sync) +static inline void iwl_trans_schedule_reset(struct iwl_trans *trans, + enum iwl_fw_error_type type) +{ + if (test_bit(STATUS_TRANS_DEAD, &trans->status)) + return; + + trans->restart.mode.type = type; + trans->restart.mode.context = IWL_ERR_CONTEXT_WORKER; + + set_bit(STATUS_RESET_PENDING, &trans->status); + + /* + * keep track of whether or not this happened while resetting, + * by the timer the worker runs it might have finished + */ + trans->restart.during_reset = test_bit(STATUS_IN_SW_RESET, + &trans->status); + queue_work(system_unbound_wq, &trans->restart.wk); +} + +static inline void iwl_trans_fw_error(struct iwl_trans *trans, + enum iwl_fw_error_type type) { if (WARN_ON_ONCE(!trans->op_mode)) return; @@ -1128,10 +1171,24 @@ static inline void iwl_trans_fw_error(struct iwl_trans *trans, bool sync) /* prevent double restarts due to the same erroneous FW */ if (!test_and_set_bit(STATUS_FW_ERROR, &trans->status)) { trans->state = IWL_TRANS_NO_FW; - iwl_op_mode_nic_error(trans->op_mode, sync); + iwl_op_mode_nic_error(trans->op_mode, type); + iwl_trans_schedule_reset(trans, type); } } +static inline void iwl_trans_opmode_sw_reset(struct iwl_trans *trans, + enum iwl_fw_error_type type) +{ + if (WARN_ON_ONCE(!trans->op_mode)) + return; + + set_bit(STATUS_IN_SW_RESET, &trans->status); + + if (!trans->op_mode->ops->sw_reset || + !trans->op_mode->ops->sw_reset(trans->op_mode, type)) + clear_bit(STATUS_IN_SW_RESET, &trans->status); +} + static inline bool iwl_trans_fw_running(struct iwl_trans *trans) { return trans->state == IWL_TRANS_FW_ALIVE; @@ -1164,6 +1221,11 @@ static inline bool iwl_trans_dbg_ini_valid(struct iwl_trans *trans) void iwl_trans_interrupts(struct iwl_trans *trans, bool enable); +static inline void iwl_trans_finish_sw_reset(struct iwl_trans *trans) +{ + clear_bit(STATUS_IN_SW_RESET, &trans->status); +} + /***************************************************** * transport helper functions *****************************************************/ @@ -1178,12 +1240,27 @@ static inline bool iwl_trans_is_hw_error_value(u32 val) return ((val & ~0xf) == 0xa5a5a5a0) || ((val & ~0xf) == 0x5a5a5a50); } +void iwl_trans_free_restart_list(void); + /***************************************************** * PCIe handling *****************************************************/ int __must_check iwl_pci_register_driver(void); void iwl_pci_unregister_driver(void); -void iwl_trans_pcie_remove(struct iwl_trans *trans, bool rescan); + +/* Note: order matters */ +enum iwl_reset_mode { + /* upper level modes: */ + IWL_RESET_MODE_SW_RESET, + IWL_RESET_MODE_REPROBE, + /* PCIE level modes: */ + IWL_RESET_MODE_REMOVE_ONLY, + IWL_RESET_MODE_RESCAN, + IWL_RESET_MODE_FUNC_RESET, + IWL_RESET_MODE_PROD_RESET, +}; + +void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode); int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-utils.c b/drivers/net/wireless/intel/iwlwifi/iwl-utils.c new file mode 100644 index 000000000000..b14ec98e28b6 --- /dev/null +++ b/drivers/net/wireless/intel/iwlwifi/iwl-utils.c @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* + * Copyright (C) 2024 Intel Corporation + */ +#include +#include +#include +#include + +#include "iwl-drv.h" +#include "iwl-utils.h" + +#ifdef CONFIG_INET +int iwl_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, + netdev_features_t netdev_flags, + struct sk_buff_head *mpdus_skbs) +{ + struct sk_buff *tmp, *next; + struct ieee80211_hdr *hdr = (void *)skb->data; + char cb[sizeof(skb->cb)]; + u16 i = 0; + unsigned int tcp_payload_len; + unsigned int mss = skb_shinfo(skb)->gso_size; + bool ipv4 = (skb->protocol == htons(ETH_P_IP)); + bool qos = ieee80211_is_data_qos(hdr->frame_control); + u16 ip_base_id = ipv4 ? ntohs(ip_hdr(skb)->id) : 0; + + skb_shinfo(skb)->gso_size = num_subframes * mss; + memcpy(cb, skb->cb, sizeof(cb)); + + next = skb_gso_segment(skb, netdev_flags); + skb_shinfo(skb)->gso_size = mss; + skb_shinfo(skb)->gso_type = ipv4 ? SKB_GSO_TCPV4 : SKB_GSO_TCPV6; + + if (IS_ERR(next) && PTR_ERR(next) == -ENOMEM) + return -ENOMEM; + + if (WARN_ONCE(IS_ERR(next), + "skb_gso_segment error: %d\n", (int)PTR_ERR(next))) + return PTR_ERR(next); + + if (next) + consume_skb(skb); + + skb_list_walk_safe(next, tmp, next) { + memcpy(tmp->cb, cb, sizeof(tmp->cb)); + /* + * Compute the length of all the data added for the A-MSDU. + * This will be used to compute the length to write in the TX + * command. We have: SNAP + IP + TCP for n -1 subframes and + * ETH header for n subframes. + */ + tcp_payload_len = skb_tail_pointer(tmp) - + skb_transport_header(tmp) - + tcp_hdrlen(tmp) + tmp->data_len; + + if (ipv4) + ip_hdr(tmp)->id = htons(ip_base_id + i * num_subframes); + + if (tcp_payload_len > mss) { + skb_shinfo(tmp)->gso_size = mss; + skb_shinfo(tmp)->gso_type = ipv4 ? SKB_GSO_TCPV4 : + SKB_GSO_TCPV6; + } else { + if (qos) { + u8 *qc; + + if (ipv4) + ip_send_check(ip_hdr(tmp)); + + qc = ieee80211_get_qos_ctl((void *)tmp->data); + *qc &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT; + } + skb_shinfo(tmp)->gso_size = 0; + } + + skb_mark_not_on_list(tmp); + __skb_queue_tail(mpdus_skbs, tmp); + i++; + } + + return 0; +} +IWL_EXPORT_SYMBOL(iwl_tx_tso_segment); +#endif /* CONFIG_INET */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-utils.h b/drivers/net/wireless/intel/iwlwifi/iwl-utils.h new file mode 100644 index 000000000000..8f1f11d06fbe --- /dev/null +++ b/drivers/net/wireless/intel/iwlwifi/iwl-utils.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* + * Copyright (C) 2024 Intel Corporation + */ +#ifndef __iwl_utils_h__ +#define __iwl_utils_h__ + +#include + +#ifdef CONFIG_INET +/** + * iwl_tx_tso_segment - Segments a TSO packet into subframes for A-MSDU. + * @skb: buffer to segment. + * @num_subframes: number of subframes to create. + * @netdev_flags: netdev feature flags. + * @mpdus_skbs: list to hold the segmented subframes. + * + * This function segments a large TCP packet into subframes. + * subframes are added to the mpdus_skbs list + * + * Returns: 0 on success and negative value on failure. + */ +int iwl_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, + netdev_features_t netdev_flags, + struct sk_buff_head *mpdus_skbs); +#else +static inline +int iwl_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, + netdev_features_t netdev_flags, + struct sk_buff_head *mpdus_skbs) +{ + WARN_ON(1); + + return -1; +} +#endif /* CONFIG_INET */ + +static inline +u32 iwl_find_ie_offset(u8 *beacon, u8 eid, u32 frame_size) +{ + struct ieee80211_mgmt *mgmt = (void *)beacon; + const u8 *ie; + + if (WARN_ON_ONCE(frame_size <= (mgmt->u.beacon.variable - beacon))) + return 0; + + frame_size -= mgmt->u.beacon.variable - beacon; + + ie = cfg80211_find_ie(eid, mgmt->u.beacon.variable, frame_size); + if (!ie) + return 0; + + return ie - beacon; +} + +#endif /* __iwl_utils_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/binding.c b/drivers/net/wireless/intel/iwlwifi/mvm/binding.c index 458b97930059..58e9a940024d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/binding.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/binding.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2012-2014, 2020 Intel Corporation * Copyright (C) 2016 Intel Deutschland GmbH - * Copyright (C) 2022 Intel Corporation + * Copyright (C) 2022, 2024 Intel Corporation */ #include #include "fw-api.h" @@ -158,9 +158,8 @@ int iwl_mvm_binding_remove_vif(struct iwl_mvm *mvm, struct ieee80211_vif *vif) ret = iwl_mvm_binding_update(mvm, vif, mvmvif->deflink.phy_ctxt, false); - if (!ret) - if (iwl_mvm_sf_update(mvm, vif, true)) - IWL_ERR(mvm, "Failed to update SF state\n"); + if (!ret && iwl_mvm_sf_update(mvm, vif, true)) + IWL_ERR(mvm, "Failed to update SF state\n"); return ret; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c index 36726ea4b822..21641d41a958 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c @@ -530,18 +530,15 @@ static void iwl_mvm_bt_coex_notif_iterator(void *_data, u8 *mac, struct ieee80211_vif *vif) { struct iwl_mvm *mvm = _data; + struct ieee80211_bss_conf *link_conf; + unsigned int link_id; lockdep_assert_held(&mvm->mutex); if (vif->type != NL80211_IFTYPE_STATION) return; - for (int link_id = 0; - link_id < IEEE80211_MLD_MAX_NUM_LINKS; - link_id++) { - struct ieee80211_bss_conf *link_conf = - rcu_dereference_check(vif->link_conf[link_id], - lockdep_is_held(&mvm->mutex)); + for_each_vif_active_link(vif, link_conf, link_id) { struct ieee80211_chanctx_conf *chanctx_conf = rcu_dereference_check(link_conf->chanctx_conf, lockdep_is_held(&mvm->mutex)); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index f85c01e04ebf..129b6bdf9ef9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1395,13 +1395,6 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw, if (ret < 0) { iwl_mvm_free_nd(mvm); - if (!unified_image) { - if (mvm->fw_restart > 0) { - mvm->fw_restart--; - ieee80211_restart_hw(mvm->hw); - } - } - clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); } out_noreset: @@ -2498,12 +2491,6 @@ static void iwl_mvm_parse_wowlan_info_notif(struct iwl_mvm *mvm, u32 expected_len = sizeof(*data) + data->num_mlo_link_keys * sizeof(status->mlo_keys[0]); - if (!data) { - IWL_ERR(mvm, "iwl_wowlan_info_notif data is NULL\n"); - status = NULL; - return; - } - if (len < expected_len) { IWL_ERR(mvm, "Invalid WoWLAN info notification!\n"); status = NULL; @@ -2555,12 +2542,6 @@ iwl_mvm_parse_wowlan_info_notif_v4(struct iwl_mvm *mvm, u32 i; u32 expected_len = sizeof(*data); - if (!data) { - IWL_ERR(mvm, "iwl_wowlan_info_notif data is NULL\n"); - status = NULL; - return; - } - if (has_mlo_keys) expected_len += (data->num_mlo_link_keys * sizeof(status->mlo_keys[0])); @@ -2609,12 +2590,6 @@ iwl_mvm_parse_wowlan_info_notif_v2(struct iwl_mvm *mvm, { u32 i; - if (!data) { - IWL_ERR(mvm, "iwl_wowlan_info_notif data is NULL\n"); - status = NULL; - return; - } - if (len < sizeof(*data)) { IWL_ERR(mvm, "Invalid WoWLAN info notification!\n"); status = NULL; @@ -2954,6 +2929,7 @@ static void iwl_mvm_query_set_freqs(struct iwl_mvm *mvm, int idx) { int i; + int n_channels = 0; if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_SCAN_OFFLOAD_CHANS)) { @@ -2962,7 +2938,7 @@ static void iwl_mvm_query_set_freqs(struct iwl_mvm *mvm, for (i = 0; i < SCAN_OFFLOAD_MATCHING_CHANNELS_LEN * 8; i++) if (matches[idx].matching_channels[i / 8] & (BIT(i % 8))) - match->channels[match->n_channels++] = + match->channels[n_channels++] = mvm->nd_channels[i]->center_freq; } else { struct iwl_scan_offload_profile_match_v1 *matches = @@ -2970,9 +2946,11 @@ static void iwl_mvm_query_set_freqs(struct iwl_mvm *mvm, for (i = 0; i < SCAN_OFFLOAD_MATCHING_CHANNELS_LEN_V1 * 8; i++) if (matches[idx].matching_channels[i / 8] & (BIT(i % 8))) - match->channels[match->n_channels++] = + match->channels[n_channels++] = mvm->nd_channels[i]->center_freq; } + /* We may have ended up with fewer channels than we allocated. */ + match->n_channels = n_channels; } /** @@ -3053,6 +3031,8 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, GFP_KERNEL); if (!net_detect || !n_matches) goto out_report_nd; + net_detect->n_matches = n_matches; + n_matches = 0; for_each_set_bit(i, &matched_profiles, mvm->n_nd_match_sets) { struct cfg80211_wowlan_nd_match *match; @@ -3066,8 +3046,9 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, GFP_KERNEL); if (!match) goto out_report_nd; + match->n_channels = n_channels; - net_detect->matches[net_detect->n_matches++] = match; + net_detect->matches[n_matches++] = match; /* We inverted the order of the SSIDs in the scan * request, so invert the index here. @@ -3082,6 +3063,8 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, iwl_mvm_query_set_freqs(mvm, d3_data->nd_results, match, i); } + /* We may have fewer matches than we allocated. */ + net_detect->n_matches = n_matches; out_report_nd: wakeup.net_detect = net_detect; @@ -3533,6 +3516,7 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test) iwl_fw_dbg_read_d3_debug_data(&mvm->fwrt); if (iwl_mvm_check_rt_status(mvm, vif)) { + IWL_ERR(mvm, "FW Error occurred during suspend. Restarting.\n"); set_bit(STATUS_FW_ERROR, &mvm->trans->status); iwl_mvm_dump_nic_error_log(mvm); iwl_dbg_tlv_time_point(&mvm->fwrt, @@ -3705,8 +3689,7 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm) iwl_fw_dbg_read_d3_debug_data(&mvm->fwrt); if (iwl_mvm_check_rt_status(mvm, NULL)) { - IWL_ERR(mvm, - "iwl_mvm_check_rt_status failed, device is gone during suspend\n"); + IWL_ERR(mvm, "FW Error occurred during suspend. Restarting.\n"); set_bit(STATUS_FW_ERROR, &mvm->trans->status); iwl_mvm_dump_nic_error_log(mvm); iwl_dbg_tlv_time_point(&mvm->fwrt, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index 91ca830a7b60..83e3c1160362 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -16,6 +16,7 @@ #include "debugfs.h" #include "iwl-modparams.h" #include "iwl-drv.h" +#include "iwl-utils.h" #include "fw/error-dump.h" #include "fw/api/phy-ctxt.h" @@ -462,7 +463,6 @@ static ssize_t iwl_dbgfs_amsdu_len_write(struct ieee80211_link_sta *link_sta, if (amsdu_len) { mvm_link_sta->orig_amsdu_len = link_sta->agg.max_amsdu_len; link_sta->agg.max_amsdu_len = amsdu_len; - link_sta->agg.max_amsdu_len = amsdu_len; for (i = 0; i < ARRAY_SIZE(link_sta->agg.max_tid_amsdu_len); i++) link_sta->agg.max_tid_amsdu_len[i] = amsdu_len; } else { @@ -537,43 +537,12 @@ static ssize_t iwl_dbgfs_disable_power_off_write(struct iwl_mvm *mvm, char *buf, return ret ?: count; } -static ssize_t iwl_dbgfs_fw_ver_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct iwl_mvm *mvm = file->private_data; - char *buff, *pos, *endpos; - static const size_t bufsz = 1024; - int ret; - - buff = kmalloc(bufsz, GFP_KERNEL); - if (!buff) - return -ENOMEM; - - pos = buff; - endpos = pos + bufsz; - - pos += scnprintf(pos, endpos - pos, "FW id: %s\n", - mvm->fwrt.fw->fw_version); - pos += scnprintf(pos, endpos - pos, "FW: %s\n", - mvm->fwrt.fw->human_readable); - pos += scnprintf(pos, endpos - pos, "Device: %s\n", - mvm->fwrt.trans->name); - pos += scnprintf(pos, endpos - pos, "Bus: %s\n", - mvm->fwrt.dev->bus->name); - - ret = simple_read_from_buffer(user_buf, count, ppos, buff, pos - buff); - kfree(buff); - - return ret; -} - static ssize_t iwl_dbgfs_tas_get_status_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct iwl_mvm *mvm = file->private_data; - struct iwl_mvm_tas_status_resp tas_rsp; - struct iwl_mvm_tas_status_resp *rsp = &tas_rsp; + struct iwl_mvm_tas_status_resp *rsp = NULL; static const size_t bufsz = 1024; char *buff, *pos, *endpos; const char * const tas_dis_reason[TAS_DISABLED_REASON_MAX] = { @@ -609,6 +578,10 @@ static ssize_t iwl_dbgfs_tas_get_status_read(struct file *file, if (!iwl_mvm_firmware_running(mvm)) return -ENODEV; + if (iwl_fw_lookup_notif_ver(mvm->fw, DEBUG_GROUP, GET_TAS_STATUS, + 0) != 3) + return -EOPNOTSUPP; + mutex_lock(&mvm->mutex); ret = iwl_mvm_send_cmd(mvm, &hcmd); mutex_unlock(&mvm->mutex); @@ -659,6 +632,14 @@ static ssize_t iwl_dbgfs_tas_get_status_read(struct file *file, rsp->tas_fw_version); pos += scnprintf(pos, endpos - pos, "Is UHB enabled for USA?: %s\n", rsp->is_uhb_for_usa_enable ? "True" : "False"); + + if (fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT)) + pos += scnprintf(pos, endpos - pos, + "Is UHB enabled for CANADA?: %s\n", + rsp->uhb_allowed_flags & + TAS_UHB_ALLOWED_CANADA ? "True" : "False"); + pos += scnprintf(pos, endpos - pos, "Current MCC: 0x%x\n", le16_to_cpu(rsp->curr_mcc)); @@ -1159,10 +1140,6 @@ static ssize_t iwl_dbgfs_fw_restart_write(struct iwl_mvm *mvm, char *buf, mutex_lock(&mvm->mutex); - /* allow one more restart that we're provoking here */ - if (mvm->fw_restart >= 0) - mvm->fw_restart++; - if (count == 6 && !strcmp(buf, "nolog\n")) { set_bit(IWL_MVM_STATUS_SUPPRESS_ERROR_LOG_ONCE, &mvm->status); set_bit(STATUS_SUPPRESS_CMD_ERROR_ONCE, &mvm->trans->status); @@ -1409,9 +1386,9 @@ static int _iwl_dbgfs_inject_beacon_ie(struct iwl_mvm *mvm, char *bin, int len) if (iwl_fw_lookup_cmd_ver(mvm->fw, BEACON_TEMPLATE_CMD, 0) >= 14) { - u32 offset = iwl_mvm_find_ie_offset(beacon->data, - WLAN_EID_S1G_TWT, - beacon->len); + u32 offset = iwl_find_ie_offset(beacon->data, + WLAN_EID_S1G_TWT, + beacon->len); beacon_cmd.btwt_offset = cpu_to_le32(offset); } @@ -1495,22 +1472,6 @@ static ssize_t iwl_dbgfs_fw_dbg_conf_write(struct iwl_mvm *mvm, return ret ?: count; } -static ssize_t iwl_dbgfs_fw_dbg_collect_write(struct iwl_mvm *mvm, - char *buf, size_t count, - loff_t *ppos) -{ - if (count == 0) - return 0; - - iwl_dbg_tlv_time_point(&mvm->fwrt, IWL_FW_INI_TIME_POINT_USER_TRIGGER, - NULL); - - iwl_fw_dbg_collect(&mvm->fwrt, FW_DBG_TRIGGER_USER, buf, - (count - 1), NULL); - - return count; -} - static ssize_t iwl_dbgfs_fw_dbg_clear_write(struct iwl_mvm *mvm, char *buf, size_t count, loff_t *ppos) @@ -1964,14 +1925,12 @@ MVM_DEBUGFS_READ_WRITE_FILE_OPS(disable_power_off, 64); MVM_DEBUGFS_READ_FILE_OPS(fw_rx_stats); MVM_DEBUGFS_READ_FILE_OPS(drv_rx_stats); MVM_DEBUGFS_READ_FILE_OPS(fw_system_stats); -MVM_DEBUGFS_READ_FILE_OPS(fw_ver); MVM_DEBUGFS_READ_FILE_OPS(phy_integration_ver); MVM_DEBUGFS_READ_FILE_OPS(tas_get_status); MVM_DEBUGFS_WRITE_FILE_OPS(fw_restart, 10); MVM_DEBUGFS_WRITE_FILE_OPS(fw_nmi, 10); MVM_DEBUGFS_READ_WRITE_FILE_OPS(scan_ant_rxchain, 8); MVM_DEBUGFS_READ_WRITE_FILE_OPS(fw_dbg_conf, 8); -MVM_DEBUGFS_WRITE_FILE_OPS(fw_dbg_collect, 64); MVM_DEBUGFS_WRITE_FILE_OPS(fw_dbg_clear, 64); MVM_DEBUGFS_WRITE_FILE_OPS(dbg_time_point, 64); MVM_DEBUGFS_WRITE_FILE_OPS(indirection_tbl, @@ -2164,7 +2123,6 @@ void iwl_mvm_dbgfs_register(struct iwl_mvm *mvm) MVM_DEBUGFS_ADD_FILE(force_ctkill, mvm->debugfs_dir, 0200); MVM_DEBUGFS_ADD_FILE(stations, mvm->debugfs_dir, 0400); MVM_DEBUGFS_ADD_FILE(disable_power_off, mvm->debugfs_dir, 0600); - MVM_DEBUGFS_ADD_FILE(fw_ver, mvm->debugfs_dir, 0400); MVM_DEBUGFS_ADD_FILE(fw_rx_stats, mvm->debugfs_dir, 0400); MVM_DEBUGFS_ADD_FILE(drv_rx_stats, mvm->debugfs_dir, 0400); MVM_DEBUGFS_ADD_FILE(fw_system_stats, mvm->debugfs_dir, 0400); @@ -2173,7 +2131,6 @@ void iwl_mvm_dbgfs_register(struct iwl_mvm *mvm) MVM_DEBUGFS_ADD_FILE(scan_ant_rxchain, mvm->debugfs_dir, 0600); MVM_DEBUGFS_ADD_FILE(prph_reg, mvm->debugfs_dir, 0600); MVM_DEBUGFS_ADD_FILE(fw_dbg_conf, mvm->debugfs_dir, 0600); - MVM_DEBUGFS_ADD_FILE(fw_dbg_collect, mvm->debugfs_dir, 0200); MVM_DEBUGFS_ADD_FILE(fw_dbg_clear, mvm->debugfs_dir, 0200); MVM_DEBUGFS_ADD_FILE(dbg_time_point, mvm->debugfs_dir, 0200); MVM_DEBUGFS_ADD_FILE(send_echo_cmd, mvm->debugfs_dir, 0200); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 5ea684802ad1..df49dd2e2026 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -642,7 +642,8 @@ static int iwl_run_unified_mvm_ucode(struct iwl_mvm *mvm) /* if we needed reset then fail here, but notify and remove */ if (mvm->fw_product_reset) { iwl_mei_alive_notif(false); - iwl_trans_pcie_remove(mvm->trans, true); + iwl_trans_pcie_reset(mvm->trans, + IWL_RESET_MODE_RESCAN); } goto error; @@ -1093,36 +1094,40 @@ static int iwl_mvm_ppag_init(struct iwl_mvm *mvm) return iwl_mvm_ppag_send_cmd(mvm); } -static bool iwl_mvm_add_to_tas_block_list(__le32 *list, __le32 *le_size, unsigned int mcc) +static bool +iwl_mvm_add_to_tas_block_list(u16 *list, u8 *size, u16 mcc) { - int i; - u32 size = le32_to_cpu(*le_size); - /* Verify that there is room for another country */ - if (size >= IWL_WTAS_BLACK_LIST_MAX) + if (*size >= IWL_WTAS_BLACK_LIST_MAX) return false; - for (i = 0; i < size; i++) { - if (list[i] == cpu_to_le32(mcc)) + for (u8 i = 0; i < *size; i++) { + if (list[i] == mcc) return true; } - list[size++] = cpu_to_le32(mcc); - *le_size = cpu_to_le32(size); + list[*size++] = mcc; return true; } static void iwl_mvm_tas_init(struct iwl_mvm *mvm) { u32 cmd_id = WIDE_ID(REGULATORY_AND_NVM_GROUP, TAS_CONFIG); - int ret; + int fw_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, + IWL_FW_CMD_VER_UNKNOWN); + struct iwl_tas_selection_data selection_data = {}; + struct iwl_tas_config_cmd_v2_v4 cmd_v2_v4 = {}; + struct iwl_tas_config_cmd cmd_v5 = {}; struct iwl_tas_data data = {}; - struct iwl_tas_config_cmd cmd = {}; - int cmd_size, fw_ver; + void *cmd_data = &cmd_v2_v4; + int cmd_size; + int ret; BUILD_BUG_ON(ARRAY_SIZE(data.block_list_array) != IWL_WTAS_BLACK_LIST_MAX); - BUILD_BUG_ON(ARRAY_SIZE(cmd.common.block_list_array) != + BUILD_BUG_ON(ARRAY_SIZE(cmd_v2_v4.common.block_list_array) != + IWL_WTAS_BLACK_LIST_MAX); + BUILD_BUG_ON(ARRAY_SIZE(cmd_v5.block_list_array) != IWL_WTAS_BLACK_LIST_MAX); if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TAS_CFG)) { @@ -1138,7 +1143,7 @@ static void iwl_mvm_tas_init(struct iwl_mvm *mvm) return; } - if (ret == 0) + if (ret == 0 && fw_ver < 5) return; if (!iwl_is_tas_approved()) { @@ -1161,27 +1166,49 @@ static void iwl_mvm_tas_init(struct iwl_mvm *mvm) dmi_get_system_info(DMI_SYS_VENDOR) ?: ""); } - fw_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, - IWL_FW_CMD_VER_UNKNOWN); - - memcpy(&cmd.common, &data, sizeof(struct iwl_tas_config_cmd_common)); - - /* Set v3 or v4 specific parts. will be trunctated for fw_ver < 3 */ - if (fw_ver == 4) { - cmd.v4.override_tas_iec = data.override_tas_iec; - cmd.v4.enable_tas_iec = data.enable_tas_iec; - cmd.v4.usa_tas_uhb_allowed = data.usa_tas_uhb_allowed; - } else { - cmd.v3.override_tas_iec = cpu_to_le16(data.override_tas_iec); - cmd.v3.enable_tas_iec = cpu_to_le16(data.enable_tas_iec); + if (fw_ver < 5) { + selection_data = iwl_parse_tas_selection(data.tas_selection, + data.table_revision); + cmd_v2_v4.common.block_list_size = + cpu_to_le32(data.block_list_size); + for (u8 i = 0; i < data.block_list_size; i++) + cmd_v2_v4.common.block_list_array[i] = + cpu_to_le32(data.block_list_array[i]); } - cmd_size = sizeof(struct iwl_tas_config_cmd_common); - if (fw_ver >= 3) - /* v4 is the same size as v3 */ - cmd_size += sizeof(struct iwl_tas_config_cmd_v3); + if (fw_ver == 5) { + cmd_size = sizeof(cmd_v5); + cmd_data = &cmd_v5; + cmd_v5.block_list_size = cpu_to_le16(data.block_list_size); + for (u16 i = 0; i < data.block_list_size; i++) + cmd_v5.block_list_array[i] = + cpu_to_le16(data.block_list_array[i]); + cmd_v5.tas_config_info.table_source = data.table_source; + cmd_v5.tas_config_info.table_revision = data.table_revision; + cmd_v5.tas_config_info.value = cpu_to_le32(data.tas_selection); + } else if (fw_ver == 4) { + cmd_size = sizeof(cmd_v2_v4.common) + sizeof(cmd_v2_v4.v4); + cmd_v2_v4.v4.override_tas_iec = selection_data.override_tas_iec; + cmd_v2_v4.v4.enable_tas_iec = selection_data.enable_tas_iec; + cmd_v2_v4.v4.usa_tas_uhb_allowed = + selection_data.usa_tas_uhb_allowed; + if (fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT) && + selection_data.canada_tas_uhb_allowed) + cmd_v2_v4.v4.uhb_allowed_flags = TAS_UHB_ALLOWED_CANADA; + } else if (fw_ver == 3) { + cmd_size = sizeof(cmd_v2_v4.common) + sizeof(cmd_v2_v4.v3); + cmd_v2_v4.v3.override_tas_iec = + cpu_to_le16(selection_data.override_tas_iec); + cmd_v2_v4.v3.enable_tas_iec = + cpu_to_le16(selection_data.enable_tas_iec); + } else if (fw_ver == 2) { + cmd_size = sizeof(cmd_v2_v4.common); + } else { + return; + } - ret = iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, cmd_size, &cmd); + ret = iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, cmd_size, cmd_data); if (ret < 0) IWL_DEBUG_RADIO(mvm, "failed to send TAS_CONFIG (%d)\n", ret); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c index 272da41567ef..851869c0bd50 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c @@ -412,9 +412,8 @@ int iwl_mvm_remove_link(struct iwl_mvm *mvm, struct ieee80211_vif *vif, ret = iwl_mvm_link_cmd_send(mvm, &cmd, FW_CTXT_ACTION_REMOVE); - if (!ret) - if (iwl_mvm_sf_update(mvm, vif, true)) - IWL_ERR(mvm, "Failed to update SF state\n"); + if (!ret && iwl_mvm_sf_update(mvm, vif, true)) + IWL_ERR(mvm, "Failed to update SF state\n"); return ret; } @@ -762,9 +761,8 @@ bool iwl_mvm_mld_valid_link_pair(struct ieee80211_vif *vif, iwl_mvm_esr_disallowed_with_link(mvm, vif, b, false)) return false; - if (a->chandef->width != b->chandef->width || - !(a->chandef->chan->band == NL80211_BAND_6GHZ && - b->chandef->chan->band == NL80211_BAND_5GHZ)) + if (a->chandef->chan->band == b->chandef->chan->band || + a->chandef->width != b->chandef->width) ret |= IWL_MVM_ESR_EXIT_BANDWIDTH; if (ret) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index 51ee62ae70fb..6b06732441c3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -12,6 +12,7 @@ #include "fw-api.h" #include "mvm.h" #include "time-event.h" +#include "iwl-utils.h" const u8 iwl_mvm_ac_to_tx_fifo[] = { IWL_MVM_TX_FIFO_VO, @@ -868,23 +869,6 @@ void iwl_mvm_mac_ctxt_set_tim(struct iwl_mvm *mvm, } } -u32 iwl_mvm_find_ie_offset(u8 *beacon, u8 eid, u32 frame_size) -{ - struct ieee80211_mgmt *mgmt = (void *)beacon; - const u8 *ie; - - if (WARN_ON_ONCE(frame_size <= (mgmt->u.beacon.variable - beacon))) - return 0; - - frame_size -= mgmt->u.beacon.variable - beacon; - - ie = cfg80211_find_ie(eid, mgmt->u.beacon.variable, frame_size); - if (!ie) - return 0; - - return ie - beacon; -} - u8 iwl_mvm_mac_ctxt_get_lowest_rate(struct iwl_mvm *mvm, struct ieee80211_tx_info *info, struct ieee80211_vif *vif) @@ -1078,22 +1062,23 @@ static int iwl_mvm_mac_ctxt_send_beacon_v7(struct iwl_mvm *mvm, beacon->data, beacon->len); beacon_cmd.csa_offset = - cpu_to_le32(iwl_mvm_find_ie_offset(beacon->data, - WLAN_EID_CHANNEL_SWITCH, - beacon->len)); + cpu_to_le32(iwl_find_ie_offset(beacon->data, + WLAN_EID_CHANNEL_SWITCH, + beacon->len)); beacon_cmd.ecsa_offset = - cpu_to_le32(iwl_mvm_find_ie_offset(beacon->data, - WLAN_EID_EXT_CHANSWITCH_ANN, - beacon->len)); + cpu_to_le32(iwl_find_ie_offset(beacon->data, + WLAN_EID_EXT_CHANSWITCH_ANN, + beacon->len)); return iwl_mvm_mac_ctxt_send_beacon_cmd(mvm, beacon, &beacon_cmd, sizeof(beacon_cmd)); } bool iwl_mvm_enable_fils(struct iwl_mvm *mvm, + struct ieee80211_vif *vif, struct ieee80211_chanctx_conf *ctx) { - if (IWL_MVM_DISABLE_AP_FILS) + if (vif->type != NL80211_IFTYPE_AP || IWL_MVM_DISABLE_AP_FILS) return false; if (cfg80211_channel_is_psc(ctx->def.chan)) @@ -1122,7 +1107,7 @@ static int iwl_mvm_mac_ctxt_send_beacon_v9(struct iwl_mvm *mvm, ctx = rcu_dereference(link_conf->chanctx_conf); channel = ieee80211_frequency_to_channel(ctx->def.chan->center_freq); WARN_ON(channel == 0); - if (iwl_mvm_enable_fils(mvm, ctx)) { + if (iwl_mvm_enable_fils(mvm, vif, ctx)) { flags |= iwl_fw_lookup_cmd_ver(mvm->fw, BEACON_TEMPLATE_CMD, 0) > 10 ? IWL_MAC_BEACON_FILS : @@ -1151,20 +1136,20 @@ static int iwl_mvm_mac_ctxt_send_beacon_v9(struct iwl_mvm *mvm, beacon->data, beacon->len); beacon_cmd.csa_offset = - cpu_to_le32(iwl_mvm_find_ie_offset(beacon->data, - WLAN_EID_CHANNEL_SWITCH, - beacon->len)); + cpu_to_le32(iwl_find_ie_offset(beacon->data, + WLAN_EID_CHANNEL_SWITCH, + beacon->len)); beacon_cmd.ecsa_offset = - cpu_to_le32(iwl_mvm_find_ie_offset(beacon->data, - WLAN_EID_EXT_CHANSWITCH_ANN, - beacon->len)); + cpu_to_le32(iwl_find_ie_offset(beacon->data, + WLAN_EID_EXT_CHANSWITCH_ANN, + beacon->len)); if (vif->type == NL80211_IFTYPE_AP && iwl_fw_lookup_cmd_ver(mvm->fw, BEACON_TEMPLATE_CMD, 0) >= 14) beacon_cmd.btwt_offset = - cpu_to_le32(iwl_mvm_find_ie_offset(beacon->data, - WLAN_EID_S1G_TWT, - beacon->len)); + cpu_to_le32(iwl_find_ie_offset(beacon->data, + WLAN_EID_S1G_TWT, + beacon->len)); return iwl_mvm_mac_ctxt_send_beacon_cmd(mvm, beacon, &beacon_cmd, sizeof(beacon_cmd)); @@ -1767,7 +1752,7 @@ void iwl_mvm_rx_stored_beacon_notif(struct iwl_mvm *mvm, data = sb_v2->data; } else { - struct iwl_stored_beacon_notif_v3 *sb_v3 = (void *)pkt->data; + struct iwl_stored_beacon_notif *sb_v3 = (void *)pkt->data; if (pkt_len < struct_size(sb_v3, data, size)) return; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 07778d55878b..af6644b7e95f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1153,7 +1153,7 @@ static void iwl_mvm_cleanup_sta_iterator(void *data, struct ieee80211_sta *sta) * Delete the stale data to avoid issues later on. */ iwl_mvm_mld_free_sta_link(mvm, mvm_sta, mvm_link_sta, - link_id, false); + link_id); } } } @@ -1300,23 +1300,16 @@ int iwl_mvm_mac_start(struct ieee80211_hw *hw) /* we are starting the mac not in error flow, and restart is enabled */ if (!test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) && - iwlwifi_mod_params.fw_restart) { + iwlwifi_mod_params.fw_restart) max_retry = IWL_MAX_INIT_RETRY; - /* - * This will prevent mac80211 recovery flows to trigger during - * init failures - */ - set_bit(IWL_MVM_STATUS_STARTING, &mvm->status); - } for (retry = 0; retry <= max_retry; retry++) { ret = __iwl_mvm_mac_start(mvm); - if (!ret) + if (ret != -ETIMEDOUT) break; IWL_ERR(mvm, "mac start retry %d\n", retry); } - clear_bit(IWL_MVM_STATUS_STARTING, &mvm->status); mutex_unlock(&mvm->mutex); @@ -1347,6 +1340,11 @@ static void iwl_mvm_restart_complete(struct iwl_mvm *mvm) iwl_mvm_teardown_tdls_peers(mvm); IWL_INFO(mvm, "restart completed\n"); + iwl_trans_finish_sw_reset(mvm->trans); + + /* no need to lock, adding in parallel would schedule too */ + if (!list_empty(&mvm->add_stream_txqs)) + schedule_work(&mvm->add_stream_wk); } void iwl_mvm_mac_reconfig_complete(struct ieee80211_hw *hw, @@ -1485,11 +1483,12 @@ int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, s16 tx_power) { u32 cmd_id = REDUCE_TX_POWER_CMD; - u32 mac_id = iwl_mvm_vif_from_mac80211(link_conf->vif)->id; + struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(link_conf->vif); + u32 mac_id = mvmvif->id; int len; struct iwl_dev_tx_power_cmd_v3_v8 cmd = { - .common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_MAC), - .common.mac_context_id = cpu_to_le32(mac_id), + .common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_LINK), + .common.link_id = cpu_to_le32(mac_id), }; struct iwl_dev_tx_power_cmd cmd_v9_v10; u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, 3); @@ -1500,9 +1499,16 @@ int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, cmd.common.pwr_restriction = cpu_to_le16(u_tx_power); if (cmd_ver > 8) { + u32 link_id; + + if (WARN_ON(!mvmvif->link[link_conf->link_id])) + return -ENODEV; + + link_id = mvmvif->link[link_conf->link_id]->fw_link_id; + /* Those fields sit on the same place for v9 and v10 */ - cmd_v9_v10.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_MAC); - cmd_v9_v10.common.mac_context_id = cpu_to_le32(mac_id); + cmd_v9_v10.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_LINK); + cmd_v9_v10.common.link_id = cpu_to_le32(link_id); cmd_v9_v10.common.pwr_restriction = cpu_to_le16(u_tx_power); cmd_data = &cmd_v9_v10; } @@ -1802,6 +1808,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw, mvmvif->deflink.active = 0; mvmvif->link[0] = &mvmvif->deflink; + vif->driver_flags = IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC; + ret = iwl_mvm_set_link_mapping(mvm, vif, &vif->bss_conf); if (ret) goto out; @@ -2967,33 +2975,6 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm, &mvm->status), "Failed to update SF upon disassociation\n"); - /* - * If we get an assert during the connection (after the - * station has been added, but before the vif is set - * to associated), mac80211 will re-add the station and - * then configure the vif. Since the vif is not - * associated, we would remove the station here and - * this would fail the recovery. - */ - if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, - &mvm->status)) { - /* first remove remaining keys */ - iwl_mvm_sec_key_remove_ap(mvm, vif, - &mvmvif->deflink, 0); - - /* - * Remove AP station now that - * the MAC is unassoc - */ - ret = iwl_mvm_rm_sta_id(mvm, vif, - mvmvif->deflink.ap_sta_id); - if (ret) - IWL_ERR(mvm, - "failed to remove AP station\n"); - - mvmvif->deflink.ap_sta_id = IWL_INVALID_STA; - } - /* remove quota for this interface */ ret = iwl_mvm_update_quotas(mvm, false, NULL); if (ret) @@ -3913,7 +3894,7 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, if (sta->tdls && (vif->p2p || - iwl_mvm_tdls_sta_count(mvm, NULL) == IWL_MVM_TDLS_STA_COUNT || + iwl_mvm_tdls_sta_count(mvm, NULL) == IWL_TDLS_STA_COUNT || iwl_mvm_phy_ctx_count(mvm) > 1)) { IWL_DEBUG_MAC80211(mvm, "refusing TDLS sta\n"); return -EBUSY; @@ -4113,10 +4094,6 @@ iwl_mvm_sta_state_authorized_to_assoc(struct iwl_mvm *mvm, wiphy_work_cancel(mvm->hw->wiphy, &mvmvif->unblock_esr_tpt_wk); wiphy_delayed_work_cancel(mvm->hw->wiphy, &mvmvif->unblock_esr_tmp_non_bss_wk); - - /* No need for the periodic statistics anymore */ - if (ieee80211_vif_is_mld(vif) && mvmvif->esr_active) - iwl_mvm_request_periodic_system_statistics(mvm, false); } return 0; @@ -5004,34 +4981,46 @@ int iwl_mvm_cancel_roc(struct ieee80211_hw *hw, return 0; } -struct iwl_mvm_ftm_responder_iter_data { - bool responder; +struct iwl_mvm_chanctx_usage_data { + struct iwl_mvm *mvm; struct ieee80211_chanctx_conf *ctx; + bool use_def; }; -static void iwl_mvm_ftm_responder_chanctx_iter(void *_data, u8 *mac, - struct ieee80211_vif *vif) +static void iwl_mvm_chanctx_usage_iter(void *_data, u8 *mac, + struct ieee80211_vif *vif) { - struct iwl_mvm_ftm_responder_iter_data *data = _data; + struct iwl_mvm_chanctx_usage_data *data = _data; + struct ieee80211_bss_conf *link_conf; + int link_id; - if (rcu_access_pointer(vif->bss_conf.chanctx_conf) == data->ctx && - vif->type == NL80211_IFTYPE_AP && vif->bss_conf.ftmr_params) - data->responder = true; + for_each_vif_active_link(vif, link_conf, link_id) { + if (rcu_access_pointer(link_conf->chanctx_conf) != data->ctx) + continue; + + if (iwl_mvm_enable_fils(data->mvm, vif, data->ctx)) + data->use_def = true; + + if (vif->type == NL80211_IFTYPE_AP && link_conf->ftmr_params) + data->use_def = true; + } } -bool iwl_mvm_is_ftm_responder_chanctx(struct iwl_mvm *mvm, - struct ieee80211_chanctx_conf *ctx) +struct cfg80211_chan_def * +iwl_mvm_chanctx_def(struct iwl_mvm *mvm, struct ieee80211_chanctx_conf *ctx) { - struct iwl_mvm_ftm_responder_iter_data data = { - .responder = false, + struct iwl_mvm_chanctx_usage_data data = { + .mvm = mvm, .ctx = ctx, + .use_def = false, }; ieee80211_iterate_active_interfaces_atomic(mvm->hw, - IEEE80211_IFACE_ITER_NORMAL, - iwl_mvm_ftm_responder_chanctx_iter, - &data); - return data.responder; + IEEE80211_IFACE_ITER_NORMAL, + iwl_mvm_chanctx_usage_iter, + &data); + + return data.use_def ? &ctx->def : &ctx->min_def; } static int __iwl_mvm_add_chanctx(struct iwl_mvm *mvm, @@ -5415,7 +5404,7 @@ out_reassign: out_restart: /* things keep failing, better restart the hw */ - iwl_mvm_nic_restart(mvm, false); + iwl_force_nmi(mvm->trans); return ret; } @@ -5451,7 +5440,7 @@ out_reassign: out_restart: /* things keep failing, better restart the hw */ - iwl_mvm_nic_restart(mvm, false); + iwl_force_nmi(mvm->trans); return ret; } @@ -6278,7 +6267,7 @@ void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw, guard(mvm)(mvm); - if (mvmvif->deflink.ap_sta_id != mvmsta->deflink.sta_id) + if (sta != mvmvif->ap_sta) return; if (iwl_mvm_request_statistics(mvm, false)) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c index b807046144c0..341a2a7a49ec 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c @@ -18,6 +18,8 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw, mvmvif->mvm = mvm; + vif->driver_flags |= IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC; + /* Not much to do here. The stack will not allow interface * types or combinations that we didn't advertise, so we * don't really have to check the types. @@ -208,32 +210,6 @@ static unsigned int iwl_mvm_mld_count_active_links(struct iwl_mvm_vif *mvmvif) return n_active; } -static void iwl_mvm_restart_mpdu_count(struct iwl_mvm *mvm, - struct iwl_mvm_vif *mvmvif) -{ - struct ieee80211_sta *ap_sta = mvmvif->ap_sta; - struct iwl_mvm_sta *mvmsta; - - lockdep_assert_held(&mvm->mutex); - - if (!ap_sta) - return; - - mvmsta = iwl_mvm_sta_from_mac80211(ap_sta); - if (!mvmsta->mpdu_counters) - return; - - for (int q = 0; q < mvm->trans->num_rx_queues; q++) { - spin_lock_bh(&mvmsta->mpdu_counters[q].lock); - memset(mvmsta->mpdu_counters[q].per_link, 0, - sizeof(mvmsta->mpdu_counters[q].per_link)); - mvmsta->mpdu_counters[q].window_start = jiffies; - spin_unlock_bh(&mvmsta->mpdu_counters[q].lock); - } - - IWL_DEBUG_INFO(mvm, "MPDU counters are cleared\n"); -} - static int iwl_mvm_esr_mode_active(struct iwl_mvm *mvm, struct ieee80211_vif *vif) { @@ -267,16 +243,6 @@ static int iwl_mvm_esr_mode_active(struct iwl_mvm *mvm, else mvmvif->primary_link = __ffs(vif->active_links); - /* Needed for tracking RSSI */ - iwl_mvm_request_periodic_system_statistics(mvm, true); - - /* - * Restart the MPDU counters and the counting window, so when the - * statistics arrive (which is where we look at the counters) we - * will be at the end of the window. - */ - iwl_mvm_restart_mpdu_count(mvm, mvmvif); - iwl_dbg_tlv_time_point(&mvm->fwrt, IWL_FW_INI_TIME_ESR_LINK_UP, NULL); @@ -323,7 +289,6 @@ __iwl_mvm_mld_assign_vif_chanctx(struct iwl_mvm *mvm, ret = iwl_mvm_esr_mode_active(mvm, vif); if (ret) { IWL_ERR(mvm, "failed to activate ESR mode (%d)\n", ret); - iwl_mvm_request_periodic_system_statistics(mvm, false); goto out; } } @@ -449,11 +414,6 @@ static int iwl_mvm_esr_mode_inactive(struct iwl_mvm *mvm, break; } - iwl_mvm_request_periodic_system_statistics(mvm, false); - - /* Start a new counting window */ - iwl_mvm_restart_mpdu_count(mvm, mvmvif); - iwl_dbg_tlv_time_point(&mvm->fwrt, IWL_FW_INI_TIME_ESR_LINK_DOWN, NULL); @@ -831,30 +791,6 @@ static bool iwl_mvm_mld_vif_have_valid_ap_sta(struct iwl_mvm_vif *mvmvif) return false; } -static void iwl_mvm_mld_vif_delete_all_stas(struct iwl_mvm *mvm, - struct ieee80211_vif *vif) -{ - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - int i, ret; - - if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) - return; - - for_each_mvm_vif_valid_link(mvmvif, i) { - struct iwl_mvm_vif_link_info *link = mvmvif->link[i]; - - if (!link) - continue; - - iwl_mvm_sec_key_remove_ap(mvm, vif, link, i); - ret = iwl_mvm_mld_rm_sta_id(mvm, link->ap_sta_id); - if (ret) - IWL_ERR(mvm, "failed to remove AP station\n"); - - link->ap_sta_id = IWL_INVALID_STA; - } -} - static void iwl_mvm_mld_vif_cfg_changed_station(struct iwl_mvm *mvm, struct ieee80211_vif *vif, u64 changes) @@ -881,8 +817,13 @@ static void iwl_mvm_mld_vif_cfg_changed_station(struct iwl_mvm *mvm, if (vif->cfg.assoc) { mvmvif->session_prot_connection_loss = false; - /* clear statistics to get clean beacon counter */ + /* + * Clear statistics to get clean beacon counter, and ask for + * periodic statistics, as they are needed for link + * selection and RX OMI decisions. + */ iwl_mvm_request_statistics(mvm, true); + iwl_mvm_request_periodic_system_statistics(mvm, true); iwl_mvm_sf_update(mvm, vif, false); iwl_mvm_power_vif_assoc(mvm, vif); @@ -930,6 +871,8 @@ static void iwl_mvm_mld_vif_cfg_changed_station(struct iwl_mvm *mvm, } else if (iwl_mvm_mld_vif_have_valid_ap_sta(mvmvif)) { iwl_mvm_mei_host_disassociated(mvm); + iwl_mvm_request_periodic_system_statistics(mvm, false); + /* If update fails - SF might be running in associated * mode while disassociated - which is forbidden. */ @@ -938,15 +881,6 @@ static void iwl_mvm_mld_vif_cfg_changed_station(struct iwl_mvm *mvm, !test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status), "Failed to update SF upon disassociation\n"); - - /* If we get an assert during the connection (after the - * station has been added, but before the vif is set - * to associated), mac80211 will re-add the station and - * then configure the vif. Since the vif is not - * associated, we would remove the station here and - * this would fail the recovery. - */ - iwl_mvm_mld_vif_delete_all_stas(mvm, vif); } iwl_mvm_bss_info_changed_station_assoc(mvm, vif, changes); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index 019839604011..2f159024eeb8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -518,14 +518,12 @@ static int iwl_mvm_mld_cfg_sta(struct iwl_mvm *mvm, struct ieee80211_sta *sta, void iwl_mvm_mld_free_sta_link(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvm_sta, struct iwl_mvm_link_sta *mvm_sta_link, - unsigned int link_id, - bool is_in_fw) + unsigned int link_id) { lockdep_assert_wiphy(mvm->hw->wiphy); lockdep_assert_held(&mvm->mutex); - RCU_INIT_POINTER(mvm->fw_id_to_mac_id[mvm_sta_link->sta_id], - is_in_fw ? ERR_PTR(-EINVAL) : NULL); + RCU_INIT_POINTER(mvm->fw_id_to_mac_id[mvm_sta_link->sta_id], NULL); RCU_INIT_POINTER(mvm->fw_id_to_link_sta[mvm_sta_link->sta_id], NULL); RCU_INIT_POINTER(mvm_sta->link[link_id], NULL); @@ -546,7 +544,7 @@ static void iwl_mvm_mld_sta_rm_all_sta_links(struct iwl_mvm *mvm, if (!link) continue; - iwl_mvm_mld_free_sta_link(mvm, mvm_sta, link, link_id, false); + iwl_mvm_mld_free_sta_link(mvm, mvm_sta, link, link_id); } } @@ -844,18 +842,11 @@ int iwl_mvm_mld_rm_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct iwl_mvm_link_sta *mvm_link_sta = rcu_dereference_protected(mvm_sta->link[link_id], lockdep_is_held(&mvm->mutex)); - bool stay_in_fw; + iwl_mvm_sta_del(mvm, vif, sta, link_sta); - stay_in_fw = iwl_mvm_sta_del(mvm, vif, sta, link_sta, &ret); - if (ret) - break; + ret = iwl_mvm_mld_rm_sta_from_fw(mvm, mvm_link_sta->sta_id); - if (!stay_in_fw) - ret = iwl_mvm_mld_rm_sta_from_fw(mvm, - mvm_link_sta->sta_id); - - iwl_mvm_mld_free_sta_link(mvm, mvm_sta, mvm_link_sta, - link_id, stay_in_fw); + iwl_mvm_mld_free_sta_link(mvm, mvm_sta, mvm_link_sta, link_id); } kfree(mvm_sta->mpdu_counters); mvm_sta->mpdu_counters = NULL; @@ -1122,8 +1113,7 @@ int iwl_mvm_mld_update_sta_links(struct iwl_mvm *mvm, if (vif->type == NL80211_IFTYPE_STATION) mvm_vif_link->ap_sta_id = IWL_INVALID_STA; - iwl_mvm_mld_free_sta_link(mvm, mvm_sta, mvm_sta_link, link_id, - false); + iwl_mvm_mld_free_sta_link(mvm, mvm_sta, mvm_sta_link, link_id); } for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) { @@ -1227,8 +1217,7 @@ err: rcu_dereference_protected(mvm_sta->link[link_id], lockdep_is_held(&mvm->mutex)); - iwl_mvm_mld_free_sta_link(mvm, mvm_sta, mvm_sta_link, link_id, - false); + iwl_mvm_mld_free_sta_link(mvm, mvm_sta, mvm_sta_link, link_id); } return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 2ad615293c75..ee769da72e68 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -103,6 +103,7 @@ struct iwl_mvm_phy_ctxt { u32 center_freq1; bool rlc_disabled; u32 channel_load_by_us; + u32 channel_load_not_by_us; }; struct iwl_mvm_time_event_data { @@ -1174,8 +1175,6 @@ struct iwl_mvm { struct ieee80211_bss_conf __rcu *link_id_to_link_conf[IWL_FW_MAX_LINK_ID + 1]; - /* -1 for always, 0 for never, >0 for that many times */ - s8 fw_restart; u8 *error_recovery_buf; #ifdef CONFIG_IWLWIFI_LEDS @@ -1401,8 +1400,6 @@ DEFINE_GUARD(mvm, struct iwl_mvm *, mutex_lock(&_T->mutex), mutex_unlock(&_T->mu * @IWL_MVM_STATUS_IN_D3: in D3 (or at least about to go into it) * @IWL_MVM_STATUS_SUPPRESS_ERROR_LOG_ONCE: suppress one error log * if this is set, when intentionally triggered - * @IWL_MVM_STATUS_STARTING: starting mac, - * used to disable restart flow while in STARTING state */ enum iwl_mvm_status { IWL_MVM_STATUS_HW_RFKILL, @@ -1414,7 +1411,6 @@ enum iwl_mvm_status { IWL_MVM_STATUS_FIRMWARE_RUNNING, IWL_MVM_STATUS_IN_D3, IWL_MVM_STATUS_SUPPRESS_ERROR_LOG_ONCE, - IWL_MVM_STATUS_STARTING, }; struct iwl_mvm_csme_conn_info { @@ -1736,12 +1732,19 @@ static inline bool iwl_mvm_is_ctdp_supported(struct iwl_mvm *mvm) static inline bool iwl_mvm_is_esr_supported(struct iwl_trans *trans) { - if ((CSR_HW_RFID_TYPE(trans->hw_rf_id) == IWL_CFG_RF_TYPE_FM) && - !CSR_HW_RFID_IS_CDB(trans->hw_rf_id)) + if (CSR_HW_RFID_IS_CDB(trans->hw_rf_id)) + return false; + + switch (CSR_HW_RFID_TYPE(trans->hw_rf_id)) { + case IWL_CFG_RF_TYPE_FM: /* Step A doesn't support eSR */ return CSR_HW_RFID_STEP(trans->hw_rf_id); - - return false; + case IWL_CFG_RF_TYPE_WH: + case IWL_CFG_RF_TYPE_PE: + return true; + default: + return false; + } } static inline int iwl_mvm_max_active_links(struct iwl_mvm *mvm, @@ -1824,7 +1827,6 @@ u8 iwl_mvm_next_antenna(struct iwl_mvm *mvm, u8 valid, u8 last_idx); void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, int clock_type, u32 *gp2, u64 *boottime, ktime_t *realtime); u32 iwl_mvm_get_systime(struct iwl_mvm *mvm); -u32 iwl_mvm_find_ie_offset(u8 *beacon, u8 eid, u32 frame_size); /* Tx / Host Commands */ int __must_check iwl_mvm_send_cmd(struct iwl_mvm *mvm, @@ -2591,7 +2593,6 @@ void iwl_mvm_tcm_add_vif(struct iwl_mvm *mvm, struct ieee80211_vif *vif); void iwl_mvm_tcm_rm_vif(struct iwl_mvm *mvm, struct ieee80211_vif *vif); u8 iwl_mvm_tcm_load_percentage(u32 airtime, u32 elapsed); -void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error); unsigned int iwl_mvm_get_wd_timeout(struct iwl_mvm *mvm, struct ieee80211_vif *vif); void iwl_mvm_connection_loss(struct iwl_mvm *mvm, struct ieee80211_vif *vif, @@ -2996,18 +2997,11 @@ int iwl_mvm_set_hw_timestamp(struct ieee80211_hw *hw, struct cfg80211_set_hw_timestamp *hwts); int iwl_mvm_update_mu_groups(struct iwl_mvm *mvm, struct ieee80211_vif *vif); bool iwl_mvm_enable_fils(struct iwl_mvm *mvm, + struct ieee80211_vif *vif, struct ieee80211_chanctx_conf *ctx); -bool iwl_mvm_is_ftm_responder_chanctx(struct iwl_mvm *mvm, - struct ieee80211_chanctx_conf *ctx); -static inline struct cfg80211_chan_def * -iwl_mvm_chanctx_def(struct iwl_mvm *mvm, struct ieee80211_chanctx_conf *ctx) -{ - bool use_def = iwl_mvm_is_ftm_responder_chanctx(mvm, ctx) || - iwl_mvm_enable_fils(mvm, ctx); - - return use_def ? &ctx->def : &ctx->min_def; -} +struct cfg80211_chan_def * +iwl_mvm_chanctx_def(struct iwl_mvm *mvm, struct ieee80211_chanctx_conf *ctx); void iwl_mvm_roc_duration_and_delay(struct ieee80211_vif *vif, u32 duration_ms, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 30fcc733395e..984f407f7027 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -208,7 +208,8 @@ static void iwl_mvm_rx_monitor_notif(struct iwl_mvm *mvm, if (notif->type != cpu_to_le32(IWL_DP_MON_NOTIF_TYPE_EXT_CCA)) return; - vif = iwl_mvm_get_vif_by_macid(mvm, notif->mac_id); + /* FIXME: should fetch the link and not the vif */ + vif = iwl_mvm_get_vif_by_macid(mvm, notif->link_id); if (!vif || vif->type != NL80211_IFTYPE_STATION) return; @@ -408,7 +409,7 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = { RX_HANDLER_SYNC, struct iwl_time_event_notif), RX_HANDLER_GRP(MAC_CONF_GROUP, SESSION_PROTECTION_NOTIF, iwl_mvm_rx_session_protect_notif, RX_HANDLER_SYNC, - struct iwl_mvm_session_prot_notif), + struct iwl_session_prot_notif), RX_HANDLER(MCC_CHUB_UPDATE_CMD, iwl_mvm_rx_chub_update_mcc, RX_HANDLER_ASYNC_LOCKED, struct iwl_mcc_chub_notif), @@ -1285,6 +1286,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, size_t scan_size; u32 min_backoff; struct iwl_mvm_csme_conn_info *csme_conn_info __maybe_unused; + int err; /* * We use IWL_STATION_COUNT_MAX to check the validity of the station @@ -1302,7 +1304,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, iwl_mvm_has_mld_api(fw) ? &iwl_mvm_mld_hw_ops : &iwl_mvm_hw_ops); if (!hw) - return NULL; + return ERR_PTR(-ENOMEM); if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) max_agg = 512; @@ -1331,6 +1333,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, iwl_mvm_get_bios_tables(mvm); iwl_uefi_get_sgom_table(trans, &mvm->fwrt); iwl_uefi_get_step_table(trans); + iwl_bios_setup_step(trans, &mvm->fwrt); mvm->init_status = 0; @@ -1346,11 +1349,12 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, trans->rx_mpdu_cmd_hdr_size = sizeof(struct iwl_rx_mpdu_res_start); - if (WARN_ON(trans->num_rx_queues > 1)) + if (WARN_ON(trans->num_rx_queues > 1)) { + err = -EINVAL; goto out_free; + } } - mvm->fw_restart = iwlwifi_mod_params.fw_restart ? -1 : 0; mvm->bios_enable_puncturing = iwl_uefi_get_puncturing(&mvm->fwrt); if (iwl_mvm_has_new_tx_api(mvm)) { @@ -1424,8 +1428,10 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, iwl_fw_lookup_notif_ver(mvm->fw, LOCATION_GROUP, TOF_RANGE_RESPONSE_NOTIF, 5); /* we only support up to version 9 */ - if (WARN_ON_ONCE(mvm->cmd_ver.range_resp > 9)) + if (WARN_ON_ONCE(mvm->cmd_ver.range_resp > 9)) { + err = -EINVAL; goto out_free; + } /* * Populate the state variables that the transport layer needs @@ -1474,9 +1480,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, trans->rx_mpdu_cmd = REPLY_RX_MPDU_CMD; trans->dbg.dest_tlv = mvm->fw->dbg.dest_tlv; trans->dbg.n_dest_reg = mvm->fw->dbg.n_dest_reg; - memcpy(trans->dbg.conf_tlv, mvm->fw->dbg.conf_tlv, - sizeof(trans->dbg.conf_tlv)); - trans->dbg.trigger_tlv = mvm->fw->dbg.trigger_tlv; trans->iml = mvm->fw->iml; trans->iml_len = mvm->fw->iml_len; @@ -1488,6 +1491,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, mvm->phy_db = iwl_phy_db_init(trans); if (!mvm->phy_db) { IWL_ERR(mvm, "Cannot init phy_db\n"); + err = -ENOMEM; goto out_free; } @@ -1500,8 +1504,10 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, scan_size = iwl_mvm_scan_size(mvm); mvm->scan_cmd = kmalloc(scan_size, GFP_KERNEL); - if (!mvm->scan_cmd) + if (!mvm->scan_cmd) { + err = -ENOMEM; goto out_free; + } mvm->scan_cmd_size = scan_size; /* invalidate ids to prevent accidental removal of sta_id 0 */ @@ -1530,7 +1536,8 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, iwl_mvm_mei_scan_filter_init(&mvm->mei_scan_filter); - if (iwl_mvm_start_get_nvm(mvm)) { + err = iwl_mvm_start_get_nvm(mvm); + if (err) { /* * Getting NVM failed while CSME is the owner, but we are * registered to MEI, we'll get the NVM later when it'll be @@ -1543,7 +1550,8 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, } - if (iwl_mvm_start_post_nvm(mvm)) + err = iwl_mvm_start_post_nvm(mvm); + if (err) goto out_thermal_exit; return op_mode; @@ -1563,7 +1571,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, iwl_trans_op_mode_leave(trans); ieee80211_free_hw(mvm->hw); - return NULL; + return ERR_PTR(err); } void iwl_mvm_stop_device(struct iwl_mvm *mvm) @@ -1998,28 +2006,63 @@ static void iwl_mvm_free_skb(struct iwl_op_mode *op_mode, struct sk_buff *skb) ieee80211_free_txskb(mvm->hw, skb); } -struct iwl_mvm_reprobe { - struct device *dev; - struct work_struct work; -}; - -static void iwl_mvm_reprobe_wk(struct work_struct *wk) +static void iwl_mvm_nic_error(struct iwl_op_mode *op_mode, + enum iwl_fw_error_type type) { - struct iwl_mvm_reprobe *reprobe; + struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); - reprobe = container_of(wk, struct iwl_mvm_reprobe, work); - if (device_reprobe(reprobe->dev)) - dev_err(reprobe->dev, "reprobe failed!\n"); - put_device(reprobe->dev); - kfree(reprobe); - module_put(THIS_MODULE); -} - -void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error) -{ iwl_abort_notification_waits(&mvm->notif_wait); iwl_dbg_tlv_del_timers(mvm->trans); + if (type == IWL_ERR_TYPE_CMD_QUEUE_FULL) + IWL_ERR(mvm, "Command queue full!\n"); + else if (!test_bit(STATUS_TRANS_DEAD, &mvm->trans->status) && + !test_and_clear_bit(IWL_MVM_STATUS_SUPPRESS_ERROR_LOG_ONCE, + &mvm->status)) + iwl_mvm_dump_nic_error_log(mvm); + + /* + * This should be first thing before trying to collect any + * data to avoid endless loops if any HW error happens while + * collecting debug data. + * It might not actually be true that we'll restart, but the + * setting of the bit doesn't matter if we're going to be + * unbound either. + */ + if (type != IWL_ERR_TYPE_RESET_HS_TIMEOUT) + set_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status); +} + +static void iwl_mvm_dump_error(struct iwl_op_mode *op_mode, + struct iwl_fw_error_dump_mode *mode) +{ + struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); + + /* if we come in from opmode we have the mutex held */ + if (mode->context == IWL_ERR_CONTEXT_FROM_OPMODE) { + lockdep_assert_held(&mvm->mutex); + iwl_fw_error_collect(&mvm->fwrt); + } else { + mutex_lock(&mvm->mutex); + if (mode->context != IWL_ERR_CONTEXT_ABORT) + iwl_fw_error_collect(&mvm->fwrt); + mutex_unlock(&mvm->mutex); + } +} + +static bool iwl_mvm_sw_reset(struct iwl_op_mode *op_mode, + enum iwl_fw_error_type type) +{ + struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); + + /* + * If the firmware crashes while we're already considering it + * to be dead then don't ask for a restart, that cannot do + * anything useful anyway. + */ + if (!test_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status)) + return false; + /* * This is a bit racy, but worst case we tell mac80211 about * a stopped/aborted scan when that was already done which @@ -2033,52 +2076,11 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error) iwl_mvm_report_scan_aborted(mvm); /* - * If we're restarting already, don't cycle restarts. * If INIT fw asserted, it will likely fail again. * If WoWLAN fw asserted, don't restart either, mac80211 * can't recover this since we're already half suspended. */ - if (!mvm->fw_restart && fw_error) { - iwl_fw_error_collect(&mvm->fwrt, false); - } else if (test_bit(IWL_MVM_STATUS_STARTING, - &mvm->status)) { - IWL_ERR(mvm, "Starting mac, retry will be triggered anyway\n"); - } else if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) { - struct iwl_mvm_reprobe *reprobe; - - IWL_ERR(mvm, - "Firmware error during reconfiguration - reprobe!\n"); - - /* - * get a module reference to avoid doing this while unloading - * anyway and to avoid scheduling a work with code that's - * being removed. - */ - if (!try_module_get(THIS_MODULE)) { - IWL_ERR(mvm, "Module is being unloaded - abort\n"); - return; - } - - reprobe = kzalloc(sizeof(*reprobe), GFP_ATOMIC); - if (!reprobe) { - module_put(THIS_MODULE); - return; - } - reprobe->dev = get_device(mvm->trans->dev); - INIT_WORK(&reprobe->work, iwl_mvm_reprobe_wk); - schedule_work(&reprobe->work); - } else if (test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, - &mvm->status)) { - IWL_ERR(mvm, "HW restart already requested, but not started\n"); - } else if (mvm->fwrt.cur_fw_img == IWL_UCODE_REGULAR && - mvm->hw_registered && - !test_bit(STATUS_TRANS_DEAD, &mvm->trans->status)) { - /* This should be first thing before trying to collect any - * data to avoid endless loops if any HW error happens while - * collecting debug data. - */ - set_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status); - + if (mvm->fwrt.cur_fw_img == IWL_UCODE_REGULAR && mvm->hw_registered) { if (mvm->fw->ucode_capa.error_log_size) { u32 src_size = mvm->fw->ucode_capa.error_log_size; u32 src_addr = mvm->fw->ucode_capa.error_log_addr; @@ -2093,57 +2095,18 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error) } } - iwl_fw_error_collect(&mvm->fwrt, false); - - if (fw_error && mvm->fw_restart > 0) { - mvm->fw_restart--; - ieee80211_restart_hw(mvm->hw); - } else if (mvm->fwrt.trans->dbg.restart_required) { + if (mvm->fwrt.trans->dbg.restart_required) { IWL_DEBUG_INFO(mvm, "FW restart requested after debug collection\n"); mvm->fwrt.trans->dbg.restart_required = false; ieee80211_restart_hw(mvm->hw); + return true; } else if (mvm->trans->trans_cfg->device_family <= IWL_DEVICE_FAMILY_8000) { ieee80211_restart_hw(mvm->hw); + return true; } } -} -static void iwl_mvm_nic_error(struct iwl_op_mode *op_mode, bool sync) -{ - struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); - - if (!test_bit(STATUS_TRANS_DEAD, &mvm->trans->status) && - !test_and_clear_bit(IWL_MVM_STATUS_SUPPRESS_ERROR_LOG_ONCE, - &mvm->status)) - iwl_mvm_dump_nic_error_log(mvm); - - if (sync) { - iwl_fw_error_collect(&mvm->fwrt, true); - /* - * Currently, the only case for sync=true is during - * shutdown, so just stop in this case. If/when that - * changes, we need to be a bit smarter here. - */ - return; - } - - /* - * If the firmware crashes while we're already considering it - * to be dead then don't ask for a restart, that cannot do - * anything useful anyway. - */ - if (!test_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status)) - return; - - iwl_mvm_nic_restart(mvm, false); -} - -static void iwl_mvm_cmd_queue_full(struct iwl_op_mode *op_mode) -{ - struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); - - WARN_ON(1); - iwl_mvm_nic_restart(mvm, true); + return false; } static void iwl_op_mode_mvm_time_point(struct iwl_op_mode *op_mode, @@ -2179,7 +2142,8 @@ static void iwl_op_mode_mvm_device_powered_off(struct iwl_op_mode *op_mode) .hw_rf_kill = iwl_mvm_set_hw_rfkill_state, \ .free_skb = iwl_mvm_free_skb, \ .nic_error = iwl_mvm_nic_error, \ - .cmd_queue_full = iwl_mvm_cmd_queue_full, \ + .dump_error = iwl_mvm_dump_error, \ + .sw_reset = iwl_mvm_sw_reset, \ .nic_config = iwl_mvm_nic_config, \ /* as we only register one, these MUST be common! */ \ .start = iwl_op_mode_mvm_start, \ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c index 7cab5373c8ae..5e7e2926be0c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c @@ -31,7 +31,7 @@ u8 iwl_mvm_get_channel_width(const struct cfg80211_chan_def *chandef) /* * Maps the driver specific control channel position (relative to the center - * freq) definitions to the the fw values + * freq) definitions to the fw values */ u8 iwl_mvm_get_ctrl_pos(const struct cfg80211_chan_def *chandef) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/power.c b/drivers/net/wireless/intel/iwlwifi/mvm/power.c index bc363e8427e4..a386b315e52f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/power.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/power.c @@ -567,7 +567,7 @@ struct iwl_power_vifs { bool monitor_active; }; -static void iwl_mvm_power_disable_pm_iterator(void *_data, u8* mac, +static void iwl_mvm_power_disable_pm_iterator(void *_data, u8 *mac, struct ieee80211_vif *vif) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); @@ -575,7 +575,7 @@ static void iwl_mvm_power_disable_pm_iterator(void *_data, u8* mac, mvmvif->pm_enabled = false; } -static void iwl_mvm_power_ps_disabled_iterator(void *_data, u8* mac, +static void iwl_mvm_power_ps_disabled_iterator(void *_data, u8 *mac, struct ieee80211_vif *vif) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c index 9e72db9bab40..2dbef7b46355 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c @@ -789,6 +789,8 @@ static void iwl_mvm_handle_per_phy_stats(struct iwl_mvm *mvm, continue; mvm->phy_ctxts[i].channel_load_by_us = le32_to_cpu(per_phy[i].channel_load_by_us); + mvm->phy_ctxts[i].channel_load_not_by_us = + le32_to_cpu(per_phy[i].channel_load_not_by_us); } } @@ -962,6 +964,9 @@ iwl_mvm_stat_iterator_all_links(struct iwl_mvm *mvm, #define SEC_LINK_MIN_TX 3000 #define SEC_LINK_MIN_RX 400 +/* Accept a ~20% short window to avoid issues due to jitter */ +#define IWL_MVM_TPT_MIN_COUNT_WINDOW (IWL_MVM_TPT_COUNT_WINDOW_SEC * HZ * 4 / 5) + static void iwl_mvm_update_esr_mode_tpt(struct iwl_mvm *mvm) { struct ieee80211_vif *bss_vif = iwl_mvm_get_bss_vif(mvm); @@ -971,6 +976,7 @@ static void iwl_mvm_update_esr_mode_tpt(struct iwl_mvm *mvm) unsigned long sec_link_tx = 0, sec_link_rx = 0; u8 sec_link_tx_perc, sec_link_rx_perc; u8 sec_link; + bool skip = false; lockdep_assert_held(&mvm->mutex); @@ -1010,13 +1016,25 @@ static void iwl_mvm_update_esr_mode_tpt(struct iwl_mvm *mvm) /* * In EMLSR we have statistics every 5 seconds, so we can reset * the counters upon every statistics notification. + * The FW sends the notification regularly, but it will be + * misaligned at the start. Skipping the measurement if it is + * short will synchronize us. */ + if (jiffies - mvmsta->mpdu_counters[q].window_start < + IWL_MVM_TPT_MIN_COUNT_WINDOW) + skip = true; + mvmsta->mpdu_counters[q].window_start = jiffies; memset(mvmsta->mpdu_counters[q].per_link, 0, sizeof(mvmsta->mpdu_counters[q].per_link)); spin_unlock_bh(&mvmsta->mpdu_counters[q].lock); } + if (skip) { + IWL_DEBUG_INFO(mvm, "MPDU statistics window was short\n"); + return; + } + IWL_DEBUG_INFO(mvm, "total Tx MPDUs: %ld. total Rx MPDUs: %ld\n", total_tx, total_rx); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index a2f16bfaec44..09fd8752046e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -636,15 +636,21 @@ static void iwl_mvm_release_frames_from_notif(struct iwl_mvm *mvm, IWL_DEBUG_HT(mvm, "Frame release notification for BAID %u, NSSN %d\n", baid, nssn); - if (WARN_ON_ONCE(baid == IWL_RX_REORDER_DATA_INVALID_BAID || - baid >= ARRAY_SIZE(mvm->baid_map))) + if (IWL_FW_CHECK(mvm, + baid == IWL_RX_REORDER_DATA_INVALID_BAID || + baid >= ARRAY_SIZE(mvm->baid_map), + "invalid BAID from FW: %d\n", baid)) return; rcu_read_lock(); ba_data = rcu_dereference(mvm->baid_map[baid]); - if (WARN(!ba_data, "BAID %d not found in map\n", baid)) + if (!ba_data) { + IWL_DEBUG_RX(mvm, + "Got valid BAID %d but not allocated, invalid frame release!\n", + baid); goto out; + } /* pick any STA ID to find the pointer */ sta_id = ffs(ba_data->sta_mask) - 1; @@ -2506,19 +2512,24 @@ void iwl_mvm_rx_bar_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi, { struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_bar_frame_release *release = (void *)pkt->data; - unsigned int baid = le32_get_bits(release->ba_info, - IWL_BAR_FRAME_RELEASE_BAID_MASK); - unsigned int nssn = le32_get_bits(release->ba_info, - IWL_BAR_FRAME_RELEASE_NSSN_MASK); - unsigned int sta_id = le32_get_bits(release->sta_tid, - IWL_BAR_FRAME_RELEASE_STA_MASK); - unsigned int tid = le32_get_bits(release->sta_tid, - IWL_BAR_FRAME_RELEASE_TID_MASK); struct iwl_mvm_baid_data *baid_data; + u32 pkt_len = iwl_rx_packet_payload_len(pkt); + unsigned int baid, nssn, sta_id, tid; - if (unlikely(iwl_rx_packet_payload_len(pkt) < sizeof(*release))) + if (IWL_FW_CHECK(mvm, pkt_len < sizeof(*release), + "Unexpected frame release notif size %d (expected %zu)\n", + pkt_len, sizeof(*release))) return; + baid = le32_get_bits(release->ba_info, + IWL_BAR_FRAME_RELEASE_BAID_MASK); + nssn = le32_get_bits(release->ba_info, + IWL_BAR_FRAME_RELEASE_NSSN_MASK); + sta_id = le32_get_bits(release->sta_tid, + IWL_BAR_FRAME_RELEASE_STA_MASK); + tid = le32_get_bits(release->sta_tid, + IWL_BAR_FRAME_RELEASE_TID_MASK); + if (WARN_ON_ONCE(baid == IWL_RX_REORDER_DATA_INVALID_BAID || baid >= ARRAY_SIZE(mvm->baid_map))) return; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 376b9b12fa62..60bd9c7e5f03 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -462,7 +462,7 @@ static int iwl_ssid_exist(u8 *ssid, u8 ssid_len, struct iwl_ssid_ie *ssid_list) if (!ssid_list[i].len) break; if (ssid_list[i].len == ssid_len && - !memcmp(ssid_list->ssid, ssid, ssid_len)) + !memcmp(ssid_list[i].ssid, ssid, ssid_len)) return i; } return -1; @@ -3477,7 +3477,7 @@ void iwl_mvm_report_scan_aborted(struct iwl_mvm *mvm) * restart_hw, so do not report if FW is about to be * restarted. */ - if (!mvm->fw_restart) + if (!iwlwifi_mod_params.fw_restart) ieee80211_sched_scan_stopped(mvm->hw); mvm->sched_scan_pass_all = SCHED_SCAN_PASS_ALL_DISABLED; mvm->scan_uid_status[uid] = 0; @@ -3528,7 +3528,7 @@ void iwl_mvm_report_scan_aborted(struct iwl_mvm *mvm) * restarted. */ if ((mvm->scan_status & IWL_MVM_SCAN_SCHED) && - !mvm->fw_restart) { + !iwlwifi_mod_params.fw_restart) { ieee80211_sched_scan_stopped(mvm->hw); mvm->sched_scan_pass_all = SCHED_SCAN_PASS_ALL_DISABLED; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index cd74c181c260..7a4844ec3c10 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1520,7 +1520,12 @@ void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk) struct iwl_mvm *mvm = container_of(wk, struct iwl_mvm, add_stream_wk); - mutex_lock(&mvm->mutex); + guard(mvm)(mvm); + + /* will reschedule to run after restart */ + if (test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) || + test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) + return; iwl_mvm_inactivity_check(mvm, IWL_INVALID_STA); @@ -1564,8 +1569,6 @@ void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk) iwl_mvm_mac_itxq_xmit(mvm->hw, txq); local_bh_enable(); } - - mutex_unlock(&mvm->mutex); } static int iwl_mvm_reserve_sta_stream(struct iwl_mvm *mvm, @@ -2045,9 +2048,9 @@ int iwl_mvm_wait_sta_queues_empty(struct iwl_mvm *mvm, * Returns if we're done with removing the station, either * with error or success */ -bool iwl_mvm_sta_del(struct iwl_mvm *mvm, struct ieee80211_vif *vif, +void iwl_mvm_sta_del(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct ieee80211_sta *sta, - struct ieee80211_link_sta *link_sta, int *ret) + struct ieee80211_link_sta *link_sta) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm_vif_link_info *mvm_link = @@ -2063,38 +2066,12 @@ bool iwl_mvm_sta_del(struct iwl_mvm *mvm, struct ieee80211_vif *vif, lockdep_is_held(&mvm->mutex)); sta_id = mvm_link_sta->sta_id; - /* If there is a TXQ still marked as reserved - free it */ - if (mvm_sta->reserved_queue != IEEE80211_INVAL_HW_QUEUE) { - u8 reserved_txq = mvm_sta->reserved_queue; - enum iwl_mvm_queue_status *status; - - /* - * If no traffic has gone through the reserved TXQ - it - * is still marked as IWL_MVM_QUEUE_RESERVED, and - * should be manually marked as free again - */ - status = &mvm->queue_info[reserved_txq].status; - if (WARN((*status != IWL_MVM_QUEUE_RESERVED) && - (*status != IWL_MVM_QUEUE_FREE), - "sta_id %d reserved txq %d status %d", - sta_id, reserved_txq, *status)) { - *ret = -EINVAL; - return true; - } - - *status = IWL_MVM_QUEUE_FREE; - } - if (vif->type == NL80211_IFTYPE_STATION && mvm_link->ap_sta_id == sta_id) { - /* if associated - we can't remove the AP STA now */ - if (vif->cfg.assoc) - return true; - /* first remove remaining keys */ - iwl_mvm_sec_key_remove_ap(mvm, vif, mvm_link, 0); + iwl_mvm_sec_key_remove_ap(mvm, vif, mvm_link, + link_sta->link_id); - /* unassoc - go ahead - remove the AP STA now */ mvm_link->ap_sta_id = IWL_INVALID_STA; } @@ -2106,8 +2083,6 @@ bool iwl_mvm_sta_del(struct iwl_mvm *mvm, struct ieee80211_vif *vif, mvm->tdls_cs.peer.sta_id = IWL_INVALID_STA; cancel_delayed_work(&mvm->tdls_cs.dwork); } - - return false; } int iwl_mvm_rm_sta(struct iwl_mvm *mvm, @@ -2143,8 +2118,27 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm, iwl_mvm_disable_sta_queues(mvm, vif, sta); - if (iwl_mvm_sta_del(mvm, vif, sta, &sta->deflink, &ret)) - return ret; + /* If there is a TXQ still marked as reserved - free it */ + if (mvm_sta->reserved_queue != IEEE80211_INVAL_HW_QUEUE) { + u8 reserved_txq = mvm_sta->reserved_queue; + enum iwl_mvm_queue_status *status; + + /* + * If no traffic has gone through the reserved TXQ - it + * is still marked as IWL_MVM_QUEUE_RESERVED, and + * should be manually marked as free again + */ + status = &mvm->queue_info[reserved_txq].status; + if (WARN((*status != IWL_MVM_QUEUE_RESERVED) && + (*status != IWL_MVM_QUEUE_FREE), + "sta_id %d reserved txq %d status %d", + mvm_sta->deflink.sta_id, reserved_txq, *status)) + return -EINVAL; + + *status = IWL_MVM_QUEUE_FREE; + } + + iwl_mvm_sta_del(mvm, vif, sta, &sta->deflink); ret = iwl_mvm_rm_sta_common(mvm, mvm_sta->deflink.sta_id); RCU_INIT_POINTER(mvm->fw_id_to_mac_id[mvm_sta->deflink.sta_id], NULL); @@ -2912,7 +2906,7 @@ int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta, /* * The division below will be OK if either the cache line size * can be divided by the entry size (ALIGN will round up) or if - * if the entry size can be divided by the cache line size, in + * the entry size can be divided by the cache line size, in * which case the ALIGN() will do nothing. */ BUILD_BUG_ON(SMP_CACHE_BYTES % sizeof(baid_data->entries[0]) && diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index 4a3799ae7c18..6856f7440ef3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -133,7 +133,7 @@ struct iwl_mvm_vif; * and no TID data as this is also not needed. * One thing to note, is that these stations have an ID in the fw, but not * in mac80211. In order to "reserve" them a sta_id in %fw_id_to_mac_id - * we fill ERR_PTR(EINVAL) in this mapping and all other dereferencing of + * we fill ERR_PTR(-EINVAL) in this mapping and all other dereferencing of * pointers from this mapping need to check that the value is not error * or NULL. * @@ -507,9 +507,9 @@ void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm, struct ieee80211_sta *sta); int iwl_mvm_wait_sta_queues_empty(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvm_sta); -bool iwl_mvm_sta_del(struct iwl_mvm *mvm, struct ieee80211_vif *vif, +void iwl_mvm_sta_del(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct ieee80211_sta *sta, - struct ieee80211_link_sta *link_sta, int *ret); + struct ieee80211_link_sta *link_sta); int iwl_mvm_rm_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct ieee80211_sta *sta); @@ -665,8 +665,7 @@ int iwl_mvm_mld_rm_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, void iwl_mvm_mld_free_sta_link(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvm_sta, struct iwl_mvm_link_sta *mvm_sta_link, - unsigned int link_id, - bool is_in_fw); + unsigned int link_id); int iwl_mvm_mld_rm_sta_id(struct iwl_mvm *mvm, u8 sta_id); int iwl_mvm_mld_update_sta_links(struct iwl_mvm *mvm, struct ieee80211_vif *vif, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c index 65927ebbabb7..36379b738de1 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c @@ -24,7 +24,7 @@ void iwl_mvm_teardown_tdls_peers(struct iwl_mvm *mvm) for (i = 0; i < mvm->fw->ucode_capa.num_stations; i++) { sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[i], lockdep_is_held(&mvm->mutex)); - if (!sta || IS_ERR(sta) || !sta->tdls) + if (IS_ERR_OR_NULL(sta) || !sta->tdls) continue; mvmsta = iwl_mvm_sta_from_mac80211(sta); @@ -47,7 +47,7 @@ int iwl_mvm_tdls_sta_count(struct iwl_mvm *mvm, struct ieee80211_vif *vif) for (i = 0; i < mvm->fw->ucode_capa.num_stations; i++) { sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[i], lockdep_is_held(&mvm->mutex)); - if (!sta || IS_ERR(sta) || !sta->tdls) + if (IS_ERR_OR_NULL(sta) || !sta->tdls) continue; if (vif) { @@ -472,7 +472,7 @@ void iwl_mvm_tdls_ch_switch_work(struct work_struct *work) mvm->fw_id_to_mac_id[mvm->tdls_cs.peer.sta_id], lockdep_is_held(&mvm->mutex)); /* the station may not be here, but if it is, it must be a TDLS peer */ - if (!sta || IS_ERR(sta) || WARN_ON(!sta->tdls)) + if (IS_ERR_OR_NULL(sta) || WARN_ON(!sta->tdls)) return; mvmsta = iwl_mvm_sta_from_mac80211(sta); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c b/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c index 1dc57e022191..d692f1813d44 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c @@ -262,7 +262,7 @@ static const struct valid_link_pair_case { .desc = "LB + HB, no BT.", .chan_a = &chan_2ghz, .chan_b = &chan_5ghz, - .valid = false, + .valid = true, }, { .desc = "LB + HB, with BT.", diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 72fa7ac86516..9216c43a35c4 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -751,7 +751,7 @@ static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm, u32 id, s8 link_id) { int mac_link_id = iwl_mvm_get_session_prot_id(mvm, vif, link_id); - struct iwl_mvm_session_prot_cmd cmd = { + struct iwl_session_prot_cmd cmd = { .id_and_color = cpu_to_le32(mac_link_id), .action = cpu_to_le32(FW_CTXT_ACTION_REMOVE), .conf_id = cpu_to_le32(id), @@ -955,7 +955,7 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) { struct iwl_rx_packet *pkt = rxb_addr(rxb); - struct iwl_mvm_session_prot_notif *notif = (void *)pkt->data; + struct iwl_session_prot_notif *notif = (void *)pkt->data; unsigned int ver = iwl_fw_lookup_notif_ver(mvm->fw, MAC_CONF_GROUP, SESSION_PROTECTION_NOTIF, 2); @@ -1148,7 +1148,7 @@ iwl_mvm_start_p2p_roc_session_protection(struct iwl_mvm *mvm, enum ieee80211_roc_type type) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm_session_prot_cmd cmd = { + struct iwl_session_prot_cmd cmd = { .id_and_color = cpu_to_le32(iwl_mvm_get_session_prot_id(mvm, vif, 0)), .action = cpu_to_le32(FW_CTXT_ACTION_ADD), @@ -1417,7 +1417,7 @@ static bool iwl_mvm_session_prot_notif(struct iwl_notif_wait_data *notif_wait, { struct iwl_mvm *mvm = container_of(notif_wait, struct iwl_mvm, notif_wait); - struct iwl_mvm_session_prot_notif *resp; + struct iwl_session_prot_notif *resp; int resp_len = iwl_rx_packet_payload_len(pkt); if (WARN_ON(pkt->hdr.cmd != SESSION_PROTECTION_NOTIF || @@ -1449,7 +1449,7 @@ void iwl_mvm_schedule_session_protection(struct iwl_mvm *mvm, const u16 notif[] = { WIDE_ID(MAC_CONF_GROUP, SESSION_PROTECTION_NOTIF) }; struct iwl_notification_wait wait_notif; int mac_link_id = iwl_mvm_get_session_prot_id(mvm, vif, (s8)link_id); - struct iwl_mvm_session_prot_cmd cmd = { + struct iwl_session_prot_cmd cmd = { .id_and_color = cpu_to_le32(mac_link_id), .action = cpu_to_le32(FW_CTXT_ACTION_ADD), .conf_id = cpu_to_le32(SESSION_PROTECT_CONF_ASSOC), diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index c9867d26361b..f67afb66ef2b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -13,6 +13,7 @@ #include "iwl-trans.h" #include "iwl-nvm-utils.h" +#include "iwl-utils.h" #include "mvm.h" #include "sta.h" #include "time-sync.h" @@ -938,78 +939,6 @@ unsigned int iwl_mvm_max_amsdu_size(struct iwl_mvm *mvm, #ifdef CONFIG_INET -static int -iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, - netdev_features_t netdev_flags, - struct sk_buff_head *mpdus_skb) -{ - struct sk_buff *tmp, *next; - struct ieee80211_hdr *hdr = (void *)skb->data; - char cb[sizeof(skb->cb)]; - u16 i = 0; - unsigned int tcp_payload_len; - unsigned int mss = skb_shinfo(skb)->gso_size; - bool ipv4 = (skb->protocol == htons(ETH_P_IP)); - bool qos = ieee80211_is_data_qos(hdr->frame_control); - u16 ip_base_id = ipv4 ? ntohs(ip_hdr(skb)->id) : 0; - - skb_shinfo(skb)->gso_size = num_subframes * mss; - memcpy(cb, skb->cb, sizeof(cb)); - - next = skb_gso_segment(skb, netdev_flags); - skb_shinfo(skb)->gso_size = mss; - skb_shinfo(skb)->gso_type = ipv4 ? SKB_GSO_TCPV4 : SKB_GSO_TCPV6; - - if (IS_ERR(next) && PTR_ERR(next) == -ENOMEM) - return -ENOMEM; - - if (WARN_ONCE(IS_ERR(next), - "skb_gso_segment error: %d\n", (int)PTR_ERR(next))) - return PTR_ERR(next); - - if (next) - consume_skb(skb); - - skb_list_walk_safe(next, tmp, next) { - memcpy(tmp->cb, cb, sizeof(tmp->cb)); - /* - * Compute the length of all the data added for the A-MSDU. - * This will be used to compute the length to write in the TX - * command. We have: SNAP + IP + TCP for n -1 subframes and - * ETH header for n subframes. - */ - tcp_payload_len = skb_tail_pointer(tmp) - - skb_transport_header(tmp) - - tcp_hdrlen(tmp) + tmp->data_len; - - if (ipv4) - ip_hdr(tmp)->id = htons(ip_base_id + i * num_subframes); - - if (tcp_payload_len > mss) { - skb_shinfo(tmp)->gso_size = mss; - skb_shinfo(tmp)->gso_type = ipv4 ? SKB_GSO_TCPV4 : - SKB_GSO_TCPV6; - } else { - if (qos) { - u8 *qc; - - if (ipv4) - ip_send_check(ip_hdr(tmp)); - - qc = ieee80211_get_qos_ctl((void *)tmp->data); - *qc &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT; - } - skb_shinfo(tmp)->gso_size = 0; - } - - skb_mark_not_on_list(tmp); - __skb_queue_tail(mpdus_skb, tmp); - i++; - } - - return 0; -} - static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, struct ieee80211_tx_info *info, struct ieee80211_sta *sta, @@ -1028,7 +957,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, if (!mvmsta->max_amsdu_len || !ieee80211_is_data_qos(hdr->frame_control) || !mvmsta->amsdu_enabled) - return iwl_mvm_tx_tso_segment(skb, 1, netdev_flags, mpdus_skb); + return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skb); /* * Do not build AMSDU for IPv6 with extension headers. @@ -1038,7 +967,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, ((struct ipv6hdr *)skb_network_header(skb))->nexthdr != IPPROTO_TCP) { netdev_flags &= ~NETIF_F_CSUM_MASK; - return iwl_mvm_tx_tso_segment(skb, 1, netdev_flags, mpdus_skb); + return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skb); } tid = ieee80211_get_tid(hdr); @@ -1052,7 +981,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, if ((info->flags & IEEE80211_TX_CTL_AMPDU && !mvmsta->tid_data[tid].amsdu_in_ampdu_allowed) || !(mvmsta->amsdu_enabled & BIT(tid))) - return iwl_mvm_tx_tso_segment(skb, 1, netdev_flags, mpdus_skb); + return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skb); /* * Take the min of ieee80211 station and mvm station @@ -1110,8 +1039,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, * Trick the segmentation function to make it * create SKBs that can fit into one A-MSDU. */ - return iwl_mvm_tx_tso_segment(skb, num_subframes, netdev_flags, - mpdus_skb); + return iwl_tx_tso_segment(skb, num_subframes, netdev_flags, mpdus_skb); } #else /* CONFIG_INET */ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, @@ -1698,8 +1626,8 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm, int txq_id = SEQ_TO_QUEUE(sequence); /* struct iwl_tx_resp_v3 is almost the same */ struct iwl_tx_resp *tx_resp = (void *)pkt->data; - int sta_id = IWL_MVM_TX_RES_GET_RA(tx_resp->ra_tid); - int tid = IWL_MVM_TX_RES_GET_TID(tx_resp->ra_tid); + int sta_id = IWL_TX_RES_GET_RA(tx_resp->ra_tid); + int tid = IWL_TX_RES_GET_TID(tx_resp->ra_tid); struct agg_tx_status *agg_status = iwl_mvm_get_agg_status(mvm, tx_resp); u32 status = le16_to_cpu(agg_status->status); @@ -1880,7 +1808,9 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm, IWL_DEBUG_TX_REPLY(mvm, "Next reclaimed packet:%d\n", next_reclaimed); - iwl_mvm_count_mpdu(mvmsta, sta_id, 1, true, 0); + if (tid < IWL_MAX_TID_COUNT) + iwl_mvm_count_mpdu(mvmsta, sta_id, 1, + true, 0); } else { IWL_DEBUG_TX_REPLY(mvm, "NDP - don't update next_reclaimed\n"); @@ -1989,8 +1919,8 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm, struct iwl_rx_packet *pkt) { struct iwl_tx_resp *tx_resp = (void *)pkt->data; - int sta_id = IWL_MVM_TX_RES_GET_RA(tx_resp->ra_tid); - int tid = IWL_MVM_TX_RES_GET_TID(tx_resp->ra_tid); + int sta_id = IWL_TX_RES_GET_RA(tx_resp->ra_tid); + int tid = IWL_TX_RES_GET_TID(tx_resp->ra_tid); u16 sequence = le16_to_cpu(pkt->hdr.sequence); struct iwl_mvm_sta *mvmsta; int queue = SEQ_TO_QUEUE(sequence); @@ -2193,7 +2123,7 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) ba_info.flags = IEEE80211_TX_STAT_AMPDU; if (iwl_mvm_has_new_tx_api(mvm)) { - struct iwl_mvm_compressed_ba_notif *ba_res = + struct iwl_compressed_ba_notif *ba_res = (void *)pkt->data; u8 lq_color = TX_RES_RATE_TABLE_COL_GET(ba_res->tlc_rate_info); u16 tfd_cnt; @@ -2241,8 +2171,7 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) /* Free per TID */ for (i = 0; i < tfd_cnt; i++) { - struct iwl_mvm_compressed_ba_tfd *ba_tfd = - &ba_res->tfd[i]; + struct iwl_compressed_ba_tfd *ba_tfd = &ba_res->tfd[i]; tid = ba_tfd->tid; if (tid == IWL_MGMT_TID) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/vendor-cmd.c b/drivers/net/wireless/intel/iwlwifi/mvm/vendor-cmd.c index 080a1587caa5..0f7fa6032c66 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/vendor-cmd.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/vendor-cmd.c @@ -104,9 +104,9 @@ static const struct wiphy_vendor_command iwl_mvm_vendor_commands[] = { }; enum iwl_mvm_vendor_events_idx { - /* 0x0 - 0x3 are deprecated */ - IWL_MVM_VENDOR_EVENT_IDX_ROAMING_FORBIDDEN = 4, - NUM_IWL_MVM_VENDOR_EVENT_IDX + /* 0x0 - 0x3 are deprecated */ + IWL_MVM_VENDOR_EVENT_IDX_ROAMING_FORBIDDEN = 4, + NUM_IWL_MVM_VENDOR_EVENT_IDX }; static const struct nl80211_vendor_cmd_info diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index ae93a72542b2..838c426db7f0 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -106,6 +106,7 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl; struct iwl_prph_info *prph_info; u32 control_flags = 0; + u32 control_flags_ext = 0; int ret; int cmdq_size = max_t(u32, IWL_CMD_QUEUE_SIZE, trans->cfg->min_txq_size); @@ -130,6 +131,12 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, break; } + if (trans->dsbr_urm_fw_dependent) + control_flags_ext |= IWL_PRPH_SCRATCH_EXT_URM_FW; + + if (trans->dsbr_urm_permanent) + control_flags_ext |= IWL_PRPH_SCRATCH_EXT_URM_PERM; + /* Allocate prph scratch */ prph_scratch = dma_alloc_coherent(trans->dev, sizeof(*prph_scratch), &trans_pcie->prph_scratch_dma_addr, @@ -165,6 +172,7 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, iwl_pcie_ctxt_info_dbg_enable(trans, &prph_sc_ctrl->hwm_cfg, &control_flags); prph_sc_ctrl->control.control_flags = cpu_to_le32(control_flags); + prph_sc_ctrl->control.control_flags_ext = cpu_to_le32(control_flags_ext); /* initialize the Step equalizer data */ prph_sc_ctrl->step_cfg.mbx_addr_0 = cpu_to_le32(trans->mbx_addr_0_step); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 805fb249a0c6..e0b657b2f74b 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -540,6 +540,9 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xE340, PCI_ANY_ID, iwl_sc_trans_cfg)}, {IWL_PCI_DEVICE(0xD340, PCI_ANY_ID, iwl_sc_trans_cfg)}, {IWL_PCI_DEVICE(0x6E70, PCI_ANY_ID, iwl_sc_trans_cfg)}, + +/* Dr devices */ + {IWL_PCI_DEVICE(0x272F, PCI_ANY_ID, iwl_dr_trans_cfg)}, #endif /* CONFIG_IWLMVM */ {0} @@ -1106,18 +1109,53 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = { iwlax210_2ax_cfg_so_jf_b0, iwl9462_name), /* Bz */ -/* FIXME: need to change the naming according to the actual CRF */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax201_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax211_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_fm_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_wh_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax201_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax211_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_cfg_bz, iwl_fm_name), _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, - IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, - iwl_cfg_bz, iwl_fm_name), + iwl_cfg_bz, iwl_wh_name), /* Ga (Gl) */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, @@ -1147,6 +1185,19 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = { IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_cfg_sc2f, iwl_sc2f_name), +/* Dr */ + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_DR, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_dr, iwl_dr_name), + +/* Br */ + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BR, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_br, iwl_br_name), #endif /* CONFIG_IWLMVM */ }; EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_dev_info_table); @@ -1251,6 +1302,9 @@ static int map_crf_id(struct iwl_trans *iwl_trans) case REG_CRF_ID_TYPE_WHP: iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_WH << 12); break; + case REG_CRF_ID_TYPE_PE: + iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_PE << 12); + break; default: ret = -EIO; IWL_ERR(iwl_trans, @@ -1356,6 +1410,47 @@ iwl_pci_find_dev_info(u16 device, u16 subsystem_device, } EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_pci_find_dev_info); +static void iwl_pcie_recheck_me_status(struct work_struct *wk) +{ + struct iwl_trans *trans = container_of(wk, typeof(*trans), + me_recheck_wk.work); + u32 val; + + val = iwl_read32(trans, CSR_HW_IF_CONFIG_REG); + trans->me_present = !!(val & CSR_HW_IF_CONFIG_REG_IAMT_UP); +} + +static void iwl_pcie_check_me_status(struct iwl_trans *trans) +{ + u32 val; + + trans->me_present = -1; + + INIT_DELAYED_WORK(&trans->me_recheck_wk, + iwl_pcie_recheck_me_status); + + /* we don't have a good way of determining this until BZ */ + if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ) + return; + + val = iwl_read_prph(trans, CNVI_SCU_REG_FOR_ECO_1); + if (val & CNVI_SCU_REG_FOR_ECO_1_WIAMT_KNOWN) { + trans->me_present = + !!(val & CNVI_SCU_REG_FOR_ECO_1_WIAMT_PRESENT); + return; + } + + val = iwl_read32(trans, CSR_HW_IF_CONFIG_REG); + if (val & (CSR_HW_IF_CONFIG_REG_ME_OWN | + CSR_HW_IF_CONFIG_REG_IAMT_UP)) { + trans->me_present = 1; + return; + } + + /* recheck again later, ME might still be initializing */ + schedule_delayed_work(&trans->me_recheck_wk, HZ); +} + static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { const struct iwl_cfg_trans_params *trans; @@ -1385,6 +1480,9 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) trans_pcie = IWL_TRANS_GET_PCIE_TRANS(iwl_trans); + iwl_trans_pcie_check_product_reset_status(pdev); + iwl_trans_pcie_check_product_reset_mode(pdev); + /* * Let's try to grab NIC access early here. Sometimes, NICs may * fail to initialize, and if that happens it's better if we see @@ -1531,6 +1629,8 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, iwl_trans); + iwl_pcie_check_me_status(iwl_trans); + /* try to get ownership so that we'll know if we don't own it */ iwl_pcie_prepare_card_hw(iwl_trans); @@ -1558,6 +1658,8 @@ static void iwl_pci_remove(struct pci_dev *pdev) if (!trans) return; + cancel_delayed_work_sync(&trans->me_recheck_wk); + iwl_drv_stop(trans->drv); iwl_trans_pcie_free(trans); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index 27a7e0b5b3d5..856b7e9f717d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -563,6 +563,9 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans); __cond_lock(nic_access_nobh, \ likely(__iwl_trans_pcie_grab_nic_access(trans))) +void iwl_trans_pcie_check_product_reset_status(struct pci_dev *pdev); +void iwl_trans_pcie_check_product_reset_mode(struct pci_dev *pdev); + /***************************************************** * RX ******************************************************/ @@ -1134,9 +1137,6 @@ void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans); int iwl_trans_pcie_gen2_send_hcmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd); void iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans); -void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans); -void iwl_pcie_d3_complete_suspend(struct iwl_trans *trans, - bool test, bool reset); int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd); int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index afb88eab8174..4a442d03d8d2 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1702,7 +1702,7 @@ static void iwl_pcie_irq_handle_error(struct iwl_trans *trans) /* The STATUS_FW_ERROR bit is set in this function. This must happen * before we wake up the command caller, to ensure a proper cleanup. */ - iwl_trans_fw_error(trans, false); + iwl_trans_fw_error(trans, IWL_ERR_TYPE_IRQ); clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status); wake_up(&trans->wait_command_queue); @@ -2297,7 +2297,9 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id) if (inta_hw & MSIX_HW_INT_CAUSES_REG_TOP_FATAL_ERR) { IWL_ERR(trans, "TOP Fatal error detected, inta_hw=0x%x.\n", inta_hw); - /* TODO: PLDR flow required here for >= Bz */ + if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) + iwl_trans_pcie_reset(trans, + IWL_RESET_MODE_PROD_RESET); } /* Error detected by uCode */ diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c index 8903a5692dfb..793514a1852a 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c @@ -43,7 +43,7 @@ int iwl_pcie_gen2_apm_init(struct iwl_trans *trans) * wake device's PCI Express link L1a -> L0s */ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_BIT_HAP_WAKE_L1A); + CSR_HW_IF_CONFIG_REG_HAP_WAKE); iwl_pcie_apm_config(trans); @@ -68,8 +68,8 @@ static void iwl_pcie_gen2_apm_stop(struct iwl_trans *trans, bool op_mode_leave) iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, CSR_RESET_LINK_PWR_MGMT_DISABLED); iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_PREPARE | - CSR_HW_IF_CONFIG_REG_ENABLE_PME); + CSR_HW_IF_CONFIG_REG_WAKE_ME | + CSR_HW_IF_CONFIG_REG_WAKE_ME_PCIE_OWNER_EN); mdelay(1); iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, CSR_RESET_LINK_PWR_MGMT_DISABLED); @@ -123,14 +123,21 @@ static void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans) "timeout waiting for FW reset ACK (inta_hw=0x%x)\n", inta_hw); - if (!(inta_hw & MSIX_HW_INT_CAUSES_REG_RESET_DONE)) - iwl_trans_fw_error(trans, true); + if (!(inta_hw & MSIX_HW_INT_CAUSES_REG_RESET_DONE)) { + struct iwl_fw_error_dump_mode mode = { + .type = IWL_ERR_TYPE_RESET_HS_TIMEOUT, + .context = IWL_ERR_CONTEXT_FROM_OPMODE, + }; + iwl_op_mode_nic_error(trans->op_mode, + IWL_ERR_TYPE_RESET_HS_TIMEOUT); + iwl_op_mode_dump_error(trans->op_mode, &mode); + } } trans_pcie->fw_reset_state = FW_RESET_IDLE; } -void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans) +static void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -139,9 +146,9 @@ void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans) if (trans_pcie->is_down) return; - if (trans->state >= IWL_TRANS_FW_STARTED) - if (trans_pcie->fw_reset_handshake) - iwl_trans_pcie_fw_reset_handshake(trans); + if (trans->state >= IWL_TRANS_FW_STARTED && + trans_pcie->fw_reset_handshake) + iwl_trans_pcie_fw_reset_handshake(trans); trans_pcie->is_down = true; @@ -287,9 +294,6 @@ static void iwl_pcie_get_rf_name(struct iwl_trans *trans) case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HRCDB): pos = scnprintf(buf, buflen, "HRCDB"); break; - case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_MS): - pos = scnprintf(buf, buflen, "MS"); - break; case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_FM): pos = scnprintf(buf, buflen, "FM"); break; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 86f1d87a909c..c917ed4c19bc 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -24,6 +24,7 @@ #include "fw/error-dump.h" #include "fw/dbg.h" #include "fw/api/tx.h" +#include "fw/acpi.h" #include "mei/iwl-mei.h" #include "internal.h" #include "iwl-fh.h" @@ -311,7 +312,7 @@ static int iwl_pcie_apm_init(struct iwl_trans *trans) * wake device's PCI Express link L1a -> L0s */ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_BIT_HAP_WAKE_L1A); + CSR_HW_IF_CONFIG_REG_HAP_WAKE); iwl_pcie_apm_config(trans); @@ -439,7 +440,7 @@ static void iwl_pcie_apm_lp_xtal_enable(struct iwl_trans *trans) * SHRD_HW_RST is applied in S3. */ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_PERSIST_MODE); + CSR_HW_IF_CONFIG_REG_PERSISTENCE); /* * Clear "initialization complete" bit to move adapter from @@ -508,8 +509,8 @@ static void iwl_pcie_apm_stop(struct iwl_trans *trans, bool op_mode_leave) iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, CSR_RESET_LINK_PWR_MGMT_DISABLED); iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_PREPARE | - CSR_HW_IF_CONFIG_REG_ENABLE_PME); + CSR_HW_IF_CONFIG_REG_WAKE_ME | + CSR_HW_IF_CONFIG_REG_WAKE_ME_PCIE_OWNER_EN); mdelay(1); iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG, CSR_RESET_LINK_PWR_MGMT_DISABLED); @@ -581,12 +582,12 @@ static int iwl_pcie_set_hw_ready(struct iwl_trans *trans) int ret; iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_BIT_NIC_READY); + CSR_HW_IF_CONFIG_REG_PCI_OWN_SET); /* See if we got it */ ret = iwl_poll_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_BIT_NIC_READY, - CSR_HW_IF_CONFIG_REG_BIT_NIC_READY, + CSR_HW_IF_CONFIG_REG_PCI_OWN_SET, + CSR_HW_IF_CONFIG_REG_PCI_OWN_SET, HW_READY_TIMEOUT); if (ret >= 0) @@ -620,7 +621,7 @@ int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) /* If HW is not ready, prepare the conditions to check again */ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_PREPARE); + CSR_HW_IF_CONFIG_REG_WAKE_ME); do { ret = iwl_pcie_set_hw_ready(trans); @@ -1488,8 +1489,8 @@ void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq) _iwl_trans_pcie_stop_device(trans, from_irq); } -void iwl_pcie_d3_complete_suspend(struct iwl_trans *trans, - bool test, bool reset) +static void iwl_pcie_d3_complete_suspend(struct iwl_trans *trans, + bool test, bool reset) { iwl_disable_interrupts(trans); @@ -1566,7 +1567,7 @@ int iwl_trans_pcie_d3_suspend(struct iwl_trans *trans, bool test, bool reset) if (!reset) /* Enable persistence mode to avoid reset */ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_PERSIST_MODE); + CSR_HW_IF_CONFIG_REG_PERSISTENCE); ret = iwl_pcie_d3_handshake(trans, true); if (ret) @@ -2105,10 +2106,157 @@ void iwl_trans_pcie_free(struct iwl_trans *trans) iwl_trans_free(trans); } +static union acpi_object * +iwl_trans_pcie_call_prod_reset_dsm(struct pci_dev *pdev, u16 cmd, u16 value) +{ +#ifdef CONFIG_ACPI + struct iwl_dsm_internal_product_reset_cmd pldr_arg = { + .cmd = cmd, + .value = value, + }; + union acpi_object arg = { + .buffer.type = ACPI_TYPE_BUFFER, + .buffer.length = sizeof(pldr_arg), + .buffer.pointer = (void *)&pldr_arg, + }; + static const guid_t dsm_guid = GUID_INIT(0x7266172C, 0x220B, 0x4B29, + 0x81, 0x4F, 0x75, 0xE4, + 0xDD, 0x26, 0xB5, 0xFD); + + if (!acpi_check_dsm(ACPI_HANDLE(&pdev->dev), &dsm_guid, ACPI_DSM_REV, + DSM_INTERNAL_FUNC_PRODUCT_RESET)) + return ERR_PTR(-ENODEV); + + return iwl_acpi_get_dsm_object(&pdev->dev, ACPI_DSM_REV, + DSM_INTERNAL_FUNC_PRODUCT_RESET, + &arg, &dsm_guid); +#else + return ERR_PTR(-EOPNOTSUPP); +#endif +} + +void iwl_trans_pcie_check_product_reset_mode(struct pci_dev *pdev) +{ + union acpi_object *res; + + res = iwl_trans_pcie_call_prod_reset_dsm(pdev, + DSM_INTERNAL_PLDR_CMD_GET_MODE, + 0); + if (IS_ERR(res)) + return; + + if (res->type != ACPI_TYPE_INTEGER) + IWL_ERR_DEV(&pdev->dev, + "unexpected return type from product reset DSM\n"); + else + IWL_DEBUG_DEV_POWER(&pdev->dev, + "product reset mode is 0x%llx\n", + res->integer.value); + + ACPI_FREE(res); +} + +static void iwl_trans_pcie_set_product_reset(struct pci_dev *pdev, bool enable, + bool integrated) +{ + union acpi_object *res; + u16 mode = enable ? DSM_INTERNAL_PLDR_MODE_EN_PROD_RESET : 0; + + if (!integrated) + mode |= DSM_INTERNAL_PLDR_MODE_EN_WIFI_FLR | + DSM_INTERNAL_PLDR_MODE_EN_BT_OFF_ON; + + res = iwl_trans_pcie_call_prod_reset_dsm(pdev, + DSM_INTERNAL_PLDR_CMD_SET_MODE, + mode); + if (IS_ERR(res)) { + if (enable) + IWL_ERR_DEV(&pdev->dev, + "ACPI _DSM not available (%d), cannot do product reset\n", + (int)PTR_ERR(res)); + return; + } + + ACPI_FREE(res); + IWL_DEBUG_DEV_POWER(&pdev->dev, "%sabled product reset via DSM\n", + enable ? "En" : "Dis"); + iwl_trans_pcie_check_product_reset_mode(pdev); +} + +void iwl_trans_pcie_check_product_reset_status(struct pci_dev *pdev) +{ + union acpi_object *res; + + res = iwl_trans_pcie_call_prod_reset_dsm(pdev, + DSM_INTERNAL_PLDR_CMD_GET_STATUS, + 0); + if (IS_ERR(res)) + return; + + if (res->type != ACPI_TYPE_INTEGER) + IWL_ERR_DEV(&pdev->dev, + "unexpected return type from product reset DSM\n"); + else + IWL_DEBUG_DEV_POWER(&pdev->dev, + "product reset status is 0x%llx\n", + res->integer.value); + + ACPI_FREE(res); +} + +static void iwl_trans_pcie_call_reset(struct pci_dev *pdev) +{ +#ifdef CONFIG_ACPI + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *p, *ref; + acpi_status status; + int ret = -EINVAL; + + status = acpi_evaluate_object(ACPI_HANDLE(&pdev->dev), + "_PRR", NULL, &buffer); + if (ACPI_FAILURE(status)) { + IWL_DEBUG_DEV_POWER(&pdev->dev, "No _PRR method found\n"); + goto out; + } + p = buffer.pointer; + + if (p->type != ACPI_TYPE_PACKAGE || p->package.count != 1) { + pci_err(pdev, "Bad _PRR return type\n"); + goto out; + } + + ref = &p->package.elements[0]; + if (ref->type != ACPI_TYPE_LOCAL_REFERENCE) { + pci_err(pdev, "_PRR wasn't a reference\n"); + goto out; + } + + status = acpi_evaluate_object(ref->reference.handle, + "_RST", NULL, NULL); + if (ACPI_FAILURE(status)) { + pci_err(pdev, + "Failed to call _RST on object returned by _PRR (%d)\n", + status); + goto out; + } + ret = 0; +out: + kfree(buffer.pointer); + if (!ret) { + IWL_DEBUG_DEV_POWER(&pdev->dev, "called _RST on _PRR object\n"); + return; + } + IWL_DEBUG_DEV_POWER(&pdev->dev, + "No BIOS support, using pci_reset_function()\n"); +#endif + pci_reset_function(pdev); +} + struct iwl_trans_pcie_removal { struct pci_dev *pdev; struct work_struct work; - bool rescan; + enum iwl_reset_mode mode; + bool integrated; }; static void iwl_trans_pcie_removal_wk(struct work_struct *wk) @@ -2126,14 +2274,66 @@ static void iwl_trans_pcie_removal_wk(struct work_struct *wk) if (!bus) goto out; - dev_err(&pdev->dev, "Device gone - attempting removal\n"); - kobject_uevent_env(&pdev->dev.kobj, KOBJ_CHANGE, prop); + if (removal->mode == IWL_RESET_MODE_PROD_RESET) { + struct pci_dev *bt = NULL; + + if (!removal->integrated) { + /* discrete devices have WiFi/BT at function 0/1 */ + int slot = PCI_SLOT(pdev->devfn); + int func = PCI_FUNC(pdev->devfn); + + if (func == 0) + bt = pci_get_slot(bus, PCI_DEVFN(slot, 1)); + else + pci_info(pdev, "Unexpected function %d\n", + func); + } else { + /* on integrated we have to look up by ID (same bus) */ + static const struct pci_device_id bt_device_ids[] = { +#define BT_DEV(_id) { PCI_DEVICE(PCI_VENDOR_ID_INTEL, _id) } + BT_DEV(0xA876), /* LNL */ + BT_DEV(0xE476), /* PTL-P */ + BT_DEV(0xE376), /* PTL-H */ + BT_DEV(0xD346), /* NVL-H */ + BT_DEV(0x6E74), /* NVL-S */ + BT_DEV(0x4D76), /* WCL */ + BT_DEV(0xD246), /* RZL-H */ + BT_DEV(0x6C46), /* RZL-M */ + {} + }; + struct pci_dev *tmp = NULL; + + for_each_pci_dev(tmp) { + if (tmp->bus != bus) + continue; + + if (pci_match_id(bt_device_ids, tmp)) { + bt = tmp; + break; + } + } + } + + if (bt) { + pci_info(bt, "Removal by WiFi due to product reset\n"); + pci_stop_and_remove_bus_device(bt); + pci_dev_put(bt); + } + } + + iwl_trans_pcie_set_product_reset(pdev, + removal->mode == + IWL_RESET_MODE_PROD_RESET, + removal->integrated); + if (removal->mode >= IWL_RESET_MODE_FUNC_RESET) + iwl_trans_pcie_call_reset(pdev); + pci_stop_and_remove_bus_device(pdev); pci_dev_put(pdev); - if (removal->rescan) { + if (removal->mode >= IWL_RESET_MODE_RESCAN) { if (bus->parent) bus = bus->parent; pci_rescan_bus(bus); @@ -2146,14 +2346,27 @@ out: module_put(THIS_MODULE); } -void iwl_trans_pcie_remove(struct iwl_trans *trans, bool rescan) +void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode) { struct iwl_trans_pcie_removal *removal; + char _msg = 0, *msg = &_msg; + + if (WARN_ON(mode < IWL_RESET_MODE_REMOVE_ONLY)) + return; if (test_bit(STATUS_TRANS_DEAD, &trans->status)) return; - IWL_ERR(trans, "Device gone - scheduling removal!\n"); + if (trans->me_present && mode == IWL_RESET_MODE_PROD_RESET) { + mode = IWL_RESET_MODE_FUNC_RESET; + if (trans->me_present < 0) + msg = " instead of product reset as ME may be present"; + else + msg = " instead of product reset as ME is present"; + } + + IWL_INFO(trans, "scheduling reset (mode=%d%s)\n", mode, msg); + iwl_pcie_dump_csr(trans); /* @@ -2180,12 +2393,13 @@ void iwl_trans_pcie_remove(struct iwl_trans *trans, bool rescan) set_bit(STATUS_TRANS_DEAD, &trans->status); removal->pdev = to_pci_dev(trans->dev); - removal->rescan = rescan; + removal->mode = mode; + removal->integrated = trans->trans_cfg->integrated; INIT_WORK(&removal->work, iwl_trans_pcie_removal_wk); pci_dev_get(removal->pdev); schedule_work(&removal->work); } -EXPORT_SYMBOL(iwl_trans_pcie_remove); +EXPORT_SYMBOL(iwl_trans_pcie_reset); /* * This version doesn't disable BHs but rather assumes they're @@ -2250,7 +2464,8 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans) iwl_trans_pcie_dump_regs(trans); if (iwlwifi_mod_params.remove_when_gone && cntrl == ~0U) - iwl_trans_pcie_remove(trans, false); + iwl_trans_pcie_reset(trans, + IWL_RESET_MODE_REMOVE_ONLY); else iwl_write32(trans, CSR_RESET, CSR_RESET_REG_FLAG_FORCE_NMI); @@ -3037,12 +3252,47 @@ static ssize_t iwl_dbgfs_rf_read(struct file *file, strlen(trans_pcie->rf_name)); } +static ssize_t iwl_dbgfs_reset_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct iwl_trans *trans = file->private_data; + static const char * const modes[] = { + [IWL_RESET_MODE_SW_RESET] = "n/a", + [IWL_RESET_MODE_REPROBE] = "n/a", + [IWL_RESET_MODE_REMOVE_ONLY] = "remove", + [IWL_RESET_MODE_RESCAN] = "rescan", + [IWL_RESET_MODE_FUNC_RESET] = "function", + [IWL_RESET_MODE_PROD_RESET] = "product", + }; + char buf[10] = {}; + int mode; + + if (count > sizeof(buf) - 1) + return -EINVAL; + + if (copy_from_user(buf, user_buf, count)) + return -EFAULT; + + mode = sysfs_match_string(modes, buf); + if (mode < 0) + return mode; + + if (mode < IWL_RESET_MODE_REMOVE_ONLY) + return -EINVAL; + + iwl_trans_pcie_reset(trans, mode); + + return count; +} + DEBUGFS_READ_WRITE_FILE_OPS(interrupt); DEBUGFS_READ_FILE_OPS(fh_reg); DEBUGFS_READ_FILE_OPS(rx_queue); DEBUGFS_WRITE_FILE_OPS(csr); DEBUGFS_READ_WRITE_FILE_OPS(rfkill); DEBUGFS_READ_FILE_OPS(rf); +DEBUGFS_WRITE_FILE_OPS(reset); static const struct file_operations iwl_dbgfs_tx_queue_ops = { .owner = THIS_MODULE, @@ -3071,6 +3321,7 @@ void iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans) DEBUGFS_ADD_FILE(rfkill, dir, 0600); DEBUGFS_ADD_FILE(monitor_data, dir, 0400); DEBUGFS_ADD_FILE(rf, dir, 0400); + DEBUGFS_ADD_FILE(reset, dir, 0200); } void iwl_trans_pcie_debugfs_cleanup(struct iwl_trans *trans) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index b1846abb99b7..1f483f15c238 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -1298,7 +1298,9 @@ int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans, spin_unlock_irqrestore(&txq->lock, flags); IWL_ERR(trans, "No space in command queue\n"); - iwl_op_mode_cmd_queue_full(trans->op_mode); + iwl_op_mode_nic_error(trans->op_mode, + IWL_ERR_TYPE_CMD_QUEUE_FULL); + iwl_trans_schedule_reset(trans, IWL_ERR_TYPE_CMD_QUEUE_FULL); idx = -ENOSPC; goto free_dup_buf; } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 1ef14340953c..334ebd4c12fa 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -1449,7 +1449,9 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans, spin_unlock_irqrestore(&txq->lock, flags); IWL_ERR(trans, "No space in command queue\n"); - iwl_op_mode_cmd_queue_full(trans->op_mode); + iwl_op_mode_nic_error(trans->op_mode, + IWL_ERR_TYPE_CMD_QUEUE_FULL); + iwl_trans_schedule_reset(trans, IWL_ERR_TYPE_CMD_QUEUE_FULL); idx = -ENOSPC; goto free_dup_buf; } diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index fca3eea7ee84..a099fdaafa45 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -410,7 +410,7 @@ mwifiex_cfg80211_set_tx_power(struct wiphy *wiphy, static int mwifiex_cfg80211_get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, - int *dbm) + unsigned int link_id, int *dbm) { struct mwifiex_adapter *adapter = mwifiex_cfg80211_get_adapter(wiphy); struct mwifiex_private *priv = mwifiex_get_priv(adapter, diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c index e06a0622973e..f79589cafe57 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c @@ -545,7 +545,7 @@ int mwifiex_enable_hs(struct mwifiex_adapter *adapter) if (wait_event_interruptible_timeout(adapter->hs_activate_wait_q, adapter->hs_activate_wait_q_woken, - (10 * HZ)) <= 0) { + (5 * HZ)) <= 0) { mwifiex_dbg(adapter, ERROR, "hs_activate_wait_q terminated\n"); return false; diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile index f7f2d9a8ab0f..87512d101a91 100644 --- a/drivers/net/wireless/mediatek/mt76/Makefile +++ b/drivers/net/wireless/mediatek/mt76/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_MT792x_USB) += mt792x-usb.o mt76-y := \ mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o \ - tx.o agg-rx.o mcu.o wed.o + tx.o agg-rx.o mcu.o wed.o scan.o channel.o mt76-$(CONFIG_PCI) += pci.o mt76-$(CONFIG_NL80211_TESTMODE) += testmode.o diff --git a/drivers/net/wireless/mediatek/mt76/channel.c b/drivers/net/wireless/mediatek/mt76/channel.c new file mode 100644 index 000000000000..6a35c6ebd823 --- /dev/null +++ b/drivers/net/wireless/mediatek/mt76/channel.c @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (C) 2024 Felix Fietkau + */ +#include "mt76.h" + +static struct mt76_vif_link * +mt76_alloc_mlink(struct mt76_dev *dev, struct mt76_vif_data *mvif) +{ + struct mt76_vif_link *mlink; + + mlink = kzalloc(dev->drv->link_data_size, GFP_KERNEL); + if (!mlink) + return NULL; + + mlink->mvif = mvif; + + return mlink; +} + +static int +mt76_phy_update_channel(struct mt76_phy *phy, + struct ieee80211_chanctx_conf *conf) +{ + phy->radar_enabled = conf->radar_enabled; + phy->main_chandef = conf->def; + phy->chanctx = (struct mt76_chanctx *)conf->drv_priv; + + return __mt76_set_channel(phy, &phy->main_chandef, false); +} + +int mt76_add_chanctx(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *conf) +{ + struct mt76_chanctx *ctx = (struct mt76_chanctx *)conf->drv_priv; + struct mt76_phy *phy = hw->priv; + struct mt76_dev *dev = phy->dev; + int ret = -EINVAL; + + phy = ctx->phy = dev->band_phys[conf->def.chan->band]; + if (WARN_ON_ONCE(!phy)) + return ret; + + if (dev->scan.phy == phy) + mt76_abort_scan(dev); + + mutex_lock(&dev->mutex); + if (!phy->chanctx) + ret = mt76_phy_update_channel(phy, conf); + else + ret = 0; + mutex_unlock(&dev->mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(mt76_add_chanctx); + +void mt76_remove_chanctx(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *conf) +{ + struct mt76_chanctx *ctx = (struct mt76_chanctx *)conf->drv_priv; + struct mt76_phy *phy = hw->priv; + struct mt76_dev *dev = phy->dev; + + phy = ctx->phy; + if (WARN_ON_ONCE(!phy)) + return; + + if (dev->scan.phy == phy) + mt76_abort_scan(dev); + + mutex_lock(&dev->mutex); + if (phy->chanctx == ctx) + phy->chanctx = NULL; + mutex_unlock(&dev->mutex); +} +EXPORT_SYMBOL_GPL(mt76_remove_chanctx); + +void mt76_change_chanctx(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *conf, + u32 changed) +{ + struct mt76_chanctx *ctx = (struct mt76_chanctx *)conf->drv_priv; + struct mt76_phy *phy = ctx->phy; + struct mt76_dev *dev = phy->dev; + + if (!(changed & (IEEE80211_CHANCTX_CHANGE_WIDTH | + IEEE80211_CHANCTX_CHANGE_RADAR))) + return; + + cancel_delayed_work_sync(&phy->mac_work); + + mutex_lock(&dev->mutex); + mt76_phy_update_channel(phy, conf); + mutex_unlock(&dev->mutex); +} +EXPORT_SYMBOL_GPL(mt76_change_chanctx); + + +int mt76_assign_vif_chanctx(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct ieee80211_chanctx_conf *conf) +{ + struct mt76_chanctx *ctx = (struct mt76_chanctx *)conf->drv_priv; + struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; + struct mt76_vif_data *mvif = mlink->mvif; + int link_id = link_conf->link_id; + struct mt76_phy *phy = ctx->phy; + struct mt76_dev *dev = phy->dev; + bool mlink_alloc = false; + int ret = 0; + + if (dev->scan.vif == vif) + mt76_abort_scan(dev); + + mutex_lock(&dev->mutex); + + if (vif->type == NL80211_IFTYPE_MONITOR && + is_zero_ether_addr(vif->addr)) + goto out; + + mlink = mt76_vif_conf_link(dev, vif, link_conf); + if (!mlink) { + mlink = mt76_alloc_mlink(dev, mvif); + if (!mlink) { + ret = -ENOMEM; + goto out; + } + mlink_alloc = true; + } + + mlink->ctx = conf; + ret = dev->drv->vif_link_add(phy, vif, link_conf, mlink); + if (ret) { + if (mlink_alloc) + kfree(mlink); + goto out; + } + + if (link_conf != &vif->bss_conf) + rcu_assign_pointer(mvif->link[link_id], mlink); + +out: + mutex_unlock(&dev->mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(mt76_assign_vif_chanctx); + +void mt76_unassign_vif_chanctx(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct ieee80211_chanctx_conf *conf) +{ + struct mt76_chanctx *ctx = (struct mt76_chanctx *)conf->drv_priv; + struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; + struct mt76_vif_data *mvif = mlink->mvif; + int link_id = link_conf->link_id; + struct mt76_phy *phy = ctx->phy; + struct mt76_dev *dev = phy->dev; + + if (dev->scan.vif == vif) + mt76_abort_scan(dev); + + mutex_lock(&dev->mutex); + + if (vif->type == NL80211_IFTYPE_MONITOR && + is_zero_ether_addr(vif->addr)) + goto out; + + mlink = mt76_vif_conf_link(dev, vif, link_conf); + if (!mlink) + goto out; + + if (link_conf != &vif->bss_conf) + rcu_assign_pointer(mvif->link[link_id], NULL); + + dev->drv->vif_link_remove(phy, vif, link_conf, mlink); + mlink->ctx = NULL; + + if (link_conf != &vif->bss_conf) + kfree_rcu(mlink, rcu_head); + +out: + mutex_unlock(&dev->mutex); +} +EXPORT_SYMBOL_GPL(mt76_unassign_vif_chanctx); + +int mt76_switch_vif_chanctx(struct ieee80211_hw *hw, + struct ieee80211_vif_chanctx_switch *vifs, + int n_vifs, + enum ieee80211_chanctx_switch_mode mode) +{ + struct mt76_chanctx *old_ctx = (struct mt76_chanctx *)vifs->old_ctx->drv_priv; + struct mt76_chanctx *new_ctx = (struct mt76_chanctx *)vifs->new_ctx->drv_priv; + struct ieee80211_chanctx_conf *conf = vifs->new_ctx; + struct mt76_phy *old_phy = old_ctx->phy; + struct mt76_phy *phy = hw->priv; + struct mt76_dev *dev = phy->dev; + struct mt76_vif_link *mlink; + bool update_chan; + int i, ret = 0; + + if (mode == CHANCTX_SWMODE_SWAP_CONTEXTS) + phy = new_ctx->phy = dev->band_phys[conf->def.chan->band]; + else + phy = new_ctx->phy; + if (!phy) + return -EINVAL; + + update_chan = phy->chanctx != new_ctx; + if (update_chan) { + if (dev->scan.phy == phy) + mt76_abort_scan(dev); + + cancel_delayed_work_sync(&phy->mac_work); + } + + mutex_lock(&dev->mutex); + + if (mode == CHANCTX_SWMODE_SWAP_CONTEXTS && + phy != old_phy && old_phy->chanctx == old_ctx) + old_phy->chanctx = NULL; + + if (update_chan) + ret = mt76_phy_update_channel(phy, vifs->new_ctx); + + if (ret) + goto out; + + if (old_phy == phy) + goto skip_link_replace; + + for (i = 0; i < n_vifs; i++) { + mlink = mt76_vif_conf_link(dev, vifs[i].vif, vifs[i].link_conf); + if (!mlink) + continue; + + dev->drv->vif_link_remove(old_phy, vifs[i].vif, + vifs[i].link_conf, mlink); + + ret = dev->drv->vif_link_add(phy, vifs[i].vif, + vifs[i].link_conf, mlink); + if (ret) + goto out; + + } + +skip_link_replace: + for (i = 0; i < n_vifs; i++) { + mlink = mt76_vif_conf_link(dev, vifs[i].vif, vifs[i].link_conf); + if (!mlink) + continue; + + mlink->ctx = vifs->new_ctx; + } + +out: + mutex_unlock(&dev->mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(mt76_switch_vif_chanctx); + +struct mt76_vif_link *mt76_get_vif_phy_link(struct mt76_phy *phy, + struct ieee80211_vif *vif) +{ + struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; + struct mt76_vif_data *mvif = mlink->mvif; + struct mt76_dev *dev = phy->dev; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(mvif->link); i++) { + mlink = mt76_dereference(mvif->link[i], dev); + if (!mlink) + continue; + + if (mt76_vif_link_phy(mlink) == phy) + return mlink; + } + + if (!dev->drv->vif_link_add) + return ERR_PTR(-EINVAL); + + mlink = mt76_alloc_mlink(dev, mvif); + if (!mlink) + return ERR_PTR(-ENOMEM); + + mlink->offchannel = true; + ret = dev->drv->vif_link_add(phy, vif, &vif->bss_conf, mlink); + if (ret) { + kfree(mlink); + return ERR_PTR(ret); + } + + return mlink; +} + +void mt76_put_vif_phy_link(struct mt76_phy *phy, struct ieee80211_vif *vif, + struct mt76_vif_link *mlink) +{ + struct mt76_dev *dev = phy->dev; + + if (IS_ERR_OR_NULL(mlink) || !mlink->offchannel) + return; + + dev->drv->vif_link_remove(phy, vif, &vif->bss_conf, mlink); + kfree(mlink); +} + +static void mt76_roc_complete(struct mt76_phy *phy) +{ + struct mt76_vif_link *mlink = phy->roc_link; + + if (!phy->roc_vif) + return; + + if (mlink) + mlink->mvif->roc_phy = NULL; + if (phy->main_chandef.chan) + mt76_set_channel(phy, &phy->main_chandef, false); + mt76_put_vif_phy_link(phy, phy->roc_vif, phy->roc_link); + phy->roc_vif = NULL; + phy->roc_link = NULL; + ieee80211_remain_on_channel_expired(phy->hw); +} + +void mt76_roc_complete_work(struct work_struct *work) +{ + struct mt76_phy *phy = container_of(work, struct mt76_phy, roc_work.work); + struct mt76_dev *dev = phy->dev; + + mutex_lock(&dev->mutex); + mt76_roc_complete(phy); + mutex_unlock(&dev->mutex); +} + +void mt76_abort_roc(struct mt76_phy *phy) +{ + struct mt76_dev *dev = phy->dev; + + cancel_delayed_work_sync(&phy->roc_work); + + mutex_lock(&dev->mutex); + mt76_roc_complete(phy); + mutex_unlock(&dev->mutex); +} + +int mt76_remain_on_channel(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_channel *chan, int duration, + enum ieee80211_roc_type type) +{ + struct cfg80211_chan_def chandef = {}; + struct mt76_phy *phy = hw->priv; + struct mt76_dev *dev = phy->dev; + struct mt76_vif_link *mlink; + int ret = 0; + + phy = dev->band_phys[chan->band]; + if (!phy) + return -EINVAL; + + mutex_lock(&dev->mutex); + + if (phy->roc_vif || dev->scan.phy == phy) { + ret = -EBUSY; + goto out; + } + + mlink = mt76_get_vif_phy_link(phy, vif); + if (IS_ERR(mlink)) { + ret = PTR_ERR(mlink); + goto out; + } + + mlink->mvif->roc_phy = phy; + phy->roc_vif = vif; + phy->roc_link = mlink; + cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_HT20); + mt76_set_channel(phy, &chandef, true); + ieee80211_ready_on_channel(hw); + ieee80211_queue_delayed_work(phy->hw, &phy->roc_work, + msecs_to_jiffies(duration)); + +out: + mutex_unlock(&dev->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(mt76_remain_on_channel); + +int mt76_cancel_remain_on_channel(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; + struct mt76_vif_data *mvif = mlink->mvif; + struct mt76_phy *phy = mvif->roc_phy; + + if (!phy) + return 0; + + mt76_abort_roc(phy); + + return 0; +} +EXPORT_SYMBOL_GPL(mt76_cancel_remain_on_channel); diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 5f46d6daeaa7..844af16ee551 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -631,7 +631,8 @@ free_skb: return ret; } -int mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q, +static int +mt76_dma_rx_fill_buf(struct mt76_dev *dev, struct mt76_queue *q, bool allow_direct) { int len = SKB_WITH_OVERHEAD(q->buf_size); @@ -640,8 +641,6 @@ int mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q, if (!q->ndesc) return 0; - spin_lock_bh(&q->lock); - while (q->queued < q->ndesc - 1) { struct mt76_queue_buf qbuf = {}; enum dma_data_direction dir; @@ -674,6 +673,19 @@ done: if (frames || mt76_queue_is_wed_rx(q)) mt76_dma_kick_queue(dev, q); + return frames; +} + +int mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q, + bool allow_direct) +{ + int frames; + + if (!q->ndesc) + return 0; + + spin_lock_bh(&q->lock); + frames = mt76_dma_rx_fill_buf(dev, q, allow_direct); spin_unlock_bh(&q->lock); return frames; @@ -796,7 +808,7 @@ mt76_dma_rx_reset(struct mt76_dev *dev, enum mt76_rxq_id qid) return; mt76_dma_sync_idx(dev, q); - mt76_dma_rx_fill(dev, q, false); + mt76_dma_rx_fill_buf(dev, q, false); } static void @@ -969,7 +981,7 @@ mt76_dma_init(struct mt76_dev *dev, mt76_for_each_q_rx(dev, i) { netif_napi_add(dev->napi_dev, &dev->napi[i], poll); - mt76_dma_rx_fill(dev, &dev->q_rx[i], false); + mt76_dma_rx_fill_buf(dev, &dev->q_rx[i], false); napi_enable(&dev->napi[i]); } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 9d5561f44134..508b472408c2 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -411,13 +411,16 @@ mt76_check_sband(struct mt76_phy *phy, struct mt76_sband *msband, } if (found) { - phy->chandef.chan = &sband->channels[0]; + cfg80211_chandef_create(&phy->chandef, &sband->channels[0], + NL80211_CHAN_HT20); phy->chan_state = &msband->chan[0]; + phy->dev->band_phys[band] = phy; return; } sband->n_channels = 0; - phy->hw->wiphy->bands[band] = NULL; + if (phy->hw->wiphy->bands[band] == sband) + phy->hw->wiphy->bands[band] = NULL; } static int @@ -428,6 +431,10 @@ mt76_phy_init(struct mt76_phy *phy, struct ieee80211_hw *hw) INIT_LIST_HEAD(&phy->tx_list); spin_lock_init(&phy->tx_lock); + INIT_DELAYED_WORK(&phy->roc_work, mt76_roc_complete_work); + + if ((void *)phy != hw->priv) + return 0; SET_IEEE80211_DEV(hw, dev->dev); SET_IEEE80211_PERM_ADDR(hw, phy->macaddr); @@ -480,6 +487,28 @@ mt76_phy_init(struct mt76_phy *phy, struct ieee80211_hw *hw) return 0; } +struct mt76_phy * +mt76_alloc_radio_phy(struct mt76_dev *dev, unsigned int size, + u8 band_idx) +{ + struct ieee80211_hw *hw = dev->phy.hw; + unsigned int phy_size; + struct mt76_phy *phy; + + phy_size = ALIGN(sizeof(*phy), 8); + phy = devm_kzalloc(dev->dev, size + phy_size, GFP_KERNEL); + if (!phy) + return NULL; + + phy->dev = dev; + phy->hw = hw; + phy->priv = (void *)phy + phy_size; + phy->band_idx = band_idx; + + return phy; +} +EXPORT_SYMBOL_GPL(mt76_alloc_radio_phy); + struct mt76_phy * mt76_alloc_phy(struct mt76_dev *dev, unsigned int size, const struct ieee80211_ops *ops, u8 band_idx) @@ -552,9 +581,11 @@ int mt76_register_phy(struct mt76_phy *phy, bool vht, mt76_check_sband(phy, &phy->sband_5g, NL80211_BAND_5GHZ); mt76_check_sband(phy, &phy->sband_6g, NL80211_BAND_6GHZ); - ret = ieee80211_register_hw(phy->hw); - if (ret) - return ret; + if ((void *)phy == phy->hw->priv) { + ret = ieee80211_register_hw(phy->hw); + if (ret) + return ret; + } set_bit(MT76_STATE_REGISTERED, &phy->state); phy->dev->phys[phy->band_idx] = phy; @@ -690,6 +721,7 @@ mt76_alloc_device(struct device *pdev, unsigned int size, INIT_LIST_HEAD(&dev->txwi_cache); INIT_LIST_HEAD(&dev->rxwi_cache); dev->token_size = dev->drv->token_size; + INIT_DELAYED_WORK(&dev->scan_work, mt76_scan_work); for (i = 0; i < ARRAY_SIZE(dev->q_rx); i++) skb_queue_head_init(&dev->rx_skb[i]); @@ -712,7 +744,7 @@ int mt76_register_device(struct mt76_dev *dev, bool vht, int ret; dev_set_drvdata(dev->dev, dev); - mt76_wcid_init(&dev->global_wcid); + mt76_wcid_init(&dev->global_wcid, phy->band_idx); ret = mt76_phy_init(phy, hw); if (ret) return ret; @@ -784,6 +816,22 @@ void mt76_free_device(struct mt76_dev *dev) } EXPORT_SYMBOL_GPL(mt76_free_device); +static struct mt76_phy * +mt76_vif_phy(struct ieee80211_hw *hw, struct ieee80211_vif *vif) +{ + struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; + struct mt76_chanctx *ctx; + + if (!hw->wiphy->n_radio) + return hw->priv; + + if (!mlink->ctx) + return NULL; + + ctx = (struct mt76_chanctx *)mlink->ctx->drv_priv; + return ctx->phy; +} + static void mt76_rx_release_amsdu(struct mt76_phy *phy, enum mt76_rxq_id q) { struct sk_buff *skb = phy->rx_amsdu[q].head; @@ -929,16 +977,13 @@ void mt76_update_survey(struct mt76_phy *phy) } EXPORT_SYMBOL_GPL(mt76_update_survey); -int mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef, - bool offchannel) +int __mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef, + bool offchannel) { struct mt76_dev *dev = phy->dev; int timeout = HZ / 5; int ret; - cancel_delayed_work_sync(&phy->mac_work); - - mutex_lock(&dev->mutex); set_bit(MT76_RESET, &phy->state); mt76_worker_disable(&dev->tx_worker); @@ -954,17 +999,30 @@ int mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef, phy->offchannel = offchannel; if (!offchannel) - phy->main_chan = chandef->chan; + phy->main_chandef = *chandef; - if (chandef->chan != phy->main_chan) + if (chandef->chan != phy->main_chandef.chan) memset(phy->chan_state, 0, sizeof(*phy->chan_state)); - mt76_worker_enable(&dev->tx_worker); ret = dev->drv->set_channel(phy); clear_bit(MT76_RESET, &phy->state); + mt76_worker_enable(&dev->tx_worker); mt76_worker_schedule(&dev->tx_worker); + return ret; +} + +int mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef, + bool offchannel) +{ + struct mt76_dev *dev = phy->dev; + int ret; + + cancel_delayed_work_sync(&phy->mac_work); + + mutex_lock(&dev->mutex); + ret = __mt76_set_channel(phy, chandef, offchannel); mutex_unlock(&dev->mutex); return ret; @@ -976,37 +1034,59 @@ int mt76_update_channel(struct mt76_phy *phy) struct cfg80211_chan_def *chandef = &hw->conf.chandef; bool offchannel = hw->conf.flags & IEEE80211_CONF_OFFCHANNEL; + phy->radar_enabled = hw->conf.radar_enabled; + return mt76_set_channel(phy, chandef, offchannel); } EXPORT_SYMBOL_GPL(mt76_update_channel); +static struct mt76_sband * +mt76_get_survey_sband(struct mt76_phy *phy, int *idx) +{ + if (*idx < phy->sband_2g.sband.n_channels) + return &phy->sband_2g; + + *idx -= phy->sband_2g.sband.n_channels; + if (*idx < phy->sband_5g.sband.n_channels) + return &phy->sband_5g; + + *idx -= phy->sband_5g.sband.n_channels; + if (*idx < phy->sband_6g.sband.n_channels) + return &phy->sband_6g; + + *idx -= phy->sband_6g.sband.n_channels; + return NULL; +} + int mt76_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey) { struct mt76_phy *phy = hw->priv; struct mt76_dev *dev = phy->dev; - struct mt76_sband *sband; + struct mt76_sband *sband = NULL; struct ieee80211_channel *chan; struct mt76_channel_state *state; + int phy_idx = 0; int ret = 0; mutex_lock(&dev->mutex); - if (idx == 0 && dev->drv->update_survey) - mt76_update_survey(phy); - if (idx >= phy->sband_2g.sband.n_channels + - phy->sband_5g.sband.n_channels) { - idx -= (phy->sband_2g.sband.n_channels + - phy->sband_5g.sband.n_channels); - sband = &phy->sband_6g; - } else if (idx >= phy->sband_2g.sband.n_channels) { - idx -= phy->sband_2g.sband.n_channels; - sband = &phy->sband_5g; - } else { - sband = &phy->sband_2g; + for (phy_idx = 0; phy_idx < ARRAY_SIZE(dev->phys); phy_idx++) { + sband = NULL; + phy = dev->phys[phy_idx]; + if (!phy || phy->hw != hw) + continue; + + sband = mt76_get_survey_sband(phy, &idx); + + if (idx == 0 && phy->dev->drv->update_survey) + mt76_update_survey(phy); + + if (sband || !hw->wiphy->n_radio) + break; } - if (idx >= sband->sband.n_channels) { + if (!sband) { ret = -ENOENT; goto out; } @@ -1021,7 +1101,7 @@ int mt76_get_survey(struct ieee80211_hw *hw, int idx, if (state->noise) survey->filled |= SURVEY_INFO_NOISE_DBM; - if (chan == phy->main_chan) { + if (chan == phy->main_chandef.chan) { survey->filled |= SURVEY_INFO_IN_USE; if (dev->drv->drv_flags & MT_DRV_SW_RX_AIRTIME) @@ -1462,21 +1542,20 @@ mt76_sta_add(struct mt76_phy *phy, struct ieee80211_vif *vif, } ewma_signal_init(&wcid->rssi); - if (phy->band_idx == MT_BAND1) - mt76_wcid_mask_set(dev->wcid_phy_mask, wcid->idx); - wcid->phy_idx = phy->band_idx; rcu_assign_pointer(dev->wcid[wcid->idx], wcid); + phy->num_sta++; - mt76_wcid_init(wcid); + mt76_wcid_init(wcid, phy->band_idx); out: mutex_unlock(&dev->mutex); return ret; } -void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, +void __mt76_sta_remove(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { + struct mt76_dev *dev = phy->dev; struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv; int i, idx = wcid->idx; @@ -1489,16 +1568,18 @@ void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, mt76_wcid_cleanup(dev, wcid); mt76_wcid_mask_clear(dev->wcid_mask, idx); - mt76_wcid_mask_clear(dev->wcid_phy_mask, idx); + phy->num_sta--; } EXPORT_SYMBOL_GPL(__mt76_sta_remove); static void -mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, +mt76_sta_remove(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { + struct mt76_dev *dev = phy->dev; + mutex_lock(&dev->mutex); - __mt76_sta_remove(dev, vif, sta); + __mt76_sta_remove(phy, vif, sta); mutex_unlock(&dev->mutex); } @@ -1511,13 +1592,17 @@ int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct mt76_dev *dev = phy->dev; enum mt76_sta_event ev; + phy = mt76_vif_phy(hw, vif); + if (!phy) + return -EINVAL; + if (old_state == IEEE80211_STA_NOTEXIST && new_state == IEEE80211_STA_NONE) return mt76_sta_add(phy, vif, sta); if (old_state == IEEE80211_STA_NONE && new_state == IEEE80211_STA_NOTEXIST) - mt76_sta_remove(dev, vif, sta); + mt76_sta_remove(phy, vif, sta); if (!dev->drv->sta_event) return 0; @@ -1553,14 +1638,19 @@ void mt76_sta_pre_rcu_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif, } EXPORT_SYMBOL_GPL(mt76_sta_pre_rcu_remove); -void mt76_wcid_init(struct mt76_wcid *wcid) +void mt76_wcid_init(struct mt76_wcid *wcid, u8 band_idx) { + wcid->hw_key_idx = -1; + wcid->phy_idx = band_idx; + INIT_LIST_HEAD(&wcid->tx_list); skb_queue_head_init(&wcid->tx_pending); skb_queue_head_init(&wcid->tx_offchannel); INIT_LIST_HEAD(&wcid->list); idr_init(&wcid->pktid); + + INIT_LIST_HEAD(&wcid->poll_list); } EXPORT_SYMBOL_GPL(mt76_wcid_init); @@ -1595,13 +1685,29 @@ void mt76_wcid_cleanup(struct mt76_dev *dev, struct mt76_wcid *wcid) } EXPORT_SYMBOL_GPL(mt76_wcid_cleanup); -int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - int *dbm) +void mt76_wcid_add_poll(struct mt76_dev *dev, struct mt76_wcid *wcid) { - struct mt76_phy *phy = hw->priv; - int n_chains = hweight16(phy->chainmask); - int delta = mt76_tx_power_nss_delta(n_chains); + if (test_bit(MT76_MCU_RESET, &dev->phy.state)) + return; + spin_lock_bh(&dev->sta_poll_lock); + if (list_empty(&wcid->poll_list)) + list_add_tail(&wcid->poll_list, &dev->sta_poll_list); + spin_unlock_bh(&dev->sta_poll_lock); +} +EXPORT_SYMBOL_GPL(mt76_wcid_add_poll); + +int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id, int *dbm) +{ + struct mt76_phy *phy = mt76_vif_phy(hw, vif); + int n_chains, delta; + + if (!phy) + return -EINVAL; + + n_chains = hweight16(phy->chainmask); + delta = mt76_tx_power_nss_delta(n_chains); *dbm = DIV_ROUND_UP(phy->txpower_cur + delta, 2); return 0; @@ -1776,10 +1882,14 @@ int mt76_get_antenna(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant) { struct mt76_phy *phy = hw->priv; struct mt76_dev *dev = phy->dev; + int i; mutex_lock(&dev->mutex); - *tx_ant = phy->antenna_mask; - *rx_ant = phy->antenna_mask; + *tx_ant = 0; + for (i = 0; i < ARRAY_SIZE(dev->phys); i++) + if (dev->phys[i] && dev->phys[i]->hw == hw) + *tx_ant |= dev->phys[i]->chainmask; + *rx_ant = *tx_ant; mutex_unlock(&dev->mutex); return 0; @@ -1808,30 +1918,6 @@ mt76_init_queue(struct mt76_dev *dev, int qid, int idx, int n_desc, } EXPORT_SYMBOL_GPL(mt76_init_queue); -u16 mt76_calculate_default_rate(struct mt76_phy *phy, - struct ieee80211_vif *vif, int rateidx) -{ - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; - struct cfg80211_chan_def *chandef = mvif->ctx ? - &mvif->ctx->def : - &phy->chandef; - int offset = 0; - - if (chandef->chan->band != NL80211_BAND_2GHZ) - offset = 4; - - /* pick the lowest rate for hidden nodes */ - if (rateidx < 0) - rateidx = 0; - - rateidx += offset; - if (rateidx >= ARRAY_SIZE(mt76_rates)) - rateidx = offset; - - return mt76_rates[rateidx].hw_value; -} -EXPORT_SYMBOL_GPL(mt76_calculate_default_rate); - void mt76_ethtool_worker(struct mt76_ethtool_worker_info *wi, struct mt76_sta_stats *stats, bool eht) { @@ -1892,7 +1978,7 @@ enum mt76_dfs_state mt76_phy_dfs_state(struct mt76_phy *phy) test_bit(MT76_SCANNING, &phy->state)) return MT_DFS_STATE_DISABLED; - if (!hw->conf.radar_enabled) { + if (!phy->radar_enabled) { if ((hw->conf.flags & IEEE80211_CONF_MONITOR) && (phy->chandef.chan->flags & IEEE80211_CHAN_RADAR)) return MT_DFS_STATE_ACTIVE; @@ -1906,3 +1992,15 @@ enum mt76_dfs_state mt76_phy_dfs_state(struct mt76_phy *phy) return MT_DFS_STATE_ACTIVE; } EXPORT_SYMBOL_GPL(mt76_phy_dfs_state); + +void mt76_vif_cleanup(struct mt76_dev *dev, struct ieee80211_vif *vif) +{ + struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; + struct mt76_vif_data *mvif = mlink->mvif; + + rcu_assign_pointer(mvif->link[0], NULL); + mt76_abort_scan(dev); + if (mvif->roc_phy) + mt76_abort_roc(mvif->roc_phy); +} +EXPORT_SYMBOL_GPL(mt76_vif_cleanup); diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 0b75a45ad2e8..132148f7b107 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -50,6 +50,8 @@ struct mt76_dev; struct mt76_phy; struct mt76_wcid; struct mt76s_intr; +struct mt76_chanctx; +struct mt76_vif_link; struct mt76_reg_pair { u32 reg; @@ -497,6 +499,8 @@ struct mt76_driver_ops { u16 token_size; u8 mcs_rates; + unsigned int link_data_size; + void (*update_survey)(struct mt76_phy *phy); int (*set_channel)(struct mt76_phy *phy); @@ -528,6 +532,15 @@ struct mt76_driver_ops { void (*sta_remove)(struct mt76_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); + + int (*vif_link_add)(struct mt76_phy *phy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink); + + void (*vif_link_remove)(struct mt76_phy *phy, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink); }; struct mt76_channel_state { @@ -636,6 +649,7 @@ struct mt76_sdio { u8 hw_ver; wait_queue_head_t wait; + int pse_mcu_quota_max; struct { int pse_data_quota; int ple_data_quota; @@ -753,7 +767,7 @@ struct mt76_testmode_data { } rx_stats; }; -struct mt76_vif { +struct mt76_vif_link { u8 idx; u8 omac_idx; u8 band_idx; @@ -763,7 +777,19 @@ struct mt76_vif { u8 basic_rates_idx; u8 mcast_rates_idx; u8 beacon_rates_idx; + bool offchannel; struct ieee80211_chanctx_conf *ctx; + struct mt76_wcid *wcid; + struct mt76_vif_data *mvif; + struct rcu_head rcu_head; +}; + +struct mt76_vif_data { + struct mt76_vif_link __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; + + struct mt76_phy *roc_phy; + u16 valid_links; + u8 deflink_id; }; struct mt76_phy { @@ -772,6 +798,7 @@ struct mt76_phy { void *priv; unsigned long state; + unsigned int num_sta; u8 band_idx; spinlock_t tx_lock; @@ -779,8 +806,15 @@ struct mt76_phy { struct mt76_queue *q_tx[__MT_TXQ_MAX]; struct cfg80211_chan_def chandef; - struct ieee80211_channel *main_chan; + struct cfg80211_chan_def main_chandef; bool offchannel; + bool radar_enabled; + + struct delayed_work roc_work; + struct ieee80211_vif *roc_vif; + struct mt76_vif_link *roc_link; + + struct mt76_chanctx *chanctx; struct mt76_channel_state *chan_state; enum mt76_dfs_state dfs_state; @@ -825,6 +859,7 @@ struct mt76_phy { struct mt76_dev { struct mt76_phy phy; /* must be first */ struct mt76_phy *phys[__MT_MAX_BAND]; + struct mt76_phy *band_phys[NUM_NL80211_BANDS]; struct ieee80211_hw *hw; @@ -880,7 +915,6 @@ struct mt76_dev { spinlock_t status_lock; u32 wcid_mask[DIV_ROUND_UP(MT76_N_WCIDS, 32)]; - u32 wcid_phy_mask[DIV_ROUND_UP(MT76_N_WCIDS, 32)]; u64 vif_mask; @@ -909,6 +943,16 @@ struct mt76_dev { u32 rxfilter; + struct delayed_work scan_work; + struct { + struct cfg80211_scan_request *req; + struct ieee80211_channel *chan; + struct ieee80211_vif *vif; + struct mt76_vif_link *mlink; + struct mt76_phy *phy; + int chan_idx; + } scan; + #ifdef CONFIG_NL80211_TESTMODE const struct mt76_testmode_ops *test_ops; struct { @@ -1036,6 +1080,10 @@ struct mt76_ethtool_worker_info { int sta_count; }; +struct mt76_chanctx { + struct mt76_phy *phy; +}; + #define CCK_RATE(_idx, _rate) { \ .bitrate = _rate, \ .flags = IEEE80211_RATE_SHORT_PREAMBLE, \ @@ -1156,6 +1204,10 @@ static inline int mt76_wed_dma_setup(struct mt76_dev *dev, struct mt76_queue *q, for (i = 0; i < ARRAY_SIZE((dev)->q_rx); i++) \ if ((dev)->q_rx[i].ndesc) + +#define mt76_dereference(p, dev) \ + rcu_dereference_protected(p, lockdep_is_held(&(dev)->mutex)) + struct mt76_dev *mt76_alloc_device(struct device *pdev, unsigned int size, const struct ieee80211_ops *ops, const struct mt76_driver_ops *drv_ops); @@ -1165,6 +1217,8 @@ void mt76_unregister_device(struct mt76_dev *dev); void mt76_free_device(struct mt76_dev *dev); void mt76_unregister_phy(struct mt76_phy *phy); +struct mt76_phy *mt76_alloc_radio_phy(struct mt76_dev *dev, unsigned int size, + u8 band_idx); struct mt76_phy *mt76_alloc_phy(struct mt76_dev *dev, unsigned int size, const struct ieee80211_ops *ops, u8 band_idx); @@ -1191,8 +1245,6 @@ int mt76_get_of_data_from_nvmem(struct mt76_dev *dev, void *eep, struct mt76_queue * mt76_init_queue(struct mt76_dev *dev, int qid, int idx, int n_desc, int ring_base, void *wed, u32 flags); -u16 mt76_calculate_default_rate(struct mt76_phy *phy, - struct ieee80211_vif *vif, int rateidx); static inline int mt76_init_tx_queue(struct mt76_phy *phy, int qid, int idx, int n_desc, int ring_base, void *wed, u32 flags) @@ -1423,15 +1475,15 @@ int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, enum ieee80211_sta_state old_state, enum ieee80211_sta_state new_state); -void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, +void __mt76_sta_remove(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void mt76_sta_pre_rcu_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); -int mt76_get_min_avg_rssi(struct mt76_dev *dev, bool ext_phy); +int mt76_get_min_avg_rssi(struct mt76_dev *dev, u8 phy_idx); int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - int *dbm); + unsigned int link_id, int *dbm); int mt76_init_sar_power(struct ieee80211_hw *hw, const struct cfg80211_sar_specs *sar); int mt76_get_sar_power(struct mt76_phy *phy, @@ -1447,11 +1499,38 @@ void mt76_insert_ccmp_hdr(struct sk_buff *skb, u8 key_id); int mt76_get_rate(struct mt76_dev *dev, struct ieee80211_supported_band *sband, int idx, bool cck); +int mt76_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_scan_request *hw_req); +void mt76_cancel_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void mt76_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const u8 *mac); void mt76_sw_scan_complete(struct ieee80211_hw *hw, struct ieee80211_vif *vif); enum mt76_dfs_state mt76_phy_dfs_state(struct mt76_phy *phy); +int mt76_add_chanctx(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *conf); +void mt76_remove_chanctx(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *conf); +void mt76_change_chanctx(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *conf, + u32 changed); +int mt76_assign_vif_chanctx(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct ieee80211_chanctx_conf *conf); +void mt76_unassign_vif_chanctx(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct ieee80211_chanctx_conf *conf); +int mt76_switch_vif_chanctx(struct ieee80211_hw *hw, + struct ieee80211_vif_chanctx_switch *vifs, + int n_vifs, + enum ieee80211_chanctx_switch_mode mode); +int mt76_remain_on_channel(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_channel *chan, int duration, + enum ieee80211_roc_type type); +int mt76_cancel_remain_on_channel(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); int mt76_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void *data, int len); int mt76_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *skb, @@ -1497,8 +1576,18 @@ void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames); void mt76_testmode_tx_pending(struct mt76_phy *phy); void mt76_queue_tx_complete(struct mt76_dev *dev, struct mt76_queue *q, struct mt76_queue_entry *e); +int __mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef, + bool offchannel); int mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef, bool offchannel); +void mt76_scan_work(struct work_struct *work); +void mt76_abort_scan(struct mt76_dev *dev); +void mt76_roc_complete_work(struct work_struct *work); +void mt76_abort_roc(struct mt76_phy *phy); +struct mt76_vif_link *mt76_get_vif_phy_link(struct mt76_phy *phy, + struct ieee80211_vif *vif); +void mt76_put_vif_phy_link(struct mt76_phy *phy, struct ieee80211_vif *vif, + struct mt76_vif_link *mlink); /* usb */ static inline bool mt76u_urb_error(struct urb *urb) @@ -1734,7 +1823,54 @@ mt76_token_put(struct mt76_dev *dev, int token) return txwi; } -void mt76_wcid_init(struct mt76_wcid *wcid); +void mt76_wcid_init(struct mt76_wcid *wcid, u8 band_idx); void mt76_wcid_cleanup(struct mt76_dev *dev, struct mt76_wcid *wcid); +void mt76_wcid_add_poll(struct mt76_dev *dev, struct mt76_wcid *wcid); + +static inline void +mt76_vif_init(struct ieee80211_vif *vif, struct mt76_vif_data *mvif) +{ + struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; + + mlink->mvif = mvif; + rcu_assign_pointer(mvif->link[0], mlink); +} + +void mt76_vif_cleanup(struct mt76_dev *dev, struct ieee80211_vif *vif); + +static inline struct mt76_vif_link * +mt76_vif_link(struct mt76_dev *dev, struct ieee80211_vif *vif, int link_id) +{ + struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; + struct mt76_vif_data *mvif = mlink->mvif; + + return mt76_dereference(mvif->link[link_id], dev); +} + +static inline struct mt76_vif_link * +mt76_vif_conf_link(struct mt76_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf) +{ + struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv; + struct mt76_vif_data *mvif = mlink->mvif; + + if (link_conf == &vif->bss_conf) + return mlink; + + return mt76_dereference(mvif->link[link_conf->link_id], dev); +} + +static inline struct mt76_phy * +mt76_vif_link_phy(struct mt76_vif_link *mlink) +{ + struct mt76_chanctx *ctx; + + if (!mlink->ctx) + return NULL; + + ctx = (struct mt76_chanctx *)mlink->ctx->drv_priv; + + return ctx->phy; +} #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c index dc8a77f0a1cc..413973d05b43 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c @@ -1277,12 +1277,7 @@ void mt7603_mac_add_txs(struct mt7603_dev *dev, void *data) msta = container_of(wcid, struct mt7603_sta, wcid); sta = wcid_to_sta(wcid); - - if (list_empty(&msta->wcid.poll_list)) { - spin_lock_bh(&dev->mt76.sta_poll_lock); - list_add_tail(&msta->wcid.poll_list, &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); - } + mt76_wcid_add_poll(&dev->mt76, &msta->wcid); if (mt7603_mac_add_txs_skb(dev, msta, pid, txs_data)) goto out; @@ -1484,14 +1479,13 @@ static void mt7603_mac_watchdog_reset(struct mt7603_dev *dev) tasklet_enable(&dev->mt76.pre_tbtt_tasklet); mt7603_beacon_set_timer(dev, -1, beacon_int); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); - napi_schedule(&dev->mt76.tx_napi); - napi_enable(&dev->mt76.napi[0]); - napi_schedule(&dev->mt76.napi[0]); - napi_enable(&dev->mt76.napi[1]); + + local_bh_disable(); + napi_schedule(&dev->mt76.tx_napi); + napi_schedule(&dev->mt76.napi[0]); napi_schedule(&dev->mt76.napi[1]); local_bh_enable(); @@ -1793,7 +1787,7 @@ mt7603_false_cca_check(struct mt7603_dev *dev) mt7603_cca_stats_reset(dev); - min_signal = mt76_get_min_avg_rssi(&dev->mt76, false); + min_signal = mt76_get_min_avg_rssi(&dev->mt76, 0); if (!min_signal) { dev->sensitivity = 0; dev->last_cca_adj = jiffies; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c index 574f74ad325d..3e8b1ec76169 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c @@ -66,11 +66,9 @@ mt7603_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) idx = MT7603_WTBL_RESERVED - 1 - mvif->idx; dev->mt76.vif_mask |= BIT_ULL(mvif->idx); - INIT_LIST_HEAD(&mvif->sta.wcid.poll_list); mvif->sta.wcid.idx = idx; - mvif->sta.wcid.hw_key_idx = -1; mvif->sta.vif = mvif; - mt76_wcid_init(&mvif->sta.wcid); + mt76_wcid_init(&mvif->sta.wcid, 0); eth_broadcast_addr(bc_addr); mt7603_wtbl_init(dev, idx, mvif->idx, bc_addr); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index 7ba789834e8d..3ca4fae7c4b0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -387,11 +387,7 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb) struct mt7615_sta *msta; msta = container_of(status->wcid, struct mt7615_sta, wcid); - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&msta->wcid.poll_list)) - list_add_tail(&msta->wcid.poll_list, - &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &msta->wcid); } if (mt76_is_mmio(&dev->mt76) && (rxd0 & csum_mask) == csum_mask && @@ -734,7 +730,7 @@ int mt7615_mac_write_txwi(struct mt7615_dev *dev, __le32 *txwi, u16 seqno = 0; if (vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; omac_idx = mvif->omac_idx; wmm_idx = mvif->wmm_idx; @@ -1514,11 +1510,7 @@ static void mt7615_mac_add_txs(struct mt7615_dev *dev, void *data) msta = container_of(wcid, struct mt7615_sta, wcid); sta = wcid_to_sta(wcid); - - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&msta->wcid.poll_list)) - list_add_tail(&msta->wcid.poll_list, &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &msta->wcid); if (mt7615_mac_add_txs_skb(dev, msta, pid, txs_data)) goto out; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c index 376975388007..2e7b05eeef7a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c @@ -209,6 +209,7 @@ static int mt7615_add_interface(struct ieee80211_hw *hw, mvif->mt76.band_idx = ext_phy; mvif->mt76.wmm_idx = vif->type != NL80211_IFTYPE_AP; + mvif->mt76.wcid = &mvif->sta.wcid; if (ext_phy) mvif->mt76.wmm_idx += 2; @@ -224,9 +225,7 @@ static int mt7615_add_interface(struct ieee80211_hw *hw, INIT_LIST_HEAD(&mvif->sta.wcid.poll_list); mvif->sta.wcid.idx = idx; - mvif->sta.wcid.phy_idx = mvif->mt76.band_idx; - mvif->sta.wcid.hw_key_idx = -1; - mt76_wcid_init(&mvif->sta.wcid); + mt76_wcid_init(&mvif->sta.wcid, mvif->mt76.band_idx); mt7615_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); @@ -463,7 +462,7 @@ mt7615_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id, u16 queue, const struct ieee80211_tx_queue_params *params) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt7615_dev *dev = mt7615_hw_dev(hw); int err; @@ -1249,7 +1248,7 @@ static int mt7615_suspend(struct ieee80211_hw *hw, phy->mt76); if (!mt7615_dev_running(dev)) - err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, true); + err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, true, true); mt7615_mutex_release(dev); @@ -1271,7 +1270,7 @@ static int mt7615_resume(struct ieee80211_hw *hw) if (!running) { int err; - err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, false); + err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, false, true); if (err < 0) { mt7615_mutex_release(dev); return err; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index 96e34277fece..b8fcd4eb3fbb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -865,8 +865,8 @@ mt7615_mcu_wtbl_sta_add(struct mt7615_phy *phy, struct ieee80211_vif *vif, mvif->sta_added = true; } conn_state = enable ? CONN_STATE_PORT_SECURE : CONN_STATE_DISCONNECT; - mt76_connac_mcu_sta_basic_tlv(&dev->mt76, sskb, vif, link_sta, - conn_state, new_entry); + mt76_connac_mcu_sta_basic_tlv(&dev->mt76, sskb, &vif->bss_conf, + link_sta, conn_state, new_entry); if (enable && sta) mt76_connac_mcu_sta_tlv(phy->mt76, sskb, sta, vif, 0, MT76_STA_INFO_STATE_ASSOC); @@ -1113,7 +1113,7 @@ mt7615_mcu_uni_add_dev(struct mt7615_phy *phy, struct ieee80211_vif *vif, { struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv; - return mt76_connac_mcu_uni_add_dev(phy->mt76, &vif->bss_conf, + return mt76_connac_mcu_uni_add_dev(phy->mt76, &vif->bss_conf, &mvif->mt76, &mvif->sta.wcid, enable); } @@ -1700,7 +1700,7 @@ int mt7615_mcu_init(struct mt7615_dev *dev) }; int ret; - dev->mt76.mcu_ops = &mt7615_mcu_ops, + dev->mt76.mcu_ops = &mt7615_mcu_ops; ret = mt7615_mcu_drv_pmctrl(dev); if (ret) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h index 530da48ce3ea..9bdd29e8d25e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h @@ -139,7 +139,7 @@ struct mt7615_sta { }; struct mt7615_vif { - struct mt76_vif mt76; /* must be first */ + struct mt76_vif_link mt76; /* must be first */ struct mt7615_sta sta; bool sta_added; }; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci.c index 9f43e673518b..68010e27f065 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci.c @@ -83,7 +83,7 @@ static int mt7615_pci_suspend(struct pci_dev *pdev, pm_message_t state) hif_suspend = !test_bit(MT76_STATE_SUSPEND, &dev->mphy.state) && mt7615_firmware_offload(dev); if (hif_suspend) { - err = mt76_connac_mcu_set_hif_suspend(mdev, true); + err = mt76_connac_mcu_set_hif_suspend(mdev, true, true); if (err) return err; } @@ -131,7 +131,7 @@ restore: } napi_enable(&mdev->tx_napi); if (hif_suspend) - mt76_connac_mcu_set_hif_suspend(mdev, false); + mt76_connac_mcu_set_hif_suspend(mdev, false, true); return err; } @@ -164,18 +164,22 @@ static int mt7615_pci_resume(struct pci_dev *pdev) dev_err(mdev->dev, "PDMA engine must be reinitialized\n"); mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { napi_enable(&mdev->napi[i]); - napi_schedule(&mdev->napi[i]); } napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + napi_schedule(&mdev->napi[i]); + } napi_schedule(&mdev->tx_napi); local_bh_enable(); if (!test_bit(MT76_STATE_SUSPEND, &dev->mphy.state) && mt7615_firmware_offload(dev)) - err = mt76_connac_mcu_set_hif_suspend(mdev, false); + err = mt76_connac_mcu_set_hif_suspend(mdev, false, true); return err; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c index fbb1181c58ff..c2e4e6aabd9f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c @@ -48,7 +48,7 @@ mt7615_write_fw_txp(struct mt7615_dev *dev, struct mt76_tx_info *tx_info, txp->flags |= cpu_to_le16(MT_CT_INFO_MGMT_FRAME); if (vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; txp->bss_idx = mvif->idx; } @@ -262,12 +262,14 @@ void mt7615_mac_reset_work(struct work_struct *work) mt76_worker_enable(&dev->mt76.tx_worker); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); - napi_schedule(&dev->mt76.tx_napi); - mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); + } + + local_bh_disable(); + napi_schedule(&dev->mt76.tx_napi); + mt76_for_each_q_rx(&dev->mt76, i) { napi_schedule(&dev->mt76.napi[i]); } local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c index aebfc4576aa4..f56038cd4d3a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c @@ -191,7 +191,7 @@ static int mt7663s_suspend(struct device *dev) mt7615_firmware_offload(mdev)) { int err; - err = mt76_connac_mcu_set_hif_suspend(&mdev->mt76, true); + err = mt76_connac_mcu_set_hif_suspend(&mdev->mt76, true, true); if (err < 0) return err; } @@ -230,7 +230,7 @@ static int mt7663s_resume(struct device *dev) if (!test_bit(MT76_STATE_SUSPEND, &mdev->mphy.state) && mt7615_firmware_offload(mdev)) - err = mt76_connac_mcu_set_hif_suspend(&mdev->mt76, false); + err = mt76_connac_mcu_set_hif_suspend(&mdev->mt76, false, true); return err; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c index b0094205ba95..a7b8acb2da83 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c @@ -147,7 +147,7 @@ int mt7663s_mcu_init(struct mt7615_dev *dev) if (ret) return ret; - dev->mt76.mcu_ops = &mt7663s_mcu_ops, + dev->mt76.mcu_ops = &mt7663s_mcu_ops; ret = mt76_get_field(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY); if (ret) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c index 5020af52c68c..4aa9fa1c4a23 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c @@ -225,7 +225,7 @@ static int mt7663u_suspend(struct usb_interface *intf, pm_message_t state) mt7615_firmware_offload(dev)) { int err; - err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, true); + err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, true, true); if (err < 0) return err; } @@ -253,7 +253,7 @@ static int mt7663u_resume(struct usb_interface *intf) if (!test_bit(MT76_STATE_SUSPEND, &dev->mphy.state) && mt7615_firmware_offload(dev)) - err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, false); + err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, false, true); return err; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c index a8b1a0f8b2d7..33c01f8ce8e2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c @@ -72,7 +72,7 @@ int mt7663u_mcu_init(struct mt7615_dev *dev) }; int ret; - dev->mt76.mcu_ops = &mt7663u_mcu_ops, + dev->mt76.mcu_ops = &mt7663u_mcu_ops; mt76_set(dev, MT_UDMA_TX_QSEL, MT_FW_DL_EN); if (test_and_clear_bit(MT76_STATE_POWER_OFF, &dev->mphy.state)) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac.h index 445d0f0ab779..455979476d11 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac.h @@ -405,7 +405,7 @@ mt76_connac_mutex_release(struct mt76_dev *dev, struct mt76_connac_pm *pm) mutex_unlock(&dev->mutex); } -void mt76_connac_gen_ppe_thresh(u8 *he_ppet, int nss); +void mt76_connac_gen_ppe_thresh(u8 *he_ppet, int nss, enum nl80211_band band); int mt76_connac_init_tx_queues(struct mt76_phy *phy, int idx, int n_desc, int ring_base, void *wed, u32 flags); @@ -427,7 +427,7 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, struct ieee80211_key_conf *key, int pid, enum mt76_txq_id qid, u32 changed); u16 mt76_connac2_mac_tx_rate_val(struct mt76_phy *mphy, - struct ieee80211_vif *vif, + struct ieee80211_bss_conf *conf, bool beacon, bool mcast); bool mt76_connac2_mac_fill_txs(struct mt76_dev *dev, struct mt76_wcid *wcid, __le32 *txs_data); diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.c index 92ad1ecf6c9d..2d300948308d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.c @@ -231,7 +231,8 @@ void mt76_connac3_mac_decode_eht_radiotap(struct sk_buff *skb, __le32 *rxv, EHT_PREP(DATA0_PE_DISAMBIGUITY_OM, PE_DISAMBIG, rxv[5]) | EHT_PREP(DATA0_LDPC_EXTRA_SYM_OM, LDPC_EXT_SYM, rxv[4]); - eht->data[7] |= le32_encode_bits(status->nss, IEEE80211_RADIOTAP_EHT_DATA7_NSS_S); + /* iwlwifi and wireshark expect radiotap to report zero-based NSS, so subtract 1. */ + eht->data[7] |= le32_encode_bits(status->nss - 1, IEEE80211_RADIOTAP_EHT_DATA7_NSS_S); eht->user_info[0] |= EHT_BITS(USER_INFO_MCS_KNOWN) | @@ -240,7 +241,7 @@ void mt76_connac3_mac_decode_eht_radiotap(struct sk_buff *skb, __le32 *rxv, EHT_BITS(USER_INFO_BEAMFORMING_KNOWN_O) | EHT_BITS(USER_INFO_DATA_FOR_USER) | le32_encode_bits(status->rate_idx, IEEE80211_RADIOTAP_EHT_USER_INFO_MCS) | - le32_encode_bits(status->nss, IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_O); + le32_encode_bits(status->nss - 1, IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_O); if (le32_to_cpu(rxv[0]) & MT_PRXV_TXBF) eht->user_info[0] |= EHT_BITS(USER_INFO_BEAMFORMING_O); diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index a3db65254e37..e9ac8a7317a1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -9,10 +9,13 @@ #define HE_PREP(f, m, v) le16_encode_bits(le32_get_bits(v, MT_CRXV_HE_##m),\ IEEE80211_RADIOTAP_HE_##f) -void mt76_connac_gen_ppe_thresh(u8 *he_ppet, int nss) +void mt76_connac_gen_ppe_thresh(u8 *he_ppet, int nss, enum nl80211_band band) { static const u8 ppet16_ppet8_ru3_ru0[] = { 0x1c, 0xc7, 0x71 }; - u8 i, ppet_bits, ppet_size, ru_bit_mask = 0x7; /* HE80 */ + u8 i, ppet_bits, ppet_size, ru_bit_mask = 0xf; + + if (band == NL80211_BAND_2GHZ) + ru_bit_mask = 0x3; he_ppet[0] = FIELD_PREP(IEEE80211_PPE_THRES_NSS_MASK, nss - 1) | FIELD_PREP(IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK, @@ -291,27 +294,28 @@ EXPORT_SYMBOL_GPL(mt76_connac_init_tx_queues); }) u16 mt76_connac2_mac_tx_rate_val(struct mt76_phy *mphy, - struct ieee80211_vif *vif, + struct ieee80211_bss_conf *conf, bool beacon, bool mcast) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = mt76_vif_conf_link(mphy->dev, conf->vif, conf); struct cfg80211_chan_def *chandef = mvif->ctx ? &mvif->ctx->def : &mphy->chandef; u8 nss = 0, mode = 0, band = chandef->chan->band; int rateidx = 0, mcast_rate; + int offset = 0; - if (!vif) + if (!conf) goto legacy; if (is_mt7921(mphy->dev)) { - rateidx = ffs(vif->bss_conf.basic_rates) - 1; + rateidx = ffs(conf->basic_rates) - 1; goto legacy; } if (beacon) { struct cfg80211_bitrate_mask *mask; - mask = &vif->bss_conf.beacon_tx_rate; + mask = &conf->beacon_tx_rate; __bitrate_mask_check(he_mcs, HE_SU); __bitrate_mask_check(vht_mcs, VHT); @@ -323,14 +327,25 @@ u16 mt76_connac2_mac_tx_rate_val(struct mt76_phy *mphy, } } - mcast_rate = vif->bss_conf.mcast_rate[band]; + mcast_rate = conf->mcast_rate[band]; if (mcast && mcast_rate > 0) rateidx = mcast_rate - 1; else - rateidx = ffs(vif->bss_conf.basic_rates) - 1; + rateidx = ffs(conf->basic_rates) - 1; legacy: - rateidx = mt76_calculate_default_rate(mphy, vif, rateidx); + if (band != NL80211_BAND_2GHZ) + offset = 4; + + /* pick the lowest rate for hidden nodes */ + if (rateidx < 0) + rateidx = 0; + + rateidx += offset; + if (rateidx >= ARRAY_SIZE(mt76_rates)) + rateidx = offset; + + rateidx = mt76_rates[rateidx].hw_value; mode = rateidx >> 8; rateidx &= GENMASK(7, 0); out: @@ -493,7 +508,7 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, bool amsdu_en = wcid->amsdu; if (vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; omac_idx = mvif->omac_idx; wmm_idx = mvif->wmm_idx; @@ -569,7 +584,7 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; bool multicast = ieee80211_is_data(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1); - u16 rate = mt76_connac2_mac_tx_rate_val(mphy, vif, beacon, + u16 rate = mt76_connac2_mac_tx_rate_val(mphy, &vif->bss_conf, beacon, multicast); u32 val = MT_TXD6_FIXED_BW; @@ -1162,11 +1177,7 @@ void mt76_connac2_txwi_free(struct mt76_dev *dev, struct mt76_txwi_cache *t, if (wcid && wcid->sta) { sta = container_of((void *)wcid, struct ieee80211_sta, drv_priv); - spin_lock_bh(&dev->sta_poll_lock); - if (list_empty(&wcid->poll_list)) - list_add_tail(&wcid->poll_list, - &dev->sta_poll_list); - spin_unlock_bh(&dev->sta_poll_lock); + mt76_wcid_add_poll(dev, wcid); } } diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index 864246f94088..f30cf9e71610 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -189,7 +189,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_set_mac_enable); int mt76_connac_mcu_set_vif_ps(struct mt76_dev *dev, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct { u8 bss_idx; u8 ps_state; /* 0: device awake @@ -232,7 +232,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_set_rts_thresh); void mt76_connac_mcu_beacon_loss_iter(void *priv, u8 *mac, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt76_connac_beacon_loss_event *event = priv; if (mvif->idx != event->bss_idx) @@ -273,7 +273,7 @@ mt76_connac_mcu_add_nested_tlv(struct sk_buff *skb, int tag, int len, EXPORT_SYMBOL_GPL(mt76_connac_mcu_add_nested_tlv); struct sk_buff * -__mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, +__mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif_link *mvif, struct mt76_wcid *wcid, int len) { struct sta_req_hdr hdr = { @@ -329,7 +329,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_alloc_wtbl_req); void mt76_connac_mcu_bss_omac_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; u8 omac_idx = mvif->omac_idx; struct bss_info_omac *omac; struct tlv *tlv; @@ -369,10 +369,11 @@ void mt76_connac_mcu_bss_omac_tlv(struct sk_buff *skb, EXPORT_SYMBOL_GPL(mt76_connac_mcu_bss_omac_tlv); void mt76_connac_mcu_sta_basic_tlv(struct mt76_dev *dev, struct sk_buff *skb, - struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, struct ieee80211_link_sta *link_sta, int conn_state, bool newly) { + struct ieee80211_vif *vif = link_conf->vif; struct sta_rec_basic *basic; struct tlv *tlv; int conn_type; @@ -390,8 +391,8 @@ void mt76_connac_mcu_sta_basic_tlv(struct mt76_dev *dev, struct sk_buff *skb, basic->conn_type = cpu_to_le32(CONNECTION_INFRA_BC); if (vif->type == NL80211_IFTYPE_STATION && - !is_zero_ether_addr(vif->bss_conf.bssid)) { - memcpy(basic->peer_addr, vif->bss_conf.bssid, ETH_ALEN); + !is_zero_ether_addr(link_conf->bssid)) { + memcpy(basic->peer_addr, link_conf->bssid, ETH_ALEN); basic->aid = cpu_to_le16(vif->cfg.aid); } else { eth_broadcast_addr(basic->peer_addr); @@ -497,7 +498,7 @@ int mt76_connac_mcu_sta_update_hdr_trans(struct mt76_dev *dev, struct ieee80211_vif *vif, struct mt76_wcid *wcid, int cmd) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct wtbl_req_hdr *wtbl_hdr; struct tlv *sta_wtbl; struct sk_buff *skb; @@ -545,7 +546,7 @@ void mt76_connac_mcu_wtbl_generic_tlv(struct mt76_dev *dev, struct ieee80211_sta *sta, void *sta_wtbl, void *wtbl_tlv) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct wtbl_generic *generic; struct wtbl_rx *rx; struct wtbl_spe *spe; @@ -849,7 +850,7 @@ void mt76_connac_mcu_sta_tlv(struct mt76_phy *mphy, struct sk_buff *skb, struct ieee80211_vif *vif, u8 rcpi, u8 sta_state) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct cfg80211_chan_def *chandef = mvif->ctx ? &mvif->ctx->def : &mphy->chandef; enum nl80211_band band = chandef->chan->band; @@ -1041,7 +1042,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_wtbl_ht_tlv); int mt76_connac_mcu_sta_cmd(struct mt76_phy *phy, struct mt76_sta_cmd_info *info) { - struct mt76_vif *mvif = (struct mt76_vif *)info->vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)info->vif->drv_priv; struct ieee80211_link_sta *link_sta; struct mt76_dev *dev = phy->dev; struct wtbl_req_hdr *wtbl_hdr; @@ -1049,6 +1050,9 @@ int mt76_connac_mcu_sta_cmd(struct mt76_phy *phy, struct sk_buff *skb; int conn_state; + if (!info->link_conf) + info->link_conf = &info->vif->bss_conf; + skb = mt76_connac_mcu_alloc_sta_req(dev, mvif, info->wcid); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -1057,7 +1061,7 @@ int mt76_connac_mcu_sta_cmd(struct mt76_phy *phy, CONN_STATE_DISCONNECT; link_sta = info->sta ? &info->sta->deflink : NULL; if (info->sta || !info->offload_fw) - mt76_connac_mcu_sta_basic_tlv(dev, skb, info->vif, + mt76_connac_mcu_sta_basic_tlv(dev, skb, info->link_conf, link_sta, conn_state, info->newly); if (info->sta && info->enable) @@ -1137,10 +1141,10 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_wtbl_ba_tlv); int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy, struct ieee80211_bss_conf *bss_conf, + struct mt76_vif_link *mvif, struct mt76_wcid *wcid, bool enable) { - struct mt76_vif *mvif = (struct mt76_vif *)bss_conf->vif->drv_priv; struct mt76_dev *dev = phy->dev; struct { struct { @@ -1202,6 +1206,9 @@ int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy, case NL80211_IFTYPE_STATION: basic_req.basic.conn_type = cpu_to_le32(CONNECTION_INFRA_STA); break; + case NL80211_IFTYPE_P2P_DEVICE: + basic_req.basic.conn_type = cpu_to_le32(CONNECTION_P2P_GO); + break; case NL80211_IFTYPE_ADHOC: basic_req.basic.conn_type = cpu_to_le32(CONNECTION_IBSS_ADHOC); break; @@ -1263,7 +1270,7 @@ int mt76_connac_mcu_sta_wed_update(struct mt76_dev *dev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(mt76_connac_mcu_sta_wed_update); -int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif, +int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif_link *mvif, struct ieee80211_ampdu_params *params, int cmd, bool enable, bool tx) { @@ -1364,7 +1371,7 @@ u8 mt76_connac_get_phy_mode(struct mt76_phy *phy, struct ieee80211_vif *vif, } EXPORT_SYMBOL_GPL(mt76_connac_get_phy_mode); -u8 mt76_connac_get_phy_mode_ext(struct mt76_phy *phy, struct ieee80211_vif *vif, +u8 mt76_connac_get_phy_mode_ext(struct mt76_phy *phy, struct ieee80211_bss_conf *conf, enum nl80211_band band) { const struct ieee80211_sta_eht_cap *eht_cap; @@ -1375,9 +1382,9 @@ u8 mt76_connac_get_phy_mode_ext(struct mt76_phy *phy, struct ieee80211_vif *vif, mode |= PHY_MODE_AX_6G; sband = phy->hw->wiphy->bands[band]; - eht_cap = ieee80211_get_eht_iftype_cap(sband, vif->type); + eht_cap = ieee80211_get_eht_iftype_cap(sband, conf->vif->type); - if (!eht_cap || !eht_cap->has_eht || !vif->bss_conf.eht_support) + if (!eht_cap || !eht_cap->has_eht || !conf->eht_support) return mode; switch (band) { @@ -1401,7 +1408,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_get_phy_mode_ext); const struct ieee80211_sta_he_cap * mt76_connac_get_he_phy_cap(struct mt76_phy *phy, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct cfg80211_chan_def *chandef = mvif->ctx ? &mvif->ctx->def : &phy->chandef; enum nl80211_band band = chandef->chan->band; @@ -1450,7 +1457,7 @@ mt76_connac_mcu_uni_bss_he_tlv(struct mt76_phy *phy, struct ieee80211_vif *vif, he->max_nss_mcs[CMD_HE_MCS_BW8080] = cap->he_mcs_nss_supp.tx_mcs_80p80; } -int mt76_connac_mcu_uni_set_chctx(struct mt76_phy *phy, struct mt76_vif *mvif, +int mt76_connac_mcu_uni_set_chctx(struct mt76_phy *phy, struct mt76_vif_link *mvif, struct ieee80211_chanctx_conf *ctx) { struct cfg80211_chan_def *chandef = ctx ? &ctx->def : &phy->chandef; @@ -1538,7 +1545,7 @@ int mt76_connac_mcu_uni_add_bss(struct mt76_phy *phy, bool enable, struct ieee80211_chanctx_conf *ctx) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct cfg80211_chan_def *chandef = ctx ? &ctx->def : &phy->chandef; enum nl80211_band band = chandef->chan->band; struct mt76_dev *mdev = phy->dev; @@ -1664,7 +1671,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_uni_add_bss); int mt76_connac_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_scan_request *scan_req) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct cfg80211_scan_request *sreq = &scan_req->req; int n_ssids = 0, err, i, duration; int ext_channels_num = max_t(int, sreq->n_channels - 32, 0); @@ -1770,7 +1777,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_hw_scan); int mt76_connac_mcu_cancel_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct { u8 seq_num; u8 is_ext_channel; @@ -1796,7 +1803,7 @@ int mt76_connac_mcu_sched_scan_req(struct mt76_phy *phy, struct ieee80211_vif *vif, struct cfg80211_sched_scan_request *sreq) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct ieee80211_channel **scan_list = sreq->channels; struct mt76_connac_mcu_scan_channel *chan; struct mt76_connac_sched_scan_req *req; @@ -2208,7 +2215,7 @@ int mt76_connac_mcu_set_rate_txpower(struct mt76_phy *phy) EXPORT_SYMBOL_GPL(mt76_connac_mcu_set_rate_txpower); int mt76_connac_mcu_update_arp_filter(struct mt76_dev *dev, - struct mt76_vif *vif, + struct mt76_vif_link *vif, struct ieee80211_bss_conf *info) { struct ieee80211_vif *mvif = container_of(info, struct ieee80211_vif, @@ -2251,7 +2258,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_update_arp_filter); int mt76_connac_mcu_set_p2p_oppps(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; int ct_window = vif->bss_conf.p2p_noa_attr.oppps_ctwindow; struct mt76_phy *phy = hw->priv; struct { @@ -2318,7 +2325,7 @@ int mt76_connac_mcu_update_gtk_rekey(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_gtk_rekey_data *key) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt76_connac_gtk_rekey_tlv *gtk_tlv; struct mt76_phy *phy = hw->priv; struct sk_buff *skb; @@ -2359,7 +2366,7 @@ static int mt76_connac_mcu_set_arp_filter(struct mt76_dev *dev, struct ieee80211_vif *vif, bool suspend) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct { struct { u8 bss_idx; @@ -2385,7 +2392,7 @@ int mt76_connac_mcu_set_gtk_rekey(struct mt76_dev *dev, struct ieee80211_vif *vif, bool suspend) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct { struct { u8 bss_idx; @@ -2414,7 +2421,7 @@ mt76_connac_mcu_set_suspend_mode(struct mt76_dev *dev, bool enable, u8 mdtim, bool wow_suspend) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct { struct { u8 bss_idx; @@ -2445,7 +2452,7 @@ mt76_connac_mcu_set_wow_pattern(struct mt76_dev *dev, u8 index, bool enable, struct cfg80211_pkt_pattern *pattern) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt76_connac_wow_pattern_tlv *ptlv; struct sk_buff *skb; struct req_hdr { @@ -2477,7 +2484,7 @@ int mt76_connac_mcu_set_wow_ctrl(struct mt76_phy *phy, struct ieee80211_vif *vif, bool suspend, struct cfg80211_wowlan *wowlan) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt76_dev *dev = phy->dev; struct { struct { @@ -2527,7 +2534,7 @@ mt76_connac_mcu_set_wow_ctrl(struct mt76_phy *phy, struct ieee80211_vif *vif, } EXPORT_SYMBOL_GPL(mt76_connac_mcu_set_wow_ctrl); -int mt76_connac_mcu_set_hif_suspend(struct mt76_dev *dev, bool suspend) +int mt76_connac_mcu_set_hif_suspend(struct mt76_dev *dev, bool suspend, bool wait_resp) { struct { struct { @@ -2559,7 +2566,7 @@ int mt76_connac_mcu_set_hif_suspend(struct mt76_dev *dev, bool suspend) req.hdr.hif_type = 0; return mt76_mcu_send_msg(dev, MCU_UNI_CMD(HIF_CTRL), &req, - sizeof(req), true); + sizeof(req), wait_resp); } EXPORT_SYMBOL_GPL(mt76_connac_mcu_set_hif_suspend); @@ -2686,7 +2693,7 @@ int mt76_connac_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, struct ieee80211_key_conf *key, int mcu_cmd, struct mt76_wcid *wcid, enum set_key_cmd cmd) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct sk_buff *skb; int ret; @@ -2708,7 +2715,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_add_key); /* SIFS 20us + 512 byte beacon transmitted by 1Mbps (3906us) */ #define BCN_TX_ESTIMATE_TIME (4096 + 20) -void mt76_connac_mcu_bss_ext_tlv(struct sk_buff *skb, struct mt76_vif *mvif) +void mt76_connac_mcu_bss_ext_tlv(struct sk_buff *skb, struct mt76_vif_link *mvif) { struct bss_info_ext_bss *ext; int ext_bss_idx, tsf_offset; @@ -2732,7 +2739,7 @@ int mt76_connac_mcu_bss_basic_tlv(struct sk_buff *skb, struct mt76_phy *phy, u16 wlan_idx, bool enable) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; u32 type = vif->p2p ? NETWORK_P2P : NETWORK_INFRA; struct bss_info_basic *bss; struct tlv *tlv; diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h index 1b0e80dfc346..43237e518373 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h @@ -1043,12 +1043,14 @@ enum { MCU_EXT_EVENT_CSA_NOTIFY = 0x4f, MCU_EXT_EVENT_WA_TX_STAT = 0x74, MCU_EXT_EVENT_BCC_NOTIFY = 0x75, + MCU_EXT_EVENT_WF_RF_PIN_CTRL = 0x9a, MCU_EXT_EVENT_MURU_CTRL = 0x9f, }; /* unified event table */ enum { MCU_UNI_EVENT_RESULT = 0x01, + MCU_UNI_EVENT_HIF_CTRL = 0x03, MCU_UNI_EVENT_FW_LOG_2_HOST = 0x04, MCU_UNI_EVENT_ACCESS_REG = 0x6, MCU_UNI_EVENT_IE_COUNTDOWN = 0x09, @@ -1251,6 +1253,7 @@ enum { MCU_EXT_CMD_GROUP_PRE_CAL_INFO = 0xab, MCU_EXT_CMD_DPD_PRE_CAL_INFO = 0xac, MCU_EXT_CMD_PHY_STAT_INFO = 0xad, + MCU_EXT_CMD_WF_RF_PIN_CTRL = 0xbd, }; enum { @@ -1756,6 +1759,7 @@ struct mt76_sta_cmd_info { struct mt76_wcid *wcid; struct ieee80211_vif *vif; + struct ieee80211_bss_conf *link_conf; bool offload_fw; bool enable; @@ -1876,10 +1880,10 @@ mt76_connac_mcu_get_wlan_idx(struct mt76_dev *dev, struct mt76_wcid *wcid, } struct sk_buff * -__mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, +__mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif_link *mvif, struct mt76_wcid *wcid, int len); static inline struct sk_buff * -mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, +mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif_link *mvif, struct mt76_wcid *wcid) { return __mt76_connac_mcu_alloc_sta_req(dev, mvif, wcid, @@ -1901,7 +1905,7 @@ mt76_connac_mcu_add_tlv(struct sk_buff *skb, int tag, int len) int mt76_connac_mcu_set_channel_domain(struct mt76_phy *phy); int mt76_connac_mcu_set_vif_ps(struct mt76_dev *dev, struct ieee80211_vif *vif); void mt76_connac_mcu_sta_basic_tlv(struct mt76_dev *dev, struct sk_buff *skb, - struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, struct ieee80211_link_sta *link_sta, int state, bool newly); void mt76_connac_mcu_wtbl_generic_tlv(struct mt76_dev *dev, struct sk_buff *skb, @@ -1938,13 +1942,14 @@ void mt76_connac_mcu_sta_ba_tlv(struct sk_buff *skb, bool enable, bool tx); int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy, struct ieee80211_bss_conf *bss_conf, + struct mt76_vif_link *mvif, struct mt76_wcid *wcid, bool enable); -int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif, +int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif_link *mvif, struct ieee80211_ampdu_params *params, int cmd, bool enable, bool tx); int mt76_connac_mcu_uni_set_chctx(struct mt76_phy *phy, - struct mt76_vif *vif, + struct mt76_vif_link *vif, struct ieee80211_chanctx_conf *ctx); int mt76_connac_mcu_uni_add_bss(struct mt76_phy *phy, struct ieee80211_vif *vif, @@ -1975,7 +1980,7 @@ int mt76_connac_mcu_sched_scan_enable(struct mt76_phy *phy, struct ieee80211_vif *vif, bool enable); int mt76_connac_mcu_update_arp_filter(struct mt76_dev *dev, - struct mt76_vif *vif, + struct mt76_vif_link *vif, struct ieee80211_bss_conf *info); int mt76_connac_mcu_set_gtk_rekey(struct mt76_dev *dev, struct ieee80211_vif *vif, bool suspend); @@ -1988,7 +1993,7 @@ int mt76_connac_mcu_set_suspend_mode(struct mt76_dev *dev, struct ieee80211_vif *vif, bool enable, u8 mdtim, bool wow_suspend); -int mt76_connac_mcu_set_hif_suspend(struct mt76_dev *dev, bool suspend); +int mt76_connac_mcu_set_hif_suspend(struct mt76_dev *dev, bool suspend, bool wait_resp); void mt76_connac_mcu_set_suspend_iter(void *priv, u8 *mac, struct ieee80211_vif *vif); int mt76_connac_sta_state_dp(struct mt76_dev *dev, @@ -2014,7 +2019,7 @@ mt76_connac_get_eht_phy_cap(struct mt76_phy *phy, struct ieee80211_vif *vif); u8 mt76_connac_get_phy_mode(struct mt76_phy *phy, struct ieee80211_vif *vif, enum nl80211_band band, struct ieee80211_link_sta *sta); -u8 mt76_connac_get_phy_mode_ext(struct mt76_phy *phy, struct ieee80211_vif *vif, +u8 mt76_connac_get_phy_mode_ext(struct mt76_phy *phy, struct ieee80211_bss_conf *conf, enum nl80211_band band); int mt76_connac_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, @@ -2022,7 +2027,7 @@ int mt76_connac_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, struct ieee80211_key_conf *key, int mcu_cmd, struct mt76_wcid *wcid, enum set_key_cmd cmd); -void mt76_connac_mcu_bss_ext_tlv(struct sk_buff *skb, struct mt76_vif *mvif); +void mt76_connac_mcu_bss_ext_tlv(struct sk_buff *skb, struct mt76_vif_link *mvif); void mt76_connac_mcu_bss_omac_tlv(struct sk_buff *skb, struct ieee80211_vif *vif); int mt76_connac_mcu_bss_basic_tlv(struct sk_buff *skb, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c index 1eb955f3ca13..b456ccd00d58 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c @@ -282,14 +282,16 @@ static int mt76x0e_resume(struct pci_dev *pdev) mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { mt76_queue_rx_reset(dev, i); napi_enable(&mdev->napi[i]); + } + napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { napi_schedule(&mdev->napi[i]); } - - napi_enable(&mdev->tx_napi); napi_schedule(&mdev->tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c index d543ef3de65b..ec554a059216 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c @@ -1071,7 +1071,7 @@ mt76x0_phy_update_channel_gain(struct mt76x02_dev *dev) u8 gain_delta; int low_gain; - dev->cal.avg_rssi_all = mt76_get_min_avg_rssi(&dev->mt76, false); + dev->cal.avg_rssi_all = mt76_get_min_avg_rssi(&dev->mt76, 0); if (!dev->cal.avg_rssi_all) dev->cal.avg_rssi_all = -75; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c index 4a49a3036a46..a82c75ba26e6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c @@ -423,7 +423,7 @@ static void mt76x02_reset_state(struct mt76x02_dev *dev) priv = msta->vif; vif = container_of(priv, struct ieee80211_vif, drv_priv); - __mt76_sta_remove(&dev->mt76, vif, sta); + __mt76_sta_remove(&dev->mphy, vif, sta); memset(msta, 0, sizeof(*msta)); } @@ -504,12 +504,14 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev) mt76_worker_enable(&dev->mt76.tx_worker); tasklet_enable(&dev->mt76.pre_tbtt_tasklet); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); - napi_schedule(&dev->mt76.tx_napi); - mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); + } + + local_bh_disable(); + napi_schedule(&dev->mt76.tx_napi); + mt76_for_each_q_rx(&dev->mt76, i) { napi_schedule(&dev->mt76.napi[i]); } local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c index 8020446be37b..4fb30589fa7a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c @@ -287,8 +287,7 @@ mt76x02_vif_init(struct mt76x02_dev *dev, struct ieee80211_vif *vif, mvif->idx = idx; mvif->group_wcid.idx = MT_VIF_WCID(idx); - mvif->group_wcid.hw_key_idx = -1; - mt76_wcid_init(&mvif->group_wcid); + mt76_wcid_init(&mvif->group_wcid, 0); mtxq = (struct mt76_txq *)vif->txq->drv_priv; rcu_assign_pointer(dev->mt76.wcid[MT_VIF_WCID(idx)], &mvif->group_wcid); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c index 67c9d1caa0bd..727bfdd00b40 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c @@ -151,12 +151,15 @@ mt76x2e_resume(struct pci_dev *pdev) mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { napi_enable(&mdev->napi[i]); - napi_schedule(&mdev->napi[i]); } napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + napi_schedule(&mdev->napi[i]); + } napi_schedule(&mdev->tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c index f84517d932dc..e2b4cf30dc44 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c @@ -280,7 +280,7 @@ void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev) int low_gain; u32 val; - dev->cal.avg_rssi_all = mt76_get_min_avg_rssi(&dev->mt76, false); + dev->cal.avg_rssi_all = mt76_get_min_avg_rssi(&dev->mt76, 0); if (!dev->cal.avg_rssi_all) dev->cal.avg_rssi_all = -75; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c index bfdbc15abaa9..928e0b07a9bf 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c @@ -2,9 +2,14 @@ /* Copyright (C) 2020 MediaTek Inc. */ #include +#include #include "mt7915.h" #include "eeprom.h" +static bool enable_6ghz; +module_param(enable_6ghz, bool, 0644); +MODULE_PARM_DESC(enable_6ghz, "Enable 6 GHz instead of 5 GHz on hardware that supports both"); + static int mt7915_eeprom_load_precal(struct mt7915_dev *dev) { struct mt76_dev *mdev = &dev->mt76; @@ -170,8 +175,20 @@ static void mt7915_eeprom_parse_band_config(struct mt7915_phy *phy) phy->mt76->cap.has_6ghz = true; return; case MT_EE_V2_BAND_SEL_5GHZ_6GHZ: - phy->mt76->cap.has_5ghz = true; - phy->mt76->cap.has_6ghz = true; + if (enable_6ghz) { + phy->mt76->cap.has_6ghz = true; + u8p_replace_bits(&eeprom[MT_EE_WIFI_CONF + band], + MT_EE_V2_BAND_SEL_6GHZ, + MT_EE_WIFI_CONF0_BAND_SEL); + } else { + phy->mt76->cap.has_5ghz = true; + u8p_replace_bits(&eeprom[MT_EE_WIFI_CONF + band], + MT_EE_V2_BAND_SEL_5GHZ, + MT_EE_WIFI_CONF0_BAND_SEL); + } + /* force to buffer mode */ + dev->flash_mode = true; + return; default: phy->mt76->cap.has_2ghz = true; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c index 6bef96e3d2a3..bee4beabc4eb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c @@ -53,7 +53,9 @@ static ssize_t mt7915_thermal_temp_show(struct device *dev, switch (i) { case 0: + mutex_lock(&phy->dev->mt76.mutex); temperature = mt7915_mcu_get_temperature(phy); + mutex_unlock(&phy->dev->mt76.mutex); if (temperature < 0) return temperature; /* display in millidegree celcius */ @@ -82,7 +84,7 @@ static ssize_t mt7915_thermal_temp_store(struct device *dev, return ret; mutex_lock(&phy->dev->mt76.mutex); - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 60, 130); + val = DIV_ROUND_CLOSEST(clamp_val(val, 60 * 1000, 130 * 1000), 1000); if ((i - 1 == MT7915_CRIT_TEMP_IDX && val > phy->throttle_temp[MT7915_MAX_TEMP_IDX]) || @@ -95,9 +97,8 @@ static ssize_t mt7915_thermal_temp_store(struct device *dev, } phy->throttle_temp[i - 1] = val; - mutex_unlock(&phy->dev->mt76.mutex); - ret = mt7915_mcu_set_thermal_protect(phy); + mutex_unlock(&phy->dev->mt76.mutex); if (ret) return ret; @@ -159,7 +160,9 @@ mt7915_thermal_set_cur_throttle_state(struct thermal_cooling_device *cdev, * cooling_device convention: 0 = no cooling, more = more cooling * mcu convention: 1 = max cooling, more = less cooling */ + mutex_lock(&phy->dev->mt76.mutex); ret = mt7915_mcu_set_thermal_throttling(phy, throttling); + mutex_unlock(&phy->dev->mt76.mutex); if (ret) return ret; @@ -512,6 +515,15 @@ mt7915_mac_init_band(struct mt7915_dev *dev, u8 band) mt76_clear(dev, MT_WF_RMAC_MIB_AIRTIME4(band), MT_WF_RMAC_MIB_QOS23_BACKOFF); + /* clear backoff time for Tx duration */ + mt76_clear(dev, MT_WTBLOFF_TOP_ACR(band), + MT_WTBLOFF_TOP_ADM_BACKOFFTIME); + + /* exclude estimated backoff time for Tx duration on MT7915 */ + if (is_mt7915(&dev->mt76)) + mt76_set(dev, MT_AGG_ATCR0(band), + MT_AGG_ATCR_MAC_BFF_TIME_EN); + /* clear backoff time and set software compensation for OBSS time */ mask = MT_WF_RMAC_MIB_OBSS_BACKOFF | MT_WF_RMAC_MIB_ED_OFFSET; set = FIELD_PREP(MT_WF_RMAC_MIB_OBSS_BACKOFF, 0) | @@ -1114,7 +1126,7 @@ mt7915_init_he_caps(struct mt7915_phy *phy, enum nl80211_band band, memset(he_cap->ppe_thres, 0, sizeof(he_cap->ppe_thres)); if (he_cap_elem->phy_cap_info[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { - mt76_connac_gen_ppe_thresh(he_cap->ppe_thres, nss); + mt76_connac_gen_ppe_thresh(he_cap->ppe_thres, nss, band); } else { he_cap_elem->phy_cap_info[9] |= u8_encode_bits(IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US, @@ -1239,14 +1251,14 @@ int mt7915_register_device(struct mt7915_dev *dev) if (ret) goto unreg_dev; - ieee80211_queue_work(mt76_hw(dev), &dev->init_work); - if (phy2) { ret = mt7915_register_ext_phy(dev, phy2); if (ret) goto unreg_thermal; } + ieee80211_queue_work(mt76_hw(dev), &dev->init_work); + dev->recovery.hw_init_done = true; ret = mt7915_init_debugfs(&dev->phy); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index cf77ce0c8759..2ba6eb3038ce 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -333,11 +333,7 @@ mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb, if (status->wcid) { msta = container_of(status->wcid, struct mt7915_sta, wcid); - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&msta->wcid.poll_list)) - list_add_tail(&msta->wcid.poll_list, - &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &msta->wcid); } status->freq = mphy->chandef.chan->center_freq; @@ -927,11 +923,7 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len) continue; msta = container_of(wcid, struct mt7915_sta, wcid); - spin_lock_bh(&mdev->sta_poll_lock); - if (list_empty(&msta->wcid.poll_list)) - list_add_tail(&msta->wcid.poll_list, - &mdev->sta_poll_list); - spin_unlock_bh(&mdev->sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &msta->wcid); continue; } @@ -1040,10 +1032,7 @@ static void mt7915_mac_add_txs(struct mt7915_dev *dev, void *data) if (!wcid->sta) goto out; - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&msta->wcid.poll_list)) - list_add_tail(&msta->wcid.poll_list, &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &msta->wcid); out: rcu_read_unlock(); @@ -1163,7 +1152,7 @@ void mt7915_mac_set_timing(struct mt7915_phy *phy) u32 ofdm = FIELD_PREP(MT_TIMEOUT_VAL_PLCP, 60) | FIELD_PREP(MT_TIMEOUT_VAL_CCA, 28); u8 band = phy->mt76->band_idx; - int eifs_ofdm = 360, sifs = 10, offset; + int eifs_ofdm = 84, sifs = 10, offset; bool a_band = !(phy->mt76->chandef.chan->band == NL80211_BAND_2GHZ); if (!test_bit(MT76_STATE_RUNNING, &phy->mt76->state)) @@ -1367,10 +1356,15 @@ mt7915_mac_restart(struct mt7915_dev *dev) mt7915_dma_reset(dev, true); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { if (mdev->q_rx[i].ndesc) { napi_enable(&dev->mt76.napi[i]); + } + } + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + if (mdev->q_rx[i].ndesc) { napi_schedule(&dev->mt76.napi[i]); } } @@ -1388,6 +1382,8 @@ mt7915_mac_restart(struct mt7915_dev *dev) if (dev_is_pci(mdev->dev)) { mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff); if (dev->hif2) { + mt76_wr(dev, MT_PCIE_RECOG_ID, + dev->hif2->index | MT_PCIE_RECOG_ID_SEM); if (is_mt7915(mdev)) mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE, 0xff); else @@ -1428,8 +1424,9 @@ out: if (phy2) clear_bit(MT76_RESET, &phy2->mt76->state); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); @@ -1442,9 +1439,11 @@ static void mt7915_mac_full_reset(struct mt7915_dev *dev) { struct mt76_phy *ext_phy; + struct mt7915_phy *phy2; int i; ext_phy = dev->mt76.phys[MT_BAND1]; + phy2 = ext_phy ? ext_phy->priv : NULL; dev->recovery.hw_full_reset = true; @@ -1474,6 +1473,9 @@ mt7915_mac_full_reset(struct mt7915_dev *dev) memset(dev->mt76.wcid_mask, 0, sizeof(dev->mt76.wcid_mask)); dev->mt76.vif_mask = 0; + dev->phy.omac_mask = 0; + if (phy2) + phy2->omac_mask = 0; i = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7915_WTBL_STA); dev->mt76.global_wcid.idx = i; @@ -1574,9 +1576,12 @@ void mt7915_mac_reset_work(struct work_struct *work) if (phy2) clear_bit(MT76_RESET, &phy2->mt76->state); - local_bh_disable(); mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); + } + + local_bh_disable(); + mt76_for_each_q_rx(&dev->mt76, i) { napi_schedule(&dev->mt76.napi[i]); } local_bh_enable(); @@ -1585,8 +1590,8 @@ void mt7915_mac_reset_work(struct work_struct *work) mt76_worker_enable(&dev->mt76.tx_worker); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index c6f498fc81ff..3aa31c5cefa6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -233,6 +233,7 @@ static int mt7915_add_interface(struct ieee80211_hw *hw, mvif->mt76.omac_idx = idx; mvif->phy = phy; mvif->mt76.band_idx = phy->mt76->band_idx; + mvif->mt76.wcid = &mvif->sta.wcid; mvif->mt76.wmm_idx = vif->type != NL80211_IFTYPE_AP; if (ext_phy) @@ -246,16 +247,15 @@ static int mt7915_add_interface(struct ieee80211_hw *hw, phy->omac_mask |= BIT_ULL(mvif->mt76.omac_idx); idx = mt76_wcid_alloc(dev->mt76.wcid_mask, mt7915_wtbl_size(dev)); - if (idx < 0) - return -ENOSPC; + if (idx < 0) { + ret = -ENOSPC; + goto out; + } INIT_LIST_HEAD(&mvif->sta.rc_list); - INIT_LIST_HEAD(&mvif->sta.wcid.poll_list); mvif->sta.wcid.idx = idx; - mvif->sta.wcid.phy_idx = ext_phy; - mvif->sta.wcid.hw_key_idx = -1; mvif->sta.wcid.tx_info |= MT_WCID_TX_INFO_SET; - mt76_wcid_init(&mvif->sta.wcid); + mt76_wcid_init(&mvif->sta.wcid, phy->mt76->band_idx); mt7915_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); @@ -366,8 +366,12 @@ static int mt7915_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, int idx = key->keyidx; int err = 0; - if (sta && !wcid->sta) + if (sta && !wcid->sta) { + if (cmd != SET_KEY) + return 0; + return -EOPNOTSUPP; + } /* The hardware does not support per-STA RX GTK, fallback * to software mode for these. @@ -619,8 +623,9 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw, if (changed & BSS_CHANGED_ASSOC) set_bss_info = vif->cfg.assoc; if (changed & BSS_CHANGED_BEACON_ENABLED && + info->enable_beacon && vif->type != NL80211_IFTYPE_AP) - set_bss_info = set_sta = info->enable_beacon; + set_bss_info = set_sta = 1; if (set_bss_info == 1) mt7915_mcu_add_bss_info(phy, vif, true); @@ -631,7 +636,11 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw, mt7915_mac_enable_rtscts(dev, vif, info->use_cts_prot); if (changed & BSS_CHANGED_ERP_SLOT) { - int slottime = info->use_short_slot ? 9 : 20; + int slottime = 9; + + if (phy->mt76->chandef.chan->band == NL80211_BAND_2GHZ && + !info->use_short_slot) + slottime = 20; if (slottime != phy->slottime) { phy->slottime = slottime; @@ -758,6 +767,57 @@ int mt7915_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, return 0; } +struct drop_sta_iter { + struct mt7915_dev *dev; + struct ieee80211_hw *hw; + struct ieee80211_vif *vif; + u8 sta_addr[ETH_ALEN]; +}; + +static void +__mt7915_drop_sta(void *ptr, u8 *mac, struct ieee80211_vif *vif) +{ + struct drop_sta_iter *data = ptr; + struct ieee80211_sta *sta; + struct mt7915_sta *msta; + + if (vif == data->vif || vif->type != NL80211_IFTYPE_AP) + return; + + sta = ieee80211_find_sta_by_ifaddr(data->hw, data->sta_addr, mac); + if (!sta) + return; + + msta = (struct mt7915_sta *)sta->drv_priv; + mt7915_mcu_add_sta(data->dev, vif, sta, CONN_STATE_DISCONNECT, false); + msta->wcid.sta_disabled = 1; + msta->wcid.sta = 0; +} + +static void +mt7915_drop_other_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct mt76_phy *ext_phy = dev->mt76.phys[MT_BAND1]; + struct drop_sta_iter data = { + .dev = dev, + .hw = dev->mphy.hw, + .vif = vif, + }; + + if (vif->type != NL80211_IFTYPE_AP) + return; + + memcpy(data.sta_addr, sta->addr, ETH_ALEN); + ieee80211_iterate_active_interfaces(data.hw, 0, __mt7915_drop_sta, &data); + + if (!ext_phy) + return; + + data.hw = ext_phy->hw; + ieee80211_iterate_active_interfaces(data.hw, 0, __mt7915_drop_sta, &data); +} + int mt7915_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta, enum mt76_sta_event ev) { @@ -786,6 +846,7 @@ int mt7915_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif, return 0; case MT76_STA_EVENT_AUTHORIZE: + mt7915_drop_other_sta(dev, vif, sta); return mt7915_mcu_add_sta(dev, vif, sta, CONN_STATE_PORT_SECURE, false); case MT76_STA_EVENT_DISASSOC: diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index 87d0dd040001..9d790f234e82 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -194,6 +194,25 @@ mt7915_mcu_parse_response(struct mt76_dev *mdev, int cmd, return ret; } +static void +mt7915_mcu_set_timeout(struct mt76_dev *mdev, int cmd) +{ + if ((cmd & __MCU_CMD_FIELD_ID) != MCU_CMD_EXT_CID) + return; + + switch (FIELD_GET(__MCU_CMD_FIELD_EXT_ID, cmd)) { + case MCU_EXT_CMD_THERMAL_CTRL: + case MCU_EXT_CMD_GET_MIB_INFO: + case MCU_EXT_CMD_PHY_STAT_INFO: + case MCU_EXT_CMD_STA_REC_UPDATE: + case MCU_EXT_CMD_BSS_INFO_UPDATE: + mdev->mcu.timeout = 2 * HZ; + return; + default: + break; + } +} + static int mt7915_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb, int cmd, int *wait_seq) @@ -208,6 +227,8 @@ mt7915_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb, else qid = MT_MCUQ_WM; + mt7915_mcu_set_timeout(mdev, cmd); + return mt76_tx_queue_skb_raw(dev, mdev->q_mcu[qid], skb, 0); } @@ -1678,7 +1699,7 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif, return PTR_ERR(skb); /* starec basic */ - mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, vif, link_sta, + mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, &vif->bss_conf, link_sta, conn_state, newly); /* tag order is in accordance with firmware dependency. */ if (sta && conn_state != CONN_STATE_DISCONNECT) { @@ -2388,7 +2409,7 @@ int mt7915_mcu_init_firmware(struct mt7915_dev *dev) int mt7915_mcu_init(struct mt7915_dev *dev) { static const struct mt76_mcu_ops mt7915_mcu_ops = { - .max_retry = 3, + .max_retry = 1, .headroom = sizeof(struct mt76_connac2_mcu_txd), .mcu_skb_prepare_msg = mt76_connac2_mcu_fill_message, .mcu_skb_send_msg = mt7915_mcu_send_message, @@ -3150,8 +3171,13 @@ int mt7915_mcu_get_chan_mib_info(struct mt7915_phy *phy, bool chan_switch) res = (struct mt7915_mcu_mib *)(skb->data + offs_cc); #define __res_u64(s) le64_to_cpu(res[s].data) - /* subtract Tx backoff time from Tx duration */ - cc_tx = is_mt7915(&dev->mt76) ? __res_u64(1) - __res_u64(4) : __res_u64(1); + /* subtract Tx backoff time from Tx duration for MT7915 */ + if (is_mt7915(&dev->mt76)) { + u64 backoff = (__res_u64(4) & 0xffff) * 79; /* 16us + 9us * 7 */ + cc_tx = __res_u64(1) - backoff; + } else { + cc_tx = __res_u64(1); + } if (chan_switch) goto out; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c index 44e112b8b5b3..876f0692850a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c @@ -138,6 +138,7 @@ static const u32 mt7915_offs[] = { [AGG_ACR0] = 0x084, [AGG_ACR4] = 0x08c, [AGG_MRCR] = 0x098, + [AGG_ATCR0] = 0x0ec, [AGG_ATCR1] = 0x0f0, [AGG_ATCR3] = 0x0f4, [LPON_UTTR0] = 0x080, @@ -212,6 +213,7 @@ static const u32 mt7916_offs[] = { [AGG_ACR0] = 0x054, [AGG_ACR4] = 0x05c, [AGG_MRCR] = 0x068, + [AGG_ATCR0] = 0x1a4, [AGG_ATCR1] = 0x1a8, [AGG_ATCR3] = 0x080, [LPON_UTTR0] = 0x360, @@ -484,7 +486,7 @@ static u32 __mt7915_reg_addr(struct mt7915_dev *dev, u32 addr) continue; ofs = addr - dev->reg.map[i].phys; - if (ofs > dev->reg.map[i].size) + if (ofs >= dev->reg.map[i].size) continue; return dev->reg.map[i].maps + ofs; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h index ac0b1f0eb27c..533939f2b7ed 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h @@ -166,7 +166,7 @@ struct mt7915_vif_cap { }; struct mt7915_vif { - struct mt76_vif mt76; /* must be first */ + struct mt76_vif_link mt76; /* must be first */ struct mt7915_vif_cap cap; struct mt7915_sta sta; @@ -191,6 +191,7 @@ struct mt7915_hif { struct device *dev; void __iomem *regs; int irq; + u32 index; }; struct mt7915_phy { diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c index 39132894e8ea..07b0a5766eab 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c @@ -42,6 +42,7 @@ static struct mt7915_hif *mt7915_pci_get_hif2(u32 idx) continue; get_device(hif->dev); + hif->index = idx; goto out; } hif = NULL; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h index 89ac8e6707b8..c5ec63a25a42 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h @@ -66,6 +66,7 @@ enum offs_rev { AGG_ACR0, AGG_ACR4, AGG_MRCR, + AGG_ATCR0, AGG_ATCR1, AGG_ATCR3, LPON_UTTR0, @@ -254,6 +255,9 @@ enum offs_rev { #define MT_WTBLOFF_TOP_RSCR_RCPI_MODE GENMASK(31, 30) #define MT_WTBLOFF_TOP_RSCR_RCPI_PARAM GENMASK(25, 24) +#define MT_WTBLOFF_TOP_ACR(_band) MT_WTBLOFF_TOP(_band, 0x010) +#define MT_WTBLOFF_TOP_ADM_BACKOFFTIME BIT(29) + /* ETBF: band 0(0x820ea000), band 1(0x820fa000) */ #define MT_WF_ETBF_BASE(_band) ((_band) ? 0x820fa000 : 0x820ea000) #define MT_WF_ETBF(_band, ofs) (MT_WF_ETBF_BASE(_band) + (ofs)) @@ -505,6 +509,9 @@ enum offs_rev { #define MT_AGG_MRCR_RTS_FAIL_LIMIT GENMASK(11, 7) #define MT_AGG_MRCR_TXCMD_RTS_FAIL_LIMIT GENMASK(28, 24) +#define MT_AGG_ATCR0(_band) MT_WF_AGG(_band, __OFFS(AGG_ATCR0)) +#define MT_AGG_ATCR_MAC_BFF_TIME_EN BIT(30) + #define MT_AGG_ATCR1(_band) MT_WF_AGG(_band, __OFFS(AGG_ATCR1)) #define MT_AGG_ATCR3(_band) MT_WF_AGG(_band, __OFFS(AGG_ATCR3)) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c index d1d64fa7d35d..14e17dc90256 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c @@ -137,6 +137,13 @@ mt7921_regd_notifier(struct wiphy *wiphy, dev->mt76.region = request->dfs_region; dev->country_ie_env = request->country_ie_env; + if (request->initiator == NL80211_REGDOM_SET_BY_USER) { + if (dev->mt76.alpha2[0] == '0' && dev->mt76.alpha2[1] == '0') + wiphy->regulatory_flags &= ~REGULATORY_COUNTRY_IE_IGNORE; + else + wiphy->regulatory_flags |= REGULATORY_COUNTRY_IE_IGNORE; + } + if (pm->suspended) return; @@ -227,6 +234,7 @@ static void mt7921_init_work(struct work_struct *work) mt76_set_stream_caps(&dev->mphy, true); mt7921_set_stream_he_caps(&dev->phy); + mt792x_config_mac_addr_list(dev); ret = mt76_register_device(&dev->mt76, true, mt76_rates, ARRAY_SIZE(mt76_rates)); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c index 047106b65d2b..5dd57de59f27 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c @@ -216,11 +216,7 @@ mt7921_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb) if (status->wcid) { mlink = container_of(status->wcid, struct mt792x_link_sta, wcid); msta = container_of(mlink, struct mt792x_sta, deflink); - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&mlink->wcid.poll_list)) - list_add_tail(&mlink->wcid.poll_list, - &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &mlink->wcid); } mt792x_get_status_freq_info(status, chfreq); @@ -479,10 +475,7 @@ void mt7921_mac_add_txs(struct mt792x_dev *dev, void *data) if (!wcid->sta) goto out; - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&mlink->wcid.poll_list)) - list_add_tail(&mlink->wcid.poll_list, &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &mlink->wcid); out: rcu_read_unlock(); @@ -529,11 +522,7 @@ static void mt7921_mac_tx_free(struct mt792x_dev *dev, void *data, int len) continue; mlink = container_of(wcid, struct mt792x_link_sta, wcid); - spin_lock_bh(&mdev->sta_poll_lock); - if (list_empty(&mlink->wcid.poll_list)) - list_add_tail(&mlink->wcid.poll_list, - &mdev->sta_poll_list); - spin_unlock_bh(&mdev->sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &mlink->wcid); continue; } @@ -647,6 +636,7 @@ mt7921_vif_connect_iter(void *priv, u8 *mac, ieee80211_disconnect(vif, true); mt76_connac_mcu_uni_add_dev(&dev->mphy, &vif->bss_conf, + &mvif->bss_conf.mt76, &mvif->sta.deflink.wcid, true); mt7921_mcu_set_tx(dev, vif); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index a7f5bfbc02ed..13e58c328aff 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -147,7 +147,7 @@ mt7921_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band, memset(he_cap->ppe_thres, 0, sizeof(he_cap->ppe_thres)); if (he_cap_elem->phy_cap_info[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { - mt76_connac_gen_ppe_thresh(he_cap->ppe_thres, nss); + mt76_connac_gen_ppe_thresh(he_cap->ppe_thres, nss, band); } else { he_cap_elem->phy_cap_info[9] |= u8_encode_bits(IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US, @@ -252,6 +252,11 @@ int __mt7921_start(struct mt792x_phy *phy) return err; } + if (phy->chip_cap & MT792x_CHIP_CAP_WF_RF_PIN_CTRL_EVT_EN) { + mt7921_mcu_wf_rf_pin_ctrl(phy, WF_RF_PIN_INIT); + wiphy_rfkill_start_polling(mphy->hw->wiphy); + } + return 0; } EXPORT_SYMBOL_GPL(__mt7921_start); @@ -308,6 +313,7 @@ mt7921_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) mvif->bss_conf.mt76.wmm_idx = mvif->bss_conf.mt76.idx % MT76_CONNAC_MAX_WMM_SETS; ret = mt76_connac_mcu_uni_add_dev(&dev->mphy, &vif->bss_conf, + &mvif->bss_conf.mt76, &mvif->sta.deflink.wcid, true); if (ret) goto out; @@ -319,10 +325,8 @@ mt7921_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) INIT_LIST_HEAD(&mvif->sta.deflink.wcid.poll_list); mvif->sta.deflink.wcid.idx = idx; - mvif->sta.deflink.wcid.phy_idx = mvif->bss_conf.mt76.band_idx; - mvif->sta.deflink.wcid.hw_key_idx = -1; mvif->sta.deflink.wcid.tx_info |= MT_WCID_TX_INFO_SET; - mt76_wcid_init(&mvif->sta.deflink.wcid); + mt76_wcid_init(&mvif->sta.deflink.wcid, mvif->bss_conf.mt76.band_idx); mt7921_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); @@ -338,6 +342,9 @@ mt7921_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER; if (phy->chip_cap & MT792x_CHIP_CAP_RSSI_NOTIFY_EVT_EN) vif->driver_flags |= IEEE80211_VIF_SUPPORTS_CQM_RSSI; + + INIT_WORK(&mvif->csa_work, mt7921_csa_work); + timer_setup(&mvif->csa_timer, mt792x_csa_timer, 0); out: mt792x_mutex_release(dev); @@ -360,9 +367,9 @@ void mt7921_roc_abort_sync(struct mt792x_dev *dev) del_timer_sync(&phy->roc_timer); cancel_work_sync(&phy->roc_work); if (test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state)) - ieee80211_iterate_active_interfaces(mt76_hw(dev), - IEEE80211_IFACE_ITER_RESUME_ALL, - mt7921_roc_iter, (void *)phy); + ieee80211_iterate_interfaces(mt76_hw(dev), + IEEE80211_IFACE_ITER_RESUME_ALL, + mt7921_roc_iter, (void *)phy); } EXPORT_SYMBOL_GPL(mt7921_roc_abort_sync); @@ -531,7 +538,13 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, } else { if (idx == *wcid_keyidx) *wcid_keyidx = -1; - goto out; + + /* For security issue we don't trigger the key deletion when + * reassociating. But we should trigger the deletion process + * to avoid using incorrect cipher after disconnection, + */ + if (vif->type != NL80211_IFTYPE_STATION || vif->cfg.assoc) + goto out; } mt76_wcid_key_setup(&dev->mt76, wcid, key); @@ -858,6 +871,7 @@ void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76); struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv; + mt7921_roc_abort_sync(dev); mt76_connac_free_pending_tx_skbs(&dev->pm, &msta->deflink.wcid); mt76_connac_pm_wake(&dev->mphy, &dev->pm); @@ -1334,6 +1348,9 @@ static int mt7921_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { + struct mt792x_dev *dev = mt792x_hw_dev(hw); + + dev->new_ctx = ctx; return 0; } @@ -1341,6 +1358,10 @@ static void mt7921_remove_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { + struct mt792x_dev *dev = mt792x_hw_dev(hw); + + if (dev->new_ctx == ctx) + dev->new_ctx = NULL; } static void @@ -1391,6 +1412,101 @@ static void mt7921_mgd_complete_tx(struct ieee80211_hw *hw, mt7921_abort_roc(mvif->phy, mvif); } +static int mt7921_switch_vif_chanctx(struct ieee80211_hw *hw, + struct ieee80211_vif_chanctx_switch *vifs, + int n_vifs, + enum ieee80211_chanctx_switch_mode mode) +{ + return mt792x_assign_vif_chanctx(hw, vifs->vif, vifs->link_conf, + vifs->new_ctx); +} + +void mt7921_csa_work(struct work_struct *work) +{ + struct mt792x_vif *mvif; + struct mt792x_dev *dev; + struct ieee80211_vif *vif; + int ret; + + mvif = (struct mt792x_vif *)container_of(work, struct mt792x_vif, + csa_work); + dev = mvif->phy->dev; + vif = container_of((void *)mvif, struct ieee80211_vif, drv_priv); + + mt792x_mutex_acquire(dev); + ret = mt76_connac_mcu_uni_set_chctx(mvif->phy->mt76, &mvif->bss_conf.mt76, + dev->new_ctx); + mt792x_mutex_release(dev); + + ieee80211_chswitch_done(vif, !ret, 0); +} + +static int mt7921_pre_channel_switch(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_channel_switch *chsw) +{ + if (vif->type != NL80211_IFTYPE_STATION || !vif->cfg.assoc) + return -EOPNOTSUPP; + + /* Avoid beacon loss due to the CAC(Channel Availability Check) time + * of the AP. + */ + if (!cfg80211_chandef_usable(hw->wiphy, &chsw->chandef, + IEEE80211_CHAN_RADAR)) + return -EOPNOTSUPP; + + return 0; +} + +static void mt7921_channel_switch(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_channel_switch *chsw) +{ + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + u16 beacon_interval = vif->bss_conf.beacon_int; + + mvif->csa_timer.expires = TU_TO_EXP_TIME(beacon_interval * chsw->count); + add_timer(&mvif->csa_timer); +} + +static void mt7921_abort_channel_switch(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf) +{ + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + + del_timer_sync(&mvif->csa_timer); + cancel_work_sync(&mvif->csa_work); +} + +static void mt7921_channel_switch_rx_beacon(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_channel_switch *chsw) +{ + struct mt792x_dev *dev = mt792x_hw_dev(hw); + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + u16 beacon_interval = vif->bss_conf.beacon_int; + + if (cfg80211_chandef_identical(&chsw->chandef, + &dev->new_ctx->def) && + chsw->count) { + mod_timer(&mvif->csa_timer, + TU_TO_EXP_TIME(beacon_interval * chsw->count)); + } +} + +static void mt7921_rfkill_poll(struct ieee80211_hw *hw) +{ + struct mt792x_phy *phy = mt792x_hw_phy(hw); + int ret = 0; + + mt792x_mutex_acquire(phy->dev); + ret = mt7921_mcu_wf_rf_pin_ctrl(phy, WF_RF_PIN_POLL); + mt792x_mutex_release(phy->dev); + + wiphy_rfkill_set_hw_state(hw->wiphy, ret ? false : true); +} + const struct ieee80211_ops mt7921_ops = { .tx = mt792x_tx, .start = mt7921_start, @@ -1441,6 +1557,7 @@ const struct ieee80211_ops mt7921_ops = { #endif /* CONFIG_PM */ .flush = mt792x_flush, .set_sar_specs = mt7921_set_sar_specs, + .rfkill_poll = mt7921_rfkill_poll, .remain_on_channel = mt7921_remain_on_channel, .cancel_remain_on_channel = mt7921_cancel_remain_on_channel, .add_chanctx = mt7921_add_chanctx, @@ -1450,6 +1567,11 @@ const struct ieee80211_ops mt7921_ops = { .unassign_vif_chanctx = mt792x_unassign_vif_chanctx, .mgd_prepare_tx = mt7921_mgd_prepare_tx, .mgd_complete_tx = mt7921_mgd_complete_tx, + .switch_vif_chanctx = mt7921_switch_vif_chanctx, + .pre_channel_switch = mt7921_pre_channel_switch, + .channel_switch = mt7921_channel_switch, + .abort_channel_switch = mt7921_abort_channel_switch, + .channel_switch_rx_beacon = mt7921_channel_switch_rx_beacon, }; EXPORT_SYMBOL_GPL(mt7921_ops); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index 02c1de8620a7..86bd33b916a9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -61,6 +61,12 @@ int mt7921_mcu_parse_response(struct mt76_dev *mdev, int cmd, skb_pull(skb, sizeof(*rxd)); event = (struct mt76_connac_mcu_reg_event *)skb->data; ret = (int)le32_to_cpu(event->val); + } else if (cmd == MCU_EXT_CMD(WF_RF_PIN_CTRL)) { + struct mt7921_wf_rf_pin_ctrl_event *event; + + skb_pull(skb, sizeof(*rxd)); + event = (struct mt7921_wf_rf_pin_ctrl_event *)skb->data; + ret = (int)event->result; } else { skb_pull(skb, sizeof(struct mt76_connac2_mcu_rxd)); } @@ -174,7 +180,7 @@ static void mt7921_mcu_connection_loss_iter(void *priv, u8 *mac, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt76_connac_beacon_loss_event *event = priv; if (mvif->idx != event->bss_idx) @@ -507,7 +513,10 @@ static void mt7921_mcu_parse_tx_resource(struct mt76_dev *dev, tx_res = (struct mt7921_tx_resource *)skb->data; sdio->sched.pse_data_quota = le32_to_cpu(tx_res->pse_data_quota); - sdio->sched.pse_mcu_quota = le32_to_cpu(tx_res->pse_mcu_quota); + sdio->pse_mcu_quota_max = le32_to_cpu(tx_res->pse_mcu_quota); + /* The mcu quota usage of this function itself must be taken into consideration */ + sdio->sched.pse_mcu_quota = + sdio->sched.pse_mcu_quota ? sdio->pse_mcu_quota_max : sdio->pse_mcu_quota_max - 1; sdio->sched.ple_data_quota = le32_to_cpu(tx_res->ple_data_quota); sdio->sched.pse_page_size = le16_to_cpu(tx_res->pse_page_size); sdio->sched.deficit = tx_res->pp_padding; @@ -1122,7 +1131,7 @@ int mt7921_get_txpwr_info(struct mt792x_dev *dev, struct mt7921_txpwr *txpwr) int mt7921_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif, bool enable) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct { struct { u8 band_idx; @@ -1424,6 +1433,21 @@ int mt7921_mcu_get_temperature(struct mt792x_phy *phy) sizeof(req), true); } +int mt7921_mcu_wf_rf_pin_ctrl(struct mt792x_phy *phy, u8 action) +{ + struct mt792x_dev *dev = phy->dev; + struct { + u8 action; + u8 value; + } req = { + .action = action, + .value = 0, + }; + + return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(WF_RF_PIN_CTRL), &req, + sizeof(req), action ? true : false); +} + int mt7921_mcu_set_rxfilter(struct mt792x_dev *dev, u32 fif, u8 bit_op, u32 bit_map) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.h index f9a259ee6b82..2834c6c53e58 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.h @@ -74,6 +74,11 @@ struct mt7921_txpwr_event { struct mt7921_txpwr txpwr; } __packed; +struct mt7921_wf_rf_pin_ctrl_event { + u8 result; + u8 value; +} __packed; + enum { TM_SWITCH_MODE, TM_SET_AT_CMD, diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h index 16c89815c0b8..c88793fcec64 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h @@ -31,6 +31,9 @@ #define EXT_CMD_RADIO_ON_LED 0x2 #define EXT_CMD_RADIO_OFF_LED 0x3 +#define WF_RF_PIN_INIT 0x0 +#define WF_RF_PIN_POLL 0x1 + enum { UNI_ROC_ACQUIRE, UNI_ROC_ABORT, @@ -202,6 +205,7 @@ void mt7921_mcu_rx_event(struct mt792x_dev *dev, struct sk_buff *skb); int mt7921_mcu_set_rxfilter(struct mt792x_dev *dev, u32 fif, u8 bit_op, u32 bit_map); int mt7921_mcu_radio_led_ctrl(struct mt792x_dev *dev, u8 value); +int mt7921_mcu_wf_rf_pin_ctrl(struct mt792x_phy *phy, u8 action); static inline u32 mt7921_reg_map_l1(struct mt792x_dev *dev, u32 addr) @@ -273,6 +277,7 @@ int mt7921_mcu_uni_rx_ba(struct mt792x_dev *dev, bool enable); void mt7921_scan_work(struct work_struct *work); void mt7921_roc_work(struct work_struct *work); +void mt7921_csa_work(struct work_struct *work); int mt7921_mcu_uni_bss_ps(struct mt792x_dev *dev, struct ieee80211_vif *vif); void mt7921_coredump_work(struct work_struct *work); int mt7921_get_txpwr_info(struct mt792x_dev *dev, struct mt7921_txpwr *txpwr); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index 67723c22aea6..a0c9df3c2cc7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -42,6 +42,10 @@ static void mt7921e_unregister_device(struct mt792x_dev *dev) { int i; struct mt76_connac_pm *pm = &dev->pm; + struct ieee80211_hw *hw = mt76_hw(dev); + + if (dev->phy.chip_cap & MT792x_CHIP_CAP_WF_RF_PIN_CTRL_EVT_EN) + wiphy_rfkill_stop_polling(hw->wiphy); cancel_work_sync(&dev->init_work); mt76_unregister_device(&dev->mt76); @@ -435,7 +439,7 @@ static int mt7921_pci_suspend(struct device *device) if (err < 0) goto restore_suspend; - err = mt76_connac_mcu_set_hif_suspend(mdev, true); + err = mt76_connac_mcu_set_hif_suspend(mdev, true, true); if (err) goto restore_suspend; @@ -481,7 +485,7 @@ restore_napi: if (!pm->ds_enable) mt76_connac_mcu_set_deep_sleep(&dev->mt76, false); - mt76_connac_mcu_set_hif_suspend(mdev, false); + mt76_connac_mcu_set_hif_suspend(mdev, false, true); restore_suspend: pm->suspended = false; @@ -519,12 +523,15 @@ static int mt7921_pci_resume(struct device *device) mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { napi_enable(&mdev->napi[i]); - napi_schedule(&mdev->napi[i]); } napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + napi_schedule(&mdev->napi[i]); + } napi_schedule(&mdev->tx_napi); local_bh_enable(); @@ -532,7 +539,7 @@ static int mt7921_pci_resume(struct device *device) if (!pm->ds_enable) mt76_connac_mcu_set_deep_sleep(&dev->mt76, false); - err = mt76_connac_mcu_set_hif_suspend(mdev, false); + err = mt76_connac_mcu_set_hif_suspend(mdev, false, true); if (err < 0) goto failed; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c index 2452b1a2d118..881812ba03ff 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c @@ -81,9 +81,12 @@ int mt7921e_mac_reset(struct mt792x_dev *dev) mt792x_wpdma_reset(dev, true); - local_bh_disable(); mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); + } + + local_bh_disable(); + mt76_for_each_q_rx(&dev->mt76, i) { napi_schedule(&dev->mt76.napi[i]); } local_bh_enable(); @@ -115,8 +118,8 @@ int mt7921e_mac_reset(struct mt792x_dev *dev) err = __mt7921_start(&dev->phy); out: - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c index 95f526f7bb99..45b9f35aab17 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c @@ -240,7 +240,7 @@ static int mt7921s_suspend(struct device *__dev) mt76s_txqs_empty(&dev->mt76), 5 * HZ); /* It is supposed that SDIO bus is idle at the point */ - err = mt76_connac_mcu_set_hif_suspend(mdev, true); + err = mt76_connac_mcu_set_hif_suspend(mdev, true, true); if (err) goto restore_worker; @@ -258,7 +258,7 @@ static int mt7921s_suspend(struct device *__dev) restore_txrx_worker: mt76_worker_enable(&mdev->sdio.net_worker); mt76_worker_enable(&mdev->sdio.txrx_worker); - mt76_connac_mcu_set_hif_suspend(mdev, false); + mt76_connac_mcu_set_hif_suspend(mdev, false, true); restore_worker: mt76_worker_enable(&mdev->tx_worker); @@ -302,7 +302,7 @@ static int mt7921s_resume(struct device *__dev) if (!pm->ds_enable) mt76_connac_mcu_set_deep_sleep(mdev, false); - err = mt76_connac_mcu_set_hif_suspend(mdev, false); + err = mt76_connac_mcu_set_hif_suspend(mdev, false, true); failed: pm->suspended = false; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c index 8aa4f0203208..fe9751851ff7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c @@ -21,6 +21,9 @@ static const struct usb_device_id mt7921u_device_table[] = { /* Netgear, Inc. [A8000,AXE3000] */ { USB_DEVICE_AND_INTERFACE_INFO(0x0846, 0x9060, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)MT7921_FIRMWARE_WM }, + /* TP-Link TXE50UH */ + { USB_DEVICE_AND_INTERFACE_INFO(0x35bc, 0x0107, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)MT7921_FIRMWARE_WM }, { }, }; @@ -257,7 +260,7 @@ static int mt7921u_suspend(struct usb_interface *intf, pm_message_t state) pm->suspended = true; flush_work(&dev->reset_work); - err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, true); + err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, true, true); if (err) goto failed; @@ -307,7 +310,7 @@ static int mt7921u_resume(struct usb_interface *intf) if (err < 0) goto failed; - err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, false); + err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, false, true); failed: pm->suspended = false; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c index 039949b344b9..f41ca4248497 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c @@ -57,6 +57,22 @@ static int mt7925_thermal_init(struct mt792x_phy *phy) mt7925_hwmon_groups); return PTR_ERR_OR_ZERO(hwmon); } + +void mt7925_regd_update(struct mt792x_dev *dev) +{ + struct mt76_dev *mdev = &dev->mt76; + struct ieee80211_hw *hw = mdev->hw; + + if (!dev->regd_change) + return; + + mt7925_mcu_set_clc(dev, mdev->alpha2, dev->country_ie_env); + mt7925_mcu_set_channel_domain(hw->priv); + mt7925_set_tx_sar_pwr(hw, NULL); + dev->regd_change = false; +} +EXPORT_SYMBOL_GPL(mt7925_regd_update); + static void mt7925_regd_notifier(struct wiphy *wiphy, struct regulatory_request *req) @@ -64,6 +80,7 @@ mt7925_regd_notifier(struct wiphy *wiphy, struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy); struct mt792x_dev *dev = mt792x_hw_dev(hw); struct mt76_dev *mdev = &dev->mt76; + struct mt76_connac_pm *pm = &dev->pm; /* allow world regdom at the first boot only */ if (!memcmp(req->alpha2, "00", 2) && @@ -78,12 +95,17 @@ mt7925_regd_notifier(struct wiphy *wiphy, memcpy(mdev->alpha2, req->alpha2, 2); mdev->region = req->dfs_region; dev->country_ie_env = req->country_ie_env; + dev->regd_change = true; + if (pm->suspended) + return; + + dev->regd_in_progress = true; mt792x_mutex_acquire(dev); - mt7925_mcu_set_clc(dev, req->alpha2, req->country_ie_env); - mt7925_mcu_set_channel_domain(hw->priv); - mt7925_set_tx_sar_pwr(hw, NULL); + mt7925_regd_update(dev); mt792x_mutex_release(dev); + dev->regd_in_progress = false; + wake_up(&dev->wait); } static void mt7925_mac_init_basic_rates(struct mt792x_dev *dev) @@ -178,6 +200,7 @@ static void mt7925_init_work(struct work_struct *work) mt76_set_stream_caps(&dev->mphy, true); mt7925_set_stream_he_eht_caps(&dev->phy); + mt792x_config_mac_addr_list(dev); ret = mt7925_init_mlo_caps(&dev->phy); if (ret) { @@ -225,6 +248,7 @@ int mt7925_register_device(struct mt792x_dev *dev) spin_lock_init(&dev->pm.wake.lock); mutex_init(&dev->pm.mutex); init_waitqueue_head(&dev->pm.wait); + init_waitqueue_head(&dev->wait); spin_lock_init(&dev->pm.txq_lock); INIT_DELAYED_WORK(&dev->mphy.mac_work, mt792x_mac_work); INIT_DELAYED_WORK(&dev->phy.scan_work, mt7925_scan_work); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index 634c42bbf23f..c871d2f9688b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -49,7 +49,7 @@ static void mt7925_mac_sta_poll(struct mt792x_dev *dev) break; mlink = list_first_entry(&sta_poll_list, struct mt792x_link_sta, wcid.poll_list); - msta = container_of(mlink, struct mt792x_sta, deflink); + msta = mlink->sta; spin_lock_bh(&dev->mt76.sta_poll_lock); list_del_init(&mlink->wcid.poll_list); spin_unlock_bh(&dev->mt76.sta_poll_lock); @@ -395,11 +395,7 @@ mt7925_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb) if (status->wcid) { mlink = container_of(status->wcid, struct mt792x_link_sta, wcid); - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&mlink->wcid.poll_list)) - list_add_tail(&mlink->wcid.poll_list, - &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &mlink->wcid); } mt792x_get_status_freq_info(status, chfreq); @@ -734,7 +730,7 @@ mt7925_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, u8 p_fmt, q_idx, omac_idx = 0, wmm_idx = 0, band_idx = 0; u32 val, sz_txd = mt76_is_mmio(dev) ? MT_TXD_SIZE : MT_SDIO_TXD_SIZE; bool is_8023 = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP; - struct mt76_vif *mvif; + struct mt76_vif_link *mvif; bool beacon = !!(changed & (BSS_CHANGED_BEACON | BSS_CHANGED_BEACON_ENABLED)); bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP | @@ -743,7 +739,7 @@ mt7925_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, mconf = vif ? mt792x_vif_to_link((struct mt792x_vif *)vif->drv_priv, wcid->link_id) : NULL; - mvif = mconf ? (struct mt76_vif *)&mconf->mt76 : NULL; + mvif = mconf ? (struct mt76_vif_link *)&mconf->mt76 : NULL; if (mvif) { omac_idx = mvif->omac_idx; @@ -1054,10 +1050,7 @@ void mt7925_mac_add_txs(struct mt792x_dev *dev, void *data) if (!wcid->sta) goto out; - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&mlink->wcid.poll_list)) - list_add_tail(&mlink->wcid.poll_list, &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &mlink->wcid); out: rcu_read_unlock(); @@ -1135,11 +1128,7 @@ mt7925_mac_tx_free(struct mt792x_dev *dev, void *data, int len) continue; mlink = container_of(wcid, struct mt792x_link_sta, wcid); - spin_lock_bh(&mdev->sta_poll_lock); - if (list_empty(&mlink->wcid.poll_list)) - list_add_tail(&mlink->wcid.poll_list, - &mdev->sta_poll_list); - spin_unlock_bh(&mdev->sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &mlink->wcid); continue; } @@ -1271,6 +1260,7 @@ mt7925_vif_connect_iter(void *priv, u8 *mac, struct mt792x_dev *dev = mvif->phy->dev; struct ieee80211_hw *hw = mt76_hw(dev); struct ieee80211_bss_conf *bss_conf; + struct mt792x_bss_conf *mconf; int i; if (vif->type == NL80211_IFTYPE_STATION) @@ -1278,8 +1268,9 @@ mt7925_vif_connect_iter(void *priv, u8 *mac, for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) { bss_conf = mt792x_vif_to_bss_conf(vif, i); + mconf = mt792x_vif_to_link(mvif, i); - mt76_connac_mcu_uni_add_dev(&dev->mphy, bss_conf, + mt76_connac_mcu_uni_add_dev(&dev->mphy, bss_conf, &mconf->mt76, &mvif->sta.deflink.wcid, true); mt7925_mcu_set_tx(dev, bss_conf); } @@ -1309,6 +1300,7 @@ void mt7925_mac_reset_work(struct work_struct *work) cancel_delayed_work_sync(&dev->mphy.mac_work); cancel_delayed_work_sync(&pm->ps_work); cancel_work_sync(&pm->wake_work); + dev->sar_inited = false; for (i = 0; i < 10; i++) { mutex_lock(&dev->mt76.mutex); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index 791c8b00e112..98daf80ac131 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -130,7 +130,7 @@ mt7925_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band, if (he_cap_elem->phy_cap_info[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { - mt76_connac_gen_ppe_thresh(he_cap->ppe_thres, nss); + mt76_connac_gen_ppe_thresh(he_cap->ppe_thres, nss, band); } else { he_cap_elem->phy_cap_info[9] |= u8_encode_bits(IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US, @@ -310,6 +310,7 @@ void mt7925_set_stream_he_eht_caps(struct mt792x_phy *phy) int __mt7925_start(struct mt792x_phy *phy) { struct mt76_phy *mphy = phy->mt76; + struct mt792x_dev *dev = phy->dev; int err; err = mt7925_mcu_set_channel_domain(mphy); @@ -320,9 +321,12 @@ int __mt7925_start(struct mt792x_phy *phy) if (err) return err; - err = mt7925_set_tx_sar_pwr(mphy->hw, NULL); - if (err) - return err; + if (!dev->sar_inited) { + err = mt7925_set_tx_sar_pwr(mphy->hw, NULL); + if (err) + return err; + dev->sar_inited = true; + } mt792x_mac_reset_counters(phy); set_bit(MT76_STATE_RUNNING, &mphy->state); @@ -365,29 +369,22 @@ static int mt7925_mac_link_bss_add(struct mt792x_dev *dev, mconf->mt76.omac_idx = ieee80211_vif_is_mld(vif) ? 0 : mconf->mt76.idx; mconf->mt76.band_idx = 0xff; - mconf->mt76.wmm_idx = mconf->mt76.idx % MT76_CONNAC_MAX_WMM_SETS; + mconf->mt76.wmm_idx = ieee80211_vif_is_mld(vif) ? + 0 : mconf->mt76.idx % MT76_CONNAC_MAX_WMM_SETS; if (mvif->phy->mt76->chandef.chan->band != NL80211_BAND_2GHZ) mconf->mt76.basic_rates_idx = MT792x_BASIC_RATES_TBL + 4; else mconf->mt76.basic_rates_idx = MT792x_BASIC_RATES_TBL; - ret = mt76_connac_mcu_uni_add_dev(&dev->mphy, link_conf, - &mlink->wcid, true); - if (ret) - goto out; - dev->mt76.vif_mask |= BIT_ULL(mconf->mt76.idx); mvif->phy->omac_mask |= BIT_ULL(mconf->mt76.omac_idx); idx = MT792x_WTBL_RESERVED - mconf->mt76.idx; - INIT_LIST_HEAD(&mlink->wcid.poll_list); mlink->wcid.idx = idx; - mlink->wcid.phy_idx = mconf->mt76.band_idx; - mlink->wcid.hw_key_idx = -1; mlink->wcid.tx_info |= MT_WCID_TX_INFO_SET; - mt76_wcid_init(&mlink->wcid); + mt76_wcid_init(&mlink->wcid, 0); mt7925_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); @@ -395,6 +392,12 @@ static int mt7925_mac_link_bss_add(struct mt792x_dev *dev, ewma_rssi_init(&mconf->rssi); rcu_assign_pointer(dev->mt76.wcid[idx], &mlink->wcid); + + ret = mt76_connac_mcu_uni_add_dev(&dev->mphy, link_conf, &mconf->mt76, + &mlink->wcid, true); + if (ret) + goto out; + if (vif->txq) { mtxq = (struct mt76_txq *)vif->txq->drv_priv; mtxq->wcid = idx; @@ -801,12 +804,12 @@ static u8 mt7925_get_rates_table(struct ieee80211_hw *hw, struct ieee80211_vif *vif, bool beacon, bool mcast) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt76_phy *mphy = hw->priv; u16 rate; u8 i, idx, ht; - rate = mt76_connac2_mac_tx_rate_val(mphy, vif, beacon, mcast); + rate = mt76_connac2_mac_tx_rate_val(mphy, &vif->bss_conf, beacon, mcast); ht = FIELD_GET(MT_TX_RATE_MODE, rate) > MT_PHY_TYPE_OFDM; if (beacon && ht) { @@ -837,6 +840,7 @@ static int mt7925_mac_link_sta_add(struct mt76_dev *mdev, u8 link_id = link_sta->link_id; struct mt792x_link_sta *mlink; struct mt792x_sta *msta; + struct mt76_wcid *wcid; int ret, idx; msta = (struct mt792x_sta *)link_sta->sta->drv_priv; @@ -847,14 +851,22 @@ static int mt7925_mac_link_sta_add(struct mt76_dev *mdev, return -ENOSPC; mconf = mt792x_vif_to_link(mvif, link_id); - INIT_LIST_HEAD(&mlink->wcid.poll_list); + mt76_wcid_init(&mlink->wcid, 0); mlink->wcid.sta = 1; mlink->wcid.idx = idx; - mlink->wcid.phy_idx = mconf->mt76.band_idx; mlink->wcid.tx_info |= MT_WCID_TX_INFO_SET; mlink->last_txs = jiffies; mlink->wcid.link_id = link_sta->link_id; mlink->wcid.link_valid = !!link_sta->sta->valid_links; + mlink->sta = msta; + + wcid = &mlink->wcid; + ewma_signal_init(&wcid->rssi); + rcu_assign_pointer(dev->mt76.wcid[wcid->idx], wcid); + mt76_wcid_init(wcid, 0); + ewma_avg_signal_init(&mlink->avg_ack_signal); + memset(mlink->airtime_ac, 0, + sizeof(msta->deflink.airtime_ac)); ret = mt76_connac_pm_wake(&dev->mphy, &dev->pm); if (ret) @@ -866,9 +878,14 @@ static int mt7925_mac_link_sta_add(struct mt76_dev *mdev, link_conf = mt792x_vif_to_bss_conf(vif, link_id); /* should update bss info before STA add */ - if (vif->type == NL80211_IFTYPE_STATION && !link_sta->sta->tdls) - mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx, - link_conf, link_sta, false); + if (vif->type == NL80211_IFTYPE_STATION && !link_sta->sta->tdls) { + if (ieee80211_vif_is_mld(vif)) + mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx, + link_conf, link_sta, link_sta != mlink->pri_link); + else + mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx, + link_conf, link_sta, false); + } if (ieee80211_vif_is_mld(vif) && link_sta == mlink->pri_link) { @@ -904,7 +921,6 @@ mt7925_mac_sta_add_links(struct mt792x_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta, unsigned long new_links) { struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv; - struct mt76_wcid *wcid; unsigned int link_id; int err = 0; @@ -921,14 +937,6 @@ mt7925_mac_sta_add_links(struct mt792x_dev *dev, struct ieee80211_vif *vif, err = -ENOMEM; break; } - - wcid = &mlink->wcid; - ewma_signal_init(&wcid->rssi); - rcu_assign_pointer(dev->mt76.wcid[wcid->idx], wcid); - mt76_wcid_init(wcid); - ewma_avg_signal_init(&mlink->avg_ack_signal); - memset(mlink->airtime_ac, 0, - sizeof(msta->deflink.airtime_ac)); } msta->valid_links |= BIT(link_id); @@ -1141,8 +1149,7 @@ static void mt7925_mac_link_sta_remove(struct mt76_dev *mdev, struct mt792x_bss_conf *mconf; mconf = mt792x_link_conf_to_mconf(link_conf); - mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx, link_conf, - link_sta, false); + mt792x_mac_link_bss_remove(dev, mconf, mlink); } spin_lock_bh(&mdev->sta_poll_lock); @@ -1185,7 +1192,6 @@ mt7925_mac_sta_remove_links(struct mt792x_dev *dev, struct ieee80211_vif *vif, if (link_sta != mlink->pri_link) { mt76_wcid_cleanup(mdev, wcid); mt76_wcid_mask_clear(mdev->wcid_mask, wcid->idx); - mt76_wcid_mask_clear(mdev->wcid_phy_mask, wcid->idx); } if (msta->deflink_id == link_id) @@ -1200,12 +1206,45 @@ void mt7925_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, { struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76); struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv; + struct { + struct { + u8 omac_idx; + u8 band_idx; + __le16 pad; + } __packed hdr; + struct req_tlv { + __le16 tag; + __le16 len; + u8 active; + u8 link_idx; /* hw link idx */ + u8 omac_addr[ETH_ALEN]; + } __packed tlv; + } dev_req = { + .hdr = { + .omac_idx = 0, + .band_idx = 0, + }, + .tlv = { + .tag = cpu_to_le16(DEV_INFO_ACTIVE), + .len = cpu_to_le16(sizeof(struct req_tlv)), + .active = true, + }, + }; unsigned long rem; rem = ieee80211_vif_is_mld(vif) ? msta->valid_links : BIT(0); mt7925_mac_sta_remove_links(dev, vif, sta, rem); + if (ieee80211_vif_is_mld(vif)) { + mt7925_mcu_set_dbdc(&dev->mphy, false); + + /* recovery omac address for the legacy interface */ + memcpy(dev_req.tlv.omac_addr, vif->addr, ETH_ALEN); + mt76_mcu_send_msg(mdev, MCU_UNI_CMD(DEV_INFO_UPDATE), + &dev_req, sizeof(dev_req), true); + } + if (vif->type == NL80211_IFTYPE_STATION) { struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; @@ -1250,22 +1289,22 @@ mt7925_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, case IEEE80211_AMPDU_RX_START: mt76_rx_aggr_start(&dev->mt76, &msta->deflink.wcid, tid, ssn, params->buf_size); - mt7925_mcu_uni_rx_ba(dev, params, true); + mt7925_mcu_uni_rx_ba(dev, vif, params, true); break; case IEEE80211_AMPDU_RX_STOP: mt76_rx_aggr_stop(&dev->mt76, &msta->deflink.wcid, tid); - mt7925_mcu_uni_rx_ba(dev, params, false); + mt7925_mcu_uni_rx_ba(dev, vif, params, false); break; case IEEE80211_AMPDU_TX_OPERATIONAL: mtxq->aggr = true; mtxq->send_bar = false; - mt7925_mcu_uni_tx_ba(dev, params, true); + mt7925_mcu_uni_tx_ba(dev, vif, params, true); break; case IEEE80211_AMPDU_TX_STOP_FLUSH: case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT: mtxq->aggr = false; clear_bit(tid, &msta->deflink.wcid.ampdu_state); - mt7925_mcu_uni_tx_ba(dev, params, false); + mt7925_mcu_uni_tx_ba(dev, vif, params, false); break; case IEEE80211_AMPDU_TX_START: set_bit(tid, &msta->deflink.wcid.ampdu_state); @@ -1274,7 +1313,7 @@ mt7925_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, case IEEE80211_AMPDU_TX_STOP_CONT: mtxq->aggr = false; clear_bit(tid, &msta->deflink.wcid.ampdu_state); - mt7925_mcu_uni_tx_ba(dev, params, false); + mt7925_mcu_uni_tx_ba(dev, vif, params, false); ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid); break; } @@ -1895,6 +1934,13 @@ static void mt7925_link_info_changed(struct ieee80211_hw *hw, if (changed & (BSS_CHANGED_QOS | BSS_CHANGED_BEACON_ENABLED)) mt7925_mcu_set_tx(dev, info); + if (changed & BSS_CHANGED_BSSID) { + if (ieee80211_vif_is_mld(vif) && + hweight16(mvif->valid_links) == 2) + /* Indicate the secondary setup done */ + mt7925_mcu_uni_bss_bcnft(dev, info, true); + } + mt792x_mutex_release(dev); } @@ -1946,6 +1992,8 @@ mt7925_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif, GFP_KERNEL); mlink = devm_kzalloc(dev->mt76.dev, sizeof(*mlink), GFP_KERNEL); + if (!mconf || !mlink) + return -ENOMEM; } mconfs[link_id] = mconf; @@ -1974,6 +2022,8 @@ mt7925_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif, goto free; if (mconf != &mvif->bss_conf) { + mt7925_mcu_set_bss_pm(dev, link_conf, true); + err = mt7925_set_mlo_roc(phy, &mvif->bss_conf, vif->active_links); if (err < 0) @@ -2071,18 +2121,16 @@ static void mt7925_unassign_vif_chanctx(struct ieee80211_hw *hw, struct mt792x_chanctx *mctx = (struct mt792x_chanctx *)ctx->drv_priv; struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; struct mt792x_dev *dev = mt792x_hw_dev(hw); - struct ieee80211_bss_conf *pri_link_conf; struct mt792x_bss_conf *mconf; mutex_lock(&dev->mt76.mutex); if (ieee80211_vif_is_mld(vif)) { mconf = mt792x_vif_to_link(mvif, link_conf->link_id); - pri_link_conf = mt792x_vif_to_bss_conf(vif, mvif->deflink_id); if (vif->type == NL80211_IFTYPE_STATION && mconf == &mvif->bss_conf) - mt7925_mcu_add_bss_info(&dev->phy, NULL, pri_link_conf, + mt7925_mcu_add_bss_info(&dev->phy, NULL, link_conf, NULL, false); } else { mconf = &mvif->bss_conf; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index 748ea6adbc6b..15815ad84713 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -39,7 +39,6 @@ int mt7925_mcu_parse_response(struct mt76_dev *mdev, int cmd, } else if (cmd == MCU_UNI_CMD(DEV_INFO_UPDATE) || cmd == MCU_UNI_CMD(BSS_INFO_UPDATE) || cmd == MCU_UNI_CMD(STA_REC_UPDATE) || - cmd == MCU_UNI_CMD(HIF_CTRL) || cmd == MCU_UNI_CMD(OFFLOAD) || cmd == MCU_UNI_CMD(SUSPEND)) { struct mt7925_mcu_uni_event *event; @@ -123,10 +122,8 @@ EXPORT_SYMBOL_GPL(mt7925_mcu_regval); int mt7925_mcu_update_arp_filter(struct mt76_dev *dev, struct ieee80211_bss_conf *link_conf) { - struct ieee80211_vif *mvif = container_of((void *)link_conf->vif, - struct ieee80211_vif, - drv_priv); struct mt792x_bss_conf *mconf = mt792x_link_conf_to_mconf(link_conf); + struct ieee80211_vif *mvif = link_conf->vif; struct sk_buff *skb; int i, len = min_t(int, mvif->cfg.arp_addr_cnt, IEEE80211_BSS_ARP_ADDR_LIST_LEN); @@ -166,7 +163,7 @@ static int mt7925_connac_mcu_set_wow_ctrl(struct mt76_phy *phy, struct ieee80211_vif *vif, bool suspend, struct cfg80211_wowlan *wowlan) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt76_dev *dev = phy->dev; struct { struct { @@ -221,7 +218,7 @@ mt7925_mcu_set_wow_pattern(struct mt76_dev *dev, u8 index, bool enable, struct cfg80211_pkt_pattern *pattern) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt7925_wow_pattern_tlv *tlv; struct sk_buff *skb; struct { @@ -276,7 +273,7 @@ static void mt7925_mcu_connection_loss_iter(void *priv, u8 *mac, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt7925_uni_beacon_loss_event *event = priv; if (mvif->idx != event->hdr.bss_idx) @@ -306,7 +303,7 @@ mt7925_mcu_connection_loss_event(struct mt792x_dev *dev, struct sk_buff *skb) static void mt7925_mcu_roc_iter(void *priv, u8 *mac, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct mt7925_roc_grant_tlv *grant = priv; if (ieee80211_vif_is_mld(vif) && vif->type == NL80211_IFTYPE_STATION) @@ -343,6 +340,51 @@ static void mt7925_mcu_roc_handle_grant(struct mt792x_dev *dev, jiffies + msecs_to_jiffies(duration)); } +static void +mt7925_mcu_handle_hif_ctrl_basic(struct mt792x_dev *dev, struct tlv *tlv) +{ + struct mt7925_mcu_hif_ctrl_basic_tlv *basic; + + basic = (struct mt7925_mcu_hif_ctrl_basic_tlv *)tlv; + + if (basic->hifsuspend) { + if (basic->hif_tx_traffic_status == HIF_TRAFFIC_IDLE && + basic->hif_rx_traffic_status == HIF_TRAFFIC_IDLE) + /* success */ + dev->hif_idle = true; + else + /* busy */ + /* invalid */ + dev->hif_idle = false; + } else { + dev->hif_resumed = true; + } + wake_up(&dev->wait); +} + +static void +mt7925_mcu_uni_hif_ctrl_event(struct mt792x_dev *dev, struct sk_buff *skb) +{ + struct tlv *tlv; + u32 tlv_len; + + skb_pull(skb, sizeof(struct mt7925_mcu_rxd) + 4); + tlv = (struct tlv *)skb->data; + tlv_len = skb->len; + + while (tlv_len > 0 && le16_to_cpu(tlv->len) <= tlv_len) { + switch (le16_to_cpu(tlv->tag)) { + case UNI_EVENT_HIF_CTRL_BASIC: + mt7925_mcu_handle_hif_ctrl_basic(dev, tlv); + break; + default: + break; + } + tlv_len -= le16_to_cpu(tlv->len); + tlv = (struct tlv *)((char *)(tlv) + le16_to_cpu(tlv->len)); + } +} + static void mt7925_mcu_uni_roc_event(struct mt792x_dev *dev, struct sk_buff *skb) { @@ -388,7 +430,7 @@ mt7925_mcu_tx_done_event(struct mt792x_dev *dev, struct sk_buff *skb) struct mt7925_mcu_txs_event { u8 ver; u8 rsv[3]; - u8 data[0]; + u8 data[]; } __packed * txs; struct tlv *tlv; u32 tlv_len; @@ -489,6 +531,9 @@ mt7925_mcu_uni_rx_unsolicited_event(struct mt792x_dev *dev, rxd = (struct mt7925_mcu_rxd *)skb->data; switch (rxd->eid) { + case MCU_UNI_EVENT_HIF_CTRL: + mt7925_mcu_uni_hif_ctrl_event(dev, skb); + break; case MCU_UNI_EVENT_FW_LOG_2_HOST: mt7925_mcu_uni_debug_msg_event(dev, skb); break; @@ -530,11 +575,11 @@ void mt7925_mcu_rx_event(struct mt792x_dev *dev, struct sk_buff *skb) } static int -mt7925_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif, +mt7925_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif_link *mvif, + struct mt76_wcid *wcid, struct ieee80211_ampdu_params *params, bool enable, bool tx) { - struct mt76_wcid *wcid = (struct mt76_wcid *)params->sta->drv_priv; struct sta_rec_ba_uni *ba; struct sk_buff *skb; struct tlv *tlv; @@ -562,28 +607,60 @@ mt7925_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif, /** starec & wtbl **/ int mt7925_mcu_uni_tx_ba(struct mt792x_dev *dev, + struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params, bool enable) { struct mt792x_sta *msta = (struct mt792x_sta *)params->sta->drv_priv; - struct mt792x_vif *mvif = msta->vif; + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + struct mt792x_link_sta *mlink; + struct mt792x_bss_conf *mconf; + unsigned long usable_links = ieee80211_vif_usable_links(vif); + struct mt76_wcid *wcid; + u8 link_id, ret; - if (enable && !params->amsdu) - msta->deflink.wcid.amsdu = false; + for_each_set_bit(link_id, &usable_links, IEEE80211_MLD_MAX_NUM_LINKS) { + mconf = mt792x_vif_to_link(mvif, link_id); + mlink = mt792x_sta_to_link(msta, link_id); + wcid = &mlink->wcid; - return mt7925_mcu_sta_ba(&dev->mt76, &mvif->bss_conf.mt76, params, - enable, true); + if (enable && !params->amsdu) + mlink->wcid.amsdu = false; + + ret = mt7925_mcu_sta_ba(&dev->mt76, &mconf->mt76, wcid, params, + enable, true); + if (ret < 0) + break; + } + + return ret; } int mt7925_mcu_uni_rx_ba(struct mt792x_dev *dev, + struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params, bool enable) { struct mt792x_sta *msta = (struct mt792x_sta *)params->sta->drv_priv; - struct mt792x_vif *mvif = msta->vif; + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + struct mt792x_link_sta *mlink; + struct mt792x_bss_conf *mconf; + unsigned long usable_links = ieee80211_vif_usable_links(vif); + struct mt76_wcid *wcid; + u8 link_id, ret; - return mt7925_mcu_sta_ba(&dev->mt76, &mvif->bss_conf.mt76, params, - enable, false); + for_each_set_bit(link_id, &usable_links, IEEE80211_MLD_MAX_NUM_LINKS) { + mconf = mt792x_vif_to_link(mvif, link_id); + mlink = mt792x_sta_to_link(msta, link_id); + wcid = &mlink->wcid; + + ret = mt7925_mcu_sta_ba(&dev->mt76, &mconf->mt76, wcid, params, + enable, false); + if (ret < 0) + break; + } + + return ret; } static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name) @@ -638,7 +715,7 @@ static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name) for (offset = 0; offset < len; offset += le32_to_cpu(clc->len)) { clc = (const struct mt7925_clc *)(clc_base + offset); - if (clc->idx > ARRAY_SIZE(phy->clc)) + if (clc->idx >= ARRAY_SIZE(phy->clc)) break; /* do not init buf again if chip reset triggered */ @@ -823,7 +900,7 @@ mt7925_mcu_get_nic_capability(struct mt792x_dev *dev) mt7925_mcu_parse_phy_cap(dev, tlv->data); break; case MT_NIC_CAP_CHIP_CAP: - memcpy(&dev->phy.chip_cap, (void *)skb->data, sizeof(u64)); + dev->phy.chip_cap = le64_to_cpu(*(__le64 *)tlv->data); break; case MT_NIC_CAP_EML_CAP: mt7925_mcu_parse_eml_cap(dev, tlv->data); @@ -1153,7 +1230,12 @@ int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links, u8 rsv[4]; } __packed hdr; struct roc_acquire_tlv roc[2]; - } __packed req; + } __packed req = { + .roc[0].tag = cpu_to_le16(UNI_ROC_NUM), + .roc[0].len = cpu_to_le16(sizeof(struct roc_acquire_tlv)), + .roc[1].tag = cpu_to_le16(UNI_ROC_NUM), + .roc[1].len = cpu_to_le16(sizeof(struct roc_acquire_tlv)) + }; if (!mconf || hweight16(vif->valid_links) < 2 || hweight16(sel_links) != 2) @@ -1200,6 +1282,8 @@ int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links, req.roc[i].bw_from_ap = CMD_CBW_20MHZ; req.roc[i].center_chan = center_ch; req.roc[i].center_chan_from_ap = center_ch; + req.roc[i].center_chan2 = 0; + req.roc[i].center_chan2_from_ap = 0; /* STR : 0xfe indicates BAND_ALL with enabling DBDC * EMLSR : 0xff indicates (BAND_AUTO) without DBDC @@ -1215,7 +1299,7 @@ int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links, } return mt76_mcu_send_msg(&mvif->phy->dev->mt76, MCU_UNI_CMD(ROC), - &req, sizeof(req), false); + &req, sizeof(req), true); } int mt7925_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf, @@ -1264,7 +1348,7 @@ int mt7925_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf, } return mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(ROC), - &req, sizeof(req), false); + &req, sizeof(req), true); } int mt7925_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf, @@ -1294,7 +1378,7 @@ int mt7925_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf, }; return mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(ROC), - &req, sizeof(req), false); + &req, sizeof(req), true); } int mt7925_mcu_set_eeprom(struct mt792x_dev *dev) @@ -1357,7 +1441,7 @@ int mt7925_mcu_uni_bss_ps(struct mt792x_dev *dev, &ps_req, sizeof(ps_req), true); } -static int +int mt7925_mcu_uni_bss_bcnft(struct mt792x_dev *dev, struct ieee80211_bss_conf *link_conf, bool enable) { @@ -1447,12 +1531,12 @@ mt7925_mcu_set_bss_pm(struct mt792x_dev *dev, int err; err = mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(BSS_INFO_UPDATE), - &req1, sizeof(req1), false); + &req1, sizeof(req1), true); if (err < 0 || !enable) return err; return mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(BSS_INFO_UPDATE), - &req, sizeof(req), false); + &req, sizeof(req), true); } static void @@ -1770,7 +1854,7 @@ static int mt7925_mcu_sta_cmd(struct mt76_phy *phy, struct mt76_sta_cmd_info *info) { - struct mt76_vif *mvif = (struct mt76_vif *)info->vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)info->vif->drv_priv; struct mt76_dev *dev = phy->dev; struct sk_buff *skb; int conn_state; @@ -1783,7 +1867,7 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy, conn_state = info->enable ? CONN_STATE_PORT_SECURE : CONN_STATE_DISCONNECT; if (info->link_sta) - mt76_connac_mcu_sta_basic_tlv(dev, skb, info->vif, + mt76_connac_mcu_sta_basic_tlv(dev, skb, info->link_conf, info->link_sta, conn_state, info->newly); if (info->link_sta && info->enable) { @@ -1837,7 +1921,7 @@ mt7925_mcu_mlo_sta_cmd(struct mt76_phy *phy, return PTR_ERR(skb); if (info->enable) - mt76_connac_mcu_sta_basic_tlv(dev, skb, info->vif, + mt76_connac_mcu_sta_basic_tlv(dev, skb, info->link_conf, info->link_sta, info->enable, info->newly); @@ -1883,6 +1967,7 @@ int mt7925_mcu_sta_update(struct mt792x_dev *dev, struct mt76_sta_cmd_info info = { .link_sta = link_sta, .vif = vif, + .link_conf = &vif->bss_conf, .enable = enable, .cmd = MCU_UNI_CMD(STA_REC_UPDATE), .state = state, @@ -1898,7 +1983,11 @@ int mt7925_mcu_sta_update(struct mt792x_dev *dev, mlink = mt792x_sta_to_link(msta, link_sta->link_id); } info.wcid = link_sta ? &mlink->wcid : &mvif->sta.deflink.wcid; - info.newly = link_sta ? state != MT76_STA_INFO_STATE_ASSOC : true; + + if (link_sta) + info.newly = state != MT76_STA_INFO_STATE_ASSOC; + else + info.newly = state == MT76_STA_INFO_STATE_ASSOC ? false : true; if (ieee80211_vif_is_mld(vif)) err = mt7925_mcu_mlo_sta_cmd(&dev->mphy, &info); @@ -1914,32 +2003,21 @@ int mt7925_mcu_set_beacon_filter(struct mt792x_dev *dev, { #define MT7925_FIF_BIT_CLR BIT(1) #define MT7925_FIF_BIT_SET BIT(0) - struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; - unsigned long valid = ieee80211_vif_is_mld(vif) ? - mvif->valid_links : BIT(0); - struct ieee80211_bss_conf *bss_conf; int err = 0; - int i; if (enable) { - for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) { - bss_conf = mt792x_vif_to_bss_conf(vif, i); - err = mt7925_mcu_uni_bss_bcnft(dev, bss_conf, true); - if (err < 0) - return err; - } + err = mt7925_mcu_uni_bss_bcnft(dev, &vif->bss_conf, true); + if (err < 0) + return err; return mt7925_mcu_set_rxfilter(dev, 0, MT7925_FIF_BIT_SET, MT_WF_RFCR_DROP_OTHER_BEACON); } - for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) { - bss_conf = mt792x_vif_to_bss_conf(vif, i); - err = mt7925_mcu_set_bss_pm(dev, bss_conf, false); - if (err) - return err; - } + err = mt7925_mcu_set_bss_pm(dev, &vif->bss_conf, false); + if (err < 0) + return err; return mt7925_mcu_set_rxfilter(dev, 0, MT7925_FIF_BIT_CLR, @@ -1976,8 +2054,6 @@ int mt7925_get_txpwr_info(struct mt792x_dev *dev, u8 band_idx, struct mt7925_txp int mt7925_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif, bool enable) { - struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; - struct { struct { u8 band_idx; @@ -1991,7 +2067,7 @@ int mt7925_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif, } __packed enable; } __packed req = { .hdr = { - .band_idx = mvif->bss_conf.mt76.band_idx, + .band_idx = 0, }, .enable = { .tag = cpu_to_le16(UNI_SNIFFER_ENABLE), @@ -2050,7 +2126,7 @@ int mt7925_mcu_config_sniffer(struct mt792x_vif *vif, } __packed tlv; } __packed req = { .hdr = { - .band_idx = vif->bss_conf.mt76.band_idx, + .band_idx = 0, }, .tlv = { .tag = cpu_to_le16(UNI_SNIFFER_CONFIG), @@ -2179,11 +2255,27 @@ void mt7925_mcu_bss_rlm_tlv(struct sk_buff *skb, struct mt76_phy *phy, req = (struct bss_rlm_tlv *)tlv; req->control_channel = chandef->chan->hw_value; req->center_chan = ieee80211_frequency_to_channel(freq1); - req->center_chan2 = ieee80211_frequency_to_channel(freq2); + req->center_chan2 = 0; req->tx_streams = hweight8(phy->antenna_mask); req->ht_op_info = 4; /* set HT 40M allowed */ req->rx_streams = hweight8(phy->antenna_mask); - req->band = band; + req->center_chan2 = 0; + req->sco = 0; + req->band = 1; + + switch (band) { + case NL80211_BAND_2GHZ: + req->band = 1; + break; + case NL80211_BAND_5GHZ: + req->band = 2; + break; + case NL80211_BAND_6GHZ: + req->band = 3; + break; + default: + break; + } switch (chandef->width) { case NL80211_CHAN_WIDTH_40: @@ -2194,6 +2286,7 @@ void mt7925_mcu_bss_rlm_tlv(struct sk_buff *skb, struct mt76_phy *phy, break; case NL80211_CHAN_WIDTH_80P80: req->bw = CMD_CBW_8080MHZ; + req->center_chan2 = ieee80211_frequency_to_channel(freq2); break; case NL80211_CHAN_WIDTH_160: req->bw = CMD_CBW_160MHZ; @@ -2219,7 +2312,7 @@ void mt7925_mcu_bss_rlm_tlv(struct sk_buff *skb, struct mt76_phy *phy, } static struct sk_buff * -__mt7925_mcu_alloc_bss_req(struct mt76_dev *dev, struct mt76_vif *mvif, int len) +__mt7925_mcu_alloc_bss_req(struct mt76_dev *dev, struct mt76_vif_link *mvif, int len) { struct bss_req_hdr hdr = { .bss_idx = mvif->idx, @@ -2235,7 +2328,7 @@ __mt7925_mcu_alloc_bss_req(struct mt76_dev *dev, struct mt76_vif *mvif, int len) return skb; } -int mt7925_mcu_set_chctx(struct mt76_phy *phy, struct mt76_vif *mvif, +int mt7925_mcu_set_chctx(struct mt76_phy *phy, struct mt76_vif_link *mvif, struct ieee80211_bss_conf *link_conf, struct ieee80211_chanctx_conf *ctx) { @@ -2388,7 +2481,7 @@ mt7925_mcu_bss_sec_tlv(struct sk_buff *skb, struct ieee80211_bss_conf *link_conf) { struct mt792x_bss_conf *mconf = mt792x_link_conf_to_mconf(link_conf); - struct mt76_vif *mvif = &mconf->mt76; + struct mt76_vif_link *mvif = &mconf->mt76; struct bss_sec_tlv { __le16 tag; __le16 len; @@ -2439,7 +2532,7 @@ mt7925_mcu_bss_bmc_tlv(struct sk_buff *skb, struct mt792x_phy *phy, &link_conf->chanreq.oper; struct mt792x_bss_conf *mconf = mt792x_link_conf_to_mconf(link_conf); enum nl80211_band band = chandef->chan->band; - struct mt76_vif *mvif = &mconf->mt76; + struct mt76_vif_link *mvif = &mconf->mt76; struct bss_rate_tlv *bmc; struct tlv *tlv; u8 idx = mvif->mcast_rates_idx ? @@ -2463,6 +2556,7 @@ static void mt7925_mcu_bss_mld_tlv(struct sk_buff *skb, struct ieee80211_bss_conf *link_conf) { + struct ieee80211_vif *vif = link_conf->vif; struct mt792x_bss_conf *mconf = mt792x_link_conf_to_mconf(link_conf); struct mt792x_vif *mvif = (struct mt792x_vif *)link_conf->vif->drv_priv; struct bss_mld_tlv *mld; @@ -2483,7 +2577,7 @@ mt7925_mcu_bss_mld_tlv(struct sk_buff *skb, mld->eml_enable = !!(link_conf->vif->cfg.eml_cap & IEEE80211_EML_CAP_EMLSR_SUPP); - memcpy(mld->mac_addr, link_conf->addr, ETH_ALEN); + memcpy(mld->mac_addr, vif->addr, ETH_ALEN); } static void @@ -2614,7 +2708,7 @@ int mt7925_mcu_add_bss_info(struct mt792x_phy *phy, MCU_UNI_CMD(BSS_INFO_UPDATE), true); } -int mt7925_mcu_set_dbdc(struct mt76_phy *phy) +int mt7925_mcu_set_dbdc(struct mt76_phy *phy, bool enable) { struct mt76_dev *mdev = phy->dev; @@ -2634,7 +2728,7 @@ int mt7925_mcu_set_dbdc(struct mt76_phy *phy) tlv = mt76_connac_mcu_add_tlv(skb, UNI_MBMC_SETTING, sizeof(*conf)); conf = (struct mbmc_conf_tlv *)tlv; - conf->mbmc_en = 1; + conf->mbmc_en = enable; conf->band = 0; /* unused */ err = mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SET_DBDC_PARMS), @@ -2643,14 +2737,12 @@ int mt7925_mcu_set_dbdc(struct mt76_phy *phy) return err; } -#define MT76_CONNAC_SCAN_CHANNEL_TIME 60 - int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_scan_request *scan_req) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct cfg80211_scan_request *sreq = &scan_req->req; - int n_ssids = 0, err, i, duration; + int n_ssids = 0, err, i; struct ieee80211_channel **scan_list = sreq->channels; struct mt76_dev *mdev = phy->dev; struct mt76_connac_mcu_scan_channel *chan; @@ -2686,14 +2778,6 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, req->scan_type = sreq->n_ssids ? 1 : 0; req->probe_req_num = sreq->n_ssids ? 2 : 0; - duration = MT76_CONNAC_SCAN_CHANNEL_TIME; - /* increase channel time for passive scan */ - if (!sreq->n_ssids) - duration *= 2; - req->timeout_value = cpu_to_le16(sreq->n_channels * duration); - req->channel_min_dwell_time = cpu_to_le16(duration); - req->channel_dwell_time = cpu_to_le16(duration); - tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_SSID, sizeof(*ssid)); ssid = (struct scan_ssid_tlv *)tlv; for (i = 0; i < sreq->n_ssids; i++) { @@ -2765,7 +2849,7 @@ int mt7925_mcu_sched_scan_req(struct mt76_phy *phy, struct ieee80211_vif *vif, struct cfg80211_sched_scan_request *sreq) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct ieee80211_channel **scan_list = sreq->channels; struct mt76_connac_mcu_scan_channel *chan; struct mt76_dev *mdev = phy->dev; @@ -2901,7 +2985,7 @@ mt7925_mcu_sched_scan_enable(struct mt76_phy *phy, int mt7925_mcu_cancel_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct { struct scan_hdr { u8 seq_num; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h index ac53bdc99332..1e47d2c61b54 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h @@ -616,7 +616,7 @@ mt7925_mcu_get_cipher(int cipher) } } -int mt7925_mcu_set_dbdc(struct mt76_phy *phy); +int mt7925_mcu_set_dbdc(struct mt76_phy *phy, bool enable); int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_scan_request *scan_req); int mt7925_mcu_cancel_hw_scan(struct mt76_phy *phy, @@ -637,10 +637,13 @@ int mt7925_mcu_set_timing(struct mt792x_phy *phy, int mt7925_mcu_set_deep_sleep(struct mt792x_dev *dev, bool enable); int mt7925_mcu_set_channel_domain(struct mt76_phy *phy); int mt7925_mcu_set_radio_en(struct mt792x_phy *phy, bool enable); -int mt7925_mcu_set_chctx(struct mt76_phy *phy, struct mt76_vif *mvif, +int mt7925_mcu_set_chctx(struct mt76_phy *phy, struct mt76_vif_link *mvif, struct ieee80211_bss_conf *link_conf, struct ieee80211_chanctx_conf *ctx); int mt7925_mcu_set_rate_txpower(struct mt76_phy *phy); int mt7925_mcu_update_arp_filter(struct mt76_dev *dev, struct ieee80211_bss_conf *link_conf); +int +mt7925_mcu_uni_bss_bcnft(struct mt792x_dev *dev, + struct ieee80211_bss_conf *link_conf, bool enable); #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h index f5c02e5f5066..8707b5d04743 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h @@ -27,6 +27,26 @@ #define MCU_UNI_EVENT_ROC 0x27 +#define HIF_TRAFFIC_IDLE 0x2 + +enum { + UNI_EVENT_HIF_CTRL_BASIC = 0, + UNI_EVENT_HIF_CTRL_TAG_NUM +}; + +struct mt7925_mcu_hif_ctrl_basic_tlv { + __le16 tag; + __le16 len; + u8 cid; + u8 pad[3]; + u32 status; + u8 hif_type; + u8 hif_tx_traffic_status; + u8 hif_rx_traffic_status; + u8 hifsuspend; + u8 rsv[4]; +} __packed; + enum { UNI_ROC_ACQUIRE, UNI_ROC_ABORT, @@ -215,6 +235,7 @@ int mt7925_mcu_chip_config(struct mt792x_dev *dev, const char *cmd); int mt7925_mcu_set_rxfilter(struct mt792x_dev *dev, u32 fif, u8 bit_op, u32 bit_map); +void mt7925_regd_update(struct mt792x_dev *dev); int mt7925_mac_init(struct mt792x_dev *dev); int mt7925_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); @@ -242,9 +263,11 @@ int mt7925_mcu_set_beacon_filter(struct mt792x_dev *dev, struct ieee80211_vif *vif, bool enable); int mt7925_mcu_uni_tx_ba(struct mt792x_dev *dev, + struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params, bool enable); int mt7925_mcu_uni_rx_ba(struct mt792x_dev *dev, + struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params, bool enable); void mt7925_scan_work(struct work_struct *work); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c index 9aec675450f2..c7b5dc1dbb34 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c @@ -442,9 +442,10 @@ static int mt7925_pci_suspend(struct device *device) struct mt76_dev *mdev = pci_get_drvdata(pdev); struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76); struct mt76_connac_pm *pm = &dev->pm; - int i, err; + int i, err, ret; pm->suspended = true; + dev->hif_resumed = false; flush_work(&dev->reset_work); cancel_delayed_work_sync(&pm->ps_work); cancel_work_sync(&pm->wake_work); @@ -455,14 +456,21 @@ static int mt7925_pci_suspend(struct device *device) if (err < 0) goto restore_suspend; + wait_event_timeout(dev->wait, + !dev->regd_in_progress, 5 * HZ); + /* always enable deep sleep during suspend to reduce * power consumption */ mt7925_mcu_set_deep_sleep(dev, true); - err = mt76_connac_mcu_set_hif_suspend(mdev, true); - if (err) + mt76_connac_mcu_set_hif_suspend(mdev, true, false); + ret = wait_event_timeout(dev->wait, + dev->hif_idle, 3 * HZ); + if (!ret) { + err = -ETIMEDOUT; goto restore_suspend; + } napi_disable(&mdev->tx_napi); mt76_worker_disable(&mdev->tx_worker); @@ -506,8 +514,11 @@ restore_napi: if (!pm->ds_enable) mt7925_mcu_set_deep_sleep(dev, false); - mt76_connac_mcu_set_hif_suspend(mdev, false); - + mt76_connac_mcu_set_hif_suspend(mdev, false, false); + ret = wait_event_timeout(dev->wait, + dev->hif_resumed, 3 * HZ); + if (!ret) + err = -ETIMEDOUT; restore_suspend: pm->suspended = false; @@ -523,8 +534,9 @@ static int mt7925_pci_resume(struct device *device) struct mt76_dev *mdev = pci_get_drvdata(pdev); struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76); struct mt76_connac_pm *pm = &dev->pm; - int i, err; + int i, err, ret; + dev->hif_idle = false; err = mt792x_mcu_drv_pmctrl(dev); if (err < 0) goto failed; @@ -544,21 +556,31 @@ static int mt7925_pci_resume(struct device *device) mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { napi_enable(&mdev->napi[i]); - napi_schedule(&mdev->napi[i]); } napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + napi_schedule(&mdev->napi[i]); + } napi_schedule(&mdev->tx_napi); local_bh_enable(); - err = mt76_connac_mcu_set_hif_suspend(mdev, false); + mt76_connac_mcu_set_hif_suspend(mdev, false, false); + ret = wait_event_timeout(dev->wait, + dev->hif_resumed, 3 * HZ); + if (!ret) { + err = -ETIMEDOUT; + goto failed; + } /* restore previous ds setting */ if (!pm->ds_enable) mt7925_mcu_set_deep_sleep(dev, false); + mt7925_regd_update(dev); failed: pm->suspended = false; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c index faedbf766d1a..4578d16bf456 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c @@ -101,12 +101,15 @@ int mt7925e_mac_reset(struct mt792x_dev *dev) mt792x_wpdma_reset(dev, true); - local_bh_disable(); mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); - napi_schedule(&dev->mt76.napi[i]); } napi_enable(&dev->mt76.tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(&dev->mt76, i) { + napi_schedule(&dev->mt76.napi[i]); + } napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c index 682db1bab21c..4dfbc1b6cfdd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c @@ -243,14 +243,19 @@ static int mt7925u_suspend(struct usb_interface *intf, pm_message_t state) { struct mt792x_dev *dev = usb_get_intfdata(intf); struct mt76_connac_pm *pm = &dev->pm; - int err; + int err, ret; pm->suspended = true; + dev->hif_resumed = false; flush_work(&dev->reset_work); - err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, true); - if (err) + mt76_connac_mcu_set_hif_suspend(&dev->mt76, true, false); + ret = wait_event_timeout(dev->wait, + dev->hif_idle, 3 * HZ); + if (!ret) { + err = -ETIMEDOUT; goto failed; + } mt76u_stop_rx(&dev->mt76); mt76u_stop_tx(&dev->mt76); @@ -271,8 +276,9 @@ static int mt7925u_resume(struct usb_interface *intf) struct mt792x_dev *dev = usb_get_intfdata(intf); struct mt76_connac_pm *pm = &dev->pm; bool reinit = true; - int err, i; + int err, i, ret; + dev->hif_idle = false; for (i = 0; i < 10; i++) { u32 val = mt76_rr(dev, MT_WF_SW_DEF_CR_USB_MCU_EVENT); @@ -298,7 +304,11 @@ static int mt7925u_resume(struct usb_interface *intf) if (err < 0) goto failed; - err = mt76_connac_mcu_set_hif_suspend(&dev->mt76, false); + mt76_connac_mcu_set_hif_suspend(&dev->mt76, false, false); + ret = wait_event_timeout(dev->wait, + dev->hif_resumed, 3 * HZ); + if (!ret) + err = -ETIMEDOUT; failed: pm->suspended = false; diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h index ab12616ec2b8..32ed01a96bf7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x.h +++ b/drivers/net/wireless/mediatek/mt76/mt792x.h @@ -28,6 +28,7 @@ #define MT792x_CHIP_CAP_CLC_EVT_EN BIT(0) #define MT792x_CHIP_CAP_RSSI_NOTIFY_EVT_EN BIT(1) #define MT792x_CHIP_CAP_MLO_EVT_EN BIT(2) +#define MT792x_CHIP_CAP_WF_RF_PIN_CTRL_EVT_EN BIT(3) /* NOTE: used to map mt76_rates. idx may change if firmware expands table */ #define MT792x_BASIC_RATES_TBL 11 @@ -116,7 +117,7 @@ struct mt792x_chanctx { }; struct mt792x_bss_conf { - struct mt76_vif mt76; /* must be first */ + struct mt76_vif_link mt76; /* must be first */ struct mt792x_vif *vif; struct ewma_rssi rssi; struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS]; @@ -133,6 +134,9 @@ struct mt792x_vif { struct mt792x_phy *phy; u16 valid_links; u8 deflink_id; + + struct work_struct csa_work; + struct timer_list csa_timer; }; struct mt792x_phy { @@ -206,6 +210,8 @@ struct mt792x_dev { struct mt76_phy mphy; }; + struct mac_address macaddr_list[8]; + const struct mt76_bus_ops *bus_ops; struct mt792x_phy phy; @@ -216,6 +222,10 @@ struct mt792x_dev { bool has_eht:1; bool regd_in_progress:1; bool aspm_supported:1; + bool hif_idle:1; + bool hif_resumed:1; + bool sar_inited:1; + bool regd_change:1; wait_queue_head_t wait; struct work_struct init_work; @@ -235,12 +245,15 @@ struct mt792x_dev { enum environment_cap country_ie_env; u32 backup_l1; u32 backup_l2; + + struct ieee80211_chanctx_conf *new_ctx; }; static inline struct mt792x_bss_conf * mt792x_vif_to_link(struct mt792x_vif *mvif, u8 link_id) { struct ieee80211_vif *vif; + struct mt792x_bss_conf *bss_conf; vif = container_of((void *)mvif, struct ieee80211_vif, drv_priv); @@ -248,8 +261,10 @@ mt792x_vif_to_link(struct mt792x_vif *mvif, u8 link_id) link_id >= IEEE80211_LINK_UNSPECIFIED) return &mvif->bss_conf; - return rcu_dereference_protected(mvif->link_conf[link_id], - lockdep_is_held(&mvif->phy->dev->mt76.mutex)); + bss_conf = rcu_dereference_protected(mvif->link_conf[link_id], + lockdep_is_held(&mvif->phy->dev->mt76.mutex)); + + return bss_conf ? bss_conf : &mvif->bss_conf; } static inline struct mt792x_link_sta * @@ -364,6 +379,7 @@ void mt792x_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 timestamp); void mt792x_tx_worker(struct mt76_worker *w); void mt792x_roc_timer(struct timer_list *timer); +void mt792x_csa_timer(struct timer_list *timer); void mt792x_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 queues, bool drop); int mt792x_assign_vif_chanctx(struct ieee80211_hw *hw, @@ -414,6 +430,7 @@ int mt792x_mcu_fw_pmctrl(struct mt792x_dev *dev); void mt792x_mac_link_bss_remove(struct mt792x_dev *dev, struct mt792x_bss_conf *mconf, struct mt792x_link_sta *mlink); +void mt792x_config_mac_addr_list(struct mt792x_dev *dev); static inline char *mt792x_ram_name(struct mt792x_dev *dev) { diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c index 78fe37c2e07b..8799627f6292 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c @@ -38,6 +38,10 @@ static const struct ieee80211_iface_limit if_limits_chanctx[] = { .max = 1, .types = BIT(NL80211_IFTYPE_AP) | BIT(NL80211_IFTYPE_P2P_GO) + }, + { + .max = 1, + .types = BIT(NL80211_IFTYPE_P2P_DEVICE) } }; @@ -45,7 +49,7 @@ static const struct ieee80211_iface_combination if_comb_chanctx[] = { { .limits = if_limits_chanctx, .n_limits = ARRAY_SIZE(if_limits_chanctx), - .max_interfaces = 2, + .max_interfaces = 3, .num_different_channels = 2, .beacon_int_infra_match = false, } @@ -147,7 +151,8 @@ void mt792x_mac_link_bss_remove(struct mt792x_dev *dev, link_conf = mt792x_vif_to_bss_conf(vif, mconf->link_id); mt76_connac_free_pending_tx_skbs(&dev->pm, &mlink->wcid); - mt76_connac_mcu_uni_add_dev(&dev->mphy, link_conf, &mlink->wcid, false); + mt76_connac_mcu_uni_add_dev(&dev->mphy, link_conf, &mconf->mt76, + &mlink->wcid, false); rcu_assign_pointer(dev->mt76.wcid[idx], NULL); @@ -284,6 +289,14 @@ void mt792x_roc_timer(struct timer_list *timer) } EXPORT_SYMBOL_GPL(mt792x_roc_timer); +void mt792x_csa_timer(struct timer_list *timer) +{ + struct mt792x_vif *mvif = from_timer(mvif, timer, csa_timer); + + ieee80211_queue_work(mvif->phy->mt76->hw, &mvif->csa_work); +} +EXPORT_SYMBOL_GPL(mt792x_csa_timer); + void mt792x_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 queues, bool drop) { @@ -325,6 +338,11 @@ void mt792x_unassign_vif_chanctx(struct ieee80211_hw *hw, mctx->bss_conf = NULL; mvif->bss_conf.mt76.ctx = NULL; mutex_unlock(&dev->mt76.mutex); + + if (vif->bss_conf.csa_active) { + del_timer_sync(&mvif->csa_timer); + cancel_work_sync(&mvif->csa_work); + } } EXPORT_SYMBOL_GPL(mt792x_unassign_vif_chanctx); @@ -614,7 +632,8 @@ int mt792x_init_wiphy(struct ieee80211_hw *hw) wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP) | BIT(NL80211_IFTYPE_P2P_CLIENT) | - BIT(NL80211_IFTYPE_P2P_GO); + BIT(NL80211_IFTYPE_P2P_GO) | + BIT(NL80211_IFTYPE_P2P_DEVICE); wiphy->max_remain_on_channel_duration = 5000; wiphy->max_scan_ie_len = MT76_CONNAC_SCAN_IE_LEN; wiphy->max_scan_ssids = 4; @@ -646,6 +665,7 @@ int mt792x_init_wiphy(struct ieee80211_hw *hw) ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS); ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); ieee80211_hw_set(hw, CONNECTION_MONITOR); + ieee80211_hw_set(hw, CHANCTX_STA_CSA); if (dev->pm.enable) ieee80211_hw_set(hw, CONNECTION_MONITOR); @@ -911,6 +931,28 @@ int mt792x_load_firmware(struct mt792x_dev *dev) } EXPORT_SYMBOL_GPL(mt792x_load_firmware); +void mt792x_config_mac_addr_list(struct mt792x_dev *dev) +{ + struct ieee80211_hw *hw = mt76_hw(dev); + struct wiphy *wiphy = hw->wiphy; + int i; + + for (i = 0; i < ARRAY_SIZE(dev->macaddr_list); i++) { + u8 *addr = dev->macaddr_list[i].addr; + + memcpy(addr, dev->mphy.macaddr, ETH_ALEN); + + if (!i) + continue; + + addr[0] |= BIT(1); + addr[0] ^= ((i - 1) << 2); + } + wiphy->addresses = dev->macaddr_list; + wiphy->n_addresses = ARRAY_SIZE(dev->macaddr_list); +} +EXPORT_SYMBOL_GPL(mt792x_config_mac_addr_list); + MODULE_DESCRIPTION("MediaTek MT792x core driver"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Lorenzo Bianconi "); diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c index 106273935b26..05978d9c7b91 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c @@ -153,7 +153,7 @@ struct mt76_wcid *mt792x_rx_get_wcid(struct mt792x_dev *dev, u16 idx, return NULL; link = container_of(wcid, struct mt792x_link_sta, wcid); - sta = container_of(link, struct mt792x_sta, deflink); + sta = link->sta; if (!sta->vif) return NULL; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c index 62c03d088925..7b2bb72b407d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c @@ -51,12 +51,10 @@ static ssize_t mt7996_sys_recovery_set(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { - struct mt7996_phy *phy = file->private_data; - struct mt7996_dev *dev = phy->dev; - bool band = phy->mt76->band_idx; - char buf[16]; + struct mt7996_dev *dev = file->private_data; + char buf[16], *sep; int ret = 0; - u16 val; + u16 band, val; if (count >= sizeof(buf)) return -EINVAL; @@ -69,21 +67,26 @@ mt7996_sys_recovery_set(struct file *file, const char __user *user_buf, else buf[count] = '\0'; - if (kstrtou16(buf, 0, &val)) + sep = strchr(buf, ','); + if (!sep) + return -EINVAL; + + *sep = 0; + if (kstrtou16(buf, 0, &band) || kstrtou16(sep + 1, 0, &val)) return -EINVAL; switch (val) { /* - * 0: grab firmware current SER state. - * 1: trigger & enable system error L1 recovery. - * 2: trigger & enable system error L2 recovery. - * 3: trigger & enable system error L3 rx abort. - * 4: trigger & enable system error L3 tx abort - * 5: trigger & enable system error L3 tx disable. - * 6: trigger & enable system error L3 bf recovery. - * 7: trigger & enable system error L4 mdp recovery. - * 8: trigger & enable system error full recovery. - * 9: trigger firmware crash. + * ,0: grab firmware current SER state. + * ,1: trigger & enable system error L1 recovery. + * ,2: trigger & enable system error L2 recovery. + * ,3: trigger & enable system error L3 rx abort. + * ,4: trigger & enable system error L3 tx abort + * ,5: trigger & enable system error L3 tx disable. + * ,6: trigger & enable system error L3 bf recovery. + * ,7: trigger & enable system error L4 mdp recovery. + * ,8: trigger & enable system error full recovery. + * ,9: trigger firmware crash. */ case UNI_CMD_SER_QUERY: ret = mt7996_mcu_set_ser(dev, UNI_CMD_SER_QUERY, 0, band); @@ -126,8 +129,7 @@ static ssize_t mt7996_sys_recovery_get(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { - struct mt7996_phy *phy = file->private_data; - struct mt7996_dev *dev = phy->dev; + struct mt7996_dev *dev = file->private_data; char *buff; int desc = 0; ssize_t ret; @@ -141,25 +143,25 @@ mt7996_sys_recovery_get(struct file *file, char __user *user_buf, desc += scnprintf(buff + desc, bufsz - desc, "Please echo the correct value ...\n"); desc += scnprintf(buff + desc, bufsz - desc, - "0: grab firmware transient SER state\n"); + ",0: grab firmware transient SER state\n"); desc += scnprintf(buff + desc, bufsz - desc, - "1: trigger system error L1 recovery\n"); + ",1: trigger system error L1 recovery\n"); desc += scnprintf(buff + desc, bufsz - desc, - "2: trigger system error L2 recovery\n"); + ",2: trigger system error L2 recovery\n"); desc += scnprintf(buff + desc, bufsz - desc, - "3: trigger system error L3 rx abort\n"); + ",3: trigger system error L3 rx abort\n"); desc += scnprintf(buff + desc, bufsz - desc, - "4: trigger system error L3 tx abort\n"); + ",4: trigger system error L3 tx abort\n"); desc += scnprintf(buff + desc, bufsz - desc, - "5: trigger system error L3 tx disable\n"); + ",5: trigger system error L3 tx disable\n"); desc += scnprintf(buff + desc, bufsz - desc, - "6: trigger system error L3 bf recovery\n"); + ",6: trigger system error L3 bf recovery\n"); desc += scnprintf(buff + desc, bufsz - desc, - "7: trigger system error L4 mdp recovery\n"); + ",7: trigger system error L4 mdp recovery\n"); desc += scnprintf(buff + desc, bufsz - desc, - "8: trigger system error full recovery\n"); + ",8: trigger system error full recovery\n"); desc += scnprintf(buff + desc, bufsz - desc, - "9: trigger firmware crash\n"); + ",9: trigger firmware crash\n"); /* SER statistics */ desc += scnprintf(buff + desc, bufsz - desc, @@ -524,16 +526,12 @@ mt7996_txbf_stat_read_phy(struct mt7996_phy *phy, struct seq_file *s) seq_puts(s, "\n"); } -static int -mt7996_tx_stats_show(struct seq_file *file, void *data) +static void +mt7996_tx_stats_show_phy(struct seq_file *file, struct mt7996_phy *phy) { - struct mt7996_phy *phy = file->private; - struct mt7996_dev *dev = phy->dev; struct mt76_mib_stats *mib = &phy->mib; - int i; u32 attempts, success, per; - - mutex_lock(&dev->mt76.mutex); + int i; mt7996_mac_update_stats(phy); mt7996_ampdu_stat_read_phy(phy, file); @@ -558,6 +556,23 @@ mt7996_tx_stats_show(struct seq_file *file, void *data) else seq_puts(file, "\n"); } +} + +static int +mt7996_tx_stats_show(struct seq_file *file, void *data) +{ + struct mt7996_dev *dev = file->private; + struct mt7996_phy *phy = &dev->phy; + + mutex_lock(&dev->mt76.mutex); + + mt7996_tx_stats_show_phy(file, phy); + phy = mt7996_phy2(dev); + if (phy) + mt7996_tx_stats_show_phy(file, phy); + phy = mt7996_phy3(dev); + if (phy) + mt7996_tx_stats_show_phy(file, phy); mutex_unlock(&dev->mt76.mutex); @@ -601,7 +616,7 @@ static void mt7996_sta_hw_queue_read(void *data, struct ieee80211_sta *sta) { struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; - struct mt7996_dev *dev = msta->vif->phy->dev; + struct mt7996_dev *dev = msta->vif->deflink.phy->dev; struct seq_file *s = data; u8 ac; @@ -621,15 +636,15 @@ mt7996_sta_hw_queue_read(void *data, struct ieee80211_sta *sta) GENMASK(11, 0)); seq_printf(s, "\tSTA %pM wcid %d: AC%d%d queued:%d\n", sta->addr, msta->wcid.idx, - msta->vif->mt76.wmm_idx, ac, qlen); + msta->vif->deflink.mt76.wmm_idx, ac, qlen); } } static int mt7996_hw_queues_show(struct seq_file *file, void *data) { - struct mt7996_phy *phy = file->private; - struct mt7996_dev *dev = phy->dev; + struct mt7996_dev *dev = file->private; + struct mt7996_phy *phy = &dev->phy; static const struct hw_queue_map ple_queue_map[] = { { "CPU_Q0", 0, 1, MT_CTX0 }, { "CPU_Q1", 1, 1, MT_CTX0 + 1 }, @@ -685,6 +700,15 @@ mt7996_hw_queues_show(struct seq_file *file, void *data) /* iterate per-sta ple queue */ ieee80211_iterate_stations_atomic(phy->mt76->hw, mt7996_sta_hw_queue_read, file); + phy = mt7996_phy2(dev); + if (phy) + ieee80211_iterate_stations_atomic(phy->mt76->hw, + mt7996_sta_hw_queue_read, file); + phy = mt7996_phy3(dev); + if (phy) + ieee80211_iterate_stations_atomic(phy->mt76->hw, + mt7996_sta_hw_queue_read, file); + /* pse queue */ seq_puts(file, "PSE non-empty queue info:\n"); mt7996_hw_queue_read(file, ARRAY_SIZE(pse_queue_map), @@ -698,19 +722,29 @@ DEFINE_SHOW_ATTRIBUTE(mt7996_hw_queues); static int mt7996_xmit_queues_show(struct seq_file *file, void *data) { - struct mt7996_phy *phy = file->private; - struct mt7996_dev *dev = phy->dev; + struct mt7996_dev *dev = file->private; + struct mt7996_phy *phy; struct { struct mt76_queue *q; char *queue; } queue_map[] = { - { phy->mt76->q_tx[MT_TXQ_BE], " MAIN" }, + { dev->mphy.q_tx[MT_TXQ_BE], " MAIN0" }, + { NULL, " MAIN1" }, + { NULL, " MAIN2" }, { dev->mt76.q_mcu[MT_MCUQ_WM], " MCUWM" }, { dev->mt76.q_mcu[MT_MCUQ_WA], " MCUWA" }, { dev->mt76.q_mcu[MT_MCUQ_FWDL], "MCUFWDL" }, }; int i; + phy = mt7996_phy2(dev); + if (phy) + queue_map[1].q = phy->mt76->q_tx[MT_TXQ_BE]; + + phy = mt7996_phy3(dev); + if (phy) + queue_map[2].q = phy->mt76->q_tx[MT_TXQ_BE]; + seq_puts(file, " queue | hw-queued | head | tail |\n"); for (i = 0; i < ARRAY_SIZE(queue_map); i++) { struct mt76_queue *q = queue_map[i].q; @@ -785,20 +819,20 @@ mt7996_rf_regval_set(void *data, u64 val) DEFINE_DEBUGFS_ATTRIBUTE(fops_rf_regval, mt7996_rf_regval_get, mt7996_rf_regval_set, "0x%08llx\n"); -int mt7996_init_debugfs(struct mt7996_phy *phy) +int mt7996_init_debugfs(struct mt7996_dev *dev) { - struct mt7996_dev *dev = phy->dev; struct dentry *dir; - dir = mt76_register_debugfs_fops(phy->mt76, NULL); + dir = mt76_register_debugfs_fops(&dev->mphy, NULL); if (!dir) return -ENOMEM; - debugfs_create_file("hw-queues", 0400, dir, phy, + + debugfs_create_file("hw-queues", 0400, dir, dev, &mt7996_hw_queues_fops); - debugfs_create_file("xmit-queues", 0400, dir, phy, + debugfs_create_file("xmit-queues", 0400, dir, dev, &mt7996_xmit_queues_fops); - debugfs_create_file("tx_stats", 0400, dir, phy, &mt7996_tx_stats_fops); - debugfs_create_file("sys_recovery", 0600, dir, phy, + debugfs_create_file("tx_stats", 0400, dir, dev, &mt7996_tx_stats_fops); + debugfs_create_file("sys_recovery", 0600, dir, dev, &mt7996_sys_recovery_ops); debugfs_create_file("fw_debug_wm", 0600, dir, dev, &fops_fw_debug_wm); debugfs_create_file("fw_debug_wa", 0600, dir, dev, &fops_fw_debug_wa); @@ -812,17 +846,13 @@ int mt7996_init_debugfs(struct mt7996_phy *phy) mt7996_twt_stats); debugfs_create_file("rf_regval", 0600, dir, dev, &fops_rf_regval); - if (phy->mt76->cap.has_5ghz) { - debugfs_create_u32("dfs_hw_pattern", 0400, dir, - &dev->hw_pattern); - debugfs_create_file("radar_trigger", 0200, dir, dev, - &fops_radar_trigger); - debugfs_create_devm_seqfile(dev->mt76.dev, "rdd_monitor", dir, - mt7996_rdd_monitor); - } + debugfs_create_u32("dfs_hw_pattern", 0400, dir, &dev->hw_pattern); + debugfs_create_file("radar_trigger", 0200, dir, dev, + &fops_radar_trigger); + debugfs_create_devm_seqfile(dev->mt76.dev, "rdd_monitor", dir, + mt7996_rdd_monitor); - if (phy == &dev->phy) - dev->debugfs_dir = dir; + dev->debugfs_dir = dir; return 0; } @@ -899,7 +929,7 @@ static ssize_t mt7996_sta_fixed_rate_set(struct file *file, #define LONG_PREAMBLE 1 struct ieee80211_sta *sta = file->private_data; struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; - struct mt7996_dev *dev = msta->vif->phy->dev; + struct mt7996_dev *dev = msta->vif->deflink.phy->dev; struct ra_rate phy = {}; char buf[100]; int ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c index 4a8237118287..53dfac02f8af 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c @@ -25,17 +25,108 @@ static int mt7996_check_eeprom(struct mt7996_dev *dev) static char *mt7996_eeprom_name(struct mt7996_dev *dev) { switch (mt76_chip(&dev->mt76)) { - case 0x7990: - return MT7996_EEPROM_DEFAULT; case 0x7992: - return MT7992_EEPROM_DEFAULT; + switch (dev->var.type) { + case MT7992_VAR_TYPE_23: + if (dev->var.fem == MT7996_FEM_INT) + return MT7992_EEPROM_DEFAULT_23_INT; + return MT7992_EEPROM_DEFAULT_23; + case MT7992_VAR_TYPE_44: + default: + if (dev->var.fem == MT7996_FEM_INT) + return MT7992_EEPROM_DEFAULT_INT; + if (dev->var.fem == MT7996_FEM_MIX) + return MT7992_EEPROM_DEFAULT_MIX; + return MT7992_EEPROM_DEFAULT; + } + case 0x7990: default: - return MT7996_EEPROM_DEFAULT; + switch (dev->var.type) { + case MT7996_VAR_TYPE_233: + if (dev->var.fem == MT7996_FEM_INT) + return MT7996_EEPROM_DEFAULT_233_INT; + return MT7996_EEPROM_DEFAULT_233; + case MT7996_VAR_TYPE_444: + default: + if (dev->var.fem == MT7996_FEM_INT) + return MT7996_EEPROM_DEFAULT_INT; + return MT7996_EEPROM_DEFAULT; + } } } +static void +mt7996_eeprom_parse_stream(const u8 *eeprom, u8 band_idx, u8 *path, + u8 *rx_path, u8 *nss) +{ + switch (band_idx) { + case MT_BAND1: + *path = FIELD_GET(MT_EE_WIFI_CONF2_TX_PATH_BAND1, + eeprom[MT_EE_WIFI_CONF + 2]); + *rx_path = FIELD_GET(MT_EE_WIFI_CONF3_RX_PATH_BAND1, + eeprom[MT_EE_WIFI_CONF + 3]); + *nss = FIELD_GET(MT_EE_WIFI_CONF5_STREAM_NUM_BAND1, + eeprom[MT_EE_WIFI_CONF + 5]); + break; + case MT_BAND2: + *path = FIELD_GET(MT_EE_WIFI_CONF2_TX_PATH_BAND2, + eeprom[MT_EE_WIFI_CONF + 2]); + *rx_path = FIELD_GET(MT_EE_WIFI_CONF4_RX_PATH_BAND2, + eeprom[MT_EE_WIFI_CONF + 4]); + *nss = FIELD_GET(MT_EE_WIFI_CONF5_STREAM_NUM_BAND2, + eeprom[MT_EE_WIFI_CONF + 5]); + break; + default: + *path = FIELD_GET(MT_EE_WIFI_CONF1_TX_PATH_BAND0, + eeprom[MT_EE_WIFI_CONF + 1]); + *rx_path = FIELD_GET(MT_EE_WIFI_CONF3_RX_PATH_BAND0, + eeprom[MT_EE_WIFI_CONF + 3]); + *nss = FIELD_GET(MT_EE_WIFI_CONF4_STREAM_NUM_BAND0, + eeprom[MT_EE_WIFI_CONF + 4]); + break; + } +} + +static bool mt7996_eeprom_variant_valid(struct mt7996_dev *dev, const u8 *def) +{ +#define FEM_INT 0 +#define FEM_EXT 3 + u8 *eeprom = dev->mt76.eeprom.data, fem[2]; + int i; + + for (i = 0; i < 2; i++) + fem[i] = u8_get_bits(eeprom[MT_EE_WIFI_CONF + 6 + i], + MT_EE_WIFI_PA_LNA_CONFIG); + + if (dev->var.fem == MT7996_FEM_EXT && + !(fem[0] == FEM_EXT && fem[1] == FEM_EXT)) + return false; + else if (dev->var.fem == MT7996_FEM_INT && + !(fem[0] == FEM_INT && fem[1] == FEM_INT)) + return false; + else if (dev->var.fem == MT7996_FEM_MIX && + !(fem[0] == FEM_INT && fem[1] == FEM_EXT)) + return false; + + for (i = 0; i < __MT_MAX_BAND; i++) { + u8 path, rx_path, nss; + u8 def_path, def_rx_path, def_nss; + + if (!dev->mt76.phys[i]) + continue; + + mt7996_eeprom_parse_stream(eeprom, i, &path, &rx_path, &nss); + mt7996_eeprom_parse_stream(def, i, &def_path, &def_rx_path, + &def_nss); + if (path > def_path || rx_path > def_rx_path || nss > def_nss) + return false; + } + + return true; +} + static int -mt7996_eeprom_load_default(struct mt7996_dev *dev) +mt7996_eeprom_check_or_use_default(struct mt7996_dev *dev, bool use_default) { u8 *eeprom = dev->mt76.eeprom.data; const struct firmware *fw = NULL; @@ -51,6 +142,10 @@ mt7996_eeprom_load_default(struct mt7996_dev *dev) goto out; } + if (!use_default && mt7996_eeprom_variant_valid(dev, fw->data)) + goto out; + + dev_warn(dev->mt76.dev, "eeprom load fail, use default bin\n"); memcpy(eeprom, fw->data, MT7996_EEPROM_SIZE); dev->flash_mode = true; @@ -62,43 +157,68 @@ out: static int mt7996_eeprom_load(struct mt7996_dev *dev) { + bool use_default = false; int ret; ret = mt76_eeprom_init(&dev->mt76, MT7996_EEPROM_SIZE); if (ret < 0) return ret; - if (ret) { + if (ret && !mt7996_check_eeprom(dev)) { dev->flash_mode = true; - } else { - u8 free_block_num; - u32 block_num, i; - u32 eeprom_blk_size = MT7996_EEPROM_BLOCK_SIZE; + goto out; + } + if (!dev->flash_mode) { + u32 eeprom_blk_size = MT7996_EEPROM_BLOCK_SIZE; + u32 block_num = DIV_ROUND_UP(MT7996_EEPROM_SIZE, eeprom_blk_size); + u8 free_block_num; + int i; + + memset(dev->mt76.eeprom.data, 0, MT7996_EEPROM_SIZE); ret = mt7996_mcu_get_eeprom_free_block(dev, &free_block_num); if (ret < 0) return ret; /* efuse info isn't enough */ - if (free_block_num >= 59) - return -EINVAL; + if (free_block_num >= 59) { + use_default = true; + goto out; + } - /* read eeprom data from efuse */ - block_num = DIV_ROUND_UP(MT7996_EEPROM_SIZE, eeprom_blk_size); - for (i = 0; i < block_num; i++) { - ret = mt7996_mcu_get_eeprom(dev, i * eeprom_blk_size); - if (ret < 0) - return ret; + /* check if eeprom data from fw is valid */ + if (mt7996_mcu_get_eeprom(dev, 0, NULL, 0) || + mt7996_check_eeprom(dev)) { + use_default = true; + goto out; + } + + /* read eeprom data from fw */ + for (i = 1; i < block_num; i++) { + u32 len = eeprom_blk_size; + + if (i == block_num - 1) + len = MT7996_EEPROM_SIZE % eeprom_blk_size; + ret = mt7996_mcu_get_eeprom(dev, i * eeprom_blk_size, + NULL, len); + if (ret && ret != -EINVAL) { + use_default = true; + goto out; + } } } - return mt7996_check_eeprom(dev); +out: + return mt7996_eeprom_check_or_use_default(dev, use_default); } -static int mt7996_eeprom_parse_efuse_hw_cap(struct mt7996_dev *dev) +static int mt7996_eeprom_parse_efuse_hw_cap(struct mt7996_phy *phy, + u8 *path, u8 *rx_path, u8 *nss) { #define MODE_HE_ONLY BIT(0) #define WTBL_SIZE_GROUP GENMASK(31, 28) +#define STREAM_CAP(_offs) ((cap & (0x7 << (_offs))) >> (_offs)) + struct mt7996_dev *dev = phy->dev; u32 cap = 0; int ret; @@ -107,13 +227,17 @@ static int mt7996_eeprom_parse_efuse_hw_cap(struct mt7996_dev *dev) return ret; if (cap) { + u8 band_offs = phy->mt76->band_idx * 3; + dev->has_eht = !(cap & MODE_HE_ONLY); dev->wtbl_size_group = u32_get_bits(cap, WTBL_SIZE_GROUP); + *nss = min_t(u8, *nss, STREAM_CAP(1 + band_offs)); + *path = min_t(u8, *path, STREAM_CAP(10 + band_offs)); + *rx_path = min_t(u8, *rx_path, STREAM_CAP(19 + band_offs)); } - if (dev->wtbl_size_group < 2 || dev->wtbl_size_group > 4 || - is_mt7992(&dev->mt76)) - dev->wtbl_size_group = 2; /* set default */ + if (dev->wtbl_size_group < 2 || dev->wtbl_size_group > 4) + dev->wtbl_size_group = is_mt7996(&dev->mt76) ? 4 : 2; return 0; } @@ -163,32 +287,10 @@ int mt7996_eeprom_parse_hw_cap(struct mt7996_dev *dev, struct mt7996_phy *phy) int max_path = 5, max_nss = 4; int ret; - switch (band_idx) { - case MT_BAND1: - path = FIELD_GET(MT_EE_WIFI_CONF2_TX_PATH_BAND1, - eeprom[MT_EE_WIFI_CONF + 2]); - rx_path = FIELD_GET(MT_EE_WIFI_CONF3_RX_PATH_BAND1, - eeprom[MT_EE_WIFI_CONF + 3]); - nss = FIELD_GET(MT_EE_WIFI_CONF5_STREAM_NUM_BAND1, - eeprom[MT_EE_WIFI_CONF + 5]); - break; - case MT_BAND2: - path = FIELD_GET(MT_EE_WIFI_CONF2_TX_PATH_BAND2, - eeprom[MT_EE_WIFI_CONF + 2]); - rx_path = FIELD_GET(MT_EE_WIFI_CONF4_RX_PATH_BAND2, - eeprom[MT_EE_WIFI_CONF + 4]); - nss = FIELD_GET(MT_EE_WIFI_CONF5_STREAM_NUM_BAND2, - eeprom[MT_EE_WIFI_CONF + 5]); - break; - default: - path = FIELD_GET(MT_EE_WIFI_CONF1_TX_PATH_BAND0, - eeprom[MT_EE_WIFI_CONF + 1]); - rx_path = FIELD_GET(MT_EE_WIFI_CONF3_RX_PATH_BAND0, - eeprom[MT_EE_WIFI_CONF + 3]); - nss = FIELD_GET(MT_EE_WIFI_CONF4_STREAM_NUM_BAND0, - eeprom[MT_EE_WIFI_CONF + 4]); - break; - } + mt7996_eeprom_parse_stream(eeprom, band_idx, &path, &rx_path, &nss); + ret = mt7996_eeprom_parse_efuse_hw_cap(phy, &path, &rx_path, &nss); + if (ret) + return ret; if (!path || path > max_path) path = max_path; @@ -203,15 +305,12 @@ int mt7996_eeprom_parse_hw_cap(struct mt7996_dev *dev, struct mt7996_phy *phy) mphy->antenna_mask = BIT(nss) - 1; mphy->chainmask = (BIT(path) - 1) << dev->chainshift[band_idx]; + phy->orig_chainmask = mphy->chainmask; dev->chainmask |= mphy->chainmask; if (band_idx < MT_BAND2) dev->chainshift[band_idx + 1] = dev->chainshift[band_idx] + hweight16(mphy->chainmask); - ret = mt7996_eeprom_parse_efuse_hw_cap(dev); - if (ret) - return ret; - return mt7996_eeprom_parse_band_config(phy); } @@ -220,15 +319,8 @@ int mt7996_eeprom_init(struct mt7996_dev *dev) int ret; ret = mt7996_eeprom_load(dev); - if (ret < 0) { - if (ret != -EINVAL) - return ret; - - dev_warn(dev->mt76.dev, "eeprom load fail, use default bin\n"); - ret = mt7996_eeprom_load_default(dev); - if (ret) - return ret; - } + if (ret < 0) + return ret; ret = mt7996_eeprom_parse_hw_cap(dev, &dev->phy); if (ret < 0) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.h index 412d6e2f8014..7a771ca2434c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.h @@ -40,6 +40,8 @@ enum mt7996_eeprom_field { #define MT_EE_WIFI_CONF5_STREAM_NUM_BAND1 GENMASK(2, 0) #define MT_EE_WIFI_CONF5_STREAM_NUM_BAND2 GENMASK(5, 3) +#define MT_EE_WIFI_PA_LNA_CONFIG GENMASK(1, 0) + #define MT_EE_RATE_DELTA_MASK GENMASK(5, 0) #define MT_EE_RATE_DELTA_SIGN BIT(6) #define MT_EE_RATE_DELTA_EN BIT(7) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c index 5e96973226bb..6b660424aedc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c @@ -14,11 +14,30 @@ #include "coredump.h" #include "eeprom.h" +static const struct ieee80211_iface_limit if_limits_global = { + .max = MT7996_MAX_INTERFACES * MT7996_MAX_RADIOS, + .types = BIT(NL80211_IFTYPE_STATION) + | BIT(NL80211_IFTYPE_ADHOC) + | BIT(NL80211_IFTYPE_AP) +#ifdef CONFIG_MAC80211_MESH + | BIT(NL80211_IFTYPE_MESH_POINT) +#endif +}; + +static const struct ieee80211_iface_combination if_comb_global = { + .limits = &if_limits_global, + .n_limits = 1, + .max_interfaces = MT7996_MAX_INTERFACES * MT7996_MAX_RADIOS, + .num_different_channels = MT7996_MAX_RADIOS, + .radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) | + BIT(NL80211_CHAN_WIDTH_20) | + BIT(NL80211_CHAN_WIDTH_40) | + BIT(NL80211_CHAN_WIDTH_80) | + BIT(NL80211_CHAN_WIDTH_160), +}; + static const struct ieee80211_iface_limit if_limits[] = { { - .max = 1, - .types = BIT(NL80211_IFTYPE_ADHOC) - }, { .max = 16, .types = BIT(NL80211_IFTYPE_AP) #ifdef CONFIG_MAC80211_MESH @@ -30,20 +49,18 @@ static const struct ieee80211_iface_limit if_limits[] = { } }; -static const struct ieee80211_iface_combination if_comb[] = { - { - .limits = if_limits, - .n_limits = ARRAY_SIZE(if_limits), - .max_interfaces = MT7996_MAX_INTERFACES, - .num_different_channels = 1, - .beacon_int_infra_match = true, - .radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) | - BIT(NL80211_CHAN_WIDTH_20) | - BIT(NL80211_CHAN_WIDTH_40) | - BIT(NL80211_CHAN_WIDTH_80) | - BIT(NL80211_CHAN_WIDTH_160), - .beacon_int_min_gcd = 100, - } +static const struct ieee80211_iface_combination if_comb = { + .limits = if_limits, + .n_limits = ARRAY_SIZE(if_limits), + .max_interfaces = MT7996_MAX_INTERFACES, + .num_different_channels = 1, + .beacon_int_infra_match = true, + .radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) | + BIT(NL80211_CHAN_WIDTH_20) | + BIT(NL80211_CHAN_WIDTH_40) | + BIT(NL80211_CHAN_WIDTH_80) | + BIT(NL80211_CHAN_WIDTH_160), + .beacon_int_min_gcd = 100, }; static ssize_t mt7996_thermal_temp_show(struct device *dev, @@ -85,7 +102,7 @@ static ssize_t mt7996_thermal_temp_store(struct device *dev, return ret; mutex_lock(&phy->dev->mt76.mutex); - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 40, 130); + val = DIV_ROUND_CLOSEST(clamp_val(val, 40 * 1000, 130 * 1000), 1000); /* add a safety margin ~10 */ if ((i - 1 == MT7996_CRIT_TEMP_IDX && @@ -180,28 +197,32 @@ static const struct thermal_cooling_device_ops mt7996_thermal_ops = { static void mt7996_unregister_thermal(struct mt7996_phy *phy) { struct wiphy *wiphy = phy->mt76->hw->wiphy; + char name[sizeof("cooling_deviceXXX")]; if (!phy->cdev) return; - sysfs_remove_link(&wiphy->dev.kobj, "cooling_device"); + snprintf(name, sizeof(name), "cooling_device%d", phy->mt76->band_idx); + sysfs_remove_link(&wiphy->dev.kobj, name); thermal_cooling_device_unregister(phy->cdev); } static int mt7996_thermal_init(struct mt7996_phy *phy) { struct wiphy *wiphy = phy->mt76->hw->wiphy; + char cname[sizeof("cooling_deviceXXX")]; struct thermal_cooling_device *cdev; struct device *hwmon; const char *name; - name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7996_%s", - wiphy_name(wiphy)); + name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7996_%s.%d", + wiphy_name(wiphy), phy->mt76->band_idx); + snprintf(cname, sizeof(cname), "cooling_device%d", phy->mt76->band_idx); cdev = thermal_cooling_device_register(name, phy, &mt7996_thermal_ops); if (!IS_ERR(cdev)) { if (sysfs_create_link(&wiphy->dev.kobj, &cdev->device.kobj, - "cooling_device") < 0) + cname) < 0) thermal_cooling_device_unregister(cdev); else phy->cdev = cdev; @@ -333,28 +354,88 @@ mt7996_regd_notifier(struct wiphy *wiphy, { struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy); struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); + struct mt7996_phy *phy; memcpy(dev->mt76.alpha2, request->alpha2, sizeof(dev->mt76.alpha2)); dev->mt76.region = request->dfs_region; - if (dev->mt76.region == NL80211_DFS_UNSET) - mt7996_mcu_rdd_background_enable(phy, NULL); + mt7996_for_each_phy(dev, phy) { + if (dev->mt76.region == NL80211_DFS_UNSET) + mt7996_mcu_rdd_background_enable(phy, NULL); + mt7996_init_txpower(phy); + phy->mt76->dfs_state = MT_DFS_STATE_UNKNOWN; + mt7996_dfs_init_radar_detector(phy); + } +} + +static void +mt7996_init_wiphy_band(struct ieee80211_hw *hw, struct mt7996_phy *phy) +{ + struct mt7996_dev *dev = phy->dev; + struct wiphy *wiphy = hw->wiphy; + int n_radios = hw->wiphy->n_radio; + struct wiphy_radio_freq_range *freq = &dev->radio_freqs[n_radios]; + struct wiphy_radio *radio = &dev->radios[n_radios]; + + phy->slottime = 9; + phy->beacon_rate = -1; + + if (phy->mt76->cap.has_2ghz) { + phy->mt76->sband_2g.sband.ht_cap.cap |= + IEEE80211_HT_CAP_LDPC_CODING | + IEEE80211_HT_CAP_MAX_AMSDU; + phy->mt76->sband_2g.sband.ht_cap.ampdu_density = + IEEE80211_HT_MPDU_DENSITY_2; + freq->start_freq = 2400000; + freq->end_freq = 2500000; + } else if (phy->mt76->cap.has_5ghz) { + phy->mt76->sband_5g.sband.ht_cap.cap |= + IEEE80211_HT_CAP_LDPC_CODING | + IEEE80211_HT_CAP_MAX_AMSDU; + + phy->mt76->sband_5g.sband.vht_cap.cap |= + IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | + IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK | + IEEE80211_VHT_CAP_SHORT_GI_160 | + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ; + phy->mt76->sband_5g.sband.ht_cap.ampdu_density = + IEEE80211_HT_MPDU_DENSITY_1; + + ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); + freq->start_freq = 5000000; + freq->end_freq = 5900000; + } else if (phy->mt76->cap.has_6ghz) { + freq->start_freq = 5900000; + freq->end_freq = 7200000; + } else { + return; + } + + dev->radio_phy[n_radios] = phy; + radio->freq_range = freq; + radio->n_freq_range = 1; + radio->iface_combinations = &if_comb; + radio->n_iface_combinations = 1; + hw->wiphy->n_radio++; + + wiphy->available_antennas_rx |= phy->mt76->chainmask; + wiphy->available_antennas_tx |= phy->mt76->chainmask; + + mt76_set_stream_caps(phy->mt76, true); + mt7996_set_stream_vht_txbf_caps(phy); + mt7996_set_stream_he_eht_caps(phy); mt7996_init_txpower(phy); - - phy->mt76->dfs_state = MT_DFS_STATE_UNKNOWN; - mt7996_dfs_init_radar_detector(phy); } static void mt7996_init_wiphy(struct ieee80211_hw *hw, struct mtk_wed_device *wed) { - struct mt7996_phy *phy = mt7996_hw_phy(hw); - struct mt76_dev *mdev = &phy->dev->mt76; + struct mt7996_dev *dev = mt7996_hw_dev(hw); + struct mt76_dev *mdev = &dev->mt76; struct wiphy *wiphy = hw->wiphy; - u16 max_subframes = phy->dev->has_eht ? IEEE80211_MAX_AMPDU_BUF_EHT : - IEEE80211_MAX_AMPDU_BUF_HE; + u16 max_subframes = dev->has_eht ? IEEE80211_MAX_AMPDU_BUF_EHT : + IEEE80211_MAX_AMPDU_BUF_HE; hw->queues = 4; hw->max_rx_aggregation_subframes = max_subframes; @@ -366,14 +447,15 @@ mt7996_init_wiphy(struct ieee80211_hw *hw, struct mtk_wed_device *wed) hw->radiotap_timestamp.units_pos = IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US; - phy->slottime = 9; - phy->beacon_rate = -1; - hw->sta_data_size = sizeof(struct mt7996_sta); hw->vif_data_size = sizeof(struct mt7996_vif); + hw->chanctx_data_size = sizeof(struct mt76_chanctx); + + wiphy->iface_combinations = &if_comb_global; + wiphy->n_iface_combinations = 1; + + wiphy->radio = dev->radios; - wiphy->iface_combinations = if_comb; - wiphy->n_iface_combinations = ARRAY_SIZE(if_comb); wiphy->reg_notifier = mt7996_regd_notifier; wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH; wiphy->mbssid_max_interfaces = 16; @@ -390,57 +472,31 @@ mt7996_init_wiphy(struct ieee80211_hw *hw, struct mtk_wed_device *wed) wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER); - if (!mdev->dev->of_node || - !of_property_read_bool(mdev->dev->of_node, - "mediatek,disable-radar-background")) + if (mt7996_has_background_radar(dev) && + (!mdev->dev->of_node || + !of_property_read_bool(mdev->dev->of_node, + "mediatek,disable-radar-background"))) wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_RADAR_BACKGROUND); ieee80211_hw_set(hw, HAS_RATE_CONTROL); ieee80211_hw_set(hw, SUPPORTS_TX_ENCAP_OFFLOAD); ieee80211_hw_set(hw, SUPPORTS_RX_DECAP_OFFLOAD); - ieee80211_hw_set(hw, WANT_MONITOR_VIF); + ieee80211_hw_set(hw, NO_VIRTUAL_MONITOR); ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); hw->max_tx_fragments = 4; - if (phy->mt76->cap.has_2ghz) { - phy->mt76->sband_2g.sband.ht_cap.cap |= - IEEE80211_HT_CAP_LDPC_CODING | - IEEE80211_HT_CAP_MAX_AMSDU; - phy->mt76->sband_2g.sband.ht_cap.ampdu_density = - IEEE80211_HT_MPDU_DENSITY_2; - } - - if (phy->mt76->cap.has_5ghz) { - phy->mt76->sband_5g.sband.ht_cap.cap |= - IEEE80211_HT_CAP_LDPC_CODING | - IEEE80211_HT_CAP_MAX_AMSDU; - - phy->mt76->sband_5g.sband.vht_cap.cap |= - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | - IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK | - IEEE80211_VHT_CAP_SHORT_GI_160 | - IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ; - phy->mt76->sband_5g.sband.ht_cap.ampdu_density = - IEEE80211_HT_MPDU_DENSITY_1; - - ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); - } - /* init led callbacks */ if (IS_ENABLED(CONFIG_MT76_LEDS)) { - phy->mt76->leds.cdev.brightness_set = mt7996_led_set_brightness; - phy->mt76->leds.cdev.blink_set = mt7996_led_set_blink; + dev->mphy.leds.cdev.brightness_set = mt7996_led_set_brightness; + dev->mphy.leds.cdev.blink_set = mt7996_led_set_blink; } - mt76_set_stream_caps(phy->mt76, true); - mt7996_set_stream_vht_txbf_caps(phy); - mt7996_set_stream_he_eht_caps(phy); - mt7996_init_txpower(phy); + wiphy->max_scan_ssids = 4; + wiphy->max_scan_ie_len = IEEE80211_MAX_DATA_LEN; - wiphy->available_antennas_rx = phy->mt76->antenna_mask; - wiphy->available_antennas_tx = phy->mt76->antenna_mask; + mt7996_init_wiphy_band(hw, &dev->phy); } static void @@ -459,6 +515,10 @@ mt7996_mac_init_band(struct mt7996_dev *dev, u8 band) mt76_clear(dev, MT_WF_RMAC_MIB_AIRTIME4(band), MT_WF_RMAC_MIB_QOS23_BACKOFF); + /* clear backoff time for Tx duration */ + mt76_clear(dev, MT_WTBLOFF_ACR(band), + MT_WTBLOFF_ADM_BACKOFFTIME); + /* clear backoff time and set software compensation for OBSS time */ mask = MT_WF_RMAC_MIB_OBSS_BACKOFF | MT_WF_RMAC_MIB_ED_OFFSET; set = FIELD_PREP(MT_WF_RMAC_MIB_OBSS_BACKOFF, 0) | @@ -557,18 +617,15 @@ int mt7996_txbf_init(struct mt7996_dev *dev) return mt7996_mcu_set_txbf(dev, BF_HW_EN_UPDATE); } -static int mt7996_register_phy(struct mt7996_dev *dev, struct mt7996_phy *phy, - enum mt76_band_id band) +static int mt7996_register_phy(struct mt7996_dev *dev, enum mt76_band_id band) { + struct mt7996_phy *phy; struct mt76_phy *mphy; u32 mac_ofs, hif1_ofs = 0; int ret; struct mtk_wed_device *wed = &dev->mt76.mmio.wed; - if (!mt7996_band_valid(dev, band) || band == MT_BAND0) - return 0; - - if (phy) + if (!mt7996_band_valid(dev, band)) return 0; if (is_mt7996(&dev->mt76) && band == MT_BAND2 && dev->hif2) { @@ -576,7 +633,7 @@ static int mt7996_register_phy(struct mt7996_dev *dev, struct mt7996_phy *phy, wed = &dev->mt76.mmio.wed_hif2; } - mphy = mt76_alloc_phy(&dev->mt76, sizeof(*phy), &mt7996_ops, band); + mphy = mt76_alloc_radio_phy(&dev->mt76, sizeof(*phy), band); if (!mphy) return -ENOMEM; @@ -607,7 +664,7 @@ static int mt7996_register_phy(struct mt7996_dev *dev, struct mt7996_phy *phy, mt76_eeprom_override(mphy); /* init wiphy according to mphy and phy */ - mt7996_init_wiphy(mphy->hw, wed); + mt7996_init_wiphy_band(mphy->hw, phy); ret = mt7996_init_tx_queues(mphy->priv, MT_TXQ_ID(band), MT7996_TX_RING_SIZE, @@ -621,14 +678,6 @@ static int mt7996_register_phy(struct mt7996_dev *dev, struct mt7996_phy *phy, if (ret) goto error; - ret = mt7996_thermal_init(phy); - if (ret) - goto error; - - ret = mt7996_init_debugfs(phy); - if (ret) - goto error; - if (wed == &dev->mt76.mmio.wed_hif2 && mtk_wed_device_active(wed)) { u32 irq_mask = dev->mt76.mmio.irqmask | MT_INT_TX_DONE_BAND2; @@ -640,24 +689,14 @@ static int mt7996_register_phy(struct mt7996_dev *dev, struct mt7996_phy *phy, error: mphy->dev->phys[band] = NULL; - ieee80211_free_hw(mphy->hw); return ret; } static void -mt7996_unregister_phy(struct mt7996_phy *phy, enum mt76_band_id band) +mt7996_unregister_phy(struct mt7996_phy *phy) { - struct mt76_phy *mphy; - - if (!phy) - return; - - mt7996_unregister_thermal(phy); - - mphy = phy->dev->mt76.phys[band]; - mt76_unregister_phy(mphy); - ieee80211_free_hw(mphy->hw); - phy->dev->mt76.phys[band] = NULL; + if (phy) + mt7996_unregister_thermal(phy); } static void mt7996_init_work(struct work_struct *work) @@ -884,6 +923,76 @@ out: #endif } +static int mt7996_variant_type_init(struct mt7996_dev *dev) +{ + u32 val = mt76_rr(dev, MT_PAD_GPIO); + u8 var_type; + + switch (mt76_chip(&dev->mt76)) { + case 0x7990: + if (val & MT_PAD_GPIO_2ADIE_TBTC) + var_type = MT7996_VAR_TYPE_233; + else + var_type = MT7996_VAR_TYPE_444; + break; + case 0x7992: + if (val & MT_PAD_GPIO_ADIE_SINGLE) + var_type = MT7992_VAR_TYPE_23; + else if (u32_get_bits(val, MT_PAD_GPIO_ADIE_COMB_7992)) + var_type = MT7992_VAR_TYPE_44; + else + return -EINVAL; + break; + default: + return -EINVAL; + } + + dev->var.type = var_type; + return 0; +} + +static int mt7996_variant_fem_init(struct mt7996_dev *dev) +{ +#define MT7976C_EFUSE_OFFSET 0x470 + u8 buf[MT7996_EEPROM_BLOCK_SIZE], idx, adie_idx, adie_comb; + u32 regval, val = mt76_rr(dev, MT_PAD_GPIO); + u16 adie_id, adie_ver; + bool is_7976c; + int ret; + + if (is_mt7992(&dev->mt76)) { + adie_idx = (val & MT_PAD_GPIO_ADIE_SINGLE) ? 0 : 1; + adie_comb = u32_get_bits(val, MT_PAD_GPIO_ADIE_COMB_7992); + } else { + adie_idx = 0; + adie_comb = u32_get_bits(val, MT_PAD_GPIO_ADIE_COMB); + } + + ret = mt7996_mcu_rf_regval(dev, MT_ADIE_CHIP_ID(adie_idx), ®val, false); + if (ret) + return ret; + + ret = mt7996_mcu_get_eeprom(dev, MT7976C_EFUSE_OFFSET, buf, sizeof(buf)); + if (ret && ret != -EINVAL) + return ret; + + adie_ver = u32_get_bits(regval, MT_ADIE_VERSION_MASK); + idx = MT7976C_EFUSE_OFFSET % MT7996_EEPROM_BLOCK_SIZE; + is_7976c = adie_ver == 0x8a10 || adie_ver == 0x8b00 || + adie_ver == 0x8c10 || buf[idx] == 0xc; + + adie_id = u32_get_bits(regval, MT_ADIE_CHIP_ID_MASK); + if (adie_id == 0x7975 || adie_id == 0x7979 || + (adie_id == 0x7976 && is_7976c)) + dev->var.fem = MT7996_FEM_INT; + else if (adie_id == 0x7977 && adie_comb == 1) + dev->var.fem = MT7996_FEM_MIX; + else + dev->var.fem = MT7996_FEM_EXT; + + return 0; +} + static int mt7996_init_hardware(struct mt7996_dev *dev) { int ret, idx; @@ -899,6 +1008,10 @@ static int mt7996_init_hardware(struct mt7996_dev *dev) INIT_LIST_HEAD(&dev->wed_rro.poll_list); spin_lock_init(&dev->wed_rro.lock); + ret = mt7996_variant_type_init(dev); + if (ret) + return ret; + ret = mt7996_dma_init(dev); if (ret) return ret; @@ -913,6 +1026,10 @@ static int mt7996_init_hardware(struct mt7996_dev *dev) if (ret) return ret; + ret = mt7996_variant_fem_init(dev); + if (ret) + return ret; + ret = mt7996_eeprom_init(dev); if (ret < 0) return ret; @@ -963,10 +1080,12 @@ void mt7996_set_stream_vht_txbf_caps(struct mt7996_phy *phy) static void mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy, - struct ieee80211_sta_he_cap *he_cap, int vif) + struct ieee80211_sta_he_cap *he_cap, int vif, + enum nl80211_band band) { struct ieee80211_he_cap_elem *elem = &he_cap->he_cap_elem; int sts = hweight16(phy->mt76->chainmask); + bool non_2g = band != NL80211_BAND_2GHZ; u8 c; #ifdef CONFIG_MAC80211_MESH @@ -996,10 +1115,10 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy, if (is_mt7996(phy->mt76->dev)) c |= IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 | - IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4; + (IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 * non_2g); else c |= IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 | - IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5; + (IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 * non_2g); elem->phy_cap_info[4] |= c; @@ -1025,8 +1144,9 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy, c = FIELD_PREP(IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK, sts - 1) | - FIELD_PREP(IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK, - sts - 1); + (FIELD_PREP(IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK, + sts - 1) * non_2g); + elem->phy_cap_info[5] |= c; if (vif != NL80211_IFTYPE_AP) @@ -1038,8 +1158,10 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy, IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB; elem->phy_cap_info[6] |= c; - c = IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ | - IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ; + c = 0; + if (non_2g) + c |= IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ | + IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ; elem->phy_cap_info[7] |= c; } @@ -1080,6 +1202,9 @@ mt7996_init_he_caps(struct mt7996_phy *phy, enum nl80211_band band, he_cap_elem->phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ; + he_cap_elem->phy_cap_info[7] = + IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI; + switch (iftype) { case NL80211_IFTYPE_AP: he_cap_elem->mac_cap_info[0] |= IEEE80211_HE_MAC_CAP0_TWT_RES; @@ -1119,8 +1244,7 @@ mt7996_init_he_caps(struct mt7996_phy *phy, enum nl80211_band band, IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE | IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT; he_cap_elem->phy_cap_info[7] |= - IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP | - IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI; + IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP; he_cap_elem->phy_cap_info[8] |= IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G | IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU | @@ -1143,12 +1267,12 @@ mt7996_init_he_caps(struct mt7996_phy *phy, enum nl80211_band band, he_mcs->rx_mcs_160 = cpu_to_le16(mcs_map); he_mcs->tx_mcs_160 = cpu_to_le16(mcs_map); - mt7996_set_stream_he_txbf_caps(phy, he_cap, iftype); + mt7996_set_stream_he_txbf_caps(phy, he_cap, iftype, band); memset(he_cap->ppe_thres, 0, sizeof(he_cap->ppe_thres)); if (he_cap_elem->phy_cap_info[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { - mt76_connac_gen_ppe_thresh(he_cap->ppe_thres, nss); + mt76_connac_gen_ppe_thresh(he_cap->ppe_thres, nss, band); } else { he_cap_elem->phy_cap_info[9] |= u8_encode_bits(IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US, @@ -1190,7 +1314,9 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band, eht_cap_elem->mac_cap_info[0] = IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS | - IEEE80211_EHT_MAC_CAP0_OM_CONTROL; + IEEE80211_EHT_MAC_CAP0_OM_CONTROL | + u8_encode_bits(IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454, + IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK); eht_cap_elem->phy_cap_info[0] = IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI | @@ -1205,13 +1331,20 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band, eht_cap_elem->phy_cap_info[1] = u8_encode_bits(u8_get_bits(val, GENMASK(2, 1)), - IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK) | - u8_encode_bits(val, - IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK); + IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK); eht_cap_elem->phy_cap_info[2] = - u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK) | - u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK); + u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK); + + if (band != NL80211_BAND_2GHZ) { + eht_cap_elem->phy_cap_info[1] |= + u8_encode_bits(val, + IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK); + + eht_cap_elem->phy_cap_info[2] |= + u8_encode_bits(sts - 1, + IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK); + } if (band == NL80211_BAND_6GHZ) { eht_cap_elem->phy_cap_info[0] |= @@ -1233,21 +1366,20 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band, IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK; eht_cap_elem->phy_cap_info[4] = + IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI | u8_encode_bits(min_t(int, sts - 1, 2), IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK); eht_cap_elem->phy_cap_info[5] = u8_encode_bits(IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US, IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK) | - u8_encode_bits(u8_get_bits(0x11, GENMASK(1, 0)), + u8_encode_bits(u8_get_bits(1, GENMASK(1, 0)), IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK); val = width == NL80211_CHAN_WIDTH_320 ? 0xf : width == NL80211_CHAN_WIDTH_160 ? 0x7 : width == NL80211_CHAN_WIDTH_80 ? 0x3 : 0x1; eht_cap_elem->phy_cap_info[6] = - u8_encode_bits(u8_get_bits(0x11, GENMASK(4, 2)), - IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK) | u8_encode_bits(val, IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK); val = u8_encode_bits(nss, IEEE80211_EHT_MCS_NSS_RX) | @@ -1273,8 +1405,13 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band, eht_cap_elem->phy_cap_info[7] = IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ | + IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ; + + if (band == NL80211_BAND_2GHZ) + return; + + eht_cap_elem->phy_cap_info[7] |= IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ | - IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ; if (band != NL80211_BAND_6GHZ) @@ -1333,6 +1470,7 @@ void mt7996_set_stream_he_eht_caps(struct mt7996_phy *phy) int mt7996_register_device(struct mt7996_dev *dev) { struct ieee80211_hw *hw = mt76_hw(dev); + struct mt7996_phy *phy; int ret; dev->phy.dev = dev; @@ -1354,28 +1492,27 @@ int mt7996_register_device(struct mt7996_dev *dev) mt7996_init_wiphy(hw, &dev->mt76.mmio.wed); + ret = mt7996_register_phy(dev, MT_BAND1); + if (ret) + return ret; + + ret = mt7996_register_phy(dev, MT_BAND2); + if (ret) + return ret; + ret = mt76_register_device(&dev->mt76, true, mt76_rates, ARRAY_SIZE(mt76_rates)); if (ret) return ret; - ret = mt7996_thermal_init(&dev->phy); - if (ret) - return ret; - - ret = mt7996_register_phy(dev, mt7996_phy2(dev), MT_BAND1); - if (ret) - return ret; - - ret = mt7996_register_phy(dev, mt7996_phy3(dev), MT_BAND2); - if (ret) - return ret; + mt7996_for_each_phy(dev, phy) + mt7996_thermal_init(phy); ieee80211_queue_work(mt76_hw(dev), &dev->init_work); dev->recovery.hw_init_done = true; - ret = mt7996_init_debugfs(&dev->phy); + ret = mt7996_init_debugfs(dev); if (ret) goto error; @@ -1394,8 +1531,8 @@ error: void mt7996_unregister_device(struct mt7996_dev *dev) { cancel_work_sync(&dev->wed_rro.work); - mt7996_unregister_phy(mt7996_phy3(dev), MT_BAND2); - mt7996_unregister_phy(mt7996_phy2(dev), MT_BAND1); + mt7996_unregister_phy(mt7996_phy3(dev)); + mt7996_unregister_phy(mt7996_phy2(dev)); mt7996_unregister_thermal(&dev->phy); mt7996_coredump_unregister(dev); mt76_unregister_device(&dev->mt76); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 0d21414e2c88..019c925ae600 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -72,7 +72,7 @@ static struct mt76_wcid *mt7996_rx_get_wcid(struct mt7996_dev *dev, if (!sta->vif) return NULL; - return &sta->vif->sta.wcid; + return &sta->vif->deflink.sta.wcid; } bool mt7996_mac_wtbl_update(struct mt7996_dev *dev, int idx, u32 mask) @@ -182,7 +182,7 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev) rssi[3] = to_rssi(GENMASK(31, 14), val); msta->ack_signal = - mt76_rx_signal(msta->vif->phy->mt76->antenna_mask, rssi); + mt76_rx_signal(msta->vif->deflink.phy->mt76->antenna_mask, rssi); ewma_avg_signal_add(&msta->avg_ack_signal, -msta->ack_signal); } @@ -196,7 +196,7 @@ void mt7996_mac_enable_rtscts(struct mt7996_dev *dev, struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; u32 addr; - addr = mt7996_mac_wtbl_lmac_addr(dev, mvif->sta.wcid.idx, 5); + addr = mt7996_mac_wtbl_lmac_addr(dev, mvif->deflink.sta.wcid.idx, 5); if (enable) mt76_set(dev, addr, BIT(5)); else @@ -478,11 +478,7 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q, if (status->wcid) { msta = container_of(status->wcid, struct mt7996_sta, wcid); - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&msta->wcid.poll_list)) - list_add_tail(&msta->wcid.poll_list, - &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &msta->wcid); } status->freq = mphy->chandef.chan->center_freq; @@ -679,14 +675,25 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q, if (ieee80211_has_a4(fc) && is_mesh && status->amsdu) *qos &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT; } + skb_set_mac_header(skb, (unsigned char *)hdr - skb->data); } else { status->flag |= RX_FLAG_8023; mt7996_wed_check_ppe(dev, &dev->mt76.q_rx[q], msta, skb, *info); } - if (rxv && mode >= MT_PHY_TYPE_HE_SU && !(status->flag & RX_FLAG_8023)) - mt76_connac3_mac_decode_he_radiotap(skb, rxv, mode); + if (rxv && !(status->flag & RX_FLAG_8023)) { + switch (status->encoding) { + case RX_ENC_EHT: + mt76_connac3_mac_decode_eht_radiotap(skb, rxv, mode); + break; + case RX_ENC_HE: + mt76_connac3_mac_decode_he_radiotap(skb, rxv, mode); + break; + default: + break; + } + } if (!status->wcid || !ieee80211_is_data_qos(fc) || hw_aggr) return 0; @@ -819,12 +826,13 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, struct ieee80211_key_conf *key, int pid, enum mt76_txq_id qid, u32 changed) { + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_vif *vif = info->control.vif; u8 band_idx = (info->hw_queue & MT_TX_HW_QUEUE_PHY) >> 2; u8 p_fmt, q_idx, omac_idx = 0, wmm_idx = 0; bool is_8023 = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP; - struct mt76_vif *mvif; + struct mt76_vif_link *mvif; u16 tx_count = 15; u32 val; bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP | @@ -832,7 +840,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, bool beacon = !!(changed & (BSS_CHANGED_BEACON | BSS_CHANGED_BEACON_ENABLED)) && (!inband_disc); - mvif = vif ? (struct mt76_vif *)vif->drv_priv : NULL; + mvif = vif ? (struct mt76_vif_link *)vif->drv_priv : NULL; if (mvif) { omac_idx = mvif->omac_idx; wmm_idx = mvif->wmm_idx; @@ -886,8 +894,9 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, val = MT_TXD6_DIS_MAT | MT_TXD6_DAS; if (is_mt7996(&dev->mt76)) val |= FIELD_PREP(MT_TXD6_MSDU_CNT, 1); - else + else if (is_8023 || !ieee80211_is_mgmt(hdr->frame_control)) val |= FIELD_PREP(MT_TXD6_MSDU_CNT_V2, 1); + txwi[6] = cpu_to_le32(val); txwi[7] = 0; @@ -897,7 +906,6 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, mt7996_mac_write_txwi_80211(dev, txwi, skb, key); if (txwi[1] & cpu_to_le32(MT_TXD1_FIXED_RATE)) { - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; bool mcast = ieee80211_is_data(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1); u8 idx = MT7996_BASIC_RATES_TBL; @@ -977,7 +985,7 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (vif) { struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - txp->fw.bss_idx = mvif->mt76.idx; + txp->fw.bss_idx = mvif->deflink.mt76.idx; } txp->fw.token = cpu_to_le16(id); @@ -1138,11 +1146,7 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len) continue; msta = container_of(wcid, struct mt7996_sta, wcid); - spin_lock_bh(&mdev->sta_poll_lock); - if (list_empty(&msta->wcid.poll_list)) - list_add_tail(&msta->wcid.poll_list, - &mdev->sta_poll_list); - spin_unlock_bh(&mdev->sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &msta->wcid); continue; } else if (info & MT_TXFREE_INFO_HEADER) { u32 tx_retries = 0, tx_failed = 0; @@ -1368,10 +1372,7 @@ static void mt7996_mac_add_txs(struct mt7996_dev *dev, void *data) if (!wcid->sta) goto out; - spin_lock_bh(&dev->mt76.sta_poll_lock); - if (list_empty(&msta->wcid.poll_list)) - list_add_tail(&msta->wcid.poll_list, &dev->mt76.sta_poll_list); - spin_unlock_bh(&dev->mt76.sta_poll_lock); + mt76_wcid_add_poll(&dev->mt76, &msta->wcid); out: rcu_read_unlock(); @@ -1593,7 +1594,7 @@ mt7996_update_vif_beacon(void *priv, u8 *mac, struct ieee80211_vif *vif) case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_AP: - mt7996_mcu_add_beacon(hw, vif, vif->bss_conf.enable_beacon); + mt7996_mcu_add_beacon(hw, vif, &vif->bss_conf); break; default: break; @@ -1694,7 +1695,6 @@ mt7996_mac_restart(struct mt7996_dev *dev) mt7996_dma_reset(dev, true); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { if (mtk_wed_device_active(&dev->mt76.mmio.wed) && mt76_queue_is_wed_rro(&mdev->q_rx[i])) @@ -1702,10 +1702,11 @@ mt7996_mac_restart(struct mt7996_dev *dev) if (mdev->q_rx[i].ndesc) { napi_enable(&dev->mt76.napi[i]); + local_bh_disable(); napi_schedule(&dev->mt76.napi[i]); + local_bh_enable(); } } - local_bh_enable(); clear_bit(MT76_MCU_RESET, &dev->mphy.state); clear_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); @@ -1738,19 +1739,19 @@ mt7996_mac_restart(struct mt7996_dev *dev) ret = mt7996_txbf_init(dev); if (test_bit(MT76_STATE_RUNNING, &dev->mphy.state)) { - ret = mt7996_run(dev->mphy.hw); + ret = mt7996_run(&dev->phy); if (ret) goto out; } if (phy2 && test_bit(MT76_STATE_RUNNING, &phy2->mt76->state)) { - ret = mt7996_run(phy2->mt76->hw); + ret = mt7996_run(phy2); if (ret) goto out; } if (phy3 && test_bit(MT76_STATE_RUNNING, &phy3->mt76->state)) { - ret = mt7996_run(phy3->mt76->hw); + ret = mt7996_run(phy3); if (ret) goto out; } @@ -1763,8 +1764,8 @@ out: if (phy3) clear_bit(MT76_RESET, &phy3->mt76->state); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); @@ -1957,23 +1958,23 @@ void mt7996_mac_reset_work(struct work_struct *work) if (phy3) clear_bit(MT76_RESET, &phy3->mt76->state); - local_bh_disable(); mt76_for_each_q_rx(&dev->mt76, i) { if (mtk_wed_device_active(&dev->mt76.mmio.wed) && mt76_queue_is_wed_rro(&dev->mt76.q_rx[i])) continue; napi_enable(&dev->mt76.napi[i]); + local_bh_disable(); napi_schedule(&dev->mt76.napi[i]); + local_bh_enable(); } - local_bh_enable(); tasklet_schedule(&dev->mt76.irq_tasklet); mt76_worker_enable(&dev->mt76.tx_worker); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 2b34ae5e0cb5..69dd565d8319 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -7,76 +7,44 @@ #include "mcu.h" #include "mac.h" -static bool mt7996_dev_running(struct mt7996_dev *dev) +int mt7996_run(struct mt7996_phy *phy) { - struct mt7996_phy *phy; - - if (test_bit(MT76_STATE_RUNNING, &dev->mphy.state)) - return true; - - phy = mt7996_phy2(dev); - if (phy && test_bit(MT76_STATE_RUNNING, &phy->mt76->state)) - return true; - - phy = mt7996_phy3(dev); - - return phy && test_bit(MT76_STATE_RUNNING, &phy->mt76->state); -} - -int mt7996_run(struct ieee80211_hw *hw) -{ - struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); - bool running; + struct mt7996_dev *dev = phy->dev; int ret; - running = mt7996_dev_running(dev); - if (!running) { - ret = mt7996_mcu_set_hdr_trans(dev, true); - if (ret) - goto out; - - if (is_mt7992(&dev->mt76)) { - u8 queue = mt76_connac_lmac_mapping(IEEE80211_AC_VI); - - ret = mt7996_mcu_cp_support(dev, queue); - if (ret) - goto out; - } - } - mt7996_mac_enable_nf(dev, phy->mt76->band_idx); ret = mt7996_mcu_set_rts_thresh(phy, 0x92b); if (ret) - goto out; + return ret; ret = mt7996_mcu_set_radio_en(phy, true); if (ret) - goto out; + return ret; ret = mt7996_mcu_set_chan_info(phy, UNI_CHANNEL_RX_PATH); if (ret) - goto out; + return ret; ret = mt7996_mcu_set_thermal_throttling(phy, MT7996_THERMAL_THROTTLE_MAX); if (ret) - goto out; + return ret; ret = mt7996_mcu_set_thermal_protect(phy, true); if (ret) - goto out; + return ret; set_bit(MT76_STATE_RUNNING, &phy->mt76->state); - ieee80211_queue_delayed_work(hw, &phy->mt76->mac_work, + ieee80211_queue_delayed_work(dev->mphy.hw, &phy->mt76->mac_work, MT7996_WATCHDOG_TIME); - if (!running) + if (!phy->counter_reset) { mt7996_mac_reset_counters(phy); + phy->counter_reset = true; + } -out: - return ret; + return 0; } static int mt7996_start(struct ieee80211_hw *hw) @@ -87,16 +55,23 @@ static int mt7996_start(struct ieee80211_hw *hw) flush_work(&dev->init_work); mutex_lock(&dev->mt76.mutex); - ret = mt7996_run(hw); + ret = mt7996_mcu_set_hdr_trans(dev, true); + if (!ret && is_mt7992(&dev->mt76)) { + u8 queue = mt76_connac_lmac_mapping(IEEE80211_AC_VI); + + ret = mt7996_mcu_cp_support(dev, queue); + } mutex_unlock(&dev->mt76.mutex); return ret; } -static void mt7996_stop(struct ieee80211_hw *hw, bool suspend) +static void mt7996_stop_phy(struct mt7996_phy *phy) { - struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); + struct mt7996_dev *dev = phy->dev; + + if (!phy || !test_bit(MT76_STATE_RUNNING, &phy->mt76->state)) + return; cancel_delayed_work_sync(&phy->mt76->mac_work); @@ -109,6 +84,10 @@ static void mt7996_stop(struct ieee80211_hw *hw, bool suspend) mutex_unlock(&dev->mt76.mutex); } +static void mt7996_stop(struct ieee80211_hw *hw, bool suspend) +{ +} + static inline int get_free_idx(u32 mask, u8 start, u8 end) { return ffs(~mask & GENMASK(end, start)); @@ -157,73 +136,133 @@ static int get_omac_idx(enum nl80211_iftype type, u64 mask) return -1; } -static void mt7996_init_bitrate_mask(struct ieee80211_vif *vif) +static void +mt7996_init_bitrate_mask(struct ieee80211_vif *vif, struct mt7996_vif_link *mlink) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; int i; - for (i = 0; i < ARRAY_SIZE(mvif->bitrate_mask.control); i++) { - mvif->bitrate_mask.control[i].gi = NL80211_TXRATE_DEFAULT_GI; - mvif->bitrate_mask.control[i].he_gi = 0xff; - mvif->bitrate_mask.control[i].he_ltf = 0xff; - mvif->bitrate_mask.control[i].legacy = GENMASK(31, 0); - memset(mvif->bitrate_mask.control[i].ht_mcs, 0xff, - sizeof(mvif->bitrate_mask.control[i].ht_mcs)); - memset(mvif->bitrate_mask.control[i].vht_mcs, 0xff, - sizeof(mvif->bitrate_mask.control[i].vht_mcs)); - memset(mvif->bitrate_mask.control[i].he_mcs, 0xff, - sizeof(mvif->bitrate_mask.control[i].he_mcs)); + for (i = 0; i < ARRAY_SIZE(mlink->bitrate_mask.control); i++) { + mlink->bitrate_mask.control[i].gi = NL80211_TXRATE_DEFAULT_GI; + mlink->bitrate_mask.control[i].he_gi = 0xff; + mlink->bitrate_mask.control[i].he_ltf = 0xff; + mlink->bitrate_mask.control[i].legacy = GENMASK(31, 0); + memset(mlink->bitrate_mask.control[i].ht_mcs, 0xff, + sizeof(mlink->bitrate_mask.control[i].ht_mcs)); + memset(mlink->bitrate_mask.control[i].vht_mcs, 0xff, + sizeof(mlink->bitrate_mask.control[i].vht_mcs)); + memset(mlink->bitrate_mask.control[i].he_mcs, 0xff, + sizeof(mlink->bitrate_mask.control[i].he_mcs)); } } -static int mt7996_add_interface(struct ieee80211_hw *hw, - struct ieee80211_vif *vif) +static int +mt7996_set_hw_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, + struct ieee80211_vif *vif, struct ieee80211_sta *sta, + struct mt7996_vif_link *mlink, struct ieee80211_key_conf *key) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); - struct mt76_txq *mtxq; - u8 band_idx = phy->mt76->band_idx; - int idx, ret = 0; + struct mt7996_sta *msta = sta ? (struct mt7996_sta *)sta->drv_priv : + &mlink->sta; + struct mt76_wcid *wcid = &msta->wcid; + u8 *wcid_keyidx = &wcid->hw_key_idx; + struct mt7996_phy *phy; + int idx = key->keyidx; - mutex_lock(&dev->mt76.mutex); + phy = mt7996_vif_link_phy(mlink); + if (!phy) + return -EINVAL; - if (vif->type == NL80211_IFTYPE_MONITOR && - is_zero_ether_addr(vif->addr)) - phy->monitor_vif = vif; + if (sta && !wcid->sta) + return -EOPNOTSUPP; - mvif->mt76.idx = __ffs64(~dev->mt76.vif_mask); - if (mvif->mt76.idx >= mt7996_max_interface_num(dev)) { - ret = -ENOSPC; - goto out; + switch (key->cipher) { + case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + if (key->keyidx == 6 || key->keyidx == 7) { + wcid_keyidx = &wcid->hw_key_idx2; + key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIE; + } + break; + default: + break; } + if (cmd == SET_KEY && !sta && !mlink->mt76.cipher) { + mlink->mt76.cipher = mt76_connac_mcu_get_cipher(key->cipher); + mt7996_mcu_add_bss_info(phy, vif, &vif->bss_conf, &mlink->mt76, true); + } + + if (cmd == SET_KEY) { + *wcid_keyidx = idx; + } else { + if (idx == *wcid_keyidx) + *wcid_keyidx = -1; + return 0; + } + + mt76_wcid_key_setup(&dev->mt76, wcid, key); + + if (key->keyidx == 6 || key->keyidx == 7) + return mt7996_mcu_bcn_prot_enable(dev, vif, key); + + return mt7996_mcu_add_key(&dev->mt76, vif, key, + MCU_WMWA_UNI_CMD(STA_REC_UPDATE), + &msta->wcid, cmd); +} + +static void +mt7996_key_iter(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, struct ieee80211_key_conf *key, + void *data) +{ + struct mt7996_vif_link *mlink = data; + + if (sta) + return; + + WARN_ON(mt7996_set_hw_key(hw, SET_KEY, vif, NULL, mlink, key)); +} + +int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink) +{ + struct mt7996_vif_link *link = container_of(mlink, struct mt7996_vif_link, mt76); + struct mt7996_phy *phy = mphy->priv; + struct mt7996_dev *dev = phy->dev; + u8 band_idx = phy->mt76->band_idx; + struct mt76_txq *mtxq; + int idx, ret; + + mlink->idx = __ffs64(~dev->mt76.vif_mask); + if (mlink->idx >= mt7996_max_interface_num(dev)) + return -ENOSPC; + idx = get_omac_idx(vif->type, phy->omac_mask); - if (idx < 0) { - ret = -ENOSPC; - goto out; - } - mvif->mt76.omac_idx = idx; - mvif->phy = phy; - mvif->mt76.band_idx = band_idx; - mvif->mt76.wmm_idx = vif->type == NL80211_IFTYPE_AP ? 0 : 3; + if (idx < 0) + return -ENOSPC; - ret = mt7996_mcu_add_dev_info(phy, vif, true); + link->phy = phy; + mlink->omac_idx = idx; + mlink->band_idx = band_idx; + mlink->wmm_idx = vif->type == NL80211_IFTYPE_AP ? 0 : 3; + mlink->wcid = &link->sta.wcid; + + ret = mt7996_mcu_add_dev_info(phy, vif, link_conf, mlink, true); if (ret) - goto out; + return ret; - dev->mt76.vif_mask |= BIT_ULL(mvif->mt76.idx); - phy->omac_mask |= BIT_ULL(mvif->mt76.omac_idx); + dev->mt76.vif_mask |= BIT_ULL(mlink->idx); + phy->omac_mask |= BIT_ULL(mlink->omac_idx); - idx = MT7996_WTBL_RESERVED - mvif->mt76.idx; + idx = MT7996_WTBL_RESERVED - mlink->idx; - INIT_LIST_HEAD(&mvif->sta.rc_list); - INIT_LIST_HEAD(&mvif->sta.wcid.poll_list); - mvif->sta.wcid.idx = idx; - mvif->sta.wcid.phy_idx = band_idx; - mvif->sta.wcid.hw_key_idx = -1; - mvif->sta.wcid.tx_info |= MT_WCID_TX_INFO_SET; - mt76_wcid_init(&mvif->sta.wcid); + INIT_LIST_HEAD(&link->sta.rc_list); + link->sta.wcid.idx = idx; + link->sta.wcid.tx_info |= MT_WCID_TX_INFO_SET; + mt76_wcid_init(&link->sta.wcid, band_idx); mt7996_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); @@ -234,54 +273,50 @@ static int mt7996_add_interface(struct ieee80211_hw *hw, } if (vif->type != NL80211_IFTYPE_AP && - (!mvif->mt76.omac_idx || mvif->mt76.omac_idx > 3)) + (!mlink->omac_idx || mlink->omac_idx > 3)) vif->offload_flags = 0; - vif->offload_flags |= IEEE80211_OFFLOAD_ENCAP_4ADDR; if (phy->mt76->chandef.chan->band != NL80211_BAND_2GHZ) - mvif->mt76.basic_rates_idx = MT7996_BASIC_RATES_TBL + 4; + mlink->basic_rates_idx = MT7996_BASIC_RATES_TBL + 4; else - mvif->mt76.basic_rates_idx = MT7996_BASIC_RATES_TBL; + mlink->basic_rates_idx = MT7996_BASIC_RATES_TBL; - mt7996_init_bitrate_mask(vif); + mt7996_init_bitrate_mask(vif, link); - mt7996_mcu_add_bss_info(phy, vif, true); + mt7996_mcu_add_bss_info(phy, vif, link_conf, mlink, true); /* defer the first STA_REC of BMC entry to BSS_CHANGED_BSSID for STA * interface, since firmware only records BSSID when the entry is new */ if (vif->type != NL80211_IFTYPE_STATION) - mt7996_mcu_add_sta(dev, vif, NULL, true, true); - rcu_assign_pointer(dev->mt76.wcid[idx], &mvif->sta.wcid); + mt7996_mcu_add_sta(dev, vif, mlink, NULL, CONN_STATE_PORT_SECURE, true); + rcu_assign_pointer(dev->mt76.wcid[idx], &link->sta.wcid); -out: - mutex_unlock(&dev->mt76.mutex); + ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, link); - return ret; + return 0; } -static void mt7996_remove_interface(struct ieee80211_hw *hw, - struct ieee80211_vif *vif) +void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct mt7996_sta *msta = &mvif->sta; - struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); - int idx = msta->wcid.idx; + struct mt7996_vif_link *link = container_of(mlink, struct mt7996_vif_link, mt76); + struct mt7996_phy *phy = mphy->priv; + struct mt7996_dev *dev = phy->dev; + struct mt7996_sta *msta; + int idx; - mt7996_mcu_add_sta(dev, vif, NULL, false, false); - mt7996_mcu_add_bss_info(phy, vif, false); + msta = &link->sta; + idx = msta->wcid.idx; + mt7996_mcu_add_sta(dev, vif, mlink, NULL, CONN_STATE_DISCONNECT, false); + mt7996_mcu_add_bss_info(phy, vif, link_conf, mlink, false); - if (vif == phy->monitor_vif) - phy->monitor_vif = NULL; - - mt7996_mcu_add_dev_info(phy, vif, false); + mt7996_mcu_add_dev_info(phy, vif, link_conf, mlink, false); rcu_assign_pointer(dev->mt76.wcid[idx], NULL); - mutex_lock(&dev->mt76.mutex); - dev->mt76.vif_mask &= ~BIT_ULL(mvif->mt76.idx); - phy->omac_mask &= ~BIT_ULL(mvif->mt76.omac_idx); - mutex_unlock(&dev->mt76.mutex); + dev->mt76.vif_mask &= ~BIT_ULL(mlink->idx); + phy->omac_mask &= ~BIT_ULL(mlink->omac_idx); spin_lock_bh(&dev->mt76.sta_poll_lock); if (!list_empty(&msta->wcid.poll_list)) @@ -291,6 +326,124 @@ static void mt7996_remove_interface(struct ieee80211_hw *hw, mt76_wcid_cleanup(&dev->mt76, &msta->wcid); } +static void mt7996_phy_set_rxfilter(struct mt7996_phy *phy) +{ + struct mt7996_dev *dev = phy->dev; + u32 ctl_flags = MT_WF_RFCR1_DROP_ACK | + MT_WF_RFCR1_DROP_BF_POLL | + MT_WF_RFCR1_DROP_BA | + MT_WF_RFCR1_DROP_CFEND | + MT_WF_RFCR1_DROP_CFACK; + u32 filter = phy->rxfilter; + + if (filter & MT_WF_RFCR_DROP_OTHER_UC) { + filter |= MT_WF_RFCR_DROP_CTS | + MT_WF_RFCR_DROP_RTS | + MT_WF_RFCR_DROP_CTL_RSV | + MT_WF_RFCR_DROP_FCSFAIL; + } + + mt76_wr(dev, MT_WF_RFCR(phy->mt76->band_idx), filter); + if (filter & MT_WF_RFCR_DROP_CTL_RSV) + mt76_set(dev, MT_WF_RFCR1(phy->mt76->band_idx), ctl_flags); + else + mt76_clear(dev, MT_WF_RFCR1(phy->mt76->band_idx), ctl_flags); +} + +static void mt7996_set_monitor(struct mt7996_phy *phy, bool enabled) +{ + struct mt7996_dev *dev = phy->dev; + + if (!phy) + return; + + if (enabled == !(phy->rxfilter & MT_WF_RFCR_DROP_OTHER_UC)) + return; + + if (!enabled) + phy->rxfilter |= MT_WF_RFCR_DROP_OTHER_UC; + else + phy->rxfilter &= ~MT_WF_RFCR_DROP_OTHER_UC; + + mt76_rmw_field(dev, MT_DMA_DCR0(phy->mt76->band_idx), + MT_DMA_DCR0_RXD_G5_EN, enabled); + mt7996_phy_set_rxfilter(phy); + mt7996_mcu_set_sniffer_mode(phy, enabled); +} + +static int mt7996_add_interface(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; + struct wireless_dev *wdev = ieee80211_vif_to_wdev(vif); + struct mt7996_dev *dev = mt7996_hw_dev(hw); + int i, err = 0; + + mutex_lock(&dev->mt76.mutex); + + for (i = 0; i < MT7996_MAX_RADIOS; i++) { + struct mt7996_phy *phy = dev->radio_phy[i]; + + if (!phy || !(wdev->radio_mask & BIT(i)) || + test_bit(MT76_STATE_RUNNING, &phy->mt76->state)) + continue; + + err = mt7996_run(phy); + if (err) + goto out; + + if (vif->type == NL80211_IFTYPE_MONITOR) + mt7996_set_monitor(phy, true); + } + + mt76_vif_init(vif, &mvif->mt76); + + vif->offload_flags |= IEEE80211_OFFLOAD_ENCAP_4ADDR; + +out: + mutex_unlock(&dev->mt76.mutex); + + return err; +} + +struct mt7996_radio_data { + u32 active_mask; + u32 monitor_mask; +}; + +static void mt7996_remove_iter(void *data, u8 *mac, struct ieee80211_vif *vif) +{ + struct wireless_dev *wdev = ieee80211_vif_to_wdev(vif); + struct mt7996_radio_data *rdata = data; + + rdata->active_mask |= wdev->radio_mask; + if (vif->type == NL80211_IFTYPE_MONITOR) + rdata->monitor_mask |= wdev->radio_mask; +} + +static void mt7996_remove_interface(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct mt7996_dev *dev = mt7996_hw_dev(hw); + struct mt7996_radio_data rdata = {}; + int i; + + ieee80211_iterate_active_interfaces_mtx(hw, 0, mt7996_remove_iter, + &rdata); + mt76_vif_cleanup(&dev->mt76, vif); + + for (i = 0; i < MT7996_MAX_RADIOS; i++) { + struct mt7996_phy *phy = dev->radio_phy[i]; + + if (!phy) + continue; + if (!(rdata.monitor_mask & BIT(i))) + mt7996_set_monitor(phy, false); + if (!(rdata.active_mask & BIT(i))) + mt7996_stop_phy(phy); + } +} + int mt7996_set_channel(struct mt76_phy *mphy) { struct mt7996_phy *phy = mphy->priv; @@ -304,6 +457,10 @@ int mt7996_set_channel(struct mt76_phy *mphy) if (ret) goto out; + ret = mt7996_mcu_set_txpower_sku(phy); + if (ret) + goto out; + ret = mt7996_dfs_init_radar_detector(phy); mt7996_mac_cca_stats_reset(phy); @@ -322,14 +479,9 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, struct ieee80211_key_conf *key) { struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct mt7996_sta *msta = sta ? (struct mt7996_sta *)sta->drv_priv : - &mvif->sta; - struct mt76_wcid *wcid = &msta->wcid; - u8 *wcid_keyidx = &wcid->hw_key_idx; - int idx = key->keyidx; - int err = 0; + struct mt7996_vif_link *mlink = &mvif->deflink; + int err; /* The hardware does not support per-STA RX GTK, fallback * to software mode for these. @@ -354,11 +506,8 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: - if (key->keyidx == 6 || key->keyidx == 7) { - wcid_keyidx = &wcid->hw_key_idx2; - key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIE; + if (key->keyidx == 6 || key->keyidx == 7) break; - } fallthrough; case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: @@ -366,30 +515,11 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, return -EOPNOTSUPP; } + if (!mt7996_vif_link_phy(mlink)) + return 0; /* defer until after link add */ + mutex_lock(&dev->mt76.mutex); - - if (cmd == SET_KEY && !sta && !mvif->mt76.cipher) { - mvif->mt76.cipher = mt76_connac_mcu_get_cipher(key->cipher); - mt7996_mcu_add_bss_info(phy, vif, true); - } - - if (cmd == SET_KEY) { - *wcid_keyidx = idx; - } else { - if (idx == *wcid_keyidx) - *wcid_keyidx = -1; - goto out; - } - - mt76_wcid_key_setup(&dev->mt76, wcid, key); - - if (key->keyidx == 6 || key->keyidx == 7) - err = mt7996_mcu_bcn_prot_enable(dev, vif, key); - else - err = mt7996_mcu_add_key(&dev->mt76, vif, key, - MCU_WMWA_UNI_CMD(STA_REC_UPDATE), - &msta->wcid, cmd); -out: + err = mt7996_set_hw_key(hw, cmd, vif, sta, mlink, key); mutex_unlock(&dev->mt76.mutex); return err; @@ -397,40 +527,6 @@ out: static int mt7996_config(struct ieee80211_hw *hw, u32 changed) { - struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); - int ret; - - if (changed & IEEE80211_CONF_CHANGE_CHANNEL) { - ret = mt76_update_channel(phy->mt76); - if (ret) - return ret; - } - - if (changed & (IEEE80211_CONF_CHANGE_POWER | - IEEE80211_CONF_CHANGE_CHANNEL)) { - ret = mt7996_mcu_set_txpower_sku(phy); - if (ret) - return ret; - } - - mutex_lock(&dev->mt76.mutex); - - if (changed & IEEE80211_CONF_CHANGE_MONITOR) { - bool enabled = !!(hw->conf.flags & IEEE80211_CONF_MONITOR); - - if (!enabled) - phy->rxfilter |= MT_WF_RFCR_DROP_OTHER_UC; - else - phy->rxfilter &= ~MT_WF_RFCR_DROP_OTHER_UC; - - mt76_rmw_field(dev, MT_DMA_DCR0(phy->mt76->band_idx), - MT_DMA_DCR0_RXD_G5_EN, enabled); - mt76_wr(dev, MT_WF_RFCR(phy->mt76->band_idx), phy->rxfilter); - } - - mutex_unlock(&dev->mt76.mutex); - return 0; } @@ -439,7 +535,8 @@ mt7996_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id, u16 queue, const struct ieee80211_tx_queue_params *params) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; + struct mt7996_dev *dev = mt7996_hw_dev(hw); + struct mt7996_vif_link *mlink = mt7996_vif_link(dev, vif, link_id); static const u8 mq_to_aci[] = { [IEEE80211_AC_VO] = 3, [IEEE80211_AC_VI] = 2, @@ -448,7 +545,7 @@ mt7996_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, }; /* firmware uses access class index */ - mvif->queue_params[mq_to_aci[queue]] = *params; + mlink->queue_params[mq_to_aci[queue]] = *params; /* no need to update right away, we'll get BSS_CHANGED_QOS */ return 0; @@ -460,34 +557,18 @@ static void mt7996_configure_filter(struct ieee80211_hw *hw, u64 multicast) { struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); - u32 ctl_flags = MT_WF_RFCR1_DROP_ACK | - MT_WF_RFCR1_DROP_BF_POLL | - MT_WF_RFCR1_DROP_BA | - MT_WF_RFCR1_DROP_CFEND | - MT_WF_RFCR1_DROP_CFACK; + struct mt7996_phy *phy; + u32 filter_mask = 0, filter_set = 0; u32 flags = 0; -#define MT76_FILTER(_flag, _hw) do { \ - flags |= *total_flags & FIF_##_flag; \ - phy->rxfilter &= ~(_hw); \ - phy->rxfilter |= !(flags & FIF_##_flag) * (_hw); \ +#define MT76_FILTER(_flag, _hw) do { \ + flags |= *total_flags & FIF_##_flag; \ + filter_mask |= (_hw); \ + filter_set |= !(flags & FIF_##_flag) * (_hw); \ } while (0) mutex_lock(&dev->mt76.mutex); - phy->rxfilter &= ~(MT_WF_RFCR_DROP_OTHER_BSS | - MT_WF_RFCR_DROP_OTHER_BEACON | - MT_WF_RFCR_DROP_FRAME_REPORT | - MT_WF_RFCR_DROP_PROBEREQ | - MT_WF_RFCR_DROP_MCAST_FILTERED | - MT_WF_RFCR_DROP_MCAST | - MT_WF_RFCR_DROP_BCAST | - MT_WF_RFCR_DROP_DUPLICATE | - MT_WF_RFCR_DROP_A2_BSSID | - MT_WF_RFCR_DROP_UNWANTED_CTL | - MT_WF_RFCR_DROP_STBC_MULTI); - MT76_FILTER(OTHER_BSS, MT_WF_RFCR_DROP_OTHER_TIM | MT_WF_RFCR_DROP_A3_MAC | MT_WF_RFCR_DROP_A3_BSSID); @@ -496,57 +577,42 @@ static void mt7996_configure_filter(struct ieee80211_hw *hw, MT76_FILTER(CONTROL, MT_WF_RFCR_DROP_CTS | MT_WF_RFCR_DROP_RTS | - MT_WF_RFCR_DROP_CTL_RSV | - MT_WF_RFCR_DROP_NDPA); + MT_WF_RFCR_DROP_CTL_RSV); *total_flags = flags; - mt76_wr(dev, MT_WF_RFCR(phy->mt76->band_idx), phy->rxfilter); - if (*total_flags & FIF_CONTROL) - mt76_clear(dev, MT_WF_RFCR1(phy->mt76->band_idx), ctl_flags); - else - mt76_set(dev, MT_WF_RFCR1(phy->mt76->band_idx), ctl_flags); + mt7996_for_each_phy(dev, phy) { + phy->rxfilter &= ~(MT_WF_RFCR_DROP_OTHER_BSS | + MT_WF_RFCR_DROP_OTHER_BEACON | + MT_WF_RFCR_DROP_FRAME_REPORT | + MT_WF_RFCR_DROP_PROBEREQ | + MT_WF_RFCR_DROP_MCAST_FILTERED | + MT_WF_RFCR_DROP_MCAST | + MT_WF_RFCR_DROP_BCAST | + MT_WF_RFCR_DROP_DUPLICATE | + MT_WF_RFCR_DROP_A2_BSSID | + MT_WF_RFCR_DROP_UNWANTED_CTL | + MT_WF_RFCR_DROP_STBC_MULTI | + filter_mask); + phy->rxfilter |= filter_set; + mt7996_phy_set_rxfilter(phy); + } mutex_unlock(&dev->mt76.mutex); } -static void -mt7996_update_bss_color(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct cfg80211_he_bss_color *bss_color) -{ - struct mt7996_dev *dev = mt7996_hw_dev(hw); - - switch (vif->type) { - case NL80211_IFTYPE_AP: { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - - if (mvif->mt76.omac_idx > HW_BSSID_MAX) - return; - fallthrough; - } - case NL80211_IFTYPE_STATION: - mt7996_mcu_update_bss_color(dev, vif, bss_color); - break; - default: - break; - } -} - static u8 -mt7996_get_rates_table(struct ieee80211_hw *hw, struct ieee80211_vif *vif, +mt7996_get_rates_table(struct mt7996_phy *phy, struct ieee80211_bss_conf *conf, bool beacon, bool mcast) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; - struct mt76_phy *mphy = hw->priv; + struct mt7996_dev *dev = phy->dev; + struct mt76_vif_link *mvif = mt76_vif_conf_link(&dev->mt76, conf->vif, conf); u16 rate; u8 i, idx; - rate = mt76_connac2_mac_tx_rate_val(mphy, vif, beacon, mcast); + rate = mt76_connac2_mac_tx_rate_val(phy->mt76, conf, beacon, mcast); if (beacon) { - struct mt7996_phy *phy = mphy->priv; - /* odd index for driver, even index for firmware */ idx = MT7996_BEACON_RATES_TBL + 2 * phy->mt76->band_idx; if (phy->beacon_rate != rate) @@ -569,7 +635,7 @@ mt7996_update_mu_group(struct ieee80211_hw *hw, struct ieee80211_vif *vif, { struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct mt7996_dev *dev = mt7996_hw_dev(hw); - u8 band = mvif->mt76.band_idx; + u8 band = mvif->deflink.mt76.band_idx; u32 *mu; mu = (u32 *)info->mu_group.membership; @@ -588,20 +654,31 @@ static void mt7996_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_bss_conf *info, u64 changed) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; - struct mt7996_phy *phy = mt7996_hw_phy(hw); struct mt7996_dev *dev = mt7996_hw_dev(hw); + struct mt76_vif_link *mvif; + struct mt7996_phy *phy; + struct mt76_phy *mphy; mutex_lock(&dev->mt76.mutex); + mvif = mt76_vif_conf_link(&dev->mt76, vif, info); + if (!mvif) + goto out; + + mphy = mt76_vif_link_phy(mvif); + if (!mphy) + goto out; + + phy = mphy->priv; + /* station mode uses BSSID to map the wlan entry to a peer, * and then peer references bss_info_rfch to set bandwidth cap. */ if ((changed & BSS_CHANGED_BSSID && !is_zero_ether_addr(info->bssid)) || (changed & BSS_CHANGED_ASSOC && vif->cfg.assoc) || (changed & BSS_CHANGED_BEACON_ENABLED && info->enable_beacon)) { - mt7996_mcu_add_bss_info(phy, vif, true); - mt7996_mcu_add_sta(dev, vif, NULL, true, + mt7996_mcu_add_bss_info(phy, vif, info, mvif, true); + mt7996_mcu_add_sta(dev, vif, mvif, NULL, CONN_STATE_PORT_SECURE, !!(changed & BSS_CHANGED_BSSID)); } @@ -613,34 +690,39 @@ static void mt7996_bss_info_changed(struct ieee80211_hw *hw, if (slottime != phy->slottime) { phy->slottime = slottime; - mt7996_mcu_set_timing(phy, vif); + mt7996_mcu_set_timing(phy, vif, info); } } if (changed & BSS_CHANGED_MCAST_RATE) mvif->mcast_rates_idx = - mt7996_get_rates_table(hw, vif, false, true); + mt7996_get_rates_table(phy, info, false, true); if (changed & BSS_CHANGED_BASIC_RATES) mvif->basic_rates_idx = - mt7996_get_rates_table(hw, vif, false, false); + mt7996_get_rates_table(phy, info, false, false); /* ensure that enable txcmd_mode after bss_info */ if (changed & (BSS_CHANGED_QOS | BSS_CHANGED_BEACON_ENABLED)) - mt7996_mcu_set_tx(dev, vif); + mt7996_mcu_set_tx(dev, vif, info); if (changed & BSS_CHANGED_HE_OBSS_PD) mt7996_mcu_add_obss_spr(phy, vif, &info->he_obss_pd); - if (changed & BSS_CHANGED_HE_BSS_COLOR) - mt7996_update_bss_color(hw, vif, &info->he_bss_color); + if (changed & BSS_CHANGED_HE_BSS_COLOR) { + if ((vif->type == NL80211_IFTYPE_AP && + mvif->omac_idx <= HW_BSSID_MAX) || + vif->type == NL80211_IFTYPE_STATION) + mt7996_mcu_update_bss_color(dev, mvif, + &info->he_bss_color); + } if (changed & (BSS_CHANGED_BEACON | BSS_CHANGED_BEACON_ENABLED)) { mvif->beacon_rates_idx = - mt7996_get_rates_table(hw, vif, true, false); + mt7996_get_rates_table(phy, info, true, false); - mt7996_mcu_add_beacon(hw, vif, info->enable_beacon); + mt7996_mcu_add_beacon(hw, vif, info); } if (changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP | @@ -650,6 +732,13 @@ static void mt7996_bss_info_changed(struct ieee80211_hw *hw, if (changed & BSS_CHANGED_MU_GROUPS) mt7996_update_mu_group(hw, vif, info); + if (changed & BSS_CHANGED_TXPOWER && + info->txpower != phy->txpower) { + phy->txpower = info->txpower; + mt7996_mcu_set_txpower_sku(phy); + } + +out: mutex_unlock(&dev->mt76.mutex); } @@ -661,7 +750,7 @@ mt7996_channel_switch_beacon(struct ieee80211_hw *hw, struct mt7996_dev *dev = mt7996_hw_dev(hw); mutex_lock(&dev->mt76.mutex); - mt7996_mcu_add_beacon(hw, vif, true); + mt7996_mcu_add_beacon(hw, vif, &vif->bss_conf); mutex_unlock(&dev->mt76.mutex); } @@ -671,8 +760,9 @@ int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - u8 band_idx = mvif->phy->mt76->band_idx; - int ret, idx; + struct mt7996_vif_link *link = &mvif->deflink; + u8 band_idx = link->phy->mt76->band_idx; + int idx; idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7996_WTBL_STA); if (idx < 0) @@ -684,18 +774,59 @@ int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, msta->wcid.sta = 1; msta->wcid.idx = idx; msta->wcid.phy_idx = band_idx; - msta->wcid.tx_info |= MT_WCID_TX_INFO_SET; ewma_avg_signal_init(&msta->avg_ack_signal); mt7996_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); + mt7996_mcu_add_sta(dev, vif, &link->mt76, sta, CONN_STATE_DISCONNECT, + true); - ret = mt7996_mcu_add_sta(dev, vif, sta, true, true); - if (ret) - return ret; + return 0; +} - return mt7996_mcu_add_rate_ctrl(dev, vif, sta, false); +int mt7996_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, enum mt76_sta_event ev) +{ + struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); + struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; + struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; + struct mt7996_vif_link *link = &mvif->deflink; + int i, ret; + + switch (ev) { + case MT76_STA_EVENT_ASSOC: + ret = mt7996_mcu_add_sta(dev, vif, &link->mt76, sta, + CONN_STATE_CONNECT, true); + if (ret) + return ret; + + ret = mt7996_mcu_add_rate_ctrl(dev, vif, sta, false); + if (ret) + return ret; + + msta->wcid.tx_info |= MT_WCID_TX_INFO_SET; + msta->wcid.sta = 1; + + return 0; + + case MT76_STA_EVENT_AUTHORIZE: + return mt7996_mcu_add_sta(dev, vif, &link->mt76, sta, + CONN_STATE_PORT_SECURE, false); + + case MT76_STA_EVENT_DISASSOC: + for (i = 0; i < ARRAY_SIZE(msta->twt.flow); i++) + mt7996_mac_twt_teardown_flow(dev, msta, i); + + mt7996_mcu_add_sta(dev, vif, &link->mt76, sta, + CONN_STATE_DISCONNECT, false); + msta->wcid.sta_disabled = 1; + msta->wcid.sta = 0; + + return 0; + } + + return 0; } void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, @@ -703,16 +834,10 @@ void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, { struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; - int i; - - mt7996_mcu_add_sta(dev, vif, sta, false, false); mt7996_mac_wtbl_update(dev, msta->wcid.idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); - for (i = 0; i < ARRAY_SIZE(msta->twt.flow); i++) - mt7996_mac_twt_teardown_flow(dev, msta, i); - spin_lock_bh(&mdev->sta_poll_lock); if (!list_empty(&msta->wcid.poll_list)) list_del_init(&msta->wcid.poll_list); @@ -731,6 +856,22 @@ static void mt7996_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif = info->control.vif; struct mt76_wcid *wcid = &dev->mt76.global_wcid; + if (vif) { + struct mt7996_vif *mvif; + + mvif = (struct mt7996_vif *)vif->drv_priv; + wcid = &mvif->deflink.sta.wcid; + + if (mvif->mt76.roc_phy && + (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)) { + mphy = mvif->mt76.roc_phy; + if (mphy->roc_link) + wcid = mphy->roc_link->wcid; + } else { + mphy = mt76_vif_link_phy(&mvif->deflink.mt76); + } + } + if (control->sta) { struct mt7996_sta *sta; @@ -738,11 +879,9 @@ static void mt7996_tx(struct ieee80211_hw *hw, wcid = &sta->wcid; } - if (vif && !control->sta) { - struct mt7996_vif *mvif; - - mvif = (struct mt7996_vif *)vif->drv_priv; - wcid = &mvif->sta.wcid; + if (!mphy) { + ieee80211_free_txskb(hw, skb); + return; } mt76_tx(mphy, control->sta, wcid, skb); @@ -750,12 +889,20 @@ static void mt7996_tx(struct ieee80211_hw *hw, static int mt7996_set_rts_threshold(struct ieee80211_hw *hw, u32 val) { - struct mt7996_phy *phy = mt7996_hw_phy(hw); - int ret; + struct mt7996_dev *dev = mt7996_hw_dev(hw); + int i, ret; - mutex_lock(&phy->dev->mt76.mutex); - ret = mt7996_mcu_set_rts_thresh(phy, val); - mutex_unlock(&phy->dev->mt76.mutex); + mutex_lock(&dev->mt76.mutex); + + for (i = 0; i < hw->wiphy->n_radio; i++) { + struct mt7996_phy *phy = dev->radio_phy[i]; + + ret = mt7996_mcu_set_rts_thresh(phy, val); + if (ret) + break; + } + + mutex_unlock(&dev->mt76.mutex); return ret; } @@ -817,36 +964,25 @@ mt7996_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, return ret; } -static int -mt7996_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - struct ieee80211_sta *sta) -{ - return mt76_sta_state(hw, vif, sta, IEEE80211_STA_NOTEXIST, - IEEE80211_STA_NONE); -} - -static int -mt7996_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - struct ieee80211_sta *sta) -{ - return mt76_sta_state(hw, vif, sta, IEEE80211_STA_NONE, - IEEE80211_STA_NOTEXIST); -} - static int mt7996_get_stats(struct ieee80211_hw *hw, struct ieee80211_low_level_stats *stats) { - struct mt7996_phy *phy = mt7996_hw_phy(hw); struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt76_mib_stats *mib = &phy->mib; + int i; mutex_lock(&dev->mt76.mutex); - stats->dot11RTSSuccessCount = mib->rts_cnt; - stats->dot11RTSFailureCount = mib->rts_retries_cnt; - stats->dot11FCSErrorCount = mib->fcs_err_cnt; - stats->dot11ACKFailureCount = mib->ack_fail_cnt; + memset(stats, 0, sizeof(*stats)); + for (i = 0; i < hw->wiphy->n_radio; i++) { + struct mt7996_phy *phy = dev->radio_phy[i]; + struct mt76_mib_stats *mib = &phy->mib; + + stats->dot11RTSSuccessCount += mib->rts_cnt; + stats->dot11RTSFailureCount += mib->rts_retries_cnt; + stats->dot11FCSErrorCount += mib->fcs_err_cnt; + stats->dot11ACKFailureCount += mib->ack_fail_cnt; + } mutex_unlock(&dev->mt76.mutex); @@ -856,17 +992,20 @@ mt7996_get_stats(struct ieee80211_hw *hw, u64 __mt7996_get_tsf(struct ieee80211_hw *hw, struct mt7996_vif *mvif) { struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); + struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink); union { u64 t64; u32 t32[2]; } tsf; u16 n; + if (!phy) + return 0; + lockdep_assert_held(&dev->mt76.mutex); - n = mvif->mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0 - : mvif->mt76.omac_idx; + n = mvif->deflink.mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0 + : mvif->deflink.mt76.omac_idx; /* TSF software read */ mt76_rmw(dev, MT_LPON_TCR(phy->mt76->band_idx, n), MT_LPON_TCR_SW_MODE, MT_LPON_TCR_SW_READ); @@ -896,17 +1035,20 @@ mt7996_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, { struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); + struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink); union { u64 t64; u32 t32[2]; } tsf = { .t64 = timestamp, }; u16 n; + if (!phy) + return; + mutex_lock(&dev->mt76.mutex); - n = mvif->mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0 - : mvif->mt76.omac_idx; + n = mvif->deflink.mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0 + : mvif->deflink.mt76.omac_idx; mt76_wr(dev, MT_LPON_UTTR0(phy->mt76->band_idx), tsf.t32[0]); mt76_wr(dev, MT_LPON_UTTR1(phy->mt76->band_idx), tsf.t32[1]); /* TSF software overwrite */ @@ -922,17 +1064,20 @@ mt7996_offset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, { struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); + struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink); union { u64 t64; u32 t32[2]; } tsf = { .t64 = timestamp, }; u16 n; + if (!phy) + return; + mutex_lock(&dev->mt76.mutex); - n = mvif->mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0 - : mvif->mt76.omac_idx; + n = mvif->deflink.mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0 + : mvif->deflink.mt76.omac_idx; mt76_wr(dev, MT_LPON_UTTR0(phy->mt76->band_idx), tsf.t32[0]); mt76_wr(dev, MT_LPON_UTTR1(phy->mt76->band_idx), tsf.t32[1]); /* TSF software adjust*/ @@ -945,12 +1090,14 @@ mt7996_offset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, static void mt7996_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class) { - struct mt7996_phy *phy = mt7996_hw_phy(hw); - struct mt7996_dev *dev = phy->dev; + struct mt7996_dev *dev = mt7996_hw_dev(hw); + struct mt7996_phy *phy; mutex_lock(&dev->mt76.mutex); - phy->coverage_class = max_t(s16, coverage_class, 0); - mt7996_mac_set_coverage_class(phy); + mt7996_for_each_phy(dev, phy) { + phy->coverage_class = max_t(s16, coverage_class, 0); + mt7996_mac_set_coverage_class(phy); + } mutex_unlock(&dev->mt76.mutex); } @@ -958,33 +1105,33 @@ static int mt7996_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant) { struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); - int max_nss = hweight8(hw->wiphy->available_antennas_tx); - u8 band_idx = phy->mt76->band_idx, shift = dev->chainshift[band_idx]; + int i; - if (!tx_ant || tx_ant != rx_ant || ffs(tx_ant) > max_nss) + if (tx_ant != rx_ant) return -EINVAL; - if ((BIT(hweight8(tx_ant)) - 1) != tx_ant) - tx_ant = BIT(ffs(tx_ant) - 1) - 1; + for (i = 0; i < hw->wiphy->n_radio; i++) { + struct mt7996_phy *phy = dev->radio_phy[i]; + + if (!(tx_ant & phy->orig_chainmask)) + return -EINVAL; + } mutex_lock(&dev->mt76.mutex); - phy->mt76->antenna_mask = tx_ant; + for (i = 0; i < hw->wiphy->n_radio; i++) { + struct mt7996_phy *phy = dev->radio_phy[i]; + u8 band_idx = phy->mt76->band_idx; + u8 shift = dev->chainshift[band_idx]; - /* restore to the origin chainmask which might have auxiliary path */ - if (hweight8(tx_ant) == max_nss && band_idx < MT_BAND2) - phy->mt76->chainmask = ((dev->chainmask >> shift) & - (BIT(dev->chainshift[band_idx + 1] - shift) - 1)) << shift; - else if (hweight8(tx_ant) == max_nss) - phy->mt76->chainmask = (dev->chainmask >> shift) << shift; - else - phy->mt76->chainmask = tx_ant << shift; + phy->mt76->chainmask = tx_ant & phy->orig_chainmask; + phy->mt76->antenna_mask = phy->mt76->chainmask >> shift; - mt76_set_stream_caps(phy->mt76, true); - mt7996_set_stream_vht_txbf_caps(phy); - mt7996_set_stream_he_eht_caps(phy); - mt7996_mcu_set_txpower_sku(phy); + mt76_set_stream_caps(phy->mt76, true); + mt7996_set_stream_vht_txbf_caps(phy); + mt7996_set_stream_he_eht_caps(phy); + mt7996_mcu_set_txpower_sku(phy); + } mutex_unlock(&dev->mt76.mutex); @@ -996,7 +1143,7 @@ static void mt7996_sta_statistics(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct station_info *sinfo) { - struct mt7996_phy *phy = mt7996_hw_phy(hw); + struct mt7996_dev *dev = mt7996_hw_dev(hw); struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; struct rate_info *txrate = &msta->wcid.rate; @@ -1030,7 +1177,7 @@ static void mt7996_sta_statistics(struct ieee80211_hw *hw, sinfo->avg_ack_signal = -(s8)ewma_avg_signal_read(&msta->avg_ack_signal); sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG); - if (mtk_wed_device_active(&phy->dev->mt76.mmio.wed)) { + if (mtk_wed_device_active(&dev->mt76.mmio.wed)) { sinfo->tx_bytes = msta->wcid.stats.tx_bytes; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64); @@ -1048,7 +1195,7 @@ static void mt7996_sta_statistics(struct ieee80211_hw *hw, static void mt7996_sta_rc_work(void *data, struct ieee80211_sta *sta) { struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; - struct mt7996_dev *dev = msta->vif->phy->dev; + struct mt7996_dev *dev = msta->vif->deflink.phy->dev; u32 *changed = data; spin_lock_bh(&dev->mt76.sta_poll_lock); @@ -1063,9 +1210,8 @@ static void mt7996_sta_rc_update(struct ieee80211_hw *hw, struct ieee80211_link_sta *link_sta, u32 changed) { + struct mt7996_dev *dev = mt7996_hw_dev(hw); struct ieee80211_sta *sta = link_sta->sta; - struct mt7996_phy *phy = mt7996_hw_phy(hw); - struct mt7996_dev *dev = phy->dev; mt7996_sta_rc_work(&changed, sta); ieee80211_queue_work(hw, &dev->rc_work); @@ -1075,12 +1221,11 @@ static int mt7996_set_bitrate_mask(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct cfg80211_bitrate_mask *mask) { + struct mt7996_dev *dev = mt7996_hw_dev(hw); struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct mt7996_phy *phy = mt7996_hw_phy(hw); - struct mt7996_dev *dev = phy->dev; u32 changed = IEEE80211_RC_SUPP_RATES_CHANGED; - mvif->bitrate_mask = *mask; + mvif->deflink.bitrate_mask = *mask; /* if multiple rates across different preambles are given we can * reconfigure this info with all peers using sta_rec command with @@ -1109,6 +1254,9 @@ static void mt7996_sta_set_4addr(struct ieee80211_hw *hw, else clear_bit(MT_WCID_FLAG_4ADDR, &msta->wcid.flags); + if (!msta->wcid.sta) + return; + mt7996_mcu_wtbl_update_hdr_trans(dev, vif, sta); } @@ -1125,6 +1273,9 @@ static void mt7996_sta_set_decap_offload(struct ieee80211_hw *hw, else clear_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags); + if (!msta->wcid.sta) + return; + mt7996_mcu_wtbl_update_hdr_trans(dev, vif, sta); } @@ -1258,7 +1409,7 @@ static void mt7996_ethtool_worker(void *wi_data, struct ieee80211_sta *sta) struct mt76_ethtool_worker_info *wi = wi_data; struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; - if (msta->vif->mt76.idx != wi->idx) + if (msta->vif->deflink.mt76.idx != wi->idx) return; mt76_ethtool_worker(wi, &msta->wcid.stats, true); @@ -1270,16 +1421,19 @@ void mt7996_get_et_stats(struct ieee80211_hw *hw, struct ethtool_stats *stats, u64 *data) { struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; + struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink); struct mt76_mib_stats *mib = &phy->mib; struct mt76_ethtool_worker_info wi = { .data = data, - .idx = mvif->mt76.idx, + .idx = mvif->deflink.mt76.idx, }; /* See mt7996_ampdu_stat_read_phy, etc */ int i, ei = 0; + if (!phy) + return; + mutex_lock(&dev->mt76.mutex); mt7996_mac_update_stats(phy); @@ -1373,11 +1527,18 @@ static int mt7996_set_radar_background(struct ieee80211_hw *hw, struct cfg80211_chan_def *chandef) { - struct mt7996_phy *phy = mt7996_hw_phy(hw); - struct mt7996_dev *dev = phy->dev; + struct mt7996_dev *dev = mt7996_hw_dev(hw); + struct mt7996_phy *phy; int ret = -EINVAL; bool running; + if (chandef) + phy = mt7996_band_phy(dev, chandef->chan->band); + else + phy = dev->rdd2_phy; + if (!phy) + return -EINVAL; + mutex_lock(&dev->mt76.mutex); if (dev->mt76.region == NL80211_DFS_UNSET) @@ -1428,9 +1589,14 @@ mt7996_net_fill_forward_path(struct ieee80211_hw *hw, { struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; + struct mt7996_vif_link *mlink = &mvif->deflink; struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); struct mtk_wed_device *wed = &dev->mt76.mmio.wed; + struct mt7996_phy *phy; + + phy = mt7996_vif_link_phy(mlink); + if (!phy) + return -ENODEV; if (phy != &dev->phy && phy->mt76->band_idx == MT_BAND2) wed = &dev->mt76.mmio.wed_hif2; @@ -1438,13 +1604,13 @@ mt7996_net_fill_forward_path(struct ieee80211_hw *hw, if (!mtk_wed_device_active(wed)) return -ENODEV; - if (msta->wcid.idx > MT7996_WTBL_STA) + if (!msta->wcid.sta || msta->wcid.idx > MT7996_WTBL_STA) return -EIO; path->type = DEV_PATH_MTK_WDMA; path->dev = ctx->dev; path->mtk_wdma.wdma_idx = wed->wdma_idx; - path->mtk_wdma.bss = mvif->mt76.idx; + path->mtk_wdma.bss = mvif->deflink.mt76.idx; path->mtk_wdma.queue = 0; path->mtk_wdma.wcid = msta->wcid.idx; @@ -1457,10 +1623,12 @@ mt7996_net_fill_forward_path(struct ieee80211_hw *hw, #endif const struct ieee80211_ops mt7996_ops = { - .add_chanctx = ieee80211_emulate_add_chanctx, - .remove_chanctx = ieee80211_emulate_remove_chanctx, - .change_chanctx = ieee80211_emulate_change_chanctx, - .switch_vif_chanctx = ieee80211_emulate_switch_vif_chanctx, + .add_chanctx = mt76_add_chanctx, + .remove_chanctx = mt76_remove_chanctx, + .change_chanctx = mt76_change_chanctx, + .assign_vif_chanctx = mt76_assign_vif_chanctx, + .unassign_vif_chanctx = mt76_unassign_vif_chanctx, + .switch_vif_chanctx = mt76_switch_vif_chanctx, .tx = mt7996_tx, .start = mt7996_start, .stop = mt7996_stop, @@ -1470,16 +1638,17 @@ const struct ieee80211_ops mt7996_ops = { .conf_tx = mt7996_conf_tx, .configure_filter = mt7996_configure_filter, .bss_info_changed = mt7996_bss_info_changed, - .sta_add = mt7996_sta_add, - .sta_remove = mt7996_sta_remove, + .sta_state = mt76_sta_state, .sta_pre_rcu_remove = mt76_sta_pre_rcu_remove, .link_sta_rc_update = mt7996_sta_rc_update, .set_key = mt7996_set_key, .ampdu_action = mt7996_ampdu_action, .set_rts_threshold = mt7996_set_rts_threshold, .wake_tx_queue = mt76_wake_tx_queue, - .sw_scan_start = mt76_sw_scan, - .sw_scan_complete = mt76_sw_scan_complete, + .hw_scan = mt76_hw_scan, + .cancel_hw_scan = mt76_cancel_hw_scan, + .remain_on_channel = mt76_remain_on_channel, + .cancel_remain_on_channel = mt76_cancel_remain_on_channel, .release_buffered_frames = mt76_release_buffered_frames, .get_txpower = mt76_get_txpower, .channel_switch_beacon = mt7996_channel_switch_beacon, diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index 6c445a9dbc03..e4569d032221 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -14,11 +14,23 @@ char *_fw; \ switch (mt76_chip(&(_dev)->mt76)) { \ case 0x7992: \ - _fw = MT7992_##name; \ + switch ((_dev)->var.type) { \ + case MT7992_VAR_TYPE_23: \ + _fw = MT7992_##name##_23; \ + break; \ + default: \ + _fw = MT7992_##name; \ + } \ break; \ case 0x7990: \ default: \ - _fw = MT7996_##name; \ + switch ((_dev)->var.type) { \ + case MT7996_VAR_TYPE_233: \ + _fw = MT7996_##name##_233; \ + break; \ + default: \ + _fw = MT7996_##name; \ + } \ break; \ } \ _fw; \ @@ -110,8 +122,8 @@ mt7996_mcu_set_sta_he_mcs(struct ieee80211_sta *sta, __le16 *he_mcs, u16 mcs_map) { struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; - enum nl80211_band band = msta->vif->phy->mt76->chandef.chan->band; - const u16 *mask = msta->vif->bitrate_mask.control[band].he_mcs; + enum nl80211_band band = msta->vif->deflink.phy->mt76->chandef.chan->band; + const u16 *mask = msta->vif->deflink.bitrate_mask.control[band].he_mcs; int nss, max_nss = sta->deflink.rx_nss > 3 ? 4 : sta->deflink.rx_nss; for (nss = 0; nss < max_nss; nss++) { @@ -744,8 +756,7 @@ mt7996_mcu_add_uni_tlv(struct sk_buff *skb, u16 tag, u16 len) } static void -mt7996_mcu_bss_rfch_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct mt7996_phy *phy) +mt7996_mcu_bss_rfch_tlv(struct sk_buff *skb, struct mt7996_phy *phy) { static const u8 rlm_ch_band[] = { [NL80211_BAND_2GHZ] = 1, @@ -775,8 +786,7 @@ mt7996_mcu_bss_rfch_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, } static void -mt7996_mcu_bss_ra_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct mt7996_phy *phy) +mt7996_mcu_bss_ra_tlv(struct sk_buff *skb, struct mt7996_phy *phy) { struct bss_ra_tlv *ra; struct tlv *tlv; @@ -789,6 +799,7 @@ mt7996_mcu_bss_ra_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, static void mt7996_mcu_bss_he_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, struct mt7996_phy *phy) { #define DEFAULT_HE_PE_DURATION 4 @@ -802,11 +813,11 @@ mt7996_mcu_bss_he_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_HE_BASIC, sizeof(*he)); he = (struct bss_info_uni_he *)tlv; - he->he_pe_duration = vif->bss_conf.htc_trig_based_pkt_ext; + he->he_pe_duration = link_conf->htc_trig_based_pkt_ext; if (!he->he_pe_duration) he->he_pe_duration = DEFAULT_HE_PE_DURATION; - he->he_rts_thres = cpu_to_le16(vif->bss_conf.frame_time_rts_th); + he->he_rts_thres = cpu_to_le16(link_conf->frame_time_rts_th); if (!he->he_rts_thres) he->he_rts_thres = cpu_to_le16(DEFAULT_HE_DURATION_RTS_THRES); @@ -816,13 +827,13 @@ mt7996_mcu_bss_he_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, } static void -mt7996_mcu_bss_mbssid_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct mt7996_phy *phy, int enable) +mt7996_mcu_bss_mbssid_tlv(struct sk_buff *skb, struct ieee80211_bss_conf *link_conf, + bool enable) { struct bss_info_uni_mbssid *mbssid; struct tlv *tlv; - if (!vif->bss_conf.bssid_indicator && enable) + if (!link_conf->bssid_indicator && enable) return; tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_11V_MBSSID, sizeof(*mbssid)); @@ -830,23 +841,22 @@ mt7996_mcu_bss_mbssid_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, mbssid = (struct bss_info_uni_mbssid *)tlv; if (enable) { - mbssid->max_indicator = vif->bss_conf.bssid_indicator; - mbssid->mbss_idx = vif->bss_conf.bssid_index; + mbssid->max_indicator = link_conf->bssid_indicator; + mbssid->mbss_idx = link_conf->bssid_index; mbssid->tx_bss_omac_idx = 0; } } static void -mt7996_mcu_bss_bmc_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, +mt7996_mcu_bss_bmc_tlv(struct sk_buff *skb, struct mt76_vif_link *mlink, struct mt7996_phy *phy) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; struct bss_rate_tlv *bmc; struct cfg80211_chan_def *chandef = &phy->mt76->chandef; enum nl80211_band band = chandef->chan->band; struct tlv *tlv; - u8 idx = mvif->mcast_rates_idx ? - mvif->mcast_rates_idx : mvif->basic_rates_idx; + u8 idx = mlink->mcast_rates_idx ? + mlink->mcast_rates_idx : mlink->basic_rates_idx; tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_RATE, sizeof(*bmc)); @@ -870,9 +880,8 @@ mt7996_mcu_bss_txcmd_tlv(struct sk_buff *skb, bool en) } static void -mt7996_mcu_bss_mld_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) +mt7996_mcu_bss_mld_tlv(struct sk_buff *skb, struct mt76_vif_link *mlink) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct bss_mld_tlv *mld; struct tlv *tlv; @@ -880,33 +889,28 @@ mt7996_mcu_bss_mld_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) mld = (struct bss_mld_tlv *)tlv; mld->group_mld_id = 0xff; - mld->own_mld_id = mvif->mt76.idx; + mld->own_mld_id = mlink->idx; mld->remap_idx = 0xff; } static void -mt7996_mcu_bss_sec_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) +mt7996_mcu_bss_sec_tlv(struct sk_buff *skb, struct mt76_vif_link *mlink) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; struct bss_sec_tlv *sec; struct tlv *tlv; tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_SEC, sizeof(*sec)); sec = (struct bss_sec_tlv *)tlv; - sec->cipher = mvif->cipher; + sec->cipher = mlink->cipher; } static int -mt7996_mcu_muar_config(struct mt7996_phy *phy, struct ieee80211_vif *vif, - bool bssid, bool enable) +mt7996_mcu_muar_config(struct mt7996_dev *dev, struct mt76_vif_link *mlink, + const u8 *addr, bool bssid, bool enable) { #define UNI_MUAR_ENTRY 2 - struct mt7996_dev *dev = phy->dev; - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - u32 idx = mvif->mt76.omac_idx - REPEATER_BSSID_START; - const u8 *addr = vif->addr; - + u32 idx = mlink->omac_idx - REPEATER_BSSID_START; struct { struct { u8 band; @@ -923,7 +927,7 @@ mt7996_mcu_muar_config(struct mt7996_phy *phy, struct ieee80211_vif *vif, u8 addr[ETH_ALEN]; u8 __rsv[2]; } __packed req = { - .hdr.band = phy->mt76->band_idx, + .hdr.band = mlink->band_idx, .tag = cpu_to_le16(UNI_MUAR_ENTRY), .len = cpu_to_le16(sizeof(req) - sizeof(req.hdr)), .smesh = false, @@ -931,9 +935,6 @@ mt7996_mcu_muar_config(struct mt7996_phy *phy, struct ieee80211_vif *vif, .entry_add = true, }; - if (bssid) - addr = vif->bss_conf.bssid; - if (enable) memcpy(req.addr, addr, ETH_ALEN); @@ -942,10 +943,8 @@ mt7996_mcu_muar_config(struct mt7996_phy *phy, struct ieee80211_vif *vif, } static void -mt7996_mcu_bss_ifs_timing_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) +mt7996_mcu_bss_ifs_timing_tlv(struct sk_buff *skb, struct mt7996_phy *phy) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct mt7996_phy *phy = mvif->phy; struct bss_ifs_time_tlv *ifs_time; struct tlv *tlv; bool is_2ghz = phy->mt76->chandef.chan->band == NL80211_BAND_2GHZ; @@ -972,15 +971,16 @@ mt7996_mcu_bss_ifs_timing_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) static int mt7996_mcu_bss_basic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mvif, struct mt76_phy *phy, u16 wlan_idx, bool enable) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; struct cfg80211_chan_def *chandef = &phy->chandef; struct mt76_connac_bss_basic_tlv *bss; u32 type = CONNECTION_INFRA_AP; u16 sta_wlan_idx = wlan_idx; + struct ieee80211_sta *sta; struct tlv *tlv; int idx; @@ -992,9 +992,7 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb, case NL80211_IFTYPE_STATION: if (enable) { rcu_read_lock(); - if (!sta) - sta = ieee80211_find_sta(vif, - vif->bss_conf.bssid); + sta = ieee80211_find_sta(vif, vif->bss_conf.bssid); /* TODO: enable BSS_INFO_UAPSD & BSS_INFO_PM */ if (sta) { struct mt76_wcid *wcid; @@ -1017,8 +1015,8 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb, tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_BASIC, sizeof(*bss)); bss = (struct mt76_connac_bss_basic_tlv *)tlv; - bss->bcn_interval = cpu_to_le16(vif->bss_conf.beacon_int); - bss->dtim_period = vif->bss_conf.dtim_period; + bss->bcn_interval = cpu_to_le16(link_conf->beacon_int); + bss->dtim_period = link_conf->dtim_period; bss->bmc_tx_wlan_idx = cpu_to_le16(wlan_idx); bss->sta_idx = cpu_to_le16(sta_wlan_idx); bss->conn_type = cpu_to_le32(type); @@ -1036,19 +1034,19 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb, return 0; } - memcpy(bss->bssid, vif->bss_conf.bssid, ETH_ALEN); - bss->bcn_interval = cpu_to_le16(vif->bss_conf.beacon_int); + memcpy(bss->bssid, link_conf->bssid, ETH_ALEN); + bss->bcn_interval = cpu_to_le16(link_conf->beacon_int); bss->dtim_period = vif->bss_conf.dtim_period; bss->phymode = mt76_connac_get_phy_mode(phy, vif, chandef->chan->band, NULL); - bss->phymode_ext = mt76_connac_get_phy_mode_ext(phy, vif, + bss->phymode_ext = mt76_connac_get_phy_mode_ext(phy, &vif->bss_conf, chandef->chan->band); return 0; } static struct sk_buff * -__mt7996_mcu_alloc_bss_req(struct mt76_dev *dev, struct mt76_vif *mvif, int len) +__mt7996_mcu_alloc_bss_req(struct mt76_dev *dev, struct mt76_vif_link *mvif, int len) { struct bss_req_hdr hdr = { .bss_idx = mvif->idx, @@ -1064,71 +1062,72 @@ __mt7996_mcu_alloc_bss_req(struct mt76_dev *dev, struct mt76_vif *mvif, int len) return skb; } -int mt7996_mcu_add_bss_info(struct mt7996_phy *phy, - struct ieee80211_vif *vif, int enable) +int mt7996_mcu_add_bss_info(struct mt7996_phy *phy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink, int enable) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct mt7996_dev *dev = phy->dev; struct sk_buff *skb; - if (mvif->mt76.omac_idx >= REPEATER_BSSID_START) { - mt7996_mcu_muar_config(phy, vif, false, enable); - mt7996_mcu_muar_config(phy, vif, true, enable); + if (mlink->omac_idx >= REPEATER_BSSID_START) { + mt7996_mcu_muar_config(dev, mlink, link_conf->addr, false, enable); + mt7996_mcu_muar_config(dev, mlink, link_conf->bssid, true, enable); } - skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76, + skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, mlink, MT7996_BSS_UPDATE_MAX_SIZE); if (IS_ERR(skb)) return PTR_ERR(skb); /* bss_basic must be first */ - mt7996_mcu_bss_basic_tlv(skb, vif, NULL, phy->mt76, - mvif->sta.wcid.idx, enable); - mt7996_mcu_bss_sec_tlv(skb, vif); + mt7996_mcu_bss_basic_tlv(skb, vif, link_conf, mlink, phy->mt76, + mlink->wcid->idx, enable); + mt7996_mcu_bss_sec_tlv(skb, mlink); if (vif->type == NL80211_IFTYPE_MONITOR) goto out; if (enable) { - mt7996_mcu_bss_rfch_tlv(skb, vif, phy); - mt7996_mcu_bss_bmc_tlv(skb, vif, phy); - mt7996_mcu_bss_ra_tlv(skb, vif, phy); + mt7996_mcu_bss_rfch_tlv(skb, phy); + mt7996_mcu_bss_bmc_tlv(skb, mlink, phy); + mt7996_mcu_bss_ra_tlv(skb, phy); mt7996_mcu_bss_txcmd_tlv(skb, true); - mt7996_mcu_bss_ifs_timing_tlv(skb, vif); + mt7996_mcu_bss_ifs_timing_tlv(skb, phy); if (vif->bss_conf.he_support) - mt7996_mcu_bss_he_tlv(skb, vif, phy); + mt7996_mcu_bss_he_tlv(skb, vif, link_conf, phy); /* this tag is necessary no matter if the vif is MLD */ - mt7996_mcu_bss_mld_tlv(skb, vif); + mt7996_mcu_bss_mld_tlv(skb, mlink); } - mt7996_mcu_bss_mbssid_tlv(skb, vif, phy, enable); + mt7996_mcu_bss_mbssid_tlv(skb, link_conf, enable); out: return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_WMWA_UNI_CMD(BSS_INFO_UPDATE), true); } -int mt7996_mcu_set_timing(struct mt7996_phy *phy, struct ieee80211_vif *vif) +int mt7996_mcu_set_timing(struct mt7996_phy *phy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct mt7996_dev *dev = phy->dev; + struct mt76_vif_link *mlink = mt76_vif_conf_link(&dev->mt76, vif, link_conf); struct sk_buff *skb; - skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76, + skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, mlink, MT7996_BSS_UPDATE_MAX_SIZE); if (IS_ERR(skb)) return PTR_ERR(skb); - mt7996_mcu_bss_ifs_timing_tlv(skb, vif); + mt7996_mcu_bss_ifs_timing_tlv(skb, phy); return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_WMWA_UNI_CMD(BSS_INFO_UPDATE), true); } static int -mt7996_mcu_sta_ba(struct mt7996_dev *dev, struct mt76_vif *mvif, +mt7996_mcu_sta_ba(struct mt7996_dev *dev, struct mt76_vif_link *mvif, struct ieee80211_ampdu_params *params, bool enable, bool tx) { @@ -1168,7 +1167,7 @@ int mt7996_mcu_add_tx_ba(struct mt7996_dev *dev, if (enable && !params->amsdu) msta->wcid.amsdu = false; - return mt7996_mcu_sta_ba(dev, &mvif->mt76, params, enable, true); + return mt7996_mcu_sta_ba(dev, &mvif->deflink.mt76, params, enable, true); } int mt7996_mcu_add_rx_ba(struct mt7996_dev *dev, @@ -1178,7 +1177,7 @@ int mt7996_mcu_add_rx_ba(struct mt7996_dev *dev, struct mt7996_sta *msta = (struct mt7996_sta *)params->sta->drv_priv; struct mt7996_vif *mvif = msta->vif; - return mt7996_mcu_sta_ba(dev, &mvif->mt76, params, enable, false); + return mt7996_mcu_sta_ba(dev, &mvif->deflink.mt76, params, enable, false); } static void @@ -1461,17 +1460,21 @@ mt7996_is_ebf_supported(struct mt7996_phy *phy, struct ieee80211_vif *vif, } static void -mt7996_mcu_sta_sounding_rate(struct sta_rec_bf *bf) +mt7996_mcu_sta_sounding_rate(struct sta_rec_bf *bf, struct mt7996_phy *phy) { bf->sounding_phy = MT_PHY_TYPE_OFDM; bf->ndp_rate = 0; /* mcs0 */ - bf->ndpa_rate = MT7996_CFEND_RATE_DEFAULT; /* ofdm 24m */ + if (is_mt7996(phy->mt76->dev)) + bf->ndpa_rate = MT7996_CFEND_RATE_DEFAULT; /* ofdm 24m */ + else + bf->ndpa_rate = MT7992_CFEND_RATE_DEFAULT; /* ofdm 6m */ + bf->rept_poll_rate = MT7996_CFEND_RATE_DEFAULT; /* ofdm 24m */ } static void mt7996_mcu_sta_bfer_ht(struct ieee80211_sta *sta, struct mt7996_phy *phy, - struct sta_rec_bf *bf) + struct sta_rec_bf *bf, bool explicit) { struct ieee80211_mcs_info *mcs = &sta->deflink.ht_cap.mcs; u8 n = 0; @@ -1491,7 +1494,8 @@ mt7996_mcu_sta_bfer_ht(struct ieee80211_sta *sta, struct mt7996_phy *phy, bf->nrow = hweight8(phy->mt76->antenna_mask) - 1; bf->ncol = min_t(u8, bf->nrow, n); - bf->ibf_ncol = n; + bf->ibf_ncol = explicit ? min_t(u8, MT7996_IBF_MAX_NC, bf->ncol) : + min_t(u8, MT7996_IBF_MAX_NC, n); } static void @@ -1509,7 +1513,7 @@ mt7996_mcu_sta_bfer_vht(struct ieee80211_sta *sta, struct mt7996_phy *phy, if (explicit) { u8 sts, snd_dim; - mt7996_mcu_sta_sounding_rate(bf); + mt7996_mcu_sta_sounding_rate(bf, phy); sts = FIELD_GET(IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK, pc->cap); @@ -1517,14 +1521,14 @@ mt7996_mcu_sta_bfer_vht(struct ieee80211_sta *sta, struct mt7996_phy *phy, vc->cap); bf->nrow = min_t(u8, min_t(u8, snd_dim, sts), tx_ant); bf->ncol = min_t(u8, nss_mcs, bf->nrow); - bf->ibf_ncol = bf->ncol; + bf->ibf_ncol = min_t(u8, MT7996_IBF_MAX_NC, bf->ncol); if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160) bf->nrow = 1; } else { bf->nrow = tx_ant; bf->ncol = min_t(u8, nss_mcs, bf->nrow); - bf->ibf_ncol = nss_mcs; + bf->ibf_ncol = min_t(u8, MT7996_IBF_MAX_NC, nss_mcs); if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160) bf->ibf_nrow = 1; @@ -1533,7 +1537,8 @@ mt7996_mcu_sta_bfer_vht(struct ieee80211_sta *sta, struct mt7996_phy *phy, static void mt7996_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif, - struct mt7996_phy *phy, struct sta_rec_bf *bf) + struct mt7996_phy *phy, struct sta_rec_bf *bf, + bool explicit) { struct ieee80211_sta_he_cap *pc = &sta->deflink.he_cap; struct ieee80211_he_cap_elem *pe = &pc->he_cap_elem; @@ -1549,7 +1554,7 @@ mt7996_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif, bf->tx_mode = MT_PHY_TYPE_HE_SU; - mt7996_mcu_sta_sounding_rate(bf); + mt7996_mcu_sta_sounding_rate(bf, phy); bf->trigger_su = HE_PHY(CAP6_TRIG_SU_BEAMFORMING_FB, pe->phy_cap_info[6]); @@ -1561,7 +1566,8 @@ mt7996_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif, pe->phy_cap_info[4]); bf->nrow = min_t(u8, snd_dim, sts); bf->ncol = min_t(u8, nss_mcs, bf->nrow); - bf->ibf_ncol = bf->ncol; + bf->ibf_ncol = explicit ? min_t(u8, MT7996_IBF_MAX_NC, bf->ncol) : + min_t(u8, MT7996_IBF_MAX_NC, nss_mcs); if (sta->deflink.bandwidth != IEEE80211_STA_RX_BW_160) return; @@ -1596,7 +1602,8 @@ mt7996_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif, static void mt7996_mcu_sta_bfer_eht(struct ieee80211_sta *sta, struct ieee80211_vif *vif, - struct mt7996_phy *phy, struct sta_rec_bf *bf) + struct mt7996_phy *phy, struct sta_rec_bf *bf, + bool explicit) { struct ieee80211_sta_eht_cap *pc = &sta->deflink.eht_cap; struct ieee80211_eht_cap_elem_fixed *pe = &pc->eht_cap_elem; @@ -1610,7 +1617,7 @@ mt7996_mcu_sta_bfer_eht(struct ieee80211_sta *sta, struct ieee80211_vif *vif, bf->tx_mode = MT_PHY_TYPE_EHT_MU; - mt7996_mcu_sta_sounding_rate(bf); + mt7996_mcu_sta_sounding_rate(bf, phy); bf->trigger_su = EHT_PHY(CAP3_TRIG_SU_BF_FDBK, pe->phy_cap_info[3]); bf->trigger_mu = EHT_PHY(CAP3_TRIG_MU_BF_PART_BW_FDBK, pe->phy_cap_info[3]); @@ -1619,7 +1626,8 @@ mt7996_mcu_sta_bfer_eht(struct ieee80211_sta *sta, struct ieee80211_vif *vif, (EHT_PHY(CAP1_BEAMFORMEE_SS_80MHZ_MASK, pe->phy_cap_info[1]) << 1); bf->nrow = min_t(u8, snd_dim, sts); bf->ncol = min_t(u8, nss_mcs, bf->nrow); - bf->ibf_ncol = bf->ncol; + bf->ibf_ncol = explicit ? min_t(u8, MT7996_IBF_MAX_NC, bf->ncol) : + min_t(u8, MT7996_IBF_MAX_NC, nss_mcs); if (sta->deflink.bandwidth < IEEE80211_STA_RX_BW_160) return; @@ -1654,12 +1662,15 @@ static void mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { +#define EBF_MODE BIT(0) +#define IBF_MODE BIT(1) +#define BF_MAT_ORDER 4 struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct mt7996_phy *phy = mvif->phy; + struct mt7996_phy *phy = mvif->deflink.phy; int tx_ant = hweight16(phy->mt76->chainmask) - 1; struct sta_rec_bf *bf; struct tlv *tlv; - static const u8 matrix[4][4] = { + static const u8 matrix[BF_MAT_ORDER][BF_MAT_ORDER] = { {0, 0, 0, 0}, {1, 1, 0, 0}, /* 2x1, 2x2, 2x3, 2x4 */ {2, 4, 4, 0}, /* 3x1, 3x2, 3x3, 3x4 */ @@ -1677,35 +1688,44 @@ mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb, tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_BF, sizeof(*bf)); bf = (struct sta_rec_bf *)tlv; - /* he/eht: eBF only, in accordance with spec + /* he/eht: eBF only, except mt7992 that has 5T on 5GHz also supports iBF * vht: support eBF and iBF * ht: iBF only, since mac80211 lacks of eBF support */ - if (sta->deflink.eht_cap.has_eht && ebf) - mt7996_mcu_sta_bfer_eht(sta, vif, phy, bf); - else if (sta->deflink.he_cap.has_he && ebf) - mt7996_mcu_sta_bfer_he(sta, vif, phy, bf); + if (sta->deflink.eht_cap.has_eht) + mt7996_mcu_sta_bfer_eht(sta, vif, phy, bf, ebf); + else if (sta->deflink.he_cap.has_he) + mt7996_mcu_sta_bfer_he(sta, vif, phy, bf, ebf); else if (sta->deflink.vht_cap.vht_supported) mt7996_mcu_sta_bfer_vht(sta, phy, bf, ebf); else if (sta->deflink.ht_cap.ht_supported) - mt7996_mcu_sta_bfer_ht(sta, phy, bf); + mt7996_mcu_sta_bfer_ht(sta, phy, bf, ebf); else return; - bf->bf_cap = ebf ? ebf : dev->ibf << 1; + bf->bf_cap = ebf ? EBF_MODE : (dev->ibf ? IBF_MODE : 0); + if (is_mt7992(&dev->mt76) && tx_ant == 4) + bf->bf_cap |= IBF_MODE; bf->bw = sta->deflink.bandwidth; bf->ibf_dbw = sta->deflink.bandwidth; bf->ibf_nrow = tx_ant; - if (!ebf && sta->deflink.bandwidth <= IEEE80211_STA_RX_BW_40 && !bf->ncol) - bf->ibf_timeout = 0x48; + if (sta->deflink.eht_cap.has_eht || sta->deflink.he_cap.has_he) + bf->ibf_timeout = is_mt7996(&dev->mt76) ? MT7996_IBF_TIMEOUT : + MT7992_IBF_TIMEOUT; + else if (!ebf && sta->deflink.bandwidth <= IEEE80211_STA_RX_BW_40 && !bf->ncol) + bf->ibf_timeout = MT7996_IBF_TIMEOUT_LEGACY; else - bf->ibf_timeout = 0x18; + bf->ibf_timeout = MT7996_IBF_TIMEOUT; - if (ebf && bf->nrow != tx_ant) - bf->mem_20m = matrix[tx_ant][bf->ncol]; - else - bf->mem_20m = matrix[bf->nrow][bf->ncol]; + if (bf->ncol < BF_MAT_ORDER) { + if (ebf) + bf->mem_20m = tx_ant < BF_MAT_ORDER ? + matrix[tx_ant][bf->ncol] : 0; + else + bf->mem_20m = bf->nrow < BF_MAT_ORDER ? + matrix[bf->nrow][bf->ncol] : 0; + } switch (sta->deflink.bandwidth) { case IEEE80211_STA_RX_BW_160: @@ -1726,7 +1746,7 @@ mt7996_mcu_sta_bfee_tlv(struct mt7996_dev *dev, struct sk_buff *skb, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct mt7996_phy *phy = mvif->phy; + struct mt7996_phy *phy = mvif->deflink.phy; int tx_ant = hweight8(phy->mt76->antenna_mask) - 1; struct sta_rec_bfee *bfee; struct tlv *tlv; @@ -1783,11 +1803,9 @@ mt7996_mcu_sta_hdrt_tlv(struct mt7996_dev *dev, struct sk_buff *skb) static void mt7996_mcu_sta_hdr_trans_tlv(struct mt7996_dev *dev, struct sk_buff *skb, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta) + struct ieee80211_vif *vif, struct mt76_wcid *wcid) { struct sta_rec_hdr_trans *hdr_trans; - struct mt76_wcid *wcid; struct tlv *tlv; tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_HDR_TRANS, sizeof(*hdr_trans)); @@ -1799,10 +1817,9 @@ mt7996_mcu_sta_hdr_trans_tlv(struct mt7996_dev *dev, struct sk_buff *skb, else hdr_trans->from_ds = true; - if (!sta) + if (!wcid) return; - wcid = (struct mt76_wcid *)sta->drv_priv; hdr_trans->dis_rx_hdr_tran = !test_bit(MT_WCID_FLAG_HDR_TRANS, &wcid->flags); if (test_bit(MT_WCID_FLAG_4ADDR, &wcid->flags)) { hdr_trans->to_ds = true; @@ -1867,7 +1884,7 @@ int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif struct sk_buff *skb; struct tlv *tlv; - skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76, &msta->wcid, MT7996_STA_UPDATE_MAX_SIZE); if (IS_ERR(skb)) @@ -1903,8 +1920,8 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif struct ieee80211_sta *sta) { struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct cfg80211_chan_def *chandef = &mvif->phy->mt76->chandef; - struct cfg80211_bitrate_mask *mask = &mvif->bitrate_mask; + struct cfg80211_chan_def *chandef = &mvif->deflink.phy->mt76->chandef; + struct cfg80211_bitrate_mask *mask = &mvif->deflink.bitrate_mask; enum nl80211_band band = chandef->chan->band; struct sta_phy_uni phy = {}; int ret, nrates = 0; @@ -1991,9 +2008,9 @@ mt7996_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7996_dev *dev, { #define INIT_RCPI 180 struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct mt76_phy *mphy = mvif->phy->mt76; + struct mt76_phy *mphy = mvif->deflink.phy->mt76; struct cfg80211_chan_def *chandef = &mphy->chandef; - struct cfg80211_bitrate_mask *mask = &mvif->bitrate_mask; + struct cfg80211_bitrate_mask *mask = &mvif->deflink.bitrate_mask; enum nl80211_band band = chandef->chan->band; struct sta_rec_ra_uni *ra; struct tlv *tlv; @@ -2070,7 +2087,7 @@ mt7996_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7996_dev *dev, cap |= STA_CAP_VHT_TX_STBC; if (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXSTBC_1) cap |= STA_CAP_VHT_RX_STBC; - if (vif->bss_conf.vht_ldpc && + if ((vif->type != NL80211_IFTYPE_AP || vif->bss_conf.vht_ldpc) && (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC)) cap |= STA_CAP_VHT_LDPC; @@ -2099,7 +2116,7 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct ieee80211_vif *vif, struct sk_buff *skb; int ret; - skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76, &msta->wcid, MT7996_STA_UPDATE_MAX_SIZE); if (IS_ERR(skb)) @@ -2146,10 +2163,10 @@ mt7996_mcu_add_group(struct mt7996_dev *dev, struct ieee80211_vif *vif, .tag = cpu_to_le16(UNI_VOW_DRR_CTRL), .len = cpu_to_le16(sizeof(req) - 4), .action = cpu_to_le32(MT_STA_BSS_GROUP), - .val = cpu_to_le32(mvif->mt76.idx % 16), + .val = cpu_to_le32(mvif->deflink.mt76.idx % 16), }; - msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->sta; + msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->deflink.sta; req.wlan_idx = cpu_to_le16(msta->wcid.idx); return mt76_mcu_send_msg(&dev->mt76, MCU_WM_UNI_CMD(VOW), &req, @@ -2157,34 +2174,35 @@ mt7996_mcu_add_group(struct mt7996_dev *dev, struct ieee80211_vif *vif, } int mt7996_mcu_add_sta(struct mt7996_dev *dev, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, bool enable, bool newly) + struct mt76_vif_link *mlink, + struct ieee80211_sta *sta, int conn_state, bool newly) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct ieee80211_link_sta *link_sta; - struct mt7996_sta *msta; + struct ieee80211_link_sta *link_sta = NULL; + struct mt76_wcid *wcid = mlink->wcid; struct sk_buff *skb; - int conn_state; int ret; - msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->sta; - link_sta = sta ? &sta->deflink : NULL; + if (sta) { + struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; - skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, - &msta->wcid, + wcid = &msta->wcid; + link_sta = &sta->deflink; + } + + skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, mlink, wcid, MT7996_STA_UPDATE_MAX_SIZE); if (IS_ERR(skb)) return PTR_ERR(skb); /* starec basic */ - conn_state = enable ? CONN_STATE_PORT_SECURE : CONN_STATE_DISCONNECT; - mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, vif, link_sta, + mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, &vif->bss_conf, link_sta, conn_state, newly); - if (!enable) + if (conn_state == CONN_STATE_DISCONNECT) goto out; /* starec hdr trans */ - mt7996_mcu_sta_hdr_trans_tlv(dev, skb, vif, sta); + mt7996_mcu_sta_hdr_trans_tlv(dev, skb, vif, wcid); /* starec tx proc */ mt7996_mcu_sta_tx_proc_tlv(skb); @@ -2273,7 +2291,7 @@ int mt7996_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, struct ieee80211_key_conf *key, int mcu_cmd, struct mt76_wcid *wcid, enum set_key_cmd cmd) { - struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct sk_buff *skb; int ret; @@ -2299,7 +2317,7 @@ static int mt7996_mcu_get_pn(struct mt7996_dev *dev, struct ieee80211_vif *vif, struct tlv *tlv; int ret; - skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, &mvif->sta.wcid); + skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76, &mvif->deflink.sta.wcid); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -2335,7 +2353,7 @@ int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, struct ieee80211_vif *vif sizeof(struct mt7996_mcu_bcn_prot_tlv); int ret; - skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76, len); + skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->deflink.mt76, len); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -2375,11 +2393,12 @@ int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, struct ieee80211_vif *vif return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_WMWA_UNI_CMD(BSS_INFO_UPDATE), true); } -int mt7996_mcu_add_dev_info(struct mt7996_phy *phy, - struct ieee80211_vif *vif, bool enable) + +int mt7996_mcu_add_dev_info(struct mt7996_phy *phy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink, bool enable) { struct mt7996_dev *dev = phy->dev; - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct { struct req_hdr { u8 omac_idx; @@ -2395,8 +2414,8 @@ int mt7996_mcu_add_dev_info(struct mt7996_phy *phy, } __packed tlv; } data = { .hdr = { - .omac_idx = mvif->mt76.omac_idx, - .band_idx = mvif->mt76.band_idx, + .omac_idx = mlink->omac_idx, + .band_idx = mlink->band_idx, }, .tlv = { .tag = cpu_to_le16(DEV_INFO_ACTIVE), @@ -2405,18 +2424,18 @@ int mt7996_mcu_add_dev_info(struct mt7996_phy *phy, }, }; - if (mvif->mt76.omac_idx >= REPEATER_BSSID_START) - return mt7996_mcu_muar_config(phy, vif, false, enable); + if (mlink->omac_idx >= REPEATER_BSSID_START) + return mt7996_mcu_muar_config(dev, mlink, link_conf->addr, false, enable); - memcpy(data.tlv.omac_addr, vif->addr, ETH_ALEN); + memcpy(data.tlv.omac_addr, link_conf->addr, ETH_ALEN); return mt76_mcu_send_msg(&dev->mt76, MCU_WMWA_UNI_CMD(DEV_INFO_UPDATE), &data, sizeof(data), true); } static void -mt7996_mcu_beacon_cntdwn(struct ieee80211_vif *vif, struct sk_buff *rskb, - struct sk_buff *skb, - struct ieee80211_mutable_offsets *offs) +mt7996_mcu_beacon_cntdwn(struct sk_buff *rskb, struct sk_buff *skb, + struct ieee80211_mutable_offsets *offs, + bool csa) { struct bss_bcn_cntdwn_tlv *info; struct tlv *tlv; @@ -2425,7 +2444,7 @@ mt7996_mcu_beacon_cntdwn(struct ieee80211_vif *vif, struct sk_buff *rskb, if (!offs->cntdwn_counter_offs[0]) return; - tag = vif->bss_conf.csa_active ? UNI_BSS_INFO_BCN_CSA : UNI_BSS_INFO_BCN_BCC; + tag = csa ? UNI_BSS_INFO_BCN_CSA : UNI_BSS_INFO_BCN_BCC; tlv = mt7996_mcu_add_uni_tlv(rskb, tag, sizeof(*info)); @@ -2435,16 +2454,13 @@ mt7996_mcu_beacon_cntdwn(struct ieee80211_vif *vif, struct sk_buff *rskb, static void mt7996_mcu_beacon_mbss(struct sk_buff *rskb, struct sk_buff *skb, - struct ieee80211_vif *vif, struct bss_bcn_content_tlv *bcn, + struct bss_bcn_content_tlv *bcn, struct ieee80211_mutable_offsets *offs) { struct bss_bcn_mbss_tlv *mbss; const struct element *elem; struct tlv *tlv; - if (!vif->bss_conf.bssid_indicator) - return; - tlv = mt7996_mcu_add_uni_tlv(rskb, UNI_BSS_INFO_BCN_MBSSID, sizeof(*mbss)); mbss = (struct bss_bcn_mbss_tlv *)tlv; @@ -2487,7 +2503,8 @@ mt7996_mcu_beacon_mbss(struct sk_buff *rskb, struct sk_buff *skb, } static void -mt7996_mcu_beacon_cont(struct mt7996_dev *dev, struct ieee80211_vif *vif, +mt7996_mcu_beacon_cont(struct mt7996_dev *dev, + struct ieee80211_bss_conf *link_conf, struct sk_buff *rskb, struct sk_buff *skb, struct bss_bcn_content_tlv *bcn, struct ieee80211_mutable_offsets *offs) @@ -2501,9 +2518,9 @@ mt7996_mcu_beacon_cont(struct mt7996_dev *dev, struct ieee80211_vif *vif, if (offs->cntdwn_counter_offs[0]) { u16 offset = offs->cntdwn_counter_offs[0]; - if (vif->bss_conf.csa_active) + if (link_conf->csa_active) bcn->csa_ie_pos = cpu_to_le16(offset - 4); - if (vif->bss_conf.color_change_active) + if (link_conf->color_change_active) bcn->bcc_ie_pos = cpu_to_le16(offset - 3); } @@ -2514,56 +2531,63 @@ mt7996_mcu_beacon_cont(struct mt7996_dev *dev, struct ieee80211_vif *vif, memcpy(buf + MT_TXD_SIZE, skb->data, skb->len); } -int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, int en) +int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf) { struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_phy *phy = mt7996_hw_phy(hw); - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; + struct mt76_vif_link *mlink = mt76_vif_conf_link(&dev->mt76, vif, link_conf); struct ieee80211_mutable_offsets offs; struct ieee80211_tx_info *info; struct sk_buff *skb, *rskb; struct tlv *tlv; struct bss_bcn_content_tlv *bcn; - int len; + int len, extra_len = 0; - if (vif->bss_conf.nontransmitted) + if (link_conf->nontransmitted) return 0; - rskb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76, + if (!mlink) + return -EINVAL; + + rskb = __mt7996_mcu_alloc_bss_req(&dev->mt76, mlink, MT7996_MAX_BSS_OFFLOAD_SIZE); if (IS_ERR(rskb)) return PTR_ERR(rskb); - skb = ieee80211_beacon_get_template(hw, vif, &offs, 0); - if (!skb) { + skb = ieee80211_beacon_get_template(hw, vif, &offs, link_conf->link_id); + if (link_conf->enable_beacon && !skb) { dev_kfree_skb(rskb); return -EINVAL; } - if (skb->len > MT7996_MAX_BEACON_SIZE) { - dev_err(dev->mt76.dev, "Bcn size limit exceed\n"); - dev_kfree_skb(rskb); - dev_kfree_skb(skb); - return -EINVAL; + if (skb) { + if (skb->len > MT7996_MAX_BEACON_SIZE) { + dev_err(dev->mt76.dev, "Bcn size limit exceed\n"); + dev_kfree_skb(rskb); + dev_kfree_skb(skb); + return -EINVAL; + } + + extra_len = skb->len; } - info = IEEE80211_SKB_CB(skb); - info->hw_queue |= FIELD_PREP(MT_TX_HW_QUEUE_PHY, phy->mt76->band_idx); - - len = ALIGN(sizeof(*bcn) + MT_TXD_SIZE + skb->len, 4); + len = ALIGN(sizeof(*bcn) + MT_TXD_SIZE + extra_len, 4); tlv = mt7996_mcu_add_uni_tlv(rskb, UNI_BSS_INFO_BCN_CONTENT, len); bcn = (struct bss_bcn_content_tlv *)tlv; - bcn->enable = en; - if (!en) + bcn->enable = link_conf->enable_beacon; + if (!bcn->enable) goto out; - mt7996_mcu_beacon_cont(dev, vif, rskb, skb, bcn, &offs); - mt7996_mcu_beacon_mbss(rskb, skb, vif, bcn, &offs); - mt7996_mcu_beacon_cntdwn(vif, rskb, skb, &offs); + info = IEEE80211_SKB_CB(skb); + info->hw_queue |= FIELD_PREP(MT_TX_HW_QUEUE_PHY, mlink->band_idx); + + mt7996_mcu_beacon_cont(dev, link_conf, rskb, skb, bcn, &offs); + if (link_conf->bssid_indicator) + mt7996_mcu_beacon_mbss(rskb, skb, bcn, &offs); + mt7996_mcu_beacon_cntdwn(rskb, skb, &offs, link_conf->csa_active); out: dev_kfree_skb(skb); - return mt76_mcu_skb_send_msg(&phy->dev->mt76, rskb, + return mt76_mcu_skb_send_msg(&dev->mt76, rskb, MCU_WMWA_UNI_CMD(BSS_INFO_UPDATE), true); } @@ -2573,22 +2597,28 @@ int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev, #define OFFLOAD_TX_MODE_SU BIT(0) #define OFFLOAD_TX_MODE_MU BIT(1) struct ieee80211_hw *hw = mt76_hw(dev); - struct mt7996_phy *phy = mt7996_hw_phy(hw); struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct cfg80211_chan_def *chandef = &mvif->phy->mt76->chandef; - enum nl80211_band band = chandef->chan->band; + struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink); struct mt76_wcid *wcid = &dev->mt76.global_wcid; struct bss_inband_discovery_tlv *discov; struct ieee80211_tx_info *info; struct sk_buff *rskb, *skb = NULL; + struct cfg80211_chan_def *chandef; + enum nl80211_band band; struct tlv *tlv; u8 *buf, interval; int len; + if (!phy) + return -EINVAL; + + chandef = &phy->mt76->chandef; + band = chandef->chan->band; + if (vif->bss_conf.nontransmitted) return 0; - rskb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76, + rskb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->deflink.mt76, MT7996_MAX_BSS_OFFLOAD_SIZE); if (IS_ERR(rskb)) return PTR_ERR(rskb); @@ -3147,7 +3177,8 @@ int mt7996_mcu_set_hdr_trans(struct mt7996_dev *dev, bool hdr_trans) MCU_WM_UNI_CMD(RX_HDR_TRANS), true); } -int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif) +int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf) { #define MCU_EDCA_AC_PARAM 0 #define WMM_AIFS_SET BIT(0) @@ -3156,12 +3187,12 @@ int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif) #define WMM_TXOP_SET BIT(3) #define WMM_PARAM_SET (WMM_AIFS_SET | WMM_CW_MIN_SET | \ WMM_CW_MAX_SET | WMM_TXOP_SET) - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; + struct mt7996_vif_link *link = mt7996_vif_conf_link(dev, vif, link_conf); struct { u8 bss_idx; u8 __rsv[3]; } __packed hdr = { - .bss_idx = mvif->mt76.idx, + .bss_idx = link->mt76.idx, }; struct sk_buff *skb; int len = sizeof(hdr) + IEEE80211_NUM_ACS * sizeof(struct edca); @@ -3174,7 +3205,7 @@ int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif) skb_put_data(skb, &hdr, sizeof(hdr)); for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - struct ieee80211_tx_queue_params *q = &mvif->queue_params[ac]; + struct ieee80211_tx_queue_params *q = &link->queue_params[ac]; struct edca *e; struct tlv *tlv; @@ -3548,7 +3579,7 @@ int mt7996_mcu_set_eeprom(struct mt7996_dev *dev) &req, sizeof(req), true); } -int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset) +int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset, u8 *buf, u32 buf_len) { struct { u8 _rsv[4]; @@ -3577,15 +3608,21 @@ int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset) valid = le32_to_cpu(*(__le32 *)(skb->data + 16)); if (valid) { u32 addr = le32_to_cpu(*(__le32 *)(skb->data + 12)); - u8 *buf = (u8 *)dev->mt76.eeprom.data + addr; + + if (!buf) + buf = (u8 *)dev->mt76.eeprom.data + addr; + if (!buf_len || buf_len > MT7996_EEPROM_BLOCK_SIZE) + buf_len = MT7996_EEPROM_BLOCK_SIZE; skb_pull(skb, 48); - memcpy(buf, skb->data, MT7996_EEPROM_BLOCK_SIZE); + memcpy(buf, skb->data, buf_len); + } else { + ret = -EINVAL; } dev_kfree_skb(skb); - return 0; + return ret; } int mt7996_mcu_get_eeprom_free_block(struct mt7996_dev *dev, u8 *block_num) @@ -3666,6 +3703,13 @@ int mt7996_mcu_get_chip_config(struct mt7996_dev *dev, u32 *cap) int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch) { + enum { + IDX_TX_TIME, + IDX_RX_TIME, + IDX_OBSS_AIRTIME, + IDX_NON_WIFI_TIME, + IDX_NUM + }; struct { struct { u8 band; @@ -3675,16 +3719,15 @@ int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch) __le16 tag; __le16 len; __le32 offs; - } data[4]; + } data[IDX_NUM]; } __packed req = { .hdr.band = phy->mt76->band_idx, }; - /* strict order */ static const u32 offs[] = { - UNI_MIB_TX_TIME, - UNI_MIB_RX_TIME, - UNI_MIB_OBSS_AIRTIME, - UNI_MIB_NON_WIFI_TIME, + [IDX_TX_TIME] = UNI_MIB_TX_TIME, + [IDX_RX_TIME] = UNI_MIB_RX_TIME, + [IDX_OBSS_AIRTIME] = UNI_MIB_OBSS_AIRTIME, + [IDX_NON_WIFI_TIME] = UNI_MIB_NON_WIFI_TIME, }; struct mt76_channel_state *state = phy->mt76->chan_state; struct mt76_channel_state *state_ts = &phy->state_ts; @@ -3693,7 +3736,7 @@ int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch) struct sk_buff *skb; int i, ret; - for (i = 0; i < 4; i++) { + for (i = 0; i < IDX_NUM; i++) { req.data[i].tag = cpu_to_le16(UNI_CMD_MIB_DATA); req.data[i].len = cpu_to_le16(sizeof(req.data[i])); req.data[i].offs = cpu_to_le32(offs[i]); @@ -3712,17 +3755,24 @@ int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch) goto out; #define __res_u64(s) le64_to_cpu(res[s].data) - state->cc_tx += __res_u64(1) - state_ts->cc_tx; - state->cc_bss_rx += __res_u64(2) - state_ts->cc_bss_rx; - state->cc_rx += __res_u64(2) + __res_u64(3) - state_ts->cc_rx; - state->cc_busy += __res_u64(0) + __res_u64(1) + __res_u64(2) + __res_u64(3) - + state->cc_tx += __res_u64(IDX_TX_TIME) - state_ts->cc_tx; + state->cc_bss_rx += __res_u64(IDX_RX_TIME) - state_ts->cc_bss_rx; + state->cc_rx += __res_u64(IDX_RX_TIME) + + __res_u64(IDX_OBSS_AIRTIME) - + state_ts->cc_rx; + state->cc_busy += __res_u64(IDX_TX_TIME) + + __res_u64(IDX_RX_TIME) + + __res_u64(IDX_OBSS_AIRTIME) + + __res_u64(IDX_NON_WIFI_TIME) - state_ts->cc_busy; - out: - state_ts->cc_tx = __res_u64(1); - state_ts->cc_bss_rx = __res_u64(2); - state_ts->cc_rx = __res_u64(2) + __res_u64(3); - state_ts->cc_busy = __res_u64(0) + __res_u64(1) + __res_u64(2) + __res_u64(3); + state_ts->cc_tx = __res_u64(IDX_TX_TIME); + state_ts->cc_bss_rx = __res_u64(IDX_RX_TIME); + state_ts->cc_rx = __res_u64(IDX_RX_TIME) + __res_u64(IDX_OBSS_AIRTIME); + state_ts->cc_busy = __res_u64(IDX_TX_TIME) + + __res_u64(IDX_RX_TIME) + + __res_u64(IDX_OBSS_AIRTIME) + + __res_u64(IDX_NON_WIFI_TIME); #undef __res_u64 dev_kfree_skb(skb); @@ -4023,7 +4073,7 @@ mt7996_mcu_set_obss_spr_siga(struct mt7996_phy *phy, struct ieee80211_vif *vif, { struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct mt7996_dev *dev = phy->dev; - u8 omac = mvif->mt76.omac_idx; + u8 omac = mvif->deflink.mt76.omac_idx; struct { u8 band_idx; u8 __rsv[3]; @@ -4137,16 +4187,16 @@ int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy, struct ieee80211_vif *vif, return mt7996_mcu_set_obss_spr_bitmap(phy, he_obss_pd); } -int mt7996_mcu_update_bss_color(struct mt7996_dev *dev, struct ieee80211_vif *vif, +int mt7996_mcu_update_bss_color(struct mt7996_dev *dev, + struct mt76_vif_link *mlink, struct cfg80211_he_bss_color *he_bss_color) { int len = sizeof(struct bss_req_hdr) + sizeof(struct bss_color_tlv); - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; struct bss_color_tlv *bss_color; struct sk_buff *skb; struct tlv *tlv; - skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76, len); + skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, mlink, len); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -4196,12 +4246,12 @@ int mt7996_mcu_twt_agrt_update(struct mt7996_dev *dev, .len = cpu_to_le16(sizeof(req) - 4), .tbl_idx = flow->table_id, .cmd = cmd, - .own_mac_idx = mvif->mt76.omac_idx, + .own_mac_idx = mvif->deflink.mt76.omac_idx, .flowid = flow->id, .peer_id = cpu_to_le16(flow->wcid), .duration = flow->duration, - .bss = mvif->mt76.idx, - .bss_idx = mvif->mt76.idx, + .bss = mvif->deflink.mt76.idx, + .bss_idx = mvif->deflink.mt76.idx, .start_tsf = cpu_to_le64(flow->tsf), .mantissa = flow->mantissa, .exponent = flow->exp, @@ -4297,16 +4347,16 @@ int mt7996_mcu_wtbl_update_hdr_trans(struct mt7996_dev *dev, struct mt7996_sta *msta; struct sk_buff *skb; - msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->sta; + msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->deflink.sta; - skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76, &msta->wcid, MT7996_STA_UPDATE_MAX_SIZE); if (IS_ERR(skb)) return PTR_ERR(skb); /* starec hdr trans */ - mt7996_mcu_sta_hdr_trans_tlv(dev, skb, vif, sta); + mt7996_mcu_sta_hdr_trans_tlv(dev, skb, vif, &msta->wcid); return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true); } @@ -4484,12 +4534,32 @@ int mt7996_mcu_wed_rro_reset_sessions(struct mt7996_dev *dev, u16 id) sizeof(req), true); } +int mt7996_mcu_set_sniffer_mode(struct mt7996_phy *phy, bool enabled) +{ + struct mt7996_dev *dev = phy->dev; + struct { + u8 band_idx; + u8 _rsv[3]; + __le16 tag; + __le16 len; + u8 enable; + u8 _pad[3]; + } __packed req = { + .band_idx = phy->mt76->band_idx, + .tag = 0, + .len = cpu_to_le16(sizeof(req) - 4), + .enable = enabled, + }; + + return mt76_mcu_send_msg(&dev->mt76, MCU_WM_UNI_CMD(SNIFFER), &req, + sizeof(req), true); +} + int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy) { #define TX_POWER_LIMIT_TABLE_RATE 0 struct mt7996_dev *dev = phy->dev; struct mt76_phy *mphy = phy->mt76; - struct ieee80211_hw *hw = mphy->hw; struct tx_power_limit_table_ctrl { u8 __rsv1[4]; @@ -4509,7 +4579,7 @@ int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy) struct sk_buff *skb; int i, tx_power; - tx_power = mt7996_get_power_bound(phy, hw->conf.power_level); + tx_power = mt7996_get_power_bound(phy, phy->txpower); tx_power = mt76_get_rate_power_limits(mphy, mphy->chandef.chan, &la, tx_power); mphy->txpower_cur = tx_power; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c index 40e45fb2b626..7a8ee6c75cf2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c @@ -177,7 +177,7 @@ static u32 __mt7996_reg_addr(struct mt7996_dev *dev, u32 addr) continue; ofs = addr - dev->reg.map[i].phys; - if (ofs > dev->reg.map[i].size) + if (ofs >= dev->reg.map[i].size) continue; return dev->reg.map[i].mapped + ofs; @@ -605,6 +605,7 @@ struct mt7996_dev *mt7996_mmio_probe(struct device *pdev, static const struct mt76_driver_ops drv_ops = { /* txwi_size = txd size + txp size */ .txwi_size = MT_TXD_SIZE + sizeof(struct mt76_connac_fw_txp), + .link_data_size = sizeof(struct mt7996_vif_link), .drv_flags = MT_DRV_TXWI_NO_FREE | MT_DRV_AMSDU_OFFLOAD | MT_DRV_HW_MGMT_TXQ, @@ -618,9 +619,12 @@ struct mt7996_dev *mt7996_mmio_probe(struct device *pdev, .rx_check = mt7996_rx_check, .rx_poll_complete = mt7996_rx_poll_complete, .sta_add = mt7996_mac_sta_add, + .sta_event = mt7996_mac_sta_event, .sta_remove = mt7996_mac_sta_remove, .update_survey = mt7996_update_channel, .set_channel = mt7996_set_channel, + .vif_link_add = mt7996_vif_link_add, + .vif_link_remove = mt7996_vif_link_remove, }; struct mt7996_dev *dev; struct mt76_dev *mdev; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h index ab8c9070630b..29fabb9b04ae 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h @@ -11,6 +11,7 @@ #include "../mt76_connac.h" #include "regs.h" +#define MT7996_MAX_RADIOS 3 #define MT7996_MAX_INTERFACES 19 /* per-band */ #define MT7996_MAX_WMM_SETS 4 #define MT7996_WTBL_BMC_SIZE (is_mt7992(&dev->mt76) ? 32 : 64) @@ -34,13 +35,32 @@ #define MT7996_FIRMWARE_DSP "mediatek/mt7996/mt7996_dsp.bin" #define MT7996_ROM_PATCH "mediatek/mt7996/mt7996_rom_patch.bin" +#define MT7996_FIRMWARE_WA_233 "mediatek/mt7996/mt7996_wa_233.bin" +#define MT7996_FIRMWARE_WM_233 "mediatek/mt7996/mt7996_wm_233.bin" +#define MT7996_FIRMWARE_DSP_233 MT7996_FIRMWARE_DSP +#define MT7996_ROM_PATCH_233 "mediatek/mt7996/mt7996_rom_patch_233.bin" + #define MT7992_FIRMWARE_WA "mediatek/mt7996/mt7992_wa.bin" #define MT7992_FIRMWARE_WM "mediatek/mt7996/mt7992_wm.bin" #define MT7992_FIRMWARE_DSP "mediatek/mt7996/mt7992_dsp.bin" #define MT7992_ROM_PATCH "mediatek/mt7996/mt7992_rom_patch.bin" +#define MT7992_FIRMWARE_WA_23 "mediatek/mt7996/mt7992_wa_23.bin" +#define MT7992_FIRMWARE_WM_23 "mediatek/mt7996/mt7992_wm_23.bin" +#define MT7992_FIRMWARE_DSP_23 "mediatek/mt7996/mt7992_dsp_23.bin" +#define MT7992_ROM_PATCH_23 "mediatek/mt7996/mt7992_rom_patch_23.bin" + #define MT7996_EEPROM_DEFAULT "mediatek/mt7996/mt7996_eeprom.bin" +#define MT7996_EEPROM_DEFAULT_INT "mediatek/mt7996/mt7996_eeprom_2i5i6i.bin" +#define MT7996_EEPROM_DEFAULT_233 "mediatek/mt7996/mt7996_eeprom_233.bin" +#define MT7996_EEPROM_DEFAULT_233_INT "mediatek/mt7996/mt7996_eeprom_233_2i5i6i.bin" + #define MT7992_EEPROM_DEFAULT "mediatek/mt7996/mt7992_eeprom.bin" +#define MT7992_EEPROM_DEFAULT_INT "mediatek/mt7996/mt7992_eeprom_2i5i.bin" +#define MT7992_EEPROM_DEFAULT_MIX "mediatek/mt7996/mt7992_eeprom_2i5e.bin" +#define MT7992_EEPROM_DEFAULT_23 "mediatek/mt7996/mt7992_eeprom_23.bin" +#define MT7992_EEPROM_DEFAULT_23_INT "mediatek/mt7996/mt7992_eeprom_23_2i5i.bin" + #define MT7996_EEPROM_SIZE 7680 #define MT7996_EEPROM_BLOCK_SIZE 16 #define MT7996_TOKEN_SIZE 16384 @@ -48,6 +68,12 @@ #define MT7996_CFEND_RATE_DEFAULT 0x49 /* OFDM 24M */ #define MT7996_CFEND_RATE_11B 0x03 /* 11B LP, 11M */ +#define MT7996_IBF_MAX_NC 2 +#define MT7996_IBF_TIMEOUT 0x18 +#define MT7996_IBF_TIMEOUT_LEGACY 0x48 + +#define MT7992_CFEND_RATE_DEFAULT 0x4b /* OFDM 6M */ +#define MT7992_IBF_TIMEOUT 0xff #define MT7996_SKU_RATE_NUM 417 #define MT7996_SKU_PATH_NUM 494 @@ -95,6 +121,22 @@ enum mt7996_ram_type { MT7996_RAM_TYPE_DSP, }; +enum mt7996_var_type { + MT7996_VAR_TYPE_444, + MT7996_VAR_TYPE_233, +}; + +enum mt7992_var_type { + MT7992_VAR_TYPE_44, + MT7992_VAR_TYPE_23, +}; + +enum mt7996_fem_type { + MT7996_FEM_EXT, + MT7996_FEM_INT, + MT7996_FEM_MIX, +}; + enum mt7996_txq_id { MT7996_TXQ_FWDL = 16, MT7996_TXQ_MCU_WM, @@ -164,8 +206,8 @@ struct mt7996_sta { } twt; }; -struct mt7996_vif { - struct mt76_vif mt76; /* must be first */ +struct mt7996_vif_link { + struct mt76_vif_link mt76; /* must be first */ struct mt7996_sta sta; struct mt7996_phy *phy; @@ -174,6 +216,11 @@ struct mt7996_vif { struct cfg80211_bitrate_mask bitrate_mask; }; +struct mt7996_vif { + struct mt7996_vif_link deflink; /* must be first */ + struct mt76_vif_data mt76; +}; + /* crash-dump */ struct mt7996_crash_data { guid_t guid; @@ -211,8 +258,6 @@ struct mt7996_phy { struct ieee80211_sband_iftype_data iftype[NUM_NL80211_BANDS][NUM_NL80211_IFTYPES]; - struct ieee80211_vif *monitor_vif; - struct thermal_cooling_device *cdev; u8 cdev_state; u8 throttle_state; @@ -232,11 +277,15 @@ struct mt7996_phy { u32 rx_ampdu_ts; u32 ampdu_ref; + int txpower; struct mt76_mib_stats mib; struct mt76_channel_state state_ts; + u16 orig_chainmask; + bool has_aux_rx; + bool counter_reset; }; struct mt7996_dev { @@ -245,6 +294,10 @@ struct mt7996_dev { struct mt76_phy mphy; }; + struct mt7996_phy *radio_phy[MT7996_MAX_RADIOS]; + struct wiphy_radio radios[MT7996_MAX_RADIOS]; + struct wiphy_radio_freq_range radio_freqs[MT7996_MAX_RADIOS]; + struct mt7996_hif *hif2; struct mt7996_reg_desc reg; u8 q_id[MT7996_MAX_QUEUE]; @@ -329,6 +382,10 @@ struct mt7996_dev { spinlock_t reg_lock; u8 wtbl_size_group; + struct { + u8 type:4; + u8 fem:4; + } var; }; enum { @@ -360,14 +417,6 @@ enum mt7996_rdd_cmd { RDD_IRQ_OFF, }; -static inline struct mt7996_phy * -mt7996_hw_phy(struct ieee80211_hw *hw) -{ - struct mt76_phy *phy = hw->priv; - - return phy->priv; -} - static inline struct mt7996_dev * mt7996_hw_dev(struct ieee80211_hw *hw) { @@ -405,14 +454,69 @@ mt7996_band_valid(struct mt7996_dev *dev, u8 band) if (is_mt7992(&dev->mt76)) return band <= MT_BAND1; - /* tri-band support */ - if (band <= MT_BAND2 && - mt76_get_field(dev, MT_PAD_GPIO, MT_PAD_GPIO_ADIE_COMB) <= 1) - return true; - - return band == MT_BAND0 || band == MT_BAND2; + return band <= MT_BAND2; } +static inline bool +mt7996_has_background_radar(struct mt7996_dev *dev) +{ + switch (mt76_chip(&dev->mt76)) { + case 0x7990: + if (dev->var.type == MT7996_VAR_TYPE_233) + return false; + break; + case 0x7992: + if (dev->var.type == MT7992_VAR_TYPE_23) + return false; + break; + default: + return false; + } + + return true; +} + +static inline struct mt7996_phy * +mt7996_band_phy(struct mt7996_dev *dev, enum nl80211_band band) +{ + struct mt76_phy *mphy; + + mphy = dev->mt76.band_phys[band]; + if (!mphy) + return NULL; + + return mphy->priv; +} + +static inline struct mt7996_vif_link * +mt7996_vif_link(struct mt7996_dev *dev, struct ieee80211_vif *vif, int link_id) +{ + return (struct mt7996_vif_link *)mt76_vif_link(&dev->mt76, vif, link_id); +} + +static inline struct mt7996_phy * +mt7996_vif_link_phy(struct mt7996_vif_link *link) +{ + struct mt76_phy *mphy = mt76_vif_link_phy(&link->mt76); + + if (!mphy) + return NULL; + + return mphy->priv; +} + +static inline struct mt7996_vif_link * +mt7996_vif_conf_link(struct mt7996_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf) +{ + return (struct mt7996_vif_link *)mt76_vif_conf_link(&dev->mt76, vif, + link_conf); +} + +#define mt7996_for_each_phy(dev, phy) \ + for (int __i = 0; __i < ARRAY_SIZE((dev)->radio_phy); __i++) \ + if (((phy) = (dev)->radio_phy[__i]) != NULL) + extern const struct ieee80211_ops mt7996_ops; extern struct pci_driver mt7996_pci_driver; extern struct pci_driver mt7996_hif_driver; @@ -424,6 +528,12 @@ irqreturn_t mt7996_irq_handler(int irq, void *dev_instance); u64 __mt7996_get_tsf(struct ieee80211_hw *hw, struct mt7996_vif *mvif); int mt7996_register_device(struct mt7996_dev *dev); void mt7996_unregister_device(struct mt7996_dev *dev); +int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink); +void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink); int mt7996_eeprom_init(struct mt7996_dev *dev); int mt7996_eeprom_parse_hw_cap(struct mt7996_dev *dev, struct mt7996_phy *phy); int mt7996_eeprom_get_target_power(struct mt7996_dev *dev, @@ -439,29 +549,33 @@ int mt7996_init_tx_queues(struct mt7996_phy *phy, int idx, void mt7996_init_txpower(struct mt7996_phy *phy); int mt7996_txbf_init(struct mt7996_dev *dev); void mt7996_reset(struct mt7996_dev *dev); -int mt7996_run(struct ieee80211_hw *hw); +int mt7996_run(struct mt7996_phy *phy); int mt7996_mcu_init(struct mt7996_dev *dev); int mt7996_mcu_init_firmware(struct mt7996_dev *dev); int mt7996_mcu_twt_agrt_update(struct mt7996_dev *dev, struct mt7996_vif *mvif, struct mt7996_twt_flow *flow, int cmd); -int mt7996_mcu_add_dev_info(struct mt7996_phy *phy, - struct ieee80211_vif *vif, bool enable); -int mt7996_mcu_add_bss_info(struct mt7996_phy *phy, - struct ieee80211_vif *vif, int enable); +int mt7996_mcu_add_dev_info(struct mt7996_phy *phy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink, bool enable); +int mt7996_mcu_add_bss_info(struct mt7996_phy *phy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf, + struct mt76_vif_link *mlink, int enable); int mt7996_mcu_add_sta(struct mt7996_dev *dev, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, bool enable, bool newly); + struct mt76_vif_link *mlink, + struct ieee80211_sta *sta, int conn_state, bool newly); int mt7996_mcu_add_tx_ba(struct mt7996_dev *dev, struct ieee80211_ampdu_params *params, bool add); int mt7996_mcu_add_rx_ba(struct mt7996_dev *dev, struct ieee80211_ampdu_params *params, bool add); -int mt7996_mcu_update_bss_color(struct mt7996_dev *dev, struct ieee80211_vif *vif, +int mt7996_mcu_update_bss_color(struct mt7996_dev *dev, + struct mt76_vif_link *mlink, struct cfg80211_he_bss_color *he_bss_color); int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - int enable); + struct ieee80211_bss_conf *link_conf); int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev, struct ieee80211_vif *vif, u32 changed); int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy, struct ieee80211_vif *vif, @@ -470,13 +584,14 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool changed); int mt7996_set_channel(struct mt76_phy *mphy); int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag); -int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif); +int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf); int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev, void *data, u16 version); int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta, void *data, u32 field); int mt7996_mcu_set_eeprom(struct mt7996_dev *dev); -int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset); +int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset, u8 *buf, u32 buf_len); int mt7996_mcu_get_eeprom_free_block(struct mt7996_dev *dev, u8 *block_num); int mt7996_mcu_get_chip_config(struct mt7996_dev *dev, u32 *cap); int mt7996_mcu_set_ser(struct mt7996_dev *dev, u8 action, u8 set, u8 band); @@ -488,7 +603,8 @@ int mt7996_mcu_set_radar_th(struct mt7996_dev *dev, int index, const struct mt7996_dfs_pattern *pattern); int mt7996_mcu_set_radio_en(struct mt7996_phy *phy, bool enable); int mt7996_mcu_set_rts_thresh(struct mt7996_phy *phy, u32 val); -int mt7996_mcu_set_timing(struct mt7996_phy *phy, struct ieee80211_vif *vif); +int mt7996_mcu_set_timing(struct mt7996_phy *phy, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf); int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch); int mt7996_mcu_get_temperature(struct mt7996_phy *phy); int mt7996_mcu_set_thermal_throttling(struct mt7996_phy *phy, u8 state); @@ -511,6 +627,7 @@ void mt7996_mcu_rx_event(struct mt7996_dev *dev, struct sk_buff *skb); void mt7996_mcu_exit(struct mt7996_dev *dev); int mt7996_mcu_get_all_sta_info(struct mt7996_phy *phy, u16 tag); int mt7996_mcu_wed_rro_reset_sessions(struct mt7996_dev *dev, u16 id); +int mt7996_mcu_set_sniffer_mode(struct mt7996_phy *phy, bool enabled); static inline u8 mt7996_max_interface_num(struct mt7996_dev *dev) { @@ -575,6 +692,8 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, void mt7996_mac_set_coverage_class(struct mt7996_phy *phy); int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); +int mt7996_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, enum mt76_sta_event ev); void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void mt7996_mac_work(struct work_struct *work); @@ -602,7 +721,7 @@ int mt7996_dfs_init_radar_detector(struct mt7996_phy *phy); void mt7996_set_stream_he_eht_caps(struct mt7996_phy *phy); void mt7996_set_stream_vht_txbf_caps(struct mt7996_phy *phy); void mt7996_update_channel(struct mt76_phy *mphy); -int mt7996_init_debugfs(struct mt7996_phy *phy); +int mt7996_init_debugfs(struct mt7996_dev *dev); void mt7996_debugfs_rx_fw_monitor(struct mt7996_dev *dev, const void *data, int len); bool mt7996_debugfs_rx_log(struct mt7996_dev *dev, const void *data, int len); int mt7996_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/regs.h b/drivers/net/wireless/mediatek/mt76/mt7996/regs.h index 47b429d8bfbe..1876a968c92d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/regs.h @@ -175,6 +175,9 @@ enum offs_rev { #define MT_WTBLOFF_RSCR_RCPI_MODE GENMASK(31, 30) #define MT_WTBLOFF_RSCR_RCPI_PARAM GENMASK(25, 24) +#define MT_WTBLOFF_ACR(_band) MT_WTBLOFF(_band, 0x010) +#define MT_WTBLOFF_ADM_BACKOFFTIME BIT(29) + /* ETBF: band 0(0x820ea000), band 1(0x820fa000), band 2(0x830ea000) */ #define MT_WF_ETBF_BASE(_band) __BASE(WF_ETBF_BASE, (_band)) #define MT_WF_ETBF(_band, ofs) (MT_WF_ETBF_BASE(_band) + (ofs)) @@ -660,8 +663,17 @@ enum offs_rev { #define MT_TOP_MISC MT_TOP(0xf0) #define MT_TOP_MISC_FW_STATE GENMASK(2, 0) +/* ADIE */ +#define MT_ADIE_CHIP_ID(_idx) (0x0f00002c + ((_idx) << 28)) +#define MT_ADIE_VERSION_MASK GENMASK(15, 0) +#define MT_ADIE_CHIP_ID_MASK GENMASK(31, 16) + #define MT_PAD_GPIO 0x700056f0 #define MT_PAD_GPIO_ADIE_COMB GENMASK(16, 15) +#define MT_PAD_GPIO_2ADIE_TBTC BIT(19) +/* for mt7992 */ +#define MT_PAD_GPIO_ADIE_COMB_7992 GENMASK(17, 16) +#define MT_PAD_GPIO_ADIE_SINGLE BIT(15) #define MT_HW_REV 0x70010204 #define MT_HW_REV1 0x8a00 diff --git a/drivers/net/wireless/mediatek/mt76/scan.c b/drivers/net/wireless/mediatek/mt76/scan.c new file mode 100644 index 000000000000..1c4f9deaaada --- /dev/null +++ b/drivers/net/wireless/mediatek/mt76/scan.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (C) 2024 Felix Fietkau + */ +#include "mt76.h" + +static void mt76_scan_complete(struct mt76_dev *dev, bool abort) +{ + struct mt76_phy *phy = dev->scan.phy; + struct cfg80211_scan_info info = { + .aborted = abort, + }; + + if (!phy) + return; + + clear_bit(MT76_SCANNING, &phy->state); + + if (dev->scan.chan && phy->main_chandef.chan) + mt76_set_channel(phy, &phy->main_chandef, false); + mt76_put_vif_phy_link(phy, dev->scan.vif, dev->scan.mlink); + memset(&dev->scan, 0, sizeof(dev->scan)); + ieee80211_scan_completed(phy->hw, &info); +} + +void mt76_abort_scan(struct mt76_dev *dev) +{ + cancel_delayed_work_sync(&dev->scan_work); + mt76_scan_complete(dev, true); +} + +static void +mt76_scan_send_probe(struct mt76_dev *dev, struct cfg80211_ssid *ssid) +{ + struct cfg80211_scan_request *req = dev->scan.req; + struct ieee80211_vif *vif = dev->scan.vif; + struct mt76_vif_link *mvif = dev->scan.mlink; + enum nl80211_band band = dev->scan.chan->band; + struct mt76_phy *phy = dev->scan.phy; + struct ieee80211_tx_info *info; + struct sk_buff *skb; + + skb = ieee80211_probereq_get(phy->hw, vif->addr, ssid->ssid, + ssid->ssid_len, req->ie_len); + if (!skb) + return; + + if (is_unicast_ether_addr(req->bssid)) { + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + + ether_addr_copy(hdr->addr1, req->bssid); + ether_addr_copy(hdr->addr3, req->bssid); + } + + info = IEEE80211_SKB_CB(skb); + if (req->no_cck) + info->flags |= IEEE80211_TX_CTL_NO_CCK_RATE; + info->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK; + + if (req->ie_len) + skb_put_data(skb, req->ie, req->ie_len); + + skb->priority = 7; + skb_set_queue_mapping(skb, IEEE80211_AC_VO); + + rcu_read_lock(); + if (ieee80211_tx_prepare_skb(phy->hw, vif, skb, band, NULL)) + mt76_tx(phy, NULL, mvif->wcid, skb); + else + ieee80211_free_txskb(phy->hw, skb); + rcu_read_unlock(); +} + +void mt76_scan_work(struct work_struct *work) +{ + struct mt76_dev *dev = container_of(work, struct mt76_dev, + scan_work.work); + struct cfg80211_scan_request *req = dev->scan.req; + struct cfg80211_chan_def chandef = {}; + struct mt76_phy *phy = dev->scan.phy; + int duration = HZ / 9; /* ~110 ms */ + int i; + + if (dev->scan.chan_idx >= req->n_channels) { + mt76_scan_complete(dev, false); + return; + } + + if (dev->scan.chan && phy->num_sta) { + dev->scan.chan = NULL; + mt76_set_channel(phy, &phy->main_chandef, false); + goto out; + } + + dev->scan.chan = req->channels[dev->scan.chan_idx++]; + cfg80211_chandef_create(&chandef, dev->scan.chan, NL80211_CHAN_HT20); + mt76_set_channel(phy, &chandef, true); + + if (!req->n_ssids || + chandef.chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) + goto out; + + duration = HZ / 16; /* ~60 ms */ + local_bh_disable(); + for (i = 0; i < req->n_ssids; i++) + mt76_scan_send_probe(dev, &req->ssids[i]); + local_bh_enable(); + +out: + if (!duration) + return; + + if (dev->scan.chan) + duration = max_t(int, duration, + msecs_to_jiffies(req->duration + + (req->duration >> 5))); + + ieee80211_queue_delayed_work(dev->phy.hw, &dev->scan_work, duration); +} + +int mt76_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_scan_request *req) +{ + struct mt76_phy *phy = hw->priv; + struct mt76_dev *dev = phy->dev; + struct mt76_vif_link *mlink; + int ret = 0; + + if (hw->wiphy->n_radio > 1) { + phy = dev->band_phys[req->req.channels[0]->band]; + if (!phy) + return -EINVAL; + } + + mutex_lock(&dev->mutex); + + if (dev->scan.req || phy->roc_vif) { + ret = -EBUSY; + goto out; + } + + mlink = mt76_get_vif_phy_link(phy, vif); + if (IS_ERR(mlink)) { + ret = PTR_ERR(mlink); + goto out; + } + + memset(&dev->scan, 0, sizeof(dev->scan)); + dev->scan.req = &req->req; + dev->scan.vif = vif; + dev->scan.phy = phy; + dev->scan.mlink = mlink; + ieee80211_queue_delayed_work(dev->phy.hw, &dev->scan_work, 0); + +out: + mutex_unlock(&dev->mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(mt76_hw_scan); + +void mt76_cancel_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif) +{ + struct mt76_phy *phy = hw->priv; + + mt76_abort_scan(phy->dev); +} +EXPORT_SYMBOL_GPL(mt76_cancel_hw_scan); diff --git a/drivers/net/wireless/mediatek/mt76/sdio_txrx.c b/drivers/net/wireless/mediatek/mt76/sdio_txrx.c index ddd8c0cc744d..0a927a7313a6 100644 --- a/drivers/net/wireless/mediatek/mt76/sdio_txrx.c +++ b/drivers/net/wireless/mediatek/mt76/sdio_txrx.c @@ -46,6 +46,10 @@ static int mt76s_refill_sched_quota(struct mt76_dev *dev, u32 *data) return 0; sdio->sched.pse_mcu_quota += pse_mcu_quota; + if (sdio->pse_mcu_quota_max && + sdio->sched.pse_mcu_quota > sdio->pse_mcu_quota_max) { + sdio->sched.pse_mcu_quota = sdio->pse_mcu_quota_max; + } sdio->sched.pse_data_quota += pse_data_quota; sdio->sched.ple_data_quota += ple_data_quota; diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index ce193e625666..af0c50c983ec 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -489,7 +489,7 @@ mt76_txq_send_burst(struct mt76_phy *phy, struct mt76_queue *q, do { if (test_bit(MT76_RESET, &phy->state) || phy->offchannel) - return -EBUSY; + break; if (stop || mt76_txq_stopped(q)) break; @@ -522,24 +522,16 @@ mt76_txq_send_burst(struct mt76_phy *phy, struct mt76_queue *q, static int mt76_txq_schedule_list(struct mt76_phy *phy, enum mt76_txq_id qid) { - struct mt76_queue *q = phy->q_tx[qid]; struct mt76_dev *dev = phy->dev; struct ieee80211_txq *txq; struct mt76_txq *mtxq; struct mt76_wcid *wcid; + struct mt76_queue *q; int ret = 0; while (1) { int n_frames = 0; - if (test_bit(MT76_RESET, &phy->state) || phy->offchannel) - return -EBUSY; - - if (dev->queue_ops->tx_cleanup && - q->queued + 2 * MT_TXQ_FREE_THR >= q->ndesc) { - dev->queue_ops->tx_cleanup(dev, q, false); - } - txq = ieee80211_next_txq(phy->hw, qid); if (!txq) break; @@ -549,6 +541,16 @@ mt76_txq_schedule_list(struct mt76_phy *phy, enum mt76_txq_id qid) if (!wcid || test_bit(MT_WCID_FLAG_PS, &wcid->flags)) continue; + phy = mt76_dev_phy(dev, wcid->phy_idx); + if (test_bit(MT76_RESET, &phy->state) || phy->offchannel) + continue; + + q = phy->q_tx[qid]; + if (dev->queue_ops->tx_cleanup && + q->queued + 2 * MT_TXQ_FREE_THR >= q->ndesc) { + dev->queue_ops->tx_cleanup(dev, q, false); + } + if (mtxq->send_bar && mtxq->aggr) { struct ieee80211_txq *txq = mtxq_to_txq(mtxq); struct ieee80211_sta *sta = txq->sta; @@ -578,7 +580,7 @@ void mt76_txq_schedule(struct mt76_phy *phy, enum mt76_txq_id qid) { int len; - if (qid >= 4 || phy->offchannel) + if (qid >= 4) return; local_bh_disable(); @@ -680,9 +682,14 @@ static void mt76_txq_schedule_pending(struct mt76_phy *phy) void mt76_txq_schedule_all(struct mt76_phy *phy) { + struct mt76_phy *main_phy = &phy->dev->phy; int i; mt76_txq_schedule_pending(phy); + + if (phy != main_phy && phy->hw == main_phy->hw) + return; + for (i = 0; i <= MT_TXQ_BK; i++) mt76_txq_schedule(phy, i); } @@ -693,6 +700,7 @@ void mt76_tx_worker_run(struct mt76_dev *dev) struct mt76_phy *phy; int i; + mt76_txq_schedule_all(&dev->phy); for (i = 0; i < ARRAY_SIZE(dev->phys); i++) { phy = dev->phys[i]; if (!phy) @@ -748,9 +756,6 @@ void mt76_wake_tx_queue(struct ieee80211_hw *hw, struct ieee80211_txq *txq) struct mt76_phy *phy = hw->priv; struct mt76_dev *dev = phy->dev; - if (!test_bit(MT76_STATE_RUNNING, &phy->state)) - return; - mt76_worker_schedule(&dev->tx_worker); } EXPORT_SYMBOL_GPL(mt76_wake_tx_queue); diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index 58ff06823389..f9e67b8c3b3c 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -33,9 +33,9 @@ int __mt76u_vendor_request(struct mt76_dev *dev, u8 req, u8 req_type, ret = usb_control_msg(udev, pipe, req, req_type, val, offset, buf, len, MT_VEND_REQ_TOUT_MS); - if (ret == -ENODEV) + if (ret == -ENODEV || ret == -EPROTO) set_bit(MT76_REMOVED, &dev->phy.state); - if (ret >= 0 || ret == -ENODEV) + if (ret >= 0 || ret == -ENODEV || ret == -EPROTO) return ret; usleep_range(5000, 10000); } diff --git a/drivers/net/wireless/mediatek/mt76/util.c b/drivers/net/wireless/mediatek/mt76/util.c index d6c01a2dd198..95b3dc96e4c4 100644 --- a/drivers/net/wireless/mediatek/mt76/util.c +++ b/drivers/net/wireless/mediatek/mt76/util.c @@ -64,7 +64,7 @@ int mt76_wcid_alloc(u32 *mask, int size) } EXPORT_SYMBOL_GPL(mt76_wcid_alloc); -int mt76_get_min_avg_rssi(struct mt76_dev *dev, bool ext_phy) +int mt76_get_min_avg_rssi(struct mt76_dev *dev, u8 phy_idx) { struct mt76_wcid *wcid; int i, j, min_rssi = 0; @@ -75,20 +75,16 @@ int mt76_get_min_avg_rssi(struct mt76_dev *dev, bool ext_phy) for (i = 0; i < ARRAY_SIZE(dev->wcid_mask); i++) { u32 mask = dev->wcid_mask[i]; - u32 phy_mask = dev->wcid_phy_mask[i]; if (!mask) continue; - for (j = i * 32; mask; j++, mask >>= 1, phy_mask >>= 1) { + for (j = i * 32; mask; j++, mask >>= 1) { if (!(mask & 1)) continue; - if (!!(phy_mask & 1) != ext_phy) - continue; - wcid = rcu_dereference(dev->wcid[j]); - if (!wcid) + if (!wcid || wcid->phy_idx != phy_idx) continue; spin_lock(&dev->rx_lock); diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index e96736cc7259..e7aa0f991923 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -1669,7 +1669,7 @@ static int set_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, } static int get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, - int *dbm) + unsigned int link_id, int *dbm) { int ret; struct wilc_vif *vif = netdev_priv(wdev->netdev); diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c index 7e84fc0fd911..af298021e050 100644 --- a/drivers/net/wireless/microchip/wilc1000/netdev.c +++ b/drivers/net/wireless/microchip/wilc1000/netdev.c @@ -925,8 +925,6 @@ void wilc_netdev_cleanup(struct wilc *wilc) wilc_wlan_cfg_deinit(wilc); wlan_deinit_locks(wilc); - wiphy_unregister(wilc->wiphy); - wiphy_free(wilc->wiphy); } EXPORT_SYMBOL_GPL(wilc_netdev_cleanup); diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c index 5262c8846c13..af970f999111 100644 --- a/drivers/net/wireless/microchip/wilc1000/sdio.c +++ b/drivers/net/wireless/microchip/wilc1000/sdio.c @@ -193,7 +193,7 @@ static int wilc_sdio_probe(struct sdio_func *func, ret = wilc_load_mac_from_nv(wilc); if (ret) { pr_err("Can not retrieve MAC address from chip\n"); - goto dispose_irq; + goto unregister_wiphy; } wilc_sdio_deinit(wilc); @@ -202,15 +202,18 @@ static int wilc_sdio_probe(struct sdio_func *func, NL80211_IFTYPE_STATION, false); if (IS_ERR(vif)) { ret = PTR_ERR(vif); - goto dispose_irq; + goto unregister_wiphy; } dev_info(&func->dev, "Driver Initializing success\n"); return 0; +unregister_wiphy: + wiphy_unregister(wilc->wiphy); dispose_irq: irq_dispose_mapping(wilc->dev_irq_num); wilc_netdev_cleanup(wilc); + wiphy_free(wilc->wiphy); free: kfree(sdio_priv->cmd53_buf); kfree(sdio_priv); @@ -223,6 +226,8 @@ static void wilc_sdio_remove(struct sdio_func *func) struct wilc_sdio *sdio_priv = wilc->bus_data; wilc_netdev_cleanup(wilc); + wiphy_unregister(wilc->wiphy); + wiphy_free(wilc->wiphy); kfree(sdio_priv->cmd53_buf); kfree(sdio_priv); } diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c index ce2a9cdd6aa7..5bcabb7decea 100644 --- a/drivers/net/wireless/microchip/wilc1000/spi.c +++ b/drivers/net/wireless/microchip/wilc1000/spi.c @@ -256,7 +256,7 @@ static int wilc_bus_probe(struct spi_device *spi) ret = wilc_load_mac_from_nv(wilc); if (ret) { pr_err("Can not retrieve MAC address from chip\n"); - goto power_down; + goto unregister_wiphy; } wilc_wlan_power(wilc, false); @@ -264,14 +264,17 @@ static int wilc_bus_probe(struct spi_device *spi) NL80211_IFTYPE_STATION, false); if (IS_ERR(vif)) { ret = PTR_ERR(vif); - goto power_down; + goto unregister_wiphy; } return 0; +unregister_wiphy: + wiphy_unregister(wilc->wiphy); power_down: wilc_wlan_power(wilc, false); netdev_cleanup: wilc_netdev_cleanup(wilc); + wiphy_free(wilc->wiphy); free: kfree(spi_priv); return ret; @@ -283,6 +286,8 @@ static void wilc_bus_remove(struct spi_device *spi) struct wilc_spi *spi_priv = wilc->bus_data; wilc_netdev_cleanup(wilc); + wiphy_unregister(wilc->wiphy); + wiphy_free(wilc->wiphy); kfree(spi_priv); } diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c index 8b97accf6638..0b2282528342 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c @@ -881,7 +881,7 @@ static int qtnf_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, } static int qtnf_get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, - int *dbm) + unsigned int link_id, int *dbm) { struct qtnf_vif *vif = qtnf_netdev_get_priv(wdev->netdev); int ret; diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.h b/drivers/net/wireless/quantenna/qtnfmac/core.h index b375a4751580..a377d85c2451 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/core.h +++ b/drivers/net/wireless/quantenna/qtnfmac/core.h @@ -102,7 +102,7 @@ struct qtnf_wmac { struct qtnf_mac_info macinfo; struct qtnf_vif iflist[QTNF_MAX_INTF]; struct cfg80211_scan_request *scan_req; - struct mutex mac_lock; /* lock during wmac speicific ops */ + struct mutex mac_lock; /* lock during wmac specific ops */ struct delayed_work scan_timeout; struct ieee80211_regdomain *rd; struct platform_device *pdev; diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c index f66eb43094d4..3adcfac2886f 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c +++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c @@ -204,7 +204,7 @@ static void qtnf_pcie_init_irq(struct qtnf_pcie_bus_priv *priv, bool use_msi) if (!priv->msi_enabled) { pr_warn("legacy PCIE interrupts enabled\n"); - pci_intx(pdev, 1); + pcim_intx(pdev, 1); } } diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 60c2a12e9d5e..e5f553a1ea24 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -8882,13 +8882,10 @@ static void rt2800_rxiq_calibration(struct rt2x00_dev *rt2x00dev) for (ch_idx = 0; ch_idx < 2; ch_idx = ch_idx + 1) { if (ch_idx == 0) { - rfval = rfb0r1 & (~0x3); rfval = rfb0r1 | 0x1; rt2800_rfcsr_write_bank(rt2x00dev, 0, 1, rfval); - rfval = rfb0r2 & (~0x33); rfval = rfb0r2 | 0x11; rt2800_rfcsr_write_bank(rt2x00dev, 0, 2, rfval); - rfval = rfb0r42 & (~0x50); rfval = rfb0r42 | 0x10; rt2800_rfcsr_write_bank(rt2x00dev, 0, 42, rfval); @@ -8901,13 +8898,10 @@ static void rt2800_rxiq_calibration(struct rt2x00_dev *rt2x00dev) rt2800_bbp_dcoc_write(rt2x00dev, 1, 0x00); } else { - rfval = rfb0r1 & (~0x3); rfval = rfb0r1 | 0x2; rt2800_rfcsr_write_bank(rt2x00dev, 0, 1, rfval); - rfval = rfb0r2 & (~0x33); rfval = rfb0r2 | 0x22; rt2800_rfcsr_write_bank(rt2x00dev, 0, 2, rfval); - rfval = rfb0r42 & (~0x50); rfval = rfb0r42 | 0x40; rt2800_rfcsr_write_bank(rt2x00dev, 0, 42, rfval); diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c index 3d04df0f5bf4..766a7a7c7d28 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c @@ -1860,7 +1860,7 @@ struct rtl8xxxu_fileops rtl8188eu_fops = { .set_crystal_cap = rtl8188f_set_crystal_cap, .cck_rssi = rtl8188e_cck_rssi, .led_classdev_brightness_set = rtl8188eu_led_brightness_set, - .writeN_block_size = 128, + .writeN_block_size = 196, .rx_desc_size = sizeof(struct rtl8xxxu_rxdesc16), .tx_desc_size = sizeof(struct rtl8xxxu_txdesc32), .has_tx_report = 1, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c index f95898f68d68..4ce0c05c5129 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c @@ -8147,6 +8147,8 @@ static const struct usb_device_id dev_table[] = { .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x817e, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x8186, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x818a, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x317f, 0xff, 0xff, 0xff), @@ -8157,12 +8159,18 @@ static const struct usb_device_id dev_table[] = { .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x050d, 0x1102, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(0x050d, 0x11f2, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x06f8, 0xe033, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(0x07b8, 0x8188, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x07b8, 0x8189, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x0846, 0x9041, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(0x0846, 0x9043, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x0b05, 0x17ba, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x1e1e, 0xff, 0xff, 0xff), @@ -8179,6 +8187,10 @@ static const struct usb_device_id dev_table[] = { .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x13d3, 0x3357, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(0x13d3, 0x3358, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(0x13d3, 0x3359, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x330b, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x2019, 0x4902, 0xff, 0xff, 0xff), @@ -8193,6 +8205,8 @@ static const struct usb_device_id dev_table[] = { .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x4856, 0x0091, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(0x9846, 0x9041, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0xcdab, 0x8010, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x04f2, 0xaff7, 0xff, 0xff, 0xff), @@ -8218,6 +8232,8 @@ static const struct usb_device_id dev_table[] = { .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x0586, 0x341f, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(0x06f8, 0xe033, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x06f8, 0xe035, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x0b05, 0x17ab, 0xff, 0xff, 0xff), @@ -8226,6 +8242,8 @@ static const struct usb_device_id dev_table[] = { .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x0df6, 0x0070, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(0x0df6, 0x0077, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x0789, 0x016d, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x07aa, 0x0056, 0xff, 0xff, 0xff), @@ -8248,6 +8266,8 @@ static const struct usb_device_id dev_table[] = { .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x330a, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, +{USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x330d, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x2019, 0xab2b, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192cu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(0x20f4, 0x624d, 0xff, 0xff, 0xff), diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index aab4605de9c4..ff61867d142f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -575,9 +575,15 @@ static void rtl_free_entries_from_ack_queue(struct ieee80211_hw *hw, void rtl_deinit_core(struct ieee80211_hw *hw) { + struct rtl_priv *rtlpriv = rtl_priv(hw); + rtl_c2hcmd_launcher(hw, 0); rtl_free_entries_from_scan_list(hw); rtl_free_entries_from_ack_queue(hw, false); + if (rtlpriv->works.rtl_wq) { + destroy_workqueue(rtlpriv->works.rtl_wq); + rtlpriv->works.rtl_wq = NULL; + } } EXPORT_SYMBOL_GPL(rtl_deinit_core); @@ -2696,9 +2702,6 @@ MODULE_AUTHOR("Larry Finger "); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Realtek 802.11n PCI wireless core"); -struct rtl_global_var rtl_global_var = {}; -EXPORT_SYMBOL_GPL(rtl_global_var); - static int __init rtl_core_module_init(void) { BUILD_BUG_ON(TX_PWR_BY_RATE_NUM_RATE < TX_PWR_BY_RATE_NUM_SECTION); @@ -2712,10 +2715,6 @@ static int __init rtl_core_module_init(void) /* add debugfs */ rtl_debugfs_add_topdir(); - /* init some global vars */ - INIT_LIST_HEAD(&rtl_global_var.glb_priv_list); - spin_lock_init(&rtl_global_var.glb_list_lock); - return 0; } diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h index f081a9a90563..f3a6a43a42ec 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.h +++ b/drivers/net/wireless/realtek/rtlwifi/base.h @@ -124,7 +124,6 @@ int rtl_send_smps_action(struct ieee80211_hw *hw, u8 *rtl_find_ie(u8 *data, unsigned int len, u8 ie); void rtl_recognize_peer(struct ieee80211_hw *hw, u8 *data, unsigned int len); u8 rtl_tid_to_ac(u8 tid); -extern struct rtl_global_var rtl_global_var; void rtl_phy_scan_operation_backup(struct ieee80211_hw *hw, u8 operation); #endif diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index 11709b6c83f1..0eafc4d125f9 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -295,46 +295,6 @@ static bool rtl_pci_get_amd_l1_patch(struct ieee80211_hw *hw) return status; } -static bool rtl_pci_check_buddy_priv(struct ieee80211_hw *hw, - struct rtl_priv **buddy_priv) -{ - struct rtl_priv *rtlpriv = rtl_priv(hw); - struct rtl_pci_priv *pcipriv = rtl_pcipriv(hw); - struct rtl_priv *tpriv = NULL, *iter; - struct rtl_pci_priv *tpcipriv = NULL; - - if (!list_empty(&rtlpriv->glb_var->glb_priv_list)) { - list_for_each_entry(iter, &rtlpriv->glb_var->glb_priv_list, - list) { - tpcipriv = (struct rtl_pci_priv *)iter->priv; - rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, - "pcipriv->ndis_adapter.funcnumber %x\n", - pcipriv->ndis_adapter.funcnumber); - rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, - "tpcipriv->ndis_adapter.funcnumber %x\n", - tpcipriv->ndis_adapter.funcnumber); - - if (pcipriv->ndis_adapter.busnumber == - tpcipriv->ndis_adapter.busnumber && - pcipriv->ndis_adapter.devnumber == - tpcipriv->ndis_adapter.devnumber && - pcipriv->ndis_adapter.funcnumber != - tpcipriv->ndis_adapter.funcnumber) { - tpriv = iter; - break; - } - } - } - - rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, - "find_buddy_priv %d\n", tpriv != NULL); - - if (tpriv) - *buddy_priv = tpriv; - - return tpriv != NULL; -} - static void rtl_pci_parse_configuration(struct pci_dev *pdev, struct ieee80211_hw *hw) { @@ -1696,8 +1656,6 @@ static void rtl_pci_deinit(struct ieee80211_hw *hw) synchronize_irq(rtlpci->pdev->irq); tasklet_kill(&rtlpriv->works.irq_tasklet); cancel_work_sync(&rtlpriv->works.lps_change_work); - - destroy_workqueue(rtlpriv->works.rtl_wq); } static int rtl_pci_init(struct ieee80211_hw *hw, struct pci_dev *pdev) @@ -2011,7 +1969,6 @@ static bool _rtl_pci_find_adapter(struct pci_dev *pdev, pcipriv->ndis_adapter.amd_l1_patch); rtl_pci_parse_configuration(pdev, hw); - list_add_tail(&rtlpriv->list, &rtlpriv->glb_var->glb_priv_list); return true; } @@ -2158,7 +2115,6 @@ int rtl_pci_probe(struct pci_dev *pdev, rtlpriv->rtlhal.interface = INTF_PCI; rtlpriv->cfg = (struct rtl_hal_cfg *)(id->driver_data); rtlpriv->intf_ops = &rtl_pci_ops; - rtlpriv->glb_var = &rtl_global_var; rtl_efuse_ops_init(hw); /* MEM map */ @@ -2209,7 +2165,7 @@ int rtl_pci_probe(struct pci_dev *pdev, if (rtlpriv->cfg->ops->init_sw_vars(hw)) { pr_err("Can't init_sw_vars\n"); err = -ENODEV; - goto fail3; + goto fail2; } rtl_init_sw_leds(hw); @@ -2227,14 +2183,14 @@ int rtl_pci_probe(struct pci_dev *pdev, err = rtl_pci_init(hw, pdev); if (err) { pr_err("Failed to init PCI\n"); - goto fail3; + goto fail4; } err = ieee80211_register_hw(hw); if (err) { pr_err("Can't register mac80211 hw.\n"); err = -ENODEV; - goto fail3; + goto fail5; } rtlpriv->mac80211.mac80211_registered = 1; @@ -2257,16 +2213,19 @@ int rtl_pci_probe(struct pci_dev *pdev, set_bit(RTL_STATUS_INTERFACE_START, &rtlpriv->status); return 0; -fail3: - pci_set_drvdata(pdev, NULL); +fail5: + rtl_pci_deinit(hw); +fail4: rtl_deinit_core(hw); +fail3: + wait_for_completion(&rtlpriv->firmware_loading_complete); + rtlpriv->cfg->ops->deinit_sw_vars(hw); fail2: if (rtlpriv->io.pci_mem_start != 0) pci_iounmap(pdev, (void __iomem *)rtlpriv->io.pci_mem_start); pci_release_regions(pdev); - complete(&rtlpriv->firmware_loading_complete); fail1: if (hw) @@ -2317,7 +2276,6 @@ void rtl_pci_disconnect(struct pci_dev *pdev) if (rtlpci->using_msi) pci_disable_msi(rtlpci->pdev); - list_del(&rtlpriv->list); if (rtlpriv->io.pci_mem_start != 0) { pci_iounmap(pdev, (void __iomem *)rtlpriv->io.pci_mem_start); pci_release_regions(pdev); @@ -2376,7 +2334,6 @@ EXPORT_SYMBOL(rtl_pci_resume); const struct rtl_intf_ops rtl_pci_ops = { .adapter_start = rtl_pci_start, .adapter_stop = rtl_pci_stop, - .check_buddy_priv = rtl_pci_check_buddy_priv, .adapter_tx = rtl_pci_tx, .flush = rtl_pci_flush, .reset_trx_ring = rtl_pci_reset_trx_ring, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c index bbf8ff63dced..e63c67b1861b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c @@ -64,22 +64,23 @@ static void rtl92se_fw_cb(const struct firmware *firmware, void *context) rtl_dbg(rtlpriv, COMP_ERR, DBG_LOUD, "Firmware callback routine entered!\n"); - complete(&rtlpriv->firmware_loading_complete); if (!firmware) { pr_err("Firmware %s not available\n", fw_name); rtlpriv->max_fw_size = 0; - return; + goto exit; } if (firmware->size > rtlpriv->max_fw_size) { pr_err("Firmware is too big!\n"); rtlpriv->max_fw_size = 0; release_firmware(firmware); - return; + goto exit; } pfirmware = (struct rt_firmware *)rtlpriv->rtlhal.pfirmware; memcpy(pfirmware->sz_fw_tmpbuffer, firmware->data, firmware->size); pfirmware->sz_fw_tmpbufferlen = firmware->size; release_firmware(firmware); +exit: + complete(&rtlpriv->firmware_loading_complete); } static int rtl92s_init_sw_vars(struct ieee80211_hw *hw) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h index c269942b3f4a..af8d17b9e012 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h @@ -197,9 +197,9 @@ enum rtl8821a_h2c_cmd { /* _MEDIA_STATUS_RPT_PARM_CMD1 */ #define SET_H2CCMD_MSRRPT_PARM_OPMODE(__cmd, __value) \ - u8p_replace_bits(__cmd + 1, __value, BIT(0)) + u8p_replace_bits(__cmd, __value, BIT(0)) #define SET_H2CCMD_MSRRPT_PARM_MACID_IND(__cmd, __value) \ - u8p_replace_bits(__cmd + 1, __value, BIT(1)) + u8p_replace_bits(__cmd, __value, BIT(1)) /* AP_OFFLOAD */ #define SET_H2CCMD_AP_OFFLOAD_ON(__cmd, __value) \ diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c index 1be51ea3f3c8..9eddbada8af1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c @@ -2033,8 +2033,10 @@ static bool _rtl8821ae_phy_config_bb_with_pgheaderfile(struct ieee80211_hw *hw, if (!_rtl8821ae_check_condition(hw, v1)) { i += 2; /* skip the pair of expression*/ v2 = array[i+1]; - while (v2 != 0xDEAD) + while (v2 != 0xDEAD) { i += 3; + v2 = array[i + 1]; + } } } } diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index d37a017b2b81..f5718e570011 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -629,11 +629,6 @@ static void _rtl_usb_cleanup_rx(struct ieee80211_hw *hw) tasklet_kill(&rtlusb->rx_work_tasklet); cancel_work_sync(&rtlpriv->works.lps_change_work); - if (rtlpriv->works.rtl_wq) { - destroy_workqueue(rtlpriv->works.rtl_wq); - rtlpriv->works.rtl_wq = NULL; - } - skb_queue_purge(&rtlusb->rx_queue); while ((urb = usb_get_from_anchor(&rtlusb->rx_cleanup_urbs))) { @@ -1028,19 +1023,22 @@ int rtl_usb_probe(struct usb_interface *intf, err = ieee80211_register_hw(hw); if (err) { pr_err("Can't register mac80211 hw.\n"); - goto error_out; + goto error_init_vars; } rtlpriv->mac80211.mac80211_registered = 1; set_bit(RTL_STATUS_INTERFACE_START, &rtlpriv->status); return 0; +error_init_vars: + wait_for_completion(&rtlpriv->firmware_loading_complete); + rtlpriv->cfg->ops->deinit_sw_vars(hw); error_out: + rtl_usb_deinit(hw); rtl_deinit_core(hw); error_out2: _rtl_usb_io_handler_release(hw); usb_put_dev(udev); - complete(&rtlpriv->firmware_loading_complete); kfree(rtlpriv->usb_data); ieee80211_free_hw(hw); return -ENODEV; diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h index ae6e351bc83c..f1830ddcdd8c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/wifi.h +++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h @@ -2270,8 +2270,6 @@ struct rtl_intf_ops { /*com */ int (*adapter_start)(struct ieee80211_hw *hw); void (*adapter_stop)(struct ieee80211_hw *hw); - bool (*check_buddy_priv)(struct ieee80211_hw *hw, - struct rtl_priv **buddy_priv); int (*adapter_tx)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, @@ -2514,14 +2512,6 @@ struct dig_t { u32 rssi_max; }; -struct rtl_global_var { - /* from this list we can get - * other adapter's rtl_priv - */ - struct list_head glb_priv_list; - spinlock_t glb_list_lock; -}; - #define IN_4WAY_TIMEOUT_TIME (30 * MSEC_PER_SEC) /* 30 seconds */ struct rtl_btc_info { @@ -2667,9 +2657,7 @@ struct rtl_scan_list { struct rtl_priv { struct ieee80211_hw *hw; struct completion firmware_loading_complete; - struct list_head list; struct rtl_priv *buddy_priv; - struct rtl_global_var *glb_var; struct rtl_dmsp_ctl dmsp_ctl; struct rtl_locks locks; struct rtl_works works; diff --git a/drivers/net/wireless/realtek/rtw88/Kconfig b/drivers/net/wireless/realtek/rtw88/Kconfig index 733b3e58da51..ab21b8059e0b 100644 --- a/drivers/net/wireless/realtek/rtw88/Kconfig +++ b/drivers/net/wireless/realtek/rtw88/Kconfig @@ -238,4 +238,9 @@ config RTW88_DEBUGFS If unsure, say Y to simplify debug problems +config RTW88_LEDS + bool + depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211 + default y + endif diff --git a/drivers/net/wireless/realtek/rtw88/Makefile b/drivers/net/wireless/realtek/rtw88/Makefile index f0b49f5a8a5a..0cbbb366e393 100644 --- a/drivers/net/wireless/realtek/rtw88/Makefile +++ b/drivers/net/wireless/realtek/rtw88/Makefile @@ -20,6 +20,8 @@ rtw88_core-y += main.o \ rtw88_core-$(CONFIG_PM) += wow.o +rtw88_core-$(CONFIG_RTW88_LEDS) += led.o + obj-$(CONFIG_RTW88_8822B) += rtw88_8822b.o rtw88_8822b-objs := rtw8822b.o rtw8822b_table.o diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c index e6e9946fbf44..02389b7c6876 100644 --- a/drivers/net/wireless/realtek/rtw88/fw.c +++ b/drivers/net/wireless/realtek/rtw88/fw.c @@ -332,6 +332,9 @@ void rtw_fw_c2h_cmd_handle(struct rtw_dev *rtwdev, struct sk_buff *skb) case C2H_RA_RPT: rtw_fw_ra_report_handle(rtwdev, c2h->payload, len); break; + case C2H_ADAPTIVITY: + rtw_fw_adaptivity_result(rtwdev, c2h->payload, len); + break; default: rtw_dbg(rtwdev, RTW_DBG_FW, "C2H 0x%x isn't handled\n", c2h->id); break; @@ -367,10 +370,6 @@ void rtw_fw_c2h_cmd_rx_irqsafe(struct rtw_dev *rtwdev, u32 pkt_offset, rtw_fw_scan_result(rtwdev, c2h->payload, len); dev_kfree_skb_any(skb); break; - case C2H_ADAPTIVITY: - rtw_fw_adaptivity_result(rtwdev, c2h->payload, len); - dev_kfree_skb_any(skb); - break; default: /* pass offset for further operation */ *((u32 *)skb->cb) = pkt_offset; diff --git a/drivers/net/wireless/realtek/rtw88/led.c b/drivers/net/wireless/realtek/rtw88/led.c new file mode 100644 index 000000000000..25aa6cbaa728 --- /dev/null +++ b/drivers/net/wireless/realtek/rtw88/led.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* Copyright(c) 2025 Realtek Corporation + */ + +#include "main.h" +#include "debug.h" +#include "led.h" + +static int rtw_led_set_blocking(struct led_classdev *led, + enum led_brightness brightness) +{ + struct rtw_dev *rtwdev = container_of(led, struct rtw_dev, led_cdev); + + rtwdev->chip->ops->led_set(led, brightness); + + return 0; +} + +void rtw_led_init(struct rtw_dev *rtwdev) +{ + static const struct ieee80211_tpt_blink rtw_tpt_blink[] = { + { .throughput = 0 * 1024, .blink_time = 334 }, + { .throughput = 1 * 1024, .blink_time = 260 }, + { .throughput = 5 * 1024, .blink_time = 220 }, + { .throughput = 10 * 1024, .blink_time = 190 }, + { .throughput = 20 * 1024, .blink_time = 170 }, + { .throughput = 50 * 1024, .blink_time = 150 }, + { .throughput = 70 * 1024, .blink_time = 130 }, + { .throughput = 100 * 1024, .blink_time = 110 }, + { .throughput = 200 * 1024, .blink_time = 80 }, + { .throughput = 300 * 1024, .blink_time = 50 }, + }; + struct led_classdev *led = &rtwdev->led_cdev; + int err; + + if (!rtwdev->chip->ops->led_set) + return; + + if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE) + led->brightness_set = rtwdev->chip->ops->led_set; + else + led->brightness_set_blocking = rtw_led_set_blocking; + + snprintf(rtwdev->led_name, sizeof(rtwdev->led_name), + "rtw88-%s", dev_name(rtwdev->dev)); + + led->name = rtwdev->led_name; + led->max_brightness = LED_ON; + led->default_trigger = + ieee80211_create_tpt_led_trigger(rtwdev->hw, + IEEE80211_TPT_LEDTRIG_FL_RADIO, + rtw_tpt_blink, + ARRAY_SIZE(rtw_tpt_blink)); + + err = led_classdev_register(rtwdev->dev, led); + if (err) { + rtw_warn(rtwdev, "Failed to register the LED, error %d\n", err); + return; + } + + rtwdev->led_registered = true; +} + +void rtw_led_deinit(struct rtw_dev *rtwdev) +{ + struct led_classdev *led = &rtwdev->led_cdev; + + if (!rtwdev->led_registered) + return; + + rtwdev->chip->ops->led_set(led, LED_OFF); + led_classdev_unregister(led); +} diff --git a/drivers/net/wireless/realtek/rtw88/led.h b/drivers/net/wireless/realtek/rtw88/led.h new file mode 100644 index 000000000000..fa64002b0215 --- /dev/null +++ b/drivers/net/wireless/realtek/rtw88/led.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright(c) 2025 Realtek Corporation + */ + +#ifndef __RTW_LED_H +#define __RTW_LED_H + +#ifdef CONFIG_RTW88_LEDS + +void rtw_led_init(struct rtw_dev *rtwdev); +void rtw_led_deinit(struct rtw_dev *rtwdev); + +#else + +static inline void rtw_led_init(struct rtw_dev *rtwdev) +{ +} + +static inline void rtw_led_deinit(struct rtw_dev *rtwdev) +{ +} + +#endif + +#endif diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index e91530ed05a0..0cee0fd8c0ef 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -19,6 +19,7 @@ #include "bf.h" #include "sar.h" #include "sdio.h" +#include "led.h" bool rtw_disable_lps_deep_mode; EXPORT_SYMBOL(rtw_disable_lps_deep_mode); @@ -1217,7 +1218,6 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si, u8 wireless_set; u8 bw_mode; u8 rate_id; - u8 rf_type = RF_1T1R; u8 stbc_en = 0; u8 ldpc_en = 0; u8 tx_num = 1; @@ -1302,13 +1302,10 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si, break; } - if (sta->deflink.vht_cap.vht_supported && ra_mask & 0xffc00000) { + if (sta->deflink.vht_cap.vht_supported && ra_mask & 0xffc00000) tx_num = 2; - rf_type = RF_2T2R; - } else if (sta->deflink.ht_cap.ht_supported && ra_mask & 0xfff00000) { + else if (sta->deflink.ht_cap.ht_supported && ra_mask & 0xfff00000) tx_num = 2; - rf_type = RF_2T2R; - } rate_id = get_rate_id(wireless_set, bw_mode, tx_num); @@ -1319,7 +1316,6 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si, si->bw_mode = bw_mode; si->stbc_en = stbc_en; si->ldpc_en = ldpc_en; - si->rf_type = rf_type; si->sgi_enable = is_support_sgi; si->vht_enable = is_vht_enable; si->ra_mask = ra_mask; @@ -2297,16 +2293,18 @@ int rtw_register_hw(struct rtw_dev *rtwdev, struct ieee80211_hw *hw) return ret; } + rtw_led_init(rtwdev); + ret = ieee80211_register_hw(hw); if (ret) { rtw_err(rtwdev, "failed to register hw\n"); - return ret; + goto led_deinit; } ret = rtw_regd_hint(rtwdev); if (ret) { rtw_err(rtwdev, "failed to hint regd\n"); - return ret; + goto led_deinit; } rtw_debugfs_init(rtwdev); @@ -2315,6 +2313,10 @@ int rtw_register_hw(struct rtw_dev *rtwdev, struct ieee80211_hw *hw) rtwdev->bf_info.bfer_su_cnt = 0; return 0; + +led_deinit: + rtw_led_deinit(rtwdev); + return ret; } EXPORT_SYMBOL(rtw_register_hw); @@ -2325,6 +2327,7 @@ void rtw_unregister_hw(struct rtw_dev *rtwdev, struct ieee80211_hw *hw) ieee80211_unregister_hw(hw); rtw_unset_supported_band(hw, chip); rtw_debugfs_deinit(rtwdev); + rtw_led_deinit(rtwdev); } EXPORT_SYMBOL(rtw_unregister_hw); diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h index cd09fb6f7b8b..62cd4c526301 100644 --- a/drivers/net/wireless/realtek/rtw88/main.h +++ b/drivers/net/wireless/realtek/rtw88/main.h @@ -510,12 +510,12 @@ struct rtw_5g_txpwr_idx { struct rtw_5g_vht_ns_pwr_idx_diff vht_2s_diff; struct rtw_5g_vht_ns_pwr_idx_diff vht_3s_diff; struct rtw_5g_vht_ns_pwr_idx_diff vht_4s_diff; -}; +} __packed; struct rtw_txpwr_idx { struct rtw_2g_txpwr_idx pwr_idx_2g; struct rtw_5g_txpwr_idx pwr_idx_5g; -}; +} __packed; struct rtw_channel_params { u8 center_chan; @@ -757,7 +757,6 @@ struct rtw_sta_info { u8 mac_id; u8 rate_id; enum rtw_bandwidth bw_mode; - enum rtw_rf_type rf_type; u8 stbc_en:2; u8 ldpc_en:2; bool sgi_enable; @@ -888,6 +887,7 @@ struct rtw_chip_ops { bool is_tx2_path); void (*config_txrx_mode)(struct rtw_dev *rtwdev, u8 tx_path, u8 rx_path, bool is_tx2_path); + void (*led_set)(struct led_classdev *led, enum led_brightness brightness); /* for USB/SDIO only */ void (*fill_txdesc_checksum)(struct rtw_dev *rtwdev, struct rtw_tx_pkt_info *pkt_info, @@ -2098,6 +2098,10 @@ struct rtw_dev { struct completion fw_scan_density; bool ap_active; + bool led_registered; + char led_name[32]; + struct led_classdev led_cdev; + /* hci related data, must be last */ u8 priv[] __aligned(sizeof(void *)); }; diff --git a/drivers/net/wireless/realtek/rtw88/reg.h b/drivers/net/wireless/realtek/rtw88/reg.h index e4d506cf9c33..e438405fba56 100644 --- a/drivers/net/wireless/realtek/rtw88/reg.h +++ b/drivers/net/wireless/realtek/rtw88/reg.h @@ -78,7 +78,19 @@ #define BIT_PAPE_SEL_EN BIT(25) #define BIT_DPDT_WL_SEL BIT(24) #define BIT_DPDT_SEL_EN BIT(23) +#define BIT_GPIO13_14_WL_CTRL_EN BIT(22) +#define BIT_LED2_SV BIT(19) +#define BIT_LED2_CM GENMASK(18, 16) +#define BIT_LED1_SV BIT(11) +#define BIT_LED1_CM GENMASK(10, 8) +#define BIT_LED0_SV BIT(3) +#define BIT_LED0_CM GENMASK(2, 0) +#define BIT_LED_MODE_SW_CTRL 0 +#define BIT_LED_MODE_RX 6 +#define BIT_LED_MODE_TX 4 +#define BIT_LED_MODE_TRX 2 #define REG_LEDCFG2 0x004E +#define REG_GPIO_PIN_CTRL_2 0x0060 #define REG_PAD_CTRL1 0x0064 #define BIT_BT_BTG_SEL BIT(31) #define BIT_PAPE_WLBT_SEL BIT(29) @@ -871,7 +883,17 @@ #define REG_USB_MOD 0xf008 #define REG_USB3_RXITV 0xf050 +#define REG_USB2_PHY_ADR 0xfe40 +#define REG_USB2_PHY_DAT 0xfe41 +#define REG_USB2_PHY_CMD 0xfe42 +#define BIT_USB2_PHY_CMD_TRG 0x81 #define REG_USB_HRPWM 0xfe58 +#define REG_USB3_PHY_ADR 0xff0c +#define REG_USB3_PHY_DAT_L 0xff0d +#define REG_USB3_PHY_DAT_H 0xff0e +#define BIT_USB3_PHY_ADR_WR BIT(7) +#define BIT_USB3_PHY_ADR_RD BIT(6) +#define BIT_USB3_PHY_ADR_MASK GENMASK(5, 0) #define RF_MODE 0x00 #define RF_MODOPT 0x01 diff --git a/drivers/net/wireless/realtek/rtw88/rtw8703b.c b/drivers/net/wireless/realtek/rtw88/rtw8703b.c index a19b94d022ee..1d232adbdd7e 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8703b.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8703b.c @@ -903,7 +903,7 @@ static void rtw8703b_set_channel_bb(struct rtw_dev *rtwdev, u8 channel, u8 bw, rtw_write32_mask(rtwdev, REG_FPGA0_RFMOD, BIT_MASK_RFMOD, 0x0); rtw_write32_mask(rtwdev, REG_FPGA1_RFMOD, BIT_MASK_RFMOD, 0x0); rtw_write32_mask(rtwdev, REG_OFDM0_TX_PSD_NOISE, - GENMASK(31, 20), 0x0); + GENMASK(31, 30), 0x0); rtw_write32(rtwdev, REG_BBRX_DFIR, 0x4A880000); rtw_write32(rtwdev, REG_OFDM0_A_TX_AFE, 0x19F60000); break; @@ -1198,9 +1198,9 @@ static u8 rtw8703b_iqk_rx_path(struct rtw_dev *rtwdev, rtw_write32(rtwdev, REG_RXIQK_TONE_A_11N, 0x38008c1c); rtw_write32(rtwdev, REG_TX_IQK_TONE_B, 0x38008c1c); rtw_write32(rtwdev, REG_RX_IQK_TONE_B, 0x38008c1c); - rtw_write32(rtwdev, REG_TXIQK_PI_A_11N, 0x8216000f); + rtw_write32(rtwdev, REG_TXIQK_PI_A_11N, 0x8214030f); rtw_write32(rtwdev, REG_RXIQK_PI_A_11N, 0x28110000); - rtw_write32(rtwdev, REG_TXIQK_PI_B, 0x28110000); + rtw_write32(rtwdev, REG_TXIQK_PI_B, 0x82110000); rtw_write32(rtwdev, REG_RXIQK_PI_B, 0x28110000); /* LOK setting */ @@ -1372,7 +1372,7 @@ void rtw8703b_iqk_fill_a_matrix(struct rtw_dev *rtwdev, const s32 result[]) return; tmp_rx_iqi |= FIELD_PREP(BIT_MASK_RXIQ_S1_X, result[IQK_S1_RX_X]); - tmp_rx_iqi |= FIELD_PREP(BIT_MASK_RXIQ_S1_Y1, result[IQK_S1_RX_X]); + tmp_rx_iqi |= FIELD_PREP(BIT_MASK_RXIQ_S1_Y1, result[IQK_S1_RX_Y]); rtw_write32(rtwdev, REG_A_RXIQI, tmp_rx_iqi); rtw_write32_mask(rtwdev, REG_RXIQK_MATRIX_LSB_11N, BIT_MASK_RXIQ_S1_Y2, BIT_SET_RXIQ_S1_Y2(result[IQK_S1_RX_Y])); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723x.h b/drivers/net/wireless/realtek/rtw88/rtw8723x.h index e93bfce994bf..a99af527c92c 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8723x.h +++ b/drivers/net/wireless/realtek/rtw88/rtw8723x.h @@ -47,7 +47,7 @@ struct rtw8723xe_efuse { u8 device_id[2]; u8 sub_vendor_id[2]; u8 sub_device_id[2]; -}; +} __packed; struct rtw8723xu_efuse { u8 res4[48]; /* 0xd0 */ @@ -56,12 +56,12 @@ struct rtw8723xu_efuse { u8 usb_option; /* 0x104 */ u8 res5[2]; /* 0x105 */ u8 mac_addr[ETH_ALEN]; /* 0x107 */ -}; +} __packed; struct rtw8723xs_efuse { u8 res4[0x4a]; /* 0xd0 */ u8 mac_addr[ETH_ALEN]; /* 0x11a */ -}; +} __packed; struct rtw8723x_efuse { __le16 rtl_id; @@ -96,7 +96,7 @@ struct rtw8723x_efuse { struct rtw8723xu_efuse u; struct rtw8723xs_efuse s; }; -}; +} __packed; #define RTW8723X_IQK_ADDA_REG_NUM 16 #define RTW8723X_IQK_MAC8_REG_NUM 3 diff --git a/drivers/net/wireless/realtek/rtw88/rtw8812a.c b/drivers/net/wireless/realtek/rtw88/rtw8812a.c index 482edd31823d..f9ba2aa2928a 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8812a.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8812a.c @@ -868,6 +868,22 @@ static void rtw8812a_pwr_track(struct rtw_dev *rtwdev) dm_info->pwr_trk_triggered = false; } +static void rtw8812a_led_set(struct led_classdev *led, + enum led_brightness brightness) +{ + struct rtw_dev *rtwdev = container_of(led, struct rtw_dev, led_cdev); + u8 ledcfg; + + ledcfg = rtw_read8(rtwdev, REG_LED_CFG); + ledcfg &= BIT(6) | BIT(4); + ledcfg |= BIT(5); + + if (brightness == LED_OFF) + ledcfg |= BIT(3); + + rtw_write8(rtwdev, REG_LED_CFG, ledcfg); +} + static void rtw8812a_fill_txdesc_checksum(struct rtw_dev *rtwdev, struct rtw_tx_pkt_info *pkt_info, u8 *txdesc) @@ -916,6 +932,7 @@ static const struct rtw_chip_ops rtw8812a_ops = { .config_bfee = NULL, .set_gid_table = NULL, .cfg_csi_rate = NULL, + .led_set = rtw8812a_led_set, .fill_txdesc_checksum = rtw8812a_fill_txdesc_checksum, .coex_set_init = rtw8812a_coex_cfg_init, .coex_set_ant_switch = NULL, @@ -985,6 +1002,9 @@ static const struct rtw_rfe_def rtw8812a_rfe_defs[] = { [1] = { .phy_pg_tbl = &rtw8812a_bb_pg_tbl, .txpwr_lmt_tbl = &rtw8812a_txpwr_lmt_tbl, .pwr_track_tbl = &rtw8812a_rtw_pwr_track_tbl, }, + [2] = { .phy_pg_tbl = &rtw8812a_bb_pg_tbl, + .txpwr_lmt_tbl = &rtw8812a_txpwr_lmt_tbl, + .pwr_track_tbl = &rtw8812a_rtw_pwr_track_tbl, }, [3] = { .phy_pg_tbl = &rtw8812a_bb_pg_rfe3_tbl, .txpwr_lmt_tbl = &rtw8812a_txpwr_lmt_tbl, .pwr_track_tbl = &rtw8812a_rtw_pwr_track_rfe3_tbl, }, @@ -1024,7 +1044,7 @@ const struct rtw_chip_info rtw8812a_hw_spec = { .rx_buf_desc_sz = 8, .phy_efuse_size = 512, .log_efuse_size = 512, - .ptct_efuse_size = 96 + 1, /* TODO or just 18? */ + .ptct_efuse_size = 0, .txff_size = 131072, .rxff_size = 16128, .rsvd_drv_pg_num = 9, diff --git a/drivers/net/wireless/realtek/rtw88/rtw8812au.c b/drivers/net/wireless/realtek/rtw88/rtw8812au.c index 4da69590a423..e18995f4cc78 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8812au.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8812au.c @@ -9,8 +9,74 @@ #include "usb.h" static const struct usb_device_id rtw_8812au_id_table[] = { - { USB_DEVICE_AND_INTERFACE_INFO(0x2604, 0x0012, 0xff, 0xff, 0xff), + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8812, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x881a, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x881b, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x881c, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x0409, 0x0408, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* NEC */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0411, 0x025d, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Buffalo */ + { USB_DEVICE_AND_INTERFACE_INFO(0x04bb, 0x0952, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* I-O DATA */ + { USB_DEVICE_AND_INTERFACE_INFO(0x050d, 0x1106, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Belkin */ + { USB_DEVICE_AND_INTERFACE_INFO(0x050d, 0x1109, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Belkin */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0586, 0x3426, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* ZyXEL */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0789, 0x016e, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Logitec */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07b8, 0x8812, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Abocom */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0846, 0x9051, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Netgear */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0b05, 0x17d2, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* ASUS */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0df6, 0x0074, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Sitecom */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0e66, 0x0022, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Hawking */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1058, 0x0632, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* WD */ + { USB_DEVICE_AND_INTERFACE_INFO(0x13b1, 0x003f, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Linksys */ + { USB_DEVICE_AND_INTERFACE_INFO(0x148f, 0x9097, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Amped Wireless */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1740, 0x0100, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* EnGenius */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x330e, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3313, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3315, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3316, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2019, 0xab30, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Planex */ + { USB_DEVICE_AND_INTERFACE_INFO(0x20f4, 0x805b, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* TRENDnet */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x0101, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* TP-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x0103, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* TP-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x010d, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* TP-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x010e, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* TP-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x010f, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* TP-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x0122, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* TP-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2604, 0x0012, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Tenda */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xa822, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8812a_hw_spec) }, /* Edimax */ {}, }; MODULE_DEVICE_TABLE(usb, rtw_8812au_id_table); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821a.c b/drivers/net/wireless/realtek/rtw88/rtw8821a.c index db242c9ad68f..f68239b07319 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821a.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821a.c @@ -706,6 +706,31 @@ static void rtw8821a_pwr_track(struct rtw_dev *rtwdev) dm_info->pwr_trk_triggered = false; } +static void rtw8821a_led_set(struct led_classdev *led, + enum led_brightness brightness) +{ + struct rtw_dev *rtwdev = container_of(led, struct rtw_dev, led_cdev); + u32 gpio8_cfg; + u8 ledcfg; + + if (brightness == LED_OFF) { + gpio8_cfg = rtw_read32(rtwdev, REG_GPIO_PIN_CTRL_2); + gpio8_cfg &= ~BIT(24); + gpio8_cfg |= BIT(16) | BIT(8); + rtw_write32(rtwdev, REG_GPIO_PIN_CTRL_2, gpio8_cfg); + } else { + ledcfg = rtw_read8(rtwdev, REG_LED_CFG + 2); + gpio8_cfg = rtw_read32(rtwdev, REG_GPIO_PIN_CTRL_2); + + ledcfg &= BIT(7) | BIT(6); + rtw_write8(rtwdev, REG_LED_CFG + 2, ledcfg); + + gpio8_cfg &= ~(BIT(24) | BIT(8)); + gpio8_cfg |= BIT(16); + rtw_write32(rtwdev, REG_GPIO_PIN_CTRL_2, gpio8_cfg); + } +} + static void rtw8821a_fill_txdesc_checksum(struct rtw_dev *rtwdev, struct rtw_tx_pkt_info *pkt_info, u8 *txdesc) @@ -853,6 +878,7 @@ static const struct rtw_chip_ops rtw8821a_ops = { .config_bfee = NULL, .set_gid_table = NULL, .cfg_csi_rate = NULL, + .led_set = rtw8821a_led_set, .fill_txdesc_checksum = rtw8821a_fill_txdesc_checksum, .coex_set_init = rtw8821a_coex_cfg_init, .coex_set_ant_switch = rtw8821a_coex_cfg_ant_switch, @@ -1118,7 +1144,7 @@ const struct rtw_chip_info rtw8821a_hw_spec = { .rx_buf_desc_sz = 8, .phy_efuse_size = 512, .log_efuse_size = 512, - .ptct_efuse_size = 96 + 1, /* TODO or just 18? */ + .ptct_efuse_size = 0, .txff_size = 65536, .rxff_size = 16128, .rsvd_drv_pg_num = 8, diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821au.c b/drivers/net/wireless/realtek/rtw88/rtw8821au.c index 730018773e1c..a01744b64e8d 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821au.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821au.c @@ -9,8 +9,58 @@ #include "usb.h" static const struct usb_device_id rtw_8821au_id_table[] = { - { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x011e, 0xff, 0xff, 0xff), + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x0811, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x0820, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x0821, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8822, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x0823, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xa811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x0411, 0x0242, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* Buffalo */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0411, 0x029b, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* Buffalo */ + { USB_DEVICE_AND_INTERFACE_INFO(0x04bb, 0x0953, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* I-O DATA */ + { USB_DEVICE_AND_INTERFACE_INFO(0x056e, 0x4007, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* ELECOM */ + { USB_DEVICE_AND_INTERFACE_INFO(0x056e, 0x400e, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* ELECOM */ + { USB_DEVICE_AND_INTERFACE_INFO(0x056e, 0x400f, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* ELECOM */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0846, 0x9052, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* Netgear */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0e66, 0x0023, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* HAWKING */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3314, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3318, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2019, 0xab32, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* Planex */ + { USB_DEVICE_AND_INTERFACE_INFO(0x20f4, 0x804b, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* TRENDnet */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x011e, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* TP Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x011f, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* TP Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x0120, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* TP Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3823, 0x6249, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* Obihai */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xa811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* Edimax */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xa812, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* Edimax */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xa813, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* Edimax */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xb611, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821a_hw_spec) }, /* Edimax */ {}, }; MODULE_DEVICE_TABLE(usb, rtw_8821au_id_table); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c index 0270225b9c20..eb7e34c545d0 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c @@ -1206,6 +1206,24 @@ static void rtw8821c_phy_cck_pd_set(struct rtw_dev *rtwdev, u8 new_lvl) dm_info->cck_pd_default + new_lvl * 2); } +static void rtw8821c_led_set(struct led_classdev *led, + enum led_brightness brightness) +{ + struct rtw_dev *rtwdev = container_of(led, struct rtw_dev, led_cdev); + u32 ledcfg; + + ledcfg = rtw_read32(rtwdev, REG_LED_CFG); + u32p_replace_bits(&ledcfg, BIT_LED_MODE_SW_CTRL, BIT_LED2_CM); + ledcfg &= ~BIT_GPIO13_14_WL_CTRL_EN; + + if (brightness == LED_OFF) + ledcfg |= BIT_LED2_SV; + else + ledcfg &= ~BIT_LED2_SV; + + rtw_write32(rtwdev, REG_LED_CFG, ledcfg); +} + static void rtw8821c_fill_txdesc_checksum(struct rtw_dev *rtwdev, struct rtw_tx_pkt_info *pkt_info, u8 *txdesc) @@ -1655,6 +1673,7 @@ static const struct rtw_chip_ops rtw8821c_ops = { .config_bfee = rtw8821c_bf_config_bfee, .set_gid_table = rtw_bf_set_gid_table, .cfg_csi_rate = rtw_bf_cfg_csi_rate, + .led_set = rtw8821c_led_set, .fill_txdesc_checksum = rtw8821c_fill_txdesc_checksum, .coex_set_init = rtw8821c_coex_cfg_init, diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.h b/drivers/net/wireless/realtek/rtw88/rtw8821c.h index 7a33ebd612ed..954e93c8020d 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.h +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.h @@ -27,7 +27,7 @@ struct rtw8821cu_efuse { u8 res11[0xcf]; u8 package_type; /* 0x1fb */ u8 res12[0x4]; -}; +} __packed; struct rtw8821ce_efuse { u8 mac_addr[ETH_ALEN]; /* 0xd0 */ @@ -47,7 +47,8 @@ struct rtw8821ce_efuse { u8 ltr_en:1; u8 res1:2; u8 obff:2; - u8 res2:3; + u8 res2_1:1; + u8 res2_2:2; u8 obff_cap:2; u8 res3:4; u8 res4[3]; @@ -63,7 +64,7 @@ struct rtw8821ce_efuse { u8 res6:1; u8 port_t_power_on_value:5; u8 res7; -}; +} __packed; struct rtw8821cs_efuse { u8 res4[0x4a]; /* 0xd0 */ @@ -101,7 +102,7 @@ struct rtw8821c_efuse { struct rtw8821cu_efuse u; struct rtw8821cs_efuse s; }; -}; +} __packed; static inline void _rtw_write32s_mask(struct rtw_dev *rtwdev, u32 addr, u32 mask, u32 data) diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c index 739809f4cab5..7f03903ddf4b 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c @@ -1566,6 +1566,24 @@ static void rtw8822b_adaptivity(struct rtw_dev *rtwdev) rtw_phy_set_edcca_th(rtwdev, l2h, h2l); } +static void rtw8822b_led_set(struct led_classdev *led, + enum led_brightness brightness) +{ + struct rtw_dev *rtwdev = container_of(led, struct rtw_dev, led_cdev); + u32 ledcfg; + + ledcfg = rtw_read32(rtwdev, REG_LED_CFG); + u32p_replace_bits(&ledcfg, BIT_LED_MODE_SW_CTRL, BIT_LED2_CM); + ledcfg &= ~BIT_GPIO13_14_WL_CTRL_EN; + + if (brightness == LED_OFF) + ledcfg |= BIT_LED2_SV; + else + ledcfg &= ~BIT_LED2_SV; + + rtw_write32(rtwdev, REG_LED_CFG, ledcfg); +} + static void rtw8822b_fill_txdesc_checksum(struct rtw_dev *rtwdev, struct rtw_tx_pkt_info *pkt_info, u8 *txdesc) @@ -2146,6 +2164,7 @@ static const struct rtw_chip_ops rtw8822b_ops = { .cfg_csi_rate = rtw_bf_cfg_csi_rate, .adaptivity_init = rtw8822b_adaptivity_init, .adaptivity = rtw8822b_adaptivity, + .led_set = rtw8822b_led_set, .fill_txdesc_checksum = rtw8822b_fill_txdesc_checksum, .coex_set_init = rtw8822b_coex_cfg_init, diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.h b/drivers/net/wireless/realtek/rtw88/rtw8822b.h index 0514958fb57c..9fca9ba67c90 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822b.h +++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.h @@ -27,7 +27,7 @@ struct rtw8822bu_efuse { u8 res11[0xcf]; u8 package_type; /* 0x1fb */ u8 res12[0x4]; -}; +} __packed; struct rtw8822be_efuse { u8 mac_addr[ETH_ALEN]; /* 0xd0 */ @@ -47,7 +47,8 @@ struct rtw8822be_efuse { u8 ltr_en:1; u8 res1:2; u8 obff:2; - u8 res2:3; + u8 res2_1:1; + u8 res2_2:2; u8 obff_cap:2; u8 res3:4; u8 res4[3]; @@ -63,7 +64,7 @@ struct rtw8822be_efuse { u8 res6:1; u8 port_t_power_on_value:5; u8 res7; -}; +} __packed; struct rtw8822bs_efuse { u8 res4[0x4a]; /* 0xd0 */ @@ -103,7 +104,7 @@ struct rtw8822b_efuse { struct rtw8822bu_efuse u; struct rtw8822bs_efuse s; }; -}; +} __packed; static inline void _rtw_write32s_mask(struct rtw_dev *rtwdev, u32 addr, u32 mask, u32 data) diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822bu.c b/drivers/net/wireless/realtek/rtw88/rtw8822bu.c index ab620a0b1dfc..8883300fc6ad 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822bu.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822bu.c @@ -67,6 +67,12 @@ static const struct usb_device_id rtw_8822bu_id_table[] = { .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* LiteOn */ { USB_DEVICE_AND_INTERFACE_INFO(0x20f4, 0x808a, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* TRENDnet TEW-808UBM */ + { USB_DEVICE_AND_INTERFACE_INFO(0x20f4, 0x805a, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* TRENDnet TEW-805UBH */ + { USB_DEVICE_AND_INTERFACE_INFO(0x056e, 0x4011, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* ELECOM WDB-867DU3S */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2c4e, 0x0107, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* Mercusys MA30H */ {}, }; MODULE_DEVICE_TABLE(usb, rtw_8822bu_id_table); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c index af6b76937f1d..ec362a817f5f 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c @@ -4537,6 +4537,24 @@ static void rtw8822c_adaptivity(struct rtw_dev *rtwdev) rtw_phy_set_edcca_th(rtwdev, l2h, h2l); } +static void rtw8822c_led_set(struct led_classdev *led, + enum led_brightness brightness) +{ + struct rtw_dev *rtwdev = container_of(led, struct rtw_dev, led_cdev); + u32 ledcfg; + + ledcfg = rtw_read32(rtwdev, REG_LED_CFG); + u32p_replace_bits(&ledcfg, BIT_LED_MODE_SW_CTRL, BIT_LED2_CM); + ledcfg &= ~BIT_GPIO13_14_WL_CTRL_EN; + + if (brightness == LED_OFF) + ledcfg |= BIT_LED2_SV; + else + ledcfg &= ~BIT_LED2_SV; + + rtw_write32(rtwdev, REG_LED_CFG, ledcfg); +} + static void rtw8822c_fill_txdesc_checksum(struct rtw_dev *rtwdev, struct rtw_tx_pkt_info *pkt_info, u8 *txdesc) @@ -4964,6 +4982,7 @@ static const struct rtw_chip_ops rtw8822c_ops = { .cfo_track = rtw8822c_cfo_track, .config_tx_path = rtw8822c_config_tx_path, .config_txrx_mode = rtw8822c_config_trx_mode, + .led_set = rtw8822c_led_set, .fill_txdesc_checksum = rtw8822c_fill_txdesc_checksum, .coex_set_init = rtw8822c_coex_cfg_init, diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.h b/drivers/net/wireless/realtek/rtw88/rtw8822c.h index e2b383d633cd..fc62b67a15f2 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822c.h +++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.h @@ -14,7 +14,7 @@ struct rtw8822cu_efuse { u8 res1[3]; u8 mac_addr[ETH_ALEN]; /* 0x157 */ u8 res2[0x3d]; -}; +} __packed; struct rtw8822cs_efuse { u8 res0[0x4a]; /* 0x120 */ @@ -39,7 +39,8 @@ struct rtw8822ce_efuse { u8 ltr_en:1; u8 res1:2; u8 obff:2; - u8 res2:3; + u8 res2_1:1; + u8 res2_2:2; u8 obff_cap:2; u8 res3:4; u8 class_code[3]; @@ -55,7 +56,7 @@ struct rtw8822ce_efuse { u8 res6:1; u8 port_t_power_on_value:5; u8 res7; -}; +} __packed; struct rtw8822c_efuse { __le16 rtl_id; @@ -102,7 +103,7 @@ struct rtw8822c_efuse { struct rtw8822cu_efuse u; struct rtw8822cs_efuse s; }; -}; +} __packed; enum rtw8822c_dpk_agc_phase { RTW_DPK_GAIN_CHECK, diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c index 799230eb5f16..e024061bdbf7 100644 --- a/drivers/net/wireless/realtek/rtw88/sdio.c +++ b/drivers/net/wireless/realtek/rtw88/sdio.c @@ -1192,6 +1192,8 @@ static void rtw_sdio_indicate_tx_status(struct rtw_dev *rtwdev, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hw *hw = rtwdev->hw; + skb_pull(skb, rtwdev->chip->tx_pkt_desc_sz); + /* enqueue to wait for tx report */ if (info->flags & IEEE80211_TX_CTL_REQ_TX_STATUS) { rtw_tx_report_enqueue(rtwdev, skb, tx_data->sn); diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c index 8d6db68246f1..c4908db4ff0e 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.c +++ b/drivers/net/wireless/realtek/rtw88/usb.c @@ -7,6 +7,7 @@ #include #include "main.h" #include "debug.h" +#include "mac.h" #include "reg.h" #include "tx.h" #include "rx.h" @@ -547,49 +548,58 @@ static void rtw_usb_rx_handler(struct work_struct *work) { struct rtw_usb *rtwusb = container_of(work, struct rtw_usb, rx_work); struct rtw_dev *rtwdev = rtwusb->rtwdev; - const struct rtw_chip_info *chip = rtwdev->chip; - u32 pkt_desc_sz = chip->rx_pkt_desc_sz; struct ieee80211_rx_status rx_status; - u32 pkt_offset, next_pkt, urb_len; struct rtw_rx_pkt_stat pkt_stat; - struct sk_buff *next_skb; + struct sk_buff *rx_skb; struct sk_buff *skb; + u32 pkt_desc_sz = rtwdev->chip->rx_pkt_desc_sz; + u32 max_skb_len = pkt_desc_sz + PHY_STATUS_SIZE * 8 + + IEEE80211_MAX_MPDU_LEN_VHT_11454; + u32 pkt_offset, next_pkt, skb_len; u8 *rx_desc; int limit; for (limit = 0; limit < 200; limit++) { - skb = skb_dequeue(&rtwusb->rx_queue); - if (!skb) + rx_skb = skb_dequeue(&rtwusb->rx_queue); + if (!rx_skb) break; if (skb_queue_len(&rtwusb->rx_queue) >= RTW_USB_MAX_RXQ_LEN) { dev_dbg_ratelimited(rtwdev->dev, "failed to get rx_queue, overflow\n"); - dev_kfree_skb_any(skb); + dev_kfree_skb_any(rx_skb); continue; } - urb_len = skb->len; + rx_desc = rx_skb->data; do { - rx_desc = skb->data; rtw_rx_query_rx_desc(rtwdev, rx_desc, &pkt_stat, &rx_status); pkt_offset = pkt_desc_sz + pkt_stat.drv_info_sz + pkt_stat.shift; - next_pkt = round_up(pkt_stat.pkt_len + pkt_offset, 8); + skb_len = pkt_stat.pkt_len + pkt_offset; + if (skb_len > max_skb_len) { + rtw_dbg(rtwdev, RTW_DBG_USB, + "skipping too big packet: %u\n", + skb_len); + goto skip_packet; + } - if (urb_len >= next_pkt + pkt_desc_sz) - next_skb = skb_clone(skb, GFP_KERNEL); - else - next_skb = NULL; + skb = alloc_skb(skb_len, GFP_ATOMIC); + if (!skb) { + rtw_dbg(rtwdev, RTW_DBG_USB, + "failed to allocate RX skb of size %u\n", + skb_len); + goto skip_packet; + } + + skb_put_data(skb, rx_desc, skb_len); if (pkt_stat.is_c2h) { - skb_trim(skb, pkt_stat.pkt_len + pkt_offset); rtw_fw_c2h_cmd_rx_irqsafe(rtwdev, pkt_offset, skb); } else { skb_pull(skb, pkt_offset); - skb_trim(skb, pkt_stat.pkt_len); rtw_update_rx_freq_for_invalid(rtwdev, skb, &rx_status, &pkt_stat); @@ -598,37 +608,75 @@ static void rtw_usb_rx_handler(struct work_struct *work) ieee80211_rx_irqsafe(rtwdev->hw, skb); } - skb = next_skb; - if (skb) - skb_pull(skb, next_pkt); +skip_packet: + next_pkt = round_up(skb_len, 8); + rx_desc += next_pkt; + } while (rx_desc + pkt_desc_sz < rx_skb->data + rx_skb->len); - urb_len -= next_pkt; - } while (skb); + if (skb_queue_len(&rtwusb->rx_free_queue) >= RTW_USB_RX_SKB_NUM) + dev_kfree_skb_any(rx_skb); + else + skb_queue_tail(&rtwusb->rx_free_queue, rx_skb); } } static void rtw_usb_read_port_complete(struct urb *urb); -static void rtw_usb_rx_resubmit(struct rtw_usb *rtwusb, struct rx_usb_ctrl_block *rxcb) +static void rtw_usb_rx_resubmit(struct rtw_usb *rtwusb, + struct rx_usb_ctrl_block *rxcb, + gfp_t gfp) { struct rtw_dev *rtwdev = rtwusb->rtwdev; + struct sk_buff *rx_skb; int error; - rxcb->rx_skb = alloc_skb(RTW_USB_MAX_RECVBUF_SZ, GFP_ATOMIC); - if (!rxcb->rx_skb) - return; + rx_skb = skb_dequeue(&rtwusb->rx_free_queue); + if (!rx_skb) + rx_skb = alloc_skb(RTW_USB_MAX_RECVBUF_SZ, gfp); + + if (!rx_skb) + goto try_later; + + skb_reset_tail_pointer(rx_skb); + rx_skb->len = 0; + + rxcb->rx_skb = rx_skb; usb_fill_bulk_urb(rxcb->rx_urb, rtwusb->udev, usb_rcvbulkpipe(rtwusb->udev, rtwusb->pipe_in), rxcb->rx_skb->data, RTW_USB_MAX_RECVBUF_SZ, rtw_usb_read_port_complete, rxcb); - error = usb_submit_urb(rxcb->rx_urb, GFP_ATOMIC); + error = usb_submit_urb(rxcb->rx_urb, gfp); if (error) { - kfree_skb(rxcb->rx_skb); + skb_queue_tail(&rtwusb->rx_free_queue, rxcb->rx_skb); + if (error != -ENODEV) rtw_err(rtwdev, "Err sending rx data urb %d\n", error); + + if (error == -ENOMEM) + goto try_later; + } + + return; + +try_later: + rxcb->rx_skb = NULL; + queue_work(rtwusb->rxwq, &rtwusb->rx_urb_work); +} + +static void rtw_usb_rx_resubmit_work(struct work_struct *work) +{ + struct rtw_usb *rtwusb = container_of(work, struct rtw_usb, rx_urb_work); + struct rx_usb_ctrl_block *rxcb; + int i; + + for (i = 0; i < RTW_USB_RXCB_NUM; i++) { + rxcb = &rtwusb->rx_cb[i]; + + if (!rxcb->rx_skb) + rtw_usb_rx_resubmit(rtwusb, rxcb, GFP_ATOMIC); } } @@ -644,15 +692,16 @@ static void rtw_usb_read_port_complete(struct urb *urb) urb->actual_length < 24) { rtw_err(rtwdev, "failed to get urb length:%d\n", urb->actual_length); - if (skb) - dev_kfree_skb_any(skb); + skb_queue_tail(&rtwusb->rx_free_queue, skb); } else { skb_put(skb, urb->actual_length); skb_queue_tail(&rtwusb->rx_queue, skb); queue_work(rtwusb->rxwq, &rtwusb->rx_work); } - rtw_usb_rx_resubmit(rtwusb, rxcb); + rtw_usb_rx_resubmit(rtwusb, rxcb, GFP_ATOMIC); } else { + skb_queue_tail(&rtwusb->rx_free_queue, skb); + switch (urb->status) { case -EINVAL: case -EPIPE: @@ -670,8 +719,6 @@ static void rtw_usb_read_port_complete(struct urb *urb) rtw_err(rtwdev, "status %d\n", urb->status); break; } - if (skb) - dev_kfree_skb_any(skb); } } @@ -789,6 +836,30 @@ static void rtw_usb_dynamic_rx_agg_v1(struct rtw_dev *rtwdev, bool enable) rtw_write16(rtwdev, REG_RXDMA_AGG_PG_TH, val16); } +static void rtw_usb_dynamic_rx_agg_v2(struct rtw_dev *rtwdev, bool enable) +{ + struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev); + u8 size, timeout; + u16 val16; + + if (!enable) { + size = 0x0; + timeout = 0x1; + } else if (rtwusb->udev->speed == USB_SPEED_SUPER) { + size = 0x6; + timeout = 0x1a; + } else { + size = 0x5; + timeout = 0x20; + } + + val16 = u16_encode_bits(size, BIT_RXDMA_AGG_PG_TH) | + u16_encode_bits(timeout, BIT_DMA_AGG_TO_V1); + + rtw_write16(rtwdev, REG_RXDMA_AGG_PG_TH, val16); + rtw_write8_set(rtwdev, REG_TXDMA_PQ_MAP, BIT_RXDMA_AGG_EN); +} + static void rtw_usb_dynamic_rx_agg(struct rtw_dev *rtwdev, bool enable) { switch (rtwdev->chip->id) { @@ -797,6 +868,10 @@ static void rtw_usb_dynamic_rx_agg(struct rtw_dev *rtwdev, bool enable) case RTW_CHIP_TYPE_8821C: rtw_usb_dynamic_rx_agg_v1(rtwdev, enable); break; + case RTW_CHIP_TYPE_8821A: + case RTW_CHIP_TYPE_8812A: + rtw_usb_dynamic_rx_agg_v2(rtwdev, enable); + break; case RTW_CHIP_TYPE_8723D: /* Doesn't like aggregation. */ break; @@ -831,16 +906,26 @@ static struct rtw_hci_ops rtw_usb_ops = { static int rtw_usb_init_rx(struct rtw_dev *rtwdev) { struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev); + struct sk_buff *rx_skb; + int i; - rtwusb->rxwq = create_singlethread_workqueue("rtw88_usb: rx wq"); + rtwusb->rxwq = alloc_workqueue("rtw88_usb: rx wq", WQ_BH, 0); if (!rtwusb->rxwq) { rtw_err(rtwdev, "failed to create RX work queue\n"); return -ENOMEM; } skb_queue_head_init(&rtwusb->rx_queue); + skb_queue_head_init(&rtwusb->rx_free_queue); INIT_WORK(&rtwusb->rx_work, rtw_usb_rx_handler); + INIT_WORK(&rtwusb->rx_urb_work, rtw_usb_rx_resubmit_work); + + for (i = 0; i < RTW_USB_RX_SKB_NUM; i++) { + rx_skb = alloc_skb(RTW_USB_MAX_RECVBUF_SZ, GFP_KERNEL); + if (rx_skb) + skb_queue_tail(&rtwusb->rx_free_queue, rx_skb); + } return 0; } @@ -853,7 +938,7 @@ static void rtw_usb_setup_rx(struct rtw_dev *rtwdev) for (i = 0; i < RTW_USB_RXCB_NUM; i++) { struct rx_usb_ctrl_block *rxcb = &rtwusb->rx_cb[i]; - rtw_usb_rx_resubmit(rtwusb, rxcb); + rtw_usb_rx_resubmit(rtwusb, rxcb, GFP_KERNEL); } } @@ -865,6 +950,8 @@ static void rtw_usb_deinit_rx(struct rtw_dev *rtwdev) flush_workqueue(rtwusb->rxwq); destroy_workqueue(rtwusb->rxwq); + + skb_queue_purge(&rtwusb->rx_free_queue); } static int rtw_usb_init_tx(struct rtw_dev *rtwdev) @@ -930,6 +1017,32 @@ static void rtw_usb_intf_deinit(struct rtw_dev *rtwdev, usb_set_intfdata(intf, NULL); } +static int rtw_usb_switch_mode_old(struct rtw_dev *rtwdev) +{ + struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev); + enum usb_device_speed cur_speed = rtwusb->udev->speed; + u8 hci_opt; + + if (cur_speed == USB_SPEED_HIGH) { + hci_opt = rtw_read8(rtwdev, REG_HCI_OPT_CTRL); + + if ((hci_opt & (BIT(2) | BIT(3))) != BIT(3)) { + rtw_write8(rtwdev, REG_HCI_OPT_CTRL, 0x8); + rtw_write8(rtwdev, REG_SYS_SDIO_CTRL, 0x2); + rtw_write8(rtwdev, REG_ACLK_MON, 0x1); + rtw_write8(rtwdev, 0x3d, 0x3); + /* usb disconnect */ + rtw_write8(rtwdev, REG_SYS_PW_CTRL + 1, 0x80); + return 1; + } + } else if (cur_speed == USB_SPEED_SUPER) { + rtw_write8_clr(rtwdev, REG_SYS_SDIO_CTRL, BIT(1)); + rtw_write8_clr(rtwdev, REG_ACLK_MON, BIT(0)); + } + + return 0; +} + static int rtw_usb_switch_mode_new(struct rtw_dev *rtwdev) { enum usb_device_speed cur_speed; @@ -979,11 +1092,22 @@ static int rtw_usb_switch_mode_new(struct rtw_dev *rtwdev) return 1; } +static bool rtw_usb3_chip_old(u8 chip_id) +{ + return chip_id == RTW_CHIP_TYPE_8812A; +} + +static bool rtw_usb3_chip_new(u8 chip_id) +{ + return chip_id == RTW_CHIP_TYPE_8822C || + chip_id == RTW_CHIP_TYPE_8822B; +} + static int rtw_usb_switch_mode(struct rtw_dev *rtwdev) { u8 id = rtwdev->chip->id; - if (id != RTW_CHIP_TYPE_8822C && id != RTW_CHIP_TYPE_8822B) + if (!rtw_usb3_chip_new(id) && !rtw_usb3_chip_old(id)) return 0; if (!rtwdev->efuse.usb_mode_switch) { @@ -998,7 +1122,75 @@ static int rtw_usb_switch_mode(struct rtw_dev *rtwdev) return 0; } - return rtw_usb_switch_mode_new(rtwdev); + if (rtw_usb3_chip_old(id)) + return rtw_usb_switch_mode_old(rtwdev); + else + return rtw_usb_switch_mode_new(rtwdev); +} + +#define USB_REG_PAGE 0xf4 +#define USB_PHY_PAGE0 0x9b +#define USB_PHY_PAGE1 0xbb + +static void rtw_usb_phy_write(struct rtw_dev *rtwdev, u8 addr, u16 data, + enum usb_device_speed speed) +{ + if (speed == USB_SPEED_SUPER) { + rtw_write8(rtwdev, REG_USB3_PHY_DAT_L, data & 0xff); + rtw_write8(rtwdev, REG_USB3_PHY_DAT_H, data >> 8); + rtw_write8(rtwdev, REG_USB3_PHY_ADR, addr | BIT_USB3_PHY_ADR_WR); + } else if (speed == USB_SPEED_HIGH) { + rtw_write8(rtwdev, REG_USB2_PHY_DAT, data); + rtw_write8(rtwdev, REG_USB2_PHY_ADR, addr); + rtw_write8(rtwdev, REG_USB2_PHY_CMD, BIT_USB2_PHY_CMD_TRG); + } +} + +static void rtw_usb_page_switch(struct rtw_dev *rtwdev, + enum usb_device_speed speed, u8 page) +{ + if (speed == USB_SPEED_SUPER) + return; + + rtw_usb_phy_write(rtwdev, USB_REG_PAGE, page, speed); +} + +static void rtw_usb_phy_cfg(struct rtw_dev *rtwdev, + enum usb_device_speed speed) +{ + const struct rtw_intf_phy_para *para = NULL; + u16 offset; + + if (!rtwdev->chip->intf_table) + return; + + if (speed == USB_SPEED_SUPER) + para = rtwdev->chip->intf_table->usb3_para; + else if (speed == USB_SPEED_HIGH) + para = rtwdev->chip->intf_table->usb2_para; + + if (!para) + return; + + for ( ; para->offset != 0xffff; para++) { + if (!(para->cut_mask & BIT(rtwdev->hal.cut_version))) + continue; + + offset = para->offset; + + if (para->ip_sel == RTW_IP_SEL_MAC) { + rtw_write8(rtwdev, offset, para->value); + } else { + if (offset > 0x100) + rtw_usb_page_switch(rtwdev, speed, USB_PHY_PAGE1); + else + rtw_usb_page_switch(rtwdev, speed, USB_PHY_PAGE0); + + offset &= 0xff; + + rtw_usb_phy_write(rtwdev, offset, para->value, speed); + } + } } int rtw_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) @@ -1056,6 +1248,9 @@ int rtw_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) goto err_destroy_rxwq; } + rtw_usb_phy_cfg(rtwdev, USB_SPEED_HIGH); + rtw_usb_phy_cfg(rtwdev, USB_SPEED_SUPER); + ret = rtw_usb_switch_mode(rtwdev); if (ret) { /* Not a fail, but we do need to skip rtw_register_hw. */ diff --git a/drivers/net/wireless/realtek/rtw88/usb.h b/drivers/net/wireless/realtek/rtw88/usb.h index 86697a5c0103..9b695b688b24 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.h +++ b/drivers/net/wireless/realtek/rtw88/usb.h @@ -38,6 +38,7 @@ #define RTW_USB_RXAGG_TIMEOUT 10 #define RTW_USB_RXCB_NUM 4 +#define RTW_USB_RX_SKB_NUM 8 #define RTW_USB_EP_MAX 4 @@ -81,7 +82,9 @@ struct rtw_usb { struct rx_usb_ctrl_block rx_cb[RTW_USB_RXCB_NUM]; struct sk_buff_head rx_queue; + struct sk_buff_head rx_free_queue; struct work_struct rx_work; + struct work_struct rx_urb_work; }; static inline struct rtw_usb_tx_data *rtw_usb_get_tx_data(struct sk_buff *skb) diff --git a/drivers/net/wireless/realtek/rtw89/Kconfig b/drivers/net/wireless/realtek/rtw89/Kconfig index d2a3361669d7..b1c86cdd9c0e 100644 --- a/drivers/net/wireless/realtek/rtw89/Kconfig +++ b/drivers/net/wireless/realtek/rtw89/Kconfig @@ -96,17 +96,19 @@ config RTW89_8852CE 802.11ax PCIe wireless network (Wi-Fi 6E) adapter config RTW89_8922AE - tristate "Realtek 8922AE PCI wireless network (Wi-Fi 7) adapter" + tristate "Realtek 8922AE/8922AE-VS PCI wireless network (Wi-Fi 7) adapter" depends on PCI select RTW89_CORE select RTW89_PCI select RTW89_8922A help - Select this option will enable support for 8922AE chipset + Select this option will enable support for 8922AE/8922AE-VS chipset 802.11be PCIe wireless network (Wi-Fi 7) adapter supporting 2x2 2GHz/5GHz/6GHz 4096-QAM 160MHz channels. + The variant 8922AE-VS has the same features except 1024-QAM. + config RTW89_DEBUG bool diff --git a/drivers/net/wireless/realtek/rtw89/acpi.c b/drivers/net/wireless/realtek/rtw89/acpi.c index 908e980a4b72..f5dedb12c129 100644 --- a/drivers/net/wireless/realtek/rtw89/acpi.c +++ b/drivers/net/wireless/realtek/rtw89/acpi.c @@ -148,3 +148,50 @@ int rtw89_acpi_evaluate_dsm(struct rtw89_dev *rtwdev, ACPI_FREE(obj); return ret; } + +int rtw89_acpi_evaluate_rtag(struct rtw89_dev *rtwdev, + struct rtw89_acpi_rtag_result *res) +{ + struct acpi_buffer buf = {ACPI_ALLOCATE_BUFFER, NULL}; + acpi_handle root, handle; + union acpi_object *obj; + acpi_status status; + u32 buf_len; + int ret = 0; + + root = ACPI_HANDLE(rtwdev->dev); + if (!root) + return -EOPNOTSUPP; + + status = acpi_get_handle(root, (acpi_string)"RTAG", &handle); + if (ACPI_FAILURE(status)) + return -EIO; + + status = acpi_evaluate_object(handle, NULL, NULL, &buf); + if (ACPI_FAILURE(status)) + return -EIO; + + obj = buf.pointer; + if (obj->type != ACPI_TYPE_BUFFER) { + rtw89_debug(rtwdev, RTW89_DBG_ACPI, + "acpi: expect buffer but type: %d\n", obj->type); + ret = -EINVAL; + goto out; + } + + buf_len = obj->buffer.length; + if (buf_len != sizeof(*res)) { + rtw89_debug(rtwdev, RTW89_DBG_ACPI, "%s: invalid buffer length: %u\n", + __func__, buf_len); + ret = -EINVAL; + goto out; + } + + *res = *(struct rtw89_acpi_rtag_result *)obj->buffer.pointer; + + rtw89_hex_dump(rtwdev, RTW89_DBG_ACPI, "antenna_gain: ", res, sizeof(*res)); + +out: + ACPI_FREE(obj); + return ret; +} diff --git a/drivers/net/wireless/realtek/rtw89/acpi.h b/drivers/net/wireless/realtek/rtw89/acpi.h index d274be1775bf..b43ab106e44d 100644 --- a/drivers/net/wireless/realtek/rtw89/acpi.h +++ b/drivers/net/wireless/realtek/rtw89/acpi.h @@ -63,8 +63,17 @@ struct rtw89_acpi_dsm_result { } u; }; +struct rtw89_acpi_rtag_result { + u8 tag[4]; + u8 revision; + __le32 domain; + u8 ant_gain_table[RTW89_ANT_GAIN_CHAIN_NUM][RTW89_ANT_GAIN_SUBBAND_NR]; +} __packed; + int rtw89_acpi_evaluate_dsm(struct rtw89_dev *rtwdev, enum rtw89_acpi_dsm_func func, struct rtw89_acpi_dsm_result *res); +int rtw89_acpi_evaluate_rtag(struct rtw89_dev *rtwdev, + struct rtw89_acpi_rtag_result *res); #endif diff --git a/drivers/net/wireless/realtek/rtw89/cam.c b/drivers/net/wireless/realtek/rtw89/cam.c index 8ef59994c0db..8fa1e6c1ce13 100644 --- a/drivers/net/wireless/realtek/rtw89/cam.c +++ b/drivers/net/wireless/realtek/rtw89/cam.c @@ -135,8 +135,8 @@ again: } static int rtw89_cam_get_addr_cam_key_idx(struct rtw89_addr_cam_entry *addr_cam, - struct rtw89_sec_cam_entry *sec_cam, - struct ieee80211_key_conf *key, + const struct rtw89_sec_cam_entry *sec_cam, + const struct ieee80211_key_conf *key, u8 *key_idx) { u8 idx; @@ -246,8 +246,8 @@ static int __rtw89_cam_detach_sec_cam(struct rtw89_dev *rtwdev, static int __rtw89_cam_attach_sec_cam(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link, struct rtw89_sta_link *rtwsta_link, - struct ieee80211_key_conf *key, - struct rtw89_sec_cam_entry *sec_cam) + const struct ieee80211_key_conf *key, + const struct rtw89_sec_cam_entry *sec_cam) { struct rtw89_addr_cam_entry *addr_cam; u8 key_idx = 0; @@ -286,6 +286,22 @@ static int __rtw89_cam_attach_sec_cam(struct rtw89_dev *rtwdev, return 0; } +int rtw89_cam_attach_link_sec_cam(struct rtw89_dev *rtwdev, + struct rtw89_vif_link *rtwvif_link, + struct rtw89_sta_link *rtwsta_link, + u8 sec_cam_idx) +{ + struct rtw89_cam_info *cam_info = &rtwdev->cam_info; + const struct rtw89_sec_cam_entry *sec_cam; + + sec_cam = cam_info->sec_entries[sec_cam_idx]; + if (!sec_cam) + return -ENOENT; + + return __rtw89_cam_attach_sec_cam(rtwdev, rtwvif_link, rtwsta_link, + sec_cam->key_conf, sec_cam); +} + static int rtw89_cam_detach_sec_cam(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta, @@ -306,6 +322,9 @@ static int rtw89_cam_detach_sec_cam(struct rtw89_dev *rtwdev, rtwvif = vif_to_rtwvif(vif); + if (rtwsta) + clear_bit(sec_cam->sec_cam_idx, rtwsta->pairwise_sec_cam_map); + rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id) { rtwsta_link = rtwsta ? rtwsta->links[link_id] : NULL; if (rtwsta && !rtwsta_link) @@ -369,6 +388,8 @@ static int rtw89_cam_attach_sec_cam(struct rtw89_dev *rtwdev, return ret; } + set_bit(sec_cam->sec_cam_idx, rtwsta->pairwise_sec_cam_map); + return 0; } @@ -410,6 +431,9 @@ static int rtw89_cam_sec_key_install(struct rtw89_dev *rtwdev, sec_cam->len = RTW89_SEC_CAM_LEN; sec_cam->ext_key = ext_key; memcpy(sec_cam->key, key->key, key->keylen); + + sec_cam->key_conf = key; + ret = rtw89_cam_send_sec_key_cmd(rtwdev, sec_cam); if (ret) { rtw89_err(rtwdev, "failed to send sec key cmd: %d\n", ret); diff --git a/drivers/net/wireless/realtek/rtw89/cam.h b/drivers/net/wireless/realtek/rtw89/cam.h index 3134ebf08825..8fd2d776408e 100644 --- a/drivers/net/wireless/realtek/rtw89/cam.h +++ b/drivers/net/wireless/realtek/rtw89/cam.h @@ -578,4 +578,9 @@ int rtw89_cam_sec_key_del(struct rtw89_dev *rtwdev, void rtw89_cam_bssid_changed(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link); void rtw89_cam_reset_keys(struct rtw89_dev *rtwdev); +int rtw89_cam_attach_link_sec_cam(struct rtw89_dev *rtwdev, + struct rtw89_vif_link *rtwvif_link, + struct rtw89_sta_link *rtwsta_link, + u8 sec_cam_idx); + #endif diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c index fb9449930c40..4df4e04c3e67 100644 --- a/drivers/net/wireless/realtek/rtw89/chan.c +++ b/drivers/net/wireless/realtek/rtw89/chan.c @@ -391,11 +391,12 @@ static void rtw89_entity_recalc_mgnt_roles(struct rtw89_dev *rtwdev) list_del(&role->mgnt_entry); list_add(&role->mgnt_entry, &mgnt->active_list); - break; + goto fill; } } } +fill: list_for_each_entry(role, &mgnt->active_list, mgnt_entry) { if (unlikely(pos >= RTW89_MAX_INTERFACE_NUM)) { rtw89_warn(rtwdev, @@ -801,7 +802,7 @@ fill: mcc_role->limit.max_toa = max_toa_us / 1024; mcc_role->limit.max_tob = max_tob_us / 1024; - mcc_role->limit.max_dur = max_dur_us / 1024; + mcc_role->limit.max_dur = mcc_role->limit.max_toa + mcc_role->limit.max_tob; mcc_role->limit.enable = true; rtw89_debug(rtwdev, RTW89_DBG_CHAN, @@ -2530,7 +2531,25 @@ void rtw89_chanctx_pause(struct rtw89_dev *rtwdev, hal->entity_pause = true; } -void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev) +static void rtw89_chanctx_proceed_cb(struct rtw89_dev *rtwdev, + const struct rtw89_chanctx_cb_parm *parm) +{ + int ret; + + if (!parm || !parm->cb) + return; + + ret = parm->cb(rtwdev, parm->data); + if (ret) + rtw89_warn(rtwdev, "%s (%s): cb failed: %d\n", __func__, + parm->caller ?: "unknown", ret); +} + +/* pass @cb_parm if there is a @cb_parm->cb which needs to invoke right after + * call rtw89_set_channel() and right before proceed entity according to mode. + */ +void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev, + const struct rtw89_chanctx_cb_parm *cb_parm) { struct rtw89_hal *hal = &rtwdev->hal; enum rtw89_entity_mode mode; @@ -2538,14 +2557,18 @@ void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev) lockdep_assert_held(&rtwdev->mutex); - if (!hal->entity_pause) + if (unlikely(!hal->entity_pause)) { + rtw89_chanctx_proceed_cb(rtwdev, cb_parm); return; + } rtw89_debug(rtwdev, RTW89_DBG_CHAN, "chanctx proceed\n"); hal->entity_pause = false; rtw89_set_channel(rtwdev); + rtw89_chanctx_proceed_cb(rtwdev, cb_parm); + mode = rtw89_get_entity_mode(rtwdev); switch (mode) { case RTW89_ENTITY_MODE_MCC: diff --git a/drivers/net/wireless/realtek/rtw89/chan.h b/drivers/net/wireless/realtek/rtw89/chan.h index 2eb31dff2083..092a6f676894 100644 --- a/drivers/net/wireless/realtek/rtw89/chan.h +++ b/drivers/net/wireless/realtek/rtw89/chan.h @@ -38,6 +38,12 @@ enum rtw89_chanctx_pause_reasons { RTW89_CHANCTX_PAUSE_REASON_ROC, }; +struct rtw89_chanctx_cb_parm { + int (*cb)(struct rtw89_dev *rtwdev, void *data); + void *data; + const char *caller; +}; + struct rtw89_entity_weight { unsigned int active_chanctxs; unsigned int active_roles; @@ -100,7 +106,8 @@ void rtw89_queue_chanctx_change(struct rtw89_dev *rtwdev, void rtw89_chanctx_track(struct rtw89_dev *rtwdev); void rtw89_chanctx_pause(struct rtw89_dev *rtwdev, enum rtw89_chanctx_pause_reasons rsn); -void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev); +void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev, + const struct rtw89_chanctx_cb_parm *cb_parm); const struct rtw89_chan *__rtw89_mgnt_chan_get(struct rtw89_dev *rtwdev, const char *caller_message, diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c index e5b2968c1431..85f739f1173d 100644 --- a/drivers/net/wireless/realtek/rtw89/core.c +++ b/drivers/net/wireless/realtek/rtw89/core.c @@ -203,6 +203,55 @@ static const struct ieee80211_iface_combination rtw89_iface_combs[] = { }, }; +#define RTW89_6GHZ_SPAN_HEAD 6145 +#define RTW89_6GHZ_SPAN_IDX(center_freq) \ + ((((int)(center_freq) - RTW89_6GHZ_SPAN_HEAD) / 5) / 2) + +#define RTW89_DECL_6GHZ_SPAN(center_freq, subband_l, subband_h) \ + [RTW89_6GHZ_SPAN_IDX(center_freq)] = { \ + .sar_subband_low = RTW89_SAR_6GHZ_ ## subband_l, \ + .sar_subband_high = RTW89_SAR_6GHZ_ ## subband_h, \ + .ant_gain_subband_low = RTW89_ANT_GAIN_6GHZ_ ## subband_l, \ + .ant_gain_subband_high = RTW89_ANT_GAIN_6GHZ_ ## subband_h, \ + } + +/* Since 6GHz subbands are not edge aligned, some cases span two subbands. + * In the following, we describe each of them with rtw89_6ghz_span. + */ +static const struct rtw89_6ghz_span rtw89_overlapping_6ghz[] = { + RTW89_DECL_6GHZ_SPAN(6145, SUBBAND_5_L, SUBBAND_5_H), + RTW89_DECL_6GHZ_SPAN(6165, SUBBAND_5_L, SUBBAND_5_H), + RTW89_DECL_6GHZ_SPAN(6185, SUBBAND_5_L, SUBBAND_5_H), + RTW89_DECL_6GHZ_SPAN(6505, SUBBAND_6, SUBBAND_7_L), + RTW89_DECL_6GHZ_SPAN(6525, SUBBAND_6, SUBBAND_7_L), + RTW89_DECL_6GHZ_SPAN(6545, SUBBAND_6, SUBBAND_7_L), + RTW89_DECL_6GHZ_SPAN(6665, SUBBAND_7_L, SUBBAND_7_H), + RTW89_DECL_6GHZ_SPAN(6705, SUBBAND_7_L, SUBBAND_7_H), + RTW89_DECL_6GHZ_SPAN(6825, SUBBAND_7_H, SUBBAND_8), + RTW89_DECL_6GHZ_SPAN(6865, SUBBAND_7_H, SUBBAND_8), + RTW89_DECL_6GHZ_SPAN(6875, SUBBAND_7_H, SUBBAND_8), + RTW89_DECL_6GHZ_SPAN(6885, SUBBAND_7_H, SUBBAND_8), +}; + +const struct rtw89_6ghz_span * +rtw89_get_6ghz_span(struct rtw89_dev *rtwdev, u32 center_freq) +{ + int idx; + + if (center_freq >= RTW89_6GHZ_SPAN_HEAD) { + idx = RTW89_6GHZ_SPAN_IDX(center_freq); + /* To decrease size of rtw89_overlapping_6ghz[], + * RTW89_6GHZ_SPAN_IDX() truncates the leading NULLs + * to make first span as index 0 of the table. So, if center + * frequency is less than the first one, it will get netative. + */ + if (idx >= 0 && idx < ARRAY_SIZE(rtw89_overlapping_6ghz)) + return &rtw89_overlapping_6ghz[idx]; + } + + return NULL; +} + bool rtw89_ra_report_to_bitrate(struct rtw89_dev *rtwdev, u8 rpt_rate, u16 *bitrate) { struct ieee80211_rate rate; @@ -931,6 +980,11 @@ rtw89_core_tx_update_desc_info(struct rtw89_dev *rtwdev, bool is_bmc; u16 seq; + if (tx_req->sta) + desc_info->mlo = tx_req->sta->mlo; + else if (tx_req->vif) + desc_info->mlo = ieee80211_vif_is_mld(tx_req->vif); + seq = (le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4; if (tx_req->tx_type != RTW89_CORE_TX_TYPE_FWCMD) { tx_type = rtw89_core_get_tx_type(rtwdev, skb); @@ -938,7 +992,7 @@ rtw89_core_tx_update_desc_info(struct rtw89_dev *rtwdev, addr_cam = rtw89_get_addr_cam_of(tx_req->rtwvif_link, tx_req->rtwsta_link); - if (addr_cam->valid) + if (addr_cam->valid && desc_info->mlo) upd_wlan_hdr = true; } is_bmc = (is_broadcast_ether_addr(hdr->addr1) || @@ -1078,6 +1132,8 @@ int rtw89_core_tx_write(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, } tx_req.skb = skb; + tx_req.vif = vif; + tx_req.sta = sta; tx_req.rtwvif_link = rtwvif_link; tx_req.rtwsta_link = rtwsta_link; @@ -2140,6 +2196,8 @@ static void rtw89_vif_rx_stats_iter(void *data, u8 *mac, if (phy_ppdu) ewma_rssi_add(&rtwdev->phystat.bcn_rssi, phy_ppdu->rssi_avg); + + pkt_stat->beacon_rate = desc_info->data_rate; } if (!ether_addr_equal(bss_conf->addr, hdr->addr1)) @@ -2317,6 +2375,12 @@ static void rtw89_core_update_radiotap(struct rtw89_dev *rtwdev, } } +static void rtw89_core_validate_rx_signal(struct ieee80211_rx_status *rx_status) +{ + if (!rx_status->signal) + rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL; +} + static void rtw89_core_rx_to_mac80211(struct rtw89_dev *rtwdev, struct rtw89_rx_phy_ppdu *phy_ppdu, struct rtw89_rx_desc_info *desc_info, @@ -2333,6 +2397,8 @@ static void rtw89_core_rx_to_mac80211(struct rtw89_dev *rtwdev, rtw89_core_rx_stats(rtwdev, phy_ppdu, desc_info, skb_ppdu); rtw89_core_update_rx_status_by_ppdu(rtwdev, rx_status, phy_ppdu); rtw89_core_update_radiotap(rtwdev, skb_ppdu, rx_status); + rtw89_core_validate_rx_signal(rx_status); + /* In low power mode, it does RX in thread context. */ local_bh_disable(); ieee80211_rx_napi(rtwdev->hw, NULL, skb_ppdu, napi); @@ -2468,6 +2534,7 @@ void rtw89_core_query_rxdesc_v2(struct rtw89_dev *rtwdev, struct rtw89_rx_desc_info *desc_info, u8 *data, u32 data_offset) { + struct rtw89_rxdesc_phy_rpt_v2 *rxd_rpt; struct rtw89_rxdesc_short_v2 *rxd_s; struct rtw89_rxdesc_long_v2 *rxd_l; u16 shift_len, drv_info_len, phy_rtp_len, hdr_cnv_len; @@ -2515,6 +2582,12 @@ void rtw89_core_query_rxdesc_v2(struct rtw89_dev *rtwdev, desc_info->rxd_len = sizeof(struct rtw89_rxdesc_short_v2); desc_info->ready = true; + if (phy_rtp_len == sizeof(*rxd_rpt)) { + rxd_rpt = (struct rtw89_rxdesc_phy_rpt_v2 *)(data + data_offset + + desc_info->rxd_len); + desc_info->rssi = le32_get_bits(rxd_rpt->dword0, BE_RXD_PHY_RSSI); + } + if (!desc_info->long_rxdesc) return; @@ -2657,6 +2730,7 @@ static void rtw89_core_update_rx_status(struct rtw89_dev *rtwdev, rx_status->flag |= RX_FLAG_MACTIME_START; rx_status->mactime = desc_info->free_run_cnt; + rtw89_chip_phy_rpt_to_rssi(rtwdev, desc_info, rx_status); rtw89_core_stats_sta_rx_status(rtwdev, desc_info, rx_status); } @@ -2664,10 +2738,6 @@ static enum rtw89_ps_mode rtw89_update_ps_mode(struct rtw89_dev *rtwdev) { const struct rtw89_chip_info *chip = rtwdev->chip; - /* FIXME: Fix __rtw89_enter_ps_mode() to consider MLO cases. */ - if (rtwdev->support_mlo) - return RTW89_PS_MODE_NONE; - if (rtw89_disable_ps_mode || !chip->ps_mode_supported || RTW89_CHK_FW_FEATURE(NO_DEEP_PS, &rtwdev->fw)) return RTW89_PS_MODE_NONE; @@ -2700,6 +2770,41 @@ static void rtw89_core_flush_ppdu_rx_queue(struct rtw89_dev *rtwdev, } } +static +void rtw89_core_rx_pkt_hdl(struct rtw89_dev *rtwdev, const struct sk_buff *skb, + const struct rtw89_rx_desc_info *desc) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + struct rtw89_sta_link *rtwsta_link; + struct ieee80211_sta *sta; + struct rtw89_sta *rtwsta; + u8 macid = desc->mac_id; + + if (!refcount_read(&rtwdev->refcount_ap_info)) + return; + + rcu_read_lock(); + + rtwsta_link = rtw89_assoc_link_rcu_dereference(rtwdev, macid); + if (!rtwsta_link) + goto out; + + rtwsta = rtwsta_link->rtwsta; + if (!test_bit(RTW89_REMOTE_STA_IN_PS, rtwsta->flags)) + goto out; + + sta = rtwsta_to_sta(rtwsta); + if (ieee80211_is_pspoll(hdr->frame_control)) + ieee80211_sta_pspoll(sta); + else if (ieee80211_has_pm(hdr->frame_control) && + (ieee80211_is_data_qos(hdr->frame_control) || + ieee80211_is_qos_nullfunc(hdr->frame_control))) + ieee80211_sta_uapsd_trigger(sta, ieee80211_get_tid(hdr)); + +out: + rcu_read_unlock(); +} + void rtw89_core_rx(struct rtw89_dev *rtwdev, struct rtw89_rx_desc_info *desc_info, struct sk_buff *skb) @@ -2722,6 +2827,7 @@ void rtw89_core_rx(struct rtw89_dev *rtwdev, rx_status = IEEE80211_SKB_RXCB(skb); memset(rx_status, 0, sizeof(*rx_status)); rtw89_core_update_rx_status(rtwdev, desc_info, rx_status); + rtw89_core_rx_pkt_hdl(rtwdev, skb, desc_info); if (desc_info->long_rxdesc && BIT(desc_info->frame_type) & PPDU_FILTER_BITMAP) skb_queue_tail(&ppdu_sts->rx_queue[band], skb); @@ -3131,6 +3237,7 @@ static int rtw89_core_send_nullfunc(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link, bool qos, bool ps) { struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link); + int link_id = ieee80211_vif_is_mld(vif) ? rtwvif_link->link_id : -1; struct ieee80211_sta *sta; struct ieee80211_hdr *hdr; struct sk_buff *skb; @@ -3146,7 +3253,7 @@ static int rtw89_core_send_nullfunc(struct rtw89_dev *rtwdev, goto out; } - skb = ieee80211_nullfunc_get(rtwdev->hw, vif, -1, qos); + skb = ieee80211_nullfunc_get(rtwdev->hw, vif, link_id, qos); if (!skb) { ret = -ENOMEM; goto out; @@ -3257,7 +3364,7 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif) roc->state = RTW89_ROC_IDLE; rtw89_config_roc_chandef(rtwdev, rtwvif_link->chanctx_idx, NULL); - rtw89_chanctx_proceed(rtwdev); + rtw89_chanctx_proceed(rtwdev, NULL); ret = rtw89_core_send_nullfunc(rtwdev, rtwvif_link, true, false); if (ret) rtw89_debug(rtwdev, RTW89_DBG_TXRX, @@ -3367,21 +3474,10 @@ static bool rtw89_traffic_stats_track(struct rtw89_dev *rtwdev) return tfc_changed; } -static void rtw89_vif_enter_lps(struct rtw89_dev *rtwdev, - struct rtw89_vif_link *rtwvif_link) -{ - if (rtwvif_link->wifi_role != RTW89_WIFI_ROLE_STATION && - rtwvif_link->wifi_role != RTW89_WIFI_ROLE_P2P_CLIENT) - return; - - rtw89_enter_lps(rtwdev, rtwvif_link, true); -} - static void rtw89_enter_lps_track(struct rtw89_dev *rtwdev) { - struct rtw89_vif_link *rtwvif_link; + struct ieee80211_vif *vif; struct rtw89_vif *rtwvif; - unsigned int link_id; rtw89_for_each_rtwvif(rtwdev, rtwvif) { if (rtwvif->tdls_peer) @@ -3393,8 +3489,13 @@ static void rtw89_enter_lps_track(struct rtw89_dev *rtwdev) rtwvif->stats.rx_tfc_lv != RTW89_TFC_IDLE) continue; - rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id) - rtw89_vif_enter_lps(rtwdev, rtwvif_link); + vif = rtwvif_to_vif(rtwvif); + + if (!(vif->type == NL80211_IFTYPE_STATION || + vif->type == NL80211_IFTYPE_P2P_CLIENT)) + continue; + + rtw89_enter_lps(rtwdev, rtwvif, true); } } @@ -3699,6 +3800,8 @@ int rtw89_core_sta_link_disassoc(struct rtw89_dev *rtwdev, { const struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link); + rtw89_assoc_link_clr(rtwsta_link); + if (vif->type == NL80211_IFTYPE_STATION) rtw89_fw_h2c_set_bcn_fltr_cfg(rtwdev, rtwvif_link, false); @@ -3748,6 +3851,22 @@ int rtw89_core_sta_link_disconnect(struct rtw89_dev *rtwdev, return ret; } +static bool rtw89_sta_link_can_er(struct rtw89_dev *rtwdev, + struct ieee80211_bss_conf *bss_conf, + struct ieee80211_link_sta *link_sta) +{ + if (!bss_conf->he_support || + bss_conf->he_oper.params & IEEE80211_HE_OPERATION_ER_SU_DISABLE) + return false; + + if (rtwdev->chip->chip_id == RTL8852C && + rtw89_sta_link_has_su_mu_4xhe08(link_sta) && + !rtw89_sta_link_has_er_su_4xhe08(link_sta)) + return false; + + return true; +} + int rtw89_core_sta_link_assoc(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link, struct rtw89_sta_link *rtwsta_link) @@ -3758,12 +3877,11 @@ int rtw89_core_sta_link_assoc(struct rtw89_dev *rtwdev, rtwsta_link); const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, rtwvif_link->chanctx_idx); + struct ieee80211_link_sta *link_sta; int ret; if (vif->type == NL80211_IFTYPE_AP || sta->tdls) { if (sta->tdls) { - struct ieee80211_link_sta *link_sta; - rcu_read_lock(); link_sta = rtw89_sta_rcu_dereference_link(rtwsta_link, true); @@ -3814,9 +3932,8 @@ int rtw89_core_sta_link_assoc(struct rtw89_dev *rtwdev, rcu_read_lock(); bss_conf = rtw89_vif_rcu_dereference_link(rtwvif_link, true); - if (bss_conf->he_support && - !(bss_conf->he_oper.params & IEEE80211_HE_OPERATION_ER_SU_DISABLE)) - rtwsta_link->er_cap = true; + link_sta = rtw89_sta_rcu_dereference_link(rtwsta_link, true); + rtwsta_link->er_cap = rtw89_sta_link_can_er(rtwdev, bss_conf, link_sta); rcu_read_unlock(); @@ -3834,6 +3951,7 @@ int rtw89_core_sta_link_assoc(struct rtw89_dev *rtwdev, rtw89_fw_h2c_set_bcn_fltr_cfg(rtwdev, rtwvif_link, true); } + rtw89_assoc_link_set(rtwsta_link); return ret; } @@ -4117,13 +4235,17 @@ static void rtw89_init_eht_cap(struct rtw89_dev *rtwdev, struct ieee80211_eht_mcs_nss_supp *eht_nss; struct ieee80211_sta_eht_cap *eht_cap; struct rtw89_hal *hal = &rtwdev->hal; + bool support_mcs_12_13 = true; bool support_320mhz = false; + u8 val, val_mcs13; int sts = 8; - u8 val; if (chip->chip_gen == RTW89_CHIP_AX) return; + if (hal->no_mcs_12_13) + support_mcs_12_13 = false; + if (band == NL80211_BAND_6GHZ && chip->support_bandwidths & BIT(NL80211_CHAN_WIDTH_320)) support_320mhz = true; @@ -4181,16 +4303,18 @@ static void rtw89_init_eht_cap(struct rtw89_dev *rtwdev, val = u8_encode_bits(hal->rx_nss, IEEE80211_EHT_MCS_NSS_RX) | u8_encode_bits(hal->tx_nss, IEEE80211_EHT_MCS_NSS_TX); + val_mcs13 = support_mcs_12_13 ? val : 0; + eht_nss->bw._80.rx_tx_mcs9_max_nss = val; eht_nss->bw._80.rx_tx_mcs11_max_nss = val; - eht_nss->bw._80.rx_tx_mcs13_max_nss = val; + eht_nss->bw._80.rx_tx_mcs13_max_nss = val_mcs13; eht_nss->bw._160.rx_tx_mcs9_max_nss = val; eht_nss->bw._160.rx_tx_mcs11_max_nss = val; - eht_nss->bw._160.rx_tx_mcs13_max_nss = val; + eht_nss->bw._160.rx_tx_mcs13_max_nss = val_mcs13; if (support_320mhz) { eht_nss->bw._320.rx_tx_mcs9_max_nss = val; eht_nss->bw._320.rx_tx_mcs11_max_nss = val; - eht_nss->bw._320.rx_tx_mcs13_max_nss = val; + eht_nss->bw._320.rx_tx_mcs13_max_nss = val_mcs13; } } @@ -4433,6 +4557,7 @@ int rtw89_core_start(struct rtw89_dev *rtwdev) rtw89_phy_dm_init(rtwdev); rtw89_mac_cfg_ppdu_status_bands(rtwdev, true); + rtw89_mac_cfg_phy_rpt_bands(rtwdev, true); rtw89_mac_update_rts_threshold(rtwdev); rtw89_tas_reset(rtwdev); @@ -4755,6 +4880,7 @@ int rtw89_core_init(struct rtw89_dev *rtwdev) rtw89_ser_init(rtwdev); rtw89_entity_init(rtwdev); rtw89_tas_init(rtwdev); + rtw89_phy_ant_gain_init(rtwdev); return 0; } @@ -5100,6 +5226,9 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev) if (RTW89_CHK_FW_FEATURE(BEACON_FILTER, &rtwdev->fw)) ieee80211_hw_set(hw, CONNECTION_MONITOR); + if (RTW89_CHK_FW_FEATURE(NOTIFY_AP_INFO, &rtwdev->fw)) + ieee80211_hw_set(hw, AP_LINK_PS); + hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP) | BIT(NL80211_IFTYPE_P2P_CLIENT) | @@ -5220,7 +5349,8 @@ EXPORT_SYMBOL(rtw89_core_unregister); struct rtw89_dev *rtw89_alloc_ieee80211_hw(struct device *device, u32 bus_data_size, - const struct rtw89_chip_info *chip) + const struct rtw89_chip_info *chip, + const struct rtw89_chip_variant *variant) { struct rtw89_fw_info early_fw = {}; const struct firmware *firmware; @@ -5278,6 +5408,7 @@ struct rtw89_dev *rtw89_alloc_ieee80211_hw(struct device *device, rtwdev->dev = device; rtwdev->ops = ops; rtwdev->chip = chip; + rtwdev->variant = variant; rtwdev->fw.req.firmware = firmware; rtwdev->fw.fw_format = fw_format; rtwdev->support_mlo = support_mlo; diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h index 5ad32eacd0d5..ff4894c7fa8a 100644 --- a/drivers/net/wireless/realtek/rtw89/core.h +++ b/drivers/net/wireless/realtek/rtw89/core.h @@ -830,6 +830,7 @@ enum rtw89_phy_idx { }; #define __RTW89_MLD_MAX_LINK_NUM 2 +#define RTW89_MLD_NON_STA_LINK_NUM 1 enum rtw89_chanctx_idx { RTW89_CHANCTX_0 = 0, @@ -1083,6 +1084,7 @@ struct rtw89_rx_desc_info { u16 offset; u16 rxd_len; bool ready; + u16 rssi; }; struct rtw89_rxdesc_short { @@ -1125,6 +1127,11 @@ struct rtw89_rxdesc_long_v2 { __le32 dword9; } __packed; +struct rtw89_rxdesc_phy_rpt_v2 { + __le32 dword0; + __le32 dword1; +} __packed; + struct rtw89_tx_desc_info { u16 pkt_size; u8 wp_offset; @@ -1163,12 +1170,15 @@ struct rtw89_tx_desc_info { bool stbc; bool ldpc; bool upd_wlan_hdr; + bool mlo; }; struct rtw89_core_tx_request { enum rtw89_core_tx_type tx_type; struct sk_buff *skb; + struct ieee80211_vif *vif; + struct ieee80211_sta *sta; struct rtw89_vif_link *rtwvif_link; struct rtw89_sta_link *rtwsta_link; struct rtw89_tx_desc_info desc_info; @@ -3358,6 +3368,8 @@ struct rtw89_sec_cam_entry { u8 spp_mode : 1; /* 256 bits */ u8 key[32]; + + struct ieee80211_key_conf *key_conf; }; struct rtw89_sta_link { @@ -3621,6 +3633,9 @@ struct rtw89_chip_ops { struct ieee80211_rx_status *status); void (*convert_rpl_to_rssi)(struct rtw89_dev *rtwdev, struct rtw89_rx_phy_ppdu *phy_ppdu); + void (*phy_rpt_to_rssi)(struct rtw89_dev *rtwdev, + struct rtw89_rx_desc_info *desc_info, + struct ieee80211_rx_status *rx_status); void (*ctrl_nbtg_bt_tx)(struct rtw89_dev *rtwdev, bool en, enum rtw89_phy_idx phy_idx); void (*cfg_txrx_path)(struct rtw89_dev *rtwdev); @@ -4255,6 +4270,7 @@ struct rtw89_chip_info { u16 support_bandwidths; bool support_unii4; bool support_rnr; + bool support_ant_gain; bool ul_tb_waveform_ctrl; bool ul_tb_pwr_diff; bool hw_sec_hdr; @@ -4296,6 +4312,7 @@ struct rtw89_chip_info { const struct rtw89_rfe_parms *dflt_parms; const struct rtw89_chanctx_listener *chanctx_listener; + u8 txpwr_factor_bb; u8 txpwr_factor_rf; u8 txpwr_factor_mac; @@ -4350,12 +4367,18 @@ struct rtw89_chip_info { const struct rtw89_xtal_info *xtal_info; }; +struct rtw89_chip_variant { + bool no_mcs_12_13: 1; + u32 fw_min_ver_code; +}; + union rtw89_bus_info { const struct rtw89_pci_info *pci; }; struct rtw89_driver_info { const struct rtw89_chip_info *chip; + const struct rtw89_chip_variant *variant; const struct dmi_system_id *quirks; union rtw89_bus_info bus; }; @@ -4448,8 +4471,13 @@ enum rtw89_fw_feature { RTW89_FW_FEATURE_SCAN_OFFLOAD_BE_V0, RTW89_FW_FEATURE_WOW_REASON_V1, RTW89_FW_FEATURE_RFK_PRE_NOTIFY_V0, + RTW89_FW_FEATURE_RFK_PRE_NOTIFY_V1, RTW89_FW_FEATURE_RFK_RXDCK_V0, RTW89_FW_FEATURE_NO_WOW_CPU_IO_RX, + RTW89_FW_FEATURE_NOTIFY_AP_INFO, + RTW89_FW_FEATURE_CH_INFO_BE_V0, + RTW89_FW_FEATURE_LPS_CH_INFO, + RTW89_FW_FEATURE_NO_PHYCAP_P1, }; struct rtw89_fw_suit { @@ -4597,6 +4625,44 @@ struct rtw89_sar_info { }; }; +enum rtw89_ant_gain_subband { + RTW89_ANT_GAIN_2GHZ_SUBBAND, + RTW89_ANT_GAIN_5GHZ_SUBBAND_1, /* U-NII-1 */ + RTW89_ANT_GAIN_5GHZ_SUBBAND_2, /* U-NII-2 */ + RTW89_ANT_GAIN_5GHZ_SUBBAND_2E, /* U-NII-2-Extended */ + RTW89_ANT_GAIN_5GHZ_SUBBAND_3_4, /* U-NII-3 and U-NII-4 */ + RTW89_ANT_GAIN_6GHZ_SUBBAND_5_L, /* U-NII-5 lower part */ + RTW89_ANT_GAIN_6GHZ_SUBBAND_5_H, /* U-NII-5 higher part */ + RTW89_ANT_GAIN_6GHZ_SUBBAND_6, /* U-NII-6 */ + RTW89_ANT_GAIN_6GHZ_SUBBAND_7_L, /* U-NII-7 lower part */ + RTW89_ANT_GAIN_6GHZ_SUBBAND_7_H, /* U-NII-7 higher part */ + RTW89_ANT_GAIN_6GHZ_SUBBAND_8, /* U-NII-8 */ + + RTW89_ANT_GAIN_SUBBAND_NR, +}; + +enum rtw89_ant_gain_domain_type { + RTW89_ANT_GAIN_ETSI = 0, + + RTW89_ANT_GAIN_DOMAIN_NUM, +}; + +#define RTW89_ANT_GAIN_CHAIN_NUM 2 +struct rtw89_ant_gain_info { + s8 offset[RTW89_ANT_GAIN_CHAIN_NUM][RTW89_ANT_GAIN_SUBBAND_NR]; + u32 regd_enabled; +}; + +struct rtw89_6ghz_span { + enum rtw89_sar_subband sar_subband_low; + enum rtw89_sar_subband sar_subband_high; + enum rtw89_ant_gain_subband ant_gain_subband_low; + enum rtw89_ant_gain_subband ant_gain_subband_high; +}; + +#define RTW89_SAR_SPAN_VALID(span) ((span)->sar_subband_high) +#define RTW89_ANT_GAIN_SPAN_VALID(span) ((span)->ant_gain_subband_high) + enum rtw89_tas_state { RTW89_TAS_STATE_DPR_OFF, RTW89_TAS_STATE_DPR_ON, @@ -4672,7 +4738,7 @@ enum rtw89_dm_type { }; #define RTW89_THERMAL_PROT_LV_MAX 5 -#define RTW89_THERMAL_PROT_STEP 19 /* -19% for each level */ +#define RTW89_THERMAL_PROT_STEP 5 /* -5% for each level */ struct rtw89_hal { u32 rx_fltr; @@ -4687,6 +4753,8 @@ struct rtw89_hal { bool ant_diversity_fixed; bool support_cckpd; bool support_igi; + bool no_mcs_12_13; + atomic_t roc_chanctx_idx; DECLARE_BITMAP(changes, NUM_OF_RTW89_CHANCTX_CHANGES); @@ -4781,6 +4849,7 @@ struct rtw89_pkt_drop_params { struct rtw89_pkt_stat { u16 beacon_nr; + u8 beacon_rate; u32 rx_rate_cnt[RTW89_HW_RATE_NR]; }; @@ -5544,6 +5613,7 @@ struct rtw89_dev { enum rtw89_mlo_dbcc_mode mlo_dbcc_mode; struct rtw89_hw_scan_info scan_info; const struct rtw89_chip_info *chip; + const struct rtw89_chip_variant *variant; const struct rtw89_pci_info *pci_info; const struct rtw89_rfe_parms *rfe_parms; struct rtw89_hal hal; @@ -5556,6 +5626,9 @@ struct rtw89_dev { struct rtw89_rfe_data *rfe_data; enum rtw89_custid custid; + struct rtw89_sta_link __rcu *assoc_link_on_macid[RTW89_MAX_MAC_ID_NUM]; + refcount_t refcount_ap_info; + /* ensures exclusive access from mac80211 callbacks */ struct mutex mutex; struct list_head rtwvifs_list; @@ -5636,6 +5709,7 @@ struct rtw89_dev { struct rtw89_regulatory_info regulatory; struct rtw89_sar_info sar; struct rtw89_tas_info tas; + struct rtw89_ant_gain_info ant_gain; struct rtw89_btc btc; enum rtw89_ps_mode ps_mode; @@ -5654,10 +5728,17 @@ struct rtw89_dev { u8 priv[] __aligned(sizeof(void *)); }; +struct rtw89_link_conf_container { + struct ieee80211_bss_conf *link_conf[IEEE80211_MLD_MAX_NUM_LINKS]; +}; + +#define RTW89_VIF_IDLE_LINK_ID 0 + struct rtw89_vif { struct rtw89_dev *rtwdev; struct list_head list; struct list_head mgnt_entry; + struct rtw89_link_conf_container __rcu *snap_link_confs; u8 mac_addr[ETH_ALEN]; __be32 ip_addr; @@ -5689,10 +5770,18 @@ static inline bool rtw89_vif_assign_link_is_valid(struct rtw89_vif_link **rtwvif for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) \ if (rtw89_vif_assign_link_is_valid(&(rtwvif_link), rtwvif, link_id)) +enum rtw89_sta_flags { + RTW89_REMOTE_STA_IN_PS, + + NUM_OF_RTW89_STA_FLAGS, +}; + struct rtw89_sta { struct rtw89_dev *rtwdev; struct rtw89_vif *rtwvif; + DECLARE_BITMAP(flags, NUM_OF_RTW89_STA_FLAGS); + bool disassoc; struct sk_buff_head roc_queue; @@ -5700,6 +5789,8 @@ struct rtw89_sta { struct rtw89_ampdu_params ampdu_params[IEEE80211_NUM_TIDS]; DECLARE_BITMAP(ampdu_map, IEEE80211_NUM_TIDS); + DECLARE_BITMAP(pairwise_sec_cam_map, RTW89_MAX_SEC_CAM_NUM); + u8 links_inst_valid_num; DECLARE_BITMAP(links_inst_map, __RTW89_MLD_MAX_LINK_NUM); struct rtw89_sta_link *links[IEEE80211_MLD_MAX_NUM_LINKS]; @@ -5770,6 +5861,31 @@ u8 rtw89_sta_link_inst_get_index(struct rtw89_sta_link *rtwsta_link) return rtwsta_link - rtwsta->links_inst; } +static inline void rtw89_assoc_link_set(struct rtw89_sta_link *rtwsta_link) +{ + struct rtw89_sta *rtwsta = rtwsta_link->rtwsta; + struct rtw89_dev *rtwdev = rtwsta->rtwdev; + + rcu_assign_pointer(rtwdev->assoc_link_on_macid[rtwsta_link->mac_id], + rtwsta_link); +} + +static inline void rtw89_assoc_link_clr(struct rtw89_sta_link *rtwsta_link) +{ + struct rtw89_sta *rtwsta = rtwsta_link->rtwsta; + struct rtw89_dev *rtwdev = rtwsta->rtwdev; + + rcu_assign_pointer(rtwdev->assoc_link_on_macid[rtwsta_link->mac_id], + NULL); + synchronize_rcu(); +} + +static inline struct rtw89_sta_link * +rtw89_assoc_link_rcu_dereference(struct rtw89_dev *rtwdev, u8 macid) +{ + return rcu_dereference(rtwdev->assoc_link_on_macid[macid]); +} + static inline int rtw89_hci_tx_write(struct rtw89_dev *rtwdev, struct rtw89_core_tx_request *tx_req) { @@ -6194,9 +6310,19 @@ static inline struct ieee80211_bss_conf * __rtw89_vif_rcu_dereference_link(struct rtw89_vif_link *rtwvif_link, bool *nolink) { struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link); + struct rtw89_vif *rtwvif = rtwvif_link->rtwvif; + struct rtw89_link_conf_container *snap; struct ieee80211_bss_conf *bss_conf; + snap = rcu_dereference(rtwvif->snap_link_confs); + if (snap) { + bss_conf = snap->link_conf[rtwvif_link->link_id]; + goto out; + } + bss_conf = rcu_dereference(vif->link_conf[rtwvif_link->link_id]); + +out: if (unlikely(!bss_conf)) { *nolink = true; return &vif->bss_conf; @@ -6605,6 +6731,16 @@ static inline void rtw89_chip_convert_rpl_to_rssi(struct rtw89_dev *rtwdev, chip->ops->convert_rpl_to_rssi(rtwdev, phy_ppdu); } +static inline void rtw89_chip_phy_rpt_to_rssi(struct rtw89_dev *rtwdev, + struct rtw89_rx_desc_info *desc_info, + struct ieee80211_rx_status *rx_status) +{ + const struct rtw89_chip_info *chip = rtwdev->chip; + + if (chip->ops->phy_rpt_to_rssi) + chip->ops->phy_rpt_to_rssi(rtwdev, desc_info, rx_status); +} + static inline void rtw89_ctrl_nbtg_bt_tx(struct rtw89_dev *rtwdev, bool en, enum rtw89_phy_idx phy_idx) { @@ -6753,6 +6889,26 @@ bool rtw89_sta_has_beamformer_cap(struct ieee80211_link_sta *link_sta) return false; } +static inline +bool rtw89_sta_link_has_su_mu_4xhe08(struct ieee80211_link_sta *link_sta) +{ + if (link_sta->he_cap.he_cap_elem.phy_cap_info[7] & + IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI) + return true; + + return false; +} + +static inline +bool rtw89_sta_link_has_er_su_4xhe08(struct ieee80211_link_sta *link_sta) +{ + if (link_sta->he_cap.he_cap_elem.phy_cap_info[8] & + IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI) + return true; + + return false; +} + static inline struct rtw89_fw_suit *rtw89_fw_suit_get(struct rtw89_dev *rtwdev, enum rtw89_fw_type type) { @@ -6893,7 +7049,8 @@ int rtw89_core_register(struct rtw89_dev *rtwdev); void rtw89_core_unregister(struct rtw89_dev *rtwdev); struct rtw89_dev *rtw89_alloc_ieee80211_hw(struct device *device, u32 bus_data_size, - const struct rtw89_chip_info *chip); + const struct rtw89_chip_info *chip, + const struct rtw89_chip_variant *variant); void rtw89_free_ieee80211_hw(struct rtw89_dev *rtwdev); u8 rtw89_acquire_mac_id(struct rtw89_dev *rtwdev); void rtw89_release_mac_id(struct rtw89_dev *rtwdev, u8 mac_id); @@ -6908,6 +7065,8 @@ struct rtw89_sta_link *rtw89_sta_set_link(struct rtw89_sta *rtwsta, unsigned int link_id); void rtw89_sta_unset_link(struct rtw89_sta *rtwsta, unsigned int link_id); void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev); +const struct rtw89_6ghz_span * +rtw89_get_6ghz_span(struct rtw89_dev *rtwdev, u32 center_freq); void rtw89_get_default_chandef(struct cfg80211_chan_def *chandef); void rtw89_get_channel_params(const struct cfg80211_chan_def *chandef, struct rtw89_chan *chan); diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c index 6abd88fa80ba..09fa977a6e6d 100644 --- a/drivers/net/wireless/realtek/rtw89/debug.c +++ b/drivers/net/wireless/realtek/rtw89/debug.c @@ -9,6 +9,7 @@ #include "fw.h" #include "mac.h" #include "pci.h" +#include "phy.h" #include "ps.h" #include "reg.h" #include "sar.h" @@ -811,6 +812,9 @@ static void __print_regd(struct seq_file *m, struct rtw89_dev *rtwdev, case_REGD(MEXICO); case_REGD(UKRAINE); case_REGD(CN); + case_REGD(QATAR); + case_REGD(UK); + case_REGD(THAILAND); } } @@ -882,6 +886,9 @@ static int rtw89_debug_priv_txpwr_table_get(struct seq_file *m, void *v) seq_puts(m, "[TAS]\n"); rtw89_print_tas(m, rtwdev); + seq_puts(m, "[DAG]\n"); + rtw89_print_ant_gain(m, rtwdev, chan); + tbl = dbgfs_txpwr_tables[chip_gen]; if (!tbl) { ret = -EOPNOTSUPP; diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index 2191c037d72e..5d4ad23cc3bd 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -709,11 +709,13 @@ static const struct __fw_feat_cfg fw_feat_tbl[] = { __CFG_FW_FEAT(RTL8852B, ge, 0, 29, 26, 0, TX_WAKE), __CFG_FW_FEAT(RTL8852B, ge, 0, 29, 29, 0, CRASH_TRIGGER), __CFG_FW_FEAT(RTL8852B, ge, 0, 29, 29, 0, SCAN_OFFLOAD), + __CFG_FW_FEAT(RTL8852B, ge, 0, 29, 29, 7, BEACON_FILTER), __CFG_FW_FEAT(RTL8852B, lt, 0, 29, 30, 0, NO_WOW_CPU_IO_RX), __CFG_FW_FEAT(RTL8852BT, ge, 0, 29, 74, 0, NO_LPS_PG), __CFG_FW_FEAT(RTL8852BT, ge, 0, 29, 74, 0, TX_WAKE), __CFG_FW_FEAT(RTL8852BT, ge, 0, 29, 90, 0, CRASH_TRIGGER), __CFG_FW_FEAT(RTL8852BT, ge, 0, 29, 91, 0, SCAN_OFFLOAD), + __CFG_FW_FEAT(RTL8852BT, ge, 0, 29, 110, 0, BEACON_FILTER), __CFG_FW_FEAT(RTL8852C, le, 0, 27, 33, 0, NO_DEEP_PS), __CFG_FW_FEAT(RTL8852C, ge, 0, 27, 34, 0, TX_WAKE), __CFG_FW_FEAT(RTL8852C, ge, 0, 27, 36, 0, SCAN_OFFLOAD), @@ -727,7 +729,12 @@ static const struct __fw_feat_cfg fw_feat_tbl[] = { __CFG_FW_FEAT(RTL8922A, ge, 0, 35, 12, 0, BEACON_FILTER), __CFG_FW_FEAT(RTL8922A, ge, 0, 35, 22, 0, WOW_REASON_V1), __CFG_FW_FEAT(RTL8922A, lt, 0, 35, 31, 0, RFK_PRE_NOTIFY_V0), + __CFG_FW_FEAT(RTL8922A, lt, 0, 35, 31, 0, LPS_CH_INFO), __CFG_FW_FEAT(RTL8922A, lt, 0, 35, 42, 0, RFK_RXDCK_V0), + __CFG_FW_FEAT(RTL8922A, ge, 0, 35, 46, 0, NOTIFY_AP_INFO), + __CFG_FW_FEAT(RTL8922A, lt, 0, 35, 47, 0, CH_INFO_BE_V0), + __CFG_FW_FEAT(RTL8922A, lt, 0, 35, 49, 0, RFK_PRE_NOTIFY_V1), + __CFG_FW_FEAT(RTL8922A, lt, 0, 35, 51, 0, NO_PHYCAP_P1), }; static void rtw89_fw_iterate_feature_cfg(struct rtw89_fw_info *fw, @@ -799,6 +806,27 @@ out: return firmware; } +static int rtw89_fw_validate_ver_required(struct rtw89_dev *rtwdev) +{ + const struct rtw89_chip_variant *variant = rtwdev->variant; + const struct rtw89_fw_suit *fw_suit; + u32 suit_ver_code; + + if (!variant) + return 0; + + fw_suit = rtw89_fw_suit_get(rtwdev, RTW89_FW_NORMAL); + suit_ver_code = RTW89_FW_SUIT_VER_CODE(fw_suit); + + if (variant->fw_min_ver_code > suit_ver_code) { + rtw89_err(rtwdev, "minimum required firmware version is 0x%x\n", + variant->fw_min_ver_code); + return -ENOENT; + } + + return 0; +} + int rtw89_fw_recognize(struct rtw89_dev *rtwdev) { const struct rtw89_chip_info *chip = rtwdev->chip; @@ -815,6 +843,10 @@ int rtw89_fw_recognize(struct rtw89_dev *rtwdev) return ret; normal_done: + ret = rtw89_fw_validate_ver_required(rtwdev); + if (ret) + return ret; + /* It still works if wowlan firmware isn't existing. */ __rtw89_fw_recognize(rtwdev, RTW89_FW_WOWLAN, false); @@ -2414,6 +2446,7 @@ static int rtw89_fw_h2c_add_general_pkt(struct rtw89_dev *rtwdev, u8 *id) { struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link); + int link_id = ieee80211_vif_is_mld(vif) ? rtwvif_link->link_id : -1; struct rtw89_pktofld_info *info; struct sk_buff *skb; int ret; @@ -2430,10 +2463,10 @@ static int rtw89_fw_h2c_add_general_pkt(struct rtw89_dev *rtwdev, skb = ieee80211_proberesp_get(rtwdev->hw, vif); break; case RTW89_PKT_OFLD_TYPE_NULL_DATA: - skb = ieee80211_nullfunc_get(rtwdev->hw, vif, -1, false); + skb = ieee80211_nullfunc_get(rtwdev->hw, vif, link_id, false); break; case RTW89_PKT_OFLD_TYPE_QOS_NULL: - skb = ieee80211_nullfunc_get(rtwdev->hw, vif, -1, true); + skb = ieee80211_nullfunc_get(rtwdev->hw, vif, link_id, true); break; case RTW89_PKT_OFLD_TYPE_EAPOL_KEY: skb = rtw89_eapol_get(rtwdev, rtwvif_link); @@ -2589,14 +2622,17 @@ fail: return ret; } -int rtw89_fw_h2c_lps_ch_info(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link) +int rtw89_fw_h2c_lps_ch_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif) { - const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, - rtwvif_link->chanctx_idx); const struct rtw89_chip_info *chip = rtwdev->chip; + const struct rtw89_chan *chan; + struct rtw89_vif_link *rtwvif_link; struct rtw89_h2c_lps_ch_info *h2c; u32 len = sizeof(*h2c); + unsigned int link_id; struct sk_buff *skb; + bool no_chan = true; + u8 phy_idx; u32 done; int ret; @@ -2611,11 +2647,27 @@ int rtw89_fw_h2c_lps_ch_info(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rt skb_put(skb, len); h2c = (struct rtw89_h2c_lps_ch_info *)skb->data; - h2c->info[0].central_ch = chan->channel; - h2c->info[0].pri_ch = chan->primary_channel; - h2c->info[0].band = chan->band_type; - h2c->info[0].bw = chan->band_width; - h2c->mlo_dbcc_mode_lps = cpu_to_le32(MLO_2_PLUS_0_1RF); + rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id) { + phy_idx = rtwvif_link->phy_idx; + if (phy_idx >= ARRAY_SIZE(h2c->info)) + continue; + + chan = rtw89_chan_get(rtwdev, rtwvif_link->chanctx_idx); + no_chan = false; + + h2c->info[phy_idx].central_ch = chan->channel; + h2c->info[phy_idx].pri_ch = chan->primary_channel; + h2c->info[phy_idx].band = chan->band_type; + h2c->info[phy_idx].bw = chan->band_width; + } + + if (no_chan) { + rtw89_err(rtwdev, "no chan for h2c lps_ch_info\n"); + ret = -ENOENT; + goto fail; + } + + h2c->mlo_dbcc_mode_lps = cpu_to_le32(rtwdev->mlo_dbcc_mode); rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, H2C_CAT_OUTSRC, H2C_CL_OUTSRC_DM, @@ -2640,6 +2692,87 @@ fail: return ret; } +int rtw89_fw_h2c_lps_ml_cmn_info(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif) +{ + const struct rtw89_phy_bb_gain_info_be *gain = &rtwdev->bb_gain.be; + struct rtw89_pkt_stat *pkt_stat = &rtwdev->phystat.cur_pkt_stat; + const struct rtw89_chip_info *chip = rtwdev->chip; + struct rtw89_h2c_lps_ml_cmn_info *h2c; + struct rtw89_vif_link *rtwvif_link; + const struct rtw89_chan *chan; + u8 bw_idx = RTW89_BB_BW_20_40; + u32 len = sizeof(*h2c); + unsigned int link_id; + struct sk_buff *skb; + u8 gain_band; + u32 done; + u8 path; + int ret; + int i; + + if (chip->chip_gen != RTW89_CHIP_BE) + return 0; + + skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len); + if (!skb) { + rtw89_err(rtwdev, "failed to alloc skb for h2c lps_ml_cmn_info\n"); + return -ENOMEM; + } + skb_put(skb, len); + h2c = (struct rtw89_h2c_lps_ml_cmn_info *)skb->data; + + h2c->fmt_id = 0x1; + + h2c->mlo_dbcc_mode = cpu_to_le32(rtwdev->mlo_dbcc_mode); + + rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id) { + path = rtwvif_link->phy_idx == RTW89_PHY_1 ? RF_PATH_B : RF_PATH_A; + chan = rtw89_chan_get(rtwdev, rtwvif_link->chanctx_idx); + gain_band = rtw89_subband_to_gain_band_be(chan->subband_type); + + h2c->central_ch[rtwvif_link->phy_idx] = chan->channel; + h2c->pri_ch[rtwvif_link->phy_idx] = chan->primary_channel; + h2c->band[rtwvif_link->phy_idx] = chan->band_type; + h2c->bw[rtwvif_link->phy_idx] = chan->band_width; + if (pkt_stat->beacon_rate < RTW89_HW_RATE_OFDM6) + h2c->bcn_rate_type[rtwvif_link->phy_idx] = 0x1; + else + h2c->bcn_rate_type[rtwvif_link->phy_idx] = 0x2; + + /* Fill BW20 RX gain table for beacon mode */ + for (i = 0; i < TIA_GAIN_NUM; i++) { + h2c->tia_gain[rtwvif_link->phy_idx][i] = + cpu_to_le16(gain->tia_gain[gain_band][bw_idx][path][i]); + } + memcpy(h2c->lna_gain[rtwvif_link->phy_idx], + gain->lna_gain[gain_band][bw_idx][path], + LNA_GAIN_NUM); + } + + rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, + H2C_CAT_OUTSRC, H2C_CL_OUTSRC_DM, + H2C_FUNC_FW_LPS_ML_CMN_INFO, 0, 0, len); + + rtw89_phy_write32_mask(rtwdev, R_CHK_LPS_STAT, B_CHK_LPS_STAT, 0); + ret = rtw89_h2c_tx(rtwdev, skb, false); + if (ret) { + rtw89_err(rtwdev, "failed to send h2c\n"); + goto fail; + } + + ret = read_poll_timeout(rtw89_phy_read32_mask, done, done, 50, 5000, + true, rtwdev, R_CHK_LPS_STAT, B_CHK_LPS_STAT); + if (ret) + rtw89_warn(rtwdev, "h2c_lps_ml_cmn_info done polling timeout\n"); + + return 0; +fail: + dev_kfree_skb_any(skb); + + return ret; +} + #define H2C_P2P_ACT_LEN 20 int rtw89_fw_h2c_p2p_act(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link, @@ -4954,13 +5087,14 @@ int rtw89_fw_h2c_scan_list_offload_be(struct rtw89_dev *rtwdev, int ch_num, struct rtw89_wait_info *wait = &rtwdev->mac.fw_ofld_wait; struct rtw89_h2c_chinfo_elem_be *elem; struct rtw89_mac_chinfo_be *ch_info; - struct rtw89_h2c_chinfo *h2c; + struct rtw89_h2c_chinfo_be *h2c; struct sk_buff *skb; unsigned int cond; + u8 ver = U8_MAX; int skb_len; int ret; - static_assert(sizeof(*elem) == RTW89_MAC_CHINFO_SIZE); + static_assert(sizeof(*elem) == RTW89_MAC_CHINFO_SIZE_BE); skb_len = struct_size(h2c, elem, ch_num); skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, skb_len); @@ -4969,8 +5103,11 @@ int rtw89_fw_h2c_scan_list_offload_be(struct rtw89_dev *rtwdev, int ch_num, return -ENOMEM; } + if (RTW89_CHK_FW_FEATURE(CH_INFO_BE_V0, &rtwdev->fw)) + ver = 0; + skb_put(skb, sizeof(*h2c)); - h2c = (struct rtw89_h2c_chinfo *)skb->data; + h2c = (struct rtw89_h2c_chinfo_be *)skb->data; h2c->ch_num = ch_num; h2c->elem_size = sizeof(*elem) / 4; /* in unit of 4 bytes */ @@ -4980,8 +5117,7 @@ int rtw89_fw_h2c_scan_list_offload_be(struct rtw89_dev *rtwdev, int ch_num, list_for_each_entry(ch_info, chan_list, list) { elem = (struct rtw89_h2c_chinfo_elem_be *)skb_put(skb, sizeof(*elem)); - elem->w0 = le32_encode_bits(ch_info->period, RTW89_H2C_CHINFO_BE_W0_PERIOD) | - le32_encode_bits(ch_info->dwell_time, RTW89_H2C_CHINFO_BE_W0_DWELL) | + elem->w0 = le32_encode_bits(ch_info->dwell_time, RTW89_H2C_CHINFO_BE_W0_DWELL) | le32_encode_bits(ch_info->central_ch, RTW89_H2C_CHINFO_BE_W0_CENTER_CH) | le32_encode_bits(ch_info->pri_ch, RTW89_H2C_CHINFO_BE_W0_PRI_CH); @@ -5028,6 +5164,12 @@ int rtw89_fw_h2c_scan_list_offload_be(struct rtw89_dev *rtwdev, int ch_num, RTW89_H2C_CHINFO_BE_W6_FW_PROBE0_SHORTSSIDS) | le32_encode_bits(ch_info->fw_probe0_bssids, RTW89_H2C_CHINFO_BE_W6_FW_PROBE0_BSSIDS); + if (ver == 0) + elem->w0 |= + le32_encode_bits(ch_info->period, RTW89_H2C_CHINFO_BE_W0_PERIOD); + else + elem->w7 = le32_encode_bits(ch_info->period, + RTW89_H2C_CHINFO_BE_W7_PERIOD_V1); } rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, @@ -5171,6 +5313,7 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev, u8 probe_id[NUM_NL80211_BANDS]; u8 cfg_len = sizeof(*h2c); unsigned int cond; + u8 ver = U8_MAX; void *ptr; int ret; u32 len; @@ -5191,6 +5334,9 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev, memset(probe_id, RTW89_SCANOFLD_PKT_NONE, sizeof(probe_id)); + if (RTW89_CHK_FW_FEATURE(CH_INFO_BE_V0, &rtwdev->fw)) + ver = 0; + if (!wowlan) { list_for_each_entry(pkt_info, &scan_info->pkt_list[NL80211_BAND_6GHZ], list) { if (pkt_info->wildcard_6ghz) { @@ -5286,9 +5432,7 @@ flex_member: le32_encode_bits(RTW89_OFF_CHAN_TIME / 10, RTW89_H2C_SCANOFLD_BE_OPCH_W0_POLICY_VAL); - opch->w1 = le32_encode_bits(RTW89_CHANNEL_TIME, - RTW89_H2C_SCANOFLD_BE_OPCH_W1_DURATION) | - le32_encode_bits(op->band_type, + opch->w1 = le32_encode_bits(op->band_type, RTW89_H2C_SCANOFLD_BE_OPCH_W1_CH_BAND) | le32_encode_bits(op->band_width, RTW89_H2C_SCANOFLD_BE_OPCH_W1_BW) | @@ -5314,6 +5458,13 @@ flex_member: RTW89_H2C_SCANOFLD_BE_OPCH_W3_PKT2) | le32_encode_bits(RTW89_SCANOFLD_PKT_NONE, RTW89_H2C_SCANOFLD_BE_OPCH_W3_PKT3); + + if (ver == 0) + opch->w1 |= le32_encode_bits(RTW89_CHANNEL_TIME, + RTW89_H2C_SCANOFLD_BE_OPCH_W1_DURATION); + else + opch->w4 = le32_encode_bits(RTW89_CHANNEL_TIME, + RTW89_H2C_SCANOFLD_BE_OPCH_W4_DURATION_V1); ptr += sizeof(*opch); } @@ -5416,7 +5567,9 @@ int rtw89_fw_h2c_rf_pre_ntfy(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx) { struct rtw89_rfk_mcc_info *rfk_mcc = &rtwdev->rfk_mcc; + struct rtw89_fw_h2c_rfk_pre_info_common *common; struct rtw89_fw_h2c_rfk_pre_info_v0 *h2c_v0; + struct rtw89_fw_h2c_rfk_pre_info_v1 *h2c_v1; struct rtw89_fw_h2c_rfk_pre_info *h2c; u8 tbl_sel[NUM_OF_RTW89_FW_RFK_PATH]; u32 len = sizeof(*h2c); @@ -5426,7 +5579,10 @@ int rtw89_fw_h2c_rf_pre_ntfy(struct rtw89_dev *rtwdev, u32 val32; int ret; - if (RTW89_CHK_FW_FEATURE(RFK_PRE_NOTIFY_V0, &rtwdev->fw)) { + if (RTW89_CHK_FW_FEATURE(RFK_PRE_NOTIFY_V1, &rtwdev->fw)) { + len = sizeof(*h2c_v1); + ver = 1; + } else if (RTW89_CHK_FW_FEATURE(RFK_PRE_NOTIFY_V0, &rtwdev->fw)) { len = sizeof(*h2c_v0); ver = 0; } @@ -5438,17 +5594,18 @@ int rtw89_fw_h2c_rf_pre_ntfy(struct rtw89_dev *rtwdev, } skb_put(skb, len); h2c = (struct rtw89_fw_h2c_rfk_pre_info *)skb->data; + common = &h2c->base_v1.common; - h2c->common.mlo_mode = cpu_to_le32(rtwdev->mlo_dbcc_mode); + common->mlo_mode = cpu_to_le32(rtwdev->mlo_dbcc_mode); BUILD_BUG_ON(NUM_OF_RTW89_FW_RFK_TBL > RTW89_RFK_CHS_NR); BUILD_BUG_ON(ARRAY_SIZE(rfk_mcc->data) < NUM_OF_RTW89_FW_RFK_PATH); for (tbl = 0; tbl < NUM_OF_RTW89_FW_RFK_TBL; tbl++) { for (path = 0; path < NUM_OF_RTW89_FW_RFK_PATH; path++) { - h2c->common.dbcc.ch[path][tbl] = + common->dbcc.ch[path][tbl] = cpu_to_le32(rfk_mcc->data[path].ch[tbl]); - h2c->common.dbcc.band[path][tbl] = + common->dbcc.band[path][tbl] = cpu_to_le32(rfk_mcc->data[path].band[tbl]); } } @@ -5456,13 +5613,19 @@ int rtw89_fw_h2c_rf_pre_ntfy(struct rtw89_dev *rtwdev, for (path = 0; path < NUM_OF_RTW89_FW_RFK_PATH; path++) { tbl_sel[path] = rfk_mcc->data[path].table_idx; - h2c->common.tbl.cur_ch[path] = + common->tbl.cur_ch[path] = cpu_to_le32(rfk_mcc->data[path].ch[tbl_sel[path]]); - h2c->common.tbl.cur_band[path] = + common->tbl.cur_band[path] = cpu_to_le32(rfk_mcc->data[path].band[tbl_sel[path]]); + + if (ver <= 1) + continue; + + h2c->cur_bandwidth[path] = + cpu_to_le32(rfk_mcc->data[path].bw[tbl_sel[path]]); } - h2c->common.phy_idx = cpu_to_le32(phy_idx); + common->phy_idx = cpu_to_le32(phy_idx); if (ver == 0) { /* RFK_PRE_NOTIFY_V0 */ h2c_v0 = (struct rtw89_fw_h2c_rfk_pre_info_v0 *)skb->data; @@ -5488,8 +5651,10 @@ int rtw89_fw_h2c_rf_pre_ntfy(struct rtw89_dev *rtwdev, goto done; } - if (rtw89_is_mlo_1_1(rtwdev)) - h2c->mlo_1_1 = cpu_to_le32(1); + if (rtw89_is_mlo_1_1(rtwdev)) { + h2c_v1 = &h2c->base_v1; + h2c_v1->mlo_1_1 = cpu_to_le32(1); + } done: rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, H2C_CAT_OUTSRC, H2C_CL_OUTSRC_RF_FW_RFK, @@ -6496,7 +6661,7 @@ int rtw89_pno_scan_add_chan_list_ax(struct rtw89_dev *rtwdev, INIT_LIST_HEAD(&chan_list); for (idx = 0, list_len = 0; - idx < nd_config->n_channels && list_len < RTW89_SCAN_LIST_LIMIT; + idx < nd_config->n_channels && list_len < RTW89_SCAN_LIST_LIMIT_AX; idx++, list_len++) { channel = nd_config->channels[idx]; ch_info = kzalloc(sizeof(*ch_info), GFP_KERNEL); @@ -6547,7 +6712,7 @@ int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev, INIT_LIST_HEAD(&chan_list); for (idx = rtwdev->scan_info.last_chan_idx, list_len = 0; - idx < req->n_channels && list_len < RTW89_SCAN_LIST_LIMIT; + idx < req->n_channels && list_len < RTW89_SCAN_LIST_LIMIT_AX; idx++, list_len++) { channel = req->channels[idx]; ch_info = kzalloc(sizeof(*ch_info), GFP_KERNEL); @@ -6624,7 +6789,7 @@ int rtw89_pno_scan_add_chan_list_be(struct rtw89_dev *rtwdev, INIT_LIST_HEAD(&chan_list); for (idx = 0, list_len = 0; - idx < nd_config->n_channels && list_len < RTW89_SCAN_LIST_LIMIT; + idx < nd_config->n_channels && list_len < RTW89_SCAN_LIST_LIMIT_BE; idx++, list_len++) { channel = nd_config->channels[idx]; ch_info = kzalloc(sizeof(*ch_info), GFP_KERNEL); @@ -6679,7 +6844,7 @@ int rtw89_hw_scan_add_chan_list_be(struct rtw89_dev *rtwdev, INIT_LIST_HEAD(&chan_list); for (idx = rtwdev->scan_info.last_chan_idx, list_len = 0; - idx < req->n_channels && list_len < RTW89_SCAN_LIST_LIMIT; + idx < req->n_channels && list_len < RTW89_SCAN_LIST_LIMIT_BE; idx++, list_len++) { channel = req->channels[idx]; ch_info = kzalloc(sizeof(*ch_info), GFP_KERNEL); @@ -6780,22 +6945,25 @@ void rtw89_hw_scan_start(struct rtw89_dev *rtwdev, rtw89_chanctx_pause(rtwdev, RTW89_CHANCTX_PAUSE_REASON_HW_SCAN); } -void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, - struct rtw89_vif_link *rtwvif_link, - bool aborted) +struct rtw89_hw_scan_complete_cb_data { + struct rtw89_vif_link *rtwvif_link; + bool aborted; +}; + +static int rtw89_hw_scan_complete_cb(struct rtw89_dev *rtwdev, void *data) { const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def; struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info; + struct rtw89_hw_scan_complete_cb_data *cb_data = data; + struct rtw89_vif_link *rtwvif_link = cb_data->rtwvif_link; struct cfg80211_scan_info info = { - .aborted = aborted, + .aborted = cb_data->aborted, }; struct rtw89_vif *rtwvif; u32 reg; if (!rtwvif_link) - return; - - rtw89_chanctx_proceed(rtwdev); + return -EINVAL; rtwvif = rtwvif_link->rtwvif; @@ -6814,6 +6982,29 @@ void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, scan_info->last_chan_idx = 0; scan_info->scanning_vif = NULL; scan_info->abort = false; + + return 0; +} + +void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, + struct rtw89_vif_link *rtwvif_link, + bool aborted) +{ + struct rtw89_hw_scan_complete_cb_data cb_data = { + .rtwvif_link = rtwvif_link, + .aborted = aborted, + }; + const struct rtw89_chanctx_cb_parm cb_parm = { + .cb = rtw89_hw_scan_complete_cb, + .data = &cb_data, + .caller = __func__, + }; + + /* The things here needs to be done after setting channel (for coex) + * and before proceeding entity mode (for MCC). So, pass a callback + * of them for the right sequence rather than doing them directly. + */ + rtw89_chanctx_proceed(rtwdev, &cb_parm); } void rtw89_hw_scan_abort(struct rtw89_dev *rtwdev, @@ -8164,6 +8355,71 @@ int rtw89_fw_h2c_mrc_upd_duration(struct rtw89_dev *rtwdev, return 0; } +static int rtw89_fw_h2c_ap_info(struct rtw89_dev *rtwdev, bool en) +{ + struct rtw89_h2c_ap_info *h2c; + u32 len = sizeof(*h2c); + struct sk_buff *skb; + int ret; + + skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len); + if (!skb) { + rtw89_err(rtwdev, "failed to alloc skb for ap info\n"); + return -ENOMEM; + } + + skb_put(skb, len); + h2c = (struct rtw89_h2c_ap_info *)skb->data; + + h2c->w0 = le32_encode_bits(en, RTW89_H2C_AP_INFO_W0_PWR_INT_EN); + + rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, + H2C_CAT_MAC, + H2C_CL_AP, + H2C_FUNC_AP_INFO, 0, 0, + len); + + ret = rtw89_h2c_tx(rtwdev, skb, false); + if (ret) { + rtw89_err(rtwdev, "failed to send h2c\n"); + dev_kfree_skb_any(skb); + return -EBUSY; + } + + return 0; +} + +int rtw89_fw_h2c_ap_info_refcount(struct rtw89_dev *rtwdev, bool en) +{ + int ret; + + if (en) { + if (refcount_inc_not_zero(&rtwdev->refcount_ap_info)) + return 0; + } else { + if (!refcount_dec_and_test(&rtwdev->refcount_ap_info)) + return 0; + } + + ret = rtw89_fw_h2c_ap_info(rtwdev, en); + if (ret) { + if (!test_bit(RTW89_FLAG_SER_HANDLING, rtwdev->flags)) + return ret; + + /* During recovery, neither driver nor stack has full error + * handling, so show a warning, but return 0 with refcount + * increased normally. It can avoid underflow when calling + * with @en == false later. + */ + rtw89_warn(rtwdev, "h2c ap_info failed during SER\n"); + } + + if (en) + refcount_set(&rtwdev->refcount_ap_info, 1); + + return 0; +} + static bool __fw_txpwr_entry_zero_ext(const void *ext_ptr, u8 ext_len) { static const u8 zeros[U8_MAX] = {}; diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h index efa63d444821..2026bc2fd2ac 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.h +++ b/drivers/net/wireless/realtek/rtw89/fw.h @@ -47,6 +47,19 @@ struct rtw89_c2hreg_phycap { #define RTW89_C2HREG_PHYCAP_W2_HW_TYPE GENMASK(7, 0) #define RTW89_C2HREG_PHYCAP_W3_ANT_TX_NUM GENMASK(15, 8) #define RTW89_C2HREG_PHYCAP_W3_ANT_RX_NUM GENMASK(23, 16) +#define RTW89_C2HREG_PHYCAP_W3_BAND_SEL GENMASK(31, 24) + +#define RTW89_C2HREG_PHYCAP_P1_W0_B1_RX_NSS GENMASK(23, 16) +#define RTW89_C2HREG_PHYCAP_P1_W0_B1_BW GENMASK(31, 24) +#define RTW89_C2HREG_PHYCAP_P1_W1_B1_TX_NSS GENMASK(7, 0) +#define RTW89_C2HREG_PHYCAP_P1_W1_B1_ANT_TX_NUM GENMASK(15, 8) +#define RTW89_C2HREG_PHYCAP_P1_W1_B1_ANT_RX_NUM GENMASK(23, 16) +#define RTW89_C2HREG_PHYCAP_P1_W1_B1_BAND_SEL GENMASK(31, 24) +#define RTW89_C2HREG_PHYCAP_P1_W2_QAM GENMASK(7, 0) +#define RTW89_C2HREG_PHYCAP_P1_W2_QAM_256 0x1 +#define RTW89_C2HREG_PHYCAP_P1_W2_QAM_1024 0x2 +#define RTW89_C2HREG_PHYCAP_P1_W2_QAM_4096 0x3 +#define RTW89_C2HREG_PHYCAP_P1_W2_B1_QAM GENMASK(15, 8) #define RTW89_C2HREG_AOAC_RPT_1_W0_KEY_IDX GENMASK(23, 16) #define RTW89_C2HREG_AOAC_RPT_1_W1_IV_0 GENMASK(7, 0) @@ -92,6 +105,8 @@ struct rtw89_h2creg_sch_tx_en { #define RTW89_H2CREG_WOW_CPUIO_RX_CTRL_EN GENMASK(23, 16) +#define RTW89_H2CREG_GET_FEATURE_PART_NUM GENMASK(23, 16) + #define RTW89_H2CREG_MAX 4 #define RTW89_C2HREG_MAX 4 #define RTW89_C2HREG_HDR_LEN 2 @@ -138,6 +153,7 @@ enum rtw89_mac_c2h_type { RTW89_FWCMD_C2HREG_FUNC_PHY_CAP, RTW89_FWCMD_C2HREG_FUNC_TX_PAUSE_RPT, RTW89_FWCMD_C2HREG_FUNC_WOW_CPUIO_RX_ACK = 0xA, + RTW89_FWCMD_C2HREG_FUNC_PHY_CAP_PART1 = 0xC, RTW89_FWCMD_C2HREG_FUNC_NULL = 0xFF, }; @@ -310,9 +326,12 @@ struct rtw89_fw_macid_pause_sleep_grp { #define RTW89_SCANOFLD_DEBUG_MASK 0x1F #define RTW89_CHAN_INVALID 0xFF #define RTW89_MAC_CHINFO_SIZE 28 +#define RTW89_MAC_CHINFO_SIZE_BE 32 #define RTW89_SCAN_LIST_GUARD 4 -#define RTW89_SCAN_LIST_LIMIT \ - ((RTW89_H2C_MAX_SIZE / RTW89_MAC_CHINFO_SIZE) - RTW89_SCAN_LIST_GUARD) +#define RTW89_SCAN_LIST_LIMIT(size) \ + ((RTW89_H2C_MAX_SIZE / (size)) - RTW89_SCAN_LIST_GUARD) +#define RTW89_SCAN_LIST_LIMIT_AX RTW89_SCAN_LIST_LIMIT(RTW89_MAC_CHINFO_SIZE) +#define RTW89_SCAN_LIST_LIMIT_BE RTW89_SCAN_LIST_LIMIT(RTW89_MAC_CHINFO_SIZE_BE) #define RTW89_BCN_LOSS_CNT 10 @@ -1780,6 +1799,21 @@ struct rtw89_h2c_lps_ch_info { __le32 mlo_dbcc_mode_lps; } __packed; +struct rtw89_h2c_lps_ml_cmn_info { + u8 fmt_id; + u8 rsvd0[3]; + __le32 mlo_dbcc_mode; + u8 central_ch[RTW89_PHY_MAX]; + u8 pri_ch[RTW89_PHY_MAX]; + u8 bw[RTW89_PHY_MAX]; + u8 band[RTW89_PHY_MAX]; + u8 bcn_rate_type[RTW89_PHY_MAX]; + u8 rsvd1[2]; + __le16 tia_gain[RTW89_PHY_MAX][TIA_GAIN_NUM]; + u8 lna_gain[RTW89_PHY_MAX][LNA_GAIN_NUM]; + u8 rsvd2[2]; +} __packed; + static inline void RTW89_SET_FWCMD_CPU_EXCEPTION_TYPE(void *cmd, u32 val) { le32p_replace_bits((__le32 *)cmd, val, GENMASK(31, 0)); @@ -2647,6 +2681,7 @@ struct rtw89_h2c_chinfo_elem_be { __le32 w4; __le32 w5; __le32 w6; + __le32 w7; } __packed; #define RTW89_H2C_CHINFO_BE_W0_PERIOD GENMASK(7, 0) @@ -2678,6 +2713,7 @@ struct rtw89_h2c_chinfo_elem_be { #define RTW89_H2C_CHINFO_BE_W5_FW_PROBE0_SSIDS GENMASK(31, 16) #define RTW89_H2C_CHINFO_BE_W6_FW_PROBE0_SHORTSSIDS GENMASK(15, 0) #define RTW89_H2C_CHINFO_BE_W6_FW_PROBE0_BSSIDS GENMASK(31, 16) +#define RTW89_H2C_CHINFO_BE_W7_PERIOD_V1 GENMASK(15, 0) struct rtw89_h2c_chinfo { u8 ch_num; @@ -2687,6 +2723,14 @@ struct rtw89_h2c_chinfo { struct rtw89_h2c_chinfo_elem elem[] __counted_by(ch_num); } __packed; +struct rtw89_h2c_chinfo_be { + u8 ch_num; + u8 elem_size; + u8 arg; + u8 rsvd0; + struct rtw89_h2c_chinfo_elem_be elem[] __counted_by(ch_num); +} __packed; + #define RTW89_H2C_CHINFO_ARG_MAC_IDX_MASK BIT(0) #define RTW89_H2C_CHINFO_ARG_APPEND_MASK BIT(1) @@ -2733,6 +2777,7 @@ struct rtw89_h2c_scanofld_be_opch { __le32 w1; __le32 w2; __le32 w3; + __le32 w4; } __packed; #define RTW89_H2C_SCANOFLD_BE_OPCH_W0_MACID GENMASK(15, 0) @@ -2754,6 +2799,7 @@ struct rtw89_h2c_scanofld_be_opch { #define RTW89_H2C_SCANOFLD_BE_OPCH_W3_PKT1 GENMASK(15, 8) #define RTW89_H2C_SCANOFLD_BE_OPCH_W3_PKT2 GENMASK(23, 16) #define RTW89_H2C_SCANOFLD_BE_OPCH_W3_PKT3 GENMASK(31, 24) +#define RTW89_H2C_SCANOFLD_BE_OPCH_W4_DURATION_V1 GENMASK(15, 0) struct rtw89_h2c_scanofld_be { __le32 w0; @@ -3466,6 +3512,12 @@ struct rtw89_h2c_wow_aoac { __le32 w0; } __packed; +struct rtw89_h2c_ap_info { + __le32 w0; +} __packed; + +#define RTW89_H2C_AP_INFO_W0_PWR_INT_EN BIT(0) + #define RTW89_C2H_HEADER_LEN 8 struct rtw89_c2h_hdr { @@ -3590,6 +3642,7 @@ struct rtw89_c2h_scanofld { __le32 w5; __le32 w6; __le32 w7; + __le32 w8; } __packed; #define RTW89_C2H_SCANOFLD_W2_PRI_CH GENMASK(7, 0) @@ -3604,6 +3657,8 @@ struct rtw89_c2h_scanofld { #define RTW89_C2H_SCANOFLD_W6_EXPECT_PERIOD GENMASK(15, 8) #define RTW89_C2H_SCANOFLD_W6_FW_DEF GENMASK(23, 16) #define RTW89_C2H_SCANOFLD_W7_REPORT_TSF GENMASK(31, 0) +#define RTW89_C2H_SCANOFLD_W8_PERIOD_V1 GENMASK(15, 0) +#define RTW89_C2H_SCANOFLD_W8_EXPECT_PERIOD_V1 GENMASK(31, 16) #define RTW89_GET_MAC_C2H_MCC_RCV_ACK_GROUP(c2h) \ le32_get_bits(*((const __le32 *)(c2h) + 2), GENMASK(1, 0)) @@ -3725,6 +3780,14 @@ struct rtw89_c2h_wow_aoac_report { #define RTW89_C2H_WOW_AOAC_RPT_REKEY_IDX BIT(0) +struct rtw89_c2h_pwr_int_notify { + struct rtw89_c2h_hdr hdr; + __le32 w2; +} __packed; + +#define RTW89_C2H_PWR_INT_NOTIFY_W2_MACID GENMASK(15, 0) +#define RTW89_C2H_PWR_INT_NOTIFY_W2_PWR_STATUS BIT(16) + struct rtw89_h2c_tx_duty { __le32 w0; __le32 w1; @@ -4168,6 +4231,10 @@ enum rtw89_mrc_h2c_func { #define RTW89_MRC_WAIT_COND_REQ_TSF \ RTW89_MRC_WAIT_COND(0 /* don't care */, H2C_FUNC_MRC_REQ_TSF) +/* CLASS 36 - AP */ +#define H2C_CL_AP 0x24 +#define H2C_FUNC_AP_INFO 0x0 + #define H2C_CAT_OUTSRC 0x2 #define H2C_CL_OUTSRC_RA 0x1 @@ -4175,6 +4242,7 @@ enum rtw89_mrc_h2c_func { #define H2C_CL_OUTSRC_DM 0x2 #define H2C_FUNC_FW_LPS_CH_INFO 0xb +#define H2C_FUNC_FW_LPS_ML_CMN_INFO 0xe #define H2C_CL_OUTSRC_RF_REG_A 0x8 #define H2C_CL_OUTSRC_RF_REG_B 0x9 @@ -4241,11 +4309,16 @@ struct rtw89_fw_h2c_rfk_pre_info_v0 { } __packed mlo; } __packed; -struct rtw89_fw_h2c_rfk_pre_info { +struct rtw89_fw_h2c_rfk_pre_info_v1 { struct rtw89_fw_h2c_rfk_pre_info_common common; __le32 mlo_1_1; } __packed; +struct rtw89_fw_h2c_rfk_pre_info { + struct rtw89_fw_h2c_rfk_pre_info_v1 base_v1; + __le32 cur_bandwidth[NUM_OF_RTW89_FW_RFK_PATH]; +} __packed; + struct rtw89_h2c_rf_tssi { __le16 len; u8 phy; @@ -4602,8 +4675,9 @@ int rtw89_fw_h2c_init_ba_cam_users(struct rtw89_dev *rtwdev, u8 users, int rtw89_fw_h2c_lps_parm(struct rtw89_dev *rtwdev, struct rtw89_lps_parm *lps_param); -int rtw89_fw_h2c_lps_ch_info(struct rtw89_dev *rtwdev, - struct rtw89_vif_link *rtwvif_link); +int rtw89_fw_h2c_lps_ch_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif); +int rtw89_fw_h2c_lps_ml_cmn_info(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif); int rtw89_fw_h2c_fwips(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link, bool enable); struct sk_buff *rtw89_fw_h2c_alloc_skb_with_hdr(struct rtw89_dev *rtwdev, u32 len); @@ -4697,6 +4771,7 @@ int rtw89_fw_h2c_mrc_sync(struct rtw89_dev *rtwdev, const struct rtw89_fw_mrc_sync_arg *arg); int rtw89_fw_h2c_mrc_upd_duration(struct rtw89_dev *rtwdev, const struct rtw89_fw_mrc_upd_duration_arg *arg); +int rtw89_fw_h2c_ap_info_refcount(struct rtw89_dev *rtwdev, bool en); static inline void rtw89_fw_h2c_init_ba_cam(struct rtw89_dev *rtwdev) { diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index 7907b84d204b..a37c6d525d6f 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -2898,22 +2898,42 @@ static int cmac_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx) } static int rtw89_mac_read_phycap(struct rtw89_dev *rtwdev, - struct rtw89_mac_c2h_info *c2h_info) + struct rtw89_mac_c2h_info *c2h_info, u8 part_num) { const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def; - struct rtw89_mac_h2c_info h2c_info = {0}; + const struct rtw89_chip_info *chip = rtwdev->chip; + struct rtw89_mac_h2c_info h2c_info = {}; + enum rtw89_mac_c2h_type c2h_type; + u8 content_len; u32 ret; + if (chip->chip_gen == RTW89_CHIP_AX) + content_len = 0; + else + content_len = 2; + + switch (part_num) { + case 0: + c2h_type = RTW89_FWCMD_C2HREG_FUNC_PHY_CAP; + break; + case 1: + c2h_type = RTW89_FWCMD_C2HREG_FUNC_PHY_CAP_PART1; + break; + default: + return -EINVAL; + } + mac->cnv_efuse_state(rtwdev, false); h2c_info.id = RTW89_FWCMD_H2CREG_FUNC_GET_FEATURE; - h2c_info.content_len = 0; + h2c_info.content_len = content_len; + h2c_info.u.hdr.w0 = u32_encode_bits(part_num, RTW89_H2CREG_GET_FEATURE_PART_NUM); ret = rtw89_fw_msg_reg(rtwdev, &h2c_info, c2h_info); if (ret) goto out; - if (c2h_info->id != RTW89_FWCMD_C2HREG_FUNC_PHY_CAP) + if (c2h_info->id != c2h_type) ret = -EINVAL; out: @@ -2922,20 +2942,20 @@ out: return ret; } -int rtw89_mac_setup_phycap(struct rtw89_dev *rtwdev) +static int rtw89_mac_setup_phycap_part0(struct rtw89_dev *rtwdev) { - struct rtw89_efuse *efuse = &rtwdev->efuse; - struct rtw89_hal *hal = &rtwdev->hal; const struct rtw89_chip_info *chip = rtwdev->chip; - struct rtw89_mac_c2h_info c2h_info = {0}; const struct rtw89_c2hreg_phycap *phycap; + struct rtw89_efuse *efuse = &rtwdev->efuse; + struct rtw89_mac_c2h_info c2h_info = {}; + struct rtw89_hal *hal = &rtwdev->hal; u8 tx_nss; u8 rx_nss; u8 tx_ant; u8 rx_ant; - u32 ret; + int ret; - ret = rtw89_mac_read_phycap(rtwdev, &c2h_info); + ret = rtw89_mac_read_phycap(rtwdev, &c2h_info, 0); if (ret) return ret; @@ -2979,6 +2999,60 @@ int rtw89_mac_setup_phycap(struct rtw89_dev *rtwdev) return 0; } +static int rtw89_mac_setup_phycap_part1(struct rtw89_dev *rtwdev) +{ + const struct rtw89_chip_variant *variant = rtwdev->variant; + const struct rtw89_c2hreg_phycap *phycap; + struct rtw89_mac_c2h_info c2h_info = {}; + struct rtw89_hal *hal = &rtwdev->hal; + u8 qam_raw, qam; + int ret; + + ret = rtw89_mac_read_phycap(rtwdev, &c2h_info, 1); + if (ret) + return ret; + + phycap = &c2h_info.u.phycap; + + qam_raw = u32_get_bits(phycap->w2, RTW89_C2HREG_PHYCAP_P1_W2_QAM); + + switch (qam_raw) { + case RTW89_C2HREG_PHYCAP_P1_W2_QAM_256: + case RTW89_C2HREG_PHYCAP_P1_W2_QAM_1024: + case RTW89_C2HREG_PHYCAP_P1_W2_QAM_4096: + qam = qam_raw; + break; + default: + qam = RTW89_C2HREG_PHYCAP_P1_W2_QAM_4096; + break; + } + + if ((variant && variant->no_mcs_12_13) || + qam <= RTW89_C2HREG_PHYCAP_P1_W2_QAM_1024) + hal->no_mcs_12_13 = true; + + rtw89_debug(rtwdev, RTW89_DBG_FW, "phycap qam=%d/%d no_mcs_12_13=%d\n", + qam_raw, qam, hal->no_mcs_12_13); + + return 0; +} + +int rtw89_mac_setup_phycap(struct rtw89_dev *rtwdev) +{ + const struct rtw89_chip_info *chip = rtwdev->chip; + int ret; + + ret = rtw89_mac_setup_phycap_part0(rtwdev); + if (ret) + return ret; + + if (chip->chip_gen == RTW89_CHIP_AX || + RTW89_CHK_FW_FEATURE(NO_PHYCAP_P1, &rtwdev->fw)) + return 0; + + return rtw89_mac_setup_phycap_part1(rtwdev); +} + static int rtw89_hw_sch_tx_en_h2c(struct rtw89_dev *rtwdev, u8 band, u16 tx_en_u16, u16 mask_u16) { @@ -4788,9 +4862,11 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb, struct rtw89_vif_link *rtwvif_link = rtwdev->scan_info.scanning_vif; struct rtw89_vif *rtwvif; struct rtw89_chan new; - u8 reason, status, tx_fail, band, actual_period, expect_period; u32 last_chan = rtwdev->scan_info.last_chan_idx, report_tsf; + u16 actual_period, expect_period; + u8 reason, status, tx_fail, band; u8 mac_idx, sw_def, fw_def; + u8 ver = U8_MAX; u16 chan; int ret; @@ -4799,6 +4875,9 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb, rtwvif = rtwvif_link->rtwvif; + if (RTW89_CHK_FW_FEATURE(CH_INFO_BE_V0, &rtwdev->fw)) + ver = 0; + tx_fail = le32_get_bits(c2h->w5, RTW89_C2H_SCANOFLD_W5_TX_FAIL); status = le32_get_bits(c2h->w2, RTW89_C2H_SCANOFLD_W2_STATUS); chan = le32_get_bits(c2h->w2, RTW89_C2H_SCANOFLD_W2_PRI_CH); @@ -4811,21 +4890,28 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb, if (!(rtwdev->chip->support_bands & BIT(NL80211_BAND_6GHZ))) band = chan > 14 ? RTW89_BAND_5G : RTW89_BAND_2G; - rtw89_debug(rtwdev, RTW89_DBG_HW_SCAN, - "mac_idx[%d] band: %d, chan: %d, reason: %d, status: %d, tx_fail: %d, actual: %d\n", - mac_idx, band, chan, reason, status, tx_fail, actual_period); - if (rtwdev->chip->chip_gen == RTW89_CHIP_BE) { sw_def = le32_get_bits(c2h->w6, RTW89_C2H_SCANOFLD_W6_SW_DEF); - expect_period = le32_get_bits(c2h->w6, RTW89_C2H_SCANOFLD_W6_EXPECT_PERIOD); fw_def = le32_get_bits(c2h->w6, RTW89_C2H_SCANOFLD_W6_FW_DEF); report_tsf = le32_get_bits(c2h->w7, RTW89_C2H_SCANOFLD_W7_REPORT_TSF); + if (ver == 0) { + expect_period = + le32_get_bits(c2h->w6, RTW89_C2H_SCANOFLD_W6_EXPECT_PERIOD); + } else { + actual_period = le32_get_bits(c2h->w8, RTW89_C2H_SCANOFLD_W8_PERIOD_V1); + expect_period = + le32_get_bits(c2h->w8, RTW89_C2H_SCANOFLD_W8_EXPECT_PERIOD_V1); + } rtw89_debug(rtwdev, RTW89_DBG_HW_SCAN, "sw_def: %d, fw_def: %d, tsf: %x, expect: %d\n", sw_def, fw_def, report_tsf, expect_period); } + rtw89_debug(rtwdev, RTW89_DBG_HW_SCAN, + "mac_idx[%d] band: %d, chan: %d, reason: %d, status: %d, tx_fail: %d, actual: %d\n", + mac_idx, band, chan, reason, status, tx_fail, actual_period); + switch (reason) { case RTW89_SCAN_LEAVE_OP_NOTIFY: case RTW89_SCAN_LEAVE_CH_NOTIFY: @@ -5364,6 +5450,39 @@ rtw89_mac_c2h_mrc_status_rpt(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 rtw89_complete_cond(wait, cond, &data); } +static void +rtw89_mac_c2h_pwr_int_notify(struct rtw89_dev *rtwdev, struct sk_buff *skb, u32 len) +{ + const struct rtw89_c2h_pwr_int_notify *c2h; + struct rtw89_sta_link *rtwsta_link; + struct ieee80211_sta *sta; + struct rtw89_sta *rtwsta; + u16 macid; + bool ps; + + c2h = (const struct rtw89_c2h_pwr_int_notify *)skb->data; + macid = le32_get_bits(c2h->w2, RTW89_C2H_PWR_INT_NOTIFY_W2_MACID); + ps = le32_get_bits(c2h->w2, RTW89_C2H_PWR_INT_NOTIFY_W2_PWR_STATUS); + + rcu_read_lock(); + + rtwsta_link = rtw89_assoc_link_rcu_dereference(rtwdev, macid); + if (unlikely(!rtwsta_link)) + goto out; + + rtwsta = rtwsta_link->rtwsta; + if (ps) + set_bit(RTW89_REMOTE_STA_IN_PS, rtwsta->flags); + else + clear_bit(RTW89_REMOTE_STA_IN_PS, rtwsta->flags); + + sta = rtwsta_to_sta(rtwsta); + ieee80211_sta_ps_transition(sta, ps); + +out: + rcu_read_unlock(); +} + static void (* const rtw89_mac_c2h_ofld_handler[])(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len) = { @@ -5409,6 +5528,12 @@ void (* const rtw89_mac_c2h_wow_handler[])(struct rtw89_dev *rtwdev, [RTW89_MAC_C2H_FUNC_AOAC_REPORT] = rtw89_mac_c2h_wow_aoac_rpt, }; +static +void (* const rtw89_mac_c2h_ap_handler[])(struct rtw89_dev *rtwdev, + struct sk_buff *c2h, u32 len) = { + [RTW89_MAC_C2H_FUNC_PWR_INT_NOTIFY] = rtw89_mac_c2h_pwr_int_notify, +}; + static void rtw89_mac_c2h_scanofld_rsp_atomic(struct rtw89_dev *rtwdev, struct sk_buff *skb) { @@ -5463,6 +5588,13 @@ bool rtw89_mac_c2h_chk_atomic(struct rtw89_dev *rtwdev, struct sk_buff *c2h, return true; case RTW89_MAC_C2H_CLASS_WOW: return true; + case RTW89_MAC_C2H_CLASS_AP: + switch (func) { + default: + return false; + case RTW89_MAC_C2H_FUNC_PWR_INT_NOTIFY: + return true; + } } } @@ -5493,14 +5625,18 @@ void rtw89_mac_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb, if (func < NUM_OF_RTW89_MAC_C2H_FUNC_WOW) handler = rtw89_mac_c2h_wow_handler[func]; break; + case RTW89_MAC_C2H_CLASS_AP: + if (func < NUM_OF_RTW89_MAC_C2H_FUNC_AP) + handler = rtw89_mac_c2h_ap_handler[func]; + break; case RTW89_MAC_C2H_CLASS_FWDBG: return; default: - rtw89_info(rtwdev, "c2h class %d not support\n", class); + rtw89_info(rtwdev, "MAC c2h class %d not support\n", class); return; } if (!handler) { - rtw89_info(rtwdev, "c2h class %d func %d not support\n", class, + rtw89_info(rtwdev, "MAC c2h class %d func %d not support\n", class, func); return; } @@ -6674,6 +6810,7 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_ax = { .typ_fltr_opt = rtw89_mac_typ_fltr_opt_ax, .cfg_ppdu_status = rtw89_mac_cfg_ppdu_status_ax, + .cfg_phy_rpt = NULL, .dle_mix_cfg = dle_mix_cfg_ax, .chk_dle_rdy = chk_dle_rdy_ax, diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h index 18579c020548..8edea96d037f 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.h +++ b/drivers/net/wireless/realtek/rtw89/mac.h @@ -169,6 +169,20 @@ enum rtw89_mac_ax_l0_to_l1_event { MAC_AX_L0_TO_L1_EVENT_MAX = 15, }; +enum rtw89_mac_phy_rpt_size { + MAC_AX_PHY_RPT_SIZE_0 = 0, + MAC_AX_PHY_RPT_SIZE_8 = 1, + MAC_AX_PHY_RPT_SIZE_16 = 2, + MAC_AX_PHY_RPT_SIZE_24 = 3, +}; + +enum rtw89_mac_hdr_cnv_size { + MAC_AX_HDR_CNV_SIZE_0 = 0, + MAC_AX_HDR_CNV_SIZE_32 = 1, + MAC_AX_HDR_CNV_SIZE_64 = 2, + MAC_AX_HDR_CNV_SIZE_96 = 3, +}; + enum rtw89_mac_wow_fw_status { WOWLAN_NOT_READY = 0x00, WOWLAN_SLEEP_READY = 0x01, @@ -426,6 +440,12 @@ enum rtw89_mac_c2h_wow_func { NUM_OF_RTW89_MAC_C2H_FUNC_WOW, }; +enum rtw89_mac_c2h_ap_func { + RTW89_MAC_C2H_FUNC_PWR_INT_NOTIFY = 0, + + NUM_OF_RTW89_MAC_C2H_FUNC_AP, +}; + enum rtw89_mac_c2h_class { RTW89_MAC_C2H_CLASS_INFO = 0x0, RTW89_MAC_C2H_CLASS_OFLD = 0x1, @@ -434,6 +454,7 @@ enum rtw89_mac_c2h_class { RTW89_MAC_C2H_CLASS_MCC = 0x4, RTW89_MAC_C2H_CLASS_FWDBG = 0x5, RTW89_MAC_C2H_CLASS_MRC = 0xe, + RTW89_MAC_C2H_CLASS_AP = 0x18, RTW89_MAC_C2H_CLASS_MAX, }; @@ -961,6 +982,7 @@ struct rtw89_mac_gen_def { enum rtw89_mac_fwd_target fwd_target, u8 mac_idx); int (*cfg_ppdu_status)(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable); + void (*cfg_phy_rpt)(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable); int (*dle_mix_cfg)(struct rtw89_dev *rtwdev, const struct rtw89_dle_mem *cfg); int (*chk_dle_rdy)(struct rtw89_dev *rtwdev, bool wde_or_ple); @@ -1216,6 +1238,27 @@ int rtw89_mac_stop_sch_tx_v2(struct rtw89_dev *rtwdev, u8 mac_idx, int rtw89_mac_resume_sch_tx(struct rtw89_dev *rtwdev, u8 mac_idx, u32 tx_en); int rtw89_mac_resume_sch_tx_v1(struct rtw89_dev *rtwdev, u8 mac_idx, u32 tx_en); int rtw89_mac_resume_sch_tx_v2(struct rtw89_dev *rtwdev, u8 mac_idx, u32 tx_en); +void rtw89_mac_cfg_phy_rpt_be(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable); + +static inline +void rtw89_mac_cfg_phy_rpt(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable) +{ + const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def; + + if (mac->cfg_phy_rpt) + mac->cfg_phy_rpt(rtwdev, mac_idx, enable); +} + +static inline +void rtw89_mac_cfg_phy_rpt_bands(struct rtw89_dev *rtwdev, bool enable) +{ + rtw89_mac_cfg_phy_rpt(rtwdev, RTW89_MAC_0, enable); + + if (!rtwdev->dbcc_en) + return; + + rtw89_mac_cfg_phy_rpt(rtwdev, RTW89_MAC_1, enable); +} static inline int rtw89_mac_cfg_ppdu_status(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable) diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c index 619d2d3771d5..b3669e0074df 100644 --- a/drivers/net/wireless/realtek/rtw89/mac80211.c +++ b/drivers/net/wireless/realtek/rtw89/mac80211.c @@ -189,10 +189,10 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw, rtw89_core_txq_init(rtwdev, vif->txq); - if (!rtw89_rtwvif_in_list(rtwdev, rtwvif)) + if (!rtw89_rtwvif_in_list(rtwdev, rtwvif)) { list_add_tail(&rtwvif->list, &rtwdev->rtwvifs_list); - - INIT_LIST_HEAD(&rtwvif->mgnt_entry); + INIT_LIST_HEAD(&rtwvif->mgnt_entry); + } ether_addr_copy(rtwvif->mac_addr, vif->addr); @@ -202,7 +202,7 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw, rtw89_traffic_stats_init(rtwdev, &rtwvif->stats); - rtwvif_link = rtw89_vif_set_link(rtwvif, 0); + rtwvif_link = rtw89_vif_set_link(rtwvif, RTW89_VIF_IDLE_LINK_ID); if (!rtwvif_link) { ret = -EINVAL; goto release_port; @@ -218,7 +218,7 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw, return 0; unset_link: - rtw89_vif_unset_link(rtwvif, 0); + rtw89_vif_unset_link(rtwvif, RTW89_VIF_IDLE_LINK_ID); release_port: list_del_init(&rtwvif->list); rtw89_core_release_bit_map(rtwdev->hw_port, port); @@ -246,17 +246,17 @@ static void rtw89_ops_remove_interface(struct ieee80211_hw *hw, mutex_lock(&rtwdev->mutex); - rtwvif_link = rtwvif->links[0]; + rtwvif_link = rtwvif->links[RTW89_VIF_IDLE_LINK_ID]; if (unlikely(!rtwvif_link)) { rtw89_err(rtwdev, "%s: rtwvif link (link_id %u) is not active\n", - __func__, 0); + __func__, RTW89_VIF_IDLE_LINK_ID); goto bottom; } __rtw89_ops_remove_iface_link(rtwdev, rtwvif_link); - rtw89_vif_unset_link(rtwvif, 0); + rtw89_vif_unset_link(rtwvif, RTW89_VIF_IDLE_LINK_ID); bottom: list_del_init(&rtwvif->list); @@ -509,6 +509,7 @@ static int __rtw89_ops_sta_add(struct rtw89_dev *rtwdev, rtw89_core_txq_init(rtwdev, sta->txq[i]); skb_queue_head_init(&rtwsta->roc_queue); + bitmap_zero(rtwsta->pairwise_sec_cam_map, RTW89_MAX_SEC_CAM_NUM); rtwsta_link = rtw89_sta_set_link(rtwsta, sta->deflink.link_id); if (!rtwsta_link) { @@ -775,6 +776,7 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw, struct rtw89_vif *rtwvif = vif_to_rtwvif(vif); struct rtw89_vif_link *rtwvif_link; const struct rtw89_chan *chan; + int ret = 0; mutex_lock(&rtwdev->mutex); @@ -783,6 +785,7 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw, rtw89_err(rtwdev, "%s: rtwvif link (link_id %u) is not active\n", __func__, link_conf->link_id); + ret = -ENOLINK; goto out; } @@ -804,12 +807,18 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw, rtw89_fw_h2c_cam(rtwdev, rtwvif_link, NULL, NULL); rtw89_chip_rfk_channel(rtwdev, rtwvif_link); + if (RTW89_CHK_FW_FEATURE(NOTIFY_AP_INFO, &rtwdev->fw)) { + ret = rtw89_fw_h2c_ap_info_refcount(rtwdev, true); + if (ret) + goto out; + } + rtw89_queue_chanctx_work(rtwdev); out: mutex_unlock(&rtwdev->mutex); - return 0; + return ret; } static @@ -830,6 +839,9 @@ void rtw89_ops_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif, goto out; } + if (RTW89_CHK_FW_FEATURE(NOTIFY_AP_INFO, &rtwdev->fw)) + rtw89_fw_h2c_ap_info_refcount(rtwdev, false); + rtw89_mac_stop_ap(rtwdev, rtwvif_link); rtw89_chip_h2c_assoc_cmac_tbl(rtwdev, rtwvif_link, NULL); rtw89_fw_h2c_join_info(rtwdev, rtwvif_link, NULL, true); @@ -1273,11 +1285,11 @@ static void rtw89_ops_cancel_hw_scan(struct ieee80211_hw *hw, if (!RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw)) return; - if (!rtwdev->scanning) - return; - mutex_lock(&rtwdev->mutex); + if (!rtwdev->scanning) + goto out; + rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0); if (unlikely(!rtwvif_link)) { rtw89_err(rtwdev, "cancel hw scan: find no link on HW-0\n"); @@ -1295,10 +1307,15 @@ static void rtw89_ops_sta_rc_update(struct ieee80211_hw *hw, struct ieee80211_link_sta *link_sta, u32 changed) { - struct ieee80211_sta *sta = link_sta->sta; + struct rtw89_sta *rtwsta = sta_to_rtwsta(link_sta->sta); struct rtw89_dev *rtwdev = hw->priv; + struct rtw89_sta_link *rtwsta_link; - rtw89_phy_ra_update_sta(rtwdev, sta, changed); + rtwsta_link = rtwsta->links[link_sta->link_id]; + if (unlikely(!rtwsta_link)) + return; + + rtw89_phy_ra_update_sta_link(rtwdev, rtwsta_link, changed); } static int rtw89_ops_add_chanctx(struct ieee80211_hw *hw, @@ -1473,6 +1490,259 @@ static int rtw89_ops_set_tid_config(struct ieee80211_hw *hw, return 0; } +static bool rtw89_can_work_on_links(struct rtw89_dev *rtwdev, + struct ieee80211_vif *vif, u16 links) +{ + struct rtw89_vif *rtwvif = vif_to_rtwvif(vif); + u8 w = hweight16(links); + + if (vif->type != NL80211_IFTYPE_STATION && + w > RTW89_MLD_NON_STA_LINK_NUM) + return false; + + return w <= rtwvif->links_inst_valid_num; +} + +static bool rtw89_ops_can_activate_links(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u16 active_links) +{ + struct rtw89_dev *rtwdev = hw->priv; + + guard(mutex)(&rtwdev->mutex); + + return rtw89_can_work_on_links(rtwdev, vif, active_links); +} + +static void __rtw89_ops_clr_vif_links(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif, + unsigned long clr_links) +{ + struct rtw89_vif_link *rtwvif_link; + unsigned int link_id; + + for_each_set_bit(link_id, &clr_links, IEEE80211_MLD_MAX_NUM_LINKS) { + rtwvif_link = rtwvif->links[link_id]; + if (unlikely(!rtwvif_link)) + continue; + + __rtw89_ops_remove_iface_link(rtwdev, rtwvif_link); + + rtw89_vif_unset_link(rtwvif, link_id); + } +} + +static int __rtw89_ops_set_vif_links(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif, + unsigned long set_links) +{ + struct rtw89_vif_link *rtwvif_link; + unsigned int link_id; + int ret; + + for_each_set_bit(link_id, &set_links, IEEE80211_MLD_MAX_NUM_LINKS) { + rtwvif_link = rtw89_vif_set_link(rtwvif, link_id); + if (!rtwvif_link) + return -EINVAL; + + ret = __rtw89_ops_add_iface_link(rtwdev, rtwvif_link); + if (ret) { + rtw89_err(rtwdev, "%s: failed to add iface (link id %u)\n", + __func__, link_id); + return ret; + } + } + + return 0; +} + +static +int rtw89_ops_change_vif_links(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u16 old_links, u16 new_links, + struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]) +{ + struct rtw89_dev *rtwdev = hw->priv; + struct rtw89_vif *rtwvif = vif_to_rtwvif(vif); + unsigned long clr_links = old_links & ~new_links; + unsigned long set_links = new_links & ~old_links; + bool removing_links = !old_links || clr_links; + struct rtw89_link_conf_container *snap; + int ret = 0; + int i; + + guard(mutex)(&rtwdev->mutex); + + rtw89_debug(rtwdev, RTW89_DBG_STATE, + "%s: old_links (0x%08x) -> new_links (0x%08x)\n", + __func__, old_links, new_links); + + if (!rtw89_can_work_on_links(rtwdev, vif, new_links)) + return -EOPNOTSUPP; + + if (removing_links) { + snap = kzalloc(sizeof(*snap), GFP_KERNEL); + if (!snap) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(snap->link_conf); i++) + snap->link_conf[i] = old[i]; + + rcu_assign_pointer(rtwvif->snap_link_confs, snap); + } + + /* might depend on @snap; don't change order */ + rtw89_leave_ips_by_hwflags(rtwdev); + + if (rtwdev->scanning) + rtw89_hw_scan_abort(rtwdev, rtwdev->scan_info.scanning_vif); + + if (!old_links) + __rtw89_ops_clr_vif_links(rtwdev, rtwvif, + BIT(RTW89_VIF_IDLE_LINK_ID)); + else if (clr_links) + __rtw89_ops_clr_vif_links(rtwdev, rtwvif, clr_links); + + if (removing_links) { + /* @snap is required if and only if during removing links. + * However, it's done here. So, cleanup @snap immediately. + */ + rcu_assign_pointer(rtwvif->snap_link_confs, NULL); + + /* The pointers in @old will free after this function return, + * so synchronously wait for all readers of snap to be done. + */ + synchronize_rcu(); + kfree(snap); + } + + if (set_links) { + ret = __rtw89_ops_set_vif_links(rtwdev, rtwvif, set_links); + if (ret) + __rtw89_ops_clr_vif_links(rtwdev, rtwvif, set_links); + } else if (!new_links) { + ret = __rtw89_ops_set_vif_links(rtwdev, rtwvif, + BIT(RTW89_VIF_IDLE_LINK_ID)); + if (ret) + __rtw89_ops_clr_vif_links(rtwdev, rtwvif, + BIT(RTW89_VIF_IDLE_LINK_ID)); + } + + rtw89_enter_ips_by_hwflags(rtwdev); + return ret; +} + +static void __rtw89_ops_clr_sta_links(struct rtw89_dev *rtwdev, + struct rtw89_sta *rtwsta, + unsigned long clr_links) +{ + struct rtw89_vif_link *rtwvif_link; + struct rtw89_sta_link *rtwsta_link; + unsigned int link_id; + + for_each_set_bit(link_id, &clr_links, IEEE80211_MLD_MAX_NUM_LINKS) { + rtwsta_link = rtwsta->links[link_id]; + if (unlikely(!rtwsta_link)) + continue; + + rtwvif_link = rtwsta_link->rtwvif_link; + + rtw89_core_sta_link_disassoc(rtwdev, rtwvif_link, rtwsta_link); + rtw89_core_sta_link_disconnect(rtwdev, rtwvif_link, rtwsta_link); + rtw89_core_sta_link_remove(rtwdev, rtwvif_link, rtwsta_link); + + rtw89_sta_unset_link(rtwsta, link_id); + } +} + +static int __rtw89_ops_set_sta_links(struct rtw89_dev *rtwdev, + struct rtw89_sta *rtwsta, + unsigned long set_links) +{ + struct rtw89_vif_link *rtwvif_link; + struct rtw89_sta_link *rtwsta_link; + unsigned int link_id; + u8 sec_cam_idx; + int ret; + + for_each_set_bit(link_id, &set_links, IEEE80211_MLD_MAX_NUM_LINKS) { + rtwsta_link = rtw89_sta_set_link(rtwsta, link_id); + if (!rtwsta_link) + return -EINVAL; + + rtwvif_link = rtwsta_link->rtwvif_link; + + ret = rtw89_core_sta_link_add(rtwdev, rtwvif_link, rtwsta_link); + if (ret) { + rtw89_err(rtwdev, "%s: failed to add sta (link id %u)\n", + __func__, link_id); + return ret; + } + + rtw89_vif_type_mapping(rtwvif_link, true); + + ret = rtw89_core_sta_link_assoc(rtwdev, rtwvif_link, rtwsta_link); + if (ret) { + rtw89_err(rtwdev, "%s: failed to assoc sta (link id %u)\n", + __func__, link_id); + return ret; + } + + __rtw89_ops_bss_link_assoc(rtwdev, rtwvif_link); + + for_each_set_bit(sec_cam_idx, rtwsta->pairwise_sec_cam_map, + RTW89_MAX_SEC_CAM_NUM) { + ret = rtw89_cam_attach_link_sec_cam(rtwdev, + rtwvif_link, + rtwsta_link, + sec_cam_idx); + if (ret) { + rtw89_err(rtwdev, + "%s: failed to apply pairwise key (link id %u)\n", + __func__, link_id); + return ret; + } + } + } + + return 0; +} + +static +int rtw89_ops_change_sta_links(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + u16 old_links, u16 new_links) +{ + struct rtw89_dev *rtwdev = hw->priv; + struct rtw89_sta *rtwsta = sta_to_rtwsta(sta); + unsigned long clr_links = old_links & ~new_links; + unsigned long set_links = new_links & ~old_links; + int ret = 0; + + guard(mutex)(&rtwdev->mutex); + + rtw89_debug(rtwdev, RTW89_DBG_STATE, + "%s: old_links (0x%08x) -> new_links (0x%08x)\n", + __func__, old_links, new_links); + + if (!rtw89_can_work_on_links(rtwdev, vif, new_links)) + return -EOPNOTSUPP; + + rtw89_leave_ps_mode(rtwdev); + + if (clr_links) + __rtw89_ops_clr_sta_links(rtwdev, rtwsta, clr_links); + + if (set_links) { + ret = __rtw89_ops_set_sta_links(rtwdev, rtwsta, set_links); + if (ret) + __rtw89_ops_clr_sta_links(rtwdev, rtwsta, set_links); + } + + return ret; +} + #ifdef CONFIG_PM static int rtw89_ops_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) @@ -1600,6 +1870,9 @@ const struct ieee80211_ops rtw89_ops = { .set_sar_specs = rtw89_ops_set_sar_specs, .link_sta_rc_update = rtw89_ops_sta_rc_update, .set_tid_config = rtw89_ops_set_tid_config, + .can_activate_links = rtw89_ops_can_activate_links, + .change_vif_links = rtw89_ops_change_vif_links, + .change_sta_links = rtw89_ops_change_sta_links, #ifdef CONFIG_PM .suspend = rtw89_ops_suspend, .resume = rtw89_ops_resume, diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c index f7a396c8a3cd..2dbdeae904ad 100644 --- a/drivers/net/wireless/realtek/rtw89/mac_be.c +++ b/drivers/net/wireless/realtek/rtw89/mac_be.c @@ -1988,6 +1988,20 @@ int rtw89_mac_resume_sch_tx_v2(struct rtw89_dev *rtwdev, u8 mac_idx, u32 tx_en) } EXPORT_SYMBOL(rtw89_mac_resume_sch_tx_v2); +void rtw89_mac_cfg_phy_rpt_be(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable) +{ + u32 reg, val; + + reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_RCR, mac_idx); + val = enable ? MAC_AX_PHY_RPT_SIZE_8 : MAC_AX_PHY_RPT_SIZE_0; + rtw89_write32_mask(rtwdev, reg, B_BE_PHY_RPT_SZ_MASK, val); + rtw89_write32_mask(rtwdev, reg, B_BE_HDR_CNV_SZ_MASK, MAC_AX_HDR_CNV_SIZE_0); + + reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_DRV_INFO_OPTION, mac_idx); + rtw89_write32_mask(rtwdev, reg, B_BE_DRV_INFO_PHYRPT_EN, enable); +} +EXPORT_SYMBOL(rtw89_mac_cfg_phy_rpt_be); + static int rtw89_mac_cfg_ppdu_status_be(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable) { @@ -2583,6 +2597,7 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_be = { .typ_fltr_opt = rtw89_mac_typ_fltr_opt_be, .cfg_ppdu_status = rtw89_mac_cfg_ppdu_status_be, + .cfg_phy_rpt = rtw89_mac_cfg_phy_rpt_be, .dle_mix_cfg = dle_mix_cfg_be, .chk_dle_rdy = chk_dle_rdy_be, diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c index f923bec03d41..c2fe5a898dc7 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.c +++ b/drivers/net/wireless/realtek/rtw89/pci.c @@ -321,10 +321,11 @@ static u32 rtw89_pci_get_rx_skb_idx(struct rtw89_dev *rtwdev, static u32 rtw89_pci_rxbd_deliver_skbs(struct rtw89_dev *rtwdev, struct rtw89_pci_rx_ring *rx_ring) { - struct rtw89_pci_dma_ring *bd_ring = &rx_ring->bd_ring; - struct rtw89_pci_rx_info *rx_info; struct rtw89_rx_desc_info *desc_info = &rx_ring->diliver_desc; + struct rtw89_pci_dma_ring *bd_ring = &rx_ring->bd_ring; + const struct rtw89_pci_info *info = rtwdev->pci_info; struct sk_buff *new = rx_ring->diliver_skb; + struct rtw89_pci_rx_info *rx_info; struct sk_buff *skb; u32 rxinfo_size = sizeof(struct rtw89_pci_rxbd_info); u32 skb_idx; @@ -344,9 +345,14 @@ static u32 rtw89_pci_rxbd_deliver_skbs(struct rtw89_dev *rtwdev, } rx_info = RTW89_PCI_RX_SKB_CB(skb); - fs = rx_info->fs; + fs = info->no_rxbd_fs ? !new : rx_info->fs; ls = rx_info->ls; + if (unlikely(!fs || !ls)) + rtw89_debug(rtwdev, RTW89_DBG_UNEXP, + "unexpected fs/ls=%d/%d tag=%u len=%u new->len=%u\n", + fs, ls, rx_info->tag, rx_info->len, new ? new->len : 0); + if (fs) { if (new) { rtw89_debug(rtwdev, RTW89_DBG_UNEXP, @@ -2516,7 +2522,7 @@ static int rtw89_pci_dphy_delay(struct rtw89_dev *rtwdev) PCIE_DPHY_DLY_25US, PCIE_PHY_GEN1); } -static void rtw89_pci_power_wake(struct rtw89_dev *rtwdev, bool pwr_up) +static void rtw89_pci_power_wake_ax(struct rtw89_dev *rtwdev, bool pwr_up) { if (pwr_up) rtw89_write32_set(rtwdev, R_AX_HCI_OPT_CTRL, BIT_WAKE_CTRL); @@ -2825,6 +2831,8 @@ static int rtw89_pci_ops_deinit(struct rtw89_dev *rtwdev) { const struct rtw89_pci_info *info = rtwdev->pci_info; + rtw89_pci_power_wake(rtwdev, false); + if (rtwdev->chip->chip_id == RTL8852A) { /* ltr sw trigger */ rtw89_write32_set(rtwdev, R_AX_LTR_CTRL_0, B_AX_APP_LTR_IDLE); @@ -2867,7 +2875,7 @@ static int rtw89_pci_ops_mac_pre_init_ax(struct rtw89_dev *rtwdev) return ret; } - rtw89_pci_power_wake(rtwdev, true); + rtw89_pci_power_wake_ax(rtwdev, true); rtw89_pci_autoload_hang(rtwdev); rtw89_pci_l12_vmain(rtwdev); rtw89_pci_gen2_force_ib(rtwdev); @@ -2912,6 +2920,13 @@ static int rtw89_pci_ops_mac_pre_init_ax(struct rtw89_dev *rtwdev) return 0; } +static int rtw89_pci_ops_mac_pre_deinit_ax(struct rtw89_dev *rtwdev) +{ + rtw89_pci_power_wake_ax(rtwdev, false); + + return 0; +} + int rtw89_pci_ltr_set(struct rtw89_dev *rtwdev, bool en) { u32 val; @@ -4069,6 +4084,15 @@ static void rtw89_pci_l1ss_cfg(struct rtw89_dev *rtwdev) rtw89_pci_l1ss_set(rtwdev, true); } +static void rtw89_pci_cpl_timeout_cfg(struct rtw89_dev *rtwdev) +{ + struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv; + struct pci_dev *pdev = rtwpci->pdev; + + pcie_capability_set_word(pdev, PCI_EXP_DEVCTL2, + PCI_EXP_DEVCTL2_COMP_TMOUT_DIS); +} + static int rtw89_pci_poll_io_idle_ax(struct rtw89_dev *rtwdev) { int ret = 0; @@ -4282,6 +4306,7 @@ void rtw89_pci_basic_cfg(struct rtw89_dev *rtwdev, bool resume) rtw89_pci_disable_eq(rtwdev); rtw89_pci_filter_out(rtwdev); + rtw89_pci_cpl_timeout_cfg(rtwdev); rtw89_pci_link_cfg(rtwdev); rtw89_pci_l1ss_cfg(rtwdev); } @@ -4325,7 +4350,7 @@ const struct rtw89_pci_gen_def rtw89_pci_gen_ax = { B_AX_RDU_INT}, .mac_pre_init = rtw89_pci_ops_mac_pre_init_ax, - .mac_pre_deinit = NULL, + .mac_pre_deinit = rtw89_pci_ops_mac_pre_deinit_ax, .mac_post_init = rtw89_pci_ops_mac_post_init_ax, .clr_idx_all = rtw89_pci_clr_idx_all_ax, @@ -4343,6 +4368,7 @@ const struct rtw89_pci_gen_def rtw89_pci_gen_ax = { .l1ss_set = rtw89_pci_l1ss_set_ax, .disable_eq = rtw89_pci_disable_eq_ax, + .power_wake = rtw89_pci_power_wake_ax, }; EXPORT_SYMBOL(rtw89_pci_gen_ax); @@ -4400,7 +4426,7 @@ int rtw89_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) rtwdev = rtw89_alloc_ieee80211_hw(&pdev->dev, sizeof(struct rtw89_pci), - info->chip); + info->chip, info->variant); if (!rtwdev) { dev_err(&pdev->dev, "failed to allocate hw\n"); return -ENOMEM; diff --git a/drivers/net/wireless/realtek/rtw89/pci.h b/drivers/net/wireless/realtek/rtw89/pci.h index b68e2d82eea9..4d11c3dd60a5 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.h +++ b/drivers/net/wireless/realtek/rtw89/pci.h @@ -1051,7 +1051,8 @@ #define RTW89_PCI_TXWD_NUM_MAX 512 #define RTW89_PCI_TXWD_PAGE_SIZE 128 #define RTW89_PCI_ADDRINFO_MAX 4 -#define RTW89_PCI_RX_BUF_SIZE (11454 + 40) /* +40 for rtw89_rxdesc_long_v2 */ +/* +40 for rtw89_rxdesc_long_v2; +4 for rtw89_pci_rxbd_info */ +#define RTW89_PCI_RX_BUF_SIZE (11454 + 40 + 4) #define RTW89_PCI_POLL_BDRAM_RST_CNT 100 #define RTW89_PCI_MULTITAG 8 @@ -1290,6 +1291,7 @@ struct rtw89_pci_gen_def { void (*l1ss_set)(struct rtw89_dev *rtwdev, bool enable); void (*disable_eq)(struct rtw89_dev *rtwdev); + void (*power_wake)(struct rtw89_dev *rtwdev, bool pwr_up); }; #define RTW89_PCI_SSID(v, d, ssv, ssd, cust) \ @@ -1323,6 +1325,7 @@ struct rtw89_pci_info { enum mac_ax_io_rcy_tmr io_rcy_tmr; bool rx_ring_eq_is_full; bool check_rx_tag; + bool no_rxbd_fs; u32 init_cfg_reg; u32 txhci_en_bit; @@ -1805,4 +1808,12 @@ static inline void rtw89_pci_disable_eq(struct rtw89_dev *rtwdev) gen_def->disable_eq(rtwdev); } +static inline void rtw89_pci_power_wake(struct rtw89_dev *rtwdev, bool pwr_up) +{ + const struct rtw89_pci_info *info = rtwdev->pci_info; + const struct rtw89_pci_gen_def *gen_def = info->gen_def; + + gen_def->power_wake(rtwdev, pwr_up); +} + #endif diff --git a/drivers/net/wireless/realtek/rtw89/pci_be.c b/drivers/net/wireless/realtek/rtw89/pci_be.c index 34154506f5d4..cd39eebe8186 100644 --- a/drivers/net/wireless/realtek/rtw89/pci_be.c +++ b/drivers/net/wireless/realtek/rtw89/pci_be.c @@ -691,5 +691,6 @@ const struct rtw89_pci_gen_def rtw89_pci_gen_be = { .l1ss_set = rtw89_pci_l1ss_set_be, .disable_eq = rtw89_pci_disable_eq_be, + .power_wake = _patch_pcie_power_wake_be, }; EXPORT_SYMBOL(rtw89_pci_gen_be); diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c index f24aca663cf0..c7c05f7fda1d 100644 --- a/drivers/net/wireless/realtek/rtw89/phy.c +++ b/drivers/net/wireless/realtek/rtw89/phy.c @@ -2,6 +2,7 @@ /* Copyright(c) 2019-2020 Realtek Corporation */ +#include "acpi.h" #include "chan.h" #include "coex.h" #include "debug.h" @@ -260,19 +261,32 @@ rtw89_ra_mask_he_rates[4] = {RA_MASK_HE_1SS_RATES, RA_MASK_HE_2SS_RATES, static const u64 rtw89_ra_mask_eht_rates[4] = {RA_MASK_EHT_1SS_RATES, RA_MASK_EHT_2SS_RATES, RA_MASK_EHT_3SS_RATES, RA_MASK_EHT_4SS_RATES}; +static const u64 +rtw89_ra_mask_eht_mcs0_11[4] = {RA_MASK_EHT_1SS_MCS0_11, RA_MASK_EHT_2SS_MCS0_11, + RA_MASK_EHT_3SS_MCS0_11, RA_MASK_EHT_4SS_MCS0_11}; static void rtw89_phy_ra_gi_ltf(struct rtw89_dev *rtwdev, struct rtw89_sta_link *rtwsta_link, + struct ieee80211_link_sta *link_sta, const struct rtw89_chan *chan, bool *fix_giltf_en, u8 *fix_giltf) { struct cfg80211_bitrate_mask *mask = &rtwsta_link->mask; u8 band = chan->band_type; enum nl80211_band nl_band = rtw89_hw_to_nl80211_band(band); - u8 he_gi = mask->control[nl_band].he_gi; u8 he_ltf = mask->control[nl_band].he_ltf; + u8 he_gi = mask->control[nl_band].he_gi; - if (!rtwsta_link->use_cfg_mask) + *fix_giltf_en = true; + + if (rtwdev->chip->chip_id == RTL8852C && + chan->band_width == RTW89_CHANNEL_WIDTH_160 && + rtw89_sta_link_has_su_mu_4xhe08(link_sta)) + *fix_giltf = RTW89_GILTF_SGI_4XHE08; + else + *fix_giltf = RTW89_GILTF_2XHE08; + + if (!(rtwsta_link->use_cfg_mask && link_sta->he_cap.has_he)) return; if (he_ltf == 2 && he_gi == 2) { @@ -287,12 +301,7 @@ static void rtw89_phy_ra_gi_ltf(struct rtw89_dev *rtwdev, *fix_giltf = RTW89_GILTF_1XHE16; } else if (he_ltf == 0 && he_gi == 0) { *fix_giltf = RTW89_GILTF_1XHE08; - } else { - *fix_giltf_en = false; - return; } - - *fix_giltf_en = true; } static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev, @@ -324,7 +333,14 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev, if (link_sta->eht_cap.has_eht) { mode |= RTW89_RA_MODE_EHT; ra_mask |= get_eht_ra_mask(link_sta); - high_rate_masks = rtw89_ra_mask_eht_rates; + + if (rtwdev->hal.no_mcs_12_13) + high_rate_masks = rtw89_ra_mask_eht_mcs0_11; + else + high_rate_masks = rtw89_ra_mask_eht_rates; + + rtw89_phy_ra_gi_ltf(rtwdev, rtwsta_link, link_sta, + chan, &fix_giltf_en, &fix_giltf); } else if (link_sta->he_cap.has_he) { mode |= RTW89_RA_MODE_HE; csi_mode = RTW89_RA_RPT_MODE_HE; @@ -336,7 +352,8 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev, if (link_sta->he_cap.he_cap_elem.phy_cap_info[1] & IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD) ldpc_en = 1; - rtw89_phy_ra_gi_ltf(rtwdev, rtwsta_link, chan, &fix_giltf_en, &fix_giltf); + rtw89_phy_ra_gi_ltf(rtwdev, rtwsta_link, link_sta, + chan, &fix_giltf_en, &fix_giltf); } else if (link_sta->vht_cap.vht_supported) { u16 mcs_map = le16_to_cpu(link_sta->vht_cap.vht_mcs.rx_mcs_map); @@ -466,11 +483,11 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev, ra->csi_mode = csi_mode; } -static void __rtw89_phy_ra_update_sta(struct rtw89_dev *rtwdev, - struct rtw89_vif_link *rtwvif_link, - struct rtw89_sta_link *rtwsta_link, - u32 changed) +void rtw89_phy_ra_update_sta_link(struct rtw89_dev *rtwdev, + struct rtw89_sta_link *rtwsta_link, + u32 changed) { + struct rtw89_vif_link *rtwvif_link = rtwsta_link->rtwvif_link; struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link); struct rtw89_ra_info *ra = &rtwsta_link->ra; struct ieee80211_link_sta *link_sta; @@ -503,14 +520,11 @@ void rtw89_phy_ra_update_sta(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta u32 changed) { struct rtw89_sta *rtwsta = sta_to_rtwsta(sta); - struct rtw89_vif_link *rtwvif_link; struct rtw89_sta_link *rtwsta_link; unsigned int link_id; - rtw89_sta_for_each_link(rtwsta, rtwsta_link, link_id) { - rtwvif_link = rtwsta_link->rtwvif_link; - __rtw89_phy_ra_update_sta(rtwdev, rtwvif_link, rtwsta_link, changed); - } + rtw89_sta_for_each_link(rtwsta, rtwsta_link, link_id) + rtw89_phy_ra_update_sta_link(rtwdev, rtwsta_link, changed); } static bool __check_rate_pattern(struct rtw89_phy_rate_pattern *next, @@ -1854,6 +1868,228 @@ void rtw89_phy_write_reg3_tbl(struct rtw89_dev *rtwdev, } EXPORT_SYMBOL(rtw89_phy_write_reg3_tbl); +static u8 rtw89_phy_ant_gain_domain_to_regd(struct rtw89_dev *rtwdev, u8 ant_gain_regd) +{ + switch (ant_gain_regd) { + case RTW89_ANT_GAIN_ETSI: + return RTW89_ETSI; + default: + rtw89_debug(rtwdev, RTW89_DBG_TXPWR, + "unknown antenna gain domain: %d\n", + ant_gain_regd); + return RTW89_REGD_NUM; + } +} + +/* antenna gain in unit of 0.25 dbm */ +#define RTW89_ANT_GAIN_2GHZ_MIN -8 +#define RTW89_ANT_GAIN_2GHZ_MAX 14 +#define RTW89_ANT_GAIN_5GHZ_MIN -8 +#define RTW89_ANT_GAIN_5GHZ_MAX 20 +#define RTW89_ANT_GAIN_6GHZ_MIN -8 +#define RTW89_ANT_GAIN_6GHZ_MAX 20 + +#define RTW89_ANT_GAIN_REF_2GHZ 14 +#define RTW89_ANT_GAIN_REF_5GHZ 20 +#define RTW89_ANT_GAIN_REF_6GHZ 20 + +void rtw89_phy_ant_gain_init(struct rtw89_dev *rtwdev) +{ + struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain; + const struct rtw89_chip_info *chip = rtwdev->chip; + struct rtw89_acpi_rtag_result res = {}; + u32 domain; + int ret; + u8 i, j; + u8 regd; + u8 val; + + if (!chip->support_ant_gain) + return; + + ret = rtw89_acpi_evaluate_rtag(rtwdev, &res); + if (ret) { + rtw89_debug(rtwdev, RTW89_DBG_TXPWR, + "acpi: cannot eval rtag: %d\n", ret); + return; + } + + if (res.revision != 0) { + rtw89_debug(rtwdev, RTW89_DBG_TXPWR, + "unknown rtag revision: %d\n", res.revision); + return; + } + + domain = get_unaligned_le32(&res.domain); + + for (i = 0; i < RTW89_ANT_GAIN_DOMAIN_NUM; i++) { + if (!(domain & BIT(i))) + continue; + + regd = rtw89_phy_ant_gain_domain_to_regd(rtwdev, i); + if (regd >= RTW89_REGD_NUM) + continue; + ant_gain->regd_enabled |= BIT(regd); + } + + for (i = 0; i < RTW89_ANT_GAIN_CHAIN_NUM; i++) { + for (j = 0; j < RTW89_ANT_GAIN_SUBBAND_NR; j++) { + val = res.ant_gain_table[i][j]; + switch (j) { + default: + case RTW89_ANT_GAIN_2GHZ_SUBBAND: + val = RTW89_ANT_GAIN_REF_2GHZ - + clamp_t(s8, val, + RTW89_ANT_GAIN_2GHZ_MIN, + RTW89_ANT_GAIN_2GHZ_MAX); + break; + case RTW89_ANT_GAIN_5GHZ_SUBBAND_1: + case RTW89_ANT_GAIN_5GHZ_SUBBAND_2: + case RTW89_ANT_GAIN_5GHZ_SUBBAND_2E: + case RTW89_ANT_GAIN_5GHZ_SUBBAND_3_4: + val = RTW89_ANT_GAIN_REF_5GHZ - + clamp_t(s8, val, + RTW89_ANT_GAIN_5GHZ_MIN, + RTW89_ANT_GAIN_5GHZ_MAX); + break; + case RTW89_ANT_GAIN_6GHZ_SUBBAND_5_L: + case RTW89_ANT_GAIN_6GHZ_SUBBAND_5_H: + case RTW89_ANT_GAIN_6GHZ_SUBBAND_6: + case RTW89_ANT_GAIN_6GHZ_SUBBAND_7_L: + case RTW89_ANT_GAIN_6GHZ_SUBBAND_7_H: + case RTW89_ANT_GAIN_6GHZ_SUBBAND_8: + val = RTW89_ANT_GAIN_REF_6GHZ - + clamp_t(s8, val, + RTW89_ANT_GAIN_6GHZ_MIN, + RTW89_ANT_GAIN_6GHZ_MAX); + } + ant_gain->offset[i][j] = val; + } + } +} + +static +enum rtw89_ant_gain_subband rtw89_phy_ant_gain_get_subband(struct rtw89_dev *rtwdev, + u32 center_freq) +{ + switch (center_freq) { + default: + rtw89_debug(rtwdev, RTW89_DBG_TXPWR, + "center freq: %u to antenna gain subband is unhandled\n", + center_freq); + fallthrough; + case 2412 ... 2484: + return RTW89_ANT_GAIN_2GHZ_SUBBAND; + case 5180 ... 5240: + return RTW89_ANT_GAIN_5GHZ_SUBBAND_1; + case 5250 ... 5320: + return RTW89_ANT_GAIN_5GHZ_SUBBAND_2; + case 5500 ... 5720: + return RTW89_ANT_GAIN_5GHZ_SUBBAND_2E; + case 5745 ... 5885: + return RTW89_ANT_GAIN_5GHZ_SUBBAND_3_4; + case 5955 ... 6155: + return RTW89_ANT_GAIN_6GHZ_SUBBAND_5_L; + case 6175 ... 6415: + return RTW89_ANT_GAIN_6GHZ_SUBBAND_5_H; + case 6435 ... 6515: + return RTW89_ANT_GAIN_6GHZ_SUBBAND_6; + case 6535 ... 6695: + return RTW89_ANT_GAIN_6GHZ_SUBBAND_7_L; + case 6715 ... 6855: + return RTW89_ANT_GAIN_6GHZ_SUBBAND_7_H; + + /* freq 6875 (ch 185, 20MHz) spans RTW89_ANT_GAIN_6GHZ_SUBBAND_7_H + * and RTW89_ANT_GAIN_6GHZ_SUBBAND_8, so directly describe it with + * struct rtw89_6ghz_span. + */ + + case 6895 ... 7115: + return RTW89_ANT_GAIN_6GHZ_SUBBAND_8; + } +} + +static s8 rtw89_phy_ant_gain_query(struct rtw89_dev *rtwdev, + enum rtw89_rf_path path, u32 center_freq) +{ + struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain; + enum rtw89_ant_gain_subband subband_l, subband_h; + const struct rtw89_6ghz_span *span; + + span = rtw89_get_6ghz_span(rtwdev, center_freq); + + if (span && RTW89_ANT_GAIN_SPAN_VALID(span)) { + subband_l = span->ant_gain_subband_low; + subband_h = span->ant_gain_subband_high; + } else { + subband_l = rtw89_phy_ant_gain_get_subband(rtwdev, center_freq); + subband_h = subband_l; + } + + rtw89_debug(rtwdev, RTW89_DBG_TXPWR, + "center_freq %u: antenna gain subband {%u, %u}\n", + center_freq, subband_l, subband_h); + + return min(ant_gain->offset[path][subband_l], + ant_gain->offset[path][subband_h]); +} + +static s8 rtw89_phy_ant_gain_offset(struct rtw89_dev *rtwdev, u8 band, u32 center_freq) +{ + struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain; + const struct rtw89_chip_info *chip = rtwdev->chip; + u8 regd = rtw89_regd_get(rtwdev, band); + s8 offset_patha, offset_pathb; + + if (!chip->support_ant_gain) + return 0; + + if (!(ant_gain->regd_enabled & BIT(regd))) + return 0; + + offset_patha = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_A, center_freq); + offset_pathb = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_B, center_freq); + + return max(offset_patha, offset_pathb); +} + +s16 rtw89_phy_ant_gain_pwr_offset(struct rtw89_dev *rtwdev, + const struct rtw89_chan *chan) +{ + struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain; + u8 regd = rtw89_regd_get(rtwdev, chan->band_type); + s8 offset_patha, offset_pathb; + + if (!(ant_gain->regd_enabled & BIT(regd))) + return 0; + + offset_patha = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_A, chan->freq); + offset_pathb = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_B, chan->freq); + + return rtw89_phy_txpwr_rf_to_bb(rtwdev, offset_patha - offset_pathb); +} +EXPORT_SYMBOL(rtw89_phy_ant_gain_pwr_offset); + +void rtw89_print_ant_gain(struct seq_file *m, struct rtw89_dev *rtwdev, + const struct rtw89_chan *chan) +{ + struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain; + const struct rtw89_chip_info *chip = rtwdev->chip; + u8 regd = rtw89_regd_get(rtwdev, chan->band_type); + s8 offset_patha, offset_pathb; + + if (!chip->support_ant_gain || !(ant_gain->regd_enabled & BIT(regd))) { + seq_puts(m, "no DAG is applied\n"); + return; + } + + offset_patha = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_A, chan->freq); + offset_pathb = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_B, chan->freq); + + seq_printf(m, "ChainA offset: %d dBm\n", offset_patha); + seq_printf(m, "ChainB offset: %d dBm\n", offset_pathb); +} + static const u8 rtw89_rs_idx_num_ax[] = { [RTW89_RS_CCK] = RTW89_RATE_CCK_NUM, [RTW89_RS_OFDM] = RTW89_RATE_OFDM_NUM, @@ -1917,20 +2153,6 @@ void rtw89_phy_load_txpwr_byrate(struct rtw89_dev *rtwdev, } EXPORT_SYMBOL(rtw89_phy_load_txpwr_byrate); -static s8 rtw89_phy_txpwr_rf_to_mac(struct rtw89_dev *rtwdev, s8 txpwr_rf) -{ - const struct rtw89_chip_info *chip = rtwdev->chip; - - return txpwr_rf >> (chip->txpwr_factor_rf - chip->txpwr_factor_mac); -} - -static s8 rtw89_phy_txpwr_dbm_to_mac(struct rtw89_dev *rtwdev, s8 dbm) -{ - const struct rtw89_chip_info *chip = rtwdev->chip; - - return clamp_t(s16, dbm << chip->txpwr_factor_mac, -64, 63); -} - static s8 rtw89_phy_txpwr_dbm_without_tolerance(s8 dbm) { const u8 tssi_deviation_point = 0; @@ -2027,7 +2249,7 @@ s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band, u8 ch_idx = rtw89_channel_to_idx(rtwdev, band, ch); u8 regd = rtw89_regd_get(rtwdev, band); u8 reg6 = regulatory->reg_6ghz_power; - s8 lmt = 0, sar; + s8 lmt = 0, sar, offset; s8 cstr; switch (band) { @@ -2059,7 +2281,8 @@ s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band, return 0; } - lmt = rtw89_phy_txpwr_rf_to_mac(rtwdev, lmt); + offset = rtw89_phy_ant_gain_offset(rtwdev, band, freq); + lmt = rtw89_phy_txpwr_rf_to_mac(rtwdev, lmt + offset); sar = rtw89_query_sar(rtwdev, freq); cstr = rtw89_phy_get_tpe_constraint(rtwdev, band); @@ -2286,7 +2509,7 @@ s8 rtw89_phy_read_txpwr_limit_ru(struct rtw89_dev *rtwdev, u8 band, u8 ch_idx = rtw89_channel_to_idx(rtwdev, band, ch); u8 regd = rtw89_regd_get(rtwdev, band); u8 reg6 = regulatory->reg_6ghz_power; - s8 lmt_ru = 0, sar; + s8 lmt_ru = 0, sar, offset; s8 cstr; switch (band) { @@ -2318,7 +2541,8 @@ s8 rtw89_phy_read_txpwr_limit_ru(struct rtw89_dev *rtwdev, u8 band, return 0; } - lmt_ru = rtw89_phy_txpwr_rf_to_mac(rtwdev, lmt_ru); + offset = rtw89_phy_ant_gain_offset(rtwdev, band, freq); + lmt_ru = rtw89_phy_txpwr_rf_to_mac(rtwdev, lmt_ru + offset); sar = rtw89_query_sar(rtwdev, freq); cstr = rtw89_phy_get_tpe_constraint(rtwdev, band); @@ -3228,10 +3452,16 @@ rtw89_phy_c2h_rfk_report_state(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u3 (int)(len - sizeof(report->hdr)), &report->state); } +static void +rtw89_phy_c2h_rfk_log_tas_pwr(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len) +{ +} + static void (* const rtw89_phy_c2h_rfk_report_handler[])(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len) = { [RTW89_PHY_C2H_RFK_REPORT_FUNC_STATE] = rtw89_phy_c2h_rfk_report_state, + [RTW89_PHY_C2H_RFK_LOG_TAS_PWR] = rtw89_phy_c2h_rfk_log_tas_pwr, }; bool rtw89_phy_c2h_chk_atomic(struct rtw89_dev *rtwdev, u8 class, u8 func) @@ -3285,11 +3515,11 @@ void rtw89_phy_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb, return; fallthrough; default: - rtw89_info(rtwdev, "c2h class %d not support\n", class); + rtw89_info(rtwdev, "PHY c2h class %d not support\n", class); return; } if (!handler) { - rtw89_info(rtwdev, "c2h class %d func %d not support\n", class, + rtw89_info(rtwdev, "PHY c2h class %d func %d not support\n", class, func); return; } @@ -4058,7 +4288,6 @@ static void rtw89_phy_cfo_set_crystal_cap(struct rtw89_dev *rtwdev, if (!force && cfo->crystal_cap == crystal_cap) return; - crystal_cap = clamp_t(u8, crystal_cap, 0, 127); if (chip->chip_id == RTL8852A || chip->chip_id == RTL8851B) { rtw89_phy_cfo_set_xcap_reg(rtwdev, true, crystal_cap); rtw89_phy_cfo_set_xcap_reg(rtwdev, false, crystal_cap); @@ -4181,7 +4410,7 @@ static void rtw89_phy_cfo_crystal_cap_adjust(struct rtw89_dev *rtwdev, s32 curr_cfo) { struct rtw89_cfo_tracking_info *cfo = &rtwdev->cfo_tracking; - s8 crystal_cap = cfo->crystal_cap; + int crystal_cap = cfo->crystal_cap; s32 cfo_abs = abs(curr_cfo); int sign; @@ -4202,15 +4431,17 @@ static void rtw89_phy_cfo_crystal_cap_adjust(struct rtw89_dev *rtwdev, } sign = curr_cfo > 0 ? 1 : -1; if (cfo_abs > CFO_TRK_STOP_TH_4) - crystal_cap += 7 * sign; - else if (cfo_abs > CFO_TRK_STOP_TH_3) - crystal_cap += 5 * sign; - else if (cfo_abs > CFO_TRK_STOP_TH_2) crystal_cap += 3 * sign; + else if (cfo_abs > CFO_TRK_STOP_TH_3) + crystal_cap += 3 * sign; + else if (cfo_abs > CFO_TRK_STOP_TH_2) + crystal_cap += 1 * sign; else if (cfo_abs > CFO_TRK_STOP_TH_1) crystal_cap += 1 * sign; else return; + + crystal_cap = clamp(crystal_cap, 0, 127); rtw89_phy_cfo_set_crystal_cap(rtwdev, (u8)crystal_cap, false); rtw89_debug(rtwdev, RTW89_DBG_CFO, "X_cap{Curr,Default}={0x%x,0x%x}\n", @@ -6310,6 +6541,12 @@ void rtw89_phy_dm_init(struct rtw89_dev *rtwdev) rtw89_chip_cfg_txrx_path(rtwdev); } +void rtw89_phy_dm_reinit(struct rtw89_dev *rtwdev) +{ + rtw89_phy_env_monitor_init(rtwdev); + rtw89_physts_parsing_init(rtwdev); +} + void rtw89_phy_set_bss_color(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link) { diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h index c683f4d7d29b..08b635c93ac3 100644 --- a/drivers/net/wireless/realtek/rtw89/phy.h +++ b/drivers/net/wireless/realtek/rtw89/phy.h @@ -51,13 +51,17 @@ #define RA_MASK_EHT_2SS_RATES GENMASK_ULL(43, 28) #define RA_MASK_EHT_3SS_RATES GENMASK_ULL(59, 44) #define RA_MASK_EHT_4SS_RATES GENMASK_ULL(62, 60) +#define RA_MASK_EHT_1SS_MCS0_11 GENMASK_ULL(23, 12) +#define RA_MASK_EHT_2SS_MCS0_11 GENMASK_ULL(39, 28) +#define RA_MASK_EHT_3SS_MCS0_11 GENMASK_ULL(55, 44) +#define RA_MASK_EHT_4SS_MCS0_11 GENMASK_ULL(62, 60) #define RA_MASK_EHT_RATES GENMASK_ULL(62, 12) #define CFO_TRK_ENABLE_TH (2 << 2) #define CFO_TRK_STOP_TH_4 (30 << 2) #define CFO_TRK_STOP_TH_3 (20 << 2) #define CFO_TRK_STOP_TH_2 (10 << 2) -#define CFO_TRK_STOP_TH_1 (00 << 2) +#define CFO_TRK_STOP_TH_1 (03 << 2) #define CFO_TRK_STOP_TH (2 << 2) #define CFO_SW_COMP_FINE_TUNE (2 << 2) #define CFO_PERIOD_CNT 15 @@ -151,6 +155,7 @@ enum rtw89_phy_c2h_rfk_log_func { enum rtw89_phy_c2h_rfk_report_func { RTW89_PHY_C2H_RFK_REPORT_FUNC_STATE = 0, + RTW89_PHY_C2H_RFK_LOG_TAS_PWR = 6, }; enum rtw89_phy_c2h_dm_func { @@ -813,6 +818,7 @@ void rtw89_phy_config_rf_reg_v1(struct rtw89_dev *rtwdev, enum rtw89_rf_path rf_path, void *extra_data); void rtw89_phy_dm_init(struct rtw89_dev *rtwdev); +void rtw89_phy_dm_reinit(struct rtw89_dev *rtwdev); void rtw89_phy_write32_idx(struct rtw89_dev *rtwdev, u32 addr, u32 mask, u32 data, enum rtw89_phy_idx phy_idx); void rtw89_phy_write32_idx_set(struct rtw89_dev *rtwdev, u32 addr, u32 bits, @@ -826,6 +832,11 @@ s8 *rtw89_phy_raw_byr_seek(struct rtw89_dev *rtwdev, const struct rtw89_rate_desc *desc); s8 rtw89_phy_read_txpwr_byrate(struct rtw89_dev *rtwdev, u8 band, u8 bw, const struct rtw89_rate_desc *rate_desc); +void rtw89_phy_ant_gain_init(struct rtw89_dev *rtwdev); +s16 rtw89_phy_ant_gain_pwr_offset(struct rtw89_dev *rtwdev, + const struct rtw89_chan *chan); +void rtw89_print_ant_gain(struct seq_file *m, struct rtw89_dev *rtwdev, + const struct rtw89_chan *chan); void rtw89_phy_load_txpwr_byrate(struct rtw89_dev *rtwdev, const struct rtw89_txpwr_table *tbl); s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band, @@ -896,10 +907,34 @@ void rtw89_phy_set_txpwr_limit_ru(struct rtw89_dev *rtwdev, phy->set_txpwr_limit_ru(rtwdev, chan, phy_idx); } +static inline s8 rtw89_phy_txpwr_rf_to_bb(struct rtw89_dev *rtwdev, s8 txpwr_rf) +{ + const struct rtw89_chip_info *chip = rtwdev->chip; + + return txpwr_rf << (chip->txpwr_factor_bb - chip->txpwr_factor_rf); +} + +static inline s8 rtw89_phy_txpwr_rf_to_mac(struct rtw89_dev *rtwdev, s8 txpwr_rf) +{ + const struct rtw89_chip_info *chip = rtwdev->chip; + + return txpwr_rf >> (chip->txpwr_factor_rf - chip->txpwr_factor_mac); +} + +static inline s8 rtw89_phy_txpwr_dbm_to_mac(struct rtw89_dev *rtwdev, s8 dbm) +{ + const struct rtw89_chip_info *chip = rtwdev->chip; + + return clamp_t(s16, dbm << chip->txpwr_factor_mac, -64, 63); +} + void rtw89_phy_ra_assoc(struct rtw89_dev *rtwdev, struct rtw89_sta_link *rtwsta_link); void rtw89_phy_ra_update(struct rtw89_dev *rtwdev); void rtw89_phy_ra_update_sta(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta, u32 changed); +void rtw89_phy_ra_update_sta_link(struct rtw89_dev *rtwdev, + struct rtw89_sta_link *rtwsta_link, + u32 changed); void rtw89_phy_rate_pattern_vif(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, const struct cfg80211_bitrate_mask *mask); diff --git a/drivers/net/wireless/realtek/rtw89/ps.c b/drivers/net/wireless/realtek/rtw89/ps.c index c1c12abc2ea9..96ea04d90cd3 100644 --- a/drivers/net/wireless/realtek/rtw89/ps.c +++ b/drivers/net/wireless/realtek/rtw89/ps.c @@ -8,6 +8,7 @@ #include "debug.h" #include "fw.h" #include "mac.h" +#include "phy.h" #include "ps.h" #include "reg.h" #include "util.h" @@ -62,11 +63,8 @@ static void rtw89_ps_power_mode_change(struct rtw89_dev *rtwdev, bool enter) rtw89_mac_power_mode_change(rtwdev, enter); } -void __rtw89_enter_ps_mode(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link) +void __rtw89_enter_ps_mode(struct rtw89_dev *rtwdev) { - if (rtwvif_link->wifi_role == RTW89_WIFI_ROLE_P2P_CLIENT) - return; - if (!rtwdev->ps_mode) return; @@ -85,8 +83,8 @@ void __rtw89_leave_ps_mode(struct rtw89_dev *rtwdev) rtw89_ps_power_mode_change(rtwdev, false); } -static void __rtw89_enter_lps(struct rtw89_dev *rtwdev, - struct rtw89_vif_link *rtwvif_link) +static void __rtw89_enter_lps_link(struct rtw89_dev *rtwdev, + struct rtw89_vif_link *rtwvif_link) { struct rtw89_lps_parm lps_param = { .macid = rtwvif_link->mac_id, @@ -96,7 +94,6 @@ static void __rtw89_enter_lps(struct rtw89_dev *rtwdev, rtw89_btc_ntfy_radio_state(rtwdev, BTC_RFCTRL_FW_CTRL); rtw89_fw_h2c_lps_parm(rtwdev, &lps_param); - rtw89_fw_h2c_lps_ch_info(rtwdev, rtwvif_link); } static void __rtw89_leave_lps(struct rtw89_dev *rtwdev, @@ -121,17 +118,32 @@ void rtw89_leave_ps_mode(struct rtw89_dev *rtwdev) __rtw89_leave_ps_mode(rtwdev); } -void rtw89_enter_lps(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link, +void rtw89_enter_lps(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, bool ps_mode) { + struct rtw89_vif_link *rtwvif_link; + bool can_ps_mode = true; + unsigned int link_id; + lockdep_assert_held(&rtwdev->mutex); if (test_and_set_bit(RTW89_FLAG_LEISURE_PS, rtwdev->flags)) return; - __rtw89_enter_lps(rtwdev, rtwvif_link); - if (ps_mode) - __rtw89_enter_ps_mode(rtwdev, rtwvif_link); + rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id) { + __rtw89_enter_lps_link(rtwdev, rtwvif_link); + + if (rtwvif_link->wifi_role == RTW89_WIFI_ROLE_P2P_CLIENT) + can_ps_mode = false; + } + + if (RTW89_CHK_FW_FEATURE(LPS_CH_INFO, &rtwdev->fw)) + rtw89_fw_h2c_lps_ch_info(rtwdev, rtwvif); + else + rtw89_fw_h2c_lps_ml_cmn_info(rtwdev, rtwvif); + + if (ps_mode && can_ps_mode) + __rtw89_enter_ps_mode(rtwdev); } static void rtw89_leave_lps_vif(struct rtw89_dev *rtwdev, @@ -157,6 +169,8 @@ void rtw89_leave_lps(struct rtw89_dev *rtwdev) __rtw89_leave_ps_mode(rtwdev); + rtw89_phy_dm_reinit(rtwdev); + rtw89_for_each_rtwvif(rtwdev, rtwvif) rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id) rtw89_leave_lps_vif(rtwdev, rtwvif_link); @@ -282,12 +296,6 @@ void rtw89_recalc_lps(struct rtw89_dev *rtwdev) enum rtw89_entity_mode mode; int count = 0; - /* FIXME: Fix rtw89_enter_lps() and __rtw89_enter_ps_mode() - * to take MLO cases into account before doing the following. - */ - if (rtwdev->support_mlo) - goto disable_lps; - mode = rtw89_get_entity_mode(rtwdev); if (mode == RTW89_ENTITY_MODE_MCC) goto disable_lps; diff --git a/drivers/net/wireless/realtek/rtw89/ps.h b/drivers/net/wireless/realtek/rtw89/ps.h index cdd712966b09..2b88f254a32d 100644 --- a/drivers/net/wireless/realtek/rtw89/ps.h +++ b/drivers/net/wireless/realtek/rtw89/ps.h @@ -5,11 +5,11 @@ #ifndef __RTW89_PS_H_ #define __RTW89_PS_H_ -void rtw89_enter_lps(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link, +void rtw89_enter_lps(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, bool ps_mode); void rtw89_leave_lps(struct rtw89_dev *rtwdev); void __rtw89_leave_ps_mode(struct rtw89_dev *rtwdev); -void __rtw89_enter_ps_mode(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link); +void __rtw89_enter_ps_mode(struct rtw89_dev *rtwdev); void rtw89_leave_ps_mode(struct rtw89_dev *rtwdev); void rtw89_enter_ips(struct rtw89_dev *rtwdev); void rtw89_leave_ips(struct rtw89_dev *rtwdev); diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h index 18ec7c0252fb..10d0efa7a58e 100644 --- a/drivers/net/wireless/realtek/rtw89/reg.h +++ b/drivers/net/wireless/realtek/rtw89/reg.h @@ -7447,6 +7447,10 @@ #define B_BE_CSIPRT_HESU_AID_EN BIT(25) #define B_BE_CSIPRT_VHTSU_AID_EN BIT(24) +#define R_BE_DRV_INFO_OPTION 0x11470 +#define R_BE_DRV_INFO_OPTION_C1 0x15470 +#define B_BE_DRV_INFO_PHYRPT_EN BIT(0) + #define R_BE_RX_ERR_ISR 0x114F4 #define R_BE_RX_ERR_ISR_C1 0x154F4 #define B_BE_RX_ERR_TRIG_ACT_TO BIT(9) diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c index cad5189708e7..80b2f74589eb 100644 --- a/drivers/net/wireless/realtek/rtw89/regd.c +++ b/drivers/net/wireless/realtek/rtw89/regd.c @@ -17,7 +17,7 @@ static const struct rtw89_regd rtw89_ww_regd = static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("AR", RTW89_MEXICO, RTW89_MEXICO, RTW89_FCC), - COUNTRY_REGD("BO", RTW89_FCC, RTW89_FCC, RTW89_FCC), + COUNTRY_REGD("BO", RTW89_FCC, RTW89_FCC, RTW89_NA), COUNTRY_REGD("BR", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("CL", RTW89_CHILE, RTW89_CHILE, RTW89_CHILE), COUNTRY_REGD("CO", RTW89_FCC, RTW89_FCC, RTW89_FCC), @@ -35,7 +35,7 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("UY", RTW89_FCC, RTW89_FCC, RTW89_NA), COUNTRY_REGD("VE", RTW89_FCC, RTW89_FCC, RTW89_NA), COUNTRY_REGD("PR", RTW89_FCC, RTW89_FCC, RTW89_NA), - COUNTRY_REGD("DO", RTW89_FCC, RTW89_FCC, RTW89_NA), + COUNTRY_REGD("DO", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("AT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("BE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("CY", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), @@ -72,7 +72,7 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("BA", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("BG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("HR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), - COUNTRY_REGD("EG", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("EG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("GH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("IQ", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("IL", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), @@ -82,13 +82,13 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("KW", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("KG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("LB", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), - COUNTRY_REGD("LS", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("LS", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("MK", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("MA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), - COUNTRY_REGD("MZ", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("MZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("NA", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("NG", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("OM", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("NG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), + COUNTRY_REGD("OM", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("QA", RTW89_QATAR, RTW89_QATAR, RTW89_QATAR), COUNTRY_REGD("RO", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("RU", RTW89_ETSI, RTW89_ETSI, RTW89_NA), @@ -101,7 +101,7 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("UA", RTW89_UKRAINE, RTW89_UKRAINE, RTW89_UKRAINE), COUNTRY_REGD("AE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("YE", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("ZW", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("ZW", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("BD", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("KH", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("CN", RTW89_CN, RTW89_CN, RTW89_CN), @@ -110,12 +110,12 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("ID", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("KR", RTW89_KCC, RTW89_KCC, RTW89_KCC), COUNTRY_REGD("MY", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), - COUNTRY_REGD("PK", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("PH", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("PK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), + COUNTRY_REGD("PH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("SG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("LK", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("TW", RTW89_FCC, RTW89_FCC, RTW89_ETSI), - COUNTRY_REGD("TH", RTW89_ETSI, RTW89_ETSI, RTW89_THAILAND), + COUNTRY_REGD("TH", RTW89_THAILAND, RTW89_THAILAND, RTW89_THAILAND), COUNTRY_REGD("VN", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("AU", RTW89_ACMA, RTW89_ACMA, RTW89_ACMA), COUNTRY_REGD("NZ", RTW89_ACMA, RTW89_ACMA, RTW89_ACMA), @@ -158,9 +158,9 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("TD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("CX", RTW89_ACMA, RTW89_ACMA, RTW89_NA), COUNTRY_REGD("CC", RTW89_ACMA, RTW89_ACMA, RTW89_NA), - COUNTRY_REGD("KM", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), - COUNTRY_REGD("CG", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("CD", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("KM", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("CG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), + COUNTRY_REGD("CD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("CK", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("CI", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("DJ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), @@ -176,12 +176,12 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("TF", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("GA", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("GM", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), - COUNTRY_REGD("GE", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("GI", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("GE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), + COUNTRY_REGD("GI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("GL", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("GD", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("GP", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("GU", RTW89_FCC, RTW89_FCC, RTW89_NA), + COUNTRY_REGD("GU", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("GG", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("GN", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("GW", RTW89_ETSI, RTW89_ETSI, RTW89_NA), @@ -194,19 +194,19 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("KI", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("XK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("LA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), - COUNTRY_REGD("LR", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("LR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("LY", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("MO", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("MG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("MW", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("MV", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("ML", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("MH", RTW89_FCC, RTW89_FCC, RTW89_NA), + COUNTRY_REGD("MH", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("MQ", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("MR", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("MU", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("YT", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("FM", RTW89_FCC, RTW89_FCC, RTW89_NA), + COUNTRY_REGD("FM", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("MD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("MN", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("MS", RTW89_ETSI, RTW89_ETSI, RTW89_NA), @@ -216,15 +216,15 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("NE", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("NU", RTW89_ACMA, RTW89_ACMA, RTW89_NA), COUNTRY_REGD("NF", RTW89_ACMA, RTW89_ACMA, RTW89_NA), - COUNTRY_REGD("MP", RTW89_FCC, RTW89_FCC, RTW89_NA), - COUNTRY_REGD("PW", RTW89_FCC, RTW89_FCC, RTW89_NA), + COUNTRY_REGD("MP", RTW89_FCC, RTW89_FCC, RTW89_FCC), + COUNTRY_REGD("PW", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("RE", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("RW", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("SH", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("KN", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("LC", RTW89_FCC, RTW89_FCC, RTW89_FCC), - COUNTRY_REGD("MF", RTW89_FCC, RTW89_FCC, RTW89_NA), - COUNTRY_REGD("SX", RTW89_FCC, RTW89_FCC, RTW89_NA), + COUNTRY_REGD("MF", RTW89_FCC, RTW89_FCC, RTW89_FCC), + COUNTRY_REGD("SX", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("PM", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("VC", RTW89_FCC, RTW89_FCC, RTW89_NA), COUNTRY_REGD("WS", RTW89_FCC, RTW89_FCC, RTW89_NA), @@ -237,9 +237,9 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("GS", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("SR", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("SJ", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("SZ", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("SZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("TJ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), - COUNTRY_REGD("TZ", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("TZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("TG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("TK", RTW89_ACMA, RTW89_ACMA, RTW89_NA), COUNTRY_REGD("TO", RTW89_ETSI, RTW89_ETSI, RTW89_NA), @@ -247,13 +247,16 @@ static const struct rtw89_regd rtw89_regd_map[] = { COUNTRY_REGD("TC", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("TV", RTW89_ETSI, RTW89_NA, RTW89_NA), COUNTRY_REGD("UG", RTW89_ETSI, RTW89_ETSI, RTW89_NA), - COUNTRY_REGD("VI", RTW89_FCC, RTW89_FCC, RTW89_NA), + COUNTRY_REGD("VI", RTW89_FCC, RTW89_FCC, RTW89_FCC), COUNTRY_REGD("UZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI), COUNTRY_REGD("VU", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("WF", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("EH", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("ZM", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("CU", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("IR", RTW89_ETSI, RTW89_ETSI, RTW89_NA), + COUNTRY_REGD("SY", RTW89_ETSI, RTW89_NA, RTW89_NA), + COUNTRY_REGD("SD", RTW89_ETSI, RTW89_ETSI, RTW89_NA), COUNTRY_REGD("PS", RTW89_ETSI, RTW89_ETSI, RTW89_NA), }; diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c index 68c67a763f4d..c56f70267882 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c @@ -2298,7 +2298,8 @@ static void rtw8851b_query_ppdu(struct rtw89_dev *rtwdev, u8 path; u8 *rx_power = phy_ppdu->rssi; - status->signal = RTW89_RSSI_RAW_TO_DBM(rx_power[RF_PATH_A]); + if (!status->signal) + status->signal = RTW89_RSSI_RAW_TO_DBM(rx_power[RF_PATH_A]); for (path = 0; path < rtwdev->chip->rf_path_num; path++) { status->chains |= BIT(path); @@ -2391,6 +2392,7 @@ static const struct rtw89_chip_ops rtw8851b_chip_ops = { .ctrl_btg_bt_rx = rtw8851b_ctrl_btg_bt_rx, .query_ppdu = rtw8851b_query_ppdu, .convert_rpl_to_rssi = NULL, + .phy_rpt_to_rssi = NULL, .ctrl_nbtg_bt_tx = rtw8851b_ctrl_nbtg_bt_tx, .cfg_txrx_path = rtw8851b_bb_cfg_txrx_path, .set_txpwr_ul_tb_offset = rtw8851b_set_txpwr_ul_tb_offset, @@ -2464,6 +2466,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = { .nctl_post_table = &rtw8851b_nctl_post_defs_tbl, .dflt_parms = &rtw89_8851b_dflt_parms, .rfe_parms_conf = rtw89_8851b_rfe_parms_conf, + .txpwr_factor_bb = 3, .txpwr_factor_rf = 2, .txpwr_factor_mac = 1, .dig_table = NULL, @@ -2479,6 +2482,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = { BIT(NL80211_CHAN_WIDTH_40) | BIT(NL80211_CHAN_WIDTH_80), .support_unii4 = true, + .support_ant_gain = false, .ul_tb_waveform_ctrl = true, .ul_tb_pwr_diff = false, .hw_sec_hdr = false, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c index 364e36354225..f72b3ac6f149 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c @@ -2199,7 +2199,7 @@ static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, if (dgain > 0x5fc || dgain < 0x556) { _dpk_one_shot(rtwdev, phy, path, D_SYNC); - dgain = _dpk_dgain_read(rtwdev); + _dpk_dgain_read(rtwdev); } if (agc_cnt == 0) { diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851be.c b/drivers/net/wireless/realtek/rtw89/rtw8851be.c index 651cbce1dd7e..5810af825242 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8851be.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8851be.c @@ -27,6 +27,7 @@ static const struct rtw89_pci_info rtw8851b_pci_info = { .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_6MS, .rx_ring_eq_is_full = false, .check_rx_tag = false, + .no_rxbd_fs = false, .init_cfg_reg = R_AX_PCIE_INIT_CFG1, .txhci_en_bit = B_AX_TXHCI_EN, @@ -66,6 +67,7 @@ static const struct rtw89_pci_info rtw8851b_pci_info = { static const struct rtw89_driver_info rtw89_8851be_info = { .chip = &rtw8851b_chip_info, + .variant = NULL, .quirks = NULL, .bus = { .pci = &rtw8851b_pci_info, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c index e647759ebd69..9bd2842c27d5 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c @@ -2068,7 +2068,9 @@ static void rtw8852a_query_ppdu(struct rtw89_dev *rtwdev, u8 path; u8 *rx_power = phy_ppdu->rssi; - status->signal = RTW89_RSSI_RAW_TO_DBM(max(rx_power[RF_PATH_A], rx_power[RF_PATH_B])); + if (!status->signal) + status->signal = RTW89_RSSI_RAW_TO_DBM(max(rx_power[RF_PATH_A], + rx_power[RF_PATH_B])); for (path = 0; path < rtwdev->chip->rf_path_num; path++) { status->chains |= BIT(path); status->chain_signal[path] = RTW89_RSSI_RAW_TO_DBM(rx_power[path]); @@ -2116,6 +2118,7 @@ static const struct rtw89_chip_ops rtw8852a_chip_ops = { .ctrl_btg_bt_rx = rtw8852a_ctrl_btg_bt_rx, .query_ppdu = rtw8852a_query_ppdu, .convert_rpl_to_rssi = NULL, + .phy_rpt_to_rssi = NULL, .ctrl_nbtg_bt_tx = rtw8852a_ctrl_nbtg_bt_tx, .cfg_txrx_path = NULL, .set_txpwr_ul_tb_offset = rtw8852a_set_txpwr_ul_tb_offset, @@ -2181,6 +2184,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = { .nctl_post_table = NULL, .dflt_parms = &rtw89_8852a_dflt_parms, .rfe_parms_conf = NULL, + .txpwr_factor_bb = 3, .txpwr_factor_rf = 2, .txpwr_factor_mac = 1, .dig_table = &rtw89_8852a_phy_dig_table, @@ -2196,6 +2200,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = { BIT(NL80211_CHAN_WIDTH_40) | BIT(NL80211_CHAN_WIDTH_80), .support_unii4 = false, + .support_ant_gain = false, .ul_tb_waveform_ctrl = false, .ul_tb_pwr_diff = false, .hw_sec_hdr = false, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852ae.c b/drivers/net/wireless/realtek/rtw89/rtw8852ae.c index 701187d69e14..2037713e3952 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852ae.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852ae.c @@ -27,6 +27,7 @@ static const struct rtw89_pci_info rtw8852a_pci_info = { .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_6MS, .rx_ring_eq_is_full = false, .check_rx_tag = false, + .no_rxbd_fs = false, .init_cfg_reg = R_AX_PCIE_INIT_CFG1, .txhci_en_bit = B_AX_TXHCI_EN, @@ -64,6 +65,7 @@ static const struct rtw89_pci_info rtw8852a_pci_info = { static const struct rtw89_driver_info rtw89_8852ae_info = { .chip = &rtw8852a_chip_info, + .variant = NULL, .quirks = NULL, .bus = { .pci = &rtw8852a_pci_info, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c index 49a319128316..dfb2bf61b0b8 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c @@ -745,6 +745,7 @@ static const struct rtw89_chip_ops rtw8852b_chip_ops = { .ctrl_btg_bt_rx = rtw8852bx_ctrl_btg_bt_rx, .query_ppdu = rtw8852bx_query_ppdu, .convert_rpl_to_rssi = rtw8852bx_convert_rpl_to_rssi, + .phy_rpt_to_rssi = NULL, .ctrl_nbtg_bt_tx = rtw8852bx_ctrl_nbtg_bt_tx, .cfg_txrx_path = rtw8852bx_bb_cfg_txrx_path, .set_txpwr_ul_tb_offset = rtw8852bx_set_txpwr_ul_tb_offset, @@ -819,6 +820,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = { .nctl_post_table = NULL, .dflt_parms = &rtw89_8852b_dflt_parms, .rfe_parms_conf = NULL, + .txpwr_factor_bb = 3, .txpwr_factor_rf = 2, .txpwr_factor_mac = 1, .dig_table = NULL, @@ -834,6 +836,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = { BIT(NL80211_CHAN_WIDTH_40) | BIT(NL80211_CHAN_WIDTH_80), .support_unii4 = true, + .support_ant_gain = true, .ul_tb_waveform_ctrl = true, .ul_tb_pwr_diff = false, .hw_sec_hdr = false, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c index f4aa4437fb75..0e094ce9c9b0 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c @@ -1206,24 +1206,25 @@ void __rtw8852bx_set_channel_bb(struct rtw89_dev *rtwdev, const struct rtw89_cha } static u32 rtw8852bx_bb_cal_txpwr_ref(struct rtw89_dev *rtwdev, - enum rtw89_phy_idx phy_idx, s16 ref) + enum rtw89_phy_idx phy_idx, + s16 ref, u16 pwr_ofst_decrease) { const u16 tssi_16dbm_cw = 0x12c; const u8 base_cw_0db = 0x27; - const s8 ofst_int = 0; s16 pwr_s10_3; s16 rf_pwr_cw; u16 bb_pwr_cw; u32 pwr_cw; u32 tssi_ofst_cw; - pwr_s10_3 = (ref << 1) + (s16)(ofst_int) + (s16)(base_cw_0db << 3); + pwr_s10_3 = (ref << 1) + (s16)(base_cw_0db << 3) - pwr_ofst_decrease; bb_pwr_cw = u16_get_bits(pwr_s10_3, GENMASK(2, 0)); rf_pwr_cw = u16_get_bits(pwr_s10_3, GENMASK(8, 3)); rf_pwr_cw = clamp_t(s16, rf_pwr_cw, 15, 63); pwr_cw = (rf_pwr_cw << 3) | bb_pwr_cw; - tssi_ofst_cw = (u32)((s16)tssi_16dbm_cw + (ref << 1) - (16 << 3)); + tssi_ofst_cw = (u32)((s16)tssi_16dbm_cw + (ref << 1) - (16 << 3)) - + pwr_ofst_decrease; rtw89_debug(rtwdev, RTW89_DBG_TXPWR, "[TXPWR] tssi_ofst_cw=%d rf_cw=0x%x bb_cw=0x%x\n", tssi_ofst_cw, rf_pwr_cw, bb_pwr_cw); @@ -1234,10 +1235,11 @@ static u32 rtw8852bx_bb_cal_txpwr_ref(struct rtw89_dev *rtwdev, } static void rtw8852bx_set_txpwr_ref(struct rtw89_dev *rtwdev, - enum rtw89_phy_idx phy_idx) + enum rtw89_phy_idx phy_idx, s16 pwr_ofst) { static const u32 addr[RF_PATH_NUM_8852BX] = {0x5800, 0x7800}; const u32 mask = B_DPD_TSSI_CW | B_DPD_PWR_CW | B_DPD_REF; + u16 ofst_dec[RF_PATH_NUM_8852BX]; const u8 ofst_ofdm = 0x4; const u8 ofst_cck = 0x8; const s16 ref_ofdm = 0; @@ -1250,19 +1252,20 @@ static void rtw8852bx_set_txpwr_ref(struct rtw89_dev *rtwdev, rtw89_mac_txpwr_write32_mask(rtwdev, phy_idx, R_AX_PWR_RATE_CTRL, B_AX_PWR_REF, 0x0); - rtw89_debug(rtwdev, RTW89_DBG_TXPWR, "[TXPWR] set bb ofdm txpwr ref\n"); - val = rtw8852bx_bb_cal_txpwr_ref(rtwdev, phy_idx, ref_ofdm); + ofst_dec[RF_PATH_A] = pwr_ofst > 0 ? 0 : abs(pwr_ofst); + ofst_dec[RF_PATH_B] = pwr_ofst > 0 ? pwr_ofst : 0; - for (i = 0; i < RF_PATH_NUM_8852BX; i++) - rtw89_phy_write32_idx(rtwdev, addr[i] + ofst_ofdm, mask, val, - phy_idx); + rtw89_debug(rtwdev, RTW89_DBG_TXPWR, "[TXPWR] set bb ofdm txpwr ref\n"); + for (i = 0; i < RF_PATH_NUM_8852BX; i++) { + val = rtw8852bx_bb_cal_txpwr_ref(rtwdev, phy_idx, ref_ofdm, ofst_dec[i]); + rtw89_phy_write32_idx(rtwdev, addr[i] + ofst_ofdm, mask, val, phy_idx); + } rtw89_debug(rtwdev, RTW89_DBG_TXPWR, "[TXPWR] set bb cck txpwr ref\n"); - val = rtw8852bx_bb_cal_txpwr_ref(rtwdev, phy_idx, ref_cck); - - for (i = 0; i < RF_PATH_NUM_8852BX; i++) - rtw89_phy_write32_idx(rtwdev, addr[i] + ofst_cck, mask, val, - phy_idx); + for (i = 0; i < RF_PATH_NUM_8852BX; i++) { + val = rtw8852bx_bb_cal_txpwr_ref(rtwdev, phy_idx, ref_cck, ofst_dec[i]); + rtw89_phy_write32_idx(rtwdev, addr[i] + ofst_cck, mask, val, phy_idx); + } } static void rtw8852bx_bb_set_tx_shape_dfir(struct rtw89_dev *rtwdev, @@ -1333,6 +1336,16 @@ static void rtw8852bx_set_tx_shape(struct rtw89_dev *rtwdev, tx_shape_ofdm); } +static void rtw8852bx_set_txpwr_diff(struct rtw89_dev *rtwdev, + const struct rtw89_chan *chan, + enum rtw89_phy_idx phy_idx) +{ + s16 pwr_ofst; + + pwr_ofst = rtw89_phy_ant_gain_pwr_offset(rtwdev, chan); + rtw8852bx_set_txpwr_ref(rtwdev, phy_idx, pwr_ofst); +} + static void __rtw8852bx_set_txpwr(struct rtw89_dev *rtwdev, const struct rtw89_chan *chan, enum rtw89_phy_idx phy_idx) @@ -1342,12 +1355,13 @@ static void __rtw8852bx_set_txpwr(struct rtw89_dev *rtwdev, rtw8852bx_set_tx_shape(rtwdev, chan, phy_idx); rtw89_phy_set_txpwr_limit(rtwdev, chan, phy_idx); rtw89_phy_set_txpwr_limit_ru(rtwdev, chan, phy_idx); + rtw8852bx_set_txpwr_diff(rtwdev, chan, phy_idx); } static void __rtw8852bx_set_txpwr_ctrl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx) { - rtw8852bx_set_txpwr_ref(rtwdev, phy_idx); + rtw8852bx_set_txpwr_ref(rtwdev, phy_idx, 0); } static @@ -1936,7 +1950,9 @@ static void __rtw8852bx_query_ppdu(struct rtw89_dev *rtwdev, u8 path; u8 *rx_power = phy_ppdu->rssi; - status->signal = RTW89_RSSI_RAW_TO_DBM(max(rx_power[RF_PATH_A], rx_power[RF_PATH_B])); + if (!status->signal) + status->signal = RTW89_RSSI_RAW_TO_DBM(max(rx_power[RF_PATH_A], + rx_power[RF_PATH_B])); for (path = 0; path < rtwdev->chip->rf_path_num; path++) { status->chains |= BIT(path); status->chain_signal[path] = RTW89_RSSI_RAW_TO_DBM(rx_power[path]); diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852be.c b/drivers/net/wireless/realtek/rtw89/rtw8852be.c index a13ea1cce4a7..abdeafc14b0b 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852be.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852be.c @@ -27,6 +27,7 @@ static const struct rtw89_pci_info rtw8852b_pci_info = { .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_6MS, .rx_ring_eq_is_full = false, .check_rx_tag = false, + .no_rxbd_fs = false, .init_cfg_reg = R_AX_PCIE_INIT_CFG1, .txhci_en_bit = B_AX_TXHCI_EN, @@ -66,6 +67,7 @@ static const struct rtw89_pci_info rtw8852b_pci_info = { static const struct rtw89_driver_info rtw89_8852be_info = { .chip = &rtw8852b_chip_info, + .variant = NULL, .quirks = NULL, .bus = { .pci = &rtw8852b_pci_info, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c index 876725133228..bde3e1fb7ca6 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c @@ -679,6 +679,7 @@ static const struct rtw89_chip_ops rtw8852bt_chip_ops = { .ctrl_btg_bt_rx = rtw8852bx_ctrl_btg_bt_rx, .query_ppdu = rtw8852bx_query_ppdu, .convert_rpl_to_rssi = rtw8852bx_convert_rpl_to_rssi, + .phy_rpt_to_rssi = NULL, .ctrl_nbtg_bt_tx = rtw8852bx_ctrl_nbtg_bt_tx, .cfg_txrx_path = rtw8852bx_bb_cfg_txrx_path, .set_txpwr_ul_tb_offset = rtw8852bx_set_txpwr_ul_tb_offset, @@ -752,6 +753,7 @@ const struct rtw89_chip_info rtw8852bt_chip_info = { .nctl_post_table = NULL, .dflt_parms = NULL, .rfe_parms_conf = NULL, + .txpwr_factor_bb = 3, .txpwr_factor_rf = 2, .txpwr_factor_mac = 1, .dig_table = NULL, @@ -767,6 +769,7 @@ const struct rtw89_chip_info rtw8852bt_chip_info = { BIT(NL80211_CHAN_WIDTH_40) | BIT(NL80211_CHAN_WIDTH_80), .support_unii4 = true, + .support_ant_gain = true, .ul_tb_waveform_ctrl = true, .ul_tb_pwr_diff = false, .hw_sec_hdr = false, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bte.c b/drivers/net/wireless/realtek/rtw89/rtw8852bte.c index e4f40c2e287d..b69fa17beb33 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852bte.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852bte.c @@ -9,6 +9,12 @@ #include "reg.h" #include "rtw8852bt.h" +static const struct rtw89_pci_ssid_quirk rtw8852bt_pci_ssid_quirks[] = { + {RTW89_PCI_SSID(PCI_VENDOR_ID_REALTEK, 0xB520, 0x103C, 0x88E9, HP), + .bitmap = BIT(RTW89_QUIRK_THERMAL_PROT_110C)}, + {}, +}; + static const struct rtw89_pci_info rtw8852bt_pci_info = { .gen_def = &rtw89_pci_gen_ax, .txbd_trunc_mode = MAC_AX_BD_TRUNC, @@ -27,6 +33,7 @@ static const struct rtw89_pci_info rtw8852bt_pci_info = { .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_6MS, .rx_ring_eq_is_full = false, .check_rx_tag = false, + .no_rxbd_fs = false, .init_cfg_reg = R_AX_PCIE_INIT_CFG1, .txhci_en_bit = B_AX_TXHCI_EN, @@ -61,11 +68,12 @@ static const struct rtw89_pci_info rtw8852bt_pci_info = { .disable_intr = rtw89_pci_disable_intr, .recognize_intrs = rtw89_pci_recognize_intrs, - .ssid_quirks = NULL, + .ssid_quirks = rtw8852bt_pci_ssid_quirks, }; static const struct rtw89_driver_info rtw89_8852bte_info = { .chip = &rtw8852bt_chip_info, + .variant = NULL, .quirks = NULL, .bus = { .pci = &rtw8852bt_pci_info, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c index cde34f8e1e67..bc84b15e7826 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c @@ -1882,9 +1882,9 @@ static void rtw8852c_rfk_track(struct rtw89_dev *rtwdev) } static u32 rtw8852c_bb_cal_txpwr_ref(struct rtw89_dev *rtwdev, - enum rtw89_phy_idx phy_idx, s16 ref) + enum rtw89_phy_idx phy_idx, + s16 ref, u16 pwr_ofst_decrease) { - s8 ofst_int = 0; u8 base_cw_0db = 0x27; u16 tssi_16dbm_cw = 0x12c; s16 pwr_s10_3 = 0; @@ -1893,13 +1893,14 @@ static u32 rtw8852c_bb_cal_txpwr_ref(struct rtw89_dev *rtwdev, u32 pwr_cw = 0; u32 tssi_ofst_cw = 0; - pwr_s10_3 = (ref << 1) + (s16)(ofst_int) + (s16)(base_cw_0db << 3); + pwr_s10_3 = (ref << 1) + (s16)(base_cw_0db << 3) - pwr_ofst_decrease; bb_pwr_cw = FIELD_GET(GENMASK(2, 0), pwr_s10_3); rf_pwr_cw = FIELD_GET(GENMASK(8, 3), pwr_s10_3); rf_pwr_cw = clamp_t(s16, rf_pwr_cw, 15, 63); pwr_cw = (rf_pwr_cw << 3) | bb_pwr_cw; - tssi_ofst_cw = (u32)((s16)tssi_16dbm_cw + (ref << 1) - (16 << 3)); + tssi_ofst_cw = (u32)((s16)tssi_16dbm_cw + (ref << 1) - (16 << 3)) - + pwr_ofst_decrease; rtw89_debug(rtwdev, RTW89_DBG_TXPWR, "[TXPWR] tssi_ofst_cw=%d rf_cw=0x%x bb_cw=0x%x\n", tssi_ofst_cw, rf_pwr_cw, bb_pwr_cw); @@ -1943,9 +1944,10 @@ void rtw8852c_set_txpwr_ul_tb_offset(struct rtw89_dev *rtwdev, } static void rtw8852c_set_txpwr_ref(struct rtw89_dev *rtwdev, - enum rtw89_phy_idx phy_idx) + enum rtw89_phy_idx phy_idx, s16 pwr_ofst) { static const u32 addr[RF_PATH_NUM_8852C] = {0x5800, 0x7800}; + u16 ofst_dec[RF_PATH_NUM_8852C]; const u32 mask = 0x7FFFFFF; const u8 ofst_ofdm = 0x4; const u8 ofst_cck = 0x8; @@ -1959,19 +1961,20 @@ static void rtw8852c_set_txpwr_ref(struct rtw89_dev *rtwdev, rtw89_mac_txpwr_write32_mask(rtwdev, phy_idx, R_AX_PWR_RATE_CTRL, GENMASK(27, 10), 0x0); - rtw89_debug(rtwdev, RTW89_DBG_TXPWR, "[TXPWR] set bb ofdm txpwr ref\n"); - val = rtw8852c_bb_cal_txpwr_ref(rtwdev, phy_idx, ref_ofdm); + ofst_dec[RF_PATH_A] = pwr_ofst > 0 ? 0 : abs(pwr_ofst); + ofst_dec[RF_PATH_B] = pwr_ofst > 0 ? pwr_ofst : 0; - for (i = 0; i < RF_PATH_NUM_8852C; i++) - rtw89_phy_write32_idx(rtwdev, addr[i] + ofst_ofdm, mask, val, - phy_idx); + rtw89_debug(rtwdev, RTW89_DBG_TXPWR, "[TXPWR] set bb ofdm txpwr ref\n"); + for (i = 0; i < RF_PATH_NUM_8852C; i++) { + val = rtw8852c_bb_cal_txpwr_ref(rtwdev, phy_idx, ref_ofdm, ofst_dec[i]); + rtw89_phy_write32_idx(rtwdev, addr[i] + ofst_ofdm, mask, val, phy_idx); + } rtw89_debug(rtwdev, RTW89_DBG_TXPWR, "[TXPWR] set bb cck txpwr ref\n"); - val = rtw8852c_bb_cal_txpwr_ref(rtwdev, phy_idx, ref_cck); - - for (i = 0; i < RF_PATH_NUM_8852C; i++) - rtw89_phy_write32_idx(rtwdev, addr[i] + ofst_cck, mask, val, - phy_idx); + for (i = 0; i < RF_PATH_NUM_8852C; i++) { + val = rtw8852c_bb_cal_txpwr_ref(rtwdev, phy_idx, ref_cck, ofst_dec[i]); + rtw89_phy_write32_idx(rtwdev, addr[i] + ofst_cck, mask, val, phy_idx); + } } static void rtw8852c_bb_set_tx_shape_dfir(struct rtw89_dev *rtwdev, @@ -2052,6 +2055,16 @@ static void rtw8852c_set_tx_shape(struct rtw89_dev *rtwdev, B_P1_DAC_COMP_POST_DPD_EN); } +static void rtw8852c_set_txpwr_diff(struct rtw89_dev *rtwdev, + const struct rtw89_chan *chan, + enum rtw89_phy_idx phy_idx) +{ + s16 pwr_ofst; + + pwr_ofst = rtw89_phy_ant_gain_pwr_offset(rtwdev, chan); + rtw8852c_set_txpwr_ref(rtwdev, phy_idx, pwr_ofst); +} + static void rtw8852c_set_txpwr(struct rtw89_dev *rtwdev, const struct rtw89_chan *chan, enum rtw89_phy_idx phy_idx) @@ -2061,12 +2074,13 @@ static void rtw8852c_set_txpwr(struct rtw89_dev *rtwdev, rtw8852c_set_tx_shape(rtwdev, chan, phy_idx); rtw89_phy_set_txpwr_limit(rtwdev, chan, phy_idx); rtw89_phy_set_txpwr_limit_ru(rtwdev, chan, phy_idx); + rtw8852c_set_txpwr_diff(rtwdev, chan, phy_idx); } static void rtw8852c_set_txpwr_ctrl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx) { - rtw8852c_set_txpwr_ref(rtwdev, phy_idx); + rtw8852c_set_txpwr_ref(rtwdev, phy_idx, 0); } static void @@ -2793,7 +2807,10 @@ static void rtw8852c_query_ppdu(struct rtw89_dev *rtwdev, u8 path; u8 *rx_power = phy_ppdu->rssi; - status->signal = RTW89_RSSI_RAW_TO_DBM(max(rx_power[RF_PATH_A], rx_power[RF_PATH_B])); + if (!status->signal) + status->signal = RTW89_RSSI_RAW_TO_DBM(max(rx_power[RF_PATH_A], + rx_power[RF_PATH_B])); + for (path = 0; path < rtwdev->chip->rf_path_num; path++) { status->chains |= BIT(path); status->chain_signal[path] = RTW89_RSSI_RAW_TO_DBM(rx_power[path]); @@ -2893,6 +2910,7 @@ static const struct rtw89_chip_ops rtw8852c_chip_ops = { .ctrl_btg_bt_rx = rtw8852c_ctrl_btg_bt_rx, .query_ppdu = rtw8852c_query_ppdu, .convert_rpl_to_rssi = NULL, + .phy_rpt_to_rssi = NULL, .ctrl_nbtg_bt_tx = rtw8852c_ctrl_nbtg_bt_tx, .cfg_txrx_path = rtw8852c_bb_cfg_txrx_path, .set_txpwr_ul_tb_offset = rtw8852c_set_txpwr_ul_tb_offset, @@ -2959,6 +2977,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = { .dflt_parms = &rtw89_8852c_dflt_parms, .rfe_parms_conf = NULL, .chanctx_listener = &rtw8852c_chanctx_listener, + .txpwr_factor_bb = 3, .txpwr_factor_rf = 2, .txpwr_factor_mac = 1, .dig_table = NULL, @@ -2976,6 +2995,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = { BIT(NL80211_CHAN_WIDTH_80) | BIT(NL80211_CHAN_WIDTH_160), .support_unii4 = true, + .support_ant_gain = true, .ul_tb_waveform_ctrl = false, .ul_tb_pwr_diff = true, .hw_sec_hdr = true, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c index bd17c0a1c684..b92e2ce4f4ad 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c @@ -1769,10 +1769,10 @@ u8 _rx_dck_channel_calc(struct rtw89_dev *rtwdev, const struct rtw89_chan *chan) target_ch = chan->channel - 33; } } else if (chan->band_type == RTW89_BAND_6G) { - if (chan->channel >= 1 && chan->channel <= 125) - target_ch = chan->channel + 32; - else + if (chan->channel > 125) target_ch = chan->channel - 32; + else + target_ch = chan->channel + 32; } else { target_ch = chan->channel; } diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852ce.c b/drivers/net/wireless/realtek/rtw89/rtw8852ce.c index 1a46878be96b..5d864fd5974e 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852ce.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852ce.c @@ -36,6 +36,7 @@ static const struct rtw89_pci_info rtw8852c_pci_info = { .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_6MS, .rx_ring_eq_is_full = false, .check_rx_tag = false, + .no_rxbd_fs = false, .init_cfg_reg = R_AX_HAXI_INIT_CFG1, .txhci_en_bit = B_AX_TXHCI_EN_V1, @@ -95,6 +96,7 @@ static const struct dmi_system_id rtw8852c_pci_quirks[] = { static const struct rtw89_driver_info rtw89_8852ce_info = { .chip = &rtw8852c_chip_info, + .variant = NULL, .quirks = rtw8852c_pci_quirks, .bus = { .pci = &rtw8852c_pci_info, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c index 9a4db04a1967..11d66bfceb15 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c @@ -14,7 +14,7 @@ #include "rtw8922a_rfk.h" #include "util.h" -#define RTW8922A_FW_FORMAT_MAX 2 +#define RTW8922A_FW_FORMAT_MAX 3 #define RTW8922A_FW_BASENAME "rtw89/rtw8922a_fw" #define RTW8922A_MODULE_FIRMWARE \ RTW8922A_FW_BASENAME "-" __stringify(RTW8922A_FW_FORMAT_MAX) ".bin" @@ -2565,8 +2565,10 @@ static void rtw8922a_query_ppdu(struct rtw89_dev *rtwdev, u8 path; u8 *rx_power = phy_ppdu->rssi; - status->signal = - RTW89_RSSI_RAW_TO_DBM(max(rx_power[RF_PATH_A], rx_power[RF_PATH_B])); + if (!status->signal) + status->signal = RTW89_RSSI_RAW_TO_DBM(max(rx_power[RF_PATH_A], + rx_power[RF_PATH_B])); + for (path = 0; path < rtwdev->chip->rf_path_num; path++) { status->chains |= BIT(path); status->chain_signal[path] = RTW89_RSSI_RAW_TO_DBM(rx_power[path]); @@ -2607,6 +2609,16 @@ static void rtw8922a_convert_rpl_to_rssi(struct rtw89_dev *rtwdev, phy_ppdu->rssi_avg = phy_ppdu->rpl_avg; } +static void rtw8922a_phy_rpt_to_rssi(struct rtw89_dev *rtwdev, + struct rtw89_rx_desc_info *desc_info, + struct ieee80211_rx_status *rx_status) +{ + if (desc_info->rssi <= 0x1 || (desc_info->rssi >> 2) > MAX_RSSI) + return; + + rx_status->signal = (desc_info->rssi >> 2) - MAX_RSSI; +} + static int rtw8922a_mac_enable_bb_rf(struct rtw89_dev *rtwdev) { rtw89_write8_set(rtwdev, R_BE_FEN_RST_ENABLE, @@ -2665,6 +2677,7 @@ static const struct rtw89_chip_ops rtw8922a_chip_ops = { .ctrl_btg_bt_rx = rtw8922a_ctrl_btg_bt_rx, .query_ppdu = rtw8922a_query_ppdu, .convert_rpl_to_rssi = rtw8922a_convert_rpl_to_rssi, + .phy_rpt_to_rssi = rtw8922a_phy_rpt_to_rssi, .ctrl_nbtg_bt_tx = rtw8922a_ctrl_nbtg_bt_tx, .cfg_txrx_path = rtw8922a_bb_cfg_txrx_path, .set_txpwr_ul_tb_offset = NULL, @@ -2729,6 +2742,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = { .nctl_post_table = NULL, .dflt_parms = NULL, /* load parm from fw */ .rfe_parms_conf = NULL, /* load parm from fw */ + .txpwr_factor_bb = 3, .txpwr_factor_rf = 2, .txpwr_factor_mac = 1, .dig_table = NULL, @@ -2746,6 +2760,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = { BIT(NL80211_CHAN_WIDTH_80) | BIT(NL80211_CHAN_WIDTH_160), .support_unii4 = true, + .support_ant_gain = false, .ul_tb_waveform_ctrl = false, .ul_tb_pwr_diff = false, .hw_sec_hdr = true, @@ -2823,6 +2838,12 @@ const struct rtw89_chip_info rtw8922a_chip_info = { }; EXPORT_SYMBOL(rtw8922a_chip_info); +const struct rtw89_chip_variant rtw8922ae_vs_variant = { + .no_mcs_12_13 = true, + .fw_min_ver_code = RTW89_FW_VER_CODE(0, 35, 54, 0), +}; +EXPORT_SYMBOL(rtw8922ae_vs_variant); + MODULE_FIRMWARE(RTW8922A_MODULE_FIRMWARE); MODULE_AUTHOR("Realtek Corporation"); MODULE_DESCRIPTION("Realtek 802.11be wireless 8922A driver"); diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.h b/drivers/net/wireless/realtek/rtw89/rtw8922a.h index 597317ab6af7..a29cfa5b4291 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8922a.h +++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.h @@ -69,5 +69,6 @@ struct rtw8922a_efuse { } __packed; extern const struct rtw89_chip_info rtw8922a_chip_info; +extern const struct rtw89_chip_variant rtw8922ae_vs_variant; #endif diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922ae.c b/drivers/net/wireless/realtek/rtw89/rtw8922ae.c index edfb1f220af0..0ea8d5281c10 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8922ae.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8922ae.c @@ -33,6 +33,7 @@ static const struct rtw89_pci_info rtw8922a_pci_info = { .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_DEF, .rx_ring_eq_is_full = true, .check_rx_tag = true, + .no_rxbd_fs = true, .init_cfg_reg = R_BE_HAXI_INIT_CFG1, .txhci_en_bit = B_BE_TXDMA_EN, @@ -70,6 +71,16 @@ static const struct rtw89_pci_info rtw8922a_pci_info = { static const struct rtw89_driver_info rtw89_8922ae_info = { .chip = &rtw8922a_chip_info, + .variant = NULL, + .quirks = NULL, + .bus = { + .pci = &rtw8922a_pci_info, + }, +}; + +static const struct rtw89_driver_info rtw89_8922ae_vs_info = { + .chip = &rtw8922a_chip_info, + .variant = &rtw8922ae_vs_variant, .quirks = NULL, .bus = { .pci = &rtw8922a_pci_info, @@ -81,6 +92,10 @@ static const struct pci_device_id rtw89_8922ae_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8922), .driver_data = (kernel_ulong_t)&rtw89_8922ae_info, }, + { + PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x892B), + .driver_data = (kernel_ulong_t)&rtw89_8922ae_vs_info, + }, {}, }; MODULE_DEVICE_TABLE(pci, rtw89_8922ae_id_table); @@ -95,5 +110,5 @@ static struct pci_driver rtw89_8922ae_driver = { module_pci_driver(rtw89_8922ae_driver); MODULE_AUTHOR("Realtek Corporation"); -MODULE_DESCRIPTION("Realtek 802.11be wireless 8922AE driver"); +MODULE_DESCRIPTION("Realtek 802.11be wireless 8922AE/8922AE-VS driver"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c index bcc287771b2a..871f45a6508c 100644 --- a/drivers/net/wireless/realtek/rtw89/sar.c +++ b/drivers/net/wireless/realtek/rtw89/sar.c @@ -42,7 +42,7 @@ static enum rtw89_sar_subband rtw89_sar_get_subband(struct rtw89_dev *rtwdev, /* freq 6875 (ch 185, 20MHz) spans RTW89_SAR_6GHZ_SUBBAND_7_H * and RTW89_SAR_6GHZ_SUBBAND_8, so directly describe it with - * struct rtw89_sar_span in the following. + * struct rtw89_6ghz_span. */ case 6895 ... 7115: @@ -50,63 +50,18 @@ static enum rtw89_sar_subband rtw89_sar_get_subband(struct rtw89_dev *rtwdev, } } -struct rtw89_sar_span { - enum rtw89_sar_subband subband_low; - enum rtw89_sar_subband subband_high; -}; - -#define RTW89_SAR_SPAN_VALID(span) ((span)->subband_high) - -#define RTW89_SAR_6GHZ_SPAN_HEAD 6145 -#define RTW89_SAR_6GHZ_SPAN_IDX(center_freq) \ - ((((int)(center_freq) - RTW89_SAR_6GHZ_SPAN_HEAD) / 5) / 2) - -#define RTW89_DECL_SAR_6GHZ_SPAN(center_freq, subband_l, subband_h) \ - [RTW89_SAR_6GHZ_SPAN_IDX(center_freq)] = { \ - .subband_low = RTW89_SAR_6GHZ_ ## subband_l, \ - .subband_high = RTW89_SAR_6GHZ_ ## subband_h, \ - } - -/* Since 6GHz SAR subbands are not edge aligned, some cases span two SAR - * subbands. In the following, we describe each of them with rtw89_sar_span. - */ -static const struct rtw89_sar_span rtw89_sar_overlapping_6ghz[] = { - RTW89_DECL_SAR_6GHZ_SPAN(6145, SUBBAND_5_L, SUBBAND_5_H), - RTW89_DECL_SAR_6GHZ_SPAN(6165, SUBBAND_5_L, SUBBAND_5_H), - RTW89_DECL_SAR_6GHZ_SPAN(6185, SUBBAND_5_L, SUBBAND_5_H), - RTW89_DECL_SAR_6GHZ_SPAN(6505, SUBBAND_6, SUBBAND_7_L), - RTW89_DECL_SAR_6GHZ_SPAN(6525, SUBBAND_6, SUBBAND_7_L), - RTW89_DECL_SAR_6GHZ_SPAN(6545, SUBBAND_6, SUBBAND_7_L), - RTW89_DECL_SAR_6GHZ_SPAN(6665, SUBBAND_7_L, SUBBAND_7_H), - RTW89_DECL_SAR_6GHZ_SPAN(6705, SUBBAND_7_L, SUBBAND_7_H), - RTW89_DECL_SAR_6GHZ_SPAN(6825, SUBBAND_7_H, SUBBAND_8), - RTW89_DECL_SAR_6GHZ_SPAN(6865, SUBBAND_7_H, SUBBAND_8), - RTW89_DECL_SAR_6GHZ_SPAN(6875, SUBBAND_7_H, SUBBAND_8), - RTW89_DECL_SAR_6GHZ_SPAN(6885, SUBBAND_7_H, SUBBAND_8), -}; - static int rtw89_query_sar_config_common(struct rtw89_dev *rtwdev, u32 center_freq, s32 *cfg) { struct rtw89_sar_cfg_common *rtwsar = &rtwdev->sar.cfg_common; - const struct rtw89_sar_span *span = NULL; enum rtw89_sar_subband subband_l, subband_h; - int idx; + const struct rtw89_6ghz_span *span; - if (center_freq >= RTW89_SAR_6GHZ_SPAN_HEAD) { - idx = RTW89_SAR_6GHZ_SPAN_IDX(center_freq); - /* To decrease size of rtw89_sar_overlapping_6ghz[], - * RTW89_SAR_6GHZ_SPAN_IDX() truncates the leading NULLs - * to make first span as index 0 of the table. So, if center - * frequency is less than the first one, it will get netative. - */ - if (idx >= 0 && idx < ARRAY_SIZE(rtw89_sar_overlapping_6ghz)) - span = &rtw89_sar_overlapping_6ghz[idx]; - } + span = rtw89_get_6ghz_span(rtwdev, center_freq); if (span && RTW89_SAR_SPAN_VALID(span)) { - subband_l = span->subband_low; - subband_h = span->subband_high; + subband_l = span->sar_subband_low; + subband_h = span->sar_subband_high; } else { subband_l = rtw89_sar_get_subband(rtwdev, center_freq); subband_h = subband_l; diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c index 7b203bb7f151..26a944d3b672 100644 --- a/drivers/net/wireless/realtek/rtw89/ser.c +++ b/drivers/net/wireless/realtek/rtw89/ser.c @@ -365,6 +365,7 @@ static void ser_reset_mac_binding(struct rtw89_dev *rtwdev) ser_reset_vif(rtwdev, rtwvif); rtwdev->total_sta_assoc = 0; + refcount_set(&rtwdev->refcount_ap_info, 0); } /* hal function */ diff --git a/drivers/net/wireless/realtek/rtw89/txrx.h b/drivers/net/wireless/realtek/rtw89/txrx.h index b2e47829983f..70fe7cebc9d5 100644 --- a/drivers/net/wireless/realtek/rtw89/txrx.h +++ b/drivers/net/wireless/realtek/rtw89/txrx.h @@ -560,6 +560,9 @@ struct rtw89_phy_sts_iehdr { #define BE_RXD_HDR_OFFSET_MASK GENMASK(20, 16) #define BE_RXD_WL_HD_IV_LEN_MASK GENMASK(26, 21) +/* BE RXD - PHY RPT dword0 */ +#define BE_RXD_PHY_RSSI GENMASK(11, 0) + struct rtw89_phy_sts_ie00 { __le32 w0; __le32 w1; diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c index 3e81fd974ec1..01754d031bb4 100644 --- a/drivers/net/wireless/realtek/rtw89/wow.c +++ b/drivers/net/wireless/realtek/rtw89/wow.c @@ -620,7 +620,10 @@ static struct ieee80211_key_conf *rtw89_wow_gtk_rekey(struct rtw89_dev *rtwdev, * need to unlock mutex */ mutex_unlock(&rtwdev->mutex); - key = ieee80211_gtk_rekey_add(wow_vif, rekey_conf, -1); + if (ieee80211_vif_is_mld(wow_vif)) + key = ieee80211_gtk_rekey_add(wow_vif, rekey_conf, rtwvif_link->link_id); + else + key = ieee80211_gtk_rekey_add(wow_vif, rekey_conf, -1); mutex_lock(&rtwdev->mutex); kfree(rekey_conf); @@ -691,9 +694,7 @@ static void rtw89_wow_leave_deep_ps(struct rtw89_dev *rtwdev) static void rtw89_wow_enter_deep_ps(struct rtw89_dev *rtwdev) { - struct rtw89_vif_link *rtwvif_link = rtwdev->wow.rtwvif_link; - - __rtw89_enter_ps_mode(rtwdev, rtwvif_link); + __rtw89_enter_ps_mode(rtwdev); } static void rtw89_wow_enter_ps(struct rtw89_dev *rtwdev) @@ -701,7 +702,7 @@ static void rtw89_wow_enter_ps(struct rtw89_dev *rtwdev) struct rtw89_vif_link *rtwvif_link = rtwdev->wow.rtwvif_link; if (rtw89_wow_mgd_linked(rtwdev)) - rtw89_enter_lps(rtwdev, rtwvif_link, false); + rtw89_enter_lps(rtwdev, rtwvif_link->rtwvif, false); else if (rtw89_wow_no_link(rtwdev)) rtw89_fw_h2c_fwips(rtwdev, rtwvif_link, true); } diff --git a/drivers/net/wireless/st/cw1200/cw1200_spi.c b/drivers/net/wireless/st/cw1200/cw1200_spi.c index 862964a8cc87..52386dfb5f4a 100644 --- a/drivers/net/wireless/st/cw1200/cw1200_spi.c +++ b/drivers/net/wireless/st/cw1200/cw1200_spi.c @@ -442,8 +442,8 @@ static void cw1200_spi_disconnect(struct spi_device *func) cw1200_core_release(self->core); self->core = NULL; } + cw1200_spi_off(self, dev_get_platdata(&func->dev)); } - cw1200_spi_off(self, dev_get_platdata(&func->dev)); } static int __maybe_unused cw1200_spi_suspend(struct device *dev) diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 986b07bfa0ee..8fb58a5d911c 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -2612,24 +2612,24 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw, if (test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags) || test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags)) { ret = -EBUSY; - goto out; + goto out_unlock; } ret = wl12xx_init_vif_data(wl, vif); if (ret < 0) - goto out; + goto out_unlock; wlvif->wl = wl; role_type = wl12xx_get_role_type(wl, wlvif); if (role_type == WL12XX_INVALID_ROLE_TYPE) { ret = -EINVAL; - goto out; + goto out_unlock; } ret = wlcore_allocate_hw_queue_base(wl, wlvif); if (ret < 0) - goto out; + goto out_unlock; /* * TODO: after the nvs issue will be solved, move this block @@ -2644,7 +2644,7 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw, ret = wl12xx_init_fw(wl); if (ret < 0) - goto out; + goto out_unlock; } /* diff --git a/drivers/net/wireless/ti/wlcore/sysfs.c b/drivers/net/wireless/ti/wlcore/sysfs.c index c07acfcbbd9c..7c57d4c8744a 100644 --- a/drivers/net/wireless/ti/wlcore/sysfs.c +++ b/drivers/net/wireless/ti/wlcore/sysfs.c @@ -88,7 +88,7 @@ static ssize_t hw_pg_ver_show(struct device *dev, static DEVICE_ATTR_RO(hw_pg_ver); static ssize_t wl1271_sysfs_read_fwlog(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -121,7 +121,7 @@ static ssize_t wl1271_sysfs_read_fwlog(struct file *filp, struct kobject *kobj, static const struct bin_attribute fwlog_attr = { .attr = { .name = "fwlog", .mode = 0400 }, - .read = wl1271_sysfs_read_fwlog, + .read_new = wl1271_sysfs_read_fwlog, }; int wlcore_sysfs_init(struct wl1271 *wl) diff --git a/drivers/net/wireless/ti/wlcore/testmode.c b/drivers/net/wireless/ti/wlcore/testmode.c index 3f338b8096c7..fc8ea58bc165 100644 --- a/drivers/net/wireless/ti/wlcore/testmode.c +++ b/drivers/net/wireless/ti/wlcore/testmode.c @@ -45,7 +45,7 @@ enum wl1271_tm_attrs { }; #define WL1271_TM_ATTR_MAX (__WL1271_TM_ATTR_AFTER_LAST - 1) -static struct nla_policy wl1271_tm_policy[WL1271_TM_ATTR_MAX + 1] = { +static const struct nla_policy wl1271_tm_policy[WL1271_TM_ATTR_MAX + 1] = { [WL1271_TM_ATTR_CMD_ID] = { .type = NLA_U32 }, [WL1271_TM_ATTR_ANSWER] = { .type = NLA_U8 }, [WL1271_TM_ATTR_DATA] = { .type = NLA_BINARY, diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 347a15544afe..cf6a331d4042 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -5048,6 +5048,45 @@ static const struct ieee80211_sband_iftype_data sband_capa_6ghz[] = { .tx_mcs_80p80 = cpu_to_le16(0xfffa), }, }, + .eht_cap = { + .has_eht = true, + .eht_cap_elem = { + .mac_cap_info[0] = IEEE80211_EHT_MAC_CAP0_OM_CONTROL | + IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1, + .phy_cap_info[0] = IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ, + /* Leave all the other PHY capability bytes + * unset, as DCM, beam forming, RU and PPE + * threshold information are not supported + */ + }, + /* For all MCS and bandwidth, set 8 NSS for both Tx and + * Rx + */ + .eht_mcs_nss_supp = { + /* As B1 and B2 are set in the supported + * channel width set field in the HE PHY + * capabilities information field and 320MHz in + * 6GHz is supported include all the following + * MCS/NSS. + */ + .bw._80 = { + .rx_tx_mcs9_max_nss = 0x88, + .rx_tx_mcs11_max_nss = 0x88, + .rx_tx_mcs13_max_nss = 0x88, + }, + .bw._160 = { + .rx_tx_mcs9_max_nss = 0x88, + .rx_tx_mcs11_max_nss = 0x88, + .rx_tx_mcs13_max_nss = 0x88, + }, + .bw._320 = { + .rx_tx_mcs9_max_nss = 0x88, + .rx_tx_mcs11_max_nss = 0x88, + .rx_tx_mcs13_max_nss = 0x88, + }, + }, + /* PPE threshold information is not supported */ + }, }, #endif }; diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.c b/drivers/net/wwan/iosm/iosm_ipc_mmio.c index 63eb08c43c05..6764c13530b9 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mmio.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.c @@ -104,7 +104,7 @@ struct iosm_mmio *ipc_mmio_init(void __iomem *mmio, struct device *dev) break; msleep(20); - } while (retries-- > 0); + } while (--retries > 0); if (!retries) { dev_err(ipc_mmio->dev, "invalid exec stage %X", stage); diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index 04517bd3325a..a066977af0be 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include "iosm_ipc_imem.h" @@ -18,6 +19,7 @@ MODULE_LICENSE("GPL v2"); /* WWAN GUID */ static guid_t wwan_acpi_guid = GUID_INIT(0xbad01b75, 0x22a8, 0x4f48, 0x87, 0x92, 0xbd, 0xde, 0x94, 0x67, 0x74, 0x7d); +static bool pci_registered; static void ipc_pcie_resources_release(struct iosm_pcie *ipc_pcie) { @@ -448,7 +450,6 @@ static struct pci_driver iosm_ipc_driver = { }, .id_table = iosm_ipc_ids, }; -module_pci_driver(iosm_ipc_driver); int ipc_pcie_addr_map(struct iosm_pcie *ipc_pcie, unsigned char *data, size_t size, dma_addr_t *mapping, int direction) @@ -530,3 +531,56 @@ void ipc_pcie_kfree_skb(struct iosm_pcie *ipc_pcie, struct sk_buff *skb) IPC_CB(skb)->mapping = 0; dev_kfree_skb(skb); } + +static int pm_notify(struct notifier_block *nb, unsigned long mode, void *_unused) +{ + if (mode == PM_HIBERNATION_PREPARE || mode == PM_RESTORE_PREPARE) { + if (pci_registered) { + pci_unregister_driver(&iosm_ipc_driver); + pci_registered = false; + } + } else if (mode == PM_POST_HIBERNATION || mode == PM_POST_RESTORE) { + if (!pci_registered) { + int ret; + + ret = pci_register_driver(&iosm_ipc_driver); + if (ret) { + pr_err(KBUILD_MODNAME ": unable to re-register PCI driver: %d\n", + ret); + } else { + pci_registered = true; + } + } + } + + return 0; +} + +static struct notifier_block pm_notifier = { + .notifier_call = pm_notify, +}; + +static int __init iosm_ipc_driver_init(void) +{ + int ret; + + ret = pci_register_driver(&iosm_ipc_driver); + if (ret) + return ret; + + pci_registered = true; + + register_pm_notifier(&pm_notifier); + + return 0; +} +module_init(iosm_ipc_driver_init); + +static void __exit iosm_ipc_driver_exit(void) +{ + unregister_pm_notifier(&pm_notifier); + + if (pci_registered) + pci_unregister_driver(&iosm_ipc_driver); +} +module_exit(iosm_ipc_driver_exit); diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 8381b0dc7acb..02f2ec7cf4ce 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -43,6 +43,8 @@ #include "t7xx_state_monitor.h" #include "t7xx_port_proxy.h" +#define DRIVER_NAME "mtk_t7xx" + #define T7XX_PCI_IREG_BASE 0 #define T7XX_PCI_EREG_BASE 2 @@ -833,6 +835,7 @@ static void t7xx_pci_infracfg_ao_calc(struct t7xx_pci_dev *t7xx_dev) static int t7xx_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct t7xx_pci_dev *t7xx_dev; + void __iomem *iomem; int ret; t7xx_dev = devm_kzalloc(&pdev->dev, sizeof(*t7xx_dev), GFP_KERNEL); @@ -848,12 +851,21 @@ static int t7xx_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); - ret = pcim_iomap_regions(pdev, BIT(T7XX_PCI_IREG_BASE) | BIT(T7XX_PCI_EREG_BASE), - pci_name(pdev)); + iomem = pcim_iomap_region(pdev, T7XX_PCI_IREG_BASE, DRIVER_NAME); + ret = PTR_ERR_OR_ZERO(iomem); if (ret) { - dev_err(&pdev->dev, "Could not request BARs: %d\n", ret); + dev_err(&pdev->dev, "Could not request IREG BAR: %d\n", ret); return -ENOMEM; } + IREG_BASE(t7xx_dev) = iomem; + + iomem = pcim_iomap_region(pdev, T7XX_PCI_EREG_BASE, DRIVER_NAME); + ret = PTR_ERR_OR_ZERO(iomem); + if (ret) { + dev_err(&pdev->dev, "Could not request EREG BAR: %d\n", ret); + return -ENOMEM; + } + t7xx_dev->base_addr.pcie_ext_reg_base = iomem; ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); if (ret) { @@ -867,9 +879,6 @@ static int t7xx_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return ret; } - IREG_BASE(t7xx_dev) = pcim_iomap_table(pdev)[T7XX_PCI_IREG_BASE]; - t7xx_dev->base_addr.pcie_ext_reg_base = pcim_iomap_table(pdev)[T7XX_PCI_EREG_BASE]; - ret = t7xx_pci_pm_init(t7xx_dev); if (ret) return ret; @@ -937,7 +946,7 @@ static const struct pci_device_id t7xx_pci_table[] = { MODULE_DEVICE_TABLE(pci, t7xx_pci_table); static struct pci_driver t7xx_pci_driver = { - .name = "mtk_t7xx", + .name = DRIVER_NAME, .id_table = t7xx_pci_table, .probe = t7xx_pci_probe, .remove = t7xx_pci_remove, diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.c b/drivers/net/wwan/t7xx/t7xx_state_monitor.c index 3931c7a13f5a..cbdbb91e8381 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.c +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.c @@ -104,14 +104,21 @@ void t7xx_fsm_broadcast_state(struct t7xx_fsm_ctl *ctl, enum md_state state) fsm_state_notify(ctl->md, state); } +static void fsm_release_command(struct kref *ref) +{ + struct t7xx_fsm_command *cmd = container_of(ref, typeof(*cmd), refcnt); + + kfree(cmd); +} + static void fsm_finish_command(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command *cmd, int result) { if (cmd->flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) { - *cmd->ret = result; - complete_all(cmd->done); + cmd->result = result; + complete_all(&cmd->done); } - kfree(cmd); + kref_put(&cmd->refcnt, fsm_release_command); } static void fsm_del_kf_event(struct t7xx_fsm_event *event) @@ -475,7 +482,6 @@ static int fsm_main_thread(void *data) int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id, unsigned int flag) { - DECLARE_COMPLETION_ONSTACK(done); struct t7xx_fsm_command *cmd; unsigned long flags; int ret; @@ -487,11 +493,13 @@ int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id INIT_LIST_HEAD(&cmd->entry); cmd->cmd_id = cmd_id; cmd->flag = flag; + kref_init(&cmd->refcnt); if (flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) { - cmd->done = &done; - cmd->ret = &ret; + init_completion(&cmd->done); + kref_get(&cmd->refcnt); } + kref_get(&cmd->refcnt); spin_lock_irqsave(&ctl->command_lock, flags); list_add_tail(&cmd->entry, &ctl->command_queue); spin_unlock_irqrestore(&ctl->command_lock, flags); @@ -501,11 +509,11 @@ int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id if (flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) { unsigned long wait_ret; - wait_ret = wait_for_completion_timeout(&done, + wait_ret = wait_for_completion_timeout(&cmd->done, msecs_to_jiffies(FSM_CMD_TIMEOUT_MS)); - if (!wait_ret) - return -ETIMEDOUT; + ret = wait_ret ? cmd->result : -ETIMEDOUT; + kref_put(&cmd->refcnt, fsm_release_command); return ret; } diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.h b/drivers/net/wwan/t7xx/t7xx_state_monitor.h index 7b0a9baf488c..6e0601bb752e 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.h +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.h @@ -110,8 +110,9 @@ struct t7xx_fsm_command { struct list_head entry; enum t7xx_fsm_cmd_state cmd_id; unsigned int flag; - struct completion *done; - int *ret; + struct completion done; + int result; + struct kref refcnt; }; struct t7xx_fsm_notifier { diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 4265c1cd0ff7..63fe51d0e64d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -867,7 +867,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev static int xennet_close(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); - unsigned int num_queues = dev->real_num_tx_queues; + unsigned int num_queues = np->queues ? dev->real_num_tx_queues : 0; unsigned int i; struct netfront_queue *queue; netif_tx_stop_all_queues(np->netdev); @@ -882,6 +882,9 @@ static void xennet_destroy_queues(struct netfront_info *info) { unsigned int i; + if (!info->queues) + return; + for (i = 0; i < info->netdev->real_num_tx_queues; i++) { struct netfront_queue *queue = &info->queues[i]; diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index 956ae92f7573..2037cd6d4f4f 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -5,11 +5,16 @@ * Copyright (C) 2015, Marvell International Ltd. */ -#include #include -#include +#include +#include +#include +#include +#include + #include #include + #include "nfcmrvl.h" static unsigned int hci_muxed; diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c index 1ec651e31064..3425b68f0ddc 100644 --- a/drivers/nfc/st21nfca/dep.c +++ b/drivers/nfc/st21nfca/dep.c @@ -116,18 +116,16 @@ static void st21nfca_tx_work(struct work_struct *work) struct nfc_dev *dev; struct sk_buff *skb; - if (info) { - dev = info->hdev->ndev; - skb = info->dep_info.tx_pending; + dev = info->hdev->ndev; + skb = info->dep_info.tx_pending; - device_lock(&dev->dev); + device_lock(&dev->dev); - nfc_hci_send_cmd_async(info->hdev, ST21NFCA_RF_READER_F_GATE, - ST21NFCA_WR_XCHG_DATA, skb->data, skb->len, - info->async_cb, info); - device_unlock(&dev->dev); - kfree_skb(skb); - } + nfc_hci_send_cmd_async(info->hdev, ST21NFCA_RF_READER_F_GATE, + ST21NFCA_WR_XCHG_DATA, skb->data, skb->len, + info->async_cb, info); + device_unlock(&dev->dev); + kfree_skb(skb); } static void st21nfca_im_send_pdu(struct st21nfca_hci_info *info, diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c index 02c3d11a19c4..6d7861383806 100644 --- a/drivers/nfc/st21nfca/i2c.c +++ b/drivers/nfc/st21nfca/i2c.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 2237715e42eb..0ccf4a9e523a 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -1212,7 +1212,7 @@ enum nd_ioctl_mode { DIMM_IOCTL, }; -static int match_dimm(struct device *dev, void *data) +static int match_dimm(struct device *dev, const void *data) { long id = (long) data; diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c index 030dbde6b088..9e84ab411564 100644 --- a/drivers/nvdimm/claim.c +++ b/drivers/nvdimm/claim.c @@ -67,13 +67,6 @@ bool nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach, return claimed; } -static int namespace_match(struct device *dev, void *data) -{ - char *name = data; - - return strcmp(name, dev_name(dev)) == 0; -} - static bool is_idle(struct device *dev, struct nd_namespace_common *ndns) { struct nd_region *nd_region = to_nd_region(dev->parent); @@ -168,7 +161,7 @@ ssize_t nd_namespace_store(struct device *dev, goto out; } - found = device_find_child(dev->parent, name, namespace_match); + found = device_find_child_by_name(dev->parent, name); if (!found) { dev_dbg(dev, "'%s' not found under %s\n", name, dev_name(dev->parent)); diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 4319ab50c10d..1de11b722f04 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1251,7 +1251,6 @@ static int apple_nvme_alloc_tagsets(struct apple_nvme *anv) anv->admin_tagset.timeout = NVME_ADMIN_TIMEOUT; anv->admin_tagset.numa_node = NUMA_NO_NODE; anv->admin_tagset.cmd_size = sizeof(struct apple_nvme_iod); - anv->admin_tagset.flags = BLK_MQ_F_NO_SCHED; anv->admin_tagset.driver_data = &anv->adminq; ret = blk_mq_alloc_tag_set(&anv->admin_tagset); @@ -1275,7 +1274,6 @@ static int apple_nvme_alloc_tagsets(struct apple_nvme *anv) anv->tagset.timeout = NVME_IO_TIMEOUT; anv->tagset.numa_node = NUMA_NO_NODE; anv->tagset.cmd_size = sizeof(struct apple_nvme_iod); - anv->tagset.flags = BLK_MQ_F_SHOULD_MERGE; anv->tagset.driver_data = &anv->ioq; ret = blk_mq_alloc_tag_set(&anv->tagset); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index d169a30eb935..40046770f1bf 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -885,6 +885,12 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, return BLK_STS_OK; } +static void nvme_set_app_tag(struct request *req, struct nvme_command *cmnd) +{ + cmnd->rw.lbat = cpu_to_le16(bio_integrity(req->bio)->app_tag); + cmnd->rw.lbatm = cpu_to_le16(0xffff); +} + static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd, struct request *req) { @@ -1017,18 +1023,17 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, control |= NVME_RW_PRINFO_PRACT; } - switch (ns->head->pi_type) { - case NVME_NS_DPS_PI_TYPE3: + if (bio_integrity_flagged(req->bio, BIP_CHECK_GUARD)) control |= NVME_RW_PRINFO_PRCHK_GUARD; - break; - case NVME_NS_DPS_PI_TYPE1: - case NVME_NS_DPS_PI_TYPE2: - control |= NVME_RW_PRINFO_PRCHK_GUARD | - NVME_RW_PRINFO_PRCHK_REF; + if (bio_integrity_flagged(req->bio, BIP_CHECK_REFTAG)) { + control |= NVME_RW_PRINFO_PRCHK_REF; if (op == nvme_cmd_zone_append) control |= NVME_RW_APPEND_PIREMAP; nvme_set_ref_tag(ns, cmnd, req); - break; + } + if (bio_integrity_flagged(req->bio, BIP_CHECK_APPTAG)) { + control |= NVME_RW_PRINFO_PRCHK_APP; + nvme_set_app_tag(req, cmnd); } } @@ -2002,6 +2007,7 @@ static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns, lim->atomic_write_hw_boundary = boundary; lim->atomic_write_hw_unit_min = bs; lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs); + lim->features |= BLK_FEAT_ATOMIC_WRITES; } static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl) @@ -2034,7 +2040,7 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, * or smaller than a sector size yet, so catch this early and don't * allow block I/O. */ - if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) { + if (blk_validate_block_size(bs)) { bs = (1 << 9); valid = false; } @@ -2126,14 +2132,16 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns, struct nvme_ns_info *info) { struct queue_limits lim; + unsigned int memflags; int ret; - blk_mq_freeze_queue(ns->disk->queue); lim = queue_limits_start_update(ns->disk->queue); nvme_set_ctrl_limits(ns->ctrl, &lim); + + memflags = blk_mq_freeze_queue(ns->disk->queue); ret = queue_limits_commit_update(ns->disk->queue, &lim); set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); - blk_mq_unfreeze_queue(ns->disk->queue); + blk_mq_unfreeze_queue(ns->disk->queue, memflags); /* Hide the block-interface for these devices */ if (!ret) @@ -2148,6 +2156,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, struct nvme_id_ns_nvm *nvm = NULL; struct nvme_zone_info zi = {}; struct nvme_id_ns *id; + unsigned int memflags; sector_t capacity; unsigned lbaf; int ret; @@ -2177,12 +2186,12 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, goto out; } - blk_mq_freeze_queue(ns->disk->queue); + lim = queue_limits_start_update(ns->disk->queue); + + memflags = blk_mq_freeze_queue(ns->disk->queue); ns->head->lba_shift = id->lbaf[lbaf].ds; ns->head->nuse = le64_to_cpu(id->nuse); capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze)); - - lim = queue_limits_start_update(ns->disk->queue); nvme_set_ctrl_limits(ns->ctrl, &lim); nvme_configure_metadata(ns->ctrl, ns->head, id, nvm, info); nvme_set_chunk_sectors(ns, id, &lim); @@ -2212,7 +2221,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, ret = queue_limits_commit_update(ns->disk->queue, &lim); if (ret) { - blk_mq_unfreeze_queue(ns->disk->queue); + blk_mq_unfreeze_queue(ns->disk->queue, memflags); goto out; } @@ -2228,7 +2237,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, ns->head->features |= NVME_NS_DEAC; set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); set_bit(NVME_NS_READY, &ns->flags); - blk_mq_unfreeze_queue(ns->disk->queue); + blk_mq_unfreeze_queue(ns->disk->queue, memflags); if (blk_queue_is_zoned(ns->queue)) { ret = blk_revalidate_disk_zones(ns->disk); @@ -2284,8 +2293,10 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) if (!ret && nvme_ns_head_multipath(ns->head)) { struct queue_limits *ns_lim = &ns->disk->queue->limits; struct queue_limits lim; + unsigned int memflags; - blk_mq_freeze_queue(ns->head->disk->queue); + lim = queue_limits_start_update(ns->head->disk->queue); + memflags = blk_mq_freeze_queue(ns->head->disk->queue); /* * queue_limits mixes values that are the hardware limitations * for bio splitting with what is the device configuration. @@ -2301,7 +2312,6 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) * the splitting limits in to make sure we still obey possibly * lower limitations of other controllers. */ - lim = queue_limits_start_update(ns->head->disk->queue); lim.logical_block_size = ns_lim->logical_block_size; lim.physical_block_size = ns_lim->physical_block_size; lim.io_min = ns_lim->io_min; @@ -2318,7 +2328,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); nvme_mpath_revalidate_paths(ns); - blk_mq_unfreeze_queue(ns->head->disk->queue); + blk_mq_unfreeze_queue(ns->head->disk->queue, memflags); } return ret; @@ -3092,7 +3102,7 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, struct nvme_effects_log **log) { - struct nvme_effects_log *cel = xa_load(&ctrl->cels, csi); + struct nvme_effects_log *old, *cel = xa_load(&ctrl->cels, csi); int ret; if (cel) @@ -3109,7 +3119,11 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, return ret; } - xa_store(&ctrl->cels, csi, cel, GFP_KERNEL); + old = xa_store(&ctrl->cels, csi, cel, GFP_KERNEL); + if (xa_is_err(old)) { + kfree(cel); + return xa_err(old); + } out: *log = cel; return 0; @@ -3171,6 +3185,25 @@ free_data: return ret; } +static int nvme_init_effects_log(struct nvme_ctrl *ctrl, + u8 csi, struct nvme_effects_log **log) +{ + struct nvme_effects_log *effects, *old; + + effects = kzalloc(sizeof(*effects), GFP_KERNEL); + if (!effects) + return -ENOMEM; + + old = xa_store(&ctrl->cels, csi, effects, GFP_KERNEL); + if (xa_is_err(old)) { + kfree(effects); + return xa_err(old); + } + + *log = effects; + return 0; +} + static void nvme_init_known_nvm_effects(struct nvme_ctrl *ctrl) { struct nvme_effects_log *log = ctrl->effects; @@ -3217,10 +3250,9 @@ static int nvme_init_effects(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) } if (!ctrl->effects) { - ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL); - if (!ctrl->effects) - return -ENOMEM; - xa_store(&ctrl->cels, NVME_CSI_NVM, ctrl->effects, GFP_KERNEL); + ret = nvme_init_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects); + if (ret < 0) + return ret; } nvme_init_known_nvm_effects(ctrl); @@ -4564,7 +4596,6 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, /* Reserved for fabric connect and keep alive */ set->reserved_tags = 2; set->numa_node = ctrl->numa_node; - set->flags = BLK_MQ_F_NO_SCHED; if (ctrl->ops->flags & NVME_F_BLOCKING) set->flags |= BLK_MQ_F_BLOCKING; set->cmd_size = cmd_size; @@ -4639,7 +4670,6 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, /* Reserved for fabric connect */ set->reserved_tags = 1; set->numa_node = ctrl->numa_node; - set->flags = BLK_MQ_F_SHOULD_MERGE; if (ctrl->ops->flags & NVME_F_BLOCKING) set->flags |= BLK_MQ_F_BLOCKING; set->cmd_size = cmd_size; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b81af7919e94..094be164ffdc 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -16,7 +16,6 @@ #include #include "fc.h" #include -#include /* *************************** Data Structures/Defines ****************** */ diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index a85d190942bd..2a7635565083 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -60,7 +60,7 @@ void nvme_mpath_unfreeze(struct nvme_subsystem *subsys) lockdep_assert_held(&subsys->lock); list_for_each_entry(h, &subsys->nsheads, entry) if (h->disk) - blk_mq_unfreeze_queue(h->disk->queue); + blk_mq_unfreeze_queue_nomemrestore(h->disk->queue); } void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 611b02c8a8b3..7be92d07430e 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -173,6 +173,11 @@ enum nvme_quirks { * MSI (but not MSI-X) interrupts are broken and never fire. */ NVME_QUIRK_BROKEN_MSI = (1 << 21), + + /* + * Align dma pool segment size to 512 bytes + */ + NVME_QUIRK_DMAPOOL_ALIGN_512 = (1 << 22), }; /* @@ -1182,43 +1187,4 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl) return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI; } -#ifdef CONFIG_NVME_VERBOSE_ERRORS -const char *nvme_get_error_status_str(u16 status); -const char *nvme_get_opcode_str(u8 opcode); -const char *nvme_get_admin_opcode_str(u8 opcode); -const char *nvme_get_fabrics_opcode_str(u8 opcode); -#else /* CONFIG_NVME_VERBOSE_ERRORS */ -static inline const char *nvme_get_error_status_str(u16 status) -{ - return "I/O Error"; -} -static inline const char *nvme_get_opcode_str(u8 opcode) -{ - return "I/O Cmd"; -} -static inline const char *nvme_get_admin_opcode_str(u8 opcode) -{ - return "Admin Cmd"; -} - -static inline const char *nvme_get_fabrics_opcode_str(u8 opcode) -{ - return "Fabrics Cmd"; -} -#endif /* CONFIG_NVME_VERBOSE_ERRORS */ - -static inline const char *nvme_opcode_str(int qid, u8 opcode) -{ - return qid ? nvme_get_opcode_str(opcode) : - nvme_get_admin_opcode_str(opcode); -} - -static inline const char *nvme_fabrics_opcode_str( - int qid, const struct nvme_command *cmd) -{ - if (nvme_is_fabrics(cmd)) - return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype); - - return nvme_opcode_str(qid, cmd->common.opcode); -} #endif /* _NVME_H */ diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 1a5ba80f1811..278bed4e35bb 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include #include @@ -373,7 +372,7 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db, /* * Ensure that the doorbell is updated before reading the event * index from memory. The controller needs to provide similar - * ordering to ensure the envent index is updated before reading + * ordering to ensure the event index is updated before reading * the doorbell. */ mb(); @@ -463,7 +462,7 @@ static void nvme_pci_map_queues(struct blk_mq_tag_set *set) */ map->queue_offset = qoff; if (i != HCTX_TYPE_POLL && offset) - blk_mq_pci_map_queues(map, to_pci_dev(dev->dev), offset); + blk_mq_map_hw_queues(map, dev->dev, offset); else blk_mq_map_queues(map); qoff += map->nr_queues; @@ -1148,13 +1147,13 @@ static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) } } -static inline int nvme_poll_cq(struct nvme_queue *nvmeq, - struct io_comp_batch *iob) +static inline bool nvme_poll_cq(struct nvme_queue *nvmeq, + struct io_comp_batch *iob) { - int found = 0; + bool found = false; while (nvme_cqe_pending(nvmeq)) { - found++; + found = true; /* * load-load control dependency between phase and the rest of * the cqe requires a full read memory barrier @@ -2086,8 +2085,8 @@ static int nvme_alloc_host_mem_single(struct nvme_dev *dev, u64 size) sizeof(*dev->host_mem_descs), &dev->host_mem_descs_dma, GFP_KERNEL); if (!dev->host_mem_descs) { - dma_free_noncontiguous(dev->dev, dev->host_mem_size, - dev->hmb_sgt, DMA_BIDIRECTIONAL); + dma_free_noncontiguous(dev->dev, size, dev->hmb_sgt, + DMA_BIDIRECTIONAL); dev->hmb_sgt = NULL; return -ENOMEM; } @@ -2834,15 +2833,20 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown) static int nvme_setup_prp_pools(struct nvme_dev *dev) { + size_t small_align = 256; + dev->prp_page_pool = dma_pool_create("prp list page", dev->dev, NVME_CTRL_PAGE_SIZE, NVME_CTRL_PAGE_SIZE, 0); if (!dev->prp_page_pool) return -ENOMEM; + if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512) + small_align = 512; + /* Optimisation for I/Os between 4k and 128k */ dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev, - 256, 256, 0); + 256, small_align, 0); if (!dev->prp_small_pool) { dma_pool_destroy(dev->prp_page_pool); return -ENOMEM; @@ -3607,7 +3611,7 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */ - .driver_data = NVME_QUIRK_QDEPTH_ONE }, + .driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, }, { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_BOGUS_NID, }, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 28c76a3e1bd2..841238f38fdd 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -54,6 +54,8 @@ MODULE_PARM_DESC(tls_handshake_timeout, "nvme TLS handshake timeout in seconds (default 10)"); #endif +static atomic_t nvme_tcp_cpu_queues[NR_CPUS]; + #ifdef CONFIG_DEBUG_LOCK_ALLOC /* lockdep can detect a circular dependency of the form * sk_lock -> mmap_lock (page fault) -> fs locks -> sk_lock @@ -127,6 +129,7 @@ enum nvme_tcp_queue_flags { NVME_TCP_Q_ALLOCATED = 0, NVME_TCP_Q_LIVE = 1, NVME_TCP_Q_POLLING = 2, + NVME_TCP_Q_IO_CPU_SET = 3, }; enum nvme_tcp_recv_state { @@ -1562,23 +1565,56 @@ static bool nvme_tcp_poll_queue(struct nvme_tcp_queue *queue) ctrl->io_queues[HCTX_TYPE_POLL]; } +/** + * Track the number of queues assigned to each cpu using a global per-cpu + * counter and select the least used cpu from the mq_map. Our goal is to spread + * different controllers I/O threads across different cpu cores. + * + * Note that the accounting is not 100% perfect, but we don't need to be, we're + * simply putting our best effort to select the best candidate cpu core that we + * find at any given point. + */ static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue) { struct nvme_tcp_ctrl *ctrl = queue->ctrl; - int qid = nvme_tcp_queue_id(queue); - int n = 0; + struct blk_mq_tag_set *set = &ctrl->tag_set; + int qid = nvme_tcp_queue_id(queue) - 1; + unsigned int *mq_map = NULL; + int cpu, min_queues = INT_MAX, io_cpu; + + if (wq_unbound) + goto out; if (nvme_tcp_default_queue(queue)) - n = qid - 1; + mq_map = set->map[HCTX_TYPE_DEFAULT].mq_map; else if (nvme_tcp_read_queue(queue)) - n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] - 1; + mq_map = set->map[HCTX_TYPE_READ].mq_map; else if (nvme_tcp_poll_queue(queue)) - n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] - - ctrl->io_queues[HCTX_TYPE_READ] - 1; - if (wq_unbound) - queue->io_cpu = WORK_CPU_UNBOUND; - else - queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false); + mq_map = set->map[HCTX_TYPE_POLL].mq_map; + + if (WARN_ON(!mq_map)) + goto out; + + /* Search for the least used cpu from the mq_map */ + io_cpu = WORK_CPU_UNBOUND; + for_each_online_cpu(cpu) { + int num_queues = atomic_read(&nvme_tcp_cpu_queues[cpu]); + + if (mq_map[cpu] != qid) + continue; + if (num_queues < min_queues) { + io_cpu = cpu; + min_queues = num_queues; + } + } + if (io_cpu != WORK_CPU_UNBOUND) { + queue->io_cpu = io_cpu; + atomic_inc(&nvme_tcp_cpu_queues[io_cpu]); + set_bit(NVME_TCP_Q_IO_CPU_SET, &queue->flags); + } +out: + dev_dbg(ctrl->ctrl.device, "queue %d: using cpu %d\n", + qid, queue->io_cpu); } static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid) @@ -1722,7 +1758,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, queue->sock->sk->sk_allocation = GFP_ATOMIC; queue->sock->sk->sk_use_task_frag = false; - nvme_tcp_set_queue_io_cpu(queue); + queue->io_cpu = WORK_CPU_UNBOUND; queue->request = NULL; queue->data_remaining = 0; queue->ddgst_remaining = 0; @@ -1844,6 +1880,9 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) if (!test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) return; + if (test_and_clear_bit(NVME_TCP_Q_IO_CPU_SET, &queue->flags)) + atomic_dec(&nvme_tcp_cpu_queues[queue->io_cpu]); + mutex_lock(&queue->queue_lock); if (test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags)) __nvme_tcp_stop_queue(queue); @@ -1878,9 +1917,10 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) nvme_tcp_init_recv_ctx(queue); nvme_tcp_setup_sock_ops(queue); - if (idx) + if (idx) { + nvme_tcp_set_queue_io_cpu(queue); ret = nvmf_connect_io_queue(nctrl, idx); - else + } else ret = nvmf_connect_admin_queue(nctrl); if (!ret) { @@ -2024,14 +2064,6 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) return __nvme_tcp_alloc_io_queues(ctrl); } -static void nvme_tcp_destroy_io_queues(struct nvme_ctrl *ctrl, bool remove) -{ - nvme_tcp_stop_io_queues(ctrl); - if (remove) - nvme_remove_io_tag_set(ctrl); - nvme_tcp_free_io_queues(ctrl); -} - static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) { int ret, nr_queues; @@ -2176,9 +2208,11 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); nvme_cancel_tagset(ctrl); - if (remove) + if (remove) { nvme_unquiesce_io_queues(ctrl); - nvme_tcp_destroy_io_queues(ctrl, remove); + nvme_remove_io_tag_set(ctrl); + } + nvme_tcp_free_io_queues(ctrl); } static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl, @@ -2267,7 +2301,9 @@ destroy_io: nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); nvme_cancel_tagset(ctrl); - nvme_tcp_destroy_io_queues(ctrl, new); + if (new) + nvme_remove_io_tag_set(ctrl); + nvme_tcp_free_io_queues(ctrl); } destroy_admin: nvme_stop_keep_alive(ctrl); @@ -2849,6 +2885,7 @@ static struct nvmf_transport_ops nvme_tcp_transport = { static int __init nvme_tcp_init_module(void) { unsigned int wq_flags = WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_SYSFS; + int cpu; BUILD_BUG_ON(sizeof(struct nvme_tcp_hdr) != 8); BUILD_BUG_ON(sizeof(struct nvme_tcp_cmd_pdu) != 72); @@ -2866,6 +2903,9 @@ static int __init nvme_tcp_init_module(void) if (!nvme_tcp_wq) return -ENOMEM; + for_each_possible_cpu(cpu) + atomic_set(&nvme_tcp_cpu_queues[cpu], 0); + nvmf_register_transport(&nvme_tcp_transport); return 0; } diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index 46be031f91b4..fb7446d6d682 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -115,3 +115,14 @@ config NVME_TARGET_AUTH target side. If unsure, say N. + +config NVME_TARGET_PCI_EPF + tristate "NVMe PCI Endpoint Function target support" + depends on NVME_TARGET && PCI_ENDPOINT + depends on NVME_CORE=y || NVME_CORE=NVME_TARGET + help + This enables the NVMe PCI Endpoint Function target driver support, + which allows creating a NVMe PCI controller using an endpoint mode + capable PCI controller. + + If unsure, say N. diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile index f2b025bbe10c..ed8522911d1f 100644 --- a/drivers/nvme/target/Makefile +++ b/drivers/nvme/target/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_NVME_TARGET_RDMA) += nvmet-rdma.o obj-$(CONFIG_NVME_TARGET_FC) += nvmet-fc.o obj-$(CONFIG_NVME_TARGET_FCLOOP) += nvme-fcloop.o obj-$(CONFIG_NVME_TARGET_TCP) += nvmet-tcp.o +obj-$(CONFIG_NVME_TARGET_PCI_EPF) += nvmet-pci-epf.o nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \ discovery.o io-cmd-file.o io-cmd-bdev.o pr.o @@ -20,4 +21,5 @@ nvmet-rdma-y += rdma.o nvmet-fc-y += fc.o nvme-fcloop-y += fcloop.o nvmet-tcp-y += tcp.o +nvmet-pci-epf-y += pci-epf.o nvmet-$(CONFIG_TRACING) += trace.o diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 2962794ce881..e670dc185a96 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -12,6 +12,142 @@ #include #include "nvmet.h" +static void nvmet_execute_delete_sq(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u16 sqid = le16_to_cpu(req->cmd->delete_queue.qid); + u16 status; + + if (!nvmet_is_pci_ctrl(ctrl)) { + status = nvmet_report_invalid_opcode(req); + goto complete; + } + + if (!sqid) { + status = NVME_SC_QID_INVALID | NVME_STATUS_DNR; + goto complete; + } + + status = nvmet_check_sqid(ctrl, sqid, false); + if (status != NVME_SC_SUCCESS) + goto complete; + + status = ctrl->ops->delete_sq(ctrl, sqid); + +complete: + nvmet_req_complete(req, status); +} + +static void nvmet_execute_create_sq(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvme_command *cmd = req->cmd; + u16 sqid = le16_to_cpu(cmd->create_sq.sqid); + u16 cqid = le16_to_cpu(cmd->create_sq.cqid); + u16 sq_flags = le16_to_cpu(cmd->create_sq.sq_flags); + u16 qsize = le16_to_cpu(cmd->create_sq.qsize); + u64 prp1 = le64_to_cpu(cmd->create_sq.prp1); + u16 status; + + if (!nvmet_is_pci_ctrl(ctrl)) { + status = nvmet_report_invalid_opcode(req); + goto complete; + } + + if (!sqid) { + status = NVME_SC_QID_INVALID | NVME_STATUS_DNR; + goto complete; + } + + status = nvmet_check_sqid(ctrl, sqid, true); + if (status != NVME_SC_SUCCESS) + goto complete; + + /* + * Note: The NVMe specification allows multiple SQs to use the same CQ. + * However, the target code does not really support that. So for now, + * prevent this and fail the command if sqid and cqid are different. + */ + if (!cqid || cqid != sqid) { + pr_err("SQ %u: Unsupported CQID %u\n", sqid, cqid); + status = NVME_SC_CQ_INVALID | NVME_STATUS_DNR; + goto complete; + } + + if (!qsize || qsize > NVME_CAP_MQES(ctrl->cap)) { + status = NVME_SC_QUEUE_SIZE | NVME_STATUS_DNR; + goto complete; + } + + status = ctrl->ops->create_sq(ctrl, sqid, sq_flags, qsize, prp1); + +complete: + nvmet_req_complete(req, status); +} + +static void nvmet_execute_delete_cq(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u16 cqid = le16_to_cpu(req->cmd->delete_queue.qid); + u16 status; + + if (!nvmet_is_pci_ctrl(ctrl)) { + status = nvmet_report_invalid_opcode(req); + goto complete; + } + + if (!cqid) { + status = NVME_SC_QID_INVALID | NVME_STATUS_DNR; + goto complete; + } + + status = nvmet_check_cqid(ctrl, cqid); + if (status != NVME_SC_SUCCESS) + goto complete; + + status = ctrl->ops->delete_cq(ctrl, cqid); + +complete: + nvmet_req_complete(req, status); +} + +static void nvmet_execute_create_cq(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvme_command *cmd = req->cmd; + u16 cqid = le16_to_cpu(cmd->create_cq.cqid); + u16 cq_flags = le16_to_cpu(cmd->create_cq.cq_flags); + u16 qsize = le16_to_cpu(cmd->create_cq.qsize); + u16 irq_vector = le16_to_cpu(cmd->create_cq.irq_vector); + u64 prp1 = le64_to_cpu(cmd->create_cq.prp1); + u16 status; + + if (!nvmet_is_pci_ctrl(ctrl)) { + status = nvmet_report_invalid_opcode(req); + goto complete; + } + + if (!cqid) { + status = NVME_SC_QID_INVALID | NVME_STATUS_DNR; + goto complete; + } + + status = nvmet_check_cqid(ctrl, cqid); + if (status != NVME_SC_SUCCESS) + goto complete; + + if (!qsize || qsize > NVME_CAP_MQES(ctrl->cap)) { + status = NVME_SC_QUEUE_SIZE | NVME_STATUS_DNR; + goto complete; + } + + status = ctrl->ops->create_cq(ctrl, cqid, cq_flags, qsize, + prp1, irq_vector); + +complete: + nvmet_req_complete(req, status); +} + u32 nvmet_get_log_page_len(struct nvme_command *cmd) { u32 len = le16_to_cpu(cmd->get_log_page.numdu); @@ -139,7 +275,7 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req, unsigned long idx; ctrl = req->sq->ctrl; - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { /* we don't have the right data for file backed ns */ if (!ns->bdev) continue; @@ -230,8 +366,18 @@ out: nvmet_req_complete(req, status); } -static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log) +static void nvmet_get_cmd_effects_admin(struct nvmet_ctrl *ctrl, + struct nvme_effects_log *log) { + /* For a PCI target controller, advertize support for the . */ + if (nvmet_is_pci_ctrl(ctrl)) { + log->acs[nvme_admin_delete_sq] = + log->acs[nvme_admin_create_sq] = + log->acs[nvme_admin_delete_cq] = + log->acs[nvme_admin_create_cq] = + cpu_to_le32(NVME_CMD_EFFECTS_CSUPP); + } + log->acs[nvme_admin_get_log_page] = log->acs[nvme_admin_identify] = log->acs[nvme_admin_abort_cmd] = @@ -240,7 +386,10 @@ static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log) log->acs[nvme_admin_async_event] = log->acs[nvme_admin_keep_alive] = cpu_to_le32(NVME_CMD_EFFECTS_CSUPP); +} +static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log) +{ log->iocs[nvme_cmd_read] = log->iocs[nvme_cmd_flush] = log->iocs[nvme_cmd_dsm] = @@ -265,6 +414,7 @@ static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log) static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req) { + struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_effects_log *log; u16 status = NVME_SC_SUCCESS; @@ -276,6 +426,7 @@ static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req) switch (req->cmd->get_log_page.csi) { case NVME_CSI_NVM: + nvmet_get_cmd_effects_admin(ctrl, log); nvmet_get_cmd_effects_nvm(log); break; case NVME_CSI_ZNS: @@ -283,6 +434,7 @@ static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req) status = NVME_SC_INVALID_IO_CMD_SET; goto free; } + nvmet_get_cmd_effects_admin(ctrl, log); nvmet_get_cmd_effects_nvm(log); nvmet_get_cmd_effects_zns(log); break; @@ -331,9 +483,10 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid, u32 count = 0; if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) { - xa_for_each(&ctrl->subsys->namespaces, idx, ns) + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->anagrpid == grpid) desc->nsids[count++] = cpu_to_le32(ns->nsid); + } } desc->grpid = cpu_to_le32(grpid); @@ -507,7 +660,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvmet_subsys *subsys = ctrl->subsys; struct nvme_id_ctrl *id; - u32 cmd_capsule_size; + u32 cmd_capsule_size, ctratt; u16 status = 0; if (!subsys->subsys_discovered) { @@ -522,9 +675,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) goto out; } - /* XXX: figure out how to assign real vendors IDs. */ - id->vid = 0; - id->ssvid = 0; + id->vid = cpu_to_le16(subsys->vendor_id); + id->ssvid = cpu_to_le16(subsys->subsys_vendor_id); memcpy(id->sn, ctrl->subsys->serial, NVMET_SN_MAX_SIZE); memcpy_and_pad(id->mn, sizeof(id->mn), subsys->model_number, @@ -556,8 +708,10 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) /* XXX: figure out what to do about RTD3R/RTD3 */ id->oaes = cpu_to_le32(NVMET_AEN_CFG_OPTIONAL); - id->ctratt = cpu_to_le32(NVME_CTRL_ATTR_HID_128_BIT | - NVME_CTRL_ATTR_TBKAS); + ctratt = NVME_CTRL_ATTR_HID_128_BIT | NVME_CTRL_ATTR_TBKAS; + if (nvmet_is_pci_ctrl(ctrl)) + ctratt |= NVME_CTRL_ATTR_RHII; + id->ctratt = cpu_to_le32(ctratt); id->oacs = 0; @@ -772,7 +926,7 @@ static void nvmet_execute_identify_endgrp_list(struct nvmet_req *req) goto out; } - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->nsid <= min_endgid) continue; @@ -815,7 +969,7 @@ static void nvmet_execute_identify_nslist(struct nvmet_req *req, bool match_css) goto out; } - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->nsid <= min_nsid) continue; if (match_css && req->ns->csi != req->cmd->identify.csi) @@ -1104,6 +1258,92 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask) return 0; } +static u16 nvmet_set_feat_host_id(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + + if (!nvmet_is_pci_ctrl(ctrl)) + return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR; + + /* + * The NVMe base specifications v2.1 recommends supporting 128-bits host + * IDs (section 5.1.25.1.28.1). However, that same section also says + * that "The controller may support a 64-bit Host Identifier and/or an + * extended 128-bit Host Identifier". So simplify this support and do + * not support 64-bits host IDs to avoid needing to check that all + * controllers associated with the same subsystem all use the same host + * ID size. + */ + if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) { + req->error_loc = offsetof(struct nvme_common_command, cdw11); + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + + return nvmet_copy_from_sgl(req, 0, &req->sq->ctrl->hostid, + sizeof(req->sq->ctrl->hostid)); +} + +static u16 nvmet_set_feat_irq_coalesce(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11); + struct nvmet_feat_irq_coalesce irqc = { + .time = (cdw11 >> 8) & 0xff, + .thr = cdw11 & 0xff, + }; + + /* + * This feature is not supported for fabrics controllers and mandatory + * for PCI controllers. + */ + if (!nvmet_is_pci_ctrl(ctrl)) { + req->error_loc = offsetof(struct nvme_common_command, cdw10); + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + + return ctrl->ops->set_feature(ctrl, NVME_FEAT_IRQ_COALESCE, &irqc); +} + +static u16 nvmet_set_feat_irq_config(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11); + struct nvmet_feat_irq_config irqcfg = { + .iv = cdw11 & 0xffff, + .cd = (cdw11 >> 16) & 0x1, + }; + + /* + * This feature is not supported for fabrics controllers and mandatory + * for PCI controllers. + */ + if (!nvmet_is_pci_ctrl(ctrl)) { + req->error_loc = offsetof(struct nvme_common_command, cdw10); + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + + return ctrl->ops->set_feature(ctrl, NVME_FEAT_IRQ_CONFIG, &irqcfg); +} + +static u16 nvmet_set_feat_arbitration(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11); + struct nvmet_feat_arbitration arb = { + .hpw = (cdw11 >> 24) & 0xff, + .mpw = (cdw11 >> 16) & 0xff, + .lpw = (cdw11 >> 8) & 0xff, + .ab = cdw11 & 0x3, + }; + + if (!ctrl->ops->set_feature) { + req->error_loc = offsetof(struct nvme_common_command, cdw10); + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + + return ctrl->ops->set_feature(ctrl, NVME_FEAT_ARBITRATION, &arb); +} + void nvmet_execute_set_features(struct nvmet_req *req) { struct nvmet_subsys *subsys = nvmet_req_subsys(req); @@ -1117,6 +1357,9 @@ void nvmet_execute_set_features(struct nvmet_req *req) return; switch (cdw10 & 0xff) { + case NVME_FEAT_ARBITRATION: + status = nvmet_set_feat_arbitration(req); + break; case NVME_FEAT_NUM_QUEUES: ncqr = (cdw11 >> 16) & 0xffff; nsqr = cdw11 & 0xffff; @@ -1127,6 +1370,12 @@ void nvmet_execute_set_features(struct nvmet_req *req) nvmet_set_result(req, (subsys->max_qid - 1) | ((subsys->max_qid - 1) << 16)); break; + case NVME_FEAT_IRQ_COALESCE: + status = nvmet_set_feat_irq_coalesce(req); + break; + case NVME_FEAT_IRQ_CONFIG: + status = nvmet_set_feat_irq_config(req); + break; case NVME_FEAT_KATO: status = nvmet_set_feat_kato(req); break; @@ -1134,7 +1383,7 @@ void nvmet_execute_set_features(struct nvmet_req *req) status = nvmet_set_feat_async_event(req, NVMET_AEN_CFG_ALL); break; case NVME_FEAT_HOST_ID: - status = NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR; + status = nvmet_set_feat_host_id(req); break; case NVME_FEAT_WRITE_PROTECT: status = nvmet_set_feat_write_protect(req); @@ -1171,6 +1420,79 @@ static u16 nvmet_get_feat_write_protect(struct nvmet_req *req) return 0; } +static u16 nvmet_get_feat_irq_coalesce(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_feat_irq_coalesce irqc = { }; + u16 status; + + /* + * This feature is not supported for fabrics controllers and mandatory + * for PCI controllers. + */ + if (!nvmet_is_pci_ctrl(ctrl)) { + req->error_loc = offsetof(struct nvme_common_command, cdw10); + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + + status = ctrl->ops->get_feature(ctrl, NVME_FEAT_IRQ_COALESCE, &irqc); + if (status != NVME_SC_SUCCESS) + return status; + + nvmet_set_result(req, ((u32)irqc.time << 8) | (u32)irqc.thr); + + return NVME_SC_SUCCESS; +} + +static u16 nvmet_get_feat_irq_config(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u32 iv = le32_to_cpu(req->cmd->common.cdw11) & 0xffff; + struct nvmet_feat_irq_config irqcfg = { .iv = iv }; + u16 status; + + /* + * This feature is not supported for fabrics controllers and mandatory + * for PCI controllers. + */ + if (!nvmet_is_pci_ctrl(ctrl)) { + req->error_loc = offsetof(struct nvme_common_command, cdw10); + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + + status = ctrl->ops->get_feature(ctrl, NVME_FEAT_IRQ_CONFIG, &irqcfg); + if (status != NVME_SC_SUCCESS) + return status; + + nvmet_set_result(req, ((u32)irqcfg.cd << 16) | iv); + + return NVME_SC_SUCCESS; +} + +static u16 nvmet_get_feat_arbitration(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_feat_arbitration arb = { }; + u16 status; + + if (!ctrl->ops->get_feature) { + req->error_loc = offsetof(struct nvme_common_command, cdw10); + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + + status = ctrl->ops->get_feature(ctrl, NVME_FEAT_ARBITRATION, &arb); + if (status != NVME_SC_SUCCESS) + return status; + + nvmet_set_result(req, + ((u32)arb.hpw << 24) | + ((u32)arb.mpw << 16) | + ((u32)arb.lpw << 8) | + (arb.ab & 0x3)); + + return NVME_SC_SUCCESS; +} + void nvmet_get_feat_kato(struct nvmet_req *req) { nvmet_set_result(req, req->sq->ctrl->kato * 1000); @@ -1197,21 +1519,24 @@ void nvmet_execute_get_features(struct nvmet_req *req) * need to come up with some fake values for these. */ #if 0 - case NVME_FEAT_ARBITRATION: - break; case NVME_FEAT_POWER_MGMT: break; case NVME_FEAT_TEMP_THRESH: break; case NVME_FEAT_ERR_RECOVERY: break; - case NVME_FEAT_IRQ_COALESCE: - break; - case NVME_FEAT_IRQ_CONFIG: - break; case NVME_FEAT_WRITE_ATOMIC: break; #endif + case NVME_FEAT_ARBITRATION: + status = nvmet_get_feat_arbitration(req); + break; + case NVME_FEAT_IRQ_COALESCE: + status = nvmet_get_feat_irq_coalesce(req); + break; + case NVME_FEAT_IRQ_CONFIG: + status = nvmet_get_feat_irq_config(req); + break; case NVME_FEAT_ASYNC_EVENT: nvmet_get_feat_async_event(req); break; @@ -1292,6 +1617,27 @@ out: nvmet_req_complete(req, status); } +u32 nvmet_admin_cmd_data_len(struct nvmet_req *req) +{ + struct nvme_command *cmd = req->cmd; + + if (nvme_is_fabrics(cmd)) + return nvmet_fabrics_admin_cmd_data_len(req); + if (nvmet_is_disc_subsys(nvmet_req_subsys(req))) + return nvmet_discovery_cmd_data_len(req); + + switch (cmd->common.opcode) { + case nvme_admin_get_log_page: + return nvmet_get_log_page_len(cmd); + case nvme_admin_identify: + return NVME_IDENTIFY_DATA_SIZE; + case nvme_admin_get_features: + return nvmet_feat_data_len(req, le32_to_cpu(cmd->common.cdw10)); + default: + return 0; + } +} + u16 nvmet_parse_admin_cmd(struct nvmet_req *req) { struct nvme_command *cmd = req->cmd; @@ -1306,13 +1652,30 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) if (unlikely(ret)) return ret; + /* For PCI controllers, admin commands shall not use SGL. */ + if (nvmet_is_pci_ctrl(req->sq->ctrl) && !req->sq->qid && + cmd->common.flags & NVME_CMD_SGL_ALL) + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + if (nvmet_is_passthru_req(req)) return nvmet_parse_passthru_admin_cmd(req); switch (cmd->common.opcode) { + case nvme_admin_delete_sq: + req->execute = nvmet_execute_delete_sq; + return 0; + case nvme_admin_create_sq: + req->execute = nvmet_execute_create_sq; + return 0; case nvme_admin_get_log_page: req->execute = nvmet_execute_get_log_page; return 0; + case nvme_admin_delete_cq: + req->execute = nvmet_execute_delete_cq; + return 0; + case nvme_admin_create_cq: + req->execute = nvmet_execute_create_cq; + return 0; case nvme_admin_identify: req->execute = nvmet_execute_identify; return 0; diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index eeee9e9b854c..e44ef69dffc2 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -37,6 +37,7 @@ static struct nvmet_type_name_map nvmet_transport[] = { { NVMF_TRTYPE_RDMA, "rdma" }, { NVMF_TRTYPE_FC, "fc" }, { NVMF_TRTYPE_TCP, "tcp" }, + { NVMF_TRTYPE_PCI, "pci" }, { NVMF_TRTYPE_LOOP, "loop" }, }; @@ -46,6 +47,7 @@ static const struct nvmet_type_name_map nvmet_addr_family[] = { { NVMF_ADDR_FAMILY_IP6, "ipv6" }, { NVMF_ADDR_FAMILY_IB, "ib" }, { NVMF_ADDR_FAMILY_FC, "fc" }, + { NVMF_ADDR_FAMILY_PCI, "pci" }, { NVMF_ADDR_FAMILY_LOOP, "loop" }, }; @@ -810,18 +812,6 @@ static struct configfs_attribute *nvmet_ns_attrs[] = { NULL, }; -bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid) -{ - struct config_item *ns_item; - char name[12]; - - snprintf(name, sizeof(name), "%u", nsid); - mutex_lock(&subsys->namespaces_group.cg_subsys->su_mutex); - ns_item = config_group_find_item(&subsys->namespaces_group, name); - mutex_unlock(&subsys->namespaces_group.cg_subsys->su_mutex); - return ns_item != NULL; -} - static void nvmet_ns_release(struct config_item *item) { struct nvmet_ns *ns = to_nvmet_ns(item); @@ -1412,6 +1402,49 @@ out_unlock: } CONFIGFS_ATTR(nvmet_subsys_, attr_cntlid_max); +static ssize_t nvmet_subsys_attr_vendor_id_show(struct config_item *item, + char *page) +{ + return snprintf(page, PAGE_SIZE, "0x%x\n", to_subsys(item)->vendor_id); +} + +static ssize_t nvmet_subsys_attr_vendor_id_store(struct config_item *item, + const char *page, size_t count) +{ + u16 vid; + + if (kstrtou16(page, 0, &vid)) + return -EINVAL; + + down_write(&nvmet_config_sem); + to_subsys(item)->vendor_id = vid; + up_write(&nvmet_config_sem); + return count; +} +CONFIGFS_ATTR(nvmet_subsys_, attr_vendor_id); + +static ssize_t nvmet_subsys_attr_subsys_vendor_id_show(struct config_item *item, + char *page) +{ + return snprintf(page, PAGE_SIZE, "0x%x\n", + to_subsys(item)->subsys_vendor_id); +} + +static ssize_t nvmet_subsys_attr_subsys_vendor_id_store(struct config_item *item, + const char *page, size_t count) +{ + u16 ssvid; + + if (kstrtou16(page, 0, &ssvid)) + return -EINVAL; + + down_write(&nvmet_config_sem); + to_subsys(item)->subsys_vendor_id = ssvid; + up_write(&nvmet_config_sem); + return count; +} +CONFIGFS_ATTR(nvmet_subsys_, attr_subsys_vendor_id); + static ssize_t nvmet_subsys_attr_model_show(struct config_item *item, char *page) { @@ -1640,6 +1673,8 @@ static struct configfs_attribute *nvmet_subsys_attrs[] = { &nvmet_subsys_attr_attr_serial, &nvmet_subsys_attr_attr_cntlid_min, &nvmet_subsys_attr_attr_cntlid_max, + &nvmet_subsys_attr_attr_vendor_id, + &nvmet_subsys_attr_attr_subsys_vendor_id, &nvmet_subsys_attr_attr_model, &nvmet_subsys_attr_attr_qid_max, &nvmet_subsys_attr_attr_ieee_oui, @@ -1794,6 +1829,7 @@ static struct config_group *nvmet_referral_make( return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&port->entry); + port->disc_addr.trtype = NVMF_TRTYPE_MAX; config_group_init_type_name(&port->group, name, &nvmet_referral_type); return &port->group; @@ -2019,6 +2055,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group, port->inline_data_size = -1; /* < 0 == let the transport choose */ port->max_queue_size = -1; /* < 0 == let the transport choose */ + port->disc_addr.trtype = NVMF_TRTYPE_MAX; port->disc_addr.portid = cpu_to_le16(portid); port->disc_addr.adrfam = NVMF_ADDR_FAMILY_MAX; port->disc_addr.treq = NVMF_TREQ_DISABLE_SQFLOW; @@ -2254,12 +2291,17 @@ static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item, const char *page, size_t count) { struct list_head *entry; + char *old_nqn, *new_nqn; size_t len; len = strcspn(page, "\n"); if (!len || len > NVMF_NQN_FIELD_LEN - 1) return -EINVAL; + new_nqn = kstrndup(page, len, GFP_KERNEL); + if (!new_nqn) + return -ENOMEM; + down_write(&nvmet_config_sem); list_for_each(entry, &nvmet_subsystems_group.cg_children) { struct config_item *item = @@ -2268,13 +2310,15 @@ static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item, if (!strncmp(config_item_name(item), page, len)) { pr_err("duplicate NQN %s\n", config_item_name(item)); up_write(&nvmet_config_sem); + kfree(new_nqn); return -EINVAL; } } - memset(nvmet_disc_subsys->subsysnqn, 0, NVMF_NQN_FIELD_LEN); - memcpy(nvmet_disc_subsys->subsysnqn, page, len); + old_nqn = nvmet_disc_subsys->subsysnqn; + nvmet_disc_subsys->subsysnqn = new_nqn; up_write(&nvmet_config_sem); + kfree(old_nqn); return len; } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 1f4e9989663b..cdc4a09a6e8a 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -127,7 +127,7 @@ static u32 nvmet_max_nsid(struct nvmet_subsys *subsys) unsigned long idx; u32 nsid = 0; - xa_for_each(&subsys->namespaces, idx, cur) + nvmet_for_each_enabled_ns(&subsys->namespaces, idx, cur) nsid = cur->nsid; return nsid; @@ -441,11 +441,14 @@ u16 nvmet_req_find_ns(struct nvmet_req *req) struct nvmet_subsys *subsys = nvmet_req_subsys(req); req->ns = xa_load(&subsys->namespaces, nsid); - if (unlikely(!req->ns)) { + if (unlikely(!req->ns || !req->ns->enabled)) { req->error_loc = offsetof(struct nvme_common_command, nsid); - if (nvmet_subsys_nsid_exists(subsys, nsid)) - return NVME_SC_INTERNAL_PATH_ERROR; - return NVME_SC_INVALID_NS | NVME_STATUS_DNR; + if (!req->ns) /* ns doesn't exist! */ + return NVME_SC_INVALID_NS | NVME_STATUS_DNR; + + /* ns exists but it's disabled */ + req->ns = NULL; + return NVME_SC_INTERNAL_PATH_ERROR; } percpu_ref_get(&req->ns->ref); @@ -583,8 +586,6 @@ int nvmet_ns_enable(struct nvmet_ns *ns) goto out_unlock; ret = -EMFILE; - if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) - goto out_unlock; ret = nvmet_bdev_ns_enable(ns); if (ret == -ENOTBLK) @@ -599,38 +600,19 @@ int nvmet_ns_enable(struct nvmet_ns *ns) list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) nvmet_p2pmem_ns_add_p2p(ctrl, ns); - ret = percpu_ref_init(&ns->ref, nvmet_destroy_namespace, - 0, GFP_KERNEL); - if (ret) - goto out_dev_put; - - if (ns->nsid > subsys->max_nsid) - subsys->max_nsid = ns->nsid; - - ret = xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL); - if (ret) - goto out_restore_subsys_maxnsid; - if (ns->pr.enable) { ret = nvmet_pr_init_ns(ns); if (ret) - goto out_remove_from_subsys; + goto out_dev_put; } - subsys->nr_namespaces++; - nvmet_ns_changed(subsys, ns->nsid); ns->enabled = true; + xa_set_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED); ret = 0; out_unlock: mutex_unlock(&subsys->lock); return ret; - -out_remove_from_subsys: - xa_erase(&subsys->namespaces, ns->nsid); -out_restore_subsys_maxnsid: - subsys->max_nsid = nvmet_max_nsid(subsys); - percpu_ref_exit(&ns->ref); out_dev_put: list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid)); @@ -649,15 +631,37 @@ void nvmet_ns_disable(struct nvmet_ns *ns) goto out_unlock; ns->enabled = false; - xa_erase(&ns->subsys->namespaces, ns->nsid); - if (ns->nsid == subsys->max_nsid) - subsys->max_nsid = nvmet_max_nsid(subsys); + xa_clear_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED); list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid)); mutex_unlock(&subsys->lock); + if (ns->pr.enable) + nvmet_pr_exit_ns(ns); + + mutex_lock(&subsys->lock); + nvmet_ns_changed(subsys, ns->nsid); + nvmet_ns_dev_disable(ns); +out_unlock: + mutex_unlock(&subsys->lock); +} + +void nvmet_ns_free(struct nvmet_ns *ns) +{ + struct nvmet_subsys *subsys = ns->subsys; + + nvmet_ns_disable(ns); + + mutex_lock(&subsys->lock); + + xa_erase(&subsys->namespaces, ns->nsid); + if (ns->nsid == subsys->max_nsid) + subsys->max_nsid = nvmet_max_nsid(subsys); + + mutex_unlock(&subsys->lock); + /* * Now that we removed the namespaces from the lookup list, we * can kill the per_cpu ref and wait for any remaining references @@ -671,21 +675,9 @@ void nvmet_ns_disable(struct nvmet_ns *ns) wait_for_completion(&ns->disable_done); percpu_ref_exit(&ns->ref); - if (ns->pr.enable) - nvmet_pr_exit_ns(ns); - mutex_lock(&subsys->lock); - subsys->nr_namespaces--; - nvmet_ns_changed(subsys, ns->nsid); - nvmet_ns_dev_disable(ns); -out_unlock: mutex_unlock(&subsys->lock); -} - -void nvmet_ns_free(struct nvmet_ns *ns) -{ - nvmet_ns_disable(ns); down_write(&nvmet_ana_sem); nvmet_ana_group_enabled[ns->anagrpid]--; @@ -699,15 +691,33 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) { struct nvmet_ns *ns; + mutex_lock(&subsys->lock); + + if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) + goto out_unlock; + ns = kzalloc(sizeof(*ns), GFP_KERNEL); if (!ns) - return NULL; + goto out_unlock; init_completion(&ns->disable_done); ns->nsid = nsid; ns->subsys = subsys; + if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL)) + goto out_free; + + if (ns->nsid > subsys->max_nsid) + subsys->max_nsid = nsid; + + if (xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL)) + goto out_exit; + + subsys->nr_namespaces++; + + mutex_unlock(&subsys->lock); + down_write(&nvmet_ana_sem); ns->anagrpid = NVMET_DEFAULT_ANA_GRPID; nvmet_ana_group_enabled[ns->anagrpid]++; @@ -718,6 +728,14 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) ns->csi = NVME_CSI_NVM; return ns; +out_exit: + subsys->max_nsid = nvmet_max_nsid(subsys); + percpu_ref_exit(&ns->ref); +out_free: + kfree(ns); +out_unlock: + mutex_unlock(&subsys->lock); + return NULL; } static void nvmet_update_sq_head(struct nvmet_req *req) @@ -818,6 +836,89 @@ static void nvmet_confirm_sq(struct percpu_ref *ref) complete(&sq->confirm_done); } +u16 nvmet_check_cqid(struct nvmet_ctrl *ctrl, u16 cqid) +{ + if (!ctrl->sqs) + return NVME_SC_INTERNAL | NVME_STATUS_DNR; + + if (cqid > ctrl->subsys->max_qid) + return NVME_SC_QID_INVALID | NVME_STATUS_DNR; + + /* + * Note: For PCI controllers, the NVMe specifications allows multiple + * SQs to share a single CQ. However, we do not support this yet, so + * check that there is no SQ defined for a CQ. If one exist, then the + * CQ ID is invalid for creation as well as when the CQ is being + * deleted (as that would mean that the SQ was not deleted before the + * CQ). + */ + if (ctrl->sqs[cqid]) + return NVME_SC_QID_INVALID | NVME_STATUS_DNR; + + return NVME_SC_SUCCESS; +} + +u16 nvmet_cq_create(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, + u16 qid, u16 size) +{ + u16 status; + + status = nvmet_check_cqid(ctrl, qid); + if (status != NVME_SC_SUCCESS) + return status; + + nvmet_cq_setup(ctrl, cq, qid, size); + + return NVME_SC_SUCCESS; +} +EXPORT_SYMBOL_GPL(nvmet_cq_create); + +u16 nvmet_check_sqid(struct nvmet_ctrl *ctrl, u16 sqid, + bool create) +{ + if (!ctrl->sqs) + return NVME_SC_INTERNAL | NVME_STATUS_DNR; + + if (sqid > ctrl->subsys->max_qid) + return NVME_SC_QID_INVALID | NVME_STATUS_DNR; + + if ((create && ctrl->sqs[sqid]) || + (!create && !ctrl->sqs[sqid])) + return NVME_SC_QID_INVALID | NVME_STATUS_DNR; + + return NVME_SC_SUCCESS; +} + +u16 nvmet_sq_create(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, + u16 sqid, u16 size) +{ + u16 status; + int ret; + + if (!kref_get_unless_zero(&ctrl->ref)) + return NVME_SC_INTERNAL | NVME_STATUS_DNR; + + status = nvmet_check_sqid(ctrl, sqid, true); + if (status != NVME_SC_SUCCESS) + return status; + + ret = nvmet_sq_init(sq); + if (ret) { + status = NVME_SC_INTERNAL | NVME_STATUS_DNR; + goto ctrl_put; + } + + nvmet_sq_setup(ctrl, sq, sqid, size); + sq->ctrl = ctrl; + + return NVME_SC_SUCCESS; + +ctrl_put: + nvmet_ctrl_put(ctrl); + return status; +} +EXPORT_SYMBOL_GPL(nvmet_sq_create); + void nvmet_sq_destroy(struct nvmet_sq *sq) { struct nvmet_ctrl *ctrl = sq->ctrl; @@ -911,6 +1012,33 @@ static inline u16 nvmet_io_cmd_check_access(struct nvmet_req *req) return 0; } +static u32 nvmet_io_cmd_transfer_len(struct nvmet_req *req) +{ + struct nvme_command *cmd = req->cmd; + u32 metadata_len = 0; + + if (nvme_is_fabrics(cmd)) + return nvmet_fabrics_io_cmd_data_len(req); + + if (!req->ns) + return 0; + + switch (req->cmd->common.opcode) { + case nvme_cmd_read: + case nvme_cmd_write: + case nvme_cmd_zone_append: + if (req->sq->ctrl->pi_support && nvmet_ns_has_pi(req->ns)) + metadata_len = nvmet_rw_metadata_len(req); + return nvmet_rw_data_len(req) + metadata_len; + case nvme_cmd_dsm: + return nvmet_dsm_len(req); + case nvme_cmd_zone_mgmt_recv: + return (le32_to_cpu(req->cmd->zmr.numd) + 1) << 2; + default: + return 0; + } +} + static u16 nvmet_parse_io_cmd(struct nvmet_req *req) { struct nvme_command *cmd = req->cmd; @@ -1012,12 +1140,15 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, /* * For fabrics, PSDT field shall describe metadata pointer (MPTR) that * contains an address of a single contiguous physical buffer that is - * byte aligned. + * byte aligned. For PCI controllers, this is optional so not enforced. */ if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) { - req->error_loc = offsetof(struct nvme_common_command, flags); - status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; - goto fail; + if (!req->sq->ctrl || !nvmet_is_pci_ctrl(req->sq->ctrl)) { + req->error_loc = + offsetof(struct nvme_common_command, flags); + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto fail; + } } if (unlikely(!req->sq->ctrl)) @@ -1059,11 +1190,27 @@ void nvmet_req_uninit(struct nvmet_req *req) } EXPORT_SYMBOL_GPL(nvmet_req_uninit); +size_t nvmet_req_transfer_len(struct nvmet_req *req) +{ + if (likely(req->sq->qid != 0)) + return nvmet_io_cmd_transfer_len(req); + if (unlikely(!req->sq->ctrl)) + return nvmet_connect_cmd_data_len(req); + return nvmet_admin_cmd_data_len(req); +} +EXPORT_SYMBOL_GPL(nvmet_req_transfer_len); + bool nvmet_check_transfer_len(struct nvmet_req *req, size_t len) { if (unlikely(len != req->transfer_len)) { + u16 status; + req->error_loc = offsetof(struct nvme_common_command, dptr); - nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR); + if (req->cmd->common.flags & NVME_CMD_SGL_ALL) + status = NVME_SC_SGL_INVALID_DATA; + else + status = NVME_SC_INVALID_FIELD; + nvmet_req_complete(req, status | NVME_STATUS_DNR); return false; } @@ -1074,8 +1221,14 @@ EXPORT_SYMBOL_GPL(nvmet_check_transfer_len); bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len) { if (unlikely(data_len > req->transfer_len)) { + u16 status; + req->error_loc = offsetof(struct nvme_common_command, dptr); - nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR); + if (req->cmd->common.flags & NVME_CMD_SGL_ALL) + status = NVME_SC_SGL_INVALID_DATA; + else + status = NVME_SC_INVALID_FIELD; + nvmet_req_complete(req, status | NVME_STATUS_DNR); return false; } @@ -1166,41 +1319,6 @@ void nvmet_req_free_sgls(struct nvmet_req *req) } EXPORT_SYMBOL_GPL(nvmet_req_free_sgls); -static inline bool nvmet_cc_en(u32 cc) -{ - return (cc >> NVME_CC_EN_SHIFT) & 0x1; -} - -static inline u8 nvmet_cc_css(u32 cc) -{ - return (cc >> NVME_CC_CSS_SHIFT) & 0x7; -} - -static inline u8 nvmet_cc_mps(u32 cc) -{ - return (cc >> NVME_CC_MPS_SHIFT) & 0xf; -} - -static inline u8 nvmet_cc_ams(u32 cc) -{ - return (cc >> NVME_CC_AMS_SHIFT) & 0x7; -} - -static inline u8 nvmet_cc_shn(u32 cc) -{ - return (cc >> NVME_CC_SHN_SHIFT) & 0x3; -} - -static inline u8 nvmet_cc_iosqes(u32 cc) -{ - return (cc >> NVME_CC_IOSQES_SHIFT) & 0xf; -} - -static inline u8 nvmet_cc_iocqes(u32 cc) -{ - return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf; -} - static inline bool nvmet_css_supported(u8 cc_css) { switch (cc_css << NVME_CC_CSS_SHIFT) { @@ -1277,6 +1395,7 @@ void nvmet_update_cc(struct nvmet_ctrl *ctrl, u32 new) ctrl->csts &= ~NVME_CSTS_SHST_CMPLT; mutex_unlock(&ctrl->lock); } +EXPORT_SYMBOL_GPL(nvmet_update_cc); static void nvmet_init_cap(struct nvmet_ctrl *ctrl) { @@ -1384,17 +1503,17 @@ bool nvmet_host_allowed(struct nvmet_subsys *subsys, const char *hostnqn) * Note: ctrl->subsys->lock should be held when calling this function */ static void nvmet_setup_p2p_ns_map(struct nvmet_ctrl *ctrl, - struct nvmet_req *req) + struct device *p2p_client) { struct nvmet_ns *ns; unsigned long idx; - if (!req->p2p_client) + if (!p2p_client) return; - ctrl->p2p_client = get_device(req->p2p_client); + ctrl->p2p_client = get_device(p2p_client); - xa_for_each(&ctrl->subsys->namespaces, idx, ns) + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) nvmet_p2pmem_ns_add_p2p(ctrl, ns); } @@ -1421,45 +1540,44 @@ static void nvmet_fatal_error_handler(struct work_struct *work) ctrl->ops->delete_ctrl(ctrl); } -u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, - struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp, - uuid_t *hostid) +struct nvmet_ctrl *nvmet_alloc_ctrl(struct nvmet_alloc_ctrl_args *args) { struct nvmet_subsys *subsys; struct nvmet_ctrl *ctrl; + u32 kato = args->kato; + u8 dhchap_status; int ret; - u16 status; - status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; - subsys = nvmet_find_get_subsys(req->port, subsysnqn); + args->status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; + subsys = nvmet_find_get_subsys(args->port, args->subsysnqn); if (!subsys) { pr_warn("connect request for invalid subsystem %s!\n", - subsysnqn); - req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(subsysnqn); - req->error_loc = offsetof(struct nvme_common_command, dptr); - goto out; + args->subsysnqn); + args->result = IPO_IATTR_CONNECT_DATA(subsysnqn); + args->error_loc = offsetof(struct nvme_common_command, dptr); + return NULL; } down_read(&nvmet_config_sem); - if (!nvmet_host_allowed(subsys, hostnqn)) { + if (!nvmet_host_allowed(subsys, args->hostnqn)) { pr_info("connect by host %s for subsystem %s not allowed\n", - hostnqn, subsysnqn); - req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn); + args->hostnqn, args->subsysnqn); + args->result = IPO_IATTR_CONNECT_DATA(hostnqn); up_read(&nvmet_config_sem); - status = NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR; - req->error_loc = offsetof(struct nvme_common_command, dptr); + args->status = NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR; + args->error_loc = offsetof(struct nvme_common_command, dptr); goto out_put_subsystem; } up_read(&nvmet_config_sem); - status = NVME_SC_INTERNAL; + args->status = NVME_SC_INTERNAL; ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); if (!ctrl) goto out_put_subsystem; mutex_init(&ctrl->lock); - ctrl->port = req->port; - ctrl->ops = req->ops; + ctrl->port = args->port; + ctrl->ops = args->ops; #ifdef CONFIG_NVME_TARGET_PASSTHRU /* By default, set loop targets to clear IDS by default */ @@ -1473,8 +1591,8 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler); INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer); - memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE); - memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE); + memcpy(ctrl->subsysnqn, args->subsysnqn, NVMF_NQN_SIZE); + memcpy(ctrl->hostnqn, args->hostnqn, NVMF_NQN_SIZE); kref_init(&ctrl->ref); ctrl->subsys = subsys; @@ -1497,12 +1615,12 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, subsys->cntlid_min, subsys->cntlid_max, GFP_KERNEL); if (ret < 0) { - status = NVME_SC_CONNECT_CTRL_BUSY | NVME_STATUS_DNR; + args->status = NVME_SC_CONNECT_CTRL_BUSY | NVME_STATUS_DNR; goto out_free_sqs; } ctrl->cntlid = ret; - uuid_copy(&ctrl->hostid, hostid); + uuid_copy(&ctrl->hostid, args->hostid); /* * Discovery controllers may use some arbitrary high value @@ -1524,12 +1642,35 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, if (ret) goto init_pr_fail; list_add_tail(&ctrl->subsys_entry, &subsys->ctrls); - nvmet_setup_p2p_ns_map(ctrl, req); + nvmet_setup_p2p_ns_map(ctrl, args->p2p_client); nvmet_debugfs_ctrl_setup(ctrl); mutex_unlock(&subsys->lock); - *ctrlp = ctrl; - return 0; + if (args->hostid) + uuid_copy(&ctrl->hostid, args->hostid); + + dhchap_status = nvmet_setup_auth(ctrl); + if (dhchap_status) { + pr_err("Failed to setup authentication, dhchap status %u\n", + dhchap_status); + nvmet_ctrl_put(ctrl); + if (dhchap_status == NVME_AUTH_DHCHAP_FAILURE_FAILED) + args->status = + NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR; + else + args->status = NVME_SC_INTERNAL; + return NULL; + } + + args->status = NVME_SC_SUCCESS; + + pr_info("Created %s controller %d for subsystem %s for NQN %s%s%s.\n", + nvmet_is_disc_subsys(ctrl->subsys) ? "discovery" : "nvm", + ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn, + ctrl->pi_support ? " T10-PI is enabled" : "", + nvmet_has_auth(ctrl) ? " with DH-HMAC-CHAP" : ""); + + return ctrl; init_pr_fail: mutex_unlock(&subsys->lock); @@ -1543,9 +1684,9 @@ out_free_ctrl: kfree(ctrl); out_put_subsystem: nvmet_subsys_put(subsys); -out: - return status; + return NULL; } +EXPORT_SYMBOL_GPL(nvmet_alloc_ctrl); static void nvmet_ctrl_free(struct kref *ref) { @@ -1581,6 +1722,7 @@ void nvmet_ctrl_put(struct nvmet_ctrl *ctrl) { kref_put(&ctrl->ref, nvmet_ctrl_free); } +EXPORT_SYMBOL_GPL(nvmet_ctrl_put); void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl) { diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 28843df5fa7c..df7207640506 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -224,6 +224,9 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req) } list_for_each_entry(r, &req->port->referrals, entry) { + if (r->disc_addr.trtype == NVMF_TRTYPE_PCI) + continue; + nvmet_format_discovery_entry(hdr, r, NVME_DISC_SUBSYS_NAME, r->disc_addr.traddr, @@ -352,6 +355,20 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req) nvmet_req_complete(req, stat); } +u32 nvmet_discovery_cmd_data_len(struct nvmet_req *req) +{ + struct nvme_command *cmd = req->cmd; + + switch (cmd->common.opcode) { + case nvme_admin_get_log_page: + return nvmet_get_log_page_len(req->cmd); + case nvme_admin_identify: + return NVME_IDENTIFY_DATA_SIZE; + default: + return 0; + } +} + u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) { struct nvme_command *cmd = req->cmd; diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index 3f2857c17d95..2022757f08dc 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -179,6 +179,11 @@ static u8 nvmet_auth_failure2(void *d) return data->rescode_exp; } +u32 nvmet_auth_send_data_len(struct nvmet_req *req) +{ + return le32_to_cpu(req->cmd->auth_send.tl); +} + void nvmet_execute_auth_send(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -206,7 +211,7 @@ void nvmet_execute_auth_send(struct nvmet_req *req) offsetof(struct nvmf_auth_send_command, spsp1); goto done; } - tl = le32_to_cpu(req->cmd->auth_send.tl); + tl = nvmet_auth_send_data_len(req); if (!tl) { status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = @@ -429,6 +434,11 @@ static void nvmet_auth_failure1(struct nvmet_req *req, void *d, int al) data->rescode_exp = req->sq->dhchap_status; } +u32 nvmet_auth_receive_data_len(struct nvmet_req *req) +{ + return le32_to_cpu(req->cmd->auth_receive.al); +} + void nvmet_execute_auth_receive(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -454,7 +464,7 @@ void nvmet_execute_auth_receive(struct nvmet_req *req) offsetof(struct nvmf_auth_receive_command, spsp1); goto done; } - al = le32_to_cpu(req->cmd->auth_receive.al); + al = nvmet_auth_receive_data_len(req); if (!al) { status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; req->error_loc = diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index c49904ebb6c2..a7ff05b3be29 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -85,6 +85,22 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) nvmet_req_complete(req, status); } +u32 nvmet_fabrics_admin_cmd_data_len(struct nvmet_req *req) +{ + struct nvme_command *cmd = req->cmd; + + switch (cmd->fabrics.fctype) { +#ifdef CONFIG_NVME_TARGET_AUTH + case nvme_fabrics_type_auth_send: + return nvmet_auth_send_data_len(req); + case nvme_fabrics_type_auth_receive: + return nvmet_auth_receive_data_len(req); +#endif + default: + return 0; + } +} + u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req) { struct nvme_command *cmd = req->cmd; @@ -114,6 +130,22 @@ u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req) return 0; } +u32 nvmet_fabrics_io_cmd_data_len(struct nvmet_req *req) +{ + struct nvme_command *cmd = req->cmd; + + switch (cmd->fabrics.fctype) { +#ifdef CONFIG_NVME_TARGET_AUTH + case nvme_fabrics_type_auth_send: + return nvmet_auth_send_data_len(req); + case nvme_fabrics_type_auth_receive: + return nvmet_auth_receive_data_len(req); +#endif + default: + return 0; + } +} + u16 nvmet_parse_fabrics_io_cmd(struct nvmet_req *req) { struct nvme_command *cmd = req->cmd; @@ -213,73 +245,67 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) struct nvmf_connect_command *c = &req->cmd->connect; struct nvmf_connect_data *d; struct nvmet_ctrl *ctrl = NULL; - u16 status; - u8 dhchap_status; + struct nvmet_alloc_ctrl_args args = { + .port = req->port, + .ops = req->ops, + .p2p_client = req->p2p_client, + .kato = le32_to_cpu(c->kato), + }; if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data))) return; d = kmalloc(sizeof(*d), GFP_KERNEL); if (!d) { - status = NVME_SC_INTERNAL; + args.status = NVME_SC_INTERNAL; goto complete; } - status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d)); - if (status) + args.status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d)); + if (args.status) goto out; if (c->recfmt != 0) { pr_warn("invalid connect version (%d).\n", le16_to_cpu(c->recfmt)); - req->error_loc = offsetof(struct nvmf_connect_command, recfmt); - status = NVME_SC_CONNECT_FORMAT | NVME_STATUS_DNR; + args.error_loc = offsetof(struct nvmf_connect_command, recfmt); + args.status = NVME_SC_CONNECT_FORMAT | NVME_STATUS_DNR; goto out; } if (unlikely(d->cntlid != cpu_to_le16(0xffff))) { pr_warn("connect attempt for invalid controller ID %#x\n", d->cntlid); - status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; - req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(cntlid); + args.status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; + args.result = IPO_IATTR_CONNECT_DATA(cntlid); goto out; } d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; - status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req, - le32_to_cpu(c->kato), &ctrl, &d->hostid); - if (status) + + args.subsysnqn = d->subsysnqn; + args.hostnqn = d->hostnqn; + args.hostid = &d->hostid; + args.kato = c->kato; + + ctrl = nvmet_alloc_ctrl(&args); + if (!ctrl) goto out; - dhchap_status = nvmet_setup_auth(ctrl); - if (dhchap_status) { - pr_err("Failed to setup authentication, dhchap status %u\n", - dhchap_status); - nvmet_ctrl_put(ctrl); - if (dhchap_status == NVME_AUTH_DHCHAP_FAILURE_FAILED) - status = (NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR); - else - status = NVME_SC_INTERNAL; - goto out; - } - - status = nvmet_install_queue(ctrl, req); - if (status) { + args.status = nvmet_install_queue(ctrl, req); + if (args.status) { nvmet_ctrl_put(ctrl); goto out; } - pr_info("creating %s controller %d for subsystem %s for NQN %s%s%s.\n", - nvmet_is_disc_subsys(ctrl->subsys) ? "discovery" : "nvm", - ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn, - ctrl->pi_support ? " T10-PI is enabled" : "", - nvmet_has_auth(ctrl) ? " with DH-HMAC-CHAP" : ""); - req->cqe->result.u32 = cpu_to_le32(nvmet_connect_result(ctrl)); + args.result = cpu_to_le32(nvmet_connect_result(ctrl)); out: kfree(d); complete: - nvmet_req_complete(req, status); + req->error_loc = args.error_loc; + req->cqe->result.u32 = args.result; + nvmet_req_complete(req, args.status); } static void nvmet_execute_io_connect(struct nvmet_req *req) @@ -343,6 +369,17 @@ out_ctrl_put: goto out; } +u32 nvmet_connect_cmd_data_len(struct nvmet_req *req) +{ + struct nvme_command *cmd = req->cmd; + + if (!nvme_is_fabrics(cmd) || + cmd->fabrics.fctype != nvme_fabrics_type_connect) + return 0; + + return sizeof(struct nvmf_connect_data); +} + u16 nvmet_parse_connect_cmd(struct nvmet_req *req) { struct nvme_command *cmd = req->cmd; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 0bda83d0fc3e..c1f574fe3280 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) */ id->nsfeat |= 1 << 4; /* NPWG = Namespace Preferred Write Granularity. 0's based */ - id->npwg = lpp0b; + id->npwg = to0based(bdev_io_min(bdev) / bdev_logical_block_size(bdev)); /* NPWA = Namespace Preferred Write Alignment. 0's based */ id->npwa = id->npwg; /* NPDG = Namespace Preferred Deallocate Granularity. 0's based */ @@ -272,6 +272,9 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) iter_flags = SG_MITER_FROM_SG; } + if (req->cmd->rw.control & NVME_RW_LR) + opf |= REQ_FAILFAST_DEV; + if (is_pci_p2pdma_page(sg_page(req->sg))) opf |= REQ_NOMERGE; diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 58328b35dc96..b540216c0c9a 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -24,6 +24,7 @@ #define NVMET_DEFAULT_VS NVME_VS(2, 1, 0) +#define NVMET_NS_ENABLED XA_MARK_1 #define NVMET_ASYNC_EVENTS 4 #define NVMET_ERROR_LOG_SLOTS 128 #define NVMET_NO_ERROR_LOC ((u16)-1) @@ -33,6 +34,12 @@ #define NVMET_FR_MAX_SIZE 8 #define NVMET_PR_LOG_QUEUE_SIZE 64 +#define nvmet_for_each_ns(xa, index, entry) \ + xa_for_each(xa, index, entry) + +#define nvmet_for_each_enabled_ns(xa, index, entry) \ + xa_for_each_marked(xa, index, entry, NVMET_NS_ENABLED) + /* * Supported optional AENs: */ @@ -238,6 +245,8 @@ struct nvmet_ctrl { struct nvmet_subsys *subsys; struct nvmet_sq **sqs; + void *drvdata; + bool reset_tbkas; struct mutex lock; @@ -324,6 +333,8 @@ struct nvmet_subsys { struct config_group namespaces_group; struct config_group allowed_hosts_group; + u16 vendor_id; + u16 subsys_vendor_id; char *model_number; u32 ieee_oui; char *firmware_rev; @@ -404,6 +415,18 @@ struct nvmet_fabrics_ops { void (*discovery_chg)(struct nvmet_port *port); u8 (*get_mdts)(const struct nvmet_ctrl *ctrl); u16 (*get_max_queue_size)(const struct nvmet_ctrl *ctrl); + + /* Operations mandatory for PCI target controllers */ + u16 (*create_sq)(struct nvmet_ctrl *ctrl, u16 sqid, u16 flags, + u16 qsize, u64 prp1); + u16 (*delete_sq)(struct nvmet_ctrl *ctrl, u16 sqid); + u16 (*create_cq)(struct nvmet_ctrl *ctrl, u16 cqid, u16 flags, + u16 qsize, u64 prp1, u16 irq_vector); + u16 (*delete_cq)(struct nvmet_ctrl *ctrl, u16 cqid); + u16 (*set_feature)(const struct nvmet_ctrl *ctrl, u8 feat, + void *feat_data); + u16 (*get_feature)(const struct nvmet_ctrl *ctrl, u8 feat, + void *feat_data); }; #define NVMET_MAX_INLINE_BIOVEC 8 @@ -513,18 +536,24 @@ void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl); void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl); u16 nvmet_parse_connect_cmd(struct nvmet_req *req); +u32 nvmet_connect_cmd_data_len(struct nvmet_req *req); void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id); u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req); u16 nvmet_file_parse_io_cmd(struct nvmet_req *req); u16 nvmet_bdev_zns_parse_io_cmd(struct nvmet_req *req); +u32 nvmet_admin_cmd_data_len(struct nvmet_req *req); u16 nvmet_parse_admin_cmd(struct nvmet_req *req); +u32 nvmet_discovery_cmd_data_len(struct nvmet_req *req); u16 nvmet_parse_discovery_cmd(struct nvmet_req *req); u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req); +u32 nvmet_fabrics_admin_cmd_data_len(struct nvmet_req *req); u16 nvmet_parse_fabrics_io_cmd(struct nvmet_req *req); +u32 nvmet_fabrics_io_cmd_data_len(struct nvmet_req *req); bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops); void nvmet_req_uninit(struct nvmet_req *req); +size_t nvmet_req_transfer_len(struct nvmet_req *req); bool nvmet_check_transfer_len(struct nvmet_req *req, size_t len); bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len); void nvmet_req_complete(struct nvmet_req *req, u16 status); @@ -535,19 +564,37 @@ void nvmet_execute_set_features(struct nvmet_req *req); void nvmet_execute_get_features(struct nvmet_req *req); void nvmet_execute_keep_alive(struct nvmet_req *req); +u16 nvmet_check_cqid(struct nvmet_ctrl *ctrl, u16 cqid); void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid, u16 size); +u16 nvmet_cq_create(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid, + u16 size); +u16 nvmet_check_sqid(struct nvmet_ctrl *ctrl, u16 sqid, bool create); void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid, u16 size); +u16 nvmet_sq_create(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid, + u16 size); void nvmet_sq_destroy(struct nvmet_sq *sq); int nvmet_sq_init(struct nvmet_sq *sq); void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl); void nvmet_update_cc(struct nvmet_ctrl *ctrl, u32 new); -u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, - struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp, - uuid_t *hostid); + +struct nvmet_alloc_ctrl_args { + struct nvmet_port *port; + char *subsysnqn; + char *hostnqn; + uuid_t *hostid; + const struct nvmet_fabrics_ops *ops; + struct device *p2p_client; + u32 kato; + u32 result; + u16 error_loc; + u16 status; +}; + +struct nvmet_ctrl *nvmet_alloc_ctrl(struct nvmet_alloc_ctrl_args *args); struct nvmet_ctrl *nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid, struct nvmet_req *req); @@ -689,6 +736,11 @@ static inline bool nvmet_is_disc_subsys(struct nvmet_subsys *subsys) return subsys->type != NVME_NQN_NVME; } +static inline bool nvmet_is_pci_ctrl(struct nvmet_ctrl *ctrl) +{ + return ctrl->port->disc_addr.trtype == NVMF_TRTYPE_PCI; +} + #ifdef CONFIG_NVME_TARGET_PASSTHRU void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys); int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys); @@ -730,6 +782,41 @@ void nvmet_passthrough_override_cap(struct nvmet_ctrl *ctrl); u16 errno_to_nvme_status(struct nvmet_req *req, int errno); u16 nvmet_report_invalid_opcode(struct nvmet_req *req); +static inline bool nvmet_cc_en(u32 cc) +{ + return (cc >> NVME_CC_EN_SHIFT) & 0x1; +} + +static inline u8 nvmet_cc_css(u32 cc) +{ + return (cc >> NVME_CC_CSS_SHIFT) & 0x7; +} + +static inline u8 nvmet_cc_mps(u32 cc) +{ + return (cc >> NVME_CC_MPS_SHIFT) & 0xf; +} + +static inline u8 nvmet_cc_ams(u32 cc) +{ + return (cc >> NVME_CC_AMS_SHIFT) & 0x7; +} + +static inline u8 nvmet_cc_shn(u32 cc) +{ + return (cc >> NVME_CC_SHN_SHIFT) & 0x3; +} + +static inline u8 nvmet_cc_iosqes(u32 cc) +{ + return (cc >> NVME_CC_IOSQES_SHIFT) & 0xf; +} + +static inline u8 nvmet_cc_iocqes(u32 cc) +{ + return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf; +} + /* Convert a 32-bit number to a 16-bit 0's based number */ static inline __le16 to0based(u32 a) { @@ -766,7 +853,9 @@ static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio) } #ifdef CONFIG_NVME_TARGET_AUTH +u32 nvmet_auth_send_data_len(struct nvmet_req *req); void nvmet_execute_auth_send(struct nvmet_req *req); +u32 nvmet_auth_receive_data_len(struct nvmet_req *req); void nvmet_execute_auth_receive(struct nvmet_req *req); int nvmet_auth_set_key(struct nvmet_host *host, const char *secret, bool set_ctrl); @@ -824,4 +913,26 @@ static inline void nvmet_pr_put_ns_pc_ref(struct nvmet_pr_per_ctrl_ref *pc_ref) { percpu_ref_put(&pc_ref->ref); } + +/* + * Data for the get_feature() and set_feature() operations of PCI target + * controllers. + */ +struct nvmet_feat_irq_coalesce { + u8 thr; + u8 time; +}; + +struct nvmet_feat_irq_config { + u16 iv; + bool cd; +}; + +struct nvmet_feat_arbitration { + u8 hpw; + u8 mpw; + u8 lpw; + u8 ab; +}; + #endif /* _NVMET_H */ diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 30b21936b0c6..26e2907ce8bb 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -261,6 +261,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq) { struct scatterlist *sg; struct bio *bio; + int ret = -EINVAL; int i; if (req->sg_cnt > BIO_MAX_VECS) @@ -277,16 +278,19 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq) } for_each_sg(req->sg, sg, req->sg_cnt, i) { - if (bio_add_pc_page(rq->q, bio, sg_page(sg), sg->length, - sg->offset) < sg->length) { - nvmet_req_bio_put(req, bio); - return -EINVAL; - } + if (bio_add_page(bio, sg_page(sg), sg->length, sg->offset) < + sg->length) + goto out_bio_put; } - blk_rq_bio_prep(rq, bio, req->sg_cnt); - + ret = blk_rq_append_bio(rq, bio); + if (ret) + goto out_bio_put; return 0; + +out_bio_put: + nvmet_req_bio_put(req, bio); + return ret; } static void nvmet_passthru_execute_cmd(struct nvmet_req *req) diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c new file mode 100644 index 000000000000..ac30b42cc622 --- /dev/null +++ b/drivers/nvme/target/pci-epf.c @@ -0,0 +1,2591 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe PCI Endpoint Function target driver. + * + * Copyright (c) 2024, Western Digital Corporation or its affiliates. + * Copyright (c) 2024, Rick Wertenbroek + * REDS Institute, HEIG-VD, HES-SO, Switzerland + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "nvmet.h" + +static LIST_HEAD(nvmet_pci_epf_ports); +static DEFINE_MUTEX(nvmet_pci_epf_ports_mutex); + +/* + * Default and maximum allowed data transfer size. For the default, + * allow up to 128 page-sized segments. For the maximum allowed, + * use 4 times the default (which is completely arbitrary). + */ +#define NVMET_PCI_EPF_MAX_SEGS 128 +#define NVMET_PCI_EPF_MDTS_KB \ + (NVMET_PCI_EPF_MAX_SEGS << (PAGE_SHIFT - 10)) +#define NVMET_PCI_EPF_MAX_MDTS_KB (NVMET_PCI_EPF_MDTS_KB * 4) + +/* + * IRQ vector coalescing threshold: by default, post 8 CQEs before raising an + * interrupt vector to the host. This default 8 is completely arbitrary and can + * be changed by the host with a nvme_set_features command. + */ +#define NVMET_PCI_EPF_IV_THRESHOLD 8 + +/* + * BAR CC register and SQ polling intervals. + */ +#define NVMET_PCI_EPF_CC_POLL_INTERVAL msecs_to_jiffies(5) +#define NVMET_PCI_EPF_SQ_POLL_INTERVAL msecs_to_jiffies(5) +#define NVMET_PCI_EPF_SQ_POLL_IDLE msecs_to_jiffies(5000) + +/* + * SQ arbitration burst default: fetch at most 8 commands at a time from an SQ. + */ +#define NVMET_PCI_EPF_SQ_AB 8 + +/* + * Handling of CQs is normally immediate, unless we fail to map a CQ or the CQ + * is full, in which case we retry the CQ processing after this interval. + */ +#define NVMET_PCI_EPF_CQ_RETRY_INTERVAL msecs_to_jiffies(1) + +enum nvmet_pci_epf_queue_flags { + NVMET_PCI_EPF_Q_IS_SQ = 0, /* The queue is a submission queue */ + NVMET_PCI_EPF_Q_LIVE, /* The queue is live */ + NVMET_PCI_EPF_Q_IRQ_ENABLED, /* IRQ is enabled for this queue */ +}; + +/* + * IRQ vector descriptor. + */ +struct nvmet_pci_epf_irq_vector { + unsigned int vector; + unsigned int ref; + bool cd; + int nr_irqs; +}; + +struct nvmet_pci_epf_queue { + union { + struct nvmet_sq nvme_sq; + struct nvmet_cq nvme_cq; + }; + struct nvmet_pci_epf_ctrl *ctrl; + unsigned long flags; + + u64 pci_addr; + size_t pci_size; + struct pci_epc_map pci_map; + + u16 qid; + u16 depth; + u16 vector; + u16 head; + u16 tail; + u16 phase; + u32 db; + + size_t qes; + + struct nvmet_pci_epf_irq_vector *iv; + struct workqueue_struct *iod_wq; + struct delayed_work work; + spinlock_t lock; + struct list_head list; +}; + +/* + * PCI Root Complex (RC) address data segment for mapping an admin or + * I/O command buffer @buf of @length bytes to the PCI address @pci_addr. + */ +struct nvmet_pci_epf_segment { + void *buf; + u64 pci_addr; + u32 length; +}; + +/* + * Command descriptors. + */ +struct nvmet_pci_epf_iod { + struct list_head link; + + struct nvmet_req req; + struct nvme_command cmd; + struct nvme_completion cqe; + unsigned int status; + + struct nvmet_pci_epf_ctrl *ctrl; + + struct nvmet_pci_epf_queue *sq; + struct nvmet_pci_epf_queue *cq; + + /* Data transfer size and direction for the command. */ + size_t data_len; + enum dma_data_direction dma_dir; + + /* + * PCI Root Complex (RC) address data segments: if nr_data_segs is 1, we + * use only @data_seg. Otherwise, the array of segments @data_segs is + * allocated to manage multiple PCI address data segments. @data_sgl and + * @data_sgt are used to setup the command request for execution by the + * target core. + */ + unsigned int nr_data_segs; + struct nvmet_pci_epf_segment data_seg; + struct nvmet_pci_epf_segment *data_segs; + struct scatterlist data_sgl; + struct sg_table data_sgt; + + struct work_struct work; + struct completion done; +}; + +/* + * PCI target controller private data. + */ +struct nvmet_pci_epf_ctrl { + struct nvmet_pci_epf *nvme_epf; + struct nvmet_port *port; + struct nvmet_ctrl *tctrl; + struct device *dev; + + unsigned int nr_queues; + struct nvmet_pci_epf_queue *sq; + struct nvmet_pci_epf_queue *cq; + unsigned int sq_ab; + + mempool_t iod_pool; + void *bar; + u64 cap; + u32 cc; + u32 csts; + + size_t io_sqes; + size_t io_cqes; + + size_t mps_shift; + size_t mps; + size_t mps_mask; + + unsigned int mdts; + + struct delayed_work poll_cc; + struct delayed_work poll_sqs; + + struct mutex irq_lock; + struct nvmet_pci_epf_irq_vector *irq_vectors; + unsigned int irq_vector_threshold; + + bool link_up; + bool enabled; +}; + +/* + * PCI EPF driver private data. + */ +struct nvmet_pci_epf { + struct pci_epf *epf; + + const struct pci_epc_features *epc_features; + + void *reg_bar; + size_t msix_table_offset; + + unsigned int irq_type; + unsigned int nr_vectors; + + struct nvmet_pci_epf_ctrl ctrl; + + bool dma_enabled; + struct dma_chan *dma_tx_chan; + struct mutex dma_tx_lock; + struct dma_chan *dma_rx_chan; + struct mutex dma_rx_lock; + + struct mutex mmio_lock; + + /* PCI endpoint function configfs attributes. */ + struct config_group group; + __le16 portid; + char subsysnqn[NVMF_NQN_SIZE]; + unsigned int mdts_kb; +}; + +static inline u32 nvmet_pci_epf_bar_read32(struct nvmet_pci_epf_ctrl *ctrl, + u32 off) +{ + __le32 *bar_reg = ctrl->bar + off; + + return le32_to_cpu(READ_ONCE(*bar_reg)); +} + +static inline void nvmet_pci_epf_bar_write32(struct nvmet_pci_epf_ctrl *ctrl, + u32 off, u32 val) +{ + __le32 *bar_reg = ctrl->bar + off; + + WRITE_ONCE(*bar_reg, cpu_to_le32(val)); +} + +static inline u64 nvmet_pci_epf_bar_read64(struct nvmet_pci_epf_ctrl *ctrl, + u32 off) +{ + return (u64)nvmet_pci_epf_bar_read32(ctrl, off) | + ((u64)nvmet_pci_epf_bar_read32(ctrl, off + 4) << 32); +} + +static inline void nvmet_pci_epf_bar_write64(struct nvmet_pci_epf_ctrl *ctrl, + u32 off, u64 val) +{ + nvmet_pci_epf_bar_write32(ctrl, off, val & 0xFFFFFFFF); + nvmet_pci_epf_bar_write32(ctrl, off + 4, (val >> 32) & 0xFFFFFFFF); +} + +static inline int nvmet_pci_epf_mem_map(struct nvmet_pci_epf *nvme_epf, + u64 pci_addr, size_t size, struct pci_epc_map *map) +{ + struct pci_epf *epf = nvme_epf->epf; + + return pci_epc_mem_map(epf->epc, epf->func_no, epf->vfunc_no, + pci_addr, size, map); +} + +static inline void nvmet_pci_epf_mem_unmap(struct nvmet_pci_epf *nvme_epf, + struct pci_epc_map *map) +{ + struct pci_epf *epf = nvme_epf->epf; + + pci_epc_mem_unmap(epf->epc, epf->func_no, epf->vfunc_no, map); +} + +struct nvmet_pci_epf_dma_filter { + struct device *dev; + u32 dma_mask; +}; + +static bool nvmet_pci_epf_dma_filter(struct dma_chan *chan, void *arg) +{ + struct nvmet_pci_epf_dma_filter *filter = arg; + struct dma_slave_caps caps; + + memset(&caps, 0, sizeof(caps)); + dma_get_slave_caps(chan, &caps); + + return chan->device->dev == filter->dev && + (filter->dma_mask & caps.directions); +} + +static void nvmet_pci_epf_init_dma(struct nvmet_pci_epf *nvme_epf) +{ + struct pci_epf *epf = nvme_epf->epf; + struct device *dev = &epf->dev; + struct nvmet_pci_epf_dma_filter filter; + struct dma_chan *chan; + dma_cap_mask_t mask; + + mutex_init(&nvme_epf->dma_rx_lock); + mutex_init(&nvme_epf->dma_tx_lock); + + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); + + filter.dev = epf->epc->dev.parent; + filter.dma_mask = BIT(DMA_DEV_TO_MEM); + + chan = dma_request_channel(mask, nvmet_pci_epf_dma_filter, &filter); + if (!chan) + goto out_dma_no_rx; + + nvme_epf->dma_rx_chan = chan; + + filter.dma_mask = BIT(DMA_MEM_TO_DEV); + chan = dma_request_channel(mask, nvmet_pci_epf_dma_filter, &filter); + if (!chan) + goto out_dma_no_tx; + + nvme_epf->dma_tx_chan = chan; + + nvme_epf->dma_enabled = true; + + dev_dbg(dev, "Using DMA RX channel %s, maximum segment size %u B\n", + dma_chan_name(chan), + dma_get_max_seg_size(dmaengine_get_dma_device(chan))); + + dev_dbg(dev, "Using DMA TX channel %s, maximum segment size %u B\n", + dma_chan_name(chan), + dma_get_max_seg_size(dmaengine_get_dma_device(chan))); + + return; + +out_dma_no_tx: + dma_release_channel(nvme_epf->dma_rx_chan); + nvme_epf->dma_rx_chan = NULL; + +out_dma_no_rx: + mutex_destroy(&nvme_epf->dma_rx_lock); + mutex_destroy(&nvme_epf->dma_tx_lock); + nvme_epf->dma_enabled = false; + + dev_info(&epf->dev, "DMA not supported, falling back to MMIO\n"); +} + +static void nvmet_pci_epf_deinit_dma(struct nvmet_pci_epf *nvme_epf) +{ + if (!nvme_epf->dma_enabled) + return; + + dma_release_channel(nvme_epf->dma_tx_chan); + nvme_epf->dma_tx_chan = NULL; + dma_release_channel(nvme_epf->dma_rx_chan); + nvme_epf->dma_rx_chan = NULL; + mutex_destroy(&nvme_epf->dma_rx_lock); + mutex_destroy(&nvme_epf->dma_tx_lock); + nvme_epf->dma_enabled = false; +} + +static int nvmet_pci_epf_dma_transfer(struct nvmet_pci_epf *nvme_epf, + struct nvmet_pci_epf_segment *seg, enum dma_data_direction dir) +{ + struct pci_epf *epf = nvme_epf->epf; + struct dma_async_tx_descriptor *desc; + struct dma_slave_config sconf = {}; + struct device *dev = &epf->dev; + struct device *dma_dev; + struct dma_chan *chan; + dma_cookie_t cookie; + dma_addr_t dma_addr; + struct mutex *lock; + int ret; + + switch (dir) { + case DMA_FROM_DEVICE: + lock = &nvme_epf->dma_rx_lock; + chan = nvme_epf->dma_rx_chan; + sconf.direction = DMA_DEV_TO_MEM; + sconf.src_addr = seg->pci_addr; + break; + case DMA_TO_DEVICE: + lock = &nvme_epf->dma_tx_lock; + chan = nvme_epf->dma_tx_chan; + sconf.direction = DMA_MEM_TO_DEV; + sconf.dst_addr = seg->pci_addr; + break; + default: + return -EINVAL; + } + + mutex_lock(lock); + + dma_dev = dmaengine_get_dma_device(chan); + dma_addr = dma_map_single(dma_dev, seg->buf, seg->length, dir); + ret = dma_mapping_error(dma_dev, dma_addr); + if (ret) + goto unlock; + + ret = dmaengine_slave_config(chan, &sconf); + if (ret) { + dev_err(dev, "Failed to configure DMA channel\n"); + goto unmap; + } + + desc = dmaengine_prep_slave_single(chan, dma_addr, seg->length, + sconf.direction, DMA_CTRL_ACK); + if (!desc) { + dev_err(dev, "Failed to prepare DMA\n"); + ret = -EIO; + goto unmap; + } + + cookie = dmaengine_submit(desc); + ret = dma_submit_error(cookie); + if (ret) { + dev_err(dev, "Failed to do DMA submit (err=%d)\n", ret); + goto unmap; + } + + if (dma_sync_wait(chan, cookie) != DMA_COMPLETE) { + dev_err(dev, "DMA transfer failed\n"); + ret = -EIO; + } + + dmaengine_terminate_sync(chan); + +unmap: + dma_unmap_single(dma_dev, dma_addr, seg->length, dir); + +unlock: + mutex_unlock(lock); + + return ret; +} + +static int nvmet_pci_epf_mmio_transfer(struct nvmet_pci_epf *nvme_epf, + struct nvmet_pci_epf_segment *seg, enum dma_data_direction dir) +{ + u64 pci_addr = seg->pci_addr; + u32 length = seg->length; + void *buf = seg->buf; + struct pci_epc_map map; + int ret = -EINVAL; + + /* + * Note: MMIO transfers do not need serialization but this is a + * simple way to avoid using too many mapping windows. + */ + mutex_lock(&nvme_epf->mmio_lock); + + while (length) { + ret = nvmet_pci_epf_mem_map(nvme_epf, pci_addr, length, &map); + if (ret) + break; + + switch (dir) { + case DMA_FROM_DEVICE: + memcpy_fromio(buf, map.virt_addr, map.pci_size); + break; + case DMA_TO_DEVICE: + memcpy_toio(map.virt_addr, buf, map.pci_size); + break; + default: + ret = -EINVAL; + goto unlock; + } + + pci_addr += map.pci_size; + buf += map.pci_size; + length -= map.pci_size; + + nvmet_pci_epf_mem_unmap(nvme_epf, &map); + } + +unlock: + mutex_unlock(&nvme_epf->mmio_lock); + + return ret; +} + +static inline int nvmet_pci_epf_transfer_seg(struct nvmet_pci_epf *nvme_epf, + struct nvmet_pci_epf_segment *seg, enum dma_data_direction dir) +{ + if (nvme_epf->dma_enabled) + return nvmet_pci_epf_dma_transfer(nvme_epf, seg, dir); + + return nvmet_pci_epf_mmio_transfer(nvme_epf, seg, dir); +} + +static inline int nvmet_pci_epf_transfer(struct nvmet_pci_epf_ctrl *ctrl, + void *buf, u64 pci_addr, u32 length, + enum dma_data_direction dir) +{ + struct nvmet_pci_epf_segment seg = { + .buf = buf, + .pci_addr = pci_addr, + .length = length, + }; + + return nvmet_pci_epf_transfer_seg(ctrl->nvme_epf, &seg, dir); +} + +static int nvmet_pci_epf_alloc_irq_vectors(struct nvmet_pci_epf_ctrl *ctrl) +{ + ctrl->irq_vectors = kcalloc(ctrl->nr_queues, + sizeof(struct nvmet_pci_epf_irq_vector), + GFP_KERNEL); + if (!ctrl->irq_vectors) + return -ENOMEM; + + mutex_init(&ctrl->irq_lock); + + return 0; +} + +static void nvmet_pci_epf_free_irq_vectors(struct nvmet_pci_epf_ctrl *ctrl) +{ + if (ctrl->irq_vectors) { + mutex_destroy(&ctrl->irq_lock); + kfree(ctrl->irq_vectors); + ctrl->irq_vectors = NULL; + } +} + +static struct nvmet_pci_epf_irq_vector * +nvmet_pci_epf_find_irq_vector(struct nvmet_pci_epf_ctrl *ctrl, u16 vector) +{ + struct nvmet_pci_epf_irq_vector *iv; + int i; + + lockdep_assert_held(&ctrl->irq_lock); + + for (i = 0; i < ctrl->nr_queues; i++) { + iv = &ctrl->irq_vectors[i]; + if (iv->ref && iv->vector == vector) + return iv; + } + + return NULL; +} + +static struct nvmet_pci_epf_irq_vector * +nvmet_pci_epf_add_irq_vector(struct nvmet_pci_epf_ctrl *ctrl, u16 vector) +{ + struct nvmet_pci_epf_irq_vector *iv; + int i; + + mutex_lock(&ctrl->irq_lock); + + iv = nvmet_pci_epf_find_irq_vector(ctrl, vector); + if (iv) { + iv->ref++; + goto unlock; + } + + for (i = 0; i < ctrl->nr_queues; i++) { + iv = &ctrl->irq_vectors[i]; + if (!iv->ref) + break; + } + + if (WARN_ON_ONCE(!iv)) + goto unlock; + + iv->ref = 1; + iv->vector = vector; + iv->nr_irqs = 0; + +unlock: + mutex_unlock(&ctrl->irq_lock); + + return iv; +} + +static void nvmet_pci_epf_remove_irq_vector(struct nvmet_pci_epf_ctrl *ctrl, + u16 vector) +{ + struct nvmet_pci_epf_irq_vector *iv; + + mutex_lock(&ctrl->irq_lock); + + iv = nvmet_pci_epf_find_irq_vector(ctrl, vector); + if (iv) { + iv->ref--; + if (!iv->ref) { + iv->vector = 0; + iv->nr_irqs = 0; + } + } + + mutex_unlock(&ctrl->irq_lock); +} + +static bool nvmet_pci_epf_should_raise_irq(struct nvmet_pci_epf_ctrl *ctrl, + struct nvmet_pci_epf_queue *cq, bool force) +{ + struct nvmet_pci_epf_irq_vector *iv = cq->iv; + bool ret; + + if (!test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags)) + return false; + + /* IRQ coalescing for the admin queue is not allowed. */ + if (!cq->qid) + return true; + + if (iv->cd) + return true; + + if (force) { + ret = iv->nr_irqs > 0; + } else { + iv->nr_irqs++; + ret = iv->nr_irqs >= ctrl->irq_vector_threshold; + } + if (ret) + iv->nr_irqs = 0; + + return ret; +} + +static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl, + struct nvmet_pci_epf_queue *cq, bool force) +{ + struct nvmet_pci_epf *nvme_epf = ctrl->nvme_epf; + struct pci_epf *epf = nvme_epf->epf; + int ret = 0; + + if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags)) + return; + + mutex_lock(&ctrl->irq_lock); + + if (!nvmet_pci_epf_should_raise_irq(ctrl, cq, force)) + goto unlock; + + switch (nvme_epf->irq_type) { + case PCI_IRQ_MSIX: + case PCI_IRQ_MSI: + ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no, + nvme_epf->irq_type, cq->vector + 1); + if (!ret) + break; + /* + * If we got an error, it is likely because the host is using + * legacy IRQs (e.g. BIOS, grub). + */ + fallthrough; + case PCI_IRQ_INTX: + ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no, + PCI_IRQ_INTX, 0); + break; + default: + WARN_ON_ONCE(1); + ret = -EINVAL; + break; + } + + if (ret) + dev_err(ctrl->dev, "Failed to raise IRQ (err=%d)\n", ret); + +unlock: + mutex_unlock(&ctrl->irq_lock); +} + +static inline const char *nvmet_pci_epf_iod_name(struct nvmet_pci_epf_iod *iod) +{ + return nvme_opcode_str(iod->sq->qid, iod->cmd.common.opcode); +} + +static void nvmet_pci_epf_exec_iod_work(struct work_struct *work); + +static struct nvmet_pci_epf_iod * +nvmet_pci_epf_alloc_iod(struct nvmet_pci_epf_queue *sq) +{ + struct nvmet_pci_epf_ctrl *ctrl = sq->ctrl; + struct nvmet_pci_epf_iod *iod; + + iod = mempool_alloc(&ctrl->iod_pool, GFP_KERNEL); + if (unlikely(!iod)) + return NULL; + + memset(iod, 0, sizeof(*iod)); + iod->req.cmd = &iod->cmd; + iod->req.cqe = &iod->cqe; + iod->req.port = ctrl->port; + iod->ctrl = ctrl; + iod->sq = sq; + iod->cq = &ctrl->cq[sq->qid]; + INIT_LIST_HEAD(&iod->link); + iod->dma_dir = DMA_NONE; + INIT_WORK(&iod->work, nvmet_pci_epf_exec_iod_work); + init_completion(&iod->done); + + return iod; +} + +/* + * Allocate or grow a command table of PCI segments. + */ +static int nvmet_pci_epf_alloc_iod_data_segs(struct nvmet_pci_epf_iod *iod, + int nsegs) +{ + struct nvmet_pci_epf_segment *segs; + int nr_segs = iod->nr_data_segs + nsegs; + + segs = krealloc(iod->data_segs, + nr_segs * sizeof(struct nvmet_pci_epf_segment), + GFP_KERNEL | __GFP_ZERO); + if (!segs) + return -ENOMEM; + + iod->nr_data_segs = nr_segs; + iod->data_segs = segs; + + return 0; +} + +static void nvmet_pci_epf_free_iod(struct nvmet_pci_epf_iod *iod) +{ + int i; + + if (iod->data_segs) { + for (i = 0; i < iod->nr_data_segs; i++) + kfree(iod->data_segs[i].buf); + if (iod->data_segs != &iod->data_seg) + kfree(iod->data_segs); + } + if (iod->data_sgt.nents > 1) + sg_free_table(&iod->data_sgt); + mempool_free(iod, &iod->ctrl->iod_pool); +} + +static int nvmet_pci_epf_transfer_iod_data(struct nvmet_pci_epf_iod *iod) +{ + struct nvmet_pci_epf *nvme_epf = iod->ctrl->nvme_epf; + struct nvmet_pci_epf_segment *seg = &iod->data_segs[0]; + int i, ret; + + /* Split the data transfer according to the PCI segments. */ + for (i = 0; i < iod->nr_data_segs; i++, seg++) { + ret = nvmet_pci_epf_transfer_seg(nvme_epf, seg, iod->dma_dir); + if (ret) { + iod->status = NVME_SC_DATA_XFER_ERROR | NVME_STATUS_DNR; + return ret; + } + } + + return 0; +} + +static inline u32 nvmet_pci_epf_prp_ofst(struct nvmet_pci_epf_ctrl *ctrl, + u64 prp) +{ + return prp & ctrl->mps_mask; +} + +static inline size_t nvmet_pci_epf_prp_size(struct nvmet_pci_epf_ctrl *ctrl, + u64 prp) +{ + return ctrl->mps - nvmet_pci_epf_prp_ofst(ctrl, prp); +} + +/* + * Transfer a PRP list from the host and return the number of prps. + */ +static int nvmet_pci_epf_get_prp_list(struct nvmet_pci_epf_ctrl *ctrl, u64 prp, + size_t xfer_len, __le64 *prps) +{ + size_t nr_prps = (xfer_len + ctrl->mps_mask) >> ctrl->mps_shift; + u32 length; + int ret; + + /* + * Compute the number of PRPs required for the number of bytes to + * transfer (xfer_len). If this number overflows the memory page size + * with the PRP list pointer specified, only return the space available + * in the memory page, the last PRP in there will be a PRP list pointer + * to the remaining PRPs. + */ + length = min(nvmet_pci_epf_prp_size(ctrl, prp), nr_prps << 3); + ret = nvmet_pci_epf_transfer(ctrl, prps, prp, length, DMA_FROM_DEVICE); + if (ret) + return ret; + + return length >> 3; +} + +static int nvmet_pci_epf_iod_parse_prp_list(struct nvmet_pci_epf_ctrl *ctrl, + struct nvmet_pci_epf_iod *iod) +{ + struct nvme_command *cmd = &iod->cmd; + struct nvmet_pci_epf_segment *seg; + size_t size = 0, ofst, prp_size, xfer_len; + size_t transfer_len = iod->data_len; + int nr_segs, nr_prps = 0; + u64 pci_addr, prp; + int i = 0, ret; + __le64 *prps; + + prps = kzalloc(ctrl->mps, GFP_KERNEL); + if (!prps) + goto err_internal; + + /* + * Allocate PCI segments for the command: this considers the worst case + * scenario where all prps are discontiguous, so get as many segments + * as we can have prps. In practice, most of the time, we will have + * far less PCI segments than prps. + */ + prp = le64_to_cpu(cmd->common.dptr.prp1); + if (!prp) + goto err_invalid_field; + + ofst = nvmet_pci_epf_prp_ofst(ctrl, prp); + nr_segs = (transfer_len + ofst + ctrl->mps - 1) >> ctrl->mps_shift; + + ret = nvmet_pci_epf_alloc_iod_data_segs(iod, nr_segs); + if (ret) + goto err_internal; + + /* Set the first segment using prp1. */ + seg = &iod->data_segs[0]; + seg->pci_addr = prp; + seg->length = nvmet_pci_epf_prp_size(ctrl, prp); + + size = seg->length; + pci_addr = prp + size; + nr_segs = 1; + + /* + * Now build the PCI address segments using the PRP lists, starting + * from prp2. + */ + prp = le64_to_cpu(cmd->common.dptr.prp2); + if (!prp) + goto err_invalid_field; + + while (size < transfer_len) { + xfer_len = transfer_len - size; + + if (!nr_prps) { + nr_prps = nvmet_pci_epf_get_prp_list(ctrl, prp, + xfer_len, prps); + if (nr_prps < 0) + goto err_internal; + + i = 0; + ofst = 0; + } + + /* Current entry */ + prp = le64_to_cpu(prps[i]); + if (!prp) + goto err_invalid_field; + + /* Did we reach the last PRP entry of the list? */ + if (xfer_len > ctrl->mps && i == nr_prps - 1) { + /* We need more PRPs: PRP is a list pointer. */ + nr_prps = 0; + continue; + } + + /* Only the first PRP is allowed to have an offset. */ + if (nvmet_pci_epf_prp_ofst(ctrl, prp)) + goto err_invalid_offset; + + if (prp != pci_addr) { + /* Discontiguous prp: new segment. */ + nr_segs++; + if (WARN_ON_ONCE(nr_segs > iod->nr_data_segs)) + goto err_internal; + + seg++; + seg->pci_addr = prp; + seg->length = 0; + pci_addr = prp; + } + + prp_size = min_t(size_t, ctrl->mps, xfer_len); + seg->length += prp_size; + pci_addr += prp_size; + size += prp_size; + + i++; + } + + iod->nr_data_segs = nr_segs; + ret = 0; + + if (size != transfer_len) { + dev_err(ctrl->dev, + "PRPs transfer length mismatch: got %zu B, need %zu B\n", + size, transfer_len); + goto err_internal; + } + + kfree(prps); + + return 0; + +err_invalid_offset: + dev_err(ctrl->dev, "PRPs list invalid offset\n"); + iod->status = NVME_SC_PRP_INVALID_OFFSET | NVME_STATUS_DNR; + goto err; + +err_invalid_field: + dev_err(ctrl->dev, "PRPs list invalid field\n"); + iod->status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto err; + +err_internal: + dev_err(ctrl->dev, "PRPs list internal error\n"); + iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR; + +err: + kfree(prps); + return -EINVAL; +} + +static int nvmet_pci_epf_iod_parse_prp_simple(struct nvmet_pci_epf_ctrl *ctrl, + struct nvmet_pci_epf_iod *iod) +{ + struct nvme_command *cmd = &iod->cmd; + size_t transfer_len = iod->data_len; + int ret, nr_segs = 1; + u64 prp1, prp2 = 0; + size_t prp1_size; + + prp1 = le64_to_cpu(cmd->common.dptr.prp1); + prp1_size = nvmet_pci_epf_prp_size(ctrl, prp1); + + /* For commands crossing a page boundary, we should have prp2. */ + if (transfer_len > prp1_size) { + prp2 = le64_to_cpu(cmd->common.dptr.prp2); + if (!prp2) { + iod->status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + return -EINVAL; + } + if (nvmet_pci_epf_prp_ofst(ctrl, prp2)) { + iod->status = + NVME_SC_PRP_INVALID_OFFSET | NVME_STATUS_DNR; + return -EINVAL; + } + if (prp2 != prp1 + prp1_size) + nr_segs = 2; + } + + if (nr_segs == 1) { + iod->nr_data_segs = 1; + iod->data_segs = &iod->data_seg; + iod->data_segs[0].pci_addr = prp1; + iod->data_segs[0].length = transfer_len; + return 0; + } + + ret = nvmet_pci_epf_alloc_iod_data_segs(iod, nr_segs); + if (ret) { + iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR; + return ret; + } + + iod->data_segs[0].pci_addr = prp1; + iod->data_segs[0].length = prp1_size; + iod->data_segs[1].pci_addr = prp2; + iod->data_segs[1].length = transfer_len - prp1_size; + + return 0; +} + +static int nvmet_pci_epf_iod_parse_prps(struct nvmet_pci_epf_iod *iod) +{ + struct nvmet_pci_epf_ctrl *ctrl = iod->ctrl; + u64 prp1 = le64_to_cpu(iod->cmd.common.dptr.prp1); + size_t ofst; + + /* Get the PCI address segments for the command using its PRPs. */ + ofst = nvmet_pci_epf_prp_ofst(ctrl, prp1); + if (ofst & 0x3) { + iod->status = NVME_SC_PRP_INVALID_OFFSET | NVME_STATUS_DNR; + return -EINVAL; + } + + if (iod->data_len + ofst <= ctrl->mps * 2) + return nvmet_pci_epf_iod_parse_prp_simple(ctrl, iod); + + return nvmet_pci_epf_iod_parse_prp_list(ctrl, iod); +} + +/* + * Transfer an SGL segment from the host and return the number of data + * descriptors and the next segment descriptor, if any. + */ +static struct nvme_sgl_desc * +nvmet_pci_epf_get_sgl_segment(struct nvmet_pci_epf_ctrl *ctrl, + struct nvme_sgl_desc *desc, unsigned int *nr_sgls) +{ + struct nvme_sgl_desc *sgls; + u32 length = le32_to_cpu(desc->length); + int nr_descs, ret; + void *buf; + + buf = kmalloc(length, GFP_KERNEL); + if (!buf) + return NULL; + + ret = nvmet_pci_epf_transfer(ctrl, buf, le64_to_cpu(desc->addr), length, + DMA_FROM_DEVICE); + if (ret) { + kfree(buf); + return NULL; + } + + sgls = buf; + nr_descs = length / sizeof(struct nvme_sgl_desc); + if (sgls[nr_descs - 1].type == (NVME_SGL_FMT_SEG_DESC << 4) || + sgls[nr_descs - 1].type == (NVME_SGL_FMT_LAST_SEG_DESC << 4)) { + /* + * We have another SGL segment following this one: do not count + * it as a regular data SGL descriptor and return it to the + * caller. + */ + *desc = sgls[nr_descs - 1]; + nr_descs--; + } else { + /* We do not have another SGL segment after this one. */ + desc->length = 0; + } + + *nr_sgls = nr_descs; + + return sgls; +} + +static int nvmet_pci_epf_iod_parse_sgl_segments(struct nvmet_pci_epf_ctrl *ctrl, + struct nvmet_pci_epf_iod *iod) +{ + struct nvme_command *cmd = &iod->cmd; + struct nvme_sgl_desc seg = cmd->common.dptr.sgl; + struct nvme_sgl_desc *sgls = NULL; + int n = 0, i, nr_sgls; + int ret; + + /* + * We do not support inline data nor keyed SGLs, so we should be seeing + * only segment descriptors. + */ + if (seg.type != (NVME_SGL_FMT_SEG_DESC << 4) && + seg.type != (NVME_SGL_FMT_LAST_SEG_DESC << 4)) { + iod->status = NVME_SC_SGL_INVALID_TYPE | NVME_STATUS_DNR; + return -EIO; + } + + while (seg.length) { + sgls = nvmet_pci_epf_get_sgl_segment(ctrl, &seg, &nr_sgls); + if (!sgls) { + iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR; + return -EIO; + } + + /* Grow the PCI segment table as needed. */ + ret = nvmet_pci_epf_alloc_iod_data_segs(iod, nr_sgls); + if (ret) { + iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR; + goto out; + } + + /* + * Parse the SGL descriptors to build the PCI segment table, + * checking the descriptor type as we go. + */ + for (i = 0; i < nr_sgls; i++) { + if (sgls[i].type != (NVME_SGL_FMT_DATA_DESC << 4)) { + iod->status = NVME_SC_SGL_INVALID_TYPE | + NVME_STATUS_DNR; + goto out; + } + iod->data_segs[n].pci_addr = le64_to_cpu(sgls[i].addr); + iod->data_segs[n].length = le32_to_cpu(sgls[i].length); + n++; + } + + kfree(sgls); + } + + out: + if (iod->status != NVME_SC_SUCCESS) { + kfree(sgls); + return -EIO; + } + + return 0; +} + +static int nvmet_pci_epf_iod_parse_sgls(struct nvmet_pci_epf_iod *iod) +{ + struct nvmet_pci_epf_ctrl *ctrl = iod->ctrl; + struct nvme_sgl_desc *sgl = &iod->cmd.common.dptr.sgl; + + if (sgl->type == (NVME_SGL_FMT_DATA_DESC << 4)) { + /* Single data descriptor case. */ + iod->nr_data_segs = 1; + iod->data_segs = &iod->data_seg; + iod->data_seg.pci_addr = le64_to_cpu(sgl->addr); + iod->data_seg.length = le32_to_cpu(sgl->length); + return 0; + } + + return nvmet_pci_epf_iod_parse_sgl_segments(ctrl, iod); +} + +static int nvmet_pci_epf_alloc_iod_data_buf(struct nvmet_pci_epf_iod *iod) +{ + struct nvmet_pci_epf_ctrl *ctrl = iod->ctrl; + struct nvmet_req *req = &iod->req; + struct nvmet_pci_epf_segment *seg; + struct scatterlist *sg; + int ret, i; + + if (iod->data_len > ctrl->mdts) { + iod->status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + return -EINVAL; + } + + /* + * Get the PCI address segments for the command data buffer using either + * its SGLs or PRPs. + */ + if (iod->cmd.common.flags & NVME_CMD_SGL_ALL) + ret = nvmet_pci_epf_iod_parse_sgls(iod); + else + ret = nvmet_pci_epf_iod_parse_prps(iod); + if (ret) + return ret; + + /* Get a command buffer using SGLs matching the PCI segments. */ + if (iod->nr_data_segs == 1) { + sg_init_table(&iod->data_sgl, 1); + iod->data_sgt.sgl = &iod->data_sgl; + iod->data_sgt.nents = 1; + iod->data_sgt.orig_nents = 1; + } else { + ret = sg_alloc_table(&iod->data_sgt, iod->nr_data_segs, + GFP_KERNEL); + if (ret) + goto err_nomem; + } + + for_each_sgtable_sg(&iod->data_sgt, sg, i) { + seg = &iod->data_segs[i]; + seg->buf = kmalloc(seg->length, GFP_KERNEL); + if (!seg->buf) + goto err_nomem; + sg_set_buf(sg, seg->buf, seg->length); + } + + req->transfer_len = iod->data_len; + req->sg = iod->data_sgt.sgl; + req->sg_cnt = iod->data_sgt.nents; + + return 0; + +err_nomem: + iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR; + return -ENOMEM; +} + +static void nvmet_pci_epf_complete_iod(struct nvmet_pci_epf_iod *iod) +{ + struct nvmet_pci_epf_queue *cq = iod->cq; + unsigned long flags; + + /* Print an error message for failed commands, except AENs. */ + iod->status = le16_to_cpu(iod->cqe.status) >> 1; + if (iod->status && iod->cmd.common.opcode != nvme_admin_async_event) + dev_err(iod->ctrl->dev, + "CQ[%d]: Command %s (0x%x) status 0x%0x\n", + iod->sq->qid, nvmet_pci_epf_iod_name(iod), + iod->cmd.common.opcode, iod->status); + + /* + * Add the command to the list of completed commands and schedule the + * CQ work. + */ + spin_lock_irqsave(&cq->lock, flags); + list_add_tail(&iod->link, &cq->list); + queue_delayed_work(system_highpri_wq, &cq->work, 0); + spin_unlock_irqrestore(&cq->lock, flags); +} + +static void nvmet_pci_epf_drain_queue(struct nvmet_pci_epf_queue *queue) +{ + struct nvmet_pci_epf_iod *iod; + unsigned long flags; + + spin_lock_irqsave(&queue->lock, flags); + while (!list_empty(&queue->list)) { + iod = list_first_entry(&queue->list, struct nvmet_pci_epf_iod, + link); + list_del_init(&iod->link); + nvmet_pci_epf_free_iod(iod); + } + spin_unlock_irqrestore(&queue->lock, flags); +} + +static int nvmet_pci_epf_add_port(struct nvmet_port *port) +{ + mutex_lock(&nvmet_pci_epf_ports_mutex); + list_add_tail(&port->entry, &nvmet_pci_epf_ports); + mutex_unlock(&nvmet_pci_epf_ports_mutex); + return 0; +} + +static void nvmet_pci_epf_remove_port(struct nvmet_port *port) +{ + mutex_lock(&nvmet_pci_epf_ports_mutex); + list_del_init(&port->entry); + mutex_unlock(&nvmet_pci_epf_ports_mutex); +} + +static struct nvmet_port * +nvmet_pci_epf_find_port(struct nvmet_pci_epf_ctrl *ctrl, __le16 portid) +{ + struct nvmet_port *p, *port = NULL; + + mutex_lock(&nvmet_pci_epf_ports_mutex); + list_for_each_entry(p, &nvmet_pci_epf_ports, entry) { + if (p->disc_addr.portid == portid) { + port = p; + break; + } + } + mutex_unlock(&nvmet_pci_epf_ports_mutex); + + return port; +} + +static void nvmet_pci_epf_queue_response(struct nvmet_req *req) +{ + struct nvmet_pci_epf_iod *iod = + container_of(req, struct nvmet_pci_epf_iod, req); + + iod->status = le16_to_cpu(req->cqe->status) >> 1; + + /* If we have no data to transfer, directly complete the command. */ + if (!iod->data_len || iod->dma_dir != DMA_TO_DEVICE) { + nvmet_pci_epf_complete_iod(iod); + return; + } + + complete(&iod->done); +} + +static u8 nvmet_pci_epf_get_mdts(const struct nvmet_ctrl *tctrl) +{ + struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata; + int page_shift = NVME_CAP_MPSMIN(tctrl->cap) + 12; + + return ilog2(ctrl->mdts) - page_shift; +} + +static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl, + u16 cqid, u16 flags, u16 qsize, u64 pci_addr, u16 vector) +{ + struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata; + struct nvmet_pci_epf_queue *cq = &ctrl->cq[cqid]; + u16 status; + + if (test_and_set_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags)) + return NVME_SC_QID_INVALID | NVME_STATUS_DNR; + + if (!(flags & NVME_QUEUE_PHYS_CONTIG)) + return NVME_SC_INVALID_QUEUE | NVME_STATUS_DNR; + + if (flags & NVME_CQ_IRQ_ENABLED) + set_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags); + + cq->pci_addr = pci_addr; + cq->qid = cqid; + cq->depth = qsize + 1; + cq->vector = vector; + cq->head = 0; + cq->tail = 0; + cq->phase = 1; + cq->db = NVME_REG_DBS + (((cqid * 2) + 1) * sizeof(u32)); + nvmet_pci_epf_bar_write32(ctrl, cq->db, 0); + + if (!cqid) + cq->qes = sizeof(struct nvme_completion); + else + cq->qes = ctrl->io_cqes; + cq->pci_size = cq->qes * cq->depth; + + cq->iv = nvmet_pci_epf_add_irq_vector(ctrl, vector); + if (!cq->iv) { + status = NVME_SC_INTERNAL | NVME_STATUS_DNR; + goto err; + } + + status = nvmet_cq_create(tctrl, &cq->nvme_cq, cqid, cq->depth); + if (status != NVME_SC_SUCCESS) + goto err; + + dev_dbg(ctrl->dev, "CQ[%u]: %u entries of %zu B, IRQ vector %u\n", + cqid, qsize, cq->qes, cq->vector); + + return NVME_SC_SUCCESS; + +err: + clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags); + clear_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags); + return status; +} + +static u16 nvmet_pci_epf_delete_cq(struct nvmet_ctrl *tctrl, u16 cqid) +{ + struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata; + struct nvmet_pci_epf_queue *cq = &ctrl->cq[cqid]; + + if (!test_and_clear_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags)) + return NVME_SC_QID_INVALID | NVME_STATUS_DNR; + + cancel_delayed_work_sync(&cq->work); + nvmet_pci_epf_drain_queue(cq); + nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector); + + return NVME_SC_SUCCESS; +} + +static u16 nvmet_pci_epf_create_sq(struct nvmet_ctrl *tctrl, + u16 sqid, u16 flags, u16 qsize, u64 pci_addr) +{ + struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata; + struct nvmet_pci_epf_queue *sq = &ctrl->sq[sqid]; + u16 status; + + if (test_and_set_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags)) + return NVME_SC_QID_INVALID | NVME_STATUS_DNR; + + if (!(flags & NVME_QUEUE_PHYS_CONTIG)) + return NVME_SC_INVALID_QUEUE | NVME_STATUS_DNR; + + sq->pci_addr = pci_addr; + sq->qid = sqid; + sq->depth = qsize + 1; + sq->head = 0; + sq->tail = 0; + sq->phase = 0; + sq->db = NVME_REG_DBS + (sqid * 2 * sizeof(u32)); + nvmet_pci_epf_bar_write32(ctrl, sq->db, 0); + if (!sqid) + sq->qes = 1UL << NVME_ADM_SQES; + else + sq->qes = ctrl->io_sqes; + sq->pci_size = sq->qes * sq->depth; + + status = nvmet_sq_create(tctrl, &sq->nvme_sq, sqid, sq->depth); + if (status != NVME_SC_SUCCESS) + goto out_clear_bit; + + sq->iod_wq = alloc_workqueue("sq%d_wq", WQ_UNBOUND, + min_t(int, sq->depth, WQ_MAX_ACTIVE), sqid); + if (!sq->iod_wq) { + dev_err(ctrl->dev, "Failed to create SQ %d work queue\n", sqid); + status = NVME_SC_INTERNAL | NVME_STATUS_DNR; + goto out_destroy_sq; + } + + dev_dbg(ctrl->dev, "SQ[%u]: %u entries of %zu B\n", + sqid, qsize, sq->qes); + + return NVME_SC_SUCCESS; + +out_destroy_sq: + nvmet_sq_destroy(&sq->nvme_sq); +out_clear_bit: + clear_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags); + return status; +} + +static u16 nvmet_pci_epf_delete_sq(struct nvmet_ctrl *tctrl, u16 sqid) +{ + struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata; + struct nvmet_pci_epf_queue *sq = &ctrl->sq[sqid]; + + if (!test_and_clear_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags)) + return NVME_SC_QID_INVALID | NVME_STATUS_DNR; + + flush_workqueue(sq->iod_wq); + destroy_workqueue(sq->iod_wq); + sq->iod_wq = NULL; + + nvmet_pci_epf_drain_queue(sq); + + if (sq->nvme_sq.ctrl) + nvmet_sq_destroy(&sq->nvme_sq); + + return NVME_SC_SUCCESS; +} + +static u16 nvmet_pci_epf_get_feat(const struct nvmet_ctrl *tctrl, + u8 feat, void *data) +{ + struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata; + struct nvmet_feat_arbitration *arb; + struct nvmet_feat_irq_coalesce *irqc; + struct nvmet_feat_irq_config *irqcfg; + struct nvmet_pci_epf_irq_vector *iv; + u16 status; + + switch (feat) { + case NVME_FEAT_ARBITRATION: + arb = data; + if (!ctrl->sq_ab) + arb->ab = 0x7; + else + arb->ab = ilog2(ctrl->sq_ab); + return NVME_SC_SUCCESS; + + case NVME_FEAT_IRQ_COALESCE: + irqc = data; + irqc->thr = ctrl->irq_vector_threshold; + irqc->time = 0; + return NVME_SC_SUCCESS; + + case NVME_FEAT_IRQ_CONFIG: + irqcfg = data; + mutex_lock(&ctrl->irq_lock); + iv = nvmet_pci_epf_find_irq_vector(ctrl, irqcfg->iv); + if (iv) { + irqcfg->cd = iv->cd; + status = NVME_SC_SUCCESS; + } else { + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + mutex_unlock(&ctrl->irq_lock); + return status; + + default: + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } +} + +static u16 nvmet_pci_epf_set_feat(const struct nvmet_ctrl *tctrl, + u8 feat, void *data) +{ + struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata; + struct nvmet_feat_arbitration *arb; + struct nvmet_feat_irq_coalesce *irqc; + struct nvmet_feat_irq_config *irqcfg; + struct nvmet_pci_epf_irq_vector *iv; + u16 status; + + switch (feat) { + case NVME_FEAT_ARBITRATION: + arb = data; + if (arb->ab == 0x7) + ctrl->sq_ab = 0; + else + ctrl->sq_ab = 1 << arb->ab; + return NVME_SC_SUCCESS; + + case NVME_FEAT_IRQ_COALESCE: + /* + * Since we do not implement precise IRQ coalescing timing, + * ignore the time field. + */ + irqc = data; + ctrl->irq_vector_threshold = irqc->thr + 1; + return NVME_SC_SUCCESS; + + case NVME_FEAT_IRQ_CONFIG: + irqcfg = data; + mutex_lock(&ctrl->irq_lock); + iv = nvmet_pci_epf_find_irq_vector(ctrl, irqcfg->iv); + if (iv) { + iv->cd = irqcfg->cd; + status = NVME_SC_SUCCESS; + } else { + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } + mutex_unlock(&ctrl->irq_lock); + return status; + + default: + return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + } +} + +static const struct nvmet_fabrics_ops nvmet_pci_epf_fabrics_ops = { + .owner = THIS_MODULE, + .type = NVMF_TRTYPE_PCI, + .add_port = nvmet_pci_epf_add_port, + .remove_port = nvmet_pci_epf_remove_port, + .queue_response = nvmet_pci_epf_queue_response, + .get_mdts = nvmet_pci_epf_get_mdts, + .create_cq = nvmet_pci_epf_create_cq, + .delete_cq = nvmet_pci_epf_delete_cq, + .create_sq = nvmet_pci_epf_create_sq, + .delete_sq = nvmet_pci_epf_delete_sq, + .get_feature = nvmet_pci_epf_get_feat, + .set_feature = nvmet_pci_epf_set_feat, +}; + +static void nvmet_pci_epf_cq_work(struct work_struct *work); + +static void nvmet_pci_epf_init_queue(struct nvmet_pci_epf_ctrl *ctrl, + unsigned int qid, bool sq) +{ + struct nvmet_pci_epf_queue *queue; + + if (sq) { + queue = &ctrl->sq[qid]; + set_bit(NVMET_PCI_EPF_Q_IS_SQ, &queue->flags); + } else { + queue = &ctrl->cq[qid]; + INIT_DELAYED_WORK(&queue->work, nvmet_pci_epf_cq_work); + } + queue->ctrl = ctrl; + queue->qid = qid; + spin_lock_init(&queue->lock); + INIT_LIST_HEAD(&queue->list); +} + +static int nvmet_pci_epf_alloc_queues(struct nvmet_pci_epf_ctrl *ctrl) +{ + unsigned int qid; + + ctrl->sq = kcalloc(ctrl->nr_queues, + sizeof(struct nvmet_pci_epf_queue), GFP_KERNEL); + if (!ctrl->sq) + return -ENOMEM; + + ctrl->cq = kcalloc(ctrl->nr_queues, + sizeof(struct nvmet_pci_epf_queue), GFP_KERNEL); + if (!ctrl->cq) { + kfree(ctrl->sq); + ctrl->sq = NULL; + return -ENOMEM; + } + + for (qid = 0; qid < ctrl->nr_queues; qid++) { + nvmet_pci_epf_init_queue(ctrl, qid, true); + nvmet_pci_epf_init_queue(ctrl, qid, false); + } + + return 0; +} + +static void nvmet_pci_epf_free_queues(struct nvmet_pci_epf_ctrl *ctrl) +{ + kfree(ctrl->sq); + ctrl->sq = NULL; + kfree(ctrl->cq); + ctrl->cq = NULL; +} + +static int nvmet_pci_epf_map_queue(struct nvmet_pci_epf_ctrl *ctrl, + struct nvmet_pci_epf_queue *queue) +{ + struct nvmet_pci_epf *nvme_epf = ctrl->nvme_epf; + int ret; + + ret = nvmet_pci_epf_mem_map(nvme_epf, queue->pci_addr, + queue->pci_size, &queue->pci_map); + if (ret) { + dev_err(ctrl->dev, "Failed to map queue %u (err=%d)\n", + queue->qid, ret); + return ret; + } + + if (queue->pci_map.pci_size < queue->pci_size) { + dev_err(ctrl->dev, "Invalid partial mapping of queue %u\n", + queue->qid); + nvmet_pci_epf_mem_unmap(nvme_epf, &queue->pci_map); + return -ENOMEM; + } + + return 0; +} + +static inline void nvmet_pci_epf_unmap_queue(struct nvmet_pci_epf_ctrl *ctrl, + struct nvmet_pci_epf_queue *queue) +{ + nvmet_pci_epf_mem_unmap(ctrl->nvme_epf, &queue->pci_map); +} + +static void nvmet_pci_epf_exec_iod_work(struct work_struct *work) +{ + struct nvmet_pci_epf_iod *iod = + container_of(work, struct nvmet_pci_epf_iod, work); + struct nvmet_req *req = &iod->req; + int ret; + + if (!iod->ctrl->link_up) { + nvmet_pci_epf_free_iod(iod); + return; + } + + if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &iod->sq->flags)) { + iod->status = NVME_SC_QID_INVALID | NVME_STATUS_DNR; + goto complete; + } + + if (!nvmet_req_init(req, &iod->cq->nvme_cq, &iod->sq->nvme_sq, + &nvmet_pci_epf_fabrics_ops)) + goto complete; + + iod->data_len = nvmet_req_transfer_len(req); + if (iod->data_len) { + /* + * Get the data DMA transfer direction. Here "device" means the + * PCI root-complex host. + */ + if (nvme_is_write(&iod->cmd)) + iod->dma_dir = DMA_FROM_DEVICE; + else + iod->dma_dir = DMA_TO_DEVICE; + + /* + * Setup the command data buffer and get the command data from + * the host if needed. + */ + ret = nvmet_pci_epf_alloc_iod_data_buf(iod); + if (!ret && iod->dma_dir == DMA_FROM_DEVICE) + ret = nvmet_pci_epf_transfer_iod_data(iod); + if (ret) { + nvmet_req_uninit(req); + goto complete; + } + } + + req->execute(req); + + /* + * If we do not have data to transfer after the command execution + * finishes, nvmet_pci_epf_queue_response() will complete the command + * directly. No need to wait for the completion in this case. + */ + if (!iod->data_len || iod->dma_dir != DMA_TO_DEVICE) + return; + + wait_for_completion(&iod->done); + + if (iod->status == NVME_SC_SUCCESS) { + WARN_ON_ONCE(!iod->data_len || iod->dma_dir != DMA_TO_DEVICE); + nvmet_pci_epf_transfer_iod_data(iod); + } + +complete: + nvmet_pci_epf_complete_iod(iod); +} + +static int nvmet_pci_epf_process_sq(struct nvmet_pci_epf_ctrl *ctrl, + struct nvmet_pci_epf_queue *sq) +{ + struct nvmet_pci_epf_iod *iod; + int ret, n = 0; + + sq->tail = nvmet_pci_epf_bar_read32(ctrl, sq->db); + while (sq->head != sq->tail && (!ctrl->sq_ab || n < ctrl->sq_ab)) { + iod = nvmet_pci_epf_alloc_iod(sq); + if (!iod) + break; + + /* Get the NVMe command submitted by the host. */ + ret = nvmet_pci_epf_transfer(ctrl, &iod->cmd, + sq->pci_addr + sq->head * sq->qes, + sq->qes, DMA_FROM_DEVICE); + if (ret) { + /* Not much we can do... */ + nvmet_pci_epf_free_iod(iod); + break; + } + + dev_dbg(ctrl->dev, "SQ[%u]: head %u, tail %u, command %s\n", + sq->qid, sq->head, sq->tail, + nvmet_pci_epf_iod_name(iod)); + + sq->head++; + if (sq->head == sq->depth) + sq->head = 0; + n++; + + queue_work_on(WORK_CPU_UNBOUND, sq->iod_wq, &iod->work); + + sq->tail = nvmet_pci_epf_bar_read32(ctrl, sq->db); + } + + return n; +} + +static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work) +{ + struct nvmet_pci_epf_ctrl *ctrl = + container_of(work, struct nvmet_pci_epf_ctrl, poll_sqs.work); + struct nvmet_pci_epf_queue *sq; + unsigned long last = 0; + int i, nr_sqs; + + while (ctrl->link_up && ctrl->enabled) { + nr_sqs = 0; + /* Do round-robin arbitration. */ + for (i = 0; i < ctrl->nr_queues; i++) { + sq = &ctrl->sq[i]; + if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags)) + continue; + if (nvmet_pci_epf_process_sq(ctrl, sq)) + nr_sqs++; + } + + if (nr_sqs) { + last = jiffies; + continue; + } + + /* + * If we have not received any command on any queue for more + * than NVMET_PCI_EPF_SQ_POLL_IDLE, assume we are idle and + * reschedule. This avoids "burning" a CPU when the controller + * is idle for a long time. + */ + if (time_is_before_jiffies(last + NVMET_PCI_EPF_SQ_POLL_IDLE)) + break; + + cpu_relax(); + } + + schedule_delayed_work(&ctrl->poll_sqs, NVMET_PCI_EPF_SQ_POLL_INTERVAL); +} + +static void nvmet_pci_epf_cq_work(struct work_struct *work) +{ + struct nvmet_pci_epf_queue *cq = + container_of(work, struct nvmet_pci_epf_queue, work.work); + struct nvmet_pci_epf_ctrl *ctrl = cq->ctrl; + struct nvme_completion *cqe; + struct nvmet_pci_epf_iod *iod; + unsigned long flags; + int ret, n = 0; + + ret = nvmet_pci_epf_map_queue(ctrl, cq); + if (ret) + goto again; + + while (test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags) && ctrl->link_up) { + + /* Check that the CQ is not full. */ + cq->head = nvmet_pci_epf_bar_read32(ctrl, cq->db); + if (cq->head == cq->tail + 1) { + ret = -EAGAIN; + break; + } + + spin_lock_irqsave(&cq->lock, flags); + iod = list_first_entry_or_null(&cq->list, + struct nvmet_pci_epf_iod, link); + if (iod) + list_del_init(&iod->link); + spin_unlock_irqrestore(&cq->lock, flags); + + if (!iod) + break; + + /* Post the IOD completion entry. */ + cqe = &iod->cqe; + cqe->status = cpu_to_le16((iod->status << 1) | cq->phase); + + dev_dbg(ctrl->dev, + "CQ[%u]: %s status 0x%x, result 0x%llx, head %u, tail %u, phase %u\n", + cq->qid, nvmet_pci_epf_iod_name(iod), iod->status, + le64_to_cpu(cqe->result.u64), cq->head, cq->tail, + cq->phase); + + memcpy_toio(cq->pci_map.virt_addr + cq->tail * cq->qes, + cqe, cq->qes); + + cq->tail++; + if (cq->tail >= cq->depth) { + cq->tail = 0; + cq->phase ^= 1; + } + + nvmet_pci_epf_free_iod(iod); + + /* Signal the host. */ + nvmet_pci_epf_raise_irq(ctrl, cq, false); + n++; + } + + nvmet_pci_epf_unmap_queue(ctrl, cq); + + /* + * We do not support precise IRQ coalescing time (100ns units as per + * NVMe specifications). So if we have posted completion entries without + * reaching the interrupt coalescing threshold, raise an interrupt. + */ + if (n) + nvmet_pci_epf_raise_irq(ctrl, cq, true); + +again: + if (ret < 0) + queue_delayed_work(system_highpri_wq, &cq->work, + NVMET_PCI_EPF_CQ_RETRY_INTERVAL); +} + +static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) +{ + u64 pci_addr, asq, acq; + u32 aqa; + u16 status, qsize; + + if (ctrl->enabled) + return 0; + + dev_info(ctrl->dev, "Enabling controller\n"); + + ctrl->mps_shift = nvmet_cc_mps(ctrl->cc) + 12; + ctrl->mps = 1UL << ctrl->mps_shift; + ctrl->mps_mask = ctrl->mps - 1; + + ctrl->io_sqes = 1UL << nvmet_cc_iosqes(ctrl->cc); + if (ctrl->io_sqes < sizeof(struct nvme_command)) { + dev_err(ctrl->dev, "Unsupported I/O SQES %zu (need %zu)\n", + ctrl->io_sqes, sizeof(struct nvme_command)); + return -EINVAL; + } + + ctrl->io_cqes = 1UL << nvmet_cc_iocqes(ctrl->cc); + if (ctrl->io_cqes < sizeof(struct nvme_completion)) { + dev_err(ctrl->dev, "Unsupported I/O CQES %zu (need %zu)\n", + ctrl->io_sqes, sizeof(struct nvme_completion)); + return -EINVAL; + } + + /* Create the admin queue. */ + aqa = nvmet_pci_epf_bar_read32(ctrl, NVME_REG_AQA); + asq = nvmet_pci_epf_bar_read64(ctrl, NVME_REG_ASQ); + acq = nvmet_pci_epf_bar_read64(ctrl, NVME_REG_ACQ); + + qsize = (aqa & 0x0fff0000) >> 16; + pci_addr = acq & GENMASK_ULL(63, 12); + status = nvmet_pci_epf_create_cq(ctrl->tctrl, 0, + NVME_CQ_IRQ_ENABLED | NVME_QUEUE_PHYS_CONTIG, + qsize, pci_addr, 0); + if (status != NVME_SC_SUCCESS) { + dev_err(ctrl->dev, "Failed to create admin completion queue\n"); + return -EINVAL; + } + + qsize = aqa & 0x00000fff; + pci_addr = asq & GENMASK_ULL(63, 12); + status = nvmet_pci_epf_create_sq(ctrl->tctrl, 0, NVME_QUEUE_PHYS_CONTIG, + qsize, pci_addr); + if (status != NVME_SC_SUCCESS) { + dev_err(ctrl->dev, "Failed to create admin submission queue\n"); + nvmet_pci_epf_delete_cq(ctrl->tctrl, 0); + return -EINVAL; + } + + ctrl->sq_ab = NVMET_PCI_EPF_SQ_AB; + ctrl->irq_vector_threshold = NVMET_PCI_EPF_IV_THRESHOLD; + ctrl->enabled = true; + + /* Start polling the controller SQs. */ + schedule_delayed_work(&ctrl->poll_sqs, 0); + + return 0; +} + +static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) +{ + int qid; + + if (!ctrl->enabled) + return; + + dev_info(ctrl->dev, "Disabling controller\n"); + + ctrl->enabled = false; + cancel_delayed_work_sync(&ctrl->poll_sqs); + + /* Delete all I/O queues first. */ + for (qid = 1; qid < ctrl->nr_queues; qid++) + nvmet_pci_epf_delete_sq(ctrl->tctrl, qid); + + for (qid = 1; qid < ctrl->nr_queues; qid++) + nvmet_pci_epf_delete_cq(ctrl->tctrl, qid); + + /* Delete the admin queue last. */ + nvmet_pci_epf_delete_sq(ctrl->tctrl, 0); + nvmet_pci_epf_delete_cq(ctrl->tctrl, 0); +} + +static void nvmet_pci_epf_poll_cc_work(struct work_struct *work) +{ + struct nvmet_pci_epf_ctrl *ctrl = + container_of(work, struct nvmet_pci_epf_ctrl, poll_cc.work); + u32 old_cc, new_cc; + int ret; + + if (!ctrl->tctrl) + return; + + old_cc = ctrl->cc; + new_cc = nvmet_pci_epf_bar_read32(ctrl, NVME_REG_CC); + ctrl->cc = new_cc; + + if (nvmet_cc_en(new_cc) && !nvmet_cc_en(old_cc)) { + ret = nvmet_pci_epf_enable_ctrl(ctrl); + if (ret) + return; + ctrl->csts |= NVME_CSTS_RDY; + } + + if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc)) { + nvmet_pci_epf_disable_ctrl(ctrl); + ctrl->csts &= ~NVME_CSTS_RDY; + } + + if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc)) { + nvmet_pci_epf_disable_ctrl(ctrl); + ctrl->csts |= NVME_CSTS_SHST_CMPLT; + } + + if (!nvmet_cc_shn(new_cc) && nvmet_cc_shn(old_cc)) + ctrl->csts &= ~NVME_CSTS_SHST_CMPLT; + + nvmet_update_cc(ctrl->tctrl, ctrl->cc); + nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts); + + schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL); +} + +static void nvmet_pci_epf_init_bar(struct nvmet_pci_epf_ctrl *ctrl) +{ + struct nvmet_ctrl *tctrl = ctrl->tctrl; + + ctrl->bar = ctrl->nvme_epf->reg_bar; + + /* Copy the target controller capabilities as a base. */ + ctrl->cap = tctrl->cap; + + /* Contiguous Queues Required (CQR). */ + ctrl->cap |= 0x1ULL << 16; + + /* Set Doorbell stride to 4B (DSTRB). */ + ctrl->cap &= ~GENMASK_ULL(35, 32); + + /* Clear NVM Subsystem Reset Supported (NSSRS). */ + ctrl->cap &= ~(0x1ULL << 36); + + /* Clear Boot Partition Support (BPS). */ + ctrl->cap &= ~(0x1ULL << 45); + + /* Clear Persistent Memory Region Supported (PMRS). */ + ctrl->cap &= ~(0x1ULL << 56); + + /* Clear Controller Memory Buffer Supported (CMBS). */ + ctrl->cap &= ~(0x1ULL << 57); + + /* Controller configuration. */ + ctrl->cc = tctrl->cc & (~NVME_CC_ENABLE); + + /* Controller status. */ + ctrl->csts = ctrl->tctrl->csts; + + nvmet_pci_epf_bar_write64(ctrl, NVME_REG_CAP, ctrl->cap); + nvmet_pci_epf_bar_write32(ctrl, NVME_REG_VS, tctrl->subsys->ver); + nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts); + nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc); +} + +static int nvmet_pci_epf_create_ctrl(struct nvmet_pci_epf *nvme_epf, + unsigned int max_nr_queues) +{ + struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl; + struct nvmet_alloc_ctrl_args args = {}; + char hostnqn[NVMF_NQN_SIZE]; + uuid_t id; + int ret; + + memset(ctrl, 0, sizeof(*ctrl)); + ctrl->dev = &nvme_epf->epf->dev; + mutex_init(&ctrl->irq_lock); + ctrl->nvme_epf = nvme_epf; + ctrl->mdts = nvme_epf->mdts_kb * SZ_1K; + INIT_DELAYED_WORK(&ctrl->poll_cc, nvmet_pci_epf_poll_cc_work); + INIT_DELAYED_WORK(&ctrl->poll_sqs, nvmet_pci_epf_poll_sqs_work); + + ret = mempool_init_kmalloc_pool(&ctrl->iod_pool, + max_nr_queues * NVMET_MAX_QUEUE_SIZE, + sizeof(struct nvmet_pci_epf_iod)); + if (ret) { + dev_err(ctrl->dev, "Failed to initialize IOD mempool\n"); + return ret; + } + + ctrl->port = nvmet_pci_epf_find_port(ctrl, nvme_epf->portid); + if (!ctrl->port) { + dev_err(ctrl->dev, "Port not found\n"); + ret = -EINVAL; + goto out_mempool_exit; + } + + /* Create the target controller. */ + uuid_gen(&id); + snprintf(hostnqn, NVMF_NQN_SIZE, + "nqn.2014-08.org.nvmexpress:uuid:%pUb", &id); + args.port = ctrl->port; + args.subsysnqn = nvme_epf->subsysnqn; + memset(&id, 0, sizeof(uuid_t)); + args.hostid = &id; + args.hostnqn = hostnqn; + args.ops = &nvmet_pci_epf_fabrics_ops; + + ctrl->tctrl = nvmet_alloc_ctrl(&args); + if (!ctrl->tctrl) { + dev_err(ctrl->dev, "Failed to create target controller\n"); + ret = -ENOMEM; + goto out_mempool_exit; + } + ctrl->tctrl->drvdata = ctrl; + + /* We do not support protection information for now. */ + if (ctrl->tctrl->pi_support) { + dev_err(ctrl->dev, + "Protection information (PI) is not supported\n"); + ret = -ENOTSUPP; + goto out_put_ctrl; + } + + /* Allocate our queues, up to the maximum number. */ + ctrl->nr_queues = min(ctrl->tctrl->subsys->max_qid + 1, max_nr_queues); + ret = nvmet_pci_epf_alloc_queues(ctrl); + if (ret) + goto out_put_ctrl; + + /* + * Allocate the IRQ vectors descriptors. We cannot have more than the + * maximum number of queues. + */ + ret = nvmet_pci_epf_alloc_irq_vectors(ctrl); + if (ret) + goto out_free_queues; + + dev_info(ctrl->dev, + "New PCI ctrl \"%s\", %u I/O queues, mdts %u B\n", + ctrl->tctrl->subsys->subsysnqn, ctrl->nr_queues - 1, + ctrl->mdts); + + /* Initialize BAR 0 using the target controller CAP. */ + nvmet_pci_epf_init_bar(ctrl); + + return 0; + +out_free_queues: + nvmet_pci_epf_free_queues(ctrl); +out_put_ctrl: + nvmet_ctrl_put(ctrl->tctrl); + ctrl->tctrl = NULL; +out_mempool_exit: + mempool_exit(&ctrl->iod_pool); + return ret; +} + +static void nvmet_pci_epf_start_ctrl(struct nvmet_pci_epf_ctrl *ctrl) +{ + schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL); +} + +static void nvmet_pci_epf_stop_ctrl(struct nvmet_pci_epf_ctrl *ctrl) +{ + cancel_delayed_work_sync(&ctrl->poll_cc); + + nvmet_pci_epf_disable_ctrl(ctrl); +} + +static void nvmet_pci_epf_destroy_ctrl(struct nvmet_pci_epf_ctrl *ctrl) +{ + if (!ctrl->tctrl) + return; + + dev_info(ctrl->dev, "Destroying PCI ctrl \"%s\"\n", + ctrl->tctrl->subsys->subsysnqn); + + nvmet_pci_epf_stop_ctrl(ctrl); + + nvmet_pci_epf_free_queues(ctrl); + nvmet_pci_epf_free_irq_vectors(ctrl); + + nvmet_ctrl_put(ctrl->tctrl); + ctrl->tctrl = NULL; + + mempool_exit(&ctrl->iod_pool); +} + +static int nvmet_pci_epf_configure_bar(struct nvmet_pci_epf *nvme_epf) +{ + struct pci_epf *epf = nvme_epf->epf; + const struct pci_epc_features *epc_features = nvme_epf->epc_features; + size_t reg_size, reg_bar_size; + size_t msix_table_size = 0; + + /* + * The first free BAR will be our register BAR and per NVMe + * specifications, it must be BAR 0. + */ + if (pci_epc_get_first_free_bar(epc_features) != BAR_0) { + dev_err(&epf->dev, "BAR 0 is not free\n"); + return -ENODEV; + } + + if (epc_features->bar[BAR_0].only_64bit) + epf->bar[BAR_0].flags |= PCI_BASE_ADDRESS_MEM_TYPE_64; + + /* + * Calculate the size of the register bar: NVMe registers first with + * enough space for the doorbells, followed by the MSI-X table + * if supported. + */ + reg_size = NVME_REG_DBS + (NVMET_NR_QUEUES * 2 * sizeof(u32)); + reg_size = ALIGN(reg_size, 8); + + if (epc_features->msix_capable) { + size_t pba_size; + + msix_table_size = PCI_MSIX_ENTRY_SIZE * epf->msix_interrupts; + nvme_epf->msix_table_offset = reg_size; + pba_size = ALIGN(DIV_ROUND_UP(epf->msix_interrupts, 8), 8); + + reg_size += msix_table_size + pba_size; + } + + if (epc_features->bar[BAR_0].type == BAR_FIXED) { + if (reg_size > epc_features->bar[BAR_0].fixed_size) { + dev_err(&epf->dev, + "BAR 0 size %llu B too small, need %zu B\n", + epc_features->bar[BAR_0].fixed_size, + reg_size); + return -ENOMEM; + } + reg_bar_size = epc_features->bar[BAR_0].fixed_size; + } else { + reg_bar_size = ALIGN(reg_size, max(epc_features->align, 4096)); + } + + nvme_epf->reg_bar = pci_epf_alloc_space(epf, reg_bar_size, BAR_0, + epc_features, PRIMARY_INTERFACE); + if (!nvme_epf->reg_bar) { + dev_err(&epf->dev, "Failed to allocate BAR 0\n"); + return -ENOMEM; + } + memset(nvme_epf->reg_bar, 0, reg_bar_size); + + return 0; +} + +static void nvmet_pci_epf_free_bar(struct nvmet_pci_epf *nvme_epf) +{ + struct pci_epf *epf = nvme_epf->epf; + + if (!nvme_epf->reg_bar) + return; + + pci_epf_free_space(epf, nvme_epf->reg_bar, BAR_0, PRIMARY_INTERFACE); + nvme_epf->reg_bar = NULL; +} + +static void nvmet_pci_epf_clear_bar(struct nvmet_pci_epf *nvme_epf) +{ + struct pci_epf *epf = nvme_epf->epf; + + pci_epc_clear_bar(epf->epc, epf->func_no, epf->vfunc_no, + &epf->bar[BAR_0]); +} + +static int nvmet_pci_epf_init_irq(struct nvmet_pci_epf *nvme_epf) +{ + const struct pci_epc_features *epc_features = nvme_epf->epc_features; + struct pci_epf *epf = nvme_epf->epf; + int ret; + + /* Enable MSI-X if supported, otherwise, use MSI. */ + if (epc_features->msix_capable && epf->msix_interrupts) { + ret = pci_epc_set_msix(epf->epc, epf->func_no, epf->vfunc_no, + epf->msix_interrupts, BAR_0, + nvme_epf->msix_table_offset); + if (ret) { + dev_err(&epf->dev, "Failed to configure MSI-X\n"); + return ret; + } + + nvme_epf->nr_vectors = epf->msix_interrupts; + nvme_epf->irq_type = PCI_IRQ_MSIX; + + return 0; + } + + if (epc_features->msi_capable && epf->msi_interrupts) { + ret = pci_epc_set_msi(epf->epc, epf->func_no, epf->vfunc_no, + epf->msi_interrupts); + if (ret) { + dev_err(&epf->dev, "Failed to configure MSI\n"); + return ret; + } + + nvme_epf->nr_vectors = epf->msi_interrupts; + nvme_epf->irq_type = PCI_IRQ_MSI; + + return 0; + } + + /* MSI and MSI-X are not supported: fall back to INTx. */ + nvme_epf->nr_vectors = 1; + nvme_epf->irq_type = PCI_IRQ_INTX; + + return 0; +} + +static int nvmet_pci_epf_epc_init(struct pci_epf *epf) +{ + struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); + const struct pci_epc_features *epc_features = nvme_epf->epc_features; + struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl; + unsigned int max_nr_queues = NVMET_NR_QUEUES; + int ret; + + /* For now, do not support virtual functions. */ + if (epf->vfunc_no > 0) { + dev_err(&epf->dev, "Virtual functions are not supported\n"); + return -EINVAL; + } + + /* + * Cap the maximum number of queues we can support on the controller + * with the number of IRQs we can use. + */ + if (epc_features->msix_capable && epf->msix_interrupts) { + dev_info(&epf->dev, + "PCI endpoint controller supports MSI-X, %u vectors\n", + epf->msix_interrupts); + max_nr_queues = min(max_nr_queues, epf->msix_interrupts); + } else if (epc_features->msi_capable && epf->msi_interrupts) { + dev_info(&epf->dev, + "PCI endpoint controller supports MSI, %u vectors\n", + epf->msi_interrupts); + max_nr_queues = min(max_nr_queues, epf->msi_interrupts); + } + + if (max_nr_queues < 2) { + dev_err(&epf->dev, "Invalid maximum number of queues %u\n", + max_nr_queues); + return -EINVAL; + } + + /* Create the target controller. */ + ret = nvmet_pci_epf_create_ctrl(nvme_epf, max_nr_queues); + if (ret) { + dev_err(&epf->dev, + "Failed to create NVMe PCI target controller (err=%d)\n", + ret); + return ret; + } + + /* Set device ID, class, etc. */ + epf->header->vendorid = ctrl->tctrl->subsys->vendor_id; + epf->header->subsys_vendor_id = ctrl->tctrl->subsys->subsys_vendor_id; + ret = pci_epc_write_header(epf->epc, epf->func_no, epf->vfunc_no, + epf->header); + if (ret) { + dev_err(&epf->dev, + "Failed to write configuration header (err=%d)\n", ret); + goto out_destroy_ctrl; + } + + ret = pci_epc_set_bar(epf->epc, epf->func_no, epf->vfunc_no, + &epf->bar[BAR_0]); + if (ret) { + dev_err(&epf->dev, "Failed to set BAR 0 (err=%d)\n", ret); + goto out_destroy_ctrl; + } + + /* + * Enable interrupts and start polling the controller BAR if we do not + * have a link up notifier. + */ + ret = nvmet_pci_epf_init_irq(nvme_epf); + if (ret) + goto out_clear_bar; + + if (!epc_features->linkup_notifier) { + ctrl->link_up = true; + nvmet_pci_epf_start_ctrl(&nvme_epf->ctrl); + } + + return 0; + +out_clear_bar: + nvmet_pci_epf_clear_bar(nvme_epf); +out_destroy_ctrl: + nvmet_pci_epf_destroy_ctrl(&nvme_epf->ctrl); + return ret; +} + +static void nvmet_pci_epf_epc_deinit(struct pci_epf *epf) +{ + struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); + struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl; + + ctrl->link_up = false; + nvmet_pci_epf_destroy_ctrl(ctrl); + + nvmet_pci_epf_deinit_dma(nvme_epf); + nvmet_pci_epf_clear_bar(nvme_epf); +} + +static int nvmet_pci_epf_link_up(struct pci_epf *epf) +{ + struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); + struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl; + + ctrl->link_up = true; + nvmet_pci_epf_start_ctrl(ctrl); + + return 0; +} + +static int nvmet_pci_epf_link_down(struct pci_epf *epf) +{ + struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); + struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl; + + ctrl->link_up = false; + nvmet_pci_epf_stop_ctrl(ctrl); + + return 0; +} + +static const struct pci_epc_event_ops nvmet_pci_epf_event_ops = { + .epc_init = nvmet_pci_epf_epc_init, + .epc_deinit = nvmet_pci_epf_epc_deinit, + .link_up = nvmet_pci_epf_link_up, + .link_down = nvmet_pci_epf_link_down, +}; + +static int nvmet_pci_epf_bind(struct pci_epf *epf) +{ + struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); + const struct pci_epc_features *epc_features; + struct pci_epc *epc = epf->epc; + int ret; + + if (WARN_ON_ONCE(!epc)) + return -EINVAL; + + epc_features = pci_epc_get_features(epc, epf->func_no, epf->vfunc_no); + if (!epc_features) { + dev_err(&epf->dev, "epc_features not implemented\n"); + return -EOPNOTSUPP; + } + nvme_epf->epc_features = epc_features; + + ret = nvmet_pci_epf_configure_bar(nvme_epf); + if (ret) + return ret; + + nvmet_pci_epf_init_dma(nvme_epf); + + return 0; +} + +static void nvmet_pci_epf_unbind(struct pci_epf *epf) +{ + struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); + struct pci_epc *epc = epf->epc; + + nvmet_pci_epf_destroy_ctrl(&nvme_epf->ctrl); + + if (epc->init_complete) { + nvmet_pci_epf_deinit_dma(nvme_epf); + nvmet_pci_epf_clear_bar(nvme_epf); + } + + nvmet_pci_epf_free_bar(nvme_epf); +} + +static struct pci_epf_header nvme_epf_pci_header = { + .vendorid = PCI_ANY_ID, + .deviceid = PCI_ANY_ID, + .progif_code = 0x02, /* NVM Express */ + .baseclass_code = PCI_BASE_CLASS_STORAGE, + .subclass_code = 0x08, /* Non-Volatile Memory controller */ + .interrupt_pin = PCI_INTERRUPT_INTA, +}; + +static int nvmet_pci_epf_probe(struct pci_epf *epf, + const struct pci_epf_device_id *id) +{ + struct nvmet_pci_epf *nvme_epf; + int ret; + + nvme_epf = devm_kzalloc(&epf->dev, sizeof(*nvme_epf), GFP_KERNEL); + if (!nvme_epf) + return -ENOMEM; + + ret = devm_mutex_init(&epf->dev, &nvme_epf->mmio_lock); + if (ret) + return ret; + + nvme_epf->epf = epf; + nvme_epf->mdts_kb = NVMET_PCI_EPF_MDTS_KB; + + epf->event_ops = &nvmet_pci_epf_event_ops; + epf->header = &nvme_epf_pci_header; + epf_set_drvdata(epf, nvme_epf); + + return 0; +} + +#define to_nvme_epf(epf_group) \ + container_of(epf_group, struct nvmet_pci_epf, group) + +static ssize_t nvmet_pci_epf_portid_show(struct config_item *item, char *page) +{ + struct config_group *group = to_config_group(item); + struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group); + + return sysfs_emit(page, "%u\n", le16_to_cpu(nvme_epf->portid)); +} + +static ssize_t nvmet_pci_epf_portid_store(struct config_item *item, + const char *page, size_t len) +{ + struct config_group *group = to_config_group(item); + struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group); + u16 portid; + + /* Do not allow setting this when the function is already started. */ + if (nvme_epf->ctrl.tctrl) + return -EBUSY; + + if (!len) + return -EINVAL; + + if (kstrtou16(page, 0, &portid)) + return -EINVAL; + + nvme_epf->portid = cpu_to_le16(portid); + + return len; +} + +CONFIGFS_ATTR(nvmet_pci_epf_, portid); + +static ssize_t nvmet_pci_epf_subsysnqn_show(struct config_item *item, + char *page) +{ + struct config_group *group = to_config_group(item); + struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group); + + return sysfs_emit(page, "%s\n", nvme_epf->subsysnqn); +} + +static ssize_t nvmet_pci_epf_subsysnqn_store(struct config_item *item, + const char *page, size_t len) +{ + struct config_group *group = to_config_group(item); + struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group); + + /* Do not allow setting this when the function is already started. */ + if (nvme_epf->ctrl.tctrl) + return -EBUSY; + + if (!len) + return -EINVAL; + + strscpy(nvme_epf->subsysnqn, page, len); + + return len; +} + +CONFIGFS_ATTR(nvmet_pci_epf_, subsysnqn); + +static ssize_t nvmet_pci_epf_mdts_kb_show(struct config_item *item, char *page) +{ + struct config_group *group = to_config_group(item); + struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group); + + return sysfs_emit(page, "%u\n", nvme_epf->mdts_kb); +} + +static ssize_t nvmet_pci_epf_mdts_kb_store(struct config_item *item, + const char *page, size_t len) +{ + struct config_group *group = to_config_group(item); + struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group); + unsigned long mdts_kb; + int ret; + + if (nvme_epf->ctrl.tctrl) + return -EBUSY; + + ret = kstrtoul(page, 0, &mdts_kb); + if (ret) + return ret; + if (!mdts_kb) + mdts_kb = NVMET_PCI_EPF_MDTS_KB; + else if (mdts_kb > NVMET_PCI_EPF_MAX_MDTS_KB) + mdts_kb = NVMET_PCI_EPF_MAX_MDTS_KB; + + if (!is_power_of_2(mdts_kb)) + return -EINVAL; + + nvme_epf->mdts_kb = mdts_kb; + + return len; +} + +CONFIGFS_ATTR(nvmet_pci_epf_, mdts_kb); + +static struct configfs_attribute *nvmet_pci_epf_attrs[] = { + &nvmet_pci_epf_attr_portid, + &nvmet_pci_epf_attr_subsysnqn, + &nvmet_pci_epf_attr_mdts_kb, + NULL, +}; + +static const struct config_item_type nvmet_pci_epf_group_type = { + .ct_attrs = nvmet_pci_epf_attrs, + .ct_owner = THIS_MODULE, +}; + +static struct config_group *nvmet_pci_epf_add_cfs(struct pci_epf *epf, + struct config_group *group) +{ + struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); + + config_group_init_type_name(&nvme_epf->group, "nvme", + &nvmet_pci_epf_group_type); + + return &nvme_epf->group; +} + +static const struct pci_epf_device_id nvmet_pci_epf_ids[] = { + { .name = "nvmet_pci_epf" }, + {}, +}; + +static struct pci_epf_ops nvmet_pci_epf_ops = { + .bind = nvmet_pci_epf_bind, + .unbind = nvmet_pci_epf_unbind, + .add_cfs = nvmet_pci_epf_add_cfs, +}; + +static struct pci_epf_driver nvmet_pci_epf_driver = { + .driver.name = "nvmet_pci_epf", + .probe = nvmet_pci_epf_probe, + .id_table = nvmet_pci_epf_ids, + .ops = &nvmet_pci_epf_ops, + .owner = THIS_MODULE, +}; + +static int __init nvmet_pci_epf_init_module(void) +{ + int ret; + + ret = pci_epf_register_driver(&nvmet_pci_epf_driver); + if (ret) + return ret; + + ret = nvmet_register_transport(&nvmet_pci_epf_fabrics_ops); + if (ret) { + pci_epf_unregister_driver(&nvmet_pci_epf_driver); + return ret; + } + + return 0; +} + +static void __exit nvmet_pci_epf_cleanup_module(void) +{ + nvmet_unregister_transport(&nvmet_pci_epf_fabrics_ops); + pci_epf_unregister_driver(&nvmet_pci_epf_driver); +} + +module_init(nvmet_pci_epf_init_module); +module_exit(nvmet_pci_epf_cleanup_module); + +MODULE_DESCRIPTION("NVMe PCI Endpoint Function target driver"); +MODULE_AUTHOR("Damien Le Moal "); +MODULE_LICENSE("GPL"); diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c index 90e9f5bbe581..cd22d8333314 100644 --- a/drivers/nvme/target/pr.c +++ b/drivers/nvme/target/pr.c @@ -60,7 +60,7 @@ u16 nvmet_set_feat_resv_notif_mask(struct nvmet_req *req, u32 mask) goto success; } - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->pr.enable) WRITE_ONCE(ns->pr.notify_mask, mask); } @@ -1056,7 +1056,7 @@ int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl) * nvmet_pr_init_ns(), see more details in nvmet_ns_enable(). * So just check ns->pr.enable. */ - xa_for_each(&subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&subsys->namespaces, idx, ns) { if (ns->pr.enable) { ret = nvmet_pr_alloc_and_insert_pc_ref(ns, ctrl->cntlid, &ctrl->hostid); @@ -1067,7 +1067,7 @@ int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl) return 0; free_per_ctrl_refs: - xa_for_each(&subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&subsys->namespaces, idx, ns) { if (ns->pr.enable) { pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid); if (pc_ref) @@ -1087,7 +1087,7 @@ void nvmet_ctrl_destroy_pr(struct nvmet_ctrl *ctrl) kfifo_free(&ctrl->pr_log_mgr.log_queue); mutex_destroy(&ctrl->pr_log_mgr.lock); - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->pr.enable) { pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid); if (pc_ref) diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index 3aef35b05111..29a60fabfcc8 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -586,8 +586,7 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req) for_each_sg(req->sg, sg, req->sg_cnt, sg_cnt) { unsigned int len = sg->length; - if (bio_add_pc_page(bdev_get_queue(bio->bi_bdev), bio, - sg_page(sg), len, sg->offset) != len) { + if (bio_add_page(bio, sg_page(sg), len, sg->offset) != len) { status = NVME_SC_INTERNAL; goto out_put_bio; } diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index d6494dfc20a7..fff85bbf0ecd 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -213,7 +213,7 @@ static struct attribute *nvmem_attrs[] = { }; static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct device *dev; @@ -246,7 +246,7 @@ static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj, } static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct device *dev; @@ -340,7 +340,7 @@ static struct nvmem_cell *nvmem_create_cell(struct nvmem_cell_entry *entry, const char *id, int index); static ssize_t nvmem_cell_attr_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct nvmem_cell_entry *entry; @@ -374,22 +374,22 @@ destroy_cell: } /* default read/write permissions */ -static struct bin_attribute bin_attr_rw_nvmem = { +static const struct bin_attribute bin_attr_rw_nvmem = { .attr = { .name = "nvmem", .mode = 0644, }, - .read = bin_attr_nvmem_read, - .write = bin_attr_nvmem_write, + .read_new = bin_attr_nvmem_read, + .write_new = bin_attr_nvmem_write, }; -static struct bin_attribute *nvmem_bin_attributes[] = { +static const struct bin_attribute *const nvmem_bin_attributes[] = { &bin_attr_rw_nvmem, NULL, }; static const struct attribute_group nvmem_bin_group = { - .bin_attrs = nvmem_bin_attributes, + .bin_attrs_new = nvmem_bin_attributes, .attrs = nvmem_attrs, .is_bin_visible = nvmem_bin_attr_is_visible, .bin_size = nvmem_bin_attr_size, @@ -401,12 +401,12 @@ static const struct attribute_group *nvmem_dev_groups[] = { NULL, }; -static struct bin_attribute bin_attr_nvmem_eeprom_compat = { +static const struct bin_attribute bin_attr_nvmem_eeprom_compat = { .attr = { .name = "eeprom", }, - .read = bin_attr_nvmem_read, - .write = bin_attr_nvmem_write, + .read_new = bin_attr_nvmem_read, + .write_new = bin_attr_nvmem_write, }; /* @@ -461,6 +461,7 @@ static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem) .name = "cells", }; struct nvmem_cell_entry *entry; + const struct bin_attribute **pattrs; struct bin_attribute *attrs; unsigned int ncells = 0, i = 0; int ret = 0; @@ -472,9 +473,9 @@ static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem) /* Allocate an array of attributes with a sentinel */ ncells = list_count_nodes(&nvmem->cells); - group.bin_attrs = devm_kcalloc(&nvmem->dev, ncells + 1, - sizeof(struct bin_attribute *), GFP_KERNEL); - if (!group.bin_attrs) { + pattrs = devm_kcalloc(&nvmem->dev, ncells + 1, + sizeof(struct bin_attribute *), GFP_KERNEL); + if (!pattrs) { ret = -ENOMEM; goto unlock_mutex; } @@ -494,17 +495,19 @@ static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem) entry->bit_offset); attrs[i].attr.mode = 0444 & nvmem_bin_attr_get_umode(nvmem); attrs[i].size = entry->bytes; - attrs[i].read = &nvmem_cell_attr_read; + attrs[i].read_new = &nvmem_cell_attr_read; attrs[i].private = entry; if (!attrs[i].attr.name) { ret = -ENOMEM; goto unlock_mutex; } - group.bin_attrs[i] = &attrs[i]; + pattrs[i] = &attrs[i]; i++; } + group.bin_attrs_new = pattrs; + ret = device_add_group(&nvmem->dev, &group); if (ret) goto unlock_mutex; @@ -1790,6 +1793,8 @@ static int __nvmem_cell_entry_write(struct nvmem_cell_entry *cell, void *buf, si return -EINVAL; if (cell->bit_offset || cell->nbits) { + if (len != BITS_TO_BYTES(cell->nbits) && len != cell->bytes) + return -EINVAL; buf = nvmem_cell_prepare_write_buffer(cell, buf, len); if (IS_ERR(buf)) return PTR_ERR(buf); diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c index 1ba494497698..ca6dd71d8a2e 100644 --- a/drivers/nvmem/imx-ocotp-ele.c +++ b/drivers/nvmem/imx-ocotp-ele.c @@ -71,14 +71,16 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz u32 *buf; void *p; int i; + u8 skipbytes; - index = offset; - num_bytes = round_up(bytes, 4); + if (offset + bytes > priv->data->size) + bytes = priv->data->size - offset; + + index = offset >> 2; + skipbytes = offset - (index << 2); + num_bytes = round_up(bytes + skipbytes, 4); count = num_bytes >> 2; - if (count > ((priv->data->size >> 2) - index)) - count = (priv->data->size >> 2) - index; - p = kzalloc(num_bytes, GFP_KERNEL); if (!p) return -ENOMEM; @@ -100,7 +102,7 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz *buf++ = readl_relaxed(reg + (i << 2)); } - memcpy(val, (u8 *)p, bytes); + memcpy(val, ((u8 *)p) + skipbytes, bytes); mutex_unlock(&priv->lock); @@ -109,6 +111,26 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz return 0; }; +static int imx_ocotp_cell_pp(void *context, const char *id, int index, + unsigned int offset, void *data, size_t bytes) +{ + u8 *buf = data; + int i; + + /* Deal with some post processing of nvmem cell data */ + if (id && !strcmp(id, "mac-address")) + for (i = 0; i < bytes / 2; i++) + swap(buf[i], buf[bytes - i - 1]); + + return 0; +} + +static void imx_ocotp_fixup_dt_cell_info(struct nvmem_device *nvmem, + struct nvmem_cell_info *cell) +{ + cell->read_post_process = imx_ocotp_cell_pp; +} + static int imx_ele_ocotp_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -131,10 +153,12 @@ static int imx_ele_ocotp_probe(struct platform_device *pdev) priv->config.owner = THIS_MODULE; priv->config.size = priv->data->size; priv->config.reg_read = priv->data->reg_read; - priv->config.word_size = 4; + priv->config.word_size = 1; priv->config.stride = 1; priv->config.priv = priv; priv->config.read_only = true; + priv->config.add_legacy_fixed_of_cells = true; + priv->config.fixup_dt_cell_info = imx_ocotp_fixup_dt_cell_info; mutex_init(&priv->lock); nvmem = devm_nvmem_register(dev, &priv->config); diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c index 9aa8f42faa4c..4f1cca6eab71 100644 --- a/drivers/nvmem/qcom-spmi-sdam.c +++ b/drivers/nvmem/qcom-spmi-sdam.c @@ -144,6 +144,7 @@ static int sdam_probe(struct platform_device *pdev) sdam->sdam_config.owner = THIS_MODULE; sdam->sdam_config.add_legacy_fixed_of_cells = true; sdam->sdam_config.stride = 1; + sdam->sdam_config.size = sdam->size; sdam->sdam_config.word_size = 1; sdam->sdam_config.reg_read = sdam_read; sdam->sdam_config.reg_write = sdam_write; diff --git a/drivers/nvmem/rmem.c b/drivers/nvmem/rmem.c index 7f907c5a445e..b39d628cb60a 100644 --- a/drivers/nvmem/rmem.c +++ b/drivers/nvmem/rmem.c @@ -3,28 +3,40 @@ * Copyright (C) 2020 Nicolas Saenz Julienne */ +#include #include #include #include #include #include +#include struct rmem { struct device *dev; struct nvmem_device *nvmem; struct reserved_mem *mem; - - phys_addr_t size; }; +struct rmem_match_data { + int (*checksum)(struct rmem *priv); +}; + +struct __packed rmem_eyeq5_header { + u32 magic; + u32 version; + u32 size; +}; + +#define RMEM_EYEQ5_MAGIC ((u32)0xDABBAD00) + static int rmem_read(void *context, unsigned int offset, void *val, size_t bytes) { struct rmem *priv = context; - size_t available = priv->mem->size; - loff_t off = offset; void *addr; - int count; + + if ((phys_addr_t)offset + bytes > priv->mem->size) + return -EIO; /* * Only map the reserved memory at this point to avoid potential rogue @@ -36,26 +48,79 @@ static int rmem_read(void *context, unsigned int offset, * An alternative would be setting the memory as RO, set_memory_ro(), * but as of Dec 2020 this isn't possible on arm64. */ - addr = memremap(priv->mem->base, available, MEMREMAP_WB); + addr = memremap(priv->mem->base, priv->mem->size, MEMREMAP_WB); if (!addr) { dev_err(priv->dev, "Failed to remap memory region\n"); return -ENOMEM; } - count = memory_read_from_buffer(val, bytes, &off, addr, available); + memcpy(val, addr + offset, bytes); memunmap(addr); - if (count < 0) - return count; + return 0; +} - return count == bytes ? 0 : -EIO; +static int rmem_eyeq5_checksum(struct rmem *priv) +{ + void *buf __free(kfree) = NULL; + struct rmem_eyeq5_header header; + u32 computed_crc, *target_crc; + size_t data_size; + int ret; + + ret = rmem_read(priv, 0, &header, sizeof(header)); + if (ret) + return ret; + + if (header.magic != RMEM_EYEQ5_MAGIC) + return -EINVAL; + + /* + * Avoid massive kmalloc() if header read is invalid; + * the check would be done by the next rmem_read() anyway. + */ + if (header.size > priv->mem->size) + return -EINVAL; + + /* + * 0 +-------------------+ + * | Header (12 bytes) | \ + * +-------------------+ | + * | | | data to be CRCed + * | ... | | + * | | / + * data_size +-------------------+ + * | CRC (4 bytes) | + * header.size +-------------------+ + */ + + buf = kmalloc(header.size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + ret = rmem_read(priv, 0, buf, header.size); + if (ret) + return ret; + + data_size = header.size - sizeof(*target_crc); + target_crc = buf + data_size; + computed_crc = crc32(U32_MAX, buf, data_size) ^ U32_MAX; + + if (computed_crc == *target_crc) + return 0; + + dev_err(priv->dev, + "checksum failed: computed %#x, expected %#x, header (%#x, %#x, %#x)\n", + computed_crc, *target_crc, header.magic, header.version, header.size); + return -EINVAL; } static int rmem_probe(struct platform_device *pdev) { struct nvmem_config config = { }; struct device *dev = &pdev->dev; + const struct rmem_match_data *match_data = device_get_match_data(dev); struct reserved_mem *mem; struct rmem *priv; @@ -78,10 +143,22 @@ static int rmem_probe(struct platform_device *pdev) config.size = mem->size; config.reg_read = rmem_read; + if (match_data && match_data->checksum) { + int ret = match_data->checksum(priv); + + if (ret) + return ret; + } + return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &config)); } +static const struct rmem_match_data rmem_eyeq5_match_data = { + .checksum = rmem_eyeq5_checksum, +}; + static const struct of_device_id rmem_match[] = { + { .compatible = "mobileye,eyeq5-bootloader-config", .data = &rmem_eyeq5_match_data }, { .compatible = "nvmem-rmem", }, { /* sentinel */ }, }; diff --git a/drivers/of/address.c b/drivers/of/address.c index c5b925ac469f..125833e5ce52 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -16,26 +16,11 @@ #include #include /* for bus_dma_region */ +/* Uncomment me to enable of_dump_addr() debugging output */ +// #define DEBUG + #include "of_private.h" -/* Max address size we deal with */ -#define OF_MAX_ADDR_CELLS 4 -#define OF_CHECK_ADDR_COUNT(na) ((na) > 0 && (na) <= OF_MAX_ADDR_CELLS) -#define OF_CHECK_COUNTS(na, ns) (OF_CHECK_ADDR_COUNT(na) && (ns) > 0) - -/* Debug utility */ -#ifdef DEBUG -static void of_dump_addr(const char *s, const __be32 *addr, int na) -{ - pr_debug("%s", s); - while (na--) - pr_cont(" %08x", be32_to_cpu(*(addr++))); - pr_cont("\n"); -} -#else -static void of_dump_addr(const char *s, const __be32 *addr, int na) { } -#endif - /* Callbacks for bus specific translators */ struct of_bus { const char *name; @@ -200,17 +185,15 @@ static u64 of_bus_pci_map(__be32 *addr, const __be32 *range, int na, int ns, static int __of_address_resource_bounds(struct resource *r, u64 start, u64 size) { - u64 end = start; - if (overflows_type(start, r->start)) return -EOVERFLOW; - if (size && check_add_overflow(end, size - 1, &end)) - return -EOVERFLOW; - if (overflows_type(end, r->end)) - return -EOVERFLOW; r->start = start; - r->end = end; + + if (!size) + r->end = wrapping_sub(typeof(r->end), r->start, 1); + else if (size && check_add_overflow(r->start, size - 1, &r->end)) + return -EOVERFLOW; return 0; } @@ -340,6 +323,15 @@ static int of_bus_default_flags_match(struct device_node *np) return of_property_present(np, "#address-cells") && (of_bus_n_addr_cells(np) == 3); } +static int of_bus_default_match(struct device_node *np) +{ + /* + * Check for presence first since of_bus_n_addr_cells() will warn when + * walking parent nodes. + */ + return of_property_present(np, "#address-cells"); +} + /* * Array of bus specific translators */ @@ -384,7 +376,7 @@ static const struct of_bus of_busses[] = { { .name = "default", .addresses = "reg", - .match = NULL, + .match = of_bus_default_match, .count_cells = of_bus_default_count_cells, .map = of_bus_default_map, .translate = of_bus_default_translate, @@ -399,7 +391,6 @@ static const struct of_bus *of_match_bus(struct device_node *np) for (i = 0; i < ARRAY_SIZE(of_busses); i++) if (!of_busses[i].match || of_busses[i].match(np)) return &of_busses[i]; - BUG(); return NULL; } @@ -459,7 +450,8 @@ static int of_translate_one(const struct device_node *parent, const struct of_bu } if (ranges == NULL || rlen == 0) { offset = of_read_number(addr, na); - memset(addr, 0, pna * 4); + /* set address to zero, pass flags through */ + memset(addr + pbus->flag_cells, 0, (pna - pbus->flag_cells) * 4); pr_debug("empty ranges; 1:1 translation\n"); goto finish; } @@ -520,6 +512,8 @@ static u64 __of_translate_address(struct device_node *node, if (parent == NULL) return OF_BAD_ADDR; bus = of_match_bus(parent); + if (!bus) + return OF_BAD_ADDR; /* Count address cells & copy address locally */ bus->count_cells(dev, &na, &ns); @@ -563,6 +557,8 @@ static u64 __of_translate_address(struct device_node *node, /* Get new parent bus and counts */ pbus = of_match_bus(parent); + if (!pbus) + return OF_BAD_ADDR; pbus->count_cells(dev, &pna, &pns); if (!OF_CHECK_COUNTS(pna, pns)) { pr_err("Bad cell count for %pOF\n", dev); @@ -619,7 +615,7 @@ struct device_node *__of_get_dma_parent(const struct device_node *np) if (ret < 0) return of_get_parent(np); - return of_node_get(args.np); + return args.np; } #endif @@ -702,7 +698,7 @@ const __be32 *__of_get_address(struct device_node *dev, int index, int bar_no, /* match the parent's bus type */ bus = of_match_bus(parent); - if (strcmp(bus->name, "pci") && (bar_no >= 0)) + if (!bus || (strcmp(bus->name, "pci") && (bar_no >= 0))) return NULL; /* Get "reg" or "assigned-addresses" property */ @@ -815,6 +811,8 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser, else range->cpu_addr = of_translate_address(parser->node, parser->range + na); + + range->parent_bus_addr = of_read_number(parser->range + na, parser->pna); range->size = of_read_number(parser->range + parser->pna + na, ns); parser->range += np; diff --git a/drivers/of/base.c b/drivers/of/base.c index 7dc394255a0a..af6c68bbb427 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -88,7 +88,8 @@ static bool __of_node_is_type(const struct device_node *np, const char *type) } #define EXCLUDED_DEFAULT_CELLS_PLATFORMS ( \ - IS_ENABLED(CONFIG_SPARC) \ + IS_ENABLED(CONFIG_SPARC) || \ + of_find_compatible_node(NULL, NULL, "coreboot") \ ) int of_bus_n_addr_cells(struct device_node *np) @@ -893,10 +894,10 @@ struct device_node *of_find_node_opts_by_path(const char *path, const char **opt /* The path could begin with an alias */ if (*path != '/') { int len; - const char *p = separator; + const char *p = strchrnul(path, '/'); - if (!p) - p = strchrnul(path, '/'); + if (separator && separator < p) + p = separator; len = p - path; /* of_aliases must not be NULL */ @@ -1026,19 +1027,15 @@ struct device_node *of_find_node_with_property(struct device_node *from, const char *prop_name) { struct device_node *np; - const struct property *pp; unsigned long flags; raw_spin_lock_irqsave(&devtree_lock, flags); for_each_of_allnodes_from(from, np) { - for (pp = np->properties; pp; pp = pp->next) { - if (of_prop_cmp(pp->name, prop_name) == 0) { - of_node_get(np); - goto out; - } + if (__of_find_property(np, prop_name, NULL)) { + of_node_get(np); + break; } } -out: of_node_put(from); raw_spin_unlock_irqrestore(&devtree_lock, flags); return np; @@ -1452,8 +1449,8 @@ int of_parse_phandle_with_args_map(const struct device_node *np, char *pass_name __free(kfree) = kasprintf(GFP_KERNEL, "%s-map-pass-thru", stem_name); struct device_node *cur, *new = NULL; const __be32 *map, *mask, *pass; - static const __be32 dummy_mask[] = { [0 ... MAX_PHANDLE_ARGS] = cpu_to_be32(~0) }; - static const __be32 dummy_pass[] = { [0 ... MAX_PHANDLE_ARGS] = cpu_to_be32(0) }; + static const __be32 dummy_mask[] = { [0 ... (MAX_PHANDLE_ARGS - 1)] = cpu_to_be32(~0) }; + static const __be32 dummy_pass[] = { [0 ... (MAX_PHANDLE_ARGS - 1)] = cpu_to_be32(0) }; __be32 initial_match_array[MAX_PHANDLE_ARGS]; const __be32 *match_array = initial_match_array; int i, ret, map_len, match; @@ -1507,8 +1504,10 @@ int of_parse_phandle_with_args_map(const struct device_node *np, map_len--; /* Check if not found */ - if (!new) + if (!new) { + ret = -EINVAL; goto put; + } if (!of_device_is_available(new)) match = 0; @@ -1518,17 +1517,20 @@ int of_parse_phandle_with_args_map(const struct device_node *np, goto put; /* Check for malformed properties */ - if (WARN_ON(new_size > MAX_PHANDLE_ARGS)) - goto put; - if (map_len < new_size) + if (WARN_ON(new_size > MAX_PHANDLE_ARGS) || + map_len < new_size) { + ret = -EINVAL; goto put; + } /* Move forward by new node's #-cells amount */ map += new_size; map_len -= new_size; } - if (!match) + if (!match) { + ret = -ENOENT; goto put; + } /* Get the -map-pass-thru property (optional) */ pass = of_get_property(cur, pass_name, NULL); @@ -1540,7 +1542,6 @@ int of_parse_phandle_with_args_map(const struct device_node *np, * specifier into the out_args structure, keeping the * bits specified in -map-pass-thru. */ - match_array = map - new_size; for (i = 0; i < new_size; i++) { __be32 val = *(map - new_size + i); @@ -1549,6 +1550,7 @@ int of_parse_phandle_with_args_map(const struct device_node *np, val |= cpu_to_be32(out_args->args[i]) & pass[i]; } + initial_match_array[i] = val; out_args->args[i] = be32_to_cpu(val); } out_args->args_count = list_size = new_size; @@ -1816,8 +1818,7 @@ static void of_alias_add(struct alias_prop *ap, struct device_node *np, * for storing the resulting tree * * The function scans all the properties of the 'aliases' node and populates - * the global lookup table with the properties. It returns the - * number of alias properties found, or an error code in case of failure. + * the global lookup table with the properties. */ void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)) { diff --git a/drivers/of/empty_root.dts b/drivers/of/empty_root.dts index cf9e97a60f48..cbe169ba3db5 100644 --- a/drivers/of/empty_root.dts +++ b/drivers/of/empty_root.dts @@ -2,5 +2,12 @@ /dts-v1/; / { - + /* + * #address-cells/#size-cells are required properties at root node. + * Use 2 cells for both address cells and size cells in order to fully + * support 64-bit addresses and sizes on systems using this empty root + * node. + */ + #address-cells = <0x02>; + #size-cells = <0x02>; }; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 0121100372b4..aedd0e2dcd89 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -8,7 +8,6 @@ #define pr_fmt(fmt) "OF: fdt: " fmt -#include #include #include #include @@ -497,6 +496,7 @@ static void __init fdt_reserve_elfcorehdr(void) void __init early_init_fdt_scan_reserved_mem(void) { int n; + int res; u64 base, size; if (!initial_boot_params) @@ -507,7 +507,11 @@ void __init early_init_fdt_scan_reserved_mem(void) /* Process header /memreserve/ fields */ for (n = 0; ; n++) { - fdt_get_mem_rsv(initial_boot_params, n, &base, &size); + res = fdt_get_mem_rsv(initial_boot_params, n, &base, &size); + if (res) { + pr_err("Invalid memory reservation block index %d\n", n); + break; + } if (!size) break; memblock_reserve(base, size); @@ -1126,13 +1130,7 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size) static void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { - void *ptr = memblock_alloc(size, align); - - if (!ptr) - panic("%s: Failed to allocate %llu bytes align=0x%llx\n", - __func__, size, align); - - return ptr; + return memblock_alloc_or_panic(size, align); } bool __init early_init_dt_verify(void *dt_virt, phys_addr_t dt_phys) @@ -1215,14 +1213,7 @@ void __init unflatten_device_tree(void) /* Save the statically-placed regions in the reserved_mem array */ fdt_scan_reserved_mem_reg_nodes(); - /* Don't use the bootloader provided DTB if ACPI is enabled */ - if (!acpi_disabled) - fdt = NULL; - - /* - * Populate an empty root node when ACPI is enabled or bootloader - * doesn't provide one. - */ + /* Populate an empty root node when bootloader doesn't provide one */ if (!fdt) { fdt = (void *) __dtb_empty_root_begin; /* fdt_totalsize() will be used for copy size */ @@ -1264,18 +1255,9 @@ void __init unflatten_and_copy_device_tree(void) } #ifdef CONFIG_SYSFS -static ssize_t of_fdt_raw_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, - char *buf, loff_t off, size_t count) -{ - memcpy(buf, initial_boot_params + off, count); - return count; -} - static int __init of_fdt_raw_init(void) { - static struct bin_attribute of_fdt_raw_attr = - __BIN_ATTR(fdt, S_IRUSR, of_fdt_raw_read, NULL, 0); + static __ro_after_init BIN_ATTR_SIMPLE_ADMIN_RO(fdt); if (!initial_boot_params) return 0; @@ -1285,8 +1267,9 @@ static int __init of_fdt_raw_init(void) pr_warn("not creating '/sys/firmware/fdt': CRC check failed\n"); return 0; } - of_fdt_raw_attr.size = fdt_totalsize(initial_boot_params); - return sysfs_create_bin_file(firmware_kobj, &of_fdt_raw_attr); + bin_attr_fdt.private = initial_boot_params; + bin_attr_fdt.size = fdt_totalsize(initial_boot_params); + return sysfs_create_bin_file(firmware_kobj, &bin_attr_fdt); } late_initcall(of_fdt_raw_init); #endif diff --git a/drivers/of/fdt_address.c b/drivers/of/fdt_address.c index 9804d7f06705..f358d2c80754 100644 --- a/drivers/of/fdt_address.c +++ b/drivers/of/fdt_address.c @@ -17,23 +17,10 @@ #include #include -/* Max address size we deal with */ -#define OF_MAX_ADDR_CELLS 4 -#define OF_CHECK_COUNTS(na, ns) ((na) > 0 && (na) <= OF_MAX_ADDR_CELLS && \ - (ns) > 0) +/* Uncomment me to enable of_dump_addr() debugging output */ +// #define DEBUG -/* Debug utility */ -#ifdef DEBUG -static void __init of_dump_addr(const char *s, const __be32 *addr, int na) -{ - pr_debug("%s", s); - while(na--) - pr_cont(" %08x", *(addr++)); - pr_cont("\n"); -} -#else -static void __init of_dump_addr(const char *s, const __be32 *addr, int na) { } -#endif +#include "of_private.h" /* Callbacks for bus specific translators */ struct of_bus { diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 67fc0ceaa5f5..6c843d54ebb1 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -111,6 +111,7 @@ const __be32 *of_irq_parse_imap_parent(const __be32 *imap, int len, struct of_ph else np = of_find_node_by_phandle(be32_to_cpup(imap)); imap++; + len--; /* Check if not found */ if (!np) { @@ -170,7 +171,7 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq) struct device_node *ipar, *tnode, *old = NULL; __be32 initial_match_array[MAX_PHANDLE_ARGS]; const __be32 *match_array = initial_match_array; - const __be32 *tmp, dummy_imask[] = { [0 ... MAX_PHANDLE_ARGS] = cpu_to_be32(~0) }; + const __be32 *tmp, dummy_imask[] = { [0 ... (MAX_PHANDLE_ARGS - 1)] = cpu_to_be32(~0) }; u32 intsize = 1, addrsize; int i, rc = -EINVAL; @@ -354,6 +355,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar return of_irq_parse_oldworld(device, index, out_irq); /* Get the reg property (if any) */ + addr_len = 0; addr = of_get_property(device, "reg", &addr_len); /* Prevent out-of-bounds read in case of longer interrupt parent address size */ diff --git a/drivers/of/kobj.c b/drivers/of/kobj.c index cab9b169dc67..aa887166f0d2 100644 --- a/drivers/of/kobj.c +++ b/drivers/of/kobj.c @@ -29,7 +29,7 @@ const struct kobj_type of_node_ktype = { }; static ssize_t of_node_property_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t offset, size_t count) { struct property *pp = container_of(bin_attr, struct property, attr); @@ -77,7 +77,7 @@ int __of_add_property_sysfs(struct device_node *np, struct property *pp) pp->attr.attr.name = safe_name(&np->kobj, pp->name); pp->attr.attr.mode = secure ? 0400 : 0444; pp->attr.size = secure ? 0 : pp->length; - pp->attr.read = of_node_property_read; + pp->attr.read_new = of_node_property_read; rc = sysfs_create_bin_file(&np->kobj, &pp->attr); WARN(rc, "error adding attribute %s to node %pOF\n", pp->name, np); diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index ea5a0951ec5e..f3e1193c8ded 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -119,6 +119,8 @@ extern void *__unflatten_device_tree(const void *blob, void *(*dt_alloc)(u64 size, u64 align), bool detached); +void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); + /** * General utilities for working with live trees. * @@ -188,4 +190,22 @@ void __init fdt_scan_reserved_mem_reg_nodes(void); bool of_fdt_device_is_available(const void *blob, unsigned long node); +/* Max address size we deal with */ +#define OF_MAX_ADDR_CELLS 4 +#define OF_CHECK_ADDR_COUNT(na) ((na) > 0 && (na) <= OF_MAX_ADDR_CELLS) +#define OF_CHECK_COUNTS(na, ns) (OF_CHECK_ADDR_COUNT(na) && (ns) > 0) + +/* Debug utility */ +#ifdef DEBUG +static void __maybe_unused of_dump_addr(const char *s, const __be32 *addr, int na) +{ + pr_debug("%s", s); + while (na--) + pr_cont(" %08x", be32_to_cpu(*(addr++))); + pr_cont("\n"); +} +#else +static void __maybe_unused of_dump_addr(const char *s, const __be32 *addr, int na) { } +#endif + #endif /* _LINUX_OF_PRIVATE_H */ diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 45517b9e57b1..75e819f66a56 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -52,7 +52,8 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, memblock_phys_free(base, size); } - kmemleak_ignore_phys(base); + if (!err) + kmemleak_ignore_phys(base); return err; } @@ -262,6 +263,11 @@ void __init fdt_scan_reserved_mem_reg_nodes(void) uname); continue; } + + if (len > t_len) + pr_warn("%s() ignores %d regions in node '%s'\n", + __func__, len / t_len - 1, uname); + base = dt_mem_next_cell(dt_root_addr_cells, &prop); size = dt_mem_next_cell(dt_root_size_cells, &prop); @@ -409,12 +415,12 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam prop = of_get_flat_dt_prop(node, "alignment", &len); if (prop) { - if (len != dt_root_addr_cells * sizeof(__be32)) { + if (len != dt_root_size_cells * sizeof(__be32)) { pr_err("invalid alignment property in '%s' node.\n", uname); return -EINVAL; } - align = dt_mem_next_cell(dt_root_addr_cells, &prop); + align = dt_mem_next_cell(dt_root_size_cells, &prop); } nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL; @@ -435,13 +441,12 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam return -EINVAL; } - base = 0; - while (len > 0) { start = dt_mem_next_cell(dt_root_addr_cells, &prop); end = start + dt_mem_next_cell(dt_root_size_cells, &prop); + base = 0; ret = __reserved_mem_alloc_in_range(size, align, start, end, nomap, &base); if (ret == 0) { diff --git a/drivers/of/pdt.c b/drivers/of/pdt.c index 7eda43c66c91..cb0cb374b21f 100644 --- a/drivers/of/pdt.c +++ b/drivers/of/pdt.c @@ -19,6 +19,8 @@ #include #include +#include "of_private.h" + static struct of_pdt_ops *of_pdt_prom_ops __initdata; #if defined(CONFIG_SPARC) diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 9bafcff3e628..c6d8afb284e8 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -24,16 +24,6 @@ #include "of_private.h" -const struct of_device_id of_default_bus_match_table[] = { - { .compatible = "simple-bus", }, - { .compatible = "simple-mfd", }, - { .compatible = "isa", }, -#ifdef CONFIG_ARM_AMBA - { .compatible = "arm,amba-bus", }, -#endif /* CONFIG_ARM_AMBA */ - {} /* Empty terminated list */ -}; - /** * of_find_device_by_node - Find the platform_device associated with a node * @np: Pointer to device tree node @@ -484,8 +474,17 @@ int of_platform_default_populate(struct device_node *root, const struct of_dev_auxdata *lookup, struct device *parent) { - return of_platform_populate(root, of_default_bus_match_table, lookup, - parent); + static const struct of_device_id match_table[] = { + { .compatible = "simple-bus", }, + { .compatible = "simple-mfd", }, + { .compatible = "isa", }, +#ifdef CONFIG_ARM_AMBA + { .compatible = "arm,amba-bus", }, +#endif /* CONFIG_ARM_AMBA */ + {} /* Empty terminated list */ + }; + + return of_platform_populate(root, match_table, lookup, parent); } EXPORT_SYMBOL_GPL(of_platform_default_populate); diff --git a/drivers/of/property.c b/drivers/of/property.c index 519bf9229e61..208d922cc24c 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -31,6 +31,32 @@ #include "of_private.h" +/** + * of_property_read_bool - Find a property + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * + * Search for a boolean property in a device node. Usage on non-boolean + * property types is deprecated. + * + * Return: true if the property exists false otherwise. + */ +bool of_property_read_bool(const struct device_node *np, const char *propname) +{ + struct property *prop = of_find_property(np, propname, NULL); + + /* + * Boolean properties should not have a value. Testing for property + * presence should either use of_property_present() or just read the + * property value and check the returned error code. + */ + if (prop && prop->length) + pr_warn("%pOF: Read of boolean property '%s' with a value.\n", np, propname); + + return prop ? true : false; +} +EXPORT_SYMBOL(of_property_read_bool); + /** * of_graph_is_present() - check graph's presence * @node: pointer to device_node containing graph port @@ -965,6 +991,12 @@ of_fwnode_device_get_dma_attr(const struct fwnode_handle *fwnode) static bool of_fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname) +{ + return of_property_present(to_of_node(fwnode), propname); +} + +static bool of_fwnode_property_read_bool(const struct fwnode_handle *fwnode, + const char *propname) { return of_property_read_bool(to_of_node(fwnode), propname); } @@ -1286,7 +1318,6 @@ DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells") DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells") DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells") DEFINE_SIMPLE_PROP(io_backends, "io-backends", "#io-backend-cells") -DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") DEFINE_SIMPLE_PROP(hwlocks, "hwlocks", "#hwlock-cells") @@ -1391,9 +1422,9 @@ static struct device_node *parse_interrupt_map(struct device_node *np, addrcells = of_bus_n_addr_cells(np); imap = of_get_property(np, "interrupt-map", &imaplen); - imaplen /= sizeof(*imap); if (!imap) return NULL; + imaplen /= sizeof(*imap); imap_end = imap + imaplen; @@ -1432,7 +1463,6 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_mboxes, }, { .parse_prop = parse_io_channels, }, { .parse_prop = parse_io_backends, }, - { .parse_prop = parse_interrupt_parent, }, { .parse_prop = parse_dmas, .optional = true, }, { .parse_prop = parse_power_domains, }, { .parse_prop = parse_hwlocks, }, @@ -1562,6 +1592,7 @@ const struct fwnode_operations of_fwnode_ops = { .device_dma_supported = of_fwnode_device_dma_supported, .device_get_dma_attr = of_fwnode_device_get_dma_attr, .property_present = of_fwnode_property_present, + .property_read_bool = of_fwnode_property_read_bool, .property_read_int_array = of_fwnode_property_read_int_array, .property_read_string_array = of_fwnode_property_read_string_array, .get_name = of_fwnode_get_name, diff --git a/drivers/of/unittest-data/tests-address.dtsi b/drivers/of/unittest-data/tests-address.dtsi index 3344f15c3755..f02a181bb125 100644 --- a/drivers/of/unittest-data/tests-address.dtsi +++ b/drivers/of/unittest-data/tests-address.dtsi @@ -114,6 +114,7 @@ device_type = "pci"; ranges = <0x82000000 0 0xe8000000 0 0xe8000000 0 0x7f00000>, <0x81000000 0 0x00000000 0 0xefff0000 0 0x0010000>; + dma-ranges = <0x43000000 0x10 0x00 0x00 0x00 0x00 0x10000000>; reg = <0x00000000 0xd1070000 0x20000>; pci@0,0 { @@ -142,6 +143,7 @@ #size-cells = <0x01>; ranges = <0xa0000000 0 0 0 0x2000000>, <0xb0000000 1 0 0 0x1000000>; + dma-ranges = <0xc0000000 0x43000000 0x10 0x00 0x10000000>; dev@e0000000 { reg = <0xa0001000 0x1000>, diff --git a/drivers/of/unittest-data/tests-platform.dtsi b/drivers/of/unittest-data/tests-platform.dtsi index fa39611071b3..4171f43cf01c 100644 --- a/drivers/of/unittest-data/tests-platform.dtsi +++ b/drivers/of/unittest-data/tests-platform.dtsi @@ -33,6 +33,24 @@ reg = <0x100>; }; }; + + test-device@2 { + compatible = "test,rust-device"; + reg = <0x2>; + }; + }; + + platform-tests-2 { + // No #address-cells or #size-cells + node { + #address-cells = <1>; + #size-cells = <1>; + + test-device@100 { + compatible = "test-sub-device"; + reg = <0x100 1>; + }; + }; }; }; }; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 42b411f32b1b..f88ddb1cf5d7 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -161,6 +161,15 @@ static void __init of_unittest_find_node_by_name(void) "option alias path test, subcase #1 failed\n"); of_node_put(np); + np = of_find_node_opts_by_path("testcase-alias/phandle-tests/consumer-a:testaliasoption", + &options); + name = kasprintf(GFP_KERNEL, "%pOF", np); + unittest(np && name && !strcmp("/testcase-data/phandle-tests/consumer-a", name) && + !strcmp("testaliasoption", options), + "option alias path test, subcase #2 failed\n"); + of_node_put(np); + kfree(name); + np = of_find_node_opts_by_path("testcase-alias:testaliasoption", NULL); unittest(np, "NULL option alias path test failed\n"); of_node_put(np); @@ -1213,6 +1222,44 @@ static void __init of_unittest_pci_dma_ranges(void) of_node_put(np); } +static void __init of_unittest_pci_empty_dma_ranges(void) +{ + struct device_node *np; + struct of_pci_range range; + struct of_pci_range_parser parser; + + if (!IS_ENABLED(CONFIG_PCI)) + return; + + np = of_find_node_by_path("/testcase-data/address-tests2/pcie@d1070000/pci@0,0/dev@0,0/local-bus@0"); + if (!np) { + pr_err("missing testcase data\n"); + return; + } + + if (of_pci_dma_range_parser_init(&parser, np)) { + pr_err("missing dma-ranges property\n"); + return; + } + + /* + * Get the dma-ranges from the device tree + */ + for_each_of_pci_range(&parser, &range) { + unittest(range.size == 0x10000000, + "for_each_of_pci_range wrong size on node %pOF size=%llx\n", + np, range.size); + unittest(range.cpu_addr == 0x00000000, + "for_each_of_pci_range wrong CPU addr (%llx) on node %pOF", + range.cpu_addr, np); + unittest(range.pci_addr == 0xc0000000, + "for_each_of_pci_range wrong DMA addr (%llx) on node %pOF", + range.pci_addr, np); + } + + of_node_put(np); +} + static void __init of_unittest_bus_ranges(void) { struct device_node *np; @@ -1342,6 +1389,7 @@ static void __init of_unittest_bus_3cell_ranges(void) static void __init of_unittest_reg(void) { struct device_node *np; + struct resource res; int ret; u64 addr, size; @@ -1358,6 +1406,19 @@ static void __init of_unittest_reg(void) np, addr); of_node_put(np); + + np = of_find_node_by_path("/testcase-data/platform-tests-2/node/test-device@100"); + if (!np) { + pr_err("missing testcase data\n"); + return; + } + + ret = of_address_to_resource(np, 0, &res); + unittest(ret == -EINVAL, "of_address_to_resource(%pOF) expected error on untranslatable address\n", + np); + + of_node_put(np); + } struct of_unittest_expected_res { @@ -3628,13 +3689,7 @@ static struct device_node *overlay_base_root; static void * __init dt_alloc_memory(u64 size, u64 align) { - void *ptr = memblock_alloc(size, align); - - if (!ptr) - panic("%s: Failed to allocate %llu bytes align=0x%llx\n", - __func__, size, align); - - return ptr; + return memblock_alloc_or_panic(size, align); } /* @@ -4272,6 +4327,7 @@ static int __init of_unittest(void) of_unittest_dma_get_max_cpu_address(); of_unittest_parse_dma_ranges(); of_unittest_pci_dma_ranges(); + of_unittest_pci_empty_dma_ranges(); of_unittest_bus_ranges(); of_unittest_bus_3cell_ranges(); of_unittest_reg(); diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 0311b18319a4..73e9a3b2f29b 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -101,11 +101,55 @@ struct opp_table *_find_opp_table(struct device *dev) * representation in the OPP table and manage the clock configuration themselves * in an platform specific way. */ -static bool assert_single_clk(struct opp_table *opp_table) +static bool assert_single_clk(struct opp_table *opp_table, + unsigned int __always_unused index) { return !WARN_ON(opp_table->clk_count > 1); } +/* + * Returns true if clock table is large enough to contain the clock index. + */ +static bool assert_clk_index(struct opp_table *opp_table, + unsigned int index) +{ + return opp_table->clk_count > index; +} + +/* + * Returns true if bandwidth table is large enough to contain the bandwidth index. + */ +static bool assert_bandwidth_index(struct opp_table *opp_table, + unsigned int index) +{ + return opp_table->path_count > index; +} + +/** + * dev_pm_opp_get_bw() - Gets the bandwidth corresponding to an opp + * @opp: opp for which bandwidth has to be returned for + * @peak: select peak or average bandwidth + * @index: bandwidth index + * + * Return: bandwidth in kBps, else return 0 + */ +unsigned long dev_pm_opp_get_bw(struct dev_pm_opp *opp, bool peak, int index) +{ + if (IS_ERR_OR_NULL(opp)) { + pr_err("%s: Invalid parameters\n", __func__); + return 0; + } + + if (index >= opp->opp_table->path_count) + return 0; + + if (!opp->bandwidth) + return 0; + + return peak ? opp->bandwidth[index].peak : opp->bandwidth[index].avg; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_bw); + /** * dev_pm_opp_get_voltage() - Gets the voltage corresponding to an opp * @opp: opp for which voltage has to be returned for @@ -499,12 +543,12 @@ static struct dev_pm_opp *_opp_table_find_key(struct opp_table *opp_table, unsigned long (*read)(struct dev_pm_opp *opp, int index), bool (*compare)(struct dev_pm_opp **opp, struct dev_pm_opp *temp_opp, unsigned long opp_key, unsigned long key), - bool (*assert)(struct opp_table *opp_table)) + bool (*assert)(struct opp_table *opp_table, unsigned int index)) { struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); /* Assert that the requirement is met */ - if (assert && !assert(opp_table)) + if (assert && !assert(opp_table, index)) return ERR_PTR(-EINVAL); mutex_lock(&opp_table->lock); @@ -532,7 +576,7 @@ _find_key(struct device *dev, unsigned long *key, int index, bool available, unsigned long (*read)(struct dev_pm_opp *opp, int index), bool (*compare)(struct dev_pm_opp **opp, struct dev_pm_opp *temp_opp, unsigned long opp_key, unsigned long key), - bool (*assert)(struct opp_table *opp_table)) + bool (*assert)(struct opp_table *opp_table, unsigned int index)) { struct opp_table *opp_table; struct dev_pm_opp *opp; @@ -555,7 +599,7 @@ _find_key(struct device *dev, unsigned long *key, int index, bool available, static struct dev_pm_opp *_find_key_exact(struct device *dev, unsigned long key, int index, bool available, unsigned long (*read)(struct dev_pm_opp *opp, int index), - bool (*assert)(struct opp_table *opp_table)) + bool (*assert)(struct opp_table *opp_table, unsigned int index)) { /* * The value of key will be updated here, but will be ignored as the @@ -568,7 +612,7 @@ static struct dev_pm_opp *_find_key_exact(struct device *dev, static struct dev_pm_opp *_opp_table_find_key_ceil(struct opp_table *opp_table, unsigned long *key, int index, bool available, unsigned long (*read)(struct dev_pm_opp *opp, int index), - bool (*assert)(struct opp_table *opp_table)) + bool (*assert)(struct opp_table *opp_table, unsigned int index)) { return _opp_table_find_key(opp_table, key, index, available, read, _compare_ceil, assert); @@ -577,7 +621,7 @@ static struct dev_pm_opp *_opp_table_find_key_ceil(struct opp_table *opp_table, static struct dev_pm_opp *_find_key_ceil(struct device *dev, unsigned long *key, int index, bool available, unsigned long (*read)(struct dev_pm_opp *opp, int index), - bool (*assert)(struct opp_table *opp_table)) + bool (*assert)(struct opp_table *opp_table, unsigned int index)) { return _find_key(dev, key, index, available, read, _compare_ceil, assert); @@ -586,7 +630,7 @@ static struct dev_pm_opp *_find_key_ceil(struct device *dev, unsigned long *key, static struct dev_pm_opp *_find_key_floor(struct device *dev, unsigned long *key, int index, bool available, unsigned long (*read)(struct dev_pm_opp *opp, int index), - bool (*assert)(struct opp_table *opp_table)) + bool (*assert)(struct opp_table *opp_table, unsigned int index)) { return _find_key(dev, key, index, available, read, _compare_floor, assert); @@ -647,7 +691,8 @@ struct dev_pm_opp * dev_pm_opp_find_freq_exact_indexed(struct device *dev, unsigned long freq, u32 index, bool available) { - return _find_key_exact(dev, freq, index, available, _read_freq, NULL); + return _find_key_exact(dev, freq, index, available, _read_freq, + assert_clk_index); } EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact_indexed); @@ -707,7 +752,8 @@ struct dev_pm_opp * dev_pm_opp_find_freq_ceil_indexed(struct device *dev, unsigned long *freq, u32 index) { - return _find_key_ceil(dev, freq, index, true, _read_freq, NULL); + return _find_key_ceil(dev, freq, index, true, _read_freq, + assert_clk_index); } EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil_indexed); @@ -760,7 +806,7 @@ struct dev_pm_opp * dev_pm_opp_find_freq_floor_indexed(struct device *dev, unsigned long *freq, u32 index) { - return _find_key_floor(dev, freq, index, true, _read_freq, NULL); + return _find_key_floor(dev, freq, index, true, _read_freq, assert_clk_index); } EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor_indexed); @@ -878,7 +924,8 @@ struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, unsigned int *bw, unsigned long temp = *bw; struct dev_pm_opp *opp; - opp = _find_key_ceil(dev, &temp, index, true, _read_bw, NULL); + opp = _find_key_ceil(dev, &temp, index, true, _read_bw, + assert_bandwidth_index); *bw = temp; return opp; } @@ -909,7 +956,8 @@ struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, unsigned long temp = *bw; struct dev_pm_opp *opp; - opp = _find_key_floor(dev, &temp, index, true, _read_bw, NULL); + opp = _find_key_floor(dev, &temp, index, true, _read_bw, + assert_bandwidth_index); *bw = temp; return opp; } @@ -1480,11 +1528,6 @@ err: return ERR_PTR(ret); } -void _get_opp_table_kref(struct opp_table *opp_table) -{ - kref_get(&opp_table->kref); -} - static struct opp_table *_update_opp_table_clk(struct device *dev, struct opp_table *opp_table, bool getclk) @@ -1645,6 +1688,17 @@ static void _opp_table_kref_release(struct kref *kref) kfree(opp_table); } +void _get_opp_table_kref(struct opp_table *opp_table) +{ + kref_get(&opp_table->kref); +} + +void dev_pm_opp_get_opp_table_ref(struct opp_table *opp_table) +{ + _get_opp_table_kref(opp_table); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table_ref); + void dev_pm_opp_put_opp_table(struct opp_table *opp_table) { kref_put_mutex(&opp_table->kref, _opp_table_kref_release, @@ -1679,6 +1733,7 @@ void dev_pm_opp_get(struct dev_pm_opp *opp) { kref_get(&opp->kref); } +EXPORT_SYMBOL_GPL(dev_pm_opp_get); void dev_pm_opp_put(struct dev_pm_opp *opp) { @@ -1702,7 +1757,7 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq) if (IS_ERR(opp_table)) return; - if (!assert_single_clk(opp_table)) + if (!assert_single_clk(opp_table, 0)) goto put_table; mutex_lock(&opp_table->lock); @@ -2054,7 +2109,7 @@ int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long tol, u_volt = data->u_volt; int ret; - if (!assert_single_clk(opp_table)) + if (!assert_single_clk(opp_table, 0)) return -EINVAL; new_opp = _opp_allocate(opp_table); @@ -2810,7 +2865,7 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, return r; } - if (!assert_single_clk(opp_table)) { + if (!assert_single_clk(opp_table, 0)) { r = -EINVAL; goto put_table; } @@ -2886,7 +2941,7 @@ int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, return r; } - if (!assert_single_clk(opp_table)) { + if (!assert_single_clk(opp_table, 0)) { r = -EINVAL; goto put_table; } diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c index 105de7c3274a..8fc6238b1728 100644 --- a/drivers/opp/debugfs.c +++ b/drivers/opp/debugfs.c @@ -217,7 +217,7 @@ static void opp_migrate_dentry(struct opp_device *opp_dev, { struct opp_device *new_dev = NULL, *iter; const struct device *dev; - struct dentry *dentry; + int err; /* Look for next opp-dev */ list_for_each_entry(iter, &opp_table->dev_list, node) @@ -234,16 +234,14 @@ static void opp_migrate_dentry(struct opp_device *opp_dev, opp_set_dev_name(dev, opp_table->dentry_name); - dentry = debugfs_rename(rootdir, opp_dev->dentry, rootdir, - opp_table->dentry_name); - if (IS_ERR(dentry)) { + err = debugfs_change_name(opp_dev->dentry, "%s", opp_table->dentry_name); + if (err) { dev_err(dev, "%s: Failed to rename link from: %s to %s\n", __func__, dev_name(opp_dev->dev), dev_name(dev)); return; } - new_dev->dentry = dentry; - opp_table->dentry = dentry; + new_dev->dentry = opp_table->dentry = opp_dev->dentry; } /** diff --git a/drivers/opp/of.c b/drivers/opp/of.c index fd5ed2858258..a24f76f5fd01 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -926,7 +926,7 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, ret = _of_opp_alloc_required_opps(opp_table, new_opp); if (ret) - goto free_opp; + goto put_node; if (!of_property_read_u32(np, "clock-latency-ns", &val)) new_opp->clock_latency_ns = val; @@ -976,6 +976,8 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, free_required_opps: _of_opp_free_required_opps(opp_table, new_opp); +put_node: + of_node_put(np); free_opp: _opp_free(new_opp); diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h index 430651e7424a..5c7c81190e41 100644 --- a/drivers/opp/opp.h +++ b/drivers/opp/opp.h @@ -250,7 +250,6 @@ struct opp_table { }; /* Routines internal to opp core */ -void dev_pm_opp_get(struct dev_pm_opp *opp); bool _opp_remove_all_static(struct opp_table *opp_table); void _get_opp_table_kref(struct opp_table *opp_table); int _get_opp_count(struct opp_table *opp_table); diff --git a/drivers/parport/parport_serial.c b/drivers/parport/parport_serial.c index 3644997a8342..24d4f3a3ec3d 100644 --- a/drivers/parport/parport_serial.c +++ b/drivers/parport/parport_serial.c @@ -266,10 +266,14 @@ static struct pci_device_id parport_serial_pci_tbl[] = { { 0x1409, 0x7168, 0x1409, 0xd079, 0, 0, timedia_9079c }, /* WCH CARDS */ - { 0x4348, 0x5053, PCI_ANY_ID, PCI_ANY_ID, 0, 0, wch_ch353_1s1p}, - { 0x4348, 0x7053, 0x4348, 0x3253, 0, 0, wch_ch353_2s1p}, - { 0x1c00, 0x3050, 0x1c00, 0x3050, 0, 0, wch_ch382_0s1p}, - { 0x1c00, 0x3250, 0x1c00, 0x3250, 0, 0, wch_ch382_2s1p}, + { PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_1S1P, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, wch_ch353_1s1p }, + { PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_2S1P, + 0x4348, 0x3253, 0, 0, wch_ch353_2s1p }, + { PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH382_0S1P, + 0x1c00, 0x3050, 0, 0, wch_ch382_0s1p }, + { PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH382_2S1P, + 0x1c00, 0x3250, 0, 0, wch_ch382_2s1p }, /* BrainBoxes PX272/PX306 MIO card */ { PCI_VENDOR_ID_INTASHIELD, 0x4100, diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 6afff1f1b143..c6b266c772c8 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -410,7 +410,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features) if (WARN_ON(pdev->pasid_enabled)) return -EBUSY; - if (!pdev->eetlp_prefix_path && !pdev->pasid_no_tlp) + if (!pdev->eetlp_prefix_max && !pdev->pasid_no_tlp) return -EINVAL; if (!pasid) diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index 5c62e1a3ba52..33d6bf460ffe 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -635,30 +635,20 @@ static int dra7xx_pcie_unaligned_memaccess(struct device *dev) { int ret; struct device_node *np = dev->of_node; - struct of_phandle_args args; + unsigned int args[2]; struct regmap *regmap; - regmap = syscon_regmap_lookup_by_phandle(np, - "ti,syscon-unaligned-access"); + regmap = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-unaligned-access", + 2, args); if (IS_ERR(regmap)) { dev_dbg(dev, "can't get ti,syscon-unaligned-access\n"); return -EINVAL; } - ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-unaligned-access", - 2, 0, &args); - if (ret) { - dev_err(dev, "failed to parse ti,syscon-unaligned-access\n"); - return ret; - } - - ret = regmap_update_bits(regmap, args.args[0], args.args[1], - args.args[1]); + ret = regmap_update_bits(regmap, args[0], args[1], args[1]); if (ret) dev_err(dev, "failed to enable unaligned access\n"); - of_node_put(args.np); - return ret; } @@ -671,18 +661,13 @@ static int dra7xx_pcie_configure_two_lane(struct device *dev, u32 mask; u32 val; - pcie_syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-lane-sel"); + pcie_syscon = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-lane-sel", + 1, &pcie_reg); if (IS_ERR(pcie_syscon)) { dev_err(dev, "unable to get ti,syscon-lane-sel\n"); return -EINVAL; } - if (of_property_read_u32_index(np, "ti,syscon-lane-sel", 1, - &pcie_reg)) { - dev_err(dev, "couldn't get lane selection reg offset\n"); - return -EINVAL; - } - mask = b1co_mode_sel_mask | PCIE_B0_B1_TSYNCEN; val = PCIE_B1C0_MODE_SEL | PCIE_B0_B1_TSYNCEN; regmap_update_bits(pcie_syscon, pcie_reg, mask, val); diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c index 6a830166d37f..ace736b025b1 100644 --- a/drivers/pci/controller/dwc/pci-exynos.c +++ b/drivers/pci/controller/dwc/pci-exynos.c @@ -300,7 +300,7 @@ static int exynos_pcie_probe(struct platform_device *pdev) if (IS_ERR(ep->elbi_base)) return PTR_ERR(ep->elbi_base); - ret = devm_clk_bulk_get_all_enable(dev, &ep->clks); + ret = devm_clk_bulk_get_all_enabled(dev, &ep->clks); if (ret < 0) return ret; diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index c8d5c90aa4d4..90ace941090f 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -33,6 +33,7 @@ #include #include +#include "../../pci.h" #include "pcie-designware.h" #define IMX8MQ_GPR_PCIE_REF_USE_PAD BIT(9) @@ -55,6 +56,22 @@ #define IMX95_PE0_GEN_CTRL_3 0x1058 #define IMX95_PCIE_LTSSM_EN BIT(0) +#define IMX95_PE0_LUT_ACSCTRL 0x1008 +#define IMX95_PEO_LUT_RWA BIT(16) +#define IMX95_PE0_LUT_ENLOC GENMASK(4, 0) + +#define IMX95_PE0_LUT_DATA1 0x100c +#define IMX95_PE0_LUT_VLD BIT(31) +#define IMX95_PE0_LUT_DAC_ID GENMASK(10, 8) +#define IMX95_PE0_LUT_STREAM_ID GENMASK(5, 0) + +#define IMX95_PE0_LUT_DATA2 0x1010 +#define IMX95_PE0_LUT_REQID GENMASK(31, 16) +#define IMX95_PE0_LUT_MASK GENMASK(15, 0) + +#define IMX95_SID_MASK GENMASK(5, 0) +#define IMX95_MAX_LUT 32 + #define to_imx_pcie(x) dev_get_drvdata((x)->dev) enum imx_pcie_variants { @@ -70,6 +87,7 @@ enum imx_pcie_variants { IMX8MQ_EP, IMX8MM_EP, IMX8MP_EP, + IMX8Q_EP, IMX95_EP, }; @@ -87,6 +105,7 @@ enum imx_pcie_variants { * workaround suspend resume on some devices which are affected by this errata. */ #define IMX_PCIE_FLAG_BROKEN_SUSPEND BIT(9) +#define IMX_PCIE_FLAG_HAS_LUT BIT(10) #define imx_check_flag(pci, val) (pci->drvdata->flags & val) @@ -103,6 +122,7 @@ struct imx_pcie_drvdata { const char *gpr; const char * const *clk_names; const u32 clks_cnt; + const u32 clks_optional_cnt; const u32 ltssm_off; const u32 ltssm_mask; const u32 mode_off[IMX_PCIE_MAX_INSTANCES]; @@ -111,19 +131,18 @@ struct imx_pcie_drvdata { int (*init_phy)(struct imx_pcie *pcie); int (*enable_ref_clk)(struct imx_pcie *pcie, bool enable); int (*core_reset)(struct imx_pcie *pcie, bool assert); + const struct dw_pcie_host_ops *ops; }; struct imx_pcie { struct dw_pcie *pci; struct gpio_desc *reset_gpiod; - bool link_is_up; struct clk_bulk_data clks[IMX_PCIE_MAX_CLKS]; struct regmap *iomuxc_gpr; u16 msi_ctrl; u32 controller_id; struct reset_control *pciephy_reset; struct reset_control *apps_reset; - struct reset_control *turnoff_reset; u32 tx_deemph_gen1; u32 tx_deemph_gen2_3p5db; u32 tx_deemph_gen2_6db; @@ -139,6 +158,9 @@ struct imx_pcie { struct device *pd_pcie_phy; struct phy *phy; const struct imx_pcie_drvdata *drvdata; + + /* Ensure that only one device's LUT is configured at any given time */ + struct mutex lock; }; /* Parameters for the waiting for PCIe PHY PLL to lock on i.MX7 */ @@ -234,11 +256,11 @@ static void imx_pcie_configure_type(struct imx_pcie *imx_pcie) id = imx_pcie->controller_id; - /* If mode_mask is 0, then generic PHY driver is used to set the mode */ + /* If mode_mask is 0, generic PHY driver is used to set the mode */ if (!drvdata->mode_mask[0]) return; - /* If mode_mask[id] is zero, means each controller have its individual gpr */ + /* If mode_mask[id] is 0, each controller has its individual GPR */ if (!drvdata->mode_mask[id]) id = 0; @@ -375,14 +397,15 @@ static int pcie_phy_write(struct imx_pcie *imx_pcie, int addr, u16 data) static int imx8mq_pcie_init_phy(struct imx_pcie *imx_pcie) { - /* TODO: Currently this code assumes external oscillator is being used */ + /* TODO: This code assumes external oscillator is being used */ regmap_update_bits(imx_pcie->iomuxc_gpr, imx_pcie_grp_offset(imx_pcie), IMX8MQ_GPR_PCIE_REF_USE_PAD, IMX8MQ_GPR_PCIE_REF_USE_PAD); /* - * Regarding the datasheet, the PCIE_VPH is suggested to be 1.8V. If the PCIE_VPH is - * supplied by 3.3V, the VREG_BYPASS should be cleared to zero. + * Per the datasheet, the PCIE_VPH is suggested to be 1.8V. If the + * PCIE_VPH is supplied by 3.3V, the VREG_BYPASS should be cleared + * to zero. */ if (imx_pcie->vph && regulator_get_voltage(imx_pcie->vph) > 3000000) regmap_update_bits(imx_pcie->iomuxc_gpr, @@ -393,13 +416,6 @@ static int imx8mq_pcie_init_phy(struct imx_pcie *imx_pcie) return 0; } -static int imx7d_pcie_init_phy(struct imx_pcie *imx_pcie) -{ - regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, 0); - - return 0; -} - static int imx_pcie_init_phy(struct imx_pcie *imx_pcie) { regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, @@ -576,7 +592,7 @@ static int imx_pcie_attach_pd(struct device *dev) DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); if (!link) { - dev_err(dev, "Failed to add device_link to pcie pd.\n"); + dev_err(dev, "Failed to add device_link to pcie pd\n"); return -EINVAL; } @@ -589,7 +605,7 @@ static int imx_pcie_attach_pd(struct device *dev) DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); if (!link) { - dev_err(dev, "Failed to add device_link to pcie_phy pd.\n"); + dev_err(dev, "Failed to add device_link to pcie_phy pd\n"); return -EINVAL; } @@ -598,10 +614,9 @@ static int imx_pcie_attach_pd(struct device *dev) static int imx6sx_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) { - if (enable) - regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_TEST_POWERDOWN); - + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_TEST_POWERDOWN, + enable ? 0 : IMX6SX_GPR12_PCIE_TEST_POWERDOWN); return 0; } @@ -611,10 +626,10 @@ static int imx6q_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) /* power up core phy and enable ref clock */ regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_TEST_PD); /* - * the async reset input need ref clock to sync internally, + * The async reset input need ref clock to sync internally, * when the ref clock comes after reset, internal synced * reset time is too short, cannot meet the requirement. - * add one ~10us delay here. + * Add a ~10us delay here. */ usleep_range(10, 100); regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_REF_CLK_EN); @@ -630,19 +645,20 @@ static int imx8mm_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) { int offset = imx_pcie_grp_offset(imx_pcie); - if (enable) { - regmap_clear_bits(imx_pcie->iomuxc_gpr, offset, IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE); - regmap_set_bits(imx_pcie->iomuxc_gpr, offset, IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN); - } - + regmap_update_bits(imx_pcie->iomuxc_gpr, offset, + IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE, + enable ? 0 : IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE); + regmap_update_bits(imx_pcie->iomuxc_gpr, offset, + IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN, + enable ? IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN : 0); return 0; } static int imx7d_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) { - if (!enable) - regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX7D_GPR12_PCIE_PHY_REFCLK_SEL); + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, + enable ? 0 : IMX7D_GPR12_PCIE_PHY_REFCLK_SEL); return 0; } @@ -775,6 +791,7 @@ static void imx_pcie_assert_core_reset(struct imx_pcie *imx_pcie) static int imx_pcie_deassert_core_reset(struct imx_pcie *imx_pcie) { reset_control_deassert(imx_pcie->pciephy_reset); + reset_control_deassert(imx_pcie->apps_reset); if (imx_pcie->drvdata->core_reset) imx_pcie->drvdata->core_reset(imx_pcie, false); @@ -884,6 +901,7 @@ static int imx_pcie_start_link(struct dw_pcie *pci) if (imx_pcie->drvdata->flags & IMX_PCIE_FLAG_IMX_SPEED_CHANGE) { + /* * On i.MX7, DIRECT_SPEED_CHANGE behaves differently * from i.MX6 family when no link speed transition @@ -892,7 +910,6 @@ static int imx_pcie_start_link(struct dw_pcie *pci) * which will cause the following code to report false * failure. */ - ret = imx_pcie_wait_for_speed_change(imx_pcie); if (ret) { dev_err(dev, "Failed to bring link up!\n"); @@ -908,13 +925,11 @@ static int imx_pcie_start_link(struct dw_pcie *pci) dev_info(dev, "Link: Only Gen1 is enabled\n"); } - imx_pcie->link_is_up = true; tmp = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA); dev_info(dev, "Link up, Gen%i\n", tmp & PCI_EXP_LNKSTA_CLS); return 0; err_reset_phy: - imx_pcie->link_is_up = false; dev_dbg(dev, "PHY DEBUG_R0=0x%08x DEBUG_R1=0x%08x\n", dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0), dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1)); @@ -930,6 +945,184 @@ static void imx_pcie_stop_link(struct dw_pcie *pci) imx_pcie_ltssm_disable(dev); } +static int imx_pcie_add_lut(struct imx_pcie *imx_pcie, u16 rid, u8 sid) +{ + struct dw_pcie *pci = imx_pcie->pci; + struct device *dev = pci->dev; + u32 data1, data2; + int free = -1; + int i; + + if (sid >= 64) { + dev_err(dev, "Invalid SID for index %d\n", sid); + return -EINVAL; + } + + guard(mutex)(&imx_pcie->lock); + + /* + * Iterate through all LUT entries to check for duplicate RID and + * identify the first available entry. Configure this available entry + * immediately after verification to avoid rescanning it. + */ + for (i = 0; i < IMX95_MAX_LUT; i++) { + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_ACSCTRL, IMX95_PEO_LUT_RWA | i); + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, &data1); + + if (!(data1 & IMX95_PE0_LUT_VLD)) { + if (free < 0) + free = i; + continue; + } + + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2); + + /* Do not add duplicate RID */ + if (rid == FIELD_GET(IMX95_PE0_LUT_REQID, data2)) { + dev_warn(dev, "Existing LUT entry available for RID (%d)", rid); + return 0; + } + } + + if (free < 0) { + dev_err(dev, "LUT entry is not available\n"); + return -ENOSPC; + } + + data1 = FIELD_PREP(IMX95_PE0_LUT_DAC_ID, 0); + data1 |= FIELD_PREP(IMX95_PE0_LUT_STREAM_ID, sid); + data1 |= IMX95_PE0_LUT_VLD; + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, data1); + + data2 = IMX95_PE0_LUT_MASK; /* Match all bits of RID */ + data2 |= FIELD_PREP(IMX95_PE0_LUT_REQID, rid); + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, data2); + + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_ACSCTRL, free); + + return 0; +} + +static void imx_pcie_remove_lut(struct imx_pcie *imx_pcie, u16 rid) +{ + u32 data2; + int i; + + guard(mutex)(&imx_pcie->lock); + + for (i = 0; i < IMX95_MAX_LUT; i++) { + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_ACSCTRL, IMX95_PEO_LUT_RWA | i); + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2); + if (FIELD_GET(IMX95_PE0_LUT_REQID, data2) == rid) { + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_DATA1, 0); + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_DATA2, 0); + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_ACSCTRL, i); + + break; + } + } +} + +static int imx_pcie_enable_device(struct pci_host_bridge *bridge, + struct pci_dev *pdev) +{ + struct imx_pcie *imx_pcie = to_imx_pcie(to_dw_pcie_from_pp(bridge->sysdata)); + u32 sid_i, sid_m, rid = pci_dev_id(pdev); + struct device_node *target; + struct device *dev; + int err_i, err_m; + u32 sid = 0; + + dev = imx_pcie->pci->dev; + + target = NULL; + err_i = of_map_id(dev->of_node, rid, "iommu-map", "iommu-map-mask", + &target, &sid_i); + if (target) { + of_node_put(target); + } else { + /* + * "target == NULL && err_i == 0" means RID out of map range. + * Use 1:1 map RID to streamID. Hardware can't support this + * because the streamID is only 6 bits + */ + err_i = -EINVAL; + } + + target = NULL; + err_m = of_map_id(dev->of_node, rid, "msi-map", "msi-map-mask", + &target, &sid_m); + + /* + * err_m target + * 0 NULL RID out of range. Use 1:1 map RID to + * streamID, Current hardware can't + * support it, so return -EINVAL. + * != 0 NULL msi-map does not exist, use built-in MSI + * 0 != NULL Get correct streamID from RID + * != 0 != NULL Invalid combination + */ + if (!err_m && !target) + return -EINVAL; + else if (target) + of_node_put(target); /* Find streamID map entry for RID in msi-map */ + + /* + * msi-map iommu-map + * N N DWC MSI Ctrl + * Y Y ITS + SMMU, require the same SID + * Y N ITS + * N Y DWC MSI Ctrl + SMMU + */ + if (err_i && err_m) + return 0; + + if (!err_i && !err_m) { + /* + * Glue Layer + * <==========> + * ┌─────┐ ┌──────────┐ + * │ LUT │ 6-bit streamID │ │ + * │ │─────────────────►│ MSI │ + * └─────┘ 2-bit ctrl ID │ │ + * ┌───────────►│ │ + * (i.MX95) │ │ │ + * 00 PCIe0 │ │ │ + * 01 ENETC │ │ │ + * 10 PCIe1 │ │ │ + * │ └──────────┘ + * The MSI glue layer auto adds 2 bits controller ID ahead of + * streamID, so mask these 2 bits to get streamID. The + * IOMMU glue layer doesn't do that. + */ + if (sid_i != (sid_m & IMX95_SID_MASK)) { + dev_err(dev, "iommu-map and msi-map entries mismatch!\n"); + return -EINVAL; + } + } + + if (!err_i) + sid = sid_i; + else if (!err_m) + sid = sid_m & IMX95_SID_MASK; + + return imx_pcie_add_lut(imx_pcie, rid, sid); +} + +static void imx_pcie_disable_device(struct pci_host_bridge *bridge, + struct pci_dev *pdev) +{ + struct imx_pcie *imx_pcie; + + imx_pcie = to_imx_pcie(to_dw_pcie_from_pp(bridge->sysdata)); + imx_pcie_remove_lut(imx_pcie, pci_dev_id(pdev)); +} + static int imx_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); @@ -946,6 +1139,11 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp) } } + if (pp->bridge && imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_LUT)) { + pp->bridge->enable_device = imx_pcie_enable_device; + pp->bridge->disable_device = imx_pcie_disable_device; + } + imx_pcie_assert_core_reset(imx_pcie); if (imx_pcie->drvdata->init_phy) @@ -966,7 +1164,9 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp) goto err_clk_disable; } - ret = phy_set_mode_ext(imx_pcie->phy, PHY_MODE_PCIE, PHY_MODE_PCIE_RC); + ret = phy_set_mode_ext(imx_pcie->phy, PHY_MODE_PCIE, + imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE ? + PHY_MODE_PCIE_EP : PHY_MODE_PCIE_RC); if (ret) { dev_err(dev, "unable to set PCIe PHY mode\n"); goto err_phy_exit; @@ -1033,9 +1233,31 @@ static u64 imx_pcie_cpu_addr_fixup(struct dw_pcie *pcie, u64 cpu_addr) return cpu_addr - entry->offset; } +/* + * In old DWC implementations, PCIE_ATU_INHIBIT_PAYLOAD in iATU Ctrl2 + * register is reserved, so the generic DWC implementation of sending the + * PME_Turn_Off message using a dummy MMIO write cannot be used. + */ +static void imx_pcie_pme_turn_off(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct imx_pcie *imx_pcie = to_imx_pcie(pci); + + regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_PM_TURN_OFF); + regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_PM_TURN_OFF); + + usleep_range(PCIE_PME_TO_L2_TIMEOUT_US/10, PCIE_PME_TO_L2_TIMEOUT_US); +} + static const struct dw_pcie_host_ops imx_pcie_host_ops = { .init = imx_pcie_host_init, .deinit = imx_pcie_host_exit, + .pme_turn_off = imx_pcie_pme_turn_off, +}; + +static const struct dw_pcie_host_ops imx_pcie_host_dw_pme_ops = { + .init = imx_pcie_host_init, + .deinit = imx_pcie_host_exit, }; static const struct dw_pcie_ops dw_pcie_ops = { @@ -1082,16 +1304,27 @@ static const struct pci_epc_features imx8m_pcie_epc_features = { .align = SZ_64K, }; +static const struct pci_epc_features imx8q_pcie_epc_features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = false, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, + .align = SZ_64K, +}; + /* - * BAR# | Default BAR enable | Default BAR Type | Default BAR Size | BAR Sizing Scheme - * ================================================================================================ - * BAR0 | Enable | 64-bit | 1 MB | Programmable Size - * BAR1 | Disable | 32-bit | 64 KB | Fixed Size - * BAR1 should be disabled if BAR0 is 64bit. - * BAR2 | Enable | 32-bit | 1 MB | Programmable Size - * BAR3 | Enable | 32-bit | 64 KB | Programmable Size - * BAR4 | Enable | 32-bit | 1M | Programmable Size - * BAR5 | Enable | 32-bit | 64 KB | Programmable Size + * | Default | Default | Default | BAR Sizing + * BAR# | Enable? | Type | Size | Scheme + * ======================================================= + * BAR0 | Enable | 64-bit | 1 MB | Programmable Size + * BAR1 | Disable | 32-bit | 64 KB | Fixed Size + * (BAR1 should be disabled if BAR0 is 64-bit) + * BAR2 | Enable | 32-bit | 1 MB | Programmable Size + * BAR3 | Enable | 32-bit | 64 KB | Programmable Size + * BAR4 | Enable | 32-bit | 1 MB | Programmable Size + * BAR5 | Enable | 32-bit | 64 KB | Programmable Size */ static const struct pci_epc_features imx95_pcie_epc_features = { .msi_capable = true, @@ -1118,7 +1351,6 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie, struct platform_device *pdev) { int ret; - unsigned int pcie_dbi2_offset; struct dw_pcie_ep *ep; struct dw_pcie *pci = imx_pcie->pci; struct dw_pcie_rp *pp = &pci->pp; @@ -1128,28 +1360,6 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie, ep = &pci->ep; ep->ops = &pcie_ep_ops; - switch (imx_pcie->drvdata->variant) { - case IMX8MQ_EP: - case IMX8MM_EP: - case IMX8MP_EP: - pcie_dbi2_offset = SZ_1M; - break; - default: - pcie_dbi2_offset = SZ_4K; - break; - } - - pci->dbi_base2 = pci->dbi_base + pcie_dbi2_offset; - - /* - * FIXME: Ideally, dbi2 base address should come from DT. But since only IMX95 is defining - * "dbi2" in DT, "dbi_base2" is set to NULL here for that platform alone so that the DWC - * core code can fetch that from DT. But once all platform DTs were fixed, this and the - * above "dbi_base2" setting should be removed. - */ - if (device_property_match_string(dev, "reg-names", "dbi2") >= 0) - pci->dbi_base2 = NULL; - if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_SUPPORT_64BIT)) dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); @@ -1176,43 +1386,6 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie, return 0; } -static void imx_pcie_pm_turnoff(struct imx_pcie *imx_pcie) -{ - struct device *dev = imx_pcie->pci->dev; - - /* Some variants have a turnoff reset in DT */ - if (imx_pcie->turnoff_reset) { - reset_control_assert(imx_pcie->turnoff_reset); - reset_control_deassert(imx_pcie->turnoff_reset); - goto pm_turnoff_sleep; - } - - /* Others poke directly at IOMUXC registers */ - switch (imx_pcie->drvdata->variant) { - case IMX6SX: - case IMX6QP: - regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_PM_TURN_OFF, - IMX6SX_GPR12_PCIE_PM_TURN_OFF); - regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_PM_TURN_OFF, 0); - break; - default: - dev_err(dev, "PME_Turn_Off not implemented\n"); - return; - } - - /* - * Components with an upstream port must respond to - * PME_Turn_Off with PME_TO_Ack but we can't check. - * - * The standard recommends a 1-10ms timeout after which to - * proceed anyway as if acks were received. - */ -pm_turnoff_sleep: - usleep_range(1000, 10000); -} - static void imx_pcie_msi_save_restore(struct imx_pcie *imx_pcie, bool save) { u8 offset; @@ -1236,7 +1409,6 @@ static void imx_pcie_msi_save_restore(struct imx_pcie *imx_pcie, bool save) static int imx_pcie_suspend_noirq(struct device *dev) { struct imx_pcie *imx_pcie = dev_get_drvdata(dev); - struct dw_pcie_rp *pp = &imx_pcie->pci->pp; if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_SUPPORTS_SUSPEND)) return 0; @@ -1251,9 +1423,7 @@ static int imx_pcie_suspend_noirq(struct device *dev) imx_pcie_assert_core_reset(imx_pcie); imx_pcie->drvdata->enable_ref_clk(imx_pcie, false); } else { - imx_pcie_pm_turnoff(imx_pcie); - imx_pcie_stop_link(imx_pcie->pci); - imx_pcie_host_exit(pp); + return dw_pcie_suspend_noirq(imx_pcie->pci); } return 0; @@ -1263,7 +1433,6 @@ static int imx_pcie_resume_noirq(struct device *dev) { int ret; struct imx_pcie *imx_pcie = dev_get_drvdata(dev); - struct dw_pcie_rp *pp = &imx_pcie->pci->pp; if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_SUPPORTS_SUSPEND)) return 0; @@ -1275,6 +1444,7 @@ static int imx_pcie_resume_noirq(struct device *dev) ret = imx_pcie_deassert_core_reset(imx_pcie); if (ret) return ret; + /* * Using PCIE_TEST_PD seems to disable MSI and powers down the * root complex. This is why we have to setup the rc again and @@ -1283,17 +1453,12 @@ static int imx_pcie_resume_noirq(struct device *dev) ret = dw_pcie_setup_rc(&imx_pcie->pci->pp); if (ret) return ret; - imx_pcie_msi_save_restore(imx_pcie, false); } else { - ret = imx_pcie_host_init(pp); + ret = dw_pcie_resume_noirq(imx_pcie->pci); if (ret) return ret; - imx_pcie_msi_save_restore(imx_pcie, false); - dw_pcie_setup_rc(pp); - - if (imx_pcie->link_is_up) - imx_pcie_start_link(imx_pcie->pci); } + imx_pcie_msi_save_restore(imx_pcie, false); return 0; } @@ -1311,9 +1476,8 @@ static int imx_pcie_probe(struct platform_device *pdev) struct device_node *np; struct resource *dbi_base; struct device_node *node = dev->of_node; - int ret; + int i, ret, req_cnt; u16 val; - int i; imx_pcie = devm_kzalloc(dev, sizeof(*imx_pcie), GFP_KERNEL); if (!imx_pcie) @@ -1325,11 +1489,17 @@ static int imx_pcie_probe(struct platform_device *pdev) pci->dev = dev; pci->ops = &dw_pcie_ops; - pci->pp.ops = &imx_pcie_host_ops; imx_pcie->pci = pci; imx_pcie->drvdata = of_device_get_match_data(dev); + mutex_init(&imx_pcie->lock); + + if (imx_pcie->drvdata->ops) + pci->pp.ops = imx_pcie->drvdata->ops; + else + pci->pp.ops = &imx_pcie_host_dw_pme_ops; + /* Find the PHY if one is defined, only imx7d uses it */ np = of_parse_phandle(node, "fsl,imx7d-pcie-phy", 0); if (np) { @@ -1363,9 +1533,13 @@ static int imx_pcie_probe(struct platform_device *pdev) imx_pcie->clks[i].id = imx_pcie->drvdata->clk_names[i]; /* Fetch clocks */ - ret = devm_clk_bulk_get(dev, imx_pcie->drvdata->clks_cnt, imx_pcie->clks); + req_cnt = imx_pcie->drvdata->clks_cnt - imx_pcie->drvdata->clks_optional_cnt; + ret = devm_clk_bulk_get(dev, req_cnt, imx_pcie->clks); if (ret) return ret; + imx_pcie->clks[req_cnt].clk = devm_clk_get_optional(dev, "ref"); + if (IS_ERR(imx_pcie->clks[req_cnt].clk)) + return PTR_ERR(imx_pcie->clks[req_cnt].clk); if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_PHYDRV)) { imx_pcie->phy = devm_phy_get(dev, "pcie-phy"); @@ -1391,7 +1565,6 @@ static int imx_pcie_probe(struct platform_device *pdev) switch (imx_pcie->drvdata->variant) { case IMX8MQ: case IMX8MQ_EP: - case IMX7D: if (dbi_base->start == IMX8MQ_PCIE2_BASE_ADDR) imx_pcie->controller_id = 1; break; @@ -1399,13 +1572,6 @@ static int imx_pcie_probe(struct platform_device *pdev) break; } - /* Grab turnoff reset */ - imx_pcie->turnoff_reset = devm_reset_control_get_optional_exclusive(dev, "turnoff"); - if (IS_ERR(imx_pcie->turnoff_reset)) { - dev_err(dev, "Failed to get TURNOFF reset control\n"); - return PTR_ERR(imx_pcie->turnoff_reset); - } - if (imx_pcie->drvdata->gpr) { /* Grab GPR config register range */ imx_pcie->iomuxc_gpr = @@ -1484,6 +1650,7 @@ static int imx_pcie_probe(struct platform_device *pdev) if (ret < 0) return ret; } else { + pci->pp.use_atu_msg = true; ret = dw_pcie_host_init(&pci->pp); if (ret < 0) return ret; @@ -1513,6 +1680,7 @@ static const char * const imx8mm_clks[] = {"pcie_bus", "pcie", "pcie_aux"}; static const char * const imx8mq_clks[] = {"pcie_bus", "pcie", "pcie_phy", "pcie_aux"}; static const char * const imx6sx_clks[] = {"pcie_bus", "pcie", "pcie_phy", "pcie_inbound_axi"}; static const char * const imx8q_clks[] = {"mstr", "slv", "dbi"}; +static const char * const imx95_clks[] = {"pcie_bus", "pcie", "pcie_phy", "pcie_aux", "ref"}; static const struct imx_pcie_drvdata drvdata[] = { [IMX6Q] = { @@ -1548,6 +1716,7 @@ static const struct imx_pcie_drvdata drvdata[] = { .init_phy = imx6sx_pcie_init_phy, .enable_ref_clk = imx6sx_pcie_enable_ref_clk, .core_reset = imx6sx_pcie_core_reset, + .ops = &imx_pcie_host_ops, }, [IMX6QP] = { .variant = IMX6QP, @@ -1565,6 +1734,7 @@ static const struct imx_pcie_drvdata drvdata[] = { .init_phy = imx_pcie_init_phy, .enable_ref_clk = imx6q_pcie_enable_ref_clk, .core_reset = imx6qp_pcie_core_reset, + .ops = &imx_pcie_host_ops, }, [IMX7D] = { .variant = IMX7D, @@ -1576,14 +1746,14 @@ static const struct imx_pcie_drvdata drvdata[] = { .clks_cnt = ARRAY_SIZE(imx6q_clks), .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, - .init_phy = imx7d_pcie_init_phy, .enable_ref_clk = imx7d_pcie_enable_ref_clk, .core_reset = imx7d_pcie_core_reset, }, [IMX8MQ] = { .variant = IMX8MQ, .flags = IMX_PCIE_FLAG_HAS_APP_RESET | - IMX_PCIE_FLAG_HAS_PHY_RESET, + IMX_PCIE_FLAG_HAS_PHY_RESET | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, .gpr = "fsl,imx8mq-iomuxc-gpr", .clk_names = imx8mq_clks, .clks_cnt = ARRAY_SIZE(imx8mq_clks), @@ -1621,15 +1791,19 @@ static const struct imx_pcie_drvdata drvdata[] = { [IMX8Q] = { .variant = IMX8Q, .flags = IMX_PCIE_FLAG_HAS_PHYDRV | - IMX_PCIE_FLAG_CPU_ADDR_FIXUP, + IMX_PCIE_FLAG_CPU_ADDR_FIXUP | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, .clk_names = imx8q_clks, .clks_cnt = ARRAY_SIZE(imx8q_clks), }, [IMX95] = { .variant = IMX95, - .flags = IMX_PCIE_FLAG_HAS_SERDES, - .clk_names = imx8mq_clks, - .clks_cnt = ARRAY_SIZE(imx8mq_clks), + .flags = IMX_PCIE_FLAG_HAS_SERDES | + IMX_PCIE_FLAG_HAS_LUT | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, + .clk_names = imx95_clks, + .clks_cnt = ARRAY_SIZE(imx95_clks), + .clks_optional_cnt = 1, .ltssm_off = IMX95_PE0_GEN_CTRL_3, .ltssm_mask = IMX95_PCIE_LTSSM_EN, .mode_off[0] = IMX95_PE0_GEN_CTRL_1, @@ -1678,6 +1852,14 @@ static const struct imx_pcie_drvdata drvdata[] = { .epc_features = &imx8m_pcie_epc_features, .enable_ref_clk = imx8mm_pcie_enable_ref_clk, }, + [IMX8Q_EP] = { + .variant = IMX8Q_EP, + .flags = IMX_PCIE_FLAG_HAS_PHYDRV, + .mode = DW_PCIE_EP_TYPE, + .epc_features = &imx8q_pcie_epc_features, + .clk_names = imx8q_clks, + .clks_cnt = ARRAY_SIZE(imx8q_clks), + }, [IMX95_EP] = { .variant = IMX95_EP, .flags = IMX_PCIE_FLAG_HAS_SERDES | @@ -1707,6 +1889,7 @@ static const struct of_device_id imx_pcie_of_match[] = { { .compatible = "fsl,imx8mq-pcie-ep", .data = &drvdata[IMX8MQ_EP], }, { .compatible = "fsl,imx8mm-pcie-ep", .data = &drvdata[IMX8MM_EP], }, { .compatible = "fsl,imx8mp-pcie-ep", .data = &drvdata[IMX8MP_EP], }, + { .compatible = "fsl,imx8q-pcie-ep", .data = &drvdata[IMX8Q_EP], }, { .compatible = "fsl,imx95-pcie-ep", .data = &drvdata[IMX95_EP], }, {}, }; diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c index ee6f52568133..239a05b36e8e 100644 --- a/drivers/pci/controller/dwc/pci-layerscape.c +++ b/drivers/pci/controller/dwc/pci-layerscape.c @@ -329,7 +329,6 @@ static int ls_pcie_probe(struct platform_device *pdev) struct ls_pcie *pcie; struct resource *dbi_base; u32 index[2]; - int ret; pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); if (!pcie) @@ -355,16 +354,15 @@ static int ls_pcie_probe(struct platform_device *pdev) pcie->pf_lut_base = pci->dbi_base + pcie->drvdata->pf_lut_off; if (pcie->drvdata->scfg_support) { - pcie->scfg = syscon_regmap_lookup_by_phandle(dev->of_node, "fsl,pcie-scfg"); + pcie->scfg = + syscon_regmap_lookup_by_phandle_args(dev->of_node, + "fsl,pcie-scfg", 2, + index); if (IS_ERR(pcie->scfg)) { dev_err(dev, "No syscfg phandle specified\n"); return PTR_ERR(pcie->scfg); } - ret = of_property_read_u32_array(dev->of_node, "fsl,pcie-scfg", index, 2); - if (ret) - return ret; - pcie->index = index[1]; } diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c index f8e7283dacd4..234c8cbcae3a 100644 --- a/drivers/pci/controller/dwc/pcie-artpec6.c +++ b/drivers/pci/controller/dwc/pcie-artpec6.c @@ -369,9 +369,22 @@ static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, return 0; } +static const struct pci_epc_features artpec6_pcie_epc_features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = false, +}; + +static const struct pci_epc_features * +artpec6_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &artpec6_pcie_epc_features; +} + static const struct dw_pcie_ep_ops pcie_ep_ops = { .init = artpec6_pcie_ep_init, .raise_irq = artpec6_pcie_raise_irq, + .get_features = artpec6_pcie_get_features, }; static int artpec6_pcie_probe(struct platform_device *pdev) diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index f3ac7d46a855..8e07d432e74f 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -128,7 +128,8 @@ static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, } static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type, - dma_addr_t cpu_addr, enum pci_barno bar) + dma_addr_t cpu_addr, enum pci_barno bar, + size_t size) { int ret; u32 free_win; @@ -145,7 +146,7 @@ static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type, } ret = dw_pcie_prog_ep_inbound_atu(pci, func_no, free_win, type, - cpu_addr, bar); + cpu_addr, bar, size); if (ret < 0) { dev_err(pci->dev, "Failed to program IB window\n"); return ret; @@ -222,20 +223,31 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, if ((flags & PCI_BASE_ADDRESS_MEM_TYPE_64) && (bar & 1)) return -EINVAL; + /* + * Certain EPF drivers dynamically change the physical address of a BAR + * (i.e. they call set_bar() twice, without ever calling clear_bar(), as + * calling clear_bar() would clear the BAR's PCI address assigned by the + * host). + */ + if (ep->epf_bar[bar]) { + /* + * We can only dynamically change a BAR if the new BAR size and + * BAR flags do not differ from the existing configuration. + */ + if (ep->epf_bar[bar]->barno != bar || + ep->epf_bar[bar]->size != size || + ep->epf_bar[bar]->flags != flags) + return -EINVAL; + + /* + * When dynamically changing a BAR, skip writing the BAR reg, as + * that would clear the BAR's PCI address assigned by the host. + */ + goto config_atu; + } + reg = PCI_BASE_ADDRESS_0 + (4 * bar); - if (!(flags & PCI_BASE_ADDRESS_SPACE)) - type = PCIE_ATU_TYPE_MEM; - else - type = PCIE_ATU_TYPE_IO; - - ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar); - if (ret) - return ret; - - if (ep->epf_bar[bar]) - return 0; - dw_pcie_dbi_ro_wr_en(pci); dw_pcie_ep_writel_dbi2(ep, func_no, reg, lower_32_bits(size - 1)); @@ -246,9 +258,21 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0); } - ep->epf_bar[bar] = epf_bar; dw_pcie_dbi_ro_wr_dis(pci); +config_atu: + if (!(flags & PCI_BASE_ADDRESS_SPACE)) + type = PCIE_ATU_TYPE_MEM; + else + type = PCIE_ATU_TYPE_IO; + + ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar, + size); + if (ret) + return ret; + + ep->epf_bar[bar] = epf_bar; + return 0; } diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index d2291c3ceb8b..ffaded8f2df7 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -436,18 +436,18 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) return ret; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config"); - if (res) { - pp->cfg0_size = resource_size(res); - pp->cfg0_base = res->start; - - pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res); - if (IS_ERR(pp->va_cfg0_base)) - return PTR_ERR(pp->va_cfg0_base); - } else { - dev_err(dev, "Missing *config* reg space\n"); + if (!res) { + dev_err(dev, "Missing \"config\" reg space\n"); return -ENODEV; } + pp->cfg0_size = resource_size(res); + pp->cfg0_base = res->start; + + pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pp->va_cfg0_base)) + return PTR_ERR(pp->va_cfg0_base); + bridge = devm_pci_alloc_host_bridge(dev, 0); if (!bridge) return -ENOMEM; @@ -530,8 +530,14 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) goto err_remove_edma; } - /* Ignore errors, the link may come up later */ - dw_pcie_wait_for_link(pci); + /* + * Note: Skip the link up delay only when a Link Up IRQ is present. + * If there is no Link Up IRQ, we should not bypass the delay + * because that would require users to manually rescan for devices. + */ + if (!pp->use_linkup_irq) + /* Ignore errors, the link may come up later */ + dw_pcie_wait_for_link(pci); bridge->sysdata = pp; @@ -918,7 +924,7 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci) { u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); u32 val; - int ret = 0; + int ret; /* * If L1SS is supported, then do not put the link into L2 as some @@ -927,25 +933,33 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci) if (dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKCTL) & PCI_EXP_LNKCTL_ASPM_L1) return 0; - if (dw_pcie_get_ltssm(pci) <= DW_PCIE_LTSSM_DETECT_ACT) - return 0; - - if (pci->pp.ops->pme_turn_off) + if (pci->pp.ops->pme_turn_off) { pci->pp.ops->pme_turn_off(&pci->pp); - else + } else { ret = dw_pcie_pme_turn_off(pci); + if (ret) + return ret; + } - if (ret) - return ret; - - ret = read_poll_timeout(dw_pcie_get_ltssm, val, val == DW_PCIE_LTSSM_L2_IDLE, + ret = read_poll_timeout(dw_pcie_get_ltssm, val, + val == DW_PCIE_LTSSM_L2_IDLE || + val <= DW_PCIE_LTSSM_DETECT_WAIT, PCIE_PME_TO_L2_TIMEOUT_US/10, PCIE_PME_TO_L2_TIMEOUT_US, false, pci); if (ret) { + /* Only log message when LTSSM isn't in DETECT or POLL */ dev_err(pci->dev, "Timeout waiting for L2 entry! LTSSM: 0x%x\n", val); return ret; } + /* + * Per PCIe r6.0, sec 5.3.3.2.1, software should wait at least + * 100ns after L2/L3 Ready before turning off refclock and + * main power. This is harmless when no endpoint is connected. + */ + udelay(1); + + dw_pcie_stop_link(pci); if (pci->pp.ops->deinit) pci->pp.ops->deinit(&pci->pp); diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index 6d6cbc8b5b2c..145e7f579072 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -597,11 +597,12 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type, } int dw_pcie_prog_ep_inbound_atu(struct dw_pcie *pci, u8 func_no, int index, - int type, u64 cpu_addr, u8 bar) + int type, u64 cpu_addr, u8 bar, size_t size) { u32 retries, val; - if (!IS_ALIGNED(cpu_addr, pci->region_align)) + if (!IS_ALIGNED(cpu_addr, pci->region_align) || + !IS_ALIGNED(cpu_addr, size)) return -EINVAL; dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET, @@ -970,7 +971,7 @@ static int dw_pcie_edma_irq_verify(struct dw_pcie *pci) { struct platform_device *pdev = to_platform_device(pci->dev); u16 ch_cnt = pci->edma.ll_wr_cnt + pci->edma.ll_rd_cnt; - char name[6]; + char name[15]; int ret; if (pci->edma.nr_irqs == 1) diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 347ab74ac35a..501d9ddfea16 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -330,6 +330,7 @@ enum dw_pcie_ltssm { /* Need to align with PCIE_PORT_DEBUG0 bits 0:5 */ DW_PCIE_LTSSM_DETECT_QUIET = 0x0, DW_PCIE_LTSSM_DETECT_ACT = 0x1, + DW_PCIE_LTSSM_DETECT_WAIT = 0x6, DW_PCIE_LTSSM_L0 = 0x11, DW_PCIE_LTSSM_L2_IDLE = 0x15, @@ -379,6 +380,7 @@ struct dw_pcie_rp { bool use_atu_msg; int msg_atu_index; struct resource *msg_res; + bool use_linkup_irq; }; struct dw_pcie_ep_ops { @@ -491,16 +493,13 @@ int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type, u64 cpu_addr, u64 pci_addr, u64 size); int dw_pcie_prog_ep_inbound_atu(struct dw_pcie *pci, u8 func_no, int index, - int type, u64 cpu_addr, u8 bar); + int type, u64 cpu_addr, u8 bar, size_t size); void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index); void dw_pcie_setup(struct dw_pcie *pci); void dw_pcie_iatu_detect(struct dw_pcie *pci); int dw_pcie_edma_detect(struct dw_pcie *pci); void dw_pcie_edma_remove(struct dw_pcie *pci); -int dw_pcie_suspend_noirq(struct dw_pcie *pci); -int dw_pcie_resume_noirq(struct dw_pcie *pci); - static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val) { dw_pcie_write_dbi(pci, reg, 0x4, val); @@ -678,6 +677,8 @@ static inline enum dw_pcie_ltssm dw_pcie_get_ltssm(struct dw_pcie *pci) } #ifdef CONFIG_PCIE_DW_HOST +int dw_pcie_suspend_noirq(struct dw_pcie *pci); +int dw_pcie_resume_noirq(struct dw_pcie *pci); irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp); int dw_pcie_setup_rc(struct dw_pcie_rp *pp); int dw_pcie_host_init(struct dw_pcie_rp *pp); @@ -686,6 +687,16 @@ int dw_pcie_allocate_domains(struct dw_pcie_rp *pp); void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn, int where); #else +static inline int dw_pcie_suspend_noirq(struct dw_pcie *pci) +{ + return 0; +} + +static inline int dw_pcie_resume_noirq(struct dw_pcie *pci) +{ + return 0; +} + static inline irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp) { return IRQ_NONE; diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c index 1170e1107508..93698abff4d9 100644 --- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c +++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c @@ -389,6 +389,34 @@ static const struct dw_pcie_ops dw_pcie_ops = { .stop_link = rockchip_pcie_stop_link, }; +static irqreturn_t rockchip_pcie_rc_sys_irq_thread(int irq, void *arg) +{ + struct rockchip_pcie *rockchip = arg; + struct dw_pcie *pci = &rockchip->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = pci->dev; + u32 reg, val; + + reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_MISC); + rockchip_pcie_writel_apb(rockchip, reg, PCIE_CLIENT_INTR_STATUS_MISC); + + dev_dbg(dev, "PCIE_CLIENT_INTR_STATUS_MISC: %#x\n", reg); + dev_dbg(dev, "LTSSM_STATUS: %#x\n", rockchip_pcie_get_ltssm(rockchip)); + + if (reg & PCIE_RDLH_LINK_UP_CHGED) { + val = rockchip_pcie_get_ltssm(rockchip); + if ((val & PCIE_LINKUP) == PCIE_LINKUP) { + dev_dbg(dev, "Received Link up event. Starting enumeration!\n"); + /* Rescan the bus to enumerate endpoint devices */ + pci_lock_rescan_remove(); + pci_rescan_bus(pp->bridge->bus); + pci_unlock_rescan_remove(); + } + } + + return IRQ_HANDLED; +} + static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) { struct rockchip_pcie *rockchip = arg; @@ -418,14 +446,29 @@ static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) return IRQ_HANDLED; } -static int rockchip_pcie_configure_rc(struct rockchip_pcie *rockchip) +static int rockchip_pcie_configure_rc(struct platform_device *pdev, + struct rockchip_pcie *rockchip) { + struct device *dev = &pdev->dev; struct dw_pcie_rp *pp; + int irq, ret; u32 val; if (!IS_ENABLED(CONFIG_PCIE_ROCKCHIP_DW_HOST)) return -ENODEV; + irq = platform_get_irq_byname(pdev, "sys"); + if (irq < 0) + return irq; + + ret = devm_request_threaded_irq(dev, irq, NULL, + rockchip_pcie_rc_sys_irq_thread, + IRQF_ONESHOT, "pcie-sys-rc", rockchip); + if (ret) { + dev_err(dev, "failed to request PCIe sys IRQ\n"); + return ret; + } + /* LTSSM enable control mode */ val = HIWORD_UPDATE_BIT(PCIE_LTSSM_ENABLE_ENHANCE); rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_HOT_RESET_CTRL); @@ -435,8 +478,19 @@ static int rockchip_pcie_configure_rc(struct rockchip_pcie *rockchip) pp = &rockchip->pci.pp; pp->ops = &rockchip_pcie_host_ops; + pp->use_linkup_irq = true; - return dw_pcie_host_init(pp); + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "failed to initialize host\n"); + return ret; + } + + /* unmask DLL up/down indicator */ + val = HIWORD_UPDATE(PCIE_RDLH_LINK_UP_CHGED, 0); + rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_INTR_MASK_MISC); + + return ret; } static int rockchip_pcie_configure_ep(struct platform_device *pdev, @@ -450,14 +504,12 @@ static int rockchip_pcie_configure_ep(struct platform_device *pdev, return -ENODEV; irq = platform_get_irq_byname(pdev, "sys"); - if (irq < 0) { - dev_err(dev, "missing sys IRQ resource\n"); + if (irq < 0) return irq; - } ret = devm_request_threaded_irq(dev, irq, NULL, rockchip_pcie_ep_sys_irq_thread, - IRQF_ONESHOT, "pcie-sys", rockchip); + IRQF_ONESHOT, "pcie-sys-ep", rockchip); if (ret) { dev_err(dev, "failed to request PCIe sys IRQ\n"); return ret; @@ -491,7 +543,8 @@ static int rockchip_pcie_configure_ep(struct platform_device *pdev, pci_epc_init_notify(rockchip->pci.ep.epc); /* unmask DLL up/down indicator and hot reset/link-down reset */ - rockchip_pcie_writel_apb(rockchip, 0x60000, PCIE_CLIENT_INTR_MASK_MISC); + val = HIWORD_UPDATE(PCIE_RDLH_LINK_UP_CHGED | PCIE_LINK_REQ_RST_NOT_INT, 0); + rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_INTR_MASK_MISC); return ret; } @@ -553,7 +606,7 @@ static int rockchip_pcie_probe(struct platform_device *pdev) switch (data->mode) { case DW_PCIE_RC_TYPE: - ret = rockchip_pcie_configure_rc(rockchip); + ret = rockchip_pcie_configure_rc(pdev, rockchip); if (ret) goto deinit_clk; break; diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index dc102d8bd58c..e4d3366ead1f 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -1569,6 +1569,8 @@ static irqreturn_t qcom_pcie_global_irq_thread(int irq, void *data) pci_lock_rescan_remove(); pci_rescan_bus(pp->bridge->bus); pci_unlock_rescan_remove(); + + qcom_pcie_icc_opp_update(pcie); } else { dev_WARN_ONCE(dev, 1, "Received unknown event. INT_STATUS: 0x%08x\n", status); @@ -1703,6 +1705,10 @@ static int qcom_pcie_probe(struct platform_device *pdev) platform_set_drvdata(pdev, pcie); + irq = platform_get_irq_byname_optional(pdev, "global"); + if (irq > 0) + pp->use_linkup_irq = true; + ret = dw_pcie_host_init(pp); if (ret) { dev_err(dev, "cannot initialize host\n"); @@ -1716,7 +1722,6 @@ static int qcom_pcie_probe(struct platform_device *pdev) goto err_host_deinit; } - irq = platform_get_irq_byname_optional(pdev, "global"); if (irq > 0) { ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, qcom_pcie_global_irq_thread, diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c index cf5f59a745b3..f441bfd6f96a 100644 --- a/drivers/pci/controller/pci-host-common.c +++ b/drivers/pci/controller/pci-host-common.c @@ -75,6 +75,8 @@ int pci_host_common_probe(struct platform_device *pdev) bridge->sysdata = cfg; bridge->ops = (struct pci_ops *)&ops->pci_ops; + bridge->enable_device = ops->enable_device; + bridge->disable_device = ops->disable_device; bridge->msi_domain = true; return pci_host_probe(bridge); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index cdd5be16021d..6084b38bdda1 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -2053,6 +2053,7 @@ static struct irq_chip hv_msi_irq_chip = { .irq_set_affinity = irq_chip_set_affinity_parent, #ifdef CONFIG_X86 .irq_ack = irq_chip_ack_parent, + .flags = IRQCHIP_MOVE_DEFERRED, #elif defined(CONFIG_ARM64) .irq_eoi = irq_chip_eoi_parent, #endif diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index 46d3afe1d308..665f35f9d826 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -1715,6 +1715,7 @@ static const struct of_device_id mvebu_pcie_of_match_table[] = { { .compatible = "marvell,kirkwood-pcie", }, {}, }; +MODULE_DEVICE_TABLE(of, mvebu_pcie_of_match_table); static const struct dev_pm_ops mvebu_pcie_pm_ops = { NOIRQ_SYSTEM_SLEEP_PM_OPS(mvebu_pcie_suspend, mvebu_pcie_resume) diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c index fefab2758a06..a7e51bc1c2fe 100644 --- a/drivers/pci/controller/pcie-apple.c +++ b/drivers/pci/controller/pcie-apple.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include @@ -667,12 +666,16 @@ static struct apple_pcie_port *apple_pcie_get_port(struct pci_dev *pdev) return NULL; } -static int apple_pcie_add_device(struct apple_pcie_port *port, - struct pci_dev *pdev) +static int apple_pcie_enable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev) { u32 sid, rid = pci_dev_id(pdev); + struct apple_pcie_port *port; int idx, err; + port = apple_pcie_get_port(pdev); + if (!port) + return 0; + dev_dbg(&pdev->dev, "added to bus %s, index %d\n", pci_name(pdev->bus->self), port->idx); @@ -698,12 +701,16 @@ static int apple_pcie_add_device(struct apple_pcie_port *port, return idx >= 0 ? 0 : -ENOSPC; } -static void apple_pcie_release_device(struct apple_pcie_port *port, - struct pci_dev *pdev) +static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev) { + struct apple_pcie_port *port; u32 rid = pci_dev_id(pdev); int idx; + port = apple_pcie_get_port(pdev); + if (!port) + return; + mutex_lock(&port->pcie->lock); for_each_set_bit(idx, port->sid_map, port->sid_map_sz) { @@ -721,45 +728,6 @@ static void apple_pcie_release_device(struct apple_pcie_port *port, mutex_unlock(&port->pcie->lock); } -static int apple_pcie_bus_notifier(struct notifier_block *nb, - unsigned long action, - void *data) -{ - struct device *dev = data; - struct pci_dev *pdev = to_pci_dev(dev); - struct apple_pcie_port *port; - int err; - - /* - * This is a bit ugly. We assume that if we get notified for - * any PCI device, we must be in charge of it, and that there - * is no other PCI controller in the whole system. It probably - * holds for now, but who knows for how long? - */ - port = apple_pcie_get_port(pdev); - if (!port) - return NOTIFY_DONE; - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - err = apple_pcie_add_device(port, pdev); - if (err) - return notifier_from_errno(err); - break; - case BUS_NOTIFY_DEL_DEVICE: - apple_pcie_release_device(port, pdev); - break; - default: - return NOTIFY_DONE; - } - - return NOTIFY_OK; -} - -static struct notifier_block apple_pcie_nb = { - .notifier_call = apple_pcie_bus_notifier, -}; - static int apple_pcie_init(struct pci_config_window *cfg) { struct device *dev = cfg->parent; @@ -799,23 +767,10 @@ static int apple_pcie_init(struct pci_config_window *cfg) return 0; } -static int apple_pcie_probe(struct platform_device *pdev) -{ - int ret; - - ret = bus_register_notifier(&pci_bus_type, &apple_pcie_nb); - if (ret) - return ret; - - ret = pci_host_common_probe(pdev); - if (ret) - bus_unregister_notifier(&pci_bus_type, &apple_pcie_nb); - - return ret; -} - static const struct pci_ecam_ops apple_pcie_cfg_ecam_ops = { .init = apple_pcie_init, + .enable_device = apple_pcie_enable_device, + .disable_device = apple_pcie_disable_device, .pci_ops = { .map_bus = pci_ecam_map_bus, .read = pci_generic_config_read, @@ -830,7 +785,7 @@ static const struct of_device_id apple_pcie_of_match[] = { MODULE_DEVICE_TABLE(of, apple_pcie_of_match); static struct platform_driver apple_pcie_driver = { - .probe = apple_pcie_probe, + .probe = pci_host_common_probe, .driver = { .name = "pcie-apple", .of_match_table = apple_pcie_of_match, diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c index be52e3a123ab..aa24ac9aaecc 100644 --- a/drivers/pci/controller/pcie-mediatek-gen3.c +++ b/drivers/pci/controller/pcie-mediatek-gen3.c @@ -125,6 +125,8 @@ #define MAX_NUM_PHY_RESETS 3 +#define PCIE_MTK_RESET_TIME_US 10 + /* Time in ms needed to complete PCIe reset on EN7581 SoC */ #define PCIE_EN7581_RESET_TIME_MS 100 @@ -133,10 +135,18 @@ struct mtk_gen3_pcie; #define PCIE_CONF_LINK2_CTL_STS (PCIE_CFG_OFFSET_ADDR + 0xb0) #define PCIE_CONF_LINK2_LCR2_LINK_SPEED GENMASK(3, 0) +enum mtk_gen3_pcie_flags { + SKIP_PCIE_RSTB = BIT(0), /* Skip PERST# assertion during device + * probing or suspend/resume phase to + * avoid hw bugs/issues. + */ +}; + /** * struct mtk_gen3_pcie_pdata - differentiate between host generations * @power_up: pcie power_up callback * @phy_resets: phy reset lines SoC data. + * @flags: pcie device flags. */ struct mtk_gen3_pcie_pdata { int (*power_up)(struct mtk_gen3_pcie *pcie); @@ -144,6 +154,7 @@ struct mtk_gen3_pcie_pdata { const char *id[MAX_NUM_PHY_RESETS]; int num_resets; } phy_resets; + u32 flags; }; /** @@ -438,22 +449,33 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie) val |= PCIE_DISABLE_DVFSRC_VLT_REQ; writel_relaxed(val, pcie->base + PCIE_MISC_CTRL_REG); - /* Assert all reset signals */ - val = readl_relaxed(pcie->base + PCIE_RST_CTRL_REG); - val |= PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | PCIE_PE_RSTB; - writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); - /* - * Described in PCIe CEM specification sections 2.2 (PERST# Signal) - * and 2.2.1 (Initial Power-Up (G3 to S0)). - * The deassertion of PERST# should be delayed 100ms (TPVPERL) - * for the power and clock to become stable. + * Airoha EN7581 has a hw bug asserting/releasing PCIE_PE_RSTB signal + * causing occasional PCIe link down. In order to overcome the issue, + * PCIE_RSTB signals are not asserted/released at this stage and the + * PCIe block is reset using en7523_reset_assert() and + * en7581_pci_enable(). */ - msleep(100); + if (!(pcie->soc->flags & SKIP_PCIE_RSTB)) { + /* Assert all reset signals */ + val = readl_relaxed(pcie->base + PCIE_RST_CTRL_REG); + val |= PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | + PCIE_PE_RSTB; + writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); - /* De-assert reset signals */ - val &= ~(PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | PCIE_PE_RSTB); - writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + /* + * Described in PCIe CEM specification revision 6.0. + * + * The deassertion of PERST# should be delayed 100ms (TPVPERL) + * for the power and clock to become stable. + */ + msleep(PCIE_T_PVPERL_MS); + + /* De-assert reset signals */ + val &= ~(PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | + PCIE_PE_RSTB); + writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + } /* Check if the link is up or not */ err = readl_poll_timeout(pcie->base + PCIE_LINK_STATUS_REG, val, @@ -913,11 +935,20 @@ static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie) u32 val; /* - * Wait for the time needed to complete the bulk assert in - * mtk_pcie_setup for EN7581 SoC. + * The controller may have been left out of reset by the bootloader + * so make sure that we get a clean start by asserting resets here. */ - mdelay(PCIE_EN7581_RESET_TIME_MS); + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + reset_control_assert(pcie->mac_reset); + /* Wait for the time needed to complete the reset lines assert. */ + msleep(PCIE_EN7581_RESET_TIME_MS); + + /* + * Unlike the other MediaTek Gen3 controllers, the Airoha EN7581 + * requires PHY initialization and power-on before PHY reset deassert. + */ err = phy_init(pcie->phy); if (err) { dev_err(dev, "failed to initialize PHY\n"); @@ -940,17 +971,11 @@ static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie) * Wait for the time needed to complete the bulk de-assert above. * This time is specific for EN7581 SoC. */ - mdelay(PCIE_EN7581_RESET_TIME_MS); + msleep(PCIE_EN7581_RESET_TIME_MS); pm_runtime_enable(dev); pm_runtime_get_sync(dev); - err = clk_bulk_prepare(pcie->num_clks, pcie->clks); - if (err) { - dev_err(dev, "failed to prepare clock\n"); - goto err_clk_prepare; - } - val = FIELD_PREP(PCIE_VAL_LN0_DOWNSTREAM, 0x47) | FIELD_PREP(PCIE_VAL_LN1_DOWNSTREAM, 0x47) | FIELD_PREP(PCIE_VAL_LN0_UPSTREAM, 0x41) | @@ -963,17 +988,22 @@ static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie) FIELD_PREP(PCIE_K_FINETUNE_MAX, 0xf); writel_relaxed(val, pcie->base + PCIE_PIPE4_PIE8_REG); - err = clk_bulk_enable(pcie->num_clks, pcie->clks); + err = clk_bulk_prepare_enable(pcie->num_clks, pcie->clks); if (err) { dev_err(dev, "failed to prepare clock\n"); - goto err_clk_enable; + goto err_clk_prepare_enable; } + /* + * Airoha EN7581 performs PCIe reset via clk callbacks since it has a + * hw issue with PCIE_PE_RSTB signal. Add wait for the time needed to + * complete the PCIe reset. + */ + msleep(PCIE_T_PVPERL_MS); + return 0; -err_clk_enable: - clk_bulk_unprepare(pcie->num_clks, pcie->clks); -err_clk_prepare: +err_clk_prepare_enable: pm_runtime_put_sync(dev); pm_runtime_disable(dev); reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); @@ -990,6 +1020,15 @@ static int mtk_pcie_power_up(struct mtk_gen3_pcie *pcie) struct device *dev = pcie->dev; int err; + /* + * The controller may have been left out of reset by the bootloader + * so make sure that we get a clean start by asserting resets here. + */ + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + reset_control_assert(pcie->mac_reset); + usleep_range(PCIE_MTK_RESET_TIME_US, 2 * PCIE_MTK_RESET_TIME_US); + /* PHY power on and enable pipe clock */ err = reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); if (err) { @@ -1074,14 +1113,6 @@ static int mtk_pcie_setup(struct mtk_gen3_pcie *pcie) * counter since the bulk is shared. */ reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); - /* - * The controller may have been left out of reset by the bootloader - * so make sure that we get a clean start by asserting resets here. - */ - reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); - - reset_control_assert(pcie->mac_reset); - usleep_range(10, 20); /* Don't touch the hardware registers before power up */ err = pcie->soc->power_up(pcie); @@ -1231,10 +1262,12 @@ static int mtk_pcie_suspend_noirq(struct device *dev) return err; } - /* Pull down the PERST# pin */ - val = readl_relaxed(pcie->base + PCIE_RST_CTRL_REG); - val |= PCIE_PE_RSTB; - writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + if (!(pcie->soc->flags & SKIP_PCIE_RSTB)) { + /* Assert the PERST# pin */ + val = readl_relaxed(pcie->base + PCIE_RST_CTRL_REG); + val |= PCIE_PE_RSTB; + writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + } dev_dbg(pcie->dev, "entered L2 states successfully"); @@ -1285,6 +1318,7 @@ static const struct mtk_gen3_pcie_pdata mtk_pcie_soc_en7581 = { .id[2] = "phy-lane2", .num_resets = 3, }, + .flags = SKIP_PCIE_RSTB, }; static const struct of_device_id mtk_pcie_of_match[] = { @@ -1301,6 +1335,7 @@ static struct platform_driver mtk_pcie_driver = { .name = "mtk-pcie-gen3", .of_match_table = mtk_pcie_of_match, .pm = &mtk_pcie_pm_ops, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, }; diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c index 047e2cef5afc..c5e0d025bc43 100644 --- a/drivers/pci/controller/pcie-rcar-ep.c +++ b/drivers/pci/controller/pcie-rcar-ep.c @@ -107,7 +107,7 @@ static int rcar_pcie_parse_outbound_ranges(struct rcar_pcie_endpoint *ep, } if (!devm_request_mem_region(&pdev->dev, res->start, resource_size(res), - outbound_name)) { + res->name)) { dev_err(pcie->dev, "Cannot request memory region %s.\n", outbound_name); return -EIO; diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 1064b7b06cef..85ea36df2f59 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -40,6 +40,10 @@ * @irq_pci_fn: the latest PCI function that has updated the mapping of * the MSI/INTX IRQ dedicated outbound region. * @irq_pending: bitmask of asserted INTX IRQs. + * @perst_irq: IRQ used for the PERST# signal. + * @perst_asserted: True if the PERST# signal was asserted. + * @link_up: True if the PCI link is up. + * @link_training: Work item to execute PCI link training. */ struct rockchip_pcie_ep { struct rockchip_pcie rockchip; @@ -784,6 +788,7 @@ static int rockchip_pcie_ep_init_ob_mem(struct rockchip_pcie_ep *ep) SZ_1M); if (!ep->irq_cpu_addr) { dev_err(dev, "failed to reserve memory space for MSI\n"); + err = -ENOMEM; goto err_epc_mem_exit; } diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c index b9ade7632e11..0f88da378805 100644 --- a/drivers/pci/controller/pcie-rockchip.c +++ b/drivers/pci/controller/pcie-rockchip.c @@ -30,7 +30,7 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) struct platform_device *pdev = to_platform_device(dev); struct device_node *node = dev->of_node; struct resource *regs; - int err; + int err, i; if (rockchip->is_rc) { regs = platform_get_resource_byname(pdev, @@ -69,55 +69,23 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) if (rockchip->link_gen < 0 || rockchip->link_gen > 2) rockchip->link_gen = 2; - rockchip->core_rst = devm_reset_control_get_exclusive(dev, "core"); - if (IS_ERR(rockchip->core_rst)) { - if (PTR_ERR(rockchip->core_rst) != -EPROBE_DEFER) - dev_err(dev, "missing core reset property in node\n"); - return PTR_ERR(rockchip->core_rst); - } + for (i = 0; i < ROCKCHIP_NUM_PM_RSTS; i++) + rockchip->pm_rsts[i].id = rockchip_pci_pm_rsts[i]; - rockchip->mgmt_rst = devm_reset_control_get_exclusive(dev, "mgmt"); - if (IS_ERR(rockchip->mgmt_rst)) { - if (PTR_ERR(rockchip->mgmt_rst) != -EPROBE_DEFER) - dev_err(dev, "missing mgmt reset property in node\n"); - return PTR_ERR(rockchip->mgmt_rst); - } + err = devm_reset_control_bulk_get_exclusive(dev, + ROCKCHIP_NUM_PM_RSTS, + rockchip->pm_rsts); + if (err) + return dev_err_probe(dev, err, "Cannot get the PM reset\n"); - rockchip->mgmt_sticky_rst = devm_reset_control_get_exclusive(dev, - "mgmt-sticky"); - if (IS_ERR(rockchip->mgmt_sticky_rst)) { - if (PTR_ERR(rockchip->mgmt_sticky_rst) != -EPROBE_DEFER) - dev_err(dev, "missing mgmt-sticky reset property in node\n"); - return PTR_ERR(rockchip->mgmt_sticky_rst); - } + for (i = 0; i < ROCKCHIP_NUM_CORE_RSTS; i++) + rockchip->core_rsts[i].id = rockchip_pci_core_rsts[i]; - rockchip->pipe_rst = devm_reset_control_get_exclusive(dev, "pipe"); - if (IS_ERR(rockchip->pipe_rst)) { - if (PTR_ERR(rockchip->pipe_rst) != -EPROBE_DEFER) - dev_err(dev, "missing pipe reset property in node\n"); - return PTR_ERR(rockchip->pipe_rst); - } - - rockchip->pm_rst = devm_reset_control_get_exclusive(dev, "pm"); - if (IS_ERR(rockchip->pm_rst)) { - if (PTR_ERR(rockchip->pm_rst) != -EPROBE_DEFER) - dev_err(dev, "missing pm reset property in node\n"); - return PTR_ERR(rockchip->pm_rst); - } - - rockchip->pclk_rst = devm_reset_control_get_exclusive(dev, "pclk"); - if (IS_ERR(rockchip->pclk_rst)) { - if (PTR_ERR(rockchip->pclk_rst) != -EPROBE_DEFER) - dev_err(dev, "missing pclk reset property in node\n"); - return PTR_ERR(rockchip->pclk_rst); - } - - rockchip->aclk_rst = devm_reset_control_get_exclusive(dev, "aclk"); - if (IS_ERR(rockchip->aclk_rst)) { - if (PTR_ERR(rockchip->aclk_rst) != -EPROBE_DEFER) - dev_err(dev, "missing aclk reset property in node\n"); - return PTR_ERR(rockchip->aclk_rst); - } + err = devm_reset_control_bulk_get_exclusive(dev, + ROCKCHIP_NUM_CORE_RSTS, + rockchip->core_rsts); + if (err) + return dev_err_probe(dev, err, "Cannot get the Core resets\n"); if (rockchip->is_rc) rockchip->perst_gpio = devm_gpiod_get_optional(dev, "ep", @@ -129,29 +97,10 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) return dev_err_probe(dev, PTR_ERR(rockchip->perst_gpio), "failed to get PERST# GPIO\n"); - rockchip->aclk_pcie = devm_clk_get(dev, "aclk"); - if (IS_ERR(rockchip->aclk_pcie)) { - dev_err(dev, "aclk clock not found\n"); - return PTR_ERR(rockchip->aclk_pcie); - } - - rockchip->aclk_perf_pcie = devm_clk_get(dev, "aclk-perf"); - if (IS_ERR(rockchip->aclk_perf_pcie)) { - dev_err(dev, "aclk_perf clock not found\n"); - return PTR_ERR(rockchip->aclk_perf_pcie); - } - - rockchip->hclk_pcie = devm_clk_get(dev, "hclk"); - if (IS_ERR(rockchip->hclk_pcie)) { - dev_err(dev, "hclk clock not found\n"); - return PTR_ERR(rockchip->hclk_pcie); - } - - rockchip->clk_pcie_pm = devm_clk_get(dev, "pm"); - if (IS_ERR(rockchip->clk_pcie_pm)) { - dev_err(dev, "pm clock not found\n"); - return PTR_ERR(rockchip->clk_pcie_pm); - } + rockchip->num_clks = devm_clk_bulk_get_all(dev, &rockchip->clks); + if (rockchip->num_clks < 0) + return dev_err_probe(dev, rockchip->num_clks, + "failed to get clocks\n"); return 0; } @@ -169,23 +118,10 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) int err, i; u32 regs; - err = reset_control_assert(rockchip->aclk_rst); - if (err) { - dev_err(dev, "assert aclk_rst err %d\n", err); - return err; - } - - err = reset_control_assert(rockchip->pclk_rst); - if (err) { - dev_err(dev, "assert pclk_rst err %d\n", err); - return err; - } - - err = reset_control_assert(rockchip->pm_rst); - if (err) { - dev_err(dev, "assert pm_rst err %d\n", err); - return err; - } + err = reset_control_bulk_assert(ROCKCHIP_NUM_PM_RSTS, + rockchip->pm_rsts); + if (err) + return dev_err_probe(dev, err, "Couldn't assert PM resets\n"); for (i = 0; i < MAX_LANE_NUM; i++) { err = phy_init(rockchip->phys[i]); @@ -195,47 +131,19 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) } } - err = reset_control_assert(rockchip->core_rst); + err = reset_control_bulk_assert(ROCKCHIP_NUM_CORE_RSTS, + rockchip->core_rsts); if (err) { - dev_err(dev, "assert core_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_assert(rockchip->mgmt_rst); - if (err) { - dev_err(dev, "assert mgmt_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_assert(rockchip->mgmt_sticky_rst); - if (err) { - dev_err(dev, "assert mgmt_sticky_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_assert(rockchip->pipe_rst); - if (err) { - dev_err(dev, "assert pipe_rst err %d\n", err); + dev_err_probe(dev, err, "Couldn't assert Core resets\n"); goto err_exit_phy; } udelay(10); - err = reset_control_deassert(rockchip->pm_rst); + err = reset_control_bulk_deassert(ROCKCHIP_NUM_PM_RSTS, + rockchip->pm_rsts); if (err) { - dev_err(dev, "deassert pm_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_deassert(rockchip->aclk_rst); - if (err) { - dev_err(dev, "deassert aclk_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_deassert(rockchip->pclk_rst); - if (err) { - dev_err(dev, "deassert pclk_rst err %d\n", err); + dev_err(dev, "Couldn't deassert PM resets %d\n", err); goto err_exit_phy; } @@ -275,31 +183,10 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) goto err_power_off_phy; } - /* - * Please don't reorder the deassert sequence of the following - * four reset pins. - */ - err = reset_control_deassert(rockchip->mgmt_sticky_rst); + err = reset_control_bulk_deassert(ROCKCHIP_NUM_CORE_RSTS, + rockchip->core_rsts); if (err) { - dev_err(dev, "deassert mgmt_sticky_rst err %d\n", err); - goto err_power_off_phy; - } - - err = reset_control_deassert(rockchip->core_rst); - if (err) { - dev_err(dev, "deassert core_rst err %d\n", err); - goto err_power_off_phy; - } - - err = reset_control_deassert(rockchip->mgmt_rst); - if (err) { - dev_err(dev, "deassert mgmt_rst err %d\n", err); - goto err_power_off_phy; - } - - err = reset_control_deassert(rockchip->pipe_rst); - if (err) { - dev_err(dev, "deassert pipe_rst err %d\n", err); + dev_err(dev, "Couldn't deassert Core reset %d\n", err); goto err_power_off_phy; } @@ -375,50 +262,18 @@ int rockchip_pcie_enable_clocks(struct rockchip_pcie *rockchip) struct device *dev = rockchip->dev; int err; - err = clk_prepare_enable(rockchip->aclk_pcie); - if (err) { - dev_err(dev, "unable to enable aclk_pcie clock\n"); - return err; - } - - err = clk_prepare_enable(rockchip->aclk_perf_pcie); - if (err) { - dev_err(dev, "unable to enable aclk_perf_pcie clock\n"); - goto err_aclk_perf_pcie; - } - - err = clk_prepare_enable(rockchip->hclk_pcie); - if (err) { - dev_err(dev, "unable to enable hclk_pcie clock\n"); - goto err_hclk_pcie; - } - - err = clk_prepare_enable(rockchip->clk_pcie_pm); - if (err) { - dev_err(dev, "unable to enable clk_pcie_pm clock\n"); - goto err_clk_pcie_pm; - } + err = clk_bulk_prepare_enable(rockchip->num_clks, rockchip->clks); + if (err) + return dev_err_probe(dev, err, "failed to enable clocks\n"); return 0; - -err_clk_pcie_pm: - clk_disable_unprepare(rockchip->hclk_pcie); -err_hclk_pcie: - clk_disable_unprepare(rockchip->aclk_perf_pcie); -err_aclk_perf_pcie: - clk_disable_unprepare(rockchip->aclk_pcie); - return err; } EXPORT_SYMBOL_GPL(rockchip_pcie_enable_clocks); -void rockchip_pcie_disable_clocks(void *data) +void rockchip_pcie_disable_clocks(struct rockchip_pcie *rockchip) { - struct rockchip_pcie *rockchip = data; - clk_disable_unprepare(rockchip->clk_pcie_pm); - clk_disable_unprepare(rockchip->hclk_pcie); - clk_disable_unprepare(rockchip->aclk_perf_pcie); - clk_disable_unprepare(rockchip->aclk_pcie); + clk_bulk_disable_unprepare(rockchip->num_clks, rockchip->clks); } EXPORT_SYMBOL_GPL(rockchip_pcie_disable_clocks); diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index a51b087ce878..11def598534b 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -11,9 +11,11 @@ #ifndef _PCIE_ROCKCHIP_H #define _PCIE_ROCKCHIP_H +#include #include #include #include +#include /* * The upper 16 bits of PCIE_CLIENT_CONFIG are a write mask for the lower 16 @@ -309,22 +311,31 @@ (((c) << ((b) * 8 + 5)) & \ ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)) +#define ROCKCHIP_NUM_PM_RSTS ARRAY_SIZE(rockchip_pci_pm_rsts) +#define ROCKCHIP_NUM_CORE_RSTS ARRAY_SIZE(rockchip_pci_core_rsts) + +static const char * const rockchip_pci_pm_rsts[] = { + "pm", + "pclk", + "aclk", +}; + +static const char * const rockchip_pci_core_rsts[] = { + "mgmt-sticky", + "core", + "mgmt", + "pipe", +}; + struct rockchip_pcie { void __iomem *reg_base; /* DT axi-base */ void __iomem *apb_base; /* DT apb-base */ bool legacy_phy; struct phy *phys[MAX_LANE_NUM]; - struct reset_control *core_rst; - struct reset_control *mgmt_rst; - struct reset_control *mgmt_sticky_rst; - struct reset_control *pipe_rst; - struct reset_control *pm_rst; - struct reset_control *aclk_rst; - struct reset_control *pclk_rst; - struct clk *aclk_pcie; - struct clk *aclk_perf_pcie; - struct clk *hclk_pcie; - struct clk *clk_pcie_pm; + struct reset_control_bulk_data pm_rsts[ROCKCHIP_NUM_PM_RSTS]; + struct reset_control_bulk_data core_rsts[ROCKCHIP_NUM_CORE_RSTS]; + struct clk_bulk_data *clks; + int num_clks; struct regulator *vpcie12v; /* 12V power supply */ struct regulator *vpcie3v3; /* 3.3V power supply */ struct regulator *vpcie1v8; /* 1.8V power supply */ @@ -358,7 +369,7 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip); int rockchip_pcie_get_phys(struct rockchip_pcie *rockchip); void rockchip_pcie_deinit_phys(struct rockchip_pcie *rockchip); int rockchip_pcie_enable_clocks(struct rockchip_pcie *rockchip); -void rockchip_pcie_disable_clocks(void *data); +void rockchip_pcie_disable_clocks(struct rockchip_pcie *rockchip); void rockchip_pcie_cfg_configuration_accesses( struct rockchip_pcie *rockchip, u32 type); diff --git a/drivers/pci/controller/pcie-xilinx-cpm.c b/drivers/pci/controller/pcie-xilinx-cpm.c index a0f5e1d67b04..81e8bfae53d0 100644 --- a/drivers/pci/controller/pcie-xilinx-cpm.c +++ b/drivers/pci/controller/pcie-xilinx-cpm.c @@ -30,11 +30,14 @@ #define XILINX_CPM_PCIE_REG_IDRN_MASK 0x00000E3C #define XILINX_CPM_PCIE_MISC_IR_STATUS 0x00000340 #define XILINX_CPM_PCIE_MISC_IR_ENABLE 0x00000348 -#define XILINX_CPM_PCIE_MISC_IR_LOCAL BIT(1) +#define XILINX_CPM_PCIE0_MISC_IR_LOCAL BIT(1) +#define XILINX_CPM_PCIE1_MISC_IR_LOCAL BIT(2) -#define XILINX_CPM_PCIE_IR_STATUS 0x000002A0 -#define XILINX_CPM_PCIE_IR_ENABLE 0x000002A8 -#define XILINX_CPM_PCIE_IR_LOCAL BIT(0) +#define XILINX_CPM_PCIE0_IR_STATUS 0x000002A0 +#define XILINX_CPM_PCIE1_IR_STATUS 0x000002B4 +#define XILINX_CPM_PCIE0_IR_ENABLE 0x000002A8 +#define XILINX_CPM_PCIE1_IR_ENABLE 0x000002BC +#define XILINX_CPM_PCIE_IR_LOCAL BIT(0) #define IMR(x) BIT(XILINX_PCIE_INTR_ ##x) @@ -80,14 +83,21 @@ enum xilinx_cpm_version { CPM, CPM5, + CPM5_HOST1, }; /** * struct xilinx_cpm_variant - CPM variant information * @version: CPM version + * @ir_status: Offset for the error interrupt status register + * @ir_enable: Offset for the CPM5 local error interrupt enable register + * @ir_misc_value: A bitmask for the miscellaneous interrupt status */ struct xilinx_cpm_variant { enum xilinx_cpm_version version; + u32 ir_status; + u32 ir_enable; + u32 ir_misc_value; }; /** @@ -269,6 +279,7 @@ static void xilinx_cpm_pcie_event_flow(struct irq_desc *desc) { struct xilinx_cpm_pcie *port = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); + const struct xilinx_cpm_variant *variant = port->variant; unsigned long val; int i; @@ -279,11 +290,11 @@ static void xilinx_cpm_pcie_event_flow(struct irq_desc *desc) generic_handle_domain_irq(port->cpm_domain, i); pcie_write(port, val, XILINX_CPM_PCIE_REG_IDR); - if (port->variant->version == CPM5) { - val = readl_relaxed(port->cpm_base + XILINX_CPM_PCIE_IR_STATUS); + if (variant->ir_status) { + val = readl_relaxed(port->cpm_base + variant->ir_status); if (val) writel_relaxed(val, port->cpm_base + - XILINX_CPM_PCIE_IR_STATUS); + variant->ir_status); } /* @@ -465,6 +476,8 @@ static int xilinx_cpm_setup_irq(struct xilinx_cpm_pcie *port) */ static void xilinx_cpm_pcie_init_port(struct xilinx_cpm_pcie *port) { + const struct xilinx_cpm_variant *variant = port->variant; + if (cpm_pcie_link_up(port)) dev_info(port->dev, "PCIe Link is UP\n"); else @@ -483,15 +496,15 @@ static void xilinx_cpm_pcie_init_port(struct xilinx_cpm_pcie *port) * XILINX_CPM_PCIE_MISC_IR_ENABLE register is mapped to * CPM SLCR block. */ - writel(XILINX_CPM_PCIE_MISC_IR_LOCAL, + writel(variant->ir_misc_value, port->cpm_base + XILINX_CPM_PCIE_MISC_IR_ENABLE); - if (port->variant->version == CPM5) { + if (variant->ir_enable) { writel(XILINX_CPM_PCIE_IR_LOCAL, - port->cpm_base + XILINX_CPM_PCIE_IR_ENABLE); + port->cpm_base + variant->ir_enable); } - /* Enable the Bridge enable bit */ + /* Set Bridge enable bit */ pcie_write(port, pcie_read(port, XILINX_CPM_PCIE_REG_RPSC) | XILINX_CPM_PCIE_REG_RPSC_BEN, XILINX_CPM_PCIE_REG_RPSC); @@ -609,10 +622,21 @@ err_parse_dt: static const struct xilinx_cpm_variant cpm_host = { .version = CPM, + .ir_misc_value = XILINX_CPM_PCIE0_MISC_IR_LOCAL, }; static const struct xilinx_cpm_variant cpm5_host = { .version = CPM5, + .ir_misc_value = XILINX_CPM_PCIE0_MISC_IR_LOCAL, + .ir_status = XILINX_CPM_PCIE0_IR_STATUS, + .ir_enable = XILINX_CPM_PCIE0_IR_ENABLE, +}; + +static const struct xilinx_cpm_variant cpm5_host1 = { + .version = CPM5_HOST1, + .ir_misc_value = XILINX_CPM_PCIE1_MISC_IR_LOCAL, + .ir_status = XILINX_CPM_PCIE1_IR_STATUS, + .ir_enable = XILINX_CPM_PCIE1_IR_ENABLE, }; static const struct of_device_id xilinx_cpm_pcie_of_match[] = { @@ -624,6 +648,10 @@ static const struct of_device_id xilinx_cpm_pcie_of_match[] = { .compatible = "xlnx,versal-cpm5-host", .data = &cpm5_host, }, + { + .compatible = "xlnx,versal-cpm5-host1", + .data = &cpm5_host1, + }, {} }; diff --git a/drivers/pci/controller/plda/pcie-microchip-host.c b/drivers/pci/controller/plda/pcie-microchip-host.c index 6630cacef301..3fdfffdf0270 100644 --- a/drivers/pci/controller/plda/pcie-microchip-host.c +++ b/drivers/pci/controller/plda/pcie-microchip-host.c @@ -7,20 +7,27 @@ * Author: Daire McNamara */ +#include +#include #include #include #include #include +#include #include #include #include #include #include #include +#include #include "../../pci.h" #include "pcie-plda.h" +#define MC_MAX_NUM_INBOUND_WINDOWS 8 +#define MPFS_NC_BOUNCE_ADDR 0x80000000 + /* PCIe Bridge Phy and Controller Phy offsets */ #define MC_PCIE1_BRIDGE_ADDR 0x00008000u #define MC_PCIE1_CTRL_ADDR 0x0000a000u @@ -607,6 +614,91 @@ static void mc_disable_interrupts(struct mc_pcie *port) writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_HOST); } +static void mc_pcie_setup_inbound_atr(struct mc_pcie *port, int window_index, + u64 axi_addr, u64 pcie_addr, u64 size) +{ + u32 table_offset = window_index * ATR_ENTRY_SIZE; + void __iomem *table_addr = port->bridge_base_addr + table_offset; + u32 atr_sz; + u32 val; + + atr_sz = ilog2(size) - 1; + + val = ALIGN_DOWN(lower_32_bits(pcie_addr), SZ_4K); + val |= FIELD_PREP(ATR_SIZE_MASK, atr_sz); + val |= ATR_IMPL_ENABLE; + + writel(val, table_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM); + + writel(upper_32_bits(pcie_addr), table_addr + ATR0_PCIE_WIN0_SRC_ADDR); + + writel(lower_32_bits(axi_addr), table_addr + ATR0_PCIE_WIN0_TRSL_ADDR_LSB); + writel(upper_32_bits(axi_addr), table_addr + ATR0_PCIE_WIN0_TRSL_ADDR_UDW); + + writel(TRSL_ID_AXI4_MASTER_0, table_addr + ATR0_PCIE_WIN0_TRSL_PARAM); +} + +static int mc_pcie_setup_inbound_ranges(struct platform_device *pdev, + struct mc_pcie *port) +{ + struct device *dev = &pdev->dev; + struct device_node *dn = dev->of_node; + struct of_range_parser parser; + struct of_range range; + int atr_index = 0; + + /* + * MPFS PCIe Root Port is 32-bit only, behind a Fabric Interface + * Controller FPGA logic block which contains the AXI-S interface. + * + * From the point of view of the PCIe Root Port, there are only two + * supported Root Port configurations: + * + * Configuration 1: for use with fully coherent designs; supports a + * window from 0x0 (CPU space) to specified PCIe space. + * + * Configuration 2: for use with non-coherent designs; supports two + * 1 GB windows to CPU space; one mapping CPU space 0 to PCIe space + * 0x80000000 and a second mapping CPU space 0x40000000 to PCIe + * space 0xc0000000. This cfg needs two windows because of how the + * MSI space is allocated in the AXI-S range on MPFS. + * + * The FIC interface outside the PCIe block *must* complete the + * inbound address translation as per MCHP MPFS FPGA design + * guidelines. + */ + if (device_property_read_bool(dev, "dma-noncoherent")) { + /* + * Always need same two tables in this case. Need two tables + * due to hardware interactions between address and size. + */ + mc_pcie_setup_inbound_atr(port, 0, 0, + MPFS_NC_BOUNCE_ADDR, SZ_1G); + mc_pcie_setup_inbound_atr(port, 1, SZ_1G, + MPFS_NC_BOUNCE_ADDR + SZ_1G, SZ_1G); + } else { + /* Find any DMA ranges */ + if (of_pci_dma_range_parser_init(&parser, dn)) { + /* No DMA range property - setup default */ + mc_pcie_setup_inbound_atr(port, 0, 0, 0, SZ_4G); + return 0; + } + + for_each_of_range(&parser, &range) { + if (atr_index >= MC_MAX_NUM_INBOUND_WINDOWS) { + dev_err(dev, "too many inbound ranges; %d available tables\n", + MC_MAX_NUM_INBOUND_WINDOWS); + return -EINVAL; + } + mc_pcie_setup_inbound_atr(port, atr_index, 0, + range.pci_addr, range.size); + atr_index++; + } + } + + return 0; +} + static int mc_platform_init(struct pci_config_window *cfg) { struct device *dev = cfg->parent; @@ -627,6 +719,10 @@ static int mc_platform_init(struct pci_config_window *cfg) if (ret) return ret; + ret = mc_pcie_setup_inbound_ranges(pdev, port); + if (ret) + return ret; + port->plda.event_ops = &mc_event_ops; port->plda.event_irq_chip = &mc_event_irq_chip; port->plda.events_bitmap = GENMASK(NUM_EVENTS - 1, 0); diff --git a/drivers/pci/controller/plda/pcie-plda-host.c b/drivers/pci/controller/plda/pcie-plda-host.c index 8533dc618d45..4153214ca410 100644 --- a/drivers/pci/controller/plda/pcie-plda-host.c +++ b/drivers/pci/controller/plda/pcie-plda-host.c @@ -8,11 +8,14 @@ * Author: Daire McNamara */ +#include +#include #include #include #include #include #include +#include #include "pcie-plda.h" @@ -502,8 +505,9 @@ void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index, writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + ATR0_AXI4_SLV0_TRSL_PARAM); - val = lower_32_bits(axi_addr) | (atr_sz << ATR_SIZE_SHIFT) | - ATR_IMPL_ENABLE; + val = ALIGN_DOWN(lower_32_bits(axi_addr), SZ_4K); + val |= FIELD_PREP(ATR_SIZE_MASK, atr_sz); + val |= ATR_IMPL_ENABLE; writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + ATR0_AXI4_SLV0_SRCADDR_PARAM); @@ -518,13 +522,20 @@ void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index, val = upper_32_bits(pci_addr); writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + ATR0_AXI4_SLV0_TRSL_ADDR_UDW); +} +EXPORT_SYMBOL_GPL(plda_pcie_setup_window); + +void plda_pcie_setup_inbound_address_translation(struct plda_pcie_rp *port) +{ + void __iomem *bridge_base_addr = port->bridge_addr; + u32 val; val = readl(bridge_base_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM); val |= (ATR0_PCIE_ATR_SIZE << ATR0_PCIE_ATR_SIZE_SHIFT); writel(val, bridge_base_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM); writel(0, bridge_base_addr + ATR0_PCIE_WIN0_SRC_ADDR); } -EXPORT_SYMBOL_GPL(plda_pcie_setup_window); +EXPORT_SYMBOL_GPL(plda_pcie_setup_inbound_address_translation); int plda_pcie_setup_iomems(struct pci_host_bridge *bridge, struct plda_pcie_rp *port) diff --git a/drivers/pci/controller/plda/pcie-plda.h b/drivers/pci/controller/plda/pcie-plda.h index 0e7dc0d8e5ba..61ece26065ea 100644 --- a/drivers/pci/controller/plda/pcie-plda.h +++ b/drivers/pci/controller/plda/pcie-plda.h @@ -89,14 +89,15 @@ /* PCIe AXI slave table init defines */ #define ATR0_AXI4_SLV0_SRCADDR_PARAM 0x800u -#define ATR_SIZE_SHIFT 1 -#define ATR_IMPL_ENABLE 1 +#define ATR_SIZE_MASK GENMASK(6, 1) +#define ATR_IMPL_ENABLE BIT(0) #define ATR0_AXI4_SLV0_SRC_ADDR 0x804u #define ATR0_AXI4_SLV0_TRSL_ADDR_LSB 0x808u #define ATR0_AXI4_SLV0_TRSL_ADDR_UDW 0x80cu #define ATR0_AXI4_SLV0_TRSL_PARAM 0x810u #define PCIE_TX_RX_INTERFACE 0x00000000u #define PCIE_CONFIG_INTERFACE 0x00000001u +#define TRSL_ID_AXI4_MASTER_0 0x00000004u #define CONFIG_SPACE_ADDR_OFFSET 0x1000u @@ -204,6 +205,7 @@ int plda_init_interrupts(struct platform_device *pdev, void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index, phys_addr_t axi_addr, phys_addr_t pci_addr, size_t size); +void plda_pcie_setup_inbound_address_translation(struct plda_pcie_rp *port); int plda_pcie_setup_iomems(struct pci_host_bridge *bridge, struct plda_pcie_rp *port); int plda_pcie_host_init(struct plda_pcie_rp *port, struct pci_ops *ops, diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index 3b59a86a764b..3431a7df3e0d 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -101,7 +101,7 @@ static inline void pcim_addr_devres_clear(struct pcim_addr_devres *res) * @bar: BAR the range is within * @offset: offset from the BAR's start address * @maxlen: length in bytes, beginning at @offset - * @name: name associated with the request + * @name: name of the driver requesting the resource * @req_flags: flags for the request, e.g., for kernel-exclusive requests * * Returns: 0 on success, a negative error code on failure. @@ -411,46 +411,20 @@ static inline bool mask_contains_bar(int mask, int bar) return mask & BIT(bar); } -/* - * This is a copy of pci_intx() used to bypass the problem of recursive - * function calls due to the hybrid nature of pci_intx(). - */ -static void __pcim_intx(struct pci_dev *pdev, int enable) -{ - u16 pci_command, new; - - pci_read_config_word(pdev, PCI_COMMAND, &pci_command); - - if (enable) - new = pci_command & ~PCI_COMMAND_INTX_DISABLE; - else - new = pci_command | PCI_COMMAND_INTX_DISABLE; - - if (new != pci_command) - pci_write_config_word(pdev, PCI_COMMAND, new); -} - static void pcim_intx_restore(struct device *dev, void *data) { struct pci_dev *pdev = to_pci_dev(dev); struct pcim_intx_devres *res = data; - __pcim_intx(pdev, res->orig_intx); + pci_intx(pdev, res->orig_intx); } -static struct pcim_intx_devres *get_or_create_intx_devres(struct device *dev) +static void save_orig_intx(struct pci_dev *pdev, struct pcim_intx_devres *res) { - struct pcim_intx_devres *res; + u16 pci_command; - res = devres_find(dev, pcim_intx_restore, NULL, NULL); - if (res) - return res; - - res = devres_alloc(pcim_intx_restore, sizeof(*res), GFP_KERNEL); - if (res) - devres_add(dev, res); - - return res; + pci_read_config_word(pdev, PCI_COMMAND, &pci_command); + res->orig_intx = !(pci_command & PCI_COMMAND_INTX_DISABLE); } /** @@ -466,16 +440,28 @@ static struct pcim_intx_devres *get_or_create_intx_devres(struct device *dev) int pcim_intx(struct pci_dev *pdev, int enable) { struct pcim_intx_devres *res; + struct device *dev = &pdev->dev; - res = get_or_create_intx_devres(&pdev->dev); - if (!res) - return -ENOMEM; + /* + * pcim_intx() must only restore the INTx value that existed before the + * driver was loaded, i.e., before it called pcim_intx() for the + * first time. + */ + res = devres_find(dev, pcim_intx_restore, NULL, NULL); + if (!res) { + res = devres_alloc(pcim_intx_restore, sizeof(*res), GFP_KERNEL); + if (!res) + return -ENOMEM; - res->orig_intx = !enable; - __pcim_intx(pdev, enable); + save_orig_intx(pdev, res); + devres_add(dev, res); + } + + pci_intx(pdev, enable); return 0; } +EXPORT_SYMBOL_GPL(pcim_intx); static void pcim_disable_device(void *pdev_raw) { @@ -723,7 +709,7 @@ EXPORT_SYMBOL(pcim_iounmap); * pcim_iomap_region - Request and iomap a PCI BAR * @pdev: PCI device to map IO resources for * @bar: Index of a BAR to map - * @name: Name associated with the request + * @name: Name of the driver requesting the resource * * Returns: __iomem pointer on success, an IOMEM_ERR_PTR on failure. * @@ -790,7 +776,7 @@ EXPORT_SYMBOL(pcim_iounmap_region); * pcim_iomap_regions - Request and iomap PCI BARs (DEPRECATED) * @pdev: PCI device to map IO resources for * @mask: Mask of BARs to request and iomap - * @name: Name associated with the requests + * @name: Name of the driver requesting the resources * * Returns: 0 on success, negative error code on failure. * @@ -855,9 +841,9 @@ static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name, /** * pcim_request_region - Request a PCI BAR - * @pdev: PCI device to requestion region for + * @pdev: PCI device to request region for * @bar: Index of BAR to request - * @name: Name associated with the request + * @name: Name of the driver requesting the resource * * Returns: 0 on success, a negative error code on failure. * @@ -874,9 +860,9 @@ EXPORT_SYMBOL(pcim_request_region); /** * pcim_request_region_exclusive - Request a PCI BAR exclusively - * @pdev: PCI device to requestion region for + * @pdev: PCI device to request region for * @bar: Index of BAR to request - * @name: Name associated with the request + * @name: Name of the driver requesting the resource * * Returns: 0 on success, a negative error code on failure. * @@ -932,7 +918,7 @@ static void pcim_release_all_regions(struct pci_dev *pdev) /** * pcim_request_all_regions - Request all regions * @pdev: PCI device to map IO resources for - * @name: name associated with the request + * @name: name of the driver requesting the resources * * Returns: 0 on success, negative error code on failure. * diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index ef6677f34116..b94e205ae10b 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -44,6 +44,8 @@ #define TIMER_RESOLUTION 1 +#define CAP_UNALIGNED_ACCESS BIT(0) + static struct workqueue_struct *kpcitest_workqueue; struct pci_epf_test { @@ -74,6 +76,7 @@ struct pci_epf_test_reg { u32 irq_type; u32 irq_number; u32 flags; + u32 caps; } __packed; static struct pci_epf_header test_header = { @@ -251,7 +254,7 @@ static int pci_epf_test_init_dma_chan(struct pci_epf_test *epf_test) fail_back_rx: dma_release_channel(epf_test->dma_chan_rx); - epf_test->dma_chan_tx = NULL; + epf_test->dma_chan_rx = NULL; fail_back_tx: dma_cap_zero(mask); @@ -328,8 +331,8 @@ static void pci_epf_test_copy(struct pci_epf_test *epf_test, void *copy_buf = NULL, *buf; if (reg->flags & FLAG_USE_DMA) { - if (epf_test->dma_private) { - dev_err(dev, "Cannot transfer data using DMA\n"); + if (!dma_has_cap(DMA_MEMCPY, epf_test->dma_chan_tx->device->cap_mask)) { + dev_err(dev, "DMA controller doesn't support MEMCPY\n"); ret = -EINVAL; goto set_status; } @@ -739,6 +742,20 @@ static void pci_epf_test_clear_bar(struct pci_epf *epf) } } +static void pci_epf_test_set_capabilities(struct pci_epf *epf) +{ + struct pci_epf_test *epf_test = epf_get_drvdata(epf); + enum pci_barno test_reg_bar = epf_test->test_reg_bar; + struct pci_epf_test_reg *reg = epf_test->reg[test_reg_bar]; + struct pci_epc *epc = epf->epc; + u32 caps = 0; + + if (epc->ops->align_addr) + caps |= CAP_UNALIGNED_ACCESS; + + reg->caps = cpu_to_le32(caps); +} + static int pci_epf_test_epc_init(struct pci_epf *epf) { struct pci_epf_test *epf_test = epf_get_drvdata(epf); @@ -763,6 +780,8 @@ static int pci_epf_test_epc_init(struct pci_epf *epf) } } + pci_epf_test_set_capabilities(epf); + ret = pci_epf_test_set_bar(epf); if (ret) return ret; diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index bed7c7d1fe3c..9e9ca5f8e8f8 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -60,26 +60,17 @@ struct pci_epc *pci_epc_get(const char *epc_name) int ret = -EINVAL; struct pci_epc *epc; struct device *dev; - struct class_dev_iter iter; - class_dev_iter_init(&iter, &pci_epc_class, NULL, NULL); - while ((dev = class_dev_iter_next(&iter))) { - if (strcmp(epc_name, dev_name(dev))) - continue; + dev = class_find_device_by_name(&pci_epc_class, epc_name); + if (!dev) + goto err; - epc = to_pci_epc(dev); - if (!try_module_get(epc->ops->owner)) { - ret = -EINVAL; - goto err; - } - - class_dev_iter_exit(&iter); - get_device(&epc->dev); + epc = to_pci_epc(dev); + if (try_module_get(epc->ops->owner)) return epc; - } err: - class_dev_iter_exit(&iter); + put_device(dev); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(pci_epc_get); @@ -609,10 +600,20 @@ EXPORT_SYMBOL_GPL(pci_epc_clear_bar); int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar) { - int ret; + const struct pci_epc_features *epc_features; + enum pci_barno bar = epf_bar->barno; int flags = epf_bar->flags; + int ret; - if (!pci_epc_function_is_valid(epc, func_no, vfunc_no)) + epc_features = pci_epc_get_features(epc, func_no, vfunc_no); + if (!epc_features) + return -EINVAL; + + if (epc_features->bar[bar].type == BAR_FIXED && + (epc_features->bar[bar].fixed_size != epf_bar->size)) + return -EINVAL; + + if (!is_power_of_2(epf_bar->size)) return -EINVAL; if ((epf_bar->barno == BAR_5 && flags & PCI_BASE_ADDRESS_MEM_TYPE_64) || @@ -942,7 +943,7 @@ void devm_pci_epc_destroy(struct device *dev, struct pci_epc *epc) { int r; - r = devres_destroy(dev, devm_pci_epc_release, devm_pci_epc_match, + r = devres_release(dev, devm_pci_epc_release, devm_pci_epc_match, epc); dev_WARN_ONCE(dev, r, "couldn't find PCI EPC resource\n"); } diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 8fa2797d4169..50bc2892a36c 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -202,6 +202,7 @@ void pci_epf_remove_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf) mutex_lock(&epf_pf->lock); clear_bit(epf_vf->vfunc_no, &epf_pf->vfunction_num_map); + epf_vf->epf_pf = NULL; list_del(&epf_vf->list); mutex_unlock(&epf_pf->lock); } diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c index 8f3a0a33f362..b3aa34e3a4a2 100644 --- a/drivers/pci/hotplug/acpiphp_ibm.c +++ b/drivers/pci/hotplug/acpiphp_ibm.c @@ -84,7 +84,7 @@ static int ibm_get_attention_status(struct hotplug_slot *slot, u8 *status); static void ibm_handle_events(acpi_handle handle, u32 event, void *context); static int ibm_get_table_from_acpi(char **bufp); static ssize_t ibm_read_apci_table(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t size); static acpi_status __init ibm_find_acpi_device(acpi_handle handle, u32 lvl, void *context, void **rv); @@ -98,7 +98,7 @@ static struct bin_attribute ibm_apci_table_attr __ro_after_init = { .name = "apci_table", .mode = S_IRUGO, }, - .read = ibm_read_apci_table, + .read_new = ibm_read_apci_table, .write = NULL, }; static struct acpiphp_attention_info ibm_attention_info = @@ -353,7 +353,7 @@ read_table_done: * our solution is to only allow reading the table in all at once. */ static ssize_t ibm_read_apci_table(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t size) { int bytes_read = -EINVAL; diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 4be402fe9ab9..9e4770cdd4d5 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -747,6 +747,7 @@ static int sriov_init(struct pci_dev *dev, int pos) struct resource *res; const char *res_name; struct pci_dev *pdev; + u32 sriovbars[PCI_SRIOV_NUM_BARS]; pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl); if (ctrl & PCI_SRIOV_CTRL_VFE) { @@ -783,6 +784,10 @@ found: if (!iov) return -ENOMEM; + /* Sizing SR-IOV BARs with VF Enable cleared - no decode */ + __pci_size_stdbars(dev, PCI_SRIOV_NUM_BARS, + pos + PCI_SRIOV_BAR, sriovbars); + nres = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { res = &dev->resource[i + PCI_IOV_RESOURCES]; @@ -796,7 +801,8 @@ found: bar64 = (res->flags & IORESOURCE_MEM_64) ? 1 : 0; else bar64 = __pci_read_base(dev, pci_bar_unknown, res, - pos + PCI_SRIOV_BAR + i * 4); + pos + PCI_SRIOV_BAR + i * 4, + &sriovbars[i]); if (!res->flags) continue; if (resource_size(res) & (PAGE_SIZE - 1)) { diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 569125726b3e..d7ba8795d60f 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -350,8 +350,11 @@ bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask, domain = dev_get_msi_domain(&pdev->dev); - if (!domain || !irq_domain_is_hierarchy(domain)) - return mode == ALLOW_LEGACY; + if (!domain || !irq_domain_is_hierarchy(domain)) { + if (IS_ENABLED(CONFIG_PCI_MSI_ARCH_FALLBACKS)) + return mode == ALLOW_LEGACY; + return false; + } if (!irq_domain_is_msi_parent(domain)) { /* diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 3a45879d85db..2f647cac4cae 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -433,6 +433,10 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, if (WARN_ON_ONCE(dev->msi_enabled)) return -EINVAL; + /* Test for the availability of MSI support */ + if (!pci_msi_domain_supports(dev, 0, ALLOW_LEGACY)) + return -ENOTSUPP; + nvec = pci_msi_vec_count(dev); if (nvec < 0) return nvec; diff --git a/drivers/pci/of.c b/drivers/pci/of.c index 52f770bcc481..7a806f5c0d20 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -190,7 +190,8 @@ EXPORT_SYMBOL_GPL(of_pci_get_devfn); * * Returns 0 on success or a negative error-code on failure. */ -int of_pci_parse_bus_range(struct device_node *node, struct resource *res) +static int of_pci_parse_bus_range(struct device_node *node, + struct resource *res) { u32 bus_range[2]; int error; @@ -207,7 +208,6 @@ int of_pci_parse_bus_range(struct device_node *node, struct resource *res) return 0; } -EXPORT_SYMBOL_GPL(of_pci_parse_bus_range); /** * of_get_pci_domain_nr - Find the host bridge domain number @@ -302,8 +302,6 @@ EXPORT_SYMBOL_GPL(of_pci_check_probe_only); * devm_of_pci_get_host_bridge_resources() - Resource-managed parsing of PCI * host bridge resources from DT * @dev: host bridge device - * @busno: bus number associated with the bridge root bus - * @bus_max: maximum number of buses for this bridge * @resources: list where the range of resources will be added after DT parsing * @ib_resources: list where the range of inbound resources (with addresses * from 'dma-ranges') will be added after DT parsing @@ -319,7 +317,6 @@ EXPORT_SYMBOL_GPL(of_pci_check_probe_only); * value if it failed. */ static int devm_of_pci_get_host_bridge_resources(struct device *dev, - unsigned char busno, unsigned char bus_max, struct list_head *resources, struct list_head *ib_resources, resource_size_t *io_base) @@ -343,14 +340,15 @@ static int devm_of_pci_get_host_bridge_resources(struct device *dev, err = of_pci_parse_bus_range(dev_node, bus_range); if (err) { - bus_range->start = busno; - bus_range->end = bus_max; + bus_range->start = 0; + bus_range->end = 0xff; bus_range->flags = IORESOURCE_BUS; - dev_info(dev, " No bus range found for %pOF, using %pR\n", - dev_node, bus_range); } else { - if (bus_range->end > bus_range->start + bus_max) - bus_range->end = bus_range->start + bus_max; + if (bus_range->end > 0xff) { + dev_warn(dev, " Invalid end bus number in %pR, defaulting to 0xff\n", + bus_range); + bus_range->end = 0xff; + } } pci_add_resource(resources, bus_range); @@ -597,7 +595,7 @@ static int pci_parse_request_of_pci_ranges(struct device *dev, INIT_LIST_HEAD(&bridge->windows); INIT_LIST_HEAD(&bridge->dma_ranges); - err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, &bridge->windows, + err = devm_of_pci_get_host_bridge_resources(dev, &bridge->windows, &bridge->dma_ranges, &iobase); if (err) return err; diff --git a/drivers/pci/of_property.c b/drivers/pci/of_property.c index 886c236e5de6..58fbafac7c6a 100644 --- a/drivers/pci/of_property.c +++ b/drivers/pci/of_property.c @@ -26,7 +26,7 @@ struct of_pci_addr_pair { * side and the child address is the corresponding address on the secondary * side. */ -struct of_pci_range { +struct of_pci_range_entry { u32 child_addr[OF_PCI_ADDRESS_CELLS]; u32 parent_addr[OF_PCI_ADDRESS_CELLS]; u32 size[OF_PCI_SIZE_CELLS]; @@ -101,7 +101,7 @@ static int of_pci_prop_bus_range(struct pci_dev *pdev, static int of_pci_prop_ranges(struct pci_dev *pdev, struct of_changeset *ocs, struct device_node *np) { - struct of_pci_range *rp; + struct of_pci_range_entry *rp; struct resource *res; int i, j, ret; u32 flags, num; diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 7abd4f546d3c..0cb7e0aaba0e 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -161,7 +161,7 @@ out: return ret; } -static struct bin_attribute p2pmem_alloc_attr = { +static const struct bin_attribute p2pmem_alloc_attr = { .attr = { .name = "allocate", .mode = 0660 }, .mmap = p2pmem_alloc_mmap, /* @@ -180,14 +180,14 @@ static struct attribute *p2pmem_attrs[] = { NULL, }; -static struct bin_attribute *p2pmem_bin_attrs[] = { +static const struct bin_attribute *const p2pmem_bin_attrs[] = { &p2pmem_alloc_attr, NULL, }; static const struct attribute_group p2pmem_group = { .attrs = p2pmem_attrs, - .bin_attrs = p2pmem_bin_attrs, + .bin_attrs_new = p2pmem_bin_attrs, .name = "p2pmem", }; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 35270172c833..f57ea36d125d 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1670,6 +1670,19 @@ static void pci_dma_cleanup(struct device *dev) iommu_device_unuse_default_domain(dev); } +/* + * pci_device_irq_get_affinity - get IRQ affinity mask for device + * @dev: ptr to dev structure + * @irq_vec: interrupt vector number + * + * Return the CPU affinity mask for @dev and @irq_vec. + */ +static const struct cpumask *pci_device_irq_get_affinity(struct device *dev, + unsigned int irq_vec) +{ + return pci_irq_get_affinity(to_pci_dev(dev), irq_vec); +} + const struct bus_type pci_bus_type = { .name = "pci", .match = pci_bus_match, @@ -1677,6 +1690,7 @@ const struct bus_type pci_bus_type = { .probe = pci_device_probe, .remove = pci_device_remove, .shutdown = pci_device_shutdown, + .irq_get_affinity = pci_device_irq_get_affinity, .dev_groups = pci_dev_groups, .bus_groups = pci_bus_groups, .drv_groups = pci_drv_groups, diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 7679d75d71e5..b46ce1a2c554 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -13,6 +13,7 @@ */ #include +#include #include #include #include @@ -694,7 +695,7 @@ static ssize_t boot_vga_show(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR_RO(boot_vga); static ssize_t pci_read_config(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *dev = to_pci_dev(kobj_to_dev(kobj)); @@ -769,7 +770,7 @@ static ssize_t pci_read_config(struct file *filp, struct kobject *kobj, } static ssize_t pci_write_config(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *dev = to_pci_dev(kobj_to_dev(kobj)); @@ -837,9 +838,9 @@ static ssize_t pci_write_config(struct file *filp, struct kobject *kobj, return count; } -static BIN_ATTR(config, 0644, pci_read_config, pci_write_config, 0); +static const BIN_ATTR(config, 0644, pci_read_config, pci_write_config, 0); -static struct bin_attribute *pci_dev_config_attrs[] = { +static const struct bin_attribute *const pci_dev_config_attrs[] = { &bin_attr_config, NULL, }; @@ -856,7 +857,7 @@ static size_t pci_dev_config_attr_bin_size(struct kobject *kobj, } static const struct attribute_group pci_dev_config_attr_group = { - .bin_attrs = pci_dev_config_attrs, + .bin_attrs_new = pci_dev_config_attrs, .bin_size = pci_dev_config_attr_bin_size, }; @@ -887,8 +888,8 @@ pci_llseek_resource(struct file *filep, * callback routine (pci_legacy_read). */ static ssize_t pci_read_legacy_io(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t off, size_t count) + const struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) { struct pci_bus *bus = to_pci_bus(kobj_to_dev(kobj)); @@ -912,8 +913,8 @@ static ssize_t pci_read_legacy_io(struct file *filp, struct kobject *kobj, * callback routine (pci_legacy_write). */ static ssize_t pci_write_legacy_io(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t off, size_t count) + const struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) { struct pci_bus *bus = to_pci_bus(kobj_to_dev(kobj)); @@ -1003,8 +1004,8 @@ void pci_create_legacy_files(struct pci_bus *b) b->legacy_io->attr.name = "legacy_io"; b->legacy_io->size = 0xffff; b->legacy_io->attr.mode = 0600; - b->legacy_io->read = pci_read_legacy_io; - b->legacy_io->write = pci_write_legacy_io; + b->legacy_io->read_new = pci_read_legacy_io; + b->legacy_io->write_new = pci_write_legacy_io; /* See pci_create_attr() for motivation */ b->legacy_io->llseek = pci_llseek_resource; b->legacy_io->mmap = pci_mmap_legacy_io; @@ -1099,7 +1100,7 @@ static int pci_mmap_resource_wc(struct file *filp, struct kobject *kobj, } static ssize_t pci_resource_io(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count, bool write) { #ifdef CONFIG_HAS_IOPORT @@ -1142,14 +1143,14 @@ static ssize_t pci_resource_io(struct file *filp, struct kobject *kobj, } static ssize_t pci_read_resource_io(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { return pci_resource_io(filp, kobj, attr, buf, off, count, false); } static ssize_t pci_write_resource_io(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { int ret; @@ -1210,8 +1211,8 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine) } else { sprintf(res_attr_name, "resource%d", num); if (pci_resource_flags(pdev, num) & IORESOURCE_IO) { - res_attr->read = pci_read_resource_io; - res_attr->write = pci_write_resource_io; + res_attr->read_new = pci_read_resource_io; + res_attr->write_new = pci_write_resource_io; if (arch_can_pci_mmap_io()) res_attr->mmap = pci_mmap_resource_uc; } else { @@ -1292,7 +1293,7 @@ void __weak pci_remove_resource_files(struct pci_dev *dev) { return; } * writing anything except 0 enables it */ static ssize_t pci_write_rom(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj)); @@ -1318,7 +1319,7 @@ static ssize_t pci_write_rom(struct file *filp, struct kobject *kobj, * device corresponding to @kobj. */ static ssize_t pci_read_rom(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj)); @@ -1344,9 +1345,9 @@ static ssize_t pci_read_rom(struct file *filp, struct kobject *kobj, return count; } -static BIN_ATTR(rom, 0600, pci_read_rom, pci_write_rom, 0); +static const BIN_ATTR(rom, 0600, pci_read_rom, pci_write_rom, 0); -static struct bin_attribute *pci_dev_rom_attrs[] = { +static const struct bin_attribute *const pci_dev_rom_attrs[] = { &bin_attr_rom, NULL, }; @@ -1372,7 +1373,7 @@ static size_t pci_dev_rom_attr_bin_size(struct kobject *kobj, } static const struct attribute_group pci_dev_rom_attr_group = { - .bin_attrs = pci_dev_rom_attrs, + .bin_attrs_new = pci_dev_rom_attrs, .is_bin_visible = pci_dev_rom_attr_is_visible, .bin_size = pci_dev_rom_attr_bin_size, }; @@ -1421,6 +1422,113 @@ static const struct attribute_group pci_dev_reset_attr_group = { .is_visible = pci_dev_reset_attr_is_visible, }; +static ssize_t reset_method_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + ssize_t len = 0; + int i, m; + + for (i = 0; i < PCI_NUM_RESET_METHODS; i++) { + m = pdev->reset_methods[i]; + if (!m) + break; + + len += sysfs_emit_at(buf, len, "%s%s", len ? " " : "", + pci_reset_fn_methods[m].name); + } + + if (len) + len += sysfs_emit_at(buf, len, "\n"); + + return len; +} + +static int reset_method_lookup(const char *name) +{ + int m; + + for (m = 1; m < PCI_NUM_RESET_METHODS; m++) { + if (sysfs_streq(name, pci_reset_fn_methods[m].name)) + return m; + } + + return 0; /* not found */ +} + +static ssize_t reset_method_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct pci_dev *pdev = to_pci_dev(dev); + char *tmp_options, *name; + int m, n; + u8 reset_methods[PCI_NUM_RESET_METHODS] = {}; + + if (sysfs_streq(buf, "")) { + pdev->reset_methods[0] = 0; + pci_warn(pdev, "All device reset methods disabled by user"); + return count; + } + + if (sysfs_streq(buf, "default")) { + pci_init_reset_methods(pdev); + return count; + } + + char *options __free(kfree) = kstrndup(buf, count, GFP_KERNEL); + if (!options) + return -ENOMEM; + + n = 0; + tmp_options = options; + while ((name = strsep(&tmp_options, " ")) != NULL) { + if (sysfs_streq(name, "")) + continue; + + name = strim(name); + + /* Leave previous methods unchanged if input is invalid */ + m = reset_method_lookup(name); + if (!m) { + pci_err(pdev, "Invalid reset method '%s'", name); + return -EINVAL; + } + + if (pci_reset_fn_methods[m].reset_fn(pdev, PCI_RESET_PROBE)) { + pci_err(pdev, "Unsupported reset method '%s'", name); + return -EINVAL; + } + + if (n == PCI_NUM_RESET_METHODS - 1) { + pci_err(pdev, "Too many reset methods\n"); + return -EINVAL; + } + + reset_methods[n++] = m; + } + + reset_methods[n] = 0; + + /* Warn if dev-specific supported but not highest priority */ + if (pci_reset_fn_methods[1].reset_fn(pdev, PCI_RESET_PROBE) == 0 && + reset_methods[0] != 1) + pci_warn(pdev, "Device-specific reset disabled/de-prioritized by user"); + memcpy(pdev->reset_methods, reset_methods, sizeof(pdev->reset_methods)); + return count; +} +static DEVICE_ATTR_RW(reset_method); + +static struct attribute *pci_dev_reset_method_attrs[] = { + &dev_attr_reset_method.attr, + NULL, +}; + +static const struct attribute_group pci_dev_reset_method_attr_group = { + .attrs = pci_dev_reset_method_attrs, + .is_visible = pci_dev_reset_attr_is_visible, +}; + static ssize_t __resource_resize_show(struct device *dev, int n, char *buf) { struct pci_dev *pdev = to_pci_dev(dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 0b29ec6e8e5e..869d204a70a3 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include @@ -1099,34 +1098,6 @@ static void pci_enable_acs(struct pci_dev *dev) pci_write_config_word(dev, pos + PCI_ACS_CTRL, caps.ctrl); } -/** - * pcie_read_tlp_log - read TLP Header Log - * @dev: PCIe device - * @where: PCI Config offset of TLP Header Log - * @tlp_log: TLP Log structure to fill - * - * Fill @tlp_log from TLP Header Log registers, e.g., AER or DPC. - * - * Return: 0 on success and filled TLP Log structure, <0 on error. - */ -int pcie_read_tlp_log(struct pci_dev *dev, int where, - struct pcie_tlp_log *tlp_log) -{ - int i, ret; - - memset(tlp_log, 0, sizeof(*tlp_log)); - - for (i = 0; i < 4; i++) { - ret = pci_read_config_dword(dev, where + i * 4, - &tlp_log->dw[i]); - if (ret) - return pcibios_err_to_errno(ret); - } - - return 0; -} -EXPORT_SYMBOL_GPL(pcie_read_tlp_log); - /** * pci_restore_bars - restore a device's BAR values (e.g. after wake-up) * @dev: PCI device to have its BARs restored @@ -2059,6 +2030,28 @@ int __weak pcibios_enable_device(struct pci_dev *dev, int bars) return pci_enable_resources(dev, bars); } +static int pci_host_bridge_enable_device(struct pci_dev *dev) +{ + struct pci_host_bridge *host_bridge = pci_find_host_bridge(dev->bus); + int err; + + if (host_bridge && host_bridge->enable_device) { + err = host_bridge->enable_device(host_bridge, dev); + if (err) + return err; + } + + return 0; +} + +static void pci_host_bridge_disable_device(struct pci_dev *dev) +{ + struct pci_host_bridge *host_bridge = pci_find_host_bridge(dev->bus); + + if (host_bridge && host_bridge->disable_device) + host_bridge->disable_device(host_bridge, dev); +} + static int do_pci_enable_device(struct pci_dev *dev, int bars) { int err; @@ -2074,9 +2067,13 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars) if (bridge) pcie_aspm_powersave_config_link(bridge); + err = pci_host_bridge_enable_device(dev); + if (err) + return err; + err = pcibios_enable_device(dev, bars); if (err < 0) - return err; + goto err_enable; pci_fixup_device(pci_fixup_enable, dev); if (dev->msi_enabled || dev->msix_enabled) @@ -2091,6 +2088,12 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars) } return 0; + +err_enable: + pci_host_bridge_disable_device(dev); + + return err; + } /** @@ -2274,6 +2277,8 @@ void pci_disable_device(struct pci_dev *dev) if (atomic_dec_return(&dev->enable_cnt) != 0) return; + pci_host_bridge_disable_device(dev); + do_pci_disable_device(dev); dev->is_busmaster = 0; @@ -3941,15 +3946,14 @@ EXPORT_SYMBOL(pci_release_region); * __pci_request_region - Reserved PCI I/O and memory resource * @pdev: PCI device whose resources are to be reserved * @bar: BAR to be reserved - * @res_name: Name to be associated with resource. + * @name: name of the driver requesting the resource * @exclusive: whether the region access is exclusive or not * * Returns: 0 on success, negative error code on failure. * - * Mark the PCI region associated with PCI device @pdev BAR @bar as - * being reserved by owner @res_name. Do not access any - * address inside the PCI regions unless this call returns - * successfully. + * Mark the PCI region associated with PCI device @pdev BAR @bar as being + * reserved by owner @name. Do not access any address inside the PCI regions + * unless this call returns successfully. * * If @exclusive is set, then the region is marked so that userspace * is explicitly not allowed to map the resource via /dev/mem or @@ -3959,13 +3963,13 @@ EXPORT_SYMBOL(pci_release_region); * message is also printed on failure. */ static int __pci_request_region(struct pci_dev *pdev, int bar, - const char *res_name, int exclusive) + const char *name, int exclusive) { if (pci_is_managed(pdev)) { if (exclusive == IORESOURCE_EXCLUSIVE) - return pcim_request_region_exclusive(pdev, bar, res_name); + return pcim_request_region_exclusive(pdev, bar, name); - return pcim_request_region(pdev, bar, res_name); + return pcim_request_region(pdev, bar, name); } if (pci_resource_len(pdev, bar) == 0) @@ -3973,11 +3977,11 @@ static int __pci_request_region(struct pci_dev *pdev, int bar, if (pci_resource_flags(pdev, bar) & IORESOURCE_IO) { if (!request_region(pci_resource_start(pdev, bar), - pci_resource_len(pdev, bar), res_name)) + pci_resource_len(pdev, bar), name)) goto err_out; } else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) { if (!__request_mem_region(pci_resource_start(pdev, bar), - pci_resource_len(pdev, bar), res_name, + pci_resource_len(pdev, bar), name, exclusive)) goto err_out; } @@ -3994,14 +3998,13 @@ err_out: * pci_request_region - Reserve PCI I/O and memory resource * @pdev: PCI device whose resources are to be reserved * @bar: BAR to be reserved - * @res_name: Name to be associated with resource + * @name: name of the driver requesting the resource * * Returns: 0 on success, negative error code on failure. * - * Mark the PCI region associated with PCI device @pdev BAR @bar as - * being reserved by owner @res_name. Do not access any - * address inside the PCI regions unless this call returns - * successfully. + * Mark the PCI region associated with PCI device @pdev BAR @bar as being + * reserved by owner @name. Do not access any address inside the PCI regions + * unless this call returns successfully. * * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. @@ -4011,9 +4014,9 @@ err_out: * when pcim_enable_device() has been called in advance. This hybrid feature is * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ -int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) +int pci_request_region(struct pci_dev *pdev, int bar, const char *name) { - return __pci_request_region(pdev, bar, res_name, 0); + return __pci_request_region(pdev, bar, name, 0); } EXPORT_SYMBOL(pci_request_region); @@ -4036,13 +4039,13 @@ void pci_release_selected_regions(struct pci_dev *pdev, int bars) EXPORT_SYMBOL(pci_release_selected_regions); static int __pci_request_selected_regions(struct pci_dev *pdev, int bars, - const char *res_name, int excl) + const char *name, int excl) { int i; for (i = 0; i < PCI_STD_NUM_BARS; i++) if (bars & (1 << i)) - if (__pci_request_region(pdev, i, res_name, excl)) + if (__pci_request_region(pdev, i, name, excl)) goto err_out; return 0; @@ -4059,7 +4062,7 @@ err_out: * pci_request_selected_regions - Reserve selected PCI I/O and memory resources * @pdev: PCI device whose resources are to be reserved * @bars: Bitmask of BARs to be requested - * @res_name: Name to be associated with resource + * @name: Name of the driver requesting the resources * * Returns: 0 on success, negative error code on failure. * @@ -4069,9 +4072,9 @@ err_out: * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_selected_regions(struct pci_dev *pdev, int bars, - const char *res_name) + const char *name) { - return __pci_request_selected_regions(pdev, bars, res_name, 0); + return __pci_request_selected_regions(pdev, bars, name, 0); } EXPORT_SYMBOL(pci_request_selected_regions); @@ -4079,7 +4082,7 @@ EXPORT_SYMBOL(pci_request_selected_regions); * pci_request_selected_regions_exclusive - Request regions exclusively * @pdev: PCI device to request regions from * @bars: bit mask of BARs to request - * @res_name: name to be associated with the requests + * @name: name of the driver requesting the resources * * Returns: 0 on success, negative error code on failure. * @@ -4089,9 +4092,9 @@ EXPORT_SYMBOL(pci_request_selected_regions); * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_selected_regions_exclusive(struct pci_dev *pdev, int bars, - const char *res_name) + const char *name) { - return __pci_request_selected_regions(pdev, bars, res_name, + return __pci_request_selected_regions(pdev, bars, name, IORESOURCE_EXCLUSIVE); } EXPORT_SYMBOL(pci_request_selected_regions_exclusive); @@ -4114,12 +4117,11 @@ EXPORT_SYMBOL(pci_release_regions); /** * pci_request_regions - Reserve PCI I/O and memory resources * @pdev: PCI device whose resources are to be reserved - * @res_name: Name to be associated with resource. + * @name: name of the driver requesting the resources * - * Mark all PCI regions associated with PCI device @pdev as - * being reserved by owner @res_name. Do not access any - * address inside the PCI regions unless this call returns - * successfully. + * Mark all PCI regions associated with PCI device @pdev as being reserved by + * owner @name. Do not access any address inside the PCI regions unless this + * call returns successfully. * * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. @@ -4129,22 +4131,22 @@ EXPORT_SYMBOL(pci_release_regions); * when pcim_enable_device() has been called in advance. This hybrid feature is * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ -int pci_request_regions(struct pci_dev *pdev, const char *res_name) +int pci_request_regions(struct pci_dev *pdev, const char *name) { return pci_request_selected_regions(pdev, - ((1 << PCI_STD_NUM_BARS) - 1), res_name); + ((1 << PCI_STD_NUM_BARS) - 1), name); } EXPORT_SYMBOL(pci_request_regions); /** * pci_request_regions_exclusive - Reserve PCI I/O and memory resources * @pdev: PCI device whose resources are to be reserved - * @res_name: Name to be associated with resource. + * @name: name of the driver requesting the resources * * Returns: 0 on success, negative error code on failure. * * Mark all PCI regions associated with PCI device @pdev as being reserved - * by owner @res_name. Do not access any address inside the PCI regions + * by owner @name. Do not access any address inside the PCI regions * unless this call returns successfully. * * pci_request_regions_exclusive() will mark the region so that /dev/mem @@ -4158,10 +4160,10 @@ EXPORT_SYMBOL(pci_request_regions); * when pcim_enable_device() has been called in advance. This hybrid feature is * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ -int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) +int pci_request_regions_exclusive(struct pci_dev *pdev, const char *name) { return pci_request_selected_regions_exclusive(pdev, - ((1 << PCI_STD_NUM_BARS) - 1), res_name); + ((1 << PCI_STD_NUM_BARS) - 1), name); } EXPORT_SYMBOL(pci_request_regions_exclusive); @@ -4488,11 +4490,6 @@ void pci_disable_parity(struct pci_dev *dev) * @enable: boolean: whether to enable or disable PCI INTx * * Enables/disables PCI INTx for device @pdev - * - * NOTE: - * This is a "hybrid" function: It's normally unmanaged, but becomes managed - * when pcim_enable_device() has been called in advance. This hybrid feature is - * DEPRECATED! If you want managed cleanup, use pcim_intx() instead. */ void pci_intx(struct pci_dev *pdev, int enable) { @@ -4505,15 +4502,10 @@ void pci_intx(struct pci_dev *pdev, int enable) else new = pci_command | PCI_COMMAND_INTX_DISABLE; - if (new != pci_command) { - /* Preserve the "hybrid" behavior for backwards compatibility */ - if (pci_is_managed(pdev)) { - WARN_ON_ONCE(pcim_intx(pdev, enable) != 0); - return; - } + if (new == pci_command) + return; - pci_write_config_word(pdev, PCI_COMMAND, new); - } + pci_write_config_word(pdev, PCI_COMMAND, new); } EXPORT_SYMBOL_GPL(pci_intx); @@ -5204,7 +5196,7 @@ static void pci_dev_restore(struct pci_dev *dev) } /* dev->reset_methods[] is a 0-terminated list of indices into this array */ -static const struct pci_reset_fn_method pci_reset_fn_methods[] = { +const struct pci_reset_fn_method pci_reset_fn_methods[] = { { }, { pci_dev_specific_reset, .name = "device_specific" }, { pci_dev_acpi_reset, .name = "acpi" }, @@ -5215,129 +5207,6 @@ static const struct pci_reset_fn_method pci_reset_fn_methods[] = { { cxl_reset_bus_function, .name = "cxl_bus" }, }; -static ssize_t reset_method_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pci_dev *pdev = to_pci_dev(dev); - ssize_t len = 0; - int i, m; - - for (i = 0; i < PCI_NUM_RESET_METHODS; i++) { - m = pdev->reset_methods[i]; - if (!m) - break; - - len += sysfs_emit_at(buf, len, "%s%s", len ? " " : "", - pci_reset_fn_methods[m].name); - } - - if (len) - len += sysfs_emit_at(buf, len, "\n"); - - return len; -} - -static int reset_method_lookup(const char *name) -{ - int m; - - for (m = 1; m < PCI_NUM_RESET_METHODS; m++) { - if (sysfs_streq(name, pci_reset_fn_methods[m].name)) - return m; - } - - return 0; /* not found */ -} - -static ssize_t reset_method_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct pci_dev *pdev = to_pci_dev(dev); - char *options, *tmp_options, *name; - int m, n; - u8 reset_methods[PCI_NUM_RESET_METHODS] = { 0 }; - - if (sysfs_streq(buf, "")) { - pdev->reset_methods[0] = 0; - pci_warn(pdev, "All device reset methods disabled by user"); - return count; - } - - if (sysfs_streq(buf, "default")) { - pci_init_reset_methods(pdev); - return count; - } - - options = kstrndup(buf, count, GFP_KERNEL); - if (!options) - return -ENOMEM; - - n = 0; - tmp_options = options; - while ((name = strsep(&tmp_options, " ")) != NULL) { - if (sysfs_streq(name, "")) - continue; - - name = strim(name); - - m = reset_method_lookup(name); - if (!m) { - pci_err(pdev, "Invalid reset method '%s'", name); - goto error; - } - - if (pci_reset_fn_methods[m].reset_fn(pdev, PCI_RESET_PROBE)) { - pci_err(pdev, "Unsupported reset method '%s'", name); - goto error; - } - - if (n == PCI_NUM_RESET_METHODS - 1) { - pci_err(pdev, "Too many reset methods\n"); - goto error; - } - - reset_methods[n++] = m; - } - - reset_methods[n] = 0; - - /* Warn if dev-specific supported but not highest priority */ - if (pci_reset_fn_methods[1].reset_fn(pdev, PCI_RESET_PROBE) == 0 && - reset_methods[0] != 1) - pci_warn(pdev, "Device-specific reset disabled/de-prioritized by user"); - memcpy(pdev->reset_methods, reset_methods, sizeof(pdev->reset_methods)); - kfree(options); - return count; - -error: - /* Leave previous methods unchanged */ - kfree(options); - return -EINVAL; -} -static DEVICE_ATTR_RW(reset_method); - -static struct attribute *pci_dev_reset_method_attrs[] = { - &dev_attr_reset_method.attr, - NULL, -}; - -static umode_t pci_dev_reset_method_attr_is_visible(struct kobject *kobj, - struct attribute *a, int n) -{ - struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj)); - - if (!pci_reset_supported(pdev)) - return 0; - - return a->mode; -} - -const struct attribute_group pci_dev_reset_method_attr_group = { - .attrs = pci_dev_reset_method_attrs, - .is_visible = pci_dev_reset_method_attr_is_visible, -}; - /** * __pci_reset_function_locked - reset a PCI device function while holding * the @dev mutex lock. @@ -6232,12 +6101,14 @@ u8 pcie_get_supported_speeds(struct pci_dev *dev) pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2); speeds = lnkcap2 & PCI_EXP_LNKCAP2_SLS; + /* Ignore speeds higher than Max Link Speed */ + pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); + speeds &= GENMASK(lnkcap & PCI_EXP_LNKCAP_SLS, 0); + /* PCIe r3.0-compliant */ if (speeds) return speeds; - pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); - /* Synthesize from the Max Link Speed field */ if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_5_0GB) speeds = PCI_EXP_LNKCAP2_SLS_5_0GB | PCI_EXP_LNKCAP2_SLS_2_5GB; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 2e40fc63ba31..01e51db8d285 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -4,6 +4,8 @@ #include +struct pcie_tlp_log; + /* Number of possible devfns: 0.0 to 1f.7 inclusive */ #define MAX_NR_DEVFNS 256 @@ -315,8 +317,10 @@ bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *pl, int rrs_timeout); int pci_setup_device(struct pci_dev *dev); +void __pci_size_stdbars(struct pci_dev *dev, int count, + unsigned int pos, u32 *sizes); int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, - struct resource *res, unsigned int reg); + struct resource *res, unsigned int reg, u32 *sizes); void pci_configure_ari(struct pci_dev *dev); void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head); @@ -547,6 +551,12 @@ struct aer_err_info { int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info); void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); + +int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2, + unsigned int tlp_len, struct pcie_tlp_log *log); +unsigned int aer_tlp_log_len(struct pci_dev *dev, u32 aercc); +void pcie_print_tlp_log(const struct pci_dev *dev, + const struct pcie_tlp_log *log, const char *pfx); #endif /* CONFIG_PCIEAER */ #ifdef CONFIG_PCIEPORTBUS @@ -565,6 +575,7 @@ void pci_dpc_init(struct pci_dev *pdev); void dpc_process_error(struct pci_dev *pdev); pci_ers_result_t dpc_reset_link(struct pci_dev *pdev); bool pci_dpc_recovered(struct pci_dev *pdev); +unsigned int dpc_tlp_log_len(struct pci_dev *dev); #else static inline void pci_save_dpc_state(struct pci_dev *dev) { } static inline void pci_restore_dpc_state(struct pci_dev *dev) { } @@ -766,6 +777,7 @@ struct pci_reset_fn_method { int (*reset_fn)(struct pci_dev *pdev, bool probe); char *name; }; +extern const struct pci_reset_fn_method pci_reset_fn_methods[]; #ifdef CONFIG_PCI_QUIRKS int pci_dev_specific_reset(struct pci_dev *dev, bool probe); @@ -797,7 +809,6 @@ static inline u64 pci_rebar_size_to_bytes(int size) struct device_node; #ifdef CONFIG_OF -int of_pci_parse_bus_range(struct device_node *node, struct resource *res); int of_get_pci_domain_nr(struct device_node *node); int of_pci_get_max_link_speed(struct device_node *node); u32 of_pci_get_slot_power_limit(struct device_node *node, @@ -813,12 +824,6 @@ int devm_of_pci_bridge_init(struct device *dev, struct pci_host_bridge *bridge); bool of_pci_supply_present(struct device_node *np); #else -static inline int -of_pci_parse_bus_range(struct device_node *node, struct resource *res) -{ - return -EINVAL; -} - static inline int of_get_pci_domain_nr(struct device_node *node) { @@ -960,8 +965,6 @@ static inline pci_power_t acpi_pci_choose_state(struct pci_dev *pdev) extern const struct attribute_group aspm_ctrl_attr_group; #endif -extern const struct attribute_group pci_dev_reset_method_attr_group; - #ifdef CONFIG_X86_INTEL_MID bool pci_use_mid_pm(void); int mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state); diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile index 53ccab62314d..173829aa02e6 100644 --- a/drivers/pci/pcie/Makefile +++ b/drivers/pci/pcie/Makefile @@ -7,7 +7,7 @@ pcieportdrv-y := portdrv.o rcec.o obj-$(CONFIG_PCIEPORTBUS) += pcieportdrv.o bwctrl.o obj-y += aspm.o -obj-$(CONFIG_PCIEAER) += aer.o err.o +obj-$(CONFIG_PCIEAER) += aer.o err.o tlp.o obj-$(CONFIG_PCIEAER_INJECT) += aer_inject.o obj-$(CONFIG_PCIE_PME) += pme.o obj-$(CONFIG_PCIE_DPC) += dpc.o diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 34ce9f834d0c..508474e17183 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -665,12 +665,6 @@ static void pci_rootport_aer_stats_incr(struct pci_dev *pdev, } } -static void __print_tlp_header(struct pci_dev *dev, struct pcie_tlp_log *t) -{ - pci_err(dev, " TLP Header: %08x %08x %08x %08x\n", - t->dw[0], t->dw[1], t->dw[2], t->dw[3]); -} - static void __aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { @@ -725,7 +719,7 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) __aer_print_error(dev, info); if (info->tlp_header_valid) - __print_tlp_header(dev, &info->tlp); + pcie_print_tlp_log(dev, &info->tlp, dev_fmt(" ")); out: if (info->id && info->error_dev_num > 1 && info->id == id) @@ -797,7 +791,7 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity, aer->uncor_severity); if (tlp_header_valid) - __print_tlp_header(dev, &aer->header_log); + pcie_print_tlp_log(dev, &aer->header_log, dev_fmt(" ")); trace_aer_event(dev_name(&dev->dev), (status & ~mask), aer_severity, tlp_header_valid, &aer->header_log); @@ -1248,7 +1242,10 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) if (info->status & AER_LOG_TLP_MASKS) { info->tlp_header_valid = 1; - pcie_read_tlp_log(dev, aer + PCI_ERR_HEADER_LOG, &info->tlp); + pcie_read_tlp_log(dev, aer + PCI_ERR_HEADER_LOG, + aer + PCI_ERR_PREFIX_LOG, + aer_tlp_log_len(dev, aercc), + &info->tlp); } } diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 28567d457613..e0bc90597dca 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -81,24 +81,47 @@ void pci_configure_aspm_l1ss(struct pci_dev *pdev) void pci_save_aspm_l1ss_state(struct pci_dev *pdev) { + struct pci_dev *parent = pdev->bus->self; struct pci_cap_saved_state *save_state; - u16 l1ss = pdev->l1ss; u32 *cap; + /* + * If this is a Downstream Port, we never restore the L1SS state + * directly; we only restore it when we restore the state of the + * Upstream Port below it. + */ + if (pcie_downstream_port(pdev) || !parent) + return; + + if (!pdev->l1ss || !parent->l1ss) + return; + /* * Save L1 substate configuration. The ASPM L0s/L1 configuration * in PCI_EXP_LNKCTL_ASPMC is saved by pci_save_pcie_state(). */ - if (!l1ss) - return; - save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_L1SS); if (!save_state) return; cap = &save_state->cap.data[0]; - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL2, cap++); - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, cap++); + pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL2, cap++); + pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1, cap++); + + if (parent->state_saved) + return; + + /* + * Save parent's L1 substate configuration so we have it for + * pci_restore_aspm_l1ss_state(pdev) to restore. + */ + save_state = pci_find_saved_ext_cap(parent, PCI_EXT_CAP_ID_L1SS); + if (!save_state) + return; + + cap = &save_state->cap.data[0]; + pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2, cap++); + pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, cap++); } void pci_restore_aspm_l1ss_state(struct pci_dev *pdev) diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c index b59cacc740fa..0a5e7efbce2c 100644 --- a/drivers/pci/pcie/bwctrl.c +++ b/drivers/pci/pcie/bwctrl.c @@ -303,14 +303,17 @@ static int pcie_bwnotif_probe(struct pcie_device *srv) if (ret) return ret; - ret = devm_request_irq(&srv->device, srv->irq, pcie_bwnotif_irq, - IRQF_SHARED, "PCIe bwctrl", srv); - if (ret) - return ret; - scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) { scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) { - port->link_bwctrl = no_free_ptr(data); + port->link_bwctrl = data; + + ret = request_irq(srv->irq, pcie_bwnotif_irq, + IRQF_SHARED, "PCIe bwctrl", srv); + if (ret) { + port->link_bwctrl = NULL; + return ret; + } + pcie_bwnotif_enable(srv); } } @@ -331,11 +334,15 @@ static void pcie_bwnotif_remove(struct pcie_device *srv) pcie_cooling_device_unregister(data->cdev); - pcie_bwnotif_disable(srv->port); + scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) { + scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) { + pcie_bwnotif_disable(srv->port); + + free_irq(srv->irq, srv); - scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) - scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) srv->port->link_bwctrl = NULL; + } + } } static int pcie_bwnotif_suspend(struct pcie_device *srv) diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index 2b6ef7efa3c1..242cabd5eeeb 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -190,7 +190,7 @@ out: static void dpc_process_rp_pio_error(struct pci_dev *pdev) { u16 cap = pdev->dpc_cap, dpc_status, first_error; - u32 status, mask, sev, syserr, exc, log, prefix; + u32 status, mask, sev, syserr, exc, log; struct pcie_tlp_log tlp_log; int i; @@ -215,22 +215,18 @@ static void dpc_process_rp_pio_error(struct pci_dev *pdev) first_error == i ? " (First)" : ""); } - if (pdev->dpc_rp_log_size < 4) + if (pdev->dpc_rp_log_size < PCIE_STD_NUM_TLP_HEADERLOG) goto clear_status; - pcie_read_tlp_log(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG, &tlp_log); - pci_err(pdev, "TLP Header: %#010x %#010x %#010x %#010x\n", - tlp_log.dw[0], tlp_log.dw[1], tlp_log.dw[2], tlp_log.dw[3]); + pcie_read_tlp_log(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG, + cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, + dpc_tlp_log_len(pdev), &tlp_log); + pcie_print_tlp_log(pdev, &tlp_log, dev_fmt("")); - if (pdev->dpc_rp_log_size < 5) + if (pdev->dpc_rp_log_size < PCIE_STD_NUM_TLP_HEADERLOG + 1) goto clear_status; pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_IMPSPEC_LOG, &log); pci_err(pdev, "RP PIO ImpSpec Log %#010x\n", log); - for (i = 0; i < pdev->dpc_rp_log_size - 5; i++) { - pci_read_config_dword(pdev, - cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG + i * 4, &prefix); - pci_err(pdev, "TLP Prefix Header: dw%d, %#010x\n", i, prefix); - } clear_status: pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, status); } @@ -404,7 +400,9 @@ void pci_dpc_init(struct pci_dev *pdev) if (!pdev->dpc_rp_log_size) { pdev->dpc_rp_log_size = FIELD_GET(PCI_EXP_DPC_RP_PIO_LOG_SIZE, cap); - if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) { + if (pdev->dpc_rp_log_size < PCIE_STD_NUM_TLP_HEADERLOG || + pdev->dpc_rp_log_size > PCIE_STD_NUM_TLP_HEADERLOG + 1 + + PCIE_STD_MAX_TLP_PREFIXLOG) { pci_err(pdev, "RP PIO log size %u is invalid\n", pdev->dpc_rp_log_size); pdev->dpc_rp_log_size = 0; diff --git a/drivers/pci/pcie/portdrv.c b/drivers/pci/pcie/portdrv.c index 5e10306b6308..02e73099bad0 100644 --- a/drivers/pci/pcie/portdrv.c +++ b/drivers/pci/pcie/portdrv.c @@ -265,12 +265,14 @@ static int get_port_device_capability(struct pci_dev *dev) (pcie_ports_dpc_native || (services & PCIE_PORT_SERVICE_AER))) services |= PCIE_PORT_SERVICE_DPC; + /* Enable bandwidth control if more than one speed is supported. */ if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM || pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) { u32 linkcap; pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &linkcap); - if (linkcap & PCI_EXP_LNKCAP_LBNC) + if (linkcap & PCI_EXP_LNKCAP_LBNC && + hweight8(dev->supported_speeds) > 1) services |= PCIE_PORT_SERVICE_BWCTRL; } diff --git a/drivers/pci/pcie/tlp.c b/drivers/pci/pcie/tlp.c new file mode 100644 index 000000000000..0860b5da837f --- /dev/null +++ b/drivers/pci/pcie/tlp.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe TLP Log handling + * + * Copyright (C) 2024 Intel Corporation + */ + +#include +#include +#include +#include + +#include "../pci.h" + +/** + * aer_tlp_log_len - Calculate AER Capability TLP Header/Prefix Log length + * @dev: PCIe device + * @aercc: AER Capabilities and Control register value + * + * Return: TLP Header/Prefix Log length + */ +unsigned int aer_tlp_log_len(struct pci_dev *dev, u32 aercc) +{ + return PCIE_STD_NUM_TLP_HEADERLOG + + ((aercc & PCI_ERR_CAP_PREFIX_LOG_PRESENT) ? + dev->eetlp_prefix_max : 0); +} + +#ifdef CONFIG_PCIE_DPC +/** + * dpc_tlp_log_len - Calculate DPC RP PIO TLP Header/Prefix Log length + * @dev: PCIe device + * + * Return: TLP Header/Prefix Log length + */ +unsigned int dpc_tlp_log_len(struct pci_dev *dev) +{ + /* Remove ImpSpec Log register from the count */ + if (dev->dpc_rp_log_size >= PCIE_STD_NUM_TLP_HEADERLOG + 1) + return dev->dpc_rp_log_size - 1; + + return dev->dpc_rp_log_size; +} +#endif + +/** + * pcie_read_tlp_log - read TLP Header Log + * @dev: PCIe device + * @where: PCI Config offset of TLP Header Log + * @where2: PCI Config offset of TLP Prefix Log + * @tlp_len: TLP Log length (Header Log + TLP Prefix Log in DWORDs) + * @log: TLP Log structure to fill + * + * Fill @log from TLP Header Log registers, e.g., AER or DPC. + * + * Return: 0 on success and filled TLP Log structure, <0 on error. + */ +int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2, + unsigned int tlp_len, struct pcie_tlp_log *log) +{ + unsigned int i; + int off, ret; + u32 *to; + + memset(log, 0, sizeof(*log)); + + for (i = 0; i < tlp_len; i++) { + if (i < PCIE_STD_NUM_TLP_HEADERLOG) { + off = where + i * 4; + to = &log->dw[i]; + } else { + off = where2 + (i - PCIE_STD_NUM_TLP_HEADERLOG) * 4; + to = &log->prefix[i - PCIE_STD_NUM_TLP_HEADERLOG]; + } + + ret = pci_read_config_dword(dev, off, to); + if (ret) + return pcibios_err_to_errno(ret); + } + + return 0; +} + +#define EE_PREFIX_STR " E-E Prefixes:" + +/** + * pcie_print_tlp_log - Print TLP Header / Prefix Log contents + * @dev: PCIe device + * @log: TLP Log structure + * @pfx: String prefix + * + * Prints TLP Header and Prefix Log information held by @log. + */ +void pcie_print_tlp_log(const struct pci_dev *dev, + const struct pcie_tlp_log *log, const char *pfx) +{ + char buf[11 * (PCIE_STD_NUM_TLP_HEADERLOG + ARRAY_SIZE(log->prefix)) + + sizeof(EE_PREFIX_STR)]; + unsigned int i; + int len; + + len = scnprintf(buf, sizeof(buf), "%#010x %#010x %#010x %#010x", + log->dw[0], log->dw[1], log->dw[2], log->dw[3]); + + if (log->prefix[0]) + len += scnprintf(buf + len, sizeof(buf) - len, EE_PREFIX_STR); + for (i = 0; i < ARRAY_SIZE(log->prefix); i++) { + if (!log->prefix[i]) + break; + len += scnprintf(buf + len, sizeof(buf) - len, + " %#010x", log->prefix[i]); + } + + pci_err(dev, "%sTLP Header: %s\n", pfx, buf); +} diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 2e81ab0f5a25..b6536ed599c3 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -164,41 +164,67 @@ static inline unsigned long decode_bar(struct pci_dev *dev, u32 bar) #define PCI_COMMAND_DECODE_ENABLE (PCI_COMMAND_MEMORY | PCI_COMMAND_IO) +/** + * __pci_size_bars - Read the raw BAR mask for a range of PCI BARs + * @dev: the PCI device + * @count: number of BARs to size + * @pos: starting config space position + * @sizes: array to store mask values + * @rom: indicate whether to use ROM mask, which avoids enabling ROM BARs + * + * Provided @sizes array must be sufficiently sized to store results for + * @count u32 BARs. Caller is responsible for disabling decode to specified + * BAR range around calling this function. This function is intended to avoid + * disabling decode around sizing each BAR individually, which can result in + * non-trivial overhead in virtualized environments with very large PCI BARs. + */ +static void __pci_size_bars(struct pci_dev *dev, int count, + unsigned int pos, u32 *sizes, bool rom) +{ + u32 orig, mask = rom ? PCI_ROM_ADDRESS_MASK : ~0; + int i; + + for (i = 0; i < count; i++, pos += 4, sizes++) { + pci_read_config_dword(dev, pos, &orig); + pci_write_config_dword(dev, pos, mask); + pci_read_config_dword(dev, pos, sizes); + pci_write_config_dword(dev, pos, orig); + } +} + +void __pci_size_stdbars(struct pci_dev *dev, int count, + unsigned int pos, u32 *sizes) +{ + __pci_size_bars(dev, count, pos, sizes, false); +} + +static void __pci_size_rom(struct pci_dev *dev, unsigned int pos, u32 *sizes) +{ + __pci_size_bars(dev, 1, pos, sizes, true); +} + /** * __pci_read_base - Read a PCI BAR * @dev: the PCI device * @type: type of the BAR * @res: resource buffer to be filled in * @pos: BAR position in the config space + * @sizes: array of one or more pre-read BAR masks * * Returns 1 if the BAR is 64-bit, or 0 if 32-bit. */ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, - struct resource *res, unsigned int pos) + struct resource *res, unsigned int pos, u32 *sizes) { - u32 l = 0, sz = 0, mask; + u32 l = 0, sz; u64 l64, sz64, mask64; - u16 orig_cmd; struct pci_bus_region region, inverted_region; const char *res_name = pci_resource_name(dev, res - dev->resource); - mask = type ? PCI_ROM_ADDRESS_MASK : ~0; - - /* No printks while decoding is disabled! */ - if (!dev->mmio_always_on) { - pci_read_config_word(dev, PCI_COMMAND, &orig_cmd); - if (orig_cmd & PCI_COMMAND_DECODE_ENABLE) { - pci_write_config_word(dev, PCI_COMMAND, - orig_cmd & ~PCI_COMMAND_DECODE_ENABLE); - } - } - res->name = pci_name(dev); pci_read_config_dword(dev, pos, &l); - pci_write_config_dword(dev, pos, l | mask); - pci_read_config_dword(dev, pos, &sz); - pci_write_config_dword(dev, pos, l); + sz = sizes[0]; /* * All bits set in sz means the device isn't working properly. @@ -238,18 +264,13 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, if (res->flags & IORESOURCE_MEM_64) { pci_read_config_dword(dev, pos + 4, &l); - pci_write_config_dword(dev, pos + 4, ~0); - pci_read_config_dword(dev, pos + 4, &sz); - pci_write_config_dword(dev, pos + 4, l); + sz = sizes[1]; l64 |= ((u64)l << 32); sz64 |= ((u64)sz << 32); mask64 |= ((u64)~0 << 32); } - if (!dev->mmio_always_on && (orig_cmd & PCI_COMMAND_DECODE_ENABLE)) - pci_write_config_word(dev, PCI_COMMAND, orig_cmd); - if (!sz64) goto fail; @@ -320,7 +341,11 @@ out: static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom) { + u32 rombar, stdbars[PCI_STD_NUM_BARS]; unsigned int pos, reg; + u16 orig_cmd; + + BUILD_BUG_ON(howmany > PCI_STD_NUM_BARS); if (dev->non_compliant_bars) return; @@ -329,10 +354,28 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom) if (dev->is_virtfn) return; + /* No printks while decoding is disabled! */ + if (!dev->mmio_always_on) { + pci_read_config_word(dev, PCI_COMMAND, &orig_cmd); + if (orig_cmd & PCI_COMMAND_DECODE_ENABLE) { + pci_write_config_word(dev, PCI_COMMAND, + orig_cmd & ~PCI_COMMAND_DECODE_ENABLE); + } + } + + __pci_size_stdbars(dev, howmany, PCI_BASE_ADDRESS_0, stdbars); + if (rom) + __pci_size_rom(dev, rom, &rombar); + + if (!dev->mmio_always_on && + (orig_cmd & PCI_COMMAND_DECODE_ENABLE)) + pci_write_config_word(dev, PCI_COMMAND, orig_cmd); + for (pos = 0; pos < howmany; pos++) { struct resource *res = &dev->resource[pos]; reg = PCI_BASE_ADDRESS_0 + (pos << 2); - pos += __pci_read_base(dev, pci_bar_unknown, res, reg); + pos += __pci_read_base(dev, pci_bar_unknown, + res, reg, &stdbars[pos]); } if (rom) { @@ -340,7 +383,7 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom) dev->rom_base_reg = rom; res->flags = IORESOURCE_MEM | IORESOURCE_PREFETCH | IORESOURCE_READONLY | IORESOURCE_SIZEALIGN; - __pci_read_base(dev, pci_bar_mem32, res, rom); + __pci_read_base(dev, pci_bar_mem32, res, rom, &rombar); } } @@ -2251,8 +2294,8 @@ static void pci_configure_relaxed_ordering(struct pci_dev *dev) static void pci_configure_eetlp_prefix(struct pci_dev *dev) { -#ifdef CONFIG_PCI_PASID struct pci_dev *bridge; + unsigned int eetlp_max; int pcie_type; u32 cap; @@ -2264,15 +2307,19 @@ static void pci_configure_eetlp_prefix(struct pci_dev *dev) return; pcie_type = pci_pcie_type(dev); + + eetlp_max = FIELD_GET(PCI_EXP_DEVCAP2_EE_PREFIX_MAX, cap); + /* 00b means 4 */ + eetlp_max = eetlp_max ?: 4; + if (pcie_type == PCI_EXP_TYPE_ROOT_PORT || pcie_type == PCI_EXP_TYPE_RC_END) - dev->eetlp_prefix_path = 1; + dev->eetlp_prefix_max = eetlp_max; else { bridge = pci_upstream_bridge(dev); - if (bridge && bridge->eetlp_prefix_path) - dev->eetlp_prefix_path = 1; + if (bridge && bridge->eetlp_prefix_max) + dev->eetlp_prefix_max = eetlp_max; } -#endif } static void pci_configure_serr(struct pci_dev *dev) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 76f4df75b08a..b84ff7bade82 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -12,6 +12,7 @@ * file, where their drivers can use them. */ +#include #include #include #include @@ -5984,6 +5985,17 @@ SWITCHTEC_QUIRK(0x5552); /* PAXA 52XG5 */ SWITCHTEC_QUIRK(0x5536); /* PAXA 36XG5 */ SWITCHTEC_QUIRK(0x5528); /* PAXA 28XG5 */ +#define SWITCHTEC_PCI100X_QUIRK(vid) \ + DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_EFAR, vid, \ + PCI_CLASS_BRIDGE_OTHER, 8, quirk_switchtec_ntb_dma_alias) +SWITCHTEC_PCI100X_QUIRK(0x1001); /* PCI1001XG4 */ +SWITCHTEC_PCI100X_QUIRK(0x1002); /* PCI1002XG4 */ +SWITCHTEC_PCI100X_QUIRK(0x1003); /* PCI1003XG4 */ +SWITCHTEC_PCI100X_QUIRK(0x1004); /* PCI1004XG4 */ +SWITCHTEC_PCI100X_QUIRK(0x1005); /* PCI1005XG4 */ +SWITCHTEC_PCI100X_QUIRK(0x1006); /* PCI1006XG4 */ + + /* * The PLX NTB uses devfn proxy IDs to move TLPs between NT endpoints. * These IDs are used to forward responses to the originator on the other @@ -6233,8 +6245,9 @@ static void dpc_log_size(struct pci_dev *dev) return; if (FIELD_GET(PCI_EXP_DPC_RP_PIO_LOG_SIZE, val) == 0) { - pci_info(dev, "Overriding RP PIO Log Size to 4\n"); - dev->dpc_rp_log_size = 4; + pci_info(dev, "Overriding RP PIO Log Size to %d\n", + PCIE_STD_NUM_TLP_HEADERLOG); + dev->dpc_rp_log_size = PCIE_STD_NUM_TLP_HEADERLOG; } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x461f, dpc_log_size); @@ -6253,6 +6266,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2b, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2d, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa72f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa73f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa76e, dpc_log_size); #endif diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index c7e1089ffdaf..b14dfab04d84 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1739,6 +1739,26 @@ static void switchtec_pci_remove(struct pci_dev *pdev) .driver_data = gen, \ } +#define SWITCHTEC_PCI100X_DEVICE(device_id, gen) \ + { \ + .vendor = PCI_VENDOR_ID_EFAR, \ + .device = device_id, \ + .subvendor = PCI_ANY_ID, \ + .subdevice = PCI_ANY_ID, \ + .class = (PCI_CLASS_MEMORY_OTHER << 8), \ + .class_mask = 0xFFFFFFFF, \ + .driver_data = gen, \ + }, \ + { \ + .vendor = PCI_VENDOR_ID_EFAR, \ + .device = device_id, \ + .subvendor = PCI_ANY_ID, \ + .subdevice = PCI_ANY_ID, \ + .class = (PCI_CLASS_BRIDGE_OTHER << 8), \ + .class_mask = 0xFFFFFFFF, \ + .driver_data = gen, \ + } + static const struct pci_device_id switchtec_pci_tbl[] = { SWITCHTEC_PCI_DEVICE(0x8531, SWITCHTEC_GEN3), /* PFX 24xG3 */ SWITCHTEC_PCI_DEVICE(0x8532, SWITCHTEC_GEN3), /* PFX 32xG3 */ @@ -1833,6 +1853,12 @@ static const struct pci_device_id switchtec_pci_tbl[] = { SWITCHTEC_PCI_DEVICE(0x5552, SWITCHTEC_GEN5), /* PAXA 52XG5 */ SWITCHTEC_PCI_DEVICE(0x5536, SWITCHTEC_GEN5), /* PAXA 36XG5 */ SWITCHTEC_PCI_DEVICE(0x5528, SWITCHTEC_GEN5), /* PAXA 28XG5 */ + SWITCHTEC_PCI100X_DEVICE(0x1001, SWITCHTEC_GEN4), /* PCI1001 16XG4 */ + SWITCHTEC_PCI100X_DEVICE(0x1002, SWITCHTEC_GEN4), /* PCI1002 12XG4 */ + SWITCHTEC_PCI100X_DEVICE(0x1003, SWITCHTEC_GEN4), /* PCI1003 16XG4 */ + SWITCHTEC_PCI100X_DEVICE(0x1004, SWITCHTEC_GEN4), /* PCI1004 16XG4 */ + SWITCHTEC_PCI100X_DEVICE(0x1005, SWITCHTEC_GEN4), /* PCI1005 16XG4 */ + SWITCHTEC_PCI100X_DEVICE(0x1006, SWITCHTEC_GEN4), /* PCI1006 16XG4 */ {0} }; MODULE_DEVICE_TABLE(pci, switchtec_pci_tbl); diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index a469bcbc0da7..3d29b2602d0f 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -271,8 +271,8 @@ void pci_vpd_init(struct pci_dev *dev) } static ssize_t vpd_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, - size_t count) + const struct bin_attribute *bin_attr, char *buf, + loff_t off, size_t count) { struct pci_dev *dev = to_pci_dev(kobj_to_dev(kobj)); struct pci_dev *vpd_dev = dev; @@ -295,8 +295,8 @@ static ssize_t vpd_read(struct file *filp, struct kobject *kobj, } static ssize_t vpd_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, - size_t count) + const struct bin_attribute *bin_attr, char *buf, + loff_t off, size_t count) { struct pci_dev *dev = to_pci_dev(kobj_to_dev(kobj)); struct pci_dev *vpd_dev = dev; @@ -317,9 +317,9 @@ static ssize_t vpd_write(struct file *filp, struct kobject *kobj, return ret; } -static BIN_ATTR(vpd, 0600, vpd_read, vpd_write, 0); +static const BIN_ATTR(vpd, 0600, vpd_read, vpd_write, 0); -static struct bin_attribute *vpd_attrs[] = { +static const struct bin_attribute *const vpd_attrs[] = { &bin_attr_vpd, NULL, }; @@ -336,7 +336,7 @@ static umode_t vpd_attr_is_visible(struct kobject *kobj, } const struct attribute_group pci_dev_vpd_attr_group = { - .bin_attrs = vpd_attrs, + .bin_attrs_new = vpd_attrs, .is_bin_visible = vpd_attr_is_visible, }; diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c index 1d4d01e1275e..06fd317529fc 100644 --- a/drivers/perf/apple_m1_cpu_pmu.c +++ b/drivers/perf/apple_m1_cpu_pmu.c @@ -168,6 +168,8 @@ static const unsigned m1_pmu_perf_map[PERF_COUNT_HW_MAX] = { PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE, [PERF_COUNT_HW_INSTRUCTIONS] = M1_PMU_PERFCTR_INST_ALL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = M1_PMU_PERFCTR_INST_BRANCH, + [PERF_COUNT_HW_BRANCH_MISSES] = M1_PMU_PERFCTR_BRANCH_MISPRED_NONSPEC, }; /* sysfs definitions */ diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index b20fa600e510..ef959e66db7c 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -1713,8 +1713,8 @@ static int arm_cmn_validate_group(struct arm_cmn *cmn, struct perf_event *event) goto done; } - for (i = 0; i < CMN_MAX_DTCS; i++) - if (val->dtc_count[i] == CMN_DT_NUM_COUNTERS) + for_each_hw_dtc_idx(hw, dtc, idx) + if (val->dtc_count[dtc] == CMN_DT_NUM_COUNTERS) goto done; for_each_hw_dn(hw, dn, i) { diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.c b/drivers/perf/arm_cspmu/nvidia_cspmu.c index d0ef611240aa..8116c7846a46 100644 --- a/drivers/perf/arm_cspmu/nvidia_cspmu.c +++ b/drivers/perf/arm_cspmu/nvidia_cspmu.c @@ -54,65 +54,24 @@ static struct attribute *scf_pmu_event_attrs[] = { ARM_CSPMU_EVENT_ATTR(scf_cache_wb, 0xF3), NV_CSPMU_EVENT_ATTR_4(socket, rd_data, 0x101), - NV_CSPMU_EVENT_ATTR_4(socket, dl_rsp, 0x105), NV_CSPMU_EVENT_ATTR_4(socket, wb_data, 0x109), - NV_CSPMU_EVENT_ATTR_4(socket, ev_rsp, 0x10d), - NV_CSPMU_EVENT_ATTR_4(socket, prb_data, 0x111), NV_CSPMU_EVENT_ATTR_4(socket, rd_outstanding, 0x115), - NV_CSPMU_EVENT_ATTR_4(socket, dl_outstanding, 0x119), - NV_CSPMU_EVENT_ATTR_4(socket, wb_outstanding, 0x11d), - NV_CSPMU_EVENT_ATTR_4(socket, wr_outstanding, 0x121), - NV_CSPMU_EVENT_ATTR_4(socket, ev_outstanding, 0x125), - NV_CSPMU_EVENT_ATTR_4(socket, prb_outstanding, 0x129), NV_CSPMU_EVENT_ATTR_4(socket, rd_access, 0x12d), - NV_CSPMU_EVENT_ATTR_4(socket, dl_access, 0x131), NV_CSPMU_EVENT_ATTR_4(socket, wb_access, 0x135), NV_CSPMU_EVENT_ATTR_4(socket, wr_access, 0x139), - NV_CSPMU_EVENT_ATTR_4(socket, ev_access, 0x13d), - NV_CSPMU_EVENT_ATTR_4(socket, prb_access, 0x141), - - NV_CSPMU_EVENT_ATTR_4(ocu, gmem_rd_data, 0x145), - NV_CSPMU_EVENT_ATTR_4(ocu, gmem_rd_access, 0x149), - NV_CSPMU_EVENT_ATTR_4(ocu, gmem_wb_access, 0x14d), - NV_CSPMU_EVENT_ATTR_4(ocu, gmem_rd_outstanding, 0x151), - NV_CSPMU_EVENT_ATTR_4(ocu, gmem_wr_outstanding, 0x155), - - NV_CSPMU_EVENT_ATTR_4(ocu, rem_rd_data, 0x159), - NV_CSPMU_EVENT_ATTR_4(ocu, rem_rd_access, 0x15d), - NV_CSPMU_EVENT_ATTR_4(ocu, rem_wb_access, 0x161), - NV_CSPMU_EVENT_ATTR_4(ocu, rem_rd_outstanding, 0x165), - NV_CSPMU_EVENT_ATTR_4(ocu, rem_wr_outstanding, 0x169), ARM_CSPMU_EVENT_ATTR(gmem_rd_data, 0x16d), ARM_CSPMU_EVENT_ATTR(gmem_rd_access, 0x16e), ARM_CSPMU_EVENT_ATTR(gmem_rd_outstanding, 0x16f), - ARM_CSPMU_EVENT_ATTR(gmem_dl_rsp, 0x170), - ARM_CSPMU_EVENT_ATTR(gmem_dl_access, 0x171), - ARM_CSPMU_EVENT_ATTR(gmem_dl_outstanding, 0x172), ARM_CSPMU_EVENT_ATTR(gmem_wb_data, 0x173), ARM_CSPMU_EVENT_ATTR(gmem_wb_access, 0x174), - ARM_CSPMU_EVENT_ATTR(gmem_wb_outstanding, 0x175), - ARM_CSPMU_EVENT_ATTR(gmem_ev_rsp, 0x176), - ARM_CSPMU_EVENT_ATTR(gmem_ev_access, 0x177), - ARM_CSPMU_EVENT_ATTR(gmem_ev_outstanding, 0x178), ARM_CSPMU_EVENT_ATTR(gmem_wr_data, 0x179), - ARM_CSPMU_EVENT_ATTR(gmem_wr_outstanding, 0x17a), ARM_CSPMU_EVENT_ATTR(gmem_wr_access, 0x17b), NV_CSPMU_EVENT_ATTR_4(socket, wr_data, 0x17c), - NV_CSPMU_EVENT_ATTR_4(ocu, gmem_wr_data, 0x180), - NV_CSPMU_EVENT_ATTR_4(ocu, gmem_wb_data, 0x184), - NV_CSPMU_EVENT_ATTR_4(ocu, gmem_wr_access, 0x188), - NV_CSPMU_EVENT_ATTR_4(ocu, gmem_wb_outstanding, 0x18c), - - NV_CSPMU_EVENT_ATTR_4(ocu, rem_wr_data, 0x190), - NV_CSPMU_EVENT_ATTR_4(ocu, rem_wb_data, 0x194), - NV_CSPMU_EVENT_ATTR_4(ocu, rem_wr_access, 0x198), - NV_CSPMU_EVENT_ATTR_4(ocu, rem_wb_outstanding, 0x19c), - ARM_CSPMU_EVENT_ATTR(gmem_wr_total_bytes, 0x1a0), ARM_CSPMU_EVENT_ATTR(remote_socket_wr_total_bytes, 0x1a1), ARM_CSPMU_EVENT_ATTR(remote_socket_rd_data, 0x1a2), @@ -122,35 +81,12 @@ static struct attribute *scf_pmu_event_attrs[] = { ARM_CSPMU_EVENT_ATTR(cmem_rd_data, 0x1a5), ARM_CSPMU_EVENT_ATTR(cmem_rd_access, 0x1a6), ARM_CSPMU_EVENT_ATTR(cmem_rd_outstanding, 0x1a7), - ARM_CSPMU_EVENT_ATTR(cmem_dl_rsp, 0x1a8), - ARM_CSPMU_EVENT_ATTR(cmem_dl_access, 0x1a9), - ARM_CSPMU_EVENT_ATTR(cmem_dl_outstanding, 0x1aa), ARM_CSPMU_EVENT_ATTR(cmem_wb_data, 0x1ab), ARM_CSPMU_EVENT_ATTR(cmem_wb_access, 0x1ac), - ARM_CSPMU_EVENT_ATTR(cmem_wb_outstanding, 0x1ad), - ARM_CSPMU_EVENT_ATTR(cmem_ev_rsp, 0x1ae), - ARM_CSPMU_EVENT_ATTR(cmem_ev_access, 0x1af), - ARM_CSPMU_EVENT_ATTR(cmem_ev_outstanding, 0x1b0), ARM_CSPMU_EVENT_ATTR(cmem_wr_data, 0x1b1), - ARM_CSPMU_EVENT_ATTR(cmem_wr_outstanding, 0x1b2), - - NV_CSPMU_EVENT_ATTR_4(ocu, cmem_rd_data, 0x1b3), - NV_CSPMU_EVENT_ATTR_4(ocu, cmem_rd_access, 0x1b7), - NV_CSPMU_EVENT_ATTR_4(ocu, cmem_wb_access, 0x1bb), - NV_CSPMU_EVENT_ATTR_4(ocu, cmem_rd_outstanding, 0x1bf), - NV_CSPMU_EVENT_ATTR_4(ocu, cmem_wr_outstanding, 0x1c3), - - ARM_CSPMU_EVENT_ATTR(ocu_prb_access, 0x1c7), - ARM_CSPMU_EVENT_ATTR(ocu_prb_data, 0x1c8), - ARM_CSPMU_EVENT_ATTR(ocu_prb_outstanding, 0x1c9), ARM_CSPMU_EVENT_ATTR(cmem_wr_access, 0x1ca), - NV_CSPMU_EVENT_ATTR_4(ocu, cmem_wr_access, 0x1cb), - NV_CSPMU_EVENT_ATTR_4(ocu, cmem_wb_data, 0x1cf), - NV_CSPMU_EVENT_ATTR_4(ocu, cmem_wr_data, 0x1d3), - NV_CSPMU_EVENT_ATTR_4(ocu, cmem_wb_outstanding, 0x1d7), - ARM_CSPMU_EVENT_ATTR(cmem_wr_total_bytes, 0x1db), ARM_CSPMU_EVENT_ATTR(cycles, ARM_CSPMU_EVT_CYCLES_DEFAULT), @@ -194,6 +130,7 @@ static struct attribute *pcie_pmu_format_attrs[] = { static struct attribute *nvlink_c2c_pmu_format_attrs[] = { ARM_CSPMU_FORMAT_EVENT_ATTR, + ARM_CSPMU_FORMAT_ATTR(port, "config1:0-1"), NULL, }; @@ -238,10 +175,12 @@ static u32 nv_cspmu_event_filter(const struct perf_event *event) const struct nv_cspmu_ctx *ctx = to_nv_cspmu_ctx(to_arm_cspmu(event->pmu)); - if (ctx->filter_mask == 0) + const u32 filter_val = event->attr.config1 & ctx->filter_mask; + + if (filter_val == 0) return ctx->filter_default_val; - return event->attr.config1 & ctx->filter_mask; + return filter_val; } enum nv_cspmu_name_fmt { @@ -274,7 +213,7 @@ static const struct nv_cspmu_match nv_cspmu_match[] = { { .prodid = 0x104, .prodid_mask = NV_PRODID_MASK, - .filter_mask = 0x0, + .filter_mask = NV_NVL_C2C_FILTER_ID_MASK, .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK, .name_pattern = "nvidia_nvlink_c2c1_pmu_%u", .name_fmt = NAME_FMT_SOCKET, @@ -284,7 +223,7 @@ static const struct nv_cspmu_match nv_cspmu_match[] = { { .prodid = 0x105, .prodid_mask = NV_PRODID_MASK, - .filter_mask = 0x0, + .filter_mask = NV_NVL_C2C_FILTER_ID_MASK, .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK, .name_pattern = "nvidia_nvlink_c2c0_pmu_%u", .name_fmt = NAME_FMT_SOCKET, diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index b5cc11abc962..0e360feb3432 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -1279,7 +1279,7 @@ static int armv8pmu_proc_user_access_handler(const struct ctl_table *table, int return 0; } -static struct ctl_table armv8_pmu_sysctl_table[] = { +static const struct ctl_table armv8_pmu_sysctl_table[] = { { .procname = "perf_user_access", .data = &sysctl_perf_user_access, diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index fd5b78732603..f5e6878db9d6 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -85,6 +85,7 @@ struct arm_spe_pmu { #define SPE_PMU_FEAT_LDS (1UL << 4) #define SPE_PMU_FEAT_ERND (1UL << 5) #define SPE_PMU_FEAT_INV_FILT_EVT (1UL << 6) +#define SPE_PMU_FEAT_DISCARD (1UL << 7) #define SPE_PMU_FEAT_DEV_PROBED (1UL << 63) u64 features; @@ -193,6 +194,9 @@ static const struct attribute_group arm_spe_pmu_cap_group = { #define ATTR_CFG_FLD_store_filter_CFG config /* PMSFCR_EL1.ST */ #define ATTR_CFG_FLD_store_filter_LO 34 #define ATTR_CFG_FLD_store_filter_HI 34 +#define ATTR_CFG_FLD_discard_CFG config /* PMBLIMITR_EL1.FM = DISCARD */ +#define ATTR_CFG_FLD_discard_LO 35 +#define ATTR_CFG_FLD_discard_HI 35 #define ATTR_CFG_FLD_event_filter_CFG config1 /* PMSEVFR_EL1 */ #define ATTR_CFG_FLD_event_filter_LO 0 @@ -216,6 +220,7 @@ GEN_PMU_FORMAT_ATTR(store_filter); GEN_PMU_FORMAT_ATTR(event_filter); GEN_PMU_FORMAT_ATTR(inv_event_filter); GEN_PMU_FORMAT_ATTR(min_latency); +GEN_PMU_FORMAT_ATTR(discard); static struct attribute *arm_spe_pmu_formats_attr[] = { &format_attr_ts_enable.attr, @@ -228,6 +233,7 @@ static struct attribute *arm_spe_pmu_formats_attr[] = { &format_attr_event_filter.attr, &format_attr_inv_event_filter.attr, &format_attr_min_latency.attr, + &format_attr_discard.attr, NULL, }; @@ -238,6 +244,9 @@ static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj, struct device *dev = kobj_to_dev(kobj); struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev); + if (attr == &format_attr_discard.attr && !(spe_pmu->features & SPE_PMU_FEAT_DISCARD)) + return 0; + if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT)) return 0; @@ -502,6 +511,12 @@ static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle, u64 base, limit; struct arm_spe_pmu_buf *buf; + if (ATTR_CFG_GET_FLD(&event->attr, discard)) { + limit = FIELD_PREP(PMBLIMITR_EL1_FM, PMBLIMITR_EL1_FM_DISCARD); + limit |= PMBLIMITR_EL1_E; + goto out_write_limit; + } + /* Start a new aux session */ buf = perf_aux_output_begin(handle, event); if (!buf) { @@ -743,6 +758,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event) !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT)) return -EOPNOTSUPP; + if (ATTR_CFG_GET_FLD(&event->attr, discard) && + !(spe_pmu->features & SPE_PMU_FEAT_DISCARD)) + return -EOPNOTSUPP; + set_spe_event_has_cx(event); reg = arm_spe_event_to_pmscr(event); if (reg & (PMSCR_EL1_PA | PMSCR_EL1_PCT)) @@ -1027,6 +1046,9 @@ static void __arm_spe_pmu_dev_probe(void *info) if (FIELD_GET(PMSIDR_EL1_ERND, reg)) spe_pmu->features |= SPE_PMU_FEAT_ERND; + if (spe_pmu->pmsver >= ID_AA64DFR0_EL1_PMSVer_V1P2) + spe_pmu->features |= SPE_PMU_FEAT_DISCARD; + /* This field has a spaced out encoding, so just use a look-up */ fld = FIELD_GET(PMSIDR_EL1_INTERVAL, reg); switch (fld) { diff --git a/drivers/perf/dwc_pcie_pmu.c b/drivers/perf/dwc_pcie_pmu.c index 9cbea9675e21..cccecae9823f 100644 --- a/drivers/perf/dwc_pcie_pmu.c +++ b/drivers/perf/dwc_pcie_pmu.c @@ -20,7 +20,6 @@ #include #include -#define DWC_PCIE_VSEC_RAS_DES_ID 0x02 #define DWC_PCIE_EVENT_CNT_CTL 0x8 /* @@ -100,14 +99,23 @@ struct dwc_pcie_dev_info { struct list_head dev_node; }; -struct dwc_pcie_vendor_id { - int vendor_id; +struct dwc_pcie_pmu_vsec_id { + u16 vendor_id; + u16 vsec_id; + u8 vsec_rev; }; -static const struct dwc_pcie_vendor_id dwc_pcie_vendor_ids[] = { - {.vendor_id = PCI_VENDOR_ID_ALIBABA }, - {.vendor_id = PCI_VENDOR_ID_AMPERE }, - {.vendor_id = PCI_VENDOR_ID_QCOM }, +/* + * VSEC IDs are allocated by the vendor, so a given ID may mean different + * things to different vendors. See PCIe r6.0, sec 7.9.5.2. + */ +static const struct dwc_pcie_pmu_vsec_id dwc_pcie_pmu_vsec_ids[] = { + { .vendor_id = PCI_VENDOR_ID_ALIBABA, + .vsec_id = 0x02, .vsec_rev = 0x4 }, + { .vendor_id = PCI_VENDOR_ID_AMPERE, + .vsec_id = 0x02, .vsec_rev = 0x4 }, + { .vendor_id = PCI_VENDOR_ID_QCOM, + .vsec_id = 0x02, .vsec_rev = 0x4 }, {} /* terminator */ }; @@ -199,8 +207,8 @@ static struct attribute *dwc_pcie_pmu_time_event_attrs[] = { DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L1_1, 0x05), DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L1_2, 0x06), DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(CFG_RCVRY, 0x07), - DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(TX_RX_L0S, 0x08), - DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L1_AUX, 0x09), + DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L1_AUX, 0x08), + DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(TX_RX_L0S, 0x09), /* Group #1 */ DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(tx_pcie_tlp_data_payload, 0x20), @@ -519,31 +527,28 @@ static void dwc_pcie_unregister_pmu(void *data) perf_pmu_unregister(&pcie_pmu->pmu); } -static bool dwc_pcie_match_des_cap(struct pci_dev *pdev) +static u16 dwc_pcie_des_cap(struct pci_dev *pdev) { - const struct dwc_pcie_vendor_id *vid; - u16 vsec = 0; + const struct dwc_pcie_pmu_vsec_id *vid; + u16 vsec; u32 val; if (!pci_is_pcie(pdev) || !(pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT)) - return false; + return 0; - for (vid = dwc_pcie_vendor_ids; vid->vendor_id; vid++) { + for (vid = dwc_pcie_pmu_vsec_ids; vid->vendor_id; vid++) { vsec = pci_find_vsec_capability(pdev, vid->vendor_id, - DWC_PCIE_VSEC_RAS_DES_ID); - if (vsec) - break; + vid->vsec_id); + if (vsec) { + pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, + &val); + if (PCI_VNDR_HEADER_REV(val) == vid->vsec_rev) { + pci_dbg(pdev, "Detected PCIe Vendor-Specific Extended Capability RAS DES\n"); + return vsec; + } + } } - if (!vsec) - return false; - - pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val); - if (PCI_VNDR_HEADER_REV(val) != 0x04) - return false; - - pci_dbg(pdev, - "Detected PCIe Vendor-Specific Extended Capability RAS DES\n"); - return true; + return 0; } static void dwc_pcie_unregister_dev(struct dwc_pcie_dev_info *dev_info) @@ -587,7 +592,7 @@ static int dwc_pcie_pmu_notifier(struct notifier_block *nb, switch (action) { case BUS_NOTIFY_ADD_DEVICE: - if (!dwc_pcie_match_des_cap(pdev)) + if (!dwc_pcie_des_cap(pdev)) return NOTIFY_DONE; if (dwc_pcie_register_dev(pdev)) return NOTIFY_BAD; @@ -612,13 +617,14 @@ static int dwc_pcie_pmu_probe(struct platform_device *plat_dev) struct pci_dev *pdev = plat_dev->dev.platform_data; struct dwc_pcie_pmu *pcie_pmu; char *name; - u32 sbdf, val; + u32 sbdf; u16 vsec; int ret; - vsec = pci_find_vsec_capability(pdev, pdev->vendor, - DWC_PCIE_VSEC_RAS_DES_ID); - pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val); + vsec = dwc_pcie_des_cap(pdev); + if (!vsec) + return -ENODEV; + sbdf = plat_dev->id; name = devm_kasprintf(&plat_dev->dev, GFP_KERNEL, "dwc_rootport_%x", sbdf); if (!name) @@ -730,7 +736,7 @@ static int __init dwc_pcie_pmu_init(void) int ret; for_each_pci_dev(pdev) { - if (!dwc_pcie_match_des_cap(pdev)) + if (!dwc_pcie_des_cap(pdev)) continue; ret = dwc_pcie_register_dev(pdev); diff --git a/drivers/perf/fsl_imx9_ddr_perf.c b/drivers/perf/fsl_imx9_ddr_perf.c index 3c856d9a4e97..843f163e6c33 100644 --- a/drivers/perf/fsl_imx9_ddr_perf.c +++ b/drivers/perf/fsl_imx9_ddr_perf.c @@ -63,8 +63,21 @@ static DEFINE_IDA(ddr_ida); +/* + * V1 support 1 read transaction, 1 write transaction and 1 read beats + * event which corresponding respecitively to counter 2, 3 and 4. + */ +#define DDR_PERF_AXI_FILTER_V1 0x1 + +/* + * V2 support 1 read beats and 3 write beats events which corresponding + * respecitively to counter 2-5. + */ +#define DDR_PERF_AXI_FILTER_V2 0x2 + struct imx_ddr_devtype_data { const char *identifier; /* system PMU identifier for userspace */ + unsigned int filter_ver; /* AXI filter version */ }; struct ddr_pmu { @@ -83,24 +96,27 @@ struct ddr_pmu { static const struct imx_ddr_devtype_data imx91_devtype_data = { .identifier = "imx91", + .filter_ver = DDR_PERF_AXI_FILTER_V1 }; static const struct imx_ddr_devtype_data imx93_devtype_data = { .identifier = "imx93", + .filter_ver = DDR_PERF_AXI_FILTER_V1 }; static const struct imx_ddr_devtype_data imx95_devtype_data = { .identifier = "imx95", + .filter_ver = DDR_PERF_AXI_FILTER_V2 }; -static inline bool is_imx93(struct ddr_pmu *pmu) +static inline bool axi_filter_v1(struct ddr_pmu *pmu) { - return pmu->devtype_data == &imx93_devtype_data; + return pmu->devtype_data->filter_ver == DDR_PERF_AXI_FILTER_V1; } -static inline bool is_imx95(struct ddr_pmu *pmu) +static inline bool axi_filter_v2(struct ddr_pmu *pmu) { - return pmu->devtype_data == &imx95_devtype_data; + return pmu->devtype_data->filter_ver == DDR_PERF_AXI_FILTER_V2; } static const struct of_device_id imx_ddr_pmu_dt_ids[] = { @@ -155,7 +171,7 @@ static const struct attribute_group ddr_perf_cpumask_attr_group = { struct imx9_pmu_events_attr { struct device_attribute attr; u64 id; - const void *devtype_data; + const struct imx_ddr_devtype_data *devtype_data; }; static ssize_t ddr_pmu_event_show(struct device *dev, @@ -307,7 +323,8 @@ ddr_perf_events_attrs_is_visible(struct kobject *kobj, if (!eattr->devtype_data) return attr->mode; - if (eattr->devtype_data != ddr_pmu->devtype_data) + if (eattr->devtype_data != ddr_pmu->devtype_data && + eattr->devtype_data->filter_ver != ddr_pmu->devtype_data->filter_ver) return 0; return attr->mode; @@ -624,11 +641,11 @@ static int ddr_perf_event_add(struct perf_event *event, int flags) hwc->idx = counter; hwc->state |= PERF_HES_STOPPED; - if (is_imx93(pmu)) + if (axi_filter_v1(pmu)) /* read trans, write trans, read beat */ imx93_ddr_perf_monitor_config(pmu, event_id, counter, cfg1, cfg2); - if (is_imx95(pmu)) + if (axi_filter_v2(pmu)) /* write beat, read beat2, read beat1, read beat */ imx95_ddr_perf_monitor_config(pmu, event_id, counter, cfg1, cfg2); diff --git a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c index 3f3fb1de11f5..b879b81adfdd 100644 --- a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c @@ -180,20 +180,18 @@ MODULE_DEVICE_TABLE(acpi, hisi_cpa_pmu_acpi_match); static int hisi_cpa_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *cpa_pmu) { - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &cpa_pmu->sicl_id)) { + hisi_uncore_pmu_init_topology(cpa_pmu, &pdev->dev); + + if (cpa_pmu->topo.sicl_id < 0) { dev_err(&pdev->dev, "Can not read sicl-id\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id", - &cpa_pmu->index_id)) { + if (cpa_pmu->topo.index_id < 0) { dev_err(&pdev->dev, "Cannot read idx-id\n"); return -EINVAL; } - cpa_pmu->ccl_id = -1; - cpa_pmu->sccl_id = -1; cpa_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(cpa_pmu->base)) return PTR_ERR(cpa_pmu->base); @@ -227,34 +225,11 @@ static const struct attribute_group hisi_cpa_pmu_events_group = { .attrs = hisi_cpa_pmu_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_cpa_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL -}; - -static const struct attribute_group hisi_cpa_pmu_cpumask_attr_group = { - .attrs = hisi_cpa_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_cpa_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_cpa_pmu_identifier_attrs[] = { - &hisi_cpa_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_cpa_pmu_identifier_group = { - .attrs = hisi_cpa_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_cpa_pmu_attr_groups[] = { &hisi_cpa_pmu_format_group, &hisi_cpa_pmu_events_group, - &hisi_cpa_pmu_cpumask_attr_group, - &hisi_cpa_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -311,8 +286,8 @@ static int hisi_cpa_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_cpa%u", - cpa_pmu->sicl_id, cpa_pmu->index_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_cpa%d", + cpa_pmu->topo.sicl_id, cpa_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -389,6 +364,7 @@ static void __exit hisi_cpa_pmu_module_exit(void) } module_exit(hisi_cpa_pmu_module_exit); +MODULE_IMPORT_NS("HISI_PMU"); MODULE_DESCRIPTION("HiSilicon SoC CPA PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Qi Liu "); diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c index a6ebf2ec99d3..7e490f8868f2 100644 --- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -111,14 +111,14 @@ static void hisi_ddrc_pmu_v2_write_counter(struct hisi_pmu *ddrc_pmu, * so there is no need to write event type, while it is programmable counter in * PMU v2. */ -static void hisi_ddrc_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx, +static void hisi_ddrc_pmu_write_evtype(struct hisi_pmu *ddrc_pmu, int idx, u32 type) { u32 offset; - if (hha_pmu->identifier >= HISI_PMU_V2) { + if (ddrc_pmu->identifier >= HISI_PMU_V2) { offset = DDRC_V2_EVENT_TYPE + 4 * idx; - writel(type, hha_pmu->base + offset); + writel(type, ddrc_pmu->base + offset); } } @@ -297,23 +297,22 @@ MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match); static int hisi_ddrc_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *ddrc_pmu) { + hisi_uncore_pmu_init_topology(ddrc_pmu, &pdev->dev); + /* * Use the SCCL_ID and DDRC channel ID to identify the * DDRC PMU, while SCCL_ID is in MPIDR[aff2]. */ if (device_property_read_u32(&pdev->dev, "hisilicon,ch-id", - &ddrc_pmu->index_id)) { + &ddrc_pmu->topo.index_id)) { dev_err(&pdev->dev, "Can not read ddrc channel-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &ddrc_pmu->sccl_id)) { + if (ddrc_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Can not read ddrc sccl-id!\n"); return -EINVAL; } - /* DDRC PMUs only share the same SCCL */ - ddrc_pmu->ccl_id = -1; ddrc_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ddrc_pmu->base)) { @@ -323,8 +322,7 @@ static int hisi_ddrc_pmu_init_data(struct platform_device *pdev, ddrc_pmu->identifier = readl(ddrc_pmu->base + DDRC_VERSION); if (ddrc_pmu->identifier >= HISI_PMU_V2) { - if (device_property_read_u32(&pdev->dev, "hisilicon,sub-id", - &ddrc_pmu->sub_id)) { + if (ddrc_pmu->topo.sub_id < 0) { dev_err(&pdev->dev, "Can not read sub-id!\n"); return -EINVAL; } @@ -382,42 +380,19 @@ static const struct attribute_group hisi_ddrc_pmu_v2_events_group = { .attrs = hisi_ddrc_pmu_v2_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_ddrc_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static const struct attribute_group hisi_ddrc_pmu_cpumask_attr_group = { - .attrs = hisi_ddrc_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_ddrc_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_ddrc_pmu_identifier_attrs[] = { - &hisi_ddrc_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_ddrc_pmu_identifier_group = { - .attrs = hisi_ddrc_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_ddrc_pmu_v1_attr_groups[] = { &hisi_ddrc_pmu_v1_format_group, &hisi_ddrc_pmu_v1_events_group, - &hisi_ddrc_pmu_cpumask_attr_group, - &hisi_ddrc_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL, }; static const struct attribute_group *hisi_ddrc_pmu_v2_attr_groups[] = { &hisi_ddrc_pmu_v2_format_group, &hisi_ddrc_pmu_v2_events_group, - &hisi_ddrc_pmu_cpumask_attr_group, - &hisi_ddrc_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -501,13 +476,13 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev) if (ddrc_pmu->identifier >= HISI_PMU_V2) name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "hisi_sccl%u_ddrc%u_%u", - ddrc_pmu->sccl_id, ddrc_pmu->index_id, - ddrc_pmu->sub_id); + "hisi_sccl%d_ddrc%d_%d", + ddrc_pmu->topo.sccl_id, ddrc_pmu->topo.index_id, + ddrc_pmu->topo.sub_id); else name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "hisi_sccl%u_ddrc%u", ddrc_pmu->sccl_id, - ddrc_pmu->index_id); + "hisi_sccl%d_ddrc%d", ddrc_pmu->topo.sccl_id, + ddrc_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -575,10 +550,10 @@ static void __exit hisi_ddrc_pmu_module_exit(void) { platform_driver_unregister(&hisi_ddrc_pmu_driver); cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE); - } module_exit(hisi_ddrc_pmu_module_exit); +MODULE_IMPORT_NS("HISI_PMU"); MODULE_DESCRIPTION("HiSilicon SoC DDRC uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Shaokun Zhang "); diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c index 32624872596f..ca609db86046 100644 --- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c @@ -295,12 +295,13 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev, unsigned long long id; acpi_status status; + hisi_uncore_pmu_init_topology(hha_pmu, &pdev->dev); + /* * Use SCCL_ID and UID to identify the HHA PMU, while * SCCL_ID is in MPIDR[aff2]. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &hha_pmu->sccl_id)) { + if (hha_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Can not read hha sccl-id!\n"); return -EINVAL; } @@ -309,8 +310,7 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev, * Early versions of BIOS support _UID by mistake, so we support * both "hisilicon, idx-id" as preference, if available. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id", - &hha_pmu->index_id)) { + if (hha_pmu->topo.index_id < 0) { status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), "_UID", NULL, &id); if (ACPI_FAILURE(status)) { @@ -318,10 +318,8 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev, return -EINVAL; } - hha_pmu->index_id = id; + hha_pmu->topo.index_id = id; } - /* HHA PMUs only share the same SCCL */ - hha_pmu->ccl_id = -1; hha_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(hha_pmu->base)) { @@ -407,42 +405,19 @@ static const struct attribute_group hisi_hha_pmu_v2_events_group = { .attrs = hisi_hha_pmu_v2_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_hha_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static const struct attribute_group hisi_hha_pmu_cpumask_attr_group = { - .attrs = hisi_hha_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_hha_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_hha_pmu_identifier_attrs[] = { - &hisi_hha_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_hha_pmu_identifier_group = { - .attrs = hisi_hha_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_hha_pmu_v1_attr_groups[] = { &hisi_hha_pmu_v1_format_group, &hisi_hha_pmu_v1_events_group, - &hisi_hha_pmu_cpumask_attr_group, - &hisi_hha_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL, }; static const struct attribute_group *hisi_hha_pmu_v2_attr_groups[] = { &hisi_hha_pmu_v2_format_group, &hisi_hha_pmu_v2_events_group, - &hisi_hha_pmu_cpumask_attr_group, - &hisi_hha_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -510,8 +485,8 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u", - hha_pmu->sccl_id, hha_pmu->index_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_hha%d", + hha_pmu->topo.sccl_id, hha_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -581,6 +556,7 @@ static void __exit hisi_hha_pmu_module_exit(void) } module_exit(hisi_hha_pmu_module_exit); +MODULE_IMPORT_NS("HISI_PMU"); MODULE_DESCRIPTION("HiSilicon SoC HHA uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Shaokun Zhang "); diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c index c235b46ce873..412fc3a97963 100644 --- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c @@ -355,18 +355,18 @@ MODULE_DEVICE_TABLE(acpi, hisi_l3c_pmu_acpi_match); static int hisi_l3c_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *l3c_pmu) { + hisi_uncore_pmu_init_topology(l3c_pmu, &pdev->dev); + /* * Use the SCCL_ID and CCL_ID to identify the L3C PMU, while * SCCL_ID is in MPIDR[aff2] and CCL_ID is in MPIDR[aff1]. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &l3c_pmu->sccl_id)) { + if (l3c_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Can not read l3c sccl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,ccl-id", - &l3c_pmu->ccl_id)) { + if (l3c_pmu->topo.ccl_id < 0) { dev_err(&pdev->dev, "Can not read l3c ccl-id!\n"); return -EINVAL; } @@ -441,42 +441,19 @@ static const struct attribute_group hisi_l3c_pmu_v2_events_group = { .attrs = hisi_l3c_pmu_v2_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_l3c_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static const struct attribute_group hisi_l3c_pmu_cpumask_attr_group = { - .attrs = hisi_l3c_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_l3c_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_l3c_pmu_identifier_attrs[] = { - &hisi_l3c_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_l3c_pmu_identifier_group = { - .attrs = hisi_l3c_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_l3c_pmu_v1_attr_groups[] = { &hisi_l3c_pmu_v1_format_group, &hisi_l3c_pmu_v1_events_group, - &hisi_l3c_pmu_cpumask_attr_group, - &hisi_l3c_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL, }; static const struct attribute_group *hisi_l3c_pmu_v2_attr_groups[] = { &hisi_l3c_pmu_v2_format_group, &hisi_l3c_pmu_v2_events_group, - &hisi_l3c_pmu_cpumask_attr_group, - &hisi_l3c_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -544,8 +521,8 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u", - l3c_pmu->sccl_id, l3c_pmu->ccl_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_l3c%d", + l3c_pmu->topo.sccl_id, l3c_pmu->topo.ccl_id); if (!name) return -ENOMEM; @@ -615,6 +592,7 @@ static void __exit hisi_l3c_pmu_module_exit(void) } module_exit(hisi_l3c_pmu_module_exit); +MODULE_IMPORT_NS("HISI_PMU"); MODULE_DESCRIPTION("HiSilicon SoC L3C uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Anurup M "); diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c index c0f5d7c73e06..a0142684e379 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c @@ -269,25 +269,22 @@ static void hisi_pa_pmu_clear_int_status(struct hisi_pmu *pa_pmu, int idx) static int hisi_pa_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *pa_pmu) { + hisi_uncore_pmu_init_topology(pa_pmu, &pdev->dev); + /* * As PA PMU is in a SICL, use the SICL_ID and the index ID * to identify the PA PMU. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &pa_pmu->sicl_id)) { + if (pa_pmu->topo.sicl_id < 0) { dev_err(&pdev->dev, "Cannot read sicl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id", - &pa_pmu->index_id)) { + if (pa_pmu->topo.index_id < 0) { dev_err(&pdev->dev, "Cannot read idx-id!\n"); return -EINVAL; } - pa_pmu->ccl_id = -1; - pa_pmu->sccl_id = -1; - pa_pmu->dev_info = device_get_match_data(&pdev->dev); if (!pa_pmu->dev_info) return -ENODEV; @@ -356,29 +353,6 @@ static const struct attribute_group hisi_h60pa_pmu_events_group = { .attrs = hisi_h60pa_pmu_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_pa_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL -}; - -static const struct attribute_group hisi_pa_pmu_cpumask_attr_group = { - .attrs = hisi_pa_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_pa_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_pa_pmu_identifier_attrs[] = { - &hisi_pa_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_pa_pmu_identifier_group = { - .attrs = hisi_pa_pmu_identifier_attrs, -}; - static struct hisi_pa_pmu_int_regs hisi_pa_pmu_regs = { .mask_offset = PA_INT_MASK, .clear_offset = PA_INT_CLEAR, @@ -388,8 +362,8 @@ static struct hisi_pa_pmu_int_regs hisi_pa_pmu_regs = { static const struct attribute_group *hisi_pa_pmu_v2_attr_groups[] = { &hisi_pa_pmu_v2_format_group, &hisi_pa_pmu_v2_events_group, - &hisi_pa_pmu_cpumask_attr_group, - &hisi_pa_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -402,8 +376,8 @@ static const struct hisi_pmu_dev_info hisi_h32pa_v2 = { static const struct attribute_group *hisi_pa_pmu_v3_attr_groups[] = { &hisi_pa_pmu_v2_format_group, &hisi_pa_pmu_v3_events_group, - &hisi_pa_pmu_cpumask_attr_group, - &hisi_pa_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -422,8 +396,8 @@ static struct hisi_pa_pmu_int_regs hisi_h60pa_pmu_regs = { static const struct attribute_group *hisi_h60pa_pmu_attr_groups[] = { &hisi_pa_pmu_v2_format_group, &hisi_h60pa_pmu_events_group, - &hisi_pa_pmu_cpumask_attr_group, - &hisi_pa_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -488,9 +462,9 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_%s%u", - pa_pmu->sicl_id, pa_pmu->dev_info->name, - pa_pmu->index_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_%s%d", + pa_pmu->topo.sicl_id, pa_pmu->dev_info->name, + pa_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -569,6 +543,7 @@ static void __exit hisi_pa_pmu_module_exit(void) } module_exit(hisi_pa_pmu_module_exit); +MODULE_IMPORT_NS("HISI_PMU"); MODULE_DESCRIPTION("HiSilicon Protocol Adapter uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Shaokun Zhang "); diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c index 918cdc31de57..ef058b1dd509 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -34,7 +35,7 @@ ssize_t hisi_event_sysfs_show(struct device *dev, return sysfs_emit(page, "config=0x%lx\n", (unsigned long)eattr->var); } -EXPORT_SYMBOL_GPL(hisi_event_sysfs_show); +EXPORT_SYMBOL_NS_GPL(hisi_event_sysfs_show, "HISI_PMU"); /* * sysfs cpumask attributes. For uncore PMU, we only have a single CPU to show @@ -46,7 +47,52 @@ ssize_t hisi_cpumask_sysfs_show(struct device *dev, return sysfs_emit(buf, "%d\n", hisi_pmu->on_cpu); } -EXPORT_SYMBOL_GPL(hisi_cpumask_sysfs_show); +EXPORT_SYMBOL_NS_GPL(hisi_cpumask_sysfs_show, "HISI_PMU"); + +static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); + +static ssize_t hisi_associated_cpus_sysfs_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev)); + + return cpumap_print_to_pagebuf(true, buf, &hisi_pmu->associated_cpus); +} +static DEVICE_ATTR(associated_cpus, 0444, hisi_associated_cpus_sysfs_show, NULL); + +static struct attribute *hisi_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + &dev_attr_associated_cpus.attr, + NULL +}; + +const struct attribute_group hisi_pmu_cpumask_attr_group = { + .attrs = hisi_pmu_cpumask_attrs, +}; +EXPORT_SYMBOL_NS_GPL(hisi_pmu_cpumask_attr_group, "HISI_PMU"); + +ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev)); + + return sysfs_emit(page, "0x%08x\n", hisi_pmu->identifier); +} +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_identifier_attr_show, "HISI_PMU"); + +static struct device_attribute hisi_pmu_identifier_attr = + __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); + +static struct attribute *hisi_pmu_identifier_attrs[] = { + &hisi_pmu_identifier_attr.attr, + NULL +}; + +const struct attribute_group hisi_pmu_identifier_group = { + .attrs = hisi_pmu_identifier_attrs, +}; +EXPORT_SYMBOL_NS_GPL(hisi_pmu_identifier_group, "HISI_PMU"); static bool hisi_validate_event_group(struct perf_event *event) { @@ -96,17 +142,7 @@ int hisi_uncore_pmu_get_event_idx(struct perf_event *event) return idx; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_get_event_idx); - -ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev, - struct device_attribute *attr, - char *page) -{ - struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev)); - - return sysfs_emit(page, "0x%08x\n", hisi_pmu->identifier); -} -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_identifier_attr_show); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_get_event_idx, "HISI_PMU"); static void hisi_uncore_pmu_clear_event_idx(struct hisi_pmu *hisi_pmu, int idx) { @@ -165,7 +201,7 @@ int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu, return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_init_irq); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_init_irq, "HISI_PMU"); int hisi_uncore_pmu_event_init(struct perf_event *event) { @@ -219,7 +255,7 @@ int hisi_uncore_pmu_event_init(struct perf_event *event) return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_event_init); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_event_init, "HISI_PMU"); /* * Set the counter to count the event that we're interested in, @@ -273,7 +309,7 @@ void hisi_uncore_pmu_set_event_period(struct perf_event *event) /* Write start value to the hardware event counter */ hisi_pmu->ops->write_counter(hisi_pmu, hwc, val); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_set_event_period); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_set_event_period, "HISI_PMU"); void hisi_uncore_pmu_event_update(struct perf_event *event) { @@ -294,7 +330,7 @@ void hisi_uncore_pmu_event_update(struct perf_event *event) HISI_MAX_PERIOD(hisi_pmu->counter_bits); local64_add(delta, &event->count); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_event_update); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_event_update, "HISI_PMU"); void hisi_uncore_pmu_start(struct perf_event *event, int flags) { @@ -317,7 +353,7 @@ void hisi_uncore_pmu_start(struct perf_event *event, int flags) hisi_uncore_pmu_enable_event(event); perf_event_update_userpage(event); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_start); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_start, "HISI_PMU"); void hisi_uncore_pmu_stop(struct perf_event *event, int flags) { @@ -334,7 +370,7 @@ void hisi_uncore_pmu_stop(struct perf_event *event, int flags) hisi_uncore_pmu_event_update(event); hwc->state |= PERF_HES_UPTODATE; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_stop); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_stop, "HISI_PMU"); int hisi_uncore_pmu_add(struct perf_event *event, int flags) { @@ -357,7 +393,7 @@ int hisi_uncore_pmu_add(struct perf_event *event, int flags) return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_add); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_add, "HISI_PMU"); void hisi_uncore_pmu_del(struct perf_event *event, int flags) { @@ -369,14 +405,14 @@ void hisi_uncore_pmu_del(struct perf_event *event, int flags) perf_event_update_userpage(event); hisi_pmu->pmu_events.hw_events[hwc->idx] = NULL; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_del); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_del, "HISI_PMU"); void hisi_uncore_pmu_read(struct perf_event *event) { /* Read hardware counter and update the perf counter statistics */ hisi_uncore_pmu_event_update(event); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_read); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_read, "HISI_PMU"); void hisi_uncore_pmu_enable(struct pmu *pmu) { @@ -389,7 +425,7 @@ void hisi_uncore_pmu_enable(struct pmu *pmu) hisi_pmu->ops->start_counters(hisi_pmu); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_enable); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_enable, "HISI_PMU"); void hisi_uncore_pmu_disable(struct pmu *pmu) { @@ -397,7 +433,7 @@ void hisi_uncore_pmu_disable(struct pmu *pmu) hisi_pmu->ops->stop_counters(hisi_pmu); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_disable); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_disable, "HISI_PMU"); /* @@ -444,22 +480,19 @@ static void hisi_read_sccl_and_ccl_id(int *scclp, int *cclp) */ static bool hisi_pmu_cpu_is_associated_pmu(struct hisi_pmu *hisi_pmu) { + struct hisi_pmu_topology *topo = &hisi_pmu->topo; int sccl_id, ccl_id; - /* If SCCL_ID is -1, the PMU is in a SICL and has no CPU affinity */ - if (hisi_pmu->sccl_id == -1) - return true; - - if (hisi_pmu->ccl_id == -1) { + if (topo->ccl_id == -1) { /* If CCL_ID is -1, the PMU only shares the same SCCL */ hisi_read_sccl_and_ccl_id(&sccl_id, NULL); - return sccl_id == hisi_pmu->sccl_id; + return sccl_id == topo->sccl_id; } hisi_read_sccl_and_ccl_id(&sccl_id, &ccl_id); - return sccl_id == hisi_pmu->sccl_id && ccl_id == hisi_pmu->ccl_id; + return sccl_id == topo->sccl_id && ccl_id == topo->ccl_id; } int hisi_uncore_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) @@ -467,13 +500,25 @@ int hisi_uncore_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) struct hisi_pmu *hisi_pmu = hlist_entry_safe(node, struct hisi_pmu, node); - if (!hisi_pmu_cpu_is_associated_pmu(hisi_pmu)) + /* + * If the CPU is not associated to PMU, initialize the hisi_pmu->on_cpu + * based on the locality if it hasn't been initialized yet. For PMUs + * do have associated CPUs, it'll be updated later. + */ + if (!hisi_pmu_cpu_is_associated_pmu(hisi_pmu)) { + if (hisi_pmu->on_cpu != -1) + return 0; + + hisi_pmu->on_cpu = cpumask_local_spread(0, dev_to_node(hisi_pmu->dev)); + WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(hisi_pmu->on_cpu))); return 0; + } cpumask_set_cpu(cpu, &hisi_pmu->associated_cpus); - /* If another CPU is already managing this PMU, simply return. */ - if (hisi_pmu->on_cpu != -1) + /* If another associated CPU is already managing this PMU, simply return. */ + if (hisi_pmu->on_cpu != -1 && + cpumask_test_cpu(hisi_pmu->on_cpu, &hisi_pmu->associated_cpus)) return 0; /* Use this CPU in cpumask for event counting */ @@ -484,7 +529,7 @@ int hisi_uncore_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_online_cpu); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_online_cpu, "HISI_PMU"); int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) { @@ -492,9 +537,6 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) node); unsigned int target; - if (!cpumask_test_and_clear_cpu(cpu, &hisi_pmu->associated_cpus)) - return 0; - /* Nothing to do if this CPU doesn't own the PMU */ if (hisi_pmu->on_cpu != cpu) return 0; @@ -502,9 +544,16 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) /* Give up ownership of the PMU */ hisi_pmu->on_cpu = -1; - /* Choose a new CPU to migrate ownership of the PMU to */ + /* + * Migrate ownership of the PMU to a new CPU chosen from PMU's online + * associated CPUs if possible, if no associated CPU online then + * migrate to one online CPU. + */ target = cpumask_any_and_but(&hisi_pmu->associated_cpus, cpu_online_mask, cpu); + if (target >= nr_cpu_ids) + target = cpumask_any_but(cpu_online_mask, cpu); + if (target >= nr_cpu_ids) return 0; @@ -515,7 +564,36 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_offline_cpu); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_offline_cpu, "HISI_PMU"); + +/* + * Retrieve the topology information from the firmware for the hisi_pmu device. + * The topology ID will be -1 if we cannot initialize it, it may either due to + * the PMU doesn't locate on this certain topology or the firmware needs to be + * fixed. + */ +void hisi_uncore_pmu_init_topology(struct hisi_pmu *hisi_pmu, struct device *dev) +{ + struct hisi_pmu_topology *topo = &hisi_pmu->topo; + + topo->sccl_id = -1; + topo->ccl_id = -1; + topo->index_id = -1; + topo->sub_id = -1; + + if (device_property_read_u32(dev, "hisilicon,scl-id", &topo->sccl_id)) + dev_dbg(dev, "no scl-id present\n"); + + if (device_property_read_u32(dev, "hisilicon,ccl-id", &topo->ccl_id)) + dev_dbg(dev, "no ccl-id present\n"); + + if (device_property_read_u32(dev, "hisilicon,idx-id", &topo->index_id)) + dev_dbg(dev, "no idx-id present\n"); + + if (device_property_read_u32(dev, "hisilicon,sub-id", &topo->sub_id)) + dev_dbg(dev, "no sub-id present\n"); +} +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_init_topology, "HISI_PMU"); void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module) { @@ -535,7 +613,7 @@ void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module) pmu->attr_groups = hisi_pmu->pmu_events.attr_groups; pmu->capabilities = PERF_PMU_CAP_NO_EXCLUDE; } -EXPORT_SYMBOL_GPL(hisi_pmu_init); +EXPORT_SYMBOL_NS_GPL(hisi_pmu_init, "HISI_PMU"); MODULE_DESCRIPTION("HiSilicon SoC uncore Performance Monitor driver framework"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h index 25b2d43b72bf..f4fed2544877 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.h +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h @@ -81,27 +81,55 @@ struct hisi_pmu_hwevents { const struct attribute_group **attr_groups; }; +/** + * struct hisi_pmu_topology - Describe the topology hierarchy on which the PMU + * is located. + * @sccl_id: ID of the SCCL on which the PMU locate is located. + * @sicl_id: ID of the SICL on which the PMU locate is located. + * @scl_id: ID used by the core which is unaware of the SCCL/SICL. + * @ccl_id: ID of the CCL (CPU cluster) on which the PMU is located. + * @index_id: the ID of the PMU module if there're several PMUs at a + * particularly location in the topology. + * @sub_id: submodule ID of the PMU. For example we use this for DDRC PMU v2 + * since each DDRC has more than one DMC + * + * The ID will be -1 if the PMU isn't located on a certain topology. + */ +struct hisi_pmu_topology { + /* + * SCCL (Super CPU CLuster) and SICL (Super I/O Cluster) are parallel + * so a PMU cannot locate on a SCCL and a SICL. If the SCCL/SICL + * distinction is not relevant, use scl_id instead. + */ + union { + int sccl_id; + int sicl_id; + int scl_id; + }; + int ccl_id; + int index_id; + int sub_id; +}; + /* Generic pmu struct for different pmu types */ struct hisi_pmu { struct pmu pmu; const struct hisi_uncore_ops *ops; const struct hisi_pmu_dev_info *dev_info; struct hisi_pmu_hwevents pmu_events; - /* associated_cpus: All CPUs associated with the PMU */ + struct hisi_pmu_topology topo; + /* + * CPUs associated to the PMU and are preferred to use for counting. + * Could be empty if PMU has no association (e.g. PMU on SICL), in + * which case any online CPU will be used. + */ cpumask_t associated_cpus; /* CPU used for counting */ int on_cpu; int irq; struct device *dev; struct hlist_node node; - int sccl_id; - int sicl_id; - int ccl_id; void __iomem *base; - /* the ID of the PMU modules */ - u32 index_id; - /* For DDRC PMU v2: each DDRC has more than one DMC */ - u32 sub_id; int num_counters; int counter_bits; /* check event code range */ @@ -109,6 +137,10 @@ struct hisi_pmu { u32 identifier; }; +/* Generic implementation of cpumask/identifier group */ +extern const struct attribute_group hisi_pmu_cpumask_attr_group; +extern const struct attribute_group hisi_pmu_identifier_group; + int hisi_uncore_pmu_get_event_idx(struct perf_event *event); void hisi_uncore_pmu_read(struct perf_event *event); int hisi_uncore_pmu_add(struct perf_event *event, int flags); @@ -132,6 +164,7 @@ ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev, char *page); int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu, struct platform_device *pdev); +void hisi_uncore_pmu_init_topology(struct hisi_pmu *hisi_pmu, struct device *dev); void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module); #endif /* __HISI_UNCORE_PMU_H__ */ diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c index c5f4764ee888..dbd079016fc4 100644 --- a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c @@ -288,25 +288,22 @@ MODULE_DEVICE_TABLE(acpi, hisi_sllc_pmu_acpi_match); static int hisi_sllc_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *sllc_pmu) { + hisi_uncore_pmu_init_topology(sllc_pmu, &pdev->dev); + /* * Use the SCCL_ID and the index ID to identify the SLLC PMU, * while SCCL_ID is from MPIDR_EL1 by CPU. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &sllc_pmu->sccl_id)) { + if (sllc_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Cannot read sccl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id", - &sllc_pmu->index_id)) { + if (sllc_pmu->topo.index_id < 0) { dev_err(&pdev->dev, "Cannot read idx-id!\n"); return -EINVAL; } - /* SLLC PMUs only share the same SCCL */ - sllc_pmu->ccl_id = -1; - sllc_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(sllc_pmu->base)) { dev_err(&pdev->dev, "ioremap failed for sllc_pmu resource.\n"); @@ -347,34 +344,11 @@ static const struct attribute_group hisi_sllc_pmu_v2_events_group = { .attrs = hisi_sllc_pmu_v2_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_sllc_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL -}; - -static const struct attribute_group hisi_sllc_pmu_cpumask_attr_group = { - .attrs = hisi_sllc_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_sllc_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_sllc_pmu_identifier_attrs[] = { - &hisi_sllc_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_sllc_pmu_identifier_group = { - .attrs = hisi_sllc_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_sllc_pmu_v2_attr_groups[] = { &hisi_sllc_pmu_v2_format_group, &hisi_sllc_pmu_v2_events_group, - &hisi_sllc_pmu_cpumask_attr_group, - &hisi_sllc_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -433,8 +407,8 @@ static int hisi_sllc_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_sllc%u", - sllc_pmu->sccl_id, sllc_pmu->index_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_sllc%d", + sllc_pmu->topo.sccl_id, sllc_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -507,6 +481,7 @@ static void __exit hisi_sllc_pmu_module_exit(void) } module_exit(hisi_sllc_pmu_module_exit); +MODULE_IMPORT_NS("HISI_PMU"); MODULE_DESCRIPTION("HiSilicon SLLC uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Shaokun Zhang "); diff --git a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c index 481dcc9e8fbf..03cb9b564b99 100644 --- a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c @@ -11,7 +11,6 @@ #include #include #include -#include #include "hisi_uncore_pmu.h" @@ -366,25 +365,24 @@ static void hisi_uc_pmu_clear_int_status(struct hisi_pmu *uc_pmu, int idx) static int hisi_uc_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *uc_pmu) { + hisi_uncore_pmu_init_topology(uc_pmu, &pdev->dev); + /* * Use SCCL (Super CPU Cluster) ID and CCL (CPU Cluster) ID to * identify the topology information of UC PMU devices in the chip. * They have some CCLs per SCCL and then 4 UC PMU per CCL. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &uc_pmu->sccl_id)) { + if (uc_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Can not read uc sccl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,ccl-id", - &uc_pmu->ccl_id)) { + if (uc_pmu->topo.ccl_id < 0) { dev_err(&pdev->dev, "Can not read uc ccl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,sub-id", - &uc_pmu->sub_id)) { + if (uc_pmu->topo.sub_id < 0) { dev_err(&pdev->dev, "Can not read sub-id!\n"); return -EINVAL; } @@ -439,34 +437,11 @@ static const struct attribute_group hisi_uc_pmu_events_group = { .attrs = hisi_uc_pmu_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_uc_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static const struct attribute_group hisi_uc_pmu_cpumask_attr_group = { - .attrs = hisi_uc_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_uc_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_uc_pmu_identifier_attrs[] = { - &hisi_uc_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_uc_pmu_identifier_group = { - .attrs = hisi_uc_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_uc_pmu_attr_groups[] = { &hisi_uc_pmu_format_group, &hisi_uc_pmu_events_group, - &hisi_uc_pmu_cpumask_attr_group, - &hisi_uc_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -538,8 +513,9 @@ static int hisi_uc_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_uc%d_%u", - uc_pmu->sccl_id, uc_pmu->ccl_id, uc_pmu->sub_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_uc%d_%d", + uc_pmu->topo.sccl_id, uc_pmu->topo.ccl_id, + uc_pmu->topo.sub_id); if (!name) return -ENOMEM; @@ -613,6 +589,7 @@ static void __exit hisi_uc_pmu_module_exit(void) } module_exit(hisi_uc_pmu_module_exit); +MODULE_IMPORT_NS("HISI_PMU"); MODULE_DESCRIPTION("HiSilicon SoC UC uncore PMU driver"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Junhao He "); diff --git a/drivers/perf/marvell_cn10k_ddr_pmu.c b/drivers/perf/marvell_cn10k_ddr_pmu.c index 8860d9f687ae..039feded9152 100644 --- a/drivers/perf/marvell_cn10k_ddr_pmu.c +++ b/drivers/perf/marvell_cn10k_ddr_pmu.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -/* Marvell CN10K DRAM Subsystem (DSS) Performance Monitor Driver +/* + * Marvell CN10K DRAM Subsystem (DSS) Performance Monitor Driver * - * Copyright (C) 2021 Marvell. + * Copyright (C) 2021-2024 Marvell. */ #include @@ -14,24 +15,29 @@ #include /* Performance Counters Operating Mode Control Registers */ -#define DDRC_PERF_CNT_OP_MODE_CTRL 0x8020 -#define OP_MODE_CTRL_VAL_MANNUAL 0x1 +#define CN10K_DDRC_PERF_CNT_OP_MODE_CTRL 0x8020 +#define ODY_DDRC_PERF_CNT_OP_MODE_CTRL 0x20020 +#define OP_MODE_CTRL_VAL_MANUAL 0x1 /* Performance Counters Start Operation Control Registers */ -#define DDRC_PERF_CNT_START_OP_CTRL 0x8028 +#define CN10K_DDRC_PERF_CNT_START_OP_CTRL 0x8028 +#define ODY_DDRC_PERF_CNT_START_OP_CTRL 0x200A0 #define START_OP_CTRL_VAL_START 0x1ULL #define START_OP_CTRL_VAL_ACTIVE 0x2 /* Performance Counters End Operation Control Registers */ -#define DDRC_PERF_CNT_END_OP_CTRL 0x8030 +#define CN10K_DDRC_PERF_CNT_END_OP_CTRL 0x8030 +#define ODY_DDRC_PERF_CNT_END_OP_CTRL 0x200E0 #define END_OP_CTRL_VAL_END 0x1ULL /* Performance Counters End Status Registers */ -#define DDRC_PERF_CNT_END_STATUS 0x8038 +#define CN10K_DDRC_PERF_CNT_END_STATUS 0x8038 +#define ODY_DDRC_PERF_CNT_END_STATUS 0x20120 #define END_STATUS_VAL_END_TIMER_MODE_END 0x1 /* Performance Counters Configuration Registers */ -#define DDRC_PERF_CFG_BASE 0x8040 +#define CN10K_DDRC_PERF_CFG_BASE 0x8040 +#define ODY_DDRC_PERF_CFG_BASE 0x20160 /* 8 Generic event counter + 2 fixed event counters */ #define DDRC_PERF_NUM_GEN_COUNTERS 8 @@ -42,18 +48,28 @@ DDRC_PERF_NUM_FIX_COUNTERS) /* Generic event counter registers */ -#define DDRC_PERF_CFG(n) (DDRC_PERF_CFG_BASE + 8 * (n)) +#define DDRC_PERF_CFG(base, n) ((base) + 8 * (n)) #define EVENT_ENABLE BIT_ULL(63) /* Two dedicated event counters for DDR reads and writes */ #define EVENT_DDR_READS 101 #define EVENT_DDR_WRITES 100 +#define DDRC_PERF_REG(base, n) ((base) + 8 * (n)) /* * programmable events IDs in programmable event counters. * DO NOT change these event-id numbers, they are used to * program event bitmap in h/w. */ +#define EVENT_DFI_CMD_IS_RETRY 61 +#define EVENT_RD_UC_ECC_ERROR 60 +#define EVENT_RD_CRC_ERROR 59 +#define EVENT_CAPAR_ERROR 58 +#define EVENT_WR_CRC_ERROR 57 +#define EVENT_DFI_PARITY_POISON 56 +#define EVENT_RETRY_FIFO_FULL 46 +#define EVENT_DFI_CYCLES 45 + #define EVENT_OP_IS_ZQLATCH 55 #define EVENT_OP_IS_ZQSTART 54 #define EVENT_OP_IS_TCR_MRR 53 @@ -102,28 +118,37 @@ #define EVENT_HIF_RD_OR_WR 1 /* Event counter value registers */ -#define DDRC_PERF_CNT_VALUE_BASE 0x8080 -#define DDRC_PERF_CNT_VALUE(n) (DDRC_PERF_CNT_VALUE_BASE + 8 * (n)) +#define CN10K_DDRC_PERF_CNT_VALUE_BASE 0x8080 +#define ODY_DDRC_PERF_CNT_VALUE_BASE 0x201C0 /* Fixed event counter enable/disable register */ -#define DDRC_PERF_CNT_FREERUN_EN 0x80C0 +#define CN10K_DDRC_PERF_CNT_FREERUN_EN 0x80C0 #define DDRC_PERF_FREERUN_WRITE_EN 0x1 #define DDRC_PERF_FREERUN_READ_EN 0x2 /* Fixed event counter control register */ -#define DDRC_PERF_CNT_FREERUN_CTRL 0x80C8 +#define CN10K_DDRC_PERF_CNT_FREERUN_CTRL 0x80C8 +#define ODY_DDRC_PERF_CNT_FREERUN_CTRL 0x20240 #define DDRC_FREERUN_WRITE_CNT_CLR 0x1 #define DDRC_FREERUN_READ_CNT_CLR 0x2 -/* Fixed event counter value register */ -#define DDRC_PERF_CNT_VALUE_WR_OP 0x80D0 -#define DDRC_PERF_CNT_VALUE_RD_OP 0x80D8 +/* Fixed event counter clear register, defined only for Odyssey */ +#define ODY_DDRC_PERF_CNT_FREERUN_CLR 0x20248 + #define DDRC_PERF_CNT_VALUE_OVERFLOW BIT_ULL(48) #define DDRC_PERF_CNT_MAX_VALUE GENMASK_ULL(48, 0) +/* Fixed event counter value register */ +#define CN10K_DDRC_PERF_CNT_VALUE_WR_OP 0x80D0 +#define CN10K_DDRC_PERF_CNT_VALUE_RD_OP 0x80D8 +#define ODY_DDRC_PERF_CNT_VALUE_WR_OP 0x20250 +#define ODY_DDRC_PERF_CNT_VALUE_RD_OP 0x20258 + struct cn10k_ddr_pmu { struct pmu pmu; void __iomem *base; + const struct ddr_pmu_platform_data *p_data; + const struct ddr_pmu_ops *ops; unsigned int cpu; struct device *dev; int active_events; @@ -132,8 +157,36 @@ struct cn10k_ddr_pmu { struct hlist_node node; }; +struct ddr_pmu_ops { + void (*enable_read_freerun_counter)(struct cn10k_ddr_pmu *pmu, + bool enable); + void (*enable_write_freerun_counter)(struct cn10k_ddr_pmu *pmu, + bool enable); + void (*clear_read_freerun_counter)(struct cn10k_ddr_pmu *pmu); + void (*clear_write_freerun_counter)(struct cn10k_ddr_pmu *pmu); + void (*pmu_overflow_handler)(struct cn10k_ddr_pmu *pmu, int evt_idx); +}; + #define to_cn10k_ddr_pmu(p) container_of(p, struct cn10k_ddr_pmu, pmu) +struct ddr_pmu_platform_data { + u64 counter_overflow_val; + u64 counter_max_val; + u64 cnt_base; + u64 cfg_base; + u64 cnt_op_mode_ctrl; + u64 cnt_start_op_ctrl; + u64 cnt_end_op_ctrl; + u64 cnt_end_status; + u64 cnt_freerun_en; + u64 cnt_freerun_ctrl; + u64 cnt_freerun_clr; + u64 cnt_value_wr_op; + u64 cnt_value_rd_op; + bool is_cn10k; + bool is_ody; +}; + static ssize_t cn10k_ddr_pmu_event_show(struct device *dev, struct device_attribute *attr, char *page) @@ -209,6 +262,85 @@ static struct attribute *cn10k_ddr_perf_events_attrs[] = { NULL }; +static struct attribute *odyssey_ddr_perf_events_attrs[] = { + /* Programmable */ + CN10K_DDR_PMU_EVENT_ATTR(ddr_hif_rd_or_wr_access, EVENT_HIF_RD_OR_WR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_hif_wr_access, EVENT_HIF_WR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_hif_rd_access, EVENT_HIF_RD), + CN10K_DDR_PMU_EVENT_ATTR(ddr_hif_rmw_access, EVENT_HIF_RMW), + CN10K_DDR_PMU_EVENT_ATTR(ddr_hif_pri_rdaccess, EVENT_HIF_HI_PRI_RD), + CN10K_DDR_PMU_EVENT_ATTR(ddr_rd_bypass_access, EVENT_READ_BYPASS), + CN10K_DDR_PMU_EVENT_ATTR(ddr_act_bypass_access, EVENT_ACT_BYPASS), + CN10K_DDR_PMU_EVENT_ATTR(ddr_dfi_wr_data_access, + EVENT_DFI_WR_DATA_CYCLES), + CN10K_DDR_PMU_EVENT_ATTR(ddr_dfi_rd_data_access, + EVENT_DFI_RD_DATA_CYCLES), + CN10K_DDR_PMU_EVENT_ATTR(ddr_hpri_sched_rd_crit_access, + EVENT_HPR_XACT_WHEN_CRITICAL), + CN10K_DDR_PMU_EVENT_ATTR(ddr_lpri_sched_rd_crit_access, + EVENT_LPR_XACT_WHEN_CRITICAL), + CN10K_DDR_PMU_EVENT_ATTR(ddr_wr_trxn_crit_access, + EVENT_WR_XACT_WHEN_CRITICAL), + CN10K_DDR_PMU_EVENT_ATTR(ddr_cam_active_access, EVENT_OP_IS_ACTIVATE), + CN10K_DDR_PMU_EVENT_ATTR(ddr_cam_rd_or_wr_access, + EVENT_OP_IS_RD_OR_WR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_cam_rd_active_access, + EVENT_OP_IS_RD_ACTIVATE), + CN10K_DDR_PMU_EVENT_ATTR(ddr_cam_read, EVENT_OP_IS_RD), + CN10K_DDR_PMU_EVENT_ATTR(ddr_cam_write, EVENT_OP_IS_WR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_cam_mwr, EVENT_OP_IS_MWR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_precharge, EVENT_OP_IS_PRECHARGE), + CN10K_DDR_PMU_EVENT_ATTR(ddr_precharge_for_rdwr, + EVENT_PRECHARGE_FOR_RDWR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_precharge_for_other, + EVENT_PRECHARGE_FOR_OTHER), + CN10K_DDR_PMU_EVENT_ATTR(ddr_rdwr_transitions, EVENT_RDWR_TRANSITIONS), + CN10K_DDR_PMU_EVENT_ATTR(ddr_write_combine, EVENT_WRITE_COMBINE), + CN10K_DDR_PMU_EVENT_ATTR(ddr_war_hazard, EVENT_WAR_HAZARD), + CN10K_DDR_PMU_EVENT_ATTR(ddr_raw_hazard, EVENT_RAW_HAZARD), + CN10K_DDR_PMU_EVENT_ATTR(ddr_waw_hazard, EVENT_WAW_HAZARD), + CN10K_DDR_PMU_EVENT_ATTR(ddr_enter_selfref, EVENT_OP_IS_ENTER_SELFREF), + CN10K_DDR_PMU_EVENT_ATTR(ddr_enter_powerdown, + EVENT_OP_IS_ENTER_POWERDOWN), + CN10K_DDR_PMU_EVENT_ATTR(ddr_enter_mpsm, EVENT_OP_IS_ENTER_MPSM), + CN10K_DDR_PMU_EVENT_ATTR(ddr_refresh, EVENT_OP_IS_REFRESH), + CN10K_DDR_PMU_EVENT_ATTR(ddr_crit_ref, EVENT_OP_IS_CRIT_REF), + CN10K_DDR_PMU_EVENT_ATTR(ddr_spec_ref, EVENT_OP_IS_SPEC_REF), + CN10K_DDR_PMU_EVENT_ATTR(ddr_load_mode, EVENT_OP_IS_LOAD_MODE), + CN10K_DDR_PMU_EVENT_ATTR(ddr_zqcl, EVENT_OP_IS_ZQCL), + CN10K_DDR_PMU_EVENT_ATTR(ddr_cam_wr_access, EVENT_OP_IS_ZQCS), + CN10K_DDR_PMU_EVENT_ATTR(ddr_dfi_cycles, EVENT_DFI_CYCLES), + CN10K_DDR_PMU_EVENT_ATTR(ddr_retry_fifo_full, + EVENT_RETRY_FIFO_FULL), + CN10K_DDR_PMU_EVENT_ATTR(ddr_bsm_alloc, EVENT_BSM_ALLOC), + CN10K_DDR_PMU_EVENT_ATTR(ddr_bsm_starvation, EVENT_BSM_STARVATION), + CN10K_DDR_PMU_EVENT_ATTR(ddr_win_limit_reached_rd, + EVENT_VISIBLE_WIN_LIMIT_REACHED_RD), + CN10K_DDR_PMU_EVENT_ATTR(ddr_win_limit_reached_wr, + EVENT_VISIBLE_WIN_LIMIT_REACHED_WR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_dqsosc_mpc, EVENT_OP_IS_DQSOSC_MPC), + CN10K_DDR_PMU_EVENT_ATTR(ddr_dqsosc_mrr, EVENT_OP_IS_DQSOSC_MRR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_tcr_mrr, EVENT_OP_IS_TCR_MRR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_zqstart, EVENT_OP_IS_ZQSTART), + CN10K_DDR_PMU_EVENT_ATTR(ddr_zqlatch, EVENT_OP_IS_ZQLATCH), + CN10K_DDR_PMU_EVENT_ATTR(ddr_dfi_parity_poison, + EVENT_DFI_PARITY_POISON), + CN10K_DDR_PMU_EVENT_ATTR(ddr_wr_crc_error, EVENT_WR_CRC_ERROR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_capar_error, EVENT_CAPAR_ERROR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_rd_crc_error, EVENT_RD_CRC_ERROR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_rd_uc_ecc_error, EVENT_RD_UC_ECC_ERROR), + CN10K_DDR_PMU_EVENT_ATTR(ddr_dfi_cmd_is_retry, EVENT_DFI_CMD_IS_RETRY), + /* Free run event counters */ + CN10K_DDR_PMU_EVENT_ATTR(ddr_ddr_reads, EVENT_DDR_READS), + CN10K_DDR_PMU_EVENT_ATTR(ddr_ddr_writes, EVENT_DDR_WRITES), + NULL +}; + +static struct attribute_group odyssey_ddr_perf_events_attr_group = { + .name = "events", + .attrs = odyssey_ddr_perf_events_attrs, +}; + static struct attribute_group cn10k_ddr_perf_events_attr_group = { .name = "events", .attrs = cn10k_ddr_perf_events_attrs, @@ -254,6 +386,13 @@ static const struct attribute_group *cn10k_attr_groups[] = { NULL, }; +static const struct attribute_group *odyssey_attr_groups[] = { + &odyssey_ddr_perf_events_attr_group, + &cn10k_ddr_perf_format_attr_group, + &cn10k_ddr_perf_cpumask_attr_group, + NULL +}; + /* Default poll timeout is 100 sec, which is very sufficient for * 48 bit counter incremented max at 5.6 GT/s, which may take many * hours to overflow. @@ -266,9 +405,18 @@ static ktime_t cn10k_ddr_pmu_timer_period(void) return ms_to_ktime((u64)cn10k_ddr_pmu_poll_period_sec * USEC_PER_SEC); } -static int ddr_perf_get_event_bitmap(int eventid, u64 *event_bitmap) +static int ddr_perf_get_event_bitmap(int eventid, u64 *event_bitmap, + struct cn10k_ddr_pmu *ddr_pmu) { + int err = 0; + switch (eventid) { + case EVENT_DFI_PARITY_POISON ...EVENT_DFI_CMD_IS_RETRY: + if (!ddr_pmu->p_data->is_ody) { + err = -EINVAL; + break; + } + fallthrough; case EVENT_HIF_RD_OR_WR ... EVENT_WAW_HAZARD: case EVENT_OP_IS_REFRESH ... EVENT_OP_IS_ZQLATCH: *event_bitmap = (1ULL << (eventid - 1)); @@ -279,11 +427,12 @@ static int ddr_perf_get_event_bitmap(int eventid, u64 *event_bitmap) *event_bitmap = (0xFULL << (eventid - 1)); break; default: - pr_err("%s Invalid eventid %d\n", __func__, eventid); - return -EINVAL; + err = -EINVAL; } - return 0; + if (err) + pr_err("%s Invalid eventid %d\n", __func__, eventid); + return err; } static int cn10k_ddr_perf_alloc_counter(struct cn10k_ddr_pmu *pmu, @@ -351,9 +500,33 @@ static int cn10k_ddr_perf_event_init(struct perf_event *event) return 0; } +static void cn10k_ddr_perf_counter_start(struct cn10k_ddr_pmu *ddr_pmu, + int counter) +{ + const struct ddr_pmu_platform_data *p_data = ddr_pmu->p_data; + u64 ctrl_reg = p_data->cnt_start_op_ctrl; + + writeq_relaxed(START_OP_CTRL_VAL_START, ddr_pmu->base + + DDRC_PERF_REG(ctrl_reg, counter)); +} + +static void cn10k_ddr_perf_counter_stop(struct cn10k_ddr_pmu *ddr_pmu, + int counter) +{ + const struct ddr_pmu_platform_data *p_data = ddr_pmu->p_data; + u64 ctrl_reg = p_data->cnt_end_op_ctrl; + + writeq_relaxed(END_OP_CTRL_VAL_END, ddr_pmu->base + + DDRC_PERF_REG(ctrl_reg, counter)); +} + static void cn10k_ddr_perf_counter_enable(struct cn10k_ddr_pmu *pmu, int counter, bool enable) { + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + u64 ctrl_reg = pmu->p_data->cnt_op_mode_ctrl; + const struct ddr_pmu_ops *ops = pmu->ops; + bool is_ody = pmu->p_data->is_ody; u32 reg; u64 val; @@ -363,7 +536,7 @@ static void cn10k_ddr_perf_counter_enable(struct cn10k_ddr_pmu *pmu, } if (counter < DDRC_PERF_NUM_GEN_COUNTERS) { - reg = DDRC_PERF_CFG(counter); + reg = DDRC_PERF_CFG(p_data->cfg_base, counter); val = readq_relaxed(pmu->base + reg); if (enable) @@ -372,40 +545,52 @@ static void cn10k_ddr_perf_counter_enable(struct cn10k_ddr_pmu *pmu, val &= ~EVENT_ENABLE; writeq_relaxed(val, pmu->base + reg); - } else { - val = readq_relaxed(pmu->base + DDRC_PERF_CNT_FREERUN_EN); - if (enable) { - if (counter == DDRC_PERF_READ_COUNTER_IDX) - val |= DDRC_PERF_FREERUN_READ_EN; - else - val |= DDRC_PERF_FREERUN_WRITE_EN; - } else { - if (counter == DDRC_PERF_READ_COUNTER_IDX) - val &= ~DDRC_PERF_FREERUN_READ_EN; - else - val &= ~DDRC_PERF_FREERUN_WRITE_EN; + + if (is_ody) { + if (enable) { + /* + * Setup the PMU counter to work in + * manual mode + */ + reg = DDRC_PERF_REG(ctrl_reg, counter); + writeq_relaxed(OP_MODE_CTRL_VAL_MANUAL, + pmu->base + reg); + + cn10k_ddr_perf_counter_start(pmu, counter); + } else { + cn10k_ddr_perf_counter_stop(pmu, counter); + } } - writeq_relaxed(val, pmu->base + DDRC_PERF_CNT_FREERUN_EN); + } else { + if (counter == DDRC_PERF_READ_COUNTER_IDX) + ops->enable_read_freerun_counter(pmu, enable); + else + ops->enable_write_freerun_counter(pmu, enable); } } static u64 cn10k_ddr_perf_read_counter(struct cn10k_ddr_pmu *pmu, int counter) { + const struct ddr_pmu_platform_data *p_data = pmu->p_data; u64 val; if (counter == DDRC_PERF_READ_COUNTER_IDX) - return readq_relaxed(pmu->base + DDRC_PERF_CNT_VALUE_RD_OP); + return readq_relaxed(pmu->base + + p_data->cnt_value_rd_op); if (counter == DDRC_PERF_WRITE_COUNTER_IDX) - return readq_relaxed(pmu->base + DDRC_PERF_CNT_VALUE_WR_OP); + return readq_relaxed(pmu->base + + p_data->cnt_value_wr_op); - val = readq_relaxed(pmu->base + DDRC_PERF_CNT_VALUE(counter)); + val = readq_relaxed(pmu->base + + DDRC_PERF_REG(p_data->cnt_base, counter)); return val; } static void cn10k_ddr_perf_event_update(struct perf_event *event) { struct cn10k_ddr_pmu *pmu = to_cn10k_ddr_pmu(event->pmu); + const struct ddr_pmu_platform_data *p_data = pmu->p_data; struct hw_perf_event *hwc = &event->hw; u64 prev_count, new_count, mask; @@ -414,7 +599,7 @@ static void cn10k_ddr_perf_event_update(struct perf_event *event) new_count = cn10k_ddr_perf_read_counter(pmu, hwc->idx); } while (local64_xchg(&hwc->prev_count, new_count) != prev_count); - mask = DDRC_PERF_CNT_MAX_VALUE; + mask = p_data->counter_max_val; local64_add((new_count - prev_count) & mask, &event->count); } @@ -435,6 +620,8 @@ static void cn10k_ddr_perf_event_start(struct perf_event *event, int flags) static int cn10k_ddr_perf_event_add(struct perf_event *event, int flags) { struct cn10k_ddr_pmu *pmu = to_cn10k_ddr_pmu(event->pmu); + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + const struct ddr_pmu_ops *ops = pmu->ops; struct hw_perf_event *hwc = &event->hw; u8 config = event->attr.config; int counter, ret; @@ -454,8 +641,8 @@ static int cn10k_ddr_perf_event_add(struct perf_event *event, int flags) if (counter < DDRC_PERF_NUM_GEN_COUNTERS) { /* Generic counters, configure event id */ - reg_offset = DDRC_PERF_CFG(counter); - ret = ddr_perf_get_event_bitmap(config, &val); + reg_offset = DDRC_PERF_CFG(p_data->cfg_base, counter); + ret = ddr_perf_get_event_bitmap(config, &val, pmu); if (ret) return ret; @@ -463,11 +650,9 @@ static int cn10k_ddr_perf_event_add(struct perf_event *event, int flags) } else { /* fixed event counter, clear counter value */ if (counter == DDRC_PERF_READ_COUNTER_IDX) - val = DDRC_FREERUN_READ_CNT_CLR; + ops->clear_read_freerun_counter(pmu); else - val = DDRC_FREERUN_WRITE_CNT_CLR; - - writeq_relaxed(val, pmu->base + DDRC_PERF_CNT_FREERUN_CTRL); + ops->clear_write_freerun_counter(pmu); } hwc->state |= PERF_HES_STOPPED; @@ -512,17 +697,19 @@ static void cn10k_ddr_perf_event_del(struct perf_event *event, int flags) static void cn10k_ddr_perf_pmu_enable(struct pmu *pmu) { struct cn10k_ddr_pmu *ddr_pmu = to_cn10k_ddr_pmu(pmu); + const struct ddr_pmu_platform_data *p_data = ddr_pmu->p_data; writeq_relaxed(START_OP_CTRL_VAL_START, ddr_pmu->base + - DDRC_PERF_CNT_START_OP_CTRL); + p_data->cnt_start_op_ctrl); } static void cn10k_ddr_perf_pmu_disable(struct pmu *pmu) { struct cn10k_ddr_pmu *ddr_pmu = to_cn10k_ddr_pmu(pmu); + const struct ddr_pmu_platform_data *p_data = ddr_pmu->p_data; writeq_relaxed(END_OP_CTRL_VAL_END, ddr_pmu->base + - DDRC_PERF_CNT_END_OP_CTRL); + p_data->cnt_end_op_ctrl); } static void cn10k_ddr_perf_event_update_all(struct cn10k_ddr_pmu *pmu) @@ -547,8 +734,123 @@ static void cn10k_ddr_perf_event_update_all(struct cn10k_ddr_pmu *pmu) } } +static void ddr_pmu_enable_read_freerun(struct cn10k_ddr_pmu *pmu, bool enable) +{ + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + u64 val; + + val = readq_relaxed(pmu->base + p_data->cnt_freerun_en); + if (enable) + val |= DDRC_PERF_FREERUN_READ_EN; + else + val &= ~DDRC_PERF_FREERUN_READ_EN; + + writeq_relaxed(val, pmu->base + p_data->cnt_freerun_en); +} + +static void ddr_pmu_enable_write_freerun(struct cn10k_ddr_pmu *pmu, bool enable) +{ + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + u64 val; + + val = readq_relaxed(pmu->base + p_data->cnt_freerun_en); + if (enable) + val |= DDRC_PERF_FREERUN_WRITE_EN; + else + val &= ~DDRC_PERF_FREERUN_WRITE_EN; + + writeq_relaxed(val, pmu->base + p_data->cnt_freerun_en); +} + +static void ddr_pmu_read_clear_freerun(struct cn10k_ddr_pmu *pmu) +{ + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + u64 val; + + val = DDRC_FREERUN_READ_CNT_CLR; + writeq_relaxed(val, pmu->base + p_data->cnt_freerun_ctrl); +} + +static void ddr_pmu_write_clear_freerun(struct cn10k_ddr_pmu *pmu) +{ + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + u64 val; + + val = DDRC_FREERUN_WRITE_CNT_CLR; + writeq_relaxed(val, pmu->base + p_data->cnt_freerun_ctrl); +} + +static void ddr_pmu_overflow_hander(struct cn10k_ddr_pmu *pmu, int evt_idx) +{ + cn10k_ddr_perf_event_update_all(pmu); + cn10k_ddr_perf_pmu_disable(&pmu->pmu); + cn10k_ddr_perf_pmu_enable(&pmu->pmu); +} + +static void ddr_pmu_ody_enable_read_freerun(struct cn10k_ddr_pmu *pmu, + bool enable) +{ + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + u64 val; + + val = readq_relaxed(pmu->base + p_data->cnt_freerun_ctrl); + if (enable) + val |= DDRC_PERF_FREERUN_READ_EN; + else + val &= ~DDRC_PERF_FREERUN_READ_EN; + + writeq_relaxed(val, pmu->base + p_data->cnt_freerun_ctrl); +} + +static void ddr_pmu_ody_enable_write_freerun(struct cn10k_ddr_pmu *pmu, + bool enable) +{ + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + u64 val; + + val = readq_relaxed(pmu->base + p_data->cnt_freerun_ctrl); + if (enable) + val |= DDRC_PERF_FREERUN_WRITE_EN; + else + val &= ~DDRC_PERF_FREERUN_WRITE_EN; + + writeq_relaxed(val, pmu->base + p_data->cnt_freerun_ctrl); +} + +static void ddr_pmu_ody_read_clear_freerun(struct cn10k_ddr_pmu *pmu) +{ + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + u64 val; + + val = DDRC_FREERUN_READ_CNT_CLR; + writeq_relaxed(val, pmu->base + p_data->cnt_freerun_clr); +} + +static void ddr_pmu_ody_write_clear_freerun(struct cn10k_ddr_pmu *pmu) +{ + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + u64 val; + + val = DDRC_FREERUN_WRITE_CNT_CLR; + writeq_relaxed(val, pmu->base + p_data->cnt_freerun_clr); +} + +static void ddr_pmu_ody_overflow_hander(struct cn10k_ddr_pmu *pmu, int evt_idx) +{ + /* + * On reaching the maximum value of the counter, the counter freezes + * there. The particular event is updated and the respective counter + * is stopped and started again so that it starts counting from zero + */ + cn10k_ddr_perf_event_update(pmu->events[evt_idx]); + cn10k_ddr_perf_counter_stop(pmu, evt_idx); + cn10k_ddr_perf_counter_start(pmu, evt_idx); +} + static irqreturn_t cn10k_ddr_pmu_overflow_handler(struct cn10k_ddr_pmu *pmu) { + const struct ddr_pmu_platform_data *p_data = pmu->p_data; + const struct ddr_pmu_ops *ops = pmu->ops; struct perf_event *event; struct hw_perf_event *hwc; u64 prev_count, new_count; @@ -586,11 +888,9 @@ static irqreturn_t cn10k_ddr_pmu_overflow_handler(struct cn10k_ddr_pmu *pmu) continue; value = cn10k_ddr_perf_read_counter(pmu, i); - if (value == DDRC_PERF_CNT_MAX_VALUE) { + if (value == p_data->counter_max_val) { pr_info("Counter-(%d) reached max value\n", i); - cn10k_ddr_perf_event_update_all(pmu); - cn10k_ddr_perf_pmu_disable(&pmu->pmu); - cn10k_ddr_perf_pmu_enable(&pmu->pmu); + ops->pmu_overflow_handler(pmu, i); } } @@ -629,11 +929,68 @@ static int cn10k_ddr_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) return 0; } +static const struct ddr_pmu_ops ddr_pmu_ops = { + .enable_read_freerun_counter = ddr_pmu_enable_read_freerun, + .enable_write_freerun_counter = ddr_pmu_enable_write_freerun, + .clear_read_freerun_counter = ddr_pmu_read_clear_freerun, + .clear_write_freerun_counter = ddr_pmu_write_clear_freerun, + .pmu_overflow_handler = ddr_pmu_overflow_hander, +}; + +#if defined(CONFIG_ACPI) || defined(CONFIG_OF) +static const struct ddr_pmu_platform_data cn10k_ddr_pmu_pdata = { + .counter_overflow_val = BIT_ULL(48), + .counter_max_val = GENMASK_ULL(48, 0), + .cnt_base = CN10K_DDRC_PERF_CNT_VALUE_BASE, + .cfg_base = CN10K_DDRC_PERF_CFG_BASE, + .cnt_op_mode_ctrl = CN10K_DDRC_PERF_CNT_OP_MODE_CTRL, + .cnt_start_op_ctrl = CN10K_DDRC_PERF_CNT_START_OP_CTRL, + .cnt_end_op_ctrl = CN10K_DDRC_PERF_CNT_END_OP_CTRL, + .cnt_end_status = CN10K_DDRC_PERF_CNT_END_STATUS, + .cnt_freerun_en = CN10K_DDRC_PERF_CNT_FREERUN_EN, + .cnt_freerun_ctrl = CN10K_DDRC_PERF_CNT_FREERUN_CTRL, + .cnt_freerun_clr = 0, + .cnt_value_wr_op = CN10K_DDRC_PERF_CNT_VALUE_WR_OP, + .cnt_value_rd_op = CN10K_DDRC_PERF_CNT_VALUE_RD_OP, + .is_cn10k = TRUE, +}; +#endif + +static const struct ddr_pmu_ops ddr_pmu_ody_ops = { + .enable_read_freerun_counter = ddr_pmu_ody_enable_read_freerun, + .enable_write_freerun_counter = ddr_pmu_ody_enable_write_freerun, + .clear_read_freerun_counter = ddr_pmu_ody_read_clear_freerun, + .clear_write_freerun_counter = ddr_pmu_ody_write_clear_freerun, + .pmu_overflow_handler = ddr_pmu_ody_overflow_hander, +}; + +#ifdef CONFIG_ACPI +static const struct ddr_pmu_platform_data odyssey_ddr_pmu_pdata = { + .counter_overflow_val = 0, + .counter_max_val = GENMASK_ULL(63, 0), + .cnt_base = ODY_DDRC_PERF_CNT_VALUE_BASE, + .cfg_base = ODY_DDRC_PERF_CFG_BASE, + .cnt_op_mode_ctrl = ODY_DDRC_PERF_CNT_OP_MODE_CTRL, + .cnt_start_op_ctrl = ODY_DDRC_PERF_CNT_START_OP_CTRL, + .cnt_end_op_ctrl = ODY_DDRC_PERF_CNT_END_OP_CTRL, + .cnt_end_status = ODY_DDRC_PERF_CNT_END_STATUS, + .cnt_freerun_en = 0, + .cnt_freerun_ctrl = ODY_DDRC_PERF_CNT_FREERUN_CTRL, + .cnt_freerun_clr = ODY_DDRC_PERF_CNT_FREERUN_CLR, + .cnt_value_wr_op = ODY_DDRC_PERF_CNT_VALUE_WR_OP, + .cnt_value_rd_op = ODY_DDRC_PERF_CNT_VALUE_RD_OP, + .is_ody = TRUE, +}; +#endif + static int cn10k_ddr_perf_probe(struct platform_device *pdev) { + const struct ddr_pmu_platform_data *dev_data; struct cn10k_ddr_pmu *ddr_pmu; struct resource *res; void __iomem *base; + bool is_cn10k; + bool is_ody; char *name; int ret; @@ -644,30 +1001,60 @@ static int cn10k_ddr_perf_probe(struct platform_device *pdev) ddr_pmu->dev = &pdev->dev; platform_set_drvdata(pdev, ddr_pmu); + dev_data = device_get_match_data(&pdev->dev); + if (!dev_data) { + dev_err(&pdev->dev, "Error: No device match data found\n"); + return -ENODEV; + } + base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(base)) return PTR_ERR(base); ddr_pmu->base = base; - /* Setup the PMU counter to work in manual mode */ - writeq_relaxed(OP_MODE_CTRL_VAL_MANNUAL, ddr_pmu->base + - DDRC_PERF_CNT_OP_MODE_CTRL); + ddr_pmu->p_data = dev_data; + is_cn10k = ddr_pmu->p_data->is_cn10k; + is_ody = ddr_pmu->p_data->is_ody; - ddr_pmu->pmu = (struct pmu) { - .module = THIS_MODULE, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, - .task_ctx_nr = perf_invalid_context, - .attr_groups = cn10k_attr_groups, - .event_init = cn10k_ddr_perf_event_init, - .add = cn10k_ddr_perf_event_add, - .del = cn10k_ddr_perf_event_del, - .start = cn10k_ddr_perf_event_start, - .stop = cn10k_ddr_perf_event_stop, - .read = cn10k_ddr_perf_event_update, - .pmu_enable = cn10k_ddr_perf_pmu_enable, - .pmu_disable = cn10k_ddr_perf_pmu_disable, - }; + if (is_cn10k) { + ddr_pmu->ops = &ddr_pmu_ops; + /* Setup the PMU counter to work in manual mode */ + writeq_relaxed(OP_MODE_CTRL_VAL_MANUAL, ddr_pmu->base + + ddr_pmu->p_data->cnt_op_mode_ctrl); + + ddr_pmu->pmu = (struct pmu) { + .module = THIS_MODULE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .task_ctx_nr = perf_invalid_context, + .attr_groups = cn10k_attr_groups, + .event_init = cn10k_ddr_perf_event_init, + .add = cn10k_ddr_perf_event_add, + .del = cn10k_ddr_perf_event_del, + .start = cn10k_ddr_perf_event_start, + .stop = cn10k_ddr_perf_event_stop, + .read = cn10k_ddr_perf_event_update, + .pmu_enable = cn10k_ddr_perf_pmu_enable, + .pmu_disable = cn10k_ddr_perf_pmu_disable, + }; + } + + if (is_ody) { + ddr_pmu->ops = &ddr_pmu_ody_ops; + + ddr_pmu->pmu = (struct pmu) { + .module = THIS_MODULE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .task_ctx_nr = perf_invalid_context, + .attr_groups = odyssey_attr_groups, + .event_init = cn10k_ddr_perf_event_init, + .add = cn10k_ddr_perf_event_add, + .del = cn10k_ddr_perf_event_del, + .start = cn10k_ddr_perf_event_start, + .stop = cn10k_ddr_perf_event_stop, + .read = cn10k_ddr_perf_event_update, + }; + } /* Choose this cpu to collect perf data */ ddr_pmu->cpu = raw_smp_processor_id(); @@ -688,7 +1075,7 @@ static int cn10k_ddr_perf_probe(struct platform_device *pdev) if (ret) goto error; - pr_info("CN10K DDR PMU Driver for ddrc@%llx\n", res->start); + pr_info("DDR PMU Driver for ddrc@%llx\n", res->start); return 0; error: cpuhp_state_remove_instance_nocalls( @@ -710,7 +1097,7 @@ static void cn10k_ddr_perf_remove(struct platform_device *pdev) #ifdef CONFIG_OF static const struct of_device_id cn10k_ddr_pmu_of_match[] = { - { .compatible = "marvell,cn10k-ddr-pmu", }, + { .compatible = "marvell,cn10k-ddr-pmu", .data = &cn10k_ddr_pmu_pdata }, { }, }; MODULE_DEVICE_TABLE(of, cn10k_ddr_pmu_of_match); @@ -718,7 +1105,8 @@ MODULE_DEVICE_TABLE(of, cn10k_ddr_pmu_of_match); #ifdef CONFIG_ACPI static const struct acpi_device_id cn10k_ddr_pmu_acpi_match[] = { - {"MRVL000A", 0}, + {"MRVL000A", (kernel_ulong_t)&cn10k_ddr_pmu_pdata }, + {"MRVL000C", (kernel_ulong_t)&odyssey_ddr_pmu_pdata}, {}, }; MODULE_DEVICE_TABLE(acpi, cn10k_ddr_pmu_acpi_match); diff --git a/drivers/perf/marvell_cn10k_tad_pmu.c b/drivers/perf/marvell_cn10k_tad_pmu.c index cda55ee35eee..51ccb0befa05 100644 --- a/drivers/perf/marvell_cn10k_tad_pmu.c +++ b/drivers/perf/marvell_cn10k_tad_pmu.c @@ -37,6 +37,15 @@ struct tad_pmu { DECLARE_BITMAP(counters_map, TAD_MAX_COUNTERS); }; +enum mrvl_tad_pmu_version { + TAD_PMU_V1 = 1, + TAD_PMU_V2, +}; + +struct tad_pmu_data { + int id; +}; + static int tad_pmu_cpuhp_state; static void tad_pmu_event_counter_read(struct perf_event *event) @@ -214,6 +223,24 @@ static const struct attribute_group tad_pmu_events_attr_group = { .attrs = tad_pmu_event_attrs, }; +static struct attribute *ody_tad_pmu_event_attrs[] = { + TAD_PMU_EVENT_ATTR(tad_req_msh_in_exlmn, 0x3), + TAD_PMU_EVENT_ATTR(tad_alloc_dtg, 0x1a), + TAD_PMU_EVENT_ATTR(tad_alloc_ltg, 0x1b), + TAD_PMU_EVENT_ATTR(tad_alloc_any, 0x1c), + TAD_PMU_EVENT_ATTR(tad_hit_dtg, 0x1d), + TAD_PMU_EVENT_ATTR(tad_hit_ltg, 0x1e), + TAD_PMU_EVENT_ATTR(tad_hit_any, 0x1f), + TAD_PMU_EVENT_ATTR(tad_tag_rd, 0x20), + TAD_PMU_EVENT_ATTR(tad_tot_cycle, 0xFF), + NULL +}; + +static const struct attribute_group ody_tad_pmu_events_attr_group = { + .name = "events", + .attrs = ody_tad_pmu_event_attrs, +}; + PMU_FORMAT_ATTR(event, "config:0-7"); static struct attribute *tad_pmu_format_attrs[] = { @@ -252,8 +279,16 @@ static const struct attribute_group *tad_pmu_attr_groups[] = { NULL }; +static const struct attribute_group *ody_tad_pmu_attr_groups[] = { + &ody_tad_pmu_events_attr_group, + &tad_pmu_format_attr_group, + &tad_pmu_cpumask_attr_group, + NULL +}; + static int tad_pmu_probe(struct platform_device *pdev) { + const struct tad_pmu_data *dev_data; struct device *dev = &pdev->dev; struct tad_region *regions; struct tad_pmu *tad_pmu; @@ -261,6 +296,7 @@ static int tad_pmu_probe(struct platform_device *pdev) u32 tad_pmu_page_size; u32 tad_page_size; u32 tad_cnt; + int version; int i, ret; char *name; @@ -270,6 +306,13 @@ static int tad_pmu_probe(struct platform_device *pdev) platform_set_drvdata(pdev, tad_pmu); + dev_data = device_get_match_data(&pdev->dev); + if (!dev_data) { + dev_err(&pdev->dev, "Error: No device match data found\n"); + return -ENODEV; + } + version = dev_data->id; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { dev_err(&pdev->dev, "Mem resource not found\n"); @@ -319,7 +362,6 @@ static int tad_pmu_probe(struct platform_device *pdev) tad_pmu->pmu = (struct pmu) { .module = THIS_MODULE, - .attr_groups = tad_pmu_attr_groups, .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, .task_ctx_nr = perf_invalid_context, @@ -332,6 +374,11 @@ static int tad_pmu_probe(struct platform_device *pdev) .read = tad_pmu_event_counter_read, }; + if (version == TAD_PMU_V1) + tad_pmu->pmu.attr_groups = tad_pmu_attr_groups; + else + tad_pmu->pmu.attr_groups = ody_tad_pmu_attr_groups; + tad_pmu->cpu = raw_smp_processor_id(); /* Register pmu instance for cpu hotplug */ @@ -360,16 +407,29 @@ static void tad_pmu_remove(struct platform_device *pdev) perf_pmu_unregister(&pmu->pmu); } +#if defined(CONFIG_OF) || defined(CONFIG_ACPI) +static const struct tad_pmu_data tad_pmu_data = { + .id = TAD_PMU_V1, +}; +#endif + +#ifdef CONFIG_ACPI +static const struct tad_pmu_data tad_pmu_v2_data = { + .id = TAD_PMU_V2, +}; +#endif + #ifdef CONFIG_OF static const struct of_device_id tad_pmu_of_match[] = { - { .compatible = "marvell,cn10k-tad-pmu", }, + { .compatible = "marvell,cn10k-tad-pmu", .data = &tad_pmu_data }, {}, }; #endif #ifdef CONFIG_ACPI static const struct acpi_device_id tad_pmu_acpi_match[] = { - {"MRVL000B", 0}, + {"MRVL000B", (kernel_ulong_t)&tad_pmu_data}, + {"MRVL000D", (kernel_ulong_t)&tad_pmu_v2_data}, {}, }; MODULE_DEVICE_TABLE(acpi, tad_pmu_acpi_match); diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 1aa303f76cc7..698de8ddf895 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -507,8 +507,7 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) { u32 type = event->attr.type; u64 config = event->attr.config; - u64 raw_config_val; - int ret; + int ret = -ENOENT; /* * Ensure we are finished checking standard hardware events for @@ -528,21 +527,23 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) case PERF_TYPE_RAW: /* * As per SBI specification, the upper 16 bits must be unused - * for a raw event. + * for a hardware raw event. * Bits 63:62 are used to distinguish between raw events * 00 - Hardware raw event * 10 - SBI firmware events * 11 - Risc-V platform specific firmware event */ - raw_config_val = config & RISCV_PMU_RAW_EVENT_MASK; + switch (config >> 62) { case 0: - ret = RISCV_PMU_RAW_EVENT_IDX; - *econfig = raw_config_val; + /* Return error any bits [48-63] is set as it is not allowed by the spec */ + if (!(config & ~RISCV_PMU_RAW_EVENT_MASK)) { + *econfig = config & RISCV_PMU_RAW_EVENT_MASK; + ret = RISCV_PMU_RAW_EVENT_IDX; + } break; case 2: - ret = (raw_config_val & 0xFFFF) | - (SBI_PMU_EVENT_TYPE_FW << 16); + ret = (config & 0xFFFF) | (SBI_PMU_EVENT_TYPE_FW << 16); break; case 3: /* @@ -551,12 +552,13 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) * Event data - raw event encoding */ ret = SBI_PMU_EVENT_TYPE_FW << 16 | RISCV_PLAT_FW_EVENT; - *econfig = raw_config_val; + *econfig = config & RISCV_PMU_PLAT_FW_EVENT_MASK; + break; + default: break; } break; default: - ret = -ENOENT; break; } @@ -1315,7 +1317,7 @@ static int riscv_pmu_proc_user_access_handler(const struct ctl_table *table, return 0; } -static struct ctl_table sbi_pmu_sysctl_table[] = { +static const struct ctl_table sbi_pmu_sysctl_table[] = { { .procname = "perf_user_access", .data = &sysctl_perf_user_access, diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c index cd159a71b23c..29b8fd4b9351 100644 --- a/drivers/phy/allwinner/phy-sun4i-usb.c +++ b/drivers/phy/allwinner/phy-sun4i-usb.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c index 950b7ae1d1a8..dc452610934a 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c @@ -325,6 +325,12 @@ static void usb_init_common_7216(struct brcm_usb_init_params *params) void __iomem *ctrl = params->regs[BRCM_REGS_CTRL]; USB_CTRL_UNSET(ctrl, USB_PM, XHC_S2_CLK_SWITCH_EN); + + /* + * The PHY might be in a bad state if it is already powered + * up. Toggle the power just in case. + */ + USB_CTRL_SET(ctrl, USB_PM, USB_PWRDN); USB_CTRL_UNSET(ctrl, USB_PM, USB_PWRDN); /* 1 millisecond - for USB clocks to settle down */ diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c index 2c8038864357..45004f598e4d 100644 --- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c +++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c @@ -331,25 +331,17 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy, { u32 pclk = cfg->pixclk; u32 fld_tg_code; - u32 pclk_khz; - u8 div = 1; + u32 int_pllclk; + u8 div; - switch (cfg->pixclk) { - case 22250000 ... 47500000: - div = 1; - break; - case 50349650 ... 99000000: - div = 2; - break; - case 100699300 ... 198000000: - div = 4; - break; - case 205000000 ... 297000000: - div = 8; - break; + /* Find int_pllclk speed */ + for (div = 0; div < 4; div++) { + int_pllclk = pclk / (1 << div); + if (int_pllclk < (50 * MHZ)) + break; } - writeb(FIELD_PREP(REG12_CK_DIV_MASK, ilog2(div)), phy->regs + PHY_REG(12)); + writeb(FIELD_PREP(REG12_CK_DIV_MASK, div), phy->regs + PHY_REG(12)); /* * Calculation for the frequency lock detector target code (fld_tg_code) @@ -362,10 +354,8 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy, * settings rounding up always too. TODO: Check if that is * correct. */ - pclk /= div; - pclk_khz = pclk / 1000; - fld_tg_code = 256 * 1000 * 1000 / pclk_khz * 24; - fld_tg_code = DIV_ROUND_UP(fld_tg_code, 1000); + + fld_tg_code = DIV_ROUND_UP(24 * MHZ * 256, int_pllclk); /* FLD_TOL and FLD_RP_CODE taken from downstream driver */ writeb(FIELD_PREP(REG13_TG_CODE_LOW_MASK, fld_tg_code), @@ -406,16 +396,15 @@ static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u1 continue; /* - * TODO: Ref Manual doesn't state the range of _m - * so this should be further refined if possible. - * This range was set based on the original values - * in the lookup table + * The Ref manual doesn't explicitly state the range of M, + * but it does show it as an 8-bit value, so reject + * any value above 255. */ tmp = (u64)fout * (_p * _s); do_div(tmp, 24 * MHZ); - _m = tmp; - if (_m < 0x30 || _m > 0x7b) + if (tmp > 255) continue; + _m = tmp; /* * Rev 2 of the Ref Manual states the @@ -424,8 +413,7 @@ static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u1 * Fvco = (M * f_ref) / P, * where f_ref is 24MHz. */ - tmp = (u64)_m * 24 * MHZ; - do_div(tmp, _p); + tmp = div64_ul((u64)_m * 24 * MHZ, _p); if (tmp < 750 * MHZ || tmp > 3000 * MHZ) continue; @@ -441,9 +429,13 @@ static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u1 min_delta = delta; best_freq = tmp; } + + /* If we have an exact match, stop looking for a better value */ + if (!delta) + goto done; } } - +done: if (best_freq) { *p = best_p; *m = best_m; diff --git a/drivers/phy/hisilicon/phy-hi3670-pcie.c b/drivers/phy/hisilicon/phy-hi3670-pcie.c index 0ac9634b398d..dbc7dcce682b 100644 --- a/drivers/phy/hisilicon/phy-hi3670-pcie.c +++ b/drivers/phy/hisilicon/phy-hi3670-pcie.c @@ -16,15 +16,20 @@ */ #include +#include #include -#include -#include +#include +#include +#include +#include #include +#include #include -#include +#include #include #include #include +#include #define AXI_CLK_FREQ 207500000 #define REF_CLK_FREQ 100000000 diff --git a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c index fefc02d921e6..71f9c14fb50d 100644 --- a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c @@ -422,7 +422,7 @@ static int mvebu_comphy_ethernet_init_reset(struct mvebu_comphy_lane *lane) /* wait until clocks are ready */ mdelay(1); - /* exlicitly disable 40B, the bits isn't clear on reset */ + /* explicitly disable 40B, the bits isn't clear on reset */ regmap_read(priv->regmap, MVEBU_COMPHY_CONF6(lane->id), &val); val &= ~MVEBU_COMPHY_CONF6_40B; regmap_write(priv->regmap, MVEBU_COMPHY_CONF6(lane->id), val); diff --git a/drivers/phy/mediatek/Kconfig b/drivers/phy/mediatek/Kconfig index 60e00057e8bc..ba6461350951 100644 --- a/drivers/phy/mediatek/Kconfig +++ b/drivers/phy/mediatek/Kconfig @@ -65,6 +65,7 @@ config PHY_MTK_HDMI depends on ARCH_MEDIATEK || COMPILE_TEST depends on COMMON_CLK depends on OF + depends on REGULATOR select GENERIC_PHY help Support HDMI PHY for Mediatek SoCs. diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c index bbfe11d6a69d..b38f3ae26b3f 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -9,6 +9,8 @@ #include #include #include +#include +#include #include #include #include @@ -478,8 +480,50 @@ static int mtk_hdmi_phy_configure(struct phy *phy, union phy_configure_opts *opt return ret; } +static int mtk_hdmi_phy_pwr5v_enable(struct regulator_dev *rdev) +{ + struct mtk_hdmi_phy *hdmi_phy = rdev_get_drvdata(rdev); + + mtk_phy_set_bits(hdmi_phy->regs + HDMI_CTL_1, RG_HDMITX_PWR5V_O); + + return 0; +} + +static int mtk_hdmi_phy_pwr5v_disable(struct regulator_dev *rdev) +{ + struct mtk_hdmi_phy *hdmi_phy = rdev_get_drvdata(rdev); + + mtk_phy_clear_bits(hdmi_phy->regs + HDMI_CTL_1, RG_HDMITX_PWR5V_O); + + return 0; +} + +static int mtk_hdmi_phy_pwr5v_is_enabled(struct regulator_dev *rdev) +{ + struct mtk_hdmi_phy *hdmi_phy = rdev_get_drvdata(rdev); + + return !!(readl(hdmi_phy->regs + HDMI_CTL_1) & RG_HDMITX_PWR5V_O); +} + +static const struct regulator_ops mtk_hdmi_pwr5v_regulator_ops = { + .enable = mtk_hdmi_phy_pwr5v_enable, + .disable = mtk_hdmi_phy_pwr5v_disable, + .is_enabled = mtk_hdmi_phy_pwr5v_is_enabled +}; + +static const struct regulator_desc mtk_hdmi_phy_pwr5v_desc = { + .name = "hdmi-pwr5v", + .id = -1, + .n_voltages = 1, + .fixed_uV = 5000000, + .ops = &mtk_hdmi_pwr5v_regulator_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, +}; + struct mtk_hdmi_phy_conf mtk_hdmi_phy_8195_conf = { .flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, + .hdmi_phy_regulator_desc = &mtk_hdmi_phy_pwr5v_desc, .hdmi_phy_clk_ops = &mtk_hdmi_pll_ops, .hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds, .hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds, diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h index 22a68dc9550c..e26caaf4d104 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h @@ -103,6 +103,9 @@ #define HDMI_ANA_CTL 0x7c #define REG_ANA_HDMI20_FIFO_EN BIT(16) +#define HDMI_CTL_1 0xc4 +#define RG_HDMITX_PWR5V_O BIT(9) + #define HDMI_CTL_3 0xcc #define REG_HDMITXPLL_DIV GENMASK(4, 0) #define REG_HDMITX_REF_XTAL_SEL BIT(7) diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.c b/drivers/phy/mediatek/phy-mtk-hdmi.c index d2e824771f9d..52a7d525ff9b 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi.c @@ -75,6 +75,28 @@ static void mtk_hdmi_phy_clk_get_data(struct mtk_hdmi_phy *hdmi_phy, clk_init->ops = hdmi_phy->conf->hdmi_phy_clk_ops; } +static int mtk_hdmi_phy_register_regulators(struct mtk_hdmi_phy *hdmi_phy) +{ + const struct regulator_desc *vreg_desc = hdmi_phy->conf->hdmi_phy_regulator_desc; + const struct regulator_init_data vreg_init_data = { + .constraints = { + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + } + }; + struct regulator_config vreg_config = { + .dev = hdmi_phy->dev, + .driver_data = hdmi_phy, + .init_data = &vreg_init_data, + .of_node = hdmi_phy->dev->of_node + }; + + hdmi_phy->rdev = devm_regulator_register(hdmi_phy->dev, vreg_desc, &vreg_config); + if (IS_ERR(hdmi_phy->rdev)) + return PTR_ERR(hdmi_phy->rdev); + + return 0; +} + static int mtk_hdmi_phy_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -150,6 +172,12 @@ static int mtk_hdmi_phy_probe(struct platform_device *pdev) if (hdmi_phy->conf->pll_default_off) hdmi_phy->conf->hdmi_phy_disable_tmds(hdmi_phy); + if (hdmi_phy->conf->hdmi_phy_regulator_desc) { + ret = mtk_hdmi_phy_register_regulators(hdmi_phy); + if (ret) + return ret; + } + return of_clk_add_provider(dev->of_node, of_clk_src_simple_get, hdmi_phy->pll); } diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.h b/drivers/phy/mediatek/phy-mtk-hdmi.h index 71c02d043485..99d917e0036a 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi.h +++ b/drivers/phy/mediatek/phy-mtk-hdmi.h @@ -13,6 +13,8 @@ #include #include #include +#include +#include #include struct mtk_hdmi_phy; @@ -20,6 +22,7 @@ struct mtk_hdmi_phy; struct mtk_hdmi_phy_conf { unsigned long flags; bool pll_default_off; + const struct regulator_desc *hdmi_phy_regulator_desc; const struct clk_ops *hdmi_phy_clk_ops; void (*hdmi_phy_enable_tmds)(struct mtk_hdmi_phy *hdmi_phy); void (*hdmi_phy_disable_tmds)(struct mtk_hdmi_phy *hdmi_phy); @@ -32,6 +35,7 @@ struct mtk_hdmi_phy { struct mtk_hdmi_phy_conf *conf; struct clk *pll; struct clk_hw pll_hw; + struct regulator_dev *rdev; unsigned long pll_rate; unsigned char drv_imp_clk; unsigned char drv_imp_d2; diff --git a/drivers/phy/mediatek/phy-mtk-tphy.c b/drivers/phy/mediatek/phy-mtk-tphy.c index 3f7095ec5978..a496fbe3352b 100644 --- a/drivers/phy/mediatek/phy-mtk-tphy.c +++ b/drivers/phy/mediatek/phy-mtk-tphy.c @@ -381,17 +381,12 @@ static const char *const u3_phy_files[] = { static int u2_phy_params_show(struct seq_file *sf, void *unused) { struct mtk_phy_instance *inst = sf->private; - const char *fname = file_dentry(sf->file)->d_iname; struct u2phy_banks *u2_banks = &inst->u2_banks; void __iomem *com = u2_banks->com; u32 max = 0; u32 tmp = 0; u32 val = 0; - int ret; - - ret = match_string(u2_phy_files, ARRAY_SIZE(u2_phy_files), fname); - if (ret < 0) - return ret; + int ret = debugfs_get_aux_num(sf->file); switch (ret) { case U2P_EYE_VRT: @@ -438,7 +433,7 @@ static int u2_phy_params_show(struct seq_file *sf, void *unused) break; } - seq_printf(sf, "%s : %d [0, %d]\n", fname, val, max); + seq_printf(sf, "%s : %d [0, %d]\n", u2_phy_files[ret], val, max); return 0; } @@ -451,23 +446,18 @@ static int u2_phy_params_open(struct inode *inode, struct file *file) static ssize_t u2_phy_params_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { - const char *fname = file_dentry(file)->d_iname; struct seq_file *sf = file->private_data; struct mtk_phy_instance *inst = sf->private; struct u2phy_banks *u2_banks = &inst->u2_banks; void __iomem *com = u2_banks->com; ssize_t rc; u32 val; - int ret; + int ret = debugfs_get_aux_num(file); rc = kstrtouint_from_user(ubuf, USER_BUF_LEN(count), 0, &val); if (rc) return rc; - ret = match_string(u2_phy_files, ARRAY_SIZE(u2_phy_files), fname); - if (ret < 0) - return (ssize_t)ret; - switch (ret) { case U2P_EYE_VRT: mtk_phy_update_field(com + U3P_USBPHYACR1, PA1_RG_VRT_SEL, val); @@ -516,23 +506,18 @@ static void u2_phy_dbgfs_files_create(struct mtk_phy_instance *inst) int i; for (i = 0; i < count; i++) - debugfs_create_file(u2_phy_files[i], 0644, inst->phy->debugfs, - inst, &u2_phy_fops); + debugfs_create_file_aux_num(u2_phy_files[i], 0644, inst->phy->debugfs, + inst, i, &u2_phy_fops); } static int u3_phy_params_show(struct seq_file *sf, void *unused) { struct mtk_phy_instance *inst = sf->private; - const char *fname = file_dentry(sf->file)->d_iname; struct u3phy_banks *u3_banks = &inst->u3_banks; u32 val = 0; u32 max = 0; u32 tmp; - int ret; - - ret = match_string(u3_phy_files, ARRAY_SIZE(u3_phy_files), fname); - if (ret < 0) - return ret; + int ret = debugfs_get_aux_num(sf->file); switch (ret) { case U3P_EFUSE_EN: @@ -564,7 +549,7 @@ static int u3_phy_params_show(struct seq_file *sf, void *unused) break; } - seq_printf(sf, "%s : %d [0, %d]\n", fname, val, max); + seq_printf(sf, "%s : %d [0, %d]\n", u3_phy_files[ret], val, max); return 0; } @@ -577,23 +562,18 @@ static int u3_phy_params_open(struct inode *inode, struct file *file) static ssize_t u3_phy_params_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { - const char *fname = file_dentry(file)->d_iname; struct seq_file *sf = file->private_data; struct mtk_phy_instance *inst = sf->private; struct u3phy_banks *u3_banks = &inst->u3_banks; void __iomem *phyd = u3_banks->phyd; ssize_t rc; u32 val; - int ret; + int ret = debugfs_get_aux_num(sf->file); rc = kstrtouint_from_user(ubuf, USER_BUF_LEN(count), 0, &val); if (rc) return rc; - ret = match_string(u3_phy_files, ARRAY_SIZE(u3_phy_files), fname); - if (ret < 0) - return (ssize_t)ret; - switch (ret) { case U3P_EFUSE_EN: mtk_phy_update_field(phyd + U3P_U3_PHYD_RSV, @@ -636,8 +616,8 @@ static void u3_phy_dbgfs_files_create(struct mtk_phy_instance *inst) int i; for (i = 0; i < count; i++) - debugfs_create_file(u3_phy_files[i], 0644, inst->phy->debugfs, - inst, &u3_phy_fops); + debugfs_create_file_aux_num(u3_phy_files[i], 0644, inst->phy->debugfs, + inst, i, &u3_phy_fops); } static int phy_type_show(struct seq_file *sf, void *unused) diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index f053b525ccff..8dfdce605a90 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -145,8 +145,10 @@ static struct phy_provider *of_phy_provider_lookup(struct device_node *node) return phy_provider; for_each_child_of_node(phy_provider->children, child) - if (child == node) + if (child == node) { + of_node_put(child); return phy_provider; + } } return ERR_PTR(-EPROBE_DEFER); @@ -629,8 +631,10 @@ static struct phy *_of_phy_get(struct device_node *np, int index) return ERR_PTR(-ENODEV); /* This phy type handled by the usb-phy subsystem for now */ - if (of_device_is_compatible(args.np, "usb-nop-xceiv")) - return ERR_PTR(-ENODEV); + if (of_device_is_compatible(args.np, "usb-nop-xceiv")) { + phy = ERR_PTR(-ENODEV); + goto out_put_node; + } mutex_lock(&phy_provider_mutex); phy_provider = of_phy_provider_lookup(args.np); @@ -652,6 +656,7 @@ out_put_module: out_unlock: mutex_unlock(&phy_provider_mutex); +out_put_node: of_node_put(args.np); return phy; @@ -737,15 +742,15 @@ void devm_phy_put(struct device *dev, struct phy *phy) if (!phy) return; - r = devres_destroy(dev, devm_phy_release, devm_phy_match, phy); + r = devres_release(dev, devm_phy_release, devm_phy_match, phy); dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); } EXPORT_SYMBOL_GPL(devm_phy_put); /** * of_phy_simple_xlate() - returns the phy instance from phy provider - * @dev: the PHY provider device - * @args: of_phandle_args (not used here) + * @dev: the PHY provider device (not used here) + * @args: of_phandle_args * * Intended to be used by phy provider for the common case where #phy-cells is * 0. For other cases where #phy-cells is greater than '0', the phy provider @@ -755,21 +760,14 @@ EXPORT_SYMBOL_GPL(devm_phy_put); struct phy *of_phy_simple_xlate(struct device *dev, const struct of_phandle_args *args) { - struct phy *phy; - struct class_dev_iter iter; + struct device *target_dev; - class_dev_iter_init(&iter, &phy_class, NULL, NULL); - while ((dev = class_dev_iter_next(&iter))) { - phy = to_phy(dev); - if (args->np != phy->dev.of_node) - continue; + target_dev = class_find_device_by_of_node(&phy_class, args->np); + if (!target_dev) + return ERR_PTR(-ENODEV); - class_dev_iter_exit(&iter); - return phy; - } - - class_dev_iter_exit(&iter); - return ERR_PTR(-ENODEV); + put_device(target_dev); + return to_phy(target_dev); } EXPORT_SYMBOL_GPL(of_phy_simple_xlate); @@ -1121,7 +1119,7 @@ void devm_phy_destroy(struct device *dev, struct phy *phy) { int r; - r = devres_destroy(dev, devm_phy_consume, devm_phy_match, phy); + r = devres_release(dev, devm_phy_consume, devm_phy_match, phy); dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); } EXPORT_SYMBOL_GPL(devm_phy_destroy); @@ -1259,12 +1257,12 @@ EXPORT_SYMBOL_GPL(of_phy_provider_unregister); * of_phy_provider_unregister to unregister the phy provider. */ void devm_of_phy_provider_unregister(struct device *dev, - struct phy_provider *phy_provider) + struct phy_provider *phy_provider) { int r; - r = devres_destroy(dev, devm_phy_provider_release, devm_phy_match, - phy_provider); + r = devres_release(dev, devm_phy_provider_release, devm_phy_match, + phy_provider); dev_WARN_ONCE(dev, r, "couldn't find PHY provider device resource\n"); } EXPORT_SYMBOL_GPL(devm_of_phy_provider_unregister); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 3bae39381fd0..b09fa00e9fe7 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -400,6 +400,57 @@ static const struct qmp_phy_init_tbl qmp_v3_usb3_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13), }; +static const struct qmp_phy_init_tbl sar2130p_usb3_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x2e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xd5), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0x25), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0xb7), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x1e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0xb7), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x1e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE0, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xd5), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0x25), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x20), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_1, 0xb6), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_2, 0x4b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_3, 0x37), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC, 0x0c), +}; + static const struct qmp_phy_init_tbl sm6350_usb3_rx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN, 0x0b), QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f), @@ -1730,6 +1781,51 @@ static const struct qmp_combo_offsets qmp_combo_offsets_v5 = { .dp_dp_phy = 0x2200, }; +static const struct qmp_phy_cfg sar2130p_usb3dpphy_cfg = { + .offsets = &qmp_combo_offsets_v3, + + .serdes_tbl = sar2130p_usb3_serdes_tbl, + .serdes_tbl_num = ARRAY_SIZE(sar2130p_usb3_serdes_tbl), + .tx_tbl = sm8550_usb3_tx_tbl, + .tx_tbl_num = ARRAY_SIZE(sm8550_usb3_tx_tbl), + .rx_tbl = sm8550_usb3_rx_tbl, + .rx_tbl_num = ARRAY_SIZE(sm8550_usb3_rx_tbl), + .pcs_tbl = sm8550_usb3_pcs_tbl, + .pcs_tbl_num = ARRAY_SIZE(sm8550_usb3_pcs_tbl), + .pcs_usb_tbl = sm8550_usb3_pcs_usb_tbl, + .pcs_usb_tbl_num = ARRAY_SIZE(sm8550_usb3_pcs_usb_tbl), + + .dp_serdes_tbl = qmp_v6_dp_serdes_tbl, + .dp_serdes_tbl_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl), + .dp_tx_tbl = qmp_v6_dp_tx_tbl, + .dp_tx_tbl_num = ARRAY_SIZE(qmp_v6_dp_tx_tbl), + + .serdes_tbl_rbr = qmp_v6_dp_serdes_tbl_rbr, + .serdes_tbl_rbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_rbr), + .serdes_tbl_hbr = qmp_v6_dp_serdes_tbl_hbr, + .serdes_tbl_hbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr), + .serdes_tbl_hbr2 = qmp_v6_dp_serdes_tbl_hbr2, + .serdes_tbl_hbr2_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr2), + .serdes_tbl_hbr3 = qmp_v6_dp_serdes_tbl_hbr3, + .serdes_tbl_hbr3_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr3), + + .swing_hbr_rbr = &qmp_dp_v5_voltage_swing_hbr_rbr, + .pre_emphasis_hbr_rbr = &qmp_dp_v6_pre_emphasis_hbr_rbr, + .swing_hbr3_hbr2 = &qmp_dp_v5_voltage_swing_hbr3_hbr2, + .pre_emphasis_hbr3_hbr2 = &qmp_dp_v5_pre_emphasis_hbr3_hbr2, + + .dp_aux_init = qmp_v4_dp_aux_init, + .configure_dp_tx = qmp_v4_configure_dp_tx, + .configure_dp_phy = qmp_v4_configure_dp_phy, + .calibrate_dp_phy = qmp_v4_calibrate_dp_phy, + + .regs = qmp_v6_usb3phy_regs_layout, + .reset_list = msm8996_usb3phy_reset_l, + .num_resets = ARRAY_SIZE(msm8996_usb3phy_reset_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), +}; + static const struct qmp_phy_cfg sc7180_usb3dpphy_cfg = { .offsets = &qmp_combo_offsets_v3, @@ -3767,6 +3863,10 @@ err_node_put: } static const struct of_device_id qmp_combo_of_match_table[] = { + { + .compatible = "qcom,sar2130p-qmp-usb3-dp-phy", + .data = &sar2130p_usb3dpphy_cfg, + }, { .compatible = "qcom,sc7180-qmp-usb3-dp-phy", .data = &sc7180_usb3dpphy_cfg, diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index 873f2f9844c6..018bbb300830 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -728,6 +728,83 @@ static const struct qmp_phy_init_tbl ipq9574_gen3x2_pcie_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_ENDPOINT_REFCLK_DRIVE, 0xc1), }; +static const struct qmp_phy_init_tbl qcs615_pcie_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x18), + QMP_PHY_INIT_CFG(QSERDES_COM_CLK_ENABLE1, 0x10), + QMP_PHY_INIT_CFG(QSERDES_COM_BG_TRIM, 0xf), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_EN, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_MAP, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER1, 0xff), + QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER2, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_COM_CMN_CONFIG, 0x6), + QMP_PHY_INIT_CFG(QSERDES_COM_PLL_IVCO, 0xf), + QMP_PHY_INIT_CFG(QSERDES_COM_HSCLK_SEL, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_SVS_MODE_CLK_SEL, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_CORE_CLK_EN, 0x20), + QMP_PHY_INIT_CFG(QSERDES_COM_CORECLK_DIV, 0xa), + QMP_PHY_INIT_CFG(QSERDES_COM_RESETSM_CNTRL, 0x20), + QMP_PHY_INIT_CFG(QSERDES_COM_BG_TIMER, 0x9), + QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_EN_SEL, 0x4), + QMP_PHY_INIT_CFG(QSERDES_COM_DEC_START_MODE0, 0x82), + QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START3_MODE0, 0x3), + QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START2_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START1_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP3_MODE0, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP2_MODE0, 0xd), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP1_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_COM_CLK_SELECT, 0x35), + QMP_PHY_INIT_CFG(QSERDES_COM_SYS_CLK_CTRL, 0x2), + QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_BUF_ENABLE, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_COM_CP_CTRL_MODE0, 0x4), + QMP_PHY_INIT_CFG(QSERDES_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_COM_PLL_CCTRL_MODE0, 0x30), + QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN1_MODE0, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN0_MODE0, 0x80), + QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CTRL_BY_PSM, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_BG_TIMER, 0xa), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_EN_CENTER, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER2, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER1, 0x2), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER2, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE1, 0x2f), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE2, 0x19), + QMP_PHY_INIT_CFG(QSERDES_COM_CLK_EP_DIV, 0x19), +}; + +static const struct qmp_phy_init_tbl qcs615_pcie_rx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_RX_SIGDET_ENABLES, 0x1c), + QMP_PHY_INIT_CFG(QSERDES_RX_SIGDET_DEGLITCH_CNTRL, 0x14), + QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2, 0x1), + QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL3, 0x0), + QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL4, 0xdb), + QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x4b), + QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN, 0x4), + QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN_HALF, 0x4), +}; + +static const struct qmp_phy_init_tbl qcs615_pcie_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_TX_HIGHZ_TRANSCEIVEREN_BIAS_DRVR_EN, 0x45), + QMP_PHY_INIT_CFG(QSERDES_TX_LANE_MODE, 0x6), + QMP_PHY_INIT_CFG(QSERDES_TX_RES_CODE_LANE_OFFSET, 0x2), + QMP_PHY_INIT_CFG(QSERDES_TX_RCV_DETECT_LVL_2, 0x12), +}; + +static const struct qmp_phy_init_tbl qcs615_pcie_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V2_PCS_ENDPOINT_REFCLK_DRIVE, 0x4), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_OSC_DTCT_ACTIONS, 0x0), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_PWRUP_RESET_DLY_TIME_AUXCLK, 0x40), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_MSB, 0x0), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_LSB, 0x40), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_PLL_LOCK_CHK_DLY_TIME_AUXCLK_LSB, 0x0), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_LP_WAKEUP_DLY_TIME_AUXCLK, 0x40), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_PLL_LOCK_CHK_DLY_TIME, 0x73), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_SIGDET_CNTRL, 0x7), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_RX_SIGDET_LVL, 0x99), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_TXDEEMPH_M6DB_V0, 0x15), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_TXDEEMPH_M3P5DB_V0, 0xe), +}; + static const struct qmp_phy_init_tbl sdm845_qmp_pcie_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN, 0x14), QMP_PHY_INIT_CFG(QSERDES_V3_COM_CLK_SELECT, 0x30), @@ -1773,7 +1850,7 @@ static const struct qmp_phy_init_tbl sdx55_qmp_pcie_rc_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_PCIE_OSC_DTCT_ACTIONS, 0x00), }; -static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_pcs_misc_tbl[] = { +static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_pcs_lane1_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00), QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), }; @@ -1907,6 +1984,9 @@ static const struct qmp_phy_init_tbl sdx65_qmp_pcie_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG2, 0x0d), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG5, 0x02), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_PRE_GAIN, 0x2e), +}; + +static const struct qmp_phy_init_tbl sdx65_qmp_pcie_pcs_lane1_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), }; @@ -2582,8 +2662,6 @@ static const struct qmp_phy_init_tbl sa8775p_qmp_gen4_pcie_rc_pcs_misc_tbl[] = { static const struct qmp_phy_init_tbl sa8775p_qmp_gen4x2_pcie_pcs_alt_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_EQ_CONFIG4, 0x16), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_EQ_CONFIG5, 0x22), - QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00), - QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_G3S2_PRE_GAIN, 0x2e), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_RX_SIGDET_LVL, 0x66), }; @@ -2724,10 +2802,106 @@ static const struct qmp_phy_init_tbl sa8775p_qmp_gen4x2_pcie_ep_pcs_alt_tbl[] = QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_INSIG_SW_CTRL7, 0x00), }; +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_rc_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x4c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_ENABLE1, 0x90), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x42), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x68), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0xab), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xea), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0xab), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xaa), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_SELECT, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC_3, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xa0), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_pcs_lane1_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_LANE1_INSIG_SW_CTRL2, 0x01), + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_LANE1_INSIG_MX_CTRL2, 0x01), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_rc_tx_tbl[] = { + QMP_PHY_INIT_CFG_LANE(QSERDES_V6_TX_BIST_MODE_LANENO, 0x00, 2), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_rc_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V6_PCS_G12S1_TXDEEMPH_M6DB, 0x17), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_G3S2_PRE_GAIN, 0x2e), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_ep_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x28), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x28), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x0d), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x0d), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x42), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x09), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x19), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE0, 0xfb), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE0, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE1, 0xfb), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE1, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_MODE, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xa0), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_ep_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V6_PCS_G12S1_TXDEEMPH_M6DB, 0x17), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_ep_pcs_misc_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_EQ_CONFIG1, 0x1e), + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_POWER_STATE_CONFIG2, 0x14), + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_POWER_STATE_CONFIG4, 0x07), +}; + struct qmp_pcie_offsets { u16 serdes; u16 pcs; u16 pcs_misc; + u16 pcs_lane1; u16 tx; u16 rx; u16 tx2; @@ -2752,6 +2926,8 @@ struct qmp_phy_cfg_tbls { int pcs_num; const struct qmp_phy_init_tbl *pcs_misc; int pcs_misc_num; + const struct qmp_phy_init_tbl *pcs_lane1; + int pcs_lane1_num; const struct qmp_phy_init_tbl *ln_shrd; int ln_shrd_num; }; @@ -2811,6 +2987,7 @@ struct qmp_pcie { void __iomem *serdes; void __iomem *pcs; void __iomem *pcs_misc; + void __iomem *pcs_lane1; void __iomem *tx; void __iomem *rx; void __iomem *tx2; @@ -2927,6 +3104,7 @@ static const struct qmp_pcie_offsets qmp_pcie_offsets_v4_20 = { .serdes = 0x1000, .pcs = 0x1200, .pcs_misc = 0x1600, + .pcs_lane1 = 0x1e00, .tx = 0x0000, .rx = 0x0200, .tx2 = 0x0800, @@ -2957,6 +3135,7 @@ static const struct qmp_pcie_offsets qmp_pcie_offsets_v5_20 = { .serdes = 0x1000, .pcs = 0x1200, .pcs_misc = 0x1400, + .pcs_lane1 = 0x1e00, .tx = 0x0000, .rx = 0x0200, .tx2 = 0x0800, @@ -3132,6 +3311,31 @@ static const struct qmp_phy_cfg ipq9574_gen3x2_pciephy_cfg = { .pipe_clock_rate = 250000000, }; +static const struct qmp_phy_cfg qcs615_pciephy_cfg = { + .lanes = 1, + + .offsets = &qmp_pcie_offsets_v2, + + .tbls = { + .serdes = qcs615_pcie_serdes_tbl, + .serdes_num = ARRAY_SIZE(qcs615_pcie_serdes_tbl), + .tx = qcs615_pcie_tx_tbl, + .tx_num = ARRAY_SIZE(qcs615_pcie_tx_tbl), + .rx = qcs615_pcie_rx_tbl, + .rx_num = ARRAY_SIZE(qcs615_pcie_rx_tbl), + .pcs = qcs615_pcie_pcs_tbl, + .pcs_num = ARRAY_SIZE(qcs615_pcie_pcs_tbl), + }, + .reset_list = sdm845_pciephy_reset_l, + .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = pciephy_v2_regs_layout, + + .pwrdn_ctrl = SW_PWRDN | REFCLK_DRV_DSBL, + .phy_status = PHYSTATUS, +}; + static const struct qmp_phy_cfg sdm845_qmp_pciephy_cfg = { .lanes = 1, @@ -3283,6 +3487,49 @@ static const struct qmp_phy_cfg msm8998_pciephy_cfg = { .skip_start_delay = true, }; +static const struct qmp_phy_cfg sar2130p_qmp_gen3x2_pciephy_cfg = { + .lanes = 2, + + .offsets = &qmp_pcie_offsets_v5, + + .tbls = { + .tx = sm8550_qmp_gen3x2_pcie_tx_tbl, + .tx_num = ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_tx_tbl), + .rx = sm8550_qmp_gen3x2_pcie_rx_tbl, + .rx_num = ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_rx_tbl), + .pcs = sm8550_qmp_gen3x2_pcie_pcs_tbl, + .pcs_num = ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_pcs_tbl), + .pcs_lane1 = sar2130p_qmp_gen3x2_pcie_pcs_lane1_tbl, + .pcs_lane1_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_pcs_lane1_tbl), + }, + .tbls_rc = &(const struct qmp_phy_cfg_tbls) { + .serdes = sar2130p_qmp_gen3x2_pcie_rc_serdes_tbl, + .serdes_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_rc_serdes_tbl), + .tx = sar2130p_qmp_gen3x2_pcie_rc_tx_tbl, + .tx_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_rc_tx_tbl), + .pcs = sar2130p_qmp_gen3x2_pcie_rc_pcs_tbl, + .pcs_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_rc_pcs_tbl), + .pcs_misc = sm8550_qmp_gen3x2_pcie_pcs_misc_tbl, + .pcs_misc_num = ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_pcs_misc_tbl), + }, + .tbls_ep = &(const struct qmp_phy_cfg_tbls) { + .serdes = sar2130p_qmp_gen3x2_pcie_ep_serdes_tbl, + .serdes_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_ep_serdes_tbl), + .pcs = sar2130p_qmp_gen3x2_pcie_ep_pcs_tbl, + .pcs_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_ep_pcs_tbl), + .pcs_misc = sar2130p_qmp_gen3x2_pcie_ep_pcs_misc_tbl, + .pcs_misc_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_ep_pcs_misc_tbl), + }, + .reset_list = sdm845_pciephy_reset_l, + .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = pciephy_v5_regs_layout, + + .pwrdn_ctrl = SW_PWRDN | REFCLK_DRV_DSBL, + .phy_status = PHYSTATUS, +}; + static const struct qmp_phy_cfg sc8180x_pciephy_cfg = { .lanes = 2, @@ -3440,8 +3687,8 @@ static const struct qmp_phy_cfg sdx55_qmp_pciephy_cfg = { .tbls_ep = &(const struct qmp_phy_cfg_tbls) { .serdes = sdx55_qmp_pcie_ep_serdes_tbl, .serdes_num = ARRAY_SIZE(sdx55_qmp_pcie_ep_serdes_tbl), - .pcs_misc = sdx55_qmp_pcie_ep_pcs_misc_tbl, - .pcs_misc_num = ARRAY_SIZE(sdx55_qmp_pcie_ep_pcs_misc_tbl), + .pcs_lane1 = sdx55_qmp_pcie_ep_pcs_lane1_tbl, + .pcs_lane1_num = ARRAY_SIZE(sdx55_qmp_pcie_ep_pcs_lane1_tbl), }, .reset_list = sdm845_pciephy_reset_l, @@ -3540,6 +3787,8 @@ static const struct qmp_phy_cfg sdx65_qmp_pciephy_cfg = { .pcs_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_tbl), .pcs_misc = sdx65_qmp_pcie_pcs_misc_tbl, .pcs_misc_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_misc_tbl), + .pcs_lane1 = sdx65_qmp_pcie_pcs_lane1_tbl, + .pcs_lane1_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_lane1_tbl), }, .reset_list = sdm845_pciephy_reset_l, .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), @@ -3739,6 +3988,8 @@ static const struct qmp_phy_cfg sa8775p_qmp_gen4x2_pciephy_cfg = { .pcs_num = ARRAY_SIZE(sa8775p_qmp_gen4x2_pcie_pcs_alt_tbl), .pcs_misc = sa8775p_qmp_gen4_pcie_pcs_misc_tbl, .pcs_misc_num = ARRAY_SIZE(sa8775p_qmp_gen4_pcie_pcs_misc_tbl), + .pcs_lane1 = sdx65_qmp_pcie_pcs_lane1_tbl, + .pcs_lane1_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_lane1_tbl), }, .tbls_rc = &(const struct qmp_phy_cfg_tbls) { @@ -3945,6 +4196,7 @@ static void qmp_pcie_init_registers(struct qmp_pcie *qmp, const struct qmp_phy_c void __iomem *rx2 = qmp->rx2; void __iomem *pcs = qmp->pcs; void __iomem *pcs_misc = qmp->pcs_misc; + void __iomem *pcs_lane1 = qmp->pcs_lane1; void __iomem *ln_shrd = qmp->ln_shrd; if (!tbls) @@ -3969,6 +4221,7 @@ static void qmp_pcie_init_registers(struct qmp_pcie *qmp, const struct qmp_phy_c qmp_configure(qmp->dev, pcs, tbls->pcs, tbls->pcs_num); qmp_configure(qmp->dev, pcs_misc, tbls->pcs_misc, tbls->pcs_misc_num); + qmp_configure(qmp->dev, pcs_lane1, tbls->pcs_lane1, tbls->pcs_lane1_num); if (cfg->lanes >= 4 && qmp->tcsr_4ln_config) { qmp_configure(qmp->dev, serdes, cfg->serdes_4ln_tbl, @@ -4420,6 +4673,14 @@ static int qmp_pcie_parse_dt_legacy(struct qmp_pcie *qmp, struct device_node *np } } + /* + * For all platforms where legacy bindings existed, PCS_LANE1 was + * mapped as a part of the PCS_MISC region. + */ + if (!IS_ERR(qmp->pcs_misc) && cfg->offsets->pcs_lane1 != 0) + qmp->pcs_lane1 = qmp->pcs_misc + + (cfg->offsets->pcs_lane1 - cfg->offsets->pcs_misc); + clk = devm_get_clk_from_child(dev, np, NULL); if (IS_ERR(clk)) { return dev_err_probe(dev, PTR_ERR(clk), @@ -4487,6 +4748,7 @@ static int qmp_pcie_parse_dt(struct qmp_pcie *qmp) qmp->serdes = base + offs->serdes; qmp->pcs = base + offs->pcs; qmp->pcs_misc = base + offs->pcs_misc; + qmp->pcs_lane1 = base + offs->pcs_lane1; qmp->tx = base + offs->tx; qmp->rx = base + offs->rx; @@ -4611,12 +4873,18 @@ static const struct of_device_id qmp_pcie_of_match_table[] = { }, { .compatible = "qcom,msm8998-qmp-pcie-phy", .data = &msm8998_pciephy_cfg, + }, { + .compatible = "qcom,qcs615-qmp-gen3x1-pcie-phy", + .data = &qcs615_pciephy_cfg, }, { .compatible = "qcom,sa8775p-qmp-gen4x2-pcie-phy", .data = &sa8775p_qmp_gen4x2_pciephy_cfg, }, { .compatible = "qcom,sa8775p-qmp-gen4x4-pcie-phy", .data = &sa8775p_qmp_gen4x4_pciephy_cfg, + }, { + .compatible = "qcom,sar2130p-qmp-gen3x2-pcie-phy", + .data = &sar2130p_qmp_gen3x2_pciephy_cfg, }, { .compatible = "qcom,sc8180x-qmp-pcie-phy", .data = &sc8180x_pciephy_cfg, diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h index ac872a9eff9a..ab892d1067c2 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h @@ -13,7 +13,8 @@ #define QPHY_V4_20_PCS_PCIE_G4_RXEQEVAL_TIME 0x0f4 #define QPHY_V4_20_PCS_PCIE_G4_EQ_CONFIG2 0x0fc #define QPHY_V4_20_PCS_PCIE_G4_EQ_CONFIG5 0x108 -#define QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2 0x824 -#define QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2 0x828 + +#define QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2 0x024 +#define QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2 0x028 #endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h index cdf8c04ea078..283d63c81593 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h @@ -17,7 +17,8 @@ #define QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG5 0x108 #define QPHY_V5_20_PCS_PCIE_G4_PRE_GAIN 0x15c #define QPHY_V5_20_PCS_PCIE_RX_MARGINING_CONFIG3 0x184 -#define QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2 0xa24 -#define QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2 0xa28 + +#define QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2 0x024 +#define QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2 0x028 #endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h index 0ca79333d942..45397cb3c0c6 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h @@ -14,4 +14,7 @@ #define QPHY_PCIE_V6_PCS_PCIE_ENDPOINT_REFCLK_DRIVE 0x20 #define QPHY_PCIE_V6_PCS_PCIE_OSC_DTCT_ACTIONS 0x94 +#define QPHY_PCIE_V6_PCS_LANE1_INSIG_SW_CTRL2 0x024 +#define QPHY_PCIE_V6_PCS_LANE1_INSIG_MX_CTRL2 0x028 + #endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h index bf36399d0057..1ecf4b5beba6 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h @@ -34,6 +34,7 @@ #define QPHY_V2_PCS_USB_PCS_STATUS 0x17c /* USB */ #define QPHY_V2_PCS_PLL_LOCK_CHK_DLY_TIME_AUXCLK_LSB 0x1a8 #define QPHY_V2_PCS_OSC_DTCT_ACTIONS 0x1ac +#define QPHY_V2_PCS_SIGDET_CNTRL 0x1b0 #define QPHY_V2_PCS_RX_SIGDET_LVL 0x1d8 #define QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_LSB 0x1dc #define QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_MSB 0x1e0 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h index 08299d2b78f0..aa5afb921f12 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h @@ -17,6 +17,8 @@ #define QPHY_V6_PCS_LOCK_DETECT_CONFIG3 0x0cc #define QPHY_V6_PCS_LOCK_DETECT_CONFIG6 0x0d8 #define QPHY_V6_PCS_REFGEN_REQ_CONFIG1 0x0dc +#define QPHY_V6_PCS_G12S1_TXDEEMPH_M6DB 0x168 +#define QPHY_V6_PCS_G3S2_PRE_GAIN 0x170 #define QPHY_V6_PCS_RX_SIGDET_LVL 0x188 #define QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L 0x190 #define QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H 0x194 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h index 23ffcfae9efa..f47fdc9cecda 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h @@ -6,6 +6,7 @@ #ifndef QCOM_PHY_QMP_QSERDES_TXRX_USB_V6_H_ #define QCOM_PHY_QMP_QSERDES_TXRX_USB_V6_H_ +#define QSERDES_V6_TX_BIST_MODE_LANENO 0x00 #define QSERDES_V6_TX_CLKBUF_ENABLE 0x08 #define QSERDES_V6_TX_TX_EMP_POST1_LVL 0x0c #define QSERDES_V6_TX_TX_DRV_LVL 0x14 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index acd6075bf6d9..787721570457 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -1052,7 +1052,7 @@ static const struct qmp_phy_init_tbl sc8280xp_usb3_uniphy_rx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f), QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff), QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f), - QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_SO_GAIN, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FO_GAIN, 0x0a), QMP_PHY_INIT_CFG(QSERDES_V5_RX_VGA_CAL_CNTRL1, 0x54), QMP_PHY_INIT_CFG(QSERDES_V5_RX_VGA_CAL_CNTRL2, 0x0f), QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f), @@ -2298,6 +2298,9 @@ err_node_put: static const struct of_device_id qmp_usb_of_match_table[] = { { + .compatible = "qcom,ipq5424-qmp-usb3-phy", + .data = &ipq9574_usb3phy_cfg, + }, { .compatible = "qcom,ipq6018-qmp-usb3-phy", .data = &ipq6018_usb3phy_cfg, }, { diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index c52655a383ce..1f5f7df14d5a 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -151,6 +151,34 @@ static const struct qusb2_phy_init_tbl ipq6018_init_tbl[] = { QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9F), }; +static const struct qusb2_phy_init_tbl ipq5424_init_tbl[] = { + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL, 0x14), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE1, 0x00), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE2, 0x53), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE4, 0xc3), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TUNE, 0x30), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL1, 0x79), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL2, 0x21), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE5, 0x00), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_PWR_CTRL, 0x00), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TEST2, 0x14), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TEST, 0x80), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9f), +}; + +static const struct qusb2_phy_init_tbl qcs615_init_tbl[] = { + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE1, 0xc8), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE2, 0xb3), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE3, 0x83), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE4, 0xc0), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TUNE, 0x30), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL1, 0x79), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL2, 0x21), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TEST2, 0x14), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9f), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_PWR_CTRL, 0x00), +}; + static const unsigned int ipq6018_regs_layout[] = { [QUSB2PHY_PLL_STATUS] = 0x38, [QUSB2PHY_PORT_TUNE1] = 0x80, @@ -331,6 +359,27 @@ static const struct qusb2_phy_cfg ipq6018_phy_cfg = { .autoresume_en = BIT(0), }; +static const struct qusb2_phy_cfg ipq5424_phy_cfg = { + .tbl = ipq5424_init_tbl, + .tbl_num = ARRAY_SIZE(ipq5424_init_tbl), + .regs = ipq6018_regs_layout, + + .disable_ctrl = POWER_DOWN, + .mask_core_ready = PLL_LOCKED, + .autoresume_en = BIT(0), +}; + +static const struct qusb2_phy_cfg qcs615_phy_cfg = { + .tbl = qcs615_init_tbl, + .tbl_num = ARRAY_SIZE(qcs615_init_tbl), + .regs = ipq6018_regs_layout, + + .disable_ctrl = (CLAMP_N_EN | FREEZIO_N | POWER_DOWN), + .mask_core_ready = PLL_LOCKED, + /* autoresume not used */ + .autoresume_en = BIT(0), +}; + static const struct qusb2_phy_cfg qusb2_v2_phy_cfg = { .tbl = qusb2_v2_init_tbl, .tbl_num = ARRAY_SIZE(qusb2_v2_init_tbl), @@ -905,6 +954,9 @@ static const struct phy_ops qusb2_phy_gen_ops = { static const struct of_device_id qusb2_phy_of_match_table[] = { { + .compatible = "qcom,ipq5424-qusb2-phy", + .data = &ipq5424_phy_cfg, + }, { .compatible = "qcom,ipq6018-qusb2-phy", .data = &ipq6018_phy_cfg, }, { @@ -922,6 +974,9 @@ static const struct of_device_id qusb2_phy_of_match_table[] = { }, { .compatible = "qcom,msm8998-qusb2-phy", .data = &msm8998_phy_cfg, + }, { + .compatible = "qcom,qcs615-qusb2-phy", + .data = &qcs615_phy_cfg, }, { .compatible = "qcom,qcm2290-qusb2-phy", .data = &sm6115_phy_cfg, diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c index 0a9989e41237..a1532ef8bbe9 100644 --- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c +++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c @@ -37,6 +37,10 @@ #define PHYREG8 0x1C #define PHYREG8_SSC_EN BIT(4) +#define PHYREG10 0x24 +#define PHYREG10_SSC_PCM_MASK GENMASK(3, 0) +#define PHYREG10_SSC_PCM_3500PPM 7 + #define PHYREG11 0x28 #define PHYREG11_SU_TRIM_0_7 0xF0 @@ -61,17 +65,26 @@ #define PHYREG16 0x3C #define PHYREG16_SSC_CNT_VALUE 0x5f +#define PHYREG17 0x40 + #define PHYREG18 0x44 #define PHYREG18_PLL_LOOP 0x32 +#define PHYREG21 0x50 +#define PHYREG21_RX_SQUELCH_VAL 0x0D + #define PHYREG27 0x6C #define PHYREG27_RX_TRIM_RK3588 0x4C +#define PHYREG30 0x74 + #define PHYREG32 0x7C #define PHYREG32_SSC_MASK GENMASK(7, 4) +#define PHYREG32_SSC_DIR_MASK GENMASK(5, 4) #define PHYREG32_SSC_DIR_SHIFT 4 #define PHYREG32_SSC_UPWARD 0 #define PHYREG32_SSC_DOWNWARD 1 +#define PHYREG32_SSC_OFFSET_MASK GENMASK(7, 6) #define PHYREG32_SSC_OFFSET_SHIFT 6 #define PHYREG32_SSC_OFFSET_500PPM 1 @@ -79,6 +92,7 @@ #define PHYREG33_PLL_KVCO_MASK GENMASK(4, 2) #define PHYREG33_PLL_KVCO_SHIFT 2 #define PHYREG33_PLL_KVCO_VALUE 2 +#define PHYREG33_PLL_KVCO_VALUE_RK3576 4 struct rockchip_combphy_priv; @@ -98,6 +112,7 @@ struct rockchip_combphy_grfcfg { struct combphy_reg pipe_rxterm_set; struct combphy_reg pipe_txelec_set; struct combphy_reg pipe_txcomp_set; + struct combphy_reg pipe_clk_24m; struct combphy_reg pipe_clk_25m; struct combphy_reg pipe_clk_100m; struct combphy_reg pipe_phymode_sel; @@ -309,7 +324,7 @@ static int rockchip_combphy_parse_dt(struct device *dev, struct rockchip_combphy priv->ext_refclk = device_property_present(dev, "rockchip,ext-refclk"); - priv->phy_rst = devm_reset_control_array_get_exclusive(dev); + priv->phy_rst = devm_reset_control_get(dev, "phy"); if (IS_ERR(priv->phy_rst)) return dev_err_probe(dev, PTR_ERR(priv->phy_rst), "failed to get phy reset\n"); @@ -584,6 +599,266 @@ static const struct rockchip_combphy_cfg rk3568_combphy_cfgs = { .combphy_cfg = rk3568_combphy_cfg, }; +static int rk3576_combphy_cfg(struct rockchip_combphy_priv *priv) +{ + const struct rockchip_combphy_grfcfg *cfg = priv->cfg->grfcfg; + unsigned long rate; + u32 val; + + switch (priv->type) { + case PHY_TYPE_PCIE: + /* Set SSC downward spread spectrum */ + val = FIELD_PREP(PHYREG32_SSC_MASK, PHYREG32_SSC_DOWNWARD); + rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32); + + rockchip_combphy_param_write(priv->phy_grf, &cfg->con0_for_pcie, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_pcie, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_pcie, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_pcie, true); + break; + + case PHY_TYPE_USB3: + /* Set SSC downward spread spectrum */ + val = FIELD_PREP(PHYREG32_SSC_MASK, PHYREG32_SSC_DOWNWARD); + rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32); + + /* Enable adaptive CTLE for USB3.0 Rx */ + val = readl(priv->mmio + PHYREG15); + val |= PHYREG15_CTLE_EN; + writel(val, priv->mmio + PHYREG15); + + /* Set PLL KVCO fine tuning signals */ + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, BIT(3), PHYREG33); + + /* Set PLL LPF R1 to su_trim[10:7]=1001 */ + writel(PHYREG12_PLL_LPF_ADJ_VALUE, priv->mmio + PHYREG12); + + /* Set PLL input clock divider 1/2 */ + val = FIELD_PREP(PHYREG6_PLL_DIV_MASK, PHYREG6_PLL_DIV_2); + rockchip_combphy_updatel(priv, PHYREG6_PLL_DIV_MASK, val, PHYREG6); + + /* Set PLL loop divider */ + writel(PHYREG18_PLL_LOOP, priv->mmio + PHYREG18); + + /* Set PLL KVCO to min and set PLL charge pump current to max */ + writel(PHYREG11_SU_TRIM_0_7, priv->mmio + PHYREG11); + + /* Set Rx squelch input filler bandwidth */ + writel(PHYREG21_RX_SQUELCH_VAL, priv->mmio + PHYREG21); + + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_txcomp_sel, false); + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_txelec_sel, false); + rockchip_combphy_param_write(priv->phy_grf, &cfg->usb_mode_set, true); + break; + + case PHY_TYPE_SATA: + /* Enable adaptive CTLE for SATA Rx */ + val = readl(priv->mmio + PHYREG15); + val |= PHYREG15_CTLE_EN; + writel(val, priv->mmio + PHYREG15); + + /* Set tx_rterm = 50 ohm and rx_rterm = 43.5 ohm */ + val = PHYREG7_TX_RTERM_50OHM << PHYREG7_TX_RTERM_SHIFT; + val |= PHYREG7_RX_RTERM_44OHM << PHYREG7_RX_RTERM_SHIFT; + writel(val, priv->mmio + PHYREG7); + + rockchip_combphy_param_write(priv->phy_grf, &cfg->con0_for_sata, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_sata, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_sata, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_sata, true); + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_con0_for_sata, true); + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_con1_for_sata, true); + break; + + default: + dev_err(priv->dev, "incompatible PHY type\n"); + return -EINVAL; + } + + rate = clk_get_rate(priv->refclk); + + switch (rate) { + case REF_CLOCK_24MHz: + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_24m, true); + if (priv->type == PHY_TYPE_USB3 || priv->type == PHY_TYPE_SATA) { + /* Set ssc_cnt[9:0]=0101111101 & 31.5KHz */ + val = FIELD_PREP(PHYREG15_SSC_CNT_MASK, PHYREG15_SSC_CNT_VALUE); + rockchip_combphy_updatel(priv, PHYREG15_SSC_CNT_MASK, + val, PHYREG15); + + writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16); + } else if (priv->type == PHY_TYPE_PCIE) { + /* PLL KVCO tuning fine */ + val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576); + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, + val, PHYREG33); + + /* Set up rx_pck invert and rx msb to disable */ + writel(0x00, priv->mmio + PHYREG27); + + /* + * Set up SU adjust signal: + * su_trim[7:0], PLL KVCO adjust bits[2:0] to min + * su_trim[15:8], PLL LPF R1 adujst bits[9:7]=3'b011 + * su_trim[31:24], CKDRV adjust + */ + writel(0x90, priv->mmio + PHYREG11); + writel(0x02, priv->mmio + PHYREG12); + writel(0x57, priv->mmio + PHYREG14); + + writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16); + } + break; + + case REF_CLOCK_25MHz: + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_25m, true); + break; + + case REF_CLOCK_100MHz: + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_100m, true); + if (priv->type == PHY_TYPE_PCIE) { + /* gate_tx_pck_sel length select work for L1SS */ + writel(0xc0, priv->mmio + PHYREG30); + + /* PLL KVCO tuning fine */ + val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576); + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, + val, PHYREG33); + + /* Set up rx_trim: PLL LPF C1 85pf R1 1.25kohm */ + writel(0x4c, priv->mmio + PHYREG27); + + /* + * Set up SU adjust signal: + * su_trim[7:0], PLL KVCO adjust bits[2:0] to min + * su_trim[15:8], bypass PLL loop divider code, and + * PLL LPF R1 adujst bits[9:7]=3'b101 + * su_trim[23:16], CKRCV adjust + * su_trim[31:24], CKDRV adjust + */ + writel(0x90, priv->mmio + PHYREG11); + writel(0x43, priv->mmio + PHYREG12); + writel(0x88, priv->mmio + PHYREG13); + writel(0x56, priv->mmio + PHYREG14); + } else if (priv->type == PHY_TYPE_SATA) { + /* downward spread spectrum +500ppm */ + val = FIELD_PREP(PHYREG32_SSC_DIR_MASK, PHYREG32_SSC_DOWNWARD); + val |= FIELD_PREP(PHYREG32_SSC_OFFSET_MASK, PHYREG32_SSC_OFFSET_500PPM); + rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32); + + /* ssc ppm adjust to 3500ppm */ + rockchip_combphy_updatel(priv, PHYREG10_SSC_PCM_MASK, + PHYREG10_SSC_PCM_3500PPM, + PHYREG10); + } + break; + + default: + dev_err(priv->dev, "Unsupported rate: %lu\n", rate); + return -EINVAL; + } + + if (priv->ext_refclk) { + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_ext, true); + if (priv->type == PHY_TYPE_PCIE && rate == REF_CLOCK_100MHz) { + val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576); + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, + val, PHYREG33); + + /* Set up rx_trim: PLL LPF C1 85pf R1 2.5kohm */ + writel(0x0c, priv->mmio + PHYREG27); + + /* + * Set up SU adjust signal: + * su_trim[7:0], PLL KVCO adjust bits[2:0] to min + * su_trim[15:8], bypass PLL loop divider code, and + * PLL LPF R1 adujst bits[9:7]=3'b101. + * su_trim[23:16], CKRCV adjust + * su_trim[31:24], CKDRV adjust + */ + writel(0x90, priv->mmio + PHYREG11); + writel(0x43, priv->mmio + PHYREG12); + writel(0x88, priv->mmio + PHYREG13); + writel(0x56, priv->mmio + PHYREG14); + } + } + + if (priv->enable_ssc) { + val = readl(priv->mmio + PHYREG8); + val |= PHYREG8_SSC_EN; + writel(val, priv->mmio + PHYREG8); + + if (priv->type == PHY_TYPE_PCIE && rate == REF_CLOCK_24MHz) { + /* Set PLL loop divider */ + writel(0x00, priv->mmio + PHYREG17); + writel(PHYREG18_PLL_LOOP, priv->mmio + PHYREG18); + + /* Set up rx_pck invert and rx msb to disable */ + writel(0x00, priv->mmio + PHYREG27); + + /* + * Set up SU adjust signal: + * su_trim[7:0], PLL KVCO adjust bits[2:0] to min + * su_trim[15:8], PLL LPF R1 adujst bits[9:7]=3'b101 + * su_trim[23:16], CKRCV adjust + * su_trim[31:24], CKDRV adjust + */ + writel(0x90, priv->mmio + PHYREG11); + writel(0x02, priv->mmio + PHYREG12); + writel(0x08, priv->mmio + PHYREG13); + writel(0x57, priv->mmio + PHYREG14); + writel(0x40, priv->mmio + PHYREG15); + + writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16); + + val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576); + writel(val, priv->mmio + PHYREG33); + } + } + + return 0; +} + +static const struct rockchip_combphy_grfcfg rk3576_combphy_grfcfgs = { + /* pipe-phy-grf */ + .pcie_mode_set = { 0x0000, 5, 0, 0x00, 0x11 }, + .usb_mode_set = { 0x0000, 5, 0, 0x00, 0x04 }, + .pipe_rxterm_set = { 0x0000, 12, 12, 0x00, 0x01 }, + .pipe_txelec_set = { 0x0004, 1, 1, 0x00, 0x01 }, + .pipe_txcomp_set = { 0x0004, 4, 4, 0x00, 0x01 }, + .pipe_clk_24m = { 0x0004, 14, 13, 0x00, 0x00 }, + .pipe_clk_25m = { 0x0004, 14, 13, 0x00, 0x01 }, + .pipe_clk_100m = { 0x0004, 14, 13, 0x00, 0x02 }, + .pipe_phymode_sel = { 0x0008, 1, 1, 0x00, 0x01 }, + .pipe_rate_sel = { 0x0008, 2, 2, 0x00, 0x01 }, + .pipe_rxterm_sel = { 0x0008, 8, 8, 0x00, 0x01 }, + .pipe_txelec_sel = { 0x0008, 12, 12, 0x00, 0x01 }, + .pipe_txcomp_sel = { 0x0008, 15, 15, 0x00, 0x01 }, + .pipe_clk_ext = { 0x000c, 9, 8, 0x02, 0x01 }, + .pipe_phy_status = { 0x0034, 6, 6, 0x01, 0x00 }, + .con0_for_pcie = { 0x0000, 15, 0, 0x00, 0x1000 }, + .con1_for_pcie = { 0x0004, 15, 0, 0x00, 0x0000 }, + .con2_for_pcie = { 0x0008, 15, 0, 0x00, 0x0101 }, + .con3_for_pcie = { 0x000c, 15, 0, 0x00, 0x0200 }, + .con0_for_sata = { 0x0000, 15, 0, 0x00, 0x0129 }, + .con1_for_sata = { 0x0004, 15, 0, 0x00, 0x0000 }, + .con2_for_sata = { 0x0008, 15, 0, 0x00, 0x80c1 }, + .con3_for_sata = { 0x000c, 15, 0, 0x00, 0x0407 }, + /* php-grf */ + .pipe_con0_for_sata = { 0x001C, 2, 0, 0x00, 0x2 }, + .pipe_con1_for_sata = { 0x0020, 2, 0, 0x00, 0x2 }, +}; + +static const struct rockchip_combphy_cfg rk3576_combphy_cfgs = { + .num_phys = 2, + .phy_ids = { + 0x2b050000, + 0x2b060000 + }, + .grfcfg = &rk3576_combphy_grfcfgs, + .combphy_cfg = rk3576_combphy_cfg, +}; + static int rk3588_combphy_cfg(struct rockchip_combphy_priv *priv) { const struct rockchip_combphy_grfcfg *cfg = priv->cfg->grfcfg; @@ -775,6 +1050,10 @@ static const struct of_device_id rockchip_combphy_of_match[] = { .compatible = "rockchip,rk3568-naneng-combphy", .data = &rk3568_combphy_cfgs, }, + { + .compatible = "rockchip,rk3576-naneng-combphy", + .data = &rk3576_combphy_cfgs, + }, { .compatible = "rockchip,rk3588-naneng-combphy", .data = &rk3588_combphy_cfgs, diff --git a/drivers/phy/rockchip/phy-rockchip-pcie.c b/drivers/phy/rockchip/phy-rockchip-pcie.c index 51cc5ece0e63..bd44af36c67a 100644 --- a/drivers/phy/rockchip/phy-rockchip-pcie.c +++ b/drivers/phy/rockchip/phy-rockchip-pcie.c @@ -124,7 +124,7 @@ static int rockchip_pcie_phy_power_off(struct phy *phy) struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst); int err = 0; - mutex_lock(&rk_phy->pcie_mutex); + guard(mutex)(&rk_phy->pcie_mutex); regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_laneoff, @@ -132,27 +132,22 @@ static int rockchip_pcie_phy_power_off(struct phy *phy) PHY_LANE_IDLE_MASK, PHY_LANE_IDLE_A_SHIFT + inst->index)); - if (--rk_phy->pwr_cnt) - goto err_out; + if (--rk_phy->pwr_cnt) { + return 0; + } err = reset_control_assert(rk_phy->phy_rst); if (err) { dev_err(&phy->dev, "assert phy_rst err %d\n", err); - goto err_restore; + rk_phy->pwr_cnt++; + regmap_write(rk_phy->reg_base, + rk_phy->phy_data->pcie_laneoff, + HIWORD_UPDATE(!PHY_LANE_IDLE_OFF, + PHY_LANE_IDLE_MASK, + PHY_LANE_IDLE_A_SHIFT + inst->index)); + return err; } -err_out: - mutex_unlock(&rk_phy->pcie_mutex); - return 0; - -err_restore: - rk_phy->pwr_cnt++; - regmap_write(rk_phy->reg_base, - rk_phy->phy_data->pcie_laneoff, - HIWORD_UPDATE(!PHY_LANE_IDLE_OFF, - PHY_LANE_IDLE_MASK, - PHY_LANE_IDLE_A_SHIFT + inst->index)); - mutex_unlock(&rk_phy->pcie_mutex); return err; } @@ -162,17 +157,18 @@ static int rockchip_pcie_phy_power_on(struct phy *phy) struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst); int err = 0; u32 status; - unsigned long timeout; - mutex_lock(&rk_phy->pcie_mutex); + guard(mutex)(&rk_phy->pcie_mutex); - if (rk_phy->pwr_cnt++) - goto err_out; + if (rk_phy->pwr_cnt++) { + return 0; + } err = reset_control_deassert(rk_phy->phy_rst); if (err) { dev_err(&phy->dev, "deassert phy_rst err %d\n", err); - goto err_pwr_cnt; + rk_phy->pwr_cnt--; + return err; } regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf, @@ -191,21 +187,11 @@ static int rockchip_pcie_phy_power_on(struct phy *phy) * so we make it large enough here. And we use loop-break * method which should not be harmful. */ - timeout = jiffies + msecs_to_jiffies(1000); - - err = -EINVAL; - while (time_before(jiffies, timeout)) { - regmap_read(rk_phy->reg_base, - rk_phy->phy_data->pcie_status, - &status); - if (status & PHY_PLL_LOCKED) { - dev_dbg(&phy->dev, "pll locked!\n"); - err = 0; - break; - } - msleep(20); - } - + err = regmap_read_poll_timeout(rk_phy->reg_base, + rk_phy->phy_data->pcie_status, + status, + status & PHY_PLL_LOCKED, + 200, 100000); if (err) { dev_err(&phy->dev, "pll lock timeout!\n"); goto err_pll_lock; @@ -214,19 +200,11 @@ static int rockchip_pcie_phy_power_on(struct phy *phy) phy_wr_cfg(rk_phy, PHY_CFG_CLK_TEST, PHY_CFG_SEPE_RATE); phy_wr_cfg(rk_phy, PHY_CFG_CLK_SCC, PHY_CFG_PLL_100M); - err = -ETIMEDOUT; - while (time_before(jiffies, timeout)) { - regmap_read(rk_phy->reg_base, - rk_phy->phy_data->pcie_status, - &status); - if (!(status & PHY_PLL_OUTPUT)) { - dev_dbg(&phy->dev, "pll output enable done!\n"); - err = 0; - break; - } - msleep(20); - } - + err = regmap_read_poll_timeout(rk_phy->reg_base, + rk_phy->phy_data->pcie_status, + status, + !(status & PHY_PLL_OUTPUT), + 200, 100000); if (err) { dev_err(&phy->dev, "pll output enable timeout!\n"); goto err_pll_lock; @@ -236,33 +214,22 @@ static int rockchip_pcie_phy_power_on(struct phy *phy) HIWORD_UPDATE(PHY_CFG_PLL_LOCK, PHY_CFG_ADDR_MASK, PHY_CFG_ADDR_SHIFT)); - err = -EINVAL; - while (time_before(jiffies, timeout)) { - regmap_read(rk_phy->reg_base, - rk_phy->phy_data->pcie_status, - &status); - if (status & PHY_PLL_LOCKED) { - dev_dbg(&phy->dev, "pll relocked!\n"); - err = 0; - break; - } - msleep(20); - } + err = regmap_read_poll_timeout(rk_phy->reg_base, + rk_phy->phy_data->pcie_status, + status, + status & PHY_PLL_LOCKED, + 200, 100000); if (err) { dev_err(&phy->dev, "pll relock timeout!\n"); goto err_pll_lock; } -err_out: - mutex_unlock(&rk_phy->pcie_mutex); - return 0; + return err; err_pll_lock: reset_control_assert(rk_phy->phy_rst); -err_pwr_cnt: rk_phy->pwr_cnt--; - mutex_unlock(&rk_phy->pcie_mutex); return err; } @@ -272,33 +239,19 @@ static int rockchip_pcie_phy_init(struct phy *phy) struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst); int err = 0; - mutex_lock(&rk_phy->pcie_mutex); + guard(mutex)(&rk_phy->pcie_mutex); - if (rk_phy->init_cnt++) - goto err_out; - - err = clk_prepare_enable(rk_phy->clk_pciephy_ref); - if (err) { - dev_err(&phy->dev, "Fail to enable pcie ref clock.\n"); - goto err_refclk; + if (rk_phy->init_cnt++) { + return 0; } err = reset_control_assert(rk_phy->phy_rst); if (err) { dev_err(&phy->dev, "assert phy_rst err %d\n", err); - goto err_reset; + rk_phy->init_cnt--; + return err; } -err_out: - mutex_unlock(&rk_phy->pcie_mutex); - return 0; - -err_reset: - - clk_disable_unprepare(rk_phy->clk_pciephy_ref); -err_refclk: - rk_phy->init_cnt--; - mutex_unlock(&rk_phy->pcie_mutex); return err; } @@ -307,15 +260,12 @@ static int rockchip_pcie_phy_exit(struct phy *phy) struct phy_pcie_instance *inst = phy_get_drvdata(phy); struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst); - mutex_lock(&rk_phy->pcie_mutex); + guard(mutex)(&rk_phy->pcie_mutex); if (--rk_phy->init_cnt) goto err_init_cnt; - clk_disable_unprepare(rk_phy->clk_pciephy_ref); - err_init_cnt: - mutex_unlock(&rk_phy->pcie_mutex); return 0; } @@ -371,18 +321,14 @@ static int rockchip_pcie_phy_probe(struct platform_device *pdev) mutex_init(&rk_phy->pcie_mutex); rk_phy->phy_rst = devm_reset_control_get(dev, "phy"); - if (IS_ERR(rk_phy->phy_rst)) { - if (PTR_ERR(rk_phy->phy_rst) != -EPROBE_DEFER) - dev_err(dev, - "missing phy property for reset controller\n"); - return PTR_ERR(rk_phy->phy_rst); - } + if (IS_ERR(rk_phy->phy_rst)) + return dev_err_probe(&pdev->dev, PTR_ERR(rk_phy->phy_rst), + "missing phy property for reset controller\n"); - rk_phy->clk_pciephy_ref = devm_clk_get(dev, "refclk"); - if (IS_ERR(rk_phy->clk_pciephy_ref)) { - dev_err(dev, "refclk not found.\n"); - return PTR_ERR(rk_phy->clk_pciephy_ref); - } + rk_phy->clk_pciephy_ref = devm_clk_get_enabled(dev, "refclk"); + if (IS_ERR(rk_phy->clk_pciephy_ref)) + return dev_err_probe(&pdev->dev, PTR_ERR(rk_phy->clk_pciephy_ref), + "failed to get phyclk\n"); /* parse #phy-cells to see if it's legacy PHY model */ if (of_property_read_u32(dev->of_node, "#phy-cells", &phy_num)) diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c index ceab9c71d3b5..0965b9d4f9cf 100644 --- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c +++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c @@ -1101,6 +1101,8 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(hdptx->grf), "Could not get GRF syscon\n"); + platform_set_drvdata(pdev, hdptx); + ret = devm_pm_runtime_enable(dev); if (ret) return dev_err_probe(dev, ret, "Failed to enable runtime PM\n"); @@ -1110,7 +1112,6 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(hdptx->phy), "Failed to create HDMI PHY\n"); - platform_set_drvdata(pdev, hdptx); phy_set_drvdata(hdptx->phy, hdptx); phy_set_bus_width(hdptx->phy, 8); diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c index 122ae0fdc785..d9701b6106d5 100644 --- a/drivers/phy/rockchip/phy-rockchip-typec.c +++ b/drivers/phy/rockchip/phy-rockchip-typec.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Copyright (C) Rockchip Electronics Co., Ltd. * Author: Chris Zhong * Kever Yang * diff --git a/drivers/phy/samsung/Kconfig b/drivers/phy/samsung/Kconfig index f10afa3d7ff5..e2330b0894d6 100644 --- a/drivers/phy/samsung/Kconfig +++ b/drivers/phy/samsung/Kconfig @@ -33,6 +33,7 @@ config PHY_SAMSUNG_UFS tristate "Exynos SoC series UFS PHY driver" depends on OF && (ARCH_EXYNOS || COMPILE_TEST) select GENERIC_PHY + select MFD_SYSCON help Enable this to support the Samsung Exynos SoC UFS PHY driver for Samsung Exynos SoCs. This driver provides the interface for UFS host diff --git a/drivers/phy/samsung/phy-samsung-ufs.c b/drivers/phy/samsung/phy-samsung-ufs.c index 6c5d41552649..8e9ccd39f97e 100644 --- a/drivers/phy/samsung/phy-samsung-ufs.c +++ b/drivers/phy/samsung/phy-samsung-ufs.c @@ -13,11 +13,11 @@ #include #include #include +#include #include #include #include #include -#include #include "phy-samsung-ufs.h" @@ -268,8 +268,8 @@ static int samsung_ufs_phy_probe(struct platform_device *pdev) goto out; } - phy->reg_pmu = exynos_get_pmu_regmap_by_phandle(dev->of_node, - "samsung,pmu-syscon"); + phy->reg_pmu = syscon_regmap_lookup_by_phandle(dev->of_node, + "samsung,pmu-syscon"); if (IS_ERR(phy->reg_pmu)) { err = PTR_ERR(phy->reg_pmu); dev_err(dev, "failed syscon remap for pmu\n"); diff --git a/drivers/phy/st/phy-stm32-combophy.c b/drivers/phy/st/phy-stm32-combophy.c index 765bb34fe358..49e9fa90a681 100644 --- a/drivers/phy/st/phy-stm32-combophy.c +++ b/drivers/phy/st/phy-stm32-combophy.c @@ -122,6 +122,7 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy) u32 max_vswing = imp_lookup[imp_size - 1].vswing[vswing_size - 1]; u32 min_vswing = imp_lookup[0].vswing[0]; u32 val; + u32 regval; if (!of_property_read_u32(combophy->dev->of_node, "st,output-micro-ohms", &val)) { if (val < min_imp || val > max_imp) { @@ -129,16 +130,20 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy) return -EINVAL; } - for (imp_of = 0; imp_of < ARRAY_SIZE(imp_lookup); imp_of++) - if (imp_lookup[imp_of].microohm <= val) + regval = 0; + for (imp_of = 0; imp_of < ARRAY_SIZE(imp_lookup); imp_of++) { + if (imp_lookup[imp_of].microohm <= val) { + regval = FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_OHM, imp_of); break; + } + } dev_dbg(combophy->dev, "Set %u micro-ohms output impedance\n", imp_lookup[imp_of].microohm); regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR, STM32MP25_PCIEPRG_IMPCTRL_OHM, - FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_OHM, imp_of)); + regval); } else { regmap_read(combophy->regmap, SYSCFG_PCIEPRGCR, &val); imp_of = FIELD_GET(STM32MP25_PCIEPRG_IMPCTRL_OHM, val); @@ -150,16 +155,20 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy) return -EINVAL; } - for (vswing_of = 0; vswing_of < ARRAY_SIZE(imp_lookup[imp_of].vswing); vswing_of++) - if (imp_lookup[imp_of].vswing[vswing_of] >= val) + regval = 0; + for (vswing_of = 0; vswing_of < ARRAY_SIZE(imp_lookup[imp_of].vswing); vswing_of++) { + if (imp_lookup[imp_of].vswing[vswing_of] >= val) { + regval = FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_VSWING, vswing_of); break; + } + } dev_dbg(combophy->dev, "Set %u microvolt swing\n", imp_lookup[imp_of].vswing[vswing_of]); regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR, STM32MP25_PCIEPRG_IMPCTRL_VSWING, - FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_VSWING, vswing_of)); + regval); } return 0; diff --git a/drivers/phy/tegra/Kconfig b/drivers/phy/tegra/Kconfig index c591c958f1eb..f30cfb42b210 100644 --- a/drivers/phy/tegra/Kconfig +++ b/drivers/phy/tegra/Kconfig @@ -13,7 +13,8 @@ config PHY_TEGRA_XUSB config PHY_TEGRA194_P2U tristate "NVIDIA Tegra194 PIPE2UPHY PHY driver" - depends on ARCH_TEGRA_194_SOC || COMPILE_TEST + depends on ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC || COMPILE_TEST select GENERIC_PHY help - Enable this to support the P2U (PIPE to UPHY) that is part of Tegra 19x SOCs. + Enable this to support the P2U (PIPE to UPHY) that is part of Tegra 19x + and 234 SOCs. diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c index 84af6aae36d1..a96be8f244e0 100644 --- a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "../pinctrl-utils.h" @@ -254,7 +255,7 @@ static int nsp_gpio_irq_set_type(struct irq_data *d, unsigned int type) raw_spin_unlock_irqrestore(&chip->lock, flags); dev_dbg(chip->dev, "gpio:%u level_low:%s falling:%s\n", gpio, - level_low ? "true" : "false", falling ? "true" : "false"); + str_true_false(level_low), str_true_false(falling)); return 0; } diff --git a/drivers/pinctrl/cirrus/pinctrl-lochnagar.c b/drivers/pinctrl/cirrus/pinctrl-lochnagar.c index 014297a3fbd2..0f32866a4aef 100644 --- a/drivers/pinctrl/cirrus/pinctrl-lochnagar.c +++ b/drivers/pinctrl/cirrus/pinctrl-lochnagar.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -1068,7 +1069,7 @@ static void lochnagar_gpio_set(struct gpio_chip *chip, value = !!value; dev_dbg(priv->dev, "Set GPIO %s to %s\n", - pin->name, value ? "high" : "low"); + pin->name, str_high_low(value)); switch (pin->type) { case LN_PTYPE_MUX: diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index b3eec63c00ba..4bdbf6bb26e2 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -1256,6 +1256,20 @@ static void pinctrl_link_add(struct pinctrl_dev *pctldev, DL_FLAG_AUTOREMOVE_CONSUMER); } +static void pinctrl_cond_disable_mux_setting(struct pinctrl_state *state, + struct pinctrl_setting *target_setting) +{ + struct pinctrl_setting *setting; + + list_for_each_entry(setting, &state->settings, node) { + if (target_setting && (&setting->node == &target_setting->node)) + break; + + if (setting->type == PIN_MAP_TYPE_MUX_GROUP) + pinmux_disable_setting(setting); + } +} + /** * pinctrl_commit_state() - select/activate/program a pinctrl state to HW * @p: the pinctrl handle for the device that requests configuration @@ -1263,7 +1277,7 @@ static void pinctrl_link_add(struct pinctrl_dev *pctldev, */ static int pinctrl_commit_state(struct pinctrl *p, struct pinctrl_state *state) { - struct pinctrl_setting *setting, *setting2; + struct pinctrl_setting *setting; struct pinctrl_state *old_state = READ_ONCE(p->state); int ret; @@ -1274,11 +1288,7 @@ static int pinctrl_commit_state(struct pinctrl *p, struct pinctrl_state *state) * still owned by the new state will be re-acquired by the call * to pinmux_enable_setting() in the loop below. */ - list_for_each_entry(setting, &old_state->settings, node) { - if (setting->type != PIN_MAP_TYPE_MUX_GROUP) - continue; - pinmux_disable_setting(setting); - } + pinctrl_cond_disable_mux_setting(old_state, NULL); } p->state = NULL; @@ -1322,7 +1332,7 @@ static int pinctrl_commit_state(struct pinctrl *p, struct pinctrl_state *state) } if (ret < 0) { - goto unapply_new_state; + goto unapply_mux_setting; } /* Do not link hogs (circular dependency) */ @@ -1334,23 +1344,23 @@ static int pinctrl_commit_state(struct pinctrl *p, struct pinctrl_state *state) return 0; +unapply_mux_setting: + pinctrl_cond_disable_mux_setting(state, NULL); + goto restore_old_state; + unapply_new_state: dev_err(p->dev, "Error applying setting, reverse things back\n"); - list_for_each_entry(setting2, &state->settings, node) { - if (&setting2->node == &setting->node) - break; - /* - * All we can do here is pinmux_disable_setting. - * That means that some pins are muxed differently now - * than they were before applying the setting (We can't - * "unmux a pin"!), but it's not a big deal since the pins - * are free to be muxed by another apply_setting. - */ - if (setting2->type == PIN_MAP_TYPE_MUX_GROUP) - pinmux_disable_setting(setting2); - } + /* + * All we can do here is pinmux_disable_setting. + * That means that some pins are muxed differently now + * than they were before applying the setting (We can't + * "unmux a pin"!), but it's not a big deal since the pins + * are free to be muxed by another apply_setting. + */ + pinctrl_cond_disable_mux_setting(state, setting); +restore_old_state: /* There's no infinite recursive loop here because p->state is NULL */ if (old_state) pinctrl_select_state(p, old_state); diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig index a417a031659c..58f32818a0e6 100644 --- a/drivers/pinctrl/mediatek/Kconfig +++ b/drivers/pinctrl/mediatek/Kconfig @@ -202,6 +202,13 @@ config PINCTRL_MT7986 default ARM64 && ARCH_MEDIATEK select PINCTRL_MTK_MOORE +config PINCTRL_MT7988 + bool "Mediatek MT7988 pin control" + depends on OF + depends on ARM64 || COMPILE_TEST + default ARM64 && ARCH_MEDIATEK + select PINCTRL_MTK_MOORE + config PINCTRL_MT8167 bool "MediaTek MT8167 pin control" depends on OF diff --git a/drivers/pinctrl/mediatek/Makefile b/drivers/pinctrl/mediatek/Makefile index 1405d434218e..721ae83476d0 100644 --- a/drivers/pinctrl/mediatek/Makefile +++ b/drivers/pinctrl/mediatek/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_PINCTRL_MT7623) += pinctrl-mt7623.o obj-$(CONFIG_PINCTRL_MT7629) += pinctrl-mt7629.o obj-$(CONFIG_PINCTRL_MT7981) += pinctrl-mt7981.o obj-$(CONFIG_PINCTRL_MT7986) += pinctrl-mt7986.o +obj-$(CONFIG_PINCTRL_MT7988) += pinctrl-mt7988.o obj-$(CONFIG_PINCTRL_MT8167) += pinctrl-mt8167.o obj-$(CONFIG_PINCTRL_MT8173) += pinctrl-mt8173.o obj-$(CONFIG_PINCTRL_MT8183) += pinctrl-mt8183.o diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7988.c b/drivers/pinctrl/mediatek/pinctrl-mt7988.c new file mode 100644 index 000000000000..68b4097792b8 --- /dev/null +++ b/drivers/pinctrl/mediatek/pinctrl-mt7988.c @@ -0,0 +1,1556 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * The MT7988 driver based on Linux generic pinctrl binding. + * + * Copyright (C) 2020 MediaTek Inc. + * Author: Sam Shih + */ + +#include "pinctrl-moore.h" + +enum mt7988_pinctrl_reg_page { + GPIO_BASE, + IOCFG_TR_BASE, + IOCFG_BR_BASE, + IOCFG_RB_BASE, + IOCFG_LB_BASE, + IOCFG_TL_BASE, +}; + +#define MT7988_PIN(_number, _name) MTK_PIN(_number, _name, 0, _number, DRV_GRP4) + +#define PIN_FIELD_BASE(_s_pin, _e_pin, _i_base, _s_addr, _x_addrs, _s_bit, \ + _x_bits) \ + PIN_FIELD_CALC(_s_pin, _e_pin, _i_base, _s_addr, _x_addrs, _s_bit, \ + _x_bits, 32, 0) + +#define PINS_FIELD_BASE(_s_pin, _e_pin, _i_base, _s_addr, _x_addrs, _s_bit, \ + _x_bits) \ + PIN_FIELD_CALC(_s_pin, _e_pin, _i_base, _s_addr, _x_addrs, _s_bit, \ + _x_bits, 32, 1) + +static const struct mtk_pin_field_calc mt7988_pin_mode_range[] = { + PIN_FIELD(0, 83, 0x300, 0x10, 0, 4), +}; + +static const struct mtk_pin_field_calc mt7988_pin_dir_range[] = { + PIN_FIELD(0, 83, 0x0, 0x10, 0, 1), +}; + +static const struct mtk_pin_field_calc mt7988_pin_di_range[] = { + PIN_FIELD(0, 83, 0x200, 0x10, 0, 1), +}; + +static const struct mtk_pin_field_calc mt7988_pin_do_range[] = { + PIN_FIELD(0, 83, 0x100, 0x10, 0, 1), +}; + +static const struct mtk_pin_field_calc mt7988_pin_ies_range[] = { + PIN_FIELD_BASE(0, 0, 5, 0x30, 0x10, 13, 1), + PIN_FIELD_BASE(1, 1, 5, 0x30, 0x10, 14, 1), + PIN_FIELD_BASE(2, 2, 5, 0x30, 0x10, 11, 1), + PIN_FIELD_BASE(3, 3, 5, 0x30, 0x10, 12, 1), + PIN_FIELD_BASE(4, 4, 5, 0x30, 0x10, 0, 1), + PIN_FIELD_BASE(5, 5, 5, 0x30, 0x10, 9, 1), + PIN_FIELD_BASE(6, 6, 5, 0x30, 0x10, 10, 1), + + PIN_FIELD_BASE(7, 7, 4, 0x30, 0x10, 8, 1), + PIN_FIELD_BASE(8, 8, 4, 0x30, 0x10, 6, 1), + PIN_FIELD_BASE(9, 9, 4, 0x30, 0x10, 5, 1), + PIN_FIELD_BASE(10, 10, 4, 0x30, 0x10, 3, 1), + + PIN_FIELD_BASE(11, 11, 1, 0x40, 0x10, 0, 1), + PIN_FIELD_BASE(12, 12, 1, 0x40, 0x10, 21, 1), + PIN_FIELD_BASE(13, 13, 1, 0x40, 0x10, 1, 1), + PIN_FIELD_BASE(14, 14, 1, 0x40, 0x10, 2, 1), + + PIN_FIELD_BASE(15, 15, 5, 0x30, 0x10, 7, 1), + PIN_FIELD_BASE(16, 16, 5, 0x30, 0x10, 8, 1), + PIN_FIELD_BASE(17, 17, 5, 0x30, 0x10, 3, 1), + PIN_FIELD_BASE(18, 18, 5, 0x30, 0x10, 4, 1), + + PIN_FIELD_BASE(19, 19, 4, 0x30, 0x10, 7, 1), + PIN_FIELD_BASE(20, 20, 4, 0x30, 0x10, 4, 1), + + PIN_FIELD_BASE(21, 21, 3, 0x50, 0x10, 17, 1), + PIN_FIELD_BASE(22, 22, 3, 0x50, 0x10, 23, 1), + PIN_FIELD_BASE(23, 23, 3, 0x50, 0x10, 20, 1), + PIN_FIELD_BASE(24, 24, 3, 0x50, 0x10, 19, 1), + PIN_FIELD_BASE(25, 25, 3, 0x50, 0x10, 21, 1), + PIN_FIELD_BASE(26, 26, 3, 0x50, 0x10, 22, 1), + PIN_FIELD_BASE(27, 27, 3, 0x50, 0x10, 18, 1), + PIN_FIELD_BASE(28, 28, 3, 0x50, 0x10, 25, 1), + PIN_FIELD_BASE(29, 29, 3, 0x50, 0x10, 26, 1), + PIN_FIELD_BASE(30, 30, 3, 0x50, 0x10, 27, 1), + PIN_FIELD_BASE(31, 31, 3, 0x50, 0x10, 24, 1), + PIN_FIELD_BASE(32, 32, 3, 0x50, 0x10, 28, 1), + PIN_FIELD_BASE(33, 33, 3, 0x60, 0x10, 0, 1), + PIN_FIELD_BASE(34, 34, 3, 0x50, 0x10, 31, 1), + PIN_FIELD_BASE(35, 35, 3, 0x50, 0x10, 29, 1), + PIN_FIELD_BASE(36, 36, 3, 0x50, 0x10, 30, 1), + PIN_FIELD_BASE(37, 37, 3, 0x60, 0x10, 1, 1), + PIN_FIELD_BASE(38, 38, 3, 0x50, 0x10, 11, 1), + PIN_FIELD_BASE(39, 39, 3, 0x50, 0x10, 10, 1), + PIN_FIELD_BASE(40, 40, 3, 0x50, 0x10, 0, 1), + PIN_FIELD_BASE(41, 41, 3, 0x50, 0x10, 1, 1), + PIN_FIELD_BASE(42, 42, 3, 0x50, 0x10, 9, 1), + PIN_FIELD_BASE(43, 43, 3, 0x50, 0x10, 8, 1), + PIN_FIELD_BASE(44, 44, 3, 0x50, 0x10, 7, 1), + PIN_FIELD_BASE(45, 45, 3, 0x50, 0x10, 6, 1), + PIN_FIELD_BASE(46, 46, 3, 0x50, 0x10, 5, 1), + PIN_FIELD_BASE(47, 47, 3, 0x50, 0x10, 4, 1), + PIN_FIELD_BASE(48, 48, 3, 0x50, 0x10, 3, 1), + PIN_FIELD_BASE(49, 49, 3, 0x50, 0x10, 2, 1), + PIN_FIELD_BASE(50, 50, 3, 0x50, 0x10, 15, 1), + PIN_FIELD_BASE(51, 51, 3, 0x50, 0x10, 12, 1), + PIN_FIELD_BASE(52, 52, 3, 0x50, 0x10, 13, 1), + PIN_FIELD_BASE(53, 53, 3, 0x50, 0x10, 14, 1), + PIN_FIELD_BASE(54, 54, 3, 0x50, 0x10, 16, 1), + + PIN_FIELD_BASE(55, 55, 1, 0x40, 0x10, 14, 1), + PIN_FIELD_BASE(56, 56, 1, 0x40, 0x10, 15, 1), + PIN_FIELD_BASE(57, 57, 1, 0x40, 0x10, 13, 1), + PIN_FIELD_BASE(58, 58, 1, 0x40, 0x10, 4, 1), + PIN_FIELD_BASE(59, 59, 1, 0x40, 0x10, 5, 1), + PIN_FIELD_BASE(60, 60, 1, 0x40, 0x10, 6, 1), + PIN_FIELD_BASE(61, 61, 1, 0x40, 0x10, 3, 1), + PIN_FIELD_BASE(62, 62, 1, 0x40, 0x10, 7, 1), + PIN_FIELD_BASE(63, 63, 1, 0x40, 0x10, 20, 1), + PIN_FIELD_BASE(64, 64, 1, 0x40, 0x10, 8, 1), + PIN_FIELD_BASE(65, 65, 1, 0x40, 0x10, 9, 1), + PIN_FIELD_BASE(66, 66, 1, 0x40, 0x10, 10, 1), + PIN_FIELD_BASE(67, 67, 1, 0x40, 0x10, 11, 1), + PIN_FIELD_BASE(68, 68, 1, 0x40, 0x10, 12, 1), + + PIN_FIELD_BASE(69, 69, 5, 0x30, 0x10, 1, 1), + PIN_FIELD_BASE(70, 70, 5, 0x30, 0x10, 2, 1), + PIN_FIELD_BASE(71, 71, 5, 0x30, 0x10, 5, 1), + PIN_FIELD_BASE(72, 72, 5, 0x30, 0x10, 6, 1), + + PIN_FIELD_BASE(73, 73, 4, 0x30, 0x10, 10, 1), + PIN_FIELD_BASE(74, 74, 4, 0x30, 0x10, 1, 1), + PIN_FIELD_BASE(75, 75, 4, 0x30, 0x10, 11, 1), + PIN_FIELD_BASE(76, 76, 4, 0x30, 0x10, 9, 1), + PIN_FIELD_BASE(77, 77, 4, 0x30, 0x10, 2, 1), + PIN_FIELD_BASE(78, 78, 4, 0x30, 0x10, 0, 1), + PIN_FIELD_BASE(79, 79, 4, 0x30, 0x10, 12, 1), + + PIN_FIELD_BASE(80, 80, 1, 0x40, 0x10, 18, 1), + PIN_FIELD_BASE(81, 81, 1, 0x40, 0x10, 19, 1), + PIN_FIELD_BASE(82, 82, 1, 0x40, 0x10, 16, 1), + PIN_FIELD_BASE(83, 83, 1, 0x40, 0x10, 17, 1), +}; + +static const struct mtk_pin_field_calc mt7988_pin_smt_range[] = { + PIN_FIELD_BASE(0, 0, 5, 0xc0, 0x10, 13, 1), + PIN_FIELD_BASE(1, 1, 5, 0xc0, 0x10, 14, 1), + PIN_FIELD_BASE(2, 2, 5, 0xc0, 0x10, 11, 1), + PIN_FIELD_BASE(3, 3, 5, 0xc0, 0x10, 12, 1), + PIN_FIELD_BASE(4, 4, 5, 0xc0, 0x10, 0, 1), + PIN_FIELD_BASE(5, 5, 5, 0xc0, 0x10, 9, 1), + PIN_FIELD_BASE(6, 6, 5, 0xc0, 0x10, 10, 1), + + PIN_FIELD_BASE(7, 7, 4, 0xb0, 0x10, 8, 1), + PIN_FIELD_BASE(8, 8, 4, 0xb0, 0x10, 6, 1), + PIN_FIELD_BASE(9, 9, 4, 0xb0, 0x10, 5, 1), + PIN_FIELD_BASE(10, 10, 4, 0xb0, 0x10, 3, 1), + + PIN_FIELD_BASE(11, 11, 1, 0xe0, 0x10, 0, 1), + PIN_FIELD_BASE(12, 12, 1, 0xe0, 0x10, 21, 1), + PIN_FIELD_BASE(13, 13, 1, 0xe0, 0x10, 1, 1), + PIN_FIELD_BASE(14, 14, 1, 0xe0, 0x10, 2, 1), + + PIN_FIELD_BASE(15, 15, 5, 0xc0, 0x10, 7, 1), + PIN_FIELD_BASE(16, 16, 5, 0xc0, 0x10, 8, 1), + PIN_FIELD_BASE(17, 17, 5, 0xc0, 0x10, 3, 1), + PIN_FIELD_BASE(18, 18, 5, 0xc0, 0x10, 4, 1), + + PIN_FIELD_BASE(19, 19, 4, 0xb0, 0x10, 7, 1), + PIN_FIELD_BASE(20, 20, 4, 0xb0, 0x10, 4, 1), + + PIN_FIELD_BASE(21, 21, 3, 0x140, 0x10, 17, 1), + PIN_FIELD_BASE(22, 22, 3, 0x140, 0x10, 23, 1), + PIN_FIELD_BASE(23, 23, 3, 0x140, 0x10, 20, 1), + PIN_FIELD_BASE(24, 24, 3, 0x140, 0x10, 19, 1), + PIN_FIELD_BASE(25, 25, 3, 0x140, 0x10, 21, 1), + PIN_FIELD_BASE(26, 26, 3, 0x140, 0x10, 22, 1), + PIN_FIELD_BASE(27, 27, 3, 0x140, 0x10, 18, 1), + PIN_FIELD_BASE(28, 28, 3, 0x140, 0x10, 25, 1), + PIN_FIELD_BASE(29, 29, 3, 0x140, 0x10, 26, 1), + PIN_FIELD_BASE(30, 30, 3, 0x140, 0x10, 27, 1), + PIN_FIELD_BASE(31, 31, 3, 0x140, 0x10, 24, 1), + PIN_FIELD_BASE(32, 32, 3, 0x140, 0x10, 28, 1), + PIN_FIELD_BASE(33, 33, 3, 0x150, 0x10, 0, 1), + PIN_FIELD_BASE(34, 34, 3, 0x140, 0x10, 31, 1), + PIN_FIELD_BASE(35, 35, 3, 0x140, 0x10, 29, 1), + PIN_FIELD_BASE(36, 36, 3, 0x140, 0x10, 30, 1), + PIN_FIELD_BASE(37, 37, 3, 0x150, 0x10, 1, 1), + PIN_FIELD_BASE(38, 38, 3, 0x140, 0x10, 11, 1), + PIN_FIELD_BASE(39, 39, 3, 0x140, 0x10, 10, 1), + PIN_FIELD_BASE(40, 40, 3, 0x140, 0x10, 0, 1), + PIN_FIELD_BASE(41, 41, 3, 0x140, 0x10, 1, 1), + PIN_FIELD_BASE(42, 42, 3, 0x140, 0x10, 9, 1), + PIN_FIELD_BASE(43, 43, 3, 0x140, 0x10, 8, 1), + PIN_FIELD_BASE(44, 44, 3, 0x140, 0x10, 7, 1), + PIN_FIELD_BASE(45, 45, 3, 0x140, 0x10, 6, 1), + PIN_FIELD_BASE(46, 46, 3, 0x140, 0x10, 5, 1), + PIN_FIELD_BASE(47, 47, 3, 0x140, 0x10, 4, 1), + PIN_FIELD_BASE(48, 48, 3, 0x140, 0x10, 3, 1), + PIN_FIELD_BASE(49, 49, 3, 0x140, 0x10, 2, 1), + PIN_FIELD_BASE(50, 50, 3, 0x140, 0x10, 15, 1), + PIN_FIELD_BASE(51, 51, 3, 0x140, 0x10, 12, 1), + PIN_FIELD_BASE(52, 52, 3, 0x140, 0x10, 13, 1), + PIN_FIELD_BASE(53, 53, 3, 0x140, 0x10, 14, 1), + PIN_FIELD_BASE(54, 54, 3, 0x140, 0x10, 16, 1), + + PIN_FIELD_BASE(55, 55, 1, 0xe0, 0x10, 14, 1), + PIN_FIELD_BASE(56, 56, 1, 0xe0, 0x10, 15, 1), + PIN_FIELD_BASE(57, 57, 1, 0xe0, 0x10, 13, 1), + PIN_FIELD_BASE(58, 58, 1, 0xe0, 0x10, 4, 1), + PIN_FIELD_BASE(59, 59, 1, 0xe0, 0x10, 5, 1), + PIN_FIELD_BASE(60, 60, 1, 0xe0, 0x10, 6, 1), + PIN_FIELD_BASE(61, 61, 1, 0xe0, 0x10, 3, 1), + PIN_FIELD_BASE(62, 62, 1, 0xe0, 0x10, 7, 1), + PIN_FIELD_BASE(63, 63, 1, 0xe0, 0x10, 20, 1), + PIN_FIELD_BASE(64, 64, 1, 0xe0, 0x10, 8, 1), + PIN_FIELD_BASE(65, 65, 1, 0xe0, 0x10, 9, 1), + PIN_FIELD_BASE(66, 66, 1, 0xe0, 0x10, 10, 1), + PIN_FIELD_BASE(67, 67, 1, 0xe0, 0x10, 11, 1), + PIN_FIELD_BASE(68, 68, 1, 0xe0, 0x10, 12, 1), + + PIN_FIELD_BASE(69, 69, 5, 0xc0, 0x10, 1, 1), + PIN_FIELD_BASE(70, 70, 5, 0xc0, 0x10, 2, 1), + PIN_FIELD_BASE(71, 71, 5, 0xc0, 0x10, 5, 1), + PIN_FIELD_BASE(72, 72, 5, 0xc0, 0x10, 6, 1), + + PIN_FIELD_BASE(73, 73, 4, 0xb0, 0x10, 10, 1), + PIN_FIELD_BASE(74, 74, 4, 0xb0, 0x10, 1, 1), + PIN_FIELD_BASE(75, 75, 4, 0xb0, 0x10, 11, 1), + PIN_FIELD_BASE(76, 76, 4, 0xb0, 0x10, 9, 1), + PIN_FIELD_BASE(77, 77, 4, 0xb0, 0x10, 2, 1), + PIN_FIELD_BASE(78, 78, 4, 0xb0, 0x10, 0, 1), + PIN_FIELD_BASE(79, 79, 4, 0xb0, 0x10, 12, 1), + + PIN_FIELD_BASE(80, 80, 1, 0xe0, 0x10, 18, 1), + PIN_FIELD_BASE(81, 81, 1, 0xe0, 0x10, 19, 1), + PIN_FIELD_BASE(82, 82, 1, 0xe0, 0x10, 16, 1), + PIN_FIELD_BASE(83, 83, 1, 0xe0, 0x10, 17, 1), +}; + +static const struct mtk_pin_field_calc mt7988_pin_pu_range[] = { + PIN_FIELD_BASE(7, 7, 4, 0x60, 0x10, 5, 1), + PIN_FIELD_BASE(8, 8, 4, 0x60, 0x10, 4, 1), + PIN_FIELD_BASE(9, 9, 4, 0x60, 0x10, 3, 1), + PIN_FIELD_BASE(10, 10, 4, 0x60, 0x10, 2, 1), + + PIN_FIELD_BASE(13, 13, 1, 0x70, 0x10, 0, 1), + PIN_FIELD_BASE(14, 14, 1, 0x70, 0x10, 1, 1), + PIN_FIELD_BASE(63, 63, 1, 0x70, 0x10, 2, 1), + + PIN_FIELD_BASE(75, 75, 4, 0x60, 0x10, 7, 1), + PIN_FIELD_BASE(76, 76, 4, 0x60, 0x10, 6, 1), + PIN_FIELD_BASE(77, 77, 4, 0x60, 0x10, 1, 1), + PIN_FIELD_BASE(78, 78, 4, 0x60, 0x10, 0, 1), + PIN_FIELD_BASE(79, 79, 4, 0x60, 0x10, 8, 1), +}; + +static const struct mtk_pin_field_calc mt7988_pin_pd_range[] = { + PIN_FIELD_BASE(7, 7, 4, 0x40, 0x10, 5, 1), + PIN_FIELD_BASE(8, 8, 4, 0x40, 0x10, 4, 1), + PIN_FIELD_BASE(9, 9, 4, 0x40, 0x10, 3, 1), + PIN_FIELD_BASE(10, 10, 4, 0x40, 0x10, 2, 1), + + PIN_FIELD_BASE(13, 13, 1, 0x50, 0x10, 0, 1), + PIN_FIELD_BASE(14, 14, 1, 0x50, 0x10, 1, 1), + + PIN_FIELD_BASE(15, 15, 5, 0x40, 0x10, 4, 1), + PIN_FIELD_BASE(16, 16, 5, 0x40, 0x10, 5, 1), + PIN_FIELD_BASE(17, 17, 5, 0x40, 0x10, 0, 1), + PIN_FIELD_BASE(18, 18, 5, 0x40, 0x10, 1, 1), + + PIN_FIELD_BASE(63, 63, 1, 0x50, 0x10, 2, 1), + PIN_FIELD_BASE(71, 71, 5, 0x40, 0x10, 2, 1), + PIN_FIELD_BASE(72, 72, 5, 0x40, 0x10, 3, 1), + + PIN_FIELD_BASE(75, 75, 4, 0x40, 0x10, 7, 1), + PIN_FIELD_BASE(76, 76, 4, 0x40, 0x10, 6, 1), + PIN_FIELD_BASE(77, 77, 4, 0x40, 0x10, 1, 1), + PIN_FIELD_BASE(78, 78, 4, 0x40, 0x10, 0, 1), + PIN_FIELD_BASE(79, 79, 4, 0x40, 0x10, 8, 1), +}; + +static const struct mtk_pin_field_calc mt7988_pin_drv_range[] = { + PIN_FIELD_BASE(0, 0, 5, 0x00, 0x10, 21, 3), + PIN_FIELD_BASE(1, 1, 5, 0x00, 0x10, 24, 3), + PIN_FIELD_BASE(2, 2, 5, 0x00, 0x10, 15, 3), + PIN_FIELD_BASE(3, 3, 5, 0x00, 0x10, 18, 3), + PIN_FIELD_BASE(4, 4, 5, 0x00, 0x10, 0, 3), + PIN_FIELD_BASE(5, 5, 5, 0x00, 0x10, 9, 3), + PIN_FIELD_BASE(6, 6, 5, 0x00, 0x10, 12, 3), + + PIN_FIELD_BASE(7, 7, 4, 0x00, 0x10, 24, 3), + PIN_FIELD_BASE(8, 8, 4, 0x00, 0x10, 28, 3), + PIN_FIELD_BASE(9, 9, 4, 0x00, 0x10, 15, 3), + PIN_FIELD_BASE(10, 10, 4, 0x00, 0x10, 9, 3), + + PIN_FIELD_BASE(11, 11, 1, 0x00, 0x10, 0, 3), + PIN_FIELD_BASE(12, 12, 1, 0x20, 0x10, 3, 3), + PIN_FIELD_BASE(13, 13, 1, 0x00, 0x10, 3, 3), + PIN_FIELD_BASE(14, 14, 1, 0x00, 0x10, 6, 3), + + PIN_FIELD_BASE(19, 19, 4, 0x00, 0x10, 21, 3), + PIN_FIELD_BASE(20, 20, 4, 0x00, 0x10, 12, 3), + + PIN_FIELD_BASE(21, 21, 3, 0x10, 0x10, 21, 3), + PIN_FIELD_BASE(22, 22, 3, 0x20, 0x10, 9, 3), + PIN_FIELD_BASE(23, 23, 3, 0x20, 0x10, 0, 3), + PIN_FIELD_BASE(24, 24, 3, 0x10, 0x10, 27, 3), + PIN_FIELD_BASE(25, 25, 3, 0x20, 0x10, 3, 3), + PIN_FIELD_BASE(26, 26, 3, 0x20, 0x10, 6, 3), + PIN_FIELD_BASE(27, 27, 3, 0x10, 0x10, 24, 3), + PIN_FIELD_BASE(28, 28, 3, 0x20, 0x10, 15, 3), + PIN_FIELD_BASE(29, 29, 3, 0x20, 0x10, 18, 3), + PIN_FIELD_BASE(30, 30, 3, 0x20, 0x10, 21, 3), + PIN_FIELD_BASE(31, 31, 3, 0x20, 0x10, 12, 3), + PIN_FIELD_BASE(32, 32, 3, 0x20, 0x10, 24, 3), + PIN_FIELD_BASE(33, 33, 3, 0x30, 0x10, 6, 3), + PIN_FIELD_BASE(34, 34, 3, 0x30, 0x10, 3, 3), + PIN_FIELD_BASE(35, 35, 3, 0x20, 0x10, 27, 3), + PIN_FIELD_BASE(36, 36, 3, 0x30, 0x10, 0, 3), + PIN_FIELD_BASE(37, 37, 3, 0x30, 0x10, 9, 3), + PIN_FIELD_BASE(38, 38, 3, 0x10, 0x10, 3, 3), + PIN_FIELD_BASE(39, 39, 3, 0x10, 0x10, 0, 3), + PIN_FIELD_BASE(40, 40, 3, 0x00, 0x10, 0, 3), + PIN_FIELD_BASE(41, 41, 3, 0x00, 0x10, 3, 3), + PIN_FIELD_BASE(42, 42, 3, 0x00, 0x10, 27, 3), + PIN_FIELD_BASE(43, 43, 3, 0x00, 0x10, 24, 3), + PIN_FIELD_BASE(44, 44, 3, 0x00, 0x10, 21, 3), + PIN_FIELD_BASE(45, 45, 3, 0x00, 0x10, 18, 3), + PIN_FIELD_BASE(46, 46, 3, 0x00, 0x10, 15, 3), + PIN_FIELD_BASE(47, 47, 3, 0x00, 0x10, 12, 3), + PIN_FIELD_BASE(48, 48, 3, 0x00, 0x10, 9, 3), + PIN_FIELD_BASE(49, 49, 3, 0x00, 0x10, 6, 3), + PIN_FIELD_BASE(50, 50, 3, 0x10, 0x10, 15, 3), + PIN_FIELD_BASE(51, 51, 3, 0x10, 0x10, 6, 3), + PIN_FIELD_BASE(52, 52, 3, 0x10, 0x10, 9, 3), + PIN_FIELD_BASE(53, 53, 3, 0x10, 0x10, 12, 3), + PIN_FIELD_BASE(54, 54, 3, 0x10, 0x10, 18, 3), + + PIN_FIELD_BASE(55, 55, 1, 0x10, 0x10, 12, 3), + PIN_FIELD_BASE(56, 56, 1, 0x10, 0x10, 15, 3), + PIN_FIELD_BASE(57, 57, 1, 0x10, 0x10, 9, 3), + PIN_FIELD_BASE(58, 58, 1, 0x00, 0x10, 12, 3), + PIN_FIELD_BASE(59, 59, 1, 0x00, 0x10, 15, 3), + PIN_FIELD_BASE(60, 60, 1, 0x00, 0x10, 18, 3), + PIN_FIELD_BASE(61, 61, 1, 0x00, 0x10, 9, 3), + PIN_FIELD_BASE(62, 62, 1, 0x00, 0x10, 21, 3), + PIN_FIELD_BASE(63, 63, 1, 0x20, 0x10, 0, 3), + PIN_FIELD_BASE(64, 64, 1, 0x00, 0x10, 24, 3), + PIN_FIELD_BASE(65, 65, 1, 0x00, 0x10, 27, 3), + PIN_FIELD_BASE(66, 66, 1, 0x10, 0x10, 0, 3), + PIN_FIELD_BASE(67, 67, 1, 0x10, 0x10, 3, 3), + PIN_FIELD_BASE(68, 68, 1, 0x10, 0x10, 6, 3), + + PIN_FIELD_BASE(69, 69, 5, 0x00, 0x10, 3, 3), + PIN_FIELD_BASE(70, 70, 5, 0x00, 0x10, 6, 3), + + PIN_FIELD_BASE(73, 73, 4, 0x10, 0x10, 0, 3), + PIN_FIELD_BASE(74, 74, 4, 0x00, 0x10, 3, 3), + PIN_FIELD_BASE(75, 75, 4, 0x10, 0x10, 3, 3), + PIN_FIELD_BASE(76, 76, 4, 0x00, 0x10, 27, 3), + PIN_FIELD_BASE(77, 77, 4, 0x00, 0x10, 6, 3), + PIN_FIELD_BASE(78, 78, 4, 0x00, 0x10, 0, 3), + PIN_FIELD_BASE(79, 79, 4, 0x10, 0x10, 6, 3), + + PIN_FIELD_BASE(80, 80, 1, 0x10, 0x10, 24, 3), + PIN_FIELD_BASE(81, 81, 1, 0x10, 0x10, 27, 3), + PIN_FIELD_BASE(82, 82, 1, 0x10, 0x10, 18, 3), + PIN_FIELD_BASE(83, 83, 1, 0x10, 0x10, 21, 3), +}; + +static const struct mtk_pin_field_calc mt7988_pin_pupd_range[] = { + PIN_FIELD_BASE(0, 0, 5, 0x50, 0x10, 7, 1), + PIN_FIELD_BASE(1, 1, 5, 0x50, 0x10, 8, 1), + PIN_FIELD_BASE(2, 2, 5, 0x50, 0x10, 5, 1), + PIN_FIELD_BASE(3, 3, 5, 0x50, 0x10, 6, 1), + PIN_FIELD_BASE(4, 4, 5, 0x50, 0x10, 0, 1), + PIN_FIELD_BASE(5, 5, 5, 0x50, 0x10, 3, 1), + PIN_FIELD_BASE(6, 6, 5, 0x50, 0x10, 4, 1), + + PIN_FIELD_BASE(11, 11, 1, 0x60, 0x10, 0, 1), + PIN_FIELD_BASE(12, 12, 1, 0x60, 0x10, 18, 1), + + PIN_FIELD_BASE(19, 19, 4, 0x50, 0x10, 2, 1), + PIN_FIELD_BASE(20, 20, 4, 0x50, 0x10, 1, 1), + + PIN_FIELD_BASE(21, 21, 3, 0x70, 0x10, 17, 1), + PIN_FIELD_BASE(22, 22, 3, 0x70, 0x10, 23, 1), + PIN_FIELD_BASE(23, 23, 3, 0x70, 0x10, 20, 1), + PIN_FIELD_BASE(24, 24, 3, 0x70, 0x10, 19, 1), + PIN_FIELD_BASE(25, 25, 3, 0x70, 0x10, 21, 1), + PIN_FIELD_BASE(26, 26, 3, 0x70, 0x10, 22, 1), + PIN_FIELD_BASE(27, 27, 3, 0x70, 0x10, 18, 1), + PIN_FIELD_BASE(28, 28, 3, 0x70, 0x10, 25, 1), + PIN_FIELD_BASE(29, 29, 3, 0x70, 0x10, 26, 1), + PIN_FIELD_BASE(30, 30, 3, 0x70, 0x10, 27, 1), + PIN_FIELD_BASE(31, 31, 3, 0x70, 0x10, 24, 1), + PIN_FIELD_BASE(32, 32, 3, 0x70, 0x10, 28, 1), + PIN_FIELD_BASE(33, 33, 3, 0x80, 0x10, 0, 1), + PIN_FIELD_BASE(34, 34, 3, 0x70, 0x10, 31, 1), + PIN_FIELD_BASE(35, 35, 3, 0x70, 0x10, 29, 1), + PIN_FIELD_BASE(36, 36, 3, 0x70, 0x10, 30, 1), + PIN_FIELD_BASE(37, 37, 3, 0x80, 0x10, 1, 1), + PIN_FIELD_BASE(38, 38, 3, 0x70, 0x10, 11, 1), + PIN_FIELD_BASE(39, 39, 3, 0x70, 0x10, 10, 1), + PIN_FIELD_BASE(40, 40, 3, 0x70, 0x10, 0, 1), + PIN_FIELD_BASE(41, 41, 3, 0x70, 0x10, 1, 1), + PIN_FIELD_BASE(42, 42, 3, 0x70, 0x10, 9, 1), + PIN_FIELD_BASE(43, 43, 3, 0x70, 0x10, 8, 1), + PIN_FIELD_BASE(44, 44, 3, 0x70, 0x10, 7, 1), + PIN_FIELD_BASE(45, 45, 3, 0x70, 0x10, 6, 1), + PIN_FIELD_BASE(46, 46, 3, 0x70, 0x10, 5, 1), + PIN_FIELD_BASE(47, 47, 3, 0x70, 0x10, 4, 1), + PIN_FIELD_BASE(48, 48, 3, 0x70, 0x10, 3, 1), + PIN_FIELD_BASE(49, 49, 3, 0x70, 0x10, 2, 1), + PIN_FIELD_BASE(50, 50, 3, 0x70, 0x10, 15, 1), + PIN_FIELD_BASE(51, 51, 3, 0x70, 0x10, 12, 1), + PIN_FIELD_BASE(52, 52, 3, 0x70, 0x10, 13, 1), + PIN_FIELD_BASE(53, 53, 3, 0x70, 0x10, 14, 1), + PIN_FIELD_BASE(54, 54, 3, 0x70, 0x10, 16, 1), + + PIN_FIELD_BASE(55, 55, 1, 0x60, 0x10, 12, 1), + PIN_FIELD_BASE(56, 56, 1, 0x60, 0x10, 13, 1), + PIN_FIELD_BASE(57, 57, 1, 0x60, 0x10, 11, 1), + PIN_FIELD_BASE(58, 58, 1, 0x60, 0x10, 2, 1), + PIN_FIELD_BASE(59, 59, 1, 0x60, 0x10, 3, 1), + PIN_FIELD_BASE(60, 60, 1, 0x60, 0x10, 4, 1), + PIN_FIELD_BASE(61, 61, 1, 0x60, 0x10, 1, 1), + PIN_FIELD_BASE(62, 62, 1, 0x60, 0x10, 5, 1), + PIN_FIELD_BASE(64, 64, 1, 0x60, 0x10, 6, 1), + PIN_FIELD_BASE(65, 65, 1, 0x60, 0x10, 7, 1), + PIN_FIELD_BASE(66, 66, 1, 0x60, 0x10, 8, 1), + PIN_FIELD_BASE(67, 67, 1, 0x60, 0x10, 9, 1), + PIN_FIELD_BASE(68, 68, 1, 0x60, 0x10, 10, 1), + + PIN_FIELD_BASE(69, 69, 5, 0x50, 0x10, 1, 1), + PIN_FIELD_BASE(70, 70, 5, 0x50, 0x10, 2, 1), + + PIN_FIELD_BASE(73, 73, 4, 0x50, 0x10, 3, 1), + PIN_FIELD_BASE(74, 74, 4, 0x50, 0x10, 0, 1), + + PIN_FIELD_BASE(80, 80, 1, 0x60, 0x10, 16, 1), + PIN_FIELD_BASE(81, 81, 1, 0x60, 0x10, 17, 1), + PIN_FIELD_BASE(82, 82, 1, 0x60, 0x10, 14, 1), + PIN_FIELD_BASE(83, 83, 1, 0x60, 0x10, 15, 1), +}; + +static const struct mtk_pin_field_calc mt7988_pin_r0_range[] = { + PIN_FIELD_BASE(0, 0, 5, 0x60, 0x10, 7, 1), + PIN_FIELD_BASE(1, 1, 5, 0x60, 0x10, 8, 1), + PIN_FIELD_BASE(2, 2, 5, 0x60, 0x10, 5, 1), + PIN_FIELD_BASE(3, 3, 5, 0x60, 0x10, 6, 1), + PIN_FIELD_BASE(4, 4, 5, 0x60, 0x10, 0, 1), + PIN_FIELD_BASE(5, 5, 5, 0x60, 0x10, 3, 1), + PIN_FIELD_BASE(6, 6, 5, 0x60, 0x10, 4, 1), + + PIN_FIELD_BASE(11, 11, 1, 0x80, 0x10, 0, 1), + PIN_FIELD_BASE(12, 12, 1, 0x80, 0x10, 18, 1), + + PIN_FIELD_BASE(19, 19, 4, 0x70, 0x10, 2, 1), + PIN_FIELD_BASE(20, 20, 4, 0x70, 0x10, 1, 1), + + PIN_FIELD_BASE(21, 21, 3, 0x90, 0x10, 17, 1), + PIN_FIELD_BASE(22, 22, 3, 0x90, 0x10, 23, 1), + PIN_FIELD_BASE(23, 23, 3, 0x90, 0x10, 20, 1), + PIN_FIELD_BASE(24, 24, 3, 0x90, 0x10, 19, 1), + PIN_FIELD_BASE(25, 25, 3, 0x90, 0x10, 21, 1), + PIN_FIELD_BASE(26, 26, 3, 0x90, 0x10, 22, 1), + PIN_FIELD_BASE(27, 27, 3, 0x90, 0x10, 18, 1), + PIN_FIELD_BASE(28, 28, 3, 0x90, 0x10, 25, 1), + PIN_FIELD_BASE(29, 29, 3, 0x90, 0x10, 26, 1), + PIN_FIELD_BASE(30, 30, 3, 0x90, 0x10, 27, 1), + PIN_FIELD_BASE(31, 31, 3, 0x90, 0x10, 24, 1), + PIN_FIELD_BASE(32, 32, 3, 0x90, 0x10, 28, 1), + PIN_FIELD_BASE(33, 33, 3, 0xa0, 0x10, 0, 1), + PIN_FIELD_BASE(34, 34, 3, 0x90, 0x10, 31, 1), + PIN_FIELD_BASE(35, 35, 3, 0x90, 0x10, 29, 1), + PIN_FIELD_BASE(36, 36, 3, 0x90, 0x10, 30, 1), + PIN_FIELD_BASE(37, 37, 3, 0xa0, 0x10, 1, 1), + PIN_FIELD_BASE(38, 38, 3, 0x90, 0x10, 11, 1), + PIN_FIELD_BASE(39, 39, 3, 0x90, 0x10, 10, 1), + PIN_FIELD_BASE(40, 40, 3, 0x90, 0x10, 0, 1), + PIN_FIELD_BASE(41, 41, 3, 0x90, 0x10, 1, 1), + PIN_FIELD_BASE(42, 42, 3, 0x90, 0x10, 9, 1), + PIN_FIELD_BASE(43, 43, 3, 0x90, 0x10, 8, 1), + PIN_FIELD_BASE(44, 44, 3, 0x90, 0x10, 7, 1), + PIN_FIELD_BASE(45, 45, 3, 0x90, 0x10, 6, 1), + PIN_FIELD_BASE(46, 46, 3, 0x90, 0x10, 5, 1), + PIN_FIELD_BASE(47, 47, 3, 0x90, 0x10, 4, 1), + PIN_FIELD_BASE(48, 48, 3, 0x90, 0x10, 3, 1), + PIN_FIELD_BASE(49, 49, 3, 0x90, 0x10, 2, 1), + PIN_FIELD_BASE(50, 50, 3, 0x90, 0x10, 15, 1), + PIN_FIELD_BASE(51, 51, 3, 0x90, 0x10, 12, 1), + PIN_FIELD_BASE(52, 52, 3, 0x90, 0x10, 13, 1), + PIN_FIELD_BASE(53, 53, 3, 0x90, 0x10, 14, 1), + PIN_FIELD_BASE(54, 54, 3, 0x90, 0x10, 16, 1), + + PIN_FIELD_BASE(55, 55, 1, 0x80, 0x10, 12, 1), + PIN_FIELD_BASE(56, 56, 1, 0x80, 0x10, 13, 1), + PIN_FIELD_BASE(57, 57, 1, 0x80, 0x10, 11, 1), + PIN_FIELD_BASE(58, 58, 1, 0x80, 0x10, 2, 1), + PIN_FIELD_BASE(59, 59, 1, 0x80, 0x10, 3, 1), + PIN_FIELD_BASE(60, 60, 1, 0x80, 0x10, 4, 1), + PIN_FIELD_BASE(61, 61, 1, 0x80, 0x10, 1, 1), + PIN_FIELD_BASE(62, 62, 1, 0x80, 0x10, 5, 1), + PIN_FIELD_BASE(64, 64, 1, 0x80, 0x10, 6, 1), + PIN_FIELD_BASE(65, 65, 1, 0x80, 0x10, 7, 1), + PIN_FIELD_BASE(66, 66, 1, 0x80, 0x10, 8, 1), + PIN_FIELD_BASE(67, 67, 1, 0x80, 0x10, 9, 1), + PIN_FIELD_BASE(68, 68, 1, 0x80, 0x10, 10, 1), + + PIN_FIELD_BASE(69, 69, 5, 0x60, 0x10, 1, 1), + PIN_FIELD_BASE(70, 70, 5, 0x60, 0x10, 2, 1), + + PIN_FIELD_BASE(73, 73, 4, 0x70, 0x10, 3, 1), + PIN_FIELD_BASE(74, 74, 4, 0x70, 0x10, 0, 1), + + PIN_FIELD_BASE(80, 80, 1, 0x80, 0x10, 16, 1), + PIN_FIELD_BASE(81, 81, 1, 0x80, 0x10, 17, 1), + PIN_FIELD_BASE(82, 82, 1, 0x80, 0x10, 14, 1), + PIN_FIELD_BASE(83, 83, 1, 0x80, 0x10, 15, 1), +}; + +static const struct mtk_pin_field_calc mt7988_pin_r1_range[] = { + PIN_FIELD_BASE(0, 0, 5, 0x70, 0x10, 7, 1), + PIN_FIELD_BASE(1, 1, 5, 0x70, 0x10, 8, 1), + PIN_FIELD_BASE(2, 2, 5, 0x70, 0x10, 5, 1), + PIN_FIELD_BASE(3, 3, 5, 0x70, 0x10, 6, 1), + PIN_FIELD_BASE(4, 4, 5, 0x70, 0x10, 0, 1), + PIN_FIELD_BASE(5, 5, 5, 0x70, 0x10, 3, 1), + PIN_FIELD_BASE(6, 6, 5, 0x70, 0x10, 4, 1), + + PIN_FIELD_BASE(11, 11, 1, 0x90, 0x10, 0, 1), + PIN_FIELD_BASE(12, 12, 1, 0x90, 0x10, 18, 1), + + PIN_FIELD_BASE(19, 19, 4, 0x80, 0x10, 2, 1), + PIN_FIELD_BASE(20, 20, 4, 0x80, 0x10, 1, 1), + + PIN_FIELD_BASE(21, 21, 3, 0xb0, 0x10, 17, 1), + PIN_FIELD_BASE(22, 22, 3, 0xb0, 0x10, 23, 1), + PIN_FIELD_BASE(23, 23, 3, 0xb0, 0x10, 20, 1), + PIN_FIELD_BASE(24, 24, 3, 0xb0, 0x10, 19, 1), + PIN_FIELD_BASE(25, 25, 3, 0xb0, 0x10, 21, 1), + PIN_FIELD_BASE(26, 26, 3, 0xb0, 0x10, 22, 1), + PIN_FIELD_BASE(27, 27, 3, 0xb0, 0x10, 18, 1), + PIN_FIELD_BASE(28, 28, 3, 0xb0, 0x10, 25, 1), + PIN_FIELD_BASE(29, 29, 3, 0xb0, 0x10, 26, 1), + PIN_FIELD_BASE(30, 30, 3, 0xb0, 0x10, 27, 1), + PIN_FIELD_BASE(31, 31, 3, 0xb0, 0x10, 24, 1), + PIN_FIELD_BASE(32, 32, 3, 0xb0, 0x10, 28, 1), + PIN_FIELD_BASE(33, 33, 3, 0xc0, 0x10, 0, 1), + PIN_FIELD_BASE(34, 34, 3, 0xb0, 0x10, 31, 1), + PIN_FIELD_BASE(35, 35, 3, 0xb0, 0x10, 29, 1), + PIN_FIELD_BASE(36, 36, 3, 0xb0, 0x10, 30, 1), + PIN_FIELD_BASE(37, 37, 3, 0xc0, 0x10, 1, 1), + PIN_FIELD_BASE(38, 38, 3, 0xb0, 0x10, 11, 1), + PIN_FIELD_BASE(39, 39, 3, 0xb0, 0x10, 10, 1), + PIN_FIELD_BASE(40, 40, 3, 0xb0, 0x10, 0, 1), + PIN_FIELD_BASE(41, 41, 3, 0xb0, 0x10, 1, 1), + PIN_FIELD_BASE(42, 42, 3, 0xb0, 0x10, 9, 1), + PIN_FIELD_BASE(43, 43, 3, 0xb0, 0x10, 8, 1), + PIN_FIELD_BASE(44, 44, 3, 0xb0, 0x10, 7, 1), + PIN_FIELD_BASE(45, 45, 3, 0xb0, 0x10, 6, 1), + PIN_FIELD_BASE(46, 46, 3, 0xb0, 0x10, 5, 1), + PIN_FIELD_BASE(47, 47, 3, 0xb0, 0x10, 4, 1), + PIN_FIELD_BASE(48, 48, 3, 0xb0, 0x10, 3, 1), + PIN_FIELD_BASE(49, 49, 3, 0xb0, 0x10, 2, 1), + PIN_FIELD_BASE(50, 50, 3, 0xb0, 0x10, 15, 1), + PIN_FIELD_BASE(51, 51, 3, 0xb0, 0x10, 12, 1), + PIN_FIELD_BASE(52, 52, 3, 0xb0, 0x10, 13, 1), + PIN_FIELD_BASE(53, 53, 3, 0xb0, 0x10, 14, 1), + PIN_FIELD_BASE(54, 54, 3, 0xb0, 0x10, 16, 1), + + PIN_FIELD_BASE(55, 55, 1, 0x90, 0x10, 12, 1), + PIN_FIELD_BASE(56, 56, 1, 0x90, 0x10, 13, 1), + PIN_FIELD_BASE(57, 57, 1, 0x90, 0x10, 11, 1), + PIN_FIELD_BASE(58, 58, 1, 0x90, 0x10, 2, 1), + PIN_FIELD_BASE(59, 59, 1, 0x90, 0x10, 3, 1), + PIN_FIELD_BASE(60, 60, 1, 0x90, 0x10, 4, 1), + PIN_FIELD_BASE(61, 61, 1, 0x90, 0x10, 1, 1), + PIN_FIELD_BASE(62, 62, 1, 0x90, 0x10, 5, 1), + PIN_FIELD_BASE(64, 64, 1, 0x90, 0x10, 6, 1), + PIN_FIELD_BASE(65, 65, 1, 0x90, 0x10, 7, 1), + PIN_FIELD_BASE(66, 66, 1, 0x90, 0x10, 8, 1), + PIN_FIELD_BASE(67, 67, 1, 0x90, 0x10, 9, 1), + PIN_FIELD_BASE(68, 68, 1, 0x90, 0x10, 10, 1), + + PIN_FIELD_BASE(69, 69, 5, 0x70, 0x10, 1, 1), + PIN_FIELD_BASE(70, 70, 5, 0x70, 0x10, 2, 1), + + PIN_FIELD_BASE(73, 73, 4, 0x80, 0x10, 3, 1), + PIN_FIELD_BASE(74, 74, 4, 0x80, 0x10, 0, 1), + + PIN_FIELD_BASE(80, 80, 1, 0x90, 0x10, 16, 1), + PIN_FIELD_BASE(81, 81, 1, 0x90, 0x10, 17, 1), + PIN_FIELD_BASE(82, 82, 1, 0x90, 0x10, 14, 1), + PIN_FIELD_BASE(83, 83, 1, 0x90, 0x10, 15, 1), +}; + +static const unsigned int mt7988_pull_type[] = { + MTK_PULL_PUPD_R1R0_TYPE,/*0*/ MTK_PULL_PUPD_R1R0_TYPE,/*1*/ + MTK_PULL_PUPD_R1R0_TYPE,/*2*/ MTK_PULL_PUPD_R1R0_TYPE,/*3*/ + MTK_PULL_PUPD_R1R0_TYPE,/*4*/ MTK_PULL_PUPD_R1R0_TYPE,/*5*/ + MTK_PULL_PUPD_R1R0_TYPE,/*6*/ MTK_PULL_PU_PD_TYPE, /*7*/ + MTK_PULL_PU_PD_TYPE, /*8*/ MTK_PULL_PU_PD_TYPE, /*9*/ + MTK_PULL_PU_PD_TYPE, /*10*/ MTK_PULL_PUPD_R1R0_TYPE,/*11*/ + MTK_PULL_PUPD_R1R0_TYPE,/*12*/ MTK_PULL_PU_PD_TYPE, /*13*/ + MTK_PULL_PU_PD_TYPE, /*14*/ MTK_PULL_PD_TYPE, /*15*/ + MTK_PULL_PD_TYPE, /*16*/ MTK_PULL_PD_TYPE, /*17*/ + MTK_PULL_PD_TYPE, /*18*/ MTK_PULL_PUPD_R1R0_TYPE,/*19*/ + MTK_PULL_PUPD_R1R0_TYPE,/*20*/ MTK_PULL_PUPD_R1R0_TYPE,/*21*/ + MTK_PULL_PUPD_R1R0_TYPE,/*22*/ MTK_PULL_PUPD_R1R0_TYPE,/*23*/ + MTK_PULL_PUPD_R1R0_TYPE,/*24*/ MTK_PULL_PUPD_R1R0_TYPE,/*25*/ + MTK_PULL_PUPD_R1R0_TYPE,/*26*/ MTK_PULL_PUPD_R1R0_TYPE,/*27*/ + MTK_PULL_PUPD_R1R0_TYPE,/*28*/ MTK_PULL_PUPD_R1R0_TYPE,/*29*/ + MTK_PULL_PUPD_R1R0_TYPE,/*30*/ MTK_PULL_PUPD_R1R0_TYPE,/*31*/ + MTK_PULL_PUPD_R1R0_TYPE,/*32*/ MTK_PULL_PUPD_R1R0_TYPE,/*33*/ + MTK_PULL_PUPD_R1R0_TYPE,/*34*/ MTK_PULL_PUPD_R1R0_TYPE,/*35*/ + MTK_PULL_PUPD_R1R0_TYPE,/*36*/ MTK_PULL_PUPD_R1R0_TYPE,/*37*/ + MTK_PULL_PUPD_R1R0_TYPE,/*38*/ MTK_PULL_PUPD_R1R0_TYPE,/*39*/ + MTK_PULL_PUPD_R1R0_TYPE,/*40*/ MTK_PULL_PUPD_R1R0_TYPE,/*41*/ + MTK_PULL_PUPD_R1R0_TYPE,/*42*/ MTK_PULL_PUPD_R1R0_TYPE,/*43*/ + MTK_PULL_PUPD_R1R0_TYPE,/*44*/ MTK_PULL_PUPD_R1R0_TYPE,/*45*/ + MTK_PULL_PUPD_R1R0_TYPE,/*46*/ MTK_PULL_PUPD_R1R0_TYPE,/*47*/ + MTK_PULL_PUPD_R1R0_TYPE,/*48*/ MTK_PULL_PUPD_R1R0_TYPE,/*49*/ + MTK_PULL_PUPD_R1R0_TYPE,/*50*/ MTK_PULL_PUPD_R1R0_TYPE,/*51*/ + MTK_PULL_PUPD_R1R0_TYPE,/*52*/ MTK_PULL_PUPD_R1R0_TYPE,/*53*/ + MTK_PULL_PUPD_R1R0_TYPE,/*54*/ MTK_PULL_PUPD_R1R0_TYPE,/*55*/ + MTK_PULL_PUPD_R1R0_TYPE,/*56*/ MTK_PULL_PUPD_R1R0_TYPE,/*57*/ + MTK_PULL_PUPD_R1R0_TYPE,/*58*/ MTK_PULL_PUPD_R1R0_TYPE,/*59*/ + MTK_PULL_PUPD_R1R0_TYPE,/*60*/ MTK_PULL_PUPD_R1R0_TYPE,/*61*/ + MTK_PULL_PUPD_R1R0_TYPE,/*62*/ MTK_PULL_PU_PD_TYPE, /*63*/ + MTK_PULL_PUPD_R1R0_TYPE,/*64*/ MTK_PULL_PUPD_R1R0_TYPE,/*65*/ + MTK_PULL_PUPD_R1R0_TYPE,/*66*/ MTK_PULL_PUPD_R1R0_TYPE,/*67*/ + MTK_PULL_PUPD_R1R0_TYPE,/*68*/ MTK_PULL_PUPD_R1R0_TYPE,/*69*/ + MTK_PULL_PUPD_R1R0_TYPE,/*70*/ MTK_PULL_PD_TYPE, /*71*/ + MTK_PULL_PD_TYPE, /*72*/ MTK_PULL_PUPD_R1R0_TYPE,/*73*/ + MTK_PULL_PUPD_R1R0_TYPE,/*74*/ MTK_PULL_PU_PD_TYPE, /*75*/ + MTK_PULL_PU_PD_TYPE, /*76*/ MTK_PULL_PU_PD_TYPE, /*77*/ + MTK_PULL_PU_PD_TYPE, /*78*/ MTK_PULL_PU_PD_TYPE, /*79*/ + MTK_PULL_PUPD_R1R0_TYPE,/*80*/ MTK_PULL_PUPD_R1R0_TYPE,/*81*/ + MTK_PULL_PUPD_R1R0_TYPE,/*82*/ MTK_PULL_PUPD_R1R0_TYPE,/*83*/ +}; + +static const struct mtk_pin_reg_calc mt7988_reg_cals[] = { + [PINCTRL_PIN_REG_MODE] = MTK_RANGE(mt7988_pin_mode_range), + [PINCTRL_PIN_REG_DIR] = MTK_RANGE(mt7988_pin_dir_range), + [PINCTRL_PIN_REG_DI] = MTK_RANGE(mt7988_pin_di_range), + [PINCTRL_PIN_REG_DO] = MTK_RANGE(mt7988_pin_do_range), + [PINCTRL_PIN_REG_SMT] = MTK_RANGE(mt7988_pin_smt_range), + [PINCTRL_PIN_REG_IES] = MTK_RANGE(mt7988_pin_ies_range), + [PINCTRL_PIN_REG_PU] = MTK_RANGE(mt7988_pin_pu_range), + [PINCTRL_PIN_REG_PD] = MTK_RANGE(mt7988_pin_pd_range), + [PINCTRL_PIN_REG_DRV] = MTK_RANGE(mt7988_pin_drv_range), + [PINCTRL_PIN_REG_PUPD] = MTK_RANGE(mt7988_pin_pupd_range), + [PINCTRL_PIN_REG_R0] = MTK_RANGE(mt7988_pin_r0_range), + [PINCTRL_PIN_REG_R1] = MTK_RANGE(mt7988_pin_r1_range), +}; + +static const struct mtk_pin_desc mt7988_pins[] = { + MT7988_PIN(0, "UART2_RXD"), + MT7988_PIN(1, "UART2_TXD"), + MT7988_PIN(2, "UART2_CTS"), + MT7988_PIN(3, "UART2_RTS"), + MT7988_PIN(4, "GPIO_A"), + MT7988_PIN(5, "SMI_0_MDC"), + MT7988_PIN(6, "SMI_0_MDIO"), + MT7988_PIN(7, "PCIE30_2L_0_WAKE_N"), + MT7988_PIN(8, "PCIE30_2L_0_CLKREQ_N"), + MT7988_PIN(9, "PCIE30_1L_1_WAKE_N"), + MT7988_PIN(10, "PCIE30_1L_1_CLKREQ_N"), + MT7988_PIN(11, "GPIO_P"), + MT7988_PIN(12, "WATCHDOG"), + MT7988_PIN(13, "GPIO_RESET"), + MT7988_PIN(14, "GPIO_WPS"), + MT7988_PIN(15, "PMIC_I2C_SCL"), + MT7988_PIN(16, "PMIC_I2C_SDA"), + MT7988_PIN(17, "I2C_1_SCL"), + MT7988_PIN(18, "I2C_1_SDA"), + MT7988_PIN(19, "PCIE30_2L_0_PRESET_N"), + MT7988_PIN(20, "PCIE30_1L_1_PRESET_N"), + MT7988_PIN(21, "PWMD1"), + MT7988_PIN(22, "SPI0_WP"), + MT7988_PIN(23, "SPI0_HOLD"), + MT7988_PIN(24, "SPI0_CSB"), + MT7988_PIN(25, "SPI0_MISO"), + MT7988_PIN(26, "SPI0_MOSI"), + MT7988_PIN(27, "SPI0_CLK"), + MT7988_PIN(28, "SPI1_CSB"), + MT7988_PIN(29, "SPI1_MISO"), + MT7988_PIN(30, "SPI1_MOSI"), + MT7988_PIN(31, "SPI1_CLK"), + MT7988_PIN(32, "SPI2_CLK"), + MT7988_PIN(33, "SPI2_MOSI"), + MT7988_PIN(34, "SPI2_MISO"), + MT7988_PIN(35, "SPI2_CSB"), + MT7988_PIN(36, "SPI2_HOLD"), + MT7988_PIN(37, "SPI2_WP"), + MT7988_PIN(38, "EMMC_RSTB"), + MT7988_PIN(39, "EMMC_DSL"), + MT7988_PIN(40, "EMMC_CK"), + MT7988_PIN(41, "EMMC_CMD"), + MT7988_PIN(42, "EMMC_DATA_7"), + MT7988_PIN(43, "EMMC_DATA_6"), + MT7988_PIN(44, "EMMC_DATA_5"), + MT7988_PIN(45, "EMMC_DATA_4"), + MT7988_PIN(46, "EMMC_DATA_3"), + MT7988_PIN(47, "EMMC_DATA_2"), + MT7988_PIN(48, "EMMC_DATA_1"), + MT7988_PIN(49, "EMMC_DATA_0"), + MT7988_PIN(50, "PCM_FS_I2S_LRCK"), + MT7988_PIN(51, "PCM_CLK_I2S_BCLK"), + MT7988_PIN(52, "PCM_DRX_I2S_DIN"), + MT7988_PIN(53, "PCM_DTX_I2S_DOUT"), + MT7988_PIN(54, "PCM_MCK_I2S_MCLK"), + MT7988_PIN(55, "UART0_RXD"), + MT7988_PIN(56, "UART0_TXD"), + MT7988_PIN(57, "PWMD0"), + MT7988_PIN(58, "JTAG_JTDI"), + MT7988_PIN(59, "JTAG_JTDO"), + MT7988_PIN(60, "JTAG_JTMS"), + MT7988_PIN(61, "JTAG_JTCLK"), + MT7988_PIN(62, "JTAG_JTRST_N"), + MT7988_PIN(63, "USB_DRV_VBUS_P1"), + MT7988_PIN(64, "LED_A"), + MT7988_PIN(65, "LED_B"), + MT7988_PIN(66, "LED_C"), + MT7988_PIN(67, "LED_D"), + MT7988_PIN(68, "LED_E"), + MT7988_PIN(69, "GPIO_B"), + MT7988_PIN(70, "GPIO_C"), + MT7988_PIN(71, "I2C_2_SCL"), + MT7988_PIN(72, "I2C_2_SDA"), + MT7988_PIN(73, "PCIE30_2L_1_PRESET_N"), + MT7988_PIN(74, "PCIE30_1L_0_PRESET_N"), + MT7988_PIN(75, "PCIE30_2L_1_WAKE_N"), + MT7988_PIN(76, "PCIE30_2L_1_CLKREQ_N"), + MT7988_PIN(77, "PCIE30_1L_0_WAKE_N"), + MT7988_PIN(78, "PCIE30_1L_0_CLKREQ_N"), + MT7988_PIN(79, "USB_DRV_VBUS_P0"), + MT7988_PIN(80, "UART1_RXD"), + MT7988_PIN(81, "UART1_TXD"), + MT7988_PIN(82, "UART1_CTS"), + MT7988_PIN(83, "UART1_RTS"), +}; + +/* jtag */ +static const int mt7988_tops_jtag0_0_pins[] = { 0, 1, 2, 3, 4 }; +static int mt7988_tops_jtag0_0_funcs[] = { 2, 2, 2, 2, 2 }; + +static const int mt7988_wo0_jtag_pins[] = { 50, 51, 52, 53, 54 }; +static int mt7988_wo0_jtag_funcs[] = { 3, 3, 3, 3, 3 }; + +static const int mt7988_wo1_jtag_pins[] = { 50, 51, 52, 53, 54 }; +static int mt7988_wo1_jtag_funcs[] = { 4, 4, 4, 4, 4 }; + +static const int mt7988_wo2_jtag_pins[] = { 50, 51, 52, 53, 54 }; +static int mt7988_wo2_jtag_funcs[] = { 5, 5, 5, 5, 5 }; + +static const int mt7988_jtag_pins[] = { 58, 59, 60, 61, 62 }; +static int mt7988_jtag_funcs[] = { 1, 1, 1, 1, 1 }; + +static const int mt7988_tops_jtag0_1_pins[] = { 58, 59, 60, 61, 62 }; +static int mt7988_tops_jtag0_1_funcs[] = { 4, 4, 4, 4, 4 }; + +/* int_usxgmii */ +static const int mt7988_int_usxgmii_pins[] = { 2, 3 }; +static int mt7988_int_usxgmii_funcs[] = { 3, 3 }; + +/* pwm */ +static const int mt7988_pwm0_pins[] = { 57 }; +static int mt7988_pwm0_funcs[] = { 1 }; + +static const int mt7988_pwm1_pins[] = { 21 }; +static int mt7988_pwm1_funcs[] = { 1 }; + +static const int mt7988_pwm2_pins[] = { 80 }; +static int mt7988_pwm2_funcs[] = { 2 }; + +static const int mt7988_pwm2_0_pins[] = { 58 }; +static int mt7988_pwm2_0_funcs[] = { 5 }; + +static const int mt7988_pwm3_pins[] = { 81 }; +static int mt7988_pwm3_funcs[] = { 2 }; + +static const int mt7988_pwm3_0_pins[] = { 59 }; +static int mt7988_pwm3_0_funcs[] = { 5 }; + +static const int mt7988_pwm4_pins[] = { 82 }; +static int mt7988_pwm4_funcs[] = { 2 }; + +static const int mt7988_pwm4_0_pins[] = { 60 }; +static int mt7988_pwm4_0_funcs[] = { 5 }; + +static const int mt7988_pwm5_pins[] = { 83 }; +static int mt7988_pwm5_funcs[] = { 2 }; + +static const int mt7988_pwm5_0_pins[] = { 61 }; +static int mt7988_pwm5_0_funcs[] = { 5 }; + +static const int mt7988_pwm6_pins[] = { 69 }; +static int mt7988_pwm6_funcs[] = { 3 }; + +static const int mt7988_pwm6_0_pins[] = { 62 }; +static int mt7988_pwm6_0_funcs[] = { 5 }; + +static const int mt7988_pwm7_pins[] = { 70 }; +static int mt7988_pwm7_funcs[] = { 3 }; + +static const int mt7988_pwm7_0_pins[] = { 4 }; +static int mt7988_pwm7_0_funcs[] = { 3 }; + +/* dfd */ +static const int mt7988_dfd_pins[] = { 0, 1, 2, 3, 4 }; +static int mt7988_dfd_funcs[] = { 4, 4, 4, 4, 4 }; + +/* i2c */ +static const int mt7988_xfi_phy0_i2c0_pins[] = { 0, 1 }; +static int mt7988_xfi_phy0_i2c0_funcs[] = { 5, 5 }; + +static const int mt7988_xfi_phy1_i2c0_pins[] = { 0, 1 }; +static int mt7988_xfi_phy1_i2c0_funcs[] = { 6, 6 }; + +static const int mt7988_xfi_phy_pll_i2c0_pins[] = { 3, 4 }; +static int mt7988_xfi_phy_pll_i2c0_funcs[] = { 5, 5 }; + +static const int mt7988_xfi_phy_pll_i2c1_pins[] = { 3, 4 }; +static int mt7988_xfi_phy_pll_i2c1_funcs[] = { 6, 6 }; + +static const int mt7988_i2c0_0_pins[] = { 5, 6 }; +static int mt7988_i2c0_0_funcs[] = { 2, 2 }; + +static const int mt7988_i2c1_sfp_pins[] = { 5, 6 }; +static int mt7988_i2c1_sfp_funcs[] = { 4, 4 }; + +static const int mt7988_xfi_pextp_phy0_i2c_pins[] = { 5, 6 }; +static int mt7988_xfi_pextp_phy0_i2c_funcs[] = { 5, 5 }; + +static const int mt7988_xfi_pextp_phy1_i2c_pins[] = { 5, 6 }; +static int mt7988_xfi_pextp_phy1_i2c_funcs[] = { 6, 6 }; + +static const int mt7988_i2c0_1_pins[] = { 15, 16 }; +static int mt7988_i2c0_1_funcs[] = { 1, 1 }; + +static const int mt7988_u30_phy_i2c0_pins[] = { 15, 16 }; +static int mt7988_u30_phy_i2c0_funcs[] = { 2, 2 }; + +static const int mt7988_u32_phy_i2c0_pins[] = { 15, 16 }; +static int mt7988_u32_phy_i2c0_funcs[] = { 3, 3 }; + +static const int mt7988_xfi_phy0_i2c1_pins[] = { 15, 16 }; +static int mt7988_xfi_phy0_i2c1_funcs[] = { 5, 5 }; + +static const int mt7988_xfi_phy1_i2c1_pins[] = { 15, 16 }; +static int mt7988_xfi_phy1_i2c1_funcs[] = { 6, 6 }; + +static const int mt7988_xfi_phy_pll_i2c2_pins[] = { 15, 16 }; +static int mt7988_xfi_phy_pll_i2c2_funcs[] = { 7, 7 }; + +static const int mt7988_i2c1_0_pins[] = { 17, 18 }; +static int mt7988_i2c1_0_funcs[] = { 1, 1 }; + +static const int mt7988_u30_phy_i2c1_pins[] = { 17, 18 }; +static int mt7988_u30_phy_i2c1_funcs[] = { 2, 2 }; + +static const int mt7988_u32_phy_i2c1_pins[] = { 17, 18 }; +static int mt7988_u32_phy_i2c1_funcs[] = { 3, 3 }; + +static const int mt7988_xfi_phy_pll_i2c3_pins[] = { 17, 18 }; +static int mt7988_xfi_phy_pll_i2c3_funcs[] = { 4, 4 }; + +static const int mt7988_sgmii0_i2c_pins[] = { 17, 18 }; +static int mt7988_sgmii0_i2c_funcs[] = { 5, 5 }; + +static const int mt7988_sgmii1_i2c_pins[] = { 17, 18 }; +static int mt7988_sgmii1_i2c_funcs[] = { 6, 6 }; + +static const int mt7988_i2c1_2_pins[] = { 69, 70 }; +static int mt7988_i2c1_2_funcs[] = { 2, 2 }; + +static const int mt7988_i2c2_0_pins[] = { 69, 70 }; +static int mt7988_i2c2_0_funcs[] = { 4, 4 }; + +static const int mt7988_i2c2_1_pins[] = { 71, 72 }; +static int mt7988_i2c2_1_funcs[] = { 1, 1 }; + +/* eth */ +static const int mt7988_mdc_mdio0_pins[] = { 5, 6 }; +static int mt7988_mdc_mdio0_funcs[] = { 1, 1 }; + +static const int mt7988_2p5g_ext_mdio_pins[] = { 28, 29 }; +static int mt7988_2p5g_ext_mdio_funcs[] = { 6, 6 }; + +static const int mt7988_gbe_ext_mdio_pins[] = { 30, 31 }; +static int mt7988_gbe_ext_mdio_funcs[] = { 6, 6 }; + +static const int mt7988_mdc_mdio1_pins[] = { 69, 70 }; +static int mt7988_mdc_mdio1_funcs[] = { 1, 1 }; + +/* pcie */ +static const int mt7988_pcie_wake_n0_0_pins[] = { 7 }; +static int mt7988_pcie_wake_n0_0_funcs[] = { 1 }; + +static const int mt7988_pcie_clk_req_n0_0_pins[] = { 8 }; +static int mt7988_pcie_clk_req_n0_0_funcs[] = { 1 }; + +static const int mt7988_pcie_wake_n3_0_pins[] = { 9 }; +static int mt7988_pcie_wake_n3_0_funcs[] = { 1 }; + +static const int mt7988_pcie_clk_req_n3_pins[] = { 10 }; +static int mt7988_pcie_clk_req_n3_funcs[] = { 1 }; + +static const int mt7988_pcie_clk_req_n0_1_pins[] = { 10 }; +static int mt7988_pcie_clk_req_n0_1_funcs[] = { 2 }; + +static const int mt7988_pcie_p0_phy_i2c_pins[] = { 7, 8 }; +static int mt7988_pcie_p0_phy_i2c_funcs[] = { 3, 3 }; + +static const int mt7988_pcie_p1_phy_i2c_pins[] = { 7, 8 }; +static int mt7988_pcie_p1_phy_i2c_funcs[] = { 4, 4 }; + +static const int mt7988_pcie_p3_phy_i2c_pins[] = { 9, 10 }; +static int mt7988_pcie_p3_phy_i2c_funcs[] = { 4, 4 }; + +static const int mt7988_pcie_p2_phy_i2c_pins[] = { 7, 8 }; +static int mt7988_pcie_p2_phy_i2c_funcs[] = { 5, 5 }; + +static const int mt7988_ckm_phy_i2c_pins[] = { 9, 10 }; +static int mt7988_ckm_phy_i2c_funcs[] = { 5, 5 }; + +static const int mt7988_pcie_wake_n0_1_pins[] = { 13 }; +static int mt7988_pcie_wake_n0_1_funcs[] = { 2 }; + +static const int mt7988_pcie_wake_n3_1_pins[] = { 14 }; +static int mt7988_pcie_wake_n3_1_funcs[] = { 2 }; + +static const int mt7988_pcie_2l_0_pereset_pins[] = { 19 }; +static int mt7988_pcie_2l_0_pereset_funcs[] = { 1 }; + +static const int mt7988_pcie_1l_1_pereset_pins[] = { 20 }; +static int mt7988_pcie_1l_1_pereset_funcs[] = { 1 }; + +static const int mt7988_pcie_clk_req_n2_1_pins[] = { 63 }; +static int mt7988_pcie_clk_req_n2_1_funcs[] = { 2 }; + +static const int mt7988_pcie_2l_1_pereset_pins[] = { 73 }; +static int mt7988_pcie_2l_1_pereset_funcs[] = { 1 }; + +static const int mt7988_pcie_1l_0_pereset_pins[] = { 74 }; +static int mt7988_pcie_1l_0_pereset_funcs[] = { 1 }; + +static const int mt7988_pcie_wake_n1_0_pins[] = { 75 }; +static int mt7988_pcie_wake_n1_0_funcs[] = { 1 }; + +static const int mt7988_pcie_clk_req_n1_pins[] = { 76 }; +static int mt7988_pcie_clk_req_n1_funcs[] = { 1 }; + +static const int mt7988_pcie_wake_n2_0_pins[] = { 77 }; +static int mt7988_pcie_wake_n2_0_funcs[] = { 1 }; + +static const int mt7988_pcie_clk_req_n2_0_pins[] = { 78 }; +static int mt7988_pcie_clk_req_n2_0_funcs[] = { 1 }; + +static const int mt7988_pcie_wake_n2_1_pins[] = { 79 }; +static int mt7988_pcie_wake_n2_1_funcs[] = { 2 }; + +/* pmic */ +static const int mt7988_pmic_pins[] = { 11 }; +static int mt7988_pmic_funcs[] = { 1 }; + +/* watchdog */ +static const int mt7988_watchdog_pins[] = { 12 }; +static int mt7988_watchdog_funcs[] = { 1 }; + +/* spi */ +static const int mt7988_spi0_wp_hold_pins[] = { 22, 23 }; +static int mt7988_spi0_wp_hold_funcs[] = { 1, 1 }; + +static const int mt7988_spi0_pins[] = { 24, 25, 26, 27 }; +static int mt7988_spi0_funcs[] = { 1, 1, 1, 1 }; + +static const int mt7988_spi1_pins[] = { 28, 29, 30, 31 }; +static int mt7988_spi1_funcs[] = { 1, 1, 1, 1 }; + +static const int mt7988_spi2_pins[] = { 32, 33, 34, 35 }; +static int mt7988_spi2_funcs[] = { 1, 1, 1, 1 }; + +static const int mt7988_spi2_wp_hold_pins[] = { 36, 37 }; +static int mt7988_spi2_wp_hold_funcs[] = { 1, 1 }; + +/* flash */ +static const int mt7988_snfi_pins[] = { 22, 23, 24, 25, 26, 27 }; +static int mt7988_snfi_funcs[] = { 2, 2, 2, 2, 2, 2 }; + +static const int mt7988_emmc_45_pins[] = { + 21, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37 +}; +static int mt7988_emmc_45_funcs[] = { 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5 }; + +static const int mt7988_sdcard_pins[] = { 32, 33, 34, 35, 36, 37 }; +static int mt7988_sdcard_funcs[] = { 5, 5, 5, 5, 5, 5 }; + +static const int mt7988_emmc_51_pins[] = { 38, 39, 40, 41, 42, 43, + 44, 45, 46, 47, 48, 49 }; +static int mt7988_emmc_51_funcs[] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }; + +/* uart */ +static const int mt7988_uart2_pins[] = { 0, 1, 2, 3 }; +static int mt7988_uart2_funcs[] = { 1, 1, 1, 1 }; + +static const int mt7988_tops_uart0_0_pins[] = { 22, 23 }; +static int mt7988_tops_uart0_0_funcs[] = { 3, 3 }; + +static const int mt7988_uart2_0_pins[] = { 28, 29, 30, 31 }; +static int mt7988_uart2_0_funcs[] = { 2, 2, 2, 2 }; + +static const int mt7988_uart1_0_pins[] = { 32, 33, 34, 35 }; +static int mt7988_uart1_0_funcs[] = { 2, 2, 2, 2 }; + +static const int mt7988_uart2_1_pins[] = { 32, 33, 34, 35 }; +static int mt7988_uart2_1_funcs[] = { 3, 3, 3, 3 }; + +static const int mt7988_net_wo0_uart_txd_0_pins[] = { 28 }; +static int mt7988_net_wo0_uart_txd_0_funcs[] = { 3 }; + +static const int mt7988_net_wo1_uart_txd_0_pins[] = { 29 }; +static int mt7988_net_wo1_uart_txd_0_funcs[] = { 3 }; + +static const int mt7988_net_wo2_uart_txd_0_pins[] = { 30 }; +static int mt7988_net_wo2_uart_txd_0_funcs[] = { 3 }; + +static const int mt7988_tops_uart1_0_pins[] = { 28, 29 }; +static int mt7988_tops_uart1_0_funcs[] = { 4, 4 }; + +static const int mt7988_tops_uart0_1_pins[] = { 30, 31 }; +static int mt7988_tops_uart0_1_funcs[] = { 4, 4 }; + +static const int mt7988_tops_uart1_1_pins[] = { 36, 37 }; +static int mt7988_tops_uart1_1_funcs[] = { 3, 3 }; + +static const int mt7988_uart0_pins[] = { 55, 56 }; +static int mt7988_uart0_funcs[] = { 1, 1 }; + +static const int mt7988_tops_uart0_2_pins[] = { 55, 56 }; +static int mt7988_tops_uart0_2_funcs[] = { 2, 2 }; + +static const int mt7988_uart2_2_pins[] = { 50, 51, 52, 53 }; +static int mt7988_uart2_2_funcs[] = { 2, 2, 2, 2 }; + +static const int mt7988_uart1_1_pins[] = { 58, 59, 60, 61 }; +static int mt7988_uart1_1_funcs[] = { 2, 2, 2, 2 }; + +static const int mt7988_uart2_3_pins[] = { 58, 59, 60, 61 }; +static int mt7988_uart2_3_funcs[] = { 3, 3, 3, 3 }; + +static const int mt7988_uart1_2_pins[] = { 80, 81, 82, 83 }; +static int mt7988_uart1_2_funcs[] = { 1, 1, 1, 1 }; + +static const int mt7988_uart1_2_lite_pins[] = { 80, 81 }; +static int mt7988_uart1_2_lite_funcs[] = { 1, 1 }; + +static const int mt7988_tops_uart1_2_pins[] = { 80, 81 }; +static int mt7988_tops_uart1_2_funcs[] = { 4, 4, }; + +static const int mt7988_net_wo0_uart_txd_1_pins[] = { 80 }; +static int mt7988_net_wo0_uart_txd_1_funcs[] = { 3 }; + +static const int mt7988_net_wo1_uart_txd_1_pins[] = { 81 }; +static int mt7988_net_wo1_uart_txd_1_funcs[] = { 3 }; + +static const int mt7988_net_wo2_uart_txd_1_pins[] = { 82 }; +static int mt7988_net_wo2_uart_txd_1_funcs[] = { 3 }; + +/* udi */ +static const int mt7988_udi_pins[] = { 32, 33, 34, 35, 36 }; +static int mt7988_udi_funcs[] = { 4, 4, 4, 4, 4 }; + +/* i2s */ +static const int mt7988_i2s_pins[] = { 50, 51, 52, 53, 54 }; +static int mt7988_i2s_funcs[] = { 1, 1, 1, 1, 1 }; + +/* pcm */ +static const int mt7988_pcm_pins[] = { 50, 51, 52, 53 }; +static int mt7988_pcm_funcs[] = { 1, 1, 1, 1 }; + +/* led */ +static const int mt7988_gbe0_led1_pins[] = { 58 }; +static int mt7988_gbe0_led1_funcs[] = { 6 }; +static const int mt7988_gbe1_led1_pins[] = { 59 }; +static int mt7988_gbe1_led1_funcs[] = { 6 }; +static const int mt7988_gbe2_led1_pins[] = { 60 }; +static int mt7988_gbe2_led1_funcs[] = { 6 }; +static const int mt7988_gbe3_led1_pins[] = { 61 }; +static int mt7988_gbe3_led1_funcs[] = { 6 }; + +static const int mt7988_2p5gbe_led1_pins[] = { 62 }; +static int mt7988_2p5gbe_led1_funcs[] = { 6 }; + +static const int mt7988_gbe0_led0_pins[] = { 64 }; +static int mt7988_gbe0_led0_funcs[] = { 1 }; +static const int mt7988_gbe1_led0_pins[] = { 65 }; +static int mt7988_gbe1_led0_funcs[] = { 1 }; +static const int mt7988_gbe2_led0_pins[] = { 66 }; +static int mt7988_gbe2_led0_funcs[] = { 1 }; +static const int mt7988_gbe3_led0_pins[] = { 67 }; +static int mt7988_gbe3_led0_funcs[] = { 1 }; + +static const int mt7988_2p5gbe_led0_pins[] = { 68 }; +static int mt7988_2p5gbe_led0_funcs[] = { 1 }; + +/* usb */ +static const int mt7988_drv_vbus_p1_pins[] = { 63 }; +static int mt7988_drv_vbus_p1_funcs[] = { 1 }; + +static const int mt7988_drv_vbus_pins[] = { 79 }; +static int mt7988_drv_vbus_funcs[] = { 1 }; + +static const struct group_desc mt7988_groups[] = { + /* @GPIO(0,1,2,3): uart2 */ + PINCTRL_PIN_GROUP("uart2", mt7988_uart2), + /* @GPIO(0,1,2,3,4): tops_jtag0_0 */ + PINCTRL_PIN_GROUP("tops_jtag0_0", mt7988_tops_jtag0_0), + /* @GPIO(2,3): int_usxgmii */ + PINCTRL_PIN_GROUP("int_usxgmii", mt7988_int_usxgmii), + /* @GPIO(0,1,2,3,4): dfd */ + PINCTRL_PIN_GROUP("dfd", mt7988_dfd), + /* @GPIO(0,1): xfi_phy0_i2c0 */ + PINCTRL_PIN_GROUP("xfi_phy0_i2c0", mt7988_xfi_phy0_i2c0), + /* @GPIO(0,1): xfi_phy1_i2c0 */ + PINCTRL_PIN_GROUP("xfi_phy1_i2c0", mt7988_xfi_phy1_i2c0), + /* @GPIO(3,4): xfi_phy_pll_i2c0 */ + PINCTRL_PIN_GROUP("xfi_phy_pll_i2c0", mt7988_xfi_phy_pll_i2c0), + /* @GPIO(3,4): xfi_phy_pll_i2c1 */ + PINCTRL_PIN_GROUP("xfi_phy_pll_i2c1", mt7988_xfi_phy_pll_i2c1), + /* @GPIO(4): pwm7 */ + PINCTRL_PIN_GROUP("pwm7_0", mt7988_pwm7_0), + /* @GPIO(5,6) i2c0_0 */ + PINCTRL_PIN_GROUP("i2c0_0", mt7988_i2c0_0), + /* @GPIO(5,6) i2c1_sfp */ + PINCTRL_PIN_GROUP("i2c1_sfp", mt7988_i2c1_sfp), + /* @GPIO(5,6) xfi_pextp_phy0_i2c */ + PINCTRL_PIN_GROUP("xfi_pextp_phy0_i2c", mt7988_xfi_pextp_phy0_i2c), + /* @GPIO(5,6) xfi_pextp_phy1_i2c */ + PINCTRL_PIN_GROUP("xfi_pextp_phy1_i2c", mt7988_xfi_pextp_phy1_i2c), + /* @GPIO(5,6) mdc_mdio0 */ + PINCTRL_PIN_GROUP("mdc_mdio0", mt7988_mdc_mdio0), + /* @GPIO(7): pcie_wake_n0_0 */ + PINCTRL_PIN_GROUP("pcie_wake_n0_0", mt7988_pcie_wake_n0_0), + /* @GPIO(8): pcie_clk_req_n0_0 */ + PINCTRL_PIN_GROUP("pcie_clk_req_n0_0", mt7988_pcie_clk_req_n0_0), + /* @GPIO(9): pcie_wake_n3_0 */ + PINCTRL_PIN_GROUP("pcie_wake_n3_0", mt7988_pcie_wake_n3_0), + /* @GPIO(10): pcie_clk_req_n3 */ + PINCTRL_PIN_GROUP("pcie_clk_req_n3", mt7988_pcie_clk_req_n3), + /* @GPIO(10): pcie_clk_req_n0_1 */ + PINCTRL_PIN_GROUP("pcie_clk_req_n0_1", mt7988_pcie_clk_req_n0_1), + /* @GPIO(7,8) pcie_p0_phy_i2c */ + PINCTRL_PIN_GROUP("pcie_p0_phy_i2c", mt7988_pcie_p0_phy_i2c), + /* @GPIO(7,8) pcie_p1_phy_i2c */ + PINCTRL_PIN_GROUP("pcie_p1_phy_i2c", mt7988_pcie_p1_phy_i2c), + /* @GPIO(7,8) pcie_p2_phy_i2c */ + PINCTRL_PIN_GROUP("pcie_p2_phy_i2c", mt7988_pcie_p2_phy_i2c), + /* @GPIO(9,10) pcie_p3_phy_i2c */ + PINCTRL_PIN_GROUP("pcie_p3_phy_i2c", mt7988_pcie_p3_phy_i2c), + /* @GPIO(9,10) ckm_phy_i2c */ + PINCTRL_PIN_GROUP("ckm_phy_i2c", mt7988_ckm_phy_i2c), + /* @GPIO(11): pmic */ + PINCTRL_PIN_GROUP("pcie_pmic", mt7988_pmic), + /* @GPIO(12): watchdog */ + PINCTRL_PIN_GROUP("watchdog", mt7988_watchdog), + /* @GPIO(13): pcie_wake_n0_1 */ + PINCTRL_PIN_GROUP("pcie_wake_n0_1", mt7988_pcie_wake_n0_1), + /* @GPIO(14): pcie_wake_n3_1 */ + PINCTRL_PIN_GROUP("pcie_wake_n3_1", mt7988_pcie_wake_n3_1), + /* @GPIO(15,16) i2c0_1 */ + PINCTRL_PIN_GROUP("i2c0_1", mt7988_i2c0_1), + /* @GPIO(15,16) u30_phy_i2c0 */ + PINCTRL_PIN_GROUP("u30_phy_i2c0", mt7988_u30_phy_i2c0), + /* @GPIO(15,16) u32_phy_i2c0 */ + PINCTRL_PIN_GROUP("u32_phy_i2c0", mt7988_u32_phy_i2c0), + /* @GPIO(15,16) xfi_phy0_i2c1 */ + PINCTRL_PIN_GROUP("xfi_phy0_i2c1", mt7988_xfi_phy0_i2c1), + /* @GPIO(15,16) xfi_phy1_i2c1 */ + PINCTRL_PIN_GROUP("xfi_phy1_i2c1", mt7988_xfi_phy1_i2c1), + /* @GPIO(15,16) xfi_phy_pll_i2c2 */ + PINCTRL_PIN_GROUP("xfi_phy_pll_i2c2", mt7988_xfi_phy_pll_i2c2), + /* @GPIO(17,18) i2c1_0 */ + PINCTRL_PIN_GROUP("i2c1_0", mt7988_i2c1_0), + /* @GPIO(17,18) u30_phy_i2c1 */ + PINCTRL_PIN_GROUP("u30_phy_i2c1", mt7988_u30_phy_i2c1), + /* @GPIO(17,18) u32_phy_i2c1 */ + PINCTRL_PIN_GROUP("u32_phy_i2c1", mt7988_u32_phy_i2c1), + /* @GPIO(17,18) xfi_phy_pll_i2c3 */ + PINCTRL_PIN_GROUP("xfi_phy_pll_i2c3", mt7988_xfi_phy_pll_i2c3), + /* @GPIO(17,18) sgmii0_i2c */ + PINCTRL_PIN_GROUP("sgmii0_i2c", mt7988_sgmii0_i2c), + /* @GPIO(17,18) sgmii1_i2c */ + PINCTRL_PIN_GROUP("sgmii1_i2c", mt7988_sgmii1_i2c), + /* @GPIO(19): pcie_2l_0_pereset */ + PINCTRL_PIN_GROUP("pcie_2l_0_pereset", mt7988_pcie_2l_0_pereset), + /* @GPIO(20): pcie_1l_1_pereset */ + PINCTRL_PIN_GROUP("pcie_1l_1_pereset", mt7988_pcie_1l_1_pereset), + /* @GPIO(21): pwm1 */ + PINCTRL_PIN_GROUP("pwm1", mt7988_pwm1), + /* @GPIO(22,23) spi0_wp_hold */ + PINCTRL_PIN_GROUP("spi0_wp_hold", mt7988_spi0_wp_hold), + /* @GPIO(24,25,26,27) spi0 */ + PINCTRL_PIN_GROUP("spi0", mt7988_spi0), + /* @GPIO(28,29,30,31) spi1 */ + PINCTRL_PIN_GROUP("spi1", mt7988_spi1), + /* @GPIO(32,33,34,35) spi2 */ + PINCTRL_PIN_GROUP("spi2", mt7988_spi2), + /* @GPIO(36,37) spi2_wp_hold */ + PINCTRL_PIN_GROUP("spi2_wp_hold", mt7988_spi2_wp_hold), + /* @GPIO(22,23,24,25,26,27) snfi */ + PINCTRL_PIN_GROUP("snfi", mt7988_snfi), + /* @GPIO(22,23) tops_uart0_0 */ + PINCTRL_PIN_GROUP("tops_uart0_0", mt7988_tops_uart0_0), + /* @GPIO(28,29,30,31) uart2_0 */ + PINCTRL_PIN_GROUP("uart2_0", mt7988_uart2_0), + /* @GPIO(32,33,34,35) uart1_0 */ + PINCTRL_PIN_GROUP("uart1_0", mt7988_uart1_0), + /* @GPIO(32,33,34,35) uart2_1 */ + PINCTRL_PIN_GROUP("uart2_1", mt7988_uart2_1), + /* @GPIO(28) net_wo0_uart_txd_0 */ + PINCTRL_PIN_GROUP("net_wo0_uart_txd_0", mt7988_net_wo0_uart_txd_0), + /* @GPIO(29) net_wo1_uart_txd_0 */ + PINCTRL_PIN_GROUP("net_wo1_uart_txd_0", mt7988_net_wo1_uart_txd_0), + /* @GPIO(30) net_wo2_uart_txd_0 */ + PINCTRL_PIN_GROUP("net_wo2_uart_txd_0", mt7988_net_wo2_uart_txd_0), + /* @GPIO(28,29) tops_uart1_0 */ + PINCTRL_PIN_GROUP("tops_uart0_0", mt7988_tops_uart1_0), + /* @GPIO(30,31) tops_uart0_1 */ + PINCTRL_PIN_GROUP("tops_uart0_1", mt7988_tops_uart0_1), + /* @GPIO(36,37) tops_uart1_1 */ + PINCTRL_PIN_GROUP("tops_uart1_1", mt7988_tops_uart1_1), + /* @GPIO(32,33,34,35,36) udi */ + PINCTRL_PIN_GROUP("udi", mt7988_udi), + /* @GPIO(21,28,29,30,31,32,33,34,35,36,37) emmc_45 */ + PINCTRL_PIN_GROUP("emmc_45", mt7988_emmc_45), + /* @GPIO(32,33,34,35,36,37) sdcard */ + PINCTRL_PIN_GROUP("sdcard", mt7988_sdcard), + /* @GPIO(38,39,40,41,42,43,44,45,46,47,48,49) emmc_51 */ + PINCTRL_PIN_GROUP("emmc_51", mt7988_emmc_51), + /* @GPIO(28,29) 2p5g_ext_mdio */ + PINCTRL_PIN_GROUP("2p5g_ext_mdio", mt7988_2p5g_ext_mdio), + /* @GPIO(30,31) gbe_ext_mdio */ + PINCTRL_PIN_GROUP("gbe_ext_mdio", mt7988_gbe_ext_mdio), + /* @GPIO(50,51,52,53,54) i2s */ + PINCTRL_PIN_GROUP("i2s", mt7988_i2s), + /* @GPIO(50,51,52,53) pcm */ + PINCTRL_PIN_GROUP("pcm", mt7988_pcm), + /* @GPIO(55,56) uart0 */ + PINCTRL_PIN_GROUP("uart0", mt7988_uart0), + /* @GPIO(55,56) tops_uart0_2 */ + PINCTRL_PIN_GROUP("tops_uart0_2", mt7988_tops_uart0_2), + /* @GPIO(50,51,52,53) uart2_2 */ + PINCTRL_PIN_GROUP("uart2_2", mt7988_uart2_2), + /* @GPIO(50,51,52,53,54) wo0_jtag */ + PINCTRL_PIN_GROUP("wo0_jtag", mt7988_wo0_jtag), + /* @GPIO(50,51,52,53,54) wo1-wo1_jtag */ + PINCTRL_PIN_GROUP("wo1_jtag", mt7988_wo1_jtag), + /* @GPIO(50,51,52,53,54) wo2_jtag */ + PINCTRL_PIN_GROUP("wo2_jtag", mt7988_wo2_jtag), + /* @GPIO(57) pwm0 */ + PINCTRL_PIN_GROUP("pwm0", mt7988_pwm0), + /* @GPIO(58) pwm2_0 */ + PINCTRL_PIN_GROUP("pwm2_0", mt7988_pwm2_0), + /* @GPIO(59) pwm3_0 */ + PINCTRL_PIN_GROUP("pwm3_0", mt7988_pwm3_0), + /* @GPIO(60) pwm4_0 */ + PINCTRL_PIN_GROUP("pwm4_0", mt7988_pwm4_0), + /* @GPIO(61) pwm5_0 */ + PINCTRL_PIN_GROUP("pwm5_0", mt7988_pwm5_0), + /* @GPIO(58,59,60,61,62) jtag */ + PINCTRL_PIN_GROUP("jtag", mt7988_jtag), + /* @GPIO(58,59,60,61,62) tops_jtag0_1 */ + PINCTRL_PIN_GROUP("tops_jtag0_1", mt7988_tops_jtag0_1), + /* @GPIO(58,59,60,61) uart2_3 */ + PINCTRL_PIN_GROUP("uart2_3", mt7988_uart2_3), + /* @GPIO(58,59,60,61) uart1_1 */ + PINCTRL_PIN_GROUP("uart1_1", mt7988_uart1_1), + /* @GPIO(58,59,60,61) gbe_led1 */ + PINCTRL_PIN_GROUP("gbe0_led1", mt7988_gbe0_led1), + PINCTRL_PIN_GROUP("gbe1_led1", mt7988_gbe1_led1), + PINCTRL_PIN_GROUP("gbe2_led1", mt7988_gbe2_led1), + PINCTRL_PIN_GROUP("gbe3_led1", mt7988_gbe3_led1), + /* @GPIO(62) pwm6_0 */ + PINCTRL_PIN_GROUP("pwm6_0", mt7988_pwm6_0), + /* @GPIO(62) 2p5gbe_led1 */ + PINCTRL_PIN_GROUP("2p5gbe_led1", mt7988_2p5gbe_led1), + /* @GPIO(64,65,66,67) gbe_led0 */ + PINCTRL_PIN_GROUP("gbe0_led0", mt7988_gbe0_led0), + PINCTRL_PIN_GROUP("gbe1_led0", mt7988_gbe1_led0), + PINCTRL_PIN_GROUP("gbe2_led0", mt7988_gbe2_led0), + PINCTRL_PIN_GROUP("gbe3_led0", mt7988_gbe3_led0), + /* @GPIO(68) 2p5gbe_led0 */ + PINCTRL_PIN_GROUP("2p5gbe_led0", mt7988_2p5gbe_led0), + /* @GPIO(63) drv_vbus_p1 */ + PINCTRL_PIN_GROUP("drv_vbus_p1", mt7988_drv_vbus_p1), + /* @GPIO(63) pcie_clk_req_n2_1 */ + PINCTRL_PIN_GROUP("pcie_clk_req_n2_1", mt7988_pcie_clk_req_n2_1), + /* @GPIO(69, 70) mdc_mdio1 */ + PINCTRL_PIN_GROUP("mdc_mdio1", mt7988_mdc_mdio1), + /* @GPIO(69, 70) i2c1_2 */ + PINCTRL_PIN_GROUP("i2c1_2", mt7988_i2c1_2), + /* @GPIO(69) pwm6 */ + PINCTRL_PIN_GROUP("pwm6", mt7988_pwm6), + /* @GPIO(70) pwm7 */ + PINCTRL_PIN_GROUP("pwm7", mt7988_pwm7), + /* @GPIO(69,70) i2c2_0 */ + PINCTRL_PIN_GROUP("i2c2_0", mt7988_i2c2_0), + /* @GPIO(71,72) i2c2_1 */ + PINCTRL_PIN_GROUP("i2c2_1", mt7988_i2c2_1), + /* @GPIO(73) pcie_2l_1_pereset */ + PINCTRL_PIN_GROUP("pcie_2l_1_pereset", mt7988_pcie_2l_1_pereset), + /* @GPIO(74) pcie_1l_0_pereset */ + PINCTRL_PIN_GROUP("pcie_1l_0_pereset", mt7988_pcie_1l_0_pereset), + /* @GPIO(75) pcie_wake_n1_0 */ + PINCTRL_PIN_GROUP("pcie_wake_n1_0", mt7988_pcie_wake_n1_0), + /* @GPIO(76) pcie_clk_req_n1 */ + PINCTRL_PIN_GROUP("pcie_clk_req_n1", mt7988_pcie_clk_req_n1), + /* @GPIO(77) pcie_wake_n2_0 */ + PINCTRL_PIN_GROUP("pcie_wake_n2_0", mt7988_pcie_wake_n2_0), + /* @GPIO(78) pcie_clk_req_n2_0 */ + PINCTRL_PIN_GROUP("pcie_clk_req_n2_0", mt7988_pcie_clk_req_n2_0), + /* @GPIO(79) drv_vbus */ + PINCTRL_PIN_GROUP("drv_vbus", mt7988_drv_vbus), + /* @GPIO(79) pcie_wake_n2_1 */ + PINCTRL_PIN_GROUP("pcie_wake_n2_1", mt7988_pcie_wake_n2_1), + /* @GPIO(80,81,82,83) uart1_2 */ + PINCTRL_PIN_GROUP("uart1_2", mt7988_uart1_2), + /* @GPIO(80,81) uart1_2_lite */ + PINCTRL_PIN_GROUP("uart1_2_lite", mt7988_uart1_2_lite), + /* @GPIO(80) pwm2 */ + PINCTRL_PIN_GROUP("pwm2", mt7988_pwm2), + /* @GPIO(81) pwm3 */ + PINCTRL_PIN_GROUP("pwm3", mt7988_pwm3), + /* @GPIO(82) pwm4 */ + PINCTRL_PIN_GROUP("pwm4", mt7988_pwm4), + /* @GPIO(83) pwm5 */ + PINCTRL_PIN_GROUP("pwm5", mt7988_pwm5), + /* @GPIO(80) net_wo0_uart_txd_0 */ + PINCTRL_PIN_GROUP("net_wo0_uart_txd_0", mt7988_net_wo0_uart_txd_0), + /* @GPIO(81) net_wo1_uart_txd_0 */ + PINCTRL_PIN_GROUP("net_wo1_uart_txd_0", mt7988_net_wo1_uart_txd_0), + /* @GPIO(82) net_wo2_uart_txd_0 */ + PINCTRL_PIN_GROUP("net_wo2_uart_txd_0", mt7988_net_wo2_uart_txd_0), + /* @GPIO(80,81) tops_uart1_2 */ + PINCTRL_PIN_GROUP("tops_uart1_2", mt7988_tops_uart1_2), + /* @GPIO(80) net_wo0_uart_txd_1 */ + PINCTRL_PIN_GROUP("net_wo0_uart_txd_1", mt7988_net_wo0_uart_txd_1), + /* @GPIO(81) net_wo1_uart_txd_1 */ + PINCTRL_PIN_GROUP("net_wo1_uart_txd_1", mt7988_net_wo1_uart_txd_1), + /* @GPIO(82) net_wo2_uart_txd_1 */ + PINCTRL_PIN_GROUP("net_wo2_uart_txd_1", mt7988_net_wo2_uart_txd_1), +}; + +/* Joint those groups owning the same capability in user point of view which + * allows that people tend to use through the device tree. + */ +static const char * const mt7988_jtag_groups[] = { + "tops_jtag0_0", "wo0_jtag", "wo1_jtag", + "wo2_jtag", "jtag", "tops_jtag0_1", +}; +static const char * const mt7988_int_usxgmii_groups[] = { + "int_usxgmii", +}; +static const char * const mt7988_pwm_groups[] = { + "pwm0", "pwm1", "pwm2", "pwm2_0", "pwm3", "pwm3_0", "pwm4", "pwm4_0", + "pwm5", "pwm5_0", "pwm6", "pwm6_0", "pwm7", "pwm7_0", + +}; +static const char * const mt7988_dfd_groups[] = { + "dfd", +}; +static const char * const mt7988_i2c_groups[] = { + "xfi_phy0_i2c0", + "xfi_phy1_i2c0", + "xfi_phy_pll_i2c0", + "xfi_phy_pll_i2c1", + "i2c0_0", + "i2c1_sfp", + "xfi_pextp_phy0_i2c", + "xfi_pextp_phy1_i2c", + "i2c0_1", + "u30_phy_i2c0", + "u32_phy_i2c0", + "xfi_phy0_i2c1", + "xfi_phy1_i2c1", + "xfi_phy_pll_i2c2", + "i2c1_0", + "u30_phy_i2c1", + "u32_phy_i2c1", + "xfi_phy_pll_i2c3", + "sgmii0_i2c", + "sgmii1_i2c", + "i2c1_2", + "i2c2_0", + "i2c2_1", +}; +static const char * const mt7988_ethernet_groups[] = { + "mdc_mdio0", + "2p5g_ext_mdio", + "gbe_ext_mdio", + "mdc_mdio1", +}; +static const char * const mt7988_pcie_groups[] = { + "pcie_wake_n0_0", "pcie_clk_req_n0_0", "pcie_wake_n3_0", + "pcie_clk_req_n3", "pcie_p0_phy_i2c", "pcie_p1_phy_i2c", + "pcie_p3_phy_i2c", "pcie_p2_phy_i2c", "ckm_phy_i2c", + "pcie_wake_n0_1", "pcie_wake_n3_1", "pcie_2l_0_pereset", + "pcie_1l_1_pereset", "pcie_clk_req_n2_1", "pcie_2l_1_pereset", + "pcie_1l_0_pereset", "pcie_wake_n1_0", "pcie_clk_req_n1", + "pcie_wake_n2_0", "pcie_clk_req_n2_0", "pcie_wake_n2_1", + "pcie_clk_req_n0_1" +}; +static const char * const mt7988_pmic_groups[] = { + "pmic", +}; +static const char * const mt7988_wdt_groups[] = { + "watchdog", +}; +static const char * const mt7988_spi_groups[] = { + "spi0", "spi0_wp_hold", "spi1", "spi2", "spi2_wp_hold", +}; +static const char * const mt7988_flash_groups[] = { "emmc_45", "sdcard", "snfi", + "emmc_51" }; +static const char * const mt7988_uart_groups[] = { + "uart2", + "tops_uart0_0", + "uart2_0", + "uart1_0", + "uart2_1", + "net_wo0_uart_txd_0", + "net_wo1_uart_txd_0", + "net_wo2_uart_txd_0", + "tops_uart1_0", + "ops_uart0_1", + "ops_uart1_1", + "uart0", + "tops_uart0_2", + "uart1_1", + "uart2_3", + "uart1_2", + "uart1_2_lite", + "tops_uart1_2", + "net_wo0_uart_txd_1", + "net_wo1_uart_txd_1", + "net_wo2_uart_txd_1", +}; +static const char * const mt7988_udi_groups[] = { + "udi", +}; +static const char * const mt7988_audio_groups[] = { + "i2s", "pcm", +}; +static const char * const mt7988_led_groups[] = { + "gbe0_led1", "gbe1_led1", "gbe2_led1", "gbe3_led1", "2p5gbe_led1", + "gbe0_led0", "gbe1_led0", "gbe2_led0", "gbe3_led0", "2p5gbe_led0", + "wf5g_led0", "wf5g_led1", +}; +static const char * const mt7988_usb_groups[] = { + "drv_vbus", + "drv_vbus_p1", +}; + +static const struct function_desc mt7988_functions[] = { + { { "audio", mt7988_audio_groups, ARRAY_SIZE(mt7988_audio_groups) }, + NULL }, + { { "jtag", mt7988_jtag_groups, ARRAY_SIZE(mt7988_jtag_groups) }, + NULL }, + { { "int_usxgmii", mt7988_int_usxgmii_groups, + ARRAY_SIZE(mt7988_int_usxgmii_groups) }, + NULL }, + { { "pwm", mt7988_pwm_groups, ARRAY_SIZE(mt7988_pwm_groups) }, NULL }, + { { "dfd", mt7988_dfd_groups, ARRAY_SIZE(mt7988_dfd_groups) }, NULL }, + { { "i2c", mt7988_i2c_groups, ARRAY_SIZE(mt7988_i2c_groups) }, NULL }, + { { "eth", mt7988_ethernet_groups, ARRAY_SIZE(mt7988_ethernet_groups) }, + NULL }, + { { "pcie", mt7988_pcie_groups, ARRAY_SIZE(mt7988_pcie_groups) }, + NULL }, + { { "pmic", mt7988_pmic_groups, ARRAY_SIZE(mt7988_pmic_groups) }, + NULL }, + { { "watchdog", mt7988_wdt_groups, ARRAY_SIZE(mt7988_wdt_groups) }, + NULL }, + { { "spi", mt7988_spi_groups, ARRAY_SIZE(mt7988_spi_groups) }, NULL }, + { { "flash", mt7988_flash_groups, ARRAY_SIZE(mt7988_flash_groups) }, + NULL }, + { { "uart", mt7988_uart_groups, ARRAY_SIZE(mt7988_uart_groups) }, + NULL }, + { { "udi", mt7988_udi_groups, ARRAY_SIZE(mt7988_udi_groups) }, NULL }, + { { "usb", mt7988_usb_groups, ARRAY_SIZE(mt7988_usb_groups) }, NULL }, + { { "led", mt7988_led_groups, ARRAY_SIZE(mt7988_led_groups) }, NULL }, +}; + +static const struct mtk_eint_hw mt7988_eint_hw = { + .port_mask = 7, + .ports = 7, + .ap_num = ARRAY_SIZE(mt7988_pins), + .db_cnt = 16, +}; + +static const char * const mt7988_pinctrl_register_base_names[] = { + "gpio", "iocfg_tr", "iocfg_br", + "iocfg_rb", "iocfg_lb", "iocfg_tl", +}; + +static const struct mtk_pin_soc mt7988_data = { + .reg_cal = mt7988_reg_cals, + .pins = mt7988_pins, + .npins = ARRAY_SIZE(mt7988_pins), + .grps = mt7988_groups, + .ngrps = ARRAY_SIZE(mt7988_groups), + .funcs = mt7988_functions, + .nfuncs = ARRAY_SIZE(mt7988_functions), + .eint_hw = &mt7988_eint_hw, + .gpio_m = 0, + .ies_present = false, + .base_names = mt7988_pinctrl_register_base_names, + .nbase_names = ARRAY_SIZE(mt7988_pinctrl_register_base_names), + .bias_disable_set = mtk_pinconf_bias_disable_set, + .bias_disable_get = mtk_pinconf_bias_disable_get, + .bias_set = mtk_pinconf_bias_set, + .bias_get = mtk_pinconf_bias_get, + .pull_type = mt7988_pull_type, + .bias_set_combo = mtk_pinconf_bias_set_combo, + .bias_get_combo = mtk_pinconf_bias_get_combo, + .drive_set = mtk_pinconf_drive_set_rev1, + .drive_get = mtk_pinconf_drive_get_rev1, + .adv_pull_get = mtk_pinconf_adv_pull_get, + .adv_pull_set = mtk_pinconf_adv_pull_set, +}; + +static const struct of_device_id mt7988_pinctrl_of_match[] = { + { .compatible = "mediatek,mt7988-pinctrl" }, + {} +}; + +static int mt7988_pinctrl_probe(struct platform_device *pdev) +{ + return mtk_moore_pinctrl_probe(pdev, &mt7988_data); +} + +static struct platform_driver mt7988_pinctrl_driver = { + .driver = { + .name = "mt7988-pinctrl", + .of_match_table = mt7988_pinctrl_of_match, + }, + .probe = mt7988_pinctrl_probe, +}; + +static int __init mt7988_pinctrl_init(void) +{ + return platform_driver_register(&mt7988_pinctrl_driver); +} +arch_initcall(mt7988_pinctrl_init); diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c index 54301fbba524..00e95682b9f8 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c @@ -573,7 +573,7 @@ EXPORT_SYMBOL_GPL(mtk_pinconf_bias_get_rev1); */ static int mtk_pinconf_bias_set_pu_pd(struct mtk_pinctrl *hw, const struct mtk_pin_desc *desc, - u32 pullup, u32 arg) + u32 pullup, u32 arg, bool pd_only) { int err, pu, pd; @@ -587,18 +587,16 @@ static int mtk_pinconf_bias_set_pu_pd(struct mtk_pinctrl *hw, pu = 0; pd = 1; } else { - err = -EINVAL; - goto out; + return -EINVAL; } - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_PU, pu); - if (err) - goto out; + if (!pd_only) { + err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_PU, pu); + if (err) + return err; + } - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_PD, pd); - -out: - return err; + return mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_PD, pd); } static int mtk_pinconf_bias_set_pullsel_pullen(struct mtk_pinctrl *hw, @@ -737,7 +735,7 @@ static int mtk_pinconf_bias_set_pu_pd_rsel(struct mtk_pinctrl *hw, return err; } - return mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, enable); + return mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, enable, false); } int mtk_pinconf_bias_set_combo(struct mtk_pinctrl *hw, @@ -758,8 +756,14 @@ int mtk_pinconf_bias_set_combo(struct mtk_pinctrl *hw, return 0; } + if (try_all_type & MTK_PULL_PD_TYPE) { + err = mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, arg, true); + if (!err) + return err; + } + if (try_all_type & MTK_PULL_PU_PD_TYPE) { - err = mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, arg); + err = mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, arg, false); if (!err) return 0; } @@ -878,6 +882,29 @@ out: return err; } +static int mtk_pinconf_bias_get_pd(struct mtk_pinctrl *hw, + const struct mtk_pin_desc *desc, + u32 *pullup, u32 *enable) +{ + int err, pd; + + err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_PD, &pd); + if (err) + goto out; + + if (pd == 0) { + *pullup = 0; + *enable = MTK_DISABLE; + } else if (pd == 1) { + *pullup = 0; + *enable = MTK_ENABLE; + } else + err = -EINVAL; + +out: + return err; +} + static int mtk_pinconf_bias_get_pullsel_pullen(struct mtk_pinctrl *hw, const struct mtk_pin_desc *desc, u32 *pullup, u32 *enable) @@ -947,6 +974,12 @@ int mtk_pinconf_bias_get_combo(struct mtk_pinctrl *hw, return 0; } + if (try_all_type & MTK_PULL_PD_TYPE) { + err = mtk_pinconf_bias_get_pd(hw, desc, pullup, enable); + if (!err) + return err; + } + if (try_all_type & MTK_PULL_PU_PD_TYPE) { err = mtk_pinconf_bias_get_pu_pd(hw, desc, pullup, enable); if (!err) diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.h b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.h index 23688ca6d04e..9c271dc2b521 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.h +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.h @@ -24,6 +24,7 @@ * turned on/off itself. But it can't be selected pull up/down */ #define MTK_PULL_RSEL_TYPE BIT(3) +#define MTK_PULL_PD_TYPE BIT(4) /* MTK_PULL_PU_PD_RSEL_TYPE is a type which is controlled by * MTK_PULL_PU_PD_TYPE and MTK_PULL_RSEL_TYPE. */ diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c index 4ce2e35a6373..8cd4ba5cf0bd 100644 --- a/drivers/pinctrl/nomadik/pinctrl-abx500.c +++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -496,7 +497,7 @@ static void abx500_gpio_dbg_show_one(struct seq_file *s, seq_printf(s, " %-9s", pull_up_down[pd]); } else - seq_printf(s, " %-9s", chip->get(chip, offset) ? "hi" : "lo"); + seq_printf(s, " %-9s", str_hi_lo(chip->get(chip, offset))); mode = abx500_get_mode(pctldev, chip, offset); @@ -865,7 +866,7 @@ static int abx500_pin_config_set(struct pinctrl_dev *pctldev, pin, configs[i], (param == PIN_CONFIG_OUTPUT) ? "output " : "input", (param == PIN_CONFIG_OUTPUT) ? - (argument ? "high" : "low") : + str_high_low(argument) : (argument ? "pull up" : "pull down")); /* on ABx500, there is no GPIO0, so adjust the offset */ diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c index f4f10c60c1d2..8940e04fcf4c 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c @@ -28,6 +28,7 @@ #include #include #include +#include #include /* Since we request GPIOs from ourself */ @@ -438,9 +439,9 @@ static void nmk_prcm_altcx_set_mode(struct nmk_pinctrl *npct, * - Any spurious wake up event during switch sequence to be ignored and * cleared */ -static void nmk_gpio_glitch_slpm_init(unsigned int *slpm) +static int nmk_gpio_glitch_slpm_init(unsigned int *slpm) { - int i; + int i, j, ret; for (i = 0; i < NMK_MAX_BANKS; i++) { struct nmk_gpio_chip *chip = nmk_gpio_chips[i]; @@ -449,11 +450,21 @@ static void nmk_gpio_glitch_slpm_init(unsigned int *slpm) if (!chip) break; - clk_enable(chip->clk); + ret = clk_enable(chip->clk); + if (ret) { + for (j = 0; j < i; j++) { + chip = nmk_gpio_chips[j]; + clk_disable(chip->clk); + } + + return ret; + } slpm[i] = readl(chip->addr + NMK_GPIO_SLPC); writel(temp, chip->addr + NMK_GPIO_SLPC); } + + return 0; } static void nmk_gpio_glitch_slpm_restore(unsigned int *slpm) @@ -923,7 +934,9 @@ static int nmk_pmx_set(struct pinctrl_dev *pctldev, unsigned int function, slpm[nmk_chip->bank] &= ~BIT(bit); } - nmk_gpio_glitch_slpm_init(slpm); + ret = nmk_gpio_glitch_slpm_init(slpm); + if (ret) + goto out_pre_slpm_init; } for (i = 0; i < g->grp.npins; i++) { @@ -940,7 +953,10 @@ static int nmk_pmx_set(struct pinctrl_dev *pctldev, unsigned int function, dev_dbg(npct->dev, "setting pin %d to altsetting %d\n", g->grp.pins[i], g->altsetting); - clk_enable(nmk_chip->clk); + ret = clk_enable(nmk_chip->clk); + if (ret) + goto out_glitch; + /* * If the pin is switching to altfunc, and there was an * interrupt installed on it which has been lazy disabled, @@ -988,6 +1004,7 @@ static int nmk_gpio_request_enable(struct pinctrl_dev *pctldev, struct nmk_gpio_chip *nmk_chip; struct gpio_chip *chip; unsigned int bit; + int ret; if (!range) { dev_err(npct->dev, "invalid range\n"); @@ -1004,7 +1021,9 @@ static int nmk_gpio_request_enable(struct pinctrl_dev *pctldev, find_nmk_gpio_from_pin(pin, &bit); - clk_enable(nmk_chip->clk); + ret = clk_enable(nmk_chip->clk); + if (ret) + return ret; /* There is no glitch when converting any pin to GPIO */ __nmk_gpio_set_mode(nmk_chip, bit, NMK_GPIO_ALT_GPIO); clk_disable(nmk_chip->clk); @@ -1058,6 +1077,7 @@ static int nmk_pin_config_set(struct pinctrl_dev *pctldev, unsigned int pin, unsigned long cfg; int pull, slpm, output, val, i; bool lowemi, gpiomode, sleep; + int ret; nmk_chip = find_nmk_gpio_from_pin(pin, &bit); if (!nmk_chip) { @@ -1106,17 +1126,19 @@ static int nmk_pin_config_set(struct pinctrl_dev *pctldev, unsigned int pin, slpm_pull ? pullnames[pull] : "same", slpm_output ? (output ? "output" : "input") : "same", - slpm_val ? (val ? "high" : "low") : "same"); + slpm_val ? str_high_low(val) : "same"); } dev_dbg(nmk_chip->chip.parent, "pin %d [%#lx]: pull %s, slpm %s (%s%s), lowemi %s\n", pin, cfg, pullnames[pull], slpmnames[slpm], output ? "output " : "input", - output ? (val ? "high" : "low") : "", - lowemi ? "on" : "off"); + output ? str_high_low(val) : "", + str_on_off(lowemi)); - clk_enable(nmk_chip->clk); + ret = clk_enable(nmk_chip->clk); + if (ret) + return ret; if (gpiomode) /* No glitch when going to GPIO mode */ __nmk_gpio_set_mode(nmk_chip, bit, NMK_GPIO_ALT_GPIO); diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index fff6d4209ad5..1d7fdcdec4c8 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include "core.h" @@ -458,7 +459,7 @@ static int amd_gpio_irq_set_wake(struct irq_data *d, unsigned int on) if (err) dev_err(&gpio_dev->pdev->dev, "failed to %s wake-up interrupt\n", - on ? "enable" : "disable"); + str_enable_disable(on)); return 0; } @@ -908,12 +909,13 @@ static bool amd_gpio_should_save(struct amd_gpio *gpio_dev, unsigned int pin) return false; } -static int amd_gpio_suspend(struct device *dev) +static int amd_gpio_suspend_hibernate_common(struct device *dev, bool is_suspend) { struct amd_gpio *gpio_dev = dev_get_drvdata(dev); struct pinctrl_desc *desc = gpio_dev->pctrl->desc; unsigned long flags; int i; + u32 wake_mask = is_suspend ? WAKE_SOURCE_SUSPEND : WAKE_SOURCE_HIBERNATE; for (i = 0; i < desc->npins; i++) { int pin = desc->pins[i].number; @@ -925,11 +927,11 @@ static int amd_gpio_suspend(struct device *dev) gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin * 4) & ~PIN_IRQ_PENDING; /* mask any interrupts not intended to be a wake source */ - if (!(gpio_dev->saved_regs[i] & WAKE_SOURCE)) { + if (!(gpio_dev->saved_regs[i] & wake_mask)) { writel(gpio_dev->saved_regs[i] & ~BIT(INTERRUPT_MASK_OFF), gpio_dev->base + pin * 4); - pm_pr_dbg("Disabling GPIO #%d interrupt for suspend.\n", - pin); + pm_pr_dbg("Disabling GPIO #%d interrupt for %s.\n", + pin, is_suspend ? "suspend" : "hibernate"); } raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); @@ -938,6 +940,16 @@ static int amd_gpio_suspend(struct device *dev) return 0; } +static int amd_gpio_suspend(struct device *dev) +{ + return amd_gpio_suspend_hibernate_common(dev, true); +} + +static int amd_gpio_hibernate(struct device *dev) +{ + return amd_gpio_suspend_hibernate_common(dev, false); +} + static int amd_gpio_resume(struct device *dev) { struct amd_gpio *gpio_dev = dev_get_drvdata(dev); @@ -961,8 +973,12 @@ static int amd_gpio_resume(struct device *dev) } static const struct dev_pm_ops amd_gpio_pm_ops = { - SET_LATE_SYSTEM_SLEEP_PM_OPS(amd_gpio_suspend, - amd_gpio_resume) + .suspend_late = amd_gpio_suspend, + .resume_early = amd_gpio_resume, + .freeze_late = amd_gpio_hibernate, + .thaw_early = amd_gpio_resume, + .poweroff_late = amd_gpio_hibernate, + .restore_early = amd_gpio_resume, }; #endif diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h index 667be49c3f48..3a1e5bffaf6e 100644 --- a/drivers/pinctrl/pinctrl-amd.h +++ b/drivers/pinctrl/pinctrl-amd.h @@ -80,10 +80,9 @@ #define FUNCTION_MASK GENMASK(1, 0) #define FUNCTION_INVALID GENMASK(7, 0) -#define WAKE_SOURCE (BIT(WAKE_CNTRL_OFF_S0I3) | \ - BIT(WAKE_CNTRL_OFF_S3) | \ - BIT(WAKE_CNTRL_OFF_S4) | \ - BIT(WAKECNTRL_Z_OFF)) +#define WAKE_SOURCE_SUSPEND (BIT(WAKE_CNTRL_OFF_S0I3) | \ + BIT(WAKE_CNTRL_OFF_S3)) +#define WAKE_SOURCE_HIBERNATE BIT(WAKE_CNTRL_OFF_S4) struct amd_function { const char *name; diff --git a/drivers/pinctrl/pinctrl-gemini.c b/drivers/pinctrl/pinctrl-gemini.c index 631612539af7..e9f61927858d 100644 --- a/drivers/pinctrl/pinctrl-gemini.c +++ b/drivers/pinctrl/pinctrl-gemini.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -2237,7 +2238,7 @@ static int gemini_pmx_set_mux(struct pinctrl_dev *pctldev, "pin group %s could not be %s: " "probably a hardware limitation\n", gemini_padgroups[i], - enabled ? "enabled" : "disabled"); + str_enabled_disabled(enabled)); dev_err(pmx->dev, "GLOBAL MISC CTRL before: %08x, after %08x, expected %08x\n", before, after, expected); @@ -2245,7 +2246,7 @@ static int gemini_pmx_set_mux(struct pinctrl_dev *pctldev, dev_dbg(pmx->dev, "padgroup %s %s\n", gemini_padgroups[i], - enabled ? "enabled" : "disabled"); + str_enabled_disabled(enabled)); } } @@ -2259,7 +2260,7 @@ static int gemini_pmx_set_mux(struct pinctrl_dev *pctldev, "pin group %s could not be %s: " "probably a hardware limitation\n", gemini_padgroups[i], - enabled ? "enabled" : "disabled"); + str_enabled_disabled(enabled)); dev_err(pmx->dev, "GLOBAL MISC CTRL before: %08x, after %08x, expected %08x\n", before, after, expected); @@ -2267,7 +2268,7 @@ static int gemini_pmx_set_mux(struct pinctrl_dev *pctldev, dev_dbg(pmx->dev, "padgroup %s %s\n", gemini_padgroups[i], - enabled ? "enabled" : "disabled"); + str_enabled_disabled(enabled)); } } @@ -2588,7 +2589,7 @@ static int gemini_pmx_probe(struct platform_device *pdev) tmp = val; for_each_set_bit(i, &tmp, PADS_MAXBIT) { dev_dbg(dev, "pad group %s %s\n", gemini_padgroups[i], - (val & BIT(i)) ? "enabled" : "disabled"); + str_enabled_disabled(val & BIT(i))); } /* Check if flash pin is set */ diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index 31703737731b..bc7ee54e062b 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -3699,7 +3699,7 @@ static void ingenic_gpio_irq_print_chip(struct irq_data *data, struct seq_file * { struct gpio_chip *gpio_chip = irq_data_get_irq_chip_data(data); - seq_printf(p, "%s", gpio_chip->label); + seq_puts(p, gpio_chip->label); } static const struct irq_chip ingenic_gpio_irqchip = { diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index d66c3a3e8429..b96e6368a956 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -86,6 +86,7 @@ const struct regmap_config mcp23x08_regmap = { .num_reg_defaults = ARRAY_SIZE(mcp23x08_defaults), .cache_type = REGCACHE_FLAT, .max_register = MCP_OLAT, + .disable_locking = true, /* mcp->lock protects the regmap */ }; EXPORT_SYMBOL_GPL(mcp23x08_regmap); @@ -132,6 +133,7 @@ const struct regmap_config mcp23x17_regmap = { .num_reg_defaults = ARRAY_SIZE(mcp23x17_defaults), .cache_type = REGCACHE_FLAT, .val_format_endian = REGMAP_ENDIAN_LITTLE, + .disable_locking = true, /* mcp->lock protects the regmap */ }; EXPORT_SYMBOL_GPL(mcp23x17_regmap); @@ -228,7 +230,9 @@ static int mcp_pinconf_get(struct pinctrl_dev *pctldev, unsigned int pin, switch (param) { case PIN_CONFIG_BIAS_PULL_UP: + mutex_lock(&mcp->lock); ret = mcp_read(mcp, MCP_GPPU, &data); + mutex_unlock(&mcp->lock); if (ret < 0) return ret; status = (data & BIT(pin)) ? 1 : 0; @@ -257,7 +261,9 @@ static int mcp_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, switch (param) { case PIN_CONFIG_BIAS_PULL_UP: + mutex_lock(&mcp->lock); ret = mcp_set_bit(mcp, MCP_GPPU, pin, arg); + mutex_unlock(&mcp->lock); break; default: dev_dbg(mcp->dev, "Invalid config param %04x\n", param); diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c index 61532a7a612a..329d54b11529 100644 --- a/drivers/pinctrl/pinctrl-ocelot.c +++ b/drivers/pinctrl/pinctrl-ocelot.c @@ -1777,7 +1777,7 @@ static const struct pinctrl_ops ocelot_pctl_ops = { .dt_free_map = pinconf_generic_dt_free_map, }; -static struct ocelot_match_data luton_desc = { +static const struct ocelot_match_data luton_desc = { .desc = { .name = "luton-pinctrl", .pins = luton_pins, @@ -1788,7 +1788,7 @@ static struct ocelot_match_data luton_desc = { }, }; -static struct ocelot_match_data serval_desc = { +static const struct ocelot_match_data serval_desc = { .desc = { .name = "serval-pinctrl", .pins = serval_pins, @@ -1799,7 +1799,7 @@ static struct ocelot_match_data serval_desc = { }, }; -static struct ocelot_match_data ocelot_desc = { +static const struct ocelot_match_data ocelot_desc = { .desc = { .name = "ocelot-pinctrl", .pins = ocelot_pins, @@ -1810,7 +1810,7 @@ static struct ocelot_match_data ocelot_desc = { }, }; -static struct ocelot_match_data jaguar2_desc = { +static const struct ocelot_match_data jaguar2_desc = { .desc = { .name = "jaguar2-pinctrl", .pins = jaguar2_pins, @@ -1821,7 +1821,7 @@ static struct ocelot_match_data jaguar2_desc = { }, }; -static struct ocelot_match_data servalt_desc = { +static const struct ocelot_match_data servalt_desc = { .desc = { .name = "servalt-pinctrl", .pins = servalt_pins, @@ -1832,7 +1832,7 @@ static struct ocelot_match_data servalt_desc = { }, }; -static struct ocelot_match_data sparx5_desc = { +static const struct ocelot_match_data sparx5_desc = { .desc = { .name = "sparx5-pinctrl", .pins = sparx5_pins, @@ -1850,7 +1850,7 @@ static struct ocelot_match_data sparx5_desc = { }, }; -static struct ocelot_match_data lan966x_desc = { +static const struct ocelot_match_data lan966x_desc = { .desc = { .name = "lan966x-pinctrl", .pins = lan966x_pins, @@ -1867,7 +1867,7 @@ static struct ocelot_match_data lan966x_desc = { }, }; -static struct ocelot_match_data lan969x_desc = { +static const struct ocelot_match_data lan969x_desc = { .desc = { .name = "lan969x-pinctrl", .pins = lan969x_pins, @@ -2116,7 +2116,7 @@ static void ocelot_irq_ack(struct irq_data *data) static int ocelot_irq_set_type(struct irq_data *data, unsigned int type); -static struct irq_chip ocelot_level_irqchip = { +static const struct irq_chip ocelot_level_irqchip = { .name = "gpio", .irq_mask = ocelot_irq_mask, .irq_ack = ocelot_irq_ack, @@ -2126,7 +2126,7 @@ static struct irq_chip ocelot_level_irqchip = { GPIOCHIP_IRQ_RESOURCE_HELPERS }; -static struct irq_chip ocelot_irqchip = { +static const struct irq_chip ocelot_irqchip = { .name = "gpio", .irq_mask = ocelot_irq_mask, .irq_ack = ocelot_irq_ack, diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 36d4eaf0ebd1..15145882950f 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Pinctrl driver for Rockchip SoCs - * + * Copyright (c) 2020-2024 Rockchip Electronics Co., Ltd. * Copyright (c) 2013 MundoReader S.L. * Author: Heiko Stuebner * @@ -2003,6 +2003,151 @@ static int rk3399_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank, return 0; } +#define RK3562_DRV_BITS_PER_PIN 8 +#define RK3562_DRV_PINS_PER_REG 2 +#define RK3562_DRV_GPIO0_OFFSET 0x20070 +#define RK3562_DRV_GPIO1_OFFSET 0x200 +#define RK3562_DRV_GPIO2_OFFSET 0x240 +#define RK3562_DRV_GPIO3_OFFSET 0x10280 +#define RK3562_DRV_GPIO4_OFFSET 0x102C0 + +static int rk3562_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank, + int pin_num, struct regmap **regmap, + int *reg, u8 *bit) +{ + struct rockchip_pinctrl *info = bank->drvdata; + + *regmap = info->regmap_base; + switch (bank->bank_num) { + case 0: + *reg = RK3562_DRV_GPIO0_OFFSET; + break; + + case 1: + *reg = RK3562_DRV_GPIO1_OFFSET; + break; + + case 2: + *reg = RK3562_DRV_GPIO2_OFFSET; + break; + + case 3: + *reg = RK3562_DRV_GPIO3_OFFSET; + break; + + case 4: + *reg = RK3562_DRV_GPIO4_OFFSET; + break; + + default: + dev_err(info->dev, "unsupported bank_num %d\n", bank->bank_num); + break; + } + + *reg += ((pin_num / RK3562_DRV_PINS_PER_REG) * 4); + *bit = pin_num % RK3562_DRV_PINS_PER_REG; + *bit *= RK3562_DRV_BITS_PER_PIN; + + return 0; +} + +#define RK3562_PULL_BITS_PER_PIN 2 +#define RK3562_PULL_PINS_PER_REG 8 +#define RK3562_PULL_GPIO0_OFFSET 0x20020 +#define RK3562_PULL_GPIO1_OFFSET 0x80 +#define RK3562_PULL_GPIO2_OFFSET 0x90 +#define RK3562_PULL_GPIO3_OFFSET 0x100A0 +#define RK3562_PULL_GPIO4_OFFSET 0x100B0 + +static int rk3562_calc_pull_reg_and_bit(struct rockchip_pin_bank *bank, + int pin_num, struct regmap **regmap, + int *reg, u8 *bit) +{ + struct rockchip_pinctrl *info = bank->drvdata; + + *regmap = info->regmap_base; + switch (bank->bank_num) { + case 0: + *reg = RK3562_PULL_GPIO0_OFFSET; + break; + + case 1: + *reg = RK3562_PULL_GPIO1_OFFSET; + break; + + case 2: + *reg = RK3562_PULL_GPIO2_OFFSET; + break; + + case 3: + *reg = RK3562_PULL_GPIO3_OFFSET; + break; + + case 4: + *reg = RK3562_PULL_GPIO4_OFFSET; + break; + + default: + dev_err(info->dev, "unsupported bank_num %d\n", bank->bank_num); + break; + } + + *reg += ((pin_num / RK3562_PULL_PINS_PER_REG) * 4); + *bit = pin_num % RK3562_PULL_PINS_PER_REG; + *bit *= RK3562_PULL_BITS_PER_PIN; + + return 0; +} + +#define RK3562_SMT_BITS_PER_PIN 2 +#define RK3562_SMT_PINS_PER_REG 8 +#define RK3562_SMT_GPIO0_OFFSET 0x20030 +#define RK3562_SMT_GPIO1_OFFSET 0xC0 +#define RK3562_SMT_GPIO2_OFFSET 0xD0 +#define RK3562_SMT_GPIO3_OFFSET 0x100E0 +#define RK3562_SMT_GPIO4_OFFSET 0x100F0 + +static int rk3562_calc_schmitt_reg_and_bit(struct rockchip_pin_bank *bank, + int pin_num, + struct regmap **regmap, + int *reg, u8 *bit) +{ + struct rockchip_pinctrl *info = bank->drvdata; + + *regmap = info->regmap_base; + switch (bank->bank_num) { + case 0: + *reg = RK3562_SMT_GPIO0_OFFSET; + break; + + case 1: + *reg = RK3562_SMT_GPIO1_OFFSET; + break; + + case 2: + *reg = RK3562_SMT_GPIO2_OFFSET; + break; + + case 3: + *reg = RK3562_SMT_GPIO3_OFFSET; + break; + + case 4: + *reg = RK3562_SMT_GPIO4_OFFSET; + break; + + default: + dev_err(info->dev, "unsupported bank_num %d\n", bank->bank_num); + break; + } + + *reg += ((pin_num / RK3562_SMT_PINS_PER_REG) * 4); + *bit = pin_num % RK3562_SMT_PINS_PER_REG; + *bit *= RK3562_SMT_BITS_PER_PIN; + + return 0; +} + #define RK3568_PULL_PMU_OFFSET 0x20 #define RK3568_PULL_GRF_OFFSET 0x80 #define RK3568_PULL_BITS_PER_PIN 2 @@ -2495,7 +2640,8 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank, rmask_bits = RK3588_DRV_BITS_PER_PIN; ret = strength; goto config; - } else if (ctrl->type == RK3568) { + } else if (ctrl->type == RK3562 || + ctrl->type == RK3568) { rmask_bits = RK3568_DRV_BITS_PER_PIN; ret = (1 << (strength + 1)) - 1; goto config; @@ -2639,6 +2785,7 @@ static int rockchip_get_pull(struct rockchip_pin_bank *bank, int pin_num) case RK3328: case RK3368: case RK3399: + case RK3562: case RK3568: case RK3576: case RK3588: @@ -2699,6 +2846,7 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank, case RK3328: case RK3368: case RK3399: + case RK3562: case RK3568: case RK3576: case RK3588: @@ -2810,6 +2958,7 @@ static int rockchip_get_schmitt(struct rockchip_pin_bank *bank, int pin_num) data >>= bit; switch (ctrl->type) { + case RK3562: case RK3568: return data & ((1 << RK3568_SCHMITT_BITS_PER_PIN) - 1); default: @@ -2839,6 +2988,7 @@ static int rockchip_set_schmitt(struct rockchip_pin_bank *bank, /* enable the write to the equivalent lower bits */ switch (ctrl->type) { + case RK3562: case RK3568: data = ((1 << RK3568_SCHMITT_BITS_PER_PIN) - 1) << (bit + 16); rmask = data | (data >> 16); @@ -2965,6 +3115,7 @@ static bool rockchip_pinconf_pull_valid(struct rockchip_pin_ctrl *ctrl, case RK3328: case RK3368: case RK3399: + case RK3562: case RK3568: case RK3576: case RK3588: @@ -4086,6 +4237,49 @@ static struct rockchip_pin_ctrl rk3399_pin_ctrl = { .drv_calc_reg = rk3399_calc_drv_reg_and_bit, }; +static struct rockchip_pin_bank rk3562_pin_banks[] = { + PIN_BANK_IOMUX_FLAGS_OFFSET(0, 32, "gpio0", + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + 0x20000, 0x20008, 0x20010, 0x20018), + PIN_BANK_IOMUX_FLAGS_OFFSET(1, 32, "gpio1", + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + 0, 0x08, 0x10, 0x18), + PIN_BANK_IOMUX_FLAGS_OFFSET(2, 32, "gpio2", + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + 0x20, 0, 0, 0), + PIN_BANK_IOMUX_FLAGS_OFFSET(3, 32, "gpio3", + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + 0x10040, 0x10048, 0x10050, 0x10058), + PIN_BANK_IOMUX_FLAGS_OFFSET(4, 16, "gpio4", + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + 0, + 0, + 0x10060, 0x10068, 0, 0), +}; + +static struct rockchip_pin_ctrl rk3562_pin_ctrl __maybe_unused = { + .pin_banks = rk3562_pin_banks, + .nr_banks = ARRAY_SIZE(rk3562_pin_banks), + .label = "RK3562-GPIO", + .type = RK3562, + .pull_calc_reg = rk3562_calc_pull_reg_and_bit, + .drv_calc_reg = rk3562_calc_drv_reg_and_bit, + .schmitt_calc_reg = rk3562_calc_schmitt_reg_and_bit, +}; + static struct rockchip_pin_bank rk3568_pin_banks[] = { PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", IOMUX_SOURCE_PMU | IOMUX_WIDTH_4BIT, IOMUX_SOURCE_PMU | IOMUX_WIDTH_4BIT, @@ -4210,6 +4404,8 @@ static const struct of_device_id rockchip_pinctrl_dt_match[] = { .data = &rk3368_pin_ctrl }, { .compatible = "rockchip,rk3399-pinctrl", .data = &rk3399_pin_ctrl }, + { .compatible = "rockchip,rk3562-pinctrl", + .data = &rk3562_pin_ctrl }, { .compatible = "rockchip,rk3568-pinctrl", .data = &rk3568_pin_ctrl }, { .compatible = "rockchip,rk3576-pinctrl", diff --git a/drivers/pinctrl/pinctrl-rockchip.h b/drivers/pinctrl/pinctrl-rockchip.h index 6ebbb0a88ce7..87a20cec8e21 100644 --- a/drivers/pinctrl/pinctrl-rockchip.h +++ b/drivers/pinctrl/pinctrl-rockchip.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2020-2021 Rockchip Electronics Co. Ltd. + * Copyright (c) 2020-2024 Rockchip Electronics Co., Ltd. * * Copyright (c) 2013 MundoReader S.L. * Author: Heiko Stuebner @@ -196,6 +196,7 @@ enum rockchip_pinctrl_type { RK3328, RK3368, RK3399, + RK3562, RK3568, RK3576, RK3588, diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c index 521f6fef0b9f..aae01120dc52 100644 --- a/drivers/pinctrl/pinctrl-stmfx.c +++ b/drivers/pinctrl/pinctrl-stmfx.c @@ -380,7 +380,7 @@ static void stmfx_pinconf_dbg_show(struct pinctrl_dev *pctldev, seq_printf(s, "input %s ", str_high_low(val)); if (type) seq_printf(s, "with internal pull-%s ", - pupd ? "up" : "down"); + str_up_down(pupd)); else seq_printf(s, "%s ", pupd ? "floating" : "analog"); } diff --git a/drivers/pinctrl/qcom/Kconfig.msm b/drivers/pinctrl/qcom/Kconfig.msm index 206226318e45..35f47660a56b 100644 --- a/drivers/pinctrl/qcom/Kconfig.msm +++ b/drivers/pinctrl/qcom/Kconfig.msm @@ -137,6 +137,12 @@ config PINCTRL_MSM8916 This is the pinctrl, pinmux, pinconf and gpiolib driver for the Qualcomm TLMM block found on the Qualcomm 8916 platform. +config PINCTRL_MSM8917 + tristate "Qualcomm 8917 pin controller driver" + help + This is the pinctrl, pinmux, pinconf and gpiolib driver for the + Qualcomm TLMM block found on the Qualcomm MSM8917 platform. + config PINCTRL_MSM8953 tristate "Qualcomm 8953 pin controller driver" depends on ARM64 || COMPILE_TEST diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile index 9a23d41d801c..5c4100925cf9 100644 --- a/drivers/pinctrl/qcom/Makefile +++ b/drivers/pinctrl/qcom/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_PINCTRL_MSM8960) += pinctrl-msm8960.o obj-$(CONFIG_PINCTRL_MSM8X74) += pinctrl-msm8x74.o obj-$(CONFIG_PINCTRL_MSM8909) += pinctrl-msm8909.o obj-$(CONFIG_PINCTRL_MSM8916) += pinctrl-msm8916.o +obj-$(CONFIG_PINCTRL_MSM8917) += pinctrl-msm8917.o obj-$(CONFIG_PINCTRL_MSM8953) += pinctrl-msm8953.o obj-$(CONFIG_PINCTRL_MSM8976) += pinctrl-msm8976.o obj-$(CONFIG_PINCTRL_MSM8994) += pinctrl-msm8994.o diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5424.c b/drivers/pinctrl/qcom/pinctrl-ipq5424.c index 796299cd2e4e..0d610b076da3 100644 --- a/drivers/pinctrl/qcom/pinctrl-ipq5424.c +++ b/drivers/pinctrl/qcom/pinctrl-ipq5424.c @@ -233,7 +233,10 @@ enum ipq5424_functions { msm_mux_sdc_clk, msm_mux_sdc_cmd, msm_mux_sdc_data, - msm_mux_spi0, + msm_mux_spi0_clk, + msm_mux_spi0_cs, + msm_mux_spi0_miso, + msm_mux_spi0_mosi, msm_mux_spi1, msm_mux_spi10, msm_mux_spi11, @@ -297,8 +300,8 @@ static const char * const qspi_clk_groups[] = { "gpio5", }; -static const char * const spi0_groups[] = { - "gpio6", "gpio7", "gpio8", "gpio9", +static const char * const spi0_clk_groups[] = { + "gpio6", }; static const char * const pwm1_groups[] = { @@ -315,14 +318,26 @@ static const char * const qdss_tracedata_a_groups[] = { "gpio38", "gpio39", }; +static const char * const spi0_cs_groups[] = { + "gpio7", +}; + static const char * const cri_trng1_groups[] = { "gpio7", }; +static const char * const spi0_miso_groups[] = { + "gpio8", +}; + static const char * const cri_trng2_groups[] = { "gpio8", }; +static const char * const spi0_mosi_groups[] = { + "gpio9", +}; + static const char * const cri_trng3_groups[] = { "gpio9", }; @@ -680,7 +695,10 @@ static const struct pinfunction ipq5424_functions[] = { MSM_PIN_FUNCTION(sdc_clk), MSM_PIN_FUNCTION(sdc_cmd), MSM_PIN_FUNCTION(sdc_data), - MSM_PIN_FUNCTION(spi0), + MSM_PIN_FUNCTION(spi0_clk), + MSM_PIN_FUNCTION(spi0_cs), + MSM_PIN_FUNCTION(spi0_miso), + MSM_PIN_FUNCTION(spi0_mosi), MSM_PIN_FUNCTION(spi1), MSM_PIN_FUNCTION(spi10), MSM_PIN_FUNCTION(spi11), @@ -700,10 +718,10 @@ static const struct msm_pingroup ipq5424_groups[] = { PINGROUP(3, sdc_data, qspi_data, pwm2, _, _, _, _, _, _), PINGROUP(4, sdc_cmd, qspi_cs, _, _, _, _, _, _, _), PINGROUP(5, sdc_clk, qspi_clk, _, _, _, _, _, _, _), - PINGROUP(6, spi0, pwm1, _, cri_trng0, qdss_tracedata_a, _, _, _, _), - PINGROUP(7, spi0, pwm1, _, cri_trng1, qdss_tracedata_a, _, _, _, _), - PINGROUP(8, spi0, pwm1, wci_txd, wci_rxd, _, cri_trng2, qdss_tracedata_a, _, _), - PINGROUP(9, spi0, pwm1, _, cri_trng3, qdss_tracedata_a, _, _, _, _), + PINGROUP(6, spi0_clk, pwm1, _, cri_trng0, qdss_tracedata_a, _, _, _, _), + PINGROUP(7, spi0_cs, pwm1, _, cri_trng1, qdss_tracedata_a, _, _, _, _), + PINGROUP(8, spi0_miso, pwm1, wci_txd, wci_rxd, _, cri_trng2, qdss_tracedata_a, _, _), + PINGROUP(9, spi0_mosi, pwm1, _, cri_trng3, qdss_tracedata_a, _, _, _, _), PINGROUP(10, uart0, pwm0, spi11, _, wci_txd, wci_rxd, _, qdss_tracedata_a, _), PINGROUP(11, uart0, pwm0, spi1, _, wci_txd, wci_rxd, _, qdss_tracedata_a, _), PINGROUP(12, uart0, pwm0, spi11, _, prng_rosc0, qdss_tracedata_a, _, _, _), diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index ec913c2e200f..47daa47153c9 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -714,7 +715,7 @@ static void msm_gpio_dbg_show_one(struct seq_file *s, } seq_printf(s, " %-8s: %-3s", g->grp.name, is_out ? "out" : "in"); - seq_printf(s, " %-4s func%d", val ? "high" : "low", func); + seq_printf(s, " %-4s func%d", str_high_low(val), func); seq_printf(s, " %dmA", msm_regval_to_drive(drive)); if (pctrl->soc->pull_no_keeper) seq_printf(s, " %s", pulls_no_keeper[pull]); diff --git a/drivers/pinctrl/qcom/pinctrl-msm8917.c b/drivers/pinctrl/qcom/pinctrl-msm8917.c new file mode 100644 index 000000000000..cff137bb3b23 --- /dev/null +++ b/drivers/pinctrl/qcom/pinctrl-msm8917.c @@ -0,0 +1,1620 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024, The Linux Foundation. All rights reserved. + */ + +#include +#include +#include + +#include "pinctrl-msm.h" + +static const struct pinctrl_pin_desc msm8917_pins[] = { + PINCTRL_PIN(0, "GPIO_0"), + PINCTRL_PIN(1, "GPIO_1"), + PINCTRL_PIN(2, "GPIO_2"), + PINCTRL_PIN(3, "GPIO_3"), + PINCTRL_PIN(4, "GPIO_4"), + PINCTRL_PIN(5, "GPIO_5"), + PINCTRL_PIN(6, "GPIO_6"), + PINCTRL_PIN(7, "GPIO_7"), + PINCTRL_PIN(8, "GPIO_8"), + PINCTRL_PIN(9, "GPIO_9"), + PINCTRL_PIN(10, "GPIO_10"), + PINCTRL_PIN(11, "GPIO_11"), + PINCTRL_PIN(12, "GPIO_12"), + PINCTRL_PIN(13, "GPIO_13"), + PINCTRL_PIN(14, "GPIO_14"), + PINCTRL_PIN(15, "GPIO_15"), + PINCTRL_PIN(16, "GPIO_16"), + PINCTRL_PIN(17, "GPIO_17"), + PINCTRL_PIN(18, "GPIO_18"), + PINCTRL_PIN(19, "GPIO_19"), + PINCTRL_PIN(20, "GPIO_20"), + PINCTRL_PIN(21, "GPIO_21"), + PINCTRL_PIN(22, "GPIO_22"), + PINCTRL_PIN(23, "GPIO_23"), + PINCTRL_PIN(24, "GPIO_24"), + PINCTRL_PIN(25, "GPIO_25"), + PINCTRL_PIN(26, "GPIO_26"), + PINCTRL_PIN(27, "GPIO_27"), + PINCTRL_PIN(28, "GPIO_28"), + PINCTRL_PIN(29, "GPIO_29"), + PINCTRL_PIN(30, "GPIO_30"), + PINCTRL_PIN(31, "GPIO_31"), + PINCTRL_PIN(32, "GPIO_32"), + PINCTRL_PIN(33, "GPIO_33"), + PINCTRL_PIN(34, "GPIO_34"), + PINCTRL_PIN(35, "GPIO_35"), + PINCTRL_PIN(36, "GPIO_36"), + PINCTRL_PIN(37, "GPIO_37"), + PINCTRL_PIN(38, "GPIO_38"), + PINCTRL_PIN(39, "GPIO_39"), + PINCTRL_PIN(40, "GPIO_40"), + PINCTRL_PIN(41, "GPIO_41"), + PINCTRL_PIN(42, "GPIO_42"), + PINCTRL_PIN(43, "GPIO_43"), + PINCTRL_PIN(44, "GPIO_44"), + PINCTRL_PIN(45, "GPIO_45"), + PINCTRL_PIN(46, "GPIO_46"), + PINCTRL_PIN(47, "GPIO_47"), + PINCTRL_PIN(48, "GPIO_48"), + PINCTRL_PIN(49, "GPIO_49"), + PINCTRL_PIN(50, "GPIO_50"), + PINCTRL_PIN(51, "GPIO_51"), + PINCTRL_PIN(52, "GPIO_52"), + PINCTRL_PIN(53, "GPIO_53"), + PINCTRL_PIN(54, "GPIO_54"), + PINCTRL_PIN(55, "GPIO_55"), + PINCTRL_PIN(56, "GPIO_56"), + PINCTRL_PIN(57, "GPIO_57"), + PINCTRL_PIN(58, "GPIO_58"), + PINCTRL_PIN(59, "GPIO_59"), + PINCTRL_PIN(60, "GPIO_60"), + PINCTRL_PIN(61, "GPIO_61"), + PINCTRL_PIN(62, "GPIO_62"), + PINCTRL_PIN(63, "GPIO_63"), + PINCTRL_PIN(64, "GPIO_64"), + PINCTRL_PIN(65, "GPIO_65"), + PINCTRL_PIN(66, "GPIO_66"), + PINCTRL_PIN(67, "GPIO_67"), + PINCTRL_PIN(68, "GPIO_68"), + PINCTRL_PIN(69, "GPIO_69"), + PINCTRL_PIN(70, "GPIO_70"), + PINCTRL_PIN(71, "GPIO_71"), + PINCTRL_PIN(72, "GPIO_72"), + PINCTRL_PIN(73, "GPIO_73"), + PINCTRL_PIN(74, "GPIO_74"), + PINCTRL_PIN(75, "GPIO_75"), + PINCTRL_PIN(76, "GPIO_76"), + PINCTRL_PIN(77, "GPIO_77"), + PINCTRL_PIN(78, "GPIO_78"), + PINCTRL_PIN(79, "GPIO_79"), + PINCTRL_PIN(80, "GPIO_80"), + PINCTRL_PIN(81, "GPIO_81"), + PINCTRL_PIN(82, "GPIO_82"), + PINCTRL_PIN(83, "GPIO_83"), + PINCTRL_PIN(84, "GPIO_84"), + PINCTRL_PIN(85, "GPIO_85"), + PINCTRL_PIN(86, "GPIO_86"), + PINCTRL_PIN(87, "GPIO_87"), + PINCTRL_PIN(88, "GPIO_88"), + PINCTRL_PIN(89, "GPIO_89"), + PINCTRL_PIN(90, "GPIO_90"), + PINCTRL_PIN(91, "GPIO_91"), + PINCTRL_PIN(92, "GPIO_92"), + PINCTRL_PIN(93, "GPIO_93"), + PINCTRL_PIN(94, "GPIO_94"), + PINCTRL_PIN(95, "GPIO_95"), + PINCTRL_PIN(96, "GPIO_96"), + PINCTRL_PIN(97, "GPIO_97"), + PINCTRL_PIN(98, "GPIO_98"), + PINCTRL_PIN(99, "GPIO_99"), + PINCTRL_PIN(100, "GPIO_100"), + PINCTRL_PIN(101, "GPIO_101"), + PINCTRL_PIN(102, "GPIO_102"), + PINCTRL_PIN(103, "GPIO_103"), + PINCTRL_PIN(104, "GPIO_104"), + PINCTRL_PIN(105, "GPIO_105"), + PINCTRL_PIN(106, "GPIO_106"), + PINCTRL_PIN(107, "GPIO_107"), + PINCTRL_PIN(108, "GPIO_108"), + PINCTRL_PIN(109, "GPIO_109"), + PINCTRL_PIN(110, "GPIO_110"), + PINCTRL_PIN(111, "GPIO_111"), + PINCTRL_PIN(112, "GPIO_112"), + PINCTRL_PIN(113, "GPIO_113"), + PINCTRL_PIN(114, "GPIO_114"), + PINCTRL_PIN(115, "GPIO_115"), + PINCTRL_PIN(116, "GPIO_116"), + PINCTRL_PIN(117, "GPIO_117"), + PINCTRL_PIN(118, "GPIO_118"), + PINCTRL_PIN(119, "GPIO_119"), + PINCTRL_PIN(120, "GPIO_120"), + PINCTRL_PIN(121, "GPIO_121"), + PINCTRL_PIN(122, "GPIO_122"), + PINCTRL_PIN(123, "GPIO_123"), + PINCTRL_PIN(124, "GPIO_124"), + PINCTRL_PIN(125, "GPIO_125"), + PINCTRL_PIN(126, "GPIO_126"), + PINCTRL_PIN(127, "GPIO_127"), + PINCTRL_PIN(128, "GPIO_128"), + PINCTRL_PIN(129, "GPIO_129"), + PINCTRL_PIN(130, "GPIO_130"), + PINCTRL_PIN(131, "GPIO_131"), + PINCTRL_PIN(132, "GPIO_132"), + PINCTRL_PIN(133, "GPIO_133"), + PINCTRL_PIN(134, "SDC1_CLK"), + PINCTRL_PIN(135, "SDC1_CMD"), + PINCTRL_PIN(136, "SDC1_DATA"), + PINCTRL_PIN(137, "SDC1_RCLK"), + PINCTRL_PIN(138, "SDC2_CLK"), + PINCTRL_PIN(139, "SDC2_CMD"), + PINCTRL_PIN(140, "SDC2_DATA"), + PINCTRL_PIN(141, "QDSD_CLK"), + PINCTRL_PIN(142, "QDSD_CMD"), + PINCTRL_PIN(143, "QDSD_DATA0"), + PINCTRL_PIN(144, "QDSD_DATA1"), + PINCTRL_PIN(145, "QDSD_DATA2"), + PINCTRL_PIN(146, "QDSD_DATA3"), +}; + +#define DECLARE_MSM_GPIO_PINS(pin) \ + static const unsigned int gpio##pin##_pins[] = { pin } + +DECLARE_MSM_GPIO_PINS(0); +DECLARE_MSM_GPIO_PINS(1); +DECLARE_MSM_GPIO_PINS(2); +DECLARE_MSM_GPIO_PINS(3); +DECLARE_MSM_GPIO_PINS(4); +DECLARE_MSM_GPIO_PINS(5); +DECLARE_MSM_GPIO_PINS(6); +DECLARE_MSM_GPIO_PINS(7); +DECLARE_MSM_GPIO_PINS(8); +DECLARE_MSM_GPIO_PINS(9); +DECLARE_MSM_GPIO_PINS(10); +DECLARE_MSM_GPIO_PINS(11); +DECLARE_MSM_GPIO_PINS(12); +DECLARE_MSM_GPIO_PINS(13); +DECLARE_MSM_GPIO_PINS(14); +DECLARE_MSM_GPIO_PINS(15); +DECLARE_MSM_GPIO_PINS(16); +DECLARE_MSM_GPIO_PINS(17); +DECLARE_MSM_GPIO_PINS(18); +DECLARE_MSM_GPIO_PINS(19); +DECLARE_MSM_GPIO_PINS(20); +DECLARE_MSM_GPIO_PINS(21); +DECLARE_MSM_GPIO_PINS(22); +DECLARE_MSM_GPIO_PINS(23); +DECLARE_MSM_GPIO_PINS(24); +DECLARE_MSM_GPIO_PINS(25); +DECLARE_MSM_GPIO_PINS(26); +DECLARE_MSM_GPIO_PINS(27); +DECLARE_MSM_GPIO_PINS(28); +DECLARE_MSM_GPIO_PINS(29); +DECLARE_MSM_GPIO_PINS(30); +DECLARE_MSM_GPIO_PINS(31); +DECLARE_MSM_GPIO_PINS(32); +DECLARE_MSM_GPIO_PINS(33); +DECLARE_MSM_GPIO_PINS(34); +DECLARE_MSM_GPIO_PINS(35); +DECLARE_MSM_GPIO_PINS(36); +DECLARE_MSM_GPIO_PINS(37); +DECLARE_MSM_GPIO_PINS(38); +DECLARE_MSM_GPIO_PINS(39); +DECLARE_MSM_GPIO_PINS(40); +DECLARE_MSM_GPIO_PINS(41); +DECLARE_MSM_GPIO_PINS(42); +DECLARE_MSM_GPIO_PINS(43); +DECLARE_MSM_GPIO_PINS(44); +DECLARE_MSM_GPIO_PINS(45); +DECLARE_MSM_GPIO_PINS(46); +DECLARE_MSM_GPIO_PINS(47); +DECLARE_MSM_GPIO_PINS(48); +DECLARE_MSM_GPIO_PINS(49); +DECLARE_MSM_GPIO_PINS(50); +DECLARE_MSM_GPIO_PINS(51); +DECLARE_MSM_GPIO_PINS(52); +DECLARE_MSM_GPIO_PINS(53); +DECLARE_MSM_GPIO_PINS(54); +DECLARE_MSM_GPIO_PINS(55); +DECLARE_MSM_GPIO_PINS(56); +DECLARE_MSM_GPIO_PINS(57); +DECLARE_MSM_GPIO_PINS(58); +DECLARE_MSM_GPIO_PINS(59); +DECLARE_MSM_GPIO_PINS(60); +DECLARE_MSM_GPIO_PINS(61); +DECLARE_MSM_GPIO_PINS(62); +DECLARE_MSM_GPIO_PINS(63); +DECLARE_MSM_GPIO_PINS(64); +DECLARE_MSM_GPIO_PINS(65); +DECLARE_MSM_GPIO_PINS(66); +DECLARE_MSM_GPIO_PINS(67); +DECLARE_MSM_GPIO_PINS(68); +DECLARE_MSM_GPIO_PINS(69); +DECLARE_MSM_GPIO_PINS(70); +DECLARE_MSM_GPIO_PINS(71); +DECLARE_MSM_GPIO_PINS(72); +DECLARE_MSM_GPIO_PINS(73); +DECLARE_MSM_GPIO_PINS(74); +DECLARE_MSM_GPIO_PINS(75); +DECLARE_MSM_GPIO_PINS(76); +DECLARE_MSM_GPIO_PINS(77); +DECLARE_MSM_GPIO_PINS(78); +DECLARE_MSM_GPIO_PINS(79); +DECLARE_MSM_GPIO_PINS(80); +DECLARE_MSM_GPIO_PINS(81); +DECLARE_MSM_GPIO_PINS(82); +DECLARE_MSM_GPIO_PINS(83); +DECLARE_MSM_GPIO_PINS(84); +DECLARE_MSM_GPIO_PINS(85); +DECLARE_MSM_GPIO_PINS(86); +DECLARE_MSM_GPIO_PINS(87); +DECLARE_MSM_GPIO_PINS(88); +DECLARE_MSM_GPIO_PINS(89); +DECLARE_MSM_GPIO_PINS(90); +DECLARE_MSM_GPIO_PINS(91); +DECLARE_MSM_GPIO_PINS(92); +DECLARE_MSM_GPIO_PINS(93); +DECLARE_MSM_GPIO_PINS(94); +DECLARE_MSM_GPIO_PINS(95); +DECLARE_MSM_GPIO_PINS(96); +DECLARE_MSM_GPIO_PINS(97); +DECLARE_MSM_GPIO_PINS(98); +DECLARE_MSM_GPIO_PINS(99); +DECLARE_MSM_GPIO_PINS(100); +DECLARE_MSM_GPIO_PINS(101); +DECLARE_MSM_GPIO_PINS(102); +DECLARE_MSM_GPIO_PINS(103); +DECLARE_MSM_GPIO_PINS(104); +DECLARE_MSM_GPIO_PINS(105); +DECLARE_MSM_GPIO_PINS(106); +DECLARE_MSM_GPIO_PINS(107); +DECLARE_MSM_GPIO_PINS(108); +DECLARE_MSM_GPIO_PINS(109); +DECLARE_MSM_GPIO_PINS(110); +DECLARE_MSM_GPIO_PINS(111); +DECLARE_MSM_GPIO_PINS(112); +DECLARE_MSM_GPIO_PINS(113); +DECLARE_MSM_GPIO_PINS(114); +DECLARE_MSM_GPIO_PINS(115); +DECLARE_MSM_GPIO_PINS(116); +DECLARE_MSM_GPIO_PINS(117); +DECLARE_MSM_GPIO_PINS(118); +DECLARE_MSM_GPIO_PINS(119); +DECLARE_MSM_GPIO_PINS(120); +DECLARE_MSM_GPIO_PINS(121); +DECLARE_MSM_GPIO_PINS(122); +DECLARE_MSM_GPIO_PINS(123); +DECLARE_MSM_GPIO_PINS(124); +DECLARE_MSM_GPIO_PINS(125); +DECLARE_MSM_GPIO_PINS(126); +DECLARE_MSM_GPIO_PINS(127); +DECLARE_MSM_GPIO_PINS(128); +DECLARE_MSM_GPIO_PINS(129); +DECLARE_MSM_GPIO_PINS(130); +DECLARE_MSM_GPIO_PINS(131); +DECLARE_MSM_GPIO_PINS(132); +DECLARE_MSM_GPIO_PINS(133); + +static const unsigned int sdc1_clk_pins[] = { 134 }; +static const unsigned int sdc1_cmd_pins[] = { 135 }; +static const unsigned int sdc1_data_pins[] = { 136 }; +static const unsigned int sdc1_rclk_pins[] = { 137 }; +static const unsigned int sdc2_clk_pins[] = { 138 }; +static const unsigned int sdc2_cmd_pins[] = { 139 }; +static const unsigned int sdc2_data_pins[] = { 140 }; +static const unsigned int qdsd_clk_pins[] = { 141 }; +static const unsigned int qdsd_cmd_pins[] = { 142 }; +static const unsigned int qdsd_data0_pins[] = { 143 }; +static const unsigned int qdsd_data1_pins[] = { 144 }; +static const unsigned int qdsd_data2_pins[] = { 145 }; +static const unsigned int qdsd_data3_pins[] = { 146 }; + +#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9) \ + { \ + .grp = PINCTRL_PINGROUP("gpio" #id, \ + gpio##id##_pins, \ + ARRAY_SIZE(gpio##id##_pins)), \ + .funcs = (int[]){ \ + msm_mux_gpio, \ + msm_mux_##f1, \ + msm_mux_##f2, \ + msm_mux_##f3, \ + msm_mux_##f4, \ + msm_mux_##f5, \ + msm_mux_##f6, \ + msm_mux_##f7, \ + msm_mux_##f8, \ + msm_mux_##f9 \ + }, \ + .nfuncs = 10, \ + .ctl_reg = 0x1000 * id, \ + .io_reg = 0x4 + 0x1000 * id, \ + .intr_cfg_reg = 0x8 + 0x1000 * id, \ + .intr_status_reg = 0xc + 0x1000 * id, \ + .intr_target_reg = 0x8 + 0x1000 * id, \ + .mux_bit = 2, \ + .pull_bit = 0, \ + .drv_bit = 6, \ + .oe_bit = 9, \ + .in_bit = 0, \ + .out_bit = 1, \ + .intr_enable_bit = 0, \ + .intr_status_bit = 0, \ + .intr_target_bit = 5, \ + .intr_target_kpss_val = 4, \ + .intr_raw_status_bit = 4, \ + .intr_polarity_bit = 1, \ + .intr_detection_bit = 2, \ + .intr_detection_width = 2, \ + } + +#define SDC_PINGROUP(pg_name, ctl, pull, drv) \ + { \ + .grp = PINCTRL_PINGROUP(#pg_name, \ + pg_name##_pins, \ + ARRAY_SIZE(pg_name##_pins)), \ + .ctl_reg = ctl, \ + .io_reg = 0, \ + .intr_cfg_reg = 0, \ + .intr_status_reg = 0, \ + .intr_target_reg = 0, \ + .mux_bit = -1, \ + .pull_bit = pull, \ + .drv_bit = drv, \ + .oe_bit = -1, \ + .in_bit = -1, \ + .out_bit = -1, \ + .intr_enable_bit = -1, \ + .intr_status_bit = -1, \ + .intr_target_bit = -1, \ + .intr_target_kpss_val = -1, \ + .intr_raw_status_bit = -1, \ + .intr_polarity_bit = -1, \ + .intr_detection_bit = -1, \ + .intr_detection_width = -1, \ + } + +enum msm8917_functions { + msm_mux_accel_int, + msm_mux_adsp_ext, + msm_mux_alsp_int, + msm_mux_atest_bbrx0, + msm_mux_atest_bbrx1, + msm_mux_atest_char, + msm_mux_atest_char0, + msm_mux_atest_char1, + msm_mux_atest_char2, + msm_mux_atest_char3, + msm_mux_atest_combodac_to_gpio_native, + msm_mux_atest_gpsadc_dtest0_native, + msm_mux_atest_gpsadc_dtest1_native, + msm_mux_atest_tsens, + msm_mux_atest_wlan0, + msm_mux_atest_wlan1, + msm_mux_audio_ref, + msm_mux_audio_reset, + msm_mux_bimc_dte0, + msm_mux_bimc_dte1, + msm_mux_blsp6_spi, + msm_mux_blsp8_spi, + msm_mux_blsp_i2c1, + msm_mux_blsp_i2c2, + msm_mux_blsp_i2c3, + msm_mux_blsp_i2c4, + msm_mux_blsp_i2c5, + msm_mux_blsp_i2c6, + msm_mux_blsp_i2c7, + msm_mux_blsp_i2c8, + msm_mux_blsp_spi1, + msm_mux_blsp_spi2, + msm_mux_blsp_spi3, + msm_mux_blsp_spi4, + msm_mux_blsp_spi5, + msm_mux_blsp_spi6, + msm_mux_blsp_spi7, + msm_mux_blsp_spi8, + msm_mux_blsp_uart1, + msm_mux_blsp_uart2, + msm_mux_blsp_uart3, + msm_mux_blsp_uart4, + msm_mux_blsp_uart5, + msm_mux_blsp_uart6, + msm_mux_blsp_uart7, + msm_mux_blsp_uart8, + msm_mux_cam0_ldo, + msm_mux_cam1_rst, + msm_mux_cam1_standby, + msm_mux_cam2_rst, + msm_mux_cam2_standby, + msm_mux_cam_mclk, + msm_mux_cci_async, + msm_mux_cci_i2c, + msm_mux_cci_timer0, + msm_mux_cci_timer1, + msm_mux_cdc_pdm0, + msm_mux_codec_int1, + msm_mux_codec_int2, + msm_mux_codec_mad, + msm_mux_coex_uart, + msm_mux_cri_trng, + msm_mux_cri_trng0, + msm_mux_cri_trng1, + msm_mux_dbg_out, + msm_mux_dmic0_clk, + msm_mux_dmic0_data, + msm_mux_ebi_cdc, + msm_mux_ebi_ch0, + msm_mux_ext_lpass, + msm_mux_forced_usb, + msm_mux_fp_gpio, + msm_mux_fp_int, + msm_mux_gcc_gp1_clk_a, + msm_mux_gcc_gp1_clk_b, + msm_mux_gcc_gp2_clk_a, + msm_mux_gcc_gp2_clk_b, + msm_mux_gcc_gp3_clk_a, + msm_mux_gcc_gp3_clk_b, + msm_mux_gcc_plltest, + msm_mux_gcc_tlmm, + msm_mux_gpio, + msm_mux_gsm0_tx, + msm_mux_key_focus, + msm_mux_key_snapshot, + msm_mux_key_volp, + msm_mux_ldo_en, + msm_mux_ldo_update, + msm_mux_lpass_slimbus, + msm_mux_lpass_slimbus0, + msm_mux_lpass_slimbus1, + msm_mux_m_voc, + msm_mux_mag_int, + msm_mux_mdp_vsync, + msm_mux_mipi_dsi0, + msm_mux_modem_tsync, + msm_mux_nav_pps, + msm_mux_nav_pps_in_a, + msm_mux_nav_pps_in_b, + msm_mux_nav_tsync, + msm_mux_nfc_pwr, + msm_mux_ov_ldo, + msm_mux_pa_indicator, + msm_mux_pbs0, + msm_mux_pbs1, + msm_mux_pbs2, + msm_mux_pri_mi2s, + msm_mux_pri_mi2s_mclk_a, + msm_mux_pri_mi2s_mclk_b, + msm_mux_pri_mi2s_ws, + msm_mux_prng_rosc, + msm_mux_pwr_crypto_enabled_a, + msm_mux_pwr_crypto_enabled_b, + msm_mux_pwr_modem_enabled_a, + msm_mux_pwr_modem_enabled_b, + msm_mux_pwr_nav_enabled_a, + msm_mux_pwr_nav_enabled_b, + msm_mux_qdss_cti_trig_in_a0, + msm_mux_qdss_cti_trig_in_a1, + msm_mux_qdss_cti_trig_in_b0, + msm_mux_qdss_cti_trig_in_b1, + msm_mux_qdss_cti_trig_out_a0, + msm_mux_qdss_cti_trig_out_a1, + msm_mux_qdss_cti_trig_out_b0, + msm_mux_qdss_cti_trig_out_b1, + msm_mux_qdss_traceclk_a, + msm_mux_qdss_traceclk_b, + msm_mux_qdss_tracectl_a, + msm_mux_qdss_tracectl_b, + msm_mux_qdss_tracedata_a, + msm_mux_qdss_tracedata_b, + msm_mux_sd_write, + msm_mux_sdcard_det, + msm_mux_sec_mi2s, + msm_mux_sec_mi2s_mclk_a, + msm_mux_sec_mi2s_mclk_b, + msm_mux_sensor_rst, + msm_mux_smb_int, + msm_mux_ssbi_wtr1, + msm_mux_ts_resout, + msm_mux_ts_sample, + msm_mux_uim1_clk, + msm_mux_uim1_data, + msm_mux_uim1_present, + msm_mux_uim1_reset, + msm_mux_uim2_clk, + msm_mux_uim2_data, + msm_mux_uim2_present, + msm_mux_uim2_reset, + msm_mux_uim_batt, + msm_mux_us_emitter, + msm_mux_us_euro, + msm_mux_wcss_bt, + msm_mux_wcss_fm, + msm_mux_wcss_wlan, + msm_mux_wcss_wlan0, + msm_mux_wcss_wlan1, + msm_mux_wcss_wlan2, + msm_mux_webcam_rst, + msm_mux_webcam_standby, + msm_mux_wsa_io, + msm_mux_wsa_irq, + msm_mux__, +}; + +static const char * const qdss_tracedata_b_groups[] = { + "gpio0", "gpio1", "gpio6", "gpio7", "gpio12", "gpio13", "gpio23", + "gpio42", "gpio43", "gpio44", "gpio47", "gpio66", "gpio86", "gpio87", + "gpio88", "gpio92", +}; + +static const char * const blsp_uart1_groups[] = { + "gpio0", "gpio1", "gpio2", "gpio3", +}; + +static const char * const gpio_groups[] = { + "gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", + "gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14", + "gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", + "gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28", + "gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35", + "gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42", + "gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49", + "gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56", + "gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63", + "gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70", + "gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77", + "gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84", + "gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91", + "gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98", + "gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104", + "gpio105", "gpio106", "gpio107", "gpio108", "gpio109", "gpio110", + "gpio111", "gpio112", "gpio113", "gpio114", "gpio115", "gpio116", + "gpio117", "gpio118", "gpio119", "gpio120", "gpio121", "gpio122", + "gpio123", "gpio124", "gpio125", "gpio126", "gpio127", "gpio128", + "gpio129", "gpio130", "gpio131", "gpio132", "gpio133", +}; + +static const char * const blsp_spi1_groups[] = { + "gpio0", "gpio1", "gpio2", "gpio3", +}; + +static const char * const adsp_ext_groups[] = { + "gpio1", +}; + +static const char * const blsp_i2c1_groups[] = { + "gpio2", "gpio3", +}; + +static const char * const prng_rosc_groups[] = { + "gpio2", +}; + +static const char * const qdss_cti_trig_out_b0_groups[] = { + "gpio2", +}; + +static const char * const blsp_spi2_groups[] = { + "gpio4", "gpio5", "gpio6", "gpio7", +}; + +static const char * const blsp_uart2_groups[] = { + "gpio4", "gpio5", "gpio6", "gpio7", +}; + +static const char * const blsp_uart3_groups[] = { + "gpio8", "gpio9", "gpio10", "gpio11", +}; + +static const char * const pbs0_groups[] = { + "gpio8", +}; + +static const char * const pbs1_groups[] = { + "gpio9", +}; + +static const char * const pwr_modem_enabled_b_groups[] = { + "gpio9", +}; + +static const char * const blsp_i2c3_groups[] = { + "gpio10", "gpio11", +}; + +static const char * const gcc_gp2_clk_b_groups[] = { + "gpio10", +}; + +static const char * const ldo_update_groups[] = { + "gpio4", +}; + +static const char * const atest_combodac_to_gpio_native_groups[] = { + "gpio4", "gpio12", "gpio13", "gpio20", "gpio21", "gpio28", "gpio29", + "gpio30", "gpio39", "gpio40", "gpio41", "gpio42", "gpio43", "gpio44", + "gpio45", "gpio46", "gpio47", "gpio48", "gpio67", "gpio115", +}; + +static const char * const ldo_en_groups[] = { + "gpio5", +}; + +static const char * const blsp_i2c2_groups[] = { + "gpio6", "gpio7", +}; + +static const char * const gcc_gp1_clk_b_groups[] = { + "gpio6", +}; + +static const char * const pbs2_groups[] = { + "gpio7", +}; + +static const char * const atest_gpsadc_dtest0_native_groups[] = { + "gpio7", +}; + +static const char * const blsp_spi3_groups[] = { + "gpio8", "gpio9", "gpio10", "gpio11", +}; + +static const char * const gcc_gp3_clk_b_groups[] = { + "gpio11", +}; + +static const char * const blsp_spi4_groups[] = { + "gpio12", "gpio13", "gpio14", "gpio15", +}; + +static const char * const blsp_uart4_groups[] = { + "gpio12", "gpio13", "gpio14", "gpio15", +}; + +static const char * const sec_mi2s_groups[] = { + "gpio12", "gpio13", "gpio94", "gpio95", +}; + +static const char * const pwr_nav_enabled_b_groups[] = { + "gpio12", +}; + +static const char * const codec_mad_groups[] = { + "gpio13", +}; + +static const char * const pwr_crypto_enabled_b_groups[] = { + "gpio13", +}; + +static const char * const blsp_i2c4_groups[] = { + "gpio14", "gpio15", +}; + +static const char * const blsp_spi5_groups[] = { + "gpio16", "gpio17", "gpio18", "gpio19", +}; + +static const char * const blsp_uart5_groups[] = { + "gpio16", "gpio17", "gpio18", "gpio19", +}; + +static const char * const qdss_traceclk_a_groups[] = { + "gpio16", +}; + +static const char * const atest_bbrx1_groups[] = { + "gpio16", +}; + +static const char * const m_voc_groups[] = { + "gpio17", "gpio21", +}; + +static const char * const qdss_cti_trig_in_a0_groups[] = { + "gpio17", +}; + +static const char * const qdss_cti_trig_in_b0_groups[] = { + "gpio21", +}; + +static const char * const blsp_i2c6_groups[] = { + "gpio22", "gpio23", +}; + +static const char * const qdss_traceclk_b_groups[] = { + "gpio22", +}; + +static const char * const atest_wlan0_groups[] = { + "gpio22", +}; + +static const char * const atest_bbrx0_groups[] = { + "gpio17", +}; + +static const char * const blsp_i2c5_groups[] = { + "gpio18", "gpio19", +}; + +static const char * const qdss_tracectl_a_groups[] = { + "gpio18", +}; + +static const char * const atest_gpsadc_dtest1_native_groups[] = { + "gpio18", +}; + +static const char * const qdss_tracedata_a_groups[] = { + "gpio19", "gpio26", "gpio27", "gpio28", "gpio29", "gpio30", "gpio31", + "gpio32", "gpio33", "gpio34", "gpio35", "gpio36", "gpio38", "gpio39", + "gpio40", "gpio50", +}; + +static const char * const blsp_spi6_groups[] = { + "gpio20", "gpio21", "gpio22", "gpio23", +}; + +static const char * const blsp_uart6_groups[] = { + "gpio20", "gpio21", "gpio22", "gpio23", +}; + +static const char * const qdss_tracectl_b_groups[] = { + "gpio20", +}; + +static const char * const atest_wlan1_groups[] = { + "gpio23", +}; + +static const char * const mdp_vsync_groups[] = { + "gpio24", "gpio25", +}; + +static const char * const pri_mi2s_mclk_a_groups[] = { + "gpio25", +}; + +static const char * const sec_mi2s_mclk_a_groups[] = { + "gpio25", +}; + +static const char * const cam_mclk_groups[] = { + "gpio26", "gpio27", "gpio28", +}; + +static const char * const cci_i2c_groups[] = { + "gpio29", "gpio30", "gpio31", "gpio32", +}; + +static const char * const pwr_modem_enabled_a_groups[] = { + "gpio29", +}; + +static const char * const cci_timer0_groups[] = { + "gpio33", +}; + +static const char * const cci_timer1_groups[] = { + "gpio34", +}; + +static const char * const cam1_standby_groups[] = { + "gpio35", +}; + +static const char * const pwr_nav_enabled_a_groups[] = { + "gpio35", +}; + +static const char * const cam1_rst_groups[] = { + "gpio36", +}; + +static const char * const pwr_crypto_enabled_a_groups[] = { + "gpio36", +}; + +static const char * const forced_usb_groups[] = { + "gpio37", +}; + +static const char * const qdss_cti_trig_out_b1_groups[] = { + "gpio37", +}; + +static const char * const cam2_rst_groups[] = { + "gpio38", +}; + +static const char * const webcam_standby_groups[] = { + "gpio39", +}; + +static const char * const cci_async_groups[] = { + "gpio39", +}; + +static const char * const webcam_rst_groups[] = { + "gpio40", +}; + +static const char * const ov_ldo_groups[] = { + "gpio41", +}; + +static const char * const sd_write_groups[] = { + "gpio41", +}; + +static const char * const accel_int_groups[] = { + "gpio42", +}; + +static const char * const gcc_gp1_clk_a_groups[] = { + "gpio42", +}; + +static const char * const alsp_int_groups[] = { + "gpio43", +}; + +static const char * const gcc_gp2_clk_a_groups[] = { + "gpio43", +}; + +static const char * const mag_int_groups[] = { + "gpio44", +}; + +static const char * const gcc_gp3_clk_a_groups[] = { + "gpio44", +}; + +static const char * const blsp6_spi_groups[] = { + "gpio47", +}; + +static const char * const fp_int_groups[] = { + "gpio48", +}; + +static const char * const qdss_cti_trig_in_b1_groups[] = { + "gpio48", +}; + +static const char * const uim_batt_groups[] = { + "gpio49", +}; + +static const char * const cam2_standby_groups[] = { + "gpio50", +}; + +static const char * const uim1_data_groups[] = { + "gpio51", +}; + +static const char * const uim1_clk_groups[] = { + "gpio52", +}; + +static const char * const uim1_reset_groups[] = { + "gpio53", +}; + +static const char * const uim1_present_groups[] = { + "gpio54", +}; + +static const char * const uim2_data_groups[] = { + "gpio55", +}; + +static const char * const uim2_clk_groups[] = { + "gpio56", +}; + +static const char * const uim2_reset_groups[] = { + "gpio57", +}; + +static const char * const uim2_present_groups[] = { + "gpio58", +}; + +static const char * const sensor_rst_groups[] = { + "gpio59", +}; + +static const char * const mipi_dsi0_groups[] = { + "gpio60", +}; + +static const char * const smb_int_groups[] = { + "gpio61", +}; + +static const char * const cam0_ldo_groups[] = { + "gpio62", +}; + +static const char * const us_euro_groups[] = { + "gpio63", +}; + +static const char * const atest_char3_groups[] = { + "gpio63", +}; + +static const char * const dbg_out_groups[] = { + "gpio63", +}; + +static const char * const bimc_dte0_groups[] = { + "gpio63", "gpio65", +}; + +static const char * const ts_resout_groups[] = { + "gpio64", +}; + +static const char * const ts_sample_groups[] = { + "gpio65", +}; + +static const char * const sec_mi2s_mclk_b_groups[] = { + "gpio66", +}; + +static const char * const pri_mi2s_groups[] = { + "gpio66", "gpio85", "gpio86", "gpio88", "gpio94", "gpio95", +}; + +static const char * const sdcard_det_groups[] = { + "gpio67", +}; + +static const char * const atest_char1_groups[] = { + "gpio67", +}; + +static const char * const ebi_cdc_groups[] = { + "gpio67", "gpio69", "gpio118", "gpio119", "gpio120", "gpio123", +}; + +static const char * const audio_reset_groups[] = { + "gpio68", +}; + +static const char * const atest_char0_groups[] = { + "gpio68", +}; + +static const char * const audio_ref_groups[] = { + "gpio69", +}; + +static const char * const cdc_pdm0_groups[] = { + "gpio69", "gpio70", "gpio71", "gpio72", "gpio73", "gpio74", +}; + +static const char * const pri_mi2s_mclk_b_groups[] = { + "gpio69", +}; + +static const char * const lpass_slimbus_groups[] = { + "gpio70", +}; + +static const char * const lpass_slimbus0_groups[] = { + "gpio71", +}; + +static const char * const lpass_slimbus1_groups[] = { + "gpio72", +}; + +static const char * const codec_int1_groups[] = { + "gpio73", +}; + +static const char * const codec_int2_groups[] = { + "gpio74", +}; + +static const char * const wcss_bt_groups[] = { + "gpio75", "gpio83", "gpio84", +}; + +static const char * const atest_char2_groups[] = { + "gpio75", +}; + +static const char * const ebi_ch0_groups[] = { + "gpio75", +}; + +static const char * const wcss_wlan2_groups[] = { + "gpio76", +}; + +static const char * const wcss_wlan1_groups[] = { + "gpio77", +}; + +static const char * const wcss_wlan0_groups[] = { + "gpio78", +}; + +static const char * const wcss_wlan_groups[] = { + "gpio79", "gpio80", +}; + +static const char * const wcss_fm_groups[] = { + "gpio81", "gpio82", +}; + +static const char * const ext_lpass_groups[] = { + "gpio81", +}; + +static const char * const cri_trng_groups[] = { + "gpio82", +}; + +static const char * const cri_trng1_groups[] = { + "gpio83", +}; + +static const char * const cri_trng0_groups[] = { + "gpio84", +}; + +static const char * const blsp_spi7_groups[] = { + "gpio85", "gpio86", "gpio87", "gpio88", +}; + +static const char * const blsp_uart7_groups[] = { + "gpio85", "gpio86", "gpio87", "gpio88", +}; + +static const char * const pri_mi2s_ws_groups[] = { + "gpio87", +}; + +static const char * const blsp_i2c7_groups[] = { + "gpio87", "gpio88", +}; + +static const char * const gcc_tlmm_groups[] = { + "gpio87", +}; + +static const char * const dmic0_clk_groups[] = { + "gpio89", +}; + +static const char * const dmic0_data_groups[] = { + "gpio90", +}; + +static const char * const key_volp_groups[] = { + "gpio91", +}; + +static const char * const qdss_cti_trig_in_a1_groups[] = { + "gpio91", +}; + +static const char * const us_emitter_groups[] = { + "gpio92", +}; + +static const char * const wsa_irq_groups[] = { + "gpio93", +}; + +static const char * const wsa_io_groups[] = { + "gpio94", "gpio95", +}; + +static const char * const blsp_spi8_groups[] = { + "gpio96", "gpio97", "gpio98", "gpio99", +}; + +static const char * const blsp_uart8_groups[] = { + "gpio96", "gpio97", "gpio98", "gpio99", +}; + +static const char * const blsp_i2c8_groups[] = { + "gpio98", "gpio99", +}; + +static const char * const gcc_plltest_groups[] = { + "gpio98", "gpio99", +}; + +static const char * const nav_pps_in_a_groups[] = { + "gpio115", +}; + +static const char * const pa_indicator_groups[] = { + "gpio116", +}; + +static const char * const modem_tsync_groups[] = { + "gpio117", +}; + +static const char * const nav_tsync_groups[] = { + "gpio117", +}; + +static const char * const nav_pps_in_b_groups[] = { + "gpio117", +}; + +static const char * const nav_pps_groups[] = { + "gpio117", +}; + +static const char * const gsm0_tx_groups[] = { + "gpio119", +}; + +static const char * const atest_char_groups[] = { + "gpio120", +}; + +static const char * const atest_tsens_groups[] = { + "gpio120", +}; + +static const char * const bimc_dte1_groups[] = { + "gpio121", "gpio122", +}; + +static const char * const ssbi_wtr1_groups[] = { + "gpio122", "gpio123", +}; + +static const char * const fp_gpio_groups[] = { + "gpio124", +}; + +static const char * const coex_uart_groups[] = { + "gpio124", "gpio127", +}; + +static const char * const key_snapshot_groups[] = { + "gpio127", +}; + +static const char * const key_focus_groups[] = { + "gpio128", +}; + +static const char * const nfc_pwr_groups[] = { + "gpio129", +}; + +static const char * const blsp8_spi_groups[] = { + "gpio130", +}; + +static const char * const qdss_cti_trig_out_a0_groups[] = { + "gpio132", +}; + +static const char * const qdss_cti_trig_out_a1_groups[] = { + "gpio133", +}; + +static const struct pinfunction msm8917_functions[] = { + MSM_PIN_FUNCTION(accel_int), + MSM_PIN_FUNCTION(adsp_ext), + MSM_PIN_FUNCTION(alsp_int), + MSM_PIN_FUNCTION(atest_bbrx0), + MSM_PIN_FUNCTION(atest_bbrx1), + MSM_PIN_FUNCTION(atest_char), + MSM_PIN_FUNCTION(atest_char0), + MSM_PIN_FUNCTION(atest_char1), + MSM_PIN_FUNCTION(atest_char2), + MSM_PIN_FUNCTION(atest_char3), + MSM_PIN_FUNCTION(atest_combodac_to_gpio_native), + MSM_PIN_FUNCTION(atest_gpsadc_dtest0_native), + MSM_PIN_FUNCTION(atest_gpsadc_dtest1_native), + MSM_PIN_FUNCTION(atest_tsens), + MSM_PIN_FUNCTION(atest_wlan0), + MSM_PIN_FUNCTION(atest_wlan1), + MSM_PIN_FUNCTION(audio_ref), + MSM_PIN_FUNCTION(audio_reset), + MSM_PIN_FUNCTION(bimc_dte0), + MSM_PIN_FUNCTION(bimc_dte1), + MSM_PIN_FUNCTION(blsp6_spi), + MSM_PIN_FUNCTION(blsp8_spi), + MSM_PIN_FUNCTION(blsp_i2c1), + MSM_PIN_FUNCTION(blsp_i2c2), + MSM_PIN_FUNCTION(blsp_i2c3), + MSM_PIN_FUNCTION(blsp_i2c4), + MSM_PIN_FUNCTION(blsp_i2c5), + MSM_PIN_FUNCTION(blsp_i2c6), + MSM_PIN_FUNCTION(blsp_i2c7), + MSM_PIN_FUNCTION(blsp_i2c8), + MSM_PIN_FUNCTION(blsp_spi1), + MSM_PIN_FUNCTION(blsp_spi2), + MSM_PIN_FUNCTION(blsp_spi3), + MSM_PIN_FUNCTION(blsp_spi4), + MSM_PIN_FUNCTION(blsp_spi5), + MSM_PIN_FUNCTION(blsp_spi6), + MSM_PIN_FUNCTION(blsp_spi7), + MSM_PIN_FUNCTION(blsp_spi8), + MSM_PIN_FUNCTION(blsp_uart1), + MSM_PIN_FUNCTION(blsp_uart2), + MSM_PIN_FUNCTION(blsp_uart3), + MSM_PIN_FUNCTION(blsp_uart4), + MSM_PIN_FUNCTION(blsp_uart5), + MSM_PIN_FUNCTION(blsp_uart6), + MSM_PIN_FUNCTION(blsp_uart7), + MSM_PIN_FUNCTION(blsp_uart8), + MSM_PIN_FUNCTION(cam0_ldo), + MSM_PIN_FUNCTION(cam1_rst), + MSM_PIN_FUNCTION(cam1_standby), + MSM_PIN_FUNCTION(cam2_rst), + MSM_PIN_FUNCTION(cam2_standby), + MSM_PIN_FUNCTION(cam_mclk), + MSM_PIN_FUNCTION(cci_async), + MSM_PIN_FUNCTION(cci_i2c), + MSM_PIN_FUNCTION(cci_timer0), + MSM_PIN_FUNCTION(cci_timer1), + MSM_PIN_FUNCTION(cdc_pdm0), + MSM_PIN_FUNCTION(codec_int1), + MSM_PIN_FUNCTION(codec_int2), + MSM_PIN_FUNCTION(codec_mad), + MSM_PIN_FUNCTION(coex_uart), + MSM_PIN_FUNCTION(cri_trng), + MSM_PIN_FUNCTION(cri_trng0), + MSM_PIN_FUNCTION(cri_trng1), + MSM_PIN_FUNCTION(dbg_out), + MSM_PIN_FUNCTION(dmic0_clk), + MSM_PIN_FUNCTION(dmic0_data), + MSM_PIN_FUNCTION(ebi_cdc), + MSM_PIN_FUNCTION(ebi_ch0), + MSM_PIN_FUNCTION(ext_lpass), + MSM_PIN_FUNCTION(forced_usb), + MSM_PIN_FUNCTION(fp_gpio), + MSM_PIN_FUNCTION(fp_int), + MSM_PIN_FUNCTION(gcc_gp1_clk_a), + MSM_PIN_FUNCTION(gcc_gp1_clk_b), + MSM_PIN_FUNCTION(gcc_gp2_clk_a), + MSM_PIN_FUNCTION(gcc_gp2_clk_b), + MSM_PIN_FUNCTION(gcc_gp3_clk_a), + MSM_PIN_FUNCTION(gcc_gp3_clk_b), + MSM_PIN_FUNCTION(gcc_plltest), + MSM_PIN_FUNCTION(gcc_tlmm), + MSM_PIN_FUNCTION(gpio), + MSM_PIN_FUNCTION(gsm0_tx), + MSM_PIN_FUNCTION(key_focus), + MSM_PIN_FUNCTION(key_snapshot), + MSM_PIN_FUNCTION(key_volp), + MSM_PIN_FUNCTION(ldo_en), + MSM_PIN_FUNCTION(ldo_update), + MSM_PIN_FUNCTION(lpass_slimbus), + MSM_PIN_FUNCTION(lpass_slimbus0), + MSM_PIN_FUNCTION(lpass_slimbus1), + MSM_PIN_FUNCTION(m_voc), + MSM_PIN_FUNCTION(mag_int), + MSM_PIN_FUNCTION(mdp_vsync), + MSM_PIN_FUNCTION(mipi_dsi0), + MSM_PIN_FUNCTION(modem_tsync), + MSM_PIN_FUNCTION(nav_pps), + MSM_PIN_FUNCTION(nav_pps_in_a), + MSM_PIN_FUNCTION(nav_pps_in_b), + MSM_PIN_FUNCTION(nav_tsync), + MSM_PIN_FUNCTION(nfc_pwr), + MSM_PIN_FUNCTION(ov_ldo), + MSM_PIN_FUNCTION(pa_indicator), + MSM_PIN_FUNCTION(pbs0), + MSM_PIN_FUNCTION(pbs1), + MSM_PIN_FUNCTION(pbs2), + MSM_PIN_FUNCTION(pri_mi2s), + MSM_PIN_FUNCTION(pri_mi2s_mclk_a), + MSM_PIN_FUNCTION(pri_mi2s_mclk_b), + MSM_PIN_FUNCTION(pri_mi2s_ws), + MSM_PIN_FUNCTION(prng_rosc), + MSM_PIN_FUNCTION(pwr_crypto_enabled_a), + MSM_PIN_FUNCTION(pwr_crypto_enabled_b), + MSM_PIN_FUNCTION(pwr_modem_enabled_a), + MSM_PIN_FUNCTION(pwr_modem_enabled_b), + MSM_PIN_FUNCTION(pwr_nav_enabled_a), + MSM_PIN_FUNCTION(pwr_nav_enabled_b), + MSM_PIN_FUNCTION(qdss_cti_trig_in_a0), + MSM_PIN_FUNCTION(qdss_cti_trig_in_a1), + MSM_PIN_FUNCTION(qdss_cti_trig_in_b0), + MSM_PIN_FUNCTION(qdss_cti_trig_in_b1), + MSM_PIN_FUNCTION(qdss_cti_trig_out_a0), + MSM_PIN_FUNCTION(qdss_cti_trig_out_a1), + MSM_PIN_FUNCTION(qdss_cti_trig_out_b0), + MSM_PIN_FUNCTION(qdss_cti_trig_out_b1), + MSM_PIN_FUNCTION(qdss_traceclk_a), + MSM_PIN_FUNCTION(qdss_traceclk_b), + MSM_PIN_FUNCTION(qdss_tracectl_a), + MSM_PIN_FUNCTION(qdss_tracectl_b), + MSM_PIN_FUNCTION(qdss_tracedata_a), + MSM_PIN_FUNCTION(qdss_tracedata_b), + MSM_PIN_FUNCTION(sd_write), + MSM_PIN_FUNCTION(sdcard_det), + MSM_PIN_FUNCTION(sec_mi2s), + MSM_PIN_FUNCTION(sec_mi2s_mclk_a), + MSM_PIN_FUNCTION(sec_mi2s_mclk_b), + MSM_PIN_FUNCTION(sensor_rst), + MSM_PIN_FUNCTION(smb_int), + MSM_PIN_FUNCTION(ssbi_wtr1), + MSM_PIN_FUNCTION(ts_resout), + MSM_PIN_FUNCTION(ts_sample), + MSM_PIN_FUNCTION(uim1_clk), + MSM_PIN_FUNCTION(uim1_data), + MSM_PIN_FUNCTION(uim1_present), + MSM_PIN_FUNCTION(uim1_reset), + MSM_PIN_FUNCTION(uim2_clk), + MSM_PIN_FUNCTION(uim2_data), + MSM_PIN_FUNCTION(uim2_present), + MSM_PIN_FUNCTION(uim2_reset), + MSM_PIN_FUNCTION(uim_batt), + MSM_PIN_FUNCTION(us_emitter), + MSM_PIN_FUNCTION(us_euro), + MSM_PIN_FUNCTION(wcss_bt), + MSM_PIN_FUNCTION(wcss_fm), + MSM_PIN_FUNCTION(wcss_wlan), + MSM_PIN_FUNCTION(wcss_wlan0), + MSM_PIN_FUNCTION(wcss_wlan1), + MSM_PIN_FUNCTION(wcss_wlan2), + MSM_PIN_FUNCTION(webcam_rst), + MSM_PIN_FUNCTION(webcam_standby), + MSM_PIN_FUNCTION(wsa_io), + MSM_PIN_FUNCTION(wsa_irq), +}; + +static const struct msm_pingroup msm8917_groups[] = { + PINGROUP(0, blsp_spi1, blsp_uart1, qdss_tracedata_b, _, _, _, _, + _, _), + PINGROUP(1, blsp_spi1, blsp_uart1, adsp_ext, _, _, _, _, _, + qdss_tracedata_b), + PINGROUP(2, blsp_spi1, blsp_uart1, blsp_i2c1, prng_rosc, _, _, _, + _, _), + PINGROUP(3, blsp_spi1, blsp_uart1, blsp_i2c1, _, _, _, _, _, _), + PINGROUP(4, blsp_spi2, blsp_uart2, ldo_update, _, + atest_combodac_to_gpio_native, _, _, _, _), + PINGROUP(5, blsp_spi2, blsp_uart2, ldo_en, _, _, _, _, _, _), + PINGROUP(6, blsp_spi2, blsp_uart2, blsp_i2c2, gcc_gp1_clk_b, + qdss_tracedata_b, _, _, _, _), + PINGROUP(7, blsp_spi2, blsp_uart2, blsp_i2c2, pbs2, _, + qdss_tracedata_b, _, atest_gpsadc_dtest0_native, _), + PINGROUP(8, blsp_spi3, blsp_uart3, pbs0, _, _, _, _, _, _), + PINGROUP(9, blsp_spi3, blsp_uart3, pbs1, pwr_modem_enabled_b, _, _, + _, _, _), + PINGROUP(10, blsp_spi3, blsp_uart3, blsp_i2c3, gcc_gp2_clk_b, _, _, + _, _, _), + PINGROUP(11, blsp_spi3, blsp_uart3, blsp_i2c3, gcc_gp3_clk_b, _, _, + _, _, _), + PINGROUP(12, blsp_spi4, blsp_uart4, sec_mi2s, pwr_nav_enabled_b, _, + _, _, _, _), + PINGROUP(13, blsp_spi4, blsp_uart4, sec_mi2s, pwr_crypto_enabled_b, _, + _, _, _, _), + PINGROUP(14, blsp_spi4, blsp_uart4, blsp_i2c4, _, _, _, _, _, _), + PINGROUP(15, blsp_spi4, blsp_uart4, blsp_i2c4, _, _, _, _, _, _), + PINGROUP(16, blsp_spi5, blsp_uart5, _, _, _, _, qdss_traceclk_a, + _, atest_bbrx1), + PINGROUP(17, blsp_spi5, blsp_uart5, m_voc, qdss_cti_trig_in_a0, _, + atest_bbrx0, _, _, _), + PINGROUP(18, blsp_spi5, blsp_uart5, blsp_i2c5, qdss_tracectl_a, _, + atest_gpsadc_dtest1_native, _, _, _), + PINGROUP(19, blsp_spi5, blsp_uart5, blsp_i2c5, qdss_tracedata_a, _, + _, _, _, _), + PINGROUP(20, blsp_spi6, blsp_uart6, _, _, _, _, _, _, + qdss_tracectl_b), + PINGROUP(21, blsp_spi6, blsp_uart6, m_voc, _, _, _, _, _, + qdss_cti_trig_in_b0), + PINGROUP(22, blsp_spi6, blsp_uart6, blsp_i2c6, qdss_traceclk_b, _, + atest_wlan0, _, _, _), + PINGROUP(23, blsp_spi6, blsp_uart6, blsp_i2c6, qdss_tracedata_b, _, + atest_wlan1, _, _, _), + PINGROUP(24, mdp_vsync, _, _, _, _, _, _, _, _), + PINGROUP(25, mdp_vsync, pri_mi2s_mclk_a, sec_mi2s_mclk_a, _, _, _, + _, _, _), + PINGROUP(26, cam_mclk, _, _, _, _, _, qdss_tracedata_a, _, _), + PINGROUP(27, cam_mclk, _, _, _, _, _, _, _, qdss_tracedata_a), + PINGROUP(28, cam_mclk, _, _, _, _, _, qdss_tracedata_a, _, + atest_combodac_to_gpio_native), + PINGROUP(29, cci_i2c, pwr_modem_enabled_a, _, _, _, _, _, + qdss_tracedata_a, _), + PINGROUP(30, cci_i2c, _, _, _, _, _, _, _, qdss_tracedata_a), + PINGROUP(31, cci_i2c, _, _, _, _, _, _, _, qdss_tracedata_a), + PINGROUP(32, cci_i2c, _, _, _, _, _, _, _, qdss_tracedata_a), + PINGROUP(33, cci_timer0, _, _, _, _, _, _, _, qdss_tracedata_a), + PINGROUP(34, cci_timer1, _, _, _, _, _, _, _, qdss_tracedata_a), + PINGROUP(35, pwr_nav_enabled_a, _, _, _, _, _, _, _, + qdss_tracedata_a), + PINGROUP(36, pwr_crypto_enabled_a, _, _, _, _, _, _, _, + qdss_tracedata_a), + PINGROUP(37, _, _, _, _, _, qdss_cti_trig_out_b1, _, _, _), + PINGROUP(38, _, qdss_tracedata_a, _, _, _, _, _, _, _), + PINGROUP(39, cci_async, _, _, _, _, _, qdss_tracedata_a, _, + atest_combodac_to_gpio_native), + PINGROUP(40, _, _, _, _, qdss_tracedata_a, _, + atest_combodac_to_gpio_native, _, _), + PINGROUP(41, sd_write, _, _, _, _, _, _, _, + atest_combodac_to_gpio_native), + PINGROUP(42, gcc_gp1_clk_a, qdss_tracedata_b, _, + atest_combodac_to_gpio_native, _, _, _, _, _), + PINGROUP(43, gcc_gp2_clk_a, qdss_tracedata_b, _, + atest_combodac_to_gpio_native, _, _, _, _, _), + PINGROUP(44, gcc_gp3_clk_a, qdss_tracedata_b, _, + atest_combodac_to_gpio_native, _, _, _, _, _), + PINGROUP(45, _, _, atest_combodac_to_gpio_native, _, _, _, _, _, + _), + PINGROUP(46, _, _, atest_combodac_to_gpio_native, _, _, _, _, _, + _), + PINGROUP(47, blsp6_spi, _, qdss_tracedata_b, _, + atest_combodac_to_gpio_native, _, _, _, _), + PINGROUP(48, _, qdss_cti_trig_in_b1, _, + atest_combodac_to_gpio_native, _, _, _, _, _), + PINGROUP(49, uim_batt, _, _, _, _, _, _, _, _), + PINGROUP(50, qdss_tracedata_a, _, _, _, _, _, _, _, _), + PINGROUP(51, uim1_data, _, _, _, _, _, _, _, _), + PINGROUP(52, uim1_clk, _, _, _, _, _, _, _, _), + PINGROUP(53, uim1_reset, _, _, _, _, _, _, _, _), + PINGROUP(54, uim1_present, _, _, _, _, _, _, _, _), + PINGROUP(55, uim2_data, _, _, _, _, _, _, _, _), + PINGROUP(56, uim2_clk, _, _, _, _, _, _, _, _), + PINGROUP(57, uim2_reset, _, _, _, _, _, _, _, _), + PINGROUP(58, uim2_present, _, _, _, _, _, _, _, _), + PINGROUP(59, _, _, _, _, _, _, _, _, _), + PINGROUP(60, _, _, _, _, _, _, _, _, _), + PINGROUP(61, _, _, _, _, _, _, _, _, _), + PINGROUP(62, _, _, _, _, _, _, _, _, _), + PINGROUP(63, atest_char3, dbg_out, bimc_dte0, _, _, _, _, _, _), + PINGROUP(64, _, _, _, _, _, _, _, _, _), + PINGROUP(65, bimc_dte0, _, _, _, _, _, _, _, _), + PINGROUP(66, sec_mi2s_mclk_b, pri_mi2s, _, qdss_tracedata_b, _, _, + _, _, _), + PINGROUP(67, atest_char1, ebi_cdc, _, atest_combodac_to_gpio_native, + _, _, _, _, _), + PINGROUP(68, atest_char0, _, _, _, _, _, _, _, _), + PINGROUP(69, audio_ref, cdc_pdm0, pri_mi2s_mclk_b, ebi_cdc, _, _, _, + _, _), + PINGROUP(70, lpass_slimbus, cdc_pdm0, _, _, _, _, _, _, _), + PINGROUP(71, lpass_slimbus0, cdc_pdm0, _, _, _, _, _, _, _), + PINGROUP(72, lpass_slimbus1, cdc_pdm0, _, _, _, _, _, _, _), + PINGROUP(73, cdc_pdm0, _, _, _, _, _, _, _, _), + PINGROUP(74, cdc_pdm0, _, _, _, _, _, _, _, _), + PINGROUP(75, wcss_bt, atest_char2, _, ebi_ch0, _, _, _, _, _), + PINGROUP(76, wcss_wlan2, _, _, _, _, _, _, _, _), + PINGROUP(77, wcss_wlan1, _, _, _, _, _, _, _, _), + PINGROUP(78, wcss_wlan0, _, _, _, _, _, _, _, _), + PINGROUP(79, wcss_wlan, _, _, _, _, _, _, _, _), + PINGROUP(80, wcss_wlan, _, _, _, _, _, _, _, _), + PINGROUP(81, wcss_fm, ext_lpass, _, _, _, _, _, _, _), + PINGROUP(82, wcss_fm, cri_trng, _, _, _, _, _, _, _), + PINGROUP(83, wcss_bt, cri_trng1, _, _, _, _, _, _, _), + PINGROUP(84, wcss_bt, cri_trng0, _, _, _, _, _, _, _), + PINGROUP(85, pri_mi2s, blsp_spi7, blsp_uart7, _, _, _, _, _, _), + PINGROUP(86, pri_mi2s, blsp_spi7, blsp_uart7, qdss_tracedata_b, _, _, + _, _, _), + PINGROUP(87, pri_mi2s_ws, blsp_spi7, blsp_uart7, blsp_i2c7, + qdss_tracedata_b, gcc_tlmm, _, _, _), + PINGROUP(88, pri_mi2s, blsp_spi7, blsp_uart7, blsp_i2c7, _, _, _, + _, _), + PINGROUP(89, dmic0_clk, _, _, _, _, _, _, _, _), + PINGROUP(90, dmic0_data, _, _, _, _, _, _, _, _), + PINGROUP(91, _, _, _, _, _, qdss_cti_trig_in_a1, _, _, _), + PINGROUP(92, _, _, _, _, _, qdss_tracedata_b, _, _, _), + PINGROUP(93, _, _, _, _, _, _, _, _, _), + PINGROUP(94, wsa_io, sec_mi2s, pri_mi2s, _, _, _, _, _, _), + PINGROUP(95, wsa_io, sec_mi2s, pri_mi2s, _, _, _, _, _, _), + PINGROUP(96, blsp_spi8, blsp_uart8, _, _, _, _, _, _, _), + PINGROUP(97, blsp_spi8, blsp_uart8, _, _, _, _, _, _, _), + PINGROUP(98, blsp_spi8, blsp_uart8, blsp_i2c8, gcc_plltest, _, _, _, + _, _), + PINGROUP(99, blsp_spi8, blsp_uart8, blsp_i2c8, gcc_plltest, _, _, _, + _, _), + PINGROUP(100, _, _, _, _, _, _, _, _, _), + PINGROUP(101, _, _, _, _, _, _, _, _, _), + PINGROUP(102, _, _, _, _, _, _, _, _, _), + PINGROUP(103, _, _, _, _, _, _, _, _, _), + PINGROUP(104, _, _, _, _, _, _, _, _, _), + PINGROUP(105, _, _, _, _, _, _, _, _, _), + PINGROUP(106, _, _, _, _, _, _, _, _, _), + PINGROUP(107, _, _, _, _, _, _, _, _, _), + PINGROUP(108, _, _, _, _, _, _, _, _, _), + PINGROUP(109, _, _, _, _, _, _, _, _, _), + PINGROUP(110, _, _, _, _, _, _, _, _, _), + PINGROUP(111, _, _, _, _, _, _, _, _, _), + PINGROUP(112, _, _, _, _, _, _, _, _, _), + PINGROUP(113, _, _, _, _, _, _, _, _, _), + PINGROUP(114, _, _, _, _, _, _, _, _, _), + PINGROUP(115, _, _, nav_pps_in_a, _, atest_combodac_to_gpio_native, + _, _, _, _), + PINGROUP(116, _, pa_indicator, _, _, _, _, _, _, _), + PINGROUP(117, _, modem_tsync, nav_tsync, nav_pps_in_b, nav_pps, _, + _, _, _), + PINGROUP(118, _, ebi_cdc, _, _, _, _, _, _, _), + PINGROUP(119, gsm0_tx, _, ebi_cdc, _, _, _, _, _, _), + PINGROUP(120, _, atest_char, ebi_cdc, _, atest_tsens, _, _, _, _), + PINGROUP(121, _, _, _, bimc_dte1, _, _, _, _, _), + PINGROUP(122, _, ssbi_wtr1, _, _, bimc_dte1, _, _, _, _), + PINGROUP(123, _, ssbi_wtr1, ebi_cdc, _, _, _, _, _, _), + PINGROUP(124, coex_uart, _, _, _, _, _, _, _, _), + PINGROUP(125, _, _, _, _, _, _, _, _, _), + PINGROUP(126, _, _, _, _, _, _, _, _, _), + PINGROUP(127, coex_uart, _, _, _, _, _, _, _, _), + PINGROUP(128, _, _, _, _, _, _, _, _, _), + PINGROUP(129, _, _, _, _, _, _, _, _, _), + PINGROUP(130, blsp8_spi, _, _, _, _, _, _, _, _), + PINGROUP(131, _, _, _, _, _, _, _, _, _), + PINGROUP(132, qdss_cti_trig_out_a0, _, _, _, _, _, _, _, _), + PINGROUP(133, qdss_cti_trig_out_a1, _, _, _, _, _, _, _, _), + SDC_PINGROUP(sdc1_clk, 0x10a000, 13, 6), + SDC_PINGROUP(sdc1_cmd, 0x10a000, 11, 3), + SDC_PINGROUP(sdc1_data, 0x10a000, 9, 0), + SDC_PINGROUP(sdc1_rclk, 0x10a000, 15, 0), + SDC_PINGROUP(sdc2_clk, 0x109000, 14, 6), + SDC_PINGROUP(sdc2_cmd, 0x109000, 11, 3), + SDC_PINGROUP(sdc2_data, 0x109000, 9, 0), + SDC_PINGROUP(qdsd_clk, 0x19c000, 3, 0), + SDC_PINGROUP(qdsd_cmd, 0x19c000, 8, 5), + SDC_PINGROUP(qdsd_data0, 0x19c000, 13, 10), + SDC_PINGROUP(qdsd_data1, 0x19c000, 18, 15), + SDC_PINGROUP(qdsd_data2, 0x19c000, 23, 20), + SDC_PINGROUP(qdsd_data3, 0x19c000, 28, 25), +}; + +static const struct msm_pinctrl_soc_data msm8917_pinctrl = { + .pins = msm8917_pins, + .npins = ARRAY_SIZE(msm8917_pins), + .functions = msm8917_functions, + .nfunctions = ARRAY_SIZE(msm8917_functions), + .groups = msm8917_groups, + .ngroups = ARRAY_SIZE(msm8917_groups), + .ngpios = 134, +}; + +static int msm8917_pinctrl_probe(struct platform_device *pdev) +{ + return msm_pinctrl_probe(pdev, &msm8917_pinctrl); +} + +static const struct of_device_id msm8917_pinctrl_of_match[] = { + { .compatible = "qcom,msm8917-pinctrl", }, + { }, +}; +MODULE_DEVICE_TABLE(of, msm8917_pinctrl_of_match); + +static struct platform_driver msm8917_pinctrl_driver = { + .driver = { + .name = "msm8917-pinctrl", + .of_match_table = msm8917_pinctrl_of_match, + }, + .probe = msm8917_pinctrl_probe, + .remove = msm_pinctrl_remove, +}; + +static int __init msm8917_pinctrl_init(void) +{ + return platform_driver_register(&msm8917_pinctrl_driver); +} +arch_initcall(msm8917_pinctrl_init); + +static void __exit msm8917_pinctrl_exit(void) +{ + platform_driver_unregister(&msm8917_pinctrl_driver); +} +module_exit(msm8917_pinctrl_exit); + +MODULE_DESCRIPTION("Qualcomm msm8917 pinctrl driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index 0c806b8128b6..c8ce61066070 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -702,7 +703,7 @@ static void pmic_gpio_config_dbg_show(struct pinctrl_dev *pctldev, else seq_printf(s, " %-4s", pad->output_enabled ? "out" : "in"); - seq_printf(s, " %-4s", pad->out_value ? "high" : "low"); + seq_printf(s, " %-4s", str_high_low(pad->out_value)); seq_printf(s, " %-7s", pmic_gpio_functions[function]); seq_printf(s, " vin-%d", pad->power_source); seq_printf(s, " %-27s", biases[pad->pullup]); diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c index 84de584cf7eb..7b28c5fb2402 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -544,7 +545,7 @@ static void pmic_mpp_config_dbg_show(struct pinctrl_dev *pctldev, seq_printf(s, " %d", pad->aout_level); if (pad->has_pullup) seq_printf(s, " %-8s", biases[pad->pullup]); - seq_printf(s, " %-4s", pad->out_value ? "high" : "low"); + seq_printf(s, " %-4s", str_high_low(pad->out_value)); if (pad->dtest) seq_printf(s, " dtest%d", pad->dtest); if (pad->paired) diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c index 2225dc49d477..82679417e25f 100644 --- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -569,7 +570,7 @@ static void pm8xxx_gpio_dbg_show_one(struct seq_file *s, seq_printf(s, " VIN%d", pin->power_source); seq_printf(s, " %-27s", biases[pin->bias]); seq_printf(s, " %-10s", buffer_types[pin->open_drain]); - seq_printf(s, " %-4s", pin->output_value ? "high" : "low"); + seq_printf(s, " %-4s", str_high_low(pin->output_value)); seq_printf(s, " %-7s", strengths[pin->output_strength]); if (pin->inverted) seq_puts(s, " inverted"); diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c index 9b1039c08aa6..4841bbfe4864 100644 --- a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c +++ b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -576,8 +577,7 @@ static void pm8xxx_mpp_dbg_show_one(struct seq_file *s, seq_puts(s, "out "); if (!pin->paired) { - seq_puts(s, pin->output_value ? - "high" : "low"); + seq_puts(s, str_high_low(pin->output_value)); } else { seq_puts(s, pin->output_value ? "inverted" : "follow"); @@ -589,8 +589,7 @@ static void pm8xxx_mpp_dbg_show_one(struct seq_file *s, if (pin->output) { seq_printf(s, "out %s ", aout_lvls[pin->aout_level]); if (!pin->paired) { - seq_puts(s, pin->output_value ? - "high" : "low"); + seq_puts(s, str_high_low(pin->output_value)); } else { seq_puts(s, pin->output_value ? "inverted" : "follow"); @@ -605,8 +604,7 @@ static void pm8xxx_mpp_dbg_show_one(struct seq_file *s, seq_printf(s, "dtest%d", pin->dtest); } else { if (!pin->paired) { - seq_puts(s, pin->output_value ? - "high" : "low"); + seq_puts(s, str_high_low(pin->output_value)); } else { seq_puts(s, pin->output_value ? "inverted" : "follow"); diff --git a/drivers/pinctrl/renesas/Kconfig b/drivers/pinctrl/renesas/Kconfig index 7f3f41c7fe54..3c18d908b21e 100644 --- a/drivers/pinctrl/renesas/Kconfig +++ b/drivers/pinctrl/renesas/Kconfig @@ -41,6 +41,7 @@ config PINCTRL_RENESAS select PINCTRL_PFC_R8A779H0 if ARCH_R8A779H0 select PINCTRL_RZG2L if ARCH_RZG2L select PINCTRL_RZV2M if ARCH_R9A09G011 + select PINCTRL_RZG2L if ARCH_R9A09G047 select PINCTRL_RZG2L if ARCH_R9A09G057 select PINCTRL_PFC_SH7203 if CPU_SUBTYPE_SH7203 select PINCTRL_PFC_SH7264 if CPU_SUBTYPE_SH7264 diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index 1df9cec2873f..ce4a07a3df49 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -26,6 +26,8 @@ #include #include +#include +#include #include #include "../core.h" @@ -157,7 +159,7 @@ #define PWPR_REGWE_B BIT(5) /* OEN Register Write Enable, known only in RZ/V2H(P) */ #define PM_MASK 0x03 -#define PFC_MASK 0x07 +#define PFC_MASK 0x0f #define IEN_MASK 0x01 #define IOLH_MASK 0x03 #define SR_MASK 0x01 @@ -381,13 +383,51 @@ static u64 rzg2l_pinctrl_get_variable_pin_cfg(struct rzg2l_pinctrl *pctrl, return 0; } +static const u64 r9a09g047_variable_pin_cfg[] = { + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PA, 0, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PA, 1, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PA, 2, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PA, 3, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PA, 4, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PA, 5, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PA, 6, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PA, 7, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PD, 0, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PD, 1, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PD, 2, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PD, 3, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PD, 4, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PD, 5, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PD, 6, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PD, 7, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PG, 0, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PG, 1, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PG, 2, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PG, 3, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PG, 4, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PG, 5, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PG, 6, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PG, 7, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PH, 0, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PH, 1, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PH, 2, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PH, 3, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PH, 4, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PH, 5, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PJ, 0, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PJ, 1, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PJ, 2, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PJ, 3, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZG3E_PJ, 4, RZV2H_MPXED_PIN_FUNCS), +}; + static const u64 r9a09g057_variable_pin_cfg[] = { - RZG2L_VARIABLE_PIN_CFG_PACK(11, 0, RZV2H_MPXED_PIN_FUNCS), - RZG2L_VARIABLE_PIN_CFG_PACK(11, 1, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), - RZG2L_VARIABLE_PIN_CFG_PACK(11, 2, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), - RZG2L_VARIABLE_PIN_CFG_PACK(11, 3, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), - RZG2L_VARIABLE_PIN_CFG_PACK(11, 4, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), - RZG2L_VARIABLE_PIN_CFG_PACK(11, 5, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZV2H_PB, 0, RZV2H_MPXED_PIN_FUNCS), + RZG2L_VARIABLE_PIN_CFG_PACK(RZV2H_PB, 1, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZV2H_PB, 2, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZV2H_PB, 3, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZV2H_PB, 4, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), + RZG2L_VARIABLE_PIN_CFG_PACK(RZV2H_PB, 5, RZV2H_MPXED_PIN_FUNCS | PIN_CFG_IEN), }; #ifdef CONFIG_RISCV @@ -1962,6 +2002,73 @@ static const u64 r9a08g045_gpio_configs[] = { RZG2L_GPIO_PORT_PACK(6, 0x2a, RZG3S_MPXED_PIN_FUNCS(A)), /* P18 */ }; +static const char * const rzg3e_gpio_names[] = { + "P00", "P01", "P02", "P03", "P04", "P05", "P06", "P07", + "P10", "P11", "P12", "P13", "P14", "P15", "P16", "P17", + "P20", "P21", "P22", "P23", "P24", "P25", "P26", "P27", + "P30", "P31", "P32", "P33", "P34", "P35", "P36", "P37", + "P40", "P41", "P42", "P43", "P44", "P45", "P46", "P47", + "P50", "P51", "P52", "P53", "P54", "P55", "P56", "P57", + "P60", "P61", "P62", "P63", "P64", "P65", "P66", "P67", + "P70", "P71", "P72", "P73", "P74", "P75", "P76", "P77", + "P80", "P81", "P82", "P83", "P84", "P85", "P86", "P87", + "", "", "", "", "", "", "", "", + "PA0", "PA1", "PA2", "PA3", "PA4", "PA5", "PA6", "PA7", + "PB0", "PB1", "PB2", "PB3", "PB4", "PB5", "PB6", "PB7", + "PC0", "PC1", "PC2", "PC3", "PC4", "PC5", "PC6", "PC7", + "PD0", "PD1", "PD2", "PD3", "PD4", "PD5", "PD6", "PD7", + "PE0", "PE1", "PE2", "PE3", "PE4", "PE5", "PE6", "PE7", + "PF0", "PF1", "PF2", "PF3", "PF4", "PF5", "PF6", "PF7", + "PG0", "PG1", "PG2", "PG3", "PG4", "PG5", "PG6", "PG7", + "PH0", "PH1", "PH2", "PH3", "PH4", "PH5", "PH6", "PH7", + "", "", "", "", "", "", "", "", + "PJ0", "PJ1", "PJ2", "PJ3", "PJ4", "PJ5", "PJ6", "PJ7", + "PK0", "PK1", "PK2", "PK3", "PK4", "PK5", "PK6", "PK7", + "PL0", "PL1", "PL2", "PL3", "PL4", "PL5", "PL6", "PL7", + "PM0", "PM1", "PM2", "PM3", "PM4", "PM5", "PM6", "PM7", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "PS0", "PS1", "PS2", "PS3", "PS4", "PS5", "PS6", "PS7", +}; + +static const u64 r9a09g047_gpio_configs[] = { + RZG2L_GPIO_PORT_PACK(8, 0x20, RZV2H_MPXED_PIN_FUNCS), /* P0 */ + RZG2L_GPIO_PORT_PACK(8, 0x21, RZV2H_MPXED_PIN_FUNCS | + PIN_CFG_ELC), /* P1 */ + RZG2L_GPIO_PORT_PACK(2, 0x22, RZG2L_MPXED_COMMON_PIN_FUNCS(RZV2H) | + PIN_CFG_NOD), /* P2 */ + RZG2L_GPIO_PORT_PACK(8, 0x23, RZV2H_MPXED_PIN_FUNCS), /* P3 */ + RZG2L_GPIO_PORT_PACK(6, 0x24, RZV2H_MPXED_PIN_FUNCS), /* P4 */ + RZG2L_GPIO_PORT_PACK(7, 0x25, RZV2H_MPXED_PIN_FUNCS), /* P5 */ + RZG2L_GPIO_PORT_PACK(7, 0x26, RZV2H_MPXED_PIN_FUNCS), /* P6 */ + RZG2L_GPIO_PORT_PACK(8, 0x27, RZV2H_MPXED_PIN_FUNCS | + PIN_CFG_ELC), /* P7 */ + RZG2L_GPIO_PORT_PACK(6, 0x28, RZV2H_MPXED_PIN_FUNCS), /* P8 */ + 0x0, + RZG2L_GPIO_PORT_PACK_VARIABLE(8, 0x2a), /* PA */ + RZG2L_GPIO_PORT_PACK(8, 0x2b, RZV2H_MPXED_PIN_FUNCS), /* PB */ + RZG2L_GPIO_PORT_PACK(3, 0x2c, RZV2H_MPXED_PIN_FUNCS), /* PC */ + RZG2L_GPIO_PORT_PACK_VARIABLE(8, 0x2d), /* PD */ + RZG2L_GPIO_PORT_PACK(8, 0x2e, RZV2H_MPXED_PIN_FUNCS), /* PE */ + RZG2L_GPIO_PORT_PACK(3, 0x2f, RZV2H_MPXED_PIN_FUNCS), /* PF */ + RZG2L_GPIO_PORT_PACK_VARIABLE(8, 0x30), /* PG */ + RZG2L_GPIO_PORT_PACK_VARIABLE(6, 0x31), /* PH */ + 0x0, + RZG2L_GPIO_PORT_PACK_VARIABLE(5, 0x33), /* PJ */ + RZG2L_GPIO_PORT_PACK(4, 0x34, RZV2H_MPXED_PIN_FUNCS), /* PK */ + RZG2L_GPIO_PORT_PACK(8, 0x35, RZV2H_MPXED_PIN_FUNCS), /* PL */ + RZG2L_GPIO_PORT_PACK(8, 0x36, RZV2H_MPXED_PIN_FUNCS), /* PM */ + 0x0, + 0x0, + 0x0, + 0x0, + 0x0, + RZG2L_GPIO_PORT_PACK(4, 0x3c, RZV2H_MPXED_PIN_FUNCS), /* PS */ +}; + static const char * const rzv2h_gpio_names[] = { "P00", "P01", "P02", "P03", "P04", "P05", "P06", "P07", "P10", "P11", "P12", "P13", "P14", "P15", "P16", "P17", @@ -2085,6 +2192,8 @@ static const struct rzg2l_dedicated_configs rzg3s_dedicated_pins[] = { { "TMS/SWDIO", RZG2L_SINGLE_PIN_PACK(0x1, 0, (PIN_CFG_IOLH_A | PIN_CFG_IEN | PIN_CFG_SOFT_PS)) }, { "TDO", RZG2L_SINGLE_PIN_PACK(0x1, 1, (PIN_CFG_IOLH_A | PIN_CFG_SOFT_PS)) }, + { "AUDIO_CLK1", RZG2L_SINGLE_PIN_PACK(0x2, 0, PIN_CFG_IEN) }, + { "AUDIO_CLK2", RZG2L_SINGLE_PIN_PACK(0x2, 1, PIN_CFG_IEN) }, { "WDTOVF_PERROUT#", RZG2L_SINGLE_PIN_PACK(0x6, 0, PIN_CFG_IOLH_A | PIN_CFG_SOFT_PS) }, { "SD0_CLK", RZG2L_SINGLE_PIN_PACK(0x10, 0, (PIN_CFG_IOLH_B | PIN_CFG_IO_VMC_SD0)) }, { "SD0_CMD", RZG2L_SINGLE_PIN_PACK(0x10, 1, (PIN_CFG_IOLH_B | PIN_CFG_IEN | @@ -2250,6 +2359,43 @@ static struct rzg2l_dedicated_configs rzv2h_dedicated_pins[] = { { "ET1_RXD3", RZG2L_SINGLE_PIN_PACK(0x14, 7, (PIN_CFG_PUPD)) }, }; +static struct rzg2l_dedicated_configs rzg3e_dedicated_pins[] = { + { "WDTUDFCA", RZG2L_SINGLE_PIN_PACK(0x5, 0, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_PUPD | PIN_CFG_NOD)) }, + { "WDTUDFCM", RZG2L_SINGLE_PIN_PACK(0x5, 1, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_PUPD | PIN_CFG_NOD)) }, + { "SCIF_RXD", RZG2L_SINGLE_PIN_PACK(0x6, 0, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_PUPD)) }, + { "SCIF_TXD", RZG2L_SINGLE_PIN_PACK(0x6, 1, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_PUPD)) }, + { "SD0CLK", RZG2L_SINGLE_PIN_PACK(0x9, 0, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR)) }, + { "SD0CMD", RZG2L_SINGLE_PIN_PACK(0x9, 1, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_IEN | PIN_CFG_PUPD)) }, + { "SD0RSTN", RZG2L_SINGLE_PIN_PACK(0x9, 2, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR)) }, + { "SD0PWEN", RZG2L_SINGLE_PIN_PACK(0x9, 3, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR)) }, + { "SD0IOVS", RZG2L_SINGLE_PIN_PACK(0x9, 4, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR)) }, + { "SD0DAT0", RZG2L_SINGLE_PIN_PACK(0xa, 0, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_IEN | PIN_CFG_PUPD)) }, + { "SD0DAT1", RZG2L_SINGLE_PIN_PACK(0xa, 1, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_IEN | PIN_CFG_PUPD)) }, + { "SD0DAT2", RZG2L_SINGLE_PIN_PACK(0xa, 2, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_IEN | PIN_CFG_PUPD)) }, + { "SD0DAT3", RZG2L_SINGLE_PIN_PACK(0xa, 3, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_IEN | PIN_CFG_PUPD)) }, + { "SD0DAT4", RZG2L_SINGLE_PIN_PACK(0xa, 4, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_IEN | PIN_CFG_PUPD)) }, + { "SD0DAT5", RZG2L_SINGLE_PIN_PACK(0xa, 5, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_IEN | PIN_CFG_PUPD)) }, + { "SD0DAT6", RZG2L_SINGLE_PIN_PACK(0xa, 6, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_IEN | PIN_CFG_PUPD)) }, + { "SD0DAT7", RZG2L_SINGLE_PIN_PACK(0xa, 7, + (PIN_CFG_IOLH_RZV2H | PIN_CFG_SR | PIN_CFG_IEN | PIN_CFG_PUPD)) }, +}; + static int rzg2l_gpio_get_gpioint(unsigned int virq, struct rzg2l_pinctrl *pctrl) { const struct pinctrl_pin_desc *pin_desc = &pctrl->desc.pins[virq]; @@ -2760,6 +2906,9 @@ static int rzg2l_pinctrl_probe(struct platform_device *pdev) BUILD_BUG_ON(ARRAY_SIZE(r9a08g045_gpio_configs) * RZG2L_PINS_PER_PORT > ARRAY_SIZE(rzg2l_gpio_names)); + BUILD_BUG_ON(ARRAY_SIZE(r9a09g047_gpio_configs) * RZG2L_PINS_PER_PORT > + ARRAY_SIZE(rzg3e_gpio_names)); + BUILD_BUG_ON(ARRAY_SIZE(r9a09g057_gpio_configs) * RZG2L_PINS_PER_PORT > ARRAY_SIZE(rzv2h_gpio_names)); @@ -3158,6 +3307,29 @@ static struct rzg2l_pinctrl_data r9a08g045_data = { .bias_param_to_hw = &rzg2l_bias_param_to_hw, }; +static struct rzg2l_pinctrl_data r9a09g047_data = { + .port_pins = rzg3e_gpio_names, + .port_pin_configs = r9a09g047_gpio_configs, + .n_ports = ARRAY_SIZE(r9a09g047_gpio_configs), + .dedicated_pins = rzg3e_dedicated_pins, + .n_port_pins = ARRAY_SIZE(r9a09g047_gpio_configs) * RZG2L_PINS_PER_PORT, + .n_dedicated_pins = ARRAY_SIZE(rzg3e_dedicated_pins), + .hwcfg = &rzv2h_hwcfg, + .variable_pin_cfg = r9a09g047_variable_pin_cfg, + .n_variable_pin_cfg = ARRAY_SIZE(r9a09g047_variable_pin_cfg), + .num_custom_params = ARRAY_SIZE(renesas_rzv2h_custom_bindings), + .custom_params = renesas_rzv2h_custom_bindings, +#ifdef CONFIG_DEBUG_FS + .custom_conf_items = renesas_rzv2h_conf_items, +#endif + .pwpr_pfc_lock_unlock = &rzv2h_pwpr_pfc_lock_unlock, + .pmc_writeb = &rzv2h_pmc_writeb, + .oen_read = &rzv2h_oen_read, + .oen_write = &rzv2h_oen_write, + .hw_to_bias_param = &rzv2h_hw_to_bias_param, + .bias_param_to_hw = &rzv2h_bias_param_to_hw, +}; + static struct rzg2l_pinctrl_data r9a09g057_data = { .port_pins = rzv2h_gpio_names, .port_pin_configs = r9a09g057_gpio_configs, @@ -3194,6 +3366,10 @@ static const struct of_device_id rzg2l_pinctrl_of_table[] = { .compatible = "renesas,r9a08g045-pinctrl", .data = &r9a08g045_data, }, + { + .compatible = "renesas,r9a09g047-pinctrl", + .data = &r9a09g047_data, + }, { .compatible = "renesas,r9a09g057-pinctrl", .data = &r9a09g057_data, diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c index b79c211c0374..42093bae8bb7 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -442,7 +443,7 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on) struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd); unsigned long bit = 1UL << (2 * bank->eint_offset + irqd->hwirq); - pr_info("wake %s for irq %u (%s-%lu)\n", on ? "enabled" : "disabled", + pr_info("wake %s for irq %u (%s-%lu)\n", str_enabled_disabled(on), irqd->irq, bank->name, irqd->hwirq); if (!on) @@ -636,7 +637,7 @@ static void exynos_irq_demux_eint16_31(struct irq_desc *desc) if (clk_enable(b->drvdata->pclk)) { dev_err(b->gpio_chip.parent, "unable to enable clock for pending IRQs\n"); - return; + goto out; } } @@ -652,6 +653,7 @@ static void exynos_irq_demux_eint16_31(struct irq_desc *desc) if (eintd->nr_banks) clk_disable(eintd->banks[0]->drvdata->pclk); +out: chained_irq_exit(chip, desc); } diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c index bbedd980ec67..cfced7afd4ca 100644 --- a/drivers/pinctrl/samsung/pinctrl-samsung.c +++ b/drivers/pinctrl/samsung/pinctrl-samsung.c @@ -1172,7 +1172,7 @@ static void samsung_banks_node_get(struct device *dev, struct samsung_pinctrl_dr else dev_warn(dev, "Missing node for bank %s - invalid DTB\n", bank->name); - /* child reference dropped in samsung_drop_banks_of_node() */ + /* child reference dropped in samsung_banks_node_put() */ } } @@ -1272,7 +1272,7 @@ static int samsung_pinctrl_probe(struct platform_device *pdev) ret = platform_get_irq_optional(pdev, 0); if (ret < 0 && ret != -ENXIO) - return ret; + goto err_put_banks; if (ret > 0) drvdata->irq = ret; diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index 5b7fa77c1184..cc0b4d1d7cff 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -86,7 +87,6 @@ struct stm32_pinctrl_group { struct stm32_gpio_bank { void __iomem *base; - struct clk *clk; struct reset_control *rstc; spinlock_t lock; struct gpio_chip gpio_chip; @@ -108,6 +108,7 @@ struct stm32_pinctrl { unsigned ngroups; const char **grp_names; struct stm32_gpio_bank *banks; + struct clk_bulk_data *clks; unsigned nbanks; const struct stm32_pinctrl_match_data *match_data; struct irq_domain *domain; @@ -1217,7 +1218,7 @@ static void stm32_pconf_dbg_show(struct pinctrl_dev *pctldev, case 0: val = stm32_pconf_get(bank, offset, true); seq_printf(s, "- %s - %s", - val ? "high" : "low", + str_high_low(val), biasing[bias]); break; @@ -1227,7 +1228,7 @@ static void stm32_pconf_dbg_show(struct pinctrl_dev *pctldev, speed = stm32_pconf_get_speed(bank, offset); val = stm32_pconf_get(bank, offset, false); seq_printf(s, "- %s - %s - %s - %s %s", - val ? "high" : "low", + str_high_low(val), drive ? "open drain" : "push pull", biasing[bias], speeds[speed], "speed"); @@ -1308,12 +1309,6 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode if (IS_ERR(bank->base)) return PTR_ERR(bank->base); - err = clk_prepare_enable(bank->clk); - if (err) { - dev_err(dev, "failed to prepare_enable clk (%d)\n", err); - return err; - } - bank->gpio_chip = stm32_gpio_template; fwnode_property_read_string(fwnode, "st,bank-name", &bank->gpio_chip.label); @@ -1360,26 +1355,20 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode bank->fwnode, &stm32_gpio_domain_ops, bank); - if (!bank->domain) { - err = -ENODEV; - goto err_clk; - } + if (!bank->domain) + return -ENODEV; } names = devm_kcalloc(dev, npins, sizeof(char *), GFP_KERNEL); - if (!names) { - err = -ENOMEM; - goto err_clk; - } + if (!names) + return -ENOMEM; for (i = 0; i < npins; i++) { stm32_pin = stm32_pctrl_get_desc_pin_from_gpio(pctl, bank, i); if (stm32_pin && stm32_pin->pin.name) { names[i] = devm_kasprintf(dev, GFP_KERNEL, "%s", stm32_pin->pin.name); - if (!names[i]) { - err = -ENOMEM; - goto err_clk; - } + if (!names[i]) + return -ENOMEM; } else { names[i] = NULL; } @@ -1390,15 +1379,11 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode err = gpiochip_add_data(&bank->gpio_chip, bank); if (err) { dev_err(dev, "Failed to add gpiochip(%d)!\n", bank_nr); - goto err_clk; + return err; } dev_info(dev, "%s bank added\n", bank->gpio_chip.label); return 0; - -err_clk: - clk_disable_unprepare(bank->clk); - return err; } static struct irq_domain *stm32_pctrl_get_irq_domain(struct platform_device *pdev) @@ -1621,6 +1606,11 @@ int stm32_pctl_probe(struct platform_device *pdev) if (!pctl->banks) return -ENOMEM; + pctl->clks = devm_kcalloc(dev, banks, sizeof(*pctl->clks), + GFP_KERNEL); + if (!pctl->clks) + return -ENOMEM; + i = 0; for_each_gpiochip_node(dev, child) { struct stm32_gpio_bank *bank = &pctl->banks[i]; @@ -1632,24 +1622,27 @@ int stm32_pctl_probe(struct platform_device *pdev) return -EPROBE_DEFER; } - bank->clk = of_clk_get_by_name(np, NULL); - if (IS_ERR(bank->clk)) { + pctl->clks[i].clk = of_clk_get_by_name(np, NULL); + if (IS_ERR(pctl->clks[i].clk)) { fwnode_handle_put(child); - return dev_err_probe(dev, PTR_ERR(bank->clk), + return dev_err_probe(dev, PTR_ERR(pctl->clks[i].clk), "failed to get clk\n"); } + pctl->clks[i].id = "pctl"; i++; } + ret = clk_bulk_prepare_enable(banks, pctl->clks); + if (ret) { + dev_err(dev, "failed to prepare_enable clk (%d)\n", ret); + return ret; + } + for_each_gpiochip_node(dev, child) { ret = stm32_gpiolib_register_bank(pctl, child); if (ret) { fwnode_handle_put(child); - - for (i = 0; i < pctl->nbanks; i++) - clk_disable_unprepare(pctl->banks[i].clk); - - return ret; + goto err_register; } pctl->nbanks++; @@ -1658,6 +1651,15 @@ int stm32_pctl_probe(struct platform_device *pdev) dev_info(dev, "Pinctrl STM32 initialized\n"); return 0; +err_register: + for (i = 0; i < pctl->nbanks; i++) { + struct stm32_gpio_bank *bank = &pctl->banks[i]; + + gpiochip_remove(&bank->gpio_chip); + } + + clk_bulk_disable_unprepare(banks, pctl->clks); + return ret; } static int __maybe_unused stm32_pinctrl_restore_gpio_regs( @@ -1726,10 +1728,8 @@ static int __maybe_unused stm32_pinctrl_restore_gpio_regs( int __maybe_unused stm32_pinctrl_suspend(struct device *dev) { struct stm32_pinctrl *pctl = dev_get_drvdata(dev); - int i; - for (i = 0; i < pctl->nbanks; i++) - clk_disable(pctl->banks[i].clk); + clk_bulk_disable(pctl->nbanks, pctl->clks); return 0; } @@ -1738,10 +1738,11 @@ int __maybe_unused stm32_pinctrl_resume(struct device *dev) { struct stm32_pinctrl *pctl = dev_get_drvdata(dev); struct stm32_pinctrl_group *g = pctl->groups; - int i; + int i, ret; - for (i = 0; i < pctl->nbanks; i++) - clk_enable(pctl->banks[i].clk); + ret = clk_bulk_enable(pctl->nbanks, pctl->clks); + if (ret) + return ret; for (i = 0; i < pctl->ngroups; i++, g++) stm32_pinctrl_restore_gpio_regs(pctl, g->pin); diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-a100.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-a100.c index df90c75fb3c5..b97de80ae2f3 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun50i-a100.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-a100.c @@ -256,72 +256,84 @@ static const struct sunxi_desc_pin a100_pins[] = { SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D12 */ + SUNXI_FUNCTION(0x3, "lvds0"), /* D3P */ SUNXI_FUNCTION(0x4, "dsi0"), /* DP3 */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 8)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 9), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D13 */ + SUNXI_FUNCTION(0x3, "lvds0"), /* D3N */ SUNXI_FUNCTION(0x4, "dsi0"), /* DM3 */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 9)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 10), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D14 */ + SUNXI_FUNCTION(0x3, "lvds1"), /* D0P */ SUNXI_FUNCTION(0x4, "spi1"), /* CS */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 10)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 11), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D15 */ + SUNXI_FUNCTION(0x3, "lvds1"), /* D0N */ SUNXI_FUNCTION(0x4, "spi1"), /* CLK */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 11)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 12), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D18 */ + SUNXI_FUNCTION(0x3, "lvds1"), /* D1P */ SUNXI_FUNCTION(0x4, "spi1"), /* MOSI */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 12)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 13), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D19 */ + SUNXI_FUNCTION(0x3, "lvds1"), /* D1N */ SUNXI_FUNCTION(0x4, "spi1"), /* MISO */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 13)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 14), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D20 */ + SUNXI_FUNCTION(0x3, "lvds1"), /* D2P */ SUNXI_FUNCTION(0x4, "uart3"), /* TX */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 14)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 15), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D21 */ + SUNXI_FUNCTION(0x3, "lvds1"), /* D2N */ SUNXI_FUNCTION(0x4, "uart3"), /* RX */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 15)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 16), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D22 */ + SUNXI_FUNCTION(0x3, "lvds1"), /* CKP */ SUNXI_FUNCTION(0x4, "uart3"), /* RTS */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 16)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 17), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* D23 */ + SUNXI_FUNCTION(0x3, "lvds1"), /* CKN */ SUNXI_FUNCTION(0x4, "uart3"), /* CTS */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 17)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 18), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* CLK */ + SUNXI_FUNCTION(0x3, "lvds1"), /* D3P */ SUNXI_FUNCTION(0x4, "uart4"), /* TX */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 18)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 19), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd0"), /* DE */ + SUNXI_FUNCTION(0x3, "lvds1"), /* D3N */ SUNXI_FUNCTION(0x4, "uart4"), /* RX */ SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 19)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 20), diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index b7dbaf77b6db..1b2f2bd09662 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -237,12 +237,19 @@ config CROS_EC_SYSFS To compile this driver as a module, choose M here: the module will be called cros_ec_sysfs. +config CROS_EC_TYPEC_ALTMODES + bool + help + Selectable symbol to enable altmodes. + config CROS_EC_TYPEC tristate "ChromeOS EC Type-C Connector Control" depends on MFD_CROS_EC_DEV && TYPEC depends on CROS_USBPD_NOTIFY depends on USB_ROLE_SWITCH default MFD_CROS_EC_DEV + select CROS_EC_TYPEC_ALTMODES if TYPEC_DP_ALTMODE + select CROS_EC_TYPEC_ALTMODES if TYPEC_TBT_ALTMODE help If you say Y here, you get support for accessing Type C connector information from the Chrome OS EC. diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index fb8335458a22..1a5a484563cc 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -19,7 +19,11 @@ obj-$(CONFIG_CROS_EC_SPI) += cros_ec_spi.o obj-$(CONFIG_CROS_EC_UART) += cros_ec_uart.o cros_ec_lpcs-objs := cros_ec_lpc.o cros_ec_lpc_mec.o cros-ec-typec-objs := cros_ec_typec.o cros_typec_vdm.o +ifneq ($(CONFIG_CROS_EC_TYPEC_ALTMODES),) + cros-ec-typec-objs += cros_typec_altmode.o +endif obj-$(CONFIG_CROS_EC_TYPEC) += cros-ec-typec.o + obj-$(CONFIG_CROS_EC_LPC) += cros_ec_lpcs.o obj-$(CONFIG_CROS_EC_PROTO) += cros_ec_proto.o cros_ec_trace.o obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT) += cros_kbd_led_backlight.o diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index e821b3d39590..110771a8645e 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -204,6 +204,11 @@ int cros_ec_register(struct cros_ec_device *ec_dev) mutex_init(&ec_dev->lock); lockdep_set_class(&ec_dev->lock, &ec_dev->lockdep_key); + /* Send RWSIG continue to jump to RW for devices using RWSIG. */ + err = cros_ec_rwsig_continue(ec_dev); + if (err) + dev_info(dev, "Failed to continue RWSIG: %d\n", err); + err = cros_ec_query_all(ec_dev); if (err) { dev_err(dev, "Cannot identify the EC: error %d\n", err); diff --git a/drivers/platform/chrome/cros_ec_i2c.c b/drivers/platform/chrome/cros_ec_i2c.c index 62662ba5bf6e..38af97cdaab2 100644 --- a/drivers/platform/chrome/cros_ec_i2c.c +++ b/drivers/platform/chrome/cros_ec_i2c.c @@ -305,7 +305,8 @@ static int cros_ec_i2c_probe(struct i2c_client *client) ec_dev->phys_name = client->adapter->name; ec_dev->din_size = sizeof(struct ec_host_response_i2c) + sizeof(struct ec_response_get_protocol_info); - ec_dev->dout_size = sizeof(struct ec_host_request_i2c); + ec_dev->dout_size = sizeof(struct ec_host_request_i2c) + + sizeof(struct ec_params_rwsig_action); err = cros_ec_register(ec_dev); if (err) { diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index 5ac37bd024c8..7e7190b30cbb 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -557,7 +557,7 @@ static int cros_ec_dev_init(struct ishtp_cl_data *client_data) ec_dev->phys_name = dev_name(dev); ec_dev->din_size = sizeof(struct cros_ish_in_msg) + sizeof(struct ec_response_get_protocol_info); - ec_dev->dout_size = sizeof(struct cros_ish_out_msg); + ec_dev->dout_size = sizeof(struct cros_ish_out_msg) + sizeof(struct ec_params_rwsig_action); return cros_ec_register(ec_dev); } diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index 924bf4d3cc77..5a2f1d98b350 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -70,13 +70,8 @@ struct lpc_driver_data { /** * struct cros_ec_lpc - LPC device-specific data * @mmio_memory_base: The first I/O port addressing EC mapped memory. - */ -struct cros_ec_lpc { - u16 mmio_memory_base; -}; - -/** - * struct lpc_driver_ops - LPC driver operations + * @base: For EC supporting memory mapping, base address of the mapped region. + * @mem32: Information about the memory mapped register region, if present. * @read: Copy length bytes from EC address offset into buffer dest. * Returns a negative error code on error, or the 8-bit checksum * of all bytes read. @@ -84,18 +79,21 @@ struct cros_ec_lpc { * Returns a negative error code on error, or the 8-bit checksum * of all bytes written. */ -struct lpc_driver_ops { - int (*read)(unsigned int offset, unsigned int length, u8 *dest); - int (*write)(unsigned int offset, unsigned int length, const u8 *msg); +struct cros_ec_lpc { + u16 mmio_memory_base; + void __iomem *base; + struct acpi_resource_fixed_memory32 mem32; + int (*read)(struct cros_ec_lpc *ec_lpc, unsigned int offset, + unsigned int length, u8 *dest); + int (*write)(struct cros_ec_lpc *ec_lpc, unsigned int offset, + unsigned int length, const u8 *msg); }; -static struct lpc_driver_ops cros_ec_lpc_ops = { }; - /* * A generic instance of the read function of struct lpc_driver_ops, used for * the LPC EC. */ -static int cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, +static int cros_ec_lpc_read_bytes(struct cros_ec_lpc *_, unsigned int offset, unsigned int length, u8 *dest) { u8 sum = 0; @@ -114,7 +112,7 @@ static int cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, * A generic instance of the write function of struct lpc_driver_ops, used for * the LPC EC. */ -static int cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, +static int cros_ec_lpc_write_bytes(struct cros_ec_lpc *_, unsigned int offset, unsigned int length, const u8 *msg) { u8 sum = 0; @@ -133,8 +131,8 @@ static int cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, * An instance of the read function of struct lpc_driver_ops, used for the * MEC variant of LPC EC. */ -static int cros_ec_lpc_mec_read_bytes(unsigned int offset, unsigned int length, - u8 *dest) +static int cros_ec_lpc_mec_read_bytes(struct cros_ec_lpc *ec_lpc, unsigned int offset, + unsigned int length, u8 *dest) { int in_range = cros_ec_lpc_mec_in_range(offset, length); @@ -145,15 +143,15 @@ static int cros_ec_lpc_mec_read_bytes(unsigned int offset, unsigned int length, cros_ec_lpc_io_bytes_mec(MEC_IO_READ, offset - EC_HOST_CMD_REGION0, length, dest) : - cros_ec_lpc_read_bytes(offset, length, dest); + cros_ec_lpc_read_bytes(ec_lpc, offset, length, dest); } /* * An instance of the write function of struct lpc_driver_ops, used for the * MEC variant of LPC EC. */ -static int cros_ec_lpc_mec_write_bytes(unsigned int offset, unsigned int length, - const u8 *msg) +static int cros_ec_lpc_mec_write_bytes(struct cros_ec_lpc *ec_lpc, unsigned int offset, + unsigned int length, const u8 *msg) { int in_range = cros_ec_lpc_mec_in_range(offset, length); @@ -164,10 +162,50 @@ static int cros_ec_lpc_mec_write_bytes(unsigned int offset, unsigned int length, cros_ec_lpc_io_bytes_mec(MEC_IO_WRITE, offset - EC_HOST_CMD_REGION0, length, (u8 *)msg) : - cros_ec_lpc_write_bytes(offset, length, msg); + cros_ec_lpc_write_bytes(ec_lpc, offset, length, msg); } -static int ec_response_timed_out(void) +static int cros_ec_lpc_direct_read(struct cros_ec_lpc *ec_lpc, unsigned int offset, + unsigned int length, u8 *dest) +{ + int sum = 0; + int i; + + if (offset < EC_HOST_CMD_REGION0 || offset > EC_LPC_ADDR_MEMMAP + + EC_MEMMAP_SIZE) { + return cros_ec_lpc_read_bytes(ec_lpc, offset, length, dest); + } + + for (i = 0; i < length; ++i) { + dest[i] = readb(ec_lpc->base + offset - EC_HOST_CMD_REGION0 + i); + sum += dest[i]; + } + + /* Return checksum of all bytes read */ + return sum; +} + +static int cros_ec_lpc_direct_write(struct cros_ec_lpc *ec_lpc, unsigned int offset, + unsigned int length, const u8 *msg) +{ + int sum = 0; + int i; + + if (offset < EC_HOST_CMD_REGION0 || offset > EC_LPC_ADDR_MEMMAP + + EC_MEMMAP_SIZE) { + return cros_ec_lpc_write_bytes(ec_lpc, offset, length, msg); + } + + for (i = 0; i < length; ++i) { + writeb(msg[i], ec_lpc->base + offset - EC_HOST_CMD_REGION0 + i); + sum += msg[i]; + } + + /* Return checksum of all bytes written */ + return sum; +} + +static int ec_response_timed_out(struct cros_ec_lpc *ec_lpc) { unsigned long one_second = jiffies + HZ; u8 data; @@ -175,7 +213,7 @@ static int ec_response_timed_out(void) usleep_range(200, 300); do { - ret = cros_ec_lpc_ops.read(EC_LPC_ADDR_HOST_CMD, 1, &data); + ret = ec_lpc->read(ec_lpc, EC_LPC_ADDR_HOST_CMD, 1, &data); if (ret < 0) return ret; if (!(data & EC_LPC_STATUS_BUSY_MASK)) @@ -189,6 +227,7 @@ static int ec_response_timed_out(void) static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec, struct cros_ec_command *msg) { + struct cros_ec_lpc *ec_lpc = ec->priv; struct ec_host_response response; u8 sum; int ret = 0; @@ -199,17 +238,17 @@ static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec, goto done; /* Write buffer */ - ret = cros_ec_lpc_ops.write(EC_LPC_ADDR_HOST_PACKET, ret, ec->dout); + ret = ec_lpc->write(ec_lpc, EC_LPC_ADDR_HOST_PACKET, ret, ec->dout); if (ret < 0) goto done; /* Here we go */ sum = EC_COMMAND_PROTOCOL_3; - ret = cros_ec_lpc_ops.write(EC_LPC_ADDR_HOST_CMD, 1, &sum); + ret = ec_lpc->write(ec_lpc, EC_LPC_ADDR_HOST_CMD, 1, &sum); if (ret < 0) goto done; - ret = ec_response_timed_out(); + ret = ec_response_timed_out(ec_lpc); if (ret < 0) goto done; if (ret) { @@ -219,7 +258,7 @@ static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec, } /* Check result */ - ret = cros_ec_lpc_ops.read(EC_LPC_ADDR_HOST_DATA, 1, &sum); + ret = ec_lpc->read(ec_lpc, EC_LPC_ADDR_HOST_DATA, 1, &sum); if (ret < 0) goto done; msg->result = ret; @@ -229,7 +268,7 @@ static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec, /* Read back response */ dout = (u8 *)&response; - ret = cros_ec_lpc_ops.read(EC_LPC_ADDR_HOST_PACKET, sizeof(response), + ret = ec_lpc->read(ec_lpc, EC_LPC_ADDR_HOST_PACKET, sizeof(response), dout); if (ret < 0) goto done; @@ -246,7 +285,7 @@ static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec, } /* Read response and process checksum */ - ret = cros_ec_lpc_ops.read(EC_LPC_ADDR_HOST_PACKET + + ret = ec_lpc->read(ec_lpc, EC_LPC_ADDR_HOST_PACKET + sizeof(response), response.data_len, msg->data); if (ret < 0) @@ -270,6 +309,7 @@ done: static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec, struct cros_ec_command *msg) { + struct cros_ec_lpc *ec_lpc = ec->priv; struct ec_lpc_host_args args; u8 sum; int ret = 0; @@ -291,7 +331,7 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec, sum = msg->command + args.flags + args.command_version + args.data_size; /* Copy data and update checksum */ - ret = cros_ec_lpc_ops.write(EC_LPC_ADDR_HOST_PARAM, msg->outsize, + ret = ec_lpc->write(ec_lpc, EC_LPC_ADDR_HOST_PARAM, msg->outsize, msg->data); if (ret < 0) goto done; @@ -299,18 +339,18 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec, /* Finalize checksum and write args */ args.checksum = sum; - ret = cros_ec_lpc_ops.write(EC_LPC_ADDR_HOST_ARGS, sizeof(args), + ret = ec_lpc->write(ec_lpc, EC_LPC_ADDR_HOST_ARGS, sizeof(args), (u8 *)&args); if (ret < 0) goto done; /* Here we go */ sum = msg->command; - ret = cros_ec_lpc_ops.write(EC_LPC_ADDR_HOST_CMD, 1, &sum); + ret = ec_lpc->write(ec_lpc, EC_LPC_ADDR_HOST_CMD, 1, &sum); if (ret < 0) goto done; - ret = ec_response_timed_out(); + ret = ec_response_timed_out(ec_lpc); if (ret < 0) goto done; if (ret) { @@ -320,7 +360,7 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec, } /* Check result */ - ret = cros_ec_lpc_ops.read(EC_LPC_ADDR_HOST_DATA, 1, &sum); + ret = ec_lpc->read(ec_lpc, EC_LPC_ADDR_HOST_DATA, 1, &sum); if (ret < 0) goto done; msg->result = ret; @@ -329,7 +369,7 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec, goto done; /* Read back args */ - ret = cros_ec_lpc_ops.read(EC_LPC_ADDR_HOST_ARGS, sizeof(args), (u8 *)&args); + ret = ec_lpc->read(ec_lpc, EC_LPC_ADDR_HOST_ARGS, sizeof(args), (u8 *)&args); if (ret < 0) goto done; @@ -345,7 +385,7 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec, sum = msg->command + args.flags + args.command_version + args.data_size; /* Read response and update checksum */ - ret = cros_ec_lpc_ops.read(EC_LPC_ADDR_HOST_PARAM, args.data_size, + ret = ec_lpc->read(ec_lpc, EC_LPC_ADDR_HOST_PARAM, args.data_size, msg->data); if (ret < 0) goto done; @@ -381,7 +421,7 @@ static int cros_ec_lpc_readmem(struct cros_ec_device *ec, unsigned int offset, /* fixed length */ if (bytes) { - ret = cros_ec_lpc_ops.read(ec_lpc->mmio_memory_base + offset, bytes, s); + ret = ec_lpc->read(ec_lpc, ec_lpc->mmio_memory_base + offset, bytes, s); if (ret < 0) return ret; return bytes; @@ -389,7 +429,7 @@ static int cros_ec_lpc_readmem(struct cros_ec_device *ec, unsigned int offset, /* string */ for (; i < EC_MEMMAP_SIZE; i++, s++) { - ret = cros_ec_lpc_ops.read(ec_lpc->mmio_memory_base + i, 1, s); + ret = ec_lpc->read(ec_lpc, ec_lpc->mmio_memory_base + i, 1, s); if (ret < 0) return ret; cnt++; @@ -419,7 +459,7 @@ static void cros_ec_lpc_acpi_notify(acpi_handle device, u32 value, void *data) return; } - if (ec_dev->mkbp_event_supported) + if (value == ACPI_NOTIFY_CROS_EC_MKBP && ec_dev->mkbp_event_supported) do { ret = cros_ec_get_next_event(ec_dev, NULL, &ec_has_more_events); @@ -453,6 +493,20 @@ static struct acpi_device *cros_ec_lpc_get_device(const char *id) return adev; } +static acpi_status cros_ec_lpc_resources(struct acpi_resource *res, void *data) +{ + struct cros_ec_lpc *ec_lpc = data; + + switch (res->type) { + case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: + ec_lpc->mem32 = res->data.fixed_memory32; + break; + default: + break; + } + return AE_OK; +} + static int cros_ec_lpc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -492,8 +546,7 @@ static int cros_ec_lpc_probe(struct platform_device *pdev) } if (quirks & CROS_EC_LPC_QUIRK_AML_MUTEX) { - const char *name - = driver_data->quirk_aml_mutex_name; + const char *name = driver_data->quirk_aml_mutex_name; ret = cros_ec_lpc_mec_acpi_mutex(ACPI_COMPANION(dev), name); if (ret) { dev_err(dev, "failed to get AML mutex '%s'", name); @@ -502,30 +555,49 @@ static int cros_ec_lpc_probe(struct platform_device *pdev) dev_info(dev, "got AML mutex '%s'", name); } } + adev = ACPI_COMPANION(dev); + if (adev) { + /* + * Retrieve the resource information in the CRS register, if available. + */ + status = acpi_walk_resources(adev->handle, METHOD_NAME__CRS, + cros_ec_lpc_resources, ec_lpc); + if (ACPI_SUCCESS(status) && ec_lpc->mem32.address_length) { + ec_lpc->base = devm_ioremap(dev, + ec_lpc->mem32.address, + ec_lpc->mem32.address_length); + if (!ec_lpc->base) + return -EINVAL; - /* - * The Framework Laptop (and possibly other non-ChromeOS devices) - * only exposes the eight I/O ports that are required for the Microchip EC. - * Requesting a larger reservation will fail. - */ - if (!devm_request_region(dev, EC_HOST_CMD_REGION0, - EC_HOST_CMD_MEC_REGION_SIZE, dev_name(dev))) { - dev_err(dev, "couldn't reserve MEC region\n"); - return -EBUSY; + ec_lpc->read = cros_ec_lpc_direct_read; + ec_lpc->write = cros_ec_lpc_direct_write; + } } + if (!ec_lpc->read) { + /* + * The Framework Laptop (and possibly other non-ChromeOS devices) + * only exposes the eight I/O ports that are required for the Microchip EC. + * Requesting a larger reservation will fail. + */ + if (!devm_request_region(dev, EC_HOST_CMD_REGION0, + EC_HOST_CMD_MEC_REGION_SIZE, dev_name(dev))) { + dev_err(dev, "couldn't reserve MEC region\n"); + return -EBUSY; + } - cros_ec_lpc_mec_init(EC_HOST_CMD_REGION0, - EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE); + cros_ec_lpc_mec_init(EC_HOST_CMD_REGION0, + EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE); - /* - * Read the mapped ID twice, the first one is assuming the - * EC is a Microchip Embedded Controller (MEC) variant, if the - * protocol fails, fallback to the non MEC variant and try to - * read again the ID. - */ - cros_ec_lpc_ops.read = cros_ec_lpc_mec_read_bytes; - cros_ec_lpc_ops.write = cros_ec_lpc_mec_write_bytes; - ret = cros_ec_lpc_ops.read(EC_LPC_ADDR_MEMMAP + EC_MEMMAP_ID, 2, buf); + /* + * Read the mapped ID twice, the first one is assuming the + * EC is a Microchip Embedded Controller (MEC) variant, if the + * protocol fails, fallback to the non MEC variant and try to + * read again the ID. + */ + ec_lpc->read = cros_ec_lpc_mec_read_bytes; + ec_lpc->write = cros_ec_lpc_mec_write_bytes; + } + ret = ec_lpc->read(ec_lpc, EC_LPC_ADDR_MEMMAP + EC_MEMMAP_ID, 2, buf); if (ret < 0) return ret; if (buf[0] != 'E' || buf[1] != 'C') { @@ -536,9 +608,9 @@ static int cros_ec_lpc_probe(struct platform_device *pdev) } /* Re-assign read/write operations for the non MEC variant */ - cros_ec_lpc_ops.read = cros_ec_lpc_read_bytes; - cros_ec_lpc_ops.write = cros_ec_lpc_write_bytes; - ret = cros_ec_lpc_ops.read(ec_lpc->mmio_memory_base + EC_MEMMAP_ID, 2, + ec_lpc->read = cros_ec_lpc_read_bytes; + ec_lpc->write = cros_ec_lpc_write_bytes; + ret = ec_lpc->read(ec_lpc, ec_lpc->mmio_memory_base + EC_MEMMAP_ID, 2, buf); if (ret < 0) return ret; @@ -573,7 +645,7 @@ static int cros_ec_lpc_probe(struct platform_device *pdev) ec_dev->cmd_readmem = cros_ec_lpc_readmem; ec_dev->din_size = sizeof(struct ec_host_response) + sizeof(struct ec_response_get_protocol_info); - ec_dev->dout_size = sizeof(struct ec_host_request); + ec_dev->dout_size = sizeof(struct ec_host_request) + sizeof(struct ec_params_rwsig_action); ec_dev->priv = ec_lpc; /* @@ -598,7 +670,6 @@ static int cros_ec_lpc_probe(struct platform_device *pdev) * Connect a notify handler to process MKBP messages if we have a * companion ACPI device. */ - adev = ACPI_COMPANION(dev); if (adev) { status = acpi_install_notify_handler(adev->handle, ACPI_ALL_NOTIFY, @@ -707,7 +778,7 @@ static const struct dmi_system_id cros_ec_lpc_dmi_table[] __initconst = { /* Framework Laptop (12th Gen Intel Core) */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Framework"), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "12th Gen Intel Core"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Laptop (12th Gen Intel Core)"), }, .driver_data = (void *)&framework_laptop_mec_lpc_driver_data, }, @@ -715,7 +786,7 @@ static const struct dmi_system_id cros_ec_lpc_dmi_table[] __initconst = { /* Framework Laptop (13th Gen Intel Core) */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Framework"), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "13th Gen Intel Core"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Laptop (13th Gen Intel Core)"), }, .driver_data = (void *)&framework_laptop_mec_lpc_driver_data, }, diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 5c9a53dffcf9..877b107fee4b 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -15,6 +15,8 @@ #include "cros_ec_trace.h" #define EC_COMMAND_RETRIES 50 +#define RWSIG_CONTINUE_RETRIES 8 +#define RWSIG_CONTINUE_MAX_ERRORS_IN_ROW 3 static const int cros_ec_error_map[] = { [EC_RES_INVALID_COMMAND] = -EOPNOTSUPP, @@ -288,6 +290,64 @@ exit: return ret; } +int cros_ec_rwsig_continue(struct cros_ec_device *ec_dev) +{ + struct cros_ec_command *msg; + struct ec_params_rwsig_action *rwsig_action; + int ret = 0; + int error_count = 0; + + ec_dev->proto_version = 3; + + msg = kmalloc(sizeof(*msg) + sizeof(*rwsig_action), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->version = 0; + msg->command = EC_CMD_RWSIG_ACTION; + msg->insize = 0; + msg->outsize = sizeof(*rwsig_action); + + rwsig_action = (struct ec_params_rwsig_action *)msg->data; + rwsig_action->action = RWSIG_ACTION_CONTINUE; + + for (int i = 0; i < RWSIG_CONTINUE_RETRIES; i++) { + ret = cros_ec_send_command(ec_dev, msg); + + if (ret < 0) { + if (++error_count >= RWSIG_CONTINUE_MAX_ERRORS_IN_ROW) + break; + } else if (msg->result == EC_RES_INVALID_COMMAND) { + /* + * If EC_RES_INVALID_COMMAND is retured, it means RWSIG + * is not supported or EC is already in RW, so there is + * nothing left to do. + */ + break; + } else if (msg->result != EC_RES_SUCCESS) { + /* Unexpected command error. */ + ret = cros_ec_map_error(msg->result); + break; + } else { + /* + * The EC_CMD_RWSIG_ACTION succeed. Send the command + * more times, to make sure EC is in RW. A following + * command can timeout, because EC may need some time to + * initialize after jump to RW. + */ + error_count = 0; + } + + if (ret != -ETIMEDOUT) + usleep_range(90000, 100000); + } + + kfree(msg); + + return ret; +} +EXPORT_SYMBOL(cros_ec_rwsig_continue); + static int cros_ec_get_proto_info(struct cros_ec_device *ec_dev, int devidx) { struct cros_ec_command *msg; @@ -306,15 +366,6 @@ static int cros_ec_get_proto_info(struct cros_ec_device *ec_dev, int devidx) msg->insize = sizeof(*info); ret = cros_ec_send_command(ec_dev, msg); - /* - * Send command once again when timeout occurred. - * Fingerprint MCU (FPMCU) is restarted during system boot which - * introduces small window in which FPMCU won't respond for any - * messages sent by kernel. There is no need to wait before next - * attempt because we waited at least EC_MSG_DEADLINE_MS. - */ - if (ret == -ETIMEDOUT) - ret = cros_ec_send_command(ec_dev, msg); if (ret < 0) { dev_dbg(ec_dev->dev, diff --git a/drivers/platform/chrome/cros_ec_rpmsg.c b/drivers/platform/chrome/cros_ec_rpmsg.c index 39d3b50a7c09..bc2666491db1 100644 --- a/drivers/platform/chrome/cros_ec_rpmsg.c +++ b/drivers/platform/chrome/cros_ec_rpmsg.c @@ -231,7 +231,7 @@ static int cros_ec_rpmsg_probe(struct rpmsg_device *rpdev) ec_dev->phys_name = dev_name(&rpdev->dev); ec_dev->din_size = sizeof(struct ec_host_response) + sizeof(struct ec_response_get_protocol_info); - ec_dev->dout_size = sizeof(struct ec_host_request); + ec_dev->dout_size = sizeof(struct ec_host_request) + sizeof(struct ec_params_rwsig_action); dev_set_drvdata(dev, ec_dev); ec_rpmsg->rpdev = rpdev; diff --git a/drivers/platform/chrome/cros_ec_spi.c b/drivers/platform/chrome/cros_ec_spi.c index 86a3d32a7763..8ca0f854e7ac 100644 --- a/drivers/platform/chrome/cros_ec_spi.c +++ b/drivers/platform/chrome/cros_ec_spi.c @@ -715,7 +715,7 @@ static int cros_ec_spi_devm_high_pri_alloc(struct device *dev, int err; ec_spi->high_pri_worker = - kthread_create_worker(0, "cros_ec_spi_high_pri"); + kthread_run_worker(0, "cros_ec_spi_high_pri"); if (IS_ERR(ec_spi->high_pri_worker)) { err = PTR_ERR(ec_spi->high_pri_worker); @@ -766,7 +766,7 @@ static int cros_ec_spi_probe(struct spi_device *spi) ec_dev->din_size = EC_MSG_PREAMBLE_COUNT + sizeof(struct ec_host_response) + sizeof(struct ec_response_get_protocol_info); - ec_dev->dout_size = sizeof(struct ec_host_request); + ec_dev->dout_size = sizeof(struct ec_host_request) + sizeof(struct ec_params_rwsig_action); ec_spi->last_transfer_ns = ktime_get_ns(); diff --git a/drivers/platform/chrome/cros_ec_trace.c b/drivers/platform/chrome/cros_ec_trace.c index 425e9441b7ca..9827b3117597 100644 --- a/drivers/platform/chrome/cros_ec_trace.c +++ b/drivers/platform/chrome/cros_ec_trace.c @@ -122,8 +122,10 @@ TRACE_SYMBOL(EC_CMD_ENTERING_MODE), \ TRACE_SYMBOL(EC_CMD_I2C_PASSTHRU_PROTECT), \ TRACE_SYMBOL(EC_CMD_CEC_WRITE_MSG), \ + TRACE_SYMBOL(EC_CMD_CEC_READ_MSG), \ TRACE_SYMBOL(EC_CMD_CEC_SET), \ TRACE_SYMBOL(EC_CMD_CEC_GET), \ + TRACE_SYMBOL(EC_CMD_CEC_PORT_COUNT), \ TRACE_SYMBOL(EC_CMD_EC_CODEC), \ TRACE_SYMBOL(EC_CMD_EC_CODEC_DMIC), \ TRACE_SYMBOL(EC_CMD_EC_CODEC_I2S_RX), \ @@ -161,11 +163,18 @@ TRACE_SYMBOL(EC_CMD_ADC_READ), \ TRACE_SYMBOL(EC_CMD_ROLLBACK_INFO), \ TRACE_SYMBOL(EC_CMD_AP_RESET), \ + TRACE_SYMBOL(EC_CMD_PCHG_COUNT), \ + TRACE_SYMBOL(EC_CMD_PCHG), \ + TRACE_SYMBOL(EC_CMD_PCHG_UPDATE), \ TRACE_SYMBOL(EC_CMD_REGULATOR_GET_INFO), \ TRACE_SYMBOL(EC_CMD_REGULATOR_ENABLE), \ TRACE_SYMBOL(EC_CMD_REGULATOR_IS_ENABLED), \ TRACE_SYMBOL(EC_CMD_REGULATOR_SET_VOLTAGE), \ TRACE_SYMBOL(EC_CMD_REGULATOR_GET_VOLTAGE), \ + TRACE_SYMBOL(EC_CMD_TYPEC_DISCOVERY), \ + TRACE_SYMBOL(EC_CMD_TYPEC_CONTROL), \ + TRACE_SYMBOL(EC_CMD_TYPEC_STATUS), \ + TRACE_SYMBOL(EC_CMD_TYPEC_VDM_RESPONSE), \ TRACE_SYMBOL(EC_CMD_CR51_BASE), \ TRACE_SYMBOL(EC_CMD_CR51_LAST), \ TRACE_SYMBOL(EC_CMD_FP_PASSTHRU), \ @@ -184,6 +193,7 @@ TRACE_SYMBOL(EC_CMD_BATTERY_GET_STATIC), \ TRACE_SYMBOL(EC_CMD_BATTERY_GET_DYNAMIC), \ TRACE_SYMBOL(EC_CMD_CHARGER_CONTROL), \ + TRACE_SYMBOL(EC_CMD_USB_PD_MUX_ACK), \ TRACE_SYMBOL(EC_CMD_BOARD_SPECIFIC_BASE), \ TRACE_SYMBOL(EC_CMD_BOARD_SPECIFIC_LAST) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index ae2f86296954..6ee182101bc9 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -18,6 +18,7 @@ #include "cros_ec_typec.h" #include "cros_typec_vdm.h" +#include "cros_typec_altmode.h" #define DRV_NAME "cros-ec-typec" @@ -290,30 +291,32 @@ static int cros_typec_register_port_altmodes(struct cros_typec_data *typec, struct typec_altmode *amode; /* All PD capable CrOS devices are assumed to support DP altmode. */ + memset(&desc, 0, sizeof(desc)); desc.svid = USB_TYPEC_DP_SID; desc.mode = USB_TYPEC_DP_MODE; desc.vdo = DP_PORT_VDO; - amode = typec_port_register_altmode(port->port, &desc); + amode = cros_typec_register_displayport(port, &desc, + typec->ap_driven_altmode); if (IS_ERR(amode)) return PTR_ERR(amode); port->port_altmode[CROS_EC_ALTMODE_DP] = amode; - typec_altmode_set_drvdata(amode, port); - amode->ops = &port_amode_ops; /* * Register TBT compatibility alt mode. The EC will not enter the mode - * if it doesn't support it, so it's safe to register it unconditionally - * here for now. + * if it doesn't support it and it will not enter automatically by + * design so we can use the |ap_driven_altmode| feature to check if we + * should register it. */ - memset(&desc, 0, sizeof(desc)); - desc.svid = USB_TYPEC_TBT_SID; - desc.mode = TYPEC_ANY_MODE; - amode = typec_port_register_altmode(port->port, &desc); - if (IS_ERR(amode)) - return PTR_ERR(amode); - port->port_altmode[CROS_EC_ALTMODE_TBT] = amode; - typec_altmode_set_drvdata(amode, port); - amode->ops = &port_amode_ops; + if (typec->ap_driven_altmode) { + memset(&desc, 0, sizeof(desc)); + desc.svid = USB_TYPEC_TBT_SID; + desc.mode = TBT_MODE; + desc.inactive = true; + amode = cros_typec_register_thunderbolt(port, &desc); + if (IS_ERR(amode)) + return PTR_ERR(amode); + port->port_altmode[CROS_EC_ALTMODE_TBT] = amode; + } port->state.alt = NULL; port->state.mode = TYPEC_STATE_USB; @@ -576,6 +579,10 @@ static int cros_typec_enable_dp(struct cros_typec_data *typec, if (!ret) ret = typec_mux_set(port->mux, &port->state); + if (!ret) + ret = cros_typec_displayport_status_update(port->state.alt, + port->state.data); + return ret; } @@ -619,6 +626,7 @@ static int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, }; struct ec_params_usb_pd_mux_ack mux_ack; enum typec_orientation orientation; + struct cros_typec_altmode_node *node; int ret; ret = cros_ec_cmd(typec->ec, 0, EC_CMD_USB_PD_MUX_INFO, @@ -677,6 +685,14 @@ static int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, port->mux_flags); } + /* Iterate all partner alt-modes and set the active alternate mode. */ + list_for_each_entry(node, &port->partner_mode_list, list) { + typec_altmode_update_active( + node->amode, + port->state.alt && + node->amode->svid == port->state.alt->svid); + } + mux_ack: if (!typec->needs_mux_ack) return ret; @@ -1244,6 +1260,8 @@ static int cros_typec_probe(struct platform_device *pdev) typec->typec_cmd_supported = cros_ec_check_features(ec_dev, EC_FEATURE_TYPEC_CMD); typec->needs_mux_ack = cros_ec_check_features(ec_dev, EC_FEATURE_TYPEC_MUX_REQUIRE_AP_ACK); + typec->ap_driven_altmode = cros_ec_check_features( + ec_dev, EC_FEATURE_TYPEC_REQUIRE_AP_MODE_ENTRY); ret = cros_ec_cmd(typec->ec, 0, EC_CMD_USB_PD_PORTS, NULL, 0, &resp, sizeof(resp)); diff --git a/drivers/platform/chrome/cros_ec_typec.h b/drivers/platform/chrome/cros_ec_typec.h index deda180a646f..9fd5342bb0ad 100644 --- a/drivers/platform/chrome/cros_ec_typec.h +++ b/drivers/platform/chrome/cros_ec_typec.h @@ -39,6 +39,7 @@ struct cros_typec_data { struct work_struct port_work; bool typec_cmd_supported; bool needs_mux_ack; + bool ap_driven_altmode; }; /* Per port data. */ diff --git a/drivers/platform/chrome/cros_ec_uart.c b/drivers/platform/chrome/cros_ec_uart.c index 62bc24f6dcc7..19c179d49c90 100644 --- a/drivers/platform/chrome/cros_ec_uart.c +++ b/drivers/platform/chrome/cros_ec_uart.c @@ -283,7 +283,7 @@ static int cros_ec_uart_probe(struct serdev_device *serdev) ec_dev->pkt_xfer = cros_ec_uart_pkt_xfer; ec_dev->din_size = sizeof(struct ec_host_response) + sizeof(struct ec_response_get_protocol_info); - ec_dev->dout_size = sizeof(struct ec_host_request); + ec_dev->dout_size = sizeof(struct ec_host_request) + sizeof(struct ec_params_rwsig_action); serdev_device_set_client_ops(serdev, &cros_ec_uart_client_ops); diff --git a/drivers/platform/chrome/cros_ec_vbc.c b/drivers/platform/chrome/cros_ec_vbc.c index 7bdb489354c5..963c4db23055 100644 --- a/drivers/platform/chrome/cros_ec_vbc.c +++ b/drivers/platform/chrome/cros_ec_vbc.c @@ -15,7 +15,7 @@ #define DRV_NAME "cros-ec-vbc" static ssize_t vboot_context_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *att, char *buf, + const struct bin_attribute *att, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -59,7 +59,7 @@ static ssize_t vboot_context_read(struct file *filp, struct kobject *kobj, } static ssize_t vboot_context_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -99,16 +99,16 @@ static ssize_t vboot_context_write(struct file *filp, struct kobject *kobj, return data_sz; } -static BIN_ATTR_RW(vboot_context, 16); +static const BIN_ATTR_RW(vboot_context, 16); -static struct bin_attribute *cros_ec_vbc_bin_attrs[] = { +static const struct bin_attribute *const cros_ec_vbc_bin_attrs[] = { &bin_attr_vboot_context, NULL }; static const struct attribute_group cros_ec_vbc_attr_group = { .name = "vbc", - .bin_attrs = cros_ec_vbc_bin_attrs, + .bin_attrs_new = cros_ec_vbc_bin_attrs, }; static int cros_ec_vbc_probe(struct platform_device *pd) diff --git a/drivers/platform/chrome/cros_kbd_led_backlight.c b/drivers/platform/chrome/cros_kbd_led_backlight.c index 78097c8a4966..fc27bd7fc4b9 100644 --- a/drivers/platform/chrome/cros_kbd_led_backlight.c +++ b/drivers/platform/chrome/cros_kbd_led_backlight.c @@ -121,7 +121,17 @@ static const struct keyboard_led_drvdata keyboard_led_drvdata_acpi = { #endif /* CONFIG_ACPI */ -#if IS_ENABLED(CONFIG_CROS_EC) +#if IS_ENABLED(CONFIG_MFD_CROS_EC_DEV) +static int keyboard_led_init_ec_pwm_mfd(struct platform_device *pdev) +{ + struct cros_ec_dev *ec_dev = dev_get_drvdata(pdev->dev.parent); + struct cros_ec_device *cros_ec = ec_dev->ec_dev; + struct keyboard_led *keyboard_led = platform_get_drvdata(pdev); + + keyboard_led->ec = cros_ec; + + return 0; +} static int keyboard_led_set_brightness_ec_pwm(struct led_classdev *cdev, @@ -169,44 +179,6 @@ keyboard_led_get_brightness_ec_pwm(struct led_classdev *cdev) return resp->percent; } -static int keyboard_led_init_ec_pwm(struct platform_device *pdev) -{ - struct keyboard_led *keyboard_led = platform_get_drvdata(pdev); - - keyboard_led->ec = dev_get_drvdata(pdev->dev.parent); - if (!keyboard_led->ec) { - dev_err(&pdev->dev, "no parent EC device\n"); - return -EINVAL; - } - - return 0; -} - -static const __maybe_unused struct keyboard_led_drvdata keyboard_led_drvdata_ec_pwm = { - .init = keyboard_led_init_ec_pwm, - .brightness_set_blocking = keyboard_led_set_brightness_ec_pwm, - .brightness_get = keyboard_led_get_brightness_ec_pwm, - .max_brightness = KEYBOARD_BACKLIGHT_MAX, -}; - -#else /* IS_ENABLED(CONFIG_CROS_EC) */ - -static const __maybe_unused struct keyboard_led_drvdata keyboard_led_drvdata_ec_pwm = {}; - -#endif /* IS_ENABLED(CONFIG_CROS_EC) */ - -#if IS_ENABLED(CONFIG_MFD_CROS_EC_DEV) -static int keyboard_led_init_ec_pwm_mfd(struct platform_device *pdev) -{ - struct cros_ec_dev *ec_dev = dev_get_drvdata(pdev->dev.parent); - struct cros_ec_device *cros_ec = ec_dev->ec_dev; - struct keyboard_led *keyboard_led = platform_get_drvdata(pdev); - - keyboard_led->ec = cros_ec; - - return 0; -} - static const struct keyboard_led_drvdata keyboard_led_drvdata_ec_pwm_mfd = { .init = keyboard_led_init_ec_pwm_mfd, .brightness_set_blocking = keyboard_led_set_brightness_ec_pwm, @@ -229,7 +201,7 @@ static int keyboard_led_probe(struct platform_device *pdev) { const struct keyboard_led_drvdata *drvdata; struct keyboard_led *keyboard_led; - int error; + int err; if (keyboard_led_is_mfd_device(pdev)) drvdata = &keyboard_led_drvdata_ec_pwm_mfd; @@ -244,9 +216,9 @@ static int keyboard_led_probe(struct platform_device *pdev) platform_set_drvdata(pdev, keyboard_led); if (drvdata->init) { - error = drvdata->init(pdev); - if (error) - return error; + err = drvdata->init(pdev); + if (err) + return err; } keyboard_led->cdev.name = "chromeos::kbd_backlight"; @@ -256,13 +228,10 @@ static int keyboard_led_probe(struct platform_device *pdev) keyboard_led->cdev.brightness_set_blocking = drvdata->brightness_set_blocking; keyboard_led->cdev.brightness_get = drvdata->brightness_get; - error = devm_led_classdev_register(&pdev->dev, &keyboard_led->cdev); - if (error == -EEXIST) /* Already bound via other mechanism */ + err = devm_led_classdev_register(&pdev->dev, &keyboard_led->cdev); + if (err == -EEXIST) /* Already bound via other mechanism */ return -ENODEV; - if (error) - return error; - - return 0; + return err; } #ifdef CONFIG_ACPI @@ -273,17 +242,6 @@ static const struct acpi_device_id keyboard_led_acpi_match[] = { MODULE_DEVICE_TABLE(acpi, keyboard_led_acpi_match); #endif -#ifdef CONFIG_OF -static const struct of_device_id keyboard_led_of_match[] = { - { - .compatible = "google,cros-kbd-led-backlight", - .data = &keyboard_led_drvdata_ec_pwm, - }, - {} -}; -MODULE_DEVICE_TABLE(of, keyboard_led_of_match); -#endif - static const struct platform_device_id keyboard_led_id[] = { { "cros-keyboard-leds", 0 }, {} @@ -294,7 +252,6 @@ static struct platform_driver keyboard_led_driver = { .driver = { .name = "cros-keyboard-leds", .acpi_match_table = ACPI_PTR(keyboard_led_acpi_match), - .of_match_table = of_match_ptr(keyboard_led_of_match), }, .probe = keyboard_led_probe, .id_table = keyboard_led_id, diff --git a/drivers/platform/chrome/cros_typec_altmode.c b/drivers/platform/chrome/cros_typec_altmode.c new file mode 100644 index 000000000000..557340b53af0 --- /dev/null +++ b/drivers/platform/chrome/cros_typec_altmode.c @@ -0,0 +1,373 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Alt-mode implementation on ChromeOS EC. + * + * Copyright 2024 Google LLC + * Author: Abhishek Pandit-Subedi + */ +#include "cros_ec_typec.h" + +#include +#include +#include +#include +#include + +#include "cros_typec_altmode.h" + +struct cros_typec_altmode_data { + struct work_struct work; + struct cros_typec_port *port; + struct typec_altmode *alt; + bool ap_mode_entry; + + struct mutex lock; + u32 header; + u32 *vdo_data; + u8 vdo_size; + + u16 sid; + u8 mode; +}; + +struct cros_typec_dp_data { + struct cros_typec_altmode_data adata; + struct typec_displayport_data data; + bool configured; + bool pending_status_update; +}; + +static void cros_typec_altmode_work(struct work_struct *work) +{ + struct cros_typec_altmode_data *data = + container_of(work, struct cros_typec_altmode_data, work); + + mutex_lock(&data->lock); + + if (typec_altmode_vdm(data->alt, data->header, data->vdo_data, + data->vdo_size)) + dev_err(&data->alt->dev, "VDM 0x%x failed\n", data->header); + + data->header = 0; + data->vdo_data = NULL; + data->vdo_size = 0; + + mutex_unlock(&data->lock); +} + +static int cros_typec_altmode_enter(struct typec_altmode *alt, u32 *vdo) +{ + struct cros_typec_altmode_data *adata = typec_altmode_get_drvdata(alt); + struct ec_params_typec_control req = { + .port = adata->port->port_num, + .command = TYPEC_CONTROL_COMMAND_ENTER_MODE, + }; + int svdm_version; + int ret; + + if (!adata->ap_mode_entry) { + dev_warn(&alt->dev, + "EC does not support AP driven mode entry\n"); + return -EOPNOTSUPP; + } + + if (adata->sid == USB_TYPEC_DP_SID) + req.mode_to_enter = CROS_EC_ALTMODE_DP; + else if (adata->sid == USB_TYPEC_TBT_SID) + req.mode_to_enter = CROS_EC_ALTMODE_TBT; + else + return -EOPNOTSUPP; + + ret = cros_ec_cmd(adata->port->typec_data->ec, 0, EC_CMD_TYPEC_CONTROL, + &req, sizeof(req), NULL, 0); + if (ret < 0) + return ret; + + svdm_version = typec_altmode_get_svdm_version(alt); + if (svdm_version < 0) + return svdm_version; + + mutex_lock(&adata->lock); + + adata->header = VDO(adata->sid, 1, svdm_version, CMD_ENTER_MODE); + adata->header |= VDO_OPOS(adata->mode); + adata->header |= VDO_CMDT(CMDT_RSP_ACK); + adata->vdo_data = NULL; + adata->vdo_size = 1; + schedule_work(&adata->work); + + mutex_unlock(&adata->lock); + return ret; +} + +static int cros_typec_altmode_exit(struct typec_altmode *alt) +{ + struct cros_typec_altmode_data *adata = typec_altmode_get_drvdata(alt); + struct ec_params_typec_control req = { + .port = adata->port->port_num, + .command = TYPEC_CONTROL_COMMAND_EXIT_MODES, + }; + int svdm_version; + int ret; + + if (!adata->ap_mode_entry) { + dev_warn(&alt->dev, + "EC does not support AP driven mode exit\n"); + return -EOPNOTSUPP; + } + + ret = cros_ec_cmd(adata->port->typec_data->ec, 0, EC_CMD_TYPEC_CONTROL, + &req, sizeof(req), NULL, 0); + + if (ret < 0) + return ret; + + svdm_version = typec_altmode_get_svdm_version(alt); + if (svdm_version < 0) + return svdm_version; + + mutex_lock(&adata->lock); + + adata->header = VDO(adata->sid, 1, svdm_version, CMD_EXIT_MODE); + adata->header |= VDO_OPOS(adata->mode); + adata->header |= VDO_CMDT(CMDT_RSP_ACK); + adata->vdo_data = NULL; + adata->vdo_size = 1; + schedule_work(&adata->work); + + mutex_unlock(&adata->lock); + return ret; +} + +static int cros_typec_displayport_vdm(struct typec_altmode *alt, u32 header, + const u32 *data, int count) +{ + struct cros_typec_dp_data *dp_data = typec_altmode_get_drvdata(alt); + struct cros_typec_altmode_data *adata = &dp_data->adata; + + + int cmd_type = PD_VDO_CMDT(header); + int cmd = PD_VDO_CMD(header); + int svdm_version; + + svdm_version = typec_altmode_get_svdm_version(alt); + if (svdm_version < 0) + return svdm_version; + + mutex_lock(&adata->lock); + + switch (cmd_type) { + case CMDT_INIT: + if (PD_VDO_SVDM_VER(header) < svdm_version) { + typec_partner_set_svdm_version(adata->port->partner, + PD_VDO_SVDM_VER(header)); + svdm_version = PD_VDO_SVDM_VER(header); + } + + adata->header = VDO(adata->sid, 1, svdm_version, cmd); + adata->header |= VDO_OPOS(adata->mode); + + /* + * DP_CMD_CONFIGURE: We can't actually do anything with the + * provided VDO yet so just send back an ACK. + * + * DP_CMD_STATUS_UPDATE: We wait for Mux changes to send + * DPStatus Acks. + */ + switch (cmd) { + case DP_CMD_CONFIGURE: + dp_data->data.conf = *data; + adata->header |= VDO_CMDT(CMDT_RSP_ACK); + dp_data->configured = true; + schedule_work(&adata->work); + break; + case DP_CMD_STATUS_UPDATE: + dp_data->pending_status_update = true; + break; + default: + adata->header |= VDO_CMDT(CMDT_RSP_ACK); + schedule_work(&adata->work); + break; + } + + break; + default: + break; + } + + mutex_unlock(&adata->lock); + return 0; +} + +static int cros_typec_thunderbolt_vdm(struct typec_altmode *alt, u32 header, + const u32 *data, int count) +{ + struct cros_typec_altmode_data *adata = typec_altmode_get_drvdata(alt); + + int cmd_type = PD_VDO_CMDT(header); + int cmd = PD_VDO_CMD(header); + int svdm_version; + + svdm_version = typec_altmode_get_svdm_version(alt); + if (svdm_version < 0) + return svdm_version; + + mutex_lock(&adata->lock); + + switch (cmd_type) { + case CMDT_INIT: + if (PD_VDO_SVDM_VER(header) < svdm_version) { + typec_partner_set_svdm_version(adata->port->partner, + PD_VDO_SVDM_VER(header)); + svdm_version = PD_VDO_SVDM_VER(header); + } + + adata->header = VDO(adata->sid, 1, svdm_version, cmd); + adata->header |= VDO_OPOS(adata->mode); + + switch (cmd) { + case CMD_ENTER_MODE: + /* Don't respond to the enter mode vdm because it + * triggers mux configuration. This is handled directly + * by the cros_ec_typec driver so the Thunderbolt driver + * doesn't need to be involved. + */ + break; + default: + adata->header |= VDO_CMDT(CMDT_RSP_ACK); + schedule_work(&adata->work); + break; + } + + break; + default: + break; + } + + mutex_unlock(&adata->lock); + return 0; +} + + +static int cros_typec_altmode_vdm(struct typec_altmode *alt, u32 header, + const u32 *data, int count) +{ + struct cros_typec_altmode_data *adata = typec_altmode_get_drvdata(alt); + + if (!adata->ap_mode_entry) + return -EOPNOTSUPP; + + if (adata->sid == USB_TYPEC_DP_SID) + return cros_typec_displayport_vdm(alt, header, data, count); + + if (adata->sid == USB_TYPEC_TBT_SID) + return cros_typec_thunderbolt_vdm(alt, header, data, count); + + return -EINVAL; +} + +static const struct typec_altmode_ops cros_typec_altmode_ops = { + .enter = cros_typec_altmode_enter, + .exit = cros_typec_altmode_exit, + .vdm = cros_typec_altmode_vdm, +}; + +#if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE) +int cros_typec_displayport_status_update(struct typec_altmode *altmode, + struct typec_displayport_data *data) +{ + struct cros_typec_dp_data *dp_data = + typec_altmode_get_drvdata(altmode); + struct cros_typec_altmode_data *adata = &dp_data->adata; + + if (!dp_data->pending_status_update) { + dev_dbg(&altmode->dev, + "Got DPStatus without a pending request\n"); + return 0; + } + + if (dp_data->configured && dp_data->data.conf != data->conf) + dev_dbg(&altmode->dev, + "DP Conf doesn't match. Requested 0x%04x, Actual 0x%04x\n", + dp_data->data.conf, data->conf); + + mutex_lock(&adata->lock); + + dp_data->data = *data; + dp_data->pending_status_update = false; + adata->header |= VDO_CMDT(CMDT_RSP_ACK); + adata->vdo_data = &dp_data->data.status; + adata->vdo_size = 2; + schedule_work(&adata->work); + + mutex_unlock(&adata->lock); + + return 0; +} + +struct typec_altmode * +cros_typec_register_displayport(struct cros_typec_port *port, + struct typec_altmode_desc *desc, + bool ap_mode_entry) +{ + struct typec_altmode *alt; + struct cros_typec_dp_data *dp_data; + struct cros_typec_altmode_data *adata; + + alt = typec_port_register_altmode(port->port, desc); + if (IS_ERR(alt)) + return alt; + + dp_data = devm_kzalloc(&alt->dev, sizeof(*dp_data), GFP_KERNEL); + if (!dp_data) { + typec_unregister_altmode(alt); + return ERR_PTR(-ENOMEM); + } + + adata = &dp_data->adata; + INIT_WORK(&adata->work, cros_typec_altmode_work); + mutex_init(&adata->lock); + adata->alt = alt; + adata->port = port; + adata->ap_mode_entry = ap_mode_entry; + adata->sid = desc->svid; + adata->mode = desc->mode; + + typec_altmode_set_ops(alt, &cros_typec_altmode_ops); + typec_altmode_set_drvdata(alt, adata); + + return alt; +} +#endif + +#if IS_ENABLED(CONFIG_TYPEC_TBT_ALTMODE) +struct typec_altmode * +cros_typec_register_thunderbolt(struct cros_typec_port *port, + struct typec_altmode_desc *desc) +{ + struct typec_altmode *alt; + struct cros_typec_altmode_data *adata; + + alt = typec_port_register_altmode(port->port, desc); + if (IS_ERR(alt)) + return alt; + + adata = devm_kzalloc(&alt->dev, sizeof(*adata), GFP_KERNEL); + if (!adata) { + typec_unregister_altmode(alt); + return ERR_PTR(-ENOMEM); + } + + INIT_WORK(&adata->work, cros_typec_altmode_work); + adata->alt = alt; + adata->port = port; + adata->ap_mode_entry = true; + adata->sid = desc->svid; + adata->mode = desc->mode; + + typec_altmode_set_ops(alt, &cros_typec_altmode_ops); + typec_altmode_set_drvdata(alt, adata); + + return alt; +} +#endif diff --git a/drivers/platform/chrome/cros_typec_altmode.h b/drivers/platform/chrome/cros_typec_altmode.h new file mode 100644 index 000000000000..3f2aa95d065a --- /dev/null +++ b/drivers/platform/chrome/cros_typec_altmode.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __CROS_TYPEC_ALTMODE_H__ +#define __CROS_TYPEC_ALTMODE_H__ + +#include +#include + +struct cros_typec_port; +struct typec_altmode; +struct typec_altmode_desc; +struct typec_displayport_data; + +#if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE) +struct typec_altmode * +cros_typec_register_displayport(struct cros_typec_port *port, + struct typec_altmode_desc *desc, + bool ap_mode_entry); + +int cros_typec_displayport_status_update(struct typec_altmode *altmode, + struct typec_displayport_data *data); +#else +static inline struct typec_altmode * +cros_typec_register_displayport(struct cros_typec_port *port, + struct typec_altmode_desc *desc, + bool ap_mode_entry) +{ + return typec_port_register_altmode(port->port, desc); +} + +static inline int cros_typec_displayport_status_update(struct typec_altmode *altmode, + struct typec_displayport_data *data) +{ + return 0; +} +#endif + +#if IS_ENABLED(CONFIG_TYPEC_TBT_ALTMODE) +struct typec_altmode * +cros_typec_register_thunderbolt(struct cros_typec_port *port, + struct typec_altmode_desc *desc); +#else +static inline struct typec_altmode * +cros_typec_register_thunderbolt(struct cros_typec_port *port, + struct typec_altmode_desc *desc) +{ + return typec_port_register_altmode(port->port, desc); +} +#endif + +#endif /* __CROS_TYPEC_ALTMODE_H__ */ diff --git a/drivers/platform/chrome/cros_usbpd_logger.c b/drivers/platform/chrome/cros_usbpd_logger.c index cd71f1caea81..7ce75e2e039e 100644 --- a/drivers/platform/chrome/cros_usbpd_logger.c +++ b/drivers/platform/chrome/cros_usbpd_logger.c @@ -13,6 +13,7 @@ #include #include #include +#include #define DRV_NAME "cros-usbpd-logger" @@ -135,8 +136,8 @@ static void cros_usbpd_print_log_entry(struct ec_response_pd_log *r, len += append_str(buf, len, "Power supply fault: %s", fault); break; case PD_EVENT_VIDEO_DP_MODE: - len += append_str(buf, len, "DP mode %sabled", r->data == 1 ? - "en" : "dis"); + len += append_str(buf, len, "DP mode %s", + str_enabled_disabled(r->data == 1)); break; case PD_EVENT_VIDEO_CODEC: minfo = (struct mcdp_info *)r->payload; diff --git a/drivers/platform/cznic/turris-omnia-mcu-base.c b/drivers/platform/cznic/turris-omnia-mcu-base.c index 58f9afae2867..770e680b96f9 100644 --- a/drivers/platform/cznic/turris-omnia-mcu-base.c +++ b/drivers/platform/cznic/turris-omnia-mcu-base.c @@ -52,6 +52,7 @@ int omnia_cmd_write_read(const struct i2c_client *client, return 0; } +EXPORT_SYMBOL_GPL(omnia_cmd_write_read); static int omnia_get_version_hash(struct omnia_mcu *mcu, bool bootloader, char version[static OMNIA_FW_VERSION_HEX_LEN]) @@ -257,6 +258,8 @@ static int omnia_mcu_read_features(struct omnia_mcu *mcu) _DEF_FEAT(NEW_INT_API, "new interrupt API"), _DEF_FEAT(POWEROFF_WAKEUP, "poweroff and wakeup"), _DEF_FEAT(TRNG, "true random number generator"), + _DEF_FEAT(BRIGHTNESS_INT, "LED panel brightness change interrupt"), + _DEF_FEAT(LED_GAMMA_CORRECTION, "LED gamma correction"), #undef _DEF_FEAT }; struct i2c_client *client = mcu->client; diff --git a/drivers/platform/cznic/turris-omnia-mcu.h b/drivers/platform/cznic/turris-omnia-mcu.h index 2b13e28ee323..088541be3f4c 100644 --- a/drivers/platform/cznic/turris-omnia-mcu.h +++ b/drivers/platform/cznic/turris-omnia-mcu.h @@ -8,7 +8,6 @@ #ifndef __TURRIS_OMNIA_MCU_H #define __TURRIS_OMNIA_MCU_H -#include #include #include #include @@ -17,8 +16,6 @@ #include #include #include -#include -#include struct i2c_client; struct rtc_device; @@ -93,133 +90,6 @@ struct omnia_mcu { #endif }; -int omnia_cmd_write_read(const struct i2c_client *client, - void *cmd, unsigned int cmd_len, - void *reply, unsigned int reply_len); - -static inline int omnia_cmd_write(const struct i2c_client *client, void *cmd, - unsigned int len) -{ - return omnia_cmd_write_read(client, cmd, len, NULL, 0); -} - -static inline int omnia_cmd_write_u8(const struct i2c_client *client, u8 cmd, - u8 val) -{ - u8 buf[2] = { cmd, val }; - - return omnia_cmd_write(client, buf, sizeof(buf)); -} - -static inline int omnia_cmd_write_u16(const struct i2c_client *client, u8 cmd, - u16 val) -{ - u8 buf[3]; - - buf[0] = cmd; - put_unaligned_le16(val, &buf[1]); - - return omnia_cmd_write(client, buf, sizeof(buf)); -} - -static inline int omnia_cmd_write_u32(const struct i2c_client *client, u8 cmd, - u32 val) -{ - u8 buf[5]; - - buf[0] = cmd; - put_unaligned_le32(val, &buf[1]); - - return omnia_cmd_write(client, buf, sizeof(buf)); -} - -static inline int omnia_cmd_read(const struct i2c_client *client, u8 cmd, - void *reply, unsigned int len) -{ - return omnia_cmd_write_read(client, &cmd, 1, reply, len); -} - -static inline unsigned int -omnia_compute_reply_length(unsigned long mask, bool interleaved, - unsigned int offset) -{ - if (!mask) - return 0; - - return ((__fls(mask) >> 3) << interleaved) + 1 + offset; -} - -/* Returns 0 on success */ -static inline int omnia_cmd_read_bits(const struct i2c_client *client, u8 cmd, - unsigned long bits, unsigned long *dst) -{ - __le32 reply; - int err; - - if (!bits) { - *dst = 0; - return 0; - } - - err = omnia_cmd_read(client, cmd, &reply, - omnia_compute_reply_length(bits, false, 0)); - if (err) - return err; - - *dst = le32_to_cpu(reply) & bits; - - return 0; -} - -static inline int omnia_cmd_read_bit(const struct i2c_client *client, u8 cmd, - unsigned long bit) -{ - unsigned long reply; - int err; - - err = omnia_cmd_read_bits(client, cmd, bit, &reply); - if (err) - return err; - - return !!reply; -} - -static inline int omnia_cmd_read_u32(const struct i2c_client *client, u8 cmd, - u32 *dst) -{ - __le32 reply; - int err; - - err = omnia_cmd_read(client, cmd, &reply, sizeof(reply)); - if (err) - return err; - - *dst = le32_to_cpu(reply); - - return 0; -} - -static inline int omnia_cmd_read_u16(const struct i2c_client *client, u8 cmd, - u16 *dst) -{ - __le16 reply; - int err; - - err = omnia_cmd_read(client, cmd, &reply, sizeof(reply)); - if (err) - return err; - - *dst = le16_to_cpu(reply); - - return 0; -} - -static inline int omnia_cmd_read_u8(const struct i2c_client *client, u8 cmd, - u8 *reply) -{ - return omnia_cmd_read(client, cmd, reply, sizeof(*reply)); -} - #ifdef CONFIG_TURRIS_OMNIA_MCU_GPIO extern const u8 omnia_int_to_gpio_idx[32]; extern const struct attribute_group omnia_mcu_gpio_group; diff --git a/drivers/platform/loongarch/Kconfig b/drivers/platform/loongarch/Kconfig index 5633e4d73991..447528797d07 100644 --- a/drivers/platform/loongarch/Kconfig +++ b/drivers/platform/loongarch/Kconfig @@ -18,7 +18,7 @@ if LOONGARCH_PLATFORM_DEVICES config LOONGSON_LAPTOP tristate "Generic Loongson-3 Laptop Driver" - depends on ACPI + depends on ACPI_EC depends on BACKLIGHT_CLASS_DEVICE depends on INPUT depends on MACH_LOONGSON64 diff --git a/drivers/platform/mellanox/mlxbf-bootctl.c b/drivers/platform/mellanox/mlxbf-bootctl.c index c5b36837e694..9cae07348d5e 100644 --- a/drivers/platform/mellanox/mlxbf-bootctl.c +++ b/drivers/platform/mellanox/mlxbf-bootctl.c @@ -177,7 +177,7 @@ static ssize_t post_reset_wdog_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", ret); + return sysfs_emit(buf, "%d\n", ret); } static ssize_t post_reset_wdog_store(struct device *dev, @@ -206,7 +206,7 @@ static ssize_t mlxbf_bootctl_show(int smc_op, char *buf) if (action < 0) return action; - return sprintf(buf, "%s\n", mlxbf_bootctl_action_to_string(action)); + return sysfs_emit(buf, "%s\n", mlxbf_bootctl_action_to_string(action)); } static int mlxbf_bootctl_store(int smc_op, const char *buf, size_t count) @@ -274,14 +274,14 @@ static ssize_t lifecycle_state_show(struct device *dev, * due to using the test bits. */ if (test_state) { - return sprintf(buf, "%s(test)\n", + return sysfs_emit(buf, "%s(test)\n", mlxbf_bootctl_lifecycle_states[lc_state]); } else if (use_dev_key && (lc_state == MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE)) { - return sprintf(buf, "Secured (development)\n"); + return sysfs_emit(buf, "Secured (development)\n"); } - return sprintf(buf, "%s\n", mlxbf_bootctl_lifecycle_states[lc_state]); + return sysfs_emit(buf, "%s\n", mlxbf_bootctl_lifecycle_states[lc_state]); } static ssize_t secure_boot_fuse_state_show(struct device *dev, @@ -332,9 +332,9 @@ static ssize_t secure_boot_fuse_state_show(struct device *dev, else status = valid ? "Invalid" : "Free"; } - buf_len += sprintf(buf + buf_len, "%d:%s ", key, status); + buf_len += sysfs_emit(buf + buf_len, "%d:%s ", key, status); } - buf_len += sprintf(buf + buf_len, "\n"); + buf_len += sysfs_emit(buf + buf_len, "\n"); return buf_len; } @@ -939,7 +939,7 @@ MODULE_DEVICE_TABLE(acpi, mlxbf_bootctl_acpi_ids); static ssize_t mlxbf_bootctl_bootfifo_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { @@ -971,9 +971,9 @@ static ssize_t mlxbf_bootctl_bootfifo_read(struct file *filp, return p - buf; } -static struct bin_attribute mlxbf_bootctl_bootfifo_sysfs_attr = { +static const struct bin_attribute mlxbf_bootctl_bootfifo_sysfs_attr = { .attr = { .name = "bootfifo", .mode = 0400 }, - .read = mlxbf_bootctl_bootfifo_read, + .read_new = mlxbf_bootctl_bootfifo_read, }; static bool mlxbf_bootctl_guid_match(const guid_t *guid, diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index 9d18dfca6a67..36a00692347d 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -88,6 +88,7 @@ #define MLXBF_PMC_CRSPACE_PERFMON_CTL(n) (n * MLXBF_PMC_CRSPACE_PERFMON_REG0_SZ) #define MLXBF_PMC_CRSPACE_PERFMON_EN BIT(30) #define MLXBF_PMC_CRSPACE_PERFMON_CLR BIT(28) +#define MLXBF_PMC_CRSPACE_PERFMON_COUNT_CLOCK(n) (MLXBF_PMC_CRSPACE_PERFMON_CTL(n) + 0x4) #define MLXBF_PMC_CRSPACE_PERFMON_VAL0(n) (MLXBF_PMC_CRSPACE_PERFMON_CTL(n) + 0xc) /** @@ -114,6 +115,7 @@ struct mlxbf_pmc_attribute { * @attr_event: Attributes for "event" sysfs files * @attr_event_list: Attributes for "event_list" sysfs files * @attr_enable: Attributes for "enable" sysfs files + * @attr_count_clock: Attributes for "count_clock" sysfs files * @block_attr: All attributes needed for the block * @block_attr_grp: Attribute group for the block */ @@ -126,6 +128,7 @@ struct mlxbf_pmc_block_info { struct mlxbf_pmc_attribute *attr_event; struct mlxbf_pmc_attribute attr_event_list; struct mlxbf_pmc_attribute attr_enable; + struct mlxbf_pmc_attribute attr_count_clock; struct attribute *block_attr[MLXBF_PMC_MAX_ATTRS]; struct attribute_group block_attr_grp; }; @@ -859,6 +862,37 @@ static const struct mlxbf_pmc_events mlxbf_pmc_llt_miss_events[] = { {75, "HISTOGRAM_HISTOGRAM_BIN9"}, }; +static const struct mlxbf_pmc_events mlxbf_pmc_clock_events[] = { + { 0x0, "FMON_CLK_LAST_COUNT_PLL_D1_INST0" }, + { 0x4, "REFERENCE_WINDOW_WIDTH_PLL_D1_INST0" }, + { 0x8, "FMON_CLK_LAST_COUNT_PLL_D1_INST1" }, + { 0xc, "REFERENCE_WINDOW_WIDTH_PLL_D1_INST1" }, + { 0x10, "FMON_CLK_LAST_COUNT_PLL_G1" }, + { 0x14, "REFERENCE_WINDOW_WIDTH_PLL_G1" }, + { 0x18, "FMON_CLK_LAST_COUNT_PLL_W1" }, + { 0x1c, "REFERENCE_WINDOW_WIDTH_PLL_W1" }, + { 0x20, "FMON_CLK_LAST_COUNT_PLL_T1" }, + { 0x24, "REFERENCE_WINDOW_WIDTH_PLL_T1" }, + { 0x28, "FMON_CLK_LAST_COUNT_PLL_A0" }, + { 0x2c, "REFERENCE_WINDOW_WIDTH_PLL_A0" }, + { 0x30, "FMON_CLK_LAST_COUNT_PLL_C0" }, + { 0x34, "REFERENCE_WINDOW_WIDTH_PLL_C0" }, + { 0x38, "FMON_CLK_LAST_COUNT_PLL_N1" }, + { 0x3c, "REFERENCE_WINDOW_WIDTH_PLL_N1" }, + { 0x40, "FMON_CLK_LAST_COUNT_PLL_I1" }, + { 0x44, "REFERENCE_WINDOW_WIDTH_PLL_I1" }, + { 0x48, "FMON_CLK_LAST_COUNT_PLL_R1" }, + { 0x4c, "REFERENCE_WINDOW_WIDTH_PLL_R1" }, + { 0x50, "FMON_CLK_LAST_COUNT_PLL_P1" }, + { 0x54, "REFERENCE_WINDOW_WIDTH_PLL_P1" }, + { 0x58, "FMON_CLK_LAST_COUNT_REF_100_INST0" }, + { 0x5c, "REFERENCE_WINDOW_WIDTH_REF_100_INST0" }, + { 0x60, "FMON_CLK_LAST_COUNT_REF_100_INST1" }, + { 0x64, "REFERENCE_WINDOW_WIDTH_REF_100_INST1" }, + { 0x68, "FMON_CLK_LAST_COUNT_REF_156" }, + { 0x6c, "REFERENCE_WINDOW_WIDTH_REF_156" }, +}; + static struct mlxbf_pmc_context *pmc; /* UUID used to probe ATF service. */ @@ -1032,6 +1066,9 @@ static const struct mlxbf_pmc_events *mlxbf_pmc_event_list(const char *blk, size } else if (strstr(blk, "llt")) { events = mlxbf_pmc_llt_events; size = ARRAY_SIZE(mlxbf_pmc_llt_events); + } else if (strstr(blk, "clock_measure")) { + events = mlxbf_pmc_clock_events; + size = ARRAY_SIZE(mlxbf_pmc_clock_events); } else { events = NULL; size = 0; @@ -1168,7 +1205,7 @@ static int mlxbf_pmc_program_l3_counter(unsigned int blk_num, u32 cnt_num, u32 e /* Method to handle crspace counter programming */ static int mlxbf_pmc_program_crspace_counter(unsigned int blk_num, u32 cnt_num, u32 evt) { - void *addr; + void __iomem *addr; u32 word; int ret; @@ -1192,7 +1229,7 @@ static int mlxbf_pmc_program_crspace_counter(unsigned int blk_num, u32 cnt_num, /* Method to clear crspace counter value */ static int mlxbf_pmc_clear_crspace_counter(unsigned int blk_num, u32 cnt_num) { - void *addr; + void __iomem *addr; addr = pmc->block[blk_num].mmio_base + MLXBF_PMC_CRSPACE_PERFMON_VAL0(pmc->block[blk_num].counters) + @@ -1405,7 +1442,7 @@ static int mlxbf_pmc_read_l3_event(unsigned int blk_num, u32 cnt_num, u64 *resul static int mlxbf_pmc_read_crspace_event(unsigned int blk_num, u32 cnt_num, u64 *result) { u32 word, evt; - void *addr; + void __iomem *addr; int ret; addr = pmc->block[blk_num].mmio_base + @@ -1466,14 +1503,15 @@ static int mlxbf_pmc_read_event(unsigned int blk_num, u32 cnt_num, bool is_l3, u /* Method to read a register */ static int mlxbf_pmc_read_reg(unsigned int blk_num, u32 offset, u64 *result) { - u32 ecc_out; + u32 reg; - if (strstr(pmc->block_name[blk_num], "ecc")) { + if ((strstr(pmc->block_name[blk_num], "ecc")) || + (strstr(pmc->block_name[blk_num], "clock_measure"))) { if (mlxbf_pmc_readl(pmc->block[blk_num].mmio_base + offset, - &ecc_out)) + ®)) return -EFAULT; - *result = ecc_out; + *result = reg; return 0; } @@ -1487,6 +1525,9 @@ static int mlxbf_pmc_read_reg(unsigned int blk_num, u32 offset, u64 *result) /* Method to write to a register */ static int mlxbf_pmc_write_reg(unsigned int blk_num, u32 offset, u64 data) { + if (strstr(pmc->block_name[blk_num], "clock_measure")) + return -EINVAL; + if (strstr(pmc->block_name[blk_num], "ecc")) { return mlxbf_pmc_write(pmc->block[blk_num].mmio_base + offset, MLXBF_PMC_WRITE_REG_32, data); @@ -1763,6 +1804,49 @@ static ssize_t mlxbf_pmc_enable_store(struct device *dev, return count; } +/* Show function for "count_clock" sysfs files - only for crspace */ +static ssize_t mlxbf_pmc_count_clock_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mlxbf_pmc_attribute *attr_count_clock = container_of( + attr, struct mlxbf_pmc_attribute, dev_attr); + unsigned int blk_num; + u32 reg; + + blk_num = attr_count_clock->nr; + + if (mlxbf_pmc_readl(pmc->block[blk_num].mmio_base + + MLXBF_PMC_CRSPACE_PERFMON_COUNT_CLOCK(pmc->block[blk_num].counters), + ®)) + return -EINVAL; + + return sysfs_emit(buf, "%u\n", reg); +} + +/* Store function for "count_clock" sysfs files - only for crspace */ +static ssize_t mlxbf_pmc_count_clock_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mlxbf_pmc_attribute *attr_count_clock = container_of( + attr, struct mlxbf_pmc_attribute, dev_attr); + unsigned int blk_num; + u32 reg; + int err; + + blk_num = attr_count_clock->nr; + + err = kstrtouint(buf, 0, ®); + if (err < 0) + return err; + + mlxbf_pmc_write(pmc->block[blk_num].mmio_base + + MLXBF_PMC_CRSPACE_PERFMON_COUNT_CLOCK(pmc->block[blk_num].counters), + MLXBF_PMC_WRITE_REG_32, reg); + + return count; +} + /* Populate attributes for blocks with counters to monitor performance */ static int mlxbf_pmc_init_perftype_counter(struct device *dev, unsigned int blk_num) { @@ -1801,6 +1885,21 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, unsigned int blk_ attr = NULL; } + if (pmc->block[blk_num].type == MLXBF_PMC_TYPE_CRSPACE) { + /* Program crspace counters to count clock cycles using "count_clock" sysfs */ + attr = &pmc->block[blk_num].attr_count_clock; + attr->dev_attr.attr.mode = 0644; + attr->dev_attr.show = mlxbf_pmc_count_clock_show; + attr->dev_attr.store = mlxbf_pmc_count_clock_store; + attr->nr = blk_num; + attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL, + "count_clock"); + if (!attr->dev_attr.attr.name) + return -ENOMEM; + pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr; + attr = NULL; + } + pmc->block[blk_num].attr_counter = devm_kcalloc( dev, pmc->block[blk_num].counters, sizeof(struct mlxbf_pmc_attribute), GFP_KERNEL); diff --git a/drivers/platform/mellanox/mlxreg-hotplug.c b/drivers/platform/mellanox/mlxreg-hotplug.c index 6aa2a4650367..b347000e4329 100644 --- a/drivers/platform/mellanox/mlxreg-hotplug.c +++ b/drivers/platform/mellanox/mlxreg-hotplug.c @@ -232,7 +232,7 @@ static ssize_t mlxreg_hotplug_attr_show(struct device *dev, regval = !!(regval & data->mask); } - return sprintf(buf, "%u\n", regval); + return sysfs_emit(buf, "%u\n", regval); } #define PRIV_ATTR(i) priv->mlxreg_hotplug_attr[i] diff --git a/drivers/platform/mellanox/mlxreg-io.c b/drivers/platform/mellanox/mlxreg-io.c index 595276206baf..97fefe6c38d1 100644 --- a/drivers/platform/mellanox/mlxreg-io.c +++ b/drivers/platform/mellanox/mlxreg-io.c @@ -126,7 +126,7 @@ mlxreg_io_attr_show(struct device *dev, struct device_attribute *attr, mutex_unlock(&priv->io_lock); - return sprintf(buf, "%u\n", regval); + return sysfs_emit(buf, "%u\n", regval); access_error: mutex_unlock(&priv->io_lock); diff --git a/drivers/platform/surface/surface_platform_profile.c b/drivers/platform/surface/surface_platform_profile.c index 08db878f1d7d..0e479e35e66e 100644 --- a/drivers/platform/surface/surface_platform_profile.c +++ b/drivers/platform/surface/surface_platform_profile.c @@ -40,7 +40,7 @@ struct ssam_tmp_profile_info { struct ssam_platform_profile_device { struct ssam_device *sdev; - struct platform_profile_handler handler; + struct device *ppdev; bool has_fan; }; @@ -154,14 +154,14 @@ static int convert_profile_to_ssam_fan(struct ssam_device *sdev, enum platform_p } } -static int ssam_platform_profile_get(struct platform_profile_handler *pprof, +static int ssam_platform_profile_get(struct device *dev, enum platform_profile_option *profile) { struct ssam_platform_profile_device *tpd; enum ssam_tmp_profile tp; int status; - tpd = container_of(pprof, struct ssam_platform_profile_device, handler); + tpd = dev_get_drvdata(dev); status = ssam_tmp_profile_get(tpd->sdev, &tp); if (status) @@ -175,13 +175,13 @@ static int ssam_platform_profile_get(struct platform_profile_handler *pprof, return 0; } -static int ssam_platform_profile_set(struct platform_profile_handler *pprof, +static int ssam_platform_profile_set(struct device *dev, enum platform_profile_option profile) { struct ssam_platform_profile_device *tpd; int tp; - tpd = container_of(pprof, struct ssam_platform_profile_device, handler); + tpd = dev_get_drvdata(dev); tp = convert_profile_to_ssam_tmp(tpd->sdev, profile); if (tp < 0) @@ -201,6 +201,22 @@ static int ssam_platform_profile_set(struct platform_profile_handler *pprof, return tp; } +static int ssam_platform_profile_probe(void *drvdata, unsigned long *choices) +{ + set_bit(PLATFORM_PROFILE_LOW_POWER, choices); + set_bit(PLATFORM_PROFILE_BALANCED, choices); + set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices); + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + + return 0; +} + +static const struct platform_profile_ops ssam_platform_profile_ops = { + .probe = ssam_platform_profile_probe, + .profile_get = ssam_platform_profile_get, + .profile_set = ssam_platform_profile_set, +}; + static int surface_platform_profile_probe(struct ssam_device *sdev) { struct ssam_platform_profile_device *tpd; @@ -210,23 +226,14 @@ static int surface_platform_profile_probe(struct ssam_device *sdev) return -ENOMEM; tpd->sdev = sdev; - - tpd->handler.profile_get = ssam_platform_profile_get; - tpd->handler.profile_set = ssam_platform_profile_set; + ssam_device_set_drvdata(sdev, tpd); tpd->has_fan = device_property_read_bool(&sdev->dev, "has_fan"); - set_bit(PLATFORM_PROFILE_LOW_POWER, tpd->handler.choices); - set_bit(PLATFORM_PROFILE_BALANCED, tpd->handler.choices); - set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, tpd->handler.choices); - set_bit(PLATFORM_PROFILE_PERFORMANCE, tpd->handler.choices); + tpd->ppdev = devm_platform_profile_register(&sdev->dev, "Surface Platform Profile", + tpd, &ssam_platform_profile_ops); - return platform_profile_register(&tpd->handler); -} - -static void surface_platform_profile_remove(struct ssam_device *sdev) -{ - platform_profile_remove(); + return PTR_ERR_OR_ZERO(tpd->ppdev); } static const struct ssam_device_id ssam_platform_profile_match[] = { @@ -237,7 +244,6 @@ MODULE_DEVICE_TABLE(ssam, ssam_platform_profile_match); static struct ssam_device_driver surface_platform_profile = { .probe = surface_platform_profile_probe, - .remove = surface_platform_profile_remove, .match_table = ssam_platform_profile_match, .driver = { .name = "surface_platform_profile", diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index d09baa3d3d90..69336bd778ee 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -30,7 +30,10 @@ #include #include #include +#include +#include #include +#include MODULE_AUTHOR("Carlos Corbacho"); MODULE_DESCRIPTION("Acer Laptop WMI Extras Driver"); @@ -67,10 +70,16 @@ MODULE_LICENSE("GPL"); #define ACER_WMID_GET_GAMING_SYS_INFO_METHODID 5 #define ACER_WMID_SET_GAMING_FAN_BEHAVIOR 14 #define ACER_WMID_SET_GAMING_MISC_SETTING_METHODID 22 +#define ACER_WMID_GET_GAMING_MISC_SETTING_METHODID 23 -#define ACER_PREDATOR_V4_THERMAL_PROFILE_EC_OFFSET 0x54 +#define ACER_GAMING_MISC_SETTING_STATUS_MASK GENMASK_ULL(7, 0) +#define ACER_GAMING_MISC_SETTING_INDEX_MASK GENMASK_ULL(7, 0) +#define ACER_GAMING_MISC_SETTING_VALUE_MASK GENMASK_ULL(15, 8) -#define ACER_PREDATOR_V4_FAN_SPEED_READ_BIT_MASK GENMASK(20, 8) +#define ACER_PREDATOR_V4_RETURN_STATUS_BIT_MASK GENMASK_ULL(7, 0) +#define ACER_PREDATOR_V4_SENSOR_INDEX_BIT_MASK GENMASK_ULL(15, 8) +#define ACER_PREDATOR_V4_SENSOR_READING_BIT_MASK GENMASK_ULL(23, 8) +#define ACER_PREDATOR_V4_SUPPORTED_SENSORS_BIT_MASK GENMASK_ULL(39, 24) /* * Acer ACPI method GUIDs @@ -95,12 +104,33 @@ enum acer_wmi_event_ids { WMID_HOTKEY_EVENT = 0x1, WMID_ACCEL_OR_KBD_DOCK_EVENT = 0x5, WMID_GAMING_TURBO_KEY_EVENT = 0x7, + WMID_AC_EVENT = 0x8, }; enum acer_wmi_predator_v4_sys_info_command { - ACER_WMID_CMD_GET_PREDATOR_V4_BAT_STATUS = 0x02, - ACER_WMID_CMD_GET_PREDATOR_V4_CPU_FAN_SPEED = 0x0201, - ACER_WMID_CMD_GET_PREDATOR_V4_GPU_FAN_SPEED = 0x0601, + ACER_WMID_CMD_GET_PREDATOR_V4_SUPPORTED_SENSORS = 0x0000, + ACER_WMID_CMD_GET_PREDATOR_V4_SENSOR_READING = 0x0001, + ACER_WMID_CMD_GET_PREDATOR_V4_BAT_STATUS = 0x0002, +}; + +enum acer_wmi_predator_v4_sensor_id { + ACER_WMID_SENSOR_CPU_TEMPERATURE = 0x01, + ACER_WMID_SENSOR_CPU_FAN_SPEED = 0x02, + ACER_WMID_SENSOR_EXTERNAL_TEMPERATURE_2 = 0x03, + ACER_WMID_SENSOR_GPU_FAN_SPEED = 0x06, + ACER_WMID_SENSOR_GPU_TEMPERATURE = 0x0A, +}; + +enum acer_wmi_predator_v4_oc { + ACER_WMID_OC_NORMAL = 0x0000, + ACER_WMID_OC_TURBO = 0x0002, +}; + +enum acer_wmi_gaming_misc_setting { + ACER_WMID_MISC_SETTING_OC_1 = 0x0005, + ACER_WMID_MISC_SETTING_OC_2 = 0x0007, + ACER_WMID_MISC_SETTING_SUPPORTED_PROFILES = 0x000A, + ACER_WMID_MISC_SETTING_PLATFORM_PROFILE = 0x000B, }; static const struct key_entry acer_wmi_keymap[] __initconst = { @@ -246,7 +276,7 @@ struct hotkey_function_type_aa { #define ACER_CAP_TURBO_LED BIT(8) #define ACER_CAP_TURBO_FAN BIT(9) #define ACER_CAP_PLATFORM_PROFILE BIT(10) -#define ACER_CAP_FAN_SPEED_READ BIT(11) +#define ACER_CAP_HWMON BIT(11) /* * Interface type flags @@ -271,6 +301,7 @@ static u16 commun_func_bitmap; static u8 commun_fn_key_number; static bool cycle_gaming_thermal_profile = true; static bool predator_v4; +static u64 supported_sensors; module_param(mailled, int, 0444); module_param(brightness, int, 0444); @@ -358,7 +389,7 @@ static void __init set_quirks(void) if (quirks->predator_v4) interface->capability |= ACER_CAP_PLATFORM_PROFILE | - ACER_CAP_FAN_SPEED_READ; + ACER_CAP_HWMON; } static int __init dmi_matched(const struct dmi_system_id *dmi) @@ -393,6 +424,20 @@ static struct quirk_entry quirk_acer_predator_ph315_53 = { .gpu_fans = 1, }; +static struct quirk_entry quirk_acer_predator_ph16_72 = { + .turbo = 1, + .cpu_fans = 1, + .gpu_fans = 1, + .predator_v4 = 1, +}; + +static struct quirk_entry quirk_acer_predator_pt14_51 = { + .turbo = 1, + .cpu_fans = 1, + .gpu_fans = 1, + .predator_v4 = 1, +}; + static struct quirk_entry quirk_acer_predator_v4 = { .predator_v4 = 1, }; @@ -564,6 +609,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = { }, .driver_data = &quirk_acer_travelmate_2490, }, + { + .callback = dmi_matched, + .ident = "Acer Nitro AN515-58", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Nitro AN515-58"), + }, + .driver_data = &quirk_acer_predator_v4, + }, { .callback = dmi_matched, .ident = "Acer Predator PH315-53", @@ -591,6 +645,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = { }, .driver_data = &quirk_acer_predator_v4, }, + { + .callback = dmi_matched, + .ident = "Acer Predator PH16-72", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Predator PH16-72"), + }, + .driver_data = &quirk_acer_predator_ph16_72, + }, { .callback = dmi_matched, .ident = "Acer Predator PH18-71", @@ -600,6 +663,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = { }, .driver_data = &quirk_acer_predator_v4, }, + { + .callback = dmi_matched, + .ident = "Acer Predator PT14-51", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Predator PT14-51"), + }, + .driver_data = &quirk_acer_predator_pt14_51, + }, { .callback = set_force_caps, .ident = "Acer Aspire Switch 10E SW3-016", @@ -713,29 +785,24 @@ static const struct dmi_system_id non_acer_quirks[] __initconst = { {} }; -static struct platform_profile_handler platform_profile_handler; +static struct device *platform_profile_device; static bool platform_profile_support; /* * The profile used before turbo mode. This variable is needed for * returning from turbo mode when the mode key is in toggle mode. */ -static int last_non_turbo_profile; +static int last_non_turbo_profile = INT_MIN; -enum acer_predator_v4_thermal_profile_ec { - ACER_PREDATOR_V4_THERMAL_PROFILE_ECO = 0x04, - ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO = 0x03, - ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE = 0x02, - ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET = 0x01, - ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED = 0x00, -}; +/* The most performant supported profile */ +static int acer_predator_v4_max_perf; -enum acer_predator_v4_thermal_profile_wmi { - ACER_PREDATOR_V4_THERMAL_PROFILE_ECO_WMI = 0x060B, - ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI = 0x050B, - ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE_WMI = 0x040B, - ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET_WMI = 0x0B, - ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI = 0x010B, +enum acer_predator_v4_thermal_profile { + ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET = 0x00, + ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED = 0x01, + ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE = 0x04, + ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO = 0x05, + ACER_PREDATOR_V4_THERMAL_PROFILE_ECO = 0x06, }; /* Find which quirks are needed for a particular vendor/ model pair */ @@ -1448,6 +1515,45 @@ WMI_gaming_execute_u64(u32 method_id, u64 in, u64 *out) return status; } +static int WMI_gaming_execute_u32_u64(u32 method_id, u32 in, u64 *out) +{ + struct acpi_buffer result = { ACPI_ALLOCATE_BUFFER, NULL }; + struct acpi_buffer input = { + .length = sizeof(in), + .pointer = &in, + }; + union acpi_object *obj; + acpi_status status; + int ret = 0; + + status = wmi_evaluate_method(WMID_GUID4, 0, method_id, &input, &result); + if (ACPI_FAILURE(status)) + return -EIO; + + obj = result.pointer; + if (obj && out) { + switch (obj->type) { + case ACPI_TYPE_INTEGER: + *out = obj->integer.value; + break; + case ACPI_TYPE_BUFFER: + if (obj->buffer.length < sizeof(*out)) + ret = -ENOMSG; + else + *out = get_unaligned_le64(obj->buffer.pointer); + + break; + default: + ret = -ENOMSG; + break; + } + } + + kfree(obj); + + return ret; +} + static acpi_status WMID_gaming_set_u64(u64 value, u32 cap) { u32 method_id = 0; @@ -1462,9 +1568,6 @@ static acpi_status WMID_gaming_set_u64(u64 value, u32 cap) case ACER_CAP_TURBO_FAN: method_id = ACER_WMID_SET_GAMING_FAN_BEHAVIOR; break; - case ACER_CAP_TURBO_OC: - method_id = ACER_WMID_SET_GAMING_MISC_SETTING_METHODID; - break; default: return AE_BAD_PARAMETER; } @@ -1497,6 +1600,24 @@ static acpi_status WMID_gaming_get_u64(u64 *value, u32 cap) return status; } +static int WMID_gaming_get_sys_info(u32 command, u64 *out) +{ + acpi_status status; + u64 result; + + status = WMI_gaming_execute_u64(ACER_WMID_GET_GAMING_SYS_INFO_METHODID, command, &result); + if (ACPI_FAILURE(status)) + return -EIO; + + /* The return status must be zero for the operation to have succeeded */ + if (FIELD_GET(ACER_PREDATOR_V4_RETURN_STATUS_BIT_MASK, result)) + return -EIO; + + *out = result; + + return 0; +} + static void WMID_gaming_set_fan_mode(u8 fan_mode) { /* fan_mode = 1 is used for auto, fan_mode = 2 used for turbo*/ @@ -1518,6 +1639,48 @@ static void WMID_gaming_set_fan_mode(u8 fan_mode) WMID_gaming_set_u64(gpu_fan_config2 | gpu_fan_config1 << 16, ACER_CAP_TURBO_FAN); } +static int WMID_gaming_set_misc_setting(enum acer_wmi_gaming_misc_setting setting, u8 value) +{ + acpi_status status; + u64 input = 0; + u64 result; + + input |= FIELD_PREP(ACER_GAMING_MISC_SETTING_INDEX_MASK, setting); + input |= FIELD_PREP(ACER_GAMING_MISC_SETTING_VALUE_MASK, value); + + status = WMI_gaming_execute_u64(ACER_WMID_SET_GAMING_MISC_SETTING_METHODID, input, &result); + if (ACPI_FAILURE(status)) + return -EIO; + + /* The return status must be zero for the operation to have succeeded */ + if (FIELD_GET(ACER_GAMING_MISC_SETTING_STATUS_MASK, result)) + return -EIO; + + return 0; +} + +static int WMID_gaming_get_misc_setting(enum acer_wmi_gaming_misc_setting setting, u8 *value) +{ + u64 input = 0; + u64 result; + int ret; + + input |= FIELD_PREP(ACER_GAMING_MISC_SETTING_INDEX_MASK, setting); + + ret = WMI_gaming_execute_u32_u64(ACER_WMID_GET_GAMING_MISC_SETTING_METHODID, input, + &result); + if (ret < 0) + return ret; + + /* The return status must be zero for the operation to have succeeded */ + if (FIELD_GET(ACER_GAMING_MISC_SETTING_STATUS_MASK, result)) + return -EIO; + + *value = FIELD_GET(ACER_GAMING_MISC_SETTING_VALUE_MASK, result); + + return 0; +} + /* * Generic Device (interface-independent) */ @@ -1744,26 +1907,6 @@ static int acer_gsensor_event(void) return 0; } -static int acer_get_fan_speed(int fan) -{ - if (quirks->predator_v4) { - acpi_status status; - u64 fanspeed; - - status = WMI_gaming_execute_u64( - ACER_WMID_GET_GAMING_SYS_INFO_METHODID, - fan == 0 ? ACER_WMID_CMD_GET_PREDATOR_V4_CPU_FAN_SPEED : - ACER_WMID_CMD_GET_PREDATOR_V4_GPU_FAN_SPEED, - &fanspeed); - - if (ACPI_FAILURE(status)) - return -EIO; - - return FIELD_GET(ACER_PREDATOR_V4_FAN_SPEED_READ_BIT_MASK, fanspeed); - } - return -EOPNOTSUPP; -} - /* * Predator series turbo button */ @@ -1783,8 +1926,12 @@ static int acer_toggle_turbo(void) WMID_gaming_set_fan_mode(0x1); /* Set OC to normal */ - WMID_gaming_set_u64(0x5, ACER_CAP_TURBO_OC); - WMID_gaming_set_u64(0x7, ACER_CAP_TURBO_OC); + if (has_cap(ACER_CAP_TURBO_OC)) { + WMID_gaming_set_misc_setting(ACER_WMID_MISC_SETTING_OC_1, + ACER_WMID_OC_NORMAL); + WMID_gaming_set_misc_setting(ACER_WMID_MISC_SETTING_OC_2, + ACER_WMID_OC_NORMAL); + } } else { /* Turn on turbo led */ WMID_gaming_set_u64(0x10001, ACER_CAP_TURBO_LED); @@ -1793,22 +1940,25 @@ static int acer_toggle_turbo(void) WMID_gaming_set_fan_mode(0x2); /* Set OC to turbo mode */ - WMID_gaming_set_u64(0x205, ACER_CAP_TURBO_OC); - WMID_gaming_set_u64(0x207, ACER_CAP_TURBO_OC); + if (has_cap(ACER_CAP_TURBO_OC)) { + WMID_gaming_set_misc_setting(ACER_WMID_MISC_SETTING_OC_1, + ACER_WMID_OC_TURBO); + WMID_gaming_set_misc_setting(ACER_WMID_MISC_SETTING_OC_2, + ACER_WMID_OC_TURBO); + } } return turbo_led_state; } static int -acer_predator_v4_platform_profile_get(struct platform_profile_handler *pprof, +acer_predator_v4_platform_profile_get(struct device *dev, enum platform_profile_option *profile) { u8 tp; int err; - err = ec_read(ACER_PREDATOR_V4_THERMAL_PROFILE_EC_OFFSET, &tp); - - if (err < 0) + err = WMID_gaming_get_misc_setting(ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, &tp); + if (err) return err; switch (tp) { @@ -1835,74 +1985,112 @@ acer_predator_v4_platform_profile_get(struct platform_profile_handler *pprof, } static int -acer_predator_v4_platform_profile_set(struct platform_profile_handler *pprof, +acer_predator_v4_platform_profile_set(struct device *dev, enum platform_profile_option profile) { - int tp; - acpi_status status; + int err, tp; switch (profile) { case PLATFORM_PROFILE_PERFORMANCE: - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI; + tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO; break; case PLATFORM_PROFILE_BALANCED_PERFORMANCE: - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE_WMI; + tp = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE; break; case PLATFORM_PROFILE_BALANCED: - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI; + tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED; break; case PLATFORM_PROFILE_QUIET: - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET_WMI; + tp = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET; break; case PLATFORM_PROFILE_LOW_POWER: - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO_WMI; + tp = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO; break; default: return -EOPNOTSUPP; } - status = WMI_gaming_execute_u64( - ACER_WMID_SET_GAMING_MISC_SETTING_METHODID, tp, NULL); + err = WMID_gaming_set_misc_setting(ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, tp); + if (err) + return err; - if (ACPI_FAILURE(status)) - return -EIO; - - if (tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI) + if (tp != acer_predator_v4_max_perf) last_non_turbo_profile = tp; return 0; } -static int acer_platform_profile_setup(void) +static int +acer_predator_v4_platform_profile_probe(void *drvdata, unsigned long *choices) +{ + unsigned long supported_profiles; + int err; + + err = WMID_gaming_get_misc_setting(ACER_WMID_MISC_SETTING_SUPPORTED_PROFILES, + (u8 *)&supported_profiles); + if (err) + return err; + + /* Iterate through supported profiles in order of increasing performance */ + if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_ECO, &supported_profiles)) { + set_bit(PLATFORM_PROFILE_LOW_POWER, choices); + acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO; + last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO; + } + + if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET, &supported_profiles)) { + set_bit(PLATFORM_PROFILE_QUIET, choices); + acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET; + last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET; + } + + if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED, &supported_profiles)) { + set_bit(PLATFORM_PROFILE_BALANCED, choices); + acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED; + last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED; + } + + if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE, &supported_profiles)) { + set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices); + acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE; + + /* We only use this profile as a fallback option in case no prior + * profile is supported. + */ + if (last_non_turbo_profile < 0) + last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE; + } + + if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO, &supported_profiles)) { + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO; + + /* We need to handle the hypothetical case where only the turbo profile + * is supported. In this case the turbo toggle will essentially be a + * no-op. + */ + if (last_non_turbo_profile < 0) + last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO; + } + + return 0; +} + +static const struct platform_profile_ops acer_predator_v4_platform_profile_ops = { + .probe = acer_predator_v4_platform_profile_probe, + .profile_get = acer_predator_v4_platform_profile_get, + .profile_set = acer_predator_v4_platform_profile_set, +}; + +static int acer_platform_profile_setup(struct platform_device *device) { if (quirks->predator_v4) { - int err; - - platform_profile_handler.profile_get = - acer_predator_v4_platform_profile_get; - platform_profile_handler.profile_set = - acer_predator_v4_platform_profile_set; - - set_bit(PLATFORM_PROFILE_PERFORMANCE, - platform_profile_handler.choices); - set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, - platform_profile_handler.choices); - set_bit(PLATFORM_PROFILE_BALANCED, - platform_profile_handler.choices); - set_bit(PLATFORM_PROFILE_QUIET, - platform_profile_handler.choices); - set_bit(PLATFORM_PROFILE_LOW_POWER, - platform_profile_handler.choices); - - err = platform_profile_register(&platform_profile_handler); - if (err) - return err; + platform_profile_device = devm_platform_profile_register( + &device->dev, "acer-wmi", NULL, &acer_predator_v4_platform_profile_ops); + if (IS_ERR(platform_profile_device)) + return PTR_ERR(platform_profile_device); platform_profile_support = true; - - /* Set default non-turbo profile */ - last_non_turbo_profile = - ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI; } return 0; } @@ -1910,83 +2098,41 @@ static int acer_platform_profile_setup(void) static int acer_thermal_profile_change(void) { /* - * This mode key can rotate each mode or toggle turbo mode. - * On battery, only ECO and BALANCED mode are available. + * This mode key will either cycle through each mode or toggle the + * most performant profile. */ if (quirks->predator_v4) { u8 current_tp; - int tp, err; - u64 on_AC; - acpi_status status; + int err, tp; - err = ec_read(ACER_PREDATOR_V4_THERMAL_PROFILE_EC_OFFSET, - ¤t_tp); + if (cycle_gaming_thermal_profile) { + platform_profile_cycle(); + } else { + /* Do nothing if no suitable platform profiles where found */ + if (last_non_turbo_profile < 0) + return 0; - if (err < 0) - return err; + err = WMID_gaming_get_misc_setting( + ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, ¤t_tp); + if (err) + return err; - /* Check power source */ - status = WMI_gaming_execute_u64( - ACER_WMID_GET_GAMING_SYS_INFO_METHODID, - ACER_WMID_CMD_GET_PREDATOR_V4_BAT_STATUS, &on_AC); - - if (ACPI_FAILURE(status)) - return -EIO; - - switch (current_tp) { - case ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO: - if (!on_AC) - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI; - else if (cycle_gaming_thermal_profile) - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO_WMI; - else + if (current_tp == acer_predator_v4_max_perf) tp = last_non_turbo_profile; - break; - case ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE: - if (!on_AC) - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI; else - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI; - break; - case ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED: - if (!on_AC) - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO_WMI; - else if (cycle_gaming_thermal_profile) - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE_WMI; - else - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI; - break; - case ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET: - if (!on_AC) - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI; - else if (cycle_gaming_thermal_profile) - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI; - else - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI; - break; - case ACER_PREDATOR_V4_THERMAL_PROFILE_ECO: - if (!on_AC) - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED_WMI; - else if (cycle_gaming_thermal_profile) - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET_WMI; - else - tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI; - break; - default: - return -EOPNOTSUPP; + tp = acer_predator_v4_max_perf; + + err = WMID_gaming_set_misc_setting( + ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, tp); + if (err) + return err; + + /* Store last profile for toggle */ + if (current_tp != acer_predator_v4_max_perf) + last_non_turbo_profile = current_tp; + + platform_profile_notify(platform_profile_device); } - - status = WMI_gaming_execute_u64( - ACER_WMID_SET_GAMING_MISC_SETTING_METHODID, tp, NULL); - - if (ACPI_FAILURE(status)) - return -EIO; - - /* Store non-turbo profile for turbo mode toggle*/ - if (tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO_WMI) - last_non_turbo_profile = tp; - - platform_profile_notify(); } return 0; @@ -2280,6 +2426,9 @@ static void acer_wmi_notify(union acpi_object *obj, void *context) if (return_value.key_num == 0x5 && has_cap(ACER_CAP_PLATFORM_PROFILE)) acer_thermal_profile_change(); break; + case WMID_AC_EVENT: + /* We ignore AC events here */ + break; default: pr_warn("Unknown function number - %d - %d\n", return_value.function, return_value.key_num); @@ -2530,12 +2679,12 @@ static int acer_platform_probe(struct platform_device *device) goto error_rfkill; if (has_cap(ACER_CAP_PLATFORM_PROFILE)) { - err = acer_platform_profile_setup(); + err = acer_platform_profile_setup(device); if (err) goto error_platform_profile; } - if (has_cap(ACER_CAP_FAN_SPEED_READ)) { + if (has_cap(ACER_CAP_HWMON)) { err = acer_wmi_hwmon_init(); if (err) goto error_hwmon; @@ -2544,8 +2693,6 @@ static int acer_platform_probe(struct platform_device *device) return 0; error_hwmon: - if (platform_profile_support) - platform_profile_remove(); error_platform_profile: acer_rfkill_exit(); error_rfkill: @@ -2566,9 +2713,6 @@ static void acer_platform_remove(struct platform_device *device) acer_backlight_exit(); acer_rfkill_exit(); - - if (platform_profile_support) - platform_profile_remove(); } #ifdef CONFIG_PM_SLEEP @@ -2655,43 +2799,86 @@ static void __init create_debugfs(void) &interface->debug.wmid_devices); } +static const enum acer_wmi_predator_v4_sensor_id acer_wmi_temp_channel_to_sensor_id[] = { + [0] = ACER_WMID_SENSOR_CPU_TEMPERATURE, + [1] = ACER_WMID_SENSOR_GPU_TEMPERATURE, + [2] = ACER_WMID_SENSOR_EXTERNAL_TEMPERATURE_2, +}; + +static const enum acer_wmi_predator_v4_sensor_id acer_wmi_fan_channel_to_sensor_id[] = { + [0] = ACER_WMID_SENSOR_CPU_FAN_SPEED, + [1] = ACER_WMID_SENSOR_GPU_FAN_SPEED, +}; + static umode_t acer_wmi_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, int channel) { + enum acer_wmi_predator_v4_sensor_id sensor_id; + const u64 *supported_sensors = data; + switch (type) { + case hwmon_temp: + sensor_id = acer_wmi_temp_channel_to_sensor_id[channel]; + break; case hwmon_fan: - if (acer_get_fan_speed(channel) >= 0) - return 0444; + sensor_id = acer_wmi_fan_channel_to_sensor_id[channel]; break; default: return 0; } + if (*supported_sensors & BIT(sensor_id - 1)) + return 0444; + return 0; } static int acer_wmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { + u64 command = ACER_WMID_CMD_GET_PREDATOR_V4_SENSOR_READING; + u64 result; int ret; switch (type) { - case hwmon_fan: - ret = acer_get_fan_speed(channel); + case hwmon_temp: + command |= FIELD_PREP(ACER_PREDATOR_V4_SENSOR_INDEX_BIT_MASK, + acer_wmi_temp_channel_to_sensor_id[channel]); + + ret = WMID_gaming_get_sys_info(command, &result); if (ret < 0) return ret; - *val = ret; - break; + + result = FIELD_GET(ACER_PREDATOR_V4_SENSOR_READING_BIT_MASK, result); + *val = result * MILLIDEGREE_PER_DEGREE; + return 0; + case hwmon_fan: + command |= FIELD_PREP(ACER_PREDATOR_V4_SENSOR_INDEX_BIT_MASK, + acer_wmi_fan_channel_to_sensor_id[channel]); + + ret = WMID_gaming_get_sys_info(command, &result); + if (ret < 0) + return ret; + + *val = FIELD_GET(ACER_PREDATOR_V4_SENSOR_READING_BIT_MASK, result); + return 0; default: return -EOPNOTSUPP; } - - return 0; } static const struct hwmon_channel_info *const acer_wmi_hwmon_info[] = { - HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT, HWMON_F_INPUT), NULL + HWMON_CHANNEL_INFO(temp, + HWMON_T_INPUT, + HWMON_T_INPUT, + HWMON_T_INPUT + ), + HWMON_CHANNEL_INFO(fan, + HWMON_F_INPUT, + HWMON_F_INPUT + ), + NULL }; static const struct hwmon_ops acer_wmi_hwmon_ops = { @@ -2708,9 +2895,20 @@ static int acer_wmi_hwmon_init(void) { struct device *dev = &acer_platform_device->dev; struct device *hwmon; + u64 result; + int ret; + + ret = WMID_gaming_get_sys_info(ACER_WMID_CMD_GET_PREDATOR_V4_SUPPORTED_SENSORS, &result); + if (ret < 0) + return ret; + + /* Return early if no sensors are available */ + supported_sensors = FIELD_GET(ACER_PREDATOR_V4_SUPPORTED_SENSORS_BIT_MASK, result); + if (!supported_sensors) + return 0; hwmon = devm_hwmon_device_register_with_info(dev, "acer", - &acer_platform_driver, + &supported_sensors, &acer_wmi_hwmon_chip_info, NULL); diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c index e981d45e1c12..444b43be35a2 100644 --- a/drivers/platform/x86/amd/hsmp/acpi.c +++ b/drivers/platform/x86/amd/hsmp/acpi.c @@ -226,7 +226,7 @@ static int hsmp_parse_acpi_table(struct device *dev, u16 sock_ind) } static ssize_t hsmp_metric_tbl_acpi_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = container_of(kobj, struct device, kobj); @@ -285,19 +285,19 @@ static int init_acpi(struct device *dev) return ret; } -static struct bin_attribute hsmp_metric_tbl_attr = { +static const struct bin_attribute hsmp_metric_tbl_attr = { .attr = { .name = HSMP_METRICS_TABLE_NAME, .mode = 0444}, - .read = hsmp_metric_tbl_acpi_read, + .read_new = hsmp_metric_tbl_acpi_read, .size = sizeof(struct hsmp_metric_table), }; -static struct bin_attribute *hsmp_attr_list[] = { +static const struct bin_attribute *hsmp_attr_list[] = { &hsmp_metric_tbl_attr, NULL }; -static struct attribute_group hsmp_attr_grp = { - .bin_attrs = hsmp_attr_list, +static const struct attribute_group hsmp_attr_grp = { + .bin_attrs_new = hsmp_attr_list, .is_bin_visible = hsmp_is_sock_attr_visible, }; diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c index 227b4ad4a51a..03164e30b3a5 100644 --- a/drivers/platform/x86/amd/hsmp/hsmp.c +++ b/drivers/platform/x86/amd/hsmp/hsmp.c @@ -33,7 +33,13 @@ #define HSMP_WR true #define HSMP_RD false -#define DRIVER_VERSION "2.3" +#define DRIVER_VERSION "2.4" + +/* + * When same message numbers are used for both GET and SET operation, + * bit:31 indicates whether its SET or GET operation. + */ +#define CHECK_GET_BIT BIT(31) static struct hsmp_plat_device hsmp_pdev; @@ -167,11 +173,28 @@ static int validate_message(struct hsmp_message *msg) if (hsmp_msg_desc_table[msg->msg_id].type == HSMP_RSVD) return -ENOMSG; - /* num_args and response_sz against the HSMP spec */ - if (msg->num_args != hsmp_msg_desc_table[msg->msg_id].num_args || - msg->response_sz != hsmp_msg_desc_table[msg->msg_id].response_sz) + /* + * num_args passed by user should match the num_args specified in + * message description table. + */ + if (msg->num_args != hsmp_msg_desc_table[msg->msg_id].num_args) return -EINVAL; + /* + * Some older HSMP SET messages are updated to add GET in the same message. + * In these messages, GET returns the current value and SET also returns + * the successfully set value. To support this GET and SET in same message + * while maintaining backward compatibility for the HSMP users, + * hsmp_msg_desc_table[] indicates only maximum allowed response_sz. + */ + if (hsmp_msg_desc_table[msg->msg_id].type == HSMP_SET_GET) { + if (msg->response_sz > hsmp_msg_desc_table[msg->msg_id].response_sz) + return -EINVAL; + } else { + /* only HSMP_SET or HSMP_GET messages go through this strict check */ + if (msg->response_sz != hsmp_msg_desc_table[msg->msg_id].response_sz) + return -EINVAL; + } return 0; } @@ -239,6 +262,18 @@ int hsmp_test(u16 sock_ind, u32 value) } EXPORT_SYMBOL_NS_GPL(hsmp_test, "AMD_HSMP"); +static bool is_get_msg(struct hsmp_message *msg) +{ + if (hsmp_msg_desc_table[msg->msg_id].type == HSMP_GET) + return true; + + if (hsmp_msg_desc_table[msg->msg_id].type == HSMP_SET_GET && + (msg->args[0] & CHECK_GET_BIT)) + return true; + + return false; +} + long hsmp_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) { int __user *arguser = (int __user *)arg; @@ -261,7 +296,7 @@ long hsmp_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) * Device is opened in O_WRONLY mode * Execute only set/configure commands */ - if (hsmp_msg_desc_table[msg.msg_id].type != HSMP_SET) + if (is_get_msg(&msg)) return -EPERM; break; case FMODE_READ: @@ -269,7 +304,7 @@ long hsmp_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) * Device is opened in O_RDONLY mode * Execute only get/monitor commands */ - if (hsmp_msg_desc_table[msg.msg_id].type != HSMP_GET) + if (!is_get_msg(&msg)) return -EPERM; break; case FMODE_READ | FMODE_WRITE: diff --git a/drivers/platform/x86/amd/hsmp/plat.c b/drivers/platform/x86/amd/hsmp/plat.c index a61f815c9f80..02ca85762b68 100644 --- a/drivers/platform/x86/amd/hsmp/plat.c +++ b/drivers/platform/x86/amd/hsmp/plat.c @@ -59,7 +59,7 @@ static int amd_hsmp_pci_rdwr(struct hsmp_socket *sock, u32 offset, } static ssize_t hsmp_metric_tbl_plat_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct hsmp_socket *sock; @@ -97,13 +97,13 @@ static umode_t hsmp_is_sock_attr_visible(struct kobject *kobj, * is_bin_visible function is used to show / hide the necessary groups. */ #define HSMP_BIN_ATTR(index, _list) \ -static struct bin_attribute attr##index = { \ +static const struct bin_attribute attr##index = { \ .attr = { .name = HSMP_METRICS_TABLE_NAME, .mode = 0444}, \ .private = (void *)index, \ - .read = hsmp_metric_tbl_plat_read, \ + .read_new = hsmp_metric_tbl_plat_read, \ .size = sizeof(struct hsmp_metric_table), \ }; \ -static struct bin_attribute _list[] = { \ +static const struct bin_attribute _list[] = { \ &attr##index, \ NULL \ } @@ -118,8 +118,8 @@ HSMP_BIN_ATTR(6, *sock6_attr_list); HSMP_BIN_ATTR(7, *sock7_attr_list); #define HSMP_BIN_ATTR_GRP(index, _list, _name) \ -static struct attribute_group sock##index##_attr_grp = { \ - .bin_attrs = _list, \ +static const struct attribute_group sock##index##_attr_grp = { \ + .bin_attrs_new = _list, \ .is_bin_visible = hsmp_is_sock_attr_visible, \ .name = #_name, \ } diff --git a/drivers/platform/x86/amd/pmc/Kconfig b/drivers/platform/x86/amd/pmc/Kconfig index 94f9563d8be7..eeffdafd686e 100644 --- a/drivers/platform/x86/amd/pmc/Kconfig +++ b/drivers/platform/x86/amd/pmc/Kconfig @@ -5,7 +5,7 @@ config AMD_PMC tristate "AMD SoC PMC driver" - depends on ACPI && PCI && RTC_CLASS && AMD_NB + depends on ACPI && PCI && RTC_CLASS && AMD_NODE depends on SUSPEND select SERIO help diff --git a/drivers/platform/x86/amd/pmc/Makefile b/drivers/platform/x86/amd/pmc/Makefile index f1d9ab19d24c..255d94ddf999 100644 --- a/drivers/platform/x86/amd/pmc/Makefile +++ b/drivers/platform/x86/amd/pmc/Makefile @@ -4,6 +4,6 @@ # AMD Power Management Controller Driver # -amd-pmc-objs := pmc.o pmc-quirks.o +amd-pmc-objs := pmc.o pmc-quirks.o mp1_stb.o obj-$(CONFIG_AMD_PMC) += amd-pmc.o amd-pmc-$(CONFIG_AMD_MP2_STB) += mp2_stb.o diff --git a/drivers/platform/x86/amd/pmc/mp1_stb.c b/drivers/platform/x86/amd/pmc/mp1_stb.c new file mode 100644 index 000000000000..c005f00988f7 --- /dev/null +++ b/drivers/platform/x86/amd/pmc/mp1_stb.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD MP1 Smart Trace Buffer (STB) Layer + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Authors: Shyam Sundar S K + * Sanket Goswami + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include + +#include "pmc.h" + +/* STB Spill to DRAM Parameters */ +#define S2D_TELEMETRY_DRAMBYTES_MAX 0x1000000 +#define S2D_TELEMETRY_BYTES_MAX 0x100000U +#define S2D_RSVD_RAM_SPACE 0x100000 + +/* STB Registers */ +#define AMD_STB_PMI_0 0x03E30600 +#define AMD_PMC_STB_DUMMY_PC 0xC6000007 + +/* STB Spill to DRAM Message Definition */ +#define STB_FORCE_FLUSH_DATA 0xCF +#define FIFO_SIZE 4096 + +/* STB S2D(Spill to DRAM) has different message port offset */ +#define AMD_S2D_REGISTER_MESSAGE 0xA20 +#define AMD_S2D_REGISTER_RESPONSE 0xA80 +#define AMD_S2D_REGISTER_ARGUMENT 0xA88 + +/* STB S2D (Spill to DRAM) message port offset for 44h model */ +#define AMD_GNR_REGISTER_MESSAGE 0x524 +#define AMD_GNR_REGISTER_RESPONSE 0x570 +#define AMD_GNR_REGISTER_ARGUMENT 0xA40 + +static bool enable_stb; +module_param(enable_stb, bool, 0644); +MODULE_PARM_DESC(enable_stb, "Enable the STB debug mechanism"); + +static bool dump_custom_stb; +module_param(dump_custom_stb, bool, 0644); +MODULE_PARM_DESC(dump_custom_stb, "Enable to dump full STB buffer"); + +enum s2d_arg { + S2D_TELEMETRY_SIZE = 0x01, + S2D_PHYS_ADDR_LOW, + S2D_PHYS_ADDR_HIGH, + S2D_NUM_SAMPLES, + S2D_DRAM_SIZE, +}; + +struct amd_stb_v2_data { + size_t size; + u8 data[] __counted_by(size); +}; + +int amd_stb_write(struct amd_pmc_dev *dev, u32 data) +{ + int err; + + err = amd_smn_write(0, AMD_STB_PMI_0, data); + if (err) { + dev_err(dev->dev, "failed to write data in stb: 0x%X\n", AMD_STB_PMI_0); + return pcibios_err_to_errno(err); + } + + return 0; +} + +int amd_stb_read(struct amd_pmc_dev *dev, u32 *buf) +{ + int i, err; + + for (i = 0; i < FIFO_SIZE; i++) { + err = amd_smn_read(0, AMD_STB_PMI_0, buf++); + if (err) { + dev_err(dev->dev, "error reading data from stb: 0x%X\n", AMD_STB_PMI_0); + return pcibios_err_to_errno(err); + } + } + + return 0; +} + +static int amd_stb_debugfs_open(struct inode *inode, struct file *filp) +{ + struct amd_pmc_dev *dev = filp->f_inode->i_private; + u32 size = FIFO_SIZE * sizeof(u32); + u32 *buf; + int rc; + + buf = kzalloc(size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + rc = amd_stb_read(dev, buf); + if (rc) { + kfree(buf); + return rc; + } + + filp->private_data = buf; + return rc; +} + +static ssize_t amd_stb_debugfs_read(struct file *filp, char __user *buf, size_t size, loff_t *pos) +{ + if (!filp->private_data) + return -EINVAL; + + return simple_read_from_buffer(buf, size, pos, filp->private_data, + FIFO_SIZE * sizeof(u32)); +} + +static int amd_stb_debugfs_release(struct inode *inode, struct file *filp) +{ + kfree(filp->private_data); + return 0; +} + +static const struct file_operations amd_stb_debugfs_fops = { + .owner = THIS_MODULE, + .open = amd_stb_debugfs_open, + .read = amd_stb_debugfs_read, + .release = amd_stb_debugfs_release, +}; + +/* Enhanced STB Firmware Reporting Mechanism */ +static int amd_stb_handle_efr(struct file *filp) +{ + struct amd_pmc_dev *dev = filp->f_inode->i_private; + struct amd_stb_v2_data *stb_data_arr; + u32 fsize; + + fsize = dev->dram_size - S2D_RSVD_RAM_SPACE; + stb_data_arr = kmalloc(struct_size(stb_data_arr, data, fsize), GFP_KERNEL); + if (!stb_data_arr) + return -ENOMEM; + + stb_data_arr->size = fsize; + memcpy_fromio(stb_data_arr->data, dev->stb_virt_addr, fsize); + filp->private_data = stb_data_arr; + + return 0; +} + +static int amd_stb_debugfs_open_v2(struct inode *inode, struct file *filp) +{ + struct amd_pmc_dev *dev = filp->f_inode->i_private; + u32 fsize, num_samples, val, stb_rdptr_offset = 0; + struct amd_stb_v2_data *stb_data_arr; + int ret; + + /* Write dummy postcode while reading the STB buffer */ + ret = amd_stb_write(dev, AMD_PMC_STB_DUMMY_PC); + if (ret) + dev_err(dev->dev, "error writing to STB: %d\n", ret); + + /* Spill to DRAM num_samples uses separate SMU message port */ + dev->msg_port = MSG_PORT_S2D; + + ret = amd_pmc_send_cmd(dev, 0, &val, STB_FORCE_FLUSH_DATA, 1); + if (ret) + dev_dbg_once(dev->dev, "S2D force flush not supported: %d\n", ret); + + /* + * We have a custom stb size and the PMFW is supposed to give + * the enhanced dram size. Note that we land here only for the + * platforms that support enhanced dram size reporting. + */ + if (dump_custom_stb) + return amd_stb_handle_efr(filp); + + /* Get the num_samples to calculate the last push location */ + ret = amd_pmc_send_cmd(dev, S2D_NUM_SAMPLES, &num_samples, dev->stb_arg.s2d_msg_id, true); + /* Clear msg_port for other SMU operation */ + dev->msg_port = MSG_PORT_PMC; + if (ret) { + dev_err(dev->dev, "error: S2D_NUM_SAMPLES not supported : %d\n", ret); + return ret; + } + + fsize = min(num_samples, S2D_TELEMETRY_BYTES_MAX); + stb_data_arr = kmalloc(struct_size(stb_data_arr, data, fsize), GFP_KERNEL); + if (!stb_data_arr) + return -ENOMEM; + + stb_data_arr->size = fsize; + + /* + * Start capturing data from the last push location. + * This is for general cases, where the stb limits + * are meant for standard usage. + */ + if (num_samples > S2D_TELEMETRY_BYTES_MAX) { + /* First read oldest data starting 1 behind last write till end of ringbuffer */ + stb_rdptr_offset = num_samples % S2D_TELEMETRY_BYTES_MAX; + fsize = S2D_TELEMETRY_BYTES_MAX - stb_rdptr_offset; + + memcpy_fromio(stb_data_arr->data, dev->stb_virt_addr + stb_rdptr_offset, fsize); + /* Second copy the newer samples from offset 0 - last write */ + memcpy_fromio(stb_data_arr->data + fsize, dev->stb_virt_addr, stb_rdptr_offset); + } else { + memcpy_fromio(stb_data_arr->data, dev->stb_virt_addr, fsize); + } + + filp->private_data = stb_data_arr; + + return 0; +} + +static ssize_t amd_stb_debugfs_read_v2(struct file *filp, char __user *buf, size_t size, + loff_t *pos) +{ + struct amd_stb_v2_data *data = filp->private_data; + + return simple_read_from_buffer(buf, size, pos, data->data, data->size); +} + +static int amd_stb_debugfs_release_v2(struct inode *inode, struct file *filp) +{ + kfree(filp->private_data); + return 0; +} + +static const struct file_operations amd_stb_debugfs_fops_v2 = { + .owner = THIS_MODULE, + .open = amd_stb_debugfs_open_v2, + .read = amd_stb_debugfs_read_v2, + .release = amd_stb_debugfs_release_v2, +}; + +static void amd_stb_update_args(struct amd_pmc_dev *dev) +{ + if (cpu_feature_enabled(X86_FEATURE_ZEN5)) + switch (boot_cpu_data.x86_model) { + case 0x44: + dev->stb_arg.msg = AMD_GNR_REGISTER_MESSAGE; + dev->stb_arg.arg = AMD_GNR_REGISTER_ARGUMENT; + dev->stb_arg.resp = AMD_GNR_REGISTER_RESPONSE; + return; + default: + break; + } + + dev->stb_arg.msg = AMD_S2D_REGISTER_MESSAGE; + dev->stb_arg.arg = AMD_S2D_REGISTER_ARGUMENT; + dev->stb_arg.resp = AMD_S2D_REGISTER_RESPONSE; +} + +static bool amd_is_stb_supported(struct amd_pmc_dev *dev) +{ + switch (dev->cpu_id) { + case AMD_CPU_ID_YC: + case AMD_CPU_ID_CB: + if (boot_cpu_data.x86_model == 0x44) + dev->stb_arg.s2d_msg_id = 0x9B; + else + dev->stb_arg.s2d_msg_id = 0xBE; + break; + case AMD_CPU_ID_PS: + dev->stb_arg.s2d_msg_id = 0x85; + break; + case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT: + case PCI_DEVICE_ID_AMD_1AH_M60H_ROOT: + if (boot_cpu_data.x86_model == 0x70) + dev->stb_arg.s2d_msg_id = 0xF1; + else + dev->stb_arg.s2d_msg_id = 0xDE; + break; + default: + return false; + } + + amd_stb_update_args(dev); + return true; +} + +int amd_stb_s2d_init(struct amd_pmc_dev *dev) +{ + u32 phys_addr_low, phys_addr_hi; + u64 stb_phys_addr; + u32 size = 0; + int ret; + + if (!enable_stb) + return 0; + + if (amd_is_stb_supported(dev)) { + debugfs_create_file("stb_read", 0644, dev->dbgfs_dir, dev, + &amd_stb_debugfs_fops_v2); + } else { + debugfs_create_file("stb_read", 0644, dev->dbgfs_dir, dev, + &amd_stb_debugfs_fops); + return 0; + } + + /* Spill to DRAM feature uses separate SMU message port */ + dev->msg_port = MSG_PORT_S2D; + + amd_pmc_send_cmd(dev, S2D_TELEMETRY_SIZE, &size, dev->stb_arg.s2d_msg_id, true); + if (size != S2D_TELEMETRY_BYTES_MAX) + return -EIO; + + /* Get DRAM size */ + ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->stb_arg.s2d_msg_id, true); + if (ret || !dev->dram_size) + dev->dram_size = S2D_TELEMETRY_DRAMBYTES_MAX; + + /* Get STB DRAM address */ + amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_LOW, &phys_addr_low, dev->stb_arg.s2d_msg_id, true); + amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_HIGH, &phys_addr_hi, dev->stb_arg.s2d_msg_id, true); + + stb_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low); + + /* Clear msg_port for other SMU operation */ + dev->msg_port = MSG_PORT_PMC; + + dev->stb_virt_addr = devm_ioremap(dev->dev, stb_phys_addr, dev->dram_size); + if (!dev->stb_virt_addr) + return -ENOMEM; + + return 0; +} diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index 26b878ee5191..e6124498b195 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -10,8 +10,8 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include #include +#include #include #include #include @@ -28,6 +28,8 @@ #include #include +#include + #include "pmc.h" /* SMU communication registers */ @@ -40,24 +42,9 @@ #define AMD_PMC_SCRATCH_REG_1AH 0xF14 /* STB Registers */ -#define AMD_PMC_STB_PMI_0 0x03E30600 #define AMD_PMC_STB_S2IDLE_PREPARE 0xC6000001 #define AMD_PMC_STB_S2IDLE_RESTORE 0xC6000002 #define AMD_PMC_STB_S2IDLE_CHECK 0xC6000003 -#define AMD_PMC_STB_DUMMY_PC 0xC6000007 - -/* STB S2D(Spill to DRAM) has different message port offset */ -#define AMD_S2D_REGISTER_MESSAGE 0xA20 -#define AMD_S2D_REGISTER_RESPONSE 0xA80 -#define AMD_S2D_REGISTER_ARGUMENT 0xA88 - -/* STB Spill to DRAM Parameters */ -#define S2D_TELEMETRY_BYTES_MAX 0x100000U -#define S2D_RSVD_RAM_SPACE 0x100000 -#define S2D_TELEMETRY_DRAMBYTES_MAX 0x1000000 - -/* STB Spill to DRAM Message Definition */ -#define STB_FORCE_FLUSH_DATA 0xCF /* Base address of SMU for mapping physical address to virtual address */ #define AMD_PMC_MAPPING_SIZE 0x01000 @@ -97,7 +84,6 @@ #define DELAY_MIN_US 2000 #define DELAY_MAX_US 3000 -#define FIFO_SIZE 4096 enum amd_pmc_def { MSG_TEST = 0x01, @@ -105,24 +91,39 @@ enum amd_pmc_def { MSG_OS_HINT_RN, }; -enum s2d_arg { - S2D_TELEMETRY_SIZE = 0x01, - S2D_PHYS_ADDR_LOW, - S2D_PHYS_ADDR_HIGH, - S2D_NUM_SAMPLES, - S2D_DRAM_SIZE, -}; - -struct amd_pmc_stb_v2_data { - size_t size; - u8 data[] __counted_by(size); -}; - struct amd_pmc_bit_map { const char *name; u32 bit_mask; }; +static const struct amd_pmc_bit_map soc15_ip_blk_v2[] = { + {"DISPLAY", BIT(0)}, + {"CPU", BIT(1)}, + {"GFX", BIT(2)}, + {"VDD", BIT(3)}, + {"VDD_CCX", BIT(4)}, + {"ACP", BIT(5)}, + {"VCN_0", BIT(6)}, + {"VCN_1", BIT(7)}, + {"ISP", BIT(8)}, + {"NBIO", BIT(9)}, + {"DF", BIT(10)}, + {"USB3_0", BIT(11)}, + {"USB3_1", BIT(12)}, + {"LAPIC", BIT(13)}, + {"USB3_2", BIT(14)}, + {"USB4_RT0", BIT(15)}, + {"USB4_RT1", BIT(16)}, + {"USB4_0", BIT(17)}, + {"USB4_1", BIT(18)}, + {"MPM", BIT(19)}, + {"JPEG_0", BIT(20)}, + {"JPEG_1", BIT(21)}, + {"IPU", BIT(22)}, + {"UMSCH", BIT(23)}, + {"VPE", BIT(24)}, +}; + static const struct amd_pmc_bit_map soc15_ip_blk[] = { {"DISPLAY", BIT(0)}, {"CPU", BIT(1)}, @@ -146,25 +147,13 @@ static const struct amd_pmc_bit_map soc15_ip_blk[] = { {"IPU", BIT(19)}, {"UMSCH", BIT(20)}, {"VPE", BIT(21)}, - {} }; -static bool enable_stb; -module_param(enable_stb, bool, 0644); -MODULE_PARM_DESC(enable_stb, "Enable the STB debug mechanism"); - static bool disable_workarounds; module_param(disable_workarounds, bool, 0644); MODULE_PARM_DESC(disable_workarounds, "Disable workarounds for platform bugs"); -static bool dump_custom_stb; -module_param(dump_custom_stb, bool, 0644); -MODULE_PARM_DESC(dump_custom_stb, "Enable to dump full STB buffer"); - static struct amd_pmc_dev pmc; -static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret); -static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf); -static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data); static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset) { @@ -193,155 +182,6 @@ struct smu_metrics { u64 timecondition_notmet_totaltime[32]; } __packed; -static int amd_pmc_stb_debugfs_open(struct inode *inode, struct file *filp) -{ - struct amd_pmc_dev *dev = filp->f_inode->i_private; - u32 size = FIFO_SIZE * sizeof(u32); - u32 *buf; - int rc; - - buf = kzalloc(size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - rc = amd_pmc_read_stb(dev, buf); - if (rc) { - kfree(buf); - return rc; - } - - filp->private_data = buf; - return rc; -} - -static ssize_t amd_pmc_stb_debugfs_read(struct file *filp, char __user *buf, size_t size, - loff_t *pos) -{ - if (!filp->private_data) - return -EINVAL; - - return simple_read_from_buffer(buf, size, pos, filp->private_data, - FIFO_SIZE * sizeof(u32)); -} - -static int amd_pmc_stb_debugfs_release(struct inode *inode, struct file *filp) -{ - kfree(filp->private_data); - return 0; -} - -static const struct file_operations amd_pmc_stb_debugfs_fops = { - .owner = THIS_MODULE, - .open = amd_pmc_stb_debugfs_open, - .read = amd_pmc_stb_debugfs_read, - .release = amd_pmc_stb_debugfs_release, -}; - -/* Enhanced STB Firmware Reporting Mechanism */ -static int amd_pmc_stb_handle_efr(struct file *filp) -{ - struct amd_pmc_dev *dev = filp->f_inode->i_private; - struct amd_pmc_stb_v2_data *stb_data_arr; - u32 fsize; - - fsize = dev->dram_size - S2D_RSVD_RAM_SPACE; - stb_data_arr = kmalloc(struct_size(stb_data_arr, data, fsize), GFP_KERNEL); - if (!stb_data_arr) - return -ENOMEM; - - stb_data_arr->size = fsize; - memcpy_fromio(stb_data_arr->data, dev->stb_virt_addr, fsize); - filp->private_data = stb_data_arr; - - return 0; -} - -static int amd_pmc_stb_debugfs_open_v2(struct inode *inode, struct file *filp) -{ - struct amd_pmc_dev *dev = filp->f_inode->i_private; - u32 fsize, num_samples, val, stb_rdptr_offset = 0; - struct amd_pmc_stb_v2_data *stb_data_arr; - int ret; - - /* Write dummy postcode while reading the STB buffer */ - ret = amd_pmc_write_stb(dev, AMD_PMC_STB_DUMMY_PC); - if (ret) - dev_err(dev->dev, "error writing to STB: %d\n", ret); - - /* Spill to DRAM num_samples uses separate SMU message port */ - dev->msg_port = 1; - - ret = amd_pmc_send_cmd(dev, 0, &val, STB_FORCE_FLUSH_DATA, 1); - if (ret) - dev_dbg_once(dev->dev, "S2D force flush not supported: %d\n", ret); - - /* - * We have a custom stb size and the PMFW is supposed to give - * the enhanced dram size. Note that we land here only for the - * platforms that support enhanced dram size reporting. - */ - if (dump_custom_stb) - return amd_pmc_stb_handle_efr(filp); - - /* Get the num_samples to calculate the last push location */ - ret = amd_pmc_send_cmd(dev, S2D_NUM_SAMPLES, &num_samples, dev->s2d_msg_id, true); - /* Clear msg_port for other SMU operation */ - dev->msg_port = 0; - if (ret) { - dev_err(dev->dev, "error: S2D_NUM_SAMPLES not supported : %d\n", ret); - return ret; - } - - fsize = min(num_samples, S2D_TELEMETRY_BYTES_MAX); - stb_data_arr = kmalloc(struct_size(stb_data_arr, data, fsize), GFP_KERNEL); - if (!stb_data_arr) - return -ENOMEM; - - stb_data_arr->size = fsize; - - /* - * Start capturing data from the last push location. - * This is for general cases, where the stb limits - * are meant for standard usage. - */ - if (num_samples > S2D_TELEMETRY_BYTES_MAX) { - /* First read oldest data starting 1 behind last write till end of ringbuffer */ - stb_rdptr_offset = num_samples % S2D_TELEMETRY_BYTES_MAX; - fsize = S2D_TELEMETRY_BYTES_MAX - stb_rdptr_offset; - - memcpy_fromio(stb_data_arr->data, dev->stb_virt_addr + stb_rdptr_offset, fsize); - /* Second copy the newer samples from offset 0 - last write */ - memcpy_fromio(stb_data_arr->data + fsize, dev->stb_virt_addr, stb_rdptr_offset); - } else { - memcpy_fromio(stb_data_arr->data, dev->stb_virt_addr, fsize); - } - - filp->private_data = stb_data_arr; - - return 0; -} - -static ssize_t amd_pmc_stb_debugfs_read_v2(struct file *filp, char __user *buf, size_t size, - loff_t *pos) -{ - struct amd_pmc_stb_v2_data *data = filp->private_data; - - return simple_read_from_buffer(buf, size, pos, data->data, data->size); -} - -static int amd_pmc_stb_debugfs_release_v2(struct inode *inode, struct file *filp) -{ - kfree(filp->private_data); - return 0; -} - -static const struct file_operations amd_pmc_stb_debugfs_fops_v2 = { - .owner = THIS_MODULE, - .open = amd_pmc_stb_debugfs_open_v2, - .read = amd_pmc_stb_debugfs_read_v2, - .release = amd_pmc_stb_debugfs_release_v2, -}; - static void amd_pmc_get_ip_info(struct amd_pmc_dev *dev) { switch (dev->cpu_id) { @@ -350,18 +190,23 @@ static void amd_pmc_get_ip_info(struct amd_pmc_dev *dev) case AMD_CPU_ID_YC: case AMD_CPU_ID_CB: dev->num_ips = 12; - dev->s2d_msg_id = 0xBE; + dev->ips_ptr = soc15_ip_blk; dev->smu_msg = 0x538; break; case AMD_CPU_ID_PS: dev->num_ips = 21; - dev->s2d_msg_id = 0x85; + dev->ips_ptr = soc15_ip_blk; dev->smu_msg = 0x538; break; case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT: case PCI_DEVICE_ID_AMD_1AH_M60H_ROOT: - dev->num_ips = 22; - dev->s2d_msg_id = 0xDE; + if (boot_cpu_data.x86_model == 0x70) { + dev->num_ips = ARRAY_SIZE(soc15_ip_blk_v2); + dev->ips_ptr = soc15_ip_blk_v2; + } else { + dev->num_ips = ARRAY_SIZE(soc15_ip_blk); + dev->ips_ptr = soc15_ip_blk; + } dev->smu_msg = 0x938; break; } @@ -529,8 +374,8 @@ static int smu_fw_info_show(struct seq_file *s, void *unused) seq_puts(s, "\n=== Active time (in us) ===\n"); for (idx = 0 ; idx < dev->num_ips ; idx++) { - if (soc15_ip_blk[idx].bit_mask & dev->active_ips) - seq_printf(s, "%-8s : %lld\n", soc15_ip_blk[idx].name, + if (dev->ips_ptr[idx].bit_mask & dev->active_ips) + seq_printf(s, "%-8s : %lld\n", dev->ips_ptr[idx].name, table.timecondition_notmet_lastcapture[idx]); } @@ -625,20 +470,6 @@ static void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev) debugfs_remove_recursive(dev->dbgfs_dir); } -static bool amd_pmc_is_stb_supported(struct amd_pmc_dev *dev) -{ - switch (dev->cpu_id) { - case AMD_CPU_ID_YC: - case AMD_CPU_ID_CB: - case AMD_CPU_ID_PS: - case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT: - case PCI_DEVICE_ID_AMD_1AH_M60H_ROOT: - return true; - default: - return false; - } -} - static void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev) { dev->dbgfs_dir = debugfs_create_dir("amd_pmc", NULL); @@ -648,14 +479,17 @@ static void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev) &s0ix_stats_fops); debugfs_create_file("amd_pmc_idlemask", 0644, dev->dbgfs_dir, dev, &amd_pmc_idlemask_fops); - /* Enable STB only when the module_param is set */ - if (enable_stb) { - if (amd_pmc_is_stb_supported(dev)) - debugfs_create_file("stb_read", 0644, dev->dbgfs_dir, dev, - &amd_pmc_stb_debugfs_fops_v2); - else - debugfs_create_file("stb_read", 0644, dev->dbgfs_dir, dev, - &amd_pmc_stb_debugfs_fops); +} + +static char *amd_pmc_get_msg_port(struct amd_pmc_dev *dev) +{ + switch (dev->msg_port) { + case MSG_PORT_PMC: + return "PMC"; + case MSG_PORT_S2D: + return "S2D"; + default: + return "Invalid message port"; } } @@ -663,10 +497,10 @@ static void amd_pmc_dump_registers(struct amd_pmc_dev *dev) { u32 value, message, argument, response; - if (dev->msg_port) { - message = AMD_S2D_REGISTER_MESSAGE; - argument = AMD_S2D_REGISTER_ARGUMENT; - response = AMD_S2D_REGISTER_RESPONSE; + if (dev->msg_port == MSG_PORT_S2D) { + message = dev->stb_arg.msg; + argument = dev->stb_arg.arg; + response = dev->stb_arg.resp; } else { message = dev->smu_msg; argument = AMD_PMC_REGISTER_ARGUMENT; @@ -674,26 +508,26 @@ static void amd_pmc_dump_registers(struct amd_pmc_dev *dev) } value = amd_pmc_reg_read(dev, response); - dev_dbg(dev->dev, "AMD_%s_REGISTER_RESPONSE:%x\n", dev->msg_port ? "S2D" : "PMC", value); + dev_dbg(dev->dev, "AMD_%s_REGISTER_RESPONSE:%x\n", amd_pmc_get_msg_port(dev), value); value = amd_pmc_reg_read(dev, argument); - dev_dbg(dev->dev, "AMD_%s_REGISTER_ARGUMENT:%x\n", dev->msg_port ? "S2D" : "PMC", value); + dev_dbg(dev->dev, "AMD_%s_REGISTER_ARGUMENT:%x\n", amd_pmc_get_msg_port(dev), value); value = amd_pmc_reg_read(dev, message); - dev_dbg(dev->dev, "AMD_%s_REGISTER_MESSAGE:%x\n", dev->msg_port ? "S2D" : "PMC", value); + dev_dbg(dev->dev, "AMD_%s_REGISTER_MESSAGE:%x\n", amd_pmc_get_msg_port(dev), value); } -static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret) +int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret) { int rc; u32 val, message, argument, response; - mutex_lock(&dev->lock); + guard(mutex)(&dev->lock); - if (dev->msg_port) { - message = AMD_S2D_REGISTER_MESSAGE; - argument = AMD_S2D_REGISTER_ARGUMENT; - response = AMD_S2D_REGISTER_RESPONSE; + if (dev->msg_port == MSG_PORT_S2D) { + message = dev->stb_arg.msg; + argument = dev->stb_arg.arg; + response = dev->stb_arg.resp; } else { message = dev->smu_msg; argument = AMD_PMC_REGISTER_ARGUMENT; @@ -706,7 +540,7 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX); if (rc) { dev_err(dev->dev, "failed to talk to SMU\n"); - goto out_unlock; + return rc; } /* Write zero to response register */ @@ -724,7 +558,7 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX); if (rc) { dev_err(dev->dev, "SMU response timed out\n"); - goto out_unlock; + return rc; } switch (val) { @@ -738,21 +572,19 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, case AMD_PMC_RESULT_CMD_REJECT_BUSY: dev_err(dev->dev, "SMU not ready. err: 0x%x\n", val); rc = -EBUSY; - goto out_unlock; + break; case AMD_PMC_RESULT_CMD_UNKNOWN: dev_err(dev->dev, "SMU cmd unknown. err: 0x%x\n", val); rc = -EINVAL; - goto out_unlock; + break; case AMD_PMC_RESULT_CMD_REJECT_PREREQ: case AMD_PMC_RESULT_FAILED: default: dev_err(dev->dev, "SMU cmd failed. err: 0x%x\n", val); rc = -EIO; - goto out_unlock; + break; } -out_unlock: - mutex_unlock(&dev->lock); amd_pmc_dump_registers(dev); return rc; } @@ -881,7 +713,7 @@ static void amd_pmc_s2idle_prepare(void) return; } - rc = amd_pmc_write_stb(pdev, AMD_PMC_STB_S2IDLE_PREPARE); + rc = amd_stb_write(pdev, AMD_PMC_STB_S2IDLE_PREPARE); if (rc) dev_err(pdev->dev, "error writing to STB: %d\n", rc); } @@ -900,7 +732,7 @@ static void amd_pmc_s2idle_check(void) /* Dump the IdleMask before we add to the STB */ amd_pmc_idlemask_read(pdev, pdev->dev, NULL); - rc = amd_pmc_write_stb(pdev, AMD_PMC_STB_S2IDLE_CHECK); + rc = amd_stb_write(pdev, AMD_PMC_STB_S2IDLE_CHECK); if (rc) dev_err(pdev->dev, "error writing to STB: %d\n", rc); } @@ -927,7 +759,7 @@ static void amd_pmc_s2idle_restore(void) /* Let SMU know that we are looking for stats */ amd_pmc_dump_data(pdev); - rc = amd_pmc_write_stb(pdev, AMD_PMC_STB_S2IDLE_RESTORE); + rc = amd_stb_write(pdev, AMD_PMC_STB_S2IDLE_RESTORE); if (rc) dev_err(pdev->dev, "error writing to STB: %d\n", rc); @@ -947,6 +779,10 @@ static int amd_pmc_suspend_handler(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); + /* + * Must be called only from the same set of dev_pm_ops handlers + * as i8042_pm_suspend() is called: currently just from .suspend. + */ if (pdev->disable_8042_wakeup && !disable_workarounds) { int rc = amd_pmc_wa_irq1(pdev); @@ -959,7 +795,9 @@ static int amd_pmc_suspend_handler(struct device *dev) return 0; } -static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmc_pm, amd_pmc_suspend_handler, NULL); +static const struct dev_pm_ops amd_pmc_pm = { + .suspend = amd_pmc_suspend_handler, +}; static const struct pci_device_id pmc_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PS) }, @@ -975,74 +813,6 @@ static const struct pci_device_id pmc_pci_ids[] = { { } }; -static int amd_pmc_s2d_init(struct amd_pmc_dev *dev) -{ - u32 phys_addr_low, phys_addr_hi; - u64 stb_phys_addr; - u32 size = 0; - int ret; - - /* Spill to DRAM feature uses separate SMU message port */ - dev->msg_port = 1; - - amd_pmc_send_cmd(dev, S2D_TELEMETRY_SIZE, &size, dev->s2d_msg_id, true); - if (size != S2D_TELEMETRY_BYTES_MAX) - return -EIO; - - /* Get DRAM size */ - ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->s2d_msg_id, true); - if (ret || !dev->dram_size) - dev->dram_size = S2D_TELEMETRY_DRAMBYTES_MAX; - - /* Get STB DRAM address */ - amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_LOW, &phys_addr_low, dev->s2d_msg_id, true); - amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_HIGH, &phys_addr_hi, dev->s2d_msg_id, true); - - if (!phys_addr_hi && !phys_addr_low) { - dev_err(dev->dev, "STB is not enabled on the system; disable enable_stb or contact system vendor\n"); - return -EINVAL; - } - - stb_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low); - - /* Clear msg_port for other SMU operation */ - dev->msg_port = 0; - - dev->stb_virt_addr = devm_ioremap(dev->dev, stb_phys_addr, dev->dram_size); - if (!dev->stb_virt_addr) - return -ENOMEM; - - return 0; -} - -static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data) -{ - int err; - - err = amd_smn_write(0, AMD_PMC_STB_PMI_0, data); - if (err) { - dev_err(dev->dev, "failed to write data in stb: 0x%X\n", AMD_PMC_STB_PMI_0); - return pcibios_err_to_errno(err); - } - - return 0; -} - -static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf) -{ - int i, err; - - for (i = 0; i < FIFO_SIZE; i++) { - err = amd_smn_read(0, AMD_PMC_STB_PMI_0, buf++); - if (err) { - dev_err(dev->dev, "error reading data from stb: 0x%X\n", AMD_PMC_STB_PMI_0); - return pcibios_err_to_errno(err); - } - } - - return 0; -} - static int amd_pmc_probe(struct platform_device *pdev) { struct amd_pmc_dev *dev = &pmc; @@ -1100,12 +870,6 @@ static int amd_pmc_probe(struct platform_device *pdev) /* Get num of IP blocks within the SoC */ amd_pmc_get_ip_info(dev); - if (enable_stb && amd_pmc_is_stb_supported(dev)) { - err = amd_pmc_s2d_init(dev); - if (err) - goto err_pci_dev_put; - } - platform_set_drvdata(pdev, dev); if (IS_ENABLED(CONFIG_SUSPEND)) { err = acpi_register_lps0_dev(&amd_pmc_s2idle_dev_ops); @@ -1116,6 +880,10 @@ static int amd_pmc_probe(struct platform_device *pdev) } amd_pmc_dbgfs_register(dev); + err = amd_stb_s2d_init(dev); + if (err) + goto err_pci_dev_put; + if (IS_ENABLED(CONFIG_AMD_MP2_STB)) amd_mp2_stb_init(dev); pm_report_max_hw_sleep(U64_MAX); diff --git a/drivers/platform/x86/amd/pmc/pmc.h b/drivers/platform/x86/amd/pmc/pmc.h index f1166d15c856..f43f0253b0f5 100644 --- a/drivers/platform/x86/amd/pmc/pmc.h +++ b/drivers/platform/x86/amd/pmc/pmc.h @@ -14,6 +14,11 @@ #include #include +enum s2d_msg_port { + MSG_PORT_PMC, + MSG_PORT_S2D, +}; + struct amd_mp2_dev { void __iomem *mmio; void __iomem *vslbase; @@ -25,24 +30,31 @@ struct amd_mp2_dev { bool is_stb_data; }; +struct stb_arg { + u32 s2d_msg_id; + u32 msg; + u32 arg; + u32 resp; +}; + struct amd_pmc_dev { void __iomem *regbase; void __iomem *smu_virt_addr; void __iomem *stb_virt_addr; void __iomem *fch_virt_addr; - bool msg_port; u32 base_addr; u32 cpu_id; - u32 active_ips; u32 dram_size; + u32 active_ips; + const struct amd_pmc_bit_map *ips_ptr; u32 num_ips; - u32 s2d_msg_id; u32 smu_msg; /* SMU version information */ u8 smu_program; u8 major; u8 minor; u8 rev; + u8 msg_port; struct device *dev; struct pci_dev *rdev; struct mutex lock; /* generic mutex lock */ @@ -50,6 +62,7 @@ struct amd_pmc_dev { struct quirk_entry *quirks; bool disable_8042_wakeup; struct amd_mp2_dev *mp2; + struct stb_arg stb_arg; }; void amd_pmc_process_restore_quirks(struct amd_pmc_dev *dev); @@ -70,4 +83,9 @@ void amd_mp2_stb_deinit(struct amd_pmc_dev *dev); #define PCI_DEVICE_ID_AMD_1AH_M60H_ROOT 0x1122 #define PCI_DEVICE_ID_AMD_MP2_STB 0x172c +int amd_stb_s2d_init(struct amd_pmc_dev *dev); +int amd_stb_read(struct amd_pmc_dev *dev, u32 *buf); +int amd_stb_write(struct amd_pmc_dev *dev, u32 data); +int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret); + #endif /* PMC_H */ diff --git a/drivers/platform/x86/amd/pmf/Kconfig b/drivers/platform/x86/amd/pmf/Kconfig index 99d67cdbd91e..25b8f7ae3abd 100644 --- a/drivers/platform/x86/amd/pmf/Kconfig +++ b/drivers/platform/x86/amd/pmf/Kconfig @@ -7,7 +7,7 @@ config AMD_PMF tristate "AMD Platform Management Framework" depends on ACPI && PCI depends on POWER_SUPPLY - depends on AMD_NB + depends on AMD_NODE select ACPI_PLATFORM_PROFILE depends on TEE && AMDTEE depends on AMD_SFH_HID diff --git a/drivers/platform/x86/amd/pmf/Makefile b/drivers/platform/x86/amd/pmf/Makefile index 7d6079b02589..6b26e48ce8ad 100644 --- a/drivers/platform/x86/amd/pmf/Makefile +++ b/drivers/platform/x86/amd/pmf/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_AMD_PMF) += amd-pmf.o amd-pmf-objs := core.o acpi.o sps.o \ auto-mode.o cnqf.o \ - tee-if.o spc.o pmf-quirks.o + tee-if.o spc.o diff --git a/drivers/platform/x86/amd/pmf/acpi.c b/drivers/platform/x86/amd/pmf/acpi.c index 1b9c7acf0ddf..dd5780a1d06e 100644 --- a/drivers/platform/x86/amd/pmf/acpi.c +++ b/drivers/platform/x86/amd/pmf/acpi.c @@ -321,17 +321,29 @@ int apmf_get_sbios_requests(struct amd_pmf_dev *pdev, struct apmf_sbios_req *req req, sizeof(*req)); } +static void apmf_event_handler_v2(acpi_handle handle, u32 event, void *data) +{ + struct amd_pmf_dev *pmf_dev = data; + int ret; + + guard(mutex)(&pmf_dev->cb_mutex); + + ret = apmf_get_sbios_requests_v2(pmf_dev, &pmf_dev->req); + if (ret) + dev_err(pmf_dev->dev, "Failed to get v2 SBIOS requests: %d\n", ret); +} + static void apmf_event_handler(acpi_handle handle, u32 event, void *data) { struct amd_pmf_dev *pmf_dev = data; struct apmf_sbios_req req; int ret; - mutex_lock(&pmf_dev->update_mutex); + guard(mutex)(&pmf_dev->update_mutex); ret = apmf_get_sbios_requests(pmf_dev, &req); if (ret) { dev_err(pmf_dev->dev, "Failed to get SBIOS requests:%d\n", ret); - goto out; + return; } if (req.pending_req & BIT(APMF_AMT_NOTIFICATION)) { @@ -353,8 +365,6 @@ static void apmf_event_handler(acpi_handle handle, u32 event, void *data) if (pmf_dev->amt_enabled) amd_pmf_update_2_cql(pmf_dev, req.cql_event); } -out: - mutex_unlock(&pmf_dev->update_mutex); } static int apmf_if_verify_interface(struct amd_pmf_dev *pdev) @@ -430,6 +440,15 @@ int apmf_install_handler(struct amd_pmf_dev *pmf_dev) apmf_event_handler(ahandle, 0, pmf_dev); } + if (pmf_dev->smart_pc_enabled && pmf_dev->pmf_if_version == PMF_IF_V2) { + status = acpi_install_notify_handler(ahandle, ACPI_ALL_NOTIFY, + apmf_event_handler_v2, pmf_dev); + if (ACPI_FAILURE(status)) { + dev_err(pmf_dev->dev, "failed to install notify handler for custom BIOS inputs\n"); + return -ENODEV; + } + } + return 0; } @@ -480,6 +499,9 @@ void apmf_acpi_deinit(struct amd_pmf_dev *pmf_dev) if (is_apmf_func_supported(pmf_dev, APMF_FUNC_AUTO_MODE) && is_apmf_func_supported(pmf_dev, APMF_FUNC_SBIOS_REQUESTS)) acpi_remove_notify_handler(ahandle, ACPI_ALL_NOTIFY, apmf_event_handler); + + if (pmf_dev->smart_pc_enabled && pmf_dev->pmf_if_version == PMF_IF_V2) + acpi_remove_notify_handler(ahandle, ACPI_ALL_NOTIFY, apmf_event_handler_v2); } int apmf_acpi_init(struct amd_pmf_dev *pmf_dev) diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index 06a97c533cb8..764cc1fe90ae 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -8,13 +8,13 @@ * Author: Shyam Sundar S K */ -#include #include #include #include #include #include #include +#include #include "pmf.h" /* PMF-SMU communication registers */ @@ -127,7 +127,8 @@ static void amd_pmf_get_metrics(struct work_struct *work) ktime_t time_elapsed_ms; int socket_power; - mutex_lock(&dev->update_mutex); + guard(mutex)(&dev->update_mutex); + /* Transfer table contents */ memset(dev->buf, 0, sizeof(dev->m_table)); amd_pmf_send_cmd(dev, SET_TRANSFER_TABLE, 0, 7, NULL); @@ -149,7 +150,6 @@ static void amd_pmf_get_metrics(struct work_struct *work) dev->start_time = ktime_to_ms(ktime_get()); schedule_delayed_work(&dev->work_buffer, msecs_to_jiffies(metrics_table_loop_ms)); - mutex_unlock(&dev->update_mutex); } static inline u32 amd_pmf_reg_read(struct amd_pmf_dev *dev, int reg_offset) @@ -181,7 +181,7 @@ int amd_pmf_send_cmd(struct amd_pmf_dev *dev, u8 message, bool get, u32 arg, u32 int rc; u32 val; - mutex_lock(&dev->lock); + guard(mutex)(&dev->lock); /* Wait until we get a valid response */ rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMF_REGISTER_RESPONSE, @@ -189,7 +189,7 @@ int amd_pmf_send_cmd(struct amd_pmf_dev *dev, u8 message, bool get, u32 arg, u32 PMF_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX); if (rc) { dev_err(dev->dev, "failed to talk to SMU\n"); - goto out_unlock; + return rc; } /* Write zero to response register */ @@ -207,7 +207,7 @@ int amd_pmf_send_cmd(struct amd_pmf_dev *dev, u8 message, bool get, u32 arg, u32 PMF_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX); if (rc) { dev_err(dev->dev, "SMU response timed out\n"); - goto out_unlock; + return rc; } switch (val) { @@ -221,21 +221,19 @@ int amd_pmf_send_cmd(struct amd_pmf_dev *dev, u8 message, bool get, u32 arg, u32 case AMD_PMF_RESULT_CMD_REJECT_BUSY: dev_err(dev->dev, "SMU not ready. err: 0x%x\n", val); rc = -EBUSY; - goto out_unlock; + break; case AMD_PMF_RESULT_CMD_UNKNOWN: dev_err(dev->dev, "SMU cmd unknown. err: 0x%x\n", val); rc = -EINVAL; - goto out_unlock; + break; case AMD_PMF_RESULT_CMD_REJECT_PREREQ: case AMD_PMF_RESULT_FAILED: default: dev_err(dev->dev, "SMU cmd failed. err: 0x%x\n", val); rc = -EIO; - goto out_unlock; + break; } -out_unlock: - mutex_unlock(&dev->lock); amd_pmf_dump_registers(dev); return rc; } @@ -373,7 +371,6 @@ static void amd_pmf_deinit_features(struct amd_pmf_dev *dev) if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR) || is_apmf_func_supported(dev, APMF_FUNC_OS_POWER_SLIDER_UPDATE)) { power_supply_unreg_notifier(&dev->pwr_src_notifier); - amd_pmf_deinit_sps(dev); } if (dev->smart_pc_enabled) { @@ -456,7 +453,6 @@ static int amd_pmf_probe(struct platform_device *pdev) mutex_init(&dev->lock); mutex_init(&dev->update_mutex); - amd_pmf_quirks_init(dev); apmf_acpi_init(dev); platform_set_drvdata(pdev, dev); amd_pmf_dbgfs_register(dev); diff --git a/drivers/platform/x86/amd/pmf/pmf-quirks.c b/drivers/platform/x86/amd/pmf/pmf-quirks.c deleted file mode 100644 index 7cde5733b9ca..000000000000 --- a/drivers/platform/x86/amd/pmf/pmf-quirks.c +++ /dev/null @@ -1,66 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * AMD Platform Management Framework Driver Quirks - * - * Copyright (c) 2024, Advanced Micro Devices, Inc. - * All Rights Reserved. - * - * Author: Mario Limonciello - */ - -#include - -#include "pmf.h" - -struct quirk_entry { - u32 supported_func; -}; - -static struct quirk_entry quirk_no_sps_bug = { - .supported_func = 0x4003, -}; - -static const struct dmi_system_id fwbug_list[] = { - { - .ident = "ROG Zephyrus G14", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GA403U"), - }, - .driver_data = &quirk_no_sps_bug, - }, - { - .ident = "ROG Ally X", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "RC72LA"), - }, - .driver_data = &quirk_no_sps_bug, - }, - { - .ident = "ASUS TUF Gaming A14", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "FA401W"), - }, - .driver_data = &quirk_no_sps_bug, - }, - {} -}; - -void amd_pmf_quirks_init(struct amd_pmf_dev *dev) -{ - const struct dmi_system_id *dmi_id; - struct quirk_entry *quirks; - - dmi_id = dmi_first_match(fwbug_list); - if (!dmi_id) - return; - - quirks = dmi_id->driver_data; - if (quirks->supported_func) { - dev->supported_func = quirks->supported_func; - pr_info("Using supported funcs quirk to avoid %s platform firmware bug\n", - dmi_id->ident); - } -} diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h index a79808fda1d8..41b2b91b8fdc 100644 --- a/drivers/platform/x86/amd/pmf/pmf.h +++ b/drivers/platform/x86/amd/pmf/pmf.h @@ -338,7 +338,7 @@ struct amd_pmf_dev { struct mutex lock; /* protects the PMF interface */ u32 supported_func; enum platform_profile_option current_profile; - struct platform_profile_handler pprof; + struct device *ppdev; /* platform profile class device */ struct dentry *dbgfs_dir; int hb_interval; /* SBIOS heartbeat interval */ struct delayed_work heart_beat; @@ -370,6 +370,8 @@ struct amd_pmf_dev { struct input_dev *pmf_idev; size_t mtable_size; struct resource *res; + struct apmf_sbios_req_v2 req; /* To get custom bios pending request */ + struct mutex cb_mutex; }; struct apmf_sps_prop_granular_v2 { @@ -616,6 +618,30 @@ enum ta_slider { TA_MAX, }; +enum apmf_smartpc_custom_bios_inputs { + APMF_SMARTPC_CUSTOM_BIOS_INPUT1, + APMF_SMARTPC_CUSTOM_BIOS_INPUT2, +}; + +enum apmf_preq_smartpc { + NOTIFY_CUSTOM_BIOS_INPUT1 = 5, + NOTIFY_CUSTOM_BIOS_INPUT2, +}; + +enum platform_type { + PTYPE_UNKNOWN = 0, + LID_CLOSE, + CLAMSHELL, + FLAT, + TENT, + STAND, + TABLET, + BOOK, + PRESENTATION, + PULL_FWD, + PTYPE_INVALID = 0xf, +}; + /* Command ids for TA communication */ enum ta_pmf_command { TA_PMF_COMMAND_POLICY_BUILDER_INITIALIZE, @@ -657,7 +683,8 @@ struct ta_pmf_condition_info { u32 power_slider; u32 lid_state; bool user_present; - u32 rsvd1[2]; + u32 bios_input1; + u32 bios_input2; u32 monitor_count; u32 rsvd2[2]; u32 bat_design; @@ -667,7 +694,9 @@ struct ta_pmf_condition_info { u32 device_state; u32 socket_power; u32 skin_temperature; - u32 rsvd3[5]; + u32 rsvd3[2]; + u32 platform_type; + u32 rsvd3_1[2]; u32 ambient_light; u32 length; u32 avg_c0residency; @@ -751,7 +780,6 @@ int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf); void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx, struct amd_pmf_static_slider_granular *table); int amd_pmf_init_sps(struct amd_pmf_dev *dev); -void amd_pmf_deinit_sps(struct amd_pmf_dev *dev); int apmf_get_static_slider_granular(struct amd_pmf_dev *pdev, struct apmf_static_slider_granular_output *output); bool is_pprof_balanced(struct amd_pmf_dev *pmf); @@ -797,7 +825,4 @@ int amd_pmf_smartpc_apply_bios_output(struct amd_pmf_dev *dev, u32 val, u32 preq void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in); void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in); -/* Quirk infrastructure */ -void amd_pmf_quirks_init(struct amd_pmf_dev *dev); - #endif /* PMF_H */ diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c index 06226eb0eab3..f34f3130c330 100644 --- a/drivers/platform/x86/amd/pmf/spc.c +++ b/drivers/platform/x86/amd/pmf/spc.c @@ -16,6 +16,46 @@ #include "pmf.h" #ifdef CONFIG_AMD_PMF_DEBUG +static const char *platform_type_as_str(u16 platform_type) +{ + switch (platform_type) { + case CLAMSHELL: + return "CLAMSHELL"; + case FLAT: + return "FLAT"; + case TENT: + return "TENT"; + case STAND: + return "STAND"; + case TABLET: + return "TABLET"; + case BOOK: + return "BOOK"; + case PRESENTATION: + return "PRESENTATION"; + case PULL_FWD: + return "PULL_FWD"; + default: + return "UNKNOWN"; + } +} + +static const char *laptop_placement_as_str(u16 device_state) +{ + switch (device_state) { + case ON_TABLE: + return "ON_TABLE"; + case ON_LAP_MOTION: + return "ON_LAP_MOTION"; + case IN_BAG: + return "IN_BAG"; + case OUT_OF_BAG: + return "OUT_OF_BAG"; + default: + return "UNKNOWN"; + } +} + static const char *ta_slider_as_str(unsigned int state) { switch (state) { @@ -47,12 +87,38 @@ void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table * dev_dbg(dev->dev, "LID State: %s\n", in->ev_info.lid_state ? "close" : "open"); dev_dbg(dev->dev, "User Presence: %s\n", in->ev_info.user_present ? "Present" : "Away"); dev_dbg(dev->dev, "Ambient Light: %d\n", in->ev_info.ambient_light); + dev_dbg(dev->dev, "Platform type: %s\n", platform_type_as_str(in->ev_info.platform_type)); + dev_dbg(dev->dev, "Laptop placement: %s\n", + laptop_placement_as_str(in->ev_info.device_state)); + dev_dbg(dev->dev, "Custom BIOS input1: %u\n", in->ev_info.bios_input1); + dev_dbg(dev->dev, "Custom BIOS input2: %u\n", in->ev_info.bios_input2); dev_dbg(dev->dev, "==== TA inputs END ====\n"); } #else void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) {} #endif +static void amd_pmf_get_custom_bios_inputs(struct amd_pmf_dev *pdev, + struct ta_pmf_enact_table *in) +{ + if (!pdev->req.pending_req) + return; + + switch (pdev->req.pending_req) { + case BIT(NOTIFY_CUSTOM_BIOS_INPUT1): + in->ev_info.bios_input1 = pdev->req.custom_policy[APMF_SMARTPC_CUSTOM_BIOS_INPUT1]; + break; + case BIT(NOTIFY_CUSTOM_BIOS_INPUT2): + in->ev_info.bios_input2 = pdev->req.custom_policy[APMF_SMARTPC_CUSTOM_BIOS_INPUT2]; + break; + default: + dev_dbg(pdev->dev, "Invalid preq for BIOS input: 0x%x\n", pdev->req.pending_req); + } + + /* Clear pending requests after handling */ + memset(&pdev->req, 0, sizeof(pdev->req)); +} + static void amd_pmf_get_c0_residency(u16 *core_res, size_t size, struct ta_pmf_enact_table *in) { u16 max, avg = 0; @@ -190,6 +256,14 @@ static void amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact } else { dev_dbg(dev->dev, "HPD is not enabled/detected\n"); } + + /* Get SRA (Secondary Accelerometer) data */ + if (!amd_get_sfh_info(&sfh_info, MT_SRA)) { + in->ev_info.platform_type = sfh_info.platform_type; + in->ev_info.device_state = sfh_info.laptop_placement; + } else { + dev_dbg(dev->dev, "SRA is not enabled/detected\n"); + } } void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) @@ -201,4 +275,5 @@ void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_tab amd_pmf_get_battery_info(dev, in); amd_pmf_get_slider_info(dev, in); amd_pmf_get_sensor_info(dev, in); + amd_pmf_get_custom_bios_inputs(dev, in); } diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c index 92f7fb22277d..e6cf0b22dac3 100644 --- a/drivers/platform/x86/amd/pmf/sps.c +++ b/drivers/platform/x86/amd/pmf/sps.c @@ -282,10 +282,10 @@ bool is_pprof_balanced(struct amd_pmf_dev *pmf) return (pmf->current_profile == PLATFORM_PROFILE_BALANCED) ? true : false; } -static int amd_pmf_profile_get(struct platform_profile_handler *pprof, +static int amd_pmf_profile_get(struct device *dev, enum platform_profile_option *profile) { - struct amd_pmf_dev *pmf = container_of(pprof, struct amd_pmf_dev, pprof); + struct amd_pmf_dev *pmf = dev_get_drvdata(dev); *profile = pmf->current_profile; return 0; @@ -363,10 +363,10 @@ int amd_pmf_power_slider_update_event(struct amd_pmf_dev *dev) return 0; } -static int amd_pmf_profile_set(struct platform_profile_handler *pprof, +static int amd_pmf_profile_set(struct device *dev, enum platform_profile_option profile) { - struct amd_pmf_dev *pmf = container_of(pprof, struct amd_pmf_dev, pprof); + struct amd_pmf_dev *pmf = dev_get_drvdata(dev); int ret = 0; pmf->current_profile = profile; @@ -387,10 +387,23 @@ static int amd_pmf_profile_set(struct platform_profile_handler *pprof, return 0; } +static int amd_pmf_profile_probe(void *drvdata, unsigned long *choices) +{ + set_bit(PLATFORM_PROFILE_LOW_POWER, choices); + set_bit(PLATFORM_PROFILE_BALANCED, choices); + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + + return 0; +} + +static const struct platform_profile_ops amd_pmf_profile_ops = { + .probe = amd_pmf_profile_probe, + .profile_get = amd_pmf_profile_get, + .profile_set = amd_pmf_profile_set, +}; + int amd_pmf_init_sps(struct amd_pmf_dev *dev) { - int err; - dev->current_profile = PLATFORM_PROFILE_BALANCED; if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) { @@ -405,24 +418,12 @@ int amd_pmf_init_sps(struct amd_pmf_dev *dev) amd_pmf_set_sps_power_limits(dev); } - dev->pprof.profile_get = amd_pmf_profile_get; - dev->pprof.profile_set = amd_pmf_profile_set; - - /* Setup supported modes */ - set_bit(PLATFORM_PROFILE_LOW_POWER, dev->pprof.choices); - set_bit(PLATFORM_PROFILE_BALANCED, dev->pprof.choices); - set_bit(PLATFORM_PROFILE_PERFORMANCE, dev->pprof.choices); - /* Create platform_profile structure and register */ - err = platform_profile_register(&dev->pprof); - if (err) - dev_err(dev->dev, "Failed to register SPS support, this is most likely an SBIOS bug: %d\n", - err); + dev->ppdev = devm_platform_profile_register(dev->dev, "amd-pmf", dev, + &amd_pmf_profile_ops); + if (IS_ERR(dev->ppdev)) + dev_err(dev->dev, "Failed to register SPS support, this is most likely an SBIOS bug: %ld\n", + PTR_ERR(dev->ppdev)); - return err; -} - -void amd_pmf_deinit_sps(struct amd_pmf_dev *dev) -{ - platform_profile_remove(); + return PTR_ERR_OR_ZERO(dev->ppdev); } diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index a5933980ade3..3f8b2a324efd 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -50,7 +50,8 @@ MODULE_PARM_DESC(tablet_mode_sw, "Tablet mode detect: -1:auto 0:disable 1:kbd-do static struct quirk_entry *quirks; static bool atkbd_reports_vol_keys; -static bool asus_i8042_filter(unsigned char data, unsigned char str, struct serio *port) +static bool asus_i8042_filter(unsigned char data, unsigned char str, struct serio *port, + void *context) { static bool extended_e0; static bool extended_e1; diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 8bd187e8b47f..38ef778e8c19 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -313,7 +313,7 @@ struct asus_wmi { bool mid_fan_curve_available; struct fan_curve_data custom_fan_curves[3]; - struct platform_profile_handler platform_profile_handler; + struct device *ppdev; bool platform_profile_support; // The RSOC controls the maximum charging percentage. @@ -3782,7 +3782,7 @@ static ssize_t throttle_thermal_policy_store(struct device *dev, * Ensure that platform_profile updates userspace with the change to ensure * that platform_profile and throttle_thermal_policy_mode are in sync. */ - platform_profile_notify(); + platform_profile_notify(asus->ppdev); return count; } @@ -3793,13 +3793,13 @@ static ssize_t throttle_thermal_policy_store(struct device *dev, static DEVICE_ATTR_RW(throttle_thermal_policy); /* Platform profile ***********************************************************/ -static int asus_wmi_platform_profile_get(struct platform_profile_handler *pprof, +static int asus_wmi_platform_profile_get(struct device *dev, enum platform_profile_option *profile) { struct asus_wmi *asus; int tp; - asus = container_of(pprof, struct asus_wmi, platform_profile_handler); + asus = dev_get_drvdata(dev); tp = asus->throttle_thermal_policy_mode; switch (tp) { @@ -3819,13 +3819,13 @@ static int asus_wmi_platform_profile_get(struct platform_profile_handler *pprof, return 0; } -static int asus_wmi_platform_profile_set(struct platform_profile_handler *pprof, +static int asus_wmi_platform_profile_set(struct device *dev, enum platform_profile_option profile) { struct asus_wmi *asus; int tp; - asus = container_of(pprof, struct asus_wmi, platform_profile_handler); + asus = dev_get_drvdata(dev); switch (profile) { case PLATFORM_PROFILE_PERFORMANCE: @@ -3845,6 +3845,21 @@ static int asus_wmi_platform_profile_set(struct platform_profile_handler *pprof, return throttle_thermal_policy_write(asus); } +static int asus_wmi_platform_profile_probe(void *drvdata, unsigned long *choices) +{ + set_bit(PLATFORM_PROFILE_QUIET, choices); + set_bit(PLATFORM_PROFILE_BALANCED, choices); + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + + return 0; +} + +static const struct platform_profile_ops asus_wmi_platform_profile_ops = { + .probe = asus_wmi_platform_profile_probe, + .profile_get = asus_wmi_platform_profile_get, + .profile_set = asus_wmi_platform_profile_set, +}; + static int platform_profile_setup(struct asus_wmi *asus) { struct device *dev = &asus->platform_device->dev; @@ -3869,22 +3884,11 @@ static int platform_profile_setup(struct asus_wmi *asus) dev_info(dev, "Using throttle_thermal_policy for platform_profile support\n"); - asus->platform_profile_handler.profile_get = asus_wmi_platform_profile_get; - asus->platform_profile_handler.profile_set = asus_wmi_platform_profile_set; - - set_bit(PLATFORM_PROFILE_QUIET, asus->platform_profile_handler.choices); - set_bit(PLATFORM_PROFILE_BALANCED, - asus->platform_profile_handler.choices); - set_bit(PLATFORM_PROFILE_PERFORMANCE, - asus->platform_profile_handler.choices); - - err = platform_profile_register(&asus->platform_profile_handler); - if (err == -EEXIST) { - pr_warn("%s, a platform_profile handler is already registered\n", __func__); - return 0; - } else if (err) { - pr_err("%s, failed at platform_profile_register: %d\n", __func__, err); - return err; + asus->ppdev = devm_platform_profile_register(dev, "asus-wmi", asus, + &asus_wmi_platform_profile_ops); + if (IS_ERR(asus->ppdev)) { + dev_err(dev, "Failed to register a platform_profile class device\n"); + return PTR_ERR(asus->ppdev); } asus->platform_profile_support = true; @@ -4815,7 +4819,7 @@ static int asus_wmi_add(struct platform_device *pdev) } if (asus->driver->i8042_filter) { - err = i8042_install_filter(asus->driver->i8042_filter); + err = i8042_install_filter(asus->driver->i8042_filter, NULL); if (err) pr_warn("Unable to install key filter - %d\n", err); } @@ -4842,8 +4846,6 @@ fail_input: fail_sysfs: fail_custom_fan_curve: fail_platform_profile_setup: - if (asus->platform_profile_support) - platform_profile_remove(); fail_fan_boost_mode: fail_platform: kfree(asus); @@ -4869,9 +4871,6 @@ static void asus_wmi_remove(struct platform_device *device) throttle_thermal_policy_set_default(asus); asus_wmi_battery_exit(asus); - if (asus->platform_profile_support) - platform_profile_remove(); - kfree(asus); } diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h index d02f15fd3482..018dfde4025e 100644 --- a/drivers/platform/x86/asus-wmi.h +++ b/drivers/platform/x86/asus-wmi.h @@ -73,8 +73,7 @@ struct asus_wmi_driver { void (*key_filter) (struct asus_wmi_driver *driver, int *code, unsigned int *value, bool *autorelease); /* Optional standard i8042 filter */ - bool (*i8042_filter)(unsigned char data, unsigned char str, - struct serio *serio); + i8042_filter_t i8042_filter; int (*probe) (struct platform_device *device); void (*detect_quirks) (struct asus_wmi_driver *driver); diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig index 2dddafb3f7fa..d09060aedd3f 100644 --- a/drivers/platform/x86/dell/Kconfig +++ b/drivers/platform/x86/dell/Kconfig @@ -152,6 +152,7 @@ config DELL_SMBIOS_SMM config DELL_SMO8800 tristate "Dell Latitude freefall driver (ACPI SMO88XX)" default m + depends on I2C depends on ACPI || COMPILE_TEST help Say Y here if you want to support SMO88XX freefall devices diff --git a/drivers/platform/x86/dell/Makefile b/drivers/platform/x86/dell/Makefile index 79d60f1bf4c1..bb3cbd470a46 100644 --- a/drivers/platform/x86/dell/Makefile +++ b/drivers/platform/x86/dell/Makefile @@ -15,6 +15,7 @@ dell-smbios-objs := dell-smbios-base.o dell-smbios-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o dell-smbios-$(CONFIG_DELL_SMBIOS_SMM) += dell-smbios-smm.o obj-$(CONFIG_DELL_SMO8800) += dell-smo8800.o +obj-$(CONFIG_DELL_SMO8800) += dell-lis3lv02d.o obj-$(CONFIG_DELL_UART_BACKLIGHT) += dell-uart-backlight.o obj-$(CONFIG_DELL_WMI) += dell-wmi.o dell-wmi-objs := dell-wmi-base.o diff --git a/drivers/platform/x86/dell/alienware-wmi.c b/drivers/platform/x86/dell/alienware-wmi.c index 77465ed9b449..e252e0cf47ef 100644 --- a/drivers/platform/x86/dell/alienware-wmi.c +++ b/drivers/platform/x86/dell/alienware-wmi.c @@ -190,7 +190,7 @@ static struct quirk_entry quirk_asm201 = { }; static struct quirk_entry quirk_g_series = { - .num_zones = 2, + .num_zones = 0, .hdmi_mux = 0, .amplifier = 0, .deepslp = 0, @@ -199,7 +199,7 @@ static struct quirk_entry quirk_g_series = { }; static struct quirk_entry quirk_x_series = { - .num_zones = 2, + .num_zones = 0, .hdmi_mux = 0, .amplifier = 0, .deepslp = 0, @@ -241,6 +241,15 @@ static const struct dmi_system_id alienware_quirks[] __initconst = { }, .driver_data = &quirk_asm201, }, + { + .callback = dmi_matched, + .ident = "Alienware m16 R1 AMD", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"), + }, + .driver_data = &quirk_x_series, + }, { .callback = dmi_matched, .ident = "Alienware m17 R5", @@ -376,12 +385,6 @@ struct color_platform { u8 red; } __packed; -struct platform_zone { - u8 location; - struct device_attribute *attr; - struct color_platform colors; -}; - struct wmax_brightness_args { u32 led_mask; u32 percentage; @@ -411,22 +414,9 @@ struct wmax_u32_args { }; static struct platform_device *platform_device; -static struct device_attribute *zone_dev_attrs; -static struct attribute **zone_attrs; -static struct platform_zone *zone_data; -static struct platform_profile_handler pp_handler; +static struct color_platform colors[4]; static enum wmax_thermal_mode supported_thermal_profiles[PLATFORM_PROFILE_LAST]; -static struct platform_driver platform_driver = { - .driver = { - .name = "alienware-wmi", - } -}; - -static struct attribute_group zone_attribute_group = { - .name = "rgb_zones", -}; - static u8 interface; static u8 lighting_control_state; static u8 global_brightness; @@ -434,7 +424,7 @@ static u8 global_brightness; /* * Helpers used for zone control */ -static int parse_rgb(const char *buf, struct platform_zone *zone) +static int parse_rgb(const char *buf, struct color_platform *colors) { long unsigned int rgb; int ret; @@ -454,28 +444,14 @@ static int parse_rgb(const char *buf, struct platform_zone *zone) repackager.package = rgb & 0x0f0f0f0f; pr_debug("alienware-wmi: r: %d g:%d b: %d\n", repackager.cp.red, repackager.cp.green, repackager.cp.blue); - zone->colors = repackager.cp; + *colors = repackager.cp; return 0; } -static struct platform_zone *match_zone(struct device_attribute *attr) -{ - u8 zone; - - for (zone = 0; zone < quirks->num_zones; zone++) { - if ((struct device_attribute *)zone_data[zone].attr == attr) { - pr_debug("alienware-wmi: matched zone location: %d\n", - zone_data[zone].location); - return &zone_data[zone]; - } - } - return NULL; -} - /* * Individual RGB zone control */ -static int alienware_update_led(struct platform_zone *zone) +static int alienware_update_led(u8 location) { int method_id; acpi_status status; @@ -484,8 +460,8 @@ static int alienware_update_led(struct platform_zone *zone) struct legacy_led_args legacy_args; struct wmax_led_args wmax_basic_args; if (interface == WMAX) { - wmax_basic_args.led_mask = 1 << zone->location; - wmax_basic_args.colors = zone->colors; + wmax_basic_args.led_mask = 1 << location; + wmax_basic_args.colors = colors[location]; wmax_basic_args.state = lighting_control_state; guid = WMAX_CONTROL_GUID; method_id = WMAX_METHOD_ZONE_CONTROL; @@ -493,7 +469,7 @@ static int alienware_update_led(struct platform_zone *zone) input.length = sizeof(wmax_basic_args); input.pointer = &wmax_basic_args; } else { - legacy_args.colors = zone->colors; + legacy_args.colors = colors[location]; legacy_args.brightness = global_brightness; legacy_args.state = 0; if (lighting_control_state == LEGACY_BOOTING || @@ -502,7 +478,7 @@ static int alienware_update_led(struct platform_zone *zone) legacy_args.state = lighting_control_state; } else guid = LEGACY_CONTROL_GUID; - method_id = zone->location + 1; + method_id = location + 1; input.length = sizeof(legacy_args); input.pointer = &legacy_args; @@ -516,35 +492,153 @@ static int alienware_update_led(struct platform_zone *zone) } static ssize_t zone_show(struct device *dev, struct device_attribute *attr, - char *buf) + char *buf, u8 location) { - struct platform_zone *target_zone; - target_zone = match_zone(attr); - if (target_zone == NULL) - return sprintf(buf, "red: -1, green: -1, blue: -1\n"); return sprintf(buf, "red: %d, green: %d, blue: %d\n", - target_zone->colors.red, - target_zone->colors.green, target_zone->colors.blue); + colors[location].red, colors[location].green, + colors[location].blue); } -static ssize_t zone_set(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t zone_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count, u8 location) { - struct platform_zone *target_zone; int ret; - target_zone = match_zone(attr); - if (target_zone == NULL) { - pr_err("alienware-wmi: invalid target zone\n"); - return 1; - } - ret = parse_rgb(buf, target_zone); + + ret = parse_rgb(buf, &colors[location]); if (ret) return ret; - ret = alienware_update_led(target_zone); + + ret = alienware_update_led(location); + return ret ? ret : count; } +static ssize_t zone00_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return zone_show(dev, attr, buf, 0); +} + +static ssize_t zone00_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return zone_store(dev, attr, buf, count, 0); +} + +static DEVICE_ATTR_RW(zone00); + +static ssize_t zone01_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return zone_show(dev, attr, buf, 1); +} + +static ssize_t zone01_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return zone_store(dev, attr, buf, count, 1); +} + +static DEVICE_ATTR_RW(zone01); + +static ssize_t zone02_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return zone_show(dev, attr, buf, 2); +} + +static ssize_t zone02_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return zone_store(dev, attr, buf, count, 2); +} + +static DEVICE_ATTR_RW(zone02); + +static ssize_t zone03_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return zone_show(dev, attr, buf, 3); +} + +static ssize_t zone03_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return zone_store(dev, attr, buf, count, 3); +} + +static DEVICE_ATTR_RW(zone03); + +/* + * Lighting control state device attribute (Global) + */ +static ssize_t lighting_control_state_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (lighting_control_state == LEGACY_BOOTING) + return sysfs_emit(buf, "[booting] running suspend\n"); + else if (lighting_control_state == LEGACY_SUSPEND) + return sysfs_emit(buf, "booting running [suspend]\n"); + + return sysfs_emit(buf, "booting [running] suspend\n"); +} + +static ssize_t lighting_control_state_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + u8 val; + + if (strcmp(buf, "booting\n") == 0) + val = LEGACY_BOOTING; + else if (strcmp(buf, "suspend\n") == 0) + val = LEGACY_SUSPEND; + else if (interface == LEGACY) + val = LEGACY_RUNNING; + else + val = WMAX_RUNNING; + + lighting_control_state = val; + pr_debug("alienware-wmi: updated control state to %d\n", + lighting_control_state); + + return count; +} + +static DEVICE_ATTR_RW(lighting_control_state); + +static umode_t zone_attr_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + if (n < quirks->num_zones + 1) + return attr->mode; + + return 0; +} + +static bool zone_group_visible(struct kobject *kobj) +{ + return quirks->num_zones > 0; +} +DEFINE_SYSFS_GROUP_VISIBLE(zone); + +static struct attribute *zone_attrs[] = { + &dev_attr_lighting_control_state.attr, + &dev_attr_zone00.attr, + &dev_attr_zone01.attr, + &dev_attr_zone02.attr, + &dev_attr_zone03.attr, + NULL +}; + +static struct attribute_group zone_attribute_group = { + .name = "rgb_zones", + .is_visible = SYSFS_GROUP_VISIBLE(zone), + .attrs = zone_attrs, +}; + /* * LED Brightness (Global) */ @@ -573,7 +667,7 @@ static void global_led_set(struct led_classdev *led_cdev, if (interface == WMAX) ret = wmax_brightness(brightness); else - ret = alienware_update_led(&zone_data[0]); + ret = alienware_update_led(0); if (ret) pr_err("LED brightness update failed\n"); } @@ -589,46 +683,8 @@ static struct led_classdev global_led = { .name = "alienware::global_brightness", }; -/* - * Lighting control state device attribute (Global) - */ -static ssize_t show_control_state(struct device *dev, - struct device_attribute *attr, char *buf) -{ - if (lighting_control_state == LEGACY_BOOTING) - return sysfs_emit(buf, "[booting] running suspend\n"); - else if (lighting_control_state == LEGACY_SUSPEND) - return sysfs_emit(buf, "booting running [suspend]\n"); - return sysfs_emit(buf, "booting [running] suspend\n"); -} - -static ssize_t store_control_state(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - long unsigned int val; - if (strcmp(buf, "booting\n") == 0) - val = LEGACY_BOOTING; - else if (strcmp(buf, "suspend\n") == 0) - val = LEGACY_SUSPEND; - else if (interface == LEGACY) - val = LEGACY_RUNNING; - else - val = WMAX_RUNNING; - lighting_control_state = val; - pr_debug("alienware-wmi: updated control state to %d\n", - lighting_control_state); - return count; -} - -static DEVICE_ATTR(lighting_control_state, 0644, show_control_state, - store_control_state); - static int alienware_zone_init(struct platform_device *dev) { - u8 zone; - char *name; - if (interface == WMAX) { lighting_control_state = WMAX_RUNNING; } else if (interface == LEGACY) { @@ -637,65 +693,15 @@ static int alienware_zone_init(struct platform_device *dev) global_led.max_brightness = 0x0F; global_brightness = global_led.max_brightness; - /* - * - zone_dev_attrs num_zones + 1 is for individual zones and then - * null terminated - * - zone_attrs num_zones + 2 is for all attrs in zone_dev_attrs + - * the lighting control + null terminated - * - zone_data num_zones is for the distinct zones - */ - zone_dev_attrs = - kcalloc(quirks->num_zones + 1, sizeof(struct device_attribute), - GFP_KERNEL); - if (!zone_dev_attrs) - return -ENOMEM; - - zone_attrs = - kcalloc(quirks->num_zones + 2, sizeof(struct attribute *), - GFP_KERNEL); - if (!zone_attrs) - return -ENOMEM; - - zone_data = - kcalloc(quirks->num_zones, sizeof(struct platform_zone), - GFP_KERNEL); - if (!zone_data) - return -ENOMEM; - - for (zone = 0; zone < quirks->num_zones; zone++) { - name = kasprintf(GFP_KERNEL, "zone%02hhX", zone); - if (name == NULL) - return 1; - sysfs_attr_init(&zone_dev_attrs[zone].attr); - zone_dev_attrs[zone].attr.name = name; - zone_dev_attrs[zone].attr.mode = 0644; - zone_dev_attrs[zone].show = zone_show; - zone_dev_attrs[zone].store = zone_set; - zone_data[zone].location = zone; - zone_attrs[zone] = &zone_dev_attrs[zone].attr; - zone_data[zone].attr = &zone_dev_attrs[zone]; - } - zone_attrs[quirks->num_zones] = &dev_attr_lighting_control_state.attr; - zone_attribute_group.attrs = zone_attrs; - - led_classdev_register(&dev->dev, &global_led); - - return sysfs_create_group(&dev->dev.kobj, &zone_attribute_group); + return led_classdev_register(&dev->dev, &global_led); } static void alienware_zone_exit(struct platform_device *dev) { - u8 zone; + if (!quirks->num_zones) + return; - sysfs_remove_group(&dev->dev.kobj, &zone_attribute_group); led_classdev_unregister(&global_led); - if (zone_dev_attrs) { - for (zone = 0; zone < quirks->num_zones; zone++) - kfree(zone_dev_attrs[zone].attr.name); - } - kfree(zone_dev_attrs); - kfree(zone_data); - kfree(zone_attrs); } static acpi_status alienware_wmax_command(void *in_args, size_t in_size, @@ -730,14 +736,15 @@ static acpi_status alienware_wmax_command(void *in_args, size_t in_size, * The HDMI mux sysfs node indicates the status of the HDMI input mux. * It can toggle between standard system GPU output and HDMI input. */ -static ssize_t show_hdmi_cable(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t cable_show(struct device *dev, struct device_attribute *attr, + char *buf) { - acpi_status status; - u32 out_data; struct wmax_basic_args in_args = { .arg = 0, }; + acpi_status status; + u32 out_data; + status = alienware_wmax_command(&in_args, sizeof(in_args), WMAX_METHOD_HDMI_CABLE, &out_data); @@ -751,14 +758,15 @@ static ssize_t show_hdmi_cable(struct device *dev, return sysfs_emit(buf, "unconnected connected [unknown]\n"); } -static ssize_t show_hdmi_source(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t source_show(struct device *dev, struct device_attribute *attr, + char *buf) { - acpi_status status; - u32 out_data; struct wmax_basic_args in_args = { .arg = 0, }; + acpi_status status; + u32 out_data; + status = alienware_wmax_command(&in_args, sizeof(in_args), WMAX_METHOD_HDMI_STATUS, &out_data); @@ -773,12 +781,12 @@ static ssize_t show_hdmi_source(struct device *dev, return sysfs_emit(buf, "input gpu [unknown]\n"); } -static ssize_t toggle_hdmi_source(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t source_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { - acpi_status status; struct wmax_basic_args args; + acpi_status status; + if (strcmp(buf, "gpu\n") == 0) args.arg = 1; else if (strcmp(buf, "input\n") == 0) @@ -796,9 +804,14 @@ static ssize_t toggle_hdmi_source(struct device *dev, return count; } -static DEVICE_ATTR(cable, S_IRUGO, show_hdmi_cable, NULL); -static DEVICE_ATTR(source, S_IRUGO | S_IWUSR, show_hdmi_source, - toggle_hdmi_source); +static DEVICE_ATTR_RO(cable); +static DEVICE_ATTR_RW(source); + +static bool hdmi_group_visible(struct kobject *kobj) +{ + return quirks->hdmi_mux; +} +DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(hdmi); static struct attribute *hdmi_attrs[] = { &dev_attr_cable.attr, @@ -808,38 +821,24 @@ static struct attribute *hdmi_attrs[] = { static const struct attribute_group hdmi_attribute_group = { .name = "hdmi", + .is_visible = SYSFS_GROUP_VISIBLE(hdmi), .attrs = hdmi_attrs, }; -static void remove_hdmi(struct platform_device *dev) -{ - if (quirks->hdmi_mux > 0) - sysfs_remove_group(&dev->dev.kobj, &hdmi_attribute_group); -} - -static int create_hdmi(struct platform_device *dev) -{ - int ret; - - ret = sysfs_create_group(&dev->dev.kobj, &hdmi_attribute_group); - if (ret) - remove_hdmi(dev); - return ret; -} - /* * Alienware GFX amplifier support * - Currently supports reading cable status * - Leaving expansion room to possibly support dock/undock events later */ -static ssize_t show_amplifier_status(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t status_show(struct device *dev, struct device_attribute *attr, + char *buf) { - acpi_status status; - u32 out_data; struct wmax_basic_args in_args = { .arg = 0, }; + acpi_status status; + u32 out_data; + status = alienware_wmax_command(&in_args, sizeof(in_args), WMAX_METHOD_AMPLIFIER_CABLE, &out_data); @@ -853,7 +852,13 @@ static ssize_t show_amplifier_status(struct device *dev, return sysfs_emit(buf, "unconnected connected [unknown]\n"); } -static DEVICE_ATTR(status, S_IRUGO, show_amplifier_status, NULL); +static DEVICE_ATTR_RO(status); + +static bool amplifier_group_visible(struct kobject *kobj) +{ + return quirks->amplifier; +} +DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(amplifier); static struct attribute *amplifier_attrs[] = { &dev_attr_status.attr, @@ -862,37 +867,23 @@ static struct attribute *amplifier_attrs[] = { static const struct attribute_group amplifier_attribute_group = { .name = "amplifier", + .is_visible = SYSFS_GROUP_VISIBLE(amplifier), .attrs = amplifier_attrs, }; -static void remove_amplifier(struct platform_device *dev) -{ - if (quirks->amplifier > 0) - sysfs_remove_group(&dev->dev.kobj, &lifier_attribute_group); -} - -static int create_amplifier(struct platform_device *dev) -{ - int ret; - - ret = sysfs_create_group(&dev->dev.kobj, &lifier_attribute_group); - if (ret) - remove_amplifier(dev); - return ret; -} - /* * Deep Sleep Control support * - Modifies BIOS setting for deep sleep control allowing extra wakeup events */ -static ssize_t show_deepsleep_status(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t deepsleep_show(struct device *dev, struct device_attribute *attr, + char *buf) { - acpi_status status; - u32 out_data; struct wmax_basic_args in_args = { .arg = 0, }; + acpi_status status; + u32 out_data; + status = alienware_wmax_command(&in_args, sizeof(in_args), WMAX_METHOD_DEEP_SLEEP_STATUS, &out_data); if (ACPI_SUCCESS(status)) { @@ -907,12 +898,11 @@ static ssize_t show_deepsleep_status(struct device *dev, return sysfs_emit(buf, "disabled s5 s5_s4 [unknown]\n"); } -static ssize_t toggle_deepsleep(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t deepsleep_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { - acpi_status status; struct wmax_basic_args args; + acpi_status status; if (strcmp(buf, "disabled\n") == 0) args.arg = 0; @@ -931,7 +921,13 @@ static ssize_t toggle_deepsleep(struct device *dev, return count; } -static DEVICE_ATTR(deepsleep, S_IRUGO | S_IWUSR, show_deepsleep_status, toggle_deepsleep); +static DEVICE_ATTR_RW(deepsleep); + +static bool deepsleep_group_visible(struct kobject *kobj) +{ + return quirks->deepslp; +} +DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(deepsleep); static struct attribute *deepsleep_attrs[] = { &dev_attr_deepsleep.attr, @@ -940,25 +936,10 @@ static struct attribute *deepsleep_attrs[] = { static const struct attribute_group deepsleep_attribute_group = { .name = "deepsleep", + .is_visible = SYSFS_GROUP_VISIBLE(deepsleep), .attrs = deepsleep_attrs, }; -static void remove_deepsleep(struct platform_device *dev) -{ - if (quirks->deepslp > 0) - sysfs_remove_group(&dev->dev.kobj, &deepsleep_attribute_group); -} - -static int create_deepsleep(struct platform_device *dev) -{ - int ret; - - ret = sysfs_create_group(&dev->dev.kobj, &deepsleep_attribute_group); - if (ret) - remove_deepsleep(dev); - return ret; -} - /* * Thermal Profile control * - Provides thermal profile control through the Platform Profile API @@ -988,13 +969,13 @@ static bool is_wmax_thermal_code(u32 code) static int wmax_thermal_information(u8 operation, u8 arg, u32 *out_data) { - acpi_status status; struct wmax_u32_args in_args = { .operation = operation, .arg1 = arg, .arg2 = 0, .arg3 = 0, }; + acpi_status status; status = alienware_wmax_command(&in_args, sizeof(in_args), WMAX_METHOD_THERMAL_INFORMATION, @@ -1011,13 +992,13 @@ static int wmax_thermal_information(u8 operation, u8 arg, u32 *out_data) static int wmax_thermal_control(u8 profile) { - acpi_status status; struct wmax_u32_args in_args = { .operation = WMAX_OPERATION_ACTIVATE_PROFILE, .arg1 = profile, .arg2 = 0, .arg3 = 0, }; + acpi_status status; u32 out_data; status = alienware_wmax_command(&in_args, sizeof(in_args), @@ -1035,13 +1016,13 @@ static int wmax_thermal_control(u8 profile) static int wmax_game_shift_status(u8 operation, u32 *out_data) { - acpi_status status; struct wmax_u32_args in_args = { .operation = operation, .arg1 = 0, .arg2 = 0, .arg3 = 0, }; + acpi_status status; status = alienware_wmax_command(&in_args, sizeof(in_args), WMAX_METHOD_GAME_SHIFT_STATUS, @@ -1056,7 +1037,7 @@ static int wmax_game_shift_status(u8 operation, u32 *out_data) return 0; } -static int thermal_profile_get(struct platform_profile_handler *pprof, +static int thermal_profile_get(struct device *dev, enum platform_profile_option *profile) { u32 out_data; @@ -1082,7 +1063,7 @@ static int thermal_profile_get(struct platform_profile_handler *pprof, return 0; } -static int thermal_profile_set(struct platform_profile_handler *pprof, +static int thermal_profile_set(struct device *dev, enum platform_profile_option profile) { if (quirks->gmode) { @@ -1108,13 +1089,13 @@ static int thermal_profile_set(struct platform_profile_handler *pprof, return wmax_thermal_control(supported_thermal_profiles[profile]); } -static int create_thermal_profile(void) +static int thermal_profile_probe(void *drvdata, unsigned long *choices) { - u32 out_data; + enum platform_profile_option profile; + enum wmax_thermal_mode mode; u8 sys_desc[4]; u32 first_mode; - enum wmax_thermal_mode mode; - enum platform_profile_option profile; + u32 out_data; int ret; ret = wmax_thermal_information(WMAX_OPERATION_SYS_DESCRIPTION, @@ -1141,31 +1122,56 @@ static int create_thermal_profile(void) profile = wmax_mode_to_platform_profile[mode]; supported_thermal_profiles[profile] = out_data; - set_bit(profile, pp_handler.choices); + set_bit(profile, choices); } - if (bitmap_empty(pp_handler.choices, PLATFORM_PROFILE_LAST)) + if (bitmap_empty(choices, PLATFORM_PROFILE_LAST)) return -ENODEV; if (quirks->gmode) { supported_thermal_profiles[PLATFORM_PROFILE_PERFORMANCE] = WMAX_THERMAL_MODE_GMODE; - set_bit(PLATFORM_PROFILE_PERFORMANCE, pp_handler.choices); + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); } - pp_handler.profile_get = thermal_profile_get; - pp_handler.profile_set = thermal_profile_set; - - return platform_profile_register(&pp_handler); + return 0; } -static void remove_thermal_profile(void) +static const struct platform_profile_ops awcc_platform_profile_ops = { + .probe = thermal_profile_probe, + .profile_get = thermal_profile_get, + .profile_set = thermal_profile_set, +}; + +static int create_thermal_profile(struct platform_device *platform_device) { - if (quirks->thermal) - platform_profile_remove(); + struct device *ppdev; + + ppdev = devm_platform_profile_register(&platform_device->dev, "alienware-wmi", + NULL, &awcc_platform_profile_ops); + + return PTR_ERR_OR_ZERO(ppdev); } +/* + * Platform Driver + */ +static const struct attribute_group *alienfx_groups[] = { + &zone_attribute_group, + &hdmi_attribute_group, + &lifier_attribute_group, + &deepsleep_attribute_group, + NULL +}; + +static struct platform_driver platform_driver = { + .driver = { + .name = "alienware-wmi", + .dev_groups = alienfx_groups, + }, +}; + static int __init alienware_wmi_init(void) { int ret; @@ -1205,43 +1211,23 @@ static int __init alienware_wmi_init(void) if (ret) goto fail_platform_device2; - if (quirks->hdmi_mux > 0) { - ret = create_hdmi(platform_device); - if (ret) - goto fail_prep_hdmi; - } - - if (quirks->amplifier > 0) { - ret = create_amplifier(platform_device); - if (ret) - goto fail_prep_amplifier; - } - - if (quirks->deepslp > 0) { - ret = create_deepsleep(platform_device); - if (ret) - goto fail_prep_deepsleep; - } - if (quirks->thermal) { - ret = create_thermal_profile(); + ret = create_thermal_profile(platform_device); if (ret) goto fail_prep_thermal_profile; } - ret = alienware_zone_init(platform_device); - if (ret) - goto fail_prep_zones; + if (quirks->num_zones > 0) { + ret = alienware_zone_init(platform_device); + if (ret) + goto fail_prep_zones; + } return 0; fail_prep_zones: alienware_zone_exit(platform_device); - remove_thermal_profile(); fail_prep_thermal_profile: -fail_prep_deepsleep: -fail_prep_amplifier: -fail_prep_hdmi: platform_device_del(platform_device); fail_platform_device2: platform_device_put(platform_device); @@ -1255,13 +1241,9 @@ module_init(alienware_wmi_init); static void __exit alienware_wmi_exit(void) { - if (platform_device) { - alienware_zone_exit(platform_device); - remove_hdmi(platform_device); - remove_thermal_profile(); - platform_device_unregister(platform_device); - platform_driver_unregister(&platform_driver); - } + alienware_zone_exit(platform_device); + platform_device_unregister(platform_device); + platform_driver_unregister(&platform_driver); } module_exit(alienware_wmi_exit); diff --git a/drivers/platform/x86/dell/dcdbas.c b/drivers/platform/x86/dell/dcdbas.c index 0aeb8149c16b..8149be25fa26 100644 --- a/drivers/platform/x86/dell/dcdbas.c +++ b/drivers/platform/x86/dell/dcdbas.c @@ -163,7 +163,7 @@ static ssize_t smi_data_buf_size_store(struct device *dev, } static ssize_t smi_data_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { ssize_t ret; @@ -176,7 +176,7 @@ static ssize_t smi_data_read(struct file *filp, struct kobject *kobj, } static ssize_t smi_data_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { ssize_t ret; @@ -636,9 +636,9 @@ static struct notifier_block dcdbas_reboot_nb = { .priority = INT_MIN }; -static DCDBAS_BIN_ATTR_RW(smi_data); +static const BIN_ATTR_ADMIN_RW(smi_data, 0); -static struct bin_attribute *dcdbas_bin_attrs[] = { +static const struct bin_attribute *const dcdbas_bin_attrs[] = { &bin_attr_smi_data, NULL }; @@ -662,7 +662,7 @@ static struct attribute *dcdbas_dev_attrs[] = { static const struct attribute_group dcdbas_attr_group = { .attrs = dcdbas_dev_attrs, - .bin_attrs = dcdbas_bin_attrs, + .bin_attrs_new = dcdbas_bin_attrs, }; static int dcdbas_probe(struct platform_device *dev) diff --git a/drivers/platform/x86/dell/dcdbas.h b/drivers/platform/x86/dell/dcdbas.h index 942a23ddded0..a05d7f667586 100644 --- a/drivers/platform/x86/dell/dcdbas.h +++ b/drivers/platform/x86/dell/dcdbas.h @@ -56,14 +56,6 @@ #define DCDBAS_DEV_ATTR_WO(_name) \ DEVICE_ATTR(_name,0200,NULL,_name##_store); -#define DCDBAS_BIN_ATTR_RW(_name) \ -struct bin_attribute bin_attr_##_name = { \ - .attr = { .name = __stringify(_name), \ - .mode = 0600 }, \ - .read = _name##_read, \ - .write = _name##_write, \ -} - struct smi_cmd { __u32 magic; __u32 ebx; diff --git a/drivers/platform/x86/dell/dell-laptop.c b/drivers/platform/x86/dell/dell-laptop.c index 5671bd0deee7..57748c3ea24f 100644 --- a/drivers/platform/x86/dell/dell-laptop.c +++ b/drivers/platform/x86/dell/dell-laptop.c @@ -103,15 +103,15 @@ static bool mute_led_registered; struct battery_mode_info { int token; - const char *label; + enum power_supply_charge_type charge_type; }; static const struct battery_mode_info battery_modes[] = { - { BAT_PRI_AC_MODE_TOKEN, "Trickle" }, - { BAT_EXPRESS_MODE_TOKEN, "Fast" }, - { BAT_STANDARD_MODE_TOKEN, "Standard" }, - { BAT_ADAPTIVE_MODE_TOKEN, "Adaptive" }, - { BAT_CUSTOM_MODE_TOKEN, "Custom" }, + { BAT_PRI_AC_MODE_TOKEN, POWER_SUPPLY_CHARGE_TYPE_TRICKLE }, + { BAT_EXPRESS_MODE_TOKEN, POWER_SUPPLY_CHARGE_TYPE_FAST }, + { BAT_STANDARD_MODE_TOKEN, POWER_SUPPLY_CHARGE_TYPE_STANDARD }, + { BAT_ADAPTIVE_MODE_TOKEN, POWER_SUPPLY_CHARGE_TYPE_ADAPTIVE }, + { BAT_CUSTOM_MODE_TOKEN, POWER_SUPPLY_CHARGE_TYPE_CUSTOM }, }; static u32 battery_supported_modes; @@ -725,8 +725,8 @@ static void dell_update_rfkill(struct work_struct *ignored) } static DECLARE_DELAYED_WORK(dell_rfkill_work, dell_update_rfkill); -static bool dell_laptop_i8042_filter(unsigned char data, unsigned char str, - struct serio *port) +static bool dell_laptop_i8042_filter(unsigned char data, unsigned char str, struct serio *port, + void *context) { static bool extended; @@ -884,7 +884,7 @@ static int __init dell_setup_rfkill(void) pr_warn("Unable to register dell rbtn notifier\n"); goto err_filter; } else { - ret = i8042_install_filter(dell_laptop_i8042_filter); + ret = i8042_install_filter(dell_laptop_i8042_filter, NULL); if (ret) { pr_warn("Unable to install key filter\n"); goto err_filter; @@ -2261,46 +2261,42 @@ static ssize_t charge_types_show(struct device *dev, struct device_attribute *attr, char *buf) { - ssize_t count = 0; + enum power_supply_charge_type charge_type; int i; for (i = 0; i < ARRAY_SIZE(battery_modes); i++) { - bool active; + charge_type = battery_modes[i].charge_type; - if (!(battery_supported_modes & BIT(i))) + if (!(battery_supported_modes & BIT(charge_type))) continue; - active = dell_battery_mode_is_active(battery_modes[i].token); - count += sysfs_emit_at(buf, count, active ? "[%s] " : "%s ", - battery_modes[i].label); + if (!dell_battery_mode_is_active(battery_modes[i].token)) + continue; + + return power_supply_charge_types_show(dev, battery_supported_modes, + charge_type, buf); } - /* convert the last space to a newline */ - if (count > 0) - count--; - count += sysfs_emit_at(buf, count, "\n"); - - return count; + /* No active mode found */ + return -EIO; } static ssize_t charge_types_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { - bool matched = false; - int err, i; + int charge_type, err, i; + + charge_type = power_supply_charge_types_parse(battery_supported_modes, buf); + if (charge_type < 0) + return charge_type; for (i = 0; i < ARRAY_SIZE(battery_modes); i++) { - if (!(battery_supported_modes & BIT(i))) - continue; - - if (sysfs_streq(battery_modes[i].label, buf)) { - matched = true; + if (battery_modes[i].charge_type == charge_type) break; - } } - if (!matched) - return -EINVAL; + if (i == ARRAY_SIZE(battery_modes)) + return -ENOENT; err = dell_battery_set_mode(battery_modes[i].token); if (err) @@ -2430,7 +2426,7 @@ static u32 __init battery_get_supported_modes(void) for (i = 0; i < ARRAY_SIZE(battery_modes); i++) { if (dell_smbios_find_token(battery_modes[i].token)) - modes |= BIT(i); + modes |= BIT(battery_modes[i].charge_type); } return modes; diff --git a/drivers/platform/x86/dell/dell-lis3lv02d.c b/drivers/platform/x86/dell/dell-lis3lv02d.c new file mode 100644 index 000000000000..efe26d667973 --- /dev/null +++ b/drivers/platform/x86/dell/dell-lis3lv02d.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * lis3lv02d i2c-client instantiation for ACPI SMO88xx devices without I2C resources. + * + * Copyright (C) 2024 Hans de Goede + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include "dell-smo8800-ids.h" + +#define LIS3_WHO_AM_I 0x0f + +#define DELL_LIS3LV02D_DMI_ENTRY(product_name, i2c_addr) \ + { \ + .matches = { \ + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), \ + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, product_name), \ + }, \ + .driver_data = (void *)(uintptr_t)(i2c_addr), \ + } + +/* + * Accelerometer's I2C address is not specified in DMI nor ACPI, + * so it is needed to define mapping table based on DMI product names. + */ +static const struct dmi_system_id lis3lv02d_devices[] __initconst = { + /* + * Dell platform team told us that these Latitude devices have + * ST microelectronics accelerometer at I2C address 0x29. + */ + DELL_LIS3LV02D_DMI_ENTRY("Latitude E5250", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Latitude E5450", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Latitude E5550", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Latitude E6440", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Latitude E6440 ATG", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Latitude E6540", 0x29), + /* + * Additional individual entries were added after verification. + */ + DELL_LIS3LV02D_DMI_ENTRY("Latitude 5480", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Latitude E6330", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Latitude E6430", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Precision 3540", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Precision M6800", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Vostro V131", 0x1d), + DELL_LIS3LV02D_DMI_ENTRY("Vostro 5568", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("XPS 15 7590", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("XPS 15 9550", 0x29), + { } +}; + +static u8 i2c_addr; +static struct i2c_client *i2c_dev; +static bool notifier_registered; + +static bool probe_i2c_addr; +module_param(probe_i2c_addr, bool, 0444); +MODULE_PARM_DESC(probe_i2c_addr, "Probe the i801 I2C bus for the accelerometer on models where the address is unknown, this may be dangerous."); + +static int detect_lis3lv02d(struct i2c_adapter *adap, unsigned short addr) +{ + union i2c_smbus_data smbus_data; + int err; + + dev_info(&adap->dev, "Probing for lis3lv02d on address 0x%02x\n", addr); + + err = i2c_smbus_xfer(adap, addr, 0, I2C_SMBUS_READ, LIS3_WHO_AM_I, + I2C_SMBUS_BYTE_DATA, &smbus_data); + if (err < 0) + return 0; /* Not found */ + + /* valid who-am-i values are from drivers/misc/lis3lv02d/lis3lv02d.c */ + switch (smbus_data.byte) { + case 0x32: + case 0x33: + case 0x3a: + case 0x3b: + break; + default: + dev_warn(&adap->dev, "Unknown who-am-i register value 0x%02x\n", + smbus_data.byte); + return 0; /* Not found */ + } + + dev_info(&adap->dev, + "Detected lis3lv02d on address 0x%02x, please report this upstream to platform-driver-x86@vger.kernel.org so that a quirk can be added\n", + addr); + + return 1; /* Found */ +} + +static bool i2c_adapter_is_main_i801(struct i2c_adapter *adap) +{ + /* + * Only match the main I801 adapter and reject secondary adapters + * which names start with "SMBus I801 IDF adapter". + */ + return strstarts(adap->name, "SMBus I801 adapter"); +} + +static int find_i801(struct device *dev, void *data) +{ + struct i2c_adapter *adap, **adap_ret = data; + + adap = i2c_verify_adapter(dev); + if (!adap) + return 0; + + if (!i2c_adapter_is_main_i801(adap)) + return 0; + + *adap_ret = i2c_get_adapter(adap->nr); + return 1; +} + +static void instantiate_i2c_client(struct work_struct *work) +{ + struct i2c_board_info info = { }; + struct i2c_adapter *adap = NULL; + + if (i2c_dev) + return; + + /* + * bus_for_each_dev() and not i2c_for_each_dev() to avoid + * a deadlock when find_i801() calls i2c_get_adapter(). + */ + bus_for_each_dev(&i2c_bus_type, NULL, &adap, find_i801); + if (!adap) + return; + + strscpy(info.type, "lis3lv02d", I2C_NAME_SIZE); + + if (i2c_addr) { + info.addr = i2c_addr; + i2c_dev = i2c_new_client_device(adap, &info); + } else { + /* First try address 0x29 (most used) and then try 0x1d */ + static const unsigned short addr_list[] = { 0x29, 0x1d, I2C_CLIENT_END }; + + i2c_dev = i2c_new_scanned_device(adap, &info, addr_list, detect_lis3lv02d); + } + + if (IS_ERR(i2c_dev)) { + dev_err(&adap->dev, "error %ld registering i2c_client\n", PTR_ERR(i2c_dev)); + i2c_dev = NULL; + } else { + dev_dbg(&adap->dev, "registered lis3lv02d on address 0x%02x\n", info.addr); + } + + i2c_put_adapter(adap); +} +static DECLARE_WORK(i2c_work, instantiate_i2c_client); + +static int i2c_bus_notify(struct notifier_block *nb, unsigned long action, void *data) +{ + struct device *dev = data; + struct i2c_client *client; + struct i2c_adapter *adap; + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + adap = i2c_verify_adapter(dev); + if (!adap) + break; + + if (i2c_adapter_is_main_i801(adap)) + queue_work(system_long_wq, &i2c_work); + break; + case BUS_NOTIFY_REMOVED_DEVICE: + client = i2c_verify_client(dev); + if (!client) + break; + + if (i2c_dev == client) { + dev_dbg(&client->adapter->dev, "lis3lv02d i2c_client removed\n"); + i2c_dev = NULL; + } + break; + default: + break; + } + + return 0; +} +static struct notifier_block i2c_nb = { .notifier_call = i2c_bus_notify }; + +static int __init match_acpi_device_ids(struct device *dev, const void *data) +{ + return acpi_match_device(data, dev) ? 1 : 0; +} + +static int __init dell_lis3lv02d_init(void) +{ + const struct dmi_system_id *lis3lv02d_dmi_id; + struct device *dev; + int err; + + /* + * First check for a matching platform_device. This protects against + * SMO88xx ACPI fwnodes which actually do have an I2C resource, which + * will already have an i2c_client instantiated (not a platform_device). + */ + dev = bus_find_device(&platform_bus_type, NULL, smo8800_ids, match_acpi_device_ids); + if (!dev) { + pr_debug("No SMO88xx platform-device found\n"); + return 0; + } + put_device(dev); + + lis3lv02d_dmi_id = dmi_first_match(lis3lv02d_devices); + if (!lis3lv02d_dmi_id && !probe_i2c_addr) { + pr_warn("accelerometer is present on SMBus but its address is unknown, skipping registration\n"); + pr_info("Pass dell_lis3lv02d.probe_i2c_addr=1 on the kernel command line to probe, this may be dangerous!\n"); + return 0; + } + + if (lis3lv02d_dmi_id) + i2c_addr = (long)lis3lv02d_dmi_id->driver_data; + + /* + * Register i2c-bus notifier + queue initial scan for lis3lv02d + * i2c_client instantiation. + */ + err = bus_register_notifier(&i2c_bus_type, &i2c_nb); + if (err) + return err; + + notifier_registered = true; + + queue_work(system_long_wq, &i2c_work); + return 0; +} +module_init(dell_lis3lv02d_init); + +static void __exit dell_lis3lv02d_module_exit(void) +{ + if (!notifier_registered) + return; + + bus_unregister_notifier(&i2c_bus_type, &i2c_nb); + cancel_work_sync(&i2c_work); + i2c_unregister_device(i2c_dev); +} +module_exit(dell_lis3lv02d_module_exit); + +MODULE_DESCRIPTION("lis3lv02d i2c-client instantiation for ACPI SMO88xx devices"); +MODULE_AUTHOR("Hans de Goede "); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell/dell-pc.c b/drivers/platform/x86/dell/dell-pc.c index 972385ca1990..483240bb36e7 100644 --- a/drivers/platform/x86/dell/dell-pc.c +++ b/drivers/platform/x86/dell/dell-pc.c @@ -18,10 +18,14 @@ #include #include #include +#include #include #include "dell-smbios.h" +static struct platform_device *platform_device; +static int supported_modes; + static const struct dmi_system_id dell_device_table[] __initconst = { { .ident = "Dell Inc.", @@ -105,8 +109,6 @@ MODULE_DEVICE_TABLE(dmi, dell_device_table); #define DELL_ACC_SET_FIELD GENMASK(11, 8) #define DELL_THERMAL_SUPPORTED GENMASK(3, 0) -static struct platform_profile_handler *thermal_handler; - enum thermal_mode_bits { DELL_BALANCED = BIT(0), DELL_COOL_BOTTOM = BIT(1), @@ -182,7 +184,7 @@ static int thermal_set_mode(enum thermal_mode_bits state) return dell_send_request(&buffer, CLASS_INFO, SELECT_THERMAL_MANAGEMENT); } -static int thermal_platform_profile_set(struct platform_profile_handler *pprof, +static int thermal_platform_profile_set(struct device *dev, enum platform_profile_option profile) { switch (profile) { @@ -199,7 +201,7 @@ static int thermal_platform_profile_set(struct platform_profile_handler *pprof, } } -static int thermal_platform_profile_get(struct platform_profile_handler *pprof, +static int thermal_platform_profile_get(struct device *dev, enum platform_profile_option *profile) { int ret; @@ -228,10 +230,30 @@ static int thermal_platform_profile_get(struct platform_profile_handler *pprof, return 0; } +static int thermal_platform_profile_probe(void *drvdata, unsigned long *choices) +{ + if (supported_modes & DELL_QUIET) + set_bit(PLATFORM_PROFILE_QUIET, choices); + if (supported_modes & DELL_COOL_BOTTOM) + set_bit(PLATFORM_PROFILE_COOL, choices); + if (supported_modes & DELL_BALANCED) + set_bit(PLATFORM_PROFILE_BALANCED, choices); + if (supported_modes & DELL_PERFORMANCE) + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + + return 0; +} + +static const struct platform_profile_ops dell_pc_platform_profile_ops = { + .probe = thermal_platform_profile_probe, + .profile_get = thermal_platform_profile_get, + .profile_set = thermal_platform_profile_set, +}; + static int thermal_init(void) { + struct device *ppdev; int ret; - int supported_modes; /* If thermal commands are not supported, exit without error */ if (!dell_smbios_class_is_supported(CLASS_INFO)) @@ -244,37 +266,28 @@ static int thermal_init(void) if (!supported_modes) return 0; - thermal_handler = kzalloc(sizeof(*thermal_handler), GFP_KERNEL); - if (!thermal_handler) - return -ENOMEM; - thermal_handler->profile_get = thermal_platform_profile_get; - thermal_handler->profile_set = thermal_platform_profile_set; + platform_device = platform_device_register_simple("dell-pc", PLATFORM_DEVID_NONE, NULL, 0); + if (IS_ERR(platform_device)) + return PTR_ERR(platform_device); - if (supported_modes & DELL_QUIET) - set_bit(PLATFORM_PROFILE_QUIET, thermal_handler->choices); - if (supported_modes & DELL_COOL_BOTTOM) - set_bit(PLATFORM_PROFILE_COOL, thermal_handler->choices); - if (supported_modes & DELL_BALANCED) - set_bit(PLATFORM_PROFILE_BALANCED, thermal_handler->choices); - if (supported_modes & DELL_PERFORMANCE) - set_bit(PLATFORM_PROFILE_PERFORMANCE, thermal_handler->choices); - - /* Clean up if failed */ - ret = platform_profile_register(thermal_handler); - if (ret) { - kfree(thermal_handler); - thermal_handler = NULL; + ppdev = devm_platform_profile_register(&platform_device->dev, "dell-pc", + NULL, &dell_pc_platform_profile_ops); + if (IS_ERR(ppdev)) { + ret = PTR_ERR(ppdev); + goto cleanup_platform_device; } + return 0; + +cleanup_platform_device: + platform_device_unregister(platform_device); + return ret; } static void thermal_cleanup(void) { - if (thermal_handler) { - platform_profile_remove(); - kfree(thermal_handler); - } + platform_device_unregister(platform_device); } static int __init dell_init(void) diff --git a/drivers/platform/x86/dell/dell-smo8800-ids.h b/drivers/platform/x86/dell/dell-smo8800-ids.h new file mode 100644 index 000000000000..ec58e229ba7a --- /dev/null +++ b/drivers/platform/x86/dell/dell-smo8800-ids.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * ACPI SMO88XX lis3lv02d freefall / accelerometer device-ids. + * + * Copyright (C) 2012 Sonal Santan + * Copyright (C) 2014 Pali Rohár + */ +#ifndef _DELL_SMO8800_IDS_H_ +#define _DELL_SMO8800_IDS_H_ + +#include +#include + +static const struct acpi_device_id smo8800_ids[] = { + { "SMO8800" }, + { "SMO8801" }, + { "SMO8810" }, + { "SMO8811" }, + { "SMO8820" }, + { "SMO8821" }, + { "SMO8830" }, + { "SMO8831" }, + { } +}; +MODULE_DEVICE_TABLE(acpi, smo8800_ids); + +#endif diff --git a/drivers/platform/x86/dell/dell-smo8800.c b/drivers/platform/x86/dell/dell-smo8800.c index 87fe03f23f24..8872f9b57fce 100644 --- a/drivers/platform/x86/dell/dell-smo8800.c +++ b/drivers/platform/x86/dell/dell-smo8800.c @@ -14,10 +14,10 @@ #include #include #include -#include #include #include #include +#include "dell-smo8800-ids.h" struct smo8800_device { u32 irq; /* acpi device irq */ @@ -163,20 +163,6 @@ static void smo8800_remove(struct platform_device *device) dev_dbg(&device->dev, "device /dev/freefall unregistered\n"); } -/* NOTE: Keep this list in sync with drivers/i2c/busses/i2c-i801.c */ -static const struct acpi_device_id smo8800_ids[] = { - { "SMO8800", 0 }, - { "SMO8801", 0 }, - { "SMO8810", 0 }, - { "SMO8811", 0 }, - { "SMO8820", 0 }, - { "SMO8821", 0 }, - { "SMO8830", 0 }, - { "SMO8831", 0 }, - { "", 0 }, -}; -MODULE_DEVICE_TABLE(acpi, smo8800_ids); - static struct platform_driver smo8800_driver = { .probe = smo8800_probe, .remove = smo8800_remove, diff --git a/drivers/platform/x86/dell/dell-uart-backlight.c b/drivers/platform/x86/dell/dell-uart-backlight.c index 6e5dc7e3674f..50002ef13d5d 100644 --- a/drivers/platform/x86/dell/dell-uart-backlight.c +++ b/drivers/platform/x86/dell/dell-uart-backlight.c @@ -159,7 +159,7 @@ static int dell_uart_set_bl_power(struct dell_uart_backlight *dell_bl, int power set_power[0] = DELL_SOF(SET_CMD_LEN); set_power[1] = CMD_SET_BL_POWER; - set_power[2] = (power == FB_BLANK_UNBLANK) ? 1 : 0; + set_power[2] = (power == BACKLIGHT_POWER_ON) ? 1 : 0; set_power[3] = dell_uart_checksum(set_power, 3); ret = dell_uart_bl_command(dell_bl, set_power, SET_CMD_LEN, resp, SET_RESP_LEN); @@ -283,6 +283,9 @@ static int dell_uart_bl_serdev_probe(struct serdev_device *serdev) init_waitqueue_head(&dell_bl->wait_queue); dell_bl->dev = dev; + serdev_device_set_drvdata(serdev, dell_bl); + serdev_device_set_client_ops(serdev, &dell_uart_bl_serdev_ops); + ret = devm_serdev_device_open(dev, serdev); if (ret) return dev_err_probe(dev, ret, "opening UART device\n"); @@ -290,8 +293,6 @@ static int dell_uart_bl_serdev_probe(struct serdev_device *serdev) /* 9600 bps, no flow control, these are the default but set them to be sure */ serdev_device_set_baudrate(serdev, 9600); serdev_device_set_flow_control(serdev, false); - serdev_device_set_drvdata(serdev, dell_bl); - serdev_device_set_client_ops(serdev, &dell_uart_bl_serdev_ops); get_version[0] = DELL_SOF(GET_CMD_LEN); get_version[1] = CMD_GET_VERSION; diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c index 40ddc6eb7562..d00389b860e4 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c @@ -25,7 +25,6 @@ struct wmi_sysman_priv wmi_priv = { /* reset bios to defaults */ static const char * const reset_types[] = {"builtinsafe", "lastknowngood", "factory", "custom"}; static int reset_option = -1; -static const struct class *fw_attr_class; /** @@ -541,15 +540,11 @@ static int __init sysman_init(void) goto err_exit_bios_attr_pass_interface; } - ret = fw_attributes_class_get(&fw_attr_class); - if (ret) - goto err_exit_bios_attr_pass_interface; - - wmi_priv.class_dev = device_create(fw_attr_class, NULL, MKDEV(0, 0), + wmi_priv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0), NULL, "%s", DRIVER_NAME); if (IS_ERR(wmi_priv.class_dev)) { ret = PTR_ERR(wmi_priv.class_dev); - goto err_unregister_class; + goto err_exit_bios_attr_pass_interface; } wmi_priv.main_dir_kset = kset_create_and_add("attributes", NULL, @@ -602,10 +597,7 @@ err_release_attributes_data: release_attributes_data(); err_destroy_classdev: - device_destroy(fw_attr_class, MKDEV(0, 0)); - -err_unregister_class: - fw_attributes_class_put(); + device_destroy(&firmware_attributes_class, MKDEV(0, 0)); err_exit_bios_attr_pass_interface: exit_bios_attr_pass_interface(); @@ -619,8 +611,7 @@ err_exit_bios_attr_set_interface: static void __exit sysman_exit(void) { release_attributes_data(); - device_destroy(fw_attr_class, MKDEV(0, 0)); - fw_attributes_class_put(); + device_destroy(&firmware_attributes_class, MKDEV(0, 0)); exit_bios_attr_set_interface(); exit_bios_attr_pass_interface(); } diff --git a/drivers/platform/x86/dell/dell_rbu.c b/drivers/platform/x86/dell/dell_rbu.c index 9f51e0fcab04..e30ca325938c 100644 --- a/drivers/platform/x86/dell/dell_rbu.c +++ b/drivers/platform/x86/dell/dell_rbu.c @@ -475,7 +475,7 @@ static ssize_t read_rbu_mono_data(char *buffer, loff_t pos, size_t count) } static ssize_t data_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { ssize_t ret_count = 0; @@ -492,7 +492,7 @@ static ssize_t data_read(struct file *filp, struct kobject *kobj, spin_unlock(&rbu_data.lock); return ret_count; } -static BIN_ATTR_RO(data, 0); +static const BIN_ATTR_RO(data, 0); static void callbackfn_rbu(const struct firmware *fw, void *context) { @@ -530,7 +530,7 @@ static void callbackfn_rbu(const struct firmware *fw, void *context) } static ssize_t image_type_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { int size = 0; @@ -540,7 +540,7 @@ static ssize_t image_type_read(struct file *filp, struct kobject *kobj, } static ssize_t image_type_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { int rc = count; @@ -597,10 +597,10 @@ static ssize_t image_type_write(struct file *filp, struct kobject *kobj, return rc; } -static BIN_ATTR_RW(image_type, 0); +static const BIN_ATTR_RW(image_type, 0); static ssize_t packet_size_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { int size = 0; @@ -613,7 +613,7 @@ static ssize_t packet_size_read(struct file *filp, struct kobject *kobj, } static ssize_t packet_size_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { unsigned long temp; @@ -626,9 +626,9 @@ static ssize_t packet_size_write(struct file *filp, struct kobject *kobj, spin_unlock(&rbu_data.lock); return count; } -static BIN_ATTR_RW(packet_size, 0); +static const BIN_ATTR_RW(packet_size, 0); -static struct bin_attribute *rbu_bin_attrs[] = { +static const struct bin_attribute *const rbu_bin_attrs[] = { &bin_attr_data, &bin_attr_image_type, &bin_attr_packet_size, @@ -636,7 +636,7 @@ static struct bin_attribute *rbu_bin_attrs[] = { }; static const struct attribute_group rbu_group = { - .bin_attrs = rbu_bin_attrs, + .bin_attrs_new = rbu_bin_attrs, }; static int __init dcdrbu_init(void) diff --git a/drivers/platform/x86/firmware_attributes_class.c b/drivers/platform/x86/firmware_attributes_class.c index 182a07d8ae3d..736e96c186d9 100644 --- a/drivers/platform/x86/firmware_attributes_class.c +++ b/drivers/platform/x86/firmware_attributes_class.c @@ -2,51 +2,25 @@ /* Firmware attributes class helper module */ -#include -#include #include #include "firmware_attributes_class.h" -static DEFINE_MUTEX(fw_attr_lock); -static int fw_attr_inuse; - -static const struct class firmware_attributes_class = { +const struct class firmware_attributes_class = { .name = "firmware-attributes", }; +EXPORT_SYMBOL_GPL(firmware_attributes_class); -int fw_attributes_class_get(const struct class **fw_attr_class) +static __init int fw_attributes_class_init(void) { - int err; - - mutex_lock(&fw_attr_lock); - if (!fw_attr_inuse) { /*first time class is being used*/ - err = class_register(&firmware_attributes_class); - if (err) { - mutex_unlock(&fw_attr_lock); - return err; - } - } - fw_attr_inuse++; - *fw_attr_class = &firmware_attributes_class; - mutex_unlock(&fw_attr_lock); - return 0; + return class_register(&firmware_attributes_class); } -EXPORT_SYMBOL_GPL(fw_attributes_class_get); +module_init(fw_attributes_class_init); -int fw_attributes_class_put(void) +static __exit void fw_attributes_class_exit(void) { - mutex_lock(&fw_attr_lock); - if (!fw_attr_inuse) { - mutex_unlock(&fw_attr_lock); - return -EINVAL; - } - fw_attr_inuse--; - if (!fw_attr_inuse) /* No more consumers */ - class_unregister(&firmware_attributes_class); - mutex_unlock(&fw_attr_lock); - return 0; + class_unregister(&firmware_attributes_class); } -EXPORT_SYMBOL_GPL(fw_attributes_class_put); +module_exit(fw_attributes_class_exit); MODULE_AUTHOR("Mark Pearson "); MODULE_DESCRIPTION("Firmware attributes class helper module"); diff --git a/drivers/platform/x86/firmware_attributes_class.h b/drivers/platform/x86/firmware_attributes_class.h index 363c75f1ac1b..d27abe54fcf9 100644 --- a/drivers/platform/x86/firmware_attributes_class.h +++ b/drivers/platform/x86/firmware_attributes_class.h @@ -5,7 +5,8 @@ #ifndef FW_ATTR_CLASS_H #define FW_ATTR_CLASS_H -int fw_attributes_class_get(const struct class **fw_attr_class); -int fw_attributes_class_put(void); +#include + +extern const struct class firmware_attributes_class; #endif /* FW_ATTR_CLASS_H */ diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index ae992ac1ab4a..a0eae24ca9e6 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -505,8 +505,8 @@ static int acpi_fujitsu_bl_add(struct acpi_device *device) return -ENOMEM; fujitsu_bl = priv; - strcpy(acpi_device_name(device), ACPI_FUJITSU_BL_DEVICE_NAME); - strcpy(acpi_device_class(device), ACPI_FUJITSU_CLASS); + strscpy(acpi_device_name(device), ACPI_FUJITSU_BL_DEVICE_NAME); + strscpy(acpi_device_class(device), ACPI_FUJITSU_CLASS); device->driver_data = priv; pr_info("ACPI: %s [%s]\n", @@ -891,8 +891,8 @@ static int acpi_fujitsu_laptop_add(struct acpi_device *device) WARN_ONCE(fext, "More than one FUJ02E3 ACPI device was found. Driver may not work as intended."); fext = device; - strcpy(acpi_device_name(device), ACPI_FUJITSU_LAPTOP_DEVICE_NAME); - strcpy(acpi_device_class(device), ACPI_FUJITSU_CLASS); + strscpy(acpi_device_name(device), ACPI_FUJITSU_LAPTOP_DEVICE_NAME); + strscpy(acpi_device_class(device), ACPI_FUJITSU_CLASS); device->driver_data = priv; /* kfifo */ diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c index 2dc50152158a..0b277b7e37dd 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c @@ -24,8 +24,6 @@ struct bioscfg_priv bioscfg_drv = { .mutex = __MUTEX_INITIALIZER(bioscfg_drv.mutex), }; -static const struct class *fw_attr_class; - ssize_t display_name_language_code_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -972,11 +970,7 @@ static int __init hp_init(void) if (ret) return ret; - ret = fw_attributes_class_get(&fw_attr_class); - if (ret) - goto err_unregister_class; - - bioscfg_drv.class_dev = device_create(fw_attr_class, NULL, MKDEV(0, 0), + bioscfg_drv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0), NULL, "%s", DRIVER_NAME); if (IS_ERR(bioscfg_drv.class_dev)) { ret = PTR_ERR(bioscfg_drv.class_dev); @@ -1043,10 +1037,9 @@ err_release_attributes_data: release_attributes_data(); err_destroy_classdev: - device_destroy(fw_attr_class, MKDEV(0, 0)); + device_destroy(&firmware_attributes_class, MKDEV(0, 0)); err_unregister_class: - fw_attributes_class_put(); hp_exit_attr_set_interface(); return ret; @@ -1055,9 +1048,8 @@ err_unregister_class: static void __exit hp_exit(void) { release_attributes_data(); - device_destroy(fw_attr_class, MKDEV(0, 0)); + device_destroy(&firmware_attributes_class, MKDEV(0, 0)); - fw_attributes_class_put(); hp_exit_attr_set_interface(); } diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 81ccc96ffe40..db5fdee2109c 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -45,6 +45,10 @@ MODULE_ALIAS("wmi:5FB7F034-2C63-45E9-BE91-3D44E2C707E4"); #define HP_OMEN_EC_THERMAL_PROFILE_TIMER_OFFSET 0x63 #define HP_OMEN_EC_THERMAL_PROFILE_OFFSET 0x95 +#define HP_FAN_SPEED_AUTOMATIC 0x00 +#define HP_POWER_LIMIT_DEFAULT 0x00 +#define HP_POWER_LIMIT_NO_CHANGE 0xFF + #define ACPI_AC_CLASS "ac_adapter" #define zero_if_sup(tmp) (zero_insize_support?0:sizeof(tmp)) // use when zero insize is required @@ -64,7 +68,7 @@ static const char * const omen_thermal_profile_boards[] = { "874A", "8603", "8604", "8748", "886B", "886C", "878A", "878B", "878C", "88C8", "88CB", "8786", "8787", "8788", "88D1", "88D2", "88F4", "88FD", "88F5", "88F6", "88F7", "88FE", "88FF", "8900", "8901", "8902", "8912", - "8917", "8918", "8949", "894A", "89EB", "8BAD", "8A42" + "8917", "8918", "8949", "894A", "89EB", "8BAD", "8A42", "8A15" }; /* DMI Board names of Omen laptops that are specifically set to be thermal @@ -80,14 +84,19 @@ static const char * const omen_thermal_profile_force_v0_boards[] = { * "balanced" when reaching zero. */ static const char * const omen_timed_thermal_profile_boards[] = { - "8BAD", "8A42" + "8BAD", "8A42", "8A15" }; -/* DMI Board names of Victus laptops */ +/* DMI Board names of Victus 16-d1xxx laptops */ static const char * const victus_thermal_profile_boards[] = { "8A25" }; +/* DMI Board names of Victus 16-s1000 laptops */ +static const char * const victus_s_thermal_profile_boards[] = { + "8C9C" +}; + enum hp_wmi_radio { HPWMI_WIFI = 0x0, HPWMI_BLUETOOTH = 0x1, @@ -147,12 +156,32 @@ enum hp_wmi_commandtype { HPWMI_THERMAL_PROFILE_QUERY = 0x4c, }; +struct victus_power_limits { + u8 pl1; + u8 pl2; + u8 pl4; + u8 cpu_gpu_concurrent_limit; +}; + +struct victus_gpu_power_modes { + u8 ctgp_enable; + u8 ppab_enable; + u8 dstate; + u8 gpu_slowdown_temp; +}; + enum hp_wmi_gm_commandtype { - HPWMI_FAN_SPEED_GET_QUERY = 0x11, - HPWMI_SET_PERFORMANCE_MODE = 0x1A, - HPWMI_FAN_SPEED_MAX_GET_QUERY = 0x26, - HPWMI_FAN_SPEED_MAX_SET_QUERY = 0x27, - HPWMI_GET_SYSTEM_DESIGN_DATA = 0x28, + HPWMI_FAN_SPEED_GET_QUERY = 0x11, + HPWMI_SET_PERFORMANCE_MODE = 0x1A, + HPWMI_FAN_SPEED_MAX_GET_QUERY = 0x26, + HPWMI_FAN_SPEED_MAX_SET_QUERY = 0x27, + HPWMI_GET_SYSTEM_DESIGN_DATA = 0x28, + HPWMI_FAN_COUNT_GET_QUERY = 0x10, + HPWMI_GET_GPU_THERMAL_MODES_QUERY = 0x21, + HPWMI_SET_GPU_THERMAL_MODES_QUERY = 0x22, + HPWMI_SET_POWER_LIMITS_QUERY = 0x29, + HPWMI_VICTUS_S_FAN_SPEED_GET_QUERY = 0x2D, + HPWMI_FAN_SPEED_SET_QUERY = 0x2E, }; enum hp_wmi_command { @@ -211,6 +240,11 @@ enum hp_thermal_profile_victus { HP_VICTUS_THERMAL_PROFILE_QUIET = 0x03, }; +enum hp_thermal_profile_victus_s { + HP_VICTUS_S_THERMAL_PROFILE_DEFAULT = 0x00, + HP_VICTUS_S_THERMAL_PROFILE_PERFORMANCE = 0x01, +}; + enum hp_thermal_profile { HP_THERMAL_PROFILE_PERFORMANCE = 0x00, HP_THERMAL_PROFILE_DEFAULT = 0x01, @@ -273,7 +307,7 @@ static DEFINE_MUTEX(active_platform_profile_lock); static struct input_dev *hp_wmi_input_dev; static struct input_dev *camera_shutter_input_dev; static struct platform_device *hp_wmi_platform_dev; -static struct platform_profile_handler platform_profile_handler; +static struct device *platform_profile_device; static struct notifier_block platform_power_source_nb; static enum platform_profile_option active_platform_profile; static bool platform_profile_support; @@ -411,6 +445,26 @@ out_free: return ret; } +/* + * Calling this hp_wmi_get_fan_count_userdefine_trigger function also enables + * and/or maintains the laptop in user defined thermal and fan states, instead + * of using a fallback state. After a 120 seconds timeout however, the laptop + * goes back to its fallback state. + */ +static int hp_wmi_get_fan_count_userdefine_trigger(void) +{ + u8 fan_data[4] = {}; + int ret; + + ret = hp_wmi_perform_query(HPWMI_FAN_COUNT_GET_QUERY, HPWMI_GM, + &fan_data, sizeof(u8), + sizeof(fan_data)); + if (ret != 0) + return -EINVAL; + + return fan_data[0]; /* Others bytes aren't providing fan count */ +} + static int hp_wmi_get_fan_speed(int fan) { u8 fsh, fsl; @@ -429,6 +483,23 @@ static int hp_wmi_get_fan_speed(int fan) return (fsh << 8) | fsl; } +static int hp_wmi_get_fan_speed_victus_s(int fan) +{ + u8 fan_data[128] = {}; + int ret; + + if (fan < 0 || fan >= sizeof(fan_data)) + return -EINVAL; + + ret = hp_wmi_perform_query(HPWMI_VICTUS_S_FAN_SPEED_GET_QUERY, + HPWMI_GM, &fan_data, sizeof(u8), + sizeof(fan_data)); + if (ret != 0) + return -EINVAL; + + return fan_data[fan] * 100; +} + static int hp_wmi_read_int(int query) { int val = 0, ret; @@ -557,6 +628,30 @@ static int hp_wmi_fan_speed_max_set(int enabled) return enabled; } +static int hp_wmi_fan_speed_reset(void) +{ + u8 fan_speed[2] = { HP_FAN_SPEED_AUTOMATIC, HP_FAN_SPEED_AUTOMATIC }; + int ret; + + ret = hp_wmi_perform_query(HPWMI_FAN_SPEED_SET_QUERY, HPWMI_GM, + &fan_speed, sizeof(fan_speed), 0); + + return ret; +} + +static int hp_wmi_fan_speed_max_reset(void) +{ + int ret; + + ret = hp_wmi_fan_speed_max_set(0); + if (ret) + return ret; + + /* Disabling max fan speed on Victus s1xxx laptops needs a 2nd step: */ + ret = hp_wmi_fan_speed_reset(); + return ret; +} + static int hp_wmi_fan_speed_max_get(void) { int val = 0, ret; @@ -1221,7 +1316,7 @@ static int platform_profile_omen_get_ec(enum platform_profile_option *profile) return 0; } -static int platform_profile_omen_get(struct platform_profile_handler *pprof, +static int platform_profile_omen_get(struct device *dev, enum platform_profile_option *profile) { /* @@ -1318,7 +1413,7 @@ static int platform_profile_omen_set_ec(enum platform_profile_option profile) return 0; } -static int platform_profile_omen_set(struct platform_profile_handler *pprof, +static int platform_profile_omen_set(struct device *dev, enum platform_profile_option profile) { int err; @@ -1345,7 +1440,7 @@ static int thermal_profile_set(int thermal_profile) sizeof(thermal_profile), 0); } -static int hp_wmi_platform_profile_get(struct platform_profile_handler *pprof, +static int hp_wmi_platform_profile_get(struct device *dev, enum platform_profile_option *profile) { int tp; @@ -1374,7 +1469,7 @@ static int hp_wmi_platform_profile_get(struct platform_profile_handler *pprof, return 0; } -static int hp_wmi_platform_profile_set(struct platform_profile_handler *pprof, +static int hp_wmi_platform_profile_set(struct device *dev, enum platform_profile_option profile) { int err, tp; @@ -1440,11 +1535,11 @@ static int platform_profile_victus_get_ec(enum platform_profile_option *profile) return 0; } -static int platform_profile_victus_get(struct platform_profile_handler *pprof, +static int platform_profile_victus_get(struct device *dev, enum platform_profile_option *profile) { /* Same behaviour as platform_profile_omen_get */ - return platform_profile_omen_get(pprof, profile); + return platform_profile_omen_get(dev, profile); } static int platform_profile_victus_set_ec(enum platform_profile_option profile) @@ -1472,7 +1567,162 @@ static int platform_profile_victus_set_ec(enum platform_profile_option profile) return 0; } -static int platform_profile_victus_set(struct platform_profile_handler *pprof, +static bool is_victus_s_thermal_profile(void) +{ + const char *board_name; + + board_name = dmi_get_system_info(DMI_BOARD_NAME); + if (!board_name) + return false; + + return match_string(victus_s_thermal_profile_boards, + ARRAY_SIZE(victus_s_thermal_profile_boards), + board_name) >= 0; +} + +static int victus_s_gpu_thermal_profile_get(bool *ctgp_enable, + bool *ppab_enable, + u8 *dstate, + u8 *gpu_slowdown_temp) +{ + struct victus_gpu_power_modes gpu_power_modes; + int ret; + + ret = hp_wmi_perform_query(HPWMI_GET_GPU_THERMAL_MODES_QUERY, HPWMI_GM, + &gpu_power_modes, sizeof(gpu_power_modes), + sizeof(gpu_power_modes)); + if (ret == 0) { + *ctgp_enable = gpu_power_modes.ctgp_enable ? true : false; + *ppab_enable = gpu_power_modes.ppab_enable ? true : false; + *dstate = gpu_power_modes.dstate; + *gpu_slowdown_temp = gpu_power_modes.gpu_slowdown_temp; + } + + return ret; +} + +static int victus_s_gpu_thermal_profile_set(bool ctgp_enable, + bool ppab_enable, + u8 dstate) +{ + struct victus_gpu_power_modes gpu_power_modes; + int ret; + + bool current_ctgp_state, current_ppab_state; + u8 current_dstate, current_gpu_slowdown_temp; + + /* Retrieving GPU slowdown temperature, in order to keep it unchanged */ + ret = victus_s_gpu_thermal_profile_get(¤t_ctgp_state, + ¤t_ppab_state, + ¤t_dstate, + ¤t_gpu_slowdown_temp); + if (ret < 0) { + pr_warn("GPU modes not updated, unable to get slowdown temp\n"); + return ret; + } + + gpu_power_modes.ctgp_enable = ctgp_enable ? 0x01 : 0x00; + gpu_power_modes.ppab_enable = ppab_enable ? 0x01 : 0x00; + gpu_power_modes.dstate = dstate; + gpu_power_modes.gpu_slowdown_temp = current_gpu_slowdown_temp; + + + ret = hp_wmi_perform_query(HPWMI_SET_GPU_THERMAL_MODES_QUERY, HPWMI_GM, + &gpu_power_modes, sizeof(gpu_power_modes), 0); + + return ret; +} + +/* Note: HP_POWER_LIMIT_DEFAULT can be used to restore default PL1 and PL2 */ +static int victus_s_set_cpu_pl1_pl2(u8 pl1, u8 pl2) +{ + struct victus_power_limits power_limits; + int ret; + + /* We need to know both PL1 and PL2 values in order to check them */ + if (pl1 == HP_POWER_LIMIT_NO_CHANGE || pl2 == HP_POWER_LIMIT_NO_CHANGE) + return -EINVAL; + + /* PL2 is not supposed to be lower than PL1 */ + if (pl2 < pl1) + return -EINVAL; + + power_limits.pl1 = pl1; + power_limits.pl2 = pl2; + power_limits.pl4 = HP_POWER_LIMIT_NO_CHANGE; + power_limits.cpu_gpu_concurrent_limit = HP_POWER_LIMIT_NO_CHANGE; + + ret = hp_wmi_perform_query(HPWMI_SET_POWER_LIMITS_QUERY, HPWMI_GM, + &power_limits, sizeof(power_limits), 0); + + return ret; +} + +static int platform_profile_victus_s_set_ec(enum platform_profile_option profile) +{ + bool gpu_ctgp_enable, gpu_ppab_enable; + u8 gpu_dstate; /* Test shows 1 = 100%, 2 = 50%, 3 = 25%, 4 = 12.5% */ + int err, tp; + + switch (profile) { + case PLATFORM_PROFILE_PERFORMANCE: + tp = HP_VICTUS_S_THERMAL_PROFILE_PERFORMANCE; + gpu_ctgp_enable = true; + gpu_ppab_enable = true; + gpu_dstate = 1; + break; + case PLATFORM_PROFILE_BALANCED: + tp = HP_VICTUS_S_THERMAL_PROFILE_DEFAULT; + gpu_ctgp_enable = false; + gpu_ppab_enable = true; + gpu_dstate = 1; + break; + case PLATFORM_PROFILE_LOW_POWER: + tp = HP_VICTUS_S_THERMAL_PROFILE_DEFAULT; + gpu_ctgp_enable = false; + gpu_ppab_enable = false; + gpu_dstate = 1; + break; + default: + return -EOPNOTSUPP; + } + + hp_wmi_get_fan_count_userdefine_trigger(); + + err = omen_thermal_profile_set(tp); + if (err < 0) { + pr_err("Failed to set platform profile %d: %d\n", profile, err); + return err; + } + + err = victus_s_gpu_thermal_profile_set(gpu_ctgp_enable, + gpu_ppab_enable, + gpu_dstate); + if (err < 0) { + pr_err("Failed to set GPU profile %d: %d\n", profile, err); + return err; + } + + return 0; +} + +static int platform_profile_victus_s_set(struct device *dev, + enum platform_profile_option profile) +{ + int err; + + guard(mutex)(&active_platform_profile_lock); + + err = platform_profile_victus_s_set_ec(profile); + if (err < 0) + return err; + + active_platform_profile = profile; + + return 0; +} + +static int platform_profile_victus_set(struct device *dev, enum platform_profile_option profile) { int err; @@ -1488,6 +1738,26 @@ static int platform_profile_victus_set(struct platform_profile_handler *pprof, return 0; } +static int hp_wmi_platform_profile_probe(void *drvdata, unsigned long *choices) +{ + if (is_omen_thermal_profile()) { + set_bit(PLATFORM_PROFILE_COOL, choices); + } else if (is_victus_thermal_profile()) { + set_bit(PLATFORM_PROFILE_QUIET, choices); + } else if (is_victus_s_thermal_profile()) { + /* Adding an equivalent to HP Omen software ECO mode: */ + set_bit(PLATFORM_PROFILE_LOW_POWER, choices); + } else { + set_bit(PLATFORM_PROFILE_QUIET, choices); + set_bit(PLATFORM_PROFILE_COOL, choices); + } + + set_bit(PLATFORM_PROFILE_BALANCED, choices); + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + + return 0; +} + static int omen_powersource_event(struct notifier_block *nb, unsigned long value, void *data) @@ -1545,6 +1815,39 @@ static int omen_powersource_event(struct notifier_block *nb, return NOTIFY_OK; } +static int victus_s_powersource_event(struct notifier_block *nb, + unsigned long value, + void *data) +{ + struct acpi_bus_event *event_entry = data; + int err; + + if (strcmp(event_entry->device_class, ACPI_AC_CLASS) != 0) + return NOTIFY_DONE; + + pr_debug("Received power source device event\n"); + + /* + * Switching to battery power source while Performance mode is active + * needs manual triggering of CPU power limits. Same goes when switching + * to AC power source while Performance mode is active. Other modes + * however are automatically behaving without any manual action. + * Seen on HP 16-s1034nf (board 8C9C) with F.11 and F.13 BIOS versions. + */ + + if (active_platform_profile == PLATFORM_PROFILE_PERFORMANCE) { + pr_debug("Triggering CPU PL1/PL2 actualization\n"); + err = victus_s_set_cpu_pl1_pl2(HP_POWER_LIMIT_DEFAULT, + HP_POWER_LIMIT_DEFAULT); + if (err) + pr_warn("Failed to actualize power limits: %d\n", err); + + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + static int omen_register_powersource_event_handler(void) { int err; @@ -1560,13 +1863,57 @@ static int omen_register_powersource_event_handler(void) return 0; } +static int victus_s_register_powersource_event_handler(void) +{ + int err; + + platform_power_source_nb.notifier_call = victus_s_powersource_event; + err = register_acpi_notifier(&platform_power_source_nb); + if (err < 0) { + pr_warn("Failed to install ACPI power source notify handler\n"); + return err; + } + + return 0; +} + static inline void omen_unregister_powersource_event_handler(void) { unregister_acpi_notifier(&platform_power_source_nb); } -static int thermal_profile_setup(void) +static inline void victus_s_unregister_powersource_event_handler(void) { + unregister_acpi_notifier(&platform_power_source_nb); +} + +static const struct platform_profile_ops platform_profile_omen_ops = { + .probe = hp_wmi_platform_profile_probe, + .profile_get = platform_profile_omen_get, + .profile_set = platform_profile_omen_set, +}; + +static const struct platform_profile_ops platform_profile_victus_ops = { + .probe = hp_wmi_platform_profile_probe, + .profile_get = platform_profile_victus_get, + .profile_set = platform_profile_victus_set, +}; + +static const struct platform_profile_ops platform_profile_victus_s_ops = { + .probe = hp_wmi_platform_profile_probe, + .profile_get = platform_profile_omen_get, + .profile_set = platform_profile_victus_s_set, +}; + +static const struct platform_profile_ops hp_wmi_platform_profile_ops = { + .probe = hp_wmi_platform_profile_probe, + .profile_get = hp_wmi_platform_profile_get, + .profile_set = hp_wmi_platform_profile_set, +}; + +static int thermal_profile_setup(struct platform_device *device) +{ + const struct platform_profile_ops *ops; int err, tp; if (is_omen_thermal_profile()) { @@ -1582,10 +1929,7 @@ static int thermal_profile_setup(void) if (err < 0) return err; - platform_profile_handler.profile_get = platform_profile_omen_get; - platform_profile_handler.profile_set = platform_profile_omen_set; - - set_bit(PLATFORM_PROFILE_COOL, platform_profile_handler.choices); + ops = &platform_profile_omen_ops; } else if (is_victus_thermal_profile()) { err = platform_profile_victus_get_ec(&active_platform_profile); if (err < 0) @@ -1599,10 +1943,19 @@ static int thermal_profile_setup(void) if (err < 0) return err; - platform_profile_handler.profile_get = platform_profile_victus_get; - platform_profile_handler.profile_set = platform_profile_victus_set; + ops = &platform_profile_victus_ops; + } else if (is_victus_s_thermal_profile()) { + /* + * Being unable to retrieve laptop's current thermal profile, + * during this setup, we set it to Balanced by default. + */ + active_platform_profile = PLATFORM_PROFILE_BALANCED; - set_bit(PLATFORM_PROFILE_QUIET, platform_profile_handler.choices); + err = platform_profile_victus_s_set_ec(active_platform_profile); + if (err < 0) + return err; + + ops = &platform_profile_victus_s_ops; } else { tp = thermal_profile_get(); @@ -1617,20 +1970,15 @@ static int thermal_profile_setup(void) if (err) return err; - platform_profile_handler.profile_get = hp_wmi_platform_profile_get; - platform_profile_handler.profile_set = hp_wmi_platform_profile_set; - - set_bit(PLATFORM_PROFILE_QUIET, platform_profile_handler.choices); - set_bit(PLATFORM_PROFILE_COOL, platform_profile_handler.choices); + ops = &hp_wmi_platform_profile_ops; } - set_bit(PLATFORM_PROFILE_BALANCED, platform_profile_handler.choices); - set_bit(PLATFORM_PROFILE_PERFORMANCE, platform_profile_handler.choices); - - err = platform_profile_register(&platform_profile_handler); - if (err) - return err; + platform_profile_device = devm_platform_profile_register(&device->dev, "hp-wmi", + NULL, ops); + if (IS_ERR(platform_profile_device)) + return PTR_ERR(platform_profile_device); + pr_info("Registered as platform profile handler\n"); platform_profile_support = true; return 0; @@ -1663,7 +2011,7 @@ static int __init hp_wmi_bios_setup(struct platform_device *device) if (err < 0) return err; - thermal_profile_setup(); + thermal_profile_setup(device); return 0; } @@ -1689,9 +2037,6 @@ static void __exit hp_wmi_bios_remove(struct platform_device *device) rfkill_unregister(wwan_rfkill); rfkill_destroy(wwan_rfkill); } - - if (platform_profile_support) - platform_profile_remove(); } static int hp_wmi_resume_handler(struct device *device) @@ -1759,8 +2104,13 @@ static umode_t hp_wmi_hwmon_is_visible(const void *data, case hwmon_pwm: return 0644; case hwmon_fan: - if (hp_wmi_get_fan_speed(channel) >= 0) - return 0444; + if (is_victus_s_thermal_profile()) { + if (hp_wmi_get_fan_speed_victus_s(channel) >= 0) + return 0444; + } else { + if (hp_wmi_get_fan_speed(channel) >= 0) + return 0444; + } break; default: return 0; @@ -1776,8 +2126,10 @@ static int hp_wmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type, switch (type) { case hwmon_fan: - ret = hp_wmi_get_fan_speed(channel); - + if (is_victus_s_thermal_profile()) + ret = hp_wmi_get_fan_speed_victus_s(channel); + else + ret = hp_wmi_get_fan_speed(channel); if (ret < 0) return ret; *val = ret; @@ -1810,11 +2162,17 @@ static int hp_wmi_hwmon_write(struct device *dev, enum hwmon_sensor_types type, case hwmon_pwm: switch (val) { case 0: + if (is_victus_s_thermal_profile()) + hp_wmi_get_fan_count_userdefine_trigger(); /* 0 is no fan speed control (max), which is 1 for us */ return hp_wmi_fan_speed_max_set(1); case 2: /* 2 is automatic speed control, which is 0 for us */ - return hp_wmi_fan_speed_max_set(0); + if (is_victus_s_thermal_profile()) { + hp_wmi_get_fan_count_userdefine_trigger(); + return hp_wmi_fan_speed_max_reset(); + } else + return hp_wmi_fan_speed_max_set(0); default: /* we don't support manual fan speed control */ return -EINVAL; @@ -1893,6 +2251,10 @@ static int __init hp_wmi_init(void) err = omen_register_powersource_event_handler(); if (err) goto err_unregister_device; + } else if (is_victus_s_thermal_profile()) { + err = victus_s_register_powersource_event_handler(); + if (err) + goto err_unregister_device; } return 0; @@ -1912,6 +2274,9 @@ static void __exit hp_wmi_exit(void) if (is_omen_thermal_profile() || is_victus_thermal_profile()) omen_unregister_powersource_event_handler(); + if (is_victus_s_thermal_profile()) + victus_s_unregister_powersource_event_handler(); + if (wmi_has_guid(HPWMI_EVENT_GUID)) hp_wmi_input_destroy(); diff --git a/drivers/platform/x86/hp/hp_accel.c b/drivers/platform/x86/hp/hp_accel.c index 39a6530f5072..10d5af18d639 100644 --- a/drivers/platform/x86/hp/hp_accel.c +++ b/drivers/platform/x86/hp/hp_accel.c @@ -267,7 +267,7 @@ static struct delayed_led_classdev hpled_led = { }; static bool hp_accel_i8042_filter(unsigned char data, unsigned char str, - struct serio *port) + struct serio *port, void *context) { static bool extended; @@ -326,7 +326,7 @@ static int lis3lv02d_probe(struct platform_device *device) /* filter to remove HPQ6000 accelerometer data * from keyboard bus stream */ if (strstr(dev_name(&device->dev), "HPQ6000")) - i8042_install_filter(hp_accel_i8042_filter); + i8042_install_filter(hp_accel_i8042_filter, NULL); INIT_WORK(&hpled_led.work, delayed_set_status_worker); ret = led_classdev_register(NULL, &hpled_led.led_classdev); diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index e980dd18e5f6..dfb5d4b8c046 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -142,7 +142,7 @@ enum { struct ideapad_dytc_priv { enum platform_profile_option current_profile; - struct platform_profile_handler pprof; + struct device *ppdev; /* platform profile device */ struct mutex mutex; /* protects the DYTC interface */ struct ideapad_private *priv; }; @@ -933,10 +933,10 @@ static int convert_profile_to_dytc(enum platform_profile_option profile, int *pe * dytc_profile_get: Function to register with platform_profile * handler. Returns current platform profile. */ -static int dytc_profile_get(struct platform_profile_handler *pprof, +static int dytc_profile_get(struct device *dev, enum platform_profile_option *profile) { - struct ideapad_dytc_priv *dytc = container_of(pprof, struct ideapad_dytc_priv, pprof); + struct ideapad_dytc_priv *dytc = dev_get_drvdata(dev); *profile = dytc->current_profile; return 0; @@ -986,10 +986,10 @@ static int dytc_cql_command(struct ideapad_private *priv, unsigned long cmd, * dytc_profile_set: Function to register with platform_profile * handler. Sets current platform profile. */ -static int dytc_profile_set(struct platform_profile_handler *pprof, +static int dytc_profile_set(struct device *dev, enum platform_profile_option profile) { - struct ideapad_dytc_priv *dytc = container_of(pprof, struct ideapad_dytc_priv, pprof); + struct ideapad_dytc_priv *dytc = dev_get_drvdata(dev); struct ideapad_private *priv = dytc->priv; unsigned long output; int err; @@ -1023,6 +1023,15 @@ static int dytc_profile_set(struct platform_profile_handler *pprof, return -EINTR; } +static int dytc_profile_probe(void *drvdata, unsigned long *choices) +{ + set_bit(PLATFORM_PROFILE_LOW_POWER, choices); + set_bit(PLATFORM_PROFILE_BALANCED, choices); + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + + return 0; +} + static void dytc_profile_refresh(struct ideapad_private *priv) { enum platform_profile_option profile; @@ -1041,7 +1050,7 @@ static void dytc_profile_refresh(struct ideapad_private *priv) if (profile != priv->dytc->current_profile) { priv->dytc->current_profile = profile; - platform_profile_notify(); + platform_profile_notify(priv->dytc->ppdev); } } @@ -1063,6 +1072,12 @@ static const struct dmi_system_id ideapad_dytc_v4_allow_table[] = { {} }; +static const struct platform_profile_ops dytc_profile_ops = { + .probe = dytc_profile_probe, + .profile_get = dytc_profile_get, + .profile_set = dytc_profile_set, +}; + static int ideapad_dytc_profile_init(struct ideapad_private *priv) { int err, dytc_version; @@ -1103,18 +1118,15 @@ static int ideapad_dytc_profile_init(struct ideapad_private *priv) mutex_init(&priv->dytc->mutex); priv->dytc->priv = priv; - priv->dytc->pprof.profile_get = dytc_profile_get; - priv->dytc->pprof.profile_set = dytc_profile_set; - - /* Setup supported modes */ - set_bit(PLATFORM_PROFILE_LOW_POWER, priv->dytc->pprof.choices); - set_bit(PLATFORM_PROFILE_BALANCED, priv->dytc->pprof.choices); - set_bit(PLATFORM_PROFILE_PERFORMANCE, priv->dytc->pprof.choices); /* Create platform_profile structure and register */ - err = platform_profile_register(&priv->dytc->pprof); - if (err) + priv->dytc->ppdev = devm_platform_profile_register(&priv->platform_device->dev, + "ideapad-laptop", &priv->dytc, + &dytc_profile_ops); + if (IS_ERR(priv->dytc->ppdev)) { + err = PTR_ERR(priv->dytc->ppdev); goto pp_reg_failed; + } /* Ensure initial values are correct */ dytc_profile_refresh(priv); @@ -1134,7 +1146,6 @@ static void ideapad_dytc_profile_exit(struct ideapad_private *priv) if (!priv->dytc) return; - platform_profile_remove(); mutex_destroy(&priv->dytc->mutex); kfree(priv->dytc); diff --git a/drivers/platform/x86/inspur_platform_profile.c b/drivers/platform/x86/inspur_platform_profile.c index 8440defa6788..e02f5a55a6c5 100644 --- a/drivers/platform/x86/inspur_platform_profile.c +++ b/drivers/platform/x86/inspur_platform_profile.c @@ -32,7 +32,7 @@ enum inspur_tmp_profile { struct inspur_wmi_priv { struct wmi_device *wdev; - struct platform_profile_handler handler; + struct device *ppdev; }; static int inspur_wmi_perform_query(struct wmi_device *wdev, @@ -84,11 +84,10 @@ out_free: * 0x0: No Error * 0x1: Error */ -static int inspur_platform_profile_set(struct platform_profile_handler *pprof, +static int inspur_platform_profile_set(struct device *dev, enum platform_profile_option profile) { - struct inspur_wmi_priv *priv = container_of(pprof, struct inspur_wmi_priv, - handler); + struct inspur_wmi_priv *priv = dev_get_drvdata(dev); u8 ret_code[4] = {0, 0, 0, 0}; int ret; @@ -132,11 +131,10 @@ static int inspur_platform_profile_set(struct platform_profile_handler *pprof, * 0x1: Performance Mode * 0x2: Power Saver Mode */ -static int inspur_platform_profile_get(struct platform_profile_handler *pprof, +static int inspur_platform_profile_get(struct device *dev, enum platform_profile_option *profile) { - struct inspur_wmi_priv *priv = container_of(pprof, struct inspur_wmi_priv, - handler); + struct inspur_wmi_priv *priv = dev_get_drvdata(dev); u8 ret_code[4] = {0, 0, 0, 0}; int ret; @@ -166,6 +164,21 @@ static int inspur_platform_profile_get(struct platform_profile_handler *pprof, return 0; } +static int inspur_platform_profile_probe(void *drvdata, unsigned long *choices) +{ + set_bit(PLATFORM_PROFILE_LOW_POWER, choices); + set_bit(PLATFORM_PROFILE_BALANCED, choices); + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + + return 0; +} + +static const struct platform_profile_ops inspur_platform_profile_ops = { + .probe = inspur_platform_profile_probe, + .profile_get = inspur_platform_profile_get, + .profile_set = inspur_platform_profile_set, +}; + static int inspur_wmi_probe(struct wmi_device *wdev, const void *context) { struct inspur_wmi_priv *priv; @@ -177,19 +190,10 @@ static int inspur_wmi_probe(struct wmi_device *wdev, const void *context) priv->wdev = wdev; dev_set_drvdata(&wdev->dev, priv); - priv->handler.profile_get = inspur_platform_profile_get; - priv->handler.profile_set = inspur_platform_profile_set; + priv->ppdev = devm_platform_profile_register(&wdev->dev, "inspur-wmi", priv, + &inspur_platform_profile_ops); - set_bit(PLATFORM_PROFILE_LOW_POWER, priv->handler.choices); - set_bit(PLATFORM_PROFILE_BALANCED, priv->handler.choices); - set_bit(PLATFORM_PROFILE_PERFORMANCE, priv->handler.choices); - - return platform_profile_register(&priv->handler); -} - -static void inspur_wmi_remove(struct wmi_device *wdev) -{ - platform_profile_remove(); + return PTR_ERR_OR_ZERO(priv->ppdev); } static const struct wmi_device_id inspur_wmi_id_table[] = { @@ -206,7 +210,6 @@ static struct wmi_driver inspur_wmi_driver = { }, .id_table = inspur_wmi_id_table, .probe = inspur_wmi_probe, - .remove = inspur_wmi_remove, .no_singleton = true, }; diff --git a/drivers/platform/x86/intel/Kconfig b/drivers/platform/x86/intel/Kconfig index eb698dcb9af9..19a2246f2770 100644 --- a/drivers/platform/x86/intel/Kconfig +++ b/drivers/platform/x86/intel/Kconfig @@ -83,6 +83,7 @@ config INTEL_BXTWC_PMIC_TMU config INTEL_BYTCRC_PWRSRC tristate "Intel Bay Trail Crystal Cove power source driver" depends on INTEL_SOC_PMIC + depends on POWER_SUPPLY help This option adds a power source driver for Crystal Cove PMICs on Intel Bay Trail devices. diff --git a/drivers/platform/x86/intel/bytcrc_pwrsrc.c b/drivers/platform/x86/intel/bytcrc_pwrsrc.c index 3edc2a9dab38..68ac040082df 100644 --- a/drivers/platform/x86/intel/bytcrc_pwrsrc.c +++ b/drivers/platform/x86/intel/bytcrc_pwrsrc.c @@ -8,13 +8,22 @@ * Copyright (C) 2013 Intel Corporation */ +#include +#include #include +#include #include #include #include +#include +#include #include +#define CRYSTALCOVE_PWRSRC_IRQ 0x03 #define CRYSTALCOVE_SPWRSRC_REG 0x1E +#define CRYSTALCOVE_SPWRSRC_USB BIT(0) +#define CRYSTALCOVE_SPWRSRC_DC BIT(1) +#define CRYSTALCOVE_SPWRSRC_BATTERY BIT(2) #define CRYSTALCOVE_RESETSRC0_REG 0x20 #define CRYSTALCOVE_RESETSRC1_REG 0x21 #define CRYSTALCOVE_WAKESRC_REG 0x22 @@ -22,6 +31,7 @@ struct crc_pwrsrc_data { struct regmap *regmap; struct dentry *debug_dentry; + struct power_supply *psy; unsigned int resetsrc0; unsigned int resetsrc1; unsigned int wakesrc; @@ -118,13 +128,60 @@ static int crc_pwrsrc_read_and_clear(struct crc_pwrsrc_data *data, return regmap_write(data->regmap, reg, *val); } +static irqreturn_t crc_pwrsrc_irq_handler(int irq, void *_data) +{ + struct crc_pwrsrc_data *data = _data; + unsigned int irq_mask; + + if (regmap_read(data->regmap, CRYSTALCOVE_PWRSRC_IRQ, &irq_mask)) + return IRQ_NONE; + + regmap_write(data->regmap, CRYSTALCOVE_PWRSRC_IRQ, irq_mask); + + power_supply_changed(data->psy); + return IRQ_HANDLED; +} + +static int crc_pwrsrc_psy_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct crc_pwrsrc_data *data = power_supply_get_drvdata(psy); + unsigned int pwrsrc; + int ret; + + if (psp != POWER_SUPPLY_PROP_ONLINE) + return -EINVAL; + + ret = regmap_read(data->regmap, CRYSTALCOVE_SPWRSRC_REG, &pwrsrc); + if (ret) + return ret; + + val->intval = !!(pwrsrc & (CRYSTALCOVE_SPWRSRC_USB | + CRYSTALCOVE_SPWRSRC_DC)); + return 0; +} + +static const enum power_supply_property crc_pwrsrc_psy_props[] = { + POWER_SUPPLY_PROP_ONLINE, +}; + +static const struct power_supply_desc crc_pwrsrc_psy_desc = { + .name = "crystal_cove_pwrsrc", + .type = POWER_SUPPLY_TYPE_MAINS, + .properties = crc_pwrsrc_psy_props, + .num_properties = ARRAY_SIZE(crc_pwrsrc_psy_props), + .get_property = crc_pwrsrc_psy_get_property, +}; + static int crc_pwrsrc_probe(struct platform_device *pdev) { struct intel_soc_pmic *pmic = dev_get_drvdata(pdev->dev.parent); + struct device *dev = &pdev->dev; struct crc_pwrsrc_data *data; - int ret; + int irq, ret; - data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -149,6 +206,24 @@ static int crc_pwrsrc_probe(struct platform_device *pdev) if (ret) return ret; + if (device_property_read_bool(dev->parent, "linux,register-pwrsrc-power_supply")) { + struct power_supply_config psy_cfg = { .drv_data = data }; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + data->psy = devm_power_supply_register(dev, &crc_pwrsrc_psy_desc, &psy_cfg); + if (IS_ERR(data->psy)) + return dev_err_probe(dev, PTR_ERR(data->psy), "registering power-supply\n"); + + ret = devm_request_threaded_irq(dev, irq, NULL, + crc_pwrsrc_irq_handler, + IRQF_ONESHOT, KBUILD_MODNAME, data); + if (ret) + return dev_err_probe(dev, ret, "requesting IRQ\n"); + } + data->debug_dentry = debugfs_create_dir(KBUILD_MODNAME, NULL); debugfs_create_file("pwrsrc", 0444, data->debug_dentry, data, &pwrsrc_fops); debugfs_create_file("resetsrc", 0444, data->debug_dentry, data, &resetsrc_fops); diff --git a/drivers/platform/x86/intel/ifs/core.c b/drivers/platform/x86/intel/ifs/core.c index bc252b883210..1ae50702bdb7 100644 --- a/drivers/platform/x86/intel/ifs/core.c +++ b/drivers/platform/x86/intel/ifs/core.c @@ -20,6 +20,7 @@ static const struct x86_cpu_id ifs_cpu_ids[] __initconst = { X86_MATCH(INTEL_GRANITERAPIDS_X, ARRAY_GEN0), X86_MATCH(INTEL_GRANITERAPIDS_D, ARRAY_GEN0), X86_MATCH(INTEL_ATOM_CRESTMONT_X, ARRAY_GEN1), + X86_MATCH(INTEL_ATOM_DARKMONT_X, ARRAY_GEN1), {} }; MODULE_DEVICE_TABLE(x86cpu, ifs_cpu_ids); diff --git a/drivers/platform/x86/intel/int0002_vgpio.c b/drivers/platform/x86/intel/int0002_vgpio.c index 0cc80603a8a9..3b48cd7a4075 100644 --- a/drivers/platform/x86/intel/int0002_vgpio.c +++ b/drivers/platform/x86/intel/int0002_vgpio.c @@ -83,8 +83,12 @@ static void int0002_irq_ack(struct irq_data *data) static void int0002_irq_unmask(struct irq_data *data) { + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + irq_hw_number_t hwirq = irqd_to_hwirq(data); u32 gpe_en_reg; + gpiochip_enable_irq(gc, hwirq); + gpe_en_reg = inl(GPE0A_EN_PORT); gpe_en_reg |= GPE0A_PME_B0_EN_BIT; outl(gpe_en_reg, GPE0A_EN_PORT); @@ -92,11 +96,15 @@ static void int0002_irq_unmask(struct irq_data *data) static void int0002_irq_mask(struct irq_data *data) { + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + irq_hw_number_t hwirq = irqd_to_hwirq(data); u32 gpe_en_reg; gpe_en_reg = inl(GPE0A_EN_PORT); gpe_en_reg &= ~GPE0A_PME_B0_EN_BIT; outl(gpe_en_reg, GPE0A_EN_PORT); + + gpiochip_disable_irq(gc, hwirq); } static int int0002_irq_set_wake(struct irq_data *data, unsigned int on) @@ -140,12 +148,14 @@ static bool int0002_check_wake(void *data) return (gpe_sts_reg & GPE0A_PME_B0_STS_BIT); } -static struct irq_chip int0002_irqchip = { +static const struct irq_chip int0002_irqchip = { .name = DRV_NAME, .irq_ack = int0002_irq_ack, .irq_mask = int0002_irq_mask, .irq_unmask = int0002_irq_unmask, .irq_set_wake = int0002_irq_set_wake, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; static void int0002_init_irq_valid_mask(struct gpio_chip *chip, @@ -203,7 +213,7 @@ static int int0002_probe(struct platform_device *pdev) } girq = &chip->irq; - girq->chip = &int0002_irqchip; + gpio_irq_chip_set_chip(girq, &int0002_irqchip); /* This let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; diff --git a/drivers/platform/x86/intel/int3472/common.c b/drivers/platform/x86/intel/int3472/common.c index b3a2578e06c1..1638be8fa71e 100644 --- a/drivers/platform/x86/intel/int3472/common.c +++ b/drivers/platform/x86/intel/int3472/common.c @@ -70,6 +70,8 @@ int skl_int3472_get_sensor_adev_and_name(struct device *dev, return -ENODEV; } + dev_dbg(dev, "Sensor name %s\n", acpi_dev_name(sensor)); + *name_ret = devm_kasprintf(dev, GFP_KERNEL, I2C_DEV_NAME_FORMAT, acpi_dev_name(sensor)); if (!*name_ret) diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c index d881b2cfcdfc..31015ebe20d8 100644 --- a/drivers/platform/x86/intel/int3472/discrete.c +++ b/drivers/platform/x86/intel/int3472/discrete.c @@ -178,11 +178,11 @@ static void int3472_get_func_and_polarity(u8 type, const char **func, u32 *polar * to create clocks and regulators via the usual frameworks. * * Return: - * * 1 - To continue the loop - * * 0 - When all resources found are handled properly. - * * -EINVAL - If the resource is not a GPIO IO resource - * * -ENODEV - If the resource has no corresponding _DSM entry - * * -Other - Errors propagated from one of the sub-functions. + * * 1 - Continue the loop without adding a copy of the resource to + * * the list passed to acpi_dev_get_resources() + * * 0 - Continue the loop after adding a copy of the resource to + * * the list passed to acpi_dev_get_resources() + * * -errno - Error, break loop */ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, void *data) @@ -220,10 +220,10 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, int3472_get_func_and_polarity(type, &func, &polarity); pin = FIELD_GET(INT3472_GPIO_DSM_PIN, obj->integer.value); - if (pin != agpio->pin_table[0]) - dev_warn(int3472->dev, "%s %s pin number mismatch _DSM %d resource %d\n", - func, agpio->resource_source.string_ptr, pin, - agpio->pin_table[0]); + /* Pin field is not really used under Windows and wraps around at 8 bits */ + if (pin != (agpio->pin_table[0] & 0xff)) + dev_dbg(int3472->dev, FW_BUG "%s %s pin number mismatch _DSM %d resource %d\n", + func, agpio->resource_source.string_ptr, pin, agpio->pin_table[0]); active_value = FIELD_GET(INT3472_GPIO_DSM_SENSOR_ON_VAL, obj->integer.value); if (!active_value) @@ -289,7 +289,8 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, if (ret < 0) return dev_err_probe(int3472->dev, ret, err_msg); - return ret; + /* Tell acpi_dev_get_resources() to not make a copy of the resource */ + return 1; } static int skl_int3472_parse_crs(struct int3472_discrete_device *int3472) @@ -336,6 +337,9 @@ static int skl_int3472_discrete_probe(struct platform_device *pdev) struct int3472_cldb cldb; int ret; + if (!adev) + return -ENODEV; + ret = skl_int3472_fill_cldb(adev, &cldb); if (ret) { dev_err(&pdev->dev, "Couldn't fill CLDB structure\n"); diff --git a/drivers/platform/x86/intel/int3472/tps68470.c b/drivers/platform/x86/intel/int3472/tps68470.c index 1e107fd49f82..81ac4c691963 100644 --- a/drivers/platform/x86/intel/int3472/tps68470.c +++ b/drivers/platform/x86/intel/int3472/tps68470.c @@ -152,6 +152,9 @@ static int skl_int3472_tps68470_probe(struct i2c_client *client) int ret; int i; + if (!adev) + return -ENODEV; + n_consumers = skl_int3472_fill_clk_pdata(&client->dev, &clk_pdata); if (n_consumers < 0) return n_consumers; diff --git a/drivers/platform/x86/intel/plr_tpmi.c b/drivers/platform/x86/intel/plr_tpmi.c index 691d43c3592c..2b55347a5a93 100644 --- a/drivers/platform/x86/intel/plr_tpmi.c +++ b/drivers/platform/x86/intel/plr_tpmi.c @@ -262,7 +262,7 @@ static int intel_plr_probe(struct auxiliary_device *auxdev, const struct auxilia struct resource *res; struct tpmi_plr *plr; void __iomem *base; - char name[16]; + char name[17]; int err; plat_info = tpmi_get_platform_data(auxdev); diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index 3e7f99ac8c94..10f04b944117 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -22,6 +22,7 @@ #include #include +#include #include #include #include @@ -935,13 +936,13 @@ static unsigned int pmc_core_get_crystal_freq(void) { unsigned int eax_denominator, ebx_numerator, ecx_hz, edx; - if (boot_cpu_data.cpuid_level < 0x15) + if (boot_cpu_data.cpuid_level < CPUID_LEAF_TSC) return 0; eax_denominator = ebx_numerator = ecx_hz = edx = 0; - /* CPUID 15H TSC/Crystal ratio, plus optionally Crystal Hz */ - cpuid(0x15, &eax_denominator, &ebx_numerator, &ecx_hz, &edx); + /* TSC/Crystal ratio, plus optionally Crystal Hz */ + cpuid(CPUID_LEAF_TSC, &eax_denominator, &ebx_numerator, &ecx_hz, &edx); if (ebx_numerator == 0 || eax_denominator == 0) return 0; diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c index 50ebfd586d3f..739569803017 100644 --- a/drivers/platform/x86/intel/pmc/core_ssram.c +++ b/drivers/platform/x86/intel/pmc/core_ssram.c @@ -269,8 +269,12 @@ pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset) /* * The secondary PMC BARS (which are behind hidden PCI devices) * are read from fixed offsets in MMIO of the primary PMC BAR. + * If a device is not present, the value will be 0. */ ssram_base = get_base(tmp_ssram, offset); + if (!ssram_base) + return 0; + ssram = ioremap(ssram_base, SSRAM_HDR_SIZE); if (!ssram) return -ENOMEM; diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c index 8ed54b7a3333..7233b654bbad 100644 --- a/drivers/platform/x86/intel/pmt/class.c +++ b/drivers/platform/x86/intel/pmt/class.c @@ -81,7 +81,7 @@ EXPORT_SYMBOL_NS_GPL(pmt_telem_read_mmio, "INTEL_PMT"); */ static ssize_t intel_pmt_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct intel_pmt_entry *entry = container_of(attr, @@ -308,7 +308,7 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry, entry->pmt_bin_attr.attr.name = ns->name; entry->pmt_bin_attr.attr.mode = 0440; entry->pmt_bin_attr.mmap = intel_pmt_mmap; - entry->pmt_bin_attr.read = intel_pmt_read; + entry->pmt_bin_attr.read_new = intel_pmt_read; entry->pmt_bin_attr.size = entry->size; ret = sysfs_create_bin_file(&dev->kobj, &entry->pmt_bin_attr); diff --git a/drivers/platform/x86/intel/punit_ipc.c b/drivers/platform/x86/intel/punit_ipc.c index cd0ba84cc8e4..bafac8aa2baf 100644 --- a/drivers/platform/x86/intel/punit_ipc.c +++ b/drivers/platform/x86/intel/punit_ipc.c @@ -130,39 +130,6 @@ static int intel_punit_ipc_check_status(IPC_DEV *ipcdev, IPC_TYPE type) return 0; } -/** - * intel_punit_ipc_simple_command() - Simple IPC command - * @cmd: IPC command code. - * @para1: First 8bit parameter, set 0 if not used. - * @para2: Second 8bit parameter, set 0 if not used. - * - * Send a IPC command to P-Unit when there is no data transaction - * - * Return: IPC error code or 0 on success. - */ -int intel_punit_ipc_simple_command(int cmd, int para1, int para2) -{ - IPC_DEV *ipcdev = punit_ipcdev; - IPC_TYPE type; - u32 val; - int ret; - - mutex_lock(&ipcdev->lock); - - reinit_completion(&ipcdev->cmd_complete); - type = (cmd & IPC_PUNIT_CMD_TYPE_MASK) >> IPC_TYPE_OFFSET; - - val = cmd & ~IPC_PUNIT_CMD_TYPE_MASK; - val |= CMD_RUN | para2 << CMD_PARA2_SHIFT | para1 << CMD_PARA1_SHIFT; - ipc_write_cmd(ipcdev, type, val); - ret = intel_punit_ipc_check_status(ipcdev, type); - - mutex_unlock(&ipcdev->lock); - - return ret; -} -EXPORT_SYMBOL(intel_punit_ipc_simple_command); - /** * intel_punit_ipc_command() - IPC command with data and pointers * @cmd: IPC command code. diff --git a/drivers/platform/x86/intel/sdsi.c b/drivers/platform/x86/intel/sdsi.c index 33f33b1070fd..30d1c2caf984 100644 --- a/drivers/platform/x86/intel/sdsi.c +++ b/drivers/platform/x86/intel/sdsi.c @@ -398,8 +398,8 @@ free_payload: } static ssize_t provision_akc_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, - size_t count) + const struct bin_attribute *attr, char *buf, + loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); struct sdsi_priv *priv = dev_get_drvdata(dev); @@ -409,11 +409,11 @@ static ssize_t provision_akc_write(struct file *filp, struct kobject *kobj, return sdsi_provision(priv, buf, count, SDSI_CMD_PROVISION_AKC); } -static BIN_ATTR_WO(provision_akc, SDSI_SIZE_WRITE_MSG); +static const BIN_ATTR_WO(provision_akc, SDSI_SIZE_WRITE_MSG); static ssize_t provision_cap_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, - size_t count) + const struct bin_attribute *attr, char *buf, + loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); struct sdsi_priv *priv = dev_get_drvdata(dev); @@ -423,7 +423,7 @@ static ssize_t provision_cap_write(struct file *filp, struct kobject *kobj, return sdsi_provision(priv, buf, count, SDSI_CMD_PROVISION_CAP); } -static BIN_ATTR_WO(provision_cap, SDSI_SIZE_WRITE_MSG); +static const BIN_ATTR_WO(provision_cap, SDSI_SIZE_WRITE_MSG); static ssize_t certificate_read(u64 command, u64 control_flags, struct sdsi_priv *priv, @@ -469,7 +469,7 @@ free_buffer: static ssize_t state_certificate_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -477,11 +477,11 @@ state_certificate_read(struct file *filp, struct kobject *kobj, return certificate_read(SDSI_CMD_READ_STATE, 0, priv, buf, off, count); } -static BIN_ATTR_ADMIN_RO(state_certificate, SDSI_SIZE_READ_MSG); +static const BIN_ATTR_ADMIN_RO(state_certificate, SDSI_SIZE_READ_MSG); static ssize_t meter_certificate_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -489,11 +489,11 @@ meter_certificate_read(struct file *filp, struct kobject *kobj, return certificate_read(SDSI_CMD_READ_METER, 0, priv, buf, off, count); } -static BIN_ATTR_ADMIN_RO(meter_certificate, SDSI_SIZE_READ_MSG); +static const BIN_ATTR_ADMIN_RO(meter_certificate, SDSI_SIZE_READ_MSG); static ssize_t meter_current_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -502,11 +502,11 @@ meter_current_read(struct file *filp, struct kobject *kobj, return certificate_read(SDSI_CMD_READ_METER, CTRL_METER_ENABLE_DRAM, priv, buf, off, count); } -static BIN_ATTR_ADMIN_RO(meter_current, SDSI_SIZE_READ_MSG); +static const BIN_ATTR_ADMIN_RO(meter_current, SDSI_SIZE_READ_MSG); static ssize_t registers_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, - size_t count) + const struct bin_attribute *attr, char *buf, + loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); struct sdsi_priv *priv = dev_get_drvdata(dev); @@ -528,9 +528,9 @@ static ssize_t registers_read(struct file *filp, struct kobject *kobj, return count; } -static BIN_ATTR_ADMIN_RO(registers, SDSI_SIZE_REGS); +static const BIN_ATTR_ADMIN_RO(registers, SDSI_SIZE_REGS); -static struct bin_attribute *sdsi_bin_attrs[] = { +static const struct bin_attribute *const sdsi_bin_attrs[] = { &bin_attr_registers, &bin_attr_state_certificate, &bin_attr_meter_certificate, @@ -576,7 +576,7 @@ static struct attribute *sdsi_attrs[] = { static const struct attribute_group sdsi_group = { .attrs = sdsi_attrs, - .bin_attrs = sdsi_bin_attrs, + .bin_attrs_new = sdsi_bin_attrs, .is_bin_visible = sdsi_battr_is_visible, }; __ATTRIBUTE_GROUPS(sdsi); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 1e46e30dae96..dbcd3087aaa4 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -804,6 +804,7 @@ EXPORT_SYMBOL_GPL(isst_if_cdev_unregister); static const struct x86_cpu_id isst_cpu_ids[] = { X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, SST_HPM_SUPPORTED), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, 0), X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, SST_HPM_SUPPORTED), diff --git a/drivers/platform/x86/intel/tpmi_power_domains.c b/drivers/platform/x86/intel/tpmi_power_domains.c index 603e7ded06a9..2f01cd22a6ee 100644 --- a/drivers/platform/x86/intel/tpmi_power_domains.c +++ b/drivers/platform/x86/intel/tpmi_power_domains.c @@ -81,6 +81,7 @@ static const struct x86_cpu_id tpmi_cpu_ids[] = { X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, NULL), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, NULL), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, NULL), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, NULL), X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, NULL), X86_MATCH_VFM(INTEL_PANTHERCOVE_X, NULL), {} diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index 4a85aad2475a..8272f1dd0fbc 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -423,6 +423,7 @@ static const struct intel_vsec_platform_info lnl_info = { #define PCI_DEVICE_ID_INTEL_VSEC_RPL 0xa77d #define PCI_DEVICE_ID_INTEL_VSEC_TGL 0x9a0d #define PCI_DEVICE_ID_INTEL_VSEC_LNL_M 0x647d +#define PCI_DEVICE_ID_INTEL_VSEC_PTL 0xb07d static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_ADL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_DG1, &dg1_info) }, @@ -432,6 +433,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) }, + { PCI_DEVICE_DATA(INTEL, VSEC_PTL, &mtl_info) }, { } }; MODULE_DEVICE_TABLE(pci, intel_vsec_pci_ids); diff --git a/drivers/platform/x86/lenovo-wmi-camera.c b/drivers/platform/x86/lenovo-wmi-camera.c index 0c0bedaf7407..eb60fb9a5b3f 100644 --- a/drivers/platform/x86/lenovo-wmi-camera.c +++ b/drivers/platform/x86/lenovo-wmi-camera.c @@ -13,6 +13,7 @@ #include #include #include +#include #define WMI_LENOVO_CAMERABUTTON_EVENT_GUID "50C76F1F-D8E4-D895-0A3D-62F4EA400013" @@ -26,10 +27,38 @@ enum { SW_CAMERA_ON = 1, }; +static int camera_shutter_input_setup(struct wmi_device *wdev, u8 camera_mode) +{ + struct lenovo_wmi_priv *priv = dev_get_drvdata(&wdev->dev); + int err; + + priv->idev = input_allocate_device(); + if (!priv->idev) + return -ENOMEM; + + priv->idev->name = "Lenovo WMI Camera Button"; + priv->idev->phys = "wmi/input0"; + priv->idev->id.bustype = BUS_HOST; + priv->idev->dev.parent = &wdev->dev; + + input_set_capability(priv->idev, EV_SW, SW_CAMERA_LENS_COVER); + + input_report_switch(priv->idev, SW_CAMERA_LENS_COVER, + camera_mode == SW_CAMERA_ON ? 0 : 1); + input_sync(priv->idev); + + err = input_register_device(priv->idev); + if (err) { + input_free_device(priv->idev); + priv->idev = NULL; + } + + return err; +} + static void lenovo_wmi_notify(struct wmi_device *wdev, union acpi_object *obj) { struct lenovo_wmi_priv *priv = dev_get_drvdata(&wdev->dev); - unsigned int keycode; u8 camera_mode; if (obj->type != ACPI_TYPE_BUFFER) { @@ -53,22 +82,24 @@ static void lenovo_wmi_notify(struct wmi_device *wdev, union acpi_object *obj) return; } - mutex_lock(&priv->notify_lock); + guard(mutex)(&priv->notify_lock); - keycode = camera_mode == SW_CAMERA_ON ? - KEY_CAMERA_ACCESS_ENABLE : KEY_CAMERA_ACCESS_DISABLE; - input_report_key(priv->idev, keycode, 1); - input_sync(priv->idev); - input_report_key(priv->idev, keycode, 0); - input_sync(priv->idev); + if (!priv->idev) { + if (camera_shutter_input_setup(wdev, camera_mode)) + dev_warn(&wdev->dev, "Failed to register input device\n"); + return; + } - mutex_unlock(&priv->notify_lock); + if (camera_mode == SW_CAMERA_ON) + input_report_switch(priv->idev, SW_CAMERA_LENS_COVER, 0); + else + input_report_switch(priv->idev, SW_CAMERA_LENS_COVER, 1); + input_sync(priv->idev); } static int lenovo_wmi_probe(struct wmi_device *wdev, const void *context) { struct lenovo_wmi_priv *priv; - int ret; priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -76,21 +107,6 @@ static int lenovo_wmi_probe(struct wmi_device *wdev, const void *context) dev_set_drvdata(&wdev->dev, priv); - priv->idev = devm_input_allocate_device(&wdev->dev); - if (!priv->idev) - return -ENOMEM; - - priv->idev->name = "Lenovo WMI Camera Button"; - priv->idev->phys = "wmi/input0"; - priv->idev->id.bustype = BUS_HOST; - priv->idev->dev.parent = &wdev->dev; - input_set_capability(priv->idev, EV_KEY, KEY_CAMERA_ACCESS_ENABLE); - input_set_capability(priv->idev, EV_KEY, KEY_CAMERA_ACCESS_DISABLE); - - ret = input_register_device(priv->idev); - if (ret) - return ret; - mutex_init(&priv->notify_lock); return 0; @@ -100,6 +116,9 @@ static void lenovo_wmi_remove(struct wmi_device *wdev) { struct lenovo_wmi_priv *priv = dev_get_drvdata(&wdev->dev); + if (priv->idev) + input_unregister_device(priv->idev); + mutex_destroy(&priv->notify_lock); } diff --git a/drivers/platform/x86/lenovo-yoga-tab2-pro-1380-fastcharger.c b/drivers/platform/x86/lenovo-yoga-tab2-pro-1380-fastcharger.c index d2699ca24f34..a96b215cd2c5 100644 --- a/drivers/platform/x86/lenovo-yoga-tab2-pro-1380-fastcharger.c +++ b/drivers/platform/x86/lenovo-yoga-tab2-pro-1380-fastcharger.c @@ -199,14 +199,15 @@ static int yt2_1380_fc_serdev_probe(struct serdev_device *serdev) if (ret) return ret; + serdev_device_set_drvdata(serdev, fc); + serdev_device_set_client_ops(serdev, &yt2_1380_fc_serdev_ops); + ret = devm_serdev_device_open(dev, serdev); if (ret) return dev_err_probe(dev, ret, "opening UART device\n"); serdev_device_set_baudrate(serdev, 600); serdev_device_set_flow_control(serdev, false); - serdev_device_set_drvdata(serdev, fc); - serdev_device_set_client_ops(serdev, &yt2_1380_fc_serdev_ops); ret = devm_extcon_register_notifier_all(dev, fc->extcon, &fc->nb); if (ret) diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index 671021cd1f59..9c7f30a47f1f 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -6237,6 +6237,7 @@ fail_pci_set_dma_mask: fail_pci_request_regions: pci_disable_device(pci_dev); fail_pci_enable_device: + pci_dev_put(pci_dev); return err; } @@ -6247,6 +6248,7 @@ mlxplat_pci_fpga_device_exit(struct pci_dev *pci_bridge, iounmap(pci_bridge_addr); pci_release_regions(pci_bridge); pci_disable_device(pci_bridge); + pci_dev_put(pci_bridge); } static int diff --git a/drivers/platform/x86/msi-laptop.c b/drivers/platform/x86/msi-laptop.c index e5391a37014d..c4b150fa093f 100644 --- a/drivers/platform/x86/msi-laptop.c +++ b/drivers/platform/x86/msi-laptop.c @@ -806,8 +806,8 @@ static void msi_send_touchpad_key(struct work_struct *ignored) } static DECLARE_DELAYED_WORK(msi_touchpad_dwork, msi_send_touchpad_key); -static bool msi_laptop_i8042_filter(unsigned char data, unsigned char str, - struct serio *port) +static bool msi_laptop_i8042_filter(unsigned char data, unsigned char str, struct serio *port, + void *context) { static bool extended; @@ -996,7 +996,7 @@ static int __init load_scm_model_init(struct platform_device *sdev) if (result) goto fail_input; - result = i8042_install_filter(msi_laptop_i8042_filter); + result = i8042_install_filter(msi_laptop_i8042_filter, NULL); if (result) { pr_err("Unable to install key filter\n"); goto fail_filter; diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index d51eb0db0626..cbbb0f809704 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -43,6 +43,7 @@ struct p2sb_res_cache { }; static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE]; +static bool p2sb_hidden_by_bios; static void p2sb_get_devfn(unsigned int *devfn) { @@ -97,6 +98,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) { + /* + * The BIOS prevents the P2SB device from being enumerated by the PCI + * subsystem, so we need to unhide and hide it back to lookup the BAR. + */ + pci_bus_write_config_dword(bus, devfn, P2SBC, 0); + /* Scan the P2SB device and cache its BAR0 */ p2sb_scan_and_cache_devfn(bus, devfn); @@ -104,6 +111,8 @@ static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) if (devfn == P2SB_DEVFN_GOLDMONT) p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT); + pci_bus_write_config_dword(bus, devfn, P2SBC, P2SBC_HIDE); + if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) return -ENOENT; @@ -129,7 +138,7 @@ static int p2sb_cache_resources(void) u32 value = P2SBC_HIDE; struct pci_bus *bus; u16 class; - int ret; + int ret = 0; /* Get devfn for P2SB device itself */ p2sb_get_devfn(&devfn_p2sb); @@ -152,26 +161,57 @@ static int p2sb_cache_resources(void) */ pci_lock_rescan_remove(); - /* - * The BIOS prevents the P2SB device from being enumerated by the PCI - * subsystem, so we need to unhide and hide it back to lookup the BAR. - * Unhide the P2SB device here, if needed. - */ pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0); + p2sb_hidden_by_bios = value & P2SBC_HIDE; - ret = p2sb_scan_and_cache(bus, devfn_p2sb); - - /* Hide the P2SB device, if it was hidden */ - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, P2SBC_HIDE); + /* + * If the BIOS does not hide the P2SB device then its resources + * are accesilble. Cache them only if the P2SB device is hidden. + */ + if (p2sb_hidden_by_bios) + ret = p2sb_scan_and_cache(bus, devfn_p2sb); pci_unlock_rescan_remove(); return ret; } +static int p2sb_read_from_cache(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)]; + + if (cache->bus_dev_id != bus->dev.id) + return -ENODEV; + + if (!p2sb_valid_resource(&cache->res)) + return -ENOENT; + + memcpy(mem, &cache->res, sizeof(*mem)); + + return 0; +} + +static int p2sb_read_from_dev(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct pci_dev *pdev; + int ret = 0; + + pdev = pci_get_slot(bus, devfn); + if (!pdev) + return -ENODEV; + + if (p2sb_valid_resource(pci_resource_n(pdev, 0))) + p2sb_read_bar0(pdev, mem); + else + ret = -ENOENT; + + pci_dev_put(pdev); + + return ret; +} + /** * p2sb_bar - Get Primary to Sideband (P2SB) bridge device BAR * @bus: PCI bus to communicate with @@ -188,8 +228,6 @@ static int p2sb_cache_resources(void) */ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) { - struct p2sb_res_cache *cache; - bus = p2sb_get_bus(bus); if (!bus) return -ENODEV; @@ -197,15 +235,10 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) if (!devfn) p2sb_get_devfn(&devfn); - cache = &p2sb_resources[PCI_FUNC(devfn)]; - if (cache->bus_dev_id != bus->dev.id) - return -ENODEV; + if (p2sb_hidden_by_bios) + return p2sb_read_from_cache(bus, devfn, mem); - if (!p2sb_valid_resource(&cache->res)) - return -ENOENT; - - memcpy(mem, &cache->res, sizeof(*mem)); - return 0; + return p2sb_read_from_dev(bus, devfn, mem); } EXPORT_SYMBOL_GPL(p2sb_bar); diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c index 22ca70eb8227..2987b4db6009 100644 --- a/drivers/platform/x86/panasonic-laptop.c +++ b/drivers/platform/x86/panasonic-laptop.c @@ -260,7 +260,7 @@ struct pcc_acpi { * keypress events over the PS/2 kbd interface, filter these out. */ static bool panasonic_i8042_filter(unsigned char data, unsigned char str, - struct serio *port) + struct serio *port, void *context) { static bool extended; @@ -1100,7 +1100,7 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) pcc->platform = NULL; } - i8042_install_filter(panasonic_i8042_filter); + i8042_install_filter(panasonic_i8042_filter, NULL); return 0; out_platform: diff --git a/drivers/platform/x86/quickstart.c b/drivers/platform/x86/quickstart.c index 8d540a1c8602..c332c7cdaff5 100644 --- a/drivers/platform/x86/quickstart.c +++ b/drivers/platform/x86/quickstart.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/platform/x86/serdev_helpers.h b/drivers/platform/x86/serdev_helpers.h index bcf3a0c356ea..57eac75805e2 100644 --- a/drivers/platform/x86/serdev_helpers.h +++ b/drivers/platform/x86/serdev_helpers.h @@ -22,32 +22,14 @@ #include static inline struct device * -get_serdev_controller(const char *serial_ctrl_hid, - const char *serial_ctrl_uid, - int serial_ctrl_port, - const char *serdev_ctrl_name) +get_serdev_controller_from_parent(struct device *ctrl_dev, + int serial_ctrl_port, + const char *serdev_ctrl_name) { - struct device *ctrl_dev, *child; - struct acpi_device *ctrl_adev; + struct device *child; char name[32]; int i; - ctrl_adev = acpi_dev_get_first_match_dev(serial_ctrl_hid, serial_ctrl_uid, -1); - if (!ctrl_adev) { - pr_err("error could not get %s/%s serial-ctrl adev\n", - serial_ctrl_hid, serial_ctrl_uid); - return ERR_PTR(-ENODEV); - } - - /* get_first_physical_node() returns a weak ref */ - ctrl_dev = get_device(acpi_get_first_physical_node(ctrl_adev)); - if (!ctrl_dev) { - pr_err("error could not get %s/%s serial-ctrl physical node\n", - serial_ctrl_hid, serial_ctrl_uid); - ctrl_dev = ERR_PTR(-ENODEV); - goto put_ctrl_adev; - } - /* Walk host -> uart-ctrl -> port -> serdev-ctrl */ for (i = 0; i < 3; i++) { switch (i) { @@ -67,14 +49,40 @@ get_serdev_controller(const char *serial_ctrl_hid, put_device(ctrl_dev); if (!child) { pr_err("error could not find '%s' device\n", name); - ctrl_dev = ERR_PTR(-ENODEV); - goto put_ctrl_adev; + return ERR_PTR(-ENODEV); } ctrl_dev = child; } -put_ctrl_adev: - acpi_dev_put(ctrl_adev); return ctrl_dev; } + +static inline struct device * +get_serdev_controller(const char *serial_ctrl_hid, + const char *serial_ctrl_uid, + int serial_ctrl_port, + const char *serdev_ctrl_name) +{ + struct acpi_device *adev; + struct device *parent; + + adev = acpi_dev_get_first_match_dev(serial_ctrl_hid, serial_ctrl_uid, -1); + if (!adev) { + pr_err("error could not get %s/%s serial-ctrl adev\n", + serial_ctrl_hid, serial_ctrl_uid ?: "*"); + return ERR_PTR(-ENODEV); + } + + /* get_first_physical_node() returns a weak ref */ + parent = get_device(acpi_get_first_physical_node(adev)); + acpi_dev_put(adev); + if (!parent) { + pr_err("error could not get %s/%s serial-ctrl physical node\n", + serial_ctrl_hid, serial_ctrl_uid ?: "*"); + return ERR_PTR(-ENODEV); + } + + /* This puts our reference on parent and returns a ref on the ctrl */ + return get_serdev_controller_from_parent(parent, serial_ctrl_port, serdev_ctrl_name); +} diff --git a/drivers/platform/x86/serial-multi-instantiate.c b/drivers/platform/x86/serial-multi-instantiate.c index ed6b28505cd6..db030b0f176a 100644 --- a/drivers/platform/x86/serial-multi-instantiate.c +++ b/drivers/platform/x86/serial-multi-instantiate.c @@ -384,6 +384,17 @@ static const struct smi_node cs35l57_hda = { .bus_type = SMI_AUTO_DETECT, }; +static const struct smi_node tas2781_hda = { + .instances = { + { "tas2781-hda", IRQ_RESOURCE_AUTO, 0 }, + { "tas2781-hda", IRQ_RESOURCE_AUTO, 0 }, + { "tas2781-hda", IRQ_RESOURCE_AUTO, 0 }, + { "tas2781-hda", IRQ_RESOURCE_AUTO, 0 }, + {} + }, + .bus_type = SMI_AUTO_DETECT, +}; + /* * Note new device-ids must also be added to ignore_serial_bus_ids in * drivers/acpi/scan.c: acpi_device_enumeration_by_parent(). @@ -396,6 +407,7 @@ static const struct acpi_device_id smi_acpi_ids[] = { { "CSC3556", (unsigned long)&cs35l56_hda }, { "CSC3557", (unsigned long)&cs35l57_hda }, { "INT3515", (unsigned long)&int3515_data }, + { "TXNW2781", (unsigned long)&tas2781_hda }, /* Non-conforming _HID for Cirrus Logic already released */ { "CLSA0100", (unsigned long)&cs35l41_hda }, { "CLSA0101", (unsigned long)&cs35l41_hda }, diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 38de0cb20d77..323316ac6783 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -194,7 +194,6 @@ static const char * const level_options[] = { [TLMI_LEVEL_MASTER] = "master", }; static struct think_lmi tlmi_priv; -static const struct class *fw_attr_class; static DEFINE_MUTEX(tlmi_mutex); static inline struct tlmi_pwd_setting *to_tlmi_pwd_setting(struct kobject *kobj) @@ -1446,11 +1445,7 @@ static int tlmi_sysfs_init(void) { int i, ret; - ret = fw_attributes_class_get(&fw_attr_class); - if (ret) - return ret; - - tlmi_priv.class_dev = device_create(fw_attr_class, NULL, MKDEV(0, 0), + tlmi_priv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0), NULL, "%s", "thinklmi"); if (IS_ERR(tlmi_priv.class_dev)) { ret = PTR_ERR(tlmi_priv.class_dev); @@ -1563,9 +1558,8 @@ static int tlmi_sysfs_init(void) fail_create_attr: tlmi_release_attr(); fail_device_created: - device_destroy(fw_attr_class, MKDEV(0, 0)); + device_destroy(&firmware_attributes_class, MKDEV(0, 0)); fail_class_created: - fw_attributes_class_put(); return ret; } @@ -1788,8 +1782,7 @@ fail_clear_attr: static void tlmi_remove(struct wmi_device *wdev) { tlmi_release_attr(); - device_destroy(fw_attr_class, MKDEV(0, 0)); - fw_attributes_class_put(); + device_destroy(&firmware_attributes_class, MKDEV(0, 0)); } static int tlmi_probe(struct wmi_device *wdev, const void *context) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 6371a9f765c1..1fcb0f99695a 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -184,7 +184,8 @@ enum tpacpi_hkey_event_t { */ TP_HKEY_EV_AMT_TOGGLE = 0x131a, /* Toggle AMT on/off */ TP_HKEY_EV_DOUBLETAP_TOGGLE = 0x131c, /* Toggle trackpoint doubletap on/off */ - TP_HKEY_EV_PROFILE_TOGGLE = 0x131f, /* Toggle platform profile */ + TP_HKEY_EV_PROFILE_TOGGLE = 0x131f, /* Toggle platform profile in 2024 systems */ + TP_HKEY_EV_PROFILE_TOGGLE2 = 0x1401, /* Toggle platform profile in 2025 + systems */ /* Reasons for waking up from S3/S4 */ TP_HKEY_EV_WKUP_S3_UNDOCK = 0x2304, /* undock requested, S3 */ @@ -962,6 +963,7 @@ static const struct proc_ops dispatch_proc_ops = { static struct platform_device *tpacpi_pdev; static struct platform_device *tpacpi_sensors_pdev; static struct device *tpacpi_hwmon; +static struct device *tpacpi_pprof; static struct input_dev *tpacpi_inputdev; static struct mutex tpacpi_inputdev_send_mutex; static LIST_HEAD(tpacpi_all_drivers); @@ -3274,6 +3276,7 @@ static const struct key_entry keymap_lenovo[] __initconst = { * scancodes to preserve uAPI compatibility, see tpacpi_input_send_key(). */ { KE_KEY, 0x131d, { KEY_VENDOR } }, /* System debug info, similar to old ThinkPad key */ + { KE_KEY, 0x1320, { KEY_LINK_PHONE } }, { KE_KEY, TP_HKEY_EV_TRACK_DOUBLETAP /* 0x8036 */, { KEY_PROG4 } }, { KE_END } }; @@ -10414,7 +10417,7 @@ static int convert_profile_to_dytc(enum platform_profile_option profile, int *pe * dytc_profile_get: Function to register with platform_profile * handler. Returns current platform profile. */ -static int dytc_profile_get(struct platform_profile_handler *pprof, +static int dytc_profile_get(struct device *dev, enum platform_profile_option *profile) { *profile = dytc_current_profile; @@ -10489,7 +10492,7 @@ static int dytc_cql_command(int command, int *output) * dytc_profile_set: Function to register with platform_profile * handler. Sets current platform profile. */ -static int dytc_profile_set(struct platform_profile_handler *pprof, +static int dytc_profile_set(struct device *dev, enum platform_profile_option profile) { int perfmode; @@ -10538,6 +10541,21 @@ unlock: return err; } +static int dytc_profile_probe(void *drvdata, unsigned long *choices) +{ + set_bit(PLATFORM_PROFILE_LOW_POWER, choices); + set_bit(PLATFORM_PROFILE_BALANCED, choices); + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + + return 0; +} + +static const struct platform_profile_ops dytc_profile_ops = { + .probe = dytc_profile_probe, + .profile_get = dytc_profile_get, + .profile_set = dytc_profile_set, +}; + static void dytc_profile_refresh(void) { enum platform_profile_option profile; @@ -10566,24 +10584,14 @@ static void dytc_profile_refresh(void) err = convert_dytc_to_profile(funcmode, perfmode, &profile); if (!err && profile != dytc_current_profile) { dytc_current_profile = profile; - platform_profile_notify(); + platform_profile_notify(tpacpi_pprof); } } -static struct platform_profile_handler dytc_profile = { - .profile_get = dytc_profile_get, - .profile_set = dytc_profile_set, -}; - static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) { int err, output; - /* Setup supported modes */ - set_bit(PLATFORM_PROFILE_LOW_POWER, dytc_profile.choices); - set_bit(PLATFORM_PROFILE_BALANCED, dytc_profile.choices); - set_bit(PLATFORM_PROFILE_PERFORMANCE, dytc_profile.choices); - err = dytc_command(DYTC_CMD_QUERY, &output); if (err) return err; @@ -10638,12 +10646,13 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) "DYTC version %d: thermal mode available\n", dytc_version); /* Create platform_profile structure and register */ - err = platform_profile_register(&dytc_profile); + tpacpi_pprof = devm_platform_profile_register(&tpacpi_pdev->dev, "thinkpad-acpi", + NULL, &dytc_profile_ops); /* * If for some reason platform_profiles aren't enabled * don't quit terminally. */ - if (err) + if (IS_ERR(tpacpi_pprof)) return -ENODEV; /* Ensure initial values are correct */ @@ -10656,14 +10665,8 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) return 0; } -static void dytc_profile_exit(void) -{ - platform_profile_remove(); -} - static struct ibm_struct dytc_profile_driver_data = { .name = "dytc-profile", - .exit = dytc_profile_exit, }; /************************************************************************* @@ -11200,6 +11203,7 @@ static bool tpacpi_driver_event(const unsigned int hkey_event) tp_features.trackpoint_doubletap = !tp_features.trackpoint_doubletap; return true; case TP_HKEY_EV_PROFILE_TOGGLE: + case TP_HKEY_EV_PROFILE_TOGGLE2: platform_profile_cycle(); return true; } @@ -11679,7 +11683,7 @@ static int __init set_ibm_param(const char *val, const struct kernel_param *kp) if (strcmp(ibm->name, kp->name) == 0 && ibm->write) { if (strlen(val) > sizeof(ibms_init[i].param) - 1) return -ENOSPC; - strcpy(ibms_init[i].param, val); + strscpy(ibms_init[i].param, val); return 0; } } diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index 78a5aac2dcfd..5ad3a7183d33 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -2755,7 +2755,7 @@ static int toshiba_acpi_enable_hotkeys(struct toshiba_acpi_dev *dev) } static bool toshiba_acpi_i8042_filter(unsigned char data, unsigned char str, - struct serio *port) + struct serio *port, void *context) { if (str & I8042_STR_AUXDATA) return false; @@ -2915,7 +2915,7 @@ static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev) if (ec_handle && acpi_has_method(ec_handle, "NTFY")) { INIT_WORK(&dev->hotkey_work, toshiba_acpi_hotkey_work); - error = i8042_install_filter(toshiba_acpi_i8042_filter); + error = i8042_install_filter(toshiba_acpi_i8042_filter, NULL); if (error) { pr_err("Error installing key filter\n"); goto err_free_dev; diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 0a39f68c641d..bdc19cd8d3ed 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -855,6 +855,23 @@ static const struct ts_dmi_data rwc_nanote_next_data = { .properties = rwc_nanote_next_props, }; +static const struct property_entry sary_tab_3_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1730), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1151), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-sary-tab-3.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data sary_tab_3_data = { + .acpi_name = "MSSL1680:00", + .properties = sary_tab_3_props, +}; + static const struct property_entry schneider_sct101ctm_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1715), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), @@ -1615,6 +1632,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BIOS_VERSION, "S8A70R100-V005"), }, }, + { + /* SARY Tab 3 */ + .driver_data = (void *)&sary_tab_3_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SARY"), + DMI_MATCH(DMI_PRODUCT_NAME, "C210C"), + DMI_MATCH(DMI_PRODUCT_SKU, "TAB3"), + }, + }, { /* Schneider SCT101CTM */ .driver_data = (void *)&schneider_sct101ctm_data, diff --git a/drivers/platform/x86/wmi-bmof.c b/drivers/platform/x86/wmi-bmof.c index df6f0ae6e6c7..3e33da36da8a 100644 --- a/drivers/platform/x86/wmi-bmof.c +++ b/drivers/platform/x86/wmi-bmof.c @@ -20,66 +20,66 @@ #define WMI_BMOF_GUID "05901221-D566-11D1-B2F0-00A0C9062910" -struct bmof_priv { - union acpi_object *bmofdata; - struct bin_attribute bmof_bin_attr; -}; - -static ssize_t read_bmof(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, +static ssize_t bmof_read(struct file *filp, struct kobject *kobj, const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct bmof_priv *priv = container_of(attr, struct bmof_priv, bmof_bin_attr); + struct device *dev = kobj_to_dev(kobj); + union acpi_object *obj = dev_get_drvdata(dev); - return memory_read_from_buffer(buf, count, &off, priv->bmofdata->buffer.pointer, - priv->bmofdata->buffer.length); + return memory_read_from_buffer(buf, count, &off, obj->buffer.pointer, obj->buffer.length); } +static const BIN_ATTR_ADMIN_RO(bmof, 0); + +static const struct bin_attribute * const bmof_attrs[] = { + &bin_attr_bmof, + NULL +}; + +static size_t bmof_bin_size(struct kobject *kobj, const struct bin_attribute *attr, int n) +{ + struct device *dev = kobj_to_dev(kobj); + union acpi_object *obj = dev_get_drvdata(dev); + + return obj->buffer.length; +} + +static const struct attribute_group bmof_group = { + .bin_size = bmof_bin_size, + .bin_attrs_new = bmof_attrs, +}; + +static const struct attribute_group *bmof_groups[] = { + &bmof_group, + NULL +}; + static int wmi_bmof_probe(struct wmi_device *wdev, const void *context) { - struct bmof_priv *priv; - int ret; + union acpi_object *obj; - priv = devm_kzalloc(&wdev->dev, sizeof(struct bmof_priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - - dev_set_drvdata(&wdev->dev, priv); - - priv->bmofdata = wmidev_block_query(wdev, 0); - if (!priv->bmofdata) { + obj = wmidev_block_query(wdev, 0); + if (!obj) { dev_err(&wdev->dev, "failed to read Binary MOF\n"); return -EIO; } - if (priv->bmofdata->type != ACPI_TYPE_BUFFER) { + if (obj->type != ACPI_TYPE_BUFFER) { dev_err(&wdev->dev, "Binary MOF is not a buffer\n"); - ret = -EIO; - goto err_free; + kfree(obj); + return -EIO; } - sysfs_bin_attr_init(&priv->bmof_bin_attr); - priv->bmof_bin_attr.attr.name = "bmof"; - priv->bmof_bin_attr.attr.mode = 0400; - priv->bmof_bin_attr.read = read_bmof; - priv->bmof_bin_attr.size = priv->bmofdata->buffer.length; - - ret = device_create_bin_file(&wdev->dev, &priv->bmof_bin_attr); - if (ret) - goto err_free; + dev_set_drvdata(&wdev->dev, obj); return 0; - - err_free: - kfree(priv->bmofdata); - return ret; } static void wmi_bmof_remove(struct wmi_device *wdev) { - struct bmof_priv *priv = dev_get_drvdata(&wdev->dev); + union acpi_object *obj = dev_get_drvdata(&wdev->dev); - device_remove_bin_file(&wdev->dev, &priv->bmof_bin_attr); - kfree(priv->bmofdata); + kfree(obj); } static const struct wmi_device_id wmi_bmof_id_table[] = { @@ -90,6 +90,7 @@ static const struct wmi_device_id wmi_bmof_id_table[] = { static struct wmi_driver wmi_bmof_driver = { .driver = { .name = "wmi-bmof", + .dev_groups = bmof_groups, }, .probe = wmi_bmof_probe, .remove = wmi_bmof_remove, diff --git a/drivers/platform/x86/x86-android-tablets/Makefile b/drivers/platform/x86/x86-android-tablets/Makefile index 41ece5a37137..313be30548bc 100644 --- a/drivers/platform/x86/x86-android-tablets/Makefile +++ b/drivers/platform/x86/x86-android-tablets/Makefile @@ -3,7 +3,7 @@ # X86 Android tablet support Makefile # +obj-$(CONFIG_X86_ANDROID_TABLETS) += vexia_atla10_ec.o obj-$(CONFIG_X86_ANDROID_TABLETS) += x86-android-tablets.o - x86-android-tablets-y := core.o dmi.o shared-psy-info.o \ asus.o lenovo.o other.o diff --git a/drivers/platform/x86/x86-android-tablets/asus.c b/drivers/platform/x86/x86-android-tablets/asus.c index 07fbeab2319a..7dde63b9943f 100644 --- a/drivers/platform/x86/x86-android-tablets/asus.c +++ b/drivers/platform/x86/x86-android-tablets/asus.c @@ -145,8 +145,8 @@ static const struct x86_i2c_client_info asus_me176c_i2c_clients[] __initconst = static const struct x86_serdev_info asus_me176c_serdevs[] __initconst = { { - .ctrl_hid = "80860F0A", - .ctrl_uid = "2", + .ctrl.acpi.hid = "80860F0A", + .ctrl.acpi.uid = "2", .ctrl_devname = "serial0", .serdev_hid = "BCM2E3A", }, diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c index 4218afcec0e9..2a9c47178505 100644 --- a/drivers/platform/x86/x86-android-tablets/core.c +++ b/drivers/platform/x86/x86-android-tablets/core.c @@ -157,7 +157,7 @@ static struct gpiod_lookup_table * const *gpiod_lookup_tables; static const struct software_node *bat_swnode; static void (*exit_handler)(void); -static struct i2c_adapter * +static __init struct i2c_adapter * get_i2c_adap_by_handle(const struct x86_i2c_client_info *client_info) { acpi_handle handle; @@ -177,7 +177,7 @@ static __init int match_parent(struct device *dev, const void *data) return dev->parent == data; } -static struct i2c_adapter * +static __init struct i2c_adapter * get_i2c_adap_by_pci_parent(const struct x86_i2c_client_info *client_info) { struct i2c_adapter *adap = NULL; @@ -212,7 +212,7 @@ static __init int x86_instantiate_i2c_client(const struct x86_dev_info *dev_info if (board_info.irq < 0) return board_info.irq; - if (dev_info->use_pci_devname) + if (dev_info->use_pci) adap = get_i2c_adap_by_pci_parent(client_info); else adap = get_i2c_adap_by_handle(client_info); @@ -271,15 +271,32 @@ static __init int x86_instantiate_spi_dev(const struct x86_dev_info *dev_info, i return 0; } -static __init int x86_instantiate_serdev(const struct x86_serdev_info *info, int idx) +static __init struct device * +get_serdev_controller_by_pci_parent(const struct x86_serdev_info *info) { + struct pci_dev *pdev; + + pdev = pci_get_domain_bus_and_slot(0, 0, info->ctrl.pci.devfn); + if (!pdev) + return ERR_PTR(-EPROBE_DEFER); + + /* This puts our reference on pdev and returns a ref on the ctrl */ + return get_serdev_controller_from_parent(&pdev->dev, 0, info->ctrl_devname); +} + +static __init int x86_instantiate_serdev(const struct x86_dev_info *dev_info, int idx) +{ + const struct x86_serdev_info *info = &dev_info->serdev_info[idx]; struct acpi_device *serdev_adev; struct serdev_device *serdev; struct device *ctrl_dev; int ret = -ENODEV; - ctrl_dev = get_serdev_controller(info->ctrl_hid, info->ctrl_uid, 0, - info->ctrl_devname); + if (dev_info->use_pci) + ctrl_dev = get_serdev_controller_by_pci_parent(info); + else + ctrl_dev = get_serdev_controller(info->ctrl.acpi.hid, info->ctrl.acpi.uid, + 0, info->ctrl_devname); if (IS_ERR(ctrl_dev)) return PTR_ERR(ctrl_dev); @@ -446,7 +463,7 @@ static __init int x86_android_tablet_probe(struct platform_device *pdev) serdev_count = dev_info->serdev_count; for (i = 0; i < serdev_count; i++) { - ret = x86_instantiate_serdev(&dev_info->serdev_info[i], i); + ret = x86_instantiate_serdev(dev_info, i); if (ret < 0) { x86_android_tablet_remove(pdev); return ret; diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c index ae087f1471c1..1241a97cda39 100644 --- a/drivers/platform/x86/x86-android-tablets/lenovo.c +++ b/drivers/platform/x86/x86-android-tablets/lenovo.c @@ -178,8 +178,8 @@ static const struct platform_device_info lenovo_yb1_x90_pdevs[] __initconst = { */ static const struct x86_serdev_info lenovo_yb1_x90_serdevs[] __initconst = { { - .ctrl_hid = "8086228A", - .ctrl_uid = "1", + .ctrl.acpi.hid = "8086228A", + .ctrl.acpi.uid = "1", .ctrl_devname = "serial0", .serdev_hid = "BCM2E1A", }, @@ -601,7 +601,7 @@ static const struct regulator_init_data lenovo_yoga_tab2_1380_bq24190_vbus_init_ .num_consumer_supplies = 1, }; -struct bq24190_platform_data lenovo_yoga_tab2_1380_bq24190_pdata = { +static struct bq24190_platform_data lenovo_yoga_tab2_1380_bq24190_pdata = { .regulator_init_data = &lenovo_yoga_tab2_1380_bq24190_vbus_init_data, }; @@ -726,7 +726,7 @@ static const struct platform_device_info lenovo_yoga_tab2_1380_pdevs[] __initcon }, }; -const char * const lenovo_yoga_tab2_1380_modules[] __initconst = { +static const char * const lenovo_yoga_tab2_1380_modules[] __initconst = { "bq24190_charger", /* For the Vbus regulator for lc824206xa */ NULL }; diff --git a/drivers/platform/x86/x86-android-tablets/other.c b/drivers/platform/x86/x86-android-tablets/other.c index 735df818f76b..1d93d9edb23f 100644 --- a/drivers/platform/x86/x86-android-tablets/other.c +++ b/drivers/platform/x86/x86-android-tablets/other.c @@ -602,14 +602,14 @@ const struct x86_dev_info whitelabel_tm800a550l_info __initconst = { * Vexia EDU ATLA 10 tablet, Android 4.2 / 4.4 + Guadalinex Ubuntu tablet * distributed to schools in the Spanish Andalucía region. */ -const char * const crystal_cove_pwrsrc_psy[] = { "crystal_cove_pwrsrc" }; +static const char * const crystal_cove_pwrsrc_psy[] = { "crystal_cove_pwrsrc" }; static const struct property_entry vexia_edu_atla10_ulpmc_props[] = { PROPERTY_ENTRY_STRING_ARRAY("supplied-from", crystal_cove_pwrsrc_psy), { } }; -const struct software_node vexia_edu_atla10_ulpmc_node = { +static const struct software_node vexia_edu_atla10_ulpmc_node = { .properties = vexia_edu_atla10_ulpmc_props, }; @@ -715,6 +715,14 @@ static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initcon } }; +static const struct x86_serdev_info vexia_edu_atla10_serdevs[] __initconst = { + { + .ctrl.pci.devfn = PCI_DEVFN(0x1e, 3), + .ctrl_devname = "serial0", + .serdev_hid = "OBDA8723", + }, +}; + static struct gpiod_lookup_table vexia_edu_atla10_ft5416_gpios = { .dev_id = "i2c-FTSC1000", .table = { @@ -755,9 +763,11 @@ static int __init vexia_edu_atla10_init(struct device *dev) const struct x86_dev_info vexia_edu_atla10_info __initconst = { .i2c_client_info = vexia_edu_atla10_i2c_clients, .i2c_client_count = ARRAY_SIZE(vexia_edu_atla10_i2c_clients), + .serdev_info = vexia_edu_atla10_serdevs, + .serdev_count = ARRAY_SIZE(vexia_edu_atla10_serdevs), .gpiod_lookup_tables = vexia_edu_atla10_gpios, .init = vexia_edu_atla10_init, - .use_pci_devname = true, + .use_pci = true, }; /* diff --git a/drivers/platform/x86/x86-android-tablets/vexia_atla10_ec.c b/drivers/platform/x86/x86-android-tablets/vexia_atla10_ec.c new file mode 100644 index 000000000000..5d02af1c5aaa --- /dev/null +++ b/drivers/platform/x86/x86-android-tablets/vexia_atla10_ec.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * power_supply class (battery) driver for the I2C attached embedded controller + * found on Vexia EDU ATLA 10 (9V version) tablets. + * + * This is based on the ACPI Battery device in the DSDT which should work + * expect that it expects the I2C controller to be enumerated as an ACPI + * device and the tablet's BIOS enumerates all LPSS devices as PCI devices + * (and changing the LPSS BIOS settings from PCI -> ACPI does not work). + * + * Copyright (c) 2024 Hans de Goede + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* State field uses ACPI Battery spec status bits */ +#define ACPI_BATTERY_STATE_DISCHARGING BIT(0) +#define ACPI_BATTERY_STATE_CHARGING BIT(1) + +#define ATLA10_EC_BATTERY_STATE_COMMAND 0x87 +#define ATLA10_EC_BATTERY_INFO_COMMAND 0x88 + +/* From broken ACPI battery device in DSDT */ +#define ATLA10_EC_VOLTAGE_MIN_DESIGN_uV 3750000 + +/* Update data every 5 seconds */ +#define UPDATE_INTERVAL_JIFFIES (5 * HZ) + +struct atla10_ec_battery_state { + u8 status; /* Using ACPI Battery spec status bits */ + u8 capacity; /* Percent */ + __le16 charge_now_mAh; + __le16 voltage_now_mV; + __le16 current_now_mA; + __le16 charge_full_mAh; + __le16 temp; /* centi degrees Celsius */ +} __packed; + +struct atla10_ec_battery_info { + __le16 charge_full_design_mAh; + __le16 voltage_now_mV; /* Should be design voltage, but is not ? */ + __le16 charge_full_design2_mAh; +} __packed; + +struct atla10_ec_data { + struct i2c_client *client; + struct power_supply *psy; + struct delayed_work work; + struct mutex update_lock; + struct atla10_ec_battery_info info; + struct atla10_ec_battery_state state; + bool valid; /* true if state is valid */ + unsigned long last_update; /* In jiffies */ +}; + +static int atla10_ec_cmd(struct atla10_ec_data *data, u8 cmd, u8 len, u8 *values) +{ + struct device *dev = &data->client->dev; + u8 buf[I2C_SMBUS_BLOCK_MAX]; + int ret; + + ret = i2c_smbus_read_block_data(data->client, cmd, buf); + if (ret != len) { + dev_err(dev, "I2C command 0x%02x error: %d\n", cmd, ret); + return -EIO; + } + + memcpy(values, buf, len); + return 0; +} + +static int atla10_ec_update(struct atla10_ec_data *data) +{ + int ret; + + if (data->valid && time_before(jiffies, data->last_update + UPDATE_INTERVAL_JIFFIES)) + return 0; + + ret = atla10_ec_cmd(data, ATLA10_EC_BATTERY_STATE_COMMAND, + sizeof(data->state), (u8 *)&data->state); + if (ret) + return ret; + + data->last_update = jiffies; + data->valid = true; + return 0; +} + +static int atla10_ec_psy_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct atla10_ec_data *data = power_supply_get_drvdata(psy); + int charge_now_mAh, charge_full_mAh, ret; + + guard(mutex)(&data->update_lock); + + ret = atla10_ec_update(data); + if (ret) + return ret; + + switch (psp) { + case POWER_SUPPLY_PROP_STATUS: + if (data->state.status & ACPI_BATTERY_STATE_DISCHARGING) + val->intval = POWER_SUPPLY_STATUS_DISCHARGING; + else if (data->state.status & ACPI_BATTERY_STATE_CHARGING) + val->intval = POWER_SUPPLY_STATUS_CHARGING; + else if (data->state.capacity == 100) + val->intval = POWER_SUPPLY_STATUS_FULL; + else + val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING; + break; + case POWER_SUPPLY_PROP_CAPACITY: + val->intval = data->state.capacity; + break; + case POWER_SUPPLY_PROP_CHARGE_NOW: + /* + * The EC has a bug where it reports charge-full-design as + * charge-now when the battery is full. Clamp charge-now to + * charge-full to workaround this. + */ + charge_now_mAh = le16_to_cpu(data->state.charge_now_mAh); + charge_full_mAh = le16_to_cpu(data->state.charge_full_mAh); + val->intval = min(charge_now_mAh, charge_full_mAh) * 1000; + break; + case POWER_SUPPLY_PROP_VOLTAGE_NOW: + val->intval = le16_to_cpu(data->state.voltage_now_mV) * 1000; + break; + case POWER_SUPPLY_PROP_CURRENT_NOW: + val->intval = le16_to_cpu(data->state.current_now_mA) * 1000; + /* + * Documentation/ABI/testing/sysfs-class-power specifies + * negative current for discharging. + */ + if (data->state.status & ACPI_BATTERY_STATE_DISCHARGING) + val->intval = -val->intval; + break; + case POWER_SUPPLY_PROP_CHARGE_FULL: + val->intval = le16_to_cpu(data->state.charge_full_mAh) * 1000; + break; + case POWER_SUPPLY_PROP_TEMP: + val->intval = le16_to_cpu(data->state.temp) / 10; + break; + case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: + val->intval = le16_to_cpu(data->info.charge_full_design_mAh) * 1000; + break; + case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: + val->intval = ATLA10_EC_VOLTAGE_MIN_DESIGN_uV; + break; + case POWER_SUPPLY_PROP_PRESENT: + val->intval = 1; + break; + case POWER_SUPPLY_PROP_TECHNOLOGY: + val->intval = POWER_SUPPLY_TECHNOLOGY_LIPO; + break; + default: + return -EINVAL; + } + + return 0; +} + +static void atla10_ec_external_power_changed_work(struct work_struct *work) +{ + struct atla10_ec_data *data = container_of(work, struct atla10_ec_data, work.work); + + dev_dbg(&data->client->dev, "External power changed\n"); + data->valid = false; + power_supply_changed(data->psy); +} + +static void atla10_ec_external_power_changed(struct power_supply *psy) +{ + struct atla10_ec_data *data = power_supply_get_drvdata(psy); + + /* After charger plug in/out wait 0.5s for things to stabilize */ + mod_delayed_work(system_wq, &data->work, HZ / 2); +} + +static const enum power_supply_property atla10_ec_psy_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_TECHNOLOGY, +}; + +static const struct power_supply_desc atla10_ec_psy_desc = { + .name = "atla10_ec_battery", + .type = POWER_SUPPLY_TYPE_BATTERY, + .properties = atla10_ec_psy_props, + .num_properties = ARRAY_SIZE(atla10_ec_psy_props), + .get_property = atla10_ec_psy_get_property, + .external_power_changed = atla10_ec_external_power_changed, +}; + +static int atla10_ec_probe(struct i2c_client *client) +{ + struct power_supply_config psy_cfg = { }; + struct device *dev = &client->dev; + struct atla10_ec_data *data; + int ret; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + psy_cfg.drv_data = data; + data->client = client; + + ret = devm_mutex_init(dev, &data->update_lock); + if (ret) + return ret; + + ret = devm_delayed_work_autocancel(dev, &data->work, + atla10_ec_external_power_changed_work); + if (ret) + return ret; + + ret = atla10_ec_cmd(data, ATLA10_EC_BATTERY_INFO_COMMAND, + sizeof(data->info), (u8 *)&data->info); + if (ret) + return ret; + + data->psy = devm_power_supply_register(dev, &atla10_ec_psy_desc, &psy_cfg); + return PTR_ERR_OR_ZERO(data->psy); +} + +static const struct i2c_device_id atla10_ec_id_table[] = { + { "vexia_atla10_ec" }, + { } +}; +MODULE_DEVICE_TABLE(i2c, atla10_ec_id_table); + +static struct i2c_driver atla10_ec_driver = { + .driver = { + .name = "vexia_atla10_ec", + }, + .probe = atla10_ec_probe, + .id_table = atla10_ec_id_table, +}; +module_i2c_driver(atla10_ec_driver); + +MODULE_AUTHOR("Hans de Goede "); +MODULE_DESCRIPTION("Battery driver for Vexia EDU ATLA 10 tablet EC"); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h index 0fc7e8cff672..63a38a0069ba 100644 --- a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h +++ b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h @@ -57,8 +57,15 @@ struct x86_spi_dev_info { }; struct x86_serdev_info { - const char *ctrl_hid; - const char *ctrl_uid; + union { + struct { + const char *hid; + const char *uid; + } acpi; + struct { + unsigned int devfn; + } pci; + } ctrl; const char *ctrl_devname; /* * ATM the serdev core only supports of or ACPI matching; and so far all @@ -91,7 +98,7 @@ struct x86_dev_info { int gpio_button_count; int (*init)(struct device *dev); void (*exit)(void); - bool use_pci_devname; + bool use_pci; }; int x86_android_tablet_get_gpiod(const char *chip, int pin, const char *con_id, diff --git a/drivers/pmdomain/arm/scmi_pm_domain.c b/drivers/pmdomain/arm/scmi_pm_domain.c index a7784a8bb5db..86b531e15b85 100644 --- a/drivers/pmdomain/arm/scmi_pm_domain.c +++ b/drivers/pmdomain/arm/scmi_pm_domain.c @@ -96,6 +96,14 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev) continue; } + /* + * Register the explicit power on request to the firmware so + * that it is tracked as used by OSPM agent and not + * accidentally turned off with OSPM's knowledge + */ + if (state == SCMI_POWER_STATE_GENERIC_ON) + power_ops->state_set(ph, i, state); + scmi_pd->domain = i; scmi_pd->ph = ph; scmi_pd->name = power_ops->name_get(ph, i); diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index bb11f467dc78..6c94137865c9 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -2142,6 +2142,11 @@ static int genpd_set_default_power_state(struct generic_pm_domain *genpd) return 0; } +static void genpd_provider_release(struct device *dev) +{ + /* nothing to be done here */ +} + static int genpd_alloc_data(struct generic_pm_domain *genpd) { struct genpd_governor_data *gd = NULL; @@ -2173,6 +2178,7 @@ static int genpd_alloc_data(struct generic_pm_domain *genpd) genpd->gd = gd; device_initialize(&genpd->dev); + genpd->dev.release = genpd_provider_release; if (!genpd_is_dev_name_fw(genpd)) { dev_set_name(&genpd->dev, "%s", genpd->name); @@ -3174,6 +3180,8 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state, if (!err) genpd_state->residency_ns = 1000LL * residency; + of_property_read_string(state_node, "idle-state-name", &genpd_state->name); + genpd_state->power_on_latency_ns = 1000LL * exit_latency; genpd_state->power_off_latency_ns = 1000LL * entry_latency; genpd_state->fwnode = &state_node->fwnode; @@ -3452,7 +3460,10 @@ static int idle_states_show(struct seq_file *s, void *data) seq_puts(s, "State Time Spent(ms) Usage Rejected\n"); for (i = 0; i < genpd->state_count; i++) { - idle_time += genpd->states[i].idle_time; + struct genpd_power_state *state = &genpd->states[i]; + char state_name[15]; + + idle_time += state->idle_time; if (genpd->status == GENPD_STATE_OFF && genpd->state_idx == i) { now = ktime_get_mono_fast_ns(); @@ -3462,9 +3473,13 @@ static int idle_states_show(struct seq_file *s, void *data) } } + if (!state->name) + snprintf(state_name, ARRAY_SIZE(state_name), "S%-13d", i); + do_div(idle_time, NSEC_PER_MSEC); - seq_printf(s, "S%-13i %-14llu %-14llu %llu\n", i, idle_time, - genpd->states[i].usage, genpd->states[i].rejected); + seq_printf(s, "%-14s %-14llu %-14llu %llu\n", + state->name ?: state_name, idle_time, + state->usage, state->rejected); } genpd_unlock(genpd); diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c index e67ecf99ef84..958d34d4821b 100644 --- a/drivers/pmdomain/imx/gpcv2.c +++ b/drivers/pmdomain/imx/gpcv2.c @@ -1437,6 +1437,7 @@ static struct platform_driver imx_pgc_domain_driver = { .driver = { .name = "imx-pgc", .pm = &imx_pgc_domain_pm_ops, + .suppress_bind_attrs = true, }, .probe = imx_pgc_domain_probe, .remove = imx_pgc_domain_remove, @@ -1458,12 +1459,12 @@ static int imx_gpcv2_probe(struct platform_device *pdev) .max_register = SZ_4K, }; struct device *dev = &pdev->dev; - struct device_node *pgc_np; + struct device_node *pgc_np __free(device_node) = + of_get_child_by_name(dev->of_node, "pgc"); struct regmap *regmap; void __iomem *base; int ret; - pgc_np = of_get_child_by_name(dev->of_node, "pgc"); if (!pgc_np) { dev_err(dev, "No power domains specified in DT\n"); return -EINVAL; @@ -1549,6 +1550,7 @@ static struct platform_driver imx_gpc_driver = { .driver = { .name = "imx-gpcv2", .of_match_table = imx_gpcv2_dt_ids, + .suppress_bind_attrs = true, }, .probe = imx_gpcv2_probe, }; diff --git a/drivers/pmdomain/imx/imx8m-blk-ctrl.c b/drivers/pmdomain/imx/imx8m-blk-ctrl.c index 23db85b7aa9e..912802b5215b 100644 --- a/drivers/pmdomain/imx/imx8m-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx8m-blk-ctrl.c @@ -894,6 +894,7 @@ static struct platform_driver imx8m_blk_ctrl_driver = { .name = "imx8m-blk-ctrl", .pm = &imx8m_blk_ctrl_pm_ops, .of_match_table = imx8m_blk_ctrl_of_match, + .suppress_bind_attrs = true, }, }; module_platform_driver(imx8m_blk_ctrl_driver); diff --git a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c index e3a0f64c144c..34576be606e3 100644 --- a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c @@ -770,7 +770,7 @@ static void imx8mp_blk_ctrl_remove(struct platform_device *pdev) of_genpd_del_provider(pdev->dev.of_node); - for (i = 0; bc->onecell_data.num_domains; i++) { + for (i = 0; i < bc->onecell_data.num_domains; i++) { struct imx8mp_blk_ctrl_domain *domain = &bc->domains[i]; pm_genpd_remove(&domain->genpd); @@ -862,6 +862,7 @@ static struct platform_driver imx8mp_blk_ctrl_driver = { .name = "imx8mp-blk-ctrl", .pm = &imx8mp_blk_ctrl_pm_ops, .of_match_table = imx8mp_blk_ctrl_of_match, + .suppress_bind_attrs = true, }, }; module_platform_driver(imx8mp_blk_ctrl_driver); diff --git a/drivers/pmdomain/mediatek/Kconfig b/drivers/pmdomain/mediatek/Kconfig index 21305c4f17fe..0e34a517ab7d 100644 --- a/drivers/pmdomain/mediatek/Kconfig +++ b/drivers/pmdomain/mediatek/Kconfig @@ -26,4 +26,16 @@ config MTK_SCPSYS_PM_DOMAINS Control Processor System (SCPSYS) has several power management related tasks in the system. +config AIROHA_CPU_PM_DOMAIN + tristate "Airoha CPU power domain" + default ARCH_AIROHA + depends on HAVE_ARM_SMCCC + depends on PM + select PM_GENERIC_DOMAINS + help + Say y here to enable CPU power domain support for Airoha SoC. + + CPU frequency and power is controlled by ATF with SMC command to + set performance states. + endmenu diff --git a/drivers/pmdomain/mediatek/Makefile b/drivers/pmdomain/mediatek/Makefile index 8cde09e654b3..18ba92e3c418 100644 --- a/drivers/pmdomain/mediatek/Makefile +++ b/drivers/pmdomain/mediatek/Makefile @@ -1,3 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_MTK_SCPSYS) += mtk-scpsys.o obj-$(CONFIG_MTK_SCPSYS_PM_DOMAINS) += mtk-pm-domains.o +obj-$(CONFIG_AIROHA_CPU_PM_DOMAIN) += airoha-cpu-pmdomain.o + +ifeq ($(CONFIG_THUMB2_KERNEL)$(CONFIG_CC_IS_CLANG),yy) +# The use of R7 in the SMCCC conflicts with the compiler's use of R7 as a frame +# pointer in Thumb2 mode, which is forcibly enabled by Clang when profiling +# hooks are inserted via the -pg switch. +CFLAGS_REMOVE_airoha-cpu-pmdomain.o += $(CC_FLAGS_FTRACE) +endif diff --git a/drivers/pmdomain/mediatek/airoha-cpu-pmdomain.c b/drivers/pmdomain/mediatek/airoha-cpu-pmdomain.c new file mode 100644 index 000000000000..0fd88d2f9ac2 --- /dev/null +++ b/drivers/pmdomain/mediatek/airoha-cpu-pmdomain.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include +#include + +#define AIROHA_SIP_AVS_HANDLE 0x82000301 +#define AIROHA_AVS_OP_BASE 0xddddddd0 +#define AIROHA_AVS_OP_MASK GENMASK(1, 0) +#define AIROHA_AVS_OP_FREQ_DYN_ADJ (AIROHA_AVS_OP_BASE | \ + FIELD_PREP(AIROHA_AVS_OP_MASK, 0x1)) +#define AIROHA_AVS_OP_GET_FREQ (AIROHA_AVS_OP_BASE | \ + FIELD_PREP(AIROHA_AVS_OP_MASK, 0x2)) + +struct airoha_cpu_pmdomain_priv { + struct clk_hw hw; + struct generic_pm_domain pd; +}; + +static long airoha_cpu_pmdomain_clk_round(struct clk_hw *hw, unsigned long rate, + unsigned long *parent_rate) +{ + return rate; +} + +static unsigned long airoha_cpu_pmdomain_clk_get(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct arm_smccc_res res; + + arm_smccc_1_1_invoke(AIROHA_SIP_AVS_HANDLE, AIROHA_AVS_OP_GET_FREQ, + 0, 0, 0, 0, 0, 0, &res); + + /* SMCCC returns freq in MHz */ + return (int)(res.a0 * 1000 * 1000); +} + +/* Airoha CPU clk SMCC is always enabled */ +static int airoha_cpu_pmdomain_clk_is_enabled(struct clk_hw *hw) +{ + return true; +} + +static const struct clk_ops airoha_cpu_pmdomain_clk_ops = { + .recalc_rate = airoha_cpu_pmdomain_clk_get, + .is_enabled = airoha_cpu_pmdomain_clk_is_enabled, + .round_rate = airoha_cpu_pmdomain_clk_round, +}; + +static int airoha_cpu_pmdomain_set_performance_state(struct generic_pm_domain *domain, + unsigned int state) +{ + struct arm_smccc_res res; + + arm_smccc_1_1_invoke(AIROHA_SIP_AVS_HANDLE, AIROHA_AVS_OP_FREQ_DYN_ADJ, + 0, state, 0, 0, 0, 0, &res); + + /* SMC signal correct apply by unsetting BIT 0 */ + return res.a0 & BIT(0) ? -EINVAL : 0; +} + +static int airoha_cpu_pmdomain_probe(struct platform_device *pdev) +{ + struct airoha_cpu_pmdomain_priv *priv; + struct device *dev = &pdev->dev; + const struct clk_init_data init = { + .name = "cpu", + .ops = &airoha_cpu_pmdomain_clk_ops, + /* Clock with no set_rate, can't cache */ + .flags = CLK_GET_RATE_NOCACHE, + }; + struct generic_pm_domain *pd; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + /* Init and register a get-only clk for Cpufreq */ + priv->hw.init = &init; + ret = devm_clk_hw_register(dev, &priv->hw); + if (ret) + return ret; + + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, + &priv->hw); + if (ret) + return ret; + + /* Init and register a PD for CPU */ + pd = &priv->pd; + pd->name = "cpu_pd"; + pd->flags = GENPD_FLAG_ALWAYS_ON; + pd->set_performance_state = airoha_cpu_pmdomain_set_performance_state; + + ret = pm_genpd_init(pd, NULL, false); + if (ret) + return ret; + + ret = of_genpd_add_provider_simple(dev->of_node, pd); + if (ret) + goto err_add_provider; + + platform_set_drvdata(pdev, priv); + + return 0; + +err_add_provider: + pm_genpd_remove(pd); + + return ret; +} + +static void airoha_cpu_pmdomain_remove(struct platform_device *pdev) +{ + struct airoha_cpu_pmdomain_priv *priv = platform_get_drvdata(pdev); + + of_genpd_del_provider(pdev->dev.of_node); + pm_genpd_remove(&priv->pd); +} + +static const struct of_device_id airoha_cpu_pmdomain_of_match[] = { + { .compatible = "airoha,en7581-cpufreq" }, + { }, +}; +MODULE_DEVICE_TABLE(of, airoha_cpu_pmdomain_of_match); + +static struct platform_driver airoha_cpu_pmdomain_driver = { + .probe = airoha_cpu_pmdomain_probe, + .remove = airoha_cpu_pmdomain_remove, + .driver = { + .name = "airoha-cpu-pmdomain", + .of_match_table = airoha_cpu_pmdomain_of_match, + }, +}; +module_platform_driver(airoha_cpu_pmdomain_driver); + +MODULE_AUTHOR("Christian Marangi "); +MODULE_DESCRIPTION("CPU PM domain driver for Airoha SoCs"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pmdomain/ti/ti_sci_pm_domains.c b/drivers/pmdomain/ti/ti_sci_pm_domains.c index 0e4bd749d067..82df7e44250b 100644 --- a/drivers/pmdomain/ti/ti_sci_pm_domains.c +++ b/drivers/pmdomain/ti/ti_sci_pm_domains.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include #include @@ -51,6 +53,56 @@ struct ti_sci_pm_domain { #define genpd_to_ti_sci_pd(gpd) container_of(gpd, struct ti_sci_pm_domain, pd) +static inline bool ti_sci_pd_is_valid_constraint(s32 val) +{ + return val != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; +} + +#ifdef CONFIG_PM_SLEEP +static void ti_sci_pd_set_lat_constraint(struct device *dev, s32 val) +{ + struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain); + struct ti_sci_pm_domain *pd = genpd_to_ti_sci_pd(genpd); + const struct ti_sci_handle *ti_sci = pd->parent->ti_sci; + u16 val_ms; + int ret; + + /* PM QoS latency unit is usecs, TI SCI uses msecs */ + val_ms = val / USEC_PER_MSEC; + ret = ti_sci->ops.pm_ops.set_latency_constraint(ti_sci, val_ms, TISCI_MSG_CONSTRAINT_SET); + if (ret) + dev_err(dev, "ti_sci_pd: set latency constraint failed: ret=%d\n", + ret); + else + dev_dbg(dev, "ti_sci_pd: ID:%d set latency constraint %d\n", + pd->idx, val); +} +#endif + +static inline void ti_sci_pd_set_wkup_constraint(struct device *dev) +{ + struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain); + struct ti_sci_pm_domain *pd = genpd_to_ti_sci_pd(genpd); + const struct ti_sci_handle *ti_sci = pd->parent->ti_sci; + int ret; + + if (device_may_wakeup(dev)) { + /* + * If device can wakeup using IO daisy chain wakeups, + * we do not want to set a constraint. + */ + if (dev->power.wakeirq) { + dev_dbg(dev, "%s: has wake IRQ, not setting constraints\n", __func__); + return; + } + + ret = ti_sci->ops.pm_ops.set_device_constraint(ti_sci, pd->idx, + TISCI_MSG_CONSTRAINT_SET); + if (!ret) + dev_dbg(dev, "ti_sci_pd: ID:%d set device constraint.\n", pd->idx); + } +} + /* * ti_sci_pd_power_off(): genpd power down hook * @domain: pointer to the powerdomain to power off @@ -79,6 +131,28 @@ static int ti_sci_pd_power_on(struct generic_pm_domain *domain) return ti_sci->ops.dev_ops.get_device(ti_sci, pd->idx); } +#ifdef CONFIG_PM_SLEEP +static int ti_sci_pd_suspend(struct device *dev) +{ + int ret; + s32 val; + + ret = pm_generic_suspend(dev); + if (ret) + return ret; + + val = dev_pm_qos_read_value(dev, DEV_PM_QOS_RESUME_LATENCY); + if (ti_sci_pd_is_valid_constraint(val)) + ti_sci_pd_set_lat_constraint(dev, val); + + ti_sci_pd_set_wkup_constraint(dev); + + return 0; +} +#else +#define ti_sci_pd_suspend NULL +#endif + /* * ti_sci_pd_xlate(): translation service for TI SCI genpds * @genpdspec: DT identification data for the genpd @@ -182,6 +256,13 @@ static int ti_sci_pm_domain_probe(struct platform_device *pdev) pd->pd.flags |= GENPD_FLAG_ACTIVE_WAKEUP; pd->idx = args.args[0]; pd->parent = pd_provider; + /* + * If SCI constraint functions are present, then firmware + * supports the constraints API. + */ + if (pd_provider->ti_sci->ops.pm_ops.set_device_constraint && + pd_provider->ti_sci->ops.pm_ops.set_latency_constraint) + pd->pd.domain.ops.suspend = ti_sci_pd_suspend; pm_genpd_init(&pd->pd, NULL, true); diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig index f5fc33a8bf44..60bf0ca64cf3 100644 --- a/drivers/power/reset/Kconfig +++ b/drivers/power/reset/Kconfig @@ -26,7 +26,7 @@ config POWER_RESET_AT91_POWEROFF config POWER_RESET_AT91_RESET tristate "Atmel AT91 reset driver" depends on ARCH_AT91 - default SOC_AT91SAM9 || SOC_SAM9X60 || SOC_SAMA5 + default SOC_AT91SAM9 || SOC_SAM9X60 || SOC_SAM9X7 || SOC_SAMA5 help This driver supports restart for Atmel AT91SAM9 and SAMA5 SoCs @@ -34,7 +34,7 @@ config POWER_RESET_AT91_RESET config POWER_RESET_AT91_SAMA5D2_SHDWC tristate "Atmel AT91 SAMA5D2-Compatible shutdown controller driver" depends on ARCH_AT91 - default SOC_SAM9X60 || SOC_SAMA5 + default SOC_SAM9X60 || SOC_SAM9X7 || SOC_SAMA5 help This driver supports the alternate shutdown controller for some Atmel SAMA5 SoCs. It is present for example on SAMA5D2 SoC. diff --git a/drivers/power/reset/as3722-poweroff.c b/drivers/power/reset/as3722-poweroff.c index bb26fa6fa67c..8075382cbc36 100644 --- a/drivers/power/reset/as3722-poweroff.c +++ b/drivers/power/reset/as3722-poweroff.c @@ -57,8 +57,6 @@ static int as3722_poweroff_probe(struct platform_device *pdev) SYS_OFF_PRIO_DEFAULT, as3722_pm_power_off, as3722_poweroff); - - return 0; } static struct platform_driver as3722_poweroff_driver = { diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c index edb0df86aff4..c2801bd6384d 100644 --- a/drivers/power/reset/at91-sama5d2_shdwc.c +++ b/drivers/power/reset/at91-sama5d2_shdwc.c @@ -326,6 +326,7 @@ static const struct of_device_id at91_pmc_ids[] = { { .compatible = "atmel,sama5d2-pmc" }, { .compatible = "microchip,sam9x60-pmc" }, { .compatible = "microchip,sama7g5-pmc" }, + { .compatible = "microchip,sam9x7-pmc" }, { /* Sentinel. */ } }; diff --git a/drivers/power/reset/gpio-poweroff.c b/drivers/power/reset/gpio-poweroff.c index 52cfeee2cb28..3eaae352ffb9 100644 --- a/drivers/power/reset/gpio-poweroff.c +++ b/drivers/power/reset/gpio-poweroff.c @@ -44,7 +44,13 @@ static int gpio_poweroff_do_poweroff(struct sys_off_data *data) /* give it some time */ mdelay(gpio_poweroff->timeout_ms); - WARN_ON(1); + /* + * If code reaches this point, it means that gpio-poweroff has failed + * to actually power off the system. + * Warn the user that the attempt to poweroff via gpio-poweroff + * has gone wrong. + */ + WARN(1, "Failed to poweroff via gpio-poweroff mechanism\n"); return NOTIFY_DONE; } diff --git a/drivers/power/reset/keystone-reset.c b/drivers/power/reset/keystone-reset.c index cfaa54ced0d0..d9268d150e1f 100644 --- a/drivers/power/reset/keystone-reset.c +++ b/drivers/power/reset/keystone-reset.c @@ -87,26 +87,16 @@ static int rsctrl_probe(struct platform_device *pdev) return -ENODEV; /* get regmaps */ - pllctrl_regs = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pll"); + pllctrl_regs = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-pll", + 1, &rspll_offset); if (IS_ERR(pllctrl_regs)) return PTR_ERR(pllctrl_regs); - devctrl_regs = syscon_regmap_lookup_by_phandle(np, "ti,syscon-dev"); + devctrl_regs = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-dev", + 1, &rsmux_offset); if (IS_ERR(devctrl_regs)) return PTR_ERR(devctrl_regs); - ret = of_property_read_u32_index(np, "ti,syscon-pll", 1, &rspll_offset); - if (ret) { - dev_err(dev, "couldn't read the reset pll offset!\n"); - return -EINVAL; - } - - ret = of_property_read_u32_index(np, "ti,syscon-dev", 1, &rsmux_offset); - if (ret) { - dev_err(dev, "couldn't read the rsmux offset!\n"); - return -EINVAL; - } - /* set soft/hard reset */ val = of_property_read_bool(np, "ti,soft-reset"); val = val ? RSCFG_RSTYPE_SOFT : RSCFG_RSTYPE_HARD; diff --git a/drivers/power/sequencing/pwrseq-qcom-wcn.c b/drivers/power/sequencing/pwrseq-qcom-wcn.c index 682a9beac69e..e8f5030f2639 100644 --- a/drivers/power/sequencing/pwrseq-qcom-wcn.c +++ b/drivers/power/sequencing/pwrseq-qcom-wcn.c @@ -272,6 +272,24 @@ static const struct pwrseq_qcom_wcn_pdata pwrseq_qca6390_of_data = { .targets = pwrseq_qcom_wcn_targets, }; +static const char *const pwrseq_wcn6750_vregs[] = { + "vddaon", + "vddasd", + "vddpmu", + "vddrfa0p8", + "vddrfa1p2", + "vddrfa1p7", + "vddrfa2p2", +}; + +static const struct pwrseq_qcom_wcn_pdata pwrseq_wcn6750_of_data = { + .vregs = pwrseq_wcn6750_vregs, + .num_vregs = ARRAY_SIZE(pwrseq_wcn6750_vregs), + .pwup_delay_ms = 50, + .gpio_enable_delay_ms = 5, + .targets = pwrseq_qcom_wcn_targets, +}; + static const char *const pwrseq_wcn6855_vregs[] = { "vddio", "vddaon", @@ -378,6 +396,13 @@ static int pwrseq_qcom_wcn_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(ctx->bt_gpio), "Failed to get the Bluetooth enable GPIO\n"); + /* + * FIXME: This should actually be GPIOD_OUT_LOW, but doing so would + * cause the WLAN power to be toggled, resulting in PCIe link down. + * Since the PCIe controller driver is not handling link down currently, + * the device becomes unusable. So we need to keep this workaround until + * the link down handling is implemented in the controller driver. + */ ctx->wlan_gpio = devm_gpiod_get_optional(dev, "wlan-enable", GPIOD_ASIS); if (IS_ERR(ctx->wlan_gpio)) @@ -431,6 +456,10 @@ static const struct of_device_id pwrseq_qcom_wcn_of_match[] = { .compatible = "qcom,wcn7850-pmu", .data = &pwrseq_wcn7850_of_data, }, + { + .compatible = "qcom,wcn6750-pmu", + .data = &pwrseq_wcn6750_of_data, + }, { } }; MODULE_DEVICE_TABLE(of, pwrseq_qcom_wcn_of_match); diff --git a/drivers/power/supply/88pm860x_battery.c b/drivers/power/supply/88pm860x_battery.c index b7938fbb24a5..edae1e843c51 100644 --- a/drivers/power/supply/88pm860x_battery.c +++ b/drivers/power/supply/88pm860x_battery.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -503,8 +504,7 @@ static void pm860x_init_battery(struct pm860x_battery_info *info) data = pm860x_reg_read(info->i2c, PM8607_POWER_UP_LOG); bat_remove = data & BAT_WU_LOG; - dev_dbg(info->dev, "battery wake up? %s\n", - bat_remove != 0 ? "yes" : "no"); + dev_dbg(info->dev, "battery wake up? %s\n", str_yes_no(bat_remove)); /* restore SOC from RTC domain register */ if (bat_remove == 0) { diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index 9f2eef6787f7..7b18358f194a 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -918,6 +918,15 @@ config FUEL_GAUGE_SC27XX Say Y here to enable support for fuel gauge with SC27XX PMIC chips. +config FUEL_GAUGE_STC3117 + tristate "STMicroelectronics STC3117 fuel gauge driver" + depends on CRC8 + depends on I2C + select REGMAP_I2C + help + Say Y here to enable support for fuel gauge with STC3117 + chip. + config CHARGER_UCS1002 tristate "Microchip UCS1002 USB Port Power Controller" depends on I2C diff --git a/drivers/power/supply/Makefile b/drivers/power/supply/Makefile index 59c4a9f40d28..b55cc48a4c86 100644 --- a/drivers/power/supply/Makefile +++ b/drivers/power/supply/Makefile @@ -108,6 +108,7 @@ obj-$(CONFIG_CHARGER_CROS_USBPD) += cros_usbpd-charger.o obj-$(CONFIG_CHARGER_CROS_PCHG) += cros_peripheral_charger.o obj-$(CONFIG_CHARGER_SC2731) += sc2731_charger.o obj-$(CONFIG_FUEL_GAUGE_SC27XX) += sc27xx_fuel_gauge.o +obj-$(CONFIG_FUEL_GAUGE_STC3117) += stc3117_fuel_gauge.o obj-$(CONFIG_CHARGER_UCS1002) += ucs1002_power.o obj-$(CONFIG_CHARGER_BD99954) += bd99954-charger.o obj-$(CONFIG_CHARGER_WILCO) += wilco-charger.o diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 37039e28fc4b..b00c84fbc33c 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -540,10 +540,9 @@ static int ab8500_btemp_get_property(struct power_supply *psy, return 0; } -static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data) +static int ab8500_btemp_get_ext_psy_data(struct power_supply *ext, void *data) { struct power_supply *psy; - struct power_supply *ext = dev_get_drvdata(dev); const char **supplicants = (const char **)ext->supplied_to; struct ab8500_btemp *di; union power_supply_propval ret; @@ -617,7 +616,7 @@ static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data) */ static void ab8500_btemp_external_power_changed(struct power_supply *psy) { - power_supply_for_each_device(psy, ab8500_btemp_get_ext_psy_data); + power_supply_for_each_psy(psy, ab8500_btemp_get_ext_psy_data); } /* ab8500 btemp driver interrupts and their respective isr */ diff --git a/drivers/power/supply/ab8500_chargalg.c b/drivers/power/supply/ab8500_chargalg.c index 14e1b448bd39..7a8d1feb8e90 100644 --- a/drivers/power/supply/ab8500_chargalg.c +++ b/drivers/power/supply/ab8500_chargalg.c @@ -844,10 +844,9 @@ static void handle_maxim_chg_curr(struct ab8500_chargalg *di) } } -static int ab8500_chargalg_get_ext_psy_data(struct device *dev, void *data) +static int ab8500_chargalg_get_ext_psy_data(struct power_supply *ext, void *data) { struct power_supply *psy; - struct power_supply *ext = dev_get_drvdata(dev); const char **supplicants = (const char **)ext->supplied_to; struct ab8500_chargalg *di; union power_supply_propval ret; @@ -1231,7 +1230,7 @@ static void ab8500_chargalg_algorithm(struct ab8500_chargalg *di) int ret; /* Collect data from all power_supply class devices */ - power_supply_for_each_device(di->chargalg_psy, ab8500_chargalg_get_ext_psy_data); + power_supply_for_each_psy(di->chargalg_psy, ab8500_chargalg_get_ext_psy_data); ab8500_chargalg_end_of_charge(di); ab8500_chargalg_check_temp(di); diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c index cece8d6753ac..1042d37424f5 100644 --- a/drivers/power/supply/ab8500_charger.c +++ b/drivers/power/supply/ab8500_charger.c @@ -1894,10 +1894,9 @@ static int ab8500_charger_update_charger_current(struct ux500_charger *charger, return ret; } -static int ab8500_charger_get_ext_psy_data(struct device *dev, void *data) +static int ab8500_charger_get_ext_psy_data(struct power_supply *ext, void *data) { struct power_supply *psy; - struct power_supply *ext = dev_get_drvdata(dev); const char **supplicants = (const char **)ext->supplied_to; struct ab8500_charger *di; union power_supply_propval ret; @@ -1961,7 +1960,7 @@ static void ab8500_charger_check_vbat_work(struct work_struct *work) struct ab8500_charger *di = container_of(work, struct ab8500_charger, check_vbat_work.work); - power_supply_for_each_device(&di->usb_chg, ab8500_charger_get_ext_psy_data); + power_supply_for_each_psy(&di->usb_chg, ab8500_charger_get_ext_psy_data); /* First run old_vbat is 0. */ if (di->old_vbat == 0) diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index 78871a2143de..9dd99722667a 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -2174,10 +2174,9 @@ static int ab8500_fg_get_property(struct power_supply *psy, return 0; } -static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data) +static int ab8500_fg_get_ext_psy_data(struct power_supply *ext, void *data) { struct power_supply *psy; - struct power_supply *ext = dev_get_drvdata(dev); const char **supplicants = (const char **)ext->supplied_to; struct ab8500_fg *di; struct power_supply_battery_info *bi; @@ -2402,7 +2401,7 @@ out: */ static void ab8500_fg_external_power_changed(struct power_supply *psy) { - power_supply_for_each_device(psy, ab8500_fg_get_ext_psy_data); + power_supply_for_each_psy(psy, ab8500_fg_get_ext_psy_data); } /** @@ -2575,7 +2574,7 @@ static ssize_t ab8505_powercut_flagtime_read(struct device *dev, { int ret; u8 reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); ret = abx500_get_register_interruptible(di->dev, AB8500_RTC, @@ -2598,7 +2597,7 @@ static ssize_t ab8505_powercut_flagtime_write(struct device *dev, { int ret; int reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); if (kstrtoint(buf, 10, ®_value)) @@ -2625,7 +2624,7 @@ static ssize_t ab8505_powercut_maxtime_read(struct device *dev, { int ret; u8 reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); ret = abx500_get_register_interruptible(di->dev, AB8500_RTC, @@ -2649,7 +2648,7 @@ static ssize_t ab8505_powercut_maxtime_write(struct device *dev, { int ret; int reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); if (kstrtoint(buf, 10, ®_value)) @@ -2676,7 +2675,7 @@ static ssize_t ab8505_powercut_restart_read(struct device *dev, { int ret; u8 reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); ret = abx500_get_register_interruptible(di->dev, AB8500_RTC, @@ -2699,7 +2698,7 @@ static ssize_t ab8505_powercut_restart_write(struct device *dev, { int ret; int reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); if (kstrtoint(buf, 10, ®_value)) @@ -2727,7 +2726,7 @@ static ssize_t ab8505_powercut_timer_read(struct device *dev, { int ret; u8 reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); ret = abx500_get_register_interruptible(di->dev, AB8500_RTC, @@ -2750,7 +2749,7 @@ static ssize_t ab8505_powercut_restart_counter_read(struct device *dev, { int ret; u8 reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); ret = abx500_get_register_interruptible(di->dev, AB8500_RTC, @@ -2773,7 +2772,7 @@ static ssize_t ab8505_powercut_read(struct device *dev, { int ret; u8 reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); ret = abx500_get_register_interruptible(di->dev, AB8500_RTC, @@ -2794,7 +2793,7 @@ static ssize_t ab8505_powercut_write(struct device *dev, { int ret; int reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); if (kstrtoint(buf, 10, ®_value)) @@ -2822,7 +2821,7 @@ static ssize_t ab8505_powercut_flag_read(struct device *dev, int ret; u8 reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); ret = abx500_get_register_interruptible(di->dev, AB8500_RTC, @@ -2845,7 +2844,7 @@ static ssize_t ab8505_powercut_debounce_read(struct device *dev, { int ret; u8 reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); ret = abx500_get_register_interruptible(di->dev, AB8500_RTC, @@ -2868,7 +2867,7 @@ static ssize_t ab8505_powercut_debounce_write(struct device *dev, { int ret; int reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); if (kstrtoint(buf, 10, ®_value)) @@ -2895,7 +2894,7 @@ static ssize_t ab8505_powercut_enable_status_read(struct device *dev, { int ret; u8 reg_value; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct ab8500_fg *di = power_supply_get_drvdata(psy); ret = abx500_get_register_interruptible(di->dev, AB8500_RTC, diff --git a/drivers/power/supply/apm_power.c b/drivers/power/supply/apm_power.c index 8ef1b6f1f787..9236e0078578 100644 --- a/drivers/power/supply/apm_power.c +++ b/drivers/power/supply/apm_power.c @@ -42,11 +42,11 @@ struct find_bat_param { int max_energy; }; -static int __find_main_battery(struct device *dev, void *data) +static int __find_main_battery(struct power_supply *psy, void *data) { struct find_bat_param *bp = (struct find_bat_param *)data; - bp->bat = dev_get_drvdata(dev); + bp->bat = psy; if (bp->bat->desc->use_for_apm) { /* nice, we explicitly asked to report this battery. */ @@ -79,7 +79,7 @@ static void find_main_battery(void) main_battery = NULL; bp.main = main_battery; - error = power_supply_for_each_device(&bp, __find_main_battery); + error = power_supply_for_each_psy(&bp, __find_main_battery); if (error) { main_battery = bp.main; return; diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c index 25e28dac900d..22f6a3b71632 100644 --- a/drivers/power/supply/bq2415x_charger.c +++ b/drivers/power/supply/bq2415x_charger.c @@ -171,6 +171,7 @@ struct bq2415x_device { char *name; int autotimer; /* 1 - if driver automatically reset timer, 0 - not */ int automode; /* 1 - enabled, 0 - disabled; -1 - not supported */ + int charge_status; int id; }; @@ -835,11 +836,13 @@ static int bq2415x_notifier_call(struct notifier_block *nb, if (!bq2415x_update_reported_mode(bq, prop.intval)) return NOTIFY_OK; + power_supply_changed(bq->charger); + /* if automode is not enabled do not tell about reported_mode */ if (bq->automode < 1) return NOTIFY_OK; - schedule_delayed_work(&bq->work, 0); + mod_delayed_work(system_wq, &bq->work, 0); return NOTIFY_OK; } @@ -889,12 +892,19 @@ static void bq2415x_timer_work(struct work_struct *work) int ret; int error; int boost; + int charge; if (bq->automode > 0 && (bq->reported_mode != bq->mode)) { sysfs_notify(&bq->charger->dev.kobj, NULL, "reported_mode"); bq2415x_set_mode(bq, bq->reported_mode); } + charge = bq2415x_exec_command(bq, BQ2415X_CHARGE_STATUS); + if (bq->charge_status != charge) { + power_supply_changed(bq->charger); + bq->charge_status = charge; + } + if (!bq->autotimer) return; @@ -1050,7 +1060,7 @@ static ssize_t bq2415x_sysfs_show_status(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); enum bq2415x_command command; int ret; @@ -1083,7 +1093,7 @@ static ssize_t bq2415x_sysfs_set_timer(struct device *dev, const char *buf, size_t count) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); int ret = 0; @@ -1104,7 +1114,7 @@ static ssize_t bq2415x_sysfs_show_timer(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); if (bq->timer_error) @@ -1128,7 +1138,7 @@ static ssize_t bq2415x_sysfs_set_mode(struct device *dev, const char *buf, size_t count) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); enum bq2415x_mode mode; int ret = 0; @@ -1180,7 +1190,7 @@ static ssize_t bq2415x_sysfs_show_mode(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); ssize_t ret = 0; @@ -1217,7 +1227,7 @@ static ssize_t bq2415x_sysfs_show_reported_mode(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); if (bq->automode < 0) @@ -1245,7 +1255,7 @@ static ssize_t bq2415x_sysfs_set_registers(struct device *dev, const char *buf, size_t count) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); ssize_t ret = 0; unsigned int reg; @@ -1280,7 +1290,7 @@ static ssize_t bq2415x_sysfs_show_registers(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); ssize_t ret = 0; @@ -1298,7 +1308,7 @@ static ssize_t bq2415x_sysfs_set_limit(struct device *dev, const char *buf, size_t count) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); long val; int ret; @@ -1329,7 +1339,7 @@ static ssize_t bq2415x_sysfs_show_limit(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); int ret; @@ -1357,7 +1367,7 @@ static ssize_t bq2415x_sysfs_set_enable(struct device *dev, const char *buf, size_t count) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); enum bq2415x_command command; long val; @@ -1392,7 +1402,7 @@ static ssize_t bq2415x_sysfs_show_enable(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq2415x_device *bq = power_supply_get_drvdata(psy); enum bq2415x_command command; int ret; diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index 2b393eb5c282..b4ba01744368 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -152,6 +152,7 @@ #define BQ24296_REG_VPRS_PN_MASK (BIT(7) | BIT(6) | BIT(5)) #define BQ24296_REG_VPRS_PN_SHIFT 5 #define BQ24296_REG_VPRS_PN_24296 0x1 +#define BQ24296_REG_VPRS_PN_24297 0x3 #define BQ24190_REG_VPRS_TS_PROFILE_MASK BIT(2) #define BQ24190_REG_VPRS_TS_PROFILE_SHIFT 2 #define BQ24190_REG_VPRS_DEV_REG_MASK (BIT(1) | BIT(0)) @@ -208,6 +209,7 @@ enum bq24190_chip { BQ24192i, BQ24196, BQ24296, + BQ24297, }; /* @@ -422,7 +424,7 @@ static struct bq24190_sysfs_field_info bq24190_sysfs_field_tbl[] = { BQ24190_SYSFS_FIELD_RO(watchdog, CTTC, WATCHDOG), BQ24190_SYSFS_FIELD_RW(en_timer, CTTC, EN_TIMER), BQ24190_SYSFS_FIELD_RW(chg_timer, CTTC, CHG_TIMER), - BQ24190_SYSFS_FIELD_RW(jeta_iset, CTTC, JEITA_ISET), + BQ24190_SYSFS_FIELD_RW(jeita_iset, CTTC, JEITA_ISET), BQ24190_SYSFS_FIELD_RW(bat_comp, ICTRC, BAT_COMP), BQ24190_SYSFS_FIELD_RW(vclamp, ICTRC, VCLAMP), BQ24190_SYSFS_FIELD_RW(treg, ICTRC, TREG), @@ -480,7 +482,7 @@ static struct bq24190_sysfs_field_info *bq24190_sysfs_field_lookup( static ssize_t bq24190_sysfs_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq24190_dev_info *bdi = power_supply_get_drvdata(psy); struct bq24190_sysfs_field_info *info; ssize_t count; @@ -510,7 +512,7 @@ static ssize_t bq24190_sysfs_show(struct device *dev, static ssize_t bq24190_sysfs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq24190_dev_info *bdi = power_supply_get_drvdata(psy); struct bq24190_sysfs_field_info *info; int ret; @@ -567,6 +569,7 @@ static int bq24190_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) static int bq24296_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) { + union power_supply_propval val = { .intval = bdi->charge_type }; int ret; ret = pm_runtime_resume_and_get(bdi->dev); @@ -587,13 +590,18 @@ static int bq24296_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) ret = bq24190_write_mask(bdi, BQ24190_REG_POC, BQ24296_REG_POC_OTG_CONFIG_MASK, - BQ24296_REG_POC_CHG_CONFIG_SHIFT, + BQ24296_REG_POC_OTG_CONFIG_SHIFT, BQ24296_REG_POC_OTG_CONFIG_OTG); - } else + } else { ret = bq24190_write_mask(bdi, BQ24190_REG_POC, BQ24296_REG_POC_OTG_CONFIG_MASK, - BQ24296_REG_POC_CHG_CONFIG_SHIFT, + BQ24296_REG_POC_OTG_CONFIG_SHIFT, BQ24296_REG_POC_OTG_CONFIG_DISABLE); + if (ret < 0) + goto out; + + ret = bq24190_charger_set_charge_type(bdi, &val); + } out: pm_runtime_mark_last_busy(bdi->dev); @@ -1313,6 +1321,7 @@ static int bq24190_charger_get_property(struct power_supply *psy, switch (psp) { case POWER_SUPPLY_PROP_CHARGE_TYPE: + case POWER_SUPPLY_PROP_CHARGE_TYPES: ret = bq24190_charger_get_charge_type(bdi, val); break; case POWER_SUPPLY_PROP_HEALTH: @@ -1393,6 +1402,7 @@ static int bq24190_charger_set_property(struct power_supply *psy, ret = bq24190_charger_set_temp_alert_max(bdi, val); break; case POWER_SUPPLY_PROP_CHARGE_TYPE: + case POWER_SUPPLY_PROP_CHARGE_TYPES: ret = bq24190_charger_set_charge_type(bdi, val); break; case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT: @@ -1421,6 +1431,7 @@ static int bq24190_charger_property_is_writeable(struct power_supply *psy, case POWER_SUPPLY_PROP_ONLINE: case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: case POWER_SUPPLY_PROP_CHARGE_TYPE: + case POWER_SUPPLY_PROP_CHARGE_TYPES: case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT: case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE: case POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT: @@ -1469,6 +1480,7 @@ static void bq24190_charger_external_power_changed(struct power_supply *psy) static enum power_supply_property bq24190_charger_properties[] = { POWER_SUPPLY_PROP_CHARGE_TYPE, + POWER_SUPPLY_PROP_CHARGE_TYPES, POWER_SUPPLY_PROP_HEALTH, POWER_SUPPLY_PROP_ONLINE, POWER_SUPPLY_PROP_STATUS, @@ -1498,6 +1510,9 @@ static const struct power_supply_desc bq24190_charger_desc = { .set_property = bq24190_charger_set_property, .property_is_writeable = bq24190_charger_property_is_writeable, .external_power_changed = bq24190_charger_external_power_changed, + .charge_types = BIT(POWER_SUPPLY_CHARGE_TYPE_NONE) | + BIT(POWER_SUPPLY_CHARGE_TYPE_TRICKLE) | + BIT(POWER_SUPPLY_CHARGE_TYPE_FAST), }; /* Battery power supply property routines */ @@ -1891,6 +1906,7 @@ static int bq24296_check_chip(struct bq24190_dev_info *bdi) switch (v) { case BQ24296_REG_VPRS_PN_24296: + case BQ24296_REG_VPRS_PN_24297: break; default: dev_err(bdi->dev, "Error unknown model: 0x%02x\n", v); @@ -2020,6 +2036,17 @@ static const struct bq24190_chip_info bq24190_chip_info_tbl[] = { .ichg_array_size = BQ24296_CCC_ICHG_VALUES_LEN, #ifdef CONFIG_REGULATOR .vbus_desc = &bq24296_vbus_desc, +#endif + .check_chip = bq24296_check_chip, + .set_chg_config = bq24296_battery_set_chg_config, + .ntc_fault_mask = BQ24296_REG_F_NTC_FAULT_MASK, + .get_ntc_status = bq24296_charger_get_ntc_status, + .set_otg_vbus = bq24296_set_otg_vbus, + }, + [BQ24297] = { + .ichg_array_size = BQ24296_CCC_ICHG_VALUES_LEN, +#ifdef CONFIG_REGULATOR + .vbus_desc = &bq24296_vbus_desc, #endif .check_chip = bq24296_check_chip, .set_chg_config = bq24296_battery_set_chg_config, @@ -2283,6 +2310,7 @@ static const struct i2c_device_id bq24190_i2c_ids[] = { { "bq24192i", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24192i] }, { "bq24196", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24196] }, { "bq24296", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24296] }, + { "bq24297", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24297] }, { }, }; MODULE_DEVICE_TABLE(i2c, bq24190_i2c_ids); @@ -2293,6 +2321,7 @@ static const struct of_device_id bq24190_of_match[] = { { .compatible = "ti,bq24192i", .data = &bq24190_chip_info_tbl[BQ24192i] }, { .compatible = "ti,bq24196", .data = &bq24190_chip_info_tbl[BQ24196] }, { .compatible = "ti,bq24296", .data = &bq24190_chip_info_tbl[BQ24296] }, + { .compatible = "ti,bq24297", .data = &bq24190_chip_info_tbl[BQ24297] }, { }, }; MODULE_DEVICE_TABLE(of, bq24190_of_match); diff --git a/drivers/power/supply/bq24257_charger.c b/drivers/power/supply/bq24257_charger.c index 801d0d2c5f2e..1416586f2459 100644 --- a/drivers/power/supply/bq24257_charger.c +++ b/drivers/power/supply/bq24257_charger.c @@ -759,7 +759,7 @@ static ssize_t bq24257_show_ovp_voltage(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq24257_device *bq = power_supply_get_drvdata(psy); return sysfs_emit(buf, "%u\n", bq24257_vovp_map[bq->init_data.vovp]); @@ -769,7 +769,7 @@ static ssize_t bq24257_show_in_dpm_voltage(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq24257_device *bq = power_supply_get_drvdata(psy); return sysfs_emit(buf, "%u\n", bq24257_vindpm_map[bq->init_data.vindpm]); @@ -779,7 +779,7 @@ static ssize_t bq24257_sysfs_show_enable(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq24257_device *bq = power_supply_get_drvdata(psy); int ret; @@ -801,7 +801,7 @@ static ssize_t bq24257_sysfs_set_enable(struct device *dev, const char *buf, size_t count) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct bq24257_device *bq = power_supply_get_drvdata(psy); long val; int ret; diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 40c5ac7a1118..90a5bccfc6b9 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -123,6 +123,7 @@ enum bq27xxx_reg_index { BQ27XXX_DM_BLOCK, /* Data Block */ BQ27XXX_DM_DATA, /* Block Data */ BQ27XXX_DM_CKSUM, /* Block Data Checksum */ + BQ27XXX_REG_SEDVF, /* End-of-discharge Voltage */ BQ27XXX_REG_MAX, /* sentinel */ }; @@ -159,6 +160,7 @@ static u8 [BQ27XXX_DM_BLOCK] = INVALID_REG_ADDR, [BQ27XXX_DM_DATA] = INVALID_REG_ADDR, [BQ27XXX_DM_CKSUM] = INVALID_REG_ADDR, + [BQ27XXX_REG_SEDVF] = 0x77, }, bq27010_regs[BQ27XXX_REG_MAX] = { [BQ27XXX_REG_CTRL] = 0x00, @@ -184,6 +186,7 @@ static u8 [BQ27XXX_DM_BLOCK] = INVALID_REG_ADDR, [BQ27XXX_DM_DATA] = INVALID_REG_ADDR, [BQ27XXX_DM_CKSUM] = INVALID_REG_ADDR, + [BQ27XXX_REG_SEDVF] = 0x77, }, bq2750x_regs[BQ27XXX_REG_MAX] = { [BQ27XXX_REG_CTRL] = 0x00, @@ -579,6 +582,7 @@ static enum power_supply_property bq27000_props[] = { POWER_SUPPLY_PROP_POWER_AVG, POWER_SUPPLY_PROP_HEALTH, POWER_SUPPLY_PROP_MANUFACTURER, + POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN, }; static enum power_supply_property bq27010_props[] = { @@ -599,6 +603,7 @@ static enum power_supply_property bq27010_props[] = { POWER_SUPPLY_PROP_CYCLE_COUNT, POWER_SUPPLY_PROP_HEALTH, POWER_SUPPLY_PROP_MANUFACTURER, + POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN, }; #define bq2750x_props bq27510g3_props @@ -2039,6 +2044,36 @@ static int bq27xxx_battery_voltage(struct bq27xxx_device_info *di, return 0; } +/* + * Return the design minimum battery Voltage in microvolts + * Or < 0 if something fails. + */ +static int bq27xxx_battery_read_dmin_volt(struct bq27xxx_device_info *di, + union power_supply_propval *val) +{ + int volt; + + /* We only have to read design minimum voltage once */ + if (di->voltage_min_design > 0) { + val->intval = di->voltage_min_design; + return 0; + } + + volt = bq27xxx_read(di, BQ27XXX_REG_SEDVF, true); + if (volt < 0) { + dev_err(di->dev, "error reading design min voltage\n"); + return volt; + } + + /* SEDVF = Design EDVF / 8 - 256 */ + val->intval = volt * 8000 + 2048000; + + /* Save for later reads */ + di->voltage_min_design = val->intval; + + return 0; +} + static int bq27xxx_simple_value(int value, union power_supply_propval *val) { @@ -2119,8 +2154,10 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, * power_supply_battery_info visible in sysfs. */ case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN: - case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: return -EINVAL; + case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: + ret = bq27xxx_battery_read_dmin_volt(di, val); + break; case POWER_SUPPLY_PROP_CYCLE_COUNT: ret = bq27xxx_battery_read_cyct(di, val); break; diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c index a69faef444c0..c49e0e4d02f7 100644 --- a/drivers/power/supply/charger-manager.c +++ b/drivers/power/supply/charger-manager.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -1088,7 +1089,7 @@ static ssize_t charger_state_show(struct device *dev, if (!charger->externally_control) state = regulator_is_enabled(charger->consumer); - return sysfs_emit(buf, "%s\n", state ? "enabled" : "disabled"); + return sysfs_emit(buf, "%s\n", str_enabled_disabled(state)); } static ssize_t charger_externally_control_show(struct device *dev, diff --git a/drivers/power/supply/cpcap-charger.c b/drivers/power/supply/cpcap-charger.c index 7781b45a67a7..6625d539d9ae 100644 --- a/drivers/power/supply/cpcap-charger.c +++ b/drivers/power/supply/cpcap-charger.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -515,7 +516,7 @@ static void cpcap_charger_vbus_work(struct work_struct *work) out_err: cpcap_charger_update_state(ddata, POWER_SUPPLY_STATUS_UNKNOWN); dev_err(ddata->dev, "%s could not %s vbus: %i\n", __func__, - ddata->vbus_enabled ? "enable" : "disable", error); + str_enable_disable(ddata->vbus_enabled), error); } static int cpcap_charger_set_vbus(struct phy_companion *comparator, diff --git a/drivers/power/supply/cros_charge-control.c b/drivers/power/supply/cros_charge-control.c index 17c53591ce19..02d5bdbe2e8d 100644 --- a/drivers/power/supply/cros_charge-control.c +++ b/drivers/power/supply/cros_charge-control.c @@ -7,8 +7,10 @@ #include #include #include +#include #include #include +#include #include #include #include @@ -18,13 +20,6 @@ BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE) | \ BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE)) -enum CROS_CHCTL_ATTR { - CROS_CHCTL_ATTR_START_THRESHOLD, - CROS_CHCTL_ATTR_END_THRESHOLD, - CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR, - _CROS_CHCTL_ATTR_COUNT -}; - /* * Semantics of data *returned* from the EC API and Linux sysfs differ * slightly, also the v1 API can not return any data. @@ -36,19 +31,15 @@ enum CROS_CHCTL_ATTR { */ struct cros_chctl_priv { + struct device *dev; struct cros_ec_device *cros_ec; struct acpi_battery_hook battery_hook; struct power_supply *hooked_battery; u8 cmd_version; - /* The callbacks need to access this priv structure. - * As neither the struct device nor power_supply are under the drivers - * control, embed the attributes within priv to use with container_of(). - */ - struct device_attribute device_attrs[_CROS_CHCTL_ATTR_COUNT]; - struct attribute *attributes[_CROS_CHCTL_ATTR_COUNT]; - struct attribute_group group; + const struct power_supply_ext *psy_ext; + struct mutex lock; /* protects fields below and cros_ec */ enum power_supply_charge_behaviour current_behaviour; u8 current_start_threshold, current_end_threshold; }; @@ -85,6 +76,8 @@ static int cros_chctl_configure_ec(struct cros_chctl_priv *priv) { struct ec_params_charge_control req = {}; + lockdep_assert_held(&priv->lock); + req.cmd = EC_CHARGE_CONTROL_CMD_SET; switch (priv->current_behaviour) { @@ -114,31 +107,48 @@ static int cros_chctl_configure_ec(struct cros_chctl_priv *priv) return cros_chctl_send_charge_control_cmd(priv->cros_ec, priv->cmd_version, &req); } -static struct cros_chctl_priv *cros_chctl_attr_to_priv(struct attribute *attr, - enum CROS_CHCTL_ATTR idx) +static int cros_chctl_psy_ext_get_prop(struct power_supply *psy, + const struct power_supply_ext *ext, + void *data, + enum power_supply_property psp, + union power_supply_propval *val) { - struct device_attribute *dev_attr = container_of(attr, struct device_attribute, attr); + struct cros_chctl_priv *priv = data; - return container_of(dev_attr, struct cros_chctl_priv, device_attrs[idx]); + switch (psp) { + case POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD: + val->intval = priv->current_start_threshold; + return 0; + case POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD: + val->intval = priv->current_end_threshold; + return 0; + case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR: + val->intval = priv->current_behaviour; + return 0; + default: + return -EINVAL; + } } -static ssize_t cros_chctl_store_threshold(struct device *dev, struct cros_chctl_priv *priv, - int is_end_threshold, const char *buf, size_t count) +static int cros_chctl_psy_ext_set_threshold(struct cros_chctl_priv *priv, + enum power_supply_property psp, + int val) { - int ret, val; + int ret; - ret = kstrtoint(buf, 10, &val); - if (ret < 0) - return ret; if (val < 0 || val > 100) return -EINVAL; - if (is_end_threshold) { - if (val <= priv->current_start_threshold) + if (psp == POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD) { + /* Start threshold is not exposed, use fixed value */ + if (priv->cmd_version == 2) + priv->current_start_threshold = val == 100 ? 0 : val; + + if (val < priv->current_start_threshold) return -EINVAL; priv->current_end_threshold = val; } else { - if (val >= priv->current_end_threshold) + if (val > priv->current_end_threshold) return -EINVAL; priv->current_start_threshold = val; } @@ -149,89 +159,73 @@ static ssize_t cros_chctl_store_threshold(struct device *dev, struct cros_chctl_ return ret; } - return count; + return 0; } -static ssize_t charge_control_start_threshold_show(struct device *dev, - struct device_attribute *attr, - char *buf) + +static int cros_chctl_psy_ext_set_prop(struct power_supply *psy, + const struct power_supply_ext *ext, + void *data, + enum power_supply_property psp, + const union power_supply_propval *val) { - struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, - CROS_CHCTL_ATTR_START_THRESHOLD); - - return sysfs_emit(buf, "%u\n", (unsigned int)priv->current_start_threshold); -} - -static ssize_t charge_control_start_threshold_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, - CROS_CHCTL_ATTR_START_THRESHOLD); - - return cros_chctl_store_threshold(dev, priv, 0, buf, count); -} - -static ssize_t charge_control_end_threshold_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, - CROS_CHCTL_ATTR_END_THRESHOLD); - - return sysfs_emit(buf, "%u\n", (unsigned int)priv->current_end_threshold); -} - -static ssize_t charge_control_end_threshold_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) -{ - struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, - CROS_CHCTL_ATTR_END_THRESHOLD); - - return cros_chctl_store_threshold(dev, priv, 1, buf, count); -} - -static ssize_t charge_behaviour_show(struct device *dev, struct device_attribute *attr, char *buf) -{ - struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, - CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR); - - return power_supply_charge_behaviour_show(dev, EC_CHARGE_CONTROL_BEHAVIOURS, - priv->current_behaviour, buf); -} - -static ssize_t charge_behaviour_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) -{ - struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, - CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR); + struct cros_chctl_priv *priv = data; int ret; - ret = power_supply_charge_behaviour_parse(EC_CHARGE_CONTROL_BEHAVIOURS, buf); - if (ret < 0) - return ret; + guard(mutex)(&priv->lock); - priv->current_behaviour = ret; - - ret = cros_chctl_configure_ec(priv); - if (ret < 0) - return ret; - - return count; + switch (psp) { + case POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD: + case POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD: + return cros_chctl_psy_ext_set_threshold(priv, psp, val->intval); + case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR: + priv->current_behaviour = val->intval; + ret = cros_chctl_configure_ec(priv); + if (ret < 0) + return ret; + return 0; + default: + return -EINVAL; + } } -static umode_t cros_chtl_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n) +static int cros_chctl_psy_prop_is_writeable(struct power_supply *psy, + const struct power_supply_ext *ext, + void *data, + enum power_supply_property psp) { - struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(attr, n); + return true; +} - if (priv->cmd_version < 2) { - if (n == CROS_CHCTL_ATTR_START_THRESHOLD) - return 0; - if (n == CROS_CHCTL_ATTR_END_THRESHOLD) - return 0; +#define DEFINE_CROS_CHCTL_POWER_SUPPLY_EXTENSION(_name, ...) \ + static const enum power_supply_property _name ## _props[] = { \ + __VA_ARGS__, \ + }; \ + \ + static const struct power_supply_ext _name = { \ + .name = "cros-charge-control", \ + .properties = _name ## _props, \ + .num_properties = ARRAY_SIZE(_name ## _props), \ + .charge_behaviours = EC_CHARGE_CONTROL_BEHAVIOURS, \ + .get_property = cros_chctl_psy_ext_get_prop, \ + .set_property = cros_chctl_psy_ext_set_prop, \ + .property_is_writeable = cros_chctl_psy_prop_is_writeable, \ } - return attr->mode; -} +DEFINE_CROS_CHCTL_POWER_SUPPLY_EXTENSION(cros_chctl_psy_ext_v1, + POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR +); + +DEFINE_CROS_CHCTL_POWER_SUPPLY_EXTENSION(cros_chctl_psy_ext_v2, + POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR, + POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD +); + +DEFINE_CROS_CHCTL_POWER_SUPPLY_EXTENSION(cros_chctl_psy_ext_v3, + POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR, + POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD, + POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD +); static int cros_chctl_add_battery(struct power_supply *battery, struct acpi_battery_hook *hook) { @@ -241,7 +235,7 @@ static int cros_chctl_add_battery(struct power_supply *battery, struct acpi_batt return 0; priv->hooked_battery = battery; - return device_add_group(&battery->dev, &priv->group); + return power_supply_register_extension(battery, priv->psy_ext, priv->dev, priv); } static int cros_chctl_remove_battery(struct power_supply *battery, struct acpi_battery_hook *hook) @@ -249,7 +243,7 @@ static int cros_chctl_remove_battery(struct power_supply *battery, struct acpi_b struct cros_chctl_priv *priv = container_of(hook, struct cros_chctl_priv, battery_hook); if (priv->hooked_battery == battery) { - device_remove_group(&battery->dev, &priv->group); + power_supply_unregister_extension(battery, priv->psy_ext); priv->hooked_battery = NULL; } @@ -275,7 +269,6 @@ static int cros_chctl_probe(struct platform_device *pdev) struct cros_ec_dev *ec_dev = dev_get_drvdata(dev->parent); struct cros_ec_device *cros_ec = ec_dev->ec_dev; struct cros_chctl_priv *priv; - size_t i; int ret; ret = cros_chctl_fwk_charge_control_versions(cros_ec); @@ -290,6 +283,10 @@ static int cros_chctl_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; + ret = devm_mutex_init(dev, &priv->lock); + if (ret) + return ret; + ret = cros_ec_get_cmd_versions(cros_ec, EC_CMD_CHARGE_CONTROL); if (ret < 0) return ret; @@ -304,19 +301,15 @@ static int cros_chctl_probe(struct platform_device *pdev) dev_dbg(dev, "Command version: %u\n", (unsigned int)priv->cmd_version); + priv->dev = dev; priv->cros_ec = cros_ec; - priv->device_attrs[CROS_CHCTL_ATTR_START_THRESHOLD] = - (struct device_attribute)__ATTR_RW(charge_control_start_threshold); - priv->device_attrs[CROS_CHCTL_ATTR_END_THRESHOLD] = - (struct device_attribute)__ATTR_RW(charge_control_end_threshold); - priv->device_attrs[CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR] = - (struct device_attribute)__ATTR_RW(charge_behaviour); - for (i = 0; i < _CROS_CHCTL_ATTR_COUNT; i++) { - sysfs_attr_init(&priv->device_attrs[i].attr); - priv->attributes[i] = &priv->device_attrs[i].attr; - } - priv->group.is_visible = cros_chtl_attr_is_visible; - priv->group.attrs = priv->attributes; + + if (priv->cmd_version == 1) + priv->psy_ext = &cros_chctl_psy_ext_v1; + else if (priv->cmd_version == 2) + priv->psy_ext = &cros_chctl_psy_ext_v2; + else + priv->psy_ext = &cros_chctl_psy_ext_v3; priv->battery_hook.name = dev_name(dev); priv->battery_hook.add_battery = cros_chctl_add_battery; @@ -327,7 +320,8 @@ static int cros_chctl_probe(struct platform_device *pdev) priv->current_end_threshold = 100; /* Bring EC into well-known state */ - ret = cros_chctl_configure_ec(priv); + scoped_guard(mutex, &priv->lock) + ret = cros_chctl_configure_ec(priv); if (ret < 0) return ret; diff --git a/drivers/power/supply/da9030_battery.c b/drivers/power/supply/da9030_battery.c index 34328f5d556e..ac2e319e9517 100644 --- a/drivers/power/supply/da9030_battery.c +++ b/drivers/power/supply/da9030_battery.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -138,7 +139,7 @@ static int bat_debug_show(struct seq_file *s, void *data) { struct da9030_charger *charger = s->private; - seq_printf(s, "charger is %s\n", charger->is_on ? "on" : "off"); + seq_printf(s, "charger is %s\n", str_on_off(charger->is_on)); if (charger->chdet) { seq_printf(s, "iset = %dmA, vset = %dmV\n", charger->mA, charger->mV); diff --git a/drivers/power/supply/ds2760_battery.c b/drivers/power/supply/ds2760_battery.c index 7cf4ea06b500..83bdec5a2bda 100644 --- a/drivers/power/supply/ds2760_battery.c +++ b/drivers/power/supply/ds2760_battery.c @@ -195,22 +195,22 @@ static int w1_ds2760_recall_eeprom(struct device *dev, int addr) } static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); return w1_ds2760_read(dev, buf, off, count); } -static BIN_ATTR_RO(w1_slave, DS2760_DATA_SIZE); +static const BIN_ATTR_RO(w1_slave, DS2760_DATA_SIZE); -static struct bin_attribute *w1_ds2760_bin_attrs[] = { +static const struct bin_attribute *const w1_ds2760_bin_attrs[] = { &bin_attr_w1_slave, NULL, }; static const struct attribute_group w1_ds2760_group = { - .bin_attrs = w1_ds2760_bin_attrs, + .bin_attrs_new = w1_ds2760_bin_attrs, }; static const struct attribute_group *w1_ds2760_groups[] = { diff --git a/drivers/power/supply/ds2780_battery.c b/drivers/power/supply/ds2780_battery.c index 1e7f297f6cb1..dd9ac7a32967 100644 --- a/drivers/power/supply/ds2780_battery.c +++ b/drivers/power/supply/ds2780_battery.c @@ -621,7 +621,7 @@ static ssize_t ds2780_set_pio_pin(struct device *dev, static ssize_t ds2780_read_param_eeprom_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -634,7 +634,7 @@ static ssize_t ds2780_read_param_eeprom_bin(struct file *filp, static ssize_t ds2780_write_param_eeprom_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -654,19 +654,19 @@ static ssize_t ds2780_write_param_eeprom_bin(struct file *filp, return count; } -static struct bin_attribute ds2780_param_eeprom_bin_attr = { +static const struct bin_attribute ds2780_param_eeprom_bin_attr = { .attr = { .name = "param_eeprom", .mode = S_IRUGO | S_IWUSR, }, .size = DS2780_PARAM_EEPROM_SIZE, - .read = ds2780_read_param_eeprom_bin, - .write = ds2780_write_param_eeprom_bin, + .read_new = ds2780_read_param_eeprom_bin, + .write_new = ds2780_write_param_eeprom_bin, }; static ssize_t ds2780_read_user_eeprom_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -679,7 +679,7 @@ static ssize_t ds2780_read_user_eeprom_bin(struct file *filp, static ssize_t ds2780_write_user_eeprom_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -699,14 +699,14 @@ static ssize_t ds2780_write_user_eeprom_bin(struct file *filp, return count; } -static struct bin_attribute ds2780_user_eeprom_bin_attr = { +static const struct bin_attribute ds2780_user_eeprom_bin_attr = { .attr = { .name = "user_eeprom", .mode = S_IRUGO | S_IWUSR, }, .size = DS2780_USER_EEPROM_SIZE, - .read = ds2780_read_user_eeprom_bin, - .write = ds2780_write_user_eeprom_bin, + .read_new = ds2780_read_user_eeprom_bin, + .write_new = ds2780_write_user_eeprom_bin, }; static DEVICE_ATTR(pmod_enabled, S_IRUGO | S_IWUSR, ds2780_get_pmod_enabled, @@ -726,7 +726,7 @@ static struct attribute *ds2780_sysfs_attrs[] = { NULL }; -static struct bin_attribute *ds2780_sysfs_bin_attrs[] = { +static const struct bin_attribute *const ds2780_sysfs_bin_attrs[] = { &ds2780_param_eeprom_bin_attr, &ds2780_user_eeprom_bin_attr, NULL @@ -734,7 +734,7 @@ static struct bin_attribute *ds2780_sysfs_bin_attrs[] = { static const struct attribute_group ds2780_sysfs_group = { .attrs = ds2780_sysfs_attrs, - .bin_attrs = ds2780_sysfs_bin_attrs, + .bin_attrs_new = ds2780_sysfs_bin_attrs, }; static const struct attribute_group *ds2780_sysfs_groups[] = { diff --git a/drivers/power/supply/ds2781_battery.c b/drivers/power/supply/ds2781_battery.c index c4f8ccc687f9..8a1f1f9835e0 100644 --- a/drivers/power/supply/ds2781_battery.c +++ b/drivers/power/supply/ds2781_battery.c @@ -623,7 +623,7 @@ static ssize_t ds2781_set_pio_pin(struct device *dev, static ssize_t ds2781_read_param_eeprom_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -636,7 +636,7 @@ static ssize_t ds2781_read_param_eeprom_bin(struct file *filp, static ssize_t ds2781_write_param_eeprom_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -656,19 +656,19 @@ static ssize_t ds2781_write_param_eeprom_bin(struct file *filp, return count; } -static struct bin_attribute ds2781_param_eeprom_bin_attr = { +static const struct bin_attribute ds2781_param_eeprom_bin_attr = { .attr = { .name = "param_eeprom", .mode = S_IRUGO | S_IWUSR, }, .size = DS2781_PARAM_EEPROM_SIZE, - .read = ds2781_read_param_eeprom_bin, - .write = ds2781_write_param_eeprom_bin, + .read_new = ds2781_read_param_eeprom_bin, + .write_new = ds2781_write_param_eeprom_bin, }; static ssize_t ds2781_read_user_eeprom_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -682,7 +682,7 @@ static ssize_t ds2781_read_user_eeprom_bin(struct file *filp, static ssize_t ds2781_write_user_eeprom_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -702,14 +702,14 @@ static ssize_t ds2781_write_user_eeprom_bin(struct file *filp, return count; } -static struct bin_attribute ds2781_user_eeprom_bin_attr = { +static const struct bin_attribute ds2781_user_eeprom_bin_attr = { .attr = { .name = "user_eeprom", .mode = S_IRUGO | S_IWUSR, }, .size = DS2781_USER_EEPROM_SIZE, - .read = ds2781_read_user_eeprom_bin, - .write = ds2781_write_user_eeprom_bin, + .read_new = ds2781_read_user_eeprom_bin, + .write_new = ds2781_write_user_eeprom_bin, }; static DEVICE_ATTR(pmod_enabled, S_IRUGO | S_IWUSR, ds2781_get_pmod_enabled, @@ -729,7 +729,7 @@ static struct attribute *ds2781_sysfs_attrs[] = { NULL }; -static struct bin_attribute *ds2781_sysfs_bin_attrs[] = { +static const struct bin_attribute *const ds2781_sysfs_bin_attrs[] = { &ds2781_param_eeprom_bin_attr, &ds2781_user_eeprom_bin_attr, NULL, @@ -737,7 +737,7 @@ static struct bin_attribute *ds2781_sysfs_bin_attrs[] = { static const struct attribute_group ds2781_sysfs_group = { .attrs = ds2781_sysfs_attrs, - .bin_attrs = ds2781_sysfs_bin_attrs, + .bin_attrs_new = ds2781_sysfs_bin_attrs, }; diff --git a/drivers/power/supply/ds2782_battery.c b/drivers/power/supply/ds2782_battery.c index 85aa9c465aa4..cae95d35d398 100644 --- a/drivers/power/supply/ds2782_battery.c +++ b/drivers/power/supply/ds2782_battery.c @@ -11,6 +11,7 @@ * UEvent sending added by Evgeny Romanov */ +#include #include #include #include @@ -57,14 +58,12 @@ struct ds278x_info { struct power_supply_desc battery_desc; const struct ds278x_battery_ops *ops; struct delayed_work bat_work; - int id; int rsns; int capacity; int status; /* State Of Charge */ }; -static DEFINE_IDR(battery_id); -static DEFINE_MUTEX(battery_lock); +static DEFINE_IDA(battery_id); static inline int ds278x_read_reg(struct ds278x_info *info, int reg, u8 *val) { @@ -312,21 +311,6 @@ static void ds278x_power_supply_init(struct power_supply_desc *battery) battery->external_power_changed = NULL; } -static void ds278x_battery_remove(struct i2c_client *client) -{ - struct ds278x_info *info = i2c_get_clientdata(client); - int id = info->id; - - power_supply_unregister(info->battery); - cancel_delayed_work_sync(&info->bat_work); - kfree(info->battery_desc.name); - kfree(info); - - mutex_lock(&battery_lock); - idr_remove(&battery_id, id); - mutex_unlock(&battery_lock); -} - #ifdef CONFIG_PM_SLEEP static int ds278x_suspend(struct device *dev) @@ -368,6 +352,13 @@ static const struct ds278x_battery_ops ds278x_ops[] = { } }; +static void ds278x_free_ida(void *data) +{ + int num = (uintptr_t)data; + + ida_free(&battery_id, num); +} + static int ds278x_battery_probe(struct i2c_client *client) { const struct i2c_device_id *id = i2c_client_get_device_id(client); @@ -387,32 +378,27 @@ static int ds278x_battery_probe(struct i2c_client *client) } /* Get an ID for this battery */ - mutex_lock(&battery_lock); - ret = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL); - mutex_unlock(&battery_lock); - if (ret < 0) - goto fail_id; - num = ret; + num = ida_alloc(&battery_id, GFP_KERNEL); + if (num < 0) + return num; + ret = devm_add_action_or_reset(&client->dev, ds278x_free_ida, (void *)(uintptr_t)num); + if (ret) + return ret; - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) { - ret = -ENOMEM; - goto fail_info; - } + info = devm_kzalloc(&client->dev, sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; - info->battery_desc.name = kasprintf(GFP_KERNEL, "%s-%d", - client->name, num); - if (!info->battery_desc.name) { - ret = -ENOMEM; - goto fail_name; - } + info->battery_desc.name = devm_kasprintf(&client->dev, GFP_KERNEL, + "%s-%d", client->name, num); + if (!info->battery_desc.name) + return -ENOMEM; if (id->driver_data == DS2786) info->rsns = pdata->rsns; i2c_set_clientdata(client, info); info->client = client; - info->id = num; info->ops = &ds278x_ops[id->driver_data]; ds278x_power_supply_init(&info->battery_desc); psy_cfg.drv_data = info; @@ -420,30 +406,20 @@ static int ds278x_battery_probe(struct i2c_client *client) info->capacity = 100; info->status = POWER_SUPPLY_STATUS_FULL; - INIT_DELAYED_WORK(&info->bat_work, ds278x_bat_work); - - info->battery = power_supply_register(&client->dev, - &info->battery_desc, &psy_cfg); + info->battery = devm_power_supply_register(&client->dev, + &info->battery_desc, + &psy_cfg); if (IS_ERR(info->battery)) { dev_err(&client->dev, "failed to register battery\n"); - ret = PTR_ERR(info->battery); - goto fail_register; - } else { - schedule_delayed_work(&info->bat_work, DS278x_DELAY); + return PTR_ERR(info->battery); } - return 0; + ret = devm_delayed_work_autocancel(&client->dev, &info->bat_work, ds278x_bat_work); + if (ret) + return ret; + schedule_delayed_work(&info->bat_work, DS278x_DELAY); -fail_register: - kfree(info->battery_desc.name); -fail_name: - kfree(info); -fail_info: - mutex_lock(&battery_lock); - idr_remove(&battery_id, num); - mutex_unlock(&battery_lock); -fail_id: - return ret; + return 0; } static const struct i2c_device_id ds278x_id[] = { @@ -459,7 +435,6 @@ static struct i2c_driver ds278x_battery_driver = { .pm = &ds278x_battery_pm_ops, }, .probe = ds278x_battery_probe, - .remove = ds278x_battery_remove, .id_table = ds278x_id, }; module_i2c_driver(ds278x_battery_driver); diff --git a/drivers/power/supply/gpio-charger.c b/drivers/power/supply/gpio-charger.c index 68212b39785b..46d18ce6a739 100644 --- a/drivers/power/supply/gpio-charger.c +++ b/drivers/power/supply/gpio-charger.c @@ -67,6 +67,14 @@ static int set_charge_current_limit(struct gpio_charger *gpio_charger, int val) if (gpio_charger->current_limit_map[i].limit_ua <= val) break; } + + /* + * If a valid charge current limit isn't found, default to smallest + * current limitation for safety reasons. + */ + if (i >= gpio_charger->current_limit_map_size) + i = gpio_charger->current_limit_map_size - 1; + mapping = gpio_charger->current_limit_map[i]; for (i = 0; i < ndescs; i++) { @@ -187,6 +195,8 @@ static int init_charge_current_limit(struct device *dev, { int i, len; u32 cur_limit = U32_MAX; + bool set_def_limit; + u32 def_limit; gpio_charger->current_limit_gpios = devm_gpiod_get_array_optional(dev, "charge-current-limit", GPIOD_OUT_LOW); @@ -220,6 +230,9 @@ static int init_charge_current_limit(struct device *dev, if (len < 0) return len; + set_def_limit = !device_property_read_u32(dev, + "charge-current-limit-default-microamp", + &def_limit); for (i=0; i < gpio_charger->current_limit_map_size; i++) { if (gpio_charger->current_limit_map[i].limit_ua > cur_limit) { dev_err(dev, "charge-current-limit-mapping not sorted by current in descending order\n"); @@ -227,8 +240,16 @@ static int init_charge_current_limit(struct device *dev, } cur_limit = gpio_charger->current_limit_map[i].limit_ua; + if (set_def_limit && def_limit == cur_limit) { + set_charge_current_limit(gpio_charger, cur_limit); + return 0; + } } + if (set_def_limit) + dev_warn(dev, "charge-current-limit-default-microamp %u not listed in charge-current-limit-mapping\n", + def_limit); + /* default to smallest current limitation for safety reasons */ len = gpio_charger->current_limit_map_size - 1; set_charge_current_limit(gpio_charger, diff --git a/drivers/power/supply/ip5xxx_power.c b/drivers/power/supply/ip5xxx_power.c index 82263646ddc6..c448e0ac0dfa 100644 --- a/drivers/power/supply/ip5xxx_power.c +++ b/drivers/power/supply/ip5xxx_power.c @@ -7,76 +7,154 @@ #include #include -#define IP5XXX_SYS_CTL0 0x01 -#define IP5XXX_SYS_CTL0_WLED_DET_EN BIT(4) -#define IP5XXX_SYS_CTL0_WLED_EN BIT(3) -#define IP5XXX_SYS_CTL0_BOOST_EN BIT(2) -#define IP5XXX_SYS_CTL0_CHARGER_EN BIT(1) -#define IP5XXX_SYS_CTL1 0x02 -#define IP5XXX_SYS_CTL1_LIGHT_SHDN_EN BIT(1) -#define IP5XXX_SYS_CTL1_LOAD_PWRUP_EN BIT(0) -#define IP5XXX_SYS_CTL2 0x0c -#define IP5XXX_SYS_CTL2_LIGHT_SHDN_TH GENMASK(7, 3) -#define IP5XXX_SYS_CTL3 0x03 -#define IP5XXX_SYS_CTL3_LONG_PRESS_TIME_SEL GENMASK(7, 6) -#define IP5XXX_SYS_CTL3_BTN_SHDN_EN BIT(5) -#define IP5XXX_SYS_CTL4 0x04 -#define IP5XXX_SYS_CTL4_SHDN_TIME_SEL GENMASK(7, 6) -#define IP5XXX_SYS_CTL4_VIN_PULLOUT_BOOST_EN BIT(5) -#define IP5XXX_SYS_CTL5 0x07 -#define IP5XXX_SYS_CTL5_NTC_DIS BIT(6) -#define IP5XXX_SYS_CTL5_WLED_MODE_SEL BIT(1) -#define IP5XXX_SYS_CTL5_BTN_SHDN_SEL BIT(0) -#define IP5XXX_CHG_CTL1 0x22 -#define IP5XXX_CHG_CTL1_BOOST_UVP_SEL GENMASK(3, 2) -#define IP5XXX_CHG_CTL2 0x24 -#define IP5XXX_CHG_CTL2_BAT_TYPE_SEL GENMASK(6, 5) -#define IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_2V (0x0 << 5) -#define IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_3V (0x1 << 5) -#define IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_35V (0x2 << 5) -#define IP5XXX_CHG_CTL2_CONST_VOLT_SEL GENMASK(2, 1) -#define IP5XXX_CHG_CTL4 0x26 -#define IP5XXX_CHG_CTL4_BAT_TYPE_SEL_EN BIT(6) -#define IP5XXX_CHG_CTL4A 0x25 -#define IP5XXX_CHG_CTL4A_CONST_CUR_SEL GENMASK(4, 0) -#define IP5XXX_MFP_CTL0 0x51 -#define IP5XXX_MFP_CTL1 0x52 -#define IP5XXX_GPIO_CTL2 0x53 -#define IP5XXX_GPIO_CTL2A 0x54 -#define IP5XXX_GPIO_CTL3 0x55 -#define IP5XXX_READ0 0x71 -#define IP5XXX_READ0_CHG_STAT GENMASK(7, 5) -#define IP5XXX_READ0_CHG_STAT_IDLE (0x0 << 5) -#define IP5XXX_READ0_CHG_STAT_TRICKLE (0x1 << 5) -#define IP5XXX_READ0_CHG_STAT_CONST_VOLT (0x2 << 5) -#define IP5XXX_READ0_CHG_STAT_CONST_CUR (0x3 << 5) -#define IP5XXX_READ0_CHG_STAT_CONST_VOLT_STOP (0x4 << 5) -#define IP5XXX_READ0_CHG_STAT_FULL (0x5 << 5) -#define IP5XXX_READ0_CHG_STAT_TIMEOUT (0x6 << 5) -#define IP5XXX_READ0_CHG_OP BIT(4) -#define IP5XXX_READ0_CHG_END BIT(3) -#define IP5XXX_READ0_CONST_VOLT_TIMEOUT BIT(2) -#define IP5XXX_READ0_CHG_TIMEOUT BIT(1) -#define IP5XXX_READ0_TRICKLE_TIMEOUT BIT(0) -#define IP5XXX_READ0_TIMEOUT GENMASK(2, 0) -#define IP5XXX_READ1 0x72 -#define IP5XXX_READ1_WLED_PRESENT BIT(7) -#define IP5XXX_READ1_LIGHT_LOAD BIT(6) -#define IP5XXX_READ1_VIN_OVERVOLT BIT(5) -#define IP5XXX_READ2 0x77 -#define IP5XXX_READ2_BTN_PRESS BIT(3) -#define IP5XXX_READ2_BTN_LONG_PRESS BIT(1) -#define IP5XXX_READ2_BTN_SHORT_PRESS BIT(0) -#define IP5XXX_BATVADC_DAT0 0xa2 -#define IP5XXX_BATVADC_DAT1 0xa3 -#define IP5XXX_BATIADC_DAT0 0xa4 -#define IP5XXX_BATIADC_DAT1 0xa5 -#define IP5XXX_BATOCV_DAT0 0xa8 -#define IP5XXX_BATOCV_DAT1 0xa9 +#define IP5XXX_BAT_TYPE_4_2V 0x0 +#define IP5XXX_BAT_TYPE_4_3V 0x1 +#define IP5XXX_BAT_TYPE_4_35V 0x2 +#define IP5XXX_BAT_TYPE_4_4V 0x3 +#define IP5XXX_CHG_STAT_IDLE 0x0 +#define IP5XXX_CHG_STAT_TRICKLE 0x1 +#define IP5XXX_CHG_STAT_CONST_VOLT 0x2 +#define IP5XXX_CHG_STAT_CONST_CUR 0x3 +#define IP5XXX_CHG_STAT_CONST_VOLT_STOP 0x4 +#define IP5XXX_CHG_STAT_FULL 0x5 +#define IP5XXX_CHG_STAT_TIMEOUT 0x6 struct ip5xxx { struct regmap *regmap; bool initialized; + struct { + struct { + /* Charger enable */ + struct regmap_field *enable; + /* Constant voltage value */ + struct regmap_field *const_volt_sel; + /* Constant current value */ + struct regmap_field *const_curr_sel; + /* Charger status */ + struct regmap_field *status; + /* Charging ended flag */ + struct regmap_field *chg_end; + /* Timeout flags (CV, charge, trickle) */ + struct regmap_field *timeout; + /* Overvoltage limit */ + struct regmap_field *vin_overvolt; + } charger; + struct { + /* Boost converter enable */ + struct regmap_field *enable; + struct { + /* Light load shutdown enable */ + struct regmap_field *enable; + /* Light load shutdown current limit */ + struct regmap_field *i_limit; + } light_load_shutdown; + /* Automatic powerup on increased load */ + struct regmap_field *load_powerup_en; + /* Automatic powerup on VIN pull-out */ + struct regmap_field *vin_pullout_en; + /* Undervoltage limit */ + struct regmap_field *undervolt_limit; + /* Light load status flag */ + struct regmap_field *light_load_status; + } boost; + struct { + /* NTC disable */ + struct regmap_field *ntc_dis; + /* Battery voltage type */ + struct regmap_field *type; + /* Battery voltage autoset from Vset pin */ + struct regmap_field *vset_en; + struct { + /* Battery measurement registers */ + struct ip5xxx_battery_adc_regs { + struct regmap_field *low; + struct regmap_field *high; + } volt, curr, open_volt; + } adc; + } battery; + struct { + /* Double/long press shutdown enable */ + struct regmap_field *shdn_enable; + /* WLED activation: double press or long press */ + struct regmap_field *wled_mode; + /* Shutdown activation: double press or long press */ + struct regmap_field *shdn_mode; + /* Long press time */ + struct regmap_field *long_press_time; + /* Button pressed */ + struct regmap_field *pressed; + /* Button long-pressed */ + struct regmap_field *long_pressed; + /* Button short-pressed */ + struct regmap_field *short_pressed; + } btn; + struct { + /* WLED enable */ + struct regmap_field *enable; + /* WLED detect */ + struct regmap_field *detect_en; + /* WLED present */ + struct regmap_field *present; + } wled; + } regs; + + /* Maximum supported battery voltage (via regs.battery.type) */ + int vbat_max; + /* Scaling constants for regs.boost.undervolt_limit */ + struct { + int setpoint; + int microvolts_per_bit; + } boost_undervolt; + /* Scaling constants for regs.charger.const_curr_sel */ + struct { + int setpoint; + } const_curr; + /* Whether regs.charger.chg_end is inverted */ + u8 chg_end_inverted; +}; + +#define REG_FIELD_UNSUPPORTED { .lsb = 1 } +/* Register fields layout. Unsupported registers marked as { .lsb = 1 } */ +struct ip5xxx_regfield_config { + const struct reg_field charger_enable; + const struct reg_field charger_const_volt_sel; + const struct reg_field charger_const_curr_sel; + const struct reg_field charger_status; + const struct reg_field charger_chg_end; + const struct reg_field charger_timeout; + const struct reg_field charger_vin_overvolt; + const struct reg_field boost_enable; + const struct reg_field boost_llshdn_enable; + const struct reg_field boost_llshdn_i_limit; + const struct reg_field boost_load_powerup_en; + const struct reg_field boost_vin_pullout_en; + const struct reg_field boost_undervolt_limit; + const struct reg_field boost_light_load_status; + const struct reg_field battery_ntc_dis; + const struct reg_field battery_type; + const struct reg_field battery_vset_en; + const struct reg_field battery_adc_volt_low; + const struct reg_field battery_adc_volt_high; + const struct reg_field battery_adc_curr_low; + const struct reg_field battery_adc_curr_high; + const struct reg_field battery_adc_ovolt_low; + const struct reg_field battery_adc_ovolt_high; + const struct reg_field btn_shdn_enable; + const struct reg_field btn_wled_mode; + const struct reg_field btn_shdn_mode; + const struct reg_field btn_long_press_time; + const struct reg_field btn_pressed; + const struct reg_field btn_long_pressed; + const struct reg_field btn_short_pressed; + const struct reg_field wled_enable; + const struct reg_field wled_detect_en; + const struct reg_field wled_present; + + int vbat_max; + int boost_undervolt_setpoint; + int boost_undervolt_uv_per_bit; + int const_curr_setpoint; + u8 chg_end_inverted; }; /* @@ -87,24 +165,30 @@ struct ip5xxx { * 2) Attempt the initialization sequence on each subsequent register access * until it succeeds. */ -static int ip5xxx_read(struct ip5xxx *ip5xxx, unsigned int reg, +static int ip5xxx_read(struct ip5xxx *ip5xxx, struct regmap_field *field, unsigned int *val) { int ret; - ret = regmap_read(ip5xxx->regmap, reg, val); + if (!field) + return -EOPNOTSUPP; + + ret = regmap_field_read(field, val); if (ret) ip5xxx->initialized = false; return ret; } -static int ip5xxx_update_bits(struct ip5xxx *ip5xxx, unsigned int reg, - unsigned int mask, unsigned int val) +static int ip5xxx_write(struct ip5xxx *ip5xxx, struct regmap_field *field, + unsigned int val) { int ret; - ret = regmap_update_bits(ip5xxx->regmap, reg, mask, val); + if (!field) + return -EOPNOTSUPP; + + ret = regmap_field_write(field, val); if (ret) ip5xxx->initialized = false; @@ -123,28 +207,26 @@ static int ip5xxx_initialize(struct power_supply *psy) * Disable shutdown under light load. * Enable power on when under load. */ - ret = ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL1, - IP5XXX_SYS_CTL1_LIGHT_SHDN_EN | - IP5XXX_SYS_CTL1_LOAD_PWRUP_EN, - IP5XXX_SYS_CTL1_LOAD_PWRUP_EN); + if (ip5xxx->regs.boost.light_load_shutdown.enable) { + ret = ip5xxx_write(ip5xxx, ip5xxx->regs.boost.light_load_shutdown.enable, 0); + if (ret) + return ret; + } + ret = ip5xxx_write(ip5xxx, ip5xxx->regs.boost.load_powerup_en, 1); if (ret) return ret; /* * Enable shutdown after a long button press (as configured below). */ - ret = ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL3, - IP5XXX_SYS_CTL3_BTN_SHDN_EN, - IP5XXX_SYS_CTL3_BTN_SHDN_EN); + ret = ip5xxx_write(ip5xxx, ip5xxx->regs.btn.shdn_enable, 1); if (ret) return ret; /* * Power on automatically when VIN is removed. */ - ret = ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL4, - IP5XXX_SYS_CTL4_VIN_PULLOUT_BOOST_EN, - IP5XXX_SYS_CTL4_VIN_PULLOUT_BOOST_EN); + ret = ip5xxx_write(ip5xxx, ip5xxx->regs.boost.vin_pullout_en, 1); if (ret) return ret; @@ -152,12 +234,15 @@ static int ip5xxx_initialize(struct power_supply *psy) * Enable the NTC. * Configure the button for two presses => LED, long press => shutdown. */ - ret = ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL5, - IP5XXX_SYS_CTL5_NTC_DIS | - IP5XXX_SYS_CTL5_WLED_MODE_SEL | - IP5XXX_SYS_CTL5_BTN_SHDN_SEL, - IP5XXX_SYS_CTL5_WLED_MODE_SEL | - IP5XXX_SYS_CTL5_BTN_SHDN_SEL); + if (ip5xxx->regs.battery.ntc_dis) { + ret = ip5xxx_write(ip5xxx, ip5xxx->regs.battery.ntc_dis, 0); + if (ret) + return ret; + } + ret = ip5xxx_write(ip5xxx, ip5xxx->regs.btn.wled_mode, 1); + if (ret) + return ret; + ret = ip5xxx_write(ip5xxx, ip5xxx->regs.btn.shdn_mode, 1); if (ret) return ret; @@ -186,24 +271,37 @@ static int ip5xxx_battery_get_status(struct ip5xxx *ip5xxx, int *val) unsigned int rval; int ret; - ret = ip5xxx_read(ip5xxx, IP5XXX_READ0, &rval); + if (!ip5xxx->regs.charger.status) { + // Fall-back to Charging Ended bit + ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.chg_end, &rval); + if (ret) + return ret; + + if (rval == ip5xxx->chg_end_inverted) + *val = POWER_SUPPLY_STATUS_CHARGING; + else + *val = POWER_SUPPLY_STATUS_NOT_CHARGING; + return 0; + } + + ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.status, &rval); if (ret) return ret; - switch (rval & IP5XXX_READ0_CHG_STAT) { - case IP5XXX_READ0_CHG_STAT_IDLE: + switch (rval) { + case IP5XXX_CHG_STAT_IDLE: *val = POWER_SUPPLY_STATUS_DISCHARGING; break; - case IP5XXX_READ0_CHG_STAT_TRICKLE: - case IP5XXX_READ0_CHG_STAT_CONST_CUR: - case IP5XXX_READ0_CHG_STAT_CONST_VOLT: + case IP5XXX_CHG_STAT_TRICKLE: + case IP5XXX_CHG_STAT_CONST_CUR: + case IP5XXX_CHG_STAT_CONST_VOLT: *val = POWER_SUPPLY_STATUS_CHARGING; break; - case IP5XXX_READ0_CHG_STAT_CONST_VOLT_STOP: - case IP5XXX_READ0_CHG_STAT_FULL: + case IP5XXX_CHG_STAT_CONST_VOLT_STOP: + case IP5XXX_CHG_STAT_FULL: *val = POWER_SUPPLY_STATUS_FULL; break; - case IP5XXX_READ0_CHG_STAT_TIMEOUT: + case IP5XXX_CHG_STAT_TIMEOUT: *val = POWER_SUPPLY_STATUS_NOT_CHARGING; break; default: @@ -218,22 +316,22 @@ static int ip5xxx_battery_get_charge_type(struct ip5xxx *ip5xxx, int *val) unsigned int rval; int ret; - ret = ip5xxx_read(ip5xxx, IP5XXX_READ0, &rval); + ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.status, &rval); if (ret) return ret; - switch (rval & IP5XXX_READ0_CHG_STAT) { - case IP5XXX_READ0_CHG_STAT_IDLE: - case IP5XXX_READ0_CHG_STAT_CONST_VOLT_STOP: - case IP5XXX_READ0_CHG_STAT_FULL: - case IP5XXX_READ0_CHG_STAT_TIMEOUT: + switch (rval) { + case IP5XXX_CHG_STAT_IDLE: + case IP5XXX_CHG_STAT_CONST_VOLT_STOP: + case IP5XXX_CHG_STAT_FULL: + case IP5XXX_CHG_STAT_TIMEOUT: *val = POWER_SUPPLY_CHARGE_TYPE_NONE; break; - case IP5XXX_READ0_CHG_STAT_TRICKLE: + case IP5XXX_CHG_STAT_TRICKLE: *val = POWER_SUPPLY_CHARGE_TYPE_TRICKLE; break; - case IP5XXX_READ0_CHG_STAT_CONST_CUR: - case IP5XXX_READ0_CHG_STAT_CONST_VOLT: + case IP5XXX_CHG_STAT_CONST_CUR: + case IP5XXX_CHG_STAT_CONST_VOLT: *val = POWER_SUPPLY_CHARGE_TYPE_STANDARD; break; default: @@ -248,11 +346,11 @@ static int ip5xxx_battery_get_health(struct ip5xxx *ip5xxx, int *val) unsigned int rval; int ret; - ret = ip5xxx_read(ip5xxx, IP5XXX_READ0, &rval); + ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.timeout, &rval); if (ret) return ret; - if (rval & IP5XXX_READ0_TIMEOUT) + if (rval) *val = POWER_SUPPLY_HEALTH_SAFETY_TIMER_EXPIRE; else *val = POWER_SUPPLY_HEALTH_GOOD; @@ -265,7 +363,7 @@ static int ip5xxx_battery_get_voltage_max(struct ip5xxx *ip5xxx, int *val) unsigned int rval; int ret; - ret = ip5xxx_read(ip5xxx, IP5XXX_CHG_CTL2, &rval); + ret = ip5xxx_read(ip5xxx, ip5xxx->regs.battery.type, &rval); if (ret) return ret; @@ -273,16 +371,19 @@ static int ip5xxx_battery_get_voltage_max(struct ip5xxx *ip5xxx, int *val) * It is not clear what this will return if * IP5XXX_CHG_CTL4_BAT_TYPE_SEL_EN is not set... */ - switch (rval & IP5XXX_CHG_CTL2_BAT_TYPE_SEL) { - case IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_2V: + switch (rval) { + case IP5XXX_BAT_TYPE_4_2V: *val = 4200000; break; - case IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_3V: + case IP5XXX_BAT_TYPE_4_3V: *val = 4300000; break; - case IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_35V: + case IP5XXX_BAT_TYPE_4_35V: *val = 4350000; break; + case IP5XXX_BAT_TYPE_4_4V: + *val = 4400000; + break; default: return -EINVAL; } @@ -291,16 +392,16 @@ static int ip5xxx_battery_get_voltage_max(struct ip5xxx *ip5xxx, int *val) } static int ip5xxx_battery_read_adc(struct ip5xxx *ip5xxx, - u8 lo_reg, u8 hi_reg, int *val) + struct ip5xxx_battery_adc_regs *regs, int *val) { unsigned int hi, lo; int ret; - ret = ip5xxx_read(ip5xxx, lo_reg, &lo); + ret = ip5xxx_read(ip5xxx, regs->low, &lo); if (ret) return ret; - ret = ip5xxx_read(ip5xxx, hi_reg, &hi); + ret = ip5xxx_read(ip5xxx, regs->high, &hi); if (ret) return ret; @@ -335,33 +436,35 @@ static int ip5xxx_battery_get_property(struct power_supply *psy, return ip5xxx_battery_get_voltage_max(ip5xxx, &val->intval); case POWER_SUPPLY_PROP_VOLTAGE_NOW: - ret = ip5xxx_battery_read_adc(ip5xxx, IP5XXX_BATVADC_DAT0, - IP5XXX_BATVADC_DAT1, &raw); + ret = ip5xxx_battery_read_adc(ip5xxx, &ip5xxx->regs.battery.adc.volt, &raw); + if (ret) + return ret; val->intval = 2600000 + DIV_ROUND_CLOSEST(raw * 26855, 100); return 0; case POWER_SUPPLY_PROP_VOLTAGE_OCV: - ret = ip5xxx_battery_read_adc(ip5xxx, IP5XXX_BATOCV_DAT0, - IP5XXX_BATOCV_DAT1, &raw); + ret = ip5xxx_battery_read_adc(ip5xxx, &ip5xxx->regs.battery.adc.open_volt, &raw); + if (ret) + return ret; val->intval = 2600000 + DIV_ROUND_CLOSEST(raw * 26855, 100); return 0; case POWER_SUPPLY_PROP_CURRENT_NOW: - ret = ip5xxx_battery_read_adc(ip5xxx, IP5XXX_BATIADC_DAT0, - IP5XXX_BATIADC_DAT1, &raw); + ret = ip5xxx_battery_read_adc(ip5xxx, &ip5xxx->regs.battery.adc.curr, &raw); + if (ret) + return ret; val->intval = DIV_ROUND_CLOSEST(raw * 149197, 200); return 0; case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT: - ret = ip5xxx_read(ip5xxx, IP5XXX_CHG_CTL4A, &rval); + ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.const_curr_sel, &rval); if (ret) return ret; - rval &= IP5XXX_CHG_CTL4A_CONST_CUR_SEL; - val->intval = 100000 * rval; + val->intval = ip5xxx->const_curr.setpoint + 100000 * rval; return 0; case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: @@ -373,12 +476,11 @@ static int ip5xxx_battery_get_property(struct power_supply *psy, if (ret) return ret; - ret = ip5xxx_read(ip5xxx, IP5XXX_CHG_CTL2, &rval); + ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.const_volt_sel, &rval); if (ret) return ret; - rval &= IP5XXX_CHG_CTL2_CONST_VOLT_SEL; - val->intval = vmax + 14000 * (rval >> 1); + val->intval = vmax + 14000 * rval; return 0; case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX: @@ -399,30 +501,36 @@ static int ip5xxx_battery_set_voltage_max(struct ip5xxx *ip5xxx, int val) unsigned int rval; int ret; + if (val > ip5xxx->vbat_max) + return -EINVAL; + switch (val) { case 4200000: - rval = IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_2V; + rval = IP5XXX_BAT_TYPE_4_2V; break; case 4300000: - rval = IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_3V; + rval = IP5XXX_BAT_TYPE_4_3V; break; case 4350000: - rval = IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_35V; + rval = IP5XXX_BAT_TYPE_4_35V; + break; + case 4400000: + rval = IP5XXX_BAT_TYPE_4_4V; break; default: return -EINVAL; } - ret = ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL2, - IP5XXX_CHG_CTL2_BAT_TYPE_SEL, rval); + ret = ip5xxx_write(ip5xxx, ip5xxx->regs.battery.type, rval); if (ret) return ret; - ret = ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL4, - IP5XXX_CHG_CTL4_BAT_TYPE_SEL_EN, - IP5XXX_CHG_CTL4_BAT_TYPE_SEL_EN); - if (ret) - return ret; + /* Don't try to auto-detect battery type, even if the IC could */ + if (ip5xxx->regs.battery.vset_en) { + ret = ip5xxx_write(ip5xxx, ip5xxx->regs.battery.vset_en, 1); + if (ret) + return ret; + } return 0; } @@ -443,7 +551,7 @@ static int ip5xxx_battery_set_property(struct power_supply *psy, case POWER_SUPPLY_PROP_STATUS: switch (val->intval) { case POWER_SUPPLY_STATUS_CHARGING: - rval = IP5XXX_SYS_CTL0_CHARGER_EN; + rval = 1; break; case POWER_SUPPLY_STATUS_DISCHARGING: case POWER_SUPPLY_STATUS_NOT_CHARGING: @@ -452,25 +560,22 @@ static int ip5xxx_battery_set_property(struct power_supply *psy, default: return -EINVAL; } - return ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL0, - IP5XXX_SYS_CTL0_CHARGER_EN, rval); + return ip5xxx_write(ip5xxx, ip5xxx->regs.charger.enable, rval); case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: return ip5xxx_battery_set_voltage_max(ip5xxx, val->intval); case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT: - rval = val->intval / 100000; - return ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL4A, - IP5XXX_CHG_CTL4A_CONST_CUR_SEL, rval); + rval = (val->intval - ip5xxx->const_curr.setpoint) / 100000; + return ip5xxx_write(ip5xxx, ip5xxx->regs.charger.const_curr_sel, rval); case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE: ret = ip5xxx_battery_get_voltage_max(ip5xxx, &vmax); if (ret) return ret; - rval = ((val->intval - vmax) / 14000) << 1; - return ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL2, - IP5XXX_CHG_CTL2_CONST_VOLT_SEL, rval); + rval = (val->intval - vmax) / 14000; + return ip5xxx_write(ip5xxx, ip5xxx->regs.charger.const_volt_sel, rval); default: return -EINVAL; @@ -515,20 +620,20 @@ static int ip5xxx_boost_get_property(struct power_supply *psy, switch (psp) { case POWER_SUPPLY_PROP_ONLINE: - ret = ip5xxx_read(ip5xxx, IP5XXX_SYS_CTL0, &rval); + ret = ip5xxx_read(ip5xxx, ip5xxx->regs.boost.enable, &rval); if (ret) return ret; - val->intval = !!(rval & IP5XXX_SYS_CTL0_BOOST_EN); + val->intval = !!rval; return 0; case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: - ret = ip5xxx_read(ip5xxx, IP5XXX_CHG_CTL1, &rval); + ret = ip5xxx_read(ip5xxx, ip5xxx->regs.boost.undervolt_limit, &rval); if (ret) return ret; - rval &= IP5XXX_CHG_CTL1_BOOST_UVP_SEL; - val->intval = 4530000 + 100000 * (rval >> 2); + val->intval = ip5xxx->boost_undervolt.setpoint + + ip5xxx->boost_undervolt.microvolts_per_bit * rval; return 0; default: @@ -550,14 +655,12 @@ static int ip5xxx_boost_set_property(struct power_supply *psy, switch (psp) { case POWER_SUPPLY_PROP_ONLINE: - rval = val->intval ? IP5XXX_SYS_CTL0_BOOST_EN : 0; - return ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL0, - IP5XXX_SYS_CTL0_BOOST_EN, rval); + return ip5xxx_write(ip5xxx, ip5xxx->regs.boost.enable, !!val->intval); case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: - rval = ((val->intval - 4530000) / 100000) << 2; - return ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL1, - IP5XXX_CHG_CTL1_BOOST_UVP_SEL, rval); + rval = (val->intval - ip5xxx->boost_undervolt.setpoint) / + ip5xxx->boost_undervolt.microvolts_per_bit; + return ip5xxx_write(ip5xxx, ip5xxx->regs.boost.undervolt_limit, rval); default: return -EINVAL; @@ -583,13 +686,152 @@ static const struct power_supply_desc ip5xxx_boost_desc = { static const struct regmap_config ip5xxx_regmap_config = { .reg_bits = 8, .val_bits = 8, - .max_register = IP5XXX_BATOCV_DAT1, + .max_register = 0xa9, }; +static struct ip5xxx_regfield_config ip51xx_fields = { + .charger_enable = REG_FIELD(0x01, 1, 1), + .charger_const_volt_sel = REG_FIELD(0x24, 1, 2), + .charger_const_curr_sel = REG_FIELD(0x25, 0, 4), + .charger_status = REG_FIELD(0x71, 5, 7), + .charger_chg_end = REG_FIELD(0x71, 3, 3), + .charger_timeout = REG_FIELD(0x71, 0, 2), + .charger_vin_overvolt = REG_FIELD(0x72, 5, 5), + .boost_enable = REG_FIELD(0x01, 2, 2), + .boost_llshdn_enable = REG_FIELD(0x02, 1, 1), + .boost_llshdn_i_limit = REG_FIELD(0x0c, 3, 7), + .boost_load_powerup_en = REG_FIELD(0x02, 0, 0), + .boost_vin_pullout_en = REG_FIELD(0x04, 5, 5), + .boost_undervolt_limit = REG_FIELD(0x22, 2, 3), + .boost_light_load_status = REG_FIELD(0x72, 6, 6), + .battery_ntc_dis = REG_FIELD(0x07, 6, 6), + .battery_type = REG_FIELD(0x24, 5, 6), + .battery_vset_en = REG_FIELD(0x26, 6, 6), + .battery_adc_volt_low = REG_FIELD(0xa2, 0, 7), + .battery_adc_volt_high = REG_FIELD(0xa3, 0, 5), + .battery_adc_curr_low = REG_FIELD(0xa4, 0, 7), + .battery_adc_curr_high = REG_FIELD(0xa5, 0, 5), + .battery_adc_ovolt_low = REG_FIELD(0xa8, 0, 7), + .battery_adc_ovolt_high = REG_FIELD(0xa9, 0, 5), + .btn_shdn_enable = REG_FIELD(0x03, 5, 5), + .btn_wled_mode = REG_FIELD(0x07, 1, 1), + .btn_shdn_mode = REG_FIELD(0x07, 0, 0), + .btn_long_press_time = REG_FIELD(0x03, 6, 7), + .btn_pressed = REG_FIELD(0x77, 3, 3), + .btn_long_pressed = REG_FIELD(0x77, 1, 1), + .btn_short_pressed = REG_FIELD(0x77, 0, 0), + .wled_enable = REG_FIELD(0x01, 3, 3), + .wled_detect_en = REG_FIELD(0x01, 4, 4), + .wled_present = REG_FIELD(0x72, 7, 7), + + .vbat_max = 4350000, + .boost_undervolt_setpoint = 4530000, + .boost_undervolt_uv_per_bit = 100000, +}; + +static struct ip5xxx_regfield_config ip5306_fields = { + .charger_enable = REG_FIELD(0x00, 4, 4), + .charger_const_volt_sel = REG_FIELD(0x22, 0, 1), + .charger_const_curr_sel = REG_FIELD(0x24, 0, 4), + .charger_status = REG_FIELD_UNSUPPORTED, // other bits... + .charger_chg_end = REG_FIELD(0x71, 3, 3), + .charger_timeout = REG_FIELD_UNSUPPORTED, + .charger_vin_overvolt = REG_FIELD_UNSUPPORTED, + .boost_enable = REG_FIELD(0x00, 5, 5), + .boost_llshdn_enable = REG_FIELD_UNSUPPORTED, + .boost_llshdn_i_limit = REG_FIELD_UNSUPPORTED, + .boost_load_powerup_en = REG_FIELD(0x00, 2, 2), + .boost_vin_pullout_en = REG_FIELD(0x01, 2, 2), + .boost_undervolt_limit = REG_FIELD(0x21, 2, 4), + .boost_light_load_status = REG_FIELD(0x72, 2, 2), + .battery_ntc_dis = REG_FIELD_UNSUPPORTED, + .battery_type = REG_FIELD(0x22, 2, 3), + .battery_vset_en = REG_FIELD_UNSUPPORTED, + .battery_adc_volt_low = REG_FIELD_UNSUPPORTED, + .battery_adc_volt_high = REG_FIELD_UNSUPPORTED, + .battery_adc_curr_low = REG_FIELD_UNSUPPORTED, + .battery_adc_curr_high = REG_FIELD_UNSUPPORTED, + .battery_adc_ovolt_low = REG_FIELD_UNSUPPORTED, + .battery_adc_ovolt_high = REG_FIELD_UNSUPPORTED, + .btn_shdn_enable = REG_FIELD(0x00, 0, 0), + .btn_wled_mode = REG_FIELD(0x01, 6, 6), + .btn_shdn_mode = REG_FIELD(0x01, 7, 7), + .btn_long_press_time = REG_FIELD(0x02, 4, 4), // +1s + .btn_pressed = REG_FIELD_UNSUPPORTED, + /* TODO: double press */ + .btn_long_pressed = REG_FIELD(0x77, 1, 1), + .btn_short_pressed = REG_FIELD(0x77, 0, 0), + .wled_enable = REG_FIELD_UNSUPPORTED, + .wled_detect_en = REG_FIELD_UNSUPPORTED, + .wled_present = REG_FIELD_UNSUPPORTED, + + .vbat_max = 4400000, + .boost_undervolt_setpoint = 4450000, + .boost_undervolt_uv_per_bit = 50000, + .const_curr_setpoint = 50000, + .chg_end_inverted = 1, +}; + +#define ip5xxx_setup_reg(_field, _reg) \ + do { \ + if (likely(cfg->_field.lsb <= cfg->_field.msb)) { \ + struct regmap_field *_tmp = devm_regmap_field_alloc(dev, \ + ip5xxx->regmap, cfg->_field); \ + if (!IS_ERR(_tmp)) \ + ip5xxx->regs._reg = _tmp; \ + } \ + } while (0) + +static void ip5xxx_setup_regs(struct device *dev, struct ip5xxx *ip5xxx, + const struct ip5xxx_regfield_config *cfg) +{ + ip5xxx_setup_reg(charger_enable, charger.enable); + ip5xxx_setup_reg(charger_const_volt_sel, charger.const_volt_sel); + ip5xxx_setup_reg(charger_const_curr_sel, charger.const_curr_sel); + ip5xxx_setup_reg(charger_status, charger.status); + ip5xxx_setup_reg(charger_chg_end, charger.chg_end); + ip5xxx_setup_reg(charger_timeout, charger.timeout); + ip5xxx_setup_reg(charger_vin_overvolt, charger.vin_overvolt); + ip5xxx_setup_reg(boost_enable, boost.enable); + ip5xxx_setup_reg(boost_llshdn_enable, boost.light_load_shutdown.enable); + ip5xxx_setup_reg(boost_llshdn_i_limit, boost.light_load_shutdown.i_limit); + ip5xxx_setup_reg(boost_load_powerup_en, boost.load_powerup_en); + ip5xxx_setup_reg(boost_vin_pullout_en, boost.vin_pullout_en); + ip5xxx_setup_reg(boost_undervolt_limit, boost.undervolt_limit); + ip5xxx_setup_reg(boost_light_load_status, boost.light_load_status); + ip5xxx_setup_reg(battery_ntc_dis, battery.ntc_dis); + ip5xxx_setup_reg(battery_type, battery.type); + ip5xxx_setup_reg(battery_vset_en, battery.vset_en); + ip5xxx_setup_reg(battery_adc_volt_low, battery.adc.volt.low); + ip5xxx_setup_reg(battery_adc_volt_high, battery.adc.volt.high); + ip5xxx_setup_reg(battery_adc_curr_low, battery.adc.curr.low); + ip5xxx_setup_reg(battery_adc_curr_high, battery.adc.curr.high); + ip5xxx_setup_reg(battery_adc_ovolt_low, battery.adc.open_volt.low); + ip5xxx_setup_reg(battery_adc_ovolt_high, battery.adc.open_volt.high); + ip5xxx_setup_reg(btn_shdn_enable, btn.shdn_enable); + ip5xxx_setup_reg(btn_wled_mode, btn.wled_mode); + ip5xxx_setup_reg(btn_shdn_mode, btn.shdn_mode); + ip5xxx_setup_reg(btn_long_press_time, btn.long_press_time); + ip5xxx_setup_reg(btn_pressed, btn.pressed); + ip5xxx_setup_reg(btn_long_pressed, btn.long_pressed); + ip5xxx_setup_reg(btn_short_pressed, btn.short_pressed); + ip5xxx_setup_reg(wled_enable, wled.enable); + ip5xxx_setup_reg(wled_detect_en, wled.detect_en); + ip5xxx_setup_reg(wled_present, wled.present); + + ip5xxx->vbat_max = cfg->vbat_max; + ip5xxx->boost_undervolt.setpoint = cfg->boost_undervolt_setpoint; + ip5xxx->boost_undervolt.microvolts_per_bit = cfg->boost_undervolt_uv_per_bit; + ip5xxx->const_curr.setpoint = cfg->const_curr_setpoint; + ip5xxx->chg_end_inverted = cfg->chg_end_inverted; +} + static int ip5xxx_power_probe(struct i2c_client *client) { + const struct ip5xxx_regfield_config *fields = &ip51xx_fields; struct power_supply_config psy_cfg = {}; struct device *dev = &client->dev; + const struct of_device_id *of_id; struct power_supply *psy; struct ip5xxx *ip5xxx; @@ -601,6 +843,11 @@ static int ip5xxx_power_probe(struct i2c_client *client) if (IS_ERR(ip5xxx->regmap)) return PTR_ERR(ip5xxx->regmap); + of_id = i2c_of_match_device(dev->driver->of_match_table, client); + if (of_id) + fields = (const struct ip5xxx_regfield_config *)of_id->data; + ip5xxx_setup_regs(dev, ip5xxx, fields); + psy_cfg.of_node = dev->of_node; psy_cfg.drv_data = ip5xxx; @@ -616,10 +863,11 @@ static int ip5xxx_power_probe(struct i2c_client *client) } static const struct of_device_id ip5xxx_power_of_match[] = { - { .compatible = "injoinic,ip5108" }, - { .compatible = "injoinic,ip5109" }, - { .compatible = "injoinic,ip5207" }, - { .compatible = "injoinic,ip5209" }, + { .compatible = "injoinic,ip5108", .data = &ip51xx_fields }, + { .compatible = "injoinic,ip5109", .data = &ip51xx_fields }, + { .compatible = "injoinic,ip5207", .data = &ip51xx_fields }, + { .compatible = "injoinic,ip5209", .data = &ip51xx_fields }, + { .compatible = "injoinic,ip5306", .data = &ip5306_fields }, { } }; MODULE_DEVICE_TABLE(of, ip5xxx_power_of_match); diff --git a/drivers/power/supply/ltc4162-l-charger.c b/drivers/power/supply/ltc4162-l-charger.c index 2e4bc74e1c4a..23eb426295db 100644 --- a/drivers/power/supply/ltc4162-l-charger.c +++ b/drivers/power/supply/ltc4162-l-charger.c @@ -1,9 +1,14 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Driver for Analog Devices (Linear Technology) LTC4162-L charger IC. + * Driver for Analog Devices (Linear Technology) + * LTC4162-L 35V/3.2A Multi-Cell Lithium-Ion Step-Down Battery Charger + * LTC4162-F 35V/3.2A Multi-Cell LiFePO4 Step-Down Battery Charger + * LTC4162-S 35V/3.2A Lead-Acid Step-Down Battery Charger + * LTC4015 35V/3.2A Multichemistry Buck Battery Charger Controller * Copyright (C) 2020, Topic Embedded Products */ +#include #include #include #include @@ -47,6 +52,20 @@ #define LTC4162L_VBAT_FILT 0x47 #define LTC4162L_INPUT_UNDERVOLTAGE_DAC 0x4B +#define LTC4162L_CHEM_MASK GENMASK(11, 8) + +enum ltc4162_chem { + ltc4162_lad, + ltc4162_l42, + ltc4162_l41, + ltc4162_l40, + ltc4162_fad, + ltc4162_ffs, + ltc4162_fst, + ltc4162_sst = 8, + ltc4162_sad, +}; + /* Enumeration as in datasheet. Individual bits are mutually exclusive. */ enum ltc4162l_state { battery_detection = 2048, @@ -75,10 +94,28 @@ enum ltc4162l_charge_status { /* Magic number to write to ARM_SHIP_MODE register */ #define LTC4162L_ARM_SHIP_MODE_MAGIC 21325 +struct ltc4162l_info; + +struct ltc4162l_chip_info { + const char *name; + int (*get_vbat)(struct ltc4162l_info *info, unsigned int reg, + union power_supply_propval *val); + int (*get_vcharge)(struct ltc4162l_info *info, unsigned int reg, + union power_supply_propval *val); + int (*set_vcharge)(struct ltc4162l_info *info, unsigned int reg, + unsigned int value); + int (*get_die_temp)(struct ltc4162l_info *info, + union power_supply_propval *val); + unsigned int ibat_resolution_pv; + unsigned int vin_resolution_uv; + u8 telemetry_mask; +}; + struct ltc4162l_info { struct i2c_client *client; struct regmap *regmap; struct power_supply *charger; + const struct ltc4162l_chip_info *chip_info; u32 rsnsb; /* Series resistor that sets charge current, microOhm */ u32 rsnsi; /* Series resistor to measure input current, microOhm */ u8 cell_count; /* Number of connected cells, 0 while unknown */ @@ -108,6 +145,18 @@ static u8 ltc4162l_get_cell_count(struct ltc4162l_info *info) return val; }; +static u8 ltc4162l_get_chem_type(struct ltc4162l_info *info) +{ + int ret; + unsigned int val; + + ret = regmap_read(info->regmap, LTC4162L_CHEM_CELLS_REG, &val); + if (ret) + return ret; + + return FIELD_GET(LTC4162L_CHEM_MASK, val); +}; + /* Convert enum value to POWER_SUPPLY_STATUS value */ static int ltc4162l_state_decode(enum ltc4162l_state value) { @@ -223,25 +272,83 @@ static int ltc4162l_get_vbat(struct ltc4162l_info *info, unsigned int reg, union power_supply_propval *val) { - unsigned int regval; + unsigned int regval, chem_type; int ret; ret = regmap_read(info->regmap, reg, ®val); if (ret) return ret; - /* cell_count × 192.4μV/LSB */ - regval *= 1924; - regval *= ltc4162l_get_cell_count(info); - regval /= 10; - val->intval = regval; + /* + * cell_count × scaling factor + * For ltc4162-s, it uses a cell_count value of 2 for each group of 3 + * physical (2V) cells, thus will return 2, 4, 6, 8 for 6V, 12V, 18V, + * and 24V respectively, and has to divide by 2 to multiply the scale + * factor by 1, 2, 3, or 4 to represent a 6V, 12V, 18V, or 24V battery + * respectively. + */ + chem_type = ltc4162l_get_chem_type(info); + switch (chem_type) { + case ltc4162_lad ... ltc4162_fst: + regval *= 1924; + regval *= ltc4162l_get_cell_count(info); + regval /= 10; + val->intval = regval; - return 0; + return 0; + case ltc4162_sst ... ltc4162_sad: + regval *= 3848; + regval *= ltc4162l_get_cell_count(info) / 2; + regval /= 10; + val->intval = regval; + + return 0; + default: + return -EINVAL; + } +} + +static int ltc4015_get_vbat(struct ltc4162l_info *info, + unsigned int reg, + union power_supply_propval *val) +{ + unsigned int regval, chem_type; + int ret; + + ret = regmap_read(info->regmap, reg, ®val); + if (ret) + return ret; + + /* + * cell count x scaling factor + * ltc4015 lead-acid fixed and lead-acid programmable corresponds to + * 0x7 and 0x8 chem respectively + */ + chem_type = ltc4162l_get_chem_type(info); + switch (chem_type) { + case ltc4162_lad ... ltc4162_fst: + regval *= 192264; + regval *= ltc4162l_get_cell_count(info); + regval /= 1000; + val->intval = regval; + + return 0; + case ltc4162_sst - 1 ... ltc4162_sad - 1: + regval *= 128176; + regval *= ltc4162l_get_cell_count(info); + regval /= 1000; + val->intval = regval; + + return 0; + default: + return -EINVAL; + } } static int ltc4162l_get_ibat(struct ltc4162l_info *info, union power_supply_propval *val) { + const struct ltc4162l_chip_info *chip_info = info->chip_info; unsigned int regval; int ret; @@ -249,9 +356,8 @@ static int ltc4162l_get_ibat(struct ltc4162l_info *info, if (ret) return ret; - /* Signed 16-bit number, 1.466μV / RSNSB amperes/LSB. */ ret = (s16)(regval & 0xFFFF); - val->intval = 100 * mult_frac(ret, 14660, (int)info->rsnsb); + val->intval = mult_frac(ret, chip_info->ibat_resolution_pv, info->rsnsb); return 0; } @@ -260,6 +366,7 @@ static int ltc4162l_get_ibat(struct ltc4162l_info *info, static int ltc4162l_get_input_voltage(struct ltc4162l_info *info, union power_supply_propval *val) { + const struct ltc4162l_chip_info *chip_info = info->chip_info; unsigned int regval; int ret; @@ -267,8 +374,7 @@ static int ltc4162l_get_input_voltage(struct ltc4162l_info *info, if (ret) return ret; - /* 1.649mV/LSB */ - val->intval = regval * 1694; + val->intval = regval * chip_info->vin_resolution_uv; return 0; } @@ -276,6 +382,7 @@ static int ltc4162l_get_input_voltage(struct ltc4162l_info *info, static int ltc4162l_get_input_current(struct ltc4162l_info *info, union power_supply_propval *val) { + const struct ltc4162l_chip_info *chip_info = info->chip_info; unsigned int regval; int ret; @@ -283,11 +390,9 @@ static int ltc4162l_get_input_current(struct ltc4162l_info *info, if (ret) return ret; - /* Signed 16-bit number, 1.466μV / RSNSI amperes/LSB. */ ret = (s16)(regval & 0xFFFF); - ret *= 14660; + ret *= chip_info->ibat_resolution_pv; ret /= info->rsnsi; - ret *= 100; val->intval = ret; @@ -305,7 +410,7 @@ static int ltc4162l_get_icharge(struct ltc4162l_info *info, if (ret) return ret; - regval &= BIT(6) - 1; /* Only the lower 5 bits */ + regval &= GENMASK(5, 0); /* The charge current servo level: (icharge_dac + 1) × 1mV/RSNSB */ ++regval; @@ -336,7 +441,7 @@ static int ltc4162l_get_vcharge(struct ltc4162l_info *info, unsigned int reg, union power_supply_propval *val) { - unsigned int regval; + unsigned int regval, chem_type; int ret; u32 voltage; @@ -344,41 +449,181 @@ static int ltc4162l_get_vcharge(struct ltc4162l_info *info, if (ret) return ret; - regval &= BIT(6) - 1; /* Only the lower 5 bits */ + regval &= GENMASK(5, 0); /* * charge voltage setting can be computed from - * cell_count × (vcharge_setting × 12.5mV + 3.8125V) - * where vcharge_setting ranges from 0 to 31 (4.2V max). + * cell_count × (vcharge_setting × a + b) + * where vcharge_setting ranges from 0 to c (d). + * for ltc4162l: a = 12.5mV , b = 3.8125V, c = 31, d = 4.2Vmax + * for ltc4162f: a = 12.5mV , b = 3.4125V, c = 31, d = 3.8Vmax + * + * for ltc4162s, the charge voltage setting can be computed from + * N x (vcharge_setting x 28.571mV + 6.0V) + * where N is 1, 2, 3, or 4 for 6V, 12V, 18V, or 24V battery respectively, + * and vcharge_setting ranges from 0 to 31 */ - voltage = 3812500 + (regval * 12500); - voltage *= ltc4162l_get_cell_count(info); - val->intval = voltage; + chem_type = ltc4162l_get_chem_type(info); + switch (chem_type) { + case ltc4162_lad ... ltc4162_l40: + voltage = 3812500 + (regval * 12500); + voltage *= ltc4162l_get_cell_count(info); + val->intval = voltage; - return 0; + return 0; + case ltc4162_fad ... ltc4162_fst: + voltage = 3412500 + (regval * 12500); + voltage *= ltc4162l_get_cell_count(info); + val->intval = voltage; + + return 0; + case ltc4162_sst ... ltc4162_sad: + voltage = 6000000 + (regval * 28571); + voltage *= ltc4162l_get_cell_count(info) / 2; + val->intval = voltage; + + return 0; + default: + return -EINVAL; + } +} + +static int ltc4015_get_vcharge(struct ltc4162l_info *info, + unsigned int reg, + union power_supply_propval *val) +{ + unsigned int regval, chem_type; + int ret; + u32 voltage; + + ret = regmap_read(info->regmap, reg, ®val); + if (ret) + return ret; + + regval &= GENMASK(5, 0); + + /* + * charge voltage setting can be computed from: + * cell_count × (vcharge_setting × a + b) + * where vcharge_setting ranges from 0 to c (d). + * Li-Ion: a = 1/80V, b = 3.8125V, c = 31, d = 4.2Vmax + * LiFePO4: a = 1/80V, b = 3.4125V, c = 31, d = 3.8Vmax + * Lead Acid: a = 1/105V, b = 2V, c = 35, d = 2.6Vmax + */ + chem_type = ltc4162l_get_chem_type(info); + switch (chem_type) { + case ltc4162_lad ... ltc4162_l40: + voltage = 3812500 + (regval * 12500); + voltage *= ltc4162l_get_cell_count(info); + val->intval = voltage; + + return 0; + case ltc4162_fad ... ltc4162_fst: + voltage = 3412500 + (regval * 12500); + voltage *= ltc4162l_get_cell_count(info); + val->intval = voltage; + + return 0; + case ltc4162_sst - 1 ... ltc4162_sad - 1: + voltage = 2000000 + mult_frac(regval, 1000000, 105); + voltage *= ltc4162l_get_cell_count(info); + val->intval = voltage; + + return 0; + default: + return -EINVAL; + } +} + +static int ltc4162l_vcharge(unsigned int base_voltage, + unsigned int scale_factor, + unsigned int range, + unsigned int value, + u8 cell_count) +{ + value /= cell_count; + + if (value < base_voltage) + return -EINVAL; + + value -= base_voltage; + value /= scale_factor; + + if (value > range) + return -EINVAL; + + return value; } static int ltc4162l_set_vcharge(struct ltc4162l_info *info, unsigned int reg, unsigned int value) { - u8 cell_count = ltc4162l_get_cell_count(info); + unsigned int chem_type; + u8 cell_count; - if (!cell_count) - return -EBUSY; /* Not available yet, try again later */ + chem_type = ltc4162l_get_chem_type(info); + switch (chem_type) { + case ltc4162_lad ... ltc4162_l40: + cell_count = ltc4162l_get_cell_count(info); + if (!cell_count) + return -EBUSY; - value /= cell_count; + value = ltc4162l_vcharge(3812500, 12500, 31, value, cell_count); + return regmap_write(info->regmap, reg, value); + case ltc4162_fad ... ltc4162_fst: + cell_count = ltc4162l_get_cell_count(info); + if (!cell_count) + return -EBUSY; - if (value < 3812500) + value = ltc4162l_vcharge(3412500, 12500, 31, value, cell_count); + return regmap_write(info->regmap, reg, value); + case ltc4162_sst ... ltc4162_sad: + cell_count = ltc4162l_get_cell_count(info) / 2; + if (!cell_count) + return -EBUSY; + + value = ltc4162l_vcharge(6000000, 28571, 31, value, cell_count); + return regmap_write(info->regmap, reg, value); + default: return -EINVAL; + } +} - value -= 3812500; - value /= 12500; +static int ltc4015_set_vcharge(struct ltc4162l_info *info, + unsigned int reg, + unsigned int value) +{ + unsigned int chem_type; + u8 cell_count; - if (value > 31) + chem_type = ltc4162l_get_chem_type(info); + switch (chem_type) { + case ltc4162_lad ... ltc4162_l40: + cell_count = ltc4162l_get_cell_count(info); + if (!cell_count) + return -EBUSY; + + value = ltc4162l_vcharge(3812500, 12500, 31, value, cell_count); + return regmap_write(info->regmap, reg, value); + case ltc4162_fad ... ltc4162_fst: + cell_count = ltc4162l_get_cell_count(info); + if (!cell_count) + return -EBUSY; + + value = ltc4162l_vcharge(3412500, 12500, 31, value, cell_count); + return regmap_write(info->regmap, reg, value); + case ltc4162_sst - 1 ... ltc4162_sad - 1: + cell_count = ltc4162l_get_cell_count(info); + if (!cell_count) + return -EBUSY; + + value = ltc4162l_vcharge(2000000, 1000000 / 105, 35, + value, cell_count); + return regmap_write(info->regmap, reg, value); + default: return -EINVAL; - - return regmap_write(info->regmap, reg, value); + } } static int ltc4162l_get_iin_limit_dac(struct ltc4162l_info *info, @@ -391,7 +636,7 @@ static int ltc4162l_get_iin_limit_dac(struct ltc4162l_info *info, if (ret) return ret; - regval &= BIT(6) - 1; /* Only 6 bits */ + regval &= GENMASK(5, 0); /* (iin_limit_dac + 1) × 500μV / RSNSI */ ++regval; @@ -437,9 +682,30 @@ static int ltc4162l_get_die_temp(struct ltc4162l_info *info, return 0; } +static int ltc4015_get_die_temp(struct ltc4162l_info *info, + union power_supply_propval *val) +{ + unsigned int regval; + int ret; + + ret = regmap_read(info->regmap, LTC4162L_DIE_TEMPERATURE, ®val); + if (ret) + return ret; + + /* (die_temp - 12010) / 45.6°C */ + ret = (s16)(regval & 0xFFFF); + ret -= 12010; + ret *= 1000; + ret /= 456; + val->intval = ret; + + return 0; +} + static int ltc4162l_get_term_current(struct ltc4162l_info *info, union power_supply_propval *val) { + const struct ltc4162l_chip_info *chip_info = info->chip_info; unsigned int regval; int ret; @@ -457,10 +723,9 @@ static int ltc4162l_get_term_current(struct ltc4162l_info *info, if (ret) return ret; - /* 1.466μV / RSNSB amperes/LSB */ - regval *= 14660u; + regval *= chip_info->ibat_resolution_pv; regval /= info->rsnsb; - val->intval = 100 * regval; + val->intval = regval; return 0; } @@ -534,10 +799,11 @@ static ssize_t vbat_show(struct device *dev, { struct power_supply *psy = to_power_supply(dev); struct ltc4162l_info *info = power_supply_get_drvdata(psy); + const struct ltc4162l_chip_info *chip_info = info->chip_info; union power_supply_propval val; int ret; - ret = ltc4162l_get_vbat(info, LTC4162L_VBAT, &val); + ret = chip_info->get_vbat(info, LTC4162L_VBAT, &val); if (ret) return ret; @@ -550,10 +816,11 @@ static ssize_t vbat_avg_show(struct device *dev, { struct power_supply *psy = to_power_supply(dev); struct ltc4162l_info *info = power_supply_get_drvdata(psy); + const struct ltc4162l_chip_info *chip_info = info->chip_info; union power_supply_propval val; int ret; - ret = ltc4162l_get_vbat(info, LTC4162L_VBAT_FILT, &val); + ret = chip_info->get_vbat(info, LTC4162L_VBAT_FILT, &val); if (ret) return ret; @@ -589,7 +856,8 @@ static ssize_t force_telemetry_show(struct device *dev, if (ret) return ret; - return sysfs_emit(buf, "%u\n", regval & BIT(2) ? 1 : 0); + return sysfs_emit(buf, "%u\n", regval & + info->chip_info->telemetry_mask ? 1 : 0); } static ssize_t force_telemetry_store(struct device *dev, @@ -607,7 +875,8 @@ static ssize_t force_telemetry_store(struct device *dev, return ret; ret = regmap_update_bits(info->regmap, LTC4162L_CONFIG_BITS_REG, - BIT(2), value ? BIT(2) : 0); + info->chip_info->telemetry_mask, + value ? info->chip_info->telemetry_mask : 0); if (ret < 0) return ret; @@ -681,6 +950,7 @@ static int ltc4162l_get_property(struct power_supply *psy, union power_supply_propval *val) { struct ltc4162l_info *info = power_supply_get_drvdata(psy); + const struct ltc4162l_chip_info *chip_info = info->chip_info; switch (psp) { case POWER_SUPPLY_PROP_STATUS: @@ -702,15 +972,13 @@ static int ltc4162l_get_property(struct power_supply *psy, return ltc4162l_get_icharge(info, LTC4162L_CHARGE_CURRENT_SETTING, val); case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE: - return ltc4162l_get_vcharge(info, - LTC4162L_VCHARGE_DAC, val); + return chip_info->get_vcharge(info, LTC4162L_VCHARGE_DAC, val); case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX: - return ltc4162l_get_vcharge(info, - LTC4162L_VCHARGE_SETTING, val); + return chip_info->get_vcharge(info, LTC4162L_VCHARGE_SETTING, val); case POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT: return ltc4162l_get_iin_limit_dac(info, val); case POWER_SUPPLY_PROP_TEMP: - return ltc4162l_get_die_temp(info, val); + return chip_info->get_die_temp(info, val); case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: return ltc4162l_get_term_current(info, val); default: @@ -772,7 +1040,6 @@ static enum power_supply_property ltc4162l_properties[] = { }; static const struct power_supply_desc ltc4162l_desc = { - .name = "ltc4162-l", .type = POWER_SUPPLY_TYPE_MAINS, .properties = ltc4162l_properties, .num_properties = ARRAY_SIZE(ltc4162l_properties), @@ -781,6 +1048,50 @@ static const struct power_supply_desc ltc4162l_desc = { .property_is_writeable = ltc4162l_property_is_writeable, }; +static const struct ltc4162l_chip_info ltc4162l_chip_info = { + .name = "ltc4162-l", + .get_vbat = ltc4162l_get_vbat, + .get_vcharge = ltc4162l_get_vcharge, + .set_vcharge = ltc4162l_set_vcharge, + .get_die_temp = ltc4162l_get_die_temp, + .ibat_resolution_pv = 1466000, + .vin_resolution_uv = 1649, + .telemetry_mask = BIT(2), +}; + +static const struct ltc4162l_chip_info ltc4162f_chip_info = { + .name = "ltc4162-f", + .get_vbat = ltc4162l_get_vbat, + .get_vcharge = ltc4162l_get_vcharge, + .set_vcharge = ltc4162l_set_vcharge, + .get_die_temp = ltc4162l_get_die_temp, + .ibat_resolution_pv = 1466000, + .vin_resolution_uv = 1649, + .telemetry_mask = BIT(2), +}; + +static const struct ltc4162l_chip_info ltc4162s_chip_info = { + .name = "ltc4162-s", + .get_vbat = ltc4162l_get_vbat, + .get_vcharge = ltc4162l_get_vcharge, + .set_vcharge = ltc4162l_set_vcharge, + .get_die_temp = ltc4162l_get_die_temp, + .ibat_resolution_pv = 1466000, + .vin_resolution_uv = 1649, + .telemetry_mask = BIT(2), +}; + +static const struct ltc4162l_chip_info ltc4015_chip_info = { + .name = "ltc4015", + .get_vbat = ltc4015_get_vbat, + .get_vcharge = ltc4015_get_vcharge, + .set_vcharge = ltc4015_set_vcharge, + .get_die_temp = ltc4015_get_die_temp, + .ibat_resolution_pv = 1464870, + .vin_resolution_uv = 1648, + .telemetry_mask = BIT(4), +}; + static bool ltc4162l_is_writeable_reg(struct device *dev, unsigned int reg) { /* all registers up to this one are writeable */ @@ -825,6 +1136,8 @@ static int ltc4162l_probe(struct i2c_client *client) struct device *dev = &client->dev; struct ltc4162l_info *info; struct power_supply_config ltc4162l_config = {}; + struct power_supply_desc *desc; + const struct ltc4162l_chip_info *chip_info; u32 value; int ret; @@ -839,6 +1152,12 @@ static int ltc4162l_probe(struct i2c_client *client) info->client = client; i2c_set_clientdata(client, info); + chip_info = i2c_get_match_data(client); + if (!chip_info) + return -ENODEV; + + info->chip_info = chip_info; + info->regmap = devm_regmap_init_i2c(client, <c4162l_regmap_config); if (IS_ERR(info->regmap)) { dev_err(dev, "Failed to initialize register map\n"); @@ -870,8 +1189,15 @@ static int ltc4162l_probe(struct i2c_client *client) ltc4162l_config.drv_data = info; ltc4162l_config.attr_grp = ltc4162l_attr_groups; - info->charger = devm_power_supply_register(dev, <c4162l_desc, - <c4162l_config); + /* Duplicate the default descriptor to set name based on chip_info. */ + desc = devm_kmemdup(dev, <c4162l_desc, + sizeof(struct power_supply_desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + desc->name = chip_info->name; + + info->charger = devm_power_supply_register(dev, desc, <c4162l_config); if (IS_ERR(info->charger)) { dev_err(dev, "Failed to register charger\n"); return PTR_ERR(info->charger); @@ -903,14 +1229,20 @@ static void ltc4162l_alert(struct i2c_client *client, } static const struct i2c_device_id ltc4162l_i2c_id_table[] = { - { "ltc4162-l" }, + { "ltc4015", (kernel_ulong_t)<c4015_chip_info }, + { "ltc4162-f", (kernel_ulong_t)<c4162f_chip_info }, + { "ltc4162-l", (kernel_ulong_t)<c4162l_chip_info }, + { "ltc4162-s", (kernel_ulong_t)<c4162s_chip_info }, { } }; MODULE_DEVICE_TABLE(i2c, ltc4162l_i2c_id_table); static const struct of_device_id ltc4162l_of_match[] __maybe_unused = { - { .compatible = "lltc,ltc4162-l", }, - { }, + { .compatible = "lltc,ltc4015", .data = <c4015_chip_info }, + { .compatible = "lltc,ltc4162-f", .data = <c4162f_chip_info }, + { .compatible = "lltc,ltc4162-l", .data = <c4162l_chip_info }, + { .compatible = "lltc,ltc4162-s", .data = <c4162s_chip_info }, + { } }; MODULE_DEVICE_TABLE(of, ltc4162l_of_match); diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c index 496c3e1f2ee6..655b3f25dbd7 100644 --- a/drivers/power/supply/max17042_battery.c +++ b/drivers/power/supply/max17042_battery.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -52,13 +53,14 @@ #define MAX17042_VMAX_TOLERANCE 50 /* 50 mV */ struct max17042_chip { - struct i2c_client *client; + struct device *dev; struct regmap *regmap; struct power_supply *battery; enum max170xx_chip_type chip_type; struct max17042_platform_data *pdata; struct work_struct work; int init_complete; + int irq; }; static enum power_supply_property max17042_battery_props[] = { @@ -573,11 +575,11 @@ static inline int max17042_model_data_compare(struct max17042_chip *chip, int i; if (memcmp(data1, data2, size)) { - dev_err(&chip->client->dev, "%s compare failed\n", __func__); + dev_err(chip->dev, "%s compare failed\n", __func__); for (i = 0; i < size; i++) - dev_info(&chip->client->dev, "0x%x, 0x%x", + dev_info(chip->dev, "0x%x, 0x%x", data1[i], data2[i]); - dev_info(&chip->client->dev, "\n"); + dev_info(chip->dev, "\n"); return -EINVAL; } return 0; @@ -812,14 +814,14 @@ static int max17042_init_chip(struct max17042_chip *chip) /* write cell characterization data */ ret = max17042_init_model(chip); if (ret) { - dev_err(&chip->client->dev, "%s init failed\n", + dev_err(chip->dev, "%s init failed\n", __func__); return -EIO; } ret = max17042_verify_model_lock(chip); if (ret) { - dev_err(&chip->client->dev, "%s lock verify failed\n", + dev_err(chip->dev, "%s lock verify failed\n", __func__); return -EIO; } @@ -875,7 +877,7 @@ static irqreturn_t max17042_thread_handler(int id, void *dev) return IRQ_HANDLED; if ((val & STATUS_SMN_BIT) || (val & STATUS_SMX_BIT)) { - dev_dbg(&chip->client->dev, "SOC threshold INTR\n"); + dev_dbg(chip->dev, "SOC threshold INTR\n"); max17042_set_soc_threshold(chip, 1); } @@ -907,7 +909,7 @@ static void max17042_init_worker(struct work_struct *work) static struct max17042_platform_data * max17042_get_of_pdata(struct max17042_chip *chip) { - struct device *dev = &chip->client->dev; + struct device *dev = chip->dev; struct device_node *np = dev->of_node; u32 prop; struct max17042_platform_data *pdata; @@ -949,7 +951,7 @@ static struct max17042_reg_data max17047_default_pdata_init_regs[] = { static struct max17042_platform_data * max17042_get_default_pdata(struct max17042_chip *chip) { - struct device *dev = &chip->client->dev; + struct device *dev = chip->dev; struct max17042_platform_data *pdata; int ret, misc_cfg; @@ -990,7 +992,7 @@ max17042_get_default_pdata(struct max17042_chip *chip) static struct max17042_platform_data * max17042_get_pdata(struct max17042_chip *chip) { - struct device *dev = &chip->client->dev; + struct device *dev = chip->dev; #ifdef CONFIG_OF if (dev->of_node) @@ -1003,6 +1005,7 @@ max17042_get_pdata(struct max17042_chip *chip) } static const struct regmap_config max17042_regmap_config = { + .name = "max17042", .reg_bits = 8, .val_bits = 16, .val_format_endian = REGMAP_ENDIAN_NATIVE, @@ -1029,14 +1032,12 @@ static const struct power_supply_desc max17042_no_current_sense_psy_desc = { .num_properties = ARRAY_SIZE(max17042_battery_props) - 2, }; -static int max17042_probe(struct i2c_client *client) +static int max17042_probe(struct i2c_client *client, struct device *dev, int irq, + enum max170xx_chip_type chip_type) { - const struct i2c_device_id *id = i2c_client_get_device_id(client); struct i2c_adapter *adapter = client->adapter; const struct power_supply_desc *max17042_desc = &max17042_psy_desc; struct power_supply_config psy_cfg = {}; - const struct acpi_device_id *acpi_id = NULL; - struct device *dev = &client->dev; struct max17042_chip *chip; int ret; int i; @@ -1045,33 +1046,25 @@ static int max17042_probe(struct i2c_client *client) if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA)) return -EIO; - chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL); + chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL); if (!chip) return -ENOMEM; - chip->client = client; - if (id) { - chip->chip_type = id->driver_data; - } else { - acpi_id = acpi_match_device(dev->driver->acpi_match_table, dev); - if (!acpi_id) - return -ENODEV; - - chip->chip_type = acpi_id->driver_data; - } + chip->dev = dev; + chip->chip_type = chip_type; chip->regmap = devm_regmap_init_i2c(client, &max17042_regmap_config); if (IS_ERR(chip->regmap)) { - dev_err(&client->dev, "Failed to initialize regmap\n"); + dev_err(dev, "Failed to initialize regmap\n"); return -EINVAL; } chip->pdata = max17042_get_pdata(chip); if (!chip->pdata) { - dev_err(&client->dev, "no platform data provided\n"); + dev_err(dev, "no platform data provided\n"); return -EINVAL; } - i2c_set_clientdata(client, chip); + dev_set_drvdata(dev, chip); psy_cfg.drv_data = chip; psy_cfg.of_node = dev->of_node; @@ -1095,24 +1088,17 @@ static int max17042_probe(struct i2c_client *client) regmap_write(chip->regmap, MAX17042_LearnCFG, 0x0007); } - chip->battery = devm_power_supply_register(&client->dev, max17042_desc, + chip->battery = devm_power_supply_register(dev, max17042_desc, &psy_cfg); if (IS_ERR(chip->battery)) { - dev_err(&client->dev, "failed: power supply register\n"); + dev_err(dev, "failed: power supply register\n"); return PTR_ERR(chip->battery); } - if (client->irq) { - unsigned int flags = IRQF_ONESHOT; + if (irq) { + unsigned int flags = IRQF_ONESHOT | IRQF_SHARED | IRQF_PROBE_SHARED; - /* - * On ACPI systems the IRQ may be handled by ACPI-event code, - * so we need to share (if the ACPI code is willing to share). - */ - if (acpi_id) - flags |= IRQF_SHARED | IRQF_PROBE_SHARED; - - ret = devm_request_threaded_irq(&client->dev, client->irq, + ret = devm_request_threaded_irq(dev, irq, NULL, max17042_thread_handler, flags, chip->battery->desc->name, @@ -1123,18 +1109,20 @@ static int max17042_probe(struct i2c_client *client) CFG_ALRT_BIT_ENBL); max17042_set_soc_threshold(chip, 1); } else { - client->irq = 0; + irq = 0; if (ret != -EBUSY) - dev_err(&client->dev, "Failed to get IRQ\n"); + dev_err(dev, "Failed to get IRQ\n"); } } /* Not able to update the charge threshold when exceeded? -> disable */ - if (!client->irq) + if (!irq) regmap_write(chip->regmap, MAX17042_SALRT_Th, 0xff00); + chip->irq = irq; + regmap_read(chip->regmap, MAX17042_STATUS, &val); if (val & STATUS_POR_BIT) { - ret = devm_work_autocancel(&client->dev, &chip->work, + ret = devm_work_autocancel(dev, &chip->work, max17042_init_worker); if (ret) return ret; @@ -1146,6 +1134,44 @@ static int max17042_probe(struct i2c_client *client) return 0; } +static int max17042_i2c_probe(struct i2c_client *client) +{ + const struct i2c_device_id *id = i2c_client_get_device_id(client); + const struct acpi_device_id *acpi_id = NULL; + struct device *dev = &client->dev; + enum max170xx_chip_type chip_type; + + if (id) { + chip_type = id->driver_data; + } else { + acpi_id = acpi_match_device(dev->driver->acpi_match_table, dev); + if (!acpi_id) + return -ENODEV; + + chip_type = acpi_id->driver_data; + } + + return max17042_probe(client, dev, client->irq, chip_type); +} + +static int max17042_platform_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct i2c_client *i2c; + const struct platform_device_id *id; + int irq; + + i2c = to_i2c_client(pdev->dev.parent); + if (!i2c) + return -EINVAL; + + dev->of_node = dev->parent->of_node; + id = platform_get_device_id(pdev); + irq = platform_get_irq(pdev, 0); + + return max17042_probe(i2c, dev, irq, id->driver_data); +} + #ifdef CONFIG_PM_SLEEP static int max17042_suspend(struct device *dev) { @@ -1155,9 +1181,9 @@ static int max17042_suspend(struct device *dev) * disable the irq and enable irq_wake * capability to the interrupt line. */ - if (chip->client->irq) { - disable_irq(chip->client->irq); - enable_irq_wake(chip->client->irq); + if (chip->irq) { + disable_irq(chip->irq); + enable_irq_wake(chip->irq); } return 0; @@ -1167,9 +1193,9 @@ static int max17042_resume(struct device *dev) { struct max17042_chip *chip = dev_get_drvdata(dev); - if (chip->client->irq) { - disable_irq_wake(chip->client->irq); - enable_irq(chip->client->irq); + if (chip->irq) { + disable_irq_wake(chip->irq); + enable_irq(chip->irq); /* re-program the SOC thresholds to 1% change */ max17042_set_soc_threshold(chip, 1); } @@ -1190,12 +1216,28 @@ MODULE_DEVICE_TABLE(acpi, max17042_acpi_match); #endif #ifdef CONFIG_OF -static const struct of_device_id max17042_dt_match[] = { - { .compatible = "maxim,max17042" }, - { .compatible = "maxim,max17047" }, - { .compatible = "maxim,max17050" }, - { .compatible = "maxim,max17055" }, - { .compatible = "maxim,max77849-battery" }, +/* + * Device may be instantiated through parent MFD device and device matching is done + * through platform_device_id. + * + * However if device's DT node contains proper clock compatible and driver is + * built as a module, then the *module* matching will be done trough DT aliases. + * This requires of_device_id table. In the same time this will not change the + * actual *device* matching so do not add .of_match_table. + */ +static const struct of_device_id max17042_dt_match[] __used = { + { .compatible = "maxim,max17042", + .data = (void *) MAXIM_DEVICE_TYPE_MAX17042 }, + { .compatible = "maxim,max17047", + .data = (void *) MAXIM_DEVICE_TYPE_MAX17047 }, + { .compatible = "maxim,max17050", + .data = (void *) MAXIM_DEVICE_TYPE_MAX17050 }, + { .compatible = "maxim,max17055", + .data = (void *) MAXIM_DEVICE_TYPE_MAX17055 }, + { .compatible = "maxim,max77705-battery", + .data = (void *) MAXIM_DEVICE_TYPE_MAX17047 }, + { .compatible = "maxim,max77849-battery", + .data = (void *) MAXIM_DEVICE_TYPE_MAX17047 }, { }, }; MODULE_DEVICE_TABLE(of, max17042_dt_match); @@ -1211,6 +1253,17 @@ static const struct i2c_device_id max17042_id[] = { }; MODULE_DEVICE_TABLE(i2c, max17042_id); +static const struct platform_device_id max17042_platform_id[] = { + { "max17042", MAXIM_DEVICE_TYPE_MAX17042 }, + { "max17047", MAXIM_DEVICE_TYPE_MAX17047 }, + { "max17050", MAXIM_DEVICE_TYPE_MAX17050 }, + { "max17055", MAXIM_DEVICE_TYPE_MAX17055 }, + { "max77705-battery", MAXIM_DEVICE_TYPE_MAX17047 }, + { "max77849-battery", MAXIM_DEVICE_TYPE_MAX17047 }, + { } +}; +MODULE_DEVICE_TABLE(platform, max17042_platform_id); + static struct i2c_driver max17042_i2c_driver = { .driver = { .name = "max17042", @@ -1218,10 +1271,44 @@ static struct i2c_driver max17042_i2c_driver = { .of_match_table = of_match_ptr(max17042_dt_match), .pm = &max17042_pm_ops, }, - .probe = max17042_probe, + .probe = max17042_i2c_probe, .id_table = max17042_id, }; -module_i2c_driver(max17042_i2c_driver); + +static struct platform_driver max17042_platform_driver = { + .driver = { + .name = "max17042", + .acpi_match_table = ACPI_PTR(max17042_acpi_match), + .pm = &max17042_pm_ops, + }, + .probe = max17042_platform_probe, + .id_table = max17042_platform_id, +}; + +static int __init max17042_init(void) +{ + int ret; + + ret = platform_driver_register(&max17042_platform_driver); + if (ret) + return ret; + + ret = i2c_add_driver(&max17042_i2c_driver); + if (ret) { + platform_driver_unregister(&max17042_platform_driver); + return ret; + } + + return 0; +} +module_init(max17042_init); + +static void __exit max17042_exit(void) +{ + i2c_del_driver(&max17042_i2c_driver); + platform_driver_unregister(&max17042_platform_driver); +} +module_exit(max17042_exit); MODULE_AUTHOR("MyungJoo Ham "); MODULE_DESCRIPTION("MAX17042 Fuel Gauge"); diff --git a/drivers/power/supply/max1720x_battery.c b/drivers/power/supply/max1720x_battery.c index 33105419e242..11580e414713 100644 --- a/drivers/power/supply/max1720x_battery.c +++ b/drivers/power/supply/max1720x_battery.c @@ -16,6 +16,11 @@ #include +/* SBS compliant registers */ +#define MAX172XX_TEMP1 0x34 +#define MAX172XX_INT_TEMP 0x35 +#define MAX172XX_TEMP2 0x3B + /* Nonvolatile registers */ #define MAX1720X_NXTABLE0 0x80 #define MAX1720X_NRSENSE 0xCF /* RSense in 10^-5 Ohm */ @@ -29,6 +34,7 @@ #define MAX172XX_TEMP 0x08 /* Temperature */ #define MAX172XX_CURRENT 0x0A /* Actual current */ #define MAX172XX_AVG_CURRENT 0x0B /* Average current */ +#define MAX172XX_FULL_CAP 0x10 /* Calculated full capacity */ #define MAX172XX_TTE 0x11 /* Time to empty */ #define MAX172XX_AVG_TA 0x16 /* Average temperature */ #define MAX172XX_CYCLES 0x17 @@ -112,11 +118,15 @@ static const struct regmap_config max1720x_regmap_cfg = { }; static const struct regmap_range max1720x_nvmem_allow[] = { + regmap_reg_range(MAX172XX_TEMP1, MAX172XX_INT_TEMP), + regmap_reg_range(MAX172XX_TEMP2, MAX172XX_TEMP2), regmap_reg_range(MAX1720X_NXTABLE0, MAX1720X_NDEVICE_NAME4), }; static const struct regmap_range max1720x_nvmem_deny[] = { - regmap_reg_range(0x00, 0x7F), + regmap_reg_range(0x00, 0x33), + regmap_reg_range(0x36, 0x3A), + regmap_reg_range(0x3C, 0x7F), regmap_reg_range(0xE0, 0xFF), }; @@ -250,6 +260,7 @@ static const enum power_supply_property max1720x_battery_props[] = { POWER_SUPPLY_PROP_TEMP, POWER_SUPPLY_PROP_CURRENT_NOW, POWER_SUPPLY_PROP_CURRENT_AVG, + POWER_SUPPLY_PROP_CHARGE_FULL, POWER_SUPPLY_PROP_MODEL_NAME, POWER_SUPPLY_PROP_MANUFACTURER, }; @@ -362,6 +373,10 @@ static int max1720x_battery_get_property(struct power_supply *psy, ret = regmap_read(info->regmap, MAX172XX_AVG_CURRENT, ®_val); val->intval = max172xx_current_to_voltage(reg_val) / info->rsense; break; + case POWER_SUPPLY_PROP_CHARGE_FULL: + ret = regmap_read(info->regmap, MAX172XX_FULL_CAP, ®_val); + val->intval = max172xx_capacity_to_ps(reg_val); + break; case POWER_SUPPLY_PROP_MODEL_NAME: ret = regmap_read(info->regmap, MAX172XX_DEV_NAME, ®_val); reg_val = FIELD_GET(MAX172XX_DEV_NAME_TYPE_MASK, reg_val); @@ -382,6 +397,54 @@ static int max1720x_battery_get_property(struct power_supply *psy, return ret; } +static int max1720x_read_temp(struct device *dev, u8 reg, char *buf) +{ + struct power_supply *psy = dev_get_drvdata(dev); + struct max1720x_device_info *info = power_supply_get_drvdata(psy); + unsigned int val; + int ret; + + ret = regmap_read(info->regmap_nv, reg, &val); + if (ret < 0) + return ret; + + /* + * Temperature in degrees Celsius starting at absolute zero, -273C or + * 0K with an LSb of 0.1C + */ + return sysfs_emit(buf, "%d\n", val - 2730); +} + +static ssize_t temp_ain1_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return max1720x_read_temp(dev, MAX172XX_TEMP1, buf); +} + +static ssize_t temp_ain2_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return max1720x_read_temp(dev, MAX172XX_TEMP2, buf); +} + +static ssize_t temp_int_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return max1720x_read_temp(dev, MAX172XX_INT_TEMP, buf); +} + +static DEVICE_ATTR_RO(temp_ain1); +static DEVICE_ATTR_RO(temp_ain2); +static DEVICE_ATTR_RO(temp_int); + +static struct attribute *max1720x_attrs[] = { + &dev_attr_temp_ain1.attr, + &dev_attr_temp_ain2.attr, + &dev_attr_temp_int.attr, + NULL +}; +ATTRIBUTE_GROUPS(max1720x); + static int max1720x_nvmem_reg_read(void *priv, unsigned int off, void *val, size_t len) { @@ -482,6 +545,7 @@ static int max1720x_probe(struct i2c_client *client) psy_cfg.drv_data = info; psy_cfg.fwnode = dev_fwnode(dev); + psy_cfg.attr_grp = max1720x_groups; i2c_set_clientdata(client, info); info->regmap = devm_regmap_init_i2c(client, &max1720x_regmap_cfg); if (IS_ERR(info->regmap)) diff --git a/drivers/power/supply/mm8013.c b/drivers/power/supply/mm8013.c index 5bcfaeeda3db..4adf2acc2779 100644 --- a/drivers/power/supply/mm8013.c +++ b/drivers/power/supply/mm8013.c @@ -90,7 +90,7 @@ static int mm8013_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) { - struct mm8013_chip *chip = psy->drv_data; + struct mm8013_chip *chip = power_supply_get_drvdata(psy); int ret = 0; u32 regval; diff --git a/drivers/power/supply/olpc_battery.c b/drivers/power/supply/olpc_battery.c index 9f60094a5599..849f63e89ba0 100644 --- a/drivers/power/supply/olpc_battery.c +++ b/drivers/power/supply/olpc_battery.c @@ -527,7 +527,7 @@ static enum power_supply_property olpc_xo15_bat_props[] = { #define EEPROM_SIZE (EEPROM_END - EEPROM_START) static ssize_t olpc_bat_eeprom_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, size_t count) + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { uint8_t ec_byte; int ret; @@ -547,13 +547,13 @@ static ssize_t olpc_bat_eeprom_read(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute olpc_bat_eeprom = { +static const struct bin_attribute olpc_bat_eeprom = { .attr = { .name = "eeprom", .mode = S_IRUGO, }, .size = EEPROM_SIZE, - .read = olpc_bat_eeprom_read, + .read_new = olpc_bat_eeprom_read, }; /* Allow userspace to see the specific error value pulled from the EC */ @@ -584,15 +584,14 @@ static struct attribute *olpc_bat_sysfs_attrs[] = { NULL }; -static struct bin_attribute *olpc_bat_sysfs_bin_attrs[] = { +static const struct bin_attribute *const olpc_bat_sysfs_bin_attrs[] = { &olpc_bat_eeprom, NULL }; static const struct attribute_group olpc_bat_sysfs_group = { .attrs = olpc_bat_sysfs_attrs, - .bin_attrs = olpc_bat_sysfs_bin_attrs, - + .bin_attrs_new = olpc_bat_sysfs_bin_attrs, }; static const struct attribute_group *olpc_bat_sysfs_groups[] = { diff --git a/drivers/power/supply/power_supply.h b/drivers/power/supply/power_supply.h index 7434a6f24775..8f6a2d44b996 100644 --- a/drivers/power/supply/power_supply.h +++ b/drivers/power/supply/power_supply.h @@ -9,24 +9,55 @@ * Modified: 2004, Oct Szabolcs Gyurko */ +#include + struct device; struct device_type; struct power_supply; extern int power_supply_property_is_writeable(struct power_supply *psy, enum power_supply_property psp); +extern bool power_supply_has_property(struct power_supply *psy, + enum power_supply_property psp); +extern bool power_supply_ext_has_property(const struct power_supply_ext *ext, + enum power_supply_property psp); + +struct power_supply_ext_registration { + struct list_head list_head; + const struct power_supply_ext *ext; + struct device *dev; + void *data; +}; + +/* Make sure that the macro is a single expression */ +#define power_supply_for_each_extension(pos, psy) \ + if ( ({ lockdep_assert_held(&(psy)->extensions_sem); 0; }) ) \ + ; \ + else \ + list_for_each_entry(pos, &(psy)->extensions, list_head) \ #ifdef CONFIG_SYSFS extern void __init power_supply_init_attrs(void); extern int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env); extern const struct attribute_group *power_supply_attr_groups[]; +extern int power_supply_sysfs_add_extension(struct power_supply *psy, + const struct power_supply_ext *ext, + struct device *dev); +extern void power_supply_sysfs_remove_extension(struct power_supply *psy, + const struct power_supply_ext *ext); #else static inline void power_supply_init_attrs(void) {} #define power_supply_attr_groups NULL #define power_supply_uevent NULL +static inline int power_supply_sysfs_add_extension(struct power_supply *psy, + const struct power_supply_ext *ext, + struct device *dev) +{ return 0; } +static inline void power_supply_sysfs_remove_extension(struct power_supply *psy, + const struct power_supply_ext *ext) {} #endif /* CONFIG_SYSFS */ diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 16085eff0084..d0bb52a7a036 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -66,21 +66,19 @@ static bool __power_supply_is_supplied_by(struct power_supply *supplier, return false; } -static int __power_supply_changed_work(struct device *dev, void *data) +static int __power_supply_changed_work(struct power_supply *pst, void *data) { struct power_supply *psy = data; - struct power_supply *pst = dev_get_drvdata(dev); - if (__power_supply_is_supplied_by(psy, pst)) { - if (pst->desc->external_power_changed) - pst->desc->external_power_changed(pst); - } + if (__power_supply_is_supplied_by(psy, pst)) + power_supply_external_power_changed(pst); return 0; } static void power_supply_changed_work(struct work_struct *work) { + int ret; unsigned long flags; struct power_supply *psy = container_of(work, struct power_supply, changed_work); @@ -88,6 +86,16 @@ static void power_supply_changed_work(struct work_struct *work) dev_dbg(&psy->dev, "%s\n", __func__); spin_lock_irqsave(&psy->changed_lock, flags); + + if (unlikely(psy->update_groups)) { + psy->update_groups = false; + spin_unlock_irqrestore(&psy->changed_lock, flags); + ret = sysfs_update_groups(&psy->dev.kobj, power_supply_dev_type.groups); + if (ret) + dev_warn(&psy->dev, "failed to update sysfs groups: %pe\n", ERR_PTR(ret)); + spin_lock_irqsave(&psy->changed_lock, flags); + } + /* * Check 'changed' here to avoid issues due to race between * power_supply_changed() and this routine. In worst case @@ -98,7 +106,7 @@ static void power_supply_changed_work(struct work_struct *work) if (likely(psy->changed)) { psy->changed = false; spin_unlock_irqrestore(&psy->changed_lock, flags); - power_supply_for_each_device(psy, __power_supply_changed_work); + power_supply_for_each_psy(psy, __power_supply_changed_work); power_supply_update_leds(psy); blocking_notifier_call_chain(&power_supply_notifier, PSY_EVENT_PROP_CHANGED, psy); @@ -116,11 +124,29 @@ static void power_supply_changed_work(struct work_struct *work) spin_unlock_irqrestore(&psy->changed_lock, flags); } -int power_supply_for_each_device(void *data, int (*fn)(struct device *dev, void *data)) +struct psy_for_each_psy_cb_data { + int (*fn)(struct power_supply *psy, void *data); + void *data; +}; + +static int psy_for_each_psy_cb(struct device *dev, void *data) { - return class_for_each_device(&power_supply_class, NULL, data, fn); + struct psy_for_each_psy_cb_data *cb_data = data; + struct power_supply *psy = dev_to_psy(dev); + + return cb_data->fn(psy, cb_data->data); } -EXPORT_SYMBOL_GPL(power_supply_for_each_device); + +int power_supply_for_each_psy(void *data, int (*fn)(struct power_supply *psy, void *data)) +{ + struct psy_for_each_psy_cb_data cb_data = { + .fn = fn, + .data = data, + }; + + return class_for_each_device(&power_supply_class, NULL, &cb_data, psy_for_each_psy_cb); +} +EXPORT_SYMBOL_GPL(power_supply_for_each_psy); void power_supply_changed(struct power_supply *psy) { @@ -166,11 +192,10 @@ static void power_supply_deferred_register_work(struct work_struct *work) } #ifdef CONFIG_OF -static int __power_supply_populate_supplied_from(struct device *dev, +static int __power_supply_populate_supplied_from(struct power_supply *epsy, void *data) { struct power_supply *psy = data; - struct power_supply *epsy = dev_get_drvdata(dev); struct device_node *np; int i = 0; @@ -197,20 +222,19 @@ static int power_supply_populate_supplied_from(struct power_supply *psy) { int error; - error = power_supply_for_each_device(psy, __power_supply_populate_supplied_from); + error = power_supply_for_each_psy(psy, __power_supply_populate_supplied_from); dev_dbg(&psy->dev, "%s %d\n", __func__, error); return error; } -static int __power_supply_find_supply_from_node(struct device *dev, +static int __power_supply_find_supply_from_node(struct power_supply *epsy, void *data) { struct device_node *np = data; - struct power_supply *epsy = dev_get_drvdata(dev); - /* returning non-zero breaks out of power_supply_for_each_device loop */ + /* returning non-zero breaks out of power_supply_for_each_psy loop */ if (epsy->of_node == np) return 1; @@ -222,16 +246,16 @@ static int power_supply_find_supply_from_node(struct device_node *supply_node) int error; /* - * power_supply_for_each_device() either returns its own errors or values + * power_supply_for_each_psy() either returns its own errors or values * returned by __power_supply_find_supply_from_node(). * * __power_supply_find_supply_from_node() will return 0 (no match) * or 1 (match). * - * We return 0 if power_supply_for_each_device() returned 1, -EPROBE_DEFER if + * We return 0 if power_supply_for_each_psy() returned 1, -EPROBE_DEFER if * it returned 0, or error as returned by it. */ - error = power_supply_for_each_device(supply_node, __power_supply_find_supply_from_node); + error = power_supply_for_each_psy(supply_node, __power_supply_find_supply_from_node); return error ? (error == 1 ? 0 : error) : -EPROBE_DEFER; } @@ -316,10 +340,9 @@ struct psy_am_i_supplied_data { unsigned int count; }; -static int __power_supply_am_i_supplied(struct device *dev, void *_data) +static int __power_supply_am_i_supplied(struct power_supply *epsy, void *_data) { union power_supply_propval ret = {0,}; - struct power_supply *epsy = dev_get_drvdata(dev); struct psy_am_i_supplied_data *data = _data; if (__power_supply_is_supplied_by(epsy, data->psy)) { @@ -337,7 +360,7 @@ int power_supply_am_i_supplied(struct power_supply *psy) struct psy_am_i_supplied_data data = { psy, 0 }; int error; - error = power_supply_for_each_device(&data, __power_supply_am_i_supplied); + error = power_supply_for_each_psy(&data, __power_supply_am_i_supplied); dev_dbg(&psy->dev, "%s count %u err %d\n", __func__, data.count, error); @@ -348,10 +371,9 @@ int power_supply_am_i_supplied(struct power_supply *psy) } EXPORT_SYMBOL_GPL(power_supply_am_i_supplied); -static int __power_supply_is_system_supplied(struct device *dev, void *data) +static int __power_supply_is_system_supplied(struct power_supply *psy, void *data) { union power_supply_propval ret = {0,}; - struct power_supply *psy = dev_get_drvdata(dev); unsigned int *count = data; if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_SCOPE, &ret)) @@ -372,7 +394,7 @@ int power_supply_is_system_supplied(void) int error; unsigned int count = 0; - error = power_supply_for_each_device(&count, __power_supply_is_system_supplied); + error = power_supply_for_each_psy(&count, __power_supply_is_system_supplied); /* * If no system scope power class device was found at all, most probably we @@ -391,9 +413,8 @@ struct psy_get_supplier_prop_data { union power_supply_propval *val; }; -static int __power_supply_get_supplier_property(struct device *dev, void *_data) +static int __power_supply_get_supplier_property(struct power_supply *epsy, void *_data) { - struct power_supply *epsy = dev_get_drvdata(dev); struct psy_get_supplier_prop_data *data = _data; if (__power_supply_is_supplied_by(epsy, data->psy)) @@ -418,7 +439,7 @@ int power_supply_get_property_from_supplier(struct power_supply *psy, * This function is not intended for use with a supply with multiple * suppliers, we simply pick the first supply to report the psp. */ - ret = power_supply_for_each_device(&data, __power_supply_get_supplier_property); + ret = power_supply_for_each_psy(&data, __power_supply_get_supplier_property); if (ret < 0) return ret; if (ret == 0) @@ -444,7 +465,7 @@ EXPORT_SYMBOL_GPL(power_supply_set_battery_charged); static int power_supply_match_device_by_name(struct device *dev, const void *data) { const char *name = data; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); return strcmp(psy->desc->name, name) == 0; } @@ -467,7 +488,7 @@ struct power_supply *power_supply_get_by_name(const char *name) power_supply_match_device_by_name); if (dev) { - psy = dev_get_drvdata(dev); + psy = dev_to_psy(dev); atomic_inc(&psy->use_cnt); } @@ -524,7 +545,7 @@ struct power_supply *power_supply_get_by_phandle(struct device_node *np, of_node_put(power_supply_np); if (dev) { - psy = dev_get_drvdata(dev); + psy = dev_to_psy(dev); atomic_inc(&psy->use_cnt); } @@ -1180,8 +1201,8 @@ bool power_supply_battery_bti_in_range(struct power_supply_battery_info *info, } EXPORT_SYMBOL_GPL(power_supply_battery_bti_in_range); -static bool psy_has_property(const struct power_supply_desc *psy_desc, - enum power_supply_property psp) +static bool psy_desc_has_property(const struct power_supply_desc *psy_desc, + enum power_supply_property psp) { bool found = false; int i; @@ -1196,17 +1217,57 @@ static bool psy_has_property(const struct power_supply_desc *psy_desc, return found; } +bool power_supply_ext_has_property(const struct power_supply_ext *psy_ext, + enum power_supply_property psp) +{ + int i; + + for (i = 0; i < psy_ext->num_properties; i++) + if (psy_ext->properties[i] == psp) + return true; + + return false; +} + +bool power_supply_has_property(struct power_supply *psy, + enum power_supply_property psp) +{ + struct power_supply_ext_registration *reg; + + if (psy_desc_has_property(psy->desc, psp)) + return true; + + if (power_supply_battery_info_has_prop(psy->battery_info, psp)) + return true; + + power_supply_for_each_extension(reg, psy) { + if (power_supply_ext_has_property(reg->ext, psp)) + return true; + } + + return false; +} + int power_supply_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) { + struct power_supply_ext_registration *reg; + if (atomic_read(&psy->use_cnt) <= 0) { if (!psy->initialized) return -EAGAIN; return -ENODEV; } - if (psy_has_property(psy->desc, psp)) + scoped_guard(rwsem_read, &psy->extensions_sem) { + power_supply_for_each_extension(reg, psy) { + if (power_supply_ext_has_property(reg->ext, psp)) + return reg->ext->get_property(psy, reg->ext, reg->data, psp, val); + } + } + + if (psy_desc_has_property(psy->desc, psp)) return psy->desc->get_property(psy, psp, val); else if (power_supply_battery_info_has_prop(psy->battery_info, psp)) return power_supply_battery_info_get_prop(psy->battery_info, psp, val); @@ -1219,7 +1280,24 @@ int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val) { - if (atomic_read(&psy->use_cnt) <= 0 || !psy->desc->set_property) + struct power_supply_ext_registration *reg; + + if (atomic_read(&psy->use_cnt) <= 0) + return -ENODEV; + + scoped_guard(rwsem_read, &psy->extensions_sem) { + power_supply_for_each_extension(reg, psy) { + if (power_supply_ext_has_property(reg->ext, psp)) { + if (reg->ext->set_property) + return reg->ext->set_property(psy, reg->ext, reg->data, + psp, val); + else + return -ENODEV; + } + } + } + + if (!psy->desc->set_property) return -ENODEV; return psy->desc->set_property(psy, psp, val); @@ -1229,7 +1307,22 @@ EXPORT_SYMBOL_GPL(power_supply_set_property); int power_supply_property_is_writeable(struct power_supply *psy, enum power_supply_property psp) { - return psy->desc->property_is_writeable && psy->desc->property_is_writeable(psy, psp); + struct power_supply_ext_registration *reg; + + power_supply_for_each_extension(reg, psy) { + if (power_supply_ext_has_property(reg->ext, psp)) { + if (reg->ext->property_is_writeable) + return reg->ext->property_is_writeable(psy, reg->ext, + reg->data, psp); + else + return 0; + } + } + + if (!psy->desc->property_is_writeable) + return 0; + + return psy->desc->property_is_writeable(psy, psp); } void power_supply_external_power_changed(struct power_supply *psy) @@ -1248,6 +1341,88 @@ int power_supply_powers(struct power_supply *psy, struct device *dev) } EXPORT_SYMBOL_GPL(power_supply_powers); +static int power_supply_update_sysfs_and_hwmon(struct power_supply *psy) +{ + unsigned long flags; + + spin_lock_irqsave(&psy->changed_lock, flags); + psy->update_groups = true; + spin_unlock_irqrestore(&psy->changed_lock, flags); + + power_supply_changed(psy); + + power_supply_remove_hwmon_sysfs(psy); + return power_supply_add_hwmon_sysfs(psy); +} + +int power_supply_register_extension(struct power_supply *psy, const struct power_supply_ext *ext, + struct device *dev, void *data) +{ + struct power_supply_ext_registration *reg; + size_t i; + int ret; + + if (!psy || !dev || !ext || !ext->name || !ext->properties || !ext->num_properties) + return -EINVAL; + + guard(rwsem_write)(&psy->extensions_sem); + + power_supply_for_each_extension(reg, psy) + if (strcmp(ext->name, reg->ext->name) == 0) + return -EEXIST; + + for (i = 0; i < ext->num_properties; i++) + if (power_supply_has_property(psy, ext->properties[i])) + return -EEXIST; + + reg = kmalloc(sizeof(*reg), GFP_KERNEL); + if (!reg) + return -ENOMEM; + + reg->ext = ext; + reg->dev = dev; + reg->data = data; + list_add(®->list_head, &psy->extensions); + + ret = power_supply_sysfs_add_extension(psy, ext, dev); + if (ret) + goto sysfs_add_failed; + + ret = power_supply_update_sysfs_and_hwmon(psy); + if (ret) + goto sysfs_hwmon_failed; + + return 0; + +sysfs_hwmon_failed: + power_supply_sysfs_remove_extension(psy, ext); +sysfs_add_failed: + list_del(®->list_head); + kfree(reg); + return ret; +} +EXPORT_SYMBOL_GPL(power_supply_register_extension); + +void power_supply_unregister_extension(struct power_supply *psy, const struct power_supply_ext *ext) +{ + struct power_supply_ext_registration *reg; + + guard(rwsem_write)(&psy->extensions_sem); + + power_supply_for_each_extension(reg, psy) { + if (reg->ext == ext) { + list_del(®->list_head); + power_supply_sysfs_remove_extension(psy, ext); + kfree(reg); + power_supply_update_sysfs_and_hwmon(psy); + return; + } + } + + dev_warn(&psy->dev, "Trying to unregister invalid extension"); +} +EXPORT_SYMBOL_GPL(power_supply_unregister_extension); + static void power_supply_dev_release(struct device *dev) { struct power_supply *psy = to_power_supply(dev); @@ -1300,7 +1475,7 @@ static int psy_register_thermal(struct power_supply *psy) return 0; /* Register battery zone device psy reports temperature */ - if (psy_has_property(psy->desc, POWER_SUPPLY_PROP_TEMP)) { + if (psy_desc_has_property(psy->desc, POWER_SUPPLY_PROP_TEMP)) { /* Prefer our hwmon device and avoid duplicates */ struct thermal_zone_params tzp = { .no_hwmon = IS_ENABLED(CONFIG_POWER_SUPPLY_HWMON) @@ -1402,6 +1577,9 @@ __power_supply_register(struct device *parent, } spin_lock_init(&psy->changed_lock); + init_rwsem(&psy->extensions_sem); + INIT_LIST_HEAD(&psy->extensions); + rc = device_add(dev); if (rc) goto device_add_failed; @@ -1414,13 +1592,15 @@ __power_supply_register(struct device *parent, if (rc) goto register_thermal_failed; - rc = power_supply_create_triggers(psy); - if (rc) - goto create_triggers_failed; + scoped_guard(rwsem_read, &psy->extensions_sem) { + rc = power_supply_create_triggers(psy); + if (rc) + goto create_triggers_failed; - rc = power_supply_add_hwmon_sysfs(psy); - if (rc) - goto add_hwmon_sysfs_failed; + rc = power_supply_add_hwmon_sysfs(psy); + if (rc) + goto add_hwmon_sysfs_failed; + } /* * Update use_cnt after any uevents (most notably from device_add()). diff --git a/drivers/power/supply/power_supply_hwmon.c b/drivers/power/supply/power_supply_hwmon.c index 01be04903d7d..95245e6a6baa 100644 --- a/drivers/power/supply/power_supply_hwmon.c +++ b/drivers/power/supply/power_supply_hwmon.c @@ -349,9 +349,28 @@ static const struct hwmon_chip_info power_supply_hwmon_chip_info = { .info = power_supply_hwmon_info, }; +static const enum power_supply_property power_supply_hwmon_props[] = { + POWER_SUPPLY_PROP_CURRENT_AVG, + POWER_SUPPLY_PROP_CURRENT_MAX, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_POWER_AVG, + POWER_SUPPLY_PROP_POWER_NOW, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_TEMP_MAX, + POWER_SUPPLY_PROP_TEMP_MIN, + POWER_SUPPLY_PROP_TEMP_ALERT_MIN, + POWER_SUPPLY_PROP_TEMP_ALERT_MAX, + POWER_SUPPLY_PROP_TEMP_AMBIENT, + POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN, + POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX, + POWER_SUPPLY_PROP_VOLTAGE_AVG, + POWER_SUPPLY_PROP_VOLTAGE_MIN, + POWER_SUPPLY_PROP_VOLTAGE_MAX, + POWER_SUPPLY_PROP_VOLTAGE_NOW, +}; + int power_supply_add_hwmon_sysfs(struct power_supply *psy) { - const struct power_supply_desc *desc = psy->desc; struct power_supply_hwmon *psyhw; struct device *dev = &psy->dev; struct device *hwmon; @@ -377,32 +396,11 @@ int power_supply_add_hwmon_sysfs(struct power_supply *psy) goto error; } - for (i = 0; i < desc->num_properties; i++) { - const enum power_supply_property prop = desc->properties[i]; + for (i = 0; i < ARRAY_SIZE(power_supply_hwmon_props); i++) { + const enum power_supply_property prop = power_supply_hwmon_props[i]; - switch (prop) { - case POWER_SUPPLY_PROP_CURRENT_AVG: - case POWER_SUPPLY_PROP_CURRENT_MAX: - case POWER_SUPPLY_PROP_CURRENT_NOW: - case POWER_SUPPLY_PROP_POWER_AVG: - case POWER_SUPPLY_PROP_POWER_NOW: - case POWER_SUPPLY_PROP_TEMP: - case POWER_SUPPLY_PROP_TEMP_MAX: - case POWER_SUPPLY_PROP_TEMP_MIN: - case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: - case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: - case POWER_SUPPLY_PROP_TEMP_AMBIENT: - case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN: - case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX: - case POWER_SUPPLY_PROP_VOLTAGE_AVG: - case POWER_SUPPLY_PROP_VOLTAGE_MIN: - case POWER_SUPPLY_PROP_VOLTAGE_MAX: - case POWER_SUPPLY_PROP_VOLTAGE_NOW: + if (power_supply_has_property(psy, prop)) set_bit(prop, psyhw->props); - break; - default: - break; - } } name = psy->desc->name; diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index 571de43fcca9..edb058c19c9c 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -99,6 +99,7 @@ static const char * const POWER_SUPPLY_HEALTH_TEXT[] = { [POWER_SUPPLY_HEALTH_OVERHEAT] = "Overheat", [POWER_SUPPLY_HEALTH_DEAD] = "Dead", [POWER_SUPPLY_HEALTH_OVERVOLTAGE] = "Over voltage", + [POWER_SUPPLY_HEALTH_UNDERVOLTAGE] = "Under voltage", [POWER_SUPPLY_HEALTH_UNSPEC_FAILURE] = "Unspecified failure", [POWER_SUPPLY_HEALTH_COLD] = "Cold", [POWER_SUPPLY_HEALTH_WATCHDOG_TIMER_EXPIRE] = "Watchdog timer expire", @@ -182,6 +183,8 @@ static struct power_supply_attr power_supply_attrs[] __ro_after_init = { POWER_SUPPLY_ATTR(CHARGE_CONTROL_START_THRESHOLD), POWER_SUPPLY_ATTR(CHARGE_CONTROL_END_THRESHOLD), POWER_SUPPLY_ENUM_ATTR(CHARGE_BEHAVIOUR), + /* Same enum value texts as "charge_type" without the 's' at the end */ + _POWER_SUPPLY_ENUM_ATTR(CHARGE_TYPES, POWER_SUPPLY_CHARGE_TYPE_TEXT), POWER_SUPPLY_ATTR(INPUT_CURRENT_LIMIT), POWER_SUPPLY_ATTR(INPUT_VOLTAGE_LIMIT), POWER_SUPPLY_ATTR(INPUT_POWER_LIMIT), @@ -237,23 +240,52 @@ static enum power_supply_property dev_attr_psp(struct device_attribute *attr) return to_ps_attr(attr) - power_supply_attrs; } +static void power_supply_escape_spaces(const char *str, char *buf, size_t bufsize) +{ + strscpy(buf, str, bufsize); + strreplace(buf, ' ', '_'); +} + +static int power_supply_match_string(const char * const *array, size_t n, const char *s) +{ + int ret; + + /* First try an exact match */ + ret = __sysfs_match_string(array, n, s); + if (ret >= 0) + return ret; + + /* Second round, try matching with spaces replaced by '_' */ + for (size_t i = 0; i < n; i++) { + char buf[32]; + + power_supply_escape_spaces(array[i], buf, sizeof(buf)); + if (sysfs_streq(buf, s)) + return i; + } + + return -EINVAL; +} + static ssize_t power_supply_show_enum_with_available( struct device *dev, const char * const labels[], int label_count, unsigned int available_values, int value, char *buf) { bool match = false, available, active; + char escaped_label[32]; ssize_t count = 0; int i; for (i = 0; i < label_count; i++) { available = available_values & BIT(i); active = i == value; + power_supply_escape_spaces(labels[i], escaped_label, sizeof(escaped_label)); if (available && active) { - count += sysfs_emit_at(buf, count, "[%s] ", labels[i]); + count += sysfs_emit_at(buf, count, "[%s] ", escaped_label); match = true; } else if (available) { - count += sysfs_emit_at(buf, count, "%s ", labels[i]); + count += sysfs_emit_at(buf, count, "%s ", escaped_label); } } @@ -268,11 +300,34 @@ static ssize_t power_supply_show_enum_with_available( return count; } -static ssize_t power_supply_show_property(struct device *dev, - struct device_attribute *attr, - char *buf) { +static ssize_t power_supply_show_charge_behaviour(struct device *dev, + struct power_supply *psy, + union power_supply_propval *value, + char *buf) +{ + struct power_supply_ext_registration *reg; + + scoped_guard(rwsem_read, &psy->extensions_sem) { + power_supply_for_each_extension(reg, psy) { + if (power_supply_ext_has_property(reg->ext, + POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR)) + return power_supply_charge_behaviour_show(dev, + reg->ext->charge_behaviours, + value->intval, buf); + } + } + + return power_supply_charge_behaviour_show(dev, psy->desc->charge_behaviours, + value->intval, buf); +} + +static ssize_t power_supply_format_property(struct device *dev, + bool uevent, + struct device_attribute *attr, + char *buf) +{ ssize_t ret; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); const struct power_supply_attr *ps_attr = to_ps_attr(attr); enum power_supply_property psp = dev_attr_psp(attr); union power_supply_propval value; @@ -287,7 +342,7 @@ static ssize_t power_supply_show_property(struct device *dev, dev_dbg_ratelimited(dev, "driver has no data for `%s' property\n", attr->attr.name); - else if (ret != -ENODEV && ret != -EAGAIN) + else if (ret != -ENODEV && ret != -EAGAIN && ret != -EINVAL) dev_err_ratelimited(dev, "driver failed to report `%s' property: %zd\n", attr->attr.name, ret); @@ -303,13 +358,21 @@ static ssize_t power_supply_show_property(struct device *dev, psy->desc->usb_types, value.intval, buf); break; case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR: - ret = power_supply_charge_behaviour_show(dev, psy->desc->charge_behaviours, - value.intval, buf); + if (uevent) /* no possible values in uevents */ + goto default_format; + ret = power_supply_show_charge_behaviour(dev, psy, &value, buf); + break; + case POWER_SUPPLY_PROP_CHARGE_TYPES: + if (uevent) /* no possible values in uevents */ + goto default_format; + ret = power_supply_charge_types_show(dev, psy->desc->charge_types, + value.intval, buf); break; case POWER_SUPPLY_PROP_MODEL_NAME ... POWER_SUPPLY_PROP_SERIAL_NUMBER: ret = sysfs_emit(buf, "%s\n", value.strval); break; default: +default_format: if (ps_attr->text_values_len > 0 && value.intval < ps_attr->text_values_len && value.intval >= 0) { ret = sysfs_emit(buf, "%s\n", ps_attr->text_values[value.intval]); @@ -321,19 +384,26 @@ static ssize_t power_supply_show_property(struct device *dev, return ret; } +static ssize_t power_supply_show_property(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return power_supply_format_property(dev, false, attr, buf); +} + static ssize_t power_supply_store_property(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { ssize_t ret; - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); const struct power_supply_attr *ps_attr = to_ps_attr(attr); enum power_supply_property psp = dev_attr_psp(attr); union power_supply_propval value; ret = -EINVAL; if (ps_attr->text_values_len > 0) { - ret = __sysfs_match_string(ps_attr->text_values, - ps_attr->text_values_len, buf); + ret = power_supply_match_string(ps_attr->text_values, + ps_attr->text_values_len, buf); } /* @@ -364,9 +434,8 @@ static umode_t power_supply_attr_is_visible(struct kobject *kobj, int attrno) { struct device *dev = kobj_to_dev(kobj); - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); umode_t mode = S_IRUSR | S_IRGRP | S_IROTH; - int i; if (!power_supply_attrs[attrno].prop_name) return 0; @@ -374,19 +443,13 @@ static umode_t power_supply_attr_is_visible(struct kobject *kobj, if (attrno == POWER_SUPPLY_PROP_TYPE) return mode; - for (i = 0; i < psy->desc->num_properties; i++) { - int property = psy->desc->properties[i]; + guard(rwsem_read)(&psy->extensions_sem); - if (property == attrno) { - if (power_supply_property_is_writeable(psy, property) > 0) - mode |= S_IWUSR; - - return mode; - } - } - - if (power_supply_battery_info_has_prop(psy->battery_info, attrno)) + if (power_supply_has_property(psy, attrno)) { + if (power_supply_property_is_writeable(psy, attrno) > 0) + mode |= S_IWUSR; return mode; + } return 0; } @@ -396,8 +459,18 @@ static const struct attribute_group power_supply_attr_group = { .is_visible = power_supply_attr_is_visible, }; +static struct attribute *power_supply_extension_attrs[] = { + NULL +}; + +static const struct attribute_group power_supply_extension_group = { + .name = "extensions", + .attrs = power_supply_extension_attrs, +}; + const struct attribute_group *power_supply_attr_groups[] = { &power_supply_attr_group, + &power_supply_extension_group, NULL }; @@ -437,8 +510,8 @@ static int add_prop_uevent(const struct device *dev, struct kobj_uevent_env *env pwr_attr = &power_supply_attrs[prop]; dev_attr = &pwr_attr->dev_attr; - ret = power_supply_show_property((struct device *)dev, dev_attr, prop_buf); - if (ret == -ENODEV || ret == -ENODATA) { + ret = power_supply_format_property((struct device *)dev, true, dev_attr, prop_buf); + if (ret == -ENODEV || ret == -ENODATA || ret == -EINVAL) { /* * When a battery is absent, we expect -ENODEV. Don't abort; * send the uevent with at least the PRESENT=0 property @@ -459,11 +532,7 @@ static int add_prop_uevent(const struct device *dev, struct kobj_uevent_env *env int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env) { - const struct power_supply *psy = dev_get_drvdata(dev); - const enum power_supply_property *battery_props = - power_supply_battery_info_properties; - unsigned long psy_drv_properties[POWER_SUPPLY_ATTR_CNT / - sizeof(unsigned long) + 1] = {0}; + const struct power_supply *psy = dev_to_psy(dev); int ret = 0, j; char *prop_buf; @@ -491,22 +560,8 @@ int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env) if (ret) goto out; - for (j = 0; j < psy->desc->num_properties; j++) { - set_bit(psy->desc->properties[j], psy_drv_properties); - ret = add_prop_uevent(dev, env, psy->desc->properties[j], - prop_buf); - if (ret) - goto out; - } - - for (j = 0; j < power_supply_battery_info_properties_size; j++) { - if (test_bit(battery_props[j], psy_drv_properties)) - continue; - if (!power_supply_battery_info_has_prop(psy->battery_info, - battery_props[j])) - continue; - ret = add_prop_uevent(dev, env, battery_props[j], - prop_buf); + for (j = 0; j < POWER_SUPPLY_ATTR_CNT; j++) { + ret = add_prop_uevent(dev, env, j, prop_buf); if (ret) goto out; } @@ -542,3 +597,44 @@ int power_supply_charge_behaviour_parse(unsigned int available_behaviours, const return -EINVAL; } EXPORT_SYMBOL_GPL(power_supply_charge_behaviour_parse); + +ssize_t power_supply_charge_types_show(struct device *dev, + unsigned int available_types, + enum power_supply_charge_type current_type, + char *buf) +{ + return power_supply_show_enum_with_available( + dev, POWER_SUPPLY_CHARGE_TYPE_TEXT, + ARRAY_SIZE(POWER_SUPPLY_CHARGE_TYPE_TEXT), + available_types, current_type, buf); +} +EXPORT_SYMBOL_GPL(power_supply_charge_types_show); + +int power_supply_charge_types_parse(unsigned int available_types, const char *buf) +{ + int i = power_supply_match_string(POWER_SUPPLY_CHARGE_TYPE_TEXT, + ARRAY_SIZE(POWER_SUPPLY_CHARGE_TYPE_TEXT), + buf); + + if (i < 0) + return i; + + if (available_types & BIT(i)) + return i; + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(power_supply_charge_types_parse); + +int power_supply_sysfs_add_extension(struct power_supply *psy, const struct power_supply_ext *ext, + struct device *dev) +{ + return sysfs_add_link_to_group(&psy->dev.kobj, power_supply_extension_group.name, + &dev->kobj, ext->name); +} + +void power_supply_sysfs_remove_extension(struct power_supply *psy, + const struct power_supply_ext *ext) +{ + sysfs_remove_link_from_group(&psy->dev.kobj, power_supply_extension_group.name, ext->name); +} diff --git a/drivers/power/supply/sbs-battery.c b/drivers/power/supply/sbs-battery.c index a6c204c08232..6f3d0413b1c1 100644 --- a/drivers/power/supply/sbs-battery.c +++ b/drivers/power/supply/sbs-battery.c @@ -21,6 +21,7 @@ #include #include #include +#include enum { REG_MANUFACTURER_DATA, @@ -320,8 +321,8 @@ static int sbs_update_presence(struct sbs_info *chip, bool is_present) client->flags &= ~I2C_CLIENT_PEC; } - dev_dbg(&client->dev, "PEC: %s\n", (client->flags & I2C_CLIENT_PEC) ? - "enabled" : "disabled"); + dev_dbg(&client->dev, "PEC: %s\n", + str_enabled_disabled(client->flags & I2C_CLIENT_PEC)); if (!chip->is_present && is_present && !chip->charger_broadcasts) sbs_disable_charger_broadcasts(chip); diff --git a/drivers/power/supply/stc3117_fuel_gauge.c b/drivers/power/supply/stc3117_fuel_gauge.c new file mode 100644 index 000000000000..a1bc5970370a --- /dev/null +++ b/drivers/power/supply/stc3117_fuel_gauge.c @@ -0,0 +1,612 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * stc3117_fuel_gauge.c - STMicroelectronics STC3117 Fuel Gauge Driver + * + * Copyright (c) 2024 Silicon Signals Pvt Ltd. + * Author: Hardevsinh Palaniya + * Bhavin Sharma + */ + +#include +#include +#include +#include +#include +#include + +#define STC3117_ADDR_MODE 0x00 +#define STC3117_ADDR_CTRL 0x01 +#define STC3117_ADDR_SOC_L 0x02 +#define STC3117_ADDR_SOC_H 0x03 +#define STC3117_ADDR_COUNTER_L 0x04 +#define STC3117_ADDR_COUNTER_H 0x05 +#define STC3117_ADDR_CURRENT_L 0x06 +#define STC3117_ADDR_CURRENT_H 0x07 +#define STC3117_ADDR_VOLTAGE_L 0x08 +#define STC3117_ADDR_VOLTAGE_H 0x09 +#define STC3117_ADDR_TEMPERATURE 0x0A +#define STC3117_ADDR_AVG_CURRENT_L 0x0B +#define STC3117_ADDR_AVG_CURRENT_H 0x0C +#define STC3117_ADDR_OCV_L 0x0D +#define STC3117_ADDR_OCV_H 0x0E +#define STC3117_ADDR_CC_CNF_L 0x0F +#define STC3117_ADDR_CC_CNF_H 0x10 +#define STC3117_ADDR_VM_CNF_L 0x11 +#define STC3117_ADDR_VM_CNF_H 0x12 +#define STC3117_ADDR_ALARM_soc 0x13 +#define STC3117_ADDR_ALARM_VOLTAGE 0x14 +#define STC3117_ADDR_ID 0x18 +#define STC3117_ADDR_CC_ADJ_L 0x1B +#define STC3117_ADDR_CC_ADJ_H 0x1C +#define STC3117_ADDR_VM_ADJ_L 0x1D +#define STC3117_ADDR_VM_ADJ_H 0x1E +#define STC3117_ADDR_RAM 0x20 +#define STC3117_ADDR_OCV_TABLE 0x30 +#define STC3117_ADDR_SOC_TABLE 0x30 + +/* Bit mask definition */ +#define STC3117_ID 0x16 +#define STC3117_MIXED_MODE 0x00 +#define STC3117_VMODE BIT(0) +#define STC3117_GG_RUN BIT(4) +#define STC3117_CC_MODE BIT(5) +#define STC3117_BATFAIL BIT(3) +#define STC3117_PORDET BIT(4) +#define STC3117_RAM_SIZE 16 +#define STC3117_OCV_TABLE_SIZE 16 +#define STC3117_RAM_TESTWORD 0x53A9 +#define STC3117_SOFT_RESET 0x11 +#define STC3117_NOMINAL_CAPACITY 2600 + +#define VOLTAGE_LSB_VALUE 9011 +#define CURRENT_LSB_VALUE 24084 +#define APP_CUTOFF_VOLTAGE 2500 +#define MAX_HRSOC 51200 +#define MAX_SOC 1000 +#define CHG_MIN_CURRENT 200 +#define CHG_END_CURRENT 20 +#define APP_MIN_CURRENT (-5) +#define BATTERY_FULL 95 +#define CRC8_POLYNOMIAL 0x07 +#define CRC8_INIT 0x00 + +DECLARE_CRC8_TABLE(stc3117_crc_table); + +enum stc3117_state { + STC3117_INIT, + STC3117_RUNNING, + STC3117_POWERDN, +}; + +/* Default ocv curve Li-ion battery */ +static const int ocv_value[16] = { + 3400, 3582, 3669, 3676, 3699, 3737, 3757, 3774, + 3804, 3844, 3936, 3984, 4028, 4131, 4246, 4320 +}; + +union stc3117_internal_ram { + u8 ram_bytes[STC3117_RAM_SIZE]; + struct { + u16 testword; /* 0-1 Bytes */ + u16 hrsoc; /* 2-3 Bytes */ + u16 cc_cnf; /* 4-5 Bytes */ + u16 vm_cnf; /* 6-7 Bytes */ + u8 soc; /* 8 Byte */ + u8 state; /* 9 Byte */ + u8 unused[5]; /* 10-14 Bytes */ + u8 crc; /* 15 Byte */ + } reg; +}; + +struct stc3117_battery_info { + int voltage_min_mv; + int voltage_max_mv; + int battery_capacity_mah; + int sense_resistor; +}; + +struct stc3117_data { + struct i2c_client *client; + struct regmap *regmap; + struct delayed_work update_work; + struct power_supply *battery; + union stc3117_internal_ram ram_data; + struct stc3117_battery_info battery_info; + + u8 soc_tab[16]; + int cc_cnf; + int vm_cnf; + int cc_adj; + int vm_adj; + int avg_current; + int avg_voltage; + int batt_current; + int voltage; + int temp; + int soc; + int ocv; + int hrsoc; + int presence; +}; + +static int stc3117_convert(int value, int factor) +{ + value = (value * factor) / 4096; + return value * 1000; +} + +static int stc3117_get_battery_data(struct stc3117_data *data) +{ + u8 reg_list[16]; + u8 data_adjust[4]; + int value, mode; + + regmap_bulk_read(data->regmap, STC3117_ADDR_MODE, + reg_list, sizeof(reg_list)); + + /* soc */ + value = (reg_list[3] << 8) + reg_list[2]; + data->hrsoc = value; + data->soc = (value * 10 + 256) / 512; + + /* current in uA*/ + value = (reg_list[7] << 8) + reg_list[6]; + data->batt_current = stc3117_convert(value, + CURRENT_LSB_VALUE / data->battery_info.sense_resistor); + + /* voltage in uV */ + value = (reg_list[9] << 8) + reg_list[8]; + data->voltage = stc3117_convert(value, VOLTAGE_LSB_VALUE); + + /* temp in 1/10 °C */ + data->temp = reg_list[10] * 10; + + /* Avg current in uA */ + value = (reg_list[12] << 8) + reg_list[11]; + regmap_read(data->regmap, STC3117_ADDR_MODE, &mode); + if (!(mode & STC3117_VMODE)) { + value = stc3117_convert(value, + CURRENT_LSB_VALUE / data->battery_info.sense_resistor); + value = value / 4; + } else { + value = stc3117_convert(value, 36 * STC3117_NOMINAL_CAPACITY); + } + data->avg_current = value; + + /* ocv in uV */ + value = (reg_list[14] << 8) + reg_list[13]; + value = stc3117_convert(value, VOLTAGE_LSB_VALUE); + value = (value + 2) / 4; + data->ocv = value; + + /* CC & VM adjustment counters */ + regmap_bulk_read(data->regmap, STC3117_ADDR_CC_ADJ_L, + data_adjust, sizeof(data_adjust)); + value = (data_adjust[1] << 8) + data_adjust[0]; + data->cc_adj = value; + + value = (data_adjust[3] << 8) + data_adjust[2]; + data->vm_adj = value; + + return 0; +} + +static int ram_write(struct stc3117_data *data) +{ + int ret; + + ret = regmap_bulk_write(data->regmap, STC3117_ADDR_RAM, + data->ram_data.ram_bytes, STC3117_RAM_SIZE); + if (ret) + return ret; + + return 0; +}; + +static int ram_read(struct stc3117_data *data) +{ + int ret; + + ret = regmap_bulk_read(data->regmap, STC3117_ADDR_RAM, + data->ram_data.ram_bytes, STC3117_RAM_SIZE); + if (ret) + return ret; + + return 0; +}; + +static int stc3117_set_para(struct stc3117_data *data) +{ + int ret; + + ret = regmap_write(data->regmap, STC3117_ADDR_MODE, STC3117_VMODE); + + for (int i = 0; i < STC3117_OCV_TABLE_SIZE; i++) + ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_TABLE + i, + ocv_value[i] * 100 / 55); + if (data->soc_tab[1] != 0) + ret |= regmap_bulk_write(data->regmap, STC3117_ADDR_SOC_TABLE, + data->soc_tab, STC3117_OCV_TABLE_SIZE); + + ret |= regmap_write(data->regmap, STC3117_ADDR_CC_CNF_H, + (data->ram_data.reg.cc_cnf >> 8) & 0xFF); + + ret |= regmap_write(data->regmap, STC3117_ADDR_CC_CNF_L, + data->ram_data.reg.cc_cnf & 0xFF); + + ret |= regmap_write(data->regmap, STC3117_ADDR_VM_CNF_H, + (data->ram_data.reg.vm_cnf >> 8) & 0xFF); + + ret |= regmap_write(data->regmap, STC3117_ADDR_VM_CNF_L, + data->ram_data.reg.vm_cnf & 0xFF); + + ret |= regmap_write(data->regmap, STC3117_ADDR_CTRL, 0x03); + + ret |= regmap_write(data->regmap, STC3117_ADDR_MODE, + STC3117_MIXED_MODE | STC3117_GG_RUN); + + return ret; +}; + +static int stc3117_init(struct stc3117_data *data) +{ + int id, ret; + int ctrl; + int ocv_m, ocv_l; + + regmap_read(data->regmap, STC3117_ADDR_ID, &id); + if (id != STC3117_ID) + return -EINVAL; + + data->cc_cnf = (data->battery_info.battery_capacity_mah * + data->battery_info.sense_resistor * 250 + 6194) / 12389; + data->vm_cnf = (data->battery_info.battery_capacity_mah + * 200 * 50 + 24444) / 48889; + + /* Battery has not been removed */ + data->presence = 1; + + /* Read RAM data */ + ret = ram_read(data); + if (ret) + return ret; + + if (data->ram_data.reg.testword != STC3117_RAM_TESTWORD || + (crc8(stc3117_crc_table, data->ram_data.ram_bytes, + STC3117_RAM_SIZE, CRC8_INIT)) != 0) { + data->ram_data.reg.testword = STC3117_RAM_TESTWORD; + data->ram_data.reg.cc_cnf = data->cc_cnf; + data->ram_data.reg.vm_cnf = data->vm_cnf; + data->ram_data.reg.crc = crc8(stc3117_crc_table, + data->ram_data.ram_bytes, + STC3117_RAM_SIZE - 1, CRC8_INIT); + + ret = regmap_read(data->regmap, STC3117_ADDR_OCV_H, &ocv_m); + + ret |= regmap_read(data->regmap, STC3117_ADDR_OCV_L, &ocv_l); + + ret |= stc3117_set_para(data); + + ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_H, ocv_m); + + ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_L, ocv_l); + if (ret) + return ret; + } else { + ret = regmap_read(data->regmap, STC3117_ADDR_CTRL, &ctrl); + if (ret) + return ret; + + if ((ctrl & STC3117_BATFAIL) != 0 || + (ctrl & STC3117_PORDET) != 0) { + ret = regmap_read(data->regmap, + STC3117_ADDR_OCV_H, &ocv_m); + + ret |= regmap_read(data->regmap, + STC3117_ADDR_OCV_L, &ocv_l); + + ret |= stc3117_set_para(data); + + ret |= regmap_write(data->regmap, + STC3117_ADDR_OCV_H, ocv_m); + + ret |= regmap_write(data->regmap, + STC3117_ADDR_OCV_L, ocv_l); + if (ret) + return ret; + } else { + ret = stc3117_set_para(data); + ret |= regmap_write(data->regmap, STC3117_ADDR_SOC_H, + (data->ram_data.reg.hrsoc >> 8 & 0xFF)); + ret |= regmap_write(data->regmap, STC3117_ADDR_SOC_L, + (data->ram_data.reg.hrsoc & 0xFF)); + if (ret) + return ret; + } + } + + data->ram_data.reg.state = STC3117_INIT; + data->ram_data.reg.crc = crc8(stc3117_crc_table, + data->ram_data.ram_bytes, + STC3117_RAM_SIZE - 1, CRC8_INIT); + ret = ram_write(data); + if (ret) + return ret; + + return 0; +}; + +static int stc3117_task(struct stc3117_data *data) +{ + int id, mode, ret; + int count_l, count_m; + int ocv_l, ocv_m; + + regmap_read(data->regmap, STC3117_ADDR_ID, &id); + if (id != STC3117_ID) { + data->presence = 0; + return -EINVAL; + } + + stc3117_get_battery_data(data); + + /* Read RAM data */ + ret = ram_read(data); + if (ret) + return ret; + + if (data->ram_data.reg.testword != STC3117_RAM_TESTWORD || + (crc8(stc3117_crc_table, data->ram_data.ram_bytes, + STC3117_RAM_SIZE, CRC8_INIT) != 0)) { + data->ram_data.reg.testword = STC3117_RAM_TESTWORD; + data->ram_data.reg.cc_cnf = data->cc_cnf; + data->ram_data.reg.vm_cnf = data->vm_cnf; + data->ram_data.reg.crc = crc8(stc3117_crc_table, + data->ram_data.ram_bytes, + STC3117_RAM_SIZE - 1, CRC8_INIT); + data->ram_data.reg.state = STC3117_INIT; + } + + /* check battery presence status */ + ret = regmap_read(data->regmap, STC3117_ADDR_CTRL, &mode); + if ((mode & STC3117_BATFAIL) != 0) { + data->presence = 0; + data->ram_data.reg.testword = 0; + data->ram_data.reg.state = STC3117_INIT; + ret = ram_write(data); + ret |= regmap_write(data->regmap, STC3117_ADDR_CTRL, STC3117_PORDET); + if (ret) + return ret; + } + + data->presence = 1; + + ret = regmap_read(data->regmap, STC3117_ADDR_MODE, &mode); + if (ret) + return ret; + if ((mode & STC3117_GG_RUN) == 0) { + if (data->ram_data.reg.state > STC3117_INIT) { + ret = stc3117_set_para(data); + + ret |= regmap_write(data->regmap, STC3117_ADDR_SOC_H, + (data->ram_data.reg.hrsoc >> 8 & 0xFF)); + ret |= regmap_write(data->regmap, STC3117_ADDR_SOC_L, + (data->ram_data.reg.hrsoc & 0xFF)); + if (ret) + return ret; + } else { + ret = regmap_read(data->regmap, STC3117_ADDR_OCV_H, &ocv_m); + + ret |= regmap_read(data->regmap, STC3117_ADDR_OCV_L, &ocv_l); + + ret |= stc3117_set_para(data); + + ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_H, ocv_m); + + ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_L, ocv_l); + if (ret) + return ret; + } + data->ram_data.reg.state = STC3117_INIT; + } + + regmap_read(data->regmap, STC3117_ADDR_COUNTER_L, &count_l); + regmap_read(data->regmap, STC3117_ADDR_COUNTER_H, &count_m); + + count_m = (count_m << 8) + count_l; + + /* INIT state, wait for batt_current & temperature value available: */ + if (data->ram_data.reg.state == STC3117_INIT && count_m > 4) { + data->avg_voltage = data->voltage; + data->avg_current = data->batt_current; + data->ram_data.reg.state = STC3117_RUNNING; + } + + if (data->ram_data.reg.state != STC3117_RUNNING) { + data->batt_current = -ENODATA; + data->temp = -ENODATA; + } else { + if (data->voltage < APP_CUTOFF_VOLTAGE) + data->soc = -ENODATA; + + if (mode & STC3117_VMODE) { + data->avg_current = -ENODATA; + data->batt_current = -ENODATA; + } + } + + data->ram_data.reg.hrsoc = data->hrsoc; + data->ram_data.reg.soc = (data->soc + 5) / 10; + data->ram_data.reg.crc = crc8(stc3117_crc_table, + data->ram_data.ram_bytes, + STC3117_RAM_SIZE - 1, CRC8_INIT); + + ret = ram_write(data); + if (ret) + return ret; + return 0; +}; + +static void fuel_gauge_update_work(struct work_struct *work) +{ + struct stc3117_data *data = + container_of(work, struct stc3117_data, update_work.work); + + stc3117_task(data); + + /* Schedule the work to run again in 2 seconds */ + schedule_delayed_work(&data->update_work, msecs_to_jiffies(2000)); +} + +static int stc3117_get_property(struct power_supply *psy, + enum power_supply_property psp, union power_supply_propval *val) +{ + struct stc3117_data *data = power_supply_get_drvdata(psy); + + switch (psp) { + case POWER_SUPPLY_PROP_STATUS: + if (data->soc > BATTERY_FULL) + val->intval = POWER_SUPPLY_STATUS_FULL; + else if (data->batt_current < 0) + val->intval = POWER_SUPPLY_STATUS_CHARGING; + else if (data->batt_current > 0) + val->intval = POWER_SUPPLY_STATUS_DISCHARGING; + else + val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING; + break; + case POWER_SUPPLY_PROP_VOLTAGE_NOW: + val->intval = data->voltage; + break; + case POWER_SUPPLY_PROP_CURRENT_NOW: + val->intval = data->batt_current; + break; + case POWER_SUPPLY_PROP_VOLTAGE_OCV: + val->intval = data->ocv; + break; + case POWER_SUPPLY_PROP_CURRENT_AVG: + val->intval = data->avg_current; + break; + case POWER_SUPPLY_PROP_CAPACITY: + val->intval = data->soc; + break; + case POWER_SUPPLY_PROP_TEMP: + val->intval = data->temp; + break; + case POWER_SUPPLY_PROP_PRESENT: + val->intval = data->presence; + break; + default: + return -EINVAL; + } + return 0; +} + +static enum power_supply_property stc3117_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_VOLTAGE_OCV, + POWER_SUPPLY_PROP_CURRENT_AVG, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_PRESENT, +}; + +static const struct power_supply_desc stc3117_battery_desc = { + .name = "stc3117-battery", + .type = POWER_SUPPLY_TYPE_BATTERY, + .get_property = stc3117_get_property, + .properties = stc3117_battery_props, + .num_properties = ARRAY_SIZE(stc3117_battery_props), +}; + +static const struct regmap_config stc3117_regmap_config = { + .reg_bits = 8, + .val_bits = 8, +}; + +static int stc3117_probe(struct i2c_client *client) +{ + struct stc3117_data *data; + struct power_supply_config psy_cfg = {}; + struct power_supply_battery_info *info; + int ret; + + data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->client = client; + data->regmap = devm_regmap_init_i2c(client, &stc3117_regmap_config); + if (IS_ERR(data->regmap)) + return PTR_ERR(data->regmap); + + psy_cfg.drv_data = data; + psy_cfg.fwnode = dev_fwnode(&client->dev); + + crc8_populate_msb(stc3117_crc_table, CRC8_POLYNOMIAL); + + data->battery = devm_power_supply_register(&client->dev, + &stc3117_battery_desc, &psy_cfg); + if (IS_ERR(data->battery)) + return dev_err_probe(&client->dev, PTR_ERR(data->battery), + "failed to register battery\n"); + + ret = device_property_read_u32(&client->dev, "shunt-resistor-micro-ohms", + &data->battery_info.sense_resistor); + if (ret) + return dev_err_probe(&client->dev, ret, + "failed to get shunt-resistor-micro-ohms\n"); + data->battery_info.sense_resistor = data->battery_info.sense_resistor / 1000; + + ret = power_supply_get_battery_info(data->battery, &info); + if (ret) + return dev_err_probe(&client->dev, ret, + "failed to get battery information\n"); + + data->battery_info.battery_capacity_mah = info->charge_full_design_uah / 1000; + data->battery_info.voltage_min_mv = info->voltage_min_design_uv / 1000; + data->battery_info.voltage_max_mv = info->voltage_max_design_uv / 1000; + + ret = stc3117_init(data); + if (ret) + return dev_err_probe(&client->dev, ret, + "failed to initialize of stc3117\n"); + + ret = devm_delayed_work_autocancel(&client->dev, &data->update_work, + fuel_gauge_update_work); + if (ret) + return ret; + + schedule_delayed_work(&data->update_work, 0); + + return 0; +} + +static const struct i2c_device_id stc3117_id[] = { + { "stc3117", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, stc3117_id); + +static const struct of_device_id stc3117_of_match[] = { + { .compatible = "st,stc3117" }, + { } +}; +MODULE_DEVICE_TABLE(of, stc3117_of_match); + +static struct i2c_driver stc3117_i2c_driver = { + .driver = { + .name = "stc3117_i2c_driver", + .of_match_table = stc3117_of_match, + }, + .probe = stc3117_probe, + .id_table = stc3117_id, +}; + +module_i2c_driver(stc3117_i2c_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Hardevsinh Palaniya "); +MODULE_AUTHOR("Bhavin Sharma "); +MODULE_DESCRIPTION("STC3117 Fuel Gauge Driver"); diff --git a/drivers/power/supply/surface_battery.c b/drivers/power/supply/surface_battery.c index ebd1edde28f1..c759add4df49 100644 --- a/drivers/power/supply/surface_battery.c +++ b/drivers/power/supply/surface_battery.c @@ -667,7 +667,7 @@ out: static ssize_t alarm_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct spwr_battery_device *bat = power_supply_get_drvdata(psy); int status; @@ -681,7 +681,7 @@ static ssize_t alarm_show(struct device *dev, struct device_attribute *attr, cha static ssize_t alarm_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct power_supply *psy = dev_get_drvdata(dev); + struct power_supply *psy = dev_to_psy(dev); struct spwr_battery_device *bat = power_supply_get_drvdata(psy); unsigned long value; int status; diff --git a/drivers/power/supply/test_power.c b/drivers/power/supply/test_power.c index 442ceb7795e1..2a975a110f48 100644 --- a/drivers/power/supply/test_power.c +++ b/drivers/power/supply/test_power.c @@ -37,6 +37,7 @@ static int battery_charge_counter = -1000; static int battery_current = -1600; static enum power_supply_charge_behaviour battery_charge_behaviour = POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO; +static bool battery_extension; static bool module_initialized; @@ -238,6 +239,87 @@ static const struct power_supply_config test_power_configs[] = { }, }; +static int test_power_battery_extmanufacture_year = 1234; +static int test_power_battery_exttemp_max = 1000; +static const enum power_supply_property test_power_battery_extprops[] = { + POWER_SUPPLY_PROP_MANUFACTURE_YEAR, + POWER_SUPPLY_PROP_TEMP_MAX, +}; + +static int test_power_battery_extget_property(struct power_supply *psy, + const struct power_supply_ext *ext, + void *ext_data, + enum power_supply_property psp, + union power_supply_propval *val) +{ + switch (psp) { + case POWER_SUPPLY_PROP_MANUFACTURE_YEAR: + val->intval = test_power_battery_extmanufacture_year; + break; + case POWER_SUPPLY_PROP_TEMP_MAX: + val->intval = test_power_battery_exttemp_max; + break; + default: + return -EINVAL; + } + return 0; +} + +static int test_power_battery_extset_property(struct power_supply *psy, + const struct power_supply_ext *ext, + void *ext_data, + enum power_supply_property psp, + const union power_supply_propval *val) +{ + switch (psp) { + case POWER_SUPPLY_PROP_MANUFACTURE_YEAR: + test_power_battery_extmanufacture_year = val->intval; + break; + case POWER_SUPPLY_PROP_TEMP_MAX: + test_power_battery_exttemp_max = val->intval; + break; + default: + return -EINVAL; + } + return 0; +} + +static int test_power_battery_extproperty_is_writeable(struct power_supply *psy, + const struct power_supply_ext *ext, + void *ext_data, + enum power_supply_property psp) +{ + return true; +} + +static const struct power_supply_ext test_power_battery_ext = { + .name = "test_power", + .properties = test_power_battery_extprops, + .num_properties = ARRAY_SIZE(test_power_battery_extprops), + .get_property = test_power_battery_extget_property, + .set_property = test_power_battery_extset_property, + .property_is_writeable = test_power_battery_extproperty_is_writeable, +}; + +static void test_power_configure_battery_extension(bool enable) +{ + struct power_supply *psy; + + psy = test_power_supplies[TEST_BATTERY]; + + if (enable) { + if (power_supply_register_extension(psy, &test_power_battery_ext, &psy->dev, + NULL)) { + pr_err("registering battery extension failed\n"); + return; + } + } else { + power_supply_unregister_extension(psy, &test_power_battery_ext); + } + + battery_extension = enable; +} + static int __init test_power_init(void) { int i; @@ -258,6 +340,8 @@ static int __init test_power_init(void) } } + test_power_configure_battery_extension(true); + module_initialized = true; return 0; failed: @@ -524,6 +608,26 @@ static int param_set_battery_current(const char *key, #define param_get_battery_current param_get_int +static int param_set_battery_extension(const char *key, + const struct kernel_param *kp) +{ + bool prev_battery_extension; + int ret; + + prev_battery_extension = battery_extension; + + ret = param_set_bool(key, kp); + if (ret) + return ret; + + if (prev_battery_extension != battery_extension) + test_power_configure_battery_extension(battery_extension); + + return 0; +} + +#define param_get_battery_extension param_get_bool + static const struct kernel_param_ops param_ops_ac_online = { .set = param_set_ac_online, .get = param_get_ac_online, @@ -574,6 +678,11 @@ static const struct kernel_param_ops param_ops_battery_current = { .get = param_get_battery_current, }; +static const struct kernel_param_ops param_ops_battery_extension = { + .set = param_set_battery_extension, + .get = param_get_battery_extension, +}; + #define param_check_ac_online(name, p) __param_check(name, p, void); #define param_check_usb_online(name, p) __param_check(name, p, void); #define param_check_battery_status(name, p) __param_check(name, p, void); @@ -584,6 +693,7 @@ static const struct kernel_param_ops param_ops_battery_current = { #define param_check_battery_voltage(name, p) __param_check(name, p, void); #define param_check_battery_charge_counter(name, p) __param_check(name, p, void); #define param_check_battery_current(name, p) __param_check(name, p, void); +#define param_check_battery_extension(name, p) __param_check(name, p, void); module_param(ac_online, ac_online, 0644); @@ -621,6 +731,9 @@ MODULE_PARM_DESC(battery_charge_counter, module_param(battery_current, battery_current, 0644); MODULE_PARM_DESC(battery_current, "battery current (milliampere)"); +module_param(battery_extension, battery_extension, 0644); +MODULE_PARM_DESC(battery_extension, "battery extension"); + MODULE_DESCRIPTION("Power supply driver for testing"); MODULE_AUTHOR("Anton Vorontsov "); MODULE_LICENSE("GPL"); diff --git a/drivers/power/supply/ug3105_battery.c b/drivers/power/supply/ug3105_battery.c index ccc5c4d2e230..38e23bdd4603 100644 --- a/drivers/power/supply/ug3105_battery.c +++ b/drivers/power/supply/ug3105_battery.c @@ -287,7 +287,6 @@ out: static enum power_supply_property ug3105_battery_props[] = { POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_PRESENT, - POWER_SUPPLY_PROP_TECHNOLOGY, POWER_SUPPLY_PROP_SCOPE, POWER_SUPPLY_PROP_VOLTAGE_NOW, POWER_SUPPLY_PROP_VOLTAGE_OCV, @@ -316,9 +315,6 @@ static int ug3105_get_property(struct power_supply *psy, case POWER_SUPPLY_PROP_PRESENT: val->intval = 1; break; - case POWER_SUPPLY_PROP_TECHNOLOGY: - val->intval = chip->info->technology; - break; case POWER_SUPPLY_PROP_SCOPE: val->intval = POWER_SUPPLY_SCOPE_SYSTEM; break; diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 5e793b80fd6b..77d75e1f14a9 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1265,6 +1265,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &rapl_defaults_spr_server), X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &rapl_defaults_spr_server), X86_MATCH_VFM(INTEL_LUNARLAKE_M, &rapl_defaults_core), + X86_MATCH_VFM(INTEL_PANTHERLAKE_L, &rapl_defaults_core), X86_MATCH_VFM(INTEL_ARROWLAKE_H, &rapl_defaults_core), X86_MATCH_VFM(INTEL_ARROWLAKE, &rapl_defaults_core), X86_MATCH_VFM(INTEL_ARROWLAKE_U, &rapl_defaults_core), diff --git a/drivers/pps/Makefile b/drivers/pps/Makefile index ceaf65cc1f1d..0aea394d4e4d 100644 --- a/drivers/pps/Makefile +++ b/drivers/pps/Makefile @@ -6,6 +6,7 @@ pps_core-y := pps.o kapi.o sysfs.o pps_core-$(CONFIG_NTP_PPS) += kc.o obj-$(CONFIG_PPS) := pps_core.o -obj-y += clients/ generators/ +obj-y += clients/ +obj-$(CONFIG_PPS_GENERATOR) += generators/ ccflags-$(CONFIG_PPS_DEBUG) := -DDEBUG diff --git a/drivers/pps/clients/pps-gpio.c b/drivers/pps/clients/pps-gpio.c index 634c3b2f8c26..75c1bae30a7c 100644 --- a/drivers/pps/clients/pps-gpio.c +++ b/drivers/pps/clients/pps-gpio.c @@ -52,7 +52,9 @@ static irqreturn_t pps_gpio_irq_handler(int irq, void *data) info = data; - rising_edge = gpiod_get_value(info->gpio_pin); + /* Small trick to bypass the check on edge's direction when capture_clear is unset */ + rising_edge = info->capture_clear ? + gpiod_get_value(info->gpio_pin) : !info->assert_falling_edge; if ((rising_edge && !info->assert_falling_edge) || (!rising_edge && info->assert_falling_edge)) pps_event(info->pps, &ts, PPS_CAPTUREASSERT, data); @@ -60,6 +62,8 @@ static irqreturn_t pps_gpio_irq_handler(int irq, void *data) ((rising_edge && info->assert_falling_edge) || (!rising_edge && !info->assert_falling_edge))) pps_event(info->pps, &ts, PPS_CAPTURECLEAR, data); + else + dev_warn_ratelimited(&info->pps->dev, "IRQ did not trigger any PPS event\n"); return IRQ_HANDLED; } @@ -214,8 +218,8 @@ static int pps_gpio_probe(struct platform_device *pdev) return -EINVAL; } - dev_info(data->pps->dev, "Registered IRQ %d as PPS source\n", - data->irq); + dev_dbg(&data->pps->dev, "Registered IRQ %d as PPS source\n", + data->irq); return 0; } diff --git a/drivers/pps/clients/pps-ktimer.c b/drivers/pps/clients/pps-ktimer.c index d33106bd7a29..2f465549b843 100644 --- a/drivers/pps/clients/pps-ktimer.c +++ b/drivers/pps/clients/pps-ktimer.c @@ -56,7 +56,7 @@ static struct pps_source_info pps_ktimer_info = { static void __exit pps_ktimer_exit(void) { - dev_info(pps->dev, "ktimer PPS source unregistered\n"); + dev_dbg(&pps->dev, "ktimer PPS source unregistered\n"); del_timer_sync(&ktimer); pps_unregister_source(pps); @@ -74,7 +74,7 @@ static int __init pps_ktimer_init(void) timer_setup(&ktimer, pps_ktimer_event, 0); mod_timer(&ktimer, jiffies + HZ); - dev_info(pps->dev, "ktimer PPS source registered\n"); + dev_dbg(&pps->dev, "ktimer PPS source registered\n"); return 0; } diff --git a/drivers/pps/clients/pps-ldisc.c b/drivers/pps/clients/pps-ldisc.c index 443d6bae19d1..fa5660f3c4b7 100644 --- a/drivers/pps/clients/pps-ldisc.c +++ b/drivers/pps/clients/pps-ldisc.c @@ -32,7 +32,7 @@ static void pps_tty_dcd_change(struct tty_struct *tty, bool active) pps_event(pps, &ts, active ? PPS_CAPTUREASSERT : PPS_CAPTURECLEAR, NULL); - dev_dbg(pps->dev, "PPS %s at %lu\n", + dev_dbg(&pps->dev, "PPS %s at %lu\n", active ? "assert" : "clear", jiffies); } @@ -69,7 +69,7 @@ static int pps_tty_open(struct tty_struct *tty) goto err_unregister; } - dev_info(pps->dev, "source \"%s\" added\n", info.path); + dev_dbg(&pps->dev, "source \"%s\" added\n", info.path); return 0; @@ -89,7 +89,7 @@ static void pps_tty_close(struct tty_struct *tty) if (WARN_ON(!pps)) return; - dev_info(pps->dev, "removed\n"); + dev_info(&pps->dev, "removed\n"); pps_unregister_source(pps); } diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c index abaffb4e1c1c..24db06750297 100644 --- a/drivers/pps/clients/pps_parport.c +++ b/drivers/pps/clients/pps_parport.c @@ -81,7 +81,7 @@ static void parport_irq(void *handle) /* check the signal (no signal means the pulse is lost this time) */ if (!signal_is_set(port)) { local_irq_restore(flags); - dev_err(dev->pps->dev, "lost the signal\n"); + dev_err(&dev->pps->dev, "lost the signal\n"); goto out_assert; } @@ -98,7 +98,7 @@ static void parport_irq(void *handle) /* timeout */ dev->cw_err++; if (dev->cw_err >= CLEAR_WAIT_MAX_ERRORS) { - dev_err(dev->pps->dev, "disabled clear edge capture after %d" + dev_err(&dev->pps->dev, "disabled clear edge capture after %d" " timeouts\n", dev->cw_err); dev->cw = 0; dev->cw_err = 0; diff --git a/drivers/pps/generators/Kconfig b/drivers/pps/generators/Kconfig index d615e640fcad..cd94bf3bfaf2 100644 --- a/drivers/pps/generators/Kconfig +++ b/drivers/pps/generators/Kconfig @@ -3,7 +3,25 @@ # PPS generators configuration # -comment "PPS generators support" +menuconfig PPS_GENERATOR + tristate "PPS generators support" + help + PPS generators are special hardware which are able to produce PPS + (Pulse Per Second) signals. + + To compile this driver as a module, choose M here: the module + will be called pps_gen_core. + +if PPS_GENERATOR + +config PPS_GENERATOR_DUMMY + tristate "Dummy PPS generator (Testing generator, use for debug)" + help + If you say yes here you get support for a PPS debugging generator + (which generates no PPS signal at all). + + This driver can also be built as a module. If so, the module + will be called pps_gen-dummy. config PPS_GENERATOR_PARPORT tristate "Parallel port PPS signal generator" @@ -12,3 +30,5 @@ config PPS_GENERATOR_PARPORT If you say yes here you get support for a PPS signal generator which utilizes STROBE pin of a parallel port to send PPS signals. It uses parport abstraction layer and hrtimers to precisely control the signal. + +endif # PPS_GENERATOR diff --git a/drivers/pps/generators/Makefile b/drivers/pps/generators/Makefile index 2589fd0f2481..dc1aa5a4688b 100644 --- a/drivers/pps/generators/Makefile +++ b/drivers/pps/generators/Makefile @@ -3,6 +3,10 @@ # Makefile for PPS generators. # +pps_gen_core-y := pps_gen.o sysfs.o +obj-$(CONFIG_PPS_GENERATOR) := pps_gen_core.o + +obj-$(CONFIG_PPS_GENERATOR_DUMMY) += pps_gen-dummy.o obj-$(CONFIG_PPS_GENERATOR_PARPORT) += pps_gen_parport.o ccflags-$(CONFIG_PPS_DEBUG) := -DDEBUG diff --git a/drivers/pps/generators/pps_gen-dummy.c b/drivers/pps/generators/pps_gen-dummy.c new file mode 100644 index 000000000000..b284c200cbe5 --- /dev/null +++ b/drivers/pps/generators/pps_gen-dummy.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * PPS dummy generator + * + * Copyright (C) 2024 Rodolfo Giometti + */ + +#include +#include +#include +#include +#include +#include +#include + +static struct pps_gen_device *pps_gen; +static struct timer_list ktimer; + +static unsigned int get_random_delay(void) +{ + unsigned int delay = get_random_u8() & 0x0f; + + return (delay + 1) * HZ; +} + +/* + * The kernel timer + */ + +static void pps_gen_ktimer_event(struct timer_list *unused) +{ + pps_gen_event(pps_gen, PPS_GEN_EVENT_MISSEDPULSE, NULL); +} + +/* + * PPS Generator methods + */ + +static int pps_gen_dummy_get_time(struct pps_gen_device *pps_gen, + struct timespec64 *time) +{ + struct system_time_snapshot snap; + + ktime_get_snapshot(&snap); + *time = ktime_to_timespec64(snap.real); + + return 0; +} + +static int pps_gen_dummy_enable(struct pps_gen_device *pps_gen, bool enable) +{ + if (enable) + mod_timer(&ktimer, jiffies + get_random_delay()); + else + del_timer_sync(&ktimer); + + return 0; +} + +/* + * The PPS info struct + */ + +static struct pps_gen_source_info pps_gen_dummy_info = { + .use_system_clock = true, + .get_time = pps_gen_dummy_get_time, + .enable = pps_gen_dummy_enable, +}; + +/* + * Module staff + */ + +static void __exit pps_gen_dummy_exit(void) +{ + del_timer_sync(&ktimer); + pps_gen_unregister_source(pps_gen); +} + +static int __init pps_gen_dummy_init(void) +{ + pps_gen = pps_gen_register_source(&pps_gen_dummy_info); + if (IS_ERR(pps_gen)) + return PTR_ERR(pps_gen); + + timer_setup(&ktimer, pps_gen_ktimer_event, 0); + + return 0; +} + +module_init(pps_gen_dummy_init); +module_exit(pps_gen_dummy_exit); + +MODULE_AUTHOR("Rodolfo Giometti "); +MODULE_DESCRIPTION("LinuxPPS dummy generator"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pps/generators/pps_gen.c b/drivers/pps/generators/pps_gen.c new file mode 100644 index 000000000000..ca592f1736f4 --- /dev/null +++ b/drivers/pps/generators/pps_gen.c @@ -0,0 +1,344 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * PPS generators core file + * + * Copyright (C) 2024 Rodolfo Giometti + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Local variables + */ + +static dev_t pps_gen_devt; +static struct class *pps_gen_class; + +static DEFINE_IDA(pps_gen_ida); + +/* + * Char device methods + */ + +static __poll_t pps_gen_cdev_poll(struct file *file, poll_table *wait) +{ + struct pps_gen_device *pps_gen = file->private_data; + + poll_wait(file, &pps_gen->queue, wait); + return EPOLLIN | EPOLLRDNORM; +} + +static int pps_gen_cdev_fasync(int fd, struct file *file, int on) +{ + struct pps_gen_device *pps_gen = file->private_data; + + return fasync_helper(fd, file, on, &pps_gen->async_queue); +} + +static long pps_gen_cdev_ioctl(struct file *file, + unsigned int cmd, unsigned long arg) +{ + struct pps_gen_device *pps_gen = file->private_data; + void __user *uarg = (void __user *) arg; + unsigned int __user *uiuarg = (unsigned int __user *) arg; + unsigned int status; + int ret; + + switch (cmd) { + case PPS_GEN_SETENABLE: + dev_dbg(pps_gen->dev, "PPS_GEN_SETENABLE\n"); + + ret = get_user(status, uiuarg); + if (ret) + return -EFAULT; + + ret = pps_gen->info.enable(pps_gen, status); + if (ret) + return ret; + pps_gen->enabled = status; + + break; + + case PPS_GEN_USESYSTEMCLOCK: + dev_dbg(pps_gen->dev, "PPS_GEN_USESYSTEMCLOCK\n"); + + ret = put_user(pps_gen->info.use_system_clock, uiuarg); + if (ret) + return -EFAULT; + + break; + + case PPS_GEN_FETCHEVENT: { + struct pps_gen_event info; + unsigned int ev = pps_gen->last_ev; + + dev_dbg(pps_gen->dev, "PPS_GEN_FETCHEVENT\n"); + + ret = wait_event_interruptible(pps_gen->queue, + ev != pps_gen->last_ev); + if (ret == -ERESTARTSYS) { + dev_dbg(pps_gen->dev, "pending signal caught\n"); + return -EINTR; + } + + spin_lock_irq(&pps_gen->lock); + info.sequence = pps_gen->sequence; + info.event = pps_gen->event; + spin_unlock_irq(&pps_gen->lock); + + ret = copy_to_user(uarg, &info, sizeof(struct pps_gen_event)); + if (ret) + return -EFAULT; + + break; + } + default: + return -ENOTTY; + } + + return 0; +} + +static int pps_gen_cdev_open(struct inode *inode, struct file *file) +{ + struct pps_gen_device *pps_gen = container_of(inode->i_cdev, + struct pps_gen_device, cdev); + + get_device(pps_gen->dev); + file->private_data = pps_gen; + return 0; +} + +static int pps_gen_cdev_release(struct inode *inode, struct file *file) +{ + struct pps_gen_device *pps_gen = file->private_data; + + put_device(pps_gen->dev); + return 0; +} + +/* + * Char device stuff + */ + +static const struct file_operations pps_gen_cdev_fops = { + .owner = THIS_MODULE, + .poll = pps_gen_cdev_poll, + .fasync = pps_gen_cdev_fasync, + .unlocked_ioctl = pps_gen_cdev_ioctl, + .open = pps_gen_cdev_open, + .release = pps_gen_cdev_release, +}; + +static void pps_gen_device_destruct(struct device *dev) +{ + struct pps_gen_device *pps_gen = dev_get_drvdata(dev); + + cdev_del(&pps_gen->cdev); + + pr_debug("deallocating pps-gen%d\n", pps_gen->id); + ida_free(&pps_gen_ida, pps_gen->id); + + kfree(dev); + kfree(pps_gen); +} + +static int pps_gen_register_cdev(struct pps_gen_device *pps_gen) +{ + int err; + dev_t devt; + + err = ida_alloc_max(&pps_gen_ida, PPS_GEN_MAX_SOURCES - 1, GFP_KERNEL); + if (err < 0) { + if (err == -ENOSPC) { + pr_err("too many PPS sources in the system\n"); + err = -EBUSY; + } + return err; + } + pps_gen->id = err; + + devt = MKDEV(MAJOR(pps_gen_devt), pps_gen->id); + + cdev_init(&pps_gen->cdev, &pps_gen_cdev_fops); + pps_gen->cdev.owner = pps_gen->info.owner; + + err = cdev_add(&pps_gen->cdev, devt, 1); + if (err) { + pr_err("failed to add char device %d:%d\n", + MAJOR(pps_gen_devt), pps_gen->id); + goto free_ida; + } + pps_gen->dev = device_create(pps_gen_class, pps_gen->info.parent, devt, + pps_gen, "pps-gen%d", pps_gen->id); + if (IS_ERR(pps_gen->dev)) { + err = PTR_ERR(pps_gen->dev); + goto del_cdev; + } + pps_gen->dev->release = pps_gen_device_destruct; + dev_set_drvdata(pps_gen->dev, pps_gen); + + pr_debug("generator got cdev (%d:%d)\n", + MAJOR(pps_gen_devt), pps_gen->id); + + return 0; + +del_cdev: + cdev_del(&pps_gen->cdev); +free_ida: + ida_free(&pps_gen_ida, pps_gen->id); + return err; +} + +static void pps_gen_unregister_cdev(struct pps_gen_device *pps_gen) +{ + pr_debug("unregistering pps-gen%d\n", pps_gen->id); + device_destroy(pps_gen_class, pps_gen->dev->devt); +} + +/* + * Exported functions + */ + +/** + * pps_gen_register_source() - add a PPS generator in the system + * @info: the PPS generator info struct + * + * This function is used to register a new PPS generator in the system. + * When it returns successfully the new generator is up and running, and + * it can be managed by the userspace. + * + * Return: the PPS generator device in case of success, and ERR_PTR(errno) + * otherwise. + */ +struct pps_gen_device *pps_gen_register_source(struct pps_gen_source_info *info) +{ + struct pps_gen_device *pps_gen; + int err; + + pps_gen = kzalloc(sizeof(struct pps_gen_device), GFP_KERNEL); + if (pps_gen == NULL) { + err = -ENOMEM; + goto pps_gen_register_source_exit; + } + pps_gen->info = *info; + pps_gen->enabled = false; + + init_waitqueue_head(&pps_gen->queue); + spin_lock_init(&pps_gen->lock); + + /* Create the char device */ + err = pps_gen_register_cdev(pps_gen); + if (err < 0) { + pr_err(" unable to create char device\n"); + goto kfree_pps_gen; + } + + return pps_gen; + +kfree_pps_gen: + kfree(pps_gen); + +pps_gen_register_source_exit: + pr_err("unable to register generator\n"); + + return ERR_PTR(err); +} +EXPORT_SYMBOL(pps_gen_register_source); + +/** + * pps_gen_unregister_source() - remove a PPS generator from the system + * @pps_gen: the PPS generator device to be removed + * + * This function is used to deregister a PPS generator from the system. When + * called, it disables the generator so no pulses are generated anymore. + */ +void pps_gen_unregister_source(struct pps_gen_device *pps_gen) +{ + pps_gen_unregister_cdev(pps_gen); +} +EXPORT_SYMBOL(pps_gen_unregister_source); + +/* pps_gen_event - register a PPS generator event into the system + * @pps: the PPS generator device + * @event: the event type + * @data: userdef pointer + * + * This function is used by each PPS generator in order to register a new + * PPS event into the system (it's usually called inside an IRQ handler). + */ +void pps_gen_event(struct pps_gen_device *pps_gen, + unsigned int event, void *data) +{ + unsigned long flags; + + dev_dbg(pps_gen->dev, "PPS generator event %u\n", event); + + spin_lock_irqsave(&pps_gen->lock, flags); + + pps_gen->event = event; + pps_gen->sequence++; + + pps_gen->last_ev++; + wake_up_interruptible_all(&pps_gen->queue); + kill_fasync(&pps_gen->async_queue, SIGIO, POLL_IN); + + spin_unlock_irqrestore(&pps_gen->lock, flags); +} +EXPORT_SYMBOL(pps_gen_event); + +/* + * Module stuff + */ + +static void __exit pps_gen_exit(void) +{ + class_destroy(pps_gen_class); + unregister_chrdev_region(pps_gen_devt, PPS_GEN_MAX_SOURCES); +} + +static int __init pps_gen_init(void) +{ + int err; + + pps_gen_class = class_create("pps-gen"); + if (IS_ERR(pps_gen_class)) { + pr_err("failed to allocate class\n"); + return PTR_ERR(pps_gen_class); + } + pps_gen_class->dev_groups = pps_gen_groups; + + err = alloc_chrdev_region(&pps_gen_devt, 0, + PPS_GEN_MAX_SOURCES, "pps-gen"); + if (err < 0) { + pr_err("failed to allocate char device region\n"); + goto remove_class; + } + + return 0; + +remove_class: + class_destroy(pps_gen_class); + return err; +} + +subsys_initcall(pps_gen_init); +module_exit(pps_gen_exit); + +MODULE_AUTHOR("Rodolfo Giometti "); +MODULE_DESCRIPTION("LinuxPPS generators support"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pps/generators/sysfs.c b/drivers/pps/generators/sysfs.c new file mode 100644 index 000000000000..faf8b1c6d202 --- /dev/null +++ b/drivers/pps/generators/sysfs.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * PPS generators sysfs support + * + * Copyright (C) 2024 Rodolfo Giometti + */ + +#include +#include +#include +#include + +/* + * Attribute functions + */ + +static ssize_t system_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct pps_gen_device *pps_gen = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%d\n", pps_gen->info.use_system_clock); +} +static DEVICE_ATTR_RO(system); + +static ssize_t time_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct pps_gen_device *pps_gen = dev_get_drvdata(dev); + struct timespec64 time; + int ret; + + ret = pps_gen->info.get_time(pps_gen, &time); + if (ret) + return ret; + + return sysfs_emit(buf, "%llu %09lu\n", time.tv_sec, time.tv_nsec); +} +static DEVICE_ATTR_RO(time); + +static ssize_t enable_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct pps_gen_device *pps_gen = dev_get_drvdata(dev); + bool status; + int ret; + + ret = kstrtobool(buf, &status); + if (ret) + return ret; + + ret = pps_gen->info.enable(pps_gen, status); + if (ret) + return ret; + pps_gen->enabled = status; + + return count; +} +static DEVICE_ATTR_WO(enable); + +static struct attribute *pps_gen_attrs[] = { + &dev_attr_enable.attr, + &dev_attr_time.attr, + &dev_attr_system.attr, + NULL, +}; + +static const struct attribute_group pps_gen_group = { + .attrs = pps_gen_attrs, +}; + +const struct attribute_group *pps_gen_groups[] = { + &pps_gen_group, + NULL, +}; diff --git a/drivers/pps/kapi.c b/drivers/pps/kapi.c index d9d566f70ed1..92d1b62ea239 100644 --- a/drivers/pps/kapi.c +++ b/drivers/pps/kapi.c @@ -41,7 +41,7 @@ static void pps_add_offset(struct pps_ktime *ts, struct pps_ktime *offset) static void pps_echo_client_default(struct pps_device *pps, int event, void *data) { - dev_info(pps->dev, "echo %s %s\n", + dev_info(&pps->dev, "echo %s %s\n", event & PPS_CAPTUREASSERT ? "assert" : "", event & PPS_CAPTURECLEAR ? "clear" : ""); } @@ -112,7 +112,7 @@ struct pps_device *pps_register_source(struct pps_source_info *info, goto kfree_pps; } - dev_info(pps->dev, "new PPS source %s\n", info->name); + dev_dbg(&pps->dev, "new PPS source %s\n", info->name); return pps; @@ -166,7 +166,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, /* check event type */ BUG_ON((event & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR)) == 0); - dev_dbg(pps->dev, "PPS event at %lld.%09ld\n", + dev_dbg(&pps->dev, "PPS event at %lld.%09ld\n", (s64)ts->ts_real.tv_sec, ts->ts_real.tv_nsec); timespec_to_pps_ktime(&ts_real, ts->ts_real); @@ -188,7 +188,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, /* Save the time stamp */ pps->assert_tu = ts_real; pps->assert_sequence++; - dev_dbg(pps->dev, "capture assert seq #%u\n", + dev_dbg(&pps->dev, "capture assert seq #%u\n", pps->assert_sequence); captured = ~0; @@ -202,7 +202,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, /* Save the time stamp */ pps->clear_tu = ts_real; pps->clear_sequence++; - dev_dbg(pps->dev, "capture clear seq #%u\n", + dev_dbg(&pps->dev, "capture clear seq #%u\n", pps->clear_sequence); captured = ~0; diff --git a/drivers/pps/kc.c b/drivers/pps/kc.c index 50dc59af45be..fbd23295afd7 100644 --- a/drivers/pps/kc.c +++ b/drivers/pps/kc.c @@ -43,11 +43,11 @@ int pps_kc_bind(struct pps_device *pps, struct pps_bind_args *bind_args) pps_kc_hardpps_mode = 0; pps_kc_hardpps_dev = NULL; spin_unlock_irq(&pps_kc_hardpps_lock); - dev_info(pps->dev, "unbound kernel" + dev_info(&pps->dev, "unbound kernel" " consumer\n"); } else { spin_unlock_irq(&pps_kc_hardpps_lock); - dev_err(pps->dev, "selected kernel consumer" + dev_err(&pps->dev, "selected kernel consumer" " is not bound\n"); return -EINVAL; } @@ -57,11 +57,11 @@ int pps_kc_bind(struct pps_device *pps, struct pps_bind_args *bind_args) pps_kc_hardpps_mode = bind_args->edge; pps_kc_hardpps_dev = pps; spin_unlock_irq(&pps_kc_hardpps_lock); - dev_info(pps->dev, "bound kernel consumer: " + dev_info(&pps->dev, "bound kernel consumer: " "edge=0x%x\n", bind_args->edge); } else { spin_unlock_irq(&pps_kc_hardpps_lock); - dev_err(pps->dev, "another kernel consumer" + dev_err(&pps->dev, "another kernel consumer" " is already bound\n"); return -EINVAL; } @@ -83,7 +83,7 @@ void pps_kc_remove(struct pps_device *pps) pps_kc_hardpps_mode = 0; pps_kc_hardpps_dev = NULL; spin_unlock_irq(&pps_kc_hardpps_lock); - dev_info(pps->dev, "unbound kernel consumer" + dev_info(&pps->dev, "unbound kernel consumer" " on device removal\n"); } else spin_unlock_irq(&pps_kc_hardpps_lock); diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 25d47907db17..6a02245ea35f 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -25,7 +25,7 @@ * Local variables */ -static dev_t pps_devt; +static int pps_major; static struct class *pps_class; static DEFINE_MUTEX(pps_idr_lock); @@ -62,7 +62,7 @@ static int pps_cdev_pps_fetch(struct pps_device *pps, struct pps_fdata *fdata) else { unsigned long ticks; - dev_dbg(pps->dev, "timeout %lld.%09d\n", + dev_dbg(&pps->dev, "timeout %lld.%09d\n", (long long) fdata->timeout.sec, fdata->timeout.nsec); ticks = fdata->timeout.sec * HZ; @@ -80,7 +80,7 @@ static int pps_cdev_pps_fetch(struct pps_device *pps, struct pps_fdata *fdata) /* Check for pending signals */ if (err == -ERESTARTSYS) { - dev_dbg(pps->dev, "pending signal caught\n"); + dev_dbg(&pps->dev, "pending signal caught\n"); return -EINTR; } @@ -98,7 +98,7 @@ static long pps_cdev_ioctl(struct file *file, switch (cmd) { case PPS_GETPARAMS: - dev_dbg(pps->dev, "PPS_GETPARAMS\n"); + dev_dbg(&pps->dev, "PPS_GETPARAMS\n"); spin_lock_irq(&pps->lock); @@ -114,7 +114,7 @@ static long pps_cdev_ioctl(struct file *file, break; case PPS_SETPARAMS: - dev_dbg(pps->dev, "PPS_SETPARAMS\n"); + dev_dbg(&pps->dev, "PPS_SETPARAMS\n"); /* Check the capabilities */ if (!capable(CAP_SYS_TIME)) @@ -124,14 +124,14 @@ static long pps_cdev_ioctl(struct file *file, if (err) return -EFAULT; if (!(params.mode & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR))) { - dev_dbg(pps->dev, "capture mode unspecified (%x)\n", + dev_dbg(&pps->dev, "capture mode unspecified (%x)\n", params.mode); return -EINVAL; } /* Check for supported capabilities */ if ((params.mode & ~pps->info.mode) != 0) { - dev_dbg(pps->dev, "unsupported capabilities (%x)\n", + dev_dbg(&pps->dev, "unsupported capabilities (%x)\n", params.mode); return -EINVAL; } @@ -144,7 +144,7 @@ static long pps_cdev_ioctl(struct file *file, /* Restore the read only parameters */ if ((params.mode & (PPS_TSFMT_TSPEC | PPS_TSFMT_NTPFP)) == 0) { /* section 3.3 of RFC 2783 interpreted */ - dev_dbg(pps->dev, "time format unspecified (%x)\n", + dev_dbg(&pps->dev, "time format unspecified (%x)\n", params.mode); pps->params.mode |= PPS_TSFMT_TSPEC; } @@ -165,7 +165,7 @@ static long pps_cdev_ioctl(struct file *file, break; case PPS_GETCAP: - dev_dbg(pps->dev, "PPS_GETCAP\n"); + dev_dbg(&pps->dev, "PPS_GETCAP\n"); err = put_user(pps->info.mode, iuarg); if (err) @@ -176,7 +176,7 @@ static long pps_cdev_ioctl(struct file *file, case PPS_FETCH: { struct pps_fdata fdata; - dev_dbg(pps->dev, "PPS_FETCH\n"); + dev_dbg(&pps->dev, "PPS_FETCH\n"); err = copy_from_user(&fdata, uarg, sizeof(struct pps_fdata)); if (err) @@ -206,7 +206,7 @@ static long pps_cdev_ioctl(struct file *file, case PPS_KC_BIND: { struct pps_bind_args bind_args; - dev_dbg(pps->dev, "PPS_KC_BIND\n"); + dev_dbg(&pps->dev, "PPS_KC_BIND\n"); /* Check the capabilities */ if (!capable(CAP_SYS_TIME)) @@ -218,7 +218,7 @@ static long pps_cdev_ioctl(struct file *file, /* Check for supported capabilities */ if ((bind_args.edge & ~pps->info.mode) != 0) { - dev_err(pps->dev, "unsupported capabilities (%x)\n", + dev_err(&pps->dev, "unsupported capabilities (%x)\n", bind_args.edge); return -EINVAL; } @@ -227,7 +227,7 @@ static long pps_cdev_ioctl(struct file *file, if (bind_args.tsformat != PPS_TSFMT_TSPEC || (bind_args.edge & ~PPS_CAPTUREBOTH) != 0 || bind_args.consumer != PPS_KC_HARDPPS) { - dev_err(pps->dev, "invalid kernel consumer bind" + dev_err(&pps->dev, "invalid kernel consumer bind" " parameters (%x)\n", bind_args.edge); return -EINVAL; } @@ -259,7 +259,7 @@ static long pps_cdev_compat_ioctl(struct file *file, struct pps_fdata fdata; int err; - dev_dbg(pps->dev, "PPS_FETCH\n"); + dev_dbg(&pps->dev, "PPS_FETCH\n"); err = copy_from_user(&compat, uarg, sizeof(struct pps_fdata_compat)); if (err) @@ -296,20 +296,36 @@ static long pps_cdev_compat_ioctl(struct file *file, #define pps_cdev_compat_ioctl NULL #endif +static struct pps_device *pps_idr_get(unsigned long id) +{ + struct pps_device *pps; + + mutex_lock(&pps_idr_lock); + pps = idr_find(&pps_idr, id); + if (pps) + get_device(&pps->dev); + + mutex_unlock(&pps_idr_lock); + return pps; +} + static int pps_cdev_open(struct inode *inode, struct file *file) { - struct pps_device *pps = container_of(inode->i_cdev, - struct pps_device, cdev); + struct pps_device *pps = pps_idr_get(iminor(inode)); + + if (!pps) + return -ENODEV; + file->private_data = pps; - kobject_get(&pps->dev->kobj); return 0; } static int pps_cdev_release(struct inode *inode, struct file *file) { - struct pps_device *pps = container_of(inode->i_cdev, - struct pps_device, cdev); - kobject_put(&pps->dev->kobj); + struct pps_device *pps = file->private_data; + + WARN_ON(pps->id != iminor(inode)); + put_device(&pps->dev); return 0; } @@ -331,22 +347,13 @@ static void pps_device_destruct(struct device *dev) { struct pps_device *pps = dev_get_drvdata(dev); - cdev_del(&pps->cdev); - - /* Now we can release the ID for re-use */ pr_debug("deallocating pps%d\n", pps->id); - mutex_lock(&pps_idr_lock); - idr_remove(&pps_idr, pps->id); - mutex_unlock(&pps_idr_lock); - - kfree(dev); kfree(pps); } int pps_register_cdev(struct pps_device *pps) { int err; - dev_t devt; mutex_lock(&pps_idr_lock); /* @@ -363,40 +370,29 @@ int pps_register_cdev(struct pps_device *pps) goto out_unlock; } pps->id = err; - mutex_unlock(&pps_idr_lock); - devt = MKDEV(MAJOR(pps_devt), pps->id); - - cdev_init(&pps->cdev, &pps_cdev_fops); - pps->cdev.owner = pps->info.owner; - - err = cdev_add(&pps->cdev, devt, 1); - if (err) { - pr_err("%s: failed to add char device %d:%d\n", - pps->info.name, MAJOR(pps_devt), pps->id); + pps->dev.class = pps_class; + pps->dev.parent = pps->info.dev; + pps->dev.devt = MKDEV(pps_major, pps->id); + dev_set_drvdata(&pps->dev, pps); + dev_set_name(&pps->dev, "pps%d", pps->id); + err = device_register(&pps->dev); + if (err) goto free_idr; - } - pps->dev = device_create(pps_class, pps->info.dev, devt, pps, - "pps%d", pps->id); - if (IS_ERR(pps->dev)) { - err = PTR_ERR(pps->dev); - goto del_cdev; - } /* Override the release function with our own */ - pps->dev->release = pps_device_destruct; + pps->dev.release = pps_device_destruct; - pr_debug("source %s got cdev (%d:%d)\n", pps->info.name, - MAJOR(pps_devt), pps->id); + pr_debug("source %s got cdev (%d:%d)\n", pps->info.name, pps_major, + pps->id); + get_device(&pps->dev); + mutex_unlock(&pps_idr_lock); return 0; -del_cdev: - cdev_del(&pps->cdev); - free_idr: - mutex_lock(&pps_idr_lock); idr_remove(&pps_idr, pps->id); + put_device(&pps->dev); out_unlock: mutex_unlock(&pps_idr_lock); return err; @@ -406,7 +402,13 @@ void pps_unregister_cdev(struct pps_device *pps) { pr_debug("unregistering pps%d\n", pps->id); pps->lookup_cookie = NULL; - device_destroy(pps_class, pps->dev->devt); + device_destroy(pps_class, pps->dev.devt); + + /* Now we can release the ID for re-use */ + mutex_lock(&pps_idr_lock); + idr_remove(&pps_idr, pps->id); + put_device(&pps->dev); + mutex_unlock(&pps_idr_lock); } /* @@ -426,6 +428,11 @@ void pps_unregister_cdev(struct pps_device *pps) * so that it will not be used again, even if the pps device cannot * be removed from the idr due to pending references holding the minor * number in use. + * + * Since pps_idr holds a reference to the device, the returned + * pps_device is guaranteed to be valid until pps_unregister_cdev() is + * called on it. But after calling pps_unregister_cdev(), it may be + * freed at any time. */ struct pps_device *pps_lookup_dev(void const *cookie) { @@ -448,13 +455,11 @@ EXPORT_SYMBOL(pps_lookup_dev); static void __exit pps_exit(void) { class_destroy(pps_class); - unregister_chrdev_region(pps_devt, PPS_MAX_SOURCES); + __unregister_chrdev(pps_major, 0, PPS_MAX_SOURCES, "pps"); } static int __init pps_init(void) { - int err; - pps_class = class_create("pps"); if (IS_ERR(pps_class)) { pr_err("failed to allocate class\n"); @@ -462,8 +467,9 @@ static int __init pps_init(void) } pps_class->dev_groups = pps_groups; - err = alloc_chrdev_region(&pps_devt, 0, PPS_MAX_SOURCES, "pps"); - if (err < 0) { + pps_major = __register_chrdev(0, 0, PPS_MAX_SOURCES, "pps", + &pps_cdev_fops); + if (pps_major < 0) { pr_err("failed to allocate char device region\n"); goto remove_class; } @@ -476,8 +482,7 @@ static int __init pps_init(void) remove_class: class_destroy(pps_class); - - return err; + return pps_major; } subsys_initcall(pps_init); diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index ea96a14d72d1..bf6468c56419 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -4,6 +4,7 @@ * * Copyright (C) 2010 OMICRON electronics GmbH */ +#include #include #include #include @@ -176,6 +177,9 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd, struct timespec64 ts; int enable, err = 0; + if (in_compat_syscall() && cmd != PTP_ENABLE_PPS && cmd != PTP_ENABLE_PPS2) + arg = (unsigned long)compat_ptr(arg); + tsevq = pccontext->private_clkdata; switch (cmd) { diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 77a36e7bddd5..35a5994bf64f 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -217,6 +217,11 @@ static int ptp_getcycles64(struct ptp_clock_info *info, struct timespec64 *ts) return info->gettime64(info, ts); } +static int ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on) +{ + return -EOPNOTSUPP; +} + static void ptp_aux_kworker(struct kthread_work *work) { struct ptp_clock *ptp = container_of(work, struct ptp_clock, @@ -294,9 +299,12 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, ptp->info->getcrosscycles = ptp->info->getcrosststamp; } + if (!ptp->info->enable) + ptp->info->enable = ptp_enable; + if (ptp->info->do_aux_work) { kthread_init_delayed_work(&ptp->aux_work, ptp_aux_kworker); - ptp->kworker = kthread_create_worker(0, "ptp%d", ptp->index); + ptp->kworker = kthread_run_worker(0, "ptp%d", ptp->index); if (IS_ERR(ptp->kworker)) { err = PTR_ERR(ptp->kworker); pr_err("failed to create ptp aux_worker %d\n", err); diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 5feecaadde8e..b651087f426f 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -3692,7 +3692,7 @@ DEVICE_FREQ_GROUP(freq4, 3); static ssize_t disciplining_config_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct ptp_ocp *bp = dev_get_drvdata(kobj_to_dev(kobj)); @@ -3727,7 +3727,7 @@ out: static ssize_t disciplining_config_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct ptp_ocp *bp = dev_get_drvdata(kobj_to_dev(kobj)); @@ -3750,11 +3750,11 @@ disciplining_config_write(struct file *filp, struct kobject *kobj, return err; } -static BIN_ATTR_RW(disciplining_config, OCP_ART_CONFIG_SIZE); +static const BIN_ATTR_RW(disciplining_config, OCP_ART_CONFIG_SIZE); static ssize_t temperature_table_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct ptp_ocp *bp = dev_get_drvdata(kobj_to_dev(kobj)); @@ -3789,7 +3789,7 @@ out: static ssize_t temperature_table_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct ptp_ocp *bp = dev_get_drvdata(kobj_to_dev(kobj)); @@ -3812,7 +3812,7 @@ temperature_table_write(struct file *filp, struct kobject *kobj, return err; } -static BIN_ATTR_RW(temperature_table, OCP_ART_TEMP_TABLE_SIZE); +static const BIN_ATTR_RW(temperature_table, OCP_ART_TEMP_TABLE_SIZE); static struct attribute *fb_timecard_attrs[] = { &dev_attr_serialnum.attr, @@ -3867,7 +3867,7 @@ static struct attribute *art_timecard_attrs[] = { NULL, }; -static struct bin_attribute *bin_art_timecard_attrs[] = { +static const struct bin_attribute *const bin_art_timecard_attrs[] = { &bin_attr_disciplining_config, &bin_attr_temperature_table, NULL, @@ -3875,7 +3875,7 @@ static struct bin_attribute *bin_art_timecard_attrs[] = { static const struct attribute_group art_timecard_group = { .attrs = art_timecard_attrs, - .bin_attrs = bin_art_timecard_attrs, + .bin_attrs_new = bin_art_timecard_attrs, }; static const struct ocp_attr_group art_timecard_groups[] = { @@ -4420,7 +4420,7 @@ ptp_ocp_complete(struct ptp_ocp *bp) pps = pps_lookup_dev(bp->ptp); if (pps) - ptp_ocp_symlink(bp, pps->dev, "pps"); + ptp_ocp_symlink(bp, &pps->dev, "pps"); ptp_ocp_debugfs_add_device(bp); diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 675b252d9c8c..ccd54c089bab 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -242,6 +242,9 @@ int pwm_round_waveform_might_sleep(struct pwm_device *pwm, struct pwm_waveform * BUG_ON(WFHWSIZE < ops->sizeof_wfhw); + if (!pwmchip_supports_waveform(chip)) + return -EOPNOTSUPP; + if (!pwm_wf_valid(wf)) return -EINVAL; @@ -294,6 +297,9 @@ int pwm_get_waveform_might_sleep(struct pwm_device *pwm, struct pwm_waveform *wf BUG_ON(WFHWSIZE < ops->sizeof_wfhw); + if (!pwmchip_supports_waveform(chip) || !ops->read_waveform) + return -EOPNOTSUPP; + guard(pwmchip)(chip); if (!chip->operational) @@ -320,6 +326,9 @@ static int __pwm_set_waveform(struct pwm_device *pwm, BUG_ON(WFHWSIZE < ops->sizeof_wfhw); + if (!pwmchip_supports_waveform(chip)) + return -EOPNOTSUPP; + if (!pwm_wf_valid(wf)) return -EINVAL; @@ -592,7 +601,7 @@ static int __pwm_apply(struct pwm_device *pwm, const struct pwm_state *state) state->usage_power == pwm->state.usage_power) return 0; - if (ops->write_waveform) { + if (pwmchip_supports_waveform(chip)) { struct pwm_waveform wf; char wfhw[WFHWSIZE]; @@ -746,7 +755,7 @@ int pwm_get_state_hw(struct pwm_device *pwm, struct pwm_state *state) if (!chip->operational) return -ENODEV; - if (ops->read_waveform) { + if (pwmchip_supports_waveform(chip) && ops->read_waveform) { char wfhw[WFHWSIZE]; struct pwm_waveform wf; @@ -1276,7 +1285,7 @@ static int pwm_export_child(struct device *pwmchip_dev, struct pwm_device *pwm) return 0; } -static int pwm_unexport_match(struct device *pwm_dev, void *data) +static int pwm_unexport_match(struct device *pwm_dev, const void *data) { return pwm_from_dev(pwm_dev) == data; } diff --git a/drivers/pwm/pwm-dwc.c b/drivers/pwm/pwm-dwc.c index fb3eadf6fbc4..b6c16139ce4a 100644 --- a/drivers/pwm/pwm-dwc.c +++ b/drivers/pwm/pwm-dwc.c @@ -66,20 +66,16 @@ static int dwc_pwm_probe(struct pci_dev *pci, const struct pci_device_id *id) pci_set_master(pci); - ret = pcim_iomap_regions(pci, BIT(0), pci_name(pci)); - if (ret) - return dev_err_probe(dev, ret, "Failed to iomap PCI BAR\n"); - info = (const struct dwc_pwm_info *)id->driver_data; ddata = devm_kzalloc(dev, struct_size(ddata, chips, info->nr), GFP_KERNEL); if (!ddata) return -ENOMEM; - /* - * No need to check for pcim_iomap_table() failure, - * pcim_iomap_regions() already does it for us. - */ - ddata->io_base = pcim_iomap_table(pci)[0]; + ddata->io_base = pcim_iomap_region(pci, 0, "pwm-dwc"); + if (IS_ERR(ddata->io_base)) + return dev_err_probe(dev, PTR_ERR(ddata->io_base), + "Failed to request / iomap PCI BAR\n"); + ddata->info = info; for (idx = 0; idx < ddata->info->nr; idx++) { diff --git a/drivers/pwm/pwm-lpss-pci.c b/drivers/pwm/pwm-lpss-pci.c index ddc2a4ca90fd..ae25d9321d75 100644 --- a/drivers/pwm/pwm-lpss-pci.c +++ b/drivers/pwm/pwm-lpss-pci.c @@ -18,6 +18,7 @@ static int pwm_lpss_probe_pci(struct pci_dev *pdev, const struct pci_device_id *id) { const struct pwm_lpss_boardinfo *info; + void __iomem *io_base; struct pwm_chip *chip; int err; @@ -25,12 +26,12 @@ static int pwm_lpss_probe_pci(struct pci_dev *pdev, if (err < 0) return err; - err = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev)); - if (err) - return err; + io_base = pcim_iomap_region(pdev, 0, "pwm-lpss"); + if (IS_ERR(io_base)) + return PTR_ERR(io_base); info = (struct pwm_lpss_boardinfo *)id->driver_data; - chip = devm_pwm_lpss_probe(&pdev->dev, pcim_iomap_table(pdev)[0], info); + chip = devm_pwm_lpss_probe(&pdev->dev, io_base, info); if (IS_ERR(chip)) return PTR_ERR(chip); diff --git a/drivers/pwm/pwm-microchip-core.c b/drivers/pwm/pwm-microchip-core.c index c1f2287b8e97..12821b4bbf97 100644 --- a/drivers/pwm/pwm-microchip-core.c +++ b/drivers/pwm/pwm-microchip-core.c @@ -327,7 +327,7 @@ static int mchp_core_pwm_apply_locked(struct pwm_chip *chip, struct pwm_device * * mchp_core_pwm_calc_period(). * The period is locked and we cannot change this, so we abort. */ - if (hw_period_steps == MCHPCOREPWM_PERIOD_STEPS_MAX) + if (hw_period_steps > MCHPCOREPWM_PERIOD_STEPS_MAX) return -EINVAL; prescale = hw_prescale; diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c index 989731256f50..5832dce8ed9d 100644 --- a/drivers/pwm/pwm-stm32-lp.c +++ b/drivers/pwm/pwm-stm32-lp.c @@ -167,8 +167,12 @@ static int stm32_pwm_lp_get_state(struct pwm_chip *chip, regmap_read(priv->regmap, STM32_LPTIM_CR, &val); state->enabled = !!FIELD_GET(STM32_LPTIM_ENABLE, val); /* Keep PWM counter clock refcount in sync with PWM initial state */ - if (state->enabled) - clk_enable(priv->clk); + if (state->enabled) { + int ret = clk_enable(priv->clk); + + if (ret) + return ret; + } regmap_read(priv->regmap, STM32_LPTIM_CFGR, &val); presc = FIELD_GET(STM32_LPTIM_PRESC, val); diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index b889e64522c3..a59de4de18b6 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -84,7 +84,7 @@ static int stm32_pwm_round_waveform_tohw(struct pwm_chip *chip, wfhw->ccer = TIM_CCER_CCxE(ch + 1); if (priv->have_complementary_output) - wfhw->ccer = TIM_CCER_CCxNE(ch + 1); + wfhw->ccer |= TIM_CCER_CCxNE(ch + 1); rate = clk_get_rate(priv->clk); @@ -858,8 +858,11 @@ static int stm32_pwm_probe(struct platform_device *pdev) chip->ops = &stm32pwm_ops; /* Initialize clock refcount to number of enabled PWM channels. */ - for (i = 0; i < num_enabled; i++) - clk_enable(priv->clk); + for (i = 0; i < num_enabled; i++) { + ret = clk_enable(priv->clk); + if (ret) + return ret; + } ret = devm_pwmchip_add(dev, chip); if (ret < 0) diff --git a/drivers/ras/amd/atl/Kconfig b/drivers/ras/amd/atl/Kconfig index 551680073e43..6e03942cd7da 100644 --- a/drivers/ras/amd/atl/Kconfig +++ b/drivers/ras/amd/atl/Kconfig @@ -10,6 +10,7 @@ config AMD_ATL tristate "AMD Address Translation Library" depends on AMD_NB && X86_64 && RAS + depends on AMD_NODE depends on MEMORY_FAILURE default N help diff --git a/drivers/ras/amd/atl/internal.h b/drivers/ras/amd/atl/internal.h index 143d04c779a8..f9be26d25348 100644 --- a/drivers/ras/amd/atl/internal.h +++ b/drivers/ras/amd/atl/internal.h @@ -18,6 +18,7 @@ #include #include +#include #include "reg_fields.h" diff --git a/drivers/regulator/bd96801-regulator.c b/drivers/regulator/bd96801-regulator.c index 9876cc05867e..3a9d772491a8 100644 --- a/drivers/regulator/bd96801-regulator.c +++ b/drivers/regulator/bd96801-regulator.c @@ -5,12 +5,7 @@ /* * This version of the "BD86801 scalable PMIC"'s driver supports only very * basic set of the PMIC features. Most notably, there is no support for - * the ERRB interrupt and the configurations which should be done when the - * PMIC is in STBY mode. - * - * Supporting the ERRB interrupt would require dropping the regmap-IRQ - * usage or working around (or accepting a presense of) a naming conflict - * in debugFS IRQs. + * the configurations which should be done when the PMIC is in STBY mode. * * Being able to reliably do the configurations like changing the * regulator safety limits (like limits for the over/under -voltages, over @@ -22,16 +17,14 @@ * be the need to configure these safety limits. Hence it's not simple to * come up with a generic solution. * - * Users who require the ERRB handling and STBY state configurations can - * have a look at the original RFC: + * Users who require the STBY state configurations can have a look at the + * original RFC: * https://lore.kernel.org/all/cover.1712920132.git.mazziesaccount@gmail.com/ - * which implements a workaround to debugFS naming conflict and some of - * the safety limit configurations - but leaves the state change handling - * and synchronization to be implemented. + * which implements some of the safety limit configurations - but leaves the + * state change handling and synchronization to be implemented. * * It would be great to hear (and receive a patch!) if you implement the - * STBY configuration support or a proper fix to the debugFS naming - * conflict in your downstream driver ;) + * STBY configuration support in your downstream driver ;) */ #include @@ -728,6 +721,95 @@ static int initialize_pmic_data(struct device *dev, return 0; } +static int bd96801_map_event_all(int irq, struct regulator_irq_data *rid, + unsigned long *dev_mask) +{ + int i; + + for (i = 0; i < rid->num_states; i++) { + rid->states[i].notifs = REGULATOR_EVENT_FAIL; + rid->states[i].errors = REGULATOR_ERROR_FAIL; + *dev_mask |= BIT(i); + } + + return 0; +} + +static int bd96801_rdev_errb_irqs(struct platform_device *pdev, + struct regulator_dev *rdev) +{ + int i; + void *retp; + static const char * const single_out_errb_irqs[] = { + "bd96801-%s-pvin-err", "bd96801-%s-ovp-err", + "bd96801-%s-uvp-err", "bd96801-%s-shdn-err", + }; + + for (i = 0; i < ARRAY_SIZE(single_out_errb_irqs); i++) { + struct regulator_irq_desc id = { + .map_event = bd96801_map_event_all, + .irq_off_ms = 1000, + }; + struct regulator_dev *rdev_arr[1]; + char tmp[255]; + int irq; + + snprintf(tmp, 255, single_out_errb_irqs[i], rdev->desc->name); + tmp[254] = 0; + id.name = tmp; + + irq = platform_get_irq_byname(pdev, tmp); + if (irq < 0) + continue; + + rdev_arr[0] = rdev; + retp = devm_regulator_irq_helper(&pdev->dev, &id, irq, 0, + REGULATOR_ERROR_FAIL, NULL, + rdev_arr, 1); + if (IS_ERR(retp)) + return PTR_ERR(retp); + + } + return 0; +} + +static int bd96801_global_errb_irqs(struct platform_device *pdev, + struct regulator_dev **rdev, int num_rdev) +{ + int i, num_irqs; + void *retp; + static const char * const global_errb_irqs[] = { + "bd96801-otp-err", "bd96801-dbist-err", "bd96801-eep-err", + "bd96801-abist-err", "bd96801-prstb-err", "bd96801-drmoserr1", + "bd96801-drmoserr2", "bd96801-slave-err", "bd96801-vref-err", + "bd96801-tsd", "bd96801-uvlo-err", "bd96801-ovlo-err", + "bd96801-osc-err", "bd96801-pon-err", "bd96801-poff-err", + "bd96801-cmd-shdn-err", "bd96801-int-shdn-err" + }; + + num_irqs = ARRAY_SIZE(global_errb_irqs); + for (i = 0; i < num_irqs; i++) { + int irq; + struct regulator_irq_desc id = { + .name = global_errb_irqs[i], + .map_event = bd96801_map_event_all, + .irq_off_ms = 1000, + }; + + irq = platform_get_irq_byname(pdev, global_errb_irqs[i]); + if (irq < 0) + continue; + + retp = devm_regulator_irq_helper(&pdev->dev, &id, irq, 0, + REGULATOR_ERROR_FAIL, NULL, + rdev, num_rdev); + if (IS_ERR(retp)) + return PTR_ERR(retp); + } + + return 0; +} + static int bd96801_rdev_intb_irqs(struct platform_device *pdev, struct bd96801_pmic_data *pdata, struct bd96801_irqinfo *iinfo, @@ -783,11 +865,10 @@ static int bd96801_rdev_intb_irqs(struct platform_device *pdev, return 0; } - - static int bd96801_probe(struct platform_device *pdev) { struct regulator_dev *ldo_errs_rdev_arr[BD96801_NUM_LDOS]; + struct regulator_dev *all_rdevs[BD96801_NUM_REGULATORS]; struct bd96801_regulator_data *rdesc; struct regulator_config config = {}; int ldo_errs_arr[BD96801_NUM_LDOS]; @@ -795,6 +876,7 @@ static int bd96801_probe(struct platform_device *pdev) int temp_notif_ldos = 0; struct device *parent; int i, ret; + bool use_errb; void *retp; parent = pdev->dev.parent; @@ -819,6 +901,13 @@ static int bd96801_probe(struct platform_device *pdev) config.regmap = pdata->regmap; config.dev = parent; + ret = of_property_match_string(pdev->dev.parent->of_node, + "interrupt-names", "errb"); + if (ret < 0) + use_errb = false; + else + use_errb = true; + ret = bd96801_walk_regulator_dt(&pdev->dev, pdata->regmap, rdesc, BD96801_NUM_REGULATORS); if (ret) @@ -837,6 +926,7 @@ static int bd96801_probe(struct platform_device *pdev) rdesc[i].desc.name); return PTR_ERR(rdev); } + all_rdevs[i] = rdev; /* * LDOs don't have own temperature monitoring. If temperature * notification was requested for this LDO from DT then we will @@ -856,6 +946,12 @@ static int bd96801_probe(struct platform_device *pdev) if (ret) return ret; } + /* Register per regulator ERRB notifiers */ + if (use_errb) { + ret = bd96801_rdev_errb_irqs(pdev, rdev); + if (ret) + return ret; + } } if (temp_notif_ldos) { int irq; @@ -877,6 +973,10 @@ static int bd96801_probe(struct platform_device *pdev) return PTR_ERR(retp); } + if (use_errb) + return bd96801_global_errb_irqs(pdev, all_rdevs, + ARRAY_SIZE(all_rdevs)); + return 0; } diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 8cb948a91e60..89578b91c468 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -917,6 +917,26 @@ static ssize_t bypass_show(struct device *dev, } static DEVICE_ATTR_RO(bypass); +static ssize_t power_budget_milliwatt_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct regulator_dev *rdev = dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", rdev->constraints->pw_budget_mW); +} +static DEVICE_ATTR_RO(power_budget_milliwatt); + +static ssize_t power_requested_milliwatt_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct regulator_dev *rdev = dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", rdev->pw_requested_mW); +} +static DEVICE_ATTR_RO(power_requested_milliwatt); + #define REGULATOR_ERROR_ATTR(name, bit) \ static ssize_t name##_show(struct device *dev, struct device_attribute *attr, \ char *buf) \ @@ -1149,6 +1169,10 @@ static void print_constraints_debug(struct regulator_dev *rdev) if (constraints->valid_modes_mask & REGULATOR_MODE_STANDBY) count += scnprintf(buf + count, len - count, "standby "); + if (constraints->pw_budget_mW) + count += scnprintf(buf + count, len - count, "%d mW budget", + constraints->pw_budget_mW); + if (!count) count = scnprintf(buf, len, "no parameters"); else @@ -1627,6 +1651,9 @@ static int set_machine_constraints(struct regulator_dev *rdev) rdev->last_off = ktime_get(); } + if (!rdev->constraints->pw_budget_mW) + rdev->constraints->pw_budget_mW = INT_MAX; + print_constraints(rdev); return 0; } @@ -1936,6 +1963,20 @@ static struct regulator_dev *regulator_lookup_by_name(const char *name) return dev ? dev_to_rdev(dev) : NULL; } +static struct regulator_dev *regulator_dt_lookup(struct device *dev, + const char *supply) +{ + struct regulator_dev *r = NULL; + + if (dev_of_node(dev)) { + r = of_regulator_dev_lookup(dev, dev_of_node(dev), supply); + if (PTR_ERR(r) == -ENODEV) + r = NULL; + } + + return r; +} + /** * regulator_dev_lookup - lookup a regulator device. * @dev: device for regulator "consumer". @@ -1960,16 +2001,9 @@ static struct regulator_dev *regulator_dev_lookup(struct device *dev, regulator_supply_alias(&dev, &supply); /* first do a dt based lookup */ - if (dev_of_node(dev)) { - r = of_regulator_dev_lookup(dev, dev_of_node(dev), supply); - if (!IS_ERR(r)) - return r; - if (PTR_ERR(r) == -EPROBE_DEFER) - return r; - - if (PTR_ERR(r) == -ENODEV) - r = NULL; - } + r = regulator_dt_lookup(dev, supply); + if (r) + return r; /* if not found, try doing it non-dt way */ if (dev) @@ -2015,7 +2049,17 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) if (rdev->supply) return 0; - r = regulator_dev_lookup(dev, rdev->supply_name); + /* first do a dt based lookup on the node described in the virtual + * device. + */ + r = regulator_dt_lookup(&rdev->dev, rdev->supply_name); + + /* If regulator not found use usual search path in the parent + * device. + */ + if (!r) + r = regulator_dev_lookup(dev, rdev->supply_name); + if (IS_ERR(r)) { ret = PTR_ERR(r); @@ -4584,6 +4628,87 @@ int regulator_get_current_limit(struct regulator *regulator) } EXPORT_SYMBOL_GPL(regulator_get_current_limit); +/** + * regulator_get_unclaimed_power_budget - get regulator unclaimed power budget + * @regulator: regulator source + * + * Return: Unclaimed power budget of the regulator in mW. + */ +int regulator_get_unclaimed_power_budget(struct regulator *regulator) +{ + return regulator->rdev->constraints->pw_budget_mW - + regulator->rdev->pw_requested_mW; +} +EXPORT_SYMBOL_GPL(regulator_get_unclaimed_power_budget); + +/** + * regulator_request_power_budget - request power budget on a regulator + * @regulator: regulator source + * @pw_req: Power requested + * + * Return: 0 on success or a negative error number on failure. + */ +int regulator_request_power_budget(struct regulator *regulator, + unsigned int pw_req) +{ + struct regulator_dev *rdev = regulator->rdev; + int ret = 0, pw_tot_req; + + regulator_lock(rdev); + if (rdev->supply) { + ret = regulator_request_power_budget(rdev->supply, pw_req); + if (ret < 0) + goto out; + } + + pw_tot_req = rdev->pw_requested_mW + pw_req; + if (pw_tot_req > rdev->constraints->pw_budget_mW) { + rdev_warn(rdev, "power requested %d mW out of budget %d mW", + pw_req, + rdev->constraints->pw_budget_mW - rdev->pw_requested_mW); + regulator_notifier_call_chain(rdev, + REGULATOR_EVENT_OVER_CURRENT_WARN, + NULL); + ret = -ERANGE; + goto out; + } + + rdev->pw_requested_mW = pw_tot_req; +out: + regulator_unlock(rdev); + return ret; +} +EXPORT_SYMBOL_GPL(regulator_request_power_budget); + +/** + * regulator_free_power_budget - free power budget on a regulator + * @regulator: regulator source + * @pw: Power to be released. + * + * Return: Power budget of the regulator in mW. + */ +void regulator_free_power_budget(struct regulator *regulator, + unsigned int pw) +{ + struct regulator_dev *rdev = regulator->rdev; + int pw_tot_req; + + regulator_lock(rdev); + if (rdev->supply) + regulator_free_power_budget(rdev->supply, pw); + + pw_tot_req = rdev->pw_requested_mW - pw; + if (pw_tot_req >= 0) + rdev->pw_requested_mW = pw_tot_req; + else + rdev_warn(rdev, + "too much power freed %d mW (already requested %d mW)", + pw, rdev->pw_requested_mW); + + regulator_unlock(rdev); +} +EXPORT_SYMBOL_GPL(regulator_free_power_budget); + /** * regulator_set_mode - set regulator operating mode * @regulator: regulator source @@ -4908,7 +5033,7 @@ int _regulator_bulk_get(struct device *dev, int num_consumers, consumers[i].supply, get_type); if (IS_ERR(consumers[i].consumer)) { ret = dev_err_probe(dev, PTR_ERR(consumers[i].consumer), - "Failed to get supply '%s'", + "Failed to get supply '%s'\n", consumers[i].supply); consumers[i].consumer = NULL; goto err; @@ -5222,6 +5347,8 @@ static struct attribute *regulator_dev_attrs[] = { &dev_attr_suspend_standby_mode.attr, &dev_attr_suspend_mem_mode.attr, &dev_attr_suspend_disk_mode.attr, + &dev_attr_power_budget_milliwatt.attr, + &dev_attr_power_requested_milliwatt.attr, NULL }; @@ -5303,6 +5430,10 @@ static umode_t regulator_attr_is_visible(struct kobject *kobj, attr == &dev_attr_suspend_disk_mode.attr) return ops->set_suspend_mode ? mode : 0; + if (attr == &dev_attr_power_budget_milliwatt.attr || + attr == &dev_attr_power_requested_milliwatt.attr) + return rdev->constraints->pw_budget_mW != INT_MAX ? mode : 0; + return mode; } diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 3d85762beda6..011088c57891 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -125,6 +125,9 @@ static int of_get_regulation_constraints(struct device *dev, if (constraints->min_uA != constraints->max_uA) constraints->valid_ops_mask |= REGULATOR_CHANGE_CURRENT; + if (!of_property_read_u32(np, "regulator-power-budget-milliwatt", &pval)) + constraints->pw_budget_mW = pval; + constraints->boot_on = of_property_read_bool(np, "regulator-boot-on"); constraints->always_on = of_property_read_bool(np, "regulator-always-on"); if (!constraints->always_on) /* status change should be possible. */ @@ -175,7 +178,7 @@ static int of_get_regulation_constraints(struct device *dev, if (!ret) constraints->enable_time = pval; - ret = of_property_read_u32(np, "regulator-uv-survival-time-ms", &pval); + ret = of_property_read_u32(np, "regulator-uv-less-critical-window-ms", &pval); if (!ret) constraints->uv_less_critical_window_ms = pval; else @@ -446,7 +449,7 @@ int of_regulator_match(struct device *dev, struct device_node *node, "failed to parse DT for regulator %pOFn\n", child); of_node_put(child); - return -EINVAL; + goto err_put; } match->of_node = of_node_get(child); count++; @@ -455,6 +458,18 @@ int of_regulator_match(struct device *dev, struct device_node *node, } return count; + +err_put: + for (i = 0; i < num_matches; i++) { + struct of_regulator_match *match = &matches[i]; + + match->init_data = NULL; + if (match->of_node) { + of_node_put(match->of_node); + match->of_node = NULL; + } + } + return -EINVAL; } EXPORT_SYMBOL_GPL(of_regulator_match); diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 9714afe347dc..faa6b79c27d7 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -247,6 +247,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .ramp_mask = BUCK1_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), + .enable_val = BUCK_ENMODE_ONREQ, .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, @@ -272,6 +273,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, .enable_mask = BUCK2_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ_STBYREQ, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, @@ -301,6 +303,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK3OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK3CTRL, .enable_mask = BUCK3_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, .ramp_reg = PCA9450_REG_BUCK3CTRL, .ramp_mask = BUCK3_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, @@ -330,6 +333,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK4OUT_MASK, .enable_reg = PCA9450_REG_BUCK4CTRL, .enable_mask = BUCK4_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, .owner = THIS_MODULE, }, }, @@ -348,6 +352,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK5OUT_MASK, .enable_reg = PCA9450_REG_BUCK5CTRL, .enable_mask = BUCK5_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, .owner = THIS_MODULE, }, }, @@ -366,6 +371,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK6OUT_MASK, .enable_reg = PCA9450_REG_BUCK6CTRL, .enable_mask = BUCK6_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, .owner = THIS_MODULE, }, }, @@ -481,6 +487,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_mask = BUCK1OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK1CTRL, .enable_mask = BUCK1_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, .ramp_reg = PCA9450_REG_BUCK1CTRL, .ramp_mask = BUCK1_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, @@ -510,6 +517,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, .enable_mask = BUCK2_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ_STBYREQ, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, @@ -539,6 +547,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_mask = BUCK4OUT_MASK, .enable_reg = PCA9450_REG_BUCK4CTRL, .enable_mask = BUCK4_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, .owner = THIS_MODULE, }, }, @@ -557,6 +566,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_mask = BUCK5OUT_MASK, .enable_reg = PCA9450_REG_BUCK5CTRL, .enable_mask = BUCK5_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, .owner = THIS_MODULE, }, }, @@ -575,6 +585,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_mask = BUCK6OUT_MASK, .enable_reg = PCA9450_REG_BUCK6CTRL, .enable_mask = BUCK6_ENMODE_MASK, + .enable_val = BUCK_ENMODE_ONREQ, .owner = THIS_MODULE, }, }, @@ -804,6 +815,24 @@ static const struct pca9450_regulator_desc pca9451a_regulators[] = { .owner = THIS_MODULE, }, }, + { + .desc = { + .name = "ldo3", + .of_match = of_match_ptr("LDO3"), + .regulators_node = of_match_ptr("regulators"), + .id = PCA9450_LDO3, + .ops = &pca9450_ldo_regulator_ops, + .type = REGULATOR_VOLTAGE, + .n_voltages = PCA9450_LDO3_VOLTAGE_NUM, + .linear_ranges = pca9450_ldo34_volts, + .n_linear_ranges = ARRAY_SIZE(pca9450_ldo34_volts), + .vsel_reg = PCA9450_REG_LDO3CTRL, + .vsel_mask = LDO3OUT_MASK, + .enable_reg = PCA9450_REG_LDO3CTRL, + .enable_mask = LDO3_EN_MASK, + .owner = THIS_MODULE, + }, + }, { .desc = { .name = "ldo4", @@ -905,6 +934,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) pca9450->rcnt = ARRAY_SIZE(pca9450bc_regulators); break; case PCA9450_TYPE_PCA9451A: + case PCA9450_TYPE_PCA9452: regulator_desc = pca9451a_regulators; pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators); break; @@ -921,25 +951,21 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) pca9450->regmap = devm_regmap_init_i2c(i2c, &pca9450_regmap_config); - if (IS_ERR(pca9450->regmap)) { - dev_err(&i2c->dev, "regmap initialization failed\n"); - return PTR_ERR(pca9450->regmap); - } + if (IS_ERR(pca9450->regmap)) + return dev_err_probe(&i2c->dev, PTR_ERR(pca9450->regmap), + "regmap initialization failed\n"); ret = regmap_read(pca9450->regmap, PCA9450_REG_DEV_ID, &device_id); - if (ret) { - dev_err(&i2c->dev, "Read device id error\n"); - return ret; - } + if (ret) + return dev_err_probe(&i2c->dev, ret, "Read device id error\n"); /* Check your board and dts for match the right pmic */ if (((device_id >> 4) != 0x1 && type == PCA9450_TYPE_PCA9450A) || ((device_id >> 4) != 0x3 && type == PCA9450_TYPE_PCA9450BC) || - ((device_id >> 4) != 0x9 && type == PCA9450_TYPE_PCA9451A)) { - dev_err(&i2c->dev, "Device id(%x) mismatched\n", - device_id >> 4); - return -EINVAL; - } + ((device_id >> 4) != 0x9 && type == PCA9450_TYPE_PCA9451A) || + ((device_id >> 4) != 0x9 && type == PCA9450_TYPE_PCA9452)) + return dev_err_probe(&i2c->dev, -EINVAL, + "Device id(%x) mismatched\n", device_id >> 4); for (i = 0; i < pca9450->rcnt; i++) { const struct regulator_desc *desc; @@ -949,17 +975,16 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) r = ®ulator_desc[i]; desc = &r->desc; + if (type == PCA9450_TYPE_PCA9451A && !strcmp(desc->name, "ldo3")) + continue; + config.regmap = pca9450->regmap; config.dev = pca9450->dev; rdev = devm_regulator_register(pca9450->dev, desc, &config); - if (IS_ERR(rdev)) { - ret = PTR_ERR(rdev); - dev_err(pca9450->dev, - "Failed to register regulator(%s): %d\n", - desc->name, ret); - return ret; - } + if (IS_ERR(rdev)) + return dev_err_probe(pca9450->dev, PTR_ERR(rdev), + "Failed to register regulator(%s)\n", desc->name); } if (pca9450->irq) { @@ -967,29 +992,24 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) pca9450_irq_handler, (IRQF_TRIGGER_FALLING | IRQF_ONESHOT), "pca9450-irq", pca9450); - if (ret != 0) { - dev_err(pca9450->dev, "Failed to request IRQ: %d\n", - pca9450->irq); - return ret; - } + if (ret != 0) + return dev_err_probe(pca9450->dev, ret, "Failed to request IRQ: %d\n", + pca9450->irq); + /* Unmask all interrupt except PWRON/WDOG/RSVD */ ret = regmap_update_bits(pca9450->regmap, PCA9450_REG_INT1_MSK, IRQ_VR_FLT1 | IRQ_VR_FLT2 | IRQ_LOWVSYS | IRQ_THERM_105 | IRQ_THERM_125, IRQ_PWRON | IRQ_WDOGB | IRQ_RSVD); - if (ret) { - dev_err(&i2c->dev, "Unmask irq error\n"); - return ret; - } + if (ret) + return dev_err_probe(&i2c->dev, ret, "Unmask irq error\n"); } /* Clear PRESET_EN bit in BUCK123_DVS to use DVS registers */ ret = regmap_clear_bits(pca9450->regmap, PCA9450_REG_BUCK123_DVS, BUCK123_PRESET_EN); - if (ret) { - dev_err(&i2c->dev, "Failed to clear PRESET_EN bit: %d\n", ret); - return ret; - } + if (ret) + return dev_err_probe(&i2c->dev, ret, "Failed to clear PRESET_EN bit\n"); if (of_property_read_bool(i2c->dev.of_node, "nxp,wdog_b-warm-reset")) reset_ctrl = WDOG_B_CFG_WARM; @@ -999,20 +1019,16 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) /* Set reset behavior on assertion of WDOG_B signal */ ret = regmap_update_bits(pca9450->regmap, PCA9450_REG_RESET_CTRL, WDOG_B_CFG_MASK, reset_ctrl); - if (ret) { - dev_err(&i2c->dev, "Failed to set WDOG_B reset behavior\n"); - return ret; - } + if (ret) + return dev_err_probe(&i2c->dev, ret, "Failed to set WDOG_B reset behavior\n"); if (of_property_read_bool(i2c->dev.of_node, "nxp,i2c-lt-enable")) { /* Enable I2C Level Translator */ ret = regmap_update_bits(pca9450->regmap, PCA9450_REG_CONFIG2, I2C_LT_MASK, I2C_LT_ON_STANDBY_RUN); - if (ret) { - dev_err(&i2c->dev, - "Failed to enable I2C level translator\n"); - return ret; - } + if (ret) + return dev_err_probe(&i2c->dev, ret, + "Failed to enable I2C level translator\n"); } /* @@ -1022,10 +1038,9 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) */ pca9450->sd_vsel_gpio = gpiod_get_optional(pca9450->dev, "sd-vsel", GPIOD_OUT_HIGH); - if (IS_ERR(pca9450->sd_vsel_gpio)) { - dev_err(&i2c->dev, "Failed to get SD_VSEL GPIO\n"); - return PTR_ERR(pca9450->sd_vsel_gpio); - } + if (IS_ERR(pca9450->sd_vsel_gpio)) + return dev_err_probe(&i2c->dev, PTR_ERR(pca9450->sd_vsel_gpio), + "Failed to get SD_VSEL GPIO\n"); dev_info(&i2c->dev, "%s probed.\n", type == PCA9450_TYPE_PCA9450A ? "pca9450a" : @@ -1051,6 +1066,10 @@ static const struct of_device_id pca9450_of_match[] = { .compatible = "nxp,pca9451a", .data = (void *)PCA9450_TYPE_PCA9451A, }, + { + .compatible = "nxp,pca9452", + .data = (void *)PCA9450_TYPE_PCA9452, + }, { } }; MODULE_DEVICE_TABLE(of, pca9450_of_match); diff --git a/drivers/regulator/tps6287x-regulator.c b/drivers/regulator/tps6287x-regulator.c index 97f5ce138548..c0f5f0a186a3 100644 --- a/drivers/regulator/tps6287x-regulator.c +++ b/drivers/regulator/tps6287x-regulator.c @@ -44,10 +44,35 @@ static const unsigned int tps6287x_voltage_range_sel[] = { 0x0, 0x1, 0x2, 0x3 }; +static const unsigned int tps6287x_voltage_range_prefix[] = { + 0x000, 0x100, 0x200, 0x300 +}; + static const unsigned int tps6287x_ramp_table[] = { 10000, 5000, 1250, 500 }; +struct tps6287x_reg_data { + int range; +}; + +static int tps6287x_best_range(struct regulator_config *config, const struct regulator_desc *desc) +{ + const struct linear_range *r; + int i; + + if (!config->init_data->constraints.apply_uV) + return -1; + + for (i = 0; i < desc->n_linear_ranges; i++) { + r = &desc->linear_ranges[i]; + if (r->min <= config->init_data->constraints.min_uV && + config->init_data->constraints.max_uV <= linear_range_get_max_value(r)) + return i; + } + return -1; +} + static int tps6287x_set_mode(struct regulator_dev *rdev, unsigned int mode) { unsigned int val; @@ -91,6 +116,28 @@ static unsigned int tps6287x_of_map_mode(unsigned int mode) } } +static int tps6287x_map_voltage(struct regulator_dev *rdev, int min_uV, int max_uV) +{ + struct tps6287x_reg_data *data = (struct tps6287x_reg_data *)rdev->reg_data; + struct linear_range selected_range; + int selector, voltage; + + if (!data || data->range == -1) + return regulator_map_voltage_pickable_linear_range(rdev, min_uV, max_uV); + + selected_range = rdev->desc->linear_ranges[data->range]; + selector = DIV_ROUND_UP(min_uV - selected_range.min, selected_range.step); + if (selector < selected_range.min_sel || selector > selected_range.max_sel) + return -EINVAL; + + selector |= tps6287x_voltage_range_prefix[data->range]; + voltage = rdev->desc->ops->list_voltage(rdev, selector); + if (voltage < min_uV || voltage > max_uV) + return -EINVAL; + + return selector; +} + static const struct regulator_ops tps6287x_regulator_ops = { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -100,6 +147,7 @@ static const struct regulator_ops tps6287x_regulator_ops = { .get_voltage_sel = regulator_get_voltage_sel_pickable_regmap, .set_voltage_sel = regulator_set_voltage_sel_pickable_regmap, .list_voltage = regulator_list_voltage_pickable_linear_range, + .map_voltage = tps6287x_map_voltage, .set_ramp_delay = regulator_set_ramp_delay_regmap, }; @@ -130,8 +178,14 @@ static int tps6287x_i2c_probe(struct i2c_client *i2c) { struct device *dev = &i2c->dev; struct regulator_config config = {}; + struct tps6287x_reg_data *reg_data; struct regulator_dev *rdev; + reg_data = devm_kzalloc(dev, sizeof(struct tps6287x_reg_data), GFP_KERNEL); + + if (!reg_data) + return -ENOMEM; + config.regmap = devm_regmap_init_i2c(i2c, &tps6287x_regmap_config); if (IS_ERR(config.regmap)) { dev_err(dev, "Failed to init i2c\n"); @@ -143,12 +197,15 @@ static int tps6287x_i2c_probe(struct i2c_client *i2c) config.init_data = of_get_regulator_init_data(dev, dev->of_node, &tps6287x_reg); + reg_data->range = tps6287x_best_range(&config, &tps6287x_reg); + rdev = devm_regulator_register(dev, &tps6287x_reg, &config); if (IS_ERR(rdev)) { dev_err(dev, "Failed to register regulator\n"); return PTR_ERR(rdev); } + rdev->reg_data = (void *)reg_data; dev_dbg(dev, "Probed regulator\n"); return 0; diff --git a/drivers/regulator/tps65219-regulator.c b/drivers/regulator/tps65219-regulator.c index b4065356392f..aa65077f9d41 100644 --- a/drivers/regulator/tps65219-regulator.c +++ b/drivers/regulator/tps65219-regulator.c @@ -287,21 +287,6 @@ static irqreturn_t tps65219_regulator_irq_handler(int irq, void *data) return IRQ_HANDLED; } -static int tps65219_get_rdev_by_name(const char *regulator_name, - struct regulator_dev *rdevtbl[7], - struct regulator_dev **dev) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(regulators); i++) { - if (strcmp(regulator_name, regulators[i].name) == 0) { - *dev = rdevtbl[i]; - return 0; - } - } - return -EINVAL; -} - static int tps65219_regulator_probe(struct platform_device *pdev) { struct tps65219 *tps = dev_get_drvdata(pdev->dev.parent); @@ -312,23 +297,18 @@ static int tps65219_regulator_probe(struct platform_device *pdev) int irq; struct tps65219_regulator_irq_data *irq_data; struct tps65219_regulator_irq_type *irq_type; - struct regulator_dev *rdevtbl[7]; config.dev = tps->dev; config.driver_data = tps; config.regmap = tps->regmap; for (i = 0; i < ARRAY_SIZE(regulators); i++) { - dev_dbg(tps->dev, "%s regul i= %d START", __func__, i); rdev = devm_regulator_register(&pdev->dev, ®ulators[i], &config); - if (IS_ERR(rdev)) { - dev_err(tps->dev, "failed to register %s regulator\n", - regulators[i].name); - return PTR_ERR(rdev); - } - rdevtbl[i] = rdev; - dev_dbg(tps->dev, "%s regul i= %d COMPLETED", __func__, i); + if (IS_ERR(rdev)) + return dev_err_probe(tps->dev, PTR_ERR(rdev), + "Failed to register %s regulator\n", + regulators[i].name); } irq_data = devm_kmalloc(tps->dev, @@ -348,14 +328,6 @@ static int tps65219_regulator_probe(struct platform_device *pdev) irq_data[i].dev = tps->dev; irq_data[i].type = irq_type; - tps65219_get_rdev_by_name(irq_type->regulator_name, rdevtbl, &rdev); - if (IS_ERR(rdev)) { - dev_err(tps->dev, "Failed to get rdev for %s\n", - irq_type->regulator_name); - return -EINVAL; - } - irq_data[i].rdev = rdev; - error = devm_request_threaded_irq(tps->dev, irq, NULL, tps65219_regulator_irq_handler, IRQF_ONESHOT, @@ -379,7 +351,7 @@ MODULE_DEVICE_TABLE(platform, tps65219_regulator_id_table); static struct platform_driver tps65219_regulator_driver = { .driver = { - .name = "tps65219-pmic", + .name = "tps65219-regulator", .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, .probe = tps65219_regulator_probe, @@ -390,5 +362,4 @@ module_platform_driver(tps65219_regulator_driver); MODULE_AUTHOR("Jerome Neanne "); MODULE_DESCRIPTION("TPS65219 voltage regulator driver"); -MODULE_ALIAS("platform:tps65219-pmic"); MODULE_LICENSE("GPL"); diff --git a/drivers/remoteproc/keystone_remoteproc.c b/drivers/remoteproc/keystone_remoteproc.c index 6e54093d1732..7b41b4547fa8 100644 --- a/drivers/remoteproc/keystone_remoteproc.c +++ b/drivers/remoteproc/keystone_remoteproc.c @@ -335,25 +335,16 @@ static int keystone_rproc_of_get_dev_syscon(struct platform_device *pdev, { struct device_node *np = pdev->dev.of_node; struct device *dev = &pdev->dev; - int ret; if (!of_property_read_bool(np, "ti,syscon-dev")) { dev_err(dev, "ti,syscon-dev property is absent\n"); return -EINVAL; } - ksproc->dev_ctrl = - syscon_regmap_lookup_by_phandle(np, "ti,syscon-dev"); - if (IS_ERR(ksproc->dev_ctrl)) { - ret = PTR_ERR(ksproc->dev_ctrl); - return ret; - } - - if (of_property_read_u32_index(np, "ti,syscon-dev", 1, - &ksproc->boot_offset)) { - dev_err(dev, "couldn't read the boot register offset\n"); - return -EINVAL; - } + ksproc->dev_ctrl = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-dev", + 1, &ksproc->boot_offset); + if (IS_ERR(ksproc->dev_ctrl)) + return PTR_ERR(ksproc->dev_ctrl); return 0; } diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c index 0f4a7065d0bd..8206a1766481 100644 --- a/drivers/remoteproc/mtk_scp.c +++ b/drivers/remoteproc/mtk_scp.c @@ -1326,6 +1326,11 @@ static int scp_cluster_init(struct platform_device *pdev, struct mtk_scp_of_clus return ret; } +static const struct of_device_id scp_core_match[] = { + { .compatible = "mediatek,scp-core" }, + {} +}; + static int scp_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1357,13 +1362,15 @@ static int scp_probe(struct platform_device *pdev) INIT_LIST_HEAD(&scp_cluster->mtk_scp_list); mutex_init(&scp_cluster->cluster_lock); - ret = devm_of_platform_populate(dev); + ret = of_platform_populate(dev_of_node(dev), scp_core_match, NULL, dev); if (ret) return dev_err_probe(dev, ret, "Failed to populate platform devices\n"); ret = scp_cluster_init(pdev, scp_cluster); - if (ret) + if (ret) { + of_platform_depopulate(dev); return ret; + } return 0; } @@ -1379,6 +1386,7 @@ static void scp_remove(struct platform_device *pdev) rproc_del(scp->rproc); scp_free(scp); } + of_platform_depopulate(&pdev->dev); mutex_destroy(&scp_cluster->cluster_lock); } diff --git a/drivers/remoteproc/omap_remoteproc.c b/drivers/remoteproc/omap_remoteproc.c index 9ae2e831456d..5f463937cbbf 100644 --- a/drivers/remoteproc/omap_remoteproc.c +++ b/drivers/remoteproc/omap_remoteproc.c @@ -37,6 +37,10 @@ #include +#ifdef CONFIG_ARM_DMA_USE_IOMMU +#include +#endif + #include "omap_remoteproc.h" #include "remoteproc_internal.h" @@ -1133,7 +1137,6 @@ static int omap_rproc_get_boot_data(struct platform_device *pdev, struct device_node *np = pdev->dev.of_node; struct omap_rproc *oproc = rproc->priv; const struct omap_rproc_dev_data *data; - int ret; data = of_device_get_match_data(&pdev->dev); if (!data) @@ -1149,10 +1152,8 @@ static int omap_rproc_get_boot_data(struct platform_device *pdev, oproc->boot_data->syscon = syscon_regmap_lookup_by_phandle(np, "ti,bootreg"); - if (IS_ERR(oproc->boot_data->syscon)) { - ret = PTR_ERR(oproc->boot_data->syscon); - return ret; - } + if (IS_ERR(oproc->boot_data->syscon)) + return PTR_ERR(oproc->boot_data->syscon); if (of_property_read_u32_index(np, "ti,bootreg", 1, &oproc->boot_data->boot_reg)) { @@ -1323,6 +1324,19 @@ static int omap_rproc_probe(struct platform_device *pdev) /* All existing OMAP IPU and DSP processors have an MMU */ rproc->has_iommu = true; +#ifdef CONFIG_ARM_DMA_USE_IOMMU + /* + * Throw away the ARM DMA mapping that we'll never use, so it doesn't + * interfere with the core rproc->domain and we get the right DMA ops. + */ + if (pdev->dev.archdata.mapping) { + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(&pdev->dev); + + arm_iommu_detach_device(&pdev->dev); + arm_iommu_release_mapping(mapping); + } +#endif + ret = omap_rproc_of_get_internal_memories(pdev, rproc); if (ret) return ret; diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index eb66f78ec8b7..c2cf0d277729 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -2486,6 +2486,13 @@ struct rproc *rproc_alloc(struct device *dev, const char *name, rproc->dev.driver_data = rproc; idr_init(&rproc->notifyids); + /* Assign a unique device index and name */ + rproc->index = ida_alloc(&rproc_dev_index, GFP_KERNEL); + if (rproc->index < 0) { + dev_err(dev, "ida_alloc failed: %d\n", rproc->index); + goto put_device; + } + rproc->name = kstrdup_const(name, GFP_KERNEL); if (!rproc->name) goto put_device; @@ -2496,13 +2503,6 @@ struct rproc *rproc_alloc(struct device *dev, const char *name, if (rproc_alloc_ops(rproc, ops)) goto put_device; - /* Assign a unique device index and name */ - rproc->index = ida_alloc(&rproc_dev_index, GFP_KERNEL); - if (rproc->index < 0) { - dev_err(dev, "ida_alloc failed: %d\n", rproc->index); - goto put_device; - } - dev_set_name(&rproc->dev, "remoteproc%d", rproc->index); atomic_set(&rproc->power, 0); diff --git a/drivers/remoteproc/st_remoteproc.c b/drivers/remoteproc/st_remoteproc.c index 5df99bae7131..e6566a9839dc 100644 --- a/drivers/remoteproc/st_remoteproc.c +++ b/drivers/remoteproc/st_remoteproc.c @@ -290,26 +290,23 @@ static int st_rproc_parse_dt(struct platform_device *pdev) if (ddata->config->sw_reset) { ddata->sw_reset = devm_reset_control_get_exclusive(dev, "sw_reset"); - if (IS_ERR(ddata->sw_reset)) { - dev_err(dev, "Failed to get S/W Reset\n"); - return PTR_ERR(ddata->sw_reset); - } + if (IS_ERR(ddata->sw_reset)) + return dev_err_probe(dev, PTR_ERR(ddata->sw_reset), + "Failed to get S/W Reset\n"); } if (ddata->config->pwr_reset) { ddata->pwr_reset = devm_reset_control_get_exclusive(dev, "pwr_reset"); - if (IS_ERR(ddata->pwr_reset)) { - dev_err(dev, "Failed to get Power Reset\n"); - return PTR_ERR(ddata->pwr_reset); - } + if (IS_ERR(ddata->pwr_reset)) + return dev_err_probe(dev, PTR_ERR(ddata->pwr_reset), + "Failed to get Power Reset\n"); } ddata->clk = devm_clk_get(dev, NULL); - if (IS_ERR(ddata->clk)) { - dev_err(dev, "Failed to get clock\n"); - return PTR_ERR(ddata->clk); - } + if (IS_ERR(ddata->clk)) + return dev_err_probe(dev, PTR_ERR(ddata->clk), + "Failed to get clock\n"); err = of_property_read_u32(np, "clock-frequency", &ddata->clk_rate); if (err) { @@ -317,18 +314,11 @@ static int st_rproc_parse_dt(struct platform_device *pdev) return err; } - ddata->boot_base = syscon_regmap_lookup_by_phandle(np, "st,syscfg"); - if (IS_ERR(ddata->boot_base)) { - dev_err(dev, "Boot base not found\n"); - return PTR_ERR(ddata->boot_base); - } - - err = of_property_read_u32_index(np, "st,syscfg", 1, - &ddata->boot_offset); - if (err) { - dev_err(dev, "Boot offset not found\n"); - return -EINVAL; - } + ddata->boot_base = syscon_regmap_lookup_by_phandle_args(np, "st,syscfg", + 1, &ddata->boot_offset); + if (IS_ERR(ddata->boot_base)) + return dev_err_probe(dev, PTR_ERR(ddata->boot_base), + "Boot base not found\n"); err = clk_prepare(ddata->clk); if (err) @@ -395,32 +385,32 @@ static int st_rproc_probe(struct platform_device *pdev) */ chan = mbox_request_channel_byname(&ddata->mbox_client_vq0, "vq0_rx"); if (IS_ERR(chan)) { - dev_err(&rproc->dev, "failed to request mbox chan 0\n"); - ret = PTR_ERR(chan); + ret = dev_err_probe(&rproc->dev, PTR_ERR(chan), + "failed to request mbox chan 0\n"); goto free_clk; } ddata->mbox_chan[ST_RPROC_VQ0 * MBOX_MAX + MBOX_RX] = chan; chan = mbox_request_channel_byname(&ddata->mbox_client_vq0, "vq0_tx"); if (IS_ERR(chan)) { - dev_err(&rproc->dev, "failed to request mbox chan 0\n"); - ret = PTR_ERR(chan); + ret = dev_err_probe(&rproc->dev, PTR_ERR(chan), + "failed to request mbox chan 0\n"); goto free_mbox; } ddata->mbox_chan[ST_RPROC_VQ0 * MBOX_MAX + MBOX_TX] = chan; chan = mbox_request_channel_byname(&ddata->mbox_client_vq1, "vq1_rx"); if (IS_ERR(chan)) { - dev_err(&rproc->dev, "failed to request mbox chan 1\n"); - ret = PTR_ERR(chan); + ret = dev_err_probe(&rproc->dev, PTR_ERR(chan), + "failed to request mbox chan 1\n"); goto free_mbox; } ddata->mbox_chan[ST_RPROC_VQ1 * MBOX_MAX + MBOX_RX] = chan; chan = mbox_request_channel_byname(&ddata->mbox_client_vq1, "vq1_tx"); if (IS_ERR(chan)) { - dev_err(&rproc->dev, "failed to request mbox chan 1\n"); - ret = PTR_ERR(chan); + ret = dev_err_probe(&rproc->dev, PTR_ERR(chan), + "failed to request mbox chan 1\n"); goto free_mbox; } ddata->mbox_chan[ST_RPROC_VQ1 * MBOX_MAX + MBOX_TX] = chan; diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c index 6560b7954027..dbc513c5569c 100644 --- a/drivers/remoteproc/ti_k3_r5_remoteproc.c +++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c @@ -955,6 +955,13 @@ out: return ret; } +static void k3_r5_mem_release(void *data) +{ + struct device *dev = data; + + of_reserved_mem_device_release(dev); +} + static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc) { struct device *dev = kproc->dev; @@ -985,27 +992,25 @@ static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc) return ret; } + ret = devm_add_action_or_reset(dev, k3_r5_mem_release, dev); + if (ret) + return ret; + num_rmems--; - kproc->rmem = kcalloc(num_rmems, sizeof(*kproc->rmem), GFP_KERNEL); - if (!kproc->rmem) { - ret = -ENOMEM; - goto release_rmem; - } + kproc->rmem = devm_kcalloc(dev, num_rmems, sizeof(*kproc->rmem), GFP_KERNEL); + if (!kproc->rmem) + return -ENOMEM; /* use remaining reserved memory regions for static carveouts */ for (i = 0; i < num_rmems; i++) { rmem_np = of_parse_phandle(np, "memory-region", i + 1); - if (!rmem_np) { - ret = -EINVAL; - goto unmap_rmem; - } + if (!rmem_np) + return -EINVAL; rmem = of_reserved_mem_lookup(rmem_np); of_node_put(rmem_np); - if (!rmem) { - ret = -EINVAL; - goto unmap_rmem; - } + if (!rmem) + return -EINVAL; kproc->rmem[i].bus_addr = rmem->base; /* @@ -1020,12 +1025,11 @@ static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc) */ kproc->rmem[i].dev_addr = (u32)rmem->base; kproc->rmem[i].size = rmem->size; - kproc->rmem[i].cpu_addr = ioremap_wc(rmem->base, rmem->size); + kproc->rmem[i].cpu_addr = devm_ioremap_wc(dev, rmem->base, rmem->size); if (!kproc->rmem[i].cpu_addr) { dev_err(dev, "failed to map reserved memory#%d at %pa of size %pa\n", i + 1, &rmem->base, &rmem->size); - ret = -ENOMEM; - goto unmap_rmem; + return -ENOMEM; } dev_dbg(dev, "reserved memory%d: bus addr %pa size 0x%zx va %pK da 0x%x\n", @@ -1036,25 +1040,6 @@ static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc) kproc->num_rmems = num_rmems; return 0; - -unmap_rmem: - for (i--; i >= 0; i--) - iounmap(kproc->rmem[i].cpu_addr); - kfree(kproc->rmem); -release_rmem: - of_reserved_mem_device_release(dev); - return ret; -} - -static void k3_r5_reserved_mem_exit(struct k3_r5_rproc *kproc) -{ - int i; - - for (i = 0; i < kproc->num_rmems; i++) - iounmap(kproc->rmem[i].cpu_addr); - kfree(kproc->rmem); - - of_reserved_mem_device_release(kproc->dev); } /* @@ -1281,10 +1266,10 @@ init_rmem: goto out; } - ret = rproc_add(rproc); + ret = devm_rproc_add(dev, rproc); if (ret) { - dev_err(dev, "rproc_add failed, ret = %d\n", ret); - goto err_add; + dev_err_probe(dev, ret, "rproc_add failed\n"); + goto out; } /* create only one rproc in lockstep, single-cpu or @@ -1312,7 +1297,7 @@ init_rmem: dev_err(dev, "Timed out waiting for %s core to power up!\n", rproc->name); - goto err_powerup; + goto out; } } @@ -1328,10 +1313,6 @@ err_split: } } -err_powerup: - rproc_del(rproc); -err_add: - k3_r5_reserved_mem_exit(kproc); out: /* undo core0 upon any failures on core1 in split-mode */ if (cluster->mode == CLUSTER_MODE_SPLIT && core == core1) { @@ -1374,10 +1355,6 @@ static void k3_r5_cluster_rproc_exit(void *data) } mbox_free_channel(kproc->mbox); - - rproc_del(rproc); - - k3_r5_reserved_mem_exit(kproc); } } @@ -1510,6 +1487,13 @@ static int k3_r5_core_of_get_sram_memories(struct platform_device *pdev, return 0; } +static void k3_r5_release_tsp(void *data) +{ + struct ti_sci_proc *tsp = data; + + ti_sci_proc_release(tsp); +} + static int k3_r5_core_of_init(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1603,6 +1587,10 @@ static int k3_r5_core_of_init(struct platform_device *pdev) goto err; } + ret = devm_add_action_or_reset(dev, k3_r5_release_tsp, core->tsp); + if (ret) + goto err; + platform_set_drvdata(pdev, core); devres_close_group(dev, k3_r5_core_of_init); @@ -1619,13 +1607,7 @@ err: */ static void k3_r5_core_of_exit(struct platform_device *pdev) { - struct k3_r5_core *core = platform_get_drvdata(pdev); struct device *dev = &pdev->dev; - int ret; - - ret = ti_sci_proc_release(core->tsp); - if (ret) - dev_err(dev, "failed to release proc, ret = %d\n", ret); platform_set_drvdata(pdev, NULL); devres_release_group(dev, k3_r5_core_of_init); diff --git a/drivers/reset/amlogic/reset-meson-aux.c b/drivers/reset/amlogic/reset-meson-aux.c index 61ce515d92a2..33c06013439e 100644 --- a/drivers/reset/amlogic/reset-meson-aux.c +++ b/drivers/reset/amlogic/reset-meson-aux.c @@ -11,20 +11,20 @@ #include #include #include -#include #include "reset-meson.h" -#include -static DEFINE_IDA(meson_rst_aux_ida); - -struct meson_reset_adev { - struct auxiliary_device adev; - struct regmap *map; +static const struct meson_reset_param meson_a1_audio_param = { + .reset_ops = &meson_reset_toggle_ops, + .reset_num = 32, + .level_offset = 0x28, }; -#define to_meson_reset_adev(_adev) \ - container_of((_adev), struct meson_reset_adev, adev) +static const struct meson_reset_param meson_a1_audio_vad_param = { + .reset_ops = &meson_reset_toggle_ops, + .reset_num = 6, + .level_offset = 0x8, +}; static const struct meson_reset_param meson_g12a_audio_param = { .reset_ops = &meson_reset_toggle_ops, @@ -40,6 +40,12 @@ static const struct meson_reset_param meson_sm1_audio_param = { static const struct auxiliary_device_id meson_reset_aux_ids[] = { { + .name = "a1-audio-clkc.rst-a1", + .driver_data = (kernel_ulong_t)&meson_a1_audio_param, + }, { + .name = "a1-audio-clkc.rst-a1-vad", + .driver_data = (kernel_ulong_t)&meson_a1_audio_vad_param, + }, { .name = "axg-audio-clkc.rst-g12a", .driver_data = (kernel_ulong_t)&meson_g12a_audio_param, }, { @@ -54,10 +60,13 @@ static int meson_reset_aux_probe(struct auxiliary_device *adev, { const struct meson_reset_param *param = (const struct meson_reset_param *)(id->driver_data); - struct meson_reset_adev *raux = - to_meson_reset_adev(adev); + struct regmap *map; - return meson_reset_controller_register(&adev->dev, raux->map, param); + map = dev_get_regmap(adev->dev.parent, NULL); + if (!map) + return -EINVAL; + + return meson_reset_controller_register(&adev->dev, map, param); } static struct auxiliary_driver meson_reset_aux_driver = { @@ -66,70 +75,6 @@ static struct auxiliary_driver meson_reset_aux_driver = { }; module_auxiliary_driver(meson_reset_aux_driver); -static void meson_rst_aux_release(struct device *dev) -{ - struct auxiliary_device *adev = to_auxiliary_dev(dev); - struct meson_reset_adev *raux = - to_meson_reset_adev(adev); - - ida_free(&meson_rst_aux_ida, adev->id); - kfree(raux); -} - -static void meson_rst_aux_unregister_adev(void *_adev) -{ - struct auxiliary_device *adev = _adev; - - auxiliary_device_delete(adev); - auxiliary_device_uninit(adev); -} - -int devm_meson_rst_aux_register(struct device *dev, - struct regmap *map, - const char *adev_name) -{ - struct meson_reset_adev *raux; - struct auxiliary_device *adev; - int ret; - - raux = kzalloc(sizeof(*raux), GFP_KERNEL); - if (!raux) - return -ENOMEM; - - ret = ida_alloc(&meson_rst_aux_ida, GFP_KERNEL); - if (ret < 0) - goto raux_free; - - raux->map = map; - - adev = &raux->adev; - adev->id = ret; - adev->name = adev_name; - adev->dev.parent = dev; - adev->dev.release = meson_rst_aux_release; - device_set_of_node_from_dev(&adev->dev, dev); - - ret = auxiliary_device_init(adev); - if (ret) - goto ida_free; - - ret = __auxiliary_device_add(adev, dev->driver->name); - if (ret) { - auxiliary_device_uninit(adev); - return ret; - } - - return devm_add_action_or_reset(dev, meson_rst_aux_unregister_adev, - adev); - -ida_free: - ida_free(&meson_rst_aux_ida, adev->id); -raux_free: - kfree(raux); - return ret; -} -EXPORT_SYMBOL_GPL(devm_meson_rst_aux_register); - MODULE_DESCRIPTION("Amlogic Meson Reset Auxiliary driver"); MODULE_AUTHOR("Jerome Brunet "); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c index 12d0535a874b..8a7f167e405e 100644 --- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c +++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c @@ -176,6 +176,7 @@ static int rzg2l_usbphy_ctrl_probe(struct platform_device *pdev) vdev->dev.parent = dev; priv->vdev = vdev; + device_set_of_node_from_dev(&vdev->dev, dev); error = platform_device_add(vdev); if (error) goto err_device_put; diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index 712c06c02696..207b64c0a2fe 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -377,9 +377,9 @@ EXPORT_SYMBOL(rpmsg_get_mtu); * this is used to make sure we're not creating rpmsg devices for channels * that already exist. */ -static int rpmsg_device_match(struct device *dev, void *data) +static int rpmsg_device_match(struct device *dev, const void *data) { - struct rpmsg_channel_info *chinfo = data; + const struct rpmsg_channel_info *chinfo = data; struct rpmsg_device *rpdev = to_rpmsg_device(dev); if (chinfo->src != RPMSG_ADDR_ANY && chinfo->src != rpdev->src) diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index a60bcc791a48..0bbbf778ecfa 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1316,7 +1316,7 @@ config RTC_DRV_SC27XX config RTC_DRV_SPEAR tristate "SPEAR ST RTC" depends on PLAT_SPEAR || COMPILE_TEST - default y + default PLAT_SPEAR help If you say Y here you will get support for the RTC found on spear diff --git a/drivers/rtc/rtc-88pm80x.c b/drivers/rtc/rtc-88pm80x.c index 5c39cf252392..a3e52a5a708f 100644 --- a/drivers/rtc/rtc-88pm80x.c +++ b/drivers/rtc/rtc-88pm80x.c @@ -308,7 +308,7 @@ static int pm80x_rtc_probe(struct platform_device *pdev) /* remember whether this power up is caused by PMIC RTC or not */ info->rtc_dev->dev.platform_data = &pdata->rtc_wakeup; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return 0; out_rtc: diff --git a/drivers/rtc/rtc-88pm860x.c b/drivers/rtc/rtc-88pm860x.c index 814230d61842..964cd048fcdb 100644 --- a/drivers/rtc/rtc-88pm860x.c +++ b/drivers/rtc/rtc-88pm860x.c @@ -326,7 +326,7 @@ static int pm860x_rtc_probe(struct platform_device *pdev) schedule_delayed_work(&info->calib_work, VRTC_CALIB_INTERVAL); #endif /* VRTC_CALIBRATION */ - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return 0; } diff --git a/drivers/rtc/rtc-amlogic-a4.c b/drivers/rtc/rtc-amlogic-a4.c index 2278b4c98a71..09d78c2cc691 100644 --- a/drivers/rtc/rtc-amlogic-a4.c +++ b/drivers/rtc/rtc-amlogic-a4.c @@ -361,7 +361,7 @@ static int aml_rtc_probe(struct platform_device *pdev) "failed to get_enable rtc sys clk\n"); aml_rtc_init(rtc); - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); platform_set_drvdata(pdev, rtc); rtc->rtc_dev = devm_rtc_allocate_device(dev); @@ -391,7 +391,7 @@ static int aml_rtc_probe(struct platform_device *pdev) return 0; err_clk: clk_disable_unprepare(rtc->sys_clk); - device_init_wakeup(dev, 0); + device_init_wakeup(dev, false); return ret; } @@ -426,7 +426,7 @@ static void aml_rtc_remove(struct platform_device *pdev) struct aml_rtc_data *rtc = dev_get_drvdata(&pdev->dev); clk_disable_unprepare(rtc->sys_clk); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); } static const struct aml_rtc_config a5_rtc_config = { diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c index 569c1054d6b0..713fa0d077cd 100644 --- a/drivers/rtc/rtc-armada38x.c +++ b/drivers/rtc/rtc-armada38x.c @@ -527,7 +527,7 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc); if (rtc->irq != -1) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); else clear_bit(RTC_FEATURE_ALARM, rtc->rtc_dev->features); diff --git a/drivers/rtc/rtc-as3722.c b/drivers/rtc/rtc-as3722.c index 0f21af27f4cf..9682d6457b7f 100644 --- a/drivers/rtc/rtc-as3722.c +++ b/drivers/rtc/rtc-as3722.c @@ -187,7 +187,7 @@ static int as3722_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); as3722_rtc->rtc = devm_rtc_device_register(&pdev->dev, "as3722-rtc", &as3722_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c index 9b3898b8de7c..f6b0102a843a 100644 --- a/drivers/rtc/rtc-at91rm9200.c +++ b/drivers/rtc/rtc-at91rm9200.c @@ -528,7 +528,7 @@ static int __init at91_rtc_probe(struct platform_device *pdev) * being wake-capable; if it didn't, do that here. */ if (!device_can_wakeup(&pdev->dev)) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); if (at91_rtc_config->has_correction) rtc->ops = &sama5d4_rtc_ops; diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c index 15b21da2788f..38991cca5930 100644 --- a/drivers/rtc/rtc-at91sam9.c +++ b/drivers/rtc/rtc-at91sam9.c @@ -353,7 +353,7 @@ static int at91_rtc_probe(struct platform_device *pdev) /* platform setup code should have handled this; sigh */ if (!device_can_wakeup(&pdev->dev)) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); platform_set_drvdata(pdev, rtc); diff --git a/drivers/rtc/rtc-cadence.c b/drivers/rtc/rtc-cadence.c index bf2a9a1fdea7..8634eea799ab 100644 --- a/drivers/rtc/rtc-cadence.c +++ b/drivers/rtc/rtc-cadence.c @@ -359,7 +359,7 @@ static void cdns_rtc_remove(struct platform_device *pdev) struct cdns_rtc *crtc = platform_get_drvdata(pdev); cdns_rtc_alarm_irq_enable(&pdev->dev, 0); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); clk_disable_unprepare(crtc->pclk); clk_disable_unprepare(crtc->ref_clk); diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 78f2ce12c75a..8172869bd3d7 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -151,11 +151,6 @@ static inline int hpet_set_periodic_freq(unsigned long freq) return 0; } -static inline int hpet_rtc_dropped_irq(void) -{ - return 0; -} - static inline int hpet_rtc_timer_init(void) { return 0; @@ -864,7 +859,7 @@ static void acpi_cmos_wake_setup(struct device *dev) dev_info(dev, "RTC can wake from S4\n"); /* RTC always wakes from S1/S2/S3, and often S4/STD */ - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); } static void cmos_check_acpi_rtc_status(struct device *dev, diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c index afc8fcba8f88..568a89e79c11 100644 --- a/drivers/rtc/rtc-cpcap.c +++ b/drivers/rtc/rtc-cpcap.c @@ -295,7 +295,7 @@ static int cpcap_rtc_probe(struct platform_device *pdev) } disable_irq(rtc->update_irq); - err = device_init_wakeup(dev, 1); + err = device_init_wakeup(dev, true); if (err) { dev_err(dev, "wakeup initialization failed (%d)\n", err); /* ignore error and continue without wakeup support */ diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c index 60a48c3ba3ca..865c2e82c7a5 100644 --- a/drivers/rtc/rtc-cros-ec.c +++ b/drivers/rtc/rtc-cros-ec.c @@ -337,7 +337,7 @@ static int cros_ec_rtc_probe(struct platform_device *pdev) return ret; } - ret = device_init_wakeup(&pdev->dev, 1); + ret = device_init_wakeup(&pdev->dev, true); if (ret) { dev_err(&pdev->dev, "failed to initialize wakeup\n"); return ret; diff --git a/drivers/rtc/rtc-da9055.c b/drivers/rtc/rtc-da9055.c index 844168fcae1e..05adec6b77bf 100644 --- a/drivers/rtc/rtc-da9055.c +++ b/drivers/rtc/rtc-da9055.c @@ -288,7 +288,7 @@ static int da9055_rtc_probe(struct platform_device *pdev) if (ret & DA9055_RTC_ALM_EN) rtc->alarm_enable = 1; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &da9055_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c index dd37b055693c..19c09c418746 100644 --- a/drivers/rtc/rtc-ds3232.c +++ b/drivers/rtc/rtc-ds3232.c @@ -508,7 +508,7 @@ static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq, return ret; if (ds3232->irq > 0) - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); ds3232_hwmon_register(dev, name); diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c index 7b82e4a14b7a..f71a6bb77b2a 100644 --- a/drivers/rtc/rtc-isl1208.c +++ b/drivers/rtc/rtc-isl1208.c @@ -830,7 +830,7 @@ static int isl1208_setup_irq(struct i2c_client *client, int irq) isl1208_driver.driver.name, client); if (!rc) { - device_init_wakeup(&client->dev, 1); + device_init_wakeup(&client->dev, true); enable_irq_wake(irq); } else { dev_err(&client->dev, diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c index bafa7d1b9b88..44bba356268c 100644 --- a/drivers/rtc/rtc-jz4740.c +++ b/drivers/rtc/rtc-jz4740.c @@ -367,7 +367,7 @@ static int jz4740_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc); - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); ret = dev_pm_set_wake_irq(dev, irq); if (ret) diff --git a/drivers/rtc/rtc-loongson.c b/drivers/rtc/rtc-loongson.c index 8d713e563d7c..97e5625c064c 100644 --- a/drivers/rtc/rtc-loongson.c +++ b/drivers/rtc/rtc-loongson.c @@ -114,6 +114,13 @@ static irqreturn_t loongson_rtc_isr(int irq, void *id) struct loongson_rtc_priv *priv = (struct loongson_rtc_priv *)id; rtc_update_irq(priv->rtcdev, 1, RTC_AF | RTC_IRQF); + + /* + * The TOY_MATCH0_REG should be cleared 0 here, + * otherwise the interrupt cannot be cleared. + */ + regmap_write(priv->regmap, TOY_MATCH0_REG, 0); + return IRQ_HANDLED; } @@ -131,11 +138,7 @@ static u32 loongson_rtc_handler(void *id) writel(RTC_STS, priv->pm_base + PM1_STS_REG); spin_unlock(&priv->lock); - /* - * The TOY_MATCH0_REG should be cleared 0 here, - * otherwise the interrupt cannot be cleared. - */ - return regmap_write(priv->regmap, TOY_MATCH0_REG, 0); + return ACPI_INTERRUPT_HANDLED; } static int loongson_rtc_set_enabled(struct device *dev) @@ -329,7 +332,7 @@ static int loongson_rtc_probe(struct platform_device *pdev) alarm_irq); priv->pm_base = regs - priv->config->pm_offset; - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); if (has_acpi_companion(dev)) acpi_install_fixed_event_handler(ACPI_EVENT_RTC, @@ -360,7 +363,7 @@ static void loongson_rtc_remove(struct platform_device *pdev) acpi_remove_fixed_event_handler(ACPI_EVENT_RTC, loongson_rtc_handler); - device_init_wakeup(dev, 0); + device_init_wakeup(dev, false); loongson_rtc_alarm_irq_enable(dev, 0); } diff --git a/drivers/rtc/rtc-lp8788.c b/drivers/rtc/rtc-lp8788.c index c0b8fbce1082..0793d70507f7 100644 --- a/drivers/rtc/rtc-lp8788.c +++ b/drivers/rtc/rtc-lp8788.c @@ -293,7 +293,7 @@ static int lp8788_rtc_probe(struct platform_device *pdev) rtc->alarm = lp->pdata ? lp->pdata->alarm_sel : DEFAULT_ALARM_SEL; platform_set_drvdata(pdev, rtc); - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); rtc->rdev = devm_rtc_device_register(dev, "lp8788_rtc", &lp8788_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-lpc32xx.c b/drivers/rtc/rtc-lpc32xx.c index 76ad7031a13d..74280bffe1b0 100644 --- a/drivers/rtc/rtc-lpc32xx.c +++ b/drivers/rtc/rtc-lpc32xx.c @@ -257,7 +257,7 @@ static int lpc32xx_rtc_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "Can't request interrupt.\n"); rtc->irq = -1; } else { - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); } } diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c index a8f4b645c09d..7bb044d2ac25 100644 --- a/drivers/rtc/rtc-max77686.c +++ b/drivers/rtc/rtc-max77686.c @@ -770,7 +770,7 @@ static int max77686_rtc_probe(struct platform_device *pdev) goto err_rtc; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); info->rtc_dev = devm_rtc_device_register(&pdev->dev, id->name, &max77686_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-max8925.c b/drivers/rtc/rtc-max8925.c index 64bb8ac6ef62..6ce8afbeac68 100644 --- a/drivers/rtc/rtc-max8925.c +++ b/drivers/rtc/rtc-max8925.c @@ -270,7 +270,7 @@ static int max8925_rtc_probe(struct platform_device *pdev) /* XXX - isn't this redundant? */ platform_set_drvdata(pdev, info); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max8925-rtc", &max8925_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-max8997.c b/drivers/rtc/rtc-max8997.c index 20e50d9fdf88..e7618d715bd8 100644 --- a/drivers/rtc/rtc-max8997.c +++ b/drivers/rtc/rtc-max8997.c @@ -473,7 +473,7 @@ static int max8997_rtc_probe(struct platform_device *pdev) max8997_rtc_enable_wtsr(info, true); max8997_rtc_enable_smpl(info, true); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max8997-rtc", &max8997_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-meson-vrtc.c b/drivers/rtc/rtc-meson-vrtc.c index 648fa362ec44..5849729f7d01 100644 --- a/drivers/rtc/rtc-meson-vrtc.c +++ b/drivers/rtc/rtc-meson-vrtc.c @@ -74,7 +74,7 @@ static int meson_vrtc_probe(struct platform_device *pdev) if (IS_ERR(vrtc->io_alarm)) return PTR_ERR(vrtc->io_alarm); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); platform_set_drvdata(pdev, vrtc); diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c index 600328131603..b90f8337a7e6 100644 --- a/drivers/rtc/rtc-mpc5121.c +++ b/drivers/rtc/rtc-mpc5121.c @@ -303,7 +303,7 @@ static int mpc5121_rtc_probe(struct platform_device *op) return PTR_ERR(rtc->regs); } - device_init_wakeup(&op->dev, 1); + device_init_wakeup(&op->dev, true); platform_set_drvdata(op, rtc); diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c index 152699219a2b..6979d225a78e 100644 --- a/drivers/rtc/rtc-mt6397.c +++ b/drivers/rtc/rtc-mt6397.c @@ -286,7 +286,7 @@ static int mtk_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rtc->rtc_dev->ops = &mtk_rtc_ops; rtc->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_1900; diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c index 51029c536244..c27ad626d09f 100644 --- a/drivers/rtc/rtc-mv.c +++ b/drivers/rtc/rtc-mv.c @@ -264,7 +264,7 @@ static int __init mv_rtc_probe(struct platform_device *pdev) } if (pdata->irq >= 0) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); else clear_bit(RTC_FEATURE_ALARM, pdata->rtc->features); @@ -287,7 +287,7 @@ static void __exit mv_rtc_remove(struct platform_device *pdev) struct rtc_plat_data *pdata = platform_get_drvdata(pdev); if (pdata->irq >= 0) - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); if (!IS_ERR(pdata->clk)) clk_disable_unprepare(pdata->clk); diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c index dbb935dbbd8a..608db97d450c 100644 --- a/drivers/rtc/rtc-mxc.c +++ b/drivers/rtc/rtc-mxc.c @@ -377,7 +377,7 @@ static int mxc_rtc_probe(struct platform_device *pdev) } if (pdata->irq >= 0) { - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); ret = dev_pm_set_wake_irq(&pdev->dev, pdata->irq); if (ret) dev_err(&pdev->dev, "failed to enable irq wake\n"); diff --git a/drivers/rtc/rtc-mxc_v2.c b/drivers/rtc/rtc-mxc_v2.c index 13c041bb79f1..570f27af4732 100644 --- a/drivers/rtc/rtc-mxc_v2.c +++ b/drivers/rtc/rtc-mxc_v2.c @@ -302,7 +302,7 @@ static int mxc_rtc_probe(struct platform_device *pdev) if (pdata->irq < 0) return pdata->irq; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); ret = dev_pm_set_wake_irq(&pdev->dev, pdata->irq); if (ret) dev_err(&pdev->dev, "failed to enable irq wake\n"); diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c index c123778e2d9b..0f90065e352c 100644 --- a/drivers/rtc/rtc-omap.c +++ b/drivers/rtc/rtc-omap.c @@ -920,7 +920,7 @@ static void omap_rtc_remove(struct platform_device *pdev) omap_rtc_power_off_rtc = NULL; } - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); if (!IS_ERR(rtc->clk)) clk_disable_unprepare(rtc->clk); diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c index 7256a88b490c..aecada6bcf8b 100644 --- a/drivers/rtc/rtc-palmas.c +++ b/drivers/rtc/rtc-palmas.c @@ -287,7 +287,7 @@ static int palmas_rtc_probe(struct platform_device *pdev) palmas_rtc->irq = platform_get_irq(pdev, 0); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); palmas_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &palmas_rtc_ops, THIS_MODULE); if (IS_ERR(palmas_rtc->rtc)) { diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c index 9c04c4e1a49c..31c7dca8f469 100644 --- a/drivers/rtc/rtc-pcf2127.c +++ b/drivers/rtc/rtc-pcf2127.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -48,6 +49,7 @@ #define PCF2127_BIT_CTRL3_BLF BIT(2) #define PCF2127_BIT_CTRL3_BF BIT(3) #define PCF2127_BIT_CTRL3_BTSE BIT(4) +#define PCF2127_CTRL3_PM GENMASK(7, 5) /* Time and date registers */ #define PCF2127_REG_TIME_BASE 0x03 #define PCF2127_BIT_SC_OSF BIT(7) @@ -331,6 +333,84 @@ static int pcf2127_rtc_set_time(struct device *dev, struct rtc_time *tm) return 0; } +static int pcf2127_param_get(struct device *dev, struct rtc_param *param) +{ + struct pcf2127 *pcf2127 = dev_get_drvdata(dev); + u32 value; + int ret; + + switch (param->param) { + case RTC_PARAM_BACKUP_SWITCH_MODE: + ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL3, &value); + if (ret < 0) + return ret; + + value = FIELD_GET(PCF2127_CTRL3_PM, value); + + if (value < 0x3) + param->uvalue = RTC_BSM_LEVEL; + else if (value < 0x6) + param->uvalue = RTC_BSM_DIRECT; + else + param->uvalue = RTC_BSM_DISABLED; + + break; + + default: + return -EINVAL; + } + + return 0; +} + +static int pcf2127_param_set(struct device *dev, struct rtc_param *param) +{ + struct pcf2127 *pcf2127 = dev_get_drvdata(dev); + u8 mode = 0; + u32 value; + int ret; + + switch (param->param) { + case RTC_PARAM_BACKUP_SWITCH_MODE: + ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL3, &value); + if (ret < 0) + return ret; + + value = FIELD_GET(PCF2127_CTRL3_PM, value); + + if (value > 5) + value -= 5; + else if (value > 2) + value -= 3; + + switch (param->uvalue) { + case RTC_BSM_LEVEL: + break; + case RTC_BSM_DIRECT: + mode = 3; + break; + case RTC_BSM_DISABLED: + if (value == 0) + value = 1; + mode = 5; + break; + default: + return -EINVAL; + } + + return regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL3, + PCF2127_CTRL3_PM, + FIELD_PREP(PCF2127_CTRL3_PM, mode + value)); + + break; + + default: + return -EINVAL; + } + + return 0; +} + static int pcf2127_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) { @@ -741,6 +821,8 @@ static const struct rtc_class_ops pcf2127_rtc_ops = { .read_alarm = pcf2127_rtc_read_alarm, .set_alarm = pcf2127_rtc_set_alarm, .alarm_irq_enable = pcf2127_rtc_alarm_irq_enable, + .param_get = pcf2127_param_get, + .param_set = pcf2127_param_set, }; /* sysfs interface */ diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c index fdbc07f14036..905986c61655 100644 --- a/drivers/rtc/rtc-pcf85063.c +++ b/drivers/rtc/rtc-pcf85063.c @@ -322,7 +322,16 @@ static const struct rtc_class_ops pcf85063_rtc_ops = { static int pcf85063_nvmem_read(void *priv, unsigned int offset, void *val, size_t bytes) { - return regmap_read(priv, PCF85063_REG_RAM, val); + unsigned int tmp; + int ret; + + ret = regmap_read(priv, PCF85063_REG_RAM, &tmp); + if (ret < 0) + return ret; + + *(u8 *)val = tmp; + + return 0; } static int pcf85063_nvmem_write(void *priv, unsigned int offset, diff --git a/drivers/rtc/rtc-pic32.c b/drivers/rtc/rtc-pic32.c index bed3c27e665f..2812da2c50c5 100644 --- a/drivers/rtc/rtc-pic32.c +++ b/drivers/rtc/rtc-pic32.c @@ -330,7 +330,7 @@ static int pic32_rtc_probe(struct platform_device *pdev) pic32_rtc_enable(pdata, 1); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); pdata->rtc->ops = &pic32_rtcops; pdata->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c index 2f32187ecc8d..b2518aea4218 100644 --- a/drivers/rtc/rtc-pm8xxx.c +++ b/drivers/rtc/rtc-pm8xxx.c @@ -503,7 +503,7 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc_dd); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rtc_dd->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(rtc_dd->rtc)) diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c index 34d8545c8e15..62ee6b8f9bcd 100644 --- a/drivers/rtc/rtc-pxa.c +++ b/drivers/rtc/rtc-pxa.c @@ -360,7 +360,7 @@ static int __init pxa_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); return 0; } diff --git a/drivers/rtc/rtc-rc5t583.c b/drivers/rtc/rtc-rc5t583.c index eecb49bab56a..8ba9cda74acf 100644 --- a/drivers/rtc/rtc-rc5t583.c +++ b/drivers/rtc/rtc-rc5t583.c @@ -245,7 +245,7 @@ static int rc5t583_rtc_probe(struct platform_device *pdev) dev_err(&pdev->dev, "IRQ is not free.\n"); return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); ricoh_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &rc5t583_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-rc5t619.c b/drivers/rtc/rtc-rc5t619.c index 711f62eecd79..74d169102074 100644 --- a/drivers/rtc/rtc-rc5t619.c +++ b/drivers/rtc/rtc-rc5t619.c @@ -414,7 +414,7 @@ static int rc5t619_rtc_probe(struct platform_device *pdev) } else { /* enable wake */ - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); enable_irq_wake(rtc->irq); } } else { diff --git a/drivers/rtc/rtc-renesas-rtca3.c b/drivers/rtc/rtc-renesas-rtca3.c index d127933bfc8a..a056291d3887 100644 --- a/drivers/rtc/rtc-renesas-rtca3.c +++ b/drivers/rtc/rtc-renesas-rtca3.c @@ -768,7 +768,7 @@ static int rtca3_probe(struct platform_device *pdev) if (ret) return ret; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); priv->rtc_dev = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(priv->rtc_dev)) diff --git a/drivers/rtc/rtc-rk808.c b/drivers/rtc/rtc-rk808.c index 2d9bcb3ce1e3..59b8e9a30fe6 100644 --- a/drivers/rtc/rtc-rk808.c +++ b/drivers/rtc/rtc-rk808.c @@ -418,7 +418,7 @@ static int rk808_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rk808_rtc->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(rk808_rtc->rtc)) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index c0ac3bdb2f42..58c957eb753d 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -456,7 +456,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "s3c2410_rtc: RTCCON=%02x\n", readw(info->base + S3C2410_RTCCON)); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); info->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(info->rtc)) { diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c index dad294a0ce2a..36acca5b2639 100644 --- a/drivers/rtc/rtc-s5m.c +++ b/drivers/rtc/rtc-s5m.c @@ -729,7 +729,7 @@ static int s5m_rtc_probe(struct platform_device *pdev) info->irq, ret); return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); } return devm_rtc_register_device(info->rtc_dev); diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c index 13799b1abca1..1ad93648d69c 100644 --- a/drivers/rtc/rtc-sa1100.c +++ b/drivers/rtc/rtc-sa1100.c @@ -292,7 +292,7 @@ static int sa1100_rtc_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, info); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return sa1100_rtc_init(pdev, info); } diff --git a/drivers/rtc/rtc-sc27xx.c b/drivers/rtc/rtc-sc27xx.c index ce7a2ddbbc16..2b83561d4d28 100644 --- a/drivers/rtc/rtc-sc27xx.c +++ b/drivers/rtc/rtc-sc27xx.c @@ -613,14 +613,14 @@ static int sprd_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rtc->rtc->ops = &sprd_rtc_ops; rtc->rtc->range_min = 0; rtc->rtc->range_max = 5662310399LL; ret = devm_rtc_register_device(rtc->rtc); if (ret) { - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); return ret; } diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c index a5df521876ba..9ea40f40188f 100644 --- a/drivers/rtc/rtc-sh.c +++ b/drivers/rtc/rtc-sh.c @@ -611,7 +611,7 @@ static int __init sh_rtc_probe(struct platform_device *pdev) if (ret) goto err_unmap; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return 0; err_unmap: diff --git a/drivers/rtc/rtc-spear.c b/drivers/rtc/rtc-spear.c index 26eed927f8b3..959acff8faff 100644 --- a/drivers/rtc/rtc-spear.c +++ b/drivers/rtc/rtc-spear.c @@ -395,7 +395,7 @@ static int spear_rtc_probe(struct platform_device *pdev) goto err_disable_clock; if (!device_can_wakeup(&pdev->dev)) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return 0; @@ -411,7 +411,7 @@ static void spear_rtc_remove(struct platform_device *pdev) spear_rtc_disable_interrupt(config); clk_disable_unprepare(config->clk); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c index 9f1a019ec8af..a0564d443569 100644 --- a/drivers/rtc/rtc-stm32.c +++ b/drivers/rtc/rtc-stm32.c @@ -1074,26 +1074,18 @@ static int stm32_rtc_probe(struct platform_device *pdev) regs = &rtc->data->regs; if (rtc->data->need_dbp) { - rtc->dbp = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, - "st,syscfg"); + unsigned int args[2]; + + rtc->dbp = syscon_regmap_lookup_by_phandle_args(pdev->dev.of_node, + "st,syscfg", + 2, args); if (IS_ERR(rtc->dbp)) { dev_err(&pdev->dev, "no st,syscfg\n"); return PTR_ERR(rtc->dbp); } - ret = of_property_read_u32_index(pdev->dev.of_node, "st,syscfg", - 1, &rtc->dbp_reg); - if (ret) { - dev_err(&pdev->dev, "can't read DBP register offset\n"); - return ret; - } - - ret = of_property_read_u32_index(pdev->dev.of_node, "st,syscfg", - 2, &rtc->dbp_mask); - if (ret) { - dev_err(&pdev->dev, "can't read DBP register mask\n"); - return ret; - } + rtc->dbp_reg = args[0]; + rtc->dbp_mask = args[1]; } if (!rtc->data->has_pclk) { diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index e681c1745866..e5e6013d080e 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -826,7 +826,7 @@ static int sun6i_rtc_probe(struct platform_device *pdev) clk_prepare_enable(chip->losc); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); chip->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(chip->rtc)) diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c index 9b1ce0e8ba27..519a06e728d6 100644 --- a/drivers/rtc/rtc-sunplus.c +++ b/drivers/rtc/rtc-sunplus.c @@ -269,7 +269,7 @@ static int sp_rtc_probe(struct platform_device *plat_dev) if (ret) goto free_reset_assert; - device_init_wakeup(&plat_dev->dev, 1); + device_init_wakeup(&plat_dev->dev, true); dev_set_drvdata(&plat_dev->dev, sp_rtc); sp_rtc->rtc = devm_rtc_allocate_device(&plat_dev->dev); @@ -307,7 +307,7 @@ static void sp_rtc_remove(struct platform_device *plat_dev) { struct sunplus_rtc *sp_rtc = dev_get_drvdata(&plat_dev->dev); - device_init_wakeup(&plat_dev->dev, 0); + device_init_wakeup(&plat_dev->dev, false); reset_control_assert(sp_rtc->rstc); clk_disable_unprepare(sp_rtc->rtcclk); } diff --git a/drivers/rtc/rtc-tegra.c b/drivers/rtc/rtc-tegra.c index 79a3102c8354..46788db89953 100644 --- a/drivers/rtc/rtc-tegra.c +++ b/drivers/rtc/rtc-tegra.c @@ -319,7 +319,7 @@ static int tegra_rtc_probe(struct platform_device *pdev) writel(0xffffffff, info->base + TEGRA_RTC_REG_INTR_STATUS); writel(0, info->base + TEGRA_RTC_REG_INTR_MASK); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); ret = devm_request_irq(&pdev->dev, info->irq, tegra_rtc_irq_handler, IRQF_TRIGGER_HIGH, dev_name(&pdev->dev), diff --git a/drivers/rtc/rtc-test.c b/drivers/rtc/rtc-test.c index 7e0d8fb26465..a68b8c884102 100644 --- a/drivers/rtc/rtc-test.c +++ b/drivers/rtc/rtc-test.c @@ -132,7 +132,7 @@ static int test_probe(struct platform_device *plat_dev) break; default: rtd->rtc->ops = &test_rtc_ops; - device_init_wakeup(&plat_dev->dev, 1); + device_init_wakeup(&plat_dev->dev, true); } timer_setup(&rtd->alarm, test_rtc_alarm_handler, 0); diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c index e796729fc817..54c8429b16bf 100644 --- a/drivers/rtc/rtc-tps6586x.c +++ b/drivers/rtc/rtc-tps6586x.c @@ -241,7 +241,7 @@ static int tps6586x_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); platform_set_drvdata(pdev, rtc); rtc->rtc = devm_rtc_allocate_device(&pdev->dev); diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c index 2ea1bbfbbc2a..284aa2f0392b 100644 --- a/drivers/rtc/rtc-tps65910.c +++ b/drivers/rtc/rtc-tps65910.c @@ -418,7 +418,7 @@ static int tps65910_rtc_probe(struct platform_device *pdev) tps_rtc->irq = irq; if (irq != -1) { if (device_property_present(tps65910->dev, "wakeup-source")) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); else device_set_wakeup_capable(&pdev->dev, 1); } else { diff --git a/drivers/rtc/rtc-tps6594.c b/drivers/rtc/rtc-tps6594.c index e69667634137..7c6246e3f029 100644 --- a/drivers/rtc/rtc-tps6594.c +++ b/drivers/rtc/rtc-tps6594.c @@ -37,7 +37,7 @@ #define MAX_OFFSET (277774) // Number of ticks per hour -#define TICKS_PER_HOUR (32768 * 3600) +#define TICKS_PER_HOUR (32768 * 3600LL) // Multiplier for ppb conversions #define PPB_MULT NANO diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c index 794429182b34..e6106e67e1f4 100644 --- a/drivers/rtc/rtc-twl.c +++ b/drivers/rtc/rtc-twl.c @@ -572,7 +572,7 @@ static int twl_rtc_probe(struct platform_device *pdev) return ret; platform_set_drvdata(pdev, twl_rtc); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); twl_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &twl_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c index 640833e21057..218316be942a 100644 --- a/drivers/rtc/rtc-wm831x.c +++ b/drivers/rtc/rtc-wm831x.c @@ -420,7 +420,7 @@ static int wm831x_rtc_probe(struct platform_device *pdev) if (ret & WM831X_RTC_ALM_ENA) wm831x_rtc->alarm_enabled = 1; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); wm831x_rtc->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(wm831x_rtc->rtc)) diff --git a/drivers/rtc/rtc-wm8350.c b/drivers/rtc/rtc-wm8350.c index 6797eb4d2e49..3bd60d067a5e 100644 --- a/drivers/rtc/rtc-wm8350.c +++ b/drivers/rtc/rtc-wm8350.c @@ -420,7 +420,7 @@ static int wm8350_rtc_probe(struct platform_device *pdev) } } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); wm_rtc->rtc = devm_rtc_device_register(&pdev->dev, "wm8350", &wm8350_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-xgene.c b/drivers/rtc/rtc-xgene.c index 0813ea1a03c2..6660b664e8dd 100644 --- a/drivers/rtc/rtc-xgene.c +++ b/drivers/rtc/rtc-xgene.c @@ -174,7 +174,7 @@ static int xgene_rtc_probe(struct platform_device *pdev) /* Turn on the clock and the crystal */ writel(RTC_CCR_EN, pdata->csr_base + RTC_CCR); - ret = device_init_wakeup(&pdev->dev, 1); + ret = device_init_wakeup(&pdev->dev, true); if (ret) { clk_disable_unprepare(pdata->clk); return ret; @@ -197,7 +197,7 @@ static void xgene_rtc_remove(struct platform_device *pdev) struct xgene_rtc_dev *pdata = platform_get_drvdata(pdev); xgene_rtc_alarm_irq_enable(&pdev->dev, 0); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); clk_disable_unprepare(pdata->clk); } diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c index af1abb69d1e3..f39102b66eac 100644 --- a/drivers/rtc/rtc-zynqmp.c +++ b/drivers/rtc/rtc-zynqmp.c @@ -318,8 +318,8 @@ static int xlnx_rtc_probe(struct platform_device *pdev) return ret; } - /* Getting the rtc_clk info */ - xrtcdev->rtc_clk = devm_clk_get_optional(&pdev->dev, "rtc_clk"); + /* Getting the rtc info */ + xrtcdev->rtc_clk = devm_clk_get_optional(&pdev->dev, "rtc"); if (IS_ERR(xrtcdev->rtc_clk)) { if (PTR_ERR(xrtcdev->rtc_clk) != -EPROBE_DEFER) dev_warn(&pdev->dev, "Device clock not found.\n"); @@ -337,7 +337,7 @@ static int xlnx_rtc_probe(struct platform_device *pdev) xlnx_init_rtc(xrtcdev); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return devm_rtc_register_device(xrtcdev->rtc); } @@ -345,7 +345,7 @@ static int xlnx_rtc_probe(struct platform_device *pdev) static void xlnx_rtc_remove(struct platform_device *pdev) { xlnx_rtc_alarm_irq_enable(&pdev->dev, 0); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); } static int __maybe_unused xlnx_rtc_suspend(struct device *dev) diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 6da47a65af61..28e92fad0ca1 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -56,7 +56,6 @@ int dasd_gendisk_alloc(struct dasd_block *block) block->tag_set.cmd_size = sizeof(struct dasd_ccw_req); block->tag_set.nr_hw_queues = nr_hw_queues; block->tag_set.queue_depth = queue_depth; - block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; block->tag_set.numa_node = NUMA_NO_NODE; rc = blk_mq_alloc_tag_set(&block->tag_set); if (rc) diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index 3fcfe029db1b..91bbe9d2e5ac 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -461,7 +461,6 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) bdev->tag_set.cmd_size = sizeof(blk_status_t); bdev->tag_set.nr_hw_queues = nr_requests; bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests; - bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; bdev->tag_set.numa_node = NUMA_NO_NODE; ret = blk_mq_alloc_tag_set(&bdev->tag_set); diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c index fbffd451031f..45bd001206a2 100644 --- a/drivers/s390/char/sclp.c +++ b/drivers/s390/char/sclp.c @@ -245,7 +245,6 @@ static void sclp_request_timeout(bool force_restart); static void sclp_process_queue(void); static void __sclp_make_read_req(void); static int sclp_init_mask(int calculate); -static int sclp_init(void); static void __sclp_queue_read_req(void) @@ -1251,8 +1250,7 @@ static struct platform_driver sclp_pdrv = { /* Initialize SCLP driver. Return zero if driver is operational, non-zero * otherwise. */ -static int -sclp_init(void) +int sclp_init(void) { unsigned long flags; int rc = 0; @@ -1305,13 +1303,7 @@ fail_unlock: static __init int sclp_initcall(void) { - int rc; - - rc = platform_driver_register(&sclp_pdrv); - if (rc) - return rc; - - return sclp_init(); + return platform_driver_register(&sclp_pdrv); } arch_initcall(sclp_initcall); diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h index 6c91e422927f..07a6e8a7f05a 100644 --- a/drivers/s390/char/sclp.h +++ b/drivers/s390/char/sclp.h @@ -85,13 +85,6 @@ typedef unsigned int sclp_cmdw_t; typedef u64 sccb_mask_t; -struct sccb_header { - u16 length; - u8 function_code; - u8 control_mask[3]; - u16 response_code; -} __attribute__((packed)); - struct init_sccb { struct sccb_header header; u16 _reserved; @@ -196,7 +189,9 @@ struct read_info_sccb { u8 byte_134; /* 134 */ u8 cpudirq; /* 135 */ u16 cbl; /* 136-137 */ - u8 _pad_138[EXT_SCCB_READ_SCP - 138]; + u8 byte_138; /* 138 */ + u8 byte_139; /* 139 */ + u8 _pad_140[EXT_SCCB_READ_SCP - 140]; } __packed __aligned(PAGE_SIZE); struct read_storage_sccb { @@ -238,13 +233,6 @@ struct gds_vector { u16 gds_id; } __attribute__((packed)); -struct evbuf_header { - u16 length; - u8 type; - u8 flags; - u16 _reserved; -} __attribute__((packed)); - struct sclp_req { struct list_head list; /* list_head for request queueing. */ sclp_cmdw_t command; /* sclp command to execute */ diff --git a/drivers/s390/char/sclp_config.c b/drivers/s390/char/sclp_config.c index f56ea9b60e08..ae5d28987177 100644 --- a/drivers/s390/char/sclp_config.c +++ b/drivers/s390/char/sclp_config.c @@ -128,7 +128,7 @@ out: } static ssize_t sysfs_ofb_data_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { int rc; @@ -142,7 +142,7 @@ static const struct bin_attribute ofb_bin_attr = { .name = "event_data", .mode = S_IWUSR, }, - .write = sysfs_ofb_data_write, + .write_new = sysfs_ofb_data_write, }; #endif diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index 29156455970e..d9d6edaf8de8 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -55,6 +55,7 @@ static void __init sclp_early_facilities_detect(void) if (sccb->fac91 & 0x40) get_lowcore()->machine_flags |= MACHINE_FLAG_TLB_GUEST; sclp.has_diag204_bif = !!(sccb->fac98 & 0x80); + sclp.has_diag310 = !!(sccb->fac91 & 0x80); if (sccb->cpuoff > 134) { sclp.has_diag318 = !!(sccb->byte_134 & 0x80); sclp.has_diag320 = !!(sccb->byte_134 & 0x04); @@ -64,6 +65,8 @@ static void __init sclp_early_facilities_detect(void) sclp.has_sipl = !!(sccb->cbl & 0x4000); sclp.has_sipl_eckd = !!(sccb->cbl & 0x2000); } + if (sccb->cpuoff > 139) + sclp.has_diag324 = !!(sccb->byte_139 & 0x80); sclp.rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2; sclp.rzm = sccb->rnsize ? sccb->rnsize : sccb->rnsize2; sclp.rzm <<= 20; diff --git a/drivers/s390/char/sclp_pci.c b/drivers/s390/char/sclp_pci.c index c3466a8c56bb..56400886f7fc 100644 --- a/drivers/s390/char/sclp_pci.c +++ b/drivers/s390/char/sclp_pci.c @@ -24,30 +24,11 @@ #define SCLP_ATYPE_PCI 2 -#define SCLP_ERRNOTIFY_AQ_RESET 0 -#define SCLP_ERRNOTIFY_AQ_REPAIR 1 -#define SCLP_ERRNOTIFY_AQ_INFO_LOG 2 -#define SCLP_ERRNOTIFY_AQ_OPTICS_DATA 3 - static DEFINE_MUTEX(sclp_pci_mutex); static struct sclp_register sclp_pci_event = { .send_mask = EVTYP_ERRNOTIFY_MASK, }; -struct err_notify_evbuf { - struct evbuf_header header; - u8 action; - u8 atype; - u32 fh; - u32 fid; - u8 data[]; -} __packed; - -struct err_notify_sccb { - struct sccb_header header; - struct err_notify_evbuf evbuf; -} __packed; - struct pci_cfg_sccb { struct sccb_header header; u8 atype; /* adapter type */ diff --git a/drivers/s390/char/sclp_sd.c b/drivers/s390/char/sclp_sd.c index c2dc9aadb7d2..8524c14affed 100644 --- a/drivers/s390/char/sclp_sd.c +++ b/drivers/s390/char/sclp_sd.c @@ -476,7 +476,7 @@ static struct kobj_type sclp_sd_file_ktype = { * on EOF. */ static ssize_t data_read(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, char *buffer, + const struct bin_attribute *attr, char *buffer, loff_t off, size_t size) { struct sclp_sd_file *sd_file = to_sd_file(kobj); @@ -539,7 +539,7 @@ static __init struct sclp_sd_file *sclp_sd_file_create(const char *name, u8 di) sysfs_bin_attr_init(&sd_file->data_attr); sd_file->data_attr.attr.name = "data"; sd_file->data_attr.attr.mode = 0444; - sd_file->data_attr.read = data_read; + sd_file->data_attr.read_new = data_read; rc = sysfs_create_bin_file(&sd_file->kobj, &sd_file->data_attr); if (rc) { diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index 3dd50ac9c5b0..b2d93a6e36c4 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -123,7 +123,7 @@ static DECLARE_WAIT_QUEUE_HEAD(read_wait_queue); */ static struct vmlogrdr_priv_t sys_ser[] = { - { .system_service = "*LOGREC ", + { .system_service = { '*', 'L', 'O', 'G', 'R', 'E', 'C', ' ' }, .internal_name = "logrec", .recording_name = "EREP", .minor_num = 0, @@ -132,7 +132,7 @@ static struct vmlogrdr_priv_t sys_ser[] = { .autorecording = 1, .autopurge = 1, }, - { .system_service = "*ACCOUNT", + { .system_service = { '*', 'A', 'C', 'C', 'O', 'U', 'N', 'T' }, .internal_name = "account", .recording_name = "ACCOUNT", .minor_num = 1, @@ -141,7 +141,7 @@ static struct vmlogrdr_priv_t sys_ser[] = { .autorecording = 1, .autopurge = 1, }, - { .system_service = "*SYMPTOM", + { .system_service = { '*', 'S', 'Y', 'M', 'P', 'T', 'O', 'M' }, .internal_name = "symptom", .recording_name = "SYMPTOM", .minor_num = 2, @@ -356,7 +356,7 @@ static int vmlogrdr_open (struct inode *inode, struct file *filp) if (connect_rc) { pr_err("vmlogrdr: iucv connection to %s " "failed with rc %i \n", - logptr->system_service, connect_rc); + logptr->internal_name, connect_rc); goto out_path; } diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index cba2d048a96b..4a0b3f19bd8e 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -128,7 +128,7 @@ static int s390_vary_chpid(struct chp_id chpid, int on) * Channel measurement related functions */ static ssize_t measurement_chars_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct channel_path *chp; @@ -142,11 +142,11 @@ static ssize_t measurement_chars_read(struct file *filp, struct kobject *kobj, return memory_read_from_buffer(buf, count, &off, &chp->cmg_chars, sizeof(chp->cmg_chars)); } -static BIN_ATTR_ADMIN_RO(measurement_chars, sizeof(struct cmg_chars)); +static const BIN_ATTR_ADMIN_RO(measurement_chars, sizeof(struct cmg_chars)); static ssize_t measurement_chars_full_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct channel_path *chp = to_channelpath(kobj_to_dev(kobj)); @@ -196,22 +196,22 @@ static ssize_t chp_measurement_copy_block(void *buf, loff_t off, size_t count, } static ssize_t measurement_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { return chp_measurement_copy_block(buf, off, count, kobj, false); } -static BIN_ATTR_ADMIN_RO(measurement, sizeof(struct cmg_entry)); +static const BIN_ATTR_ADMIN_RO(measurement, sizeof(struct cmg_entry)); static ssize_t ext_measurement_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { return chp_measurement_copy_block(buf, off, count, kobj, true); } -static BIN_ATTR_ADMIN_RO(ext_measurement, sizeof(struct cmg_ext_entry)); +static const BIN_ATTR_ADMIN_RO(ext_measurement, sizeof(struct cmg_ext_entry)); -static struct bin_attribute *measurement_attrs[] = { +static const struct bin_attribute *measurement_attrs[] = { &bin_attr_measurement_chars, &bin_attr_measurement_chars_full, &bin_attr_measurement, @@ -435,7 +435,7 @@ static ssize_t speed_bps_show(struct device *dev, static DEVICE_ATTR_RO(speed_bps); static ssize_t util_string_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct channel_path *chp = to_channelpath(kobj_to_dev(kobj)); @@ -448,10 +448,10 @@ static ssize_t util_string_read(struct file *filp, struct kobject *kobj, return rc; } -static BIN_ATTR_RO(util_string, - sizeof(((struct channel_path_desc_fmt3 *)0)->util_str)); +static const BIN_ATTR_RO(util_string, + sizeof(((struct channel_path_desc_fmt3 *)0)->util_str)); -static struct bin_attribute *chp_bin_attrs[] = { +static const struct bin_attribute *const chp_bin_attrs[] = { &bin_attr_util_string, NULL, }; @@ -468,9 +468,9 @@ static struct attribute *chp_attrs[] = { &dev_attr_speed_bps.attr, NULL, }; -static struct attribute_group chp_attr_group = { +static const struct attribute_group chp_attr_group = { .attrs = chp_attrs, - .bin_attrs = chp_bin_attrs, + .bin_attrs_new = chp_bin_attrs, }; static const struct attribute_group *chp_attr_groups[] = { &chp_attr_group, diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index acd6790dba4d..61c07b4a0fe8 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -445,7 +445,7 @@ struct ciw *ccw_device_get_ciw(struct ccw_device *cdev, __u32 ct) return NULL; for (ciw_cnt = 0; ciw_cnt < MAX_CIWS; ciw_cnt++) if (cdev->private->dma_area->senseid.ciw[ciw_cnt].ct == ct) - return cdev->private->dma_area->senseid.ciw + ciw_cnt; + return &cdev->private->dma_area->senseid.ciw[ciw_cnt]; return NULL; } diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 641f0dbb65a9..4bd4c00c9c0c 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -210,11 +210,10 @@ struct qdio_q { qdio_handler_t (*handler); struct qdio_irq *irq_ptr; + + /* memory page (PAGE_SIZE) used to place slib and sl on */ + void *sl_page; struct sl *sl; - /* - * A page is allocated under this pointer and used for slib and sl. - * slib is 2048 bytes big and sl points to offset PAGE_SIZE / 2. - */ struct slib *slib; } __attribute__ ((aligned(256))); @@ -266,7 +265,7 @@ struct qdio_irq { #define is_thinint_irq(irq) \ (irq->qib.qfmt == QDIO_IQDIO_QFMT || \ - css_general_characteristics.aif_osa) + css_general_characteristics.aif_qdio) #define qperf(__qdev, __attr) ((__qdev)->perf_stat.(__attr)) diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index 99c0fd23022d..ea09aadaae4e 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -83,7 +83,7 @@ static void __qdio_free_queues(struct qdio_q **queues, unsigned int count) for (i = 0; i < count; i++) { q = queues[i]; - free_page((unsigned long) q->slib); + free_page((unsigned long)q->sl_page); kmem_cache_free(qdio_q_cache, q); } } @@ -109,12 +109,16 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues) return -ENOMEM; } - q->slib = (struct slib *) __get_free_page(GFP_KERNEL); - if (!q->slib) { + q->sl_page = (void *)__get_free_page(GFP_KERNEL); + if (!q->sl_page) { kmem_cache_free(qdio_q_cache, q); __qdio_free_queues(irq_ptr_qs, i); return -ENOMEM; } + q->slib = q->sl_page; + /* As per architecture: SLIB is 2K bytes long, and SL 1K. */ + q->sl = (struct sl *)(q->slib + 1); + irq_ptr_qs[i] = q; } return 0; @@ -142,11 +146,15 @@ int qdio_allocate_qs(struct qdio_irq *irq_ptr, int nr_input_qs, int nr_output_qs static void setup_queues_misc(struct qdio_q *q, struct qdio_irq *irq_ptr, qdio_handler_t *handler, int i) { - struct slib *slib = q->slib; + struct slib *const slib = q->slib; + void *const sl_page = q->sl_page; + struct sl *const sl = q->sl; /* queue must be cleared for qdio_establish */ memset(q, 0, sizeof(*q)); - memset(slib, 0, PAGE_SIZE); + memset(sl_page, 0, PAGE_SIZE); + q->sl_page = sl_page; + q->sl = sl; q->slib = slib; q->irq_ptr = irq_ptr; q->mask = 1 << (31 - i); @@ -161,7 +169,6 @@ static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr, int j; DBF_HEX(&q, sizeof(void *)); - q->sl = (struct sl *)((char *)q->slib + PAGE_SIZE / 2); /* fill in sbal */ for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++) @@ -423,7 +430,7 @@ int __init qdio_setup_init(void) /* Check for OSA/FCP thin interrupts (bit 67). */ DBF_EVENT("thinint:%1d", - (css_general_characteristics.aif_osa) ? 1 : 0); + (css_general_characteristics.aif_qdio) ? 1 : 0); /* Check for QEBSM support in general (bit 58). */ DBF_EVENT("cssQEBSM:%1d", css_general_characteristics.qebsm); diff --git a/drivers/s390/crypto/pkey_sysfs.c b/drivers/s390/crypto/pkey_sysfs.c index a4eb45803f5e..57edc97bafd2 100644 --- a/drivers/s390/crypto/pkey_sysfs.c +++ b/drivers/s390/crypto/pkey_sysfs.c @@ -184,7 +184,7 @@ static ssize_t pkey_protkey_hmac_attr_read(u32 keytype, char *buf, static ssize_t protkey_aes_128_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -194,7 +194,7 @@ static ssize_t protkey_aes_128_read(struct file *filp, static ssize_t protkey_aes_192_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -204,7 +204,7 @@ static ssize_t protkey_aes_192_read(struct file *filp, static ssize_t protkey_aes_256_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -214,7 +214,7 @@ static ssize_t protkey_aes_256_read(struct file *filp, static ssize_t protkey_aes_128_xts_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -224,7 +224,7 @@ static ssize_t protkey_aes_128_xts_read(struct file *filp, static ssize_t protkey_aes_256_xts_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -234,7 +234,7 @@ static ssize_t protkey_aes_256_xts_read(struct file *filp, static ssize_t protkey_aes_xts_128_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -244,7 +244,7 @@ static ssize_t protkey_aes_xts_128_read(struct file *filp, static ssize_t protkey_aes_xts_256_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -254,7 +254,7 @@ static ssize_t protkey_aes_xts_256_read(struct file *filp, static ssize_t protkey_hmac_512_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -264,7 +264,7 @@ static ssize_t protkey_hmac_512_read(struct file *filp, static ssize_t protkey_hmac_1024_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -272,17 +272,17 @@ static ssize_t protkey_hmac_1024_read(struct file *filp, buf, off, count); } -static BIN_ATTR_RO(protkey_aes_128, sizeof(struct protaeskeytoken)); -static BIN_ATTR_RO(protkey_aes_192, sizeof(struct protaeskeytoken)); -static BIN_ATTR_RO(protkey_aes_256, sizeof(struct protaeskeytoken)); -static BIN_ATTR_RO(protkey_aes_128_xts, 2 * sizeof(struct protaeskeytoken)); -static BIN_ATTR_RO(protkey_aes_256_xts, 2 * sizeof(struct protaeskeytoken)); -static BIN_ATTR_RO(protkey_aes_xts_128, sizeof(struct protkeytoken) + 64); -static BIN_ATTR_RO(protkey_aes_xts_256, sizeof(struct protkeytoken) + 96); -static BIN_ATTR_RO(protkey_hmac_512, sizeof(struct protkeytoken) + 96); -static BIN_ATTR_RO(protkey_hmac_1024, sizeof(struct protkeytoken) + 160); +static const BIN_ATTR_RO(protkey_aes_128, sizeof(struct protaeskeytoken)); +static const BIN_ATTR_RO(protkey_aes_192, sizeof(struct protaeskeytoken)); +static const BIN_ATTR_RO(protkey_aes_256, sizeof(struct protaeskeytoken)); +static const BIN_ATTR_RO(protkey_aes_128_xts, 2 * sizeof(struct protaeskeytoken)); +static const BIN_ATTR_RO(protkey_aes_256_xts, 2 * sizeof(struct protaeskeytoken)); +static const BIN_ATTR_RO(protkey_aes_xts_128, sizeof(struct protkeytoken) + 64); +static const BIN_ATTR_RO(protkey_aes_xts_256, sizeof(struct protkeytoken) + 96); +static const BIN_ATTR_RO(protkey_hmac_512, sizeof(struct protkeytoken) + 96); +static const BIN_ATTR_RO(protkey_hmac_1024, sizeof(struct protkeytoken) + 160); -static struct bin_attribute *protkey_attrs[] = { +static const struct bin_attribute *const protkey_attrs[] = { &bin_attr_protkey_aes_128, &bin_attr_protkey_aes_192, &bin_attr_protkey_aes_256, @@ -295,9 +295,9 @@ static struct bin_attribute *protkey_attrs[] = { NULL }; -static struct attribute_group protkey_attr_group = { - .name = "protkey", - .bin_attrs = protkey_attrs, +static const struct attribute_group protkey_attr_group = { + .name = "protkey", + .bin_attrs_new = protkey_attrs, }; /* @@ -341,7 +341,7 @@ static ssize_t pkey_ccadata_aes_attr_read(u32 keytype, bool is_xts, char *buf, static ssize_t ccadata_aes_128_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -351,7 +351,7 @@ static ssize_t ccadata_aes_128_read(struct file *filp, static ssize_t ccadata_aes_192_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -361,7 +361,7 @@ static ssize_t ccadata_aes_192_read(struct file *filp, static ssize_t ccadata_aes_256_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -371,7 +371,7 @@ static ssize_t ccadata_aes_256_read(struct file *filp, static ssize_t ccadata_aes_128_xts_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -381,7 +381,7 @@ static ssize_t ccadata_aes_128_xts_read(struct file *filp, static ssize_t ccadata_aes_256_xts_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -389,13 +389,13 @@ static ssize_t ccadata_aes_256_xts_read(struct file *filp, off, count); } -static BIN_ATTR_RO(ccadata_aes_128, sizeof(struct secaeskeytoken)); -static BIN_ATTR_RO(ccadata_aes_192, sizeof(struct secaeskeytoken)); -static BIN_ATTR_RO(ccadata_aes_256, sizeof(struct secaeskeytoken)); -static BIN_ATTR_RO(ccadata_aes_128_xts, 2 * sizeof(struct secaeskeytoken)); -static BIN_ATTR_RO(ccadata_aes_256_xts, 2 * sizeof(struct secaeskeytoken)); +static const BIN_ATTR_RO(ccadata_aes_128, sizeof(struct secaeskeytoken)); +static const BIN_ATTR_RO(ccadata_aes_192, sizeof(struct secaeskeytoken)); +static const BIN_ATTR_RO(ccadata_aes_256, sizeof(struct secaeskeytoken)); +static const BIN_ATTR_RO(ccadata_aes_128_xts, 2 * sizeof(struct secaeskeytoken)); +static const BIN_ATTR_RO(ccadata_aes_256_xts, 2 * sizeof(struct secaeskeytoken)); -static struct bin_attribute *ccadata_attrs[] = { +static const struct bin_attribute *const ccadata_attrs[] = { &bin_attr_ccadata_aes_128, &bin_attr_ccadata_aes_192, &bin_attr_ccadata_aes_256, @@ -404,9 +404,9 @@ static struct bin_attribute *ccadata_attrs[] = { NULL }; -static struct attribute_group ccadata_attr_group = { - .name = "ccadata", - .bin_attrs = ccadata_attrs, +static const struct attribute_group ccadata_attr_group = { + .name = "ccadata", + .bin_attrs_new = ccadata_attrs, }; #define CCACIPHERTOKENSIZE (sizeof(struct cipherkeytoken) + 80) @@ -455,7 +455,7 @@ static ssize_t pkey_ccacipher_aes_attr_read(enum pkey_key_size keybits, static ssize_t ccacipher_aes_128_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -465,7 +465,7 @@ static ssize_t ccacipher_aes_128_read(struct file *filp, static ssize_t ccacipher_aes_192_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -475,7 +475,7 @@ static ssize_t ccacipher_aes_192_read(struct file *filp, static ssize_t ccacipher_aes_256_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -485,7 +485,7 @@ static ssize_t ccacipher_aes_256_read(struct file *filp, static ssize_t ccacipher_aes_128_xts_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -495,7 +495,7 @@ static ssize_t ccacipher_aes_128_xts_read(struct file *filp, static ssize_t ccacipher_aes_256_xts_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -503,13 +503,13 @@ static ssize_t ccacipher_aes_256_xts_read(struct file *filp, off, count); } -static BIN_ATTR_RO(ccacipher_aes_128, CCACIPHERTOKENSIZE); -static BIN_ATTR_RO(ccacipher_aes_192, CCACIPHERTOKENSIZE); -static BIN_ATTR_RO(ccacipher_aes_256, CCACIPHERTOKENSIZE); -static BIN_ATTR_RO(ccacipher_aes_128_xts, 2 * CCACIPHERTOKENSIZE); -static BIN_ATTR_RO(ccacipher_aes_256_xts, 2 * CCACIPHERTOKENSIZE); +static const BIN_ATTR_RO(ccacipher_aes_128, CCACIPHERTOKENSIZE); +static const BIN_ATTR_RO(ccacipher_aes_192, CCACIPHERTOKENSIZE); +static const BIN_ATTR_RO(ccacipher_aes_256, CCACIPHERTOKENSIZE); +static const BIN_ATTR_RO(ccacipher_aes_128_xts, 2 * CCACIPHERTOKENSIZE); +static const BIN_ATTR_RO(ccacipher_aes_256_xts, 2 * CCACIPHERTOKENSIZE); -static struct bin_attribute *ccacipher_attrs[] = { +static const struct bin_attribute *const ccacipher_attrs[] = { &bin_attr_ccacipher_aes_128, &bin_attr_ccacipher_aes_192, &bin_attr_ccacipher_aes_256, @@ -518,9 +518,9 @@ static struct bin_attribute *ccacipher_attrs[] = { NULL }; -static struct attribute_group ccacipher_attr_group = { - .name = "ccacipher", - .bin_attrs = ccacipher_attrs, +static const struct attribute_group ccacipher_attr_group = { + .name = "ccacipher", + .bin_attrs_new = ccacipher_attrs, }; /* @@ -570,7 +570,7 @@ static ssize_t pkey_ep11_aes_attr_read(enum pkey_key_size keybits, static ssize_t ep11_aes_128_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -580,7 +580,7 @@ static ssize_t ep11_aes_128_read(struct file *filp, static ssize_t ep11_aes_192_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -590,7 +590,7 @@ static ssize_t ep11_aes_192_read(struct file *filp, static ssize_t ep11_aes_256_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -600,7 +600,7 @@ static ssize_t ep11_aes_256_read(struct file *filp, static ssize_t ep11_aes_128_xts_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -610,7 +610,7 @@ static ssize_t ep11_aes_128_xts_read(struct file *filp, static ssize_t ep11_aes_256_xts_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -618,13 +618,13 @@ static ssize_t ep11_aes_256_xts_read(struct file *filp, off, count); } -static BIN_ATTR_RO(ep11_aes_128, MAXEP11AESKEYBLOBSIZE); -static BIN_ATTR_RO(ep11_aes_192, MAXEP11AESKEYBLOBSIZE); -static BIN_ATTR_RO(ep11_aes_256, MAXEP11AESKEYBLOBSIZE); -static BIN_ATTR_RO(ep11_aes_128_xts, 2 * MAXEP11AESKEYBLOBSIZE); -static BIN_ATTR_RO(ep11_aes_256_xts, 2 * MAXEP11AESKEYBLOBSIZE); +static const BIN_ATTR_RO(ep11_aes_128, MAXEP11AESKEYBLOBSIZE); +static const BIN_ATTR_RO(ep11_aes_192, MAXEP11AESKEYBLOBSIZE); +static const BIN_ATTR_RO(ep11_aes_256, MAXEP11AESKEYBLOBSIZE); +static const BIN_ATTR_RO(ep11_aes_128_xts, 2 * MAXEP11AESKEYBLOBSIZE); +static const BIN_ATTR_RO(ep11_aes_256_xts, 2 * MAXEP11AESKEYBLOBSIZE); -static struct bin_attribute *ep11_attrs[] = { +static const struct bin_attribute *const ep11_attrs[] = { &bin_attr_ep11_aes_128, &bin_attr_ep11_aes_192, &bin_attr_ep11_aes_256, @@ -633,9 +633,9 @@ static struct bin_attribute *ep11_attrs[] = { NULL }; -static struct attribute_group ep11_attr_group = { +static const struct attribute_group ep11_attr_group = { .name = "ep11", - .bin_attrs = ep11_attrs, + .bin_attrs_new = ep11_attrs, }; const struct attribute_group *pkey_attr_groups[] = { diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index d6516ab00437..1d50f463afe7 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -537,6 +537,11 @@ static void zfcp_fc_adisc_handler(void *data) /* port is still good, nothing to do */ out: atomic_andnot(ZFCP_STATUS_PORT_LINK_TEST, &port->status); + /* + * port ref comes from get_device() in zfcp_fc_test_link() and + * work item zfcp_fc_link_test_work() passes ref via + * zfcp_fc_adisc() to here, if zfcp_fc_adisc() could send ADISC + */ put_device(&port->dev); kmem_cache_free(zfcp_fc_req_cache, fc_req); } @@ -603,7 +608,7 @@ void zfcp_fc_link_test_work(struct work_struct *work) retval = zfcp_fc_adisc(port); if (retval == 0) - return; + return; /* port ref passed to zfcp_fc_adisc(), no put here */ /* send of ADISC was not possible */ atomic_andnot(ZFCP_STATUS_PORT_LINK_TEST, &port->status); diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 22e82000334a..99d6b3f8692b 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -1218,7 +1218,7 @@ static int zfcp_fsf_setup_ct_els(struct zfcp_fsf_req *req, /** * zfcp_fsf_send_ct - initiate a Generic Service request (FC-GS) * @wka_port: pointer to zfcp WKA port to send CT/GS to - * @ct: pointer to struct zfcp_send_ct with data for request + * @ct: pointer to struct zfcp_fsf_ct_els with data for CT request * @pool: if non-null this mempool is used to allocate struct zfcp_fsf_req * @timeout: timeout that hardware should use, and a later software timeout */ @@ -1316,7 +1316,7 @@ skip_fsfstatus: * zfcp_fsf_send_els - initiate an ELS command (FC-FS) * @adapter: pointer to zfcp adapter * @d_id: N_Port_ID to send ELS to - * @els: pointer to struct zfcp_send_els with data for the command + * @els: pointer to struct zfcp_fsf_ct_els with data for the ELS command * @timeout: timeout that hardware should use, and a later software timeout */ int zfcp_fsf_send_els(struct zfcp_adapter *adapter, u32 d_id, diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index b2a8cd792266..b31f860af47b 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -37,11 +37,11 @@ static bool allow_lun_scan = true; module_param(allow_lun_scan, bool, 0600); MODULE_PARM_DESC(allow_lun_scan, "For NPIV, scan and attach all storage LUNs"); -static void zfcp_scsi_slave_destroy(struct scsi_device *sdev) +static void zfcp_scsi_sdev_destroy(struct scsi_device *sdev) { struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(sdev); - /* if previous slave_alloc returned early, there is nothing to do */ + /* if previous sdev_init returned early, there is nothing to do */ if (!zfcp_sdev->port) return; @@ -49,7 +49,8 @@ static void zfcp_scsi_slave_destroy(struct scsi_device *sdev) put_device(&zfcp_sdev->port->dev); } -static int zfcp_scsi_slave_configure(struct scsi_device *sdp) +static int zfcp_scsi_sdev_configure(struct scsi_device *sdp, + struct queue_limits *lim) { if (sdp->tagged_supported) scsi_change_queue_depth(sdp, default_depth); @@ -110,7 +111,7 @@ int zfcp_scsi_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scpnt) return ret; } -static int zfcp_scsi_slave_alloc(struct scsi_device *sdev) +static int zfcp_scsi_sdev_init(struct scsi_device *sdev) { struct fc_rport *rport = starget_to_rport(scsi_target(sdev)); struct zfcp_adapter *adapter = @@ -427,9 +428,9 @@ static const struct scsi_host_template zfcp_scsi_host_template = { .eh_device_reset_handler = zfcp_scsi_eh_device_reset_handler, .eh_target_reset_handler = zfcp_scsi_eh_target_reset_handler, .eh_host_reset_handler = zfcp_scsi_eh_host_reset_handler, - .slave_alloc = zfcp_scsi_slave_alloc, - .slave_configure = zfcp_scsi_slave_configure, - .slave_destroy = zfcp_scsi_slave_destroy, + .sdev_init = zfcp_scsi_sdev_init, + .sdev_configure = zfcp_scsi_sdev_configure, + .sdev_destroy = zfcp_scsi_sdev_destroy, .change_queue_depth = scsi_change_queue_depth, .host_reset = zfcp_scsi_sysfs_host_reset, .proc_name = "zfcp", diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index 304b81bb5f90..41e36af35488 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -284,7 +284,7 @@ static bool zfcp_sysfs_port_in_use(struct zfcp_port *const port) goto unlock_host_lock; } - /* port is about to be removed, so no more unit_add or slave_alloc */ + /* port is about to be removed, so no more unit_add or sdev_init */ zfcp_sysfs_port_set_removing(port); in_use = false; diff --git a/drivers/s390/scsi/zfcp_unit.c b/drivers/s390/scsi/zfcp_unit.c index 60f2a04f0869..4ef2a635d34f 100644 --- a/drivers/s390/scsi/zfcp_unit.c +++ b/drivers/s390/scsi/zfcp_unit.c @@ -170,7 +170,7 @@ int zfcp_unit_add(struct zfcp_port *port, u64 fcp_lun) write_unlock_irq(&port->unit_list_lock); /* * lock order: shost->scan_mutex before zfcp_sysfs_port_units_mutex - * due to zfcp_unit_scsi_scan() => zfcp_scsi_slave_alloc() + * due to zfcp_unit_scsi_scan() => zfcp_scsi_sdev_init() */ mutex_unlock(&zfcp_sysfs_port_units_mutex); diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index 6fb61c88ea11..883d4a12a172 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -1968,13 +1968,14 @@ static char *twa_string_lookup(twa_message_type *table, unsigned int code) } /* End twa_string_lookup() */ /* This function gets called when a disk is coming on-line */ -static int twa_slave_configure(struct scsi_device *sdev) +static int twa_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { /* Force 60 second timeout */ blk_queue_rq_timeout(sdev->request_queue, 60 * HZ); return 0; -} /* End twa_slave_configure() */ +} /* End twa_sdev_configure() */ static const struct scsi_host_template driver_template = { .module = THIS_MODULE, @@ -1984,7 +1985,7 @@ static const struct scsi_host_template driver_template = { .bios_param = twa_scsi_biosparam, .change_queue_depth = scsi_change_queue_depth, .can_queue = TW_Q_LENGTH-2, - .slave_configure = twa_slave_configure, + .sdev_configure = twa_sdev_configure, .this_id = -1, .sg_tablesize = TW_APACHE_MAX_SGL_LENGTH, .max_sectors = TW_MAX_SECTORS, @@ -2260,7 +2261,7 @@ out_disable_device: } /* End twa_resume() */ /* PCI Devices supported by this driver */ -static struct pci_device_id twa_pci_tbl[] = { +static const struct pci_device_id twa_pci_tbl[] = { { PCI_VENDOR_ID_3WARE, PCI_DEVICE_ID_3WARE_9000, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, { PCI_VENDOR_ID_3WARE, PCI_DEVICE_ID_3WARE_9550SX, diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c index caa6713a62a4..e057ab9c7b90 100644 --- a/drivers/scsi/3w-sas.c +++ b/drivers/scsi/3w-sas.c @@ -96,7 +96,7 @@ static int twl_reset_device_extension(TW_Device_Extension *tw_dev, int ioctl_res /* This function returns AENs through sysfs */ static ssize_t twl_sysfs_aen_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *outbuf, loff_t offset, size_t count) { struct device *dev = container_of(kobj, struct device, kobj); @@ -116,18 +116,18 @@ static ssize_t twl_sysfs_aen_read(struct file *filp, struct kobject *kobj, } /* End twl_sysfs_aen_read() */ /* aen_read sysfs attribute initializer */ -static struct bin_attribute twl_sysfs_aen_read_attr = { +static const struct bin_attribute twl_sysfs_aen_read_attr = { .attr = { .name = "3ware_aen_read", .mode = S_IRUSR, }, .size = 0, - .read = twl_sysfs_aen_read + .read_new = twl_sysfs_aen_read }; /* This function returns driver compatibility info through sysfs */ static ssize_t twl_sysfs_compat_info(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *outbuf, loff_t offset, size_t count) { struct device *dev = container_of(kobj, struct device, kobj); @@ -147,13 +147,13 @@ static ssize_t twl_sysfs_compat_info(struct file *filp, struct kobject *kobj, } /* End twl_sysfs_compat_info() */ /* compat_info sysfs attribute initializer */ -static struct bin_attribute twl_sysfs_compat_info_attr = { +static const struct bin_attribute twl_sysfs_compat_info_attr = { .attr = { .name = "3ware_compat_info", .mode = S_IRUSR, }, .size = 0, - .read = twl_sysfs_compat_info + .read_new = twl_sysfs_compat_info }; /* Show some statistics about the card */ @@ -1523,13 +1523,14 @@ static void twl_shutdown(struct pci_dev *pdev) } /* End twl_shutdown() */ /* This function configures unit settings when a unit is coming on-line */ -static int twl_slave_configure(struct scsi_device *sdev) +static int twl_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { /* Force 60 second timeout */ blk_queue_rq_timeout(sdev->request_queue, 60 * HZ); return 0; -} /* End twl_slave_configure() */ +} /* End twl_sdev_configure() */ static const struct scsi_host_template driver_template = { .module = THIS_MODULE, @@ -1539,7 +1540,7 @@ static const struct scsi_host_template driver_template = { .bios_param = twl_scsi_biosparam, .change_queue_depth = scsi_change_queue_depth, .can_queue = TW_Q_LENGTH-2, - .slave_configure = twl_slave_configure, + .sdev_configure = twl_sdev_configure, .this_id = -1, .sg_tablesize = TW_LIBERATOR_MAX_SGL_LENGTH, .max_sectors = TW_MAX_SECTORS, @@ -1821,7 +1822,7 @@ out_disable_device: } /* End twl_resume() */ /* PCI Devices supported by this driver */ -static struct pci_device_id twl_pci_tbl[] = { +static const struct pci_device_id twl_pci_tbl[] = { { PCI_VDEVICE(3WARE, PCI_DEVICE_ID_3WARE_9750) }, { } }; diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c index 2c0fb6da0e60..89bd56f78ef9 100644 --- a/drivers/scsi/3w-xxxx.c +++ b/drivers/scsi/3w-xxxx.c @@ -172,7 +172,7 @@ Initialize queues correctly when loading with no valid units. 1.02.00.034 - Fix tw_decode_bits() to handle multiple errors. Add support for user configurable cmd_per_lun. - Add support for sht->slave_configure(). + Add support for sht->sdev_configure(). 1.02.00.035 - Improve tw_allocate_memory() memory allocation. Fix tw_chrdev_ioctl() to sleep correctly. 1.02.00.036 - Increase character ioctl timeout to 60 seconds. @@ -2221,13 +2221,13 @@ static void tw_shutdown(struct pci_dev *pdev) } /* End tw_shutdown() */ /* This function gets called when a disk is coming online */ -static int tw_slave_configure(struct scsi_device *sdev) +static int tw_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { /* Force 60 second timeout */ blk_queue_rq_timeout(sdev->request_queue, 60 * HZ); return 0; -} /* End tw_slave_configure() */ +} /* End tw_sdev_configure() */ static const struct scsi_host_template driver_template = { .module = THIS_MODULE, @@ -2237,7 +2237,7 @@ static const struct scsi_host_template driver_template = { .bios_param = tw_scsi_biosparam, .change_queue_depth = scsi_change_queue_depth, .can_queue = TW_Q_LENGTH-2, - .slave_configure = tw_slave_configure, + .sdev_configure = tw_sdev_configure, .this_id = -1, .sg_tablesize = TW_MAX_SGL_LENGTH, .max_sectors = TW_MAX_SECTORS, @@ -2393,7 +2393,7 @@ static void tw_remove(struct pci_dev *pdev) } /* End tw_remove() */ /* PCI Devices supported by this driver */ -static struct pci_device_id tw_pci_tbl[] = { +static const struct pci_device_id tw_pci_tbl[] = { { PCI_VENDOR_ID_3WARE, PCI_DEVICE_ID_3WARE_1000, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, { PCI_VENDOR_ID_3WARE, PCI_DEVICE_ID_3WARE_7000, diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index 85439e976143..71b7ac027f48 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -158,9 +158,10 @@ STATIC int NCR_700_abort(struct scsi_cmnd * SCpnt); STATIC int NCR_700_host_reset(struct scsi_cmnd * SCpnt); STATIC void NCR_700_chip_setup(struct Scsi_Host *host); STATIC void NCR_700_chip_reset(struct Scsi_Host *host); -STATIC int NCR_700_slave_alloc(struct scsi_device *SDpnt); -STATIC int NCR_700_slave_configure(struct scsi_device *SDpnt); -STATIC void NCR_700_slave_destroy(struct scsi_device *SDpnt); +STATIC int NCR_700_sdev_init(struct scsi_device *SDpnt); +STATIC int NCR_700_sdev_configure(struct scsi_device *SDpnt, + struct queue_limits *lim); +STATIC void NCR_700_sdev_destroy(struct scsi_device *SDpnt); static int NCR_700_change_queue_depth(struct scsi_device *SDpnt, int depth); STATIC const struct attribute_group *NCR_700_dev_groups[]; @@ -330,9 +331,9 @@ NCR_700_detect(struct scsi_host_template *tpnt, tpnt->can_queue = NCR_700_COMMAND_SLOTS_PER_HOST; tpnt->sg_tablesize = NCR_700_SG_SEGMENTS; tpnt->cmd_per_lun = NCR_700_CMD_PER_LUN; - tpnt->slave_configure = NCR_700_slave_configure; - tpnt->slave_destroy = NCR_700_slave_destroy; - tpnt->slave_alloc = NCR_700_slave_alloc; + tpnt->sdev_configure = NCR_700_sdev_configure; + tpnt->sdev_destroy = NCR_700_sdev_destroy; + tpnt->sdev_init = NCR_700_sdev_init; tpnt->change_queue_depth = NCR_700_change_queue_depth; if(tpnt->name == NULL) @@ -2017,7 +2018,7 @@ NCR_700_set_offset(struct scsi_target *STp, int offset) } STATIC int -NCR_700_slave_alloc(struct scsi_device *SDp) +NCR_700_sdev_init(struct scsi_device *SDp) { SDp->hostdata = kzalloc(sizeof(struct NCR_700_Device_Parameters), GFP_KERNEL); @@ -2029,7 +2030,7 @@ NCR_700_slave_alloc(struct scsi_device *SDp) } STATIC int -NCR_700_slave_configure(struct scsi_device *SDp) +NCR_700_sdev_configure(struct scsi_device *SDp, struct queue_limits *lim) { struct NCR_700_Host_Parameters *hostdata = (struct NCR_700_Host_Parameters *)SDp->host->hostdata[0]; @@ -2052,7 +2053,7 @@ NCR_700_slave_configure(struct scsi_device *SDp) } STATIC void -NCR_700_slave_destroy(struct scsi_device *SDp) +NCR_700_sdev_destroy(struct scsi_device *SDp) { kfree(SDp->hostdata); SDp->hostdata = NULL; diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c index 2135a2b3e2d0..1f100270cd38 100644 --- a/drivers/scsi/BusLogic.c +++ b/drivers/scsi/BusLogic.c @@ -2153,14 +2153,15 @@ static void __init blogic_inithoststruct(struct blogic_adapter *adapter, } /* - blogic_slaveconfig will actually set the queue depth on individual + blogic_sdev_configure will actually set the queue depth on individual scsi devices as they are permanently added to the device chain. We shamelessly rip off the SelectQueueDepths code to make this work mostly like it used to. Since we don't get called once at the end of the scan but instead get called for each device, we have to do things a bit differently. */ -static int blogic_slaveconfig(struct scsi_device *dev) +static int blogic_sdev_configure(struct scsi_device *dev, + struct queue_limits *lim) { struct blogic_adapter *adapter = (struct blogic_adapter *) dev->host->hostdata; @@ -3672,7 +3673,7 @@ static const struct scsi_host_template blogic_template = { .name = "BusLogic", .info = blogic_drvr_info, .queuecommand = blogic_qcmd, - .slave_configure = blogic_slaveconfig, + .sdev_configure = blogic_sdev_configure, .bios_param = blogic_diskparam, .eh_host_reset_handler = blogic_hostreset, #if 0 @@ -3715,7 +3716,7 @@ static void __exit blogic_exit(void) __setup("BusLogic=", blogic_setup); #ifdef MODULE -/*static struct pci_device_id blogic_pci_tbl[] = { +/*static const struct pci_device_id blogic_pci_tbl[] = { { PCI_VENDOR_ID_BUSLOGIC, PCI_DEVICE_ID_BUSLOGIC_MULTIMASTER, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, { PCI_VENDOR_ID_BUSLOGIC, PCI_DEVICE_ID_BUSLOGIC_MULTIMASTER_NC, diff --git a/drivers/scsi/BusLogic.h b/drivers/scsi/BusLogic.h index 7d1ec10f2430..61bf26d4fc10 100644 --- a/drivers/scsi/BusLogic.h +++ b/drivers/scsi/BusLogic.h @@ -1274,7 +1274,8 @@ static inline void blogic_incszbucket(unsigned int *cmdsz_buckets, static const char *blogic_drvr_info(struct Scsi_Host *); static int blogic_qcmd(struct Scsi_Host *h, struct scsi_cmnd *); static int blogic_diskparam(struct scsi_device *, struct block_device *, sector_t, int *); -static int blogic_slaveconfig(struct scsi_device *); +static int blogic_sdev_configure(struct scsi_device *, + struct queue_limits *lim); static void blogic_qcompleted_ccb(struct blogic_ccb *); static irqreturn_t blogic_inthandler(int, void *); static int blogic_resetadapter(struct blogic_adapter *, bool hard_reset); diff --git a/drivers/scsi/a100u2w.c b/drivers/scsi/a100u2w.c index b95147fb18b0..a8979f9e30ff 100644 --- a/drivers/scsi/a100u2w.c +++ b/drivers/scsi/a100u2w.c @@ -1206,7 +1206,7 @@ static void inia100_remove_one(struct pci_dev *pdev) scsi_host_put(shost); } -static struct pci_device_id inia100_pci_tbl[] = { +static const struct pci_device_id inia100_pci_tbl[] = { {PCI_VENDOR_ID_INIT, 0x1060, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {0,} }; diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 68f4dbcfff49..91170a67cc91 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -377,15 +377,17 @@ static int aac_biosparm(struct scsi_device *sdev, struct block_device *bdev, } /** - * aac_slave_configure - compute queue depths + * aac_sdev_configure - compute queue depths * @sdev: SCSI device we are considering + * @lim: Request queue limits * * Selects queue depths for each target device based on the host adapter's * total capacity and the queue depth supported by the target device. * A queue depth of one automatically disables tagged queueing. */ -static int aac_slave_configure(struct scsi_device *sdev) +static int aac_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct aac_dev *aac = (struct aac_dev *)sdev->host->hostdata; int chn, tid; @@ -1487,7 +1489,7 @@ static const struct scsi_host_template aac_driver_template = { .queuecommand = aac_queuecommand, .bios_param = aac_biosparm, .shost_groups = aac_host_groups, - .slave_configure = aac_slave_configure, + .sdev_configure = aac_sdev_configure, .change_queue_depth = aac_change_queue_depth, .sdev_groups = aac_dev_groups, .eh_abort_handler = aac_eh_abort, diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c index fd4fcb37863d..3a2c336307c0 100644 --- a/drivers/scsi/advansys.c +++ b/drivers/scsi/advansys.c @@ -4496,7 +4496,7 @@ static int AdvInitAsc3550Driver(ADV_DVC_VAR *asc_dvc) /* * Microcode operating variables for WDTR, SDTR, and command tag - * queuing will be set in slave_configure() based on what a + * queuing will be set in sdev_configure() based on what a * device reports it is capable of in Inquiry byte 7. * * If SCSI Bus Resets have been disabled, then directly set @@ -5013,7 +5013,7 @@ static int AdvInitAsc38C0800Driver(ADV_DVC_VAR *asc_dvc) /* * Microcode operating variables for WDTR, SDTR, and command tag - * queuing will be set in slave_configure() based on what a + * queuing will be set in sdev_configure() based on what a * device reports it is capable of in Inquiry byte 7. * * If SCSI Bus Resets have been disabled, then directly set @@ -5508,7 +5508,7 @@ static int AdvInitAsc38C1600Driver(ADV_DVC_VAR *asc_dvc) /* * Microcode operating variables for WDTR, SDTR, and command tag - * queuing will be set in slave_configure() based on what a + * queuing will be set in sdev_configure() based on what a * device reports it is capable of in Inquiry byte 7. * * If SCSI Bus Resets have been disabled, then directly set @@ -7219,7 +7219,7 @@ static void AscAsyncFix(ASC_DVC_VAR *asc_dvc, struct scsi_device *sdev) } static void -advansys_narrow_slave_configure(struct scsi_device *sdev, ASC_DVC_VAR *asc_dvc) +advansys_narrow_sdev_configure(struct scsi_device *sdev, ASC_DVC_VAR *asc_dvc) { ASC_SCSI_BIT_ID_TYPE tid_bit = 1 << sdev->id; ASC_SCSI_BIT_ID_TYPE orig_use_tagged_qng = asc_dvc->use_tagged_qng; @@ -7345,7 +7345,7 @@ static void advansys_wide_enable_ppr(ADV_DVC_VAR *adv_dvc, } static void -advansys_wide_slave_configure(struct scsi_device *sdev, ADV_DVC_VAR *adv_dvc) +advansys_wide_sdev_configure(struct scsi_device *sdev, ADV_DVC_VAR *adv_dvc) { AdvPortAddr iop_base = adv_dvc->iop_base; unsigned short tidmask = 1 << sdev->id; @@ -7391,16 +7391,17 @@ advansys_wide_slave_configure(struct scsi_device *sdev, ADV_DVC_VAR *adv_dvc) * Set the number of commands to queue per device for the * specified host adapter. */ -static int advansys_slave_configure(struct scsi_device *sdev) +static int advansys_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct asc_board *boardp = shost_priv(sdev->host); if (ASC_NARROW_BOARD(boardp)) - advansys_narrow_slave_configure(sdev, - &boardp->dvc_var.asc_dvc_var); + advansys_narrow_sdev_configure(sdev, + &boardp->dvc_var.asc_dvc_var); else - advansys_wide_slave_configure(sdev, - &boardp->dvc_var.adv_dvc_var); + advansys_wide_sdev_configure(sdev, + &boardp->dvc_var.adv_dvc_var); return 0; } @@ -10612,7 +10613,7 @@ static const struct scsi_host_template advansys_template = { .queuecommand = advansys_queuecommand, .eh_host_reset_handler = advansys_reset, .bios_param = advansys_biosparam, - .slave_configure = advansys_slave_configure, + .sdev_configure = advansys_sdev_configure, .cmd_size = sizeof(struct advansys_cmd), }; @@ -11408,7 +11409,7 @@ static struct eisa_driver advansys_eisa_driver = { }; /* PCI Devices supported by this driver */ -static struct pci_device_id advansys_pci_tbl[] = { +static const struct pci_device_id advansys_pci_tbl[] = { {PCI_VENDOR_ID_ASP, PCI_DEVICE_ID_ASP_1200A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {PCI_VENDOR_ID_ASP, PCI_DEVICE_ID_ASP_ABP940, diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c index 4202059815a0..17dfc3c72110 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.c +++ b/drivers/scsi/aic7xxx/aic79xx_osm.c @@ -672,7 +672,7 @@ ahd_linux_target_destroy(struct scsi_target *starget) } static int -ahd_linux_slave_alloc(struct scsi_device *sdev) +ahd_linux_sdev_init(struct scsi_device *sdev) { struct ahd_softc *ahd = *((struct ahd_softc **)sdev->host->hostdata); @@ -701,7 +701,7 @@ ahd_linux_slave_alloc(struct scsi_device *sdev) } static int -ahd_linux_slave_configure(struct scsi_device *sdev) +ahd_linux_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { if (bootverbose) sdev_printk(KERN_INFO, sdev, "Slave Configure\n"); @@ -906,8 +906,8 @@ struct scsi_host_template aic79xx_driver_template = { .this_id = -1, .max_sectors = 8192, .cmd_per_lun = 2, - .slave_alloc = ahd_linux_slave_alloc, - .slave_configure = ahd_linux_slave_configure, + .sdev_init = ahd_linux_sdev_init, + .sdev_configure = ahd_linux_sdev_configure, .target_alloc = ahd_linux_target_alloc, .target_destroy = ahd_linux_target_destroy, }; diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c index b0c4f2345321..cebf8c5d0caf 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c @@ -632,7 +632,7 @@ ahc_linux_target_destroy(struct scsi_target *starget) } static int -ahc_linux_slave_alloc(struct scsi_device *sdev) +ahc_linux_sdev_init(struct scsi_device *sdev) { struct ahc_softc *ahc = *((struct ahc_softc **)sdev->host->hostdata); @@ -664,7 +664,7 @@ ahc_linux_slave_alloc(struct scsi_device *sdev) } static int -ahc_linux_slave_configure(struct scsi_device *sdev) +ahc_linux_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { if (bootverbose) sdev_printk(KERN_INFO, sdev, "Slave Configure\n"); @@ -791,8 +791,8 @@ struct scsi_host_template aic7xxx_driver_template = { .this_id = -1, .max_sectors = 8192, .cmd_per_lun = 2, - .slave_alloc = ahc_linux_slave_alloc, - .slave_configure = ahc_linux_slave_configure, + .sdev_init = ahc_linux_sdev_init, + .sdev_configure = ahc_linux_sdev_configure, .target_alloc = ahc_linux_target_alloc, .target_destroy = ahc_linux_target_destroy, }; diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y b/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y index 65182ad9cdf8..b1c9ce477cbd 100644 --- a/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y +++ b/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y @@ -102,6 +102,7 @@ static void add_conditional(symbol_t *symbol); static void add_version(const char *verstring); static int is_download_const(expression_t *immed); static int is_location_address(symbol_t *symbol); +int yylex(); void yyerror(const char *string); #define SRAM_SYMNAME "SRAM_BASE" diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.y b/drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.y index 8c0479865f04..5c7350eb5b5c 100644 --- a/drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.y +++ b/drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.y @@ -61,6 +61,7 @@ static symbol_t *macro_symbol; static void add_macro_arg(const char *argtext, int position); +int mmlex(); void mmerror(const char *string); %} diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l b/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l index c78d4f68eea5..fc7e6c58148d 100644 --- a/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l +++ b/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l @@ -64,6 +64,9 @@ static char *string_buf_ptr; static int parren_count; static int quote_count; static char buf[255]; +void mm_switch_to_buffer(YY_BUFFER_STATE); +void mmparse(); +void mm_delete_buffer(YY_BUFFER_STATE); %} PATH ([/]*[-A-Za-z0-9_.])+ diff --git a/drivers/scsi/am53c974.c b/drivers/scsi/am53c974.c index fbb29dbb1e50..003e61831e33 100644 --- a/drivers/scsi/am53c974.c +++ b/drivers/scsi/am53c974.c @@ -513,7 +513,7 @@ static void pci_esp_remove_one(struct pci_dev *pdev) scsi_host_put(esp->host); } -static struct pci_device_id am53c974_pci_tbl[] = { +static const struct pci_device_id am53c974_pci_tbl[] = { { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_SCSI, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, { } diff --git a/drivers/scsi/arcmsr/arcmsr_attr.c b/drivers/scsi/arcmsr/arcmsr_attr.c index baeb5e795690..8e3d4799ce93 100644 --- a/drivers/scsi/arcmsr/arcmsr_attr.c +++ b/drivers/scsi/arcmsr/arcmsr_attr.c @@ -60,7 +60,7 @@ static ssize_t arcmsr_sysfs_iop_message_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin, + const struct bin_attribute *bin, char *buf, loff_t off, size_t count) { @@ -107,7 +107,7 @@ static ssize_t arcmsr_sysfs_iop_message_read(struct file *filp, static ssize_t arcmsr_sysfs_iop_message_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin, + const struct bin_attribute *bin, char *buf, loff_t off, size_t count) { @@ -155,7 +155,7 @@ static ssize_t arcmsr_sysfs_iop_message_write(struct file *filp, static ssize_t arcmsr_sysfs_iop_message_clear(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin, + const struct bin_attribute *bin, char *buf, loff_t off, size_t count) { @@ -194,7 +194,7 @@ static const struct bin_attribute arcmsr_sysfs_message_read_attr = { .mode = S_IRUSR , }, .size = ARCMSR_API_DATA_BUFLEN, - .read = arcmsr_sysfs_iop_message_read, + .read_new = arcmsr_sysfs_iop_message_read, }; static const struct bin_attribute arcmsr_sysfs_message_write_attr = { @@ -203,7 +203,7 @@ static const struct bin_attribute arcmsr_sysfs_message_write_attr = { .mode = S_IWUSR, }, .size = ARCMSR_API_DATA_BUFLEN, - .write = arcmsr_sysfs_iop_message_write, + .write_new = arcmsr_sysfs_iop_message_write, }; static const struct bin_attribute arcmsr_sysfs_message_clear_attr = { @@ -212,7 +212,7 @@ static const struct bin_attribute arcmsr_sysfs_message_clear_attr = { .mode = S_IWUSR, }, .size = 1, - .write = arcmsr_sysfs_iop_message_clear, + .write_new = arcmsr_sysfs_iop_message_clear, }; int arcmsr_alloc_sysfs_attr(struct AdapterControlBlock *acb) diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index 35860c61468b..221a520e8a9b 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -143,7 +143,8 @@ static irqreturn_t arcmsr_interrupt(struct AdapterControlBlock *acb); static void arcmsr_free_irq(struct pci_dev *, struct AdapterControlBlock *); static void arcmsr_wait_firmware_ready(struct AdapterControlBlock *acb); static void arcmsr_set_iop_datetime(struct timer_list *); -static int arcmsr_slave_config(struct scsi_device *sdev); +static int arcmsr_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim); static int arcmsr_adjust_disk_queue_depth(struct scsi_device *sdev, int queue_depth) { if (queue_depth > ARCMSR_MAX_CMD_PERLUN) @@ -160,7 +161,7 @@ static const struct scsi_host_template arcmsr_scsi_host_template = { .eh_abort_handler = arcmsr_abort, .eh_bus_reset_handler = arcmsr_bus_reset, .bios_param = arcmsr_bios_param, - .slave_configure = arcmsr_slave_config, + .sdev_configure = arcmsr_sdev_configure, .change_queue_depth = arcmsr_adjust_disk_queue_depth, .can_queue = ARCMSR_DEFAULT_OUTSTANDING_CMD, .this_id = ARCMSR_SCSI_INITIATOR_ID, @@ -171,7 +172,7 @@ static const struct scsi_host_template arcmsr_scsi_host_template = { .no_write_same = 1, }; -static struct pci_device_id arcmsr_device_id_table[] = { +static const struct pci_device_id arcmsr_device_id_table[] = { {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1110), .driver_data = ACB_ADAPTER_TYPE_A}, {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1120), @@ -1044,7 +1045,7 @@ static void arcmsr_init_get_devmap_timer(struct AdapterControlBlock *pacb) static void arcmsr_init_set_datetime_timer(struct AdapterControlBlock *pacb) { timer_setup(&pacb->refresh_timer, arcmsr_set_iop_datetime, 0); - pacb->refresh_timer.expires = jiffies + msecs_to_jiffies(60 * 1000); + pacb->refresh_timer.expires = jiffies + secs_to_jiffies(60); add_timer(&pacb->refresh_timer); } @@ -3344,7 +3345,8 @@ static int arcmsr_queue_command_lck(struct scsi_cmnd *cmd) static DEF_SCSI_QCMD(arcmsr_queue_command) -static int arcmsr_slave_config(struct scsi_device *sdev) +static int arcmsr_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { unsigned int dev_timeout; diff --git a/drivers/scsi/atp870u.c b/drivers/scsi/atp870u.c index 928151ec927a..401242912855 100644 --- a/drivers/scsi/atp870u.c +++ b/drivers/scsi/atp870u.c @@ -1743,7 +1743,7 @@ static const struct scsi_host_template atp870u_template = { .max_sectors = ATP870U_MAX_SECTORS, }; -static struct pci_device_id atp870u_id_table[] = { +static const struct pci_device_id atp870u_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_ARTOP, ATP885_DEVID) }, { PCI_DEVICE(PCI_VENDOR_ID_ARTOP, ATP880_DEVID1) }, { PCI_DEVICE(PCI_VENDOR_ID_ARTOP, ATP880_DEVID2) }, diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c index 66fb701401de..a719a18f0fbc 100644 --- a/drivers/scsi/bfa/bfad_im.c +++ b/drivers/scsi/bfa/bfad_im.c @@ -25,7 +25,7 @@ struct scsi_transport_template *bfad_im_scsi_transport_template; struct scsi_transport_template *bfad_im_scsi_vport_transport_template; static void bfad_im_itnim_work_handler(struct work_struct *work); static int bfad_im_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *cmnd); -static int bfad_im_slave_alloc(struct scsi_device *sdev); +static int bfad_im_sdev_init(struct scsi_device *sdev); static void bfad_im_fc_rport_add(struct bfad_im_port_s *im_port, struct bfad_itnim_s *itnim); @@ -404,10 +404,10 @@ bfad_im_reset_target_handler(struct scsi_cmnd *cmnd) } /* - * Scsi_Host template entry slave_destroy. + * Scsi_Host template entry sdev_destroy. */ static void -bfad_im_slave_destroy(struct scsi_device *sdev) +bfad_im_sdev_destroy(struct scsi_device *sdev) { sdev->hostdata = NULL; return; @@ -783,7 +783,7 @@ bfad_thread_workq(struct bfad_s *bfad) * Return non-zero if fails. */ static int -bfad_im_slave_configure(struct scsi_device *sdev) +bfad_im_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { scsi_change_queue_depth(sdev, bfa_lun_queue_depth); return 0; @@ -800,9 +800,9 @@ struct scsi_host_template bfad_im_scsi_host_template = { .eh_device_reset_handler = bfad_im_reset_lun_handler, .eh_target_reset_handler = bfad_im_reset_target_handler, - .slave_alloc = bfad_im_slave_alloc, - .slave_configure = bfad_im_slave_configure, - .slave_destroy = bfad_im_slave_destroy, + .sdev_init = bfad_im_sdev_init, + .sdev_configure = bfad_im_sdev_configure, + .sdev_destroy = bfad_im_sdev_destroy, .this_id = -1, .sg_tablesize = BFAD_IO_MAX_SGE, @@ -823,9 +823,9 @@ struct scsi_host_template bfad_im_vport_template = { .eh_device_reset_handler = bfad_im_reset_lun_handler, .eh_target_reset_handler = bfad_im_reset_target_handler, - .slave_alloc = bfad_im_slave_alloc, - .slave_configure = bfad_im_slave_configure, - .slave_destroy = bfad_im_slave_destroy, + .sdev_init = bfad_im_sdev_init, + .sdev_configure = bfad_im_sdev_configure, + .sdev_destroy = bfad_im_sdev_destroy, .this_id = -1, .sg_tablesize = BFAD_IO_MAX_SGE, @@ -915,7 +915,7 @@ bfad_get_itnim(struct bfad_im_port_s *im_port, int id) } /* - * Function is invoked from the SCSI Host Template slave_alloc() entry point. + * Function is invoked from the SCSI Host Template sdev_init() entry point. * Has the logic to query the LUN Mask database to check if this LUN needs to * be made visible to the SCSI mid-layer or not. * @@ -946,10 +946,10 @@ bfad_im_check_if_make_lun_visible(struct scsi_device *sdev, } /* - * Scsi_Host template entry slave_alloc + * Scsi_Host template entry sdev_init */ static int -bfad_im_slave_alloc(struct scsi_device *sdev) +bfad_im_sdev_init(struct scsi_device *sdev) { struct fc_rport *rport = starget_to_rport(scsi_target(sdev)); struct bfad_itnim_data_s *itnim_data; diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index f49783b89d04..5ac20c93637c 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -2610,14 +2610,11 @@ static int bnx2fc_cpu_online(unsigned int cpu) p = &per_cpu(bnx2fc_percpu, cpu); - thread = kthread_create_on_node(bnx2fc_percpu_io_thread, - (void *)p, cpu_to_node(cpu), - "bnx2fc_thread/%d", cpu); + thread = kthread_create_on_cpu(bnx2fc_percpu_io_thread, + (void *)p, cpu, "bnx2fc_thread/%d"); if (IS_ERR(thread)) return PTR_ERR(thread); - /* bind thread to the cpu */ - kthread_bind(thread, cpu); p->iothread = thread; wake_up_process(thread); return 0; @@ -2652,7 +2649,8 @@ static int bnx2fc_cpu_offline(unsigned int cpu) return 0; } -static int bnx2fc_slave_configure(struct scsi_device *sdev) +static int bnx2fc_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { if (!bnx2fc_queue_depth) return 0; @@ -2951,7 +2949,7 @@ static struct scsi_host_template bnx2fc_shost_template = { .eh_device_reset_handler = bnx2fc_eh_device_reset, /* lun reset */ .eh_target_reset_handler = bnx2fc_eh_target_reset, /* tgt reset */ .eh_host_reset_handler = fc_eh_host_reset, - .slave_alloc = fc_slave_alloc, + .sdev_init = fc_sdev_init, .change_queue_depth = scsi_change_queue_depth, .this_id = -1, .cmd_per_lun = 3, @@ -2959,7 +2957,7 @@ static struct scsi_host_template bnx2fc_shost_template = { .dma_boundary = 0x7fff, .max_sectors = 0x3fbf, .track_queue_depth = 1, - .slave_configure = bnx2fc_slave_configure, + .sdev_configure = bnx2fc_sdev_configure, .shost_groups = bnx2fc_host_groups, .cmd_size = sizeof(struct bnx2fc_priv), }; diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c index 872ad37e2a6e..cecc3a026762 100644 --- a/drivers/scsi/bnx2i/bnx2i_init.c +++ b/drivers/scsi/bnx2i/bnx2i_init.c @@ -415,14 +415,11 @@ static int bnx2i_cpu_online(unsigned int cpu) p = &per_cpu(bnx2i_percpu, cpu); - thread = kthread_create_on_node(bnx2i_percpu_io_thread, (void *)p, - cpu_to_node(cpu), - "bnx2i_thread/%d", cpu); + thread = kthread_create_on_cpu(bnx2i_percpu_io_thread, (void *)p, + cpu, "bnx2i_thread/%d"); if (IS_ERR(thread)) return PTR_ERR(thread); - /* bind thread to the cpu */ - kthread_bind(thread, cpu); p->iothread = thread; wake_up_process(thread); return 0; diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c index 8329f0cab4e7..34bde6650fae 100644 --- a/drivers/scsi/csiostor/csio_scsi.c +++ b/drivers/scsi/csiostor/csio_scsi.c @@ -800,7 +800,7 @@ csio_scsis_io_active(struct csio_ioreq *req, enum csio_scsi_ev evt) rn = req->rnode; /* * FW says remote device is lost, but rnode - * doesnt reflect it. + * doesn't reflect it. */ if (csio_scsi_itnexus_loss_error(req->wr_status) && csio_is_rnode_ready(rn)) { @@ -2224,7 +2224,7 @@ fail: } static int -csio_slave_alloc(struct scsi_device *sdev) +csio_sdev_init(struct scsi_device *sdev) { struct fc_rport *rport = starget_to_rport(scsi_target(sdev)); @@ -2237,14 +2237,14 @@ csio_slave_alloc(struct scsi_device *sdev) } static int -csio_slave_configure(struct scsi_device *sdev) +csio_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { scsi_change_queue_depth(sdev, csio_lun_qdepth); return 0; } static void -csio_slave_destroy(struct scsi_device *sdev) +csio_sdev_destroy(struct scsi_device *sdev) { sdev->hostdata = NULL; } @@ -2276,9 +2276,9 @@ struct scsi_host_template csio_fcoe_shost_template = { .eh_timed_out = fc_eh_timed_out, .eh_abort_handler = csio_eh_abort_handler, .eh_device_reset_handler = csio_eh_lun_reset_handler, - .slave_alloc = csio_slave_alloc, - .slave_configure = csio_slave_configure, - .slave_destroy = csio_slave_destroy, + .sdev_init = csio_sdev_init, + .sdev_configure = csio_sdev_configure, + .sdev_destroy = csio_sdev_destroy, .scan_finished = csio_scan_finished, .this_id = -1, .sg_tablesize = CSIO_SCSI_MAX_SGE, @@ -2295,9 +2295,9 @@ struct scsi_host_template csio_fcoe_shost_vport_template = { .eh_timed_out = fc_eh_timed_out, .eh_abort_handler = csio_eh_abort_handler, .eh_device_reset_handler = csio_eh_lun_reset_handler, - .slave_alloc = csio_slave_alloc, - .slave_configure = csio_slave_configure, - .slave_destroy = csio_slave_destroy, + .sdev_init = csio_sdev_init, + .sdev_configure = csio_sdev_configure, + .sdev_destroy = csio_sdev_destroy, .scan_finished = csio_scan_finished, .this_id = -1, .sg_tablesize = CSIO_SCSI_MAX_SGE, diff --git a/drivers/scsi/cxlflash/Kconfig b/drivers/scsi/cxlflash/Kconfig index 5533bdcb0458..c424d36e89a6 100644 --- a/drivers/scsi/cxlflash/Kconfig +++ b/drivers/scsi/cxlflash/Kconfig @@ -4,10 +4,12 @@ # config CXLFLASH - tristate "Support for IBM CAPI Flash" + tristate "Support for IBM CAPI Flash (DEPRECATED)" depends on PCI && SCSI && (CXL || OCXL) && EEH select IRQ_POLL - default m help + The cxlflash driver is deprecated and will be removed in a future + kernel release. + Allows CAPI Accelerated IO to Flash If unsure, say N. diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 60d62b93d624..ae626e389c8b 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3177,7 +3177,7 @@ static struct dev_dependent_vals dev_briard_vals = { CXLFLASH_MAX_SECTORS, /* * PCI device binding table */ -static struct pci_device_id cxlflash_pci_table[] = { +static const struct pci_device_id cxlflash_pci_table[] = { {PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CORSA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_corsa_vals}, {PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_FLASH_GT, @@ -3651,6 +3651,8 @@ static int cxlflash_probe(struct pci_dev *pdev, int rc = 0; int k; + dev_err_once(&pdev->dev, "DEPRECATION: cxlflash is deprecated and will be removed in a future kernel release\n"); + dev_dbg(&pdev->dev, "%s: Found CXLFLASH with IRQ: %d\n", __func__, pdev->irq); diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c index b375509d1470..97631f48e19d 100644 --- a/drivers/scsi/cxlflash/superpipe.c +++ b/drivers/scsi/cxlflash/superpipe.c @@ -966,7 +966,7 @@ static int cxlflash_disk_detach(struct scsi_device *sdev, void *detach) * * This routine is the release handler for the fops registered with * the CXL services on an initial attach for a context. It is called - * when a close (explicity by the user or as part of a process tear + * when a close (explicitly by the user or as part of a process tear * down) is performed on the adapter file descriptor returned to the * user. The user should be aware that explicitly performing a close * considered catastrophic and subsequent usage of the superpipe API diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c index d108a86e196e..e71de2419758 100644 --- a/drivers/scsi/dc395x.c +++ b/drivers/scsi/dc395x.c @@ -3715,13 +3715,13 @@ static void adapter_remove_and_free_all_devices(struct AdapterCtlBlk* acb) /** - * dc395x_slave_alloc - Called by the scsi mid layer to tell us about a new + * dc395x_sdev_init - Called by the scsi mid layer to tell us about a new * scsi device that we need to deal with. We allocate a new device and then * insert that device into the adapters device list. * * @scsi_device: The new scsi device that we need to handle. **/ -static int dc395x_slave_alloc(struct scsi_device *scsi_device) +static int dc395x_sdev_init(struct scsi_device *scsi_device) { struct AdapterCtlBlk *acb = (struct AdapterCtlBlk *)scsi_device->host->hostdata; struct DeviceCtlBlk *dcb; @@ -3736,12 +3736,12 @@ static int dc395x_slave_alloc(struct scsi_device *scsi_device) /** - * dc395x_slave_destroy - Called by the scsi mid layer to tell us about a + * dc395x_sdev_destroy - Called by the scsi mid layer to tell us about a * device that is going away. * * @scsi_device: The new scsi device that we need to handle. **/ -static void dc395x_slave_destroy(struct scsi_device *scsi_device) +static void dc395x_sdev_destroy(struct scsi_device *scsi_device) { struct AdapterCtlBlk *acb = (struct AdapterCtlBlk *)scsi_device->host->hostdata; struct DeviceCtlBlk *dcb = find_dcb(acb, scsi_device->id, scsi_device->lun); @@ -4547,8 +4547,8 @@ static const struct scsi_host_template dc395x_driver_template = { .show_info = dc395x_show_info, .name = DC395X_BANNER " " DC395X_VERSION, .queuecommand = dc395x_queue_command, - .slave_alloc = dc395x_slave_alloc, - .slave_destroy = dc395x_slave_destroy, + .sdev_init = dc395x_sdev_init, + .sdev_destroy = dc395x_sdev_destroy, .can_queue = DC395x_MAX_CAN_QUEUE, .this_id = 7, .sg_tablesize = DC395x_MAX_SG_TABLESIZE, @@ -4668,7 +4668,7 @@ static void dc395x_remove_one(struct pci_dev *dev) } -static struct pci_device_id dc395x_pci_table[] = { +static const struct pci_device_id dc395x_pci_table[] = { { .vendor = PCI_VENDOR_ID_TEKRAM, .device = PCI_DEVICE_ID_TEKRAM_TRMS1040, diff --git a/drivers/scsi/dmx3191d.c b/drivers/scsi/dmx3191d.c index dfb091d34363..d6d091b2f3c7 100644 --- a/drivers/scsi/dmx3191d.c +++ b/drivers/scsi/dmx3191d.c @@ -127,7 +127,7 @@ static void dmx3191d_remove_one(struct pci_dev *pdev) pci_disable_device(pdev); } -static struct pci_device_id dmx3191d_pci_tbl[] = { +static const struct pci_device_id dmx3191d_pci_tbl[] = { {PCI_VENDOR_ID_DOMEX, PCI_DEVICE_ID_DOMEX_DMX3191D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 4}, { } diff --git a/drivers/scsi/elx/efct/efct_driver.c b/drivers/scsi/elx/efct/efct_driver.c index 55d2301bfd7d..8469c156ab33 100644 --- a/drivers/scsi/elx/efct/efct_driver.c +++ b/drivers/scsi/elx/efct/efct_driver.c @@ -470,7 +470,7 @@ out: return rc; } -static struct pci_device_id efct_pci_table[] = { +static const struct pci_device_id efct_pci_table[] = { {PCI_DEVICE(EFCT_VENDOR_ID, EFCT_DEVICE_LANCER_G6), 0}, {PCI_DEVICE(EFCT_VENDOR_ID, EFCT_DEVICE_LANCER_G7), 0}, {} /* terminate list */ diff --git a/drivers/scsi/esas2r/esas2r.h b/drivers/scsi/esas2r/esas2r.h index 1e2d7c63a8e3..c48275d53aef 100644 --- a/drivers/scsi/esas2r/esas2r.h +++ b/drivers/scsi/esas2r/esas2r.h @@ -1411,11 +1411,11 @@ static inline void esas2r_comp_list_drain(struct esas2r_adapter *a, } /* sysfs handlers */ -extern struct bin_attribute bin_attr_fw; -extern struct bin_attribute bin_attr_fs; -extern struct bin_attribute bin_attr_vda; -extern struct bin_attribute bin_attr_hw; -extern struct bin_attribute bin_attr_live_nvram; -extern struct bin_attribute bin_attr_default_nvram; +extern const struct bin_attribute bin_attr_fw; +extern const struct bin_attribute bin_attr_fs; +extern const struct bin_attribute bin_attr_vda; +extern const struct bin_attribute bin_attr_hw; +extern const struct bin_attribute bin_attr_live_nvram; +extern const struct bin_attribute bin_attr_default_nvram; #endif /* ESAS2R_H */ diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c index f700a16cd885..44871746944a 100644 --- a/drivers/scsi/esas2r/esas2r_main.c +++ b/drivers/scsi/esas2r/esas2r_main.c @@ -66,7 +66,7 @@ static struct esas2r_adapter *esas2r_adapter_from_kobj(struct kobject *kobj) } static ssize_t read_fw(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -75,7 +75,7 @@ static ssize_t read_fw(struct file *file, struct kobject *kobj, } static ssize_t write_fw(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -84,7 +84,7 @@ static ssize_t write_fw(struct file *file, struct kobject *kobj, } static ssize_t read_fs(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -93,7 +93,7 @@ static ssize_t read_fs(struct file *file, struct kobject *kobj, } static ssize_t write_fs(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -109,7 +109,7 @@ static ssize_t write_fs(struct file *file, struct kobject *kobj, } static ssize_t read_vda(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -118,7 +118,7 @@ static ssize_t read_vda(struct file *file, struct kobject *kobj, } static ssize_t write_vda(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -127,7 +127,7 @@ static ssize_t write_vda(struct file *file, struct kobject *kobj, } static ssize_t read_live_nvram(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -138,7 +138,7 @@ static ssize_t read_live_nvram(struct file *file, struct kobject *kobj, } static ssize_t write_live_nvram(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -158,7 +158,7 @@ static ssize_t write_live_nvram(struct file *file, struct kobject *kobj, } static ssize_t read_default_nvram(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -169,7 +169,7 @@ static ssize_t read_default_nvram(struct file *file, struct kobject *kobj, } static ssize_t read_hw(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -187,7 +187,7 @@ static ssize_t read_hw(struct file *file, struct kobject *kobj, } static ssize_t write_hw(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj); @@ -211,12 +211,12 @@ static ssize_t write_hw(struct file *file, struct kobject *kobj, } #define ESAS2R_RW_BIN_ATTR(_name) \ - struct bin_attribute bin_attr_ ## _name = { \ + const struct bin_attribute bin_attr_ ## _name = { \ .attr = \ { .name = __stringify(_name), .mode = S_IRUSR | S_IWUSR }, \ .size = 0, \ - .read = read_ ## _name, \ - .write = write_ ## _name } + .read_new = read_ ## _name, \ + .write_new = write_ ## _name } ESAS2R_RW_BIN_ATTR(fw); ESAS2R_RW_BIN_ATTR(fs); @@ -224,10 +224,10 @@ ESAS2R_RW_BIN_ATTR(vda); ESAS2R_RW_BIN_ATTR(hw); ESAS2R_RW_BIN_ATTR(live_nvram); -struct bin_attribute bin_attr_default_nvram = { +const struct bin_attribute bin_attr_default_nvram = { .attr = { .name = "default_nvram", .mode = S_IRUGO }, .size = 0, - .read = read_default_nvram, + .read_new = read_default_nvram, .write = NULL }; diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c index 0175d2282b45..802718ffad84 100644 --- a/drivers/scsi/esp_scsi.c +++ b/drivers/scsi/esp_scsi.c @@ -2261,7 +2261,7 @@ static void esp_init_swstate(struct esp *esp) INIT_LIST_HEAD(&esp->active_cmds); INIT_LIST_HEAD(&esp->esp_cmd_pool); - /* Start with a clear state, domain validation (via ->slave_configure, + /* Start with a clear state, domain validation (via ->sdev_configure, * spi_dv_device()) will attempt to enable SYNC, WIDE, and tagged * commands. */ @@ -2441,7 +2441,7 @@ static void esp_target_destroy(struct scsi_target *starget) tp->starget = NULL; } -static int esp_slave_alloc(struct scsi_device *dev) +static int esp_sdev_init(struct scsi_device *dev) { struct esp *esp = shost_priv(dev->host); struct esp_target_data *tp = &esp->target[dev->id]; @@ -2463,7 +2463,7 @@ static int esp_slave_alloc(struct scsi_device *dev) return 0; } -static int esp_slave_configure(struct scsi_device *dev) +static int esp_sdev_configure(struct scsi_device *dev, struct queue_limits *lim) { struct esp *esp = shost_priv(dev->host); struct esp_target_data *tp = &esp->target[dev->id]; @@ -2479,7 +2479,7 @@ static int esp_slave_configure(struct scsi_device *dev) return 0; } -static void esp_slave_destroy(struct scsi_device *dev) +static void esp_sdev_destroy(struct scsi_device *dev) { struct esp_lun_data *lp = dev->hostdata; @@ -2667,9 +2667,9 @@ const struct scsi_host_template scsi_esp_template = { .queuecommand = esp_queuecommand, .target_alloc = esp_target_alloc, .target_destroy = esp_target_destroy, - .slave_alloc = esp_slave_alloc, - .slave_configure = esp_slave_configure, - .slave_destroy = esp_slave_destroy, + .sdev_init = esp_sdev_init, + .sdev_configure = esp_sdev_configure, + .sdev_destroy = esp_sdev_destroy, .eh_abort_handler = esp_eh_abort_handler, .eh_bus_reset_handler = esp_eh_bus_reset_handler, .eh_host_reset_handler = esp_eh_host_reset_handler, diff --git a/drivers/scsi/esp_scsi.h b/drivers/scsi/esp_scsi.h index 00cd7c0ccc76..7bb0b69bff24 100644 --- a/drivers/scsi/esp_scsi.h +++ b/drivers/scsi/esp_scsi.h @@ -80,7 +80,7 @@ /* ESP config register 4 read-write */ #define ESP_CONFIG4_BBTE 0x01 /* Back-to-back transfers (fsc) */ -#define ESP_CONGIG4_TEST 0x02 /* Transfer counter test mode (fsc) */ +#define ESP_CONFIG4_TEST 0x02 /* Transfer counter test mode (fsc) */ #define ESP_CONFIG4_RADE 0x04 /* Active negation (am53c974/fsc) */ #define ESP_CONFIG4_RAE 0x08 /* Act. negation REQ/ACK (am53c974) */ #define ESP_CONFIG4_PWD 0x20 /* Reduced power feature (am53c974) */ diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 39aec710660c..038e38578676 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -269,7 +269,7 @@ static const struct scsi_host_template fcoe_shost_template = { .eh_abort_handler = fc_eh_abort, .eh_device_reset_handler = fc_eh_device_reset, .eh_host_reset_handler = fc_eh_host_reset, - .slave_alloc = fc_slave_alloc, + .sdev_init = fc_sdev_init, .change_queue_depth = scsi_change_queue_depth, .this_id = -1, .cmd_per_lun = 3, diff --git a/drivers/scsi/fdomain_pci.c b/drivers/scsi/fdomain_pci.c index 3e05ce7b89e5..c15b2ce76e9f 100644 --- a/drivers/scsi/fdomain_pci.c +++ b/drivers/scsi/fdomain_pci.c @@ -47,7 +47,7 @@ static void fdomain_pci_remove(struct pci_dev *pdev) pci_disable_device(pdev); } -static struct pci_device_id fdomain_pci_table[] = { +static const struct pci_device_id fdomain_pci_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_FD, PCI_DEVICE_ID_FD_36C70) }, {} }; diff --git a/drivers/scsi/fnic/Makefile b/drivers/scsi/fnic/Makefile index 6214a6b2e96d..c025e875009e 100644 --- a/drivers/scsi/fnic/Makefile +++ b/drivers/scsi/fnic/Makefile @@ -2,11 +2,13 @@ obj-$(CONFIG_FCOE_FNIC) += fnic.o fnic-y := \ + fip.o\ fnic_attrs.o \ fnic_isr.o \ fnic_main.o \ fnic_res.o \ fnic_fcs.o \ + fdls_disc.o \ fnic_scsi.o \ fnic_trace.o \ fnic_debugfs.o \ @@ -15,4 +17,5 @@ fnic-y := \ vnic_intr.o \ vnic_rq.o \ vnic_wq_copy.o \ - vnic_wq.o + vnic_wq.o \ + fnic_pci_subsys_devid.o diff --git a/drivers/scsi/fnic/fdls_disc.c b/drivers/scsi/fnic/fdls_disc.c new file mode 100644 index 000000000000..11211c469583 --- /dev/null +++ b/drivers/scsi/fnic/fdls_disc.c @@ -0,0 +1,4997 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2008 Cisco Systems, Inc. All rights reserved. + * Copyright 2007 Nuova Systems, Inc. All rights reserved. + */ + +#include +#include "fnic.h" +#include "fdls_fc.h" +#include "fnic_fdls.h" +#include +#include +#include + +#define FC_FC4_TYPE_SCSI 0x08 +#define PORT_SPEED_BIT_8 8 +#define PORT_SPEED_BIT_9 9 +#define PORT_SPEED_BIT_14 14 +#define PORT_SPEED_BIT_15 15 + +/* FNIC FDMI Register HBA Macros */ +#define FNIC_FDMI_NUM_PORTS 1 +#define FNIC_FDMI_NUM_HBA_ATTRS 9 +#define FNIC_FDMI_TYPE_NODE_NAME 0X1 +#define FNIC_FDMI_TYPE_MANUFACTURER 0X2 +#define FNIC_FDMI_MANUFACTURER "Cisco Systems" +#define FNIC_FDMI_TYPE_SERIAL_NUMBER 0X3 +#define FNIC_FDMI_TYPE_MODEL 0X4 +#define FNIC_FDMI_TYPE_MODEL_DES 0X5 +#define FNIC_FDMI_MODEL_DESCRIPTION "Cisco Virtual Interface Card" +#define FNIC_FDMI_TYPE_HARDWARE_VERSION 0X6 +#define FNIC_FDMI_TYPE_DRIVER_VERSION 0X7 +#define FNIC_FDMI_TYPE_ROM_VERSION 0X8 +#define FNIC_FDMI_TYPE_FIRMWARE_VERSION 0X9 +#define FNIC_FDMI_NN_LEN 8 +#define FNIC_FDMI_MANU_LEN 20 +#define FNIC_FDMI_SERIAL_LEN 16 +#define FNIC_FDMI_MODEL_LEN 12 +#define FNIC_FDMI_MODEL_DES_LEN 56 +#define FNIC_FDMI_HW_VER_LEN 16 +#define FNIC_FDMI_DR_VER_LEN 28 +#define FNIC_FDMI_ROM_VER_LEN 8 +#define FNIC_FDMI_FW_VER_LEN 16 + +/* FNIC FDMI Register PA Macros */ +#define FNIC_FDMI_TYPE_FC4_TYPES 0X1 +#define FNIC_FDMI_TYPE_SUPPORTED_SPEEDS 0X2 +#define FNIC_FDMI_TYPE_CURRENT_SPEED 0X3 +#define FNIC_FDMI_TYPE_MAX_FRAME_SIZE 0X4 +#define FNIC_FDMI_TYPE_OS_NAME 0X5 +#define FNIC_FDMI_TYPE_HOST_NAME 0X6 +#define FNIC_FDMI_NUM_PORT_ATTRS 6 +#define FNIC_FDMI_FC4_LEN 32 +#define FNIC_FDMI_SUPP_SPEED_LEN 4 +#define FNIC_FDMI_CUR_SPEED_LEN 4 +#define FNIC_FDMI_MFS_LEN 4 +#define FNIC_FDMI_MFS 0x800 +#define FNIC_FDMI_OS_NAME_LEN 16 +#define FNIC_FDMI_HN_LEN 24 + +#define FDLS_FDMI_PLOGI_PENDING 0x1 +#define FDLS_FDMI_REG_HBA_PENDING 0x2 +#define FDLS_FDMI_RPA_PENDING 0x4 +#define FDLS_FDMI_ABORT_PENDING 0x8 +#define FDLS_FDMI_MAX_RETRY 3 + +#define RETRIES_EXHAUSTED(iport) \ + (iport->fabric.retry_counter == FABRIC_LOGO_MAX_RETRY) + +#define FNIC_TPORT_MAX_NEXUS_RESTART (8) + +#define SCHEDULE_OXID_FREE_RETRY_TIME (300) + +/* Private Functions */ +static void fdls_fdmi_register_hba(struct fnic_iport_s *iport); +static void fdls_fdmi_register_pa(struct fnic_iport_s *iport); +static void fdls_send_rpn_id(struct fnic_iport_s *iport); +static void fdls_process_flogi_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr, + void *rx_frame); +static void fnic_fdls_start_plogi(struct fnic_iport_s *iport); +static void fnic_fdls_start_flogi(struct fnic_iport_s *iport); +static struct fnic_tport_s *fdls_create_tport(struct fnic_iport_s *iport, + uint32_t fcid, + uint64_t wwpn); +static void fdls_target_restart_nexus(struct fnic_tport_s *tport); +static void fdls_start_tport_timer(struct fnic_iport_s *iport, + struct fnic_tport_s *tport, int timeout); +static void fdls_tport_timer_callback(struct timer_list *t); +static void fdls_send_fdmi_plogi(struct fnic_iport_s *iport); +static void fdls_start_fabric_timer(struct fnic_iport_s *iport, + int timeout); +static void fdls_init_plogi_frame(uint8_t *frame, struct fnic_iport_s *iport); +static void fdls_init_els_acc_frame(uint8_t *frame, struct fnic_iport_s *iport); +static void fdls_init_els_rjt_frame(uint8_t *frame, struct fnic_iport_s *iport); +static void fdls_init_logo_frame(uint8_t *frame, struct fnic_iport_s *iport); +static void fdls_init_fabric_abts_frame(uint8_t *frame, + struct fnic_iport_s *iport); + +uint8_t *fdls_alloc_frame(struct fnic_iport_s *iport) +{ + struct fnic *fnic = iport->fnic; + uint8_t *frame = NULL; + + frame = mempool_alloc(fnic->frame_pool, GFP_ATOMIC); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame"); + return NULL; + } + + memset(frame, 0, FNIC_FCOE_FRAME_MAXSZ); + return frame; +} + +/** + * fdls_alloc_oxid - Allocate an oxid from the bitmap based oxid pool + * @iport: Handle to iport instance + * @oxid_frame_type: Type of frame to allocate + * @active_oxid: the oxid which is in use + * + * Called with fnic lock held + */ +uint16_t fdls_alloc_oxid(struct fnic_iport_s *iport, int oxid_frame_type, + uint16_t *active_oxid) +{ + struct fnic *fnic = iport->fnic; + struct fnic_oxid_pool_s *oxid_pool = &iport->oxid_pool; + int idx; + uint16_t oxid; + + lockdep_assert_held(&fnic->fnic_lock); + + /* + * Allocate next available oxid from bitmap + */ + idx = find_next_zero_bit(oxid_pool->bitmap, FNIC_OXID_POOL_SZ, oxid_pool->next_idx); + if (idx == FNIC_OXID_POOL_SZ) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Alloc oxid: all oxid slots are busy iport state:%d\n", + iport->state); + return FNIC_UNASSIGNED_OXID; + } + + WARN_ON(test_and_set_bit(idx, oxid_pool->bitmap)); + oxid_pool->next_idx = (idx + 1) % FNIC_OXID_POOL_SZ; /* cycle through the bitmap */ + + oxid = FNIC_OXID_ENCODE(idx, oxid_frame_type); + *active_oxid = oxid; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "alloc oxid: 0x%x, iport state: %d\n", + oxid, iport->state); + return oxid; +} + +/** + * fdls_free_oxid_idx - Free the oxid using the idx + * @iport: Handle to iport instance + * @oxid_idx: The index to free + * + * Free the oxid immediately and make it available for new requests + * Called with fnic lock held + */ +static void fdls_free_oxid_idx(struct fnic_iport_s *iport, uint16_t oxid_idx) +{ + struct fnic *fnic = iport->fnic; + struct fnic_oxid_pool_s *oxid_pool = &iport->oxid_pool; + + lockdep_assert_held(&fnic->fnic_lock); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "free oxid idx: 0x%x\n", oxid_idx); + + WARN_ON(!test_and_clear_bit(oxid_idx, oxid_pool->bitmap)); +} + +/** + * fdls_reclaim_oxid_handler - Callback handler for delayed_oxid_work + * @work: Handle to work_struct + * + * Scheduled when an oxid is to be freed later + * After freeing expired oxid(s), the handler schedules + * another callback with the remaining time + * of next unexpired entry in the reclaim list. + */ +void fdls_reclaim_oxid_handler(struct work_struct *work) +{ + struct fnic_oxid_pool_s *oxid_pool = container_of(work, + struct fnic_oxid_pool_s, oxid_reclaim_work.work); + struct fnic_iport_s *iport = container_of(oxid_pool, + struct fnic_iport_s, oxid_pool); + struct fnic *fnic = iport->fnic; + struct reclaim_entry_s *reclaim_entry, *next; + unsigned long delay_j, cur_jiffies; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Reclaim oxid callback\n"); + + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + + /* Though the work was scheduled for one entry, + * walk through and free the expired entries which might have been scheduled + * at around the same time as the first entry + */ + list_for_each_entry_safe(reclaim_entry, next, + &(oxid_pool->oxid_reclaim_list), links) { + + /* The list is always maintained in the order of expiry time */ + cur_jiffies = jiffies; + if (time_before(cur_jiffies, reclaim_entry->expires)) + break; + + list_del(&reclaim_entry->links); + fdls_free_oxid_idx(iport, reclaim_entry->oxid_idx); + kfree(reclaim_entry); + } + + /* schedule to free up the next entry */ + if (!list_empty(&oxid_pool->oxid_reclaim_list)) { + reclaim_entry = list_first_entry(&oxid_pool->oxid_reclaim_list, + struct reclaim_entry_s, links); + + delay_j = reclaim_entry->expires - cur_jiffies; + schedule_delayed_work(&oxid_pool->oxid_reclaim_work, delay_j); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Scheduling next callback at:%ld jiffies\n", delay_j); + } + + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); +} + +/** + * fdls_free_oxid - Helper function to free the oxid + * @iport: Handle to iport instance + * @oxid: oxid to free + * @active_oxid: the oxid which is in use + * + * Called with fnic lock held + */ +void fdls_free_oxid(struct fnic_iport_s *iport, + uint16_t oxid, uint16_t *active_oxid) +{ + fdls_free_oxid_idx(iport, FNIC_OXID_IDX(oxid)); + *active_oxid = FNIC_UNASSIGNED_OXID; +} + +/** + * fdls_schedule_oxid_free - Schedule oxid to be freed later + * @iport: Handle to iport instance + * @active_oxid: the oxid which is in use + * + * Gets called in a rare case scenario when both a command + * (fdls or target discovery) timed out and the following ABTS + * timed out as well, without a link change. + * + * Called with fnic lock held + */ +void fdls_schedule_oxid_free(struct fnic_iport_s *iport, uint16_t *active_oxid) +{ + struct fnic *fnic = iport->fnic; + struct fnic_oxid_pool_s *oxid_pool = &iport->oxid_pool; + struct reclaim_entry_s *reclaim_entry; + unsigned long delay_j = msecs_to_jiffies(OXID_RECLAIM_TOV(iport)); + int oxid_idx = FNIC_OXID_IDX(*active_oxid); + + lockdep_assert_held(&fnic->fnic_lock); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Schedule oxid free. oxid: 0x%x\n", *active_oxid); + + *active_oxid = FNIC_UNASSIGNED_OXID; + + reclaim_entry = (struct reclaim_entry_s *) + kzalloc(sizeof(struct reclaim_entry_s), GFP_ATOMIC); + + if (!reclaim_entry) { + FNIC_FCS_DBG(KERN_WARNING, fnic->host, fnic->fnic_num, + "Failed to allocate memory for reclaim struct for oxid idx: %d\n", + oxid_idx); + + /* Retry the scheduling */ + WARN_ON(test_and_set_bit(oxid_idx, oxid_pool->pending_schedule_free)); + schedule_delayed_work(&oxid_pool->schedule_oxid_free_retry, 0); + return; + } + + reclaim_entry->oxid_idx = oxid_idx; + reclaim_entry->expires = round_jiffies(jiffies + delay_j); + + list_add_tail(&reclaim_entry->links, &oxid_pool->oxid_reclaim_list); + + schedule_delayed_work(&oxid_pool->oxid_reclaim_work, delay_j); +} + +/** + * fdls_schedule_oxid_free_retry_work - Thread to schedule the + * oxid to be freed later + * + * @work: Handle to the work struct + */ +void fdls_schedule_oxid_free_retry_work(struct work_struct *work) +{ + struct fnic_oxid_pool_s *oxid_pool = container_of(work, + struct fnic_oxid_pool_s, schedule_oxid_free_retry.work); + struct fnic_iport_s *iport = container_of(oxid_pool, + struct fnic_iport_s, oxid_pool); + struct fnic *fnic = iport->fnic; + struct reclaim_entry_s *reclaim_entry; + unsigned long delay_j = msecs_to_jiffies(OXID_RECLAIM_TOV(iport)); + int idx; + + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + + for_each_set_bit(idx, oxid_pool->pending_schedule_free, FNIC_OXID_POOL_SZ) { + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Schedule oxid free. oxid idx: %d\n", idx); + + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + reclaim_entry = (struct reclaim_entry_s *) + kzalloc(sizeof(struct reclaim_entry_s), GFP_KERNEL); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + + if (!reclaim_entry) { + FNIC_FCS_DBG(KERN_WARNING, fnic->host, fnic->fnic_num, + "Failed to allocate memory for reclaim struct for oxid idx: 0x%x\n", + idx); + + schedule_delayed_work(&oxid_pool->schedule_oxid_free_retry, + msecs_to_jiffies(SCHEDULE_OXID_FREE_RETRY_TIME)); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + return; + } + + if (test_and_clear_bit(idx, oxid_pool->pending_schedule_free)) { + reclaim_entry->oxid_idx = idx; + reclaim_entry->expires = round_jiffies(jiffies + delay_j); + list_add_tail(&reclaim_entry->links, &oxid_pool->oxid_reclaim_list); + schedule_delayed_work(&oxid_pool->oxid_reclaim_work, delay_j); + } else { + /* unlikely scenario, free the allocated memory and continue */ + kfree(reclaim_entry); + } +} + + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); +} + +static bool fdls_is_oxid_fabric_req(uint16_t oxid) +{ + int oxid_frame_type = FNIC_FRAME_TYPE(oxid); + + switch (oxid_frame_type) { + case FNIC_FRAME_TYPE_FABRIC_FLOGI: + case FNIC_FRAME_TYPE_FABRIC_PLOGI: + case FNIC_FRAME_TYPE_FABRIC_RPN: + case FNIC_FRAME_TYPE_FABRIC_RFT: + case FNIC_FRAME_TYPE_FABRIC_RFF: + case FNIC_FRAME_TYPE_FABRIC_GPN_FT: + case FNIC_FRAME_TYPE_FABRIC_LOGO: + break; + default: + return false; + } + return true; +} + +static bool fdls_is_oxid_fdmi_req(uint16_t oxid) +{ + int oxid_frame_type = FNIC_FRAME_TYPE(oxid); + + switch (oxid_frame_type) { + case FNIC_FRAME_TYPE_FDMI_PLOGI: + case FNIC_FRAME_TYPE_FDMI_RHBA: + case FNIC_FRAME_TYPE_FDMI_RPA: + break; + default: + return false; + } + return true; +} + +static bool fdls_is_oxid_tgt_req(uint16_t oxid) +{ + int oxid_frame_type = FNIC_FRAME_TYPE(oxid); + + switch (oxid_frame_type) { + case FNIC_FRAME_TYPE_TGT_PLOGI: + case FNIC_FRAME_TYPE_TGT_PRLI: + case FNIC_FRAME_TYPE_TGT_ADISC: + case FNIC_FRAME_TYPE_TGT_LOGO: + break; + default: + return false; + } + return true; +} + +static void fdls_reset_oxid_pool(struct fnic_iport_s *iport) +{ + struct fnic_oxid_pool_s *oxid_pool = &iport->oxid_pool; + + oxid_pool->next_idx = 0; +} + +void fnic_del_fabric_timer_sync(struct fnic *fnic) +{ + fnic->iport.fabric.del_timer_inprogress = 1; + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + del_timer_sync(&fnic->iport.fabric.retry_timer); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + fnic->iport.fabric.del_timer_inprogress = 0; +} + +void fnic_del_tport_timer_sync(struct fnic *fnic, + struct fnic_tport_s *tport) +{ + tport->del_timer_inprogress = 1; + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + del_timer_sync(&tport->retry_timer); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + tport->del_timer_inprogress = 0; +} + +static void +fdls_start_fabric_timer(struct fnic_iport_s *iport, int timeout) +{ + u64 fabric_tov; + struct fnic *fnic = iport->fnic; + + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport fcid: 0x%x: Canceling fabric disc timer\n", + iport->fcid); + fnic_del_fabric_timer_sync(fnic); + iport->fabric.timer_pending = 0; + } + + if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) + iport->fabric.retry_counter++; + + fabric_tov = jiffies + msecs_to_jiffies(timeout); + mod_timer(&iport->fabric.retry_timer, round_jiffies(fabric_tov)); + iport->fabric.timer_pending = 1; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fabric timer is %d ", timeout); +} + +static void +fdls_start_tport_timer(struct fnic_iport_s *iport, + struct fnic_tport_s *tport, int timeout) +{ + u64 fabric_tov; + struct fnic *fnic = iport->fnic; + + if (tport->timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport fcid 0x%x: Canceling disc timer\n", + tport->fcid); + fnic_del_tport_timer_sync(fnic, tport); + tport->timer_pending = 0; + } + + if (!(tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) + tport->retry_counter++; + + fabric_tov = jiffies + msecs_to_jiffies(timeout); + mod_timer(&tport->retry_timer, round_jiffies(fabric_tov)); + tport->timer_pending = 1; +} + +void fdls_init_plogi_frame(uint8_t *frame, + struct fnic_iport_s *iport) +{ + struct fc_std_flogi *pplogi; + uint8_t s_id[3]; + + pplogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *pplogi = (struct fc_std_flogi) { + .fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ, .fh_d_id = {0xFF, 0xFF, 0xFC}, + .fh_type = FC_TYPE_ELS, .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)}, + .els = { + .fl_cmd = ELS_PLOGI, + .fl_csp = {.sp_hi_ver = FNIC_FC_PH_VER_HI, + .sp_lo_ver = FNIC_FC_PH_VER_LO, + .sp_bb_cred = cpu_to_be16(FNIC_FC_B2B_CREDIT), + .sp_features = cpu_to_be16(FC_SP_FT_CIRO), + .sp_bb_data = cpu_to_be16(FNIC_FC_B2B_RDF_SZ), + .sp_tot_seq = cpu_to_be16(FNIC_FC_CONCUR_SEQS), + .sp_rel_off = cpu_to_be16(FNIC_FC_RO_INFO), + .sp_e_d_tov = cpu_to_be32(FC_DEF_E_D_TOV)}, + .fl_cssp[2].cp_class = cpu_to_be16(FC_CPC_VALID | FC_CPC_SEQ), + .fl_cssp[2].cp_rdfs = cpu_to_be16(0x800), + .fl_cssp[2].cp_con_seq = cpu_to_be16(0xFF), + .fl_cssp[2].cp_open_seq = 1} + }; + + FNIC_STD_SET_NPORT_NAME(&pplogi->els.fl_wwpn, iport->wwpn); + FNIC_STD_SET_NODE_NAME(&pplogi->els.fl_wwnn, iport->wwnn); + FNIC_LOGI_SET_RDF_SIZE(pplogi->els, iport->max_payload_size); + + hton24(s_id, iport->fcid); + FNIC_STD_SET_S_ID(pplogi->fchdr, s_id); +} + +static void fdls_init_els_acc_frame(uint8_t *frame, + struct fnic_iport_s *iport) +{ + struct fc_std_els_acc_rsp *pels_acc; + uint8_t s_id[3]; + + pels_acc = (struct fc_std_els_acc_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *pels_acc = (struct fc_std_els_acc_rsp) { + .fchdr = {.fh_r_ctl = FC_RCTL_ELS_REP, + .fh_type = FC_TYPE_ELS, .fh_f_ctl = {FNIC_ELS_REP_FCTL, 0, 0}}, + .acc.la_cmd = ELS_LS_ACC, + }; + + hton24(s_id, iport->fcid); + FNIC_STD_SET_S_ID(pels_acc->fchdr, s_id); + FNIC_STD_SET_RX_ID(pels_acc->fchdr, FNIC_UNASSIGNED_RXID); +} + +static void fdls_init_els_rjt_frame(uint8_t *frame, + struct fnic_iport_s *iport) +{ + struct fc_std_els_rjt_rsp *pels_rjt; + + pels_rjt = (struct fc_std_els_rjt_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *pels_rjt = (struct fc_std_els_rjt_rsp) { + .fchdr = {.fh_r_ctl = FC_RCTL_ELS_REP, .fh_type = FC_TYPE_ELS, + .fh_f_ctl = {FNIC_ELS_REP_FCTL, 0, 0}}, + .rej.er_cmd = ELS_LS_RJT, + }; + + FNIC_STD_SET_RX_ID(pels_rjt->fchdr, FNIC_UNASSIGNED_RXID); +} + +static void fdls_init_logo_frame(uint8_t *frame, + struct fnic_iport_s *iport) +{ + struct fc_std_logo *plogo; + uint8_t s_id[3]; + + plogo = (struct fc_std_logo *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *plogo = (struct fc_std_logo) { + .fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ, .fh_type = FC_TYPE_ELS, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}}, + .els.fl_cmd = ELS_LOGO, + }; + + hton24(s_id, iport->fcid); + FNIC_STD_SET_S_ID(plogo->fchdr, s_id); + memcpy(plogo->els.fl_n_port_id, s_id, 3); + + FNIC_STD_SET_NPORT_NAME(&plogo->els.fl_n_port_wwn, + iport->wwpn); +} + +static void fdls_init_fabric_abts_frame(uint8_t *frame, + struct fnic_iport_s *iport) +{ + struct fc_frame_header *pfabric_abts; + + pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *pfabric_abts = (struct fc_frame_header) { + .fh_r_ctl = FC_RCTL_BA_ABTS, /* ABTS */ + .fh_s_id = {0x00, 0x00, 0x00}, + .fh_cs_ctl = 0x00, .fh_type = FC_TYPE_BLS, + .fh_f_ctl = {FNIC_REQ_ABTS_FCTL, 0, 0}, .fh_seq_id = 0x00, + .fh_df_ctl = 0x00, .fh_seq_cnt = 0x0000, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID), + .fh_parm_offset = 0x00000000, /* bit:0 = 0 Abort a exchange */ + }; +} + +static void +fdls_send_rscn_resp(struct fnic_iport_s *iport, + struct fc_frame_header *rscn_fchdr) +{ + uint8_t *frame; + struct fc_std_els_acc_rsp *pels_acc; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_els_acc_rsp); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send RSCN response"); + return; + } + + pels_acc = (struct fc_std_els_acc_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_els_acc_frame(frame, iport); + + FNIC_STD_SET_D_ID(pels_acc->fchdr, rscn_fchdr->fh_s_id); + + oxid = FNIC_STD_GET_OX_ID(rscn_fchdr); + FNIC_STD_SET_OX_ID(pels_acc->fchdr, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send RSCN response with oxid: 0x%x", + iport->fcid, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); +} + +static void +fdls_send_logo_resp(struct fnic_iport_s *iport, + struct fc_frame_header *req_fchdr) +{ + uint8_t *frame; + struct fc_std_els_acc_rsp *plogo_resp; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_els_acc_rsp); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send LOGO response"); + return; + } + + plogo_resp = (struct fc_std_els_acc_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_els_acc_frame(frame, iport); + + FNIC_STD_SET_D_ID(plogo_resp->fchdr, req_fchdr->fh_s_id); + + oxid = FNIC_STD_GET_OX_ID(req_fchdr); + FNIC_STD_SET_OX_ID(plogo_resp->fchdr, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send LOGO response with oxid: 0x%x", + iport->fcid, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); +} + +void +fdls_send_tport_abts(struct fnic_iport_s *iport, + struct fnic_tport_s *tport) +{ + uint8_t *frame; + uint8_t s_id[3]; + uint8_t d_id[3]; + struct fnic *fnic = iport->fnic; + struct fc_frame_header *ptport_abts; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_frame_header); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send tport ABTS"); + return; + } + + ptport_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *ptport_abts = (struct fc_frame_header) { + .fh_r_ctl = FC_RCTL_BA_ABTS, /* ABTS */ + .fh_cs_ctl = 0x00, .fh_type = FC_TYPE_BLS, + .fh_f_ctl = {FNIC_REQ_ABTS_FCTL, 0, 0}, .fh_seq_id = 0x00, + .fh_df_ctl = 0x00, .fh_seq_cnt = 0x0000, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID), + .fh_parm_offset = 0x00000000, /* bit:0 = 0 Abort a exchange */ + }; + + hton24(s_id, iport->fcid); + hton24(d_id, tport->fcid); + FNIC_STD_SET_S_ID(*ptport_abts, s_id); + FNIC_STD_SET_D_ID(*ptport_abts, d_id); + tport->flags |= FNIC_FDLS_TGT_ABORT_ISSUED; + + FNIC_STD_SET_OX_ID(*ptport_abts, tport->active_oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send tport abts: tport->state: %d ", + iport->fcid, tport->state); + + fnic_send_fcoe_frame(iport, frame, frame_size); + + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_tport_timer(iport, tport, 2 * iport->e_d_tov); +} +static void fdls_send_fabric_abts(struct fnic_iport_s *iport) +{ + uint8_t *frame; + uint8_t s_id[3]; + uint8_t d_id[3]; + struct fnic *fnic = iport->fnic; + struct fc_frame_header *pfabric_abts; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_frame_header); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send fabric ABTS"); + return; + } + + pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_fabric_abts_frame(frame, iport); + + hton24(s_id, iport->fcid); + + switch (iport->fabric.state) { + case FDLS_STATE_FABRIC_LOGO: + hton24(d_id, FC_FID_FLOGI); + FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + break; + + case FDLS_STATE_FABRIC_FLOGI: + hton24(d_id, FC_FID_FLOGI); + FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + break; + + case FDLS_STATE_FABRIC_PLOGI: + FNIC_STD_SET_S_ID(*pfabric_abts, s_id); + hton24(d_id, FC_FID_DIR_SERV); + FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + break; + + case FDLS_STATE_RPN_ID: + FNIC_STD_SET_S_ID(*pfabric_abts, s_id); + hton24(d_id, FC_FID_DIR_SERV); + FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + break; + + case FDLS_STATE_SCR: + FNIC_STD_SET_S_ID(*pfabric_abts, s_id); + hton24(d_id, FC_FID_FCTRL); + FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + break; + + case FDLS_STATE_REGISTER_FC4_TYPES: + FNIC_STD_SET_S_ID(*pfabric_abts, s_id); + hton24(d_id, FC_FID_DIR_SERV); + FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + break; + + case FDLS_STATE_REGISTER_FC4_FEATURES: + FNIC_STD_SET_S_ID(*pfabric_abts, s_id); + hton24(d_id, FC_FID_DIR_SERV); + FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + break; + + case FDLS_STATE_GPN_FT: + FNIC_STD_SET_S_ID(*pfabric_abts, s_id); + hton24(d_id, FC_FID_DIR_SERV); + FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + break; + default: + return; + } + + oxid = iport->active_oxid_fabric_req; + FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send fabric abts. iport->fabric.state: %d oxid: 0x%x", + iport->fcid, iport->fabric.state, oxid); + + iport->fabric.flags |= FNIC_FDLS_FABRIC_ABORT_ISSUED; + + fnic_send_fcoe_frame(iport, frame, frame_size); + + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_fabric_timer(iport, 2 * iport->e_d_tov); + iport->fabric.timer_pending = 1; +} + +static void fdls_send_fdmi_abts(struct fnic_iport_s *iport) +{ + uint8_t *frame; + uint8_t d_id[3]; + struct fnic *fnic = iport->fnic; + struct fc_frame_header *pfabric_abts; + unsigned long fdmi_tov; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_frame_header); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send FDMI ABTS"); + return; + } + + pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_fabric_abts_frame(frame, iport); + + hton24(d_id, FC_FID_MGMT_SERV); + FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + + if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) { + oxid = iport->active_oxid_fdmi_plogi; + FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + fnic_send_fcoe_frame(iport, frame, frame_size); + } else { + if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) { + oxid = iport->active_oxid_fdmi_rhba; + FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + fnic_send_fcoe_frame(iport, frame, frame_size); + } + if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) { + oxid = iport->active_oxid_fdmi_rpa; + FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + fnic_send_fcoe_frame(iport, frame, frame_size); + } + } + + fdmi_tov = jiffies + msecs_to_jiffies(2 * iport->e_d_tov); + mod_timer(&iport->fabric.fdmi_timer, round_jiffies(fdmi_tov)); + iport->fabric.fdmi_pending |= FDLS_FDMI_ABORT_PENDING; +} + +static void fdls_send_fabric_flogi(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_flogi *pflogi; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_flogi); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send FLOGI"); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + + pflogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *pflogi = (struct fc_std_flogi) { + .fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ, .fh_d_id = {0xFF, 0xFF, 0xFE}, + .fh_type = FC_TYPE_ELS, .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)}, + .els.fl_cmd = ELS_FLOGI, + .els.fl_csp = {.sp_hi_ver = FNIC_FC_PH_VER_HI, + .sp_lo_ver = FNIC_FC_PH_VER_LO, + .sp_bb_cred = cpu_to_be16(FNIC_FC_B2B_CREDIT), + .sp_bb_data = cpu_to_be16(FNIC_FC_B2B_RDF_SZ)}, + .els.fl_cssp[2].cp_class = cpu_to_be16(FC_CPC_VALID | FC_CPC_SEQ) + }; + + FNIC_STD_SET_NPORT_NAME(&pflogi->els.fl_wwpn, iport->wwpn); + FNIC_STD_SET_NODE_NAME(&pflogi->els.fl_wwnn, iport->wwnn); + FNIC_LOGI_SET_RDF_SIZE(pflogi->els, iport->max_payload_size); + FNIC_LOGI_SET_R_A_TOV(pflogi->els, iport->r_a_tov); + FNIC_LOGI_SET_E_D_TOV(pflogi->els, iport->e_d_tov); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_FLOGI, + &iport->active_oxid_fabric_req); + + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send FLOGI", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + FNIC_STD_SET_OX_ID(pflogi->fchdr, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send fabric FLOGI with oxid: 0x%x", iport->fcid, + oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + atomic64_inc(&iport->iport_stats.fabric_flogi_sent); +err_out: + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_fabric_timer(iport, 2 * iport->e_d_tov); +} + +static void fdls_send_fabric_plogi(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_flogi *pplogi; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_flogi); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send PLOGI"); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + + pplogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_plogi_frame(frame, iport); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_PLOGI, + &iport->active_oxid_fabric_req); + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send fabric PLOGI", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + FNIC_STD_SET_OX_ID(pplogi->fchdr, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send fabric PLOGI with oxid: 0x%x", iport->fcid, + oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + atomic64_inc(&iport->iport_stats.fabric_plogi_sent); + +err_out: + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_fabric_timer(iport, 2 * iport->e_d_tov); +} + +static void fdls_send_fdmi_plogi(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_flogi *pplogi; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_flogi); + uint8_t d_id[3]; + u64 fdmi_tov; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send FDMI PLOGI"); + goto err_out; + } + + pplogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_plogi_frame(frame, iport); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FDMI_PLOGI, + &iport->active_oxid_fdmi_plogi); + + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send FDMI PLOGI", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + goto err_out; + } + FNIC_STD_SET_OX_ID(pplogi->fchdr, oxid); + + hton24(d_id, FC_FID_MGMT_SERV); + FNIC_STD_SET_D_ID(pplogi->fchdr, d_id); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send FDMI PLOGI with oxid: 0x%x", + iport->fcid, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + +err_out: + fdmi_tov = jiffies + msecs_to_jiffies(2 * iport->e_d_tov); + mod_timer(&iport->fabric.fdmi_timer, round_jiffies(fdmi_tov)); + iport->fabric.fdmi_pending = FDLS_FDMI_PLOGI_PENDING; +} + +static void fdls_send_rpn_id(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_rpn_id *prpn_id; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_rpn_id); + uint8_t fcid[3]; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send RPN_ID"); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + + prpn_id = (struct fc_std_rpn_id *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *prpn_id = (struct fc_std_rpn_id) { + .fchdr = {.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL, + .fh_d_id = {0xFF, 0xFF, 0xFC}, .fh_type = FC_TYPE_CT, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)}, + .fc_std_ct_hdr = {.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_DIR, + .ct_fs_subtype = FC_NS_SUBTYPE, + .ct_cmd = cpu_to_be16(FC_NS_RPN_ID)} + }; + + hton24(fcid, iport->fcid); + FNIC_STD_SET_S_ID(prpn_id->fchdr, fcid); + + FNIC_STD_SET_PORT_ID(prpn_id->rpn_id, fcid); + FNIC_STD_SET_PORT_NAME(prpn_id->rpn_id, iport->wwpn); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_RPN, + &iport->active_oxid_fabric_req); + + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send RPN_ID", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + FNIC_STD_SET_OX_ID(prpn_id->fchdr, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send RPN ID with oxid: 0x%x", iport->fcid, + oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + +err_out: + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_fabric_timer(iport, 2 * iport->e_d_tov); +} + +static void fdls_send_scr(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_scr *pscr; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_scr); + uint8_t fcid[3]; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send SCR"); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + + pscr = (struct fc_std_scr *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *pscr = (struct fc_std_scr) { + .fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ, + .fh_d_id = {0xFF, 0xFF, 0xFD}, .fh_type = FC_TYPE_ELS, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)}, + .scr = {.scr_cmd = ELS_SCR, + .scr_reg_func = ELS_SCRF_FULL} + }; + + hton24(fcid, iport->fcid); + FNIC_STD_SET_S_ID(pscr->fchdr, fcid); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_SCR, + &iport->active_oxid_fabric_req); + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send SCR", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + FNIC_STD_SET_OX_ID(pscr->fchdr, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send SCR with oxid: 0x%x", iport->fcid, + oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + atomic64_inc(&iport->iport_stats.fabric_scr_sent); + +err_out: + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_fabric_timer(iport, 2 * iport->e_d_tov); +} + +static void fdls_send_gpn_ft(struct fnic_iport_s *iport, int fdls_state) +{ + uint8_t *frame; + struct fc_std_gpn_ft *pgpn_ft; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_gpn_ft); + uint8_t fcid[3]; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send GPN FT"); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + + pgpn_ft = (struct fc_std_gpn_ft *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *pgpn_ft = (struct fc_std_gpn_ft) { + .fchdr = {.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL, + .fh_d_id = {0xFF, 0xFF, 0xFC}, .fh_type = FC_TYPE_CT, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)}, + .fc_std_ct_hdr = {.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_DIR, + .ct_fs_subtype = FC_NS_SUBTYPE, + .ct_cmd = cpu_to_be16(FC_NS_GPN_FT)}, + .gpn_ft.fn_fc4_type = 0x08 + }; + + hton24(fcid, iport->fcid); + FNIC_STD_SET_S_ID(pgpn_ft->fchdr, fcid); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_GPN_FT, + &iport->active_oxid_fabric_req); + + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send GPN FT", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + FNIC_STD_SET_OX_ID(pgpn_ft->fchdr, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send GPN FT with oxid: 0x%x", iport->fcid, + oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + +err_out: + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_fabric_timer(iport, 2 * iport->e_d_tov); + fdls_set_state((&iport->fabric), fdls_state); +} + +static void +fdls_send_tgt_adisc(struct fnic_iport_s *iport, struct fnic_tport_s *tport) +{ + uint8_t *frame; + struct fc_std_els_adisc *padisc; + uint8_t s_id[3]; + uint8_t d_id[3]; + uint16_t oxid; + struct fnic *fnic = iport->fnic; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_els_adisc); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send TGT ADISC"); + tport->flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + + padisc = (struct fc_std_els_adisc *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + + hton24(s_id, iport->fcid); + hton24(d_id, tport->fcid); + memcpy(padisc->els.adisc_port_id, s_id, 3); + FNIC_STD_SET_S_ID(padisc->fchdr, s_id); + FNIC_STD_SET_D_ID(padisc->fchdr, d_id); + + FNIC_STD_SET_F_CTL(padisc->fchdr, FNIC_ELS_REQ_FCTL << 16); + FNIC_STD_SET_R_CTL(padisc->fchdr, FC_RCTL_ELS_REQ); + FNIC_STD_SET_TYPE(padisc->fchdr, FC_TYPE_ELS); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_TGT_ADISC, &tport->active_oxid); + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send TGT ADISC", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + tport->flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + FNIC_STD_SET_OX_ID(padisc->fchdr, oxid); + FNIC_STD_SET_RX_ID(padisc->fchdr, FNIC_UNASSIGNED_RXID); + + tport->flags &= ~FNIC_FDLS_TGT_ABORT_ISSUED; + + FNIC_STD_SET_NPORT_NAME(&padisc->els.adisc_wwpn, + iport->wwpn); + FNIC_STD_SET_NODE_NAME(&padisc->els.adisc_wwnn, + iport->wwnn); + + padisc->els.adisc_cmd = ELS_ADISC; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send ADISC to tgt fcid: 0x%x", + iport->fcid, tport->fcid); + + atomic64_inc(&iport->iport_stats.tport_adisc_sent); + + fnic_send_fcoe_frame(iport, frame, frame_size); + +err_out: + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_tport_timer(iport, tport, 2 * iport->e_d_tov); +} + +bool fdls_delete_tport(struct fnic_iport_s *iport, struct fnic_tport_s *tport) +{ + struct fnic_tport_event_s *tport_del_evt; + struct fnic *fnic = iport->fnic; + + if ((tport->state == FDLS_TGT_STATE_OFFLINING) + || (tport->state == FDLS_TGT_STATE_OFFLINE)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport fcid 0x%x: tport state is offlining/offline\n", + tport->fcid); + return false; + } + + fdls_set_tport_state(tport, FDLS_TGT_STATE_OFFLINING); + /* + * By setting this flag, the tport will not be seen in a look-up + * in an RSCN. Even if we move to multithreaded model, this tport + * will be destroyed and a new RSCN will have to create a new one + */ + tport->flags |= FNIC_FDLS_TPORT_TERMINATING; + + if (tport->timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport fcid 0x%x: Canceling disc timer\n", + tport->fcid); + fnic_del_tport_timer_sync(fnic, tport); + tport->timer_pending = 0; + } + + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + fnic_rport_exch_reset(iport->fnic, tport->fcid); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + + if (tport->flags & FNIC_FDLS_SCSI_REGISTERED) { + tport_del_evt = + kzalloc(sizeof(struct fnic_tport_event_s), GFP_ATOMIC); + if (!tport_del_evt) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Failed to allocate memory for tport fcid: 0x%0x\n", + tport->fcid); + return false; + } + tport_del_evt->event = TGT_EV_RPORT_DEL; + tport_del_evt->arg1 = (void *) tport; + list_add_tail(&tport_del_evt->links, &fnic->tport_event_list); + queue_work(fnic_event_queue, &fnic->tport_work); + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport 0x%x not reg with scsi_transport. Freeing locally", + tport->fcid); + list_del(&tport->links); + kfree(tport); + } + return true; +} + +static void +fdls_send_tgt_plogi(struct fnic_iport_s *iport, struct fnic_tport_s *tport) +{ + uint8_t *frame; + struct fc_std_flogi *pplogi; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_flogi); + uint8_t d_id[3]; + uint32_t timeout; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send TGT PLOGI"); + tport->flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + + pplogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_plogi_frame(frame, iport); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_TGT_PLOGI, &tport->active_oxid); + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate oxid to send PLOGI to fcid: 0x%x", + iport->fcid, tport->fcid); + mempool_free(frame, fnic->frame_pool); + tport->flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + FNIC_STD_SET_OX_ID(pplogi->fchdr, oxid); + + tport->flags &= ~FNIC_FDLS_TGT_ABORT_ISSUED; + + hton24(d_id, tport->fcid); + FNIC_STD_SET_D_ID(pplogi->fchdr, d_id); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send tgt PLOGI to tgt: 0x%x with oxid: 0x%x", + iport->fcid, tport->fcid, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + atomic64_inc(&iport->iport_stats.tport_plogi_sent); + +err_out: + timeout = max(2 * iport->e_d_tov, iport->plogi_timeout); + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_tport_timer(iport, tport, timeout); +} + +static uint16_t +fnic_fc_plogi_rsp_rdf(struct fnic_iport_s *iport, + struct fc_std_flogi *plogi_rsp) +{ + uint16_t b2b_rdf_size = + be16_to_cpu(FNIC_LOGI_RDF_SIZE(plogi_rsp->els)); + uint16_t spc3_rdf_size = + be16_to_cpu(plogi_rsp->els.fl_cssp[2].cp_rdfs) & FNIC_FC_C3_RDF; + struct fnic *fnic = iport->fnic; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "MFS: b2b_rdf_size: 0x%x spc3_rdf_size: 0x%x", + b2b_rdf_size, spc3_rdf_size); + + return min(b2b_rdf_size, spc3_rdf_size); +} + +static void fdls_send_register_fc4_types(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_rft_id *prft_id; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_rft_id); + uint8_t fcid[3]; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send RFT"); + return; + } + + prft_id = (struct fc_std_rft_id *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *prft_id = (struct fc_std_rft_id) { + .fchdr = {.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL, + .fh_d_id = {0xFF, 0xFF, 0xFC}, .fh_type = FC_TYPE_CT, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)}, + .fc_std_ct_hdr = {.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_DIR, + .ct_fs_subtype = FC_NS_SUBTYPE, + .ct_cmd = cpu_to_be16(FC_NS_RFT_ID)} + }; + + hton24(fcid, iport->fcid); + FNIC_STD_SET_S_ID(prft_id->fchdr, fcid); + FNIC_STD_SET_PORT_ID(prft_id->rft_id, fcid); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_RFT, + &iport->active_oxid_fabric_req); + + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send RFT", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + return; + } + FNIC_STD_SET_OX_ID(prft_id->fchdr, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send RFT with oxid: 0x%x", iport->fcid, + oxid); + + prft_id->rft_id.fr_fts.ff_type_map[0] = + cpu_to_be32(1 << FC_TYPE_FCP); + + prft_id->rft_id.fr_fts.ff_type_map[1] = + cpu_to_be32(1 << (FC_TYPE_CT % FC_NS_BPW)); + + fnic_send_fcoe_frame(iport, frame, frame_size); + + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_fabric_timer(iport, 2 * iport->e_d_tov); +} + +static void fdls_send_register_fc4_features(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_rff_id *prff_id; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_rff_id); + uint8_t fcid[3]; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send RFF"); + return; + } + + prff_id = (struct fc_std_rff_id *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *prff_id = (struct fc_std_rff_id) { + .fchdr = {.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL, + .fh_d_id = {0xFF, 0xFF, 0xFC}, .fh_type = FC_TYPE_CT, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)}, + .fc_std_ct_hdr = {.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_DIR, + .ct_fs_subtype = FC_NS_SUBTYPE, + .ct_cmd = cpu_to_be16(FC_NS_RFF_ID)}, + .rff_id.fr_feat = 0x2, + .rff_id.fr_type = FC_TYPE_FCP + }; + + hton24(fcid, iport->fcid); + FNIC_STD_SET_S_ID(prff_id->fchdr, fcid); + FNIC_STD_SET_PORT_ID(prff_id->rff_id, fcid); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_RFF, + &iport->active_oxid_fabric_req); + + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send RFF", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + return; + } + FNIC_STD_SET_OX_ID(prff_id->fchdr, oxid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send RFF with oxid: 0x%x", iport->fcid, + oxid); + + prff_id->rff_id.fr_type = FC_TYPE_FCP; + + fnic_send_fcoe_frame(iport, frame, frame_size); + + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_fabric_timer(iport, 2 * iport->e_d_tov); +} + +static void +fdls_send_tgt_prli(struct fnic_iport_s *iport, struct fnic_tport_s *tport) +{ + uint8_t *frame; + struct fc_std_els_prli *pprli; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_els_prli); + uint8_t s_id[3]; + uint8_t d_id[3]; + uint32_t timeout; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send TGT PRLI"); + tport->flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + + pprli = (struct fc_std_els_prli *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *pprli = (struct fc_std_els_prli) { + .fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ, .fh_type = FC_TYPE_ELS, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)}, + .els_prli = {.prli_cmd = ELS_PRLI, + .prli_spp_len = 16, + .prli_len = cpu_to_be16(0x14)}, + .sp = {.spp_type = 0x08, .spp_flags = 0x0020, + .spp_params = cpu_to_be32(0xA2)} + }; + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_TGT_PRLI, &tport->active_oxid); + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send TGT PRLI to 0x%x", + iport->fcid, tport->fcid); + mempool_free(frame, fnic->frame_pool); + tport->flags |= FNIC_FDLS_RETRY_FRAME; + goto err_out; + } + + tport->flags &= ~FNIC_FDLS_TGT_ABORT_ISSUED; + + hton24(s_id, iport->fcid); + hton24(d_id, tport->fcid); + + FNIC_STD_SET_OX_ID(pprli->fchdr, oxid); + FNIC_STD_SET_S_ID(pprli->fchdr, s_id); + FNIC_STD_SET_D_ID(pprli->fchdr, d_id); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send PRLI to tgt: 0x%x with oxid: 0x%x", + iport->fcid, tport->fcid, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + atomic64_inc(&iport->iport_stats.tport_prli_sent); + +err_out: + timeout = max(2 * iport->e_d_tov, iport->plogi_timeout); + /* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */ + fdls_start_tport_timer(iport, tport, timeout); +} + +/** + * fdls_send_fabric_logo - Send flogo to the fcf + * @iport: Handle to fnic iport + * + * This function does not change or check the fabric state. + * It the caller's responsibility to set the appropriate iport fabric + * state when this is called. Normally it is FDLS_STATE_FABRIC_LOGO. + * Currently this assumes to be called with fnic lock held. + */ +void fdls_send_fabric_logo(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_logo *plogo; + struct fnic *fnic = iport->fnic; + uint8_t d_id[3]; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_logo); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send fabric LOGO"); + return; + } + + plogo = (struct fc_std_logo *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_logo_frame(frame, iport); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_LOGO, + &iport->active_oxid_fabric_req); + + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send fabric LOGO", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + return; + } + FNIC_STD_SET_OX_ID(plogo->fchdr, oxid); + + hton24(d_id, FC_FID_FLOGI); + FNIC_STD_SET_D_ID(plogo->fchdr, d_id); + + iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send fabric LOGO with oxid: 0x%x", + iport->fcid, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + + fdls_start_fabric_timer(iport, 2 * iport->e_d_tov); +} + +/** + * fdls_tgt_logout - Send plogo to the remote port + * @iport: Handle to fnic iport + * @tport: Handle to remote port + * + * This function does not change or check the fabric/tport state. + * It the caller's responsibility to set the appropriate tport/fabric + * state when this is called. Normally that is fdls_tgt_state_plogo. + * This could be used to send plogo to nameserver process + * also not just target processes + */ +void fdls_tgt_logout(struct fnic_iport_s *iport, struct fnic_tport_s *tport) +{ + uint8_t *frame; + struct fc_std_logo *plogo; + struct fnic *fnic = iport->fnic; + uint8_t d_id[3]; + uint16_t oxid; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_logo); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send fabric LOGO"); + return; + } + + plogo = (struct fc_std_logo *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_logo_frame(frame, iport); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_TGT_LOGO, &tport->active_oxid); + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send tgt LOGO", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + return; + } + FNIC_STD_SET_OX_ID(plogo->fchdr, oxid); + + hton24(d_id, tport->fcid); + FNIC_STD_SET_D_ID(plogo->fchdr, d_id); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send tgt LOGO with oxid: 0x%x", + iport->fcid, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); + + atomic64_inc(&iport->iport_stats.tport_logo_sent); +} + +static void fdls_tgt_discovery_start(struct fnic_iport_s *iport) +{ + struct fnic_tport_s *tport, *next; + u32 old_link_down_cnt = iport->fnic->link_down_cnt; + struct fnic *fnic = iport->fnic; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Starting FDLS target discovery", iport->fcid); + + list_for_each_entry_safe(tport, next, &iport->tport_list, links) { + if ((old_link_down_cnt != iport->fnic->link_down_cnt) + || (iport->state != FNIC_IPORT_STATE_READY)) { + break; + } + /* if we marked the tport as deleted due to GPN_FT + * We should not send ADISC anymore + */ + if ((tport->state == FDLS_TGT_STATE_OFFLINING) || + (tport->state == FDLS_TGT_STATE_OFFLINE)) + continue; + + /* For tports which have received RSCN */ + if (tport->flags & FNIC_FDLS_TPORT_SEND_ADISC) { + tport->retry_counter = 0; + fdls_set_tport_state(tport, FDLS_TGT_STATE_ADISC); + tport->flags &= ~FNIC_FDLS_TPORT_SEND_ADISC; + fdls_send_tgt_adisc(iport, tport); + continue; + } + if (fdls_get_tport_state(tport) != FDLS_TGT_STATE_INIT) { + /* Not a new port, skip */ + continue; + } + tport->retry_counter = 0; + fdls_set_tport_state(tport, FDLS_TGT_STATE_PLOGI); + fdls_send_tgt_plogi(iport, tport); + } + fdls_set_state((&iport->fabric), FDLS_STATE_TGT_DISCOVERY); +} + +/* + * Function to restart the IT nexus if we received any out of + * sequence PLOGI/PRLI response from the target. + * The memory for the new tport structure is allocated + * inside fdls_create_tport and added to the iport's tport list. + * This will get freed later during tport_offline/linkdown + * or module unload. The new_tport pointer will go out of scope + * safely since the memory it is + * pointing to it will be freed later + */ +static void fdls_target_restart_nexus(struct fnic_tport_s *tport) +{ + struct fnic_iport_s *iport = tport->iport; + struct fnic_tport_s *new_tport = NULL; + uint32_t fcid; + uint64_t wwpn; + int nexus_restart_count; + struct fnic *fnic = iport->fnic; + bool retval = true; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport fcid: 0x%x state: %d restart_count: %d", + tport->fcid, tport->state, tport->nexus_restart_count); + + fcid = tport->fcid; + wwpn = tport->wwpn; + nexus_restart_count = tport->nexus_restart_count; + + retval = fdls_delete_tport(iport, tport); + if (retval != true) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Error deleting tport: 0x%x", fcid); + return; + } + + if (nexus_restart_count >= FNIC_TPORT_MAX_NEXUS_RESTART) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Exceeded nexus restart retries tport: 0x%x", + fcid); + return; + } + + /* + * Allocate memory for the new tport and add it to + * iport's tport list. + * This memory will be freed during tport_offline/linkdown + * or module unload. The pointer new_tport is safe to go + * out of scope when this function returns, since the memory + * it is pointing to is guaranteed to be freed later + * as mentioned above. + */ + new_tport = fdls_create_tport(iport, fcid, wwpn); + if (!new_tport) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Error creating new tport: 0x%x", fcid); + return; + } + + new_tport->nexus_restart_count = nexus_restart_count + 1; + fdls_send_tgt_plogi(iport, new_tport); + fdls_set_tport_state(new_tport, FDLS_TGT_STATE_PLOGI); +} + +struct fnic_tport_s *fnic_find_tport_by_fcid(struct fnic_iport_s *iport, + uint32_t fcid) +{ + struct fnic_tport_s *tport, *next; + + list_for_each_entry_safe(tport, next, &(iport->tport_list), links) { + if ((tport->fcid == fcid) + && !(tport->flags & FNIC_FDLS_TPORT_TERMINATING)) + return tport; + } + return NULL; +} + +static struct fnic_tport_s *fdls_create_tport(struct fnic_iport_s *iport, + uint32_t fcid, uint64_t wwpn) +{ + struct fnic_tport_s *tport; + struct fnic *fnic = iport->fnic; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDLS create tport: fcid: 0x%x wwpn: 0x%llx", fcid, wwpn); + + tport = kzalloc(sizeof(struct fnic_tport_s), GFP_ATOMIC); + if (!tport) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Memory allocation failure while creating tport: 0x%x\n", + fcid); + return NULL; + } + + tport->max_payload_size = FNIC_FCOE_MAX_FRAME_SZ; + tport->r_a_tov = FC_DEF_R_A_TOV; + tport->e_d_tov = FC_DEF_E_D_TOV; + tport->fcid = fcid; + tport->wwpn = wwpn; + tport->iport = iport; + + FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "Need to setup tport timer callback"); + + timer_setup(&tport->retry_timer, fdls_tport_timer_callback, 0); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Added tport 0x%x", tport->fcid); + fdls_set_tport_state(tport, FDLS_TGT_STATE_INIT); + list_add_tail(&tport->links, &iport->tport_list); + atomic_set(&tport->in_flight, 0); + return tport; +} + +struct fnic_tport_s *fnic_find_tport_by_wwpn(struct fnic_iport_s *iport, + uint64_t wwpn) +{ + struct fnic_tport_s *tport, *next; + + list_for_each_entry_safe(tport, next, &(iport->tport_list), links) { + if ((tport->wwpn == wwpn) + && !(tport->flags & FNIC_FDLS_TPORT_TERMINATING)) + return tport; + } + return NULL; +} + +static void +fnic_fdmi_attr_set(void *attr_start, u16 type, u16 len, + void *data, u32 *off) +{ + u16 size = len + FC_FDMI_ATTR_ENTRY_HEADER_LEN; + struct fc_fdmi_attr_entry *fdmi_attr = (struct fc_fdmi_attr_entry *) + ((u8 *)attr_start + *off); + + put_unaligned_be16(type, &fdmi_attr->type); + put_unaligned_be16(size, &fdmi_attr->len); + memcpy(fdmi_attr->value, data, len); + *off += size; +} + +static void fdls_fdmi_register_hba(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_fdmi_rhba *prhba; + struct fc_fdmi_attr_entry *fdmi_attr; + uint8_t fcid[3]; + int err; + struct fnic *fnic = iport->fnic; + struct vnic_devcmd_fw_info *fw_info = NULL; + uint16_t oxid; + u32 attr_off_bytes, len; + u8 data[64]; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send FDMI RHBA"); + return; + } + + prhba = (struct fc_std_fdmi_rhba *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *prhba = (struct fc_std_fdmi_rhba) { + .fchdr = { + .fh_r_ctl = FC_RCTL_DD_UNSOL_CTL, + .fh_d_id = {0xFF, 0XFF, 0XFA}, + .fh_type = FC_TYPE_CT, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID) + }, + .fc_std_ct_hdr = { + .ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_MGMT, + .ct_fs_subtype = FC_FDMI_SUBTYPE, + .ct_cmd = cpu_to_be16(FC_FDMI_RHBA) + }, + }; + + hton24(fcid, iport->fcid); + FNIC_STD_SET_S_ID(prhba->fchdr, fcid); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FDMI_RHBA, + &iport->active_oxid_fdmi_rhba); + + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send FDMI RHBA", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + return; + } + FNIC_STD_SET_OX_ID(prhba->fchdr, oxid); + + put_unaligned_be64(iport->wwpn, &prhba->rhba.hbaid.id); + put_unaligned_be32(FNIC_FDMI_NUM_PORTS, &prhba->rhba.port.numport); + put_unaligned_be64(iport->wwpn, &prhba->rhba.port.port[0].portname); + put_unaligned_be32(FNIC_FDMI_NUM_HBA_ATTRS, + &prhba->rhba.hba_attrs.numattrs); + + fdmi_attr = prhba->rhba.hba_attrs.attr; + attr_off_bytes = 0; + + put_unaligned_be64(iport->wwnn, data); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_NODE_NAME, + FNIC_FDMI_NN_LEN, data, &attr_off_bytes); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "NN set, off=%d", attr_off_bytes); + + strscpy_pad(data, FNIC_FDMI_MANUFACTURER, FNIC_FDMI_MANU_LEN); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_MANUFACTURER, + FNIC_FDMI_MANU_LEN, data, &attr_off_bytes); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "MFG set <%s>, off=%d", data, attr_off_bytes); + + err = vnic_dev_fw_info(fnic->vdev, &fw_info); + if (!err) { + strscpy_pad(data, fw_info->hw_serial_number, + FNIC_FDMI_SERIAL_LEN); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_SERIAL_NUMBER, + FNIC_FDMI_SERIAL_LEN, data, &attr_off_bytes); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "SERIAL set <%s>, off=%d", data, attr_off_bytes); + + } + + if (fnic->subsys_desc_len >= FNIC_FDMI_MODEL_LEN) + fnic->subsys_desc_len = FNIC_FDMI_MODEL_LEN - 1; + strscpy_pad(data, fnic->subsys_desc, FNIC_FDMI_MODEL_LEN); + data[FNIC_FDMI_MODEL_LEN - 1] = 0; + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_MODEL, FNIC_FDMI_MODEL_LEN, + data, &attr_off_bytes); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "MODEL set <%s>, off=%d", data, attr_off_bytes); + + strscpy_pad(data, FNIC_FDMI_MODEL_DESCRIPTION, FNIC_FDMI_MODEL_DES_LEN); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_MODEL_DES, + FNIC_FDMI_MODEL_DES_LEN, data, &attr_off_bytes); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "MODEL_DESC set <%s>, off=%d", data, attr_off_bytes); + + if (!err) { + strscpy_pad(data, fw_info->hw_version, FNIC_FDMI_HW_VER_LEN); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_HARDWARE_VERSION, + FNIC_FDMI_HW_VER_LEN, data, &attr_off_bytes); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "HW_VER set <%s>, off=%d", data, attr_off_bytes); + + } + + strscpy_pad(data, DRV_VERSION, FNIC_FDMI_DR_VER_LEN); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_DRIVER_VERSION, + FNIC_FDMI_DR_VER_LEN, data, &attr_off_bytes); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "DRV_VER set <%s>, off=%d", data, attr_off_bytes); + + strscpy_pad(data, "N/A", FNIC_FDMI_ROM_VER_LEN); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_ROM_VERSION, + FNIC_FDMI_ROM_VER_LEN, data, &attr_off_bytes); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ROM_VER set <%s>, off=%d", data, attr_off_bytes); + + if (!err) { + strscpy_pad(data, fw_info->fw_version, FNIC_FDMI_FW_VER_LEN); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_FIRMWARE_VERSION, + FNIC_FDMI_FW_VER_LEN, data, &attr_off_bytes); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FW_VER set <%s>, off=%d", data, attr_off_bytes); + } + + len = sizeof(struct fc_std_fdmi_rhba) + attr_off_bytes; + frame_size += len; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send FDMI RHBA with oxid: 0x%x fs: %d", iport->fcid, + oxid, frame_size); + + fnic_send_fcoe_frame(iport, frame, frame_size); + iport->fabric.fdmi_pending |= FDLS_FDMI_REG_HBA_PENDING; +} + +static void fdls_fdmi_register_pa(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fc_std_fdmi_rpa *prpa; + struct fc_fdmi_attr_entry *fdmi_attr; + uint8_t fcid[3]; + struct fnic *fnic = iport->fnic; + u32 port_speed_bm; + u32 port_speed = vnic_dev_port_speed(fnic->vdev); + uint16_t oxid; + u32 attr_off_bytes, len; + u8 tmp_data[16], data[64]; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET; + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send FDMI RPA"); + return; + } + + prpa = (struct fc_std_fdmi_rpa *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *prpa = (struct fc_std_fdmi_rpa) { + .fchdr = { + .fh_r_ctl = FC_RCTL_DD_UNSOL_CTL, + .fh_d_id = {0xFF, 0xFF, 0xFA}, + .fh_type = FC_TYPE_CT, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID) + }, + .fc_std_ct_hdr = { + .ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_MGMT, + .ct_fs_subtype = FC_FDMI_SUBTYPE, + .ct_cmd = cpu_to_be16(FC_FDMI_RPA) + }, + }; + + hton24(fcid, iport->fcid); + FNIC_STD_SET_S_ID(prpa->fchdr, fcid); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FDMI_RPA, + &iport->active_oxid_fdmi_rpa); + + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate OXID to send FDMI RPA", + iport->fcid); + mempool_free(frame, fnic->frame_pool); + return; + } + FNIC_STD_SET_OX_ID(prpa->fchdr, oxid); + + put_unaligned_be64(iport->wwpn, &prpa->rpa.port.portname); + put_unaligned_be32(FNIC_FDMI_NUM_PORT_ATTRS, + &prpa->rpa.hba_attrs.numattrs); + + /* MDS does not support GIGE speed. + * Bit shift standard definitions from scsi_transport_fc.h to + * match FC spec. + */ + switch (port_speed) { + case DCEM_PORTSPEED_10G: + case DCEM_PORTSPEED_20G: + /* There is no bit for 20G */ + port_speed_bm = FC_PORTSPEED_10GBIT << PORT_SPEED_BIT_14; + break; + case DCEM_PORTSPEED_25G: + port_speed_bm = FC_PORTSPEED_25GBIT << PORT_SPEED_BIT_8; + break; + case DCEM_PORTSPEED_40G: + case DCEM_PORTSPEED_4x10G: + port_speed_bm = FC_PORTSPEED_40GBIT << PORT_SPEED_BIT_9; + break; + case DCEM_PORTSPEED_100G: + port_speed_bm = FC_PORTSPEED_100GBIT << PORT_SPEED_BIT_8; + break; + default: + port_speed_bm = FC_PORTSPEED_1GBIT << PORT_SPEED_BIT_15; + break; + } + attr_off_bytes = 0; + + fdmi_attr = prpa->rpa.hba_attrs.attr; + + put_unaligned_be64(iport->wwnn, data); + + memset(data, 0, FNIC_FDMI_FC4_LEN); + data[2] = 1; + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_FC4_TYPES, + FNIC_FDMI_FC4_LEN, data, &attr_off_bytes); + + put_unaligned_be32(port_speed_bm, data); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_SUPPORTED_SPEEDS, + FNIC_FDMI_SUPP_SPEED_LEN, data, &attr_off_bytes); + + put_unaligned_be32(port_speed_bm, data); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_CURRENT_SPEED, + FNIC_FDMI_CUR_SPEED_LEN, data, &attr_off_bytes); + + put_unaligned_be32(FNIC_FDMI_MFS, data); + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_MAX_FRAME_SIZE, + FNIC_FDMI_MFS_LEN, data, &attr_off_bytes); + + snprintf(tmp_data, FNIC_FDMI_OS_NAME_LEN - 1, "host%d", + fnic->host->host_no); + strscpy_pad(data, tmp_data, FNIC_FDMI_OS_NAME_LEN); + data[FNIC_FDMI_OS_NAME_LEN - 1] = 0; + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_OS_NAME, + FNIC_FDMI_OS_NAME_LEN, data, &attr_off_bytes); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "OS name set <%s>, off=%d", data, attr_off_bytes); + + sprintf(fc_host_system_hostname(fnic->host), "%s", utsname()->nodename); + strscpy_pad(data, fc_host_system_hostname(fnic->host), + FNIC_FDMI_HN_LEN); + data[FNIC_FDMI_HN_LEN - 1] = 0; + fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_HOST_NAME, + FNIC_FDMI_HN_LEN, data, &attr_off_bytes); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Host name set <%s>, off=%d", data, attr_off_bytes); + + len = sizeof(struct fc_std_fdmi_rpa) + attr_off_bytes; + frame_size += len; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send FDMI RPA with oxid: 0x%x fs: %d", iport->fcid, + oxid, frame_size); + + fnic_send_fcoe_frame(iport, frame, frame_size); + iport->fabric.fdmi_pending |= FDLS_FDMI_RPA_PENDING; +} + +void fdls_fabric_timer_callback(struct timer_list *t) +{ + struct fnic_fdls_fabric_s *fabric = from_timer(fabric, t, retry_timer); + struct fnic_iport_s *iport = + container_of(fabric, struct fnic_iport_s, fabric); + struct fnic *fnic = iport->fnic; + unsigned long flags; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tp: %d fab state: %d fab retry counter: %d max_flogi_retries: %d", + iport->fabric.timer_pending, iport->fabric.state, + iport->fabric.retry_counter, iport->max_flogi_retries); + + spin_lock_irqsave(&fnic->fnic_lock, flags); + + if (!iport->fabric.timer_pending) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + return; + } + + if (iport->fabric.del_timer_inprogress) { + iport->fabric.del_timer_inprogress = 0; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fabric_del_timer inprogress(%d). Skip timer cb", + iport->fabric.del_timer_inprogress); + return; + } + + iport->fabric.timer_pending = 0; + + /* The fabric state indicates which frames have time out, and we retry */ + switch (iport->fabric.state) { + case FDLS_STATE_FABRIC_FLOGI: + /* Flogi received a LS_RJT with busy we retry from here */ + if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME) + && (iport->fabric.retry_counter < iport->max_flogi_retries)) { + iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME; + fdls_send_fabric_flogi(iport); + } else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) { + /* Flogi has time out 2*ed_tov send abts */ + fdls_send_fabric_abts(iport); + } else { + /* ABTS has timed out + * Mark the OXID to be freed after 2 * r_a_tov and retry the req + */ + fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req); + if (iport->fabric.retry_counter < iport->max_flogi_retries) { + iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED; + fdls_send_fabric_flogi(iport); + } else + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Exceeded max FLOGI retries"); + } + break; + case FDLS_STATE_FABRIC_PLOGI: + /* Plogi received a LS_RJT with busy we retry from here */ + if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME) + && (iport->fabric.retry_counter < iport->max_plogi_retries)) { + iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME; + fdls_send_fabric_plogi(iport); + } else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) { + /* Plogi has timed out 2*ed_tov send abts */ + fdls_send_fabric_abts(iport); + } else { + /* ABTS has timed out + * Mark the OXID to be freed after 2 * r_a_tov and retry the req + */ + fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req); + if (iport->fabric.retry_counter < iport->max_plogi_retries) { + iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED; + fdls_send_fabric_plogi(iport); + } else + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Exceeded max PLOGI retries"); + } + break; + case FDLS_STATE_RPN_ID: + /* Rpn_id received a LS_RJT with busy we retry from here */ + if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME) + && (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) { + iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME; + fdls_send_rpn_id(iport); + } else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) + /* RPN has timed out. Send abts */ + fdls_send_fabric_abts(iport); + else { + /* ABTS has timed out */ + fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req); + fnic_fdls_start_plogi(iport); /* go back to fabric Plogi */ + } + break; + case FDLS_STATE_SCR: + /* scr received a LS_RJT with busy we retry from here */ + if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME) + && (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) { + iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME; + fdls_send_scr(iport); + } else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) + /* scr has timed out. Send abts */ + fdls_send_fabric_abts(iport); + else { + /* ABTS has timed out */ + fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ABTS timed out. Starting PLOGI: %p", iport); + fnic_fdls_start_plogi(iport); + } + break; + case FDLS_STATE_REGISTER_FC4_TYPES: + /* scr received a LS_RJT with busy we retry from here */ + if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME) + && (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) { + iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME; + fdls_send_register_fc4_types(iport); + } else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) { + /* RFT_ID timed out send abts */ + fdls_send_fabric_abts(iport); + } else { + /* ABTS has timed out */ + fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ABTS timed out. Starting PLOGI: %p", iport); + fnic_fdls_start_plogi(iport); /* go back to fabric Plogi */ + } + break; + case FDLS_STATE_REGISTER_FC4_FEATURES: + /* scr received a LS_RJT with busy we retry from here */ + if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME) + && (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) { + iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME; + fdls_send_register_fc4_features(iport); + } else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) + /* SCR has timed out. Send abts */ + fdls_send_fabric_abts(iport); + else { + /* ABTS has timed out */ + fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ABTS timed out. Starting PLOGI %p", iport); + fnic_fdls_start_plogi(iport); /* go back to fabric Plogi */ + } + break; + case FDLS_STATE_RSCN_GPN_FT: + case FDLS_STATE_SEND_GPNFT: + case FDLS_STATE_GPN_FT: + /* GPN_FT received a LS_RJT with busy we retry from here */ + if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME) + && (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) { + iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME; + fdls_send_gpn_ft(iport, iport->fabric.state); + } else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) { + /* gpn_ft has timed out. Send abts */ + fdls_send_fabric_abts(iport); + } else { + /* ABTS has timed out */ + fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req); + if (iport->fabric.retry_counter < FDLS_RETRY_COUNT) { + fdls_send_gpn_ft(iport, iport->fabric.state); + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ABTS timeout for fabric GPN_FT. Check name server: %p", + iport); + } + } + break; + default: + break; + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); +} + +void fdls_fdmi_timer_callback(struct timer_list *t) +{ + struct fnic_fdls_fabric_s *fabric = from_timer(fabric, t, fdmi_timer); + struct fnic_iport_s *iport = + container_of(fabric, struct fnic_iport_s, fabric); + struct fnic *fnic = iport->fnic; + unsigned long flags; + + spin_lock_irqsave(&fnic->fnic_lock, flags); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + + if (!iport->fabric.fdmi_pending) { + /* timer expired after fdmi responses received. */ + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + return; + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + + /* if not abort pending, send an abort */ + if (!(iport->fabric.fdmi_pending & FDLS_FDMI_ABORT_PENDING)) { + fdls_send_fdmi_abts(iport); + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + return; + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + + /* ABTS pending for an active fdmi request that is pending. + * That means FDMI ABTS timed out + * Schedule to free the OXID after 2*r_a_tov and proceed + */ + if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) { + fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_plogi); + } else { + if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) + fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rhba); + if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) + fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rpa); + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + + iport->fabric.fdmi_pending = 0; + /* If max retries not exhaused, start over from fdmi plogi */ + if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) { + iport->fabric.fdmi_retry++; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "retry fdmi timer %d", iport->fabric.fdmi_retry); + fdls_send_fdmi_plogi(iport); + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + spin_unlock_irqrestore(&fnic->fnic_lock, flags); +} + +static void fdls_send_delete_tport_msg(struct fnic_tport_s *tport) +{ + struct fnic_iport_s *iport = (struct fnic_iport_s *) tport->iport; + struct fnic *fnic = iport->fnic; + struct fnic_tport_event_s *tport_del_evt; + + tport_del_evt = kzalloc(sizeof(struct fnic_tport_event_s), GFP_ATOMIC); + if (!tport_del_evt) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Failed to allocate memory for tport event fcid: 0x%x", + tport->fcid); + return; + } + tport_del_evt->event = TGT_EV_TPORT_DELETE; + tport_del_evt->arg1 = (void *) tport; + list_add_tail(&tport_del_evt->links, &fnic->tport_event_list); + queue_work(fnic_event_queue, &fnic->tport_work); +} + +static void fdls_tport_timer_callback(struct timer_list *t) +{ + struct fnic_tport_s *tport = from_timer(tport, t, retry_timer); + struct fnic_iport_s *iport = (struct fnic_iport_s *) tport->iport; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + unsigned long flags; + + spin_lock_irqsave(&fnic->fnic_lock, flags); + if (!tport->timer_pending) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + return; + } + + if (iport->state != FNIC_IPORT_STATE_READY) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + return; + } + + if (tport->del_timer_inprogress) { + tport->del_timer_inprogress = 0; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport_del_timer inprogress. Skip timer cb tport fcid: 0x%x\n", + tport->fcid); + return; + } + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport fcid: 0x%x timer pending: %d state: %d retry counter: %d", + tport->fcid, tport->timer_pending, tport->state, + tport->retry_counter); + + tport->timer_pending = 0; + oxid = tport->active_oxid; + + /* We retry plogi/prli/adisc frames depending on the tport state */ + switch (tport->state) { + case FDLS_TGT_STATE_PLOGI: + /* PLOGI frame received a LS_RJT with busy, we retry from here */ + if ((tport->flags & FNIC_FDLS_RETRY_FRAME) + && (tport->retry_counter < iport->max_plogi_retries)) { + tport->flags &= ~FNIC_FDLS_RETRY_FRAME; + fdls_send_tgt_plogi(iport, tport); + } else if (!(tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) { + /* Plogi frame has timed out, send abts */ + fdls_send_tport_abts(iport, tport); + } else if (tport->retry_counter < iport->max_plogi_retries) { + /* + * ABTS has timed out + */ + fdls_schedule_oxid_free(iport, &tport->active_oxid); + fdls_send_tgt_plogi(iport, tport); + } else { + /* exceeded plogi retry count */ + fdls_schedule_oxid_free(iport, &tport->active_oxid); + fdls_send_delete_tport_msg(tport); + } + break; + case FDLS_TGT_STATE_PRLI: + /* PRLI received a LS_RJT with busy , hence we retry from here */ + if ((tport->flags & FNIC_FDLS_RETRY_FRAME) + && (tport->retry_counter < FDLS_RETRY_COUNT)) { + tport->flags &= ~FNIC_FDLS_RETRY_FRAME; + fdls_send_tgt_prli(iport, tport); + } else if (!(tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) { + /* PRLI has time out, send abts */ + fdls_send_tport_abts(iport, tport); + } else { + /* ABTS has timed out for prli, we go back to PLOGI */ + fdls_schedule_oxid_free(iport, &tport->active_oxid); + fdls_send_tgt_plogi(iport, tport); + fdls_set_tport_state(tport, FDLS_TGT_STATE_PLOGI); + } + break; + case FDLS_TGT_STATE_ADISC: + /* ADISC timed out send an ABTS */ + if (!(tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) { + fdls_send_tport_abts(iport, tport); + } else if ((tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED) + && (tport->retry_counter < FDLS_RETRY_COUNT)) { + /* + * ABTS has timed out + */ + fdls_schedule_oxid_free(iport, &tport->active_oxid); + fdls_send_tgt_adisc(iport, tport); + } else { + /* exceeded retry count */ + fdls_schedule_oxid_free(iport, &tport->active_oxid); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ADISC not responding. Deleting target port: 0x%x", + tport->fcid); + fdls_send_delete_tport_msg(tport); + } + break; + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "oxid: 0x%x Unknown tport state: 0x%x", oxid, tport->state); + break; + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); +} + +static void fnic_fdls_start_flogi(struct fnic_iport_s *iport) +{ + iport->fabric.retry_counter = 0; + fdls_send_fabric_flogi(iport); + fdls_set_state((&iport->fabric), FDLS_STATE_FABRIC_FLOGI); + iport->fabric.flags = 0; +} + +static void fnic_fdls_start_plogi(struct fnic_iport_s *iport) +{ + iport->fabric.retry_counter = 0; + fdls_send_fabric_plogi(iport); + fdls_set_state((&iport->fabric), FDLS_STATE_FABRIC_PLOGI); + iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED; + + if ((fnic_fdmi_support == 1) && (!(iport->flags & FNIC_FDMI_ACTIVE))) { + /* we can do FDMI at the same time */ + iport->fabric.fdmi_retry = 0; + timer_setup(&iport->fabric.fdmi_timer, fdls_fdmi_timer_callback, + 0); + fdls_send_fdmi_plogi(iport); + iport->flags |= FNIC_FDMI_ACTIVE; + } +} +static void +fdls_process_tgt_adisc_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + uint32_t tgt_fcid; + struct fnic_tport_s *tport; + uint8_t *fcid; + uint64_t frame_wwnn; + uint64_t frame_wwpn; + uint16_t oxid; + struct fc_std_els_adisc *adisc_rsp = (struct fc_std_els_adisc *)fchdr; + struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *)fchdr; + struct fnic *fnic = iport->fnic; + + fcid = FNIC_STD_GET_S_ID(fchdr); + tgt_fcid = ntoh24(fcid); + tport = fnic_find_tport_by_fcid(iport, tgt_fcid); + + if (!tport) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Tgt ADISC response tport not found: 0x%x", tgt_fcid); + return; + } + if ((iport->state != FNIC_IPORT_STATE_READY) + || (tport->state != FDLS_TGT_STATE_ADISC) + || (tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping this ADISC response"); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport state: %d tport state: %d Is abort issued on PRLI? %d", + iport->state, tport->state, + (tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)); + return; + } + if (FNIC_STD_GET_OX_ID(fchdr) != tport->active_oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping frame from target: 0x%x", + tgt_fcid); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Reason: Stale ADISC/Aborted ADISC/OOO frame delivery"); + return; + } + + oxid = FNIC_STD_GET_OX_ID(fchdr); + fdls_free_oxid(iport, oxid, &tport->active_oxid); + + switch (adisc_rsp->els.adisc_cmd) { + case ELS_LS_ACC: + atomic64_inc(&iport->iport_stats.tport_adisc_ls_accepts); + if (tport->timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport 0x%p Canceling fabric disc timer\n", + tport); + fnic_del_tport_timer_sync(fnic, tport); + } + tport->timer_pending = 0; + tport->retry_counter = 0; + frame_wwnn = get_unaligned_be64(&adisc_rsp->els.adisc_wwnn); + frame_wwpn = get_unaligned_be64(&adisc_rsp->els.adisc_wwpn); + if ((frame_wwnn == tport->wwnn) && (frame_wwpn == tport->wwpn)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ADISC accepted from target: 0x%x. Target logged in", + tgt_fcid); + fdls_set_tport_state(tport, FDLS_TGT_STATE_READY); + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Error mismatch frame: ADISC"); + } + break; + + case ELS_LS_RJT: + atomic64_inc(&iport->iport_stats.tport_adisc_ls_rejects); + if (((els_rjt->rej.er_reason == ELS_RJT_BUSY) + || (els_rjt->rej.er_reason == ELS_RJT_UNAB)) + && (tport->retry_counter < FDLS_RETRY_COUNT)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ADISC ret ELS_LS_RJT BUSY. Retry from timer routine: 0x%x", + tgt_fcid); + + /* Retry ADISC again from the timer routine. */ + tport->flags |= FNIC_FDLS_RETRY_FRAME; + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ADISC returned ELS_LS_RJT from target: 0x%x", + tgt_fcid); + fdls_delete_tport(iport, tport); + } + break; + } +} +static void +fdls_process_tgt_plogi_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + uint32_t tgt_fcid; + struct fnic_tport_s *tport; + uint8_t *fcid; + uint16_t oxid; + struct fc_std_flogi *plogi_rsp = (struct fc_std_flogi *)fchdr; + struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *)fchdr; + uint16_t max_payload_size; + struct fnic *fnic = iport->fnic; + + fcid = FNIC_STD_GET_S_ID(fchdr); + tgt_fcid = ntoh24(fcid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDLS processing target PLOGI response: tgt_fcid: 0x%x", + tgt_fcid); + + tport = fnic_find_tport_by_fcid(iport, tgt_fcid); + if (!tport) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport not found: 0x%x", tgt_fcid); + return; + } + if ((iport->state != FNIC_IPORT_STATE_READY) + || (tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping frame! iport state: %d tport state: %d", + iport->state, tport->state); + return; + } + + if (tport->state != FDLS_TGT_STATE_PLOGI) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PLOGI rsp recvd in wrong state. Drop the frame and restart nexus"); + fdls_target_restart_nexus(tport); + return; + } + + if (FNIC_STD_GET_OX_ID(fchdr) != tport->active_oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PLOGI response from target: 0x%x. Dropping frame", + tgt_fcid); + return; + } + + oxid = FNIC_STD_GET_OX_ID(fchdr); + fdls_free_oxid(iport, oxid, &tport->active_oxid); + + switch (plogi_rsp->els.fl_cmd) { + case ELS_LS_ACC: + atomic64_inc(&iport->iport_stats.tport_plogi_ls_accepts); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PLOGI accepted by target: 0x%x", tgt_fcid); + break; + + case ELS_LS_RJT: + atomic64_inc(&iport->iport_stats.tport_plogi_ls_rejects); + if (((els_rjt->rej.er_reason == ELS_RJT_BUSY) + || (els_rjt->rej.er_reason == ELS_RJT_UNAB)) + && (tport->retry_counter < iport->max_plogi_retries)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PLOGI ret ELS_LS_RJT BUSY. Retry from timer routine: 0x%x", + tgt_fcid); + /* Retry plogi again from the timer routine. */ + tport->flags |= FNIC_FDLS_RETRY_FRAME; + return; + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PLOGI returned ELS_LS_RJT from target: 0x%x", + tgt_fcid); + fdls_delete_tport(iport, tport); + return; + + default: + atomic64_inc(&iport->iport_stats.tport_plogi_misc_rejects); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PLOGI not accepted from target fcid: 0x%x", + tgt_fcid); + return; + } + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Found the PLOGI target: 0x%x and state: %d", + (unsigned int) tgt_fcid, tport->state); + + if (tport->timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport fcid 0x%x: Canceling disc timer\n", + tport->fcid); + fnic_del_tport_timer_sync(fnic, tport); + } + + tport->timer_pending = 0; + tport->wwpn = get_unaligned_be64(&FNIC_LOGI_PORT_NAME(plogi_rsp->els)); + tport->wwnn = get_unaligned_be64(&FNIC_LOGI_NODE_NAME(plogi_rsp->els)); + + /* Learn the Service Params */ + + /* Max frame size - choose the lowest */ + max_payload_size = fnic_fc_plogi_rsp_rdf(iport, plogi_rsp); + tport->max_payload_size = + min(max_payload_size, iport->max_payload_size); + + if (tport->max_payload_size < FNIC_MIN_DATA_FIELD_SIZE) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "MFS: tport max frame size below spec bounds: %d", + tport->max_payload_size); + tport->max_payload_size = FNIC_MIN_DATA_FIELD_SIZE; + } + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "MAX frame size: %u iport max_payload_size: %d tport mfs: %d", + max_payload_size, iport->max_payload_size, + tport->max_payload_size); + + tport->max_concur_seqs = FNIC_FC_PLOGI_RSP_CONCUR_SEQ(plogi_rsp); + + tport->retry_counter = 0; + fdls_set_tport_state(tport, FDLS_TGT_STATE_PRLI); + fdls_send_tgt_prli(iport, tport); +} +static void +fdls_process_tgt_prli_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + uint32_t tgt_fcid; + struct fnic_tport_s *tport; + uint8_t *fcid; + uint16_t oxid; + struct fc_std_els_prli *prli_rsp = (struct fc_std_els_prli *)fchdr; + struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *)fchdr; + struct fnic_tport_event_s *tport_add_evt; + struct fnic *fnic = iport->fnic; + bool mismatched_tgt = false; + + fcid = FNIC_STD_GET_S_ID(fchdr); + tgt_fcid = ntoh24(fcid); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDLS process tgt PRLI response: 0x%x", tgt_fcid); + + tport = fnic_find_tport_by_fcid(iport, tgt_fcid); + if (!tport) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport not found: 0x%x", tgt_fcid); + /* Handle or just drop? */ + return; + } + + if ((iport->state != FNIC_IPORT_STATE_READY) + || (tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping frame! iport st: %d tport st: %d tport fcid: 0x%x", + iport->state, tport->state, tport->fcid); + return; + } + + if (tport->state != FDLS_TGT_STATE_PRLI) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PRLI rsp recvd in wrong state. Drop frame. Restarting nexus"); + fdls_target_restart_nexus(tport); + return; + } + + if (FNIC_STD_GET_OX_ID(fchdr) != tport->active_oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping PRLI response from target: 0x%x ", + tgt_fcid); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Reason: Stale PRLI response/Aborted PDISC/OOO frame delivery"); + return; + } + + oxid = FNIC_STD_GET_OX_ID(fchdr); + fdls_free_oxid(iport, oxid, &tport->active_oxid); + + switch (prli_rsp->els_prli.prli_cmd) { + case ELS_LS_ACC: + atomic64_inc(&iport->iport_stats.tport_prli_ls_accepts); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PRLI accepted from target: 0x%x", tgt_fcid); + + if (prli_rsp->sp.spp_type != FC_FC4_TYPE_SCSI) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "mismatched target zoned with FC SCSI initiator: 0x%x", + tgt_fcid); + mismatched_tgt = true; + } + if (mismatched_tgt) { + fdls_tgt_logout(iport, tport); + fdls_delete_tport(iport, tport); + return; + } + break; + case ELS_LS_RJT: + atomic64_inc(&iport->iport_stats.tport_prli_ls_rejects); + if (((els_rjt->rej.er_reason == ELS_RJT_BUSY) + || (els_rjt->rej.er_reason == ELS_RJT_UNAB)) + && (tport->retry_counter < FDLS_RETRY_COUNT)) { + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PRLI ret ELS_LS_RJT BUSY. Retry from timer routine: 0x%x", + tgt_fcid); + + /*Retry Plogi again from the timer routine. */ + tport->flags |= FNIC_FDLS_RETRY_FRAME; + return; + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PRLI returned ELS_LS_RJT from target: 0x%x", + tgt_fcid); + + fdls_tgt_logout(iport, tport); + fdls_delete_tport(iport, tport); + return; + default: + atomic64_inc(&iport->iport_stats.tport_prli_misc_rejects); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PRLI not accepted from target: 0x%x", tgt_fcid); + return; + } + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Found the PRLI target: 0x%x and state: %d", + (unsigned int) tgt_fcid, tport->state); + + if (tport->timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport fcid 0x%x: Canceling disc timer\n", + tport->fcid); + fnic_del_tport_timer_sync(fnic, tport); + } + tport->timer_pending = 0; + + /* Learn Service Params */ + tport->fcp_csp = be32_to_cpu(prli_rsp->sp.spp_params); + tport->retry_counter = 0; + + if (tport->fcp_csp & FCP_SPPF_RETRY) + tport->tgt_flags |= FNIC_FC_RP_FLAGS_RETRY; + + /* Check if the device plays Target Mode Function */ + if (!(tport->fcp_csp & FCP_PRLI_FUNC_TARGET)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Remote port(0x%x): no target support. Deleting it\n", + tgt_fcid); + fdls_tgt_logout(iport, tport); + fdls_delete_tport(iport, tport); + return; + } + + fdls_set_tport_state(tport, FDLS_TGT_STATE_READY); + + /* Inform the driver about new target added */ + tport_add_evt = kzalloc(sizeof(struct fnic_tport_event_s), GFP_ATOMIC); + if (!tport_add_evt) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport event memory allocation failure: 0x%0x\n", + tport->fcid); + return; + } + tport_add_evt->event = TGT_EV_RPORT_ADD; + tport_add_evt->arg1 = (void *) tport; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport fcid: 0x%x add tport event fcid: 0x%x\n", + tport->fcid, iport->fcid); + list_add_tail(&tport_add_evt->links, &fnic->tport_event_list); + queue_work(fnic_event_queue, &fnic->tport_work); +} + + +static void +fdls_process_rff_id_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + struct fnic *fnic = iport->fnic; + struct fnic_fdls_fabric_s *fdls = &iport->fabric; + struct fc_std_rff_id *rff_rsp = (struct fc_std_rff_id *) fchdr; + uint16_t rsp; + uint8_t reason_code; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + + if (fdls_get_state(fdls) != FDLS_STATE_REGISTER_FC4_FEATURES) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RFF_ID resp recvd in state(%d). Dropping.", + fdls_get_state(fdls)); + return; + } + + if (iport->active_oxid_fabric_req != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n", + fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req); + return; + } + + rsp = FNIC_STD_GET_FC_CT_CMD((&rff_rsp->fc_std_ct_hdr)); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS process RFF ID response: 0x%04x", iport->fcid, + (uint32_t) rsp); + + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + + switch (rsp) { + case FC_FS_ACC: + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Canceling fabric disc timer %p\n", iport); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + fdls->retry_counter = 0; + fdls_set_state((&iport->fabric), FDLS_STATE_SCR); + fdls_send_scr(iport); + break; + case FC_FS_RJT: + reason_code = rff_rsp->fc_std_ct_hdr.ct_reason; + if (((reason_code == FC_FS_RJT_BSY) + || (reason_code == FC_FS_RJT_UNABL)) + && (fdls->retry_counter < FDLS_RETRY_COUNT)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RFF_ID ret ELS_LS_RJT BUSY. Retry from timer routine %p", + iport); + + /* Retry again from the timer routine */ + fdls->flags |= FNIC_FDLS_RETRY_FRAME; + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RFF_ID returned ELS_LS_RJT. Halting discovery %p", + iport); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Canceling fabric disc timer %p\n", iport); + fnic_del_fabric_timer_sync(fnic); + } + fdls->timer_pending = 0; + fdls->retry_counter = 0; + } + break; + default: + break; + } +} + +static void +fdls_process_rft_id_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + struct fnic_fdls_fabric_s *fdls = &iport->fabric; + struct fc_std_rft_id *rft_rsp = (struct fc_std_rft_id *) fchdr; + uint16_t rsp; + uint8_t reason_code; + struct fnic *fnic = iport->fnic; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + + if (fdls_get_state(fdls) != FDLS_STATE_REGISTER_FC4_TYPES) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RFT_ID resp recvd in state(%d). Dropping.", + fdls_get_state(fdls)); + return; + } + + if (iport->active_oxid_fabric_req != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n", + fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req); + return; + } + + + rsp = FNIC_STD_GET_FC_CT_CMD((&rft_rsp->fc_std_ct_hdr)); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS process RFT ID response: 0x%04x", iport->fcid, + (uint32_t) rsp); + + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + + switch (rsp) { + case FC_FS_ACC: + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Canceling fabric disc timer %p\n", iport); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + fdls->retry_counter = 0; + fdls_send_register_fc4_features(iport); + fdls_set_state((&iport->fabric), FDLS_STATE_REGISTER_FC4_FEATURES); + break; + case FC_FS_RJT: + reason_code = rft_rsp->fc_std_ct_hdr.ct_reason; + if (((reason_code == FC_FS_RJT_BSY) + || (reason_code == FC_FS_RJT_UNABL)) + && (fdls->retry_counter < FDLS_RETRY_COUNT)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: RFT_ID ret ELS_LS_RJT BUSY. Retry from timer routine", + iport->fcid); + + /* Retry again from the timer routine */ + fdls->flags |= FNIC_FDLS_RETRY_FRAME; + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: RFT_ID REJ. Halting discovery reason %d expl %d", + iport->fcid, reason_code, + rft_rsp->fc_std_ct_hdr.ct_explan); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Canceling fabric disc timer %p\n", iport); + fnic_del_fabric_timer_sync(fnic); + } + fdls->timer_pending = 0; + fdls->retry_counter = 0; + } + break; + default: + break; + } +} + +static void +fdls_process_rpn_id_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + struct fnic_fdls_fabric_s *fdls = &iport->fabric; + struct fc_std_rpn_id *rpn_rsp = (struct fc_std_rpn_id *) fchdr; + uint16_t rsp; + uint8_t reason_code; + struct fnic *fnic = iport->fnic; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + + if (fdls_get_state(fdls) != FDLS_STATE_RPN_ID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RPN_ID resp recvd in state(%d). Dropping.", + fdls_get_state(fdls)); + return; + } + if (iport->active_oxid_fabric_req != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n", + fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req); + return; + } + + rsp = FNIC_STD_GET_FC_CT_CMD((&rpn_rsp->fc_std_ct_hdr)); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS process RPN ID response: 0x%04x", iport->fcid, + (uint32_t) rsp); + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + + switch (rsp) { + case FC_FS_ACC: + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Canceling fabric disc timer %p\n", iport); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + fdls->retry_counter = 0; + fdls_send_register_fc4_types(iport); + fdls_set_state((&iport->fabric), FDLS_STATE_REGISTER_FC4_TYPES); + break; + case FC_FS_RJT: + reason_code = rpn_rsp->fc_std_ct_hdr.ct_reason; + if (((reason_code == FC_FS_RJT_BSY) + || (reason_code == FC_FS_RJT_UNABL)) + && (fdls->retry_counter < FDLS_RETRY_COUNT)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RPN_ID returned REJ BUSY. Retry from timer routine %p", + iport); + + /* Retry again from the timer routine */ + fdls->flags |= FNIC_FDLS_RETRY_FRAME; + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RPN_ID ELS_LS_RJT. Halting discovery %p", iport); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Canceling fabric disc timer %p\n", iport); + fnic_del_fabric_timer_sync(fnic); + } + fdls->timer_pending = 0; + fdls->retry_counter = 0; + } + break; + default: + break; + } +} + +static void +fdls_process_scr_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + struct fnic_fdls_fabric_s *fdls = &iport->fabric; + struct fc_std_scr *scr_rsp = (struct fc_std_scr *) fchdr; + struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *) fchdr; + struct fnic *fnic = iport->fnic; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDLS process SCR response: 0x%04x", + (uint32_t) scr_rsp->scr.scr_cmd); + + if (fdls_get_state(fdls) != FDLS_STATE_SCR) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "SCR resp recvd in state(%d). Dropping.", + fdls_get_state(fdls)); + return; + } + if (iport->active_oxid_fabric_req != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n", + fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req); + } + + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + + switch (scr_rsp->scr.scr_cmd) { + case ELS_LS_ACC: + atomic64_inc(&iport->iport_stats.fabric_scr_ls_accepts); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Canceling fabric disc timer %p\n", iport); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + iport->fabric.retry_counter = 0; + fdls_send_gpn_ft(iport, FDLS_STATE_GPN_FT); + break; + + case ELS_LS_RJT: + atomic64_inc(&iport->iport_stats.fabric_scr_ls_rejects); + if (((els_rjt->rej.er_reason == ELS_RJT_BUSY) + || (els_rjt->rej.er_reason == ELS_RJT_UNAB)) + && (fdls->retry_counter < FDLS_RETRY_COUNT)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "SCR ELS_LS_RJT BUSY. Retry from timer routine %p", + iport); + /* Retry again from the timer routine */ + fdls->flags |= FNIC_FDLS_RETRY_FRAME; + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "SCR returned ELS_LS_RJT. Halting discovery %p", + iport); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Canceling fabric disc timer %p\n", + iport); + fnic_del_fabric_timer_sync(fnic); + } + fdls->timer_pending = 0; + fdls->retry_counter = 0; + } + break; + + default: + atomic64_inc(&iport->iport_stats.fabric_scr_misc_rejects); + break; + } +} + +static void +fdls_process_gpn_ft_tgt_list(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr, int len) +{ + struct fc_gpn_ft_rsp_iu *gpn_ft_tgt; + struct fnic_tport_s *tport, *next; + uint32_t fcid; + uint64_t wwpn; + int rem_len = len; + u32 old_link_down_cnt = iport->fnic->link_down_cnt; + struct fnic *fnic = iport->fnic; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS process GPN_FT tgt list", iport->fcid); + + gpn_ft_tgt = + (struct fc_gpn_ft_rsp_iu *)((uint8_t *) fchdr + + sizeof(struct fc_frame_header) + + sizeof(struct fc_ct_hdr)); + len -= sizeof(struct fc_frame_header) + sizeof(struct fc_ct_hdr); + + while (rem_len > 0) { + + fcid = ntoh24(gpn_ft_tgt->fcid); + wwpn = be64_to_cpu(gpn_ft_tgt->wwpn); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "tport: 0x%x: ctrl:0x%x", fcid, gpn_ft_tgt->ctrl); + + if (fcid == iport->fcid) { + if (gpn_ft_tgt->ctrl & FC_NS_FID_LAST) + break; + gpn_ft_tgt++; + rem_len -= sizeof(struct fc_gpn_ft_rsp_iu); + continue; + } + + tport = fnic_find_tport_by_wwpn(iport, wwpn); + if (!tport) { + /* + * New port registered with the switch or first time query + */ + tport = fdls_create_tport(iport, fcid, wwpn); + if (!tport) + return; + } + /* + * check if this was an existing tport with same fcid + * but whose wwpn has changed now ,then remove it and + * create a new one + */ + if (tport->fcid != fcid) { + fdls_delete_tport(iport, tport); + tport = fdls_create_tport(iport, fcid, wwpn); + if (!tport) + return; + } + + /* + * If this GPN_FT rsp is after RSCN then mark the tports which + * matches with the new GPN_FT list, if some tport is not + * found in GPN_FT we went to delete that tport later. + */ + if (fdls_get_state((&iport->fabric)) == FDLS_STATE_RSCN_GPN_FT) + tport->flags |= FNIC_FDLS_TPORT_IN_GPN_FT_LIST; + + if (gpn_ft_tgt->ctrl & FC_NS_FID_LAST) + break; + + gpn_ft_tgt++; + rem_len -= sizeof(struct fc_gpn_ft_rsp_iu); + } + if (rem_len <= 0) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "GPN_FT response: malformed/corrupt frame rxlen: %d remlen: %d", + len, rem_len); +} + + /*remove those ports which was not listed in GPN_FT */ + if (fdls_get_state((&iport->fabric)) == FDLS_STATE_RSCN_GPN_FT) { + list_for_each_entry_safe(tport, next, &iport->tport_list, links) { + + if (!(tport->flags & FNIC_FDLS_TPORT_IN_GPN_FT_LIST)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Remove port: 0x%x not found in GPN_FT list", + tport->fcid); + fdls_delete_tport(iport, tport); + } else { + tport->flags &= ~FNIC_FDLS_TPORT_IN_GPN_FT_LIST; + } + if ((old_link_down_cnt != iport->fnic->link_down_cnt) + || (iport->state != FNIC_IPORT_STATE_READY)) { + return; + } + } + } +} + +static void +fdls_process_gpn_ft_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr, int len) +{ + struct fnic_fdls_fabric_s *fdls = &iport->fabric; + struct fc_std_gpn_ft *gpn_ft_rsp = (struct fc_std_gpn_ft *) fchdr; + uint16_t rsp; + uint8_t reason_code; + int count = 0; + struct fnic_tport_s *tport, *next; + u32 old_link_down_cnt = iport->fnic->link_down_cnt; + struct fnic *fnic = iport->fnic; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDLS process GPN_FT response: iport state: %d len: %d", + iport->state, len); + + /* + * GPNFT response :- + * FDLS_STATE_GPN_FT : GPNFT send after SCR state + * during fabric discovery(FNIC_IPORT_STATE_FABRIC_DISC) + * FDLS_STATE_RSCN_GPN_FT : GPNFT send in response to RSCN + * FDLS_STATE_SEND_GPNFT : GPNFT send after deleting a Target, + * e.g. after receiving Target LOGO + * FDLS_STATE_TGT_DISCOVERY :Target discovery is currently in progress + * from previous GPNFT response,a new GPNFT response has come. + */ + if (!(((iport->state == FNIC_IPORT_STATE_FABRIC_DISC) + && (fdls_get_state(fdls) == FDLS_STATE_GPN_FT)) + || ((iport->state == FNIC_IPORT_STATE_READY) + && ((fdls_get_state(fdls) == FDLS_STATE_RSCN_GPN_FT) + || (fdls_get_state(fdls) == FDLS_STATE_SEND_GPNFT) + || (fdls_get_state(fdls) == FDLS_STATE_TGT_DISCOVERY))))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "GPNFT resp recvd in fab state(%d) iport_state(%d). Dropping.", + fdls_get_state(fdls), iport->state); + return; + } + + if (iport->active_oxid_fabric_req != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n", + fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req); + } + + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + + iport->state = FNIC_IPORT_STATE_READY; + rsp = FNIC_STD_GET_FC_CT_CMD((&gpn_ft_rsp->fc_std_ct_hdr)); + + switch (rsp) { + + case FC_FS_ACC: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: GPNFT_RSP accept", iport->fcid); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Canceling fabric disc timer\n", + iport->fcid); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + iport->fabric.retry_counter = 0; + fdls_process_gpn_ft_tgt_list(iport, fchdr, len); + + /* + * iport state can change only if link down event happened + * We don't need to undo fdls_process_gpn_ft_tgt_list, + * that will be taken care in next link up event + */ + if (iport->state != FNIC_IPORT_STATE_READY) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Halting target discovery: fab st: %d iport st: %d ", + fdls_get_state(fdls), iport->state); + break; + } + fdls_tgt_discovery_start(iport); + break; + + case FC_FS_RJT: + reason_code = gpn_ft_rsp->fc_std_ct_hdr.ct_reason; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: GPNFT_RSP Reject reason: %d", iport->fcid, reason_code); + + if (((reason_code == FC_FS_RJT_BSY) + || (reason_code == FC_FS_RJT_UNABL)) + && (fdls->retry_counter < FDLS_RETRY_COUNT)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: GPNFT_RSP ret REJ/BSY. Retry from timer routine", + iport->fcid); + /* Retry again from the timer routine */ + fdls->flags |= FNIC_FDLS_RETRY_FRAME; + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: GPNFT_RSP reject", iport->fcid); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Canceling fabric disc timer\n", + iport->fcid); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + iport->fabric.retry_counter = 0; + /* + * If GPN_FT ls_rjt then we should delete + * all existing tports + */ + count = 0; + list_for_each_entry_safe(tport, next, &iport->tport_list, + links) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "GPN_FT_REJECT: Remove port: 0x%x", + tport->fcid); + fdls_delete_tport(iport, tport); + if ((old_link_down_cnt != iport->fnic->link_down_cnt) + || (iport->state != FNIC_IPORT_STATE_READY)) { + return; + } + count++; + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "GPN_FT_REJECT: Removed (0x%x) ports", count); + } + break; + + default: + break; + } +} + +/** + * fdls_process_fabric_logo_rsp - Handle an flogo response from the fcf + * @iport: Handle to fnic iport + * @fchdr: Incoming frame + */ +static void +fdls_process_fabric_logo_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + struct fc_std_flogi *flogo_rsp = (struct fc_std_flogi *) fchdr; + struct fnic_fdls_fabric_s *fdls = &iport->fabric; + struct fnic *fnic = iport->fnic; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + + if (iport->active_oxid_fabric_req != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n", + fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req); + } + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + + switch (flogo_rsp->els.fl_cmd) { + case ELS_LS_ACC: + if (iport->fabric.state != FDLS_STATE_FABRIC_LOGO) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Flogo response. Fabric not in LOGO state. Dropping! %p", + iport); + return; + } + + iport->fabric.state = FDLS_STATE_FLOGO_DONE; + iport->state = FNIC_IPORT_STATE_LINK_WAIT; + + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport 0x%p Canceling fabric disc timer\n", + iport); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Flogo response from Fabric for did: 0x%x", + ntoh24(fchdr->fh_d_id)); + return; + + case ELS_LS_RJT: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Flogo response from Fabric for did: 0x%x returned ELS_LS_RJT", + ntoh24(fchdr->fh_d_id)); + return; + + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGO response not accepted or rejected: 0x%x", + flogo_rsp->els.fl_cmd); + } +} + +static void +fdls_process_flogi_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr, void *rx_frame) +{ + struct fnic_fdls_fabric_s *fabric = &iport->fabric; + struct fc_std_flogi *flogi_rsp = (struct fc_std_flogi *) fchdr; + uint8_t *fcid; + uint16_t rdf_size; + uint8_t fcmac[6] = { 0x0E, 0XFC, 0x00, 0x00, 0x00, 0x00 }; + struct fnic *fnic = iport->fnic; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS processing FLOGI response", iport->fcid); + + if (fdls_get_state(fabric) != FDLS_STATE_FABRIC_FLOGI) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI response received in state (%d). Dropping frame", + fdls_get_state(fabric)); + return; + } + if (iport->active_oxid_fabric_req != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n", + fdls_get_state(fabric), oxid, iport->active_oxid_fabric_req); + return; + } + + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + + switch (flogi_rsp->els.fl_cmd) { + case ELS_LS_ACC: + atomic64_inc(&iport->iport_stats.fabric_flogi_ls_accepts); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport fcid: 0x%x Canceling fabric disc timer\n", + iport->fcid); + fnic_del_fabric_timer_sync(fnic); + } + + iport->fabric.timer_pending = 0; + iport->fabric.retry_counter = 0; + fcid = FNIC_STD_GET_D_ID(fchdr); + iport->fcid = ntoh24(fcid); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FLOGI response accepted", iport->fcid); + + /* Learn the Service Params */ + rdf_size = be16_to_cpu(FNIC_LOGI_RDF_SIZE(flogi_rsp->els)); + if ((rdf_size >= FNIC_MIN_DATA_FIELD_SIZE) + && (rdf_size < FNIC_FC_MAX_PAYLOAD_LEN)) + iport->max_payload_size = min(rdf_size, + iport->max_payload_size); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "max_payload_size from fabric: %u set: %d", rdf_size, + iport->max_payload_size); + + iport->r_a_tov = be32_to_cpu(FNIC_LOGI_R_A_TOV(flogi_rsp->els)); + iport->e_d_tov = be32_to_cpu(FNIC_LOGI_E_D_TOV(flogi_rsp->els)); + + if (FNIC_LOGI_FEATURES(flogi_rsp->els) & FNIC_FC_EDTOV_NSEC) + iport->e_d_tov = iport->e_d_tov / FNIC_NSEC_TO_MSEC; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "From fabric: R_A_TOV: %d E_D_TOV: %d", + iport->r_a_tov, iport->e_d_tov); + + fc_host_fabric_name(iport->fnic->host) = + get_unaligned_be64(&FNIC_LOGI_NODE_NAME(flogi_rsp->els)); + fc_host_port_id(iport->fnic->host) = iport->fcid; + + fnic_fdls_learn_fcoe_macs(iport, rx_frame, fcid); + + if (fnic_fdls_register_portid(iport, iport->fcid, rx_frame) != 0) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FLOGI registration failed", iport->fcid); + break; + } + + memcpy(&fcmac[3], fcid, 3); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Adding vNIC device MAC addr: %02x:%02x:%02x:%02x:%02x:%02x", + fcmac[0], fcmac[1], fcmac[2], fcmac[3], fcmac[4], + fcmac[5]); + vnic_dev_add_addr(iport->fnic->vdev, fcmac); + + if (fdls_get_state(fabric) == FDLS_STATE_FABRIC_FLOGI) { + fnic_fdls_start_plogi(iport); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI response received. Starting PLOGI"); + } else { + /* From FDLS_STATE_FABRIC_FLOGI state fabric can only go to + * FDLS_STATE_LINKDOWN + * state, hence we don't have to worry about undoing: + * the fnic_fdls_register_portid and vnic_dev_add_addr + */ + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI response received in state (%d). Dropping frame", + fdls_get_state(fabric)); + } + break; + + case ELS_LS_RJT: + atomic64_inc(&iport->iport_stats.fabric_flogi_ls_rejects); + if (fabric->retry_counter < iport->max_flogi_retries) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI returned ELS_LS_RJT BUSY. Retry from timer routine %p", + iport); + + /* Retry Flogi again from the timer routine. */ + fabric->flags |= FNIC_FDLS_RETRY_FRAME; + + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI returned ELS_LS_RJT. Halting discovery %p", + iport); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport 0x%p Canceling fabric disc timer\n", + iport); + fnic_del_fabric_timer_sync(fnic); + } + fabric->timer_pending = 0; + fabric->retry_counter = 0; + } + break; + + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI response not accepted: 0x%x", + flogi_rsp->els.fl_cmd); + atomic64_inc(&iport->iport_stats.fabric_flogi_misc_rejects); + break; + } +} + +static void +fdls_process_fabric_plogi_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + struct fc_std_flogi *plogi_rsp = (struct fc_std_flogi *) fchdr; + struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *) fchdr; + struct fnic_fdls_fabric_s *fdls = &iport->fabric; + struct fnic *fnic = iport->fnic; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + + if (fdls_get_state((&iport->fabric)) != FDLS_STATE_FABRIC_PLOGI) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Fabric PLOGI response received in state (%d). Dropping frame", + fdls_get_state(&iport->fabric)); + return; + } + if (iport->active_oxid_fabric_req != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n", + fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req); + return; + } + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + + switch (plogi_rsp->els.fl_cmd) { + case ELS_LS_ACC: + atomic64_inc(&iport->iport_stats.fabric_plogi_ls_accepts); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport fcid: 0x%x fabric PLOGI response: Accepted\n", + iport->fcid); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + iport->fabric.retry_counter = 0; + fdls_set_state(&iport->fabric, FDLS_STATE_RPN_ID); + fdls_send_rpn_id(iport); + break; + case ELS_LS_RJT: + atomic64_inc(&iport->iport_stats.fabric_plogi_ls_rejects); + if (((els_rjt->rej.er_reason == ELS_RJT_BUSY) + || (els_rjt->rej.er_reason == ELS_RJT_UNAB)) + && (iport->fabric.retry_counter < iport->max_plogi_retries)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Fabric PLOGI ELS_LS_RJT BUSY. Retry from timer routine", + iport->fcid); + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Fabric PLOGI ELS_LS_RJT. Halting discovery", + iport->fcid); + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport fcid: 0x%x Canceling fabric disc timer\n", + iport->fcid); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + iport->fabric.retry_counter = 0; + return; + } + break; + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PLOGI response not accepted: 0x%x", + plogi_rsp->els.fl_cmd); + atomic64_inc(&iport->iport_stats.fabric_plogi_misc_rejects); + break; + } +} + +static void fdls_process_fdmi_plogi_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + struct fc_std_flogi *plogi_rsp = (struct fc_std_flogi *)fchdr; + struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *)fchdr; + struct fnic_fdls_fabric_s *fdls = &iport->fabric; + struct fnic *fnic = iport->fnic; + u64 fdmi_tov; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + + if (iport->active_oxid_fdmi_plogi != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n", + fdls_get_state(fdls), oxid, iport->active_oxid_fdmi_plogi); + return; + } + + iport->fabric.fdmi_pending &= ~FDLS_FDMI_PLOGI_PENDING; + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_plogi); + + if (ntoh24(fchdr->fh_s_id) == FC_FID_MGMT_SERV) { + del_timer_sync(&iport->fabric.fdmi_timer); + iport->fabric.fdmi_pending = 0; + switch (plogi_rsp->els.fl_cmd) { + case ELS_LS_ACC: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDLS process fdmi PLOGI response status: ELS_LS_ACC\n"); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Sending fdmi registration for port 0x%x\n", + iport->fcid); + + fdls_fdmi_register_hba(iport); + fdls_fdmi_register_pa(iport); + fdmi_tov = jiffies + msecs_to_jiffies(5000); + mod_timer(&iport->fabric.fdmi_timer, + round_jiffies(fdmi_tov)); + break; + case ELS_LS_RJT: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Fabric FDMI PLOGI returned ELS_LS_RJT reason: 0x%x", + els_rjt->rej.er_reason); + + if (((els_rjt->rej.er_reason == ELS_RJT_BUSY) + || (els_rjt->rej.er_reason == ELS_RJT_UNAB)) + && (iport->fabric.fdmi_retry < 7)) { + iport->fabric.fdmi_retry++; + fdls_send_fdmi_plogi(iport); + } + break; + default: + break; + } + } +} +static void fdls_process_fdmi_reg_ack(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr, + int rsp_type) +{ + struct fnic *fnic = iport->fnic; + uint16_t oxid; + + if (!iport->fabric.fdmi_pending) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Received FDMI ack while not waiting: 0x%x\n", + FNIC_STD_GET_OX_ID(fchdr)); + return; + } + + oxid = FNIC_STD_GET_OX_ID(fchdr); + + if ((iport->active_oxid_fdmi_rhba != oxid) && + (iport->active_oxid_fdmi_rpa != oxid)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Incorrect OXID in response. oxid recvd: 0x%x, active oxids(rhba,rpa): 0x%x, 0x%x\n", + oxid, iport->active_oxid_fdmi_rhba, iport->active_oxid_fdmi_rpa); + return; + } + if (FNIC_FRAME_TYPE(oxid) == FNIC_FRAME_TYPE_FDMI_RHBA) { + iport->fabric.fdmi_pending &= ~FDLS_FDMI_REG_HBA_PENDING; + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rhba); + } else { + iport->fabric.fdmi_pending &= ~FDLS_FDMI_RPA_PENDING; + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rpa); + } + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport fcid: 0x%x: Received FDMI registration ack\n", + iport->fcid); + + if (!iport->fabric.fdmi_pending) { + del_timer_sync(&iport->fabric.fdmi_timer); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport fcid: 0x%x: Canceling FDMI timer\n", + iport->fcid); + } +} + +static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + uint32_t s_id; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + + s_id = ntoh24(FNIC_STD_GET_S_ID(fchdr)); + + if (!(s_id != FC_FID_MGMT_SERV)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received abts rsp with invalid SID: 0x%x. Dropping frame", + s_id); + return; + } + + oxid = FNIC_STD_GET_OX_ID(fchdr); + + switch (FNIC_FRAME_TYPE(oxid)) { + case FNIC_FRAME_TYPE_FDMI_PLOGI: + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_plogi); + break; + case FNIC_FRAME_TYPE_FDMI_RHBA: + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rhba); + break; + case FNIC_FRAME_TYPE_FDMI_RPA: + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rpa); + break; + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received abts rsp with invalid oxid: 0x%x. Dropping frame", + oxid); + break; + } + + del_timer_sync(&iport->fabric.fdmi_timer); + iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING; + + fdls_send_fdmi_plogi(iport); +} + +static void +fdls_process_fabric_abts_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + uint32_t s_id; + struct fc_std_abts_ba_acc *ba_acc = (struct fc_std_abts_ba_acc *)fchdr; + struct fc_std_abts_ba_rjt *ba_rjt; + uint32_t fabric_state = iport->fabric.state; + struct fnic *fnic = iport->fnic; + int frame_type; + uint16_t oxid; + + s_id = ntoh24(fchdr->fh_s_id); + ba_rjt = (struct fc_std_abts_ba_rjt *) fchdr; + + if (!((s_id == FC_FID_DIR_SERV) || (s_id == FC_FID_FLOGI) + || (s_id == FC_FID_FCTRL))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received abts rsp with invalid SID: 0x%x. Dropping frame", + s_id); + return; + } + + oxid = FNIC_STD_GET_OX_ID(fchdr); + if (iport->active_oxid_fabric_req != oxid) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received abts rsp with invalid oxid: 0x%x. Dropping frame", + oxid); + return; + } + + if (iport->fabric.timer_pending) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Canceling fabric disc timer %p\n", iport); + fnic_del_fabric_timer_sync(fnic); + } + iport->fabric.timer_pending = 0; + iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED; + + if (fchdr->fh_r_ctl == FC_RCTL_BA_ACC) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received abts rsp BA_ACC for fabric_state: %d OX_ID: 0x%x", + fabric_state, be16_to_cpu(ba_acc->acc.ba_ox_id)); + } else if (fchdr->fh_r_ctl == FC_RCTL_BA_RJT) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "BA_RJT fs: %d OX_ID: 0x%x rc: 0x%x rce: 0x%x", + fabric_state, FNIC_STD_GET_OX_ID(&ba_rjt->fchdr), + ba_rjt->rjt.br_reason, ba_rjt->rjt.br_explan); + } + + frame_type = FNIC_FRAME_TYPE(oxid); + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + + /* currently error handling/retry logic is same for ABTS BA_ACC & BA_RJT */ + switch (frame_type) { + case FNIC_FRAME_TYPE_FABRIC_FLOGI: + if (iport->fabric.retry_counter < iport->max_flogi_retries) + fdls_send_fabric_flogi(iport); + else + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Exceeded max FLOGI retries"); + break; + case FNIC_FRAME_TYPE_FABRIC_LOGO: + if (iport->fabric.retry_counter < FABRIC_LOGO_MAX_RETRY) + fdls_send_fabric_logo(iport); + break; + case FNIC_FRAME_TYPE_FABRIC_PLOGI: + if (iport->fabric.retry_counter < iport->max_plogi_retries) + fdls_send_fabric_plogi(iport); + else + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Exceeded max PLOGI retries"); + break; + case FNIC_FRAME_TYPE_FABRIC_RPN: + if (iport->fabric.retry_counter < FDLS_RETRY_COUNT) + fdls_send_rpn_id(iport); + else + /* go back to fabric Plogi */ + fnic_fdls_start_plogi(iport); + break; + case FNIC_FRAME_TYPE_FABRIC_SCR: + if (iport->fabric.retry_counter < FDLS_RETRY_COUNT) + fdls_send_scr(iport); + else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "SCR exhausted retries. Start fabric PLOGI %p", + iport); + fnic_fdls_start_plogi(iport); /* go back to fabric Plogi */ + } + break; + case FNIC_FRAME_TYPE_FABRIC_RFT: + if (iport->fabric.retry_counter < FDLS_RETRY_COUNT) + fdls_send_register_fc4_types(iport); + else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RFT exhausted retries. Start fabric PLOGI %p", + iport); + fnic_fdls_start_plogi(iport); /* go back to fabric Plogi */ + } + break; + case FNIC_FRAME_TYPE_FABRIC_RFF: + if (iport->fabric.retry_counter < FDLS_RETRY_COUNT) + fdls_send_register_fc4_features(iport); + else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RFF exhausted retries. Start fabric PLOGI %p", + iport); + fnic_fdls_start_plogi(iport); /* go back to fabric Plogi */ + } + break; + case FNIC_FRAME_TYPE_FABRIC_GPN_FT: + if (iport->fabric.retry_counter <= FDLS_RETRY_COUNT) + fdls_send_gpn_ft(iport, fabric_state); + else + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "GPN FT exhausted retries. Start fabric PLOGI %p", + iport); + break; + default: + /* + * We should not be here since we already validated rx oxid with + * our active_oxid_fabric_req + */ + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Invalid OXID/active oxid 0x%x\n", oxid); + WARN_ON(true); + return; + } +} + +static void +fdls_process_abts_req(struct fnic_iport_s *iport, struct fc_frame_header *fchdr) +{ + uint8_t *frame; + struct fc_std_abts_ba_acc *pba_acc; + uint32_t nport_id; + uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr); + struct fnic_tport_s *tport; + struct fnic *fnic = iport->fnic; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_abts_ba_acc); + + nport_id = ntoh24(fchdr->fh_s_id); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received abort from SID 0x%8x", nport_id); + + tport = fnic_find_tport_by_fcid(iport, nport_id); + if (tport) { + if (tport->active_oxid == oxid) { + tport->flags |= FNIC_FDLS_TGT_ABORT_ISSUED; + fdls_free_oxid(iport, oxid, &tport->active_oxid); + } + } + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "0x%x: Failed to allocate frame to send response for ABTS req", + iport->fcid); + return; + } + + pba_acc = (struct fc_std_abts_ba_acc *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + *pba_acc = (struct fc_std_abts_ba_acc) { + .fchdr = {.fh_r_ctl = FC_RCTL_BA_ACC, + .fh_f_ctl = {FNIC_FCP_RSP_FCTL, 0, 0}}, + .acc = {.ba_low_seq_cnt = 0, .ba_high_seq_cnt = cpu_to_be16(0xFFFF)} + }; + + FNIC_STD_SET_S_ID(pba_acc->fchdr, fchdr->fh_d_id); + FNIC_STD_SET_D_ID(pba_acc->fchdr, fchdr->fh_s_id); + FNIC_STD_SET_OX_ID(pba_acc->fchdr, FNIC_STD_GET_OX_ID(fchdr)); + FNIC_STD_SET_RX_ID(pba_acc->fchdr, FNIC_STD_GET_RX_ID(fchdr)); + + pba_acc->acc.ba_rx_id = cpu_to_be16(FNIC_STD_GET_RX_ID(fchdr)); + pba_acc->acc.ba_ox_id = cpu_to_be16(FNIC_STD_GET_OX_ID(fchdr)); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send BA ACC with oxid: 0x%x", + iport->fcid, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); +} + +static void +fdls_process_unsupported_els_req(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + uint8_t *frame; + struct fc_std_els_rjt_rsp *pls_rsp; + uint16_t oxid; + uint32_t d_id = ntoh24(fchdr->fh_d_id); + struct fnic *fnic = iport->fnic; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_els_rjt_rsp); + + if (iport->fcid != d_id) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping unsupported ELS with illegal frame bits 0x%x\n", + d_id); + atomic64_inc(&iport->iport_stats.unsupported_frames_dropped); + return; + } + + if ((iport->state != FNIC_IPORT_STATE_READY) + && (iport->state != FNIC_IPORT_STATE_FABRIC_DISC)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping unsupported ELS request in iport state: %d", + iport->state); + atomic64_inc(&iport->iport_stats.unsupported_frames_dropped); + return; + } + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send response to unsupported ELS request"); + return; + } + + pls_rsp = (struct fc_std_els_rjt_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_els_rjt_frame(frame, iport); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Process unsupported ELS request from SID: 0x%x", + iport->fcid, ntoh24(fchdr->fh_s_id)); + + /* We don't support this ELS request, send a reject */ + pls_rsp->rej.er_reason = 0x0B; + pls_rsp->rej.er_explan = 0x0; + pls_rsp->rej.er_vendor = 0x0; + + FNIC_STD_SET_S_ID(pls_rsp->fchdr, fchdr->fh_d_id); + FNIC_STD_SET_D_ID(pls_rsp->fchdr, fchdr->fh_s_id); + oxid = FNIC_STD_GET_OX_ID(fchdr); + FNIC_STD_SET_OX_ID(pls_rsp->fchdr, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); +} + +static void +fdls_process_rls_req(struct fnic_iport_s *iport, struct fc_frame_header *fchdr) +{ + uint8_t *frame; + struct fc_std_rls_acc *prls_acc_rsp; + uint16_t oxid; + struct fnic *fnic = iport->fnic; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_rls_acc); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Process RLS request %d", iport->fnic->fnic_num); + + if ((iport->state != FNIC_IPORT_STATE_READY) + && (iport->state != FNIC_IPORT_STATE_FABRIC_DISC)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received RLS req in iport state: %d. Dropping the frame.", + iport->state); + return; + } + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send RLS accept"); + return; + } + prls_acc_rsp = (struct fc_std_rls_acc *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + + FNIC_STD_SET_S_ID(prls_acc_rsp->fchdr, fchdr->fh_d_id); + FNIC_STD_SET_D_ID(prls_acc_rsp->fchdr, fchdr->fh_s_id); + + oxid = FNIC_STD_GET_OX_ID(fchdr); + FNIC_STD_SET_OX_ID(prls_acc_rsp->fchdr, oxid); + FNIC_STD_SET_RX_ID(prls_acc_rsp->fchdr, FNIC_UNASSIGNED_RXID); + + FNIC_STD_SET_F_CTL(prls_acc_rsp->fchdr, FNIC_ELS_REP_FCTL << 16); + FNIC_STD_SET_R_CTL(prls_acc_rsp->fchdr, FC_RCTL_ELS_REP); + FNIC_STD_SET_TYPE(prls_acc_rsp->fchdr, FC_TYPE_ELS); + + prls_acc_rsp->els.rls_cmd = ELS_LS_ACC; + prls_acc_rsp->els.rls_lesb.lesb_link_fail = + cpu_to_be32(iport->fnic->link_down_cnt); + + fnic_send_fcoe_frame(iport, frame, frame_size); +} + +static void +fdls_process_els_req(struct fnic_iport_s *iport, struct fc_frame_header *fchdr, + uint32_t len) +{ + uint8_t *frame; + struct fc_std_els_acc_rsp *pels_acc; + uint16_t oxid; + uint8_t *fc_payload; + uint8_t type; + struct fnic *fnic = iport->fnic; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET; + + fc_payload = (uint8_t *) fchdr + sizeof(struct fc_frame_header); + type = *fc_payload; + + if ((iport->state != FNIC_IPORT_STATE_READY) + && (iport->state != FNIC_IPORT_STATE_FABRIC_DISC)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping ELS frame type: 0x%x in iport state: %d", + type, iport->state); + return; + } + switch (type) { + case ELS_ECHO: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "sending LS_ACC for ECHO request %d\n", + iport->fnic->fnic_num); + break; + + case ELS_RRQ: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "sending LS_ACC for RRQ request %d\n", + iport->fnic->fnic_num); + break; + + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "sending LS_ACC for 0x%x ELS frame\n", type); + break; + } + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send ELS response for 0x%x", + type); + return; + } + + if (type == ELS_ECHO) { + /* Brocade sends a longer payload, copy all frame back */ + memcpy(frame, fchdr, len); + } + + pels_acc = (struct fc_std_els_acc_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_els_acc_frame(frame, iport); + + FNIC_STD_SET_D_ID(pels_acc->fchdr, fchdr->fh_s_id); + + oxid = FNIC_STD_GET_OX_ID(fchdr); + FNIC_STD_SET_OX_ID(pels_acc->fchdr, oxid); + + if (type == ELS_ECHO) + frame_size += len; + else + frame_size += sizeof(struct fc_std_els_acc_rsp); + + fnic_send_fcoe_frame(iport, frame, frame_size); +} + +static void +fdls_process_tgt_abts_rsp(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + uint32_t s_id; + struct fnic_tport_s *tport; + uint32_t tport_state; + struct fc_std_abts_ba_acc *ba_acc; + struct fc_std_abts_ba_rjt *ba_rjt; + uint16_t oxid; + struct fnic *fnic = iport->fnic; + int frame_type; + + s_id = ntoh24(fchdr->fh_s_id); + ba_acc = (struct fc_std_abts_ba_acc *)fchdr; + ba_rjt = (struct fc_std_abts_ba_rjt *)fchdr; + + tport = fnic_find_tport_by_fcid(iport, s_id); + if (!tport) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Received tgt abts rsp with invalid SID: 0x%x", s_id); + return; + } + if (tport->timer_pending) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "tport 0x%p Canceling fabric disc timer\n", tport); + fnic_del_tport_timer_sync(fnic, tport); + } + if (iport->state != FNIC_IPORT_STATE_READY) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Received tgt abts rsp in iport state(%d). Dropping.", + iport->state); + return; + } + tport->timer_pending = 0; + tport->flags &= ~FNIC_FDLS_TGT_ABORT_ISSUED; + tport_state = tport->state; + oxid = FNIC_STD_GET_OX_ID(fchdr); + + /*This abort rsp is for ADISC */ + frame_type = FNIC_FRAME_TYPE(oxid); + switch (frame_type) { + case FNIC_FRAME_TYPE_TGT_ADISC: + if (fchdr->fh_r_ctl == FC_RCTL_BA_ACC) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "OX_ID: 0x%x tgt_fcid: 0x%x rcvd tgt adisc abts resp BA_ACC", + be16_to_cpu(ba_acc->acc.ba_ox_id), + tport->fcid); + } else if (fchdr->fh_r_ctl == FC_RCTL_BA_RJT) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "ADISC BA_RJT rcvd tport_fcid: 0x%x tport_state: %d ", + tport->fcid, tport_state); + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "reason code: 0x%x reason code explanation:0x%x ", + ba_rjt->rjt.br_reason, + ba_rjt->rjt.br_explan); + } + if ((tport->retry_counter < FDLS_RETRY_COUNT) + && (fchdr->fh_r_ctl == FC_RCTL_BA_ACC)) { + fdls_free_oxid(iport, oxid, &tport->active_oxid); + fdls_send_tgt_adisc(iport, tport); + return; + } + fdls_free_oxid(iport, oxid, &tport->active_oxid); + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "ADISC not responding. Deleting target port: 0x%x", + tport->fcid); + fdls_delete_tport(iport, tport); + /* Restart discovery of targets */ + if ((iport->state == FNIC_IPORT_STATE_READY) + && (iport->fabric.state != FDLS_STATE_SEND_GPNFT) + && (iport->fabric.state != FDLS_STATE_RSCN_GPN_FT)) { + fdls_send_gpn_ft(iport, FDLS_STATE_SEND_GPNFT); + } + break; + case FNIC_FRAME_TYPE_TGT_PLOGI: + if (fchdr->fh_r_ctl == FC_RCTL_BA_ACC) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Received tgt PLOGI abts response BA_ACC tgt_fcid: 0x%x", + tport->fcid); + } else if (fchdr->fh_r_ctl == FC_RCTL_BA_RJT) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PLOGI BA_RJT received for tport_fcid: 0x%x OX_ID: 0x%x", + tport->fcid, FNIC_STD_GET_OX_ID(fchdr)); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "reason code: 0x%x reason code explanation: 0x%x", + ba_rjt->rjt.br_reason, + ba_rjt->rjt.br_explan); + } + if ((tport->retry_counter < iport->max_plogi_retries) + && (fchdr->fh_r_ctl == FC_RCTL_BA_ACC)) { + fdls_free_oxid(iport, oxid, &tport->active_oxid); + fdls_send_tgt_plogi(iport, tport); + return; + } + + fdls_free_oxid(iport, oxid, &tport->active_oxid); + fdls_delete_tport(iport, tport); + /* Restart discovery of targets */ + if ((iport->state == FNIC_IPORT_STATE_READY) + && (iport->fabric.state != FDLS_STATE_SEND_GPNFT) + && (iport->fabric.state != FDLS_STATE_RSCN_GPN_FT)) { + fdls_send_gpn_ft(iport, FDLS_STATE_SEND_GPNFT); + } + break; + case FNIC_FRAME_TYPE_TGT_PRLI: + if (fchdr->fh_r_ctl == FC_RCTL_BA_ACC) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Received tgt PRLI abts response BA_ACC", + tport->fcid); + } else if (fchdr->fh_r_ctl == FC_RCTL_BA_RJT) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PRLI BA_RJT received for tport_fcid: 0x%x OX_ID: 0x%x ", + tport->fcid, FNIC_STD_GET_OX_ID(fchdr)); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "reason code: 0x%x reason code explanation: 0x%x", + ba_rjt->rjt.br_reason, + ba_rjt->rjt.br_explan); + } + if ((tport->retry_counter < FDLS_RETRY_COUNT) + && (fchdr->fh_r_ctl == FC_RCTL_BA_ACC)) { + fdls_free_oxid(iport, oxid, &tport->active_oxid); + fdls_send_tgt_prli(iport, tport); + return; + } + fdls_free_oxid(iport, oxid, &tport->active_oxid); + fdls_send_tgt_plogi(iport, tport); /* go back to plogi */ + fdls_set_tport_state(tport, FDLS_TGT_STATE_PLOGI); + break; + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received ABTS response for unknown frame %p", iport); + break; + } + +} + +static void +fdls_process_plogi_req(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + uint8_t *frame; + struct fc_std_els_rjt_rsp *pplogi_rsp; + uint16_t oxid; + uint32_t d_id = ntoh24(fchdr->fh_d_id); + struct fnic *fnic = iport->fnic; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_els_rjt_rsp); + + if (iport->fcid != d_id) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received PLOGI with illegal frame bits. Dropping frame from 0x%x", + d_id); + return; + } + + if (iport->state != FNIC_IPORT_STATE_READY) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received PLOGI request in iport state: %d Dropping frame", + iport->state); + return; + } + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send response to PLOGI request"); + return; + } + + pplogi_rsp = (struct fc_std_els_rjt_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_els_rjt_frame(frame, iport); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: Process PLOGI request from SID: 0x%x", + iport->fcid, ntoh24(fchdr->fh_s_id)); + + /* We don't support PLOGI request, send a reject */ + pplogi_rsp->rej.er_reason = 0x0B; + pplogi_rsp->rej.er_explan = 0x0; + pplogi_rsp->rej.er_vendor = 0x0; + + FNIC_STD_SET_S_ID(pplogi_rsp->fchdr, fchdr->fh_d_id); + FNIC_STD_SET_D_ID(pplogi_rsp->fchdr, fchdr->fh_s_id); + oxid = FNIC_STD_GET_OX_ID(fchdr); + FNIC_STD_SET_OX_ID(pplogi_rsp->fchdr, oxid); + + fnic_send_fcoe_frame(iport, frame, frame_size); +} + +static void +fdls_process_logo_req(struct fnic_iport_s *iport, struct fc_frame_header *fchdr) +{ + struct fc_std_logo *logo = (struct fc_std_logo *)fchdr; + uint32_t nport_id; + uint64_t nport_name; + struct fnic_tport_s *tport; + struct fnic *fnic = iport->fnic; + uint16_t oxid; + + nport_id = ntoh24(logo->els.fl_n_port_id); + nport_name = be64_to_cpu(logo->els.fl_n_port_wwn); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Process LOGO request from fcid: 0x%x", nport_id); + + if (iport->state != FNIC_IPORT_STATE_READY) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Dropping LOGO req from 0x%x in iport state: %d", + nport_id, iport->state); + return; + } + + tport = fnic_find_tport_by_fcid(iport, nport_id); + + if (!tport) { + /* We are not logged in with the nport, log and drop... */ + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Received LOGO from an nport not logged in: 0x%x(0x%llx)", + nport_id, nport_name); + return; + } + if (tport->fcid != nport_id) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Received LOGO with invalid target port fcid: 0x%x(0x%llx)", + nport_id, nport_name); + return; + } + if (tport->timer_pending) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "tport fcid 0x%x: Canceling disc timer\n", + tport->fcid); + fnic_del_tport_timer_sync(fnic, tport); + tport->timer_pending = 0; + } + + /* got a logo in response to adisc to a target which has logged out */ + if (tport->state == FDLS_TGT_STATE_ADISC) { + tport->retry_counter = 0; + oxid = tport->active_oxid; + fdls_free_oxid(iport, oxid, &tport->active_oxid); + fdls_delete_tport(iport, tport); + fdls_send_logo_resp(iport, &logo->fchdr); + if ((iport->state == FNIC_IPORT_STATE_READY) + && (fdls_get_state(&iport->fabric) != FDLS_STATE_SEND_GPNFT) + && (fdls_get_state(&iport->fabric) != FDLS_STATE_RSCN_GPN_FT)) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Sending GPNFT in response to LOGO from Target:0x%x", + nport_id); + fdls_send_gpn_ft(iport, FDLS_STATE_SEND_GPNFT); + return; + } + } else { + fdls_delete_tport(iport, tport); + } + if (iport->state == FNIC_IPORT_STATE_READY) { + fdls_send_logo_resp(iport, &logo->fchdr); + if ((fdls_get_state(&iport->fabric) != FDLS_STATE_SEND_GPNFT) && + (fdls_get_state(&iport->fabric) != FDLS_STATE_RSCN_GPN_FT)) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Sending GPNFT in response to LOGO from Target:0x%x", + nport_id); + fdls_send_gpn_ft(iport, FDLS_STATE_SEND_GPNFT); + } + } +} + +static void +fdls_process_rscn(struct fnic_iport_s *iport, struct fc_frame_header *fchdr) +{ + struct fc_std_rscn *rscn; + struct fc_els_rscn_page *rscn_port = NULL; + int num_ports; + struct fnic_tport_s *tport, *next; + uint32_t nport_id; + uint8_t fcid[3]; + int newports = 0; + struct fnic_fdls_fabric_s *fdls = &iport->fabric; + struct fnic *fnic = iport->fnic; + int rscn_type = NOT_PC_RSCN; + uint32_t sid = ntoh24(fchdr->fh_s_id); + unsigned long reset_fnic_list_lock_flags = 0; + uint16_t rscn_payload_len; + + atomic64_inc(&iport->iport_stats.num_rscns); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDLS process RSCN %p", iport); + + if (iport->state != FNIC_IPORT_STATE_READY) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDLS RSCN received in state(%d). Dropping", + fdls_get_state(fdls)); + return; + } + + rscn = (struct fc_std_rscn *)fchdr; + rscn_payload_len = be16_to_cpu(rscn->els.rscn_plen); + + /* frame validation */ + if ((rscn_payload_len % 4 != 0) || (rscn_payload_len < 8) + || (rscn_payload_len > 1024) + || (rscn->els.rscn_page_len != 4)) { + num_ports = 0; + if ((rscn_payload_len == 0xFFFF) + && (sid == FC_FID_FCTRL)) { + rscn_type = PC_RSCN; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "pcrscn: PCRSCN received. sid: 0x%x payload len: 0x%x", + sid, rscn_payload_len); + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RSCN payload_len: 0x%x page_len: 0x%x", + rscn_payload_len, rscn->els.rscn_page_len); + /* if this happens then we need to send ADISC to all the tports. */ + list_for_each_entry_safe(tport, next, &iport->tport_list, links) { + if (tport->state == FDLS_TGT_STATE_READY) + tport->flags |= FNIC_FDLS_TPORT_SEND_ADISC; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RSCN for port id: 0x%x", tport->fcid); + } + } /* end else */ + } else { + num_ports = (rscn_payload_len - 4) / rscn->els.rscn_page_len; + rscn_port = (struct fc_els_rscn_page *)(rscn + 1); + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RSCN received for num_ports: %d payload_len: %d page_len: %d ", + num_ports, rscn_payload_len, rscn->els.rscn_page_len); + + /* + * RSCN have at least one Port_ID page , but may not have any port_id + * in it. If no port_id is specified in the Port_ID page , we send + * ADISC to all the tports + */ + + while (num_ports) { + + memcpy(fcid, rscn_port->rscn_fid, 3); + + nport_id = ntoh24(fcid); + rscn_port++; + num_ports--; + /* if this happens then we need to send ADISC to all the tports. */ + if (nport_id == 0) { + list_for_each_entry_safe(tport, next, &iport->tport_list, + links) { + if (tport->state == FDLS_TGT_STATE_READY) + tport->flags |= FNIC_FDLS_TPORT_SEND_ADISC; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RSCN for port id: 0x%x", tport->fcid); + } + break; + } + tport = fnic_find_tport_by_fcid(iport, nport_id); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "RSCN port id list: 0x%x", nport_id); + + if (!tport) { + newports++; + continue; + } + if (tport->state == FDLS_TGT_STATE_READY) + tport->flags |= FNIC_FDLS_TPORT_SEND_ADISC; + } + + if (pc_rscn_handling_feature_flag == PC_RSCN_HANDLING_FEATURE_ON && + rscn_type == PC_RSCN && fnic->role == FNIC_ROLE_FCP_INITIATOR) { + + if (fnic->pc_rscn_handling_status == PC_RSCN_HANDLING_IN_PROGRESS) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PCRSCN handling already in progress. Skip host reset: %d", + iport->fnic->fnic_num); + return; + } + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Processing PCRSCN. Queuing fnic for host reset: %d", + iport->fnic->fnic_num); + fnic->pc_rscn_handling_status = PC_RSCN_HANDLING_IN_PROGRESS; + + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + + spin_lock_irqsave(&reset_fnic_list_lock, + reset_fnic_list_lock_flags); + list_add_tail(&fnic->links, &reset_fnic_list); + spin_unlock_irqrestore(&reset_fnic_list_lock, + reset_fnic_list_lock_flags); + + queue_work(reset_fnic_work_queue, &reset_fnic_work); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDLS process RSCN sending GPN_FT: newports: %d", newports); + fdls_send_gpn_ft(iport, FDLS_STATE_RSCN_GPN_FT); + fdls_send_rscn_resp(iport, fchdr); + } +} + +void fnic_fdls_disc_start(struct fnic_iport_s *iport) +{ + struct fnic *fnic = iport->fnic; + + fc_host_fabric_name(iport->fnic->host) = 0; + fc_host_post_event(iport->fnic->host, fc_get_event_number(), + FCH_EVT_LIPRESET, 0); + + if (!iport->usefip) { + if (iport->flags & FNIC_FIRST_LINK_UP) { + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + fnic_scsi_fcpio_reset(iport->fnic); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + + iport->flags &= ~FNIC_FIRST_LINK_UP; + } + fnic_fdls_start_flogi(iport); + } else + fnic_fdls_start_plogi(iport); +} + +static void +fdls_process_adisc_req(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + struct fc_std_els_adisc *padisc_acc; + struct fc_std_els_adisc *adisc_req = (struct fc_std_els_adisc *)fchdr; + uint64_t frame_wwnn; + uint64_t frame_wwpn; + uint32_t tgt_fcid; + struct fnic_tport_s *tport; + uint8_t *fcid; + uint8_t *rjt_frame; + uint8_t *acc_frame; + struct fc_std_els_rjt_rsp *prjts_rsp; + uint16_t oxid; + struct fnic *fnic = iport->fnic; + uint16_t rjt_frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_els_rjt_rsp); + uint16_t acc_frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_std_els_adisc); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Process ADISC request %d", iport->fnic->fnic_num); + + fcid = FNIC_STD_GET_S_ID(fchdr); + tgt_fcid = ntoh24(fcid); + tport = fnic_find_tport_by_fcid(iport, tgt_fcid); + if (!tport) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "tport for fcid: 0x%x not found. Dropping ADISC req.", + tgt_fcid); + return; + } + if (iport->state != FNIC_IPORT_STATE_READY) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Dropping ADISC req from fcid: 0x%x in iport state: %d", + tgt_fcid, iport->state); + return; + } + + frame_wwnn = be64_to_cpu(adisc_req->els.adisc_wwnn); + frame_wwpn = be64_to_cpu(adisc_req->els.adisc_wwpn); + + if ((frame_wwnn != tport->wwnn) || (frame_wwpn != tport->wwpn)) { + /* send reject */ + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "ADISC req from fcid: 0x%x mismatch wwpn: 0x%llx wwnn: 0x%llx", + tgt_fcid, frame_wwpn, frame_wwnn); + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "local tport wwpn: 0x%llx wwnn: 0x%llx. Sending RJT", + tport->wwpn, tport->wwnn); + + rjt_frame = fdls_alloc_frame(iport); + if (rjt_frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate rjt_frame to send response to ADISC request"); + return; + } + + prjts_rsp = (struct fc_std_els_rjt_rsp *) (rjt_frame + FNIC_ETH_FCOE_HDRS_OFFSET); + fdls_init_els_rjt_frame(rjt_frame, iport); + + prjts_rsp->rej.er_reason = 0x03; /* logical error */ + prjts_rsp->rej.er_explan = 0x1E; /* N_port login required */ + prjts_rsp->rej.er_vendor = 0x0; + + FNIC_STD_SET_S_ID(prjts_rsp->fchdr, fchdr->fh_d_id); + FNIC_STD_SET_D_ID(prjts_rsp->fchdr, fchdr->fh_s_id); + oxid = FNIC_STD_GET_OX_ID(fchdr); + FNIC_STD_SET_OX_ID(prjts_rsp->fchdr, oxid); + + fnic_send_fcoe_frame(iport, rjt_frame, rjt_frame_size); + return; + } + + acc_frame = fdls_alloc_frame(iport); + if (acc_frame == NULL) { + FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send ADISC accept"); + return; + } + + padisc_acc = (struct fc_std_els_adisc *) (acc_frame + FNIC_ETH_FCOE_HDRS_OFFSET); + + FNIC_STD_SET_S_ID(padisc_acc->fchdr, fchdr->fh_d_id); + FNIC_STD_SET_D_ID(padisc_acc->fchdr, fchdr->fh_s_id); + + FNIC_STD_SET_F_CTL(padisc_acc->fchdr, FNIC_ELS_REP_FCTL << 16); + FNIC_STD_SET_R_CTL(padisc_acc->fchdr, FC_RCTL_ELS_REP); + FNIC_STD_SET_TYPE(padisc_acc->fchdr, FC_TYPE_ELS); + + oxid = FNIC_STD_GET_OX_ID(fchdr); + FNIC_STD_SET_OX_ID(padisc_acc->fchdr, oxid); + FNIC_STD_SET_RX_ID(padisc_acc->fchdr, FNIC_UNASSIGNED_RXID); + + padisc_acc->els.adisc_cmd = ELS_LS_ACC; + + FNIC_STD_SET_NPORT_NAME(&padisc_acc->els.adisc_wwpn, + iport->wwpn); + FNIC_STD_SET_NODE_NAME(&padisc_acc->els.adisc_wwnn, + iport->wwnn); + memcpy(padisc_acc->els.adisc_port_id, fchdr->fh_d_id, 3); + + fnic_send_fcoe_frame(iport, acc_frame, acc_frame_size); +} + +/* + * Performs a validation for all FCOE frames and return the frame type + */ +int +fnic_fdls_validate_and_get_frame_type(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr) +{ + uint8_t type; + uint8_t *fc_payload; + uint16_t oxid; + uint32_t s_id; + uint32_t d_id; + struct fnic *fnic = iport->fnic; + struct fnic_fdls_fabric_s *fabric = &iport->fabric; + int oxid_frame_type; + + oxid = FNIC_STD_GET_OX_ID(fchdr); + fc_payload = (uint8_t *) fchdr + sizeof(struct fc_frame_header); + type = *fc_payload; + s_id = ntoh24(fchdr->fh_s_id); + d_id = ntoh24(fchdr->fh_d_id); + + /* some common validation */ + if (fdls_get_state(fabric) > FDLS_STATE_FABRIC_FLOGI) { + if ((iport->fcid != d_id) || (!FNIC_FC_FRAME_CS_CTL(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "invalid frame received. Dropping frame"); + return -1; + } + } + + /* BLS ABTS response */ + if ((fchdr->fh_r_ctl == FC_RCTL_BA_ACC) + || (fchdr->fh_r_ctl == FC_RCTL_BA_RJT)) { + if (!(FNIC_FC_FRAME_TYPE_BLS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received ABTS invalid frame. Dropping frame"); + return -1; + + } + if (fdls_is_oxid_fabric_req(oxid)) { + if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received unexpected ABTS RSP(oxid:0x%x) from 0x%x. Dropping frame", + oxid, s_id); + return -1; + } + return FNIC_FABRIC_BLS_ABTS_RSP; + } else if (fdls_is_oxid_fdmi_req(oxid)) { + return FNIC_FDMI_BLS_ABTS_RSP; + } else if (fdls_is_oxid_tgt_req(oxid)) { + return FNIC_TPORT_BLS_ABTS_RSP; + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received ABTS rsp with unknown oxid(0x%x) from 0x%x. Dropping frame", + oxid, s_id); + return -1; + } + + /* BLS ABTS Req */ + if ((fchdr->fh_r_ctl == FC_RCTL_BA_ABTS) + && (FNIC_FC_FRAME_TYPE_BLS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Receiving Abort Request from s_id: 0x%x", s_id); + return FNIC_BLS_ABTS_REQ; + } + + /* unsolicited requests frames */ + if (FNIC_FC_FRAME_UNSOLICITED(fchdr)) { + switch (type) { + case ELS_LOGO: + if ((!FNIC_FC_FRAME_FCTL_FIRST_LAST_SEQINIT(fchdr)) + || (!FNIC_FC_FRAME_UNSOLICITED(fchdr)) + || (!FNIC_FC_FRAME_TYPE_ELS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received LOGO invalid frame. Dropping frame"); + return -1; + } + return FNIC_ELS_LOGO_REQ; + case ELS_RSCN: + if ((!FNIC_FC_FRAME_FCTL_FIRST_LAST_SEQINIT(fchdr)) + || (!FNIC_FC_FRAME_TYPE_ELS(fchdr)) + || (!FNIC_FC_FRAME_UNSOLICITED(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received RSCN invalid FCTL. Dropping frame"); + return -1; + } + if (s_id != FC_FID_FCTRL) + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received RSCN from target FCTL: 0x%x type: 0x%x s_id: 0x%x.", + fchdr->fh_f_ctl[0], fchdr->fh_type, s_id); + return FNIC_ELS_RSCN_REQ; + case ELS_PLOGI: + return FNIC_ELS_PLOGI_REQ; + case ELS_ECHO: + return FNIC_ELS_ECHO_REQ; + case ELS_ADISC: + return FNIC_ELS_ADISC; + case ELS_RLS: + return FNIC_ELS_RLS; + case ELS_RRQ: + return FNIC_ELS_RRQ; + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Unsupported frame (type:0x%02x) from fcid: 0x%x", + type, s_id); + return FNIC_ELS_UNSUPPORTED_REQ; + } + } + + /* solicited response from fabric or target */ + oxid_frame_type = FNIC_FRAME_TYPE(oxid); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "oxid frame code: 0x%x, oxid: 0x%x\n", oxid_frame_type, oxid); + switch (oxid_frame_type) { + case FNIC_FRAME_TYPE_FABRIC_FLOGI: + if (type == ELS_LS_ACC) { + if ((s_id != FC_FID_FLOGI) + || (!FNIC_FC_FRAME_TYPE_ELS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received unknown frame. Dropping frame"); + return -1; + } + } + return FNIC_FABRIC_FLOGI_RSP; + + case FNIC_FRAME_TYPE_FABRIC_PLOGI: + if (type == ELS_LS_ACC) { + if ((s_id != FC_FID_DIR_SERV) + || (!FNIC_FC_FRAME_TYPE_ELS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received unknown frame. Dropping frame"); + return -1; + } + } + return FNIC_FABRIC_PLOGI_RSP; + + case FNIC_FRAME_TYPE_FABRIC_SCR: + if (type == ELS_LS_ACC) { + if ((s_id != FC_FID_FCTRL) + || (!FNIC_FC_FRAME_TYPE_ELS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received unknown frame. Dropping frame"); + return -1; + } + } + return FNIC_FABRIC_SCR_RSP; + + case FNIC_FRAME_TYPE_FABRIC_RPN: + if ((s_id != FC_FID_DIR_SERV) || (!FNIC_FC_FRAME_TYPE_FC_GS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received unknown frame. Dropping frame"); + return -1; + } + return FNIC_FABRIC_RPN_RSP; + + case FNIC_FRAME_TYPE_FABRIC_RFT: + if ((s_id != FC_FID_DIR_SERV) || (!FNIC_FC_FRAME_TYPE_FC_GS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received unknown frame. Dropping frame"); + return -1; + } + return FNIC_FABRIC_RFT_RSP; + + case FNIC_FRAME_TYPE_FABRIC_RFF: + if ((s_id != FC_FID_DIR_SERV) || (!FNIC_FC_FRAME_TYPE_FC_GS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received unknown frame. Dropping frame"); + return -1; + } + return FNIC_FABRIC_RFF_RSP; + + case FNIC_FRAME_TYPE_FABRIC_GPN_FT: + if ((s_id != FC_FID_DIR_SERV) || (!FNIC_FC_FRAME_TYPE_FC_GS(fchdr))) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received unknown frame. Dropping frame"); + return -1; + } + return FNIC_FABRIC_GPN_FT_RSP; + + case FNIC_FRAME_TYPE_FABRIC_LOGO: + return FNIC_FABRIC_LOGO_RSP; + case FNIC_FRAME_TYPE_FDMI_PLOGI: + return FNIC_FDMI_PLOGI_RSP; + case FNIC_FRAME_TYPE_FDMI_RHBA: + return FNIC_FDMI_REG_HBA_RSP; + case FNIC_FRAME_TYPE_FDMI_RPA: + return FNIC_FDMI_RPA_RSP; + case FNIC_FRAME_TYPE_TGT_PLOGI: + return FNIC_TPORT_PLOGI_RSP; + case FNIC_FRAME_TYPE_TGT_PRLI: + return FNIC_TPORT_PRLI_RSP; + case FNIC_FRAME_TYPE_TGT_ADISC: + return FNIC_TPORT_ADISC_RSP; + case FNIC_FRAME_TYPE_TGT_LOGO: + if (!FNIC_FC_FRAME_TYPE_ELS(fchdr)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping Unknown frame in tport solicited exchange range type: 0x%x.", + fchdr->fh_type); + return -1; + } + return FNIC_TPORT_LOGO_RSP; + default: + /* Drop the Rx frame and log/stats it */ + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Solicited response: unknown OXID: 0x%x", oxid); + return -1; + } + + return -1; +} + +void fnic_fdls_recv_frame(struct fnic_iport_s *iport, void *rx_frame, + int len, int fchdr_offset) +{ + struct fc_frame_header *fchdr; + uint32_t s_id = 0; + uint32_t d_id = 0; + struct fnic *fnic = iport->fnic; + int frame_type; + + fchdr = (struct fc_frame_header *) ((uint8_t *) rx_frame + fchdr_offset); + s_id = ntoh24(fchdr->fh_s_id); + d_id = ntoh24(fchdr->fh_d_id); + + fnic_debug_dump_fc_frame(fnic, fchdr, len, "Incoming"); + + frame_type = + fnic_fdls_validate_and_get_frame_type(iport, fchdr); + + /*if we are in flogo drop everything else */ + if (iport->fabric.state == FDLS_STATE_FABRIC_LOGO && + frame_type != FNIC_FABRIC_LOGO_RSP) + return; + + switch (frame_type) { + case FNIC_FABRIC_FLOGI_RSP: + fdls_process_flogi_rsp(iport, fchdr, rx_frame); + break; + case FNIC_FABRIC_PLOGI_RSP: + fdls_process_fabric_plogi_rsp(iport, fchdr); + break; + case FNIC_FDMI_PLOGI_RSP: + fdls_process_fdmi_plogi_rsp(iport, fchdr); + break; + case FNIC_FABRIC_RPN_RSP: + fdls_process_rpn_id_rsp(iport, fchdr); + break; + case FNIC_FABRIC_RFT_RSP: + fdls_process_rft_id_rsp(iport, fchdr); + break; + case FNIC_FABRIC_RFF_RSP: + fdls_process_rff_id_rsp(iport, fchdr); + break; + case FNIC_FABRIC_SCR_RSP: + fdls_process_scr_rsp(iport, fchdr); + break; + case FNIC_FABRIC_GPN_FT_RSP: + fdls_process_gpn_ft_rsp(iport, fchdr, len); + break; + case FNIC_TPORT_PLOGI_RSP: + fdls_process_tgt_plogi_rsp(iport, fchdr); + break; + case FNIC_TPORT_PRLI_RSP: + fdls_process_tgt_prli_rsp(iport, fchdr); + break; + case FNIC_TPORT_ADISC_RSP: + fdls_process_tgt_adisc_rsp(iport, fchdr); + break; + case FNIC_TPORT_BLS_ABTS_RSP: + fdls_process_tgt_abts_rsp(iport, fchdr); + break; + case FNIC_TPORT_LOGO_RSP: + /* Logo response from tgt which we have deleted */ + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Logo response from tgt: 0x%x", + ntoh24(fchdr->fh_s_id)); + break; + case FNIC_FABRIC_LOGO_RSP: + fdls_process_fabric_logo_rsp(iport, fchdr); + break; + case FNIC_FABRIC_BLS_ABTS_RSP: + fdls_process_fabric_abts_rsp(iport, fchdr); + break; + case FNIC_FDMI_BLS_ABTS_RSP: + fdls_process_fdmi_abts_rsp(iport, fchdr); + break; + case FNIC_BLS_ABTS_REQ: + fdls_process_abts_req(iport, fchdr); + break; + case FNIC_ELS_UNSUPPORTED_REQ: + fdls_process_unsupported_els_req(iport, fchdr); + break; + case FNIC_ELS_PLOGI_REQ: + fdls_process_plogi_req(iport, fchdr); + break; + case FNIC_ELS_RSCN_REQ: + fdls_process_rscn(iport, fchdr); + break; + case FNIC_ELS_LOGO_REQ: + fdls_process_logo_req(iport, fchdr); + break; + case FNIC_ELS_RRQ: + case FNIC_ELS_ECHO_REQ: + fdls_process_els_req(iport, fchdr, len); + break; + case FNIC_ELS_ADISC: + fdls_process_adisc_req(iport, fchdr); + break; + case FNIC_ELS_RLS: + fdls_process_rls_req(iport, fchdr); + break; + case FNIC_FDMI_REG_HBA_RSP: + case FNIC_FDMI_RPA_RSP: + fdls_process_fdmi_reg_ack(iport, fchdr, frame_type); + break; + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "s_id: 0x%x d_did: 0x%x", s_id, d_id); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received unknown FCoE frame of len: %d. Dropping frame", len); + break; + } +} + +void fnic_fdls_disc_init(struct fnic_iport_s *iport) +{ + fdls_reset_oxid_pool(iport); + fdls_set_state((&iport->fabric), FDLS_STATE_INIT); +} + +void fnic_fdls_link_down(struct fnic_iport_s *iport) +{ + struct fnic_tport_s *tport, *next; + struct fnic *fnic = iport->fnic; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS processing link down", iport->fcid); + + fdls_set_state((&iport->fabric), FDLS_STATE_LINKDOWN); + iport->fabric.flags = 0; + + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + fnic_scsi_fcpio_reset(iport->fnic); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + list_for_each_entry_safe(tport, next, &iport->tport_list, links) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "removing rport: 0x%x", tport->fcid); + fdls_delete_tport(iport, tport); + } + + if ((fnic_fdmi_support == 1) && (iport->fabric.fdmi_pending > 0)) { + del_timer_sync(&iport->fabric.fdmi_timer); + iport->fabric.fdmi_pending = 0; + } + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS finish processing link down", iport->fcid); +} diff --git a/drivers/scsi/fnic/fdls_fc.h b/drivers/scsi/fnic/fdls_fc.h new file mode 100644 index 000000000000..012f43afd083 --- /dev/null +++ b/drivers/scsi/fnic/fdls_fc.h @@ -0,0 +1,253 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2008 Cisco Systems, Inc. All rights reserved. + * Copyright 2007 Nuova Systems, Inc. All rights reserved. + */ + +#ifndef _FDLS_FC_H_ +#define _FDLS_FC_H_ + +/* This file contains the declarations for FC fabric services + * and target discovery + * + * Request and Response for + * 1. FLOGI + * 2. PLOGI to Fabric Controller + * 3. GPN_ID, GPN_FT + * 4. RSCN + * 5. PLOGI to Target + * 6. PRLI to Target + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define FDLS_MIN_FRAMES (32) +#define FDLS_MIN_FRAME_ELEM (4) +#define FNIC_FCP_SP_RD_XRDY_DIS 0x00000002 +#define FNIC_FCP_SP_TARGET 0x00000010 +#define FNIC_FCP_SP_INITIATOR 0x00000020 +#define FNIC_FCP_SP_CONF_CMPL 0x00000080 +#define FNIC_FCP_SP_RETRY 0x00000100 + +#define FNIC_FC_CONCUR_SEQS (0xFF) +#define FNIC_FC_RO_INFO (0x1F) + +/* Little Endian */ +#define FNIC_UNASSIGNED_OXID (0xffff) +#define FNIC_UNASSIGNED_RXID (0xffff) +#define FNIC_ELS_REQ_FCTL (0x000029) +#define FNIC_ELS_REP_FCTL (0x000099) + +#define FNIC_FCP_RSP_FCTL (0x000099) +#define FNIC_REQ_ABTS_FCTL (0x000009) + +#define FNIC_FC_PH_VER_HI (0x20) +#define FNIC_FC_PH_VER_LO (0x20) +#define FNIC_FC_PH_VER (0x2020) +#define FNIC_FC_B2B_CREDIT (0x0A) +#define FNIC_FC_B2B_RDF_SZ (0x0800) + +#define FNIC_LOGI_RDF_SIZE(_logi) ((_logi).fl_csp.sp_bb_data) +#define FNIC_LOGI_R_A_TOV(_logi) ((_logi).fl_csp.sp_r_a_tov) +#define FNIC_LOGI_E_D_TOV(_logi) ((_logi).fl_csp.sp_e_d_tov) +#define FNIC_LOGI_FEATURES(_logi) (be16_to_cpu((_logi).fl_csp.sp_features)) +#define FNIC_LOGI_PORT_NAME(_logi) ((_logi).fl_wwpn) +#define FNIC_LOGI_NODE_NAME(_logi) ((_logi).fl_wwnn) + +#define FNIC_LOGI_SET_RDF_SIZE(_logi, _rdf_size) \ + (FNIC_LOGI_RDF_SIZE(_logi) = cpu_to_be16(_rdf_size)) +#define FNIC_LOGI_SET_E_D_TOV(_logi, _e_d_tov) \ + (FNIC_LOGI_E_D_TOV(_logi) = cpu_to_be32(_e_d_tov)) +#define FNIC_LOGI_SET_R_A_TOV(_logi, _r_a_tov) \ + (FNIC_LOGI_R_A_TOV(_logi) = cpu_to_be32(_r_a_tov)) + +#define FNIC_STD_SET_S_ID(_fchdr, _sid) memcpy((_fchdr).fh_s_id, _sid, 3) +#define FNIC_STD_SET_D_ID(_fchdr, _did) memcpy((_fchdr).fh_d_id, _did, 3) +#define FNIC_STD_SET_OX_ID(_fchdr, _oxid) ((_fchdr).fh_ox_id = cpu_to_be16(_oxid)) +#define FNIC_STD_SET_RX_ID(_fchdr, _rxid) ((_fchdr).fh_rx_id = cpu_to_be16(_rxid)) + +#define FNIC_STD_SET_R_CTL(_fchdr, _rctl) ((_fchdr).fh_r_ctl = _rctl) +#define FNIC_STD_SET_TYPE(_fchdr, _type) ((_fchdr).fh_type = _type) +#define FNIC_STD_SET_F_CTL(_fchdr, _fctl) \ + put_unaligned_be24(_fctl, &((_fchdr).fh_f_ctl)) + +#define FNIC_STD_SET_NPORT_NAME(_ptr, _wwpn) put_unaligned_be64(_wwpn, _ptr) +#define FNIC_STD_SET_NODE_NAME(_ptr, _wwnn) put_unaligned_be64(_wwnn, _ptr) +#define FNIC_STD_SET_PORT_ID(__req, __portid) \ + memcpy(__req.fr_fid.fp_fid, __portid, 3) +#define FNIC_STD_SET_PORT_NAME(_req, _pName) \ + (put_unaligned_be64(_pName, &_req.fr_wwn)) + +#define FNIC_STD_GET_OX_ID(_fchdr) (be16_to_cpu((_fchdr)->fh_ox_id)) +#define FNIC_STD_GET_RX_ID(_fchdr) (be16_to_cpu((_fchdr)->fh_rx_id)) +#define FNIC_STD_GET_S_ID(_fchdr) ((_fchdr)->fh_s_id) +#define FNIC_STD_GET_D_ID(_fchdr) ((_fchdr)->fh_d_id) +#define FNIC_STD_GET_TYPE(_fchdr) ((_fchdr)->fh_type) +#define FNIC_STD_GET_F_CTL(_fchdr) ((_fchdr)->fh_f_ctl) +#define FNIC_STD_GET_R_CTL(_fchdr) ((_fchdr)->fh_r_ctl) + +#define FNIC_STD_GET_FC_CT_CMD(__fcct_hdr) (be16_to_cpu(__fcct_hdr->ct_cmd)) + +#define FNIC_FCOE_MAX_FRAME_SZ (2048) +#define FNIC_FCOE_MIN_FRAME_SZ (280) +#define FNIC_FC_MAX_PAYLOAD_LEN (2048) +#define FNIC_MIN_DATA_FIELD_SIZE (256) + +#define FNIC_FC_EDTOV_NSEC (0x400) +#define FNIC_NSEC_TO_MSEC (0x1000000) +#define FCP_PRLI_FUNC_TARGET (0x0010) + +#define FNIC_FC_R_CTL_SOLICITED_DATA (0x21) +#define FNIC_FC_F_CTL_LAST_END_SEQ (0x98) +#define FNIC_FC_F_CTL_LAST_END_SEQ_INT (0x99) +#define FNIC_FC_F_CTL_FIRST_LAST_SEQINIT (0x29) +#define FNIC_FC_R_CTL_FC4_SCTL (0x03) +#define FNIC_FC_CS_CTL (0x00) + +#define FNIC_FC_FRAME_UNSOLICITED(_fchdr) \ + (_fchdr->fh_r_ctl == FC_RCTL_ELS_REQ) +#define FNIC_FC_FRAME_SOLICITED_DATA(_fchdr) \ + (_fchdr->fh_r_ctl == FNIC_FC_R_CTL_SOLICITED_DATA) +#define FNIC_FC_FRAME_SOLICITED_CTRL_REPLY(_fchdr) \ + (_fchdr->fh_r_ctl == FC_RCTL_ELS_REP) +#define FNIC_FC_FRAME_FCTL_LAST_END_SEQ(_fchdr) \ + (_fchdr->fh_f_ctl[0] == FNIC_FC_F_CTL_LAST_END_SEQ) +#define FNIC_FC_FRAME_FCTL_LAST_END_SEQ_INT(_fchdr) \ + (_fchdr->fh_f_ctl[0] == FNIC_FC_F_CTL_LAST_END_SEQ_INT) +#define FNIC_FC_FRAME_FCTL_FIRST_LAST_SEQINIT(_fchdr) \ + (_fchdr->fh_f_ctl[0] == FNIC_FC_F_CTL_FIRST_LAST_SEQINIT) +#define FNIC_FC_FRAME_FC4_SCTL(_fchdr) \ + (_fchdr->fh_r_ctl == FNIC_FC_R_CTL_FC4_SCTL) +#define FNIC_FC_FRAME_TYPE_BLS(_fchdr) (_fchdr->fh_type == FC_TYPE_BLS) +#define FNIC_FC_FRAME_TYPE_ELS(_fchdr) (_fchdr->fh_type == FC_TYPE_ELS) +#define FNIC_FC_FRAME_TYPE_FC_GS(_fchdr) (_fchdr->fh_type == FC_TYPE_CT) +#define FNIC_FC_FRAME_CS_CTL(_fchdr) (_fchdr->fh_cs_ctl == FNIC_FC_CS_CTL) + +#define FNIC_FC_C3_RDF (0xfff) +#define FNIC_FC_PLOGI_RSP_RDF(_plogi_rsp) \ + (min(_plogi_rsp->u.csp_plogi.b2b_rdf_size, \ + (_plogi_rsp->spc3[4] & FNIC_FC_C3_RDF))) +#define FNIC_FC_PLOGI_RSP_CONCUR_SEQ(_plogi_rsp) \ + (min((uint16_t) (be16_to_cpu(_plogi_rsp->els.fl_csp.sp_tot_seq)), \ + (uint16_t) (be16_to_cpu(_plogi_rsp->els.fl_cssp[2].cp_con_seq) & 0xff))) + +/* FLOGI/PLOGI struct */ +struct fc_std_flogi { + struct fc_frame_header fchdr; + struct fc_els_flogi els; +} __packed; + +struct fc_std_els_acc_rsp { + struct fc_frame_header fchdr; + struct fc_els_ls_acc acc; +} __packed; + +struct fc_std_els_rjt_rsp { + struct fc_frame_header fchdr; + struct fc_els_ls_rjt rej; +} __packed; + +struct fc_std_els_adisc { + struct fc_frame_header fchdr; + struct fc_els_adisc els; +} __packed; + +struct fc_std_rls_acc { + struct fc_frame_header fchdr; + struct fc_els_rls_resp els; +} __packed; + +struct fc_std_abts_ba_acc { + struct fc_frame_header fchdr; + struct fc_ba_acc acc; +} __packed; + +struct fc_std_abts_ba_rjt { + struct fc_frame_header fchdr; + struct fc_ba_rjt rjt; +} __packed; + +struct fc_std_els_prli { + struct fc_frame_header fchdr; + struct fc_els_prli els_prli; + struct fc_els_spp sp; +} __packed; + +struct fc_std_rpn_id { + struct fc_frame_header fchdr; + struct fc_ct_hdr fc_std_ct_hdr; + struct fc_ns_rn_id rpn_id; +} __packed; + +struct fc_std_fdmi_rhba { + struct fc_frame_header fchdr; + struct fc_ct_hdr fc_std_ct_hdr; + struct fc_fdmi_rhba rhba; +} __packed; + +struct fc_std_fdmi_rpa { + struct fc_frame_header fchdr; + struct fc_ct_hdr fc_std_ct_hdr; + struct fc_fdmi_rpa rpa; +} __packed; + +struct fc_std_rft_id { + struct fc_frame_header fchdr; + struct fc_ct_hdr fc_std_ct_hdr; + struct fc_ns_rft_id rft_id; +} __packed; + +struct fc_std_rff_id { + struct fc_frame_header fchdr; + struct fc_ct_hdr fc_std_ct_hdr; + struct fc_ns_rff_id rff_id; +} __packed; + +struct fc_std_gpn_ft { + struct fc_frame_header fchdr; + struct fc_ct_hdr fc_std_ct_hdr; + struct fc_ns_gid_ft gpn_ft; +} __packed; + +/* Accept CT_IU for GPN_FT */ +struct fc_gpn_ft_rsp_iu { + uint8_t ctrl; + uint8_t fcid[3]; + uint32_t rsvd; + __be64 wwpn; +} __packed; + +struct fc_std_rls { + struct fc_frame_header fchdr; + struct fc_els_rls els; +} __packed; + +struct fc_std_scr { + struct fc_frame_header fchdr; + struct fc_els_scr scr; +} __packed; + +struct fc_std_rscn { + struct fc_frame_header fchdr; + struct fc_els_rscn els; +} __packed; + +struct fc_std_logo { + struct fc_frame_header fchdr; + struct fc_els_logo els; +} __packed; + +#define FNIC_ETH_FCOE_HDRS_OFFSET \ + (sizeof(struct ethhdr) + sizeof(struct fcoe_hdr)) + +#endif /* _FDLS_FC_H */ diff --git a/drivers/scsi/fnic/fip.c b/drivers/scsi/fnic/fip.c new file mode 100644 index 000000000000..7bb85949033f --- /dev/null +++ b/drivers/scsi/fnic/fip.c @@ -0,0 +1,1005 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2008 Cisco Systems, Inc. All rights reserved. + * Copyright 2007 Nuova Systems, Inc. All rights reserved. + */ +#include "fnic.h" +#include "fip.h" +#include + +#define FIP_FNIC_RESET_WAIT_COUNT 15 + +/** + * fnic_fcoe_reset_vlans - Free up the list of discovered vlans + * @fnic: Handle to fnic driver instance + */ +void fnic_fcoe_reset_vlans(struct fnic *fnic) +{ + unsigned long flags; + struct fcoe_vlan *vlan, *next; + + spin_lock_irqsave(&fnic->vlans_lock, flags); + if (!list_empty(&fnic->vlan_list)) { + list_for_each_entry_safe(vlan, next, &fnic->vlan_list, list) { + list_del(&vlan->list); + kfree(vlan); + } + } + + spin_unlock_irqrestore(&fnic->vlans_lock, flags); + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Reset vlan complete\n"); +} + +/** + * fnic_fcoe_send_vlan_req - Send FIP vlan request to all FCFs MAC + * @fnic: Handle to fnic driver instance + */ +void fnic_fcoe_send_vlan_req(struct fnic *fnic) +{ + uint8_t *frame; + struct fnic_iport_s *iport = &fnic->iport; + struct fnic_stats *fnic_stats = &fnic->fnic_stats; + u64 vlan_tov; + struct fip_vlan_req *pvlan_req; + uint16_t frame_size = sizeof(struct fip_vlan_req); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send VLAN req"); + return; + } + + fnic_fcoe_reset_vlans(fnic); + + fnic->set_vlan(fnic, 0); + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "set vlan done\n"); + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "got MAC 0x%x:%x:%x:%x:%x:%x\n", iport->hwmac[0], + iport->hwmac[1], iport->hwmac[2], iport->hwmac[3], + iport->hwmac[4], iport->hwmac[5]); + + pvlan_req = (struct fip_vlan_req *) frame; + *pvlan_req = (struct fip_vlan_req) { + .eth = {.h_dest = FCOE_ALL_FCFS_MAC, + .h_proto = cpu_to_be16(ETH_P_FIP)}, + .fip = {.fip_ver = FIP_VER_ENCAPS(FIP_VER), + .fip_op = cpu_to_be16(FIP_OP_VLAN), + .fip_subcode = FIP_SC_REQ, + .fip_dl_len = cpu_to_be16(FIP_VLAN_REQ_LEN)}, + .mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC, + .fip_dlen = 2}} + }; + + memcpy(pvlan_req->eth.h_source, iport->hwmac, ETH_ALEN); + memcpy(pvlan_req->mac_desc.fd_mac, iport->hwmac, ETH_ALEN); + + atomic64_inc(&fnic_stats->vlan_stats.vlan_disc_reqs); + + iport->fip.state = FDLS_FIP_VLAN_DISCOVERY_STARTED; + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Send VLAN req\n"); + fnic_send_fip_frame(iport, frame, frame_size); + + vlan_tov = jiffies + msecs_to_jiffies(FCOE_CTLR_FIPVLAN_TOV); + mod_timer(&fnic->retry_fip_timer, round_jiffies(vlan_tov)); + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fip timer set\n"); +} + +/** + * fnic_fcoe_process_vlan_resp - Processes the vlan response from one FCF and + * populates VLAN list. + * @fnic: Handle to fnic driver instance + * @fiph: Received FIP frame + * + * Will wait for responses from multiple FCFs until timeout. + */ +void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct fip_header *fiph) +{ + struct fip_vlan_notif *vlan_notif = (struct fip_vlan_notif *)fiph; + + struct fnic_stats *fnic_stats = &fnic->fnic_stats; + u16 vid; + int num_vlan = 0; + int cur_desc, desc_len; + struct fcoe_vlan *vlan; + struct fip_vlan_desc *vlan_desc; + unsigned long flags; + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic 0x%p got vlan resp\n", fnic); + + desc_len = be16_to_cpu(vlan_notif->fip.fip_dl_len); + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "desc_len %d\n", desc_len); + + spin_lock_irqsave(&fnic->vlans_lock, flags); + + cur_desc = 0; + while (desc_len > 0) { + vlan_desc = + (struct fip_vlan_desc *)(((char *)vlan_notif->vlans_desc) + + cur_desc * 4); + + if (vlan_desc->fd_desc.fip_dtype == FIP_DT_VLAN) { + if (vlan_desc->fd_desc.fip_dlen != 1) { + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, + "Invalid descriptor length(%x) in VLan response\n", + vlan_desc->fd_desc.fip_dlen); + + } + num_vlan++; + vid = be16_to_cpu(vlan_desc->fd_vlan); + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, + "process_vlan_resp: FIP VLAN %d\n", vid); + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + + if (!vlan) { + /* retry from timer */ + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, + "Mem Alloc failure\n"); + spin_unlock_irqrestore(&fnic->vlans_lock, + flags); + goto out; + } + vlan->vid = vid & 0x0fff; + vlan->state = FIP_VLAN_AVAIL; + list_add_tail(&vlan->list, &fnic->vlan_list); + break; + } + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, + "Invalid descriptor type(%x) in VLan response\n", + vlan_desc->fd_desc.fip_dtype); + /* + * Note : received a type=2 descriptor here i.e. FIP + * MAC Address Descriptor + */ + cur_desc += vlan_desc->fd_desc.fip_dlen; + desc_len -= vlan_desc->fd_desc.fip_dlen; + } + + /* any VLAN descriptors present ? */ + if (num_vlan == 0) { + atomic64_inc(&fnic_stats->vlan_stats.resp_withno_vlanID); + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic 0x%p No VLAN descriptors in FIP VLAN response\n", + fnic); + } + + spin_unlock_irqrestore(&fnic->vlans_lock, flags); + + out: + return; +} + +/** + * fnic_fcoe_start_fcf_discovery - Start FIP FCF discovery in a selected vlan + * @fnic: Handle to fnic driver instance + */ +void fnic_fcoe_start_fcf_discovery(struct fnic *fnic) +{ + uint8_t *frame; + struct fnic_iport_s *iport = &fnic->iport; + u64 fcs_tov; + struct fip_discovery *pdisc_sol; + uint16_t frame_size = sizeof(struct fip_discovery); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to start FCF discovery"); + return; + } + + memset(iport->selected_fcf.fcf_mac, 0, ETH_ALEN); + + pdisc_sol = (struct fip_discovery *) frame; + *pdisc_sol = (struct fip_discovery) { + .eth = {.h_dest = FCOE_ALL_FCFS_MAC, + .h_proto = cpu_to_be16(ETH_P_FIP)}, + .fip = { + .fip_ver = FIP_VER_ENCAPS(FIP_VER), .fip_op = cpu_to_be16(FIP_OP_DISC), + .fip_subcode = FIP_SC_REQ, .fip_dl_len = cpu_to_be16(FIP_DISC_SOL_LEN), + .fip_flags = cpu_to_be16(FIP_FL_FPMA)}, + .mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC, .fip_dlen = 2}}, + .name_desc = {.fd_desc = {.fip_dtype = FIP_DT_NAME, .fip_dlen = 3}}, + .fcoe_desc = {.fd_desc = {.fip_dtype = FIP_DT_FCOE_SIZE, .fip_dlen = 1}, + .fd_size = cpu_to_be16(FCOE_MAX_SIZE)} + }; + + memcpy(pdisc_sol->eth.h_source, iport->hwmac, ETH_ALEN); + memcpy(pdisc_sol->mac_desc.fd_mac, iport->hwmac, ETH_ALEN); + iport->selected_fcf.fcf_priority = 0xFF; + + FNIC_STD_SET_NODE_NAME(&pdisc_sol->name_desc.fd_wwn, iport->wwnn); + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Start FCF discovery\n"); + fnic_send_fip_frame(iport, frame, frame_size); + + iport->fip.state = FDLS_FIP_FCF_DISCOVERY_STARTED; + + fcs_tov = jiffies + msecs_to_jiffies(FCOE_CTLR_FCS_TOV); + mod_timer(&fnic->retry_fip_timer, round_jiffies(fcs_tov)); +} + +/** + * fnic_fcoe_fip_discovery_resp - Processes FCF advertisements. + * @fnic: Handle to fnic driver instance + * @fiph: Received frame + * + * FCF advertisements can be: + * solicited - Sent in response of a discover FCF FIP request + * Store the information of the FCF with highest priority. + * Wait until timeout in case of multiple FCFs. + * + * unsolicited - Sent periodically by the FCF for keep alive. + * If FLOGI is in progress or completed and the advertisement is + * received by our selected FCF, refresh the keep alive timer. + */ +void fnic_fcoe_fip_discovery_resp(struct fnic *fnic, struct fip_header *fiph) +{ + struct fnic_iport_s *iport = &fnic->iport; + struct fip_disc_adv *disc_adv = (struct fip_disc_adv *)fiph; + u64 fcs_ka_tov; + u64 tov; + int fka_has_changed; + + switch (iport->fip.state) { + case FDLS_FIP_FCF_DISCOVERY_STARTED: + if (be16_to_cpu(disc_adv->fip.fip_flags) & FIP_FL_SOL) { + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, + "fnic 0x%p Solicited adv\n", fnic); + + if ((disc_adv->prio_desc.fd_pri < + iport->selected_fcf.fcf_priority) + && (be16_to_cpu(disc_adv->fip.fip_flags) & FIP_FL_AVAIL)) { + + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, + "fnic 0x%p FCF Available\n", fnic); + memcpy(iport->selected_fcf.fcf_mac, + disc_adv->mac_desc.fd_mac, ETH_ALEN); + iport->selected_fcf.fcf_priority = + disc_adv->prio_desc.fd_pri; + iport->selected_fcf.fka_adv_period = + be32_to_cpu(disc_adv->fka_adv_desc.fd_fka_period); + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, "adv time %d", + iport->selected_fcf.fka_adv_period); + iport->selected_fcf.ka_disabled = + (disc_adv->fka_adv_desc.fd_flags & 1); + } + } + break; + case FDLS_FIP_FLOGI_STARTED: + case FDLS_FIP_FLOGI_COMPLETE: + if (!(be16_to_cpu(disc_adv->fip.fip_flags) & FIP_FL_SOL)) { + /* same fcf */ + if (memcmp + (iport->selected_fcf.fcf_mac, + disc_adv->mac_desc.fd_mac, ETH_ALEN) == 0) { + if (iport->selected_fcf.fka_adv_period != + be32_to_cpu(disc_adv->fka_adv_desc.fd_fka_period)) { + iport->selected_fcf.fka_adv_period = + be32_to_cpu(disc_adv->fka_adv_desc.fd_fka_period); + FNIC_FIP_DBG(KERN_INFO, + fnic->host, + fnic->fnic_num, + "change fka to %d", + iport->selected_fcf.fka_adv_period); + } + + fka_has_changed = + (iport->selected_fcf.ka_disabled == 1) + && ((disc_adv->fka_adv_desc.fd_flags & 1) == + 0); + + iport->selected_fcf.ka_disabled = + (disc_adv->fka_adv_desc.fd_flags & 1); + if (!((iport->selected_fcf.ka_disabled) + || (iport->selected_fcf.fka_adv_period == + 0))) { + + fcs_ka_tov = jiffies + + 3 + * + msecs_to_jiffies(iport->selected_fcf.fka_adv_period); + mod_timer(&fnic->fcs_ka_timer, + round_jiffies(fcs_ka_tov)); + } else { + if (timer_pending(&fnic->fcs_ka_timer)) + del_timer_sync(&fnic->fcs_ka_timer); + } + + if (fka_has_changed) { + if (iport->selected_fcf.fka_adv_period != 0) { + tov = + jiffies + + msecs_to_jiffies( + iport->selected_fcf.fka_adv_period); + mod_timer(&fnic->enode_ka_timer, + round_jiffies(tov)); + + tov = + jiffies + + msecs_to_jiffies + (FIP_VN_KA_PERIOD); + mod_timer(&fnic->vn_ka_timer, + round_jiffies(tov)); + } + } + } + } + break; + default: + break; + } /* end switch */ +} + +/** + * fnic_fcoe_start_flogi - Send FIP FLOGI to the selected FCF + * @fnic: Handle to fnic driver instance + */ +void fnic_fcoe_start_flogi(struct fnic *fnic) +{ + uint8_t *frame; + struct fnic_iport_s *iport = &fnic->iport; + struct fip_flogi *pflogi_req; + u64 flogi_tov; + uint16_t oxid; + uint16_t frame_size = sizeof(struct fip_flogi); + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to start FIP FLOGI"); + return; + } + + pflogi_req = (struct fip_flogi *) frame; + *pflogi_req = (struct fip_flogi) { + .eth = { + .h_proto = cpu_to_be16(ETH_P_FIP)}, + .fip = { + .fip_ver = FIP_VER_ENCAPS(FIP_VER), + .fip_op = cpu_to_be16(FIP_OP_LS), + .fip_subcode = FIP_SC_REQ, + .fip_dl_len = cpu_to_be16(FIP_FLOGI_LEN), + .fip_flags = cpu_to_be16(FIP_FL_FPMA)}, + .flogi_desc = { + .fd_desc = {.fip_dtype = FIP_DT_FLOGI, .fip_dlen = 36}, + .flogi = { + .fchdr = { + .fh_r_ctl = FC_RCTL_ELS_REQ, + .fh_d_id = {0xFF, 0xFF, 0xFE}, + .fh_type = FC_TYPE_ELS, + .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}, + .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)}, + .els = { + .fl_cmd = ELS_FLOGI, + .fl_csp = { + .sp_hi_ver = + FNIC_FC_PH_VER_HI, + .sp_lo_ver = + FNIC_FC_PH_VER_LO, + .sp_bb_cred = + cpu_to_be16 + (FNIC_FC_B2B_CREDIT), + .sp_bb_data = + cpu_to_be16 + (FNIC_FC_B2B_RDF_SZ)}, + .fl_cssp[2].cp_class = + cpu_to_be16(FC_CPC_VALID | FC_CPC_SEQ) + }, + } + }, + .mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC, .fip_dlen = 2}} + }; + + memcpy(pflogi_req->eth.h_source, iport->hwmac, ETH_ALEN); + if (iport->usefip) + memcpy(pflogi_req->eth.h_dest, iport->selected_fcf.fcf_mac, + ETH_ALEN); + + oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_FLOGI, + &iport->active_oxid_fabric_req); + if (oxid == FNIC_UNASSIGNED_OXID) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Failed to allocate OXID to send FIP FLOGI"); + mempool_free(frame, fnic->frame_pool); + return; + } + FNIC_STD_SET_OX_ID(pflogi_req->flogi_desc.flogi.fchdr, oxid); + + FNIC_STD_SET_NPORT_NAME(&pflogi_req->flogi_desc.flogi.els.fl_wwpn, + iport->wwpn); + FNIC_STD_SET_NODE_NAME(&pflogi_req->flogi_desc.flogi.els.fl_wwnn, + iport->wwnn); + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FIP start FLOGI\n"); + fnic_send_fip_frame(iport, frame, frame_size); + iport->fip.flogi_retry++; + + iport->fip.state = FDLS_FIP_FLOGI_STARTED; + flogi_tov = jiffies + msecs_to_jiffies(fnic->config.flogi_timeout); + mod_timer(&fnic->retry_fip_timer, round_jiffies(flogi_tov)); +} + +/** + * fnic_fcoe_process_flogi_resp - Processes FLOGI response from FCF. + * @fnic: Handle to fnic driver instance + * @fiph: Received frame + * + * If successful save assigned fc_id and MAC, program firmware + * and start fdls discovery, else restart vlan discovery. + */ +void fnic_fcoe_process_flogi_resp(struct fnic *fnic, struct fip_header *fiph) +{ + struct fnic_iport_s *iport = &fnic->iport; + struct fip_flogi_rsp *flogi_rsp = (struct fip_flogi_rsp *)fiph; + int desc_len; + uint32_t s_id; + int frame_type; + uint16_t oxid; + + struct fnic_stats *fnic_stats = &fnic->fnic_stats; + struct fc_frame_header *fchdr = &flogi_rsp->rsp_desc.flogi.fchdr; + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic 0x%p FIP FLOGI rsp\n", fnic); + desc_len = be16_to_cpu(flogi_rsp->fip.fip_dl_len); + if (desc_len != 38) { + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Invalid Descriptor List len (%x). Dropping frame\n", + desc_len); + return; + } + + if (!((flogi_rsp->rsp_desc.fd_desc.fip_dtype == 7) + && (flogi_rsp->rsp_desc.fd_desc.fip_dlen == 36)) + || !((flogi_rsp->mac_desc.fd_desc.fip_dtype == 2) + && (flogi_rsp->mac_desc.fd_desc.fip_dlen == 2))) { + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping frame invalid type and len mix\n"); + return; + } + + frame_type = fnic_fdls_validate_and_get_frame_type(iport, fchdr); + + s_id = ntoh24(fchdr->fh_s_id); + if ((fchdr->fh_f_ctl[0] != 0x98) + || (fchdr->fh_r_ctl != 0x23) + || (s_id != FC_FID_FLOGI) + || (frame_type != FNIC_FABRIC_FLOGI_RSP) + || (fchdr->fh_type != 0x01)) { + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping invalid frame: s_id %x F %x R %x t %x OX_ID %x\n", + s_id, fchdr->fh_f_ctl[0], fchdr->fh_r_ctl, + fchdr->fh_type, FNIC_STD_GET_OX_ID(fchdr)); + return; + } + + if (iport->fip.state == FDLS_FIP_FLOGI_STARTED) { + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic 0x%p rsp for pending FLOGI\n", fnic); + + oxid = FNIC_STD_GET_OX_ID(fchdr); + fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req); + del_timer_sync(&fnic->retry_fip_timer); + + if ((be16_to_cpu(flogi_rsp->fip.fip_dl_len) == FIP_FLOGI_LEN) + && (flogi_rsp->rsp_desc.flogi.els.fl_cmd == ELS_LS_ACC)) { + + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, + "fnic 0x%p FLOGI success\n", fnic); + memcpy(iport->fpma, flogi_rsp->mac_desc.fd_mac, ETH_ALEN); + iport->fcid = + ntoh24(flogi_rsp->rsp_desc.flogi.fchdr.fh_d_id); + + iport->r_a_tov = + be32_to_cpu(flogi_rsp->rsp_desc.flogi.els.fl_csp.sp_r_a_tov); + iport->e_d_tov = + be32_to_cpu(flogi_rsp->rsp_desc.flogi.els.fl_csp.sp_e_d_tov); + memcpy(fnic->iport.fcfmac, iport->selected_fcf.fcf_mac, + ETH_ALEN); + vnic_dev_add_addr(fnic->vdev, flogi_rsp->mac_desc.fd_mac); + + if (fnic_fdls_register_portid(iport, iport->fcid, NULL) + != 0) { + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, + "fnic 0x%p flogi registration failed\n", + fnic); + return; + } + + iport->fip.state = FDLS_FIP_FLOGI_COMPLETE; + iport->state = FNIC_IPORT_STATE_FABRIC_DISC; + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, "iport->state:%d\n", + iport->state); + fnic_fdls_disc_start(iport); + if (!((iport->selected_fcf.ka_disabled) + || (iport->selected_fcf.fka_adv_period == 0))) { + u64 tov; + + tov = jiffies + + + msecs_to_jiffies(iport->selected_fcf.fka_adv_period); + mod_timer(&fnic->enode_ka_timer, + round_jiffies(tov)); + + tov = + jiffies + + msecs_to_jiffies(FIP_VN_KA_PERIOD); + mod_timer(&fnic->vn_ka_timer, + round_jiffies(tov)); + + } + } else { + /* + * If there's FLOGI rejects - clear all + * fcf's & restart from scratch + */ + atomic64_inc(&fnic_stats->vlan_stats.flogi_rejects); + /* start FCoE VLAN discovery */ + fnic_fcoe_send_vlan_req(fnic); + + iport->fip.state = FDLS_FIP_VLAN_DISCOVERY_STARTED; + } + } +} + +/** + * fnic_common_fip_cleanup - Clean up FCF info and timers in case of + * link down/CVL + * @fnic: Handle to fnic driver instance + */ +void fnic_common_fip_cleanup(struct fnic *fnic) +{ + + struct fnic_iport_s *iport = &fnic->iport; + + if (!iport->usefip) + return; + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic 0x%p fip cleanup\n", fnic); + + iport->fip.state = FDLS_FIP_INIT; + + del_timer_sync(&fnic->retry_fip_timer); + del_timer_sync(&fnic->fcs_ka_timer); + del_timer_sync(&fnic->enode_ka_timer); + del_timer_sync(&fnic->vn_ka_timer); + + if (!is_zero_ether_addr(iport->fpma)) + vnic_dev_del_addr(fnic->vdev, iport->fpma); + + memset(iport->fpma, 0, ETH_ALEN); + iport->fcid = 0; + iport->r_a_tov = 0; + iport->e_d_tov = 0; + memset(fnic->iport.fcfmac, 0, ETH_ALEN); + memset(iport->selected_fcf.fcf_mac, 0, ETH_ALEN); + iport->selected_fcf.fcf_priority = 0; + iport->selected_fcf.fka_adv_period = 0; + iport->selected_fcf.ka_disabled = 0; + + fnic_fcoe_reset_vlans(fnic); +} + +/** + * fnic_fcoe_process_cvl - Processes Clear Virtual Link from FCF. + * @fnic: Handle to fnic driver instance + * @fiph: Received frame + * + * Verify that cvl is received from our current FCF for our assigned MAC + * and clean up and restart the vlan discovery. + */ +void fnic_fcoe_process_cvl(struct fnic *fnic, struct fip_header *fiph) +{ + struct fnic_iport_s *iport = &fnic->iport; + struct fip_cvl *cvl_msg = (struct fip_cvl *)fiph; + int i; + int found = false; + int max_count = 0; + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic 0x%p clear virtual link handler\n", fnic); + + if (!((cvl_msg->fcf_mac_desc.fd_desc.fip_dtype == 2) + && (cvl_msg->fcf_mac_desc.fd_desc.fip_dlen == 2)) + || !((cvl_msg->name_desc.fd_desc.fip_dtype == 4) + && (cvl_msg->name_desc.fd_desc.fip_dlen == 3))) { + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "invalid mix: ft %x fl %x ndt %x ndl %x", + cvl_msg->fcf_mac_desc.fd_desc.fip_dtype, + cvl_msg->fcf_mac_desc.fd_desc.fip_dlen, + cvl_msg->name_desc.fd_desc.fip_dtype, + cvl_msg->name_desc.fd_desc.fip_dlen); + } + + if (memcmp + (iport->selected_fcf.fcf_mac, cvl_msg->fcf_mac_desc.fd_mac, ETH_ALEN) + == 0) { + for (i = 0; i < ((be16_to_cpu(fiph->fip_dl_len) / 5) - 1); i++) { + if (!((cvl_msg->vn_ports_desc[i].fd_desc.fip_dtype == 11) + && (cvl_msg->vn_ports_desc[i].fd_desc.fip_dlen == 5))) { + + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, + "Invalid type and len mix type: %d len: %d\n", + cvl_msg->vn_ports_desc[i].fd_desc.fip_dtype, + cvl_msg->vn_ports_desc[i].fd_desc.fip_dlen); + } + if (memcmp + (iport->fpma, cvl_msg->vn_ports_desc[i].fd_mac, + ETH_ALEN) == 0) { + found = true; + break; + } + } + if (!found) + return; + fnic_common_fip_cleanup(fnic); + + while (fnic->reset_in_progress == IN_PROGRESS) { + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + wait_for_completion_timeout(&fnic->reset_completion_wait, + msecs_to_jiffies(5000)); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + max_count++; + if (max_count >= FIP_FNIC_RESET_WAIT_COUNT) { + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Rthr waited too long. Skipping handle link event %p\n", + fnic); + return; + } + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic reset in progress. Link event needs to wait %p", + fnic); + } + fnic->reset_in_progress = IN_PROGRESS; + fnic_fdls_link_down(iport); + fnic->reset_in_progress = NOT_IN_PROGRESS; + complete(&fnic->reset_completion_wait); + fnic_fcoe_send_vlan_req(fnic); + } +} + +/** + * fdls_fip_recv_frame - Demultiplexer for FIP frames + * @fnic: Handle to fnic driver instance + * @frame: Received ethernet frame + */ +int fdls_fip_recv_frame(struct fnic *fnic, void *frame) +{ + struct ethhdr *eth = (struct ethhdr *)frame; + struct fip_header *fiph; + u16 op; + u8 sub; + int len = 2048; + + if (be16_to_cpu(eth->h_proto) == ETH_P_FIP) { + fiph = (struct fip_header *)(eth + 1); + op = be16_to_cpu(fiph->fip_op); + sub = fiph->fip_subcode; + + fnic_debug_dump_fip_frame(fnic, eth, len, "Incoming"); + + if (op == FIP_OP_DISC && sub == FIP_SC_REP) + fnic_fcoe_fip_discovery_resp(fnic, fiph); + else if (op == FIP_OP_VLAN && sub == FIP_SC_REP) + fnic_fcoe_process_vlan_resp(fnic, fiph); + else if (op == FIP_OP_CTRL && sub == FIP_SC_REP) + fnic_fcoe_process_cvl(fnic, fiph); + else if (op == FIP_OP_LS && sub == FIP_SC_REP) + fnic_fcoe_process_flogi_resp(fnic, fiph); + + /* Return true if the frame was a FIP frame */ + return true; + } + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Not a FIP Frame"); + return false; +} + +void fnic_work_on_fip_timer(struct work_struct *work) +{ + struct fnic *fnic = container_of(work, struct fnic, fip_timer_work); + struct fnic_iport_s *iport = &fnic->iport; + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FIP timeout\n"); + + if (iport->fip.state == FDLS_FIP_VLAN_DISCOVERY_STARTED) { + fnic_vlan_discovery_timeout(fnic); + } else if (iport->fip.state == FDLS_FIP_FCF_DISCOVERY_STARTED) { + u8 zmac[ETH_ALEN] = { 0, 0, 0, 0, 0, 0 }; + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FCF Discovery timeout\n"); + if (memcmp(iport->selected_fcf.fcf_mac, zmac, ETH_ALEN) != 0) { + + if (iport->flags & FNIC_FIRST_LINK_UP) { + fnic_scsi_fcpio_reset(iport->fnic); + iport->flags &= ~FNIC_FIRST_LINK_UP; + } + + fnic_fcoe_start_flogi(fnic); + if (!((iport->selected_fcf.ka_disabled) + || (iport->selected_fcf.fka_adv_period == 0))) { + u64 fcf_tov; + + fcf_tov = jiffies + + 3 + * + msecs_to_jiffies(iport->selected_fcf.fka_adv_period); + mod_timer(&fnic->fcs_ka_timer, + round_jiffies(fcf_tov)); + } + } else { + FNIC_FIP_DBG(KERN_INFO, fnic->host, + fnic->fnic_num, "FCF Discovery timeout\n"); + fnic_vlan_discovery_timeout(fnic); + } + } else if (iport->fip.state == FDLS_FIP_FLOGI_STARTED) { + fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req); + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI timeout\n"); + if (iport->fip.flogi_retry < fnic->config.flogi_retries) + fnic_fcoe_start_flogi(fnic); + else + fnic_vlan_discovery_timeout(fnic); + } +} + +/** + * fnic_handle_fip_timer - Timeout handler for FIP discover phase. + * @t: Handle to the timer list + * + * Based on the current state, start next phase or restart discovery. + */ +void fnic_handle_fip_timer(struct timer_list *t) +{ + struct fnic *fnic = from_timer(fnic, t, retry_fip_timer); + + INIT_WORK(&fnic->fip_timer_work, fnic_work_on_fip_timer); + queue_work(fnic_fip_queue, &fnic->fip_timer_work); +} + +/** + * fnic_handle_enode_ka_timer - FIP node keep alive. + * @t: Handle to the timer list + */ +void fnic_handle_enode_ka_timer(struct timer_list *t) +{ + uint8_t *frame; + struct fnic *fnic = from_timer(fnic, t, enode_ka_timer); + + struct fnic_iport_s *iport = &fnic->iport; + struct fip_enode_ka *penode_ka; + u64 enode_ka_tov; + uint16_t frame_size = sizeof(struct fip_enode_ka); + + if (iport->fip.state != FDLS_FIP_FLOGI_COMPLETE) + return; + + if ((iport->selected_fcf.ka_disabled) + || (iport->selected_fcf.fka_adv_period == 0)) { + return; + } + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send enode ka"); + return; + } + + penode_ka = (struct fip_enode_ka *) frame; + *penode_ka = (struct fip_enode_ka) { + .eth = { + .h_proto = cpu_to_be16(ETH_P_FIP)}, + .fip = { + .fip_ver = FIP_VER_ENCAPS(FIP_VER), + .fip_op = cpu_to_be16(FIP_OP_CTRL), + .fip_subcode = FIP_SC_REQ, + .fip_dl_len = cpu_to_be16(FIP_ENODE_KA_LEN)}, + .mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC, .fip_dlen = 2}} + }; + + memcpy(penode_ka->eth.h_source, iport->hwmac, ETH_ALEN); + memcpy(penode_ka->eth.h_dest, iport->selected_fcf.fcf_mac, ETH_ALEN); + memcpy(penode_ka->mac_desc.fd_mac, iport->hwmac, ETH_ALEN); + + FNIC_FIP_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "Handle enode KA timer\n"); + fnic_send_fip_frame(iport, frame, frame_size); + enode_ka_tov = jiffies + + msecs_to_jiffies(iport->selected_fcf.fka_adv_period); + mod_timer(&fnic->enode_ka_timer, round_jiffies(enode_ka_tov)); +} + +/** + * fnic_handle_vn_ka_timer - FIP virtual port keep alive. + * @t: Handle to the timer list + */ +void fnic_handle_vn_ka_timer(struct timer_list *t) +{ + uint8_t *frame; + struct fnic *fnic = from_timer(fnic, t, vn_ka_timer); + + struct fnic_iport_s *iport = &fnic->iport; + struct fip_vn_port_ka *pvn_port_ka; + u64 vn_ka_tov; + uint8_t fcid[3]; + uint16_t frame_size = sizeof(struct fip_vn_port_ka); + + if (iport->fip.state != FDLS_FIP_FLOGI_COMPLETE) + return; + + if ((iport->selected_fcf.ka_disabled) + || (iport->selected_fcf.fka_adv_period == 0)) { + return; + } + + frame = fdls_alloc_frame(iport); + if (frame == NULL) { + FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Failed to allocate frame to send vn ka"); + return; + } + + pvn_port_ka = (struct fip_vn_port_ka *) frame; + *pvn_port_ka = (struct fip_vn_port_ka) { + .eth = { + .h_proto = cpu_to_be16(ETH_P_FIP)}, + .fip = { + .fip_ver = FIP_VER_ENCAPS(FIP_VER), + .fip_op = cpu_to_be16(FIP_OP_CTRL), + .fip_subcode = FIP_SC_REQ, + .fip_dl_len = cpu_to_be16(FIP_VN_KA_LEN)}, + .mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC, .fip_dlen = 2}}, + .vn_port_desc = {.fd_desc = {.fip_dtype = FIP_DT_VN_ID, .fip_dlen = 5}} + }; + + memcpy(pvn_port_ka->eth.h_source, iport->fpma, ETH_ALEN); + memcpy(pvn_port_ka->eth.h_dest, iport->selected_fcf.fcf_mac, ETH_ALEN); + memcpy(pvn_port_ka->mac_desc.fd_mac, iport->hwmac, ETH_ALEN); + memcpy(pvn_port_ka->vn_port_desc.fd_mac, iport->fpma, ETH_ALEN); + hton24(fcid, iport->fcid); + memcpy(pvn_port_ka->vn_port_desc.fd_fc_id, fcid, 3); + FNIC_STD_SET_NPORT_NAME(&pvn_port_ka->vn_port_desc.fd_wwpn, iport->wwpn); + + FNIC_FIP_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "Handle vnport KA timer\n"); + fnic_send_fip_frame(iport, frame, frame_size); + vn_ka_tov = jiffies + msecs_to_jiffies(FIP_VN_KA_PERIOD); + mod_timer(&fnic->vn_ka_timer, round_jiffies(vn_ka_tov)); +} + +/** + * fnic_vlan_discovery_timeout - Handle vlan discovery timeout + * @fnic: Handle to fnic driver instance + * + * End of VLAN discovery or FCF discovery time window. + * Start the FCF discovery if VLAN was never used. + */ +void fnic_vlan_discovery_timeout(struct fnic *fnic) +{ + struct fcoe_vlan *vlan; + struct fnic_iport_s *iport = &fnic->iport; + struct fnic_stats *fnic_stats = &fnic->fnic_stats; + unsigned long flags; + + spin_lock_irqsave(&fnic->fnic_lock, flags); + if (fnic->stop_rx_link_events) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + return; + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + + if (!iport->usefip) + return; + + spin_lock_irqsave(&fnic->vlans_lock, flags); + if (list_empty(&fnic->vlan_list)) { + /* no vlans available, try again */ + spin_unlock_irqrestore(&fnic->vlans_lock, flags); + fnic_fcoe_send_vlan_req(fnic); + return; + } + + vlan = list_first_entry(&fnic->vlan_list, struct fcoe_vlan, list); + + if (vlan->state == FIP_VLAN_SENT) { + if (vlan->sol_count >= FCOE_CTLR_MAX_SOL) { + /* + * no response on this vlan, remove from the list. + * Try the next vlan + */ + list_del(&vlan->list); + kfree(vlan); + vlan = NULL; + if (list_empty(&fnic->vlan_list)) { + /* we exhausted all vlans, restart vlan disc */ + spin_unlock_irqrestore(&fnic->vlans_lock, + flags); + fnic_fcoe_send_vlan_req(fnic); + return; + } + /* check the next vlan */ + vlan = + list_first_entry(&fnic->vlan_list, struct fcoe_vlan, + list); + + fnic->set_vlan(fnic, vlan->vid); + vlan->state = FIP_VLAN_SENT; /* sent now */ + + } + atomic64_inc(&fnic_stats->vlan_stats.sol_expiry_count); + + } else { + fnic->set_vlan(fnic, vlan->vid); + vlan->state = FIP_VLAN_SENT; /* sent now */ + } + vlan->sol_count++; + spin_unlock_irqrestore(&fnic->vlans_lock, flags); + fnic_fcoe_start_fcf_discovery(fnic); +} + +/** + * fnic_work_on_fcs_ka_timer - Handle work on FCS keep alive timer. + * @work: the work queue to be serviced + * + * Finish handling fcs_ka_timer in process context. + * Clean up, bring the link down, and restart all FIP discovery. + */ +void fnic_work_on_fcs_ka_timer(struct work_struct *work) +{ + struct fnic + *fnic = container_of(work, struct fnic, fip_timer_work); + struct fnic_iport_s *iport = &fnic->iport; + + FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic 0x%p fcs ka timeout\n", fnic); + + fnic_common_fip_cleanup(fnic); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + fnic_fdls_link_down(iport); + iport->state = FNIC_IPORT_STATE_FIP; + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + + fnic_fcoe_send_vlan_req(fnic); +} + +/** + * fnic_handle_fcs_ka_timer - Handle FCS keep alive timer. + * @t: Handle to the timer list + * + * No keep alives received from FCF. Clean up, bring the link down + * and restart all the FIP discovery. + */ +void fnic_handle_fcs_ka_timer(struct timer_list *t) +{ + struct fnic *fnic = from_timer(fnic, t, fcs_ka_timer); + + INIT_WORK(&fnic->fip_timer_work, fnic_work_on_fcs_ka_timer); + queue_work(fnic_fip_queue, &fnic->fip_timer_work); +} diff --git a/drivers/scsi/fnic/fip.h b/drivers/scsi/fnic/fip.h new file mode 100644 index 000000000000..79fee7628870 --- /dev/null +++ b/drivers/scsi/fnic/fip.h @@ -0,0 +1,159 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2008 Cisco Systems, Inc. All rights reserved. + * Copyright 2007 Nuova Systems, Inc. All rights reserved. + */ +#ifndef _FIP_H_ +#define _FIP_H_ + +#include "fdls_fc.h" +#include "fnic_fdls.h" +#include + +/* Drop the cast from the standard definition */ +#define FCOE_ALL_FCFS_MAC {0x01, 0x10, 0x18, 0x01, 0x00, 0x02} +#define FCOE_MAX_SIZE 0x082E + +#define FCOE_CTLR_FIPVLAN_TOV (3*1000) +#define FCOE_CTLR_FCS_TOV (3*1000) +#define FCOE_CTLR_MAX_SOL (5*1000) + +#define FIP_DISC_SOL_LEN (6) +#define FIP_VLAN_REQ_LEN (2) +#define FIP_ENODE_KA_LEN (2) +#define FIP_VN_KA_LEN (7) +#define FIP_FLOGI_LEN (38) + +enum fdls_vlan_state { + FIP_VLAN_AVAIL, + FIP_VLAN_SENT +}; + +enum fdls_fip_state { + FDLS_FIP_INIT, + FDLS_FIP_VLAN_DISCOVERY_STARTED, + FDLS_FIP_FCF_DISCOVERY_STARTED, + FDLS_FIP_FLOGI_STARTED, + FDLS_FIP_FLOGI_COMPLETE, +}; + +/* + * VLAN entry. + */ +struct fcoe_vlan { + struct list_head list; + uint16_t vid; /* vlan ID */ + uint16_t sol_count; /* no. of sols sent */ + uint16_t state; /* state */ +}; + +struct fip_vlan_req { + struct ethhdr eth; + struct fip_header fip; + struct fip_mac_desc mac_desc; +} __packed; + +struct fip_vlan_notif { + struct fip_header fip; + struct fip_vlan_desc vlans_desc[]; +} __packed; + +struct fip_vn_port_ka { + struct ethhdr eth; + struct fip_header fip; + struct fip_mac_desc mac_desc; + struct fip_vn_desc vn_port_desc; +} __packed; + +struct fip_enode_ka { + struct ethhdr eth; + struct fip_header fip; + struct fip_mac_desc mac_desc; +} __packed; + +struct fip_cvl { + struct fip_header fip; + struct fip_mac_desc fcf_mac_desc; + struct fip_wwn_desc name_desc; + struct fip_vn_desc vn_ports_desc[]; +} __packed; + +struct fip_flogi_desc { + struct fip_desc fd_desc; + uint16_t rsvd; + struct fc_std_flogi flogi; +} __packed; + +struct fip_flogi_rsp_desc { + struct fip_desc fd_desc; + uint16_t rsvd; + struct fc_std_flogi flogi; +} __packed; + +struct fip_flogi { + struct ethhdr eth; + struct fip_header fip; + struct fip_flogi_desc flogi_desc; + struct fip_mac_desc mac_desc; +} __packed; + +struct fip_flogi_rsp { + struct fip_header fip; + struct fip_flogi_rsp_desc rsp_desc; + struct fip_mac_desc mac_desc; +} __packed; + +struct fip_discovery { + struct ethhdr eth; + struct fip_header fip; + struct fip_mac_desc mac_desc; + struct fip_wwn_desc name_desc; + struct fip_size_desc fcoe_desc; +} __packed; + +struct fip_disc_adv { + struct fip_header fip; + struct fip_pri_desc prio_desc; + struct fip_mac_desc mac_desc; + struct fip_wwn_desc name_desc; + struct fip_fab_desc fabric_desc; + struct fip_fka_desc fka_adv_desc; +} __packed; + +void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct fip_header *fiph); +void fnic_fcoe_fip_discovery_resp(struct fnic *fnic, struct fip_header *fiph); +void fnic_fcoe_process_flogi_resp(struct fnic *fnic, struct fip_header *fiph); +void fnic_work_on_fip_timer(struct work_struct *work); +void fnic_work_on_fcs_ka_timer(struct work_struct *work); +void fnic_fcoe_send_vlan_req(struct fnic *fnic); +void fnic_fcoe_start_fcf_discovery(struct fnic *fnic); +void fnic_fcoe_start_flogi(struct fnic *fnic); +void fnic_fcoe_process_cvl(struct fnic *fnic, struct fip_header *fiph); +void fnic_vlan_discovery_timeout(struct fnic *fnic); + +extern struct workqueue_struct *fnic_fip_queue; + +#ifdef FNIC_DEBUG +static inline void +fnic_debug_dump_fip_frame(struct fnic *fnic, struct ethhdr *eth, + int len, char *pfx) +{ + struct fip_header *fiph = (struct fip_header *)(eth + 1); + u16 op = be16_to_cpu(fiph->fip_op); + u8 sub = fiph->fip_subcode; + + FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "FIP %s packet contents: op: 0x%x sub: 0x%x (len = %d)", + pfx, op, sub, len); + + fnic_debug_dump(fnic, (uint8_t *)eth, len); +} + +#else /* FNIC_DEBUG */ + +static inline void +fnic_debug_dump_fip_frame(struct fnic *fnic, struct ethhdr *eth, + int len, char *pfx) {} +#endif /* FNIC_DEBUG */ + +#endif /* _FIP_H_ */ diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index ce73f08ee889..6c5f6046b1f5 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -10,8 +10,10 @@ #include #include #include -#include -#include +#include +#include +#include +#include #include "fnic_io.h" #include "fnic_res.h" #include "fnic_trace.h" @@ -24,13 +26,15 @@ #include "vnic_intr.h" #include "vnic_stats.h" #include "vnic_scsi.h" +#include "fnic_fdls.h" #define DRV_NAME "fnic" #define DRV_DESCRIPTION "Cisco FCoE HBA Driver" -#define DRV_VERSION "1.7.0.0" +#define DRV_VERSION "1.8.0.0" #define PFX DRV_NAME ": " #define DFX DRV_NAME "%d: " +#define FABRIC_LOGO_MAX_RETRY 3 #define DESC_CLEAN_LOW_WATERMARK 8 #define FNIC_UCSM_DFLT_THROTTLE_CNT_BLD 16 /* UCSM default throttle count */ #define FNIC_MIN_IO_REQ 256 /* Min IO throttle count */ @@ -38,6 +42,7 @@ #define FNIC_DFLT_IO_REQ 256 /* Default scsi_cmnd tag map entries */ #define FNIC_DFLT_QUEUE_DEPTH 256 #define FNIC_STATS_RATE_LIMIT 4 /* limit rate at which stats are pulled up */ +#define LUN0_DELAY_TIME 9 /* * Tag bits used for special requests. @@ -75,6 +80,77 @@ #define FNIC_DEV_RST_TERM_DONE BIT(20) #define FNIC_DEV_RST_ABTS_PENDING BIT(21) +#define FNIC_FW_RESET_TIMEOUT 60000 /* mSec */ +#define FNIC_FCOE_MAX_CMD_LEN 16 +/* Retry supported by rport (returned by PRLI service parameters) */ +#define FNIC_FC_RP_FLAGS_RETRY 0x1 + +/* Cisco vendor id */ +#define PCI_VENDOR_ID_CISCO 0x1137 +#define PCI_DEVICE_ID_CISCO_VIC_FC 0x0045 /* fc vnic */ + +/* sereno pcie switch */ +#define PCI_DEVICE_ID_CISCO_SERENO 0x004e +#define PCI_DEVICE_ID_CISCO_CRUZ 0x007a /* Cruz */ +#define PCI_DEVICE_ID_CISCO_BODEGA 0x0131 /* Bodega */ +#define PCI_DEVICE_ID_CISCO_BEVERLY 0x025f /* Beverly */ + +/* Sereno */ +#define PCI_SUBDEVICE_ID_CISCO_VASONA 0x004f /* vasona mezz */ +#define PCI_SUBDEVICE_ID_CISCO_COTATI 0x0084 /* cotati mlom */ +#define PCI_SUBDEVICE_ID_CISCO_LEXINGTON 0x0085 /* lexington pcie */ +#define PCI_SUBDEVICE_ID_CISCO_ICEHOUSE 0x00cd /* Icehouse */ +#define PCI_SUBDEVICE_ID_CISCO_KIRKWOODLAKE 0x00ce /* KirkwoodLake pcie */ +#define PCI_SUBDEVICE_ID_CISCO_SUSANVILLE 0x012e /* Susanville MLOM */ +#define PCI_SUBDEVICE_ID_CISCO_TORRANCE 0x0139 /* Torrance MLOM */ + +/* Cruz */ +#define PCI_SUBDEVICE_ID_CISCO_CALISTOGA 0x012c /* Calistoga MLOM */ +#define PCI_SUBDEVICE_ID_CISCO_MOUNTAINVIEW 0x0137 /* Cruz Mezz */ +/* Cruz MountTian SIOC */ +#define PCI_SUBDEVICE_ID_CISCO_MOUNTTIAN 0x014b +#define PCI_SUBDEVICE_ID_CISCO_CLEARLAKE 0x014d /* ClearLake pcie */ +/* Cruz MountTian2 SIOC */ +#define PCI_SUBDEVICE_ID_CISCO_MOUNTTIAN2 0x0157 +#define PCI_SUBDEVICE_ID_CISCO_CLAREMONT 0x015d /* Claremont MLOM */ + +/* Bodega */ +/* VIC 1457 PCIe mLOM */ +#define PCI_SUBDEVICE_ID_CISCO_BRADBURY 0x0218 +#define PCI_SUBDEVICE_ID_CISCO_BRENTWOOD 0x0217 /* VIC 1455 PCIe */ +/* VIC 1487 PCIe mLOM */ +#define PCI_SUBDEVICE_ID_CISCO_BURLINGAME 0x021a +#define PCI_SUBDEVICE_ID_CISCO_BAYSIDE 0x0219 /* VIC 1485 PCIe */ +/* VIC 1440 Mezz mLOM */ +#define PCI_SUBDEVICE_ID_CISCO_BAKERSFIELD 0x0215 +#define PCI_SUBDEVICE_ID_CISCO_BOONVILLE 0x0216 /* VIC 1480 Mezz */ +#define PCI_SUBDEVICE_ID_CISCO_BENICIA 0x024a /* VIC 1495 */ +#define PCI_SUBDEVICE_ID_CISCO_BEAUMONT 0x024b /* VIC 1497 */ +#define PCI_SUBDEVICE_ID_CISCO_BRISBANE 0x02af /* VIC 1467 */ +#define PCI_SUBDEVICE_ID_CISCO_BENTON 0x02b0 /* VIC 1477 */ +#define PCI_SUBDEVICE_ID_CISCO_TWIN_RIVER 0x02cf /* VIC 14425 */ +#define PCI_SUBDEVICE_ID_CISCO_TWIN_PEAK 0x02d0 /* VIC 14825 */ + +/* Beverly */ +#define PCI_SUBDEVICE_ID_CISCO_BERN 0x02de /* VIC 15420 */ +#define PCI_SUBDEVICE_ID_CISCO_STOCKHOLM 0x02dd /* VIC 15428 */ +#define PCI_SUBDEVICE_ID_CISCO_KRAKOW 0x02dc /* VIC 15411 */ +#define PCI_SUBDEVICE_ID_CISCO_LUCERNE 0x02db /* VIC 15231 */ +#define PCI_SUBDEVICE_ID_CISCO_TURKU 0x02e8 /* VIC 15238 */ +#define PCI_SUBDEVICE_ID_CISCO_TURKU_PLUS 0x02f3 /* VIC 15237 */ +#define PCI_SUBDEVICE_ID_CISCO_ZURICH 0x02df /* VIC 15230 */ +#define PCI_SUBDEVICE_ID_CISCO_RIGA 0x02e0 /* VIC 15427 */ +#define PCI_SUBDEVICE_ID_CISCO_GENEVA 0x02e1 /* VIC 15422 */ +#define PCI_SUBDEVICE_ID_CISCO_HELSINKI 0x02e4 /* VIC 15235 */ +#define PCI_SUBDEVICE_ID_CISCO_GOTHENBURG 0x02f2 /* VIC 15425 */ + +struct fnic_pcie_device { + u32 device; + u8 *desc; + u32 subsystem_device; + u8 *subsys_desc; +}; + /* * fnic private data per SCSI command. * These fields are locked by the hashed io_req_lock. @@ -127,8 +203,38 @@ static inline u64 fnic_flags_and_state(struct scsi_cmnd *cmd) #define fnic_clear_state_flags(fnicp, st_flags) \ __fnic_set_state_flags(fnicp, st_flags, 1) +enum reset_states { + NOT_IN_PROGRESS = 0, + IN_PROGRESS, + RESET_ERROR +}; + +enum rscn_type { + NOT_PC_RSCN = 0, + PC_RSCN +}; + +enum pc_rscn_handling_status { + PC_RSCN_HANDLING_NOT_IN_PROGRESS = 0, + PC_RSCN_HANDLING_IN_PROGRESS +}; + +enum pc_rscn_handling_feature { + PC_RSCN_HANDLING_FEATURE_OFF = 0, + PC_RSCN_HANDLING_FEATURE_ON +}; + +extern unsigned int fnic_fdmi_support; extern unsigned int fnic_log_level; extern unsigned int io_completions; +extern struct workqueue_struct *fnic_event_queue; + +extern unsigned int pc_rscn_handling_feature_flag; +extern spinlock_t reset_fnic_list_lock; +extern struct list_head reset_fnic_list; +extern struct workqueue_struct *reset_fnic_work_queue; +extern struct work_struct reset_fnic_work; + #define FNIC_MAIN_LOGGING 0x01 #define FNIC_FCS_LOGGING 0x02 @@ -155,6 +261,12 @@ do { \ "fnic<%d>: %s: %d: " fmt, fnic_num,\ __func__, __LINE__, ##args);) +#define FNIC_FIP_DBG(kern_level, host, fnic_num, fmt, args...) \ + FNIC_CHECK_LOGGING(FNIC_FCS_LOGGING, \ + shost_printk(kern_level, host, \ + "fnic<%d>: %s: %d: " fmt, fnic_num,\ + __func__, __LINE__, ##args);) + #define FNIC_SCSI_DBG(kern_level, host, fnic_num, fmt, args...) \ FNIC_CHECK_LOGGING(FNIC_SCSI_LOGGING, \ shost_printk(kern_level, host, \ @@ -213,12 +325,26 @@ enum fnic_state { struct mempool; +enum fnic_role_e { + FNIC_ROLE_FCP_INITIATOR = 0, +}; + enum fnic_evt { FNIC_EVT_START_VLAN_DISC = 1, FNIC_EVT_START_FCF_DISC = 2, FNIC_EVT_MAX, }; +struct fnic_frame_list { + /* + * Link to frame lists + */ + struct list_head links; + void *fp; + int frame_len; + int rx_ethhdr_stripped; +}; + struct fnic_event { struct list_head list; struct fnic *fnic; @@ -235,8 +361,9 @@ struct fnic_cpy_wq { /* Per-instance private data structure */ struct fnic { int fnic_num; - struct fc_lport *lport; - struct fcoe_ctlr ctlr; /* FIP FCoE controller structure */ + enum fnic_role_e role; + struct fnic_iport_s iport; + struct Scsi_Host *host; struct vnic_dev_bar bar0; struct fnic_msix_entry msix[FNIC_MSIX_INTR_MAX]; @@ -255,6 +382,7 @@ struct fnic { unsigned int wq_count; unsigned int cq_count; + struct completion reset_completion_wait; struct mutex sgreset_mutex; spinlock_t sgreset_lock; /* lock for sgreset */ struct scsi_cmnd *sgreset_sc; @@ -268,25 +396,27 @@ struct fnic { u32 vlan_hw_insert:1; /* let hw insert the tag */ u32 in_remove:1; /* fnic device in removal */ u32 stop_rx_link_events:1; /* stop proc. rx frames, link events */ - u32 link_events:1; /* set when we get any link event*/ - - struct completion *remove_wait; /* device remove thread blocks */ + struct completion *fw_reset_done; + u32 reset_in_progress; atomic_t in_flight; /* io counter */ bool internal_reset_inprogress; u32 _reserved; /* fill hole */ unsigned long state_flags; /* protected by host lock */ enum fnic_state state; spinlock_t fnic_lock; + unsigned long lock_flags; u16 vlan_id; /* VLAN tag including priority */ u8 data_src_addr[ETH_ALEN]; u64 fcp_input_bytes; /* internal statistic */ u64 fcp_output_bytes; /* internal statistic */ u32 link_down_cnt; + u32 soft_reset_count; int link_status; struct list_head list; + struct list_head links; struct pci_dev *pdev; struct vnic_fc_config config; struct vnic_dev *vdev; @@ -306,19 +436,29 @@ struct fnic { struct work_struct link_work; struct work_struct frame_work; struct work_struct flush_work; - struct sk_buff_head frame_queue; - struct sk_buff_head tx_queue; + struct list_head frame_queue; + struct list_head tx_queue; + mempool_t *frame_pool; + mempool_t *frame_elem_pool; + struct work_struct tport_work; + struct list_head tport_event_list; + + char subsys_desc[14]; + int subsys_desc_len; + int pc_rscn_handling_status; /*** FIP related data members -- start ***/ void (*set_vlan)(struct fnic *, u16 vlan); struct work_struct fip_frame_work; - struct sk_buff_head fip_frame_queue; + struct work_struct fip_timer_work; + struct list_head fip_frame_queue; struct timer_list fip_timer; - struct list_head vlans; spinlock_t vlans_lock; - - struct work_struct event_work; - struct list_head evlist; + struct timer_list retry_fip_timer; + struct timer_list fcs_ka_timer; + struct timer_list enode_ka_timer; + struct timer_list vn_ka_timer; + struct list_head vlan_list; /*** FIP related data members -- end ***/ /* copy work queue cache line section */ @@ -341,11 +481,6 @@ struct fnic { ____cacheline_aligned struct vnic_intr intr[FNIC_MSIX_INTR_MAX]; }; -static inline struct fnic *fnic_from_ctlr(struct fcoe_ctlr *fip) -{ - return container_of(fip, struct fnic, ctlr); -} - extern struct workqueue_struct *fnic_event_queue; extern struct workqueue_struct *fnic_fip_queue; extern const struct attribute_group *fnic_host_groups[]; @@ -356,29 +491,29 @@ int fnic_set_intr_mode_msix(struct fnic *fnic); void fnic_free_intr(struct fnic *fnic); int fnic_request_intr(struct fnic *fnic); -int fnic_send(struct fc_lport *, struct fc_frame *); void fnic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf); void fnic_handle_frame(struct work_struct *work); +void fnic_tport_event_handler(struct work_struct *work); void fnic_handle_link(struct work_struct *work); void fnic_handle_event(struct work_struct *work); +void fdls_reclaim_oxid_handler(struct work_struct *work); +void fdls_schedule_oxid_free(struct fnic_iport_s *iport, uint16_t *active_oxid); +void fdls_schedule_oxid_free_retry_work(struct work_struct *work); int fnic_rq_cmpl_handler(struct fnic *fnic, int); int fnic_alloc_rq_frame(struct vnic_rq *rq); void fnic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf); void fnic_flush_tx(struct work_struct *work); -void fnic_eth_send(struct fcoe_ctlr *, struct sk_buff *skb); -void fnic_set_port_id(struct fc_lport *, u32, struct fc_frame *); -void fnic_update_mac(struct fc_lport *, u8 *new); void fnic_update_mac_locked(struct fnic *, u8 *new); int fnic_queuecommand(struct Scsi_Host *, struct scsi_cmnd *); int fnic_abort_cmd(struct scsi_cmnd *); int fnic_device_reset(struct scsi_cmnd *); -int fnic_host_reset(struct scsi_cmnd *); -int fnic_reset(struct Scsi_Host *); -void fnic_scsi_cleanup(struct fc_lport *); -void fnic_scsi_abort_io(struct fc_lport *); -void fnic_empty_scsi_cleanup(struct fc_lport *); -void fnic_exch_mgr_reset(struct fc_lport *, u32, u32); +int fnic_eh_host_reset_handler(struct scsi_cmnd *sc); +int fnic_host_reset(struct Scsi_Host *shost); +void fnic_reset(struct Scsi_Host *shost); +int fnic_issue_fc_host_lip(struct Scsi_Host *shost); +void fnic_get_host_port_state(struct Scsi_Host *shost); +void fnic_scsi_fcpio_reset(struct fnic *fnic); int fnic_wq_copy_cmpl_handler(struct fnic *fnic, int copy_work_to_do, unsigned int cq_index); int fnic_wq_cmpl_handler(struct fnic *fnic, int); int fnic_flogi_reg_handler(struct fnic *fnic, u32); @@ -390,14 +525,15 @@ const char *fnic_state_to_str(unsigned int state); void fnic_mq_map_queues_cpus(struct Scsi_Host *host); void fnic_log_q_error(struct fnic *fnic); void fnic_handle_link_event(struct fnic *fnic); - +int fnic_stats_debugfs_init(struct fnic *fnic); +void fnic_stats_debugfs_remove(struct fnic *fnic); int fnic_is_abts_pending(struct fnic *, struct scsi_cmnd *); void fnic_handle_fip_frame(struct work_struct *work); +void fnic_reset_work_handler(struct work_struct *work); void fnic_handle_fip_event(struct fnic *fnic); void fnic_fcoe_reset_vlans(struct fnic *fnic); -void fnic_fcoe_evlist_free(struct fnic *fnic); -extern void fnic_handle_fip_timer(struct fnic *fnic); +extern void fnic_handle_fip_timer(struct timer_list *t); static inline int fnic_chk_state_flags_locked(struct fnic *fnic, unsigned long st_flags) @@ -406,4 +542,90 @@ fnic_chk_state_flags_locked(struct fnic *fnic, unsigned long st_flags) } void __fnic_set_state_flags(struct fnic *, unsigned long, unsigned long); void fnic_dump_fchost_stats(struct Scsi_Host *, struct fc_host_statistics *); +void fnic_free_txq(struct list_head *head); +int fnic_get_desc_by_devid(struct pci_dev *pdev, char **desc, + char **subsys_desc); +void fnic_fdls_link_status_change(struct fnic *fnic, int linkup); +void fnic_delete_fcp_tports(struct fnic *fnic); +void fnic_flush_tport_event_list(struct fnic *fnic); +int fnic_count_ioreqs_wq(struct fnic *fnic, u32 hwq, u32 portid); +unsigned int fnic_count_ioreqs(struct fnic *fnic, u32 portid); +unsigned int fnic_count_all_ioreqs(struct fnic *fnic); +unsigned int fnic_count_lun_ioreqs_wq(struct fnic *fnic, u32 hwq, + struct scsi_device *device); +unsigned int fnic_count_lun_ioreqs(struct fnic *fnic, + struct scsi_device *device); +void fnic_scsi_unload(struct fnic *fnic); +void fnic_scsi_unload_cleanup(struct fnic *fnic); +int fnic_get_debug_info(struct stats_debug_info *info, + struct fnic *fnic); + +struct fnic_scsi_iter_data { + struct fnic *fnic; + void *data1; + void *data2; + bool (*fn)(struct fnic *fnic, struct scsi_cmnd *sc, + void *data1, void *data2); +}; + +static inline bool +fnic_io_iter_handler(struct scsi_cmnd *sc, void *iter_data) +{ + struct fnic_scsi_iter_data *iter = iter_data; + + return iter->fn(iter->fnic, sc, iter->data1, iter->data2); +} + +static inline void +fnic_scsi_io_iter(struct fnic *fnic, + bool (*fn)(struct fnic *fnic, struct scsi_cmnd *sc, + void *data1, void *data2), + void *data1, void *data2) +{ + struct fnic_scsi_iter_data iter_data = { + .fn = fn, + .fnic = fnic, + .data1 = data1, + .data2 = data2, + }; + scsi_host_busy_iter(fnic->host, fnic_io_iter_handler, &iter_data); +} + +#ifdef FNIC_DEBUG +static inline void +fnic_debug_dump(struct fnic *fnic, uint8_t *u8arr, int len) +{ + int i; + + for (i = 0; i < len; i = i+8) { + FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "%d: %02x %02x %02x %02x %02x %02x %02x %02x", i / 8, + u8arr[i + 0], u8arr[i + 1], u8arr[i + 2], u8arr[i + 3], + u8arr[i + 4], u8arr[i + 5], u8arr[i + 6], u8arr[i + 7]); + } +} + +static inline void +fnic_debug_dump_fc_frame(struct fnic *fnic, struct fc_frame_header *fchdr, + int len, char *pfx) +{ + uint32_t s_id, d_id; + + s_id = ntoh24(fchdr->fh_s_id); + d_id = ntoh24(fchdr->fh_d_id); + FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "%s packet contents: sid/did/type/oxid = 0x%x/0x%x/0x%x/0x%x (len = %d)\n", + pfx, s_id, d_id, fchdr->fh_type, + FNIC_STD_GET_OX_ID(fchdr), len); + + fnic_debug_dump(fnic, (uint8_t *)fchdr, len); + +} +#else /* FNIC_DEBUG */ +static inline void +fnic_debug_dump(struct fnic *fnic, uint8_t *u8arr, int len) {} +static inline void +fnic_debug_dump_fc_frame(struct fnic *fnic, struct fc_frame_header *fchdr, + uint32_t len, char *pfx) {} +#endif /* FNIC_DEBUG */ #endif /* _FNIC_H_ */ diff --git a/drivers/scsi/fnic/fnic_attrs.c b/drivers/scsi/fnic/fnic_attrs.c index 0c5e57c7e322..705718f0809b 100644 --- a/drivers/scsi/fnic/fnic_attrs.c +++ b/drivers/scsi/fnic/fnic_attrs.c @@ -11,8 +11,8 @@ static ssize_t fnic_show_state(struct device *dev, struct device_attribute *attr, char *buf) { - struct fc_lport *lp = shost_priv(class_to_shost(dev)); - struct fnic *fnic = lport_priv(lp); + struct fnic *fnic = + *((struct fnic **) shost_priv(class_to_shost(dev))); return sysfs_emit(buf, "%s\n", fnic_state_str[fnic->state]); } @@ -26,9 +26,13 @@ static ssize_t fnic_show_drv_version(struct device *dev, static ssize_t fnic_show_link_state(struct device *dev, struct device_attribute *attr, char *buf) { - struct fc_lport *lp = shost_priv(class_to_shost(dev)); + struct fnic *fnic = + *((struct fnic **) shost_priv(class_to_shost(dev))); - return sysfs_emit(buf, "%s\n", (lp->link_up) ? "Link Up" : "Link Down"); + return sysfs_emit(buf, "%s\n", + ((fnic->iport.state != FNIC_IPORT_STATE_INIT) && + (fnic->iport.state != FNIC_IPORT_STATE_LINK_WAIT)) ? + "Link Up" : "Link Down"); } static DEVICE_ATTR(fnic_state, S_IRUGO, fnic_show_state, NULL); diff --git a/drivers/scsi/fnic/fnic_debugfs.c b/drivers/scsi/fnic/fnic_debugfs.c index 2619a2d4f5f1..5767862ae42f 100644 --- a/drivers/scsi/fnic/fnic_debugfs.c +++ b/drivers/scsi/fnic/fnic_debugfs.c @@ -7,6 +7,9 @@ #include #include "fnic.h" +extern int fnic_get_debug_info(struct stats_debug_info *debug_buffer, + struct fnic *fnic); + static struct dentry *fnic_trace_debugfs_root; static struct dentry *fnic_trace_debugfs_file; static struct dentry *fnic_trace_enable; @@ -593,6 +596,7 @@ static int fnic_stats_debugfs_open(struct inode *inode, debug->buf_size = buf_size; memset((void *)debug->debug_buffer, 0, buf_size); debug->buffer_len = fnic_get_stats_data(debug, fnic_stats); + debug->buffer_len += fnic_get_debug_info(debug, fnic); file->private_data = debug; @@ -673,26 +677,25 @@ static const struct file_operations fnic_reset_debugfs_fops = { * It will create file stats and reset_stats under statistics/host# directory * to log per fnic stats. */ -void fnic_stats_debugfs_init(struct fnic *fnic) +int fnic_stats_debugfs_init(struct fnic *fnic) { char name[16]; - snprintf(name, sizeof(name), "host%d", fnic->lport->host->host_no); + snprintf(name, sizeof(name), "host%d", fnic->host->host_no); fnic->fnic_stats_debugfs_host = debugfs_create_dir(name, fnic_stats_debugfs_root); - fnic->fnic_stats_debugfs_file = debugfs_create_file("stats", S_IFREG|S_IRUGO|S_IWUSR, fnic->fnic_stats_debugfs_host, fnic, &fnic_stats_debugfs_fops); - fnic->fnic_reset_debugfs_file = debugfs_create_file("reset_stats", S_IFREG|S_IRUGO|S_IWUSR, fnic->fnic_stats_debugfs_host, fnic, &fnic_reset_debugfs_fops); + return 0; } /* diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c index a08293b2ad9f..1e8cd64f9a5c 100644 --- a/drivers/scsi/fnic/fnic_fcs.c +++ b/drivers/scsi/fnic/fnic_fcs.c @@ -14,701 +14,379 @@ #include #include #include -#include #include -#include +#include +#include #include "fnic_io.h" #include "fnic.h" -#include "fnic_fip.h" +#include "fnic_fdls.h" +#include "fdls_fc.h" #include "cq_enet_desc.h" #include "cq_exch_desc.h" +#include "fip.h" + +#define MAX_RESET_WAIT_COUNT 64 -static u8 fcoe_all_fcfs[ETH_ALEN] = FIP_ALL_FCF_MACS; -struct workqueue_struct *fnic_fip_queue; struct workqueue_struct *fnic_event_queue; -static void fnic_set_eth_mode(struct fnic *); -static void fnic_fcoe_send_vlan_req(struct fnic *fnic); -static void fnic_fcoe_start_fcf_disc(struct fnic *fnic); -static void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct sk_buff *); -static int fnic_fcoe_vlan_check(struct fnic *fnic, u16 flag); -static int fnic_fcoe_handle_fip_frame(struct fnic *fnic, struct sk_buff *skb); +static uint8_t FCOE_ALL_FCF_MAC[6] = FC_FCOE_FLOGI_MAC; + +/* + * Internal Functions + * This function will initialize the src_mac address to be + * used in outgoing frames + */ +static inline void fnic_fdls_set_fcoe_srcmac(struct fnic *fnic, + uint8_t *src_mac) +{ + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Setting src mac: %02x:%02x:%02x:%02x:%02x:%02x", + src_mac[0], src_mac[1], src_mac[2], src_mac[3], + src_mac[4], src_mac[5]); + + memcpy(fnic->iport.fpma, src_mac, 6); +} + +/* + * This function will initialize the dst_mac address to be + * used in outgoing frames + */ +static inline void fnic_fdls_set_fcoe_dstmac(struct fnic *fnic, + uint8_t *dst_mac) +{ + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Setting dst mac: %02x:%02x:%02x:%02x:%02x:%02x", + dst_mac[0], dst_mac[1], dst_mac[2], dst_mac[3], + dst_mac[4], dst_mac[5]); + + memcpy(fnic->iport.fcfmac, dst_mac, 6); +} + +void fnic_get_host_port_state(struct Scsi_Host *shost) +{ + struct fnic *fnic = *((struct fnic **) shost_priv(shost)); + struct fnic_iport_s *iport = &fnic->iport; + unsigned long flags; + + spin_lock_irqsave(&fnic->fnic_lock, flags); + if (!fnic->link_status) + fc_host_port_state(shost) = FC_PORTSTATE_LINKDOWN; + else if (iport->state == FNIC_IPORT_STATE_READY) + fc_host_port_state(shost) = FC_PORTSTATE_ONLINE; + else + fc_host_port_state(shost) = FC_PORTSTATE_OFFLINE; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); +} + +void fnic_fdls_link_status_change(struct fnic *fnic, int linkup) +{ + struct fnic_iport_s *iport = &fnic->iport; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "link up: %d, usefip: %d", linkup, iport->usefip); + + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + + if (linkup) { + if (iport->usefip) { + iport->state = FNIC_IPORT_STATE_FIP; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "link up: %d, usefip: %d", linkup, iport->usefip); + fnic_fcoe_send_vlan_req(fnic); + } else { + iport->state = FNIC_IPORT_STATE_FABRIC_DISC; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport->state: %d", iport->state); + fnic_fdls_disc_start(iport); + } + } else { + iport->state = FNIC_IPORT_STATE_LINK_WAIT; + if (!is_zero_ether_addr(iport->fpma)) + vnic_dev_del_addr(fnic->vdev, iport->fpma); + fnic_common_fip_cleanup(fnic); + fnic_fdls_link_down(iport); + + } + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); +} + + +/* + * FPMA can be either taken from ethhdr(dst_mac) or flogi resp + * or derive from FC_MAP and FCID combination. While it should be + * same, revisit this if there is any possibility of not-correct. + */ +void fnic_fdls_learn_fcoe_macs(struct fnic_iport_s *iport, void *rx_frame, + uint8_t *fcid) +{ + struct fnic *fnic = iport->fnic; + struct ethhdr *ethhdr = (struct ethhdr *) rx_frame; + uint8_t fcmac[6] = { 0x0E, 0xFC, 0x00, 0x00, 0x00, 0x00 }; + + memcpy(&fcmac[3], fcid, 3); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "learn fcoe: dst_mac: %02x:%02x:%02x:%02x:%02x:%02x", + ethhdr->h_dest[0], ethhdr->h_dest[1], + ethhdr->h_dest[2], ethhdr->h_dest[3], + ethhdr->h_dest[4], ethhdr->h_dest[5]); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "learn fcoe: fc_mac: %02x:%02x:%02x:%02x:%02x:%02x", + fcmac[0], fcmac[1], fcmac[2], fcmac[3], fcmac[4], + fcmac[5]); + + fnic_fdls_set_fcoe_srcmac(fnic, fcmac); + fnic_fdls_set_fcoe_dstmac(fnic, ethhdr->h_source); +} + +void fnic_fdls_init(struct fnic *fnic, int usefip) +{ + struct fnic_iport_s *iport = &fnic->iport; + + /* Initialize iPort structure */ + iport->state = FNIC_IPORT_STATE_INIT; + iport->fnic = fnic; + iport->usefip = usefip; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iportsrcmac: %02x:%02x:%02x:%02x:%02x:%02x", + iport->hwmac[0], iport->hwmac[1], iport->hwmac[2], + iport->hwmac[3], iport->hwmac[4], iport->hwmac[5]); + + INIT_LIST_HEAD(&iport->tport_list); + INIT_LIST_HEAD(&iport->tport_list_pending_del); + + fnic_fdls_disc_init(iport); +} void fnic_handle_link(struct work_struct *work) { struct fnic *fnic = container_of(work, struct fnic, link_work); - unsigned long flags; int old_link_status; u32 old_link_down_cnt; - u64 old_port_speed, new_port_speed; + int max_count = 0; - spin_lock_irqsave(&fnic->fnic_lock, flags); + if (vnic_dev_get_intr_mode(fnic->vdev) != VNIC_DEV_INTR_MODE_MSI) + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Interrupt mode is not MSI\n"); - fnic->link_events = 1; /* less work to just set everytime*/ + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); if (fnic->stop_rx_link_events) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Stop link rx events\n"); + return; + } + + /* Do not process if the fnic is already in transitional state */ + if ((fnic->state != FNIC_IN_ETH_MODE) + && (fnic->state != FNIC_IN_FC_MODE)) { + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic in transitional state: %d. link up: %d ignored", + fnic->state, vnic_dev_link_status(fnic->vdev)); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Current link status: %d iport state: %d\n", + fnic->link_status, fnic->iport.state); return; } old_link_down_cnt = fnic->link_down_cnt; old_link_status = fnic->link_status; - old_port_speed = atomic64_read( - &fnic->fnic_stats.misc_stats.current_port_speed); - fnic->link_status = vnic_dev_link_status(fnic->vdev); fnic->link_down_cnt = vnic_dev_link_down_cnt(fnic->vdev); - new_port_speed = vnic_dev_port_speed(fnic->vdev); - atomic64_set(&fnic->fnic_stats.misc_stats.current_port_speed, - new_port_speed); - if (old_port_speed != new_port_speed) - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "Current vnic speed set to: %llu\n", - new_port_speed); + while (fnic->reset_in_progress == IN_PROGRESS) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic reset in progress. Link event needs to wait\n"); - switch (vnic_dev_port_speed(fnic->vdev)) { - case DCEM_PORTSPEED_10G: - fc_host_speed(fnic->lport->host) = FC_PORTSPEED_10GBIT; - fnic->lport->link_supported_speeds = FC_PORTSPEED_10GBIT; - break; - case DCEM_PORTSPEED_20G: - fc_host_speed(fnic->lport->host) = FC_PORTSPEED_20GBIT; - fnic->lport->link_supported_speeds = FC_PORTSPEED_20GBIT; - break; - case DCEM_PORTSPEED_25G: - fc_host_speed(fnic->lport->host) = FC_PORTSPEED_25GBIT; - fnic->lport->link_supported_speeds = FC_PORTSPEED_25GBIT; - break; - case DCEM_PORTSPEED_40G: - case DCEM_PORTSPEED_4x10G: - fc_host_speed(fnic->lport->host) = FC_PORTSPEED_40GBIT; - fnic->lport->link_supported_speeds = FC_PORTSPEED_40GBIT; - break; - case DCEM_PORTSPEED_100G: - fc_host_speed(fnic->lport->host) = FC_PORTSPEED_100GBIT; - fnic->lport->link_supported_speeds = FC_PORTSPEED_100GBIT; - break; - default: - fc_host_speed(fnic->lport->host) = FC_PORTSPEED_UNKNOWN; - fnic->lport->link_supported_speeds = FC_PORTSPEED_UNKNOWN; - break; + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "waiting for reset completion\n"); + wait_for_completion_timeout(&fnic->reset_completion_wait, + msecs_to_jiffies(5000)); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "woken up from reset completion wait\n"); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + + max_count++; + if (max_count >= MAX_RESET_WAIT_COUNT) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Rstth waited for too long. Skipping handle link event\n"); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + return; + } + } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Marking fnic reset in progress\n"); + fnic->reset_in_progress = IN_PROGRESS; + + if ((vnic_dev_get_intr_mode(fnic->vdev) != VNIC_DEV_INTR_MODE_MSI) || + (fnic->link_status != old_link_status)) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "old link status: %d link status: %d\n", + old_link_status, (int) fnic->link_status); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "old down count %d down count: %d\n", + old_link_down_cnt, (int) fnic->link_down_cnt); } if (old_link_status == fnic->link_status) { if (!fnic->link_status) { /* DOWN -> DOWN */ - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - fnic_fc_trace_set_data(fnic->lport->host->host_no, - FNIC_FC_LE, "Link Status: DOWN->DOWN", - strlen("Link Status: DOWN->DOWN")); - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "down->down\n"); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "down->down\n"); } else { if (old_link_down_cnt != fnic->link_down_cnt) { /* UP -> DOWN -> UP */ - fnic->lport->host_stats.link_failure_count++; - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - fnic_fc_trace_set_data( - fnic->lport->host->host_no, - FNIC_FC_LE, - "Link Status:UP_DOWN_UP", - strlen("Link_Status:UP_DOWN_UP") - ); - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "link down\n"); - fcoe_ctlr_link_down(&fnic->ctlr); - if (fnic->config.flags & VFCF_FIP_CAPABLE) { - /* start FCoE VLAN discovery */ - fnic_fc_trace_set_data( - fnic->lport->host->host_no, - FNIC_FC_LE, - "Link Status: UP_DOWN_UP_VLAN", - strlen( - "Link Status: UP_DOWN_UP_VLAN") - ); - fnic_fcoe_send_vlan_req(fnic); - return; - } - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "up->down->up: Link up\n"); - fcoe_ctlr_link_up(&fnic->ctlr); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "up->down. Link down\n"); + fnic_fdls_link_status_change(fnic, 0); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "down->up. Link up\n"); + fnic_fdls_link_status_change(fnic, 1); } else { /* UP -> UP */ - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - fnic_fc_trace_set_data( - fnic->lport->host->host_no, FNIC_FC_LE, - "Link Status: UP_UP", - strlen("Link Status: UP_UP")); - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "up->up\n"); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "up->up\n"); } } } else if (fnic->link_status) { /* DOWN -> UP */ - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - if (fnic->config.flags & VFCF_FIP_CAPABLE) { - /* start FCoE VLAN discovery */ - fnic_fc_trace_set_data(fnic->lport->host->host_no, - FNIC_FC_LE, "Link Status: DOWN_UP_VLAN", - strlen("Link Status: DOWN_UP_VLAN")); - fnic_fcoe_send_vlan_req(fnic); - - return; - } - - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "down->up: Link up\n"); - fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_LE, - "Link Status: DOWN_UP", strlen("Link Status: DOWN_UP")); - fcoe_ctlr_link_up(&fnic->ctlr); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "down->up. Link up\n"); + fnic_fdls_link_status_change(fnic, 1); } else { /* UP -> DOWN */ - fnic->lport->host_stats.link_failure_count++; - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "up->down: Link down\n"); - fnic_fc_trace_set_data( - fnic->lport->host->host_no, FNIC_FC_LE, - "Link Status: UP_DOWN", - strlen("Link Status: UP_DOWN")); - if (fnic->config.flags & VFCF_FIP_CAPABLE) { - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "deleting fip-timer during link-down\n"); - del_timer_sync(&fnic->fip_timer); - } - fcoe_ctlr_link_down(&fnic->ctlr); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "up->down. Link down\n"); + fnic_fdls_link_status_change(fnic, 0); } + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + fnic->reset_in_progress = NOT_IN_PROGRESS; + complete(&fnic->reset_completion_wait); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Marking fnic reset completion\n"); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); } -/* - * This function passes incoming fabric frames to libFC - */ void fnic_handle_frame(struct work_struct *work) { struct fnic *fnic = container_of(work, struct fnic, frame_work); - struct fc_lport *lp = fnic->lport; - unsigned long flags; - struct sk_buff *skb; - struct fc_frame *fp; + struct fnic_frame_list *cur_frame, *next; + int fchdr_offset = 0; - while ((skb = skb_dequeue(&fnic->frame_queue))) { - - spin_lock_irqsave(&fnic->fnic_lock, flags); + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + list_for_each_entry_safe(cur_frame, next, &fnic->frame_queue, links) { if (fnic->stop_rx_link_events) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - dev_kfree_skb(skb); + list_del(&cur_frame->links); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + kfree(cur_frame->fp); + mempool_free(cur_frame, fnic->frame_elem_pool); return; } - fp = (struct fc_frame *)skb; /* * If we're in a transitional state, just re-queue and return. * The queue will be serviced when we get to a stable state. */ if (fnic->state != FNIC_IN_FC_MODE && - fnic->state != FNIC_IN_ETH_MODE) { - skb_queue_head(&fnic->frame_queue, skb); - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - return; - } - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - - fc_exch_recv(lp, fp); - } -} - -void fnic_fcoe_evlist_free(struct fnic *fnic) -{ - struct fnic_event *fevt = NULL; - struct fnic_event *next = NULL; - unsigned long flags; - - spin_lock_irqsave(&fnic->fnic_lock, flags); - if (list_empty(&fnic->evlist)) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - return; - } - - list_for_each_entry_safe(fevt, next, &fnic->evlist, list) { - list_del(&fevt->list); - kfree(fevt); - } - spin_unlock_irqrestore(&fnic->fnic_lock, flags); -} - -void fnic_handle_event(struct work_struct *work) -{ - struct fnic *fnic = container_of(work, struct fnic, event_work); - struct fnic_event *fevt = NULL; - struct fnic_event *next = NULL; - unsigned long flags; - - spin_lock_irqsave(&fnic->fnic_lock, flags); - if (list_empty(&fnic->evlist)) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - return; - } - - list_for_each_entry_safe(fevt, next, &fnic->evlist, list) { - if (fnic->stop_rx_link_events) { - list_del(&fevt->list); - kfree(fevt); - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - return; - } - /* - * If we're in a transitional state, just re-queue and return. - * The queue will be serviced when we get to a stable state. - */ - if (fnic->state != FNIC_IN_FC_MODE && - fnic->state != FNIC_IN_ETH_MODE) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); + fnic->state != FNIC_IN_ETH_MODE) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Cannot process frame in transitional state\n"); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); return; } - list_del(&fevt->list); - switch (fevt->event) { - case FNIC_EVT_START_VLAN_DISC: - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - fnic_fcoe_send_vlan_req(fnic); - spin_lock_irqsave(&fnic->fnic_lock, flags); - break; - case FNIC_EVT_START_FCF_DISC: - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "Start FCF Discovery\n"); - fnic_fcoe_start_fcf_disc(fnic); - break; - default: - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "Unknown event 0x%x\n", fevt->event); - break; - } - kfree(fevt); + list_del(&cur_frame->links); + + /* Frames from FCP_RQ will have ethhdrs stripped off */ + fchdr_offset = (cur_frame->rx_ethhdr_stripped) ? + 0 : FNIC_ETH_FCOE_HDRS_OFFSET; + + fnic_fdls_recv_frame(&fnic->iport, cur_frame->fp, + cur_frame->frame_len, fchdr_offset); + + kfree(cur_frame->fp); + mempool_free(cur_frame, fnic->frame_elem_pool); } - spin_unlock_irqrestore(&fnic->fnic_lock, flags); -} - -/** - * is_fnic_fip_flogi_reject() - Check if the Received FIP FLOGI frame is rejected - * @fip: The FCoE controller that received the frame - * @skb: The received FIP frame - * - * Returns non-zero if the frame is rejected with unsupported cmd with - * insufficient resource els explanation. - */ -static inline int is_fnic_fip_flogi_reject(struct fcoe_ctlr *fip, - struct sk_buff *skb) -{ - struct fc_lport *lport = fip->lp; - struct fip_header *fiph; - struct fc_frame_header *fh = NULL; - struct fip_desc *desc; - struct fip_encaps *els; - u16 op; - u8 els_op; - u8 sub; - - size_t rlen; - size_t dlen = 0; - - if (skb_linearize(skb)) - return 0; - - if (skb->len < sizeof(*fiph)) - return 0; - - fiph = (struct fip_header *)skb->data; - op = ntohs(fiph->fip_op); - sub = fiph->fip_subcode; - - if (op != FIP_OP_LS) - return 0; - - if (sub != FIP_SC_REP) - return 0; - - rlen = ntohs(fiph->fip_dl_len) * 4; - if (rlen + sizeof(*fiph) > skb->len) - return 0; - - desc = (struct fip_desc *)(fiph + 1); - dlen = desc->fip_dlen * FIP_BPW; - - if (desc->fip_dtype == FIP_DT_FLOGI) { - - if (dlen < sizeof(*els) + sizeof(*fh) + 1) - return 0; - - els = (struct fip_encaps *)desc; - fh = (struct fc_frame_header *)(els + 1); - - if (!fh) - return 0; - - /* - * ELS command code, reason and explanation should be = Reject, - * unsupported command and insufficient resource - */ - els_op = *(u8 *)(fh + 1); - if (els_op == ELS_LS_RJT) { - shost_printk(KERN_INFO, lport->host, - "Flogi Request Rejected by Switch\n"); - return 1; - } - shost_printk(KERN_INFO, lport->host, - "Flogi Request Accepted by Switch\n"); - } - return 0; -} - -static void fnic_fcoe_send_vlan_req(struct fnic *fnic) -{ - struct fcoe_ctlr *fip = &fnic->ctlr; - struct fnic_stats *fnic_stats = &fnic->fnic_stats; - struct sk_buff *skb; - char *eth_fr; - struct fip_vlan *vlan; - u64 vlan_tov; - - fnic_fcoe_reset_vlans(fnic); - fnic->set_vlan(fnic, 0); - - if (printk_ratelimit()) - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "Sending VLAN request...\n"); - - skb = dev_alloc_skb(sizeof(struct fip_vlan)); - if (!skb) - return; - - eth_fr = (char *)skb->data; - vlan = (struct fip_vlan *)eth_fr; - - memset(vlan, 0, sizeof(*vlan)); - memcpy(vlan->eth.h_source, fip->ctl_src_addr, ETH_ALEN); - memcpy(vlan->eth.h_dest, fcoe_all_fcfs, ETH_ALEN); - vlan->eth.h_proto = htons(ETH_P_FIP); - - vlan->fip.fip_ver = FIP_VER_ENCAPS(FIP_VER); - vlan->fip.fip_op = htons(FIP_OP_VLAN); - vlan->fip.fip_subcode = FIP_SC_VL_REQ; - vlan->fip.fip_dl_len = htons(sizeof(vlan->desc) / FIP_BPW); - - vlan->desc.mac.fd_desc.fip_dtype = FIP_DT_MAC; - vlan->desc.mac.fd_desc.fip_dlen = sizeof(vlan->desc.mac) / FIP_BPW; - memcpy(&vlan->desc.mac.fd_mac, fip->ctl_src_addr, ETH_ALEN); - - vlan->desc.wwnn.fd_desc.fip_dtype = FIP_DT_NAME; - vlan->desc.wwnn.fd_desc.fip_dlen = sizeof(vlan->desc.wwnn) / FIP_BPW; - put_unaligned_be64(fip->lp->wwnn, &vlan->desc.wwnn.fd_wwn); - atomic64_inc(&fnic_stats->vlan_stats.vlan_disc_reqs); - - skb_put(skb, sizeof(*vlan)); - skb->protocol = htons(ETH_P_FIP); - skb_reset_mac_header(skb); - skb_reset_network_header(skb); - fip->send(fip, skb); - - /* set a timer so that we can retry if there no response */ - vlan_tov = jiffies + msecs_to_jiffies(FCOE_CTLR_FIPVLAN_TOV); - mod_timer(&fnic->fip_timer, round_jiffies(vlan_tov)); -} - -static void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct sk_buff *skb) -{ - struct fcoe_ctlr *fip = &fnic->ctlr; - struct fip_header *fiph; - struct fip_desc *desc; - struct fnic_stats *fnic_stats = &fnic->fnic_stats; - u16 vid; - size_t rlen; - size_t dlen; - struct fcoe_vlan *vlan; - u64 sol_time; - unsigned long flags; - - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "Received VLAN response...\n"); - - fiph = (struct fip_header *) skb->data; - - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "Received VLAN response... OP 0x%x SUB_OP 0x%x\n", - ntohs(fiph->fip_op), fiph->fip_subcode); - - rlen = ntohs(fiph->fip_dl_len) * 4; - fnic_fcoe_reset_vlans(fnic); - spin_lock_irqsave(&fnic->vlans_lock, flags); - desc = (struct fip_desc *)(fiph + 1); - while (rlen > 0) { - dlen = desc->fip_dlen * FIP_BPW; - switch (desc->fip_dtype) { - case FIP_DT_VLAN: - vid = ntohs(((struct fip_vlan_desc *)desc)->fd_vlan); - shost_printk(KERN_INFO, fnic->lport->host, - "process_vlan_resp: FIP VLAN %d\n", vid); - vlan = kzalloc(sizeof(*vlan), GFP_ATOMIC); - if (!vlan) { - /* retry from timer */ - spin_unlock_irqrestore(&fnic->vlans_lock, - flags); - goto out; - } - vlan->vid = vid & 0x0fff; - vlan->state = FIP_VLAN_AVAIL; - list_add_tail(&vlan->list, &fnic->vlans); - break; - } - desc = (struct fip_desc *)((char *)desc + dlen); - rlen -= dlen; - } - - /* any VLAN descriptors present ? */ - if (list_empty(&fnic->vlans)) { - /* retry from timer */ - atomic64_inc(&fnic_stats->vlan_stats.resp_withno_vlanID); - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "No VLAN descriptors in FIP VLAN response\n"); - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - goto out; - } - - vlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, list); - fnic->set_vlan(fnic, vlan->vid); - vlan->state = FIP_VLAN_SENT; /* sent now */ - vlan->sol_count++; - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - - /* start the solicitation */ - fcoe_ctlr_link_up(fip); - - sol_time = jiffies + msecs_to_jiffies(FCOE_CTLR_START_DELAY); - mod_timer(&fnic->fip_timer, round_jiffies(sol_time)); -out: - return; -} - -static void fnic_fcoe_start_fcf_disc(struct fnic *fnic) -{ - unsigned long flags; - struct fcoe_vlan *vlan; - u64 sol_time; - - spin_lock_irqsave(&fnic->vlans_lock, flags); - vlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, list); - fnic->set_vlan(fnic, vlan->vid); - vlan->state = FIP_VLAN_SENT; /* sent now */ - vlan->sol_count = 1; - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - - /* start the solicitation */ - fcoe_ctlr_link_up(&fnic->ctlr); - - sol_time = jiffies + msecs_to_jiffies(FCOE_CTLR_START_DELAY); - mod_timer(&fnic->fip_timer, round_jiffies(sol_time)); -} - -static int fnic_fcoe_vlan_check(struct fnic *fnic, u16 flag) -{ - unsigned long flags; - struct fcoe_vlan *fvlan; - - spin_lock_irqsave(&fnic->vlans_lock, flags); - if (list_empty(&fnic->vlans)) { - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - return -EINVAL; - } - - fvlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, list); - if (fvlan->state == FIP_VLAN_USED) { - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - return 0; - } - - if (fvlan->state == FIP_VLAN_SENT) { - fvlan->state = FIP_VLAN_USED; - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - return 0; - } - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - return -EINVAL; -} - -static void fnic_event_enq(struct fnic *fnic, enum fnic_evt ev) -{ - struct fnic_event *fevt; - unsigned long flags; - - fevt = kmalloc(sizeof(*fevt), GFP_ATOMIC); - if (!fevt) - return; - - fevt->fnic = fnic; - fevt->event = ev; - - spin_lock_irqsave(&fnic->fnic_lock, flags); - list_add_tail(&fevt->list, &fnic->evlist); - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - - schedule_work(&fnic->event_work); -} - -static int fnic_fcoe_handle_fip_frame(struct fnic *fnic, struct sk_buff *skb) -{ - struct fip_header *fiph; - int ret = 1; - u16 op; - u8 sub; - - if (!skb || !(skb->data)) - return -1; - - if (skb_linearize(skb)) - goto drop; - - fiph = (struct fip_header *)skb->data; - op = ntohs(fiph->fip_op); - sub = fiph->fip_subcode; - - if (FIP_VER_DECAPS(fiph->fip_ver) != FIP_VER) - goto drop; - - if (ntohs(fiph->fip_dl_len) * FIP_BPW + sizeof(*fiph) > skb->len) - goto drop; - - if (op == FIP_OP_DISC && sub == FIP_SC_ADV) { - if (fnic_fcoe_vlan_check(fnic, ntohs(fiph->fip_flags))) - goto drop; - /* pass it on to fcoe */ - ret = 1; - } else if (op == FIP_OP_VLAN && sub == FIP_SC_VL_NOTE) { - /* set the vlan as used */ - fnic_fcoe_process_vlan_resp(fnic, skb); - ret = 0; - } else if (op == FIP_OP_CTRL && sub == FIP_SC_CLR_VLINK) { - /* received CVL request, restart vlan disc */ - fnic_event_enq(fnic, FNIC_EVT_START_VLAN_DISC); - /* pass it on to fcoe */ - ret = 1; - } -drop: - return ret; + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); } void fnic_handle_fip_frame(struct work_struct *work) { + struct fnic_frame_list *cur_frame, *next; struct fnic *fnic = container_of(work, struct fnic, fip_frame_work); - struct fnic_stats *fnic_stats = &fnic->fnic_stats; - unsigned long flags; - struct sk_buff *skb; - struct ethhdr *eh; - while ((skb = skb_dequeue(&fnic->fip_frame_queue))) { - spin_lock_irqsave(&fnic->fnic_lock, flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Processing FIP frame\n"); + + spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags); + list_for_each_entry_safe(cur_frame, next, &fnic->fip_frame_queue, + links) { if (fnic->stop_rx_link_events) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - dev_kfree_skb(skb); + list_del(&cur_frame->links); + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); + kfree(cur_frame->fp); + kfree(cur_frame); return; } + /* * If we're in a transitional state, just re-queue and return. * The queue will be serviced when we get to a stable state. */ if (fnic->state != FNIC_IN_FC_MODE && - fnic->state != FNIC_IN_ETH_MODE) { - skb_queue_head(&fnic->fip_frame_queue, skb); - spin_unlock_irqrestore(&fnic->fnic_lock, flags); + fnic->state != FNIC_IN_ETH_MODE) { + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); return; } - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - eh = (struct ethhdr *)skb->data; - if (eh->h_proto == htons(ETH_P_FIP)) { - skb_pull(skb, sizeof(*eh)); - if (fnic_fcoe_handle_fip_frame(fnic, skb) <= 0) { - dev_kfree_skb(skb); - continue; - } - /* - * If there's FLOGI rejects - clear all - * fcf's & restart from scratch - */ - if (is_fnic_fip_flogi_reject(&fnic->ctlr, skb)) { - atomic64_inc( - &fnic_stats->vlan_stats.flogi_rejects); - shost_printk(KERN_INFO, fnic->lport->host, - "Trigger a Link down - VLAN Disc\n"); - fcoe_ctlr_link_down(&fnic->ctlr); - /* start FCoE VLAN discovery */ - fnic_fcoe_send_vlan_req(fnic); - dev_kfree_skb(skb); - continue; - } - fcoe_ctlr_recv(&fnic->ctlr, skb); - continue; + + list_del(&cur_frame->links); + + if (fdls_fip_recv_frame(fnic, cur_frame->fp)) { + kfree(cur_frame->fp); + kfree(cur_frame); } } + spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags); } /** * fnic_import_rq_eth_pkt() - handle received FCoE or FIP frame. * @fnic: fnic instance. - * @skb: Ethernet Frame. + * @fp: Ethernet Frame. */ -static inline int fnic_import_rq_eth_pkt(struct fnic *fnic, struct sk_buff *skb) +static inline int fnic_import_rq_eth_pkt(struct fnic *fnic, void *fp) { - struct fc_frame *fp; struct ethhdr *eh; - struct fcoe_hdr *fcoe_hdr; - struct fcoe_crc_eof *ft; + struct fnic_frame_list *fip_fr_elem; + unsigned long flags; - /* - * Undo VLAN encapsulation if present. - */ - eh = (struct ethhdr *)skb->data; - if (eh->h_proto == htons(ETH_P_8021Q)) { - memmove((u8 *)eh + VLAN_HLEN, eh, ETH_ALEN * 2); - eh = skb_pull(skb, VLAN_HLEN); - skb_reset_mac_header(skb); - } - if (eh->h_proto == htons(ETH_P_FIP)) { - if (!(fnic->config.flags & VFCF_FIP_CAPABLE)) { - printk(KERN_ERR "Dropped FIP frame, as firmware " - "uses non-FIP mode, Enable FIP " - "using UCSM\n"); - goto drop; - } - if ((fnic_fc_trace_set_data(fnic->lport->host->host_no, - FNIC_FC_RECV|0x80, (char *)skb->data, skb->len)) != 0) { - printk(KERN_ERR "fnic ctlr frame trace error!!!"); - } - skb_queue_tail(&fnic->fip_frame_queue, skb); + eh = (struct ethhdr *) fp; + if ((eh->h_proto == cpu_to_be16(ETH_P_FIP)) && (fnic->iport.usefip)) { + fip_fr_elem = (struct fnic_frame_list *) + kzalloc(sizeof(struct fnic_frame_list), GFP_ATOMIC); + if (!fip_fr_elem) + return 0; + fip_fr_elem->fp = fp; + spin_lock_irqsave(&fnic->fnic_lock, flags); + list_add_tail(&fip_fr_elem->links, &fnic->fip_frame_queue); + spin_unlock_irqrestore(&fnic->fnic_lock, flags); queue_work(fnic_fip_queue, &fnic->fip_frame_work); - return 1; /* let caller know packet was used */ - } - if (eh->h_proto != htons(ETH_P_FCOE)) - goto drop; - skb_set_network_header(skb, sizeof(*eh)); - skb_pull(skb, sizeof(*eh)); - - fcoe_hdr = (struct fcoe_hdr *)skb->data; - if (FC_FCOE_DECAPS_VER(fcoe_hdr) != FC_FCOE_VER) - goto drop; - - fp = (struct fc_frame *)skb; - fc_frame_init(fp); - fr_sof(fp) = fcoe_hdr->fcoe_sof; - skb_pull(skb, sizeof(struct fcoe_hdr)); - skb_reset_transport_header(skb); - - ft = (struct fcoe_crc_eof *)(skb->data + skb->len - sizeof(*ft)); - fr_eof(fp) = ft->fcoe_eof; - skb_trim(skb, skb->len - sizeof(*ft)); - return 0; -drop: - dev_kfree_skb_irq(skb); - return -1; + return 1; /* let caller know packet was used */ + } else + return 0; } /** @@ -720,206 +398,147 @@ drop: */ void fnic_update_mac_locked(struct fnic *fnic, u8 *new) { - u8 *ctl = fnic->ctlr.ctl_src_addr; + struct fnic_iport_s *iport = &fnic->iport; + u8 *ctl = iport->hwmac; u8 *data = fnic->data_src_addr; if (is_zero_ether_addr(new)) new = ctl; if (ether_addr_equal(data, new)) return; - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "update_mac %pM\n", new); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Update MAC: %u\n", *new); + if (!is_zero_ether_addr(data) && !ether_addr_equal(data, ctl)) vnic_dev_del_addr(fnic->vdev, data); + memcpy(data, new, ETH_ALEN); if (!ether_addr_equal(new, ctl)) vnic_dev_add_addr(fnic->vdev, new); } -/** - * fnic_update_mac() - set data MAC address and filters. - * @lport: local port. - * @new: newly-assigned FCoE MAC address. - */ -void fnic_update_mac(struct fc_lport *lport, u8 *new) -{ - struct fnic *fnic = lport_priv(lport); - - spin_lock_irq(&fnic->fnic_lock); - fnic_update_mac_locked(fnic, new); - spin_unlock_irq(&fnic->fnic_lock); -} - -/** - * fnic_set_port_id() - set the port_ID after successful FLOGI. - * @lport: local port. - * @port_id: assigned FC_ID. - * @fp: received frame containing the FLOGI accept or NULL. - * - * This is called from libfc when a new FC_ID has been assigned. - * This causes us to reset the firmware to FC_MODE and setup the new MAC - * address and FC_ID. - * - * It is also called with FC_ID 0 when we're logged off. - * - * If the FC_ID is due to point-to-point, fp may be NULL. - */ -void fnic_set_port_id(struct fc_lport *lport, u32 port_id, struct fc_frame *fp) -{ - struct fnic *fnic = lport_priv(lport); - u8 *mac; - int ret; - - FNIC_FCS_DBG(KERN_DEBUG, lport->host, fnic->fnic_num, - "set port_id 0x%x fp 0x%p\n", - port_id, fp); - - /* - * If we're clearing the FC_ID, change to use the ctl_src_addr. - * Set ethernet mode to send FLOGI. - */ - if (!port_id) { - fnic_update_mac(lport, fnic->ctlr.ctl_src_addr); - fnic_set_eth_mode(fnic); - return; - } - - if (fp) { - mac = fr_cb(fp)->granted_mac; - if (is_zero_ether_addr(mac)) { - /* non-FIP - FLOGI already accepted - ignore return */ - fcoe_ctlr_recv_flogi(&fnic->ctlr, lport, fp); - } - fnic_update_mac(lport, mac); - } - - /* Change state to reflect transition to FC mode */ - spin_lock_irq(&fnic->fnic_lock); - if (fnic->state == FNIC_IN_ETH_MODE || fnic->state == FNIC_IN_FC_MODE) - fnic->state = FNIC_IN_ETH_TRANS_FC_MODE; - else { - FNIC_FCS_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, - "Unexpected fnic state: %s processing FLOGI response", - fnic_state_to_str(fnic->state)); - spin_unlock_irq(&fnic->fnic_lock); - return; - } - spin_unlock_irq(&fnic->fnic_lock); - - /* - * Send FLOGI registration to firmware to set up FC mode. - * The new address will be set up when registration completes. - */ - ret = fnic_flogi_reg_handler(fnic, port_id); - - if (ret < 0) { - spin_lock_irq(&fnic->fnic_lock); - if (fnic->state == FNIC_IN_ETH_TRANS_FC_MODE) - fnic->state = FNIC_IN_ETH_MODE; - spin_unlock_irq(&fnic->fnic_lock); - } -} - static void fnic_rq_cmpl_frame_recv(struct vnic_rq *rq, struct cq_desc *cq_desc, struct vnic_rq_buf *buf, int skipped __attribute__((unused)), void *opaque) { struct fnic *fnic = vnic_dev_priv(rq->vdev); - struct sk_buff *skb; - struct fc_frame *fp; + uint8_t *fp; struct fnic_stats *fnic_stats = &fnic->fnic_stats; + unsigned int ethhdr_stripped; u8 type, color, eop, sop, ingress_port, vlan_stripped; - u8 fcoe = 0, fcoe_sof, fcoe_eof; - u8 fcoe_fc_crc_ok = 1, fcoe_enc_error = 0; - u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok; - u8 ipv6, ipv4, ipv4_fragment, rss_type, csum_not_calc; + u8 fcoe_fnic_crc_ok = 1, fcoe_enc_error = 0; u8 fcs_ok = 1, packet_error = 0; - u16 q_number, completed_index, bytes_written = 0, vlan, checksum; + u16 q_number, completed_index, vlan; u32 rss_hash; + u16 checksum; + u8 csum_not_calc, rss_type, ipv4, ipv6, ipv4_fragment; + u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok; + u8 fcoe = 0, fcoe_sof, fcoe_eof; u16 exchange_id, tmpl; u8 sof = 0; u8 eof = 0; u32 fcp_bytes_written = 0; + u16 enet_bytes_written = 0; + u32 bytes_written = 0; unsigned long flags; + struct fnic_frame_list *frame_elem = NULL; + struct ethhdr *eh; dma_unmap_single(&fnic->pdev->dev, buf->dma_addr, buf->len, - DMA_FROM_DEVICE); - skb = buf->os_buf; - fp = (struct fc_frame *)skb; + DMA_FROM_DEVICE); + fp = (uint8_t *) buf->os_buf; buf->os_buf = NULL; cq_desc_dec(cq_desc, &type, &color, &q_number, &completed_index); if (type == CQ_DESC_TYPE_RQ_FCP) { - cq_fcp_rq_desc_dec((struct cq_fcp_rq_desc *)cq_desc, - &type, &color, &q_number, &completed_index, - &eop, &sop, &fcoe_fc_crc_ok, &exchange_id, - &tmpl, &fcp_bytes_written, &sof, &eof, - &ingress_port, &packet_error, - &fcoe_enc_error, &fcs_ok, &vlan_stripped, - &vlan); - skb_trim(skb, fcp_bytes_written); - fr_sof(fp) = sof; - fr_eof(fp) = eof; - + cq_fcp_rq_desc_dec((struct cq_fcp_rq_desc *) cq_desc, &type, + &color, &q_number, &completed_index, &eop, &sop, + &fcoe_fnic_crc_ok, &exchange_id, &tmpl, + &fcp_bytes_written, &sof, &eof, &ingress_port, + &packet_error, &fcoe_enc_error, &fcs_ok, + &vlan_stripped, &vlan); + ethhdr_stripped = 1; + bytes_written = fcp_bytes_written; } else if (type == CQ_DESC_TYPE_RQ_ENET) { - cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc, - &type, &color, &q_number, &completed_index, - &ingress_port, &fcoe, &eop, &sop, - &rss_type, &csum_not_calc, &rss_hash, - &bytes_written, &packet_error, - &vlan_stripped, &vlan, &checksum, - &fcoe_sof, &fcoe_fc_crc_ok, - &fcoe_enc_error, &fcoe_eof, - &tcp_udp_csum_ok, &udp, &tcp, - &ipv4_csum_ok, &ipv6, &ipv4, - &ipv4_fragment, &fcs_ok); - skb_trim(skb, bytes_written); + cq_enet_rq_desc_dec((struct cq_enet_rq_desc *) cq_desc, &type, + &color, &q_number, &completed_index, + &ingress_port, &fcoe, &eop, &sop, &rss_type, + &csum_not_calc, &rss_hash, &enet_bytes_written, + &packet_error, &vlan_stripped, &vlan, + &checksum, &fcoe_sof, &fcoe_fnic_crc_ok, + &fcoe_enc_error, &fcoe_eof, &tcp_udp_csum_ok, + &udp, &tcp, &ipv4_csum_ok, &ipv6, &ipv4, + &ipv4_fragment, &fcs_ok); + + ethhdr_stripped = 0; + bytes_written = enet_bytes_written; + if (!fcs_ok) { atomic64_inc(&fnic_stats->misc_stats.frame_errors); - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "fcs error. dropping packet.\n"); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic 0x%p fcs error. Dropping packet.\n", fnic); goto drop; } - if (fnic_import_rq_eth_pkt(fnic, skb)) - return; + eh = (struct ethhdr *) fp; + if (eh->h_proto != cpu_to_be16(ETH_P_FCOE)) { + if (fnic_import_rq_eth_pkt(fnic, fp)) + return; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Dropping h_proto 0x%x", + be16_to_cpu(eh->h_proto)); + goto drop; + } } else { - /* wrong CQ type*/ - shost_printk(KERN_ERR, fnic->lport->host, - "fnic rq_cmpl wrong cq type x%x\n", type); + /* wrong CQ type */ + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic rq_cmpl wrong cq type x%x\n", type); goto drop; } - if (!fcs_ok || packet_error || !fcoe_fc_crc_ok || fcoe_enc_error) { + if (!fcs_ok || packet_error || !fcoe_fnic_crc_ok || fcoe_enc_error) { atomic64_inc(&fnic_stats->misc_stats.frame_errors); - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "fnic rq_cmpl fcoe x%x fcsok x%x" - " pkterr x%x fcoe_fc_crc_ok x%x, fcoe_enc_err" - " x%x\n", - fcoe, fcs_ok, packet_error, - fcoe_fc_crc_ok, fcoe_enc_error); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fcoe %x fcsok %x pkterr %x ffco %x fee %x\n", + fcoe, fcs_ok, packet_error, + fcoe_fnic_crc_ok, fcoe_enc_error); goto drop; } spin_lock_irqsave(&fnic->fnic_lock, flags); if (fnic->stop_rx_link_events) { spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic->stop_rx_link_events: %d\n", + fnic->stop_rx_link_events); goto drop; } - fr_dev(fp) = fnic->lport; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); - if ((fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_RECV, - (char *)skb->data, skb->len)) != 0) { - printk(KERN_ERR "fnic ctlr frame trace error!!!"); + + frame_elem = mempool_alloc(fnic->frame_elem_pool, + GFP_ATOMIC | __GFP_ZERO); + if (!frame_elem) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Failed to allocate memory for frame elem"); + goto drop; } + frame_elem->fp = fp; + frame_elem->rx_ethhdr_stripped = ethhdr_stripped; + frame_elem->frame_len = bytes_written; + + spin_lock_irqsave(&fnic->fnic_lock, flags); + list_add_tail(&frame_elem->links, &fnic->frame_queue); + spin_unlock_irqrestore(&fnic->fnic_lock, flags); - skb_queue_tail(&fnic->frame_queue, skb); queue_work(fnic_event_queue, &fnic->frame_work); - return; + drop: - dev_kfree_skb_irq(skb); + kfree(fp); } static int fnic_rq_cmpl_handler_cont(struct vnic_dev *vdev, @@ -945,10 +564,10 @@ int fnic_rq_cmpl_handler(struct fnic *fnic, int rq_work_to_do) cur_work_done = vnic_cq_service(&fnic->cq[i], rq_work_to_do, fnic_rq_cmpl_handler_cont, NULL); - if (cur_work_done) { + if (cur_work_done && fnic->stop_rx_link_events != 1) { err = vnic_rq_fill(&fnic->rq[i], fnic_alloc_rq_frame); if (err) - shost_printk(KERN_ERR, fnic->lport->host, + shost_printk(KERN_ERR, fnic->host, "fnic_alloc_rq_frame can't alloc" " frame\n"); } @@ -966,218 +585,179 @@ int fnic_rq_cmpl_handler(struct fnic *fnic, int rq_work_to_do) int fnic_alloc_rq_frame(struct vnic_rq *rq) { struct fnic *fnic = vnic_dev_priv(rq->vdev); - struct sk_buff *skb; + void *buf; u16 len; dma_addr_t pa; - int r; + int ret; - len = FC_FRAME_HEADROOM + FC_MAX_FRAME + FC_FRAME_TAILROOM; - skb = dev_alloc_skb(len); - if (!skb) { - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "Unable to allocate RQ sk_buff\n"); + len = FNIC_FRAME_HT_ROOM; + buf = kmalloc(len, GFP_ATOMIC); + if (!buf) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Unable to allocate RQ buffer of size: %d\n", len); return -ENOMEM; } - skb_reset_mac_header(skb); - skb_reset_transport_header(skb); - skb_reset_network_header(skb); - skb_put(skb, len); - pa = dma_map_single(&fnic->pdev->dev, skb->data, len, DMA_FROM_DEVICE); + + pa = dma_map_single(&fnic->pdev->dev, buf, len, DMA_FROM_DEVICE); if (dma_mapping_error(&fnic->pdev->dev, pa)) { - r = -ENOMEM; - printk(KERN_ERR "PCI mapping failed with error %d\n", r); - goto free_skb; + ret = -ENOMEM; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "PCI mapping failed with error %d\n", ret); + goto free_buf; } - fnic_queue_rq_desc(rq, skb, pa, len); + fnic_queue_rq_desc(rq, buf, pa, len); return 0; - -free_skb: - kfree_skb(skb); - return r; +free_buf: + kfree(buf); + return ret; } void fnic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf) { - struct fc_frame *fp = buf->os_buf; + void *rq_buf = buf->os_buf; struct fnic *fnic = vnic_dev_priv(rq->vdev); dma_unmap_single(&fnic->pdev->dev, buf->dma_addr, buf->len, DMA_FROM_DEVICE); - dev_kfree_skb(fp_skb(fp)); + kfree(rq_buf); buf->os_buf = NULL; } -/** - * fnic_eth_send() - Send Ethernet frame. - * @fip: fcoe_ctlr instance. - * @skb: Ethernet Frame, FIP, without VLAN encapsulation. - */ -void fnic_eth_send(struct fcoe_ctlr *fip, struct sk_buff *skb) -{ - struct fnic *fnic = fnic_from_ctlr(fip); - struct vnic_wq *wq = &fnic->wq[0]; - dma_addr_t pa; - struct ethhdr *eth_hdr; - struct vlan_ethhdr *vlan_hdr; - unsigned long flags; - - if (!fnic->vlan_hw_insert) { - eth_hdr = (struct ethhdr *)skb_mac_header(skb); - vlan_hdr = skb_push(skb, sizeof(*vlan_hdr) - sizeof(*eth_hdr)); - memcpy(vlan_hdr, eth_hdr, 2 * ETH_ALEN); - vlan_hdr->h_vlan_proto = htons(ETH_P_8021Q); - vlan_hdr->h_vlan_encapsulated_proto = eth_hdr->h_proto; - vlan_hdr->h_vlan_TCI = htons(fnic->vlan_id); - if ((fnic_fc_trace_set_data(fnic->lport->host->host_no, - FNIC_FC_SEND|0x80, (char *)eth_hdr, skb->len)) != 0) { - printk(KERN_ERR "fnic ctlr frame trace error!!!"); - } - } else { - if ((fnic_fc_trace_set_data(fnic->lport->host->host_no, - FNIC_FC_SEND|0x80, (char *)skb->data, skb->len)) != 0) { - printk(KERN_ERR "fnic ctlr frame trace error!!!"); - } - } - - pa = dma_map_single(&fnic->pdev->dev, skb->data, skb->len, - DMA_TO_DEVICE); - if (dma_mapping_error(&fnic->pdev->dev, pa)) { - printk(KERN_ERR "DMA mapping failed\n"); - goto free_skb; - } - - spin_lock_irqsave(&fnic->wq_lock[0], flags); - if (!vnic_wq_desc_avail(wq)) - goto irq_restore; - - fnic_queue_wq_eth_desc(wq, skb, pa, skb->len, - 0 /* hw inserts cos value */, - fnic->vlan_id, 1); - spin_unlock_irqrestore(&fnic->wq_lock[0], flags); - return; - -irq_restore: - spin_unlock_irqrestore(&fnic->wq_lock[0], flags); - dma_unmap_single(&fnic->pdev->dev, pa, skb->len, DMA_TO_DEVICE); -free_skb: - kfree_skb(skb); -} - /* * Send FC frame. */ -static int fnic_send_frame(struct fnic *fnic, struct fc_frame *fp) +static int fnic_send_frame(struct fnic *fnic, void *frame, int frame_len) { struct vnic_wq *wq = &fnic->wq[0]; - struct sk_buff *skb; dma_addr_t pa; - struct ethhdr *eth_hdr; - struct vlan_ethhdr *vlan_hdr; - struct fcoe_hdr *fcoe_hdr; - struct fc_frame_header *fh; - u32 tot_len, eth_hdr_len; int ret = 0; unsigned long flags; - fh = fc_frame_header_get(fp); - skb = fp_skb(fp); + pa = dma_map_single(&fnic->pdev->dev, frame, frame_len, DMA_TO_DEVICE); - if (unlikely(fh->fh_r_ctl == FC_RCTL_ELS_REQ) && - fcoe_ctlr_els_send(&fnic->ctlr, fnic->lport, skb)) - return 0; - - if (!fnic->vlan_hw_insert) { - eth_hdr_len = sizeof(*vlan_hdr) + sizeof(*fcoe_hdr); - vlan_hdr = skb_push(skb, eth_hdr_len); - eth_hdr = (struct ethhdr *)vlan_hdr; - vlan_hdr->h_vlan_proto = htons(ETH_P_8021Q); - vlan_hdr->h_vlan_encapsulated_proto = htons(ETH_P_FCOE); - vlan_hdr->h_vlan_TCI = htons(fnic->vlan_id); - fcoe_hdr = (struct fcoe_hdr *)(vlan_hdr + 1); - } else { - eth_hdr_len = sizeof(*eth_hdr) + sizeof(*fcoe_hdr); - eth_hdr = skb_push(skb, eth_hdr_len); - eth_hdr->h_proto = htons(ETH_P_FCOE); - fcoe_hdr = (struct fcoe_hdr *)(eth_hdr + 1); - } - - if (fnic->ctlr.map_dest) - fc_fcoe_set_mac(eth_hdr->h_dest, fh->fh_d_id); - else - memcpy(eth_hdr->h_dest, fnic->ctlr.dest_addr, ETH_ALEN); - memcpy(eth_hdr->h_source, fnic->data_src_addr, ETH_ALEN); - - tot_len = skb->len; - BUG_ON(tot_len % 4); - - memset(fcoe_hdr, 0, sizeof(*fcoe_hdr)); - fcoe_hdr->fcoe_sof = fr_sof(fp); - if (FC_FCOE_VER) - FC_FCOE_ENCAPS_VER(fcoe_hdr, FC_FCOE_VER); - - pa = dma_map_single(&fnic->pdev->dev, eth_hdr, tot_len, DMA_TO_DEVICE); - if (dma_mapping_error(&fnic->pdev->dev, pa)) { - ret = -ENOMEM; - printk(KERN_ERR "DMA map failed with error %d\n", ret); - goto free_skb_on_err; - } - - if ((fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_SEND, - (char *)eth_hdr, tot_len)) != 0) { - printk(KERN_ERR "fnic ctlr frame trace error!!!"); + if ((fnic_fc_trace_set_data(fnic->fnic_num, + FNIC_FC_SEND | 0x80, (char *) frame, + frame_len)) != 0) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic ctlr frame trace error"); } spin_lock_irqsave(&fnic->wq_lock[0], flags); if (!vnic_wq_desc_avail(wq)) { - dma_unmap_single(&fnic->pdev->dev, pa, tot_len, DMA_TO_DEVICE); + dma_unmap_single(&fnic->pdev->dev, pa, frame_len, DMA_TO_DEVICE); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "vnic work queue descriptor is not available"); ret = -1; - goto irq_restore; + goto fnic_send_frame_end; } - fnic_queue_wq_desc(wq, skb, pa, tot_len, fr_eof(fp), - 0 /* hw inserts cos value */, - fnic->vlan_id, 1, 1, 1); + /* hw inserts cos value */ + fnic_queue_wq_desc(wq, frame, pa, frame_len, FC_EOF_T, + 0, fnic->vlan_id, 1, 1, 1); -irq_restore: +fnic_send_frame_end: spin_unlock_irqrestore(&fnic->wq_lock[0], flags); - -free_skb_on_err: - if (ret) - dev_kfree_skb_any(fp_skb(fp)); - return ret; } -/* - * fnic_send - * Routine to send a raw frame +/** + * fdls_send_fcoe_frame - send a filled-in FC frame, filling in eth and FCoE + * info. This interface is used only in the non fast path. (login, fabric + * registrations etc.) + * + * @fnic: fnic instance + * @frame: frame structure with FC payload filled in + * @frame_size: length of the frame to be sent + * @srcmac: source mac address + * @dstmac: destination mac address + * + * Called with the fnic lock held. */ -int fnic_send(struct fc_lport *lp, struct fc_frame *fp) +static int +fdls_send_fcoe_frame(struct fnic *fnic, void *frame, int frame_size, + uint8_t *srcmac, uint8_t *dstmac) { - struct fnic *fnic = lport_priv(lp); - unsigned long flags; + struct ethhdr *pethhdr; + struct fcoe_hdr *pfcoe_hdr; + struct fnic_frame_list *frame_elem; + int len = frame_size; + int ret; + struct fc_frame_header *fchdr = (struct fc_frame_header *) (frame + + FNIC_ETH_FCOE_HDRS_OFFSET); - if (fnic->in_remove) { - dev_kfree_skb(fp_skb(fp)); - return -1; - } + pethhdr = (struct ethhdr *) frame; + pethhdr->h_proto = cpu_to_be16(ETH_P_FCOE); + memcpy(pethhdr->h_source, srcmac, ETH_ALEN); + memcpy(pethhdr->h_dest, dstmac, ETH_ALEN); + + pfcoe_hdr = (struct fcoe_hdr *) (frame + sizeof(struct ethhdr)); + pfcoe_hdr->fcoe_sof = FC_SOF_I3; /* * Queue frame if in a transitional state. * This occurs while registering the Port_ID / MAC address after FLOGI. */ - spin_lock_irqsave(&fnic->fnic_lock, flags); - if (fnic->state != FNIC_IN_FC_MODE && fnic->state != FNIC_IN_ETH_MODE) { - skb_queue_tail(&fnic->tx_queue, fp_skb(fp)); - spin_unlock_irqrestore(&fnic->fnic_lock, flags); + if ((fnic->state != FNIC_IN_FC_MODE) + && (fnic->state != FNIC_IN_ETH_MODE)) { + frame_elem = mempool_alloc(fnic->frame_elem_pool, + GFP_ATOMIC | __GFP_ZERO); + if (!frame_elem) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Failed to allocate memory for frame elem"); + return -ENOMEM; + } + + FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "Queueing FC frame: sid/did/type/oxid = 0x%x/0x%x/0x%x/0x%x\n", + ntoh24(fchdr->fh_s_id), ntoh24(fchdr->fh_d_id), + fchdr->fh_type, FNIC_STD_GET_OX_ID(fchdr)); + frame_elem->fp = frame; + frame_elem->frame_len = len; + list_add_tail(&frame_elem->links, &fnic->tx_queue); return 0; } - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - return fnic_send_frame(fnic, fp); + fnic_debug_dump_fc_frame(fnic, fchdr, frame_size, "Outgoing"); + + ret = fnic_send_frame(fnic, frame, len); + return ret; +} + +void fnic_send_fcoe_frame(struct fnic_iport_s *iport, void *frame, + int frame_size) +{ + struct fnic *fnic = iport->fnic; + uint8_t *dstmac, *srcmac; + + /* If module unload is in-progress, don't send */ + if (fnic->in_remove) + return; + + if (iport->fabric.flags & FNIC_FDLS_FPMA_LEARNT) { + srcmac = iport->fpma; + dstmac = iport->fcfmac; + } else { + srcmac = iport->hwmac; + dstmac = FCOE_ALL_FCF_MAC; + } + + fdls_send_fcoe_frame(fnic, frame, frame_size, srcmac, dstmac); +} + +int +fnic_send_fip_frame(struct fnic_iport_s *iport, void *frame, + int frame_size) +{ + struct fnic *fnic = iport->fnic; + + if (fnic->in_remove) + return -1; + + fnic_debug_dump_fip_frame(fnic, frame, frame_size, "Outgoing"); + return fnic_send_frame(fnic, frame, frame_size); } /** @@ -1193,64 +773,87 @@ int fnic_send(struct fc_lport *lp, struct fc_frame *fp) void fnic_flush_tx(struct work_struct *work) { struct fnic *fnic = container_of(work, struct fnic, flush_work); - struct sk_buff *skb; struct fc_frame *fp; + struct fnic_frame_list *cur_frame, *next; - while ((skb = skb_dequeue(&fnic->tx_queue))) { - fp = (struct fc_frame *)skb; - fnic_send_frame(fnic, fp); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Flush queued frames"); + + list_for_each_entry_safe(cur_frame, next, &fnic->tx_queue, links) { + fp = cur_frame->fp; + list_del(&cur_frame->links); + fnic_send_frame(fnic, fp, cur_frame->frame_len); + mempool_free(cur_frame, fnic->frame_elem_pool); } } -/** - * fnic_set_eth_mode() - put fnic into ethernet mode. - * @fnic: fnic device - * - * Called without fnic lock held. - */ -static void fnic_set_eth_mode(struct fnic *fnic) +int +fnic_fdls_register_portid(struct fnic_iport_s *iport, u32 port_id, + void *fp) { - unsigned long flags; - enum fnic_state old_state; + struct fnic *fnic = iport->fnic; + struct ethhdr *ethhdr; int ret; - spin_lock_irqsave(&fnic->fnic_lock, flags); -again: - old_state = fnic->state; - switch (old_state) { - case FNIC_IN_FC_MODE: - case FNIC_IN_ETH_TRANS_FC_MODE: - default: - fnic->state = FNIC_IN_FC_TRANS_ETH_MODE; - spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Setting port id: 0x%x fp: 0x%p fnic state: %d", port_id, + fp, fnic->state); - ret = fnic_fw_reset_handler(fnic); - - spin_lock_irqsave(&fnic->fnic_lock, flags); - if (fnic->state != FNIC_IN_FC_TRANS_ETH_MODE) - goto again; - if (ret) - fnic->state = old_state; - break; - - case FNIC_IN_FC_TRANS_ETH_MODE: - case FNIC_IN_ETH_MODE: - break; + if (fp) { + ethhdr = (struct ethhdr *) fp; + vnic_dev_add_addr(fnic->vdev, ethhdr->h_dest); + } + + /* Change state to reflect transition to FC mode */ + if (fnic->state == FNIC_IN_ETH_MODE || fnic->state == FNIC_IN_FC_MODE) + fnic->state = FNIC_IN_ETH_TRANS_FC_MODE; + else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Unexpected fnic state while processing FLOGI response\n"); + return -1; + } + + /* + * Send FLOGI registration to firmware to set up FC mode. + * The new address will be set up when registration completes. + */ + ret = fnic_flogi_reg_handler(fnic, port_id); + if (ret < 0) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI registration error ret: %d fnic state: %d\n", + ret, fnic->state); + if (fnic->state == FNIC_IN_ETH_TRANS_FC_MODE) + fnic->state = FNIC_IN_ETH_MODE; + + return -1; + } + iport->fabric.flags |= FNIC_FDLS_FPMA_LEARNT; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI registration success\n"); + return 0; +} + +void fnic_free_txq(struct list_head *head) +{ + struct fnic_frame_list *cur_frame, *next; + + list_for_each_entry_safe(cur_frame, next, head, links) { + list_del(&cur_frame->links); + kfree(cur_frame->fp); + kfree(cur_frame); } - spin_unlock_irqrestore(&fnic->fnic_lock, flags); } static void fnic_wq_complete_frame_send(struct vnic_wq *wq, struct cq_desc *cq_desc, struct vnic_wq_buf *buf, void *opaque) { - struct sk_buff *skb = buf->os_buf; - struct fc_frame *fp = (struct fc_frame *)skb; struct fnic *fnic = vnic_dev_priv(wq->vdev); dma_unmap_single(&fnic->pdev->dev, buf->dma_addr, buf->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(fp_skb(fp)); + mempool_free(buf->os_buf, fnic->frame_pool); buf->os_buf = NULL; } @@ -1288,119 +891,218 @@ int fnic_wq_cmpl_handler(struct fnic *fnic, int work_to_do) void fnic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf) { - struct fc_frame *fp = buf->os_buf; struct fnic *fnic = vnic_dev_priv(wq->vdev); dma_unmap_single(&fnic->pdev->dev, buf->dma_addr, buf->len, DMA_TO_DEVICE); - dev_kfree_skb(fp_skb(fp)); + kfree(buf->os_buf); buf->os_buf = NULL; } -void fnic_fcoe_reset_vlans(struct fnic *fnic) +void +fnic_fdls_add_tport(struct fnic_iport_s *iport, struct fnic_tport_s *tport, + unsigned long flags) { - unsigned long flags; - struct fcoe_vlan *vlan; - struct fcoe_vlan *next; + struct fnic *fnic = iport->fnic; + struct fc_rport *rport; + struct fc_rport_identifiers ids; + struct rport_dd_data_s *rdd_data; - /* - * indicate a link down to fcoe so that all fcf's are free'd - * might not be required since we did this before sending vlan - * discovery request - */ - spin_lock_irqsave(&fnic->vlans_lock, flags); - if (!list_empty(&fnic->vlans)) { - list_for_each_entry_safe(vlan, next, &fnic->vlans, list) { - list_del(&vlan->list); - kfree(vlan); - } + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Adding rport fcid: 0x%x", tport->fcid); + + ids.node_name = tport->wwnn; + ids.port_name = tport->wwpn; + ids.port_id = tport->fcid; + ids.roles = FC_RPORT_ROLE_FCP_TARGET; + + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + rport = fc_remote_port_add(fnic->host, 0, &ids); + spin_lock_irqsave(&fnic->fnic_lock, flags); + if (!rport) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Failed to add rport for tport: 0x%x", tport->fcid); + return; } - spin_unlock_irqrestore(&fnic->vlans_lock, flags); + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Added rport fcid: 0x%x", tport->fcid); + + /* Mimic these assignments in queuecommand to avoid timing issues */ + rport->maxframe_size = FNIC_FC_MAX_PAYLOAD_LEN; + rport->supported_classes = FC_COS_CLASS3 | FC_RPORT_ROLE_FCP_TARGET; + rdd_data = rport->dd_data; + rdd_data->tport = tport; + rdd_data->iport = iport; + tport->rport = rport; + tport->flags |= FNIC_FDLS_SCSI_REGISTERED; } -void fnic_handle_fip_timer(struct fnic *fnic) +void +fnic_fdls_remove_tport(struct fnic_iport_s *iport, + struct fnic_tport_s *tport, unsigned long flags) { + struct fnic *fnic = iport->fnic; + struct rport_dd_data_s *rdd_data; + + struct fc_rport *rport; + + if (!tport) + return; + + fdls_set_tport_state(tport, FDLS_TGT_STATE_OFFLINE); + rport = tport->rport; + + if (rport) { + /* tport resource release will be done + * after fnic_terminate_rport_io() + */ + tport->flags |= FNIC_FDLS_TPORT_DELETED; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + + /* Interface to scsi_fc_transport */ + fc_remote_port_delete(rport); + + spin_lock_irqsave(&fnic->fnic_lock, flags); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Deregistered and freed tport fcid: 0x%x from scsi transport fc", + tport->fcid); + + /* + * the dd_data is allocated by fc transport + * of size dd_fcrport_size + */ + rdd_data = rport->dd_data; + rdd_data->tport = NULL; + rdd_data->iport = NULL; + list_del(&tport->links); + kfree(tport); + } else { + fnic_del_tport_timer_sync(fnic, tport); + list_del(&tport->links); + kfree(tport); + } +} + +void fnic_delete_fcp_tports(struct fnic *fnic) +{ + struct fnic_tport_s *tport, *next; unsigned long flags; - struct fcoe_vlan *vlan; - struct fnic_stats *fnic_stats = &fnic->fnic_stats; - u64 sol_time; spin_lock_irqsave(&fnic->fnic_lock, flags); - if (fnic->stop_rx_link_events) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - return; + list_for_each_entry_safe(tport, next, &fnic->iport.tport_list, links) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "removing fcp rport fcid: 0x%x", tport->fcid); + fdls_set_tport_state(tport, FDLS_TGT_STATE_OFFLINING); + fnic_del_tport_timer_sync(fnic, tport); + fnic_fdls_remove_tport(&fnic->iport, tport, flags); } spin_unlock_irqrestore(&fnic->fnic_lock, flags); +} - if (fnic->ctlr.mode == FIP_MODE_NON_FIP) - return; +/** + * fnic_tport_event_handler() - Handler for remote port events + * in the tport_event_queue. + * + * @work: Handle to the remote port being dequeued + */ +void fnic_tport_event_handler(struct work_struct *work) +{ + struct fnic *fnic = container_of(work, struct fnic, tport_work); + struct fnic_tport_event_s *cur_evt, *next; + unsigned long flags; + struct fnic_tport_s *tport; - spin_lock_irqsave(&fnic->vlans_lock, flags); - if (list_empty(&fnic->vlans)) { - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - /* no vlans available, try again */ - if (unlikely(fnic_log_level & FNIC_FCS_LOGGING)) - if (printk_ratelimit()) - shost_printk(KERN_DEBUG, fnic->lport->host, - "Start VLAN Discovery\n"); - fnic_event_enq(fnic, FNIC_EVT_START_VLAN_DISC); - return; + spin_lock_irqsave(&fnic->fnic_lock, flags); + list_for_each_entry_safe(cur_evt, next, &fnic->tport_event_list, links) { + tport = cur_evt->arg1; + switch (cur_evt->event) { + case TGT_EV_RPORT_ADD: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Add rport event"); + if (tport->state == FDLS_TGT_STATE_READY) { + fnic_fdls_add_tport(&fnic->iport, + (struct fnic_tport_s *) cur_evt->arg1, flags); + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Target not ready. Add rport event dropped: 0x%x", + tport->fcid); + } + break; + case TGT_EV_RPORT_DEL: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Remove rport event"); + if (tport->state == FDLS_TGT_STATE_OFFLINING) { + fnic_fdls_remove_tport(&fnic->iport, + (struct fnic_tport_s *) cur_evt->arg1, flags); + } else { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "remove rport event dropped tport fcid: 0x%x", + tport->fcid); + } + break; + case TGT_EV_TPORT_DELETE: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Delete tport event"); + fdls_delete_tport(tport->iport, tport); + break; + default: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Unknown tport event"); + break; + } + list_del(&cur_evt->links); + kfree(cur_evt); + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); +} + +void fnic_flush_tport_event_list(struct fnic *fnic) +{ + struct fnic_tport_event_s *cur_evt, *next; + unsigned long flags; + + spin_lock_irqsave(&fnic->fnic_lock, flags); + list_for_each_entry_safe(cur_evt, next, &fnic->tport_event_list, links) { + list_del(&cur_evt->links); + kfree(cur_evt); } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); +} - vlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, list); - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "fip_timer: vlan %d state %d sol_count %d\n", - vlan->vid, vlan->state, vlan->sol_count); - switch (vlan->state) { - case FIP_VLAN_USED: - FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "FIP VLAN is selected for FC transaction\n"); - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - break; - case FIP_VLAN_FAILED: - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - /* if all vlans are in failed state, restart vlan disc */ - if (unlikely(fnic_log_level & FNIC_FCS_LOGGING)) - if (printk_ratelimit()) - shost_printk(KERN_DEBUG, fnic->lport->host, - "Start VLAN Discovery\n"); - fnic_event_enq(fnic, FNIC_EVT_START_VLAN_DISC); - break; - case FIP_VLAN_SENT: - if (vlan->sol_count >= FCOE_CTLR_MAX_SOL) { - /* - * no response on this vlan, remove from the list. - * Try the next vlan - */ - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "Dequeue this VLAN ID %d from list\n", - vlan->vid); - list_del(&vlan->list); - kfree(vlan); - vlan = NULL; - if (list_empty(&fnic->vlans)) { - /* we exhausted all vlans, restart vlan disc */ - spin_unlock_irqrestore(&fnic->vlans_lock, - flags); - FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "fip_timer: vlan list empty, " - "trigger vlan disc\n"); - fnic_event_enq(fnic, FNIC_EVT_START_VLAN_DISC); - return; - } - /* check the next vlan */ - vlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, - list); - fnic->set_vlan(fnic, vlan->vid); - vlan->state = FIP_VLAN_SENT; /* sent now */ - } - spin_unlock_irqrestore(&fnic->vlans_lock, flags); - atomic64_inc(&fnic_stats->vlan_stats.sol_expiry_count); - vlan->sol_count++; - sol_time = jiffies + msecs_to_jiffies - (FCOE_CTLR_START_DELAY); - mod_timer(&fnic->fip_timer, round_jiffies(sol_time)); - break; +void fnic_reset_work_handler(struct work_struct *work) +{ + struct fnic *cur_fnic, *next_fnic; + unsigned long reset_fnic_list_lock_flags; + int host_reset_ret_code; + + /* + * This is a single thread. It is per fnic module, not per fnic + * All the fnics that need to be reset + * have been serialized via the reset fnic list. + */ + spin_lock_irqsave(&reset_fnic_list_lock, reset_fnic_list_lock_flags); + list_for_each_entry_safe(cur_fnic, next_fnic, &reset_fnic_list, links) { + list_del(&cur_fnic->links); + spin_unlock_irqrestore(&reset_fnic_list_lock, + reset_fnic_list_lock_flags); + + dev_err(&cur_fnic->pdev->dev, "fnic: <%d>: issuing a host reset\n", + cur_fnic->fnic_num); + host_reset_ret_code = fnic_host_reset(cur_fnic->host); + dev_err(&cur_fnic->pdev->dev, + "fnic: <%d>: returned from host reset with status: %d\n", + cur_fnic->fnic_num, host_reset_ret_code); + + spin_lock_irqsave(&cur_fnic->fnic_lock, cur_fnic->lock_flags); + cur_fnic->pc_rscn_handling_status = + PC_RSCN_HANDLING_NOT_IN_PROGRESS; + spin_unlock_irqrestore(&cur_fnic->fnic_lock, cur_fnic->lock_flags); + + spin_lock_irqsave(&reset_fnic_list_lock, + reset_fnic_list_lock_flags); } + spin_unlock_irqrestore(&reset_fnic_list_lock, + reset_fnic_list_lock_flags); } diff --git a/drivers/scsi/fnic/fnic_fdls.h b/drivers/scsi/fnic/fnic_fdls.h new file mode 100644 index 000000000000..8e610b65ad57 --- /dev/null +++ b/drivers/scsi/fnic/fnic_fdls.h @@ -0,0 +1,434 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2008 Cisco Systems, Inc. All rights reserved. + * Copyright 2007 Nuova Systems, Inc. All rights reserved. + */ + +#ifndef _FNIC_FDLS_H_ +#define _FNIC_FDLS_H_ + +#include "fnic_stats.h" +#include "fdls_fc.h" + +/* FDLS - Fabric discovery and login services + * -> VLAN discovery + * -> retry every retry delay seconds until it succeeds. + * <- List of VLANs + * + * -> Solicitation + * <- Solicitation response (Advertisement) + * + * -> FCF selection & FLOGI ( FLOGI timeout - 2 * E_D_TOV) + * <- FLOGI response + * + * -> FCF keep alive + * <- FCF keep alive + * + * -> PLOGI to FFFFFC (DNS) (PLOGI timeout - 2 * R_A_TOV) + * -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV) + * <- PLOGI response + * -> Retry PLOGI to FFFFFC (DNS) - Number of retries from vnic.cfg + * + * -> SCR to FFFFFC (DNS) (SCR timeout - 2 * R_A_TOV) + * -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV) + * <- SCR response + * -> Retry SCR - Number of retries 2 + * + * -> GPN_FT to FFFFFC (GPN_FT timeout - 2 * R_A_TOV)a + * -> Retry on BUSY until it succeeds + * -> Retry on BUSY until it succeeds + * -> 2 retries on timeout + * + * -> RFT_ID to FFFFFC (DNS) (RFT_ID timeout - 3 * R_A_TOV) + * -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV) + * -> Retry RFT_ID to FFFFFC (DNS) (Number of retries 2 ) + * -> Ignore if both retires fail. + * + * Session establishment with targets + * For each PWWN + * -> PLOGI to FCID of that PWWN (PLOGI timeout 2 * R_A_TOV) + * -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV) + * <- PLOGI response + * -> Retry PLOGI. Num retries using vnic.cfg + * + * -> PRLI to FCID of that PWWN (PRLI timeout 2 * R_A_TOV) + * -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV) + * <- PRLI response + * -> Retry PRLI. Num retries using vnic.cfg + * + */ + +#define FDLS_RETRY_COUNT 2 + +/* + * OXID encoding: + * bits 0-8: oxid idx - allocated from poool + * bits 9-13: oxid frame code from fnic_oxid_frame_type_e + * bits 14-15: all zeros + */ +#define FNIC_OXID_POOL_SZ (512) /* always power of 2 */ +#define FNIC_OXID_ENCODE(idx, frame_type) (frame_type | idx) +#define FNIC_FRAME_MASK 0xFE00 +#define FNIC_FRAME_TYPE(oxid) (oxid & FNIC_FRAME_MASK) +#define FNIC_OXID_IDX(oxid) ((oxid) & (FNIC_OXID_POOL_SZ - 1)) + +#define OXID_RECLAIM_TOV(iport) (2 * iport->r_a_tov) /* in milliseconds */ + +#define FNIC_FDLS_FABRIC_ABORT_ISSUED 0x1 +#define FNIC_FDLS_FPMA_LEARNT 0x2 + +/* tport flags */ +#define FNIC_FDLS_TPORT_IN_GPN_FT_LIST 0x1 +#define FNIC_FDLS_TGT_ABORT_ISSUED 0x2 +#define FNIC_FDLS_TPORT_SEND_ADISC 0x4 +#define FNIC_FDLS_RETRY_FRAME 0x8 +#define FNIC_FDLS_TPORT_BUSY 0x10 +#define FNIC_FDLS_TPORT_TERMINATING 0x20 +#define FNIC_FDLS_TPORT_DELETED 0x40 +#define FNIC_FDLS_SCSI_REGISTERED 0x200 + +/* Retry supported by rport(returned by prli service parameters) */ +#define FDLS_FC_RP_FLAGS_RETRY 0x1 + +#define fdls_set_state(_fdls_fabric, _state) ((_fdls_fabric)->state = _state) +#define fdls_get_state(_fdls_fabric) ((_fdls_fabric)->state) + +#define FNIC_FDMI_ACTIVE 0x8 +#define FNIC_FIRST_LINK_UP 0x2 + +#define fdls_set_tport_state(_tport, _state) (_tport->state = _state) +#define fdls_get_tport_state(_tport) (_tport->state) + +#define FNIC_PORTSPEED_10GBIT 1 +#define FNIC_FRAME_HT_ROOM (2148) +#define FNIC_FCOE_FRAME_MAXSZ (2112) + + +#define FNIC_FRAME_TYPE_FABRIC_FLOGI 0x1000 +#define FNIC_FRAME_TYPE_FABRIC_PLOGI 0x1200 +#define FNIC_FRAME_TYPE_FABRIC_RPN 0x1400 +#define FNIC_FRAME_TYPE_FABRIC_RFT 0x1600 +#define FNIC_FRAME_TYPE_FABRIC_RFF 0x1800 +#define FNIC_FRAME_TYPE_FABRIC_SCR 0x1A00 +#define FNIC_FRAME_TYPE_FABRIC_GPN_FT 0x1C00 +#define FNIC_FRAME_TYPE_FABRIC_LOGO 0x1E00 +#define FNIC_FRAME_TYPE_FDMI_PLOGI 0x2000 +#define FNIC_FRAME_TYPE_FDMI_RHBA 0x2200 +#define FNIC_FRAME_TYPE_FDMI_RPA 0x2400 +#define FNIC_FRAME_TYPE_TGT_PLOGI 0x2600 +#define FNIC_FRAME_TYPE_TGT_PRLI 0x2800 +#define FNIC_FRAME_TYPE_TGT_ADISC 0x2A00 +#define FNIC_FRAME_TYPE_TGT_LOGO 0x2C00 + +struct fnic_fip_fcf_s { + uint16_t vlan_id; + uint8_t fcf_mac[6]; + uint8_t fcf_priority; + uint32_t fka_adv_period; + uint8_t ka_disabled; +}; + +enum fnic_fdls_state_e { + FDLS_STATE_INIT = 0, + FDLS_STATE_LINKDOWN, + FDLS_STATE_FABRIC_LOGO, + FDLS_STATE_FLOGO_DONE, + FDLS_STATE_FABRIC_FLOGI, + FDLS_STATE_FABRIC_PLOGI, + FDLS_STATE_RPN_ID, + FDLS_STATE_REGISTER_FC4_TYPES, + FDLS_STATE_REGISTER_FC4_FEATURES, + FDLS_STATE_SCR, + FDLS_STATE_GPN_FT, + FDLS_STATE_TGT_DISCOVERY, + FDLS_STATE_RSCN_GPN_FT, + FDLS_STATE_SEND_GPNFT +}; + +struct fnic_fdls_fabric_s { + enum fnic_fdls_state_e state; + uint32_t flags; + struct list_head tport_list; /* List of discovered tports */ + struct timer_list retry_timer; + int del_timer_inprogress; + int del_fdmi_timer_inprogress; + int retry_counter; + int timer_pending; + int fdmi_retry; + struct timer_list fdmi_timer; + int fdmi_pending; +}; + +struct fnic_fdls_fip_s { + uint32_t state; + uint32_t flogi_retry; +}; + +/* Message to tport_event_handler */ +enum fnic_tgt_msg_id { + TGT_EV_NONE = 0, + TGT_EV_RPORT_ADD, + TGT_EV_RPORT_DEL, + TGT_EV_TPORT_DELETE, + TGT_EV_REMOVE +}; + +struct fnic_tport_event_s { + struct list_head links; + enum fnic_tgt_msg_id event; + void *arg1; +}; + +enum fdls_tgt_state_e { + FDLS_TGT_STATE_INIT = 0, + FDLS_TGT_STATE_PLOGI, + FDLS_TGT_STATE_PRLI, + FDLS_TGT_STATE_READY, + FDLS_TGT_STATE_LOGO_RECEIVED, + FDLS_TGT_STATE_ADISC, + FDL_TGT_STATE_PLOGO, + FDLS_TGT_STATE_OFFLINING, + FDLS_TGT_STATE_OFFLINE +}; + +struct fnic_tport_s { + struct list_head links; /* To link the tports */ + enum fdls_tgt_state_e state; + uint32_t flags; + uint32_t fcid; + uint64_t wwpn; + uint64_t wwnn; + uint16_t active_oxid; + uint16_t tgt_flags; + atomic_t in_flight; /* io counter */ + uint16_t max_payload_size; + uint16_t r_a_tov; + uint16_t e_d_tov; + uint16_t lun0_delay; + int max_concur_seqs; + uint32_t fcp_csp; + struct timer_list retry_timer; + int del_timer_inprogress; + int retry_counter; + int timer_pending; + unsigned int num_pending_cmds; + int nexus_restart_count; + int exch_reset_in_progress; + void *iport; + struct work_struct tport_del_work; + struct completion *tport_del_done; + struct fc_rport *rport; + char str_wwpn[20]; + char str_wwnn[20]; +}; + +/* OXID pool related structures */ +struct reclaim_entry_s { + struct list_head links; + /* oxid that needs to be freed after 2*r_a_tov */ + uint16_t oxid_idx; + /* in jiffies. Use this to waiting time */ + unsigned long expires; + unsigned long *bitmap; +}; + +/* used for allocating oxids for fabric and fdmi requests */ +struct fnic_oxid_pool_s { + DECLARE_BITMAP(bitmap, FNIC_OXID_POOL_SZ); + int sz; /* size of the pool or block */ + int next_idx; /* used for cycling through the oxid pool */ + + /* retry schedule free */ + DECLARE_BITMAP(pending_schedule_free, FNIC_OXID_POOL_SZ); + struct delayed_work schedule_oxid_free_retry; + + /* List of oxids that need to be freed and reclaimed. + * This list is shared by all the oxid pools + */ + struct list_head oxid_reclaim_list; + /* Work associated with reclaim list */ + struct delayed_work oxid_reclaim_work; +}; + +/* iport */ +enum fnic_iport_state_e { + FNIC_IPORT_STATE_INIT = 0, + FNIC_IPORT_STATE_LINK_WAIT, + FNIC_IPORT_STATE_FIP, + FNIC_IPORT_STATE_FABRIC_DISC, + FNIC_IPORT_STATE_READY +}; + +struct fnic_iport_s { + enum fnic_iport_state_e state; + struct fnic *fnic; + uint64_t boot_time; + uint32_t flags; + int usefip; + uint8_t hwmac[6]; /* HW MAC Addr */ + uint8_t fpma[6]; /* Fabric Provided MA */ + uint8_t fcfmac[6]; /* MAC addr of Fabric */ + uint16_t vlan_id; + uint32_t fcid; + + /* oxid pool */ + struct fnic_oxid_pool_s oxid_pool; + + /* + * fabric reqs are serialized and only one req at a time. + * Tracking the oxid for sending abort + */ + uint16_t active_oxid_fabric_req; + /* fdmi only */ + uint16_t active_oxid_fdmi_plogi; + uint16_t active_oxid_fdmi_rhba; + uint16_t active_oxid_fdmi_rpa; + + struct fnic_fip_fcf_s selected_fcf; + struct fnic_fdls_fip_s fip; + struct fnic_fdls_fabric_s fabric; + struct list_head tport_list; + struct list_head tport_list_pending_del; + /* list of tports for which we are yet to send PLOGO */ + struct list_head inprocess_tport_list; + struct list_head deleted_tport_list; + struct work_struct tport_event_work; + uint32_t e_d_tov; /* msec */ + uint32_t r_a_tov; /* msec */ + uint32_t link_supported_speeds; + uint32_t max_flogi_retries; + uint32_t max_plogi_retries; + uint32_t plogi_timeout; + uint32_t service_params; + uint64_t wwpn; + uint64_t wwnn; + uint16_t max_payload_size; + spinlock_t deleted_tport_lst_lock; + struct completion *flogi_reg_done; + struct fnic_iport_stats iport_stats; + char str_wwpn[20]; + char str_wwnn[20]; +}; + +struct rport_dd_data_s { + struct fnic_tport_s *tport; + struct fnic_iport_s *iport; +}; + +enum fnic_recv_frame_type_e { + FNIC_FABRIC_FLOGI_RSP = 1, + FNIC_FABRIC_PLOGI_RSP, + FNIC_FABRIC_RPN_RSP, + FNIC_FABRIC_RFT_RSP, + FNIC_FABRIC_RFF_RSP, + FNIC_FABRIC_SCR_RSP, + FNIC_FABRIC_GPN_FT_RSP, + FNIC_FABRIC_BLS_ABTS_RSP, + FNIC_FDMI_PLOGI_RSP, + FNIC_FDMI_REG_HBA_RSP, + FNIC_FDMI_RPA_RSP, + FNIC_FDMI_BLS_ABTS_RSP, + FNIC_FABRIC_LOGO_RSP, + + /* responses to target requests */ + FNIC_TPORT_PLOGI_RSP, + FNIC_TPORT_PRLI_RSP, + FNIC_TPORT_ADISC_RSP, + FNIC_TPORT_BLS_ABTS_RSP, + FNIC_TPORT_LOGO_RSP, + + /* unsolicited requests */ + FNIC_BLS_ABTS_REQ, + FNIC_ELS_PLOGI_REQ, + FNIC_ELS_RSCN_REQ, + FNIC_ELS_LOGO_REQ, + FNIC_ELS_ECHO_REQ, + FNIC_ELS_ADISC, + FNIC_ELS_RLS, + FNIC_ELS_RRQ, + FNIC_ELS_UNSUPPORTED_REQ, +}; + +enum fnic_port_speeds { + DCEM_PORTSPEED_NONE = 0, + DCEM_PORTSPEED_1G = 1000, + DCEM_PORTSPEED_2G = 2000, + DCEM_PORTSPEED_4G = 4000, + DCEM_PORTSPEED_8G = 8000, + DCEM_PORTSPEED_10G = 10000, + DCEM_PORTSPEED_16G = 16000, + DCEM_PORTSPEED_20G = 20000, + DCEM_PORTSPEED_25G = 25000, + DCEM_PORTSPEED_32G = 32000, + DCEM_PORTSPEED_40G = 40000, + DCEM_PORTSPEED_4x10G = 41000, + DCEM_PORTSPEED_50G = 50000, + DCEM_PORTSPEED_64G = 64000, + DCEM_PORTSPEED_100G = 100000, + DCEM_PORTSPEED_128G = 128000, +}; + +/* Function Declarations */ +/* fdls_disc.c */ +void fnic_fdls_disc_init(struct fnic_iport_s *iport); +void fnic_fdls_disc_start(struct fnic_iport_s *iport); +void fnic_fdls_recv_frame(struct fnic_iport_s *iport, void *rx_frame, + int len, int fchdr_offset); +void fnic_fdls_link_down(struct fnic_iport_s *iport); +int fdls_init_frame_pool(struct fnic_iport_s *iport); +uint8_t *fdls_alloc_frame(struct fnic_iport_s *iport); +uint16_t fdls_alloc_oxid(struct fnic_iport_s *iport, int oxid_frame_type, + uint16_t *active_oxid); +void fdls_free_oxid(struct fnic_iport_s *iport, + uint16_t oxid, uint16_t *active_oxid); +void fdls_tgt_logout(struct fnic_iport_s *iport, + struct fnic_tport_s *tport); +void fnic_del_fabric_timer_sync(struct fnic *fnic); +void fnic_del_tport_timer_sync(struct fnic *fnic, + struct fnic_tport_s *tport); +void fdls_send_fabric_logo(struct fnic_iport_s *iport); +int fnic_fdls_validate_and_get_frame_type(struct fnic_iport_s *iport, + struct fc_frame_header *fchdr); +void fdls_send_tport_abts(struct fnic_iport_s *iport, + struct fnic_tport_s *tport); +bool fdls_delete_tport(struct fnic_iport_s *iport, + struct fnic_tport_s *tport); +void fdls_fdmi_timer_callback(struct timer_list *t); + +/* fnic_fcs.c */ +void fnic_fdls_init(struct fnic *fnic, int usefip); +void fnic_send_fcoe_frame(struct fnic_iport_s *iport, void *frame, + int frame_size); +void fnic_fcoe_send_vlan_req(struct fnic *fnic); +int fnic_send_fip_frame(struct fnic_iport_s *iport, + void *frame, int frame_size); +void fnic_fdls_learn_fcoe_macs(struct fnic_iport_s *iport, void *rx_frame, + uint8_t *fcid); +void fnic_fdls_add_tport(struct fnic_iport_s *iport, + struct fnic_tport_s *tport, unsigned long flags); +void fnic_fdls_remove_tport(struct fnic_iport_s *iport, + struct fnic_tport_s *tport, + unsigned long flags); + +/* fip.c */ +void fnic_fcoe_send_vlan_req(struct fnic *fnic); +void fnic_common_fip_cleanup(struct fnic *fnic); +int fdls_fip_recv_frame(struct fnic *fnic, void *frame); +void fnic_handle_fcs_ka_timer(struct timer_list *t); +void fnic_handle_enode_ka_timer(struct timer_list *t); +void fnic_handle_vn_ka_timer(struct timer_list *t); +void fnic_handle_fip_timer(struct timer_list *t); +extern void fdls_fabric_timer_callback(struct timer_list *t); + +/* fnic_scsi.c */ +void fnic_scsi_fcpio_reset(struct fnic *fnic); +extern void fdls_fabric_timer_callback(struct timer_list *t); +void fnic_rport_exch_reset(struct fnic *fnic, u32 fcid); +int fnic_fdls_register_portid(struct fnic_iport_s *iport, u32 port_id, + void *fp); +struct fnic_tport_s *fnic_find_tport_by_fcid(struct fnic_iport_s *iport, + uint32_t fcid); +struct fnic_tport_s *fnic_find_tport_by_wwpn(struct fnic_iport_s *iport, + uint64_t wwpn); + +#endif /* _FNIC_FDLS_H_ */ diff --git a/drivers/scsi/fnic/fnic_fip.h b/drivers/scsi/fnic/fnic_fip.h deleted file mode 100644 index 79f53029737b..000000000000 --- a/drivers/scsi/fnic/fnic_fip.h +++ /dev/null @@ -1,48 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2008 Cisco Systems, Inc. All rights reserved. - * Copyright 2007 Nuova Systems, Inc. All rights reserved. - */ - -#ifndef _FNIC_FIP_H_ -#define _FNIC_FIP_H_ - - -#define FCOE_CTLR_START_DELAY 2000 /* ms after first adv. to choose FCF */ -#define FCOE_CTLR_FIPVLAN_TOV 2000 /* ms after FIP VLAN disc */ -#define FCOE_CTLR_MAX_SOL 8 - -#define FINC_MAX_FLOGI_REJECTS 8 - -struct vlan { - __be16 vid; - __be16 type; -}; - -/* - * VLAN entry. - */ -struct fcoe_vlan { - struct list_head list; - u16 vid; /* vlan ID */ - u16 sol_count; /* no. of sols sent */ - u16 state; /* state */ -}; - -enum fip_vlan_state { - FIP_VLAN_AVAIL = 0, /* don't do anything */ - FIP_VLAN_SENT = 1, /* sent */ - FIP_VLAN_USED = 2, /* succeed */ - FIP_VLAN_FAILED = 3, /* failed to response */ -}; - -struct fip_vlan { - struct ethhdr eth; - struct fip_header fip; - struct { - struct fip_mac_desc mac; - struct fip_wwn_desc wwnn; - } desc; -}; - -#endif /* __FINC_FIP_H_ */ diff --git a/drivers/scsi/fnic/fnic_io.h b/drivers/scsi/fnic/fnic_io.h index 5895ead20e14..0d974e040ab7 100644 --- a/drivers/scsi/fnic/fnic_io.h +++ b/drivers/scsi/fnic/fnic_io.h @@ -7,6 +7,7 @@ #define _FNIC_IO_H_ #include +#include "fnic_fdls.h" #define FNIC_DFLT_SG_DESC_CNT 32 #define FNIC_MAX_SG_DESC_CNT 256 /* Maximum descriptors per sgl */ @@ -41,6 +42,8 @@ enum fnic_ioreq_state { }; struct fnic_io_req { + struct fnic_iport_s *iport; + struct fnic_tport_s *tport; struct host_sg_desc *sgl_list; /* sgl list */ void *sgl_list_alloc; /* sgl list address used for free */ dma_addr_t sense_buf_pa; /* dma address for sense buffer*/ @@ -55,15 +58,4 @@ struct fnic_io_req { unsigned int tag; struct scsi_cmnd *sc; /* midlayer's cmd pointer */ }; - -enum fnic_port_speeds { - DCEM_PORTSPEED_NONE = 0, - DCEM_PORTSPEED_1G = 1000, - DCEM_PORTSPEED_10G = 10000, - DCEM_PORTSPEED_20G = 20000, - DCEM_PORTSPEED_25G = 25000, - DCEM_PORTSPEED_40G = 40000, - DCEM_PORTSPEED_4x10G = 41000, - DCEM_PORTSPEED_100G = 100000, -}; #endif /* _FNIC_IO_H_ */ diff --git a/drivers/scsi/fnic/fnic_isr.c b/drivers/scsi/fnic/fnic_isr.c index ff85441c6cea..7ed50b11afa6 100644 --- a/drivers/scsi/fnic/fnic_isr.c +++ b/drivers/scsi/fnic/fnic_isr.c @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include #include "vnic_dev.h" #include "vnic_intr.h" @@ -222,7 +222,7 @@ int fnic_request_intr(struct fnic *fnic) fnic->msix[i].devname, fnic->msix[i].devid); if (err) { - FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "request_irq failed with error: %d\n", err); fnic_free_intr(fnic); @@ -250,10 +250,10 @@ int fnic_set_intr_mode_msix(struct fnic *fnic) * We need n RQs, m WQs, o Copy WQs, n+m+o CQs, and n+m+o+1 INTRs * (last INTR is used for WQ/RQ errors and notification area) */ - FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "rq-array size: %d wq-array size: %d copy-wq array size: %d\n", n, m, o); - FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "rq_count: %d raw_wq_count: %d wq_copy_count: %d cq_count: %d\n", fnic->rq_count, fnic->raw_wq_count, fnic->wq_copy_count, fnic->cq_count); @@ -265,17 +265,17 @@ int fnic_set_intr_mode_msix(struct fnic *fnic) vec_count = pci_alloc_irq_vectors(fnic->pdev, min_irqs, vecs, PCI_IRQ_MSIX | PCI_IRQ_AFFINITY); - FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "allocated %d MSI-X vectors\n", vec_count); if (vec_count > 0) { if (vec_count < vecs) { - FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "interrupts number mismatch: vec_count: %d vecs: %d\n", vec_count, vecs); if (vec_count < min_irqs) { - FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "no interrupts for copy wq\n"); return 1; } @@ -287,7 +287,7 @@ int fnic_set_intr_mode_msix(struct fnic *fnic) fnic->wq_copy_count = vec_count - n - m - 1; fnic->wq_count = fnic->raw_wq_count + fnic->wq_copy_count; if (fnic->cq_count != vec_count - 1) { - FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "CQ count: %d does not match MSI-X vector count: %d\n", fnic->cq_count, vec_count); fnic->cq_count = vec_count - 1; @@ -295,23 +295,23 @@ int fnic_set_intr_mode_msix(struct fnic *fnic) fnic->intr_count = vec_count; fnic->err_intr_offset = fnic->rq_count + fnic->wq_count; - FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "rq_count: %d raw_wq_count: %d copy_wq_base: %d\n", fnic->rq_count, fnic->raw_wq_count, fnic->copy_wq_base); - FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "wq_copy_count: %d wq_count: %d cq_count: %d\n", fnic->wq_copy_count, fnic->wq_count, fnic->cq_count); - FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "intr_count: %d err_intr_offset: %u", fnic->intr_count, fnic->err_intr_offset); vnic_dev_set_intr_mode(fnic->vdev, VNIC_DEV_INTR_MODE_MSIX); - FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "fnic using MSI-X\n"); return 0; } @@ -351,7 +351,7 @@ int fnic_set_intr_mode(struct fnic *fnic) fnic->intr_count = 1; fnic->err_intr_offset = 0; - FNIC_ISR_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "Using MSI Interrupts\n"); vnic_dev_set_intr_mode(fnic->vdev, VNIC_DEV_INTR_MODE_MSI); @@ -377,7 +377,7 @@ int fnic_set_intr_mode(struct fnic *fnic) fnic->cq_count = 3; fnic->intr_count = 3; - FNIC_ISR_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_ISR_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "Using Legacy Interrupts\n"); vnic_dev_set_intr_mode(fnic->vdev, VNIC_DEV_INTR_MODE_INTX); diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c index adec0df24bc4..0b20ac8c3f46 100644 --- a/drivers/scsi/fnic/fnic_main.c +++ b/drivers/scsi/fnic/fnic_main.c @@ -16,21 +16,20 @@ #include #include #include -#include #include #include #include #include #include -#include #include #include "vnic_dev.h" #include "vnic_intr.h" #include "vnic_stats.h" #include "fnic_io.h" -#include "fnic_fip.h" #include "fnic.h" +#include "fnic_fdls.h" +#include "fdls_fc.h" #define PCI_DEVICE_ID_CISCO_FNIC 0x0045 @@ -39,12 +38,18 @@ static struct kmem_cache *fnic_sgl_cache[FNIC_SGL_NUM_CACHES]; static struct kmem_cache *fnic_io_req_cache; +static struct kmem_cache *fdls_frame_cache; +static struct kmem_cache *fdls_frame_elem_cache; static LIST_HEAD(fnic_list); static DEFINE_SPINLOCK(fnic_list_lock); static DEFINE_IDA(fnic_ida); +struct work_struct reset_fnic_work; +LIST_HEAD(reset_fnic_list); +DEFINE_SPINLOCK(reset_fnic_list_lock); + /* Supported devices by fnic module */ -static struct pci_device_id fnic_id_table[] = { +static const struct pci_device_id fnic_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_CISCO, PCI_DEVICE_ID_CISCO_FNIC) }, { 0, } }; @@ -60,6 +65,14 @@ unsigned int fnic_log_level; module_param(fnic_log_level, int, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(fnic_log_level, "bit mask of fnic logging levels"); +unsigned int fnic_fdmi_support = 1; +module_param(fnic_fdmi_support, int, 0644); +MODULE_PARM_DESC(fnic_fdmi_support, "FDMI support"); + +static unsigned int fnic_tgt_id_binding = 1; +module_param(fnic_tgt_id_binding, uint, 0644); +MODULE_PARM_DESC(fnic_tgt_id_binding, + "Target ID binding (0 for none. 1 for binding by WWPN (default))"); unsigned int io_completions = FNIC_DFLT_IO_COMPLETIONS; module_param(io_completions, int, S_IRUGO|S_IWUSR); @@ -79,15 +92,15 @@ static unsigned int fnic_max_qdepth = FNIC_DFLT_QUEUE_DEPTH; module_param(fnic_max_qdepth, uint, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(fnic_max_qdepth, "Queue depth to report for each LUN"); -static struct libfc_function_template fnic_transport_template = { - .frame_send = fnic_send, - .lport_set_port_id = fnic_set_port_id, - .fcp_abort_io = fnic_empty_scsi_cleanup, - .fcp_cleanup = fnic_empty_scsi_cleanup, - .exch_mgr_reset = fnic_exch_mgr_reset -}; +unsigned int pc_rscn_handling_feature_flag = PC_RSCN_HANDLING_FEATURE_ON; +module_param(pc_rscn_handling_feature_flag, uint, 0644); +MODULE_PARM_DESC(pc_rscn_handling_feature_flag, + "PCRSCN handling (0 for none. 1 to handle PCRSCN (default))"); -static int fnic_slave_alloc(struct scsi_device *sdev) +struct workqueue_struct *reset_fnic_work_queue; +struct workqueue_struct *fnic_fip_queue; + +static int fnic_sdev_init(struct scsi_device *sdev) { struct fc_rport *rport = starget_to_rport(scsi_target(sdev)); @@ -105,8 +118,8 @@ static const struct scsi_host_template fnic_host_template = { .eh_timed_out = fc_eh_timed_out, .eh_abort_handler = fnic_abort_cmd, .eh_device_reset_handler = fnic_device_reset, - .eh_host_reset_handler = fnic_host_reset, - .slave_alloc = fnic_slave_alloc, + .eh_host_reset_handler = fnic_eh_host_reset_handler, + .sdev_init = fnic_sdev_init, .change_queue_depth = scsi_change_queue_depth, .this_id = -1, .cmd_per_lun = 3, @@ -146,7 +159,7 @@ static struct fc_function_template fnic_fc_functions = { .get_host_speed = fnic_get_host_speed, .show_host_speed = 1, .show_host_port_type = 1, - .get_host_port_state = fc_get_host_port_state, + .get_host_port_state = fnic_get_host_port_state, .show_host_port_state = 1, .show_host_symbolic_name = 1, .show_rport_maxframe_size = 1, @@ -157,54 +170,88 @@ static struct fc_function_template fnic_fc_functions = { .show_starget_port_id = 1, .show_rport_dev_loss_tmo = 1, .set_rport_dev_loss_tmo = fnic_set_rport_dev_loss_tmo, - .issue_fc_host_lip = fnic_reset, + .issue_fc_host_lip = fnic_issue_fc_host_lip, .get_fc_host_stats = fnic_get_stats, .reset_fc_host_stats = fnic_reset_host_stats, - .dd_fcrport_size = sizeof(struct fc_rport_libfc_priv), + .dd_fcrport_size = sizeof(struct rport_dd_data_s), .terminate_rport_io = fnic_terminate_rport_io, - .bsg_request = fc_lport_bsg_request, + .bsg_request = NULL, }; static void fnic_get_host_speed(struct Scsi_Host *shost) { - struct fc_lport *lp = shost_priv(shost); - struct fnic *fnic = lport_priv(lp); + struct fnic *fnic = *((struct fnic **) shost_priv(shost)); u32 port_speed = vnic_dev_port_speed(fnic->vdev); + struct fnic_stats *fnic_stats = &fnic->fnic_stats; + + FNIC_MAIN_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "port_speed: %d Mbps", port_speed); + atomic64_set(&fnic_stats->misc_stats.port_speed_in_mbps, port_speed); /* Add in other values as they get defined in fw */ switch (port_speed) { + case DCEM_PORTSPEED_1G: + fc_host_speed(shost) = FC_PORTSPEED_1GBIT; + break; + case DCEM_PORTSPEED_2G: + fc_host_speed(shost) = FC_PORTSPEED_2GBIT; + break; + case DCEM_PORTSPEED_4G: + fc_host_speed(shost) = FC_PORTSPEED_4GBIT; + break; + case DCEM_PORTSPEED_8G: + fc_host_speed(shost) = FC_PORTSPEED_8GBIT; + break; case DCEM_PORTSPEED_10G: fc_host_speed(shost) = FC_PORTSPEED_10GBIT; break; + case DCEM_PORTSPEED_16G: + fc_host_speed(shost) = FC_PORTSPEED_16GBIT; + break; case DCEM_PORTSPEED_20G: fc_host_speed(shost) = FC_PORTSPEED_20GBIT; break; case DCEM_PORTSPEED_25G: fc_host_speed(shost) = FC_PORTSPEED_25GBIT; break; + case DCEM_PORTSPEED_32G: + fc_host_speed(shost) = FC_PORTSPEED_32GBIT; + break; case DCEM_PORTSPEED_40G: case DCEM_PORTSPEED_4x10G: fc_host_speed(shost) = FC_PORTSPEED_40GBIT; break; + case DCEM_PORTSPEED_50G: + fc_host_speed(shost) = FC_PORTSPEED_50GBIT; + break; + case DCEM_PORTSPEED_64G: + fc_host_speed(shost) = FC_PORTSPEED_64GBIT; + break; case DCEM_PORTSPEED_100G: fc_host_speed(shost) = FC_PORTSPEED_100GBIT; break; + case DCEM_PORTSPEED_128G: + fc_host_speed(shost) = FC_PORTSPEED_128GBIT; + break; default: + FNIC_MAIN_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Unknown FC speed: %d Mbps", port_speed); fc_host_speed(shost) = FC_PORTSPEED_UNKNOWN; break; } } +/* Placeholder function */ static struct fc_host_statistics *fnic_get_stats(struct Scsi_Host *host) { int ret; - struct fc_lport *lp = shost_priv(host); - struct fnic *fnic = lport_priv(lp); - struct fc_host_statistics *stats = &lp->host_stats; + struct fnic *fnic = *((struct fnic **) shost_priv(host)); + struct fc_host_statistics *stats = &fnic->fnic_stats.host_stats; struct vnic_stats *vs; unsigned long flags; - if (time_before(jiffies, fnic->stats_time + HZ / FNIC_STATS_RATE_LIMIT)) + if (time_before + (jiffies, fnic->stats_time + HZ / FNIC_STATS_RATE_LIMIT)) return stats; fnic->stats_time = jiffies; @@ -213,24 +260,22 @@ static struct fc_host_statistics *fnic_get_stats(struct Scsi_Host *host) spin_unlock_irqrestore(&fnic->fnic_lock, flags); if (ret) { - FNIC_MAIN_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "fnic: Get vnic stats failed" - " 0x%x", ret); + FNIC_MAIN_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "fnic: Get vnic stats failed: 0x%x", ret); return stats; } vs = fnic->stats; stats->tx_frames = vs->tx.tx_unicast_frames_ok; - stats->tx_words = vs->tx.tx_unicast_bytes_ok / 4; + stats->tx_words = vs->tx.tx_unicast_bytes_ok / 4; stats->rx_frames = vs->rx.rx_unicast_frames_ok; - stats->rx_words = vs->rx.rx_unicast_bytes_ok / 4; + stats->rx_words = vs->rx.rx_unicast_bytes_ok / 4; stats->error_frames = vs->tx.tx_errors + vs->rx.rx_errors; stats->dumped_frames = vs->tx.tx_drops + vs->rx.rx_drop; stats->invalid_crc_count = vs->rx.rx_crc_errors; stats->seconds_since_last_reset = - (jiffies - fnic->stats_reset_time) / HZ; + (jiffies - fnic->stats_reset_time) / HZ; stats->fcp_input_megabytes = div_u64(fnic->fcp_input_bytes, 1000000); stats->fcp_output_megabytes = div_u64(fnic->fcp_output_bytes, 1000000); - return stats; } @@ -311,8 +356,7 @@ void fnic_dump_fchost_stats(struct Scsi_Host *host, static void fnic_reset_host_stats(struct Scsi_Host *host) { int ret; - struct fc_lport *lp = shost_priv(host); - struct fnic *fnic = lport_priv(lp); + struct fnic *fnic = *((struct fnic **) shost_priv(host)); struct fc_host_statistics *stats; unsigned long flags; @@ -325,7 +369,7 @@ static void fnic_reset_host_stats(struct Scsi_Host *host) spin_unlock_irqrestore(&fnic->fnic_lock, flags); if (ret) { - FNIC_MAIN_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_MAIN_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "fnic: Reset vnic stats failed" " 0x%x", ret); return; @@ -344,25 +388,19 @@ void fnic_log_q_error(struct fnic *fnic) for (i = 0; i < fnic->raw_wq_count; i++) { error_status = ioread32(&fnic->wq[i].ctrl->error_status); if (error_status) - shost_printk(KERN_ERR, fnic->lport->host, - "WQ[%d] error_status" - " %d\n", i, error_status); + dev_err(&fnic->pdev->dev, "WQ[%d] error_status %d\n", i, error_status); } for (i = 0; i < fnic->rq_count; i++) { error_status = ioread32(&fnic->rq[i].ctrl->error_status); if (error_status) - shost_printk(KERN_ERR, fnic->lport->host, - "RQ[%d] error_status" - " %d\n", i, error_status); + dev_err(&fnic->pdev->dev, "RQ[%d] error_status %d\n", i, error_status); } for (i = 0; i < fnic->wq_copy_count; i++) { error_status = ioread32(&fnic->hw_copy_wq[i].ctrl->error_status); if (error_status) - shost_printk(KERN_ERR, fnic->lport->host, - "CWQ[%d] error_status" - " %d\n", i, error_status); + dev_err(&fnic->pdev->dev, "CWQ[%d] error_status %d\n", i, error_status); } } @@ -396,8 +434,7 @@ static int fnic_notify_set(struct fnic *fnic) err = vnic_dev_notify_set(fnic->vdev, fnic->wq_copy_count + fnic->copy_wq_base); break; default: - shost_printk(KERN_ERR, fnic->lport->host, - "Interrupt mode should be set up" + dev_err(&fnic->pdev->dev, "Interrupt mode should be set up" " before devcmd notify set %d\n", vnic_dev_get_intr_mode(fnic->vdev)); err = -1; @@ -416,13 +453,6 @@ static void fnic_notify_timer(struct timer_list *t) round_jiffies(jiffies + FNIC_NOTIFY_TIMER_PERIOD)); } -static void fnic_fip_notify_timer(struct timer_list *t) -{ - struct fnic *fnic = from_timer(fnic, t, fip_timer); - - fnic_handle_fip_timer(fnic); -} - static void fnic_notify_timer_start(struct fnic *fnic) { switch (vnic_dev_get_intr_mode(fnic->vdev)) { @@ -522,6 +552,8 @@ static int fnic_cleanup(struct fnic *fnic) vnic_intr_clean(&fnic->intr[i]); mempool_destroy(fnic->io_req_pool); + mempool_destroy(fnic->frame_pool); + mempool_destroy(fnic->frame_elem_pool); for (i = 0; i < FNIC_SGL_NUM_CACHES; i++) mempool_destroy(fnic->io_sgl_pool[i]); @@ -534,25 +566,36 @@ static void fnic_iounmap(struct fnic *fnic) iounmap(fnic->bar0.vaddr); } -/** - * fnic_get_mac() - get assigned data MAC address for FIP code. - * @lport: local port. - */ -static u8 *fnic_get_mac(struct fc_lport *lport) -{ - struct fnic *fnic = lport_priv(lport); - - return fnic->data_src_addr; -} - static void fnic_set_vlan(struct fnic *fnic, u16 vlan_id) { vnic_dev_set_default_vlan(fnic->vdev, vlan_id); } +static void fnic_scsi_init(struct fnic *fnic) +{ + struct Scsi_Host *host = fnic->host; + + snprintf(fnic->name, sizeof(fnic->name) - 1, "%s%d", DRV_NAME, + host->host_no); + + host->transportt = fnic_fc_transport; +} + +static void fnic_free_ioreq_tables_mq(struct fnic *fnic) +{ + int hwq; + + for (hwq = 0; hwq < fnic->wq_copy_count; hwq++) + kfree(fnic->sw_copy_wq[hwq].io_req_table); +} + static int fnic_scsi_drv_init(struct fnic *fnic) { - struct Scsi_Host *host = fnic->lport->host; + struct Scsi_Host *host = fnic->host; + int err; + struct pci_dev *pdev = fnic->pdev; + struct fnic_iport_s *iport = &fnic->iport; + int hwq; /* Configure maximum outstanding IO reqs*/ if (fnic->config.io_throttle_count != FNIC_UCSM_DFLT_THROTTLE_CNT_BLD) @@ -563,103 +606,160 @@ static int fnic_scsi_drv_init(struct fnic *fnic) fnic->fnic_max_tag_id = host->can_queue; host->max_lun = fnic->config.luns_per_tgt; host->max_id = FNIC_MAX_FCP_TARGET; - host->max_cmd_len = FCOE_MAX_CMD_LEN; + host->max_cmd_len = FNIC_FCOE_MAX_CMD_LEN; host->nr_hw_queues = fnic->wq_copy_count; - shost_printk(KERN_INFO, host, - "fnic: can_queue: %d max_lun: %llu", + dev_info(&fnic->pdev->dev, "fnic: can_queue: %d max_lun: %llu", host->can_queue, host->max_lun); - shost_printk(KERN_INFO, host, - "fnic: max_id: %d max_cmd_len: %d nr_hw_queues: %d", + dev_info(&fnic->pdev->dev, "fnic: max_id: %d max_cmd_len: %d nr_hw_queues: %d", host->max_id, host->max_cmd_len, host->nr_hw_queues); + for (hwq = 0; hwq < fnic->wq_copy_count; hwq++) { + fnic->sw_copy_wq[hwq].ioreq_table_size = fnic->fnic_max_tag_id; + fnic->sw_copy_wq[hwq].io_req_table = + kzalloc((fnic->sw_copy_wq[hwq].ioreq_table_size + 1) * + sizeof(struct fnic_io_req *), GFP_KERNEL); + + if (!fnic->sw_copy_wq[hwq].io_req_table) { + fnic_free_ioreq_tables_mq(fnic); + return -ENOMEM; + } + } + + dev_info(&fnic->pdev->dev, "fnic copy wqs: %d, Q0 ioreq table size: %d\n", + fnic->wq_copy_count, fnic->sw_copy_wq[0].ioreq_table_size); + + fnic_scsi_init(fnic); + + err = scsi_add_host(fnic->host, &pdev->dev); + if (err) { + dev_err(&fnic->pdev->dev, "fnic: scsi add host failed: aborting\n"); + return err; + } + fc_host_maxframe_size(fnic->host) = iport->max_payload_size; + fc_host_dev_loss_tmo(fnic->host) = + fnic->config.port_down_timeout / 1000; + sprintf(fc_host_symbolic_name(fnic->host), + DRV_NAME " v" DRV_VERSION " over %s", fnic->name); + fc_host_port_type(fnic->host) = FC_PORTTYPE_NPORT; + fc_host_node_name(fnic->host) = iport->wwnn; + fc_host_port_name(fnic->host) = iport->wwpn; + fc_host_supported_classes(fnic->host) = FC_COS_CLASS3; + memset(fc_host_supported_fc4s(fnic->host), 0, + sizeof(fc_host_supported_fc4s(fnic->host))); + fc_host_supported_fc4s(fnic->host)[2] = 1; + fc_host_supported_fc4s(fnic->host)[7] = 1; + fc_host_supported_speeds(fnic->host) = 0; + fc_host_supported_speeds(fnic->host) |= FC_PORTSPEED_8GBIT; + + dev_info(&fnic->pdev->dev, "shost_data: 0x%p\n", fnic->host->shost_data); + if (fnic->host->shost_data != NULL) { + if (fnic_tgt_id_binding == 0) { + dev_info(&fnic->pdev->dev, "Setting target binding to NONE\n"); + fc_host_tgtid_bind_type(fnic->host) = FC_TGTID_BIND_NONE; + } else { + dev_info(&fnic->pdev->dev, "Setting target binding to WWPN\n"); + fc_host_tgtid_bind_type(fnic->host) = FC_TGTID_BIND_BY_WWPN; + } + } + + fnic->io_req_pool = mempool_create_slab_pool(2, fnic_io_req_cache); + if (!fnic->io_req_pool) { + scsi_remove_host(fnic->host); + return -ENOMEM; + } + return 0; } void fnic_mq_map_queues_cpus(struct Scsi_Host *host) { - struct fc_lport *lp = shost_priv(host); - struct fnic *fnic = lport_priv(lp); + struct fnic *fnic = *((struct fnic **) shost_priv(host)); struct pci_dev *l_pdev = fnic->pdev; int intr_mode = fnic->config.intr_mode; struct blk_mq_queue_map *qmap = &host->tag_set.map[HCTX_TYPE_DEFAULT]; if (intr_mode == VNIC_DEV_INTR_MODE_MSI || intr_mode == VNIC_DEV_INTR_MODE_INTX) { - FNIC_MAIN_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_MAIN_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "intr_mode is not msix\n"); return; } - FNIC_MAIN_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_MAIN_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "qmap->nr_queues: %d\n", qmap->nr_queues); if (l_pdev == NULL) { - FNIC_MAIN_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_MAIN_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "l_pdev is null\n"); return; } - blk_mq_pci_map_queues(qmap, l_pdev, FNIC_PCI_OFFSET); + blk_mq_map_hw_queues(qmap, &l_pdev->dev, FNIC_PCI_OFFSET); } static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - struct Scsi_Host *host; - struct fc_lport *lp; + struct Scsi_Host *host = NULL; struct fnic *fnic; mempool_t *pool; + struct fnic_iport_s *iport; int err = 0; int fnic_id = 0; int i; unsigned long flags; - int hwq; + char *desc, *subsys_desc; + int len; /* - * Allocate SCSI Host and set up association between host, - * local port, and fnic + * Allocate fnic */ - lp = libfc_host_alloc(&fnic_host_template, sizeof(struct fnic)); - if (!lp) { - printk(KERN_ERR PFX "Unable to alloc libfc local port\n"); + fnic = kzalloc(sizeof(struct fnic), GFP_KERNEL); + if (!fnic) { err = -ENOMEM; - goto err_out; + goto err_out_fnic_alloc; } - host = lp->host; - fnic = lport_priv(lp); + iport = &fnic->iport; fnic_id = ida_alloc(&fnic_ida, GFP_KERNEL); if (fnic_id < 0) { - pr_err("Unable to alloc fnic ID\n"); + dev_err(&pdev->dev, "Unable to alloc fnic ID\n"); err = fnic_id; goto err_out_ida_alloc; } - fnic->lport = lp; - fnic->ctlr.lp = lp; - fnic->link_events = 0; + fnic->pdev = pdev; - - snprintf(fnic->name, sizeof(fnic->name) - 1, "%s%d", DRV_NAME, - host->host_no); - - host->transportt = fnic_fc_transport; fnic->fnic_num = fnic_id; - fnic_stats_debugfs_init(fnic); + + /* Find model name from PCIe subsys ID */ + if (fnic_get_desc_by_devid(pdev, &desc, &subsys_desc) == 0) { + dev_info(&fnic->pdev->dev, "Model: %s\n", subsys_desc); + + /* Update FDMI model */ + fnic->subsys_desc_len = strlen(subsys_desc); + len = ARRAY_SIZE(fnic->subsys_desc); + if (fnic->subsys_desc_len > len) + fnic->subsys_desc_len = len; + memcpy(fnic->subsys_desc, subsys_desc, fnic->subsys_desc_len); + dev_info(&fnic->pdev->dev, "FDMI Model: %s\n", fnic->subsys_desc); + } else { + fnic->subsys_desc_len = 0; + dev_info(&fnic->pdev->dev, "Model: %s subsys_id: 0x%04x\n", "Unknown", + pdev->subsystem_device); + } err = pci_enable_device(pdev); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "Cannot enable PCI device, aborting.\n"); - goto err_out_free_hba; + dev_err(&fnic->pdev->dev, "Cannot enable PCI device, aborting.\n"); + goto err_out_pci_enable_device; } err = pci_request_regions(pdev, DRV_NAME); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "Cannot enable PCI resources, aborting\n"); - goto err_out_disable_device; + dev_err(&fnic->pdev->dev, "Cannot enable PCI resources, aborting\n"); + goto err_out_pci_request_regions; } pci_set_master(pdev); @@ -672,19 +772,17 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) { err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "No usable DMA configuration " + dev_err(&fnic->pdev->dev, "No usable DMA configuration " "aborting\n"); - goto err_out_release_regions; + goto err_out_set_dma_mask; } } /* Map vNIC resources from BAR0 */ if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) { - shost_printk(KERN_ERR, fnic->lport->host, - "BAR0 not memory-map'able, aborting.\n"); + dev_err(&fnic->pdev->dev, "BAR0 not memory-map'able, aborting.\n"); err = -ENODEV; - goto err_out_release_regions; + goto err_out_map_bar; } fnic->bar0.vaddr = pci_iomap(pdev, 0, 0); @@ -692,61 +790,79 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) fnic->bar0.len = pci_resource_len(pdev, 0); if (!fnic->bar0.vaddr) { - shost_printk(KERN_ERR, fnic->lport->host, - "Cannot memory-map BAR0 res hdr, " + dev_err(&fnic->pdev->dev, "Cannot memory-map BAR0 res hdr, " "aborting.\n"); err = -ENODEV; - goto err_out_release_regions; + goto err_out_fnic_map_bar; } fnic->vdev = vnic_dev_register(NULL, fnic, pdev, &fnic->bar0); if (!fnic->vdev) { - shost_printk(KERN_ERR, fnic->lport->host, - "vNIC registration failed, " + dev_err(&fnic->pdev->dev, "vNIC registration failed, " "aborting.\n"); err = -ENODEV; - goto err_out_iounmap; + goto err_out_dev_register; } err = vnic_dev_cmd_init(fnic->vdev); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "vnic_dev_cmd_init() returns %d, aborting\n", + dev_err(&fnic->pdev->dev, "vnic_dev_cmd_init() returns %d, aborting\n", err); - goto err_out_vnic_unregister; + goto err_out_dev_cmd_init; } err = fnic_dev_wait(fnic->vdev, vnic_dev_open, vnic_dev_open_done, CMD_OPENF_RQ_ENABLE_THEN_POST); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "vNIC dev open failed, aborting.\n"); - goto err_out_dev_cmd_deinit; + dev_err(&fnic->pdev->dev, "vNIC dev open failed, aborting.\n"); + goto err_out_dev_open; } err = vnic_dev_init(fnic->vdev, 0); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "vNIC dev init failed, aborting.\n"); - goto err_out_dev_close; + dev_err(&fnic->pdev->dev, "vNIC dev init failed, aborting.\n"); + goto err_out_dev_init; } - err = vnic_dev_mac_addr(fnic->vdev, fnic->ctlr.ctl_src_addr); + err = vnic_dev_mac_addr(fnic->vdev, iport->hwmac); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "vNIC get MAC addr failed \n"); - goto err_out_dev_close; + dev_err(&fnic->pdev->dev, "vNIC get MAC addr failed\n"); + goto err_out_dev_mac_addr; } /* set data_src for point-to-point mode and to keep it non-zero */ - memcpy(fnic->data_src_addr, fnic->ctlr.ctl_src_addr, ETH_ALEN); + memcpy(fnic->data_src_addr, iport->hwmac, ETH_ALEN); /* Get vNIC configuration */ err = fnic_get_vnic_config(fnic); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "Get vNIC configuration failed, " + dev_err(&fnic->pdev->dev, "Get vNIC configuration failed, " "aborting.\n"); - goto err_out_dev_close; + goto err_out_fnic_get_config; + } + + switch (fnic->config.flags & 0xff0) { + case VFCF_FC_INITIATOR: + { + host = + scsi_host_alloc(&fnic_host_template, + sizeof(struct fnic *)); + if (!host) { + dev_err(&fnic->pdev->dev, "Unable to allocate scsi host\n"); + err = -ENOMEM; + goto err_out_scsi_host_alloc; + } + *((struct fnic **) shost_priv(host)) = fnic; + + fnic->host = host; + fnic->role = FNIC_ROLE_FCP_INITIATOR; + dev_info(&fnic->pdev->dev, "fnic: %d is scsi initiator\n", + fnic->fnic_num); + } + break; + default: + dev_info(&fnic->pdev->dev, "fnic: %d has no role defined\n", fnic->fnic_num); + err = -EINVAL; + goto err_out_fnic_role; } /* Setup PCI resources */ @@ -756,29 +872,18 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = fnic_set_intr_mode(fnic); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "Failed to set intr mode, " + dev_err(&fnic->pdev->dev, "Failed to set intr mode, " "aborting.\n"); - goto err_out_dev_close; + goto err_out_fnic_set_intr_mode; } err = fnic_alloc_vnic_resources(fnic); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "Failed to alloc vNIC resources, " + dev_err(&fnic->pdev->dev, "Failed to alloc vNIC resources, " "aborting.\n"); - goto err_out_clear_intr; + goto err_out_fnic_alloc_vnic_res; } - - fnic_scsi_drv_init(fnic); - - for (hwq = 0; hwq < fnic->wq_copy_count; hwq++) { - fnic->sw_copy_wq[hwq].ioreq_table_size = fnic->fnic_max_tag_id; - fnic->sw_copy_wq[hwq].io_req_table = - kzalloc((fnic->sw_copy_wq[hwq].ioreq_table_size + 1) * - sizeof(struct fnic_io_req *), GFP_KERNEL); - } - shost_printk(KERN_INFO, fnic->lport->host, "fnic copy wqs: %d, Q0 ioreq table size: %d\n", + dev_info(&fnic->pdev->dev, "fnic copy wqs: %d, Q0 ioreq table size: %d\n", fnic->wq_copy_count, fnic->sw_copy_wq[0].ioreq_table_size); /* initialize all fnic locks */ @@ -794,50 +899,56 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) fnic->fw_ack_index[i] = -1; } - err = -ENOMEM; - fnic->io_req_pool = mempool_create_slab_pool(2, fnic_io_req_cache); - if (!fnic->io_req_pool) - goto err_out_free_resources; - pool = mempool_create_slab_pool(2, fnic_sgl_cache[FNIC_SGL_CACHE_DFLT]); - if (!pool) - goto err_out_free_ioreq_pool; + if (!pool) { + err = -ENOMEM; + goto err_out_free_resources; + } fnic->io_sgl_pool[FNIC_SGL_CACHE_DFLT] = pool; pool = mempool_create_slab_pool(2, fnic_sgl_cache[FNIC_SGL_CACHE_MAX]); - if (!pool) + if (!pool) { + err = -ENOMEM; goto err_out_free_dflt_pool; + } fnic->io_sgl_pool[FNIC_SGL_CACHE_MAX] = pool; + pool = mempool_create_slab_pool(FDLS_MIN_FRAMES, fdls_frame_cache); + if (!pool) { + err = -ENOMEM; + goto err_out_fdls_frame_pool; + } + fnic->frame_pool = pool; + + pool = mempool_create_slab_pool(FDLS_MIN_FRAME_ELEM, + fdls_frame_elem_cache); + if (!pool) { + err = -ENOMEM; + goto err_out_fdls_frame_elem_pool; + } + fnic->frame_elem_pool = pool; + /* setup vlan config, hw inserts vlan header */ fnic->vlan_hw_insert = 1; fnic->vlan_id = 0; - /* Initialize the FIP fcoe_ctrl struct */ - fnic->ctlr.send = fnic_eth_send; - fnic->ctlr.update_mac = fnic_update_mac; - fnic->ctlr.get_src_addr = fnic_get_mac; if (fnic->config.flags & VFCF_FIP_CAPABLE) { - shost_printk(KERN_INFO, fnic->lport->host, - "firmware supports FIP\n"); + dev_info(&fnic->pdev->dev, "firmware supports FIP\n"); /* enable directed and multicast */ vnic_dev_packet_filter(fnic->vdev, 1, 1, 0, 0, 0); vnic_dev_add_addr(fnic->vdev, FIP_ALL_ENODE_MACS); - vnic_dev_add_addr(fnic->vdev, fnic->ctlr.ctl_src_addr); - fnic->set_vlan = fnic_set_vlan; - fcoe_ctlr_init(&fnic->ctlr, FIP_MODE_AUTO); - timer_setup(&fnic->fip_timer, fnic_fip_notify_timer, 0); + vnic_dev_add_addr(fnic->vdev, iport->hwmac); spin_lock_init(&fnic->vlans_lock); INIT_WORK(&fnic->fip_frame_work, fnic_handle_fip_frame); - INIT_WORK(&fnic->event_work, fnic_handle_event); - skb_queue_head_init(&fnic->fip_frame_queue); - INIT_LIST_HEAD(&fnic->evlist); - INIT_LIST_HEAD(&fnic->vlans); + INIT_LIST_HEAD(&fnic->fip_frame_queue); + INIT_LIST_HEAD(&fnic->vlan_list); + timer_setup(&fnic->retry_fip_timer, fnic_handle_fip_timer, 0); + timer_setup(&fnic->fcs_ka_timer, fnic_handle_fcs_ka_timer, 0); + timer_setup(&fnic->enode_ka_timer, fnic_handle_enode_ka_timer, 0); + timer_setup(&fnic->vn_ka_timer, fnic_handle_vn_ka_timer, 0); + fnic->set_vlan = fnic_set_vlan; } else { - shost_printk(KERN_INFO, fnic->lport->host, - "firmware uses non-FIP mode\n"); - fcoe_ctlr_init(&fnic->ctlr, FIP_MODE_NON_FIP); - fnic->ctlr.state = FIP_ST_NON_FIP; + dev_info(&fnic->pdev->dev, "firmware uses non-FIP mode\n"); } fnic->state = FNIC_IN_FC_MODE; @@ -850,9 +961,8 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup notification buffer area */ err = fnic_notify_set(fnic); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "Failed to alloc notify buffer, aborting.\n"); - goto err_out_free_max_pool; + dev_err(&fnic->pdev->dev, "Failed to alloc notify buffer, aborting.\n"); + goto err_out_fnic_notify_set; } /* Setup notify timer when using MSI interrupts */ @@ -863,13 +973,62 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) for (i = 0; i < fnic->rq_count; i++) { err = vnic_rq_fill(&fnic->rq[i], fnic_alloc_rq_frame); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "fnic_alloc_rq_frame can't alloc " + dev_err(&fnic->pdev->dev, "fnic_alloc_rq_frame can't alloc " "frame\n"); - goto err_out_rq_buf; + goto err_out_alloc_rq_buf; } } + init_completion(&fnic->reset_completion_wait); + + /* Start local port initialization */ + iport->max_flogi_retries = fnic->config.flogi_retries; + iport->max_plogi_retries = fnic->config.plogi_retries; + iport->plogi_timeout = fnic->config.plogi_timeout; + iport->service_params = + (FNIC_FCP_SP_INITIATOR | FNIC_FCP_SP_RD_XRDY_DIS | + FNIC_FCP_SP_CONF_CMPL); + if (fnic->config.flags & VFCF_FCP_SEQ_LVL_ERR) + iport->service_params |= FNIC_FCP_SP_RETRY; + + iport->boot_time = jiffies; + iport->e_d_tov = fnic->config.ed_tov; + iport->r_a_tov = fnic->config.ra_tov; + iport->link_supported_speeds = FNIC_PORTSPEED_10GBIT; + iport->wwpn = fnic->config.port_wwn; + iport->wwnn = fnic->config.node_wwn; + + iport->max_payload_size = fnic->config.maxdatafieldsize; + + if ((iport->max_payload_size < FNIC_MIN_DATA_FIELD_SIZE) || + (iport->max_payload_size > FNIC_FC_MAX_PAYLOAD_LEN) || + ((iport->max_payload_size % 4) != 0)) { + iport->max_payload_size = FNIC_FC_MAX_PAYLOAD_LEN; + } + + iport->flags |= FNIC_FIRST_LINK_UP; + + timer_setup(&(iport->fabric.retry_timer), fdls_fabric_timer_callback, + 0); + + fnic->stats_reset_time = jiffies; + + INIT_WORK(&fnic->link_work, fnic_handle_link); + INIT_WORK(&fnic->frame_work, fnic_handle_frame); + INIT_WORK(&fnic->tport_work, fnic_tport_event_handler); + INIT_WORK(&fnic->flush_work, fnic_flush_tx); + + INIT_LIST_HEAD(&fnic->frame_queue); + INIT_LIST_HEAD(&fnic->tx_queue); + INIT_LIST_HEAD(&fnic->tport_event_list); + + INIT_DELAYED_WORK(&iport->oxid_pool.schedule_oxid_free_retry, + fdls_schedule_oxid_free_retry_work); + + /* Initialize the oxid reclaim list and work struct */ + INIT_LIST_HEAD(&iport->oxid_pool.oxid_reclaim_list); + INIT_DELAYED_WORK(&iport->oxid_pool.oxid_reclaim_work, fdls_reclaim_oxid_handler); + /* Enable all queues */ for (i = 0; i < fnic->raw_wq_count; i++) vnic_wq_enable(&fnic->wq[i]); @@ -880,180 +1039,131 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) for (i = 0; i < fnic->wq_copy_count; i++) vnic_wq_copy_enable(&fnic->hw_copy_wq[i]); + vnic_dev_enable(fnic->vdev); + err = fnic_request_intr(fnic); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "Unable to request irq.\n"); - goto err_out_request_intr; + dev_err(&fnic->pdev->dev, "Unable to request irq.\n"); + goto err_out_fnic_request_intr; } - /* - * Initialization done with PCI system, hardware, firmware. - * Add host to SCSI - */ - err = scsi_add_host(lp->host, &pdev->dev); + fnic_notify_timer_start(fnic); + + fnic_fdls_init(fnic, (fnic->config.flags & VFCF_FIP_CAPABLE)); + + err = fnic_scsi_drv_init(fnic); + if (err) + goto err_out_scsi_drv_init; + + err = fnic_stats_debugfs_init(fnic); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "fnic: scsi_add_host failed...exiting\n"); - goto err_out_scsi_add_host; + dev_err(&fnic->pdev->dev, "Failed to initialize debugfs for stats\n"); + goto err_out_free_stats_debugfs; } - - /* Start local port initiatialization */ - - lp->link_up = 0; - - lp->max_retry_count = fnic->config.flogi_retries; - lp->max_rport_retry_count = fnic->config.plogi_retries; - lp->service_params = (FCP_SPPF_INIT_FCN | FCP_SPPF_RD_XRDY_DIS | - FCP_SPPF_CONF_COMPL); - if (fnic->config.flags & VFCF_FCP_SEQ_LVL_ERR) - lp->service_params |= FCP_SPPF_RETRY; - - lp->boot_time = jiffies; - lp->e_d_tov = fnic->config.ed_tov; - lp->r_a_tov = fnic->config.ra_tov; - lp->link_supported_speeds = FC_PORTSPEED_10GBIT; - fc_set_wwnn(lp, fnic->config.node_wwn); - fc_set_wwpn(lp, fnic->config.port_wwn); - - fcoe_libfc_config(lp, &fnic->ctlr, &fnic_transport_template, 0); - - if (!fc_exch_mgr_alloc(lp, FC_CLASS_3, FCPIO_HOST_EXCH_RANGE_START, - FCPIO_HOST_EXCH_RANGE_END, NULL)) { - err = -ENOMEM; - goto err_out_fc_exch_mgr_alloc; - } - - fc_lport_init_stats(lp); - fnic->stats_reset_time = jiffies; - - fc_lport_config(lp); - - if (fc_set_mfs(lp, fnic->config.maxdatafieldsize + - sizeof(struct fc_frame_header))) { - err = -EINVAL; - goto err_out_free_exch_mgr; - } - fc_host_maxframe_size(lp->host) = lp->mfs; - fc_host_dev_loss_tmo(lp->host) = fnic->config.port_down_timeout / 1000; - - sprintf(fc_host_symbolic_name(lp->host), - DRV_NAME " v" DRV_VERSION " over %s", fnic->name); + for (i = 0; i < fnic->intr_count; i++) + vnic_intr_unmask(&fnic->intr[i]); spin_lock_irqsave(&fnic_list_lock, flags); list_add_tail(&fnic->list, &fnic_list); spin_unlock_irqrestore(&fnic_list_lock, flags); - INIT_WORK(&fnic->link_work, fnic_handle_link); - INIT_WORK(&fnic->frame_work, fnic_handle_frame); - INIT_WORK(&fnic->flush_work, fnic_flush_tx); - skb_queue_head_init(&fnic->frame_queue); - skb_queue_head_init(&fnic->tx_queue); - - fc_fabric_login(lp); - - vnic_dev_enable(fnic->vdev); - - for (i = 0; i < fnic->intr_count; i++) - vnic_intr_unmask(&fnic->intr[i]); - - fnic_notify_timer_start(fnic); - return 0; -err_out_free_exch_mgr: - fc_exch_mgr_free(lp); -err_out_fc_exch_mgr_alloc: - fc_remove_host(lp->host); - scsi_remove_host(lp->host); -err_out_scsi_add_host: +err_out_free_stats_debugfs: + fnic_stats_debugfs_remove(fnic); + fnic_free_ioreq_tables_mq(fnic); + scsi_remove_host(fnic->host); +err_out_scsi_drv_init: fnic_free_intr(fnic); -err_out_request_intr: - for (i = 0; i < fnic->rq_count; i++) +err_out_fnic_request_intr: +err_out_alloc_rq_buf: + for (i = 0; i < fnic->rq_count; i++) { + if (ioread32(&fnic->rq[i].ctrl->enable)) + vnic_rq_disable(&fnic->rq[i]); vnic_rq_clean(&fnic->rq[i], fnic_free_rq_buf); -err_out_rq_buf: + } vnic_dev_notify_unset(fnic->vdev); -err_out_free_max_pool: +err_out_fnic_notify_set: + mempool_destroy(fnic->frame_elem_pool); +err_out_fdls_frame_elem_pool: + mempool_destroy(fnic->frame_pool); +err_out_fdls_frame_pool: mempool_destroy(fnic->io_sgl_pool[FNIC_SGL_CACHE_MAX]); err_out_free_dflt_pool: mempool_destroy(fnic->io_sgl_pool[FNIC_SGL_CACHE_DFLT]); -err_out_free_ioreq_pool: - mempool_destroy(fnic->io_req_pool); err_out_free_resources: - for (hwq = 0; hwq < fnic->wq_copy_count; hwq++) - kfree(fnic->sw_copy_wq[hwq].io_req_table); fnic_free_vnic_resources(fnic); -err_out_clear_intr: +err_out_fnic_alloc_vnic_res: fnic_clear_intr_mode(fnic); -err_out_dev_close: +err_out_fnic_set_intr_mode: + scsi_host_put(fnic->host); +err_out_fnic_role: +err_out_scsi_host_alloc: +err_out_fnic_get_config: +err_out_dev_mac_addr: +err_out_dev_init: vnic_dev_close(fnic->vdev); -err_out_dev_cmd_deinit: -err_out_vnic_unregister: +err_out_dev_open: +err_out_dev_cmd_init: vnic_dev_unregister(fnic->vdev); -err_out_iounmap: +err_out_dev_register: fnic_iounmap(fnic); -err_out_release_regions: +err_out_fnic_map_bar: +err_out_map_bar: +err_out_set_dma_mask: pci_release_regions(pdev); -err_out_disable_device: +err_out_pci_request_regions: pci_disable_device(pdev); -err_out_free_hba: - fnic_stats_debugfs_remove(fnic); +err_out_pci_enable_device: ida_free(&fnic_ida, fnic->fnic_num); err_out_ida_alloc: - scsi_host_put(lp->host); -err_out: + kfree(fnic); +err_out_fnic_alloc: return err; } static void fnic_remove(struct pci_dev *pdev) { struct fnic *fnic = pci_get_drvdata(pdev); - struct fc_lport *lp = fnic->lport; unsigned long flags; - int hwq; /* - * Mark state so that the workqueue thread stops forwarding - * received frames and link events to the local port. ISR and - * other threads that can queue work items will also stop - * creating work items on the fnic workqueue + * Sometimes when probe() fails and do not exit with an error code, + * remove() gets called with 'drvdata' not set. Avoid a crash by + * adding a defensive check. */ + if (!fnic) + return; + spin_lock_irqsave(&fnic->fnic_lock, flags); fnic->stop_rx_link_events = 1; spin_unlock_irqrestore(&fnic->fnic_lock, flags); - if (vnic_dev_get_intr_mode(fnic->vdev) == VNIC_DEV_INTR_MODE_MSI) - del_timer_sync(&fnic->notify_timer); - /* * Flush the fnic event queue. After this call, there should * be no event queued for this fnic device in the workqueue */ flush_workqueue(fnic_event_queue); - skb_queue_purge(&fnic->frame_queue); - skb_queue_purge(&fnic->tx_queue); + + fnic_scsi_unload(fnic); + + if (vnic_dev_get_intr_mode(fnic->vdev) == VNIC_DEV_INTR_MODE_MSI) + del_timer_sync(&fnic->notify_timer); if (fnic->config.flags & VFCF_FIP_CAPABLE) { - del_timer_sync(&fnic->fip_timer); - skb_queue_purge(&fnic->fip_frame_queue); + del_timer_sync(&fnic->retry_fip_timer); + del_timer_sync(&fnic->fcs_ka_timer); + del_timer_sync(&fnic->enode_ka_timer); + del_timer_sync(&fnic->vn_ka_timer); + + fnic_free_txq(&fnic->fip_frame_queue); fnic_fcoe_reset_vlans(fnic); - fnic_fcoe_evlist_free(fnic); } - /* - * Log off the fabric. This stops all remote ports, dns port, - * logs off the fabric. This flushes all rport, disc, lport work - * before returning - */ - fc_fabric_logoff(fnic->lport); + if ((fnic_fdmi_support == 1) && (fnic->iport.fabric.fdmi_pending > 0)) + del_timer_sync(&fnic->iport.fabric.fdmi_timer); - spin_lock_irqsave(&fnic->fnic_lock, flags); - fnic->in_remove = 1; - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - - fcoe_ctlr_destroy(&fnic->ctlr); - fc_lport_destroy(lp); fnic_stats_debugfs_remove(fnic); /* @@ -1063,18 +1173,13 @@ static void fnic_remove(struct pci_dev *pdev) */ fnic_cleanup(fnic); - BUG_ON(!skb_queue_empty(&fnic->frame_queue)); - BUG_ON(!skb_queue_empty(&fnic->tx_queue)); - spin_lock_irqsave(&fnic_list_lock, flags); list_del(&fnic->list); spin_unlock_irqrestore(&fnic_list_lock, flags); - fc_remove_host(fnic->lport->host); - scsi_remove_host(fnic->lport->host); - for (hwq = 0; hwq < fnic->wq_copy_count; hwq++) - kfree(fnic->sw_copy_wq[hwq].io_req_table); - fc_exch_mgr_free(fnic->lport); + fnic_free_txq(&fnic->frame_queue); + fnic_free_txq(&fnic->tx_queue); + vnic_dev_notify_unset(fnic->vdev); fnic_free_intr(fnic); fnic_free_vnic_resources(fnic); @@ -1084,8 +1189,11 @@ static void fnic_remove(struct pci_dev *pdev) fnic_iounmap(fnic); pci_release_regions(pdev); pci_disable_device(pdev); + pci_set_drvdata(pdev, NULL); ida_free(&fnic_ida, fnic->fnic_num); - scsi_host_put(lp->host); + fnic_scsi_unload_cleanup(fnic); + scsi_host_put(fnic->host); + kfree(fnic); } static struct pci_driver fnic_driver = { @@ -1161,6 +1269,24 @@ static int __init fnic_init_module(void) goto err_create_fnic_ioreq_slab; } + fdls_frame_cache = kmem_cache_create("fdls_frames", + FNIC_FCOE_FRAME_MAXSZ, + 0, SLAB_HWCACHE_ALIGN, NULL); + if (!fdls_frame_cache) { + pr_err("fnic fdls frame cache create failed\n"); + err = -ENOMEM; + goto err_create_fdls_frame_cache; + } + + fdls_frame_elem_cache = kmem_cache_create("fdls_frame_elem", + sizeof(struct fnic_frame_list), + 0, SLAB_HWCACHE_ALIGN, NULL); + if (!fdls_frame_elem_cache) { + pr_err("fnic fdls frame elem cache create failed\n"); + err = -ENOMEM; + goto err_create_fdls_frame_cache_elem; + } + fnic_event_queue = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, "fnic_event_wq"); if (!fnic_event_queue) { @@ -1177,6 +1303,19 @@ static int __init fnic_init_module(void) goto err_create_fip_workq; } + if (pc_rscn_handling_feature_flag == PC_RSCN_HANDLING_FEATURE_ON) { + reset_fnic_work_queue = + create_singlethread_workqueue("reset_fnic_work_queue"); + if (!reset_fnic_work_queue) { + pr_err("reset fnic work queue create failed\n"); + err = -ENOMEM; + goto err_create_reset_fnic_workq; + } + spin_lock_init(&reset_fnic_list_lock); + INIT_LIST_HEAD(&reset_fnic_list); + INIT_WORK(&reset_fnic_work, fnic_reset_work_handler); + } + fnic_fc_transport = fc_attach_transport(&fnic_fc_functions); if (!fnic_fc_transport) { printk(KERN_ERR PFX "fc_attach_transport error\n"); @@ -1197,8 +1336,15 @@ err_pci_register: err_fc_transport: destroy_workqueue(fnic_fip_queue); err_create_fip_workq: + if (pc_rscn_handling_feature_flag == PC_RSCN_HANDLING_FEATURE_ON) + destroy_workqueue(reset_fnic_work_queue); +err_create_reset_fnic_workq: destroy_workqueue(fnic_event_queue); err_create_fnic_workq: + kmem_cache_destroy(fdls_frame_elem_cache); +err_create_fdls_frame_cache_elem: + kmem_cache_destroy(fdls_frame_cache); +err_create_fdls_frame_cache: kmem_cache_destroy(fnic_io_req_cache); err_create_fnic_ioreq_slab: kmem_cache_destroy(fnic_sgl_cache[FNIC_SGL_CACHE_MAX]); @@ -1215,11 +1361,18 @@ static void __exit fnic_cleanup_module(void) { pci_unregister_driver(&fnic_driver); destroy_workqueue(fnic_event_queue); - if (fnic_fip_queue) + + if (pc_rscn_handling_feature_flag == PC_RSCN_HANDLING_FEATURE_ON) + destroy_workqueue(reset_fnic_work_queue); + + if (fnic_fip_queue) { + flush_workqueue(fnic_fip_queue); destroy_workqueue(fnic_fip_queue); + } kmem_cache_destroy(fnic_sgl_cache[FNIC_SGL_CACHE_MAX]); kmem_cache_destroy(fnic_sgl_cache[FNIC_SGL_CACHE_DFLT]); kmem_cache_destroy(fnic_io_req_cache); + kmem_cache_destroy(fdls_frame_cache); fc_release_transport(fnic_fc_transport); fnic_trace_free(); fnic_fc_trace_free(); diff --git a/drivers/scsi/fnic/fnic_pci_subsys_devid.c b/drivers/scsi/fnic/fnic_pci_subsys_devid.c new file mode 100644 index 000000000000..36a2c1268422 --- /dev/null +++ b/drivers/scsi/fnic/fnic_pci_subsys_devid.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2008 Cisco Systems, Inc. All rights reserved. + * Copyright 2007 Nuova Systems, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "fnic.h" + +static struct fnic_pcie_device fnic_pcie_device_table[] = { + {PCI_DEVICE_ID_CISCO_SERENO, "Sereno", PCI_SUBDEVICE_ID_CISCO_VASONA, + "VIC 1280"}, + {PCI_DEVICE_ID_CISCO_SERENO, "Sereno", PCI_SUBDEVICE_ID_CISCO_COTATI, + "VIC 1240"}, + {PCI_DEVICE_ID_CISCO_SERENO, "Sereno", + PCI_SUBDEVICE_ID_CISCO_LEXINGTON, "VIC 1225"}, + {PCI_DEVICE_ID_CISCO_SERENO, "Sereno", PCI_SUBDEVICE_ID_CISCO_ICEHOUSE, + "VIC 1285"}, + {PCI_DEVICE_ID_CISCO_SERENO, "Sereno", + PCI_SUBDEVICE_ID_CISCO_KIRKWOODLAKE, "VIC 1225T"}, + {PCI_DEVICE_ID_CISCO_SERENO, "Sereno", + PCI_SUBDEVICE_ID_CISCO_SUSANVILLE, "VIC 1227"}, + {PCI_DEVICE_ID_CISCO_SERENO, "Sereno", PCI_SUBDEVICE_ID_CISCO_TORRANCE, + "VIC 1227T"}, + + {PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_CALISTOGA, + "VIC 1340"}, + {PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_MOUNTAINVIEW, + "VIC 1380"}, + {PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_MOUNTTIAN, + "C3260-SIOC"}, + {PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_CLEARLAKE, + "VIC 1385"}, + {PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_MOUNTTIAN2, + "C3260-SIOC"}, + {PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_CLAREMONT, + "VIC 1387"}, + + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BRADBURY, + "VIC 1457"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", + PCI_SUBDEVICE_ID_CISCO_BRENTWOOD, "VIC 1455"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", + PCI_SUBDEVICE_ID_CISCO_BURLINGAME, "VIC 1487"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BAYSIDE, + "VIC 1485"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", + PCI_SUBDEVICE_ID_CISCO_BAKERSFIELD, "VIC 1440"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", + PCI_SUBDEVICE_ID_CISCO_BOONVILLE, "VIC 1480"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BENICIA, + "VIC 1495"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BEAUMONT, + "VIC 1497"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BRISBANE, + "VIC 1467"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BENTON, + "VIC 1477"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", + PCI_SUBDEVICE_ID_CISCO_TWIN_RIVER, "VIC 14425"}, + {PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", + PCI_SUBDEVICE_ID_CISCO_TWIN_PEAK, "VIC 14825"}, + + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_BERN, + "VIC 15420"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", + PCI_SUBDEVICE_ID_CISCO_STOCKHOLM, "VIC 15428"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_KRAKOW, + "VIC 15411"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", + PCI_SUBDEVICE_ID_CISCO_LUCERNE, "VIC 15231"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_TURKU, + "VIC 15238"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_GENEVA, + "VIC 15422"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", + PCI_SUBDEVICE_ID_CISCO_HELSINKI, "VIC 15235"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", + PCI_SUBDEVICE_ID_CISCO_GOTHENBURG, "VIC 15425"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", + PCI_SUBDEVICE_ID_CISCO_TURKU_PLUS, "VIC 15237"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_ZURICH, + "VIC 15230"}, + {PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_RIGA, + "VIC 15427"}, + + {0,} +}; + +int fnic_get_desc_by_devid(struct pci_dev *pdev, char **desc, + char **subsys_desc) +{ + unsigned short device = PCI_DEVICE_ID_CISCO_VIC_FC; + int max = ARRAY_SIZE(fnic_pcie_device_table); + struct fnic_pcie_device *t = fnic_pcie_device_table; + int index = 0; + + if (pdev->device != device) + return 1; + + while (t->device != 0) { + if (memcmp + ((char *) &pdev->subsystem_device, + (char *) &t->subsystem_device, sizeof(short)) == 0) + break; + t++; + index++; + } + + if (index >= max - 1) { + *desc = NULL; + *subsys_desc = NULL; + return 1; + } + + *desc = fnic_pcie_device_table[index].desc; + *subsys_desc = fnic_pcie_device_table[index].subsys_desc; + return 0; +} diff --git a/drivers/scsi/fnic/fnic_res.c b/drivers/scsi/fnic/fnic_res.c index 33dd27f6f24e..763475587b7f 100644 --- a/drivers/scsi/fnic/fnic_res.c +++ b/drivers/scsi/fnic/fnic_res.c @@ -30,9 +30,7 @@ int fnic_get_vnic_config(struct fnic *fnic) offsetof(struct vnic_fc_config, m), \ sizeof(c->m), &c->m); \ if (err) { \ - shost_printk(KERN_ERR, fnic->lport->host, \ - "Error getting %s, %d\n", #m, \ - err); \ + dev_err(&fnic->pdev->dev, "Error getting %s, %d\n", #m, err); \ return err; \ } \ } while (0); @@ -60,6 +58,11 @@ int fnic_get_vnic_config(struct fnic *fnic) GET_CONFIG(intr_mode); GET_CONFIG(wq_copy_count); + if ((c->flags & (VFCF_FC_INITIATOR)) == 0) { + dev_info(&fnic->pdev->dev, "vNIC role not defined (def role: FC Init)\n"); + c->flags |= VFCF_FC_INITIATOR; + } + c->wq_enet_desc_count = min_t(u32, VNIC_FNIC_WQ_DESCS_MAX, max_t(u32, VNIC_FNIC_WQ_DESCS_MIN, @@ -139,40 +142,28 @@ int fnic_get_vnic_config(struct fnic *fnic) c->wq_copy_count = min_t(u16, FNIC_WQ_COPY_MAX, c->wq_copy_count); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC MAC addr %pM " - "wq/wq_copy/rq %d/%d/%d\n", - fnic->ctlr.ctl_src_addr, + dev_info(&fnic->pdev->dev, "fNIC MAC addr %p wq/wq_copy/rq %d/%d/%d\n", + fnic->data_src_addr, c->wq_enet_desc_count, c->wq_copy_desc_count, c->rq_desc_count); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC node wwn %llx port wwn %llx\n", + dev_info(&fnic->pdev->dev, "fNIC node wwn 0x%llx port wwn 0x%llx\n", c->node_wwn, c->port_wwn); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC ed_tov %d ra_tov %d\n", + dev_info(&fnic->pdev->dev, "fNIC ed_tov %d ra_tov %d\n", c->ed_tov, c->ra_tov); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC mtu %d intr timer %d\n", + dev_info(&fnic->pdev->dev, "fNIC mtu %d intr timer %d\n", c->maxdatafieldsize, c->intr_timer); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC flags 0x%x luns per tgt %d\n", + dev_info(&fnic->pdev->dev, "fNIC flags 0x%x luns per tgt %d\n", c->flags, c->luns_per_tgt); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC flogi_retries %d flogi timeout %d\n", + dev_info(&fnic->pdev->dev, "fNIC flogi_retries %d flogi timeout %d\n", c->flogi_retries, c->flogi_timeout); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC plogi retries %d plogi timeout %d\n", + dev_info(&fnic->pdev->dev, "fNIC plogi retries %d plogi timeout %d\n", c->plogi_retries, c->plogi_timeout); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC io throttle count %d link dn timeout %d\n", + dev_info(&fnic->pdev->dev, "fNIC io throttle count %d link dn timeout %d\n", c->io_throttle_count, c->link_down_timeout); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC port dn io retries %d port dn timeout %d\n", + dev_info(&fnic->pdev->dev, "fNIC port dn io retries %d port dn timeout %d\n", c->port_down_io_retries, c->port_down_timeout); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC wq_copy_count: %d\n", c->wq_copy_count); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC intr mode: %d\n", c->intr_mode); + dev_info(&fnic->pdev->dev, "fNIC wq_copy_count: %d\n", c->wq_copy_count); + dev_info(&fnic->pdev->dev, "fNIC intr mode: %d\n", c->intr_mode); return 0; } @@ -206,18 +197,12 @@ void fnic_get_res_counts(struct fnic *fnic) fnic->intr_count = vnic_dev_get_res_count(fnic->vdev, RES_TYPE_INTR_CTRL); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC fw resources wq_count: %d\n", fnic->wq_count); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC fw resources raw_wq_count: %d\n", fnic->raw_wq_count); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC fw resources wq_copy_count: %d\n", fnic->wq_copy_count); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC fw resources rq_count: %d\n", fnic->rq_count); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC fw resources cq_count: %d\n", fnic->cq_count); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC fw resources intr_count: %d\n", fnic->intr_count); + dev_info(&fnic->pdev->dev, "vNIC fw resources wq_count: %d\n", fnic->wq_count); + dev_info(&fnic->pdev->dev, "vNIC fw resources raw_wq_count: %d\n", fnic->raw_wq_count); + dev_info(&fnic->pdev->dev, "vNIC fw resources wq_copy_count: %d\n", fnic->wq_copy_count); + dev_info(&fnic->pdev->dev, "vNIC fw resources rq_count: %d\n", fnic->rq_count); + dev_info(&fnic->pdev->dev, "vNIC fw resources cq_count: %d\n", fnic->cq_count); + dev_info(&fnic->pdev->dev, "vNIC fw resources intr_count: %d\n", fnic->intr_count); } void fnic_free_vnic_resources(struct fnic *fnic) @@ -253,19 +238,17 @@ int fnic_alloc_vnic_resources(struct fnic *fnic) intr_mode = vnic_dev_get_intr_mode(fnic->vdev); - shost_printk(KERN_INFO, fnic->lport->host, "vNIC interrupt mode: %s\n", + dev_info(&fnic->pdev->dev, "vNIC interrupt mode: %s\n", intr_mode == VNIC_DEV_INTR_MODE_INTX ? "legacy PCI INTx" : intr_mode == VNIC_DEV_INTR_MODE_MSI ? "MSI" : intr_mode == VNIC_DEV_INTR_MODE_MSIX ? "MSI-X" : "unknown"); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC resources avail: wq %d cp_wq %d raw_wq %d rq %d", + dev_info(&fnic->pdev->dev, "res avail: wq %d cp_wq %d raw_wq %d rq %d", fnic->wq_count, fnic->wq_copy_count, fnic->raw_wq_count, fnic->rq_count); - shost_printk(KERN_INFO, fnic->lport->host, - "vNIC resources avail: cq %d intr %d cpy-wq desc count %d\n", + dev_info(&fnic->pdev->dev, "res avail: cq %d intr %d cpy-wq desc count %d\n", fnic->cq_count, fnic->intr_count, fnic->config.wq_copy_desc_count); @@ -340,8 +323,7 @@ int fnic_alloc_vnic_resources(struct fnic *fnic) RES_TYPE_INTR_PBA_LEGACY, 0); if (!fnic->legacy_pba && intr_mode == VNIC_DEV_INTR_MODE_INTX) { - shost_printk(KERN_ERR, fnic->lport->host, - "Failed to hook legacy pba resource\n"); + dev_err(&fnic->pdev->dev, "Failed to hook legacy pba resource\n"); err = -ENODEV; goto err_out_cleanup; } @@ -444,8 +426,7 @@ int fnic_alloc_vnic_resources(struct fnic *fnic) /* init the stats memory by making the first call here */ err = vnic_dev_stats_dump(fnic->vdev, &fnic->stats); if (err) { - shost_printk(KERN_ERR, fnic->lport->host, - "vnic_dev_stats_dump failed - x%x\n", err); + dev_err(&fnic->pdev->dev, "vnic_dev_stats_dump failed - x%x\n", err); goto err_out_cleanup; } diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 2ba61dba4569..7133b254cbe4 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -23,11 +23,13 @@ #include #include #include -#include #include +#include #include "fnic_io.h" #include "fnic.h" +static void fnic_cleanup_io(struct fnic *fnic, int exclude_id); + const char *fnic_state_str[] = { [FNIC_IN_FC_MODE] = "FNIC_IN_FC_MODE", [FNIC_IN_FC_TRANS_ETH_MODE] = "FNIC_IN_FC_TRANS_ETH_MODE", @@ -65,6 +67,18 @@ static const char *fcpio_status_str[] = { [FCPIO_LUNMAP_CHNG_PEND] = "FCPIO_LUNHMAP_CHNG_PEND", }; +enum terminate_io_return { + TERM_SUCCESS = 0, + TERM_NO_SC = 1, + TERM_IO_REQ_NOT_FOUND, + TERM_ANOTHER_PORT, + TERM_GSTATE, + TERM_IO_BLOCKED, + TERM_OUT_OF_WQ_DESC, + TERM_TIMED_OUT, + TERM_MISC, +}; + const char *fnic_state_to_str(unsigned int state) { if (state >= ARRAY_SIZE(fnic_state_str) || !fnic_state_str[state]) @@ -90,8 +104,6 @@ static const char *fnic_fcpio_status_to_str(unsigned int status) return fcpio_status_str[status]; } -static void fnic_cleanup_io(struct fnic *fnic); - /* * Unmap the data buffer and sense buffer for an io_req, * also unmap and free the device-private scatter/gather list. @@ -114,6 +126,65 @@ static void fnic_release_ioreq_buf(struct fnic *fnic, SCSI_SENSE_BUFFERSIZE, DMA_FROM_DEVICE); } +static bool +fnic_count_portid_ioreqs_iter(struct fnic *fnic, struct scsi_cmnd *sc, + void *data1, void *data2) +{ + u32 *portid = data1; + unsigned int *count = data2; + struct fnic_io_req *io_req = fnic_priv(sc)->io_req; + + if (!io_req || (*portid && (io_req->port_id != *portid))) + return true; + + *count += 1; + return true; +} + +unsigned int fnic_count_ioreqs(struct fnic *fnic, u32 portid) +{ + unsigned int count = 0; + + fnic_scsi_io_iter(fnic, fnic_count_portid_ioreqs_iter, + &portid, &count); + + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "portid = 0x%x count = %u\n", portid, count); + return count; +} + +unsigned int fnic_count_all_ioreqs(struct fnic *fnic) +{ + return fnic_count_ioreqs(fnic, 0); +} + +static bool +fnic_count_lun_ioreqs_iter(struct fnic *fnic, struct scsi_cmnd *sc, + void *data1, void *data2) +{ + struct scsi_device *scsi_device = data1; + unsigned int *count = data2; + + if (sc->device != scsi_device || !fnic_priv(sc)->io_req) + return true; + + *count += 1; + return true; +} + +unsigned int +fnic_count_lun_ioreqs(struct fnic *fnic, struct scsi_device *scsi_device) +{ + unsigned int count = 0; + + fnic_scsi_io_iter(fnic, fnic_count_lun_ioreqs_iter, + scsi_device, &count); + + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "lun = %p count = %u\n", scsi_device, count); + return count; +} + /* Free up Copy Wq descriptors. Called with copy_wq lock held */ static int free_wq_copy_descs(struct fnic *fnic, struct vnic_wq_copy *wq, unsigned int hwq) { @@ -179,12 +250,11 @@ int fnic_fw_reset_handler(struct fnic *fnic) struct vnic_wq_copy *wq = &fnic->hw_copy_wq[0]; int ret = 0; unsigned long flags; + unsigned int ioreq_count; /* indicate fwreset to io path */ fnic_set_state_flags(fnic, FNIC_FLAGS_FWRESET); - - skb_queue_purge(&fnic->frame_queue); - skb_queue_purge(&fnic->tx_queue); + ioreq_count = fnic_count_all_ioreqs(fnic); /* wait for io cmpl */ while (atomic_read(&fnic->in_flight)) @@ -198,6 +268,8 @@ int fnic_fw_reset_handler(struct fnic *fnic) if (!vnic_wq_copy_desc_avail(wq)) ret = -EAGAIN; else { + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "ioreq_count: %u\n", ioreq_count); fnic_queue_wq_copy_desc_fw_reset(wq, SCSI_NO_TAG); atomic64_inc(&fnic->fnic_stats.fw_stats.active_fw_reqs); if (atomic64_read(&fnic->fnic_stats.fw_stats.active_fw_reqs) > @@ -211,11 +283,11 @@ int fnic_fw_reset_handler(struct fnic *fnic) if (!ret) { atomic64_inc(&fnic->fnic_stats.reset_stats.fw_resets); - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "Issued fw reset\n"); } else { fnic_clear_state_flags(fnic, FNIC_FLAGS_FWRESET); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "Failed to issue fw reset\n"); } @@ -231,10 +303,10 @@ int fnic_flogi_reg_handler(struct fnic *fnic, u32 fc_id) { struct vnic_wq_copy *wq = &fnic->hw_copy_wq[0]; enum fcpio_flogi_reg_format_type format; - struct fc_lport *lp = fnic->lport; u8 gw_mac[ETH_ALEN]; int ret = 0; unsigned long flags; + struct fnic_iport_s *iport = &fnic->iport; spin_lock_irqsave(&fnic->wq_copy_lock[0], flags); @@ -246,28 +318,23 @@ int fnic_flogi_reg_handler(struct fnic *fnic, u32 fc_id) goto flogi_reg_ioreq_end; } - if (fnic->ctlr.map_dest) { - eth_broadcast_addr(gw_mac); - format = FCPIO_FLOGI_REG_DEF_DEST; - } else { - memcpy(gw_mac, fnic->ctlr.dest_addr, ETH_ALEN); - format = FCPIO_FLOGI_REG_GW_DEST; - } + memcpy(gw_mac, fnic->iport.fcfmac, ETH_ALEN); + format = FCPIO_FLOGI_REG_GW_DEST; - if ((fnic->config.flags & VFCF_FIP_CAPABLE) && !fnic->ctlr.map_dest) { + if (fnic->config.flags & VFCF_FIP_CAPABLE) { fnic_queue_wq_copy_desc_fip_reg(wq, SCSI_NO_TAG, fc_id, gw_mac, - fnic->data_src_addr, - lp->r_a_tov, lp->e_d_tov); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "FLOGI FIP reg issued fcid %x src %pM dest %pM\n", - fc_id, fnic->data_src_addr, gw_mac); + fnic->iport.fpma, + iport->r_a_tov, iport->e_d_tov); + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI FIP reg issued fcid: 0x%x src %p dest %p\n", + fc_id, fnic->iport.fpma, gw_mac); } else { fnic_queue_wq_copy_desc_flogi_reg(wq, SCSI_NO_TAG, format, fc_id, gw_mac); - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "FLOGI reg issued fcid 0x%x map %d dest 0x%p\n", - fc_id, fnic->ctlr.map_dest, gw_mac); + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FLOGI reg issued fcid 0x%x dest %p\n", + fc_id, gw_mac); } atomic64_inc(&fnic->fnic_stats.fw_stats.active_fw_reqs); @@ -295,13 +362,17 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic, { struct scatterlist *sg; struct fc_rport *rport = starget_to_rport(scsi_target(sc->device)); - struct fc_rport_libfc_priv *rp = rport->dd_data; struct host_sg_desc *desc; struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats; unsigned int i; int flags; u8 exch_flags; struct scsi_lun fc_lun; + struct fnic_tport_s *tport; + struct rport_dd_data_s *rdd_data; + + rdd_data = rport->dd_data; + tport = rdd_data->tport; if (sg_count) { /* For each SGE, create a device desc entry */ @@ -342,7 +413,7 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic, free_wq_copy_descs(fnic, wq, hwq); if (unlikely(!vnic_wq_copy_desc_avail(wq))) { - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "fnic_queue_wq_copy_desc failure - no descriptors\n"); atomic64_inc(&misc_stats->io_cpwq_alloc_failures); return SCSI_MLQUEUE_HOST_BUSY; @@ -356,7 +427,7 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic, exch_flags = 0; if ((fnic->config.flags & VFCF_FCP_SEQ_LVL_ERR) && - (rp->flags & FC_RP_FLAGS_RETRY)) + (tport->tgt_flags & FDLS_FC_RP_FLAGS_RETRY)) exch_flags |= FCPIO_ICMND_SRFLAG_RETRY; fnic_queue_wq_copy_desc_icmnd_16(wq, mqtag, @@ -371,8 +442,8 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic, sc->cmnd, sc->cmd_len, scsi_bufflen(sc), fc_lun.scsi_lun, io_req->port_id, - rport->maxframe_size, rp->r_a_tov, - rp->e_d_tov); + tport->max_payload_size, + tport->r_a_tov, tport->e_d_tov); atomic64_inc(&fnic->fnic_stats.fw_stats.active_fw_reqs); if (atomic64_read(&fnic->fnic_stats.fw_stats.active_fw_reqs) > @@ -388,10 +459,10 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc) struct request *const rq = scsi_cmd_to_rq(sc); uint32_t mqtag = 0; void (*done)(struct scsi_cmnd *) = scsi_done; - struct fc_lport *lp = shost_priv(sc->device->host); struct fc_rport *rport; struct fnic_io_req *io_req = NULL; - struct fnic *fnic = lport_priv(lp); + struct fnic *fnic = *((struct fnic **) shost_priv(sc->device->host)); + struct fnic_iport_s *iport = NULL; struct fnic_stats *fnic_stats = &fnic->fnic_stats; struct vnic_wq_copy *wq; int ret = 1; @@ -400,32 +471,14 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc) unsigned long flags = 0; unsigned long ptr; int io_lock_acquired = 0; - struct fc_rport_libfc_priv *rp; uint16_t hwq = 0; - - mqtag = blk_mq_unique_tag(rq); - spin_lock_irqsave(&fnic->fnic_lock, flags); - - if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED))) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, - "fnic IO blocked flags: 0x%lx. Returning SCSI_MLQUEUE_HOST_BUSY\n", - fnic->state_flags); - return SCSI_MLQUEUE_HOST_BUSY; - } - - if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_FWRESET))) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, - "fnic flags: 0x%lx. Returning SCSI_MLQUEUE_HOST_BUSY\n", - fnic->state_flags); - return SCSI_MLQUEUE_HOST_BUSY; - } + struct fnic_tport_s *tport = NULL; + struct rport_dd_data_s *rdd_data; + uint16_t lun0_delay = 0; rport = starget_to_rport(scsi_target(sc->device)); if (!rport) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "returning DID_NO_CONNECT for IO as rport is NULL\n"); sc->result = DID_NO_CONNECT << 16; done(sc); @@ -434,50 +487,96 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc) ret = fc_remote_port_chkready(rport); if (ret) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "rport is not ready\n"); - atomic64_inc(&fnic_stats->misc_stats.rport_not_ready); + atomic64_inc(&fnic_stats->misc_stats.tport_not_ready); sc->result = ret; done(sc); return 0; } - rp = rport->dd_data; - if (!rp || rp->rp_state == RPORT_ST_DELETE) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "rport 0x%x removed, returning DID_NO_CONNECT\n", - rport->port_id); + mqtag = blk_mq_unique_tag(rq); + spin_lock_irqsave(&fnic->fnic_lock, flags); + iport = &fnic->iport; - atomic64_inc(&fnic_stats->misc_stats.rport_not_ready); - sc->result = DID_NO_CONNECT<<16; + if (iport->state != FNIC_IPORT_STATE_READY) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "returning DID_NO_CONNECT for IO as iport state: %d\n", + iport->state); + sc->result = DID_NO_CONNECT << 16; done(sc); return 0; } - if (rp->rp_state != RPORT_ST_READY) { - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "rport 0x%x in state 0x%x, returning DID_IMM_RETRY\n", - rport->port_id, rp->rp_state); + /* fc_remote_port_add() may have added the tport to + * fc_transport but dd_data not yet set + */ + rdd_data = rport->dd_data; + tport = rdd_data->tport; + if (!tport || (rdd_data->iport != iport)) { + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "dd_data not yet set in SCSI for rport portid: 0x%x\n", + rport->port_id); + tport = fnic_find_tport_by_fcid(iport, rport->port_id); + if (!tport) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "returning DID_BUS_BUSY for IO as tport not found for: 0x%x\n", + rport->port_id); + sc->result = DID_BUS_BUSY << 16; + done(sc); + return 0; + } - sc->result = DID_IMM_RETRY << 16; - done(sc); - return 0; + /* Re-assign same params as in fnic_fdls_add_tport */ + rport->maxframe_size = FNIC_FC_MAX_PAYLOAD_LEN; + rport->supported_classes = + FC_COS_CLASS3 | FC_RPORT_ROLE_FCP_TARGET; + /* the dd_data is allocated by fctransport of size dd_fcrport_size */ + rdd_data = rport->dd_data; + rdd_data->tport = tport; + rdd_data->iport = iport; + tport->rport = rport; + tport->flags |= FNIC_FDLS_SCSI_REGISTERED; } - if (lp->state != LPORT_ST_READY || !(lp->link_up)) { + if ((tport->state != FDLS_TGT_STATE_READY) + && (tport->state != FDLS_TGT_STATE_ADISC)) { spin_unlock_irqrestore(&fnic->fnic_lock, flags); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, - "state not ready: %d/link not up: %d Returning HOST_BUSY\n", - lp->state, lp->link_up); - return SCSI_MLQUEUE_HOST_BUSY; + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "returning DID_NO_CONNECT for IO as tport state: %d\n", + tport->state); + sc->result = DID_NO_CONNECT << 16; + done(sc); + return 0; } atomic_inc(&fnic->in_flight); + atomic_inc(&tport->in_flight); + + if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED))) { + atomic_dec(&fnic->in_flight); + atomic_dec(&tport->in_flight); + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + return SCSI_MLQUEUE_HOST_BUSY; + } + + if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_FWRESET))) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "fnic flags FW reset: 0x%lx. Returning SCSI_MLQUEUE_HOST_BUSY\n", + fnic->state_flags); + return SCSI_MLQUEUE_HOST_BUSY; + } + + if (!tport->lun0_delay) { + lun0_delay = 1; + tport->lun0_delay++; + } spin_unlock_irqrestore(&fnic->fnic_lock, flags); + fnic_priv(sc)->state = FNIC_IOREQ_NOT_INITED; fnic_priv(sc)->flags = FNIC_NO_FLAGS; @@ -499,6 +598,7 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc) goto out; } + io_req->tport = tport; /* Determine the type of scatter/gather list we need */ io_req->sgl_cnt = sg_count; io_req->sgl_type = FNIC_SGL_CACHE_DFLT; @@ -575,6 +675,7 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc) mempool_free(io_req, fnic->io_req_pool); } atomic_dec(&fnic->in_flight); + atomic_dec(&tport->in_flight); return ret; } else { atomic64_inc(&fnic_stats->io_stats.active_ios); @@ -602,6 +703,14 @@ out: spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); atomic_dec(&fnic->in_flight); + atomic_dec(&tport->in_flight); + + if (lun0_delay) { + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "LUN0 delay\n"); + mdelay(LUN0_DELAY_TIME); + } + return ret; } @@ -625,7 +734,7 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic, atomic64_inc(&reset_stats->fw_reset_completions); /* Clean up all outstanding io requests */ - fnic_cleanup_io(fnic); + fnic_cleanup_io(fnic, SCSI_NO_TAG); atomic64_set(&fnic->fnic_stats.fw_stats.active_fw_reqs, 0); atomic64_set(&fnic->fnic_stats.io_stats.active_ios, 0); @@ -637,44 +746,37 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic, if (fnic->state == FNIC_IN_FC_TRANS_ETH_MODE) { /* Check status of reset completion */ if (!hdr_status) { - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "reset cmpl success\n"); /* Ready to send flogi out */ fnic->state = FNIC_IN_ETH_MODE; } else { - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "reset failed with header status: %s\n", fnic_fcpio_status_to_str(hdr_status)); - /* - * Unable to change to eth mode, cannot send out flogi - * Change state to fc mode, so that subsequent Flogi - * requests from libFC will cause more attempts to - * reset the firmware. Free the cached flogi - */ fnic->state = FNIC_IN_FC_MODE; atomic64_inc(&reset_stats->fw_reset_failures); ret = -1; } } else { - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "Unexpected state while processing reset completion: %s\n", fnic_state_to_str(fnic->state)); atomic64_inc(&reset_stats->fw_reset_failures); ret = -1; } - /* Thread removing device blocks till firmware reset is complete */ - if (fnic->remove_wait) - complete(fnic->remove_wait); + if (fnic->fw_reset_done) + complete(fnic->fw_reset_done); /* * If fnic is being removed, or fw reset failed * free the flogi frame. Else, send it out */ - if (fnic->remove_wait || ret) { + if (ret) { spin_unlock_irqrestore(&fnic->fnic_lock, flags); - skb_queue_purge(&fnic->tx_queue); + fnic_free_txq(&fnic->tx_queue); goto reset_cmpl_handler_end; } @@ -710,19 +812,19 @@ static int fnic_fcpio_flogi_reg_cmpl_handler(struct fnic *fnic, /* Check flogi registration completion status */ if (!hdr_status) { - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "flog reg succeeded\n"); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "FLOGI reg succeeded\n"); fnic->state = FNIC_IN_FC_MODE; } else { FNIC_SCSI_DBG(KERN_DEBUG, - fnic->lport->host, fnic->fnic_num, - "fnic flogi reg :failed %s\n", + fnic->host, fnic->fnic_num, + "fnic flogi reg failed: %s\n", fnic_fcpio_status_to_str(hdr_status)); fnic->state = FNIC_IN_ETH_MODE; ret = -1; } } else { - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "Unexpected fnic state %s while" " processing flogi reg completion\n", fnic_state_to_str(fnic->state)); @@ -795,7 +897,7 @@ static inline void fnic_fcpio_ack_handler(struct fnic *fnic, spin_unlock_irqrestore(&fnic->wq_copy_lock[wq_index], flags); FNIC_TRACE(fnic_fcpio_ack_handler, - fnic->lport->host->host_no, 0, 0, ox_id_tag[2], ox_id_tag[3], + fnic->host->host_no, 0, 0, ox_id_tag[2], ox_id_tag[3], ox_id_tag[4], ox_id_tag[5]); } @@ -833,36 +935,36 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind hwq = blk_mq_unique_tag_to_hwq(mqtag); if (hwq != cq_index) { - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ", hwq, mqtag, tag, cq_index); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hdr status: %s icmnd completion on the wrong queue\n", fnic_fcpio_status_to_str(hdr_status)); } if (tag >= fnic->fnic_max_tag_id) { - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ", hwq, mqtag, tag, cq_index); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hdr status: %s Out of range tag\n", fnic_fcpio_status_to_str(hdr_status)); return; } spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); - sc = scsi_host_find_tag(fnic->lport->host, id); + sc = scsi_host_find_tag(fnic->host, id); WARN_ON_ONCE(!sc); if (!sc) { atomic64_inc(&fnic_stats->io_stats.sc_null); spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - shost_printk(KERN_ERR, fnic->lport->host, + shost_printk(KERN_ERR, fnic->host, "icmnd_cmpl sc is null - " "hdr status = %s tag = 0x%x desc = 0x%p\n", fnic_fcpio_status_to_str(hdr_status), id, desc); FNIC_TRACE(fnic_fcpio_icmnd_cmpl_handler, - fnic->lport->host->host_no, id, + fnic->host->host_no, id, ((u64)icmnd_cmpl->_resvd0[1] << 16 | (u64)icmnd_cmpl->_resvd0[0]), ((u64)hdr_status << 16 | @@ -885,7 +987,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind atomic64_inc(&fnic_stats->io_stats.ioreq_null); fnic_priv(sc)->flags |= FNIC_IO_REQ_NULL; spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - shost_printk(KERN_ERR, fnic->lport->host, + shost_printk(KERN_ERR, fnic->host, "icmnd_cmpl io_req is null - " "hdr status = %s tag = 0x%x sc 0x%p\n", fnic_fcpio_status_to_str(hdr_status), id, sc); @@ -912,7 +1014,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind if(FCPIO_ABORTED == hdr_status) fnic_priv(sc)->flags |= FNIC_IO_ABORTED; - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "icmnd_cmpl abts pending " "hdr status = %s tag = 0x%x sc = 0x%p " "scsi_status = %x residual = %d\n", @@ -943,6 +1045,9 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind if (icmnd_cmpl->scsi_status == SAM_STAT_TASK_SET_FULL) atomic64_inc(&fnic_stats->misc_stats.queue_fulls); + + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "xfer_len: %llu", xfer_len); break; case FCPIO_TIMEOUT: /* request was timed out */ @@ -1004,7 +1109,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind if (hdr_status != FCPIO_SUCCESS) { atomic64_inc(&fnic_stats->io_stats.io_failures); - shost_printk(KERN_ERR, fnic->lport->host, "hdr status = %s\n", + shost_printk(KERN_ERR, fnic->host, "hdr status = %s\n", fnic_fcpio_status_to_str(hdr_status)); } @@ -1024,13 +1129,13 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind desc, cmd_trace, fnic_flags_and_state(sc)); if (sc->sc_data_direction == DMA_FROM_DEVICE) { - fnic->lport->host_stats.fcp_input_requests++; + fnic_stats->host_stats.fcp_input_requests++; fnic->fcp_input_bytes += xfer_len; } else if (sc->sc_data_direction == DMA_TO_DEVICE) { - fnic->lport->host_stats.fcp_output_requests++; + fnic_stats->host_stats.fcp_output_requests++; fnic->fcp_output_bytes += xfer_len; } else - fnic->lport->host_stats.fcp_control_requests++; + fnic_stats->host_stats.fcp_control_requests++; /* Call SCSI completion function to complete the IO */ scsi_done(sc); @@ -1097,27 +1202,27 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde hwq = blk_mq_unique_tag_to_hwq(id & FNIC_TAG_MASK); if (hwq != cq_index) { - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ", hwq, mqtag, tag, cq_index); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hdr status: %s ITMF completion on the wrong queue\n", fnic_fcpio_status_to_str(hdr_status)); } if (tag > fnic->fnic_max_tag_id) { - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ", hwq, mqtag, tag, cq_index); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hdr status: %s Tag out of range\n", fnic_fcpio_status_to_str(hdr_status)); return; } else if ((tag == fnic->fnic_max_tag_id) && !(id & FNIC_TAG_DEV_RST)) { - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ", hwq, mqtag, tag, cq_index); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hdr status: %s Tag out of range\n", fnic_fcpio_status_to_str(hdr_status)); return; @@ -1133,14 +1238,14 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde if (io_req) sc = io_req->sc; } else { - sc = scsi_host_find_tag(fnic->lport->host, id & FNIC_TAG_MASK); + sc = scsi_host_find_tag(fnic->host, id & FNIC_TAG_MASK); } WARN_ON_ONCE(!sc); if (!sc) { atomic64_inc(&fnic_stats->io_stats.sc_null); spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - shost_printk(KERN_ERR, fnic->lport->host, + shost_printk(KERN_ERR, fnic->host, "itmf_cmpl sc is null - hdr status = %s tag = 0x%x\n", fnic_fcpio_status_to_str(hdr_status), tag); return; @@ -1152,7 +1257,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde atomic64_inc(&fnic_stats->io_stats.ioreq_null); spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); fnic_priv(sc)->flags |= FNIC_IO_ABT_TERM_REQ_NULL; - shost_printk(KERN_ERR, fnic->lport->host, + shost_printk(KERN_ERR, fnic->host, "itmf_cmpl io_req is null - " "hdr status = %s tag = 0x%x sc 0x%p\n", fnic_fcpio_status_to_str(hdr_status), tag, sc); @@ -1163,7 +1268,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde if ((id & FNIC_TAG_ABORT) && (id & FNIC_TAG_DEV_RST)) { /* Abort and terminate completion of device reset req */ /* REVISIT : Add asserts about various flags */ - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x hst: %s Abt/term completion received\n", hwq, mqtag, tag, fnic_fcpio_status_to_str(hdr_status)); @@ -1175,7 +1280,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); } else if (id & FNIC_TAG_ABORT) { /* Completion of abort cmd */ - shost_printk(KERN_DEBUG, fnic->lport->host, + shost_printk(KERN_DEBUG, fnic->host, "hwq: %d mqtag: 0x%x tag: 0x%x Abort header status: %s\n", hwq, mqtag, tag, fnic_fcpio_status_to_str(hdr_status)); @@ -1190,7 +1295,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde &term_stats->terminate_fw_timeouts); break; case FCPIO_ITMF_REJECTED: - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "abort reject recd. id %d\n", (int)(id & FNIC_TAG_MASK)); break; @@ -1225,7 +1330,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde if (!(fnic_priv(sc)->flags & (FNIC_IO_ABORTED | FNIC_IO_DONE))) atomic64_inc(&misc_stats->no_icmnd_itmf_cmpls); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "abts cmpl recd. id %d status %s\n", (int)(id & FNIC_TAG_MASK), fnic_fcpio_status_to_str(hdr_status)); @@ -1238,11 +1343,11 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde if (io_req->abts_done) { complete(io_req->abts_done); spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - shost_printk(KERN_INFO, fnic->lport->host, + shost_printk(KERN_INFO, fnic->host, "hwq: %d mqtag: 0x%x tag: 0x%x Waking up abort thread\n", hwq, mqtag, tag); } else { - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x hst: %s Completing IO\n", hwq, mqtag, tag, fnic_fcpio_status_to_str(hdr_status)); @@ -1273,7 +1378,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde } } else if (id & FNIC_TAG_DEV_RST) { /* Completion of device reset */ - shost_printk(KERN_INFO, fnic->lport->host, + shost_printk(KERN_INFO, fnic->host, "hwq: %d mqtag: 0x%x tag: 0x%x DR hst: %s\n", hwq, mqtag, tag, fnic_fcpio_status_to_str(hdr_status)); @@ -1285,7 +1390,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde sc->device->host->host_no, id, sc, jiffies_to_msecs(jiffies - start_time), desc, 0, fnic_flags_and_state(sc)); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x hst: %s Terminate pending\n", hwq, mqtag, tag, fnic_fcpio_status_to_str(hdr_status)); @@ -1298,7 +1403,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde sc->device->host->host_no, id, sc, jiffies_to_msecs(jiffies - start_time), desc, 0, fnic_flags_and_state(sc)); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "dev reset cmpl recd after time out. " "id %d status %s\n", (int)(id & FNIC_TAG_MASK), @@ -1307,7 +1412,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde } fnic_priv(sc)->state = FNIC_IOREQ_CMD_COMPLETE; fnic_priv(sc)->flags |= FNIC_DEV_RST_DONE; - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x hst: %s DR completion received\n", hwq, mqtag, tag, fnic_fcpio_status_to_str(hdr_status)); @@ -1316,7 +1421,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); } else { - shost_printk(KERN_ERR, fnic->lport->host, + shost_printk(KERN_ERR, fnic->host, "%s: Unexpected itmf io state: hwq: %d tag 0x%x %s\n", __func__, hwq, id, fnic_ioreq_state_to_str(fnic_priv(sc)->state)); spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); @@ -1371,7 +1476,7 @@ static int fnic_fcpio_cmpl_handler(struct vnic_dev *vdev, break; default: - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "firmware completion type %d\n", desc->hdr.type); break; @@ -1414,8 +1519,8 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data) struct request *const rq = scsi_cmd_to_rq(sc); struct fnic *fnic = data; struct fnic_io_req *io_req; - unsigned long flags = 0; unsigned long start_time = 0; + unsigned long flags; struct fnic_stats *fnic_stats = &fnic->fnic_stats; uint16_t hwq = 0; int tag; @@ -1432,14 +1537,14 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data) io_req = fnic_priv(sc)->io_req; if (!io_req) { spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hwq: %d mqtag: 0x%x tag: 0x%x flags: 0x%x No ioreq. Returning\n", hwq, mqtag, tag, fnic_priv(sc)->flags); return true; } if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) && - !(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) { + !(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) { /* * We will be here only when FW completes reset * without sending completions for outstanding ios. @@ -1449,6 +1554,7 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data) complete(io_req->dr_done); else if (io_req && io_req->abts_done) complete(io_req->abts_done); + spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); return true; } else if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET) { @@ -1458,19 +1564,19 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data) fnic_priv(sc)->io_req = NULL; io_req->sc = NULL; + start_time = io_req->start_time; spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); /* * If there is a scsi_cmnd associated with this io_req, then * free the corresponding state */ - start_time = io_req->start_time; fnic_release_ioreq_buf(fnic, io_req, sc); mempool_free(io_req, fnic->io_req_pool); sc->result = DID_TRANSPORT_DISRUPTED << 16; - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, - "mqtag:0x%x tag: 0x%x sc:0x%p duration = %lu DID_TRANSPORT_DISRUPTED\n", + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "mqtag: 0x%x tag: 0x%x sc: 0x%p duration = %lu DID_TRANSPORT_DISRUPTED\n", mqtag, tag, sc, (jiffies - start_time)); if (atomic64_read(&fnic->io_cmpl_skip)) @@ -1479,23 +1585,60 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data) atomic64_inc(&fnic_stats->io_stats.io_completions); FNIC_TRACE(fnic_cleanup_io, - sc->device->host->host_no, tag, sc, - jiffies_to_msecs(jiffies - start_time), - 0, ((u64)sc->cmnd[0] << 32 | - (u64)sc->cmnd[2] << 24 | - (u64)sc->cmnd[3] << 16 | - (u64)sc->cmnd[4] << 8 | sc->cmnd[5]), - fnic_flags_and_state(sc)); + sc->device->host->host_no, tag, sc, + jiffies_to_msecs(jiffies - start_time), + 0, ((u64) sc->cmnd[0] << 32 | + (u64) sc->cmnd[2] << 24 | + (u64) sc->cmnd[3] << 16 | + (u64) sc->cmnd[4] << 8 | sc->cmnd[5]), + (((u64) fnic_priv(sc)->flags << 32) | fnic_priv(sc)-> + state)); + /* Complete the command to SCSI */ scsi_done(sc); - return true; } -static void fnic_cleanup_io(struct fnic *fnic) +static void fnic_cleanup_io(struct fnic *fnic, int exclude_id) { - scsi_host_busy_iter(fnic->lport->host, - fnic_cleanup_io_iter, fnic); + unsigned int io_count = 0; + unsigned long flags; + struct fnic_io_req *io_req = NULL; + struct scsi_cmnd *sc = NULL; + + io_count = fnic_count_all_ioreqs(fnic); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "Outstanding ioreq count: %d active io count: %lld Waiting\n", + io_count, + atomic64_read(&fnic->fnic_stats.io_stats.active_ios)); + + scsi_host_busy_iter(fnic->host, + fnic_cleanup_io_iter, fnic); + + /* with sg3utils device reset, SC needs to be retrieved from ioreq */ + spin_lock_irqsave(&fnic->wq_copy_lock[0], flags); + io_req = fnic->sw_copy_wq[0].io_req_table[fnic->fnic_max_tag_id]; + if (io_req) { + sc = io_req->sc; + if (sc) { + if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) + && !(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) { + fnic_priv(sc)->flags |= FNIC_DEV_RST_DONE; + if (io_req && io_req->dr_done) + complete(io_req->dr_done); + } + } + } + spin_unlock_irqrestore(&fnic->wq_copy_lock[0], flags); + + while ((io_count = fnic_count_all_ioreqs(fnic))) { + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "Outstanding ioreq count: %d active io count: %lld Waiting\n", + io_count, + atomic64_read(&fnic->fnic_stats.io_stats.active_ios)); + + schedule_timeout(msecs_to_jiffies(100)); + } } void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq, @@ -1516,7 +1659,7 @@ void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq, if (id >= fnic->fnic_max_tag_id) return; - sc = scsi_host_find_tag(fnic->lport->host, id); + sc = scsi_host_find_tag(fnic->host, id); if (!sc) return; @@ -1545,7 +1688,7 @@ void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq, wq_copy_cleanup_scsi_cmd: sc->result = DID_NO_CONNECT << 16; - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, "wq_copy_cleanup_handler:" + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "wq_copy_cleanup_handler:" " DID_NO_CONNECT\n"); FNIC_TRACE(fnic_wq_copy_cleanup_handler, @@ -1567,10 +1710,13 @@ static inline int fnic_queue_abort_io_req(struct fnic *fnic, int tag, struct vnic_wq_copy *wq = &fnic->hw_copy_wq[hwq]; struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats; unsigned long flags; + struct fnic_tport_s *tport = io_req->tport; spin_lock_irqsave(&fnic->fnic_lock, flags); if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED))) { + atomic_dec(&fnic->in_flight); + atomic_dec(&tport->in_flight); spin_unlock_irqrestore(&fnic->fnic_lock, flags); return 1; } else @@ -1585,7 +1731,8 @@ static inline int fnic_queue_abort_io_req(struct fnic *fnic, int tag, if (!vnic_wq_copy_desc_avail(wq)) { spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); atomic_dec(&fnic->in_flight); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + atomic_dec(&tport->in_flight); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "fnic_queue_abort_io_req: failure: no descriptors\n"); atomic64_inc(&misc_stats->abts_cpwq_alloc_failures); return 1; @@ -1619,20 +1766,24 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data) struct fnic *fnic = iter_data->fnic; int abt_tag = 0; struct fnic_io_req *io_req; - unsigned long flags; struct reset_stats *reset_stats = &fnic->fnic_stats.reset_stats; struct terminate_stats *term_stats = &fnic->fnic_stats.term_stats; struct scsi_lun fc_lun; enum fnic_ioreq_state old_ioreq_state; uint16_t hwq = 0; + unsigned long flags; abt_tag = blk_mq_unique_tag(rq); hwq = blk_mq_unique_tag_to_hwq(abt_tag); + if (!sc) { + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "sc is NULL abt_tag: 0x%x hwq: %d\n", abt_tag, hwq); + return true; + } + spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); - io_req = fnic_priv(sc)->io_req; - if (!io_req || io_req->port_id != iter_data->port_id) { spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); return true; @@ -1640,7 +1791,7 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data) if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) && !(fnic_priv(sc)->flags & FNIC_DEV_RST_ISSUED)) { - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hwq: %d abt_tag: 0x%x flags: 0x%x Device reset is not pending\n", hwq, abt_tag, fnic_priv(sc)->flags); spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); @@ -1655,37 +1806,40 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data) spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); return true; } + if (io_req->abts_done) { - shost_printk(KERN_ERR, fnic->lport->host, - "fnic_rport_exch_reset: io_req->abts_done is set " - "state is %s\n", + shost_printk(KERN_ERR, fnic->host, + "fnic_rport_exch_reset: io_req->abts_done is set state is %s\n", fnic_ioreq_state_to_str(fnic_priv(sc)->state)); } if (!(fnic_priv(sc)->flags & FNIC_IO_ISSUED)) { - shost_printk(KERN_ERR, fnic->lport->host, - "rport_exch_reset " - "IO not yet issued %p tag 0x%x flags " - "%x state %d\n", - sc, abt_tag, fnic_priv(sc)->flags, fnic_priv(sc)->state); + shost_printk(KERN_ERR, fnic->host, + "rport_exch_reset IO not yet issued %p abt_tag 0x%x", + sc, abt_tag); + shost_printk(KERN_ERR, fnic->host, + "flags %x state %d\n", fnic_priv(sc)->flags, + fnic_priv(sc)->state); } old_ioreq_state = fnic_priv(sc)->state; fnic_priv(sc)->state = FNIC_IOREQ_ABTS_PENDING; fnic_priv(sc)->abts_status = FCPIO_INVALID_CODE; + if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET) { atomic64_inc(&reset_stats->device_reset_terminates); abt_tag |= FNIC_TAG_DEV_RST; + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "dev reset sc 0x%p\n", sc); } - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "fnic_rport_exch_reset dev rst sc 0x%p\n", sc); - BUG_ON(io_req->abts_done); - - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "fnic_rport_exch_reset: dev rst sc 0x%p\n", sc); + WARN_ON_ONCE(io_req->abts_done); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "fnic_rport_reset_exch: Issuing abts\n"); spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - /* Now queue the abort command to firmware */ + /* Queue the abort command to firmware */ int_to_scsilun(sc->device->lun, &fc_lun); if (fnic_queue_abort_io_req(fnic, abt_tag, @@ -1698,7 +1852,7 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data) * lun reset */ spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hwq: %d abt_tag: 0x%x flags: 0x%x Queuing abort failed\n", hwq, abt_tag, fnic_priv(sc)->flags); if (fnic_priv(sc)->state == FNIC_IOREQ_ABTS_PENDING) @@ -1714,11 +1868,14 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data) atomic64_inc(&term_stats->terminates); iter_data->term_cnt++; } + return true; } -static void fnic_rport_exch_reset(struct fnic *fnic, u32 port_id) +void fnic_rport_exch_reset(struct fnic *fnic, u32 port_id) { + unsigned int io_count = 0; + unsigned long flags; struct terminate_stats *term_stats = &fnic->fnic_stats.term_stats; struct fnic_rport_abort_io_iter_data iter_data = { .fnic = fnic, @@ -1726,53 +1883,115 @@ static void fnic_rport_exch_reset(struct fnic *fnic, u32 port_id) .term_cnt = 0, }; - FNIC_SCSI_DBG(KERN_DEBUG, - fnic->lport->host, fnic->fnic_num, - "fnic_rport_exch_reset called portid 0x%06x\n", - port_id); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "fnic rport exchange reset for tport: 0x%06x\n", + port_id); if (fnic->in_remove) return; - scsi_host_busy_iter(fnic->lport->host, fnic_rport_abort_io_iter, + io_count = fnic_count_ioreqs(fnic, port_id); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "Starting terminates: rport:0x%x portid-io-count: %d active-io-count: %lld\n", + port_id, io_count, + atomic64_read(&fnic->fnic_stats.io_stats.active_ios)); + + spin_lock_irqsave(&fnic->fnic_lock, flags); + /* Bump in_flight counter to hold off fnic_fw_reset_handler. */ + atomic_inc(&fnic->in_flight); + if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED))) { + atomic_dec(&fnic->in_flight); + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + return; + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + + scsi_host_busy_iter(fnic->host, fnic_rport_abort_io_iter, &iter_data); + if (iter_data.term_cnt > atomic64_read(&term_stats->max_terminates)) atomic64_set(&term_stats->max_terminates, iter_data.term_cnt); + atomic_dec(&fnic->in_flight); + + while ((io_count = fnic_count_ioreqs(fnic, port_id))) + schedule_timeout(msecs_to_jiffies(1000)); + + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "rport: 0x%x remaining portid-io-count: %d ", + port_id, io_count); } void fnic_terminate_rport_io(struct fc_rport *rport) { - struct fc_rport_libfc_priv *rdata; - struct fc_lport *lport; - struct fnic *fnic; + struct fnic_tport_s *tport; + struct rport_dd_data_s *rdd_data; + struct fnic_iport_s *iport = NULL; + struct fnic *fnic = NULL; if (!rport) { - printk(KERN_ERR "fnic_terminate_rport_io: rport is NULL\n"); + pr_err("rport is NULL\n"); return; } - rdata = rport->dd_data; - if (!rdata) { - printk(KERN_ERR "fnic_terminate_rport_io: rdata is NULL\n"); - return; + rdd_data = rport->dd_data; + if (rdd_data) { + tport = rdd_data->tport; + if (!tport) { + pr_err( + "term rport io called after tport is deleted. Returning 0x%8x\n", + rport->port_id); + } else { + pr_err( + "term rport io called after tport is set 0x%8x\n", + rport->port_id); + pr_err( + "tport maybe rediscovered\n"); + + iport = (struct fnic_iport_s *) tport->iport; + fnic = iport->fnic; + fnic_rport_exch_reset(fnic, rport->port_id); + } } - lport = rdata->local_port; +} - if (!lport) { - printk(KERN_ERR "fnic_terminate_rport_io: lport is NULL\n"); - return; - } - fnic = lport_priv(lport); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "wwpn 0x%llx, wwnn0x%llx, rport 0x%p, portid 0x%06x\n", - rport->port_name, rport->node_name, rport, - rport->port_id); +/* + * FCP-SCSI specific handling for module unload + * + */ +void fnic_scsi_unload(struct fnic *fnic) +{ + unsigned long flags; - if (fnic->in_remove) - return; + /* + * Mark state so that the workqueue thread stops forwarding + * received frames and link events to the local port. ISR and + * other threads that can queue work items will also stop + * creating work items on the fnic workqueue + */ + spin_lock_irqsave(&fnic->fnic_lock, flags); + fnic->iport.state = FNIC_IPORT_STATE_LINK_WAIT; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); - fnic_rport_exch_reset(fnic, rport->port_id); + if (fdls_get_state(&fnic->iport.fabric) != FDLS_STATE_INIT) + fnic_scsi_fcpio_reset(fnic); + + spin_lock_irqsave(&fnic->fnic_lock, flags); + fnic->in_remove = 1; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + + fnic_flush_tport_event_list(fnic); + fnic_delete_fcp_tports(fnic); +} + +void fnic_scsi_unload_cleanup(struct fnic *fnic) +{ + int hwq = 0; + + fc_remove_host(fnic->host); + scsi_remove_host(fnic->host); + for (hwq = 0; hwq < fnic->wq_copy_count; hwq++) + kfree(fnic->sw_copy_wq[hwq].io_req_table); } /* @@ -1783,10 +2002,12 @@ void fnic_terminate_rport_io(struct fc_rport *rport) int fnic_abort_cmd(struct scsi_cmnd *sc) { struct request *const rq = scsi_cmd_to_rq(sc); - struct fc_lport *lp; + struct fnic_iport_s *iport; + struct fnic_tport_s *tport; struct fnic *fnic; struct fnic_io_req *io_req = NULL; struct fc_rport *rport; + struct rport_dd_data_s *rdd_data; unsigned long flags; unsigned long start_time = 0; int ret = SUCCESS; @@ -1806,11 +2027,11 @@ int fnic_abort_cmd(struct scsi_cmnd *sc) fc_block_scsi_eh(sc); /* Get local-port, check ready and link up */ - lp = shost_priv(sc->device->host); - - fnic = lport_priv(lp); + fnic = *((struct fnic **) shost_priv(sc->device->host)); spin_lock_irqsave(&fnic->fnic_lock, flags); + iport = &fnic->iport; + fnic_stats = &fnic->fnic_stats; abts_stats = &fnic->fnic_stats.abts_stats; term_stats = &fnic->fnic_stats.term_stats; @@ -1821,7 +2042,44 @@ int fnic_abort_cmd(struct scsi_cmnd *sc) fnic_priv(sc)->flags = FNIC_NO_FLAGS; - if (lp->state != LPORT_ST_READY || !(lp->link_up)) { + rdd_data = rport->dd_data; + tport = rdd_data->tport; + + if (!tport) { + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Abort cmd called after tport delete! rport fcid: 0x%x", + rport->port_id); + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "lun: %llu hwq: 0x%x mqtag: 0x%x Op: 0x%x flags: 0x%x\n", + sc->device->lun, hwq, mqtag, + sc->cmnd[0], fnic_priv(sc)->flags); + ret = FAILED; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + goto fnic_abort_cmd_end; + } + + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Abort cmd called rport fcid: 0x%x lun: %llu hwq: 0x%x mqtag: 0x%x", + rport->port_id, sc->device->lun, hwq, mqtag); + + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Op: 0x%x flags: 0x%x\n", + sc->cmnd[0], + fnic_priv(sc)->flags); + + if (iport->state != FNIC_IPORT_STATE_READY) { + atomic64_inc(&fnic_stats->misc_stats.iport_not_ready); + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport NOT in READY state"); + ret = FAILED; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + goto fnic_abort_cmd_end; + } + + if ((tport->state != FDLS_TGT_STATE_READY) && + (tport->state != FDLS_TGT_STATE_ADISC)) { + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "tport state: %d\n", tport->state); ret = FAILED; spin_unlock_irqrestore(&fnic->fnic_lock, flags); goto fnic_abort_cmd_end; @@ -1843,6 +2101,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc) spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); io_req = fnic_priv(sc)->io_req; if (!io_req) { + ret = FAILED; spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); goto fnic_abort_cmd_end; } @@ -1870,7 +2129,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc) else atomic64_inc(&abts_stats->abort_issued_greater_than_60_sec); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "CDB Opcode: 0x%02x Abort issued time: %lu msec\n", sc->cmnd[0], abt_issued_time); /* @@ -1893,7 +2152,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc) if (fc_remote_port_chkready(rport) == 0) task_req = FCPIO_ITMF_ABT_TASK; else { - atomic64_inc(&fnic_stats->misc_stats.rport_not_ready); + atomic64_inc(&fnic_stats->misc_stats.tport_not_ready); task_req = FCPIO_ITMF_ABT_TASK_TERM; } @@ -1961,7 +2220,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc) if (!(fnic_priv(sc)->flags & (FNIC_IO_ABORTED | FNIC_IO_DONE))) { spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "Issuing host reset due to out of order IO\n"); ret = FAILED; @@ -2009,7 +2268,7 @@ fnic_abort_cmd_end: (u64)sc->cmnd[4] << 8 | sc->cmnd[5]), fnic_flags_and_state(sc)); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "Returning from abort cmd type %x %s\n", task_req, (ret == SUCCESS) ? "SUCCESS" : "FAILED"); @@ -2027,6 +2286,7 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic, unsigned long flags; uint16_t hwq = 0; uint32_t tag = 0; + struct fnic_tport_s *tport = io_req->tport; tag = io_req->tag; hwq = blk_mq_unique_tag_to_hwq(tag); @@ -2037,8 +2297,10 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic, FNIC_FLAGS_IO_BLOCKED))) { spin_unlock_irqrestore(&fnic->fnic_lock, flags); return FAILED; - } else + } else { atomic_inc(&fnic->in_flight); + atomic_inc(&tport->in_flight); + } spin_unlock_irqrestore(&fnic->fnic_lock, flags); spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); @@ -2047,7 +2309,7 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic, free_wq_copy_descs(fnic, wq, hwq); if (!vnic_wq_copy_desc_avail(wq)) { - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "queue_dr_io_req failure - no descriptors\n"); atomic64_inc(&misc_stats->devrst_cpwq_alloc_failures); ret = -EAGAIN; @@ -2072,6 +2334,7 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic, lr_io_req_end: spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); atomic_dec(&fnic->in_flight); + atomic_dec(&tport->in_flight); return ret; } @@ -2114,7 +2377,7 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data) * Found IO that is still pending with firmware and * belongs to the LUN that we are resetting */ - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "Found IO in %s on lun\n", fnic_ioreq_state_to_str(fnic_priv(sc)->state)); @@ -2124,14 +2387,14 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data) } if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) && (!(fnic_priv(sc)->flags & FNIC_DEV_RST_ISSUED))) { - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "dev rst not pending sc 0x%p\n", sc); spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); return true; } if (io_req->abts_done) - shost_printk(KERN_ERR, fnic->lport->host, + shost_printk(KERN_ERR, fnic->host, "%s: io_req->abts_done is set state is %s\n", __func__, fnic_ioreq_state_to_str(fnic_priv(sc)->state)); old_ioreq_state = fnic_priv(sc)->state; @@ -2147,7 +2410,7 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data) BUG_ON(io_req->abts_done); if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET) { - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "dev rst sc 0x%p\n", sc); } @@ -2169,7 +2432,7 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data) fnic_priv(sc)->state = old_ioreq_state; spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); iter_data->ret = FAILED; - FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "hwq: %d abt_tag: 0x%lx Abort could not be queued\n", hwq, abt_tag); return false; @@ -2248,7 +2511,7 @@ static int fnic_clean_pending_aborts(struct fnic *fnic, iter_data.lr_sc = lr_sc; - scsi_host_busy_iter(fnic->lport->host, + scsi_host_busy_iter(fnic->host, fnic_pending_aborts_iter, &iter_data); if (iter_data.ret == FAILED) { ret = iter_data.ret; @@ -2261,7 +2524,7 @@ static int fnic_clean_pending_aborts(struct fnic *fnic, ret = 1; clean_pending_aborts_end: - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "exit status: %d\n", ret); return ret; } @@ -2274,11 +2537,11 @@ clean_pending_aborts_end: int fnic_device_reset(struct scsi_cmnd *sc) { struct request *rq = scsi_cmd_to_rq(sc); - struct fc_lport *lp; struct fnic *fnic; struct fnic_io_req *io_req = NULL; struct fc_rport *rport; int status; + int count = 0; int ret = FAILED; unsigned long flags; unsigned long start_time = 0; @@ -2289,31 +2552,63 @@ int fnic_device_reset(struct scsi_cmnd *sc) DECLARE_COMPLETION_ONSTACK(tm_done); bool new_sc = 0; uint16_t hwq = 0; + struct fnic_iport_s *iport = NULL; + struct rport_dd_data_s *rdd_data; + struct fnic_tport_s *tport; + u32 old_soft_reset_count; + u32 old_link_down_cnt; + int exit_dr = 0; /* Wait for rport to unblock */ fc_block_scsi_eh(sc); /* Get local-port, check ready and link up */ - lp = shost_priv(sc->device->host); + fnic = *((struct fnic **) shost_priv(sc->device->host)); + iport = &fnic->iport; - fnic = lport_priv(lp); fnic_stats = &fnic->fnic_stats; - reset_stats = &fnic->fnic_stats.reset_stats; + reset_stats = &fnic_stats->reset_stats; atomic64_inc(&reset_stats->device_resets); rport = starget_to_rport(scsi_target(sc->device)); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "fcid: 0x%x lun: 0x%llx hwq: %d mqtag: 0x%x flags: 0x%x Device reset\n", + + spin_lock_irqsave(&fnic->fnic_lock, flags); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "fcid: 0x%x lun: %llu hwq: %d mqtag: 0x%x flags: 0x%x Device reset\n", rport->port_id, sc->device->lun, hwq, mqtag, fnic_priv(sc)->flags); - if (lp->state != LPORT_ST_READY || !(lp->link_up)) + rdd_data = rport->dd_data; + tport = rdd_data->tport; + if (!tport) { + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Dev rst called after tport delete! rport fcid: 0x%x lun: %llu\n", + rport->port_id, sc->device->lun); + spin_unlock_irqrestore(&fnic->fnic_lock, flags); goto fnic_device_reset_end; + } + + if (iport->state != FNIC_IPORT_STATE_READY) { + atomic64_inc(&fnic_stats->misc_stats.iport_not_ready); + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "iport NOT in READY state"); + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + goto fnic_device_reset_end; + } + + if ((tport->state != FDLS_TGT_STATE_READY) && + (tport->state != FDLS_TGT_STATE_ADISC)) { + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "tport state: %d\n", tport->state); + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + goto fnic_device_reset_end; + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); /* Check if remote port up */ if (fc_remote_port_chkready(rport)) { - atomic64_inc(&fnic_stats->misc_stats.rport_not_ready); + atomic64_inc(&fnic_stats->misc_stats.tport_not_ready); goto fnic_device_reset_end; } @@ -2352,6 +2647,7 @@ int fnic_device_reset(struct scsi_cmnd *sc) io_req->port_id = rport->port_id; io_req->tag = mqtag; fnic_priv(sc)->io_req = io_req; + io_req->tport = tport; io_req->sc = sc; if (fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] != NULL) @@ -2366,7 +2662,7 @@ int fnic_device_reset(struct scsi_cmnd *sc) fnic_priv(sc)->lr_status = FCPIO_INVALID_CODE; spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, "TAG %x\n", mqtag); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "TAG %x\n", mqtag); /* * issue the device reset, if enqueue failed, clean up the ioreq @@ -2383,6 +2679,11 @@ int fnic_device_reset(struct scsi_cmnd *sc) fnic_priv(sc)->flags |= FNIC_DEV_RST_ISSUED; spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); + spin_lock_irqsave(&fnic->fnic_lock, flags); + old_link_down_cnt = iport->fnic->link_down_cnt; + old_soft_reset_count = fnic->soft_reset_count; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + /* * Wait on the local completion for LUN reset. The io_req may be * freed while we wait since we hold no lock. @@ -2390,14 +2691,39 @@ int fnic_device_reset(struct scsi_cmnd *sc) wait_for_completion_timeout(&tm_done, msecs_to_jiffies(FNIC_LUN_RESET_TIMEOUT)); + /* + * Wake up can be due to the following reasons: + * 1) The device reset completed from target. + * 2) Device reset timed out. + * 3) A link-down/host_reset may have happened in between. + * 4) The device reset was aborted and io_req->dr_done was called. + */ + + exit_dr = 0; + spin_lock_irqsave(&fnic->fnic_lock, flags); + if ((old_link_down_cnt != fnic->link_down_cnt) || + (fnic->reset_in_progress) || + (fnic->soft_reset_count != old_soft_reset_count) || + (iport->state != FNIC_IPORT_STATE_READY)) + exit_dr = 1; + + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); io_req = fnic_priv(sc)->io_req; if (!io_req) { spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "io_req is null mqtag 0x%x sc 0x%p\n", mqtag, sc); goto fnic_device_reset_end; } + + if (exit_dr) { + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Host reset called for fnic. Exit device reset\n"); + io_req->dr_done = NULL; + goto fnic_device_reset_clean; + } io_req->dr_done = NULL; status = fnic_priv(sc)->lr_status; @@ -2408,53 +2734,11 @@ int fnic_device_reset(struct scsi_cmnd *sc) */ if (status == FCPIO_INVALID_CODE) { atomic64_inc(&reset_stats->device_reset_timeouts); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "Device reset timed out\n"); fnic_priv(sc)->flags |= FNIC_DEV_RST_TIMED_OUT; - spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); int_to_scsilun(sc->device->lun, &fc_lun); - /* - * Issue abort and terminate on device reset request. - * If q'ing of terminate fails, retry it after a delay. - */ - while (1) { - spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); - if (fnic_priv(sc)->flags & FNIC_DEV_RST_TERM_ISSUED) { - spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - break; - } - spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - if (fnic_queue_abort_io_req(fnic, - mqtag | FNIC_TAG_DEV_RST, - FCPIO_ITMF_ABT_TASK_TERM, - fc_lun.scsi_lun, io_req, hwq)) { - wait_for_completion_timeout(&tm_done, - msecs_to_jiffies(FNIC_ABT_TERM_DELAY_TIMEOUT)); - } else { - spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); - fnic_priv(sc)->flags |= FNIC_DEV_RST_TERM_ISSUED; - fnic_priv(sc)->state = FNIC_IOREQ_ABTS_PENDING; - io_req->abts_done = &tm_done; - spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "Abort and terminate issued on Device reset mqtag 0x%x sc 0x%p\n", - mqtag, sc); - break; - } - } - while (1) { - spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); - if (!(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) { - spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); - wait_for_completion_timeout(&tm_done, - msecs_to_jiffies(FNIC_LUN_RESET_TIMEOUT)); - break; - } else { - io_req = fnic_priv(sc)->io_req; - io_req->abts_done = NULL; - goto fnic_device_reset_clean; - } - } + goto fnic_device_reset_clean; } else { spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags); } @@ -2463,7 +2747,7 @@ int fnic_device_reset(struct scsi_cmnd *sc) if (status != FCPIO_SUCCESS) { spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); FNIC_SCSI_DBG(KERN_DEBUG, - fnic->lport->host, fnic->fnic_num, + fnic->host, fnic->fnic_num, "Device reset completed - failed\n"); io_req = fnic_priv(sc)->io_req; goto fnic_device_reset_clean; @@ -2479,9 +2763,8 @@ int fnic_device_reset(struct scsi_cmnd *sc) if (fnic_clean_pending_aborts(fnic, sc, new_sc)) { spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags); io_req = fnic_priv(sc)->io_req; - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "Device reset failed" - " since could not abort all IOs\n"); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, + "Device reset failed: Cannot abort all IOs\n"); goto fnic_device_reset_clean; } @@ -2507,6 +2790,15 @@ fnic_device_reset_clean: mempool_free(io_req, fnic->io_req_pool); } + /* + * If link-event is seen while LUN reset is issued we need + * to complete the LUN reset here + */ + if (!new_sc) { + sc->result = DID_RESET << 16; + scsi_done(sc); + } + fnic_device_reset_end: FNIC_TRACE(fnic_device_reset, sc->device->host->host_no, rq->tag, sc, jiffies_to_msecs(jiffies - start_time), @@ -2520,7 +2812,18 @@ fnic_device_reset_end: mutex_unlock(&fnic->sgreset_mutex); } - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, + while ((ret == SUCCESS) && fnic_count_lun_ioreqs(fnic, sc->device)) { + if (count >= 2) { + ret = FAILED; + break; + } + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "Cannot clean up all IOs for the LUN\n"); + schedule_timeout(msecs_to_jiffies(1000)); + count++; + } + + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "Returning from device reset %s\n", (ret == SUCCESS) ? "SUCCESS" : "FAILED"); @@ -2531,67 +2834,78 @@ fnic_device_reset_end: return ret; } -/* Clean up all IOs, clean up libFC local port */ -int fnic_reset(struct Scsi_Host *shost) +static void fnic_post_flogo_linkflap(struct fnic *fnic) +{ + unsigned long flags; + + fnic_fdls_link_status_change(fnic, 0); + spin_lock_irqsave(&fnic->fnic_lock, flags); + + if (fnic->link_status) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + fnic_fdls_link_status_change(fnic, 1); + return; + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); +} + +/* Logout from all the targets and simulate link flap */ +void fnic_reset(struct Scsi_Host *shost) { - struct fc_lport *lp; struct fnic *fnic; - int ret = 0; struct reset_stats *reset_stats; - lp = shost_priv(shost); - fnic = lport_priv(lp); + fnic = *((struct fnic **) shost_priv(shost)); reset_stats = &fnic->fnic_stats.reset_stats; - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "Issuing fnic reset\n"); + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Issuing fnic reset\n"); atomic64_inc(&reset_stats->fnic_resets); + fnic_post_flogo_linkflap(fnic); - /* - * Reset local port, this will clean up libFC exchanges, - * reset remote port sessions, and if link is up, begin flogi - */ - ret = fc_lport_reset(lp); + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Returning from fnic reset"); - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, - "Returning from fnic reset with: %s\n", - (ret == 0) ? "SUCCESS" : "FAILED"); + atomic64_inc(&reset_stats->fnic_reset_completions); +} - if (ret == 0) - atomic64_inc(&reset_stats->fnic_reset_completions); - else - atomic64_inc(&reset_stats->fnic_reset_failures); +int fnic_issue_fc_host_lip(struct Scsi_Host *shost) +{ + int ret = 0; + struct fnic *fnic = *((struct fnic **) shost_priv(shost)); + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FC host lip issued"); + + ret = fnic_host_reset(shost); return ret; } -/* - * SCSI Error handling calls driver's eh_host_reset if all prior - * error handling levels return FAILED. If host reset completes - * successfully, and if link is up, then Fabric login begins. - * - * Host Reset is the highest level of error recovery. If this fails, then - * host is offlined by SCSI. - * - */ -int fnic_host_reset(struct scsi_cmnd *sc) +int fnic_host_reset(struct Scsi_Host *shost) { - int ret; + int ret = SUCCESS; unsigned long wait_host_tmo; - struct Scsi_Host *shost = sc->device->host; - struct fc_lport *lp = shost_priv(shost); - struct fnic *fnic = lport_priv(lp); + struct fnic *fnic = *((struct fnic **) shost_priv(shost)); unsigned long flags; + struct fnic_iport_s *iport = &fnic->iport; spin_lock_irqsave(&fnic->fnic_lock, flags); - if (!fnic->internal_reset_inprogress) { - fnic->internal_reset_inprogress = true; + if (fnic->reset_in_progress == NOT_IN_PROGRESS) { + fnic->reset_in_progress = IN_PROGRESS; } else { spin_unlock_irqrestore(&fnic->fnic_lock, flags); - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "host reset in progress skipping another host reset\n"); - return SUCCESS; + wait_for_completion_timeout(&fnic->reset_completion_wait, + msecs_to_jiffies(10000)); + + spin_lock_irqsave(&fnic->fnic_lock, flags); + if (fnic->reset_in_progress == IN_PROGRESS) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_SCSI_DBG(KERN_WARNING, fnic->host, fnic->fnic_num, + "Firmware reset in progress. Skipping another host reset\n"); + return SUCCESS; + } + fnic->reset_in_progress = IN_PROGRESS; } spin_unlock_irqrestore(&fnic->fnic_lock, flags); @@ -2600,142 +2914,36 @@ int fnic_host_reset(struct scsi_cmnd *sc) * scsi-ml tries to send a TUR to every device if host reset is * successful, so before returning to scsi, fabric should be up */ - ret = (fnic_reset(shost) == 0) ? SUCCESS : FAILED; - if (ret == SUCCESS) { + fnic_reset(shost); + + spin_lock_irqsave(&fnic->fnic_lock, flags); + fnic->reset_in_progress = NOT_IN_PROGRESS; + complete(&fnic->reset_completion_wait); + fnic->soft_reset_count++; + + /* wait till the link is up */ + if (fnic->link_status) { wait_host_tmo = jiffies + FNIC_HOST_RESET_SETTLE_TIME * HZ; ret = FAILED; while (time_before(jiffies, wait_host_tmo)) { - if ((lp->state == LPORT_ST_READY) && - (lp->link_up)) { + if (iport->state != FNIC_IPORT_STATE_READY + && fnic->link_status) { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + ssleep(1); + spin_lock_irqsave(&fnic->fnic_lock, flags); + } else { ret = SUCCESS; break; } - ssleep(1); } } - - spin_lock_irqsave(&fnic->fnic_lock, flags); - fnic->internal_reset_inprogress = false; spin_unlock_irqrestore(&fnic->fnic_lock, flags); + + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "host reset return status: %d\n", ret); return ret; } -/* - * This fxn is called from libFC when host is removed - */ -void fnic_scsi_abort_io(struct fc_lport *lp) -{ - int err = 0; - unsigned long flags; - enum fnic_state old_state; - struct fnic *fnic = lport_priv(lp); - DECLARE_COMPLETION_ONSTACK(remove_wait); - - /* Issue firmware reset for fnic, wait for reset to complete */ -retry_fw_reset: - spin_lock_irqsave(&fnic->fnic_lock, flags); - if (unlikely(fnic->state == FNIC_IN_FC_TRANS_ETH_MODE) && - fnic->link_events) { - /* fw reset is in progress, poll for its completion */ - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - schedule_timeout(msecs_to_jiffies(100)); - goto retry_fw_reset; - } - - fnic->remove_wait = &remove_wait; - old_state = fnic->state; - fnic->state = FNIC_IN_FC_TRANS_ETH_MODE; - fnic_update_mac_locked(fnic, fnic->ctlr.ctl_src_addr); - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - - err = fnic_fw_reset_handler(fnic); - if (err) { - spin_lock_irqsave(&fnic->fnic_lock, flags); - if (fnic->state == FNIC_IN_FC_TRANS_ETH_MODE) - fnic->state = old_state; - fnic->remove_wait = NULL; - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - return; - } - - /* Wait for firmware reset to complete */ - wait_for_completion_timeout(&remove_wait, - msecs_to_jiffies(FNIC_RMDEVICE_TIMEOUT)); - - spin_lock_irqsave(&fnic->fnic_lock, flags); - fnic->remove_wait = NULL; - FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, - "fnic_scsi_abort_io %s\n", - (fnic->state == FNIC_IN_ETH_MODE) ? - "SUCCESS" : "FAILED"); - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - -} - -/* - * This fxn called from libFC to clean up driver IO state on link down - */ -void fnic_scsi_cleanup(struct fc_lport *lp) -{ - unsigned long flags; - enum fnic_state old_state; - struct fnic *fnic = lport_priv(lp); - - /* issue fw reset */ -retry_fw_reset: - spin_lock_irqsave(&fnic->fnic_lock, flags); - if (unlikely(fnic->state == FNIC_IN_FC_TRANS_ETH_MODE)) { - /* fw reset is in progress, poll for its completion */ - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - schedule_timeout(msecs_to_jiffies(100)); - goto retry_fw_reset; - } - old_state = fnic->state; - fnic->state = FNIC_IN_FC_TRANS_ETH_MODE; - fnic_update_mac_locked(fnic, fnic->ctlr.ctl_src_addr); - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - - if (fnic_fw_reset_handler(fnic)) { - spin_lock_irqsave(&fnic->fnic_lock, flags); - if (fnic->state == FNIC_IN_FC_TRANS_ETH_MODE) - fnic->state = old_state; - spin_unlock_irqrestore(&fnic->fnic_lock, flags); - } - -} - -void fnic_empty_scsi_cleanup(struct fc_lport *lp) -{ -} - -void fnic_exch_mgr_reset(struct fc_lport *lp, u32 sid, u32 did) -{ - struct fnic *fnic = lport_priv(lp); - - /* Non-zero sid, nothing to do */ - if (sid) - goto call_fc_exch_mgr_reset; - - if (did) { - fnic_rport_exch_reset(fnic, did); - goto call_fc_exch_mgr_reset; - } - - /* - * sid = 0, did = 0 - * link down or device being removed - */ - if (!fnic->in_remove) - fnic_scsi_cleanup(lp); - else - fnic_scsi_abort_io(lp); - - /* call libFC exch mgr reset to reset its exchanges */ -call_fc_exch_mgr_reset: - fc_exch_mgr_reset(lp, sid, did); - -} - static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data) { struct request *const rq = scsi_cmd_to_rq(sc); @@ -2771,7 +2979,7 @@ static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data) * Found IO that is still pending with firmware and * belongs to the LUN that we are resetting */ - FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "hwq: %d tag: 0x%x Found IO in state: %s on lun\n", hwq, tag, fnic_ioreq_state_to_str(fnic_priv(sc)->state)); @@ -2804,8 +3012,81 @@ int fnic_is_abts_pending(struct fnic *fnic, struct scsi_cmnd *lr_sc) } /* walk again to check, if IOs are still pending in fw */ - scsi_host_busy_iter(fnic->lport->host, + scsi_host_busy_iter(fnic->host, fnic_abts_pending_iter, &iter_data); return iter_data.ret; } + +/* + * SCSI Error handling calls driver's eh_host_reset if all prior + * error handling levels return FAILED. If host reset completes + * successfully, and if link is up, then Fabric login begins. + * + * Host Reset is the highest level of error recovery. If this fails, then + * host is offlined by SCSI. + * + */ +int fnic_eh_host_reset_handler(struct scsi_cmnd *sc) +{ + int ret = 0; + struct Scsi_Host *shost = sc->device->host; + struct fnic *fnic = *((struct fnic **) shost_priv(shost)); + + FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num, + "SCSI error handling: fnic host reset"); + + ret = fnic_host_reset(shost); + return ret; +} + + +void fnic_scsi_fcpio_reset(struct fnic *fnic) +{ + unsigned long flags; + enum fnic_state old_state; + struct fnic_iport_s *iport = &fnic->iport; + DECLARE_COMPLETION_ONSTACK(fw_reset_done); + int time_remain; + + /* issue fw reset */ + spin_lock_irqsave(&fnic->fnic_lock, flags); + if (unlikely(fnic->state == FNIC_IN_FC_TRANS_ETH_MODE)) { + /* fw reset is in progress, poll for its completion */ + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "fnic is in unexpected state: %d for fw_reset\n", + fnic->state); + return; + } + + old_state = fnic->state; + fnic->state = FNIC_IN_FC_TRANS_ETH_MODE; + + fnic_update_mac_locked(fnic, iport->hwmac); + fnic->fw_reset_done = &fw_reset_done; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Issuing fw reset\n"); + if (fnic_fw_reset_handler(fnic)) { + spin_lock_irqsave(&fnic->fnic_lock, flags); + if (fnic->state == FNIC_IN_FC_TRANS_ETH_MODE) + fnic->state = old_state; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + } else { + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Waiting for fw completion\n"); + time_remain = wait_for_completion_timeout(&fw_reset_done, + msecs_to_jiffies(FNIC_FW_RESET_TIMEOUT)); + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Woken up after fw completion timeout\n"); + if (time_remain == 0) { + FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FW reset completion timed out after %d ms)\n", + FNIC_FW_RESET_TIMEOUT); + } + atomic64_inc(&fnic->fnic_stats.reset_stats.fw_reset_timeouts); + } + fnic->fw_reset_done = NULL; +} diff --git a/drivers/scsi/fnic/fnic_stats.h b/drivers/scsi/fnic/fnic_stats.h index 9d7f98c452dd..8ddd20401a59 100644 --- a/drivers/scsi/fnic/fnic_stats.h +++ b/drivers/scsi/fnic/fnic_stats.h @@ -3,6 +3,7 @@ #ifndef _FNIC_STATS_H_ #define _FNIC_STATS_H_ #define FNIC_MQ_MAX_QUEUES 64 +#include struct stats_timestamps { struct timespec64 last_reset_time; @@ -63,6 +64,7 @@ struct reset_stats { atomic64_t fw_resets; atomic64_t fw_reset_completions; atomic64_t fw_reset_failures; + atomic64_t fw_reset_timeouts; atomic64_t fnic_resets; atomic64_t fnic_reset_completions; atomic64_t fnic_reset_failures; @@ -102,10 +104,51 @@ struct misc_stats { atomic64_t no_icmnd_itmf_cmpls; atomic64_t check_condition; atomic64_t queue_fulls; - atomic64_t rport_not_ready; + atomic64_t tport_not_ready; + atomic64_t iport_not_ready; atomic64_t frame_errors; atomic64_t current_port_speed; atomic64_t intx_dummy; + atomic64_t port_speed_in_mbps; +}; + +struct fnic_iport_stats { + atomic64_t num_linkdn; + atomic64_t num_linkup; + atomic64_t link_failure_count; + atomic64_t num_rscns; + atomic64_t rscn_redisc; + atomic64_t rscn_not_redisc; + atomic64_t frame_err; + atomic64_t num_rnid; + atomic64_t fabric_flogi_sent; + atomic64_t fabric_flogi_ls_accepts; + atomic64_t fabric_flogi_ls_rejects; + atomic64_t fabric_flogi_misc_rejects; + atomic64_t fabric_plogi_sent; + atomic64_t fabric_plogi_ls_accepts; + atomic64_t fabric_plogi_ls_rejects; + atomic64_t fabric_plogi_misc_rejects; + atomic64_t fabric_scr_sent; + atomic64_t fabric_scr_ls_accepts; + atomic64_t fabric_scr_ls_rejects; + atomic64_t fabric_scr_misc_rejects; + atomic64_t fabric_logo_sent; + atomic64_t tport_alive; + atomic64_t tport_plogi_sent; + atomic64_t tport_plogi_ls_accepts; + atomic64_t tport_plogi_ls_rejects; + atomic64_t tport_plogi_misc_rejects; + atomic64_t tport_prli_sent; + atomic64_t tport_prli_ls_accepts; + atomic64_t tport_prli_ls_rejects; + atomic64_t tport_prli_misc_rejects; + atomic64_t tport_adisc_sent; + atomic64_t tport_adisc_ls_accepts; + atomic64_t tport_adisc_ls_rejects; + atomic64_t tport_logo_sent; + atomic64_t unsupported_frames_ls_rejects; + atomic64_t unsupported_frames_dropped; }; struct fnic_stats { @@ -116,6 +159,7 @@ struct fnic_stats { struct reset_stats reset_stats; struct fw_stats fw_stats; struct vlan_stats vlan_stats; + struct fc_host_statistics host_stats; struct misc_stats misc_stats; }; @@ -127,6 +171,5 @@ struct stats_debug_info { }; int fnic_get_stats_data(struct stats_debug_info *, struct fnic_stats *); -void fnic_stats_debugfs_init(struct fnic *); -void fnic_stats_debugfs_remove(struct fnic *); +const char *fnic_role_to_str(unsigned int role); #endif /* _FNIC_STATS_H_ */ diff --git a/drivers/scsi/fnic/fnic_trace.c b/drivers/scsi/fnic/fnic_trace.c index aaa4ea02fb7c..cdc6b12b1ec2 100644 --- a/drivers/scsi/fnic/fnic_trace.c +++ b/drivers/scsi/fnic/fnic_trace.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "fnic_io.h" #include "fnic.h" @@ -29,6 +30,17 @@ int fnic_fc_tracing_enabled = 1; int fnic_fc_trace_cleared = 1; static DEFINE_SPINLOCK(fnic_fc_trace_lock); +static const char * const fnic_role_str[] = { + [FNIC_ROLE_FCP_INITIATOR] = "FCP_Initiator", +}; + +const char *fnic_role_to_str(unsigned int role) +{ + if (role >= ARRAY_SIZE(fnic_role_str) || !fnic_role_str[role]) + return "Unknown"; + + return fnic_role_str[role]; +} /* * fnic_trace_get_buf - Give buffer pointer to user to fill up trace information @@ -423,7 +435,8 @@ int fnic_get_stats_data(struct stats_debug_info *debug, "Number of Check Conditions encountered: %lld\n" "Number of QUEUE Fulls: %lld\n" "Number of rport not ready: %lld\n" - "Number of receive frame errors: %lld\n", + "Number of receive frame errors: %lld\n" + "Port speed (in Mbps): %lld\n", (u64)stats->misc_stats.last_isr_time, (s64)val1.tv_sec, val1.tv_nsec, (u64)stats->misc_stats.last_ack_time, @@ -446,18 +459,68 @@ int fnic_get_stats_data(struct stats_debug_info *debug, (u64)atomic64_read(&stats->misc_stats.no_icmnd_itmf_cmpls), (u64)atomic64_read(&stats->misc_stats.check_condition), (u64)atomic64_read(&stats->misc_stats.queue_fulls), - (u64)atomic64_read(&stats->misc_stats.rport_not_ready), - (u64)atomic64_read(&stats->misc_stats.frame_errors)); - - len += scnprintf(debug->debug_buffer + len, buf_size - len, - "Firmware reported port speed: %llu\n", - (u64)atomic64_read( - &stats->misc_stats.current_port_speed)); + (u64)atomic64_read(&stats->misc_stats.tport_not_ready), + (u64)atomic64_read(&stats->misc_stats.frame_errors), + (u64)atomic64_read(&stats->misc_stats.port_speed_in_mbps)); return len; } +int fnic_get_debug_info(struct stats_debug_info *info, struct fnic *fnic) +{ + struct fnic_iport_s *iport = &fnic->iport; + int buf_size = info->buf_size; + int len = info->buffer_len; + struct fnic_tport_s *tport, *next; + unsigned long flags; + + len += snprintf(info->debug_buffer + len, buf_size - len, + "------------------------------------------\n" + "\t\t Debug Info\n" + "------------------------------------------\n"); + len += snprintf(info->debug_buffer + len, buf_size - len, + "fnic Name:%s number:%d Role:%s State:%s\n", + fnic->name, fnic->fnic_num, + fnic_role_to_str(fnic->role), + fnic_state_to_str(fnic->state)); + len += + snprintf(info->debug_buffer + len, buf_size - len, + "iport State:%d Flags:0x%x vlan_id:%d fcid:0x%x\n", + iport->state, iport->flags, iport->vlan_id, iport->fcid); + len += + snprintf(info->debug_buffer + len, buf_size - len, + "usefip:%d fip_state:%d fip_flogi_retry:%d\n", + iport->usefip, iport->fip.state, iport->fip.flogi_retry); + len += + snprintf(info->debug_buffer + len, buf_size - len, + "fpma %02x:%02x:%02x:%02x:%02x:%02x", + iport->fpma[5], iport->fpma[4], iport->fpma[3], + iport->fpma[2], iport->fpma[1], iport->fpma[0]); + len += + snprintf(info->debug_buffer + len, buf_size - len, + "fcfmac %02x:%02x:%02x:%02x:%02x:%02x\n", + iport->fcfmac[5], iport->fcfmac[4], iport->fcfmac[3], + iport->fcfmac[2], iport->fcfmac[1], iport->fcfmac[0]); + len += + snprintf(info->debug_buffer + len, buf_size - len, + "fabric state:%d flags:0x%x retry_counter:%d e_d_tov:%d r_a_tov:%d\n", + iport->fabric.state, iport->fabric.flags, + iport->fabric.retry_counter, iport->e_d_tov, + iport->r_a_tov); + + spin_lock_irqsave(&fnic->fnic_lock, flags); + list_for_each_entry_safe(tport, next, &iport->tport_list, links) { + len += snprintf(info->debug_buffer + len, buf_size - len, + "tport fcid:0x%x state:%d flags:0x%x inflight:%d retry_counter:%d\n", + tport->fcid, tport->state, tport->flags, + atomic_read(&tport->in_flight), + tport->retry_counter); + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + return len; +} + /* * fnic_trace_buf_init - Initialize fnic trace buffer logging facility * @@ -485,8 +548,7 @@ int fnic_trace_buf_init(void) } fnic_trace_entries.page_offset = - vmalloc(array_size(fnic_max_trace_entries, - sizeof(unsigned long))); + vcalloc(fnic_max_trace_entries, sizeof(unsigned long)); if (!fnic_trace_entries.page_offset) { printk(KERN_ERR PFX "Failed to allocate memory for" " page_offset\n"); @@ -497,8 +559,6 @@ int fnic_trace_buf_init(void) err = -ENOMEM; goto err_fnic_trace_buf_init; } - memset((void *)fnic_trace_entries.page_offset, 0, - (fnic_max_trace_entries * sizeof(unsigned long))); fnic_trace_entries.wr_idx = fnic_trace_entries.rd_idx = 0; fnic_buf_head = fnic_trace_buf_p; @@ -559,8 +619,7 @@ int fnic_fc_trace_init(void) fc_trace_max_entries = (fnic_fc_trace_max_pages * PAGE_SIZE)/ FC_TRC_SIZE_BYTES; fnic_fc_ctlr_trace_buf_p = - (unsigned long)vmalloc(array_size(PAGE_SIZE, - fnic_fc_trace_max_pages)); + (unsigned long)vcalloc(fnic_fc_trace_max_pages, PAGE_SIZE); if (!fnic_fc_ctlr_trace_buf_p) { pr_err("fnic: Failed to allocate memory for " "FC Control Trace Buf\n"); @@ -568,13 +627,9 @@ int fnic_fc_trace_init(void) goto err_fnic_fc_ctlr_trace_buf_init; } - memset((void *)fnic_fc_ctlr_trace_buf_p, 0, - fnic_fc_trace_max_pages * PAGE_SIZE); - /* Allocate memory for page offset */ fc_trace_entries.page_offset = - vmalloc(array_size(fc_trace_max_entries, - sizeof(unsigned long))); + vcalloc(fc_trace_max_entries, sizeof(unsigned long)); if (!fc_trace_entries.page_offset) { pr_err("fnic:Failed to allocate memory for page_offset\n"); if (fnic_fc_ctlr_trace_buf_p) { @@ -585,8 +640,6 @@ int fnic_fc_trace_init(void) err = -ENOMEM; goto err_fnic_fc_ctlr_trace_buf_init; } - memset((void *)fc_trace_entries.page_offset, 0, - (fc_trace_max_entries * sizeof(unsigned long))); fc_trace_entries.rd_idx = fc_trace_entries.wr_idx = 0; fc_trace_buf_head = fnic_fc_ctlr_trace_buf_p; @@ -688,7 +741,7 @@ int fnic_fc_trace_set_data(u32 host_no, u8 frame_type, */ if (frame_type == FNIC_FC_RECV) { eth_fcoe_hdr_len = sizeof(struct ethhdr) + - sizeof(struct fcoe_hdr); + sizeof(struct fcoe_hdr); memset((char *)fc_trace, 0xff, eth_fcoe_hdr_len); /* Copy the rest of data frame */ memcpy((char *)(fc_trace + eth_fcoe_hdr_len), (void *)frame, diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h index a44768bceb9a..2d438d722d0b 100644 --- a/drivers/scsi/hisi_sas/hisi_sas.h +++ b/drivers/scsi/hisi_sas/hisi_sas.h @@ -9,7 +9,6 @@ #include #include -#include #include #include #include @@ -644,9 +643,8 @@ extern int hisi_sas_probe(struct platform_device *pdev, const struct hisi_sas_hw *ops); extern void hisi_sas_remove(struct platform_device *pdev); -int hisi_sas_device_configure(struct scsi_device *sdev, - struct queue_limits *lim); -extern int hisi_sas_slave_alloc(struct scsi_device *sdev); +int hisi_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim); +extern int hisi_sas_sdev_init(struct scsi_device *sdev); extern int hisi_sas_scan_finished(struct Scsi_Host *shost, unsigned long time); extern void hisi_sas_scan_start(struct Scsi_Host *shost); extern int hisi_sas_host_reset(struct Scsi_Host *shost, int reset_type); diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 53cb15f6714b..da4a2ed8ee86 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -805,13 +805,13 @@ static int hisi_sas_init_device(struct domain_device *device) return rc; } -int hisi_sas_slave_alloc(struct scsi_device *sdev) +int hisi_sas_sdev_init(struct scsi_device *sdev) { struct domain_device *ddev = sdev_to_domain_dev(sdev); struct hisi_sas_device *sas_dev = ddev->lldd_dev; int rc; - rc = sas_slave_alloc(sdev); + rc = sas_sdev_init(sdev); if (rc) return rc; @@ -821,7 +821,7 @@ int hisi_sas_slave_alloc(struct scsi_device *sdev) sas_dev->dev_status = HISI_SAS_DEV_NORMAL; return 0; } -EXPORT_SYMBOL_GPL(hisi_sas_slave_alloc); +EXPORT_SYMBOL_GPL(hisi_sas_sdev_init); static int hisi_sas_dev_found(struct domain_device *device) { @@ -868,11 +868,10 @@ err_out: return rc; } -int hisi_sas_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +int hisi_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { struct domain_device *dev = sdev_to_domain_dev(sdev); - int ret = sas_device_configure(sdev, lim); + int ret = sas_sdev_configure(sdev, lim); if (ret) return ret; @@ -881,7 +880,7 @@ int hisi_sas_device_configure(struct scsi_device *sdev, return 0; } -EXPORT_SYMBOL_GPL(hisi_sas_device_configure); +EXPORT_SYMBOL_GPL(hisi_sas_sdev_configure); void hisi_sas_scan_start(struct Scsi_Host *shost) { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c index c3e571be2222..bb78e53c66e2 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c @@ -1753,11 +1753,11 @@ static int check_fw_info_v1_hw(struct hisi_hba *hisi_hba) static const struct scsi_host_template sht_v1_hw = { LIBSAS_SHT_BASE_NO_SLAVE_INIT - .device_configure = hisi_sas_device_configure, + .sdev_configure = hisi_sas_sdev_configure, .scan_finished = hisi_sas_scan_finished, .scan_start = hisi_sas_scan_start, .sg_tablesize = HISI_SAS_SGE_PAGE_CNT, - .slave_alloc = hisi_sas_slave_alloc, + .sdev_init = hisi_sas_sdev_init, .shost_groups = host_v1_hw_groups, .host_reset = hisi_sas_host_reset, }; diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 1a62b5d15eca..71cd5b4450c2 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -3585,11 +3585,11 @@ static int check_fw_info_v2_hw(struct hisi_hba *hisi_hba) static const struct scsi_host_template sht_v2_hw = { LIBSAS_SHT_BASE_NO_SLAVE_INIT - .device_configure = hisi_sas_device_configure, + .sdev_configure = hisi_sas_sdev_configure, .scan_finished = hisi_sas_scan_finished, .scan_start = hisi_sas_scan_start, .sg_tablesize = HISI_SAS_SGE_PAGE_CNT, - .slave_alloc = hisi_sas_slave_alloc, + .sdev_init = hisi_sas_sdev_init, .shost_groups = host_v2_hw_groups, .sdev_groups = sdev_groups_v2_hw, .host_reset = hisi_sas_host_reset, diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 5db931663ae4..48b95d9a7927 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2908,12 +2908,12 @@ static ssize_t iopoll_q_cnt_v3_hw_show(struct device *dev, } static DEVICE_ATTR_RO(iopoll_q_cnt_v3_hw); -static int device_configure_v3_hw(struct scsi_device *sdev, - struct queue_limits *lim) +static int sdev_configure_v3_hw(struct scsi_device *sdev, + struct queue_limits *lim) { struct Scsi_Host *shost = dev_to_shost(&sdev->sdev_gendev); struct hisi_hba *hisi_hba = shost_priv(shost); - int ret = hisi_sas_device_configure(sdev, lim); + int ret = hisi_sas_sdev_configure(sdev, lim); struct device *dev = hisi_hba->dev; if (ret) @@ -3328,24 +3328,24 @@ static void hisi_sas_map_queues(struct Scsi_Host *shost) if (i == HCTX_TYPE_POLL) blk_mq_map_queues(qmap); else - blk_mq_pci_map_queues(qmap, hisi_hba->pci_dev, - BASE_VECTORS_V3_HW); + blk_mq_map_hw_queues(qmap, hisi_hba->dev, + BASE_VECTORS_V3_HW); qoff += qmap->nr_queues; } } static const struct scsi_host_template sht_v3_hw = { LIBSAS_SHT_BASE_NO_SLAVE_INIT - .device_configure = device_configure_v3_hw, + .sdev_configure = sdev_configure_v3_hw, .scan_finished = hisi_sas_scan_finished, .scan_start = hisi_sas_scan_start, .map_queues = hisi_sas_map_queues, .sg_tablesize = HISI_SAS_SGE_PAGE_CNT, .sg_prot_tablesize = HISI_SAS_SGE_PAGE_CNT, - .slave_alloc = hisi_sas_slave_alloc, + .sdev_init = hisi_sas_sdev_init, .shost_groups = host_v3_hw_groups, .sdev_groups = sdev_groups_v3_hw, - .tag_alloc_policy = BLK_TAG_ALLOC_RR, + .tag_alloc_policy_rr = true, .host_reset = hisi_sas_host_reset, .host_tagset = 1, .mq_poll = queue_complete_v3_hw, diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 0c49414c1f35..84d8de07b7ae 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -283,9 +283,10 @@ static int hpsa_scan_finished(struct Scsi_Host *sh, static int hpsa_change_queue_depth(struct scsi_device *sdev, int qdepth); static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd); -static int hpsa_slave_alloc(struct scsi_device *sdev); -static int hpsa_slave_configure(struct scsi_device *sdev); -static void hpsa_slave_destroy(struct scsi_device *sdev); +static int hpsa_sdev_init(struct scsi_device *sdev); +static int hpsa_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim); +static void hpsa_sdev_destroy(struct scsi_device *sdev); static void hpsa_update_scsi_devices(struct ctlr_info *h); static int check_for_unit_attention(struct ctlr_info *h, @@ -978,9 +979,9 @@ static const struct scsi_host_template hpsa_driver_template = { .this_id = -1, .eh_device_reset_handler = hpsa_eh_device_reset_handler, .ioctl = hpsa_ioctl, - .slave_alloc = hpsa_slave_alloc, - .slave_configure = hpsa_slave_configure, - .slave_destroy = hpsa_slave_destroy, + .sdev_init = hpsa_sdev_init, + .sdev_configure = hpsa_sdev_configure, + .sdev_destroy = hpsa_sdev_destroy, #ifdef CONFIG_COMPAT .compat_ioctl = hpsa_compat_ioctl, #endif @@ -2107,7 +2108,7 @@ static struct hpsa_scsi_dev_t *lookup_hpsa_scsi_dev(struct ctlr_info *h, return NULL; } -static int hpsa_slave_alloc(struct scsi_device *sdev) +static int hpsa_sdev_init(struct scsi_device *sdev) { struct hpsa_scsi_dev_t *sd = NULL; unsigned long flags; @@ -2142,7 +2143,8 @@ static int hpsa_slave_alloc(struct scsi_device *sdev) /* configure scsi device based on internal per-device structure */ #define CTLR_TIMEOUT (120 * HZ) -static int hpsa_slave_configure(struct scsi_device *sdev) +static int hpsa_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct hpsa_scsi_dev_t *sd; int queue_depth; @@ -2173,7 +2175,7 @@ static int hpsa_slave_configure(struct scsi_device *sdev) return 0; } -static void hpsa_slave_destroy(struct scsi_device *sdev) +static void hpsa_sdev_destroy(struct scsi_device *sdev) { struct hpsa_scsi_dev_t *hdev = NULL; diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c index e889f268601b..21f1d9871a33 100644 --- a/drivers/scsi/hptiop.c +++ b/drivers/scsi/hptiop.c @@ -1151,8 +1151,8 @@ static struct attribute *hptiop_host_attrs[] = { ATTRIBUTE_GROUPS(hptiop_host); -static int hptiop_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int hptiop_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { if (sdev->type == TYPE_TAPE) lim->max_hw_sectors = 8192; @@ -1168,7 +1168,7 @@ static const struct scsi_host_template driver_template = { .emulated = 0, .proc_name = driver_name, .shost_groups = hptiop_host_groups, - .device_configure = hptiop_device_configure, + .sdev_configure = hptiop_sdev_configure, .this_id = -1, .change_queue_depth = hptiop_adjust_disk_queue_depth, .cmd_size = sizeof(struct hpt_cmd_priv), @@ -1634,7 +1634,7 @@ static struct hptiop_adapter_ops hptiop_mvfrey_ops = { .host_phy_flag = cpu_to_le64(1), }; -static struct pci_device_id hptiop_id_table[] = { +static const struct pci_device_id hptiop_id_table[] = { { PCI_VDEVICE(TTI, 0x3220), (kernel_ulong_t)&hptiop_itl_ops }, { PCI_VDEVICE(TTI, 0x3320), (kernel_ulong_t)&hptiop_itl_ops }, { PCI_VDEVICE(TTI, 0x3410), (kernel_ulong_t)&hptiop_itl_ops }, diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index e66c3ef74267..773ec2f31bc4 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -3393,7 +3393,7 @@ static int ibmvfc_scan_finished(struct Scsi_Host *shost, unsigned long time) } /** - * ibmvfc_slave_alloc - Setup the device's task set value + * ibmvfc_sdev_init - Setup the device's task set value * @sdev: struct scsi_device device to configure * * Set the device's task set value so that error handling works as @@ -3402,7 +3402,7 @@ static int ibmvfc_scan_finished(struct Scsi_Host *shost, unsigned long time) * Returns: * 0 on success / -ENXIO if device does not exist **/ -static int ibmvfc_slave_alloc(struct scsi_device *sdev) +static int ibmvfc_sdev_init(struct scsi_device *sdev) { struct Scsi_Host *shost = sdev->host; struct fc_rport *rport = starget_to_rport(scsi_target(sdev)); @@ -3441,8 +3441,9 @@ static int ibmvfc_target_alloc(struct scsi_target *starget) } /** - * ibmvfc_slave_configure - Configure the device + * ibmvfc_sdev_configure - Configure the device * @sdev: struct scsi_device device to configure + * @lim: Request queue limits * * Enable allow_restart for a device if it is a disk. Adjust the * queue_depth here also. @@ -3450,7 +3451,8 @@ static int ibmvfc_target_alloc(struct scsi_target *starget) * Returns: * 0 **/ -static int ibmvfc_slave_configure(struct scsi_device *sdev) +static int ibmvfc_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct Scsi_Host *shost = sdev->host; unsigned long flags = 0; @@ -3639,7 +3641,7 @@ static DEVICE_ATTR(nr_scsi_channels, S_IRUGO | S_IWUSR, * number of bytes printed to buffer **/ static ssize_t ibmvfc_read_trace(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -3662,13 +3664,13 @@ static ssize_t ibmvfc_read_trace(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute ibmvfc_trace_attr = { +static const struct bin_attribute ibmvfc_trace_attr = { .attr = { .name = "trace", .mode = S_IRUGO, }, .size = 0, - .read = ibmvfc_read_trace, + .read_new = ibmvfc_read_trace, }; #endif @@ -3696,8 +3698,8 @@ static const struct scsi_host_template driver_template = { .eh_device_reset_handler = ibmvfc_eh_device_reset_handler, .eh_target_reset_handler = ibmvfc_eh_target_reset_handler, .eh_host_reset_handler = ibmvfc_eh_host_reset_handler, - .slave_alloc = ibmvfc_slave_alloc, - .slave_configure = ibmvfc_slave_configure, + .sdev_init = ibmvfc_sdev_init, + .sdev_configure = ibmvfc_sdev_configure, .target_alloc = ibmvfc_target_alloc, .scan_finished = ibmvfc_scan_finished, .change_queue_depth = ibmvfc_change_queue_depth, diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 71f3e9563520..16a1aac11911 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -1860,14 +1860,16 @@ static void ibmvscsi_handle_crq(struct viosrp_crq *crq, } /** - * ibmvscsi_slave_configure: Set the "allow_restart" flag for each disk. + * ibmvscsi_sdev_configure: Set the "allow_restart" flag for each disk. * @sdev: struct scsi_device device to configure + * @lim: Request queue limits * * Enable allow_restart for a device if it is a disk. Adjust the * queue_depth here also as is required by the documentation for * struct scsi_host_template. */ -static int ibmvscsi_slave_configure(struct scsi_device *sdev) +static int ibmvscsi_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct Scsi_Host *shost = sdev->host; unsigned long lock_flags = 0; @@ -2091,7 +2093,7 @@ static struct scsi_host_template driver_template = { .eh_abort_handler = ibmvscsi_eh_abort_handler, .eh_device_reset_handler = ibmvscsi_eh_device_reset_handler, .eh_host_reset_handler = ibmvscsi_eh_host_reset_handler, - .slave_configure = ibmvscsi_slave_configure, + .sdev_configure = ibmvscsi_sdev_configure, .change_queue_depth = ibmvscsi_change_queue_depth, .host_reset = ibmvscsi_host_reset, .cmd_per_lun = IBMVSCSI_CMDS_PER_LUN_DEFAULT, diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c index 625fd547ee60..8648bd965287 100644 --- a/drivers/scsi/initio.c +++ b/drivers/scsi/initio.c @@ -2941,7 +2941,7 @@ static void initio_remove_one(struct pci_dev *pdev) MODULE_LICENSE("GPL"); -static struct pci_device_id initio_pci_tbl[] = { +static const struct pci_device_id initio_pci_tbl[] = { {PCI_VENDOR_ID_INIT, 0x9500, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {PCI_VENDOR_ID_INIT, 0x9400, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {PCI_VENDOR_ID_INIT, 0x9401, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 31cf2d31cceb..3bfafd43e42a 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -3366,7 +3366,7 @@ static void ipr_worker_thread(struct work_struct *work) * number of bytes printed to buffer **/ static ssize_t ipr_read_trace(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -3383,13 +3383,13 @@ static ssize_t ipr_read_trace(struct file *filp, struct kobject *kobj, return ret; } -static struct bin_attribute ipr_trace_attr = { +static const struct bin_attribute ipr_trace_attr = { .attr = { .name = "trace", .mode = S_IRUGO, }, .size = 0, - .read = ipr_read_trace, + .read_new = ipr_read_trace, }; #endif @@ -4087,7 +4087,7 @@ static struct device_attribute ipr_ioa_fw_type_attr = { }; static ssize_t ipr_read_async_err_log(struct file *filep, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *cdev = kobj_to_dev(kobj); @@ -4111,7 +4111,7 @@ static ssize_t ipr_read_async_err_log(struct file *filep, struct kobject *kobj, } static ssize_t ipr_next_async_err_log(struct file *filep, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *cdev = kobj_to_dev(kobj); @@ -4134,14 +4134,14 @@ static ssize_t ipr_next_async_err_log(struct file *filep, struct kobject *kobj, return count; } -static struct bin_attribute ipr_ioa_async_err_log = { +static const struct bin_attribute ipr_ioa_async_err_log = { .attr = { .name = "async_err_log", .mode = S_IRUGO | S_IWUSR, }, .size = 0, - .read = ipr_read_async_err_log, - .write = ipr_next_async_err_log + .read_new = ipr_read_async_err_log, + .write_new = ipr_next_async_err_log }; static struct attribute *ipr_ioa_attrs[] = { @@ -4172,7 +4172,7 @@ ATTRIBUTE_GROUPS(ipr_ioa); * number of bytes printed to buffer **/ static ssize_t ipr_read_dump(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *cdev = kobj_to_dev(kobj); @@ -4361,7 +4361,7 @@ static int ipr_free_dump(struct ipr_ioa_cfg *ioa_cfg) * number of bytes printed to buffer **/ static ssize_t ipr_write_dump(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *cdev = kobj_to_dev(kobj); @@ -4385,14 +4385,14 @@ static ssize_t ipr_write_dump(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute ipr_dump_attr = { +static const struct bin_attribute ipr_dump_attr = { .attr = { .name = "dump", .mode = S_IRUSR | S_IWUSR, }, .size = 0, - .read = ipr_read_dump, - .write = ipr_write_dump + .read_new = ipr_read_dump, + .write_new = ipr_write_dump }; #else static int ipr_free_dump(struct ipr_ioa_cfg *ioa_cfg) { return 0; }; @@ -4745,13 +4745,13 @@ static struct ipr_resource_entry *ipr_find_sdev(struct scsi_device *sdev) } /** - * ipr_slave_destroy - Unconfigure a SCSI device + * ipr_sdev_destroy - Unconfigure a SCSI device * @sdev: scsi device struct * * Return value: * nothing **/ -static void ipr_slave_destroy(struct scsi_device *sdev) +static void ipr_sdev_destroy(struct scsi_device *sdev) { struct ipr_resource_entry *res; struct ipr_ioa_cfg *ioa_cfg; @@ -4769,7 +4769,7 @@ static void ipr_slave_destroy(struct scsi_device *sdev) } /** - * ipr_device_configure - Configure a SCSI device + * ipr_sdev_configure - Configure a SCSI device * @sdev: scsi device struct * @lim: queue limits * @@ -4778,8 +4778,8 @@ static void ipr_slave_destroy(struct scsi_device *sdev) * Return value: * 0 on success **/ -static int ipr_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int ipr_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *) sdev->host->hostdata; struct ipr_resource_entry *res; @@ -4815,7 +4815,7 @@ static int ipr_device_configure(struct scsi_device *sdev, } /** - * ipr_slave_alloc - Prepare for commands to a device. + * ipr_sdev_init - Prepare for commands to a device. * @sdev: scsi device struct * * This function saves a pointer to the resource entry @@ -4826,7 +4826,7 @@ static int ipr_device_configure(struct scsi_device *sdev, * Return value: * 0 on success / -ENXIO if device does not exist **/ -static int ipr_slave_alloc(struct scsi_device *sdev) +static int ipr_sdev_init(struct scsi_device *sdev) { struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *) sdev->host->hostdata; struct ipr_resource_entry *res; @@ -6398,9 +6398,9 @@ static const struct scsi_host_template driver_template = { .eh_abort_handler = ipr_eh_abort, .eh_device_reset_handler = ipr_eh_dev_reset, .eh_host_reset_handler = ipr_eh_host_reset, - .slave_alloc = ipr_slave_alloc, - .device_configure = ipr_device_configure, - .slave_destroy = ipr_slave_destroy, + .sdev_init = ipr_sdev_init, + .sdev_configure = ipr_sdev_configure, + .sdev_destroy = ipr_sdev_destroy, .scan_finished = ipr_scan_finished, .target_destroy = ipr_target_destroy, .change_queue_depth = ipr_change_queue_depth, @@ -9844,7 +9844,7 @@ static void ipr_shutdown(struct pci_dev *pdev) } } -static struct pci_device_id ipr_pci_table[] = { +static const struct pci_device_id ipr_pci_table[] = { { PCI_VENDOR_ID_MYLEX, PCI_DEVICE_ID_IBM_GEMSTONE, PCI_VENDOR_ID_IBM, IPR_SUBS_DEV_ID_5702, 0, 0, 0 }, { PCI_VENDOR_ID_MYLEX, PCI_DEVICE_ID_IBM_GEMSTONE, diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c index 10cf5775a939..cce6c6b409ad 100644 --- a/drivers/scsi/ips.c +++ b/drivers/scsi/ips.c @@ -364,7 +364,7 @@ static struct scsi_host_template ips_driver_template = { .proc_name = "ips", .show_info = ips_show_info, .write_info = ips_write_info, - .slave_configure = ips_slave_configure, + .sdev_configure = ips_sdev_configure, .bios_param = ips_biosparam, .this_id = -1, .sg_tablesize = IPS_MAX_SG, @@ -1166,7 +1166,7 @@ static int ips_biosparam(struct scsi_device *sdev, struct block_device *bdev, /****************************************************************************/ /* */ -/* Routine Name: ips_slave_configure */ +/* Routine Name: ips_sdev_configure */ /* */ /* Routine Description: */ /* */ @@ -1174,7 +1174,7 @@ static int ips_biosparam(struct scsi_device *sdev, struct block_device *bdev, /* */ /****************************************************************************/ static int -ips_slave_configure(struct scsi_device * SDptr) +ips_sdev_configure(struct scsi_device *SDptr, struct queue_limits *lim) { ips_ha_t *ha; int min; diff --git a/drivers/scsi/ips.h b/drivers/scsi/ips.h index 65edf000e447..8ac932ec4444 100644 --- a/drivers/scsi/ips.h +++ b/drivers/scsi/ips.h @@ -400,7 +400,8 @@ */ static int ips_biosparam(struct scsi_device *sdev, struct block_device *bdev, sector_t capacity, int geom[]); - static int ips_slave_configure(struct scsi_device *SDptr); + static int ips_sdev_configure(struct scsi_device *SDptr, + struct queue_limits *lim); /* * Raid Command Formats diff --git a/drivers/scsi/isci/remote_device.c b/drivers/scsi/isci/remote_device.c index 866950a02965..287e1ba8ddd7 100644 --- a/drivers/scsi/isci/remote_device.c +++ b/drivers/scsi/isci/remote_device.c @@ -422,21 +422,6 @@ enum sci_status sci_remote_device_reset(struct isci_remote_device *idev) } } -enum sci_status sci_remote_device_reset_complete(struct isci_remote_device *idev) -{ - struct sci_base_state_machine *sm = &idev->sm; - enum sci_remote_device_states state = sm->current_state_id; - - if (state != SCI_DEV_RESETTING) { - dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %s\n", - __func__, dev_state_name(state)); - return SCI_FAILURE_INVALID_STATE; - } - - sci_change_state(sm, SCI_DEV_READY); - return SCI_SUCCESS; -} - enum sci_status sci_remote_device_frame_handler(struct isci_remote_device *idev, u32 frame_index) { @@ -1694,20 +1679,6 @@ enum sci_status sci_remote_device_abort_requests_pending_abort( return sci_remote_device_terminate_reqs_checkabort(idev, 1); } -enum sci_status isci_remote_device_reset_complete( - struct isci_host *ihost, - struct isci_remote_device *idev) -{ - unsigned long flags; - enum sci_status status; - - spin_lock_irqsave(&ihost->scic_lock, flags); - status = sci_remote_device_reset_complete(idev); - spin_unlock_irqrestore(&ihost->scic_lock, flags); - - return status; -} - void isci_dev_set_hang_detection_timeout( struct isci_remote_device *idev, u32 timeout) diff --git a/drivers/scsi/isci/remote_device.h b/drivers/scsi/isci/remote_device.h index 3ad681c4c20a..27ae45332704 100644 --- a/drivers/scsi/isci/remote_device.h +++ b/drivers/scsi/isci/remote_device.h @@ -174,19 +174,6 @@ enum sci_status sci_remote_device_stop( enum sci_status sci_remote_device_reset( struct isci_remote_device *idev); -/** - * sci_remote_device_reset_complete() - This method informs the device object - * that the reset operation is complete and the device can resume operation - * again. - * @remote_device: This parameter specifies the device which is to be informed - * of the reset complete operation. - * - * An indication that the device is resuming operation. SCI_SUCCESS the device - * is resuming operation. - */ -enum sci_status sci_remote_device_reset_complete( - struct isci_remote_device *idev); - /** * enum sci_remote_device_states - This enumeration depicts all the states * for the common remote device state machine. @@ -364,10 +351,6 @@ enum sci_status isci_remote_device_reset( struct isci_host *ihost, struct isci_remote_device *idev); -enum sci_status isci_remote_device_reset_complete( - struct isci_host *ihost, - struct isci_remote_device *idev); - enum sci_status isci_remote_device_suspend_terminate( struct isci_host *ihost, struct isci_remote_device *idev, diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index c708e1059638..e81f60985193 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -1057,8 +1057,8 @@ static umode_t iscsi_sw_tcp_attr_is_visible(int param_type, int param) return 0; } -static int iscsi_sw_tcp_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int iscsi_sw_tcp_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(sdev->host); struct iscsi_session *session = tcp_sw_host->session; @@ -1083,7 +1083,7 @@ static const struct scsi_host_template iscsi_sw_tcp_sht = { .eh_device_reset_handler= iscsi_eh_device_reset, .eh_target_reset_handler = iscsi_eh_recover_target, .dma_boundary = PAGE_SIZE - 1, - .device_configure = iscsi_sw_tcp_device_configure, + .sdev_configure = iscsi_sw_tcp_sdev_configure, .proc_name = "iscsi_tcp", .this_id = -1, .track_queue_depth = 1, diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index 80be3a936d92..fd1ef06655cb 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -2222,13 +2222,13 @@ int fc_eh_host_reset(struct scsi_cmnd *sc_cmd) EXPORT_SYMBOL(fc_eh_host_reset); /** - * fc_slave_alloc() - Configure the queue depth of a Scsi_Host + * fc_sdev_init() - Configure the queue depth of a Scsi_Host * @sdev: The SCSI device that identifies the SCSI host * * Configures queue depth based on host's cmd_per_len. If not set * then we use the libfc default. */ -int fc_slave_alloc(struct scsi_device *sdev) +int fc_sdev_init(struct scsi_device *sdev) { struct fc_rport *rport = starget_to_rport(scsi_target(sdev)); @@ -2238,7 +2238,7 @@ int fc_slave_alloc(struct scsi_device *sdev) scsi_change_queue_depth(sdev, FC_FCP_DFLT_QUEUE_DEPTH); return 0; } -EXPORT_SYMBOL(fc_slave_alloc); +EXPORT_SYMBOL(fc_sdev_init); /** * fc_fcp_destroy() - Tear down the FCP layer for a given local port diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index da11d32840e2..55ce7892f217 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -804,15 +804,14 @@ EXPORT_SYMBOL_GPL(sas_target_alloc); #define SAS_DEF_QD 256 -int sas_device_configure(struct scsi_device *scsi_dev, - struct queue_limits *lim) +int sas_sdev_configure(struct scsi_device *scsi_dev, struct queue_limits *lim) { struct domain_device *dev = sdev_to_domain_dev(scsi_dev); BUG_ON(dev->rphy->identify.device_type != SAS_END_DEVICE); if (dev_is_sata(dev)) { - ata_sas_device_configure(scsi_dev, lim, dev->sata_dev.ap); + ata_sas_sdev_configure(scsi_dev, lim, dev->sata_dev.ap); return 0; } @@ -830,7 +829,7 @@ int sas_device_configure(struct scsi_device *scsi_dev, return 0; } -EXPORT_SYMBOL_GPL(sas_device_configure); +EXPORT_SYMBOL_GPL(sas_sdev_configure); int sas_change_queue_depth(struct scsi_device *sdev, int depth) { @@ -1194,14 +1193,14 @@ void sas_task_abort(struct sas_task *task) } EXPORT_SYMBOL_GPL(sas_task_abort); -int sas_slave_alloc(struct scsi_device *sdev) +int sas_sdev_init(struct scsi_device *sdev) { if (dev_is_sata(sdev_to_domain_dev(sdev)) && sdev->lun) return -ENXIO; return 0; } -EXPORT_SYMBOL_GPL(sas_slave_alloc); +EXPORT_SYMBOL_GPL(sas_sdev_init); void sas_target_destroy(struct scsi_target *starget) { diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index 39b504164ecc..0d0213bba35d 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -6185,7 +6185,7 @@ const struct attribute_group *lpfc_vport_groups[] = { **/ static ssize_t sysfs_ctlreg_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { size_t buf_off; @@ -6244,7 +6244,7 @@ sysfs_ctlreg_write(struct file *filp, struct kobject *kobj, **/ static ssize_t sysfs_ctlreg_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { size_t buf_off; @@ -6280,14 +6280,14 @@ sysfs_ctlreg_read(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_ctlreg_attr = { +static const struct bin_attribute sysfs_ctlreg_attr = { .attr = { .name = "ctlreg", .mode = S_IRUSR | S_IWUSR, }, .size = 256, - .read = sysfs_ctlreg_read, - .write = sysfs_ctlreg_write, + .read_new = sysfs_ctlreg_read, + .write_new = sysfs_ctlreg_write, }; /** @@ -6308,7 +6308,7 @@ static struct bin_attribute sysfs_ctlreg_attr = { **/ static ssize_t sysfs_mbox_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { return -EPERM; @@ -6332,20 +6332,20 @@ sysfs_mbox_write(struct file *filp, struct kobject *kobj, **/ static ssize_t sysfs_mbox_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { return -EPERM; } -static struct bin_attribute sysfs_mbox_attr = { +static const struct bin_attribute sysfs_mbox_attr = { .attr = { .name = "mbox", .mode = S_IRUSR | S_IWUSR, }, .size = MAILBOX_SYSFS_MAX, - .read = sysfs_mbox_read, - .write = sysfs_mbox_write, + .read_new = sysfs_mbox_read, + .write_new = sysfs_mbox_write, }; /** diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index 1c6b024160da..c8f8496bbdf8 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -120,6 +120,16 @@ enum ELX_LOOPBACK_CMD { #define ELX_LOOPBACK_HEADER_SZ \ (size_t)(&((struct lpfc_sli_ct_request *)NULL)->un) +/* For non-embedded read object command */ +#define READ_OBJ_EMB0_SCHEME_0 {1, 10, 256, 128} +#define READ_OBJ_EMB0_SCHEME_1 {11, LPFC_EMB0_MAX_RD_OBJ_HBD_CNT, 512, 192} +static const struct lpfc_read_object_cmd_scheme { + u32 min_hbd_cnt; + u32 max_hbd_cnt; + u32 cmd_size; + u32 payload_word_offset; +} rd_obj_scheme[2] = {READ_OBJ_EMB0_SCHEME_0, READ_OBJ_EMB0_SCHEME_1}; + struct lpfc_dmabufext { struct lpfc_dmabuf dma; uint32_t size; @@ -3538,6 +3548,103 @@ lpfc_bsg_mbox_ext_session_reset(struct lpfc_hba *phba) return; } +/** + * lpfc_rd_obj_emb0_handle_job - Handles completion for non-embedded + * READ_OBJECT_V0 mailbox commands + * @phba: pointer to lpfc_hba data struct + * @pmb_buf: pointer to mailbox buffer + * @sli_cfg_mbx: pointer to SLI_CONFIG mailbox memory region + * @job: pointer to bsg_job struct + * @bsg_reply: point to bsg_reply struct + * + * Given a non-embedded READ_OBJECT_V0's HBD_CNT, this routine copies + * a READ_OBJECT_V0 mailbox command's read data payload into a bsg_job + * structure for passing back to application layer. + * + * Return codes + * 0 - successful + * -EINVAL - invalid HBD_CNT + * -ENODEV - pointer to bsg_job struct is NULL + **/ +static int +lpfc_rd_obj_emb0_handle_job(struct lpfc_hba *phba, u8 *pmb_buf, + struct lpfc_sli_config_mbox *sli_cfg_mbx, + struct bsg_job *job, + struct fc_bsg_reply *bsg_reply) +{ + struct lpfc_dmabuf *curr_dmabuf, *next_dmabuf; + struct lpfc_sli_config_emb0_subsys *emb0_subsys; + u32 hbd_cnt; + u32 dma_buf_len; + u8 i = 0; + size_t extra_bytes; + off_t skip = 0; + + if (!job) { + lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC, + "2496 NULL job\n"); + return -ENODEV; + } + + if (!bsg_reply) { + lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC, + "2498 NULL bsg_reply\n"); + return -ENODEV; + } + + emb0_subsys = &sli_cfg_mbx->un.sli_config_emb0_subsys; + + hbd_cnt = bsg_bf_get(lpfc_emb0_subcmnd_rd_obj_hbd_cnt, + emb0_subsys); + + /* Calculate where the read object's read data payload is located based + * on HBD count scheme. + */ + if (hbd_cnt >= rd_obj_scheme[0].min_hbd_cnt && + hbd_cnt <= rd_obj_scheme[0].max_hbd_cnt) { + skip = rd_obj_scheme[0].payload_word_offset * 4; + } else if (hbd_cnt >= rd_obj_scheme[1].min_hbd_cnt && + hbd_cnt <= rd_obj_scheme[1].max_hbd_cnt) { + skip = rd_obj_scheme[1].payload_word_offset * 4; + } else { + lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC, + "2497 bad hbd_count 0x%08x\n", + hbd_cnt); + return -EINVAL; + } + + /* Copy SLI_CONFIG command and READ_OBJECT response first */ + bsg_reply->reply_payload_rcv_len = + sg_copy_from_buffer(job->reply_payload.sg_list, + job->reply_payload.sg_cnt, + pmb_buf, skip); + + /* Copy data from hbds */ + list_for_each_entry_safe(curr_dmabuf, next_dmabuf, + &phba->mbox_ext_buf_ctx.ext_dmabuf_list, + list) { + dma_buf_len = emb0_subsys->hbd[i].buf_len; + + /* Use sg_copy_buffer to specify a skip offset */ + extra_bytes = sg_copy_buffer(job->reply_payload.sg_list, + job->reply_payload.sg_cnt, + curr_dmabuf->virt, + dma_buf_len, skip, false); + + bsg_reply->reply_payload_rcv_len += extra_bytes; + + skip += extra_bytes; + + lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC, + "2499 copied hbd[%d] " + "0x%zx bytes\n", + i, extra_bytes); + i++; + } + + return 0; +} + /** * lpfc_bsg_issue_mbox_ext_handle_job - job handler for multi-buffer mbox cmpl * @phba: Pointer to HBA context object. @@ -3551,10 +3658,10 @@ lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq) { struct bsg_job_data *dd_data; struct bsg_job *job; - struct fc_bsg_reply *bsg_reply; + struct fc_bsg_reply *bsg_reply = NULL; uint8_t *pmb, *pmb_buf; unsigned long flags; - uint32_t size; + u32 size, opcode; int rc = 0; struct lpfc_dmabuf *dmabuf; struct lpfc_sli_config_mbox *sli_cfg_mbx; @@ -3591,6 +3698,24 @@ lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq) lpfc_sli_pcimem_bcopy(&pmbx[sizeof(MAILBOX_t)], &pmbx[sizeof(MAILBOX_t)], sli_cfg_mbx->un.sli_config_emb0_subsys.mse[0].buf_len); + + /* Special handling for non-embedded READ_OBJECT */ + opcode = bsg_bf_get(lpfc_emb0_subcmnd_opcode, + &sli_cfg_mbx->un.sli_config_emb0_subsys); + switch (opcode) { + case COMN_OPCODE_READ_OBJECT: + if (job) { + rc = lpfc_rd_obj_emb0_handle_job(phba, pmb_buf, + sli_cfg_mbx, + job, + bsg_reply); + bsg_reply->result = rc; + goto done; + } + break; + default: + break; + } } /* Complete the job if the job is still active */ @@ -3604,12 +3729,14 @@ lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq) /* result for successful */ bsg_reply->result = 0; +done: lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC, "2937 SLI_CONFIG ext-buffer mailbox command " "(x%x/x%x) complete bsg job done, bsize:%d\n", phba->mbox_ext_buf_ctx.nembType, - phba->mbox_ext_buf_ctx.mboxType, size); + phba->mbox_ext_buf_ctx.mboxType, + job->reply_payload.payload_len); lpfc_idiag_mbxacc_dump_bsg_mbox(phba, phba->mbox_ext_buf_ctx.nembType, phba->mbox_ext_buf_ctx.mboxType, @@ -3819,14 +3946,16 @@ lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct bsg_job *job, { struct fc_bsg_request *bsg_request = job->request; struct lpfc_sli_config_mbox *sli_cfg_mbx; + struct lpfc_sli_config_emb0_subsys *emb0_subsys; + struct list_head *ext_dmabuf_list; struct dfc_mbox_req *mbox_req; struct lpfc_dmabuf *curr_dmabuf, *next_dmabuf; - uint32_t ext_buf_cnt, ext_buf_index; + u32 ext_buf_cnt, ext_buf_index, hbd_cnt; struct lpfc_dmabuf *ext_dmabuf = NULL; struct bsg_job_data *dd_data = NULL; LPFC_MBOXQ_t *pmboxq = NULL; MAILBOX_t *pmb; - uint8_t *pmbx; + u8 *pmbx, opcode; int rc, i; mbox_req = @@ -3836,8 +3965,9 @@ lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct bsg_job *job, sli_cfg_mbx = (struct lpfc_sli_config_mbox *)dmabuf->virt; if (nemb_tp == nemb_mse) { + emb0_subsys = &sli_cfg_mbx->un.sli_config_emb0_subsys; ext_buf_cnt = bsg_bf_get(lpfc_mbox_hdr_mse_cnt, - &sli_cfg_mbx->un.sli_config_emb0_subsys.sli_config_hdr); + &emb0_subsys->sli_config_hdr); if (ext_buf_cnt > LPFC_MBX_SLI_CONFIG_MAX_MSE) { lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC, "2945 Handled SLI_CONFIG(mse) rd, " @@ -3847,6 +3977,57 @@ lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct bsg_job *job, rc = -ERANGE; goto job_error; } + + /* Special handling for non-embedded READ_OBJECT */ + opcode = bsg_bf_get(lpfc_emb0_subcmnd_opcode, emb0_subsys); + switch (opcode) { + case COMN_OPCODE_READ_OBJECT: + hbd_cnt = bsg_bf_get(lpfc_emb0_subcmnd_rd_obj_hbd_cnt, + emb0_subsys); + lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC, + "2449 SLI_CONFIG(mse) rd non-embedded " + "hbd count = %d\n", + hbd_cnt); + + ext_dmabuf_list = + &phba->mbox_ext_buf_ctx.ext_dmabuf_list; + + /* Allocate hbds */ + for (i = 0; i < hbd_cnt; i++) { + ext_dmabuf = lpfc_bsg_dma_page_alloc(phba); + if (!ext_dmabuf) { + rc = -ENOMEM; + goto job_error; + } + list_add_tail(&ext_dmabuf->list, + ext_dmabuf_list); + } + + /* Fill out the physical memory addresses for the + * hbds + */ + i = 0; + list_for_each_entry_safe(curr_dmabuf, next_dmabuf, + ext_dmabuf_list, list) { + emb0_subsys->hbd[i].pa_hi = + putPaddrHigh(curr_dmabuf->phys); + emb0_subsys->hbd[i].pa_lo = + putPaddrLow(curr_dmabuf->phys); + + lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC, + "2495 SLI_CONFIG(hbd)[%d], " + "bufLen:%d, addrHi:x%x, " + "addrLo:x%x\n", i, + emb0_subsys->hbd[i].buf_len, + emb0_subsys->hbd[i].pa_hi, + emb0_subsys->hbd[i].pa_lo); + i++; + } + break; + default: + break; + } + lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC, "2941 Handled SLI_CONFIG(mse) rd, " "ext_buf_cnt:%d\n", ext_buf_cnt); @@ -4223,6 +4404,7 @@ lpfc_bsg_handle_sli_cfg_mbox(struct lpfc_hba *phba, struct bsg_job *job, case COMN_OPCODE_GET_CNTL_ATTRIBUTES: case COMN_OPCODE_GET_PROFILE_CONFIG: case COMN_OPCODE_SET_FEATURES: + case COMN_OPCODE_READ_OBJECT: lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC, "3106 Handled SLI_CONFIG " "subsys_comn, opcode:x%x\n", @@ -4665,8 +4847,7 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct bsg_job *job, bsg_reply->reply_payload_rcv_len = 0; /* sanity check to protect driver */ - if (job->reply_payload.payload_len > BSG_MBOX_SIZE || - job->request_payload.payload_len > BSG_MBOX_SIZE) { + if (job->request_payload.payload_len > BSG_MBOX_SIZE) { rc = -ERANGE; goto job_done; } @@ -4737,6 +4918,19 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct bsg_job *job, pmb->mbxOwner = OWN_HOST; pmboxq->vport = vport; + /* non-embedded SLI_CONFIG requests already parsed, check others */ + if (unlikely(job->reply_payload.payload_len > BSG_MBOX_SIZE)) { + lpfc_printf_log(phba, KERN_WARNING, LOG_LIBDFC, + "2729 Cmd x%x (x%x/x%x) request has " + "out-of-range reply payload length x%x\n", + pmb->mbxCommand, + lpfc_sli_config_mbox_subsys_get(phba, pmboxq), + lpfc_sli_config_mbox_opcode_get(phba, pmboxq), + job->reply_payload.payload_len); + rc = -ERANGE; + goto job_done; + } + /* If HBA encountered an error attention, allow only DUMP * or RESTART mailbox commands until the HBA is restarted. */ diff --git a/drivers/scsi/lpfc/lpfc_bsg.h b/drivers/scsi/lpfc/lpfc_bsg.h index 3c04ca2d7455..27e7a033b53d 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.h +++ b/drivers/scsi/lpfc/lpfc_bsg.h @@ -1,7 +1,7 @@ /******************************************************************* * This file is part of the Emulex Linux Device Driver for * * Fibre Channel Host Bus Adapters. * - * Copyright (C) 2017-2022 Broadcom. All Rights Reserved. The term * + * Copyright (C) 2017-2024 Broadcom. All Rights Reserved. The term * * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries. * * Copyright (C) 2010-2015 Emulex. All rights reserved. * * EMULEX and SLI are trademarks of Emulex. * @@ -239,12 +239,27 @@ struct lpfc_sli_config_emb0_subsys { uint32_t timeout; /* comn_set_feature timeout */ uint32_t request_length; /* comn_set_feature request len */ uint32_t version; /* comn_set_feature version */ - uint32_t csf_feature; /* comn_set_feature feature */ + uint32_t word68; /* comn_set_feature feature */ +#define lpfc_emb0_subcmnd_csf_feat_SHIFT 0 +#define lpfc_emb0_subcmnd_csf_feat_MASK 0xffffffff +#define lpfc_emb0_subcmnd_csf_feat_WORD word68 +#define lpfc_emb0_subcmnd_rd_obj_des_rd_len_SHIFT 0 +#define lpfc_emb0_subcmnd_rd_obj_des_rd_len_MASK 0x00ffffff +#define lpfc_emb0_subcmnd_rd_obj_des_rd_len_WORD word68 uint32_t word69; /* comn_set_feature parameter len */ uint32_t word70; /* comn_set_feature parameter val0 */ #define lpfc_emb0_subcmnd_csf_p0_SHIFT 0 #define lpfc_emb0_subcmnd_csf_p0_MASK 0x3 #define lpfc_emb0_subcmnd_csf_p0_WORD word70 + uint32_t reserved71[25]; + uint32_t word96; /* rd_obj hbd_count */ +#define lpfc_emb0_subcmnd_rd_obj_hbd_cnt_SHIFT 0 +#define lpfc_emb0_subcmnd_rd_obj_hbd_cnt_MASK 0xffffffff +#define lpfc_emb0_subcmnd_rd_obj_hbd_cnt_WORD word96 +#define LPFC_EMB0_MAX_RD_OBJ_HBD_CNT 31 + struct lpfc_sli_config_hbd hbd[LPFC_EMB0_MAX_RD_OBJ_HBD_CNT]; + uint32_t word190; + uint32_t word191; }; struct lpfc_sli_config_emb1_subsys { diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index 30891ad17e2a..12c67cdd7c19 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -1646,14 +1646,12 @@ out: /* If the caller wanted a synchronous DA_ID completion, signal the * wait obj and clear flag to reset the vport. */ - if (ndlp->save_flags & NLP_WAIT_FOR_DA_ID) { + if (test_bit(NLP_WAIT_FOR_DA_ID, &ndlp->save_flags)) { if (ndlp->da_id_waitq) wake_up(ndlp->da_id_waitq); } - spin_lock_irq(&ndlp->lock); - ndlp->save_flags &= ~NLP_WAIT_FOR_DA_ID; - spin_unlock_irq(&ndlp->lock); + clear_bit(NLP_WAIT_FOR_DA_ID, &ndlp->save_flags); lpfc_ct_free_iocb(phba, cmdiocb); lpfc_nlp_put(ndlp); diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h index 3e173b5d00e0..3d47dc7458d1 100644 --- a/drivers/scsi/lpfc/lpfc_disc.h +++ b/drivers/scsi/lpfc/lpfc_disc.h @@ -85,13 +85,13 @@ enum lpfc_fc4_xpt_flags { NLP_XPT_HAS_HH = 0x10 }; -enum lpfc_nlp_save_flags { +enum lpfc_nlp_save_flags { /* mask bits */ /* devloss occurred during recovery */ - NLP_IN_RECOV_POST_DEV_LOSS = 0x1, + NLP_IN_RECOV_POST_DEV_LOSS, /* wait for outstanding LOGO to cmpl */ - NLP_WAIT_FOR_LOGO = 0x2, + NLP_WAIT_FOR_LOGO, /* wait for outstanding DA_ID to finish */ - NLP_WAIT_FOR_DA_ID = 0x4 + NLP_WAIT_FOR_DA_ID }; struct lpfc_nodelist { @@ -154,7 +154,7 @@ struct lpfc_nodelist { uint32_t fc4_prli_sent; /* flags to keep ndlp alive until special conditions are met */ - enum lpfc_nlp_save_flags save_flags; + unsigned long save_flags; enum lpfc_fc4_xpt_flags fc4_xpt_flags; @@ -208,7 +208,6 @@ enum lpfc_nlp_flag { NPR list */ NLP_RM_DFLT_RPI = 26, /* need to remove leftover dflt RPI */ NLP_NODEV_REMOVE = 27, /* Defer removal till discovery ends */ - NLP_TARGET_REMOVE = 28, /* Target remove in process */ NLP_SC_REQ = 29, /* Target requires authentication */ NLP_FIRSTBURST = 30, /* Target supports FirstBurst */ NLP_RPI_REGISTERED = 31 /* nlp_rpi is valid */ diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 37f0a930d469..1d7db49a8fe4 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -2988,12 +2988,8 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag); - spin_lock_irq(&ndlp->lock); - if (ndlp->save_flags & NLP_WAIT_FOR_LOGO) { + if (test_and_clear_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags)) wake_up_waiter = 1; - ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO; - } - spin_unlock_irq(&ndlp->lock); lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD, "LOGO cmpl: status:x%x/x%x did:x%x", @@ -3035,19 +3031,6 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, /* Call state machine. This will unregister the rpi if needed. */ lpfc_disc_state_machine(vport, ndlp, cmdiocb, NLP_EVT_CMPL_LOGO); - if (skip_recovery) - goto out; - - /* The driver sets this flag for an NPIV instance that doesn't want to - * log into the remote port. - */ - if (test_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag)) { - clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag); - lpfc_disc_state_machine(vport, ndlp, cmdiocb, - NLP_EVT_DEVICE_RM); - goto out_rsrc_free; - } - out: /* At this point, the LOGO processing is complete. NOTE: For a * pt2pt topology, we are assuming the NPortID will only change @@ -3091,7 +3074,7 @@ out: lpfc_disc_state_machine(vport, ndlp, cmdiocb, NLP_EVT_DEVICE_RM); } -out_rsrc_free: + /* Driver is done with the I/O. */ lpfc_els_free_iocb(phba, cmdiocb); lpfc_nlp_put(ndlp); @@ -4583,6 +4566,7 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, int link_reset = 0, rc; u32 ulp_status = get_job_ulpstatus(phba, rspiocb); u32 ulp_word4 = get_job_word4(phba, rspiocb); + u8 rsn_code_exp = 0; /* Note: cmd_dmabuf may be 0 for internal driver abort @@ -4798,11 +4782,22 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, break; case LSRJT_LOGICAL_BSY: + rsn_code_exp = stat.un.b.lsRjtRsnCodeExp; if ((cmd == ELS_CMD_PLOGI) || (cmd == ELS_CMD_PRLI) || (cmd == ELS_CMD_NVMEPRLI)) { delay = 1000; maxretry = 48; + + /* An authentication LS_RJT reason code + * explanation means some error in the + * security settings end-to-end. Reduce + * the retry count to allow lpfc to clear + * RSCN mode and not race with dev_loss. + */ + if (cmd == ELS_CMD_PLOGI && + rsn_code_exp == LSEXP_AUTH_REQ) + maxretry = 8; } else if (cmd == ELS_CMD_FDISC) { /* FDISC retry policy */ maxretry = 48; @@ -4831,6 +4826,20 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, "0820 FLOGI (x%x). " "BBCredit Not Supported\n", stat.un.lsRjtError); + } else if (cmd == ELS_CMD_PLOGI) { + rsn_code_exp = stat.un.b.lsRjtRsnCodeExp; + + /* An authentication LS_RJT reason code + * explanation means some error in the + * security settings end-to-end. Reduce + * the retry count to allow lpfc to clear + * RSCN mode and not race with dev_loss. + */ + if (rsn_code_exp == LSEXP_AUTH_REQ) { + delay = 1000; + retry = 1; + maxretry = 8; + } } break; @@ -10411,8 +10420,6 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, } } - clear_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag); - lpfc_disc_state_machine(vport, ndlp, elsiocb, NLP_EVT_RCV_PLOGI); @@ -11498,15 +11505,13 @@ lpfc_cmpl_els_npiv_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, lpfc_can_disctmo(vport); } - if (ndlp->save_flags & NLP_WAIT_FOR_LOGO) { + if (test_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags)) { /* Wake up lpfc_vport_delete if waiting...*/ if (ndlp->logo_waitq) wake_up(ndlp->logo_waitq); clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag); clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag); - spin_lock_irq(&ndlp->lock); - ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO; - spin_unlock_irq(&ndlp->lock); + clear_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags); } /* Safe to release resources now. */ diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 4036a9838bb5..36e66df36a18 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -414,12 +414,7 @@ void lpfc_check_nlp_post_devloss(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) { - unsigned long iflags; - - spin_lock_irqsave(&ndlp->lock, iflags); - if (ndlp->save_flags & NLP_IN_RECOV_POST_DEV_LOSS) { - ndlp->save_flags &= ~NLP_IN_RECOV_POST_DEV_LOSS; - spin_unlock_irqrestore(&ndlp->lock, iflags); + if (test_and_clear_bit(NLP_IN_RECOV_POST_DEV_LOSS, &ndlp->save_flags)) { lpfc_nlp_get(ndlp); lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_NODE, "8438 Devloss timeout reversed on DID x%x " @@ -427,9 +422,7 @@ lpfc_check_nlp_post_devloss(struct lpfc_vport *vport, "port_state = x%x\n", ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp, ndlp->nlp_flag, vport->port_state); - return; } - spin_unlock_irqrestore(&ndlp->lock, iflags); } /** @@ -546,9 +539,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp, ndlp->nlp_flag, vport->port_state); - spin_lock_irqsave(&ndlp->lock, iflags); - ndlp->save_flags |= NLP_IN_RECOV_POST_DEV_LOSS; - spin_unlock_irqrestore(&ndlp->lock, iflags); + set_bit(NLP_IN_RECOV_POST_DEV_LOSS, &ndlp->save_flags); return fcf_inuse; } else if (ndlp->nlp_state == NLP_STE_UNMAPPED_NODE) { /* Fabric node fully recovered before this dev_loss_tmo diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h index d5c15742f7f2..32298285ea5e 100644 --- a/drivers/scsi/lpfc/lpfc_hw.h +++ b/drivers/scsi/lpfc/lpfc_hw.h @@ -1,7 +1,7 @@ /******************************************************************* * This file is part of the Emulex Linux Device Driver for * * Fibre Channel Host Bus Adapters. * - * Copyright (C) 2017-2023 Broadcom. All Rights Reserved. The term * + * Copyright (C) 2017-2024 Broadcom. All Rights Reserved. The term * * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries. * * Copyright (C) 2004-2016 Emulex. All rights reserved. * * EMULEX and SLI are trademarks of Emulex. * @@ -724,6 +724,7 @@ struct ls_rjt { /* Structure is in Big Endian format */ #define LSEXP_OUT_OF_RESOURCE 0x29 #define LSEXP_CANT_GIVE_DATA 0x2A #define LSEXP_REQ_UNSUPPORTED 0x2C +#define LSEXP_AUTH_REQ 0x48 #define LSEXP_NO_RSRC_ASSIGN 0x52 uint8_t vendorUnique; /* FC Word 0, bit 0: 7 */ } b; diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h index 26e1313ebb21..2dedb273b091 100644 --- a/drivers/scsi/lpfc/lpfc_hw4.h +++ b/drivers/scsi/lpfc/lpfc_hw4.h @@ -1907,22 +1907,22 @@ struct lpfc_mbx_query_fw_config { uint32_t asic_revision; uint32_t physical_port; uint32_t function_mode; -#define LPFC_FCOE_INI_MODE 0x00000040 -#define LPFC_FCOE_TGT_MODE 0x00000080 +#define LPFC_FC_INI_MODE 0x00000040 +#define LPFC_FC_TGT_MODE 0x00000080 #define LPFC_DUA_MODE 0x00000800 - uint32_t ulp0_mode; -#define LPFC_ULP_FCOE_INIT_MODE 0x00000040 -#define LPFC_ULP_FCOE_TGT_MODE 0x00000080 - uint32_t ulp0_nap_words[12]; - uint32_t ulp1_mode; - uint32_t ulp1_nap_words[12]; + uint32_t oper_mode; + uint32_t rsvd9[2]; + uint32_t wqid_base; + uint32_t wqid_tot; + uint32_t rqid_base; + uint32_t rqid_tot; + uint32_t rsvd15[19]; uint32_t function_capabilities; uint32_t cqid_base; uint32_t cqid_tot; uint32_t eqid_base; uint32_t eqid_tot; - uint32_t ulp0_nap2_words[2]; - uint32_t ulp1_nap2_words[2]; + uint32_t rsvd39[4]; } rsp; }; @@ -3778,25 +3778,22 @@ struct lpfc_mbx_get_prof_cfg { struct lpfc_controller_attribute { uint32_t version_string[8]; uint32_t manufacturer_name[8]; - uint32_t supported_modes; + uint32_t rsvd16; uint32_t word17; -#define lpfc_cntl_attr_eprom_ver_lo_SHIFT 0 -#define lpfc_cntl_attr_eprom_ver_lo_MASK 0x000000ff -#define lpfc_cntl_attr_eprom_ver_lo_WORD word17 -#define lpfc_cntl_attr_eprom_ver_hi_SHIFT 8 -#define lpfc_cntl_attr_eprom_ver_hi_MASK 0x000000ff -#define lpfc_cntl_attr_eprom_ver_hi_WORD word17 #define lpfc_cntl_attr_flash_id_SHIFT 16 #define lpfc_cntl_attr_flash_id_MASK 0x000000ff #define lpfc_cntl_attr_flash_id_WORD word17 - uint32_t mbx_da_struct_ver; - uint32_t ep_fw_da_struct_ver; +#define lpfc_cntl_attr_boot_enable_SHIFT 24 +#define lpfc_cntl_attr_boot_enable_MASK 0x00000001 +#define lpfc_cntl_attr_boot_enable_WORD word17 + uint32_t rsvd18[2]; uint32_t ncsi_ver_str[3]; - uint32_t dflt_ext_timeout; + uint32_t rsvd23; uint32_t model_number[8]; uint32_t description[16]; uint32_t serial_number[8]; - uint32_t ip_ver_str[8]; + uint32_t ipl_name[5]; + uint32_t rsvd61[3]; uint32_t fw_ver_str[8]; uint32_t bios_ver_str[8]; uint32_t redboot_ver_str[8]; @@ -3804,53 +3801,31 @@ struct lpfc_controller_attribute { uint32_t flash_fw_ver_str[8]; uint32_t functionality; uint32_t word105; -#define lpfc_cntl_attr_max_cbd_len_SHIFT 0 -#define lpfc_cntl_attr_max_cbd_len_MASK 0x0000ffff -#define lpfc_cntl_attr_max_cbd_len_WORD word105 #define lpfc_cntl_attr_asic_rev_SHIFT 16 #define lpfc_cntl_attr_asic_rev_MASK 0x000000ff #define lpfc_cntl_attr_asic_rev_WORD word105 -#define lpfc_cntl_attr_gen_guid0_SHIFT 24 -#define lpfc_cntl_attr_gen_guid0_MASK 0x000000ff -#define lpfc_cntl_attr_gen_guid0_WORD word105 - uint32_t gen_guid1_12[3]; + uint32_t rsvd106[3]; uint32_t word109; -#define lpfc_cntl_attr_gen_guid13_14_SHIFT 0 -#define lpfc_cntl_attr_gen_guid13_14_MASK 0x0000ffff -#define lpfc_cntl_attr_gen_guid13_14_WORD word109 -#define lpfc_cntl_attr_gen_guid15_SHIFT 16 -#define lpfc_cntl_attr_gen_guid15_MASK 0x000000ff -#define lpfc_cntl_attr_gen_guid15_WORD word109 #define lpfc_cntl_attr_hba_port_cnt_SHIFT 24 #define lpfc_cntl_attr_hba_port_cnt_MASK 0x000000ff #define lpfc_cntl_attr_hba_port_cnt_WORD word109 - uint32_t word110; -#define lpfc_cntl_attr_dflt_lnk_tmo_SHIFT 0 -#define lpfc_cntl_attr_dflt_lnk_tmo_MASK 0x0000ffff -#define lpfc_cntl_attr_dflt_lnk_tmo_WORD word110 -#define lpfc_cntl_attr_multi_func_dev_SHIFT 24 -#define lpfc_cntl_attr_multi_func_dev_MASK 0x000000ff -#define lpfc_cntl_attr_multi_func_dev_WORD word110 + uint32_t rsvd110; uint32_t word111; -#define lpfc_cntl_attr_cache_valid_SHIFT 0 -#define lpfc_cntl_attr_cache_valid_MASK 0x000000ff -#define lpfc_cntl_attr_cache_valid_WORD word111 #define lpfc_cntl_attr_hba_status_SHIFT 8 #define lpfc_cntl_attr_hba_status_MASK 0x000000ff #define lpfc_cntl_attr_hba_status_WORD word111 -#define lpfc_cntl_attr_max_domain_SHIFT 16 -#define lpfc_cntl_attr_max_domain_MASK 0x000000ff -#define lpfc_cntl_attr_max_domain_WORD word111 #define lpfc_cntl_attr_lnk_numb_SHIFT 24 #define lpfc_cntl_attr_lnk_numb_MASK 0x0000003f #define lpfc_cntl_attr_lnk_numb_WORD word111 #define lpfc_cntl_attr_lnk_type_SHIFT 30 #define lpfc_cntl_attr_lnk_type_MASK 0x00000003 #define lpfc_cntl_attr_lnk_type_WORD word111 - uint32_t fw_post_status; - uint32_t hba_mtu[8]; + uint32_t rsvd112[9]; uint32_t word121; - uint32_t reserved1[3]; +#define lpfc_cntl_attr_asic_gen_SHIFT 8 +#define lpfc_cntl_attr_asic_gen_MASK 0x000000ff +#define lpfc_cntl_attr_asic_gen_WORD word121 + uint32_t rsvd122[3]; uint32_t word125; #define lpfc_cntl_attr_pci_vendor_id_SHIFT 0 #define lpfc_cntl_attr_pci_vendor_id_MASK 0x0000ffff @@ -3875,15 +3850,7 @@ struct lpfc_controller_attribute { #define lpfc_cntl_attr_pci_fnc_num_SHIFT 16 #define lpfc_cntl_attr_pci_fnc_num_MASK 0x000000ff #define lpfc_cntl_attr_pci_fnc_num_WORD word127 -#define lpfc_cntl_attr_inf_type_SHIFT 24 -#define lpfc_cntl_attr_inf_type_MASK 0x000000ff -#define lpfc_cntl_attr_inf_type_WORD word127 - uint32_t unique_id[2]; - uint32_t word130; -#define lpfc_cntl_attr_num_netfil_SHIFT 0 -#define lpfc_cntl_attr_num_netfil_MASK 0x000000ff -#define lpfc_cntl_attr_num_netfil_WORD word130 - uint32_t reserved2[4]; + uint32_t rsvd128[7]; }; struct lpfc_mbx_get_cntl_attributes { diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 7f57397d91a9..bcadf11414c8 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -598,7 +598,7 @@ lpfc_config_port_post(struct lpfc_hba *phba) jiffies + msecs_to_jiffies(1000 * timeout)); /* Set up heart beat (HB) timer */ mod_timer(&phba->hb_tmofunc, - jiffies + msecs_to_jiffies(1000 * LPFC_HB_MBOX_INTERVAL)); + jiffies + secs_to_jiffies(LPFC_HB_MBOX_INTERVAL)); clear_bit(HBA_HBEAT_INP, &phba->hba_flag); clear_bit(HBA_HBEAT_TMO, &phba->hba_flag); phba->last_completion_time = jiffies; @@ -1267,7 +1267,7 @@ lpfc_hb_mbox_cmpl(struct lpfc_hba * phba, LPFC_MBOXQ_t * pmboxq) !test_bit(FC_UNLOADING, &phba->pport->load_flag)) mod_timer(&phba->hb_tmofunc, jiffies + - msecs_to_jiffies(1000 * LPFC_HB_MBOX_INTERVAL)); + secs_to_jiffies(LPFC_HB_MBOX_INTERVAL)); return; } @@ -1555,7 +1555,7 @@ lpfc_hb_timeout_handler(struct lpfc_hba *phba) /* If IOs are completing, no need to issue a MBX_HEARTBEAT */ spin_lock_irq(&phba->pport->work_port_lock); if (time_after(phba->last_completion_time + - msecs_to_jiffies(1000 * LPFC_HB_MBOX_INTERVAL), + secs_to_jiffies(LPFC_HB_MBOX_INTERVAL), jiffies)) { spin_unlock_irq(&phba->pport->work_port_lock); if (test_bit(HBA_HBEAT_INP, &phba->hba_flag)) @@ -3354,7 +3354,7 @@ lpfc_block_mgmt_io(struct lpfc_hba *phba, int mbx_action) spin_unlock_irqrestore(&phba->hbalock, iflag); if (mbx_action == LPFC_MBX_NO_WAIT) return; - timeout = msecs_to_jiffies(LPFC_MBOX_TMO * 1000) + jiffies; + timeout = secs_to_jiffies(LPFC_MBOX_TMO) + jiffies; spin_lock_irqsave(&phba->hbalock, iflag); if (phba->sli.mbox_active) { actcmd = phba->sli.mbox_active->u.mb.mbxCommand; @@ -3847,8 +3847,8 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) * Otherwise, let dev_loss take care of * the node. */ - if (!(ndlp->save_flags & - NLP_IN_RECOV_POST_DEV_LOSS) && + if (!test_bit(NLP_IN_RECOV_POST_DEV_LOSS, + &ndlp->save_flags) && !(ndlp->fc4_xpt_flags & (NVME_XPT_REGD | SCSI_XPT_REGD))) lpfc_disc_state_machine @@ -4924,14 +4924,14 @@ int lpfc_scan_finished(struct Scsi_Host *shost, unsigned long time) stat = 1; goto finished; } - if (time >= msecs_to_jiffies(30 * 1000)) { + if (time >= secs_to_jiffies(30)) { lpfc_printf_log(phba, KERN_INFO, LOG_INIT, "0461 Scanning longer than 30 " "seconds. Continuing initialization\n"); stat = 1; goto finished; } - if (time >= msecs_to_jiffies(15 * 1000) && + if (time >= secs_to_jiffies(15) && phba->link_state <= LPFC_LINK_DOWN) { lpfc_printf_log(phba, KERN_INFO, LOG_INIT, "0465 Link down longer than 15 " @@ -4945,7 +4945,7 @@ int lpfc_scan_finished(struct Scsi_Host *shost, unsigned long time) if (vport->num_disc_nodes || vport->fc_prli_sent) goto finished; if (!atomic_read(&vport->fc_map_cnt) && - time < msecs_to_jiffies(2 * 1000)) + time < secs_to_jiffies(2)) goto finished; if ((phba->sli.sli_flag & LPFC_SLI_MBOX_ACTIVE) != 0) goto finished; @@ -5179,8 +5179,8 @@ lpfc_vmid_poll(struct timer_list *t) lpfc_worker_wake_up(phba); /* restart the timer for the next iteration */ - mod_timer(&phba->inactive_vmid_poll, jiffies + msecs_to_jiffies(1000 * - LPFC_VMID_TIMER)); + mod_timer(&phba->inactive_vmid_poll, + jiffies + secs_to_jiffies(LPFC_VMID_TIMER)); } /** @@ -11109,14 +11109,11 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba) phba->sli4_hba.fw_func_mode = mboxq->u.mqe.un.query_fw_cfg.rsp.function_mode; - phba->sli4_hba.ulp0_mode = mboxq->u.mqe.un.query_fw_cfg.rsp.ulp0_mode; - phba->sli4_hba.ulp1_mode = mboxq->u.mqe.un.query_fw_cfg.rsp.ulp1_mode; phba->sli4_hba.physical_port = mboxq->u.mqe.un.query_fw_cfg.rsp.physical_port; lpfc_printf_log(phba, KERN_INFO, LOG_INIT, - "3251 QUERY_FW_CFG: func_mode:x%x, ulp0_mode:x%x, " - "ulp1_mode:x%x\n", phba->sli4_hba.fw_func_mode, - phba->sli4_hba.ulp0_mode, phba->sli4_hba.ulp1_mode); + "3251 QUERY_FW_CFG: func_mode:x%x\n", + phba->sli4_hba.fw_func_mode); mempool_free(mboxq, phba->mbox_mem_pool); diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c index e98f1c2b2220..fb6dbcb86c09 100644 --- a/drivers/scsi/lpfc/lpfc_mbox.c +++ b/drivers/scsi/lpfc/lpfc_mbox.c @@ -2524,8 +2524,10 @@ lpfc_reg_fcfi(struct lpfc_hba *phba, struct lpfcMboxq *mbox) bf_set(lpfc_reg_fcfi_rq_id1, reg_fcfi, REG_FCF_INVALID_QID); /* addr mode is bit wise inverted value of fcf addr_mode */ - bf_set(lpfc_reg_fcfi_mam, reg_fcfi, - (~phba->fcf.addr_mode) & 0x3); + if (test_bit(HBA_FCOE_MODE, &phba->hba_flag)) { + bf_set(lpfc_reg_fcfi_mam, reg_fcfi, + (~phba->fcf.addr_mode) & 0x3); + } } else { /* This is ONLY for NVMET MRQ == 1 */ if (phba->cfg_nvmet_mrq != 1) diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index 4d88cfe71cae..a596b80d03d4 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -64,9 +64,6 @@ static int lpfc_check_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, struct lpfc_name *nn, struct lpfc_name *pn) { - /* First, we MUST have a RPI registered */ - if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) - return 0; /* Compare the ADISC rsp WWNN / WWPN matches our internal node * table entry for that node. @@ -735,6 +732,7 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ADISC *ap; uint32_t *lp; uint32_t cmd; + int rc; pcmd = cmdiocb->cmd_dmabuf; lp = (uint32_t *) pcmd->virt; @@ -759,21 +757,29 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, * resume the RPI before the ACC goes out. */ if (vport->phba->sli_rev == LPFC_SLI_REV4) { - elsiocb = kmalloc(sizeof(struct lpfc_iocbq), - GFP_KERNEL); - if (elsiocb) { - /* Save info from cmd IOCB used in rsp */ - memcpy((uint8_t *)elsiocb, (uint8_t *)cmdiocb, - sizeof(struct lpfc_iocbq)); + /* Don't resume an unregistered RPI - unnecessary + * mailbox. Just send the ACC when the RPI is not + * registered. + */ + if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) { + elsiocb = kmalloc(sizeof(*elsiocb), GFP_KERNEL); + if (elsiocb) { + /* Save info from cmd IOCB used in + * rsp + */ + memcpy(elsiocb, cmdiocb, + sizeof(*elsiocb)); - /* Save the ELS cmd */ - elsiocb->drvrTimeout = cmd; + elsiocb->drvrTimeout = cmd; - if (lpfc_sli4_resume_rpi(ndlp, - lpfc_mbx_cmpl_resume_rpi, - elsiocb)) - kfree(elsiocb); - goto out; + rc = lpfc_sli4_resume_rpi(ndlp, + lpfc_mbx_cmpl_resume_rpi, + elsiocb); + if (rc) + kfree(elsiocb); + + goto out; + } } } @@ -815,7 +821,6 @@ out: set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag); ndlp->nlp_last_elscmd = ELS_CMD_PLOGI; ndlp->nlp_prev_state = ndlp->nlp_state; - lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); return 0; } @@ -906,7 +911,7 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, (ndlp->nlp_state >= NLP_STE_ADISC_ISSUE || ndlp->nlp_state <= NLP_STE_PRLI_ISSUE)) { mod_timer(&ndlp->nlp_delayfunc, - jiffies + msecs_to_jiffies(1000 * 1)); + jiffies + secs_to_jiffies(1)); set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag); ndlp->nlp_last_elscmd = ELS_CMD_PLOGI; lpfc_printf_vlog(vport, KERN_INFO, @@ -1332,7 +1337,7 @@ lpfc_rcv_els_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, } /* Put ndlp in npr state set plogi timer for 1 sec */ - mod_timer(&ndlp->nlp_delayfunc, jiffies + msecs_to_jiffies(1000 * 1)); + mod_timer(&ndlp->nlp_delayfunc, jiffies + secs_to_jiffies(1)); set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag); ndlp->nlp_last_elscmd = ELS_CMD_PLOGI; ndlp->nlp_prev_state = NLP_STE_PLOGI_ISSUE; @@ -1936,7 +1941,7 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport, /* Put ndlp in npr state set plogi timer for 1 sec */ mod_timer(&ndlp->nlp_delayfunc, - jiffies + msecs_to_jiffies(1000 * 1)); + jiffies + secs_to_jiffies(1)); set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag); ndlp->nlp_last_elscmd = ELS_CMD_PLOGI; @@ -2255,11 +2260,13 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, (vport->port_type == LPFC_NPIV_PORT) && vport->cfg_restrict_login) { out: - set_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag); + lpfc_printf_vlog(vport, KERN_INFO, + LOG_ELS | LOG_DISCOVERY | LOG_NODE, + "6228 Sending LOGO, determined nlp_type " + "0x%x nlp_flag x%lx refcnt %u\n", + ndlp->nlp_type, ndlp->nlp_flag, + kref_read(&ndlp->kref)); lpfc_issue_els_logo(vport, ndlp, 0); - - ndlp->nlp_prev_state = NLP_STE_PRLI_ISSUE; - lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); return ndlp->nlp_state; } @@ -2743,7 +2750,7 @@ lpfc_rcv_prlo_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag)) { mod_timer(&ndlp->nlp_delayfunc, - jiffies + msecs_to_jiffies(1000 * 1)); + jiffies + secs_to_jiffies(1)); set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag); clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag); ndlp->nlp_last_elscmd = ELS_CMD_PLOGI; diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 43dc1da4a156..b1adb9f59097 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -2237,7 +2237,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, * wait. Print a message if a 10 second wait expires and renew the * wait. This is unexpected. */ - wait_tmo = msecs_to_jiffies(LPFC_NVME_WAIT_TMO * 1000); + wait_tmo = secs_to_jiffies(LPFC_NVME_WAIT_TMO); while (true) { ret = wait_for_completion_timeout(lport_unreg_cmp, wait_tmo); if (unlikely(!ret)) { diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 905026a4782c..055ed632c14d 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5136,6 +5136,12 @@ lpfc_info(struct Scsi_Host *host) goto buffer_done; } + /* Support for BSG ioctls */ + scnprintf(tmp, sizeof(tmp), " BSG"); + if (strlcat(lpfcinfobuf, tmp, sizeof(lpfcinfobuf)) >= + sizeof(lpfcinfobuf)) + goto buffer_done; + /* PCI resettable */ if (!lpfc_check_pci_resettable(phba)) { scnprintf(tmp, sizeof(tmp), " PCI resettable"); @@ -6120,31 +6126,28 @@ lpfc_target_reset_handler(struct scsi_cmnd *cmnd) /* Issue LOGO, if no LOGO is outstanding */ spin_lock_irqsave(&pnode->lock, flags); - if (!(pnode->save_flags & NLP_WAIT_FOR_LOGO) && + if (!test_bit(NLP_WAIT_FOR_LOGO, &pnode->save_flags) && !pnode->logo_waitq) { pnode->logo_waitq = &waitq; pnode->nlp_fcp_info &= ~NLP_FCP_2_DEVICE; - set_bit(NLP_ISSUE_LOGO, &pnode->nlp_flag); - pnode->save_flags |= NLP_WAIT_FOR_LOGO; spin_unlock_irqrestore(&pnode->lock, flags); + set_bit(NLP_ISSUE_LOGO, &pnode->nlp_flag); + set_bit(NLP_WAIT_FOR_LOGO, &pnode->save_flags); lpfc_unreg_rpi(vport, pnode); wait_event_timeout(waitq, - (!(pnode->save_flags & - NLP_WAIT_FOR_LOGO)), + !test_bit(NLP_WAIT_FOR_LOGO, + &pnode->save_flags), msecs_to_jiffies(dev_loss_tmo * 1000)); - if (pnode->save_flags & NLP_WAIT_FOR_LOGO) { + if (test_and_clear_bit(NLP_WAIT_FOR_LOGO, + &pnode->save_flags)) lpfc_printf_vlog(vport, KERN_ERR, logit, "0725 SCSI layer TGTRST " "failed & LOGO TMO (%d, %llu) " "return x%x\n", tgt_id, lun_id, status); - spin_lock_irqsave(&pnode->lock, flags); - pnode->save_flags &= ~NLP_WAIT_FOR_LOGO; - } else { - spin_lock_irqsave(&pnode->lock, flags); - } + spin_lock_irqsave(&pnode->lock, flags); pnode->logo_waitq = NULL; spin_unlock_irqrestore(&pnode->lock, flags); status = SUCCESS; @@ -6226,7 +6229,7 @@ error: } /** - * lpfc_slave_alloc - scsi_host_template slave_alloc entry point + * lpfc_sdev_init - scsi_host_template sdev_init entry point * @sdev: Pointer to scsi_device. * * This routine populates the cmds_per_lun count + 2 scsi_bufs into this host's @@ -6239,7 +6242,7 @@ error: * 0 - Success **/ static int -lpfc_slave_alloc(struct scsi_device *sdev) +lpfc_sdev_init(struct scsi_device *sdev) { struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata; struct lpfc_hba *phba = vport->phba; @@ -6342,8 +6345,9 @@ lpfc_slave_alloc(struct scsi_device *sdev) } /** - * lpfc_slave_configure - scsi_host_template slave_configure entry point + * lpfc_sdev_configure - scsi_host_template sdev_configure entry point * @sdev: Pointer to scsi_device. + * @lim: Request queue limits. * * This routine configures following items * - Tag command queuing support for @sdev if supported. @@ -6353,7 +6357,7 @@ lpfc_slave_alloc(struct scsi_device *sdev) * 0 - Success **/ static int -lpfc_slave_configure(struct scsi_device *sdev) +lpfc_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata; struct lpfc_hba *phba = vport->phba; @@ -6371,13 +6375,13 @@ lpfc_slave_configure(struct scsi_device *sdev) } /** - * lpfc_slave_destroy - slave_destroy entry point of SHT data structure + * lpfc_sdev_destroy - sdev_destroy entry point of SHT data structure * @sdev: Pointer to scsi_device. * * This routine sets @sdev hostatdata filed to null. **/ static void -lpfc_slave_destroy(struct scsi_device *sdev) +lpfc_sdev_destroy(struct scsi_device *sdev) { struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata; struct lpfc_hba *phba = vport->phba; @@ -6422,7 +6426,7 @@ lpfc_create_device_data(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn, { struct lpfc_device_data *lun_info; - int memory_flags; + gfp_t memory_flags; if (unlikely(!phba) || !vport_wwpn || !target_wwpn || !(phba->cfg_fof)) @@ -6737,7 +6741,13 @@ lpfc_no_command(struct Scsi_Host *shost, struct scsi_cmnd *cmnd) } static int -lpfc_no_slave(struct scsi_device *sdev) +lpfc_init_no_sdev(struct scsi_device *sdev) +{ + return -ENODEV; +} + +static int +lpfc_config_no_sdev(struct scsi_device *sdev, struct queue_limits *lim) { return -ENODEV; } @@ -6748,8 +6758,8 @@ struct scsi_host_template lpfc_template_nvme = { .proc_name = LPFC_DRIVER_NAME, .info = lpfc_info, .queuecommand = lpfc_no_command, - .slave_alloc = lpfc_no_slave, - .slave_configure = lpfc_no_slave, + .sdev_init = lpfc_init_no_sdev, + .sdev_configure = lpfc_config_no_sdev, .scan_finished = lpfc_scan_finished, .this_id = -1, .sg_tablesize = 1, @@ -6772,9 +6782,9 @@ struct scsi_host_template lpfc_template = { .eh_device_reset_handler = lpfc_device_reset_handler, .eh_target_reset_handler = lpfc_target_reset_handler, .eh_host_reset_handler = lpfc_host_reset_handler, - .slave_alloc = lpfc_slave_alloc, - .slave_configure = lpfc_slave_configure, - .slave_destroy = lpfc_slave_destroy, + .sdev_init = lpfc_sdev_init, + .sdev_configure = lpfc_sdev_configure, + .sdev_destroy = lpfc_sdev_destroy, .scan_finished = lpfc_scan_finished, .this_id = -1, .sg_tablesize = LPFC_DEFAULT_SG_SEG_CNT, @@ -6799,9 +6809,9 @@ struct scsi_host_template lpfc_vport_template = { .eh_target_reset_handler = lpfc_target_reset_handler, .eh_bus_reset_handler = NULL, .eh_host_reset_handler = NULL, - .slave_alloc = lpfc_slave_alloc, - .slave_configure = lpfc_slave_configure, - .slave_destroy = lpfc_slave_destroy, + .sdev_init = lpfc_sdev_init, + .sdev_configure = lpfc_sdev_configure, + .sdev_destroy = lpfc_sdev_destroy, .scan_finished = lpfc_scan_finished, .this_id = -1, .sg_tablesize = LPFC_DEFAULT_SG_SEG_CNT, diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 874644b31a3e..3fd9723cd271 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -9012,7 +9012,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba) /* Start heart beat timer */ mod_timer(&phba->hb_tmofunc, - jiffies + msecs_to_jiffies(1000 * LPFC_HB_MBOX_INTERVAL)); + jiffies + secs_to_jiffies(LPFC_HB_MBOX_INTERVAL)); clear_bit(HBA_HBEAT_INP, &phba->hba_flag); clear_bit(HBA_HBEAT_TMO, &phba->hba_flag); phba->last_completion_time = jiffies; @@ -13323,7 +13323,7 @@ lpfc_sli_mbox_sys_shutdown(struct lpfc_hba *phba, int mbx_action) lpfc_sli_mbox_sys_flush(phba); return; } - timeout = msecs_to_jiffies(LPFC_MBOX_TMO * 1000) + jiffies; + timeout = secs_to_jiffies(LPFC_MBOX_TMO) + jiffies; /* Disable softirqs, including timers from obtaining phba->hbalock */ local_bh_disable(); diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h index c1e9ec0243ba..9be3da91c923 100644 --- a/drivers/scsi/lpfc/lpfc_sli4.h +++ b/drivers/scsi/lpfc/lpfc_sli4.h @@ -865,8 +865,6 @@ struct lpfc_sli4_hba { struct lpfc_name wwpn; uint32_t fw_func_mode; /* FW function protocol mode */ - uint32_t ulp0_mode; /* ULP0 protocol mode */ - uint32_t ulp1_mode; /* ULP1 protocol mode */ /* Optimized Access Storage specific queues/structures */ uint64_t oas_next_lun; diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index 61fe1220f8ad..c35f7225058e 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "14.4.0.6" +#define LPFC_DRIVER_VERSION "14.4.0.7" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/lpfc/lpfc_vmid.c b/drivers/scsi/lpfc/lpfc_vmid.c index cc3e4736f2fe..14dbfe954e42 100644 --- a/drivers/scsi/lpfc/lpfc_vmid.c +++ b/drivers/scsi/lpfc/lpfc_vmid.c @@ -278,7 +278,7 @@ int lpfc_vmid_get_appid(struct lpfc_vport *vport, char *uuid, if (!(vport->phba->pport->vmid_flag & LPFC_VMID_TIMER_ENBLD)) { mod_timer(&vport->phba->inactive_vmid_poll, jiffies + - msecs_to_jiffies(1000 * LPFC_VMID_TIMER)); + secs_to_jiffies(LPFC_VMID_TIMER)); vport->phba->pport->vmid_flag |= LPFC_VMID_TIMER_ENBLD; } } diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c index 9e0e35763377..3d70cc517573 100644 --- a/drivers/scsi/lpfc/lpfc_vport.c +++ b/drivers/scsi/lpfc/lpfc_vport.c @@ -492,21 +492,22 @@ lpfc_send_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq); spin_lock_irq(&ndlp->lock); - if (!(ndlp->save_flags & NLP_WAIT_FOR_LOGO) && + if (!test_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags) && !ndlp->logo_waitq) { ndlp->logo_waitq = &waitq; ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE; set_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag); - ndlp->save_flags |= NLP_WAIT_FOR_LOGO; + set_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags); } spin_unlock_irq(&ndlp->lock); rc = lpfc_issue_els_npiv_logo(vport, ndlp); if (!rc) { wait_event_timeout(waitq, - (!(ndlp->save_flags & NLP_WAIT_FOR_LOGO)), + !test_bit(NLP_WAIT_FOR_LOGO, + &ndlp->save_flags), msecs_to_jiffies(phba->fc_ratov * 2000)); - if (!(ndlp->save_flags & NLP_WAIT_FOR_LOGO)) + if (!test_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags)) goto logo_cmpl; /* LOGO wait failed. Correct status. */ rc = -EINTR; @@ -516,9 +517,7 @@ lpfc_send_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) /* Error - clean up node flags. */ clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag); - spin_lock_irq(&ndlp->lock); - ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO; - spin_unlock_irq(&ndlp->lock); + clear_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags); logo_cmpl: lpfc_printf_vlog(vport, KERN_INFO, LOG_VPORT, @@ -696,19 +695,20 @@ lpfc_vport_delete(struct fc_vport *fc_vport) spin_lock_irq(&ndlp->lock); ndlp->da_id_waitq = &waitq; - ndlp->save_flags |= NLP_WAIT_FOR_DA_ID; spin_unlock_irq(&ndlp->lock); + set_bit(NLP_WAIT_FOR_DA_ID, &ndlp->save_flags); rc = lpfc_ns_cmd(vport, SLI_CTNS_DA_ID, 0, 0); if (!rc) { wait_event_timeout(waitq, - !(ndlp->save_flags & NLP_WAIT_FOR_DA_ID), + !test_bit(NLP_WAIT_FOR_DA_ID, + &ndlp->save_flags), msecs_to_jiffies(phba->fc_ratov * 2000)); } lpfc_printf_vlog(vport, KERN_INFO, LOG_VPORT | LOG_ELS, "1829 DA_ID issue status %d. " - "SFlag x%x NState x%x, NFlag x%lx " + "SFlag x%lx NState x%x, NFlag x%lx " "Rpi x%x\n", rc, ndlp->save_flags, ndlp->nlp_state, ndlp->nlp_flag, ndlp->nlp_rpi); @@ -718,8 +718,8 @@ lpfc_vport_delete(struct fc_vport *fc_vport) */ spin_lock_irq(&ndlp->lock); ndlp->da_id_waitq = NULL; - ndlp->save_flags &= ~NLP_WAIT_FOR_DA_ID; spin_unlock_irq(&ndlp->lock); + clear_bit(NLP_WAIT_FOR_DA_ID, &ndlp->save_flags); } issue_logo: diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index 38976f94453e..adab151663dd 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -4551,7 +4551,7 @@ megaraid_shutdown(struct pci_dev *pdev) __megaraid_shutdown(adapter); } -static struct pci_device_id megaraid_pci_tbl[] = { +static const struct pci_device_id megaraid_pci_tbl[] = { {PCI_VENDOR_ID_AMI, PCI_DEVICE_ID_AMI_MEGARAID, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {PCI_VENDOR_ID_AMI, PCI_DEVICE_ID_AMI_MEGARAID2, diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c index bc867da650b6..60cc3372991f 100644 --- a/drivers/scsi/megaraid/megaraid_mbox.c +++ b/drivers/scsi/megaraid/megaraid_mbox.c @@ -199,7 +199,7 @@ MODULE_PARM_DESC(debug_level, "Debug level for driver (default=0)"); /* * PCI table for all supported controllers. */ -static struct pci_device_id pci_id_table_g[] = { +static const struct pci_device_id pci_id_table_g[] = { { PCI_VENDOR_ID_DELL, PCI_DEVICE_ID_PERC4_DI_DISCOVERY, @@ -621,7 +621,7 @@ megaraid_io_attach(adapter_t *adapter) host = scsi_host_alloc(&megaraid_template_g, 8); if (!host) { con_log(CL_ANN, (KERN_WARNING - "megaraid mbox: scsi_register failed\n")); + "megaraid mbox: scsi_host_alloc failed\n")); return -1; } diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 50f1dcb6d584..d85f990aec88 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include @@ -147,7 +146,7 @@ megasas_set_ld_removed_by_fw(struct megasas_instance *instance); /* * PCI ID table for all supported controllers */ -static struct pci_device_id megasas_pci_table[] = { +static const struct pci_device_id megasas_pci_table[] = { {PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_SAS1064R)}, /* xscale IOP */ @@ -2068,8 +2067,8 @@ static void megasas_set_static_target_properties(struct scsi_device *sdev, } -static int megasas_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int megasas_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { u16 pd_index = 0; struct megasas_instance *instance; @@ -2109,7 +2108,7 @@ static int megasas_device_configure(struct scsi_device *sdev, return 0; } -static int megasas_slave_alloc(struct scsi_device *sdev) +static int megasas_sdev_init(struct scsi_device *sdev) { u16 pd_index = 0, ld_tgt_id; struct megasas_instance *instance ; @@ -2154,7 +2153,7 @@ scan_target: return 0; } -static void megasas_slave_destroy(struct scsi_device *sdev) +static void megasas_sdev_destroy(struct scsi_device *sdev) { u16 ld_tgt_id; struct megasas_instance *instance; @@ -3193,7 +3192,7 @@ static void megasas_map_queues(struct Scsi_Host *shost) map = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; map->nr_queues = instance->msix_vectors - offset; map->queue_offset = 0; - blk_mq_pci_map_queues(map, instance->pdev, offset); + blk_mq_map_hw_queues(map, &instance->pdev->dev, offset); qoff += map->nr_queues; offset += map->nr_queues; @@ -3510,9 +3509,9 @@ static const struct scsi_host_template megasas_template = { .module = THIS_MODULE, .name = "Avago SAS based MegaRAID driver", .proc_name = "megaraid_sas", - .device_configure = megasas_device_configure, - .slave_alloc = megasas_slave_alloc, - .slave_destroy = megasas_slave_destroy, + .sdev_configure = megasas_sdev_configure, + .sdev_init = megasas_sdev_init, + .sdev_destroy = megasas_sdev_destroy, .queuecommand = megasas_queue_command, .eh_target_reset_handler = megasas_reset_target, .eh_abort_handler = megasas_task_abort, diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index 0c3e1ac076b5..0d72b5f1b69d 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -12,7 +12,6 @@ #include #include -#include #include #include #include diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index 10b8e4dc64f8..7589f48aebc8 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -2951,6 +2951,7 @@ void mpi3mr_bsg_init(struct mpi3mr_ioc *mrioc) .max_hw_sectors = MPI3MR_MAX_APP_XFER_SECTORS, .max_segments = MPI3MR_MAX_APP_XFER_SEGMENTS, }; + struct request_queue *q; device_initialize(bsg_dev); @@ -2966,14 +2967,17 @@ void mpi3mr_bsg_init(struct mpi3mr_ioc *mrioc) return; } - mrioc->bsg_queue = bsg_setup_queue(bsg_dev, dev_name(bsg_dev), &lim, + q = bsg_setup_queue(bsg_dev, dev_name(bsg_dev), &lim, mpi3mr_bsg_request, NULL, 0); - if (IS_ERR(mrioc->bsg_queue)) { + if (IS_ERR(q)) { ioc_err(mrioc, "%s: bsg registration failed\n", dev_name(bsg_dev)); device_del(bsg_dev); put_device(bsg_dev); + return; } + + mrioc->bsg_queue = q; } /** diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index 1bef88130d0c..b9a51d3f2024 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -4042,7 +4042,7 @@ static void mpi3mr_map_queues(struct Scsi_Host *shost) */ map->queue_offset = qoff; if (i != HCTX_TYPE_POLL) - blk_mq_pci_map_queues(map, mrioc->pdev, offset); + blk_mq_map_hw_queues(map, &mrioc->pdev->dev, offset); else blk_mq_map_queues(map); @@ -4465,14 +4465,14 @@ static int mpi3mr_scan_finished(struct Scsi_Host *shost, } /** - * mpi3mr_slave_destroy - Slave destroy callback handler + * mpi3mr_sdev_destroy - Slave destroy callback handler * @sdev: SCSI device reference * * Cleanup and free per device(lun) private data. * * Return: Nothing. */ -static void mpi3mr_slave_destroy(struct scsi_device *sdev) +static void mpi3mr_sdev_destroy(struct scsi_device *sdev) { struct Scsi_Host *shost; struct mpi3mr_ioc *mrioc; @@ -4552,7 +4552,7 @@ static void mpi3mr_target_destroy(struct scsi_target *starget) } /** - * mpi3mr_device_configure - Slave configure callback handler + * mpi3mr_sdev_configure - Slave configure callback handler * @sdev: SCSI device reference * @lim: queue limits * @@ -4561,8 +4561,8 @@ static void mpi3mr_target_destroy(struct scsi_target *starget) * * Return: 0 always. */ -static int mpi3mr_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int mpi3mr_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct scsi_target *starget; struct Scsi_Host *shost; @@ -4599,14 +4599,14 @@ static int mpi3mr_device_configure(struct scsi_device *sdev, } /** - * mpi3mr_slave_alloc -Slave alloc callback handler + * mpi3mr_sdev_init -Slave alloc callback handler * @sdev: SCSI device reference * * Allocate per device(lun) private data and initialize it. * * Return: 0 on success -ENOMEM on memory allocation failure. */ -static int mpi3mr_slave_alloc(struct scsi_device *sdev) +static int mpi3mr_sdev_init(struct scsi_device *sdev) { struct Scsi_Host *shost; struct mpi3mr_ioc *mrioc; @@ -5062,10 +5062,10 @@ static const struct scsi_host_template mpi3mr_driver_template = { .proc_name = MPI3MR_DRIVER_NAME, .queuecommand = mpi3mr_qcmd, .target_alloc = mpi3mr_target_alloc, - .slave_alloc = mpi3mr_slave_alloc, - .device_configure = mpi3mr_device_configure, + .sdev_init = mpi3mr_sdev_init, + .sdev_configure = mpi3mr_sdev_configure, .target_destroy = mpi3mr_target_destroy, - .slave_destroy = mpi3mr_slave_destroy, + .sdev_destroy = mpi3mr_sdev_destroy, .scan_finished = mpi3mr_scan_finished, .scan_start = mpi3mr_scan_start, .change_queue_depth = mpi3mr_change_queue_depth, diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 16ac2267c71e..dc43cfa83088 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5627,10 +5627,9 @@ _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc) if (rc) return rc; if (!ioc->is_gen35_ioc && ioc->manu_pg11.EEDPTagMode == 0) { - pr_err("%s: overriding NVDATA EEDPTagMode setting\n", + pr_err("%s: overriding NVDATA EEDPTagMode setting from 0 to 1\n", ioc->name); - ioc->manu_pg11.EEDPTagMode &= ~0x3; - ioc->manu_pg11.EEDPTagMode |= 0x1; + ioc->manu_pg11.EEDPTagMode = 0x1; mpt3sas_config_set_manufacturing_pg11(ioc, &mpi_reply, &ioc->manu_pg11); } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index f2a55aa5fe65..a456e5ec74d8 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -53,7 +53,6 @@ #include #include #include -#include #include #include "mpt3sas_base.h" @@ -2026,14 +2025,14 @@ scsih_target_destroy(struct scsi_target *starget) } /** - * scsih_slave_alloc - device add routine + * scsih_sdev_init - device add routine * @sdev: scsi device struct * * Return: 0 if ok. Any other return is assumed to be an error and * the device is ignored. */ static int -scsih_slave_alloc(struct scsi_device *sdev) +scsih_sdev_init(struct scsi_device *sdev) { struct Scsi_Host *shost; struct MPT3SAS_ADAPTER *ioc; @@ -2108,11 +2107,11 @@ scsih_slave_alloc(struct scsi_device *sdev) } /** - * scsih_slave_destroy - device destroy routine + * scsih_sdev_destroy - device destroy routine * @sdev: scsi device struct */ static void -scsih_slave_destroy(struct scsi_device *sdev) +scsih_sdev_destroy(struct scsi_device *sdev) { struct MPT3SAS_TARGET *sas_target_priv_data; struct scsi_target *starget; @@ -2497,7 +2496,7 @@ _scsih_enable_tlr(struct MPT3SAS_ADAPTER *ioc, struct scsi_device *sdev) } /** - * scsih_device_configure - device configure routine. + * scsih_sdev_configure - device configure routine. * @sdev: scsi device struct * @lim: queue limits * @@ -2505,7 +2504,7 @@ _scsih_enable_tlr(struct MPT3SAS_ADAPTER *ioc, struct scsi_device *sdev) * the device is ignored. */ static int -scsih_device_configure(struct scsi_device *sdev, struct queue_limits *lim) +scsih_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { struct Scsi_Host *shost = sdev->host; struct MPT3SAS_ADAPTER *ioc = shost_priv(shost); @@ -11890,7 +11889,7 @@ static void scsih_map_queues(struct Scsi_Host *shost) */ map->queue_offset = qoff; if (i != HCTX_TYPE_POLL) - blk_mq_pci_map_queues(map, ioc->pdev, offset); + blk_mq_map_hw_queues(map, &ioc->pdev->dev, offset); else blk_mq_map_queues(map); @@ -11905,10 +11904,10 @@ static const struct scsi_host_template mpt2sas_driver_template = { .proc_name = MPT2SAS_DRIVER_NAME, .queuecommand = scsih_qcmd, .target_alloc = scsih_target_alloc, - .slave_alloc = scsih_slave_alloc, - .device_configure = scsih_device_configure, + .sdev_init = scsih_sdev_init, + .sdev_configure = scsih_sdev_configure, .target_destroy = scsih_target_destroy, - .slave_destroy = scsih_slave_destroy, + .sdev_destroy = scsih_sdev_destroy, .scan_finished = scsih_scan_finished, .scan_start = scsih_scan_start, .change_queue_depth = scsih_change_queue_depth, @@ -11943,10 +11942,10 @@ static const struct scsi_host_template mpt3sas_driver_template = { .proc_name = MPT3SAS_DRIVER_NAME, .queuecommand = scsih_qcmd, .target_alloc = scsih_target_alloc, - .slave_alloc = scsih_slave_alloc, - .device_configure = scsih_device_configure, + .sdev_init = scsih_sdev_init, + .sdev_configure = scsih_sdev_configure, .target_destroy = scsih_target_destroy, - .slave_destroy = scsih_slave_destroy, + .sdev_destroy = scsih_sdev_destroy, .scan_finished = scsih_scan_finished, .scan_start = scsih_scan_start, .change_queue_depth = scsih_change_queue_depth, diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c index 020037cbf0d9..2c72da6b8cf0 100644 --- a/drivers/scsi/mvsas/mv_init.c +++ b/drivers/scsi/mvsas/mv_init.c @@ -609,7 +609,7 @@ static void mvs_pci_remove(struct pci_dev *pdev) return; } -static struct pci_device_id mvs_pci_table[] = { +static const struct pci_device_id mvs_pci_table[] = { { PCI_VDEVICE(MARVELL, 0x6320), chip_6320 }, { PCI_VDEVICE(MARVELL, 0x6340), chip_6440 }, { diff --git a/drivers/scsi/mvumi.c b/drivers/scsi/mvumi.c index d9d366ec17dc..96549e7f5705 100644 --- a/drivers/scsi/mvumi.c +++ b/drivers/scsi/mvumi.c @@ -2000,7 +2000,8 @@ static struct mvumi_instance_template mvumi_instance_9580 = { .reset_host = mvumi_reset_host_9580, }; -static int mvumi_slave_configure(struct scsi_device *sdev) +static int mvumi_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct mvumi_hba *mhba; unsigned char bitcount = sizeof(unsigned char) * 8; @@ -2172,7 +2173,7 @@ static const struct scsi_host_template mvumi_template = { .module = THIS_MODULE, .name = "Marvell Storage Controller", - .slave_configure = mvumi_slave_configure, + .sdev_configure = mvumi_sdev_configure, .queuecommand = mvumi_queue_command, .eh_timed_out = mvumi_timed_out, .eh_host_reset_handler = mvumi_host_reset, diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c index a7e64b867c8e..dc4bd422b601 100644 --- a/drivers/scsi/myrb.c +++ b/drivers/scsi/myrb.c @@ -1619,7 +1619,7 @@ static int myrb_queuecommand(struct Scsi_Host *shost, return myrb_pthru_queuecommand(shost, scmd); } -static int myrb_ldev_slave_alloc(struct scsi_device *sdev) +static int myrb_ldev_sdev_init(struct scsi_device *sdev) { struct myrb_hba *cb = shost_priv(sdev->host); struct myrb_ldev_info *ldev_info; @@ -1627,8 +1627,6 @@ static int myrb_ldev_slave_alloc(struct scsi_device *sdev) enum raid_level level; ldev_info = cb->ldev_info_buf + ldev_num; - if (!ldev_info) - return -ENXIO; sdev->hostdata = kzalloc(sizeof(*ldev_info), GFP_KERNEL); if (!sdev->hostdata) @@ -1665,7 +1663,7 @@ static int myrb_ldev_slave_alloc(struct scsi_device *sdev) return 0; } -static int myrb_pdev_slave_alloc(struct scsi_device *sdev) +static int myrb_pdev_sdev_init(struct scsi_device *sdev) { struct myrb_hba *cb = shost_priv(sdev->host); struct myrb_pdev_state *pdev_info; @@ -1701,7 +1699,7 @@ static int myrb_pdev_slave_alloc(struct scsi_device *sdev) return 0; } -static int myrb_slave_alloc(struct scsi_device *sdev) +static int myrb_sdev_init(struct scsi_device *sdev) { if (sdev->channel > myrb_logical_channel(sdev->host)) return -ENXIO; @@ -1710,12 +1708,13 @@ static int myrb_slave_alloc(struct scsi_device *sdev) return -ENXIO; if (sdev->channel == myrb_logical_channel(sdev->host)) - return myrb_ldev_slave_alloc(sdev); + return myrb_ldev_sdev_init(sdev); - return myrb_pdev_slave_alloc(sdev); + return myrb_pdev_sdev_init(sdev); } -static int myrb_slave_configure(struct scsi_device *sdev) +static int myrb_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct myrb_ldev_info *ldev_info; @@ -1741,7 +1740,7 @@ static int myrb_slave_configure(struct scsi_device *sdev) return 0; } -static void myrb_slave_destroy(struct scsi_device *sdev) +static void myrb_sdev_destroy(struct scsi_device *sdev) { kfree(sdev->hostdata); } @@ -2208,9 +2207,9 @@ static const struct scsi_host_template myrb_template = { .proc_name = "myrb", .queuecommand = myrb_queuecommand, .eh_host_reset_handler = myrb_host_reset, - .slave_alloc = myrb_slave_alloc, - .slave_configure = myrb_slave_configure, - .slave_destroy = myrb_slave_destroy, + .sdev_init = myrb_sdev_init, + .sdev_configure = myrb_sdev_configure, + .sdev_destroy = myrb_sdev_destroy, .bios_param = myrb_biosparam, .cmd_size = sizeof(struct myrb_cmdblk), .shost_groups = myrb_shost_groups, diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index 1469d0c54e45..95af3bb03834 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -1786,7 +1786,7 @@ static unsigned short myrs_translate_ldev(struct myrs_hba *cs, return ldev_num; } -static int myrs_slave_alloc(struct scsi_device *sdev) +static int myrs_sdev_init(struct scsi_device *sdev) { struct myrs_hba *cs = shost_priv(sdev->host); unsigned char status; @@ -1882,7 +1882,8 @@ static int myrs_slave_alloc(struct scsi_device *sdev) return 0; } -static int myrs_slave_configure(struct scsi_device *sdev) +static int myrs_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct myrs_hba *cs = shost_priv(sdev->host); struct myrs_ldev_info *ldev_info; @@ -1910,7 +1911,7 @@ static int myrs_slave_configure(struct scsi_device *sdev) return 0; } -static void myrs_slave_destroy(struct scsi_device *sdev) +static void myrs_sdev_destroy(struct scsi_device *sdev) { kfree(sdev->hostdata); } @@ -1921,9 +1922,9 @@ static const struct scsi_host_template myrs_template = { .proc_name = "myrs", .queuecommand = myrs_queuecommand, .eh_host_reset_handler = myrs_host_reset, - .slave_alloc = myrs_slave_alloc, - .slave_configure = myrs_slave_configure, - .slave_destroy = myrs_slave_destroy, + .sdev_init = myrs_sdev_init, + .sdev_configure = myrs_sdev_configure, + .sdev_destroy = myrs_sdev_destroy, .cmd_size = sizeof(struct myrs_cmdblk), .shost_groups = myrs_shost_groups, .sdev_groups = myrs_sdev_groups, diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c index 35869b4f9329..14ac81ec0aa0 100644 --- a/drivers/scsi/ncr53c8xx.c +++ b/drivers/scsi/ncr53c8xx.c @@ -7786,7 +7786,7 @@ static void __init ncr_getclock (struct ncb *np, int mult) /*===================== LINUX ENTRY POINTS SECTION ==========================*/ -static int ncr53c8xx_slave_alloc(struct scsi_device *device) +static int ncr53c8xx_sdev_init(struct scsi_device *device) { struct Scsi_Host *host = device->host; struct ncb *np = ((struct host_data *) host->hostdata)->ncb; @@ -7796,7 +7796,8 @@ static int ncr53c8xx_slave_alloc(struct scsi_device *device) return 0; } -static int ncr53c8xx_slave_configure(struct scsi_device *device) +static int ncr53c8xx_sdev_configure(struct scsi_device *device, + struct queue_limits *lim) { struct Scsi_Host *host = device->host; struct ncb *np = ((struct host_data *) host->hostdata)->ncb; @@ -8093,8 +8094,8 @@ struct Scsi_Host * __init ncr_attach(struct scsi_host_template *tpnt, tpnt->shost_groups = ncr53c8xx_host_groups; tpnt->queuecommand = ncr53c8xx_queue_command; - tpnt->slave_configure = ncr53c8xx_slave_configure; - tpnt->slave_alloc = ncr53c8xx_slave_alloc; + tpnt->sdev_configure = ncr53c8xx_sdev_configure; + tpnt->sdev_init = ncr53c8xx_sdev_init; tpnt->eh_bus_reset_handler = ncr53c8xx_bus_reset; tpnt->can_queue = SCSI_NCR_CAN_QUEUE; tpnt->this_id = 7; diff --git a/drivers/scsi/nsp32.c b/drivers/scsi/nsp32.c index b7987019686e..abc4ce9eae74 100644 --- a/drivers/scsi/nsp32.c +++ b/drivers/scsi/nsp32.c @@ -66,7 +66,7 @@ static const char *nsp32_release_version = "1.2"; /**************************************************************************** * Supported hardware */ -static struct pci_device_id nsp32_pci_table[] = { +static const struct pci_device_id nsp32_pci_table[] = { { .vendor = PCI_VENDOR_ID_IODATA, .device = PCI_DEVICE_ID_NINJASCSI_32BI_CBSC_II, diff --git a/drivers/scsi/pm8001/pm8001_defs.h b/drivers/scsi/pm8001/pm8001_defs.h index 7871e29a820a..4e19d61dffbb 100644 --- a/drivers/scsi/pm8001/pm8001_defs.h +++ b/drivers/scsi/pm8001/pm8001_defs.h @@ -90,7 +90,7 @@ enum port_type { #define PM8001_MAX_PORTS 16 /* max. possible ports */ #define PM8001_MAX_DEVICES 2048 /* max supported device */ #define PM8001_MAX_MSIX_VEC 64 /* max msi-x int for spcv/ve */ -#define PM8001_RESERVE_SLOT 8 +#define PM8001_RESERVE_SLOT 128 #define PM8001_SECTOR_SIZE 512 #define PM8001_PAGE_SIZE_4K 4096 diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index dec1e2d380f1..42a4eeac24c9 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -3472,12 +3472,13 @@ int pm8001_mpi_task_abort_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) status, tag, scp); switch (status) { case IO_SUCCESS: - pm8001_dbg(pm8001_ha, EH, "IO_SUCCESS\n"); + pm8001_dbg(pm8001_ha, FAIL, "ABORT IO_SUCCESS for tag %#x\n", + tag); ts->resp = SAS_TASK_COMPLETE; ts->stat = SAS_SAM_STAT_GOOD; break; case IO_NOT_VALID: - pm8001_dbg(pm8001_ha, EH, "IO_NOT_VALID\n"); + pm8001_dbg(pm8001_ha, FAIL, "IO_NOT_VALID for tag %#x\n", tag); ts->resp = TMF_RESP_FUNC_FAILED; break; } diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index f8c81e53e93f..599410bcdfea 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -105,7 +105,7 @@ static void pm8001_map_queues(struct Scsi_Host *shost) struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; if (pm8001_ha->number_of_intr > 1) { - blk_mq_pci_map_queues(qmap, pm8001_ha->pdev, 1); + blk_mq_map_hw_queues(qmap, &pm8001_ha->pdev->dev, 1); return; } @@ -736,7 +736,7 @@ static int pm8001_init_sas_add(struct pm8001_hba_info *pm8001_ha) return -EIO; } time_remaining = wait_for_completion_timeout(&completion, - msecs_to_jiffies(60*1000)); // 1 min + secs_to_jiffies(60)); // 1 min if (!time_remaining) { kfree(payload.func_specific); pm8001_dbg(pm8001_ha, FAIL, "get_nvmd_req timeout\n"); @@ -1435,7 +1435,7 @@ err_out_disable: /* update of pci device, vendor id and driver data with * unique value for each of the controller */ -static struct pci_device_id pm8001_pci_table[] = { +static const struct pci_device_id pm8001_pci_table[] = { { PCI_VDEVICE(PMC_Sierra, 0x8001), chip_8001 }, { PCI_VDEVICE(PMC_Sierra, 0x8006), chip_8006 }, { PCI_VDEVICE(ADAPTEC2, 0x8006), chip_8006 }, diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index d80cffd25a6e..183ce00aa671 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -101,6 +101,63 @@ int pm8001_tag_alloc(struct pm8001_hba_info *pm8001_ha, u32 *tag_out) return 0; } +static void pm80xx_get_tag_opcodes(struct sas_task *task, int *ata_op, + int *ata_tag, bool *task_aborted) +{ + unsigned long flags; + struct ata_queued_cmd *qc = NULL; + + *ata_op = 0; + *ata_tag = -1; + *task_aborted = false; + + if (!task) + return; + + spin_lock_irqsave(&task->task_state_lock, flags); + if (unlikely((task->task_state_flags & SAS_TASK_STATE_ABORTED))) + *task_aborted = true; + spin_unlock_irqrestore(&task->task_state_lock, flags); + + if (task->task_proto == SAS_PROTOCOL_STP) { + // sas_ata_qc_issue path uses SAS_PROTOCOL_STP. + // This only works for scsi + libsas + libata users. + qc = task->uldd_task; + if (qc) { + *ata_op = qc->tf.command; + *ata_tag = qc->tag; + } + } +} + +void pm80xx_show_pending_commands(struct pm8001_hba_info *pm8001_ha, + struct pm8001_device *target_pm8001_dev) +{ + int i = 0, ata_op = 0, ata_tag = -1; + struct pm8001_ccb_info *ccb = NULL; + struct sas_task *task = NULL; + struct pm8001_device *pm8001_dev = NULL; + bool task_aborted; + + for (i = 0; i < pm8001_ha->ccb_count; i++) { + ccb = &pm8001_ha->ccb_info[i]; + if (ccb->ccb_tag == PM8001_INVALID_TAG) + continue; + pm8001_dev = ccb->device; + if (target_pm8001_dev && pm8001_dev && + target_pm8001_dev != pm8001_dev) + continue; + task = ccb->task; + pm80xx_get_tag_opcodes(task, &ata_op, &ata_tag, &task_aborted); + pm8001_dbg(pm8001_ha, FAIL, + "tag %#x, device %#x task %p task aborted %d ata opcode %#x ata tag %d\n", + ccb->ccb_tag, + (pm8001_dev ? pm8001_dev->device_id : 0), + task, task_aborted, + ata_op, ata_tag); + } +} + /** * pm8001_mem_alloc - allocate memory for pm8001. * @pdev: pci device. @@ -374,23 +431,6 @@ static int pm8001_task_prep_ssp(struct pm8001_hba_info *pm8001_ha, return PM8001_CHIP_DISP->ssp_io_req(pm8001_ha, ccb); } - /* Find the local port id that's attached to this device */ -static int sas_find_local_port_id(struct domain_device *dev) -{ - struct domain_device *pdev = dev->parent; - - /* Directly attached device */ - if (!pdev) - return dev->port->id; - while (pdev) { - struct domain_device *pdev_p = pdev->parent; - if (!pdev_p) - return pdev->port->id; - pdev = pdev->parent; - } - return 0; -} - #define DEV_IS_GONE(pm8001_dev) \ ((!pm8001_dev || (pm8001_dev->dev_type == SAS_PHY_UNUSED))) @@ -463,10 +503,10 @@ int pm8001_queue_command(struct sas_task *task, gfp_t gfp_flags) spin_lock_irqsave(&pm8001_ha->lock, flags); pm8001_dev = dev->lldd_dev; - port = &pm8001_ha->port[sas_find_local_port_id(dev)]; + port = pm8001_ha->phy[pm8001_dev->attached_phy].port; if (!internal_abort && - (DEV_IS_GONE(pm8001_dev) || !port->port_attached)) { + (DEV_IS_GONE(pm8001_dev) || !port || !port->port_attached)) { ts->resp = SAS_TASK_UNDELIVERED; ts->stat = SAS_PHY_DOWN; if (sas_protocol_ata(task_proto)) { diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h index 42c7b3f7afbf..315f6a7523f0 100644 --- a/drivers/scsi/pm8001/pm8001_sas.h +++ b/drivers/scsi/pm8001/pm8001_sas.h @@ -56,7 +56,6 @@ #include #include #include -#include #include "pm8001_defs.h" #define DRV_NAME "pm80xx" @@ -787,6 +786,8 @@ static inline void pm8001_ccb_task_free_done(struct pm8001_hba_info *pm8001_ha, } void pm8001_setds_completion(struct domain_device *dev); void pm8001_tmf_aborted(struct sas_task *task); +void pm80xx_show_pending_commands(struct pm8001_hba_info *pm8001_ha, + struct pm8001_device *dev); #endif diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index e65951dd2024..5b373c53c036 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -2246,7 +2246,7 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, u32 param; u32 status; u32 tag; - int i, j; + int i, j, ata_tag = -1; u8 sata_addr_low[4]; u32 temp_sata_addr_low, temp_sata_addr_hi; u8 sata_addr_hi[4]; @@ -2256,6 +2256,7 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, u32 *sata_resp; struct pm8001_device *pm8001_dev; unsigned long flags; + struct ata_queued_cmd *qc; psataPayload = (struct sata_completion_resp *)(piomb + 4); status = le32_to_cpu(psataPayload->status); @@ -2267,8 +2268,11 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, pm8001_dev = ccb->device; if (t) { - if (t->dev && (t->dev->lldd_dev)) + if (t->dev && (t->dev->lldd_dev)) { pm8001_dev = t->dev->lldd_dev; + qc = t->uldd_task; + ata_tag = qc ? qc->tag : -1; + } } else { pm8001_dbg(pm8001_ha, FAIL, "task null, freeing CCB tag %d\n", ccb->ccb_tag); @@ -2276,16 +2280,14 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, return; } - if (pm8001_dev && unlikely(!t->lldd_task || !t->dev)) return; ts = &t->task_status; - if (status != IO_SUCCESS) { pm8001_dbg(pm8001_ha, FAIL, - "IO failed device_id %u status 0x%x tag %d\n", - pm8001_dev->device_id, status, tag); + "IO failed status %#x pm80xx tag %#x ata tag %d\n", + status, tag, ata_tag); } /* Print sas address of IO failed device */ @@ -2667,13 +2669,19 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, /* Check if this is NCQ error */ if (event == IO_XFER_ERROR_ABORTED_NCQ_MODE) { + /* tag value is invalid with this event */ + pm8001_dbg(pm8001_ha, FAIL, "NCQ ERROR for device %#x tag %#x\n", + dev_id, tag); + /* find device using device id */ pm8001_dev = pm8001_find_dev(pm8001_ha, dev_id); /* send read log extension by aborting the link - libata does what we want */ - if (pm8001_dev) + if (pm8001_dev) { + pm80xx_show_pending_commands(pm8001_ha, pm8001_dev); pm8001_handle_event(pm8001_ha, pm8001_dev, IO_XFER_ERROR_ABORTED_NCQ_MODE); + } return; } @@ -3336,10 +3344,11 @@ static int mpi_phy_start_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) u32 phy_id = le32_to_cpu(pPayload->phyid) & 0xFF; struct pm8001_phy *phy = &pm8001_ha->phy[phy_id]; + u32 tag = le32_to_cpu(pPayload->tag); pm8001_dbg(pm8001_ha, INIT, - "phy start resp status:0x%x, phyid:0x%x\n", - status, phy_id); + "phy start resp status:0x%x, phyid:0x%x, tag 0x%x\n", + status, phy_id, tag); if (status == 0) phy->phy_state = PHY_LINK_DOWN; @@ -3348,6 +3357,8 @@ static int mpi_phy_start_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) complete(phy->enable_completion); phy->enable_completion = NULL; } + + pm8001_tag_free(pm8001_ha, tag); return 0; } @@ -3628,8 +3639,10 @@ static int mpi_phy_stop_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) u32 phyid = le32_to_cpu(pPayload->phyid) & 0xFF; struct pm8001_phy *phy = &pm8001_ha->phy[phyid]; - pm8001_dbg(pm8001_ha, MSG, "phy:0x%x status:0x%x\n", - phyid, status); + u32 tag = le32_to_cpu(pPayload->tag); + + pm8001_dbg(pm8001_ha, MSG, "phy:0x%x status:0x%x tag 0x%x\n", phyid, + status, tag); if (status == PHY_STOP_SUCCESS || status == PHY_STOP_ERR_DEVICE_ATTACHED) { phy->phy_state = PHY_LINK_DISABLE; @@ -3637,6 +3650,7 @@ static int mpi_phy_stop_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) phy->sas_phy.linkrate = SAS_PHY_DISABLED; } + pm8001_tag_free(pm8001_ha, tag); return 0; } @@ -3655,10 +3669,9 @@ static int mpi_set_controller_config_resp(struct pm8001_hba_info *pm8001_ha, u32 tag = le32_to_cpu(pPayload->tag); pm8001_dbg(pm8001_ha, MSG, - "SET CONTROLLER RESP: status 0x%x qlfr_pgcd 0x%x\n", - status, err_qlfr_pgcd); + "SET CONTROLLER RESP: status 0x%x qlfr_pgcd 0x%x tag 0x%x\n", + status, err_qlfr_pgcd, tag); pm8001_tag_free(pm8001_ha, tag); - return 0; } @@ -4632,9 +4645,16 @@ static int pm80xx_chip_phy_start_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id) { struct phy_start_req payload; - u32 tag = 0x01; + int ret; + u32 tag; u32 opcode = OPC_INB_PHYSTART; + ret = pm8001_tag_alloc(pm8001_ha, &tag); + if (ret) { + pm8001_dbg(pm8001_ha, FAIL, "Tag allocation failed\n"); + return ret; + } + memset(&payload, 0, sizeof(payload)); payload.tag = cpu_to_le32(tag); @@ -4670,9 +4690,16 @@ static int pm80xx_chip_phy_stop_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id) { struct phy_stop_req payload; - u32 tag = 0x01; + int ret; + u32 tag; u32 opcode = OPC_INB_PHYSTOP; + ret = pm8001_tag_alloc(pm8001_ha, &tag); + if (ret) { + pm8001_dbg(pm8001_ha, FAIL, "Tag allocation failed\n"); + return ret; + } + memset(&payload, 0, sizeof(payload)); payload.tag = cpu_to_le32(tag); payload.phy_id = cpu_to_le32(phy_id); diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 4c5881917d76..3ba53916fd86 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -113,7 +113,7 @@ static struct pmcraid_chip_details pmcraid_chip_cfg[] = { /* * PCI device ids supported by pmcraid driver */ -static struct pci_device_id pmcraid_pci_table[] = { +static const struct pci_device_id pmcraid_pci_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_PMC, PCI_DEVICE_ID_PMC_MAXRAID), 0, 0, (kernel_ulong_t)&pmcraid_chip_cfg[0] }, @@ -125,7 +125,7 @@ MODULE_DEVICE_TABLE(pci, pmcraid_pci_table); /** - * pmcraid_slave_alloc - Prepare for commands to a device + * pmcraid_sdev_init - Prepare for commands to a device * @scsi_dev: scsi device struct * * This function is called by mid-layer prior to sending any command to the new @@ -136,7 +136,7 @@ MODULE_DEVICE_TABLE(pci, pmcraid_pci_table); * Return value: * 0 on success / -ENXIO if device does not exist */ -static int pmcraid_slave_alloc(struct scsi_device *scsi_dev) +static int pmcraid_sdev_init(struct scsi_device *scsi_dev) { struct pmcraid_resource_entry *temp, *res = NULL; struct pmcraid_instance *pinstance; @@ -197,7 +197,7 @@ static int pmcraid_slave_alloc(struct scsi_device *scsi_dev) } /** - * pmcraid_device_configure - Configures a SCSI device + * pmcraid_sdev_configure - Configures a SCSI device * @scsi_dev: scsi device struct * @lim: queue limits * @@ -210,8 +210,8 @@ static int pmcraid_slave_alloc(struct scsi_device *scsi_dev) * Return value: * 0 on success */ -static int pmcraid_device_configure(struct scsi_device *scsi_dev, - struct queue_limits *lim) +static int pmcraid_sdev_configure(struct scsi_device *scsi_dev, + struct queue_limits *lim) { struct pmcraid_resource_entry *res = scsi_dev->hostdata; @@ -248,17 +248,17 @@ static int pmcraid_device_configure(struct scsi_device *scsi_dev, } /** - * pmcraid_slave_destroy - Unconfigure a SCSI device before removing it + * pmcraid_sdev_destroy - Unconfigure a SCSI device before removing it * * @scsi_dev: scsi device struct * * This is called by mid-layer before removing a device. Pointer assignments - * done in pmcraid_slave_alloc will be reset to NULL here. + * done in pmcraid_sdev_init will be reset to NULL here. * * Return value * none */ -static void pmcraid_slave_destroy(struct scsi_device *scsi_dev) +static void pmcraid_sdev_destroy(struct scsi_device *scsi_dev) { struct pmcraid_resource_entry *res; @@ -3668,9 +3668,9 @@ static const struct scsi_host_template pmcraid_host_template = { .eh_device_reset_handler = pmcraid_eh_device_reset_handler, .eh_host_reset_handler = pmcraid_eh_host_reset_handler, - .slave_alloc = pmcraid_slave_alloc, - .device_configure = pmcraid_device_configure, - .slave_destroy = pmcraid_slave_destroy, + .sdev_init = pmcraid_sdev_init, + .sdev_configure = pmcraid_sdev_configure, + .sdev_destroy = pmcraid_sdev_destroy, .change_queue_depth = pmcraid_change_queue_depth, .can_queue = PMCRAID_MAX_IO_CMD, .this_id = -1, diff --git a/drivers/scsi/ps3rom.c b/drivers/scsi/ps3rom.c index 90495a832f34..92fe5c5c5bb0 100644 --- a/drivers/scsi/ps3rom.c +++ b/drivers/scsi/ps3rom.c @@ -61,7 +61,8 @@ enum lv1_atapi_in_out { }; -static int ps3rom_slave_configure(struct scsi_device *scsi_dev) +static int ps3rom_sdev_configure(struct scsi_device *scsi_dev, + struct queue_limits *lim) { struct ps3rom_private *priv = shost_priv(scsi_dev->host); struct ps3_storage_device *dev = priv->dev; @@ -325,7 +326,7 @@ done: static const struct scsi_host_template ps3rom_host_template = { .name = DEVICE_NAME, - .slave_configure = ps3rom_slave_configure, + .sdev_configure = ps3rom_sdev_configure, .queuecommand = ps3rom_queuecommand, .can_queue = 1, .this_id = 7, diff --git a/drivers/scsi/qedf/qedf_attr.c b/drivers/scsi/qedf/qedf_attr.c index 8d8c760eee43..769da92ee20d 100644 --- a/drivers/scsi/qedf/qedf_attr.c +++ b/drivers/scsi/qedf/qedf_attr.c @@ -104,7 +104,7 @@ void qedf_capture_grc_dump(struct qedf_ctx *qedf) static ssize_t qedf_sysfs_read_grcdump(struct file *filep, struct kobject *kobj, - struct bin_attribute *ba, char *buf, loff_t off, + const struct bin_attribute *ba, char *buf, loff_t off, size_t count) { ssize_t ret = 0; @@ -124,7 +124,7 @@ qedf_sysfs_read_grcdump(struct file *filep, struct kobject *kobj, static ssize_t qedf_sysfs_write_grcdump(struct file *filep, struct kobject *kobj, - struct bin_attribute *ba, char *buf, loff_t off, + const struct bin_attribute *ba, char *buf, loff_t off, size_t count) { struct fc_lport *lport = NULL; @@ -160,14 +160,14 @@ qedf_sysfs_write_grcdump(struct file *filep, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_grcdump_attr = { +static const struct bin_attribute sysfs_grcdump_attr = { .attr = { .name = "grcdump", .mode = S_IRUSR | S_IWUSR, }, .size = 0, - .read = qedf_sysfs_read_grcdump, - .write = qedf_sysfs_write_grcdump, + .read_new = qedf_sysfs_read_grcdump, + .write_new = qedf_sysfs_write_grcdump, }; static struct sysfs_bin_attrs bin_file_entries[] = { diff --git a/drivers/scsi/qedf/qedf_dbg.h b/drivers/scsi/qedf/qedf_dbg.h index 5ec2b817c694..eeb6c841dacb 100644 --- a/drivers/scsi/qedf/qedf_dbg.h +++ b/drivers/scsi/qedf/qedf_dbg.h @@ -100,7 +100,7 @@ struct Scsi_Host; struct sysfs_bin_attrs { char *name; - struct bin_attribute *attr; + const struct bin_attribute *attr; }; extern int qedf_alloc_grc_dump_buf(uint8_t **buf, uint32_t len); diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index d2f47dc31dbf..436bd29d5eba 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -982,7 +982,8 @@ static int qedf_eh_host_reset(struct scsi_cmnd *sc_cmd) return SUCCESS; } -static int qedf_slave_configure(struct scsi_device *sdev) +static int qedf_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { if (qedf_queue_depth) { scsi_change_queue_depth(sdev, qedf_queue_depth); @@ -1003,7 +1004,7 @@ static const struct scsi_host_template qedf_host_template = { .eh_device_reset_handler = qedf_eh_device_reset, /* lun reset */ .eh_target_reset_handler = qedf_eh_target_reset, /* target reset */ .eh_host_reset_handler = qedf_eh_host_reset, - .slave_configure = qedf_slave_configure, + .sdev_configure = qedf_sdev_configure, .dma_boundary = QED_HW_DMA_BOUNDARY, .sg_tablesize = QEDF_MAX_BDS_PER_CMD, .can_queue = FCOE_PARAMS_NUM_TASKS, diff --git a/drivers/scsi/qedi/qedi_dbg.h b/drivers/scsi/qedi/qedi_dbg.h index fdda12ef13b0..5a1ec4542183 100644 --- a/drivers/scsi/qedi/qedi_dbg.h +++ b/drivers/scsi/qedi/qedi_dbg.h @@ -91,7 +91,7 @@ struct Scsi_Host; struct sysfs_bin_attrs { char *name; - struct bin_attribute *attr; + const struct bin_attribute *attr; }; int qedi_create_sysfs_attr(struct Scsi_Host *shost, diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 628d59dda20c..c9539897048a 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1961,13 +1961,11 @@ static int qedi_cpu_online(unsigned int cpu) struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu); struct task_struct *thread; - thread = kthread_create_on_node(qedi_percpu_io_thread, (void *)p, - cpu_to_node(cpu), - "qedi_thread/%d", cpu); + thread = kthread_create_on_cpu(qedi_percpu_io_thread, (void *)p, + cpu, "qedi_thread/%d"); if (IS_ERR(thread)) return PTR_ERR(thread); - kthread_bind(thread, cpu); p->iothread = thread; wake_up_process(thread); return 0; @@ -2869,7 +2867,7 @@ static void qedi_remove(struct pci_dev *pdev) __qedi_remove(pdev, QEDI_MODE_NORMAL); } -static struct pci_device_id qedi_pci_tbl[] = { +static const struct pci_device_id qedi_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x165E) }, { PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x8084) }, { 0 }, diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c index 8958547ac111..1fd2da0264e3 100644 --- a/drivers/scsi/qla1280.c +++ b/drivers/scsi/qla1280.c @@ -501,7 +501,7 @@ struct qla_boards { }; /* NOTE: the last argument in each entry is used to index ql1280_board_tbl */ -static struct pci_device_id qla1280_pci_tbl[] = { +static const struct pci_device_id qla1280_pci_tbl[] = { {PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP12160, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP1020, @@ -1159,7 +1159,7 @@ qla1280_set_target_parameters(struct scsi_qla_host *ha, int bus, int target) /************************************************************************** - * qla1280_slave_configure + * qla1280_sdev_configure * * Description: * Determines the queue depth for a given device. There are two ways @@ -1170,7 +1170,7 @@ qla1280_set_target_parameters(struct scsi_qla_host *ha, int bus, int target) * default queue depth (dependent on the number of hardware SCBs). **************************************************************************/ static int -qla1280_slave_configure(struct scsi_device *device) +qla1280_sdev_configure(struct scsi_device *device, struct queue_limits *lim) { struct scsi_qla_host *ha; int default_depth = 3; @@ -4121,7 +4121,7 @@ static const struct scsi_host_template qla1280_driver_template = { .proc_name = "qla1280", .name = "Qlogic ISP 1280/12160", .info = qla1280_info, - .slave_configure = qla1280_slave_configure, + .sdev_configure = qla1280_sdev_configure, .queuecommand = qla1280_queuecommand, .eh_abort_handler = qla1280_eh_abort, .eh_device_reset_handler= qla1280_eh_device_reset, diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index e6ece30c4348..dcb0c2af1fa7 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -17,7 +17,7 @@ static int qla24xx_vport_disable(struct fc_vport *, bool); static ssize_t qla2x00_sysfs_read_fw_dump(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -58,7 +58,7 @@ qla2x00_sysfs_read_fw_dump(struct file *filp, struct kobject *kobj, static ssize_t qla2x00_sysfs_write_fw_dump(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -168,19 +168,19 @@ qla2x00_sysfs_write_fw_dump(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_fw_dump_attr = { +static const struct bin_attribute sysfs_fw_dump_attr = { .attr = { .name = "fw_dump", .mode = S_IRUSR | S_IWUSR, }, .size = 0, - .read = qla2x00_sysfs_read_fw_dump, - .write = qla2x00_sysfs_write_fw_dump, + .read_new = qla2x00_sysfs_read_fw_dump, + .write_new = qla2x00_sysfs_write_fw_dump, }; static ssize_t qla2x00_sysfs_read_nvram(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -220,7 +220,7 @@ skip: static ssize_t qla2x00_sysfs_write_nvram(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -282,19 +282,19 @@ qla2x00_sysfs_write_nvram(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_nvram_attr = { +static const struct bin_attribute sysfs_nvram_attr = { .attr = { .name = "nvram", .mode = S_IRUSR | S_IWUSR, }, .size = 512, - .read = qla2x00_sysfs_read_nvram, - .write = qla2x00_sysfs_write_nvram, + .read_new = qla2x00_sysfs_read_nvram, + .write_new = qla2x00_sysfs_write_nvram, }; static ssize_t qla2x00_sysfs_read_optrom(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -318,7 +318,7 @@ out: static ssize_t qla2x00_sysfs_write_optrom(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -344,19 +344,19 @@ qla2x00_sysfs_write_optrom(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_optrom_attr = { +static const struct bin_attribute sysfs_optrom_attr = { .attr = { .name = "optrom", .mode = S_IRUSR | S_IWUSR, }, .size = 0, - .read = qla2x00_sysfs_read_optrom, - .write = qla2x00_sysfs_write_optrom, + .read_new = qla2x00_sysfs_read_optrom, + .write_new = qla2x00_sysfs_write_optrom, }; static ssize_t qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -529,18 +529,18 @@ out: return rval; } -static struct bin_attribute sysfs_optrom_ctl_attr = { +static const struct bin_attribute sysfs_optrom_ctl_attr = { .attr = { .name = "optrom_ctl", .mode = S_IWUSR, }, .size = 0, - .write = qla2x00_sysfs_write_optrom_ctl, + .write_new = qla2x00_sysfs_write_optrom_ctl, }; static ssize_t qla2x00_sysfs_read_vpd(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -587,7 +587,7 @@ skip: static ssize_t qla2x00_sysfs_write_vpd(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -642,19 +642,19 @@ qla2x00_sysfs_write_vpd(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_vpd_attr = { +static const struct bin_attribute sysfs_vpd_attr = { .attr = { .name = "vpd", .mode = S_IRUSR | S_IWUSR, }, .size = 0, - .read = qla2x00_sysfs_read_vpd, - .write = qla2x00_sysfs_write_vpd, + .read_new = qla2x00_sysfs_read_vpd, + .write_new = qla2x00_sysfs_write_vpd, }; static ssize_t qla2x00_sysfs_read_sfp(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -679,18 +679,18 @@ qla2x00_sysfs_read_sfp(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_sfp_attr = { +static const struct bin_attribute sysfs_sfp_attr = { .attr = { .name = "sfp", .mode = S_IRUSR | S_IWUSR, }, .size = SFP_DEV_SIZE, - .read = qla2x00_sysfs_read_sfp, + .read_new = qla2x00_sysfs_read_sfp, }; static ssize_t qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -823,19 +823,19 @@ qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_reset_attr = { +static const struct bin_attribute sysfs_reset_attr = { .attr = { .name = "reset", .mode = S_IWUSR, }, .size = 0, - .write = qla2x00_sysfs_write_reset, + .write_new = qla2x00_sysfs_write_reset, }; static ssize_t qla2x00_issue_logo(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, - char *buf, loff_t off, size_t count) + const struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, struct device, kobj))); @@ -866,18 +866,18 @@ qla2x00_issue_logo(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_issue_logo_attr = { +static const struct bin_attribute sysfs_issue_logo_attr = { .attr = { .name = "issue_logo", .mode = S_IWUSR, }, .size = 0, - .write = qla2x00_issue_logo, + .write_new = qla2x00_issue_logo, }; static ssize_t qla2x00_sysfs_read_xgmac_stats(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -929,18 +929,18 @@ do_read: return count; } -static struct bin_attribute sysfs_xgmac_stats_attr = { +static const struct bin_attribute sysfs_xgmac_stats_attr = { .attr = { .name = "xgmac_stats", .mode = S_IRUSR, }, .size = 0, - .read = qla2x00_sysfs_read_xgmac_stats, + .read_new = qla2x00_sysfs_read_xgmac_stats, }; static ssize_t qla2x00_sysfs_read_dcbx_tlv(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj, @@ -987,18 +987,18 @@ do_read: return count; } -static struct bin_attribute sysfs_dcbx_tlv_attr = { +static const struct bin_attribute sysfs_dcbx_tlv_attr = { .attr = { .name = "dcbx_tlv", .mode = S_IRUSR, }, .size = 0, - .read = qla2x00_sysfs_read_dcbx_tlv, + .read_new = qla2x00_sysfs_read_dcbx_tlv, }; static struct sysfs_entry { char *name; - struct bin_attribute *attr; + const struct bin_attribute *attr; int type; } bin_file_entries[] = { { "fw_dump", &sysfs_fw_dump_attr, }, diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 15066c112817..cb95b7b12051 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -4098,6 +4098,8 @@ struct qla_hw_data { uint32_t npiv_supported :1; uint32_t pci_channel_io_perm_failure :1; uint32_t fce_enabled :1; + uint32_t user_enabled_fce :1; + uint32_t fce_dump_buf_alloced :1; uint32_t fac_supported :1; uint32_t chip_reset_done :1; diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c index a1545dad0c0c..08273520c777 100644 --- a/drivers/scsi/qla2xxx/qla_dfs.c +++ b/drivers/scsi/qla2xxx/qla_dfs.c @@ -409,27 +409,32 @@ qla2x00_dfs_fce_show(struct seq_file *s, void *unused) mutex_lock(&ha->fce_mutex); - seq_puts(s, "FCE Trace Buffer\n"); - seq_printf(s, "In Pointer = %llx\n\n", (unsigned long long)ha->fce_wr); - seq_printf(s, "Base = %llx\n\n", (unsigned long long) ha->fce_dma); - seq_puts(s, "FCE Enable Registers\n"); - seq_printf(s, "%08x %08x %08x %08x %08x %08x\n", - ha->fce_mb[0], ha->fce_mb[2], ha->fce_mb[3], ha->fce_mb[4], - ha->fce_mb[5], ha->fce_mb[6]); + if (ha->flags.user_enabled_fce) { + seq_puts(s, "FCE Trace Buffer\n"); + seq_printf(s, "In Pointer = %llx\n\n", (unsigned long long)ha->fce_wr); + seq_printf(s, "Base = %llx\n\n", (unsigned long long)ha->fce_dma); + seq_puts(s, "FCE Enable Registers\n"); + seq_printf(s, "%08x %08x %08x %08x %08x %08x\n", + ha->fce_mb[0], ha->fce_mb[2], ha->fce_mb[3], ha->fce_mb[4], + ha->fce_mb[5], ha->fce_mb[6]); - fce = (uint32_t *) ha->fce; - fce_start = (unsigned long long) ha->fce_dma; - for (cnt = 0; cnt < fce_calc_size(ha->fce_bufs) / 4; cnt++) { - if (cnt % 8 == 0) - seq_printf(s, "\n%llx: ", - (unsigned long long)((cnt * 4) + fce_start)); - else - seq_putc(s, ' '); - seq_printf(s, "%08x", *fce++); + fce = (uint32_t *)ha->fce; + fce_start = (unsigned long long)ha->fce_dma; + for (cnt = 0; cnt < fce_calc_size(ha->fce_bufs) / 4; cnt++) { + if (cnt % 8 == 0) + seq_printf(s, "\n%llx: ", + (unsigned long long)((cnt * 4) + fce_start)); + else + seq_putc(s, ' '); + seq_printf(s, "%08x", *fce++); + } + + seq_puts(s, "\nEnd\n"); + } else { + seq_puts(s, "FCE Trace is currently not enabled\n"); + seq_puts(s, "\techo [ 1 | 0 ] > fce\n"); } - seq_puts(s, "\nEnd\n"); - mutex_unlock(&ha->fce_mutex); return 0; @@ -467,7 +472,7 @@ qla2x00_dfs_fce_release(struct inode *inode, struct file *file) struct qla_hw_data *ha = vha->hw; int rval; - if (ha->flags.fce_enabled) + if (ha->flags.fce_enabled || !ha->fce) goto out; mutex_lock(&ha->fce_mutex); @@ -488,11 +493,88 @@ out: return single_release(inode, file); } +static ssize_t +qla2x00_dfs_fce_write(struct file *file, const char __user *buffer, + size_t count, loff_t *pos) +{ + struct seq_file *s = file->private_data; + struct scsi_qla_host *vha = s->private; + struct qla_hw_data *ha = vha->hw; + char *buf; + int rc = 0; + unsigned long enable; + + if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) && + !IS_QLA27XX(ha) && !IS_QLA28XX(ha)) { + ql_dbg(ql_dbg_user, vha, 0xd034, + "this adapter does not support FCE."); + return -EINVAL; + } + + buf = memdup_user_nul(buffer, count); + if (IS_ERR(buf)) { + ql_dbg(ql_dbg_user, vha, 0xd037, + "fail to copy user buffer."); + return PTR_ERR(buf); + } + + enable = kstrtoul(buf, 0, 0); + rc = count; + + mutex_lock(&ha->fce_mutex); + + if (enable) { + if (ha->flags.user_enabled_fce) { + mutex_unlock(&ha->fce_mutex); + goto out_free; + } + ha->flags.user_enabled_fce = 1; + if (!ha->fce) { + rc = qla2x00_alloc_fce_trace(vha); + if (rc) { + ha->flags.user_enabled_fce = 0; + mutex_unlock(&ha->fce_mutex); + goto out_free; + } + + /* adjust fw dump buffer to take into account of this feature */ + if (!ha->flags.fce_dump_buf_alloced) + qla2x00_alloc_fw_dump(vha); + } + + if (!ha->flags.fce_enabled) + qla_enable_fce_trace(vha); + + ql_dbg(ql_dbg_user, vha, 0xd045, "User enabled FCE .\n"); + } else { + if (!ha->flags.user_enabled_fce) { + mutex_unlock(&ha->fce_mutex); + goto out_free; + } + ha->flags.user_enabled_fce = 0; + if (ha->flags.fce_enabled) { + qla2x00_disable_fce_trace(vha, NULL, NULL); + ha->flags.fce_enabled = 0; + } + + qla2x00_free_fce_trace(ha); + /* no need to re-adjust fw dump buffer */ + + ql_dbg(ql_dbg_user, vha, 0xd04f, "User disabled FCE .\n"); + } + + mutex_unlock(&ha->fce_mutex); +out_free: + kfree(buf); + return rc; +} + static const struct file_operations dfs_fce_ops = { .open = qla2x00_dfs_fce_open, .read = seq_read, .llseek = seq_lseek, .release = qla2x00_dfs_fce_release, + .write = qla2x00_dfs_fce_write, }; static int @@ -626,8 +708,6 @@ qla2x00_dfs_setup(scsi_qla_host_t *vha) if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) && !IS_QLA27XX(ha) && !IS_QLA28XX(ha)) goto out; - if (!ha->fce) - goto out; if (qla2x00_dfs_root) goto create_dir; diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index cededfda9d0e..e556f57c91af 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -11,6 +11,9 @@ /* * Global Function Prototypes in qla_init.c source file. */ +int qla2x00_alloc_fce_trace(scsi_qla_host_t *); +void qla2x00_free_fce_trace(struct qla_hw_data *ha); +void qla_enable_fce_trace(scsi_qla_host_t *); extern int qla2x00_initialize_adapter(scsi_qla_host_t *); extern int qla24xx_post_prli_work(struct scsi_qla_host *vha, fc_port_t *fcport); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 31fc6a0eca3e..79cdfec2bca3 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2681,7 +2681,7 @@ exit: return rval; } -static void qla_enable_fce_trace(scsi_qla_host_t *vha) +void qla_enable_fce_trace(scsi_qla_host_t *vha) { int rval; struct qla_hw_data *ha = vha->hw; @@ -3717,25 +3717,24 @@ qla24xx_chip_diag(scsi_qla_host_t *vha) return rval; } -static void -qla2x00_alloc_fce_trace(scsi_qla_host_t *vha) +int qla2x00_alloc_fce_trace(scsi_qla_host_t *vha) { dma_addr_t tc_dma; void *tc; struct qla_hw_data *ha = vha->hw; if (!IS_FWI2_CAPABLE(ha)) - return; + return -EINVAL; if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) && !IS_QLA27XX(ha) && !IS_QLA28XX(ha)) - return; + return -EINVAL; if (ha->fce) { ql_dbg(ql_dbg_init, vha, 0x00bd, "%s: FCE Mem is already allocated.\n", __func__); - return; + return -EIO; } /* Allocate memory for Fibre Channel Event Buffer. */ @@ -3745,7 +3744,7 @@ qla2x00_alloc_fce_trace(scsi_qla_host_t *vha) ql_log(ql_log_warn, vha, 0x00be, "Unable to allocate (%d KB) for FCE.\n", FCE_SIZE / 1024); - return; + return -ENOMEM; } ql_dbg(ql_dbg_init, vha, 0x00c0, @@ -3754,6 +3753,16 @@ qla2x00_alloc_fce_trace(scsi_qla_host_t *vha) ha->fce_dma = tc_dma; ha->fce = tc; ha->fce_bufs = FCE_NUM_BUFFERS; + return 0; +} + +void qla2x00_free_fce_trace(struct qla_hw_data *ha) +{ + if (!ha->fce) + return; + dma_free_coherent(&ha->pdev->dev, FCE_SIZE, ha->fce, ha->fce_dma); + ha->fce = NULL; + ha->fce_dma = 0; } static void @@ -3844,9 +3853,10 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) if (ha->tgt.atio_ring) mq_size += ha->tgt.atio_q_length * sizeof(request_t); - qla2x00_alloc_fce_trace(vha); - if (ha->fce) + if (ha->fce) { fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE; + ha->flags.fce_dump_buf_alloced = 1; + } qla2x00_alloc_eft_trace(vha); if (ha->eft) eft_size = EFT_SIZE; diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 8f4cc136a9c9..8ee2e337c9e1 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -8,7 +8,6 @@ #include #include #include -#include #include static struct nvme_fc_port_template qla_nvme_fc_transport; @@ -841,7 +840,7 @@ static void qla_nvme_map_queues(struct nvme_fc_local_port *lport, { struct scsi_qla_host *vha = lport->private; - blk_mq_pci_map_queues(map, vha->hw->pdev, vha->irq_offset); + blk_mq_map_hw_queues(map, &vha->hw->pdev->dev, vha->irq_offset); } static void qla_nvme_localport_delete(struct nvme_fc_local_port *lport) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 7ab717ed7232..6b9b8218b512 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include @@ -1934,7 +1933,7 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res) } static int -qla2xxx_slave_alloc(struct scsi_device *sdev) +qla2xxx_sdev_init(struct scsi_device *sdev) { struct fc_rport *rport = starget_to_rport(scsi_target(sdev)); @@ -1947,7 +1946,7 @@ qla2xxx_slave_alloc(struct scsi_device *sdev) } static int -qla2xxx_slave_configure(struct scsi_device *sdev) +qla2xxx_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { scsi_qla_host_t *vha = shost_priv(sdev->host); struct req_que *req = vha->req; @@ -1957,7 +1956,7 @@ qla2xxx_slave_configure(struct scsi_device *sdev) } static void -qla2xxx_slave_destroy(struct scsi_device *sdev) +qla2xxx_sdev_destroy(struct scsi_device *sdev) { sdev->hostdata = NULL; } @@ -8071,7 +8070,8 @@ static void qla2xxx_map_queues(struct Scsi_Host *shost) if (USER_CTRL_IRQ(vha->hw) || !vha->hw->mqiobase) blk_mq_map_queues(qmap); else - blk_mq_pci_map_queues(qmap, vha->hw->pdev, vha->irq_offset); + blk_mq_map_hw_queues(qmap, &vha->hw->pdev->dev, + vha->irq_offset); } struct scsi_host_template qla2xxx_driver_template = { @@ -8087,10 +8087,10 @@ struct scsi_host_template qla2xxx_driver_template = { .eh_bus_reset_handler = qla2xxx_eh_bus_reset, .eh_host_reset_handler = qla2xxx_eh_host_reset, - .slave_configure = qla2xxx_slave_configure, + .sdev_configure = qla2xxx_sdev_configure, - .slave_alloc = qla2xxx_slave_alloc, - .slave_destroy = qla2xxx_slave_destroy, + .sdev_init = qla2xxx_sdev_init, + .sdev_destroy = qla2xxx_sdev_destroy, .scan_finished = qla2xxx_scan_finished, .scan_start = qla2xxx_scan_start, .change_queue_depth = scsi_change_queue_depth, @@ -8116,7 +8116,7 @@ static const struct pci_error_handlers qla2xxx_err_handler = { .reset_done = qla_pci_reset_done, }; -static struct pci_device_id qla2xxx_pci_tbl[] = { +static const struct pci_device_id qla2xxx_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP2100) }, { PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP2200) }, { PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP2300) }, diff --git a/drivers/scsi/qla4xxx/ql4_attr.c b/drivers/scsi/qla4xxx/ql4_attr.c index abfa6ef60480..e3f85d6ea0db 100644 --- a/drivers/scsi/qla4xxx/ql4_attr.c +++ b/drivers/scsi/qla4xxx/ql4_attr.c @@ -10,7 +10,7 @@ static ssize_t qla4_8xxx_sysfs_read_fw_dump(struct file *filep, struct kobject *kobj, - struct bin_attribute *ba, char *buf, loff_t off, + const struct bin_attribute *ba, char *buf, loff_t off, size_t count) { struct scsi_qla_host *ha = to_qla_host(dev_to_shost(container_of(kobj, @@ -28,7 +28,7 @@ qla4_8xxx_sysfs_read_fw_dump(struct file *filep, struct kobject *kobj, static ssize_t qla4_8xxx_sysfs_write_fw_dump(struct file *filep, struct kobject *kobj, - struct bin_attribute *ba, char *buf, loff_t off, + const struct bin_attribute *ba, char *buf, loff_t off, size_t count) { struct scsi_qla_host *ha = to_qla_host(dev_to_shost(container_of(kobj, @@ -104,19 +104,19 @@ qla4_8xxx_sysfs_write_fw_dump(struct file *filep, struct kobject *kobj, return count; } -static struct bin_attribute sysfs_fw_dump_attr = { +static const struct bin_attribute sysfs_fw_dump_attr = { .attr = { .name = "fw_dump", .mode = S_IRUSR | S_IWUSR, }, .size = 0, - .read = qla4_8xxx_sysfs_read_fw_dump, - .write = qla4_8xxx_sysfs_write_fw_dump, + .read_new = qla4_8xxx_sysfs_read_fw_dump, + .write_new = qla4_8xxx_sysfs_write_fw_dump, }; static struct sysfs_entry { char *name; - struct bin_attribute *attr; + const struct bin_attribute *attr; } bin_file_entries[] = { { "fw_dump", &sysfs_fw_dump_attr }, { NULL }, diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index d91f54a6e752..6b0e6b4cd8af 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -160,7 +160,7 @@ static int qla4xxx_eh_abort(struct scsi_cmnd *cmd); static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd); static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd); static int qla4xxx_eh_host_reset(struct scsi_cmnd *cmd); -static int qla4xxx_slave_alloc(struct scsi_device *device); +static int qla4xxx_sdev_init(struct scsi_device *device); static umode_t qla4_attr_is_visible(int param_type, int param); static int qla4xxx_host_reset(struct Scsi_Host *shost, int reset_type); @@ -234,7 +234,7 @@ static struct scsi_host_template qla4xxx_driver_template = { .eh_host_reset_handler = qla4xxx_eh_host_reset, .eh_timed_out = qla4xxx_eh_cmd_timed_out, - .slave_alloc = qla4xxx_slave_alloc, + .sdev_init = qla4xxx_sdev_init, .change_queue_depth = scsi_change_queue_depth, .this_id = -1, @@ -7189,7 +7189,8 @@ exit_new_nt_list: * 1: if flashnode entry is non-persistent * 0: if flashnode entry is persistent **/ -static int qla4xxx_sysfs_ddb_is_non_persistent(struct device *dev, void *data) +static int qla4xxx_sysfs_ddb_is_non_persistent(struct device *dev, + const void *data) { struct iscsi_bus_flash_session *fnode_sess; @@ -9052,7 +9053,7 @@ static void qla4xxx_config_dma_addressing(struct scsi_qla_host *ha) } } -static int qla4xxx_slave_alloc(struct scsi_device *sdev) +static int qla4xxx_sdev_init(struct scsi_device *sdev) { struct iscsi_cls_session *cls_sess; struct iscsi_session *sess; @@ -9846,7 +9847,7 @@ static const struct pci_error_handlers qla4xxx_err_handler = { .resume = qla4xxx_pci_resume, }; -static struct pci_device_id qla4xxx_pci_tbl[] = { +static const struct pci_device_id qla4xxx_pci_tbl[] = { { .vendor = PCI_VENDOR_ID_QLOGIC, .device = PCI_DEVICE_ID_QLOGIC_ISP4010, diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c index 74866b9f2b14..c9984ef57f26 100644 --- a/drivers/scsi/qlogicpti.c +++ b/drivers/scsi/qlogicpti.c @@ -975,7 +975,8 @@ static inline void update_can_queue(struct Scsi_Host *host, u_int in_ptr, u_int host->sg_tablesize = QLOGICPTI_MAX_SG(num_free); } -static int qlogicpti_slave_configure(struct scsi_device *sdev) +static int qlogicpti_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct qlogicpti *qpti = shost_priv(sdev->host); int tgt = sdev->id; @@ -1292,7 +1293,7 @@ static const struct scsi_host_template qpti_template = { .name = "qlogicpti", .info = qlogicpti_info, .queuecommand = qlogicpti_queuecommand, - .slave_configure = qlogicpti_slave_configure, + .sdev_configure = qlogicpti_sdev_configure, .eh_abort_handler = qlogicpti_abort, .eh_host_reset_handler = qlogicpti_reset, .can_queue = QLOGICPTI_REQ_QUEUE_LEN, diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 680ba180a672..5ceaa4665e5d 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -5879,23 +5879,24 @@ static struct sdebug_dev_info *find_build_dev_info(struct scsi_device *sdev) return open_devip; } -static int scsi_debug_slave_alloc(struct scsi_device *sdp) +static int scsi_debug_sdev_init(struct scsi_device *sdp) { if (sdebug_verbose) - pr_info("slave_alloc <%u %u %u %llu>\n", + pr_info("sdev_init <%u %u %u %llu>\n", sdp->host->host_no, sdp->channel, sdp->id, sdp->lun); return 0; } -static int scsi_debug_slave_configure(struct scsi_device *sdp) +static int scsi_debug_sdev_configure(struct scsi_device *sdp, + struct queue_limits *lim) { struct sdebug_dev_info *devip = (struct sdebug_dev_info *)sdp->hostdata; struct dentry *dentry; if (sdebug_verbose) - pr_info("slave_configure <%u %u %u %llu>\n", + pr_info("sdev_configure <%u %u %u %llu>\n", sdp->host->host_no, sdp->channel, sdp->id, sdp->lun); if (sdp->host->max_cmd_len != SDEBUG_MAX_CMD_LEN) sdp->host->max_cmd_len = SDEBUG_MAX_CMD_LEN; @@ -5927,14 +5928,14 @@ static int scsi_debug_slave_configure(struct scsi_device *sdp) return 0; } -static void scsi_debug_slave_destroy(struct scsi_device *sdp) +static void scsi_debug_sdev_destroy(struct scsi_device *sdp) { struct sdebug_dev_info *devip = (struct sdebug_dev_info *)sdp->hostdata; struct sdebug_err_inject *err; if (sdebug_verbose) - pr_info("slave_destroy <%u %u %u %llu>\n", + pr_info("sdev_destroy <%u %u %u %llu>\n", sdp->host->host_no, sdp->channel, sdp->id, sdp->lun); if (!devip) @@ -8706,15 +8707,15 @@ static int sdebug_init_cmd_priv(struct Scsi_Host *shost, struct scsi_cmnd *cmd) return 0; } -static struct scsi_host_template sdebug_driver_template = { +static const struct scsi_host_template sdebug_driver_template = { .show_info = scsi_debug_show_info, .write_info = scsi_debug_write_info, .proc_name = sdebug_proc_name, .name = "SCSI DEBUG", .info = scsi_debug_info, - .slave_alloc = scsi_debug_slave_alloc, - .slave_configure = scsi_debug_slave_configure, - .slave_destroy = scsi_debug_slave_destroy, + .sdev_init = scsi_debug_sdev_init, + .sdev_configure = scsi_debug_sdev_configure, + .sdev_destroy = scsi_debug_sdev_destroy, .ioctl = scsi_debug_ioctl, .queuecommand = scsi_debug_queuecommand, .change_queue_depth = sdebug_change_qdepth, @@ -8732,6 +8733,7 @@ static struct scsi_host_template sdebug_driver_template = { .max_sectors = -1U, .max_segment_size = -1U, .module = THIS_MODULE, + .skip_settle_delay = 1, .track_queue_depth = 1, .cmd_size = sizeof(struct sdebug_scsi_cmd), .init_cmd_priv = sdebug_init_cmd_priv, @@ -8748,17 +8750,17 @@ static int sdebug_driver_probe(struct device *dev) sdbg_host = dev_to_sdebug_host(dev); - sdebug_driver_template.can_queue = sdebug_max_queue; - sdebug_driver_template.cmd_per_lun = sdebug_max_queue; - if (!sdebug_clustering) - sdebug_driver_template.dma_boundary = PAGE_SIZE - 1; - hpnt = scsi_host_alloc(&sdebug_driver_template, 0); if (NULL == hpnt) { pr_err("scsi_host_alloc failed\n"); error = -ENODEV; return error; } + hpnt->can_queue = sdebug_max_queue; + hpnt->cmd_per_lun = sdebug_max_queue; + if (!sdebug_clustering) + hpnt->dma_boundary = PAGE_SIZE - 1; + if (submit_queues > nr_cpu_ids) { pr_warn("%s: trim submit_queues (was %d) to nr_cpu_ids=%u\n", my_name, submit_queues, nr_cpu_ids); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 10154d78e336..815e7d63f3e2 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -2363,14 +2363,14 @@ int scsi_error_handler(void *data) return 0; } -/* - * Function: scsi_report_bus_reset() +/** + * scsi_report_bus_reset() - report bus reset observed * - * Purpose: Utility function used by low-level drivers to report that - * they have observed a bus reset on the bus being handled. + * Utility function used by low-level drivers to report that + * they have observed a bus reset on the bus being handled. * - * Arguments: shost - Host in question - * channel - channel on which reset was observed. + * @shost: Host in question + * @channel: channel on which reset was observed. * * Returns: Nothing * @@ -2395,15 +2395,15 @@ void scsi_report_bus_reset(struct Scsi_Host *shost, int channel) } EXPORT_SYMBOL(scsi_report_bus_reset); -/* - * Function: scsi_report_device_reset() +/** + * scsi_report_device_reset() - report device reset observed * - * Purpose: Utility function used by low-level drivers to report that - * they have observed a device reset on the device being handled. + * Utility function used by low-level drivers to report that + * they have observed a device reset on the device being handled. * - * Arguments: shost - Host in question - * channel - channel on which reset was observed - * target - target on which reset was observed + * @shost: Host in question + * @channel: channel on which reset was observed + * @target: target on which reset was observed * * Returns: Nothing * diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c index 6f6c5973c3ea..2fa45556e1ea 100644 --- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -37,8 +37,10 @@ * @host: host to identify * @buffer: userspace buffer for identification * - * Return an identifying string at @buffer, if @buffer is non-NULL, filling - * to the length stored at * (int *) @buffer. + * Return: + * * if successful, %1 and an identifying string at @buffer, if @buffer + * is non-NULL, filling to the length stored at * (int *) @buffer. + * * <0 error code on failure. */ static int ioctl_probe(struct Scsi_Host *host, void __user *buffer) { @@ -121,6 +123,16 @@ out: return result; } +/** + * scsi_set_medium_removal() - send command to allow or prevent medium removal + * @sdev: target scsi device + * @state: removal state to set (prevent or allow) + * + * Returns: + * * %0 if @sdev is not removable or not lockable or successful. + * * non-%0 is a SCSI result code if > 0 or kernel error code if < 0. + * * Sets @sdev->locked to the new state on success. + */ int scsi_set_medium_removal(struct scsi_device *sdev, char state) { char scsi_cmd[MAX_COMMAND_SIZE]; @@ -242,11 +254,15 @@ static int scsi_send_start_stop(struct scsi_device *sdev, int data) NORMAL_RETRIES); } -/* - * Check if the given command is allowed. +/** + * scsi_cmd_allowed() - Check if the given command is allowed. + * @cmd: SCSI command to check + * @open_for_write: is the file / block device opened for writing? * * Only a subset of commands are allowed for unprivileged users. Commands used * to format the media, update the firmware, etc. are not permitted. + * + * Return: %true if the cmd is allowed, otherwise @false. */ bool scsi_cmd_allowed(unsigned char *cmd, bool open_for_write) { @@ -859,6 +875,8 @@ static int scsi_ioctl_sg_io(struct scsi_device *sdev, bool open_for_write, * Description: The scsi_ioctl() function differs from most ioctls in that it * does not take a major/minor number as the dev field. Rather, it takes * a pointer to a &struct scsi_device. + * + * Return: varies depending on the @cmd */ int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd, void __user *arg) @@ -941,8 +959,15 @@ int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd, } EXPORT_SYMBOL(scsi_ioctl); -/* +/** + * scsi_ioctl_block_when_processing_errors - prevent commands from being queued + * @sdev: target scsi device + * @cmd: which ioctl is it + * @ndelay: no delay (non-blocking) + * * We can process a reset even when a device isn't fully operable. + * + * Return: %0 on success, <0 error code. */ int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev, int cmd, bool ndelay) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index adee6f60c966..d776f13cd160 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -184,6 +184,10 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason) __scsi_queue_insert(cmd, reason, true); } +/** + * scsi_failures_reset_retries - reset all failures to zero + * @failures: &struct scsi_failures with specific failure modes set + */ void scsi_failures_reset_retries(struct scsi_failures *failures) { struct scsi_failure *failure; @@ -210,6 +214,9 @@ static int scsi_check_passthrough(struct scsi_cmnd *scmd, struct scsi_sense_hdr sshdr; enum sam_status status; + if (!scmd->result) + return 0; + if (!failures) return 0; @@ -1214,6 +1221,15 @@ static void scsi_initialize_rq(struct request *rq) cmd->retries = 0; } +/** + * scsi_alloc_request - allocate a block request and partially + * initialize its &scsi_cmnd + * @q: the device's request queue + * @opf: the request operation code + * @flags: block layer allocation flags + * + * Return: &struct request pointer on success or %NULL on failure + */ struct request *scsi_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags) { @@ -2065,9 +2081,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost) tag_set->queue_depth = shost->can_queue; tag_set->cmd_size = cmd_size; tag_set->numa_node = dev_to_node(shost->dma_dev); - tag_set->flags = BLK_MQ_F_SHOULD_MERGE; - tag_set->flags |= - BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy); + if (shost->hostt->tag_alloc_policy_rr) + tag_set->flags |= BLK_MQ_F_TAG_RR; if (shost->queuecommand_may_block) tag_set->flags |= BLK_MQ_F_BLOCKING; tag_set->driver_data = shost; @@ -2721,6 +2736,7 @@ int scsi_device_quiesce(struct scsi_device *sdev) { struct request_queue *q = sdev->request_queue; + unsigned int memflags; int err; /* @@ -2735,7 +2751,7 @@ scsi_device_quiesce(struct scsi_device *sdev) blk_set_pm_only(q); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); /* * Ensure that the effect of blk_set_pm_only() will be visible * for percpu_ref_tryget() callers that occur after the queue @@ -2743,7 +2759,7 @@ scsi_device_quiesce(struct scsi_device *sdev) * was called. See also https://lwn.net/Articles/573497/. */ synchronize_rcu(); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); mutex_lock(&sdev->state_mutex); err = scsi_device_set_state(sdev, SDEV_QUIESCE); @@ -3365,14 +3381,16 @@ int scsi_vpd_lun_id(struct scsi_device *sdev, char *id, size_t id_len) } EXPORT_SYMBOL(scsi_vpd_lun_id); -/* +/** * scsi_vpd_tpg_id - return a target port group identifier * @sdev: SCSI device + * @rel_id: pointer to return relative target port in if not %NULL * * Returns the Target Port Group identifier from the information - * froom VPD page 0x83 of the device. + * from VPD page 0x83 of the device. + * Optionally sets @rel_id to the relative target port on success. * - * Returns the identifier or error on failure. + * Return: the identifier or error on failure. */ int scsi_vpd_tpg_id(struct scsi_device *sdev, int *rel_id) { diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 042329b74c6e..087fcbfc9aaa 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -220,6 +220,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, int new_shift = sbitmap_calculate_shift(depth); bool need_alloc = !sdev->budget_map.map; bool need_free = false; + unsigned int memflags; int ret; struct sbitmap sb_backup; @@ -227,7 +228,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, /* * realloc if new shift is calculated, which is caused by setting - * up one new default queue depth after calling ->device_configure + * up one new default queue depth after calling ->sdev_configure */ if (!need_alloc && new_shift != sdev->budget_map.shift) need_alloc = need_free = true; @@ -240,7 +241,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, * and here disk isn't added yet, so freezing is pretty fast */ if (need_free) { - blk_mq_freeze_queue(sdev->request_queue); + memflags = blk_mq_freeze_queue(sdev->request_queue); sb_backup = sdev->budget_map; } ret = sbitmap_init_node(&sdev->budget_map, @@ -256,7 +257,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, else sbitmap_free(&sb_backup); ret = 0; - blk_mq_unfreeze_queue(sdev->request_queue); + blk_mq_unfreeze_queue(sdev->request_queue, memflags); } return ret; } @@ -265,7 +266,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, * scsi_alloc_sdev - allocate and setup a scsi_Device * @starget: which target to allocate a &scsi_device for * @lun: which lun - * @hostdata: usually NULL and set by ->slave_alloc instead + * @hostdata: usually NULL and set by ->sdev_init instead * * Description: * Allocate, initialize for io, and return a pointer to a scsi_Device. @@ -312,11 +313,11 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, sdev->sdev_gendev.parent = get_device(&starget->dev); sdev->sdev_target = starget; - /* usually NULL and set by ->slave_alloc instead */ + /* usually NULL and set by ->sdev_init instead */ sdev->hostdata = hostdata; /* if the device needs this changing, it may do so in the - * slave_configure function */ + * sdev_configure function */ sdev->max_device_blocked = SCSI_DEFAULT_DEVICE_BLOCKED; /* @@ -363,8 +364,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, scsi_sysfs_device_initialize(sdev); - if (shost->hostt->slave_alloc) { - ret = shost->hostt->slave_alloc(sdev); + if (shost->hostt->sdev_init) { + ret = shost->hostt->sdev_init(sdev); if (ret) { /* * if LLDD reports slave not present, don't clutter @@ -1074,10 +1075,8 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, else if (*bflags & BLIST_MAX_1024) lim.max_hw_sectors = 1024; - if (hostt->device_configure) - ret = hostt->device_configure(sdev, &lim); - else if (hostt->slave_configure) - ret = hostt->slave_configure(sdev); + if (hostt->sdev_configure) + ret = hostt->sdev_configure(sdev, &lim); if (ret) { queue_limits_cancel_update(sdev->request_queue); /* @@ -1097,12 +1096,12 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, } /* - * The queue_depth is often changed in ->device_configure. + * The queue_depth is often changed in ->sdev_configure. * * Set up budget map again since memory consumption of the map depends * on actual queue depth. */ - if (hostt->device_configure || hostt->slave_configure) + if (hostt->sdev_configure) scsi_realloc_sdev_budget_map(sdev, sdev->queue_depth); if (sdev->scsi_level >= SCSI_3) @@ -1636,6 +1635,24 @@ struct scsi_device *__scsi_add_device(struct Scsi_Host *shost, uint channel, } EXPORT_SYMBOL(__scsi_add_device); +/** + * scsi_add_device - creates a new SCSI (LU) instance + * @host: the &Scsi_Host instance where the device is located + * @channel: target channel number (rarely other than %0) + * @target: target id number + * @lun: LUN of target device + * + * Probe for a specific LUN and add it if found. + * + * Notes: This call is usually performed internally during a SCSI + * bus scan when an HBA is added (i.e. scsi_scan_host()). So it + * should only be called if the HBA becomes aware of a new SCSI + * device (LU) after scsi_scan_host() has completed. If successful + * this call can lead to sdev_init() and sdev_configure() callbacks + * into the LLD. + * + * Return: %0 on success or negative error code on failure + */ int scsi_add_device(struct Scsi_Host *host, uint channel, uint target, u64 lun) { @@ -2027,6 +2044,8 @@ static void do_scan_async(void *_data, async_cookie_t c) /** * scsi_scan_host - scan the given adapter * @shost: adapter to scan + * + * Notes: Should be called after scsi_add_host() **/ void scsi_scan_host(struct Scsi_Host *shost) { diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c index 093774d77534..be4aef0f4f99 100644 --- a/drivers/scsi/scsi_sysctl.c +++ b/drivers/scsi/scsi_sysctl.c @@ -12,7 +12,7 @@ #include "scsi_priv.h" -static struct ctl_table scsi_table[] = { +static const struct ctl_table scsi_table[] = { { .procname = "logging_level", .data = &scsi_logging_level, .maxlen = sizeof(scsi_logging_level), diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index f3a1ecb42128..d772258e29ad 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -898,7 +898,7 @@ static DEVICE_ATTR(queue_type, S_IRUGO | S_IWUSR, show_queue_type_field, #define sdev_vpd_pg_attr(_page) \ static ssize_t \ show_vpd_##_page(struct file *filp, struct kobject *kobj, \ - struct bin_attribute *bin_attr, \ + const struct bin_attribute *bin_attr, \ char *buf, loff_t off, size_t count) \ { \ struct device *dev = kobj_to_dev(kobj); \ @@ -914,10 +914,10 @@ show_vpd_##_page(struct file *filp, struct kobject *kobj, \ rcu_read_unlock(); \ return ret; \ } \ -static struct bin_attribute dev_attr_vpd_##_page = { \ +static const struct bin_attribute dev_attr_vpd_##_page = { \ .attr = {.name = __stringify(vpd_##_page), .mode = S_IRUGO }, \ .size = 0, \ - .read = show_vpd_##_page, \ + .read_new = show_vpd_##_page, \ }; sdev_vpd_pg_attr(pg83); @@ -930,7 +930,7 @@ sdev_vpd_pg_attr(pgb7); sdev_vpd_pg_attr(pg0); static ssize_t show_inquiry(struct file *filep, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -943,13 +943,13 @@ static ssize_t show_inquiry(struct file *filep, struct kobject *kobj, sdev->inquiry_len); } -static struct bin_attribute dev_attr_inquiry = { +static const struct bin_attribute dev_attr_inquiry = { .attr = { .name = "inquiry", .mode = S_IRUGO, }, .size = 0, - .read = show_inquiry, + .read_new = show_inquiry, }; static ssize_t @@ -1348,7 +1348,7 @@ static struct attribute *scsi_sdev_attrs[] = { NULL }; -static struct bin_attribute *scsi_sdev_bin_attrs[] = { +static const struct bin_attribute *const scsi_sdev_bin_attrs[] = { &dev_attr_vpd_pg0, &dev_attr_vpd_pg83, &dev_attr_vpd_pg80, @@ -1362,7 +1362,7 @@ static struct bin_attribute *scsi_sdev_bin_attrs[] = { }; static struct attribute_group scsi_sdev_attr_group = { .attrs = scsi_sdev_attrs, - .bin_attrs = scsi_sdev_bin_attrs, + .bin_attrs_new = scsi_sdev_bin_attrs, .is_visible = scsi_sdev_attr_is_visible, .is_bin_visible = scsi_sdev_bin_attr_is_visible, }; @@ -1513,8 +1513,8 @@ void __scsi_remove_device(struct scsi_device *sdev) kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags); cancel_work_sync(&sdev->requeue_work); - if (sdev->host->hostt->slave_destroy) - sdev->host->hostt->slave_destroy(sdev); + if (sdev->host->hostt->sdev_destroy) + sdev->host->hostt->sdev_destroy(sdev); transport_destroy_device(dev); /* diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index fde7de3b1e55..9c347c64c315 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -1324,7 +1324,7 @@ EXPORT_SYMBOL_GPL(iscsi_create_flashnode_conn); * 1 on success * 0 on failure */ -static int iscsi_is_flashnode_conn_dev(struct device *dev, void *data) +static int iscsi_is_flashnode_conn_dev(struct device *dev, const void *data) { return dev->bus == &iscsi_flashnode_bus; } @@ -1335,7 +1335,7 @@ static int iscsi_destroy_flashnode_conn(struct iscsi_bus_flash_conn *fnode_conn) return 0; } -static int flashnode_match_index(struct device *dev, void *data) +static int flashnode_match_index(struct device *dev, const void *data) { struct iscsi_bus_flash_session *fnode_sess = NULL; int ret = 0; @@ -1344,7 +1344,7 @@ static int flashnode_match_index(struct device *dev, void *data) goto exit_match_index; fnode_sess = iscsi_dev_to_flash_session(dev); - ret = (fnode_sess->target_id == *((int *)data)) ? 1 : 0; + ret = (fnode_sess->target_id == *((const int *)data)) ? 1 : 0; exit_match_index: return ret; @@ -1389,8 +1389,8 @@ iscsi_get_flashnode_by_index(struct Scsi_Host *shost, uint32_t idx) * %NULL on failure */ struct device * -iscsi_find_flashnode_sess(struct Scsi_Host *shost, void *data, - int (*fn)(struct device *dev, void *data)) +iscsi_find_flashnode_sess(struct Scsi_Host *shost, const void *data, + device_match_t fn) { return device_find_child(&shost->shost_gendev, data, fn); } @@ -2122,33 +2122,6 @@ destroy_wq: } EXPORT_SYMBOL_GPL(iscsi_add_session); -/** - * iscsi_create_session - create iscsi class session - * @shost: scsi host - * @transport: iscsi transport - * @dd_size: private driver data size - * @target_id: which target - * - * This can be called from a LLD or iscsi_transport. - */ -struct iscsi_cls_session * -iscsi_create_session(struct Scsi_Host *shost, struct iscsi_transport *transport, - int dd_size, unsigned int target_id) -{ - struct iscsi_cls_session *session; - - session = iscsi_alloc_session(shost, transport, dd_size); - if (!session) - return NULL; - - if (iscsi_add_session(session, target_id)) { - iscsi_free_session(session); - return NULL; - } - return session; -} -EXPORT_SYMBOL_GPL(iscsi_create_session); - static void iscsi_conn_release(struct device *dev) { struct iscsi_cls_conn *conn = iscsi_dev_to_conn(dev); @@ -4104,7 +4077,7 @@ iscsi_if_rx(struct sk_buff *skb) } do { /* - * special case for GET_STATS: + * special case for GET_STATS, GET_CHAP and GET_HOST_STATS: * on success - sending reply and stats from * inside of if_recv_msg(), * on error - fall through. @@ -4113,6 +4086,8 @@ iscsi_if_rx(struct sk_buff *skb) break; if (ev->type == ISCSI_UEVENT_GET_CHAP && !err) break; + if (ev->type == ISCSI_UEVENT_GET_HOST_STATS && !err) + break; err = iscsi_if_send_reply(portid, nlh->nlmsg_type, ev, sizeof(*ev)); if (err == -EAGAIN && --retries < 0) { diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 4e33f1661e4c..351b028ef893 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -888,7 +888,8 @@ static void sas_port_delete_link(struct sas_port *port, sysfs_remove_link(&phy->dev.kobj, "port"); } -/** sas_port_alloc - allocate and initialize a SAS port structure +/** + * sas_port_alloc - allocate and initialize a SAS port structure * * @parent: parent device * @port_id: port number @@ -897,7 +898,7 @@ static void sas_port_delete_link(struct sas_port *port, * below the device specified by @parent which must be either a Scsi_Host * or a sas_expander_device. * - * Returns %NULL on error + * Returns: %NULL on error */ struct sas_port *sas_port_alloc(struct device *parent, int port_id) { @@ -932,7 +933,8 @@ struct sas_port *sas_port_alloc(struct device *parent, int port_id) } EXPORT_SYMBOL(sas_port_alloc); -/** sas_port_alloc_num - allocate and initialize a SAS port structure +/** + * sas_port_alloc_num - allocate and initialize a SAS port structure * * @parent: parent device * @@ -942,7 +944,7 @@ EXPORT_SYMBOL(sas_port_alloc); * the device tree below the device specified by @parent which must be * either a Scsi_Host or a sas_expander_device. * - * Returns %NULL on error + * Returns: %NULL on error */ struct sas_port *sas_port_alloc_num(struct device *parent) { diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c index 64852e6df3e3..fe47850a8258 100644 --- a/drivers/scsi/scsi_transport_spi.c +++ b/drivers/scsi/scsi_transport_spi.c @@ -985,7 +985,8 @@ spi_dv_device_internal(struct scsi_device *sdev, u8 *buffer) } -/** spi_dv_device - Do Domain Validation on the device +/** + * spi_dv_device - Do Domain Validation on the device * @sdev: scsi device to validate * * Performs the domain validation on the given device in the diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 8947dab132d7..950d8c9fb884 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -177,9 +177,8 @@ cache_type_store(struct device *dev, struct device_attribute *attr, lim = queue_limits_start_update(sdkp->disk->queue); sd_set_flush_flag(sdkp, &lim); - blk_mq_freeze_queue(sdkp->disk->queue); - ret = queue_limits_commit_update(sdkp->disk->queue, &lim); - blk_mq_unfreeze_queue(sdkp->disk->queue); + ret = queue_limits_commit_update_frozen(sdkp->disk->queue, + &lim); if (ret) return ret; return count; @@ -483,9 +482,7 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr, lim = queue_limits_start_update(sdkp->disk->queue); sd_config_discard(sdkp, &lim, mode); - blk_mq_freeze_queue(sdkp->disk->queue); - err = queue_limits_commit_update(sdkp->disk->queue, &lim); - blk_mq_unfreeze_queue(sdkp->disk->queue); + err = queue_limits_commit_update_frozen(sdkp->disk->queue, &lim); if (err) return err; return count; @@ -594,9 +591,7 @@ max_write_same_blocks_store(struct device *dev, struct device_attribute *attr, lim = queue_limits_start_update(sdkp->disk->queue); sd_config_write_same(sdkp, &lim); - blk_mq_freeze_queue(sdkp->disk->queue); - err = queue_limits_commit_update(sdkp->disk->queue, &lim); - blk_mq_unfreeze_queue(sdkp->disk->queue); + err = queue_limits_commit_update_frozen(sdkp->disk->queue, &lim); if (err) return err; return count; @@ -814,14 +809,14 @@ static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd, if (bio_integrity_flagged(bio, BIP_IP_CHECKSUM)) scmd->prot_flags |= SCSI_PROT_IP_CHECKSUM; - if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false) + if (bio_integrity_flagged(bio, BIP_CHECK_GUARD)) scmd->prot_flags |= SCSI_PROT_GUARD_CHECK; } if (dif != T10_PI_TYPE3_PROTECTION) { /* DIX/DIF Type 0, 1, 2 */ scmd->prot_flags |= SCSI_PROT_REF_INCREMENT; - if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false) + if (bio_integrity_flagged(bio, BIP_CHECK_REFTAG)) scmd->prot_flags |= SCSI_PROT_REF_CHECK; } @@ -996,6 +991,7 @@ static void sd_config_atomic(struct scsi_disk *sdkp, struct queue_limits *lim) lim->atomic_write_hw_boundary = 0; lim->atomic_write_hw_unit_min = unit_min * logical_block_size; lim->atomic_write_hw_unit_max = unit_max * logical_block_size; + lim->features |= BLK_FEAT_ATOMIC_WRITES; } static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, @@ -3803,9 +3799,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_config_write_same(sdkp, &lim); kfree(buffer); - blk_mq_freeze_queue(sdkp->disk->queue); - err = queue_limits_commit_update(sdkp->disk->queue, &lim); - blk_mq_unfreeze_queue(sdkp->disk->queue); + err = queue_limits_commit_update_frozen(sdkp->disk->queue, &lim); if (err) return err; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 94127868bedf..effb7e768165 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1639,7 +1639,7 @@ MODULE_PARM_DESC(allow_dio, "allow direct I/O (default: 0 (disallow))"); #ifdef CONFIG_SYSCTL #include -static struct ctl_table sg_sysctls[] = { +static const struct ctl_table sg_sysctls[] = { { .procname = "sg-big-buff", .data = &sg_big_buff, diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 870f37b70546..0da7be40c925 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -6490,7 +6489,7 @@ out: return SUCCESS; } -static int pqi_slave_alloc(struct scsi_device *sdev) +static int pqi_sdev_init(struct scsi_device *sdev) { struct pqi_scsi_dev *device; unsigned long flags; @@ -6547,10 +6546,10 @@ static void pqi_map_queues(struct Scsi_Host *shost) struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost); if (!ctrl_info->disable_managed_interrupts) - return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], - ctrl_info->pci_dev, 0); + blk_mq_map_hw_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], + &ctrl_info->pci_dev->dev, 0); else - return blk_mq_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT]); } static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device) @@ -6558,7 +6557,8 @@ static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device) return device->devtype == TYPE_TAPE || device->devtype == TYPE_MEDIUM_CHANGER; } -static int pqi_slave_configure(struct scsi_device *sdev) +static int pqi_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { int rc = 0; struct pqi_scsi_dev *device; @@ -6574,7 +6574,7 @@ static int pqi_slave_configure(struct scsi_device *sdev) return rc; } -static void pqi_slave_destroy(struct scsi_device *sdev) +static void pqi_sdev_destroy(struct scsi_device *sdev) { struct pqi_ctrl_info *ctrl_info; struct pqi_scsi_dev *device; @@ -7549,9 +7549,9 @@ static const struct scsi_host_template pqi_driver_template = { .eh_device_reset_handler = pqi_eh_device_reset_handler, .eh_abort_handler = pqi_eh_abort_handler, .ioctl = pqi_ioctl, - .slave_alloc = pqi_slave_alloc, - .slave_configure = pqi_slave_configure, - .slave_destroy = pqi_slave_destroy, + .sdev_init = pqi_sdev_init, + .sdev_configure = pqi_sdev_configure, + .sdev_destroy = pqi_sdev_destroy, .map_queues = pqi_map_queues, .sdev_groups = pqi_sdev_groups, .shost_groups = pqi_shost_groups, diff --git a/drivers/scsi/snic/snic_main.c b/drivers/scsi/snic/snic_main.c index 9be3f0193145..1c24517e4e65 100644 --- a/drivers/scsi/snic/snic_main.c +++ b/drivers/scsi/snic/snic_main.c @@ -21,7 +21,7 @@ #define PCI_DEVICE_ID_CISCO_SNIC 0x0046 /* Supported devices by snic module */ -static struct pci_device_id snic_id_table[] = { +static const struct pci_device_id snic_id_table[] = { {PCI_DEVICE(0x1137, PCI_DEVICE_ID_CISCO_SNIC) }, { 0, } /* end of table */ }; @@ -42,11 +42,11 @@ module_param(snic_max_qdepth, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(snic_max_qdepth, "Queue depth to report for each LUN"); /* - * snic_slave_alloc : callback function to SCSI Mid Layer, called on + * snic_sdev_init : callback function to SCSI Mid Layer, called on * scsi device initialization. */ static int -snic_slave_alloc(struct scsi_device *sdev) +snic_sdev_init(struct scsi_device *sdev) { struct snic_tgt *tgt = starget_to_tgt(scsi_target(sdev)); @@ -57,11 +57,11 @@ snic_slave_alloc(struct scsi_device *sdev) } /* - * snic_slave_configure : callback function to SCSI Mid Layer, called on + * snic_sdev_configure : callback function to SCSI Mid Layer, called on * scsi device initialization. */ static int -snic_slave_configure(struct scsi_device *sdev) +snic_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { struct snic *snic = shost_priv(sdev->host); u32 qdepth = 0, max_ios = 0; @@ -107,8 +107,8 @@ static const struct scsi_host_template snic_host_template = { .eh_abort_handler = snic_abort_cmd, .eh_device_reset_handler = snic_device_reset, .eh_host_reset_handler = snic_host_reset, - .slave_alloc = snic_slave_alloc, - .slave_configure = snic_slave_configure, + .sdev_init = snic_sdev_init, + .sdev_configure = snic_sdev_configure, .change_queue_depth = snic_change_queue_depth, .this_id = -1, .cmd_per_lun = SNIC_DFLT_QUEUE_DEPTH, diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 198bec87bb8e..b17796d5ee66 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -797,10 +797,7 @@ static int get_sectorsize(struct scsi_cd *cd) lim = queue_limits_start_update(q); lim.logical_block_size = sector_size; - blk_mq_freeze_queue(q); - err = queue_limits_commit_update(q, &lim); - blk_mq_unfreeze_queue(q); - return err; + return queue_limits_commit_update_frozen(q, &lim); } static int get_capabilities(struct scsi_cd *cd) diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index e8ef27d7ef61..ebbd50ec0cda 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -1030,6 +1030,11 @@ static int test_ready(struct scsi_tape *STp, int do_wait) retval = new_session ? CHKRES_NEW_SESSION : CHKRES_READY; break; } + if (STp->first_tur) { + /* Don't set pos_unknown right after device recognition */ + STp->pos_unknown = 0; + STp->first_tur = 0; + } if (SRpnt != NULL) st_release_request(SRpnt); @@ -4328,6 +4333,7 @@ static int st_probe(struct device *dev) blk_queue_rq_timeout(tpnt->device->request_queue, ST_TIMEOUT); tpnt->long_timeout = ST_LONG_TIMEOUT; tpnt->try_dio = try_direct_io; + tpnt->first_tur = 1; for (i = 0; i < ST_NBR_MODES; i++) { STm = &(tpnt->modes[i]); diff --git a/drivers/scsi/st.h b/drivers/scsi/st.h index 7a68eaba7e81..1aaaf5369a40 100644 --- a/drivers/scsi/st.h +++ b/drivers/scsi/st.h @@ -170,6 +170,7 @@ struct scsi_tape { unsigned char rew_at_close; /* rewind necessary at close */ unsigned char inited; unsigned char cleaning_req; /* cleaning requested? */ + unsigned char first_tur; /* first TEST UNIT READY */ int block_size; int min_block; int max_block; diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c index 0e81125df8c7..63ed7f9aaa93 100644 --- a/drivers/scsi/stex.c +++ b/drivers/scsi/stex.c @@ -584,7 +584,7 @@ static void return_abnormal_state(struct st_hba *hba, int status) spin_unlock_irqrestore(hba->host->host_lock, flags); } static int -stex_slave_config(struct scsi_device *sdev) +stex_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { sdev->use_10_for_rw = 1; sdev->use_10_for_ms = 1; @@ -1481,14 +1481,14 @@ static const struct scsi_host_template driver_template = { .proc_name = DRV_NAME, .bios_param = stex_biosparam, .queuecommand = stex_queuecommand, - .slave_configure = stex_slave_config, + .sdev_configure = stex_sdev_configure, .eh_abort_handler = stex_abort, .eh_host_reset_handler = stex_reset, .this_id = -1, .dma_boundary = PAGE_SIZE - 1, }; -static struct pci_device_id stex_pci_tbl[] = { +static const struct pci_device_id stex_pci_tbl[] = { /* st_shasta */ { 0x105a, 0x8350, PCI_ANY_ID, PCI_ANY_ID, 0, 0, st_shasta }, /* SuperTrak EX8350/8300/16350/16300 */ diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index d0b55c1fa908..5a101ac06c47 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -171,6 +171,12 @@ do { \ dev_warn(&(dev)->device, fmt, ##__VA_ARGS__); \ } while (0) +#define storvsc_log_ratelimited(dev, level, fmt, ...) \ +do { \ + if (do_logging(level)) \ + dev_warn_ratelimited(&(dev)->device, fmt, ##__VA_ARGS__); \ +} while (0) + struct vmscsi_request { u16 length; u8 srb_status; @@ -917,14 +923,13 @@ static int storvsc_channel_init(struct hv_device *device, bool is_fc) /* * Allocate state to manage the sub-channels. - * We allocate an array based on the numbers of possible CPUs - * (Hyper-V does not support cpu online/offline). - * This Array will be sparseley populated with unique - * channels - primary + sub-channels. - * We will however populate all the slots to evenly distribute - * the load. + * We allocate an array based on the number of CPU ids. This array + * is initially sparsely populated for the CPUs assigned to channels: + * primary + sub-channels. As I/Os are initiated by different CPUs, + * the slots for all online CPUs are populated to evenly distribute + * the load across all channels. */ - stor_device->stor_chns = kcalloc(num_possible_cpus(), sizeof(void *), + stor_device->stor_chns = kcalloc(nr_cpu_ids, sizeof(void *), GFP_KERNEL); if (stor_device->stor_chns == NULL) return -ENOMEM; @@ -1177,7 +1182,7 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, int loglevel = (stor_pkt->vm_srb.cdb[0] == TEST_UNIT_READY) ? STORVSC_LOGGING_WARN : STORVSC_LOGGING_ERROR; - storvsc_log(device, loglevel, + storvsc_log_ratelimited(device, loglevel, "tag#%d cmd 0x%x status: scsi 0x%x srb 0x%x hv 0x%x\n", scsi_cmd_to_rq(request->cmd)->tag, stor_pkt->vm_srb.cdb[0], @@ -1579,7 +1584,8 @@ static int storvsc_device_alloc(struct scsi_device *sdevice) return 0; } -static int storvsc_device_configure(struct scsi_device *sdevice) +static int storvsc_sdev_configure(struct scsi_device *sdevice, + struct queue_limits *lim) { blk_queue_rq_timeout(sdevice->request_queue, (storvsc_timeout * HZ)); @@ -1880,8 +1886,8 @@ static struct scsi_host_template scsi_driver = { .eh_host_reset_handler = storvsc_host_reset_handler, .proc_name = "storvsc_host", .eh_timed_out = storvsc_eh_timed_out, - .slave_alloc = storvsc_device_alloc, - .slave_configure = storvsc_device_configure, + .sdev_init = storvsc_device_alloc, + .sdev_configure = storvsc_sdev_configure, .cmd_per_lun = 2048, .this_id = -1, /* Ensure there are no gaps in presented sgls */ diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c index a2560cc807d3..212d89d0d23e 100644 --- a/drivers/scsi/sym53c8xx_2/sym_glue.c +++ b/drivers/scsi/sym53c8xx_2/sym_glue.c @@ -765,7 +765,7 @@ static void sym_tune_dev_queuing(struct sym_tcb *tp, int lun, u_short reqtags) } } -static int sym53c8xx_slave_alloc(struct scsi_device *sdev) +static int sym53c8xx_sdev_init(struct scsi_device *sdev) { struct sym_hcb *np = sym_get_hcb(sdev->host); struct sym_tcb *tp = &np->target[sdev->id]; @@ -825,7 +825,8 @@ out: /* * Linux entry point for device queue sizing. */ -static int sym53c8xx_slave_configure(struct scsi_device *sdev) +static int sym53c8xx_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct sym_hcb *np = sym_get_hcb(sdev->host); struct sym_tcb *tp = &np->target[sdev->id]; @@ -861,14 +862,14 @@ static int sym53c8xx_slave_configure(struct scsi_device *sdev) return 0; } -static void sym53c8xx_slave_destroy(struct scsi_device *sdev) +static void sym53c8xx_sdev_destroy(struct scsi_device *sdev) { struct sym_hcb *np = sym_get_hcb(sdev->host); struct sym_tcb *tp = &np->target[sdev->id]; struct sym_lcb *lp = sym_lp(tp, sdev->lun); unsigned long flags; - /* if slave_alloc returned before allocating a sym_lcb, return */ + /* if sdev_init returned before allocating a sym_lcb, return */ if (!lp) return; @@ -1684,9 +1685,9 @@ static const struct scsi_host_template sym2_template = { .info = sym53c8xx_info, .cmd_size = sizeof(struct sym_ucmd), .queuecommand = sym53c8xx_queue_command, - .slave_alloc = sym53c8xx_slave_alloc, - .slave_configure = sym53c8xx_slave_configure, - .slave_destroy = sym53c8xx_slave_destroy, + .sdev_init = sym53c8xx_sdev_init, + .sdev_configure = sym53c8xx_sdev_configure, + .sdev_destroy = sym53c8xx_sdev_destroy, .eh_abort_handler = sym53c8xx_eh_abort_handler, .eh_target_reset_handler = sym53c8xx_eh_target_reset_handler, .eh_bus_reset_handler = sym53c8xx_eh_bus_reset_handler, @@ -2030,7 +2031,7 @@ static struct spi_function_template sym2_transport_functions = { .get_signalling = sym2_get_signalling, }; -static struct pci_device_id sym2_id_table[] = { +static const struct pci_device_id sym2_id_table[] = { { PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_NCR_53C810, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL }, { PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_NCR_53C820, diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 8471f38b730e..21ce3e940192 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -29,7 +29,6 @@ #include #include #include -#include #include "sd.h" @@ -746,7 +745,7 @@ static void virtscsi_map_queues(struct Scsi_Host *shost) if (i == HCTX_TYPE_POLL) blk_mq_map_queues(map); else - blk_mq_virtio_map_queues(map, vscsi->vdev, 2); + blk_mq_map_hw_queues(map, &vscsi->vdev->dev, 2); } } @@ -801,7 +800,7 @@ static const struct scsi_host_template virtscsi_host_template = { .eh_abort_handler = virtscsi_abort, .eh_device_reset_handler = virtscsi_device_reset, .eh_timed_out = virtscsi_eh_timed_out, - .slave_alloc = virtscsi_device_alloc, + .sdev_init = virtscsi_device_alloc, .dma_boundary = UINT_MAX, .map_queues = virtscsi_map_queues, diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 9ec55ddc1204..924025305753 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -735,7 +735,8 @@ static int scsifront_dev_reset_handler(struct scsi_cmnd *sc) return scsifront_action_handler(sc, VSCSIIF_ACT_SCSI_RESET); } -static int scsifront_sdev_configure(struct scsi_device *sdev) +static int scsifront_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct vscsifrnt_info *info = shost_priv(sdev->host); int err; @@ -776,8 +777,8 @@ static const struct scsi_host_template scsifront_sht = { .queuecommand = scsifront_queuecommand, .eh_abort_handler = scsifront_eh_abort_handler, .eh_device_reset_handler = scsifront_dev_reset_handler, - .slave_configure = scsifront_sdev_configure, - .slave_destroy = scsifront_sdev_destroy, + .sdev_configure = scsifront_sdev_configure, + .sdev_destroy = scsifront_sdev_destroy, .cmd_per_lun = VSCSIIF_DEFAULT_CMD_PER_LUN, .can_queue = VSCSIIF_MAX_REQS, .this_id = -1, @@ -1074,8 +1075,8 @@ static void scsifront_do_lun_hotplug(struct vscsifrnt_info *info, int op) continue; /* - * Front device state path, used in slave_configure called - * on successfull scsi_add_device, and in slave_destroy called + * Front device state path, used in sdev_configure called + * on successfull scsi_add_device, and in sdev_destroy called * on remove of a device. */ snprintf(info->dev_state_path, sizeof(info->dev_state_path), diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index 65e5515f7555..005fa2ef100f 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -328,7 +328,8 @@ void slim_report_absent(struct slim_device *sbdev) } EXPORT_SYMBOL_GPL(slim_report_absent); -static bool slim_eaddr_equal(struct slim_eaddr *a, struct slim_eaddr *b) +static bool slim_eaddr_equal(const struct slim_eaddr *a, + const struct slim_eaddr *b) { return (a->manf_id == b->manf_id && a->prod_code == b->prod_code && @@ -336,9 +337,9 @@ static bool slim_eaddr_equal(struct slim_eaddr *a, struct slim_eaddr *b) a->instance == b->instance); } -static int slim_match_dev(struct device *dev, void *data) +static int slim_match_dev(struct device *dev, const void *data) { - struct slim_eaddr *e_addr = data; + const struct slim_eaddr *e_addr = data; struct slim_device *sbdev = to_slim_device(dev); return slim_eaddr_equal(&sbdev->e_addr, e_addr); @@ -384,21 +385,13 @@ struct slim_device *slim_get_device(struct slim_controller *ctrl, } EXPORT_SYMBOL_GPL(slim_get_device); -static int of_slim_match_dev(struct device *dev, void *data) -{ - struct device_node *np = data; - struct slim_device *sbdev = to_slim_device(dev); - - return (sbdev->dev.of_node == np); -} - static struct slim_device *of_find_slim_device(struct slim_controller *ctrl, struct device_node *np) { struct slim_device *sbdev; struct device *dev; - dev = device_find_child(ctrl->dev, np, of_slim_match_dev); + dev = device_find_child(ctrl->dev, np, device_match_of_node); if (dev) { sbdev = to_slim_device(dev); return sbdev; diff --git a/drivers/slimbus/messaging.c b/drivers/slimbus/messaging.c index 242570a5e565..e7aa9bd4b44b 100644 --- a/drivers/slimbus/messaging.c +++ b/drivers/slimbus/messaging.c @@ -13,8 +13,8 @@ * * @ctrl: Controller handle * @reply: Reply received from the device - * @len: Length of the reply * @tid: Transaction ID received with which framework can associate reply. + * @len: Length of the reply * * Called by controller to inform framework about the response received. * This helps in making the API asynchronous, and controller-driver doesn't need diff --git a/drivers/soc/atmel/soc.c b/drivers/soc/atmel/soc.c index 2a42b28931c9..298b542dd1c0 100644 --- a/drivers/soc/atmel/soc.c +++ b/drivers/soc/atmel/soc.c @@ -399,7 +399,7 @@ static const struct of_device_id at91_soc_allowed_list[] __initconst = { static int __init atmel_soc_device_init(void) { - struct device_node *np = of_find_node_by_path("/"); + struct device_node *np __free(device_node) = of_find_node_by_path("/"); if (!of_match_node(at91_soc_allowed_list, np)) return 0; diff --git a/drivers/soc/fsl/qbman/qman_test_stash.c b/drivers/soc/fsl/qbman/qman_test_stash.c index b7e8e5ec884c..f4d3c2146f4f 100644 --- a/drivers/soc/fsl/qbman/qman_test_stash.c +++ b/drivers/soc/fsl/qbman/qman_test_stash.c @@ -108,14 +108,12 @@ static int on_all_cpus(int (*fn)(void)) .fn = fn, .started = ATOMIC_INIT(0) }; - struct task_struct *k = kthread_create(bstrap_fn, &bstrap, - "hotpotato%d", cpu); + struct task_struct *k = kthread_run_on_cpu(bstrap_fn, &bstrap, + cpu, "hotpotato%d"); int ret; if (IS_ERR(k)) return -ENOMEM; - kthread_bind(k, cpu); - wake_up_process(k); /* * If we call kthread_stop() before the "wake up" has had an * effect, then the thread may exit with -EINTR without ever diff --git a/drivers/soc/imx/Makefile b/drivers/soc/imx/Makefile index 3ad321ca608a..ca6a5fa1618f 100644 --- a/drivers/soc/imx/Makefile +++ b/drivers/soc/imx/Makefile @@ -3,4 +3,4 @@ ifeq ($(CONFIG_ARM),y) obj-$(CONFIG_ARCH_MXC) += soc-imx.o endif obj-$(CONFIG_SOC_IMX8M) += soc-imx8m.o -obj-$(CONFIG_SOC_IMX9) += imx93-src.o +obj-$(CONFIG_SOC_IMX9) += imx93-src.o soc-imx9.o diff --git a/drivers/soc/imx/soc-imx9.c b/drivers/soc/imx/soc-imx9.c new file mode 100644 index 000000000000..b46d22cf0212 --- /dev/null +++ b/drivers/soc/imx/soc-imx9.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2024 NXP + */ + +#include +#include +#include +#include +#include +#include +#include + +#define IMX_SIP_GET_SOC_INFO 0xc2000006 +#define SOC_ID(x) (((x) & 0xFFFF) >> 8) +#define SOC_REV_MAJOR(x) ((((x) >> 28) & 0xF) - 0x9) +#define SOC_REV_MINOR(x) (((x) >> 24) & 0xF) + +static int imx9_soc_probe(struct platform_device *pdev) +{ + struct soc_device_attribute *attr; + struct arm_smccc_res res; + struct soc_device *sdev; + u32 soc_id, rev_major, rev_minor; + u64 uid127_64, uid63_0; + int err; + + attr = kzalloc(sizeof(*attr), GFP_KERNEL); + if (!attr) + return -ENOMEM; + + err = of_property_read_string(of_root, "model", &attr->machine); + if (err) { + pr_err("%s: missing model property: %d\n", __func__, err); + goto attr; + } + + attr->family = kasprintf(GFP_KERNEL, "Freescale i.MX"); + + /* + * Retrieve the soc id, rev & uid info: + * res.a1[31:16]: soc revision; + * res.a1[15:0]: soc id; + * res.a2: uid[127:64]; + * res.a3: uid[63:0]; + */ + arm_smccc_smc(IMX_SIP_GET_SOC_INFO, 0, 0, 0, 0, 0, 0, 0, &res); + if (res.a0 != SMCCC_RET_SUCCESS) { + pr_err("%s: SMC failed: 0x%lx\n", __func__, res.a0); + err = -EINVAL; + goto family; + } + + soc_id = SOC_ID(res.a1); + rev_major = SOC_REV_MAJOR(res.a1); + rev_minor = SOC_REV_MINOR(res.a1); + + attr->soc_id = kasprintf(GFP_KERNEL, "i.MX%2x", soc_id); + attr->revision = kasprintf(GFP_KERNEL, "%d.%d", rev_major, rev_minor); + + uid127_64 = res.a2; + uid63_0 = res.a3; + attr->serial_number = kasprintf(GFP_KERNEL, "%016llx%016llx", uid127_64, uid63_0); + + sdev = soc_device_register(attr); + if (IS_ERR(sdev)) { + err = PTR_ERR(sdev); + pr_err("%s failed to register SoC as a device: %d\n", __func__, err); + goto serial_number; + } + + return 0; + +serial_number: + kfree(attr->serial_number); + kfree(attr->revision); + kfree(attr->soc_id); +family: + kfree(attr->family); +attr: + kfree(attr); + return err; +} + +static __maybe_unused const struct of_device_id imx9_soc_match[] = { + { .compatible = "fsl,imx93", }, + { .compatible = "fsl,imx95", }, + { } +}; + +#define IMX_SOC_DRIVER "imx9-soc" + +static struct platform_driver imx9_soc_driver = { + .probe = imx9_soc_probe, + .driver = { + .name = IMX_SOC_DRIVER, + }, +}; + +static int __init imx9_soc_init(void) +{ + int ret; + struct platform_device *pdev; + + /* No match means it is not an i.MX 9 series SoC, do nothing. */ + if (!of_match_node(imx9_soc_match, of_root)) + return 0; + + ret = platform_driver_register(&imx9_soc_driver); + if (ret) { + pr_err("failed to register imx9_soc platform driver: %d\n", ret); + return ret; + } + + pdev = platform_device_register_simple(IMX_SOC_DRIVER, -1, NULL, 0); + if (IS_ERR(pdev)) { + pr_err("failed to register imx9_soc platform device: %ld\n", PTR_ERR(pdev)); + platform_driver_unregister(&imx9_soc_driver); + return PTR_ERR(pdev); + } + + return 0; +} +device_initcall(imx9_soc_init); + +MODULE_AUTHOR("NXP"); +MODULE_DESCRIPTION("NXP i.MX9 SoC"); +MODULE_LICENSE("GPL"); diff --git a/drivers/soc/litex/litex_soc_ctrl.c b/drivers/soc/litex/litex_soc_ctrl.c index d08bfc8ef7be..104a5f9bfd26 100644 --- a/drivers/soc/litex/litex_soc_ctrl.c +++ b/drivers/soc/litex/litex_soc_ctrl.c @@ -69,14 +69,11 @@ static int litex_check_csr_access(void __iomem *reg_addr) struct litex_soc_ctrl_device { void __iomem *base; - struct notifier_block reset_nb; }; -static int litex_reset_handler(struct notifier_block *this, unsigned long mode, - void *cmd) +static int litex_reset_handler(struct sys_off_data *data) { - struct litex_soc_ctrl_device *soc_ctrl_dev = - container_of(this, struct litex_soc_ctrl_device, reset_nb); + struct litex_soc_ctrl_device *soc_ctrl_dev = data->cb_data; litex_write32(soc_ctrl_dev->base + RESET_REG_OFF, RESET_REG_VALUE); return NOTIFY_DONE; @@ -105,11 +102,9 @@ static int litex_soc_ctrl_probe(struct platform_device *pdev) if (error) return error; - platform_set_drvdata(pdev, soc_ctrl_dev); - - soc_ctrl_dev->reset_nb.notifier_call = litex_reset_handler; - soc_ctrl_dev->reset_nb.priority = 128; - error = register_restart_handler(&soc_ctrl_dev->reset_nb); + error = devm_register_restart_handler(&pdev->dev, + litex_reset_handler, + soc_ctrl_dev); if (error) { dev_warn(&pdev->dev, "cannot register restart handler: %d\n", error); @@ -118,20 +113,12 @@ static int litex_soc_ctrl_probe(struct platform_device *pdev) return 0; } -static void litex_soc_ctrl_remove(struct platform_device *pdev) -{ - struct litex_soc_ctrl_device *soc_ctrl_dev = platform_get_drvdata(pdev); - - unregister_restart_handler(&soc_ctrl_dev->reset_nb); -} - static struct platform_driver litex_soc_ctrl_driver = { .driver = { .name = "litex-soc-controller", .of_match_table = litex_soc_ctrl_of_match, }, .probe = litex_soc_ctrl_probe, - .remove = litex_soc_ctrl_remove, }; module_platform_driver(litex_soc_ctrl_driver); diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c index 0a05ee87a0fc..455221e8de24 100644 --- a/drivers/soc/mediatek/mtk-cmdq-helper.c +++ b/drivers/soc/mediatek/mtk-cmdq-helper.c @@ -524,23 +524,5 @@ int cmdq_pkt_eoc(struct cmdq_pkt *pkt) } EXPORT_SYMBOL(cmdq_pkt_eoc); -int cmdq_pkt_finalize(struct cmdq_pkt *pkt) -{ - struct cmdq_instruction inst = { {0} }; - int err; - - /* insert EOC and generate IRQ for each command iteration */ - err = cmdq_pkt_eoc(pkt); - if (err < 0) - return err; - - /* JUMP to end */ - inst.op = CMDQ_CODE_JUMP; - inst.value = CMDQ_JUMP_PASS >> - cmdq_get_shift_pa(((struct cmdq_client *)pkt->cl)->chan); - return cmdq_pkt_append_command(pkt, inst); -} -EXPORT_SYMBOL(cmdq_pkt_finalize); - MODULE_DESCRIPTION("MediaTek Command Queue (CMDQ) driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/soc/mediatek/mtk-devapc.c b/drivers/soc/mediatek/mtk-devapc.c index 2a1adcb87d4e..f54c966138b5 100644 --- a/drivers/soc/mediatek/mtk-devapc.c +++ b/drivers/soc/mediatek/mtk-devapc.c @@ -273,23 +273,31 @@ static int mtk_devapc_probe(struct platform_device *pdev) return -EINVAL; devapc_irq = irq_of_parse_and_map(node, 0); - if (!devapc_irq) - return -EINVAL; + if (!devapc_irq) { + ret = -EINVAL; + goto err; + } ctx->infra_clk = devm_clk_get_enabled(&pdev->dev, "devapc-infra-clock"); - if (IS_ERR(ctx->infra_clk)) - return -EINVAL; + if (IS_ERR(ctx->infra_clk)) { + ret = -EINVAL; + goto err; + } ret = devm_request_irq(&pdev->dev, devapc_irq, devapc_violation_irq, IRQF_TRIGGER_NONE, "devapc", ctx); if (ret) - return ret; + goto err; platform_set_drvdata(pdev, ctx); start_devapc(ctx); return 0; + +err: + iounmap(ctx->infra_base); + return ret; } static void mtk_devapc_remove(struct platform_device *pdev) @@ -297,6 +305,7 @@ static void mtk_devapc_remove(struct platform_device *pdev) struct mtk_devapc_context *ctx = platform_get_drvdata(pdev); stop_devapc(ctx); + iounmap(ctx->infra_base); } static struct platform_driver mtk_devapc_driver = { diff --git a/drivers/soc/mediatek/mtk-pmic-wrap.c b/drivers/soc/mediatek/mtk-pmic-wrap.c index 9fdc0ef79202..0bcd85826375 100644 --- a/drivers/soc/mediatek/mtk-pmic-wrap.c +++ b/drivers/soc/mediatek/mtk-pmic-wrap.c @@ -2518,8 +2518,8 @@ static int pwrap_probe(struct platform_device *pdev) } } - ret = devm_clk_bulk_get_all_enable(wrp->dev, &clk); - if (ret) + ret = devm_clk_bulk_get_all_enabled(wrp->dev, &clk); + if (ret < 0) return dev_err_probe(wrp->dev, ret, "failed to get clocks\n"); diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig index 74b9121240f8..58e63cf0036b 100644 --- a/drivers/soc/qcom/Kconfig +++ b/drivers/soc/qcom/Kconfig @@ -139,7 +139,7 @@ config QCOM_RAMP_CTRL config QCOM_RMTFS_MEM tristate "Qualcomm Remote Filesystem memory driver" - depends on ARCH_QCOM + depends on ARCH_QCOM || COMPILE_TEST select QCOM_SCM help The Qualcomm remote filesystem memory driver is used for allocating diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 32c3bc887cef..56823b6a2fac 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -142,6 +142,7 @@ struct qcom_llcc_config { bool skip_llcc_cfg; bool no_edac; bool irq_configured; + bool no_broadcast_register; }; struct qcom_sct_config { @@ -154,6 +155,38 @@ enum llcc_reg_offset { LLCC_COMMON_STATUS0, }; +static const struct llcc_slice_config ipq5424_data[] = { + { + .usecase_id = LLCC_CPUSS, + .slice_id = 1, + .max_cap = 768, + .priority = 1, + .bonus_ways = 0xFFFF, + .retain_on_pc = true, + .activate_on_init = true, + .write_scid_cacheable_en = true, + .stale_en = true, + .stale_cap_en = true, + .alloc_oneway_en = true, + .ovcap_en = true, + .ovcap_prio = true, + .vict_prio = true, + }, + { + .usecase_id = LLCC_VIDSC0, + .slice_id = 2, + .max_cap = 256, + .priority = 2, + .fixed_size = true, + .bonus_ways = 0xF000, + .retain_on_pc = true, + .activate_on_init = true, + .write_scid_cacheable_en = true, + .stale_en = true, + .stale_cap_en = true, + }, +}; + static const struct llcc_slice_config sa8775p_data[] = { { .usecase_id = LLCC_CPUSS, @@ -3004,6 +3037,7 @@ static const struct llcc_slice_config x1e80100_data[] = { .fixed_size = true, .bonus_ways = 0xfff, .cache_mode = 0, + .activate_on_init = true, }, { .usecase_id = LLCC_CAMEXP0, .slice_id = 4, @@ -3185,6 +3219,16 @@ static const struct qcom_llcc_config qdu1000_cfg[] = { }, }; +static const struct qcom_llcc_config ipq5424_cfg[] = { + { + .sct_data = ipq5424_data, + .size = ARRAY_SIZE(ipq5424_data), + .reg_offset = llcc_v2_1_reg_offset, + .edac_reg_offset = &llcc_v2_1_edac_reg_offset, + .no_broadcast_register = true, + }, +}; + static const struct qcom_llcc_config sa8775p_cfg[] = { { .sct_data = sa8775p_data, @@ -3360,6 +3404,11 @@ static const struct qcom_sct_config qdu1000_cfgs = { .num_config = ARRAY_SIZE(qdu1000_cfg), }; +static const struct qcom_sct_config ipq5424_cfgs = { + .llcc_config = ipq5424_cfg, + .num_config = ARRAY_SIZE(ipq5424_cfg), +}; + static const struct qcom_sct_config sa8775p_cfgs = { .llcc_config = sa8775p_cfg, .num_config = ARRAY_SIZE(sa8775p_cfg), @@ -3957,8 +4006,12 @@ static int qcom_llcc_probe(struct platform_device *pdev) drv_data->bcast_regmap = qcom_llcc_init_mmio(pdev, i, "llcc_broadcast_base"); if (IS_ERR(drv_data->bcast_regmap)) { - ret = PTR_ERR(drv_data->bcast_regmap); - goto err; + if (cfg->no_broadcast_register) { + drv_data->bcast_regmap = regmap; + } else { + ret = PTR_ERR(drv_data->bcast_regmap); + goto err; + } } /* Extract version of the IP */ @@ -4029,6 +4082,7 @@ err: } static const struct of_device_id qcom_llcc_of_match[] = { + { .compatible = "qcom,ipq5424-llcc", .data = &ipq5424_cfgs}, { .compatible = "qcom,qcs615-llcc", .data = &qcs615_cfgs}, { .compatible = "qcom,qcs8300-llcc", .data = &qcs8300_cfgs}, { .compatible = "qcom,qdu1000-llcc", .data = &qdu1000_cfgs}, diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c index caf3f63d940e..052c292eeda6 100644 --- a/drivers/soc/qcom/pmic_glink.c +++ b/drivers/soc/qcom/pmic_glink.c @@ -4,6 +4,7 @@ * Copyright (c) 2022, Linaro Ltd */ #include +#include #include #include #include @@ -100,15 +101,13 @@ void pmic_glink_client_register(struct pmic_glink_client *client) struct pmic_glink *pg = client->pg; unsigned long flags; - mutex_lock(&pg->state_lock); + guard(mutex)(&pg->state_lock); spin_lock_irqsave(&pg->client_lock, flags); list_add(&client->node, &pg->clients); client->pdr_notify(client->priv, pg->client_state); spin_unlock_irqrestore(&pg->client_lock, flags); - mutex_unlock(&pg->state_lock); - } EXPORT_SYMBOL_GPL(pmic_glink_client_register); @@ -119,26 +118,25 @@ int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len) unsigned long start; int ret; - mutex_lock(&pg->state_lock); + guard(mutex)(&pg->state_lock); if (!pg->ept) { - ret = -ECONNRESET; - } else { - start = jiffies; - for (;;) { - ret = rpmsg_send(pg->ept, data, len); - if (ret != -EAGAIN) - break; + return -ECONNRESET; + } - if (timeout_reached) { - ret = -ETIMEDOUT; - break; - } + start = jiffies; + for (;;) { + ret = rpmsg_send(pg->ept, data, len); + if (ret != -EAGAIN) + break; - usleep_range(1000, 5000); - timeout_reached = time_after(jiffies, start + PMIC_GLINK_SEND_TIMEOUT); + if (timeout_reached) { + ret = -ETIMEDOUT; + break; } + + usleep_range(1000, 5000); + timeout_reached = time_after(jiffies, start + PMIC_GLINK_SEND_TIMEOUT); } - mutex_unlock(&pg->state_lock); return ret; } @@ -227,51 +225,42 @@ static void pmic_glink_pdr_callback(int state, char *svc_path, void *priv) { struct pmic_glink *pg = priv; - mutex_lock(&pg->state_lock); + guard(mutex)(&pg->state_lock); pg->pdr_state = state; pmic_glink_state_notify_clients(pg); - mutex_unlock(&pg->state_lock); } static int pmic_glink_rpmsg_probe(struct rpmsg_device *rpdev) { struct pmic_glink *pg = __pmic_glink; - int ret = 0; - mutex_lock(&__pmic_glink_lock); - if (!pg) { - ret = dev_err_probe(&rpdev->dev, -ENODEV, "no pmic_glink device to attach to\n"); - goto out_unlock; - } + guard(mutex)(&__pmic_glink_lock); + pg = __pmic_glink; + if (!pg) + return dev_err_probe(&rpdev->dev, -ENODEV, "no pmic_glink device to attach to\n"); dev_set_drvdata(&rpdev->dev, pg); - mutex_lock(&pg->state_lock); + guard(mutex)(&pg->state_lock); pg->ept = rpdev->ept; pmic_glink_state_notify_clients(pg); - mutex_unlock(&pg->state_lock); -out_unlock: - mutex_unlock(&__pmic_glink_lock); - return ret; + return 0; } static void pmic_glink_rpmsg_remove(struct rpmsg_device *rpdev) { struct pmic_glink *pg; - mutex_lock(&__pmic_glink_lock); + guard(mutex)(&__pmic_glink_lock); pg = __pmic_glink; if (!pg) - goto out_unlock; + return; - mutex_lock(&pg->state_lock); + guard(mutex)(&pg->state_lock); pg->ept = NULL; pmic_glink_state_notify_clients(pg); - mutex_unlock(&pg->state_lock); -out_unlock: - mutex_unlock(&__pmic_glink_lock); } static const struct rpmsg_device_id pmic_glink_rpmsg_id_match[] = { @@ -378,9 +367,8 @@ static void pmic_glink_remove(struct platform_device *pdev) if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI)) pmic_glink_del_aux_device(pg, &pg->ucsi_aux); - mutex_lock(&__pmic_glink_lock); + guard(mutex)(&__pmic_glink_lock); __pmic_glink = NULL; - mutex_unlock(&__pmic_glink_lock); } static const unsigned long pmic_glink_sc8280xp_client_mask = BIT(PMIC_GLINK_CLIENT_BATT) | diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c index 463b1c528831..bd06ce161804 100644 --- a/drivers/soc/qcom/pmic_glink_altmode.c +++ b/drivers/soc/qcom/pmic_glink_altmode.c @@ -5,6 +5,7 @@ */ #include #include +#include #include #include #include @@ -114,7 +115,7 @@ static int pmic_glink_altmode_request(struct pmic_glink_altmode *altmode, u32 cm * The USBC_CMD_WRITE_REQ ack doesn't identify the request, so wait for * one ack at a time. */ - mutex_lock(&altmode->lock); + guard(mutex)(&altmode->lock); req.hdr.owner = cpu_to_le32(altmode->owner_id); req.hdr.type = cpu_to_le32(PMIC_GLINK_REQ_RESP); @@ -125,18 +126,16 @@ static int pmic_glink_altmode_request(struct pmic_glink_altmode *altmode, u32 cm ret = pmic_glink_send(altmode->client, &req, sizeof(req)); if (ret) { dev_err(altmode->dev, "failed to send altmode request: %#x (%d)\n", cmd, ret); - goto out_unlock; + return ret; } left = wait_for_completion_timeout(&altmode->pan_ack, 5 * HZ); if (!left) { dev_err(altmode->dev, "timeout waiting for altmode request ack for: %#x\n", cmd); - ret = -ETIMEDOUT; + return -ETIMEDOUT; } -out_unlock: - mutex_unlock(&altmode->lock); - return ret; + return 0; } static void pmic_glink_altmode_enable_dp(struct pmic_glink_altmode *altmode, diff --git a/drivers/soc/qcom/qcom_pd_mapper.c b/drivers/soc/qcom/qcom_pd_mapper.c index 6e30f08761aa..154ca5beb471 100644 --- a/drivers/soc/qcom/qcom_pd_mapper.c +++ b/drivers/soc/qcom/qcom_pd_mapper.c @@ -553,6 +553,7 @@ static const struct of_device_id qcom_pdm_domains[] __maybe_unused = { { .compatible = "qcom,sm4250", .data = sm6115_domains, }, { .compatible = "qcom,sm6115", .data = sm6115_domains, }, { .compatible = "qcom,sm6350", .data = sm6350_domains, }, + { .compatible = "qcom,sm7225", .data = sm6350_domains, }, { .compatible = "qcom,sm7325", .data = sc7280_domains, }, { .compatible = "qcom,sm8150", .data = sm8150_domains, }, { .compatible = "qcom,sm8250", .data = sm8250_domains, }, @@ -561,6 +562,7 @@ static const struct of_device_id qcom_pdm_domains[] __maybe_unused = { { .compatible = "qcom,sm8550", .data = sm8550_domains, }, { .compatible = "qcom,sm8650", .data = sm8550_domains, }, { .compatible = "qcom,x1e80100", .data = x1e80100_domains, }, + { .compatible = "qcom,x1p42100", .data = x1e80100_domains, }, {}, }; diff --git a/drivers/soc/qcom/rmtfs_mem.c b/drivers/soc/qcom/rmtfs_mem.c index 33603b8fd8f3..1b32469f2789 100644 --- a/drivers/soc/qcom/rmtfs_mem.c +++ b/drivers/soc/qcom/rmtfs_mem.c @@ -125,7 +125,7 @@ static int qcom_rmtfs_mem_release(struct inode *inode, struct file *filp) return 0; } -static struct class rmtfs_class = { +static const struct class rmtfs_class = { .name = "rmtfs", }; diff --git a/drivers/soc/qcom/smem_state.c b/drivers/soc/qcom/smem_state.c index d9bfac6c54fb..cc5be8019b6a 100644 --- a/drivers/soc/qcom/smem_state.c +++ b/drivers/soc/qcom/smem_state.c @@ -112,7 +112,8 @@ struct qcom_smem_state *qcom_smem_state_get(struct device *dev, if (args.args_count != 1) { dev_err(dev, "invalid #qcom,smem-state-cells\n"); - return ERR_PTR(-EINVAL); + state = ERR_PTR(-EINVAL); + goto put; } state = of_node_to_state(args.np); diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c index 62fadfe44a09..18d7f1be9093 100644 --- a/drivers/soc/qcom/socinfo.c +++ b/drivers/soc/qcom/socinfo.c @@ -451,6 +451,7 @@ static const struct soc_id soc_id[] = { { qcom_board_id(QCS9100) }, { qcom_board_id(QCS8300) }, { qcom_board_id(QCS8275) }, + { qcom_board_id(QCS9075) }, { qcom_board_id(QCS615) }, }; @@ -796,7 +797,7 @@ static int qcom_socinfo_probe(struct platform_device *pdev) if (!qs->attr.soc_id || !qs->attr.revision) return -ENOMEM; - if (offsetof(struct socinfo, serial_num) <= item_size) { + if (offsetofend(struct socinfo, serial_num) <= item_size) { qs->attr.serial_number = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%u", le32_to_cpu(info->serial_num)); diff --git a/drivers/soc/renesas/Kconfig b/drivers/soc/renesas/Kconfig index 9f7fe02310b9..6d2e135eed89 100644 --- a/drivers/soc/renesas/Kconfig +++ b/drivers/soc/renesas/Kconfig @@ -345,6 +345,11 @@ config ARCH_R9A09G011 help This enables support for the Renesas RZ/V2M SoC. +config ARCH_R9A09G047 + bool "ARM64 Platform support for RZ/G3E" + help + This enables support for the Renesas RZ/G3E SoC variants. + config ARCH_R9A09G057 bool "ARM64 Platform support for RZ/V2H(P)" select RENESAS_RZV2H_ICU diff --git a/drivers/soc/samsung/exynos-pmu.c b/drivers/soc/samsung/exynos-pmu.c index d8c53cec7f37..dd5256e5aae1 100644 --- a/drivers/soc/samsung/exynos-pmu.c +++ b/drivers/soc/samsung/exynos-pmu.c @@ -126,7 +126,7 @@ static int tensor_set_bits_atomic(void *ctx, unsigned int offset, u32 val, if (ret) return ret; } - return ret; + return 0; } static bool tensor_is_atomic(unsigned int reg) diff --git a/drivers/soc/tegra/cbb/tegra-cbb.c b/drivers/soc/tegra/cbb/tegra-cbb.c index 84ab46c9d9f5..6215c6a84fbe 100644 --- a/drivers/soc/tegra/cbb/tegra-cbb.c +++ b/drivers/soc/tegra/cbb/tegra-cbb.c @@ -69,19 +69,12 @@ static int tegra_cbb_err_show(struct seq_file *file, void *data) } DEFINE_SHOW_ATTRIBUTE(tegra_cbb_err); -static int tegra_cbb_err_debugfs_init(struct tegra_cbb *cbb) +static void tegra_cbb_err_debugfs_init(struct tegra_cbb *cbb) { static struct dentry *root; - if (!root) { + if (!root) root = debugfs_create_file("tegra_cbb_err", 0444, NULL, cbb, &tegra_cbb_err_fops); - if (IS_ERR_OR_NULL(root)) { - pr_err("%s(): could not create debugfs node\n", __func__); - return PTR_ERR(root); - } - } - - return 0; } void tegra_cbb_stall_enable(struct tegra_cbb *cbb) @@ -148,13 +141,8 @@ int tegra_cbb_register(struct tegra_cbb *cbb) { int ret; - if (IS_ENABLED(CONFIG_DEBUG_FS)) { - ret = tegra_cbb_err_debugfs_init(cbb); - if (ret) { - dev_err(cbb->dev, "failed to create debugfs\n"); - return ret; - } - } + if (IS_ENABLED(CONFIG_DEBUG_FS)) + tegra_cbb_err_debugfs_init(cbb); /* register interrupt handler for errors due to different initiators */ ret = cbb->ops->interrupt_enable(cbb); diff --git a/drivers/soc/tegra/cbb/tegra234-cbb.c b/drivers/soc/tegra/cbb/tegra234-cbb.c index 5cf0e8c34164..c74629af9bb5 100644 --- a/drivers/soc/tegra/cbb/tegra234-cbb.c +++ b/drivers/soc/tegra/cbb/tegra234-cbb.c @@ -277,7 +277,7 @@ static void tegra234_lookup_slave_timeout(struct seq_file *file, struct tegra234 * which timed out. * a) Get block number from the index of set bit in * _SN_AXI2APB_<>_BLOCK_TMO_STATUS_0 register. - * b) Get address of register repective to block number i.e. + * b) Get address of register respective to block number i.e. * _SN_AXI2APB_<>_BLOCK_TMO_0. * c) Read the register in above step to get client_id which * timed out as per the set bits. diff --git a/drivers/soc/tegra/fuse/fuse-tegra30.c b/drivers/soc/tegra/fuse/fuse-tegra30.c index eb14e5ff5a0a..e24ab5f7d2bf 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra30.c +++ b/drivers/soc/tegra/fuse/fuse-tegra30.c @@ -647,15 +647,20 @@ static const struct nvmem_cell_lookup tegra234_fuse_lookups[] = { }; static const struct nvmem_keepout tegra234_fuse_keepouts[] = { - { .start = 0x01c, .end = 0x0c8 }, - { .start = 0x12c, .end = 0x184 }, + { .start = 0x01c, .end = 0x064 }, + { .start = 0x084, .end = 0x0a0 }, + { .start = 0x0a4, .end = 0x0c8 }, + { .start = 0x12c, .end = 0x164 }, + { .start = 0x16c, .end = 0x184 }, { .start = 0x190, .end = 0x198 }, { .start = 0x1a0, .end = 0x204 }, - { .start = 0x21c, .end = 0x250 }, - { .start = 0x25c, .end = 0x2f0 }, + { .start = 0x21c, .end = 0x2f0 }, { .start = 0x310, .end = 0x3d8 }, - { .start = 0x400, .end = 0x4f0 }, - { .start = 0x4f8, .end = 0x7e8 }, + { .start = 0x400, .end = 0x420 }, + { .start = 0x444, .end = 0x490 }, + { .start = 0x4bc, .end = 0x4f0 }, + { .start = 0x4f8, .end = 0x54c }, + { .start = 0x57c, .end = 0x7e8 }, { .start = 0x8d0, .end = 0x8d8 }, { .start = 0xacc, .end = 0xf00 } }; diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index 96a7f9709720..5a54b10daf77 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -384,7 +384,7 @@ static u32 amd_sdw_read_ping_status(struct sdw_bus *bus) return slave_stat; } -static int amd_sdw_compute_params(struct sdw_bus *bus) +static int amd_sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { struct sdw_transport_data t_data = {0}; struct sdw_master_runtime *m_rt; @@ -410,7 +410,7 @@ static int amd_sdw_compute_params(struct sdw_bus *bus) sdw_fill_xport_params(&p_rt->transport_params, p_rt->num, false, SDW_BLK_GRP_CNT_1, sample_int, port_bo, port_bo >> 8, hstart, hstop, - SDW_BLK_PKG_PER_PORT, 0x0); + SDW_BLK_PKG_PER_PORT, p_rt->lane); sdw_fill_port_params(&p_rt->port_params, p_rt->num, bps, @@ -1190,6 +1190,7 @@ static int __maybe_unused amd_resume_runtime(struct device *dev) if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { return amd_sdw_clock_stop_exit(amd_manager); } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { + writel(0x00, amd_manager->acp_mmio + ACP_SW_WAKE_EN(amd_manager->instance)); val = readl(amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL); if (val) { val |= AMD_SDW_CLK_RESUME_REQ; diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index d1dc62c34f1c..9b295fc9acd5 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -813,6 +813,16 @@ void sdw_extract_slave_id(struct sdw_bus *bus, } EXPORT_SYMBOL(sdw_extract_slave_id); +bool is_clock_scaling_supported_by_slave(struct sdw_slave *slave) +{ + /* + * Dynamic scaling is a defined by SDCA. However, some devices expose the class ID but + * can't support dynamic scaling. We might need a quirk to handle such devices. + */ + return slave->id.class_id; +} +EXPORT_SYMBOL(is_clock_scaling_supported_by_slave); + static int sdw_program_device_num(struct sdw_bus *bus, bool *programmed) { u8 buf[SDW_NUM_DEV_ID_REGISTERS] = {0}; @@ -1276,23 +1286,12 @@ int sdw_configure_dpn_intr(struct sdw_slave *slave, return ret; } -static int sdw_slave_set_frequency(struct sdw_slave *slave) +int sdw_slave_get_scale_index(struct sdw_slave *slave, u8 *base) { u32 mclk_freq = slave->bus->prop.mclk_freq; u32 curr_freq = slave->bus->params.curr_dr_freq >> 1; unsigned int scale; u8 scale_index; - u8 base; - int ret; - - /* - * frequency base and scale registers are required for SDCA - * devices. They may also be used for 1.2+/non-SDCA devices. - * Driver can set the property, we will need a DisCo property - * to discover this case from platform firmware. - */ - if (!slave->id.class_id && !slave->prop.clock_reg_supported) - return 0; if (!mclk_freq) { dev_err(&slave->dev, @@ -1311,19 +1310,19 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave) */ if (!(19200000 % mclk_freq)) { mclk_freq = 19200000; - base = SDW_SCP_BASE_CLOCK_19200000_HZ; + *base = SDW_SCP_BASE_CLOCK_19200000_HZ; } else if (!(22579200 % mclk_freq)) { mclk_freq = 22579200; - base = SDW_SCP_BASE_CLOCK_22579200_HZ; + *base = SDW_SCP_BASE_CLOCK_22579200_HZ; } else if (!(24576000 % mclk_freq)) { mclk_freq = 24576000; - base = SDW_SCP_BASE_CLOCK_24576000_HZ; + *base = SDW_SCP_BASE_CLOCK_24576000_HZ; } else if (!(32000000 % mclk_freq)) { mclk_freq = 32000000; - base = SDW_SCP_BASE_CLOCK_32000000_HZ; + *base = SDW_SCP_BASE_CLOCK_32000000_HZ; } else if (!(96000000 % mclk_freq)) { mclk_freq = 24000000; - base = SDW_SCP_BASE_CLOCK_24000000_HZ; + *base = SDW_SCP_BASE_CLOCK_24000000_HZ; } else { dev_err(&slave->dev, "Unsupported clock base, mclk %d\n", @@ -1354,6 +1353,34 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave) } scale_index++; + dev_dbg(&slave->dev, + "Configured bus base %d, scale %d, mclk %d, curr_freq %d\n", + *base, scale_index, mclk_freq, curr_freq); + + return scale_index; +} +EXPORT_SYMBOL(sdw_slave_get_scale_index); + +static int sdw_slave_set_frequency(struct sdw_slave *slave) +{ + int scale_index; + u8 base; + int ret; + + /* + * frequency base and scale registers are required for SDCA + * devices. They may also be used for 1.2+/non-SDCA devices. + * Driver can set the property directly, for now there's no + * DisCo property to discover support for the scaling registers + * from platform firmware. + */ + if (!slave->id.class_id && !slave->prop.clock_reg_supported) + return 0; + + scale_index = sdw_slave_get_scale_index(slave, &base); + if (scale_index < 0) + return scale_index; + ret = sdw_write_no_pm(slave, SDW_SCP_BUS_CLOCK_BASE, base); if (ret < 0) { dev_err(&slave->dev, @@ -1373,10 +1400,6 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave) dev_err(&slave->dev, "SDW_SCP_BUSCLOCK_SCALE_B1 write failed:%d\n", ret); - dev_dbg(&slave->dev, - "Configured bus base %d, scale %d, mclk %d, curr_freq %d\n", - base, scale_index, mclk_freq, curr_freq); - return ret; } diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h index fda6b24ac2da..fc990171b3f7 100644 --- a/drivers/soundwire/bus.h +++ b/drivers/soundwire/bus.h @@ -90,6 +90,7 @@ int sdw_find_col_index(int col); * @transport_params: Transport parameters * @port_params: Port parameters * @port_node: List node for Master or Slave port_list + * @lane: Which lane is used * * SoundWire spec has no mention of ports for Master interface but the * concept is logically extended. @@ -100,6 +101,7 @@ struct sdw_port_runtime { struct sdw_transport_params transport_params; struct sdw_port_params port_params; struct list_head port_node; + unsigned int lane; }; /** @@ -149,6 +151,7 @@ struct sdw_transport_data { int hstop; int block_offset; int sub_block_offset; + unsigned int lane; }; struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave, diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index 77dc094075e1..e98d5db81b1c 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -167,9 +167,6 @@ static int sdw_drv_remove(struct device *dev) slave->probed = false; - if (slave->prop.use_domain_irq) - sdw_irq_dispose_mapping(slave); - mutex_unlock(&slave->sdw_dev_lock); if (drv->remove) diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c index b9316207c3ab..59965f43c2fb 100644 --- a/drivers/soundwire/generic_bandwidth_allocation.c +++ b/drivers/soundwire/generic_bandwidth_allocation.c @@ -18,6 +18,7 @@ struct sdw_group_params { unsigned int rate; + unsigned int lane; int full_bw; int payload_bw; int hwidth; @@ -27,6 +28,7 @@ struct sdw_group { unsigned int count; unsigned int max_size; unsigned int *rates; + unsigned int *lanes; }; void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, @@ -48,6 +50,9 @@ void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, slave_total_ch = 0; list_for_each_entry(p_rt, &s_rt->port_list, port_node) { + if (p_rt->lane != t_data->lane) + continue; + ch = hweight32(p_rt->ch_mask); sdw_fill_xport_params(&p_rt->transport_params, @@ -56,7 +61,7 @@ void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, sample_int, port_bo, port_bo >> 8, t_data->hstart, t_data->hstop, - SDW_BLK_PKG_PER_PORT, 0x0); + SDW_BLK_PKG_PER_PORT, p_rt->lane); sdw_fill_port_params(&p_rt->port_params, p_rt->num, bps, @@ -105,11 +110,13 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt, t_data.hstart = hstart; list_for_each_entry(p_rt, &m_rt->port_list, port_node) { + if (p_rt->lane != params->lane) + continue; sdw_fill_xport_params(&p_rt->transport_params, p_rt->num, false, SDW_BLK_GRP_CNT_1, sample_int, *port_bo, (*port_bo) >> 8, hstart, hstop, - SDW_BLK_PKG_PER_PORT, 0x0); + SDW_BLK_PKG_PER_PORT, p_rt->lane); sdw_fill_port_params(&p_rt->port_params, p_rt->num, bps, @@ -131,6 +138,7 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt, (*port_bo) += bps * ch; } + t_data.lane = params->lane; sdw_compute_slave_ports(m_rt, &t_data); } @@ -138,69 +146,107 @@ static void _sdw_compute_port_params(struct sdw_bus *bus, struct sdw_group_params *params, int count) { struct sdw_master_runtime *m_rt; - int hstop = bus->params.col - 1; - int port_bo, i; + int port_bo, i, l; + int hstop; /* Run loop for all groups to compute transport parameters */ - for (i = 0; i < count; i++) { - port_bo = 1; + for (l = 0; l < SDW_MAX_LANES; l++) { + if (l > 0 && !bus->lane_used_bandwidth[l]) + continue; + /* reset hstop for each lane */ + hstop = bus->params.col - 1; + for (i = 0; i < count; i++) { + if (params[i].lane != l) + continue; + port_bo = 1; - list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { - sdw_compute_master_ports(m_rt, ¶ms[i], &port_bo, hstop); + list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { + sdw_compute_master_ports(m_rt, ¶ms[i], &port_bo, hstop); + } + + hstop = hstop - params[i].hwidth; } - - hstop = hstop - params[i].hwidth; } } static int sdw_compute_group_params(struct sdw_bus *bus, + struct sdw_stream_runtime *stream, struct sdw_group_params *params, - int *rates, int count) + struct sdw_group *group) { struct sdw_master_runtime *m_rt; + struct sdw_port_runtime *p_rt; int sel_col = bus->params.col; unsigned int rate, bps, ch; - int i, column_needed = 0; + int i, l, column_needed; /* Calculate bandwidth per group */ - for (i = 0; i < count; i++) { - params[i].rate = rates[i]; + for (i = 0; i < group->count; i++) { + params[i].rate = group->rates[i]; + params[i].lane = group->lanes[i]; params[i].full_bw = bus->params.curr_dr_freq / params[i].rate; } list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { - rate = m_rt->stream->params.rate; - bps = m_rt->stream->params.bps; - ch = m_rt->ch_count; + if (m_rt->stream == stream) { + /* Only runtime during prepare should be added */ + if (stream->state != SDW_STREAM_CONFIGURED) + continue; + } else { + /* + * Include runtimes with running (ENABLED state) and paused (DISABLED state) + * streams + */ + if (m_rt->stream->state != SDW_STREAM_ENABLED && + m_rt->stream->state != SDW_STREAM_DISABLED) + continue; + } + list_for_each_entry(p_rt, &m_rt->port_list, port_node) { + rate = m_rt->stream->params.rate; + bps = m_rt->stream->params.bps; + ch = hweight32(p_rt->ch_mask); - for (i = 0; i < count; i++) { - if (rate == params[i].rate) - params[i].payload_bw += bps * ch; + for (i = 0; i < group->count; i++) { + if (rate == params[i].rate && p_rt->lane == params[i].lane) + params[i].payload_bw += bps * ch; + } } } - for (i = 0; i < count; i++) { - params[i].hwidth = (sel_col * - params[i].payload_bw + params[i].full_bw - 1) / - params[i].full_bw; + for (l = 0; l < SDW_MAX_LANES; l++) { + if (l > 0 && !bus->lane_used_bandwidth[l]) + continue; + /* reset column_needed for each lane */ + column_needed = 0; + for (i = 0; i < group->count; i++) { + if (params[i].lane != l) + continue; - column_needed += params[i].hwidth; + params[i].hwidth = (sel_col * params[i].payload_bw + + params[i].full_bw - 1) / params[i].full_bw; + + column_needed += params[i].hwidth; + /* There is no control column for lane 1 and above */ + if (column_needed > sel_col) + return -EINVAL; + /* Column 0 is control column on lane 0 */ + if (params[i].lane == 0 && column_needed > sel_col - 1) + return -EINVAL; + } } - if (column_needed > sel_col - 1) - return -EINVAL; return 0; } static int sdw_add_element_group_count(struct sdw_group *group, - unsigned int rate) + unsigned int rate, unsigned int lane) { int num = group->count; int i; for (i = 0; i <= num; i++) { - if (rate == group->rates[i]) + if (rate == group->rates[i] && lane == group->lanes[i]) break; if (i != num) @@ -208,6 +254,7 @@ static int sdw_add_element_group_count(struct sdw_group *group, if (group->count >= group->max_size) { unsigned int *rates; + unsigned int *lanes; group->max_size += 1; rates = krealloc(group->rates, @@ -215,10 +262,20 @@ static int sdw_add_element_group_count(struct sdw_group *group, GFP_KERNEL); if (!rates) return -ENOMEM; + group->rates = rates; + + lanes = krealloc(group->lanes, + (sizeof(int) * group->max_size), + GFP_KERNEL); + if (!lanes) + return -ENOMEM; + + group->lanes = lanes; } - group->rates[group->count++] = rate; + group->rates[group->count] = rate; + group->lanes[group->count++] = lane; } return 0; @@ -228,6 +285,7 @@ static int sdw_get_group_count(struct sdw_bus *bus, struct sdw_group *group) { struct sdw_master_runtime *m_rt; + struct sdw_port_runtime *p_rt; unsigned int rate; int ret = 0; @@ -237,17 +295,32 @@ static int sdw_get_group_count(struct sdw_bus *bus, if (!group->rates) return -ENOMEM; + group->lanes = kcalloc(group->max_size, sizeof(int), GFP_KERNEL); + if (!group->lanes) { + kfree(group->rates); + group->rates = NULL; + return -ENOMEM; + } + list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { + if (m_rt->stream->state == SDW_STREAM_DEPREPARED) + continue; + rate = m_rt->stream->params.rate; if (m_rt == list_first_entry(&bus->m_rt_list, struct sdw_master_runtime, bus_node)) { group->rates[group->count++] = rate; - - } else { - ret = sdw_add_element_group_count(group, rate); + } + /* + * Different ports could use different lane, add group element + * even if m_rt is the first entry + */ + list_for_each_entry(p_rt, &m_rt->port_list, port_node) { + ret = sdw_add_element_group_count(group, rate, p_rt->lane); if (ret < 0) { kfree(group->rates); + kfree(group->lanes); return ret; } } @@ -260,8 +333,9 @@ static int sdw_get_group_count(struct sdw_bus *bus, * sdw_compute_port_params: Compute transport and port parameters * * @bus: SDW Bus instance + * @stream: Soundwire stream */ -static int sdw_compute_port_params(struct sdw_bus *bus) +static int sdw_compute_port_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { struct sdw_group_params *params = NULL; struct sdw_group group; @@ -281,8 +355,7 @@ static int sdw_compute_port_params(struct sdw_bus *bus) } /* Compute transport parameters for grouped streams */ - ret = sdw_compute_group_params(bus, params, - &group.rates[0], group.count); + ret = sdw_compute_group_params(bus, stream, params, &group); if (ret < 0) goto free_params; @@ -292,6 +365,7 @@ free_params: kfree(params); out: kfree(group.rates); + kfree(group.lanes); return ret; } @@ -299,7 +373,6 @@ out: static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq) { struct sdw_master_prop *prop = &bus->prop; - int frame_int, frame_freq; int r, c; for (c = 0; c < SDW_FRAME_COLS; c++) { @@ -308,11 +381,8 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq) sdw_cols[c] != prop->default_col) continue; - frame_int = sdw_rows[r] * sdw_cols[c]; - frame_freq = clk_freq / frame_int; - - if ((clk_freq - (frame_freq * SDW_FRAME_CTRL_BITS)) < - bus->params.bandwidth) + if (clk_freq * (sdw_cols[c] - 1) < + bus->params.bandwidth * sdw_cols[c]) continue; bus->params.row = sdw_rows[r]; @@ -324,6 +394,95 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq) return -EINVAL; } +static bool is_clock_scaling_supported(struct sdw_bus *bus) +{ + struct sdw_master_runtime *m_rt; + struct sdw_slave_runtime *s_rt; + + list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) + list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) + if (!is_clock_scaling_supported_by_slave(s_rt->slave)) + return false; + + return true; +} + +/** + * is_lane_connected_to_all_peripherals: Check if the given manager lane connects to all peripherals + * So that all peripherals can use the manager lane. + * + * @m_rt: Manager runtime + * @lane: Lane number + */ +static bool is_lane_connected_to_all_peripherals(struct sdw_master_runtime *m_rt, unsigned int lane) +{ + struct sdw_slave_prop *slave_prop; + struct sdw_slave_runtime *s_rt; + int i; + + list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) { + slave_prop = &s_rt->slave->prop; + for (i = 1; i < SDW_MAX_LANES; i++) { + if (slave_prop->lane_maps[i] == lane) { + dev_dbg(&s_rt->slave->dev, + "M lane %d is connected to P lane %d\n", + lane, i); + break; + } + } + if (i == SDW_MAX_LANES) { + dev_dbg(&s_rt->slave->dev, "M lane %d is not connected\n", lane); + return false; + } + } + return true; +} + +static int get_manager_lane(struct sdw_bus *bus, struct sdw_master_runtime *m_rt, + struct sdw_slave_runtime *s_rt, unsigned int curr_dr_freq) +{ + struct sdw_slave_prop *slave_prop = &s_rt->slave->prop; + struct sdw_port_runtime *m_p_rt; + unsigned int required_bandwidth; + int m_lane; + int l; + + for (l = 1; l < SDW_MAX_LANES; l++) { + if (!slave_prop->lane_maps[l]) + continue; + + required_bandwidth = 0; + list_for_each_entry(m_p_rt, &m_rt->port_list, port_node) { + required_bandwidth += m_rt->stream->params.rate * + hweight32(m_p_rt->ch_mask) * + m_rt->stream->params.bps; + } + if (required_bandwidth <= + curr_dr_freq - bus->lane_used_bandwidth[l]) { + /* Check if m_lane is connected to all Peripherals */ + if (!is_lane_connected_to_all_peripherals(m_rt, + slave_prop->lane_maps[l])) { + dev_dbg(bus->dev, + "Not all Peripherals are connected to M lane %d\n", + slave_prop->lane_maps[l]); + continue; + } + m_lane = slave_prop->lane_maps[l]; + dev_dbg(&s_rt->slave->dev, "M lane %d is used\n", m_lane); + bus->lane_used_bandwidth[l] += required_bandwidth; + /* + * Use non-zero manager lane, subtract the lane 0 + * bandwidth that is already calculated + */ + bus->params.bandwidth -= required_bandwidth; + return m_lane; + } + } + + /* No available multi lane found, only lane 0 can be used */ + return 0; +} + /** * sdw_compute_bus_params: Compute bus parameters * @@ -331,10 +490,16 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq) */ static int sdw_compute_bus_params(struct sdw_bus *bus) { - unsigned int curr_dr_freq = 0; struct sdw_master_prop *mstr_prop = &bus->prop; - int i, clk_values, ret; + struct sdw_slave_prop *slave_prop; + struct sdw_port_runtime *m_p_rt; + struct sdw_port_runtime *s_p_rt; + struct sdw_master_runtime *m_rt; + struct sdw_slave_runtime *s_rt; + unsigned int curr_dr_freq = 0; + int i, l, clk_values, ret; bool is_gear = false; + int m_lane = 0; u32 *clk_buf; if (mstr_prop->num_clk_gears) { @@ -349,6 +514,10 @@ static int sdw_compute_bus_params(struct sdw_bus *bus) clk_buf = NULL; } + /* If dynamic scaling is not supported, don't try higher freq */ + if (!is_clock_scaling_supported(bus)) + clk_values = 1; + for (i = 0; i < clk_values; i++) { if (!clk_buf) curr_dr_freq = bus->params.max_dr_freq; @@ -357,10 +526,26 @@ static int sdw_compute_bus_params(struct sdw_bus *bus) (bus->params.max_dr_freq >> clk_buf[i]) : clk_buf[i] * SDW_DOUBLE_RATE_FACTOR; - if (curr_dr_freq <= bus->params.bandwidth) - continue; + if (curr_dr_freq * (mstr_prop->default_col - 1) >= + bus->params.bandwidth * mstr_prop->default_col) + break; - break; + list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { + /* + * Get the first s_rt that will be used to find the available lane that + * can be used. No need to check all Peripherals because we can't use + * multi-lane if we can't find any available lane for the first Peripheral. + */ + s_rt = list_first_entry(&m_rt->slave_rt_list, + struct sdw_slave_runtime, m_rt_node); + + /* + * Find the available Manager lane that connected to the first Peripheral. + */ + m_lane = get_manager_lane(bus, m_rt, s_rt, curr_dr_freq); + if (m_lane > 0) + goto out; + } /* * TODO: Check all the Slave(s) port(s) audio modes and find @@ -374,6 +559,38 @@ static int sdw_compute_bus_params(struct sdw_bus *bus) __func__, bus->params.bandwidth); return -EINVAL; } +out: + /* multilane can be used */ + if (m_lane > 0) { + /* Set Peripheral lanes */ + list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) { + slave_prop = &s_rt->slave->prop; + for (l = 1; l < SDW_MAX_LANES; l++) { + if (slave_prop->lane_maps[l] == m_lane) { + list_for_each_entry(s_p_rt, &s_rt->port_list, port_node) { + s_p_rt->lane = l; + dev_dbg(&s_rt->slave->dev, + "Set P lane %d for port %d\n", + l, s_p_rt->num); + } + break; + } + } + } + /* + * Set Manager lanes. Configure the last m_rt in bus->m_rt_list only since + * we don't want to touch other m_rts that are already working. + */ + list_for_each_entry(m_p_rt, &m_rt->port_list, port_node) { + m_p_rt->lane = m_lane; + } + } + + if (!mstr_prop->default_frame_rate || !mstr_prop->default_row) + return -EINVAL; + + mstr_prop->default_col = curr_dr_freq / mstr_prop->default_frame_rate / + mstr_prop->default_row; ret = sdw_select_row_col(bus, curr_dr_freq); if (ret < 0) { @@ -390,8 +607,9 @@ static int sdw_compute_bus_params(struct sdw_bus *bus) * sdw_compute_params: Compute bus, transport and port parameters * * @bus: SDW Bus instance + * @stream: Soundwire stream */ -int sdw_compute_params(struct sdw_bus *bus) +int sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { int ret; @@ -401,7 +619,7 @@ int sdw_compute_params(struct sdw_bus *bus) return ret; /* Compute transport and port params */ - ret = sdw_compute_port_params(bus); + ret = sdw_compute_port_params(bus, stream); if (ret < 0) { dev_err(bus->dev, "Compute transport params failed: %d\n", ret); return ret; diff --git a/drivers/soundwire/irq.c b/drivers/soundwire/irq.c index 0c08cebb1235..c237e6d0766b 100644 --- a/drivers/soundwire/irq.c +++ b/drivers/soundwire/irq.c @@ -46,14 +46,18 @@ void sdw_irq_delete(struct sdw_bus *bus) irq_domain_remove(bus->domain); } +static void sdw_irq_dispose_mapping(void *data) +{ + struct sdw_slave *slave = data; + + irq_dispose_mapping(irq_find_mapping(slave->bus->domain, slave->dev_num)); +} + void sdw_irq_create_mapping(struct sdw_slave *slave) { slave->irq = irq_create_mapping(slave->bus->domain, slave->dev_num); if (!slave->irq) dev_warn(&slave->dev, "Failed to map IRQ\n"); -} -void sdw_irq_dispose_mapping(struct sdw_slave *slave) -{ - irq_dispose_mapping(irq_find_mapping(slave->bus->domain, slave->dev_num)); + devm_add_action_or_reset(&slave->dev, sdw_irq_dispose_mapping, slave); } diff --git a/drivers/soundwire/irq.h b/drivers/soundwire/irq.h index 58a58046d92b..86e2318409da 100644 --- a/drivers/soundwire/irq.h +++ b/drivers/soundwire/irq.h @@ -16,7 +16,6 @@ int sdw_irq_create(struct sdw_bus *bus, struct fwnode_handle *fwnode); void sdw_irq_delete(struct sdw_bus *bus); void sdw_irq_create_mapping(struct sdw_slave *slave); -void sdw_irq_dispose_mapping(struct sdw_slave *slave); #else /* CONFIG_IRQ_DOMAIN */ @@ -34,10 +33,6 @@ static inline void sdw_irq_create_mapping(struct sdw_slave *slave) { } -static inline void sdw_irq_dispose_mapping(struct sdw_slave *slave) -{ -} - #endif /* CONFIG_IRQ_DOMAIN */ #endif /* __SDW_IRQ_H */ diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c index 9d59f486edbe..65afb28ef8fa 100644 --- a/drivers/soundwire/mipi_disco.c +++ b/drivers/soundwire/mipi_disco.c @@ -366,6 +366,44 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, return 0; } +/* + * In MIPI DisCo spec for SoundWire, lane mapping for a slave device is done with + * mipi-sdw-lane-x-mapping properties, where x is 1..7, and the values for those + * properties are mipi-sdw-manager-lane-x or mipi-sdw-peripheral-link-y, where x + * is an integer between 1 to 7 if the lane is connected to a manager lane, y is a + * character between A to E if the lane is connected to another peripheral lane. + */ +int sdw_slave_read_lane_mapping(struct sdw_slave *slave) +{ + struct sdw_slave_prop *prop = &slave->prop; + struct device *dev = &slave->dev; + char prop_name[30]; + const char *prop_val; + size_t len; + int ret, i; + u8 lane; + + for (i = 0; i < SDW_MAX_LANES; i++) { + snprintf(prop_name, sizeof(prop_name), "mipi-sdw-lane-%d-mapping", i); + ret = device_property_read_string(dev, prop_name, &prop_val); + if (ret) + continue; + + len = strlen(prop_val); + if (len < 1) + return -EINVAL; + + /* The last character is enough to identify the connection */ + ret = kstrtou8(&prop_val[len - 1], 10, &lane); + if (ret) + return ret; + if (in_range(lane, 1, SDW_MAX_LANES - 1)) + prop->lane_maps[i] = lane; + } + return 0; +} +EXPORT_SYMBOL(sdw_slave_read_lane_mapping); + /** * sdw_slave_read_prop() - Read Slave properties * @slave: SDW Slave @@ -486,6 +524,6 @@ int sdw_slave_read_prop(struct sdw_slave *slave) sdw_slave_read_dpn(slave, prop->sink_dpn_prop, nval, prop->sink_ports, "sink"); - return 0; + return sdw_slave_read_lane_mapping(slave); } EXPORT_SYMBOL(sdw_slave_read_prop); diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index e00c5ac496a6..0f45e3404756 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -1072,7 +1072,7 @@ static const struct sdw_master_ops qcom_swrm_ops = { .pre_bank_switch = qcom_swrm_pre_bank_switch, }; -static int qcom_swrm_compute_params(struct sdw_bus *bus) +static int qcom_swrm_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { struct qcom_swrm_ctrl *ctrl = to_qcom_sdw(bus); struct sdw_master_runtime *m_rt; diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 7aa4900dcf31..e9df503332bb 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -629,8 +629,44 @@ static int sdw_notify_config(struct sdw_master_runtime *m_rt) static int sdw_program_params(struct sdw_bus *bus, bool prepare) { struct sdw_master_runtime *m_rt; + struct sdw_slave *slave; int ret = 0; + u32 addr1; + /* Check if all Peripherals comply with SDCA */ + list_for_each_entry(slave, &bus->slaves, node) { + if (!slave->dev_num_sticky) + continue; + if (!is_clock_scaling_supported_by_slave(slave)) { + dev_dbg(&slave->dev, "The Peripheral doesn't comply with SDCA\n"); + goto manager_runtime; + } + } + + if (bus->params.next_bank) + addr1 = SDW_SCP_BUSCLOCK_SCALE_B1; + else + addr1 = SDW_SCP_BUSCLOCK_SCALE_B0; + + /* Program SDW_SCP_BUSCLOCK_SCALE if all Peripherals comply with SDCA */ + list_for_each_entry(slave, &bus->slaves, node) { + int scale_index; + u8 base; + + if (!slave->dev_num_sticky) + continue; + scale_index = sdw_slave_get_scale_index(slave, &base); + if (scale_index < 0) + return scale_index; + + ret = sdw_write_no_pm(slave, addr1, scale_index); + if (ret < 0) { + dev_err(&slave->dev, "SDW_SCP_BUSCLOCK_SCALE register write failed\n"); + return ret; + } + } + +manager_runtime: list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { /* @@ -1383,7 +1419,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream, /* Compute params */ if (bus->compute_params) { - ret = bus->compute_params(bus); + ret = bus->compute_params(bus, stream); if (ret < 0) { dev_err(bus->dev, "Compute params failed: %d\n", ret); @@ -1642,9 +1678,19 @@ EXPORT_SYMBOL(sdw_disable_stream); static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) { struct sdw_master_runtime *m_rt; + struct sdw_port_runtime *p_rt; + unsigned int multi_lane_bandwidth; + unsigned int bandwidth; struct sdw_bus *bus; + int state = stream->state; int ret = 0; + /* + * first mark the state as DEPREPARED so that it is not taken into account + * for bit allocation + */ + stream->state = SDW_STREAM_DEPREPARED; + list_for_each_entry(m_rt, &stream->master_list, stream_node) { bus = m_rt->bus; /* De-prepare port(s) */ @@ -1652,19 +1698,34 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) if (ret < 0) { dev_err(bus->dev, "De-prepare port(s) failed: %d\n", ret); + stream->state = state; return ret; } + multi_lane_bandwidth = 0; + + list_for_each_entry(p_rt, &m_rt->port_list, port_node) { + if (!p_rt->lane) + continue; + + bandwidth = m_rt->stream->params.rate * hweight32(p_rt->ch_mask) * + m_rt->stream->params.bps; + multi_lane_bandwidth += bandwidth; + bus->lane_used_bandwidth[p_rt->lane] -= bandwidth; + if (!bus->lane_used_bandwidth[p_rt->lane]) + p_rt->lane = 0; + } /* TODO: Update this during Device-Device support */ - bus->params.bandwidth -= m_rt->stream->params.rate * - m_rt->ch_count * m_rt->stream->params.bps; + bandwidth = m_rt->stream->params.rate * m_rt->ch_count * m_rt->stream->params.bps; + bus->params.bandwidth -= bandwidth - multi_lane_bandwidth; /* Compute params */ if (bus->compute_params) { - ret = bus->compute_params(bus); + ret = bus->compute_params(bus, stream); if (ret < 0) { dev_err(bus->dev, "Compute params failed: %d\n", ret); + stream->state = state; return ret; } } @@ -1673,11 +1734,11 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) ret = sdw_program_params(bus, false); if (ret < 0) { dev_err(bus->dev, "%s: Program params failed: %d\n", __func__, ret); + stream->state = state; return ret; } } - stream->state = SDW_STREAM_DEPREPARED; return do_bank_switch(stream); } diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index f51f9466e518..ea8a31032927 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -542,6 +542,18 @@ config SPI_JCORE This enables support for the SPI master controller in the J-Core synthesizable, open source SoC. +config SPI_KSPI2 + tristate "Support for KEBA SPI master type 2 hardware" + depends on HAS_IOMEM + depends on KEBA_CP500 || COMPILE_TEST + select AUXILIARY_BUS + help + This driver supports KEBA SPI master type 2 FPGA implementation, + as found on CP500 devices for example. + + This driver can also be built as a module. If so, the module + will be called spi-kspi2. + config SPI_LM70_LLP tristate "Parallel port adapter for LM70 eval board (DEVELOPMENT)" depends on PARPORT diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile index aea5e54de195..9db7554c1864 100644 --- a/drivers/spi/Makefile +++ b/drivers/spi/Makefile @@ -74,6 +74,7 @@ obj-$(CONFIG_SPI_INTEL_PCI) += spi-intel-pci.o obj-$(CONFIG_SPI_INTEL_PLATFORM) += spi-intel-platform.o obj-$(CONFIG_SPI_LANTIQ_SSC) += spi-lantiq-ssc.o obj-$(CONFIG_SPI_JCORE) += spi-jcore.o +obj-$(CONFIG_SPI_KSPI2) += spi-kspi2.o obj-$(CONFIG_SPI_LJCA) += spi-ljca.o obj-$(CONFIG_SPI_LM70_LLP) += spi-lm70llp.o obj-$(CONFIG_SPI_LOONGSON_CORE) += spi-loongson-core.o diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c index 316bce577081..abdc49d9d940 100644 --- a/drivers/spi/atmel-quadspi.c +++ b/drivers/spi/atmel-quadspi.c @@ -11,11 +11,15 @@ * This driver is based on drivers/mtd/spi-nor/fsl-quadspi.c from Freescale. */ +#include #include #include +#include +#include #include #include #include +#include #include #include #include @@ -34,6 +38,7 @@ #define QSPI_IDR 0x0018 /* Interrupt Disable Register */ #define QSPI_IMR 0x001c /* Interrupt Mask Register */ #define QSPI_SCR 0x0020 /* Serial Clock Register */ +#define QSPI_SR2 0x0024 /* SAMA7G5 Status Register */ #define QSPI_IAR 0x0030 /* Instruction Address Register */ #define QSPI_ICR 0x0034 /* Instruction Code Register */ @@ -44,16 +49,32 @@ #define QSPI_SMR 0x0040 /* Scrambling Mode Register */ #define QSPI_SKR 0x0044 /* Scrambling Key Register */ +#define QSPI_REFRESH 0x0050 /* Refresh Register */ +#define QSPI_WRACNT 0x0054 /* Write Access Counter Register */ +#define QSPI_DLLCFG 0x0058 /* DLL Configuration Register */ +#define QSPI_PCALCFG 0x005C /* Pad Calibration Configuration Register */ +#define QSPI_PCALBP 0x0060 /* Pad Calibration Bypass Register */ +#define QSPI_TOUT 0x0064 /* Timeout Register */ + #define QSPI_WPMR 0x00E4 /* Write Protection Mode Register */ #define QSPI_WPSR 0x00E8 /* Write Protection Status Register */ #define QSPI_VERSION 0x00FC /* Version Register */ +#define SAMA7G5_QSPI0_MAX_SPEED_HZ 200000000 +#define SAMA7G5_QSPI1_SDR_MAX_SPEED_HZ 133000000 /* Bitfields in QSPI_CR (Control Register) */ #define QSPI_CR_QSPIEN BIT(0) #define QSPI_CR_QSPIDIS BIT(1) +#define QSPI_CR_DLLON BIT(2) +#define QSPI_CR_DLLOFF BIT(3) +#define QSPI_CR_STPCAL BIT(4) +#define QSPI_CR_SRFRSH BIT(5) #define QSPI_CR_SWRST BIT(7) +#define QSPI_CR_UPDCFG BIT(8) +#define QSPI_CR_STTFR BIT(9) +#define QSPI_CR_RTOUT BIT(10) #define QSPI_CR_LASTXFER BIT(24) /* Bitfields in QSPI_MR (Mode Register) */ @@ -61,12 +82,14 @@ #define QSPI_MR_LLB BIT(1) #define QSPI_MR_WDRBT BIT(2) #define QSPI_MR_SMRM BIT(3) +#define QSPI_MR_DQSDLYEN BIT(3) #define QSPI_MR_CSMODE_MASK GENMASK(5, 4) #define QSPI_MR_CSMODE_NOT_RELOADED (0 << 4) #define QSPI_MR_CSMODE_LASTXFER (1 << 4) #define QSPI_MR_CSMODE_SYSTEMATICALLY (2 << 4) #define QSPI_MR_NBBITS_MASK GENMASK(11, 8) #define QSPI_MR_NBBITS(n) ((((n) - 8) << 8) & QSPI_MR_NBBITS_MASK) +#define QSPI_MR_OENSD BIT(15) #define QSPI_MR_DLYBCT_MASK GENMASK(23, 16) #define QSPI_MR_DLYBCT(n) (((n) << 16) & QSPI_MR_DLYBCT_MASK) #define QSPI_MR_DLYCS_MASK GENMASK(31, 24) @@ -80,6 +103,13 @@ #define QSPI_SR_CSR BIT(8) #define QSPI_SR_CSS BIT(9) #define QSPI_SR_INSTRE BIT(10) +#define QSPI_SR_LWRA BIT(11) +#define QSPI_SR_QITF BIT(12) +#define QSPI_SR_QITR BIT(13) +#define QSPI_SR_CSFA BIT(14) +#define QSPI_SR_CSRA BIT(15) +#define QSPI_SR_RFRSHD BIT(16) +#define QSPI_SR_TOUT BIT(17) #define QSPI_SR_QSPIENS BIT(24) #define QSPI_SR_CMD_COMPLETED (QSPI_SR_INSTRE | QSPI_SR_CSR) @@ -92,9 +122,22 @@ #define QSPI_SCR_DLYBS_MASK GENMASK(23, 16) #define QSPI_SCR_DLYBS(n) (((n) << 16) & QSPI_SCR_DLYBS_MASK) +/* Bitfields in QSPI_SR2 (SAMA7G5 Status Register) */ +#define QSPI_SR2_SYNCBSY BIT(0) +#define QSPI_SR2_QSPIENS BIT(1) +#define QSPI_SR2_CSS BIT(2) +#define QSPI_SR2_RBUSY BIT(3) +#define QSPI_SR2_HIDLE BIT(4) +#define QSPI_SR2_DLOCK BIT(5) +#define QSPI_SR2_CALBSY BIT(6) + +/* Bitfields in QSPI_IAR (Instruction Address Register) */ +#define QSPI_IAR_ADDR GENMASK(31, 0) + /* Bitfields in QSPI_ICR (Read/Write Instruction Code Register) */ #define QSPI_ICR_INST_MASK GENMASK(7, 0) #define QSPI_ICR_INST(inst) (((inst) << 0) & QSPI_ICR_INST_MASK) +#define QSPI_ICR_INST_MASK_SAMA7G5 GENMASK(15, 0) #define QSPI_ICR_OPT_MASK GENMASK(23, 16) #define QSPI_ICR_OPT(opt) (((opt) << 16) & QSPI_ICR_OPT_MASK) @@ -107,6 +150,9 @@ #define QSPI_IFR_WIDTH_QUAD_IO (4 << 0) #define QSPI_IFR_WIDTH_DUAL_CMD (5 << 0) #define QSPI_IFR_WIDTH_QUAD_CMD (6 << 0) +#define QSPI_IFR_WIDTH_OCT_OUTPUT (7 << 0) +#define QSPI_IFR_WIDTH_OCT_IO (8 << 0) +#define QSPI_IFR_WIDTH_OCT_CMD (9 << 0) #define QSPI_IFR_INSTEN BIT(4) #define QSPI_IFR_ADDREN BIT(5) #define QSPI_IFR_OPTEN BIT(6) @@ -117,19 +163,60 @@ #define QSPI_IFR_OPTL_4BIT (2 << 8) #define QSPI_IFR_OPTL_8BIT (3 << 8) #define QSPI_IFR_ADDRL BIT(10) +#define QSPI_IFR_ADDRL_SAMA7G5 GENMASK(11, 10) #define QSPI_IFR_TFRTYP_MEM BIT(12) #define QSPI_IFR_SAMA5D2_WRITE_TRSFR BIT(13) #define QSPI_IFR_CRM BIT(14) +#define QSPI_IFR_DDREN BIT(15) #define QSPI_IFR_NBDUM_MASK GENMASK(20, 16) #define QSPI_IFR_NBDUM(n) (((n) << 16) & QSPI_IFR_NBDUM_MASK) +#define QSPI_IFR_END BIT(22) +#define QSPI_IFR_SMRM BIT(23) #define QSPI_IFR_APBTFRTYP_READ BIT(24) /* Defined in SAM9X60 */ +#define QSPI_IFR_DQSEN BIT(25) +#define QSPI_IFR_DDRCMDEN BIT(26) +#define QSPI_IFR_HFWBEN BIT(27) +#define QSPI_IFR_PROTTYP GENMASK(29, 28) +#define QSPI_IFR_PROTTYP_STD_SPI 0 +#define QSPI_IFR_PROTTYP_TWIN_QUAD 1 +#define QSPI_IFR_PROTTYP_OCTAFLASH 2 +#define QSPI_IFR_PROTTYP_HYPERFLASH 3 /* Bitfields in QSPI_SMR (Scrambling Mode Register) */ #define QSPI_SMR_SCREN BIT(0) #define QSPI_SMR_RVDIS BIT(1) +#define QSPI_SMR_SCRKL BIT(2) + +/* Bitfields in QSPI_REFRESH (Refresh Register) */ +#define QSPI_REFRESH_DELAY_COUNTER GENMASK(31, 0) + +/* Bitfields in QSPI_WRACNT (Write Access Counter Register) */ +#define QSPI_WRACNT_NBWRA GENMASK(31, 0) + +/* Bitfields in QSPI_DLLCFG (DLL Configuration Register) */ +#define QSPI_DLLCFG_RANGE BIT(0) + +/* Bitfields in QSPI_PCALCFG (DLL Pad Calibration Configuration Register) */ +#define QSPI_PCALCFG_AAON BIT(0) +#define QSPI_PCALCFG_DAPCAL BIT(1) +#define QSPI_PCALCFG_DIFFPM BIT(2) +#define QSPI_PCALCFG_CLKDIV GENMASK(6, 4) +#define QSPI_PCALCFG_CALCNT GENMASK(16, 8) +#define QSPI_PCALCFG_CALP GENMASK(27, 24) +#define QSPI_PCALCFG_CALN GENMASK(31, 28) + +/* Bitfields in QSPI_PCALBP (DLL Pad Calibration Bypass Register) */ +#define QSPI_PCALBP_BPEN BIT(0) +#define QSPI_PCALBP_CALPBP GENMASK(11, 8) +#define QSPI_PCALBP_CALNBP GENMASK(19, 16) + +/* Bitfields in QSPI_TOUT (Timeout Register) */ +#define QSPI_TOUT_TCNTM GENMASK(15, 0) /* Bitfields in QSPI_WPMR (Write Protection Mode Register) */ #define QSPI_WPMR_WPEN BIT(0) +#define QSPI_WPMR_WPITEN BIT(1) +#define QSPI_WPMR_WPCREN BIT(2) #define QSPI_WPMR_WPKEY_MASK GENMASK(31, 8) #define QSPI_WPMR_WPKEY(wpkey) (((wpkey) << 8) & QSPI_WPMR_WPKEY_MASK) @@ -138,23 +225,74 @@ #define QSPI_WPSR_WPVSRC_MASK GENMASK(15, 8) #define QSPI_WPSR_WPVSRC(src) (((src) << 8) & QSPI_WPSR_WPVSRC) -struct atmel_qspi_caps { - bool has_qspick; - bool has_ricr; +#define ATMEL_QSPI_TIMEOUT 1000 /* ms */ +#define ATMEL_QSPI_SYNC_TIMEOUT 300 /* ms */ +#define QSPI_DLLCFG_THRESHOLD_FREQ 90000000U +#define QSPI_CALIB_TIME 2000 /* 2 us */ + +/* Use PIO for small transfers. */ +#define ATMEL_QSPI_DMA_MIN_BYTES 16 +/** + * struct atmel_qspi_pcal - Pad Calibration Clock Division + * @pclk_rate: peripheral clock rate. + * @pclkdiv: calibration clock division. The clock applied to the calibration + * cell is divided by pclkdiv + 1. + */ +struct atmel_qspi_pcal { + u32 pclk_rate; + u8 pclk_div; }; +#define ATMEL_QSPI_PCAL_ARRAY_SIZE 8 +static const struct atmel_qspi_pcal pcal[ATMEL_QSPI_PCAL_ARRAY_SIZE] = { + {25000000, 0}, + {50000000, 1}, + {75000000, 2}, + {100000000, 3}, + {125000000, 4}, + {150000000, 5}, + {175000000, 6}, + {200000000, 7}, +}; + +struct atmel_qspi_caps { + u32 max_speed_hz; + bool has_qspick; + bool has_gclk; + bool has_ricr; + bool octal; + bool has_dma; +}; + +struct atmel_qspi_ops; + struct atmel_qspi { void __iomem *regs; void __iomem *mem; struct clk *pclk; struct clk *qspick; + struct clk *gclk; struct platform_device *pdev; const struct atmel_qspi_caps *caps; + const struct atmel_qspi_ops *ops; resource_size_t mmap_size; u32 pending; + u32 irq_mask; u32 mr; u32 scr; + u32 target_max_speed_hz; struct completion cmd_completion; + struct completion dma_completion; + dma_addr_t mmap_phys_base; + struct dma_chan *rx_chan; + struct dma_chan *tx_chan; +}; + +struct atmel_qspi_ops { + int (*set_cfg)(struct atmel_qspi *aq, const struct spi_mem_op *op, + u32 *offset); + int (*transfer)(struct spi_mem *mem, const struct spi_mem_op *op, + u32 offset); }; struct atmel_qspi_mode { @@ -174,6 +312,19 @@ static const struct atmel_qspi_mode atmel_qspi_modes[] = { { 4, 4, 4, QSPI_IFR_WIDTH_QUAD_CMD }, }; +static const struct atmel_qspi_mode atmel_qspi_sama7g5_modes[] = { + { 1, 1, 1, QSPI_IFR_WIDTH_SINGLE_BIT_SPI }, + { 1, 1, 2, QSPI_IFR_WIDTH_DUAL_OUTPUT }, + { 1, 1, 4, QSPI_IFR_WIDTH_QUAD_OUTPUT }, + { 1, 2, 2, QSPI_IFR_WIDTH_DUAL_IO }, + { 1, 4, 4, QSPI_IFR_WIDTH_QUAD_IO }, + { 2, 2, 2, QSPI_IFR_WIDTH_DUAL_CMD }, + { 4, 4, 4, QSPI_IFR_WIDTH_QUAD_CMD }, + { 1, 1, 8, QSPI_IFR_WIDTH_OCT_OUTPUT }, + { 1, 8, 8, QSPI_IFR_WIDTH_OCT_IO }, + { 8, 8, 8, QSPI_IFR_WIDTH_OCT_CMD }, +}; + #ifdef VERBOSE_DEBUG static const char *atmel_qspi_reg_name(u32 offset, char *tmp, size_t sz) { @@ -196,6 +347,8 @@ static const char *atmel_qspi_reg_name(u32 offset, char *tmp, size_t sz) return "IMR"; case QSPI_SCR: return "SCR"; + case QSPI_SR2: + return "SR2"; case QSPI_IAR: return "IAR"; case QSPI_ICR: @@ -208,6 +361,18 @@ static const char *atmel_qspi_reg_name(u32 offset, char *tmp, size_t sz) return "SMR"; case QSPI_SKR: return "SKR"; + case QSPI_REFRESH: + return "REFRESH"; + case QSPI_WRACNT: + return "WRACNT"; + case QSPI_DLLCFG: + return "DLLCFG"; + case QSPI_PCALCFG: + return "PCALCFG"; + case QSPI_PCALBP: + return "PCALBP"; + case QSPI_TOUT: + return "TOUT"; case QSPI_WPMR: return "WPMR"; case QSPI_WPSR: @@ -249,6 +414,28 @@ static void atmel_qspi_write(u32 value, struct atmel_qspi *aq, u32 offset) writel_relaxed(value, aq->regs + offset); } +static int atmel_qspi_reg_sync(struct atmel_qspi *aq) +{ + u32 val; + int ret; + + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + !(val & QSPI_SR2_SYNCBSY), 40, + ATMEL_QSPI_SYNC_TIMEOUT); + return ret; +} + +static int atmel_qspi_update_config(struct atmel_qspi *aq) +{ + int ret; + + ret = atmel_qspi_reg_sync(aq); + if (ret) + return ret; + atmel_qspi_write(QSPI_CR_UPDCFG, aq, QSPI_CR); + return atmel_qspi_reg_sync(aq); +} + static inline bool atmel_qspi_is_compatible(const struct spi_mem_op *op, const struct atmel_qspi_mode *mode) { @@ -275,12 +462,31 @@ static int atmel_qspi_find_mode(const struct spi_mem_op *op) return -EOPNOTSUPP; } +static int atmel_qspi_sama7g5_find_mode(const struct spi_mem_op *op) +{ + u32 i; + + for (i = 0; i < ARRAY_SIZE(atmel_qspi_sama7g5_modes); i++) + if (atmel_qspi_is_compatible(op, &atmel_qspi_sama7g5_modes[i])) + return i; + + return -EOPNOTSUPP; +} + static bool atmel_qspi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) { + struct atmel_qspi *aq = spi_controller_get_devdata(mem->spi->controller); if (!spi_mem_default_supports_op(mem, op)) return false; + if (aq->caps->octal) { + if (atmel_qspi_sama7g5_find_mode(op) < 0) + return false; + else + return true; + } + if (atmel_qspi_find_mode(op) < 0) return false; @@ -292,6 +498,25 @@ static bool atmel_qspi_supports_op(struct spi_mem *mem, return true; } +/* + * If the QSPI controller is set in regular SPI mode, set it in + * Serial Memory Mode (SMM). + */ +static int atmel_qspi_set_serial_memory_mode(struct atmel_qspi *aq) +{ + int ret = 0; + + if (!(aq->mr & QSPI_MR_SMM)) { + aq->mr |= QSPI_MR_SMM; + atmel_qspi_write(aq->mr, aq, QSPI_MR); + + if (aq->caps->has_gclk) + ret = atmel_qspi_update_config(aq); + } + + return ret; +} + static int atmel_qspi_set_cfg(struct atmel_qspi *aq, const struct spi_mem_op *op, u32 *offset) { @@ -371,14 +596,9 @@ static int atmel_qspi_set_cfg(struct atmel_qspi *aq, ifr |= QSPI_IFR_TFRTYP_MEM; } - /* - * If the QSPI controller is set in regular SPI mode, set it in - * Serial Memory Mode (SMM). - */ - if (!(aq->mr & QSPI_MR_SMM)) { - aq->mr |= QSPI_MR_SMM; - atmel_qspi_write(aq->mr, aq, QSPI_MR); - } + mode = atmel_qspi_set_serial_memory_mode(aq); + if (mode < 0) + return mode; /* Clear pending interrupts */ (void)atmel_qspi_read(aq, QSPI_SR); @@ -404,10 +624,326 @@ static int atmel_qspi_set_cfg(struct atmel_qspi *aq, return 0; } +static int atmel_qspi_wait_for_completion(struct atmel_qspi *aq, u32 irq_mask) +{ + int err = 0; + u32 sr; + + /* Poll INSTRuction End status */ + sr = atmel_qspi_read(aq, QSPI_SR); + if ((sr & irq_mask) == irq_mask) + return 0; + + /* Wait for INSTRuction End interrupt */ + reinit_completion(&aq->cmd_completion); + aq->pending = sr & irq_mask; + aq->irq_mask = irq_mask; + atmel_qspi_write(irq_mask, aq, QSPI_IER); + if (!wait_for_completion_timeout(&aq->cmd_completion, + msecs_to_jiffies(ATMEL_QSPI_TIMEOUT))) + err = -ETIMEDOUT; + atmel_qspi_write(irq_mask, aq, QSPI_IDR); + + return err; +} + +static int atmel_qspi_transfer(struct spi_mem *mem, + const struct spi_mem_op *op, u32 offset) +{ + struct atmel_qspi *aq = spi_controller_get_devdata(mem->spi->controller); + + /* Skip to the final steps if there is no data */ + if (!op->data.nbytes) + return atmel_qspi_wait_for_completion(aq, + QSPI_SR_CMD_COMPLETED); + + /* Dummy read of QSPI_IFR to synchronize APB and AHB accesses */ + (void)atmel_qspi_read(aq, QSPI_IFR); + + /* Send/Receive data */ + if (op->data.dir == SPI_MEM_DATA_IN) { + memcpy_fromio(op->data.buf.in, aq->mem + offset, + op->data.nbytes); + + /* Synchronize AHB and APB accesses again */ + rmb(); + } else { + memcpy_toio(aq->mem + offset, op->data.buf.out, + op->data.nbytes); + + /* Synchronize AHB and APB accesses again */ + wmb(); + } + + /* Release the chip-select */ + atmel_qspi_write(QSPI_CR_LASTXFER, aq, QSPI_CR); + + return atmel_qspi_wait_for_completion(aq, QSPI_SR_CMD_COMPLETED); +} + +static int atmel_qspi_sama7g5_set_cfg(struct atmel_qspi *aq, + const struct spi_mem_op *op, u32 *offset) +{ + u32 iar, icr, ifr; + int mode, ret; + + iar = 0; + icr = FIELD_PREP(QSPI_ICR_INST_MASK_SAMA7G5, op->cmd.opcode); + ifr = QSPI_IFR_INSTEN; + + mode = atmel_qspi_sama7g5_find_mode(op); + if (mode < 0) + return mode; + ifr |= atmel_qspi_sama7g5_modes[mode].config; + + if (op->dummy.buswidth && op->dummy.nbytes) { + if (op->addr.dtr && op->dummy.dtr && op->data.dtr) + ifr |= QSPI_IFR_NBDUM(op->dummy.nbytes * 8 / + (2 * op->dummy.buswidth)); + else + ifr |= QSPI_IFR_NBDUM(op->dummy.nbytes * 8 / + op->dummy.buswidth); + } + + if (op->addr.buswidth && op->addr.nbytes) { + ifr |= FIELD_PREP(QSPI_IFR_ADDRL_SAMA7G5, op->addr.nbytes - 1) | + QSPI_IFR_ADDREN; + iar = FIELD_PREP(QSPI_IAR_ADDR, op->addr.val); + } + + if (op->addr.dtr && op->dummy.dtr && op->data.dtr) { + ifr |= QSPI_IFR_DDREN; + if (op->cmd.dtr) + ifr |= QSPI_IFR_DDRCMDEN; + + ifr |= QSPI_IFR_DQSEN; + } + + if (op->cmd.buswidth == 8 || op->addr.buswidth == 8 || + op->data.buswidth == 8) + ifr |= FIELD_PREP(QSPI_IFR_PROTTYP, QSPI_IFR_PROTTYP_OCTAFLASH); + + /* offset of the data access in the QSPI memory space */ + *offset = iar; + + /* Set data enable */ + if (op->data.nbytes) { + ifr |= QSPI_IFR_DATAEN; + + if (op->addr.nbytes) + ifr |= QSPI_IFR_TFRTYP_MEM; + } + + ret = atmel_qspi_set_serial_memory_mode(aq); + if (ret < 0) + return ret; + + /* Clear pending interrupts */ + (void)atmel_qspi_read(aq, QSPI_SR); + + /* Set QSPI Instruction Frame registers */ + if (op->addr.nbytes && !op->data.nbytes) + atmel_qspi_write(iar, aq, QSPI_IAR); + + if (op->data.dir == SPI_MEM_DATA_IN) { + atmel_qspi_write(icr, aq, QSPI_RICR); + } else { + atmel_qspi_write(icr, aq, QSPI_WICR); + if (op->data.nbytes) + atmel_qspi_write(FIELD_PREP(QSPI_WRACNT_NBWRA, + op->data.nbytes), + aq, QSPI_WRACNT); + } + + atmel_qspi_write(ifr, aq, QSPI_IFR); + + return atmel_qspi_update_config(aq); +} + +static void atmel_qspi_dma_callback(void *param) +{ + struct atmel_qspi *aq = param; + + complete(&aq->dma_completion); +} + +static int atmel_qspi_dma_xfer(struct atmel_qspi *aq, struct dma_chan *chan, + dma_addr_t dma_dst, dma_addr_t dma_src, + unsigned int len) +{ + struct dma_async_tx_descriptor *tx; + dma_cookie_t cookie; + int ret; + + tx = dmaengine_prep_dma_memcpy(chan, dma_dst, dma_src, len, + DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + if (!tx) { + dev_err(&aq->pdev->dev, "device_prep_dma_memcpy error\n"); + return -EIO; + } + + reinit_completion(&aq->dma_completion); + tx->callback = atmel_qspi_dma_callback; + tx->callback_param = aq; + cookie = tx->tx_submit(tx); + ret = dma_submit_error(cookie); + if (ret) { + dev_err(&aq->pdev->dev, "dma_submit_error %d\n", cookie); + return ret; + } + + dma_async_issue_pending(chan); + ret = wait_for_completion_timeout(&aq->dma_completion, + msecs_to_jiffies(20 * ATMEL_QSPI_TIMEOUT)); + if (ret == 0) { + dmaengine_terminate_sync(chan); + dev_err(&aq->pdev->dev, "DMA wait_for_completion_timeout\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static int atmel_qspi_dma_rx_xfer(struct spi_mem *mem, + const struct spi_mem_op *op, + struct sg_table *sgt, loff_t loff) +{ + struct atmel_qspi *aq = + spi_controller_get_devdata(mem->spi->controller); + struct scatterlist *sg; + dma_addr_t dma_src; + unsigned int i, len; + int ret; + + dma_src = aq->mmap_phys_base + loff; + + for_each_sg(sgt->sgl, sg, sgt->nents, i) { + len = sg_dma_len(sg); + ret = atmel_qspi_dma_xfer(aq, aq->rx_chan, sg_dma_address(sg), + dma_src, len); + if (ret) + return ret; + dma_src += len; + } + + return 0; +} + +static int atmel_qspi_dma_tx_xfer(struct spi_mem *mem, + const struct spi_mem_op *op, + struct sg_table *sgt, loff_t loff) +{ + struct atmel_qspi *aq = + spi_controller_get_devdata(mem->spi->controller); + struct scatterlist *sg; + dma_addr_t dma_dst; + unsigned int i, len; + int ret; + + dma_dst = aq->mmap_phys_base + loff; + + for_each_sg(sgt->sgl, sg, sgt->nents, i) { + len = sg_dma_len(sg); + ret = atmel_qspi_dma_xfer(aq, aq->tx_chan, dma_dst, + sg_dma_address(sg), len); + if (ret) + return ret; + dma_dst += len; + } + + return 0; +} + +static int atmel_qspi_dma_transfer(struct spi_mem *mem, + const struct spi_mem_op *op, loff_t loff) +{ + struct sg_table sgt; + int ret; + + ret = spi_controller_dma_map_mem_op_data(mem->spi->controller, op, + &sgt); + if (ret) + return ret; + + if (op->data.dir == SPI_MEM_DATA_IN) + ret = atmel_qspi_dma_rx_xfer(mem, op, &sgt, loff); + else + ret = atmel_qspi_dma_tx_xfer(mem, op, &sgt, loff); + + spi_controller_dma_unmap_mem_op_data(mem->spi->controller, op, &sgt); + + return ret; +} + +static int atmel_qspi_sama7g5_transfer(struct spi_mem *mem, + const struct spi_mem_op *op, u32 offset) +{ + struct atmel_qspi *aq = + spi_controller_get_devdata(mem->spi->controller); + u32 val; + int ret; + + if (!op->data.nbytes) { + /* Start the transfer. */ + ret = atmel_qspi_reg_sync(aq); + if (ret) + return ret; + atmel_qspi_write(QSPI_CR_STTFR, aq, QSPI_CR); + + return atmel_qspi_wait_for_completion(aq, QSPI_SR_CSRA); + } + + /* Send/Receive data. */ + if (op->data.dir == SPI_MEM_DATA_IN) { + if (aq->rx_chan && op->addr.nbytes && + op->data.nbytes > ATMEL_QSPI_DMA_MIN_BYTES) { + ret = atmel_qspi_dma_transfer(mem, op, offset); + if (ret) + return ret; + } else { + memcpy_fromio(op->data.buf.in, aq->mem + offset, + op->data.nbytes); + } + + if (op->addr.nbytes) { + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + !(val & QSPI_SR2_RBUSY), 40, + ATMEL_QSPI_SYNC_TIMEOUT); + if (ret) + return ret; + } + } else { + if (aq->tx_chan && op->addr.nbytes && + op->data.nbytes > ATMEL_QSPI_DMA_MIN_BYTES) { + ret = atmel_qspi_dma_transfer(mem, op, offset); + if (ret) + return ret; + } else { + memcpy_toio(aq->mem + offset, op->data.buf.out, + op->data.nbytes); + } + + ret = atmel_qspi_wait_for_completion(aq, QSPI_SR_LWRA); + if (ret) + return ret; + } + + /* Release the chip-select. */ + ret = atmel_qspi_reg_sync(aq); + if (ret) { + pm_runtime_mark_last_busy(&aq->pdev->dev); + pm_runtime_put_autosuspend(&aq->pdev->dev); + return ret; + } + atmel_qspi_write(QSPI_CR_LASTXFER, aq, QSPI_CR); + + return atmel_qspi_wait_for_completion(aq, QSPI_SR_CSRA); +} + static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) { struct atmel_qspi *aq = spi_controller_get_devdata(mem->spi->controller); - u32 sr, offset; + u32 offset; int err; /* @@ -416,46 +952,20 @@ static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) * when the flash memories overrun the controller's memory space. */ if (op->addr.val + op->data.nbytes > aq->mmap_size) - return -ENOTSUPP; + return -EOPNOTSUPP; + + if (op->addr.nbytes > 4) + return -EOPNOTSUPP; err = pm_runtime_resume_and_get(&aq->pdev->dev); if (err < 0) return err; - err = atmel_qspi_set_cfg(aq, op, &offset); + err = aq->ops->set_cfg(aq, op, &offset); if (err) goto pm_runtime_put; - /* Skip to the final steps if there is no data */ - if (op->data.nbytes) { - /* Dummy read of QSPI_IFR to synchronize APB and AHB accesses */ - (void)atmel_qspi_read(aq, QSPI_IFR); - - /* Send/Receive data */ - if (op->data.dir == SPI_MEM_DATA_IN) - memcpy_fromio(op->data.buf.in, aq->mem + offset, - op->data.nbytes); - else - memcpy_toio(aq->mem + offset, op->data.buf.out, - op->data.nbytes); - - /* Release the chip-select */ - atmel_qspi_write(QSPI_CR_LASTXFER, aq, QSPI_CR); - } - - /* Poll INSTRuction End status */ - sr = atmel_qspi_read(aq, QSPI_SR); - if ((sr & QSPI_SR_CMD_COMPLETED) == QSPI_SR_CMD_COMPLETED) - goto pm_runtime_put; - - /* Wait for INSTRuction End interrupt */ - reinit_completion(&aq->cmd_completion); - aq->pending = sr & QSPI_SR_CMD_COMPLETED; - atmel_qspi_write(QSPI_SR_CMD_COMPLETED, aq, QSPI_IER); - if (!wait_for_completion_timeout(&aq->cmd_completion, - msecs_to_jiffies(1000))) - err = -ETIMEDOUT; - atmel_qspi_write(QSPI_SR_CMD_COMPLETED, aq, QSPI_IDR); + err = aq->ops->transfer(mem, op, offset); pm_runtime_put: pm_runtime_mark_last_busy(&aq->pdev->dev); @@ -474,6 +984,159 @@ static const struct spi_controller_mem_ops atmel_qspi_mem_ops = { .get_name = atmel_qspi_get_name }; +static int atmel_qspi_set_pad_calibration(struct atmel_qspi *aq) +{ + unsigned long pclk_rate; + u32 status, val; + int i, ret; + u8 pclk_div = 0; + + pclk_rate = clk_get_rate(aq->pclk); + if (!pclk_rate) + return -EINVAL; + + for (i = 0; i < ATMEL_QSPI_PCAL_ARRAY_SIZE; i++) { + if (pclk_rate <= pcal[i].pclk_rate) { + pclk_div = pcal[i].pclk_div; + break; + } + } + + /* + * Use the biggest divider in case the peripheral clock exceeds + * 200MHZ. + */ + if (pclk_rate > pcal[ATMEL_QSPI_PCAL_ARRAY_SIZE - 1].pclk_rate) + pclk_div = pcal[ATMEL_QSPI_PCAL_ARRAY_SIZE - 1].pclk_div; + + /* Disable QSPI while configuring the pad calibration. */ + status = atmel_qspi_read(aq, QSPI_SR2); + if (status & QSPI_SR2_QSPIENS) { + ret = atmel_qspi_reg_sync(aq); + if (ret) + return ret; + atmel_qspi_write(QSPI_CR_QSPIDIS, aq, QSPI_CR); + } + + /* + * The analog circuitry is not shut down at the end of the calibration + * and the start-up time is only required for the first calibration + * sequence, thus increasing performance. Set the delay between the Pad + * calibration analog circuitry and the calibration request to 2us. + */ + atmel_qspi_write(QSPI_PCALCFG_AAON | + FIELD_PREP(QSPI_PCALCFG_CLKDIV, pclk_div) | + FIELD_PREP(QSPI_PCALCFG_CALCNT, + 2 * (pclk_rate / 1000000)), + aq, QSPI_PCALCFG); + + /* DLL On + start calibration. */ + atmel_qspi_write(QSPI_CR_DLLON | QSPI_CR_STPCAL, aq, QSPI_CR); + + /* Check synchronization status before updating configuration. */ + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + (val & QSPI_SR2_DLOCK) && + !(val & QSPI_SR2_CALBSY), 40, + ATMEL_QSPI_TIMEOUT); + + /* Refresh analogic blocks every 1 ms.*/ + atmel_qspi_write(FIELD_PREP(QSPI_REFRESH_DELAY_COUNTER, + aq->target_max_speed_hz / 1000), + aq, QSPI_REFRESH); + + return ret; +} + +static int atmel_qspi_set_gclk(struct atmel_qspi *aq) +{ + u32 status, val; + int ret; + + /* Disable DLL before setting GCLK */ + status = atmel_qspi_read(aq, QSPI_SR2); + if (status & QSPI_SR2_DLOCK) { + atmel_qspi_write(QSPI_CR_DLLOFF, aq, QSPI_CR); + + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + !(val & QSPI_SR2_DLOCK), 40, + ATMEL_QSPI_TIMEOUT); + if (ret) + return ret; + } + + if (aq->target_max_speed_hz > QSPI_DLLCFG_THRESHOLD_FREQ) + atmel_qspi_write(QSPI_DLLCFG_RANGE, aq, QSPI_DLLCFG); + else + atmel_qspi_write(0, aq, QSPI_DLLCFG); + + ret = clk_set_rate(aq->gclk, aq->target_max_speed_hz); + if (ret) { + dev_err(&aq->pdev->dev, "Failed to set generic clock rate.\n"); + return ret; + } + + /* Enable the QSPI generic clock */ + ret = clk_prepare_enable(aq->gclk); + if (ret) + dev_err(&aq->pdev->dev, "Failed to enable generic clock.\n"); + + return ret; +} + +static int atmel_qspi_sama7g5_init(struct atmel_qspi *aq) +{ + u32 val; + int ret; + + ret = atmel_qspi_set_gclk(aq); + if (ret) + return ret; + + if (aq->caps->octal) { + ret = atmel_qspi_set_pad_calibration(aq); + if (ret) + return ret; + } else { + atmel_qspi_write(QSPI_CR_DLLON, aq, QSPI_CR); + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + (val & QSPI_SR2_DLOCK), 40, + ATMEL_QSPI_TIMEOUT); + } + + /* Set the QSPI controller by default in Serial Memory Mode */ + aq->mr |= QSPI_MR_DQSDLYEN; + ret = atmel_qspi_set_serial_memory_mode(aq); + if (ret < 0) + return ret; + + /* Enable the QSPI controller. */ + atmel_qspi_write(QSPI_CR_QSPIEN, aq, QSPI_CR); + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + val & QSPI_SR2_QSPIENS, 40, + ATMEL_QSPI_SYNC_TIMEOUT); + if (ret) + return ret; + + if (aq->caps->octal) { + ret = readl_poll_timeout(aq->regs + QSPI_SR, val, + val & QSPI_SR_RFRSHD, 40, + ATMEL_QSPI_TIMEOUT); + } + + atmel_qspi_write(QSPI_TOUT_TCNTM, aq, QSPI_TOUT); + return ret; +} + +static int atmel_qspi_sama7g5_setup(struct spi_device *spi) +{ + struct atmel_qspi *aq = spi_controller_get_devdata(spi->controller); + + /* The controller can communicate with a single peripheral device (target). */ + aq->target_max_speed_hz = spi->max_speed_hz; + + return atmel_qspi_sama7g5_init(aq); +} + static int atmel_qspi_setup(struct spi_device *spi) { struct spi_controller *ctrl = spi->controller; @@ -488,6 +1151,9 @@ static int atmel_qspi_setup(struct spi_device *spi) if (!spi->max_speed_hz) return -EINVAL; + if (aq->caps->has_gclk) + return atmel_qspi_sama7g5_setup(spi); + src_rate = clk_get_rate(aq->pclk); if (!src_rate) return -EINVAL; @@ -573,17 +1239,29 @@ static int atmel_qspi_set_cs_timing(struct spi_device *spi) return 0; } -static void atmel_qspi_init(struct atmel_qspi *aq) +static int atmel_qspi_init(struct atmel_qspi *aq) { + int ret; + + if (aq->caps->has_gclk) { + ret = atmel_qspi_reg_sync(aq); + if (ret) + return ret; + atmel_qspi_write(QSPI_CR_SWRST, aq, QSPI_CR); + return 0; + } + /* Reset the QSPI controller */ atmel_qspi_write(QSPI_CR_SWRST, aq, QSPI_CR); /* Set the QSPI controller by default in Serial Memory Mode */ - aq->mr |= QSPI_MR_SMM; - atmel_qspi_write(aq->mr, aq, QSPI_MR); + ret = atmel_qspi_set_serial_memory_mode(aq); + if (ret < 0) + return ret; /* Enable the QSPI controller */ atmel_qspi_write(QSPI_CR_QSPIEN, aq, QSPI_CR); + return 0; } static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id) @@ -599,12 +1277,65 @@ static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id) return IRQ_NONE; aq->pending |= pending; - if ((aq->pending & QSPI_SR_CMD_COMPLETED) == QSPI_SR_CMD_COMPLETED) + if ((aq->pending & aq->irq_mask) == aq->irq_mask) complete(&aq->cmd_completion); return IRQ_HANDLED; } +static int atmel_qspi_dma_init(struct spi_controller *ctrl) +{ + struct atmel_qspi *aq = spi_controller_get_devdata(ctrl); + int ret; + + aq->rx_chan = dma_request_chan(&aq->pdev->dev, "rx"); + if (IS_ERR(aq->rx_chan)) { + aq->rx_chan = NULL; + return dev_err_probe(&aq->pdev->dev, PTR_ERR(aq->rx_chan), + "RX DMA channel is not available\n"); + } + + aq->tx_chan = dma_request_chan(&aq->pdev->dev, "tx"); + if (IS_ERR(aq->tx_chan)) { + ret = dev_err_probe(&aq->pdev->dev, PTR_ERR(aq->tx_chan), + "TX DMA channel is not available\n"); + goto release_rx_chan; + } + + ctrl->dma_rx = aq->rx_chan; + ctrl->dma_tx = aq->tx_chan; + init_completion(&aq->dma_completion); + + dev_info(&aq->pdev->dev, "Using %s (tx) and %s (rx) for DMA transfers\n", + dma_chan_name(aq->tx_chan), dma_chan_name(aq->rx_chan)); + + return 0; + +release_rx_chan: + dma_release_channel(aq->rx_chan); + aq->rx_chan = NULL; + aq->tx_chan = NULL; + return ret; +} + +static void atmel_qspi_dma_release(struct atmel_qspi *aq) +{ + if (aq->rx_chan) + dma_release_channel(aq->rx_chan); + if (aq->tx_chan) + dma_release_channel(aq->tx_chan); +} + +static const struct atmel_qspi_ops atmel_qspi_ops = { + .set_cfg = atmel_qspi_set_cfg, + .transfer = atmel_qspi_transfer, +}; + +static const struct atmel_qspi_ops atmel_qspi_sama7g5_ops = { + .set_cfg = atmel_qspi_sama7g5_set_cfg, + .transfer = atmel_qspi_sama7g5_transfer, +}; + static int atmel_qspi_probe(struct platform_device *pdev) { struct spi_controller *ctrl; @@ -616,7 +1347,27 @@ static int atmel_qspi_probe(struct platform_device *pdev) if (!ctrl) return -ENOMEM; + aq = spi_controller_get_devdata(ctrl); + + aq->caps = of_device_get_match_data(&pdev->dev); + if (!aq->caps) { + dev_err(&pdev->dev, "Could not retrieve QSPI caps\n"); + return -EINVAL; + } + + init_completion(&aq->cmd_completion); + aq->pdev = pdev; + ctrl->mode_bits = SPI_RX_DUAL | SPI_RX_QUAD | SPI_TX_DUAL | SPI_TX_QUAD; + if (aq->caps->octal) + ctrl->mode_bits |= SPI_RX_OCTAL | SPI_TX_OCTAL; + + if (aq->caps->has_gclk) + aq->ops = &atmel_qspi_sama7g5_ops; + else + aq->ops = &atmel_qspi_ops; + + ctrl->max_speed_hz = aq->caps->max_speed_hz; ctrl->setup = atmel_qspi_setup; ctrl->set_cs_timing = atmel_qspi_set_cs_timing; ctrl->bus_num = -1; @@ -625,11 +1376,6 @@ static int atmel_qspi_probe(struct platform_device *pdev) ctrl->dev.of_node = pdev->dev.of_node; platform_set_drvdata(pdev, ctrl); - aq = spi_controller_get_devdata(ctrl); - - init_completion(&aq->cmd_completion); - aq->pdev = pdev; - /* Map the registers */ aq->regs = devm_platform_ioremap_resource_byname(pdev, "qspi_base"); if (IS_ERR(aq->regs)) @@ -644,57 +1390,52 @@ static int atmel_qspi_probe(struct platform_device *pdev) "missing AHB memory\n"); aq->mmap_size = resource_size(res); + aq->mmap_phys_base = (dma_addr_t)res->start; /* Get the peripheral clock */ - aq->pclk = devm_clk_get(&pdev->dev, "pclk"); + aq->pclk = devm_clk_get_enabled(&pdev->dev, "pclk"); if (IS_ERR(aq->pclk)) - aq->pclk = devm_clk_get(&pdev->dev, NULL); + aq->pclk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(aq->pclk)) return dev_err_probe(&pdev->dev, PTR_ERR(aq->pclk), "missing peripheral clock\n"); - /* Enable the peripheral clock */ - err = clk_prepare_enable(aq->pclk); - if (err) - return dev_err_probe(&pdev->dev, err, - "failed to enable the peripheral clock\n"); - - aq->caps = of_device_get_match_data(&pdev->dev); - if (!aq->caps) { - dev_err(&pdev->dev, "Could not retrieve QSPI caps\n"); - err = -EINVAL; - goto disable_pclk; - } - if (aq->caps->has_qspick) { /* Get the QSPI system clock */ - aq->qspick = devm_clk_get(&pdev->dev, "qspick"); + aq->qspick = devm_clk_get_enabled(&pdev->dev, "qspick"); if (IS_ERR(aq->qspick)) { dev_err(&pdev->dev, "missing system clock\n"); err = PTR_ERR(aq->qspick); - goto disable_pclk; + return err; } - /* Enable the QSPI system clock */ - err = clk_prepare_enable(aq->qspick); - if (err) { - dev_err(&pdev->dev, - "failed to enable the QSPI system clock\n"); - goto disable_pclk; + } else if (aq->caps->has_gclk) { + /* Get the QSPI generic clock */ + aq->gclk = devm_clk_get(&pdev->dev, "gclk"); + if (IS_ERR(aq->gclk)) { + dev_err(&pdev->dev, "missing Generic clock\n"); + err = PTR_ERR(aq->gclk); + return err; } } + if (aq->caps->has_dma) { + err = atmel_qspi_dma_init(ctrl); + if (err == -EPROBE_DEFER) + return err; + } + /* Request the IRQ */ irq = platform_get_irq(pdev, 0); if (irq < 0) { err = irq; - goto disable_qspick; + goto dma_release; } err = devm_request_irq(&pdev->dev, irq, atmel_qspi_interrupt, 0, dev_name(&pdev->dev), aq); if (err) - goto disable_qspick; + goto dma_release; pm_runtime_set_autosuspend_delay(&pdev->dev, 500); pm_runtime_use_autosuspend(&pdev->dev); @@ -702,7 +1443,9 @@ static int atmel_qspi_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); pm_runtime_get_noresume(&pdev->dev); - atmel_qspi_init(aq); + err = atmel_qspi_init(aq); + if (err) + goto dma_release; err = spi_register_controller(ctrl); if (err) { @@ -710,21 +1453,57 @@ static int atmel_qspi_probe(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); - goto disable_qspick; + goto dma_release; } pm_runtime_mark_last_busy(&pdev->dev); pm_runtime_put_autosuspend(&pdev->dev); return 0; -disable_qspick: - clk_disable_unprepare(aq->qspick); -disable_pclk: - clk_disable_unprepare(aq->pclk); +dma_release: + if (aq->caps->has_dma) + atmel_qspi_dma_release(aq); return err; } +static int atmel_qspi_sama7g5_suspend(struct atmel_qspi *aq) +{ + int ret; + u32 val; + + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + !(val & QSPI_SR2_RBUSY) && + (val & QSPI_SR2_HIDLE), 40, + ATMEL_QSPI_SYNC_TIMEOUT); + if (ret) + return ret; + + atmel_qspi_write(QSPI_CR_QSPIDIS, aq, QSPI_CR); + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + !(val & QSPI_SR2_QSPIENS), 40, + ATMEL_QSPI_SYNC_TIMEOUT); + if (ret) + return ret; + + clk_disable_unprepare(aq->gclk); + + atmel_qspi_write(QSPI_CR_DLLOFF, aq, QSPI_CR); + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + !(val & QSPI_SR2_DLOCK), 40, + ATMEL_QSPI_TIMEOUT); + if (ret) + return ret; + + ret = readl_poll_timeout(aq->regs + QSPI_SR2, val, + !(val & QSPI_SR2_CALBSY), 40, + ATMEL_QSPI_TIMEOUT); + if (ret) + return ret; + + return 0; +} + static void atmel_qspi_remove(struct platform_device *pdev) { struct spi_controller *ctrl = platform_get_drvdata(pdev); @@ -735,9 +1514,17 @@ static void atmel_qspi_remove(struct platform_device *pdev) ret = pm_runtime_get_sync(&pdev->dev); if (ret >= 0) { + if (aq->caps->has_dma) + atmel_qspi_dma_release(aq); + + if (aq->caps->has_gclk) { + ret = atmel_qspi_sama7g5_suspend(aq); + if (ret) + dev_warn(&pdev->dev, "Failed to de-init device on remove: %d\n", ret); + return; + } + atmel_qspi_write(QSPI_CR_QSPIDIS, aq, QSPI_CR); - clk_disable(aq->qspick); - clk_disable(aq->pclk); } else { /* * atmel_qspi_runtime_{suspend,resume} just disable and enable @@ -747,9 +1534,6 @@ static void atmel_qspi_remove(struct platform_device *pdev) dev_warn(&pdev->dev, "Failed to resume device on remove\n"); } - clk_unprepare(aq->qspick); - clk_unprepare(aq->pclk); - pm_runtime_disable(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); @@ -765,6 +1549,12 @@ static int __maybe_unused atmel_qspi_suspend(struct device *dev) if (ret < 0) return ret; + if (aq->caps->has_gclk) { + ret = atmel_qspi_sama7g5_suspend(aq); + clk_disable_unprepare(aq->pclk); + return ret; + } + atmel_qspi_write(QSPI_CR_QSPIDIS, aq, QSPI_CR); pm_runtime_mark_last_busy(dev); @@ -792,6 +1582,9 @@ static int __maybe_unused atmel_qspi_resume(struct device *dev) return ret; } + if (aq->caps->has_gclk) + return atmel_qspi_sama7g5_init(aq); + ret = pm_runtime_force_resume(dev); if (ret < 0) return ret; @@ -847,6 +1640,19 @@ static const struct atmel_qspi_caps atmel_sam9x60_qspi_caps = { .has_ricr = true, }; +static const struct atmel_qspi_caps atmel_sama7g5_ospi_caps = { + .max_speed_hz = SAMA7G5_QSPI0_MAX_SPEED_HZ, + .has_gclk = true, + .octal = true, + .has_dma = true, +}; + +static const struct atmel_qspi_caps atmel_sama7g5_qspi_caps = { + .max_speed_hz = SAMA7G5_QSPI1_SDR_MAX_SPEED_HZ, + .has_gclk = true, + .has_dma = true, +}; + static const struct of_device_id atmel_qspi_dt_ids[] = { { .compatible = "atmel,sama5d2-qspi", @@ -856,6 +1662,15 @@ static const struct of_device_id atmel_qspi_dt_ids[] = { .compatible = "microchip,sam9x60-qspi", .data = &atmel_sam9x60_qspi_caps, }, + { + .compatible = "microchip,sama7g5-ospi", + .data = &atmel_sama7g5_ospi_caps, + }, + { + .compatible = "microchip,sama7g5-qspi", + .data = &atmel_sama7g5_qspi_caps, + }, + { /* sentinel */ } }; diff --git a/drivers/spi/spi-amd.c b/drivers/spi/spi-amd.c index d30a21b0b05f..c85997478b81 100644 --- a/drivers/spi/spi-amd.c +++ b/drivers/spi/spi-amd.c @@ -298,19 +298,16 @@ static const struct amd_spi_freq amd_spi_freq[] = { { AMD_SPI_MIN_HZ, F_800KHz, 0}, }; -static int amd_set_spi_freq(struct amd_spi *amd_spi, u32 speed_hz) +static void amd_set_spi_freq(struct amd_spi *amd_spi, u32 speed_hz) { unsigned int i, spd7_val, alt_spd; - if (speed_hz < AMD_SPI_MIN_HZ) - return -EINVAL; - for (i = 0; i < ARRAY_SIZE(amd_spi_freq); i++) if (speed_hz >= amd_spi_freq[i].speed_hz) break; if (amd_spi->speed_hz == amd_spi_freq[i].speed_hz) - return 0; + return; amd_spi->speed_hz = amd_spi_freq[i].speed_hz; @@ -329,8 +326,6 @@ static int amd_set_spi_freq(struct amd_spi *amd_spi, u32 speed_hz) amd_spi_setclear_reg32(amd_spi, AMD_SPI_SPEED_REG, spd7_val, AMD_SPI_SPD7_MASK); } - - return 0; } static inline int amd_spi_fifo_xfer(struct amd_spi *amd_spi, @@ -479,6 +474,9 @@ static bool amd_spi_supports_op(struct spi_mem *mem, return false; } + if (op->max_freq < mem->spi->controller->min_speed_hz) + return false; + return spi_mem_default_supports_op(mem, op); } @@ -672,13 +670,10 @@ static int amd_spi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op) { struct amd_spi *amd_spi; - int ret; amd_spi = spi_controller_get_devdata(mem->spi->controller); - ret = amd_set_spi_freq(amd_spi, mem->spi->max_speed_hz); - if (ret) - return ret; + amd_set_spi_freq(amd_spi, op->max_freq); if (amd_spi->version == AMD_SPI_V2) amd_set_spi_addr_mode(amd_spi, op); @@ -693,10 +688,10 @@ static int amd_spi_exec_mem_op(struct spi_mem *mem, amd_spi_mem_data_out(amd_spi, op); break; default: - ret = -EOPNOTSUPP; + return -EOPNOTSUPP; } - return ret; + return 0; } static const struct spi_controller_mem_ops amd_spi_mem_ops = { @@ -705,6 +700,10 @@ static const struct spi_controller_mem_ops amd_spi_mem_ops = { .supports_op = amd_spi_supports_op, }; +static const struct spi_controller_mem_caps amd_spi_mem_caps = { + .per_op_freq = true, +}; + static int amd_spi_host_transfer(struct spi_controller *host, struct spi_message *msg) { @@ -782,6 +781,7 @@ static int amd_spi_probe(struct platform_device *pdev) host->setup = amd_spi_host_setup; host->transfer_one_message = amd_spi_host_transfer; host->mem_ops = &amd_spi_mem_ops; + host->mem_caps = &amd_spi_mem_caps; host->max_transfer_size = amd_spi_max_transfer_size; host->max_message_size = amd_spi_max_transfer_size; diff --git a/drivers/spi/spi-amlogic-spifc-a1.c b/drivers/spi/spi-amlogic-spifc-a1.c index fadf6667cd51..18c9aa2cbc29 100644 --- a/drivers/spi/spi-amlogic-spifc-a1.c +++ b/drivers/spi/spi-amlogic-spifc-a1.c @@ -259,7 +259,7 @@ static int amlogic_spifc_a1_exec_op(struct spi_mem *mem, size_t data_size = op->data.nbytes; int ret; - ret = amlogic_spifc_a1_set_freq(spifc, mem->spi->max_speed_hz); + ret = amlogic_spifc_a1_set_freq(spifc, op->max_freq); if (ret) return ret; @@ -320,6 +320,10 @@ static const struct spi_controller_mem_ops amlogic_spifc_a1_mem_ops = { .adjust_op_size = amlogic_spifc_a1_adjust_op_size, }; +static const struct spi_controller_mem_caps amlogic_spifc_a1_mem_caps = { + .per_op_freq = true, +}; + static int amlogic_spifc_a1_probe(struct platform_device *pdev) { struct spi_controller *ctrl; @@ -356,6 +360,7 @@ static int amlogic_spifc_a1_probe(struct platform_device *pdev) ctrl->bits_per_word_mask = SPI_BPW_MASK(8); ctrl->auto_runtime_pm = true; ctrl->mem_ops = &amlogic_spifc_a1_mem_ops; + ctrl->mem_caps = &amlogic_spifc_a1_mem_caps; ctrl->min_speed_hz = SPIFC_A1_MIN_HZ; ctrl->max_speed_hz = SPIFC_A1_MAX_HZ; ctrl->mode_bits = (SPI_RX_DUAL | SPI_TX_DUAL | diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index a031ecb358e0..0cd37a7436d5 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -43,10 +43,13 @@ static_assert(CQSPI_MAX_CHIPSELECT <= SPI_CS_CNT_MAX); #define CQSPI_SLOW_SRAM BIT(4) #define CQSPI_NEEDS_APB_AHB_HAZARD_WAR BIT(5) #define CQSPI_RD_NO_IRQ BIT(6) -#define CQSPI_DISABLE_STIG_MODE BIT(7) +#define CQSPI_DMA_SET_MASK BIT(7) +#define CQSPI_SUPPORT_DEVICE_RESET BIT(8) +#define CQSPI_DISABLE_STIG_MODE BIT(9) /* Capabilities */ #define CQSPI_SUPPORTS_OCTAL BIT(0) +#define CQSPI_SUPPORTS_QUAD BIT(1) #define CQSPI_OP_WIDTH(part) ((part).nbytes ? ilog2((part).buswidth) : 0) @@ -111,7 +114,7 @@ struct cqspi_st { struct cqspi_driver_platdata { u32 hwcaps_mask; - u8 quirks; + u16 quirks; int (*indirect_read_dma)(struct cqspi_flash_pdata *f_pdata, u_char *rxbuf, loff_t from_addr, size_t n_rx); u32 (*get_dma_status)(struct cqspi_st *cqspi); @@ -146,6 +149,8 @@ struct cqspi_driver_platdata { #define CQSPI_REG_CONFIG_IDLE_LSB 31 #define CQSPI_REG_CONFIG_CHIPSELECT_MASK 0xF #define CQSPI_REG_CONFIG_BAUD_MASK 0xF +#define CQSPI_REG_CONFIG_RESET_PIN_FLD_MASK BIT(5) +#define CQSPI_REG_CONFIG_RESET_CFG_FLD_MASK BIT(6) #define CQSPI_REG_RD_INSTR 0x04 #define CQSPI_REG_RD_INSTR_OPCODE_LSB 0 @@ -832,6 +837,25 @@ failrd: return ret; } +static void cqspi_device_reset(struct cqspi_st *cqspi) +{ + u32 reg; + + reg = readl(cqspi->iobase + CQSPI_REG_CONFIG); + reg |= CQSPI_REG_CONFIG_RESET_CFG_FLD_MASK; + writel(reg, cqspi->iobase + CQSPI_REG_CONFIG); + /* + * NOTE: Delay timing implementation is derived from + * spi_nor_hw_reset() + */ + writel(reg & ~CQSPI_REG_CONFIG_RESET_PIN_FLD_MASK, cqspi->iobase + CQSPI_REG_CONFIG); + usleep_range(1, 5); + writel(reg | CQSPI_REG_CONFIG_RESET_PIN_FLD_MASK, cqspi->iobase + CQSPI_REG_CONFIG); + usleep_range(100, 150); + writel(reg & ~CQSPI_REG_CONFIG_RESET_PIN_FLD_MASK, cqspi->iobase + CQSPI_REG_CONFIG); + usleep_range(1000, 1200); +} + static void cqspi_controller_enable(struct cqspi_st *cqspi, bool enable) { void __iomem *reg_base = cqspi->iobase; @@ -1409,7 +1433,7 @@ static int cqspi_mem_process(struct spi_mem *mem, const struct spi_mem_op *op) struct cqspi_flash_pdata *f_pdata; f_pdata = &cqspi->f_pdata[spi_get_chipselect(mem->spi, 0)]; - cqspi_configure(f_pdata, mem->spi->max_speed_hz); + cqspi_configure(f_pdata, op->max_freq); if (op->data.dir == SPI_MEM_DATA_IN && op->data.buf.in) { /* @@ -1658,6 +1682,7 @@ static const struct spi_controller_mem_ops cqspi_mem_ops = { static const struct spi_controller_mem_caps cqspi_mem_caps = { .dtr = true, + .per_op_freq = true, }; static int cqspi_setup_flash(struct cqspi_st *cqspi) @@ -1865,6 +1890,8 @@ static int cqspi_probe(struct platform_device *pdev) cqspi->master_ref_clk_hz); if (ddata->hwcaps_mask & CQSPI_SUPPORTS_OCTAL) host->mode_bits |= SPI_RX_OCTAL | SPI_TX_OCTAL; + if (ddata->hwcaps_mask & CQSPI_SUPPORTS_QUAD) + host->mode_bits |= SPI_TX_QUAD; if (!(ddata->quirks & CQSPI_DISABLE_DAC_MODE)) { cqspi->use_direct_mode = true; cqspi->use_direct_mode_wr = true; @@ -1886,8 +1913,7 @@ static int cqspi_probe(struct platform_device *pdev) if (ddata->quirks & CQSPI_DISABLE_STIG_MODE) cqspi->disable_stig_mode = true; - if (of_device_is_compatible(pdev->dev.of_node, - "xlnx,versal-ospi-1.0")) { + if (ddata->quirks & CQSPI_DMA_SET_MASK) { ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); if (ret) goto probe_reset_failed; @@ -1917,6 +1943,9 @@ static int cqspi_probe(struct platform_device *pdev) host->num_chipselect = cqspi->num_chipselect; + if (ddata->quirks & CQSPI_SUPPORT_DEVICE_RESET) + cqspi_device_reset(cqspi); + if (cqspi->use_direct_mode) { ret = cqspi_request_mmap_dma(cqspi); if (ret == -EPROBE_DEFER) @@ -2037,7 +2066,7 @@ static const struct cqspi_driver_platdata k2g_qspi = { }; static const struct cqspi_driver_platdata am654_ospi = { - .hwcaps_mask = CQSPI_SUPPORTS_OCTAL, + .hwcaps_mask = CQSPI_SUPPORTS_OCTAL | CQSPI_SUPPORTS_QUAD, .quirks = CQSPI_NEEDS_WR_DELAY, }; @@ -2054,7 +2083,17 @@ static const struct cqspi_driver_platdata socfpga_qspi = { static const struct cqspi_driver_platdata versal_ospi = { .hwcaps_mask = CQSPI_SUPPORTS_OCTAL, - .quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_SUPPORT_EXTERNAL_DMA, + .quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_SUPPORT_EXTERNAL_DMA + | CQSPI_DMA_SET_MASK, + .indirect_read_dma = cqspi_versal_indirect_read_dma, + .get_dma_status = cqspi_get_versal_dma_status, +}; + +static const struct cqspi_driver_platdata versal2_ospi = { + .hwcaps_mask = CQSPI_SUPPORTS_OCTAL, + .quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_SUPPORT_EXTERNAL_DMA + | CQSPI_DMA_SET_MASK + | CQSPI_SUPPORT_DEVICE_RESET, .indirect_read_dma = cqspi_versal_indirect_read_dma, .get_dma_status = cqspi_get_versal_dma_status, }; @@ -2111,6 +2150,10 @@ static const struct of_device_id cqspi_dt_ids[] = { .compatible = "mobileye,eyeq5-ospi", .data = &mobileye_eyeq5_ospi, }, + { + .compatible = "amd,versal2-ospi", + .data = &versal2_ospi, + }, { /* end of table */ } }; diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c index ea517af9435f..941ecc6f59f8 100644 --- a/drivers/spi/spi-dw-core.c +++ b/drivers/spi/spi-dw-core.c @@ -677,7 +677,7 @@ static int dw_spi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op) * operation. Transmit-only mode is suitable for the rest of them. */ cfg.dfs = 8; - cfg.freq = clamp(mem->spi->max_speed_hz, 0U, dws->max_mem_freq); + cfg.freq = clamp(op->max_freq, 0U, dws->max_mem_freq); if (op->data.dir == SPI_MEM_DATA_IN) { cfg.tmode = DW_SPI_CTRLR0_TMOD_EPROMREAD; cfg.ndf = op->data.nbytes; @@ -894,6 +894,10 @@ static void dw_spi_hw_init(struct device *dev, struct dw_spi *dws) dw_writel(dws, DW_SPI_CS_OVERRIDE, 0xF); } +static const struct spi_controller_mem_caps dw_spi_mem_caps = { + .per_op_freq = true, +}; + int dw_spi_add_host(struct device *dev, struct dw_spi *dws) { struct spi_controller *host; @@ -941,8 +945,10 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws) host->set_cs = dw_spi_set_cs; host->transfer_one = dw_spi_transfer_one; host->handle_err = dw_spi_handle_err; - if (dws->mem_ops.exec_op) + if (dws->mem_ops.exec_op) { host->mem_ops = &dws->mem_ops; + host->mem_caps = &dw_spi_mem_caps; + } host->max_speed_hz = dws->max_freq; host->flags = SPI_CONTROLLER_GPIO_SS; host->auto_runtime_pm = true; diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c index 9ec53bf0dda8..355e6a39fb41 100644 --- a/drivers/spi/spi-fsl-qspi.c +++ b/drivers/spi/spi-fsl-qspi.c @@ -522,9 +522,10 @@ static void fsl_qspi_invalidate(struct fsl_qspi *q) qspi_writel(q, reg, q->iobase + QUADSPI_MCR); } -static void fsl_qspi_select_mem(struct fsl_qspi *q, struct spi_device *spi) +static void fsl_qspi_select_mem(struct fsl_qspi *q, struct spi_device *spi, + const struct spi_mem_op *op) { - unsigned long rate = spi->max_speed_hz; + unsigned long rate = op->max_freq; int ret; if (q->selected == spi_get_chipselect(spi, 0)) @@ -652,7 +653,7 @@ static int fsl_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) fsl_qspi_readl_poll_tout(q, base + QUADSPI_SR, (QUADSPI_SR_IP_ACC_MASK | QUADSPI_SR_AHB_ACC_MASK), 10, 1000); - fsl_qspi_select_mem(q, mem->spi); + fsl_qspi_select_mem(q, mem->spi, op); if (needs_amba_base_offset(q)) addr_offset = q->memmap_phy; @@ -839,6 +840,10 @@ static const struct spi_controller_mem_ops fsl_qspi_mem_ops = { .get_name = fsl_qspi_get_name, }; +static const struct spi_controller_mem_caps fsl_qspi_mem_caps = { + .per_op_freq = true, +}; + static int fsl_qspi_probe(struct platform_device *pdev) { struct spi_controller *ctlr; @@ -923,6 +928,7 @@ static int fsl_qspi_probe(struct platform_device *pdev) ctlr->bus_num = -1; ctlr->num_chipselect = 4; ctlr->mem_ops = &fsl_qspi_mem_ops; + ctlr->mem_caps = &fsl_qspi_mem_caps; fsl_qspi_default_setup(q); diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index 856a4a9def66..2f2082652a1a 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -618,7 +618,7 @@ static struct spi_controller *fsl_spi_probe(struct device *dev, if (ret < 0) goto err_probe; - dev_info(dev, "at 0x%p (irq = %d), %s mode\n", reg_base, + dev_info(dev, "at MMIO %pa (irq = %d), %s mode\n", &mem->start, mpc8xxx_spi->irq, mpc8xxx_spi_strmode(mpc8xxx_spi->flags)); return host; diff --git a/drivers/spi/spi-kspi2.c b/drivers/spi/spi-kspi2.c new file mode 100644 index 000000000000..ca73ec52ce63 --- /dev/null +++ b/drivers/spi/spi-kspi2.c @@ -0,0 +1,431 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) KEBA Industrial Automation Gmbh 2024 + * + * Driver for KEBA SPI host controller type 2 FPGA IP core + */ + +#include +#include +#include + +#define KSPI2 "kspi2" + +#define KSPI2_CLK_FREQ_REG 0x03 +#define KSPI2_CLK_FREQ_MASK 0x0f +#define KSPI2_CLK_FREQ_62_5M 0x0 +#define KSPI2_CLK_FREQ_33_3M 0x1 +#define KSPI2_CLK_FREQ_125M 0x2 +#define KSPI2_CLK_FREQ_50M 0x3 +#define KSPI2_CLK_FREQ_100M 0x4 + +#define KSPI2_CONTROL_REG 0x04 +#define KSPI2_CONTROL_CLK_DIV_MAX 0x0f +#define KSPI2_CONTROL_CLK_DIV_MASK 0x0f +#define KSPI2_CONTROL_CPHA 0x10 +#define KSPI2_CONTROL_CPOL 0x20 +#define KSPI2_CONTROL_CLK_MODE_MASK 0x30 +#define KSPI2_CONTROL_INIT KSPI2_CONTROL_CLK_DIV_MAX + +#define KSPI2_STATUS_REG 0x08 +#define KSPI2_STATUS_IN_USE 0x01 +#define KSPI2_STATUS_BUSY 0x02 + +#define KSPI2_DATA_REG 0x0c + +#define KSPI2_CS_NR_REG 0x10 +#define KSPI2_CS_NR_NONE 0xff + +#define KSPI2_MODE_BITS (SPI_CPHA | SPI_CPOL) +#define KSPI2_NUM_CS 255 + +#define KSPI2_SPEED_HZ_MIN(kspi) (kspi->base_speed_hz / 65536) +#define KSPI2_SPEED_HZ_MAX(kspi) (kspi->base_speed_hz / 2) + +/* timeout is 10 times the time to transfer one byte at slowest clock */ +#define KSPI2_XFER_TIMEOUT_US(kspi) (USEC_PER_SEC / \ + KSPI2_SPEED_HZ_MIN(kspi) * 8 * 10) + +#define KSPI2_INUSE_SLEEP_US (2 * USEC_PER_MSEC) +#define KSPI2_INUSE_TIMEOUT_US (10 * USEC_PER_SEC) + +struct kspi2 { + struct keba_spi_auxdev *auxdev; + void __iomem *base; + struct spi_controller *host; + + u32 base_speed_hz; /* SPI base clock frequency in HZ */ + u8 control_shadow; + + struct spi_device **device; + int device_size; +}; + +static int kspi2_inuse_lock(struct kspi2 *kspi) +{ + u8 sts; + int ret; + + /* + * The SPI controller has an IN_USE bit for locking access to the + * controller. This enables the use of the SPI controller by other none + * Linux processors. + * + * If the SPI controller is free, then the first read returns + * IN_USE == 0. After that the SPI controller is locked and further + * reads of IN_USE return 1. + * + * The SPI controller is unlocked by writing 1 into IN_USE. + * + * The IN_USE bit acts as a hardware semaphore for the SPI controller. + * Poll for semaphore, but sleep while polling to free the CPU. + */ + ret = readb_poll_timeout(kspi->base + KSPI2_STATUS_REG, + sts, (sts & KSPI2_STATUS_IN_USE) == 0, + KSPI2_INUSE_SLEEP_US, KSPI2_INUSE_TIMEOUT_US); + if (ret != 0) + dev_warn(&kspi->auxdev->auxdev.dev, "%s err!\n", __func__); + + return ret; +} + +static void kspi2_inuse_unlock(struct kspi2 *kspi) +{ + /* unlock the controller by writing 1 into IN_USE */ + iowrite8(KSPI2_STATUS_IN_USE, kspi->base + KSPI2_STATUS_REG); +} + +static int kspi2_prepare_hardware(struct spi_controller *host) +{ + struct kspi2 *kspi = spi_controller_get_devdata(host); + + /* lock hardware semaphore before actual use of controller */ + return kspi2_inuse_lock(kspi); +} + +static int kspi2_unprepare_hardware(struct spi_controller *host) +{ + struct kspi2 *kspi = spi_controller_get_devdata(host); + + /* unlock hardware semaphore after actual use of controller */ + kspi2_inuse_unlock(kspi); + + return 0; +} + +static u8 kspi2_calc_minimal_divider(struct kspi2 *kspi, u32 max_speed_hz) +{ + u8 div; + + /* + * Divider values 2, 4, 8, 16, ..., 65536 are possible. They are coded + * as 0, 1, 2, 3, ..., 15 in the CONTROL_CLK_DIV bit. + */ + for (div = 0; div < KSPI2_CONTROL_CLK_DIV_MAX; div++) { + if ((kspi->base_speed_hz >> (div + 1)) <= max_speed_hz) + return div; + } + + /* return divider for slowest clock if loop fails to find one */ + return KSPI2_CONTROL_CLK_DIV_MAX; +} + +static void kspi2_write_control_reg(struct kspi2 *kspi, u8 val, u8 mask) +{ + /* write control register only when necessary to improve performance */ + if (val != (kspi->control_shadow & mask)) { + kspi->control_shadow = (kspi->control_shadow & ~mask) | val; + iowrite8(kspi->control_shadow, kspi->base + KSPI2_CONTROL_REG); + } +} + +static int kspi2_txrx_byte(struct kspi2 *kspi, u8 tx, u8 *rx) +{ + u8 sts; + int ret; + + /* start transfer by writing TX byte */ + iowrite8(tx, kspi->base + KSPI2_DATA_REG); + + /* wait till finished (BUSY == 0) */ + ret = readb_poll_timeout(kspi->base + KSPI2_STATUS_REG, + sts, (sts & KSPI2_STATUS_BUSY) == 0, + 0, KSPI2_XFER_TIMEOUT_US(kspi)); + if (ret != 0) + return ret; + + /* read RX byte */ + if (rx) + *rx = ioread8(kspi->base + KSPI2_DATA_REG); + + return 0; +} + +static int kspi2_process_transfer(struct kspi2 *kspi, struct spi_transfer *t) +{ + u8 tx = 0; + u8 rx; + int i; + int ret; + + for (i = 0; i < t->len; i++) { + if (t->tx_buf) + tx = ((const u8 *)t->tx_buf)[i]; + + ret = kspi2_txrx_byte(kspi, tx, &rx); + if (ret) + return ret; + + if (t->rx_buf) + ((u8 *)t->rx_buf)[i] = rx; + } + + return 0; +} + +static int kspi2_setup_transfer(struct kspi2 *kspi, + struct spi_device *spi, + struct spi_transfer *t) +{ + u32 max_speed_hz = spi->max_speed_hz; + u8 clk_div; + + /* + * spi_device (spi) has default parameters. Some of these can be + * overwritten by parameters in spi_transfer (t). + */ + if (t->bits_per_word && ((t->bits_per_word % 8) != 0)) { + dev_err(&spi->dev, "Word width %d not supported!\n", + t->bits_per_word); + + return -EINVAL; + } + + if (t->speed_hz && (t->speed_hz < max_speed_hz)) + max_speed_hz = t->speed_hz; + + clk_div = kspi2_calc_minimal_divider(kspi, max_speed_hz); + kspi2_write_control_reg(kspi, clk_div, KSPI2_CONTROL_CLK_DIV_MASK); + + return 0; +} + +static int kspi2_transfer_one(struct spi_controller *host, + struct spi_device *spi, + struct spi_transfer *t) +{ + struct kspi2 *kspi = spi_controller_get_devdata(host); + int ret; + + ret = kspi2_setup_transfer(kspi, spi, t); + if (ret != 0) + return ret; + + if (t->len) { + ret = kspi2_process_transfer(kspi, t); + if (ret != 0) + return ret; + } + + return 0; +} + +static void kspi2_set_cs(struct spi_device *spi, bool enable) +{ + struct spi_controller *host = spi->controller; + struct kspi2 *kspi = spi_controller_get_devdata(host); + + /* controller is using active low chip select signals by design */ + if (!enable) + iowrite8(spi_get_chipselect(spi, 0), kspi->base + KSPI2_CS_NR_REG); + else + iowrite8(KSPI2_CS_NR_NONE, kspi->base + KSPI2_CS_NR_REG); +} + +static int kspi2_prepare_message(struct spi_controller *host, + struct spi_message *msg) +{ + struct kspi2 *kspi = spi_controller_get_devdata(host); + struct spi_device *spi = msg->spi; + u8 mode = 0; + + /* setup SPI clock phase and polarity */ + if (spi->mode & SPI_CPHA) + mode |= KSPI2_CONTROL_CPHA; + if (spi->mode & SPI_CPOL) + mode |= KSPI2_CONTROL_CPOL; + kspi2_write_control_reg(kspi, mode, KSPI2_CONTROL_CLK_MODE_MASK); + + return 0; +} + +static int kspi2_setup(struct spi_device *spi) +{ + struct kspi2 *kspi = spi_controller_get_devdata(spi->controller); + + /* + * Check only parameters. Actual setup is done in kspi2_prepare_message + * and directly before the SPI transfer starts. + */ + + if (spi->mode & ~KSPI2_MODE_BITS) { + dev_err(&spi->dev, "Mode %d not supported!\n", spi->mode); + + return -EINVAL; + } + + if ((spi->bits_per_word % 8) != 0) { + dev_err(&spi->dev, "Word width %d not supported!\n", + spi->bits_per_word); + + return -EINVAL; + } + + if ((spi->max_speed_hz == 0) || + (spi->max_speed_hz > KSPI2_SPEED_HZ_MAX(kspi))) + spi->max_speed_hz = KSPI2_SPEED_HZ_MAX(kspi); + + if (spi->max_speed_hz < KSPI2_SPEED_HZ_MIN(kspi)) { + dev_err(&spi->dev, "Requested speed of %d Hz is too low!\n", + spi->max_speed_hz); + + return -EINVAL; + } + + return 0; +} + +static void kspi2_unregister_devices(struct kspi2 *kspi) +{ + int i; + + for (i = 0; i < kspi->device_size; i++) { + struct spi_device *device = kspi->device[i]; + + if (device) + spi_unregister_device(device); + } +} + +static int kspi2_register_devices(struct kspi2 *kspi) +{ + struct spi_board_info *info = kspi->auxdev->info; + int i; + + /* register all known SPI devices */ + for (i = 0; i < kspi->auxdev->info_size; i++) { + struct spi_device *device = spi_new_device(kspi->host, &info[i]); + + if (!device) { + kspi2_unregister_devices(kspi); + + return -ENODEV; + } + kspi->device[i] = device; + } + + return 0; +} + +static void kspi2_init(struct kspi2 *kspi) +{ + iowrite8(KSPI2_CONTROL_INIT, kspi->base + KSPI2_CONTROL_REG); + kspi->control_shadow = KSPI2_CONTROL_INIT; + + iowrite8(KSPI2_CS_NR_NONE, kspi->base + KSPI2_CS_NR_REG); +} + +static int kspi2_probe(struct auxiliary_device *auxdev, + const struct auxiliary_device_id *id) +{ + struct device *dev = &auxdev->dev; + struct spi_controller *host; + struct kspi2 *kspi; + u8 clk_reg; + int ret; + + host = devm_spi_alloc_host(dev, sizeof(struct kspi2)); + if (!host) + return -ENOMEM; + kspi = spi_controller_get_devdata(host); + kspi->auxdev = container_of(auxdev, struct keba_spi_auxdev, auxdev); + kspi->host = host; + kspi->device = devm_kcalloc(dev, kspi->auxdev->info_size, + sizeof(*kspi->device), GFP_KERNEL); + if (!kspi->device) + return -ENOMEM; + kspi->device_size = kspi->auxdev->info_size; + auxiliary_set_drvdata(auxdev, kspi); + + kspi->base = devm_ioremap_resource(dev, &kspi->auxdev->io); + if (IS_ERR(kspi->base)) + return PTR_ERR(kspi->base); + + /* read the SPI base clock frequency */ + clk_reg = ioread8(kspi->base + KSPI2_CLK_FREQ_REG); + switch (clk_reg & KSPI2_CLK_FREQ_MASK) { + case KSPI2_CLK_FREQ_62_5M: + kspi->base_speed_hz = 62500000; break; + case KSPI2_CLK_FREQ_33_3M: + kspi->base_speed_hz = 33333333; break; + case KSPI2_CLK_FREQ_125M: + kspi->base_speed_hz = 125000000; break; + case KSPI2_CLK_FREQ_50M: + kspi->base_speed_hz = 50000000; break; + case KSPI2_CLK_FREQ_100M: + kspi->base_speed_hz = 100000000; break; + default: + dev_err(dev, "Undefined SPI base clock frequency!\n"); + return -ENODEV; + } + + kspi2_init(kspi); + + host->bus_num = -1; + host->num_chipselect = KSPI2_NUM_CS; + host->mode_bits = KSPI2_MODE_BITS; + host->setup = kspi2_setup; + host->prepare_transfer_hardware = kspi2_prepare_hardware; + host->unprepare_transfer_hardware = kspi2_unprepare_hardware; + host->prepare_message = kspi2_prepare_message; + host->set_cs = kspi2_set_cs; + host->transfer_one = kspi2_transfer_one; + ret = devm_spi_register_controller(dev, host); + if (ret) { + dev_err(dev, "Failed to register host (%d)!\n", ret); + return ret; + } + + ret = kspi2_register_devices(kspi); + if (ret) { + dev_err(dev, "Failed to register devices (%d)!\n", ret); + return ret; + } + + return 0; +} + +static void kspi2_remove(struct auxiliary_device *auxdev) +{ + struct kspi2 *kspi = auxiliary_get_drvdata(auxdev); + + kspi2_unregister_devices(kspi); +} + +static const struct auxiliary_device_id kspi2_devtype_aux[] = { + { .name = "keba.spi" }, + { }, +}; +MODULE_DEVICE_TABLE(auxiliary, kspi2_devtype_aux); + +static struct auxiliary_driver kspi2_driver_aux = { + .name = KSPI2, + .id_table = kspi2_devtype_aux, + .probe = kspi2_probe, + .remove = kspi2_remove, +}; +module_auxiliary_driver(kspi2_driver_aux); + +MODULE_AUTHOR("Gerhard Engleder "); +MODULE_DESCRIPTION("KEBA SPI host controller driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index abc6792e738c..a9f0f47f4759 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -187,6 +187,16 @@ bool spi_mem_default_supports_op(struct spi_mem *mem, return false; } + if (op->max_freq && mem->spi->controller->min_speed_hz && + op->max_freq < mem->spi->controller->min_speed_hz) + return false; + + if (op->max_freq && + op->max_freq < mem->spi->max_speed_hz) { + if (!spi_mem_controller_is_capable(ctlr, per_op_freq)) + return false; + } + return spi_mem_check_buswidth(mem, op); } EXPORT_SYMBOL_GPL(spi_mem_default_supports_op); @@ -364,6 +374,9 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) u8 *tmpbuf; int ret; + /* Make sure the operation frequency is correct before going futher */ + spi_mem_adjust_op_freq(mem, (struct spi_mem_op *)op); + ret = spi_mem_check_op(op); if (ret) return ret; @@ -410,6 +423,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) xfers[xferpos].tx_buf = tmpbuf; xfers[xferpos].len = op->cmd.nbytes; xfers[xferpos].tx_nbits = op->cmd.buswidth; + xfers[xferpos].speed_hz = op->max_freq; spi_message_add_tail(&xfers[xferpos], &msg); xferpos++; totalxferlen++; @@ -424,6 +438,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) xfers[xferpos].tx_buf = tmpbuf + 1; xfers[xferpos].len = op->addr.nbytes; xfers[xferpos].tx_nbits = op->addr.buswidth; + xfers[xferpos].speed_hz = op->max_freq; spi_message_add_tail(&xfers[xferpos], &msg); xferpos++; totalxferlen += op->addr.nbytes; @@ -435,6 +450,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) xfers[xferpos].len = op->dummy.nbytes; xfers[xferpos].tx_nbits = op->dummy.buswidth; xfers[xferpos].dummy_data = 1; + xfers[xferpos].speed_hz = op->max_freq; spi_message_add_tail(&xfers[xferpos], &msg); xferpos++; totalxferlen += op->dummy.nbytes; @@ -450,6 +466,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) } xfers[xferpos].len = op->data.nbytes; + xfers[xferpos].speed_hz = op->max_freq; spi_message_add_tail(&xfers[xferpos], &msg); xferpos++; totalxferlen += op->data.nbytes; @@ -528,6 +545,53 @@ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op) } EXPORT_SYMBOL_GPL(spi_mem_adjust_op_size); +/** + * spi_mem_adjust_op_freq() - Adjust the frequency of a SPI mem operation to + * match controller, PCB and chip limitations + * @mem: the SPI memory + * @op: the operation to adjust + * + * Some chips have per-op frequency limitations and must adapt the maximum + * speed. This function allows SPI mem drivers to set @op->max_freq to the + * maximum supported value. + */ +void spi_mem_adjust_op_freq(struct spi_mem *mem, struct spi_mem_op *op) +{ + if (!op->max_freq || op->max_freq > mem->spi->max_speed_hz) + op->max_freq = mem->spi->max_speed_hz; +} +EXPORT_SYMBOL_GPL(spi_mem_adjust_op_freq); + +/** + * spi_mem_calc_op_duration() - Derives the theoretical length (in ns) of an + * operation. This helps finding the best variant + * among a list of possible choices. + * @op: the operation to benchmark + * + * Some chips have per-op frequency limitations, PCBs usually have their own + * limitations as well, and controllers can support dual, quad or even octal + * modes, sometimes in DTR. All these combinations make it impossible to + * statically list the best combination for all situations. If we want something + * accurate, all these combinations should be rated (eg. with a time estimate) + * and the best pick should be taken based on these calculations. + * + * Returns a ns estimate for the time this op would take. + */ +u64 spi_mem_calc_op_duration(struct spi_mem_op *op) +{ + u64 ncycles = 0; + u32 ns_per_cycles; + + ns_per_cycles = 1000000000 / op->max_freq; + ncycles += ((op->cmd.nbytes * 8) / op->cmd.buswidth) / (op->cmd.dtr ? 2 : 1); + ncycles += ((op->addr.nbytes * 8) / op->addr.buswidth) / (op->addr.dtr ? 2 : 1); + ncycles += ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1); + ncycles += ((op->data.nbytes * 8) / op->data.buswidth) / (op->data.dtr ? 2 : 1); + + return ncycles * ns_per_cycles; +} +EXPORT_SYMBOL_GPL(spi_mem_calc_op_duration); + static ssize_t spi_mem_no_dirmap_read(struct spi_mem_dirmap_desc *desc, u64 offs, size_t len, void *buf) { diff --git a/drivers/spi/spi-microchip-core-qspi.c b/drivers/spi/spi-microchip-core-qspi.c index ad2b5ffa6153..fa828fcaaef2 100644 --- a/drivers/spi/spi-microchip-core-qspi.c +++ b/drivers/spi/spi-microchip-core-qspi.c @@ -265,7 +265,8 @@ static irqreturn_t mchp_coreqspi_isr(int irq, void *dev_id) return ret; } -static int mchp_coreqspi_setup_clock(struct mchp_coreqspi *qspi, struct spi_device *spi) +static int mchp_coreqspi_setup_clock(struct mchp_coreqspi *qspi, struct spi_device *spi, + const struct spi_mem_op *op) { unsigned long clk_hz; u32 control, baud_rate_val = 0; @@ -274,11 +275,11 @@ static int mchp_coreqspi_setup_clock(struct mchp_coreqspi *qspi, struct spi_devi if (!clk_hz) return -EINVAL; - baud_rate_val = DIV_ROUND_UP(clk_hz, 2 * spi->max_speed_hz); + baud_rate_val = DIV_ROUND_UP(clk_hz, 2 * op->max_freq); if (baud_rate_val > MAX_DIVIDER || baud_rate_val < MIN_DIVIDER) { dev_err(&spi->dev, "could not configure the clock for spi clock %d Hz & system clock %ld Hz\n", - spi->max_speed_hz, clk_hz); + op->max_freq, clk_hz); return -EINVAL; } @@ -399,7 +400,7 @@ static int mchp_coreqspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *o if (err) goto error; - err = mchp_coreqspi_setup_clock(qspi, mem->spi); + err = mchp_coreqspi_setup_clock(qspi, mem->spi, op); if (err) goto error; @@ -457,6 +458,10 @@ error: static bool mchp_coreqspi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) { + struct mchp_coreqspi *qspi = spi_controller_get_devdata(mem->spi->controller); + unsigned long clk_hz; + u32 baud_rate_val; + if (!spi_mem_default_supports_op(mem, op)) return false; @@ -479,6 +484,14 @@ static bool mchp_coreqspi_supports_op(struct spi_mem *mem, const struct spi_mem_ return false; } + clk_hz = clk_get_rate(qspi->clk); + if (!clk_hz) + return false; + + baud_rate_val = DIV_ROUND_UP(clk_hz, 2 * op->max_freq); + if (baud_rate_val > MAX_DIVIDER || baud_rate_val < MIN_DIVIDER) + return false; + return true; } @@ -498,6 +511,10 @@ static const struct spi_controller_mem_ops mchp_coreqspi_mem_ops = { .exec_op = mchp_coreqspi_exec_op, }; +static const struct spi_controller_mem_caps mchp_coreqspi_mem_caps = { + .per_op_freq = true, +}; + static int mchp_coreqspi_probe(struct platform_device *pdev) { struct spi_controller *ctlr; @@ -540,6 +557,7 @@ static int mchp_coreqspi_probe(struct platform_device *pdev) ctlr->bits_per_word_mask = SPI_BPW_MASK(8); ctlr->mem_ops = &mchp_coreqspi_mem_ops; + ctlr->mem_caps = &mchp_coreqspi_mem_caps; ctlr->setup = mchp_coreqspi_setup_op; ctlr->mode_bits = SPI_CPOL | SPI_CPHA | SPI_RX_DUAL | SPI_RX_QUAD | SPI_TX_DUAL | SPI_TX_QUAD; diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 85f3bafc975d..197bf2dbe5de 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -961,7 +961,7 @@ static int mtk_spi_mem_exec_op(struct spi_mem *mem, mtk_spi_reset(mdata); mtk_spi_hw_init(mem->spi->controller, mem->spi); - mtk_spi_prepare_transfer(mem->spi->controller, mem->spi->max_speed_hz); + mtk_spi_prepare_transfer(mem->spi->controller, op->max_freq); reg_val = readl(mdata->base + SPI_CFG3_IPM_REG); /* opcode byte len */ @@ -1122,6 +1122,10 @@ static const struct spi_controller_mem_ops mtk_spi_mem_ops = { .exec_op = mtk_spi_mem_exec_op, }; +static const struct spi_controller_mem_caps mtk_spi_mem_caps = { + .per_op_freq = true, +}; + static int mtk_spi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1160,6 +1164,7 @@ static int mtk_spi_probe(struct platform_device *pdev) if (mdata->dev_comp->ipm_design) { mdata->dev = dev; host->mem_ops = &mtk_spi_mem_ops; + host->mem_caps = &mtk_spi_mem_caps; init_completion(&mdata->spimem_done); } diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c index 809767d3145c..eeaea6a5e310 100644 --- a/drivers/spi/spi-mxic.c +++ b/drivers/spi/spi-mxic.c @@ -522,7 +522,7 @@ static int mxic_spi_mem_exec_op(struct spi_mem *mem, int i, ret; u8 addr[8], cmd[2]; - ret = mxic_spi_set_freq(mxic, mem->spi->max_speed_hz); + ret = mxic_spi_set_freq(mxic, op->max_freq); if (ret) return ret; @@ -582,6 +582,7 @@ static const struct spi_controller_mem_caps mxic_spi_mem_caps = { .dtr = true, .ecc = true, .swap16 = true, + .per_op_freq = true, }; static void mxic_spi_set_cs(struct spi_device *spi, bool lvl) diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c index e6d955d964f4..43455305fdf4 100644 --- a/drivers/spi/spi-mxs.c +++ b/drivers/spi/spi-mxs.c @@ -381,6 +381,8 @@ static int mxs_spi_transfer_one(struct spi_controller *host, if (status) break; + t->effective_speed_hz = ssp->clk_rate; + /* De-assert on last transfer, inverted by cs_change flag */ flag = (&t->transfer_list == m->transfers.prev) ^ t->cs_change ? TXRX_DEASSERT_CS : 0; diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index 1161b9e5a4dc..bad6b30bab0e 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -705,9 +705,10 @@ static void nxp_fspi_dll_calibration(struct nxp_fspi *f) * Value for rest of the CS FLSHxxCR0 register would be zero. * */ -static void nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi) +static void nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi, + const struct spi_mem_op *op) { - unsigned long rate = spi->max_speed_hz; + unsigned long rate = op->max_freq; int ret; uint64_t size_kb; @@ -931,7 +932,7 @@ static int nxp_fspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) FSPI_STS0_ARB_IDLE, 1, POLL_TOUT, true); WARN_ON(err); - nxp_fspi_select_mem(f, mem->spi); + nxp_fspi_select_mem(f, mem->spi, op); nxp_fspi_prepare_lut(f, op); /* @@ -1149,6 +1150,10 @@ static const struct spi_controller_mem_ops nxp_fspi_mem_ops = { .get_name = nxp_fspi_get_name, }; +static const struct spi_controller_mem_caps nxp_fspi_mem_caps = { + .per_op_freq = true, +}; + static int nxp_fspi_probe(struct platform_device *pdev) { struct spi_controller *ctlr; @@ -1246,6 +1251,7 @@ static int nxp_fspi_probe(struct platform_device *pdev) ctlr->bus_num = -1; ctlr->num_chipselect = NXP_FSPI_MAX_CHIPSELECT; ctlr->mem_ops = &nxp_fspi_mem_ops; + ctlr->mem_caps = &nxp_fspi_mem_caps; nxp_fspi_default_setup(f); diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index add6247d3481..29c616e2c408 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -1561,10 +1561,15 @@ static int omap2_mcspi_probe(struct platform_device *pdev) } mcspi->ref_clk = devm_clk_get_optional_enabled(&pdev->dev, NULL); - if (IS_ERR(mcspi->ref_clk)) - mcspi->ref_clk_hz = OMAP2_MCSPI_MAX_FREQ; - else + if (IS_ERR(mcspi->ref_clk)) { + status = PTR_ERR(mcspi->ref_clk); + dev_err_probe(&pdev->dev, status, "Failed to get ref_clk"); + goto free_ctlr; + } + if (mcspi->ref_clk) mcspi->ref_clk_hz = clk_get_rate(mcspi->ref_clk); + else + mcspi->ref_clk_hz = OMAP2_MCSPI_MAX_FREQ; ctlr->max_speed_hz = mcspi->ref_clk_hz; ctlr->min_speed_hz = mcspi->ref_clk_hz >> 15; diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 903d76145272..5f9cac41baff 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -73,8 +73,9 @@ struct chip_data { #define LPSS_CAPS_CS_EN_MASK (0xf << LPSS_CAPS_CS_EN_SHIFT) #define LPSS_PRIV_CLOCK_GATE 0x38 -#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK 0x3 -#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON 0x3 +#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK 0x3 +#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON 0x3 +#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_OFF 0x0 struct lpss_config { /* LPSS offset from drv_data->ioaddr */ @@ -321,6 +322,20 @@ static void __lpss_ssp_write_priv(struct driver_data *drv_data, writel(value, drv_data->lpss_base + offset); } +static bool __lpss_ssp_update_priv(struct driver_data *drv_data, unsigned int offset, + u32 mask, u32 value) +{ + u32 new, curr; + + curr = __lpss_ssp_read_priv(drv_data, offset); + new = (curr & ~mask) | (value & mask); + if (new == curr) + return false; + + __lpss_ssp_write_priv(drv_data, offset, new); + return true; +} + /* * lpss_ssp_setup - perform LPSS SSP specific setup * @drv_data: pointer to the driver private data @@ -337,21 +352,16 @@ static void lpss_ssp_setup(struct driver_data *drv_data) drv_data->lpss_base = drv_data->ssp->mmio_base + config->offset; /* Enable software chip select control */ - value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl); - value &= ~(LPSS_CS_CONTROL_SW_MODE | LPSS_CS_CONTROL_CS_HIGH); - value |= LPSS_CS_CONTROL_SW_MODE | LPSS_CS_CONTROL_CS_HIGH; - __lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value); + value = LPSS_CS_CONTROL_SW_MODE | LPSS_CS_CONTROL_CS_HIGH; + __lpss_ssp_update_priv(drv_data, config->reg_cs_ctrl, value, value); /* Enable multiblock DMA transfers */ if (drv_data->controller_info->enable_dma) { - __lpss_ssp_write_priv(drv_data, config->reg_ssp, 1); + __lpss_ssp_update_priv(drv_data, config->reg_ssp, BIT(0), BIT(0)); if (config->reg_general >= 0) { - value = __lpss_ssp_read_priv(drv_data, - config->reg_general); - value |= LPSS_GENERAL_REG_RXTO_HOLDOFF_DISABLE; - __lpss_ssp_write_priv(drv_data, - config->reg_general, value); + value = LPSS_GENERAL_REG_RXTO_HOLDOFF_DISABLE; + __lpss_ssp_update_priv(drv_data, config->reg_general, value, value); } } } @@ -361,30 +371,19 @@ static void lpss_ssp_select_cs(struct spi_device *spi, { struct driver_data *drv_data = spi_controller_get_devdata(spi->controller); - u32 value, cs; + u32 cs; - if (!config->cs_sel_mask) + cs = spi_get_chipselect(spi, 0) << config->cs_sel_shift; + if (!__lpss_ssp_update_priv(drv_data, config->reg_cs_ctrl, config->cs_sel_mask, cs)) return; - value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl); - - cs = spi_get_chipselect(spi, 0); - cs <<= config->cs_sel_shift; - if (cs != (value & config->cs_sel_mask)) { - /* - * When switching another chip select output active the - * output must be selected first and wait 2 ssp_clk cycles - * before changing state to active. Otherwise a short - * glitch will occur on the previous chip select since - * output select is latched but state control is not. - */ - value &= ~config->cs_sel_mask; - value |= cs; - __lpss_ssp_write_priv(drv_data, - config->reg_cs_ctrl, value); - ndelay(1000000000 / - (drv_data->controller->max_speed_hz / 2)); - } + /* + * When switching another chip select output active the output must be + * selected first and wait 2 ssp_clk cycles before changing state to + * active. Otherwise a short glitch will occur on the previous chip + * select since output select is latched but state control is not. + */ + ndelay(1000000000 / (drv_data->controller->max_speed_hz / 2)); } static void lpss_ssp_cs_control(struct spi_device *spi, bool enable) @@ -392,34 +391,27 @@ static void lpss_ssp_cs_control(struct spi_device *spi, bool enable) struct driver_data *drv_data = spi_controller_get_devdata(spi->controller); const struct lpss_config *config; - u32 value; + u32 mask; config = lpss_get_config(drv_data); if (enable) lpss_ssp_select_cs(spi, config); - value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl); - if (enable) - value &= ~LPSS_CS_CONTROL_CS_HIGH; - else - value |= LPSS_CS_CONTROL_CS_HIGH; - __lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value); + mask = LPSS_CS_CONTROL_CS_HIGH; + __lpss_ssp_update_priv(drv_data, config->reg_cs_ctrl, mask, enable ? mask : 0); if (config->cs_clk_stays_gated) { - u32 clkgate; - /* * Changing CS alone when dynamic clock gating is on won't * actually flip CS at that time. This ruins SPI transfers * that specify delays, or have no data. Toggle the clock mode * to force on briefly to poke the CS pin to move. */ - clkgate = __lpss_ssp_read_priv(drv_data, LPSS_PRIV_CLOCK_GATE); - value = (clkgate & ~LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK) | - LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON; - - __lpss_ssp_write_priv(drv_data, LPSS_PRIV_CLOCK_GATE, value); - __lpss_ssp_write_priv(drv_data, LPSS_PRIV_CLOCK_GATE, clkgate); + mask = LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK; + if (__lpss_ssp_update_priv(drv_data, LPSS_PRIV_CLOCK_GATE, mask, + LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON)) + __lpss_ssp_update_priv(drv_data, LPSS_PRIV_CLOCK_GATE, mask, + LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_OFF); } } diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c index 69d0f2175568..f3fe10eddb6a 100644 --- a/drivers/spi/spi-rockchip-sfc.c +++ b/drivers/spi/spi-rockchip-sfc.c @@ -13,12 +13,14 @@ #include #include #include +#include #include #include #include +#include #include +#include #include -#include #include /* System control */ @@ -110,6 +112,7 @@ #define SFC_VER_3 0x3 #define SFC_VER_4 0x4 #define SFC_VER_5 0x5 +#define SFC_VER_8 0x8 /* Delay line controller register */ #define SFC_DLL_CTRL0 0x3C @@ -150,16 +153,13 @@ /* Data */ #define SFC_DATA 0x108 -/* The controller and documentation reports that it supports up to 4 CS - * devices (0-3), however I have only been able to test a single CS (CS 0) - * due to the configuration of my device. - */ -#define SFC_MAX_CHIPSELECT_NUM 4 +#define SFC_CS1_REG_OFFSET 0x200 + +#define SFC_MAX_CHIPSELECT_NUM 2 -/* The SFC can transfer max 16KB - 1 at one time - * we set it to 15.5KB here for alignment. - */ #define SFC_MAX_IOSIZE_VER3 (512 * 31) +/* Although up to 4GB, 64KB is enough with less mem reserved */ +#define SFC_MAX_IOSIZE_VER4 (0x10000U) /* DMA is only enabled for large data transmission */ #define SFC_DMA_TRANS_THRETHOLD (0x40) @@ -169,12 +169,14 @@ */ #define SFC_MAX_SPEED (150 * 1000 * 1000) +#define ROCKCHIP_AUTOSUSPEND_DELAY 2000 + struct rockchip_sfc { struct device *dev; void __iomem *regbase; struct clk *hclk; struct clk *clk; - u32 frequency; + u32 speed[SFC_MAX_CHIPSELECT_NUM]; /* virtual mapped addr for dma_buffer */ void *buffer; dma_addr_t dma_buffer; @@ -182,6 +184,7 @@ struct rockchip_sfc { bool use_dma; u32 max_iosize; u16 version; + struct spi_controller *host; }; static int rockchip_sfc_reset(struct rockchip_sfc *sfc) @@ -215,6 +218,22 @@ static u32 rockchip_sfc_get_max_iosize(struct rockchip_sfc *sfc) return SFC_MAX_IOSIZE_VER3; } +static int rockchip_sfc_clk_set_rate(struct rockchip_sfc *sfc, unsigned long speed) +{ + if (sfc->version >= SFC_VER_8) + return clk_set_rate(sfc->clk, speed * 2); + else + return clk_set_rate(sfc->clk, speed); +} + +static unsigned long rockchip_sfc_clk_get_rate(struct rockchip_sfc *sfc) +{ + if (sfc->version >= SFC_VER_8) + return clk_get_rate(sfc->clk) / 2; + else + return clk_get_rate(sfc->clk); +} + static void rockchip_sfc_irq_unmask(struct rockchip_sfc *sfc, u32 mask) { u32 reg; @@ -301,6 +320,7 @@ static int rockchip_sfc_xfer_setup(struct rockchip_sfc *sfc, u32 len) { u32 ctrl = 0, cmd = 0; + u8 cs = spi_get_chipselect(mem->spi, 0); /* set CMD */ cmd = op->cmd.opcode; @@ -314,7 +334,8 @@ static int rockchip_sfc_xfer_setup(struct rockchip_sfc *sfc, cmd |= SFC_CMD_ADDR_24BITS << SFC_CMD_ADDR_SHIFT; } else { cmd |= SFC_CMD_ADDR_XBITS << SFC_CMD_ADDR_SHIFT; - writel(op->addr.nbytes * 8 - 1, sfc->regbase + SFC_ABIT); + writel(op->addr.nbytes * 8 - 1, + sfc->regbase + cs * SFC_CS1_REG_OFFSET + SFC_ABIT); } ctrl |= ((op->addr.buswidth >> 1) << SFC_CTRL_ADDR_BITS_SHIFT); @@ -346,7 +367,7 @@ static int rockchip_sfc_xfer_setup(struct rockchip_sfc *sfc, /* set the Controller */ ctrl |= SFC_CTRL_PHASE_SEL_NEGETIVE; - cmd |= spi_get_chipselect(mem->spi, 0) << SFC_CMD_CS_SHIFT; + cmd |= cs << SFC_CMD_CS_SHIFT; dev_dbg(sfc->dev, "sfc addr.nbytes=%x(x%d) dummy.nbytes=%x(x%d)\n", op->addr.nbytes, op->addr.buswidth, @@ -354,7 +375,7 @@ static int rockchip_sfc_xfer_setup(struct rockchip_sfc *sfc, dev_dbg(sfc->dev, "sfc ctrl=%x cmd=%x addr=%llx len=%x\n", ctrl, cmd, op->addr.val, len); - writel(ctrl, sfc->regbase + SFC_CTRL); + writel(ctrl, sfc->regbase + cs * SFC_CS1_REG_OFFSET + SFC_CTRL); writel(cmd, sfc->regbase + SFC_CMD); if (op->addr.nbytes) writel(op->addr.val, sfc->regbase + SFC_ADDR); @@ -452,8 +473,10 @@ static int rockchip_sfc_xfer_data_dma(struct rockchip_sfc *sfc, dev_dbg(sfc->dev, "sfc xfer_dma len=%x\n", len); - if (op->data.dir == SPI_MEM_DATA_OUT) + if (op->data.dir == SPI_MEM_DATA_OUT) { memcpy(sfc->buffer, op->data.buf.out, len); + dma_sync_single_for_device(sfc->dev, sfc->dma_buffer, len, DMA_TO_DEVICE); + } ret = rockchip_sfc_fifo_transfer_dma(sfc, sfc->dma_buffer, len); if (!wait_for_completion_timeout(&sfc->cp, msecs_to_jiffies(2000))) { @@ -461,8 +484,11 @@ static int rockchip_sfc_xfer_data_dma(struct rockchip_sfc *sfc, ret = -ETIMEDOUT; } rockchip_sfc_irq_mask(sfc, SFC_IMR_DMA); - if (op->data.dir == SPI_MEM_DATA_IN) + + if (op->data.dir == SPI_MEM_DATA_IN) { + dma_sync_single_for_cpu(sfc->dev, sfc->dma_buffer, len, DMA_FROM_DEVICE); memcpy(op->data.buf.in, sfc->buffer, len); + } return ret; } @@ -472,6 +498,16 @@ static int rockchip_sfc_xfer_done(struct rockchip_sfc *sfc, u32 timeout_us) int ret = 0; u32 status; + /* + * There is very little data left in fifo, and the controller will + * complete the transmission in a short period of time. + */ + ret = readl_poll_timeout(sfc->regbase + SFC_SR, status, + !(status & SFC_SR_IS_BUSY), + 0, 10); + if (!ret) + return 0; + ret = readl_poll_timeout(sfc->regbase + SFC_SR, status, !(status & SFC_SR_IS_BUSY), 20, timeout_us); @@ -490,14 +526,22 @@ static int rockchip_sfc_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op struct rockchip_sfc *sfc = spi_controller_get_devdata(mem->spi->controller); u32 len = op->data.nbytes; int ret; + u8 cs = spi_get_chipselect(mem->spi, 0); - if (unlikely(mem->spi->max_speed_hz != sfc->frequency)) { - ret = clk_set_rate(sfc->clk, mem->spi->max_speed_hz); + ret = pm_runtime_get_sync(sfc->dev); + if (ret < 0) { + pm_runtime_put_noidle(sfc->dev); + return ret; + } + + if (unlikely(op->max_freq != sfc->speed[cs]) && + !has_acpi_companion(sfc->dev)) { + ret = rockchip_sfc_clk_set_rate(sfc, op->max_freq); if (ret) - return ret; - sfc->frequency = mem->spi->max_speed_hz; + goto out; + sfc->speed[cs] = op->max_freq; dev_dbg(sfc->dev, "set_freq=%dHz real_freq=%ldHz\n", - sfc->frequency, clk_get_rate(sfc->clk)); + sfc->speed[cs], rockchip_sfc_clk_get_rate(sfc)); } rockchip_sfc_adjust_op_work((struct spi_mem_op *)op); @@ -514,11 +558,17 @@ static int rockchip_sfc_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op if (ret != len) { dev_err(sfc->dev, "xfer data failed ret %d dir %d\n", ret, op->data.dir); - return -EIO; + ret = -EIO; + goto out; } } - return rockchip_sfc_xfer_done(sfc, 100000); + ret = rockchip_sfc_xfer_done(sfc, 100000); +out: + pm_runtime_mark_last_busy(sfc->dev); + pm_runtime_put_autosuspend(sfc->dev); + + return ret; } static int rockchip_sfc_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op) @@ -535,6 +585,10 @@ static const struct spi_controller_mem_ops rockchip_sfc_mem_ops = { .adjust_op_size = rockchip_sfc_adjust_op_size, }; +static const struct spi_controller_mem_caps rockchip_sfc_mem_caps = { + .per_op_freq = true, +}; + static irqreturn_t rockchip_sfc_irq_handler(int irq, void *dev_id) { struct rockchip_sfc *sfc = dev_id; @@ -560,6 +614,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev) struct spi_controller *host; struct rockchip_sfc *sfc; int ret; + u32 i, val; host = devm_spi_alloc_host(&pdev->dev, sizeof(*sfc)); if (!host) @@ -567,6 +622,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev) host->flags = SPI_CONTROLLER_HALF_DUPLEX; host->mem_ops = &rockchip_sfc_mem_ops; + host->mem_caps = &rockchip_sfc_mem_caps; host->dev.of_node = pdev->dev.of_node; host->mode_bits = SPI_TX_QUAD | SPI_TX_DUAL | SPI_RX_QUAD | SPI_RX_DUAL; host->max_speed_hz = SFC_MAX_SPEED; @@ -574,36 +630,35 @@ static int rockchip_sfc_probe(struct platform_device *pdev) sfc = spi_controller_get_devdata(host); sfc->dev = dev; + sfc->host = host; sfc->regbase = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(sfc->regbase)) return PTR_ERR(sfc->regbase); - sfc->clk = devm_clk_get(&pdev->dev, "clk_sfc"); + if (!has_acpi_companion(&pdev->dev)) + sfc->clk = devm_clk_get(&pdev->dev, "clk_sfc"); if (IS_ERR(sfc->clk)) return dev_err_probe(&pdev->dev, PTR_ERR(sfc->clk), "Failed to get sfc interface clk\n"); - sfc->hclk = devm_clk_get(&pdev->dev, "hclk_sfc"); + if (!has_acpi_companion(&pdev->dev)) + sfc->hclk = devm_clk_get(&pdev->dev, "hclk_sfc"); if (IS_ERR(sfc->hclk)) return dev_err_probe(&pdev->dev, PTR_ERR(sfc->hclk), "Failed to get sfc ahb clk\n"); - sfc->use_dma = !of_property_read_bool(sfc->dev->of_node, "rockchip,sfc-no-dma"); - - if (sfc->use_dma) { - ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); - if (ret) { - dev_warn(dev, "Unable to set dma mask\n"); - return ret; - } - - sfc->buffer = dmam_alloc_coherent(dev, SFC_MAX_IOSIZE_VER3, - &sfc->dma_buffer, GFP_KERNEL); - if (!sfc->buffer) - return -ENOMEM; + if (has_acpi_companion(&pdev->dev)) { + ret = device_property_read_u32(&pdev->dev, "clock-frequency", &val); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Failed to find clock-frequency in ACPI\n"); + for (i = 0; i < SFC_MAX_CHIPSELECT_NUM; i++) + sfc->speed[i] = val; } + sfc->use_dma = !of_property_read_bool(sfc->dev->of_node, "rockchip,sfc-no-dma"); + ret = clk_prepare_enable(sfc->hclk); if (ret) { dev_err(&pdev->dev, "Failed to enable ahb clk\n"); @@ -628,19 +683,47 @@ static int rockchip_sfc_probe(struct platform_device *pdev) goto err_irq; } + platform_set_drvdata(pdev, sfc); + ret = rockchip_sfc_init(sfc); if (ret) goto err_irq; - sfc->max_iosize = rockchip_sfc_get_max_iosize(sfc); sfc->version = rockchip_sfc_get_version(sfc); + sfc->max_iosize = rockchip_sfc_get_max_iosize(sfc); - ret = spi_register_controller(host); + pm_runtime_set_autosuspend_delay(dev, ROCKCHIP_AUTOSUSPEND_DELAY); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + pm_runtime_get_noresume(dev); + + if (sfc->use_dma) { + sfc->buffer = (u8 *)__get_free_pages(GFP_KERNEL | GFP_DMA32, + get_order(sfc->max_iosize)); + if (!sfc->buffer) { + ret = -ENOMEM; + goto err_dma; + } + sfc->dma_buffer = virt_to_phys(sfc->buffer); + } + + ret = devm_spi_register_controller(dev, host); if (ret) - goto err_irq; + goto err_register; + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); return 0; - +err_register: + free_pages((unsigned long)sfc->buffer, get_order(sfc->max_iosize)); +err_dma: + pm_runtime_get_sync(dev); + pm_runtime_put_noidle(dev); + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + pm_runtime_dont_use_autosuspend(dev); err_irq: clk_disable_unprepare(sfc->clk); err_clk: @@ -651,15 +734,84 @@ err_hclk: static void rockchip_sfc_remove(struct platform_device *pdev) { - struct spi_controller *host = platform_get_drvdata(pdev); struct rockchip_sfc *sfc = platform_get_drvdata(pdev); + struct spi_controller *host = sfc->host; spi_unregister_controller(host); + free_pages((unsigned long)sfc->buffer, get_order(sfc->max_iosize)); clk_disable_unprepare(sfc->clk); clk_disable_unprepare(sfc->hclk); } +#ifdef CONFIG_PM +static int rockchip_sfc_runtime_suspend(struct device *dev) +{ + struct rockchip_sfc *sfc = dev_get_drvdata(dev); + + clk_disable_unprepare(sfc->clk); + clk_disable_unprepare(sfc->hclk); + + return 0; +} + +static int rockchip_sfc_runtime_resume(struct device *dev) +{ + struct rockchip_sfc *sfc = dev_get_drvdata(dev); + int ret; + + ret = clk_prepare_enable(sfc->hclk); + if (ret < 0) + return ret; + + ret = clk_prepare_enable(sfc->clk); + if (ret < 0) + clk_disable_unprepare(sfc->hclk); + + return ret; +} +#endif /* CONFIG_PM */ + +#ifdef CONFIG_PM_SLEEP +static int rockchip_sfc_suspend(struct device *dev) +{ + pinctrl_pm_select_sleep_state(dev); + + return pm_runtime_force_suspend(dev); +} + +static int rockchip_sfc_resume(struct device *dev) +{ + struct rockchip_sfc *sfc = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret < 0) + return ret; + + pinctrl_pm_select_default_state(dev); + + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + pm_runtime_put_noidle(dev); + return ret; + } + + rockchip_sfc_init(sfc); + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + +static const struct dev_pm_ops rockchip_sfc_pm_ops = { + SET_RUNTIME_PM_OPS(rockchip_sfc_runtime_suspend, + rockchip_sfc_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(rockchip_sfc_suspend, rockchip_sfc_resume) +}; + static const struct of_device_id rockchip_sfc_dt_ids[] = { { .compatible = "rockchip,sfc"}, { /* sentinel */ } @@ -670,6 +822,7 @@ static struct platform_driver rockchip_sfc_driver = { .driver = { .name = "rockchip-sfc", .of_match_table = rockchip_sfc_dt_ids, + .pm = &rockchip_sfc_pm_ops, }, .probe = rockchip_sfc_probe, .remove = rockchip_sfc_remove, diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c index eecf9ea95ae3..1627aa66c965 100644 --- a/drivers/spi/spi-sc18is602.c +++ b/drivers/spi/spi-sc18is602.c @@ -7,13 +7,15 @@ #include #include +#include #include #include #include #include #include -#include #include +#include + #include enum chips { sc18is602, sc18is602b, sc18is603 }; @@ -236,9 +238,7 @@ static int sc18is602_setup(struct spi_device *spi) static int sc18is602_probe(struct i2c_client *client) { - const struct i2c_device_id *id = i2c_client_get_device_id(client); struct device *dev = &client->dev; - struct device_node *np = dev->of_node; struct sc18is602_platform_data *pdata = dev_get_platdata(dev); struct sc18is602 *hw; struct spi_controller *host; @@ -251,8 +251,9 @@ static int sc18is602_probe(struct i2c_client *client) if (!host) return -ENOMEM; + device_set_node(&host->dev, dev_fwnode(dev)); + hw = spi_controller_get_devdata(host); - i2c_set_clientdata(client, hw); /* assert reset and then release */ hw->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); @@ -265,11 +266,7 @@ static int sc18is602_probe(struct i2c_client *client) hw->dev = dev; hw->ctrl = 0xff; - if (client->dev.of_node) - hw->id = (uintptr_t)of_device_get_match_data(&client->dev); - else - hw->id = id->driver_data; - + hw->id = (uintptr_t)i2c_get_match_data(client); switch (hw->id) { case sc18is602: case sc18is602b: @@ -278,28 +275,21 @@ static int sc18is602_probe(struct i2c_client *client) break; case sc18is603: host->num_chipselect = 2; - if (pdata) { + if (pdata) hw->freq = pdata->clock_frequency; - } else { - const __be32 *val; - int len; - - val = of_get_property(np, "clock-frequency", &len); - if (val && len >= sizeof(__be32)) - hw->freq = be32_to_cpup(val); - } + else + device_property_read_u32(dev, "clock-frequency", &hw->freq); if (!hw->freq) hw->freq = SC18IS602_CLOCK; break; } - host->bus_num = np ? -1 : client->adapter->nr; + host->bus_num = dev_fwnode(dev) ? -1 : client->adapter->nr; host->mode_bits = SPI_CPHA | SPI_CPOL | SPI_LSB_FIRST; host->bits_per_word_mask = SPI_BPW_MASK(8); host->setup = sc18is602_setup; host->transfer_one_message = sc18is602_transfer_one; host->max_transfer_size = sc18is602_max_transfer_size; host->max_message_size = sc18is602_max_transfer_size; - host->dev.of_node = np; host->min_speed_hz = hw->freq / 128; host->max_speed_hz = hw->freq / 4; @@ -314,7 +304,7 @@ static const struct i2c_device_id sc18is602_id[] = { }; MODULE_DEVICE_TABLE(i2c, sc18is602_id); -static const struct of_device_id sc18is602_of_match[] __maybe_unused = { +static const struct of_device_id sc18is602_of_match[] = { { .compatible = "nxp,sc18is602", .data = (void *)sc18is602 @@ -334,7 +324,7 @@ MODULE_DEVICE_TABLE(of, sc18is602_of_match); static struct i2c_driver sc18is602_driver = { .driver = { .name = "sc18is602", - .of_match_table = of_match_ptr(sc18is602_of_match), + .of_match_table = sc18is602_of_match, }, .probe = sc18is602_probe, .id_table = sc18is602_id, diff --git a/drivers/spi/spi-sn-f-ospi.c b/drivers/spi/spi-sn-f-ospi.c index adac645732fe..6ad4b729897e 100644 --- a/drivers/spi/spi-sn-f-ospi.c +++ b/drivers/spi/spi-sn-f-ospi.c @@ -335,7 +335,6 @@ static void f_ospi_config_indir_protocol(struct f_ospi *ospi, static int f_ospi_indir_prepare_op(struct f_ospi *ospi, struct spi_mem *mem, const struct spi_mem_op *op) { - struct spi_device *spi = mem->spi; u32 irq_stat_en; int ret; @@ -343,7 +342,7 @@ static int f_ospi_indir_prepare_op(struct f_ospi *ospi, struct spi_mem *mem, if (ret) return ret; - f_ospi_config_clk(ospi, spi->max_speed_hz); + f_ospi_config_clk(ospi, op->max_freq); f_ospi_config_indir_protocol(ospi, mem, op); @@ -577,6 +576,10 @@ static const struct spi_controller_mem_ops f_ospi_mem_ops = { .exec_op = f_ospi_exec_op, }; +static const struct spi_controller_mem_caps f_ospi_mem_caps = { + .per_op_freq = true, +}; + static int f_ospi_init(struct f_ospi *ospi) { int ret; @@ -614,6 +617,7 @@ static int f_ospi_probe(struct platform_device *pdev) | SPI_RX_DUAL | SPI_RX_QUAD | SPI_RX_OCTAL | SPI_MODE_0 | SPI_MODE_1 | SPI_LSB_FIRST; ctlr->mem_ops = &f_ospi_mem_ops; + ctlr->mem_caps = &f_ospi_mem_caps; ctlr->bus_num = -1; of_property_read_u32(dev->of_node, "num-cs", &num_cs); if (num_cs > OSPI_NUM_CS) { diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c index 9122350402b5..a284d2794586 100644 --- a/drivers/spi/spi-ti-qspi.c +++ b/drivers/spi/spi-ti-qspi.c @@ -623,7 +623,7 @@ static int ti_qspi_exec_mem_op(struct spi_mem *mem, mutex_lock(&qspi->list_lock); if (!qspi->mmap_enabled || qspi->current_cs != spi_get_chipselect(mem->spi, 0)) { - ti_qspi_setup_clk(qspi, mem->spi->max_speed_hz); + ti_qspi_setup_clk(qspi, op->max_freq); ti_qspi_enable_memory_map(mem->spi); } ti_qspi_setup_mmap_read(mem->spi, op->cmd.opcode, op->data.buswidth, @@ -658,6 +658,10 @@ static const struct spi_controller_mem_ops ti_qspi_mem_ops = { .adjust_op_size = ti_qspi_adjust_op_size, }; +static const struct spi_controller_mem_caps ti_qspi_mem_caps = { + .per_op_freq = true, +}; + static int ti_qspi_start_transfer_one(struct spi_controller *host, struct spi_message *m) { @@ -777,6 +781,7 @@ static int ti_qspi_probe(struct platform_device *pdev) host->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) | SPI_BPW_MASK(8); host->mem_ops = &ti_qspi_mem_ops; + host->mem_caps = &ti_qspi_mem_caps; if (!of_property_read_u32(np, "num-cs", &num_cs)) host->num_chipselect = num_cs; @@ -826,20 +831,12 @@ static int ti_qspi_probe(struct platform_device *pdev) if (of_property_present(np, "syscon-chipselects")) { qspi->ctrl_base = - syscon_regmap_lookup_by_phandle(np, - "syscon-chipselects"); + syscon_regmap_lookup_by_phandle_args(np, "syscon-chipselects", + 1, &qspi->ctrl_reg); if (IS_ERR(qspi->ctrl_base)) { ret = PTR_ERR(qspi->ctrl_base); goto free_host; } - ret = of_property_read_u32_index(np, - "syscon-chipselects", - 1, &qspi->ctrl_reg); - if (ret) { - dev_err(&pdev->dev, - "couldn't get ctrl_mod reg index\n"); - goto free_host; - } } qspi->fclk = devm_clk_get(&pdev->dev, "fck"); diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c index dee9c339a35e..2bd25c75f881 100644 --- a/drivers/spi/spi-zynq-qspi.c +++ b/drivers/spi/spi-zynq-qspi.c @@ -318,6 +318,7 @@ static void zynq_qspi_chipselect(struct spi_device *spi, bool assert) * zynq_qspi_config_op - Configure QSPI controller for specified transfer * @xqspi: Pointer to the zynq_qspi structure * @spi: Pointer to the spi_device structure + * @op: The memory operation to execute * * Sets the operational mode of QSPI controller for the next QSPI transfer and * sets the requested clock frequency. @@ -331,7 +332,8 @@ static void zynq_qspi_chipselect(struct spi_device *spi, bool assert) * controller the driver will set the highest or lowest frequency supported by * controller. */ -static int zynq_qspi_config_op(struct zynq_qspi *xqspi, struct spi_device *spi) +static int zynq_qspi_config_op(struct zynq_qspi *xqspi, struct spi_device *spi, + const struct spi_mem_op *op) { u32 config_reg, baud_rate_val = 0; @@ -346,7 +348,7 @@ static int zynq_qspi_config_op(struct zynq_qspi *xqspi, struct spi_device *spi) */ while ((baud_rate_val < ZYNQ_QSPI_CONFIG_BAUD_DIV_MAX) && (clk_get_rate(xqspi->refclk) / (2 << baud_rate_val)) > - spi->max_speed_hz) + op->max_freq) baud_rate_val++; config_reg = zynq_qspi_read(xqspi, ZYNQ_QSPI_CONFIG_OFFSET); @@ -379,12 +381,21 @@ static int zynq_qspi_setup_op(struct spi_device *spi) { struct spi_controller *ctlr = spi->controller; struct zynq_qspi *qspi = spi_controller_get_devdata(ctlr); + int ret; if (ctlr->busy) return -EBUSY; - clk_enable(qspi->refclk); - clk_enable(qspi->pclk); + ret = clk_enable(qspi->refclk); + if (ret) + return ret; + + ret = clk_enable(qspi->pclk); + if (ret) { + clk_disable(qspi->refclk); + return ret; + } + zynq_qspi_write(qspi, ZYNQ_QSPI_ENABLE_OFFSET, ZYNQ_QSPI_ENABLE_ENABLE_MASK); @@ -534,7 +545,7 @@ static int zynq_qspi_exec_mem_op(struct spi_mem *mem, op->dummy.buswidth, op->data.buswidth); zynq_qspi_chipselect(mem->spi, true); - zynq_qspi_config_op(xqspi, mem->spi); + zynq_qspi_config_op(xqspi, mem->spi, op); if (op->cmd.opcode) { reinit_completion(&xqspi->data_completion); @@ -620,6 +631,10 @@ static const struct spi_controller_mem_ops zynq_qspi_mem_ops = { .exec_op = zynq_qspi_exec_mem_op, }; +static const struct spi_controller_mem_caps zynq_qspi_mem_caps = { + .per_op_freq = true, +}; + /** * zynq_qspi_probe - Probe method for the QSPI driver * @pdev: Pointer to the platform_device structure @@ -706,6 +721,7 @@ static int zynq_qspi_probe(struct platform_device *pdev) ctlr->mode_bits = SPI_RX_DUAL | SPI_RX_QUAD | SPI_TX_DUAL | SPI_TX_QUAD; ctlr->mem_ops = &zynq_qspi_mem_ops; + ctlr->mem_caps = &zynq_qspi_mem_caps; ctlr->setup = zynq_qspi_setup_op; ctlr->max_speed_hz = clk_get_rate(xqspi->refclk) / 2; ctlr->dev.of_node = np; diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c index 549a6e0c9654..d800d79f62a7 100644 --- a/drivers/spi/spi-zynqmp-gqspi.c +++ b/drivers/spi/spi-zynqmp-gqspi.c @@ -535,7 +535,7 @@ static inline u32 zynqmp_qspi_selectspimode(struct zynqmp_qspi *xqspi, * zynqmp_qspi_config_op - Configure QSPI controller for specified * transfer * @xqspi: Pointer to the zynqmp_qspi structure - * @qspi: Pointer to the spi_device structure + * @op: The memory operation to execute * * Sets the operational mode of QSPI controller for the next QSPI transfer and * sets the requested clock frequency. @@ -553,12 +553,12 @@ static inline u32 zynqmp_qspi_selectspimode(struct zynqmp_qspi *xqspi, * frequency supported by controller. */ static int zynqmp_qspi_config_op(struct zynqmp_qspi *xqspi, - struct spi_device *qspi) + const struct spi_mem_op *op) { ulong clk_rate; u32 config_reg, req_speed_hz, baud_rate_val = 0; - req_speed_hz = qspi->max_speed_hz; + req_speed_hz = op->max_freq; if (xqspi->speed_hz != req_speed_hz) { xqspi->speed_hz = req_speed_hz; @@ -1072,7 +1072,7 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem, op->dummy.buswidth, op->data.buswidth); mutex_lock(&xqspi->op_lock); - zynqmp_qspi_config_op(xqspi, mem->spi); + zynqmp_qspi_config_op(xqspi, op); zynqmp_qspi_chipselect(mem->spi, false); genfifoentry |= xqspi->genfifocs; genfifoentry |= xqspi->genfifobus; @@ -1224,6 +1224,10 @@ static const struct spi_controller_mem_ops zynqmp_qspi_mem_ops = { .exec_op = zynqmp_qspi_exec_op, }; +static const struct spi_controller_mem_caps zynqmp_qspi_mem_caps = { + .per_op_freq = true, +}; + /** * zynqmp_qspi_probe - Probe method for the QSPI driver * @pdev: Pointer to the platform_device structure @@ -1333,6 +1337,7 @@ static int zynqmp_qspi_probe(struct platform_device *pdev) ctlr->bits_per_word_mask = SPI_BPW_MASK(8); ctlr->mem_ops = &zynqmp_qspi_mem_ops; + ctlr->mem_caps = &zynqmp_qspi_mem_caps; ctlr->setup = zynqmp_qspi_setup_op; ctlr->bits_per_word_mask = SPI_BPW_MASK(8); ctlr->dev.of_node = np; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ff1add2ecb91..a7a4647717d4 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -410,29 +410,21 @@ static int spi_probe(struct device *dev) { const struct spi_driver *sdrv = to_spi_driver(dev->driver); struct spi_device *spi = to_spi_device(dev); + struct fwnode_handle *fwnode = dev_fwnode(dev); int ret; ret = of_clk_set_defaults(dev->of_node, false); if (ret) return ret; - if (dev->of_node) { + if (is_of_node(fwnode)) spi->irq = of_irq_get(dev->of_node, 0); - if (spi->irq == -EPROBE_DEFER) - return dev_err_probe(dev, -EPROBE_DEFER, "Failed to get irq\n"); - if (spi->irq < 0) - spi->irq = 0; - } - - if (has_acpi_companion(dev) && spi->irq < 0) { - struct acpi_device *adev = to_acpi_device_node(dev->fwnode); - - spi->irq = acpi_dev_gpio_irq_get(adev, 0); - if (spi->irq == -EPROBE_DEFER) - return -EPROBE_DEFER; - if (spi->irq < 0) - spi->irq = 0; - } + else if (is_acpi_device_node(fwnode) && spi->irq < 0) + spi->irq = acpi_dev_gpio_irq_get(to_acpi_device_node(fwnode), 0); + if (spi->irq == -EPROBE_DEFER) + return dev_err_probe(dev, spi->irq, "Failed to get irq\n"); + if (spi->irq < 0) + spi->irq = 0; ret = dev_pm_domain_attach(dev, true); if (ret) @@ -874,15 +866,18 @@ EXPORT_SYMBOL_GPL(spi_new_device); */ void spi_unregister_device(struct spi_device *spi) { + struct fwnode_handle *fwnode; + if (!spi) return; - if (spi->dev.of_node) { - of_node_clear_flag(spi->dev.of_node, OF_POPULATED); - of_node_put(spi->dev.of_node); + fwnode = dev_fwnode(&spi->dev); + if (is_of_node(fwnode)) { + of_node_clear_flag(to_of_node(fwnode), OF_POPULATED); + of_node_put(to_of_node(fwnode)); + } else if (is_acpi_device_node(fwnode)) { + acpi_device_clear_enumerated(to_acpi_device_node(fwnode)); } - if (ACPI_COMPANION(&spi->dev)) - acpi_device_clear_enumerated(ACPI_COMPANION(&spi->dev)); device_remove_software_node(&spi->dev); device_del(&spi->dev); spi_cleanup(spi); @@ -1059,7 +1054,7 @@ static void spi_toggle_csgpiod(struct spi_device *spi, u8 idx, bool enable, bool * ambiguity. That's why we use enable, that takes SPI_CS_HIGH * into account. */ - if (has_acpi_companion(&spi->dev)) + if (is_acpi_device_node(dev_fwnode(&spi->dev))) gpiod_set_value_cansleep(spi_get_csgpiod(spi, idx), !enable); else /* Polarity handled by GPIO library */ @@ -2060,7 +2055,7 @@ static int spi_init_queue(struct spi_controller *ctlr) ctlr->busy = false; ctlr->queue_empty = true; - ctlr->kworker = kthread_create_worker(0, dev_name(&ctlr->dev)); + ctlr->kworker = kthread_run_worker(0, dev_name(&ctlr->dev)); if (IS_ERR(ctlr->kworker)) { dev_err(&ctlr->dev, "failed to create message pump kworker\n"); return PTR_ERR(ctlr->kworker); @@ -4841,7 +4836,7 @@ extern struct notifier_block spi_of_notifier; #if IS_ENABLED(CONFIG_ACPI) static int spi_acpi_controller_match(struct device *dev, const void *data) { - return ACPI_COMPANION(dev->parent) == data; + return device_match_acpi_dev(dev->parent, data); } struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev) diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 653f82984216..58ae4304fdab 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -698,19 +698,24 @@ static const struct class spidev_class = { .name = "spidev", }; +/* + * The spi device ids are expected to match the device names of the + * spidev_dt_ids array below. Both arrays are kept in the same ordering. + */ static const struct spi_device_id spidev_spi_ids[] = { - { .name = "bh2228fv" }, - { .name = "dh2228fv" }, - { .name = "jg10309-01" }, - { .name = "ltc2488" }, - { .name = "sx1301" }, - { .name = "bk4" }, - { .name = "dhcom-board" }, - { .name = "m53cpld" }, - { .name = "spi-petra" }, - { .name = "spi-authenta" }, - { .name = "em3581" }, - { .name = "si3210" }, + { .name = /* cisco */ "spi-petra" }, + { .name = /* dh */ "dhcom-board" }, + { .name = /* elgin */ "jg10309-01" }, + { .name = /* lineartechnology */ "ltc2488" }, + { .name = /* lwn */ "bk4" }, + { .name = /* lwn */ "bk4-spi" }, + { .name = /* menlo */ "m53cpld" }, + { .name = /* micron */ "spi-authenta" }, + { .name = /* rohm */ "bh2228fv" }, + { .name = /* rohm */ "dh2228fv" }, + { .name = /* semtech */ "sx1301" }, + { .name = /* silabs */ "em3581" }, + { .name = /* silabs */ "si3210" }, {}, }; MODULE_DEVICE_TABLE(spi, spidev_spi_ids); @@ -734,6 +739,7 @@ static const struct of_device_id spidev_dt_ids[] = { { .compatible = "elgin,jg10309-01", .data = &spidev_of_check }, { .compatible = "lineartechnology,ltc2488", .data = &spidev_of_check }, { .compatible = "lwn,bk4", .data = &spidev_of_check }, + { .compatible = "lwn,bk4-spi", .data = &spidev_of_check }, { .compatible = "menlo,m53cpld", .data = &spidev_of_check }, { .compatible = "micron,spi-authenta", .data = &spidev_of_check }, { .compatible = "rohm,bh2228fv", .data = &spidev_of_check }, diff --git a/drivers/spmi/hisi-spmi-controller.c b/drivers/spmi/hisi-spmi-controller.c index 3cafdf22c909..122140b97579 100644 --- a/drivers/spmi/hisi-spmi-controller.c +++ b/drivers/spmi/hisi-spmi-controller.c @@ -300,9 +300,6 @@ static int spmi_controller_probe(struct platform_device *pdev) spin_lock_init(&spmi_controller->lock); - ctrl->dev.parent = pdev->dev.parent; - ctrl->dev.of_node = of_node_get(pdev->dev.of_node); - /* Callbacks */ ctrl->read_cmd = spmi_read_cmd; ctrl->write_cmd = spmi_write_cmd; diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c index fb0101da1485..3cf8d9bd4566 100644 --- a/drivers/spmi/spmi.c +++ b/drivers/spmi/spmi.c @@ -517,7 +517,7 @@ static void of_spmi_register_devices(struct spmi_controller *ctrl) if (!sdev) continue; - sdev->dev.of_node = node; + device_set_node(&sdev->dev, of_fwnode_handle(node)); sdev->usid = (u8)reg[0]; err = spmi_device_add(sdev); diff --git a/drivers/staging/fbtft/Kconfig b/drivers/staging/fbtft/Kconfig index 77ab44362f16..dcf6a70455cc 100644 --- a/drivers/staging/fbtft/Kconfig +++ b/drivers/staging/fbtft/Kconfig @@ -3,6 +3,7 @@ menuconfig FB_TFT tristate "Support for small TFT LCD display modules" depends on FB && SPI depends on FB_DEVICE + depends on BACKLIGHT_CLASS_DEVICE depends on GPIOLIB || COMPILE_TEST select FB_BACKLIGHT select FB_SYSMEM_HELPERS_DEFERRED diff --git a/drivers/staging/fbtft/fb_ssd1351.c b/drivers/staging/fbtft/fb_ssd1351.c index f6db2933ebba..6736b09b2f45 100644 --- a/drivers/staging/fbtft/fb_ssd1351.c +++ b/drivers/staging/fbtft/fb_ssd1351.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "fbtft.h" @@ -162,7 +163,7 @@ static int set_gamma(struct fbtft_par *par, u32 *curves) static int blank(struct fbtft_par *par, bool on) { fbtft_par_dbg(DEBUG_BLANK, par, "(%s=%s)\n", - __func__, on ? "true" : "false"); + __func__, str_true_false(on)); if (on) write_reg(par, 0xAE); else diff --git a/drivers/staging/gpib/Kconfig b/drivers/staging/gpib/Kconfig index 259f3ff33646..81510db3072e 100644 --- a/drivers/staging/gpib/Kconfig +++ b/drivers/staging/gpib/Kconfig @@ -65,6 +65,8 @@ config GPIB_NI_PCI_ISA depends on ISA_BUS || PCI || PCMCIA depends on HAS_IOPORT depends on !X86_PAE + depends on PCMCIA || !PCMCIA + depends on HAS_IOPORT_MAP select GPIB_COMMON select GPIB_NEC7210 help @@ -89,6 +91,7 @@ config GPIB_CB7210 depends on HAS_IOPORT depends on ISA_BUS || PCI || PCMCIA depends on !X86_PAE + depends on PCMCIA || !PCMCIA select GPIB_COMMON select GPIB_NEC7210 help @@ -177,6 +180,7 @@ config GPIB_HP82341 config GPIB_INES tristate "INES" depends on PCI || ISA_BUS || PCMCIA + depends on PCMCIA || !PCMCIA depends on HAS_IOPORT depends on !X86_PAE select GPIB_COMMON @@ -199,8 +203,8 @@ config GPIB_INES called cb7210. config GPIB_PCMCIA - bool "PCMCIA/Cardbus support for NI MC and Ines boards" - depends on PCCARD && (GPIB_NI_PCI_ISA || GPIB_CB7210 || GPIB_INES) + def_bool y + depends on PCMCIA && (GPIB_NI_PCI_ISA || GPIB_CB7210 || GPIB_INES) help Enable PCMCIA/CArdbus support for National Instruments, measurement computing boards and Ines boards. diff --git a/drivers/staging/gpib/agilent_82350b/Makefile b/drivers/staging/gpib/agilent_82350b/Makefile index d9236c92e04b..f24e1e713a63 100644 --- a/drivers/staging/gpib/agilent_82350b/Makefile +++ b/drivers/staging/gpib/agilent_82350b/Makefile @@ -1,2 +1,2 @@ -obj-m += agilent_82350b.o +obj-$(CONFIG_GPIB_AGILENT_82350B) += agilent_82350b.o diff --git a/drivers/staging/gpib/agilent_82350b/agilent_82350b.c b/drivers/staging/gpib/agilent_82350b/agilent_82350b.c index 53006d0cc79c..3f4f95b7fe34 100644 --- a/drivers/staging/gpib/agilent_82350b/agilent_82350b.c +++ b/drivers/staging/gpib/agilent_82350b/agilent_82350b.c @@ -30,11 +30,8 @@ int agilent_82350b_accel_read(gpib_board_t *board, uint8_t *buffer, size_t lengt unsigned short event_status; int i, num_fifo_bytes; //hardware doesn't support checking for end-of-string character when using fifo - if (tms_priv->eos_flags & REOS) { - //pr_info("ag-rd: using tms9914 read for REOS %x EOS %x\n",tms_priv->eos_flags, - // tms_priv->eos); + if (tms_priv->eos_flags & REOS) return tms9914_read(board, tms_priv, buffer, length, end, bytes_read); - } clear_bit(DEV_CLEAR_BN, &tms_priv->state); @@ -700,7 +697,7 @@ static int agilent_82350b_generic_attach(gpib_board_t *board, const gpib_board_c GPIB_82350A_REGION)); dev_dbg(board->gpib_dev, "%s: gpib base address remapped to 0x%p\n", driver_name, a_priv->gpib_base); - tms_priv->iobase = a_priv->gpib_base + TMS9914_BASE_REG; + tms_priv->mmiobase = a_priv->gpib_base + TMS9914_BASE_REG; a_priv->sram_base = ioremap(pci_resource_start(a_priv->pci_device, SRAM_82350A_REGION), pci_resource_len(a_priv->pci_device, @@ -724,7 +721,7 @@ static int agilent_82350b_generic_attach(gpib_board_t *board, const gpib_board_c pci_resource_len(a_priv->pci_device, GPIB_REGION)); dev_dbg(board->gpib_dev, "%s: gpib base address remapped to 0x%p\n", driver_name, a_priv->gpib_base); - tms_priv->iobase = a_priv->gpib_base + TMS9914_BASE_REG; + tms_priv->mmiobase = a_priv->gpib_base + TMS9914_BASE_REG; a_priv->sram_base = ioremap(pci_resource_start(a_priv->pci_device, SRAM_REGION), pci_resource_len(a_priv->pci_device, SRAM_REGION)); dev_dbg(board->gpib_dev, "%s: sram base address remapped to 0x%p\n", @@ -811,15 +808,15 @@ void agilent_82350b_detach(gpib_board_t *board) if (a_priv->gpib_base) { tms9914_board_reset(tms_priv); if (a_priv->misc_base) - iounmap((void *)a_priv->misc_base); + iounmap(a_priv->misc_base); if (a_priv->borg_base) - iounmap((void *)a_priv->borg_base); + iounmap(a_priv->borg_base); if (a_priv->sram_base) - iounmap((void *)a_priv->sram_base); + iounmap(a_priv->sram_base); if (a_priv->gpib_base) - iounmap((void *)a_priv->gpib_base); + iounmap(a_priv->gpib_base); if (a_priv->plx_base) - iounmap((void *)a_priv->plx_base); + iounmap(a_priv->plx_base); pci_release_regions(a_priv->pci_device); } if (a_priv->pci_device) @@ -828,58 +825,58 @@ void agilent_82350b_detach(gpib_board_t *board) agilent_82350b_free_private(board); } -gpib_interface_t agilent_82350b_unaccel_interface = { -name: "agilent_82350b_unaccel", -attach : agilent_82350b_unaccel_attach, -detach : agilent_82350b_detach, -read : agilent_82350b_read, -write : agilent_82350b_write, -command : agilent_82350b_command, -request_system_control : agilent_82350b_request_system_control, -take_control : agilent_82350b_take_control, -go_to_standby : agilent_82350b_go_to_standby, -interface_clear : agilent_82350b_interface_clear, -remote_enable : agilent_82350b_remote_enable, -enable_eos : agilent_82350b_enable_eos, -disable_eos : agilent_82350b_disable_eos, -parallel_poll : agilent_82350b_parallel_poll, -parallel_poll_configure : agilent_82350b_parallel_poll_configure, -parallel_poll_response : agilent_82350b_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : agilent_82350b_line_status, -update_status : agilent_82350b_update_status, -primary_address : agilent_82350b_primary_address, -secondary_address : agilent_82350b_secondary_address, -serial_poll_response : agilent_82350b_serial_poll_response, -t1_delay : agilent_82350b_t1_delay, -return_to_local : agilent_82350b_return_to_local, +static gpib_interface_t agilent_82350b_unaccel_interface = { + .name = "agilent_82350b_unaccel", + .attach = agilent_82350b_unaccel_attach, + .detach = agilent_82350b_detach, + .read = agilent_82350b_read, + .write = agilent_82350b_write, + .command = agilent_82350b_command, + .request_system_control = agilent_82350b_request_system_control, + .take_control = agilent_82350b_take_control, + .go_to_standby = agilent_82350b_go_to_standby, + .interface_clear = agilent_82350b_interface_clear, + .remote_enable = agilent_82350b_remote_enable, + .enable_eos = agilent_82350b_enable_eos, + .disable_eos = agilent_82350b_disable_eos, + .parallel_poll = agilent_82350b_parallel_poll, + .parallel_poll_configure = agilent_82350b_parallel_poll_configure, + .parallel_poll_response = agilent_82350b_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = agilent_82350b_line_status, + .update_status = agilent_82350b_update_status, + .primary_address = agilent_82350b_primary_address, + .secondary_address = agilent_82350b_secondary_address, + .serial_poll_response = agilent_82350b_serial_poll_response, + .t1_delay = agilent_82350b_t1_delay, + .return_to_local = agilent_82350b_return_to_local, }; -gpib_interface_t agilent_82350b_interface = { -name: "agilent_82350b", -attach : agilent_82350b_accel_attach, -detach : agilent_82350b_detach, -read : agilent_82350b_accel_read, -write : agilent_82350b_accel_write, -command : agilent_82350b_command, -request_system_control : agilent_82350b_request_system_control, -take_control : agilent_82350b_take_control, -go_to_standby : agilent_82350b_go_to_standby, -interface_clear : agilent_82350b_interface_clear, -remote_enable : agilent_82350b_remote_enable, -enable_eos : agilent_82350b_enable_eos, -disable_eos : agilent_82350b_disable_eos, -parallel_poll : agilent_82350b_parallel_poll, -parallel_poll_configure : agilent_82350b_parallel_poll_configure, -parallel_poll_response : agilent_82350b_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : agilent_82350b_line_status, -update_status : agilent_82350b_update_status, -primary_address : agilent_82350b_primary_address, -secondary_address : agilent_82350b_secondary_address, -serial_poll_response : agilent_82350b_serial_poll_response, -t1_delay : agilent_82350b_t1_delay, -return_to_local : agilent_82350b_return_to_local, +static gpib_interface_t agilent_82350b_interface = { + .name = "agilent_82350b", + .attach = agilent_82350b_accel_attach, + .detach = agilent_82350b_detach, + .read = agilent_82350b_accel_read, + .write = agilent_82350b_accel_write, + .command = agilent_82350b_command, + .request_system_control = agilent_82350b_request_system_control, + .take_control = agilent_82350b_take_control, + .go_to_standby = agilent_82350b_go_to_standby, + .interface_clear = agilent_82350b_interface_clear, + .remote_enable = agilent_82350b_remote_enable, + .enable_eos = agilent_82350b_enable_eos, + .disable_eos = agilent_82350b_disable_eos, + .parallel_poll = agilent_82350b_parallel_poll, + .parallel_poll_configure = agilent_82350b_parallel_poll_configure, + .parallel_poll_response = agilent_82350b_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = agilent_82350b_line_status, + .update_status = agilent_82350b_update_status, + .primary_address = agilent_82350b_primary_address, + .secondary_address = agilent_82350b_secondary_address, + .serial_poll_response = agilent_82350b_serial_poll_response, + .t1_delay = agilent_82350b_t1_delay, + .return_to_local = agilent_82350b_return_to_local, }; static int agilent_82350b_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) @@ -910,13 +907,30 @@ static int __init agilent_82350b_init_module(void) result = pci_register_driver(&agilent_82350b_pci_driver); if (result) { - pr_err("agilent_82350b: pci_driver_register failed!\n"); + pr_err("agilent_82350b: pci_register_driver failed: error = %d\n", result); return result; } - gpib_register_driver(&agilent_82350b_unaccel_interface, THIS_MODULE); - gpib_register_driver(&agilent_82350b_interface, THIS_MODULE); + result = gpib_register_driver(&agilent_82350b_unaccel_interface, THIS_MODULE); + if (result) { + pr_err("agilent_82350b: gpib_register_driver failed: error = %d\n", result); + goto err_unaccel; + } + + result = gpib_register_driver(&agilent_82350b_interface, THIS_MODULE); + if (result) { + pr_err("agilent_82350b: gpib_register_driver failed: error = %d\n", result); + goto err_interface; + } + return 0; + +err_interface: + gpib_unregister_driver(&agilent_82350b_unaccel_interface); +err_unaccel: + pci_unregister_driver(&agilent_82350b_pci_driver); + + return result; } static void __exit agilent_82350b_exit_module(void) diff --git a/drivers/staging/gpib/agilent_82350b/agilent_82350b.h b/drivers/staging/gpib/agilent_82350b/agilent_82350b.h index 30683d67d170..32b322113c10 100644 --- a/drivers/staging/gpib/agilent_82350b/agilent_82350b.h +++ b/drivers/staging/gpib/agilent_82350b/agilent_82350b.h @@ -45,11 +45,11 @@ enum board_model { struct agilent_82350b_priv { struct tms9914_priv tms9914_priv; struct pci_dev *pci_device; - void *plx_base; //82350a only - void *gpib_base; - void *sram_base; - void *misc_base; - void *borg_base; + void __iomem *plx_base; //82350a only + void __iomem *gpib_base; + void __iomem *sram_base; + void __iomem *misc_base; + void __iomem *borg_base; int irq; unsigned short card_mode_bits; unsigned short event_status_bits; @@ -60,8 +60,6 @@ struct agilent_82350b_priv { // driver name extern const char *driver_name; -// interfaces -extern gpib_interface_t agilent_82350b_interface; // init functions int agilent_82350b_unaccel_attach(gpib_board_t *board, const gpib_board_config_t *config); diff --git a/drivers/staging/gpib/agilent_82357a/Makefile b/drivers/staging/gpib/agilent_82357a/Makefile index 4a1d940fce2b..81a55c257a6e 100644 --- a/drivers/staging/gpib/agilent_82357a/Makefile +++ b/drivers/staging/gpib/agilent_82357a/Makefile @@ -1,4 +1,4 @@ -obj-m += agilent_82357a.o +obj-$(CONFIG_GPIB_AGILENT_82357A) += agilent_82357a.o diff --git a/drivers/staging/gpib/agilent_82357a/agilent_82357a.c b/drivers/staging/gpib/agilent_82357a/agilent_82357a.c index bf05fb4a736b..69f0e490d401 100644 --- a/drivers/staging/gpib/agilent_82357a/agilent_82357a.c +++ b/drivers/staging/gpib/agilent_82357a/agilent_82357a.c @@ -19,7 +19,7 @@ MODULE_DESCRIPTION("GPIB driver for Agilent 82357A/B usb adapters"); #define MAX_NUM_82357A_INTERFACES 128 static struct usb_interface *agilent_82357a_driver_interfaces[MAX_NUM_82357A_INTERFACES]; -DEFINE_MUTEX(agilent_82357a_hotplug_lock); // protect board insertion and removal +static DEFINE_MUTEX(agilent_82357a_hotplug_lock); // protect board insertion and removal static unsigned int agilent_82357a_update_status(gpib_board_t *board, unsigned int clear_mask); @@ -1146,25 +1146,6 @@ setup_exit: return retval; } -#ifdef RESET_USB_CONFIG -static int agilent_82357a_reset_usb_configuration(gpib_board_t *board) -{ - struct agilent_82357a_priv *a_priv = board->private_data; - struct usb_device *usb_dev = interface_to_usbdev(a_priv->bus_interface); - struct usb_device *usb_dev; - int retval; - - if (!a_priv->bus_interface) - return -ENODEV; - usb_dev = interface_to_usbdev(a_priv->bus_interface); - retval = usb_reset_configuration(usb_dev); - if (retval) - dev_err(&usb_dev->dev, "%s: usb_reset_configuration() returned %i\n", - __func__, retval); - return retval; -} -#endif - static void agilent_82357a_cleanup_urbs(struct agilent_82357a_priv *a_priv) { if (a_priv && a_priv->bus_interface) { @@ -1175,15 +1156,23 @@ static void agilent_82357a_cleanup_urbs(struct agilent_82357a_priv *a_priv) } }; +static void agilent_82357a_release_urbs(struct agilent_82357a_priv *a_priv) +{ + if (a_priv) { + usb_free_urb(a_priv->interrupt_urb); + a_priv->interrupt_urb = NULL; + kfree(a_priv->interrupt_buffer); + } +} + static int agilent_82357a_allocate_private(gpib_board_t *board) { struct agilent_82357a_priv *a_priv; - board->private_data = kmalloc(sizeof(struct agilent_82357a_priv), GFP_KERNEL); + board->private_data = kzalloc(sizeof(struct agilent_82357a_priv), GFP_KERNEL); if (!board->private_data) return -ENOMEM; a_priv = board->private_data; - memset(a_priv, 0, sizeof(struct agilent_82357a_priv)); mutex_init(&a_priv->bulk_transfer_lock); mutex_init(&a_priv->bulk_alloc_lock); mutex_init(&a_priv->control_alloc_lock); @@ -1191,11 +1180,11 @@ static int agilent_82357a_allocate_private(gpib_board_t *board) return 0; } -static void agilent_82357a_free_private(struct agilent_82357a_priv *a_priv) +static void agilent_82357a_free_private(gpib_board_t *board) { - usb_free_urb(a_priv->interrupt_urb); - kfree(a_priv->interrupt_buffer); - kfree(a_priv); + kfree(board->private_data); + board->private_data = NULL; + } static int agilent_82357a_init(gpib_board_t *board) @@ -1342,16 +1331,14 @@ static int agilent_82357a_attach(gpib_board_t *board, const gpib_board_config_t a_priv->bus_interface = agilent_82357a_driver_interfaces[i]; usb_set_intfdata(agilent_82357a_driver_interfaces[i], board); usb_dev = interface_to_usbdev(a_priv->bus_interface); - dev_info(&usb_dev->dev, - "bus %d dev num %d attached to gpib minor %d, agilent usb interface %i\n", - usb_dev->bus->busnum, usb_dev->devnum, board->minor, i); break; } } if (i == MAX_NUM_82357A_INTERFACES) { - mutex_unlock(&agilent_82357a_hotplug_lock); - pr_err("No Agilent 82357 gpib adapters found, have you loaded its firmware?\n"); - return -ENODEV; + dev_err(board->gpib_dev, + "No Agilent 82357 gpib adapters found, have you loaded its firmware?\n"); + retval = -ENODEV; + goto attach_fail; } product_id = le16_to_cpu(interface_to_usbdev(a_priv->bus_interface)->descriptor.idProduct); switch (product_id) { @@ -1365,20 +1352,13 @@ static int agilent_82357a_attach(gpib_board_t *board, const gpib_board_config_t break; default: dev_err(&usb_dev->dev, "bug, unhandled product_id in switch?\n"); - return -EIO; + retval = -EIO; + goto attach_fail; } -#ifdef RESET_USB_CONFIG - retval = agilent_82357a_reset_usb_configuration(board); - if (retval < 0) { - mutex_unlock(&agilent_82357a_hotplug_lock); - return retval; - } -#endif + retval = agilent_82357a_setup_urbs(board); - if (retval < 0) { - mutex_unlock(&agilent_82357a_hotplug_lock); - return retval; - } + if (retval < 0) + goto attach_fail; timer_setup(&a_priv->bulk_timer, agilent_82357a_timeout_handler, 0); @@ -1387,11 +1367,19 @@ static int agilent_82357a_attach(gpib_board_t *board, const gpib_board_config_t retval = agilent_82357a_init(board); if (retval < 0) { - mutex_unlock(&agilent_82357a_hotplug_lock); - return retval; + agilent_82357a_cleanup_urbs(a_priv); + agilent_82357a_release_urbs(a_priv); + goto attach_fail; } - dev_info(&usb_dev->dev, "%s: attached\n", __func__); + dev_info(&usb_dev->dev, + "bus %d dev num %d attached to gpib minor %d, agilent usb interface %i\n", + usb_dev->bus->busnum, usb_dev->devnum, board->minor, i); + mutex_unlock(&agilent_82357a_hotplug_lock); + return retval; + +attach_fail: + agilent_82357a_free_private(board); mutex_unlock(&agilent_82357a_hotplug_lock); return retval; } @@ -1441,12 +1429,10 @@ static int agilent_82357a_go_idle(gpib_board_t *board) static void agilent_82357a_detach(gpib_board_t *board) { struct agilent_82357a_priv *a_priv; - struct usb_device *usb_dev; mutex_lock(&agilent_82357a_hotplug_lock); a_priv = board->private_data; - usb_dev = interface_to_usbdev(a_priv->bus_interface); if (a_priv) { if (a_priv->bus_interface) { agilent_82357a_go_idle(board); @@ -1456,40 +1442,41 @@ static void agilent_82357a_detach(gpib_board_t *board) mutex_lock(&a_priv->bulk_alloc_lock); mutex_lock(&a_priv->interrupt_alloc_lock); agilent_82357a_cleanup_urbs(a_priv); - agilent_82357a_free_private(a_priv); + agilent_82357a_release_urbs(a_priv); + agilent_82357a_free_private(board); } - dev_info(&usb_dev->dev, "%s: detached\n", __func__); + dev_info(board->gpib_dev, "%s: detached\n", __func__); mutex_unlock(&agilent_82357a_hotplug_lock); } -gpib_interface_t agilent_82357a_gpib_interface = { -name: "agilent_82357a", -attach : agilent_82357a_attach, -detach : agilent_82357a_detach, -read : agilent_82357a_read, -write : agilent_82357a_write, -command : agilent_82357a_command, -take_control : agilent_82357a_take_control, -go_to_standby : agilent_82357a_go_to_standby, -request_system_control : agilent_82357a_request_system_control, -interface_clear : agilent_82357a_interface_clear, -remote_enable : agilent_82357a_remote_enable, -enable_eos : agilent_82357a_enable_eos, -disable_eos : agilent_82357a_disable_eos, -parallel_poll : agilent_82357a_parallel_poll, -parallel_poll_configure : agilent_82357a_parallel_poll_configure, -parallel_poll_response : agilent_82357a_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : agilent_82357a_line_status, -update_status : agilent_82357a_update_status, -primary_address : agilent_82357a_primary_address, -secondary_address : agilent_82357a_secondary_address, -serial_poll_response : agilent_82357a_serial_poll_response, -serial_poll_status : agilent_82357a_serial_poll_status, -t1_delay : agilent_82357a_t1_delay, -return_to_local : agilent_82357a_return_to_local, -no_7_bit_eos : 1, -skip_check_for_command_acceptors : 1 +static gpib_interface_t agilent_82357a_gpib_interface = { + .name = "agilent_82357a", + .attach = agilent_82357a_attach, + .detach = agilent_82357a_detach, + .read = agilent_82357a_read, + .write = agilent_82357a_write, + .command = agilent_82357a_command, + .take_control = agilent_82357a_take_control, + .go_to_standby = agilent_82357a_go_to_standby, + .request_system_control = agilent_82357a_request_system_control, + .interface_clear = agilent_82357a_interface_clear, + .remote_enable = agilent_82357a_remote_enable, + .enable_eos = agilent_82357a_enable_eos, + .disable_eos = agilent_82357a_disable_eos, + .parallel_poll = agilent_82357a_parallel_poll, + .parallel_poll_configure = agilent_82357a_parallel_poll_configure, + .parallel_poll_response = agilent_82357a_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = agilent_82357a_line_status, + .update_status = agilent_82357a_update_status, + .primary_address = agilent_82357a_primary_address, + .secondary_address = agilent_82357a_secondary_address, + .serial_poll_response = agilent_82357a_serial_poll_response, + .serial_poll_status = agilent_82357a_serial_poll_status, + .t1_delay = agilent_82357a_t1_delay, + .return_to_local = agilent_82357a_return_to_local, + .no_7_bit_eos = 1, + .skip_check_for_command_acceptors = 1 }; // Table with the USB-devices: just now only testing IDs @@ -1691,12 +1678,24 @@ static struct usb_driver agilent_82357a_bus_driver = { static int __init agilent_82357a_init_module(void) { int i; + int ret; pr_info("agilent_82357a_gpib driver loading"); for (i = 0; i < MAX_NUM_82357A_INTERFACES; ++i) agilent_82357a_driver_interfaces[i] = NULL; - usb_register(&agilent_82357a_bus_driver); - gpib_register_driver(&agilent_82357a_gpib_interface, THIS_MODULE); + + ret = usb_register(&agilent_82357a_bus_driver); + if (ret) { + pr_err("agilent_82357a: usb_register failed: error = %d\n", ret); + return ret; + } + + ret = gpib_register_driver(&agilent_82357a_gpib_interface, THIS_MODULE); + if (ret) { + pr_err("agilent_82357a: gpib_register_driver failed: error = %d\n", ret); + usb_deregister(&agilent_82357a_bus_driver); + return ret; + } return 0; } diff --git a/drivers/staging/gpib/cb7210/Makefile b/drivers/staging/gpib/cb7210/Makefile index 22e0214fc17d..cda0725d6487 100644 --- a/drivers/staging/gpib/cb7210/Makefile +++ b/drivers/staging/gpib/cb7210/Makefile @@ -1,4 +1,4 @@ ccflags-$(CONFIG_GPIB_PCMCIA) := -DGPIB_PCMCIA -obj-m += cb7210.o +obj-$(CONFIG_GPIB_CB7210) += cb7210.o diff --git a/drivers/staging/gpib/cb7210/cb7210.c b/drivers/staging/gpib/cb7210/cb7210.c index 63df7f3eb3f3..4d22f647a453 100644 --- a/drivers/staging/gpib/cb7210/cb7210.c +++ b/drivers/staging/gpib/cb7210/cb7210.c @@ -683,170 +683,170 @@ void cb7210_return_to_local(gpib_board_t *board) write_byte(nec_priv, AUX_RTL, AUXMR); } -gpib_interface_t cb_pci_unaccel_interface = { -name: "cbi_pci_unaccel", -attach : cb_pci_attach, -detach : cb_pci_detach, -read : cb7210_read, -write : cb7210_write, -command : cb7210_command, -take_control : cb7210_take_control, -go_to_standby : cb7210_go_to_standby, -request_system_control : cb7210_request_system_control, -interface_clear : cb7210_interface_clear, -remote_enable : cb7210_remote_enable, -enable_eos : cb7210_enable_eos, -disable_eos : cb7210_disable_eos, -parallel_poll : cb7210_parallel_poll, -parallel_poll_configure : cb7210_parallel_poll_configure, -parallel_poll_response : cb7210_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : cb7210_line_status, -update_status : cb7210_update_status, -primary_address : cb7210_primary_address, -secondary_address : cb7210_secondary_address, -serial_poll_response : cb7210_serial_poll_response, -serial_poll_status : cb7210_serial_poll_status, -t1_delay : cb7210_t1_delay, -return_to_local : cb7210_return_to_local, +static gpib_interface_t cb_pci_unaccel_interface = { + .name = "cbi_pci_unaccel", + .attach = cb_pci_attach, + .detach = cb_pci_detach, + .read = cb7210_read, + .write = cb7210_write, + .command = cb7210_command, + .take_control = cb7210_take_control, + .go_to_standby = cb7210_go_to_standby, + .request_system_control = cb7210_request_system_control, + .interface_clear = cb7210_interface_clear, + .remote_enable = cb7210_remote_enable, + .enable_eos = cb7210_enable_eos, + .disable_eos = cb7210_disable_eos, + .parallel_poll = cb7210_parallel_poll, + .parallel_poll_configure = cb7210_parallel_poll_configure, + .parallel_poll_response = cb7210_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = cb7210_line_status, + .update_status = cb7210_update_status, + .primary_address = cb7210_primary_address, + .secondary_address = cb7210_secondary_address, + .serial_poll_response = cb7210_serial_poll_response, + .serial_poll_status = cb7210_serial_poll_status, + .t1_delay = cb7210_t1_delay, + .return_to_local = cb7210_return_to_local, }; -gpib_interface_t cb_pci_accel_interface = { -name: "cbi_pci_accel", -attach : cb_pci_attach, -detach : cb_pci_detach, -read : cb7210_accel_read, -write : cb7210_accel_write, -command : cb7210_command, -take_control : cb7210_take_control, -go_to_standby : cb7210_go_to_standby, -request_system_control : cb7210_request_system_control, -interface_clear : cb7210_interface_clear, -remote_enable : cb7210_remote_enable, -enable_eos : cb7210_enable_eos, -disable_eos : cb7210_disable_eos, -parallel_poll : cb7210_parallel_poll, -parallel_poll_configure : cb7210_parallel_poll_configure, -parallel_poll_response : cb7210_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : cb7210_line_status, -update_status : cb7210_update_status, -primary_address : cb7210_primary_address, -secondary_address : cb7210_secondary_address, -serial_poll_response : cb7210_serial_poll_response, -serial_poll_status : cb7210_serial_poll_status, -t1_delay : cb7210_t1_delay, -return_to_local : cb7210_return_to_local, +static gpib_interface_t cb_pci_accel_interface = { + .name = "cbi_pci_accel", + .attach = cb_pci_attach, + .detach = cb_pci_detach, + .read = cb7210_accel_read, + .write = cb7210_accel_write, + .command = cb7210_command, + .take_control = cb7210_take_control, + .go_to_standby = cb7210_go_to_standby, + .request_system_control = cb7210_request_system_control, + .interface_clear = cb7210_interface_clear, + .remote_enable = cb7210_remote_enable, + .enable_eos = cb7210_enable_eos, + .disable_eos = cb7210_disable_eos, + .parallel_poll = cb7210_parallel_poll, + .parallel_poll_configure = cb7210_parallel_poll_configure, + .parallel_poll_response = cb7210_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = cb7210_line_status, + .update_status = cb7210_update_status, + .primary_address = cb7210_primary_address, + .secondary_address = cb7210_secondary_address, + .serial_poll_response = cb7210_serial_poll_response, + .serial_poll_status = cb7210_serial_poll_status, + .t1_delay = cb7210_t1_delay, + .return_to_local = cb7210_return_to_local, }; -gpib_interface_t cb_pci_interface = { -name: "cbi_pci", -attach : cb_pci_attach, -detach : cb_pci_detach, -read : cb7210_accel_read, -write : cb7210_accel_write, -command : cb7210_command, -take_control : cb7210_take_control, -go_to_standby : cb7210_go_to_standby, -request_system_control : cb7210_request_system_control, -interface_clear : cb7210_interface_clear, -remote_enable : cb7210_remote_enable, -enable_eos : cb7210_enable_eos, -disable_eos : cb7210_disable_eos, -parallel_poll : cb7210_parallel_poll, -parallel_poll_configure : cb7210_parallel_poll_configure, -parallel_poll_response : cb7210_parallel_poll_response, -line_status : cb7210_line_status, -update_status : cb7210_update_status, -primary_address : cb7210_primary_address, -secondary_address : cb7210_secondary_address, -serial_poll_response : cb7210_serial_poll_response, -serial_poll_status : cb7210_serial_poll_status, -t1_delay : cb7210_t1_delay, -return_to_local : cb7210_return_to_local, +static gpib_interface_t cb_pci_interface = { + .name = "cbi_pci", + .attach = cb_pci_attach, + .detach = cb_pci_detach, + .read = cb7210_accel_read, + .write = cb7210_accel_write, + .command = cb7210_command, + .take_control = cb7210_take_control, + .go_to_standby = cb7210_go_to_standby, + .request_system_control = cb7210_request_system_control, + .interface_clear = cb7210_interface_clear, + .remote_enable = cb7210_remote_enable, + .enable_eos = cb7210_enable_eos, + .disable_eos = cb7210_disable_eos, + .parallel_poll = cb7210_parallel_poll, + .parallel_poll_configure = cb7210_parallel_poll_configure, + .parallel_poll_response = cb7210_parallel_poll_response, + .line_status = cb7210_line_status, + .update_status = cb7210_update_status, + .primary_address = cb7210_primary_address, + .secondary_address = cb7210_secondary_address, + .serial_poll_response = cb7210_serial_poll_response, + .serial_poll_status = cb7210_serial_poll_status, + .t1_delay = cb7210_t1_delay, + .return_to_local = cb7210_return_to_local, }; -gpib_interface_t cb_isa_unaccel_interface = { -name: "cbi_isa_unaccel", -attach : cb_isa_attach, -detach : cb_isa_detach, -read : cb7210_read, -write : cb7210_write, -command : cb7210_command, -take_control : cb7210_take_control, -go_to_standby : cb7210_go_to_standby, -request_system_control : cb7210_request_system_control, -interface_clear : cb7210_interface_clear, -remote_enable : cb7210_remote_enable, -enable_eos : cb7210_enable_eos, -disable_eos : cb7210_disable_eos, -parallel_poll : cb7210_parallel_poll, -parallel_poll_configure : cb7210_parallel_poll_configure, -parallel_poll_response : cb7210_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : cb7210_line_status, -update_status : cb7210_update_status, -primary_address : cb7210_primary_address, -secondary_address : cb7210_secondary_address, -serial_poll_response : cb7210_serial_poll_response, -serial_poll_status : cb7210_serial_poll_status, -t1_delay : cb7210_t1_delay, -return_to_local : cb7210_return_to_local, +static gpib_interface_t cb_isa_unaccel_interface = { + .name = "cbi_isa_unaccel", + .attach = cb_isa_attach, + .detach = cb_isa_detach, + .read = cb7210_read, + .write = cb7210_write, + .command = cb7210_command, + .take_control = cb7210_take_control, + .go_to_standby = cb7210_go_to_standby, + .request_system_control = cb7210_request_system_control, + .interface_clear = cb7210_interface_clear, + .remote_enable = cb7210_remote_enable, + .enable_eos = cb7210_enable_eos, + .disable_eos = cb7210_disable_eos, + .parallel_poll = cb7210_parallel_poll, + .parallel_poll_configure = cb7210_parallel_poll_configure, + .parallel_poll_response = cb7210_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = cb7210_line_status, + .update_status = cb7210_update_status, + .primary_address = cb7210_primary_address, + .secondary_address = cb7210_secondary_address, + .serial_poll_response = cb7210_serial_poll_response, + .serial_poll_status = cb7210_serial_poll_status, + .t1_delay = cb7210_t1_delay, + .return_to_local = cb7210_return_to_local, }; -gpib_interface_t cb_isa_interface = { -name: "cbi_isa", -attach : cb_isa_attach, -detach : cb_isa_detach, -read : cb7210_accel_read, -write : cb7210_accel_write, -command : cb7210_command, -take_control : cb7210_take_control, -go_to_standby : cb7210_go_to_standby, -request_system_control : cb7210_request_system_control, -interface_clear : cb7210_interface_clear, -remote_enable : cb7210_remote_enable, -enable_eos : cb7210_enable_eos, -disable_eos : cb7210_disable_eos, -parallel_poll : cb7210_parallel_poll, -parallel_poll_configure : cb7210_parallel_poll_configure, -parallel_poll_response : cb7210_parallel_poll_response, -line_status : cb7210_line_status, -update_status : cb7210_update_status, -primary_address : cb7210_primary_address, -secondary_address : cb7210_secondary_address, -serial_poll_response : cb7210_serial_poll_response, -serial_poll_status : cb7210_serial_poll_status, -t1_delay : cb7210_t1_delay, -return_to_local : cb7210_return_to_local, +static gpib_interface_t cb_isa_interface = { + .name = "cbi_isa", + .attach = cb_isa_attach, + .detach = cb_isa_detach, + .read = cb7210_accel_read, + .write = cb7210_accel_write, + .command = cb7210_command, + .take_control = cb7210_take_control, + .go_to_standby = cb7210_go_to_standby, + .request_system_control = cb7210_request_system_control, + .interface_clear = cb7210_interface_clear, + .remote_enable = cb7210_remote_enable, + .enable_eos = cb7210_enable_eos, + .disable_eos = cb7210_disable_eos, + .parallel_poll = cb7210_parallel_poll, + .parallel_poll_configure = cb7210_parallel_poll_configure, + .parallel_poll_response = cb7210_parallel_poll_response, + .line_status = cb7210_line_status, + .update_status = cb7210_update_status, + .primary_address = cb7210_primary_address, + .secondary_address = cb7210_secondary_address, + .serial_poll_response = cb7210_serial_poll_response, + .serial_poll_status = cb7210_serial_poll_status, + .t1_delay = cb7210_t1_delay, + .return_to_local = cb7210_return_to_local, }; -gpib_interface_t cb_isa_accel_interface = { -name: "cbi_isa_accel", -attach : cb_isa_attach, -detach : cb_isa_detach, -read : cb7210_accel_read, -write : cb7210_accel_write, -command : cb7210_command, -take_control : cb7210_take_control, -go_to_standby : cb7210_go_to_standby, -request_system_control : cb7210_request_system_control, -interface_clear : cb7210_interface_clear, -remote_enable : cb7210_remote_enable, -enable_eos : cb7210_enable_eos, -disable_eos : cb7210_disable_eos, -parallel_poll : cb7210_parallel_poll, -parallel_poll_configure : cb7210_parallel_poll_configure, -parallel_poll_response : cb7210_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : cb7210_line_status, -update_status : cb7210_update_status, -primary_address : cb7210_primary_address, -secondary_address : cb7210_secondary_address, -serial_poll_response : cb7210_serial_poll_response, -serial_poll_status : cb7210_serial_poll_status, -t1_delay : cb7210_t1_delay, -return_to_local : cb7210_return_to_local, +static gpib_interface_t cb_isa_accel_interface = { + .name = "cbi_isa_accel", + .attach = cb_isa_attach, + .detach = cb_isa_detach, + .read = cb7210_accel_read, + .write = cb7210_accel_write, + .command = cb7210_command, + .take_control = cb7210_take_control, + .go_to_standby = cb7210_go_to_standby, + .request_system_control = cb7210_request_system_control, + .interface_clear = cb7210_interface_clear, + .remote_enable = cb7210_remote_enable, + .enable_eos = cb7210_enable_eos, + .disable_eos = cb7210_disable_eos, + .parallel_poll = cb7210_parallel_poll, + .parallel_poll_configure = cb7210_parallel_poll_configure, + .parallel_poll_response = cb7210_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = cb7210_line_status, + .update_status = cb7210_update_status, + .primary_address = cb7210_primary_address, + .secondary_address = cb7210_secondary_address, + .serial_poll_response = cb7210_serial_poll_response, + .serial_poll_status = cb7210_serial_poll_status, + .t1_delay = cb7210_t1_delay, + .return_to_local = cb7210_return_to_local, }; static int cb7210_allocate_private(gpib_board_t *board) @@ -971,12 +971,12 @@ int cb_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) switch (cb_priv->pci_chip) { case PCI_CHIP_AMCC_S5933: cb_priv->amcc_iobase = pci_resource_start(cb_priv->pci_device, 0); - nec_priv->iobase = (void *)(pci_resource_start(cb_priv->pci_device, 1)); + nec_priv->iobase = pci_resource_start(cb_priv->pci_device, 1); cb_priv->fifo_iobase = pci_resource_start(cb_priv->pci_device, 2); break; case PCI_CHIP_QUANCOM: - nec_priv->iobase = (void *)(pci_resource_start(cb_priv->pci_device, 0)); - cb_priv->fifo_iobase = (unsigned long)nec_priv->iobase; + nec_priv->iobase = pci_resource_start(cb_priv->pci_device, 0); + cb_priv->fifo_iobase = nec_priv->iobase; break; default: pr_err("cb7210: bug! unhandled pci_chip=%i\n", cb_priv->pci_chip); @@ -1040,8 +1040,8 @@ int cb_isa_attach(gpib_board_t *board, const gpib_board_config_t *config) return retval; cb_priv = board->private_data; nec_priv = &cb_priv->nec7210_priv; - if (request_region((unsigned long)config->ibbase, cb7210_iosize, "cb7210") == 0) { - pr_err("gpib: ioports starting at 0x%p are already in use\n", config->ibbase); + if (!request_region(config->ibbase, cb7210_iosize, "cb7210")) { + pr_err("gpib: ioports starting at 0x%x are already in use\n", config->ibbase); return -EIO; } nec_priv->iobase = config->ibbase; @@ -1351,100 +1351,94 @@ static struct pcmcia_driver cb_gpib_cs_driver = { .resume = cb_gpib_resume, }; -int cb_pcmcia_init_module(void) -{ - pcmcia_register_driver(&cb_gpib_cs_driver); - return 0; -} - void cb_pcmcia_cleanup_module(void) { DEBUG(0, "cb_gpib_cs: unloading\n"); pcmcia_unregister_driver(&cb_gpib_cs_driver); } -gpib_interface_t cb_pcmcia_unaccel_interface = { -name: "cbi_pcmcia_unaccel", -attach : cb_pcmcia_attach, -detach : cb_pcmcia_detach, -read : cb7210_read, -write : cb7210_write, -command : cb7210_command, -take_control : cb7210_take_control, -go_to_standby : cb7210_go_to_standby, -request_system_control : cb7210_request_system_control, -interface_clear : cb7210_interface_clear, -remote_enable : cb7210_remote_enable, -enable_eos : cb7210_enable_eos, -disable_eos : cb7210_disable_eos, -parallel_poll : cb7210_parallel_poll, -parallel_poll_configure : cb7210_parallel_poll_configure, -parallel_poll_response : cb7210_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : cb7210_line_status, -update_status : cb7210_update_status, -primary_address : cb7210_primary_address, -secondary_address : cb7210_secondary_address, -serial_poll_response : cb7210_serial_poll_response, -serial_poll_status : cb7210_serial_poll_status, -t1_delay : cb7210_t1_delay, -return_to_local : cb7210_return_to_local, +static gpib_interface_t cb_pcmcia_unaccel_interface = { + .name = "cbi_pcmcia_unaccel", + .attach = cb_pcmcia_attach, + .detach = cb_pcmcia_detach, + .read = cb7210_read, + .write = cb7210_write, + .command = cb7210_command, + .take_control = cb7210_take_control, + .go_to_standby = cb7210_go_to_standby, + .request_system_control = cb7210_request_system_control, + .interface_clear = cb7210_interface_clear, + .remote_enable = cb7210_remote_enable, + .enable_eos = cb7210_enable_eos, + .disable_eos = cb7210_disable_eos, + .parallel_poll = cb7210_parallel_poll, + .parallel_poll_configure = cb7210_parallel_poll_configure, + .parallel_poll_response = cb7210_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = cb7210_line_status, + .update_status = cb7210_update_status, + .primary_address = cb7210_primary_address, + .secondary_address = cb7210_secondary_address, + .serial_poll_response = cb7210_serial_poll_response, + .serial_poll_status = cb7210_serial_poll_status, + .t1_delay = cb7210_t1_delay, + .return_to_local = cb7210_return_to_local, }; -gpib_interface_t cb_pcmcia_interface = { -name: "cbi_pcmcia", -attach : cb_pcmcia_attach, -detach : cb_pcmcia_detach, -read : cb7210_accel_read, -write : cb7210_accel_write, -command : cb7210_command, -take_control : cb7210_take_control, -go_to_standby : cb7210_go_to_standby, -request_system_control : cb7210_request_system_control, -interface_clear : cb7210_interface_clear, -remote_enable : cb7210_remote_enable, -enable_eos : cb7210_enable_eos, -disable_eos : cb7210_disable_eos, -parallel_poll : cb7210_parallel_poll, -parallel_poll_configure : cb7210_parallel_poll_configure, -parallel_poll_response : cb7210_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : cb7210_line_status, -update_status : cb7210_update_status, -primary_address : cb7210_primary_address, -secondary_address : cb7210_secondary_address, -serial_poll_response : cb7210_serial_poll_response, -serial_poll_status : cb7210_serial_poll_status, -t1_delay : cb7210_t1_delay, -return_to_local : cb7210_return_to_local, +static gpib_interface_t cb_pcmcia_interface = { + .name = "cbi_pcmcia", + .attach = cb_pcmcia_attach, + .detach = cb_pcmcia_detach, + .read = cb7210_accel_read, + .write = cb7210_accel_write, + .command = cb7210_command, + .take_control = cb7210_take_control, + .go_to_standby = cb7210_go_to_standby, + .request_system_control = cb7210_request_system_control, + .interface_clear = cb7210_interface_clear, + .remote_enable = cb7210_remote_enable, + .enable_eos = cb7210_enable_eos, + .disable_eos = cb7210_disable_eos, + .parallel_poll = cb7210_parallel_poll, + .parallel_poll_configure = cb7210_parallel_poll_configure, + .parallel_poll_response = cb7210_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = cb7210_line_status, + .update_status = cb7210_update_status, + .primary_address = cb7210_primary_address, + .secondary_address = cb7210_secondary_address, + .serial_poll_response = cb7210_serial_poll_response, + .serial_poll_status = cb7210_serial_poll_status, + .t1_delay = cb7210_t1_delay, + .return_to_local = cb7210_return_to_local, }; -gpib_interface_t cb_pcmcia_accel_interface = { -name: "cbi_pcmcia_accel", -attach : cb_pcmcia_attach, -detach : cb_pcmcia_detach, -read : cb7210_accel_read, -write : cb7210_accel_write, -command : cb7210_command, -take_control : cb7210_take_control, -go_to_standby : cb7210_go_to_standby, -request_system_control : cb7210_request_system_control, -interface_clear : cb7210_interface_clear, -remote_enable : cb7210_remote_enable, -enable_eos : cb7210_enable_eos, -disable_eos : cb7210_disable_eos, -parallel_poll : cb7210_parallel_poll, -parallel_poll_configure : cb7210_parallel_poll_configure, -parallel_poll_response : cb7210_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : cb7210_line_status, -update_status : cb7210_update_status, -primary_address : cb7210_primary_address, -secondary_address : cb7210_secondary_address, -serial_poll_response : cb7210_serial_poll_response, -serial_poll_status : cb7210_serial_poll_status, -t1_delay : cb7210_t1_delay, -return_to_local : cb7210_return_to_local, +static gpib_interface_t cb_pcmcia_accel_interface = { + .name = "cbi_pcmcia_accel", + .attach = cb_pcmcia_attach, + .detach = cb_pcmcia_detach, + .read = cb7210_accel_read, + .write = cb7210_accel_write, + .command = cb7210_command, + .take_control = cb7210_take_control, + .go_to_standby = cb7210_go_to_standby, + .request_system_control = cb7210_request_system_control, + .interface_clear = cb7210_interface_clear, + .remote_enable = cb7210_remote_enable, + .enable_eos = cb7210_enable_eos, + .disable_eos = cb7210_disable_eos, + .parallel_poll = cb7210_parallel_poll, + .parallel_poll_configure = cb7210_parallel_poll_configure, + .parallel_poll_response = cb7210_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = cb7210_line_status, + .update_status = cb7210_update_status, + .primary_address = cb7210_primary_address, + .secondary_address = cb7210_secondary_address, + .serial_poll_response = cb7210_serial_poll_response, + .serial_poll_status = cb7210_serial_poll_status, + .t1_delay = cb7210_t1_delay, + .return_to_local = cb7210_return_to_local, }; int cb_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) @@ -1465,13 +1459,13 @@ int cb_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) cb_priv = board->private_data; nec_priv = &cb_priv->nec7210_priv; - if (request_region(curr_dev->resource[0]->start, resource_size(curr_dev->resource[0]), - "cb7210") == 0) { + if (!request_region(curr_dev->resource[0]->start, resource_size(curr_dev->resource[0]), + "cb7210")) { pr_err("gpib: ioports starting at 0x%lx are already in use\n", (unsigned long)curr_dev->resource[0]->start); return -EIO; } - nec_priv->iobase = (void *)(unsigned long)curr_dev->resource[0]->start; + nec_priv->iobase = curr_dev->resource[0]->start; cb_priv->fifo_iobase = curr_dev->resource[0]->start; if (request_irq(curr_dev->irq, cb7210_interrupt, IRQF_SHARED, @@ -1506,32 +1500,102 @@ void cb_pcmcia_detach(gpib_board_t *board) static int __init cb7210_init_module(void) { - int err = 0; - int result; + int ret; - result = pci_register_driver(&cb7210_pci_driver); - if (result) { - pr_err("cb7210: pci_driver_register failed!\n"); - return result; + ret = pci_register_driver(&cb7210_pci_driver); + if (ret) { + pr_err("cb7210: pci_register_driver failed: error = %d\n", ret); + return ret; } - gpib_register_driver(&cb_pci_interface, THIS_MODULE); - gpib_register_driver(&cb_isa_interface, THIS_MODULE); - gpib_register_driver(&cb_pci_accel_interface, THIS_MODULE); - gpib_register_driver(&cb_pci_unaccel_interface, THIS_MODULE); - gpib_register_driver(&cb_isa_accel_interface, THIS_MODULE); - gpib_register_driver(&cb_isa_unaccel_interface, THIS_MODULE); + ret = gpib_register_driver(&cb_pci_interface, THIS_MODULE); + if (ret) { + pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret); + goto err_pci; + } -#ifdef GPIB__PCMCIA - gpib_register_driver(&cb_pcmcia_interface, THIS_MODULE); - gpib_register_driver(&cb_pcmcia_accel_interface, THIS_MODULE); - gpib_register_driver(&cb_pcmcia_unaccel_interface, THIS_MODULE); - err += cb_pcmcia_init_module(); + ret = gpib_register_driver(&cb_isa_interface, THIS_MODULE); + if (ret) { + pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret); + goto err_isa; + } + + ret = gpib_register_driver(&cb_pci_accel_interface, THIS_MODULE); + if (ret) { + pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret); + goto err_pci_accel; + } + + ret = gpib_register_driver(&cb_pci_unaccel_interface, THIS_MODULE); + if (ret) { + pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret); + goto err_pci_unaccel; + } + + ret = gpib_register_driver(&cb_isa_accel_interface, THIS_MODULE); + if (ret) { + pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret); + goto err_isa_accel; + } + + ret = gpib_register_driver(&cb_isa_unaccel_interface, THIS_MODULE); + if (ret) { + pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret); + goto err_isa_unaccel; + } + +#ifdef GPIB_PCMCIA + ret = gpib_register_driver(&cb_pcmcia_interface, THIS_MODULE); + if (ret) { + pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret); + goto err_pcmcia; + } + + ret = gpib_register_driver(&cb_pcmcia_accel_interface, THIS_MODULE); + if (ret) { + pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret); + goto err_pcmcia_accel; + } + + ret = gpib_register_driver(&cb_pcmcia_unaccel_interface, THIS_MODULE); + if (ret) { + pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret); + goto err_pcmcia_unaccel; + } + + ret = pcmcia_register_driver(&cb_gpib_cs_driver); + if (ret) { + pr_err("cb7210: pcmcia_register_driver failed: error = %d\n", ret); + goto err_pcmcia_driver; + } #endif - if (err) - return -1; return 0; + +#ifdef GPIB_PCMCIA +err_pcmcia_driver: + gpib_unregister_driver(&cb_pcmcia_unaccel_interface); +err_pcmcia_unaccel: + gpib_unregister_driver(&cb_pcmcia_accel_interface); +err_pcmcia_accel: + gpib_unregister_driver(&cb_pcmcia_interface); +err_pcmcia: +#endif + gpib_unregister_driver(&cb_isa_unaccel_interface); +err_isa_unaccel: + gpib_unregister_driver(&cb_isa_accel_interface); +err_isa_accel: + gpib_unregister_driver(&cb_pci_unaccel_interface); +err_pci_unaccel: + gpib_unregister_driver(&cb_pci_accel_interface); +err_pci_accel: + gpib_unregister_driver(&cb_isa_interface); +err_isa: + gpib_unregister_driver(&cb_pci_interface); +err_pci: + pci_unregister_driver(&cb7210_pci_driver); + + return ret; } static void __exit cb7210_exit_module(void) diff --git a/drivers/staging/gpib/cb7210/cb7210.h b/drivers/staging/gpib/cb7210/cb7210.h index 4ad976de2b68..d56cd905cc8c 100644 --- a/drivers/staging/gpib/cb7210/cb7210.h +++ b/drivers/staging/gpib/cb7210/cb7210.h @@ -36,11 +36,6 @@ struct cb7210_priv { unsigned in_fifo_half_full : 1; }; -// interfaces -extern gpib_interface_t cb_pcmcia_interface; -extern gpib_interface_t cb_pcmcia_accel_interface; -extern gpib_interface_t cb_pcmcia_unaccel_interface; - // interrupt service routines irqreturn_t cb_pci_interrupt(int irq, void *arg); irqreturn_t cb7210_interrupt(int irq, void *arg); @@ -113,9 +108,9 @@ enum hs_regs { HS_STATUS = 0x8, /* HS_STATUS register */ }; -static inline unsigned long nec7210_iobase(const struct cb7210_priv *cb_priv) +static inline u32 nec7210_iobase(const struct cb7210_priv *cb_priv) { - return (unsigned long)(cb_priv->nec7210_priv.iobase); + return cb_priv->nec7210_priv.iobase; } static inline int cb7210_page_in_bits(unsigned int page) diff --git a/drivers/staging/gpib/cec/Makefile b/drivers/staging/gpib/cec/Makefile index f4638628ff29..b7141e23d4e0 100644 --- a/drivers/staging/gpib/cec/Makefile +++ b/drivers/staging/gpib/cec/Makefile @@ -1,3 +1,3 @@ -obj-m += cec_gpib.o +obj-$(CONFIG_GPIB_CEC_PCI) += cec_gpib.o diff --git a/drivers/staging/gpib/cec/cec.h b/drivers/staging/gpib/cec/cec.h index 352cf83d8328..040ca70ed708 100644 --- a/drivers/staging/gpib/cec/cec.h +++ b/drivers/staging/gpib/cec/cec.h @@ -16,10 +16,6 @@ struct cec_priv { unsigned int irq; }; -// interfaces -extern gpib_interface_t cec_pci_interface; -extern gpib_interface_t cec_pcmcia_interface; - // interface functions int cec_read(gpib_board_t *board, uint8_t *buffer, size_t length, int *end, size_t *bytes_read); int cec_write(gpib_board_t *board, uint8_t *buffer, size_t length, int send_eoi, diff --git a/drivers/staging/gpib/cec/cec_gpib.c b/drivers/staging/gpib/cec/cec_gpib.c index 3dc933deb401..d056cd1d6b3e 100644 --- a/drivers/staging/gpib/cec/cec_gpib.c +++ b/drivers/staging/gpib/cec/cec_gpib.c @@ -182,32 +182,32 @@ void cec_return_to_local(gpib_board_t *board) nec7210_return_to_local(board, &priv->nec7210_priv); } -gpib_interface_t cec_pci_interface = { -name: "cec_pci", -attach : cec_pci_attach, -detach : cec_pci_detach, -read : cec_read, -write : cec_write, -command : cec_command, -take_control : cec_take_control, -go_to_standby : cec_go_to_standby, -request_system_control : cec_request_system_control, -interface_clear : cec_interface_clear, -remote_enable : cec_remote_enable, -enable_eos : cec_enable_eos, -disable_eos : cec_disable_eos, -parallel_poll : cec_parallel_poll, -parallel_poll_configure : cec_parallel_poll_configure, -parallel_poll_response : cec_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : NULL, //XXX -update_status : cec_update_status, -primary_address : cec_primary_address, -secondary_address : cec_secondary_address, -serial_poll_response : cec_serial_poll_response, -serial_poll_status : cec_serial_poll_status, -t1_delay : cec_t1_delay, -return_to_local : cec_return_to_local, +static gpib_interface_t cec_pci_interface = { + .name = "cec_pci", + .attach = cec_pci_attach, + .detach = cec_pci_detach, + .read = cec_read, + .write = cec_write, + .command = cec_command, + .take_control = cec_take_control, + .go_to_standby = cec_go_to_standby, + .request_system_control = cec_request_system_control, + .interface_clear = cec_interface_clear, + .remote_enable = cec_remote_enable, + .enable_eos = cec_enable_eos, + .disable_eos = cec_disable_eos, + .parallel_poll = cec_parallel_poll, + .parallel_poll_configure = cec_parallel_poll_configure, + .parallel_poll_response = cec_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = NULL, //XXX + .update_status = cec_update_status, + .primary_address = cec_primary_address, + .secondary_address = cec_secondary_address, + .serial_poll_response = cec_serial_poll_response, + .serial_poll_status = cec_serial_poll_status, + .t1_delay = cec_t1_delay, + .return_to_local = cec_return_to_local, }; static int cec_allocate_private(gpib_board_t *board) @@ -297,8 +297,8 @@ int cec_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) cec_priv->plx_iobase = pci_resource_start(cec_priv->pci_device, 1); pr_info(" plx9050 base address 0x%lx\n", cec_priv->plx_iobase); - nec_priv->iobase = (void *)(pci_resource_start(cec_priv->pci_device, 3)); - pr_info(" nec7210 base address 0x%p\n", nec_priv->iobase); + nec_priv->iobase = pci_resource_start(cec_priv->pci_device, 3); + pr_info(" nec7210 base address 0x%x\n", nec_priv->iobase); isr_flags |= IRQF_SHARED; if (request_irq(cec_priv->pci_device->irq, cec_interrupt, isr_flags, "pci-gpib", board)) { @@ -365,11 +365,15 @@ static int __init cec_init_module(void) result = pci_register_driver(&cec_pci_driver); if (result) { - pr_err("cec_gpib: pci_driver_register failed!\n"); + pr_err("cec_gpib: pci_register_driver failed: error = %d\n", result); return result; } - gpib_register_driver(&cec_pci_interface, THIS_MODULE); + result = gpib_register_driver(&cec_pci_interface, THIS_MODULE); + if (result) { + pr_err("cec_gpib: gpib_register_driver failed: error = %d\n", result); + return result; + } return 0; } diff --git a/drivers/staging/gpib/common/Makefile b/drivers/staging/gpib/common/Makefile index 0c4c77bea75b..460586edb574 100644 --- a/drivers/staging/gpib/common/Makefile +++ b/drivers/staging/gpib/common/Makefile @@ -1,5 +1,5 @@ -obj-m += gpib_common.o +obj-$(CONFIG_GPIB_COMMON) += gpib_common.o gpib_common-objs := gpib_os.o iblib.o diff --git a/drivers/staging/gpib/common/gpib_os.c b/drivers/staging/gpib/common/gpib_os.c index 405237d8cb47..4901e660242e 100644 --- a/drivers/staging/gpib/common/gpib_os.c +++ b/drivers/staging/gpib/common/gpib_os.c @@ -116,56 +116,6 @@ int io_timed_out(gpib_board_t *board) return 0; } -void writeb_wrapper(unsigned int value, void *address) -{ - writeb(value, address); -}; -EXPORT_SYMBOL(writeb_wrapper); - -void writew_wrapper(unsigned int value, void *address) -{ - writew(value, address); -}; -EXPORT_SYMBOL(writew_wrapper); - -unsigned int readb_wrapper(void *address) -{ - return readb(address); -}; -EXPORT_SYMBOL(readb_wrapper); - -unsigned int readw_wrapper(void *address) -{ - return readw(address); -}; -EXPORT_SYMBOL(readw_wrapper); - -#ifdef CONFIG_HAS_IOPORT -void outb_wrapper(unsigned int value, void *address) -{ - outb(value, (unsigned long)(address)); -}; -EXPORT_SYMBOL(outb_wrapper); - -void outw_wrapper(unsigned int value, void *address) -{ - outw(value, (unsigned long)(address)); -}; -EXPORT_SYMBOL(outw_wrapper); - -unsigned int inb_wrapper(void *address) -{ - return inb((unsigned long)(address)); -}; -EXPORT_SYMBOL(inb_wrapper); - -unsigned int inw_wrapper(void *address) -{ - return inw((unsigned long)(address)); -}; -EXPORT_SYMBOL(inw_wrapper); -#endif - /* this is a function instead of a constant because of Suse * defining HZ to be a function call to get_hz() */ @@ -536,7 +486,7 @@ int dvrsp(gpib_board_t *board, unsigned int pad, int sad, return -1; } - if (pad > MAX_GPIB_PRIMARY_ADDRESS || sad > MAX_GPIB_SECONDARY_ADDRESS) { + if (pad > MAX_GPIB_PRIMARY_ADDRESS || sad > MAX_GPIB_SECONDARY_ADDRESS || sad < -1) { pr_err("gpib: bad address for serial poll"); return -1; } @@ -885,7 +835,7 @@ static int board_type_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, return -EBUSY; } - retval = copy_from_user(&cmd, (void *)arg, sizeof(board_type_ioctl_t)); + retval = copy_from_user(&cmd, (void __user *)arg, sizeof(board_type_ioctl_t)); if (retval) return retval; @@ -929,7 +879,7 @@ static int read_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, unsigned long arg) { read_write_ioctl_t read_cmd; - u8 *userbuf; + u8 __user *userbuf; unsigned long remain; int end_flag = 0; int retval; @@ -937,7 +887,7 @@ static int read_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, gpib_descriptor_t *desc; size_t nbytes; - retval = copy_from_user(&read_cmd, (void *)arg, sizeof(read_cmd)); + retval = copy_from_user(&read_cmd, (void __user *)arg, sizeof(read_cmd)); if (retval) return -EFAULT; @@ -951,7 +901,7 @@ static int read_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, if (WARN_ON_ONCE(sizeof(userbuf) > sizeof(read_cmd.buffer_ptr))) return -EFAULT; - userbuf = (u8 *)(unsigned long)read_cmd.buffer_ptr; + userbuf = (u8 __user *)(unsigned long)read_cmd.buffer_ptr; userbuf += read_cmd.completed_transfer_count; remain = read_cmd.requested_transfer_count - read_cmd.completed_transfer_count; @@ -989,7 +939,7 @@ static int read_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, if (remain == 0 || end_flag) read_ret = 0; if (retval == 0) - retval = copy_to_user((void *)arg, &read_cmd, sizeof(read_cmd)); + retval = copy_to_user((void __user *)arg, &read_cmd, sizeof(read_cmd)); atomic_set(&desc->io_in_progress, 0); @@ -1004,7 +954,7 @@ static int command_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, unsigned long arg) { read_write_ioctl_t cmd; - u8 *userbuf; + u8 __user *userbuf; unsigned long remain; int retval; int fault = 0; @@ -1012,7 +962,7 @@ static int command_ioctl(gpib_file_private_t *file_priv, size_t bytes_written; int no_clear_io_in_prog; - retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd)); + retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd)); if (retval) return -EFAULT; @@ -1023,7 +973,7 @@ static int command_ioctl(gpib_file_private_t *file_priv, if (!desc) return -EINVAL; - userbuf = (u8 *)(unsigned long)cmd.buffer_ptr; + userbuf = (u8 __user *)(unsigned long)cmd.buffer_ptr; userbuf += cmd.completed_transfer_count; no_clear_io_in_prog = cmd.end; @@ -1066,7 +1016,7 @@ static int command_ioctl(gpib_file_private_t *file_priv, cmd.completed_transfer_count = cmd.requested_transfer_count - remain; if (fault == 0) - fault = copy_to_user((void *)arg, &cmd, sizeof(cmd)); + fault = copy_to_user((void __user *)arg, &cmd, sizeof(cmd)); /* * no_clear_io_in_prog (cmd.end) is true when io_in_progress should @@ -1088,13 +1038,13 @@ static int write_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, unsigned long arg) { read_write_ioctl_t write_cmd; - u8 *userbuf; + u8 __user *userbuf; unsigned long remain; int retval = 0; int fault; gpib_descriptor_t *desc; - fault = copy_from_user(&write_cmd, (void *)arg, sizeof(write_cmd)); + fault = copy_from_user(&write_cmd, (void __user *)arg, sizeof(write_cmd)); if (fault) return -EFAULT; @@ -1105,7 +1055,7 @@ static int write_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, if (!desc) return -EINVAL; - userbuf = (u8 *)(unsigned long)write_cmd.buffer_ptr; + userbuf = (u8 __user *)(unsigned long)write_cmd.buffer_ptr; userbuf += write_cmd.completed_transfer_count; remain = write_cmd.requested_transfer_count - write_cmd.completed_transfer_count; @@ -1144,7 +1094,7 @@ static int write_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, if (remain == 0) retval = 0; if (fault == 0) - fault = copy_to_user((void *)arg, &write_cmd, sizeof(write_cmd)); + fault = copy_to_user((void __user *)arg, &write_cmd, sizeof(write_cmd)); atomic_set(&desc->io_in_progress, 0); @@ -1161,7 +1111,7 @@ static int status_bytes_ioctl(gpib_board_t *board, unsigned long arg) spoll_bytes_ioctl_t cmd; int retval; - retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd)); + retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd)); if (retval) return -EFAULT; @@ -1171,7 +1121,7 @@ static int status_bytes_ioctl(gpib_board_t *board, unsigned long arg) else cmd.num_bytes = num_status_bytes(device); - retval = copy_to_user((void *)arg, &cmd, sizeof(cmd)); + retval = copy_to_user((void __user *)arg, &cmd, sizeof(cmd)); if (retval) return -EFAULT; @@ -1281,7 +1231,7 @@ static int open_dev_ioctl(struct file *filep, gpib_board_t *board, unsigned long gpib_file_private_t *file_priv = filep->private_data; int i; - retval = copy_from_user(&open_dev_cmd, (void *)arg, sizeof(open_dev_cmd)); + retval = copy_from_user(&open_dev_cmd, (void __user *)arg, sizeof(open_dev_cmd)); if (retval) return -EFAULT; @@ -1317,7 +1267,7 @@ static int open_dev_ioctl(struct file *filep, gpib_board_t *board, unsigned long atomic_set(&board->stuck_srq, 0); open_dev_cmd.handle = i; - retval = copy_to_user((void *)arg, &open_dev_cmd, sizeof(open_dev_cmd)); + retval = copy_to_user((void __user *)arg, &open_dev_cmd, sizeof(open_dev_cmd)); if (retval) return -EFAULT; @@ -1330,7 +1280,7 @@ static int close_dev_ioctl(struct file *filep, gpib_board_t *board, unsigned lon gpib_file_private_t *file_priv = filep->private_data; int retval; - retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd)); + retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd)); if (retval) return -EFAULT; @@ -1358,7 +1308,7 @@ static int serial_poll_ioctl(gpib_board_t *board, unsigned long arg) dev_dbg(board->gpib_dev, "pid %i, entering %s()\n", current->pid, __func__); - retval = copy_from_user(&serial_cmd, (void *)arg, sizeof(serial_cmd)); + retval = copy_from_user(&serial_cmd, (void __user *)arg, sizeof(serial_cmd)); if (retval) return -EFAULT; @@ -1367,7 +1317,7 @@ static int serial_poll_ioctl(gpib_board_t *board, unsigned long arg) if (retval < 0) return retval; - retval = copy_to_user((void *)arg, &serial_cmd, sizeof(serial_cmd)); + retval = copy_to_user((void __user *)arg, &serial_cmd, sizeof(serial_cmd)); if (retval) return -EFAULT; @@ -1381,7 +1331,7 @@ static int wait_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, int retval; gpib_descriptor_t *desc; - retval = copy_from_user(&wait_cmd, (void *)arg, sizeof(wait_cmd)); + retval = copy_from_user(&wait_cmd, (void __user *)arg, sizeof(wait_cmd)); if (retval) return -EFAULT; @@ -1394,7 +1344,7 @@ static int wait_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board, if (retval < 0) return retval; - retval = copy_to_user((void *)arg, &wait_cmd, sizeof(wait_cmd)); + retval = copy_to_user((void __user *)arg, &wait_cmd, sizeof(wait_cmd)); if (retval) return -EFAULT; @@ -1410,7 +1360,7 @@ static int parallel_poll_ioctl(gpib_board_t *board, unsigned long arg) if (retval < 0) return retval; - retval = copy_to_user((void *)arg, &poll_byte, sizeof(poll_byte)); + retval = copy_to_user((void __user *)arg, &poll_byte, sizeof(poll_byte)); if (retval) return -EFAULT; @@ -1421,14 +1371,14 @@ static int online_ioctl(gpib_board_t *board, unsigned long arg) { online_ioctl_t online_cmd; int retval; - void *init_data = NULL; + void __user *init_data = NULL; board->config.init_data = NULL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - retval = copy_from_user(&online_cmd, (void *)arg, sizeof(online_cmd)); + retval = copy_from_user(&online_cmd, (void __user *)arg, sizeof(online_cmd)); if (retval) return -EFAULT; if (online_cmd.init_data_length > 0) { @@ -1437,7 +1387,7 @@ static int online_ioctl(gpib_board_t *board, unsigned long arg) return -ENOMEM; if (WARN_ON_ONCE(sizeof(init_data) > sizeof(online_cmd.init_data_ptr))) return -EFAULT; - init_data = (void *)(unsigned long)(online_cmd.init_data_ptr); + init_data = (void __user *)(unsigned long)(online_cmd.init_data_ptr); retval = copy_from_user(board->config.init_data, init_data, online_cmd.init_data_length); if (retval) { @@ -1466,7 +1416,7 @@ static int remote_enable_ioctl(gpib_board_t *board, unsigned long arg) int enable; int retval; - retval = copy_from_user(&enable, (void *)arg, sizeof(enable)); + retval = copy_from_user(&enable, (void __user *)arg, sizeof(enable)); if (retval) return -EFAULT; @@ -1478,7 +1428,7 @@ static int take_control_ioctl(gpib_board_t *board, unsigned long arg) int synchronous; int retval; - retval = copy_from_user(&synchronous, (void *)arg, sizeof(synchronous)); + retval = copy_from_user(&synchronous, (void __user *)arg, sizeof(synchronous)); if (retval) return -EFAULT; @@ -1494,7 +1444,7 @@ static int line_status_ioctl(gpib_board_t *board, unsigned long arg) if (retval < 0) return retval; - retval = copy_to_user((void *)arg, &lines, sizeof(lines)); + retval = copy_to_user((void __user *)arg, &lines, sizeof(lines)); if (retval) return -EFAULT; @@ -1508,7 +1458,7 @@ static int pad_ioctl(gpib_board_t *board, gpib_file_private_t *file_priv, int retval; gpib_descriptor_t *desc; - retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd)); + retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd)); if (retval) return -EFAULT; @@ -1544,7 +1494,7 @@ static int sad_ioctl(gpib_board_t *board, gpib_file_private_t *file_priv, int retval; gpib_descriptor_t *desc; - retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd)); + retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd)); if (retval) return -EFAULT; @@ -1577,7 +1527,7 @@ static int eos_ioctl(gpib_board_t *board, unsigned long arg) eos_ioctl_t eos_cmd; int retval; - retval = copy_from_user(&eos_cmd, (void *)arg, sizeof(eos_cmd)); + retval = copy_from_user(&eos_cmd, (void __user *)arg, sizeof(eos_cmd)); if (retval) return -EFAULT; @@ -1589,7 +1539,7 @@ static int request_service_ioctl(gpib_board_t *board, unsigned long arg) u8 status_byte; int retval; - retval = copy_from_user(&status_byte, (void *)arg, sizeof(status_byte)); + retval = copy_from_user(&status_byte, (void __user *)arg, sizeof(status_byte)); if (retval) return -EFAULT; @@ -1601,7 +1551,8 @@ static int request_service2_ioctl(gpib_board_t *board, unsigned long arg) request_service2_t request_service2_cmd; int retval; - retval = copy_from_user(&request_service2_cmd, (void *)arg, sizeof(request_service2_t)); + retval = copy_from_user(&request_service2_cmd, (void __user *)arg, + sizeof(request_service2_t)); if (retval) return -EFAULT; @@ -1617,13 +1568,13 @@ static int iobase_ioctl(gpib_board_config_t *config, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - retval = copy_from_user(&base_addr, (void *)arg, sizeof(base_addr)); + retval = copy_from_user(&base_addr, (void __user *)arg, sizeof(base_addr)); if (retval) return -EFAULT; if (WARN_ON_ONCE(sizeof(void *) > sizeof(base_addr))) return -EFAULT; - config->ibbase = (void *)(unsigned long)(base_addr); + config->ibbase = base_addr; return 0; } @@ -1636,7 +1587,7 @@ static int irq_ioctl(gpib_board_config_t *config, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - retval = copy_from_user(&irq, (void *)arg, sizeof(irq)); + retval = copy_from_user(&irq, (void __user *)arg, sizeof(irq)); if (retval) return -EFAULT; @@ -1653,7 +1604,7 @@ static int dma_ioctl(gpib_board_config_t *config, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - retval = copy_from_user(&dma_channel, (void *)arg, sizeof(dma_channel)); + retval = copy_from_user(&dma_channel, (void __user *)arg, sizeof(dma_channel)); if (retval) return -EFAULT; @@ -1669,7 +1620,7 @@ static int autospoll_ioctl(gpib_board_t *board, gpib_file_private_t *file_priv, int retval; gpib_descriptor_t *desc; - retval = copy_from_user(&enable, (void *)arg, sizeof(enable)); + retval = copy_from_user(&enable, (void __user *)arg, sizeof(enable)); if (retval) return -EFAULT; @@ -1704,7 +1655,7 @@ static int mutex_ioctl(gpib_board_t *board, gpib_file_private_t *file_priv, { int retval, lock_mutex; - retval = copy_from_user(&lock_mutex, (void *)arg, sizeof(lock_mutex)); + retval = copy_from_user(&lock_mutex, (void __user *)arg, sizeof(lock_mutex)); if (retval) return -EFAULT; @@ -1748,7 +1699,7 @@ static int timeout_ioctl(gpib_board_t *board, unsigned long arg) unsigned int timeout; int retval; - retval = copy_from_user(&timeout, (void *)arg, sizeof(timeout)); + retval = copy_from_user(&timeout, (void __user *)arg, sizeof(timeout)); if (retval) return -EFAULT; @@ -1763,7 +1714,7 @@ static int ppc_ioctl(gpib_board_t *board, unsigned long arg) ppoll_config_ioctl_t cmd; int retval; - retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd)); + retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd)); if (retval) return -EFAULT; @@ -1789,7 +1740,7 @@ static int set_local_ppoll_mode_ioctl(gpib_board_t *board, unsigned long arg) local_ppoll_mode_ioctl_t cmd; int retval; - retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd)); + retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd)); if (retval) return -EFAULT; @@ -1809,7 +1760,7 @@ static int get_local_ppoll_mode_ioctl(gpib_board_t *board, unsigned long arg) int retval; cmd = board->local_ppoll_mode; - retval = copy_to_user((void *)arg, &cmd, sizeof(cmd)); + retval = copy_to_user((void __user *)arg, &cmd, sizeof(cmd)); if (retval) return -EFAULT; @@ -1823,7 +1774,7 @@ static int query_board_rsv_ioctl(gpib_board_t *board, unsigned long arg) status = board->interface->serial_poll_status(board); - retval = copy_to_user((void *)arg, &status, sizeof(status)); + retval = copy_to_user((void __user *)arg, &status, sizeof(status)); if (retval) return -EFAULT; @@ -1846,7 +1797,7 @@ static int board_info_ioctl(const gpib_board_t *board, unsigned long arg) info.t1_delay = board->t1_nano_sec; info.ist = board->ist; info.no_7_bit_eos = board->interface->no_7_bit_eos; - retval = copy_to_user((void *)arg, &info, sizeof(info)); + retval = copy_to_user((void __user *)arg, &info, sizeof(info)); if (retval) return -EFAULT; @@ -1858,7 +1809,7 @@ static int interface_clear_ioctl(gpib_board_t *board, unsigned long arg) unsigned int usec_duration; int retval; - retval = copy_from_user(&usec_duration, (void *)arg, sizeof(usec_duration)); + retval = copy_from_user(&usec_duration, (void __user *)arg, sizeof(usec_duration)); if (retval) return -EFAULT; @@ -1873,7 +1824,7 @@ static int select_pci_ioctl(gpib_board_config_t *config, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - retval = copy_from_user(&selection, (void *)arg, sizeof(selection)); + retval = copy_from_user(&selection, (void __user *)arg, sizeof(selection)); if (retval) return -EFAULT; @@ -1895,7 +1846,7 @@ static int select_device_path_ioctl(gpib_board_config_t *config, unsigned long a if (!selection) return -ENOMEM; - retval = copy_from_user(selection, (void *)arg, sizeof(select_device_path_ioctl_t)); + retval = copy_from_user(selection, (void __user *)arg, sizeof(select_device_path_ioctl_t)); if (retval) { vfree(selection); return -EFAULT; @@ -2029,7 +1980,7 @@ static int event_ioctl(gpib_board_t *board, unsigned long arg) user_event = event; - retval = copy_to_user((void *)arg, &user_event, sizeof(user_event)); + retval = copy_to_user((void __user *)arg, &user_event, sizeof(user_event)); if (retval) return -EFAULT; @@ -2041,7 +1992,7 @@ static int request_system_control_ioctl(gpib_board_t *board, unsigned long arg) rsc_ioctl_t request_control; int retval; - retval = copy_from_user(&request_control, (void *)arg, sizeof(request_control)); + retval = copy_from_user(&request_control, (void __user *)arg, sizeof(request_control)); if (retval) return -EFAULT; @@ -2061,7 +2012,7 @@ static int t1_delay_ioctl(gpib_board_t *board, unsigned long arg) return -EIO; } - retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd)); + retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd)); if (retval) return -EFAULT; @@ -2072,13 +2023,13 @@ static int t1_delay_ioctl(gpib_board_t *board, unsigned long arg) return 0; } -const struct file_operations ib_fops = { -owner: THIS_MODULE, -llseek : NULL, -unlocked_ioctl : &ibioctl, -compat_ioctl : &ibioctl, -open : &ibopen, -release : &ibclose, +static const struct file_operations ib_fops = { + .owner = THIS_MODULE, + .llseek = NULL, + .unlocked_ioctl = &ibioctl, + .compat_ioctl = &ibioctl, + .open = &ibopen, + .release = &ibclose, }; gpib_board_t board_array[GPIB_MAX_NUM_BOARDS]; @@ -2094,18 +2045,19 @@ void init_gpib_descriptor(gpib_descriptor_t *desc) atomic_set(&desc->io_in_progress, 0); } -void gpib_register_driver(gpib_interface_t *interface, struct module *provider_module) +int gpib_register_driver(gpib_interface_t *interface, struct module *provider_module) { struct gpib_interface_list_struct *entry; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) - return; + return -ENOMEM; entry->interface = interface; entry->module = provider_module; list_add(&entry->list, ®istered_drivers); - pr_info("gpib: registered %s interface\n", interface->name); + + return 0; } EXPORT_SYMBOL(gpib_register_driver); @@ -2245,7 +2197,7 @@ static int __init gpib_common_init_module(void) return PTR_ERR(gpib_class); } for (i = 0; i < GPIB_MAX_NUM_BOARDS; ++i) - board_array[i].gpib_dev = device_create(gpib_class, 0, + board_array[i].gpib_dev = device_create(gpib_class, NULL, MKDEV(GPIB_CODE, i), NULL, "gpib%i", i); return 0; diff --git a/drivers/staging/gpib/common/iblib.c b/drivers/staging/gpib/common/iblib.c index db1911cc1b26..5f6fa135f505 100644 --- a/drivers/staging/gpib/common/iblib.c +++ b/drivers/staging/gpib/common/iblib.c @@ -695,7 +695,7 @@ int ibwait(gpib_board_t *board, int wait_mask, int clear_mask, int set_mask, /* make sure we only clear status bits that we are reporting */ if (*status & clear_mask || set_mask) - general_ibstatus(board, status_queue, *status & clear_mask, set_mask, 0); + general_ibstatus(board, status_queue, *status & clear_mask, set_mask, NULL); return 0; } diff --git a/drivers/staging/gpib/eastwood/Makefile b/drivers/staging/gpib/eastwood/Makefile index c74056f959d0..384825195f77 100644 --- a/drivers/staging/gpib/eastwood/Makefile +++ b/drivers/staging/gpib/eastwood/Makefile @@ -1,3 +1,3 @@ -obj-m += fluke_gpib.o +obj-$(CONFIG_GPIB_FLUKE) += fluke_gpib.o diff --git a/drivers/staging/gpib/eastwood/fluke_gpib.c b/drivers/staging/gpib/eastwood/fluke_gpib.c index 3f938ab0c84d..0304c5de4ccd 100644 --- a/drivers/staging/gpib/eastwood/fluke_gpib.c +++ b/drivers/staging/gpib/eastwood/fluke_gpib.c @@ -720,31 +720,31 @@ static int fluke_accel_read(gpib_board_t *board, uint8_t *buffer, size_t length, return retval; } -gpib_interface_t fluke_unaccel_interface = { -name: "fluke_unaccel", -attach : fluke_attach_holdoff_all, -detach : fluke_detach, -read : fluke_read, -write : fluke_write, -command : fluke_command, -take_control : fluke_take_control, -go_to_standby : fluke_go_to_standby, -request_system_control : fluke_request_system_control, -interface_clear : fluke_interface_clear, -remote_enable : fluke_remote_enable, -enable_eos : fluke_enable_eos, -disable_eos : fluke_disable_eos, -parallel_poll : fluke_parallel_poll, -parallel_poll_configure : fluke_parallel_poll_configure, -parallel_poll_response : fluke_parallel_poll_response, -line_status : fluke_line_status, -update_status : fluke_update_status, -primary_address : fluke_primary_address, -secondary_address : fluke_secondary_address, -serial_poll_response : fluke_serial_poll_response, -serial_poll_status : fluke_serial_poll_status, -t1_delay : fluke_t1_delay, -return_to_local : fluke_return_to_local, +static gpib_interface_t fluke_unaccel_interface = { + .name = "fluke_unaccel", + .attach = fluke_attach_holdoff_all, + .detach = fluke_detach, + .read = fluke_read, + .write = fluke_write, + .command = fluke_command, + .take_control = fluke_take_control, + .go_to_standby = fluke_go_to_standby, + .request_system_control = fluke_request_system_control, + .interface_clear = fluke_interface_clear, + .remote_enable = fluke_remote_enable, + .enable_eos = fluke_enable_eos, + .disable_eos = fluke_disable_eos, + .parallel_poll = fluke_parallel_poll, + .parallel_poll_configure = fluke_parallel_poll_configure, + .parallel_poll_response = fluke_parallel_poll_response, + .line_status = fluke_line_status, + .update_status = fluke_update_status, + .primary_address = fluke_primary_address, + .secondary_address = fluke_secondary_address, + .serial_poll_response = fluke_serial_poll_response, + .serial_poll_status = fluke_serial_poll_status, + .t1_delay = fluke_t1_delay, + .return_to_local = fluke_return_to_local, }; /* fluke_hybrid uses dma for writes but not for reads. Added @@ -755,58 +755,58 @@ return_to_local : fluke_return_to_local, * register just as the dma controller is also doing a read. */ -gpib_interface_t fluke_hybrid_interface = { -name: "fluke_hybrid", -attach : fluke_attach_holdoff_all, -detach : fluke_detach, -read : fluke_read, -write : fluke_accel_write, -command : fluke_command, -take_control : fluke_take_control, -go_to_standby : fluke_go_to_standby, -request_system_control : fluke_request_system_control, -interface_clear : fluke_interface_clear, -remote_enable : fluke_remote_enable, -enable_eos : fluke_enable_eos, -disable_eos : fluke_disable_eos, -parallel_poll : fluke_parallel_poll, -parallel_poll_configure : fluke_parallel_poll_configure, -parallel_poll_response : fluke_parallel_poll_response, -line_status : fluke_line_status, -update_status : fluke_update_status, -primary_address : fluke_primary_address, -secondary_address : fluke_secondary_address, -serial_poll_response : fluke_serial_poll_response, -serial_poll_status : fluke_serial_poll_status, -t1_delay : fluke_t1_delay, -return_to_local : fluke_return_to_local, +static gpib_interface_t fluke_hybrid_interface = { + .name = "fluke_hybrid", + .attach = fluke_attach_holdoff_all, + .detach = fluke_detach, + .read = fluke_read, + .write = fluke_accel_write, + .command = fluke_command, + .take_control = fluke_take_control, + .go_to_standby = fluke_go_to_standby, + .request_system_control = fluke_request_system_control, + .interface_clear = fluke_interface_clear, + .remote_enable = fluke_remote_enable, + .enable_eos = fluke_enable_eos, + .disable_eos = fluke_disable_eos, + .parallel_poll = fluke_parallel_poll, + .parallel_poll_configure = fluke_parallel_poll_configure, + .parallel_poll_response = fluke_parallel_poll_response, + .line_status = fluke_line_status, + .update_status = fluke_update_status, + .primary_address = fluke_primary_address, + .secondary_address = fluke_secondary_address, + .serial_poll_response = fluke_serial_poll_response, + .serial_poll_status = fluke_serial_poll_status, + .t1_delay = fluke_t1_delay, + .return_to_local = fluke_return_to_local, }; -gpib_interface_t fluke_interface = { -name: "fluke", -attach : fluke_attach_holdoff_end, -detach : fluke_detach, -read : fluke_accel_read, -write : fluke_accel_write, -command : fluke_command, -take_control : fluke_take_control, -go_to_standby : fluke_go_to_standby, -request_system_control : fluke_request_system_control, -interface_clear : fluke_interface_clear, -remote_enable : fluke_remote_enable, -enable_eos : fluke_enable_eos, -disable_eos : fluke_disable_eos, -parallel_poll : fluke_parallel_poll, -parallel_poll_configure : fluke_parallel_poll_configure, -parallel_poll_response : fluke_parallel_poll_response, -line_status : fluke_line_status, -update_status : fluke_update_status, -primary_address : fluke_primary_address, -secondary_address : fluke_secondary_address, -serial_poll_response : fluke_serial_poll_response, -serial_poll_status : fluke_serial_poll_status, -t1_delay : fluke_t1_delay, -return_to_local : fluke_return_to_local, +static gpib_interface_t fluke_interface = { + .name = "fluke", + .attach = fluke_attach_holdoff_end, + .detach = fluke_detach, + .read = fluke_accel_read, + .write = fluke_accel_write, + .command = fluke_command, + .take_control = fluke_take_control, + .go_to_standby = fluke_go_to_standby, + .request_system_control = fluke_request_system_control, + .interface_clear = fluke_interface_clear, + .remote_enable = fluke_remote_enable, + .enable_eos = fluke_enable_eos, + .disable_eos = fluke_disable_eos, + .parallel_poll = fluke_parallel_poll, + .parallel_poll_configure = fluke_parallel_poll_configure, + .parallel_poll_response = fluke_parallel_poll_response, + .line_status = fluke_line_status, + .update_status = fluke_update_status, + .primary_address = fluke_primary_address, + .secondary_address = fluke_secondary_address, + .serial_poll_response = fluke_serial_poll_response, + .serial_poll_status = fluke_serial_poll_status, + .t1_delay = fluke_t1_delay, + .return_to_local = fluke_return_to_local, }; irqreturn_t fluke_gpib_internal_interrupt(gpib_board_t *board) @@ -1011,12 +1011,12 @@ static int fluke_attach_impl(gpib_board_t *board, const gpib_board_config_t *con } e_priv->gpib_iomem_res = res; - nec_priv->iobase = ioremap(e_priv->gpib_iomem_res->start, + nec_priv->mmiobase = ioremap(e_priv->gpib_iomem_res->start, resource_size(e_priv->gpib_iomem_res)); - pr_info("gpib: iobase %lx remapped to %p, length=%d\n", - (unsigned long)e_priv->gpib_iomem_res->start, - nec_priv->iobase, (int)resource_size(e_priv->gpib_iomem_res)); - if (!nec_priv->iobase) { + pr_info("gpib: mmiobase %llx remapped to %p, length=%d\n", + (u64)e_priv->gpib_iomem_res->start, + nec_priv->mmiobase, (int)resource_size(e_priv->gpib_iomem_res)); + if (!nec_priv->mmiobase) { dev_err(&fluke_gpib_pdev->dev, "Could not map I/O memory\n"); return -ENOMEM; } @@ -1107,7 +1107,7 @@ void fluke_detach(gpib_board_t *board) gpib_free_pseudo_irq(board); nec_priv = &e_priv->nec7210_priv; - if (nec_priv->iobase) { + if (nec_priv->mmiobase) { fluke_paged_write_byte(e_priv, 0, ISR0_IMR0, ISR0_IMR0_PAGE); nec7210_board_reset(nec_priv, board); } @@ -1155,16 +1155,38 @@ static int __init fluke_init_module(void) result = platform_driver_register(&fluke_gpib_platform_driver); if (result) { - pr_err("fluke_gpib: platform_driver_register failed!\n"); + pr_err("fluke_gpib: platform_driver_register failed: error = %d\n", result); return result; } - gpib_register_driver(&fluke_unaccel_interface, THIS_MODULE); - gpib_register_driver(&fluke_hybrid_interface, THIS_MODULE); - gpib_register_driver(&fluke_interface, THIS_MODULE); + result = gpib_register_driver(&fluke_unaccel_interface, THIS_MODULE); + if (result) { + pr_err("fluke_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_unaccel; + } + + result = gpib_register_driver(&fluke_hybrid_interface, THIS_MODULE); + if (result) { + pr_err("fluke_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_hybrid; + } + + result = gpib_register_driver(&fluke_interface, THIS_MODULE); + if (result) { + pr_err("fluke_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_interface; + } - pr_info("fluke_gpib\n"); return 0; + +err_interface: + gpib_unregister_driver(&fluke_hybrid_interface); +err_hybrid: + gpib_unregister_driver(&fluke_unaccel_interface); +err_unaccel: + platform_driver_unregister(&fluke_gpib_platform_driver); + + return result; } static void __exit fluke_exit_module(void) diff --git a/drivers/staging/gpib/eastwood/fluke_gpib.h b/drivers/staging/gpib/eastwood/fluke_gpib.h index fcbd42f8f9af..3e4348196b42 100644 --- a/drivers/staging/gpib/eastwood/fluke_gpib.h +++ b/drivers/staging/gpib/eastwood/fluke_gpib.h @@ -21,7 +21,7 @@ struct fluke_priv { struct dma_chan *dma_channel; u8 *dma_buffer; int dma_buffer_size; - void *write_transfer_counter; + void __iomem *write_transfer_counter; }; // cb7210 specific registers and bits @@ -72,7 +72,7 @@ static inline uint8_t fluke_read_byte_nolock(struct nec7210_priv *nec_priv, { u8 retval; - retval = readl(nec_priv->iobase + register_num * nec_priv->offset); + retval = readl(nec_priv->mmiobase + register_num * nec_priv->offset); return retval; } @@ -80,7 +80,7 @@ static inline uint8_t fluke_read_byte_nolock(struct nec7210_priv *nec_priv, static inline void fluke_write_byte_nolock(struct nec7210_priv *nec_priv, uint8_t data, int register_num) { - writel(data, nec_priv->iobase + register_num * nec_priv->offset); + writel(data, nec_priv->mmiobase + register_num * nec_priv->offset); } static inline uint8_t fluke_paged_read_byte(struct fluke_priv *e_priv, diff --git a/drivers/staging/gpib/fmh_gpib/fmh_gpib.c b/drivers/staging/gpib/fmh_gpib/fmh_gpib.c index 62791db1c34a..f950e7cdd8f8 100644 --- a/drivers/staging/gpib/fmh_gpib/fmh_gpib.c +++ b/drivers/staging/gpib/fmh_gpib/fmh_gpib.c @@ -24,6 +24,8 @@ #include MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("GPIB Driver for fmh_gpib_core"); +MODULE_AUTHOR("Frank Mori Hess "); static irqreturn_t fmh_gpib_interrupt(int irq, void *arg); static int fmh_gpib_attach_holdoff_all(gpib_board_t *board, const gpib_board_config_t *config); @@ -1038,116 +1040,116 @@ static int fmh_gpib_fifo_read(gpib_board_t *board, uint8_t *buffer, size_t lengt return retval; } -gpib_interface_t fmh_gpib_unaccel_interface = { -name: "fmh_gpib_unaccel", -attach : fmh_gpib_attach_holdoff_all, -detach : fmh_gpib_detach, -read : fmh_gpib_read, -write : fmh_gpib_write, -command : fmh_gpib_command, -take_control : fmh_gpib_take_control, -go_to_standby : fmh_gpib_go_to_standby, -request_system_control : fmh_gpib_request_system_control, -interface_clear : fmh_gpib_interface_clear, -remote_enable : fmh_gpib_remote_enable, -enable_eos : fmh_gpib_enable_eos, -disable_eos : fmh_gpib_disable_eos, -parallel_poll : fmh_gpib_parallel_poll, -parallel_poll_configure : fmh_gpib_parallel_poll_configure, -parallel_poll_response : fmh_gpib_parallel_poll_response, -local_parallel_poll_mode : fmh_gpib_local_parallel_poll_mode, -line_status : fmh_gpib_line_status, -update_status : fmh_gpib_update_status, -primary_address : fmh_gpib_primary_address, -secondary_address : fmh_gpib_secondary_address, -serial_poll_response2 : fmh_gpib_serial_poll_response2, -serial_poll_status : fmh_gpib_serial_poll_status, -t1_delay : fmh_gpib_t1_delay, -return_to_local : fmh_gpib_return_to_local, +static gpib_interface_t fmh_gpib_unaccel_interface = { + .name = "fmh_gpib_unaccel", + .attach = fmh_gpib_attach_holdoff_all, + .detach = fmh_gpib_detach, + .read = fmh_gpib_read, + .write = fmh_gpib_write, + .command = fmh_gpib_command, + .take_control = fmh_gpib_take_control, + .go_to_standby = fmh_gpib_go_to_standby, + .request_system_control = fmh_gpib_request_system_control, + .interface_clear = fmh_gpib_interface_clear, + .remote_enable = fmh_gpib_remote_enable, + .enable_eos = fmh_gpib_enable_eos, + .disable_eos = fmh_gpib_disable_eos, + .parallel_poll = fmh_gpib_parallel_poll, + .parallel_poll_configure = fmh_gpib_parallel_poll_configure, + .parallel_poll_response = fmh_gpib_parallel_poll_response, + .local_parallel_poll_mode = fmh_gpib_local_parallel_poll_mode, + .line_status = fmh_gpib_line_status, + .update_status = fmh_gpib_update_status, + .primary_address = fmh_gpib_primary_address, + .secondary_address = fmh_gpib_secondary_address, + .serial_poll_response2 = fmh_gpib_serial_poll_response2, + .serial_poll_status = fmh_gpib_serial_poll_status, + .t1_delay = fmh_gpib_t1_delay, + .return_to_local = fmh_gpib_return_to_local, }; -gpib_interface_t fmh_gpib_interface = { -name: "fmh_gpib", -attach : fmh_gpib_attach_holdoff_end, -detach : fmh_gpib_detach, -read : fmh_gpib_accel_read, -write : fmh_gpib_accel_write, -command : fmh_gpib_command, -take_control : fmh_gpib_take_control, -go_to_standby : fmh_gpib_go_to_standby, -request_system_control : fmh_gpib_request_system_control, -interface_clear : fmh_gpib_interface_clear, -remote_enable : fmh_gpib_remote_enable, -enable_eos : fmh_gpib_enable_eos, -disable_eos : fmh_gpib_disable_eos, -parallel_poll : fmh_gpib_parallel_poll, -parallel_poll_configure : fmh_gpib_parallel_poll_configure, -parallel_poll_response : fmh_gpib_parallel_poll_response, -local_parallel_poll_mode : fmh_gpib_local_parallel_poll_mode, -line_status : fmh_gpib_line_status, -update_status : fmh_gpib_update_status, -primary_address : fmh_gpib_primary_address, -secondary_address : fmh_gpib_secondary_address, -serial_poll_response2 : fmh_gpib_serial_poll_response2, -serial_poll_status : fmh_gpib_serial_poll_status, -t1_delay : fmh_gpib_t1_delay, -return_to_local : fmh_gpib_return_to_local, +static gpib_interface_t fmh_gpib_interface = { + .name = "fmh_gpib", + .attach = fmh_gpib_attach_holdoff_end, + .detach = fmh_gpib_detach, + .read = fmh_gpib_accel_read, + .write = fmh_gpib_accel_write, + .command = fmh_gpib_command, + .take_control = fmh_gpib_take_control, + .go_to_standby = fmh_gpib_go_to_standby, + .request_system_control = fmh_gpib_request_system_control, + .interface_clear = fmh_gpib_interface_clear, + .remote_enable = fmh_gpib_remote_enable, + .enable_eos = fmh_gpib_enable_eos, + .disable_eos = fmh_gpib_disable_eos, + .parallel_poll = fmh_gpib_parallel_poll, + .parallel_poll_configure = fmh_gpib_parallel_poll_configure, + .parallel_poll_response = fmh_gpib_parallel_poll_response, + .local_parallel_poll_mode = fmh_gpib_local_parallel_poll_mode, + .line_status = fmh_gpib_line_status, + .update_status = fmh_gpib_update_status, + .primary_address = fmh_gpib_primary_address, + .secondary_address = fmh_gpib_secondary_address, + .serial_poll_response2 = fmh_gpib_serial_poll_response2, + .serial_poll_status = fmh_gpib_serial_poll_status, + .t1_delay = fmh_gpib_t1_delay, + .return_to_local = fmh_gpib_return_to_local, }; -gpib_interface_t fmh_gpib_pci_interface = { -name: "fmh_gpib_pci", -attach : fmh_gpib_pci_attach_holdoff_end, -detach : fmh_gpib_pci_detach, -read : fmh_gpib_fifo_read, -write : fmh_gpib_fifo_write, -command : fmh_gpib_command, -take_control : fmh_gpib_take_control, -go_to_standby : fmh_gpib_go_to_standby, -request_system_control : fmh_gpib_request_system_control, -interface_clear : fmh_gpib_interface_clear, -remote_enable : fmh_gpib_remote_enable, -enable_eos : fmh_gpib_enable_eos, -disable_eos : fmh_gpib_disable_eos, -parallel_poll : fmh_gpib_parallel_poll, -parallel_poll_configure : fmh_gpib_parallel_poll_configure, -parallel_poll_response : fmh_gpib_parallel_poll_response, -local_parallel_poll_mode : fmh_gpib_local_parallel_poll_mode, -line_status : fmh_gpib_line_status, -update_status : fmh_gpib_update_status, -primary_address : fmh_gpib_primary_address, -secondary_address : fmh_gpib_secondary_address, -serial_poll_response2 : fmh_gpib_serial_poll_response2, -serial_poll_status : fmh_gpib_serial_poll_status, -t1_delay : fmh_gpib_t1_delay, -return_to_local : fmh_gpib_return_to_local, +static gpib_interface_t fmh_gpib_pci_interface = { + .name = "fmh_gpib_pci", + .attach = fmh_gpib_pci_attach_holdoff_end, + .detach = fmh_gpib_pci_detach, + .read = fmh_gpib_fifo_read, + .write = fmh_gpib_fifo_write, + .command = fmh_gpib_command, + .take_control = fmh_gpib_take_control, + .go_to_standby = fmh_gpib_go_to_standby, + .request_system_control = fmh_gpib_request_system_control, + .interface_clear = fmh_gpib_interface_clear, + .remote_enable = fmh_gpib_remote_enable, + .enable_eos = fmh_gpib_enable_eos, + .disable_eos = fmh_gpib_disable_eos, + .parallel_poll = fmh_gpib_parallel_poll, + .parallel_poll_configure = fmh_gpib_parallel_poll_configure, + .parallel_poll_response = fmh_gpib_parallel_poll_response, + .local_parallel_poll_mode = fmh_gpib_local_parallel_poll_mode, + .line_status = fmh_gpib_line_status, + .update_status = fmh_gpib_update_status, + .primary_address = fmh_gpib_primary_address, + .secondary_address = fmh_gpib_secondary_address, + .serial_poll_response2 = fmh_gpib_serial_poll_response2, + .serial_poll_status = fmh_gpib_serial_poll_status, + .t1_delay = fmh_gpib_t1_delay, + .return_to_local = fmh_gpib_return_to_local, }; -gpib_interface_t fmh_gpib_pci_unaccel_interface = { -name: "fmh_gpib_pci_unaccel", -attach : fmh_gpib_pci_attach_holdoff_all, -detach : fmh_gpib_pci_detach, -read : fmh_gpib_read, -write : fmh_gpib_write, -command : fmh_gpib_command, -take_control : fmh_gpib_take_control, -go_to_standby : fmh_gpib_go_to_standby, -request_system_control : fmh_gpib_request_system_control, -interface_clear : fmh_gpib_interface_clear, -remote_enable : fmh_gpib_remote_enable, -enable_eos : fmh_gpib_enable_eos, -disable_eos : fmh_gpib_disable_eos, -parallel_poll : fmh_gpib_parallel_poll, -parallel_poll_configure : fmh_gpib_parallel_poll_configure, -parallel_poll_response : fmh_gpib_parallel_poll_response, -local_parallel_poll_mode : fmh_gpib_local_parallel_poll_mode, -line_status : fmh_gpib_line_status, -update_status : fmh_gpib_update_status, -primary_address : fmh_gpib_primary_address, -secondary_address : fmh_gpib_secondary_address, -serial_poll_response2 : fmh_gpib_serial_poll_response2, -serial_poll_status : fmh_gpib_serial_poll_status, -t1_delay : fmh_gpib_t1_delay, -return_to_local : fmh_gpib_return_to_local, +static gpib_interface_t fmh_gpib_pci_unaccel_interface = { + .name = "fmh_gpib_pci_unaccel", + .attach = fmh_gpib_pci_attach_holdoff_all, + .detach = fmh_gpib_pci_detach, + .read = fmh_gpib_read, + .write = fmh_gpib_write, + .command = fmh_gpib_command, + .take_control = fmh_gpib_take_control, + .go_to_standby = fmh_gpib_go_to_standby, + .request_system_control = fmh_gpib_request_system_control, + .interface_clear = fmh_gpib_interface_clear, + .remote_enable = fmh_gpib_remote_enable, + .enable_eos = fmh_gpib_enable_eos, + .disable_eos = fmh_gpib_disable_eos, + .parallel_poll = fmh_gpib_parallel_poll, + .parallel_poll_configure = fmh_gpib_parallel_poll_configure, + .parallel_poll_response = fmh_gpib_parallel_poll_response, + .local_parallel_poll_mode = fmh_gpib_local_parallel_poll_mode, + .line_status = fmh_gpib_line_status, + .update_status = fmh_gpib_update_status, + .primary_address = fmh_gpib_primary_address, + .secondary_address = fmh_gpib_secondary_address, + .serial_poll_response2 = fmh_gpib_serial_poll_response2, + .serial_poll_status = fmh_gpib_serial_poll_status, + .t1_delay = fmh_gpib_t1_delay, + .return_to_local = fmh_gpib_return_to_local, }; irqreturn_t fmh_gpib_internal_interrupt(gpib_board_t *board) @@ -1419,15 +1421,14 @@ static int fmh_gpib_attach_impl(gpib_board_t *board, const gpib_board_config_t * } e_priv->gpib_iomem_res = res; - nec_priv->iobase = ioremap(e_priv->gpib_iomem_res->start, + nec_priv->mmiobase = ioremap(e_priv->gpib_iomem_res->start, resource_size(e_priv->gpib_iomem_res)); - if (!nec_priv->iobase) { + if (!nec_priv->mmiobase) { dev_err(board->dev, "Could not map I/O memory for gpib\n"); return -ENOMEM; } - dev_info(board->dev, "iobase 0x%lx remapped to %p, length=%ld\n", - (unsigned long)e_priv->gpib_iomem_res->start, - nec_priv->iobase, (unsigned long)resource_size(e_priv->gpib_iomem_res)); + dev_info(board->dev, "iobase %pr remapped to %p\n", + e_priv->gpib_iomem_res, nec_priv->mmiobase); res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dma_fifos"); if (!res) { @@ -1507,14 +1508,14 @@ void fmh_gpib_detach(gpib_board_t *board) free_irq(e_priv->irq, board); if (e_priv->fifo_base) fifos_write(e_priv, 0, FIFO_CONTROL_STATUS_REG); - if (nec_priv->iobase) { + if (nec_priv->mmiobase) { write_byte(nec_priv, 0, ISR0_IMR0_REG); nec7210_board_reset(nec_priv, board); } if (e_priv->fifo_base) iounmap(e_priv->fifo_base); - if (nec_priv->iobase) - iounmap(nec_priv->iobase); + if (nec_priv->mmiobase) + iounmap(nec_priv->mmiobase); if (e_priv->dma_port_res) { release_mem_region(e_priv->dma_port_res->start, resource_size(e_priv->dma_port_res)); @@ -1564,12 +1565,12 @@ static int fmh_gpib_pci_attach_impl(gpib_board_t *board, const gpib_board_config e_priv->gpib_iomem_res = &pci_device->resource[gpib_control_status_pci_resource_index]; e_priv->dma_port_res = &pci_device->resource[gpib_fifo_pci_resource_index]; - nec_priv->iobase = ioremap(pci_resource_start(pci_device, + nec_priv->mmiobase = ioremap(pci_resource_start(pci_device, gpib_control_status_pci_resource_index), pci_resource_len(pci_device, gpib_control_status_pci_resource_index)); dev_info(board->dev, "base address for gpib control/status registers remapped to 0x%p\n", - nec_priv->iobase); + nec_priv->mmiobase); if (e_priv->dma_port_res->flags & IORESOURCE_MEM) { e_priv->fifo_base = ioremap(pci_resource_start(pci_device, @@ -1632,14 +1633,14 @@ void fmh_gpib_pci_detach(gpib_board_t *board) free_irq(e_priv->irq, board); if (e_priv->fifo_base) fifos_write(e_priv, 0, FIFO_CONTROL_STATUS_REG); - if (nec_priv->iobase) { + if (nec_priv->mmiobase) { write_byte(nec_priv, 0, ISR0_IMR0_REG); nec7210_board_reset(nec_priv, board); } if (e_priv->fifo_base) iounmap(e_priv->fifo_base); - if (nec_priv->iobase) - iounmap(nec_priv->iobase); + if (nec_priv->mmiobase) + iounmap(nec_priv->mmiobase); if (e_priv->dma_port_res || e_priv->gpib_iomem_res) pci_release_regions(to_pci_dev(board->dev)); if (board->dev) @@ -1691,23 +1692,54 @@ static int __init fmh_gpib_init_module(void) result = platform_driver_register(&fmh_gpib_platform_driver); if (result) { - pr_err("fmh_gpib: platform_driver_register failed!\n"); + pr_err("fmh_gpib: platform_driver_register failed: error = %d\n", result); return result; } result = pci_register_driver(&fmh_gpib_pci_driver); if (result) { - pr_err("fmh_gpib: pci_driver_register failed!\n"); - return result; + pr_err("fmh_gpib: pci_register_driver failed: error = %d\n", result); + goto err_pci_driver; } - gpib_register_driver(&fmh_gpib_unaccel_interface, THIS_MODULE); - gpib_register_driver(&fmh_gpib_interface, THIS_MODULE); - gpib_register_driver(&fmh_gpib_pci_unaccel_interface, THIS_MODULE); - gpib_register_driver(&fmh_gpib_pci_interface, THIS_MODULE); + result = gpib_register_driver(&fmh_gpib_unaccel_interface, THIS_MODULE); + if (result) { + pr_err("fmh_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_unaccel; + } + + result = gpib_register_driver(&fmh_gpib_interface, THIS_MODULE); + if (result) { + pr_err("fmh_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_interface; + } + + result = gpib_register_driver(&fmh_gpib_pci_unaccel_interface, THIS_MODULE); + if (result) { + pr_err("fmh_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_pci_unaccel; + } + + result = gpib_register_driver(&fmh_gpib_pci_interface, THIS_MODULE); + if (result) { + pr_err("fmh_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_pci; + } - pr_info("fmh_gpib\n"); return 0; + +err_pci: + gpib_unregister_driver(&fmh_gpib_pci_unaccel_interface); +err_pci_unaccel: + gpib_unregister_driver(&fmh_gpib_interface); +err_interface: + gpib_unregister_driver(&fmh_gpib_unaccel_interface); +err_unaccel: + pci_unregister_driver(&fmh_gpib_pci_driver); +err_pci_driver: + platform_driver_unregister(&fmh_gpib_platform_driver); + + return result; } static void __exit fmh_gpib_exit_module(void) diff --git a/drivers/staging/gpib/fmh_gpib/fmh_gpib.h b/drivers/staging/gpib/fmh_gpib/fmh_gpib.h index 43bfc89d2a6f..de6fd2164414 100644 --- a/drivers/staging/gpib/fmh_gpib/fmh_gpib.h +++ b/drivers/staging/gpib/fmh_gpib/fmh_gpib.h @@ -33,7 +33,7 @@ struct fmh_priv { u8 *dma_buffer; int dma_buffer_size; int dma_burst_length; - void *fifo_base; + void __iomem *fifo_base; unsigned supports_fifo_interrupts : 1; }; @@ -127,13 +127,13 @@ static const unsigned int fifo_max_burst_length_mask = 0x00ff; static inline uint8_t gpib_cs_read_byte(struct nec7210_priv *nec_priv, unsigned int register_num) { - return readb(nec_priv->iobase + register_num * nec_priv->offset); + return readb(nec_priv->mmiobase + register_num * nec_priv->offset); } static inline void gpib_cs_write_byte(struct nec7210_priv *nec_priv, uint8_t data, unsigned int register_num) { - writeb(data, nec_priv->iobase + register_num * nec_priv->offset); + writeb(data, nec_priv->mmiobase + register_num * nec_priv->offset); } static inline uint16_t fifos_read(struct fmh_priv *fmh_priv, int register_num) diff --git a/drivers/staging/gpib/gpio/Makefile b/drivers/staging/gpib/gpio/Makefile index a31ded6e5924..00ea52abdda7 100644 --- a/drivers/staging/gpib/gpio/Makefile +++ b/drivers/staging/gpib/gpio/Makefile @@ -1,4 +1,4 @@ -obj-m += gpib_bitbang.o +obj-$(CONFIG_GPIB_GPIO) += gpib_bitbang.o diff --git a/drivers/staging/gpib/gpio/gpib_bitbang.c b/drivers/staging/gpib/gpio/gpib_bitbang.c index a2d562cbd65b..828c99ea613f 100644 --- a/drivers/staging/gpib/gpio/gpib_bitbang.c +++ b/drivers/staging/gpib/gpio/gpib_bitbang.c @@ -147,7 +147,7 @@ DEFINE_LED_TRIGGER(ledtrig_gpib); led_trigger_event(ledtrig_gpib, LED_OFF); } \ while (0) -struct gpio_desc *all_descriptors[GPIB_PINS + SN7516X_PINS]; +static struct gpio_desc *all_descriptors[GPIB_PINS + SN7516X_PINS]; #define D01 all_descriptors[0] #define D02 all_descriptors[1] @@ -175,7 +175,7 @@ struct gpio_desc *all_descriptors[GPIB_PINS + SN7516X_PINS]; /* YOGA dapter uses a global enable for the buffer chips, re-using the TE pin */ #define YOGA_ENABLE TE -int gpios_vector[] = { +static int gpios_vector[] = { D01_pin_nr, D02_pin_nr, D03_pin_nr, @@ -265,7 +265,7 @@ static struct gpiod_lookup_table gpib_gpio_table_0 = { static struct gpiod_lookup_table *lookup_tables[] = { &gpib_gpio_table_0, &gpib_gpio_table_1, - 0 + NULL }; /* struct which defines private_data for gpio driver */ @@ -315,7 +315,7 @@ struct bb_priv { enum listener_function_state listener_state; }; -inline long usec_diff(struct timespec64 *a, struct timespec64 *b); +static inline long usec_diff(struct timespec64 *a, struct timespec64 *b); static void bb_buffer_print(unsigned char *buffer, size_t length, int cmd, int eoi); static void set_data_lines(u8 byte); static u8 get_data_lines(void); @@ -1119,7 +1119,7 @@ static void release_gpios(void) for (j = 0 ; j < NUM_PINS ; j++) { if (all_descriptors[j]) { gpiod_put(all_descriptors[j]); - all_descriptors[j] = 0; + all_descriptors[j] = NULL; } } } @@ -1312,36 +1312,41 @@ bb_attach_out: return retval; } -gpib_interface_t bb_interface = { -name: NAME, -attach : bb_attach, -detach : bb_detach, -read : bb_read, -write : bb_write, -command : bb_command, -take_control : bb_take_control, -go_to_standby : bb_go_to_standby, -request_system_control : bb_request_system_control, -interface_clear : bb_interface_clear, -remote_enable : bb_remote_enable, -enable_eos : bb_enable_eos, -disable_eos : bb_disable_eos, -parallel_poll : bb_parallel_poll, -parallel_poll_configure : bb_parallel_poll_configure, -parallel_poll_response : bb_parallel_poll_response, -line_status : bb_line_status, -update_status : bb_update_status, -primary_address : bb_primary_address, -secondary_address : bb_secondary_address, -serial_poll_response : bb_serial_poll_response, -serial_poll_status : bb_serial_poll_status, -t1_delay : bb_t1_delay, -return_to_local : bb_return_to_local, +static gpib_interface_t bb_interface = { + .name = NAME, + .attach = bb_attach, + .detach = bb_detach, + .read = bb_read, + .write = bb_write, + .command = bb_command, + .take_control = bb_take_control, + .go_to_standby = bb_go_to_standby, + .request_system_control = bb_request_system_control, + .interface_clear = bb_interface_clear, + .remote_enable = bb_remote_enable, + .enable_eos = bb_enable_eos, + .disable_eos = bb_disable_eos, + .parallel_poll = bb_parallel_poll, + .parallel_poll_configure = bb_parallel_poll_configure, + .parallel_poll_response = bb_parallel_poll_response, + .line_status = bb_line_status, + .update_status = bb_update_status, + .primary_address = bb_primary_address, + .secondary_address = bb_secondary_address, + .serial_poll_response = bb_serial_poll_response, + .serial_poll_status = bb_serial_poll_status, + .t1_delay = bb_t1_delay, + .return_to_local = bb_return_to_local, }; static int __init bb_init_module(void) { - gpib_register_driver(&bb_interface, THIS_MODULE); + int result = gpib_register_driver(&bb_interface, THIS_MODULE); + + if (result) { + pr_err("gpib_bitbang: gpib_register_driver failed: error = %d\n", result); + return result; + } dbg_printk(0, "module loaded with pin map \"%s\"%s\n", pin_map, (sn7516x_used) ? " and SN7516x driver support" : ""); diff --git a/drivers/staging/gpib/hp_82335/Makefile b/drivers/staging/gpib/hp_82335/Makefile index 8b7a552e9355..305ce44ee48a 100644 --- a/drivers/staging/gpib/hp_82335/Makefile +++ b/drivers/staging/gpib/hp_82335/Makefile @@ -1,4 +1,4 @@ -obj-m += hp82335.o +obj-$(CONFIG_GPIB_HP82335) += hp82335.o diff --git a/drivers/staging/gpib/hp_82335/hp82335.c b/drivers/staging/gpib/hp_82335/hp82335.c index 40afe42aea47..700d1ba029d2 100644 --- a/drivers/staging/gpib/hp_82335/hp82335.c +++ b/drivers/staging/gpib/hp_82335/hp82335.c @@ -9,6 +9,7 @@ */ #include "hp82335.h" +#include #include #include #include @@ -172,32 +173,32 @@ void hp82335_return_to_local(gpib_board_t *board) tms9914_return_to_local(board, &priv->tms9914_priv); } -gpib_interface_t hp82335_interface = { -name: "hp82335", -attach : hp82335_attach, -detach : hp82335_detach, -read : hp82335_read, -write : hp82335_write, -command : hp82335_command, -request_system_control : hp82335_request_system_control, -take_control : hp82335_take_control, -go_to_standby : hp82335_go_to_standby, -interface_clear : hp82335_interface_clear, -remote_enable : hp82335_remote_enable, -enable_eos : hp82335_enable_eos, -disable_eos : hp82335_disable_eos, -parallel_poll : hp82335_parallel_poll, -parallel_poll_configure : hp82335_parallel_poll_configure, -parallel_poll_response : hp82335_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : hp82335_line_status, -update_status : hp82335_update_status, -primary_address : hp82335_primary_address, -secondary_address : hp82335_secondary_address, -serial_poll_response : hp82335_serial_poll_response, -serial_poll_status : hp82335_serial_poll_status, -t1_delay : hp82335_t1_delay, -return_to_local : hp82335_return_to_local, +static gpib_interface_t hp82335_interface = { + .name = "hp82335", + .attach = hp82335_attach, + .detach = hp82335_detach, + .read = hp82335_read, + .write = hp82335_write, + .command = hp82335_command, + .request_system_control = hp82335_request_system_control, + .take_control = hp82335_take_control, + .go_to_standby = hp82335_go_to_standby, + .interface_clear = hp82335_interface_clear, + .remote_enable = hp82335_remote_enable, + .enable_eos = hp82335_enable_eos, + .disable_eos = hp82335_disable_eos, + .parallel_poll = hp82335_parallel_poll, + .parallel_poll_configure = hp82335_parallel_poll_configure, + .parallel_poll_response = hp82335_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = hp82335_line_status, + .update_status = hp82335_update_status, + .primary_address = hp82335_primary_address, + .secondary_address = hp82335_secondary_address, + .serial_poll_response = hp82335_serial_poll_response, + .serial_poll_status = hp82335_serial_poll_status, + .t1_delay = hp82335_t1_delay, + .return_to_local = hp82335_return_to_local, }; int hp82335_allocate_private(gpib_board_t *board) @@ -233,7 +234,7 @@ static void hp82335_clear_interrupt(struct hp82335_priv *hp_priv) { struct tms9914_priv *tms_priv = &hp_priv->tms9914_priv; - writeb(0, tms_priv->iobase + HPREG_INTR_CLEAR); + writeb(0, tms_priv->mmiobase + HPREG_INTR_CLEAR); } int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) @@ -241,7 +242,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) struct hp82335_priv *hp_priv; struct tms9914_priv *tms_priv; int retval; - const unsigned long upper_iomem_base = (unsigned long)config->ibbase + hp82335_rom_size; + const unsigned long upper_iomem_base = config->ibbase + hp82335_rom_size; board->status = 0; @@ -253,7 +254,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) tms_priv->write_byte = hp82335_write_byte; tms_priv->offset = 1; - switch ((unsigned long)(config->ibbase)) { + switch (config->ibbase) { case 0xc4000: case 0xc8000: case 0xcc000: @@ -271,7 +272,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) case 0xfc000: break; default: - pr_err("hp82335: invalid base io address 0x%p\n", config->ibbase); + pr_err("hp82335: invalid base io address 0x%u\n", config->ibbase); return -EINVAL; } if (!request_mem_region(upper_iomem_base, hp82335_upper_iomem_size, "hp82335")) { @@ -280,9 +281,9 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) return -EBUSY; } hp_priv->raw_iobase = upper_iomem_base; - tms_priv->iobase = ioremap(upper_iomem_base, hp82335_upper_iomem_size); + tms_priv->mmiobase = ioremap(upper_iomem_base, hp82335_upper_iomem_size); pr_info("hp82335: upper half of 82335 iomem region 0x%lx remapped to 0x%p\n", - hp_priv->raw_iobase, tms_priv->iobase); + hp_priv->raw_iobase, tms_priv->mmiobase); retval = request_irq(config->ibirq, hp82335_interrupt, 0, "hp82335", board); if (retval) { @@ -296,7 +297,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) hp82335_clear_interrupt(hp_priv); - writeb(INTR_ENABLE, tms_priv->iobase + HPREG_CCR); + writeb(INTR_ENABLE, tms_priv->mmiobase + HPREG_CCR); tms9914_online(board, tms_priv); @@ -312,10 +313,10 @@ void hp82335_detach(gpib_board_t *board) tms_priv = &hp_priv->tms9914_priv; if (hp_priv->irq) free_irq(hp_priv->irq, board); - if (tms_priv->iobase) { - writeb(0, tms_priv->iobase + HPREG_CCR); + if (tms_priv->mmiobase) { + writeb(0, tms_priv->mmiobase + HPREG_CCR); tms9914_board_reset(tms_priv); - iounmap((void *)tms_priv->iobase); + iounmap(tms_priv->mmiobase); } if (hp_priv->raw_iobase) release_mem_region(hp_priv->raw_iobase, hp82335_upper_iomem_size); @@ -325,7 +326,13 @@ void hp82335_detach(gpib_board_t *board) static int __init hp82335_init_module(void) { - gpib_register_driver(&hp82335_interface, THIS_MODULE); + int result = gpib_register_driver(&hp82335_interface, THIS_MODULE); + + if (result) { + pr_err("hp82335: gpib_register_driver failed: error = %d\n", result); + return result; + } + return 0; } diff --git a/drivers/staging/gpib/hp_82335/hp82335.h b/drivers/staging/gpib/hp_82335/hp82335.h index 5e5297af731a..4b185d7c5188 100644 --- a/drivers/staging/gpib/hp_82335/hp82335.h +++ b/drivers/staging/gpib/hp_82335/hp82335.h @@ -17,9 +17,6 @@ struct hp82335_priv { unsigned long raw_iobase; }; -// interfaces -extern gpib_interface_t hp82335_interface; - // interface functions int hp82335_read(gpib_board_t *board, uint8_t *buffer, size_t length, int *end, size_t *bytes_read); int hp82335_write(gpib_board_t *board, uint8_t *buffer, size_t length, diff --git a/drivers/staging/gpib/hp_82341/Makefile b/drivers/staging/gpib/hp_82341/Makefile index 1fe7db4f8ca4..21367310a17e 100644 --- a/drivers/staging/gpib/hp_82341/Makefile +++ b/drivers/staging/gpib/hp_82341/Makefile @@ -1,2 +1,2 @@ -obj-m += hp_82341.o +obj-$(CONFIG_GPIB_HP82341) += hp_82341.o diff --git a/drivers/staging/gpib/hp_82341/hp_82341.c b/drivers/staging/gpib/hp_82341/hp_82341.c index 8ad1c885a9fb..0ddae295912f 100644 --- a/drivers/staging/gpib/hp_82341/hp_82341.c +++ b/drivers/staging/gpib/hp_82341/hp_82341.c @@ -402,59 +402,59 @@ void hp_82341_return_to_local(gpib_board_t *board) tms9914_return_to_local(board, &priv->tms9914_priv); } -gpib_interface_t hp_82341_unaccel_interface = { -name: "hp_82341_unaccel", -attach : hp_82341_attach, -detach : hp_82341_detach, -read : hp_82341_read, -write : hp_82341_write, -command : hp_82341_command, -request_system_control : hp_82341_request_system_control, -take_control : hp_82341_take_control, -go_to_standby : hp_82341_go_to_standby, -interface_clear : hp_82341_interface_clear, -remote_enable : hp_82341_remote_enable, -enable_eos : hp_82341_enable_eos, -disable_eos : hp_82341_disable_eos, -parallel_poll : hp_82341_parallel_poll, -parallel_poll_configure : hp_82341_parallel_poll_configure, -parallel_poll_response : hp_82341_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : hp_82341_line_status, -update_status : hp_82341_update_status, -primary_address : hp_82341_primary_address, -secondary_address : hp_82341_secondary_address, -serial_poll_response : hp_82341_serial_poll_response, -serial_poll_status : hp_82341_serial_poll_status, -t1_delay : hp_82341_t1_delay, -return_to_local : hp_82341_return_to_local, +static gpib_interface_t hp_82341_unaccel_interface = { + .name = "hp_82341_unaccel", + .attach = hp_82341_attach, + .detach = hp_82341_detach, + .read = hp_82341_read, + .write = hp_82341_write, + .command = hp_82341_command, + .request_system_control = hp_82341_request_system_control, + .take_control = hp_82341_take_control, + .go_to_standby = hp_82341_go_to_standby, + .interface_clear = hp_82341_interface_clear, + .remote_enable = hp_82341_remote_enable, + .enable_eos = hp_82341_enable_eos, + .disable_eos = hp_82341_disable_eos, + .parallel_poll = hp_82341_parallel_poll, + .parallel_poll_configure = hp_82341_parallel_poll_configure, + .parallel_poll_response = hp_82341_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = hp_82341_line_status, + .update_status = hp_82341_update_status, + .primary_address = hp_82341_primary_address, + .secondary_address = hp_82341_secondary_address, + .serial_poll_response = hp_82341_serial_poll_response, + .serial_poll_status = hp_82341_serial_poll_status, + .t1_delay = hp_82341_t1_delay, + .return_to_local = hp_82341_return_to_local, }; -gpib_interface_t hp_82341_interface = { -name: "hp_82341", -attach : hp_82341_attach, -detach : hp_82341_detach, -read : hp_82341_accel_read, -write : hp_82341_accel_write, -command : hp_82341_command, -request_system_control : hp_82341_request_system_control, -take_control : hp_82341_take_control, -go_to_standby : hp_82341_go_to_standby, -interface_clear : hp_82341_interface_clear, -remote_enable : hp_82341_remote_enable, -enable_eos : hp_82341_enable_eos, -disable_eos : hp_82341_disable_eos, -parallel_poll : hp_82341_parallel_poll, -parallel_poll_configure : hp_82341_parallel_poll_configure, -parallel_poll_response : hp_82341_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : hp_82341_line_status, -update_status : hp_82341_update_status, -primary_address : hp_82341_primary_address, -secondary_address : hp_82341_secondary_address, -serial_poll_response : hp_82341_serial_poll_response, -t1_delay : hp_82341_t1_delay, -return_to_local : hp_82341_return_to_local, +static gpib_interface_t hp_82341_interface = { + .name = "hp_82341", + .attach = hp_82341_attach, + .detach = hp_82341_detach, + .read = hp_82341_accel_read, + .write = hp_82341_accel_write, + .command = hp_82341_command, + .request_system_control = hp_82341_request_system_control, + .take_control = hp_82341_take_control, + .go_to_standby = hp_82341_go_to_standby, + .interface_clear = hp_82341_interface_clear, + .remote_enable = hp_82341_remote_enable, + .enable_eos = hp_82341_enable_eos, + .disable_eos = hp_82341_disable_eos, + .parallel_poll = hp_82341_parallel_poll, + .parallel_poll_configure = hp_82341_parallel_poll_configure, + .parallel_poll_response = hp_82341_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = hp_82341_line_status, + .update_status = hp_82341_update_status, + .primary_address = hp_82341_primary_address, + .secondary_address = hp_82341_secondary_address, + .serial_poll_response = hp_82341_serial_poll_response, + .t1_delay = hp_82341_t1_delay, + .return_to_local = hp_82341_return_to_local, }; int hp_82341_allocate_private(gpib_board_t *board) @@ -473,12 +473,12 @@ void hp_82341_free_private(gpib_board_t *board) static uint8_t hp_82341_read_byte(struct tms9914_priv *priv, unsigned int register_num) { - return inb((unsigned long)(priv->iobase) + register_num); + return inb(priv->iobase + register_num); } static void hp_82341_write_byte(struct tms9914_priv *priv, uint8_t data, unsigned int register_num) { - outb(data, (unsigned long)(priv->iobase) + register_num); + outb(data, priv->iobase + register_num); } static int hp_82341_find_isapnp_board(struct pnp_dev **dev) @@ -682,8 +682,8 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) { struct hp_82341_priv *hp_priv; struct tms9914_priv *tms_priv; - unsigned long start_addr; - void *iobase; + u32 start_addr; + u32 iobase; int irq; int i; int retval; @@ -704,7 +704,7 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) if (retval < 0) return retval; hp_priv->pnp_dev = dev; - iobase = (void *)(pnp_port_start(dev, 0)); + iobase = pnp_port_start(dev, 0); irq = pnp_irq(dev, 0); hp_priv->hw_version = HW_VERSION_82341D; hp_priv->io_region_offset = 0x8; @@ -714,9 +714,9 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) hp_priv->hw_version = HW_VERSION_82341C; hp_priv->io_region_offset = 0x400; } - pr_info("hp_82341: base io 0x%p\n", iobase); + pr_info("hp_82341: base io 0x%u\n", iobase); for (i = 0; i < hp_82341_num_io_regions; ++i) { - start_addr = (unsigned long)(iobase) + i * hp_priv->io_region_offset; + start_addr = iobase + i * hp_priv->io_region_offset; if (!request_region(start_addr, hp_82341_region_iosize, "hp_82341")) { pr_err("hp_82341: failed to allocate io ports 0x%lx-0x%lx\n", start_addr, @@ -725,7 +725,7 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) } hp_priv->iobase[i] = start_addr; } - tms_priv->iobase = (void *)(hp_priv->iobase[2]); + tms_priv->iobase = hp_priv->iobase[2]; if (hp_priv->hw_version == HW_VERSION_82341D) { retval = isapnp_cfg_begin(hp_priv->pnp_dev->card->number, hp_priv->pnp_dev->number); @@ -807,8 +807,21 @@ MODULE_DEVICE_TABLE(pnp, hp_82341_pnp_table); static int __init hp_82341_init_module(void) { - gpib_register_driver(&hp_82341_unaccel_interface, THIS_MODULE); - gpib_register_driver(&hp_82341_interface, THIS_MODULE); + int ret; + + ret = gpib_register_driver(&hp_82341_unaccel_interface, THIS_MODULE); + if (ret) { + pr_err("hp_82341: gpib_register_driver failed: error = %d\n", ret); + return ret; + } + + ret = gpib_register_driver(&hp_82341_interface, THIS_MODULE); + if (ret) { + pr_err("hp_82341: gpib_register_driver failed: error = %d\n", ret); + gpib_unregister_driver(&hp_82341_unaccel_interface); + return ret; + } + return 0; } diff --git a/drivers/staging/gpib/hp_82341/hp_82341.h b/drivers/staging/gpib/hp_82341/hp_82341.h index 7c391860b399..0065ebd9747c 100644 --- a/drivers/staging/gpib/hp_82341/hp_82341.h +++ b/drivers/staging/gpib/hp_82341/hp_82341.h @@ -26,8 +26,6 @@ struct hp_82341_priv { enum hp_82341_hardware_version hw_version; }; -// interfaces -extern gpib_interface_t hp_82341_interface; // interface functions int hp_82341_accel_read(gpib_board_t *board, uint8_t *buffer, size_t length, int *end, diff --git a/drivers/staging/gpib/include/amcc5920.h b/drivers/staging/gpib/include/amcc5920.h index 766b3799223f..7a88bd282feb 100644 --- a/drivers/staging/gpib/include/amcc5920.h +++ b/drivers/staging/gpib/include/amcc5920.h @@ -22,7 +22,7 @@ static const int bits_per_region = 8; static inline uint32_t amcc_wait_state_bits(unsigned int region, unsigned int num_wait_states) { - return (num_wait_states & 0x7) << (-region * bits_per_region); + return (num_wait_states & 0x7) << (--region * bits_per_region); }; enum amcc_prefetch_bits { diff --git a/drivers/staging/gpib/include/gpibP.h b/drivers/staging/gpib/include/gpibP.h index 5fc42b645ab7..d35fdd391f7e 100644 --- a/drivers/staging/gpib/include/gpibP.h +++ b/drivers/staging/gpib/include/gpibP.h @@ -16,8 +16,9 @@ #include #include +#include -void gpib_register_driver(gpib_interface_t *interface, struct module *mod); +int gpib_register_driver(gpib_interface_t *interface, struct module *mod); void gpib_unregister_driver(gpib_interface_t *interface); struct pci_dev *gpib_pci_get_device(const gpib_board_config_t *config, unsigned int vendor_id, unsigned int device_id, struct pci_dev *from); @@ -35,16 +36,5 @@ extern gpib_board_t board_array[GPIB_MAX_NUM_BOARDS]; extern struct list_head registered_drivers; -#include - -void writeb_wrapper(unsigned int value, void *address); -unsigned int readb_wrapper(void *address); -void outb_wrapper(unsigned int value, void *address); -unsigned int inb_wrapper(void *address); -void writew_wrapper(unsigned int value, void *address); -unsigned int readw_wrapper(void *address); -void outw_wrapper(unsigned int value, void *address); -unsigned int inw_wrapper(void *address); - #endif // _GPIB_P_H diff --git a/drivers/staging/gpib/include/gpib_types.h b/drivers/staging/gpib/include/gpib_types.h index ee2643da6d71..b41781a55a60 100644 --- a/drivers/staging/gpib/include/gpib_types.h +++ b/drivers/staging/gpib/include/gpib_types.h @@ -31,7 +31,8 @@ typedef struct { void *init_data; int init_data_length; /* IO base address to use for non-pnp cards (set by core, driver should make local copy) */ - void *ibbase; + u32 ibbase; + void __iomem *mmibbase; /* IRQ to use for non-pnp cards (set by core, driver should make local copy) */ unsigned int ibirq; /* dma channel to use for non-pnp cards (set by core, driver should make local copy) */ diff --git a/drivers/staging/gpib/include/nec7210.h b/drivers/staging/gpib/include/nec7210.h index c00aba4ce846..ca998c4a84bf 100644 --- a/drivers/staging/gpib/include/nec7210.h +++ b/drivers/staging/gpib/include/nec7210.h @@ -18,7 +18,10 @@ /* struct used to provide variables local to a nec7210 chip */ struct nec7210_priv { - void *iobase; +#ifdef CONFIG_HAS_IOPORT + u32 iobase; +#endif + void __iomem *mmiobase; unsigned int offset; // offset between successive nec7210 io addresses unsigned int dma_channel; u8 *dma_buffer; diff --git a/drivers/staging/gpib/include/tms9914.h b/drivers/staging/gpib/include/tms9914.h index 456b488212d2..d8c8d1c9b131 100644 --- a/drivers/staging/gpib/include/tms9914.h +++ b/drivers/staging/gpib/include/tms9914.h @@ -20,7 +20,10 @@ enum tms9914_holdoff_mode { /* struct used to provide variables local to a tms9914 chip */ struct tms9914_priv { - void *iobase; +#ifdef CONFIG_HAS_IOPORT + u32 iobase; +#endif + void __iomem *mmiobase; unsigned int offset; // offset between successive tms9914 io addresses unsigned int dma_channel; // software copy of bits written to interrupt mask registers diff --git a/drivers/staging/gpib/ines/Makefile b/drivers/staging/gpib/ines/Makefile index cdcaa59a4e39..6b6e480fd811 100644 --- a/drivers/staging/gpib/ines/Makefile +++ b/drivers/staging/gpib/ines/Makefile @@ -1,4 +1,4 @@ ccflags-$(CONFIG_GPIB_PCMCIA) := -DGPIB_PCMCIA -obj-m += ines_gpib.o +obj-$(CONFIG_GPIB_INES) += ines_gpib.o diff --git a/drivers/staging/gpib/ines/ines.h b/drivers/staging/gpib/ines/ines.h index 7e8302619998..3918737fa21a 100644 --- a/drivers/staging/gpib/ines/ines.h +++ b/drivers/staging/gpib/ines/ines.h @@ -35,13 +35,6 @@ struct ines_priv { u8 extend_mode_bits; }; -// interfaces -extern gpib_interface_t ines_pci_interface; -extern gpib_interface_t ines_pci_accel_interface; -extern gpib_interface_t ines_pcmcia_interface; -extern gpib_interface_t ines_pcmcia_accel_interface; -extern gpib_interface_t ines_pcmcia_unaccel_interface; - // interface functions int ines_read(gpib_board_t *board, uint8_t *buffer, size_t length, int *end, size_t *bytes_read); int ines_write(gpib_board_t *board, uint8_t *buffer, size_t length, @@ -83,14 +76,14 @@ void ines_set_xfer_counter(struct ines_priv *priv, unsigned int count); /* inb/outb wrappers */ static inline unsigned int ines_inb(struct ines_priv *priv, unsigned int register_number) { - return inb((unsigned long)(priv->nec7210_priv.iobase) + + return inb(priv->nec7210_priv.iobase + register_number * priv->nec7210_priv.offset); } static inline void ines_outb(struct ines_priv *priv, unsigned int value, unsigned int register_number) { - outb(value, (unsigned long)(priv->nec7210_priv.iobase) + + outb(value, priv->nec7210_priv.iobase + register_number * priv->nec7210_priv.offset); } diff --git a/drivers/staging/gpib/ines/ines_gpib.c b/drivers/staging/gpib/ines/ines_gpib.c index 9d8387c3bf01..22a05a287bce 100644 --- a/drivers/staging/gpib/ines/ines_gpib.c +++ b/drivers/staging/gpib/ines/ines_gpib.c @@ -273,10 +273,10 @@ irqreturn_t ines_pci_interrupt(int irq, void *arg) struct nec7210_priv *nec_priv = &priv->nec7210_priv; if (priv->pci_chip_type == PCI_CHIP_QUANCOM) { - if ((inb((unsigned long)nec_priv->iobase + + if ((inb(nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG) & QUANCOM_IRQ_ASSERTED_BIT)) - outb(QUANCOM_IRQ_ENABLE_BIT, (unsigned long)(nec_priv->iobase) + + outb(QUANCOM_IRQ_ENABLE_BIT, nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG); } @@ -357,38 +357,38 @@ struct ines_pci_id { enum ines_pci_chip pci_chip_type; }; -struct ines_pci_id pci_ids[] = { - {vendor_id: PCI_VENDOR_ID_PLX, - device_id : PCI_DEVICE_ID_PLX_9050, - subsystem_vendor_id : PCI_VENDOR_ID_PLX, - subsystem_device_id : PCI_SUBDEVICE_ID_INES_GPIB, - gpib_region : 2, - io_offset : 1, - pci_chip_type : PCI_CHIP_PLX9050, +static struct ines_pci_id pci_ids[] = { + {.vendor_id = PCI_VENDOR_ID_PLX, + .device_id = PCI_DEVICE_ID_PLX_9050, + .subsystem_vendor_id = PCI_VENDOR_ID_PLX, + .subsystem_device_id = PCI_SUBDEVICE_ID_INES_GPIB, + .gpib_region = 2, + .io_offset = 1, + .pci_chip_type = PCI_CHIP_PLX9050, }, - {vendor_id: PCI_VENDOR_ID_AMCC, - device_id : PCI_DEVICE_ID_INES_GPIB_AMCC, - subsystem_vendor_id : PCI_VENDOR_ID_AMCC, - subsystem_device_id : PCI_SUBDEVICE_ID_INES_GPIB, - gpib_region : 1, - io_offset : 1, - pci_chip_type : PCI_CHIP_AMCC5920, + {.vendor_id = PCI_VENDOR_ID_AMCC, + .device_id = PCI_DEVICE_ID_INES_GPIB_AMCC, + .subsystem_vendor_id = PCI_VENDOR_ID_AMCC, + .subsystem_device_id = PCI_SUBDEVICE_ID_INES_GPIB, + .gpib_region = 1, + .io_offset = 1, + .pci_chip_type = PCI_CHIP_AMCC5920, }, - {vendor_id: PCI_VENDOR_ID_INES_QUICKLOGIC, - device_id : PCI_DEVICE_ID_INES_GPIB_QL5030, - subsystem_vendor_id : PCI_VENDOR_ID_INES_QUICKLOGIC, - subsystem_device_id : PCI_DEVICE_ID_INES_GPIB_QL5030, - gpib_region : 1, - io_offset : 1, - pci_chip_type : PCI_CHIP_QUICKLOGIC5030, + {.vendor_id = PCI_VENDOR_ID_INES_QUICKLOGIC, + .device_id = PCI_DEVICE_ID_INES_GPIB_QL5030, + .subsystem_vendor_id = PCI_VENDOR_ID_INES_QUICKLOGIC, + .subsystem_device_id = PCI_DEVICE_ID_INES_GPIB_QL5030, + .gpib_region = 1, + .io_offset = 1, + .pci_chip_type = PCI_CHIP_QUICKLOGIC5030, }, - {vendor_id: PCI_VENDOR_ID_QUANCOM, - device_id : PCI_DEVICE_ID_QUANCOM_GPIB, - subsystem_vendor_id : -1, - subsystem_device_id : -1, - gpib_region : 0, - io_offset : 4, - pci_chip_type : PCI_CHIP_QUANCOM, + {.vendor_id = PCI_VENDOR_ID_QUANCOM, + .device_id = PCI_DEVICE_ID_QUANCOM_GPIB, + .subsystem_vendor_id = -1, + .subsystem_device_id = -1, + .gpib_region = 0, + .io_offset = 4, + .pci_chip_type = PCI_CHIP_QUANCOM, }, }; @@ -540,116 +540,116 @@ void ines_return_to_local(gpib_board_t *board) nec7210_return_to_local(board, &priv->nec7210_priv); } -gpib_interface_t ines_pci_unaccel_interface = { -name: "ines_pci_unaccel", -attach : ines_pci_attach, -detach : ines_pci_detach, -read : ines_read, -write : ines_write, -command : ines_command, -take_control : ines_take_control, -go_to_standby : ines_go_to_standby, -request_system_control : ines_request_system_control, -interface_clear : ines_interface_clear, -remote_enable : ines_remote_enable, -enable_eos : ines_enable_eos, -disable_eos : ines_disable_eos, -parallel_poll : ines_parallel_poll, -parallel_poll_configure : ines_parallel_poll_configure, -parallel_poll_response : ines_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : ines_line_status, -update_status : ines_update_status, -primary_address : ines_primary_address, -secondary_address : ines_secondary_address, -serial_poll_response : ines_serial_poll_response, -serial_poll_status : ines_serial_poll_status, -t1_delay : ines_t1_delay, -return_to_local : ines_return_to_local, +static gpib_interface_t ines_pci_unaccel_interface = { + .name = "ines_pci_unaccel", + .attach = ines_pci_attach, + .detach = ines_pci_detach, + .read = ines_read, + .write = ines_write, + .command = ines_command, + .take_control = ines_take_control, + .go_to_standby = ines_go_to_standby, + .request_system_control = ines_request_system_control, + .interface_clear = ines_interface_clear, + .remote_enable = ines_remote_enable, + .enable_eos = ines_enable_eos, + .disable_eos = ines_disable_eos, + .parallel_poll = ines_parallel_poll, + .parallel_poll_configure = ines_parallel_poll_configure, + .parallel_poll_response = ines_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = ines_line_status, + .update_status = ines_update_status, + .primary_address = ines_primary_address, + .secondary_address = ines_secondary_address, + .serial_poll_response = ines_serial_poll_response, + .serial_poll_status = ines_serial_poll_status, + .t1_delay = ines_t1_delay, + .return_to_local = ines_return_to_local, }; -gpib_interface_t ines_pci_interface = { -name: "ines_pci", -attach : ines_pci_accel_attach, -detach : ines_pci_detach, -read : ines_accel_read, -write : ines_accel_write, -command : ines_command, -take_control : ines_take_control, -go_to_standby : ines_go_to_standby, -request_system_control : ines_request_system_control, -interface_clear : ines_interface_clear, -remote_enable : ines_remote_enable, -enable_eos : ines_enable_eos, -disable_eos : ines_disable_eos, -parallel_poll : ines_parallel_poll, -parallel_poll_configure : ines_parallel_poll_configure, -parallel_poll_response : ines_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : ines_line_status, -update_status : ines_update_status, -primary_address : ines_primary_address, -secondary_address : ines_secondary_address, -serial_poll_response : ines_serial_poll_response, -serial_poll_status : ines_serial_poll_status, -t1_delay : ines_t1_delay, -return_to_local : ines_return_to_local, +static gpib_interface_t ines_pci_interface = { + .name = "ines_pci", + .attach = ines_pci_accel_attach, + .detach = ines_pci_detach, + .read = ines_accel_read, + .write = ines_accel_write, + .command = ines_command, + .take_control = ines_take_control, + .go_to_standby = ines_go_to_standby, + .request_system_control = ines_request_system_control, + .interface_clear = ines_interface_clear, + .remote_enable = ines_remote_enable, + .enable_eos = ines_enable_eos, + .disable_eos = ines_disable_eos, + .parallel_poll = ines_parallel_poll, + .parallel_poll_configure = ines_parallel_poll_configure, + .parallel_poll_response = ines_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = ines_line_status, + .update_status = ines_update_status, + .primary_address = ines_primary_address, + .secondary_address = ines_secondary_address, + .serial_poll_response = ines_serial_poll_response, + .serial_poll_status = ines_serial_poll_status, + .t1_delay = ines_t1_delay, + .return_to_local = ines_return_to_local, }; -gpib_interface_t ines_pci_accel_interface = { -name: "ines_pci_accel", -attach : ines_pci_accel_attach, -detach : ines_pci_detach, -read : ines_accel_read, -write : ines_accel_write, -command : ines_command, -take_control : ines_take_control, -go_to_standby : ines_go_to_standby, -request_system_control : ines_request_system_control, -interface_clear : ines_interface_clear, -remote_enable : ines_remote_enable, -enable_eos : ines_enable_eos, -disable_eos : ines_disable_eos, -parallel_poll : ines_parallel_poll, -parallel_poll_configure : ines_parallel_poll_configure, -parallel_poll_response : ines_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : ines_line_status, -update_status : ines_update_status, -primary_address : ines_primary_address, -secondary_address : ines_secondary_address, -serial_poll_response : ines_serial_poll_response, -serial_poll_status : ines_serial_poll_status, -t1_delay : ines_t1_delay, -return_to_local : ines_return_to_local, +static gpib_interface_t ines_pci_accel_interface = { + .name = "ines_pci_accel", + .attach = ines_pci_accel_attach, + .detach = ines_pci_detach, + .read = ines_accel_read, + .write = ines_accel_write, + .command = ines_command, + .take_control = ines_take_control, + .go_to_standby = ines_go_to_standby, + .request_system_control = ines_request_system_control, + .interface_clear = ines_interface_clear, + .remote_enable = ines_remote_enable, + .enable_eos = ines_enable_eos, + .disable_eos = ines_disable_eos, + .parallel_poll = ines_parallel_poll, + .parallel_poll_configure = ines_parallel_poll_configure, + .parallel_poll_response = ines_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = ines_line_status, + .update_status = ines_update_status, + .primary_address = ines_primary_address, + .secondary_address = ines_secondary_address, + .serial_poll_response = ines_serial_poll_response, + .serial_poll_status = ines_serial_poll_status, + .t1_delay = ines_t1_delay, + .return_to_local = ines_return_to_local, }; -gpib_interface_t ines_isa_interface = { -name: "ines_isa", -attach : ines_isa_attach, -detach : ines_isa_detach, -read : ines_accel_read, -write : ines_accel_write, -command : ines_command, -take_control : ines_take_control, -go_to_standby : ines_go_to_standby, -request_system_control : ines_request_system_control, -interface_clear : ines_interface_clear, -remote_enable : ines_remote_enable, -enable_eos : ines_enable_eos, -disable_eos : ines_disable_eos, -parallel_poll : ines_parallel_poll, -parallel_poll_configure : ines_parallel_poll_configure, -parallel_poll_response : ines_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : ines_line_status, -update_status : ines_update_status, -primary_address : ines_primary_address, -secondary_address : ines_secondary_address, -serial_poll_response : ines_serial_poll_response, -serial_poll_status : ines_serial_poll_status, -t1_delay : ines_t1_delay, -return_to_local : ines_return_to_local, +static gpib_interface_t ines_isa_interface = { + .name = "ines_isa", + .attach = ines_isa_attach, + .detach = ines_isa_detach, + .read = ines_accel_read, + .write = ines_accel_write, + .command = ines_command, + .take_control = ines_take_control, + .go_to_standby = ines_go_to_standby, + .request_system_control = ines_request_system_control, + .interface_clear = ines_interface_clear, + .remote_enable = ines_remote_enable, + .enable_eos = ines_enable_eos, + .disable_eos = ines_disable_eos, + .parallel_poll = ines_parallel_poll, + .parallel_poll_configure = ines_parallel_poll_configure, + .parallel_poll_response = ines_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = ines_line_status, + .update_status = ines_update_status, + .primary_address = ines_primary_address, + .secondary_address = ines_secondary_address, + .serial_poll_response = ines_serial_poll_response, + .serial_poll_status = ines_serial_poll_status, + .t1_delay = ines_t1_delay, + .return_to_local = ines_return_to_local, }; static int ines_allocate_private(gpib_board_t *board) @@ -780,8 +780,8 @@ static int ines_common_pci_attach(gpib_board_t *board, const gpib_board_config_t if (pci_request_regions(ines_priv->pci_device, "ines-gpib")) return -1; - nec_priv->iobase = (void *)(pci_resource_start(ines_priv->pci_device, - found_id.gpib_region)); + nec_priv->iobase = pci_resource_start(ines_priv->pci_device, + found_id.gpib_region); ines_priv->pci_chip_type = found_id.pci_chip_type; nec_priv->offset = found_id.io_offset; @@ -840,7 +840,7 @@ static int ines_common_pci_attach(gpib_board_t *board, const gpib_board_config_t } break; case PCI_CHIP_QUANCOM: - outb(QUANCOM_IRQ_ENABLE_BIT, (unsigned long)(nec_priv->iobase) + + outb(QUANCOM_IRQ_ENABLE_BIT, nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG); break; case PCI_CHIP_QUICKLOGIC5030: @@ -899,8 +899,8 @@ int ines_isa_attach(gpib_board_t *board, const gpib_board_config_t *config) ines_priv = board->private_data; nec_priv = &ines_priv->nec7210_priv; - if (!request_region((unsigned long)config->ibbase, ines_isa_iosize, "ines_gpib")) { - pr_err("ines_gpib: ioports at 0x%p already in use\n", config->ibbase); + if (!request_region(config->ibbase, ines_isa_iosize, "ines_gpib")) { + pr_err("ines_gpib: ioports at 0x%x already in use\n", config->ibbase); return -1; } nec_priv->iobase = config->ibbase; @@ -931,7 +931,7 @@ void ines_pci_detach(gpib_board_t *board) break; case PCI_CHIP_QUANCOM: if (nec_priv->iobase) - outb(0, (unsigned long)(nec_priv->iobase) + + outb(0, nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG); break; default: @@ -960,7 +960,7 @@ void ines_isa_detach(gpib_board_t *board) free_irq(ines_priv->irq, board); if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); - release_region((unsigned long)(nec_priv->iobase), ines_isa_iosize); + release_region(nec_priv->iobase, ines_isa_iosize); } } ines_free_private(board); @@ -1122,7 +1122,7 @@ static int ines_gpib_config(struct pcmcia_device *link) { struct local_info *dev; int retval; - void *virt; + void __iomem *virt; dev = link->priv; DEBUG(0, "%s(0x%p)\n", __func__, link); @@ -1156,7 +1156,7 @@ static int ines_gpib_config(struct pcmcia_device *link) } virt = ioremap(link->resource[2]->start, resource_size(link->resource[2])); writeb((link->resource[2]->start >> 2) & 0xff, virt + 0xf0); // IOWindow base - iounmap((void *)virt); + iounmap(virt); /* * This actually configures the PCMCIA socket -- setting up @@ -1227,100 +1227,94 @@ static struct pcmcia_driver ines_gpib_cs_driver = { .resume = ines_gpib_resume, }; -int ines_pcmcia_init_module(void) -{ - pcmcia_register_driver(&ines_gpib_cs_driver); - return 0; -} - void ines_pcmcia_cleanup_module(void) { DEBUG(0, "ines_cs: unloading\n"); pcmcia_unregister_driver(&ines_gpib_cs_driver); } -gpib_interface_t ines_pcmcia_unaccel_interface = { -name: "ines_pcmcia_unaccel", -attach : ines_pcmcia_attach, -detach : ines_pcmcia_detach, -read : ines_read, -write : ines_write, -command : ines_command, -take_control : ines_take_control, -go_to_standby : ines_go_to_standby, -request_system_control : ines_request_system_control, -interface_clear : ines_interface_clear, -remote_enable : ines_remote_enable, -enable_eos : ines_enable_eos, -disable_eos : ines_disable_eos, -parallel_poll : ines_parallel_poll, -parallel_poll_configure : ines_parallel_poll_configure, -parallel_poll_response : ines_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : ines_line_status, -update_status : ines_update_status, -primary_address : ines_primary_address, -secondary_address : ines_secondary_address, -serial_poll_response : ines_serial_poll_response, -serial_poll_status : ines_serial_poll_status, -t1_delay : ines_t1_delay, -return_to_local : ines_return_to_local, +static gpib_interface_t ines_pcmcia_unaccel_interface = { + .name = "ines_pcmcia_unaccel", + .attach = ines_pcmcia_attach, + .detach = ines_pcmcia_detach, + .read = ines_read, + .write = ines_write, + .command = ines_command, + .take_control = ines_take_control, + .go_to_standby = ines_go_to_standby, + .request_system_control = ines_request_system_control, + .interface_clear = ines_interface_clear, + .remote_enable = ines_remote_enable, + .enable_eos = ines_enable_eos, + .disable_eos = ines_disable_eos, + .parallel_poll = ines_parallel_poll, + .parallel_poll_configure = ines_parallel_poll_configure, + .parallel_poll_response = ines_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = ines_line_status, + .update_status = ines_update_status, + .primary_address = ines_primary_address, + .secondary_address = ines_secondary_address, + .serial_poll_response = ines_serial_poll_response, + .serial_poll_status = ines_serial_poll_status, + .t1_delay = ines_t1_delay, + .return_to_local = ines_return_to_local, }; -gpib_interface_t ines_pcmcia_accel_interface = { -name: "ines_pcmcia_accel", -attach : ines_pcmcia_accel_attach, -detach : ines_pcmcia_detach, -read : ines_accel_read, -write : ines_accel_write, -command : ines_command, -take_control : ines_take_control, -go_to_standby : ines_go_to_standby, -request_system_control : ines_request_system_control, -interface_clear : ines_interface_clear, -remote_enable : ines_remote_enable, -enable_eos : ines_enable_eos, -disable_eos : ines_disable_eos, -parallel_poll : ines_parallel_poll, -parallel_poll_configure : ines_parallel_poll_configure, -parallel_poll_response : ines_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : ines_line_status, -update_status : ines_update_status, -primary_address : ines_primary_address, -secondary_address : ines_secondary_address, -serial_poll_response : ines_serial_poll_response, -serial_poll_status : ines_serial_poll_status, -t1_delay : ines_t1_delay, -return_to_local : ines_return_to_local, +static gpib_interface_t ines_pcmcia_accel_interface = { + .name = "ines_pcmcia_accel", + .attach = ines_pcmcia_accel_attach, + .detach = ines_pcmcia_detach, + .read = ines_accel_read, + .write = ines_accel_write, + .command = ines_command, + .take_control = ines_take_control, + .go_to_standby = ines_go_to_standby, + .request_system_control = ines_request_system_control, + .interface_clear = ines_interface_clear, + .remote_enable = ines_remote_enable, + .enable_eos = ines_enable_eos, + .disable_eos = ines_disable_eos, + .parallel_poll = ines_parallel_poll, + .parallel_poll_configure = ines_parallel_poll_configure, + .parallel_poll_response = ines_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = ines_line_status, + .update_status = ines_update_status, + .primary_address = ines_primary_address, + .secondary_address = ines_secondary_address, + .serial_poll_response = ines_serial_poll_response, + .serial_poll_status = ines_serial_poll_status, + .t1_delay = ines_t1_delay, + .return_to_local = ines_return_to_local, }; -gpib_interface_t ines_pcmcia_interface = { -name: "ines_pcmcia", -attach : ines_pcmcia_accel_attach, -detach : ines_pcmcia_detach, -read : ines_accel_read, -write : ines_accel_write, -command : ines_command, -take_control : ines_take_control, -go_to_standby : ines_go_to_standby, -request_system_control : ines_request_system_control, -interface_clear : ines_interface_clear, -remote_enable : ines_remote_enable, -enable_eos : ines_enable_eos, -disable_eos : ines_disable_eos, -parallel_poll : ines_parallel_poll, -parallel_poll_configure : ines_parallel_poll_configure, -parallel_poll_response : ines_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : ines_line_status, -update_status : ines_update_status, -primary_address : ines_primary_address, -secondary_address : ines_secondary_address, -serial_poll_response : ines_serial_poll_response, -serial_poll_status : ines_serial_poll_status, -t1_delay : ines_t1_delay, -return_to_local : ines_return_to_local, +static gpib_interface_t ines_pcmcia_interface = { + .name = "ines_pcmcia", + .attach = ines_pcmcia_accel_attach, + .detach = ines_pcmcia_detach, + .read = ines_accel_read, + .write = ines_accel_write, + .command = ines_command, + .take_control = ines_take_control, + .go_to_standby = ines_go_to_standby, + .request_system_control = ines_request_system_control, + .interface_clear = ines_interface_clear, + .remote_enable = ines_remote_enable, + .enable_eos = ines_enable_eos, + .disable_eos = ines_disable_eos, + .parallel_poll = ines_parallel_poll, + .parallel_poll_configure = ines_parallel_poll_configure, + .parallel_poll_response = ines_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = ines_line_status, + .update_status = ines_update_status, + .primary_address = ines_primary_address, + .secondary_address = ines_secondary_address, + .serial_poll_response = ines_serial_poll_response, + .serial_poll_status = ines_serial_poll_status, + .t1_delay = ines_t1_delay, + .return_to_local = ines_return_to_local, }; irqreturn_t ines_pcmcia_interrupt(int irq, void *arg) @@ -1348,14 +1342,14 @@ int ines_common_pcmcia_attach(gpib_board_t *board) ines_priv = board->private_data; nec_priv = &ines_priv->nec7210_priv; - if (request_region(curr_dev->resource[0]->start, - resource_size(curr_dev->resource[0]), "ines_gpib") == 0) { + if (!request_region(curr_dev->resource[0]->start, + resource_size(curr_dev->resource[0]), "ines_gpib")) { pr_err("ines_gpib: ioports at 0x%lx already in use\n", (unsigned long)(curr_dev->resource[0]->start)); return -1; } - nec_priv->iobase = (void *)(unsigned long)curr_dev->resource[0]->start; + nec_priv->iobase = curr_dev->resource[0]->start; nec7210_board_reset(nec_priv, board); @@ -1410,7 +1404,7 @@ void ines_pcmcia_detach(gpib_board_t *board) free_irq(ines_priv->irq, board); if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); - release_region((unsigned long)(nec_priv->iobase), ines_pcmcia_iosize); + release_region(nec_priv->iobase, ines_pcmcia_iosize); } } ines_free_private(board); @@ -1420,28 +1414,86 @@ void ines_pcmcia_detach(gpib_board_t *board) static int __init ines_init_module(void) { - int err = 0; + int ret; - err = pci_register_driver(&ines_pci_driver); - if (err) { - pr_err("ines_gpib: pci_driver_register failed!\n"); - return err; + ret = pci_register_driver(&ines_pci_driver); + if (ret) { + pr_err("ines_gpib: pci_register_driver failed: error = %d\n", ret); + return ret; + } + + ret = gpib_register_driver(&ines_pci_interface, THIS_MODULE); + if (ret) { + pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_pci; + } + + ret = gpib_register_driver(&ines_pci_unaccel_interface, THIS_MODULE); + if (ret) { + pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_pci_unaccel; + } + + ret = gpib_register_driver(&ines_pci_accel_interface, THIS_MODULE); + if (ret) { + pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_pci_accel; + } + + ret = gpib_register_driver(&ines_isa_interface, THIS_MODULE); + if (ret) { + pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_isa; } - gpib_register_driver(&ines_pci_interface, THIS_MODULE); - gpib_register_driver(&ines_pci_unaccel_interface, THIS_MODULE); - gpib_register_driver(&ines_pci_accel_interface, THIS_MODULE); - gpib_register_driver(&ines_isa_interface, THIS_MODULE); #ifdef GPIB_PCMCIA - gpib_register_driver(&ines_pcmcia_interface, THIS_MODULE); - gpib_register_driver(&ines_pcmcia_unaccel_interface, THIS_MODULE); - gpib_register_driver(&ines_pcmcia_accel_interface, THIS_MODULE); - err += ines_pcmcia_init_module(); + ret = gpib_register_driver(&ines_pcmcia_interface, THIS_MODULE); + if (ret) { + pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_pcmcia; + } + + ret = gpib_register_driver(&ines_pcmcia_unaccel_interface, THIS_MODULE); + if (ret) { + pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_pcmcia_unaccel; + } + + ret = gpib_register_driver(&ines_pcmcia_accel_interface, THIS_MODULE); + if (ret) { + pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_pcmcia_accel; + } + + ret = pcmcia_register_driver(&ines_gpib_cs_driver); + if (ret) { + pr_err("ines_gpib: pcmcia_register_driver failed: error = %d\n", ret); + goto err_pcmcia_driver; + } #endif - if (err) - return -1; return 0; + +#ifdef GPIB_PCMCIA +err_pcmcia_driver: + gpib_unregister_driver(&ines_pcmcia_accel_interface); +err_pcmcia_accel: + gpib_unregister_driver(&ines_pcmcia_unaccel_interface); +err_pcmcia_unaccel: + gpib_unregister_driver(&ines_pcmcia_interface); +err_pcmcia: +#endif + gpib_unregister_driver(&ines_isa_interface); +err_isa: + gpib_unregister_driver(&ines_pci_accel_interface); +err_pci_accel: + gpib_unregister_driver(&ines_pci_unaccel_interface); +err_pci_unaccel: + gpib_unregister_driver(&ines_pci_interface); +err_pci: + pci_unregister_driver(&ines_pci_driver); + + return ret; } static void __exit ines_exit_module(void) diff --git a/drivers/staging/gpib/lpvo_usb_gpib/Makefile b/drivers/staging/gpib/lpvo_usb_gpib/Makefile index 137511acce63..360553488e6d 100644 --- a/drivers/staging/gpib/lpvo_usb_gpib/Makefile +++ b/drivers/staging/gpib/lpvo_usb_gpib/Makefile @@ -1,3 +1,3 @@ -obj-m += lpvo_usb_gpib.o +obj-$(CONFIG_GPIB_LPVO) += lpvo_usb_gpib.o diff --git a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c index 267651a15fa0..85322af62c23 100644 --- a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c +++ b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c @@ -10,7 +10,6 @@ /* base module includes */ -#include #include #include #include @@ -25,7 +24,6 @@ #include #include #include -#include #include #include "gpibP.h" @@ -99,8 +97,8 @@ module_param(debug, int, 0644); #define USB_GPIB_DEBUG_ON "\nIBDE\xAA\n" #define USB_GPIB_SET_LISTEN "\nIBDT0\n" #define USB_GPIB_SET_TALK "\nIBDT1\n" -#define USB_GPIB_SET_LINES "\nIBDC\n" -#define USB_GPIB_SET_DATA "\nIBDM\n" +#define USB_GPIB_SET_LINES "\nIBDC.\n" +#define USB_GPIB_SET_DATA "\nIBDM.\n" #define USB_GPIB_READ_LINES "\nIBD?C\n" #define USB_GPIB_READ_DATA "\nIBD?M\n" #define USB_GPIB_READ_BUS "\nIBD??\n" @@ -210,7 +208,7 @@ static int skel_do_release(gpib_board_t *); * (unix time in sec and NANOsec) */ -inline int usec_diff(struct timespec64 *a, struct timespec64 *b) +static inline int usec_diff(struct timespec64 *a, struct timespec64 *b) { return ((a->tv_sec - b->tv_sec) * 1000000 + (a->tv_nsec - b->tv_nsec) / 1000); @@ -436,7 +434,7 @@ static void set_timeout(gpib_board_t *board) static int usb_gpib_attach(gpib_board_t *board, const gpib_board_config_t *config) { int retval, j; - int base = (long)config->ibbase; + u32 base = config->ibbase; char *device_path; int match; struct usb_device *udev; @@ -589,7 +587,7 @@ static int usb_gpib_command(gpib_board_t *board, size_t *bytes_written) { int i, retval; - char command[6] = "IBc\n"; + char command[6] = "IBc.\n"; DIA_LOG(1, "enter %p\n", board); @@ -608,7 +606,7 @@ static int usb_gpib_command(gpib_board_t *board, } /** - * disable_eos() - Disable END on eos byte (END on EOI only) + * usb_gpib_disable_eos() - Disable END on eos byte (END on EOI only) * * @board: the gpib_board data area for this gpib interface * @@ -624,7 +622,7 @@ static void usb_gpib_disable_eos(gpib_board_t *board) } /** - * enable_eos() - Enable END for reads when eos byte is received. + * usb_gpib_enable_eos() - Enable END for reads when eos byte is received. * * @board: the gpib_board data area for this gpib interface * @eos_byte: the 'eos' byte @@ -647,7 +645,7 @@ static int usb_gpib_enable_eos(gpib_board_t *board, } /** - * go_to_standby() - De-assert ATN + * usb_gpib_go_to_standby() - De-assert ATN * * @board: the gpib_board data area for this gpib interface */ @@ -664,7 +662,7 @@ static int usb_gpib_go_to_standby(gpib_board_t *board) } /** - * interface_clear() - Assert or de-assert IFC + * usb_gpib_interface_clear() - Assert or de-assert IFC * * @board: the gpib_board data area for this gpib interface * assert: 1: assert IFC; 0: de-assert IFC @@ -1133,33 +1131,33 @@ static unsigned int usb_gpib_t1_delay(gpib_board_t *board, unsigned int nano_sec * *** module dispatch table and init/exit functions *** */ -gpib_interface_t usb_gpib_interface = { -name: NAME, -attach : usb_gpib_attach, -detach : usb_gpib_detach, -read : usb_gpib_read, -write : usb_gpib_write, -command : usb_gpib_command, -take_control : usb_gpib_take_control, -go_to_standby : usb_gpib_go_to_standby, -request_system_control : usb_gpib_request_system_control, -interface_clear : usb_gpib_interface_clear, -remote_enable : usb_gpib_remote_enable, -enable_eos : usb_gpib_enable_eos, -disable_eos : usb_gpib_disable_eos, -parallel_poll : usb_gpib_parallel_poll, -parallel_poll_configure : usb_gpib_parallel_poll_configure, -parallel_poll_response : usb_gpib_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : usb_gpib_line_status, -update_status : usb_gpib_update_status, -primary_address : usb_gpib_primary_address, -secondary_address : usb_gpib_secondary_address, -serial_poll_response : usb_gpib_serial_poll_response, -serial_poll_status : usb_gpib_serial_poll_status, -t1_delay : usb_gpib_t1_delay, -return_to_local : usb_gpib_return_to_local, -skip_check_for_command_acceptors : 1 +static gpib_interface_t usb_gpib_interface = { + .name = NAME, + .attach = usb_gpib_attach, + .detach = usb_gpib_detach, + .read = usb_gpib_read, + .write = usb_gpib_write, + .command = usb_gpib_command, + .take_control = usb_gpib_take_control, + .go_to_standby = usb_gpib_go_to_standby, + .request_system_control = usb_gpib_request_system_control, + .interface_clear = usb_gpib_interface_clear, + .remote_enable = usb_gpib_remote_enable, + .enable_eos = usb_gpib_enable_eos, + .disable_eos = usb_gpib_disable_eos, + .parallel_poll = usb_gpib_parallel_poll, + .parallel_poll_configure = usb_gpib_parallel_poll_configure, + .parallel_poll_response = usb_gpib_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = usb_gpib_line_status, + .update_status = usb_gpib_update_status, + .primary_address = usb_gpib_primary_address, + .secondary_address = usb_gpib_secondary_address, + .serial_poll_response = usb_gpib_serial_poll_response, + .serial_poll_status = usb_gpib_serial_poll_status, + .t1_delay = usb_gpib_t1_delay, + .return_to_local = usb_gpib_return_to_local, + .skip_check_for_command_acceptors = 1 }; /* @@ -1181,7 +1179,11 @@ static int usb_gpib_init_module(struct usb_interface *interface) return rv; if (!assigned_usb_minors) { - gpib_register_driver(&usb_gpib_interface, THIS_MODULE); + rv = gpib_register_driver(&usb_gpib_interface, THIS_MODULE); + if (rv) { + pr_err("lpvo_usb_gpib: gpib_register_driver failed: error = %d\n", rv); + goto exit; + } } else { /* check if minor is already registered - maybe useless, but if * it happens the code is inconsistent somewhere @@ -1878,7 +1880,7 @@ static int skel_release(struct inode *inode, struct file *file) * user space access to read function */ -static ssize_t skel_read(struct file *file, char *buffer, size_t count, +static ssize_t skel_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct usb_skel *dev; @@ -1909,7 +1911,7 @@ static ssize_t skel_read(struct file *file, char *buffer, size_t count, * user space access to write function */ -static ssize_t skel_write(struct file *file, const char *user_buffer, +static ssize_t skel_write(struct file *file, const char __user *user_buffer, size_t count, loff_t *ppos) { struct usb_skel *dev; diff --git a/drivers/staging/gpib/nec7210/Makefile b/drivers/staging/gpib/nec7210/Makefile index 8d4d90f21109..64330f2e89d1 100644 --- a/drivers/staging/gpib/nec7210/Makefile +++ b/drivers/staging/gpib/nec7210/Makefile @@ -1,4 +1,4 @@ -obj-m += nec7210.o +obj-$(CONFIG_GPIB_NEC7210) += nec7210.o diff --git a/drivers/staging/gpib/nec7210/nec7210.c b/drivers/staging/gpib/nec7210/nec7210.c index 1d9951035497..c9a837fad96e 100644 --- a/drivers/staging/gpib/nec7210/nec7210.c +++ b/drivers/staging/gpib/nec7210/nec7210.c @@ -1035,7 +1035,7 @@ EXPORT_SYMBOL(nec7210_board_online); /* wrappers for io */ uint8_t nec7210_ioport_read_byte(struct nec7210_priv *priv, unsigned int register_num) { - return inb((unsigned long)(priv->iobase) + register_num * priv->offset); + return inb(priv->iobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_ioport_read_byte); @@ -1047,7 +1047,7 @@ void nec7210_ioport_write_byte(struct nec7210_priv *priv, uint8_t data, unsigned */ nec7210_locking_ioport_write_byte(priv, data, register_num); else - outb(data, (unsigned long)(priv->iobase) + register_num * priv->offset); + outb(data, priv->iobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_ioport_write_byte); @@ -1058,7 +1058,7 @@ uint8_t nec7210_locking_ioport_read_byte(struct nec7210_priv *priv, unsigned int unsigned long flags; spin_lock_irqsave(&priv->register_page_lock, flags); - retval = inb((unsigned long)(priv->iobase) + register_num * priv->offset); + retval = inb(priv->iobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); return retval; } @@ -1072,7 +1072,7 @@ void nec7210_locking_ioport_write_byte(struct nec7210_priv *priv, uint8_t data, spin_lock_irqsave(&priv->register_page_lock, flags); if (register_num == AUXMR) udelay(1); - outb(data, (unsigned long)(priv->iobase) + register_num * priv->offset); + outb(data, priv->iobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); } EXPORT_SYMBOL(nec7210_locking_ioport_write_byte); @@ -1080,7 +1080,7 @@ EXPORT_SYMBOL(nec7210_locking_ioport_write_byte); uint8_t nec7210_iomem_read_byte(struct nec7210_priv *priv, unsigned int register_num) { - return readb(priv->iobase + register_num * priv->offset); + return readb(priv->mmiobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_iomem_read_byte); @@ -1092,7 +1092,7 @@ void nec7210_iomem_write_byte(struct nec7210_priv *priv, uint8_t data, unsigned */ nec7210_locking_iomem_write_byte(priv, data, register_num); else - writeb(data, priv->iobase + register_num * priv->offset); + writeb(data, priv->mmiobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_iomem_write_byte); @@ -1102,7 +1102,7 @@ uint8_t nec7210_locking_iomem_read_byte(struct nec7210_priv *priv, unsigned int unsigned long flags; spin_lock_irqsave(&priv->register_page_lock, flags); - retval = readb(priv->iobase + register_num * priv->offset); + retval = readb(priv->mmiobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); return retval; } @@ -1116,7 +1116,7 @@ void nec7210_locking_iomem_write_byte(struct nec7210_priv *priv, uint8_t data, spin_lock_irqsave(&priv->register_page_lock, flags); if (register_num == AUXMR) udelay(1); - writeb(data, priv->iobase + register_num * priv->offset); + writeb(data, priv->mmiobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); } EXPORT_SYMBOL(nec7210_locking_iomem_write_byte); diff --git a/drivers/staging/gpib/ni_usb/Makefile b/drivers/staging/gpib/ni_usb/Makefile index e22b3b21a62c..469c5d16add3 100644 --- a/drivers/staging/gpib/ni_usb/Makefile +++ b/drivers/staging/gpib/ni_usb/Makefile @@ -1,4 +1,4 @@ -obj-m += ni_usb_gpib.o +obj-$(CONFIG_GPIB_NI_USB) += ni_usb_gpib.o diff --git a/drivers/staging/gpib/ni_usb/ni_usb_gpib.c b/drivers/staging/gpib/ni_usb/ni_usb_gpib.c index b7b6fb1be379..d0656dc520f5 100644 --- a/drivers/staging/gpib/ni_usb/ni_usb_gpib.c +++ b/drivers/staging/gpib/ni_usb/ni_usb_gpib.c @@ -85,7 +85,7 @@ static void ni_usb_bulk_complete(struct urb *urb) // printk("debug: %s: status=0x%x, error_count=%i, actual_length=%i\n", __func__, // urb->status, urb->error_count, urb->actual_length); - up(&context->complete); + complete(&context->complete); } static void ni_usb_timeout_handler(struct timer_list *t) @@ -94,7 +94,7 @@ static void ni_usb_timeout_handler(struct timer_list *t) struct ni_usb_urb_ctx *context = &ni_priv->context; context->timed_out = 1; - up(&context->complete); + complete(&context->complete); }; // I'm using nonblocking loosely here, it only means -EAGAIN can be returned in certain cases @@ -124,7 +124,7 @@ static int ni_usb_nonblocking_send_bulk_msg(struct ni_usb_priv *ni_priv, void *d } usb_dev = interface_to_usbdev(ni_priv->bus_interface); out_pipe = usb_sndbulkpipe(usb_dev, ni_priv->bulk_out_endpoint); - sema_init(&context->complete, 0); + init_completion(&context->complete); context->timed_out = 0; usb_fill_bulk_urb(ni_priv->bulk_urb, usb_dev, out_pipe, data, data_length, &ni_usb_bulk_complete, context); @@ -143,7 +143,7 @@ static int ni_usb_nonblocking_send_bulk_msg(struct ni_usb_priv *ni_priv, void *d return retval; } mutex_unlock(&ni_priv->bulk_transfer_lock); - down(&context->complete); // wait for ni_usb_bulk_complete + wait_for_completion(&context->complete); // wait for ni_usb_bulk_complete if (context->timed_out) { usb_kill_urb(ni_priv->bulk_urb); dev_err(&usb_dev->dev, "%s: killed urb due to timeout\n", __func__); @@ -210,7 +210,7 @@ static int ni_usb_nonblocking_receive_bulk_msg(struct ni_usb_priv *ni_priv, } usb_dev = interface_to_usbdev(ni_priv->bus_interface); in_pipe = usb_rcvbulkpipe(usb_dev, ni_priv->bulk_in_endpoint); - sema_init(&context->complete, 0); + init_completion(&context->complete); context->timed_out = 0; usb_fill_bulk_urb(ni_priv->bulk_urb, usb_dev, in_pipe, data, data_length, &ni_usb_bulk_complete, context); @@ -231,7 +231,7 @@ static int ni_usb_nonblocking_receive_bulk_msg(struct ni_usb_priv *ni_priv, } mutex_unlock(&ni_priv->bulk_transfer_lock); if (interruptible) { - if (down_interruptible(&context->complete)) { + if (wait_for_completion_interruptible(&context->complete)) { /* If we got interrupted by a signal while * waiting for the usb gpib to respond, we * should send a stop command so it will @@ -243,10 +243,10 @@ static int ni_usb_nonblocking_receive_bulk_msg(struct ni_usb_priv *ni_priv, /* now do an uninterruptible wait, it shouldn't take long * for the board to respond now. */ - down(&context->complete); + wait_for_completion(&context->complete); } } else { - down(&context->complete); + wait_for_completion(&context->complete); } if (context->timed_out) { usb_kill_urb(ni_priv->bulk_urb); @@ -783,8 +783,10 @@ static int ni_usb_write(gpib_board_t *board, uint8_t *buffer, size_t length, } in_data = kmalloc(in_data_length, GFP_KERNEL); - if (!in_data) + if (!in_data) { + mutex_unlock(&ni_priv->addressed_transfer_lock); return -ENOMEM; + } retval = ni_usb_receive_bulk_msg(ni_priv, in_data, in_data_length, &usb_bytes_read, ni_usb_timeout_msecs(board->usec_timeout), 1); @@ -2351,33 +2353,33 @@ static void ni_usb_detach(gpib_board_t *board) mutex_unlock(&ni_usb_hotplug_lock); } -gpib_interface_t ni_usb_gpib_interface = { -name: "ni_usb_b", -attach : ni_usb_attach, -detach : ni_usb_detach, -read : ni_usb_read, -write : ni_usb_write, -command : ni_usb_command, -take_control : ni_usb_take_control, -go_to_standby : ni_usb_go_to_standby, -request_system_control : ni_usb_request_system_control, -interface_clear : ni_usb_interface_clear, -remote_enable : ni_usb_remote_enable, -enable_eos : ni_usb_enable_eos, -disable_eos : ni_usb_disable_eos, -parallel_poll : ni_usb_parallel_poll, -parallel_poll_configure : ni_usb_parallel_poll_configure, -parallel_poll_response : ni_usb_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : ni_usb_line_status, -update_status : ni_usb_update_status, -primary_address : ni_usb_primary_address, -secondary_address : ni_usb_secondary_address, -serial_poll_response : ni_usb_serial_poll_response, -serial_poll_status : ni_usb_serial_poll_status, -t1_delay : ni_usb_t1_delay, -return_to_local : ni_usb_return_to_local, -skip_check_for_command_acceptors : 1 +static gpib_interface_t ni_usb_gpib_interface = { + .name = "ni_usb_b", + .attach = ni_usb_attach, + .detach = ni_usb_detach, + .read = ni_usb_read, + .write = ni_usb_write, + .command = ni_usb_command, + .take_control = ni_usb_take_control, + .go_to_standby = ni_usb_go_to_standby, + .request_system_control = ni_usb_request_system_control, + .interface_clear = ni_usb_interface_clear, + .remote_enable = ni_usb_remote_enable, + .enable_eos = ni_usb_enable_eos, + .disable_eos = ni_usb_disable_eos, + .parallel_poll = ni_usb_parallel_poll, + .parallel_poll_configure = ni_usb_parallel_poll_configure, + .parallel_poll_response = ni_usb_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = ni_usb_line_status, + .update_status = ni_usb_update_status, + .primary_address = ni_usb_primary_address, + .secondary_address = ni_usb_secondary_address, + .serial_poll_response = ni_usb_serial_poll_response, + .serial_poll_status = ni_usb_serial_poll_status, + .t1_delay = ni_usb_t1_delay, + .return_to_local = ni_usb_return_to_local, + .skip_check_for_command_acceptors = 1 }; // Table with the USB-devices: just now only testing IDs @@ -2619,12 +2621,23 @@ static struct usb_driver ni_usb_bus_driver = { static int __init ni_usb_init_module(void) { int i; + int ret; pr_info("ni_usb_gpib driver loading\n"); for (i = 0; i < MAX_NUM_NI_USB_INTERFACES; i++) ni_usb_driver_interfaces[i] = NULL; - usb_register(&ni_usb_bus_driver); - gpib_register_driver(&ni_usb_gpib_interface, THIS_MODULE); + + ret = usb_register(&ni_usb_bus_driver); + if (ret) { + pr_err("ni_usb_gpib: usb_register failed: error = %d\n", ret); + return ret; + } + + ret = gpib_register_driver(&ni_usb_gpib_interface, THIS_MODULE); + if (ret) { + pr_err("ni_usb_gpib: gpib_register_driver failed: error = %d\n", ret); + return ret; + } return 0; } diff --git a/drivers/staging/gpib/ni_usb/ni_usb_gpib.h b/drivers/staging/gpib/ni_usb/ni_usb_gpib.h index 9b21dfa0f3f6..4b297db09a9b 100644 --- a/drivers/staging/gpib/ni_usb/ni_usb_gpib.h +++ b/drivers/staging/gpib/ni_usb/ni_usb_gpib.h @@ -56,7 +56,7 @@ enum hs_plus_endpoint_addresses { }; struct ni_usb_urb_ctx { - struct semaphore complete; + struct completion complete; unsigned timed_out : 1; }; diff --git a/drivers/staging/gpib/pc2/Makefile b/drivers/staging/gpib/pc2/Makefile index 8148425e0f87..481ee4296e1b 100644 --- a/drivers/staging/gpib/pc2/Makefile +++ b/drivers/staging/gpib/pc2/Makefile @@ -1,5 +1,5 @@ -obj-m += pc2_gpib.o +obj-$(CONFIG_GPIB_PC2) += pc2_gpib.o diff --git a/drivers/staging/gpib/pc2/pc2_gpib.c b/drivers/staging/gpib/pc2/pc2_gpib.c index 7b3b34f47341..c0b07cb63d9a 100644 --- a/drivers/staging/gpib/pc2/pc2_gpib.c +++ b/drivers/staging/gpib/pc2/pc2_gpib.c @@ -238,116 +238,116 @@ static void pc2_return_to_local(gpib_board_t *board) nec7210_return_to_local(board, &priv->nec7210_priv); } -gpib_interface_t pc2_interface = { -name: "pcII", -attach : pc2_attach, -detach : pc2_detach, -read : pc2_read, -write : pc2_write, -command : pc2_command, -take_control : pc2_take_control, -go_to_standby : pc2_go_to_standby, -request_system_control : pc2_request_system_control, -interface_clear : pc2_interface_clear, -remote_enable : pc2_remote_enable, -enable_eos : pc2_enable_eos, -disable_eos : pc2_disable_eos, -parallel_poll : pc2_parallel_poll, -parallel_poll_configure : pc2_parallel_poll_configure, -parallel_poll_response : pc2_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : NULL, -update_status : pc2_update_status, -primary_address : pc2_primary_address, -secondary_address : pc2_secondary_address, -serial_poll_response : pc2_serial_poll_response, -serial_poll_status : pc2_serial_poll_status, -t1_delay : pc2_t1_delay, -return_to_local : pc2_return_to_local, +static gpib_interface_t pc2_interface = { + .name = "pcII", + .attach = pc2_attach, + .detach = pc2_detach, + .read = pc2_read, + .write = pc2_write, + .command = pc2_command, + .take_control = pc2_take_control, + .go_to_standby = pc2_go_to_standby, + .request_system_control = pc2_request_system_control, + .interface_clear = pc2_interface_clear, + .remote_enable = pc2_remote_enable, + .enable_eos = pc2_enable_eos, + .disable_eos = pc2_disable_eos, + .parallel_poll = pc2_parallel_poll, + .parallel_poll_configure = pc2_parallel_poll_configure, + .parallel_poll_response = pc2_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = NULL, + .update_status = pc2_update_status, + .primary_address = pc2_primary_address, + .secondary_address = pc2_secondary_address, + .serial_poll_response = pc2_serial_poll_response, + .serial_poll_status = pc2_serial_poll_status, + .t1_delay = pc2_t1_delay, + .return_to_local = pc2_return_to_local, }; -gpib_interface_t pc2a_interface = { -name: "pcIIa", -attach : pc2a_attach, -detach : pc2a_detach, -read : pc2_read, -write : pc2_write, -command : pc2_command, -take_control : pc2_take_control, -go_to_standby : pc2_go_to_standby, -request_system_control : pc2_request_system_control, -interface_clear : pc2_interface_clear, -remote_enable : pc2_remote_enable, -enable_eos : pc2_enable_eos, -disable_eos : pc2_disable_eos, -parallel_poll : pc2_parallel_poll, -parallel_poll_configure : pc2_parallel_poll_configure, -parallel_poll_response : pc2_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : NULL, -update_status : pc2_update_status, -primary_address : pc2_primary_address, -secondary_address : pc2_secondary_address, -serial_poll_response : pc2_serial_poll_response, -serial_poll_status : pc2_serial_poll_status, -t1_delay : pc2_t1_delay, -return_to_local : pc2_return_to_local, +static gpib_interface_t pc2a_interface = { + .name = "pcIIa", + .attach = pc2a_attach, + .detach = pc2a_detach, + .read = pc2_read, + .write = pc2_write, + .command = pc2_command, + .take_control = pc2_take_control, + .go_to_standby = pc2_go_to_standby, + .request_system_control = pc2_request_system_control, + .interface_clear = pc2_interface_clear, + .remote_enable = pc2_remote_enable, + .enable_eos = pc2_enable_eos, + .disable_eos = pc2_disable_eos, + .parallel_poll = pc2_parallel_poll, + .parallel_poll_configure = pc2_parallel_poll_configure, + .parallel_poll_response = pc2_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = NULL, + .update_status = pc2_update_status, + .primary_address = pc2_primary_address, + .secondary_address = pc2_secondary_address, + .serial_poll_response = pc2_serial_poll_response, + .serial_poll_status = pc2_serial_poll_status, + .t1_delay = pc2_t1_delay, + .return_to_local = pc2_return_to_local, }; -gpib_interface_t pc2a_cb7210_interface = { -name: "pcIIa_cb7210", -attach : pc2a_cb7210_attach, -detach : pc2a_detach, -read : pc2_read, -write : pc2_write, -command : pc2_command, -take_control : pc2_take_control, -go_to_standby : pc2_go_to_standby, -request_system_control : pc2_request_system_control, -interface_clear : pc2_interface_clear, -remote_enable : pc2_remote_enable, -enable_eos : pc2_enable_eos, -disable_eos : pc2_disable_eos, -parallel_poll : pc2_parallel_poll, -parallel_poll_configure : pc2_parallel_poll_configure, -parallel_poll_response : pc2_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : NULL, //XXX -update_status : pc2_update_status, -primary_address : pc2_primary_address, -secondary_address : pc2_secondary_address, -serial_poll_response : pc2_serial_poll_response, -serial_poll_status : pc2_serial_poll_status, -t1_delay : pc2_t1_delay, -return_to_local : pc2_return_to_local, +static gpib_interface_t pc2a_cb7210_interface = { + .name = "pcIIa_cb7210", + .attach = pc2a_cb7210_attach, + .detach = pc2a_detach, + .read = pc2_read, + .write = pc2_write, + .command = pc2_command, + .take_control = pc2_take_control, + .go_to_standby = pc2_go_to_standby, + .request_system_control = pc2_request_system_control, + .interface_clear = pc2_interface_clear, + .remote_enable = pc2_remote_enable, + .enable_eos = pc2_enable_eos, + .disable_eos = pc2_disable_eos, + .parallel_poll = pc2_parallel_poll, + .parallel_poll_configure = pc2_parallel_poll_configure, + .parallel_poll_response = pc2_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = NULL, //XXX + .update_status = pc2_update_status, + .primary_address = pc2_primary_address, + .secondary_address = pc2_secondary_address, + .serial_poll_response = pc2_serial_poll_response, + .serial_poll_status = pc2_serial_poll_status, + .t1_delay = pc2_t1_delay, + .return_to_local = pc2_return_to_local, }; -gpib_interface_t pc2_2a_interface = { -name: "pcII_IIa", -attach : pc2_2a_attach, -detach : pc2_2a_detach, -read : pc2_read, -write : pc2_write, -command : pc2_command, -take_control : pc2_take_control, -go_to_standby : pc2_go_to_standby, -request_system_control : pc2_request_system_control, -interface_clear : pc2_interface_clear, -remote_enable : pc2_remote_enable, -enable_eos : pc2_enable_eos, -disable_eos : pc2_disable_eos, -parallel_poll : pc2_parallel_poll, -parallel_poll_configure : pc2_parallel_poll_configure, -parallel_poll_response : pc2_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : NULL, -update_status : pc2_update_status, -primary_address : pc2_primary_address, -secondary_address : pc2_secondary_address, -serial_poll_response : pc2_serial_poll_response, -serial_poll_status : pc2_serial_poll_status, -t1_delay : pc2_t1_delay, -return_to_local : pc2_return_to_local, +static gpib_interface_t pc2_2a_interface = { + .name = "pcII_IIa", + .attach = pc2_2a_attach, + .detach = pc2_2a_detach, + .read = pc2_read, + .write = pc2_write, + .command = pc2_command, + .take_control = pc2_take_control, + .go_to_standby = pc2_go_to_standby, + .request_system_control = pc2_request_system_control, + .interface_clear = pc2_interface_clear, + .remote_enable = pc2_remote_enable, + .enable_eos = pc2_enable_eos, + .disable_eos = pc2_disable_eos, + .parallel_poll = pc2_parallel_poll, + .parallel_poll_configure = pc2_parallel_poll_configure, + .parallel_poll_response = pc2_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = NULL, + .update_status = pc2_update_status, + .primary_address = pc2_primary_address, + .secondary_address = pc2_secondary_address, + .serial_poll_response = pc2_serial_poll_response, + .serial_poll_status = pc2_serial_poll_status, + .t1_delay = pc2_t1_delay, + .return_to_local = pc2_return_to_local, }; static int allocate_private(gpib_board_t *board) @@ -426,7 +426,7 @@ int pc2_attach(gpib_board_t *board, const gpib_board_config_t *config) nec_priv = &pc2_priv->nec7210_priv; nec_priv->offset = pc2_reg_offset; - if (request_region((unsigned long)config->ibbase, pc2_iosize, "pc2") == 0) { + if (!request_region(config->ibbase, pc2_iosize, "pc2")) { pr_err("gpib: ioports are already in use\n"); return -1; } @@ -471,7 +471,7 @@ void pc2_detach(gpib_board_t *board) free_irq(pc2_priv->irq, board); if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); - release_region((unsigned long)(nec_priv->iobase), pc2_iosize); + release_region(nec_priv->iobase, pc2_iosize); } if (nec_priv->dma_buffer) { dma_free_coherent(board->dev, nec_priv->dma_buffer_length, @@ -498,14 +498,14 @@ static int pc2a_common_attach(gpib_board_t *board, const gpib_board_config_t *co nec_priv = &pc2_priv->nec7210_priv; nec_priv->offset = pc2a_reg_offset; - switch ((unsigned long)(config->ibbase)) { + switch (config->ibbase) { case 0x02e1: case 0x22e1: case 0x42e1: case 0x62e1: break; default: - pr_err("PCIIa base range invalid, must be one of 0x[0246]2e1, but is 0x%p\n", + pr_err("PCIIa base range invalid, must be one of 0x[0246]2e1, but is 0x%d\n", config->ibbase); return -1; } @@ -522,7 +522,7 @@ static int pc2a_common_attach(gpib_board_t *board, const gpib_board_config_t *co unsigned int err = 0; for (i = 0; i < num_registers; i++) { - if (check_region((unsigned long)config->ibbase + i * pc2a_reg_offset, 1)) + if (check_region(config->ibbase + i * pc2a_reg_offset, 1)) err++; } if (config->ibirq && check_region(pc2a_clear_intr_iobase + config->ibirq, 1)) @@ -533,11 +533,11 @@ static int pc2a_common_attach(gpib_board_t *board, const gpib_board_config_t *co } #endif for (i = 0; i < num_registers; i++) { - if (!request_region((unsigned long)config->ibbase + + if (!request_region(config->ibbase + i * pc2a_reg_offset, 1, "pc2a")) { pr_err("gpib: ioports are already in use"); for (j = 0; j < i; j++) - release_region((unsigned long)(config->ibbase) + + release_region(config->ibbase + j * pc2a_reg_offset, 1); return -1; } @@ -608,7 +608,7 @@ static void pc2a_common_detach(gpib_board_t *board, unsigned int num_registers) if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); for (i = 0; i < num_registers; i++) - release_region((unsigned long)nec_priv->iobase + + release_region(nec_priv->iobase + i * pc2a_reg_offset, 1); } if (pc2_priv->clear_intr_addr) @@ -635,12 +635,42 @@ void pc2_2a_detach(gpib_board_t *board) static int __init pc2_init_module(void) { - gpib_register_driver(&pc2_interface, THIS_MODULE); - gpib_register_driver(&pc2a_interface, THIS_MODULE); - gpib_register_driver(&pc2a_cb7210_interface, THIS_MODULE); - gpib_register_driver(&pc2_2a_interface, THIS_MODULE); + int ret; + + ret = gpib_register_driver(&pc2_interface, THIS_MODULE); + if (ret) { + pr_err("pc2_gpib: gpib_register_driver failed: error = %d\n", ret); + return ret; + } + + ret = gpib_register_driver(&pc2a_interface, THIS_MODULE); + if (ret) { + pr_err("pc2_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_pc2a; + } + + ret = gpib_register_driver(&pc2a_cb7210_interface, THIS_MODULE); + if (ret) { + pr_err("pc2_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_cb7210; + } + + ret = gpib_register_driver(&pc2_2a_interface, THIS_MODULE); + if (ret) { + pr_err("pc2_gpib: gpib_register_driver failed: error = %d\n", ret); + goto err_pc2_2a; + } return 0; + +err_pc2_2a: + gpib_unregister_driver(&pc2a_cb7210_interface); +err_cb7210: + gpib_unregister_driver(&pc2a_interface); +err_pc2a: + gpib_unregister_driver(&pc2_interface); + + return ret; } static void __exit pc2_exit_module(void) diff --git a/drivers/staging/gpib/tms9914/Makefile b/drivers/staging/gpib/tms9914/Makefile index 81b7e3cf104c..4705ab07f413 100644 --- a/drivers/staging/gpib/tms9914/Makefile +++ b/drivers/staging/gpib/tms9914/Makefile @@ -1,5 +1,5 @@ -obj-m += tms9914.o +obj-$(CONFIG_GPIB_TMS9914) += tms9914.o diff --git a/drivers/staging/gpib/tms9914/tms9914.c b/drivers/staging/gpib/tms9914/tms9914.c index 152b243b845b..ec8e1d4d762f 100644 --- a/drivers/staging/gpib/tms9914/tms9914.c +++ b/drivers/staging/gpib/tms9914/tms9914.c @@ -866,14 +866,14 @@ EXPORT_SYMBOL_GPL(tms9914_online); // wrapper for inb uint8_t tms9914_ioport_read_byte(struct tms9914_priv *priv, unsigned int register_num) { - return inb((unsigned long)(priv->iobase) + register_num * priv->offset); + return inb(priv->iobase + register_num * priv->offset); } EXPORT_SYMBOL_GPL(tms9914_ioport_read_byte); // wrapper for outb void tms9914_ioport_write_byte(struct tms9914_priv *priv, uint8_t data, unsigned int register_num) { - outb(data, (unsigned long)(priv->iobase) + register_num * priv->offset); + outb(data, priv->iobase + register_num * priv->offset); if (register_num == AUXCR) udelay(1); } @@ -883,14 +883,14 @@ EXPORT_SYMBOL_GPL(tms9914_ioport_write_byte); // wrapper for readb uint8_t tms9914_iomem_read_byte(struct tms9914_priv *priv, unsigned int register_num) { - return readb(priv->iobase + register_num * priv->offset); + return readb(priv->mmiobase + register_num * priv->offset); } EXPORT_SYMBOL_GPL(tms9914_iomem_read_byte); // wrapper for writeb void tms9914_iomem_write_byte(struct tms9914_priv *priv, uint8_t data, unsigned int register_num) { - writeb(data, priv->iobase + register_num * priv->offset); + writeb(data, priv->mmiobase + register_num * priv->offset); if (register_num == AUXCR) udelay(1); } diff --git a/drivers/staging/gpib/tnt4882/Makefile b/drivers/staging/gpib/tnt4882/Makefile index f767c990db7a..a3c3fb96d5ed 100644 --- a/drivers/staging/gpib/tnt4882/Makefile +++ b/drivers/staging/gpib/tnt4882/Makefile @@ -1,5 +1,5 @@ ccflags-$(CONFIG_GPIB_PCMCIA) := -DGPIB_PCMCIA -obj-m += tnt4882.o +obj-$(CONFIG_GPIB_NI_PCI_ISA) += tnt4882.o tnt4882-objs := tnt4882_gpib.o mite.o diff --git a/drivers/staging/gpib/tnt4882/mite.c b/drivers/staging/gpib/tnt4882/mite.c index 0edf34d243e9..ea64dde46bcb 100644 --- a/drivers/staging/gpib/tnt4882/mite.c +++ b/drivers/staging/gpib/tnt4882/mite.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2 +// SPDX-License-Identifier: GPL-2.0-only /* * Hardware driver for NI Mite PCI interface chip, @@ -148,72 +148,3 @@ void mite_list_devices(void) } pr_info("\n"); } - -int mite_bytes_transferred(struct mite_struct *mite, int chan) -{ - int dar, fcr; - - dar = readl(mite->mite_io_addr + MITE_DAR + CHAN_OFFSET(chan)); - fcr = readl(mite->mite_io_addr + MITE_FCR + CHAN_OFFSET(chan)) & 0x000000FF; - return dar - fcr; -} - -int mite_dma_tcr(struct mite_struct *mite) -{ - int tcr; - int lkar; - - lkar = readl(mite->mite_io_addr + CHAN_OFFSET(0) + MITE_LKAR); - tcr = readl(mite->mite_io_addr + CHAN_OFFSET(0) + MITE_TCR); - MDPRINTK("lkar=0x%08x tcr=%d\n", lkar, tcr); - - return tcr; -} - -void mite_dma_disarm(struct mite_struct *mite) -{ - int chor; - - /* disarm */ - chor = CHOR_ABORT; - writel(chor, mite->mite_io_addr + CHAN_OFFSET(0) + MITE_CHOR); -} - -void mite_dump_regs(struct mite_struct *mite) -{ - void *addr = 0; - unsigned long temp = 0; - - pr_info("mite address is =0x%p\n", mite->mite_io_addr); - - addr = mite->mite_io_addr + MITE_CHOR + CHAN_OFFSET(0); - pr_info("mite status[CHOR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CHOR_strings,temp); - addr = mite->mite_io_addr + MITE_CHCR + CHAN_OFFSET(0); - pr_info("mite status[CHCR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CHCR_strings,temp); - addr = mite->mite_io_addr + MITE_TCR + CHAN_OFFSET(0); - pr_info("mite status[TCR] at 0x%p =0x%08x\n", addr, readl(addr)); - addr = mite->mite_io_addr + MITE_MCR + CHAN_OFFSET(0); - pr_info("mite status[MCR] at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_MCR_strings,temp); - addr = mite->mite_io_addr + MITE_MAR + CHAN_OFFSET(0); - pr_info("mite status[MAR] at 0x%p =0x%08x\n", addr, readl(addr)); - addr = mite->mite_io_addr + MITE_DCR + CHAN_OFFSET(0); - pr_info("mite status[DCR] at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CR_strings,temp); - addr = mite->mite_io_addr + MITE_DAR + CHAN_OFFSET(0); - pr_info("mite status[DAR] at 0x%p =0x%08x\n", addr, readl(addr)); - addr = mite->mite_io_addr + MITE_LKCR + CHAN_OFFSET(0); - pr_info("mite status[LKCR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CR_strings,temp); - addr = mite->mite_io_addr + MITE_LKAR + CHAN_OFFSET(0); - pr_info("mite status[LKAR]at 0x%p =0x%08x\n", addr, readl(addr)); - - addr = mite->mite_io_addr + MITE_CHSR + CHAN_OFFSET(0); - pr_info("mite status[CHSR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CHSR_strings,temp); - addr = mite->mite_io_addr + MITE_FCR + CHAN_OFFSET(0); - pr_info("mite status[FCR] at 0x%p =0x%08x\n\n", addr, readl(addr)); -} - diff --git a/drivers/staging/gpib/tnt4882/mite.h b/drivers/staging/gpib/tnt4882/mite.h index 6454d069b8cc..522d6b56cb7d 100644 --- a/drivers/staging/gpib/tnt4882/mite.h +++ b/drivers/staging/gpib/tnt4882/mite.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2 */ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Hardware driver for NI Mite PCI interface chip @@ -34,9 +34,9 @@ struct mite_struct { struct pci_dev *pcidev; unsigned long mite_phys_addr; - void *mite_io_addr; + void __iomem *mite_io_addr; unsigned long daq_phys_addr; - void *daq_io_addr; + void __iomem *daq_io_addr; int DMA_CheckNearEnd; @@ -61,15 +61,6 @@ int mite_setup(struct mite_struct *mite); void mite_unsetup(struct mite_struct *mite); void mite_list_devices(void); -int mite_dma_tcr(struct mite_struct *mite); - -void mite_dma_arm(struct mite_struct *mite); -void mite_dma_disarm(struct mite_struct *mite); - -void mite_dump_regs(struct mite_struct *mite); -void mite_setregs(struct mite_struct *mite, unsigned long ll_start, int chan, int dir); -int mite_bytes_transferred(struct mite_struct *mite, int chan); - #define CHAN_OFFSET(x) (0x100 * (x)) /* DMA base for chan 0 is 0x500, chan 1 is 0x600 */ diff --git a/drivers/staging/gpib/tnt4882/tnt4882_gpib.c b/drivers/staging/gpib/tnt4882/tnt4882_gpib.c index e49a952fa0d8..b39ab2abe495 100644 --- a/drivers/staging/gpib/tnt4882/tnt4882_gpib.c +++ b/drivers/staging/gpib/tnt4882/tnt4882_gpib.c @@ -45,10 +45,6 @@ struct tnt4882_priv { unsigned short imr0_bits; unsigned short imr3_bits; unsigned short auxg_bits; // bits written to auxiliary register G - void (*io_writeb)(unsigned int value, void *address); - void (*io_writew)(unsigned int value, void *address); - unsigned int (*io_readb)(void *address); - unsigned int (*io_readw)(void *address); }; // interface functions @@ -104,23 +100,23 @@ static const int atgpib_iosize = 32; /* paged io */ static inline unsigned int tnt_paged_readb(struct tnt4882_priv *priv, unsigned long offset) { - priv->io_writeb(AUX_PAGEIN, priv->nec7210_priv.iobase + AUXMR * priv->nec7210_priv.offset); + iowrite8(AUX_PAGEIN, priv->nec7210_priv.mmiobase + AUXMR * priv->nec7210_priv.offset); udelay(1); - return priv->io_readb(priv->nec7210_priv.iobase + offset); + return ioread8(priv->nec7210_priv.mmiobase + offset); } static inline void tnt_paged_writeb(struct tnt4882_priv *priv, unsigned int value, unsigned long offset) { - priv->io_writeb(AUX_PAGEIN, priv->nec7210_priv.iobase + AUXMR * priv->nec7210_priv.offset); + iowrite8(AUX_PAGEIN, priv->nec7210_priv.mmiobase + AUXMR * priv->nec7210_priv.offset); udelay(1); - priv->io_writeb(value, priv->nec7210_priv.iobase + offset); + iowrite8(value, priv->nec7210_priv.mmiobase + offset); } /* readb/writeb wrappers */ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long offset) { - void *address = priv->nec7210_priv.iobase + offset; + void __iomem *address = priv->nec7210_priv.mmiobase + offset; unsigned long flags; unsigned short retval; spinlock_t *register_lock = &priv->nec7210_priv.register_page_lock; @@ -134,7 +130,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long switch (priv->nec7210_priv.type) { case TNT4882: case TNT5004: - retval = priv->io_readb(address); + retval = ioread8(address); break; case NAT4882: retval = tnt_paged_readb(priv, offset - tnt_pagein_offset); @@ -149,7 +145,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long } break; default: - retval = priv->io_readb(address); + retval = ioread8(address); break; } spin_unlock_irqrestore(register_lock, flags); @@ -158,7 +154,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, unsigned long offset) { - void *address = priv->nec7210_priv.iobase + offset; + void __iomem *address = priv->nec7210_priv.mmiobase + offset; unsigned long flags; spinlock_t *register_lock = &priv->nec7210_priv.register_page_lock; @@ -170,7 +166,7 @@ static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, u switch (priv->nec7210_priv.type) { case TNT4882: case TNT5004: - priv->io_writeb(value, address); + iowrite8(value, address); break; case NAT4882: tnt_paged_writeb(priv, value, offset - tnt_pagein_offset); @@ -183,7 +179,7 @@ static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, u } break; default: - priv->io_writeb(value, address); + iowrite8(value, address); break; } spin_unlock_irqrestore(register_lock, flags); @@ -288,7 +284,7 @@ static int drain_fifo_words(struct tnt4882_priv *tnt_priv, uint8_t *buffer, int while (fifo_word_available(tnt_priv) && count + 2 <= num_bytes) { short word; - word = tnt_priv->io_readw(nec_priv->iobase + FIFOB); + word = ioread16(nec_priv->mmiobase + FIFOB); buffer[count++] = word & 0xff; buffer[count++] = (word >> 8) & 0xff; } @@ -573,7 +569,7 @@ static int generic_write(gpib_board_t *board, uint8_t *buffer, size_t length, word = buffer[count++] & 0xff; if (count < length) word |= (buffer[count++] << 8) & 0xff00; - tnt_priv->io_writew(word, nec_priv->iobase + FIFOB); + iowrite16(word, nec_priv->mmiobase + FIFOB); } // avoid unnecessary HR_NFF interrupts // tnt_priv->imr3_bits |= HR_NFF; @@ -894,285 +890,285 @@ void tnt4882_return_to_local(gpib_board_t *board) nec7210_return_to_local(board, &priv->nec7210_priv); } -gpib_interface_t ni_pci_interface = { -name: "ni_pci", -attach : ni_pci_attach, -detach : ni_pci_detach, -read : tnt4882_accel_read, -write : tnt4882_accel_write, -command : tnt4882_command, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : tnt4882_line_status, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response2 : tnt4882_serial_poll_response2, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_pci_interface = { + .name = "ni_pci", + .attach = ni_pci_attach, + .detach = ni_pci_detach, + .read = tnt4882_accel_read, + .write = tnt4882_accel_write, + .command = tnt4882_command, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = tnt4882_line_status, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response2 = tnt4882_serial_poll_response2, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; -gpib_interface_t ni_pci_accel_interface = { -name: "ni_pci_accel", -attach : ni_pci_attach, -detach : ni_pci_detach, -read : tnt4882_accel_read, -write : tnt4882_accel_write, -command : tnt4882_command, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : tnt4882_line_status, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response2 : tnt4882_serial_poll_response2, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_pci_accel_interface = { + .name = "ni_pci_accel", + .attach = ni_pci_attach, + .detach = ni_pci_detach, + .read = tnt4882_accel_read, + .write = tnt4882_accel_write, + .command = tnt4882_command, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = tnt4882_line_status, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response2 = tnt4882_serial_poll_response2, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; -gpib_interface_t ni_isa_interface = { -name: "ni_isa", -attach : ni_tnt_isa_attach, -detach : ni_isa_detach, -read : tnt4882_accel_read, -write : tnt4882_accel_write, -command : tnt4882_command, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : tnt4882_line_status, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response2 : tnt4882_serial_poll_response2, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_isa_interface = { + .name = "ni_isa", + .attach = ni_tnt_isa_attach, + .detach = ni_isa_detach, + .read = tnt4882_accel_read, + .write = tnt4882_accel_write, + .command = tnt4882_command, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = tnt4882_line_status, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response2 = tnt4882_serial_poll_response2, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; -gpib_interface_t ni_nat4882_isa_interface = { -name: "ni_nat4882_isa", -attach : ni_nat4882_isa_attach, -detach : ni_isa_detach, -read : tnt4882_read, -write : tnt4882_write, -command : tnt4882_command_unaccel, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : tnt4882_line_status, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response2 : tnt4882_serial_poll_response2, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_nat4882_isa_interface = { + .name = "ni_nat4882_isa", + .attach = ni_nat4882_isa_attach, + .detach = ni_isa_detach, + .read = tnt4882_read, + .write = tnt4882_write, + .command = tnt4882_command_unaccel, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = tnt4882_line_status, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response2 = tnt4882_serial_poll_response2, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; -gpib_interface_t ni_nec_isa_interface = { -name: "ni_nec_isa", -attach : ni_nec_isa_attach, -detach : ni_isa_detach, -read : tnt4882_read, -write : tnt4882_write, -command : tnt4882_command_unaccel, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : NULL, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response : tnt4882_serial_poll_response, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_nec_isa_interface = { + .name = "ni_nec_isa", + .attach = ni_nec_isa_attach, + .detach = ni_isa_detach, + .read = tnt4882_read, + .write = tnt4882_write, + .command = tnt4882_command_unaccel, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = NULL, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response = tnt4882_serial_poll_response, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; -gpib_interface_t ni_isa_accel_interface = { -name: "ni_isa_accel", -attach : ni_tnt_isa_attach, -detach : ni_isa_detach, -read : tnt4882_accel_read, -write : tnt4882_accel_write, -command : tnt4882_command, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : tnt4882_line_status, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response2 : tnt4882_serial_poll_response2, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_isa_accel_interface = { + .name = "ni_isa_accel", + .attach = ni_tnt_isa_attach, + .detach = ni_isa_detach, + .read = tnt4882_accel_read, + .write = tnt4882_accel_write, + .command = tnt4882_command, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = tnt4882_line_status, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response2 = tnt4882_serial_poll_response2, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; -gpib_interface_t ni_nat4882_isa_accel_interface = { -name: "ni_nat4882_isa_accel", -attach : ni_nat4882_isa_attach, -detach : ni_isa_detach, -read : tnt4882_accel_read, -write : tnt4882_accel_write, -command : tnt4882_command_unaccel, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : tnt4882_line_status, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response2 : tnt4882_serial_poll_response2, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_nat4882_isa_accel_interface = { + .name = "ni_nat4882_isa_accel", + .attach = ni_nat4882_isa_attach, + .detach = ni_isa_detach, + .read = tnt4882_accel_read, + .write = tnt4882_accel_write, + .command = tnt4882_command_unaccel, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = tnt4882_line_status, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response2 = tnt4882_serial_poll_response2, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; -gpib_interface_t ni_nec_isa_accel_interface = { -name: "ni_nec_isa_accel", -attach : ni_nec_isa_attach, -detach : ni_isa_detach, -read : tnt4882_accel_read, -write : tnt4882_accel_write, -command : tnt4882_command_unaccel, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : NULL, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response : tnt4882_serial_poll_response, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_nec_isa_accel_interface = { + .name = "ni_nec_isa_accel", + .attach = ni_nec_isa_attach, + .detach = ni_isa_detach, + .read = tnt4882_accel_read, + .write = tnt4882_accel_write, + .command = tnt4882_command_unaccel, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = NULL, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response = tnt4882_serial_poll_response, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; #ifdef GPIB_PCMCIA -gpib_interface_t ni_pcmcia_interface = { -name: "ni_pcmcia", -attach : ni_pcmcia_attach, -detach : ni_pcmcia_detach, -read : tnt4882_accel_read, -write : tnt4882_accel_write, -command : tnt4882_command, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : tnt4882_line_status, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response : tnt4882_serial_poll_response, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_pcmcia_interface = { + .name = "ni_pcmcia", + .attach = ni_pcmcia_attach, + .detach = ni_pcmcia_detach, + .read = tnt4882_accel_read, + .write = tnt4882_accel_write, + .command = tnt4882_command, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = tnt4882_line_status, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response = tnt4882_serial_poll_response, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; -gpib_interface_t ni_pcmcia_accel_interface = { -name: "ni_pcmcia_accel", -attach : ni_pcmcia_attach, -detach : ni_pcmcia_detach, -read : tnt4882_accel_read, -write : tnt4882_accel_write, -command : tnt4882_command, -take_control : tnt4882_take_control, -go_to_standby : tnt4882_go_to_standby, -request_system_control : tnt4882_request_system_control, -interface_clear : tnt4882_interface_clear, -remote_enable : tnt4882_remote_enable, -enable_eos : tnt4882_enable_eos, -disable_eos : tnt4882_disable_eos, -parallel_poll : tnt4882_parallel_poll, -parallel_poll_configure : tnt4882_parallel_poll_configure, -parallel_poll_response : tnt4882_parallel_poll_response, -local_parallel_poll_mode : NULL, // XXX -line_status : tnt4882_line_status, -update_status : tnt4882_update_status, -primary_address : tnt4882_primary_address, -secondary_address : tnt4882_secondary_address, -serial_poll_response : tnt4882_serial_poll_response, -serial_poll_status : tnt4882_serial_poll_status, -t1_delay : tnt4882_t1_delay, -return_to_local : tnt4882_return_to_local, +static gpib_interface_t ni_pcmcia_accel_interface = { + .name = "ni_pcmcia_accel", + .attach = ni_pcmcia_attach, + .detach = ni_pcmcia_detach, + .read = tnt4882_accel_read, + .write = tnt4882_accel_write, + .command = tnt4882_command, + .take_control = tnt4882_take_control, + .go_to_standby = tnt4882_go_to_standby, + .request_system_control = tnt4882_request_system_control, + .interface_clear = tnt4882_interface_clear, + .remote_enable = tnt4882_remote_enable, + .enable_eos = tnt4882_enable_eos, + .disable_eos = tnt4882_disable_eos, + .parallel_poll = tnt4882_parallel_poll, + .parallel_poll_configure = tnt4882_parallel_poll_configure, + .parallel_poll_response = tnt4882_parallel_poll_response, + .local_parallel_poll_mode = NULL, // XXX + .line_status = tnt4882_line_status, + .update_status = tnt4882_update_status, + .primary_address = tnt4882_primary_address, + .secondary_address = tnt4882_secondary_address, + .serial_poll_response = tnt4882_serial_poll_response, + .serial_poll_status = tnt4882_serial_poll_status, + .t1_delay = tnt4882_t1_delay, + .return_to_local = tnt4882_return_to_local, }; #endif @@ -1269,10 +1265,6 @@ int ni_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) if (tnt4882_allocate_private(board)) return -ENOMEM; tnt_priv = board->private_data; - tnt_priv->io_writeb = writeb_wrapper; - tnt_priv->io_readb = readb_wrapper; - tnt_priv->io_writew = writew_wrapper; - tnt_priv->io_readw = readw_wrapper; nec_priv = &tnt_priv->nec7210_priv; nec_priv->type = TNT4882; nec_priv->read_byte = nec7210_locking_iomem_read_byte; @@ -1324,7 +1316,7 @@ int ni_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) return retval; } - nec_priv->iobase = tnt_priv->mite->daq_io_addr; + nec_priv->mmiobase = tnt_priv->mite->daq_io_addr; // get irq if (request_irq(mite_irq(tnt_priv->mite), tnt4882_interrupt, isr_flags, @@ -1359,7 +1351,7 @@ void ni_pci_detach(gpib_board_t *board) if (tnt_priv) { nec_priv = &tnt_priv->nec7210_priv; - if (nec_priv->iobase) + if (nec_priv->mmiobase) tnt4882_board_reset(tnt_priv, board); if (tnt_priv->irq) free_irq(tnt_priv->irq, board); @@ -1400,7 +1392,7 @@ static int ni_isa_attach_common(gpib_board_t *board, const gpib_board_config_t * struct tnt4882_priv *tnt_priv; struct nec7210_priv *nec_priv; int isr_flags = 0; - void *iobase; + u32 iobase; int irq; board->status = 0; @@ -1408,10 +1400,6 @@ static int ni_isa_attach_common(gpib_board_t *board, const gpib_board_config_t * if (tnt4882_allocate_private(board)) return -ENOMEM; tnt_priv = board->private_data; - tnt_priv->io_writeb = outb_wrapper; - tnt_priv->io_readb = inb_wrapper; - tnt_priv->io_writew = outw_wrapper; - tnt_priv->io_readw = inw_wrapper; nec_priv = &tnt_priv->nec7210_priv; nec_priv->type = chipset; nec_priv->read_byte = nec7210_locking_ioport_read_byte; @@ -1427,18 +1415,20 @@ static int ni_isa_attach_common(gpib_board_t *board, const gpib_board_config_t * if (retval < 0) return retval; tnt_priv->pnp_dev = dev; - iobase = (void *)(pnp_port_start(dev, 0)); + iobase = pnp_port_start(dev, 0); irq = pnp_irq(dev, 0); } else { iobase = config->ibbase; irq = config->ibirq; } // allocate ioports - if (!request_region((unsigned long)(iobase), atgpib_iosize, "atgpib")) { + if (!request_region(iobase, atgpib_iosize, "atgpib")) { pr_err("tnt4882: failed to allocate ioports\n"); return -1; } - nec_priv->iobase = iobase; + nec_priv->mmiobase = ioport_map(iobase, atgpib_iosize); + if (!nec_priv->mmiobase) + return -1; // get irq if (request_irq(irq, tnt4882_interrupt, isr_flags, "atgpib", board)) { @@ -1478,8 +1468,10 @@ void ni_isa_detach(gpib_board_t *board) tnt4882_board_reset(tnt_priv, board); if (tnt_priv->irq) free_irq(tnt_priv->irq, board); + if (nec_priv->mmiobase) + ioport_unmap(nec_priv->mmiobase); if (nec_priv->iobase) - release_region((unsigned long)(nec_priv->iobase), atgpib_iosize); + release_region(nec_priv->iobase, atgpib_iosize); if (tnt_priv->pnp_dev) pnp_device_detach(tnt_priv->pnp_dev); } @@ -1524,29 +1516,109 @@ static int __init tnt4882_init_module(void) result = pci_register_driver(&tnt4882_pci_driver); if (result) { - pr_err("tnt4882: pci_driver_register failed!\n"); + pr_err("tnt4882_gpib: pci_register_driver failed: error = %d\n", result); return result; } - gpib_register_driver(&ni_isa_interface, THIS_MODULE); - gpib_register_driver(&ni_isa_accel_interface, THIS_MODULE); - gpib_register_driver(&ni_nat4882_isa_interface, THIS_MODULE); - gpib_register_driver(&ni_nat4882_isa_accel_interface, THIS_MODULE); - gpib_register_driver(&ni_nec_isa_interface, THIS_MODULE); - gpib_register_driver(&ni_nec_isa_accel_interface, THIS_MODULE); - gpib_register_driver(&ni_pci_interface, THIS_MODULE); - gpib_register_driver(&ni_pci_accel_interface, THIS_MODULE); + result = gpib_register_driver(&ni_isa_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_isa; + } + + result = gpib_register_driver(&ni_isa_accel_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_isa_accel; + } + + result = gpib_register_driver(&ni_nat4882_isa_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_nat4882_isa; + } + + result = gpib_register_driver(&ni_nat4882_isa_accel_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_nat4882_isa_accel; + } + + result = gpib_register_driver(&ni_nec_isa_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_nec_isa; + } + + result = gpib_register_driver(&ni_nec_isa_accel_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_nec_isa_accel; + } + + result = gpib_register_driver(&ni_pci_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_pci; + } + + result = gpib_register_driver(&ni_pci_accel_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_pci_accel; + } + #ifdef GPIB_PCMCIA - gpib_register_driver(&ni_pcmcia_interface, THIS_MODULE); - gpib_register_driver(&ni_pcmcia_accel_interface, THIS_MODULE); - if (init_ni_gpib_cs() < 0) - return -1; + result = gpib_register_driver(&ni_pcmcia_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_pcmcia; + } + + result = gpib_register_driver(&ni_pcmcia_accel_interface, THIS_MODULE); + if (result) { + pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result); + goto err_pcmcia_accel; + } + + result = init_ni_gpib_cs(); + if (result) { + pr_err("tnt4882_gpib: pcmcia_register_driver failed: error = %d\n", result); + goto err_pcmcia_driver; + } #endif mite_init(); mite_list_devices(); return 0; + +#ifdef GPIB_PCMCIA +err_pcmcia_driver: + gpib_unregister_driver(&ni_pcmcia_accel_interface); +err_pcmcia_accel: + gpib_unregister_driver(&ni_pcmcia_interface); +err_pcmcia: +#endif + gpib_unregister_driver(&ni_pci_accel_interface); +err_pci_accel: + gpib_unregister_driver(&ni_pci_interface); +err_pci: + gpib_unregister_driver(&ni_nec_isa_accel_interface); +err_nec_isa_accel: + gpib_unregister_driver(&ni_nec_isa_interface); +err_nec_isa: + gpib_unregister_driver(&ni_nat4882_isa_accel_interface); +err_nat4882_isa_accel: + gpib_unregister_driver(&ni_nat4882_isa_interface); +err_nat4882_isa: + gpib_unregister_driver(&ni_isa_accel_interface); +err_isa_accel: + gpib_unregister_driver(&ni_isa_interface); +err_isa: + pci_unregister_driver(&tnt4882_pci_driver); + + return result; } static void __exit tnt4882_exit_module(void) @@ -1817,10 +1889,6 @@ int ni_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) if (tnt4882_allocate_private(board)) return -ENOMEM; tnt_priv = board->private_data; - tnt_priv->io_writeb = outb_wrapper; - tnt_priv->io_readb = inb_wrapper; - tnt_priv->io_writew = outw_wrapper; - tnt_priv->io_readw = inw_wrapper; nec_priv = &tnt_priv->nec7210_priv; nec_priv->type = TNT4882; nec_priv->read_byte = nec7210_locking_ioport_read_byte; @@ -1828,14 +1896,17 @@ int ni_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) nec_priv->offset = atgpib_reg_offset; DEBUG(0, "ioport1 window attributes: 0x%lx\n", curr_dev->resource[0]->flags); - if (request_region(curr_dev->resource[0]->start, resource_size(curr_dev->resource[0]), - "tnt4882") == 0) { + if (!request_region(curr_dev->resource[0]->start, resource_size(curr_dev->resource[0]), + "tnt4882")) { pr_err("gpib: ioports starting at 0x%lx are already in use\n", (unsigned long)curr_dev->resource[0]->start); return -EIO; } - nec_priv->iobase = (void *)(unsigned long)curr_dev->resource[0]->start; + nec_priv->mmiobase = ioport_map(curr_dev->resource[0]->start, + resource_size(curr_dev->resource[0])); + if (!nec_priv->mmiobase) + return -1; // get irq if (request_irq(curr_dev->irq, tnt4882_interrupt, isr_flags, "tnt4882", board)) { @@ -1860,9 +1931,11 @@ void ni_pcmcia_detach(gpib_board_t *board) nec_priv = &tnt_priv->nec7210_priv; if (tnt_priv->irq) free_irq(tnt_priv->irq, board); + if (nec_priv->mmiobase) + ioport_unmap(nec_priv->mmiobase); if (nec_priv->iobase) { tnt4882_board_reset(tnt_priv, board); - release_region((unsigned long)nec_priv->iobase, pcmcia_gpib_iosize); + release_region(nec_priv->iobase, pcmcia_gpib_iosize); } } tnt4882_free_private(board); diff --git a/drivers/staging/greybus/camera.c b/drivers/staging/greybus/camera.c index ca71023df447..5d80ace41d8e 100644 --- a/drivers/staging/greybus/camera.c +++ b/drivers/staging/greybus/camera.c @@ -1128,18 +1128,7 @@ done: static int gb_camera_debugfs_open(struct inode *inode, struct file *file) { - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(gb_camera_debugfs_entries); ++i) { - const struct gb_camera_debugfs_entry *entry = - &gb_camera_debugfs_entries[i]; - - if (!strcmp(file->f_path.dentry->d_iname, entry->name)) { - file->private_data = (void *)entry; - break; - } - } - + file->private_data = (void *)debugfs_get_aux(file); return 0; } @@ -1175,8 +1164,8 @@ static int gb_camera_debugfs_init(struct gb_camera *gcam) gcam->debugfs.buffers[i].length = 0; - debugfs_create_file(entry->name, entry->mask, - gcam->debugfs.root, gcam, + debugfs_create_file_aux(entry->name, entry->mask, + gcam->debugfs.root, gcam, entry, &gb_camera_debugfs_ops); } diff --git a/drivers/staging/iio/frequency/ad9832.c b/drivers/staging/iio/frequency/ad9832.c index 492612e8f8ba..140ee4f9c137 100644 --- a/drivers/staging/iio/frequency/ad9832.c +++ b/drivers/staging/iio/frequency/ad9832.c @@ -158,7 +158,7 @@ static int ad9832_write_frequency(struct ad9832_state *st, static int ad9832_write_phase(struct ad9832_state *st, unsigned long addr, unsigned long phase) { - if (phase > BIT(AD9832_PHASE_BITS)) + if (phase >= BIT(AD9832_PHASE_BITS)) return -EINVAL; st->phase_data[0] = cpu_to_be16((AD9832_CMD_PHA8BITSW << CMD_SHIFT) | diff --git a/drivers/staging/iio/frequency/ad9834.c b/drivers/staging/iio/frequency/ad9834.c index 47e7d7e6d920..6e99e008c5f4 100644 --- a/drivers/staging/iio/frequency/ad9834.c +++ b/drivers/staging/iio/frequency/ad9834.c @@ -131,7 +131,7 @@ static int ad9834_write_frequency(struct ad9834_state *st, static int ad9834_write_phase(struct ad9834_state *st, unsigned long addr, unsigned long phase) { - if (phase > BIT(AD9834_PHASE_BITS)) + if (phase >= BIT(AD9834_PHASE_BITS)) return -EINVAL; st->data = cpu_to_be16(addr | phase); diff --git a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c index 07ed33464d71..224ca8d42721 100644 --- a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c +++ b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c @@ -624,10 +624,10 @@ static int alloc_private_pages(struct hmm_buffer_object *bo) const gfp_t gfp = __GFP_NOWARN | __GFP_RECLAIM | __GFP_FS; int ret; - ret = alloc_pages_bulk_array(gfp, bo->pgnr, bo->pages); + ret = alloc_pages_bulk(gfp, bo->pgnr, bo->pages); if (ret != bo->pgnr) { free_pages_bulk_array(ret, bo->pages); - dev_err(atomisp_dev, "alloc_pages_bulk_array() failed\n"); + dev_err(atomisp_dev, "alloc_pages_bulk() failed\n"); return -ENOMEM; } diff --git a/drivers/staging/media/imx/imx-media-of.c b/drivers/staging/media/imx/imx-media-of.c index 118bff988bc7..bb28daa4d713 100644 --- a/drivers/staging/media/imx/imx-media-of.c +++ b/drivers/staging/media/imx/imx-media-of.c @@ -54,22 +54,18 @@ int imx_media_add_of_subdevs(struct imx_media_dev *imxmd, break; ret = imx_media_of_add_csi(imxmd, csi_np); + of_node_put(csi_np); if (ret) { /* unavailable or already added is not an error */ if (ret == -ENODEV || ret == -EEXIST) { - of_node_put(csi_np); continue; } /* other error, can't continue */ - goto err_out; + return ret; } } return 0; - -err_out: - of_node_put(csi_np); - return ret; } EXPORT_SYMBOL_GPL(imx_media_add_of_subdevs); diff --git a/drivers/staging/media/max96712/max96712.c b/drivers/staging/media/max96712/max96712.c index ede02e8c891c..0751b2e04895 100644 --- a/drivers/staging/media/max96712/max96712.c +++ b/drivers/staging/media/max96712/max96712.c @@ -418,7 +418,6 @@ static int max96712_probe(struct i2c_client *client) priv->info = of_device_get_match_data(&client->dev); priv->client = client; - i2c_set_clientdata(client, priv); priv->regmap = devm_regmap_init_i2c(client, &max96712_i2c_regmap); if (IS_ERR(priv->regmap)) @@ -448,7 +447,8 @@ static int max96712_probe(struct i2c_client *client) static void max96712_remove(struct i2c_client *client) { - struct max96712_priv *priv = i2c_get_clientdata(client); + struct v4l2_subdev *sd = i2c_get_clientdata(client); + struct max96712_priv *priv = container_of(sd, struct max96712_priv, sd); v4l2_async_unregister_subdev(&priv->sd); diff --git a/drivers/staging/rtl8723bs/Makefile b/drivers/staging/rtl8723bs/Makefile index ba200ee669f3..8560b84a3146 100644 --- a/drivers/staging/rtl8723bs/Makefile +++ b/drivers/staging/rtl8723bs/Makefile @@ -48,7 +48,6 @@ r8723bs-y = \ hal/HalHWImg8723B_RF.o \ hal/HalPhyRf_8723B.o \ os_dep/ioctl_cfg80211.o \ - os_dep/ioctl_linux.o \ os_dep/mlme_linux.o \ os_dep/osdep_service.o \ os_dep/os_intfs.o \ diff --git a/drivers/staging/rtl8723bs/core/rtw_io.c b/drivers/staging/rtl8723bs/core/rtw_io.c index fcda9db6ebb5..79d543d88278 100644 --- a/drivers/staging/rtl8723bs/core/rtw_io.c +++ b/drivers/staging/rtl8723bs/core/rtw_io.c @@ -141,12 +141,12 @@ int rtw_init_io_priv(struct adapter *padapter, void (*set_intf_ops)(struct adapt */ int rtw_inc_and_chk_continual_io_error(struct dvobj_priv *dvobj) { - int ret = false; - int value = atomic_inc_return(&dvobj->continual_io_error); - if (value > MAX_CONTINUAL_IO_ERR) - ret = true; + int error_count = atomic_inc_return(&dvobj->continual_io_error); - return ret; + if (error_count > MAX_CONTINUAL_IO_ERR) + return true; + + return false; } /* diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c index 317f3db19397..952ce6dd5af9 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c @@ -4959,7 +4959,6 @@ void _linked_info_dump(struct adapter *padapter) rtw_hal_get_def_var(padapter, HW_DEF_RA_INFO_DUMP, &i); } } - rtw_hal_set_def_var(padapter, HAL_DEF_DBG_RX_INFO_DUMP, NULL); } } diff --git a/drivers/staging/rtl8723bs/core/rtw_xmit.c b/drivers/staging/rtl8723bs/core/rtw_xmit.c index 699cff7b0ac9..297c93d65315 100644 --- a/drivers/staging/rtl8723bs/core/rtw_xmit.c +++ b/drivers/staging/rtl8723bs/core/rtw_xmit.c @@ -1467,7 +1467,8 @@ struct xmit_buf *rtw_alloc_xmitbuf_ext(struct xmit_priv *pxmitpriv) pxmitbuf->priv_data = NULL; pxmitbuf->len = 0; - pxmitbuf->pdata = pxmitbuf->ptail = pxmitbuf->phead; + pxmitbuf->pdata = pxmitbuf->phead; + pxmitbuf->ptail = pxmitbuf->phead; pxmitbuf->agg_num = 1; if (pxmitbuf->sctx) @@ -1526,7 +1527,8 @@ struct xmit_buf *rtw_alloc_xmitbuf(struct xmit_priv *pxmitpriv) pxmitbuf->priv_data = NULL; pxmitbuf->len = 0; - pxmitbuf->pdata = pxmitbuf->ptail = pxmitbuf->phead; + pxmitbuf->pdata = pxmitbuf->phead; + pxmitbuf->ptail = pxmitbuf->phead; pxmitbuf->agg_num = 0; pxmitbuf->pg_num = 0; diff --git a/drivers/staging/rtl8723bs/hal/hal_com.c b/drivers/staging/rtl8723bs/hal/hal_com.c index 95fb38283c58..b41ec89932af 100644 --- a/drivers/staging/rtl8723bs/hal/hal_com.c +++ b/drivers/staging/rtl8723bs/hal/hal_com.c @@ -682,14 +682,6 @@ u8 SetHalDefVar( u8 bResult = _SUCCESS; switch (variable) { - case HAL_DEF_DBG_RX_INFO_DUMP: - - if (odm->bLinked) { - #ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA - rtw_dump_raw_rssi_info(adapter); - #endif - } - break; case HW_DEF_ODM_DBG_FLAG: ODM_CmnInfoUpdate(odm, ODM_CMNINFO_DBG_COMP, *((u64 *)value)); break; @@ -879,53 +871,6 @@ void rtw_hal_check_rxfifo_full(struct adapter *adapter) } } -#ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA -void rtw_dump_raw_rssi_info(struct adapter *padapter) -{ - u8 isCCKrate, rf_path; - struct hal_com_data *pHalData = GET_HAL_DATA(padapter); - struct rx_raw_rssi *psample_pkt_rssi = &padapter->recvpriv.raw_rssi_info; - - isCCKrate = psample_pkt_rssi->data_rate <= DESC_RATE11M; - - if (isCCKrate) - psample_pkt_rssi->mimo_signal_strength[0] = psample_pkt_rssi->pwdball; - - for (rf_path = 0; rf_path < pHalData->NumTotalRFPath; rf_path++) { - if (!isCCKrate) { - netdev_dbg(padapter->pnetdev, ", rx_ofdm_pwr:%d(dBm), rx_ofdm_snr:%d(dB)\n", - psample_pkt_rssi->ofdm_pwr[rf_path], - psample_pkt_rssi->ofdm_snr[rf_path]); - } - } -} - -void rtw_store_phy_info(struct adapter *padapter, union recv_frame *prframe) -{ - u8 isCCKrate, rf_path; - struct hal_com_data *pHalData = GET_HAL_DATA(padapter); - struct rx_pkt_attrib *pattrib = &prframe->u.hdr.attrib; - - struct odm_phy_info *pPhyInfo = (PODM_PHY_INFO_T)(&pattrib->phy_info); - struct rx_raw_rssi *psample_pkt_rssi = &padapter->recvpriv.raw_rssi_info; - - psample_pkt_rssi->data_rate = pattrib->data_rate; - isCCKrate = pattrib->data_rate <= DESC_RATE11M; - - psample_pkt_rssi->pwdball = pPhyInfo->rx_pwd_ba11; - psample_pkt_rssi->pwr_all = pPhyInfo->recv_signal_power; - - for (rf_path = 0; rf_path < pHalData->NumTotalRFPath; rf_path++) { - psample_pkt_rssi->mimo_signal_strength[rf_path] = pPhyInfo->rx_mimo_signal_strength[rf_path]; - psample_pkt_rssi->mimo_signal_quality[rf_path] = pPhyInfo->rx_mimo_signal_quality[rf_path]; - if (!isCCKrate) { - psample_pkt_rssi->ofdm_pwr[rf_path] = pPhyInfo->RxPwr[rf_path]; - psample_pkt_rssi->ofdm_snr[rf_path] = pPhyInfo->RxSNR[rf_path]; - } - } -} -#endif - static u32 Array_kfreemap[] = { 0xf8, 0xe, 0xf6, 0xc, diff --git a/drivers/staging/rtl8723bs/hal/rtl8723b_rxdesc.c b/drivers/staging/rtl8723bs/hal/rtl8723b_rxdesc.c index 717faebf8aca..db3d7d72bffa 100644 --- a/drivers/staging/rtl8723bs/hal/rtl8723b_rxdesc.c +++ b/drivers/staging/rtl8723bs/hal/rtl8723b_rxdesc.c @@ -67,8 +67,4 @@ void rtl8723b_process_phy_info(struct adapter *padapter, void *prframe) /* Check EVM */ /* */ process_link_qual(padapter, precvframe); - #ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA - rtw_store_phy_info(padapter, prframe); - #endif - } diff --git a/drivers/staging/rtl8723bs/include/hal_com.h b/drivers/staging/rtl8723bs/include/hal_com.h index 4db93484725f..258a74076dd9 100644 --- a/drivers/staging/rtl8723bs/include/hal_com.h +++ b/drivers/staging/rtl8723bs/include/hal_com.h @@ -149,11 +149,6 @@ bool eqNByte(u8 *str1, u8 *str2, u32 num); bool GetU1ByteIntegerFromStringInDecimal(char *str, u8 *in); -#ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA -void rtw_store_phy_info(struct adapter *padapter, union recv_frame *prframe); -void rtw_dump_raw_rssi_info(struct adapter *padapter); -#endif - #define HWSET_MAX_SIZE 512 void rtw_bb_rf_gain_offset(struct adapter *padapter); diff --git a/drivers/staging/rtl8723bs/include/hal_intf.h b/drivers/staging/rtl8723bs/include/hal_intf.h index 282e141616b0..85de862823c2 100644 --- a/drivers/staging/rtl8723bs/include/hal_intf.h +++ b/drivers/staging/rtl8723bs/include/hal_intf.h @@ -144,7 +144,6 @@ enum hal_def_variable { HAL_DEF_PCI_AMD_L1_SUPPORT, HAL_DEF_PCI_ASPM_OSC, /* Support for ASPM OSC, added by Roger, 2013.03.27. */ HAL_DEF_MACID_SLEEP, /* Support for MACID sleep */ - HAL_DEF_DBG_RX_INFO_DUMP, }; enum hal_odm_variable { diff --git a/drivers/staging/rtl8723bs/include/osdep_intf.h b/drivers/staging/rtl8723bs/include/osdep_intf.h index 215ece612f71..73199be78139 100644 --- a/drivers/staging/rtl8723bs/include/osdep_intf.h +++ b/drivers/staging/rtl8723bs/include/osdep_intf.h @@ -47,8 +47,6 @@ u32 rtw_start_drv_threads(struct adapter *padapter); void rtw_stop_drv_threads(struct adapter *padapter); void rtw_cancel_all_timer(struct adapter *padapter); -int rtw_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); - int rtw_init_netdev_name(struct net_device *pnetdev, const char *ifname); struct net_device *rtw_init_netdev(struct adapter *padapter); void rtw_unregister_netdevs(struct dvobj_priv *dvobj); diff --git a/drivers/staging/rtl8723bs/include/rtw_recv.h b/drivers/staging/rtl8723bs/include/rtw_recv.h index 18dd1464e0c2..aa9f9d5ecd01 100644 --- a/drivers/staging/rtl8723bs/include/rtw_recv.h +++ b/drivers/staging/rtl8723bs/include/rtw_recv.h @@ -89,21 +89,6 @@ struct phy_info { u8 btCoexPwrAdjust; }; -#ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA -struct rx_raw_rssi { - u8 data_rate; - u8 pwdball; - s8 pwr_all; - - u8 mimo_signal_strength[4];/* in 0~100 index */ - u8 mimo_signal_quality[4]; - - s8 ofdm_pwr[4]; - u8 ofdm_snr[4]; - -}; -#endif - struct rx_pkt_attrib { u16 pkt_len; u8 physt; @@ -221,9 +206,6 @@ struct recv_priv { u8 signal_strength; u8 signal_qual; s8 rssi; /* translate_percentage_to_dbm(ptarget_wlan->network.PhyInfo.SignalStrength); */ - #ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA - struct rx_raw_rssi raw_rssi_info; - #endif /* s8 rxpwdb; */ s16 noise; /* int RxSNRdB[2]; */ diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index c053ee9c1361..7fcc46a0bb48 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -1802,7 +1802,8 @@ static int cfg80211_rtw_set_txpower(struct wiphy *wiphy, } static int cfg80211_rtw_get_txpower(struct wiphy *wiphy, - struct wireless_dev *wdev, int *dbm) + struct wireless_dev *wdev, + unsigned int link_id, int *dbm) { *dbm = (12); diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c deleted file mode 100644 index 793b051536f3..000000000000 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c +++ /dev/null @@ -1,1286 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/****************************************************************************** - * - * Copyright(c) 2007 - 2012 Realtek Corporation. All rights reserved. - * - ******************************************************************************/ - -#include -#include -#include -#include -#include -#include - -#define RTL_IOCTL_WPA_SUPPLICANT (SIOCIWFIRSTPRIV + 30) - -static int wpa_set_auth_algs(struct net_device *dev, u32 value) -{ - struct adapter *padapter = rtw_netdev_priv(dev); - int ret = 0; - - if ((value & IW_AUTH_ALG_SHARED_KEY) && (value & IW_AUTH_ALG_OPEN_SYSTEM)) { - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled; - padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeAutoSwitch; - padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_Auto; - } else if (value & IW_AUTH_ALG_SHARED_KEY) { - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled; - - padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeShared; - padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_Shared; - } else if (value & IW_AUTH_ALG_OPEN_SYSTEM) { - /* padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled; */ - if (padapter->securitypriv.ndisauthtype < Ndis802_11AuthModeWPAPSK) { - padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeOpen; - padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_Open; - } - } else { - ret = -EINVAL; - } - - return ret; -} - -static int wpa_set_encryption(struct net_device *dev, struct ieee_param *param, u32 param_len) -{ - int ret = 0; - u8 max_idx; - u32 wep_key_idx, wep_key_len, wep_total_len; - struct ndis_802_11_wep *pwep = NULL; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - struct security_priv *psecuritypriv = &padapter->securitypriv; - - param->u.crypt.err = 0; - param->u.crypt.alg[IEEE_CRYPT_ALG_NAME_LEN - 1] = '\0'; - - if (param_len < (u32)((u8 *)param->u.crypt.key - (u8 *)param) + param->u.crypt.key_len) { - ret = -EINVAL; - goto exit; - } - - if (param->sta_addr[0] != 0xff || param->sta_addr[1] != 0xff || - param->sta_addr[2] != 0xff || param->sta_addr[3] != 0xff || - param->sta_addr[4] != 0xff || param->sta_addr[5] != 0xff) { - ret = -EINVAL; - goto exit; - } - - if (strcmp(param->u.crypt.alg, "WEP") == 0) - max_idx = WEP_KEYS - 1; - else - max_idx = BIP_MAX_KEYID; - - if (param->u.crypt.idx > max_idx) { - netdev_err(dev, "Error crypt.idx %d > %d\n", param->u.crypt.idx, max_idx); - ret = -EINVAL; - goto exit; - } - - if (strcmp(param->u.crypt.alg, "WEP") == 0) { - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled; - padapter->securitypriv.dot11PrivacyAlgrthm = _WEP40_; - padapter->securitypriv.dot118021XGrpPrivacy = _WEP40_; - - wep_key_idx = param->u.crypt.idx; - wep_key_len = param->u.crypt.key_len; - - if (wep_key_len > 0) { - wep_key_len = wep_key_len <= 5 ? 5 : 13; - wep_total_len = wep_key_len + FIELD_OFFSET(struct ndis_802_11_wep, key_material); - /* Allocate a full structure to avoid potentially running off the end. */ - pwep = kzalloc(sizeof(*pwep), GFP_KERNEL); - if (!pwep) { - ret = -ENOMEM; - goto exit; - } - - pwep->key_length = wep_key_len; - pwep->length = wep_total_len; - - if (wep_key_len == 13) { - padapter->securitypriv.dot11PrivacyAlgrthm = _WEP104_; - padapter->securitypriv.dot118021XGrpPrivacy = _WEP104_; - } - } else { - ret = -EINVAL; - goto exit; - } - - pwep->key_index = wep_key_idx; - pwep->key_index |= 0x80000000; - - memcpy(pwep->key_material, param->u.crypt.key, pwep->key_length); - - if (param->u.crypt.set_tx) { - if (rtw_set_802_11_add_wep(padapter, pwep) == (u8)_FAIL) - ret = -EOPNOTSUPP; - } else { - /* don't update "psecuritypriv->dot11PrivacyAlgrthm" and */ - /* psecuritypriv->dot11PrivacyKeyIndex =keyid", but can rtw_set_key to fw/cam */ - - if (wep_key_idx >= WEP_KEYS) { - ret = -EOPNOTSUPP; - goto exit; - } - - memcpy(&psecuritypriv->dot11DefKey[wep_key_idx].skey[0], pwep->key_material, pwep->key_length); - psecuritypriv->dot11DefKeylen[wep_key_idx] = pwep->key_length; - rtw_set_key(padapter, psecuritypriv, wep_key_idx, 0, true); - } - - goto exit; - } - - if (padapter->securitypriv.dot11AuthAlgrthm == dot11AuthAlgrthm_8021X) { /* 802_1x */ - struct sta_info *psta, *pbcmc_sta; - struct sta_priv *pstapriv = &padapter->stapriv; - - if (check_fwstate(pmlmepriv, WIFI_STATION_STATE | WIFI_MP_STATE) == true) { /* sta mode */ - psta = rtw_get_stainfo(pstapriv, get_bssid(pmlmepriv)); - if (psta) { - /* Jeff: don't disable ieee8021x_blocked while clearing key */ - if (strcmp(param->u.crypt.alg, "none") != 0) - psta->ieee8021x_blocked = false; - - if ((padapter->securitypriv.ndisencryptstatus == Ndis802_11Encryption2Enabled) || - (padapter->securitypriv.ndisencryptstatus == Ndis802_11Encryption3Enabled)) { - psta->dot118021XPrivacy = padapter->securitypriv.dot11PrivacyAlgrthm; - } - - if (param->u.crypt.set_tx == 1) { /* pairwise key */ - memcpy(psta->dot118021x_UncstKey.skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - - if (strcmp(param->u.crypt.alg, "TKIP") == 0) { /* set mic key */ - memcpy(psta->dot11tkiptxmickey.skey, ¶m->u.crypt.key[16], 8); - memcpy(psta->dot11tkiprxmickey.skey, ¶m->u.crypt.key[24], 8); - - padapter->securitypriv.busetkipkey = false; - /* _set_timer(&padapter->securitypriv.tkip_timer, 50); */ - } - - rtw_setstakey_cmd(padapter, psta, true, true); - } else { /* group key */ - if (strcmp(param->u.crypt.alg, "TKIP") == 0 || strcmp(param->u.crypt.alg, "CCMP") == 0) { - memcpy(padapter->securitypriv.dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - /* only TKIP group key need to install this */ - if (param->u.crypt.key_len > 16) { - memcpy(padapter->securitypriv.dot118021XGrptxmickey[param->u.crypt.idx].skey, ¶m->u.crypt.key[16], 8); - memcpy(padapter->securitypriv.dot118021XGrprxmickey[param->u.crypt.idx].skey, ¶m->u.crypt.key[24], 8); - } - padapter->securitypriv.binstallGrpkey = true; - - padapter->securitypriv.dot118021XGrpKeyid = param->u.crypt.idx; - - rtw_set_key(padapter, &padapter->securitypriv, param->u.crypt.idx, 1, true); - } else if (strcmp(param->u.crypt.alg, "BIP") == 0) { - /* save the IGTK key, length 16 bytes */ - memcpy(padapter->securitypriv.dot11wBIPKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - padapter->securitypriv.dot11wBIPKeyid = param->u.crypt.idx; - padapter->securitypriv.binstallBIPkey = true; - } - } - } - - pbcmc_sta = rtw_get_bcmc_stainfo(padapter); - if (pbcmc_sta) { - /* Jeff: don't disable ieee8021x_blocked while clearing key */ - if (strcmp(param->u.crypt.alg, "none") != 0) - pbcmc_sta->ieee8021x_blocked = false; - - if ((padapter->securitypriv.ndisencryptstatus == Ndis802_11Encryption2Enabled) || - (padapter->securitypriv.ndisencryptstatus == Ndis802_11Encryption3Enabled)) { - pbcmc_sta->dot118021XPrivacy = padapter->securitypriv.dot11PrivacyAlgrthm; - } - } - } else if (check_fwstate(pmlmepriv, WIFI_ADHOC_STATE)) { - /* adhoc mode */ - } - } - -exit: - - kfree(pwep); - return ret; -} - -static int rtw_set_wpa_ie(struct adapter *padapter, char *pie, unsigned short ielen) -{ - u8 *buf = NULL; - int group_cipher = 0, pairwise_cipher = 0; - int ret = 0; - u8 null_addr[] = {0, 0, 0, 0, 0, 0}; - - if (ielen > MAX_WPA_IE_LEN || !pie) { - _clr_fwstate_(&padapter->mlmepriv, WIFI_UNDER_WPS); - if (!pie) - return ret; - else - return -EINVAL; - } - - if (ielen) { - buf = rtw_zmalloc(ielen); - if (!buf) { - ret = -ENOMEM; - goto exit; - } - - memcpy(buf, pie, ielen); - - if (ielen < RSN_HEADER_LEN) { - ret = -1; - goto exit; - } - - if (rtw_parse_wpa_ie(buf, ielen, &group_cipher, &pairwise_cipher, NULL) == _SUCCESS) { - padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_8021X; - padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPAPSK; - memcpy(padapter->securitypriv.supplicant_ie, &buf[0], ielen); - } - - if (rtw_parse_wpa2_ie(buf, ielen, &group_cipher, &pairwise_cipher, NULL) == _SUCCESS) { - padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_8021X; - padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPA2PSK; - memcpy(padapter->securitypriv.supplicant_ie, &buf[0], ielen); - } - - if (group_cipher == 0) - group_cipher = WPA_CIPHER_NONE; - if (pairwise_cipher == 0) - pairwise_cipher = WPA_CIPHER_NONE; - - switch (group_cipher) { - case WPA_CIPHER_NONE: - padapter->securitypriv.dot118021XGrpPrivacy = _NO_PRIVACY_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled; - break; - case WPA_CIPHER_WEP40: - padapter->securitypriv.dot118021XGrpPrivacy = _WEP40_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled; - break; - case WPA_CIPHER_TKIP: - padapter->securitypriv.dot118021XGrpPrivacy = _TKIP_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled; - break; - case WPA_CIPHER_CCMP: - padapter->securitypriv.dot118021XGrpPrivacy = _AES_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled; - break; - case WPA_CIPHER_WEP104: - padapter->securitypriv.dot118021XGrpPrivacy = _WEP104_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled; - break; - } - - switch (pairwise_cipher) { - case WPA_CIPHER_NONE: - padapter->securitypriv.dot11PrivacyAlgrthm = _NO_PRIVACY_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled; - break; - case WPA_CIPHER_WEP40: - padapter->securitypriv.dot11PrivacyAlgrthm = _WEP40_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled; - break; - case WPA_CIPHER_TKIP: - padapter->securitypriv.dot11PrivacyAlgrthm = _TKIP_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled; - break; - case WPA_CIPHER_CCMP: - padapter->securitypriv.dot11PrivacyAlgrthm = _AES_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled; - break; - case WPA_CIPHER_WEP104: - padapter->securitypriv.dot11PrivacyAlgrthm = _WEP104_; - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled; - break; - } - - _clr_fwstate_(&padapter->mlmepriv, WIFI_UNDER_WPS); - {/* set wps_ie */ - u16 cnt = 0; - u8 eid, wps_oui[4] = {0x0, 0x50, 0xf2, 0x04}; - - while (cnt < ielen) { - eid = buf[cnt]; - - if ((eid == WLAN_EID_VENDOR_SPECIFIC) && (!memcmp(&buf[cnt + 2], wps_oui, 4))) { - padapter->securitypriv.wps_ie_len = ((buf[cnt + 1] + 2) < MAX_WPS_IE_LEN) ? (buf[cnt + 1] + 2) : MAX_WPS_IE_LEN; - - memcpy(padapter->securitypriv.wps_ie, &buf[cnt], padapter->securitypriv.wps_ie_len); - - set_fwstate(&padapter->mlmepriv, WIFI_UNDER_WPS); - - cnt += buf[cnt + 1] + 2; - - break; - } else { - cnt += buf[cnt + 1] + 2; /* goto next */ - } - } - } - } - - /* TKIP and AES disallow multicast packets until installing group key */ - if (padapter->securitypriv.dot11PrivacyAlgrthm == _TKIP_ || - padapter->securitypriv.dot11PrivacyAlgrthm == _TKIP_WTMIC_ || - padapter->securitypriv.dot11PrivacyAlgrthm == _AES_) - /* WPS open need to enable multicast */ - /* check_fwstate(&padapter->mlmepriv, WIFI_UNDER_WPS) == true) */ - rtw_hal_set_hwreg(padapter, HW_VAR_OFF_RCR_AM, null_addr); - -exit: - - kfree(buf); - - return ret; -} - -static int wpa_set_param(struct net_device *dev, u8 name, u32 value) -{ - uint ret = 0; - struct adapter *padapter = rtw_netdev_priv(dev); - - switch (name) { - case IEEE_PARAM_WPA_ENABLED: - - padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_8021X; /* 802.1x */ - - /* ret = ieee80211_wpa_enable(ieee, value); */ - - switch ((value) & 0xff) { - case 1: /* WPA */ - padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPAPSK; /* WPA_PSK */ - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled; - break; - case 2: /* WPA2 */ - padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPA2PSK; /* WPA2_PSK */ - padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled; - break; - } - - break; - - case IEEE_PARAM_TKIP_COUNTERMEASURES: - /* ieee->tkip_countermeasures =value; */ - break; - - case IEEE_PARAM_DROP_UNENCRYPTED: - { - /* HACK: - * - * wpa_supplicant calls set_wpa_enabled when the driver - * is loaded and unloaded, regardless of if WPA is being - * used. No other calls are made which can be used to - * determine if encryption will be used or not prior to - * association being expected. If encryption is not being - * used, drop_unencrypted is set to false, else true -- we - * can use this to determine if the CAP_PRIVACY_ON bit should - * be set. - */ - break; - } - case IEEE_PARAM_PRIVACY_INVOKED: - - /* ieee->privacy_invoked =value; */ - - break; - - case IEEE_PARAM_AUTH_ALGS: - - ret = wpa_set_auth_algs(dev, value); - - break; - - case IEEE_PARAM_IEEE_802_1X: - - /* ieee->ieee802_1x =value; */ - - break; - - case IEEE_PARAM_WPAX_SELECT: - - /* added for WPA2 mixed mode */ - /* - spin_lock_irqsave(&ieee->wpax_suitlist_lock, flags); - ieee->wpax_type_set = 1; - ieee->wpax_type_notify = value; - spin_unlock_irqrestore(&ieee->wpax_suitlist_lock, flags); - */ - - break; - - default: - - ret = -EOPNOTSUPP; - - break; - } - - return ret; -} - -static int wpa_mlme(struct net_device *dev, u32 command, u32 reason) -{ - int ret = 0; - struct adapter *padapter = rtw_netdev_priv(dev); - - switch (command) { - case IEEE_MLME_STA_DEAUTH: - - if (!rtw_set_802_11_disassociate(padapter)) - ret = -1; - - break; - - case IEEE_MLME_STA_DISASSOC: - - if (!rtw_set_802_11_disassociate(padapter)) - ret = -1; - - break; - - default: - ret = -EOPNOTSUPP; - break; - } - - return ret; -} - -static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) -{ - struct ieee_param *param; - uint ret = 0; - - /* down(&ieee->wx_sem); */ - - if (!p->pointer || p->length != sizeof(struct ieee_param)) - return -EINVAL; - - param = rtw_malloc(p->length); - if (!param) - return -ENOMEM; - - if (copy_from_user(param, p->pointer, p->length)) { - kfree(param); - return -EFAULT; - } - - switch (param->cmd) { - case IEEE_CMD_SET_WPA_PARAM: - ret = wpa_set_param(dev, param->u.wpa_param.name, param->u.wpa_param.value); - break; - - case IEEE_CMD_SET_WPA_IE: - /* ret = wpa_set_wpa_ie(dev, param, p->length); */ - ret = rtw_set_wpa_ie(rtw_netdev_priv(dev), (char *)param->u.wpa_ie.data, (u16)param->u.wpa_ie.len); - break; - - case IEEE_CMD_SET_ENCRYPTION: - ret = wpa_set_encryption(dev, param, p->length); - break; - - case IEEE_CMD_MLME: - ret = wpa_mlme(dev, param->u.mlme.command, param->u.mlme.reason_code); - break; - - default: - ret = -EOPNOTSUPP; - break; - } - - if (ret == 0 && copy_to_user(p->pointer, param, p->length)) - ret = -EFAULT; - - kfree(param); - - /* up(&ieee->wx_sem); */ - return ret; -} - -static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, u32 param_len) -{ - int ret = 0; - u32 wep_key_idx, wep_key_len, wep_total_len; - struct ndis_802_11_wep *pwep = NULL; - struct sta_info *psta = NULL, *pbcmc_sta = NULL; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - struct security_priv *psecuritypriv = &padapter->securitypriv; - struct sta_priv *pstapriv = &padapter->stapriv; - char *txkey = padapter->securitypriv.dot118021XGrptxmickey[param->u.crypt.idx].skey; - char *rxkey = padapter->securitypriv.dot118021XGrprxmickey[param->u.crypt.idx].skey; - char *grpkey = psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey; - - param->u.crypt.err = 0; - param->u.crypt.alg[IEEE_CRYPT_ALG_NAME_LEN - 1] = '\0'; - - /* sizeof(struct ieee_param) = 64 bytes; */ - /* if (param_len != (u32) ((u8 *) param->u.crypt.key - (u8 *) param) + param->u.crypt.key_len) */ - if (param_len != sizeof(struct ieee_param) + param->u.crypt.key_len) { - ret = -EINVAL; - goto exit; - } - - if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff && - param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff && - param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) { - if (param->u.crypt.idx >= WEP_KEYS) { - ret = -EINVAL; - goto exit; - } - } else { - psta = rtw_get_stainfo(pstapriv, param->sta_addr); - if (!psta) - /* ret = -EINVAL; */ - goto exit; - } - - if (strcmp(param->u.crypt.alg, "none") == 0 && !psta) { - /* todo:clear default encryption keys */ - - psecuritypriv->dot11AuthAlgrthm = dot11AuthAlgrthm_Open; - psecuritypriv->ndisencryptstatus = Ndis802_11EncryptionDisabled; - psecuritypriv->dot11PrivacyAlgrthm = _NO_PRIVACY_; - psecuritypriv->dot118021XGrpPrivacy = _NO_PRIVACY_; - - goto exit; - } - - if (strcmp(param->u.crypt.alg, "WEP") == 0 && !psta) { - wep_key_idx = param->u.crypt.idx; - wep_key_len = param->u.crypt.key_len; - - if ((wep_key_idx >= WEP_KEYS) || (wep_key_len <= 0)) { - ret = -EINVAL; - goto exit; - } - - if (wep_key_len > 0) { - wep_key_len = wep_key_len <= 5 ? 5 : 13; - wep_total_len = wep_key_len + FIELD_OFFSET(struct ndis_802_11_wep, key_material); - /* Allocate a full structure to avoid potentially running off the end. */ - pwep = kzalloc(sizeof(*pwep), GFP_KERNEL); - if (!pwep) - goto exit; - - pwep->key_length = wep_key_len; - pwep->length = wep_total_len; - } - - pwep->key_index = wep_key_idx; - - memcpy(pwep->key_material, param->u.crypt.key, pwep->key_length); - - if (param->u.crypt.set_tx) { - psecuritypriv->dot11AuthAlgrthm = dot11AuthAlgrthm_Auto; - psecuritypriv->ndisencryptstatus = Ndis802_11Encryption1Enabled; - psecuritypriv->dot11PrivacyAlgrthm = _WEP40_; - psecuritypriv->dot118021XGrpPrivacy = _WEP40_; - - if (pwep->key_length == 13) { - psecuritypriv->dot11PrivacyAlgrthm = _WEP104_; - psecuritypriv->dot118021XGrpPrivacy = _WEP104_; - } - - psecuritypriv->dot11PrivacyKeyIndex = wep_key_idx; - - memcpy(&psecuritypriv->dot11DefKey[wep_key_idx].skey[0], pwep->key_material, pwep->key_length); - - psecuritypriv->dot11DefKeylen[wep_key_idx] = pwep->key_length; - - rtw_ap_set_wep_key(padapter, pwep->key_material, pwep->key_length, wep_key_idx, 1); - } else { - /* don't update "psecuritypriv->dot11PrivacyAlgrthm" and */ - /* psecuritypriv->dot11PrivacyKeyIndex =keyid", but can rtw_set_key to cam */ - - memcpy(&psecuritypriv->dot11DefKey[wep_key_idx].skey[0], pwep->key_material, pwep->key_length); - - psecuritypriv->dot11DefKeylen[wep_key_idx] = pwep->key_length; - - rtw_ap_set_wep_key(padapter, pwep->key_material, pwep->key_length, wep_key_idx, 0); - } - - goto exit; - } - - if (!psta && check_fwstate(pmlmepriv, WIFI_AP_STATE)) { /* group key */ - if (param->u.crypt.set_tx == 1) { - if (strcmp(param->u.crypt.alg, "WEP") == 0) { - memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - - psecuritypriv->dot118021XGrpPrivacy = _WEP40_; - if (param->u.crypt.key_len == 13) - psecuritypriv->dot118021XGrpPrivacy = _WEP104_; - - } else if (strcmp(param->u.crypt.alg, "TKIP") == 0) { - psecuritypriv->dot118021XGrpPrivacy = _TKIP_; - - memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - - /* set mic key */ - memcpy(txkey, ¶m->u.crypt.key[16], 8); - memcpy(psecuritypriv->dot118021XGrprxmickey[param->u.crypt.idx].skey, ¶m->u.crypt.key[24], 8); - - psecuritypriv->busetkipkey = true; - - } else if (strcmp(param->u.crypt.alg, "CCMP") == 0) { - psecuritypriv->dot118021XGrpPrivacy = _AES_; - - memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - } else { - psecuritypriv->dot118021XGrpPrivacy = _NO_PRIVACY_; - } - - psecuritypriv->dot118021XGrpKeyid = param->u.crypt.idx; - - psecuritypriv->binstallGrpkey = true; - - psecuritypriv->dot11PrivacyAlgrthm = psecuritypriv->dot118021XGrpPrivacy;/* */ - - rtw_ap_set_group_key(padapter, param->u.crypt.key, psecuritypriv->dot118021XGrpPrivacy, param->u.crypt.idx); - - pbcmc_sta = rtw_get_bcmc_stainfo(padapter); - if (pbcmc_sta) { - pbcmc_sta->ieee8021x_blocked = false; - pbcmc_sta->dot118021XPrivacy = psecuritypriv->dot118021XGrpPrivacy;/* rx will use bmc_sta's dot118021XPrivacy */ - } - } - - goto exit; - } - - if (psecuritypriv->dot11AuthAlgrthm == dot11AuthAlgrthm_8021X && psta) { /* psk/802_1x */ - if (check_fwstate(pmlmepriv, WIFI_AP_STATE)) { - if (param->u.crypt.set_tx == 1) { - memcpy(psta->dot118021x_UncstKey.skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - - if (strcmp(param->u.crypt.alg, "WEP") == 0) { - psta->dot118021XPrivacy = _WEP40_; - if (param->u.crypt.key_len == 13) - psta->dot118021XPrivacy = _WEP104_; - } else if (strcmp(param->u.crypt.alg, "TKIP") == 0) { - psta->dot118021XPrivacy = _TKIP_; - - /* set mic key */ - memcpy(psta->dot11tkiptxmickey.skey, ¶m->u.crypt.key[16], 8); - memcpy(psta->dot11tkiprxmickey.skey, ¶m->u.crypt.key[24], 8); - - psecuritypriv->busetkipkey = true; - - } else if (strcmp(param->u.crypt.alg, "CCMP") == 0) { - psta->dot118021XPrivacy = _AES_; - } else { - psta->dot118021XPrivacy = _NO_PRIVACY_; - } - - rtw_ap_set_pairwise_key(padapter, psta); - - psta->ieee8021x_blocked = false; - - } else { /* group key??? */ - if (strcmp(param->u.crypt.alg, "WEP") == 0) { - memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - - psecuritypriv->dot118021XGrpPrivacy = _WEP40_; - if (param->u.crypt.key_len == 13) - psecuritypriv->dot118021XGrpPrivacy = _WEP104_; - } else if (strcmp(param->u.crypt.alg, "TKIP") == 0) { - psecuritypriv->dot118021XGrpPrivacy = _TKIP_; - - memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - - /* set mic key */ - memcpy(txkey, ¶m->u.crypt.key[16], 8); - memcpy(rxkey, ¶m->u.crypt.key[24], 8); - - psecuritypriv->busetkipkey = true; - - } else if (strcmp(param->u.crypt.alg, "CCMP") == 0) { - psecuritypriv->dot118021XGrpPrivacy = _AES_; - - memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len)); - } else { - psecuritypriv->dot118021XGrpPrivacy = _NO_PRIVACY_; - } - - psecuritypriv->dot118021XGrpKeyid = param->u.crypt.idx; - - psecuritypriv->binstallGrpkey = true; - - psecuritypriv->dot11PrivacyAlgrthm = psecuritypriv->dot118021XGrpPrivacy;/* */ - - rtw_ap_set_group_key(padapter, param->u.crypt.key, psecuritypriv->dot118021XGrpPrivacy, param->u.crypt.idx); - - pbcmc_sta = rtw_get_bcmc_stainfo(padapter); - if (pbcmc_sta) { - pbcmc_sta->ieee8021x_blocked = false; - pbcmc_sta->dot118021XPrivacy = psecuritypriv->dot118021XGrpPrivacy;/* rx will use bmc_sta's dot118021XPrivacy */ - } - } - } - } - -exit: - kfree(pwep); - - return ret; -} - -static int rtw_set_beacon(struct net_device *dev, struct ieee_param *param, int len) -{ - int ret = 0; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - struct sta_priv *pstapriv = &padapter->stapriv; - unsigned char *pbuf = param->u.bcn_ie.buf; - - if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true) - return -EINVAL; - - memcpy(&pstapriv->max_num_sta, param->u.bcn_ie.reserved, 2); - - if ((pstapriv->max_num_sta > NUM_STA) || (pstapriv->max_num_sta <= 0)) - pstapriv->max_num_sta = NUM_STA; - - if (rtw_check_beacon_data(padapter, pbuf, (len - 12 - 2)) == _SUCCESS)/* 12 = param header, 2:no packed */ - ret = 0; - else - ret = -EINVAL; - - return ret; -} - -static void rtw_hostapd_sta_flush(struct net_device *dev) -{ - /* _irqL irqL; */ - /* struct list_head *phead, *plist; */ - /* struct sta_info *psta = NULL; */ - struct adapter *padapter = rtw_netdev_priv(dev); - /* struct sta_priv *pstapriv = &padapter->stapriv; */ - - flush_all_cam_entry(padapter); /* clear CAM */ - - rtw_sta_flush(padapter); -} - -static int rtw_add_sta(struct net_device *dev, struct ieee_param *param) -{ - int ret = 0; - struct sta_info *psta = NULL; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - struct sta_priv *pstapriv = &padapter->stapriv; - - if (check_fwstate(pmlmepriv, (_FW_LINKED | WIFI_AP_STATE)) != true) - return -EINVAL; - - if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff && - param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff && - param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) { - return -EINVAL; - } - -/* - psta = rtw_get_stainfo(pstapriv, param->sta_addr); - if (psta) - { - rtw_free_stainfo(padapter, psta); - - psta = NULL; - } -*/ - /* psta = rtw_alloc_stainfo(pstapriv, param->sta_addr); */ - psta = rtw_get_stainfo(pstapriv, param->sta_addr); - if (psta) { - int flags = param->u.add_sta.flags; - - psta->aid = param->u.add_sta.aid;/* aid = 1~2007 */ - - memcpy(psta->bssrateset, param->u.add_sta.tx_supp_rates, 16); - - /* check wmm cap. */ - if (WLAN_STA_WME & flags) - psta->qos_option = 1; - else - psta->qos_option = 0; - - if (pmlmepriv->qospriv.qos_option == 0) - psta->qos_option = 0; - - /* chec 802.11n ht cap. */ - if (WLAN_STA_HT & flags) { - psta->htpriv.ht_option = true; - psta->qos_option = 1; - memcpy((void *)&psta->htpriv.ht_cap, (void *)¶m->u.add_sta.ht_cap, sizeof(struct ieee80211_ht_cap)); - } else { - psta->htpriv.ht_option = false; - } - - if (!pmlmepriv->htpriv.ht_option) - psta->htpriv.ht_option = false; - - update_sta_info_apmode(padapter, psta); - - } else { - ret = -ENOMEM; - } - - return ret; -} - -static int rtw_del_sta(struct net_device *dev, struct ieee_param *param) -{ - int ret = 0; - struct sta_info *psta = NULL; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - struct sta_priv *pstapriv = &padapter->stapriv; - - if (check_fwstate(pmlmepriv, (_FW_LINKED | WIFI_AP_STATE)) != true) - return -EINVAL; - - if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff && - param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff && - param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) { - return -EINVAL; - } - - psta = rtw_get_stainfo(pstapriv, param->sta_addr); - if (psta) { - u8 updated = false; - - spin_lock_bh(&pstapriv->asoc_list_lock); - if (list_empty(&psta->asoc_list) == false) { - list_del_init(&psta->asoc_list); - pstapriv->asoc_list_cnt--; - updated = ap_free_sta(padapter, psta, true, WLAN_REASON_DEAUTH_LEAVING); - } - spin_unlock_bh(&pstapriv->asoc_list_lock); - - associated_clients_update(padapter, updated); - - psta = NULL; - } - - return ret; -} - -static int rtw_ioctl_get_sta_data(struct net_device *dev, struct ieee_param *param, int len) -{ - int ret = 0; - struct sta_info *psta = NULL; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - struct sta_priv *pstapriv = &padapter->stapriv; - struct ieee_param_ex *param_ex = (struct ieee_param_ex *)param; - struct sta_data *psta_data = (struct sta_data *)param_ex->data; - - if (check_fwstate(pmlmepriv, (_FW_LINKED | WIFI_AP_STATE)) != true) - return -EINVAL; - - if (param_ex->sta_addr[0] == 0xff && param_ex->sta_addr[1] == 0xff && - param_ex->sta_addr[2] == 0xff && param_ex->sta_addr[3] == 0xff && - param_ex->sta_addr[4] == 0xff && param_ex->sta_addr[5] == 0xff) { - return -EINVAL; - } - - psta = rtw_get_stainfo(pstapriv, param_ex->sta_addr); - if (psta) { - psta_data->aid = (u16)psta->aid; - psta_data->capability = psta->capability; - psta_data->flags = psta->flags; - -/* - nonerp_set : BIT(0) - no_short_slot_time_set : BIT(1) - no_short_preamble_set : BIT(2) - no_ht_gf_set : BIT(3) - no_ht_set : BIT(4) - ht_20mhz_set : BIT(5) -*/ - - psta_data->sta_set = ((psta->nonerp_set) | - (psta->no_short_slot_time_set << 1) | - (psta->no_short_preamble_set << 2) | - (psta->no_ht_gf_set << 3) | - (psta->no_ht_set << 4) | - (psta->ht_20mhz_set << 5)); - - psta_data->tx_supp_rates_len = psta->bssratelen; - memcpy(psta_data->tx_supp_rates, psta->bssrateset, psta->bssratelen); - memcpy(&psta_data->ht_cap, &psta->htpriv.ht_cap, sizeof(struct ieee80211_ht_cap)); - psta_data->rx_pkts = psta->sta_stats.rx_data_pkts; - psta_data->rx_bytes = psta->sta_stats.rx_bytes; - psta_data->rx_drops = psta->sta_stats.rx_drops; - - psta_data->tx_pkts = psta->sta_stats.tx_pkts; - psta_data->tx_bytes = psta->sta_stats.tx_bytes; - psta_data->tx_drops = psta->sta_stats.tx_drops; - - } else { - ret = -1; - } - - return ret; -} - -static int rtw_get_sta_wpaie(struct net_device *dev, struct ieee_param *param) -{ - int ret = 0; - struct sta_info *psta = NULL; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - struct sta_priv *pstapriv = &padapter->stapriv; - - if (check_fwstate(pmlmepriv, (_FW_LINKED | WIFI_AP_STATE)) != true) - return -EINVAL; - - if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff && - param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff && - param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) { - return -EINVAL; - } - - psta = rtw_get_stainfo(pstapriv, param->sta_addr); - if (psta) { - if ((psta->wpa_ie[0] == WLAN_EID_RSN) || (psta->wpa_ie[0] == WLAN_EID_VENDOR_SPECIFIC)) { - int wpa_ie_len; - int copy_len; - - wpa_ie_len = psta->wpa_ie[1]; - - copy_len = ((wpa_ie_len + 2) > sizeof(psta->wpa_ie)) ? (sizeof(psta->wpa_ie)) : (wpa_ie_len + 2); - - param->u.wpa_ie.len = copy_len; - - memcpy(param->u.wpa_ie.reserved, psta->wpa_ie, copy_len); - } - } else { - ret = -1; - } - - return ret; -} - -static int rtw_set_wps_beacon(struct net_device *dev, struct ieee_param *param, int len) -{ - int ret = 0; - unsigned char wps_oui[4] = {0x0, 0x50, 0xf2, 0x04}; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - struct mlme_ext_priv *pmlmeext = &padapter->mlmeextpriv; - int ie_len; - - if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true) - return -EINVAL; - - ie_len = len - 12 - 2;/* 12 = param header, 2:no packed */ - - kfree(pmlmepriv->wps_beacon_ie); - pmlmepriv->wps_beacon_ie = NULL; - - if (ie_len > 0) { - pmlmepriv->wps_beacon_ie = rtw_malloc(ie_len); - pmlmepriv->wps_beacon_ie_len = ie_len; - if (!pmlmepriv->wps_beacon_ie) - return -EINVAL; - - memcpy(pmlmepriv->wps_beacon_ie, param->u.bcn_ie.buf, ie_len); - - update_beacon(padapter, WLAN_EID_VENDOR_SPECIFIC, wps_oui, true); - - pmlmeext->bstart_bss = true; - } - - return ret; -} - -static int rtw_set_wps_probe_resp(struct net_device *dev, struct ieee_param *param, int len) -{ - int ret = 0; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - int ie_len; - - if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true) - return -EINVAL; - - ie_len = len - 12 - 2;/* 12 = param header, 2:no packed */ - - kfree(pmlmepriv->wps_probe_resp_ie); - pmlmepriv->wps_probe_resp_ie = NULL; - - if (ie_len > 0) { - pmlmepriv->wps_probe_resp_ie = rtw_malloc(ie_len); - pmlmepriv->wps_probe_resp_ie_len = ie_len; - if (!pmlmepriv->wps_probe_resp_ie) - return -EINVAL; - - memcpy(pmlmepriv->wps_probe_resp_ie, param->u.bcn_ie.buf, ie_len); - } - - return ret; -} - -static int rtw_set_wps_assoc_resp(struct net_device *dev, struct ieee_param *param, int len) -{ - int ret = 0; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - int ie_len; - - if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true) - return -EINVAL; - - ie_len = len - 12 - 2;/* 12 = param header, 2:no packed */ - - kfree(pmlmepriv->wps_assoc_resp_ie); - pmlmepriv->wps_assoc_resp_ie = NULL; - - if (ie_len > 0) { - pmlmepriv->wps_assoc_resp_ie = rtw_malloc(ie_len); - pmlmepriv->wps_assoc_resp_ie_len = ie_len; - if (!pmlmepriv->wps_assoc_resp_ie) - return -EINVAL; - - memcpy(pmlmepriv->wps_assoc_resp_ie, param->u.bcn_ie.buf, ie_len); - } - - return ret; -} - -static int rtw_set_hidden_ssid(struct net_device *dev, struct ieee_param *param, int len) -{ - int ret = 0; - struct adapter *adapter = rtw_netdev_priv(dev); - struct mlme_priv *mlmepriv = &adapter->mlmepriv; - struct mlme_ext_priv *mlmeext = &adapter->mlmeextpriv; - struct mlme_ext_info *mlmeinfo = &mlmeext->mlmext_info; - int ie_len; - u8 *ssid_ie; - char ssid[NDIS_802_11_LENGTH_SSID + 1]; - signed int ssid_len; - u8 ignore_broadcast_ssid; - - if (check_fwstate(mlmepriv, WIFI_AP_STATE) != true) - return -EPERM; - - if (param->u.bcn_ie.reserved[0] != 0xea) - return -EINVAL; - - mlmeinfo->hidden_ssid_mode = ignore_broadcast_ssid = param->u.bcn_ie.reserved[1]; - - ie_len = len - 12 - 2;/* 12 = param header, 2:no packed */ - ssid_ie = rtw_get_ie(param->u.bcn_ie.buf, WLAN_EID_SSID, &ssid_len, ie_len); - - if (ssid_ie && ssid_len > 0 && ssid_len <= NDIS_802_11_LENGTH_SSID) { - struct wlan_bssid_ex *pbss_network = &mlmepriv->cur_network.network; - struct wlan_bssid_ex *pbss_network_ext = &mlmeinfo->network; - - memcpy(ssid, ssid_ie + 2, ssid_len); - ssid[ssid_len] = 0x0; - - memcpy(pbss_network->ssid.ssid, (void *)ssid, ssid_len); - pbss_network->ssid.ssid_length = ssid_len; - memcpy(pbss_network_ext->ssid.ssid, (void *)ssid, ssid_len); - pbss_network_ext->ssid.ssid_length = ssid_len; - } - - return ret; -} - -static int rtw_ioctl_acl_remove_sta(struct net_device *dev, struct ieee_param *param, int len) -{ - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - - if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true) - return -EINVAL; - - if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff && - param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff && - param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) { - return -EINVAL; - } - - rtw_acl_remove_sta(padapter, param->sta_addr); - return 0; -} - -static int rtw_ioctl_acl_add_sta(struct net_device *dev, struct ieee_param *param, int len) -{ - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - - if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true) - return -EINVAL; - - if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff && - param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff && - param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) { - return -EINVAL; - } - - return rtw_acl_add_sta(padapter, param->sta_addr); -} - -static int rtw_ioctl_set_macaddr_acl(struct net_device *dev, struct ieee_param *param, int len) -{ - int ret = 0; - struct adapter *padapter = rtw_netdev_priv(dev); - struct mlme_priv *pmlmepriv = &padapter->mlmepriv; - - if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true) - return -EINVAL; - - rtw_set_macaddr_acl(padapter, param->u.mlme.command); - - return ret; -} - -static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) -{ - struct ieee_param *param; - int ret = 0; - struct adapter *padapter = rtw_netdev_priv(dev); - - /* - * this function is expect to call in master mode, which allows no power saving - * so, we just check hw_init_completed - */ - - if (!padapter->hw_init_completed) - return -EPERM; - - if (!p->pointer || p->length != sizeof(*param)) - return -EINVAL; - - param = rtw_malloc(p->length); - if (!param) - return -ENOMEM; - - if (copy_from_user(param, p->pointer, p->length)) { - kfree(param); - return -EFAULT; - } - - switch (param->cmd) { - case RTL871X_HOSTAPD_FLUSH: - - rtw_hostapd_sta_flush(dev); - - break; - - case RTL871X_HOSTAPD_ADD_STA: - - ret = rtw_add_sta(dev, param); - - break; - - case RTL871X_HOSTAPD_REMOVE_STA: - - ret = rtw_del_sta(dev, param); - - break; - - case RTL871X_HOSTAPD_SET_BEACON: - - ret = rtw_set_beacon(dev, param, p->length); - - break; - - case RTL871X_SET_ENCRYPTION: - - ret = rtw_set_encryption(dev, param, p->length); - - break; - - case RTL871X_HOSTAPD_GET_WPAIE_STA: - - ret = rtw_get_sta_wpaie(dev, param); - - break; - - case RTL871X_HOSTAPD_SET_WPS_BEACON: - - ret = rtw_set_wps_beacon(dev, param, p->length); - - break; - - case RTL871X_HOSTAPD_SET_WPS_PROBE_RESP: - - ret = rtw_set_wps_probe_resp(dev, param, p->length); - - break; - - case RTL871X_HOSTAPD_SET_WPS_ASSOC_RESP: - - ret = rtw_set_wps_assoc_resp(dev, param, p->length); - - break; - - case RTL871X_HOSTAPD_SET_HIDDEN_SSID: - - ret = rtw_set_hidden_ssid(dev, param, p->length); - - break; - - case RTL871X_HOSTAPD_GET_INFO_STA: - - ret = rtw_ioctl_get_sta_data(dev, param, p->length); - - break; - - case RTL871X_HOSTAPD_SET_MACADDR_ACL: - - ret = rtw_ioctl_set_macaddr_acl(dev, param, p->length); - - break; - - case RTL871X_HOSTAPD_ACL_ADD_STA: - - ret = rtw_ioctl_acl_add_sta(dev, param, p->length); - - break; - - case RTL871X_HOSTAPD_ACL_REMOVE_STA: - - ret = rtw_ioctl_acl_remove_sta(dev, param, p->length); - - break; - - default: - ret = -EOPNOTSUPP; - break; - } - - if (ret == 0 && copy_to_user(p->pointer, param, p->length)) - ret = -EFAULT; - - kfree(param); - return ret; -} - -/* copy from net/wireless/wext.c end */ - -int rtw_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) -{ - struct iwreq *wrq = (struct iwreq *)rq; - int ret = 0; - - switch (cmd) { - case RTL_IOCTL_WPA_SUPPLICANT: - ret = wpa_supplicant_ioctl(dev, &wrq->u.data); - break; - case RTL_IOCTL_HOSTAPD: - ret = rtw_hostapd_ioctl(dev, &wrq->u.data); - break; - default: - ret = -EOPNOTSUPP; - break; - } - - return ret; -} diff --git a/drivers/staging/rtl8723bs/os_dep/os_intfs.c b/drivers/staging/rtl8723bs/os_dep/os_intfs.c index 4e1917c05402..738a601c55bb 100644 --- a/drivers/staging/rtl8723bs/os_dep/os_intfs.c +++ b/drivers/staging/rtl8723bs/os_dep/os_intfs.c @@ -407,7 +407,6 @@ static const struct net_device_ops rtw_netdev_ops = { .ndo_select_queue = rtw_select_queue, .ndo_set_mac_address = rtw_net_set_mac_address, .ndo_get_stats = rtw_net_get_stats, - .ndo_do_ioctl = rtw_ioctl, }; int rtw_init_netdev_name(struct net_device *pnetdev, const char *ifname) diff --git a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c index dc0d715ed970..0dbe76ee5570 100644 --- a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c +++ b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c @@ -59,7 +59,7 @@ static int bcm2835_audio_send_msg_locked(struct bcm2835_audio_instance *instance if (wait) { if (!wait_for_completion_timeout(&instance->msg_avail_comp, - msecs_to_jiffies(10 * 1000))) { + secs_to_jiffies(10))) { dev_err(instance->dev, "vchi message timeout, msg=%d\n", m->type); return -ETIMEDOUT; diff --git a/drivers/staging/vme_user/vme_tsi148.c b/drivers/staging/vme_user/vme_tsi148.c index 31a44025e08f..733594dde9ae 100644 --- a/drivers/staging/vme_user/vme_tsi148.c +++ b/drivers/staging/vme_user/vme_tsi148.c @@ -761,8 +761,7 @@ static int tsi148_alloc_resource(struct vme_master_resource *image, goto err_resource; } - image->kern_base = ioremap( - image->bus_resource.start, size); + image->kern_base = ioremap(image->bus_resource.start, size); if (!image->kern_base) { dev_err(tsi148_bridge->parent, "Failed to remap resource\n"); retval = -ENOMEM; diff --git a/drivers/target/iscsi/Kconfig b/drivers/target/iscsi/Kconfig index 922b207bc69d..70d76f3dd693 100644 --- a/drivers/target/iscsi/Kconfig +++ b/drivers/target/iscsi/Kconfig @@ -2,9 +2,9 @@ config ISCSI_TARGET tristate "SCSI Target Mode Stack" depends on INET + select CRC32 select CRYPTO - select CRYPTO_CRC32C - select CRYPTO_CRC32C_INTEL if X86 + select CRYPTO_HASH help Say M to enable the SCSI target mode stack. A SCSI target mode stack is software that makes local storage available over a storage network diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 6002283cbeba..1244ef3aa86c 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -8,7 +8,7 @@ * ******************************************************************************/ -#include +#include #include #include #include @@ -490,8 +490,8 @@ void iscsit_aborted_task(struct iscsit_conn *conn, struct iscsit_cmd *cmd) } EXPORT_SYMBOL(iscsit_aborted_task); -static void iscsit_do_crypto_hash_buf(struct ahash_request *, const void *, - u32, u32, const void *, void *); +static u32 iscsit_crc_buf(const void *buf, u32 payload_length, + u32 padding, const void *pad_bytes); static void iscsit_tx_thread_wait_for_tcp(struct iscsit_conn *); static int @@ -510,9 +510,7 @@ iscsit_xmit_nondatain_pdu(struct iscsit_conn *conn, struct iscsit_cmd *cmd, if (conn->conn_ops->HeaderDigest) { u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN]; - iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr, - ISCSI_HDR_LEN, 0, NULL, - header_digest); + *header_digest = iscsit_crc_buf(hdr, ISCSI_HDR_LEN, 0, NULL); iov[0].iov_len += ISCSI_CRC_LEN; tx_size += ISCSI_CRC_LEN; @@ -537,11 +535,9 @@ iscsit_xmit_nondatain_pdu(struct iscsit_conn *conn, struct iscsit_cmd *cmd, } if (conn->conn_ops->DataDigest) { - iscsit_do_crypto_hash_buf(conn->conn_tx_hash, - data_buf, data_buf_len, - padding, &cmd->pad_bytes, - &cmd->data_crc); - + cmd->data_crc = iscsit_crc_buf(data_buf, data_buf_len, + padding, + &cmd->pad_bytes); iov[niov].iov_base = &cmd->data_crc; iov[niov++].iov_len = ISCSI_CRC_LEN; tx_size += ISCSI_CRC_LEN; @@ -566,8 +562,8 @@ iscsit_xmit_nondatain_pdu(struct iscsit_conn *conn, struct iscsit_cmd *cmd, static int iscsit_map_iovec(struct iscsit_cmd *cmd, struct kvec *iov, int nvec, u32 data_offset, u32 data_length); static void iscsit_unmap_iovec(struct iscsit_cmd *); -static u32 iscsit_do_crypto_hash_sg(struct ahash_request *, struct iscsit_cmd *, - u32, u32, u32, u8 *); +static u32 iscsit_crc_sglist(const struct iscsit_cmd *cmd, u32 data_length, + u32 padding, const u8 *pad_bytes); static int iscsit_xmit_datain_pdu(struct iscsit_conn *conn, struct iscsit_cmd *cmd, const struct iscsi_datain *datain) @@ -584,10 +580,8 @@ iscsit_xmit_datain_pdu(struct iscsit_conn *conn, struct iscsit_cmd *cmd, if (conn->conn_ops->HeaderDigest) { u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN]; - iscsit_do_crypto_hash_buf(conn->conn_tx_hash, cmd->pdu, - ISCSI_HDR_LEN, 0, NULL, - header_digest); - + *header_digest = iscsit_crc_buf(cmd->pdu, ISCSI_HDR_LEN, 0, + NULL); iov[0].iov_len += ISCSI_CRC_LEN; tx_size += ISCSI_CRC_LEN; @@ -614,12 +608,8 @@ iscsit_xmit_datain_pdu(struct iscsit_conn *conn, struct iscsit_cmd *cmd, } if (conn->conn_ops->DataDigest) { - cmd->data_crc = iscsit_do_crypto_hash_sg(conn->conn_tx_hash, - cmd, datain->offset, - datain->length, - cmd->padding, - cmd->pad_bytes); - + cmd->data_crc = iscsit_crc_sglist(cmd, datain->length, + cmd->padding, cmd->pad_bytes); iov[iov_count].iov_base = &cmd->data_crc; iov[iov_count++].iov_len = ISCSI_CRC_LEN; tx_size += ISCSI_CRC_LEN; @@ -1404,77 +1394,45 @@ iscsit_handle_scsi_cmd(struct iscsit_conn *conn, struct iscsit_cmd *cmd, return iscsit_get_immediate_data(cmd, hdr, dump_payload); } -static u32 iscsit_do_crypto_hash_sg( - struct ahash_request *hash, - struct iscsit_cmd *cmd, - u32 data_offset, - u32 data_length, - u32 padding, - u8 *pad_bytes) +static u32 iscsit_crc_sglist(const struct iscsit_cmd *cmd, u32 data_length, + u32 padding, const u8 *pad_bytes) { - u32 data_crc; - struct scatterlist *sg; - unsigned int page_off; - - crypto_ahash_init(hash); - - sg = cmd->first_data_sg; - page_off = cmd->first_data_sg_off; - - if (data_length && page_off) { - struct scatterlist first_sg; - u32 len = min_t(u32, data_length, sg->length - page_off); - - sg_init_table(&first_sg, 1); - sg_set_page(&first_sg, sg_page(sg), len, sg->offset + page_off); - - ahash_request_set_crypt(hash, &first_sg, NULL, len); - crypto_ahash_update(hash); - - data_length -= len; - sg = sg_next(sg); - } + struct scatterlist *sg = cmd->first_data_sg; + unsigned int page_off = cmd->first_data_sg_off; + u32 crc = ~0; while (data_length) { - u32 cur_len = min_t(u32, data_length, sg->length); + u32 cur_len = min_t(u32, data_length, sg->length - page_off); + const void *virt; - ahash_request_set_crypt(hash, sg, NULL, cur_len); - crypto_ahash_update(hash); + virt = kmap_local_page(sg_page(sg)) + sg->offset + page_off; + crc = crc32c(crc, virt, cur_len); + kunmap_local(virt); - data_length -= cur_len; /* iscsit_map_iovec has already checked for invalid sg pointers */ sg = sg_next(sg); + + page_off = 0; + data_length -= cur_len; } - if (padding) { - struct scatterlist pad_sg; + if (padding) + crc = crc32c(crc, pad_bytes, padding); - sg_init_one(&pad_sg, pad_bytes, padding); - ahash_request_set_crypt(hash, &pad_sg, (u8 *)&data_crc, - padding); - crypto_ahash_finup(hash); - } else { - ahash_request_set_crypt(hash, NULL, (u8 *)&data_crc, 0); - crypto_ahash_final(hash); - } - - return data_crc; + return ~crc; } -static void iscsit_do_crypto_hash_buf(struct ahash_request *hash, - const void *buf, u32 payload_length, u32 padding, - const void *pad_bytes, void *data_crc) +static u32 iscsit_crc_buf(const void *buf, u32 payload_length, + u32 padding, const void *pad_bytes) { - struct scatterlist sg[2]; + u32 crc = ~0; + + crc = crc32c(crc, buf, payload_length); - sg_init_table(sg, ARRAY_SIZE(sg)); - sg_set_buf(sg, buf, payload_length); if (padding) - sg_set_buf(sg + 1, pad_bytes, padding); + crc = crc32c(crc, pad_bytes, padding); - ahash_request_set_crypt(hash, sg, data_crc, payload_length + padding); - - crypto_ahash_digest(hash); + return ~crc; } int @@ -1662,11 +1620,8 @@ iscsit_get_dataout(struct iscsit_conn *conn, struct iscsit_cmd *cmd, if (conn->conn_ops->DataDigest) { u32 data_crc; - data_crc = iscsit_do_crypto_hash_sg(conn->conn_rx_hash, cmd, - be32_to_cpu(hdr->offset), - payload_length, padding, - cmd->pad_bytes); - + data_crc = iscsit_crc_sglist(cmd, payload_length, padding, + cmd->pad_bytes); if (checksum != data_crc) { pr_err("ITT: 0x%08x, Offset: %u, Length: %u," " DataSN: 0x%08x, CRC32C DataDigest 0x%08x" @@ -1925,10 +1880,8 @@ static int iscsit_handle_nop_out(struct iscsit_conn *conn, struct iscsit_cmd *cm } if (conn->conn_ops->DataDigest) { - iscsit_do_crypto_hash_buf(conn->conn_rx_hash, ping_data, - payload_length, padding, - cmd->pad_bytes, &data_crc); - + data_crc = iscsit_crc_buf(ping_data, payload_length, + padding, cmd->pad_bytes); if (checksum != data_crc) { pr_err("Ping data CRC32C DataDigest" " 0x%08x does not match computed 0x%08x\n", @@ -2328,10 +2281,7 @@ iscsit_handle_text_cmd(struct iscsit_conn *conn, struct iscsit_cmd *cmd, goto reject; if (conn->conn_ops->DataDigest) { - iscsit_do_crypto_hash_buf(conn->conn_rx_hash, - text_in, rx_size, 0, NULL, - &data_crc); - + data_crc = iscsit_crc_buf(text_in, rx_size, 0, NULL); if (checksum != data_crc) { pr_err("Text data CRC32C DataDigest" " 0x%08x does not match computed" @@ -2688,10 +2638,8 @@ static int iscsit_handle_immediate_data( if (conn->conn_ops->DataDigest) { u32 data_crc; - data_crc = iscsit_do_crypto_hash_sg(conn->conn_rx_hash, cmd, - cmd->write_data_done, length, padding, - cmd->pad_bytes); - + data_crc = iscsit_crc_sglist(cmd, length, padding, + cmd->pad_bytes); if (checksum != data_crc) { pr_err("ImmediateData CRC32C DataDigest 0x%08x" " does not match computed 0x%08x\n", checksum, @@ -4116,10 +4064,8 @@ static void iscsit_get_rx_pdu(struct iscsit_conn *conn) break; } - iscsit_do_crypto_hash_buf(conn->conn_rx_hash, buffer, - ISCSI_HDR_LEN, 0, NULL, - &checksum); - + checksum = iscsit_crc_buf(buffer, ISCSI_HDR_LEN, 0, + NULL); if (digest != checksum) { pr_err("HeaderDigest CRC32C failed," " received 0x%08x, computed 0x%08x\n", @@ -4406,15 +4352,6 @@ int iscsit_close_connection( */ iscsit_check_conn_usage_count(conn); - ahash_request_free(conn->conn_tx_hash); - if (conn->conn_rx_hash) { - struct crypto_ahash *tfm; - - tfm = crypto_ahash_reqtfm(conn->conn_rx_hash); - ahash_request_free(conn->conn_rx_hash); - crypto_free_ahash(tfm); - } - if (conn->sock) sock_release(conn->sock); @@ -4727,21 +4664,6 @@ int iscsit_logout_post_handler( } EXPORT_SYMBOL(iscsit_logout_post_handler); -void iscsit_fail_session(struct iscsit_session *sess) -{ - struct iscsit_conn *conn; - - spin_lock_bh(&sess->conn_lock); - list_for_each_entry(conn, &sess->sess_conn_list, conn_list) { - pr_debug("Moving to TARG_CONN_STATE_CLEANUP_WAIT.\n"); - conn->conn_state = TARG_CONN_STATE_CLEANUP_WAIT; - } - spin_unlock_bh(&sess->conn_lock); - - pr_debug("Moving to TARG_SESS_STATE_FAILED.\n"); - sess->session_state = TARG_SESS_STATE_FAILED; -} - void iscsit_stop_session( struct iscsit_session *sess, int session_sleep, diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h index 873411e95ed2..f4addae2aae4 100644 --- a/drivers/target/iscsi/iscsi_target.h +++ b/drivers/target/iscsi/iscsi_target.h @@ -40,7 +40,6 @@ extern int iscsi_target_tx_thread(void *); extern int iscsi_target_rx_thread(void *); extern int iscsit_close_connection(struct iscsit_conn *); extern int iscsit_close_session(struct iscsit_session *, bool can_sleep); -extern void iscsit_fail_session(struct iscsit_session *); extern void iscsit_stop_session(struct iscsit_session *, int, int); extern int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *, int); diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c index 18e88d2ea5fd..56d78af7cec7 100644 --- a/drivers/target/iscsi/iscsi_target_erl2.c +++ b/drivers/target/iscsi/iscsi_target_erl2.c @@ -25,54 +25,6 @@ /* * FIXME: Does RData SNACK apply here as well? */ -void iscsit_create_conn_recovery_datain_values( - struct iscsit_cmd *cmd, - __be32 exp_data_sn) -{ - u32 data_sn = 0; - struct iscsit_conn *conn = cmd->conn; - - cmd->next_burst_len = 0; - cmd->read_data_done = 0; - - while (be32_to_cpu(exp_data_sn) > data_sn) { - if ((cmd->next_burst_len + - conn->conn_ops->MaxRecvDataSegmentLength) < - conn->sess->sess_ops->MaxBurstLength) { - cmd->read_data_done += - conn->conn_ops->MaxRecvDataSegmentLength; - cmd->next_burst_len += - conn->conn_ops->MaxRecvDataSegmentLength; - } else { - cmd->read_data_done += - (conn->sess->sess_ops->MaxBurstLength - - cmd->next_burst_len); - cmd->next_burst_len = 0; - } - data_sn++; - } -} - -void iscsit_create_conn_recovery_dataout_values( - struct iscsit_cmd *cmd) -{ - u32 write_data_done = 0; - struct iscsit_conn *conn = cmd->conn; - - cmd->data_sn = 0; - cmd->next_burst_len = 0; - - while (cmd->write_data_done > write_data_done) { - if ((write_data_done + conn->sess->sess_ops->MaxBurstLength) <= - cmd->write_data_done) - write_data_done += conn->sess->sess_ops->MaxBurstLength; - else - break; - } - - cmd->write_data_done = write_data_done; -} - static int iscsit_attach_active_connection_recovery_entry( struct iscsit_session *sess, struct iscsi_conn_recovery *cr) diff --git a/drivers/target/iscsi/iscsi_target_erl2.h b/drivers/target/iscsi/iscsi_target_erl2.h index 6655e4bcf893..9064c74eef7a 100644 --- a/drivers/target/iscsi/iscsi_target_erl2.h +++ b/drivers/target/iscsi/iscsi_target_erl2.h @@ -9,8 +9,6 @@ struct iscsit_conn; struct iscsi_conn_recovery; struct iscsit_session; -extern void iscsit_create_conn_recovery_datain_values(struct iscsit_cmd *, __be32); -extern void iscsit_create_conn_recovery_dataout_values(struct iscsit_cmd *); extern struct iscsi_conn_recovery *iscsit_get_inactive_connection_recovery_entry( struct iscsit_session *, u16); extern void iscsit_free_connection_recovery_entries(struct iscsit_session *); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 90b870f234f0..c2ac9a99ebbb 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -8,7 +8,6 @@ * ******************************************************************************/ -#include #include #include #include @@ -71,46 +70,6 @@ out_login: return NULL; } -/* - * Used by iscsi_target_nego.c:iscsi_target_locate_portal() to setup - * per struct iscsit_conn libcrypto contexts for crc32c and crc32-intel - */ -int iscsi_login_setup_crypto(struct iscsit_conn *conn) -{ - struct crypto_ahash *tfm; - - /* - * Setup slicing by CRC32C algorithm for RX and TX libcrypto contexts - * which will default to crc32c_intel.ko for cpu_has_xmm4_2, or fallback - * to software 1x8 byte slicing from crc32c.ko - */ - tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) { - pr_err("crypto_alloc_ahash() failed\n"); - return -ENOMEM; - } - - conn->conn_rx_hash = ahash_request_alloc(tfm, GFP_KERNEL); - if (!conn->conn_rx_hash) { - pr_err("ahash_request_alloc() failed for conn_rx_hash\n"); - crypto_free_ahash(tfm); - return -ENOMEM; - } - ahash_request_set_callback(conn->conn_rx_hash, 0, NULL, NULL); - - conn->conn_tx_hash = ahash_request_alloc(tfm, GFP_KERNEL); - if (!conn->conn_tx_hash) { - pr_err("ahash_request_alloc() failed for conn_tx_hash\n"); - ahash_request_free(conn->conn_rx_hash); - conn->conn_rx_hash = NULL; - crypto_free_ahash(tfm); - return -ENOMEM; - } - ahash_request_set_callback(conn->conn_tx_hash, 0, NULL, NULL); - - return 0; -} - static int iscsi_login_check_initiator_version( struct iscsit_conn *conn, u8 version_max, @@ -1165,15 +1124,6 @@ old_sess_out: iscsit_dec_session_usage_count(conn->sess); } - ahash_request_free(conn->conn_tx_hash); - if (conn->conn_rx_hash) { - struct crypto_ahash *tfm; - - tfm = crypto_ahash_reqtfm(conn->conn_rx_hash); - ahash_request_free(conn->conn_rx_hash); - crypto_free_ahash(tfm); - } - if (conn->param_list) { iscsi_release_param_list(conn->param_list); conn->param_list = NULL; diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h index e8760735486b..03c7d695d58f 100644 --- a/drivers/target/iscsi/iscsi_target_login.h +++ b/drivers/target/iscsi/iscsi_target_login.h @@ -9,7 +9,6 @@ struct iscsi_login; struct iscsi_np; struct sockaddr_storage; -extern int iscsi_login_setup_crypto(struct iscsit_conn *); extern int iscsi_check_for_session_reinstatement(struct iscsit_conn *); extern int iscsi_login_post_auth_non_zero_tsih(struct iscsit_conn *, u16, u32); extern int iscsit_setup_np(struct iscsi_np *, diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index fa3fb5f4e6bc..16e3ded98c32 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -1194,14 +1194,7 @@ int iscsi_target_locate_portal( goto get_target; sess->sess_ops->SessionType = 1; - /* - * Setup crc32c modules from libcrypto - */ - if (iscsi_login_setup_crypto(conn) < 0) { - pr_err("iscsi_login_setup_crypto() failed\n"); - ret = -1; - goto out; - } + /* * Serialize access across the discovery struct iscsi_portal_group to * process login attempt. @@ -1258,17 +1251,7 @@ get_target: } conn->tpg_np = tpg_np; pr_debug("Located Portal Group Object: %hu\n", conn->tpg->tpgt); - /* - * Setup crc32c modules from libcrypto - */ - if (iscsi_login_setup_crypto(conn) < 0) { - pr_err("iscsi_login_setup_crypto() failed\n"); - kref_put(&tpg_np->tpg_np_kref, iscsit_login_kref_put); - iscsit_put_tiqn_for_login(tiqn); - conn->tpg = NULL; - ret = -1; - goto out; - } + /* * Serialize access across the struct iscsi_portal_group to * process login attempt. diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index 5b90c22ee3dc..1d4e1788e073 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -67,54 +67,6 @@ int iscsi_login_tx_data( return 0; } -void iscsi_dump_conn_ops(struct iscsi_conn_ops *conn_ops) -{ - pr_debug("HeaderDigest: %s\n", (conn_ops->HeaderDigest) ? - "CRC32C" : "None"); - pr_debug("DataDigest: %s\n", (conn_ops->DataDigest) ? - "CRC32C" : "None"); - pr_debug("MaxRecvDataSegmentLength: %u\n", - conn_ops->MaxRecvDataSegmentLength); -} - -void iscsi_dump_sess_ops(struct iscsi_sess_ops *sess_ops) -{ - pr_debug("InitiatorName: %s\n", sess_ops->InitiatorName); - pr_debug("InitiatorAlias: %s\n", sess_ops->InitiatorAlias); - pr_debug("TargetName: %s\n", sess_ops->TargetName); - pr_debug("TargetAlias: %s\n", sess_ops->TargetAlias); - pr_debug("TargetPortalGroupTag: %hu\n", - sess_ops->TargetPortalGroupTag); - pr_debug("MaxConnections: %hu\n", sess_ops->MaxConnections); - pr_debug("InitialR2T: %s\n", - (sess_ops->InitialR2T) ? "Yes" : "No"); - pr_debug("ImmediateData: %s\n", (sess_ops->ImmediateData) ? - "Yes" : "No"); - pr_debug("MaxBurstLength: %u\n", sess_ops->MaxBurstLength); - pr_debug("FirstBurstLength: %u\n", sess_ops->FirstBurstLength); - pr_debug("DefaultTime2Wait: %hu\n", sess_ops->DefaultTime2Wait); - pr_debug("DefaultTime2Retain: %hu\n", - sess_ops->DefaultTime2Retain); - pr_debug("MaxOutstandingR2T: %hu\n", - sess_ops->MaxOutstandingR2T); - pr_debug("DataPDUInOrder: %s\n", - (sess_ops->DataPDUInOrder) ? "Yes" : "No"); - pr_debug("DataSequenceInOrder: %s\n", - (sess_ops->DataSequenceInOrder) ? "Yes" : "No"); - pr_debug("ErrorRecoveryLevel: %hu\n", - sess_ops->ErrorRecoveryLevel); - pr_debug("SessionType: %s\n", (sess_ops->SessionType) ? - "Discovery" : "Normal"); -} - -void iscsi_print_params(struct iscsi_param_list *param_list) -{ - struct iscsi_param *param; - - list_for_each_entry(param, ¶m_list->param_list, p_list) - pr_debug("%s: %s\n", param->name, param->value); -} - static struct iscsi_param *iscsi_set_default_param(struct iscsi_param_list *param_list, char *name, char *value, u8 phase, u8 scope, u8 sender, u16 type_range, u8 use) diff --git a/drivers/target/iscsi/iscsi_target_parameters.h b/drivers/target/iscsi/iscsi_target_parameters.h index 00fbbebb8c75..c672a971fcb7 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.h +++ b/drivers/target/iscsi/iscsi_target_parameters.h @@ -32,9 +32,6 @@ struct iscsi_sess_ops; extern int iscsi_login_rx_data(struct iscsit_conn *, char *, int); extern int iscsi_login_tx_data(struct iscsit_conn *, char *, char *, int); -extern void iscsi_dump_conn_ops(struct iscsi_conn_ops *); -extern void iscsi_dump_sess_ops(struct iscsi_sess_ops *); -extern void iscsi_print_params(struct iscsi_param_list *); extern int iscsi_create_default_params(struct iscsi_param_list **); extern int iscsi_set_keys_to_negotiate(struct iscsi_param_list *, bool); extern int iscsi_set_keys_irrelevant_for_discovery(struct iscsi_param_list *); diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index f7bac98fd4fe..bf06cfdfb012 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -200,11 +200,6 @@ static void iscsit_clear_tpg_np_login_threads( spin_unlock(&tpg->tpg_np_lock); } -void iscsit_tpg_dump_params(struct iscsi_portal_group *tpg) -{ - iscsi_print_params(tpg->param_list); -} - static void iscsit_set_default_tpg_attribs(struct iscsi_portal_group *tpg) { struct iscsi_tpg_attrib *a = &tpg->tpg_attrib; diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h index d44d09f2dde9..1155b7b3164a 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.h +++ b/drivers/target/iscsi/iscsi_target_tpg.h @@ -18,7 +18,6 @@ extern struct iscsi_portal_group *iscsit_get_tpg_from_np(struct iscsi_tiqn *, struct iscsi_np *, struct iscsi_tpg_np **); extern int iscsit_get_tpg(struct iscsi_portal_group *); extern void iscsit_put_tpg(struct iscsi_portal_group *); -extern void iscsit_tpg_dump_params(struct iscsi_portal_group *); extern int iscsit_tpg_add_portal_group(struct iscsi_tiqn *, struct iscsi_portal_group *); extern int iscsit_tpg_del_portal_group(struct iscsi_tiqn *, struct iscsi_portal_group *, int); diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 91a75a4a7cc1..ed2dadb21f75 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -333,50 +333,6 @@ int iscsit_sequence_cmd(struct iscsit_conn *conn, struct iscsit_cmd *cmd, } EXPORT_SYMBOL(iscsit_sequence_cmd); -int iscsit_check_unsolicited_dataout(struct iscsit_cmd *cmd, unsigned char *buf) -{ - struct iscsit_conn *conn = cmd->conn; - struct se_cmd *se_cmd = &cmd->se_cmd; - struct iscsi_data *hdr = (struct iscsi_data *) buf; - u32 payload_length = ntoh24(hdr->dlength); - - if (conn->sess->sess_ops->InitialR2T) { - pr_err("Received unexpected unsolicited data" - " while InitialR2T=Yes, protocol error.\n"); - transport_send_check_condition_and_sense(se_cmd, - TCM_UNEXPECTED_UNSOLICITED_DATA, 0); - return -1; - } - - if ((cmd->first_burst_len + payload_length) > - conn->sess->sess_ops->FirstBurstLength) { - pr_err("Total %u bytes exceeds FirstBurstLength: %u" - " for this Unsolicited DataOut Burst.\n", - (cmd->first_burst_len + payload_length), - conn->sess->sess_ops->FirstBurstLength); - transport_send_check_condition_and_sense(se_cmd, - TCM_INCORRECT_AMOUNT_OF_DATA, 0); - return -1; - } - - if (!(hdr->flags & ISCSI_FLAG_CMD_FINAL)) - return 0; - - if (((cmd->first_burst_len + payload_length) != cmd->se_cmd.data_length) && - ((cmd->first_burst_len + payload_length) != - conn->sess->sess_ops->FirstBurstLength)) { - pr_err("Unsolicited non-immediate data received %u" - " does not equal FirstBurstLength: %u, and does" - " not equal ExpXferLen %u.\n", - (cmd->first_burst_len + payload_length), - conn->sess->sess_ops->FirstBurstLength, cmd->se_cmd.data_length); - transport_send_check_condition_and_sense(se_cmd, - TCM_INCORRECT_AMOUNT_OF_DATA, 0); - return -1; - } - return 0; -} - struct iscsit_cmd *iscsit_find_cmd_from_itt( struct iscsit_conn *conn, itt_t init_task_tag) @@ -1252,20 +1208,6 @@ int iscsit_tx_login_rsp(struct iscsit_conn *conn, u8 status_class, u8 status_det return conn->conn_transport->iscsit_put_login_tx(conn, login, 0); } -void iscsit_print_session_params(struct iscsit_session *sess) -{ - struct iscsit_conn *conn; - - pr_debug("-----------------------------[Session Params for" - " SID: %u]-----------------------------\n", sess->sid); - spin_lock_bh(&sess->conn_lock); - list_for_each_entry(conn, &sess->sess_conn_list, conn_list) - iscsi_dump_conn_ops(conn->conn_ops); - spin_unlock_bh(&sess->conn_lock); - - iscsi_dump_sess_ops(sess->sess_ops); -} - int rx_data( struct iscsit_conn *conn, struct kvec *iov, diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h index 336da4fb0a77..7ae48a8a5cbf 100644 --- a/drivers/target/iscsi/iscsi_target_util.h +++ b/drivers/target/iscsi/iscsi_target_util.h @@ -23,7 +23,6 @@ extern struct iscsi_seq *iscsit_get_seq_holder_for_r2t(struct iscsit_cmd *); extern struct iscsi_r2t *iscsit_get_holder_for_r2tsn(struct iscsit_cmd *, u32); extern int iscsit_sequence_cmd(struct iscsit_conn *conn, struct iscsit_cmd *cmd, unsigned char * ,__be32 cmdsn); -extern int iscsit_check_unsolicited_dataout(struct iscsit_cmd *, unsigned char *); extern struct iscsit_cmd *iscsit_find_cmd_from_itt_or_dump(struct iscsit_conn *, itt_t, u32); extern struct iscsit_cmd *iscsit_find_cmd_from_ttt(struct iscsit_conn *, u32); @@ -61,7 +60,6 @@ extern int iscsit_set_login_timer_kworker(struct iscsit_conn *, struct task_stru extern int iscsit_send_tx_data(struct iscsit_cmd *, struct iscsit_conn *, int); extern int iscsit_fe_sendpage_sg(struct iscsit_cmd *, struct iscsit_conn *); extern int iscsit_tx_login_rsp(struct iscsit_conn *, u8, u8); -extern void iscsit_print_session_params(struct iscsit_session *); extern int rx_data(struct iscsit_conn *, struct kvec *, int, int); extern int tx_data(struct iscsit_conn *, struct kvec *, int, int); extern void iscsit_collect_login_stats(struct iscsit_conn *, u8, u8); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 287ac5b0495f..f991cf759836 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -823,7 +823,6 @@ static sense_reason_t pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, struct request *req) { - struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev); struct bio *bio = NULL; struct page *page; struct scatterlist *sg; @@ -871,12 +870,11 @@ new_bio: (rw) ? "rw" : "r", nr_vecs); } - pr_debug("PSCSI: Calling bio_add_pc_page() i: %d" + pr_debug("PSCSI: Calling bio_add_page() i: %d" " bio: %p page: %p len: %d off: %d\n", i, bio, page, len, off); - rc = bio_add_pc_page(pdv->pdv_sd->request_queue, - bio, page, bytes, off); + rc = bio_add_page(bio, page, bytes, off); pr_debug("PSCSI: bio->bi_vcnt: %d nr_vecs: %d\n", bio_segments(bio), nr_vecs); if (rc != bytes) { diff --git a/drivers/tee/optee/smc_abi.c b/drivers/tee/optee/smc_abi.c index 3e33cf2af73b..f0c3ac1103bb 100644 --- a/drivers/tee/optee/smc_abi.c +++ b/drivers/tee/optee/smc_abi.c @@ -1272,8 +1272,9 @@ static void optee_msg_get_os_revision(optee_invoke_fn *invoke_fn) &res.smccc); if (res.result.build_id) - pr_info("revision %lu.%lu (%08lx)", res.result.major, - res.result.minor, res.result.build_id); + pr_info("revision %lu.%lu (%0*lx)", res.result.major, + res.result.minor, (int)sizeof(res.result.build_id) * 2, + res.result.build_id); else pr_info("revision %lu.%lu", res.result.major, res.result.minor); } diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index 97f3d819852b..51951967d67f 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -7,6 +7,27 @@ * Based on step_wise.c with following Copyrights: * Copyright (C) 2012 Intel Corp * Copyright (C) 2012 Durgadoss R + * + * Regulation Logic: a two point regulation, deliver cooling state depending + * on the previous state shown in this diagram: + * + * Fan: OFF ON + * + * | + * | + * trip_temp: +---->+ + * | | ^ + * | | | + * | | Temperature + * (trip_temp - hyst): +<----+ + * | + * | + * | + * + * * If the fan is not running and temperature exceeds trip_temp, the fan + * gets turned on. + * * In case the fan is running, temperature must fall below + * (trip_temp - hyst) so that the fan gets turned off again. */ #include @@ -34,36 +55,14 @@ static void bang_bang_set_instance_target(struct thermal_instance *instance, } /** - * bang_bang_control - controls devices associated with the given zone + * bang_bang_trip_crossed - controls devices associated with the given zone * @tz: thermal_zone_device * @trip: the trip point - * @crossed_up: whether or not the trip has been crossed on the way up - * - * Regulation Logic: a two point regulation, deliver cooling state depending - * on the previous state shown in this diagram: - * - * Fan: OFF ON - * - * | - * | - * trip_temp: +---->+ - * | | ^ - * | | | - * | | Temperature - * (trip_temp - hyst): +<----+ - * | - * | - * | - * - * * If the fan is not running and temperature exceeds trip_temp, the fan - * gets turned on. - * * In case the fan is running, temperature must fall below - * (trip_temp - hyst) so that the fan gets turned off again. - * + * @upward: whether or not the trip has been crossed on the way up */ -static void bang_bang_control(struct thermal_zone_device *tz, - const struct thermal_trip *trip, - bool crossed_up) +static void bang_bang_trip_crossed(struct thermal_zone_device *tz, + const struct thermal_trip *trip, + bool upward) { const struct thermal_trip_desc *td = trip_to_trip_desc(trip); struct thermal_instance *instance; @@ -75,7 +74,7 @@ static void bang_bang_control(struct thermal_zone_device *tz, tz->temperature, trip->hysteresis); list_for_each_entry(instance, &td->thermal_instances, trip_node) - bang_bang_set_instance_target(instance, crossed_up); + bang_bang_set_instance_target(instance, upward); } static void bang_bang_manage(struct thermal_zone_device *tz) @@ -123,7 +122,7 @@ static void bang_bang_update_tz(struct thermal_zone_device *tz, static struct thermal_governor thermal_gov_bang_bang = { .name = "bang_bang", - .trip_crossed = bang_bang_control, + .trip_crossed = bang_bang_trip_crossed, .manage = bang_bang_manage, .update_tz = bang_bang_update_tz, }; diff --git a/drivers/thermal/gov_user_space.c b/drivers/thermal/gov_user_space.c index 75137b419eb2..ef95cf7d65ef 100644 --- a/drivers/thermal/gov_user_space.c +++ b/drivers/thermal/gov_user_space.c @@ -23,16 +23,16 @@ static int user_space_bind(struct thermal_zone_device *tz) } /** - * notify_user_space - Notifies user space about thermal events + * user_space_trip_crossed - Notify user space about trip crossing events * @tz: thermal_zone_device * @trip: trip point - * @crossed_up: whether or not the trip has been crossed on the way up + * @upward: whether or not the trip has been crossed on the way up * * This function notifies the user space through UEvents. */ -static void notify_user_space(struct thermal_zone_device *tz, - const struct thermal_trip *trip, - bool crossed_up) +static void user_space_trip_crossed(struct thermal_zone_device *tz, + const struct thermal_trip *trip, + bool upward) { char *thermal_prop[5]; int i; @@ -52,7 +52,7 @@ static void notify_user_space(struct thermal_zone_device *tz, static struct thermal_governor thermal_gov_user_space = { .name = "user_space", - .trip_crossed = notify_user_space, + .trip_crossed = user_space_trip_crossed, .bind_to_tz = user_space_bind, }; THERMAL_GOVERNOR_DECLARE(thermal_gov_user_space); diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig index a31f2f32996a..e0268fac7093 100644 --- a/drivers/thermal/intel/Kconfig +++ b/drivers/thermal/intel/Kconfig @@ -21,8 +21,8 @@ config INTEL_TCC config X86_PKG_TEMP_THERMAL tristate "X86 package temperature thermal driver" - depends on X86_THERMAL_VECTOR - select THERMAL_GOV_USER_SPACE + depends on X86_THERMAL_VECTOR && NET + select THERMAL_NETLINK select INTEL_TCC default m help diff --git a/drivers/thermal/intel/int340x_thermal/Kconfig b/drivers/thermal/intel/int340x_thermal/Kconfig index e76b13e44d03..4c699f0896b5 100644 --- a/drivers/thermal/intel/int340x_thermal/Kconfig +++ b/drivers/thermal/intel/int340x_thermal/Kconfig @@ -5,8 +5,8 @@ config INT340X_THERMAL tristate "ACPI INT340X thermal drivers" - depends on X86_64 && ACPI && PCI - select THERMAL_GOV_USER_SPACE + depends on X86_64 && ACPI && PCI && NET + select THERMAL_NETLINK select ACPI_THERMAL_REL select ACPI_FAN select ACPI_THERMAL_LIB diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 8660ef2175be..0e07693ecf59 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -521,7 +521,6 @@ static struct thermal_zone_device_ops int3400_thermal_ops = { }; static struct thermal_zone_params int3400_thermal_params = { - .governor_name = "user_space", .no_hwmon = true, }; @@ -690,6 +689,7 @@ static const struct acpi_device_id int3400_thermal_match[] = { {"INTC1042", 0}, {"INTC1068", 0}, {"INTC10A0", 0}, + {"INTC10D4", 0}, {} }; diff --git a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c index 04aa0afb3b1d..5a925a8df7b3 100644 --- a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c @@ -275,6 +275,7 @@ static const struct acpi_device_id int3403_device_ids[] = { {"INTC1062", 0}, {"INTC1069", 0}, {"INTC10A1", 0}, + {"INTC10D5", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, int3403_device_ids); diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c index 31ed338eb83c..8dca6a6aceca 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c @@ -105,7 +105,6 @@ static int int340x_thermal_read_trips(struct acpi_device *zone_adev, } static struct thermal_zone_params int340x_thermal_params = { - .governor_name = "user_space", .no_hwmon = true, }; diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h index d5eca6db2c00..ba2d89d3024c 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h @@ -30,6 +30,7 @@ #define PCI_DEVICE_ID_INTEL_RPL_THERMAL 0xA71D #define PCI_DEVICE_ID_INTEL_SKL_THERMAL 0x1903 #define PCI_DEVICE_ID_INTEL_TGL_THERMAL 0x9A03 +#define PCI_DEVICE_ID_INTEL_PTL_THERMAL 0xB01D struct power_config { u32 index; diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c index 145d471546d5..a55aaa8cef42 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c @@ -272,7 +272,6 @@ static const struct thermal_zone_device_ops tzone_ops = { }; static struct thermal_zone_params tzone_params = { - .governor_name = "user_space", .no_hwmon = true, }; @@ -495,6 +494,9 @@ static const struct pci_device_id proc_thermal_pci_ids[] = { PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_WT_HINT) }, { PCI_DEVICE_DATA(INTEL, RPL_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) }, + { PCI_DEVICE_DATA(INTEL, PTL_THERMAL, PROC_THERMAL_FEATURE_RAPL | + PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_MSI_SUPPORT | + PROC_THERMAL_FEATURE_WT_HINT | PROC_THERMAL_FEATURE_POWER_FLOOR) }, { }, }; diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 19a3894ad752..2328ac0d8561 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -453,23 +453,23 @@ static void move_to_trips_invalid(struct thermal_zone_device *tz, static void thermal_governor_trip_crossed(struct thermal_governor *governor, struct thermal_zone_device *tz, const struct thermal_trip *trip, - bool crossed_up) + bool upward) { if (trip->type == THERMAL_TRIP_HOT || trip->type == THERMAL_TRIP_CRITICAL) return; if (governor->trip_crossed) - governor->trip_crossed(tz, trip, crossed_up); + governor->trip_crossed(tz, trip, upward); } static void thermal_trip_crossed(struct thermal_zone_device *tz, struct thermal_trip_desc *td, struct thermal_governor *governor, - bool crossed_up) + bool upward) { const struct thermal_trip *trip = &td->trip; - if (crossed_up) { + if (upward) { if (trip->type == THERMAL_TRIP_PASSIVE) tz->passive++; else if (trip->type == THERMAL_TRIP_CRITICAL || @@ -486,7 +486,7 @@ static void thermal_trip_crossed(struct thermal_zone_device *tz, thermal_notify_tz_trip_down(tz, trip); thermal_debug_tz_trip_down(tz, trip); } - thermal_governor_trip_crossed(governor, tz, trip, crossed_up); + thermal_governor_trip_crossed(governor, tz, trip, upward); } void thermal_zone_set_trip_hyst(struct thermal_zone_device *tz, diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h index be271e7c8f41..09866f0ce765 100644 --- a/drivers/thermal/thermal_core.h +++ b/drivers/thermal/thermal_core.h @@ -56,7 +56,7 @@ struct thermal_governor { void (*unbind_from_tz)(struct thermal_zone_device *tz); void (*trip_crossed)(struct thermal_zone_device *tz, const struct thermal_trip *trip, - bool crossed_up); + bool upward); void (*manage)(struct thermal_zone_device *tz); void (*update_tz)(struct thermal_zone_device *tz, enum thermal_notify_event reason); diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index fab11b98ca49..5ab4ce4daaeb 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -160,6 +160,7 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int return ERR_PTR(ret); } + of_node_put(sensor_specs.np); if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ? sensor_specs.args[0] : 0)) { pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, child); diff --git a/drivers/thermal/thermal_thresholds.c b/drivers/thermal/thermal_thresholds.c index d9b2a0bb44fc..38f5fd0e8930 100644 --- a/drivers/thermal/thermal_thresholds.c +++ b/drivers/thermal/thermal_thresholds.c @@ -69,40 +69,18 @@ static struct user_threshold *__thermal_thresholds_find(const struct list_head * return NULL; } -static bool __thermal_threshold_is_crossed(struct user_threshold *threshold, int temperature, - int last_temperature, int direction, - int *low, int *high) -{ - - if (temperature >= threshold->temperature) { - if (threshold->temperature > *low && - THERMAL_THRESHOLD_WAY_DOWN & threshold->direction) - *low = threshold->temperature; - - if (last_temperature < threshold->temperature && - threshold->direction & direction) - return true; - } else { - if (threshold->temperature < *high && THERMAL_THRESHOLD_WAY_UP - & threshold->direction) - *high = threshold->temperature; - - if (last_temperature >= threshold->temperature && - threshold->direction & direction) - return true; - } - - return false; -} - static bool thermal_thresholds_handle_raising(struct list_head *thresholds, int temperature, - int last_temperature, int *low, int *high) + int last_temperature) { struct user_threshold *t; list_for_each_entry(t, thresholds, list_node) { - if (__thermal_threshold_is_crossed(t, temperature, last_temperature, - THERMAL_THRESHOLD_WAY_UP, low, high)) + + if (!(t->direction & THERMAL_THRESHOLD_WAY_UP)) + continue; + + if (temperature >= t->temperature && + last_temperature < t->temperature) return true; } @@ -110,19 +88,43 @@ static bool thermal_thresholds_handle_raising(struct list_head *thresholds, int } static bool thermal_thresholds_handle_dropping(struct list_head *thresholds, int temperature, - int last_temperature, int *low, int *high) + int last_temperature) { struct user_threshold *t; list_for_each_entry_reverse(t, thresholds, list_node) { - if (__thermal_threshold_is_crossed(t, temperature, last_temperature, - THERMAL_THRESHOLD_WAY_DOWN, low, high)) + + if (!(t->direction & THERMAL_THRESHOLD_WAY_DOWN)) + continue; + + if (temperature <= t->temperature && + last_temperature > t->temperature) return true; } return false; } +static void thermal_threshold_find_boundaries(struct list_head *thresholds, int temperature, + int *low, int *high) +{ + struct user_threshold *t; + + list_for_each_entry(t, thresholds, list_node) { + if (temperature < t->temperature && + (t->direction & THERMAL_THRESHOLD_WAY_UP) && + *high > t->temperature) + *high = t->temperature; + } + + list_for_each_entry_reverse(t, thresholds, list_node) { + if (temperature > t->temperature && + (t->direction & THERMAL_THRESHOLD_WAY_DOWN) && + *low < t->temperature) + *low = t->temperature; + } +} + void thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *high) { struct list_head *thresholds = &tz->user_thresholds; @@ -132,6 +134,8 @@ void thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *hi lockdep_assert_held(&tz->lock); + thermal_threshold_find_boundaries(thresholds, temperature, low, high); + /* * We need a second update in order to detect a threshold being crossed */ @@ -151,12 +155,12 @@ void thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *hi * - decreased : thresholds are crossed the way down */ if (temperature > last_temperature) { - if (thermal_thresholds_handle_raising(thresholds, temperature, - last_temperature, low, high)) + if (thermal_thresholds_handle_raising(thresholds, + temperature, last_temperature)) thermal_notify_threshold_up(tz); } else { - if (thermal_thresholds_handle_dropping(thresholds, temperature, - last_temperature, low, high)) + if (thermal_thresholds_handle_dropping(thresholds, + temperature, last_temperature)) thermal_notify_threshold_down(tz); } } diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c index 4bdb2d45e0bf..dc1f456736dc 100644 --- a/drivers/thunderbolt/ctl.c +++ b/drivers/thunderbolt/ctl.c @@ -70,6 +70,9 @@ struct tb_ctl { #define tb_ctl_dbg(ctl, format, arg...) \ dev_dbg(&(ctl)->nhi->pdev->dev, format, ## arg) +#define tb_ctl_dbg_once(ctl, format, arg...) \ + dev_dbg_once(&(ctl)->nhi->pdev->dev, format, ## arg) + static DECLARE_WAIT_QUEUE_HEAD(tb_cfg_request_cancel_queue); /* Serializes access to request kref_get/put */ static DEFINE_MUTEX(tb_cfg_request_lock); @@ -265,7 +268,7 @@ static struct tb_cfg_result parse_header(const struct ctl_pkg *pkg, u32 len, return res; } -static void tb_cfg_print_error(struct tb_ctl *ctl, +static void tb_cfg_print_error(struct tb_ctl *ctl, enum tb_cfg_space space, const struct tb_cfg_result *res) { WARN_ON(res->err != 1); @@ -279,8 +282,8 @@ static void tb_cfg_print_error(struct tb_ctl *ctl, * Invalid cfg_space/offset/length combination in * cfg_read/cfg_write. */ - tb_ctl_dbg(ctl, "%llx:%x: invalid config space or offset\n", - res->response_route, res->response_port); + tb_ctl_dbg_once(ctl, "%llx:%x: invalid config space (%u) or offset\n", + res->response_route, res->response_port, space); return; case TB_CFG_ERROR_NO_SUCH_PORT: /* @@ -1072,7 +1075,7 @@ static int tb_cfg_get_error(struct tb_ctl *ctl, enum tb_cfg_space space, res->tb_error == TB_CFG_ERROR_INVALID_CONFIG_SPACE) return -ENODEV; - tb_cfg_print_error(ctl, res); + tb_cfg_print_error(ctl, space, res); if (res->tb_error == TB_CFG_ERROR_LOCK) return -EACCES; diff --git a/drivers/thunderbolt/ctl.h b/drivers/thunderbolt/ctl.h index bf930a191472..7e08ca8f0895 100644 --- a/drivers/thunderbolt/ctl.h +++ b/drivers/thunderbolt/ctl.h @@ -140,5 +140,4 @@ int tb_cfg_write(struct tb_ctl *ctl, const void *buffer, u64 route, u32 port, enum tb_cfg_space space, u32 offset, u32 length); int tb_cfg_get_upstream_port(struct tb_ctl *ctl, u64 route); - #endif diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index a1d0d8a33f20..f8328ca7e22e 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -168,6 +168,13 @@ static bool parse_line(char **line, u32 *offs, u32 *val, int short_fmt_len, * offset relative_offset cap_id vs_cap_id value\n * v[0] v[1] v[2] v[3] v[4] * + * For Path configuration space: + * Short format is: offset value\n + * v[0] v[1] + * Long format as produced from the read side: + * offset relative_offset in_hop_id value\n + * v[0] v[1] v[2] v[3] + * * For Counter configuration space: * Short format is: offset\n * v[0] @@ -191,14 +198,33 @@ static bool parse_line(char **line, u32 *offs, u32 *val, int short_fmt_len, } #if IS_ENABLED(CONFIG_USB4_DEBUGFS_WRITE) -static ssize_t regs_write(struct tb_switch *sw, struct tb_port *port, - const char __user *user_buf, size_t count, - loff_t *ppos) +/* + * Path registers need to be written in double word pairs and they both must be + * read before written. This writes one double word in patch config space + * following the spec flow. + */ +static int path_write_one(struct tb_port *port, u32 val, u32 offset) { + u32 index = offset % PATH_LEN; + u32 offs = offset - index; + u32 data[PATH_LEN]; + int ret; + + ret = tb_port_read(port, data, TB_CFG_HOPS, offs, PATH_LEN); + if (ret) + return ret; + data[index] = val; + return tb_port_write(port, data, TB_CFG_HOPS, offs, PATH_LEN); +} + +static ssize_t regs_write(struct tb_switch *sw, struct tb_port *port, + enum tb_cfg_space space, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + int long_fmt_len, ret = 0; struct tb *tb = sw->tb; char *line, *buf; u32 val, offset; - int ret = 0; buf = validate_and_copy_from_user(user_buf, &count); if (IS_ERR(buf)) @@ -214,12 +240,21 @@ static ssize_t regs_write(struct tb_switch *sw, struct tb_port *port, /* User did hardware changes behind the driver's back */ add_taint(TAINT_USER, LOCKDEP_STILL_OK); + if (space == TB_CFG_HOPS) + long_fmt_len = 4; + else + long_fmt_len = 5; + line = buf; - while (parse_line(&line, &offset, &val, 2, 5)) { - if (port) - ret = tb_port_write(port, &val, TB_CFG_PORT, offset, 1); - else + while (parse_line(&line, &offset, &val, 2, long_fmt_len)) { + if (port) { + if (space == TB_CFG_HOPS) + ret = path_write_one(port, val, offset); + else + ret = tb_port_write(port, &val, space, offset, 1); + } else { ret = tb_sw_write(sw, &val, TB_CFG_SWITCH, offset, 1); + } if (ret) break; } @@ -240,7 +275,16 @@ static ssize_t port_regs_write(struct file *file, const char __user *user_buf, struct seq_file *s = file->private_data; struct tb_port *port = s->private; - return regs_write(port->sw, port, user_buf, count, ppos); + return regs_write(port->sw, port, TB_CFG_PORT, user_buf, count, ppos); +} + +static ssize_t path_write(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct seq_file *s = file->private_data; + struct tb_port *port = s->private; + + return regs_write(port->sw, port, TB_CFG_HOPS, user_buf, count, ppos); } static ssize_t switch_regs_write(struct file *file, const char __user *user_buf, @@ -249,7 +293,7 @@ static ssize_t switch_regs_write(struct file *file, const char __user *user_buf, struct seq_file *s = file->private_data; struct tb_switch *sw = s->private; - return regs_write(sw, NULL, user_buf, count, ppos); + return regs_write(sw, NULL, TB_CFG_SWITCH, user_buf, count, ppos); } static bool parse_sb_line(char **line, u8 *reg, u8 *data, size_t data_size, @@ -401,6 +445,7 @@ out: #define DEBUGFS_MODE 0600 #else #define port_regs_write NULL +#define path_write NULL #define switch_regs_write NULL #define port_sb_regs_write NULL #define retimer_sb_regs_write NULL @@ -2243,7 +2288,7 @@ out_rpm_put: return ret; } -DEBUGFS_ATTR_RO(path); +DEBUGFS_ATTR_RW(path); static int counter_set_regs_show(struct tb_port *port, struct seq_file *s, int counter) @@ -2368,6 +2413,8 @@ void tb_switch_debugfs_init(struct tb_switch *sw) sw->debugfs_dir = debugfs_dir; debugfs_create_file("regs", DEBUGFS_MODE, debugfs_dir, sw, &switch_regs_fops); + if (sw->drom) + debugfs_create_blob("drom", 0400, debugfs_dir, &sw->drom_blob); tb_switch_for_each_port(sw, port) { struct dentry *debugfs_dir; diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c index eb241b270f79..9c1d65d26553 100644 --- a/drivers/thunderbolt/eeprom.c +++ b/drivers/thunderbolt/eeprom.c @@ -435,6 +435,29 @@ static int tb_drom_parse_entries(struct tb_switch *sw, size_t header_size) return 0; } +static int tb_switch_drom_alloc(struct tb_switch *sw, size_t size) +{ + sw->drom = kzalloc(size, GFP_KERNEL); + if (!sw->drom) + return -ENOMEM; + +#ifdef CONFIG_DEBUG_FS + sw->drom_blob.data = sw->drom; + sw->drom_blob.size = size; +#endif + return 0; +} + +static void tb_switch_drom_free(struct tb_switch *sw) +{ +#ifdef CONFIG_DEBUG_FS + sw->drom_blob.data = NULL; + sw->drom_blob.size = 0; +#endif + kfree(sw->drom); + sw->drom = NULL; +} + /* * tb_drom_copy_efi - copy drom supplied by EFI to sw->drom if present */ @@ -447,9 +470,9 @@ static int tb_drom_copy_efi(struct tb_switch *sw, u16 *size) if (len < 0 || len < sizeof(struct tb_drom_header)) return -EINVAL; - sw->drom = kmalloc(len, GFP_KERNEL); - if (!sw->drom) - return -ENOMEM; + res = tb_switch_drom_alloc(sw, len); + if (res) + return res; res = device_property_read_u8_array(dev, "ThunderboltDROM", sw->drom, len); @@ -464,8 +487,7 @@ static int tb_drom_copy_efi(struct tb_switch *sw, u16 *size) return 0; err: - kfree(sw->drom); - sw->drom = NULL; + tb_switch_drom_free(sw); return -EINVAL; } @@ -491,13 +513,15 @@ static int tb_drom_copy_nvm(struct tb_switch *sw, u16 *size) /* Size includes CRC8 + UID + CRC32 */ *size += 1 + 8 + 4; - sw->drom = kzalloc(*size, GFP_KERNEL); - if (!sw->drom) - return -ENOMEM; + ret = tb_switch_drom_alloc(sw, *size); + if (ret) + return ret; ret = dma_port_flash_read(sw->dma_port, drom_offset, sw->drom, *size); - if (ret) - goto err_free; + if (ret) { + tb_switch_drom_free(sw); + return ret; + } /* * Read UID from the minimal DROM because the one in NVM is just @@ -505,11 +529,6 @@ static int tb_drom_copy_nvm(struct tb_switch *sw, u16 *size) */ tb_drom_read_uid_only(sw, &sw->uid); return 0; - -err_free: - kfree(sw->drom); - sw->drom = NULL; - return ret; } static int usb4_copy_drom(struct tb_switch *sw, u16 *size) @@ -522,15 +541,13 @@ static int usb4_copy_drom(struct tb_switch *sw, u16 *size) /* Size includes CRC8 + UID + CRC32 */ *size += 1 + 8 + 4; - sw->drom = kzalloc(*size, GFP_KERNEL); - if (!sw->drom) - return -ENOMEM; + ret = tb_switch_drom_alloc(sw, *size); + if (ret) + return ret; ret = usb4_switch_drom_read(sw, 0, sw->drom, *size); - if (ret) { - kfree(sw->drom); - sw->drom = NULL; - } + if (ret) + tb_switch_drom_free(sw); return ret; } @@ -552,19 +569,14 @@ static int tb_drom_bit_bang(struct tb_switch *sw, u16 *size) return -EIO; } - sw->drom = kzalloc(*size, GFP_KERNEL); - if (!sw->drom) - return -ENOMEM; + ret = tb_switch_drom_alloc(sw, *size); + if (ret) + return ret; ret = tb_eeprom_read_n(sw, 0, sw->drom, *size); if (ret) - goto err; + tb_switch_drom_free(sw); - return 0; - -err: - kfree(sw->drom); - sw->drom = NULL; return ret; } @@ -646,9 +658,7 @@ static int tb_drom_parse(struct tb_switch *sw, u16 size) return 0; err: - kfree(sw->drom); - sw->drom = NULL; - + tb_switch_drom_free(sw); return ret; } diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 1257dd3ce7e6..f3a2264e012b 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -1520,6 +1520,14 @@ static struct pci_device_id nhi_ids[] = { .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI1), .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI0), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI1), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI0), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI1), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) }, diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index 7a07c7c1a9c2..16744f25a9a0 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -92,6 +92,10 @@ extern const struct tb_nhi_ops icl_nhi_ops; #define PCI_DEVICE_ID_INTEL_RPL_NHI1 0xa76d #define PCI_DEVICE_ID_INTEL_LNL_NHI0 0xa833 #define PCI_DEVICE_ID_INTEL_LNL_NHI1 0xa834 +#define PCI_DEVICE_ID_INTEL_PTL_M_NHI0 0xe333 +#define PCI_DEVICE_ID_INTEL_PTL_M_NHI1 0xe334 +#define PCI_DEVICE_ID_INTEL_PTL_P_NHI0 0xe433 +#define PCI_DEVICE_ID_INTEL_PTL_P_NHI1 0xe434 #define PCI_CLASS_SERIAL_USB_USB4 0x0c0340 diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c index f760e54cd9bd..e1a5f6e3d0b6 100644 --- a/drivers/thunderbolt/path.c +++ b/drivers/thunderbolt/path.c @@ -581,10 +581,10 @@ int tb_path_activate(struct tb_path *path) } } path->activated = true; - tb_dbg(path->tb, "path activation complete\n"); + tb_dbg(path->tb, "%s path activation complete\n", path->name); return 0; err: - tb_WARN(path->tb, "path activation failed\n"); + tb_WARN(path->tb, "%s path activation failed\n", path->name); return res; } diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 89d2919d0193..1f25529fe05d 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -103,6 +103,7 @@ static int tb_retimer_nvm_add(struct tb_retimer *rt) err_nvm: dev_dbg(&rt->dev, "NVM upgrade disabled\n"); + rt->no_nvm_upgrade = true; if (!IS_ERR(nvm)) tb_nvm_free(nvm); @@ -182,8 +183,6 @@ static ssize_t nvm_authenticate_show(struct device *dev, if (!rt->nvm) ret = -EAGAIN; - else if (rt->no_nvm_upgrade) - ret = -EOPNOTSUPP; else ret = sysfs_emit(buf, "%#x\n", rt->auth_status); @@ -323,8 +322,6 @@ static ssize_t nvm_version_show(struct device *dev, if (!rt->nvm) ret = -EAGAIN; - else if (rt->no_nvm_upgrade) - ret = -EOPNOTSUPP; else ret = sysfs_emit(buf, "%x.%x\n", rt->nvm->major, rt->nvm->minor); @@ -342,6 +339,19 @@ static ssize_t vendor_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(vendor); +static umode_t retimer_is_visible(struct kobject *kobj, struct attribute *attr, + int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct tb_retimer *rt = tb_to_retimer(dev); + + if (attr == &dev_attr_nvm_authenticate.attr || + attr == &dev_attr_nvm_version.attr) + return rt->no_nvm_upgrade ? 0 : attr->mode; + + return attr->mode; +} + static struct attribute *retimer_attrs[] = { &dev_attr_device.attr, &dev_attr_nvm_authenticate.attr, @@ -351,6 +361,7 @@ static struct attribute *retimer_attrs[] = { }; static const struct attribute_group retimer_group = { + .is_visible = retimer_is_visible, .attrs = retimer_attrs, }; @@ -461,7 +472,7 @@ struct tb_retimer_lookup { u8 index; }; -static int retimer_match(struct device *dev, void *data) +static int retimer_match(struct device *dev, const void *data) { const struct tb_retimer_lookup *lookup = data; struct tb_retimer *rt = tb_to_retimer(dev); diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 4f777788e917..390abcfe7188 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -19,6 +19,12 @@ #define TB_TIMEOUT 100 /* ms */ #define TB_RELEASE_BW_TIMEOUT 10000 /* ms */ +/* + * How many time bandwidth allocation request from graphics driver is + * retried if the DP tunnel is still activating. + */ +#define TB_BW_ALLOC_RETRIES 3 + /* * Minimum bandwidth (in Mb/s) that is needed in the single transmitter/receiver * direction. This is 40G - 10% guard band bandwidth. @@ -69,14 +75,20 @@ static inline struct tb *tcm_to_tb(struct tb_cm *tcm) } struct tb_hotplug_event { - struct work_struct work; + struct delayed_work work; struct tb *tb; u64 route; u8 port; bool unplug; + int retry; }; +static void tb_scan_port(struct tb_port *port); static void tb_handle_hotplug(struct work_struct *work); +static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port, + const char *reason); +static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port, + int retry, unsigned long delay); static void tb_queue_hotplug(struct tb *tb, u64 route, u8 port, bool unplug) { @@ -90,8 +102,8 @@ static void tb_queue_hotplug(struct tb *tb, u64 route, u8 port, bool unplug) ev->route = route; ev->port = port; ev->unplug = unplug; - INIT_WORK(&ev->work, tb_handle_hotplug); - queue_work(tb->wq, &ev->work); + INIT_DELAYED_WORK(&ev->work, tb_handle_hotplug); + queue_delayed_work(tb->wq, &ev->work, 0); } /* enumeration & hot plug handling */ @@ -961,7 +973,7 @@ static int tb_tunnel_usb3(struct tb *tb, struct tb_switch *sw) return 0; err_free: - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); err_reclaim: if (tb_route(parent)) tb_reclaim_usb3_bandwidth(tb, down, up); @@ -1238,8 +1250,6 @@ static void tb_configure_link(struct tb_port *down, struct tb_port *up, tb_switch_configure_link(sw); } -static void tb_scan_port(struct tb_port *port); - /* * tb_scan_switch() - scan for and initialize downstream switches */ @@ -1727,7 +1737,7 @@ static void tb_deactivate_and_free_tunnel(struct tb_tunnel *tunnel) break; } - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } /* @@ -1864,12 +1874,76 @@ static struct tb_port *tb_find_dp_out(struct tb *tb, struct tb_port *in) return NULL; } -static bool tb_tunnel_one_dp(struct tb *tb, struct tb_port *in, +static void tb_dp_tunnel_active(struct tb_tunnel *tunnel, void *data) +{ + struct tb_port *in = tunnel->src_port; + struct tb_port *out = tunnel->dst_port; + struct tb *tb = data; + + mutex_lock(&tb->lock); + if (tb_tunnel_is_active(tunnel)) { + int consumed_up, consumed_down, ret; + + tb_tunnel_dbg(tunnel, "DPRX capabilities read completed\n"); + + /* If fail reading tunnel's consumed bandwidth, tear it down */ + ret = tb_tunnel_consumed_bandwidth(tunnel, &consumed_up, + &consumed_down); + if (ret) { + tb_tunnel_warn(tunnel, + "failed to read consumed bandwidth, tearing down\n"); + tb_deactivate_and_free_tunnel(tunnel); + } else { + tb_reclaim_usb3_bandwidth(tb, in, out); + /* + * Transition the links to asymmetric if the + * consumption exceeds the threshold. + */ + tb_configure_asym(tb, in, out, consumed_up, + consumed_down); + /* + * Update the domain with the new bandwidth + * estimation. + */ + tb_recalc_estimated_bandwidth(tb); + /* + * In case of DP tunnel exists, change host + * router's 1st children TMU mode to HiFi for + * CL0s to work. + */ + tb_increase_tmu_accuracy(tunnel); + } + } else { + struct tb_port *in = tunnel->src_port; + + /* + * This tunnel failed to establish. This means DPRX + * negotiation most likely did not complete which + * happens either because there is no graphics driver + * loaded or not all DP cables where connected to the + * discrete router. + * + * In both cases we remove the DP IN adapter from the + * available resources as it is not usable. This will + * also tear down the tunnel and try to re-use the + * released DP OUT. + * + * It will be added back only if there is hotplug for + * the DP IN again. + */ + tb_tunnel_warn(tunnel, "not active, tearing down\n"); + tb_dp_resource_unavailable(tb, in, "DPRX negotiation failed"); + } + mutex_unlock(&tb->lock); + + tb_domain_put(tb); +} + +static void tb_tunnel_one_dp(struct tb *tb, struct tb_port *in, struct tb_port *out) { int available_up, available_down, ret, link_nr; struct tb_cm *tcm = tb_priv(tb); - int consumed_up, consumed_down; struct tb_tunnel *tunnel; /* @@ -1921,47 +1995,29 @@ static bool tb_tunnel_one_dp(struct tb *tb, struct tb_port *in, available_up, available_down); tunnel = tb_tunnel_alloc_dp(tb, in, out, link_nr, available_up, - available_down); + available_down, tb_dp_tunnel_active, + tb_domain_get(tb)); if (!tunnel) { tb_port_dbg(out, "could not allocate DP tunnel\n"); goto err_reclaim_usb; } - if (tb_tunnel_activate(tunnel)) { + list_add_tail(&tunnel->list, &tcm->tunnel_list); + + ret = tb_tunnel_activate(tunnel); + if (ret && ret != -EINPROGRESS) { tb_port_info(out, "DP tunnel activation failed, aborting\n"); + list_del(&tunnel->list); goto err_free; } - /* If fail reading tunnel's consumed bandwidth, tear it down */ - ret = tb_tunnel_consumed_bandwidth(tunnel, &consumed_up, &consumed_down); - if (ret) - goto err_deactivate; + return; - list_add_tail(&tunnel->list, &tcm->tunnel_list); - - tb_reclaim_usb3_bandwidth(tb, in, out); - /* - * Transition the links to asymmetric if the consumption exceeds - * the threshold. - */ - tb_configure_asym(tb, in, out, consumed_up, consumed_down); - - /* Update the domain with the new bandwidth estimation */ - tb_recalc_estimated_bandwidth(tb); - - /* - * In case of DP tunnel exists, change host router's 1st children - * TMU mode to HiFi for CL0s to work. - */ - tb_increase_tmu_accuracy(tunnel); - return true; - -err_deactivate: - tb_tunnel_deactivate(tunnel); err_free: - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); err_reclaim_usb: tb_reclaim_usb3_bandwidth(tb, in, out); + tb_domain_put(tb); err_detach_group: tb_detach_bandwidth_group(in); err_dealloc_dp: @@ -1971,8 +2027,6 @@ err_rpm_put: pm_runtime_put_autosuspend(&out->sw->dev); pm_runtime_mark_last_busy(&in->sw->dev); pm_runtime_put_autosuspend(&in->sw->dev); - - return false; } static void tb_tunnel_dp(struct tb *tb) @@ -2059,17 +2113,49 @@ static void tb_exit_redrive(struct tb_port *port) } } -static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port) +static void tb_switch_enter_redrive(struct tb_switch *sw) +{ + struct tb_port *port; + + tb_switch_for_each_port(sw, port) + tb_enter_redrive(port); +} + +/* + * Called during system and runtime suspend to forcefully exit redrive + * mode without querying whether the resource is available. + */ +static void tb_switch_exit_redrive(struct tb_switch *sw) +{ + struct tb_port *port; + + if (!(sw->quirks & QUIRK_KEEP_POWER_IN_DP_REDRIVE)) + return; + + tb_switch_for_each_port(sw, port) { + if (!tb_port_is_dpin(port)) + continue; + + if (port->redrive) { + port->redrive = false; + pm_runtime_put(&sw->dev); + tb_port_dbg(port, "exit redrive mode\n"); + } + } +} + +static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port, + const char *reason) { struct tb_port *in, *out; struct tb_tunnel *tunnel; if (tb_port_is_dpin(port)) { - tb_port_dbg(port, "DP IN resource unavailable\n"); + tb_port_dbg(port, "DP IN resource unavailable: %s\n", reason); in = port; out = NULL; } else { - tb_port_dbg(port, "DP OUT resource unavailable\n"); + tb_port_dbg(port, "DP OUT resource unavailable: %s\n", reason); in = NULL; out = port; } @@ -2151,7 +2237,7 @@ static int tb_disconnect_pci(struct tb *tb, struct tb_switch *sw) tb_tunnel_deactivate(tunnel); list_del(&tunnel->list); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return 0; } @@ -2181,7 +2267,7 @@ static int tb_tunnel_pci(struct tb *tb, struct tb_switch *sw) if (tb_tunnel_activate(tunnel)) { tb_port_info(up, "PCIe tunnel activation failed, aborting\n"); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return -EIO; } @@ -2240,7 +2326,7 @@ static int tb_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd, return 0; err_free: - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); err_clx: tb_enable_clx(sw); mutex_unlock(&tb->lock); @@ -2303,7 +2389,7 @@ static int tb_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd, */ static void tb_handle_hotplug(struct work_struct *work) { - struct tb_hotplug_event *ev = container_of(work, typeof(*ev), work); + struct tb_hotplug_event *ev = container_of(work, typeof(*ev), work.work); struct tb *tb = ev->tb; struct tb_cm *tcm = tb_priv(tb); struct tb_switch *sw; @@ -2375,7 +2461,7 @@ static void tb_handle_hotplug(struct work_struct *work) tb_xdomain_put(xd); tb_port_unconfigure_xdomain(port); } else if (tb_port_is_dpout(port) || tb_port_is_dpin(port)) { - tb_dp_resource_unavailable(tb, port); + tb_dp_resource_unavailable(tb, port, "adapter unplug"); } else if (!port->port) { tb_sw_dbg(sw, "xHCI disconnect request\n"); tb_switch_xhci_disconnect(sw); @@ -2608,7 +2694,7 @@ fail: static void tb_handle_dp_bandwidth_request(struct work_struct *work) { - struct tb_hotplug_event *ev = container_of(work, typeof(*ev), work); + struct tb_hotplug_event *ev = container_of(work, typeof(*ev), work.work); int requested_bw, requested_up, requested_down, ret; struct tb_tunnel *tunnel; struct tb *tb = ev->tb; @@ -2635,7 +2721,7 @@ static void tb_handle_dp_bandwidth_request(struct work_struct *work) goto put_sw; } - tb_port_dbg(in, "handling bandwidth allocation request\n"); + tb_port_dbg(in, "handling bandwidth allocation request, retry %d\n", ev->retry); tunnel = tb_find_tunnel(tb, TB_TUNNEL_DP, in, NULL); if (!tunnel) { @@ -2688,12 +2774,33 @@ static void tb_handle_dp_bandwidth_request(struct work_struct *work) ret = tb_alloc_dp_bandwidth(tunnel, &requested_up, &requested_down); if (ret) { - if (ret == -ENOBUFS) + if (ret == -ENOBUFS) { tb_tunnel_warn(tunnel, "not enough bandwidth available\n"); - else + } else if (ret == -ENOTCONN) { + tb_tunnel_dbg(tunnel, "not active yet\n"); + /* + * We got bandwidth allocation request but the + * tunnel is not yet active. This means that + * tb_dp_tunnel_active() is not yet called for + * this tunnel. Allow it some time and retry + * this request a couple of times. + */ + if (ev->retry < TB_BW_ALLOC_RETRIES) { + tb_tunnel_dbg(tunnel, + "retrying bandwidth allocation request\n"); + tb_queue_dp_bandwidth_request(tb, ev->route, + ev->port, + ev->retry + 1, + msecs_to_jiffies(50)); + } else { + tb_tunnel_dbg(tunnel, + "run out of retries, failing the request"); + } + } else { tb_tunnel_warn(tunnel, "failed to change bandwidth allocation\n"); + } } else { tb_tunnel_dbg(tunnel, "bandwidth allocation changed to %d/%d Mb/s\n", @@ -2714,7 +2821,8 @@ unlock: kfree(ev); } -static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port) +static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port, + int retry, unsigned long delay) { struct tb_hotplug_event *ev; @@ -2725,8 +2833,9 @@ static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port) ev->tb = tb; ev->route = route; ev->port = port; - INIT_WORK(&ev->work, tb_handle_dp_bandwidth_request); - queue_work(tb->wq, &ev->work); + ev->retry = retry; + INIT_DELAYED_WORK(&ev->work, tb_handle_dp_bandwidth_request); + queue_delayed_work(tb->wq, &ev->work, delay); } static void tb_handle_notification(struct tb *tb, u64 route, @@ -2746,7 +2855,7 @@ static void tb_handle_notification(struct tb *tb, u64 route, if (tb_cfg_ack_notification(tb->ctl, route, error)) tb_warn(tb, "could not ack notification on %llx\n", route); - tb_queue_dp_bandwidth_request(tb, route, error->port); + tb_queue_dp_bandwidth_request(tb, route, error->port, 0, 0); break; default: @@ -2801,7 +2910,7 @@ static void tb_stop(struct tb *tb) */ if (tb_tunnel_is_dma(tunnel)) tb_tunnel_deactivate(tunnel); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } tb_switch_remove(tb->root_switch); tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */ @@ -2909,6 +3018,7 @@ static int tb_start(struct tb *tb, bool reset) tb_create_usb3_tunnels(tb->root_switch); /* Add DP IN resources for the root switch */ tb_add_dp_resources(tb->root_switch); + tb_switch_enter_redrive(tb->root_switch); /* Make the discovered switches available to the userspace */ device_for_each_child(&tb->root_switch->dev, NULL, tb_scan_finalize_switch); @@ -2924,6 +3034,7 @@ static int tb_suspend_noirq(struct tb *tb) tb_dbg(tb, "suspending...\n"); tb_disconnect_and_release_dp(tb); + tb_switch_exit_redrive(tb->root_switch); tb_switch_suspend(tb->root_switch, false); tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */ tb_dbg(tb, "suspend finished\n"); @@ -2995,7 +3106,7 @@ static int tb_resume_noirq(struct tb *tb) if (tb_tunnel_is_usb3(tunnel)) usb3_delay = 500; tb_tunnel_deactivate(tunnel); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } /* Re-create our tunnels now */ @@ -3006,7 +3117,7 @@ static int tb_resume_noirq(struct tb *tb) /* Only need to do it once */ usb3_delay = 0; } - tb_tunnel_restart(tunnel); + tb_tunnel_activate(tunnel); } if (!list_empty(&tcm->tunnel_list)) { /* @@ -3016,6 +3127,7 @@ static int tb_resume_noirq(struct tb *tb) tb_dbg(tb, "tunnels restarted, sleeping for 100ms\n"); msleep(100); } + tb_switch_enter_redrive(tb->root_switch); /* Allow tb_handle_hotplug to progress events */ tcm->hotplug_active = true; tb_dbg(tb, "resume finished\n"); @@ -3079,6 +3191,12 @@ static int tb_runtime_suspend(struct tb *tb) struct tb_cm *tcm = tb_priv(tb); mutex_lock(&tb->lock); + /* + * The below call only releases DP resources to allow exiting and + * re-entering redrive mode. + */ + tb_disconnect_and_release_dp(tb); + tb_switch_exit_redrive(tb->root_switch); tb_switch_suspend(tb->root_switch, true); tcm->hotplug_active = false; mutex_unlock(&tb->lock); @@ -3109,7 +3227,8 @@ static int tb_runtime_resume(struct tb *tb) tb_free_invalid_tunnels(tb); tb_restore_children(tb->root_switch); list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) - tb_tunnel_restart(tunnel); + tb_tunnel_activate(tunnel); + tb_switch_enter_redrive(tb->root_switch); tcm->hotplug_active = true; mutex_unlock(&tb->lock); diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index ddbf0cd78377..b54147a1ba87 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -9,6 +9,7 @@ #ifndef TB_H_ #define TB_H_ +#include #include #include #include @@ -160,6 +161,7 @@ struct tb_switch_tmu { * @max_pcie_credits: Router preferred number of buffers for PCIe * @max_dma_credits: Router preferred number of buffers for DMA/P2P * @clx: CLx states on the upstream link of the router + * @drom_blob: DROM debugfs blob wrapper * * When the switch is being added or removed to the domain (other * switches) you need to have domain lock held. @@ -212,6 +214,9 @@ struct tb_switch { unsigned int max_pcie_credits; unsigned int max_dma_credits; unsigned int clx; +#ifdef CONFIG_DEBUG_FS + struct debugfs_blob_wrapper drom_blob; +#endif }; /** diff --git a/drivers/thunderbolt/test.c b/drivers/thunderbolt/test.c index 9475c6698c7d..1f4318249c22 100644 --- a/drivers/thunderbolt/test.c +++ b/drivers/thunderbolt/test.c @@ -1382,8 +1382,8 @@ static void tb_test_tunnel_pcie(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, tunnel2->paths[1]->hops[0].in_port, up); KUNIT_EXPECT_PTR_EQ(test, tunnel2->paths[1]->hops[1].out_port, down); - tb_tunnel_free(tunnel2); - tb_tunnel_free(tunnel1); + tb_tunnel_put(tunnel2); + tb_tunnel_put(tunnel1); } static void tb_test_tunnel_dp(struct kunit *test) @@ -1406,7 +1406,7 @@ static void tb_test_tunnel_dp(struct kunit *test) in = &host->ports[5]; out = &dev->ports[13]; - tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0); + tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_NOT_NULL(test, tunnel); KUNIT_EXPECT_EQ(test, tunnel->type, TB_TUNNEL_DP); KUNIT_EXPECT_PTR_EQ(test, tunnel->src_port, in); @@ -1421,7 +1421,7 @@ static void tb_test_tunnel_dp(struct kunit *test) KUNIT_ASSERT_EQ(test, tunnel->paths[2]->path_length, 2); KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[0].in_port, out); KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[1].out_port, in); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_tunnel_dp_chain(struct kunit *test) @@ -1452,7 +1452,7 @@ static void tb_test_tunnel_dp_chain(struct kunit *test) in = &host->ports[5]; out = &dev4->ports[14]; - tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0); + tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_NOT_NULL(test, tunnel); KUNIT_EXPECT_EQ(test, tunnel->type, TB_TUNNEL_DP); KUNIT_EXPECT_PTR_EQ(test, tunnel->src_port, in); @@ -1467,7 +1467,7 @@ static void tb_test_tunnel_dp_chain(struct kunit *test) KUNIT_ASSERT_EQ(test, tunnel->paths[2]->path_length, 3); KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[0].in_port, out); KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[2].out_port, in); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_tunnel_dp_tree(struct kunit *test) @@ -1502,7 +1502,7 @@ static void tb_test_tunnel_dp_tree(struct kunit *test) in = &dev2->ports[13]; out = &dev5->ports[13]; - tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0); + tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_NOT_NULL(test, tunnel); KUNIT_EXPECT_EQ(test, tunnel->type, TB_TUNNEL_DP); KUNIT_EXPECT_PTR_EQ(test, tunnel->src_port, in); @@ -1517,7 +1517,7 @@ static void tb_test_tunnel_dp_tree(struct kunit *test) KUNIT_ASSERT_EQ(test, tunnel->paths[2]->path_length, 4); KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[0].in_port, out); KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[3].out_port, in); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_tunnel_dp_max_length(struct kunit *test) @@ -1567,7 +1567,7 @@ static void tb_test_tunnel_dp_max_length(struct kunit *test) in = &dev6->ports[13]; out = &dev12->ports[13]; - tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0); + tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_NOT_NULL(test, tunnel); KUNIT_EXPECT_EQ(test, tunnel->type, TB_TUNNEL_DP); KUNIT_EXPECT_PTR_EQ(test, tunnel->src_port, in); @@ -1597,7 +1597,7 @@ static void tb_test_tunnel_dp_max_length(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[6].out_port, &host->ports[1]); KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[12].out_port, in); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_tunnel_3dp(struct kunit *test) @@ -1637,7 +1637,7 @@ static void tb_test_tunnel_3dp(struct kunit *test) out2 = &dev5->ports[13]; out3 = &dev4->ports[14]; - tunnel1 = tb_tunnel_alloc_dp(NULL, in1, out1, 1, 0, 0); + tunnel1 = tb_tunnel_alloc_dp(NULL, in1, out1, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_TRUE(test, tunnel1 != NULL); KUNIT_EXPECT_EQ(test, tunnel1->type, TB_TUNNEL_DP); KUNIT_EXPECT_PTR_EQ(test, tunnel1->src_port, in1); @@ -1645,7 +1645,7 @@ static void tb_test_tunnel_3dp(struct kunit *test) KUNIT_ASSERT_EQ(test, tunnel1->npaths, 3); KUNIT_ASSERT_EQ(test, tunnel1->paths[0]->path_length, 3); - tunnel2 = tb_tunnel_alloc_dp(NULL, in2, out2, 1, 0, 0); + tunnel2 = tb_tunnel_alloc_dp(NULL, in2, out2, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_TRUE(test, tunnel2 != NULL); KUNIT_EXPECT_EQ(test, tunnel2->type, TB_TUNNEL_DP); KUNIT_EXPECT_PTR_EQ(test, tunnel2->src_port, in2); @@ -1653,7 +1653,7 @@ static void tb_test_tunnel_3dp(struct kunit *test) KUNIT_ASSERT_EQ(test, tunnel2->npaths, 3); KUNIT_ASSERT_EQ(test, tunnel2->paths[0]->path_length, 4); - tunnel3 = tb_tunnel_alloc_dp(NULL, in3, out3, 1, 0, 0); + tunnel3 = tb_tunnel_alloc_dp(NULL, in3, out3, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_TRUE(test, tunnel3 != NULL); KUNIT_EXPECT_EQ(test, tunnel3->type, TB_TUNNEL_DP); KUNIT_EXPECT_PTR_EQ(test, tunnel3->src_port, in3); @@ -1661,8 +1661,8 @@ static void tb_test_tunnel_3dp(struct kunit *test) KUNIT_ASSERT_EQ(test, tunnel3->npaths, 3); KUNIT_ASSERT_EQ(test, tunnel3->paths[0]->path_length, 3); - tb_tunnel_free(tunnel2); - tb_tunnel_free(tunnel1); + tb_tunnel_put(tunnel2); + tb_tunnel_put(tunnel1); } static void tb_test_tunnel_usb3(struct kunit *test) @@ -1716,8 +1716,8 @@ static void tb_test_tunnel_usb3(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, tunnel2->paths[1]->hops[0].in_port, up); KUNIT_EXPECT_PTR_EQ(test, tunnel2->paths[1]->hops[1].out_port, down); - tb_tunnel_free(tunnel2); - tb_tunnel_free(tunnel1); + tb_tunnel_put(tunnel2); + tb_tunnel_put(tunnel1); } static void tb_test_tunnel_port_on_path(struct kunit *test) @@ -1750,7 +1750,7 @@ static void tb_test_tunnel_port_on_path(struct kunit *test) in = &dev2->ports[13]; out = &dev5->ports[13]; - dp_tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0); + dp_tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_NOT_NULL(test, dp_tunnel); KUNIT_EXPECT_TRUE(test, tb_tunnel_port_on_path(dp_tunnel, in)); @@ -1783,7 +1783,7 @@ static void tb_test_tunnel_port_on_path(struct kunit *test) port = &dev4->ports[1]; KUNIT_EXPECT_FALSE(test, tb_tunnel_port_on_path(dp_tunnel, port)); - tb_tunnel_free(dp_tunnel); + tb_tunnel_put(dp_tunnel); } static void tb_test_tunnel_dma(struct kunit *test) @@ -1826,7 +1826,7 @@ static void tb_test_tunnel_dma(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[1]->hops[0].out_port, port); KUNIT_EXPECT_EQ(test, tunnel->paths[1]->hops[0].next_hop_index, 8); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_tunnel_dma_rx(struct kunit *test) @@ -1863,7 +1863,7 @@ static void tb_test_tunnel_dma_rx(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[0]->hops[0].out_port, nhi); KUNIT_EXPECT_EQ(test, tunnel->paths[0]->hops[0].next_hop_index, 2); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_tunnel_dma_tx(struct kunit *test) @@ -1900,7 +1900,7 @@ static void tb_test_tunnel_dma_tx(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[0]->hops[0].out_port, port); KUNIT_EXPECT_EQ(test, tunnel->paths[0]->hops[0].next_hop_index, 15); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_tunnel_dma_chain(struct kunit *test) @@ -1966,7 +1966,7 @@ static void tb_test_tunnel_dma_chain(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[1]->hops[2].out_port, port); KUNIT_EXPECT_EQ(test, tunnel->paths[1]->hops[2].next_hop_index, 8); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_tunnel_dma_match(struct kunit *test) @@ -1993,7 +1993,7 @@ static void tb_test_tunnel_dma_match(struct kunit *test) KUNIT_ASSERT_TRUE(test, tb_tunnel_match_dma(tunnel, -1, -1, -1, -1)); KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, 8, -1, 8, -1)); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); tunnel = tb_tunnel_alloc_dma(NULL, nhi, port, 15, 1, -1, -1); KUNIT_ASSERT_NOT_NULL(test, tunnel); @@ -2005,7 +2005,7 @@ static void tb_test_tunnel_dma_match(struct kunit *test) KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, -1, -1, 15, 1)); KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, 15, 11, -1, -1)); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); tunnel = tb_tunnel_alloc_dma(NULL, nhi, port, -1, -1, 15, 11); KUNIT_ASSERT_NOT_NULL(test, tunnel); @@ -2017,7 +2017,7 @@ static void tb_test_tunnel_dma_match(struct kunit *test) KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, -1, -1, 10, 11)); KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, 15, 11, -1, -1)); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_credit_alloc_legacy_not_bonded(struct kunit *test) @@ -2050,7 +2050,7 @@ static void tb_test_credit_alloc_legacy_not_bonded(struct kunit *test) KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U); KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 16U); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_credit_alloc_legacy_bonded(struct kunit *test) @@ -2083,7 +2083,7 @@ static void tb_test_credit_alloc_legacy_bonded(struct kunit *test) KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U); KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 32U); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_credit_alloc_pcie(struct kunit *test) @@ -2116,7 +2116,7 @@ static void tb_test_credit_alloc_pcie(struct kunit *test) KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U); KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 64U); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_credit_alloc_without_dp(struct kunit *test) @@ -2166,7 +2166,7 @@ static void tb_test_credit_alloc_without_dp(struct kunit *test) KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U); KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 64U); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_credit_alloc_dp(struct kunit *test) @@ -2182,7 +2182,7 @@ static void tb_test_credit_alloc_dp(struct kunit *test) in = &host->ports[5]; out = &dev->ports[14]; - tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0); + tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_NOT_NULL(test, tunnel); KUNIT_ASSERT_EQ(test, tunnel->npaths, (size_t)3); @@ -2210,7 +2210,7 @@ static void tb_test_credit_alloc_dp(struct kunit *test) KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U); KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 1U); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_credit_alloc_usb3(struct kunit *test) @@ -2243,7 +2243,7 @@ static void tb_test_credit_alloc_usb3(struct kunit *test) KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U); KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 32U); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_credit_alloc_dma(struct kunit *test) @@ -2279,7 +2279,7 @@ static void tb_test_credit_alloc_dma(struct kunit *test) KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U); KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 14U); - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); } static void tb_test_credit_alloc_dma_multiple(struct kunit *test) @@ -2356,7 +2356,7 @@ static void tb_test_credit_alloc_dma_multiple(struct kunit *test) * Release the first DMA tunnel. That should make 14 buffers * available for the next tunnel. */ - tb_tunnel_free(tunnel1); + tb_tunnel_put(tunnel1); tunnel3 = tb_tunnel_alloc_dma(NULL, nhi, port, 10, 3, 10, 3); KUNIT_ASSERT_NOT_NULL(test, tunnel3); @@ -2375,8 +2375,8 @@ static void tb_test_credit_alloc_dma_multiple(struct kunit *test) KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U); KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 14U); - tb_tunnel_free(tunnel3); - tb_tunnel_free(tunnel2); + tb_tunnel_put(tunnel3); + tb_tunnel_put(tunnel2); } static struct tb_tunnel *TB_TEST_PCIE_TUNNEL(struct kunit *test, @@ -2418,7 +2418,7 @@ static struct tb_tunnel *TB_TEST_DP_TUNNEL1(struct kunit *test, in = &host->ports[5]; out = &dev->ports[13]; - dp_tunnel1 = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0); + dp_tunnel1 = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_NOT_NULL(test, dp_tunnel1); KUNIT_ASSERT_EQ(test, dp_tunnel1->npaths, (size_t)3); @@ -2455,7 +2455,7 @@ static struct tb_tunnel *TB_TEST_DP_TUNNEL2(struct kunit *test, in = &host->ports[6]; out = &dev->ports[14]; - dp_tunnel2 = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0); + dp_tunnel2 = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL); KUNIT_ASSERT_NOT_NULL(test, dp_tunnel2); KUNIT_ASSERT_EQ(test, dp_tunnel2->npaths, (size_t)3); @@ -2595,12 +2595,12 @@ static void tb_test_credit_alloc_all(struct kunit *test) dma_tunnel1 = TB_TEST_DMA_TUNNEL1(test, host, dev); dma_tunnel2 = TB_TEST_DMA_TUNNEL2(test, host, dev); - tb_tunnel_free(dma_tunnel2); - tb_tunnel_free(dma_tunnel1); - tb_tunnel_free(usb3_tunnel); - tb_tunnel_free(dp_tunnel2); - tb_tunnel_free(dp_tunnel1); - tb_tunnel_free(pcie_tunnel); + tb_tunnel_put(dma_tunnel2); + tb_tunnel_put(dma_tunnel1); + tb_tunnel_put(usb3_tunnel); + tb_tunnel_put(dp_tunnel2); + tb_tunnel_put(dp_tunnel1); + tb_tunnel_put(pcie_tunnel); } static const u32 root_directory[] = { diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 41cf6378ad25..8229a6fbda5a 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -70,6 +70,24 @@ #define USB4_V2_PCI_MIN_BANDWIDTH (1500 * TB_PCI_WEIGHT) #define USB4_V2_USB3_MIN_BANDWIDTH (1500 * TB_USB3_WEIGHT) +/* + * According to VESA spec, the DPRX negotiation shall compete in 5 + * seconds after tunnel is established. Since at least i915 can runtime + * suspend if there is nothing connected, and that it polls any new + * connections every 10 seconds, we use 12 seconds here. + * + * These are in ms. + */ +#define TB_DPRX_TIMEOUT 12000 +#define TB_DPRX_WAIT_TIMEOUT 25 +#define TB_DPRX_POLL_DELAY 50 + +static int dprx_timeout = TB_DPRX_TIMEOUT; +module_param(dprx_timeout, int, 0444); +MODULE_PARM_DESC(dprx_timeout, + "DPRX capability read timeout in ms, -1 waits forever (default: " + __MODULE_STRING(TB_DPRX_TIMEOUT) ")"); + static unsigned int dma_credits = TB_DMA_CREDITS; module_param(dma_credits, uint, 0444); MODULE_PARM_DESC(dma_credits, "specify custom credits for DMA tunnels (default: " @@ -82,6 +100,9 @@ MODULE_PARM_DESC(bw_alloc_mode, static const char * const tb_tunnel_names[] = { "PCI", "DP", "DMA", "USB3" }; +/* Synchronizes kref_get()/put() of struct tb_tunnel */ +static DEFINE_MUTEX(tb_tunnel_lock); + static inline unsigned int tb_usable_credits(const struct tb_port *port) { return port->total_credits - port->ctl_credits; @@ -155,7 +176,7 @@ static struct tb_tunnel *tb_tunnel_alloc(struct tb *tb, size_t npaths, tunnel->paths = kcalloc(npaths, sizeof(tunnel->paths[0]), GFP_KERNEL); if (!tunnel->paths) { - tb_tunnel_free(tunnel); + kfree(tunnel); return NULL; } @@ -163,10 +184,42 @@ static struct tb_tunnel *tb_tunnel_alloc(struct tb *tb, size_t npaths, tunnel->tb = tb; tunnel->npaths = npaths; tunnel->type = type; + kref_init(&tunnel->kref); return tunnel; } +static void tb_tunnel_get(struct tb_tunnel *tunnel) +{ + mutex_lock(&tb_tunnel_lock); + kref_get(&tunnel->kref); + mutex_unlock(&tb_tunnel_lock); +} + +static void tb_tunnel_destroy(struct kref *kref) +{ + struct tb_tunnel *tunnel = container_of(kref, typeof(*tunnel), kref); + int i; + + if (tunnel->destroy) + tunnel->destroy(tunnel); + + for (i = 0; i < tunnel->npaths; i++) { + if (tunnel->paths[i]) + tb_path_free(tunnel->paths[i]); + } + + kfree(tunnel->paths); + kfree(tunnel); +} + +void tb_tunnel_put(struct tb_tunnel *tunnel) +{ + mutex_lock(&tb_tunnel_lock); + kref_put(&tunnel->kref, tb_tunnel_destroy); + mutex_unlock(&tb_tunnel_lock); +} + static int tb_pci_set_ext_encapsulation(struct tb_tunnel *tunnel, bool enable) { struct tb_port *port = tb_upstream_port(tunnel->dst_port->sw); @@ -355,7 +408,7 @@ struct tb_tunnel *tb_tunnel_discover_pci(struct tb *tb, struct tb_port *down, err_deactivate: tb_tunnel_deactivate(tunnel); err_free: - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return NULL; } @@ -404,7 +457,7 @@ struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, return tunnel; err_free: - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return NULL; } @@ -851,7 +904,7 @@ static int tb_dp_bandwidth_alloc_mode_enable(struct tb_tunnel *tunnel) return 0; } -static int tb_dp_init(struct tb_tunnel *tunnel) +static int tb_dp_pre_activate(struct tb_tunnel *tunnel) { struct tb_port *in = tunnel->src_port; struct tb_switch *sw = in->sw; @@ -877,7 +930,7 @@ static int tb_dp_init(struct tb_tunnel *tunnel) return tb_dp_bandwidth_alloc_mode_enable(tunnel); } -static void tb_dp_deinit(struct tb_tunnel *tunnel) +static void tb_dp_post_deactivate(struct tb_tunnel *tunnel) { struct tb_port *in = tunnel->src_port; @@ -889,6 +942,90 @@ static void tb_dp_deinit(struct tb_tunnel *tunnel) } } +static ktime_t dprx_timeout_to_ktime(int timeout_msec) +{ + return timeout_msec >= 0 ? + ktime_add_ms(ktime_get(), timeout_msec) : KTIME_MAX; +} + +static int tb_dp_wait_dprx(struct tb_tunnel *tunnel, int timeout_msec) +{ + ktime_t timeout = dprx_timeout_to_ktime(timeout_msec); + struct tb_port *in = tunnel->src_port; + + /* + * Wait for DPRX done. Normally it should be already set for + * active tunnel. + */ + do { + u32 val; + int ret; + + ret = tb_port_read(in, &val, TB_CFG_PORT, + in->cap_adap + DP_COMMON_CAP, 1); + if (ret) + return ret; + + if (val & DP_COMMON_CAP_DPRX_DONE) + return 0; + + usleep_range(100, 150); + } while (ktime_before(ktime_get(), timeout)); + + tb_tunnel_dbg(tunnel, "DPRX read timeout\n"); + return -ETIMEDOUT; +} + +static void tb_dp_dprx_work(struct work_struct *work) +{ + struct tb_tunnel *tunnel = container_of(work, typeof(*tunnel), dprx_work.work); + struct tb *tb = tunnel->tb; + + if (!tunnel->dprx_canceled) { + mutex_lock(&tb->lock); + if (tb_dp_is_usb4(tunnel->src_port->sw) && + tb_dp_wait_dprx(tunnel, TB_DPRX_WAIT_TIMEOUT)) { + if (ktime_before(ktime_get(), tunnel->dprx_timeout)) { + queue_delayed_work(tb->wq, &tunnel->dprx_work, + msecs_to_jiffies(TB_DPRX_POLL_DELAY)); + mutex_unlock(&tb->lock); + return; + } + } else { + tunnel->state = TB_TUNNEL_ACTIVE; + } + mutex_unlock(&tb->lock); + } + + if (tunnel->callback) + tunnel->callback(tunnel, tunnel->callback_data); +} + +static int tb_dp_dprx_start(struct tb_tunnel *tunnel) +{ + /* + * Bump up the reference to keep the tunnel around. It will be + * dropped in tb_dp_dprx_stop() once the tunnel is deactivated. + */ + tb_tunnel_get(tunnel); + + if (tunnel->callback) { + tunnel->dprx_timeout = dprx_timeout_to_ktime(dprx_timeout); + queue_delayed_work(tunnel->tb->wq, &tunnel->dprx_work, 0); + return -EINPROGRESS; + } + + return tb_dp_is_usb4(tunnel->src_port->sw) ? + tb_dp_wait_dprx(tunnel, dprx_timeout) : 0; +} + +static void tb_dp_dprx_stop(struct tb_tunnel *tunnel) +{ + tunnel->dprx_canceled = true; + cancel_delayed_work(&tunnel->dprx_work); + tb_tunnel_put(tunnel); +} + static int tb_dp_activate(struct tb_tunnel *tunnel, bool active) { int ret; @@ -910,6 +1047,7 @@ static int tb_dp_activate(struct tb_tunnel *tunnel, bool active) paths[TB_DP_AUX_PATH_IN]->hops[0].in_hop_index, paths[TB_DP_AUX_PATH_OUT]->hops[last].next_hop_index); } else { + tb_dp_dprx_stop(tunnel); tb_dp_port_hpd_clear(tunnel->src_port); tb_dp_port_set_hops(tunnel->src_port, 0, 0, 0); if (tb_port_is_dpout(tunnel->dst_port)) @@ -920,10 +1058,13 @@ static int tb_dp_activate(struct tb_tunnel *tunnel, bool active) if (ret) return ret; - if (tb_port_is_dpout(tunnel->dst_port)) - return tb_dp_port_enable(tunnel->dst_port, active); + if (tb_port_is_dpout(tunnel->dst_port)) { + ret = tb_dp_port_enable(tunnel->dst_port, active); + if (ret) + return ret; + } - return 0; + return active ? tb_dp_dprx_start(tunnel) : 0; } /** @@ -1076,35 +1217,6 @@ static int tb_dp_alloc_bandwidth(struct tb_tunnel *tunnel, int *alloc_up, return 0; } -static int tb_dp_wait_dprx(struct tb_tunnel *tunnel, int timeout_msec) -{ - ktime_t timeout = ktime_add_ms(ktime_get(), timeout_msec); - struct tb_port *in = tunnel->src_port; - - /* - * Wait for DPRX done. Normally it should be already set for - * active tunnel. - */ - do { - u32 val; - int ret; - - ret = tb_port_read(in, &val, TB_CFG_PORT, - in->cap_adap + DP_COMMON_CAP, 1); - if (ret) - return ret; - - if (val & DP_COMMON_CAP_DPRX_DONE) { - tb_tunnel_dbg(tunnel, "DPRX read done\n"); - return 0; - } - usleep_range(100, 150); - } while (ktime_before(ktime_get(), timeout)); - - tb_tunnel_dbg(tunnel, "DPRX read timeout\n"); - return -ETIMEDOUT; -} - /* Read cap from tunnel DP IN */ static int tb_dp_read_cap(struct tb_tunnel *tunnel, unsigned int cap, u32 *rate, u32 *lanes) @@ -1168,32 +1280,39 @@ static int tb_dp_consumed_bandwidth(struct tb_tunnel *tunnel, int *consumed_up, int ret; if (tb_dp_is_usb4(sw)) { - /* - * On USB4 routers check if the bandwidth allocation - * mode is enabled first and then read the bandwidth - * through those registers. - */ - ret = tb_dp_bandwidth_mode_consumed_bandwidth(tunnel, consumed_up, - consumed_down); - if (ret < 0) { - if (ret != -EOPNOTSUPP) + ret = tb_dp_wait_dprx(tunnel, 0); + if (ret) { + if (ret == -ETIMEDOUT) { + /* + * While we wait for DPRX complete the + * tunnel consumes as much as it had + * been reserved initially. + */ + ret = tb_dp_read_cap(tunnel, DP_REMOTE_CAP, + &rate, &lanes); + if (ret) + return ret; + } else { + return ret; + } + } else { + /* + * On USB4 routers check if the bandwidth allocation + * mode is enabled first and then read the bandwidth + * through those registers. + */ + ret = tb_dp_bandwidth_mode_consumed_bandwidth(tunnel, consumed_up, + consumed_down); + if (ret < 0) { + if (ret != -EOPNOTSUPP) + return ret; + } else if (!ret) { + return 0; + } + ret = tb_dp_read_cap(tunnel, DP_COMMON_CAP, &rate, &lanes); + if (ret) return ret; - } else if (!ret) { - return 0; } - /* - * Then see if the DPRX negotiation is ready and if yes - * return that bandwidth (it may be smaller than the - * reduced one). According to VESA spec, the DPRX - * negotiation shall compete in 5 seconds after tunnel - * established. We give it 100ms extra just in case. - */ - ret = tb_dp_wait_dprx(tunnel, 5100); - if (ret) - return ret; - ret = tb_dp_read_cap(tunnel, DP_COMMON_CAP, &rate, &lanes); - if (ret) - return ret; } else if (sw->generation >= 2) { ret = tb_dp_read_cap(tunnel, DP_REMOTE_CAP, &rate, &lanes); if (ret) @@ -1365,9 +1484,9 @@ struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in, if (!tunnel) return NULL; - tunnel->init = tb_dp_init; - tunnel->deinit = tb_dp_deinit; + tunnel->pre_activate = tb_dp_pre_activate; tunnel->activate = tb_dp_activate; + tunnel->post_deactivate = tb_dp_post_deactivate; tunnel->maximum_bandwidth = tb_dp_maximum_bandwidth; tunnel->allocated_bandwidth = tb_dp_allocated_bandwidth; tunnel->alloc_bandwidth = tb_dp_alloc_bandwidth; @@ -1424,7 +1543,7 @@ struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in, err_deactivate: tb_tunnel_deactivate(tunnel); err_free: - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return NULL; } @@ -1439,15 +1558,24 @@ err_free: * %0 if no available bandwidth. * @max_down: Maximum available downstream bandwidth for the DP tunnel. * %0 if no available bandwidth. + * @callback: Optional callback that is called when the DP tunnel is + * fully activated (or there is an error) + * @callback_data: Optional data for @callback * * Allocates a tunnel between @in and @out that is capable of tunneling - * Display Port traffic. + * Display Port traffic. If @callback is not %NULL it will be called + * after tb_tunnel_activate() once the tunnel has been fully activated. + * It can call tb_tunnel_is_active() to check if activation was + * successful (or if it returns %false there was some sort of issue). + * The @callback is called without @tb->lock held. * - * Return: Returns a tb_tunnel on success or NULL on failure. + * Return: Returns a tb_tunnel on success or &NULL on failure. */ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, struct tb_port *out, int link_nr, - int max_up, int max_down) + int max_up, int max_down, + void (*callback)(struct tb_tunnel *, void *), + void *callback_data) { struct tb_tunnel *tunnel; struct tb_path **paths; @@ -1461,9 +1589,9 @@ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, if (!tunnel) return NULL; - tunnel->init = tb_dp_init; - tunnel->deinit = tb_dp_deinit; + tunnel->pre_activate = tb_dp_pre_activate; tunnel->activate = tb_dp_activate; + tunnel->post_deactivate = tb_dp_post_deactivate; tunnel->maximum_bandwidth = tb_dp_maximum_bandwidth; tunnel->allocated_bandwidth = tb_dp_allocated_bandwidth; tunnel->alloc_bandwidth = tb_dp_alloc_bandwidth; @@ -1472,6 +1600,9 @@ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, tunnel->dst_port = out; tunnel->max_up = max_up; tunnel->max_down = max_down; + tunnel->callback = callback; + tunnel->callback_data = callback_data; + INIT_DELAYED_WORK(&tunnel->dprx_work, tb_dp_dprx_work); paths = tunnel->paths; pm_support = usb4_switch_version(in->sw) >= 2; @@ -1500,7 +1631,7 @@ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, return tunnel; err_free: - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return NULL; } @@ -1620,7 +1751,7 @@ static void tb_dma_release_credits(struct tb_path_hop *hop) } } -static void tb_dma_deinit_path(struct tb_path *path) +static void tb_dma_destroy_path(struct tb_path *path) { struct tb_path_hop *hop; @@ -1628,14 +1759,14 @@ static void tb_dma_deinit_path(struct tb_path *path) tb_dma_release_credits(hop); } -static void tb_dma_deinit(struct tb_tunnel *tunnel) +static void tb_dma_destroy(struct tb_tunnel *tunnel) { int i; for (i = 0; i < tunnel->npaths; i++) { if (!tunnel->paths[i]) continue; - tb_dma_deinit_path(tunnel->paths[i]); + tb_dma_destroy_path(tunnel->paths[i]); } } @@ -1681,7 +1812,7 @@ struct tb_tunnel *tb_tunnel_alloc_dma(struct tb *tb, struct tb_port *nhi, tunnel->src_port = nhi; tunnel->dst_port = dst; - tunnel->deinit = tb_dma_deinit; + tunnel->destroy = tb_dma_destroy; credits = min_not_zero(dma_credits, nhi->sw->max_dma_credits); @@ -1712,7 +1843,7 @@ struct tb_tunnel *tb_tunnel_alloc_dma(struct tb *tb, struct tb_port *nhi, return tunnel; err_free: - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return NULL; } @@ -1793,7 +1924,7 @@ static int tb_usb3_max_link_rate(struct tb_port *up, struct tb_port *down) return min(up_max_rate, down_max_rate); } -static int tb_usb3_init(struct tb_tunnel *tunnel) +static int tb_usb3_pre_activate(struct tb_tunnel *tunnel) { tb_tunnel_dbg(tunnel, "allocating initial bandwidth %d/%d Mb/s\n", tunnel->allocated_up, tunnel->allocated_down); @@ -2024,7 +2155,7 @@ struct tb_tunnel *tb_tunnel_discover_usb3(struct tb *tb, struct tb_port *down, tb_tunnel_dbg(tunnel, "currently allocated bandwidth %d/%d Mb/s\n", tunnel->allocated_up, tunnel->allocated_down); - tunnel->init = tb_usb3_init; + tunnel->pre_activate = tb_usb3_pre_activate; tunnel->consumed_bandwidth = tb_usb3_consumed_bandwidth; tunnel->release_unused_bandwidth = tb_usb3_release_unused_bandwidth; @@ -2038,7 +2169,7 @@ struct tb_tunnel *tb_tunnel_discover_usb3(struct tb *tb, struct tb_port *down, err_deactivate: tb_tunnel_deactivate(tunnel); err_free: - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return NULL; } @@ -2094,7 +2225,7 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up, path = tb_path_alloc(tb, down, TB_USB3_HOPID, up, TB_USB3_HOPID, 0, "USB3 Down"); if (!path) { - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return NULL; } tb_usb3_init_path(path); @@ -2103,7 +2234,7 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up, path = tb_path_alloc(tb, up, TB_USB3_HOPID, down, TB_USB3_HOPID, 0, "USB3 Up"); if (!path) { - tb_tunnel_free(tunnel); + tb_tunnel_put(tunnel); return NULL; } tb_usb3_init_path(path); @@ -2113,7 +2244,7 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up, tunnel->allocated_up = min(max_rate, max_up); tunnel->allocated_down = min(max_rate, max_down); - tunnel->init = tb_usb3_init; + tunnel->pre_activate = tb_usb3_pre_activate; tunnel->consumed_bandwidth = tb_usb3_consumed_bandwidth; tunnel->release_unused_bandwidth = tb_usb3_release_unused_bandwidth; @@ -2124,31 +2255,6 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up, return tunnel; } -/** - * tb_tunnel_free() - free a tunnel - * @tunnel: Tunnel to be freed - * - * Frees a tunnel. The tunnel does not need to be deactivated. - */ -void tb_tunnel_free(struct tb_tunnel *tunnel) -{ - int i; - - if (!tunnel) - return; - - if (tunnel->deinit) - tunnel->deinit(tunnel); - - for (i = 0; i < tunnel->npaths; i++) { - if (tunnel->paths[i]) - tb_path_free(tunnel->paths[i]); - } - - kfree(tunnel->paths); - kfree(tunnel); -} - /** * tb_tunnel_is_invalid - check whether an activated path is still valid * @tunnel: Tunnel to check @@ -2167,12 +2273,15 @@ bool tb_tunnel_is_invalid(struct tb_tunnel *tunnel) } /** - * tb_tunnel_restart() - activate a tunnel after a hardware reset - * @tunnel: Tunnel to restart + * tb_tunnel_activate() - activate a tunnel + * @tunnel: Tunnel to activate * - * Return: 0 on success and negative errno in case if failure + * Return: 0 on success and negative errno in case if failure. + * Specifically returns %-EINPROGRESS if the tunnel activation is still + * in progress (that's for DP tunnels to complete DPRX capabilities + * read). */ -int tb_tunnel_restart(struct tb_tunnel *tunnel) +int tb_tunnel_activate(struct tb_tunnel *tunnel) { int res, i; @@ -2189,8 +2298,10 @@ int tb_tunnel_restart(struct tb_tunnel *tunnel) } } - if (tunnel->init) { - res = tunnel->init(tunnel); + tunnel->state = TB_TUNNEL_ACTIVATING; + + if (tunnel->pre_activate) { + res = tunnel->pre_activate(tunnel); if (res) return res; } @@ -2203,10 +2314,14 @@ int tb_tunnel_restart(struct tb_tunnel *tunnel) if (tunnel->activate) { res = tunnel->activate(tunnel, true); - if (res) + if (res) { + if (res == -EINPROGRESS) + return res; goto err; + } } + tunnel->state = TB_TUNNEL_ACTIVE; return 0; err: @@ -2215,27 +2330,6 @@ err: return res; } -/** - * tb_tunnel_activate() - activate a tunnel - * @tunnel: Tunnel to activate - * - * Return: Returns 0 on success or an error code on failure. - */ -int tb_tunnel_activate(struct tb_tunnel *tunnel) -{ - int i; - - for (i = 0; i < tunnel->npaths; i++) { - if (tunnel->paths[i]->activated) { - tb_tunnel_WARN(tunnel, - "trying to activate an already activated tunnel\n"); - return -EINVAL; - } - } - - return tb_tunnel_restart(tunnel); -} - /** * tb_tunnel_deactivate() - deactivate a tunnel * @tunnel: Tunnel to deactivate @@ -2253,6 +2347,11 @@ void tb_tunnel_deactivate(struct tb_tunnel *tunnel) if (tunnel->paths[i] && tunnel->paths[i]->activated) tb_path_deactivate(tunnel->paths[i]); } + + if (tunnel->post_deactivate) + tunnel->post_deactivate(tunnel); + + tunnel->state = TB_TUNNEL_INACTIVE; } /** @@ -2279,18 +2378,10 @@ bool tb_tunnel_port_on_path(const struct tb_tunnel *tunnel, return false; } -static bool tb_tunnel_is_active(const struct tb_tunnel *tunnel) +// Is tb_tunnel_activate() called for the tunnel +static bool tb_tunnel_is_activated(const struct tb_tunnel *tunnel) { - int i; - - for (i = 0; i < tunnel->npaths; i++) { - if (!tunnel->paths[i]) - return false; - if (!tunnel->paths[i]->activated) - return false; - } - - return true; + return tunnel->state == TB_TUNNEL_ACTIVATING || tb_tunnel_is_active(tunnel); } /** @@ -2307,7 +2398,7 @@ int tb_tunnel_maximum_bandwidth(struct tb_tunnel *tunnel, int *max_up, int *max_down) { if (!tb_tunnel_is_active(tunnel)) - return -EINVAL; + return -ENOTCONN; if (tunnel->maximum_bandwidth) return tunnel->maximum_bandwidth(tunnel, max_up, max_down); @@ -2328,7 +2419,7 @@ int tb_tunnel_allocated_bandwidth(struct tb_tunnel *tunnel, int *allocated_up, int *allocated_down) { if (!tb_tunnel_is_active(tunnel)) - return -EINVAL; + return -ENOTCONN; if (tunnel->allocated_bandwidth) return tunnel->allocated_bandwidth(tunnel, allocated_up, @@ -2351,7 +2442,7 @@ int tb_tunnel_alloc_bandwidth(struct tb_tunnel *tunnel, int *alloc_up, int *alloc_down) { if (!tb_tunnel_is_active(tunnel)) - return -EINVAL; + return -ENOTCONN; if (tunnel->alloc_bandwidth) return tunnel->alloc_bandwidth(tunnel, alloc_up, alloc_down); @@ -2376,26 +2467,27 @@ int tb_tunnel_consumed_bandwidth(struct tb_tunnel *tunnel, int *consumed_up, { int up_bw = 0, down_bw = 0; - if (!tb_tunnel_is_active(tunnel)) - goto out; - - if (tunnel->consumed_bandwidth) { + /* + * Here we need to distinguish between not active tunnel from + * tunnels that are either fully active or activation started. + * The latter is true for DP tunnels where we must report the + * consumed to be the maximum we gave it until DPRX capabilities + * read is done by the graphics driver. + */ + if (tb_tunnel_is_activated(tunnel) && tunnel->consumed_bandwidth) { int ret; ret = tunnel->consumed_bandwidth(tunnel, &up_bw, &down_bw); if (ret) return ret; - - tb_tunnel_dbg(tunnel, "consumed bandwidth %d/%d Mb/s\n", up_bw, - down_bw); } -out: if (consumed_up) *consumed_up = up_bw; if (consumed_down) *consumed_down = down_bw; + tb_tunnel_dbg(tunnel, "consumed bandwidth %d/%d Mb/s\n", up_bw, down_bw); return 0; } @@ -2411,7 +2503,7 @@ out: int tb_tunnel_release_unused_bandwidth(struct tb_tunnel *tunnel) { if (!tb_tunnel_is_active(tunnel)) - return 0; + return -ENOTCONN; if (tunnel->release_unused_bandwidth) { int ret; diff --git a/drivers/thunderbolt/tunnel.h b/drivers/thunderbolt/tunnel.h index 1a27ccd08b86..7f6d3a18a41e 100644 --- a/drivers/thunderbolt/tunnel.h +++ b/drivers/thunderbolt/tunnel.h @@ -18,17 +18,34 @@ enum tb_tunnel_type { TB_TUNNEL_USB3, }; +/** + * enum tb_tunnel_state - State of a tunnel + * @TB_TUNNEL_INACTIVE: tb_tunnel_activate() is not called for the tunnel + * @TB_TUNNEL_ACTIVATING: tb_tunnel_activate() returned successfully for the tunnel + * @TB_TUNNEL_ACTIVE: The tunnel is fully active + */ +enum tb_tunnel_state { + TB_TUNNEL_INACTIVE, + TB_TUNNEL_ACTIVATING, + TB_TUNNEL_ACTIVE, +}; + /** * struct tb_tunnel - Tunnel between two ports + * @kref: Reference count * @tb: Pointer to the domain * @src_port: Source port of the tunnel * @dst_port: Destination port of the tunnel. For discovered incomplete * tunnels may be %NULL or null adapter port instead. * @paths: All paths required by the tunnel * @npaths: Number of paths in @paths - * @init: Optional tunnel specific initialization - * @deinit: Optional tunnel specific de-initialization + * @pre_activate: Optional tunnel specific initialization called before + * activation. Can touch hardware. * @activate: Optional tunnel specific activation/deactivation + * @post_deactivate: Optional tunnel specific de-initialization called + * after deactivation. Can touch hardware. + * @destroy: Optional tunnel specific callback called when the tunnel + * memory is being released. Should not touch hardware. * @maximum_bandwidth: Returns maximum possible bandwidth for this tunnel * @allocated_bandwidth: Return how much bandwidth is allocated for the tunnel * @alloc_bandwidth: Change tunnel bandwidth allocation @@ -37,6 +54,7 @@ enum tb_tunnel_type { * @reclaim_available_bandwidth: Reclaim back available bandwidth * @list: Tunnels are linked using this field * @type: Type of the tunnel + * @state: Current state of the tunnel * @max_up: Maximum upstream bandwidth (Mb/s) available for the tunnel. * Only set if the bandwidth needs to be limited. * @max_down: Maximum downstream bandwidth (Mb/s) available for the tunnel. @@ -45,16 +63,23 @@ enum tb_tunnel_type { * @allocated_down: Allocated downstream bandwidth (only for USB3) * @bw_mode: DP bandwidth allocation mode registers can be used to * determine consumed and allocated bandwidth + * @dprx_canceled: Was DPRX capabilities read poll canceled + * @dprx_timeout: If set DPRX capabilities read poll work will timeout after this passes + * @dprx_work: Worker that is scheduled to poll completion of DPRX capabilities read + * @callback: Optional callback called when DP tunnel is fully activated + * @callback_data: Optional data for @callback */ struct tb_tunnel { + struct kref kref; struct tb *tb; struct tb_port *src_port; struct tb_port *dst_port; struct tb_path **paths; size_t npaths; - int (*init)(struct tb_tunnel *tunnel); - void (*deinit)(struct tb_tunnel *tunnel); + int (*pre_activate)(struct tb_tunnel *tunnel); int (*activate)(struct tb_tunnel *tunnel, bool activate); + void (*post_deactivate)(struct tb_tunnel *tunnel); + void (*destroy)(struct tb_tunnel *tunnel); int (*maximum_bandwidth)(struct tb_tunnel *tunnel, int *max_up, int *max_down); int (*allocated_bandwidth)(struct tb_tunnel *tunnel, int *allocated_up, @@ -69,11 +94,17 @@ struct tb_tunnel { int *available_down); struct list_head list; enum tb_tunnel_type type; + enum tb_tunnel_state state; int max_up; int max_down; int allocated_up; int allocated_down; bool bw_mode; + bool dprx_canceled; + ktime_t dprx_timeout; + struct delayed_work dprx_work; + void (*callback)(struct tb_tunnel *tunnel, void *data); + void *callback_data; }; struct tb_tunnel *tb_tunnel_discover_pci(struct tb *tb, struct tb_port *down, @@ -86,7 +117,9 @@ struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in, bool alloc_hopid); struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, struct tb_port *out, int link_nr, - int max_up, int max_down); + int max_up, int max_down, + void (*callback)(struct tb_tunnel *, void *), + void *callback_data); struct tb_tunnel *tb_tunnel_alloc_dma(struct tb *tb, struct tb_port *nhi, struct tb_port *dst, int transmit_path, int transmit_ring, int receive_path, @@ -99,10 +132,24 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up, struct tb_port *down, int max_up, int max_down); -void tb_tunnel_free(struct tb_tunnel *tunnel); +void tb_tunnel_put(struct tb_tunnel *tunnel); int tb_tunnel_activate(struct tb_tunnel *tunnel); -int tb_tunnel_restart(struct tb_tunnel *tunnel); void tb_tunnel_deactivate(struct tb_tunnel *tunnel); + +/** + * tb_tunnel_is_active() - Is tunnel fully activated + * @tunnel: Tunnel to check + * + * Returns %true if @tunnel is fully activated. For other than DP + * tunnels this is pretty much once tb_tunnel_activate() returns + * successfully. However, for DP tunnels this returns %true only once the + * DPRX capabilities read has been issued successfully. + */ +static inline bool tb_tunnel_is_active(const struct tb_tunnel *tunnel) +{ + return tunnel->state == TB_TUNNEL_ACTIVE; +} + bool tb_tunnel_is_invalid(struct tb_tunnel *tunnel); bool tb_tunnel_port_on_path(const struct tb_tunnel *tunnel, const struct tb_port *port); diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index 11a50c86a1e4..b0630e6d9472 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -1026,7 +1026,7 @@ static int remove_missing_service(struct device *dev, void *data) return 0; } -static int find_service(struct device *dev, void *data) +static int find_service(struct device *dev, const void *data) { const struct tb_property *p = data; struct tb_service *svc; diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c index afbf7738c7c4..58b28be63c79 100644 --- a/drivers/tty/mips_ejtag_fdc.c +++ b/drivers/tty/mips_ejtag_fdc.c @@ -1154,7 +1154,7 @@ static char kgdbfdc_rbuf[4]; /* write buffer to allow compaction */ static unsigned int kgdbfdc_wbuflen; -static char kgdbfdc_wbuf[4]; +static u8 kgdbfdc_wbuf[4]; static void __iomem *kgdbfdc_setup(void) { @@ -1215,7 +1215,7 @@ static int kgdbfdc_read_char(void) /* push an FDC word from write buffer to TX FIFO */ static void kgdbfdc_push_one(void) { - const char *bufs[1] = { kgdbfdc_wbuf }; + const u8 *bufs[1] = { kgdbfdc_wbuf }; struct fdc_word word; void __iomem *regs; unsigned int i; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 252849910588..363afe11974f 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2224,7 +2224,7 @@ static int gsm_dlci_negotiate(struct gsm_dlci *dlci) * * Some control dlci can stay in ADM mode with other dlci working just * fine. In that case we can just keep the control dlci open after the - * DLCI_OPENING retries time out. + * DLCI_OPENING receives DM. */ static void gsm_dlci_t1(struct timer_list *t) @@ -2243,16 +2243,19 @@ static void gsm_dlci_t1(struct timer_list *t) } break; case DLCI_OPENING: - if (dlci->retries) { - dlci->retries--; - gsm_command(dlci->gsm, dlci->addr, SABM|PF); - mod_timer(&dlci->t1, jiffies + gsm->t1 * HZ / 100); - } else if (!dlci->addr && gsm->control == (DM | PF)) { + if (!dlci->addr && gsm->control == (DM | PF)) { if (debug & DBG_ERRORS) - pr_info("DLCI %d opening in ADM mode.\n", - dlci->addr); + pr_info("DLCI 0 opening in ADM mode.\n"); dlci->mode = DLCI_MODE_ADM; gsm_dlci_open(dlci); + } else if (dlci->retries) { + if (!dlci->addr || !gsm->dlci[0] || + gsm->dlci[0]->state != DLCI_OPENING) { + dlci->retries--; + gsm_command(dlci->gsm, dlci->addr, SABM|PF); + } + + mod_timer(&dlci->t1, jiffies + gsm->t1 * HZ / 100); } else { gsm->open_error++; gsm_dlci_begin_close(dlci); /* prevent half open link */ @@ -2308,7 +2311,9 @@ static void gsm_dlci_begin_open(struct gsm_dlci *dlci) dlci->retries = gsm->n2; if (!need_pn) { dlci->state = DLCI_OPENING; - gsm_command(gsm, dlci->addr, SABM|PF); + if (!dlci->addr || !gsm->dlci[0] || + gsm->dlci[0]->state != DLCI_OPENING) + gsm_command(gsm, dlci->addr, SABM|PF); } else { /* Configure DLCI before setup */ dlci->state = DLCI_CONFIGURE; @@ -4251,7 +4256,7 @@ static const struct tty_port_operations gsm_port_ops = { static int gsmtty_install(struct tty_driver *driver, struct tty_struct *tty) { struct gsm_mux *gsm; - struct gsm_dlci *dlci; + struct gsm_dlci *dlci, *dlci0; unsigned int line = tty->index; unsigned int mux = mux_line_to_num(line); bool alloc = false; @@ -4274,10 +4279,20 @@ static int gsmtty_install(struct tty_driver *driver, struct tty_struct *tty) perspective as we don't have to worry about this if DLCI0 is lost */ mutex_lock(&gsm->mutex); - if (gsm->dlci[0] && gsm->dlci[0]->state != DLCI_OPEN) { + + dlci0 = gsm->dlci[0]; + if (dlci0 && dlci0->state != DLCI_OPEN) { mutex_unlock(&gsm->mutex); - return -EL2NSYNC; + + if (dlci0->state == DLCI_OPENING) + wait_event(gsm->event, dlci0->state != DLCI_OPENING); + + if (dlci0->state != DLCI_OPEN) + return -EL2NSYNC; + + mutex_lock(&gsm->mutex); } + dlci = gsm->dlci[line]; if (dlci == NULL) { alloc = true; diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index e5310c65cf52..11e05aa014e5 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -231,8 +231,8 @@ void serial8250_rpm_put_tx(struct uart_8250_port *p); int serial8250_em485_config(struct uart_port *port, struct ktermios *termios, struct serial_rs485 *rs485); -void serial8250_em485_start_tx(struct uart_8250_port *p); -void serial8250_em485_stop_tx(struct uart_8250_port *p); +void serial8250_em485_start_tx(struct uart_8250_port *p, bool toggle_ier); +void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier); void serial8250_em485_destroy(struct uart_8250_port *p); extern struct serial_rs485 serial8250_em485_supported; diff --git a/drivers/tty/serial/8250/8250_bcm2835aux.c b/drivers/tty/serial/8250/8250_bcm2835aux.c index fdb53b54e99e..0609582a62f7 100644 --- a/drivers/tty/serial/8250/8250_bcm2835aux.c +++ b/drivers/tty/serial/8250/8250_bcm2835aux.c @@ -46,7 +46,7 @@ struct bcm2835aux_data { u32 cntl; }; -static void bcm2835aux_rs485_start_tx(struct uart_8250_port *up) +static void bcm2835aux_rs485_start_tx(struct uart_8250_port *up, bool toggle_ier) { if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX)) { struct bcm2835aux_data *data = dev_get_drvdata(up->port.dev); @@ -65,7 +65,7 @@ static void bcm2835aux_rs485_start_tx(struct uart_8250_port *up) serial8250_out_MCR(up, UART_MCR_RTS); } -static void bcm2835aux_rs485_stop_tx(struct uart_8250_port *up) +static void bcm2835aux_rs485_stop_tx(struct uart_8250_port *up, bool toggle_ier) { if (up->port.rs485.flags & SER_RS485_RTS_AFTER_SEND) serial8250_out_MCR(up, 0); diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 5f9f06911795..6f676bb37ac3 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -675,7 +675,6 @@ static void serial_8250_overrun_backoff_work(struct work_struct *work) uart_port_lock_irqsave(port, &flags); up->ier |= UART_IER_RLSI | UART_IER_RDI; - up->port.read_status_mask |= UART_LSR_DR; serial_out(up, UART_IER, up->ier); uart_port_unlock_irqrestore(port, flags); } @@ -812,6 +811,9 @@ int serial8250_register_8250_port(const struct uart_8250_port *up) uart->dl_write = up->dl_write; if (uart->port.type != PORT_8250_CIR) { + if (uart_console_registered(&uart->port)) + pm_runtime_get_sync(uart->port.dev); + if (serial8250_isa_config != NULL) serial8250_isa_config(0, &uart->port, &uart->capabilities); diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 9eb9aa766811..c2b75e3f106d 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -365,7 +365,7 @@ static void omap8250_restore_regs(struct uart_8250_port *up) if (up->port.rs485.flags & SER_RS485_ENABLED && up->port.rs485_config == serial8250_em485_config) - serial8250_em485_stop_tx(up); + serial8250_em485_stop_tx(up, true); } /* @@ -412,7 +412,13 @@ static void omap_8250_set_termios(struct uart_port *port, */ uart_update_timeout(port, termios->c_cflag, baud); - up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR; + /* + * Specify which conditions may be considered for error + * handling and the ignoring of characters. The actual + * ignoring of characters only occurs if the bit is set + * in @ignore_status_mask as well. + */ + up->port.read_status_mask = UART_LSR_OE | UART_LSR_DR; if (termios->c_iflag & INPCK) up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE; if (termios->c_iflag & (IGNBRK | PARMRK)) @@ -838,7 +844,6 @@ static void omap_8250_unthrottle(struct uart_port *port) if (up->dma) up->dma->rx_dma(up); up->ier |= UART_IER_RLSI | UART_IER_RDI; - port->read_status_mask |= UART_LSR_DR; serial_out(up, UART_IER, up->ier); uart_port_unlock_irqrestore(port, flags); diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 3c3f7c926afb..df4d0d832e54 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -64,23 +64,17 @@ #define PCIE_DEVICE_ID_NEO_2_OX_IBM 0x00F6 #define PCI_DEVICE_ID_PLX_CRONYX_OMEGA 0xc001 #define PCI_DEVICE_ID_INTEL_PATSBURG_KT 0x1d3d -#define PCI_VENDOR_ID_WCH 0x4348 -#define PCI_DEVICE_ID_WCH_CH352_2S 0x3253 -#define PCI_DEVICE_ID_WCH_CH353_4S 0x3453 -#define PCI_DEVICE_ID_WCH_CH353_2S1PF 0x5046 -#define PCI_DEVICE_ID_WCH_CH353_1S1P 0x5053 -#define PCI_DEVICE_ID_WCH_CH353_2S1P 0x7053 -#define PCI_DEVICE_ID_WCH_CH355_4S 0x7173 + +#define PCI_DEVICE_ID_WCHCN_CH352_2S 0x3253 +#define PCI_DEVICE_ID_WCHCN_CH355_4S 0x7173 + #define PCI_VENDOR_ID_AGESTAR 0x5372 #define PCI_DEVICE_ID_AGESTAR_9375 0x6872 #define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 0x818e -#define PCIE_VENDOR_ID_WCH 0x1c00 -#define PCIE_DEVICE_ID_WCH_CH382_2S1P 0x3250 -#define PCIE_DEVICE_ID_WCH_CH384_4S 0x3470 -#define PCIE_DEVICE_ID_WCH_CH384_8S 0x3853 -#define PCIE_DEVICE_ID_WCH_CH382_2S 0x3253 +#define PCI_DEVICE_ID_WCHIC_CH384_4S 0x3470 +#define PCI_DEVICE_ID_WCHIC_CH384_8S 0x3853 #define PCI_DEVICE_ID_MOXA_CP102E 0x1024 #define PCI_DEVICE_ID_MOXA_CP102EL 0x1025 @@ -2817,80 +2811,80 @@ static struct pci_serial_quirk pci_serial_quirks[] = { }, /* WCH CH353 1S1P card (16550 clone) */ { - .vendor = PCI_VENDOR_ID_WCH, - .device = PCI_DEVICE_ID_WCH_CH353_1S1P, + .vendor = PCI_VENDOR_ID_WCHCN, + .device = PCI_DEVICE_ID_WCHCN_CH353_1S1P, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .setup = pci_wch_ch353_setup, }, /* WCH CH353 2S1P card (16550 clone) */ { - .vendor = PCI_VENDOR_ID_WCH, - .device = PCI_DEVICE_ID_WCH_CH353_2S1P, + .vendor = PCI_VENDOR_ID_WCHCN, + .device = PCI_DEVICE_ID_WCHCN_CH353_2S1P, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .setup = pci_wch_ch353_setup, }, /* WCH CH353 4S card (16550 clone) */ { - .vendor = PCI_VENDOR_ID_WCH, - .device = PCI_DEVICE_ID_WCH_CH353_4S, + .vendor = PCI_VENDOR_ID_WCHCN, + .device = PCI_DEVICE_ID_WCHCN_CH353_4S, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .setup = pci_wch_ch353_setup, }, /* WCH CH353 2S1PF card (16550 clone) */ { - .vendor = PCI_VENDOR_ID_WCH, - .device = PCI_DEVICE_ID_WCH_CH353_2S1PF, + .vendor = PCI_VENDOR_ID_WCHCN, + .device = PCI_DEVICE_ID_WCHCN_CH353_2S1PF, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .setup = pci_wch_ch353_setup, }, /* WCH CH352 2S card (16550 clone) */ { - .vendor = PCI_VENDOR_ID_WCH, - .device = PCI_DEVICE_ID_WCH_CH352_2S, + .vendor = PCI_VENDOR_ID_WCHCN, + .device = PCI_DEVICE_ID_WCHCN_CH352_2S, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .setup = pci_wch_ch353_setup, }, /* WCH CH355 4S card (16550 clone) */ { - .vendor = PCI_VENDOR_ID_WCH, - .device = PCI_DEVICE_ID_WCH_CH355_4S, + .vendor = PCI_VENDOR_ID_WCHCN, + .device = PCI_DEVICE_ID_WCHCN_CH355_4S, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .setup = pci_wch_ch355_setup, }, /* WCH CH382 2S card (16850 clone) */ { - .vendor = PCIE_VENDOR_ID_WCH, - .device = PCIE_DEVICE_ID_WCH_CH382_2S, + .vendor = PCI_VENDOR_ID_WCHIC, + .device = PCI_DEVICE_ID_WCHIC_CH382_2S, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .setup = pci_wch_ch38x_setup, }, /* WCH CH382 2S1P card (16850 clone) */ { - .vendor = PCIE_VENDOR_ID_WCH, - .device = PCIE_DEVICE_ID_WCH_CH382_2S1P, + .vendor = PCI_VENDOR_ID_WCHIC, + .device = PCI_DEVICE_ID_WCHIC_CH382_2S1P, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .setup = pci_wch_ch38x_setup, }, /* WCH CH384 4S card (16850 clone) */ { - .vendor = PCIE_VENDOR_ID_WCH, - .device = PCIE_DEVICE_ID_WCH_CH384_4S, + .vendor = PCI_VENDOR_ID_WCHIC, + .device = PCI_DEVICE_ID_WCHIC_CH384_4S, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .setup = pci_wch_ch38x_setup, }, /* WCH CH384 8S card (16850 clone) */ { - .vendor = PCIE_VENDOR_ID_WCH, - .device = PCIE_DEVICE_ID_WCH_CH384_8S, + .vendor = PCI_VENDOR_ID_WCHIC, + .device = PCI_DEVICE_ID_WCHIC_CH384_8S, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .init = pci_wch_ch38x_init, @@ -3967,11 +3961,11 @@ static const struct pci_device_id blacklist[] = { /* multi-io cards handled by parport_serial */ /* WCH CH353 2S1P */ - { PCI_DEVICE(0x4348, 0x7053), 0, 0, REPORT_CONFIG(PARPORT_SERIAL), }, + { PCI_VDEVICE(WCHCN, 0x7053), REPORT_CONFIG(PARPORT_SERIAL), }, /* WCH CH353 1S1P */ - { PCI_DEVICE(0x4348, 0x5053), 0, 0, REPORT_CONFIG(PARPORT_SERIAL), }, + { PCI_VDEVICE(WCHCN, 0x5053), REPORT_CONFIG(PARPORT_SERIAL), }, /* WCH CH382 2S1P */ - { PCI_DEVICE(0x1c00, 0x3250), 0, 0, REPORT_CONFIG(PARPORT_SERIAL), }, + { PCI_VDEVICE(WCHIC, 0x3250), REPORT_CONFIG(PARPORT_SERIAL), }, /* Intel platforms with MID UART */ { PCI_VDEVICE(INTEL, 0x081b), REPORT_8250_CONFIG(MID), }, @@ -6044,27 +6038,27 @@ static const struct pci_device_id serial_pci_tbl[] = { * WCH CH353 series devices: The 2S1P is handled by parport_serial * so not listed here. */ - { PCI_VENDOR_ID_WCH, PCI_DEVICE_ID_WCH_CH353_4S, + { PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_4S, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b0_bt_4_115200 }, - { PCI_VENDOR_ID_WCH, PCI_DEVICE_ID_WCH_CH353_2S1PF, + { PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_2S1PF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b0_bt_2_115200 }, - { PCI_VENDOR_ID_WCH, PCI_DEVICE_ID_WCH_CH355_4S, + { PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH355_4S, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b0_bt_4_115200 }, - { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S, + { PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH382_2S, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_wch382_2 }, - { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S, + { PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH384_4S, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_wch384_4 }, - { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_8S, + { PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH384_8S, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_wch384_8 }, /* diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c index 838f181f929b..e9c51d4e447d 100644 --- a/drivers/tty/serial/8250/8250_pci1xxxx.c +++ b/drivers/tty/serial/8250/8250_pci1xxxx.c @@ -78,6 +78,12 @@ #define UART_TX_BYTE_FIFO 0x00 #define UART_FIFO_CTL 0x02 +#define UART_MODEM_CTL_REG 0x04 +#define UART_MODEM_CTL_RTS_SET BIT(1) + +#define UART_LINE_STAT_REG 0x05 +#define UART_LINE_XMIT_CHECK_MASK GENMASK(6, 5) + #define UART_ACTV_REG 0x11 #define UART_BLOCK_SET_ACTIVE BIT(0) @@ -94,6 +100,7 @@ #define UART_BIT_SAMPLE_CNT_16 16 #define BAUD_CLOCK_DIV_INT_MSK GENMASK(31, 8) #define ADCL_CFG_RTS_DELAY_MASK GENMASK(11, 8) +#define FRAC_DIV_TX_END_POINT_MASK GENMASK(23, 20) #define UART_WAKE_REG 0x8C #define UART_WAKE_MASK_REG 0x90 @@ -134,6 +141,11 @@ #define UART_BST_STAT_LSR_FRAME_ERR 0x8000000 #define UART_BST_STAT_LSR_THRE 0x20000000 +#define GET_MODEM_CTL_RTS_STATUS(reg) ((reg) & UART_MODEM_CTL_RTS_SET) +#define GET_RTS_PIN_STATUS(val) (((val) & TIOCM_RTS) >> 1) +#define RTS_TOGGLE_STATUS_MASK(val, reg) (GET_MODEM_CTL_RTS_STATUS(reg) \ + != GET_RTS_PIN_STATUS(val)) + struct pci1xxxx_8250 { unsigned int nr; u8 dev_rev; @@ -254,6 +266,47 @@ static void pci1xxxx_set_divisor(struct uart_port *port, unsigned int baud, port->membase + UART_BAUD_CLK_DIVISOR_REG); } +static void pci1xxxx_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ + u32 fract_div_cfg_reg; + u32 line_stat_reg; + u32 modem_ctl_reg; + u32 adcl_cfg_reg; + + adcl_cfg_reg = readl(port->membase + ADCL_CFG_REG); + + /* HW is responsible in ADCL_EN case */ + if ((adcl_cfg_reg & (ADCL_CFG_EN | ADCL_CFG_PIN_SEL))) + return; + + modem_ctl_reg = readl(port->membase + UART_MODEM_CTL_REG); + + serial8250_do_set_mctrl(port, mctrl); + + if (RTS_TOGGLE_STATUS_MASK(mctrl, modem_ctl_reg)) { + line_stat_reg = readl(port->membase + UART_LINE_STAT_REG); + if (line_stat_reg & UART_LINE_XMIT_CHECK_MASK) { + fract_div_cfg_reg = readl(port->membase + + FRAC_DIV_CFG_REG); + + writel((fract_div_cfg_reg & + ~(FRAC_DIV_TX_END_POINT_MASK)), + port->membase + FRAC_DIV_CFG_REG); + + /* Enable ADC and set the nRTS pin */ + writel((adcl_cfg_reg | (ADCL_CFG_EN | + ADCL_CFG_PIN_SEL)), + port->membase + ADCL_CFG_REG); + + /* Revert to the original settings */ + writel(adcl_cfg_reg, port->membase + ADCL_CFG_REG); + + writel(fract_div_cfg_reg, port->membase + + FRAC_DIV_CFG_REG); + } + } +} + static int pci1xxxx_rs485_config(struct uart_port *port, struct ktermios *termios, struct serial_rs485 *rs485) @@ -631,9 +684,14 @@ static int pci1xxxx_setup(struct pci_dev *pdev, port->port.rs485_config = pci1xxxx_rs485_config; port->port.rs485_supported = pci1xxxx_rs485_supported; - /* From C0 rev Burst operation is supported */ + /* + * C0 and later revisions support Burst operation. + * RTS workaround in mctrl is applicable only to B0. + */ if (rev >= 0xC0) port->port.handle_irq = pci1xxxx_handle_irq; + else if (rev == 0xB0) + port->port.set_mctrl = pci1xxxx_set_mctrl; ret = serial8250_pci_setup_port(pdev, port, 0, PORT_OFFSET * port_idx, 0); if (ret < 0) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 649e74e9b52f..d7976a21cca9 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -578,7 +578,7 @@ static int serial8250_em485_init(struct uart_8250_port *p) deassert_rts: if (p->em485->tx_stopped) - p->rs485_stop_tx(p); + p->rs485_stop_tx(p, true); return 0; } @@ -1390,7 +1390,6 @@ static void serial8250_stop_rx(struct uart_port *port) serial8250_rpm_get(up); up->ier &= ~(UART_IER_RLSI | UART_IER_RDI); - up->port.read_status_mask &= ~UART_LSR_DR; serial_port_out(port, UART_IER, up->ier); serial8250_rpm_put(up); @@ -1399,10 +1398,11 @@ static void serial8250_stop_rx(struct uart_port *port) /** * serial8250_em485_stop_tx() - generic ->rs485_stop_tx() callback * @p: uart 8250 port + * @toggle_ier: true to allow enabling receive interrupts * * Generic callback usable by 8250 uart drivers to stop rs485 transmission. */ -void serial8250_em485_stop_tx(struct uart_8250_port *p) +void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier) { unsigned char mcr = serial8250_in_MCR(p); @@ -1423,8 +1423,10 @@ void serial8250_em485_stop_tx(struct uart_8250_port *p) if (!(p->port.rs485.flags & SER_RS485_RX_DURING_TX)) { serial8250_clear_and_reinit_fifos(p); - p->ier |= UART_IER_RLSI | UART_IER_RDI; - serial_port_out(&p->port, UART_IER, p->ier); + if (toggle_ier) { + p->ier |= UART_IER_RLSI | UART_IER_RDI; + serial_port_out(&p->port, UART_IER, p->ier); + } } } EXPORT_SYMBOL_GPL(serial8250_em485_stop_tx); @@ -1439,7 +1441,7 @@ static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t) serial8250_rpm_get(p); uart_port_lock_irqsave(&p->port, &flags); if (em485->active_timer == &em485->stop_tx_timer) { - p->rs485_stop_tx(p); + p->rs485_stop_tx(p, true); em485->active_timer = NULL; em485->tx_stopped = true; } @@ -1471,7 +1473,7 @@ static void __stop_tx_rs485(struct uart_8250_port *p, u64 stop_delay) em485->active_timer = &em485->stop_tx_timer; hrtimer_start(&em485->stop_tx_timer, ns_to_ktime(stop_delay), HRTIMER_MODE_REL); } else { - p->rs485_stop_tx(p); + p->rs485_stop_tx(p, true); em485->active_timer = NULL; em485->tx_stopped = true; } @@ -1560,6 +1562,7 @@ static inline void __start_tx(struct uart_port *port) /** * serial8250_em485_start_tx() - generic ->rs485_start_tx() callback * @up: uart 8250 port + * @toggle_ier: true to allow disabling receive interrupts * * Generic callback usable by 8250 uart drivers to start rs485 transmission. * Assumes that setting the RTS bit in the MCR register means RTS is high. @@ -1567,11 +1570,11 @@ static inline void __start_tx(struct uart_port *port) * stoppable by disabling the UART_IER_RDI interrupt. (Some chips set the * UART_LSR_DR bit even when UART_IER_RDI is disabled, foiling this approach.) */ -void serial8250_em485_start_tx(struct uart_8250_port *up) +void serial8250_em485_start_tx(struct uart_8250_port *up, bool toggle_ier) { unsigned char mcr = serial8250_in_MCR(up); - if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX)) + if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX) && toggle_ier) serial8250_stop_rx(&up->port); if (up->port.rs485.flags & SER_RS485_RTS_ON_SEND) @@ -1605,7 +1608,7 @@ static bool start_tx_rs485(struct uart_port *port) if (em485->tx_stopped) { em485->tx_stopped = false; - up->rs485_start_tx(up); + up->rs485_start_tx(up, true); if (up->port.rs485.delay_rts_before_send > 0) { em485->active_timer = &em485->start_tx_timer; @@ -1931,7 +1934,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) */ if (!(status & (UART_LSR_FIFOE | UART_LSR_BRK_ERROR_BITS)) && (port->status & (UPSTAT_AUTOCTS | UPSTAT_AUTORTS)) && - !(port->read_status_mask & UART_LSR_DR)) + !(up->ier & (UART_IER_RLSI | UART_IER_RDI))) skip_rx = true; if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { @@ -2079,11 +2082,20 @@ static void serial8250_break_ctl(struct uart_port *port, int break_state) serial8250_rpm_put(up); } -static void wait_for_lsr(struct uart_8250_port *up, int bits) +/* Returns true if @bits were set, false on timeout */ +static bool wait_for_lsr(struct uart_8250_port *up, int bits) { - unsigned int status, tmout = 10000; + unsigned int status, tmout; + + /* + * Wait for a character to be sent. Fallback to a safe default + * timeout value if @frame_time is not available. + */ + if (up->port.frame_time) + tmout = up->port.frame_time * 2 / NSEC_PER_USEC; + else + tmout = 10000; - /* Wait up to 10ms for the character(s) to be sent. */ for (;;) { status = serial_lsr_in(up); @@ -2094,11 +2106,11 @@ static void wait_for_lsr(struct uart_8250_port *up, int bits) udelay(1); touch_nmi_watchdog(); } + + return (tmout != 0); } -/* - * Wait for transmitter & holding register to empty - */ +/* Wait for transmitter and holding register to empty with timeout */ static void wait_for_xmitr(struct uart_8250_port *up, int bits) { unsigned int tmout; @@ -2786,7 +2798,13 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, */ uart_update_timeout(port, termios->c_cflag, baud); - port->read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR; + /* + * Specify which conditions may be considered for error + * handling and the ignoring of characters. The actual + * ignoring of characters only occurs if the bit is set + * in @ignore_status_mask as well. + */ + port->read_status_mask = UART_LSR_OE | UART_LSR_DR; if (termios->c_iflag & INPCK) port->read_status_mask |= UART_LSR_FE | UART_LSR_PE; if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) @@ -3250,7 +3268,7 @@ void serial8250_init_port(struct uart_8250_port *up) port->ops = &serial8250_pops; port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); - up->cur_iotype = 0xFF; + up->cur_iotype = UPIO_UNKNOWN; } EXPORT_SYMBOL_GPL(serial8250_init_port); @@ -3284,11 +3302,16 @@ EXPORT_SYMBOL_GPL(serial8250_set_defaults); #ifdef CONFIG_SERIAL_8250_CONSOLE static void serial8250_console_putchar(struct uart_port *port, unsigned char ch) +{ + serial_port_out(port, UART_TX, ch); +} + +static void serial8250_console_wait_putchar(struct uart_port *port, unsigned char ch) { struct uart_8250_port *up = up_to_u8250p(port); wait_for_xmitr(up, UART_LSR_THRE); - serial_port_out(port, UART_TX, ch); + serial8250_console_putchar(port, ch); } /* @@ -3317,6 +3340,16 @@ static void serial8250_console_restore(struct uart_8250_port *up) serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS); } +static void fifo_wait_for_lsr(struct uart_8250_port *up, unsigned int count) +{ + unsigned int i; + + for (i = 0; i < count; i++) { + if (wait_for_lsr(up, UART_LSR_THRE)) + return; + } +} + /* * Print a string to the serial port using the device FIFO * @@ -3326,24 +3359,34 @@ static void serial8250_console_restore(struct uart_8250_port *up) static void serial8250_console_fifo_write(struct uart_8250_port *up, const char *s, unsigned int count) { - int i; const char *end = s + count; unsigned int fifosize = up->tx_loadsz; + struct uart_port *port = &up->port; + unsigned int tx_count = 0; bool cr_sent = false; + unsigned int i; while (s != end) { - wait_for_lsr(up, UART_LSR_THRE); + /* Allow timeout for each byte of a possibly full FIFO */ + fifo_wait_for_lsr(up, fifosize); for (i = 0; i < fifosize && s != end; ++i) { if (*s == '\n' && !cr_sent) { - serial_out(up, UART_TX, '\r'); + serial8250_console_putchar(port, '\r'); cr_sent = true; } else { - serial_out(up, UART_TX, *s++); + serial8250_console_putchar(port, *s++); cr_sent = false; } } + tx_count = i; } + + /* + * Allow timeout for each byte written since the caller will only wait + * for UART_LSR_BOTH_EMPTY using the timeout of a single character + */ + fifo_wait_for_lsr(up, tx_count); } /* @@ -3385,7 +3428,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, if (em485) { if (em485->tx_stopped) - up->rs485_start_tx(up); + up->rs485_start_tx(up, false); mdelay(port->rs485.delay_rts_before_send); } @@ -3412,7 +3455,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, if (likely(use_fifo)) serial8250_console_fifo_write(up, s, count); else - uart_console_write(port, s, count, serial8250_console_putchar); + uart_console_write(port, s, count, serial8250_console_wait_putchar); /* * Finally, wait for transmitter to become empty @@ -3423,7 +3466,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, if (em485) { mdelay(port->rs485.delay_rts_after_send); if (em485->tx_stopped) - up->rs485_stop_tx(up); + up->rs485_stop_tx(up, false); } serial_port_out(port, UART_IER, ier); diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 45f0f779fbf9..976dae3bb1bb 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -128,7 +128,7 @@ config SERIAL_SB1250_DUART_CONSOLE config SERIAL_ATMEL bool "AT91 on-chip serial port support" depends on COMMON_CLK - depends on ARCH_AT91 || COMPILE_TEST + depends on ARCH_AT91 || ARCH_LAN969X || COMPILE_TEST select SERIAL_CORE select SERIAL_MCTRL_GPIO if GPIOLIB select MFD_AT91_USART diff --git a/drivers/tty/serial/altera_jtaguart.c b/drivers/tty/serial/altera_jtaguart.c index b9c3c3bed0c1..d47a62d1c9f7 100644 --- a/drivers/tty/serial/altera_jtaguart.c +++ b/drivers/tty/serial/altera_jtaguart.c @@ -24,8 +24,6 @@ #include #include -#define DRV_NAME "altera_jtaguart" - /* * Altera JTAG UART register definitions according to the Altera JTAG UART * datasheet: https://www.altera.com/literature/hb/nios2/n2cpu_nii51009.pdf @@ -173,7 +171,7 @@ static int altera_jtaguart_startup(struct uart_port *port) int ret; ret = request_irq(port->irq, altera_jtaguart_interrupt, 0, - DRV_NAME, port); + dev_name(port->dev), port); if (ret) { dev_err(port->dev, "unable to attach Altera JTAG UART %d interrupt vector=%d\n", port->line, port->irq); @@ -365,7 +363,7 @@ OF_EARLYCON_DECLARE(juart, "altr,juart-1.0", altera_jtaguart_earlycon_setup); static struct uart_driver altera_jtaguart_driver = { .owner = THIS_MODULE, - .driver_name = "altera_jtaguart", + .driver_name = KBUILD_MODNAME, .dev_name = "ttyJ", .major = ALTERA_JTAGUART_MAJOR, .minor = ALTERA_JTAGUART_MINOR, @@ -451,7 +449,7 @@ static struct platform_driver altera_jtaguart_platform_driver = { .probe = altera_jtaguart_probe, .remove = altera_jtaguart_remove, .driver = { - .name = DRV_NAME, + .name = KBUILD_MODNAME, .of_match_table = of_match_ptr(altera_jtaguart_match), }, }; @@ -481,4 +479,4 @@ module_exit(altera_jtaguart_exit); MODULE_DESCRIPTION("Altera JTAG UART driver"); MODULE_AUTHOR("Thomas Chou "); MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:" DRV_NAME); +MODULE_ALIAS("platform:" KBUILD_MODNAME); diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c index c94655453c33..1759137121cc 100644 --- a/drivers/tty/serial/altera_uart.c +++ b/drivers/tty/serial/altera_uart.c @@ -24,7 +24,6 @@ #include #include -#define DRV_NAME "altera_uart" #define SERIAL_ALTERA_MAJOR 204 #define SERIAL_ALTERA_MINOR 213 @@ -518,7 +517,7 @@ OF_EARLYCON_DECLARE(uart, "altr,uart-1.0", altera_uart_earlycon_setup); */ static struct uart_driver altera_uart_driver = { .owner = THIS_MODULE, - .driver_name = DRV_NAME, + .driver_name = KBUILD_MODNAME, .dev_name = "ttyAL", .major = SERIAL_ALTERA_MAJOR, .minor = SERIAL_ALTERA_MINOR, @@ -619,7 +618,7 @@ static struct platform_driver altera_uart_platform_driver = { .probe = altera_uart_probe, .remove = altera_uart_remove, .driver = { - .name = DRV_NAME, + .name = KBUILD_MODNAME, .of_match_table = of_match_ptr(altera_uart_match), }, }; @@ -649,5 +648,5 @@ module_exit(altera_uart_exit); MODULE_DESCRIPTION("Altera UART driver"); MODULE_AUTHOR("Thomas Chou "); MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:" DRV_NAME); +MODULE_ALIAS("platform:" KBUILD_MODNAME); MODULE_ALIAS_CHARDEV_MAJOR(SERIAL_ALTERA_MAJOR); diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 69b7a3e1e418..04212c823a91 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -248,6 +248,13 @@ struct pl011_dmatx_data { bool queued; }; +enum pl011_rs485_tx_state { + OFF, + WAIT_AFTER_RTS, + SEND, + WAIT_AFTER_SEND, +}; + /* * We wrap our port structure around the generic uart_port. */ @@ -261,8 +268,10 @@ struct uart_amba_port { unsigned int fifosize; /* vendor-specific */ unsigned int fixed_baud; /* vendor-set fixed baud rate */ char type[12]; - bool rs485_tx_started; - unsigned int rs485_tx_drain_interval; /* usecs */ + ktime_t rs485_tx_drain_interval; /* nano */ + enum pl011_rs485_tx_state rs485_tx_state; + struct hrtimer trigger_start_tx; + struct hrtimer trigger_stop_tx; #ifdef CONFIG_DMA_ENGINE /* DMA stuff */ unsigned int dmacr; /* dma control reg */ @@ -1260,30 +1269,31 @@ static inline bool pl011_dma_rx_running(struct uart_amba_port *uap) static void pl011_rs485_tx_stop(struct uart_amba_port *uap) { - /* - * To be on the safe side only time out after twice as many iterations - * as fifo size. - */ - const int MAX_TX_DRAIN_ITERS = uap->port.fifosize * 2; struct uart_port *port = &uap->port; - int i = 0; u32 cr; - /* Wait until hardware tx queue is empty */ - while (!pl011_tx_empty(port)) { - if (i > MAX_TX_DRAIN_ITERS) { - dev_warn(port->dev, - "timeout while draining hardware tx queue\n"); - break; + if (uap->rs485_tx_state == SEND) + uap->rs485_tx_state = WAIT_AFTER_SEND; + + if (uap->rs485_tx_state == WAIT_AFTER_SEND) { + /* Schedule hrtimer if tx queue not empty */ + if (!pl011_tx_empty(port)) { + hrtimer_start(&uap->trigger_stop_tx, + uap->rs485_tx_drain_interval, + HRTIMER_MODE_REL); + return; } - - udelay(uap->rs485_tx_drain_interval); - i++; + if (port->rs485.delay_rts_after_send > 0) { + hrtimer_start(&uap->trigger_stop_tx, + ms_to_ktime(port->rs485.delay_rts_after_send), + HRTIMER_MODE_REL); + return; + } + /* Continue without any delay */ + } else if (uap->rs485_tx_state == WAIT_AFTER_RTS) { + hrtimer_try_to_cancel(&uap->trigger_start_tx); } - if (port->rs485.delay_rts_after_send) - mdelay(port->rs485.delay_rts_after_send); - cr = pl011_read(uap, REG_CR); if (port->rs485.flags & SER_RS485_RTS_AFTER_SEND) @@ -1296,7 +1306,7 @@ static void pl011_rs485_tx_stop(struct uart_amba_port *uap) cr |= UART011_CR_RXE; pl011_write(cr, uap, REG_CR); - uap->rs485_tx_started = false; + uap->rs485_tx_state = OFF; } static void pl011_stop_tx(struct uart_port *port) @@ -1304,11 +1314,18 @@ static void pl011_stop_tx(struct uart_port *port) struct uart_amba_port *uap = container_of(port, struct uart_amba_port, port); + if (port->rs485.flags & SER_RS485_ENABLED && + uap->rs485_tx_state == WAIT_AFTER_RTS) { + pl011_rs485_tx_stop(uap); + return; + } + uap->im &= ~UART011_TXIM; pl011_write(uap->im, uap, REG_IMSC); pl011_dma_tx_stop(uap); - if ((port->rs485.flags & SER_RS485_ENABLED) && uap->rs485_tx_started) + if (port->rs485.flags & SER_RS485_ENABLED && + uap->rs485_tx_state != OFF) pl011_rs485_tx_stop(uap); } @@ -1328,10 +1345,19 @@ static void pl011_rs485_tx_start(struct uart_amba_port *uap) struct uart_port *port = &uap->port; u32 cr; + if (uap->rs485_tx_state == WAIT_AFTER_RTS) { + uap->rs485_tx_state = SEND; + return; + } + if (uap->rs485_tx_state == WAIT_AFTER_SEND) { + hrtimer_try_to_cancel(&uap->trigger_stop_tx); + uap->rs485_tx_state = SEND; + return; + } + /* uap->rs485_tx_state == OFF */ /* Enable transmitter */ cr = pl011_read(uap, REG_CR); cr |= UART011_CR_TXE; - /* Disable receiver if half-duplex */ if (!(port->rs485.flags & SER_RS485_RX_DURING_TX)) cr &= ~UART011_CR_RXE; @@ -1343,10 +1369,14 @@ static void pl011_rs485_tx_start(struct uart_amba_port *uap) pl011_write(cr, uap, REG_CR); - if (port->rs485.delay_rts_before_send) - mdelay(port->rs485.delay_rts_before_send); - - uap->rs485_tx_started = true; + if (port->rs485.delay_rts_before_send > 0) { + uap->rs485_tx_state = WAIT_AFTER_RTS; + hrtimer_start(&uap->trigger_start_tx, + ms_to_ktime(port->rs485.delay_rts_before_send), + HRTIMER_MODE_REL); + } else { + uap->rs485_tx_state = SEND; + } } static void pl011_start_tx(struct uart_port *port) @@ -1355,13 +1385,44 @@ static void pl011_start_tx(struct uart_port *port) container_of(port, struct uart_amba_port, port); if ((uap->port.rs485.flags & SER_RS485_ENABLED) && - !uap->rs485_tx_started) + uap->rs485_tx_state != SEND) { pl011_rs485_tx_start(uap); + if (uap->rs485_tx_state == WAIT_AFTER_RTS) + return; + } if (!pl011_dma_tx_start(uap)) pl011_start_tx_pio(uap); } +static enum hrtimer_restart pl011_trigger_start_tx(struct hrtimer *t) +{ + struct uart_amba_port *uap = + container_of(t, struct uart_amba_port, trigger_start_tx); + unsigned long flags; + + uart_port_lock_irqsave(&uap->port, &flags); + if (uap->rs485_tx_state == WAIT_AFTER_RTS) + pl011_start_tx(&uap->port); + uart_port_unlock_irqrestore(&uap->port, flags); + + return HRTIMER_NORESTART; +} + +static enum hrtimer_restart pl011_trigger_stop_tx(struct hrtimer *t) +{ + struct uart_amba_port *uap = + container_of(t, struct uart_amba_port, trigger_stop_tx); + unsigned long flags; + + uart_port_lock_irqsave(&uap->port, &flags); + if (uap->rs485_tx_state == WAIT_AFTER_SEND) + pl011_rs485_tx_stop(uap); + uart_port_unlock_irqrestore(&uap->port, flags); + + return HRTIMER_NORESTART; +} + static void pl011_stop_rx(struct uart_port *port) { struct uart_amba_port *uap = @@ -1953,7 +2014,7 @@ static void pl011_shutdown(struct uart_port *port) pl011_dma_shutdown(uap); - if ((port->rs485.flags & SER_RS485_ENABLED) && uap->rs485_tx_started) + if ((port->rs485.flags & SER_RS485_ENABLED && uap->rs485_tx_state != OFF)) pl011_rs485_tx_stop(uap); free_irq(uap->port.irq, uap); @@ -2098,7 +2159,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios, * with the given baud rate. We use this as the poll interval when we * wait for the tx queue to empty. */ - uap->rs485_tx_drain_interval = DIV_ROUND_UP(bits * 1000 * 1000, baud); + uap->rs485_tx_drain_interval = ns_to_ktime(DIV_ROUND_UP(bits * NSEC_PER_SEC, baud)); pl011_setup_status_masks(port, termios); @@ -2807,6 +2868,11 @@ static int pl011_probe(struct amba_device *dev, const struct amba_id *id) } } + hrtimer_init(&uap->trigger_start_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&uap->trigger_stop_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + uap->trigger_start_tx.function = pl011_trigger_start_tx; + uap->trigger_stop_tx.function = pl011_trigger_stop_tx; + ret = pl011_setup_port(&dev->dev, uap, &dev->res, portnr); if (ret) return ret; diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 0cf05ac18993..f44f9d20a974 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -1727,26 +1727,16 @@ static void atmel_init_property(struct atmel_uart_port *atmel_port, /* DMA/PDC usage specification */ if (of_property_read_bool(np, "atmel,use-dma-rx")) { - if (of_property_read_bool(np, "dmas")) { - atmel_port->use_dma_rx = true; - atmel_port->use_pdc_rx = false; - } else { - atmel_port->use_dma_rx = false; - atmel_port->use_pdc_rx = true; - } + atmel_port->use_dma_rx = of_property_present(np, "dmas"); + atmel_port->use_pdc_rx = !atmel_port->use_dma_rx; } else { atmel_port->use_dma_rx = false; atmel_port->use_pdc_rx = false; } if (of_property_read_bool(np, "atmel,use-dma-tx")) { - if (of_property_read_bool(np, "dmas")) { - atmel_port->use_dma_tx = true; - atmel_port->use_pdc_tx = false; - } else { - atmel_port->use_dma_tx = false; - atmel_port->use_pdc_tx = true; - } + atmel_port->use_dma_tx = of_property_present(np, "dmas"); + atmel_port->use_pdc_tx = !atmel_port->use_dma_tx; } else { atmel_port->use_dma_tx = false; atmel_port->use_pdc_tx = false; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 57b0632a3db6..c91b9d9818cd 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -245,7 +245,7 @@ #define DRIVER_NAME "fsl-lpuart" #define DEV_NAME "ttyLP" -#define UART_NR 8 +#define UART_NR 12 /* IMX lpuart has four extra unused regs located at the beginning */ #define IMX_REG_OFF 0x10 @@ -1965,6 +1965,11 @@ static void lpuart32_shutdown(struct uart_port *port) UARTCTRL_TIE | UARTCTRL_TCIE | UARTCTRL_RIE | UARTCTRL_SBK); lpuart32_write(port, temp, UARTCTRL); + /* flush Rx/Tx FIFO */ + temp = lpuart32_read(port, UARTFIFO); + temp |= UARTFIFO_TXFLUSH | UARTFIFO_RXFLUSH; + lpuart32_write(port, temp, UARTFIFO); + uart_port_unlock_irqrestore(port, flags); lpuart_dma_shutdown(sport); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 17f70e4bee43..9c59ec128bb4 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2692,7 +2692,7 @@ static void imx_uart_enable_wakeup(struct imx_port *sport, bool on) { u32 ucr3; - uart_port_lock(&sport->port); + uart_port_lock_irq(&sport->port); ucr3 = imx_uart_readl(sport, UCR3); if (on) { @@ -2714,7 +2714,7 @@ static void imx_uart_enable_wakeup(struct imx_port *sport, bool on) imx_uart_writel(sport, ucr1, UCR1); } - uart_port_unlock(&sport->port); + uart_port_unlock_irq(&sport->port); } static int imx_uart_suspend_noirq(struct device *dev) diff --git a/drivers/tty/serial/kgdb_nmi.c b/drivers/tty/serial/kgdb_nmi.c index e93850f6447a..2833708e369f 100644 --- a/drivers/tty/serial/kgdb_nmi.c +++ b/drivers/tty/serial/kgdb_nmi.c @@ -27,18 +27,6 @@ #include #include -static int kgdb_nmi_knock = 1; -module_param_named(knock, kgdb_nmi_knock, int, 0600); -MODULE_PARM_DESC(knock, "if set to 1 (default), the special '$3#33' command " \ - "must be used to enter the debugger; when set to 0, " \ - "hitting return key is enough to enter the debugger; " \ - "when set to -1, the debugger is entered immediately " \ - "upon NMI"); - -static char *kgdb_nmi_magic = "$3#33"; -module_param_named(magic, kgdb_nmi_magic, charp, 0600); -MODULE_PARM_DESC(magic, "magic sequence to enter NMI debugger (default $3#33)"); - static atomic_t kgdb_nmi_num_readers = ATOMIC_INIT(0); static int kgdb_nmi_console_setup(struct console *co, char *options) @@ -95,95 +83,6 @@ struct kgdb_nmi_tty_priv { static struct tty_port *kgdb_nmi_port; -static void kgdb_tty_recv(int ch) -{ - struct kgdb_nmi_tty_priv *priv; - char c = ch; - - if (!kgdb_nmi_port || ch < 0) - return; - /* - * Can't use port->tty->driver_data as tty might be not there. Timer - * will check for tty and will get the ref, but here we don't have to - * do that, and actually, we can't: we're in NMI context, no locks are - * possible. - */ - priv = container_of(kgdb_nmi_port, struct kgdb_nmi_tty_priv, port); - kfifo_in(&priv->fifo, &c, 1); -} - -static int kgdb_nmi_poll_one_knock(void) -{ - static int n; - int c; - const char *magic = kgdb_nmi_magic; - size_t m = strlen(magic); - bool printch = false; - - c = dbg_io_ops->read_char(); - if (c == NO_POLL_CHAR) - return c; - - if (!kgdb_nmi_knock && (c == '\r' || c == '\n')) { - return 1; - } else if (c == magic[n]) { - n = (n + 1) % m; - if (!n) - return 1; - printch = true; - } else { - n = 0; - } - - if (atomic_read(&kgdb_nmi_num_readers)) { - kgdb_tty_recv(c); - return 0; - } - - if (printch) { - kdb_printf("%c", c); - return 0; - } - - kdb_printf("\r%s %s to enter the debugger> %*s", - kgdb_nmi_knock ? "Type" : "Hit", - kgdb_nmi_knock ? magic : "", (int)m, ""); - while (m--) - kdb_printf("\b"); - return 0; -} - -/** - * kgdb_nmi_poll_knock - Check if it is time to enter the debugger - * - * "Serial ports are often noisy, especially when muxed over another port (we - * often use serial over the headset connector). Noise on the async command - * line just causes characters that are ignored, on a command line that blocked - * execution noise would be catastrophic." -- Colin Cross - * - * So, this function implements KGDB/KDB knocking on the serial line: we won't - * enter the debugger until we receive a known magic phrase (which is actually - * "$3#33", known as "escape to KDB" command. There is also a relaxed variant - * of knocking, i.e. just pressing the return key is enough to enter the - * debugger. And if knocking is disabled, the function always returns 1. - */ -bool kgdb_nmi_poll_knock(void) -{ - if (kgdb_nmi_knock < 0) - return true; - - while (1) { - int ret; - - ret = kgdb_nmi_poll_one_knock(); - if (ret == NO_POLL_CHAR) - return false; - else if (ret == 1) - break; - } - return true; -} - /* * The tasklet is cheap, it does not cause wakeups when reschedules itself, * instead it waits for the next tick. diff --git a/drivers/tty/serial/mpc52xx_uart.c b/drivers/tty/serial/mpc52xx_uart.c index f55aa353aed9..2204cc3e3b07 100644 --- a/drivers/tty/serial/mpc52xx_uart.c +++ b/drivers/tty/serial/mpc52xx_uart.c @@ -1621,7 +1621,7 @@ mpc52xx_console_setup(struct console *co, char *options) (void *)port->mapbase, port->membase, port->irq, port->uartclk); - /* Setup the port parameters accoding to options */ + /* Setup the port parameters according to options */ if (options) uart_parse_options(options, &baud, &parity, &bits, &flow); else diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index a3093e09309f..7b51cdc274fd 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -314,6 +314,7 @@ #define SC16IS7XX_FIFO_SIZE (64) #define SC16IS7XX_GPIOS_PER_BANK 4 +#define SC16IS7XX_POLL_PERIOD_MS 10 #define SC16IS7XX_RECONF_MD BIT(0) #define SC16IS7XX_RECONF_IER BIT(1) #define SC16IS7XX_RECONF_RS485 BIT(2) @@ -348,6 +349,8 @@ struct sc16is7xx_port { u8 mctrl_mask; struct kthread_worker kworker; struct task_struct *kworker_task; + struct kthread_delayed_work poll_work; + bool polling; struct sc16is7xx_one p[]; }; @@ -861,6 +864,18 @@ static irqreturn_t sc16is7xx_irq(int irq, void *dev_id) return IRQ_HANDLED; } +static void sc16is7xx_poll_proc(struct kthread_work *ws) +{ + struct sc16is7xx_port *s = container_of(ws, struct sc16is7xx_port, poll_work.work); + + /* Reuse standard IRQ handler. Interrupt ID is unused in this context. */ + sc16is7xx_irq(0, s); + + /* Setup delay based on SC16IS7XX_POLL_PERIOD_MS */ + kthread_queue_delayed_work(&s->kworker, &s->poll_work, + msecs_to_jiffies(SC16IS7XX_POLL_PERIOD_MS)); +} + static void sc16is7xx_tx_proc(struct kthread_work *ws) { struct uart_port *port = &(to_sc16is7xx_one(ws, tx_work)->port); @@ -1149,6 +1164,7 @@ static int sc16is7xx_config_rs485(struct uart_port *port, struct ktermios *termi static int sc16is7xx_startup(struct uart_port *port) { struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); + struct sc16is7xx_port *s = dev_get_drvdata(port->dev); unsigned int val; unsigned long flags; @@ -1211,6 +1227,10 @@ static int sc16is7xx_startup(struct uart_port *port) sc16is7xx_enable_ms(port); uart_port_unlock_irqrestore(port, flags); + if (s->polling) + kthread_queue_delayed_work(&s->kworker, &s->poll_work, + msecs_to_jiffies(SC16IS7XX_POLL_PERIOD_MS)); + return 0; } @@ -1232,6 +1252,9 @@ static void sc16is7xx_shutdown(struct uart_port *port) sc16is7xx_power(port, 0); + if (s->polling) + kthread_cancel_delayed_work_sync(&s->poll_work); + kthread_flush_worker(&s->kworker); } @@ -1538,6 +1561,11 @@ int sc16is7xx_probe(struct device *dev, const struct sc16is7xx_devtype *devtype, /* Always ask for fixed clock rate from a property. */ device_property_read_u32(dev, "clock-frequency", &uartclk); + s->polling = !!irq; + if (s->polling) + dev_dbg(dev, + "No interrupt pin definition, falling back to polling mode\n"); + s->clk = devm_clk_get_optional(dev, NULL); if (IS_ERR(s->clk)) return PTR_ERR(s->clk); @@ -1665,6 +1693,12 @@ int sc16is7xx_probe(struct device *dev, const struct sc16is7xx_devtype *devtype, goto out_ports; #endif + if (s->polling) { + /* Initialize kernel thread for polling */ + kthread_init_delayed_work(&s->poll_work, sc16is7xx_poll_proc); + return 0; + } + /* * Setup interrupt. We first try to acquire the IRQ line as level IRQ. * If that succeeds, we can allow sharing the interrupt as well. @@ -1724,6 +1758,9 @@ void sc16is7xx_remove(struct device *dev) sc16is7xx_power(&s->p[i].port, 0); } + if (s->polling) + kthread_cancel_delayed_work_sync(&s->poll_work); + kthread_flush_worker(&s->kworker); kthread_stop(s->kworker_task); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 74fa02b23772..92f7e752f862 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -790,7 +790,6 @@ static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; - int ret = -ENODEV; /* Initialize structure in case we error out later to prevent any stack info leakage. */ *retinfo = (struct serial_struct){}; @@ -799,10 +798,10 @@ static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo) * Ensure the state we copy is consistent and no hardware changes * occur as we go */ - mutex_lock(&port->mutex); + guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) - goto out; + return -ENODEV; retinfo->type = uport->type; retinfo->line = uport->line; @@ -823,10 +822,7 @@ static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo) retinfo->iomem_reg_shift = uport->regshift; retinfo->iomem_base = (void *)(unsigned long)uport->mapbase; - ret = 0; -out: - mutex_unlock(&port->mutex); - return ret; + return 0; } static int uart_get_info_user(struct tty_struct *tty, @@ -838,6 +834,61 @@ static int uart_get_info_user(struct tty_struct *tty, return uart_get_info(port, ss) < 0 ? -EIO : 0; } +static int uart_change_port(struct uart_port *uport, + const struct serial_struct *new_info, + unsigned long new_port) +{ + unsigned long old_iobase, old_mapbase; + unsigned int old_type, old_iotype, old_hub6, old_shift; + int retval; + + old_iobase = uport->iobase; + old_mapbase = uport->mapbase; + old_type = uport->type; + old_hub6 = uport->hub6; + old_iotype = uport->iotype; + old_shift = uport->regshift; + + if (old_type != PORT_UNKNOWN && uport->ops->release_port) + uport->ops->release_port(uport); + + uport->iobase = new_port; + uport->type = new_info->type; + uport->hub6 = new_info->hub6; + uport->iotype = new_info->io_type; + uport->regshift = new_info->iomem_reg_shift; + uport->mapbase = (unsigned long)new_info->iomem_base; + + if (uport->type == PORT_UNKNOWN || !uport->ops->request_port) + return 0; + + retval = uport->ops->request_port(uport); + if (retval == 0) + return 0; /* succeeded => done */ + + /* + * If we fail to request resources for the new port, try to restore the + * old settings. + */ + uport->iobase = old_iobase; + uport->type = old_type; + uport->hub6 = old_hub6; + uport->iotype = old_iotype; + uport->regshift = old_shift; + uport->mapbase = old_mapbase; + + if (old_type == PORT_UNKNOWN) + return retval; + + retval = uport->ops->request_port(uport); + /* If we failed to restore the old settings, we fail like this. */ + if (retval) + uport->type = PORT_UNKNOWN; + + /* We failed anyway. */ + return -EBUSY; +} + static int uart_set_info(struct tty_struct *tty, struct tty_port *port, struct uart_state *state, struct serial_struct *new_info) @@ -847,7 +898,7 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, unsigned int change_irq, change_port, closing_wait; unsigned int old_custom_divisor, close_delay; upf_t old_flags, new_flags; - int retval = 0; + int retval; if (!uport) return -EIO; @@ -886,13 +937,10 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, if (!(uport->flags & UPF_FIXED_PORT)) { unsigned int uartclk = new_info->baud_base * 16; /* check needs to be done here before other settings made */ - if (uartclk == 0) { - retval = -EINVAL; - goto exit; - } + if (uartclk == 0) + return -EINVAL; } if (!capable(CAP_SYS_ADMIN)) { - retval = -EPERM; if (change_irq || change_port || (new_info->baud_base != uport->uartclk / 16) || (close_delay != port->close_delay) || @@ -900,7 +948,7 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, (new_info->xmit_fifo_size && new_info->xmit_fifo_size != uport->fifosize) || (((new_flags ^ old_flags) & ~UPF_USR_MASK) != 0)) - goto exit; + return -EPERM; uport->flags = ((uport->flags & ~UPF_USR_MASK) | (new_flags & UPF_USR_MASK)); uport->custom_divisor = new_info->custom_divisor; @@ -910,30 +958,24 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, if (change_irq || change_port) { retval = security_locked_down(LOCKDOWN_TIOCSSERIAL); if (retval) - goto exit; + return retval; } - /* - * Ask the low level driver to verify the settings. - */ - if (uport->ops->verify_port) + /* Ask the low level driver to verify the settings. */ + if (uport->ops->verify_port) { retval = uport->ops->verify_port(uport, new_info); + if (retval) + return retval; + } if ((new_info->irq >= irq_get_nr_irqs()) || (new_info->irq < 0) || (new_info->baud_base < 9600)) - retval = -EINVAL; - - if (retval) - goto exit; + return -EINVAL; if (change_port || change_irq) { - retval = -EBUSY; - - /* - * Make sure that we are the sole user of this port. - */ + /* Make sure that we are the sole user of this port. */ if (tty_port_users(port) > 1) - goto exit; + return -EBUSY; /* * We need to shutdown the serial port at the old @@ -943,69 +985,9 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, } if (change_port) { - unsigned long old_iobase, old_mapbase; - unsigned int old_type, old_iotype, old_hub6, old_shift; - - old_iobase = uport->iobase; - old_mapbase = uport->mapbase; - old_type = uport->type; - old_hub6 = uport->hub6; - old_iotype = uport->iotype; - old_shift = uport->regshift; - - /* - * Free and release old regions - */ - if (old_type != PORT_UNKNOWN && uport->ops->release_port) - uport->ops->release_port(uport); - - uport->iobase = new_port; - uport->type = new_info->type; - uport->hub6 = new_info->hub6; - uport->iotype = new_info->io_type; - uport->regshift = new_info->iomem_reg_shift; - uport->mapbase = (unsigned long)new_info->iomem_base; - - /* - * Claim and map the new regions - */ - if (uport->type != PORT_UNKNOWN && uport->ops->request_port) { - retval = uport->ops->request_port(uport); - } else { - /* Always success - Jean II */ - retval = 0; - } - - /* - * If we fail to request resources for the - * new port, try to restore the old settings. - */ - if (retval) { - uport->iobase = old_iobase; - uport->type = old_type; - uport->hub6 = old_hub6; - uport->iotype = old_iotype; - uport->regshift = old_shift; - uport->mapbase = old_mapbase; - - if (old_type != PORT_UNKNOWN) { - retval = uport->ops->request_port(uport); - /* - * If we failed to restore the old settings, - * we fail like this. - */ - if (retval) - uport->type = PORT_UNKNOWN; - - /* - * We failed anyway. - */ - retval = -EBUSY; - } - - /* Added to return the correct error -Ram Gupta */ - goto exit; - } + retval = uart_change_port(uport, new_info, new_port); + if (retval) + return retval; } if (change_irq) @@ -1021,9 +1003,9 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, uport->fifosize = new_info->xmit_fifo_size; check_and_exit: - retval = 0; if (uport->type == PORT_UNKNOWN) - goto exit; + return 0; + if (tty_port_initialized(port)) { if (((old_flags ^ uport->flags) & UPF_SPD_MASK) || old_custom_divisor != uport->custom_divisor) { @@ -1039,15 +1021,17 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, } uart_change_line_settings(tty, state, NULL); } - } else { - retval = uart_startup(tty, state, true); - if (retval == 0) - tty_port_set_initialized(port, true); - if (retval > 0) - retval = 0; + + return 0; } - exit: - return retval; + + retval = uart_startup(tty, state, true); + if (retval < 0) + return retval; + if (retval == 0) + tty_port_set_initialized(port, true); + + return 0; } static int uart_set_info_user(struct tty_struct *tty, struct serial_struct *ss) @@ -2365,9 +2349,9 @@ struct uart_match { struct uart_driver *driver; }; -static int serial_match_port(struct device *dev, void *data) +static int serial_match_port(struct device *dev, const void *data) { - struct uart_match *match = data; + const struct uart_match *match = data; struct tty_driver *tty_drv = match->driver->tty_driver; dev_t devt = MKDEV(tty_drv->major, tty_drv->minor_start) + match->port->line; @@ -3061,26 +3045,25 @@ static ssize_t console_store(struct device *dev, if (ret) return ret; - mutex_lock(&port->mutex); + guard(mutex)(&port->mutex); uport = uart_port_check(state); - if (uport) { - oldconsole = uart_console_registered(uport); - if (oldconsole && !newconsole) { - ret = unregister_console(uport->cons); - } else if (!oldconsole && newconsole) { - if (uart_console(uport)) { - uport->console_reinit = 1; - register_console(uport->cons); - } else { - ret = -ENOENT; - } - } - } else { - ret = -ENXIO; - } - mutex_unlock(&port->mutex); + if (!uport) + return -ENXIO; - return ret < 0 ? ret : count; + oldconsole = uart_console_registered(uport); + if (oldconsole && !newconsole) { + ret = unregister_console(uport->cons); + if (ret < 0) + return ret; + } else if (!oldconsole && newconsole) { + if (!uart_console(uport)) + return -ENOENT; + + uport->console_reinit = 1; + register_console(uport->cons); + } + + return count; } static DEVICE_ATTR_RO(uartclk); @@ -3136,7 +3119,6 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u { struct uart_state *state; struct tty_port *port; - int ret = 0; struct device *tty_dev; int num_groups; @@ -3146,11 +3128,9 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u state = drv->state + uport->line; port = &state->port; - mutex_lock(&port->mutex); - if (state->uart_port) { - ret = -EINVAL; - goto out; - } + guard(mutex)(&port->mutex); + if (state->uart_port) + return -EINVAL; /* Link the port to the driver state table and vice versa */ atomic_set(&state->refcount, 1); @@ -3170,10 +3150,8 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u uport->minor = drv->tty_driver->minor_start + uport->line; uport->name = kasprintf(GFP_KERNEL, "%s%d", drv->dev_name, drv->tty_driver->name_base + uport->line); - if (!uport->name) { - ret = -ENOMEM; - goto out; - } + if (!uport->name) + return -ENOMEM; if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); @@ -3189,10 +3167,9 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u uport->tty_groups = kcalloc(num_groups, sizeof(*uport->tty_groups), GFP_KERNEL); - if (!uport->tty_groups) { - ret = -ENOMEM; - goto out; - } + if (!uport->tty_groups) + return -ENOMEM; + uport->tty_groups[0] = &tty_dev_attr_group; if (uport->attr_group) uport->tty_groups[1] = uport->attr_group; @@ -3215,10 +3192,7 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u uport->line); } - out: - mutex_unlock(&port->mutex); - - return ret; + return 0; } /** @@ -3384,7 +3358,7 @@ int serial_core_register_port(struct uart_driver *drv, struct uart_port *port) struct serial_ctrl_device *ctrl_dev, *new_ctrl_dev = NULL; int ret; - mutex_lock(&port_mutex); + guard(mutex)(&port_mutex); /* * Prevent serial_port_runtime_resume() from trying to use the port @@ -3396,10 +3370,8 @@ int serial_core_register_port(struct uart_driver *drv, struct uart_port *port) ctrl_dev = serial_core_ctrl_find(drv, port->dev, port->ctrl_id); if (!ctrl_dev) { new_ctrl_dev = serial_core_ctrl_device_add(port); - if (IS_ERR(new_ctrl_dev)) { - ret = PTR_ERR(new_ctrl_dev); - goto err_unlock; - } + if (IS_ERR(new_ctrl_dev)) + return PTR_ERR(new_ctrl_dev); ctrl_dev = new_ctrl_dev; } @@ -3420,8 +3392,6 @@ int serial_core_register_port(struct uart_driver *drv, struct uart_port *port) if (ret) goto err_unregister_port_dev; - mutex_unlock(&port_mutex); - return 0; err_unregister_port_dev: @@ -3430,9 +3400,6 @@ err_unregister_port_dev: err_unregister_ctrl_dev: serial_base_ctrl_device_remove(new_ctrl_dev); -err_unlock: - mutex_unlock(&port_mutex); - return ret; } diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 924b803af440..b1ea48f38248 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -165,6 +165,8 @@ struct sci_port { static struct sci_port sci_ports[SCI_NPORTS]; static unsigned long sci_ports_in_use; static struct uart_driver sci_uart_driver; +static bool sci_uart_earlycon; +static bool sci_uart_earlycon_dev_probing; static inline struct sci_port * to_sci_port(struct uart_port *uart) @@ -3056,10 +3058,6 @@ static int sci_init_single(struct platform_device *dev, ret = sci_init_clocks(sci_port, &dev->dev); if (ret < 0) return ret; - - port->dev = &dev->dev; - - pm_runtime_enable(&dev->dev); } port->type = p->type; @@ -3086,11 +3084,6 @@ static int sci_init_single(struct platform_device *dev, return 0; } -static void sci_cleanup_single(struct sci_port *port) -{ - pm_runtime_disable(port->port.dev); -} - #if defined(CONFIG_SERIAL_SH_SCI_CONSOLE) || \ defined(CONFIG_SERIAL_SH_SCI_EARLYCON) static void serial_console_putchar(struct uart_port *port, unsigned char ch) @@ -3260,8 +3253,6 @@ static void sci_remove(struct platform_device *dev) sci_ports_in_use &= ~BIT(port->port.line); uart_remove_one_port(&sci_uart_driver, &port->port); - sci_cleanup_single(port); - if (port->port.fifosize > 1) device_remove_file(&dev->dev, &dev_attr_rx_fifo_trigger); if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF) @@ -3396,7 +3387,8 @@ static struct plat_sci_port *sci_parse_dt(struct platform_device *pdev, static int sci_probe_single(struct platform_device *dev, unsigned int index, struct plat_sci_port *p, - struct sci_port *sciport) + struct sci_port *sciport, + struct resource *sci_res) { int ret; @@ -3425,6 +3417,11 @@ static int sci_probe_single(struct platform_device *dev, if (ret) return ret; + sciport->port.dev = &dev->dev; + ret = devm_pm_runtime_enable(&dev->dev); + if (ret) + return ret; + sciport->gpios = mctrl_gpio_init(&sciport->port, 0); if (IS_ERR(sciport->gpios)) return PTR_ERR(sciport->gpios); @@ -3438,18 +3435,37 @@ static int sci_probe_single(struct platform_device *dev, sciport->port.flags |= UPF_HARD_FLOW; } - ret = uart_add_one_port(&sci_uart_driver, &sciport->port); - if (ret) { - sci_cleanup_single(sciport); - return ret; + if (sci_uart_earlycon && sci_ports[0].port.mapbase == sci_res->start) { + /* + * In case: + * - this is the earlycon port (mapped on index 0 in sci_ports[]) and + * - it now maps to an alias other than zero and + * - the earlycon is still alive (e.g., "earlycon keep_bootcon" is + * available in bootargs) + * + * we need to avoid disabling clocks and PM domains through the runtime + * PM APIs called in __device_attach(). For this, increment the runtime + * PM reference counter (the clocks and PM domains were already enabled + * by the bootloader). Otherwise the earlycon may access the HW when it + * has no clocks enabled leading to failures (infinite loop in + * sci_poll_put_char()). + */ + pm_runtime_get_noresume(&dev->dev); + + /* + * Skip cleanup the sci_port[0] in early_console_exit(), this + * port is the same as the earlycon one. + */ + sci_uart_earlycon_dev_probing = true; } - return 0; + return uart_add_one_port(&sci_uart_driver, &sciport->port); } static int sci_probe(struct platform_device *dev) { struct plat_sci_port *p; + struct resource *res; struct sci_port *sp; unsigned int dev_id; int ret; @@ -3479,9 +3495,29 @@ static int sci_probe(struct platform_device *dev) } sp = &sci_ports[dev_id]; + + /* + * In case: + * - the probed port alias is zero (as the one used by earlycon), and + * - the earlycon is still active (e.g., "earlycon keep_bootcon" in + * bootargs) + * + * defer the probe of this serial. This is a debug scenario and the user + * must be aware of it. + * + * Except when the probed port is the same as the earlycon port. + */ + + res = platform_get_resource(dev, IORESOURCE_MEM, 0); + if (!res) + return -ENODEV; + + if (sci_uart_earlycon && sp == &sci_ports[0] && sp->port.mapbase != res->start) + return dev_err_probe(&dev->dev, -EBUSY, "sci_port[0] is used by earlycon!\n"); + platform_set_drvdata(dev, sp); - ret = sci_probe_single(dev, dev_id, p, sp); + ret = sci_probe_single(dev, dev_id, p, sp, res); if (ret) return ret; @@ -3562,7 +3598,23 @@ sh_early_platform_init_buffer("earlyprintk", &sci_driver, early_serial_buf, ARRAY_SIZE(early_serial_buf)); #endif #ifdef CONFIG_SERIAL_SH_SCI_EARLYCON -static struct plat_sci_port port_cfg __initdata; +static struct plat_sci_port port_cfg; + +static int early_console_exit(struct console *co) +{ + struct sci_port *sci_port = &sci_ports[0]; + + /* + * Clean the slot used by earlycon. A new SCI device might + * map to this slot. + */ + if (!sci_uart_earlycon_dev_probing) { + memset(sci_port, 0, sizeof(*sci_port)); + sci_uart_earlycon = false; + } + + return 0; +} static int __init early_console_setup(struct earlycon_device *device, int type) @@ -3571,15 +3623,18 @@ static int __init early_console_setup(struct earlycon_device *device, return -ENODEV; device->port.type = type; - memcpy(&sci_ports[0].port, &device->port, sizeof(struct uart_port)); + sci_ports[0].port = device->port; port_cfg.type = type; sci_ports[0].cfg = &port_cfg; sci_ports[0].params = sci_probe_regmap(&port_cfg); + sci_uart_earlycon = true; port_cfg.scscr = sci_serial_in(&sci_ports[0].port, SCSCR); sci_serial_out(&sci_ports[0].port, SCSCR, SCSCR_RE | SCSCR_TE | port_cfg.scscr); device->con->write = serial_console_write; + device->con->exit = early_console_exit; + return 0; } static int __init sci_early_console_setup(struct earlycon_device *device, diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 7dc254546075..1ec5d8c3aef8 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -1051,14 +1051,14 @@ static void stm32_usart_break_ctl(struct uart_port *port, int break_state) const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; unsigned long flags; - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); if (break_state) stm32_usart_set_bits(port, ofs->rqr, USART_RQR_SBKRQ); else stm32_usart_clr_bits(port, ofs->rqr, USART_RQR_SBKRQ); - spin_unlock_irqrestore(&port->lock, flags); + uart_port_unlock_irqrestore(port, flags); } static int stm32_usart_startup(struct uart_port *port) diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index beb151be4d32..92ec51870d1d 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -287,7 +287,7 @@ static void cdns_uart_handle_rx(void *dev_id, unsigned int isrstatus) continue; } - if (uart_handle_sysrq_char(port, data)) + if (uart_prepare_sysrq_char(port, data)) continue; if (is_rxbs_support) { @@ -495,7 +495,7 @@ static irqreturn_t cdns_uart_isr(int irq, void *dev_id) !(readl(port->membase + CDNS_UART_CR) & CDNS_UART_CR_RX_DIS)) cdns_uart_handle_rx(dev_id, isrstatus); - uart_port_unlock(port); + uart_unlock_and_check_sysrq(port); return IRQ_HANDLED; } @@ -1380,9 +1380,7 @@ static void cdns_uart_console_write(struct console *co, const char *s, unsigned int imr, ctrl; int locked = 1; - if (port->sysrq) - locked = 0; - else if (oops_in_progress) + if (oops_in_progress) locked = uart_port_trylock_irqsave(port, &flags); else uart_port_lock_irqsave(port, &flags); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index dcb1769c3625..449dbd216460 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2622,14 +2622,13 @@ static int tty_tiocgicount(struct tty_struct *tty, void __user *arg) static int tty_set_serial(struct tty_struct *tty, struct serial_struct *ss) { - char comm[TASK_COMM_LEN]; int flags; flags = ss->flags & ASYNC_DEPRECATED; if (flags) pr_warn_ratelimited("%s: '%s' is using deprecated serial flags (with no effect): %.8x\n", - __func__, get_task_comm(comm, current), flags); + __func__, current->comm, flags); if (!tty->ops->set_serial) return -ENOTTY; @@ -3618,7 +3617,7 @@ void console_sysfs_notify(void) sysfs_notify(&consdev->kobj, NULL, "active"); } -static struct ctl_table tty_table[] = { +static const struct ctl_table tty_table[] = { { .procname = "legacy_tiocsti", .data = &tty_legacy_tiocsti, diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c index 564341f1a74f..0bd6544e30a6 100644 --- a/drivers/tty/vt/selection.c +++ b/drivers/tty/vt/selection.c @@ -192,6 +192,20 @@ int set_selection_user(const struct tiocl_selection __user *sel, if (copy_from_user(&v, sel, sizeof(*sel))) return -EFAULT; + /* + * TIOCL_SELCLEAR, TIOCL_SELPOINTER and TIOCL_SELMOUSEREPORT are OK to + * use without CAP_SYS_ADMIN as they do not modify the selection. + */ + switch (v.sel_mode) { + case TIOCL_SELCLEAR: + case TIOCL_SELPOINTER: + case TIOCL_SELMOUSEREPORT: + break; + default: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + } + return set_selection_kernel(&v, tty); } diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 96842ce817af..be5564ed8c01 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -3345,8 +3345,6 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) switch (type) { case TIOCL_SETSEL: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; return set_selection_user(param, tty); case TIOCL_PASTESEL: if (!capable(CAP_SYS_ADMIN)) diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c index 796e37a1d859..3438269a5440 100644 --- a/drivers/ufs/core/ufs-sysfs.c +++ b/drivers/ufs/core/ufs-sysfs.c @@ -1439,6 +1439,7 @@ static ssize_t max_number_of_rtt_store(struct device *dev, struct ufs_hba *hba = dev_get_drvdata(dev); struct ufs_dev_info *dev_info = &hba->dev_info; struct scsi_device *sdev; + unsigned int memflags; unsigned int rtt; int ret; @@ -1458,14 +1459,16 @@ static ssize_t max_number_of_rtt_store(struct device *dev, ufshcd_rpm_get_sync(hba); + memflags = memalloc_noio_save(); shost_for_each_device(sdev, hba->host) - blk_mq_freeze_queue(sdev->request_queue); + blk_mq_freeze_queue_nomemsave(sdev->request_queue); ret = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR, QUERY_ATTR_IDN_MAX_NUM_OF_RTT, 0, 0, &rtt); shost_for_each_device(sdev, hba->host) - blk_mq_unfreeze_queue(sdev->request_queue); + blk_mq_unfreeze_queue_nomemrestore(sdev->request_queue); + memalloc_noio_restore(memflags); ufshcd_rpm_put_sync(hba); diff --git a/drivers/ufs/core/ufs_bsg.c b/drivers/ufs/core/ufs_bsg.c index 6c09d97ae006..8d4ad0a3f2cf 100644 --- a/drivers/ufs/core/ufs_bsg.c +++ b/drivers/ufs/core/ufs_bsg.c @@ -216,6 +216,7 @@ void ufs_bsg_remove(struct ufs_hba *hba) return; bsg_remove_queue(hba->bsg_queue); + hba->bsg_queue = NULL; device_del(bsg_dev); put_device(bsg_dev); @@ -257,6 +258,7 @@ int ufs_bsg_probe(struct ufs_hba *hba) NULL, 0); if (IS_ERR(q)) { ret = PTR_ERR(q); + device_del(bsg_dev); goto out; } diff --git a/drivers/ufs/core/ufshcd-crypto.c b/drivers/ufs/core/ufshcd-crypto.c index a714dad82cd1..694ff7578fc1 100644 --- a/drivers/ufs/core/ufshcd-crypto.c +++ b/drivers/ufs/core/ufshcd-crypto.c @@ -17,20 +17,14 @@ static const struct ufs_crypto_alg_entry { }, }; -static int ufshcd_program_key(struct ufs_hba *hba, - const union ufs_crypto_cfg_entry *cfg, int slot) +static void ufshcd_program_key(struct ufs_hba *hba, + const union ufs_crypto_cfg_entry *cfg, int slot) { int i; u32 slot_offset = hba->crypto_cfg_register + slot * sizeof(*cfg); - int err = 0; ufshcd_hold(hba); - if (hba->vops && hba->vops->program_key) { - err = hba->vops->program_key(hba, cfg, slot); - goto out; - } - /* Ensure that CFGE is cleared before programming the key */ ufshcd_writel(hba, 0, slot_offset + 16 * sizeof(cfg->reg_val[0])); for (i = 0; i < 16; i++) { @@ -43,17 +37,14 @@ static int ufshcd_program_key(struct ufs_hba *hba, /* Dword 16 must be written last */ ufshcd_writel(hba, le32_to_cpu(cfg->reg_val[16]), slot_offset + 16 * sizeof(cfg->reg_val[0])); -out: ufshcd_release(hba); - return err; } static int ufshcd_crypto_keyslot_program(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot) { - struct ufs_hba *hba = - container_of(profile, struct ufs_hba, crypto_profile); + struct ufs_hba *hba = ufs_hba_from_crypto_profile(profile); const union ufs_crypto_cap_entry *ccap_array = hba->crypto_cap_array; const struct ufs_crypto_alg_entry *alg = &ufs_crypto_algs[key->crypto_cfg.crypto_mode]; @@ -61,7 +52,6 @@ static int ufshcd_crypto_keyslot_program(struct blk_crypto_profile *profile, int i; int cap_idx = -1; union ufs_crypto_cfg_entry cfg = {}; - int err; BUILD_BUG_ON(UFS_CRYPTO_KEY_SIZE_INVALID != 0); for (i = 0; i < hba->crypto_capabilities.num_crypto_cap; i++) { @@ -89,25 +79,25 @@ static int ufshcd_crypto_keyslot_program(struct blk_crypto_profile *profile, memcpy(cfg.crypto_key, key->raw, key->size); } - err = ufshcd_program_key(hba, &cfg, slot); + ufshcd_program_key(hba, &cfg, slot); memzero_explicit(&cfg, sizeof(cfg)); - return err; + return 0; } static int ufshcd_crypto_keyslot_evict(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot) { - struct ufs_hba *hba = - container_of(profile, struct ufs_hba, crypto_profile); + struct ufs_hba *hba = ufs_hba_from_crypto_profile(profile); /* * Clear the crypto cfg on the device. Clearing CFGE * might not be sufficient, so just clear the entire cfg. */ union ufs_crypto_cfg_entry cfg = {}; - return ufshcd_program_key(hba, &cfg, slot); + ufshcd_program_key(hba, &cfg, slot); + return 0; } /* diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h index 9ffd94ddf8c7..786f20ef2238 100644 --- a/drivers/ufs/core/ufshcd-priv.h +++ b/drivers/ufs/core/ufshcd-priv.h @@ -237,12 +237,6 @@ static inline void ufshcd_vops_config_scaling_param(struct ufs_hba *hba, hba->vops->config_scaling_param(hba, p, data); } -static inline void ufshcd_vops_reinit_notify(struct ufs_hba *hba) -{ - if (hba->vops && hba->vops->reinit_notify) - hba->vops->reinit_notify(hba); -} - static inline int ufshcd_vops_mcq_config_resource(struct ufs_hba *hba) { if (hba->vops && hba->vops->mcq_config_resource) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 8a01e4393159..cd404ade48dc 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -258,10 +258,15 @@ ufs_get_desired_pm_lvl_for_dev_link_state(enum ufs_dev_pwr_mode dev_state, return UFS_PM_LVL_0; } +static bool ufshcd_has_pending_tasks(struct ufs_hba *hba) +{ + return hba->outstanding_tasks || hba->active_uic_cmd || + hba->uic_async_done; +} + static bool ufshcd_is_ufs_dev_busy(struct ufs_hba *hba) { - return (hba->clk_gating.active_reqs || hba->outstanding_reqs || hba->outstanding_tasks || - hba->active_uic_cmd || hba->uic_async_done); + return hba->outstanding_reqs || ufshcd_has_pending_tasks(hba); } static const struct ufs_dev_quirk ufs_fixups[] = { @@ -1447,16 +1452,16 @@ static void ufshcd_clk_scaling_suspend_work(struct work_struct *work) { struct ufs_hba *hba = container_of(work, struct ufs_hba, clk_scaling.suspend_work); - unsigned long irq_flags; - spin_lock_irqsave(hba->host->host_lock, irq_flags); - if (hba->clk_scaling.active_reqs || hba->clk_scaling.is_suspended) { - spin_unlock_irqrestore(hba->host->host_lock, irq_flags); - return; + scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock) + { + if (hba->clk_scaling.active_reqs || + hba->clk_scaling.is_suspended) + return; + + hba->clk_scaling.is_suspended = true; + hba->clk_scaling.window_start_t = 0; } - hba->clk_scaling.is_suspended = true; - hba->clk_scaling.window_start_t = 0; - spin_unlock_irqrestore(hba->host->host_lock, irq_flags); devfreq_suspend_device(hba->devfreq); } @@ -1465,15 +1470,13 @@ static void ufshcd_clk_scaling_resume_work(struct work_struct *work) { struct ufs_hba *hba = container_of(work, struct ufs_hba, clk_scaling.resume_work); - unsigned long irq_flags; - spin_lock_irqsave(hba->host->host_lock, irq_flags); - if (!hba->clk_scaling.is_suspended) { - spin_unlock_irqrestore(hba->host->host_lock, irq_flags); - return; + scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock) + { + if (!hba->clk_scaling.is_suspended) + return; + hba->clk_scaling.is_suspended = false; } - hba->clk_scaling.is_suspended = false; - spin_unlock_irqrestore(hba->host->host_lock, irq_flags); devfreq_resume_device(hba->devfreq); } @@ -1487,7 +1490,6 @@ static int ufshcd_devfreq_target(struct device *dev, bool scale_up = false, sched_clk_scaling_suspend_work = false; struct list_head *clk_list = &hba->clk_list_head; struct ufs_clk_info *clki; - unsigned long irq_flags; if (!ufshcd_is_clkscaling_supported(hba)) return -EINVAL; @@ -1508,44 +1510,39 @@ static int ufshcd_devfreq_target(struct device *dev, *freq = (unsigned long) clk_round_rate(clki->clk, *freq); } - spin_lock_irqsave(hba->host->host_lock, irq_flags); - if (ufshcd_eh_in_progress(hba)) { - spin_unlock_irqrestore(hba->host->host_lock, irq_flags); - return 0; + scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock) + { + if (ufshcd_eh_in_progress(hba)) + return 0; + + /* Skip scaling clock when clock scaling is suspended */ + if (hba->clk_scaling.is_suspended) { + dev_warn(hba->dev, "clock scaling is suspended, skip"); + return 0; + } + + if (!hba->clk_scaling.active_reqs) + sched_clk_scaling_suspend_work = true; + + if (list_empty(clk_list)) + goto out; + + /* Decide based on the target or rounded-off frequency and update */ + if (hba->use_pm_opp) + scale_up = *freq > hba->clk_scaling.target_freq; + else + scale_up = *freq == clki->max_freq; + + if (!hba->use_pm_opp && !scale_up) + *freq = clki->min_freq; + + /* Update the frequency */ + if (!ufshcd_is_devfreq_scaling_required(hba, *freq, scale_up)) { + ret = 0; + goto out; /* no state change required */ + } } - /* Skip scaling clock when clock scaling is suspended */ - if (hba->clk_scaling.is_suspended) { - spin_unlock_irqrestore(hba->host->host_lock, irq_flags); - dev_warn(hba->dev, "clock scaling is suspended, skip"); - return 0; - } - - if (!hba->clk_scaling.active_reqs) - sched_clk_scaling_suspend_work = true; - - if (list_empty(clk_list)) { - spin_unlock_irqrestore(hba->host->host_lock, irq_flags); - goto out; - } - - /* Decide based on the target or rounded-off frequency and update */ - if (hba->use_pm_opp) - scale_up = *freq > hba->clk_scaling.target_freq; - else - scale_up = *freq == clki->max_freq; - - if (!hba->use_pm_opp && !scale_up) - *freq = clki->min_freq; - - /* Update the frequency */ - if (!ufshcd_is_devfreq_scaling_required(hba, *freq, scale_up)) { - spin_unlock_irqrestore(hba->host->host_lock, irq_flags); - ret = 0; - goto out; /* no state change required */ - } - spin_unlock_irqrestore(hba->host->host_lock, irq_flags); - start = ktime_get(); ret = ufshcd_devfreq_scale(hba, *freq, scale_up); if (!ret) @@ -1569,7 +1566,6 @@ static int ufshcd_devfreq_get_dev_status(struct device *dev, { struct ufs_hba *hba = dev_get_drvdata(dev); struct ufs_clk_scaling *scaling = &hba->clk_scaling; - unsigned long flags; ktime_t curr_t; if (!ufshcd_is_clkscaling_supported(hba)) @@ -1577,7 +1573,8 @@ static int ufshcd_devfreq_get_dev_status(struct device *dev, memset(stat, 0, sizeof(*stat)); - spin_lock_irqsave(hba->host->host_lock, flags); + guard(spinlock_irqsave)(&hba->clk_scaling.lock); + curr_t = ktime_get(); if (!scaling->window_start_t) goto start_window; @@ -1613,7 +1610,7 @@ start_window: scaling->busy_start_t = 0; scaling->is_busy_started = false; } - spin_unlock_irqrestore(hba->host->host_lock, flags); + return 0; } @@ -1677,19 +1674,19 @@ static void ufshcd_devfreq_remove(struct ufs_hba *hba) static void ufshcd_suspend_clkscaling(struct ufs_hba *hba) { - unsigned long flags; bool suspend = false; cancel_work_sync(&hba->clk_scaling.suspend_work); cancel_work_sync(&hba->clk_scaling.resume_work); - spin_lock_irqsave(hba->host->host_lock, flags); - if (!hba->clk_scaling.is_suspended) { - suspend = true; - hba->clk_scaling.is_suspended = true; - hba->clk_scaling.window_start_t = 0; + scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock) + { + if (!hba->clk_scaling.is_suspended) { + suspend = true; + hba->clk_scaling.is_suspended = true; + hba->clk_scaling.window_start_t = 0; + } } - spin_unlock_irqrestore(hba->host->host_lock, flags); if (suspend) devfreq_suspend_device(hba->devfreq); @@ -1697,15 +1694,15 @@ static void ufshcd_suspend_clkscaling(struct ufs_hba *hba) static void ufshcd_resume_clkscaling(struct ufs_hba *hba) { - unsigned long flags; bool resume = false; - spin_lock_irqsave(hba->host->host_lock, flags); - if (hba->clk_scaling.is_suspended) { - resume = true; - hba->clk_scaling.is_suspended = false; + scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock) + { + if (hba->clk_scaling.is_suspended) { + resume = true; + hba->clk_scaling.is_suspended = false; + } } - spin_unlock_irqrestore(hba->host->host_lock, flags); if (resume) devfreq_resume_device(hba->devfreq); @@ -1791,6 +1788,8 @@ static void ufshcd_init_clk_scaling(struct ufs_hba *hba) INIT_WORK(&hba->clk_scaling.resume_work, ufshcd_clk_scaling_resume_work); + spin_lock_init(&hba->clk_scaling.lock); + hba->clk_scaling.workq = alloc_ordered_workqueue( "ufs_clkscaling_%d", WQ_MEM_RECLAIM, hba->host->host_no); @@ -1811,19 +1810,16 @@ static void ufshcd_exit_clk_scaling(struct ufs_hba *hba) static void ufshcd_ungate_work(struct work_struct *work) { int ret; - unsigned long flags; struct ufs_hba *hba = container_of(work, struct ufs_hba, clk_gating.ungate_work); cancel_delayed_work_sync(&hba->clk_gating.gate_work); - spin_lock_irqsave(hba->host->host_lock, flags); - if (hba->clk_gating.state == CLKS_ON) { - spin_unlock_irqrestore(hba->host->host_lock, flags); - return; + scoped_guard(spinlock_irqsave, &hba->clk_gating.lock) { + if (hba->clk_gating.state == CLKS_ON) + return; } - spin_unlock_irqrestore(hba->host->host_lock, flags); ufshcd_hba_vreg_set_hpm(hba); ufshcd_setup_clocks(hba, true); @@ -1858,7 +1854,7 @@ void ufshcd_hold(struct ufs_hba *hba) if (!ufshcd_is_clkgating_allowed(hba) || !hba->clk_gating.is_initialized) return; - spin_lock_irqsave(hba->host->host_lock, flags); + spin_lock_irqsave(&hba->clk_gating.lock, flags); hba->clk_gating.active_reqs++; start: @@ -1874,11 +1870,11 @@ start: */ if (ufshcd_can_hibern8_during_gating(hba) && ufshcd_is_link_hibern8(hba)) { - spin_unlock_irqrestore(hba->host->host_lock, flags); + spin_unlock_irqrestore(&hba->clk_gating.lock, flags); flush_result = flush_work(&hba->clk_gating.ungate_work); if (hba->clk_gating.is_suspended && !flush_result) return; - spin_lock_irqsave(hba->host->host_lock, flags); + spin_lock_irqsave(&hba->clk_gating.lock, flags); goto start; } break; @@ -1907,17 +1903,17 @@ start: */ fallthrough; case REQ_CLKS_ON: - spin_unlock_irqrestore(hba->host->host_lock, flags); + spin_unlock_irqrestore(&hba->clk_gating.lock, flags); flush_work(&hba->clk_gating.ungate_work); /* Make sure state is CLKS_ON before returning */ - spin_lock_irqsave(hba->host->host_lock, flags); + spin_lock_irqsave(&hba->clk_gating.lock, flags); goto start; default: dev_err(hba->dev, "%s: clk gating is in invalid state %d\n", __func__, hba->clk_gating.state); break; } - spin_unlock_irqrestore(hba->host->host_lock, flags); + spin_unlock_irqrestore(&hba->clk_gating.lock, flags); } EXPORT_SYMBOL_GPL(ufshcd_hold); @@ -1925,28 +1921,32 @@ static void ufshcd_gate_work(struct work_struct *work) { struct ufs_hba *hba = container_of(work, struct ufs_hba, clk_gating.gate_work.work); - unsigned long flags; int ret; - spin_lock_irqsave(hba->host->host_lock, flags); - /* - * In case you are here to cancel this work the gating state - * would be marked as REQ_CLKS_ON. In this case save time by - * skipping the gating work and exit after changing the clock - * state to CLKS_ON. - */ - if (hba->clk_gating.is_suspended || - (hba->clk_gating.state != REQ_CLKS_OFF)) { - hba->clk_gating.state = CLKS_ON; - trace_ufshcd_clk_gating(dev_name(hba->dev), - hba->clk_gating.state); - goto rel_lock; + scoped_guard(spinlock_irqsave, &hba->clk_gating.lock) { + /* + * In case you are here to cancel this work the gating state + * would be marked as REQ_CLKS_ON. In this case save time by + * skipping the gating work and exit after changing the clock + * state to CLKS_ON. + */ + if (hba->clk_gating.is_suspended || + hba->clk_gating.state != REQ_CLKS_OFF) { + hba->clk_gating.state = CLKS_ON; + trace_ufshcd_clk_gating(dev_name(hba->dev), + hba->clk_gating.state); + return; + } + + if (hba->clk_gating.active_reqs) + return; } - if (ufshcd_is_ufs_dev_busy(hba) || hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL) - goto rel_lock; - - spin_unlock_irqrestore(hba->host->host_lock, flags); + scoped_guard(spinlock_irqsave, hba->host->host_lock) { + if (ufshcd_is_ufs_dev_busy(hba) || + hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL) + return; + } /* put the link into hibern8 mode before turning off clocks */ if (ufshcd_can_hibern8_during_gating(hba)) { @@ -1957,7 +1957,7 @@ static void ufshcd_gate_work(struct work_struct *work) __func__, ret); trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state); - goto out; + return; } ufshcd_set_link_hibern8(hba); } @@ -1977,33 +1977,34 @@ static void ufshcd_gate_work(struct work_struct *work) * prevent from doing cancel work multiple times when there are * new requests arriving before the current cancel work is done. */ - spin_lock_irqsave(hba->host->host_lock, flags); + guard(spinlock_irqsave)(&hba->clk_gating.lock); if (hba->clk_gating.state == REQ_CLKS_OFF) { hba->clk_gating.state = CLKS_OFF; trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state); } -rel_lock: - spin_unlock_irqrestore(hba->host->host_lock, flags); -out: - return; } -/* host lock must be held before calling this variant */ static void __ufshcd_release(struct ufs_hba *hba) { + lockdep_assert_held(&hba->clk_gating.lock); + if (!ufshcd_is_clkgating_allowed(hba)) return; hba->clk_gating.active_reqs--; if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended || - hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL || - hba->outstanding_tasks || !hba->clk_gating.is_initialized || - hba->active_uic_cmd || hba->uic_async_done || + !hba->clk_gating.is_initialized || hba->clk_gating.state == CLKS_OFF) return; + scoped_guard(spinlock_irqsave, hba->host->host_lock) { + if (ufshcd_has_pending_tasks(hba) || + hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL) + return; + } + hba->clk_gating.state = REQ_CLKS_OFF; trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state); queue_delayed_work(hba->clk_gating.clk_gating_workq, @@ -2013,11 +2014,8 @@ static void __ufshcd_release(struct ufs_hba *hba) void ufshcd_release(struct ufs_hba *hba) { - unsigned long flags; - - spin_lock_irqsave(hba->host->host_lock, flags); + guard(spinlock_irqsave)(&hba->clk_gating.lock); __ufshcd_release(hba); - spin_unlock_irqrestore(hba->host->host_lock, flags); } EXPORT_SYMBOL_GPL(ufshcd_release); @@ -2032,11 +2030,9 @@ static ssize_t ufshcd_clkgate_delay_show(struct device *dev, void ufshcd_clkgate_delay_set(struct device *dev, unsigned long value) { struct ufs_hba *hba = dev_get_drvdata(dev); - unsigned long flags; - spin_lock_irqsave(hba->host->host_lock, flags); + guard(spinlock_irqsave)(&hba->clk_gating.lock); hba->clk_gating.delay_ms = value; - spin_unlock_irqrestore(hba->host->host_lock, flags); } EXPORT_SYMBOL_GPL(ufshcd_clkgate_delay_set); @@ -2064,7 +2060,6 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct ufs_hba *hba = dev_get_drvdata(dev); - unsigned long flags; u32 value; if (kstrtou32(buf, 0, &value)) @@ -2072,9 +2067,10 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev, value = !!value; - spin_lock_irqsave(hba->host->host_lock, flags); + guard(spinlock_irqsave)(&hba->clk_gating.lock); + if (value == hba->clk_gating.is_enabled) - goto out; + return count; if (value) __ufshcd_release(hba); @@ -2082,8 +2078,7 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev, hba->clk_gating.active_reqs++; hba->clk_gating.is_enabled = value; -out: - spin_unlock_irqrestore(hba->host->host_lock, flags); + return count; } @@ -2125,6 +2120,8 @@ static void ufshcd_init_clk_gating(struct ufs_hba *hba) INIT_DELAYED_WORK(&hba->clk_gating.gate_work, ufshcd_gate_work); INIT_WORK(&hba->clk_gating.ungate_work, ufshcd_ungate_work); + spin_lock_init(&hba->clk_gating.lock); + hba->clk_gating.clk_gating_workq = alloc_ordered_workqueue( "ufs_clk_gating_%d", WQ_MEM_RECLAIM | WQ_HIGHPRI, hba->host->host_no); @@ -2154,19 +2151,17 @@ static void ufshcd_clk_scaling_start_busy(struct ufs_hba *hba) { bool queue_resume_work = false; ktime_t curr_t = ktime_get(); - unsigned long flags; if (!ufshcd_is_clkscaling_supported(hba)) return; - spin_lock_irqsave(hba->host->host_lock, flags); + guard(spinlock_irqsave)(&hba->clk_scaling.lock); + if (!hba->clk_scaling.active_reqs++) queue_resume_work = true; - if (!hba->clk_scaling.is_enabled || hba->pm_op_in_progress) { - spin_unlock_irqrestore(hba->host->host_lock, flags); + if (!hba->clk_scaling.is_enabled || hba->pm_op_in_progress) return; - } if (queue_resume_work) queue_work(hba->clk_scaling.workq, @@ -2182,18 +2177,17 @@ static void ufshcd_clk_scaling_start_busy(struct ufs_hba *hba) hba->clk_scaling.busy_start_t = curr_t; hba->clk_scaling.is_busy_started = true; } - spin_unlock_irqrestore(hba->host->host_lock, flags); } static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba) { struct ufs_clk_scaling *scaling = &hba->clk_scaling; - unsigned long flags; if (!ufshcd_is_clkscaling_supported(hba)) return; - spin_lock_irqsave(hba->host->host_lock, flags); + guard(spinlock_irqsave)(&hba->clk_scaling.lock); + hba->clk_scaling.active_reqs--; if (!scaling->active_reqs && scaling->is_busy_started) { scaling->tot_busy_t += ktime_to_us(ktime_sub(ktime_get(), @@ -2201,7 +2195,6 @@ static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba) scaling->busy_start_t = 0; scaling->is_busy_started = false; } - spin_unlock_irqrestore(hba->host->host_lock, flags); } static inline int ufshcd_monitor_opcode2dir(u8 opcode) @@ -2418,12 +2411,7 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba) else hba->lsdb_sup = true; - if (!hba->mcq_sup) - return 0; - hba->mcq_capabilities = ufshcd_readl(hba, REG_MCQCAP); - hba->ext_iid_sup = FIELD_GET(MASK_EXT_IID_SUPPORT, - hba->mcq_capabilities); return 0; } @@ -4812,20 +4800,14 @@ EXPORT_SYMBOL_GPL(ufshcd_make_hba_operational); */ void ufshcd_hba_stop(struct ufs_hba *hba) { - unsigned long flags; int err; - /* - * Obtain the host lock to prevent that the controller is disabled - * while the UFS interrupt handler is active on another CPU. - */ - spin_lock_irqsave(hba->host->host_lock, flags); + ufshcd_disable_irq(hba); ufshcd_writel(hba, CONTROLLER_DISABLE, REG_CONTROLLER_ENABLE); - spin_unlock_irqrestore(hba->host->host_lock, flags); - err = ufshcd_wait_for_register(hba, REG_CONTROLLER_ENABLE, CONTROLLER_ENABLE, CONTROLLER_DISABLE, 10, 1); + ufshcd_enable_irq(hba); if (err) dev_err(hba->dev, "%s: Controller disable failed\n", __func__); } @@ -5195,12 +5177,12 @@ set_qdepth: } /** - * ufshcd_slave_alloc - handle initial SCSI device configurations + * ufshcd_sdev_init - handle initial SCSI device configurations * @sdev: pointer to SCSI device * * Return: success. */ -static int ufshcd_slave_alloc(struct scsi_device *sdev) +static int ufshcd_sdev_init(struct scsi_device *sdev) { struct ufs_hba *hba; @@ -5243,14 +5225,14 @@ static int ufshcd_change_queue_depth(struct scsi_device *sdev, int depth) } /** - * ufshcd_device_configure - adjust SCSI device configurations + * ufshcd_sdev_configure - adjust SCSI device configurations * @sdev: pointer to SCSI device * @lim: queue limits * * Return: 0 (success). */ -static int ufshcd_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int ufshcd_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct ufs_hba *hba = shost_priv(sdev->host); struct request_queue *q = sdev->request_queue; @@ -5281,10 +5263,10 @@ static int ufshcd_device_configure(struct scsi_device *sdev, } /** - * ufshcd_slave_destroy - remove SCSI device configurations + * ufshcd_sdev_destroy - remove SCSI device configurations * @sdev: pointer to SCSI device */ -static void ufshcd_slave_destroy(struct scsi_device *sdev) +static void ufshcd_sdev_destroy(struct scsi_device *sdev) { struct ufs_hba *hba; unsigned long flags; @@ -8133,31 +8115,6 @@ static void ufshcd_temp_notif_probe(struct ufs_hba *hba, const u8 *desc_buf) } } -static void ufshcd_ext_iid_probe(struct ufs_hba *hba, u8 *desc_buf) -{ - struct ufs_dev_info *dev_info = &hba->dev_info; - u32 ext_ufs_feature; - u32 ext_iid_en = 0; - int err; - - /* Only UFS-4.0 and above may support EXT_IID */ - if (dev_info->wspecversion < 0x400) - goto out; - - ext_ufs_feature = get_unaligned_be32(desc_buf + - DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP); - if (!(ext_ufs_feature & UFS_DEV_EXT_IID_SUP)) - goto out; - - err = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR, - QUERY_ATTR_IDN_EXT_IID_EN, 0, 0, &ext_iid_en); - if (err) - dev_err(hba->dev, "failed reading bEXTIIDEn. err = %d\n", err); - -out: - dev_info->b_ext_iid_en = ext_iid_en; -} - static void ufshcd_set_rtt(struct ufs_hba *hba) { struct ufs_dev_info *dev_info = &hba->dev_info; @@ -8259,7 +8216,9 @@ static void ufshcd_rtc_work(struct work_struct *work) hba = container_of(to_delayed_work(work), struct ufs_hba, ufs_rtc_update_work); /* Update RTC only when there are no requests in progress and UFSHCI is operational */ - if (!ufshcd_is_ufs_dev_busy(hba) && hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL) + if (!ufshcd_is_ufs_dev_busy(hba) && + hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL && + !hba->clk_gating.active_reqs) ufshcd_update_rtc(hba); if (ufshcd_is_ufs_dev_active(hba) && hba->dev_info.rtc_update_period) @@ -8351,9 +8310,6 @@ static int ufs_get_device_desc(struct ufs_hba *hba) ufs_init_rtc(hba, desc_buf); - if (hba->ext_iid_sup) - ufshcd_ext_iid_probe(hba, desc_buf); - /* * ufshcd_read_string_desc returns size of the string * reset the error value @@ -8858,7 +8814,6 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params) ufshcd_device_reset(hba); ufs_put_device_desc(hba); ufshcd_hba_stop(hba); - ufshcd_vops_reinit_notify(hba); ret = ufshcd_hba_enable(hba); if (ret) { dev_err(hba->dev, "Host controller enable failed\n"); @@ -8968,9 +8923,9 @@ static const struct scsi_host_template ufshcd_driver_template = { .map_queues = ufshcd_map_queues, .queuecommand = ufshcd_queuecommand, .mq_poll = ufshcd_poll, - .slave_alloc = ufshcd_slave_alloc, - .device_configure = ufshcd_device_configure, - .slave_destroy = ufshcd_slave_destroy, + .sdev_init = ufshcd_sdev_init, + .sdev_configure = ufshcd_sdev_configure, + .sdev_destroy = ufshcd_sdev_destroy, .change_queue_depth = ufshcd_change_queue_depth, .eh_abort_handler = ufshcd_abort, .eh_device_reset_handler = ufshcd_eh_device_reset_handler, @@ -9156,7 +9111,6 @@ static int ufshcd_setup_clocks(struct ufs_hba *hba, bool on) int ret = 0; struct ufs_clk_info *clki; struct list_head *head = &hba->clk_list_head; - unsigned long flags; ktime_t start = ktime_get(); bool clk_state_changed = false; @@ -9207,11 +9161,10 @@ out: clk_disable_unprepare(clki->clk); } } else if (!ret && on) { - spin_lock_irqsave(hba->host->host_lock, flags); - hba->clk_gating.state = CLKS_ON; + scoped_guard(spinlock_irqsave, &hba->clk_gating.lock) + hba->clk_gating.state = CLKS_ON; trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state); - spin_unlock_irqrestore(hba->host->host_lock, flags); } if (clk_state_changed) @@ -10412,7 +10365,6 @@ static int ufshcd_add_scsi_host(struct ufs_hba *hba) .nr_hw_queues = 1, .queue_depth = hba->nutmrs, .ops = &ufshcd_tmf_ops, - .flags = BLK_MQ_F_NO_SCHED, }; err = blk_mq_alloc_tag_set(&hba->tmf_tag_set); if (err < 0) @@ -10591,14 +10543,17 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) } /* - * Set the default power management level for runtime and system PM. + * Set the default power management level for runtime and system PM if + * not set by the host controller drivers. * Default power saving mode is to keep UFS link in Hibern8 state * and UFS device in sleep state. */ - hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( + if (!hba->rpm_lvl) + hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( UFS_SLEEP_PWR_MODE, UIC_LINK_HIBERN8_STATE); - hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( + if (!hba->spm_lvl) + hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( UFS_SLEEP_PWR_MODE, UIC_LINK_HIBERN8_STATE); diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 68040b2ab5f8..23b9f6efa047 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -112,11 +112,18 @@ static inline void ufs_qcom_ice_enable(struct ufs_qcom_host *host) qcom_ice_enable(host->ice); } +static const struct blk_crypto_ll_ops ufs_qcom_crypto_ops; /* forward decl */ + static int ufs_qcom_ice_init(struct ufs_qcom_host *host) { struct ufs_hba *hba = host->hba; + struct blk_crypto_profile *profile = &hba->crypto_profile; struct device *dev = hba->dev; struct qcom_ice *ice; + union ufs_crypto_capabilities caps; + union ufs_crypto_cap_entry cap; + int err; + int i; ice = of_qcom_ice_get(dev); if (ice == ERR_PTR(-EOPNOTSUPP)) { @@ -128,8 +135,38 @@ static int ufs_qcom_ice_init(struct ufs_qcom_host *host) return PTR_ERR_OR_ZERO(ice); host->ice = ice; - hba->caps |= UFSHCD_CAP_CRYPTO; + /* Initialize the blk_crypto_profile */ + + caps.reg_val = cpu_to_le32(ufshcd_readl(hba, REG_UFS_CCAP)); + + /* The number of keyslots supported is (CFGC+1) */ + err = devm_blk_crypto_profile_init(dev, profile, caps.config_count + 1); + if (err) + return err; + + profile->ll_ops = ufs_qcom_crypto_ops; + profile->max_dun_bytes_supported = 8; + profile->dev = dev; + + /* + * Currently this driver only supports AES-256-XTS. All known versions + * of ICE support it, but to be safe make sure it is really declared in + * the crypto capability registers. The crypto capability registers + * also give the supported data unit size(s). + */ + for (i = 0; i < caps.num_crypto_cap; i++) { + cap.reg_val = cpu_to_le32(ufshcd_readl(hba, + REG_UFS_CRYPTOCAP + + i * sizeof(__le32))); + if (cap.algorithm_id == UFS_CRYPTO_ALG_AES_XTS && + cap.key_size == UFS_CRYPTO_KEY_SIZE_256) + profile->modes_supported[BLK_ENCRYPTION_MODE_AES_256_XTS] |= + cap.sdus_mask * 512; + } + + hba->caps |= UFSHCD_CAP_CRYPTO; + hba->quirks |= UFSHCD_QUIRK_CUSTOM_CRYPTO_PROFILE; return 0; } @@ -149,34 +186,49 @@ static inline int ufs_qcom_ice_suspend(struct ufs_qcom_host *host) return 0; } -static int ufs_qcom_ice_program_key(struct ufs_hba *hba, - const union ufs_crypto_cfg_entry *cfg, - int slot) +static int ufs_qcom_ice_keyslot_program(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, + unsigned int slot) { + struct ufs_hba *hba = ufs_hba_from_crypto_profile(profile); struct ufs_qcom_host *host = ufshcd_get_variant(hba); - union ufs_crypto_cap_entry cap; - bool config_enable = - cfg->config_enable & UFS_CRYPTO_CONFIGURATION_ENABLE; + int err; /* Only AES-256-XTS has been tested so far. */ - cap = hba->crypto_cap_array[cfg->crypto_cap_idx]; - if (cap.algorithm_id != UFS_CRYPTO_ALG_AES_XTS || - cap.key_size != UFS_CRYPTO_KEY_SIZE_256) + if (key->crypto_cfg.crypto_mode != BLK_ENCRYPTION_MODE_AES_256_XTS) return -EOPNOTSUPP; - if (config_enable) - return qcom_ice_program_key(host->ice, - QCOM_ICE_CRYPTO_ALG_AES_XTS, - QCOM_ICE_CRYPTO_KEY_SIZE_256, - cfg->crypto_key, - cfg->data_unit_size, slot); - else - return qcom_ice_evict_key(host->ice, slot); + ufshcd_hold(hba); + err = qcom_ice_program_key(host->ice, + QCOM_ICE_CRYPTO_ALG_AES_XTS, + QCOM_ICE_CRYPTO_KEY_SIZE_256, + key->raw, + key->crypto_cfg.data_unit_size / 512, + slot); + ufshcd_release(hba); + return err; } -#else +static int ufs_qcom_ice_keyslot_evict(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, + unsigned int slot) +{ + struct ufs_hba *hba = ufs_hba_from_crypto_profile(profile); + struct ufs_qcom_host *host = ufshcd_get_variant(hba); + int err; -#define ufs_qcom_ice_program_key NULL + ufshcd_hold(hba); + err = qcom_ice_evict_key(host->ice, slot); + ufshcd_release(hba); + return err; +} + +static const struct blk_crypto_ll_ops ufs_qcom_crypto_ops = { + .keyslot_program = ufs_qcom_ice_keyslot_program, + .keyslot_evict = ufs_qcom_ice_keyslot_evict, +}; + +#else static inline void ufs_qcom_ice_enable(struct ufs_qcom_host *host) { @@ -368,6 +420,11 @@ static int ufs_qcom_power_up_sequence(struct ufs_hba *hba) if (ret) return ret; + if (phy->power_count) { + phy_power_off(phy); + phy_exit(phy); + } + /* phy initialization - calibrate the phy */ ret = phy_init(phy); if (ret) { @@ -866,6 +923,7 @@ static u32 ufs_qcom_get_ufs_hci_version(struct ufs_hba *hba) */ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba) { + const struct ufs_qcom_drvdata *drvdata = of_device_get_match_data(hba->dev); struct ufs_qcom_host *host = ufshcd_get_variant(hba); if (host->hw_ver.major == 0x2) @@ -874,9 +932,8 @@ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba) if (host->hw_ver.major > 0x3) hba->quirks |= UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH; - if (of_device_is_compatible(hba->dev->of_node, "qcom,sm8550-ufshc") || - of_device_is_compatible(hba->dev->of_node, "qcom,sm8650-ufshc")) - hba->quirks |= UFSHCD_QUIRK_BROKEN_LSDBS_CAP; + if (drvdata && drvdata->quirks) + hba->quirks |= drvdata->quirks; } static void ufs_qcom_set_phy_gear(struct ufs_qcom_host *host) @@ -1064,6 +1121,7 @@ static int ufs_qcom_init(struct ufs_hba *hba) struct device *dev = hba->dev; struct ufs_qcom_host *host; struct ufs_clk_info *clki; + const struct ufs_qcom_drvdata *drvdata = of_device_get_match_data(hba->dev); host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL); if (!host) @@ -1143,6 +1201,9 @@ static int ufs_qcom_init(struct ufs_hba *hba) dev_warn(dev, "%s: failed to configure the testbus %d\n", __func__, err); + if (drvdata && drvdata->no_phy_retention) + hba->spm_lvl = UFS_PM_LVL_5; + return 0; out_variant_clear: @@ -1579,13 +1640,6 @@ static void ufs_qcom_config_scaling_param(struct ufs_hba *hba, } #endif -static void ufs_qcom_reinit_notify(struct ufs_hba *hba) -{ - struct ufs_qcom_host *host = ufshcd_get_variant(hba); - - phy_power_off(host->generic_phy); -} - /* Resources */ static const struct ufshcd_res_info ufs_res_info[RES_MAX] = { {.name = "ufs_mem",}, @@ -1824,8 +1878,6 @@ static const struct ufs_hba_variant_ops ufs_hba_qcom_vops = { .dbg_register_dump = ufs_qcom_dump_dbg_regs, .device_reset = ufs_qcom_device_reset, .config_scaling_param = ufs_qcom_config_scaling_param, - .program_key = ufs_qcom_ice_program_key, - .reinit_notify = ufs_qcom_reinit_notify, .mcq_config_resource = ufs_qcom_mcq_config_resource, .get_hba_mac = ufs_qcom_get_hba_mac, .op_runtime_config = ufs_qcom_op_runtime_config, @@ -1868,9 +1920,15 @@ static void ufs_qcom_remove(struct platform_device *pdev) platform_device_msi_free_irqs_all(hba->dev); } +static const struct ufs_qcom_drvdata ufs_qcom_sm8550_drvdata = { + .quirks = UFSHCD_QUIRK_BROKEN_LSDBS_CAP, + .no_phy_retention = true, +}; + static const struct of_device_id ufs_qcom_of_match[] __maybe_unused = { { .compatible = "qcom,ufshc" }, - { .compatible = "qcom,sm8550-ufshc" }, + { .compatible = "qcom,sm8550-ufshc", .data = &ufs_qcom_sm8550_drvdata }, + { .compatible = "qcom,sm8650-ufshc", .data = &ufs_qcom_sm8550_drvdata }, {}, }; MODULE_DEVICE_TABLE(of, ufs_qcom_of_match); diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h index b9de170983c9..919f53682beb 100644 --- a/drivers/ufs/host/ufs-qcom.h +++ b/drivers/ufs/host/ufs-qcom.h @@ -217,6 +217,11 @@ struct ufs_qcom_host { bool esi_enabled; }; +struct ufs_qcom_drvdata { + enum ufshcd_quirks quirks; + bool no_phy_retention; +}; + static inline u32 ufs_qcom_get_debug_reg_offset(struct ufs_qcom_host *host, u32 reg) { diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 004a549c6c7d..d93ed4e86a17 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -565,7 +565,7 @@ static __poll_t uio_poll(struct file *filep, poll_table *wait) mutex_lock(&idev->info_lock); if (!idev->info || !idev->info->irq) - ret = -EIO; + ret = EPOLLERR; mutex_unlock(&idev->info_lock); if (ret) diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c index c70dd81bfc61..31aa75110ba5 100644 --- a/drivers/uio/uio_dmem_genirq.c +++ b/drivers/uio/uio_dmem_genirq.c @@ -167,6 +167,8 @@ static int uio_dmem_genirq_probe(struct platform_device *pdev) } uioinfo->name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%pOFn", pdev->dev.of_node); + if (!uioinfo->name) + return -ENOMEM; uioinfo->version = "devicetree"; } diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 3976360d0096..1b19b5647495 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -296,51 +296,51 @@ hv_uio_probe(struct hv_device *dev, pdata->info.mem[MON_PAGE_MAP].size = PAGE_SIZE; pdata->info.mem[MON_PAGE_MAP].memtype = UIO_MEM_LOGICAL; - pdata->recv_buf = vzalloc(RECV_BUFFER_SIZE); - if (pdata->recv_buf == NULL) { - ret = -ENOMEM; - goto fail_free_ring; + if (channel->device_id == HV_NIC) { + pdata->recv_buf = vzalloc(RECV_BUFFER_SIZE); + if (!pdata->recv_buf) { + ret = -ENOMEM; + goto fail_free_ring; + } + + ret = vmbus_establish_gpadl(channel, pdata->recv_buf, + RECV_BUFFER_SIZE, &pdata->recv_gpadl); + if (ret) { + if (!pdata->recv_gpadl.decrypted) + vfree(pdata->recv_buf); + goto fail_close; + } + + /* put Global Physical Address Label in name */ + snprintf(pdata->recv_name, sizeof(pdata->recv_name), + "recv:%u", pdata->recv_gpadl.gpadl_handle); + pdata->info.mem[RECV_BUF_MAP].name = pdata->recv_name; + pdata->info.mem[RECV_BUF_MAP].addr = (uintptr_t)pdata->recv_buf; + pdata->info.mem[RECV_BUF_MAP].size = RECV_BUFFER_SIZE; + pdata->info.mem[RECV_BUF_MAP].memtype = UIO_MEM_VIRTUAL; + + pdata->send_buf = vzalloc(SEND_BUFFER_SIZE); + if (!pdata->send_buf) { + ret = -ENOMEM; + goto fail_close; + } + + ret = vmbus_establish_gpadl(channel, pdata->send_buf, + SEND_BUFFER_SIZE, &pdata->send_gpadl); + if (ret) { + if (!pdata->send_gpadl.decrypted) + vfree(pdata->send_buf); + goto fail_close; + } + + snprintf(pdata->send_name, sizeof(pdata->send_name), + "send:%u", pdata->send_gpadl.gpadl_handle); + pdata->info.mem[SEND_BUF_MAP].name = pdata->send_name; + pdata->info.mem[SEND_BUF_MAP].addr = (uintptr_t)pdata->send_buf; + pdata->info.mem[SEND_BUF_MAP].size = SEND_BUFFER_SIZE; + pdata->info.mem[SEND_BUF_MAP].memtype = UIO_MEM_VIRTUAL; } - ret = vmbus_establish_gpadl(channel, pdata->recv_buf, - RECV_BUFFER_SIZE, &pdata->recv_gpadl); - if (ret) { - if (!pdata->recv_gpadl.decrypted) - vfree(pdata->recv_buf); - goto fail_close; - } - - /* put Global Physical Address Label in name */ - snprintf(pdata->recv_name, sizeof(pdata->recv_name), - "recv:%u", pdata->recv_gpadl.gpadl_handle); - pdata->info.mem[RECV_BUF_MAP].name = pdata->recv_name; - pdata->info.mem[RECV_BUF_MAP].addr - = (uintptr_t)pdata->recv_buf; - pdata->info.mem[RECV_BUF_MAP].size = RECV_BUFFER_SIZE; - pdata->info.mem[RECV_BUF_MAP].memtype = UIO_MEM_VIRTUAL; - - pdata->send_buf = vzalloc(SEND_BUFFER_SIZE); - if (pdata->send_buf == NULL) { - ret = -ENOMEM; - goto fail_close; - } - - ret = vmbus_establish_gpadl(channel, pdata->send_buf, - SEND_BUFFER_SIZE, &pdata->send_gpadl); - if (ret) { - if (!pdata->send_gpadl.decrypted) - vfree(pdata->send_buf); - goto fail_close; - } - - snprintf(pdata->send_name, sizeof(pdata->send_name), - "send:%u", pdata->send_gpadl.gpadl_handle); - pdata->info.mem[SEND_BUF_MAP].name = pdata->send_name; - pdata->info.mem[SEND_BUF_MAP].addr - = (uintptr_t)pdata->send_buf; - pdata->info.mem[SEND_BUF_MAP].size = SEND_BUFFER_SIZE; - pdata->info.mem[SEND_BUF_MAP].memtype = UIO_MEM_VIRTUAL; - pdata->info.priv = pdata; pdata->device = dev; diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 4a3f0f958256..97edf767ecee 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -1671,12 +1672,12 @@ static int cdnsp_gadget_init_endpoints(struct cdnsp_device *pdev) "CTRL: %s, INT: %s, BULK: %s, ISOC %s, " "SupDir IN: %s, OUT: %s\n", pep->name, 1024, - (pep->endpoint.caps.type_control) ? "yes" : "no", - (pep->endpoint.caps.type_int) ? "yes" : "no", - (pep->endpoint.caps.type_bulk) ? "yes" : "no", - (pep->endpoint.caps.type_iso) ? "yes" : "no", - (pep->endpoint.caps.dir_in) ? "yes" : "no", - (pep->endpoint.caps.dir_out) ? "yes" : "no"); + str_yes_no(pep->endpoint.caps.type_control), + str_yes_no(pep->endpoint.caps.type_int), + str_yes_no(pep->endpoint.caps.type_bulk), + str_yes_no(pep->endpoint.caps.type_iso), + str_yes_no(pep->endpoint.caps.dir_in), + str_yes_no(pep->endpoint.caps.dir_out)); INIT_LIST_HEAD(&pep->pending_list); } diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index 465e9267b49c..98980a23e1c2 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -529,9 +529,7 @@ int cdns_resume(struct cdns *cdns) int ret = 0; if (cdns_power_is_lost(cdns)) { - if (cdns->role_sw) { - cdns->role = cdns_role_get(cdns->role_sw); - } else { + if (!cdns->role_sw) { real_role = cdns_hw_role_state_machine(cdns); if (real_role != cdns->role) { ret = cdns_hw_role_switch(cdns); diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index f2801700be8e..1a7fc638213e 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -370,25 +370,29 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) data->pinctrl = devm_pinctrl_get(dev); if (PTR_ERR(data->pinctrl) == -ENODEV) data->pinctrl = NULL; - else if (IS_ERR(data->pinctrl)) - return dev_err_probe(dev, PTR_ERR(data->pinctrl), + else if (IS_ERR(data->pinctrl)) { + ret = dev_err_probe(dev, PTR_ERR(data->pinctrl), "pinctrl get failed\n"); + goto err_put; + } data->hsic_pad_regulator = devm_regulator_get_optional(dev, "hsic"); if (PTR_ERR(data->hsic_pad_regulator) == -ENODEV) { /* no pad regulator is needed */ data->hsic_pad_regulator = NULL; - } else if (IS_ERR(data->hsic_pad_regulator)) - return dev_err_probe(dev, PTR_ERR(data->hsic_pad_regulator), + } else if (IS_ERR(data->hsic_pad_regulator)) { + ret = dev_err_probe(dev, PTR_ERR(data->hsic_pad_regulator), "Get HSIC pad regulator error\n"); + goto err_put; + } if (data->hsic_pad_regulator) { ret = regulator_enable(data->hsic_pad_regulator); if (ret) { dev_err(dev, "Failed to enable HSIC pad regulator\n"); - return ret; + goto err_put; } } } @@ -402,13 +406,14 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) dev_err(dev, "pinctrl_hsic_idle lookup failed, err=%ld\n", PTR_ERR(pinctrl_hsic_idle)); - return PTR_ERR(pinctrl_hsic_idle); + ret = PTR_ERR(pinctrl_hsic_idle); + goto err_put; } ret = pinctrl_select_state(data->pinctrl, pinctrl_hsic_idle); if (ret) { dev_err(dev, "hsic_idle select failed, err=%d\n", ret); - return ret; + goto err_put; } data->pinctrl_hsic_active = pinctrl_lookup_state(data->pinctrl, @@ -417,7 +422,8 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) dev_err(dev, "pinctrl_hsic_active lookup failed, err=%ld\n", PTR_ERR(data->pinctrl_hsic_active)); - return PTR_ERR(data->pinctrl_hsic_active); + ret = PTR_ERR(data->pinctrl_hsic_active); + goto err_put; } } @@ -527,6 +533,8 @@ disable_hsic_regulator: if (pdata.flags & CI_HDRC_PMQOS) cpu_latency_qos_remove_request(&data->pm_qos_req); data->ci_pdev = NULL; +err_put: + put_device(data->usbmisc_data->dev); return ret; } @@ -551,6 +559,7 @@ static void ci_hdrc_imx_remove(struct platform_device *pdev) if (data->hsic_pad_regulator) regulator_disable(data->hsic_pad_regulator); } + put_device(data->usbmisc_data->dev); } static void ci_hdrc_imx_shutdown(struct platform_device *pdev) diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c index 0cce19208370..ced6076a8248 100644 --- a/drivers/usb/chipidea/host.c +++ b/drivers/usb/chipidea/host.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "../host/ehci.h" @@ -56,7 +57,7 @@ static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable) if (ret) { dev_err(dev, "Failed to %s vbus regulator, ret=%d\n", - enable ? "enable" : "disable", ret); + str_enable_disable(enable), ret); return ret; } priv->enabled = enable; @@ -256,8 +257,14 @@ static int ci_ehci_hub_control( struct device *dev = hcd->self.controller; struct ci_hdrc *ci = dev_get_drvdata(dev); - port_index = wIndex & 0xff; - port_index -= (port_index > 0); + /* + * Avoid out-of-bounds values while calculating the port index + * from wIndex. The compiler doesn't like pointers to invalid + * addresses, even if they are never used. + */ + port_index = (wIndex - 1) & 0xff; + if (port_index >= HCS_N_PORTS_MAX) + port_index = 0; status_reg = &ehci->regs->port_status[port_index]; spin_lock_irqsave(&ehci->lock, flags); diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index 5a2e43331064..e2527faa6592 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -87,7 +87,7 @@ /* Get two-int array: [0]=vendor ID, [1]=product ID: */ #define LPIOC_GET_VID_PID(len) _IOC(_IOC_READ, 'P', IOCNR_GET_VID_PID, len) /* Perform class specific soft reset */ -#define LPIOC_SOFT_RESET _IOC(_IOC_NONE, 'P', IOCNR_SOFT_RESET, 0); +#define LPIOC_SOFT_RESET _IOC(_IOC_NONE, 'P', IOCNR_SOFT_RESET, 0) /* * A DEVICE_ID string may include the printer's serial number. @@ -1337,11 +1337,12 @@ static int usblp_set_protocol(struct usblp *usblp, int protocol) if (protocol < USBLP_FIRST_PROTOCOL || protocol > USBLP_LAST_PROTOCOL) return -EINVAL; + alts = usblp->protocol[protocol].alt_setting; + if (alts < 0) + return -EINVAL; + /* Don't unnecessarily set the interface if there's a single alt. */ if (usblp->intf->num_altsetting > 1) { - alts = usblp->protocol[protocol].alt_setting; - if (alts < 0) - return -EINVAL; r = usb_set_interface(usblp->dev, usblp->ifnum, alts); if (r < 0) { printk(KERN_ERR "usblp: can't set desired altsetting %d on interface %d\n", diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c index 871cf199b6bf..fc0845f681be 100644 --- a/drivers/usb/common/common.c +++ b/drivers/usb/common/common.c @@ -41,6 +41,12 @@ const char *usb_ep_type_string(int ep_type) } EXPORT_SYMBOL_GPL(usb_ep_type_string); +/** + * usb_otg_state_string() - returns human readable name of OTG state. + * @state: the OTG state to return the human readable name of. If it's not + * any of the states defined in usb_otg_state enum, 'UNDEFINED' will be + * returned. + */ const char *usb_otg_state_string(enum usb_otg_state state) { static const char *const names[] = { @@ -179,6 +185,14 @@ static const char *const usb_dr_modes[] = { [USB_DR_MODE_OTG] = "otg", }; +/** + * usb_get_dr_mode_from_string() - Get dual role mode for given string + * @str: String to find the corresponding dual role mode for + * + * This function performs a lookup for the given string and returns the + * corresponding enum usb_dr_mode. If no match for the string could be found, + * 'USB_DR_MODE_UNKNOWN' is returned. + */ static enum usb_dr_mode usb_get_dr_mode_from_string(const char *str) { int ret; diff --git a/drivers/usb/common/usb-conn-gpio.c b/drivers/usb/common/usb-conn-gpio.c index c84b4a700084..aa710b50791b 100644 --- a/drivers/usb/common/usb-conn-gpio.c +++ b/drivers/usb/common/usb-conn-gpio.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #define USB_GPIO_DEB_MS 20 /* ms */ @@ -111,7 +112,7 @@ static void usb_conn_detect_cable(struct work_struct *work) if (info->vbus) dev_dbg(info->dev, "vbus regulator is %s\n", - regulator_is_enabled(info->vbus) ? "enabled" : "disabled"); + str_enabled_disabled(regulator_is_enabled(info->vbus))); power_supply_changed(info->charger); } diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 25a00f974934..f7bf8d1de3ad 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include "usb.h" @@ -18,12 +19,6 @@ #define USB_MAXCONFIG 8 /* Arbitrary limit */ - -static inline const char *plural(int n) -{ - return (n == 1 ? "" : "s"); -} - static int find_next_descriptor(unsigned char *buffer, int size, int dt1, int dt2, int *num_skipped) { @@ -484,7 +479,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, retval = buffer - buffer0 + i; if (n > 0) dev_dbg(ddev, "skipped %d descriptor%s after %s\n", - n, plural(n), "endpoint"); + n, str_plural(n), "endpoint"); return retval; skip_to_next_endpoint_or_interface_descriptor: @@ -563,7 +558,7 @@ static int usb_parse_interface(struct device *ddev, int cfgno, alt->extralen = i; if (n > 0) dev_dbg(ddev, "skipped %d descriptor%s after %s\n", - n, plural(n), "interface"); + n, str_plural(n), "interface"); buffer += i; size -= i; @@ -605,7 +600,7 @@ static int usb_parse_interface(struct device *ddev, int cfgno, dev_notice(ddev, "config %d interface %d altsetting %d has %d " "endpoint descriptor%s, different from the interface " "descriptor's value: %d\n", - cfgno, inum, asnum, n, plural(n), num_ep_orig); + cfgno, inum, asnum, n, str_plural(n), num_ep_orig); return buffer - buffer0; skip_to_next_interface_descriptor: @@ -664,7 +659,7 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx, if (size2 < sizeof(struct usb_descriptor_header)) { dev_notice(ddev, "config %d descriptor has %d excess " "byte%s, ignoring\n", - cfgno, size2, plural(size2)); + cfgno, size2, str_plural(size2)); break; } @@ -754,7 +749,7 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx, if (n != nintf) dev_notice(ddev, "config %d has %d interface%s, different from " "the descriptor's value: %d\n", - cfgno, n, plural(n), nintf_orig); + cfgno, n, str_plural(n), nintf_orig); else if (n == 0) dev_notice(ddev, "config %d has no interfaces?\n", cfgno); config->desc.bNumInterfaces = nintf = n; @@ -798,7 +793,7 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx, config->extralen = i; if (n > 0) dev_dbg(ddev, "skipped %d descriptor%s after %s\n", - n, plural(n), "configuration"); + n, str_plural(n), "configuration"); buffer += i; size -= i; diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index f203fdbfb6f6..460d4dde5994 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -1086,15 +1086,14 @@ int usb_register_driver(struct usb_driver *new_driver, struct module *owner, pr_info("%s: registered new interface driver %s\n", usbcore_name, new_driver->name); -out: - return retval; + return 0; out_newid: driver_unregister(&new_driver->driver); - +out: pr_err("%s: error %d registering interface driver %s\n", usbcore_name, retval, new_driver->name); - goto out; + return retval; } EXPORT_SYMBOL_GPL(usb_register_driver); diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c index b134bff5c3fe..9c6ae5e1198b 100644 --- a/drivers/usb/core/generic.c +++ b/drivers/usb/core/generic.c @@ -21,14 +21,10 @@ #include #include +#include #include #include "usb.h" -static inline const char *plural(int n) -{ - return (n == 1 ? "" : "s"); -} - static int is_rndis(struct usb_interface_descriptor *desc) { return desc->bInterfaceClass == USB_CLASS_COMM @@ -194,18 +190,18 @@ int usb_choose_configuration(struct usb_device *udev) if (insufficient_power > 0) dev_info(&udev->dev, "rejected %d configuration%s " "due to insufficient available bus power\n", - insufficient_power, plural(insufficient_power)); + insufficient_power, str_plural(insufficient_power)); if (best) { i = best->desc.bConfigurationValue; dev_dbg(&udev->dev, "configuration #%d chosen from %d choice%s\n", - i, num_configs, plural(num_configs)); + i, num_configs, str_plural(num_configs)); } else { i = -1; dev_warn(&udev->dev, "no configuration chosen from %d choice%s\n", - num_configs, plural(num_configs)); + num_configs, str_plural(num_configs)); } return i; } diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index a08f3f228e6d..56b534f59907 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -422,7 +422,12 @@ static int suspend_common(struct device *dev, pm_message_t msg) bool do_wakeup; int retval; - do_wakeup = PMSG_IS_AUTO(msg) ? true : device_may_wakeup(dev); + if (PMSG_IS_AUTO(msg)) + do_wakeup = true; + else if (PMSG_NO_WAKEUP(msg)) + do_wakeup = false; + else + do_wakeup = device_may_wakeup(dev); /* Root hub suspend should have stopped all downstream traffic, * and all bus master traffic. And done so for both the interface @@ -521,6 +526,11 @@ static int hcd_pci_suspend(struct device *dev) return suspend_common(dev, PMSG_SUSPEND); } +static int hcd_pci_freeze(struct device *dev) +{ + return suspend_common(dev, PMSG_FREEZE); +} + static int hcd_pci_suspend_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); @@ -590,6 +600,7 @@ static int hcd_pci_restore(struct device *dev) #else #define hcd_pci_suspend NULL +#define hcd_pci_freeze NULL #define hcd_pci_suspend_noirq NULL #define hcd_pci_poweroff_late NULL #define hcd_pci_resume_noirq NULL @@ -624,7 +635,7 @@ const struct dev_pm_ops usb_hcd_pci_pm_ops = { .suspend_noirq = hcd_pci_suspend_noirq, .resume_noirq = hcd_pci_resume_noirq, .resume = hcd_pci_resume, - .freeze = hcd_pci_suspend, + .freeze = hcd_pci_freeze, .freeze_noirq = check_root_hub_suspended, .thaw_noirq = NULL, .thaw = hcd_pci_resume, diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 0b2490347b9f..a75cf1f6d741 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -415,7 +415,7 @@ ascii2desc(char const *s, u8 *buf, unsigned len) static unsigned rh_string(int id, struct usb_hcd const *hcd, u8 *data, unsigned len) { - char buf[100]; + char buf[160]; char const *s; static char const langids[4] = {4, USB_DT_STRING, 0x09, 0x04}; diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 4b93c0bd1d4b..c3f839637cb5 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -1496,7 +1497,7 @@ static int hub_configure(struct usb_hub *hub, maxchild = hub->descriptor->bNbrPorts; dev_info(hub_dev, "%d port%s detected\n", maxchild, - (maxchild == 1) ? "" : "s"); + str_plural(maxchild)); hub->ports = kcalloc(maxchild, sizeof(struct usb_port *), GFP_KERNEL); if (!hub->ports) { @@ -2663,13 +2664,13 @@ int usb_new_device(struct usb_device *udev) err = sysfs_create_link(&udev->dev.kobj, &port_dev->dev.kobj, "port"); if (err) - goto fail; + goto out_del_dev; err = sysfs_create_link(&port_dev->dev.kobj, &udev->dev.kobj, "device"); if (err) { sysfs_remove_link(&udev->dev.kobj, "port"); - goto fail; + goto out_del_dev; } if (!test_and_set_bit(port1, hub->child_usage_bits)) @@ -2683,6 +2684,8 @@ int usb_new_device(struct usb_device *udev) pm_runtime_put_sync_autosuspend(&udev->dev); return err; +out_del_dev: + device_del(&udev->dev); fail: usb_set_device_state(udev, USB_STATE_NOTATTACHED); pm_runtime_disable(&udev->dev); @@ -4137,14 +4140,14 @@ static int usb_set_device_initiated_lpm(struct usb_device *udev, break; default: dev_warn(&udev->dev, "%s: Can't %s non-U1 or U2 state.\n", - __func__, enable ? "enable" : "disable"); + __func__, str_enable_disable(enable)); return -EINVAL; } if (udev->state != USB_STATE_CONFIGURED) { dev_dbg(&udev->dev, "%s: Can't %s %s state " "for unconfigured device.\n", - __func__, enable ? "enable" : "disable", + __func__, str_enable_disable(enable), usb3_lpm_names[state]); return 0; } @@ -4170,8 +4173,7 @@ static int usb_set_device_initiated_lpm(struct usb_device *udev, } if (ret < 0) { dev_warn(&udev->dev, "%s of device-initiated %s failed.\n", - enable ? "Enable" : "Disable", - usb3_lpm_names[state]); + str_enable_disable(enable), usb3_lpm_names[state]); return -EBUSY; } return 0; diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 45d7af00f8d1..f54198171b6a 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -25,7 +26,7 @@ static ssize_t early_stop_show(struct device *dev, { struct usb_port *port_dev = to_usb_port(dev); - return sysfs_emit(buf, "%s\n", port_dev->early_stop ? "yes" : "no"); + return sysfs_emit(buf, "%s\n", str_yes_no(port_dev->early_stop)); } static ssize_t early_stop_store(struct device *dev, struct device_attribute *attr, @@ -453,10 +454,11 @@ static int usb_port_runtime_suspend(struct device *dev) static void usb_port_shutdown(struct device *dev) { struct usb_port *port_dev = to_usb_port(dev); + struct usb_device *udev = port_dev->child; - if (port_dev->child) { - usb_disable_usb2_hardware_lpm(port_dev->child); - usb_unlocked_disable_lpm(port_dev->child); + if (udev && !udev->port_is_suspended) { + usb_disable_usb2_hardware_lpm(udev); + usb_unlocked_disable_lpm(udev); } } diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 13171454f959..67732c791c93 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -394,6 +394,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Kingston DataTraveler 3.0 */ { USB_DEVICE(0x0951, 0x1666), .driver_info = USB_QUIRK_NO_LPM }, + /* TOSHIBA TransMemory-Mx */ + { USB_DEVICE(0x0930, 0x1408), .driver_info = USB_QUIRK_NO_LPM }, + /* NVIDIA Jetson devices in Force Recovery mode */ { USB_DEVICE(0x0955, 0x7018), .driver_info = USB_QUIRK_RESET_RESUME }, { USB_DEVICE(0x0955, 0x7019), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index b4cba23831ac..23f3cb1989f4 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -854,7 +854,7 @@ static const struct attribute_group dev_string_attr_grp = { static ssize_t descriptors_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -890,11 +890,11 @@ descriptors_read(struct file *filp, struct kobject *kobj, } return count - nleft; } -static BIN_ATTR_RO(descriptors, 18 + 65535); /* dev descr + max-size raw descriptor */ +static const BIN_ATTR_RO(descriptors, 18 + 65535); /* dev descr + max-size raw descriptor */ static ssize_t bos_descriptors_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -913,12 +913,12 @@ bos_descriptors_read(struct file *filp, struct kobject *kobj, } return n; } -static BIN_ATTR_RO(bos_descriptors, 65535); /* max-size BOS */ +static const BIN_ATTR_RO(bos_descriptors, 65535); /* max-size BOS */ /* When modifying this list, be sure to modify dev_bin_attrs_are_visible() * accordingly. */ -static struct bin_attribute *dev_bin_attrs[] = { +static const struct bin_attribute *const dev_bin_attrs[] = { &bin_attr_descriptors, &bin_attr_bos_descriptors, NULL @@ -944,7 +944,7 @@ static umode_t dev_bin_attrs_are_visible(struct kobject *kobj, } static const struct attribute_group dev_bin_attr_grp = { - .bin_attrs = dev_bin_attrs, + .bin_attrs_new = dev_bin_attrs, .is_bin_visible = dev_bin_attrs_are_visible, }; diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c index 03c22114214b..935c0efea0b6 100644 --- a/drivers/usb/core/usb-acpi.c +++ b/drivers/usb/core/usb-acpi.c @@ -213,8 +213,7 @@ usb_acpi_get_connect_type(struct usb_port *port_dev, acpi_handle *handle) * no connectable, the port would be not used. */ - status = acpi_get_physical_device_location(handle, &pld); - if (ACPI_SUCCESS(status) && pld) + if (acpi_get_physical_device_location(handle, &pld) && pld) port_dev->location = USB_ACPI_LOCATION_VALID | pld->group_token << 8 | pld->group_position; diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index f219c82e9619..dfa1b5fe48dc 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1479,6 +1479,26 @@ static int dwc3_core_init(struct dwc3 *dwc) } } + /* + * STAR 9001346572: This issue affects DWC_usb31 versions 1.80a and + * prior. When an active endpoint not currently cached in the host + * controller is chosen to be cached to the same index as an endpoint + * receiving NAKs, the endpoint receiving NAKs enters continuous + * retry mode. This prevents it from being evicted from the host + * controller cache, blocking the new endpoint from being cached and + * serviced. + * + * To resolve this, for controller versions 1.70a and 1.80a, set the + * GUCTL3 bit[16] (USB2.0 Internal Retry Disable) to 1. This bit + * disables the USB2.0 internal retry feature. The GUCTL3[16] register + * function is available only from version 1.70a. + */ + if (DWC3_VER_IS_WITHIN(DWC31, 170A, 180A)) { + reg = dwc3_readl(dwc->regs, DWC3_GUCTL3); + reg |= DWC3_GUCTL3_USB20_RETRY_DISABLE; + dwc3_writel(dwc->regs, DWC3_GUCTL3, reg); + } + return 0; err_power_off_phy: @@ -1664,8 +1684,6 @@ static void dwc3_get_properties(struct dwc3 *dwc) u8 tx_thr_num_pkt_prd = 0; u8 tx_max_burst_prd = 0; u8 tx_fifo_resize_max_num; - const char *usb_psy_name; - int ret; /* default to highest possible threshold */ lpm_nyet_threshold = 0xf; @@ -1700,13 +1718,6 @@ static void dwc3_get_properties(struct dwc3 *dwc) dwc->sys_wakeup = device_may_wakeup(dwc->sysdev); - ret = device_property_read_string(dev, "usb-psy-name", &usb_psy_name); - if (ret >= 0) { - dwc->usb_psy = power_supply_get_by_name(usb_psy_name); - if (!dwc->usb_psy) - dev_err(dev, "couldn't get usb power supply\n"); - } - dwc->has_lpm_erratum = device_property_read_bool(dev, "snps,has-lpm-erratum"); device_property_read_u8(dev, "snps,lpm-nyet-threshold", @@ -2109,6 +2120,23 @@ static int dwc3_get_num_ports(struct dwc3 *dwc) return 0; } +static struct power_supply *dwc3_get_usb_power_supply(struct dwc3 *dwc) +{ + struct power_supply *usb_psy; + const char *usb_psy_name; + int ret; + + ret = device_property_read_string(dwc->dev, "usb-psy-name", &usb_psy_name); + if (ret < 0) + return NULL; + + usb_psy = power_supply_get_by_name(usb_psy_name); + if (!usb_psy) + return ERR_PTR(-EPROBE_DEFER); + + return usb_psy; +} + static int dwc3_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -2165,6 +2193,10 @@ static int dwc3_probe(struct platform_device *pdev) dwc3_get_software_properties(dwc); + dwc->usb_psy = dwc3_get_usb_power_supply(dwc); + if (IS_ERR(dwc->usb_psy)) + return dev_err_probe(dev, PTR_ERR(dwc->usb_psy), "couldn't get usb power supply\n"); + dwc->reset = devm_reset_control_array_get_optional_shared(dev); if (IS_ERR(dwc->reset)) { ret = PTR_ERR(dwc->reset); @@ -2589,12 +2621,15 @@ static int dwc3_resume(struct device *dev) pinctrl_pm_select_default_state(dev); pm_runtime_disable(dev); - pm_runtime_set_active(dev); + ret = pm_runtime_set_active(dev); + if (ret) + goto out; ret = dwc3_resume_common(dwc, PMSG_RESUME); if (ret) pm_runtime_set_suspended(dev); +out: pm_runtime_enable(dev); return ret; diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index ee73789326bc..ac7c730f81ac 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -425,6 +425,7 @@ /* Global User Control Register 3 */ #define DWC3_GUCTL3_SPLITDISABLE BIT(14) +#define DWC3_GUCTL3_USB20_RETRY_DISABLE BIT(16) /* Device Configuration Register */ #define DWC3_DCFG_NUMLANES(n) (((n) & 0x3) << 30) /* DWC_usb32 only */ @@ -464,6 +465,7 @@ #define DWC3_DCTL_TRGTULST_SS_INACT (DWC3_DCTL_TRGTULST(6)) /* These apply for core versions 1.94a and later */ +#define DWC3_DCTL_NYET_THRES_MASK (0xf << 20) #define DWC3_DCTL_NYET_THRES(n) (((n) & 0xf) << 20) #define DWC3_DCTL_KEEP_CONNECT BIT(19) @@ -741,6 +743,7 @@ struct dwc3_event_buffer { */ struct dwc3_ep { struct usb_ep endpoint; + struct delayed_work nostream_work; struct list_head cancelled_list; struct list_head pending_list; struct list_head started_list; @@ -763,7 +766,7 @@ struct dwc3_ep { #define DWC3_EP_WAIT_TRANSFER_COMPLETE BIT(7) #define DWC3_EP_IGNORE_NEXT_NOSTREAM BIT(8) #define DWC3_EP_FORCE_RESTART_STREAM BIT(9) -#define DWC3_EP_FIRST_STREAM_PRIMED BIT(10) +#define DWC3_EP_STREAM_PRIMED BIT(10) #define DWC3_EP_PENDING_CLEAR_STALL BIT(11) #define DWC3_EP_TXFIFO_RESIZED BIT(12) #define DWC3_EP_DELAY_STOP BIT(13) @@ -956,7 +959,6 @@ struct dwc3_request { struct usb_request request; struct list_head list; struct dwc3_ep *dep; - struct scatterlist *sg; struct scatterlist *start_sg; unsigned int num_pending_sgs; diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index 5e3d1741701f..c158364bc03e 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -108,6 +108,9 @@ #define DWC3_AM62_AUTOSUSPEND_DELAY 100 +#define USBSS_DEBUG_CFG_OFF 0x0 +#define USBSS_DEBUG_CFG_DISABLED 0x7 + struct dwc3_am62 { struct device *dev; void __iomem *usbss; @@ -117,6 +120,7 @@ struct dwc3_am62 { unsigned int offset; unsigned int vbus_divider; u32 wakeup_stat; + void __iomem *phy_regs; }; static const int dwc3_ti_rate_table[] = { /* in KHZ */ @@ -166,6 +170,7 @@ static int phy_syscon_pll_refclk(struct dwc3_am62 *am62) if (ret) return ret; + of_node_put(args.np); am62->offset = args.args[0]; /* Core voltage. PHY_CORE_VOLTAGE bit Recommended to be 0 always */ @@ -184,15 +189,47 @@ static int phy_syscon_pll_refclk(struct dwc3_am62 *am62) return 0; } +static int dwc3_ti_init(struct dwc3_am62 *am62) +{ + int ret; + u32 reg; + + /* Read the syscon property and set the rate code */ + ret = phy_syscon_pll_refclk(am62); + if (ret) + return ret; + + /* Workaround Errata i2409 */ + if (am62->phy_regs) { + reg = readl(am62->phy_regs + USB_PHY_PLL_REG12); + reg |= USB_PHY_PLL_LDO_REF_EN | USB_PHY_PLL_LDO_REF_EN_EN; + writel(reg, am62->phy_regs + USB_PHY_PLL_REG12); + } + + /* VBUS divider select */ + reg = dwc3_ti_readl(am62, USBSS_PHY_CONFIG); + if (am62->vbus_divider) + reg |= 1 << USBSS_PHY_VBUS_SEL_SHIFT; + + dwc3_ti_writel(am62, USBSS_PHY_CONFIG, reg); + + clk_prepare_enable(am62->usb2_refclk); + + /* Set mode valid bit to indicate role is valid */ + reg = dwc3_ti_readl(am62, USBSS_MODE_CONTROL); + reg |= USBSS_MODE_VALID; + dwc3_ti_writel(am62, USBSS_MODE_CONTROL, reg); + + return 0; +} + static int dwc3_ti_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *node = pdev->dev.of_node; struct dwc3_am62 *am62; unsigned long rate; - void __iomem *phy; int i, ret; - u32 reg; am62 = devm_kzalloc(dev, sizeof(*am62), GFP_KERNEL); if (!am62) @@ -228,29 +265,17 @@ static int dwc3_ti_probe(struct platform_device *pdev) am62->rate_code = i; - /* Read the syscon property and set the rate code */ - ret = phy_syscon_pll_refclk(am62); - if (ret) - return ret; - - /* Workaround Errata i2409 */ - phy = devm_platform_ioremap_resource(pdev, 1); - if (IS_ERR(phy)) { + am62->phy_regs = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(am62->phy_regs)) { dev_err(dev, "can't map PHY IOMEM resource. Won't apply i2409 fix.\n"); - phy = NULL; - } else { - reg = readl(phy + USB_PHY_PLL_REG12); - reg |= USB_PHY_PLL_LDO_REF_EN | USB_PHY_PLL_LDO_REF_EN_EN; - writel(reg, phy + USB_PHY_PLL_REG12); + am62->phy_regs = NULL; } - /* VBUS divider select */ am62->vbus_divider = device_property_read_bool(dev, "ti,vbus-divider"); - reg = dwc3_ti_readl(am62, USBSS_PHY_CONFIG); - if (am62->vbus_divider) - reg |= 1 << USBSS_PHY_VBUS_SEL_SHIFT; - dwc3_ti_writel(am62, USBSS_PHY_CONFIG, reg); + ret = dwc3_ti_init(am62); + if (ret) + return ret; pm_runtime_set_active(dev); pm_runtime_enable(dev); @@ -258,7 +283,6 @@ static int dwc3_ti_probe(struct platform_device *pdev) * Don't ignore its dependencies with its children */ pm_suspend_ignore_children(dev, false); - clk_prepare_enable(am62->usb2_refclk); pm_runtime_get_noresume(dev); ret = of_platform_populate(node, NULL, NULL, dev); @@ -267,11 +291,6 @@ static int dwc3_ti_probe(struct platform_device *pdev) goto err_pm_disable; } - /* Set mode valid bit to indicate role is valid */ - reg = dwc3_ti_readl(am62, USBSS_MODE_CONTROL); - reg |= USBSS_MODE_VALID; - dwc3_ti_writel(am62, USBSS_MODE_CONTROL, reg); - /* Device has capability to wakeup system from sleep */ device_set_wakeup_capable(dev, true); ret = device_wakeup_enable(dev); @@ -309,6 +328,7 @@ static void dwc3_ti_remove(struct platform_device *pdev) pm_runtime_put_sync(dev); pm_runtime_disable(dev); + pm_runtime_dont_use_autosuspend(dev); pm_runtime_set_suspended(dev); } @@ -338,6 +358,9 @@ static int dwc3_ti_suspend_common(struct device *dev) dwc3_ti_writel(am62, USBSS_WAKEUP_STAT, USBSS_WAKEUP_STAT_CLR); } + /* just to track if module resets on suspend */ + dwc3_ti_writel(am62, USBSS_DEBUG_CFG, USBSS_DEBUG_CFG_DISABLED); + clk_disable_unprepare(am62->usb2_refclk); return 0; @@ -348,7 +371,14 @@ static int dwc3_ti_resume_common(struct device *dev) struct dwc3_am62 *am62 = dev_get_drvdata(dev); u32 reg; - clk_prepare_enable(am62->usb2_refclk); + reg = dwc3_ti_readl(am62, USBSS_DEBUG_CFG); + if (reg != USBSS_DEBUG_CFG_DISABLED) { + /* lost power/context */ + dwc3_ti_init(am62); + } else { + dwc3_ti_writel(am62, USBSS_DEBUG_CFG, USBSS_DEBUG_CFG_OFF); + clk_prepare_enable(am62->usb2_refclk); + } if (device_may_wakeup(dev)) { /* Clear wakeup config enable bits */ diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c index b261c46124c6..fe74d11bb629 100644 --- a/drivers/usb/dwc3/dwc3-omap.c +++ b/drivers/usb/dwc3/dwc3-omap.c @@ -457,7 +457,7 @@ static int dwc3_omap_probe(struct platform_device *pdev) struct dwc3_omap *omap; struct device *dev = &pdev->dev; - struct regulator *vbus_reg = NULL; + struct regulator *vbus_reg; int ret; int irq; @@ -483,12 +483,11 @@ static int dwc3_omap_probe(struct platform_device *pdev) if (IS_ERR(base)) return PTR_ERR(base); - if (of_property_read_bool(node, "vbus-supply")) { - vbus_reg = devm_regulator_get(dev, "vbus"); - if (IS_ERR(vbus_reg)) { - dev_err(dev, "vbus init failed\n"); - return PTR_ERR(vbus_reg); - } + vbus_reg = devm_regulator_get_optional(dev, "vbus"); + if (IS_ERR(vbus_reg)) { + if (PTR_ERR(vbus_reg) != -ENODEV) + return dev_err_probe(dev, PTR_ERR(vbus_reg), "vbus init failed\n"); + vbus_reg = NULL; } omap->dev = dev; diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c index e16c3237180e..ef7c43008946 100644 --- a/drivers/usb/dwc3/dwc3-st.c +++ b/drivers/usb/dwc3/dwc3-st.c @@ -309,7 +309,6 @@ static void st_dwc3_remove(struct platform_device *pdev) reset_control_assert(dwc3_data->rstc_rst); } -#ifdef CONFIG_PM_SLEEP static int st_dwc3_suspend(struct device *dev) { struct st_dwc3 *dwc3_data = dev_get_drvdata(dev); @@ -343,9 +342,8 @@ static int st_dwc3_resume(struct device *dev) return 0; } -#endif /* CONFIG_PM_SLEEP */ -static SIMPLE_DEV_PM_OPS(st_dwc3_dev_pm_ops, st_dwc3_suspend, st_dwc3_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(st_dwc3_dev_pm_ops, st_dwc3_suspend, st_dwc3_resume); static const struct of_device_id st_dwc3_match[] = { { .compatible = "st,stih407-dwc3" }, @@ -360,7 +358,7 @@ static struct platform_driver st_dwc3_driver = { .driver = { .name = "usb-st-dwc3", .of_match_table = st_dwc3_match, - .pm = &st_dwc3_dev_pm_ops, + .pm = pm_sleep_ptr(&st_dwc3_dev_pm_ops), }, }; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 83dc7304d701..d27af65eb08a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -996,8 +996,7 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, unsigned int action) /* * All stream eps will reinitiate stream on NoStream - * rejection until we can determine that the host can - * prime after the first transfer. + * rejection. * * However, if the controller is capable of * TXF_FLUSH_BYPASS, then IN direction endpoints will @@ -2740,6 +2739,8 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); + usb_gadget_set_state(dwc->gadget, USB_STATE_NOTATTACHED); + return ret; } @@ -3298,6 +3299,50 @@ static int dwc3_gadget_init_out_endpoint(struct dwc3_ep *dep) return dwc3_alloc_trb_pool(dep); } +#define nostream_work_to_dep(w) (container_of(to_delayed_work(w), struct dwc3_ep, nostream_work)) +static void dwc3_nostream_work(struct work_struct *work) +{ + struct dwc3_ep *dep = nostream_work_to_dep(work); + struct dwc3 *dwc = dep->dwc; + unsigned long flags; + + spin_lock_irqsave(&dwc->lock, flags); + if (dep->flags & DWC3_EP_STREAM_PRIMED) + goto out; + + if ((dep->flags & DWC3_EP_IGNORE_NEXT_NOSTREAM) || + (!DWC3_MST_CAPABLE(&dwc->hwparams) && + !(dep->flags & DWC3_EP_WAIT_TRANSFER_COMPLETE))) + goto out; + /* + * If the host rejects a stream due to no active stream, by the + * USB and xHCI spec, the endpoint will be put back to idle + * state. When the host is ready (buffer added/updated), it will + * prime the endpoint to inform the usb device controller. This + * triggers the device controller to issue ERDY to restart the + * stream. However, some hosts don't follow this and keep the + * endpoint in the idle state. No prime will come despite host + * streams are updated, and the device controller will not be + * triggered to generate ERDY to move the next stream data. To + * workaround this and maintain compatibility with various + * hosts, force to reinitiate the stream until the host is ready + * instead of waiting for the host to prime the endpoint. + */ + if (DWC3_VER_IS_WITHIN(DWC32, 100A, ANY)) { + unsigned int cmd = DWC3_DGCMD_SET_ENDPOINT_PRIME; + + dwc3_send_gadget_generic_command(dwc, cmd, dep->number); + } else { + dep->flags |= DWC3_EP_DELAY_START; + dwc3_stop_active_transfer(dep, true, true); + spin_unlock_irqrestore(&dwc->lock, flags); + return; + } +out: + dep->flags &= ~DWC3_EP_IGNORE_NEXT_NOSTREAM; + spin_unlock_irqrestore(&dwc->lock, flags); +} + static int dwc3_gadget_init_endpoint(struct dwc3 *dwc, u8 epnum) { struct dwc3_ep *dep; @@ -3343,6 +3388,7 @@ static int dwc3_gadget_init_endpoint(struct dwc3 *dwc, u8 epnum) INIT_LIST_HEAD(&dep->pending_list); INIT_LIST_HEAD(&dep->started_list); INIT_LIST_HEAD(&dep->cancelled_list); + INIT_DELAYED_WORK(&dep->nostream_work, dwc3_nostream_work); dwc3_debugfs_create_endpoint_dir(dep); @@ -3742,66 +3788,27 @@ static void dwc3_gadget_endpoint_command_complete(struct dwc3_ep *dep, static void dwc3_gadget_endpoint_stream_event(struct dwc3_ep *dep, const struct dwc3_event_depevt *event) { - struct dwc3 *dwc = dep->dwc; - if (event->status == DEPEVT_STREAMEVT_FOUND) { - dep->flags |= DWC3_EP_FIRST_STREAM_PRIMED; - goto out; + cancel_delayed_work(&dep->nostream_work); + dep->flags |= DWC3_EP_STREAM_PRIMED; + dep->flags &= ~DWC3_EP_IGNORE_NEXT_NOSTREAM; + return; } /* Note: NoStream rejection event param value is 0 and not 0xFFFF */ switch (event->parameters) { case DEPEVT_STREAM_PRIME: - /* - * If the host can properly transition the endpoint state from - * idle to prime after a NoStream rejection, there's no need to - * force restarting the endpoint to reinitiate the stream. To - * simplify the check, assume the host follows the USB spec if - * it primed the endpoint more than once. - */ - if (dep->flags & DWC3_EP_FORCE_RESTART_STREAM) { - if (dep->flags & DWC3_EP_FIRST_STREAM_PRIMED) - dep->flags &= ~DWC3_EP_FORCE_RESTART_STREAM; - else - dep->flags |= DWC3_EP_FIRST_STREAM_PRIMED; - } - + cancel_delayed_work(&dep->nostream_work); + dep->flags |= DWC3_EP_STREAM_PRIMED; + dep->flags &= ~DWC3_EP_IGNORE_NEXT_NOSTREAM; break; case DEPEVT_STREAM_NOSTREAM: - if ((dep->flags & DWC3_EP_IGNORE_NEXT_NOSTREAM) || - !(dep->flags & DWC3_EP_FORCE_RESTART_STREAM) || - (!DWC3_MST_CAPABLE(&dwc->hwparams) && - !(dep->flags & DWC3_EP_WAIT_TRANSFER_COMPLETE))) - break; - - /* - * If the host rejects a stream due to no active stream, by the - * USB and xHCI spec, the endpoint will be put back to idle - * state. When the host is ready (buffer added/updated), it will - * prime the endpoint to inform the usb device controller. This - * triggers the device controller to issue ERDY to restart the - * stream. However, some hosts don't follow this and keep the - * endpoint in the idle state. No prime will come despite host - * streams are updated, and the device controller will not be - * triggered to generate ERDY to move the next stream data. To - * workaround this and maintain compatibility with various - * hosts, force to reinitiate the stream until the host is ready - * instead of waiting for the host to prime the endpoint. - */ - if (DWC3_VER_IS_WITHIN(DWC32, 100A, ANY)) { - unsigned int cmd = DWC3_DGCMD_SET_ENDPOINT_PRIME; - - dwc3_send_gadget_generic_command(dwc, cmd, dep->number); - } else { - dep->flags |= DWC3_EP_DELAY_START; - dwc3_stop_active_transfer(dep, true, true); - return; - } + dep->flags &= ~DWC3_EP_STREAM_PRIMED; + if (dep->flags & DWC3_EP_FORCE_RESTART_STREAM) + queue_delayed_work(system_wq, &dep->nostream_work, + msecs_to_jiffies(100)); break; } - -out: - dep->flags &= ~DWC3_EP_IGNORE_NEXT_NOSTREAM; } static void dwc3_endpoint_interrupt(struct dwc3 *dwc, @@ -4195,8 +4202,10 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) WARN_ONCE(DWC3_VER_IS_PRIOR(DWC3, 240A) && dwc->has_lpm_erratum, "LPM Erratum not available on dwc3 revisions < 2.40a\n"); - if (dwc->has_lpm_erratum && !DWC3_VER_IS_PRIOR(DWC3, 240A)) + if (dwc->has_lpm_erratum && !DWC3_VER_IS_PRIOR(DWC3, 240A)) { + reg &= ~DWC3_DCTL_NYET_THRES_MASK; reg |= DWC3_DCTL_NYET_THRES(dwc->lpm_nyet_threshold); + } dwc3_gadget_dctl_write_safe(dwc, reg); } else { diff --git a/drivers/usb/fotg210/fotg210-core.c b/drivers/usb/fotg210/fotg210-core.c index 49f25a70b32e..7fb4d4715e9f 100644 --- a/drivers/usb/fotg210/fotg210-core.c +++ b/drivers/usb/fotg210/fotg210-core.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -119,8 +120,8 @@ void fotg210_vbus(struct fotg210 *fotg, bool enable) ret = regmap_update_bits(fotg->map, GEMINI_GLOBAL_MISC_CTRL, mask, val); if (ret) dev_err(fotg->dev, "failed to %s VBUS\n", - enable ? "enable" : "disable"); - dev_info(fotg->dev, "%s: %s VBUS\n", __func__, enable ? "enable" : "disable"); + str_enable_disable(enable)); + dev_info(fotg->dev, "%s: %s VBUS\n", __func__, str_enable_disable(enable)); } static int fotg210_probe(struct platform_device *pdev) diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 566ff0b1282a..76521555e3c1 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -211,6 +211,8 @@ config USB_F_MIDI config USB_F_MIDI2 tristate + select SND_UMP + select SND_UMP_LEGACY_RAWMIDI config USB_F_HID tristate @@ -445,8 +447,6 @@ config USB_CONFIGFS_F_MIDI2 depends on USB_CONFIGFS depends on SND select USB_LIBCOMPOSITE - select SND_UMP - select SND_UMP_LEGACY_RAWMIDI select USB_F_MIDI2 help The MIDI 2.0 function driver provides the generic emulated diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 6499a88d346c..fba2a56dae97 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -827,11 +827,15 @@ static ssize_t gadget_string_s_store(struct config_item *item, const char *page, { struct gadget_string *string = to_gadget_string(item); int size = min(sizeof(string->string), len + 1); + ssize_t cpy_len; if (len > USB_MAX_STRING_LEN) return -EINVAL; - return strscpy(string->string, page, size); + cpy_len = strscpy(string->string, page, size); + if (cpy_len > 0 && string->string[cpy_len - 1] == '\n') + string->string[cpy_len - 1] = 0; + return len; } CONFIGFS_ATTR(gadget_string_, s); diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c index 6cb7771e8a69..80841de845b0 100644 --- a/drivers/usb/gadget/function/f_ecm.c +++ b/drivers/usb/gadget/function/f_ecm.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "u_ether.h" #include "u_ether_configfs.h" @@ -387,8 +388,7 @@ static void ecm_do_notify(struct f_ecm *ecm) event->wLength = 0; req->length = sizeof *event; - DBG(cdev, "notify connect %s\n", - ecm->is_open ? "true" : "false"); + DBG(cdev, "notify connect %s\n", str_true_false(ecm->is_open)); ecm->notify_state = ECM_NOTIFY_SPEED; break; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ad79eb0f729b..2dea9e42a0f8 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2285,7 +2285,7 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev) struct usb_gadget_strings **lang; int first_id; - if (WARN_ON(ffs->state != FFS_ACTIVE + if ((ffs->state != FFS_ACTIVE || test_and_set_bit(FFS_FL_BOUND, &ffs->flags))) return -EBADFD; diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 8e761249d672..f60576a65ca6 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -17,6 +17,7 @@ #include #include #include +#include #include @@ -558,7 +559,7 @@ static void ncm_do_notify(struct f_ncm *ncm) req->length = sizeof *event; DBG(cdev, "notify connect %s\n", - ncm->is_open ? "true" : "false"); + str_true_false(ncm->is_open)); ncm->notify_state = NCM_NOTIFY_NONE; break; diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 15bb3aa12aa8..5a2e1237f85c 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -50,7 +51,7 @@ static int bot_enqueue_cmd_cbw(struct f_uas *fu) if (fu->flags & USBG_BOT_CMD_PEND) return 0; - ret = usb_ep_queue(fu->ep_out, fu->cmd.req, GFP_ATOMIC); + ret = usb_ep_queue(fu->ep_out, fu->cmd[0].req, GFP_ATOMIC); if (!ret) fu->flags |= USBG_BOT_CMD_PEND; return ret; @@ -62,10 +63,11 @@ static void bot_status_complete(struct usb_ep *ep, struct usb_request *req) struct f_uas *fu = cmd->fu; transport_generic_free_cmd(&cmd->se_cmd, 0); - if (req->status < 0) { - pr_err("ERR %s(%d)\n", __func__, __LINE__); + if (req->status == -ESHUTDOWN) return; - } + + if (req->status < 0) + pr_err("ERR %s(%d)\n", __func__, __LINE__); /* CSW completed, wait for next CBW */ bot_enqueue_cmd_cbw(fu); @@ -136,7 +138,7 @@ static void bot_send_bad_status(struct usbg_cmd *cmd) } req->complete = bot_err_compl; req->context = cmd; - req->buf = fu->cmd.buf; + req->buf = fu->cmd[0].buf; usb_ep_queue(ep, req, GFP_KERNEL); } else { bot_enqueue_sense_code(fu, cmd); @@ -196,6 +198,11 @@ static void bot_read_compl(struct usb_ep *ep, struct usb_request *req) if (req->status < 0) pr_err("ERR %s(%d)\n", __func__, __LINE__); + if (req->status == -ESHUTDOWN) { + transport_generic_free_cmd(&cmd->se_cmd, 0); + return; + } + bot_send_status(cmd, true); } @@ -244,11 +251,8 @@ static int usbg_prepare_w_request(struct usbg_cmd *, struct usb_request *); static int bot_send_write_request(struct usbg_cmd *cmd) { struct f_uas *fu = cmd->fu; - struct se_cmd *se_cmd = &cmd->se_cmd; - struct usb_gadget *gadget = fuas_to_gadget(fu); int ret; - init_completion(&cmd->write_complete); cmd->fu = fu; if (!cmd->data_len) { @@ -256,22 +260,6 @@ static int bot_send_write_request(struct usbg_cmd *cmd) return -EINVAL; } - if (!gadget->sg_supported) { - cmd->data_buf = kmalloc(se_cmd->data_length, GFP_KERNEL); - if (!cmd->data_buf) - return -ENOMEM; - - fu->bot_req_out->buf = cmd->data_buf; - } else { - fu->bot_req_out->buf = NULL; - fu->bot_req_out->num_sgs = se_cmd->t_data_nents; - fu->bot_req_out->sg = se_cmd->t_data_sg; - } - - fu->bot_req_out->complete = usbg_data_write_cmpl; - fu->bot_req_out->length = se_cmd->data_length; - fu->bot_req_out->context = cmd; - ret = usbg_prepare_w_request(cmd, fu->bot_req_out); if (ret) goto cleanup; @@ -279,8 +267,6 @@ static int bot_send_write_request(struct usbg_cmd *cmd) if (ret) pr_err("%s(%d)\n", __func__, __LINE__); - wait_for_completion(&cmd->write_complete); - target_execute_cmd(se_cmd); cleanup: return ret; } @@ -292,14 +278,31 @@ static void bot_cmd_complete(struct usb_ep *ep, struct usb_request *req) struct f_uas *fu = req->context; int ret; - fu->flags &= ~USBG_BOT_CMD_PEND; - - if (req->status < 0) + if (req->status == -ESHUTDOWN) return; + fu->flags &= ~USBG_BOT_CMD_PEND; + + if (req->status < 0) { + struct usb_gadget *gadget = fuas_to_gadget(fu); + + dev_err(&gadget->dev, "BOT command req err (%d)\n", req->status); + bot_enqueue_cmd_cbw(fu); + return; + } + ret = bot_submit_command(fu, req->buf, req->actual); - if (ret) + if (ret) { pr_err("%s(%d): %d\n", __func__, __LINE__, ret); + if (!(fu->flags & USBG_BOT_WEDGED)) + usb_ep_set_wedge(fu->ep_in); + + fu->flags |= USBG_BOT_WEDGED; + bot_enqueue_cmd_cbw(fu); + } else if (fu->flags & USBG_BOT_WEDGED) { + fu->flags &= ~USBG_BOT_WEDGED; + usb_ep_clear_halt(fu->ep_in); + } } static int bot_prepare_reqs(struct f_uas *fu) @@ -314,8 +317,8 @@ static int bot_prepare_reqs(struct f_uas *fu) if (!fu->bot_req_out) goto err_out; - fu->cmd.req = usb_ep_alloc_request(fu->ep_out, GFP_KERNEL); - if (!fu->cmd.req) + fu->cmd[0].req = usb_ep_alloc_request(fu->ep_out, GFP_KERNEL); + if (!fu->cmd[0].req) goto err_cmd; fu->bot_status.req = usb_ep_alloc_request(fu->ep_in, GFP_KERNEL); @@ -327,27 +330,27 @@ static int bot_prepare_reqs(struct f_uas *fu) fu->bot_status.req->complete = bot_status_complete; fu->bot_status.csw.Signature = cpu_to_le32(US_BULK_CS_SIGN); - fu->cmd.buf = kmalloc(fu->ep_out->maxpacket, GFP_KERNEL); - if (!fu->cmd.buf) + fu->cmd[0].buf = kmalloc(fu->ep_out->maxpacket, GFP_KERNEL); + if (!fu->cmd[0].buf) goto err_buf; - fu->cmd.req->complete = bot_cmd_complete; - fu->cmd.req->buf = fu->cmd.buf; - fu->cmd.req->length = fu->ep_out->maxpacket; - fu->cmd.req->context = fu; + fu->cmd[0].req->complete = bot_cmd_complete; + fu->cmd[0].req->buf = fu->cmd[0].buf; + fu->cmd[0].req->length = fu->ep_out->maxpacket; + fu->cmd[0].req->context = fu; ret = bot_enqueue_cmd_cbw(fu); if (ret) goto err_queue; return 0; err_queue: - kfree(fu->cmd.buf); - fu->cmd.buf = NULL; + kfree(fu->cmd[0].buf); + fu->cmd[0].buf = NULL; err_buf: usb_ep_free_request(fu->ep_in, fu->bot_status.req); err_sts: - usb_ep_free_request(fu->ep_out, fu->cmd.req); - fu->cmd.req = NULL; + usb_ep_free_request(fu->ep_out, fu->cmd[0].req); + fu->cmd[0].req = NULL; err_cmd: usb_ep_free_request(fu->ep_out, fu->bot_req_out); fu->bot_req_out = NULL; @@ -372,16 +375,16 @@ static void bot_cleanup_old_alt(struct f_uas *fu) usb_ep_free_request(fu->ep_in, fu->bot_req_in); usb_ep_free_request(fu->ep_out, fu->bot_req_out); - usb_ep_free_request(fu->ep_out, fu->cmd.req); + usb_ep_free_request(fu->ep_out, fu->cmd[0].req); usb_ep_free_request(fu->ep_in, fu->bot_status.req); - kfree(fu->cmd.buf); + kfree(fu->cmd[0].buf); fu->bot_req_in = NULL; fu->bot_req_out = NULL; - fu->cmd.req = NULL; + fu->cmd[0].req = NULL; fu->bot_status.req = NULL; - fu->cmd.buf = NULL; + fu->cmd[0].buf = NULL; } static void bot_set_alt(struct f_uas *fu) @@ -441,14 +444,10 @@ static int usbg_bot_setup(struct usb_function *f, pr_err("No LUNs configured?\n"); return -EINVAL; } - /* - * If 4 LUNs are present we return 3 i.e. LUN 0..3 can be - * accessed. The upper limit is 0xf - */ luns--; - if (luns > 0xf) { + if (luns > US_BULK_MAX_LUN_LIMIT) { pr_info_once("Limiting the number of luns to 16\n"); - luns = 0xf; + luns = US_BULK_MAX_LUN_LIMIT; } ret_lun = cdev->req->buf; *ret_lun = luns; @@ -457,6 +456,11 @@ static int usbg_bot_setup(struct usb_function *f, case US_BULK_RESET_REQUEST: /* XXX maybe we should remove previous requests for IN + OUT */ + if (fu->flags & USBG_BOT_WEDGED) { + fu->flags &= ~USBG_BOT_WEDGED; + usb_ep_clear_halt(fu->ep_in); + } + bot_enqueue_cmd_cbw(fu); return 0; } @@ -465,6 +469,45 @@ static int usbg_bot_setup(struct usb_function *f, /* Start uas.c code */ +static int tcm_to_uasp_response(enum tcm_tmrsp_table code) +{ + switch (code) { + case TMR_FUNCTION_FAILED: + return RC_TMF_FAILED; + case TMR_FUNCTION_COMPLETE: + case TMR_TASK_DOES_NOT_EXIST: + return RC_TMF_COMPLETE; + case TMR_LUN_DOES_NOT_EXIST: + return RC_INCORRECT_LUN; + case TMR_FUNCTION_REJECTED: + case TMR_TASK_MGMT_FUNCTION_NOT_SUPPORTED: + default: + return RC_TMF_NOT_SUPPORTED; + } +} + +static unsigned char uasp_to_tcm_func(int code) +{ + switch (code) { + case TMF_ABORT_TASK: + return TMR_ABORT_TASK; + case TMF_ABORT_TASK_SET: + return TMR_ABORT_TASK_SET; + case TMF_CLEAR_TASK_SET: + return TMR_CLEAR_TASK_SET; + case TMF_LOGICAL_UNIT_RESET: + return TMR_LUN_RESET; + case TMF_CLEAR_ACA: + return TMR_CLEAR_ACA; + case TMF_I_T_NEXUS_RESET: + case TMF_QUERY_TASK: + case TMF_QUERY_TASK_SET: + case TMF_QUERY_ASYNC_EVENT: + default: + return TMR_UNKNOWN; + } +} + static void uasp_cleanup_one_stream(struct f_uas *fu, struct uas_stream *stream) { /* We have either all three allocated or none */ @@ -482,10 +525,14 @@ static void uasp_cleanup_one_stream(struct f_uas *fu, struct uas_stream *stream) static void uasp_free_cmdreq(struct f_uas *fu) { - usb_ep_free_request(fu->ep_cmd, fu->cmd.req); - kfree(fu->cmd.buf); - fu->cmd.req = NULL; - fu->cmd.buf = NULL; + int i; + + for (i = 0; i < USBG_NUM_CMDS; i++) { + usb_ep_free_request(fu->ep_cmd, fu->cmd[i].req); + kfree(fu->cmd[i].buf); + fu->cmd[i].req = NULL; + fu->cmd[i].buf = NULL; + } } static void uasp_cleanup_old_alt(struct f_uas *fu) @@ -500,7 +547,7 @@ static void uasp_cleanup_old_alt(struct f_uas *fu) usb_ep_disable(fu->ep_status); usb_ep_disable(fu->ep_cmd); - for (i = 0; i < UASP_SS_EP_COMP_NUM_STREAMS; i++) + for (i = 0; i < USBG_NUM_CMDS; i++) uasp_cleanup_one_stream(fu, &fu->stream[i]); uasp_free_cmdreq(fu); } @@ -512,7 +559,7 @@ static int uasp_prepare_r_request(struct usbg_cmd *cmd) struct se_cmd *se_cmd = &cmd->se_cmd; struct f_uas *fu = cmd->fu; struct usb_gadget *gadget = fuas_to_gadget(fu); - struct uas_stream *stream = cmd->stream; + struct uas_stream *stream = &fu->stream[se_cmd->map_tag]; if (!gadget->sg_supported) { cmd->data_buf = kmalloc(se_cmd->data_length, GFP_ATOMIC); @@ -532,6 +579,7 @@ static int uasp_prepare_r_request(struct usbg_cmd *cmd) } stream->req_in->is_last = 1; + stream->req_in->stream_id = cmd->tag; stream->req_in->complete = uasp_status_data_cmpl; stream->req_in->length = se_cmd->data_length; stream->req_in->context = cmd; @@ -544,7 +592,7 @@ static void uasp_prepare_status(struct usbg_cmd *cmd) { struct se_cmd *se_cmd = &cmd->se_cmd; struct sense_iu *iu = &cmd->sense_iu; - struct uas_stream *stream = cmd->stream; + struct uas_stream *stream = &cmd->fu->stream[se_cmd->map_tag]; cmd->state = UASP_QUEUE_COMMAND; iu->iu_id = IU_ID_STATUS; @@ -556,20 +604,76 @@ static void uasp_prepare_status(struct usbg_cmd *cmd) iu->len = cpu_to_be16(se_cmd->scsi_sense_length); iu->status = se_cmd->scsi_status; stream->req_status->is_last = 1; + stream->req_status->stream_id = cmd->tag; stream->req_status->context = cmd; stream->req_status->length = se_cmd->scsi_sense_length + 16; stream->req_status->buf = iu; stream->req_status->complete = uasp_status_data_cmpl; } +static void uasp_prepare_response(struct usbg_cmd *cmd) +{ + struct se_cmd *se_cmd = &cmd->se_cmd; + struct response_iu *rsp_iu = &cmd->response_iu; + struct uas_stream *stream = &cmd->fu->stream[se_cmd->map_tag]; + + cmd->state = UASP_QUEUE_COMMAND; + rsp_iu->iu_id = IU_ID_RESPONSE; + rsp_iu->tag = cpu_to_be16(cmd->tag); + + if (cmd->tmr_rsp != RC_RESPONSE_UNKNOWN) + rsp_iu->response_code = cmd->tmr_rsp; + else + rsp_iu->response_code = + tcm_to_uasp_response(se_cmd->se_tmr_req->response); + + /* + * The UASP driver must support all the task management functions listed + * in Table 20 of UAS-r04. To remain compliant while indicate that the + * TMR did not go through, report RC_TMF_FAILED instead of + * RC_TMF_NOT_SUPPORTED and print a warning to the user. + */ + switch (cmd->tmr_func) { + case TMF_ABORT_TASK: + case TMF_ABORT_TASK_SET: + case TMF_CLEAR_TASK_SET: + case TMF_LOGICAL_UNIT_RESET: + case TMF_CLEAR_ACA: + case TMF_I_T_NEXUS_RESET: + case TMF_QUERY_TASK: + case TMF_QUERY_TASK_SET: + case TMF_QUERY_ASYNC_EVENT: + if (rsp_iu->response_code == RC_TMF_NOT_SUPPORTED) { + struct usb_gadget *gadget = fuas_to_gadget(cmd->fu); + + dev_warn(&gadget->dev, "TMF function %d not supported\n", + cmd->tmr_func); + rsp_iu->response_code = RC_TMF_FAILED; + } + break; + default: + break; + } + + stream->req_status->is_last = 1; + stream->req_status->stream_id = cmd->tag; + stream->req_status->context = cmd; + stream->req_status->length = sizeof(struct response_iu); + stream->req_status->buf = rsp_iu; + stream->req_status->complete = uasp_status_data_cmpl; +} + +static void usbg_release_cmd(struct se_cmd *se_cmd); +static int uasp_send_tm_response(struct usbg_cmd *cmd); + static void uasp_status_data_cmpl(struct usb_ep *ep, struct usb_request *req) { struct usbg_cmd *cmd = req->context; - struct uas_stream *stream = cmd->stream; struct f_uas *fu = cmd->fu; + struct uas_stream *stream = &fu->stream[cmd->se_cmd.map_tag]; int ret; - if (req->status < 0) + if (req->status == -ESHUTDOWN) goto cleanup; switch (cmd->state) { @@ -600,8 +704,37 @@ static void uasp_status_data_cmpl(struct usb_ep *ep, struct usb_request *req) break; case UASP_QUEUE_COMMAND: - transport_generic_free_cmd(&cmd->se_cmd, 0); - usb_ep_queue(fu->ep_cmd, fu->cmd.req, GFP_ATOMIC); + /* + * Overlapped command detected and cancelled. + * So send overlapped attempted status. + */ + if (cmd->tmr_rsp == RC_OVERLAPPED_TAG && + req->status == -ECONNRESET) { + uasp_send_tm_response(cmd); + return; + } + + hash_del(&stream->node); + + /* + * If no command submitted to target core here, just free the + * bitmap index. This is for the cases where f_tcm handles + * status response instead of the target core. + */ + if (cmd->tmr_rsp != RC_OVERLAPPED_TAG && + cmd->tmr_rsp != RC_RESPONSE_UNKNOWN) { + struct se_session *se_sess; + + se_sess = fu->tpg->tpg_nexus->tvn_se_sess; + sbitmap_queue_clear(&se_sess->sess_tag_pool, + cmd->se_cmd.map_tag, + cmd->se_cmd.map_cpu); + } else { + transport_generic_free_cmd(&cmd->se_cmd, 0); + } + + usb_ep_queue(fu->ep_cmd, cmd->req, GFP_ATOMIC); + complete(&stream->cmd_completion); break; default: @@ -610,27 +743,38 @@ static void uasp_status_data_cmpl(struct usb_ep *ep, struct usb_request *req) return; cleanup: + hash_del(&stream->node); transport_generic_free_cmd(&cmd->se_cmd, 0); } static int uasp_send_status_response(struct usbg_cmd *cmd) { struct f_uas *fu = cmd->fu; - struct uas_stream *stream = cmd->stream; + struct uas_stream *stream = &fu->stream[cmd->se_cmd.map_tag]; struct sense_iu *iu = &cmd->sense_iu; iu->tag = cpu_to_be16(cmd->tag); - stream->req_status->complete = uasp_status_data_cmpl; - stream->req_status->context = cmd; cmd->fu = fu; uasp_prepare_status(cmd); return usb_ep_queue(fu->ep_status, stream->req_status, GFP_ATOMIC); } +static int uasp_send_tm_response(struct usbg_cmd *cmd) +{ + struct f_uas *fu = cmd->fu; + struct uas_stream *stream = &fu->stream[cmd->se_cmd.map_tag]; + struct response_iu *iu = &cmd->response_iu; + + iu->tag = cpu_to_be16(cmd->tag); + cmd->fu = fu; + uasp_prepare_response(cmd); + return usb_ep_queue(fu->ep_status, stream->req_status, GFP_ATOMIC); +} + static int uasp_send_read_response(struct usbg_cmd *cmd) { struct f_uas *fu = cmd->fu; - struct uas_stream *stream = cmd->stream; + struct uas_stream *stream = &fu->stream[cmd->se_cmd.map_tag]; struct sense_iu *iu = &cmd->sense_iu; int ret; @@ -674,11 +818,10 @@ static int uasp_send_write_request(struct usbg_cmd *cmd) { struct f_uas *fu = cmd->fu; struct se_cmd *se_cmd = &cmd->se_cmd; - struct uas_stream *stream = cmd->stream; + struct uas_stream *stream = &fu->stream[se_cmd->map_tag]; struct sense_iu *iu = &cmd->sense_iu; int ret; - init_completion(&cmd->write_complete); cmd->fu = fu; iu->tag = cpu_to_be16(cmd->tag); @@ -710,36 +853,31 @@ static int uasp_send_write_request(struct usbg_cmd *cmd) pr_err("%s(%d)\n", __func__, __LINE__); } - wait_for_completion(&cmd->write_complete); - target_execute_cmd(se_cmd); cleanup: return ret; } -static int usbg_submit_command(struct f_uas *, void *, unsigned int); +static int usbg_submit_command(struct f_uas *, struct usb_request *); static void uasp_cmd_complete(struct usb_ep *ep, struct usb_request *req) { struct f_uas *fu = req->context; - int ret; - if (req->status < 0) + if (req->status == -ESHUTDOWN) return; - ret = usbg_submit_command(fu, req->buf, req->actual); - /* - * Once we tune for performance enqueue the command req here again so - * we can receive a second command while we processing this one. Pay - * attention to properly sync STAUS endpoint with DATA IN + OUT so you - * don't break HS. - */ - if (!ret) + if (req->status < 0) { + usb_ep_queue(fu->ep_cmd, req, GFP_ATOMIC); return; - usb_ep_queue(fu->ep_cmd, fu->cmd.req, GFP_ATOMIC); + } + + usbg_submit_command(fu, req); } static int uasp_alloc_stream_res(struct f_uas *fu, struct uas_stream *stream) { + init_completion(&stream->cmd_completion); + stream->req_in = usb_ep_alloc_request(fu->ep_in, GFP_KERNEL); if (!stream->req_in) goto out; @@ -764,66 +902,48 @@ out: return -ENOMEM; } -static int uasp_alloc_cmd(struct f_uas *fu) +static int uasp_alloc_cmd(struct f_uas *fu, int i) { - fu->cmd.req = usb_ep_alloc_request(fu->ep_cmd, GFP_KERNEL); - if (!fu->cmd.req) + fu->cmd[i].req = usb_ep_alloc_request(fu->ep_cmd, GFP_KERNEL); + if (!fu->cmd[i].req) goto err; - fu->cmd.buf = kmalloc(fu->ep_cmd->maxpacket, GFP_KERNEL); - if (!fu->cmd.buf) + fu->cmd[i].buf = kmalloc(fu->ep_cmd->maxpacket, GFP_KERNEL); + if (!fu->cmd[i].buf) goto err_buf; - fu->cmd.req->complete = uasp_cmd_complete; - fu->cmd.req->buf = fu->cmd.buf; - fu->cmd.req->length = fu->ep_cmd->maxpacket; - fu->cmd.req->context = fu; + fu->cmd[i].req->complete = uasp_cmd_complete; + fu->cmd[i].req->buf = fu->cmd[i].buf; + fu->cmd[i].req->length = fu->ep_cmd->maxpacket; + fu->cmd[i].req->context = fu; return 0; err_buf: - usb_ep_free_request(fu->ep_cmd, fu->cmd.req); + usb_ep_free_request(fu->ep_cmd, fu->cmd[i].req); err: return -ENOMEM; } -static void uasp_setup_stream_res(struct f_uas *fu, int max_streams) -{ - int i; - - for (i = 0; i < max_streams; i++) { - struct uas_stream *s = &fu->stream[i]; - - s->req_in->stream_id = i + 1; - s->req_out->stream_id = i + 1; - s->req_status->stream_id = i + 1; - } -} - static int uasp_prepare_reqs(struct f_uas *fu) { int ret; int i; - int max_streams; - if (fu->flags & USBG_USE_STREAMS) - max_streams = UASP_SS_EP_COMP_NUM_STREAMS; - else - max_streams = 1; - - for (i = 0; i < max_streams; i++) { + for (i = 0; i < USBG_NUM_CMDS; i++) { ret = uasp_alloc_stream_res(fu, &fu->stream[i]); if (ret) goto err_cleanup; } - ret = uasp_alloc_cmd(fu); - if (ret) - goto err_free_stream; - uasp_setup_stream_res(fu, max_streams); + for (i = 0; i < USBG_NUM_CMDS; i++) { + ret = uasp_alloc_cmd(fu, i); + if (ret) + goto err_free_stream; - ret = usb_ep_queue(fu->ep_cmd, fu->cmd.req, GFP_ATOMIC); - if (ret) - goto err_free_stream; + ret = usb_ep_queue(fu->ep_cmd, fu->cmd[i].req, GFP_ATOMIC); + if (ret) + goto err_free_stream; + } return 0; @@ -914,6 +1034,8 @@ static int get_cmd_dir(const unsigned char *cdb) case READ_TOC: case READ_FORMAT_CAPACITIES: case REQUEST_SENSE: + case ATA_12: + case ATA_16: ret = DMA_FROM_DEVICE; break; @@ -957,7 +1079,18 @@ static void usbg_data_write_cmpl(struct usb_ep *ep, struct usb_request *req) struct usbg_cmd *cmd = req->context; struct se_cmd *se_cmd = &cmd->se_cmd; - if (req->status < 0) { + cmd->state = UASP_QUEUE_COMMAND; + + if (req->status == -ESHUTDOWN) { + struct uas_stream *stream = &cmd->fu->stream[se_cmd->map_tag]; + + hash_del(&stream->node); + target_put_sess_cmd(se_cmd); + transport_generic_free_cmd(&cmd->se_cmd, 0); + return; + } + + if (req->status) { pr_err("%s() state %d transfer failed\n", __func__, cmd->state); goto cleanup; } @@ -969,11 +1102,22 @@ static void usbg_data_write_cmpl(struct usb_ep *ep, struct usb_request *req) se_cmd->data_length); } - complete(&cmd->write_complete); + cmd->flags |= USBG_CMD_PENDING_DATA_WRITE; + queue_work(cmd->fu->tpg->workqueue, &cmd->work); return; cleanup: - transport_generic_free_cmd(&cmd->se_cmd, 0); + target_put_sess_cmd(se_cmd); + + /* Command was aborted due to overlapped tag */ + if (cmd->state == UASP_QUEUE_COMMAND && + cmd->tmr_rsp == RC_OVERLAPPED_TAG) { + uasp_send_tm_response(cmd); + return; + } + + transport_send_check_condition_and_sense(se_cmd, + TCM_CHECK_CONDITION_ABORT_CMD, 0); } static int usbg_prepare_w_request(struct usbg_cmd *cmd, struct usb_request *req) @@ -995,9 +1139,12 @@ static int usbg_prepare_w_request(struct usbg_cmd *cmd, struct usb_request *req) } req->is_last = 1; + req->stream_id = cmd->tag; req->complete = usbg_data_write_cmpl; req->length = se_cmd->data_length; req->context = cmd; + + cmd->state = UASP_SEND_STATUS; return 0; } @@ -1037,36 +1184,153 @@ static int usbg_send_read_response(struct se_cmd *se_cmd) return uasp_send_read_response(cmd); } -static void usbg_cmd_work(struct work_struct *work) +static void usbg_aborted_task(struct se_cmd *se_cmd); + +static void usbg_submit_tmr(struct usbg_cmd *cmd) +{ + struct se_session *se_sess; + struct se_cmd *se_cmd; + int flags = TARGET_SCF_ACK_KREF; + + se_cmd = &cmd->se_cmd; + se_sess = cmd->fu->tpg->tpg_nexus->tvn_se_sess; + + target_submit_tmr(se_cmd, se_sess, + cmd->response_iu.add_response_info, + cmd->unpacked_lun, NULL, uasp_to_tcm_func(cmd->tmr_func), + GFP_ATOMIC, cmd->tag, flags); +} + +static void usbg_submit_cmd(struct usbg_cmd *cmd) { - struct usbg_cmd *cmd = container_of(work, struct usbg_cmd, work); struct se_cmd *se_cmd; struct tcm_usbg_nexus *tv_nexus; struct usbg_tpg *tpg; int dir, flags = (TARGET_SCF_UNKNOWN_SIZE | TARGET_SCF_ACK_KREF); + /* + * Note: each command will spawn its own process, and each stage of the + * command is processed sequentially. Should this no longer be the case, + * locking is needed. + */ + if (cmd->flags & USBG_CMD_PENDING_DATA_WRITE) { + target_execute_cmd(&cmd->se_cmd); + cmd->flags &= ~USBG_CMD_PENDING_DATA_WRITE; + return; + } + se_cmd = &cmd->se_cmd; tpg = cmd->fu->tpg; tv_nexus = tpg->tpg_nexus; dir = get_cmd_dir(cmd->cmd_buf); - if (dir < 0) { - __target_init_cmd(se_cmd, - tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo, - tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE, - cmd->prio_attr, cmd->sense_iu.sense, - cmd->unpacked_lun, NULL); + if (dir < 0) goto out; - } target_submit_cmd(se_cmd, tv_nexus->tvn_se_sess, cmd->cmd_buf, cmd->sense_iu.sense, cmd->unpacked_lun, 0, cmd->prio_attr, dir, flags); + return; out: + __target_init_cmd(se_cmd, + tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo, + tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE, + cmd->prio_attr, cmd->sense_iu.sense, + cmd->unpacked_lun, NULL); transport_send_check_condition_and_sense(se_cmd, - TCM_UNSUPPORTED_SCSI_OPCODE, 1); - transport_generic_free_cmd(&cmd->se_cmd, 0); + TCM_UNSUPPORTED_SCSI_OPCODE, 0); +} + +static void usbg_cmd_work(struct work_struct *work) +{ + struct usbg_cmd *cmd = container_of(work, struct usbg_cmd, work); + + /* + * Failure is detected by f_tcm here. Skip submitting the command to the + * target core if we already know the failing response and send the usb + * response to the host directly. + */ + if (cmd->tmr_rsp != RC_RESPONSE_UNKNOWN) + goto skip; + + if (cmd->tmr_func) + usbg_submit_tmr(cmd); + else + usbg_submit_cmd(cmd); + + return; + +skip: + if (cmd->tmr_rsp == RC_OVERLAPPED_TAG) { + struct f_uas *fu = cmd->fu; + struct se_session *se_sess; + struct uas_stream *stream = NULL; + struct hlist_node *tmp; + struct usbg_cmd *active_cmd = NULL; + + se_sess = cmd->fu->tpg->tpg_nexus->tvn_se_sess; + + hash_for_each_possible_safe(fu->stream_hash, stream, tmp, node, cmd->tag) { + int i = stream - &fu->stream[0]; + + active_cmd = &((struct usbg_cmd *)se_sess->sess_cmd_map)[i]; + if (active_cmd->tag == cmd->tag) + break; + } + + /* Sanity check */ + if (!stream || (active_cmd && active_cmd->tag != cmd->tag)) { + usbg_submit_command(cmd->fu, cmd->req); + return; + } + + reinit_completion(&stream->cmd_completion); + + /* + * A UASP command consists of the command, data, and status + * stages, each operating sequentially from different endpoints. + * + * Each USB endpoint operates independently, and depending on + * hardware implementation, a completion callback for a transfer + * from one endpoint may not reflect the order of completion on + * the wire. This is particularly true for devices with + * endpoints that have independent interrupts and event buffers. + * + * The driver must still detect misbehaving hosts and respond + * with an overlap status. To reduce false overlap failures, + * allow the active and matching stream ID a brief 1ms to + * complete before responding with an overlap command failure. + * Overlap failure should be rare. + */ + wait_for_completion_timeout(&stream->cmd_completion, msecs_to_jiffies(1)); + + /* If the previous stream is completed, retry the command. */ + if (!hash_hashed(&stream->node)) { + usbg_submit_command(cmd->fu, cmd->req); + return; + } + + /* + * The command isn't submitted to the target core, so we're safe + * to remove the bitmap index from the session tag pool. + */ + sbitmap_queue_clear(&se_sess->sess_tag_pool, + cmd->se_cmd.map_tag, + cmd->se_cmd.map_cpu); + + /* + * Overlap command tag detected. Cancel any pending transfer of + * the command submitted to target core. + */ + active_cmd->tmr_rsp = RC_OVERLAPPED_TAG; + usbg_aborted_task(&active_cmd->se_cmd); + + /* Send the response after the transfer is aborted. */ + return; + } + + uasp_send_tm_response(cmd); } static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu, @@ -1084,6 +1348,7 @@ static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu, memset(cmd, 0, sizeof(*cmd)); cmd->se_cmd.map_tag = tag; cmd->se_cmd.map_cpu = cpu; + cmd->se_cmd.cpuid = cpu; cmd->se_cmd.tag = cmd->tag = scsi_tag; cmd->fu = fu; @@ -1092,50 +1357,82 @@ static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu, static void usbg_release_cmd(struct se_cmd *); -static int usbg_submit_command(struct f_uas *fu, - void *cmdbuf, unsigned int len) +static int usbg_submit_command(struct f_uas *fu, struct usb_request *req) { - struct command_iu *cmd_iu = cmdbuf; + struct iu *iu = req->buf; struct usbg_cmd *cmd; struct usbg_tpg *tpg = fu->tpg; struct tcm_usbg_nexus *tv_nexus; + struct uas_stream *stream; + struct hlist_node *tmp; + struct command_iu *cmd_iu; u32 cmd_len; u16 scsi_tag; - if (cmd_iu->iu_id != IU_ID_COMMAND) { - pr_err("Unsupported type %d\n", cmd_iu->iu_id); - return -EINVAL; - } - tv_nexus = tpg->tpg_nexus; if (!tv_nexus) { pr_err("Missing nexus, ignoring command\n"); return -EINVAL; } - cmd_len = (cmd_iu->len & ~0x3) + 16; - if (cmd_len > USBG_MAX_CMD) - return -EINVAL; - - scsi_tag = be16_to_cpup(&cmd_iu->tag); + scsi_tag = be16_to_cpup(&iu->tag); cmd = usbg_get_cmd(fu, tv_nexus, scsi_tag); if (IS_ERR(cmd)) { pr_err("usbg_get_cmd failed\n"); return -ENOMEM; } - memcpy(cmd->cmd_buf, cmd_iu->cdb, cmd_len); - if (fu->flags & USBG_USE_STREAMS) { - if (cmd->tag > UASP_SS_EP_COMP_NUM_STREAMS) - goto err; - if (!cmd->tag) - cmd->stream = &fu->stream[0]; - else - cmd->stream = &fu->stream[cmd->tag - 1]; - } else { - cmd->stream = &fu->stream[0]; + cmd->req = req; + cmd->fu = fu; + cmd->tag = scsi_tag; + cmd->se_cmd.tag = scsi_tag; + cmd->tmr_func = 0; + cmd->tmr_rsp = RC_RESPONSE_UNKNOWN; + cmd->flags = 0; + + cmd_iu = (struct command_iu *)iu; + + /* Command and Task Management IUs share the same LUN offset */ + cmd->unpacked_lun = scsilun_to_int(&cmd_iu->lun); + + if (iu->iu_id != IU_ID_COMMAND && iu->iu_id != IU_ID_TASK_MGMT) { + cmd->tmr_rsp = RC_INVALID_INFO_UNIT; + goto skip; } + hash_for_each_possible_safe(fu->stream_hash, stream, tmp, node, scsi_tag) { + struct usbg_cmd *active_cmd; + struct se_session *se_sess; + int i = stream - &fu->stream[0]; + + se_sess = cmd->fu->tpg->tpg_nexus->tvn_se_sess; + active_cmd = &((struct usbg_cmd *)se_sess->sess_cmd_map)[i]; + + if (active_cmd->tag == scsi_tag) { + cmd->tmr_rsp = RC_OVERLAPPED_TAG; + goto skip; + } + } + + stream = &fu->stream[cmd->se_cmd.map_tag]; + hash_add(fu->stream_hash, &stream->node, scsi_tag); + + if (iu->iu_id == IU_ID_TASK_MGMT) { + struct task_mgmt_iu *tm_iu; + + tm_iu = (struct task_mgmt_iu *)iu; + cmd->tmr_func = tm_iu->function; + goto skip; + } + + cmd_len = (cmd_iu->len & ~0x3) + 16; + if (cmd_len > USBG_MAX_CMD) { + target_free_tag(tv_nexus->tvn_se_sess, &cmd->se_cmd); + hash_del(&stream->node); + return -EINVAL; + } + memcpy(cmd->cmd_buf, cmd_iu->cdb, cmd_len); + switch (cmd_iu->prio_attr & 0x7) { case UAS_HEAD_TAG: cmd->prio_attr = TCM_HEAD_TAG; @@ -1155,15 +1452,11 @@ static int usbg_submit_command(struct f_uas *fu, break; } - cmd->unpacked_lun = scsilun_to_int(&cmd_iu->lun); - +skip: INIT_WORK(&cmd->work, usbg_cmd_work); queue_work(tpg->workqueue, &cmd->work); return 0; -err: - usbg_release_cmd(&cmd->se_cmd); - return -EINVAL; } static void bot_cmd_work(struct work_struct *work) @@ -1172,30 +1465,40 @@ static void bot_cmd_work(struct work_struct *work) struct se_cmd *se_cmd; struct tcm_usbg_nexus *tv_nexus; struct usbg_tpg *tpg; + int flags = TARGET_SCF_ACK_KREF; int dir; + /* + * Note: each command will spawn its own process, and each stage of the + * command is processed sequentially. Should this no longer be the case, + * locking is needed. + */ + if (cmd->flags & USBG_CMD_PENDING_DATA_WRITE) { + target_execute_cmd(&cmd->se_cmd); + cmd->flags &= ~USBG_CMD_PENDING_DATA_WRITE; + return; + } + se_cmd = &cmd->se_cmd; tpg = cmd->fu->tpg; tv_nexus = tpg->tpg_nexus; dir = get_cmd_dir(cmd->cmd_buf); - if (dir < 0) { - __target_init_cmd(se_cmd, - tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo, - tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE, - cmd->prio_attr, cmd->sense_iu.sense, - cmd->unpacked_lun, NULL); + if (dir < 0) goto out; - } target_submit_cmd(se_cmd, tv_nexus->tvn_se_sess, cmd->cmd_buf, cmd->sense_iu.sense, cmd->unpacked_lun, - cmd->data_len, cmd->prio_attr, dir, 0); + cmd->data_len, cmd->prio_attr, dir, flags); return; out: + __target_init_cmd(se_cmd, + tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo, + tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE, + cmd->prio_attr, cmd->sense_iu.sense, + cmd->unpacked_lun, NULL); transport_send_check_condition_and_sense(se_cmd, - TCM_UNSUPPORTED_SCSI_OPCODE, 1); - transport_generic_free_cmd(&cmd->se_cmd, 0); + TCM_UNSUPPORTED_SCSI_OPCODE, 0); } static int bot_submit_command(struct f_uas *fu, @@ -1239,6 +1542,7 @@ static int bot_submit_command(struct f_uas *fu, cmd->is_read = cbw->Flags & US_BULK_FLAG_IN ? 1 : 0; cmd->data_len = le32_to_cpu(cbw->DataTransferLength); cmd->se_cmd.tag = le32_to_cpu(cmd->bot_tag); + cmd->flags = 0; INIT_WORK(&cmd->work, bot_cmd_work); queue_work(tpg->workqueue, &cmd->work); @@ -1275,16 +1579,38 @@ static void usbg_release_cmd(struct se_cmd *se_cmd) se_cmd); struct se_session *se_sess = se_cmd->se_sess; + cmd->tag = 0; kfree(cmd->data_buf); target_free_tag(se_sess, se_cmd); } static void usbg_queue_tm_rsp(struct se_cmd *se_cmd) { + struct usbg_cmd *cmd = container_of(se_cmd, struct usbg_cmd, se_cmd); + + uasp_send_tm_response(cmd); } static void usbg_aborted_task(struct se_cmd *se_cmd) { + struct usbg_cmd *cmd = container_of(se_cmd, struct usbg_cmd, se_cmd); + struct f_uas *fu = cmd->fu; + struct usb_gadget *gadget = fuas_to_gadget(fu); + struct uas_stream *stream = &fu->stream[se_cmd->map_tag]; + int ret = 0; + + if (stream->req_out->status == -EINPROGRESS) + ret = usb_ep_dequeue(fu->ep_out, stream->req_out); + else if (stream->req_in->status == -EINPROGRESS) + ret = usb_ep_dequeue(fu->ep_in, stream->req_in); + else if (stream->req_status->status == -EINPROGRESS) + ret = usb_ep_dequeue(fu->ep_status, stream->req_status); + + if (ret) + dev_err(&gadget->dev, "Failed to abort cmd tag %d, (%d)\n", + cmd->tag, ret); + + cmd->state = UASP_QUEUE_COMMAND; } static const char *usbg_check_wwn(const char *name) @@ -1355,7 +1681,8 @@ static struct se_portal_group *usbg_make_tpg(struct se_wwn *wwn, goto unref_dep; mutex_init(&tpg->tpg_mutex); atomic_set(&tpg->tpg_port_count, 0); - tpg->workqueue = alloc_workqueue("tcm_usb_gadget", 0, 1); + tpg->workqueue = alloc_workqueue("tcm_usb_gadget", + WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); if (!tpg->workqueue) goto free_tpg; @@ -1746,7 +2073,7 @@ static struct usb_endpoint_descriptor uasp_ss_bi_desc = { static struct usb_ss_ep_comp_descriptor uasp_bi_ep_comp_desc = { .bLength = sizeof(uasp_bi_ep_comp_desc), .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, - .bMaxBurst = 0, + .bMaxBurst = 15, .bmAttributes = UASP_SS_EP_COMP_LOG_STREAMS, .wBytesPerInterval = 0, }; @@ -1754,7 +2081,7 @@ static struct usb_ss_ep_comp_descriptor uasp_bi_ep_comp_desc = { static struct usb_ss_ep_comp_descriptor bot_bi_ep_comp_desc = { .bLength = sizeof(bot_bi_ep_comp_desc), .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, - .bMaxBurst = 0, + .bMaxBurst = 15, }; static struct usb_endpoint_descriptor uasp_bo_desc = { @@ -1789,12 +2116,14 @@ static struct usb_endpoint_descriptor uasp_ss_bo_desc = { static struct usb_ss_ep_comp_descriptor uasp_bo_ep_comp_desc = { .bLength = sizeof(uasp_bo_ep_comp_desc), .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + .bMaxBurst = 15, .bmAttributes = UASP_SS_EP_COMP_LOG_STREAMS, }; static struct usb_ss_ep_comp_descriptor bot_bo_ep_comp_desc = { .bLength = sizeof(bot_bo_ep_comp_desc), .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + .bMaxBurst = 15, }; static struct usb_endpoint_descriptor uasp_status_desc = { @@ -1971,43 +2300,39 @@ static int tcm_bind(struct usb_configuration *c, struct usb_function *f) bot_intf_desc.bInterfaceNumber = iface; uasp_intf_desc.bInterfaceNumber = iface; fu->iface = iface; - ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_bi_desc, - &uasp_bi_ep_comp_desc); + ep = usb_ep_autoconfig(gadget, &uasp_fs_bi_desc); if (!ep) goto ep_fail; fu->ep_in = ep; - ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_bo_desc, - &uasp_bo_ep_comp_desc); + ep = usb_ep_autoconfig(gadget, &uasp_fs_bo_desc); if (!ep) goto ep_fail; fu->ep_out = ep; - ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_status_desc, - &uasp_status_in_ep_comp_desc); + ep = usb_ep_autoconfig(gadget, &uasp_fs_status_desc); if (!ep) goto ep_fail; fu->ep_status = ep; - ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_cmd_desc, - &uasp_cmd_comp_desc); + ep = usb_ep_autoconfig(gadget, &uasp_fs_cmd_desc); if (!ep) goto ep_fail; fu->ep_cmd = ep; /* Assume endpoint addresses are the same for both speeds */ - uasp_bi_desc.bEndpointAddress = uasp_ss_bi_desc.bEndpointAddress; - uasp_bo_desc.bEndpointAddress = uasp_ss_bo_desc.bEndpointAddress; + uasp_bi_desc.bEndpointAddress = uasp_fs_bi_desc.bEndpointAddress; + uasp_bo_desc.bEndpointAddress = uasp_fs_bo_desc.bEndpointAddress; uasp_status_desc.bEndpointAddress = - uasp_ss_status_desc.bEndpointAddress; - uasp_cmd_desc.bEndpointAddress = uasp_ss_cmd_desc.bEndpointAddress; + uasp_fs_status_desc.bEndpointAddress; + uasp_cmd_desc.bEndpointAddress = uasp_fs_cmd_desc.bEndpointAddress; - uasp_fs_bi_desc.bEndpointAddress = uasp_ss_bi_desc.bEndpointAddress; - uasp_fs_bo_desc.bEndpointAddress = uasp_ss_bo_desc.bEndpointAddress; - uasp_fs_status_desc.bEndpointAddress = - uasp_ss_status_desc.bEndpointAddress; - uasp_fs_cmd_desc.bEndpointAddress = uasp_ss_cmd_desc.bEndpointAddress; + uasp_ss_bi_desc.bEndpointAddress = uasp_fs_bi_desc.bEndpointAddress; + uasp_ss_bo_desc.bEndpointAddress = uasp_fs_bo_desc.bEndpointAddress; + uasp_ss_status_desc.bEndpointAddress = + uasp_fs_status_desc.bEndpointAddress; + uasp_ss_cmd_desc.bEndpointAddress = uasp_fs_cmd_desc.bEndpointAddress; ret = usb_assign_descriptors(f, uasp_fs_function_desc, uasp_hs_function_desc, uasp_ss_function_desc, @@ -2051,9 +2376,14 @@ static void tcm_delayed_set_alt(struct work_struct *wq) static int tcm_get_alt(struct usb_function *f, unsigned intf) { - if (intf == bot_intf_desc.bInterfaceNumber) + struct f_uas *fu = to_f_uas(f); + + if (fu->iface != intf) + return -EOPNOTSUPP; + + if (fu->flags & USBG_IS_BOT) return USB_G_ALT_INT_BBB; - if (intf == uasp_intf_desc.bInterfaceNumber) + else if (fu->flags & USBG_IS_UAS) return USB_G_ALT_INT_UAS; return -EOPNOTSUPP; @@ -2063,6 +2393,9 @@ static int tcm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) { struct f_uas *fu = to_f_uas(f); + if (fu->iface != intf) + return -EOPNOTSUPP; + if ((alt == USB_G_ALT_INT_BBB) || (alt == USB_G_ALT_INT_UAS)) { struct guas_setup_wq *work; @@ -2271,6 +2604,8 @@ static struct usb_function *tcm_alloc(struct usb_function_instance *fi) fu->function.disable = tcm_disable; fu->function.free_func = tcm_free; fu->tpg = tpg_instances[i].tpg; + + hash_init(fu->stream_hash); mutex_unlock(&tpg_instances_lock); return &fu->function; diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index ce5b77f89190..9b324821c93b 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -1185,6 +1185,7 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) uac2->as_in_alt = 0; } + std_ac_if_desc.bNumEndpoints = 0; if (FUOUT_EN(uac2_opts) || FUIN_EN(uac2_opts)) { uac2->int_ep = usb_ep_autoconfig(gadget, &fs_ep_int_desc); if (!uac2->int_ep) { diff --git a/drivers/usb/gadget/function/storage_common.h b/drivers/usb/gadget/function/storage_common.h index ced5d2b09234..11ac785d5eee 100644 --- a/drivers/usb/gadget/function/storage_common.h +++ b/drivers/usb/gadget/function/storage_common.h @@ -131,7 +131,7 @@ static inline bool fsg_lun_is_open(struct fsg_lun *curlun) #define FSG_BUFLEN ((u32)16384) /* Maximal number of LUNs supported in mass storage function */ -#define FSG_MAX_LUNS 16 +#define FSG_MAX_LUNS (US_BULK_MAX_LUN_LIMIT + 1) enum fsg_buffer_state { BUF_STATE_SENDING = -2, diff --git a/drivers/usb/gadget/function/tcm.h b/drivers/usb/gadget/function/tcm.h index 3cd565794ad7..009974d81d66 100644 --- a/drivers/usb/gadget/function/tcm.h +++ b/drivers/usb/gadget/function/tcm.h @@ -4,6 +4,7 @@ #include /* #include */ +#include #include #include #include @@ -13,9 +14,11 @@ #define USBG_NAMELEN 32 #define fuas_to_gadget(f) (f->function.config->cdev->gadget) -#define UASP_SS_EP_COMP_LOG_STREAMS 4 +#define UASP_SS_EP_COMP_LOG_STREAMS 5 #define UASP_SS_EP_COMP_NUM_STREAMS (1 << UASP_SS_EP_COMP_LOG_STREAMS) +#define USBG_NUM_CMDS (UASP_SS_EP_COMP_NUM_STREAMS + 1) + enum { USB_G_STR_INT_UAS = 0, USB_G_STR_INT_BBB, @@ -24,7 +27,7 @@ enum { #define USB_G_ALT_INT_BBB 0 #define USB_G_ALT_INT_UAS 1 -#define USB_G_DEFAULT_SESSION_TAGS 128 +#define USB_G_DEFAULT_SESSION_TAGS USBG_NUM_CMDS struct tcm_usbg_nexus { struct se_session *tvn_se_sess; @@ -72,15 +75,23 @@ struct usbg_cmd { struct se_cmd se_cmd; void *data_buf; /* used if no sg support available */ struct f_uas *fu; - struct completion write_complete; struct kref ref; + struct usb_request *req; + + u32 flags; +#define USBG_CMD_PENDING_DATA_WRITE BIT(0) + /* UAS only */ u16 tag; u16 prio_attr; struct sense_iu sense_iu; + struct response_iu response_iu; enum uas_state state; - struct uas_stream *stream; + + int tmr_func; + int tmr_rsp; +#define RC_RESPONSE_UNKNOWN 0xff /* BOT only */ __le32 bot_tag; @@ -93,6 +104,9 @@ struct uas_stream { struct usb_request *req_in; struct usb_request *req_out; struct usb_request *req_status; + + struct completion cmd_completion; + struct hlist_node node; }; struct usbg_cdb { @@ -116,15 +130,17 @@ struct f_uas { #define USBG_USE_STREAMS (1 << 2) #define USBG_IS_BOT (1 << 3) #define USBG_BOT_CMD_PEND (1 << 4) +#define USBG_BOT_WEDGED (1 << 5) - struct usbg_cdb cmd; + struct usbg_cdb cmd[USBG_NUM_CMDS]; struct usb_ep *ep_in; struct usb_ep *ep_out; /* UAS */ struct usb_ep *ep_status; struct usb_ep *ep_cmd; - struct uas_stream stream[UASP_SS_EP_COMP_NUM_STREAMS]; + struct uas_stream stream[USBG_NUM_CMDS]; + DECLARE_HASHTABLE(stream_hash, UASP_SS_EP_COMP_LOG_STREAMS); /* BOT */ struct bot_status bot_status; diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 53d9fc41acc5..36fff45e8c9b 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -1545,7 +1546,7 @@ static int __init userial_init(void) pr_debug("%s: registered %d ttyGS* device%s\n", __func__, MAX_U_SERIAL_PORTS, - (MAX_U_SERIAL_PORTS == 1) ? "" : "s"); + str_plural(MAX_U_SERIAL_PORTS)); return status; fail: diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 9c7381661016..b6a30d88a800 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -1182,7 +1183,7 @@ ep0_fasync (int f, struct file *fd, int on) { struct dev_data *dev = fd->private_data; // caller must F_SETOWN before signal delivery happens - VDEBUG (dev, "%s %s\n", __func__, on ? "on" : "off"); + VDEBUG(dev, "%s %s\n", __func__, str_on_off(on)); return fasync_helper (f, fd, on, &dev->fasync); } diff --git a/drivers/usb/gadget/udc/aspeed-vhub/hub.c b/drivers/usb/gadget/udc/aspeed-vhub/hub.c index a63e4af60a56..02fe1a08d575 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/hub.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/hub.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -219,7 +220,7 @@ static int ast_vhub_hub_dev_feature(struct ast_vhub_ep *ep, if (wValue == USB_DEVICE_REMOTE_WAKEUP) { ep->vhub->wakeup_en = is_set; EPDBG(ep, "Hub remote wakeup %s\n", - is_set ? "enabled" : "disabled"); + str_enabled_disabled(is_set)); return std_req_complete; } diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c index e3af4ec3794e..aa4c61094dc6 100644 --- a/drivers/usb/gadget/udc/at91_udc.c +++ b/drivers/usb/gadget/udc/at91_udc.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -131,7 +132,7 @@ static void proc_ep_show(struct seq_file *s, struct at91_ep *ep) seq_printf(s, "csr %08x rxbytes=%d %s %s %s" EIGHTBITS "\n", csr, (csr & 0x07ff0000) >> 16, - (csr & (1 << 15)) ? "enabled" : "disabled", + str_enabled_disabled(csr & (1 << 15)), (csr & (1 << 11)) ? "DATA1" : "DATA0", types[(csr & 0x700) >> 8], diff --git a/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c b/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c index 62fce42ef2da..7e69944ef18a 100644 --- a/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c +++ b/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -2233,12 +2234,12 @@ static int cdns2_init_eps(struct cdns2_device *pdev) dev_dbg(pdev->dev, "Init %s, SupType: CTRL: %s, INT: %s, " "BULK: %s, ISOC %s, SupDir IN: %s, OUT: %s\n", pep->name, - (pep->endpoint.caps.type_control) ? "yes" : "no", - (pep->endpoint.caps.type_int) ? "yes" : "no", - (pep->endpoint.caps.type_bulk) ? "yes" : "no", - (pep->endpoint.caps.type_iso) ? "yes" : "no", - (pep->endpoint.caps.dir_in) ? "yes" : "no", - (pep->endpoint.caps.dir_out) ? "yes" : "no"); + str_yes_no(pep->endpoint.caps.type_control), + str_yes_no(pep->endpoint.caps.type_int), + str_yes_no(pep->endpoint.caps.type_bulk), + str_yes_no(pep->endpoint.caps.type_iso), + str_yes_no(pep->endpoint.caps.dir_in), + str_yes_no(pep->endpoint.caps.dir_out)); INIT_LIST_HEAD(&pep->pending_list); INIT_LIST_HEAD(&pep->deferred_list); diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index a7e8fa45776b..bda08c5ba7c0 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -625,7 +626,7 @@ static int dummy_enable(struct usb_ep *_ep, desc->bEndpointAddress & 0x0f, (desc->bEndpointAddress & USB_DIR_IN) ? "in" : "out", usb_ep_type_string(usb_endpoint_type(desc)), - max, ep->stream_en ? "enabled" : "disabled"); + max, str_enabled_disabled(ep->stream_en)); /* at this point real hardware should be NAKing transfers * to that endpoint, until a buffer is queued to it. diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index 8b7f7f961774..4dea8bc30cf6 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -1181,7 +1182,7 @@ static int fsl_vbus_session(struct usb_gadget *gadget, int is_active) udc = container_of(gadget, struct fsl_udc, gadget); spin_lock_irqsave(&udc->lock, flags); - dev_vdbg(&gadget->dev, "VBUS %s\n", is_active ? "on" : "off"); + dev_vdbg(&gadget->dev, "VBUS %s\n", str_on_off(is_active)); udc->vbus_active = (is_active != 0); if (can_pullup(udc)) fsl_writel((fsl_readl(&dr_regs->usbcmd) | USB_CMD_RUN_STOP), diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index 698463bf697b..8902abe3ca76 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -1252,7 +1253,7 @@ static int omap_vbus_session(struct usb_gadget *gadget, int is_active) udc = container_of(gadget, struct omap_udc, gadget); spin_lock_irqsave(&udc->lock, flags); - VDBG("VBUS %s\n", is_active ? "on" : "off"); + VDBG("VBUS %s\n", str_on_off(is_active)); udc->vbus_active = (is_active != 0); if (cpu_is_omap15xx()) { /* "software" detect, ignored if !VBUS_MODE_1510 */ diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c index f9a55d4f189f..897f53601b5b 100644 --- a/drivers/usb/gadget/udc/pxa27x_udc.c +++ b/drivers/usb/gadget/udc/pxa27x_udc.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -1083,7 +1084,7 @@ static int pxa_ep_queue(struct usb_ep *_ep, struct usb_request *_req, is_first_req = list_empty(&ep->queue); ep_dbg(ep, "queue req %p(first=%s), len %d buf %p\n", - _req, is_first_req ? "yes" : "no", + _req, str_yes_no(is_first_req), _req->length, _req->buf); if (!ep->enabled) { diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c index a6c20facf945..fce800ba4c61 100644 --- a/drivers/usb/host/oxu210hp-hcd.c +++ b/drivers/usb/host/oxu210hp-hcd.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -2756,7 +2757,7 @@ static void ehci_port_power(struct oxu_hcd *oxu, int is_on) if (!HCS_PPC(oxu->hcs_params)) return; - oxu_dbg(oxu, "...power%s ports...\n", is_on ? "up" : "down"); + oxu_dbg(oxu, "...power%s ports...\n", str_up_down(is_on)); for (port = HCS_N_PORTS(oxu->hcs_params); port > 0; ) { if (is_on) oxu_hub_control(oxu_to_hcd(oxu), SetPortFeature, diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index 036f5fd6d159..fa2e4badd288 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include @@ -98,7 +99,7 @@ static void port_power(struct sl811 *sl811, int is_on) if (sl811->board && sl811->board->port_power) { /* switch VBUS, at 500mA unless hub power budget gets set */ dev_dbg(hcd->self.controller, "power %s\n", - is_on ? "on" : "off"); + str_on_off(is_on)); sl811->board->port_power(hcd->self.controller, is_on); } diff --git a/drivers/usb/host/xhci-caps.h b/drivers/usb/host/xhci-caps.h index 9e94cebf4a56..f6b9a00a0ab9 100644 --- a/drivers/usb/host/xhci-caps.h +++ b/drivers/usb/host/xhci-caps.h @@ -83,3 +83,9 @@ #define HCC2_CIC(p) ((p) & (1 << 5)) /* true: HC support Extended TBC Capability, Isoc burst count > 65535 */ #define HCC2_ETC(p) ((p) & (1 << 6)) +/* true: HC support Extended TBC TRB Status Capability */ +#define HCC2_ETC_TSC(p) ((p) & (1 << 7)) +/* true: HC support Get/Set Extended Property Capability */ +#define HCC2_GSC(p) ((p) & (1 << 8)) +/* true: HC support Virtualization Based Trusted I/O Capability */ +#define HCC2_VTC(p) ((p) & (1 << 9)) diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index 227e513867dd..fd7895b24367 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -957,7 +957,7 @@ static void xhci_dbc_handle_events(struct work_struct *work) /* set fast poll rate if there are pending data transfers */ if (!list_empty(&dbc->eps[BULK_OUT].list_pending) || !list_empty(&dbc->eps[BULK_IN].list_pending)) - poll_interval = 1; + poll_interval = 0; break; default: dev_info(dbc->dev, "stop handling dbc events\n"); diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c index d719c16ea30b..60ed753c85bb 100644 --- a/drivers/usb/host/xhci-dbgtty.c +++ b/drivers/usb/host/xhci-dbgtty.c @@ -110,15 +110,74 @@ static void dbc_start_rx(struct dbc_port *port) } } +/* + * Queue received data to tty buffer and push it. + * + * Returns nr of remaining bytes that didn't fit tty buffer, i.e. 0 if all + * bytes sucessfullt moved. In case of error returns negative errno. + * Call with lock held + */ +static int dbc_rx_push_buffer(struct dbc_port *port, struct dbc_request *req) +{ + char *packet = req->buf; + unsigned int n, size = req->actual; + int count; + + if (!req->actual) + return 0; + + /* if n_read is set then request was partially moved to tty buffer */ + n = port->n_read; + if (n) { + packet += n; + size -= n; + } + + count = tty_insert_flip_string(&port->port, packet, size); + if (count) + tty_flip_buffer_push(&port->port); + if (count != size) { + port->n_read += count; + return size - count; + } + + port->n_read = 0; + return 0; +} + static void dbc_read_complete(struct xhci_dbc *dbc, struct dbc_request *req) { unsigned long flags; struct dbc_port *port = dbc_to_port(dbc); + struct tty_struct *tty; + int untransferred; + + tty = port->port.tty; spin_lock_irqsave(&port->port_lock, flags); + + /* + * Only defer copyig data to tty buffer in case: + * - !list_empty(&port->read_queue), there are older pending data + * - tty is throttled + * - failed to copy all data to buffer, defer remaining part + */ + + if (list_empty(&port->read_queue) && tty && !tty_throttled(tty)) { + untransferred = dbc_rx_push_buffer(port, req); + if (untransferred == 0) { + list_add_tail(&req->list_pool, &port->read_pool); + if (req->status != -ESHUTDOWN) + dbc_start_rx(port); + goto out; + } + } + + /* defer moving data from req to tty buffer to a tasklet */ list_add_tail(&req->list_pool, &port->read_queue); tasklet_schedule(&port->push); +out: spin_unlock_irqrestore(&port->port_lock, flags); } @@ -331,10 +390,10 @@ static void dbc_rx_push(struct tasklet_struct *t) struct dbc_request *req; struct tty_struct *tty; unsigned long flags; - bool do_push = false; bool disconnect = false; struct dbc_port *port = from_tasklet(port, t, push); struct list_head *queue = &port->read_queue; + int untransferred; spin_lock_irqsave(&port->port_lock, flags); tty = port->port.tty; @@ -356,42 +415,15 @@ static void dbc_rx_push(struct tasklet_struct *t) break; } - if (req->actual) { - char *packet = req->buf; - unsigned int n, size = req->actual; - int count; - - n = port->n_read; - if (n) { - packet += n; - size -= n; - } - - count = tty_insert_flip_string(&port->port, packet, - size); - if (count) - do_push = true; - if (count != size) { - port->n_read += count; - break; - } - port->n_read = 0; - } + untransferred = dbc_rx_push_buffer(port, req); + if (untransferred > 0) + break; list_move_tail(&req->list_pool, &port->read_pool); } - if (do_push) - tty_flip_buffer_push(&port->port); - - if (!list_empty(queue) && tty) { - if (!tty_throttled(tty)) { - if (do_push) - tasklet_schedule(&port->push); - else - pr_warn("ttyDBC0: RX not scheduled?\n"); - } - } + if (!list_empty(queue)) + tasklet_schedule(&port->push); if (!disconnect) dbc_start_rx(port); diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index 4f0c1b96e208..1f5ef174abea 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -232,16 +232,7 @@ static struct xhci_file_map ring_files[] = { static int xhci_ring_open(struct inode *inode, struct file *file) { - int i; - struct xhci_file_map *f_map; - const char *file_name = file_dentry(file)->d_iname; - - for (i = 0; i < ARRAY_SIZE(ring_files); i++) { - f_map = &ring_files[i]; - - if (strcmp(f_map->name, file_name) == 0) - break; - } + const struct xhci_file_map *f_map = debugfs_get_aux(file); return single_open(file, f_map->show, inode->i_private); } @@ -318,16 +309,7 @@ static struct xhci_file_map context_files[] = { static int xhci_context_open(struct inode *inode, struct file *file) { - int i; - struct xhci_file_map *f_map; - const char *file_name = file_dentry(file)->d_iname; - - for (i = 0; i < ARRAY_SIZE(context_files); i++) { - f_map = &context_files[i]; - - if (strcmp(f_map->name, file_name) == 0) - break; - } + const struct xhci_file_map *f_map = debugfs_get_aux(file); return single_open(file, f_map->show, inode->i_private); } @@ -410,7 +392,8 @@ static void xhci_debugfs_create_files(struct xhci_hcd *xhci, int i; for (i = 0; i < nentries; i++) - debugfs_create_file(files[i].name, 0444, parent, data, fops); + debugfs_create_file_aux(files[i].name, 0444, parent, + data, &files[i], fops); } static struct dentry *xhci_debugfs_create_ring_dir(struct xhci_hcd *xhci, diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 15db90c54a45..92703efda1f7 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -436,7 +436,7 @@ int xhci_ring_expansion(struct xhci_hcd *xhci, struct xhci_ring *ring, goto free_segments; } - xhci_link_rings(xhci, ring, &new_ring); + xhci_link_rings(xhci, &new_ring, ring); trace_xhci_ring_expansion(ring); xhci_dbg_trace(xhci, trace_xhci_dbg_ring_expansion, "ring expansion succeed, now has %d segments", diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index e6c9006bd568..d85ffa9ffaa7 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -290,7 +290,8 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s hcd->tpl_support = of_usb_host_tpl_support(sysdev->of_node); - if (priv && (priv->quirks & XHCI_SKIP_PHY_INIT)) + if ((priv && (priv->quirks & XHCI_SKIP_PHY_INIT)) || + (xhci->quirks & XHCI_SKIP_PHY_INIT)) hcd->skip_phy_initialization = 1; if (priv && (priv->quirks & XHCI_SG_TRB_CACHE_SIZE_QUIRK)) @@ -329,6 +330,8 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s usb3_hcd->can_do_streams = 1; if (xhci->shared_hcd) { + xhci->shared_hcd->rsrc_start = hcd->rsrc_start; + xhci->shared_hcd->rsrc_len = hcd->rsrc_len; ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED); if (ret) goto put_usb3_hcd; @@ -566,6 +569,7 @@ EXPORT_SYMBOL_GPL(xhci_plat_pm_ops); static const struct acpi_device_id usb_xhci_acpi_match[] = { /* XHCI-compliant USB Controller */ { "PNP0D10", }, + { "PNP0D15", }, { } }; MODULE_DEVICE_TABLE(acpi, usb_xhci_acpi_match); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 4cf5363875c7..965bffce301e 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -55,6 +55,7 @@ #include #include #include +#include #include #include "xhci.h" #include "xhci-trace.h" @@ -422,7 +423,8 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci, if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) && !(xhci->xhc_state & XHCI_STATE_DYING)) { xhci->current_cmd = cur_cmd; - xhci_mod_cmd_timer(xhci); + if (cur_cmd) + xhci_mod_cmd_timer(xhci); xhci_ring_cmd_db(xhci); } } @@ -1199,8 +1201,6 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id, * Keep retrying until the EP starts and stops again, on * chips where this is known to help. Wait for 100ms. */ - if (!(xhci->quirks & XHCI_NEC_HOST)) - break; if (time_is_before_jiffies(ep->stop_time + msecs_to_jiffies(100))) break; fallthrough; @@ -1651,12 +1651,13 @@ static void xhci_handle_cmd_nec_get_fw(struct xhci_hcd *xhci, NEC_FW_MINOR(le32_to_cpu(event->status))); } -static void xhci_complete_del_and_free_cmd(struct xhci_command *cmd, u32 status) +static void xhci_complete_del_and_free_cmd(struct xhci_command *cmd, u32 comp_code, u32 comp_param) { list_del(&cmd->cmd_list); if (cmd->completion) { - cmd->status = status; + cmd->status = comp_code; + cmd->comp_param = comp_param; complete(cmd->completion); } else { kfree(cmd); @@ -1668,7 +1669,7 @@ void xhci_cleanup_command_queue(struct xhci_hcd *xhci) struct xhci_command *cur_cmd, *tmp_cmd; xhci->current_cmd = NULL; list_for_each_entry_safe(cur_cmd, tmp_cmd, &xhci->cmd_list, cmd_list) - xhci_complete_del_and_free_cmd(cur_cmd, COMP_COMMAND_ABORTED); + xhci_complete_del_and_free_cmd(cur_cmd, COMP_COMMAND_ABORTED, 0); } void xhci_handle_command_timeout(struct work_struct *work) @@ -1753,6 +1754,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, struct xhci_event_cmd *event) { unsigned int slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags)); + u32 status = le32_to_cpu(event->status); u64 cmd_dma; dma_addr_t cmd_dequeue_dma; u32 cmd_comp_code; @@ -1881,7 +1883,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, } event_handled: - xhci_complete_del_and_free_cmd(cmd, cmd_comp_code); + xhci_complete_del_and_free_cmd(cmd, cmd_comp_code, COMP_PARAM(status)); inc_deq(xhci, xhci->cmd_ring); } @@ -3440,8 +3442,8 @@ static void check_interval(struct urb *urb, struct xhci_ep_ctx *ep_ctx) if (xhci_interval != ep_interval) { dev_dbg_ratelimited(&urb->dev->dev, "Driver uses different interval (%d microframe%s) than xHCI (%d microframe%s)\n", - ep_interval, ep_interval == 1 ? "" : "s", - xhci_interval, xhci_interval == 1 ? "" : "s"); + ep_interval, str_plural(ep_interval), + xhci_interval, str_plural(xhci_interval)); urb->interval = xhci_interval; /* Convert back to frames for LS/FS devices */ if (urb->dev->speed == USB_SPEED_LOW || diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 06ae193ec874..22dc86fb5254 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -724,7 +725,7 @@ static void tegra_xusb_mbox_handle(struct tegra_xusb *tegra, if (err < 0) { dev_err(dev, "failed to %s LFPS detection on USB3#%u: %d\n", - enable ? "enable" : "disable", port, err); + str_enable_disable(enable), port, err); rsp.cmd = MBOX_CMD_NAK; } else { rsp.cmd = MBOX_CMD_ACK; @@ -1349,7 +1350,7 @@ static void tegra_xhci_id_work(struct work_struct *work) u32 status; int ret; - dev_dbg(tegra->dev, "host mode %s\n", tegra->host_mode ? "on" : "off"); + dev_dbg(tegra->dev, "host mode %s\n", str_on_off(tegra->host_mode)); mutex_lock(&tegra->lock); @@ -1667,7 +1668,7 @@ static int tegra_xusb_probe(struct platform_device *pdev) goto put_padctl; } - if (!of_property_read_bool(pdev->dev.of_node, "power-domains")) { + if (!of_property_present(pdev->dev.of_node, "power-domains")) { tegra->host_rst = devm_reset_control_get(&pdev->dev, "xusb_host"); if (IS_ERR(tegra->host_rst)) { diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 5ebde8cae4fc..45653114ccd7 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -4523,7 +4524,7 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd, hlpm_addr = ports[port_num]->addr + PORTHLPMC; xhci_dbg(xhci, "%s port %d USB2 hardware LPM\n", - enable ? "enable" : "disable", port_num + 1); + str_enable_disable(enable), port_num + 1); if (enable) { /* Host supports BESL timeout instead of HIRD */ diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 4914f0a10cff..8c164340a2c3 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -529,6 +529,7 @@ struct xhci_command { /* Input context for changing device state */ struct xhci_container_ctx *in_ctx; u32 status; + u32 comp_param; int slot_id; /* If completion is null, no one is waiting on this command * and the structure can be freed after the command completes. @@ -959,6 +960,9 @@ struct xhci_event_cmd { __le32 flags; }; +/* status bitmasks */ +#define COMP_PARAM(p) ((p) & 0xffffff) /* Command Completion Parameter */ + /* Address device - disable SetAddress */ #define TRB_BSR (1<<9) diff --git a/drivers/usb/image/microtek.c b/drivers/usb/image/microtek.c index 9f758241d9d3..934ec5310fb9 100644 --- a/drivers/usb/image/microtek.c +++ b/drivers/usb/image/microtek.c @@ -322,7 +322,7 @@ static inline void mts_urb_abort(struct mts_desc* desc) { usb_kill_urb( desc->urb ); } -static int mts_slave_alloc (struct scsi_device *s) +static int mts_sdev_init (struct scsi_device *s) { s->inquiry_len = 0x24; return 0; @@ -626,7 +626,7 @@ static const struct scsi_host_template mts_scsi_host_template = { .this_id = -1, .emulated = 1, .dma_alignment = 511, - .slave_alloc = mts_slave_alloc, + .sdev_init = mts_sdev_init, .max_sectors= 256, /* 128 K */ }; diff --git a/drivers/usb/mtu3/mtu3_debugfs.c b/drivers/usb/mtu3/mtu3_debugfs.c index f0de99858353..c003049bafbf 100644 --- a/drivers/usb/mtu3/mtu3_debugfs.c +++ b/drivers/usb/mtu3/mtu3_debugfs.c @@ -7,6 +7,7 @@ * Author: Chunfeng Yun */ +#include #include #include "mtu3.h" @@ -256,16 +257,7 @@ static const struct mtu3_file_map mtu3_ep_files[] = { static int mtu3_ep_open(struct inode *inode, struct file *file) { - const char *file_name = file_dentry(file)->d_iname; - const struct mtu3_file_map *f_map; - int i; - - for (i = 0; i < ARRAY_SIZE(mtu3_ep_files); i++) { - f_map = &mtu3_ep_files[i]; - - if (strcmp(f_map->name, file_name) == 0) - break; - } + const struct mtu3_file_map *f_map = debugfs_get_aux(file); return single_open(file, f_map->show, inode->i_private); } @@ -288,17 +280,8 @@ static const struct debugfs_reg32 mtu3_prb_regs[] = { static int mtu3_probe_show(struct seq_file *sf, void *unused) { - const char *file_name = file_dentry(sf->file)->d_iname; struct mtu3 *mtu = sf->private; - const struct debugfs_reg32 *regs; - int i; - - for (i = 0; i < ARRAY_SIZE(mtu3_prb_regs); i++) { - regs = &mtu3_prb_regs[i]; - - if (strcmp(regs->name, file_name) == 0) - break; - } + const struct debugfs_reg32 *regs = debugfs_get_aux(sf->file); seq_printf(sf, "0x%04x - 0x%08x\n", (u32)regs->offset, mtu3_readl(mtu->ippc_base, (u32)regs->offset)); @@ -314,13 +297,11 @@ static int mtu3_probe_open(struct inode *inode, struct file *file) static ssize_t mtu3_probe_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { - const char *file_name = file_dentry(file)->d_iname; struct seq_file *sf = file->private_data; struct mtu3 *mtu = sf->private; - const struct debugfs_reg32 *regs; + const struct debugfs_reg32 *regs = debugfs_get_aux(file); char buf[32]; u32 val; - int i; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -328,12 +309,6 @@ static ssize_t mtu3_probe_write(struct file *file, const char __user *ubuf, if (kstrtou32(buf, 0, &val)) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(mtu3_prb_regs); i++) { - regs = &mtu3_prb_regs[i]; - - if (strcmp(regs->name, file_name) == 0) - break; - } mtu3_writel(mtu->ippc_base, (u32)regs->offset, val); return count; @@ -358,8 +333,8 @@ static void mtu3_debugfs_create_prb_files(struct mtu3 *mtu) for (i = 0; i < ARRAY_SIZE(mtu3_prb_regs); i++) { regs = &mtu3_prb_regs[i]; - debugfs_create_file(regs->name, 0644, dir_prb, - mtu, &mtu3_probe_fops); + debugfs_create_file_aux(regs->name, 0644, dir_prb, + mtu, regs, &mtu3_probe_fops); } mtu3_debugfs_regset(mtu, mtu->ippc_base, mtu3_prb_regs, @@ -379,8 +354,8 @@ static void mtu3_debugfs_create_ep_dir(struct mtu3_ep *mep, for (i = 0; i < ARRAY_SIZE(mtu3_ep_files); i++) { files = &mtu3_ep_files[i]; - debugfs_create_file(files->name, 0444, dir_ep, - mep, &mtu3_ep_fops); + debugfs_create_file_aux(files->name, 0444, dir_ep, + mep, files, &mtu3_ep_fops); } } @@ -479,7 +454,7 @@ static int ssusb_vbus_show(struct seq_file *sf, void *unused) struct otg_switch_mtk *otg_sx = &ssusb->otg_switch; seq_printf(sf, "vbus state: %s\n(echo on/off)\n", - regulator_is_enabled(otg_sx->vbus) ? "on" : "off"); + str_on_off(regulator_is_enabled(otg_sx->vbus))); return 0; } diff --git a/drivers/usb/mtu3/mtu3_dr.c b/drivers/usb/mtu3/mtu3_dr.c index 8191b7ed3852..ffa5b9401dad 100644 --- a/drivers/usb/mtu3/mtu3_dr.c +++ b/drivers/usb/mtu3/mtu3_dr.c @@ -7,6 +7,7 @@ * Author: Chunfeng Yun */ +#include #include "mtu3.h" #include "mtu3_dr.h" #include "mtu3_debug.h" @@ -109,7 +110,7 @@ int ssusb_set_vbus(struct otg_switch_mtk *otg_sx, int is_on) if (!vbus) return 0; - dev_dbg(ssusb->dev, "%s: turn %s\n", __func__, is_on ? "on" : "off"); + dev_dbg(ssusb->dev, "%s: turn %s\n", __func__, str_on_off(is_on)); if (is_on) { ret = regulator_enable(vbus); diff --git a/drivers/usb/mtu3/mtu3_gadget.c b/drivers/usb/mtu3/mtu3_gadget.c index ad0eeac4332d..bf73fbc29976 100644 --- a/drivers/usb/mtu3/mtu3_gadget.c +++ b/drivers/usb/mtu3/mtu3_gadget.c @@ -7,6 +7,7 @@ * Author: Chunfeng Yun */ +#include #include "mtu3.h" #include "mtu3_trace.h" @@ -490,7 +491,7 @@ static int mtu3_gadget_pullup(struct usb_gadget *gadget, int is_on) unsigned long flags; dev_dbg(mtu->dev, "%s (%s) for %sactive device\n", __func__, - is_on ? "on" : "off", mtu->is_active ? "" : "in"); + str_on_off(is_on), mtu->is_active ? "" : "in"); pm_runtime_get_sync(mtu->dev); diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c index f772aa272bea..26fd71a5f9b2 100644 --- a/drivers/usb/musb/da8xx.c +++ b/drivers/usb/musb/da8xx.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -306,7 +307,7 @@ static irqreturn_t da8xx_musb_interrupt(int irq, void *hci) } dev_dbg(musb->controller, "VBUS %s (%s)%s, devctl %02x\n", - drvvbus ? "on" : "off", + str_on_off(drvvbus), usb_otg_state_string(musb->xceiv->otg->state), err ? " ERROR" : "", devctl); diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 03b1154a6014..7f349f5e781d 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -72,6 +72,7 @@ #include #include #include +#include #include #include #include @@ -1937,7 +1938,7 @@ vbus_show(struct device *dev, struct device_attribute *attr, char *buf) pm_runtime_put_sync(dev); return sprintf(buf, "Vbus %s, timeout %lu msec\n", - vbus ? "on" : "off", val); + str_on_off(vbus), val); } static DEVICE_ATTR_RW(vbus); diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 2542239ec64e..f877faf5a930 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -378,7 +379,7 @@ static irqreturn_t dsps_interrupt(int irq, void *hci) /* NOTE: this must complete power-on within 100 ms. */ dev_dbg(musb->controller, "VBUS %s (%s)%s, devctl %02x\n", - drvvbus ? "on" : "off", + str_on_off(drvvbus), usb_otg_state_string(musb->xceiv->otg->state), err ? " ERROR" : "", devctl); diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index c6076df0d50c..6869c58367f2 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -1606,7 +1607,7 @@ static void musb_pullup(struct musb *musb, int is_on) /* FIXME if on, HdrcStart; if off, HdrcStop */ musb_dbg(musb, "gadget D+ pullup %s", - is_on ? "on" : "off"); + str_on_off(is_on)); musb_writeb(musb->mregs, MUSB_POWER, power); } diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 732ba981e607..6b4481a867c5 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -1028,7 +1029,7 @@ static bool musb_h_ep0_continue(struct musb *musb, u16 len, struct urb *urb) + urb->actual_length); musb_dbg(musb, "Sending %d byte%s to ep0 fifo %p", fifo_count, - (fifo_count == 1) ? "" : "s", + str_plural(fifo_count), fifo_dest); musb_write_fifo(hw_ep, fifo_count, fifo_dest); diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c index 42c42e193232..40ac68e52cee 100644 --- a/drivers/usb/phy/phy-fsl-usb.c +++ b/drivers/usb/phy/phy-fsl-usb.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -529,7 +530,7 @@ int fsl_otg_start_gadget(struct otg_fsm *fsm, int on) if (!otg->gadget || !otg->gadget->dev.parent) return -ENODEV; - VDBG("gadget %s\n", on ? "on" : "off"); + VDBG("gadget %s\n", str_on_off(on)); dev = otg->gadget->dev.parent; if (on) { diff --git a/drivers/usb/phy/phy-mv-usb.c b/drivers/usb/phy/phy-mv-usb.c index a7a102f2e163..30d6c8840a5e 100644 --- a/drivers/usb/phy/phy-mv-usb.c +++ b/drivers/usb/phy/phy-mv-usb.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -217,7 +218,7 @@ static void mv_otg_start_periphrals(struct mv_otg *mvotg, int on) if (!otg->gadget) return; - dev_info(mvotg->phy.dev, "gadget %s\n", on ? "on" : "off"); + dev_info(mvotg->phy.dev, "gadget %s\n", str_on_off(on)); if (on) usb_gadget_vbus_connect(otg->gadget); diff --git a/drivers/usb/phy/phy-tahvo.c b/drivers/usb/phy/phy-tahvo.c index ae7bf3ff89ee..88607d0edb01 100644 --- a/drivers/usb/phy/phy-tahvo.c +++ b/drivers/usb/phy/phy-tahvo.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -63,7 +64,7 @@ static ssize_t vbus_show(struct device *device, struct device_attribute *attr, char *buf) { struct tahvo_usb *tu = dev_get_drvdata(device); - return sprintf(buf, "%s\n", tu->vbus_state ? "on" : "off"); + return sprintf(buf, "%s\n", str_on_off(tu->vbus_state)); } static DEVICE_ATTR_RO(vbus); diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index 1ce134505cee..e1435bc59662 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -346,13 +346,6 @@ static void devm_usb_phy_release2(struct device *dev, void *_res) usb_put_phy(res->phy); } -static int devm_usb_phy_match(struct device *dev, void *res, void *match_data) -{ - struct usb_phy **phy = res; - - return *phy == match_data; -} - static void usb_charger_init(struct usb_phy *usb_phy) { usb_phy->chg_type = UNKNOWN_TYPE; @@ -614,25 +607,6 @@ struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, } EXPORT_SYMBOL_GPL(devm_usb_get_phy_by_phandle); -/** - * devm_usb_put_phy - release the USB PHY - * @dev: device that wants to release this phy - * @phy: the phy returned by devm_usb_get_phy() - * - * destroys the devres associated with this phy and invokes usb_put_phy - * to release the phy. - * - * For use by USB host and peripheral drivers. - */ -void devm_usb_put_phy(struct device *dev, struct usb_phy *phy) -{ - int r; - - r = devres_release(dev, devm_usb_phy_release, devm_usb_phy_match, phy); - dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); -} -EXPORT_SYMBOL_GPL(devm_usb_put_phy); - /** * usb_put_phy - release the USB PHY * @x: the phy returned by usb_get_phy() diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index d10e4c4848a0..7cc36f84821f 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -63,6 +63,7 @@ #define CH341_REG_DIVISOR 0x13 #define CH341_REG_LCR 0x18 #define CH341_REG_LCR2 0x25 +#define CH341_REG_FLOW_CTL 0x27 #define CH341_NBREAK_BITS 0x01 @@ -77,6 +78,9 @@ #define CH341_LCR_CS6 0x01 #define CH341_LCR_CS5 0x00 +#define CH341_FLOW_CTL_NONE 0x00 +#define CH341_FLOW_CTL_RTSCTS 0x01 + #define CH341_QUIRK_LIMITED_PRESCALER BIT(0) #define CH341_QUIRK_SIMULATE_BREAK BIT(1) @@ -478,6 +482,28 @@ err_kill_interrupt_urb: return r; } +static void ch341_set_flow_control(struct tty_struct *tty, + struct usb_serial_port *port, + const struct ktermios *old_termios) +{ + u16 flow_ctl; + int r; + + if (C_CRTSCTS(tty)) + flow_ctl = CH341_FLOW_CTL_RTSCTS; + else + flow_ctl = CH341_FLOW_CTL_NONE; + + r = ch341_control_out(port->serial->dev, + CH341_REQ_WRITE_REG, + (CH341_REG_FLOW_CTL << 8) | CH341_REG_FLOW_CTL, + (flow_ctl << 8) | flow_ctl); + if (r < 0 && old_termios) { + tty->termios.c_cflag &= ~CRTSCTS; + tty->termios.c_cflag |= (old_termios->c_cflag & CRTSCTS); + } +} + /* Old_termios contains the original termios settings and * tty->termios contains the new setting to be used. */ @@ -546,6 +572,8 @@ static void ch341_set_termios(struct tty_struct *tty, spin_unlock_irqrestore(&priv->lock, flags); ch341_set_handshake(port->serial->dev, priv->mcr); + + ch341_set_flow_control(tty, port, old_termios); } /* @@ -632,13 +660,12 @@ restore: static int ch341_break_ctl(struct tty_struct *tty, int break_state) { - const uint16_t ch341_break_reg = - ((uint16_t) CH341_REG_LCR << 8) | CH341_REG_BREAK; + const u16 ch341_break_reg = (CH341_REG_LCR << 8) | CH341_REG_BREAK; struct usb_serial_port *port = tty->driver_data; struct ch341_private *priv = usb_get_serial_port_data(port); + u16 reg_contents; + u8 break_reg[2]; int r; - uint16_t reg_contents; - uint8_t break_reg[2]; if (priv->quirks & CH341_QUIRK_SIMULATE_BREAK) return ch341_simulate_break(tty, break_state); diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index c24101f0a07a..9960ac2b10b7 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -223,6 +223,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ + { USB_DEVICE(0x1B93, 0x1013) }, /* Phoenix Contact UPS Device */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ { USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */ { USB_DEVICE(0x1D6F, 0x0010) }, /* Seluxit ApS RF Dongle */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 9ba5584061c8..1e2ae0c6c41c 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -621,10 +621,12 @@ static void option_instat_callback(struct urb *urb); /* MeiG Smart Technology products */ #define MEIGSMART_VENDOR_ID 0x2dee -/* MeiG Smart SRM825L based on Qualcomm 315 */ +/* MeiG Smart SRM815/SRM825L based on Qualcomm 315 */ #define MEIGSMART_PRODUCT_SRM825L 0x4d22 /* MeiG Smart SLM320 based on UNISOC UIS8910 */ #define MEIGSMART_PRODUCT_SLM320 0x4d41 +/* MeiG Smart SLM770A based on ASR1803 */ +#define MEIGSMART_PRODUCT_SLM770A 0x4d57 /* Device flags */ @@ -1395,6 +1397,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10aa, 0xff), /* Telit FN920C04 (MBIM) */ .driver_info = NCTRL(3) | RSVD(4) | RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c0, 0xff), /* Telit FE910C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c4, 0xff), /* Telit FE910C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c8, 0xff), /* Telit FE910C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -2247,6 +2255,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) }, { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x7127, 0xff, 0x00, 0x00), .driver_info = NCTRL(2) | NCTRL(3) | NCTRL(4) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x7129, 0xff, 0x00, 0x00), /* MediaTek T7XX */ + .driver_info = NCTRL(2) | NCTRL(3) | NCTRL(4) }, { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) }, { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MPL200), .driver_info = RSVD(1) | RSVD(4) }, @@ -2375,6 +2385,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for Golbal EDU */ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WRD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WRD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) }, @@ -2382,9 +2404,16 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM770A, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x60) }, + { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff), /* TCL IK512 MBIM */ + .driver_info = NCTRL(1) }, + { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0640, 0xff), /* TCL IK512 ECM */ + .driver_info = NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(0x2949, 0x8700, 0xff) }, /* Neoway N723-EA */ { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c index a317bdbd00ad..72fe83a6c978 100644 --- a/drivers/usb/serial/quatech2.c +++ b/drivers/usb/serial/quatech2.c @@ -503,7 +503,7 @@ static void qt2_process_read_urb(struct urb *urb) newport = *(ch + 3); - if (newport > serial->num_ports) { + if (newport >= serial->num_ports) { dev_err(&port->dev, "%s - port change to invalid port: %i\n", __func__, newport); diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig index d17b60a644ef..4be1d617d63d 100644 --- a/drivers/usb/storage/Kconfig +++ b/drivers/usb/storage/Kconfig @@ -3,8 +3,7 @@ # USB Storage driver configuration # -comment "NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may" -comment "also be needed; see USB_STORAGE Help for more info" +comment "NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed; see USB_STORAGE Help for more info" config USB_STORAGE tristate "USB Mass Storage support" diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 8c8b5e6041cc..d2f476e48d0c 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -64,7 +64,7 @@ static const char* host_info(struct Scsi_Host *host) return us->scsi_name; } -static int slave_alloc (struct scsi_device *sdev) +static int sdev_init (struct scsi_device *sdev) { struct us_data *us = host_to_us(sdev->host); @@ -88,7 +88,7 @@ static int slave_alloc (struct scsi_device *sdev) return 0; } -static int device_configure(struct scsi_device *sdev, struct queue_limits *lim) +static int sdev_configure(struct scsi_device *sdev, struct queue_limits *lim) { struct us_data *us = host_to_us(sdev->host); struct device *dev = us->pusb_dev->bus->sysdev; @@ -127,7 +127,7 @@ static int device_configure(struct scsi_device *sdev, struct queue_limits *lim) lim->max_hw_sectors, dma_max_mapping_size(dev) >> SECTOR_SHIFT); /* - * We can't put these settings in slave_alloc() because that gets + * We can't put these settings in sdev_init() because that gets * called before the device type is known. Consequently these * settings can't be overridden via the scsi devinfo mechanism. */ @@ -592,12 +592,9 @@ static ssize_t max_sectors_store(struct device *dev, struct device_attribute *at if (sscanf(buf, "%hu", &ms) <= 0) return -EINVAL; - blk_mq_freeze_queue(sdev->request_queue); lim = queue_limits_start_update(sdev->request_queue); lim.max_hw_sectors = ms; - ret = queue_limits_commit_update(sdev->request_queue, &lim); - blk_mq_unfreeze_queue(sdev->request_queue); - + ret = queue_limits_commit_update_frozen(sdev->request_queue, &lim); if (ret) return ret; return count; @@ -637,8 +634,8 @@ static const struct scsi_host_template usb_stor_host_template = { /* unknown initiator id */ .this_id = -1, - .slave_alloc = slave_alloc, - .device_configure = device_configure, + .sdev_init = sdev_init, + .sdev_configure = sdev_configure, .target_alloc = target_alloc, /* lots of sg segments can be handled */ diff --git a/drivers/usb/storage/shuttle_usbat.c b/drivers/usb/storage/shuttle_usbat.c index 087c706bb315..c33cbf177e6f 100644 --- a/drivers/usb/storage/shuttle_usbat.c +++ b/drivers/usb/storage/shuttle_usbat.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -651,8 +652,7 @@ static int usbat_hp8200e_rw_block_test(struct us_data *us, return USB_STOR_TRANSPORT_FAILED; usb_stor_dbg(us, "Redoing %s\n", - direction == DMA_TO_DEVICE - ? "write" : "read"); + str_write_read(direction == DMA_TO_DEVICE)); } else if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 9d767f6bf722..e6bc8ecaecbb 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -1087,13 +1087,9 @@ int usb_stor_Bulk_max_lun(struct us_data *us) usb_stor_dbg(us, "GetMaxLUN command result is %d, data is %d\n", result, us->iobuf[0]); - /* - * If we have a successful request, return the result if valid. The - * CBW LUN field is 4 bits wide, so the value reported by the device - * should fit into that. - */ + /* If we have a successful request, return the result if valid. */ if (result > 0) { - if (us->iobuf[0] < 16) { + if (us->iobuf[0] <= US_BULK_MAX_LUN_LIMIT) { return us->iobuf[0]; } else { dev_info(&us->pusb_intf->dev, diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index f9ad90ce7af4..4ed0dc19afe0 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -817,7 +817,7 @@ static int uas_target_alloc(struct scsi_target *starget) return 0; } -static int uas_slave_alloc(struct scsi_device *sdev) +static int uas_sdev_init(struct scsi_device *sdev) { struct uas_dev_info *devinfo = (struct uas_dev_info *)sdev->host->hostdata; @@ -832,8 +832,8 @@ static int uas_slave_alloc(struct scsi_device *sdev) return 0; } -static int uas_device_configure(struct scsi_device *sdev, - struct queue_limits *lim) +static int uas_sdev_configure(struct scsi_device *sdev, + struct queue_limits *lim) { struct uas_dev_info *devinfo = sdev->hostdata; @@ -905,8 +905,8 @@ static const struct scsi_host_template uas_host_template = { .name = "uas", .queuecommand = uas_queuecommand, .target_alloc = uas_target_alloc, - .slave_alloc = uas_slave_alloc, - .device_configure = uas_device_configure, + .sdev_init = uas_sdev_init, + .sdev_configure = uas_sdev_configure, .eh_abort_handler = uas_eh_abort_handler, .eh_device_reset_handler = uas_eh_device_reset_handler, .this_id = -1, diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index e5ad23d86833..54f0b1c83317 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -255,6 +255,13 @@ UNUSUAL_DEV( 0x0421, 0x06aa, 0x1110, 0x1110, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_MAX_SECTORS_64 ), +/* Added by Lubomir Rintel , a very fine chap */ +UNUSUAL_DEV( 0x0421, 0x06c2, 0x0000, 0x0406, + "Nokia", + "Nokia 208", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_MAX_SECTORS_64 ), + #ifdef NO_SDDR09 UNUSUAL_DEV( 0x0436, 0x0005, 0x0100, 0x0100, "Microtech", diff --git a/drivers/usb/typec/altmodes/Kconfig b/drivers/usb/typec/altmodes/Kconfig index 1a6b5e872b0d..7867fa7c405d 100644 --- a/drivers/usb/typec/altmodes/Kconfig +++ b/drivers/usb/typec/altmodes/Kconfig @@ -23,4 +23,13 @@ config TYPEC_NVIDIA_ALTMODE To compile this driver as a module, choose M here: the module will be called typec_nvidia. +config TYPEC_TBT_ALTMODE + tristate "Thunderbolt3 Alternate Mode driver" + help + Select this option if you have Thunderbolt3 hardware on your + system. + + To compile this driver as a module, choose M here: the + module will be called typec_thunderbolt. + endmenu diff --git a/drivers/usb/typec/altmodes/Makefile b/drivers/usb/typec/altmodes/Makefile index 45717548b396..508a68351bd2 100644 --- a/drivers/usb/typec/altmodes/Makefile +++ b/drivers/usb/typec/altmodes/Makefile @@ -4,3 +4,5 @@ obj-$(CONFIG_TYPEC_DP_ALTMODE) += typec_displayport.o typec_displayport-y := displayport.o obj-$(CONFIG_TYPEC_NVIDIA_ALTMODE) += typec_nvidia.o typec_nvidia-y := nvidia.o +obj-$(CONFIG_TYPEC_TBT_ALTMODE) += typec_thunderbolt.o +typec_thunderbolt-y := thunderbolt.o diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 2f03190a9873..ac84a6d64c2f 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -252,7 +252,7 @@ static void dp_altmode_work(struct work_struct *work) case DP_STATE_ENTER: ret = typec_altmode_enter(dp->alt, NULL); if (ret && ret != -EBUSY) - dev_err(&dp->alt->dev, "failed to enter mode\n"); + dev_err(&dp->alt->dev, "failed to enter mode: %d\n", ret); break; case DP_STATE_ENTER_PRIME: ret = typec_cable_altmode_enter(dp->alt, TYPEC_PLUG_SOP_P, NULL); @@ -791,7 +791,7 @@ void dp_altmode_remove(struct typec_altmode *alt) EXPORT_SYMBOL_GPL(dp_altmode_remove); static const struct typec_device_id dp_typec_id[] = { - { USB_TYPEC_DP_SID, USB_TYPEC_DP_MODE }, + { USB_TYPEC_DP_SID }, { }, }; MODULE_DEVICE_TABLE(typec, dp_typec_id); diff --git a/drivers/usb/typec/altmodes/nvidia.c b/drivers/usb/typec/altmodes/nvidia.c index fe70b36f078f..2b77d931e494 100644 --- a/drivers/usb/typec/altmodes/nvidia.c +++ b/drivers/usb/typec/altmodes/nvidia.c @@ -24,7 +24,7 @@ static void nvidia_altmode_remove(struct typec_altmode *alt) } static const struct typec_device_id nvidia_typec_id[] = { - { USB_TYPEC_NVIDIA_VLINK_SID, TYPEC_ANY_MODE }, + { USB_TYPEC_NVIDIA_VLINK_SID }, { }, }; MODULE_DEVICE_TABLE(typec, nvidia_typec_id); diff --git a/drivers/usb/typec/altmodes/thunderbolt.c b/drivers/usb/typec/altmodes/thunderbolt.c new file mode 100644 index 000000000000..1b475b1d98e7 --- /dev/null +++ b/drivers/usb/typec/altmodes/thunderbolt.c @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * USB Typec-C Thunderbolt3 Alternate Mode driver + * + * Copyright (C) 2019 Intel Corporation + * Author: Heikki Krogerus + */ + +#include +#include +#include +#include +#include +#include +#include + +enum tbt_state { + TBT_STATE_IDLE, + TBT_STATE_SOP_P_ENTER, + TBT_STATE_SOP_PP_ENTER, + TBT_STATE_ENTER, + TBT_STATE_EXIT, + TBT_STATE_SOP_PP_EXIT, + TBT_STATE_SOP_P_EXIT +}; + +struct tbt_altmode { + enum tbt_state state; + struct typec_cable *cable; + struct typec_altmode *alt; + struct typec_altmode *plug[2]; + u32 enter_vdo; + + struct work_struct work; + struct mutex lock; /* device lock */ +}; + +static bool tbt_ready(struct typec_altmode *alt); + +static int tbt_enter_mode(struct tbt_altmode *tbt) +{ + struct typec_altmode *plug = tbt->plug[TYPEC_PLUG_SOP_P]; + u32 vdo; + + vdo = tbt->alt->vdo & (TBT_VENDOR_SPECIFIC_B0 | TBT_VENDOR_SPECIFIC_B1); + vdo |= tbt->alt->vdo & TBT_INTEL_SPECIFIC_B0; + vdo |= TBT_MODE; + + if (plug) { + if (typec_cable_is_active(tbt->cable)) + vdo |= TBT_ENTER_MODE_ACTIVE_CABLE; + + vdo |= TBT_ENTER_MODE_CABLE_SPEED(TBT_CABLE_SPEED(plug->vdo)); + vdo |= plug->vdo & TBT_CABLE_ROUNDED; + vdo |= plug->vdo & TBT_CABLE_OPTICAL; + vdo |= plug->vdo & TBT_CABLE_RETIMER; + vdo |= plug->vdo & TBT_CABLE_LINK_TRAINING; + } else { + vdo |= TBT_ENTER_MODE_CABLE_SPEED(TBT_CABLE_USB3_PASSIVE); + } + + tbt->enter_vdo = vdo; + return typec_altmode_enter(tbt->alt, &vdo); +} + +static void tbt_altmode_work(struct work_struct *work) +{ + struct tbt_altmode *tbt = container_of(work, struct tbt_altmode, work); + int ret; + + mutex_lock(&tbt->lock); + + switch (tbt->state) { + case TBT_STATE_SOP_P_ENTER: + ret = typec_cable_altmode_enter(tbt->alt, TYPEC_PLUG_SOP_P, NULL); + if (ret) { + dev_dbg(&tbt->plug[TYPEC_PLUG_SOP_P]->dev, + "failed to enter mode (%d)\n", ret); + goto disable_plugs; + } + break; + case TBT_STATE_SOP_PP_ENTER: + ret = typec_cable_altmode_enter(tbt->alt, TYPEC_PLUG_SOP_PP, NULL); + if (ret) { + dev_dbg(&tbt->plug[TYPEC_PLUG_SOP_PP]->dev, + "failed to enter mode (%d)\n", ret); + goto disable_plugs; + } + break; + case TBT_STATE_ENTER: + ret = tbt_enter_mode(tbt); + if (ret) + dev_dbg(&tbt->alt->dev, "failed to enter mode (%d)\n", + ret); + break; + case TBT_STATE_EXIT: + typec_altmode_exit(tbt->alt); + break; + case TBT_STATE_SOP_PP_EXIT: + typec_cable_altmode_exit(tbt->alt, TYPEC_PLUG_SOP_PP); + break; + case TBT_STATE_SOP_P_EXIT: + typec_cable_altmode_exit(tbt->alt, TYPEC_PLUG_SOP_P); + break; + default: + break; + } + + tbt->state = TBT_STATE_IDLE; + + mutex_unlock(&tbt->lock); + return; + +disable_plugs: + for (int i = TYPEC_PLUG_SOP_PP; i > 0; --i) { + if (tbt->plug[i]) + typec_altmode_put_plug(tbt->plug[i]); + + tbt->plug[i] = NULL; + } + + tbt->state = TBT_STATE_ENTER; + schedule_work(&tbt->work); + mutex_unlock(&tbt->lock); +} + +/* + * If SOP' is available, enter that first (which will trigger a VDM response + * that will enter SOP" if available and then the port). If entering SOP' fails, + * stop attempting to enter either cable altmode (probably not supported) and + * directly enter the port altmode. + */ +static int tbt_enter_modes_ordered(struct typec_altmode *alt) +{ + struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt); + int ret = 0; + + lockdep_assert_held(&tbt->lock); + + if (!tbt_ready(tbt->alt)) + return -ENODEV; + + if (tbt->plug[TYPEC_PLUG_SOP_P]) { + ret = typec_cable_altmode_enter(alt, TYPEC_PLUG_SOP_P, NULL); + if (ret < 0) { + for (int i = TYPEC_PLUG_SOP_PP; i > 0; --i) { + if (tbt->plug[i]) + typec_altmode_put_plug(tbt->plug[i]); + + tbt->plug[i] = NULL; + } + } else { + return ret; + } + } + + return tbt_enter_mode(tbt); +} + +static int tbt_cable_altmode_vdm(struct typec_altmode *alt, + enum typec_plug_index sop, const u32 hdr, + const u32 *vdo, int count) +{ + struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt); + int cmd_type = PD_VDO_CMDT(hdr); + int cmd = PD_VDO_CMD(hdr); + + mutex_lock(&tbt->lock); + + if (tbt->state != TBT_STATE_IDLE) { + mutex_unlock(&tbt->lock); + return -EBUSY; + } + + switch (cmd_type) { + case CMDT_RSP_ACK: + switch (cmd) { + case CMD_ENTER_MODE: + /* + * Following the order described in USB Type-C Spec + * R2.0 Section 6.7.3: SOP', SOP", then port. + */ + if (sop == TYPEC_PLUG_SOP_P) { + if (tbt->plug[TYPEC_PLUG_SOP_PP]) + tbt->state = TBT_STATE_SOP_PP_ENTER; + else + tbt->state = TBT_STATE_ENTER; + } else if (sop == TYPEC_PLUG_SOP_PP) + tbt->state = TBT_STATE_ENTER; + + break; + case CMD_EXIT_MODE: + /* Exit in opposite order: Port, SOP", then SOP'. */ + if (sop == TYPEC_PLUG_SOP_PP) + tbt->state = TBT_STATE_SOP_P_EXIT; + break; + } + break; + default: + break; + } + + if (tbt->state != TBT_STATE_IDLE) + schedule_work(&tbt->work); + + mutex_unlock(&tbt->lock); + return 0; +} + +static int tbt_altmode_vdm(struct typec_altmode *alt, + const u32 hdr, const u32 *vdo, int count) +{ + struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt); + struct typec_thunderbolt_data data; + int cmd_type = PD_VDO_CMDT(hdr); + int cmd = PD_VDO_CMD(hdr); + + mutex_lock(&tbt->lock); + + if (tbt->state != TBT_STATE_IDLE) { + mutex_unlock(&tbt->lock); + return -EBUSY; + } + + switch (cmd_type) { + case CMDT_RSP_ACK: + /* Port altmode is last to enter and first to exit. */ + switch (cmd) { + case CMD_ENTER_MODE: + memset(&data, 0, sizeof(data)); + + data.device_mode = tbt->alt->vdo; + data.enter_vdo = tbt->enter_vdo; + if (tbt->plug[TYPEC_PLUG_SOP_P]) + data.cable_mode = tbt->plug[TYPEC_PLUG_SOP_P]->vdo; + + typec_altmode_notify(alt, TYPEC_STATE_MODAL, &data); + break; + case CMD_EXIT_MODE: + if (tbt->plug[TYPEC_PLUG_SOP_PP]) + tbt->state = TBT_STATE_SOP_PP_EXIT; + else if (tbt->plug[TYPEC_PLUG_SOP_P]) + tbt->state = TBT_STATE_SOP_P_EXIT; + break; + } + break; + case CMDT_RSP_NAK: + switch (cmd) { + case CMD_ENTER_MODE: + dev_warn(&alt->dev, "Enter Mode refused\n"); + break; + default: + break; + } + break; + default: + break; + } + + if (tbt->state != TBT_STATE_IDLE) + schedule_work(&tbt->work); + + mutex_unlock(&tbt->lock); + + return 0; +} + +static int tbt_altmode_activate(struct typec_altmode *alt, int activate) +{ + struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt); + int ret; + + mutex_lock(&tbt->lock); + + if (activate) + ret = tbt_enter_modes_ordered(alt); + else + ret = typec_altmode_exit(alt); + + mutex_unlock(&tbt->lock); + + return ret; +} + +static const struct typec_altmode_ops tbt_altmode_ops = { + .vdm = tbt_altmode_vdm, + .activate = tbt_altmode_activate +}; + +static const struct typec_cable_ops tbt_cable_ops = { + .vdm = tbt_cable_altmode_vdm, +}; + +static int tbt_altmode_probe(struct typec_altmode *alt) +{ + struct tbt_altmode *tbt; + + tbt = devm_kzalloc(&alt->dev, sizeof(*tbt), GFP_KERNEL); + if (!tbt) + return -ENOMEM; + + INIT_WORK(&tbt->work, tbt_altmode_work); + mutex_init(&tbt->lock); + tbt->alt = alt; + + alt->desc = "Thunderbolt3"; + typec_altmode_set_drvdata(alt, tbt); + typec_altmode_set_ops(alt, &tbt_altmode_ops); + + if (tbt_ready(alt)) { + if (tbt->plug[TYPEC_PLUG_SOP_P]) + tbt->state = TBT_STATE_SOP_P_ENTER; + else if (tbt->plug[TYPEC_PLUG_SOP_PP]) + tbt->state = TBT_STATE_SOP_PP_ENTER; + else + tbt->state = TBT_STATE_ENTER; + schedule_work(&tbt->work); + } + + return 0; +} + +static void tbt_altmode_remove(struct typec_altmode *alt) +{ + struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt); + + for (int i = TYPEC_PLUG_SOP_PP; i > 0; --i) { + if (tbt->plug[i]) + typec_altmode_put_plug(tbt->plug[i]); + } + + if (tbt->cable) + typec_cable_put(tbt->cable); +} + +static bool tbt_ready(struct typec_altmode *alt) +{ + struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt); + struct typec_altmode *plug; + + if (tbt->cable) + return true; + + /* Thunderbolt 3 requires a cable with eMarker */ + tbt->cable = typec_cable_get(typec_altmode2port(tbt->alt)); + if (!tbt->cable) + return false; + + /* We accept systems without SOP' or SOP''. This means the port altmode + * driver will be responsible for properly ordering entry/exit. + */ + for (int i = 0; i < TYPEC_PLUG_SOP_PP + 1; i++) { + plug = typec_altmode_get_plug(tbt->alt, i); + if (IS_ERR(plug)) + continue; + + if (!plug || plug->svid != USB_TYPEC_TBT_SID) + break; + + plug->desc = "Thunderbolt3"; + plug->cable_ops = &tbt_cable_ops; + typec_altmode_set_drvdata(plug, tbt); + + tbt->plug[i] = plug; + } + + return true; +} + +static const struct typec_device_id tbt_typec_id[] = { + { USB_TYPEC_TBT_SID }, + { } +}; +MODULE_DEVICE_TABLE(typec, tbt_typec_id); + +static struct typec_altmode_driver tbt_altmode_driver = { + .id_table = tbt_typec_id, + .probe = tbt_altmode_probe, + .remove = tbt_altmode_remove, + .driver = { + .name = "typec-thunderbolt", + } +}; +module_typec_altmode_driver(tbt_altmode_driver); + +MODULE_AUTHOR("Heikki Krogerus "); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Thunderbolt3 USB Type-C Alternate Mode"); diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index aa879253d3b8..ae90688d23e4 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -454,8 +454,7 @@ static int typec_match(struct device *dev, const struct device_driver *driver) const struct typec_device_id *id; for (id = drv->id_table; id->svid; id++) - if (id->svid == altmode->svid && - (id->mode == TYPEC_ANY_MODE || id->mode == altmode->mode)) + if (id->svid == altmode->svid) return 1; return 0; } @@ -470,8 +469,7 @@ static int typec_uevent(const struct device *dev, struct kobj_uevent_env *env) if (add_uevent_var(env, "MODE=%u", altmode->mode)) return -ENOMEM; - return add_uevent_var(env, "MODALIAS=typec:id%04Xm%02X", - altmode->svid, altmode->mode); + return add_uevent_var(env, "MODALIAS=typec:id%04X", altmode->svid); } static int typec_altmode_create_links(struct altmode *alt) diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 4b3047e055a3..9c76c3d0c6cf 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -229,21 +230,21 @@ static const char * const usb_modes[] = { /* ------------------------------------------------------------------------- */ /* Alternate Modes */ -static int altmode_match(struct device *dev, void *data) +static int altmode_match(struct device *dev, const void *data) { struct typec_altmode *adev = to_typec_altmode(dev); - struct typec_device_id *id = data; + const struct typec_device_id *id = data; if (!is_typec_altmode(dev)) return 0; - return ((adev->svid == id->svid) && (adev->mode == id->mode)); + return (adev->svid == id->svid); } static void typec_altmode_set_partner(struct altmode *altmode) { struct typec_altmode *adev = &altmode->adev; - struct typec_device_id id = { adev->svid, adev->mode, }; + struct typec_device_id id = { adev->svid }; struct typec_port *port = typec_altmode2port(adev); struct altmode *partner; struct device *dev; @@ -361,7 +362,7 @@ active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct typec_altmode *alt = to_typec_altmode(dev); - return sprintf(buf, "%s\n", alt->active ? "yes" : "no"); + return sprintf(buf, "%s\n", str_yes_no(alt->active)); } static ssize_t active_store(struct device *dev, struct device_attribute *attr, @@ -458,7 +459,8 @@ static umode_t typec_altmode_attr_is_visible(struct kobject *kobj, struct typec_altmode *adev = to_typec_altmode(kobj_to_dev(kobj)); if (attr == &dev_attr_active.attr) - if (!adev->ops || !adev->ops->activate) + if (!is_typec_port(adev->dev.parent) && + (!adev->ops || !adev->ops->activate)) return 0444; return attr->mode; @@ -563,7 +565,7 @@ typec_register_altmode(struct device *parent, if (is_port) { alt->attrs[3] = &dev_attr_supported_roles.attr; - alt->adev.active = true; /* Enabled by default */ + alt->adev.active = !desc->inactive; /* Enabled by default */ } sprintf(alt->group_name, "mode%d", desc->mode); @@ -706,7 +708,7 @@ static ssize_t supports_usb_power_delivery_show(struct device *dev, { struct typec_partner *p = to_typec_partner(dev); - return sprintf(buf, "%s\n", p->usb_pd ? "yes" : "no"); + return sprintf(buf, "%s\n", str_yes_no(p->usb_pd)); } static DEVICE_ATTR_RO(supports_usb_power_delivery); @@ -1282,11 +1284,6 @@ const struct device_type typec_cable_dev_type = { .release = typec_cable_release, }; -static int cable_match(struct device *dev, void *data) -{ - return is_typec_cable(dev); -} - /** * typec_cable_get - Get a reference to the USB Type-C cable * @port: The USB Type-C Port the cable is connected to @@ -1298,7 +1295,8 @@ struct typec_cable *typec_cable_get(struct typec_port *port) { struct device *dev; - dev = device_find_child(&port->dev, NULL, cable_match); + dev = device_find_child(&port->dev, &typec_cable_dev_type, + device_match_type); if (!dev) return NULL; @@ -1858,7 +1856,7 @@ static ssize_t vconn_source_show(struct device *dev, struct typec_port *port = to_typec_port(dev); return sprintf(buf, "%s\n", - port->vconn_role == TYPEC_SOURCE ? "yes" : "no"); + str_yes_no(port->vconn_role == TYPEC_SOURCE)); } static DEVICE_ATTR_RW(vconn_source); @@ -2028,16 +2026,12 @@ const struct device_type typec_port_dev_type = { /* --------------------------------------- */ /* Driver callbacks to report role updates */ -static int partner_match(struct device *dev, void *data) -{ - return is_typec_partner(dev); -} - static struct typec_partner *typec_get_partner(struct typec_port *port) { struct device *dev; - dev = device_find_child(&port->dev, NULL, partner_match); + dev = device_find_child(&port->dev, &typec_partner_dev_type, + device_match_type); if (!dev) return NULL; @@ -2170,7 +2164,9 @@ void typec_set_pwr_opmode(struct typec_port *port, sysfs_notify(&port->dev.kobj, NULL, "power_operation_mode"); kobject_uevent(&port->dev.kobj, KOBJ_CHANGE); - partner_dev = device_find_child(&port->dev, NULL, partner_match); + partner_dev = device_find_child(&port->dev, + &typec_partner_dev_type, + device_match_type); if (partner_dev) { struct typec_partner *partner = to_typec_partner(partner_dev); @@ -2334,7 +2330,9 @@ int typec_get_negotiated_svdm_version(struct typec_port *port) enum usb_pd_svdm_ver svdm_version; struct device *partner_dev; - partner_dev = device_find_child(&port->dev, NULL, partner_match); + partner_dev = device_find_child(&port->dev, + &typec_partner_dev_type, + device_match_type); if (!partner_dev) return -ENODEV; @@ -2361,7 +2359,8 @@ int typec_get_cable_svdm_version(struct typec_port *port) enum usb_pd_svdm_ver svdm_version; struct device *cable_dev; - cable_dev = device_find_child(&port->dev, NULL, cable_match); + cable_dev = device_find_child(&port->dev, &typec_cable_dev_type, + device_match_type); if (!cable_dev) return -ENODEV; diff --git a/drivers/usb/typec/hd3ss3220.c b/drivers/usb/typec/hd3ss3220.c index fb1242e82ffd..3ecc688dda82 100644 --- a/drivers/usb/typec/hd3ss3220.c +++ b/drivers/usb/typec/hd3ss3220.c @@ -16,10 +16,17 @@ #include #include +#define HD3SS3220_REG_CN_STAT 0x08 #define HD3SS3220_REG_CN_STAT_CTRL 0x09 #define HD3SS3220_REG_GEN_CTRL 0x0A #define HD3SS3220_REG_DEV_REV 0xA0 +/* Register HD3SS3220_REG_CN_STAT */ +#define HD3SS3220_REG_CN_STAT_CURRENT_MODE_MASK (BIT(7) | BIT(6)) +#define HD3SS3220_REG_CN_STAT_CURRENT_MODE_DEFAULT 0x00 +#define HD3SS3220_REG_CN_STAT_CURRENT_MODE_MID BIT(6) +#define HD3SS3220_REG_CN_STAT_CURRENT_MODE_HIGH BIT(7) + /* Register HD3SS3220_REG_CN_STAT_CTRL*/ #define HD3SS3220_REG_CN_STAT_CTRL_ATTACHED_STATE_MASK (BIT(7) | BIT(6)) #define HD3SS3220_REG_CN_STAT_CTRL_AS_DFP BIT(6) @@ -28,10 +35,16 @@ #define HD3SS3220_REG_CN_STAT_CTRL_INT_STATUS BIT(4) /* Register HD3SS3220_REG_GEN_CTRL*/ +#define HD3SS3220_REG_GEN_CTRL_DISABLE_TERM BIT(0) #define HD3SS3220_REG_GEN_CTRL_SRC_PREF_MASK (BIT(2) | BIT(1)) #define HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_DEFAULT 0x00 #define HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SNK BIT(1) #define HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SRC (BIT(2) | BIT(1)) +#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_MASK (BIT(5) | BIT(4)) +#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DEFAULT 0x00 +#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DFP BIT(5) +#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_UFP BIT(4) +#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DRP (BIT(5) | BIT(4)) struct hd3ss3220 { struct device *dev; @@ -43,8 +56,96 @@ struct hd3ss3220 { bool poll; }; -static int hd3ss3220_set_source_pref(struct hd3ss3220 *hd3ss3220, int src_pref) +static int hd3ss3220_set_power_opmode(struct hd3ss3220 *hd3ss3220, int power_opmode) { + int current_mode; + + switch (power_opmode) { + case TYPEC_PWR_MODE_USB: + current_mode = HD3SS3220_REG_CN_STAT_CURRENT_MODE_DEFAULT; + break; + case TYPEC_PWR_MODE_1_5A: + current_mode = HD3SS3220_REG_CN_STAT_CURRENT_MODE_MID; + break; + case TYPEC_PWR_MODE_3_0A: + current_mode = HD3SS3220_REG_CN_STAT_CURRENT_MODE_HIGH; + break; + case TYPEC_PWR_MODE_PD: /* Power delivery not supported */ + default: + dev_err(hd3ss3220->dev, "bad power operation mode: %d\n", power_opmode); + return -EINVAL; + } + + return regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_CN_STAT, + HD3SS3220_REG_CN_STAT_CURRENT_MODE_MASK, + current_mode); +} + +static int hd3ss3220_set_port_type(struct hd3ss3220 *hd3ss3220, int type) +{ + int mode_select, err; + + switch (type) { + case TYPEC_PORT_SRC: + mode_select = HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DFP; + break; + case TYPEC_PORT_SNK: + mode_select = HD3SS3220_REG_GEN_CTRL_MODE_SELECT_UFP; + break; + case TYPEC_PORT_DRP: + mode_select = HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DRP; + break; + default: + dev_err(hd3ss3220->dev, "bad port type: %d\n", type); + return -EINVAL; + } + + /* Disable termination before changing MODE_SELECT as required by datasheet */ + err = regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL, + HD3SS3220_REG_GEN_CTRL_DISABLE_TERM, + HD3SS3220_REG_GEN_CTRL_DISABLE_TERM); + if (err < 0) { + dev_err(hd3ss3220->dev, "Failed to disable port for mode change: %d\n", err); + return err; + } + + err = regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL, + HD3SS3220_REG_GEN_CTRL_MODE_SELECT_MASK, + mode_select); + if (err < 0) { + dev_err(hd3ss3220->dev, "Failed to change mode: %d\n", err); + regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL, + HD3SS3220_REG_GEN_CTRL_DISABLE_TERM, 0); + return err; + } + + err = regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL, + HD3SS3220_REG_GEN_CTRL_DISABLE_TERM, 0); + if (err < 0) + dev_err(hd3ss3220->dev, "Failed to re-enable port after mode change: %d\n", err); + + return err; +} + +static int hd3ss3220_set_source_pref(struct hd3ss3220 *hd3ss3220, int prefer_role) +{ + int src_pref; + + switch (prefer_role) { + case TYPEC_NO_PREFERRED_ROLE: + src_pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_DEFAULT; + break; + case TYPEC_SINK: + src_pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SNK; + break; + case TYPEC_SOURCE: + src_pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SRC; + break; + default: + dev_err(hd3ss3220->dev, "bad role preference: %d\n", prefer_role); + return -EINVAL; + } + return regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL, HD3SS3220_REG_GEN_CTRL_SRC_PREF_MASK, src_pref); @@ -76,31 +177,23 @@ static enum usb_role hd3ss3220_get_attached_state(struct hd3ss3220 *hd3ss3220) return attached_state; } -static int hd3ss3220_dr_set(struct typec_port *port, enum typec_data_role role) +static int hd3ss3220_try_role(struct typec_port *port, int role) { struct hd3ss3220 *hd3ss3220 = typec_get_drvdata(port); - enum usb_role role_val; - int pref, ret = 0; - if (role == TYPEC_HOST) { - role_val = USB_ROLE_HOST; - pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SRC; - } else { - role_val = USB_ROLE_DEVICE; - pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SNK; - } + return hd3ss3220_set_source_pref(hd3ss3220, role); +} - ret = hd3ss3220_set_source_pref(hd3ss3220, pref); - usleep_range(10, 100); +static int hd3ss3220_port_type_set(struct typec_port *port, enum typec_port_type type) +{ + struct hd3ss3220 *hd3ss3220 = typec_get_drvdata(port); - usb_role_switch_set_role(hd3ss3220->role_sw, role_val); - typec_set_data_role(hd3ss3220->port, role); - - return ret; + return hd3ss3220_set_port_type(hd3ss3220, type); } static const struct typec_operations hd3ss3220_ops = { - .dr_set = hd3ss3220_dr_set + .try_role = hd3ss3220_try_role, + .port_type_set = hd3ss3220_port_type_set, }; static void hd3ss3220_set_role(struct hd3ss3220 *hd3ss3220) @@ -108,9 +201,6 @@ static void hd3ss3220_set_role(struct hd3ss3220 *hd3ss3220) enum usb_role role_state = hd3ss3220_get_attached_state(hd3ss3220); usb_role_switch_set_role(hd3ss3220->role_sw, role_state); - if (role_state == USB_ROLE_NONE) - hd3ss3220_set_source_pref(hd3ss3220, - HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_DEFAULT); switch (role_state) { case USB_ROLE_HOST: @@ -162,6 +252,67 @@ static irqreturn_t hd3ss3220_irq_handler(int irq, void *data) return hd3ss3220_irq(hd3ss3220); } +static int hd3ss3220_configure_power_opmode(struct hd3ss3220 *hd3ss3220, + struct fwnode_handle *connector) +{ + /* + * Supported power operation mode can be configured through device tree + */ + const char *cap_str; + int ret, power_opmode; + + ret = fwnode_property_read_string(connector, "typec-power-opmode", &cap_str); + if (ret) + return 0; + + power_opmode = typec_find_pwr_opmode(cap_str); + return hd3ss3220_set_power_opmode(hd3ss3220, power_opmode); +} + +static int hd3ss3220_configure_port_type(struct hd3ss3220 *hd3ss3220, + struct fwnode_handle *connector, + struct typec_capability *cap) +{ + /* + * Port type can be configured through device tree + */ + const char *cap_str; + int ret; + + ret = fwnode_property_read_string(connector, "power-role", &cap_str); + if (ret) + return 0; + + ret = typec_find_port_power_role(cap_str); + if (ret < 0) + return ret; + + cap->type = ret; + return hd3ss3220_set_port_type(hd3ss3220, cap->type); +} + +static int hd3ss3220_configure_source_pref(struct hd3ss3220 *hd3ss3220, + struct fwnode_handle *connector, + struct typec_capability *cap) +{ + /* + * Preferred role can be configured through device tree + */ + const char *cap_str; + int ret; + + ret = fwnode_property_read_string(connector, "try-power-role", &cap_str); + if (ret) + return 0; + + ret = typec_find_power_role(cap_str); + if (ret < 0) + return ret; + + cap->prefer_role = ret; + return hd3ss3220_set_source_pref(hd3ss3220, cap->prefer_role); +} + static const struct regmap_config config = { .reg_bits = 8, .val_bits = 8, @@ -188,8 +339,6 @@ static int hd3ss3220_probe(struct i2c_client *client) if (IS_ERR(hd3ss3220->regmap)) return PTR_ERR(hd3ss3220->regmap); - hd3ss3220_set_source_pref(hd3ss3220, - HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_DEFAULT); /* For backward compatibility check the connector child node first */ connector = device_get_named_child_node(hd3ss3220->dev, "connector"); if (connector) { @@ -217,12 +366,24 @@ static int hd3ss3220_probe(struct i2c_client *client) typec_cap.ops = &hd3ss3220_ops; typec_cap.fwnode = connector; + ret = hd3ss3220_configure_source_pref(hd3ss3220, connector, &typec_cap); + if (ret < 0) + goto err_put_role; + + ret = hd3ss3220_configure_port_type(hd3ss3220, connector, &typec_cap); + if (ret < 0) + goto err_put_role; + hd3ss3220->port = typec_register_port(&client->dev, &typec_cap); if (IS_ERR(hd3ss3220->port)) { ret = PTR_ERR(hd3ss3220->port); goto err_put_role; } + ret = hd3ss3220_configure_power_opmode(hd3ss3220, connector); + if (ret < 0) + goto err_unreg_port; + hd3ss3220_set_role(hd3ss3220); ret = regmap_read(hd3ss3220->regmap, HD3SS3220_REG_CN_STAT_CTRL, &data); if (ret < 0) diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index 5dfe95754394..65dda9183e6f 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -718,7 +718,7 @@ DEFINE_SHOW_ATTRIBUTE(port_iom_status); static void pmc_mux_port_debugfs_init(struct pmc_usb_port *port) { struct dentry *debugfs_dir; - char name[6]; + char name[8]; snprintf(name, sizeof(name), "port%d", port->usb3_port - 1); diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c index e2fe479e16ad..f15c63d3a8f4 100644 --- a/drivers/usb/typec/tcpm/fusb302.c +++ b/drivers/usb/typec/tcpm/fusb302.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -733,7 +734,7 @@ static int tcpm_set_vconn(struct tcpc_dev *dev, bool on) mutex_lock(&chip->lock); if (chip->vconn_on == on) { - fusb302_log(chip, "vconn is already %s", on ? "On" : "Off"); + fusb302_log(chip, "vconn is already %s", str_on_off(on)); goto done; } if (on) { @@ -746,7 +747,7 @@ static int tcpm_set_vconn(struct tcpc_dev *dev, bool on) if (ret < 0) goto done; chip->vconn_on = on; - fusb302_log(chip, "vconn := %s", on ? "On" : "Off"); + fusb302_log(chip, "vconn := %s", str_on_off(on)); done: mutex_unlock(&chip->lock); @@ -761,7 +762,7 @@ static int tcpm_set_vbus(struct tcpc_dev *dev, bool on, bool charge) mutex_lock(&chip->lock); if (chip->vbus_on == on) { - fusb302_log(chip, "vbus is already %s", on ? "On" : "Off"); + fusb302_log(chip, "vbus is already %s", str_on_off(on)); } else { if (on) ret = regulator_enable(chip->vbus); @@ -769,15 +770,14 @@ static int tcpm_set_vbus(struct tcpc_dev *dev, bool on, bool charge) ret = regulator_disable(chip->vbus); if (ret < 0) { fusb302_log(chip, "cannot %s vbus regulator, ret=%d", - on ? "enable" : "disable", ret); + str_enable_disable(on), ret); goto done; } chip->vbus_on = on; - fusb302_log(chip, "vbus := %s", on ? "On" : "Off"); + fusb302_log(chip, "vbus := %s", str_on_off(on)); } if (chip->charge_on == charge) - fusb302_log(chip, "charge is already %s", - charge ? "On" : "Off"); + fusb302_log(chip, "charge is already %s", str_on_off(charge)); else chip->charge_on = charge; @@ -854,16 +854,16 @@ static int tcpm_set_pd_rx(struct tcpc_dev *dev, bool on) ret = fusb302_pd_set_auto_goodcrc(chip, on); if (ret < 0) { fusb302_log(chip, "cannot turn %s auto GCRC, ret=%d", - on ? "on" : "off", ret); + str_on_off(on), ret); goto done; } ret = fusb302_pd_set_interrupts(chip, on); if (ret < 0) { fusb302_log(chip, "cannot turn %s pd interrupts, ret=%d", - on ? "on" : "off", ret); + str_on_off(on), ret); goto done; } - fusb302_log(chip, "pd := %s", on ? "on" : "off"); + fusb302_log(chip, "pd := %s", str_on_off(on)); done: mutex_unlock(&chip->lock); @@ -1531,7 +1531,7 @@ static void fusb302_irq_work(struct work_struct *work) if (interrupt & FUSB_REG_INTERRUPT_VBUSOK) { vbus_present = !!(status0 & FUSB_REG_STATUS0_VBUSOK); fusb302_log(chip, "IRQ: VBUS_OK, vbus=%s", - vbus_present ? "On" : "Off"); + str_on_off(vbus_present)); if (vbus_present != chip->vbus_present) { chip->vbus_present = vbus_present; tcpm_vbus_change(chip->tcpm_port); @@ -1562,7 +1562,7 @@ static void fusb302_irq_work(struct work_struct *work) if ((interrupt & FUSB_REG_INTERRUPT_COMP_CHNG) && intr_comp_chng) { comp_result = !!(status0 & FUSB_REG_STATUS0_COMP); fusb302_log(chip, "IRQ: COMP_CHNG, comp=%s", - comp_result ? "true" : "false"); + str_true_false(comp_result)); if (comp_result) { /* cc level > Rd_threshold, detach */ chip->cc1 = TYPEC_CC_OPEN; diff --git a/drivers/usb/typec/tcpm/maxim_contaminant.c b/drivers/usb/typec/tcpm/maxim_contaminant.c index 22163d8f9eb0..0cdda06592fd 100644 --- a/drivers/usb/typec/tcpm/maxim_contaminant.c +++ b/drivers/usb/typec/tcpm/maxim_contaminant.c @@ -135,7 +135,7 @@ static int max_contaminant_read_resistance_kohm(struct max_tcpci_chip *chip, mv = max_contaminant_read_adc_mv(chip, channel, sleep_msec, raw, true); if (mv < 0) - return ret; + return mv; /* OVP enable */ ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, CCOVPDIS, 0); @@ -157,7 +157,7 @@ static int max_contaminant_read_resistance_kohm(struct max_tcpci_chip *chip, mv = max_contaminant_read_adc_mv(chip, channel, sleep_msec, raw, true); if (mv < 0) - return ret; + return mv; /* Disable current source */ ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, SBURPCTRL, 0); if (ret < 0) diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c index 726423684bae..18303b34594b 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include "qcom_pmic_typec.h" @@ -418,7 +419,7 @@ static int qcom_pmic_typec_pdphy_set_pd_rx(struct tcpc_dev *tcpc, bool on) spin_unlock_irqrestore(&pmic_typec_pdphy->lock, flags); - dev_dbg(pmic_typec_pdphy->dev, "set_pd_rx: %s\n", on ? "on" : "off"); + dev_dbg(pmic_typec_pdphy->dev, "set_pd_rx: %s\n", str_on_off(on)); return ret; } diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy_stub.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy_stub.c index df79059cda67..8fac171778da 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy_stub.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy_stub.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include "qcom_pmic_typec.h" @@ -38,7 +39,7 @@ static int qcom_pmic_typec_pdphy_stub_set_pd_rx(struct tcpc_dev *tcpc, bool on) struct pmic_typec *tcpm = tcpc_to_tcpm(tcpc); struct device *dev = tcpm->dev; - dev_dbg(dev, "set_pd_rx: %s\n", on ? "on" : "off"); + dev_dbg(dev, "set_pd_rx: %s\n", str_on_off(on)); return 0; } diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c index c37dede62e12..4fc83dcfae64 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -562,7 +563,8 @@ done: spin_unlock_irqrestore(&pmic_typec_port->lock, flags); dev_dbg(dev, "set_vconn: orientation %d control 0x%08x state %s cc %s vconn %s\n", - orientation, value, on ? "on" : "off", misc_to_vconn(misc), misc_to_cc(misc)); + orientation, value, str_on_off(on), misc_to_vconn(misc), + misc_to_cc(misc)); return ret; } diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index ed32583829be..19ab6647af70 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -27,6 +27,7 @@ #define VPPS_NEW_MIN_PERCENT 95 #define VPPS_VALID_MIN_MV 100 #define VSINKDISCONNECT_PD_MIN_PERCENT 90 +#define VPPS_SHUTDOWN_MIN_PERCENT 85 struct tcpci { struct device *dev; @@ -282,7 +283,7 @@ static int tcpci_set_polarity(struct tcpc_dev *tcpc, if (cc2 == TYPEC_CC_RD) /* Role control would have the Rp setting when DRP was enabled */ reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP); - else + else if (cc2 >= TYPEC_CC_RP_DEF) reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RD); } else { reg &= ~TCPC_ROLE_CTRL_CC1; @@ -290,7 +291,7 @@ static int tcpci_set_polarity(struct tcpc_dev *tcpc, if (cc1 == TYPEC_CC_RD) /* Role control would have the Rp setting when DRP was enabled */ reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP); - else + else if (cc1 >= TYPEC_CC_RP_DEF) reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RD); } } @@ -366,7 +367,8 @@ static int tcpci_enable_auto_vbus_discharge(struct tcpc_dev *dev, bool enable) } static int tcpci_set_auto_vbus_discharge_threshold(struct tcpc_dev *dev, enum typec_pwr_opmode mode, - bool pps_active, u32 requested_vbus_voltage_mv) + bool pps_active, u32 requested_vbus_voltage_mv, + u32 apdo_min_voltage_mv) { struct tcpci *tcpci = tcpc_to_tcpci(dev); unsigned int pwr_ctrl, threshold = 0; @@ -388,9 +390,12 @@ static int tcpci_set_auto_vbus_discharge_threshold(struct tcpc_dev *dev, enum ty threshold = AUTO_DISCHARGE_DEFAULT_THRESHOLD_MV; } else if (mode == TYPEC_PWR_MODE_PD) { if (pps_active) - threshold = ((VPPS_NEW_MIN_PERCENT * requested_vbus_voltage_mv / 100) - - VSINKPD_MIN_IR_DROP_MV - VPPS_VALID_MIN_MV) * - VSINKDISCONNECT_PD_MIN_PERCENT / 100; + /* + * To prevent disconnect when the source is in Current Limit Mode. + * Set the threshold to the lowest possible voltage vPpsShutdown (min) + */ + threshold = VPPS_SHUTDOWN_MIN_PERCENT * apdo_min_voltage_mv / 100 - + VSINKPD_MIN_IR_DROP_MV; else threshold = ((VSRC_NEW_MIN_PERCENT * requested_vbus_voltage_mv / 100) - VSINKPD_MIN_IR_DROP_MV - VSRC_VALID_MIN_MV) * @@ -700,7 +705,7 @@ static int tcpci_init(struct tcpc_dev *tcpc) tcpci->alert_mask = reg; - return tcpci_write16(tcpci, TCPC_ALERT_MASK, reg); + return 0; } irqreturn_t tcpci_irq(struct tcpci *tcpci) @@ -923,22 +928,27 @@ static int tcpci_probe(struct i2c_client *client) chip->data.set_orientation = err; + chip->tcpci = tcpci_register_port(&client->dev, &chip->data); + if (IS_ERR(chip->tcpci)) + return PTR_ERR(chip->tcpci); + err = devm_request_threaded_irq(&client->dev, client->irq, NULL, _tcpci_irq, IRQF_SHARED | IRQF_ONESHOT, dev_name(&client->dev), chip); if (err < 0) - return err; + goto unregister_port; - /* - * Disable irq while registering port. If irq is configured as an edge - * irq this allow to keep track and process the irq as soon as it is enabled. - */ - disable_irq(client->irq); - chip->tcpci = tcpci_register_port(&client->dev, &chip->data); - enable_irq(client->irq); + /* Enable chip interrupts at last */ + err = tcpci_write16(chip->tcpci, TCPC_ALERT_MASK, chip->tcpci->alert_mask); + if (err < 0) + goto unregister_port; - return PTR_ERR_OR_ZERO(chip->tcpci); + return 0; + +unregister_port: + tcpci_unregister_port(chip->tcpci); + return err; } static void tcpci_remove(struct i2c_client *client) diff --git a/drivers/usb/typec/tcpm/tcpci_mt6370.c b/drivers/usb/typec/tcpm/tcpci_mt6370.c index 1479f961772d..ed822f438a09 100644 --- a/drivers/usb/typec/tcpm/tcpci_mt6370.c +++ b/drivers/usb/typec/tcpm/tcpci_mt6370.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 6021eeb903fe..47be450d2be3 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -185,7 +186,8 @@ S(UNSTRUCTURED_VDMS), \ S(STRUCTURED_VDMS), \ S(COUNTRY_INFO), \ - S(COUNTRY_CODES) + S(COUNTRY_CODES), \ + S(REVISION_INFORMATION) #define GENERATE_ENUM(e) e #define GENERATE_STRING(s) #s @@ -225,6 +227,7 @@ enum pd_msg_request { PD_MSG_CTRL_NOT_SUPP, PD_MSG_DATA_SINK_CAP, PD_MSG_DATA_SOURCE_CAP, + PD_MSG_DATA_REV, }; enum adev_actions { @@ -310,6 +313,13 @@ struct pd_data { unsigned int operating_snk_mw; }; +struct pd_revision_info { + u8 rev_major; + u8 rev_minor; + u8 ver_major; + u8 ver_minor; +}; + /* * @sink_wait_cap_time: Deadline (in ms) for tTypeCSinkWaitCap timer * @ps_src_wait_off_time: Deadline (in ms) for tPSSourceOff timer @@ -567,6 +577,9 @@ struct tcpm_port { /* Timer deadline values configured at runtime */ struct pd_timings timings; + + /* Indicates maximum (revision, version) supported */ + struct pd_revision_info pd_rev; #ifdef CONFIG_DEBUG_FS struct dentry *dentry; struct mutex logbuffer_lock; /* log buffer access lock */ @@ -880,8 +893,8 @@ static int tcpm_enable_auto_vbus_discharge(struct tcpm_port *port, bool enable) if (port->tcpc->enable_auto_vbus_discharge) { ret = port->tcpc->enable_auto_vbus_discharge(port->tcpc, enable); - tcpm_log_force(port, "%s vbus discharge ret:%d", enable ? "enable" : "disable", - ret); + tcpm_log_force(port, "%s vbus discharge ret:%d", + str_enable_disable(enable), ret); if (!ret) port->auto_vbus_discharge_enabled = enable; } @@ -1234,6 +1247,24 @@ static u32 tcpm_forge_legacy_pdo(struct tcpm_port *port, u32 pdo, enum typec_rol } } +static int tcpm_pd_send_revision(struct tcpm_port *port) +{ + struct pd_message msg; + u32 rmdo; + + memset(&msg, 0, sizeof(msg)); + rmdo = RMDO(port->pd_rev.rev_major, port->pd_rev.rev_minor, + port->pd_rev.ver_major, port->pd_rev.ver_minor); + msg.payload[0] = cpu_to_le32(rmdo); + msg.header = PD_HEADER_LE(PD_DATA_REVISION, + port->pwr_role, + port->data_role, + port->negotiated_rev, + port->message_id, + 1); + return tcpm_pd_transmit(port, TCPC_TX_SOP, &msg); +} + static int tcpm_pd_send_source_caps(struct tcpm_port *port) { struct pd_message msg; @@ -2943,10 +2974,12 @@ static int tcpm_set_auto_vbus_discharge_threshold(struct tcpm_port *port, return 0; ret = port->tcpc->set_auto_vbus_discharge_threshold(port->tcpc, mode, pps_active, - requested_vbus_voltage); + requested_vbus_voltage, + port->pps_data.min_volt); tcpm_log_force(port, - "set_auto_vbus_discharge_threshold mode:%d pps_active:%c vbus:%u ret:%d", - mode, pps_active ? 'y' : 'n', requested_vbus_voltage, ret); + "set_auto_vbus_discharge_threshold mode:%d pps_active:%c vbus:%u pps_apdo_min_volt:%u ret:%d", + mode, pps_active ? 'y' : 'n', requested_vbus_voltage, + port->pps_data.min_volt, ret); return ret; } @@ -3537,6 +3570,17 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port, PD_MSG_CTRL_NOT_SUPP, NONE_AMS); break; + case PD_CTRL_GET_REVISION: + if (port->negotiated_rev >= PD_REV30 && port->pd_rev.rev_major) + tcpm_pd_handle_msg(port, PD_MSG_DATA_REV, + REVISION_INFORMATION); + else + tcpm_pd_handle_msg(port, + port->negotiated_rev < PD_REV30 ? + PD_MSG_CTRL_REJECT : + PD_MSG_CTRL_NOT_SUPP, + NONE_AMS); + break; default: tcpm_pd_handle_msg(port, port->negotiated_rev < PD_REV30 ? @@ -3781,6 +3825,14 @@ static bool tcpm_send_queued_message(struct tcpm_port *port) tcpm_ams_finish(port); } break; + case PD_MSG_DATA_REV: + ret = tcpm_pd_send_revision(port); + if (ret) + tcpm_log(port, + "Unable to send revision msg, ret=%d", + ret); + tcpm_ams_finish(port); + break; default: break; } @@ -4390,7 +4442,7 @@ static void tcpm_unregister_altmodes(struct tcpm_port *port) static void tcpm_set_partner_usb_comm_capable(struct tcpm_port *port, bool capable) { - tcpm_log(port, "Setting usb_comm capable %s", capable ? "true" : "false"); + tcpm_log(port, "Setting usb_comm capable %s", str_true_false(capable)); if (port->tcpc->set_partner_usb_comm_capable) port->tcpc->set_partner_usb_comm_capable(port->tcpc, capable); @@ -4772,7 +4824,7 @@ static void run_state_machine(struct tcpm_port *port) port->caps_count = 0; port->pd_capable = true; tcpm_set_state_cond(port, SRC_SEND_CAPABILITIES_TIMEOUT, - PD_T_SEND_SOURCE_CAP); + PD_T_SENDER_RESPONSE); } break; case SRC_SEND_CAPABILITIES_TIMEOUT: @@ -7036,7 +7088,9 @@ static void tcpm_port_unregister_pd(struct tcpm_port *port) static int tcpm_port_register_pd(struct tcpm_port *port) { - struct usb_power_delivery_desc desc = { port->typec_caps.pd_revision }; + u16 pd_revision = port->typec_caps.pd_revision; + u16 pd_version = port->pd_rev.ver_major << 8 | port->pd_rev.ver_minor; + struct usb_power_delivery_desc desc = { pd_revision, pd_version }; struct usb_power_delivery_capabilities *cap; int ret, i; @@ -7331,6 +7385,29 @@ static int tcpm_fw_get_snk_vdos(struct tcpm_port *port, struct fwnode_handle *fw return 0; } +static void tcpm_fw_get_pd_revision(struct tcpm_port *port, struct fwnode_handle *fwnode) +{ + int ret; + u8 val[4]; + + ret = fwnode_property_count_u8(fwnode, "pd-revision"); + if (!ret || ret != 4) { + tcpm_log(port, "Unable to find pd-revision property or incorrect array size"); + return; + } + + ret = fwnode_property_read_u8_array(fwnode, "pd-revision", val, 4); + if (ret) { + tcpm_log(port, "Failed to parse pd-revision, ret:(%d)", ret); + return; + } + + port->pd_rev.rev_major = val[0]; + port->pd_rev.rev_minor = val[1]; + port->pd_rev.ver_major = val[2]; + port->pd_rev.ver_minor = val[3]; +} + /* Power Supply access to expose source power information */ enum tcpm_psy_online_states { TCPM_PSY_OFFLINE = 0, @@ -7635,7 +7712,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) mutex_init(&port->lock); mutex_init(&port->swap_lock); - port->wq = kthread_create_worker(0, dev_name(dev)); + port->wq = kthread_run_worker(0, dev_name(dev)); if (IS_ERR(port->wq)) return ERR_CAST(port->wq); sched_set_fifo(port->wq->task); @@ -7669,11 +7746,18 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) goto out_destroy_wq; tcpm_fw_get_timings(port, tcpc->fwnode); + tcpm_fw_get_pd_revision(port, tcpc->fwnode); port->try_role = port->typec_caps.prefer_role; port->typec_caps.revision = 0x0120; /* Type-C spec release 1.2 */ - port->typec_caps.pd_revision = 0x0300; /* USB-PD spec release 3.0 */ + + if (port->pd_rev.rev_major) + port->typec_caps.pd_revision = port->pd_rev.rev_major << 8 | + port->pd_rev.rev_minor; + else + port->typec_caps.pd_revision = 0x0300; /* USB-PD spec release 3.0 */ + port->typec_caps.svdm_version = SVDM_VER_2_0; port->typec_caps.driver_data = port; port->typec_caps.ops = &tcpm_ops; diff --git a/drivers/usb/typec/ucsi/Kconfig b/drivers/usb/typec/ucsi/Kconfig index 680e1b87b152..75559601fe8f 100644 --- a/drivers/usb/typec/ucsi/Kconfig +++ b/drivers/usb/typec/ucsi/Kconfig @@ -69,6 +69,19 @@ config UCSI_PMIC_GLINK To compile the driver as a module, choose M here: the module will be called ucsi_glink. +config CROS_EC_UCSI + tristate "UCSI Driver for ChromeOS EC" + depends on MFD_CROS_EC_DEV + depends on CROS_USBPD_NOTIFY + depends on !EXTCON_TCSS_CROS_EC + default MFD_CROS_EC_DEV + help + This driver enables UCSI support for a ChromeOS EC. The EC is + expected to implement a PPM. + + To compile the driver as a module, choose M here: the module + will be called cros_ec_ucsi. + config UCSI_LENOVO_YOGA_C630 tristate "UCSI Interface Driver for Lenovo Yoga C630" depends on EC_LENOVO_YOGA_C630 diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile index aed41d23887b..be98a879104d 100644 --- a/drivers/usb/typec/ucsi/Makefile +++ b/drivers/usb/typec/ucsi/Makefile @@ -21,4 +21,5 @@ obj-$(CONFIG_UCSI_ACPI) += ucsi_acpi.o obj-$(CONFIG_UCSI_CCG) += ucsi_ccg.o obj-$(CONFIG_UCSI_STM32G0) += ucsi_stm32g0.o obj-$(CONFIG_UCSI_PMIC_GLINK) += ucsi_glink.o +obj-$(CONFIG_CROS_EC_UCSI) += cros_ec_ucsi.o obj-$(CONFIG_UCSI_LENOVO_YOGA_C630) += ucsi_yoga_c630.o diff --git a/drivers/usb/typec/ucsi/cros_ec_ucsi.c b/drivers/usb/typec/ucsi/cros_ec_ucsi.c new file mode 100644 index 000000000000..c605c8616726 --- /dev/null +++ b/drivers/usb/typec/ucsi/cros_ec_ucsi.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * UCSI driver for ChromeOS EC + * + * Copyright 2024 Google LLC. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "ucsi.h" + +/* + * Maximum size in bytes of a UCSI message between AP and EC + */ +#define MAX_EC_DATA_SIZE 256 + +/* + * Maximum time in milliseconds the cros_ec_ucsi driver + * will wait for a response to a command or and ack. + */ +#define WRITE_TMO_MS 5000 + +/* Number of times to attempt recovery from a write timeout before giving up. */ +#define WRITE_TMO_CTR_MAX 5 + +struct cros_ucsi_data { + struct device *dev; + struct ucsi *ucsi; + + struct cros_ec_device *ec; + struct notifier_block nb; + struct work_struct work; + struct delayed_work write_tmo; + int tmo_counter; + + struct completion complete; + unsigned long flags; +}; + +static int cros_ucsi_read(struct ucsi *ucsi, unsigned int offset, void *val, + size_t val_len) +{ + struct cros_ucsi_data *udata = ucsi_get_drvdata(ucsi); + struct ec_params_ucsi_ppm_get req = { + .offset = offset, + .size = val_len, + }; + int ret; + + if (val_len > MAX_EC_DATA_SIZE) { + dev_err(udata->dev, "Can't read %zu bytes. Too big.\n", val_len); + return -EINVAL; + } + + ret = cros_ec_cmd(udata->ec, 0, EC_CMD_UCSI_PPM_GET, + &req, sizeof(req), val, val_len); + if (ret < 0) { + dev_warn(udata->dev, "Failed to send EC message UCSI_PPM_GET: error=%d\n", ret); + return ret; + } + return 0; +} + +static int cros_ucsi_read_version(struct ucsi *ucsi, u16 *version) +{ + return cros_ucsi_read(ucsi, UCSI_VERSION, version, sizeof(*version)); +} + +static int cros_ucsi_read_cci(struct ucsi *ucsi, u32 *cci) +{ + return cros_ucsi_read(ucsi, UCSI_CCI, cci, sizeof(*cci)); +} + +static int cros_ucsi_read_message_in(struct ucsi *ucsi, void *val, + size_t val_len) +{ + return cros_ucsi_read(ucsi, UCSI_MESSAGE_IN, val, val_len); +} + +static int cros_ucsi_async_control(struct ucsi *ucsi, u64 cmd) +{ + struct cros_ucsi_data *udata = ucsi_get_drvdata(ucsi); + u8 ec_buf[sizeof(struct ec_params_ucsi_ppm_set) + sizeof(cmd)]; + struct ec_params_ucsi_ppm_set *req = (struct ec_params_ucsi_ppm_set *) ec_buf; + int ret; + + req->offset = UCSI_CONTROL; + memcpy(req->data, &cmd, sizeof(cmd)); + ret = cros_ec_cmd(udata->ec, 0, EC_CMD_UCSI_PPM_SET, + req, sizeof(ec_buf), NULL, 0); + if (ret < 0) { + dev_warn(udata->dev, "Failed to send EC message UCSI_PPM_SET: error=%d\n", ret); + return ret; + } + return 0; +} + +static int cros_ucsi_sync_control(struct ucsi *ucsi, u64 cmd) +{ + struct cros_ucsi_data *udata = ucsi_get_drvdata(ucsi); + int ret; + + ret = ucsi_sync_control_common(ucsi, cmd); + switch (ret) { + case -EBUSY: + /* EC may return -EBUSY if CCI.busy is set. + * Convert this to a timeout. + */ + case -ETIMEDOUT: + /* Schedule recovery attempt when we timeout + * or tried to send a command while still busy. + */ + cancel_delayed_work_sync(&udata->write_tmo); + schedule_delayed_work(&udata->write_tmo, + msecs_to_jiffies(WRITE_TMO_MS)); + break; + case 0: + /* Successful write. Cancel any pending recovery work. */ + cancel_delayed_work_sync(&udata->write_tmo); + break; + } + + return ret; +} + +static const struct ucsi_operations cros_ucsi_ops = { + .read_version = cros_ucsi_read_version, + .read_cci = cros_ucsi_read_cci, + .read_message_in = cros_ucsi_read_message_in, + .async_control = cros_ucsi_async_control, + .sync_control = cros_ucsi_sync_control, +}; + +static void cros_ucsi_work(struct work_struct *work) +{ + struct cros_ucsi_data *udata = container_of(work, struct cros_ucsi_data, work); + u32 cci; + + if (cros_ucsi_read_cci(udata->ucsi, &cci)) + return; + + ucsi_notify_common(udata->ucsi, cci); +} + +static void cros_ucsi_write_timeout(struct work_struct *work) +{ + struct cros_ucsi_data *udata = + container_of(work, struct cros_ucsi_data, write_tmo.work); + u32 cci; + u64 cmd; + + if (cros_ucsi_read(udata->ucsi, UCSI_CCI, &cci, sizeof(cci))) { + dev_err(udata->dev, + "Reading CCI failed; no write timeout recovery possible.\n"); + return; + } + + if (cci & UCSI_CCI_BUSY) { + udata->tmo_counter++; + + if (udata->tmo_counter <= WRITE_TMO_CTR_MAX) + schedule_delayed_work(&udata->write_tmo, + msecs_to_jiffies(WRITE_TMO_MS)); + else + dev_err(udata->dev, + "PPM unresponsive - too many write timeouts.\n"); + + return; + } + + /* No longer busy means we can reset our timeout counter. */ + udata->tmo_counter = 0; + + /* Need to ack previous command which may have timed out. */ + if (cci & UCSI_CCI_COMMAND_COMPLETE) { + cmd = UCSI_ACK_CC_CI | UCSI_ACK_COMMAND_COMPLETE; + cros_ucsi_async_control(udata->ucsi, cmd); + + /* Check again after a few seconds that the system has + * recovered to make sure our async write above was successful. + */ + schedule_delayed_work(&udata->write_tmo, + msecs_to_jiffies(WRITE_TMO_MS)); + return; + } + + /* We recovered from a previous timeout. Treat this as a recovery from + * suspend and call resume. + */ + ucsi_resume(udata->ucsi); +} + +static int cros_ucsi_event(struct notifier_block *nb, + unsigned long host_event, void *_notify) +{ + struct cros_ucsi_data *udata = container_of(nb, struct cros_ucsi_data, nb); + + if (!(host_event & PD_EVENT_PPM)) + return NOTIFY_OK; + + dev_dbg(udata->dev, "UCSI notification received\n"); + flush_work(&udata->work); + schedule_work(&udata->work); + + return NOTIFY_OK; +} + +static void cros_ucsi_destroy(struct cros_ucsi_data *udata) +{ + cros_usbpd_unregister_notify(&udata->nb); + cancel_delayed_work_sync(&udata->write_tmo); + cancel_work_sync(&udata->work); + ucsi_destroy(udata->ucsi); +} + +static int cros_ucsi_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cros_ec_dev *ec_data = dev_get_drvdata(dev->parent); + struct cros_ucsi_data *udata; + int ret; + + udata = devm_kzalloc(dev, sizeof(*udata), GFP_KERNEL); + if (!udata) + return -ENOMEM; + + udata->dev = dev; + + udata->ec = ec_data->ec_dev; + if (!udata->ec) + return dev_err_probe(dev, -ENODEV, "couldn't find parent EC device\n"); + + platform_set_drvdata(pdev, udata); + + INIT_WORK(&udata->work, cros_ucsi_work); + INIT_DELAYED_WORK(&udata->write_tmo, cros_ucsi_write_timeout); + init_completion(&udata->complete); + + udata->ucsi = ucsi_create(dev, &cros_ucsi_ops); + if (IS_ERR(udata->ucsi)) + return dev_err_probe(dev, PTR_ERR(udata->ucsi), "failed to allocate UCSI instance\n"); + + ucsi_set_drvdata(udata->ucsi, udata); + + udata->nb.notifier_call = cros_ucsi_event; + ret = cros_usbpd_register_notify(&udata->nb); + if (ret) { + dev_err_probe(dev, ret, "failed to register notifier\n"); + ucsi_destroy(udata->ucsi); + return ret; + } + + ret = ucsi_register(udata->ucsi); + if (ret) { + dev_err_probe(dev, ret, "failed to register UCSI\n"); + cros_ucsi_destroy(udata); + return ret; + } + + return 0; +} + +static void cros_ucsi_remove(struct platform_device *dev) +{ + struct cros_ucsi_data *udata = platform_get_drvdata(dev); + + ucsi_unregister(udata->ucsi); + cros_ucsi_destroy(udata); +} + +static int __maybe_unused cros_ucsi_suspend(struct device *dev) +{ + struct cros_ucsi_data *udata = dev_get_drvdata(dev); + + cancel_delayed_work_sync(&udata->write_tmo); + cancel_work_sync(&udata->work); + + return 0; +} + +static void __maybe_unused cros_ucsi_complete(struct device *dev) +{ + struct cros_ucsi_data *udata = dev_get_drvdata(dev); + + ucsi_resume(udata->ucsi); +} + +/* + * UCSI protocol is also used on ChromeOS platforms which reply on + * cros_ec_lpc.c driver for communication with embedded controller (EC). + * On such platforms communication with the EC is not available until + * the .complete() callback of the cros_ec_lpc driver is executed. + * For this reason we delay ucsi_resume() until the .complete() stage + * otherwise UCSI SET_NOTIFICATION_ENABLE command will fail and we won't + * receive any UCSI notifications from the EC where PPM is implemented. + */ +static const struct dev_pm_ops cros_ucsi_pm_ops = { +#ifdef CONFIG_PM_SLEEP + .suspend = cros_ucsi_suspend, + .complete = cros_ucsi_complete, +#endif +}; + +static const struct platform_device_id cros_ucsi_id[] = { + { KBUILD_MODNAME, 0 }, + {} +}; +MODULE_DEVICE_TABLE(platform, cros_ucsi_id); + +static struct platform_driver cros_ucsi_driver = { + .driver = { + .name = KBUILD_MODNAME, + .pm = &cros_ucsi_pm_ops, + }, + .id_table = cros_ucsi_id, + .probe = cros_ucsi_probe, + .remove = cros_ucsi_remove, +}; + +module_platform_driver(cros_ucsi_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("UCSI driver for ChromeOS EC"); diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 5ff369c24a2f..82735eb34f0e 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -30,6 +30,7 @@ struct dentry; #define UCSIv2_MESSAGE_OUT 272 /* UCSI versions */ +#define UCSI_VERSION_1_0 0x0100 #define UCSI_VERSION_1_1 0x0110 #define UCSI_VERSION_1_2 0x0120 #define UCSI_VERSION_2_0 0x0200 diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index fcb8e61136cf..740171f24ef9 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -646,7 +646,7 @@ static int ucsi_ccg_sync_control(struct ucsi *ucsi, u64 command) UCSI_CMD_CONNECTOR_MASK; if (con_index == 0) { ret = -EINVAL; - goto unlock; + goto err_put; } con = &uc->ucsi->connector[con_index - 1]; ucsi_ccg_update_set_new_cam_cmd(uc, con, &command); @@ -654,8 +654,8 @@ static int ucsi_ccg_sync_control(struct ucsi *ucsi, u64 command) ret = ucsi_sync_control_common(ucsi, command); +err_put: pm_runtime_put_sync(uc->dev); -unlock: mutex_unlock(&uc->lock); return ret; diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index 90948cd6d297..fed39d458090 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -185,6 +185,11 @@ static void pmic_glink_ucsi_connector_status(struct ucsi_connector *con) struct pmic_glink_ucsi *ucsi = ucsi_get_drvdata(con->ucsi); int orientation; + if (!UCSI_CONSTAT(con, CONNECTED)) { + typec_set_orientation(con->port, TYPEC_ORIENTATION_NONE); + return; + } + if (con->num > PMIC_GLINK_MAX_PORTS || !ucsi->port_orientation[con->num - 1]) return; diff --git a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c index f3a5e24ea84d..4cae85c0dc12 100644 --- a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c +++ b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c @@ -71,7 +71,7 @@ static int yoga_c630_ucsi_async_control(struct ucsi *ucsi, u64 command) return yoga_c630_ec_ucsi_write(uec->ec, (u8*)&command); } -const struct ucsi_operations yoga_c630_ucsi_ops = { +static const struct ucsi_operations yoga_c630_ucsi_ops = { .read_version = yoga_c630_ucsi_read_version, .read_cci = yoga_c630_ucsi_read_cci, .read_message_in = yoga_c630_ucsi_read_message_in, diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c index 6338d818bc8b..9aa30ef76f3b 100644 --- a/drivers/usb/usbip/stub_rx.c +++ b/drivers/usb/usbip/stub_rx.c @@ -269,7 +269,7 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev, return 0; } - usbip_dbg_stub_rx("seqnum %d is not pending\n", + usbip_dbg_stub_rx("seqnum %u is not pending\n", pdu->u.cmd_unlink.seqnum); /* diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c index b1c2f6781cb3..7eb2e074012a 100644 --- a/drivers/usb/usbip/stub_tx.c +++ b/drivers/usb/usbip/stub_tx.c @@ -201,7 +201,7 @@ static int stub_send_ret_submit(struct stub_device *sdev) /* 1. setup usbip_header */ setup_ret_submit_pdu(&pdu_header, urb); - usbip_dbg_stub_tx("setup txdata seqnum: %d\n", + usbip_dbg_stub_tx("setup txdata seqnum: %u\n", pdu_header.base.seqnum); if (priv->sgl) { diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index b03e5021c25b..e70fba9f55d6 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "usbip_common.h" #include "vhci.h" @@ -675,7 +676,7 @@ static void vhci_tx_urb(struct urb *urb, struct vhci_device *vdev) spin_lock_irqsave(&vdev->priv_lock, flags); - priv->seqnum = atomic_inc_return(&vhci_hcd->seqnum); + priv->seqnum = (u32)atomic_inc_return(&vhci_hcd->seqnum); if (priv->seqnum == 0xffff) dev_info(&urb->dev->dev, "seqnum max\n"); @@ -1161,12 +1162,8 @@ static int vhci_setup(struct usb_hcd *hcd) hcd->self.root_hub->speed = USB_SPEED_SUPER_PLUS; } - /* - * Support SG. - * sg_tablesize is an arbitrary value to alleviate memory pressure - * on the host. - */ - hcd->self.sg_tablesize = 32; + /* accept arbitrarily long scatter-gather lists */ + hcd->self.sg_tablesize = ~0; hcd->self.no_sg_constraint = 1; return 0; @@ -1453,7 +1450,7 @@ static int vhci_hcd_suspend(struct platform_device *pdev, pm_message_t state) if (connected > 0) { dev_info(&pdev->dev, "We have %d active connection%s. Do not suspend.\n", - connected, (connected == 1 ? "" : "s")); + connected, str_plural(connected)); ret = -EBUSY; } else { dev_info(&pdev->dev, "suspend vhci_hcd"); diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c index 7f2d1c241559..a75f4a898a41 100644 --- a/drivers/usb/usbip/vhci_rx.c +++ b/drivers/usb/usbip/vhci_rx.c @@ -66,7 +66,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev, spin_unlock_irqrestore(&vdev->priv_lock, flags); if (!urb) { - pr_err("cannot find a urb of seqnum %u max seqnum %d\n", + pr_err("cannot find a urb of seqnum %u max seqnum %u\n", pdu->base.seqnum, atomic_read(&vhci_hcd->seqnum)); usbip_event_add(ud, VDEV_EVENT_ERROR_TCP); @@ -162,10 +162,10 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev, * already received the result of its submit result and gave * back the URB. */ - pr_info("the urb (seqnum %d) was already given back\n", + pr_info("the urb (seqnum %u) was already given back\n", pdu->base.seqnum); } else { - usbip_dbg_vhci_rx("now giveback urb %d\n", pdu->base.seqnum); + usbip_dbg_vhci_rx("now giveback urb %u\n", pdu->base.seqnum); /* If unlink is successful, status is -ECONNRESET */ urb->status = pdu->u.ret_unlink.status; diff --git a/drivers/usb/usbip/vudc_sysfs.c b/drivers/usb/usbip/vudc_sysfs.c index 907a43a00896..2aae3edfc813 100644 --- a/drivers/usb/usbip/vudc_sysfs.c +++ b/drivers/usb/usbip/vudc_sysfs.c @@ -67,7 +67,7 @@ out: * Exposes device descriptor from the gadget driver. */ static ssize_t dev_desc_read(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, char *out, + const struct bin_attribute *attr, char *out, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -88,7 +88,7 @@ unlock: spin_unlock_irqrestore(&udc->lock, flags); return ret; } -static BIN_ATTR_RO(dev_desc, sizeof(struct usb_device_descriptor)); +static const BIN_ATTR_RO(dev_desc, sizeof(struct usb_device_descriptor)); static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *attr, @@ -252,14 +252,14 @@ static struct attribute *dev_attrs[] = { NULL, }; -static struct bin_attribute *dev_bin_attrs[] = { +static const struct bin_attribute *const dev_bin_attrs[] = { &bin_attr_dev_desc, NULL, }; static const struct attribute_group vudc_attr_group = { .attrs = dev_attrs, - .bin_attrs = dev_bin_attrs, + .bin_attrs_new = dev_bin_attrs, }; const struct attribute_group *vudc_groups[] = { diff --git a/drivers/usb/usbip/vudc_tx.c b/drivers/usb/usbip/vudc_tx.c index 3ccb17c3e840..30c11bf9f4e7 100644 --- a/drivers/usb/usbip/vudc_tx.c +++ b/drivers/usb/usbip/vudc_tx.c @@ -107,7 +107,7 @@ static int v_send_ret_submit(struct vudc *udc, struct urbp *urb_p) /* 1. setup usbip_header */ setup_ret_submit_pdu(&pdu_header, urb_p); - usbip_dbg_stub_tx("setup txdata seqnum: %d\n", + usbip_dbg_stub_tx("setup txdata seqnum: %u\n", pdu_header.base.seqnum); usbip_header_correct_endian(&pdu_header, 1); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 5f581e71e201..36099047560d 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1952,7 +1952,7 @@ static int mlx5_vdpa_add_mac_vlan_rules(struct mlx5_vdpa_net *ndev, u8 *mac, goto out_free; #if defined(CONFIG_MLX5_VDPA_STEERING_DEBUG) - dests[1].counter_id = mlx5_fc_id(node->ucast_counter.counter); + dests[1].counter = node->ucast_counter.counter; #endif node->ucast_rule = mlx5_add_flow_rules(ndev->rxft, spec, &flow_act, dests, NUM_DESTS); if (IS_ERR(node->ucast_rule)) { @@ -1961,7 +1961,7 @@ static int mlx5_vdpa_add_mac_vlan_rules(struct mlx5_vdpa_net *ndev, u8 *mac, } #if defined(CONFIG_MLX5_VDPA_STEERING_DEBUG) - dests[1].counter_id = mlx5_fc_id(node->mcast_counter.counter); + dests[1].counter = node->mcast_counter.counter; #endif memset(dmac_c, 0, ETH_ALEN); diff --git a/drivers/vdpa/octeon_ep/octep_vdpa.h b/drivers/vdpa/octeon_ep/octep_vdpa.h index 046710ec4d42..53b020b019f7 100644 --- a/drivers/vdpa/octeon_ep/octep_vdpa.h +++ b/drivers/vdpa/octeon_ep/octep_vdpa.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -29,12 +30,12 @@ #define OCTEP_EPF_RINFO(x) (0x000209f0 | ((x) << 25)) #define OCTEP_VF_MBOX_DATA(x) (0x00010210 | ((x) << 17)) #define OCTEP_PF_MBOX_DATA(x) (0x00022000 | ((x) << 4)) - -#define OCTEP_EPF_RINFO_RPVF(val) (((val) >> 32) & 0xF) -#define OCTEP_EPF_RINFO_NVFS(val) (((val) >> 48) & 0x7F) +#define OCTEP_VF_IN_CTRL(x) (0x00010000 | ((x) << 17)) +#define OCTEP_VF_IN_CTRL_RPVF(val) (((val) >> 48) & 0xF) #define OCTEP_FW_READY_SIGNATURE0 0xFEEDFEED #define OCTEP_FW_READY_SIGNATURE1 0x3355ffaa +#define OCTEP_MAX_CB_INTR 8 enum octep_vdpa_dev_status { OCTEP_VDPA_DEV_STATUS_INVALID, @@ -48,9 +49,26 @@ enum octep_vdpa_dev_status { struct octep_vring_info { struct vdpa_callback cb; void __iomem *notify_addr; - u32 __iomem *cb_notify_addr; + void __iomem *cb_notify_addr; phys_addr_t notify_pa; - char msix_name[256]; +}; + +enum octep_pci_vndr_cfg_type { + OCTEP_PCI_VNDR_CFG_TYPE_VIRTIO_ID, + OCTEP_PCI_VNDR_CFG_TYPE_MAX, +}; + +struct octep_pci_vndr_data { + struct virtio_pci_vndr_data hdr; + u8 id; + u8 bar; + union { + u64 data; + struct { + u32 offset; + u32 length; + }; + }; }; struct octep_hw { @@ -68,7 +86,9 @@ struct octep_hw { u64 features; u16 nr_vring; u32 config_size; - int irq; + int nb_irqs; + int *irqs; + u8 dev_id; }; u8 octep_hw_get_status(struct octep_hw *oct_hw); diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c index 1d4767b33315..74240101c505 100644 --- a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c +++ b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c @@ -2,6 +2,7 @@ /* Copyright (C) 2024 Marvell. */ #include +#include #include "octep_vdpa.h" @@ -358,7 +359,14 @@ u16 octep_get_vq_size(struct octep_hw *oct_hw) static u32 octep_get_config_size(struct octep_hw *oct_hw) { - return sizeof(struct virtio_net_config); + switch (oct_hw->dev_id) { + case VIRTIO_ID_NET: + return sizeof(struct virtio_net_config); + case VIRTIO_ID_CRYPTO: + return sizeof(struct virtio_crypto_config); + default: + return 0; + } } static void __iomem *octep_get_cap_addr(struct octep_hw *oct_hw, struct virtio_pci_cap *cap) @@ -416,8 +424,25 @@ static int octep_pci_signature_verify(struct octep_hw *oct_hw) return 0; } +static void octep_vndr_data_process(struct octep_hw *oct_hw, + struct octep_pci_vndr_data *vndr_data) +{ + BUILD_BUG_ON(sizeof(struct octep_pci_vndr_data) % 4 != 0); + + switch (vndr_data->id) { + case OCTEP_PCI_VNDR_CFG_TYPE_VIRTIO_ID: + oct_hw->dev_id = (u8)vndr_data->data; + break; + default: + dev_err(&oct_hw->pdev->dev, "Invalid vendor data id %u\n", + vndr_data->id); + break; + } +} + int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev) { + struct octep_pci_vndr_data vndr_data; struct octep_mbox __iomem *mbox; struct device *dev = &pdev->dev; struct virtio_pci_cap cap; @@ -466,6 +491,15 @@ int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev) case VIRTIO_PCI_CAP_ISR_CFG: oct_hw->isr = octep_get_cap_addr(oct_hw, &cap); break; + case VIRTIO_PCI_CAP_VENDOR_CFG: + octep_pci_caps_read(oct_hw, &vndr_data, sizeof(vndr_data), pos); + if (vndr_data.hdr.vendor_id != PCI_VENDOR_ID_CAVIUM) { + dev_err(dev, "Invalid vendor data\n"); + return -EINVAL; + } + + octep_vndr_data_process(oct_hw, &vndr_data); + break; } pos = cap.cap_next; @@ -495,8 +529,6 @@ int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev) if (!oct_hw->vqs) return -ENOMEM; - oct_hw->irq = -1; - dev_info(&pdev->dev, "Device features : %llx\n", oct_hw->features); dev_info(&pdev->dev, "Maximum queues : %u\n", oct_hw->nr_vring); diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_main.c b/drivers/vdpa/octeon_ep/octep_vdpa_main.c index cd55b1aac151..f3d4dda4e04c 100644 --- a/drivers/vdpa/octeon_ep/octep_vdpa_main.c +++ b/drivers/vdpa/octeon_ep/octep_vdpa_main.c @@ -49,58 +49,89 @@ static irqreturn_t octep_vdpa_intr_handler(int irq, void *data) struct octep_hw *oct_hw = data; int i; - for (i = 0; i < oct_hw->nr_vring; i++) { - if (oct_hw->vqs[i].cb.callback && ioread32(oct_hw->vqs[i].cb_notify_addr)) { - /* Acknowledge the per queue notification to the device */ - iowrite32(0, oct_hw->vqs[i].cb_notify_addr); - oct_hw->vqs[i].cb.callback(oct_hw->vqs[i].cb.private); + /* Each device has multiple interrupts (nb_irqs) shared among rings + * (nr_vring). Device interrupts are mapped to the rings in a + * round-robin fashion. + * + * For example, if nb_irqs = 8 and nr_vring = 64: + * 0 -> 0, 8, 16, 24, 32, 40, 48, 56; + * 1 -> 1, 9, 17, 25, 33, 41, 49, 57; + * ... + * 7 -> 7, 15, 23, 31, 39, 47, 55, 63; + */ + + for (i = irq - oct_hw->irqs[0]; i < oct_hw->nr_vring; i += oct_hw->nb_irqs) { + if (ioread8(oct_hw->vqs[i].cb_notify_addr)) { + /* Acknowledge the per ring notification to the device */ + iowrite8(0, oct_hw->vqs[i].cb_notify_addr); + + if (likely(oct_hw->vqs[i].cb.callback)) + oct_hw->vqs[i].cb.callback(oct_hw->vqs[i].cb.private); + break; } } + /* Check for config interrupt. Config uses the first interrupt */ + if (unlikely(irq == oct_hw->irqs[0] && ioread8(oct_hw->isr))) { + iowrite8(0, oct_hw->isr); + + if (oct_hw->config_cb.callback) + oct_hw->config_cb.callback(oct_hw->config_cb.private); + } + return IRQ_HANDLED; } static void octep_free_irqs(struct octep_hw *oct_hw) { struct pci_dev *pdev = oct_hw->pdev; + int irq; - if (oct_hw->irq != -1) { - devm_free_irq(&pdev->dev, oct_hw->irq, oct_hw); - oct_hw->irq = -1; + if (!oct_hw->irqs) + return; + + for (irq = 0; irq < oct_hw->nb_irqs; irq++) { + if (!oct_hw->irqs[irq]) + break; + + devm_free_irq(&pdev->dev, oct_hw->irqs[irq], oct_hw); } + pci_free_irq_vectors(pdev); + devm_kfree(&pdev->dev, oct_hw->irqs); + oct_hw->irqs = NULL; } static int octep_request_irqs(struct octep_hw *oct_hw) { struct pci_dev *pdev = oct_hw->pdev; - int ret, irq; + int ret, irq, idx; - /* Currently HW device provisions one IRQ per VF, hence - * allocate one IRQ for all virtqueues call interface. - */ - ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX); + oct_hw->irqs = devm_kcalloc(&pdev->dev, oct_hw->nb_irqs, sizeof(int), GFP_KERNEL); + if (!oct_hw->irqs) + return -ENOMEM; + + ret = pci_alloc_irq_vectors(pdev, 1, oct_hw->nb_irqs, PCI_IRQ_MSIX); if (ret < 0) { dev_err(&pdev->dev, "Failed to alloc msix vector"); return ret; } - snprintf(oct_hw->vqs->msix_name, sizeof(oct_hw->vqs->msix_name), - OCTEP_VDPA_DRIVER_NAME "-vf-%d", pci_iov_vf_id(pdev)); - - irq = pci_irq_vector(pdev, 0); - ret = devm_request_irq(&pdev->dev, irq, octep_vdpa_intr_handler, 0, - oct_hw->vqs->msix_name, oct_hw); - if (ret) { - dev_err(&pdev->dev, "Failed to register interrupt handler\n"); - goto free_irq_vec; + for (idx = 0; idx < oct_hw->nb_irqs; idx++) { + irq = pci_irq_vector(pdev, idx); + ret = devm_request_irq(&pdev->dev, irq, octep_vdpa_intr_handler, 0, + dev_name(&pdev->dev), oct_hw); + if (ret) { + dev_err(&pdev->dev, "Failed to register interrupt handler\n"); + goto free_irqs; + } + oct_hw->irqs[idx] = irq; } - oct_hw->irq = irq; return 0; -free_irq_vec: - pci_free_irq_vectors(pdev); +free_irqs: + octep_free_irqs(oct_hw); return ret; } @@ -271,7 +302,9 @@ static u32 octep_vdpa_get_generation(struct vdpa_device *vdpa_dev) static u32 octep_vdpa_get_device_id(struct vdpa_device *vdpa_dev) { - return VIRTIO_ID_NET; + struct octep_hw *oct_hw = vdpa_to_octep_hw(vdpa_dev); + + return oct_hw->dev_id; } static u32 octep_vdpa_get_vendor_id(struct vdpa_device *vdpa_dev) @@ -559,6 +592,7 @@ static void octep_vdpa_setup_task(struct work_struct *work) struct device *dev = &pdev->dev; struct octep_hw *oct_hw; unsigned long timeout; + u64 val; int ret; oct_hw = &mgmt_dev->oct_hw; @@ -590,6 +624,13 @@ static void octep_vdpa_setup_task(struct work_struct *work) if (ret) return; + val = readq(oct_hw->base[OCTEP_HW_MBOX_BAR] + OCTEP_VF_IN_CTRL(0)); + oct_hw->nb_irqs = OCTEP_VF_IN_CTRL_RPVF(val); + if (!oct_hw->nb_irqs || oct_hw->nb_irqs > OCTEP_MAX_CB_INTR) { + dev_err(dev, "Invalid number of interrupts %d\n", oct_hw->nb_irqs); + goto unmap_region; + } + ret = octep_hw_caps_read(oct_hw, pdev); if (ret < 0) goto unmap_region; @@ -768,12 +809,6 @@ static int octep_vdpa_pf_setup(struct octep_pf *octpf) return -EINVAL; } - if (OCTEP_EPF_RINFO_RPVF(val) != BIT_ULL(0)) { - val &= ~GENMASK_ULL(35, 32); - val |= BIT_ULL(32); - writeq(val, addr + OCTEP_EPF_RINFO(0)); - } - len = pci_resource_len(pdev, OCTEP_HW_CAPS_BAR); octpf->vf_stride = len / totalvfs; diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index c8b74980dbd1..55ec51c17ab3 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -556,58 +556,60 @@ static const struct vdpa_config_ops snet_config_ops = { static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) { char *name; - int ret, i, mask = 0; + unsigned short i; + bool bars_found = false; + + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev)); + if (!name) + return -ENOMEM; + /* We don't know which BAR will be used to communicate.. * We will map every bar with len > 0. * * Later, we will discover the BAR and unmap all other BARs. */ for (i = 0; i < PCI_STD_NUM_BARS; i++) { - if (pci_resource_len(pdev, i)) - mask |= (1 << i); + void __iomem *io; + + if (pci_resource_len(pdev, i) == 0) + continue; + + io = pcim_iomap_region(pdev, i, name); + if (IS_ERR(io)) { + SNET_ERR(pdev, "Failed to request and map PCI BARs\n"); + return PTR_ERR(io); + } + + psnet->bars[i] = io; + bars_found = true; } /* No BAR can be used.. */ - if (!mask) { + if (!bars_found) { SNET_ERR(pdev, "Failed to find a PCI BAR\n"); return -ENODEV; } - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev)); - if (!name) - return -ENOMEM; - - ret = pcim_iomap_regions(pdev, mask, name); - if (ret) { - SNET_ERR(pdev, "Failed to request and map PCI BARs\n"); - return ret; - } - - for (i = 0; i < PCI_STD_NUM_BARS; i++) { - if (mask & (1 << i)) - psnet->bars[i] = pcim_iomap_table(pdev)[i]; - } - return 0; } static int snet_open_vf_bar(struct pci_dev *pdev, struct snet *snet) { char *name; - int ret; + void __iomem *io; name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "snet[%s]-bars", pci_name(pdev)); if (!name) return -ENOMEM; /* Request and map BAR */ - ret = pcim_iomap_regions(pdev, BIT(snet->psnet->cfg.vf_bar), name); - if (ret) { + io = pcim_iomap_region(pdev, snet->psnet->cfg.vf_bar, name); + if (IS_ERR(io)) { SNET_ERR(pdev, "Failed to request and map PCI BAR for a VF\n"); - return ret; + return PTR_ERR(io); } - snet->bar = pcim_iomap_table(pdev)[snet->psnet->cfg.vf_bar]; + snet->bar = io; return 0; } @@ -656,15 +658,12 @@ static int psnet_detect_bar(struct psnet *psnet, u32 off) static void psnet_unmap_unused_bars(struct pci_dev *pdev, struct psnet *psnet) { - int i, mask = 0; + unsigned short i; for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (psnet->bars[i] && i != psnet->barno) - mask |= (1 << i); + pcim_iounmap_region(pdev, i); } - - if (mask) - pcim_iounmap_regions(pdev, mask); } /* Read SNET config from PCI BAR */ diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 8ffea8430f95..c204fc8e471a 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -229,7 +229,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, dev = &vdpasim->vdpa.dev; kthread_init_work(&vdpasim->work, vdpasim_work_fn); - vdpasim->worker = kthread_create_worker(0, "vDPA sim worker: %s", + vdpasim->worker = kthread_run_worker(0, "vDPA sim worker: %s", dev_attr->name); if (IS_ERR(vdpasim->worker)) goto err_iommu; diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index 16380764275e..8787407f75b0 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -367,6 +367,14 @@ static void vp_vdpa_kick_vq(struct vdpa_device *vdpa, u16 qid) vp_iowrite16(qid, vp_vdpa->vring[qid].notify); } +static void vp_vdpa_kick_vq_with_data(struct vdpa_device *vdpa, u32 data) +{ + struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa); + u16 qid = data & 0xFFFF; + + vp_iowrite32(data, vp_vdpa->vring[qid].notify); +} + static u32 vp_vdpa_get_generation(struct vdpa_device *vdpa) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); @@ -472,6 +480,7 @@ static const struct vdpa_config_ops vp_vdpa_ops = { .get_vq_size = vp_vdpa_get_vq_size, .set_vq_address = vp_vdpa_set_vq_address, .kick_vq = vp_vdpa_kick_vq, + .kick_vq_with_data = vp_vdpa_kick_vq_with_data, .get_generation = vp_vdpa_get_generation, .get_device_id = vp_vdpa_get_device_id, .get_vendor_id = vp_vdpa_get_vendor_id, diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c index ed4737de4528..f2e686f8f1ef 100644 --- a/drivers/vfio/mdev/mdev_core.c +++ b/drivers/vfio/mdev/mdev_core.c @@ -76,7 +76,7 @@ int mdev_register_parent(struct mdev_parent *parent, struct device *dev, if (ret) return ret; - ret = class_compat_create_link(mdev_bus_compat_class, dev, NULL); + ret = class_compat_create_link(mdev_bus_compat_class, dev); if (ret) dev_warn(dev, "Failed to create compatibility class link\n"); @@ -98,7 +98,7 @@ void mdev_unregister_parent(struct mdev_parent *parent) dev_info(parent->dev, "MDEV: Unregistering\n"); down_write(&parent->unreg_sem); - class_compat_remove_link(mdev_bus_compat_class, parent->dev, NULL); + class_compat_remove_link(mdev_bus_compat_class, parent->dev); device_for_each_child(parent->dev, NULL, mdev_device_remove_cb); parent_remove_sysfs_files(parent); up_write(&parent->unreg_sem); diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c index eb7387ee6ebd..11eda6b207f1 100644 --- a/drivers/vfio/pci/mlx5/cmd.c +++ b/drivers/vfio/pci/mlx5/cmd.c @@ -408,7 +408,7 @@ void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf) buf->dma_dir, 0); } - /* Undo alloc_pages_bulk_array() */ + /* Undo alloc_pages_bulk() */ for_each_sgtable_page(&buf->table.sgt, &sg_iter, 0) __free_page(sg_page_iter_page(&sg_iter)); sg_free_append_table(&buf->table); @@ -431,8 +431,8 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf, return -ENOMEM; do { - filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, to_fill, - page_list); + filled = alloc_pages_bulk(GFP_KERNEL_ACCOUNT, to_fill, + page_list); if (!filled) { ret = -ENOMEM; goto err; @@ -1342,7 +1342,7 @@ static void free_recv_pages(struct mlx5_vhca_recv_buf *recv_buf) { int i; - /* Undo alloc_pages_bulk_array() */ + /* Undo alloc_pages_bulk() */ for (i = 0; i < recv_buf->npages; i++) __free_page(recv_buf->page_list[i]); @@ -1361,9 +1361,9 @@ static int alloc_recv_pages(struct mlx5_vhca_recv_buf *recv_buf, return -ENOMEM; for (;;) { - filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, - npages - done, - recv_buf->page_list + done); + filled = alloc_pages_bulk(GFP_KERNEL_ACCOUNT, + npages - done, + recv_buf->page_list + done); if (!filled) goto err; diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index a467085038f0..e5ac39c4cc6b 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -5,6 +5,8 @@ #include #include +#include +#include /* * The device memory usable to the workloads running in the VM is cached @@ -17,12 +19,21 @@ #define RESMEM_REGION_INDEX VFIO_PCI_BAR2_REGION_INDEX #define USEMEM_REGION_INDEX VFIO_PCI_BAR4_REGION_INDEX -/* Memory size expected as non cached and reserved by the VM driver */ -#define RESMEM_SIZE SZ_1G - /* A hardwired and constant ABI value between the GPU FW and VFIO driver. */ #define MEMBLK_SIZE SZ_512M +#define DVSEC_BITMAP_OFFSET 0xA +#define MIG_SUPPORTED_WITH_CACHED_RESMEM BIT(0) + +#define GPU_CAP_DVSEC_REGISTER 3 + +#define C2C_LINK_BAR0_OFFSET 0x1498 +#define HBM_TRAINING_BAR0_OFFSET 0x200BC +#define STATUS_READY 0xFF + +#define POLL_QUANTUM_MS 1000 +#define POLL_TIMEOUT_MS (30 * 1000) + /* * The state of the two device memory region - resmem and usemem - is * saved as struct mem_region. @@ -46,6 +57,7 @@ struct nvgrace_gpu_pci_core_device { struct mem_region resmem; /* Lock to control device memory kernel mapping */ struct mutex remap_lock; + bool has_mig_hw_bug; }; static void nvgrace_gpu_init_fake_bar_emu_regs(struct vfio_device *core_vdev) @@ -66,7 +78,7 @@ nvgrace_gpu_memregion(int index, if (index == USEMEM_REGION_INDEX) return &nvdev->usemem; - if (index == RESMEM_REGION_INDEX) + if (nvdev->resmem.memlength && index == RESMEM_REGION_INDEX) return &nvdev->resmem; return NULL; @@ -751,40 +763,67 @@ nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev, u64 memphys, u64 memlength) { int ret = 0; + u64 resmem_size = 0; /* - * The VM GPU device driver needs a non-cacheable region to support - * the MIG feature. Since the device memory is mapped as NORMAL cached, - * carve out a region from the end with a different NORMAL_NC - * property (called as reserved memory and represented as resmem). This - * region then is exposed as a 64b BAR (region 2 and 3) to the VM, while - * exposing the rest (termed as usable memory and represented using usemem) - * as cacheable 64b BAR (region 4 and 5). + * On Grace Hopper systems, the VM GPU device driver needs a non-cacheable + * region to support the MIG feature owing to a hardware bug. Since the + * device memory is mapped as NORMAL cached, carve out a region from the end + * with a different NORMAL_NC property (called as reserved memory and + * represented as resmem). This region then is exposed as a 64b BAR + * (region 2 and 3) to the VM, while exposing the rest (termed as usable + * memory and represented using usemem) as cacheable 64b BAR (region 4 and 5). * * devmem (memlength) * |-------------------------------------------------| * | | * usemem.memphys resmem.memphys + * + * This hardware bug is fixed on the Grace Blackwell platforms and the + * presence of the bug can be determined through nvdev->has_mig_hw_bug. + * Thus on systems with the hardware fix, there is no need to partition + * the GPU device memory and the entire memory is usable and mapped as + * NORMAL cached (i.e. resmem size is 0). */ + if (nvdev->has_mig_hw_bug) + resmem_size = SZ_1G; + nvdev->usemem.memphys = memphys; /* * The device memory exposed to the VM is added to the kernel by the - * VM driver module in chunks of memory block size. Only the usable - * memory (usemem) is added to the kernel for usage by the VM - * workloads. Make the usable memory size memblock aligned. + * VM driver module in chunks of memory block size. Note that only the + * usable memory (usemem) is added to the kernel for usage by the VM + * workloads. */ - if (check_sub_overflow(memlength, RESMEM_SIZE, + if (check_sub_overflow(memlength, resmem_size, &nvdev->usemem.memlength)) { ret = -EOVERFLOW; goto done; } /* - * The USEMEM part of the device memory has to be MEMBLK_SIZE - * aligned. This is a hardwired ABI value between the GPU FW and - * VFIO driver. The VM device driver is also aware of it and make - * use of the value for its calculation to determine USEMEM size. + * The usemem region is exposed as a 64B Bar composed of region 4 and 5. + * Calculate and save the BAR size for the region. + */ + nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength); + + /* + * If the hardware has the fix for MIG, there is no requirement + * for splitting the device memory to create RESMEM. The entire + * device memory is usable and will be USEMEM. Return here for + * such case. + */ + if (!nvdev->has_mig_hw_bug) + goto done; + + /* + * When the device memory is split to workaround the MIG bug on + * Grace Hopper, the USEMEM part of the device memory has to be + * MEMBLK_SIZE aligned. This is a hardwired ABI value between the + * GPU FW and VFIO driver. The VM device driver is also aware of it + * and make use of the value for its calculation to determine USEMEM + * size. Note that the device memory may not be 512M aligned. */ nvdev->usemem.memlength = round_down(nvdev->usemem.memlength, MEMBLK_SIZE); @@ -803,15 +842,93 @@ nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev, } /* - * The memory regions are exposed as BARs. Calculate and save - * the BAR size for them. + * The resmem region is exposed as a 64b BAR composed of region 2 and 3 + * for Grace Hopper. Calculate and save the BAR size for the region. */ - nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength); nvdev->resmem.bar_size = roundup_pow_of_two(nvdev->resmem.memlength); done: return ret; } +static bool nvgrace_gpu_has_mig_hw_bug(struct pci_dev *pdev) +{ + int pcie_dvsec; + u16 dvsec_ctrl16; + + pcie_dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_NVIDIA, + GPU_CAP_DVSEC_REGISTER); + + if (pcie_dvsec) { + pci_read_config_word(pdev, + pcie_dvsec + DVSEC_BITMAP_OFFSET, + &dvsec_ctrl16); + + if (dvsec_ctrl16 & MIG_SUPPORTED_WITH_CACHED_RESMEM) + return false; + } + + return true; +} + +/* + * To reduce the system bootup time, the HBM training has + * been moved out of the UEFI on the Grace-Blackwell systems. + * + * The onus of checking whether the HBM training has completed + * thus falls on the module. The HBM training status can be + * determined from a BAR0 register. + * + * Similarly, another BAR0 register exposes the status of the + * CPU-GPU chip-to-chip (C2C) cache coherent interconnect. + * + * Poll these register and check for 30s. If the HBM training is + * not complete or if the C2C link is not ready, fail the probe. + * + * While the wait is not required on Grace Hopper systems, it + * is beneficial to make the check to ensure the device is in an + * expected state. + * + * Ensure that the BAR0 region is enabled before accessing the + * registers. + */ +static int nvgrace_gpu_wait_device_ready(struct pci_dev *pdev) +{ + unsigned long timeout = jiffies + msecs_to_jiffies(POLL_TIMEOUT_MS); + void __iomem *io; + int ret = -ETIME; + + ret = pci_enable_device(pdev); + if (ret) + return ret; + + ret = pci_request_selected_regions(pdev, 1 << 0, KBUILD_MODNAME); + if (ret) + goto request_region_exit; + + io = pci_iomap(pdev, 0, 0); + if (!io) { + ret = -ENOMEM; + goto iomap_exit; + } + + do { + if ((ioread32(io + C2C_LINK_BAR0_OFFSET) == STATUS_READY) && + (ioread32(io + HBM_TRAINING_BAR0_OFFSET) == STATUS_READY)) { + ret = 0; + goto reg_check_exit; + } + msleep(POLL_QUANTUM_MS); + } while (!time_after(jiffies, timeout)); + +reg_check_exit: + pci_iounmap(pdev, io); +iomap_exit: + pci_release_selected_regions(pdev, 1 << 0); +request_region_exit: + pci_disable_device(pdev); + return ret; +} + static int nvgrace_gpu_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -820,6 +937,10 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev, u64 memphys, memlength; int ret; + ret = nvgrace_gpu_wait_device_ready(pdev); + if (ret) + return ret; + ret = nvgrace_gpu_fetch_memory_property(pdev, &memphys, &memlength); if (!ret) ops = &nvgrace_gpu_pci_ops; @@ -832,6 +953,8 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev, dev_set_drvdata(&pdev->dev, &nvdev->core_device); if (ops == &nvgrace_gpu_pci_ops) { + nvdev->has_mig_hw_bug = nvgrace_gpu_has_mig_hw_bug(pdev); + /* * Device memory properties are identified in the host ACPI * table. Set the nvgrace_gpu_pci_core_device structure. @@ -868,6 +991,8 @@ static const struct pci_device_id nvgrace_gpu_vfio_pci_table[] = { { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2345) }, /* GH200 SKU */ { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2348) }, + /* GB200 SKU */ + { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2941) }, {} }; diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index ea2745c1ac5e..94142581c98c 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -511,13 +511,13 @@ static void vfio_bar_fixup(struct vfio_pci_core_device *vdev) mask = ~(pci_resource_len(pdev, PCI_ROM_RESOURCE) - 1); mask |= PCI_ROM_ADDRESS_ENABLE; *vbar &= cpu_to_le32((u32)mask); - } else if (pdev->resource[PCI_ROM_RESOURCE].flags & - IORESOURCE_ROM_SHADOW) { - mask = ~(0x20000 - 1); + } else if (pdev->rom && pdev->romlen) { + mask = ~(roundup_pow_of_two(pdev->romlen) - 1); mask |= PCI_ROM_ADDRESS_ENABLE; *vbar &= cpu_to_le32((u32)mask); - } else + } else { *vbar = 0; + } vdev->bardirty = false; } @@ -1389,11 +1389,12 @@ static int vfio_ext_cap_len(struct vfio_pci_core_device *vdev, u16 ecap, u16 epo switch (ecap) { case PCI_EXT_CAP_ID_VNDR: - ret = pci_read_config_dword(pdev, epos + PCI_VSEC_HDR, &dword); + ret = pci_read_config_dword(pdev, epos + PCI_VNDR_HEADER, + &dword); if (ret) return pcibios_err_to_errno(ret); - return dword >> PCI_VSEC_HDR_LEN_SHIFT; + return PCI_VNDR_HEADER_LEN(dword); case PCI_EXT_CAP_ID_VC: case PCI_EXT_CAP_ID_VC9: case PCI_EXT_CAP_ID_MFVC: diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 1ab58da9f38a..586e49efb81b 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1054,31 +1054,27 @@ static int vfio_pci_ioctl_get_region_info(struct vfio_pci_core_device *vdev, info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); info.flags = 0; + info.size = 0; - /* Report the BAR size, not the ROM size */ - info.size = pci_resource_len(pdev, info.index); - if (!info.size) { - /* Shadow ROMs appear as PCI option ROMs */ - if (pdev->resource[PCI_ROM_RESOURCE].flags & - IORESOURCE_ROM_SHADOW) - info.size = 0x20000; - else - break; - } - - /* - * Is it really there? Enable memory decode for implicit access - * in pci_map_rom(). - */ - cmd = vfio_pci_memory_lock_and_enable(vdev); - io = pci_map_rom(pdev, &size); - if (io) { + if (pci_resource_start(pdev, PCI_ROM_RESOURCE)) { + /* + * Check ROM content is valid. Need to enable memory + * decode for ROM access in pci_map_rom(). + */ + cmd = vfio_pci_memory_lock_and_enable(vdev); + io = pci_map_rom(pdev, &size); + if (io) { + info.flags = VFIO_REGION_INFO_FLAG_READ; + /* Report the BAR size, not the ROM size. */ + info.size = pci_resource_len(pdev, PCI_ROM_RESOURCE); + pci_unmap_rom(pdev, io); + } + vfio_pci_memory_unlock_and_restore(vdev, cmd); + } else if (pdev->rom && pdev->romlen) { info.flags = VFIO_REGION_INFO_FLAG_READ; - pci_unmap_rom(pdev, io); - } else { - info.size = 0; + /* Report BAR size as power of two. */ + info.size = roundup_pow_of_two(pdev->romlen); } - vfio_pci_memory_unlock_and_restore(vdev, cmd); break; } @@ -1661,14 +1657,15 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff; vm_fault_t ret = VM_FAULT_SIGBUS; - if (order && (vmf->address & ((PAGE_SIZE << order) - 1) || + pfn = vma_to_pfn(vma) + pgoff; + + if (order && (pfn & ((1 << order) - 1) || + vmf->address & ((PAGE_SIZE << order) - 1) || vmf->address + (PAGE_SIZE << order) > vma->vm_end)) { ret = VM_FAULT_FALLBACK; goto out; } - pfn = vma_to_pfn(vma); - down_read(&vdev->memory_lock); if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) @@ -1676,18 +1673,18 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, switch (order) { case 0: - ret = vmf_insert_pfn(vma, vmf->address, pfn + pgoff); + ret = vmf_insert_pfn(vma, vmf->address, pfn); break; #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP case PMD_ORDER: - ret = vmf_insert_pfn_pmd(vmf, __pfn_to_pfn_t(pfn + pgoff, - PFN_DEV), false); + ret = vmf_insert_pfn_pmd(vmf, + __pfn_to_pfn_t(pfn, PFN_DEV), false); break; #endif #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP case PUD_ORDER: - ret = vmf_insert_pfn_pud(vmf, __pfn_to_pfn_t(pfn + pgoff, - PFN_DEV), false); + ret = vmf_insert_pfn_pud(vmf, + __pfn_to_pfn_t(pfn, PFN_DEV), false); break; #endif default: diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 66b72c289284..6192788c8ba3 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "vfio_pci_priv.h" @@ -61,9 +62,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_iowrite##size); VFIO_IOWRITE(8) VFIO_IOWRITE(16) VFIO_IOWRITE(32) -#ifdef iowrite64 VFIO_IOWRITE(64) -#endif #define VFIO_IOREAD(size) \ int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev, \ @@ -89,9 +88,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_ioread##size); VFIO_IOREAD(8) VFIO_IOREAD(16) VFIO_IOREAD(32) -#ifdef ioread64 VFIO_IOREAD(64) -#endif #define VFIO_IORDWR(size) \ static int vfio_pci_iordwr##size(struct vfio_pci_core_device *vdev,\ @@ -127,9 +124,7 @@ static int vfio_pci_iordwr##size(struct vfio_pci_core_device *vdev,\ VFIO_IORDWR(8) VFIO_IORDWR(16) VFIO_IORDWR(32) -#if defined(ioread64) && defined(iowrite64) VFIO_IORDWR(64) -#endif /* * Read or write from an __iomem region (MMIO or I/O port) with an excluded @@ -155,7 +150,6 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, else fillable = 0; -#if defined(ioread64) && defined(iowrite64) if (fillable >= 8 && !(off % 8)) { ret = vfio_pci_iordwr64(vdev, iswrite, test_mem, io, buf, off, &filled); @@ -163,7 +157,6 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, return ret; } else -#endif if (fillable >= 4 && !(off % 4)) { ret = vfio_pci_iordwr32(vdev, iswrite, test_mem, io, buf, off, &filled); @@ -244,9 +237,8 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, if (pci_resource_start(pdev, bar)) end = pci_resource_len(pdev, bar); - else if (bar == PCI_ROM_RESOURCE && - pdev->resource[bar].flags & IORESOURCE_ROM_SHADOW) - end = 0x20000; + else if (bar == PCI_ROM_RESOURCE && pdev->rom && pdev->romlen) + end = roundup_pow_of_two(pdev->romlen); else return -EINVAL; @@ -261,11 +253,14 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, * excluded range at the end of the actual ROM. This makes * filling large ROM BARs much faster. */ - io = pci_map_rom(pdev, &x_start); - if (!io) { - done = -ENOMEM; - goto out; + if (pci_resource_start(pdev, bar)) { + io = pci_map_rom(pdev, &x_start); + } else { + io = ioremap(pdev->rom, pdev->romlen); + x_start = pdev->romlen; } + if (!io) + return -ENOMEM; x_end = end; } else { int ret = vfio_pci_core_setup_barmap(vdev, bar); @@ -288,8 +283,13 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, if (done >= 0) *ppos += done; - if (bar == PCI_ROM_RESOURCE) - pci_unmap_rom(pdev, io); + if (bar == PCI_ROM_RESOURCE) { + if (pci_resource_start(pdev, bar)) + pci_unmap_rom(pdev, io); + else + iounmap(io); + } + out: return done; } @@ -381,12 +381,10 @@ static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd, vfio_pci_core_iowrite32(ioeventfd->vdev, test_mem, ioeventfd->data, ioeventfd->addr); break; -#ifdef iowrite64 case 8: vfio_pci_core_iowrite64(ioeventfd->vdev, test_mem, ioeventfd->data, ioeventfd->addr); break; -#endif } } @@ -440,10 +438,8 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, pos >= vdev->msix_offset + vdev->msix_size)) return -EINVAL; -#ifndef iowrite64 if (count == 8) return -EINVAL; -#endif ret = vfio_pci_core_setup_barmap(vdev, bar); if (ret) diff --git a/drivers/vfio/pci/virtio/migrate.c b/drivers/vfio/pci/virtio/migrate.c index ee54f4c17857..ba92bb4e9af9 100644 --- a/drivers/vfio/pci/virtio/migrate.c +++ b/drivers/vfio/pci/virtio/migrate.c @@ -77,8 +77,8 @@ static int virtiovf_add_migration_pages(struct virtiovf_data_buffer *buf, return -ENOMEM; do { - filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, to_fill, - page_list); + filled = alloc_pages_bulk(GFP_KERNEL_ACCOUNT, to_fill, + page_list); if (!filled) { ret = -ENOMEM; goto err; @@ -112,7 +112,7 @@ static void virtiovf_free_data_buffer(struct virtiovf_data_buffer *buf) { struct sg_page_iter sg_iter; - /* Undo alloc_pages_bulk_array() */ + /* Undo alloc_pages_bulk() */ for_each_sgtable_page(&buf->table.sgt, &sg_iter, 0) __free_page(sg_page_iter_page(&sg_iter)); sg_free_append_table(&buf->table); diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index e53757d1d095..3bf1043cd795 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -388,6 +388,11 @@ static ssize_t vfio_platform_read_mmio(struct vfio_platform_region *reg, { unsigned int done = 0; + if (off >= reg->size) + return -EINVAL; + + count = min_t(size_t, count, reg->size - off); + if (!reg->ioaddr) { reg->ioaddr = ioremap(reg->addr, reg->size); @@ -467,6 +472,11 @@ static ssize_t vfio_platform_write_mmio(struct vfio_platform_region *reg, { unsigned int done = 0; + if (off >= reg->size) + return -EINVAL; + + count = min_t(size_t, count, reg->size - off); + if (!reg->ioaddr) { reg->ioaddr = ioremap(reg->addr, reg->size); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 9ad37c012189..b9b9e9d40951 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1107,6 +1107,7 @@ static void handle_rx(struct vhost_net *net) size_t vhost_hlen, sock_hlen; size_t vhost_len, sock_len; bool busyloop_intr = false; + bool set_num_buffers; struct socket *sock; struct iov_iter fixup; __virtio16 num_buffers; @@ -1129,6 +1130,8 @@ static void handle_rx(struct vhost_net *net) vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ? vq->log : NULL; mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF); + set_num_buffers = mergeable || + vhost_has_feature(vq, VIRTIO_F_VERSION_1); do { sock_len = vhost_net_rx_peek_head_len(net, sock->sk, @@ -1205,7 +1208,7 @@ static void handle_rx(struct vhost_net *net) /* TODO: Should check and handle checksum. */ num_buffers = cpu_to_vhost16(vq, headcount); - if (likely(mergeable) && + if (likely(set_num_buffers) && copy_to_iter(&num_buffers, sizeof num_buffers, &fixup) != sizeof num_buffers) { vq_err(vq, "Failed num_buffers write"); diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index de035071fedb..55c6686f091e 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -649,6 +649,7 @@ config FB_S1D13XXX config FB_ATMEL tristate "AT91 LCD Controller support" depends on FB && OF && HAVE_CLK && HAS_IOMEM + depends on BACKLIGHT_CLASS_DEVICE depends on HAVE_FB_ATMEL || COMPILE_TEST select FB_BACKLIGHT select FB_IOMEM_HELPERS @@ -660,7 +661,6 @@ config FB_ATMEL config FB_NVIDIA tristate "nVidia Framebuffer Support" depends on FB && PCI - select FB_BACKLIGHT if FB_NVIDIA_BACKLIGHT select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT @@ -700,6 +700,8 @@ config FB_NVIDIA_DEBUG config FB_NVIDIA_BACKLIGHT bool "Support for backlight control" depends on FB_NVIDIA + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_NVIDIA + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -707,7 +709,6 @@ config FB_NVIDIA_BACKLIGHT config FB_RIVA tristate "nVidia Riva support" depends on FB && PCI - select FB_BACKLIGHT if FB_RIVA_BACKLIGHT select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT @@ -747,6 +748,8 @@ config FB_RIVA_DEBUG config FB_RIVA_BACKLIGHT bool "Support for backlight control" depends on FB_RIVA + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_RIVA + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -934,7 +937,6 @@ config FB_MATROX_MAVEN config FB_RADEON tristate "ATI Radeon display support" depends on FB && PCI - select FB_BACKLIGHT if FB_RADEON_BACKLIGHT select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT @@ -960,6 +962,8 @@ config FB_RADEON_I2C config FB_RADEON_BACKLIGHT bool "Support for backlight control" depends on FB_RADEON + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_RADEON + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -975,7 +979,6 @@ config FB_RADEON_DEBUG config FB_ATY128 tristate "ATI Rage128 display support" depends on FB && PCI - select FB_BACKLIGHT if FB_ATY128_BACKLIGHT select FB_IOMEM_HELPERS select FB_MACMODES if PPC_PMAC help @@ -989,6 +992,8 @@ config FB_ATY128 config FB_ATY128_BACKLIGHT bool "Support for backlight control" depends on FB_ATY128 + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_ATY128 + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -999,7 +1004,6 @@ config FB_ATY select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT - select FB_BACKLIGHT if FB_ATY_BACKLIGHT select FB_IOMEM_FOPS select FB_MACMODES if PPC select FB_ATY_CT if SPARC64 && PCI @@ -1040,6 +1044,8 @@ config FB_ATY_GX config FB_ATY_BACKLIGHT bool "Support for backlight control" depends on FB_ATY + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_ATY + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -1528,6 +1534,7 @@ config FB_SH_MOBILE_LCDC depends on FB && HAVE_CLK && HAS_IOMEM depends on SUPERH || COMPILE_TEST depends on FB_DEVICE + depends on BACKLIGHT_CLASS_DEVICE select FB_BACKLIGHT select FB_DEFERRED_IO select FB_DMAMEM_HELPERS @@ -1793,6 +1800,7 @@ config FB_SSD1307 tristate "Solomon SSD1307 framebuffer support" depends on FB && I2C depends on GPIOLIB || COMPILE_TEST + depends on BACKLIGHT_CLASS_DEVICE select FB_BACKLIGHT select FB_SYSMEM_HELPERS_DEFERRED help diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c index 36bfb6deb8ab..d866608da8d1 100644 --- a/drivers/video/fbdev/aty/radeon_base.c +++ b/drivers/video/fbdev/aty/radeon_base.c @@ -2199,7 +2199,7 @@ static ssize_t radeon_show_one_edid(char *buf, loff_t off, size_t count, const u static ssize_t radeon_show_edid1(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -2211,7 +2211,7 @@ static ssize_t radeon_show_edid1(struct file *filp, struct kobject *kobj, static ssize_t radeon_show_edid2(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -2227,7 +2227,7 @@ static const struct bin_attribute edid1_attr = { .mode = 0444, }, .size = EDID_LENGTH, - .read = radeon_show_edid1, + .read_new = radeon_show_edid1, }; static const struct bin_attribute edid2_attr = { @@ -2236,7 +2236,7 @@ static const struct bin_attribute edid2_attr = { .mode = 0444, }, .size = EDID_LENGTH, - .read = radeon_show_edid2, + .read_new = radeon_show_edid2, }; static int radeonfb_pci_register(struct pci_dev *pdev, diff --git a/drivers/video/fbdev/core/Kconfig b/drivers/video/fbdev/core/Kconfig index 0ab8848ba2f1..d554d8c543d4 100644 --- a/drivers/video/fbdev/core/Kconfig +++ b/drivers/video/fbdev/core/Kconfig @@ -183,9 +183,8 @@ config FB_SYSMEM_HELPERS_DEFERRED select FB_SYSMEM_HELPERS config FB_BACKLIGHT - tristate + bool depends on FB - select BACKLIGHT_CLASS_DEVICE config FB_MODE_HELPERS bool "Enable Video Mode Handling Helpers" diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 20517448487e..0e1bd3dba255 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -275,7 +275,7 @@ static const struct fb_ops efifb_ops = { .fb_setcolreg = efifb_setcolreg, }; -static int efifb_setup(struct screen_info *si, char *options) +static void efifb_setup(struct screen_info *si, char *options) { char *this_opt; @@ -299,8 +299,6 @@ static int efifb_setup(struct screen_info *si, char *options) use_bgrt = false; } } - - return 0; } static inline bool fb_base_is_valid(struct screen_info *si) diff --git a/drivers/video/fbdev/omap/lcd_dma.c b/drivers/video/fbdev/omap/lcd_dma.c index f85817635a8c..0da23c57e475 100644 --- a/drivers/video/fbdev/omap/lcd_dma.c +++ b/drivers/video/fbdev/omap/lcd_dma.c @@ -432,8 +432,8 @@ static int __init omap_init_lcd_dma(void) spin_lock_init(&lcd_dma.lock); - r = request_irq(INT_DMA_LCD, lcd_dma_irq_handler, 0, - "LCD DMA", NULL); + r = request_threaded_irq(INT_DMA_LCD, NULL, lcd_dma_irq_handler, + IRQF_ONESHOT, "LCD DMA", NULL); if (r != 0) pr_err("unable to request IRQ for LCD DMA (error %d)\n", r); diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c index c3329c8b4c16..ccb96a5be07e 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c @@ -3933,18 +3933,13 @@ static int dispc_bind(struct device *dev, struct device *master, void *data) return -ENODEV; } - if (np && of_property_read_bool(np, "syscon-pol")) { - dispc.syscon_pol = syscon_regmap_lookup_by_phandle(np, "syscon-pol"); + if (np && of_property_present(np, "syscon-pol")) { + dispc.syscon_pol = syscon_regmap_lookup_by_phandle_args(np, "syscon-pol", + 1, &dispc.syscon_pol_offset); if (IS_ERR(dispc.syscon_pol)) { dev_err(&pdev->dev, "failed to get syscon-pol regmap\n"); return PTR_ERR(dispc.syscon_pol); } - - if (of_property_read_u32_index(np, "syscon-pol", 1, - &dispc.syscon_pol_offset)) { - dev_err(&pdev->dev, "failed to get syscon-pol offset\n"); - return -EINVAL; - } } pm_runtime_enable(&pdev->dev); diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c index c04cbe0ef173..7c636db79882 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c @@ -36,6 +36,7 @@ struct device_node *dss_of_port_get_parent_device(struct device_node *port) np = of_get_next_parent(np); } + of_node_put(np); return NULL; } diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c index b33f62c5cb22..bb7fe54dd019 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c @@ -567,23 +567,6 @@ static void hdmi_core_enable_interrupts(struct hdmi_core_data *core) REG_FLD_MOD(core->base, HDMI_CORE_IH_MUTE, 0x0, 1, 0); } -int hdmi5_core_handle_irqs(struct hdmi_core_data *core) -{ - void __iomem *base = core->base; - - REG_FLD_MOD(base, HDMI_CORE_IH_FC_STAT0, 0xff, 7, 0); - REG_FLD_MOD(base, HDMI_CORE_IH_FC_STAT1, 0xff, 7, 0); - REG_FLD_MOD(base, HDMI_CORE_IH_FC_STAT2, 0xff, 7, 0); - REG_FLD_MOD(base, HDMI_CORE_IH_AS_STAT0, 0xff, 7, 0); - REG_FLD_MOD(base, HDMI_CORE_IH_PHY_STAT0, 0xff, 7, 0); - REG_FLD_MOD(base, HDMI_CORE_IH_I2CM_STAT0, 0xff, 7, 0); - REG_FLD_MOD(base, HDMI_CORE_IH_CEC_STAT0, 0xff, 7, 0); - REG_FLD_MOD(base, HDMI_CORE_IH_VP_STAT0, 0xff, 7, 0); - REG_FLD_MOD(base, HDMI_CORE_IH_I2CMPHY_STAT0, 0xff, 7, 0); - - return 0; -} - void hdmi5_configure(struct hdmi_core_data *core, struct hdmi_wp_data *wp, struct hdmi_config *cfg) { diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.h b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.h index 192c9b6e2f7b..493857374a15 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.h +++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.h @@ -283,7 +283,6 @@ struct csc_table { int hdmi5_read_edid(struct hdmi_core_data *core, u8 *edid, int len); void hdmi5_core_dump(struct hdmi_core_data *core, struct seq_file *s); -int hdmi5_core_handle_irqs(struct hdmi_core_data *core); void hdmi5_configure(struct hdmi_core_data *core, struct hdmi_wp_data *wp, struct hdmi_config *cfg); int hdmi5_core_init(struct platform_device *pdev, struct hdmi_core_data *core); diff --git a/drivers/video/fbdev/sh_mobile_lcdcfb.c b/drivers/video/fbdev/sh_mobile_lcdcfb.c index 935cd8413ed5..4715dcb59811 100644 --- a/drivers/video/fbdev/sh_mobile_lcdcfb.c +++ b/drivers/video/fbdev/sh_mobile_lcdcfb.c @@ -2123,11 +2123,7 @@ sh_mobile_lcdc_channel_fb_init(struct sh_mobile_lcdc_chan *ch, static int sh_mobile_lcdc_update_bl(struct backlight_device *bdev) { struct sh_mobile_lcdc_chan *ch = bl_get_data(bdev); - int brightness = bdev->props.brightness; - - if (bdev->props.power != BACKLIGHT_POWER_ON || - bdev->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK)) - brightness = 0; + int brightness = backlight_get_brightness(bdev); ch->bl_brightness = brightness; return ch->cfg->bl_info.set_brightness(brightness); diff --git a/drivers/video/fbdev/sm501fb.c b/drivers/video/fbdev/sm501fb.c index 86ecbb2d86db..7734377b2d87 100644 --- a/drivers/video/fbdev/sm501fb.c +++ b/drivers/video/fbdev/sm501fb.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -1712,8 +1713,8 @@ static int sm501fb_init_fb(struct fb_info *fb, enum sm501_controller head, BUG(); } - dev_info(info->dev, "fb %s %sabled at start\n", - fbname, enable ? "en" : "dis"); + dev_info(info->dev, "fb %s %s at start\n", + fbname, str_enabled_disabled(enable)); /* check to see if our routing allows this */ diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index 71ac9e36f67c..acadf0eb450c 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -1416,7 +1416,7 @@ static ssize_t metrics_cpu_kcycles_used_show(struct device *fbdev, static ssize_t edid_show( struct file *filp, - struct kobject *kobj, struct bin_attribute *a, + struct kobject *kobj, const struct bin_attribute *a, char *buf, loff_t off, size_t count) { struct device *fbdev = kobj_to_dev(kobj); struct fb_info *fb_info = dev_get_drvdata(fbdev); @@ -1438,7 +1438,7 @@ static ssize_t edid_show( static ssize_t edid_store( struct file *filp, - struct kobject *kobj, struct bin_attribute *a, + struct kobject *kobj, const struct bin_attribute *a, char *src, loff_t src_off, size_t src_size) { struct device *fbdev = kobj_to_dev(kobj); struct fb_info *fb_info = dev_get_drvdata(fbdev); @@ -1482,8 +1482,8 @@ static const struct bin_attribute edid_attr = { .attr.name = "edid", .attr.mode = 0666, .size = EDID_LENGTH, - .read = edid_show, - .write = edid_store + .read_new = edid_show, + .write_new = edid_store }; static const struct device_attribute fb_device_attrs[] = { diff --git a/drivers/video/fbdev/vga16fb.c b/drivers/video/fbdev/vga16fb.c index fce0f5db7ba3..eedab14c7d51 100644 --- a/drivers/video/fbdev/vga16fb.c +++ b/drivers/video/fbdev/vga16fb.c @@ -185,9 +185,10 @@ static inline void setindex(int index) /* Check if the video mode is supported by the driver */ static inline int check_mode_supported(const struct screen_info *si) { + unsigned int type = screen_info_video_type(si); + /* only EGA and VGA in 16 color graphic mode are supported */ - if (si->orig_video_isVGA != VIDEO_TYPE_EGAC && - si->orig_video_isVGA != VIDEO_TYPE_VGAC) + if (type != VIDEO_TYPE_EGAC && type != VIDEO_TYPE_VGAC) return -ENODEV; if (si->orig_video_mode != 0x0D && /* 320x200/4 (EGA) */ @@ -1338,7 +1339,7 @@ static int vga16fb_probe(struct platform_device *dev) printk(KERN_INFO "vga16fb: mapped to 0x%p\n", info->screen_base); par = info->par; - par->isVGA = si->orig_video_isVGA == VIDEO_TYPE_VGAC; + par->isVGA = screen_info_video_type(si) == VIDEO_TYPE_VGAC; par->palette_blanked = 0; par->vesa_blanked = 0; diff --git a/drivers/video/hdmi.c b/drivers/video/hdmi.c index ba301f3f4951..45b42f14a750 100644 --- a/drivers/video/hdmi.c +++ b/drivers/video/hdmi.c @@ -894,34 +894,6 @@ hdmi_vendor_any_infoframe_pack(union hdmi_vendor_any_infoframe *frame, return hdmi_vendor_any_infoframe_pack_only(frame, buffer, size); } -/** - * hdmi_infoframe_check() - check a HDMI infoframe - * @frame: HDMI infoframe - * - * Validates that the infoframe is consistent and updates derived fields - * (eg. length) based on other fields. - * - * Returns 0 on success or a negative error code on failure. - */ -int -hdmi_infoframe_check(union hdmi_infoframe *frame) -{ - switch (frame->any.type) { - case HDMI_INFOFRAME_TYPE_AVI: - return hdmi_avi_infoframe_check(&frame->avi); - case HDMI_INFOFRAME_TYPE_SPD: - return hdmi_spd_infoframe_check(&frame->spd); - case HDMI_INFOFRAME_TYPE_AUDIO: - return hdmi_audio_infoframe_check(&frame->audio); - case HDMI_INFOFRAME_TYPE_VENDOR: - return hdmi_vendor_any_infoframe_check(&frame->vendor); - default: - WARN(1, "Bad infoframe type %d\n", frame->any.type); - return -EINVAL; - } -} -EXPORT_SYMBOL(hdmi_infoframe_check); - /** * hdmi_infoframe_pack_only() - write a HDMI infoframe to binary buffer * @frame: HDMI infoframe diff --git a/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c index 488153879ec9..87f162736b2e 100644 --- a/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c +++ b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -219,6 +220,13 @@ static void __exit arm_cca_guest_exit(void) } module_exit(arm_cca_guest_exit); +/* modalias, so userspace can autoload this module when RSI is available */ +static const struct platform_device_id arm_cca_match[] __maybe_unused = { + { RSI_PDEV_NAME, 0}, + { } +}; + +MODULE_DEVICE_TABLE(platform, arm_cca_match); MODULE_AUTHOR("Sami Mujawar "); MODULE_DESCRIPTION("Arm CCA Guest TSM Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig index 0b772bd921d8..a6405ab6c2c3 100644 --- a/drivers/virt/coco/sev-guest/Kconfig +++ b/drivers/virt/coco/sev-guest/Kconfig @@ -2,7 +2,6 @@ config SEV_GUEST tristate "AMD SEV Guest driver" default m depends on AMD_MEM_ENCRYPT - select CRYPTO_LIB_AESGCM select TSM_REPORTS help SEV-SNP firmware provides the guest a mechanism to communicate with diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index b699771be029..264b6523fe52 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -31,9 +31,6 @@ #define DEVICE_NAME "sev-guest" -#define SNP_REQ_MAX_RETRY_DURATION (60*HZ) -#define SNP_REQ_RETRY_DELAY (2*HZ) - #define SVSM_MAX_RETRIES 3 struct snp_guest_dev { @@ -60,86 +57,6 @@ static int vmpck_id = -1; module_param(vmpck_id, int, 0444); MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP."); -/* Mutex to serialize the shared buffer access and command handling. */ -static DEFINE_MUTEX(snp_cmd_mutex); - -static bool is_vmpck_empty(struct snp_msg_desc *mdesc) -{ - char zero_key[VMPCK_KEY_LEN] = {0}; - - if (mdesc->vmpck) - return !memcmp(mdesc->vmpck, zero_key, VMPCK_KEY_LEN); - - return true; -} - -/* - * If an error is received from the host or AMD Secure Processor (ASP) there - * are two options. Either retry the exact same encrypted request or discontinue - * using the VMPCK. - * - * This is because in the current encryption scheme GHCB v2 uses AES-GCM to - * encrypt the requests. The IV for this scheme is the sequence number. GCM - * cannot tolerate IV reuse. - * - * The ASP FW v1.51 only increments the sequence numbers on a successful - * guest<->ASP back and forth and only accepts messages at its exact sequence - * number. - * - * So if the sequence number were to be reused the encryption scheme is - * vulnerable. If the sequence number were incremented for a fresh IV the ASP - * will reject the request. - */ -static void snp_disable_vmpck(struct snp_msg_desc *mdesc) -{ - pr_alert("Disabling VMPCK%d communication key to prevent IV reuse.\n", - vmpck_id); - memzero_explicit(mdesc->vmpck, VMPCK_KEY_LEN); - mdesc->vmpck = NULL; -} - -static inline u64 __snp_get_msg_seqno(struct snp_msg_desc *mdesc) -{ - u64 count; - - lockdep_assert_held(&snp_cmd_mutex); - - /* Read the current message sequence counter from secrets pages */ - count = *mdesc->os_area_msg_seqno; - - return count + 1; -} - -/* Return a non-zero on success */ -static u64 snp_get_msg_seqno(struct snp_msg_desc *mdesc) -{ - u64 count = __snp_get_msg_seqno(mdesc); - - /* - * The message sequence counter for the SNP guest request is a 64-bit - * value but the version 2 of GHCB specification defines a 32-bit storage - * for it. If the counter exceeds the 32-bit value then return zero. - * The caller should check the return value, but if the caller happens to - * not check the value and use it, then the firmware treats zero as an - * invalid number and will fail the message request. - */ - if (count >= UINT_MAX) { - pr_err("request message sequence counter overflow\n"); - return 0; - } - - return count; -} - -static void snp_inc_msg_seqno(struct snp_msg_desc *mdesc) -{ - /* - * The counter is also incremented by the PSP, so increment it by 2 - * and save in secrets page. - */ - *mdesc->os_area_msg_seqno += 2; -} - static inline struct snp_guest_dev *to_snp_dev(struct file *file) { struct miscdevice *dev = file->private_data; @@ -147,242 +64,6 @@ static inline struct snp_guest_dev *to_snp_dev(struct file *file) return container_of(dev, struct snp_guest_dev, misc); } -static struct aesgcm_ctx *snp_init_crypto(u8 *key, size_t keylen) -{ - struct aesgcm_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); - if (!ctx) - return NULL; - - if (aesgcm_expandkey(ctx, key, keylen, AUTHTAG_LEN)) { - pr_err("Crypto context initialization failed\n"); - kfree(ctx); - return NULL; - } - - return ctx; -} - -static int verify_and_dec_payload(struct snp_msg_desc *mdesc, struct snp_guest_req *req) -{ - struct snp_guest_msg *resp_msg = &mdesc->secret_response; - struct snp_guest_msg *req_msg = &mdesc->secret_request; - struct snp_guest_msg_hdr *req_msg_hdr = &req_msg->hdr; - struct snp_guest_msg_hdr *resp_msg_hdr = &resp_msg->hdr; - struct aesgcm_ctx *ctx = mdesc->ctx; - u8 iv[GCM_AES_IV_SIZE] = {}; - - pr_debug("response [seqno %lld type %d version %d sz %d]\n", - resp_msg_hdr->msg_seqno, resp_msg_hdr->msg_type, resp_msg_hdr->msg_version, - resp_msg_hdr->msg_sz); - - /* Copy response from shared memory to encrypted memory. */ - memcpy(resp_msg, mdesc->response, sizeof(*resp_msg)); - - /* Verify that the sequence counter is incremented by 1 */ - if (unlikely(resp_msg_hdr->msg_seqno != (req_msg_hdr->msg_seqno + 1))) - return -EBADMSG; - - /* Verify response message type and version number. */ - if (resp_msg_hdr->msg_type != (req_msg_hdr->msg_type + 1) || - resp_msg_hdr->msg_version != req_msg_hdr->msg_version) - return -EBADMSG; - - /* - * If the message size is greater than our buffer length then return - * an error. - */ - if (unlikely((resp_msg_hdr->msg_sz + ctx->authsize) > req->resp_sz)) - return -EBADMSG; - - /* Decrypt the payload */ - memcpy(iv, &resp_msg_hdr->msg_seqno, min(sizeof(iv), sizeof(resp_msg_hdr->msg_seqno))); - if (!aesgcm_decrypt(ctx, req->resp_buf, resp_msg->payload, resp_msg_hdr->msg_sz, - &resp_msg_hdr->algo, AAD_LEN, iv, resp_msg_hdr->authtag)) - return -EBADMSG; - - return 0; -} - -static int enc_payload(struct snp_msg_desc *mdesc, u64 seqno, struct snp_guest_req *req) -{ - struct snp_guest_msg *msg = &mdesc->secret_request; - struct snp_guest_msg_hdr *hdr = &msg->hdr; - struct aesgcm_ctx *ctx = mdesc->ctx; - u8 iv[GCM_AES_IV_SIZE] = {}; - - memset(msg, 0, sizeof(*msg)); - - hdr->algo = SNP_AEAD_AES_256_GCM; - hdr->hdr_version = MSG_HDR_VER; - hdr->hdr_sz = sizeof(*hdr); - hdr->msg_type = req->msg_type; - hdr->msg_version = req->msg_version; - hdr->msg_seqno = seqno; - hdr->msg_vmpck = req->vmpck_id; - hdr->msg_sz = req->req_sz; - - /* Verify the sequence number is non-zero */ - if (!hdr->msg_seqno) - return -ENOSR; - - pr_debug("request [seqno %lld type %d version %d sz %d]\n", - hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz); - - if (WARN_ON((req->req_sz + ctx->authsize) > sizeof(msg->payload))) - return -EBADMSG; - - memcpy(iv, &hdr->msg_seqno, min(sizeof(iv), sizeof(hdr->msg_seqno))); - aesgcm_encrypt(ctx, msg->payload, req->req_buf, req->req_sz, &hdr->algo, - AAD_LEN, iv, hdr->authtag); - - return 0; -} - -static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, - struct snp_guest_request_ioctl *rio) -{ - unsigned long req_start = jiffies; - unsigned int override_npages = 0; - u64 override_err = 0; - int rc; - -retry_request: - /* - * Call firmware to process the request. In this function the encrypted - * message enters shared memory with the host. So after this call the - * sequence number must be incremented or the VMPCK must be deleted to - * prevent reuse of the IV. - */ - rc = snp_issue_guest_request(req, &mdesc->input, rio); - switch (rc) { - case -ENOSPC: - /* - * If the extended guest request fails due to having too - * small of a certificate data buffer, retry the same - * guest request without the extended data request in - * order to increment the sequence number and thus avoid - * IV reuse. - */ - override_npages = mdesc->input.data_npages; - req->exit_code = SVM_VMGEXIT_GUEST_REQUEST; - - /* - * Override the error to inform callers the given extended - * request buffer size was too small and give the caller the - * required buffer size. - */ - override_err = SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN); - - /* - * If this call to the firmware succeeds, the sequence number can - * be incremented allowing for continued use of the VMPCK. If - * there is an error reflected in the return value, this value - * is checked further down and the result will be the deletion - * of the VMPCK and the error code being propagated back to the - * user as an ioctl() return code. - */ - goto retry_request; - - /* - * The host may return SNP_GUEST_VMM_ERR_BUSY if the request has been - * throttled. Retry in the driver to avoid returning and reusing the - * message sequence number on a different message. - */ - case -EAGAIN: - if (jiffies - req_start > SNP_REQ_MAX_RETRY_DURATION) { - rc = -ETIMEDOUT; - break; - } - schedule_timeout_killable(SNP_REQ_RETRY_DELAY); - goto retry_request; - } - - /* - * Increment the message sequence number. There is no harm in doing - * this now because decryption uses the value stored in the response - * structure and any failure will wipe the VMPCK, preventing further - * use anyway. - */ - snp_inc_msg_seqno(mdesc); - - if (override_err) { - rio->exitinfo2 = override_err; - - /* - * If an extended guest request was issued and the supplied certificate - * buffer was not large enough, a standard guest request was issued to - * prevent IV reuse. If the standard request was successful, return -EIO - * back to the caller as would have originally been returned. - */ - if (!rc && override_err == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) - rc = -EIO; - } - - if (override_npages) - mdesc->input.data_npages = override_npages; - - return rc; -} - -static int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, - struct snp_guest_request_ioctl *rio) -{ - u64 seqno; - int rc; - - guard(mutex)(&snp_cmd_mutex); - - /* Check if the VMPCK is not empty */ - if (is_vmpck_empty(mdesc)) { - pr_err_ratelimited("VMPCK is disabled\n"); - return -ENOTTY; - } - - /* Get message sequence and verify that its a non-zero */ - seqno = snp_get_msg_seqno(mdesc); - if (!seqno) - return -EIO; - - /* Clear shared memory's response for the host to populate. */ - memset(mdesc->response, 0, sizeof(struct snp_guest_msg)); - - /* Encrypt the userspace provided payload in mdesc->secret_request. */ - rc = enc_payload(mdesc, seqno, req); - if (rc) - return rc; - - /* - * Write the fully encrypted request to the shared unencrypted - * request page. - */ - memcpy(mdesc->request, &mdesc->secret_request, - sizeof(mdesc->secret_request)); - - rc = __handle_guest_request(mdesc, req, rio); - if (rc) { - if (rc == -EIO && - rio->exitinfo2 == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) - return rc; - - pr_alert("Detected error from ASP request. rc: %d, exitinfo2: 0x%llx\n", - rc, rio->exitinfo2); - - snp_disable_vmpck(mdesc); - return rc; - } - - rc = verify_and_dec_payload(mdesc, req); - if (rc) { - pr_alert("Detected unexpected decode failure from ASP. rc: %d\n", rc); - snp_disable_vmpck(mdesc); - return rc; - } - - return 0; -} - struct snp_req_resp { sockptr_t req_data; sockptr_t resp_data; @@ -414,7 +95,7 @@ static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_io req.msg_version = arg->msg_version; req.msg_type = SNP_MSG_REPORT_REQ; - req.vmpck_id = vmpck_id; + req.vmpck_id = mdesc->vmpck_id; req.req_buf = report_req; req.req_sz = sizeof(*report_req); req.resp_buf = report_resp->data; @@ -461,7 +142,7 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque req.msg_version = arg->msg_version; req.msg_type = SNP_MSG_KEY_REQ; - req.vmpck_id = vmpck_id; + req.vmpck_id = mdesc->vmpck_id; req.req_buf = derived_key_req; req.req_sz = sizeof(*derived_key_req); req.resp_buf = buf; @@ -539,7 +220,7 @@ cmd: req.msg_version = arg->msg_version; req.msg_type = SNP_MSG_REPORT_REQ; - req.vmpck_id = vmpck_id; + req.vmpck_id = mdesc->vmpck_id; req.req_buf = &report_req->data; req.req_sz = sizeof(report_req->data); req.resp_buf = report_resp->data; @@ -616,76 +297,11 @@ static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long return ret; } -static void free_shared_pages(void *buf, size_t sz) -{ - unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - int ret; - - if (!buf) - return; - - ret = set_memory_encrypted((unsigned long)buf, npages); - if (ret) { - WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); - return; - } - - __free_pages(virt_to_page(buf), get_order(sz)); -} - -static void *alloc_shared_pages(struct device *dev, size_t sz) -{ - unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - struct page *page; - int ret; - - page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz)); - if (!page) - return NULL; - - ret = set_memory_decrypted((unsigned long)page_address(page), npages); - if (ret) { - dev_err(dev, "failed to mark page shared, ret=%d\n", ret); - __free_pages(page, get_order(sz)); - return NULL; - } - - return page_address(page); -} - static const struct file_operations snp_guest_fops = { .owner = THIS_MODULE, .unlocked_ioctl = snp_guest_ioctl, }; -static u8 *get_vmpck(int id, struct snp_secrets_page *secrets, u32 **seqno) -{ - u8 *key = NULL; - - switch (id) { - case 0: - *seqno = &secrets->os_area.msg_seqno_0; - key = secrets->vmpck0; - break; - case 1: - *seqno = &secrets->os_area.msg_seqno_1; - key = secrets->vmpck1; - break; - case 2: - *seqno = &secrets->os_area.msg_seqno_2; - key = secrets->vmpck2; - break; - case 3: - *seqno = &secrets->os_area.msg_seqno_3; - key = secrets->vmpck3; - break; - default: - break; - } - - return key; -} - struct snp_msg_report_resp_hdr { u32 status; u32 report_size; @@ -979,13 +595,10 @@ static void unregister_sev_tsm(void *data) static int __init sev_guest_probe(struct platform_device *pdev) { - struct sev_guest_platform_data *data; - struct snp_secrets_page *secrets; struct device *dev = &pdev->dev; struct snp_guest_dev *snp_dev; struct snp_msg_desc *mdesc; struct miscdevice *misc; - void __iomem *mapping; int ret; BUILD_BUG_ON(sizeof(struct snp_guest_msg) > PAGE_SIZE); @@ -993,115 +606,57 @@ static int __init sev_guest_probe(struct platform_device *pdev) if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return -ENODEV; - if (!dev->platform_data) - return -ENODEV; - - data = (struct sev_guest_platform_data *)dev->platform_data; - mapping = ioremap_encrypted(data->secrets_gpa, PAGE_SIZE); - if (!mapping) - return -ENODEV; - - secrets = (__force void *)mapping; - - ret = -ENOMEM; snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL); if (!snp_dev) - goto e_unmap; + return -ENOMEM; - mdesc = devm_kzalloc(&pdev->dev, sizeof(struct snp_msg_desc), GFP_KERNEL); - if (!mdesc) - goto e_unmap; + mdesc = snp_msg_alloc(); + if (IS_ERR_OR_NULL(mdesc)) + return -ENOMEM; - /* Adjust the default VMPCK key based on the executing VMPL level */ - if (vmpck_id == -1) - vmpck_id = snp_vmpl; - - ret = -EINVAL; - mdesc->vmpck = get_vmpck(vmpck_id, secrets, &mdesc->os_area_msg_seqno); - if (!mdesc->vmpck) { - dev_err(dev, "Invalid VMPCK%d communication key\n", vmpck_id); - goto e_unmap; - } - - /* Verify that VMPCK is not zero. */ - if (is_vmpck_empty(mdesc)) { - dev_err(dev, "Empty VMPCK%d communication key\n", vmpck_id); - goto e_unmap; - } + ret = snp_msg_init(mdesc, vmpck_id); + if (ret) + goto e_msg_init; platform_set_drvdata(pdev, snp_dev); snp_dev->dev = dev; - mdesc->secrets = secrets; - - /* Allocate the shared page used for the request and response message. */ - mdesc->request = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); - if (!mdesc->request) - goto e_unmap; - - mdesc->response = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); - if (!mdesc->response) - goto e_free_request; - - mdesc->certs_data = alloc_shared_pages(dev, SEV_FW_BLOB_MAX_SIZE); - if (!mdesc->certs_data) - goto e_free_response; - - ret = -EIO; - mdesc->ctx = snp_init_crypto(mdesc->vmpck, VMPCK_KEY_LEN); - if (!mdesc->ctx) - goto e_free_cert_data; misc = &snp_dev->misc; misc->minor = MISC_DYNAMIC_MINOR; misc->name = DEVICE_NAME; misc->fops = &snp_guest_fops; - /* Initialize the input addresses for guest request */ - mdesc->input.req_gpa = __pa(mdesc->request); - mdesc->input.resp_gpa = __pa(mdesc->response); - mdesc->input.data_gpa = __pa(mdesc->certs_data); - /* Set the privlevel_floor attribute based on the vmpck_id */ - sev_tsm_ops.privlevel_floor = vmpck_id; + sev_tsm_ops.privlevel_floor = mdesc->vmpck_id; ret = tsm_register(&sev_tsm_ops, snp_dev); if (ret) - goto e_free_cert_data; + goto e_msg_init; ret = devm_add_action_or_reset(&pdev->dev, unregister_sev_tsm, NULL); if (ret) - goto e_free_cert_data; + goto e_msg_init; ret = misc_register(misc); if (ret) - goto e_free_ctx; + goto e_msg_init; snp_dev->msg_desc = mdesc; - dev_info(dev, "Initialized SEV guest driver (using VMPCK%d communication key)\n", vmpck_id); + dev_info(dev, "Initialized SEV guest driver (using VMPCK%d communication key)\n", + mdesc->vmpck_id); return 0; -e_free_ctx: - kfree(mdesc->ctx); -e_free_cert_data: - free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE); -e_free_response: - free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); -e_free_request: - free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); -e_unmap: - iounmap(mapping); +e_msg_init: + snp_msg_free(mdesc); + return ret; } static void __exit sev_guest_remove(struct platform_device *pdev) { struct snp_guest_dev *snp_dev = platform_get_drvdata(pdev); - struct snp_msg_desc *mdesc = snp_dev->msg_desc; - free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE); - free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); - free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); - kfree(mdesc->ctx); + snp_msg_free(snp_dev->msg_desc); misc_deregister(&snp_dev->misc); } diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c index d7db6c824e13..224e7dde9cde 100644 --- a/drivers/virt/coco/tdx-guest/tdx-guest.c +++ b/drivers/virt/coco/tdx-guest/tdx-guest.c @@ -124,10 +124,8 @@ static void *alloc_quote_buf(void) if (!addr) return NULL; - if (set_memory_decrypted((unsigned long)addr, count)) { - free_pages_exact(addr, len); + if (set_memory_decrypted((unsigned long)addr, count)) return NULL; - } return addr; } diff --git a/drivers/virt/vboxguest/Kconfig b/drivers/virt/vboxguest/Kconfig index cc329887bfae..11b153e7454e 100644 --- a/drivers/virt/vboxguest/Kconfig +++ b/drivers/virt/vboxguest/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config VBOXGUEST tristate "Virtual Box Guest integration support" - depends on X86 && PCI && INPUT + depends on (ARM64 || X86) && PCI && INPUT help This is a driver for the Virtual Box Guest PCI device used in Virtual Box virtual machines. Enabling this driver will add diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index b9095751e43b..ba37665188b5 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -377,6 +377,24 @@ static void virtio_dev_remove(struct device *_d) of_node_put(dev->dev.of_node); } +/* + * virtio_irq_get_affinity - get IRQ affinity mask for device + * @_d: ptr to dev structure + * @irq_vec: interrupt vector number + * + * Return the CPU affinity mask for @_d and @irq_vec. + */ +static const struct cpumask *virtio_irq_get_affinity(struct device *_d, + unsigned int irq_vec) +{ + struct virtio_device *dev = dev_to_virtio(_d); + + if (!dev->config->get_vq_affinity) + return NULL; + + return dev->config->get_vq_affinity(dev, irq_vec); +} + static const struct bus_type virtio_bus = { .name = "virtio", .match = virtio_dev_match, @@ -384,6 +402,7 @@ static const struct bus_type virtio_bus = { .uevent = virtio_uevent, .probe = virtio_dev_probe, .remove = virtio_dev_remove, + .irq_get_affinity = virtio_irq_get_affinity, }; int __register_virtio_driver(struct virtio_driver *driver, struct module *owner) @@ -527,29 +546,7 @@ void unregister_virtio_device(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(unregister_virtio_device); -#ifdef CONFIG_PM_SLEEP -int virtio_device_freeze(struct virtio_device *dev) -{ - struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - int ret; - - virtio_config_core_disable(dev); - - dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; - - if (drv && drv->freeze) { - ret = drv->freeze(dev); - if (ret) { - virtio_config_core_enable(dev); - return ret; - } - } - - return 0; -} -EXPORT_SYMBOL_GPL(virtio_device_freeze); - -int virtio_device_restore(struct virtio_device *dev) +static int virtio_device_restore_priv(struct virtio_device *dev, bool restore) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); int ret; @@ -580,8 +577,14 @@ int virtio_device_restore(struct virtio_device *dev) if (ret) goto err; - if (drv->restore) { - ret = drv->restore(dev); + if (restore) { + if (drv->restore) { + ret = drv->restore(dev); + if (ret) + goto err; + } + } else { + ret = drv->reset_done(dev); if (ret) goto err; } @@ -598,9 +601,69 @@ err: virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return ret; } + +#ifdef CONFIG_PM_SLEEP +int virtio_device_freeze(struct virtio_device *dev) +{ + struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); + int ret; + + virtio_config_core_disable(dev); + + dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; + + if (drv && drv->freeze) { + ret = drv->freeze(dev); + if (ret) { + virtio_config_core_enable(dev); + return ret; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_device_freeze); + +int virtio_device_restore(struct virtio_device *dev) +{ + return virtio_device_restore_priv(dev, true); +} EXPORT_SYMBOL_GPL(virtio_device_restore); #endif +int virtio_device_reset_prepare(struct virtio_device *dev) +{ + struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); + int ret; + + if (!drv || !drv->reset_prepare) + return -EOPNOTSUPP; + + virtio_config_core_disable(dev); + + dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; + + ret = drv->reset_prepare(dev); + if (ret) { + virtio_config_core_enable(dev); + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_device_reset_prepare); + +int virtio_device_reset_done(struct virtio_device *dev) +{ + struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); + + if (!drv || !drv->reset_done) + return -EOPNOTSUPP; + + return virtio_device_restore_priv(dev, false); +} +EXPORT_SYMBOL_GPL(virtio_device_reset_done); + static int virtio_init(void) { if (bus_register(&virtio_bus) != 0) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index b36d2803674e..89da052f4f68 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -251,7 +251,7 @@ static unsigned int fill_balloon(struct virtio_balloon *vb, size_t num) for (num_pfns = 0; num_pfns < num; num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) { - struct page *page = balloon_page_alloc(); + page = balloon_page_alloc(); if (!page) { dev_info_ratelimited(&vb->vdev->dev, diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index b0b871441578..8a294b9cbcf6 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -133,6 +133,8 @@ struct virtio_mem { uint64_t addr; /* Maximum region size in bytes. */ uint64_t region_size; + /* Usable region size in bytes. */ + uint64_t usable_region_size; /* The parent resource for all memory added via this device. */ struct resource *parent_resource; @@ -2368,7 +2370,7 @@ static int virtio_mem_cleanup_pending_mb(struct virtio_mem *vm) static void virtio_mem_refresh_config(struct virtio_mem *vm) { const struct range pluggable_range = mhp_get_pluggable_range(true); - uint64_t new_plugged_size, usable_region_size, end_addr; + uint64_t new_plugged_size, end_addr; /* the plugged_size is just a reflection of what _we_ did previously */ virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size, @@ -2378,8 +2380,8 @@ static void virtio_mem_refresh_config(struct virtio_mem *vm) /* calculate the last usable memory block id */ virtio_cread_le(vm->vdev, struct virtio_mem_config, - usable_region_size, &usable_region_size); - end_addr = min(vm->addr + usable_region_size - 1, + usable_region_size, &vm->usable_region_size); + end_addr = min(vm->addr + vm->usable_region_size - 1, pluggable_range.end); if (vm->in_sbm) { @@ -2648,6 +2650,7 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm) if (rc) goto out_unreg_pm; + virtio_device_ready(vm->vdev); return 0; out_unreg_pm: unregister_pm_notifier(&vm->pm_notifier); @@ -2725,13 +2728,103 @@ static bool virtio_mem_vmcore_pfn_is_ram(struct vmcore_cb *cb, mutex_unlock(&vm->hotplug_mutex); return is_ram; } + +#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM +static int virtio_mem_vmcore_add_device_ram(struct virtio_mem *vm, + struct list_head *list, uint64_t start, uint64_t end) +{ + int rc; + + rc = vmcore_alloc_add_range(list, start, end - start); + if (rc) + dev_err(&vm->vdev->dev, + "Error adding device RAM range: %d\n", rc); + return rc; +} + +static int virtio_mem_vmcore_get_device_ram(struct vmcore_cb *cb, + struct list_head *list) +{ + struct virtio_mem *vm = container_of(cb, struct virtio_mem, + vmcore_cb); + const uint64_t device_start = vm->addr; + const uint64_t device_end = vm->addr + vm->usable_region_size; + uint64_t chunk_size, cur_start, cur_end, plugged_range_start = 0; + LIST_HEAD(tmp_list); + int rc; + + if (!vm->plugged_size) + return 0; + + /* Process memory sections, unless the device block size is bigger. */ + chunk_size = max_t(uint64_t, PFN_PHYS(PAGES_PER_SECTION), + vm->device_block_size); + + mutex_lock(&vm->hotplug_mutex); + + /* + * We process larger chunks and indicate the complete chunk if any + * block in there is plugged. This reduces the number of pfn_is_ram() + * callbacks and mimic what is effectively being done when the old + * kernel would add complete memory sections/blocks to the elfcore hdr. + */ + cur_start = device_start; + for (cur_start = device_start; cur_start < device_end; cur_start = cur_end) { + cur_end = ALIGN_DOWN(cur_start + chunk_size, chunk_size); + cur_end = min_t(uint64_t, cur_end, device_end); + + rc = virtio_mem_send_state_request(vm, cur_start, + cur_end - cur_start); + + if (rc < 0) { + dev_err(&vm->vdev->dev, + "Error querying block states: %d\n", rc); + goto out; + } else if (rc != VIRTIO_MEM_STATE_UNPLUGGED) { + /* Merge ranges with plugged memory. */ + if (!plugged_range_start) + plugged_range_start = cur_start; + continue; + } + + /* Flush any plugged range. */ + if (plugged_range_start) { + rc = virtio_mem_vmcore_add_device_ram(vm, &tmp_list, + plugged_range_start, + cur_start); + if (rc) + goto out; + plugged_range_start = 0; + } + } + + /* Flush any plugged range. */ + if (plugged_range_start) + rc = virtio_mem_vmcore_add_device_ram(vm, &tmp_list, + plugged_range_start, + cur_start); +out: + mutex_unlock(&vm->hotplug_mutex); + if (rc < 0) { + vmcore_free_ranges(&tmp_list); + return rc; + } + list_splice_tail(&tmp_list, list); + return 0; +} +#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */ #endif /* CONFIG_PROC_VMCORE */ static int virtio_mem_init_kdump(struct virtio_mem *vm) { + /* We must be prepared to receive a callback immediately. */ + virtio_device_ready(vm->vdev); #ifdef CONFIG_PROC_VMCORE dev_info(&vm->vdev->dev, "memory hot(un)plug disabled in kdump kernel\n"); vm->vmcore_cb.pfn_is_ram = virtio_mem_vmcore_pfn_is_ram; +#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM + vm->vmcore_cb.get_device_ram = virtio_mem_vmcore_get_device_ram; +#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */ register_vmcore_cb(&vm->vmcore_cb); return 0; #else /* CONFIG_PROC_VMCORE */ @@ -2760,6 +2853,8 @@ static int virtio_mem_init(struct virtio_mem *vm) virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr); virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size, &vm->region_size); + virtio_cread_le(vm->vdev, struct virtio_mem_config, usable_region_size, + &vm->usable_region_size); /* Determine the nid for the device based on the lowest address. */ if (vm->nid == NUMA_NO_NODE) @@ -2870,8 +2965,6 @@ static int virtio_mem_probe(struct virtio_device *vdev) if (rc) goto out_del_vq; - virtio_device_ready(vdev); - /* trigger a config update to start processing the requested_size */ if (!vm->in_kdump) { atomic_set(&vm->config_changed, 1); diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 88074451dd61..d6d79af44569 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -794,6 +794,46 @@ static int virtio_pci_sriov_configure(struct pci_dev *pci_dev, int num_vfs) return num_vfs; } +static void virtio_pci_reset_prepare(struct pci_dev *pci_dev) +{ + struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + int ret = 0; + + ret = virtio_device_reset_prepare(&vp_dev->vdev); + if (ret) { + if (ret != -EOPNOTSUPP) + dev_warn(&pci_dev->dev, "Reset prepare failure: %d", + ret); + return; + } + + if (pci_is_enabled(pci_dev)) + pci_disable_device(pci_dev); +} + +static void virtio_pci_reset_done(struct pci_dev *pci_dev) +{ + struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + int ret; + + if (pci_is_enabled(pci_dev)) + return; + + ret = pci_enable_device(pci_dev); + if (!ret) { + pci_set_master(pci_dev); + ret = virtio_device_reset_done(&vp_dev->vdev); + } + + if (ret && ret != -EOPNOTSUPP) + dev_warn(&pci_dev->dev, "Reset done failure: %d", ret); +} + +static const struct pci_error_handlers virtio_pci_err_handler = { + .reset_prepare = virtio_pci_reset_prepare, + .reset_done = virtio_pci_reset_done, +}; + static struct pci_driver virtio_pci_driver = { .name = "virtio-pci", .id_table = virtio_pci_id_table, @@ -803,6 +843,7 @@ static struct pci_driver virtio_pci_driver = { .driver.pm = &virtio_pci_pm_ops, #endif .sriov_configure = virtio_pci_sriov_configure, + .err_handler = &virtio_pci_err_handler, }; struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev) diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c index a2ecbb863c57..e2a568c9a43a 100644 --- a/drivers/w1/masters/ds2482.c +++ b/drivers/w1/masters/ds2482.c @@ -7,7 +7,7 @@ * It is a I2C to 1-wire bridge. * There are two variations: -100 and -800, which have 1 or 8 1-wire ports. * The complete datasheet can be obtained from MAXIM's website at: - * http://www.maxim-ic.com/quick_view2.cfm/qv_pk/4382 + * https://www.analog.com/en/products/ds2482-100.html */ #include @@ -15,6 +15,7 @@ #include #include #include +#include #include @@ -445,17 +446,20 @@ static int ds2482_probe(struct i2c_client *client) int err = -ENODEV; int temp1; int idx; + int ret; if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_WRITE_BYTE_DATA | I2C_FUNC_SMBUS_BYTE)) return -ENODEV; - data = kzalloc(sizeof(struct ds2482_data), GFP_KERNEL); - if (!data) { - err = -ENOMEM; - goto exit; - } + data = devm_kzalloc(&client->dev, sizeof(struct ds2482_data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + ret = devm_regulator_get_enable(&client->dev, "vcc"); + if (ret) + return dev_err_probe(&client->dev, ret, "Failed to enable regulator\n"); data->client = client; i2c_set_clientdata(client, data); @@ -463,7 +467,7 @@ static int ds2482_probe(struct i2c_client *client) /* Reset the device (sets the read_ptr to status) */ if (ds2482_send_cmd(data, DS2482_CMD_RESET) < 0) { dev_warn(&client->dev, "DS2482 reset failed.\n"); - goto exit_free; + return err; } /* Sleep at least 525ns to allow the reset to complete */ @@ -474,7 +478,7 @@ static int ds2482_probe(struct i2c_client *client) if (temp1 != (DS2482_REG_STS_LL | DS2482_REG_STS_RST)) { dev_warn(&client->dev, "DS2482 reset status " "0x%02X - not a DS2482\n", temp1); - goto exit_free; + return err; } /* Detect the 8-port version */ @@ -516,9 +520,6 @@ exit_w1_remove: if (data->w1_ch[idx].pdev != NULL) w1_remove_master_device(&data->w1_ch[idx].w1_bm); } -exit_free: - kfree(data); -exit: return err; } @@ -532,9 +533,6 @@ static void ds2482_remove(struct i2c_client *client) if (data->w1_ch[idx].pdev != NULL) w1_remove_master_device(&data->w1_ch[idx].w1_bm); } - - /* Free the memory */ - kfree(data); } /* diff --git a/drivers/w1/slaves/w1_ds2406.c b/drivers/w1/slaves/w1_ds2406.c index 2f5926859b8b..1cae9b243ff8 100644 --- a/drivers/w1/slaves/w1_ds2406.c +++ b/drivers/w1/slaves/w1_ds2406.c @@ -24,7 +24,7 @@ static ssize_t w1_f12_read_state( struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { u8 w1_buf[6] = {W1_F12_FUNC_READ_STATUS, 7, 0, 0, 0, 0}; @@ -61,7 +61,7 @@ static ssize_t w1_f12_read_state( static ssize_t w1_f12_write_output( struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -95,14 +95,14 @@ static ssize_t w1_f12_write_output( } #define NB_SYSFS_BIN_FILES 2 -static struct bin_attribute w1_f12_sysfs_bin_files[NB_SYSFS_BIN_FILES] = { +static const struct bin_attribute w1_f12_sysfs_bin_files[NB_SYSFS_BIN_FILES] = { { .attr = { .name = "state", .mode = 0444, }, .size = 1, - .read = w1_f12_read_state, + .read_new = w1_f12_read_state, }, { .attr = { @@ -110,7 +110,7 @@ static struct bin_attribute w1_f12_sysfs_bin_files[NB_SYSFS_BIN_FILES] = { .mode = 0664, }, .size = 1, - .write = w1_f12_write_output, + .write_new = w1_f12_write_output, } }; diff --git a/drivers/w1/slaves/w1_ds2408.c b/drivers/w1/slaves/w1_ds2408.c index 56f822a1dfdb..beccd2912d2a 100644 --- a/drivers/w1/slaves/w1_ds2408.c +++ b/drivers/w1/slaves/w1_ds2408.c @@ -65,8 +65,8 @@ static int _read_reg(struct w1_slave *sl, u8 address, unsigned char *buf) } static ssize_t state_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, - size_t count) + const struct bin_attribute *bin_attr, char *buf, + loff_t off, size_t count) { dev_dbg(&kobj_to_w1_slave(kobj)->dev, "Reading %s kobj: %p, off: %0#10x, count: %zu, buff addr: %p", @@ -77,7 +77,7 @@ static ssize_t state_read(struct file *filp, struct kobject *kobj, } static ssize_t output_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { dev_dbg(&kobj_to_w1_slave(kobj)->dev, @@ -90,7 +90,7 @@ static ssize_t output_read(struct file *filp, struct kobject *kobj, } static ssize_t activity_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { dev_dbg(&kobj_to_w1_slave(kobj)->dev, @@ -103,8 +103,8 @@ static ssize_t activity_read(struct file *filp, struct kobject *kobj, } static ssize_t cond_search_mask_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t off, size_t count) + const struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) { dev_dbg(&kobj_to_w1_slave(kobj)->dev, "Reading %s kobj: %p, off: %0#10x, count: %zu, buff addr: %p", @@ -117,7 +117,7 @@ static ssize_t cond_search_mask_read(struct file *filp, struct kobject *kobj, static ssize_t cond_search_polarity_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { if (count != 1 || off != 0) @@ -127,8 +127,8 @@ static ssize_t cond_search_polarity_read(struct file *filp, } static ssize_t status_control_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t off, size_t count) + const struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) { if (count != 1 || off != 0) return -EFAULT; @@ -160,7 +160,7 @@ static bool optional_read_back_valid(struct w1_slave *sl, u8 expected) #endif static ssize_t output_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -210,7 +210,7 @@ out: * Writing to the activity file resets the activity latches. */ static ssize_t activity_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -240,8 +240,8 @@ error: } static ssize_t status_control_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t off, size_t count) + const struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); u8 w1_buf[4]; @@ -310,14 +310,14 @@ out: return res; } -static BIN_ATTR_RO(state, 1); -static BIN_ATTR_RW(output, 1); -static BIN_ATTR_RW(activity, 1); -static BIN_ATTR_RO(cond_search_mask, 1); -static BIN_ATTR_RO(cond_search_polarity, 1); -static BIN_ATTR_RW(status_control, 1); +static const BIN_ATTR_RO(state, 1); +static const BIN_ATTR_RW(output, 1); +static const BIN_ATTR_RW(activity, 1); +static const BIN_ATTR_RO(cond_search_mask, 1); +static const BIN_ATTR_RO(cond_search_polarity, 1); +static const BIN_ATTR_RW(status_control, 1); -static struct bin_attribute *w1_f29_bin_attrs[] = { +static const struct bin_attribute *const w1_f29_bin_attrs[] = { &bin_attr_state, &bin_attr_output, &bin_attr_activity, @@ -328,7 +328,7 @@ static struct bin_attribute *w1_f29_bin_attrs[] = { }; static const struct attribute_group w1_f29_group = { - .bin_attrs = w1_f29_bin_attrs, + .bin_attrs_new = w1_f29_bin_attrs, }; static const struct attribute_group *w1_f29_groups[] = { diff --git a/drivers/w1/slaves/w1_ds2413.c b/drivers/w1/slaves/w1_ds2413.c index 739009806467..5fa46017ca7c 100644 --- a/drivers/w1/slaves/w1_ds2413.c +++ b/drivers/w1/slaves/w1_ds2413.c @@ -25,8 +25,8 @@ #define W1_F3A_INVALID_PIO_STATE 0xFF static ssize_t state_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, - size_t count) + const struct bin_attribute *bin_attr, char *buf, + loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); unsigned int retries = W1_F3A_RETRIES; @@ -78,10 +78,10 @@ out: return bytes_read; } -static BIN_ATTR_RO(state, 1); +static const BIN_ATTR_RO(state, 1); static ssize_t output_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -128,16 +128,16 @@ out: return bytes_written; } -static BIN_ATTR(output, 0664, NULL, output_write, 1); +static const BIN_ATTR(output, 0664, NULL, output_write, 1); -static struct bin_attribute *w1_f3a_bin_attrs[] = { +static const struct bin_attribute *const w1_f3a_bin_attrs[] = { &bin_attr_state, &bin_attr_output, NULL, }; static const struct attribute_group w1_f3a_group = { - .bin_attrs = w1_f3a_bin_attrs, + .bin_attrs_new = w1_f3a_bin_attrs, }; static const struct attribute_group *w1_f3a_groups[] = { diff --git a/drivers/w1/slaves/w1_ds2430.c b/drivers/w1/slaves/w1_ds2430.c index 0ea7d779d17a..ff56e2e68e58 100644 --- a/drivers/w1/slaves/w1_ds2430.c +++ b/drivers/w1/slaves/w1_ds2430.c @@ -95,7 +95,7 @@ static int w1_f14_readblock(struct w1_slave *sl, int off, int count, char *buf) } static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -202,7 +202,7 @@ retry: } static ssize_t eeprom_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -263,15 +263,15 @@ out_up: return count; } -static BIN_ATTR_RW(eeprom, W1_F14_EEPROM_SIZE); +static const BIN_ATTR_RW(eeprom, W1_F14_EEPROM_SIZE); -static struct bin_attribute *w1_f14_bin_attrs[] = { +static const struct bin_attribute *const w1_f14_bin_attrs[] = { &bin_attr_eeprom, NULL, }; static const struct attribute_group w1_f14_group = { - .bin_attrs = w1_f14_bin_attrs, + .bin_attrs_new = w1_f14_bin_attrs, }; static const struct attribute_group *w1_f14_groups[] = { diff --git a/drivers/w1/slaves/w1_ds2431.c b/drivers/w1/slaves/w1_ds2431.c index 6856b1c29e17..27b390fb59da 100644 --- a/drivers/w1/slaves/w1_ds2431.c +++ b/drivers/w1/slaves/w1_ds2431.c @@ -95,7 +95,7 @@ static int w1_f2d_readblock(struct w1_slave *sl, int off, int count, char *buf) } static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -201,7 +201,7 @@ retry: } static ssize_t eeprom_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -262,15 +262,15 @@ out_up: return count; } -static BIN_ATTR_RW(eeprom, W1_F2D_EEPROM_SIZE); +static const BIN_ATTR_RW(eeprom, W1_F2D_EEPROM_SIZE); -static struct bin_attribute *w1_f2d_bin_attrs[] = { +static const struct bin_attribute *const w1_f2d_bin_attrs[] = { &bin_attr_eeprom, NULL, }; static const struct attribute_group w1_f2d_group = { - .bin_attrs = w1_f2d_bin_attrs, + .bin_attrs_new = w1_f2d_bin_attrs, }; static const struct attribute_group *w1_f2d_groups[] = { diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c index 250b7f7ec429..22331d840ec1 100644 --- a/drivers/w1/slaves/w1_ds2433.c +++ b/drivers/w1/slaves/w1_ds2433.c @@ -110,7 +110,7 @@ static int w1_f23_refresh_block(struct w1_slave *sl, struct w1_f23_data *data, #endif /* CONFIG_W1_SLAVE_DS2433_CRC */ static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -224,7 +224,7 @@ static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data) } static ssize_t eeprom_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -274,27 +274,27 @@ out_up: return count; } -static struct bin_attribute bin_attr_f23_eeprom = { +static const struct bin_attribute bin_attr_f23_eeprom = { .attr = { .name = "eeprom", .mode = 0644 }, - .read = eeprom_read, - .write = eeprom_write, + .read_new = eeprom_read, + .write_new = eeprom_write, .size = W1_EEPROM_DS2433_SIZE, }; -static struct bin_attribute bin_attr_f43_eeprom = { +static const struct bin_attribute bin_attr_f43_eeprom = { .attr = { .name = "eeprom", .mode = 0644 }, - .read = eeprom_read, - .write = eeprom_write, + .read_new = eeprom_read, + .write_new = eeprom_write, .size = W1_EEPROM_DS28EC20_SIZE, }; -static struct bin_attribute *w1_f23_bin_attributes[] = { +static const struct bin_attribute *const w1_f23_bin_attributes[] = { &bin_attr_f23_eeprom, NULL, }; static const struct attribute_group w1_f23_group = { - .bin_attrs = w1_f23_bin_attributes, + .bin_attrs_new = w1_f23_bin_attributes, }; static const struct attribute_group *w1_f23_groups[] = { @@ -302,13 +302,13 @@ static const struct attribute_group *w1_f23_groups[] = { NULL, }; -static struct bin_attribute *w1_f43_bin_attributes[] = { +static const struct bin_attribute *const w1_f43_bin_attributes[] = { &bin_attr_f43_eeprom, NULL, }; static const struct attribute_group w1_f43_group = { - .bin_attrs = w1_f43_bin_attributes, + .bin_attrs_new = w1_f43_bin_attributes, }; static const struct attribute_group *w1_f43_groups[] = { diff --git a/drivers/w1/slaves/w1_ds2438.c b/drivers/w1/slaves/w1_ds2438.c index e008c27b3db9..630a6db5045e 100644 --- a/drivers/w1/slaves/w1_ds2438.c +++ b/drivers/w1/slaves/w1_ds2438.c @@ -288,7 +288,7 @@ static int w1_ds2438_get_current(struct w1_slave *sl, int16_t *voltage) } static ssize_t iad_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -310,7 +310,7 @@ static ssize_t iad_write(struct file *filp, struct kobject *kobj, } static ssize_t iad_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -331,7 +331,7 @@ static ssize_t iad_read(struct file *filp, struct kobject *kobj, } static ssize_t page0_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -361,7 +361,7 @@ static ssize_t page0_read(struct file *filp, struct kobject *kobj, } static ssize_t page1_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -391,7 +391,7 @@ static ssize_t page1_read(struct file *filp, struct kobject *kobj, } static ssize_t offset_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -410,7 +410,7 @@ static ssize_t offset_write(struct file *filp, struct kobject *kobj, } static ssize_t temperature_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -431,7 +431,7 @@ static ssize_t temperature_read(struct file *filp, struct kobject *kobj, } static ssize_t vad_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -452,7 +452,7 @@ static ssize_t vad_read(struct file *filp, struct kobject *kobj, } static ssize_t vdd_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -472,15 +472,15 @@ static ssize_t vdd_read(struct file *filp, struct kobject *kobj, return ret; } -static BIN_ATTR_RW(iad, 0); -static BIN_ATTR_RO(page0, DS2438_PAGE_SIZE); -static BIN_ATTR_RO(page1, DS2438_PAGE_SIZE); -static BIN_ATTR_WO(offset, 2); -static BIN_ATTR_RO(temperature, 0/* real length varies */); -static BIN_ATTR_RO(vad, 0/* real length varies */); -static BIN_ATTR_RO(vdd, 0/* real length varies */); +static const BIN_ATTR_RW(iad, 0); +static const BIN_ATTR_RO(page0, DS2438_PAGE_SIZE); +static const BIN_ATTR_RO(page1, DS2438_PAGE_SIZE); +static const BIN_ATTR_WO(offset, 2); +static const BIN_ATTR_RO(temperature, 0/* real length varies */); +static const BIN_ATTR_RO(vad, 0/* real length varies */); +static const BIN_ATTR_RO(vdd, 0/* real length varies */); -static struct bin_attribute *w1_ds2438_bin_attrs[] = { +static const struct bin_attribute *const w1_ds2438_bin_attrs[] = { &bin_attr_iad, &bin_attr_page0, &bin_attr_page1, @@ -492,7 +492,7 @@ static struct bin_attribute *w1_ds2438_bin_attrs[] = { }; static const struct attribute_group w1_ds2438_group = { - .bin_attrs = w1_ds2438_bin_attrs, + .bin_attrs_new = w1_ds2438_bin_attrs, }; static const struct attribute_group *w1_ds2438_groups[] = { diff --git a/drivers/w1/slaves/w1_ds2780.c b/drivers/w1/slaves/w1_ds2780.c index 3cde1bb1886b..ba7beb7b01f9 100644 --- a/drivers/w1/slaves/w1_ds2780.c +++ b/drivers/w1/slaves/w1_ds2780.c @@ -87,7 +87,7 @@ int w1_ds2780_eeprom_cmd(struct device *dev, int addr, int cmd) EXPORT_SYMBOL(w1_ds2780_eeprom_cmd); static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -95,15 +95,15 @@ static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj, return w1_ds2780_io(dev, buf, off, count, 0); } -static BIN_ATTR_RO(w1_slave, DS2780_DATA_SIZE); +static const BIN_ATTR_RO(w1_slave, DS2780_DATA_SIZE); -static struct bin_attribute *w1_ds2780_bin_attrs[] = { +static const struct bin_attribute *const w1_ds2780_bin_attrs[] = { &bin_attr_w1_slave, NULL, }; static const struct attribute_group w1_ds2780_group = { - .bin_attrs = w1_ds2780_bin_attrs, + .bin_attrs_new = w1_ds2780_bin_attrs, }; static const struct attribute_group *w1_ds2780_groups[] = { diff --git a/drivers/w1/slaves/w1_ds2781.c b/drivers/w1/slaves/w1_ds2781.c index e418484b4a49..acd04ee96e81 100644 --- a/drivers/w1/slaves/w1_ds2781.c +++ b/drivers/w1/slaves/w1_ds2781.c @@ -84,7 +84,7 @@ int w1_ds2781_eeprom_cmd(struct device *dev, int addr, int cmd) EXPORT_SYMBOL(w1_ds2781_eeprom_cmd); static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -92,15 +92,15 @@ static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj, return w1_ds2781_io(dev, buf, off, count, 0); } -static BIN_ATTR_RO(w1_slave, DS2781_DATA_SIZE); +static const BIN_ATTR_RO(w1_slave, DS2781_DATA_SIZE); -static struct bin_attribute *w1_ds2781_bin_attrs[] = { +static const struct bin_attribute *const w1_ds2781_bin_attrs[] = { &bin_attr_w1_slave, NULL, }; static const struct attribute_group w1_ds2781_group = { - .bin_attrs = w1_ds2781_bin_attrs, + .bin_attrs_new = w1_ds2781_bin_attrs, }; static const struct attribute_group *w1_ds2781_groups[] = { diff --git a/drivers/w1/slaves/w1_ds2805.c b/drivers/w1/slaves/w1_ds2805.c index 4c1a2c515317..6ee895640d4a 100644 --- a/drivers/w1/slaves/w1_ds2805.c +++ b/drivers/w1/slaves/w1_ds2805.c @@ -92,7 +92,7 @@ static int w1_f0d_readblock(struct w1_slave *sl, int off, int count, char *buf) } static ssize_t w1_f0d_read_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -200,7 +200,7 @@ retry: } static ssize_t w1_f0d_write_bin(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -261,14 +261,14 @@ out_up: return count; } -static struct bin_attribute w1_f0d_bin_attr = { +static const struct bin_attribute w1_f0d_bin_attr = { .attr = { .name = "eeprom", .mode = 0644, }, .size = W1_F0D_EEPROM_SIZE, - .read = w1_f0d_read_bin, - .write = w1_f0d_write_bin, + .read_new = w1_f0d_read_bin, + .write_new = w1_f0d_write_bin, }; static int w1_f0d_add_slave(struct w1_slave *sl) diff --git a/drivers/w1/slaves/w1_ds28e04.c b/drivers/w1/slaves/w1_ds28e04.c index 2854b8b9e93f..d99ffadbe29b 100644 --- a/drivers/w1/slaves/w1_ds28e04.c +++ b/drivers/w1/slaves/w1_ds28e04.c @@ -112,7 +112,7 @@ static int w1_f1C_read(struct w1_slave *sl, int addr, int len, char *data) } static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -223,7 +223,7 @@ static int w1_f1C_write(struct w1_slave *sl, int addr, int len, const u8 *data) } static ssize_t eeprom_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -276,10 +276,10 @@ out_up: return count; } -static BIN_ATTR_RW(eeprom, W1_EEPROM_SIZE); +static const BIN_ATTR_RW(eeprom, W1_EEPROM_SIZE); static ssize_t pio_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -298,8 +298,8 @@ static ssize_t pio_read(struct file *filp, struct kobject *kobj, } static ssize_t pio_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, - size_t count) + const struct bin_attribute *bin_attr, char *buf, + loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -337,7 +337,7 @@ static ssize_t pio_write(struct file *filp, struct kobject *kobj, return count; } -static BIN_ATTR_RW(pio, 1); +static const BIN_ATTR_RW(pio, 1); static ssize_t crccheck_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -363,7 +363,7 @@ static struct attribute *w1_f1C_attrs[] = { NULL, }; -static struct bin_attribute *w1_f1C_bin_attrs[] = { +static const struct bin_attribute *const w1_f1C_bin_attrs[] = { &bin_attr_eeprom, &bin_attr_pio, NULL, @@ -371,7 +371,7 @@ static struct bin_attribute *w1_f1C_bin_attrs[] = { static const struct attribute_group w1_f1C_group = { .attrs = w1_f1C_attrs, - .bin_attrs = w1_f1C_bin_attrs, + .bin_attrs_new = w1_f1C_bin_attrs, }; static const struct attribute_group *w1_f1C_groups[] = { diff --git a/drivers/w1/slaves/w1_ds28e17.c b/drivers/w1/slaves/w1_ds28e17.c index 52261b54d842..5738cbce1a37 100644 --- a/drivers/w1/slaves/w1_ds28e17.c +++ b/drivers/w1/slaves/w1_ds28e17.c @@ -583,7 +583,7 @@ static ssize_t speed_show(struct device *dev, struct device_attribute *attr, return result; /* Return current speed value. */ - return sprintf(buf, "%d\n", result); + return sysfs_emit(buf, "%d\n", result); } static ssize_t speed_store(struct device *dev, struct device_attribute *attr, @@ -633,7 +633,7 @@ static ssize_t stretch_show(struct device *dev, struct device_attribute *attr, struct w1_f19_data *data = sl->family_data; /* Return current stretch value. */ - return sprintf(buf, "%d\n", data->stretch); + return sysfs_emit(buf, "%d\n", data->stretch); } static ssize_t stretch_store(struct device *dev, struct device_attribute *attr, diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index d82e86d3ddf6..29f200bbab41 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -111,7 +111,7 @@ ATTRIBUTE_GROUPS(w1_slave); /* Default family */ static ssize_t rw_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -130,8 +130,8 @@ out_up: } static ssize_t rw_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, loff_t off, - size_t count) + const struct bin_attribute *bin_attr, char *buf, + loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); @@ -141,15 +141,15 @@ static ssize_t rw_read(struct file *filp, struct kobject *kobj, return count; } -static BIN_ATTR_RW(rw, PAGE_SIZE); +static const BIN_ATTR_RW(rw, PAGE_SIZE); -static struct bin_attribute *w1_slave_bin_attrs[] = { +static const struct bin_attribute *const w1_slave_bin_attrs[] = { &bin_attr_rw, NULL, }; static const struct attribute_group w1_slave_default_group = { - .bin_attrs = w1_slave_bin_attrs, + .bin_attrs_new = w1_slave_bin_attrs, }; static const struct attribute_group *w1_slave_default_groups[] = { diff --git a/drivers/watchdog/da9052_wdt.c b/drivers/watchdog/da9052_wdt.c index d708c091bf1b..77039f2f0be5 100644 --- a/drivers/watchdog/da9052_wdt.c +++ b/drivers/watchdog/da9052_wdt.c @@ -135,7 +135,11 @@ static int da9052_wdt_ping(struct watchdog_device *wdt_dev) } static const struct watchdog_info da9052_wdt_info = { - .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING, + .options = WDIOF_SETTIMEOUT | + WDIOF_KEEPALIVEPING | + WDIOF_CARDRESET | + WDIOF_OVERHEAT | + WDIOF_POWERUNDER, .identity = "DA9052 Watchdog", }; @@ -169,6 +173,13 @@ static int da9052_wdt_probe(struct platform_device *pdev) da9052_wdt->parent = dev; watchdog_set_drvdata(da9052_wdt, driver_data); + if (da9052->fault_log & DA9052_FAULTLOG_TWDERROR) + da9052_wdt->bootstatus |= WDIOF_CARDRESET; + if (da9052->fault_log & DA9052_FAULTLOG_TEMPOVER) + da9052_wdt->bootstatus |= WDIOF_OVERHEAT; + if (da9052->fault_log & DA9052_FAULTLOG_VDDFAULT) + da9052_wdt->bootstatus |= WDIOF_POWERUNDER; + ret = da9052_reg_update(da9052, DA9052_CONTROL_D_REG, DA9052_CONTROLD_TWDSCALE, 0); if (ret < 0) { diff --git a/drivers/watchdog/max77620_wdt.c b/drivers/watchdog/max77620_wdt.c index 33835c0b06de..d3ced783a5f4 100644 --- a/drivers/watchdog/max77620_wdt.c +++ b/drivers/watchdog/max77620_wdt.c @@ -25,7 +25,6 @@ static bool nowayout = WATCHDOG_NOWAYOUT; /** * struct max77620_variant - Data specific to a chip variant - * @wdt_info: watchdog descriptor * @reg_onoff_cnfg2: ONOFF_CNFG2 register offset * @reg_cnfg_glbl2: CNFG_GLBL2 register offset * @reg_cnfg_glbl3: CNFG_GLBL3 register offset diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c index 58c9445c0f88..d1f9ce4100a8 100644 --- a/drivers/watchdog/rti_wdt.c +++ b/drivers/watchdog/rti_wdt.c @@ -273,7 +273,8 @@ static int rti_wdt_probe(struct platform_device *pdev) set_bit(WDOG_HW_RUNNING, &wdd->status); time_left_ms = rti_wdt_get_timeleft_ms(wdd); - heartbeat_ms = readl(wdt->base + RTIDWDPRLD); + /* AM62x TRM: texp = (RTIDWDPRLD + 1) * (2^13) / RTICLK1 */ + heartbeat_ms = readl(wdt->base + RTIDWDPRLD) + 1; heartbeat_ms <<= WDT_PRELOAD_SHIFT; heartbeat_ms *= 1000; do_div(heartbeat_ms, wdt->freq); @@ -301,6 +302,7 @@ static int rti_wdt_probe(struct platform_device *pdev) node = of_parse_phandle(pdev->dev.of_node, "memory-region", 0); if (node) { ret = of_address_to_resource(node, 0, &res); + of_node_put(node); if (ret) { dev_err(dev, "No memory address assigned to the region.\n"); goto err_iomap; diff --git a/drivers/watchdog/rzv2h_wdt.c b/drivers/watchdog/rzv2h_wdt.c index 1d1b17312747..8defd0241213 100644 --- a/drivers/watchdog/rzv2h_wdt.c +++ b/drivers/watchdog/rzv2h_wdt.c @@ -217,24 +217,24 @@ static int rzv2h_wdt_probe(struct platform_device *pdev) if (IS_ERR(priv->base)) return PTR_ERR(priv->base); - priv->pclk = devm_clk_get_prepared(&pdev->dev, "pclk"); + priv->pclk = devm_clk_get_prepared(dev, "pclk"); if (IS_ERR(priv->pclk)) - return dev_err_probe(&pdev->dev, PTR_ERR(priv->pclk), "no pclk"); + return dev_err_probe(dev, PTR_ERR(priv->pclk), "no pclk"); - priv->oscclk = devm_clk_get_prepared(&pdev->dev, "oscclk"); + priv->oscclk = devm_clk_get_prepared(dev, "oscclk"); if (IS_ERR(priv->oscclk)) - return dev_err_probe(&pdev->dev, PTR_ERR(priv->oscclk), "no oscclk"); + return dev_err_probe(dev, PTR_ERR(priv->oscclk), "no oscclk"); - priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + priv->rstc = devm_reset_control_get_exclusive(dev, NULL); if (IS_ERR(priv->rstc)) - return dev_err_probe(&pdev->dev, PTR_ERR(priv->rstc), + return dev_err_probe(dev, PTR_ERR(priv->rstc), "failed to get cpg reset"); priv->wdev.max_hw_heartbeat_ms = (MILLI * MAX_TIMEOUT_CYCLES * CLOCK_DIV_BY_256) / clk_get_rate(priv->oscclk); dev_dbg(dev, "max hw timeout of %dms\n", priv->wdev.max_hw_heartbeat_ms); - ret = devm_pm_runtime_enable(&pdev->dev); + ret = devm_pm_runtime_enable(dev); if (ret) return ret; @@ -251,7 +251,7 @@ static int rzv2h_wdt_probe(struct platform_device *pdev) if (ret) dev_warn(dev, "Specified timeout invalid, using default"); - return devm_watchdog_register_device(&pdev->dev, &priv->wdev); + return devm_watchdog_register_device(dev, &priv->wdev); } static const struct of_device_id rzv2h_wdt_ids[] = { diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c index 109e2e37e8f0..c2125f204a13 100644 --- a/drivers/watchdog/sp805_wdt.c +++ b/drivers/watchdog/sp805_wdt.c @@ -62,7 +62,6 @@ * @clk: (optional) clock structure of wdt * @rate: (optional) clock rate when provided via properties * @adev: amba device structure of wdt - * @status: current status of wdt * @load_val: load value to be set for current timeout */ struct sp805_wdt { @@ -128,7 +127,7 @@ static unsigned int wdt_timeleft(struct watchdog_device *wdd) /*If the interrupt is inactive then time left is WDTValue + WDTLoad. */ if (!(readl_relaxed(wdt->base + WDTRIS) & INT_MASK)) - load += wdt->load_val + 1; + load += (u64)wdt->load_val + 1; spin_unlock(&wdt->lock); return div_u64(load, wdt->rate); diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c index d700e0d49bb9..8ad06b54c5ad 100644 --- a/drivers/watchdog/stm32_iwdg.c +++ b/drivers/watchdog/stm32_iwdg.c @@ -286,7 +286,7 @@ static int stm32_iwdg_irq_init(struct platform_device *pdev, if (!wdt->data->has_early_wakeup) return 0; - irq = platform_get_irq(pdev, 0); + irq = platform_get_irq_optional(pdev, 0); if (irq <= 0) return 0; diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index 4190cb800cc4..19698d87dc57 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -1229,7 +1229,7 @@ int __init watchdog_dev_init(void) { int err; - watchdog_kworker = kthread_create_worker(0, "watchdogd"); + watchdog_kworker = kthread_run_worker(0, "watchdogd"); if (IS_ERR(watchdog_kworker)) { pr_err("Failed to create watchdog kworker\n"); return PTR_ERR(watchdog_kworker); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 528395133b4f..163f7f1d70f1 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -84,7 +84,7 @@ module_param(balloon_boot_timeout, uint, 0444); #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG static int xen_hotplug_unpopulated; -static struct ctl_table balloon_table[] = { +static const struct ctl_table balloon_table[] = { { .procname = "hotplug_unpopulated", .data = &xen_hotplug_unpopulated, diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 985e155ebe4b..41309d38f78c 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -722,12 +722,6 @@ static struct irq_info *xen_irq_init(unsigned int irq) INIT_RCU_WORK(&info->rwork, delayed_free_irq); set_info_for_irq(irq, info); - /* - * Interrupt affinity setting can be immediate. No point - * in delaying it until an interrupt is handled. - */ - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - INIT_LIST_HEAD(&info->eoi_list); list_add_tail(&info->list, &xen_irq_list_head); } diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index c63f317e3df3..093ad4a08672 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -105,7 +105,7 @@ static ssize_t online_show(struct device *dev, return sprintf(buf, "%u\n", !!(cpu->flags & XEN_PCPU_FLAGS_ONLINE)); } -static ssize_t __ref online_store(struct device *dev, +static ssize_t online_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index b72ee9379d77..4926d4badc57 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -341,6 +341,7 @@ int pvcalls_front_socket(struct socket *sock) pvcalls_exit(); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_socket); static void free_active_ring(struct sock_mapping *map) { @@ -486,6 +487,7 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_connect); static int __write_ring(struct pvcalls_data_intf *intf, struct pvcalls_data *data, @@ -581,6 +583,7 @@ again: pvcalls_exit_sock(sock); return tot_sent; } +EXPORT_SYMBOL_GPL(pvcalls_front_sendmsg); static int __read_ring(struct pvcalls_data_intf *intf, struct pvcalls_data *data, @@ -666,6 +669,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_recvmsg); int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { @@ -719,6 +723,7 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) pvcalls_exit_sock(sock); return 0; } +EXPORT_SYMBOL_GPL(pvcalls_front_bind); int pvcalls_front_listen(struct socket *sock, int backlog) { @@ -768,8 +773,10 @@ int pvcalls_front_listen(struct socket *sock, int backlog) pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_listen); -int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) +int pvcalls_front_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct pvcalls_bedata *bedata; struct sock_mapping *map; @@ -788,7 +795,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) return -EINVAL; } - nonblock = flags & SOCK_NONBLOCK; + nonblock = arg->flags & SOCK_NONBLOCK; /* * Backend only supports 1 inflight accept request, will return * errors for the others @@ -904,6 +911,7 @@ received: pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_accept); static __poll_t pvcalls_front_poll_passive(struct file *file, struct pvcalls_bedata *bedata, @@ -1004,6 +1012,7 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_poll); int pvcalls_front_release(struct socket *sock) { @@ -1087,6 +1096,7 @@ int pvcalls_front_release(struct socket *sock) pvcalls_exit(); return 0; } +EXPORT_SYMBOL_GPL(pvcalls_front_release); static const struct xenbus_device_id pvcalls_front_ids[] = { { "pvcalls" }, diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h index f694ad77379f..881ef14660bc 100644 --- a/drivers/xen/pvcalls-front.h +++ b/drivers/xen/pvcalls-front.h @@ -12,7 +12,7 @@ int pvcalls_front_bind(struct socket *sock, int pvcalls_front_listen(struct socket *sock, int backlog); int pvcalls_front_accept(struct socket *sock, struct socket *newsock, - int flags); + struct proto_accept_arg *arg); int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg, size_t len); diff --git a/drivers/zorro/zorro-sysfs.c b/drivers/zorro/zorro-sysfs.c index 3d34dba9bb2d..10aedcd21363 100644 --- a/drivers/zorro/zorro-sysfs.c +++ b/drivers/zorro/zorro-sysfs.c @@ -81,7 +81,7 @@ static struct attribute *zorro_device_attrs[] = { }; static ssize_t zorro_read_config(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct zorro_dev *z = to_zorro_dev(kobj_to_dev(kobj)); @@ -98,23 +98,23 @@ static ssize_t zorro_read_config(struct file *filp, struct kobject *kobj, return memory_read_from_buffer(buf, count, &off, &cd, sizeof(cd)); } -static struct bin_attribute zorro_config_attr = { +static const struct bin_attribute zorro_config_attr = { .attr = { .name = "config", .mode = S_IRUGO, }, .size = sizeof(struct ConfigDev), - .read = zorro_read_config, + .read_new = zorro_read_config, }; -static struct bin_attribute *zorro_device_bin_attrs[] = { +static const struct bin_attribute *const zorro_device_bin_attrs[] = { &zorro_config_attr, NULL }; static const struct attribute_group zorro_device_attr_group = { .attrs = zorro_device_attrs, - .bin_attrs = zorro_device_bin_attrs, + .bin_attrs_new = zorro_device_bin_attrs, }; const struct attribute_group *zorro_device_attribute_groups[] = { diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 698c43dd5dc8..f28bc763847a 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -202,7 +202,7 @@ static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode) return inode->i_sb->s_fs_info; } -static inline struct v9fs_session_info *v9fs_dentry2v9ses(struct dentry *dentry) +static inline struct v9fs_session_info *v9fs_dentry2v9ses(const struct dentry *dentry) { return dentry->d_sb->s_fs_info; } diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 819c75233235..32619d146cbc 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -57,6 +57,8 @@ static void v9fs_issue_write(struct netfs_io_subrequest *subreq) int err, len; len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err); + if (len > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); netfs_write_subrequest_terminated(subreq, len ?: err, false); } @@ -79,11 +81,13 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); if (pos + total >= i_size_read(rreq->inode)) __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); - - if (!err) + if (!err && total) { subreq->transferred += total; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + } - netfs_read_subreq_terminated(subreq, err, false); + subreq->error = err; + netfs_read_subreq_terminated(subreq); } /** diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index 01338d4c2d9e..5061f192eafd 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -61,7 +61,7 @@ static void v9fs_dentry_release(struct dentry *dentry) p9_fid_put(hlist_entry(p, struct p9_fid, dlist)); } -static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) +static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { struct p9_fid *fid; struct inode *inode; @@ -99,14 +99,36 @@ out_valid: return 1; } +static int v9fs_lookup_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) +{ + return __v9fs_lookup_revalidate(dentry, flags); +} + +static bool v9fs_dentry_unalias_trylock(const struct dentry *dentry) +{ + struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry); + return down_write_trylock(&v9ses->rename_sem); +} + +static void v9fs_dentry_unalias_unlock(const struct dentry *dentry) +{ + struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry); + up_write(&v9ses->rename_sem); +} + const struct dentry_operations v9fs_cached_dentry_operations = { .d_revalidate = v9fs_lookup_revalidate, - .d_weak_revalidate = v9fs_lookup_revalidate, + .d_weak_revalidate = __v9fs_lookup_revalidate, .d_delete = v9fs_cached_dentry_delete, .d_release = v9fs_dentry_release, + .d_unalias_trylock = v9fs_dentry_unalias_trylock, + .d_unalias_unlock = v9fs_dentry_unalias_unlock, }; const struct dentry_operations v9fs_dentry_operations = { .d_delete = always_delete_dentry, .d_release = v9fs_dentry_release, + .d_unalias_trylock = v9fs_dentry_unalias_trylock, + .d_unalias_unlock = v9fs_dentry_unalias_unlock, }; diff --git a/fs/afs/Makefile b/fs/afs/Makefile index dcdc0f1bb76f..5efd7e13b304 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -11,6 +11,7 @@ kafs-y := \ cmservice.o \ dir.o \ dir_edit.o \ + dir_search.o \ dir_silly.o \ dynroot.o \ file.o \ diff --git a/fs/afs/addr_prefs.c b/fs/afs/addr_prefs.c index a189ff8a5034..c0384201b8fe 100644 --- a/fs/afs/addr_prefs.c +++ b/fs/afs/addr_prefs.c @@ -413,8 +413,10 @@ int afs_proc_addr_prefs_write(struct file *file, char *buf, size_t size) do { argc = afs_split_string(&buf, argv, ARRAY_SIZE(argv)); - if (argc < 0) - return argc; + if (argc < 0) { + ret = argc; + goto done; + } if (argc < 2) goto inval; diff --git a/fs/afs/afs.h b/fs/afs/afs.h index b488072aee87..ec3db00bd081 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -10,7 +10,7 @@ #include -#define AFS_MAXCELLNAME 256 /* Maximum length of a cell name */ +#define AFS_MAXCELLNAME 253 /* Maximum length of a cell name (DNS limited) */ #define AFS_MAXVOLNAME 64 /* Maximum length of a volume name */ #define AFS_MAXNSERVERS 8 /* Maximum servers in a basic volume record */ #define AFS_NMAXNSERVERS 13 /* Maximum servers in a N/U-class volume record */ diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h index a06296c8827d..b835e25a2c02 100644 --- a/fs/afs/afs_vl.h +++ b/fs/afs/afs_vl.h @@ -13,6 +13,7 @@ #define AFS_VL_PORT 7003 /* volume location service port */ #define VL_SERVICE 52 /* RxRPC service ID for the Volume Location service */ #define YFS_VL_SERVICE 2503 /* Service ID for AuriStor upgraded VL service */ +#define YFS_VL_MAXCELLNAME 256 /* Maximum length of a cell name in YFS protocol */ enum AFSVL_Operations { VLGETENTRYBYID = 503, /* AFS Get VLDB entry by ID */ diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 99b2c8172021..69e1dd55b160 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -41,7 +41,7 @@ static void afs_volume_init_callback(struct afs_volume *volume) list_for_each_entry(vnode, &volume->open_mmaps, cb_mmap_link) { if (vnode->cb_v_check != atomic_read(&volume->cb_v_break)) { - atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE); + afs_clear_cb_promise(vnode, afs_cb_promise_clear_vol_init_cb); queue_work(system_unbound_wq, &vnode->cb_work); } } @@ -79,7 +79,7 @@ void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reas _enter(""); clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); - if (atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE) { + if (afs_clear_cb_promise(vnode, afs_cb_promise_clear_cb_break)) { vnode->cb_break++; vnode->cb_v_check = atomic_read(&vnode->volume->cb_v_break); afs_clear_permits(vnode); diff --git a/fs/afs/cell.c b/fs/afs/cell.c index caa09875f520..cee42646736c 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -146,18 +146,20 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, return ERR_PTR(-ENOMEM); } - cell->name = kmalloc(namelen + 1, GFP_KERNEL); + cell->name = kmalloc(1 + namelen + 1, GFP_KERNEL); if (!cell->name) { kfree(cell); return ERR_PTR(-ENOMEM); } - cell->net = net; + cell->name[0] = '.'; + cell->name++; cell->name_len = namelen; for (i = 0; i < namelen; i++) cell->name[i] = tolower(name[i]); cell->name[i] = 0; + cell->net = net; refcount_set(&cell->ref, 1); atomic_set(&cell->active, 0); INIT_WORK(&cell->manager, afs_manage_cell_work); @@ -211,7 +213,7 @@ parse_failed: if (ret == -EINVAL) printk(KERN_ERR "kAFS: bad VL server IP address\n"); error: - kfree(cell->name); + kfree(cell->name - 1); kfree(cell); _leave(" = %d", ret); return ERR_PTR(ret); @@ -365,6 +367,14 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) len = cp - rootcell; } + if (len == 0 || !rootcell[0] || rootcell[0] == '.' || rootcell[len - 1] == '.') + return -EINVAL; + if (memchr(rootcell, '/', len)) + return -EINVAL; + cp = strstr(rootcell, ".."); + if (cp && cp < rootcell + len) + return -EINVAL; + /* allocate a cell record for the root cell */ new_root = afs_lookup_cell(net, rootcell, len, vllist, false); if (IS_ERR(new_root)) { @@ -502,7 +512,7 @@ static void afs_cell_destroy(struct rcu_head *rcu) afs_put_vlserverlist(net, rcu_access_pointer(cell->vl_servers)); afs_unuse_cell(net, cell->alias_of, afs_cell_trace_unuse_alias); key_put(cell->anonymous_key); - kfree(cell->name); + kfree(cell->name - 1); kfree(cell); afs_dec_cells_outstanding(net); @@ -710,7 +720,8 @@ static void afs_deactivate_cell(struct afs_net *net, struct afs_cell *cell) afs_proc_cell_remove(cell); mutex_lock(&net->proc_cells_lock); - hlist_del_rcu(&cell->proc_link); + if (!hlist_unhashed(&cell->proc_link)) + hlist_del_rcu(&cell->proc_link); afs_dynroot_rmdir(net, cell); mutex_unlock(&net->proc_cells_lock); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index ada363af5aab..02cbf38e1a77 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "internal.h" #include "afs_fs.h" @@ -22,7 +23,8 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); static int afs_dir_open(struct inode *inode, struct file *file); static int afs_readdir(struct file *file, struct dir_context *ctx); -static int afs_d_revalidate(struct dentry *dentry, unsigned int flags); +static int afs_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags); static int afs_d_delete(const struct dentry *dentry); static void afs_d_iput(struct dentry *dentry, struct inode *inode); static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name, int nlen, @@ -42,15 +44,6 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); -static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags); -static void afs_dir_invalidate_folio(struct folio *folio, size_t offset, - size_t length); - -static bool afs_dir_dirty_folio(struct address_space *mapping, - struct folio *folio) -{ - BUG(); /* This should never happen. */ -} const struct file_operations afs_dir_file_operations = { .open = afs_dir_open, @@ -75,10 +68,7 @@ const struct inode_operations afs_dir_inode_operations = { }; const struct address_space_operations afs_dir_aops = { - .dirty_folio = afs_dir_dirty_folio, - .release_folio = afs_dir_release_folio, - .invalidate_folio = afs_dir_invalidate_folio, - .migrate_folio = filemap_migrate_folio, + .writepages = afs_single_writepages, }; const struct dentry_operations afs_fs_dentry_operations = { @@ -99,152 +89,124 @@ struct afs_lookup_one_cookie { struct afs_lookup_cookie { struct dir_context ctx; struct qstr name; - bool found; - bool one_only; unsigned short nr_fids; struct afs_fid fids[50]; }; -/* - * Drop the refs that we're holding on the folios we were reading into. We've - * got refs on the first nr_pages pages. - */ -static void afs_dir_read_cleanup(struct afs_read *req) +static void afs_dir_unuse_cookie(struct afs_vnode *dvnode, int ret) { - struct address_space *mapping = req->vnode->netfs.inode.i_mapping; - struct folio *folio; - pgoff_t last = req->nr_pages - 1; + if (ret == 0) { + struct afs_vnode_cache_aux aux; + loff_t i_size = i_size_read(&dvnode->netfs.inode); - XA_STATE(xas, &mapping->i_pages, 0); - - if (unlikely(!req->nr_pages)) - return; - - rcu_read_lock(); - xas_for_each(&xas, folio, last) { - if (xas_retry(&xas, folio)) - continue; - BUG_ON(xa_is_value(folio)); - ASSERTCMP(folio->mapping, ==, mapping); - - folio_put(folio); + afs_set_cache_aux(dvnode, &aux); + fscache_unuse_cookie(afs_vnode_cache(dvnode), &aux, &i_size); + } else { + fscache_unuse_cookie(afs_vnode_cache(dvnode), NULL, NULL); } - - rcu_read_unlock(); } /* - * check that a directory folio is valid + * Iterate through a kmapped directory segment, dumping a summary of + * the contents. */ -static bool afs_dir_check_folio(struct afs_vnode *dvnode, struct folio *folio, - loff_t i_size) +static size_t afs_dir_dump_step(void *iter_base, size_t progress, size_t len, + void *priv, void *priv2) { - union afs_xdr_dir_block *block; - size_t offset, size; - loff_t pos; + do { + union afs_xdr_dir_block *block = iter_base; - /* Determine how many magic numbers there should be in this folio, but - * we must take care because the directory may change size under us. - */ - pos = folio_pos(folio); - if (i_size <= pos) - goto checked; + pr_warn("[%05zx] %32phN\n", progress, block); + iter_base += AFS_DIR_BLOCK_SIZE; + progress += AFS_DIR_BLOCK_SIZE; + len -= AFS_DIR_BLOCK_SIZE; + } while (len > 0); - size = min_t(loff_t, folio_size(folio), i_size - pos); - for (offset = 0; offset < size; offset += sizeof(*block)) { - block = kmap_local_folio(folio, offset); - if (block->hdr.magic != AFS_DIR_MAGIC) { - printk("kAFS: %s(%lx): [%llx] bad magic %zx/%zx is %04hx\n", - __func__, dvnode->netfs.inode.i_ino, - pos, offset, size, ntohs(block->hdr.magic)); - trace_afs_dir_check_failed(dvnode, pos + offset, i_size); - kunmap_local(block); - trace_afs_file_error(dvnode, -EIO, afs_file_error_dir_bad_magic); - goto error; - } - - /* Make sure each block is NUL terminated so we can reasonably - * use string functions on it. The filenames in the folio - * *should* be NUL-terminated anyway. - */ - ((u8 *)block)[AFS_DIR_BLOCK_SIZE - 1] = 0; - - kunmap_local(block); - } -checked: - afs_stat_v(dvnode, n_read_dir); - return true; - -error: - return false; + return len; } /* * Dump the contents of a directory. */ -static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req) +static void afs_dir_dump(struct afs_vnode *dvnode) { - union afs_xdr_dir_block *block; - struct address_space *mapping = dvnode->netfs.inode.i_mapping; - struct folio *folio; - pgoff_t last = req->nr_pages - 1; - size_t offset, size; + struct iov_iter iter; + unsigned long long i_size = i_size_read(&dvnode->netfs.inode); - XA_STATE(xas, &mapping->i_pages, 0); + pr_warn("DIR %llx:%llx is=%llx\n", + dvnode->fid.vid, dvnode->fid.vnode, i_size); - pr_warn("DIR %llx:%llx f=%llx l=%llx al=%llx\n", - dvnode->fid.vid, dvnode->fid.vnode, - req->file_size, req->len, req->actual_len); - pr_warn("DIR %llx %x %zx %zx\n", - req->pos, req->nr_pages, - req->iter->iov_offset, iov_iter_count(req->iter)); - - xas_for_each(&xas, folio, last) { - if (xas_retry(&xas, folio)) - continue; - - BUG_ON(folio->mapping != mapping); - - size = min_t(loff_t, folio_size(folio), req->actual_len - folio_pos(folio)); - for (offset = 0; offset < size; offset += sizeof(*block)) { - block = kmap_local_folio(folio, offset); - pr_warn("[%02lx] %32phN\n", folio->index + offset, block); - kunmap_local(block); - } - } + iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, i_size); + iterate_folioq(&iter, iov_iter_count(&iter), NULL, NULL, + afs_dir_dump_step); } /* - * Check all the blocks in a directory. All the folios are held pinned. + * check that a directory folio is valid */ -static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req) +static bool afs_dir_check_block(struct afs_vnode *dvnode, size_t progress, + union afs_xdr_dir_block *block) { - struct address_space *mapping = dvnode->netfs.inode.i_mapping; - struct folio *folio; - pgoff_t last = req->nr_pages - 1; - int ret = 0; - - XA_STATE(xas, &mapping->i_pages, 0); - - if (unlikely(!req->nr_pages)) - return 0; - - rcu_read_lock(); - xas_for_each(&xas, folio, last) { - if (xas_retry(&xas, folio)) - continue; - - BUG_ON(folio->mapping != mapping); - - if (!afs_dir_check_folio(dvnode, folio, req->actual_len)) { - afs_dir_dump(dvnode, req); - ret = -EIO; - break; - } + if (block->hdr.magic != AFS_DIR_MAGIC) { + pr_warn("%s(%lx): [%zx] bad magic %04x\n", + __func__, dvnode->netfs.inode.i_ino, + progress, ntohs(block->hdr.magic)); + trace_afs_dir_check_failed(dvnode, progress); + trace_afs_file_error(dvnode, -EIO, afs_file_error_dir_bad_magic); + return false; } - rcu_read_unlock(); - return ret; + /* Make sure each block is NUL terminated so we can reasonably + * use string functions on it. The filenames in the folio + * *should* be NUL-terminated anyway. + */ + ((u8 *)block)[AFS_DIR_BLOCK_SIZE - 1] = 0; + afs_stat_v(dvnode, n_read_dir); + return true; +} + +/* + * Iterate through a kmapped directory segment, checking the content. + */ +static size_t afs_dir_check_step(void *iter_base, size_t progress, size_t len, + void *priv, void *priv2) +{ + struct afs_vnode *dvnode = priv; + + if (WARN_ON_ONCE(progress % AFS_DIR_BLOCK_SIZE || + len % AFS_DIR_BLOCK_SIZE)) + return len; + + do { + if (!afs_dir_check_block(dvnode, progress, iter_base)) + break; + iter_base += AFS_DIR_BLOCK_SIZE; + len -= AFS_DIR_BLOCK_SIZE; + } while (len > 0); + + return len; +} + +/* + * Check all the blocks in a directory. + */ +static int afs_dir_check(struct afs_vnode *dvnode) +{ + struct iov_iter iter; + unsigned long long i_size = i_size_read(&dvnode->netfs.inode); + size_t checked = 0; + + if (unlikely(!i_size)) + return 0; + + iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, i_size); + checked = iterate_folioq(&iter, iov_iter_count(&iter), dvnode, NULL, + afs_dir_check_step); + if (checked != i_size) { + afs_dir_dump(dvnode); + return -EIO; + } + return 0; } /* @@ -264,134 +226,140 @@ static int afs_dir_open(struct inode *inode, struct file *file) } /* - * Read the directory into the pagecache in one go, scrubbing the previous - * contents. The list of folios is returned, pinning them so that they don't - * get reclaimed during the iteration. + * Read a file in a single download. */ -static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) +static ssize_t afs_do_read_single(struct afs_vnode *dvnode, struct file *file) +{ + struct iov_iter iter; + ssize_t ret; + loff_t i_size; + bool is_dir = (S_ISDIR(dvnode->netfs.inode.i_mode) && + !test_bit(AFS_VNODE_MOUNTPOINT, &dvnode->flags)); + + i_size = i_size_read(&dvnode->netfs.inode); + if (is_dir) { + if (i_size < AFS_DIR_BLOCK_SIZE) + return afs_bad(dvnode, afs_file_error_dir_small); + if (i_size > AFS_DIR_BLOCK_SIZE * 1024) { + trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); + return -EFBIG; + } + } else { + if (i_size > AFSPATHMAX) { + trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); + return -EFBIG; + } + } + + /* Expand the storage. TODO: Shrink the storage too. */ + if (dvnode->directory_size < i_size) { + size_t cur_size = dvnode->directory_size; + + ret = netfs_alloc_folioq_buffer(NULL, + &dvnode->directory, &cur_size, i_size, + mapping_gfp_mask(dvnode->netfs.inode.i_mapping)); + dvnode->directory_size = cur_size; + if (ret < 0) + return ret; + } + + iov_iter_folio_queue(&iter, ITER_DEST, dvnode->directory, 0, 0, dvnode->directory_size); + + /* AFS requires us to perform the read of a directory synchronously as + * a single unit to avoid issues with the directory contents being + * changed between reads. + */ + ret = netfs_read_single(&dvnode->netfs.inode, file, &iter); + if (ret >= 0) { + i_size = i_size_read(&dvnode->netfs.inode); + if (i_size > ret) { + /* The content has grown, so we need to expand the + * buffer. + */ + ret = -ESTALE; + } else if (is_dir) { + int ret2 = afs_dir_check(dvnode); + + if (ret2 < 0) + ret = ret2; + } else if (i_size < folioq_folio_size(dvnode->directory, 0)) { + /* NUL-terminate a symlink. */ + char *symlink = kmap_local_folio(folioq_folio(dvnode->directory, 0), 0); + + symlink[i_size] = 0; + kunmap_local(symlink); + } + } + + return ret; +} + +ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file) +{ + ssize_t ret; + + fscache_use_cookie(afs_vnode_cache(dvnode), false); + ret = afs_do_read_single(dvnode, file); + fscache_unuse_cookie(afs_vnode_cache(dvnode), NULL, NULL); + return ret; +} + +/* + * Read the directory into a folio_queue buffer in one go, scrubbing the + * previous contents. We return -ESTALE if the caller needs to call us again. + */ +ssize_t afs_read_dir(struct afs_vnode *dvnode, struct file *file) __acquires(&dvnode->validate_lock) { - struct address_space *mapping = dvnode->netfs.inode.i_mapping; - struct afs_read *req; + ssize_t ret; loff_t i_size; - int nr_pages, i; - int ret; - loff_t remote_size = 0; - _enter(""); - - req = kzalloc(sizeof(*req), GFP_KERNEL); - if (!req) - return ERR_PTR(-ENOMEM); - - refcount_set(&req->usage, 1); - req->vnode = dvnode; - req->key = key_get(key); - req->cleanup = afs_dir_read_cleanup; - -expand: i_size = i_size_read(&dvnode->netfs.inode); - if (i_size < remote_size) - i_size = remote_size; - if (i_size < 2048) { - ret = afs_bad(dvnode, afs_file_error_dir_small); - goto error; - } - if (i_size > 2048 * 1024) { - trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); - ret = -EFBIG; - goto error; - } - _enter("%llu", i_size); - - nr_pages = (i_size + PAGE_SIZE - 1) / PAGE_SIZE; - - req->actual_len = i_size; /* May change */ - req->len = nr_pages * PAGE_SIZE; /* We can ask for more than there is */ - req->data_version = dvnode->status.data_version; /* May change */ - iov_iter_xarray(&req->def_iter, ITER_DEST, &dvnode->netfs.inode.i_mapping->i_pages, - 0, i_size); - req->iter = &req->def_iter; - - /* Fill in any gaps that we might find where the memory reclaimer has - * been at work and pin all the folios. If there are any gaps, we will - * need to reread the entire directory contents. - */ - i = req->nr_pages; - while (i < nr_pages) { - struct folio *folio; - - folio = filemap_get_folio(mapping, i); - if (IS_ERR(folio)) { - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_stat_v(dvnode, n_inval); - folio = __filemap_get_folio(mapping, - i, FGP_LOCK | FGP_CREAT, - mapping->gfp_mask); - if (IS_ERR(folio)) { - ret = PTR_ERR(folio); - goto error; - } - folio_attach_private(folio, (void *)1); - folio_unlock(folio); - } - - req->nr_pages += folio_nr_pages(folio); - i += folio_nr_pages(folio); - } - - /* If we're going to reload, we need to lock all the pages to prevent - * races. - */ ret = -ERESTARTSYS; if (down_read_killable(&dvnode->validate_lock) < 0) goto error; - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - goto success; + /* We only need to reread the data if it became invalid - or if we + * haven't read it yet. + */ + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + test_bit(AFS_VNODE_DIR_READ, &dvnode->flags)) { + ret = i_size; + goto valid; + } up_read(&dvnode->validate_lock); if (down_write_killable(&dvnode->validate_lock) < 0) goto error; - if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { + if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + afs_invalidate_cache(dvnode, 0); + + if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) || + !test_bit(AFS_VNODE_DIR_READ, &dvnode->flags)) { trace_afs_reload_dir(dvnode); - ret = afs_fetch_data(dvnode, req); - if (ret < 0) - goto error_unlock; - - task_io_account_read(PAGE_SIZE * req->nr_pages); - - if (req->len < req->file_size) { - /* The content has grown, so we need to expand the - * buffer. - */ - up_write(&dvnode->validate_lock); - remote_size = req->file_size; - goto expand; - } - - /* Validate the data we just read. */ - ret = afs_dir_check(dvnode, req); + ret = afs_read_single(dvnode, file); if (ret < 0) goto error_unlock; // TODO: Trim excess pages set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags); + set_bit(AFS_VNODE_DIR_READ, &dvnode->flags); + } else { + ret = i_size; } downgrade_write(&dvnode->validate_lock); -success: - return req; +valid: + return ret; error_unlock: up_write(&dvnode->validate_lock); error: - afs_put_read(req); - _leave(" = %d", ret); - return ERR_PTR(ret); + _leave(" = %zd", ret); + return ret; } /* @@ -399,79 +367,69 @@ error: */ static int afs_dir_iterate_block(struct afs_vnode *dvnode, struct dir_context *ctx, - union afs_xdr_dir_block *block, - unsigned blkoff) + union afs_xdr_dir_block *block) { union afs_xdr_dirent *dire; - unsigned offset, next, curr, nr_slots; + unsigned int blknum, base, hdr, pos, next, nr_slots; size_t nlen; int tmp; - _enter("%llx,%x", ctx->pos, blkoff); + blknum = ctx->pos / AFS_DIR_BLOCK_SIZE; + base = blknum * AFS_DIR_SLOTS_PER_BLOCK; + hdr = (blknum == 0 ? AFS_DIR_RESV_BLOCKS0 : AFS_DIR_RESV_BLOCKS); + pos = DIV_ROUND_UP(ctx->pos, AFS_DIR_DIRENT_SIZE) - base; - curr = (ctx->pos - blkoff) / sizeof(union afs_xdr_dirent); + _enter("%llx,%x", ctx->pos, blknum); /* walk through the block, an entry at a time */ - for (offset = (blkoff == 0 ? AFS_DIR_RESV_BLOCKS0 : AFS_DIR_RESV_BLOCKS); - offset < AFS_DIR_SLOTS_PER_BLOCK; - offset = next - ) { + for (unsigned int slot = hdr; slot < AFS_DIR_SLOTS_PER_BLOCK; slot = next) { /* skip entries marked unused in the bitmap */ - if (!(block->hdr.bitmap[offset / 8] & - (1 << (offset % 8)))) { - _debug("ENT[%zu.%u]: unused", - blkoff / sizeof(union afs_xdr_dir_block), offset); - next = offset + 1; - if (offset >= curr) - ctx->pos = blkoff + - next * sizeof(union afs_xdr_dirent); + if (!(block->hdr.bitmap[slot / 8] & + (1 << (slot % 8)))) { + _debug("ENT[%x]: Unused", base + slot); + next = slot + 1; + if (next >= pos) + ctx->pos = (base + next) * sizeof(union afs_xdr_dirent); continue; } /* got a valid entry */ - dire = &block->dirents[offset]; + dire = &block->dirents[slot]; nlen = strnlen(dire->u.name, - sizeof(*block) - - offset * sizeof(union afs_xdr_dirent)); + (unsigned long)(block + 1) - (unsigned long)dire->u.name - 1); if (nlen > AFSNAMEMAX - 1) { - _debug("ENT[%zu]: name too long (len %u/%zu)", - blkoff / sizeof(union afs_xdr_dir_block), - offset, nlen); + _debug("ENT[%x]: Name too long (len %zx)", + base + slot, nlen); return afs_bad(dvnode, afs_file_error_dir_name_too_long); } - _debug("ENT[%zu.%u]: %s %zu \"%s\"", - blkoff / sizeof(union afs_xdr_dir_block), offset, - (offset < curr ? "skip" : "fill"), + _debug("ENT[%x]: %s %zx \"%s\"", + base + slot, (slot < pos ? "skip" : "fill"), nlen, dire->u.name); nr_slots = afs_dir_calc_slots(nlen); - next = offset + nr_slots; + next = slot + nr_slots; if (next > AFS_DIR_SLOTS_PER_BLOCK) { - _debug("ENT[%zu.%u]:" - " %u extends beyond end dir block" - " (len %zu)", - blkoff / sizeof(union afs_xdr_dir_block), - offset, next, nlen); + _debug("ENT[%x]: extends beyond end dir block (len %zx)", + base + slot, nlen); return afs_bad(dvnode, afs_file_error_dir_over_end); } /* Check that the name-extension dirents are all allocated */ for (tmp = 1; tmp < nr_slots; tmp++) { - unsigned int ix = offset + tmp; - if (!(block->hdr.bitmap[ix / 8] & (1 << (ix % 8)))) { - _debug("ENT[%zu.u]:" - " %u unmarked extension (%u/%u)", - blkoff / sizeof(union afs_xdr_dir_block), - offset, tmp, nr_slots); + unsigned int xslot = slot + tmp; + + if (!(block->hdr.bitmap[xslot / 8] & (1 << (xslot % 8)))) { + _debug("ENT[%x]: Unmarked extension (%x/%x)", + base + slot, tmp, nr_slots); return afs_bad(dvnode, afs_file_error_dir_unmarked_ext); } } /* skip if starts before the current position */ - if (offset < curr) { - if (next > curr) - ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); + if (slot < pos) { + if (next > pos) + ctx->pos = (base + next) * sizeof(union afs_xdr_dirent); continue; } @@ -485,75 +443,110 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, return 0; } - ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); + ctx->pos = (base + next) * sizeof(union afs_xdr_dirent); } _leave(" = 1 [more]"); return 1; } +struct afs_dir_iteration_ctx { + struct dir_context *dir_ctx; + int error; +}; + +/* + * Iterate through a kmapped directory segment. + */ +static size_t afs_dir_iterate_step(void *iter_base, size_t progress, size_t len, + void *priv, void *priv2) +{ + struct afs_dir_iteration_ctx *ctx = priv2; + struct afs_vnode *dvnode = priv; + int ret; + + if (WARN_ON_ONCE(progress % AFS_DIR_BLOCK_SIZE || + len % AFS_DIR_BLOCK_SIZE)) { + pr_err("Mis-iteration prog=%zx len=%zx\n", + progress % AFS_DIR_BLOCK_SIZE, + len % AFS_DIR_BLOCK_SIZE); + return len; + } + + do { + ret = afs_dir_iterate_block(dvnode, ctx->dir_ctx, iter_base); + if (ret != 1) + break; + + ctx->dir_ctx->pos = round_up(ctx->dir_ctx->pos, AFS_DIR_BLOCK_SIZE); + iter_base += AFS_DIR_BLOCK_SIZE; + len -= AFS_DIR_BLOCK_SIZE; + } while (len > 0); + + return len; +} + +/* + * Iterate through the directory folios. + */ +static int afs_dir_iterate_contents(struct inode *dir, struct dir_context *dir_ctx) +{ + struct afs_dir_iteration_ctx ctx = { .dir_ctx = dir_ctx }; + struct afs_vnode *dvnode = AFS_FS_I(dir); + struct iov_iter iter; + unsigned long long i_size = i_size_read(dir); + + /* Round the file position up to the next entry boundary */ + dir_ctx->pos = round_up(dir_ctx->pos, sizeof(union afs_xdr_dirent)); + + if (i_size <= 0 || dir_ctx->pos >= i_size) + return 0; + + iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, i_size); + iov_iter_advance(&iter, round_down(dir_ctx->pos, AFS_DIR_BLOCK_SIZE)); + + iterate_folioq(&iter, iov_iter_count(&iter), dvnode, &ctx, + afs_dir_iterate_step); + + if (ctx.error == -ESTALE) + afs_invalidate_dir(dvnode, afs_dir_invalid_iter_stale); + return ctx.error; +} + /* * iterate through the data blob that lists the contents of an AFS directory */ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, - struct key *key, afs_dataversion_t *_dir_version) + struct file *file, afs_dataversion_t *_dir_version) { struct afs_vnode *dvnode = AFS_FS_I(dir); - union afs_xdr_dir_block *dblock; - struct afs_read *req; - struct folio *folio; - unsigned offset, size; + int retry_limit = 100; int ret; - _enter("{%lu},%u,,", dir->i_ino, (unsigned)ctx->pos); + _enter("{%lu},%llx,,", dir->i_ino, ctx->pos); - if (test_bit(AFS_VNODE_DELETED, &AFS_FS_I(dir)->flags)) { - _leave(" = -ESTALE"); - return -ESTALE; - } - - req = afs_read_dir(dvnode, key); - if (IS_ERR(req)) - return PTR_ERR(req); - *_dir_version = req->data_version; - - /* round the file position up to the next entry boundary */ - ctx->pos += sizeof(union afs_xdr_dirent) - 1; - ctx->pos &= ~(sizeof(union afs_xdr_dirent) - 1); - - /* walk through the blocks in sequence */ - ret = 0; - while (ctx->pos < req->actual_len) { - /* Fetch the appropriate folio from the directory and re-add it - * to the LRU. We have all the pages pinned with an extra ref. - */ - folio = __filemap_get_folio(dir->i_mapping, ctx->pos / PAGE_SIZE, - FGP_ACCESSED, 0); - if (IS_ERR(folio)) { - ret = afs_bad(dvnode, afs_file_error_dir_missing_page); + do { + if (--retry_limit < 0) { + pr_warn("afs_read_dir(): Too many retries\n"); + ret = -ESTALE; break; } + ret = afs_read_dir(dvnode, file); + if (ret < 0) { + if (ret != -ESTALE) + break; + if (test_bit(AFS_VNODE_DELETED, &AFS_FS_I(dir)->flags)) { + ret = -ESTALE; + break; + } + continue; + } + *_dir_version = inode_peek_iversion_raw(dir); - offset = round_down(ctx->pos, sizeof(*dblock)) - folio_pos(folio); - size = min_t(loff_t, folio_size(folio), - req->actual_len - folio_pos(folio)); + ret = afs_dir_iterate_contents(dir, ctx); + up_read(&dvnode->validate_lock); + } while (ret == -ESTALE); - do { - dblock = kmap_local_folio(folio, offset); - ret = afs_dir_iterate_block(dvnode, ctx, dblock, - folio_pos(folio) + offset); - kunmap_local(dblock); - if (ret != 1) - goto out; - - } while (offset += sizeof(*dblock), offset < size); - - ret = 0; - } - -out: - up_read(&dvnode->validate_lock); - afs_put_read(req); _leave(" = %d", ret); return ret; } @@ -565,8 +558,7 @@ static int afs_readdir(struct file *file, struct dir_context *ctx) { afs_dataversion_t dir_version; - return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file), - &dir_version); + return afs_dir_iterate(file_inode(file), ctx, file, &dir_version); } /* @@ -606,22 +598,22 @@ static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name, * Do a lookup of a single name in a directory * - just returns the FID the dentry name maps to if found */ -static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, - struct afs_fid *fid, struct key *key, +static int afs_do_lookup_one(struct inode *dir, const struct qstr *name, + struct afs_fid *fid, afs_dataversion_t *_dir_version) { struct afs_super_info *as = dir->i_sb->s_fs_info; struct afs_lookup_one_cookie cookie = { .ctx.actor = afs_lookup_one_filldir, - .name = dentry->d_name, + .name = *name, .fid.vid = as->volume->vid }; int ret; - _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); + _enter("{%lu},{%.*s},", dir->i_ino, name->len, name->name); /* search the directory */ - ret = afs_dir_iterate(dir, &cookie.ctx, key, _dir_version); + ret = afs_dir_iterate(dir, &cookie.ctx, NULL, _dir_version); if (ret < 0) { _leave(" = %d [iter]", ret); return ret; @@ -656,19 +648,10 @@ static bool afs_lookup_filldir(struct dir_context *ctx, const char *name, BUILD_BUG_ON(sizeof(union afs_xdr_dir_block) != 2048); BUILD_BUG_ON(sizeof(union afs_xdr_dirent) != 32); - if (cookie->found) { - if (cookie->nr_fids < 50) { - cookie->fids[cookie->nr_fids].vnode = ino; - cookie->fids[cookie->nr_fids].unique = dtype; - cookie->nr_fids++; - } - } else if (cookie->name.len == nlen && - memcmp(cookie->name.name, name, nlen) == 0) { - cookie->fids[1].vnode = ino; - cookie->fids[1].unique = dtype; - cookie->found = 1; - if (cookie->one_only) - return false; + if (cookie->nr_fids < 50) { + cookie->fids[cookie->nr_fids].vnode = ino; + cookie->fids[cookie->nr_fids].unique = dtype; + cookie->nr_fids++; } return cookie->nr_fids < 50; @@ -788,8 +771,7 @@ static bool afs_server_supports_ibulk(struct afs_vnode *dvnode) * files in one go and create inodes for them. The inode of the file we were * asked for is returned. */ -static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, - struct key *key) +static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry) { struct afs_lookup_cookie *cookie; struct afs_vnode_param *vp; @@ -797,6 +779,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; struct inode *inode = NULL, *ti; afs_dataversion_t data_version = READ_ONCE(dvnode->status.data_version); + bool supports_ibulk; long ret; int i; @@ -813,19 +796,19 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, cookie->nr_fids = 2; /* slot 1 is saved for the fid we actually want * and slot 0 for the directory */ - if (!afs_server_supports_ibulk(dvnode)) - cookie->one_only = true; - - /* search the directory */ - ret = afs_dir_iterate(dir, &cookie->ctx, key, &data_version); + /* Search the directory for the named entry using the hash table... */ + ret = afs_dir_search(dvnode, &dentry->d_name, &cookie->fids[1], &data_version); if (ret < 0) goto out; - dentry->d_fsdata = (void *)(unsigned long)data_version; + supports_ibulk = afs_server_supports_ibulk(dvnode); + if (supports_ibulk) { + /* ...then scan linearly from that point for entries to lookup-ahead. */ + cookie->ctx.pos = (ret + 1) * AFS_DIR_DIRENT_SIZE; + afs_dir_iterate(dir, &cookie->ctx, NULL, &data_version); + } - ret = -ENOENT; - if (!cookie->found) - goto out; + dentry->d_fsdata = (void *)(unsigned long)data_version; /* Check to see if we already have an inode for the primary fid. */ inode = ilookup5(dir->i_sb, cookie->fids[1].vnode, @@ -884,7 +867,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, * the whole operation. */ afs_op_set_error(op, -ENOTSUPP); - if (!cookie->one_only) { + if (supports_ibulk) { op->ops = &afs_inline_bulk_status_operation; afs_begin_vnode_operation(op); afs_wait_for_operation(op); @@ -926,8 +909,7 @@ out: /* * Look up an entry in a directory with @sys substitution. */ -static struct dentry *afs_lookup_atsys(struct inode *dir, struct dentry *dentry, - struct key *key) +static struct dentry *afs_lookup_atsys(struct inode *dir, struct dentry *dentry) { struct afs_sysnames *subs; struct afs_net *net = afs_i2net(dir); @@ -975,7 +957,6 @@ out_s: afs_put_sysnames(subs); kfree(buf); out_p: - key_put(key); return ret; } @@ -989,7 +970,6 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, struct afs_fid fid = {}; struct inode *inode; struct dentry *d; - struct key *key; int ret; _enter("{%llx:%llu},%p{%pd},", @@ -1007,15 +987,9 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, return ERR_PTR(-ESTALE); } - key = afs_request_key(dvnode->volume->cell); - if (IS_ERR(key)) { - _leave(" = %ld [key]", PTR_ERR(key)); - return ERR_CAST(key); - } - - ret = afs_validate(dvnode, key); + ret = afs_validate(dvnode, NULL); if (ret < 0) { - key_put(key); + afs_dir_unuse_cookie(dvnode, ret); _leave(" = %d [val]", ret); return ERR_PTR(ret); } @@ -1025,11 +999,10 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, dentry->d_name.name[dentry->d_name.len - 3] == 's' && dentry->d_name.name[dentry->d_name.len - 2] == 'y' && dentry->d_name.name[dentry->d_name.len - 1] == 's') - return afs_lookup_atsys(dir, dentry, key); + return afs_lookup_atsys(dir, dentry); afs_stat_v(dvnode, n_lookup); - inode = afs_do_lookup(dir, dentry, key); - key_put(key); + inode = afs_do_lookup(dir, dentry); if (inode == ERR_PTR(-ENOENT)) inode = afs_try_auto_mntpt(dentry, dir); @@ -1051,21 +1024,12 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, /* * Check the validity of a dentry under RCU conditions. */ -static int afs_d_revalidate_rcu(struct dentry *dentry) +static int afs_d_revalidate_rcu(struct afs_vnode *dvnode, struct dentry *dentry) { - struct afs_vnode *dvnode; - struct dentry *parent; - struct inode *dir; long dir_version, de_version; _enter("%p", dentry); - /* Check the parent directory is still valid first. */ - parent = READ_ONCE(dentry->d_parent); - dir = d_inode_rcu(parent); - if (!dir) - return -ECHILD; - dvnode = AFS_FS_I(dir); if (test_bit(AFS_VNODE_DELETED, &dvnode->flags)) return -ECHILD; @@ -1093,11 +1057,11 @@ static int afs_d_revalidate_rcu(struct dentry *dentry) * - NOTE! the hit can be a negative hit too, so we can't assume we have an * inode */ -static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) +static int afs_d_revalidate(struct inode *parent_dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - struct afs_vnode *vnode, *dir; + struct afs_vnode *vnode, *dir = AFS_FS_I(parent_dir); struct afs_fid fid; - struct dentry *parent; struct inode *inode; struct key *key; afs_dataversion_t dir_version, invalid_before; @@ -1105,7 +1069,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) int ret; if (flags & LOOKUP_RCU) - return afs_d_revalidate_rcu(dentry); + return afs_d_revalidate_rcu(dir, dentry); if (d_really_is_positive(dentry)) { vnode = AFS_FS_I(d_inode(dentry)); @@ -1120,14 +1084,9 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) if (IS_ERR(key)) key = NULL; - /* Hold the parent dentry so we can peer at it */ - parent = dget_parent(dentry); - dir = AFS_FS_I(d_inode(parent)); - /* validate the parent directory */ ret = afs_validate(dir, key); if (ret == -ERESTARTSYS) { - dput(parent); key_put(key); return ret; } @@ -1155,7 +1114,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) afs_stat_v(dir, n_reval); /* search the directory for this vnode */ - ret = afs_do_lookup_one(&dir->netfs.inode, dentry, &fid, key, &dir_version); + ret = afs_do_lookup_one(&dir->netfs.inode, name, &fid, &dir_version); switch (ret) { case 0: /* the filename maps to something */ @@ -1199,22 +1158,19 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) goto out_valid; default: - _debug("failed to iterate dir %pd: %d", - parent, ret); + _debug("failed to iterate parent %pd2: %d", dentry, ret); goto not_found; } out_valid: dentry->d_fsdata = (void *)(unsigned long)dir_version; out_valid_noupdate: - dput(parent); key_put(key); _leave(" = 1 [valid]"); return 1; not_found: _debug("dropping dentry %pd2", dentry); - dput(parent); key_put(key); _leave(" = 0 [bad]"); @@ -1282,6 +1238,7 @@ void afs_check_for_remote_deletion(struct afs_operation *op) */ static void afs_vnode_new_inode(struct afs_operation *op) { + struct afs_vnode_param *dvp = &op->file[0]; struct afs_vnode_param *vp = &op->file[1]; struct afs_vnode *vnode; struct inode *inode; @@ -1301,6 +1258,10 @@ static void afs_vnode_new_inode(struct afs_operation *op) vnode = AFS_FS_I(inode); set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); + if (S_ISDIR(inode->i_mode)) + afs_mkdir_init_dir(vnode, dvp->vnode); + else if (S_ISLNK(inode->i_mode)) + afs_init_new_symlink(vnode, op); if (!afs_op_error(op)) afs_cache_permit(vnode, op->key, vnode->cb_break, &vp->scb); d_instantiate(op->dentry, inode); @@ -1317,18 +1278,21 @@ static void afs_create_success(struct afs_operation *op) static void afs_create_edit_dir(struct afs_operation *op) { + struct netfs_cache_resources cres = {}; struct afs_vnode_param *dvp = &op->file[0]; struct afs_vnode_param *vp = &op->file[1]; struct afs_vnode *dvnode = dvp->vnode; _enter("op=%08x", op->debug_id); + fscache_begin_write_operation(&cres, afs_vnode_cache(dvnode)); down_write(&dvnode->validate_lock); if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) afs_edit_dir_add(dvnode, &op->dentry->d_name, &vp->fid, op->create.reason); up_write(&dvnode->validate_lock); + fscache_end_operation(&cres); } static void afs_create_put(struct afs_operation *op) @@ -1356,6 +1320,7 @@ static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, { struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); + int ret; _enter("{%llx:%llu},{%pd},%ho", dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); @@ -1366,6 +1331,8 @@ static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, return PTR_ERR(op); } + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; op->file[0].modification = true; @@ -1375,7 +1342,9 @@ static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, op->create.reason = afs_edit_dir_for_mkdir; op->mtime = current_time(dir); op->ops = &afs_mkdir_operation; - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; } /* @@ -1388,8 +1357,8 @@ static void afs_dir_remove_subdir(struct dentry *dentry) clear_nlink(&vnode->netfs.inode); set_bit(AFS_VNODE_DELETED, &vnode->flags); - atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_clear_cb_promise(vnode, afs_cb_promise_clear_rmdir); + afs_invalidate_dir(vnode, afs_dir_invalid_subdir_removed); } } @@ -1403,18 +1372,21 @@ static void afs_rmdir_success(struct afs_operation *op) static void afs_rmdir_edit_dir(struct afs_operation *op) { + struct netfs_cache_resources cres = {}; struct afs_vnode_param *dvp = &op->file[0]; struct afs_vnode *dvnode = dvp->vnode; _enter("op=%08x", op->debug_id); afs_dir_remove_subdir(op->dentry); + fscache_begin_write_operation(&cres, afs_vnode_cache(dvnode)); down_write(&dvnode->validate_lock); if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) afs_edit_dir_remove(dvnode, &op->dentry->d_name, afs_edit_dir_for_rmdir); up_write(&dvnode->validate_lock); + fscache_end_operation(&cres); } static void afs_rmdir_put(struct afs_operation *op) @@ -1449,6 +1421,8 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) if (IS_ERR(op)) return PTR_ERR(op); + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; op->file[0].modification = true; @@ -1472,10 +1446,18 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) op->file[1].vnode = vnode; } - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + + /* Not all systems that can host afs servers have ENOTEMPTY. */ + if (ret == -EEXIST) + ret = -ENOTEMPTY; +out: + afs_dir_unuse_cookie(dvnode, ret); + return ret; error: - return afs_put_operation(op); + ret = afs_put_operation(op); + goto out; } /* @@ -1538,16 +1520,19 @@ static void afs_unlink_success(struct afs_operation *op) static void afs_unlink_edit_dir(struct afs_operation *op) { + struct netfs_cache_resources cres = {}; struct afs_vnode_param *dvp = &op->file[0]; struct afs_vnode *dvnode = dvp->vnode; _enter("op=%08x", op->debug_id); + fscache_begin_write_operation(&cres, afs_vnode_cache(dvnode)); down_write(&dvnode->validate_lock); if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) afs_edit_dir_remove(dvnode, &op->dentry->d_name, afs_edit_dir_for_unlink); up_write(&dvnode->validate_lock); + fscache_end_operation(&cres); } static void afs_unlink_put(struct afs_operation *op) @@ -1586,6 +1571,8 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) if (IS_ERR(op)) return PTR_ERR(op); + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; op->file[0].modification = true; @@ -1632,10 +1619,10 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) afs_wait_for_operation(op); } - return afs_put_operation(op); - error: - return afs_put_operation(op); + ret = afs_put_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; } static const struct afs_operation_ops afs_create_operation = { @@ -1669,6 +1656,8 @@ static int afs_create(struct mnt_idmap *idmap, struct inode *dir, goto error; } + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; op->file[0].modification = true; @@ -1679,7 +1668,9 @@ static int afs_create(struct mnt_idmap *idmap, struct inode *dir, op->create.reason = afs_edit_dir_for_create; op->mtime = current_time(dir); op->ops = &afs_create_operation; - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; error: d_drop(dentry); @@ -1744,6 +1735,8 @@ static int afs_link(struct dentry *from, struct inode *dir, goto error; } + fscache_use_cookie(afs_vnode_cache(dvnode), true); + ret = afs_validate(vnode, op->key); if (ret < 0) goto error_op; @@ -1759,10 +1752,13 @@ static int afs_link(struct dentry *from, struct inode *dir, op->dentry_2 = from; op->ops = &afs_link_operation; op->create.reason = afs_edit_dir_for_link; - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; error_op: afs_put_operation(op); + afs_dir_unuse_cookie(dvnode, ret); error: d_drop(dentry); _leave(" = %d", ret); @@ -1806,6 +1802,8 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, goto error; } + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; @@ -1814,7 +1812,9 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, op->create.reason = afs_edit_dir_for_symlink; op->create.symlink = content; op->mtime = current_time(dir); - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; error: d_drop(dentry); @@ -1846,6 +1846,7 @@ static void afs_rename_success(struct afs_operation *op) write_seqlock(&vnode->cb_lock); new_dv = vnode->status.data_version + 1; + trace_afs_set_dv(vnode, new_dv); vnode->status.data_version = new_dv; inode_set_iversion_raw(&vnode->netfs.inode, new_dv); @@ -1855,6 +1856,7 @@ static void afs_rename_success(struct afs_operation *op) static void afs_rename_edit_dir(struct afs_operation *op) { + struct netfs_cache_resources orig_cres = {}, new_cres = {}; struct afs_vnode_param *orig_dvp = &op->file[0]; struct afs_vnode_param *new_dvp = &op->file[1]; struct afs_vnode *orig_dvnode = orig_dvp->vnode; @@ -1871,6 +1873,10 @@ static void afs_rename_edit_dir(struct afs_operation *op) op->rename.rehash = NULL; } + fscache_begin_write_operation(&orig_cres, afs_vnode_cache(orig_dvnode)); + if (new_dvnode != orig_dvnode) + fscache_begin_write_operation(&new_cres, afs_vnode_cache(new_dvnode)); + down_write(&orig_dvnode->validate_lock); if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags) && orig_dvnode->status.data_version == orig_dvp->dv_before + orig_dvp->dv_delta) @@ -1920,6 +1926,9 @@ static void afs_rename_edit_dir(struct afs_operation *op) d_move(old_dentry, new_dentry); up_write(&new_dvnode->validate_lock); + fscache_end_operation(&orig_cres); + if (new_dvnode != orig_dvnode) + fscache_end_operation(&new_cres); } static void afs_rename_put(struct afs_operation *op) @@ -1972,6 +1981,10 @@ static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (IS_ERR(op)) return PTR_ERR(op); + fscache_use_cookie(afs_vnode_cache(orig_dvnode), true); + if (new_dvnode != orig_dvnode) + fscache_use_cookie(afs_vnode_cache(new_dvnode), true); + ret = afs_validate(vnode, op->key); afs_op_set_error(op, ret); if (ret < 0) @@ -2039,47 +2052,43 @@ static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, */ d_drop(old_dentry); - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); +out: + afs_dir_unuse_cookie(orig_dvnode, ret); + if (new_dvnode != orig_dvnode) + afs_dir_unuse_cookie(new_dvnode, ret); + return ret; error: - return afs_put_operation(op); + ret = afs_put_operation(op); + goto out; } /* - * Release a directory folio and clean up its private state if it's not busy - * - return true if the folio can now be released, false if not + * Write the file contents to the cache as a single blob. */ -static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags) +int afs_single_writepages(struct address_space *mapping, + struct writeback_control *wbc) { - struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); + struct afs_vnode *dvnode = AFS_FS_I(mapping->host); + struct iov_iter iter; + bool is_dir = (S_ISDIR(dvnode->netfs.inode.i_mode) && + !test_bit(AFS_VNODE_MOUNTPOINT, &dvnode->flags)); + int ret = 0; - _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio->index); + /* Need to lock to prevent the folio queue and folios from being thrown + * away. + */ + down_read(&dvnode->validate_lock); - folio_detach_private(folio); + if (is_dir ? + test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) : + atomic64_read(&dvnode->cb_expires_at) != AFS_NO_CB_PROMISE) { + iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, + i_size_read(&dvnode->netfs.inode)); + ret = netfs_writeback_single(mapping, wbc, &iter); + } - /* The directory will need reloading. */ - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_stat_v(dvnode, n_relpg); - return true; -} - -/* - * Invalidate part or all of a folio. - */ -static void afs_dir_invalidate_folio(struct folio *folio, size_t offset, - size_t length) -{ - struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); - - _enter("{%lu},%zu,%zu", folio->index, offset, length); - - BUG_ON(!folio_test_locked(folio)); - - /* The directory will need reloading. */ - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_stat_v(dvnode, n_inval); - - /* we clean up only if the entire folio is being invalidated */ - if (offset == 0 && length == folio_size(folio)) - folio_detach_private(folio); + up_read(&dvnode->validate_lock); + return ret; } diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index fe223fb78111..60a549f1d9c5 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "internal.h" #include "xdr_fs.h" @@ -105,23 +106,57 @@ static void afs_clear_contig_bits(union afs_xdr_dir_block *block, } /* - * Get a new directory folio. + * Get a specific block, extending the directory storage to cover it as needed. */ -static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index) +static union afs_xdr_dir_block *afs_dir_get_block(struct afs_dir_iter *iter, size_t block) { - struct address_space *mapping = vnode->netfs.inode.i_mapping; + struct folio_queue *fq; + struct afs_vnode *dvnode = iter->dvnode; struct folio *folio; + size_t blpos = block * AFS_DIR_BLOCK_SIZE; + size_t blend = (block + 1) * AFS_DIR_BLOCK_SIZE, fpos = iter->fpos; + int ret; - folio = __filemap_get_folio(mapping, index, - FGP_LOCK | FGP_ACCESSED | FGP_CREAT, - mapping->gfp_mask); - if (IS_ERR(folio)) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - return NULL; + if (dvnode->directory_size < blend) { + size_t cur_size = dvnode->directory_size; + + ret = netfs_alloc_folioq_buffer( + NULL, &dvnode->directory, &cur_size, blend, + mapping_gfp_mask(dvnode->netfs.inode.i_mapping)); + dvnode->directory_size = cur_size; + if (ret < 0) + goto fail; } - if (!folio_test_private(folio)) - folio_attach_private(folio, (void *)1); - return folio; + + fq = iter->fq; + if (!fq) + fq = dvnode->directory; + + /* Search the folio queue for the folio containing the block... */ + for (; fq; fq = fq->next) { + for (int s = iter->fq_slot; s < folioq_count(fq); s++) { + size_t fsize = folioq_folio_size(fq, s); + + if (blend <= fpos + fsize) { + /* ... and then return the mapped block. */ + folio = folioq_folio(fq, s); + if (WARN_ON_ONCE(folio_pos(folio) != fpos)) + goto fail; + iter->fq = fq; + iter->fq_slot = s; + iter->fpos = fpos; + return kmap_local_folio(folio, blpos - fpos); + } + fpos += fsize; + } + iter->fq_slot = 0; + } + +fail: + iter->fq = NULL; + iter->fq_slot = 0; + afs_invalidate_dir(dvnode, afs_dir_invalid_edit_get_block); + return NULL; } /* @@ -209,9 +244,8 @@ void afs_edit_dir_add(struct afs_vnode *vnode, { union afs_xdr_dir_block *meta, *block; union afs_xdr_dirent *de; - struct folio *folio0, *folio; - unsigned int need_slots, nr_blocks, b; - pgoff_t index; + struct afs_dir_iter iter = { .dvnode = vnode }; + unsigned int nr_blocks, b, entry; loff_t i_size; int slot; @@ -220,20 +254,17 @@ void afs_edit_dir_add(struct afs_vnode *vnode, i_size = i_size_read(&vnode->netfs.inode); if (i_size > AFS_DIR_BLOCK_SIZE * AFS_DIR_MAX_BLOCKS || (i_size & (AFS_DIR_BLOCK_SIZE - 1))) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_add_bad_size); return; } - folio0 = afs_dir_get_folio(vnode, 0); - if (!folio0) { - _leave(" [fgp]"); + meta = afs_dir_get_block(&iter, 0); + if (!meta) return; - } /* Work out how many slots we're going to need. */ - need_slots = afs_dir_calc_slots(name->len); + iter.nr_slots = afs_dir_calc_slots(name->len); - meta = kmap_local_folio(folio0, 0); if (i_size == 0) goto new_directory; nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; @@ -245,22 +276,21 @@ void afs_edit_dir_add(struct afs_vnode *vnode, /* If the directory extended into a new folio, then we need to * tack a new folio on the end. */ - index = b / AFS_DIR_BLOCKS_PER_PAGE; if (nr_blocks >= AFS_DIR_MAX_BLOCKS) - goto error; - if (index >= folio_nr_pages(folio0)) { - folio = afs_dir_get_folio(vnode, index); - if (!folio) - goto error; - } else { - folio = folio0; - } + goto error_too_many_blocks; - block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_pos(folio)); + /* Lower dir blocks have a counter in the header we can check. */ + if (b < AFS_DIR_BLOCKS_WITH_CTR && + meta->meta.alloc_ctrs[b] < iter.nr_slots) + continue; + + block = afs_dir_get_block(&iter, b); + if (!block) + goto error; /* Abandon the edit if we got a callback break. */ if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - goto invalidated; + goto already_invalidated; _debug("block %u: %2u %3u %u", b, @@ -275,31 +305,23 @@ void afs_edit_dir_add(struct afs_vnode *vnode, afs_set_i_size(vnode, (b + 1) * AFS_DIR_BLOCK_SIZE); } - /* Only lower dir blocks have a counter in the header. */ - if (b >= AFS_DIR_BLOCKS_WITH_CTR || - meta->meta.alloc_ctrs[b] >= need_slots) { - /* We need to try and find one or more consecutive - * slots to hold the entry. - */ - slot = afs_find_contig_bits(block, need_slots); - if (slot >= 0) { - _debug("slot %u", slot); - goto found_space; - } + /* We need to try and find one or more consecutive slots to + * hold the entry. + */ + slot = afs_find_contig_bits(block, iter.nr_slots); + if (slot >= 0) { + _debug("slot %u", slot); + goto found_space; } kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } } /* There are no spare slots of sufficient size, yet the operation * succeeded. Download the directory again. */ trace_afs_edit_dir(vnode, why, afs_edit_dir_create_nospc, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_add_no_slots); goto out_unmap; new_directory: @@ -307,8 +329,7 @@ new_directory: i_size = AFS_DIR_BLOCK_SIZE; afs_set_i_size(vnode, i_size); slot = AFS_DIR_RESV_BLOCKS0; - folio = folio0; - block = kmap_local_folio(folio, 0); + block = afs_dir_get_block(&iter, 0); nr_blocks = 1; b = 0; @@ -326,41 +347,39 @@ found_space: de->u.name[name->len] = 0; /* Adjust the bitmap. */ - afs_set_contig_bits(block, slot, need_slots); - kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } + afs_set_contig_bits(block, slot, iter.nr_slots); /* Adjust the allocation counter. */ if (b < AFS_DIR_BLOCKS_WITH_CTR) - meta->meta.alloc_ctrs[b] -= need_slots; + meta->meta.alloc_ctrs[b] -= iter.nr_slots; + + /* Adjust the hash chain. */ + entry = b * AFS_DIR_SLOTS_PER_BLOCK + slot; + iter.bucket = afs_dir_hash_name(name); + de->u.hash_next = meta->meta.hashtable[iter.bucket]; + meta->meta.hashtable[iter.bucket] = htons(entry); + kunmap_local(block); inode_inc_iversion_raw(&vnode->netfs.inode); afs_stat_v(vnode, n_dir_cr); _debug("Insert %s in %u[%u]", name->name, b, slot); + netfs_single_mark_inode_dirty(&vnode->netfs.inode); + out_unmap: kunmap_local(meta); - folio_unlock(folio0); - folio_put(folio0); _leave(""); return; -invalidated: +already_invalidated: trace_afs_edit_dir(vnode, why, afs_edit_dir_create_inval, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } goto out_unmap; +error_too_many_blocks: + afs_invalidate_dir(vnode, afs_dir_invalid_edit_add_too_many_blocks); error: trace_afs_edit_dir(vnode, why, afs_edit_dir_create_error, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); goto out_unmap; } @@ -374,13 +393,14 @@ error: void afs_edit_dir_remove(struct afs_vnode *vnode, struct qstr *name, enum afs_edit_dir_reason why) { - union afs_xdr_dir_block *meta, *block; - union afs_xdr_dirent *de; - struct folio *folio0, *folio; - unsigned int need_slots, nr_blocks, b; - pgoff_t index; + union afs_xdr_dir_block *meta, *block, *pblock; + union afs_xdr_dirent *de, *pde; + struct afs_dir_iter iter = { .dvnode = vnode }; + struct afs_fid fid; + unsigned int b, slot, entry; loff_t i_size; - int slot; + __be16 next; + int found; _enter(",,{%d,%s},", name->len, name->name); @@ -388,81 +408,95 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, if (i_size < AFS_DIR_BLOCK_SIZE || i_size > AFS_DIR_BLOCK_SIZE * AFS_DIR_MAX_BLOCKS || (i_size & (AFS_DIR_BLOCK_SIZE - 1))) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - return; - } - nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; - - folio0 = afs_dir_get_folio(vnode, 0); - if (!folio0) { - _leave(" [fgp]"); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_rem_bad_size); return; } - /* Work out how many slots we're going to discard. */ - need_slots = afs_dir_calc_slots(name->len); + if (!afs_dir_init_iter(&iter, name)) + return; - meta = kmap_local_folio(folio0, 0); + meta = afs_dir_find_block(&iter, 0); + if (!meta) + return; - /* Find a block that has sufficient slots available. Each folio - * contains two or more directory blocks. - */ - for (b = 0; b < nr_blocks; b++) { - index = b / AFS_DIR_BLOCKS_PER_PAGE; - if (index >= folio_nr_pages(folio0)) { - folio = afs_dir_get_folio(vnode, index); - if (!folio) - goto error; - } else { - folio = folio0; - } - - block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_pos(folio)); - - /* Abandon the edit if we got a callback break. */ - if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - goto invalidated; - - if (b > AFS_DIR_BLOCKS_WITH_CTR || - meta->meta.alloc_ctrs[b] <= AFS_DIR_SLOTS_PER_BLOCK - 1 - need_slots) { - slot = afs_dir_scan_block(block, name, b); - if (slot >= 0) - goto found_dirent; - } - - kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } + /* Find the entry in the blob. */ + found = afs_dir_search_bucket(&iter, name, &fid); + if (found < 0) { + /* Didn't find the dirent to clobber. Re-download. */ + trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_noent, + 0, 0, 0, 0, name->name); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_rem_wrong_name); + goto out_unmap; } - /* Didn't find the dirent to clobber. Download the directory again. */ - trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_noent, - 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - goto out_unmap; + entry = found; + b = entry / AFS_DIR_SLOTS_PER_BLOCK; + slot = entry % AFS_DIR_SLOTS_PER_BLOCK; -found_dirent: + block = afs_dir_find_block(&iter, b); + if (!block) + goto error; + if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) + goto already_invalidated; + + /* Check and clear the entry. */ de = &block->dirents[slot]; + if (de->u.valid != 1) + goto error_unmap; trace_afs_edit_dir(vnode, why, afs_edit_dir_delete, b, slot, ntohl(de->u.vnode), ntohl(de->u.unique), name->name); - memset(de, 0, sizeof(*de) * need_slots); - /* Adjust the bitmap. */ - afs_clear_contig_bits(block, slot, need_slots); - kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } + afs_clear_contig_bits(block, slot, iter.nr_slots); /* Adjust the allocation counter. */ if (b < AFS_DIR_BLOCKS_WITH_CTR) - meta->meta.alloc_ctrs[b] += need_slots; + meta->meta.alloc_ctrs[b] += iter.nr_slots; + + /* Clear the constituent entries. */ + next = de->u.hash_next; + memset(de, 0, sizeof(*de) * iter.nr_slots); + kunmap_local(block); + + /* Adjust the hash chain: if iter->prev_entry is 0, the hashtable head + * index is previous; otherwise it's slot number of the previous entry. + */ + if (!iter.prev_entry) { + __be16 prev_next = meta->meta.hashtable[iter.bucket]; + + if (unlikely(prev_next != htons(entry))) { + pr_warn("%llx:%llx:%x: not head of chain b=%x p=%x,%x e=%x %*s", + vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, + iter.bucket, iter.prev_entry, prev_next, entry, + name->len, name->name); + goto error; + } + meta->meta.hashtable[iter.bucket] = next; + } else { + unsigned int pb = iter.prev_entry / AFS_DIR_SLOTS_PER_BLOCK; + unsigned int ps = iter.prev_entry % AFS_DIR_SLOTS_PER_BLOCK; + __be16 prev_next; + + pblock = afs_dir_find_block(&iter, pb); + if (!pblock) + goto error; + pde = &pblock->dirents[ps]; + prev_next = pde->u.hash_next; + if (prev_next != htons(entry)) { + kunmap_local(pblock); + pr_warn("%llx:%llx:%x: not prev in chain b=%x p=%x,%x e=%x %*s", + vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, + iter.bucket, iter.prev_entry, prev_next, entry, + name->len, name->name); + goto error; + } + pde->u.hash_next = next; + kunmap_local(pblock); + } + + netfs_single_mark_inode_dirty(&vnode->netfs.inode); inode_set_iversion_raw(&vnode->netfs.inode, vnode->status.data_version); afs_stat_v(vnode, n_dir_rm); @@ -470,26 +504,20 @@ found_dirent: out_unmap: kunmap_local(meta); - folio_unlock(folio0); - folio_put(folio0); _leave(""); return; -invalidated: +already_invalidated: + kunmap_local(block); trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_inval, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } goto out_unmap; +error_unmap: + kunmap_local(block); error: trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_error, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); goto out_unmap; } @@ -502,9 +530,8 @@ void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_d { union afs_xdr_dir_block *block; union afs_xdr_dirent *de; - struct folio *folio; + struct afs_dir_iter iter = { .dvnode = vnode }; unsigned int nr_blocks, b; - pgoff_t index; loff_t i_size; int slot; @@ -512,39 +539,35 @@ void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_d i_size = i_size_read(&vnode->netfs.inode); if (i_size < AFS_DIR_BLOCK_SIZE) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_upd_bad_size); return; } + nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; /* Find a block that has sufficient slots available. Each folio * contains two or more directory blocks. */ for (b = 0; b < nr_blocks; b++) { - index = b / AFS_DIR_BLOCKS_PER_PAGE; - folio = afs_dir_get_folio(vnode, index); - if (!folio) + block = afs_dir_get_block(&iter, b); + if (!block) goto error; - block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_pos(folio)); - /* Abandon the edit if we got a callback break. */ if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - goto invalidated; + goto already_invalidated; slot = afs_dir_scan_block(block, &dotdot_name, b); if (slot >= 0) goto found_dirent; kunmap_local(block); - folio_unlock(folio); - folio_put(folio); } /* Didn't find the dirent to clobber. Download the directory again. */ trace_afs_edit_dir(vnode, why, afs_edit_dir_update_nodd, 0, 0, 0, 0, ".."); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_upd_no_dd); goto out; found_dirent: @@ -556,26 +579,70 @@ found_dirent: ntohl(de->u.vnode), ntohl(de->u.unique), ".."); kunmap_local(block); - folio_unlock(folio); - folio_put(folio); + netfs_single_mark_inode_dirty(&vnode->netfs.inode); inode_set_iversion_raw(&vnode->netfs.inode, vnode->status.data_version); out: _leave(""); return; -invalidated: +already_invalidated: kunmap_local(block); - folio_unlock(folio); - folio_put(folio); trace_afs_edit_dir(vnode, why, afs_edit_dir_update_inval, 0, 0, 0, 0, ".."); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); goto out; error: trace_afs_edit_dir(vnode, why, afs_edit_dir_update_error, 0, 0, 0, 0, ".."); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); goto out; } + +/* + * Initialise a new directory. We need to fill in the "." and ".." entries. + */ +void afs_mkdir_init_dir(struct afs_vnode *dvnode, struct afs_vnode *parent_dvnode) +{ + union afs_xdr_dir_block *meta; + struct afs_dir_iter iter = { .dvnode = dvnode }; + union afs_xdr_dirent *de; + unsigned int slot = AFS_DIR_RESV_BLOCKS0; + loff_t i_size; + + i_size = i_size_read(&dvnode->netfs.inode); + if (i_size != AFS_DIR_BLOCK_SIZE) { + afs_invalidate_dir(dvnode, afs_dir_invalid_edit_add_bad_size); + return; + } + + meta = afs_dir_get_block(&iter, 0); + if (!meta) + return; + + afs_edit_init_block(meta, meta, 0); + + de = &meta->dirents[slot]; + de->u.valid = 1; + de->u.vnode = htonl(dvnode->fid.vnode); + de->u.unique = htonl(dvnode->fid.unique); + memcpy(de->u.name, ".", 2); + trace_afs_edit_dir(dvnode, afs_edit_dir_for_mkdir, afs_edit_dir_mkdir, 0, slot, + dvnode->fid.vnode, dvnode->fid.unique, "."); + slot++; + + de = &meta->dirents[slot]; + de->u.valid = 1; + de->u.vnode = htonl(parent_dvnode->fid.vnode); + de->u.unique = htonl(parent_dvnode->fid.unique); + memcpy(de->u.name, "..", 3); + trace_afs_edit_dir(dvnode, afs_edit_dir_for_mkdir, afs_edit_dir_mkdir, 0, slot, + parent_dvnode->fid.vnode, parent_dvnode->fid.unique, ".."); + + afs_set_contig_bits(meta, AFS_DIR_RESV_BLOCKS0, 2); + meta->meta.alloc_ctrs[0] -= 2; + kunmap_local(meta); + + netfs_single_mark_inode_dirty(&dvnode->netfs.inode); + set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags); + set_bit(AFS_VNODE_DIR_READ, &dvnode->flags); +} diff --git a/fs/afs/dir_search.c b/fs/afs/dir_search.c new file mode 100644 index 000000000000..b25bd892db4d --- /dev/null +++ b/fs/afs/dir_search.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Search a directory's hash table. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * https://tools.ietf.org/html/draft-keiser-afs3-directory-object-00 + */ + +#include +#include +#include +#include +#include "internal.h" +#include "afs_fs.h" +#include "xdr_fs.h" + +/* + * Calculate the name hash. + */ +unsigned int afs_dir_hash_name(const struct qstr *name) +{ + const unsigned char *p = name->name; + unsigned int hash = 0, i; + int bucket; + + for (i = 0; i < name->len; i++) + hash = (hash * 173) + p[i]; + bucket = hash & (AFS_DIR_HASHTBL_SIZE - 1); + if (hash > INT_MAX) { + bucket = AFS_DIR_HASHTBL_SIZE - bucket; + bucket &= (AFS_DIR_HASHTBL_SIZE - 1); + } + return bucket; +} + +/* + * Reset a directory iterator. + */ +static bool afs_dir_reset_iter(struct afs_dir_iter *iter) +{ + unsigned long long i_size = i_size_read(&iter->dvnode->netfs.inode); + unsigned int nblocks; + + /* Work out the maximum number of steps we can take. */ + nblocks = umin(i_size / AFS_DIR_BLOCK_SIZE, AFS_DIR_MAX_BLOCKS); + if (!nblocks) + return false; + iter->loop_check = nblocks * (AFS_DIR_SLOTS_PER_BLOCK - AFS_DIR_RESV_BLOCKS); + iter->prev_entry = 0; /* Hash head is previous */ + return true; +} + +/* + * Initialise a directory iterator for looking up a name. + */ +bool afs_dir_init_iter(struct afs_dir_iter *iter, const struct qstr *name) +{ + iter->nr_slots = afs_dir_calc_slots(name->len); + iter->bucket = afs_dir_hash_name(name); + return afs_dir_reset_iter(iter); +} + +/* + * Get a specific block. + */ +union afs_xdr_dir_block *afs_dir_find_block(struct afs_dir_iter *iter, size_t block) +{ + struct folio_queue *fq = iter->fq; + struct afs_vnode *dvnode = iter->dvnode; + struct folio *folio; + size_t blpos = block * AFS_DIR_BLOCK_SIZE; + size_t blend = (block + 1) * AFS_DIR_BLOCK_SIZE, fpos = iter->fpos; + int slot = iter->fq_slot; + + _enter("%zx,%d", block, slot); + + if (iter->block) { + kunmap_local(iter->block); + iter->block = NULL; + } + + if (dvnode->directory_size < blend) + goto fail; + + if (!fq || blpos < fpos) { + fq = dvnode->directory; + slot = 0; + fpos = 0; + } + + /* Search the folio queue for the folio containing the block... */ + for (; fq; fq = fq->next) { + for (; slot < folioq_count(fq); slot++) { + size_t fsize = folioq_folio_size(fq, slot); + + if (blend <= fpos + fsize) { + /* ... and then return the mapped block. */ + folio = folioq_folio(fq, slot); + if (WARN_ON_ONCE(folio_pos(folio) != fpos)) + goto fail; + iter->fq = fq; + iter->fq_slot = slot; + iter->fpos = fpos; + iter->block = kmap_local_folio(folio, blpos - fpos); + return iter->block; + } + fpos += fsize; + } + slot = 0; + } + +fail: + iter->fq = NULL; + iter->fq_slot = 0; + afs_invalidate_dir(dvnode, afs_dir_invalid_edit_get_block); + return NULL; +} + +/* + * Search through a directory bucket. + */ +int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, + struct afs_fid *_fid) +{ + const union afs_xdr_dir_block *meta; + unsigned int entry; + int ret = -ESTALE; + + meta = afs_dir_find_block(iter, 0); + if (!meta) + return -ESTALE; + + entry = ntohs(meta->meta.hashtable[iter->bucket & (AFS_DIR_HASHTBL_SIZE - 1)]); + _enter("%x,%x", iter->bucket, entry); + + while (entry) { + const union afs_xdr_dir_block *block; + const union afs_xdr_dirent *dire; + unsigned int blnum = entry / AFS_DIR_SLOTS_PER_BLOCK; + unsigned int slot = entry % AFS_DIR_SLOTS_PER_BLOCK; + unsigned int resv = (blnum == 0 ? AFS_DIR_RESV_BLOCKS0 : AFS_DIR_RESV_BLOCKS); + + _debug("search %x", entry); + + if (slot < resv) { + kdebug("slot out of range h=%x rs=%2x sl=%2x-%2x", + iter->bucket, resv, slot, slot + iter->nr_slots - 1); + goto bad; + } + + block = afs_dir_find_block(iter, blnum); + if (!block) + goto bad; + dire = &block->dirents[slot]; + + if (slot + iter->nr_slots <= AFS_DIR_SLOTS_PER_BLOCK && + memcmp(dire->u.name, name->name, name->len) == 0 && + dire->u.name[name->len] == '\0') { + _fid->vnode = ntohl(dire->u.vnode); + _fid->unique = ntohl(dire->u.unique); + ret = entry; + goto found; + } + + iter->prev_entry = entry; + entry = ntohs(dire->u.hash_next); + if (!--iter->loop_check) { + kdebug("dir chain loop h=%x", iter->bucket); + goto bad; + } + } + + ret = -ENOENT; +found: + if (iter->block) { + kunmap_local(iter->block); + iter->block = NULL; + } + +bad: + if (ret == -ESTALE) + afs_invalidate_dir(iter->dvnode, afs_dir_invalid_iter_stale); + _leave(" = %d", ret); + return ret; +} + +/* + * Search the appropriate hash chain in the contents of an AFS directory. + */ +int afs_dir_search(struct afs_vnode *dvnode, struct qstr *name, + struct afs_fid *_fid, afs_dataversion_t *_dir_version) +{ + struct afs_dir_iter iter = { .dvnode = dvnode, }; + int ret, retry_limit = 3; + + _enter("{%lu},,,", dvnode->netfs.inode.i_ino); + + if (!afs_dir_init_iter(&iter, name)) + return -ENOENT; + do { + if (--retry_limit < 0) { + pr_warn("afs_read_dir(): Too many retries\n"); + ret = -ESTALE; + break; + } + ret = afs_read_dir(dvnode, NULL); + if (ret < 0) { + if (ret != -ESTALE) + break; + if (test_bit(AFS_VNODE_DELETED, &dvnode->flags)) { + ret = -ESTALE; + break; + } + continue; + } + *_dir_version = inode_peek_iversion_raw(&dvnode->netfs.inode); + + ret = afs_dir_search_bucket(&iter, name, _fid); + up_read(&dvnode->validate_lock); + if (ret == -ESTALE) + afs_dir_reset_iter(&iter); + } while (ret == -ESTALE); + + _leave(" = %d", ret); + return ret; +} diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index c4d2711e20ad..d8bf52f77d93 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -185,50 +185,6 @@ out: return ret == -ENOENT ? NULL : ERR_PTR(ret); } -/* - * Look up @cell in a dynroot directory. This is a substitution for the - * local cell name for the net namespace. - */ -static struct dentry *afs_lookup_atcell(struct dentry *dentry) -{ - struct afs_cell *cell; - struct afs_net *net = afs_d2net(dentry); - struct dentry *ret; - char *name; - int len; - - if (!net->ws_cell) - return ERR_PTR(-ENOENT); - - ret = ERR_PTR(-ENOMEM); - name = kmalloc(AFS_MAXCELLNAME + 1, GFP_KERNEL); - if (!name) - goto out_p; - - down_read(&net->cells_lock); - cell = net->ws_cell; - if (cell) { - len = cell->name_len; - memcpy(name, cell->name, len + 1); - } - up_read(&net->cells_lock); - - ret = ERR_PTR(-ENOENT); - if (!cell) - goto out_n; - - ret = lookup_one_len(name, dentry->d_parent, len); - - /* We don't want to d_add() the @cell dentry here as we don't want to - * the cached dentry to hide changes to the local cell name. - */ - -out_n: - kfree(name); -out_p: - return ret; -} - /* * Look up an entry in a dynroot directory. */ @@ -247,10 +203,6 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr return ERR_PTR(-ENAMETOOLONG); } - if (dentry->d_name.len == 5 && - memcmp(dentry->d_name.name, "@cell", 5) == 0) - return afs_lookup_atcell(dentry); - return d_splice_alias(afs_try_auto_mntpt(dentry, dir), dentry); } @@ -271,7 +223,8 @@ const struct dentry_operations afs_dynroot_dentry_operations = { int afs_dynroot_mkdir(struct afs_net *net, struct afs_cell *cell) { struct super_block *sb = net->dynroot_sb; - struct dentry *root, *subdir; + struct dentry *root, *subdir, *dsubdir; + char *dotname = cell->name - 1; int ret; if (!sb || atomic_read(&sb->s_active) == 0) @@ -286,34 +239,31 @@ int afs_dynroot_mkdir(struct afs_net *net, struct afs_cell *cell) goto unlock; } - /* Note that we're retaining an extra ref on the dentry */ + dsubdir = lookup_one_len(dotname, root, cell->name_len + 1); + if (IS_ERR(dsubdir)) { + ret = PTR_ERR(dsubdir); + dput(subdir); + goto unlock; + } + + /* Note that we're retaining extra refs on the dentries. */ subdir->d_fsdata = (void *)1UL; + dsubdir->d_fsdata = (void *)1UL; ret = 0; unlock: inode_unlock(root->d_inode); return ret; } -/* - * Remove a manually added cell mount directory. - * - The caller must hold net->proc_cells_lock - */ -void afs_dynroot_rmdir(struct afs_net *net, struct afs_cell *cell) +static void afs_dynroot_rm_one_dir(struct dentry *root, const char *name, size_t name_len) { - struct super_block *sb = net->dynroot_sb; - struct dentry *root, *subdir; - - if (!sb || atomic_read(&sb->s_active) == 0) - return; - - root = sb->s_root; - inode_lock(root->d_inode); + struct dentry *subdir; /* Don't want to trigger a lookup call, which will re-add the cell */ - subdir = try_lookup_one_len(cell->name, root, cell->name_len); + subdir = try_lookup_one_len(name, root, name_len); if (IS_ERR_OR_NULL(subdir)) { _debug("lookup %ld", PTR_ERR(subdir)); - goto no_dentry; + return; } _debug("rmdir %pd %u", subdir, d_count(subdir)); @@ -324,11 +274,152 @@ void afs_dynroot_rmdir(struct afs_net *net, struct afs_cell *cell) dput(subdir); } dput(subdir); -no_dentry: - inode_unlock(root->d_inode); +} + +/* + * Remove a manually added cell mount directory. + * - The caller must hold net->proc_cells_lock + */ +void afs_dynroot_rmdir(struct afs_net *net, struct afs_cell *cell) +{ + struct super_block *sb = net->dynroot_sb; + char *dotname = cell->name - 1; + + if (!sb || atomic_read(&sb->s_active) == 0) + return; + + inode_lock(sb->s_root->d_inode); + afs_dynroot_rm_one_dir(sb->s_root, cell->name, cell->name_len); + afs_dynroot_rm_one_dir(sb->s_root, dotname, cell->name_len + 1); + inode_unlock(sb->s_root->d_inode); _leave(""); } +static void afs_atcell_delayed_put_cell(void *arg) +{ + struct afs_cell *cell = arg; + + afs_put_cell(cell, afs_cell_trace_put_atcell); +} + +/* + * Read @cell or .@cell symlinks. + */ +static const char *afs_atcell_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) +{ + struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_cell *cell; + struct afs_net *net = afs_i2net(inode); + const char *name; + bool dotted = vnode->fid.vnode == 3; + + if (!net->ws_cell) + return ERR_PTR(-ENOENT); + + down_read(&net->cells_lock); + + cell = net->ws_cell; + if (dotted) + name = cell->name - 1; + else + name = cell->name; + afs_get_cell(cell, afs_cell_trace_get_atcell); + set_delayed_call(done, afs_atcell_delayed_put_cell, cell); + + up_read(&net->cells_lock); + return name; +} + +static const struct inode_operations afs_atcell_inode_operations = { + .get_link = afs_atcell_get_link, +}; + +/* + * Look up @cell or .@cell in a dynroot directory. This is a substitution for + * the local cell name for the net namespace. + */ +static struct dentry *afs_dynroot_create_symlink(struct dentry *root, const char *name) +{ + struct afs_vnode *vnode; + struct afs_fid fid = { .vnode = 2, .unique = 1, }; + struct dentry *dentry; + struct inode *inode; + + if (name[0] == '.') + fid.vnode = 3; + + dentry = d_alloc_name(root, name); + if (!dentry) + return ERR_PTR(-ENOMEM); + + inode = iget5_locked(dentry->d_sb, fid.vnode, + afs_iget5_pseudo_test, afs_iget5_pseudo_set, &fid); + if (!inode) { + dput(dentry); + return ERR_PTR(-ENOMEM); + } + + vnode = AFS_FS_I(inode); + + /* there shouldn't be an existing inode */ + if (WARN_ON_ONCE(!(inode->i_state & I_NEW))) { + iput(inode); + dput(dentry); + return ERR_PTR(-EIO); + } + + netfs_inode_init(&vnode->netfs, NULL, false); + simple_inode_init_ts(inode); + set_nlink(inode, 1); + inode->i_size = 0; + inode->i_mode = S_IFLNK | 0555; + inode->i_op = &afs_atcell_inode_operations; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + inode->i_blocks = 0; + inode->i_generation = 0; + inode->i_flags |= S_NOATIME; + + unlock_new_inode(inode); + d_splice_alias(inode, dentry); + return dentry; +} + +/* + * Create @cell and .@cell symlinks. + */ +static int afs_dynroot_symlink(struct afs_net *net) +{ + struct super_block *sb = net->dynroot_sb; + struct dentry *root, *symlink, *dsymlink; + int ret; + + /* Let the ->lookup op do the creation */ + root = sb->s_root; + inode_lock(root->d_inode); + symlink = afs_dynroot_create_symlink(root, "@cell"); + if (IS_ERR(symlink)) { + ret = PTR_ERR(symlink); + goto unlock; + } + + dsymlink = afs_dynroot_create_symlink(root, ".@cell"); + if (IS_ERR(dsymlink)) { + ret = PTR_ERR(dsymlink); + dput(symlink); + goto unlock; + } + + /* Note that we're retaining extra refs on the dentries. */ + symlink->d_fsdata = (void *)1UL; + dsymlink->d_fsdata = (void *)1UL; + ret = 0; +unlock: + inode_unlock(root->d_inode); + return ret; +} + /* * Populate a newly created dynamic root with cell names. */ @@ -341,6 +432,10 @@ int afs_dynroot_populate(struct super_block *sb) mutex_lock(&net->proc_cells_lock); net->dynroot_sb = sb; + ret = afs_dynroot_symlink(net); + if (ret < 0) + goto error; + hlist_for_each_entry(cell, &net->proc_cells, proc_link) { ret = afs_dynroot_mkdir(net, cell); if (ret < 0) diff --git a/fs/afs/file.c b/fs/afs/file.c index 6762eff97517..fc15497608c6 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -20,7 +20,6 @@ #include "internal.h" static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); -static int afs_symlink_read_folio(struct file *file, struct folio *folio); static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos, @@ -61,13 +60,6 @@ const struct address_space_operations afs_file_aops = { .writepages = afs_writepages, }; -const struct address_space_operations afs_symlink_aops = { - .read_folio = afs_symlink_read_folio, - .release_folio = netfs_release_folio, - .invalidate_folio = netfs_invalidate_folio, - .migrate_folio = filemap_migrate_folio, -}; - static const struct vm_operations_struct afs_vm_ops = { .open = afs_vm_open, .close = afs_vm_close, @@ -208,49 +200,12 @@ int afs_release(struct inode *inode, struct file *file) return ret; } -/* - * Allocate a new read record. - */ -struct afs_read *afs_alloc_read(gfp_t gfp) -{ - struct afs_read *req; - - req = kzalloc(sizeof(struct afs_read), gfp); - if (req) - refcount_set(&req->usage, 1); - - return req; -} - -/* - * Dispose of a ref to a read record. - */ -void afs_put_read(struct afs_read *req) -{ - if (refcount_dec_and_test(&req->usage)) { - if (req->cleanup) - req->cleanup(req); - key_put(req->key); - kfree(req); - } -} - static void afs_fetch_data_notify(struct afs_operation *op) { - struct afs_read *req = op->fetch.req; - struct netfs_io_subrequest *subreq = req->subreq; - int error = afs_op_error(op); + struct netfs_io_subrequest *subreq = op->fetch.subreq; - req->error = error; - if (subreq) { - subreq->rreq->i_size = req->file_size; - if (req->pos + req->actual_len >= req->file_size) - __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); - netfs_read_subreq_terminated(subreq, error, false); - req->subreq = NULL; - } else if (req->done) { - req->done(req); - } + subreq->error = afs_op_error(op); + netfs_read_subreq_terminated(subreq); } static void afs_fetch_data_success(struct afs_operation *op) @@ -260,7 +215,7 @@ static void afs_fetch_data_success(struct afs_operation *op) _enter("op=%08x", op->debug_id); afs_vnode_commit_status(op, &op->file[0]); afs_stat_v(vnode, n_fetches); - atomic_long_add(op->fetch.req->actual_len, &op->net->n_fetch_bytes); + atomic_long_add(op->fetch.subreq->transferred, &op->net->n_fetch_bytes); afs_fetch_data_notify(op); } @@ -270,107 +225,188 @@ static void afs_fetch_data_aborted(struct afs_operation *op) afs_fetch_data_notify(op); } -static void afs_fetch_data_put(struct afs_operation *op) -{ - op->fetch.req->error = afs_op_error(op); - afs_put_read(op->fetch.req); -} - -static const struct afs_operation_ops afs_fetch_data_operation = { +const struct afs_operation_ops afs_fetch_data_operation = { .issue_afs_rpc = afs_fs_fetch_data, .issue_yfs_rpc = yfs_fs_fetch_data, .success = afs_fetch_data_success, .aborted = afs_fetch_data_aborted, .failed = afs_fetch_data_notify, - .put = afs_fetch_data_put, }; +static void afs_issue_read_call(struct afs_operation *op) +{ + op->call_responded = false; + op->call_error = 0; + op->call_abort_code = 0; + if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags)) + yfs_fs_fetch_data(op); + else + afs_fs_fetch_data(op); +} + +static void afs_end_read(struct afs_operation *op) +{ + if (op->call_responded && op->server) + set_bit(AFS_SERVER_FL_RESPONDING, &op->server->flags); + + if (!afs_op_error(op)) + afs_fetch_data_success(op); + else if (op->cumul_error.aborted) + afs_fetch_data_aborted(op); + else + afs_fetch_data_notify(op); + + afs_end_vnode_operation(op); + afs_put_operation(op); +} + +/* + * Perform I/O processing on an asynchronous call. The work item carries a ref + * to the call struct that we either need to release or to pass on. + */ +static void afs_read_receive(struct afs_call *call) +{ + struct afs_operation *op = call->op; + enum afs_call_state state; + + _enter(""); + + state = READ_ONCE(call->state); + if (state == AFS_CALL_COMPLETE) + return; + trace_afs_read_recv(op, call); + + while (state < AFS_CALL_COMPLETE && READ_ONCE(call->need_attention)) { + WRITE_ONCE(call->need_attention, false); + afs_deliver_to_call(call); + state = READ_ONCE(call->state); + } + + if (state < AFS_CALL_COMPLETE) { + netfs_read_subreq_progress(op->fetch.subreq); + if (rxrpc_kernel_check_life(call->net->socket, call->rxcall)) + return; + /* rxrpc terminated the call. */ + afs_set_call_complete(call, call->error, call->abort_code); + } + + op->call_abort_code = call->abort_code; + op->call_error = call->error; + op->call_responded = call->responded; + op->call = NULL; + call->op = NULL; + afs_put_call(call); + + /* If the call failed, then we need to crank the server rotation + * handle and try the next. + */ + if (afs_select_fileserver(op)) { + afs_issue_read_call(op); + return; + } + + afs_end_read(op); +} + +void afs_fetch_data_async_rx(struct work_struct *work) +{ + struct afs_call *call = container_of(work, struct afs_call, async_work); + + afs_read_receive(call); + afs_put_call(call); +} + +void afs_fetch_data_immediate_cancel(struct afs_call *call) +{ + if (call->async) { + afs_get_call(call, afs_call_trace_wake); + if (!queue_work(afs_async_calls, &call->async_work)) + afs_deferred_put_call(call); + flush_work(&call->async_work); + } +} + /* * Fetch file data from the volume. */ -int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req) +static void afs_issue_read(struct netfs_io_subrequest *subreq) { struct afs_operation *op; + struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode); + struct key *key = subreq->rreq->netfs_priv; _enter("%s{%llx:%llu.%u},%x,,,", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, - key_serial(req->key)); + key_serial(key)); - op = afs_alloc_operation(req->key, vnode->volume); + op = afs_alloc_operation(key, vnode->volume); if (IS_ERR(op)) { - if (req->subreq) - netfs_read_subreq_terminated(req->subreq, PTR_ERR(op), false); - return PTR_ERR(op); + subreq->error = PTR_ERR(op); + netfs_read_subreq_terminated(subreq); + return; } afs_op_set_vnode(op, 0, vnode); - op->fetch.req = afs_get_read(req); + op->fetch.subreq = subreq; op->ops = &afs_fetch_data_operation; - return afs_do_sync_operation(op); -} - -static void afs_read_worker(struct work_struct *work) -{ - struct netfs_io_subrequest *subreq = container_of(work, struct netfs_io_subrequest, work); - struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode); - struct afs_read *fsreq; - - fsreq = afs_alloc_read(GFP_NOFS); - if (!fsreq) - return netfs_read_subreq_terminated(subreq, -ENOMEM, false); - - fsreq->subreq = subreq; - fsreq->pos = subreq->start + subreq->transferred; - fsreq->len = subreq->len - subreq->transferred; - fsreq->key = key_get(subreq->rreq->netfs_priv); - fsreq->vnode = vnode; - fsreq->iter = &subreq->io_iter; trace_netfs_sreq(subreq, netfs_sreq_trace_submit); - afs_fetch_data(fsreq->vnode, fsreq); - afs_put_read(fsreq); -} -static void afs_issue_read(struct netfs_io_subrequest *subreq) -{ - INIT_WORK(&subreq->work, afs_read_worker); - queue_work(system_long_wq, &subreq->work); -} + if (subreq->rreq->origin == NETFS_READAHEAD || + subreq->rreq->iocb) { + op->flags |= AFS_OPERATION_ASYNC; -static int afs_symlink_read_folio(struct file *file, struct folio *folio) -{ - struct afs_vnode *vnode = AFS_FS_I(folio->mapping->host); - struct afs_read *fsreq; - int ret; + if (!afs_begin_vnode_operation(op)) { + subreq->error = afs_put_operation(op); + netfs_read_subreq_terminated(subreq); + return; + } - fsreq = afs_alloc_read(GFP_NOFS); - if (!fsreq) - return -ENOMEM; + if (!afs_select_fileserver(op)) { + afs_end_read(op); + return; + } - fsreq->pos = folio_pos(folio); - fsreq->len = folio_size(folio); - fsreq->vnode = vnode; - fsreq->iter = &fsreq->def_iter; - iov_iter_xarray(&fsreq->def_iter, ITER_DEST, &folio->mapping->i_pages, - fsreq->pos, fsreq->len); - - ret = afs_fetch_data(fsreq->vnode, fsreq); - if (ret == 0) - folio_mark_uptodate(folio); - folio_unlock(folio); - return ret; + afs_issue_read_call(op); + } else { + afs_do_sync_operation(op); + } } static int afs_init_request(struct netfs_io_request *rreq, struct file *file) { + struct afs_vnode *vnode = AFS_FS_I(rreq->inode); + if (file) rreq->netfs_priv = key_get(afs_file_key(file)); rreq->rsize = 256 * 1024; rreq->wsize = 256 * 1024 * 1024; + + switch (rreq->origin) { + case NETFS_READ_SINGLE: + if (!file) { + struct key *key = afs_request_key(vnode->volume->cell); + + if (IS_ERR(key)) + return PTR_ERR(key); + rreq->netfs_priv = key; + } + break; + case NETFS_WRITEBACK: + case NETFS_WRITETHROUGH: + case NETFS_UNBUFFERED_WRITE: + case NETFS_DIO_WRITE: + if (S_ISREG(rreq->inode->i_mode)) + rreq->io_streams[0].avail = true; + break; + case NETFS_WRITEBACK_SINGLE: + default: + break; + } return 0; } diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c index 428721bbe4f6..8418813ee043 100644 --- a/fs/afs/fs_operation.c +++ b/fs/afs/fs_operation.c @@ -49,6 +49,105 @@ struct afs_operation *afs_alloc_operation(struct key *key, struct afs_volume *vo return op; } +struct afs_io_locker { + struct list_head link; + struct task_struct *task; + unsigned long have_lock; +}; + +/* + * Unlock the I/O lock on a vnode. + */ +static void afs_unlock_for_io(struct afs_vnode *vnode) +{ + struct afs_io_locker *locker; + + spin_lock(&vnode->lock); + locker = list_first_entry_or_null(&vnode->io_lock_waiters, + struct afs_io_locker, link); + if (locker) { + list_del(&locker->link); + smp_store_release(&locker->have_lock, 1); /* The unlock barrier. */ + smp_mb__after_atomic(); /* Store have_lock before task state */ + wake_up_process(locker->task); + } else { + clear_bit(AFS_VNODE_IO_LOCK, &vnode->flags); + } + spin_unlock(&vnode->lock); +} + +/* + * Lock the I/O lock on a vnode uninterruptibly. We can't use an ordinary + * mutex as lockdep will complain if we unlock it in the wrong thread. + */ +static void afs_lock_for_io(struct afs_vnode *vnode) +{ + struct afs_io_locker myself = { .task = current, }; + + spin_lock(&vnode->lock); + + if (!test_and_set_bit(AFS_VNODE_IO_LOCK, &vnode->flags)) { + spin_unlock(&vnode->lock); + return; + } + + list_add_tail(&myself.link, &vnode->io_lock_waiters); + spin_unlock(&vnode->lock); + + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (smp_load_acquire(&myself.have_lock)) /* The lock barrier */ + break; + schedule(); + } + __set_current_state(TASK_RUNNING); +} + +/* + * Lock the I/O lock on a vnode interruptibly. We can't use an ordinary mutex + * as lockdep will complain if we unlock it in the wrong thread. + */ +static int afs_lock_for_io_interruptible(struct afs_vnode *vnode) +{ + struct afs_io_locker myself = { .task = current, }; + int ret = 0; + + spin_lock(&vnode->lock); + + if (!test_and_set_bit(AFS_VNODE_IO_LOCK, &vnode->flags)) { + spin_unlock(&vnode->lock); + return 0; + } + + list_add_tail(&myself.link, &vnode->io_lock_waiters); + spin_unlock(&vnode->lock); + + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + if (smp_load_acquire(&myself.have_lock) || /* The lock barrier */ + signal_pending(current)) + break; + schedule(); + } + __set_current_state(TASK_RUNNING); + + /* If we got a signal, try to transfer the lock onto the next + * waiter. + */ + if (unlikely(signal_pending(current))) { + spin_lock(&vnode->lock); + if (myself.have_lock) { + spin_unlock(&vnode->lock); + afs_unlock_for_io(vnode); + } else { + list_del(&myself.link); + spin_unlock(&vnode->lock); + } + ret = -ERESTARTSYS; + } + return ret; +} + /* * Lock the vnode(s) being operated upon. */ @@ -60,7 +159,7 @@ static bool afs_get_io_locks(struct afs_operation *op) _enter(""); if (op->flags & AFS_OPERATION_UNINTR) { - mutex_lock(&vnode->io_lock); + afs_lock_for_io(vnode); op->flags |= AFS_OPERATION_LOCK_0; _leave(" = t [1]"); return true; @@ -72,7 +171,7 @@ static bool afs_get_io_locks(struct afs_operation *op) if (vnode2 > vnode) swap(vnode, vnode2); - if (mutex_lock_interruptible(&vnode->io_lock) < 0) { + if (afs_lock_for_io_interruptible(vnode) < 0) { afs_op_set_error(op, -ERESTARTSYS); op->flags |= AFS_OPERATION_STOP; _leave(" = f [I 0]"); @@ -81,10 +180,10 @@ static bool afs_get_io_locks(struct afs_operation *op) op->flags |= AFS_OPERATION_LOCK_0; if (vnode2) { - if (mutex_lock_interruptible_nested(&vnode2->io_lock, 1) < 0) { + if (afs_lock_for_io_interruptible(vnode2) < 0) { afs_op_set_error(op, -ERESTARTSYS); op->flags |= AFS_OPERATION_STOP; - mutex_unlock(&vnode->io_lock); + afs_unlock_for_io(vnode); op->flags &= ~AFS_OPERATION_LOCK_0; _leave(" = f [I 1]"); return false; @@ -104,9 +203,9 @@ static void afs_drop_io_locks(struct afs_operation *op) _enter(""); if (op->flags & AFS_OPERATION_LOCK_1) - mutex_unlock(&vnode2->io_lock); + afs_unlock_for_io(vnode2); if (op->flags & AFS_OPERATION_LOCK_0) - mutex_unlock(&vnode->io_lock); + afs_unlock_for_io(vnode); } static void afs_prepare_vnode(struct afs_operation *op, struct afs_vnode_param *vp, @@ -157,7 +256,7 @@ bool afs_begin_vnode_operation(struct afs_operation *op) /* * Tidy up a filesystem cursor and unlock the vnode. */ -static void afs_end_vnode_operation(struct afs_operation *op) +void afs_end_vnode_operation(struct afs_operation *op) { _enter(""); diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 098fa034a1cc..1d9ecd5418d8 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -301,19 +301,19 @@ void afs_fs_fetch_status(struct afs_operation *op) static int afs_deliver_fs_fetch_data(struct afs_call *call) { struct afs_operation *op = call->op; + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; - struct afs_read *req = op->fetch.req; const __be32 *bp; size_t count_before; int ret; _enter("{%u,%zu,%zu/%llu}", call->unmarshall, call->iov_len, iov_iter_count(call->iter), - req->actual_len); + call->remaining); switch (call->unmarshall) { case 0: - req->actual_len = 0; + call->remaining = 0; call->unmarshall++; if (call->operation_ID == FSFETCHDATA64) { afs_extract_to_tmp64(call); @@ -323,8 +323,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) } fallthrough; - /* Extract the returned data length into - * ->actual_len. This may indicate more or less data than was + /* Extract the returned data length into ->remaining. + * This may indicate more or less data than was * requested will be returned. */ case 1: @@ -333,42 +333,40 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) if (ret < 0) return ret; - req->actual_len = be64_to_cpu(call->tmp64); - _debug("DATA length: %llu", req->actual_len); + call->remaining = be64_to_cpu(call->tmp64); + _debug("DATA length: %llu", call->remaining); - if (req->actual_len == 0) + if (call->remaining == 0) goto no_more_data; - call->iter = req->iter; - call->iov_len = min(req->actual_len, req->len); + call->iter = &subreq->io_iter; + call->iov_len = umin(call->remaining, subreq->len - subreq->transferred); call->unmarshall++; fallthrough; /* extract the returned data */ case 2: count_before = call->iov_len; - _debug("extract data %zu/%llu", count_before, req->actual_len); + _debug("extract data %zu/%llu", count_before, call->remaining); ret = afs_extract_data(call, true); - if (req->subreq) { - req->subreq->transferred += count_before - call->iov_len; - netfs_read_subreq_progress(req->subreq, false); - } + subreq->transferred += count_before - call->iov_len; + call->remaining -= count_before - call->iov_len; if (ret < 0) return ret; call->iter = &call->def_iter; - if (req->actual_len <= req->len) + if (call->remaining) goto no_more_data; /* Discard any excess data the server gave us */ - afs_extract_discard(call, req->actual_len - req->len); + afs_extract_discard(call, call->remaining); call->unmarshall = 3; fallthrough; case 3: _debug("extract discard %zu/%llu", - iov_iter_count(call->iter), req->actual_len - req->len); + iov_iter_count(call->iter), call->remaining); ret = afs_extract_data(call, true); if (ret < 0) @@ -390,8 +388,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) xdr_decode_AFSCallBack(&bp, call, &vp->scb); xdr_decode_AFSVolSync(&bp, &op->volsync); - req->data_version = vp->scb.status.data_version; - req->file_size = vp->scb.status.size; + if (subreq->start + subreq->transferred >= vp->scb.status.size) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); call->unmarshall++; fallthrough; @@ -410,14 +408,18 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) static const struct afs_call_type afs_RXFSFetchData = { .name = "FS.FetchData", .op = afs_FS_FetchData, + .async_rx = afs_fetch_data_async_rx, .deliver = afs_deliver_fs_fetch_data, + .immediate_cancel = afs_fetch_data_immediate_cancel, .destructor = afs_flat_call_destructor, }; static const struct afs_call_type afs_RXFSFetchData64 = { .name = "FS.FetchData64", .op = afs_FS_FetchData64, + .async_rx = afs_fetch_data_async_rx, .deliver = afs_deliver_fs_fetch_data, + .immediate_cancel = afs_fetch_data_immediate_cancel, .destructor = afs_flat_call_destructor, }; @@ -426,8 +428,8 @@ static const struct afs_call_type afs_RXFSFetchData64 = { */ static void afs_fs_fetch_data64(struct afs_operation *op) { + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; - struct afs_read *req = op->fetch.req; struct afs_call *call; __be32 *bp; @@ -437,16 +439,19 @@ static void afs_fs_fetch_data64(struct afs_operation *op) if (!call) return afs_op_nomem(op); + if (op->flags & AFS_OPERATION_ASYNC) + call->async = true; + /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHDATA64); bp[1] = htonl(vp->fid.vid); bp[2] = htonl(vp->fid.vnode); bp[3] = htonl(vp->fid.unique); - bp[4] = htonl(upper_32_bits(req->pos)); - bp[5] = htonl(lower_32_bits(req->pos)); + bp[4] = htonl(upper_32_bits(subreq->start + subreq->transferred)); + bp[5] = htonl(lower_32_bits(subreq->start + subreq->transferred)); bp[6] = 0; - bp[7] = htonl(lower_32_bits(req->len)); + bp[7] = htonl(lower_32_bits(subreq->len - subreq->transferred)); call->fid = vp->fid; trace_afs_make_fs_call(call, &vp->fid); @@ -458,9 +463,9 @@ static void afs_fs_fetch_data64(struct afs_operation *op) */ void afs_fs_fetch_data(struct afs_operation *op) { + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_read *req = op->fetch.req; __be32 *bp; if (test_bit(AFS_SERVER_FL_HAS_FS64, &op->server->flags)) @@ -472,16 +477,14 @@ void afs_fs_fetch_data(struct afs_operation *op) if (!call) return afs_op_nomem(op); - req->call_debug_id = call->debug_id; - /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHDATA); bp[1] = htonl(vp->fid.vid); bp[2] = htonl(vp->fid.vnode); bp[3] = htonl(vp->fid.unique); - bp[4] = htonl(lower_32_bits(req->pos)); - bp[5] = htonl(lower_32_bits(req->len)); + bp[4] = htonl(lower_32_bits(subreq->start + subreq->transferred)); + bp[5] = htonl(lower_32_bits(subreq->len + subreq->transferred)); call->fid = vp->fid; trace_afs_make_fs_call(call, &vp->fid); @@ -1733,6 +1736,7 @@ static const struct afs_call_type afs_RXFSGetCapabilities = { .op = afs_FS_GetCapabilities, .deliver = afs_deliver_fs_get_capabilities, .done = afs_fileserver_probe_result, + .immediate_cancel = afs_fileserver_probe_result, .destructor = afs_fs_get_capabilities_destructor, }; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index a95e77670b49..e9538e91f848 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -25,8 +25,94 @@ #include "internal.h" #include "afs_fs.h" +void afs_init_new_symlink(struct afs_vnode *vnode, struct afs_operation *op) +{ + size_t size = strlen(op->create.symlink) + 1; + size_t dsize = 0; + char *p; + + if (netfs_alloc_folioq_buffer(NULL, &vnode->directory, &dsize, size, + mapping_gfp_mask(vnode->netfs.inode.i_mapping)) < 0) + return; + + vnode->directory_size = dsize; + p = kmap_local_folio(folioq_folio(vnode->directory, 0), 0); + memcpy(p, op->create.symlink, size); + kunmap_local(p); + set_bit(AFS_VNODE_DIR_READ, &vnode->flags); + netfs_single_mark_inode_dirty(&vnode->netfs.inode); +} + +static void afs_put_link(void *arg) +{ + struct folio *folio = virt_to_folio(arg); + + kunmap_local(arg); + folio_put(folio); +} + +const char *afs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + struct afs_vnode *vnode = AFS_FS_I(inode); + struct folio *folio; + char *content; + ssize_t ret; + + if (!dentry) { + /* RCU pathwalk. */ + if (!test_bit(AFS_VNODE_DIR_READ, &vnode->flags) || !afs_check_validity(vnode)) + return ERR_PTR(-ECHILD); + goto good; + } + + if (test_bit(AFS_VNODE_DIR_READ, &vnode->flags)) + goto fetch; + + ret = afs_validate(vnode, NULL); + if (ret < 0) + return ERR_PTR(ret); + + if (!test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) && + test_bit(AFS_VNODE_DIR_READ, &vnode->flags)) + goto good; + +fetch: + ret = afs_read_single(vnode, NULL); + if (ret < 0) + return ERR_PTR(ret); + set_bit(AFS_VNODE_DIR_READ, &vnode->flags); + +good: + folio = folioq_folio(vnode->directory, 0); + folio_get(folio); + content = kmap_local_folio(folio, 0); + set_delayed_call(callback, afs_put_link, content); + return content; +} + +int afs_readlink(struct dentry *dentry, char __user *buffer, int buflen) +{ + DEFINE_DELAYED_CALL(done); + const char *content; + int len; + + content = afs_get_link(dentry, d_inode(dentry), &done); + if (IS_ERR(content)) { + do_delayed_call(&done); + return PTR_ERR(content); + } + + len = umin(strlen(content), buflen); + if (copy_to_user(buffer, content, len)) + len = -EFAULT; + do_delayed_call(&done); + return len; +} + static const struct inode_operations afs_symlink_inode_operations = { - .get_link = page_get_link, + .get_link = afs_get_link, + .readlink = afs_readlink, }; static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode) @@ -110,7 +196,9 @@ static int afs_inode_init_from_status(struct afs_operation *op, inode->i_op = &afs_dir_inode_operations; inode->i_fop = &afs_dir_file_operations; inode->i_mapping->a_ops = &afs_dir_aops; - mapping_set_large_folios(inode->i_mapping); + __set_bit(NETFS_ICTX_SINGLE_NO_UPLOAD, &vnode->netfs.flags); + /* Assume locally cached directory data will be valid. */ + __set_bit(AFS_VNODE_DIR_VALID, &vnode->flags); break; case AFS_FTYPE_SYMLINK: /* Symlinks with a mode of 0644 are actually mountpoints. */ @@ -122,13 +210,13 @@ static int afs_inode_init_from_status(struct afs_operation *op, inode->i_mode = S_IFDIR | 0555; inode->i_op = &afs_mntpt_inode_operations; inode->i_fop = &afs_mntpt_file_operations; - inode->i_mapping->a_ops = &afs_symlink_aops; } else { inode->i_mode = S_IFLNK | status->mode; inode->i_op = &afs_symlink_inode_operations; - inode->i_mapping->a_ops = &afs_symlink_aops; } + inode->i_mapping->a_ops = &afs_dir_aops; inode_nohighmem(inode); + mapping_set_release_always(inode->i_mapping); break; default: dump_vnode(vnode, op->file[0].vnode != vnode ? op->file[0].vnode : NULL); @@ -140,15 +228,17 @@ static int afs_inode_init_from_status(struct afs_operation *op, afs_set_netfs_context(vnode); vnode->invalid_before = status->data_version; + trace_afs_set_dv(vnode, status->data_version); inode_set_iversion_raw(&vnode->netfs.inode, status->data_version); if (!vp->scb.have_cb) { /* it's a symlink we just created (the fileserver * didn't give us a callback) */ - atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE); + afs_clear_cb_promise(vnode, afs_cb_promise_set_new_symlink); } else { vnode->cb_server = op->server; - atomic64_set(&vnode->cb_expires_at, vp->scb.callback.expires_at); + afs_set_cb_promise(vnode, vp->scb.callback.expires_at, + afs_cb_promise_set_new_inode); } write_sequnlock(&vnode->cb_lock); @@ -207,12 +297,17 @@ static void afs_apply_status(struct afs_operation *op, if (vp->update_ctime) inode_set_ctime_to_ts(inode, op->ctime); - if (vnode->status.data_version != status->data_version) + if (vnode->status.data_version != status->data_version) { + trace_afs_set_dv(vnode, status->data_version); data_changed = true; + } vnode->status = *status; if (vp->dv_before + vp->dv_delta != status->data_version) { + trace_afs_dv_mismatch(vnode, vp->dv_before, vp->dv_delta, + status->data_version); + if (vnode->cb_ro_snapshot == atomic_read(&vnode->volume->cb_ro_snapshot) && atomic64_read(&vnode->cb_expires_at) != AFS_NO_CB_PROMISE) pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s (op=%x)\n", @@ -223,12 +318,10 @@ static void afs_apply_status(struct afs_operation *op, op->debug_id); vnode->invalid_before = status->data_version; - if (vnode->status.type == AFS_FTYPE_DIR) { - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - afs_stat_v(vnode, n_inval); - } else { + if (vnode->status.type == AFS_FTYPE_DIR) + afs_invalidate_dir(vnode, afs_dir_invalid_dv_mismatch); + else set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); - } change_size = true; data_changed = true; unexpected_jump = true; @@ -258,6 +351,8 @@ static void afs_apply_status(struct afs_operation *op, inode_set_ctime_to_ts(inode, t); inode_set_atime_to_ts(inode, t); } + if (op->ops == &afs_fetch_data_operation) + op->fetch.subreq->rreq->i_size = status->size; } } @@ -273,7 +368,7 @@ static void afs_apply_callback(struct afs_operation *op, if (!afs_cb_is_broken(vp->cb_break_before, vnode)) { if (op->volume->type == AFSVL_RWVOL) vnode->cb_server = op->server; - atomic64_set(&vnode->cb_expires_at, cb->expires_at); + afs_set_cb_promise(vnode, cb->expires_at, afs_cb_promise_set_apply_cb); } } @@ -435,7 +530,9 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) } __packed key; struct afs_vnode_cache_aux aux; - if (vnode->status.type != AFS_FTYPE_FILE) { + if (vnode->status.type != AFS_FTYPE_FILE && + vnode->status.type != AFS_FTYPE_DIR && + vnode->status.type != AFS_FTYPE_SYMLINK) { vnode->netfs.cache = NULL; return; } @@ -637,6 +734,7 @@ int afs_drop_inode(struct inode *inode) void afs_evict_inode(struct inode *inode) { struct afs_vnode_cache_aux aux; + struct afs_super_info *sbi = AFS_FS_S(inode->i_sb); struct afs_vnode *vnode = AFS_FS_I(inode); _enter("{%llx:%llu.%d}", @@ -648,8 +746,22 @@ void afs_evict_inode(struct inode *inode) ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); + if ((S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) && + (inode->i_state & I_DIRTY) && + !sbi->dyn_root) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .for_sync = true, + .range_end = LLONG_MAX, + }; + + afs_single_writepages(inode->i_mapping, &wbc); + } + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); + netfs_free_folioq_buffer(vnode->directory); afs_set_cache_aux(vnode, &aux); netfs_clear_inode_writeback(inode, &aux); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index c9d620175e80..90f407774a9a 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -163,6 +163,7 @@ struct afs_call { spinlock_t state_lock; int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ + unsigned long long remaining; /* How much is left to receive */ unsigned int max_lifespan; /* Maximum lifespan in secs to set if not 0 */ unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ @@ -201,11 +202,17 @@ struct afs_call_type { /* clean up a call */ void (*destructor)(struct afs_call *call); + /* Async receive processing function */ + void (*async_rx)(struct work_struct *work); + /* Work function */ void (*work)(struct work_struct *work); /* Call done function (gets called immediately on success or failure) */ void (*done)(struct afs_call *call); + + /* Handle a call being immediately cancelled. */ + void (*immediate_cancel)(struct afs_call *call); }; /* @@ -232,28 +239,6 @@ static inline struct key *afs_file_key(struct file *file) return af->key; } -/* - * Record of an outstanding read operation on a vnode. - */ -struct afs_read { - loff_t pos; /* Where to start reading */ - loff_t len; /* How much we're asking for */ - loff_t actual_len; /* How much we're actually getting */ - loff_t file_size; /* File size returned by server */ - struct key *key; /* The key to use to reissue the read */ - struct afs_vnode *vnode; /* The file being read into. */ - struct netfs_io_subrequest *subreq; /* Fscache helper read request this belongs to */ - afs_dataversion_t data_version; /* Version number returned by server */ - refcount_t usage; - unsigned int call_debug_id; - unsigned int nr_pages; - int error; - void (*done)(struct afs_read *); - void (*cleanup)(struct afs_read *); - struct iov_iter *iter; /* Iterator representing the buffer */ - struct iov_iter def_iter; /* Default iterator */ -}; - /* * AFS superblock private data * - there's one superblock per volume @@ -702,13 +687,14 @@ struct afs_vnode { struct afs_file_status status; /* AFS status info for this file */ afs_dataversion_t invalid_before; /* Child dentries are invalid before this */ struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */ - struct mutex io_lock; /* Lock for serialising I/O on this mutex */ + struct list_head io_lock_waiters; /* Threads waiting for the I/O lock */ struct rw_semaphore validate_lock; /* lock for validating this vnode */ struct rw_semaphore rmdir_lock; /* Lock for rmdir vs sillyrename */ struct key *silly_key; /* Silly rename key */ spinlock_t wb_lock; /* lock for wb_keys */ spinlock_t lock; /* waitqueue/flags lock */ unsigned long flags; +#define AFS_VNODE_IO_LOCK 0 /* Set if the I/O serialisation lock is held */ #define AFS_VNODE_UNSET 1 /* set if vnode attributes not yet set */ #define AFS_VNODE_DIR_VALID 2 /* Set if dir contents are valid */ #define AFS_VNODE_ZAP_DATA 3 /* set if vnode's data should be invalidated */ @@ -719,7 +705,9 @@ struct afs_vnode { #define AFS_VNODE_NEW_CONTENT 8 /* Set if file has new content (create/trunc-0) */ #define AFS_VNODE_SILLY_DELETED 9 /* Set if file has been silly-deleted */ #define AFS_VNODE_MODIFYING 10 /* Set if we're performing a modification op */ +#define AFS_VNODE_DIR_READ 11 /* Set if we've read a dir's contents */ + struct folio_queue *directory; /* Directory contents */ struct list_head wb_keys; /* List of keys available for writeback */ struct list_head pending_locks; /* locks waiting to be granted */ struct list_head granted_locks; /* locks granted on this file */ @@ -728,6 +716,7 @@ struct afs_vnode { ktime_t locked_at; /* Time at which lock obtained */ enum afs_lock_state lock_state : 8; afs_lock_type_t lock_type : 8; + unsigned int directory_size; /* Amount of space in ->directory */ /* outstanding callback notification on this file */ struct work_struct cb_work; /* Work for mmap'd files */ @@ -907,7 +896,7 @@ struct afs_operation { bool new_negative; } rename; struct { - struct afs_read *req; + struct netfs_io_subrequest *subreq; } fetch; struct { afs_lock_type_t type; @@ -959,6 +948,7 @@ struct afs_operation { #define AFS_OPERATION_TRIED_ALL 0x0400 /* Set if we've tried all the fileservers */ #define AFS_OPERATION_RETRY_SERVER 0x0800 /* Set if we should retry the current server */ #define AFS_OPERATION_DIR_CONFLICT 0x1000 /* Set if we detected a 3rd-party dir change */ +#define AFS_OPERATION_ASYNC 0x2000 /* Set if should run asynchronously */ }; /* @@ -983,6 +973,21 @@ static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int fl i_size_read(&vnode->netfs.inode), flags); } +/* + * Directory iteration management. + */ +struct afs_dir_iter { + struct afs_vnode *dvnode; + union afs_xdr_dir_block *block; + struct folio_queue *fq; + unsigned int fpos; + int fq_slot; + unsigned int loop_check; + u8 nr_slots; + u8 bucket; + unsigned int prev_entry; +}; + #include /*****************************************************************************/ @@ -1064,8 +1069,13 @@ extern const struct inode_operations afs_dir_inode_operations; extern const struct address_space_operations afs_dir_aops; extern const struct dentry_operations afs_fs_dentry_operations; +ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file); +ssize_t afs_read_dir(struct afs_vnode *dvnode, struct file *file) + __acquires(&dvnode->validate_lock); extern void afs_d_release(struct dentry *); extern void afs_check_for_remote_deletion(struct afs_operation *); +int afs_single_writepages(struct address_space *mapping, + struct writeback_control *wbc); /* * dir_edit.c @@ -1075,6 +1085,18 @@ extern void afs_edit_dir_add(struct afs_vnode *, struct qstr *, struct afs_fid * extern void afs_edit_dir_remove(struct afs_vnode *, struct qstr *, enum afs_edit_dir_reason); void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_dvnode, enum afs_edit_dir_reason why); +void afs_mkdir_init_dir(struct afs_vnode *dvnode, struct afs_vnode *parent_vnode); + +/* + * dir_search.c + */ +unsigned int afs_dir_hash_name(const struct qstr *name); +bool afs_dir_init_iter(struct afs_dir_iter *iter, const struct qstr *name); +union afs_xdr_dir_block *afs_dir_find_block(struct afs_dir_iter *iter, size_t block); +int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, + struct afs_fid *_fid); +int afs_dir_search(struct afs_vnode *dvnode, struct qstr *name, + struct afs_fid *_fid, afs_dataversion_t *_dir_version); /* * dir_silly.c @@ -1099,24 +1121,17 @@ extern void afs_dynroot_depopulate(struct super_block *); * file.c */ extern const struct address_space_operations afs_file_aops; -extern const struct address_space_operations afs_symlink_aops; extern const struct inode_operations afs_file_inode_operations; extern const struct file_operations afs_file_operations; +extern const struct afs_operation_ops afs_fetch_data_operation; extern const struct netfs_request_ops afs_req_ops; extern int afs_cache_wb_key(struct afs_vnode *, struct afs_file *); extern void afs_put_wb_key(struct afs_wb_key *); extern int afs_open(struct inode *, struct file *); extern int afs_release(struct inode *, struct file *); -extern int afs_fetch_data(struct afs_vnode *, struct afs_read *); -extern struct afs_read *afs_alloc_read(gfp_t); -extern void afs_put_read(struct afs_read *); - -static inline struct afs_read *afs_get_read(struct afs_read *req) -{ - refcount_inc(&req->usage); - return req; -} +void afs_fetch_data_async_rx(struct work_struct *work); +void afs_fetch_data_immediate_cancel(struct afs_call *call); /* * flock.c @@ -1168,6 +1183,7 @@ extern void afs_fs_store_acl(struct afs_operation *); extern struct afs_operation *afs_alloc_operation(struct key *, struct afs_volume *); extern int afs_put_operation(struct afs_operation *); extern bool afs_begin_vnode_operation(struct afs_operation *); +extern void afs_end_vnode_operation(struct afs_operation *op); extern void afs_wait_for_operation(struct afs_operation *); extern int afs_do_sync_operation(struct afs_operation *); @@ -1205,6 +1221,10 @@ extern void afs_fs_probe_cleanup(struct afs_net *); */ extern const struct afs_operation_ops afs_fetch_status_operation; +void afs_init_new_symlink(struct afs_vnode *vnode, struct afs_operation *op); +const char *afs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback); +int afs_readlink(struct dentry *dentry, char __user *buffer, int buflen); extern void afs_vnode_commit_status(struct afs_operation *, struct afs_vnode_param *); extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *); extern int afs_ilookup5_test_by_fid(struct inode *, void *); @@ -1336,6 +1356,7 @@ extern void afs_charge_preallocation(struct work_struct *); extern void afs_put_call(struct afs_call *); void afs_deferred_put_call(struct afs_call *call); void afs_make_call(struct afs_call *call, gfp_t gfp); +void afs_deliver_to_call(struct afs_call *call); void afs_wait_for_call_to_complete(struct afs_call *call); extern struct afs_call *afs_alloc_flat_call(struct afs_net *, const struct afs_call_type *, @@ -1346,6 +1367,28 @@ extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); extern int afs_extract_data(struct afs_call *, bool); extern int afs_protocol_error(struct afs_call *, enum afs_eproto_cause); +static inline struct afs_call *afs_get_call(struct afs_call *call, + enum afs_call_trace why) +{ + int r; + + __refcount_inc(&call->ref, &r); + + trace_afs_call(call->debug_id, why, r + 1, + atomic_read(&call->net->nr_outstanding_calls), + __builtin_return_address(0)); + return call; +} + +static inline void afs_see_call(struct afs_call *call, enum afs_call_trace why) +{ + int r = refcount_read(&call->ref); + + trace_afs_call(call->debug_id, why, r, + atomic_read(&call->net->nr_outstanding_calls), + __builtin_return_address(0)); +} + static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *call, gfp_t gfp) { @@ -1712,6 +1755,38 @@ static inline int afs_bad(struct afs_vnode *vnode, enum afs_file_error where) return -EIO; } +/* + * Set the callback promise on a vnode. + */ +static inline void afs_set_cb_promise(struct afs_vnode *vnode, time64_t expires_at, + enum afs_cb_promise_trace trace) +{ + atomic64_set(&vnode->cb_expires_at, expires_at); + trace_afs_cb_promise(vnode, trace); +} + +/* + * Clear the callback promise on a vnode, returning true if it was promised. + */ +static inline bool afs_clear_cb_promise(struct afs_vnode *vnode, + enum afs_cb_promise_trace trace) +{ + trace_afs_cb_promise(vnode, trace); + return atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE; +} + +/* + * Mark a directory as being invalid. + */ +static inline void afs_invalidate_dir(struct afs_vnode *dvnode, + enum afs_dir_invalid_trace trace) +{ + if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { + trace_afs_dir_invalid(dvnode, trace); + afs_stat_v(dvnode, n_inval); + } +} + /*****************************************************************************/ /* * debug tracing diff --git a/fs/afs/main.c b/fs/afs/main.c index a14f6013e316..1ae0067f772d 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -177,7 +177,7 @@ static int __init afs_init(void) afs_wq = alloc_workqueue("afs", 0, 0); if (!afs_wq) goto error_afs_wq; - afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM, 0); + afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (!afs_async_calls) goto error_async; afs_lock_manager = alloc_workqueue("kafs_lockd", WQ_MEM_RECLAIM, 0); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 297487ee8323..507c25a5b2cb 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -30,7 +30,7 @@ const struct file_operations afs_mntpt_file_operations = { const struct inode_operations afs_mntpt_inode_operations = { .lookup = afs_mntpt_lookup, - .readlink = page_readlink, + .readlink = afs_readlink, .getattr = afs_getattr, }; @@ -118,9 +118,9 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) ctx->volnamesz = sizeof(afs_root_volume) - 1; } else { /* read the contents of the AFS special symlink */ - struct page *page; + DEFINE_DELAYED_CALL(cleanup); + const char *content; loff_t size = i_size_read(d_inode(mntpt)); - char *buf; if (src_as->cell) ctx->cell = afs_use_cell(src_as->cell, afs_cell_trace_use_mntpt); @@ -128,16 +128,16 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) if (size < 2 || size > PAGE_SIZE - 1) return -EINVAL; - page = read_mapping_page(d_inode(mntpt)->i_mapping, 0, NULL); - if (IS_ERR(page)) - return PTR_ERR(page); + content = afs_get_link(mntpt, d_inode(mntpt), &cleanup); + if (IS_ERR(content)) { + do_delayed_call(&cleanup); + return PTR_ERR(content); + } - buf = kmap(page); ret = -EINVAL; - if (buf[size - 1] == '.') - ret = vfs_parse_fs_string(fc, "source", buf, size - 1); - kunmap(page); - put_page(page); + if (content[size - 1] == '.') + ret = vfs_parse_fs_string(fc, "source", content, size - 1); + do_delayed_call(&cleanup); if (ret < 0) return ret; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 15eab053af6d..e7614f4f30c2 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -240,7 +240,13 @@ static int afs_proc_rootcell_write(struct file *file, char *buf, size_t size) /* determine command to perform */ _debug("rootcell=%s", buf); - ret = afs_cell_init(net, buf); + ret = -EEXIST; + inode_lock(file_inode(file)); + if (!net->ws_cell) + ret = afs_cell_init(net, buf); + else + printk("busy\n"); + inode_unlock(file_inode(file)); out: _leave(" = %d", ret); diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index d612983d6f38..a1c24f589d9e 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -99,7 +99,7 @@ static bool afs_start_fs_iteration(struct afs_operation *op, write_seqlock(&vnode->cb_lock); ASSERTCMP(cb_server, ==, vnode->cb_server); vnode->cb_server = NULL; - if (atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE) + if (afs_clear_cb_promise(vnode, afs_cb_promise_clear_rotate_server)) vnode->cb_break++; write_sequnlock(&vnode->cb_lock); } @@ -583,7 +583,7 @@ selected_server: if (vnode->cb_server != server) { vnode->cb_server = server; vnode->cb_v_check = atomic_read(&vnode->volume->cb_v_break); - atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE); + afs_clear_cb_promise(vnode, afs_cb_promise_clear_server_change); } retry_server: diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 9f2a3bb56ec6..886416ea1d96 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -149,7 +149,8 @@ static struct afs_call *afs_alloc_call(struct afs_net *net, call->net = net; call->debug_id = atomic_inc_return(&rxrpc_debug_id); refcount_set(&call->ref, 1); - INIT_WORK(&call->async_work, afs_process_async_call); + INIT_WORK(&call->async_work, type->async_rx ?: afs_process_async_call); + INIT_WORK(&call->work, call->type->work); INIT_WORK(&call->free_work, afs_deferred_free_worker); init_waitqueue_head(&call->waitq); spin_lock_init(&call->state_lock); @@ -235,27 +236,12 @@ void afs_deferred_put_call(struct afs_call *call) schedule_work(&call->free_work); } -static struct afs_call *afs_get_call(struct afs_call *call, - enum afs_call_trace why) -{ - int r; - - __refcount_inc(&call->ref, &r); - - trace_afs_call(call->debug_id, why, r + 1, - atomic_read(&call->net->nr_outstanding_calls), - __builtin_return_address(0)); - return call; -} - /* * Queue the call for actual work. */ static void afs_queue_call_work(struct afs_call *call) { if (call->type->work) { - INIT_WORK(&call->work, call->type->work); - afs_get_call(call, afs_call_trace_work); if (!queue_work(afs_wq, &call->work)) afs_put_call(call); @@ -430,11 +416,16 @@ void afs_make_call(struct afs_call *call, gfp_t gfp) return; error_do_abort: - if (ret != -ECONNABORTED) { + if (ret != -ECONNABORTED) rxrpc_kernel_abort_call(call->net->socket, rxcall, RX_USER_ABORT, ret, afs_abort_send_data_error); - } else { + if (call->async) { + afs_see_call(call, afs_call_trace_async_abort); + return; + } + + if (ret == -ECONNABORTED) { len = 0; iov_iter_kvec(&msg.msg_iter, ITER_DEST, NULL, 0, 0); rxrpc_kernel_recv_data(call->net->socket, rxcall, @@ -445,8 +436,10 @@ error_do_abort: call->error = ret; trace_afs_call_done(call); error_kill_call: - if (call->type->done) - call->type->done(call); + if (call->async) + afs_see_call(call, afs_call_trace_async_kill); + if (call->type->immediate_cancel) + call->type->immediate_cancel(call); /* We need to dispose of the extra ref we grabbed for an async call. * The call, however, might be queued on afs_async_calls and we need to @@ -501,7 +494,7 @@ static void afs_log_error(struct afs_call *call, s32 remote_abort) /* * deliver messages to a call */ -static void afs_deliver_to_call(struct afs_call *call) +void afs_deliver_to_call(struct afs_call *call) { enum afs_call_state state; size_t len; @@ -602,7 +595,6 @@ local_abort: abort_code = 0; call_complete: afs_set_call_complete(call, ret, remote_abort); - state = AFS_CALL_COMPLETE; goto done; } @@ -803,6 +795,7 @@ static int afs_deliver_cm_op_id(struct afs_call *call) return -ENOTSUPP; trace_afs_cb_call(call); + call->work.func = call->type->work; /* pass responsibility for the remainer of this message off to the * cache manager op */ diff --git a/fs/afs/super.c b/fs/afs/super.c index f3ba1c3e72f5..a9bee610674e 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -663,7 +663,7 @@ static void afs_i_init_once(void *_vnode) memset(vnode, 0, sizeof(*vnode)); inode_init_once(&vnode->netfs.inode); - mutex_init(&vnode->io_lock); + INIT_LIST_HEAD(&vnode->io_lock_waiters); init_rwsem(&vnode->validate_lock); spin_lock_init(&vnode->wb_lock); spin_lock_init(&vnode->lock); @@ -696,6 +696,8 @@ static struct inode *afs_alloc_inode(struct super_block *sb) vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; + vnode->directory = NULL; + vnode->directory_size = 0; vnode->flags = 1 << AFS_VNODE_UNSET; vnode->lock_state = AFS_VNODE_LOCK_NONE; diff --git a/fs/afs/validation.c b/fs/afs/validation.c index bef8af12ebe2..0ba8336c9025 100644 --- a/fs/afs/validation.c +++ b/fs/afs/validation.c @@ -120,22 +120,31 @@ bool afs_check_validity(const struct afs_vnode *vnode) { const struct afs_volume *volume = vnode->volume; + enum afs_vnode_invalid_trace trace = afs_vnode_valid_trace; + time64_t cb_expires_at = atomic64_read(&vnode->cb_expires_at); time64_t deadline = ktime_get_real_seconds() + 10; if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) return true; - if (atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) || - atomic64_read(&vnode->cb_expires_at) <= deadline || - volume->cb_expires_at <= deadline || - vnode->cb_ro_snapshot != atomic_read(&volume->cb_ro_snapshot) || - vnode->cb_scrub != atomic_read(&volume->cb_scrub) || - test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) { - _debug("inval"); - return false; - } - - return true; + if (atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break)) + trace = afs_vnode_invalid_trace_cb_v_break; + else if (cb_expires_at == AFS_NO_CB_PROMISE) + trace = afs_vnode_invalid_trace_no_cb_promise; + else if (cb_expires_at <= deadline) + trace = afs_vnode_invalid_trace_expired; + else if (volume->cb_expires_at <= deadline) + trace = afs_vnode_invalid_trace_vol_expired; + else if (vnode->cb_ro_snapshot != atomic_read(&volume->cb_ro_snapshot)) + trace = afs_vnode_invalid_trace_cb_ro_snapshot; + else if (vnode->cb_scrub != atomic_read(&volume->cb_scrub)) + trace = afs_vnode_invalid_trace_cb_scrub; + else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) + trace = afs_vnode_invalid_trace_zap_data; + else + return true; + trace_afs_vnode_invalid(vnode, trace); + return false; } /* diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 9f36e14f1c2d..f9e76b604f31 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -253,6 +253,7 @@ static char *afs_vl_get_cell_name(struct afs_cell *cell, struct key *key) static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) { struct afs_cell *master; + size_t name_len; char *cell_name; cell_name = afs_vl_get_cell_name(cell, key); @@ -264,8 +265,11 @@ static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) return 0; } - master = afs_lookup_cell(cell->net, cell_name, strlen(cell_name), - NULL, false); + name_len = strlen(cell_name); + if (!name_len || name_len > AFS_MAXCELLNAME) + master = ERR_PTR(-EOPNOTSUPP); + else + master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false); kfree(cell_name); if (IS_ERR(master)) return PTR_ERR(master); diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index cac75f89b64a..3a23c0b08eb6 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -370,6 +370,7 @@ static const struct afs_call_type afs_RXVLGetCapabilities = { .name = "VL.GetCapabilities", .op = afs_VL_GetCapabilities, .deliver = afs_deliver_vl_get_capabilities, + .immediate_cancel = afs_vlserver_probe_result, .done = afs_vlserver_probe_result, .destructor = afs_destroy_vl_get_capabilities, }; @@ -697,7 +698,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call) return ret; namesz = ntohl(call->tmp); - if (namesz > AFS_MAXCELLNAME) + if (namesz > YFS_VL_MAXCELLNAME) return afs_protocol_error(call, afs_eproto_cellname_len); paddedsz = (namesz + 3) & ~3; call->count = namesz; diff --git a/fs/afs/write.c b/fs/afs/write.c index 34107b55f834..18b0a9f1615e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -122,7 +122,7 @@ static void afs_issue_write_worker(struct work_struct *work) if (subreq->debug_index == 3) return netfs_write_subrequest_terminated(subreq, -ENOANO, false); - if (!test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) { + if (!subreq->retry_count) { set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); return netfs_write_subrequest_terminated(subreq, -EAGAIN, false); } @@ -149,6 +149,9 @@ static void afs_issue_write_worker(struct work_struct *work) afs_wait_for_operation(op); ret = afs_put_operation(op); switch (ret) { + case 0: + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + break; case -EACCES: case -EPERM: case -ENOKEY: @@ -179,8 +182,8 @@ void afs_issue_write(struct netfs_io_subrequest *subreq) */ void afs_begin_writeback(struct netfs_io_request *wreq) { - afs_get_writeback_key(wreq); - wreq->io_streams[0].avail = true; + if (S_ISREG(wreq->inode->i_mode)) + afs_get_writeback_key(wreq); } /* @@ -193,6 +196,18 @@ void afs_retry_request(struct netfs_io_request *wreq, struct netfs_io_stream *st list_first_entry(&stream->subrequests, struct netfs_io_subrequest, rreq_link); + switch (wreq->origin) { + case NETFS_READAHEAD: + case NETFS_READPAGE: + case NETFS_READ_GAPS: + case NETFS_READ_SINGLE: + case NETFS_READ_FOR_WRITE: + case NETFS_DIO_READ: + return; + default: + break; + } + switch (subreq->error) { case -EACCES: case -EPERM: diff --git a/fs/afs/xdr_fs.h b/fs/afs/xdr_fs.h index 8ca868164507..cc5f143d21a3 100644 --- a/fs/afs/xdr_fs.h +++ b/fs/afs/xdr_fs.h @@ -88,7 +88,7 @@ union afs_xdr_dir_block { struct { struct afs_xdr_dir_hdr hdr; - u8 alloc_ctrs[AFS_DIR_MAX_BLOCKS]; + u8 alloc_ctrs[AFS_DIR_BLOCKS_WITH_CTR]; __be16 hashtable[AFS_DIR_HASHTBL_SIZE]; } meta; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 024227aba4cd..257af259c04a 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -352,19 +352,19 @@ static int yfs_deliver_status_and_volsync(struct afs_call *call) static int yfs_deliver_fs_fetch_data64(struct afs_call *call) { struct afs_operation *op = call->op; + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; - struct afs_read *req = op->fetch.req; const __be32 *bp; size_t count_before; int ret; _enter("{%u,%zu, %zu/%llu}", call->unmarshall, call->iov_len, iov_iter_count(call->iter), - req->actual_len); + call->remaining); switch (call->unmarshall) { case 0: - req->actual_len = 0; + call->remaining = 0; afs_extract_to_tmp64(call); call->unmarshall++; fallthrough; @@ -379,42 +379,39 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) if (ret < 0) return ret; - req->actual_len = be64_to_cpu(call->tmp64); - _debug("DATA length: %llu", req->actual_len); + call->remaining = be64_to_cpu(call->tmp64); + _debug("DATA length: %llu", call->remaining); - if (req->actual_len == 0) + if (call->remaining == 0) goto no_more_data; - call->iter = req->iter; - call->iov_len = min(req->actual_len, req->len); + call->iter = &subreq->io_iter; + call->iov_len = min(call->remaining, subreq->len - subreq->transferred); call->unmarshall++; fallthrough; /* extract the returned data */ case 2: count_before = call->iov_len; - _debug("extract data %zu/%llu", count_before, req->actual_len); + _debug("extract data %zu/%llu", count_before, call->remaining); ret = afs_extract_data(call, true); - if (req->subreq) { - req->subreq->transferred += count_before - call->iov_len; - netfs_read_subreq_progress(req->subreq, false); - } + subreq->transferred += count_before - call->iov_len; if (ret < 0) return ret; call->iter = &call->def_iter; - if (req->actual_len <= req->len) + if (call->remaining) goto no_more_data; /* Discard any excess data the server gave us */ - afs_extract_discard(call, req->actual_len - req->len); + afs_extract_discard(call, call->remaining); call->unmarshall = 3; fallthrough; case 3: _debug("extract discard %zu/%llu", - iov_iter_count(call->iter), req->actual_len - req->len); + iov_iter_count(call->iter), call->remaining); ret = afs_extract_data(call, true); if (ret < 0) @@ -439,8 +436,8 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) xdr_decode_YFSCallBack(&bp, call, &vp->scb); xdr_decode_YFSVolSync(&bp, &op->volsync); - req->data_version = vp->scb.status.data_version; - req->file_size = vp->scb.status.size; + if (subreq->start + subreq->transferred >= vp->scb.status.size) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); call->unmarshall++; fallthrough; @@ -459,7 +456,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) static const struct afs_call_type yfs_RXYFSFetchData64 = { .name = "YFS.FetchData64", .op = yfs_FS_FetchData64, + .async_rx = afs_fetch_data_async_rx, .deliver = yfs_deliver_fs_fetch_data64, + .immediate_cancel = afs_fetch_data_immediate_cancel, .destructor = afs_flat_call_destructor, }; @@ -468,14 +467,15 @@ static const struct afs_call_type yfs_RXYFSFetchData64 = { */ void yfs_fs_fetch_data(struct afs_operation *op) { + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; - struct afs_read *req = op->fetch.req; struct afs_call *call; __be32 *bp; - _enter(",%x,{%llx:%llu},%llx,%llx", + _enter(",%x,{%llx:%llu},%llx,%zx", key_serial(op->key), vp->fid.vid, vp->fid.vnode, - req->pos, req->len); + subreq->start + subreq->transferred, + subreq->len - subreq->transferred); call = afs_alloc_flat_call(op->net, &yfs_RXYFSFetchData64, sizeof(__be32) * 2 + @@ -487,15 +487,16 @@ void yfs_fs_fetch_data(struct afs_operation *op) if (!call) return afs_op_nomem(op); - req->call_debug_id = call->debug_id; + if (op->flags & AFS_OPERATION_ASYNC) + call->async = true; /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSFETCHDATA64); bp = xdr_encode_u32(bp, 0); /* RPC flags */ bp = xdr_encode_YFSFid(bp, &vp->fid); - bp = xdr_encode_u64(bp, req->pos); - bp = xdr_encode_u64(bp, req->len); + bp = xdr_encode_u64(bp, subreq->start + subreq->transferred); + bp = xdr_encode_u64(bp, subreq->len - subreq->transferred); yfs_check_req(call, bp); call->fid = vp->fid; @@ -666,8 +667,9 @@ static int yfs_deliver_fs_remove_file2(struct afs_call *call) static void yfs_done_fs_remove_file2(struct afs_call *call) { if (call->error == -ECONNABORTED && - call->abort_code == RX_INVALID_OPERATION) { - set_bit(AFS_SERVER_FL_NO_RM2, &call->server->flags); + (call->abort_code == RX_INVALID_OPERATION || + call->abort_code == RXGEN_OPCODE)) { + set_bit(AFS_SERVER_FL_NO_RM2, &call->op->server->flags); call->op->flags |= AFS_OPERATION_DOWNGRADE; } } diff --git a/fs/aio.c b/fs/aio.c index 50671640b588..7b976b564cfc 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -224,7 +224,7 @@ static unsigned long aio_nr; /* current system wide number of aio requests */ static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ /*----end sysctl variables---*/ #ifdef CONFIG_SYSCTL -static struct ctl_table aio_sysctls[] = { +static const struct ctl_table aio_sysctls[] = { { .procname = "aio-nr", .data = &aio_nr, diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 42bd1cb7c9cd..583ac81669c2 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -60,14 +60,14 @@ static struct inode *anon_inode_make_secure_inode( const struct inode *context_inode) { struct inode *inode; - const struct qstr qname = QSTR_INIT(name, strlen(name)); int error; inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; - error = security_inode_init_security_anon(inode, &qname, context_inode); + error = security_inode_init_security_anon(inode, &QSTR(name), + context_inode); if (error) { iput(inode); return ERR_PTR(error); diff --git a/fs/backing-file.c b/fs/backing-file.c index cbdad8b68474..763fbe9b72b2 100644 --- a/fs/backing-file.c +++ b/fs/backing-file.c @@ -176,7 +176,7 @@ ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, !(file->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); if (is_sync_kiocb(iocb)) { rwf_t rwf = iocb_to_rw_flags(flags); @@ -197,7 +197,7 @@ ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, backing_aio_cleanup(aio, ret); } out: - revert_creds_light(old_cred); + revert_creds(old_cred); if (ctx->accessed) ctx->accessed(iocb->ki_filp); @@ -233,7 +233,7 @@ ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, */ flags &= ~IOCB_DIO_CALLER_COMP; - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); if (is_sync_kiocb(iocb)) { rwf_t rwf = iocb_to_rw_flags(flags); @@ -264,7 +264,7 @@ ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, backing_aio_cleanup(aio, ret); } out: - revert_creds_light(old_cred); + revert_creds(old_cred); return ret; } @@ -281,9 +281,9 @@ ssize_t backing_file_splice_read(struct file *in, struct kiocb *iocb, if (WARN_ON_ONCE(!(in->f_mode & FMODE_BACKING))) return -EIO; - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); ret = vfs_splice_read(in, &iocb->ki_pos, pipe, len, flags); - revert_creds_light(old_cred); + revert_creds(old_cred); if (ctx->accessed) ctx->accessed(iocb->ki_filp); @@ -310,11 +310,11 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe, if (ret) return ret; - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); file_start_write(out); ret = out->f_op->splice_write(pipe, out, &iocb->ki_pos, len, flags); file_end_write(out); - revert_creds_light(old_cred); + revert_creds(old_cred); if (ctx->end_write) ctx->end_write(iocb, ret); @@ -338,9 +338,9 @@ int backing_file_mmap(struct file *file, struct vm_area_struct *vma, vma_set_file(vma, file); - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); ret = call_mmap(vma->vm_file, vma); - revert_creds_light(old_cred); + revert_creds(old_cred); if (ctx->accessed) ctx->accessed(user_file); diff --git a/fs/bcachefs/Kconfig b/fs/bcachefs/Kconfig index ab6c95b895b3..85eea7a4dea3 100644 --- a/fs/bcachefs/Kconfig +++ b/fs/bcachefs/Kconfig @@ -15,6 +15,7 @@ config BCACHEFS_FS select ZLIB_INFLATE select ZSTD_COMPRESS select ZSTD_DECOMPRESS + select CRYPTO select CRYPTO_SHA256 select CRYPTO_CHACHA20 select CRYPTO_POLY1305 @@ -90,7 +91,7 @@ config BCACHEFS_SIX_OPTIMISTIC_SPIN config BCACHEFS_PATH_TRACEPOINTS bool "Extra btree_path tracepoints" - depends on BCACHEFS_FS + depends on BCACHEFS_FS && TRACING help Enable extra tracepoints for debugging btree_path operations; we don't normally want these enabled because they happen at very high rates. diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile index 56d20e219f59..d2689388d5e8 100644 --- a/fs/bcachefs/Makefile +++ b/fs/bcachefs/Makefile @@ -82,6 +82,7 @@ bcachefs-y := \ siphash.o \ six.o \ snapshot.o \ + str_hash.o \ subvolume.o \ super.o \ super-io.o \ diff --git a/fs/bcachefs/acl.c b/fs/bcachefs/acl.c index 87f1be9d4db4..99487727ae64 100644 --- a/fs/bcachefs/acl.c +++ b/fs/bcachefs/acl.c @@ -184,11 +184,6 @@ invalid: return ERR_PTR(-EINVAL); } -#define acl_for_each_entry(acl, acl_e) \ - for (acl_e = acl->a_entries; \ - acl_e < acl->a_entries + acl->a_count; \ - acl_e++) - /* * Convert from in-memory to filesystem representation. */ @@ -199,11 +194,11 @@ bch2_acl_to_xattr(struct btree_trans *trans, { struct bkey_i_xattr *xattr; bch_acl_header *acl_header; - const struct posix_acl_entry *acl_e; + const struct posix_acl_entry *acl_e, *pe; void *outptr; unsigned nr_short = 0, nr_long = 0, acl_len, u64s; - acl_for_each_entry(acl, acl_e) { + FOREACH_ACL_ENTRY(acl_e, acl, pe) { switch (acl_e->e_tag) { case ACL_USER: case ACL_GROUP: @@ -241,7 +236,7 @@ bch2_acl_to_xattr(struct btree_trans *trans, outptr = (void *) acl_header + sizeof(*acl_header); - acl_for_each_entry(acl, acl_e) { + FOREACH_ACL_ENTRY(acl_e, acl, pe) { bch_acl_entry *entry = outptr; entry->e_tag = cpu_to_le16(acl_e->e_tag); diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index c84a91572a1d..fc2ef33b67b3 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -198,7 +198,7 @@ static unsigned bch_alloc_v1_val_u64s(const struct bch_alloc *a) } int bch2_alloc_v1_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_alloc a = bkey_s_c_to_alloc(k); int ret = 0; @@ -213,7 +213,7 @@ fsck_err: } int bch2_alloc_v2_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_alloc_unpacked u; int ret = 0; @@ -226,7 +226,7 @@ fsck_err: } int bch2_alloc_v3_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_alloc_unpacked u; int ret = 0; @@ -239,7 +239,7 @@ fsck_err: } int bch2_alloc_v4_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bch_alloc_v4 a; int ret = 0; @@ -322,9 +322,9 @@ fsck_err: void bch2_alloc_v4_swab(struct bkey_s k) { struct bch_alloc_v4 *a = bkey_s_to_alloc_v4(k).v; - struct bch_backpointer *bp, *bps; - a->journal_seq = swab64(a->journal_seq); + a->journal_seq_nonempty = swab64(a->journal_seq_nonempty); + a->journal_seq_empty = swab64(a->journal_seq_empty); a->flags = swab32(a->flags); a->dirty_sectors = swab32(a->dirty_sectors); a->cached_sectors = swab32(a->cached_sectors); @@ -333,13 +333,6 @@ void bch2_alloc_v4_swab(struct bkey_s k) a->stripe = swab32(a->stripe); a->nr_external_backpointers = swab32(a->nr_external_backpointers); a->stripe_sectors = swab32(a->stripe_sectors); - - bps = alloc_v4_backpointers(a); - for (bp = bps; bp < bps + BCH_ALLOC_V4_NR_BACKPOINTERS(a); bp++) { - bp->bucket_offset = swab40(bp->bucket_offset); - bp->bucket_len = swab32(bp->bucket_len); - bch2_bpos_swab(&bp->pos); - } } void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) @@ -354,16 +347,17 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c prt_printf(out, "gen %u oldest_gen %u data_type ", a->gen, a->oldest_gen); bch2_prt_data_type(out, a->data_type); prt_newline(out); - prt_printf(out, "journal_seq %llu\n", a->journal_seq); - prt_printf(out, "need_discard %llu\n", BCH_ALLOC_V4_NEED_DISCARD(a)); - prt_printf(out, "need_inc_gen %llu\n", BCH_ALLOC_V4_NEED_INC_GEN(a)); - prt_printf(out, "dirty_sectors %u\n", a->dirty_sectors); - prt_printf(out, "stripe_sectors %u\n", a->stripe_sectors); - prt_printf(out, "cached_sectors %u\n", a->cached_sectors); - prt_printf(out, "stripe %u\n", a->stripe); - prt_printf(out, "stripe_redundancy %u\n", a->stripe_redundancy); - prt_printf(out, "io_time[READ] %llu\n", a->io_time[READ]); - prt_printf(out, "io_time[WRITE] %llu\n", a->io_time[WRITE]); + prt_printf(out, "journal_seq_nonempty %llu\n", a->journal_seq_nonempty); + prt_printf(out, "journal_seq_empty %llu\n", a->journal_seq_empty); + prt_printf(out, "need_discard %llu\n", BCH_ALLOC_V4_NEED_DISCARD(a)); + prt_printf(out, "need_inc_gen %llu\n", BCH_ALLOC_V4_NEED_INC_GEN(a)); + prt_printf(out, "dirty_sectors %u\n", a->dirty_sectors); + prt_printf(out, "stripe_sectors %u\n", a->stripe_sectors); + prt_printf(out, "cached_sectors %u\n", a->cached_sectors); + prt_printf(out, "stripe %u\n", a->stripe); + prt_printf(out, "stripe_redundancy %u\n", a->stripe_redundancy); + prt_printf(out, "io_time[READ] %llu\n", a->io_time[READ]); + prt_printf(out, "io_time[WRITE] %llu\n", a->io_time[WRITE]); if (ca) prt_printf(out, "fragmentation %llu\n", alloc_lru_idx_fragmentation(*a, ca)); @@ -392,7 +386,7 @@ void __bch2_alloc_to_v4(struct bkey_s_c k, struct bch_alloc_v4 *out) struct bkey_alloc_unpacked u = bch2_alloc_unpack(k); *out = (struct bch_alloc_v4) { - .journal_seq = u.journal_seq, + .journal_seq_nonempty = u.journal_seq, .flags = u.need_discard, .gen = u.gen, .oldest_gen = u.oldest_gen, @@ -517,7 +511,7 @@ static unsigned alloc_gen(struct bkey_s_c k, unsigned offset) } int bch2_bucket_gens_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -664,74 +658,80 @@ int bch2_alloc_read(struct bch_fs *c) /* Free space/discard btree: */ +static int __need_discard_or_freespace_err(struct btree_trans *trans, + struct bkey_s_c alloc_k, + bool set, bool discard, bool repair) +{ + struct bch_fs *c = trans->c; + enum bch_fsck_flags flags = FSCK_CAN_IGNORE|(repair ? FSCK_CAN_FIX : 0); + enum bch_sb_error_id err_id = discard + ? BCH_FSCK_ERR_need_discard_key_wrong + : BCH_FSCK_ERR_freespace_key_wrong; + enum btree_id btree = discard ? BTREE_ID_need_discard : BTREE_ID_freespace; + struct printbuf buf = PRINTBUF; + + bch2_bkey_val_to_text(&buf, c, alloc_k); + + int ret = __bch2_fsck_err(NULL, trans, flags, err_id, + "bucket incorrectly %sset in %s btree\n" + " %s", + set ? "" : "un", + bch2_btree_id_str(btree), + buf.buf); + if (ret == -BCH_ERR_fsck_ignore || + ret == -BCH_ERR_fsck_errors_not_fixed) + ret = 0; + + printbuf_exit(&buf); + return ret; +} + +#define need_discard_or_freespace_err(...) \ + fsck_err_wrap(__need_discard_or_freespace_err(__VA_ARGS__)) + +#define need_discard_or_freespace_err_on(cond, ...) \ + (unlikely(cond) ? need_discard_or_freespace_err(__VA_ARGS__) : false) + static int bch2_bucket_do_index(struct btree_trans *trans, struct bch_dev *ca, struct bkey_s_c alloc_k, const struct bch_alloc_v4 *a, bool set) { - struct bch_fs *c = trans->c; - struct btree_iter iter; - struct bkey_s_c old; - struct bkey_i *k; enum btree_id btree; - enum bch_bkey_type old_type = !set ? KEY_TYPE_set : KEY_TYPE_deleted; - enum bch_bkey_type new_type = set ? KEY_TYPE_set : KEY_TYPE_deleted; - struct printbuf buf = PRINTBUF; - int ret; + struct bpos pos; if (a->data_type != BCH_DATA_free && a->data_type != BCH_DATA_need_discard) return 0; - k = bch2_trans_kmalloc_nomemzero(trans, sizeof(*k)); - if (IS_ERR(k)) - return PTR_ERR(k); - - bkey_init(&k->k); - k->k.type = new_type; - switch (a->data_type) { case BCH_DATA_free: btree = BTREE_ID_freespace; - k->k.p = alloc_freespace_pos(alloc_k.k->p, *a); - bch2_key_resize(&k->k, 1); + pos = alloc_freespace_pos(alloc_k.k->p, *a); break; case BCH_DATA_need_discard: btree = BTREE_ID_need_discard; - k->k.p = alloc_k.k->p; + pos = alloc_k.k->p; break; default: return 0; } - old = bch2_bkey_get_iter(trans, &iter, btree, - bkey_start_pos(&k->k), - BTREE_ITER_intent); - ret = bkey_err(old); + struct btree_iter iter; + struct bkey_s_c old = bch2_bkey_get_iter(trans, &iter, btree, pos, BTREE_ITER_intent); + int ret = bkey_err(old); if (ret) return ret; - if (ca->mi.freespace_initialized && - c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info && - bch2_trans_inconsistent_on(old.k->type != old_type, trans, - "incorrect key when %s %s:%llu:%llu:0 (got %s should be %s)\n" - " for %s", - set ? "setting" : "clearing", - bch2_btree_id_str(btree), - iter.pos.inode, - iter.pos.offset, - bch2_bkey_types[old.k->type], - bch2_bkey_types[old_type], - (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { - ret = -EIO; - goto err; - } + need_discard_or_freespace_err_on(ca->mi.freespace_initialized && + !old.k->type != set, + trans, alloc_k, set, + btree == BTREE_ID_need_discard, false); - ret = bch2_trans_update(trans, &iter, k, 0); -err: + ret = bch2_btree_bit_mod_iter(trans, &iter, set); +fsck_err: bch2_trans_iter_exit(trans, &iter); - printbuf_exit(&buf); return ret; } @@ -858,7 +858,10 @@ int bch2_trigger_alloc(struct btree_trans *trans, if (flags & BTREE_TRIGGER_transactional) { alloc_data_type_set(new_a, new_a->data_type); - if (bch2_bucket_sectors_total(*new_a) > bch2_bucket_sectors_total(*old_a)) { + int is_empty_delta = (int) data_type_is_empty(new_a->data_type) - + (int) data_type_is_empty(old_a->data_type); + + if (is_empty_delta < 0) { new_a->io_time[READ] = bch2_current_io_time(c, READ); new_a->io_time[WRITE]= bch2_current_io_time(c, WRITE); SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, true); @@ -928,37 +931,55 @@ int bch2_trigger_alloc(struct btree_trans *trans, } if ((flags & BTREE_TRIGGER_atomic) && (flags & BTREE_TRIGGER_insert)) { - u64 journal_seq = trans->journal_res.seq; - u64 bucket_journal_seq = new_a->journal_seq; + u64 transaction_seq = trans->journal_res.seq; + BUG_ON(!transaction_seq); - if ((flags & BTREE_TRIGGER_insert) && - data_type_is_empty(old_a->data_type) != - data_type_is_empty(new_a->data_type) && - new.k->type == KEY_TYPE_alloc_v4) { - struct bch_alloc_v4 *v = bkey_s_to_alloc_v4(new).v; + if (log_fsck_err_on(transaction_seq && new_a->journal_seq_nonempty > transaction_seq, + trans, alloc_key_journal_seq_in_future, + "bucket journal seq in future (currently at %llu)\n%s", + journal_cur_seq(&c->journal), + (bch2_bkey_val_to_text(&buf, c, new.s_c), buf.buf))) + new_a->journal_seq_nonempty = transaction_seq; - /* - * If the btree updates referring to a bucket weren't flushed - * before the bucket became empty again, then the we don't have - * to wait on a journal flush before we can reuse the bucket: - */ - v->journal_seq = bucket_journal_seq = - data_type_is_empty(new_a->data_type) && - (journal_seq == v->journal_seq || - bch2_journal_noflush_seq(&c->journal, v->journal_seq)) - ? 0 : journal_seq; + int is_empty_delta = (int) data_type_is_empty(new_a->data_type) - + (int) data_type_is_empty(old_a->data_type); + + /* + * Record journal sequence number of empty -> nonempty transition: + * Note that there may be multiple empty -> nonempty + * transitions, data in a bucket may be overwritten while we're + * still writing to it - so be careful to only record the first: + * */ + if (is_empty_delta < 0 && + new_a->journal_seq_empty <= c->journal.flushed_seq_ondisk) { + new_a->journal_seq_nonempty = transaction_seq; + new_a->journal_seq_empty = 0; } - if (!data_type_is_empty(old_a->data_type) && - data_type_is_empty(new_a->data_type) && - bucket_journal_seq) { - ret = bch2_set_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, - c->journal.flushed_seq_ondisk, - new.k->p.inode, new.k->p.offset, - bucket_journal_seq); - if (bch2_fs_fatal_err_on(ret, c, - "setting bucket_needs_journal_commit: %s", bch2_err_str(ret))) - goto err; + /* + * Bucket becomes empty: mark it as waiting for a journal flush, + * unless updates since empty -> nonempty transition were never + * flushed - we may need to ask the journal not to flush + * intermediate sequence numbers: + */ + if (is_empty_delta > 0) { + if (new_a->journal_seq_nonempty == transaction_seq || + bch2_journal_noflush_seq(&c->journal, + new_a->journal_seq_nonempty, + transaction_seq)) { + new_a->journal_seq_nonempty = new_a->journal_seq_empty = 0; + } else { + new_a->journal_seq_empty = transaction_seq; + + ret = bch2_set_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, + c->journal.flushed_seq_ondisk, + new.k->p.inode, new.k->p.offset, + transaction_seq); + if (bch2_fs_fatal_err_on(ret, c, + "setting bucket_needs_journal_commit: %s", + bch2_err_str(ret))) + goto err; + } } if (new_a->gen != old_a->gen) { @@ -974,7 +995,7 @@ int bch2_trigger_alloc(struct btree_trans *trans, #define eval_state(_a, expr) ({ const struct bch_alloc_v4 *a = _a; expr; }) #define statechange(expr) !eval_state(old_a, expr) && eval_state(new_a, expr) -#define bucket_flushed(a) (!a->journal_seq || a->journal_seq <= c->journal.flushed_seq_ondisk) +#define bucket_flushed(a) (a->journal_seq_empty <= c->journal.flushed_seq_ondisk) if (statechange(a->data_type == BCH_DATA_free) && bucket_flushed(new_a)) @@ -1006,6 +1027,7 @@ int bch2_trigger_alloc(struct btree_trans *trans, rcu_read_unlock(); } err: +fsck_err: printbuf_exit(&buf); bch2_dev_put(ca); return ret; @@ -1045,7 +1067,7 @@ static struct bkey_s_c bch2_get_key_or_hole(struct btree_iter *iter, struct bpos * btree node min/max is a closed interval, upto takes a half * open interval: */ - k = bch2_btree_iter_peek_upto(&iter2, end); + k = bch2_btree_iter_peek_max(&iter2, end); next = iter2.pos; bch2_trans_iter_exit(iter->trans, &iter2); @@ -1129,7 +1151,6 @@ int bch2_check_alloc_key(struct btree_trans *trans, struct bch_fs *c = trans->c; struct bch_alloc_v4 a_convert; const struct bch_alloc_v4 *a; - unsigned discard_key_type, freespace_key_type; unsigned gens_offset; struct bkey_s_c k; struct printbuf buf = PRINTBUF; @@ -1149,64 +1170,30 @@ int bch2_check_alloc_key(struct btree_trans *trans, a = bch2_alloc_to_v4(alloc_k, &a_convert); - discard_key_type = a->data_type == BCH_DATA_need_discard ? KEY_TYPE_set : 0; bch2_btree_iter_set_pos(discard_iter, alloc_k.k->p); k = bch2_btree_iter_peek_slot(discard_iter); ret = bkey_err(k); if (ret) goto err; - if (fsck_err_on(k.k->type != discard_key_type, - trans, need_discard_key_wrong, - "incorrect key in need_discard btree (got %s should be %s)\n" - " %s", - bch2_bkey_types[k.k->type], - bch2_bkey_types[discard_key_type], - (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { - struct bkey_i *update = - bch2_trans_kmalloc(trans, sizeof(*update)); - - ret = PTR_ERR_OR_ZERO(update); - if (ret) - goto err; - - bkey_init(&update->k); - update->k.type = discard_key_type; - update->k.p = discard_iter->pos; - - ret = bch2_trans_update(trans, discard_iter, update, 0); + bool is_discarded = a->data_type == BCH_DATA_need_discard; + if (need_discard_or_freespace_err_on(!!k.k->type != is_discarded, + trans, alloc_k, !is_discarded, true, true)) { + ret = bch2_btree_bit_mod_iter(trans, discard_iter, is_discarded); if (ret) goto err; } - freespace_key_type = a->data_type == BCH_DATA_free ? KEY_TYPE_set : 0; bch2_btree_iter_set_pos(freespace_iter, alloc_freespace_pos(alloc_k.k->p, *a)); k = bch2_btree_iter_peek_slot(freespace_iter); ret = bkey_err(k); if (ret) goto err; - if (fsck_err_on(k.k->type != freespace_key_type, - trans, freespace_key_wrong, - "incorrect key in freespace btree (got %s should be %s)\n" - " %s", - bch2_bkey_types[k.k->type], - bch2_bkey_types[freespace_key_type], - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { - struct bkey_i *update = - bch2_trans_kmalloc(trans, sizeof(*update)); - - ret = PTR_ERR_OR_ZERO(update); - if (ret) - goto err; - - bkey_init(&update->k); - update->k.type = freespace_key_type; - update->k.p = freespace_iter->pos; - bch2_key_resize(&update->k, 1); - - ret = bch2_trans_update(trans, freespace_iter, update, 0); + bool is_free = a->data_type == BCH_DATA_free; + if (need_discard_or_freespace_err_on(!!k.k->type != is_free, + trans, alloc_k, !is_free, false, true)) { + ret = bch2_btree_bit_mod_iter(trans, freespace_iter, is_free); if (ret) goto err; } @@ -1368,51 +1355,88 @@ fsck_err: return ret; } -static noinline_for_stack int bch2_check_discard_freespace_key(struct btree_trans *trans, - struct btree_iter *iter) +struct check_discard_freespace_key_async { + struct work_struct work; + struct bch_fs *c; + struct bbpos pos; +}; + +static int bch2_recheck_discard_freespace_key(struct btree_trans *trans, struct bbpos pos) +{ + struct btree_iter iter; + struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, pos.btree, pos.pos, 0); + int ret = bkey_err(k); + if (ret) + return ret; + + u8 gen; + ret = k.k->type != KEY_TYPE_set + ? bch2_check_discard_freespace_key(trans, &iter, &gen, false) + : 0; + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +static void check_discard_freespace_key_work(struct work_struct *work) +{ + struct check_discard_freespace_key_async *w = + container_of(work, struct check_discard_freespace_key_async, work); + + bch2_trans_do(w->c, bch2_recheck_discard_freespace_key(trans, w->pos)); + bch2_write_ref_put(w->c, BCH_WRITE_REF_check_discard_freespace_key); + kfree(w); +} + +int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_iter *iter, u8 *gen, + bool async_repair) { struct bch_fs *c = trans->c; - struct btree_iter alloc_iter; - struct bkey_s_c alloc_k; - struct bch_alloc_v4 a_convert; - const struct bch_alloc_v4 *a; - u64 genbits; - struct bpos pos; enum bch_data_type state = iter->btree_id == BTREE_ID_need_discard ? BCH_DATA_need_discard : BCH_DATA_free; struct printbuf buf = PRINTBUF; - int ret; - pos = iter->pos; - pos.offset &= ~(~0ULL << 56); - genbits = iter->pos.offset & (~0ULL << 56); + struct bpos bucket = iter->pos; + bucket.offset &= ~(~0ULL << 56); + u64 genbits = iter->pos.offset & (~0ULL << 56); - alloc_k = bch2_bkey_get_iter(trans, &alloc_iter, BTREE_ID_alloc, pos, 0); - ret = bkey_err(alloc_k); + struct btree_iter alloc_iter; + struct bkey_s_c alloc_k = bch2_bkey_get_iter(trans, &alloc_iter, + BTREE_ID_alloc, bucket, + async_repair ? BTREE_ITER_cached : 0); + int ret = bkey_err(alloc_k); if (ret) return ret; - if (fsck_err_on(!bch2_dev_bucket_exists(c, pos), - trans, need_discard_freespace_key_to_invalid_dev_bucket, - "entry in %s btree for nonexistant dev:bucket %llu:%llu", - bch2_btree_id_str(iter->btree_id), pos.inode, pos.offset)) - goto delete; + if (!bch2_dev_bucket_exists(c, bucket)) { + if (fsck_err(trans, need_discard_freespace_key_to_invalid_dev_bucket, + "entry in %s btree for nonexistant dev:bucket %llu:%llu", + bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset)) + goto delete; + ret = 1; + goto out; + } - a = bch2_alloc_to_v4(alloc_k, &a_convert); + struct bch_alloc_v4 a_convert; + const struct bch_alloc_v4 *a = bch2_alloc_to_v4(alloc_k, &a_convert); - if (fsck_err_on(a->data_type != state || - (state == BCH_DATA_free && - genbits != alloc_freespace_genbits(*a)), - trans, need_discard_freespace_key_bad, - "%s\n incorrectly set at %s:%llu:%llu:0 (free %u, genbits %llu should be %llu)", - (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf), - bch2_btree_id_str(iter->btree_id), - iter->pos.inode, - iter->pos.offset, - a->data_type == state, - genbits >> 56, alloc_freespace_genbits(*a) >> 56)) - goto delete; + if (a->data_type != state || + (state == BCH_DATA_free && + genbits != alloc_freespace_genbits(*a))) { + if (fsck_err(trans, need_discard_freespace_key_bad, + "%s\n incorrectly set at %s:%llu:%llu:0 (free %u, genbits %llu should be %llu)", + (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf), + bch2_btree_id_str(iter->btree_id), + iter->pos.inode, + iter->pos.offset, + a->data_type == state, + genbits >> 56, alloc_freespace_genbits(*a) >> 56)) + goto delete; + ret = 1; + goto out; + } + + *gen = a->gen; out: fsck_err: bch2_set_btree_iter_dontneed(&alloc_iter); @@ -1420,11 +1444,40 @@ fsck_err: printbuf_exit(&buf); return ret; delete: - ret = bch2_btree_delete_extent_at(trans, iter, - iter->btree_id == BTREE_ID_freespace ? 1 : 0, 0) ?: - bch2_trans_commit(trans, NULL, NULL, - BCH_TRANS_COMMIT_no_enospc); - goto out; + if (!async_repair) { + ret = bch2_btree_bit_mod_iter(trans, iter, false) ?: + bch2_trans_commit(trans, NULL, NULL, + BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_commit; + goto out; + } else { + /* + * We can't repair here when called from the allocator path: the + * commit will recurse back into the allocator + */ + struct check_discard_freespace_key_async *w = + kzalloc(sizeof(*w), GFP_KERNEL); + if (!w) + goto out; + + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_check_discard_freespace_key)) { + kfree(w); + goto out; + } + + INIT_WORK(&w->work, check_discard_freespace_key_work); + w->c = c; + w->pos = BBPOS(iter->btree_id, iter->pos); + queue_work(c->write_ref_wq, &w->work); + goto out; + } +} + +static int bch2_check_discard_freespace_key_fsck(struct btree_trans *trans, struct btree_iter *iter) +{ + u8 gen; + int ret = bch2_check_discard_freespace_key(trans, iter, &gen, false); + return ret < 0 ? ret : 0; } /* @@ -1581,7 +1634,7 @@ bkey_err: ret = for_each_btree_key(trans, iter, BTREE_ID_need_discard, POS_MIN, BTREE_ITER_prefetch, k, - bch2_check_discard_freespace_key(trans, &iter)); + bch2_check_discard_freespace_key_fsck(trans, &iter)); if (ret) goto err; @@ -1594,7 +1647,7 @@ bkey_err: break; ret = bkey_err(k) ?: - bch2_check_discard_freespace_key(trans, &iter); + bch2_check_discard_freespace_key_fsck(trans, &iter); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) { ret = 0; continue; @@ -1757,7 +1810,8 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, struct bch_dev *ca, struct btree_iter *need_discard_iter, struct bpos *discard_pos_done, - struct discard_buckets_state *s) + struct discard_buckets_state *s, + bool fastpath) { struct bch_fs *c = trans->c; struct bpos pos = need_discard_iter->pos; @@ -1793,45 +1847,24 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, if (ret) goto out; - if (bch2_bucket_sectors_total(a->v)) { - if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, - trans, "attempting to discard bucket with dirty data\n%s", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - ret = -EIO; - goto out; - } - if (a->v.data_type != BCH_DATA_need_discard) { - if (data_type_is_empty(a->v.data_type) && - BCH_ALLOC_V4_NEED_INC_GEN(&a->v)) { - a->v.gen++; - SET_BCH_ALLOC_V4_NEED_INC_GEN(&a->v, false); - goto write; + if (need_discard_or_freespace_err(trans, k, true, true, true)) { + ret = bch2_btree_bit_mod_iter(trans, need_discard_iter, false); + if (ret) + goto out; + goto commit; } - if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, - trans, "bucket incorrectly set in need_discard btree\n" - "%s", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - ret = -EIO; goto out; } - if (a->v.journal_seq > c->journal.flushed_seq_ondisk) { - if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, - trans, "clearing need_discard but journal_seq %llu > flushed_seq %llu\n%s", - a->v.journal_seq, - c->journal.flushed_seq_ondisk, - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - ret = -EIO; - goto out; + if (!fastpath) { + if (discard_in_flight_add(ca, iter.pos.offset, true)) + goto out; + + discard_locked = true; } - if (discard_in_flight_add(ca, iter.pos.offset, true)) - goto out; - - discard_locked = true; - if (!bkey_eq(*discard_pos_done, iter.pos) && ca->mi.discard && !c->opts.nochanges) { /* @@ -1844,6 +1877,7 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, ca->mi.bucket_size, GFP_KERNEL); *discard_pos_done = iter.pos; + s->discarded++; ret = bch2_trans_relock_notrace(trans); if (ret) @@ -1851,22 +1885,25 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, } SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false); -write: alloc_data_type_set(&a->v, a->v.data_type); - ret = bch2_trans_update(trans, &iter, &a->k_i, 0) ?: - bch2_trans_commit(trans, NULL, NULL, - BCH_WATERMARK_btree| - BCH_TRANS_COMMIT_no_enospc); + ret = bch2_trans_update(trans, &iter, &a->k_i, 0); + if (ret) + goto out; +commit: + ret = bch2_trans_commit(trans, NULL, NULL, + BCH_WATERMARK_btree| + BCH_TRANS_COMMIT_no_enospc); if (ret) goto out; count_event(c, bucket_discard); - s->discarded++; out: +fsck_err: if (discard_locked) discard_in_flight_remove(ca, iter.pos.offset); - s->seen++; + if (!ret) + s->seen++; bch2_trans_iter_exit(trans, &iter); printbuf_exit(&buf); return ret; @@ -1886,11 +1923,11 @@ static void bch2_do_discards_work(struct work_struct *work) * successful commit: */ ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, + for_each_btree_key_max(trans, iter, BTREE_ID_need_discard, POS(ca->dev_idx, 0), POS(ca->dev_idx, U64_MAX), 0, k, - bch2_discard_one_bucket(trans, ca, &iter, &discard_pos_done, &s))); + bch2_discard_one_bucket(trans, ca, &iter, &discard_pos_done, &s, false))); trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret)); @@ -1923,27 +1960,29 @@ void bch2_do_discards(struct bch_fs *c) bch2_dev_do_discards(ca); } -static int bch2_clear_bucket_needs_discard(struct btree_trans *trans, struct bpos bucket) +static int bch2_do_discards_fast_one(struct btree_trans *trans, + struct bch_dev *ca, + u64 bucket, + struct bpos *discard_pos_done, + struct discard_buckets_state *s) { - struct btree_iter iter; - bch2_trans_iter_init(trans, &iter, BTREE_ID_alloc, bucket, BTREE_ITER_intent); - struct bkey_s_c k = bch2_btree_iter_peek_slot(&iter); - int ret = bkey_err(k); + struct btree_iter need_discard_iter; + struct bkey_s_c discard_k = bch2_bkey_get_iter(trans, &need_discard_iter, + BTREE_ID_need_discard, POS(ca->dev_idx, bucket), 0); + int ret = bkey_err(discard_k); if (ret) - goto err; + return ret; - struct bkey_i_alloc_v4 *a = bch2_alloc_to_v4_mut(trans, k); - ret = PTR_ERR_OR_ZERO(a); - if (ret) - goto err; + if (log_fsck_err_on(discard_k.k->type != KEY_TYPE_set, + trans, discarding_bucket_not_in_need_discard_btree, + "attempting to discard bucket %u:%llu not in need_discard btree", + ca->dev_idx, bucket)) + goto out; - BUG_ON(a->v.dirty_sectors); - SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false); - alloc_data_type_set(&a->v, a->v.data_type); - - ret = bch2_trans_update(trans, &iter, &a->k_i, 0); -err: - bch2_trans_iter_exit(trans, &iter); + ret = bch2_discard_one_bucket(trans, ca, &need_discard_iter, discard_pos_done, s, true); +out: +fsck_err: + bch2_trans_iter_exit(trans, &need_discard_iter); return ret; } @@ -1951,6 +1990,10 @@ static void bch2_do_discards_fast_work(struct work_struct *work) { struct bch_dev *ca = container_of(work, struct bch_dev, discard_fast_work); struct bch_fs *c = ca->fs; + struct discard_buckets_state s = {}; + struct bpos discard_pos_done = POS_MAX; + struct btree_trans *trans = bch2_trans_get(c); + int ret = 0; while (1) { bool got_bucket = false; @@ -1971,16 +2014,8 @@ static void bch2_do_discards_fast_work(struct work_struct *work) if (!got_bucket) break; - if (ca->mi.discard && !c->opts.nochanges) - blkdev_issue_discard(ca->disk_sb.bdev, - bucket_to_sector(ca, bucket), - ca->mi.bucket_size, - GFP_KERNEL); - - int ret = bch2_trans_commit_do(c, NULL, NULL, - BCH_WATERMARK_btree| - BCH_TRANS_COMMIT_no_enospc, - bch2_clear_bucket_needs_discard(trans, POS(ca->dev_idx, bucket))); + ret = lockrestart_do(trans, + bch2_do_discards_fast_one(trans, ca, bucket, &discard_pos_done, &s)); bch_err_fn(c, ret); discard_in_flight_remove(ca, bucket); @@ -1989,6 +2024,9 @@ static void bch2_do_discards_fast_work(struct work_struct *work) break; } + trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret)); + + bch2_trans_put(trans); percpu_ref_put(&ca->io_ref); bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast); } @@ -2030,8 +2068,11 @@ static int invalidate_one_bucket(struct btree_trans *trans, return 1; if (!bch2_dev_bucket_exists(c, bucket)) { - prt_str(&buf, "lru entry points to invalid bucket"); - goto err; + if (fsck_err(trans, lru_entry_to_invalid_bucket, + "lru key points to nonexistent device:bucket %llu:%llu", + bucket.inode, bucket.offset)) + return bch2_btree_bit_mod_buffered(trans, BTREE_ID_lru, lru_iter->pos, false); + goto out; } if (bch2_bucket_is_open_safe(c, bucket.inode, bucket.offset)) @@ -2072,28 +2113,9 @@ static int invalidate_one_bucket(struct btree_trans *trans, trace_and_count(c, bucket_invalidate, c, bucket.inode, bucket.offset, cached_sectors); --*nr_to_invalidate; out: +fsck_err: printbuf_exit(&buf); return ret; -err: - prt_str(&buf, "\n lru key: "); - bch2_bkey_val_to_text(&buf, c, lru_k); - - prt_str(&buf, "\n lru entry: "); - bch2_lru_pos_to_text(&buf, lru_iter->pos); - - prt_str(&buf, "\n alloc key: "); - if (!a) - bch2_bpos_to_text(&buf, bucket); - else - bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&a->k_i)); - - bch_err(c, "%s", buf.buf); - if (c->curr_recovery_pass > BCH_RECOVERY_PASS_check_lrus) { - bch2_inconsistent_error(c); - ret = -EINVAL; - } - - goto out; } static struct bkey_s_c next_lru_key(struct btree_trans *trans, struct btree_iter *iter, @@ -2101,7 +2123,7 @@ static struct bkey_s_c next_lru_key(struct btree_trans *trans, struct btree_iter { struct bkey_s_c k; again: - k = bch2_btree_iter_peek_upto(iter, lru_pos(ca->dev_idx, U64_MAX, LRU_TIME_MAX)); + k = bch2_btree_iter_peek_max(iter, lru_pos(ca->dev_idx, U64_MAX, LRU_TIME_MAX)); if (!k.k && !*wrapped) { bch2_btree_iter_set_pos(iter, lru_pos(ca->dev_idx, 0, 0)); *wrapped = true; diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h index 163a67b97a40..de25ba4ee94b 100644 --- a/fs/bcachefs/alloc_background.h +++ b/fs/bcachefs/alloc_background.h @@ -8,8 +8,6 @@ #include "debug.h" #include "super.h" -enum bch_validate_flags; - /* How out of date a pointer gen is allowed to be: */ #define BUCKET_GC_GEN_MAX 96U @@ -245,10 +243,14 @@ struct bkey_i_alloc_v4 *bch2_alloc_to_v4_mut(struct btree_trans *, struct bkey_s int bch2_bucket_io_time_reset(struct btree_trans *, unsigned, size_t, int); -int bch2_alloc_v1_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); -int bch2_alloc_v2_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); -int bch2_alloc_v3_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); -int bch2_alloc_v4_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_alloc_v1_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int bch2_alloc_v2_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int bch2_alloc_v3_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int bch2_alloc_v4_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_alloc_v4_swab(struct bkey_s); void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); @@ -282,7 +284,7 @@ void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); }) int bch2_bucket_gens_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_bucket_gens_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_bucket_gens ((struct bkey_ops) { \ @@ -307,6 +309,8 @@ int bch2_alloc_key_to_dev_counters(struct btree_trans *, struct bch_dev *, int bch2_trigger_alloc(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); + +int bch2_check_discard_freespace_key(struct btree_trans *, struct btree_iter *, u8 *, bool); int bch2_check_alloc_info(struct bch_fs *); int bch2_check_alloc_to_lru_refs(struct bch_fs *); void bch2_dev_do_discards(struct bch_dev *); diff --git a/fs/bcachefs/alloc_background_format.h b/fs/bcachefs/alloc_background_format.h index befdaa95c515..740238369a5a 100644 --- a/fs/bcachefs/alloc_background_format.h +++ b/fs/bcachefs/alloc_background_format.h @@ -58,7 +58,7 @@ LE32_BITMASK(BCH_ALLOC_V3_NEED_INC_GEN,struct bch_alloc_v3, flags, 1, 2) struct bch_alloc_v4 { struct bch_val v; - __u64 journal_seq; + __u64 journal_seq_nonempty; __u32 flags; __u8 gen; __u8 oldest_gen; @@ -70,7 +70,7 @@ struct bch_alloc_v4 { __u32 stripe; __u32 nr_external_backpointers; /* end of fields in original version of alloc_v4 */ - __u64 _fragmentation_lru; /* obsolete */ + __u64 journal_seq_empty; __u32 stripe_sectors; __u32 pad; } __packed __aligned(8); diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index 372178c8d416..6df41c331a52 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -107,14 +107,10 @@ void __bch2_open_bucket_put(struct bch_fs *c, struct open_bucket *ob) return; } - percpu_down_read(&c->mark_lock); spin_lock(&ob->lock); - ob->valid = false; ob->data_type = 0; - spin_unlock(&ob->lock); - percpu_up_read(&c->mark_lock); spin_lock(&c->freelist_lock); bch2_open_bucket_hash_remove(c, ob); @@ -156,6 +152,14 @@ static struct open_bucket *bch2_open_bucket_alloc(struct bch_fs *c) return ob; } +static inline bool is_superblock_bucket(struct bch_fs *c, struct bch_dev *ca, u64 b) +{ + if (c->curr_recovery_pass > BCH_RECOVERY_PASS_trans_mark_dev_sbs) + return false; + + return bch2_is_superblock_bucket(ca, b); +} + static void open_bucket_free_unused(struct bch_fs *c, struct open_bucket *ob) { BUG_ON(c->open_buckets_partial_nr >= @@ -175,20 +179,6 @@ static void open_bucket_free_unused(struct bch_fs *c, struct open_bucket *ob) closure_wake_up(&c->freelist_wait); } -/* _only_ for allocating the journal on a new device: */ -long bch2_bucket_alloc_new_fs(struct bch_dev *ca) -{ - while (ca->new_fs_bucket_idx < ca->mi.nbuckets) { - u64 b = ca->new_fs_bucket_idx++; - - if (!is_superblock_bucket(ca, b) && - (!ca->buckets_nouse || !test_bit(b, ca->buckets_nouse))) - return b; - } - - return -1; -} - static inline unsigned open_buckets_reserved(enum bch_watermark watermark) { switch (watermark) { @@ -206,33 +196,40 @@ static inline unsigned open_buckets_reserved(enum bch_watermark watermark) } } -static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev *ca, - u64 bucket, - enum bch_watermark watermark, - const struct bch_alloc_v4 *a, - struct bucket_alloc_state *s, - struct closure *cl) +static inline bool may_alloc_bucket(struct bch_fs *c, + struct bpos bucket, + struct bucket_alloc_state *s) { - struct open_bucket *ob; - - if (unlikely(ca->buckets_nouse && test_bit(bucket, ca->buckets_nouse))) { - s->skipped_nouse++; - return NULL; - } - - if (bch2_bucket_is_open(c, ca->dev_idx, bucket)) { + if (bch2_bucket_is_open(c, bucket.inode, bucket.offset)) { s->skipped_open++; - return NULL; + return false; } if (bch2_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, - c->journal.flushed_seq_ondisk, ca->dev_idx, bucket)) { + c->journal.flushed_seq_ondisk, bucket.inode, bucket.offset)) { s->skipped_need_journal_commit++; - return NULL; + return false; } - if (bch2_bucket_nocow_is_locked(&c->nocow_locks, POS(ca->dev_idx, bucket))) { + if (bch2_bucket_nocow_is_locked(&c->nocow_locks, bucket)) { s->skipped_nocow++; + return false; + } + + return true; +} + +static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev *ca, + u64 bucket, u8 gen, + enum bch_watermark watermark, + struct bucket_alloc_state *s, + struct closure *cl) +{ + if (unlikely(is_superblock_bucket(c, ca, bucket))) + return NULL; + + if (unlikely(ca->buckets_nouse && test_bit(bucket, ca->buckets_nouse))) { + s->skipped_nouse++; return NULL; } @@ -254,14 +251,13 @@ static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev * return NULL; } - ob = bch2_open_bucket_alloc(c); + struct open_bucket *ob = bch2_open_bucket_alloc(c); spin_lock(&ob->lock); - ob->valid = true; ob->sectors_free = ca->mi.bucket_size; ob->dev = ca->dev_idx; - ob->gen = a->gen; + ob->gen = gen; ob->bucket = bucket; spin_unlock(&ob->lock); @@ -276,111 +272,29 @@ static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev * } static struct open_bucket *try_alloc_bucket(struct btree_trans *trans, struct bch_dev *ca, - enum bch_watermark watermark, u64 free_entry, + enum bch_watermark watermark, struct bucket_alloc_state *s, - struct bkey_s_c freespace_k, + struct btree_iter *freespace_iter, struct closure *cl) { struct bch_fs *c = trans->c; - struct btree_iter iter = { NULL }; - struct bkey_s_c k; - struct open_bucket *ob; - struct bch_alloc_v4 a_convert; - const struct bch_alloc_v4 *a; - u64 b = free_entry & ~(~0ULL << 56); - unsigned genbits = free_entry >> 56; - struct printbuf buf = PRINTBUF; - int ret; + u64 b = freespace_iter->pos.offset & ~(~0ULL << 56); - if (b < ca->mi.first_bucket || b >= ca->mi.nbuckets) { - prt_printf(&buf, "freespace btree has bucket outside allowed range %u-%llu\n" - " freespace key ", - ca->mi.first_bucket, ca->mi.nbuckets); - bch2_bkey_val_to_text(&buf, c, freespace_k); - bch2_trans_inconsistent(trans, "%s", buf.buf); - ob = ERR_PTR(-EIO); - goto err; - } + if (!may_alloc_bucket(c, POS(ca->dev_idx, b), s)) + return NULL; - k = bch2_bkey_get_iter(trans, &iter, - BTREE_ID_alloc, POS(ca->dev_idx, b), - BTREE_ITER_cached); - ret = bkey_err(k); - if (ret) { - ob = ERR_PTR(ret); - goto err; - } + u8 gen; + int ret = bch2_check_discard_freespace_key(trans, freespace_iter, &gen, true); + if (ret < 0) + return ERR_PTR(ret); + if (ret) + return NULL; - a = bch2_alloc_to_v4(k, &a_convert); - - if (a->data_type != BCH_DATA_free) { - if (c->curr_recovery_pass <= BCH_RECOVERY_PASS_check_alloc_info) { - ob = NULL; - goto err; - } - - prt_printf(&buf, "non free bucket in freespace btree\n" - " freespace key "); - bch2_bkey_val_to_text(&buf, c, freespace_k); - prt_printf(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, k); - bch2_trans_inconsistent(trans, "%s", buf.buf); - ob = ERR_PTR(-EIO); - goto err; - } - - if (genbits != (alloc_freespace_genbits(*a) >> 56) && - c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info) { - prt_printf(&buf, "bucket in freespace btree with wrong genbits (got %u should be %llu)\n" - " freespace key ", - genbits, alloc_freespace_genbits(*a) >> 56); - bch2_bkey_val_to_text(&buf, c, freespace_k); - prt_printf(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, k); - bch2_trans_inconsistent(trans, "%s", buf.buf); - ob = ERR_PTR(-EIO); - goto err; - } - - if (c->curr_recovery_pass <= BCH_RECOVERY_PASS_check_extents_to_backpointers) { - struct bch_backpointer bp; - struct bpos bp_pos = POS_MIN; - - ret = bch2_get_next_backpointer(trans, ca, POS(ca->dev_idx, b), -1, - &bp_pos, &bp, - BTREE_ITER_nopreserve); - if (ret) { - ob = ERR_PTR(ret); - goto err; - } - - if (!bkey_eq(bp_pos, POS_MAX)) { - /* - * Bucket may have data in it - we don't call - * bc2h_trans_inconnsistent() because fsck hasn't - * finished yet - */ - ob = NULL; - goto err; - } - } - - ob = __try_alloc_bucket(c, ca, b, watermark, a, s, cl); - if (!ob) - bch2_set_btree_iter_dontneed(&iter); -err: - if (iter.path) - bch2_set_btree_iter_dontneed(&iter); - bch2_trans_iter_exit(trans, &iter); - printbuf_exit(&buf); - return ob; + return __try_alloc_bucket(c, ca, b, gen, watermark, s, cl); } /* * This path is for before the freespace btree is initialized: - * - * If ca->new_fs_bucket_idx is nonzero, we haven't yet marked superblock & - * journal buckets - journal buckets will be < ca->new_fs_bucket_idx */ static noinline struct open_bucket * bch2_bucket_alloc_early(struct btree_trans *trans, @@ -389,10 +303,11 @@ bch2_bucket_alloc_early(struct btree_trans *trans, struct bucket_alloc_state *s, struct closure *cl) { + struct bch_fs *c = trans->c; struct btree_iter iter, citer; struct bkey_s_c k, ck; struct open_bucket *ob = NULL; - u64 first_bucket = max_t(u64, ca->mi.first_bucket, ca->new_fs_bucket_idx); + u64 first_bucket = ca->mi.first_bucket; u64 *dev_alloc_cursor = &ca->alloc_cursor[s->btree_bitmap]; u64 alloc_start = max(first_bucket, *dev_alloc_cursor); u64 alloc_cursor = alloc_start; @@ -415,10 +330,6 @@ again: if (bkey_ge(k.k->p, POS(ca->dev_idx, ca->mi.nbuckets))) break; - if (ca->new_fs_bucket_idx && - is_superblock_bucket(ca, k.k->p.offset)) - continue; - if (s->btree_bitmap != BTREE_BITMAP_ANY && s->btree_bitmap != bch2_dev_btree_bitmap_marked_sectors(ca, bucket_to_sector(ca, bucket), ca->mi.bucket_size)) { @@ -452,7 +363,10 @@ again: s->buckets_seen++; - ob = __try_alloc_bucket(trans->c, ca, k.k->p.offset, watermark, a, s, cl); + ob = may_alloc_bucket(c, k.k->p, s) + ? __try_alloc_bucket(c, ca, k.k->p.offset, a->gen, + watermark, s, cl) + : NULL; next: bch2_set_btree_iter_dontneed(&citer); bch2_trans_iter_exit(trans, &citer); @@ -489,20 +403,21 @@ static struct open_bucket *bch2_bucket_alloc_freelist(struct btree_trans *trans, u64 alloc_start = max_t(u64, ca->mi.first_bucket, READ_ONCE(*dev_alloc_cursor)); u64 alloc_cursor = alloc_start; int ret; - - BUG_ON(ca->new_fs_bucket_idx); again: - for_each_btree_key_norestart(trans, iter, BTREE_ID_freespace, - POS(ca->dev_idx, alloc_cursor), 0, k, ret) { - if (k.k->p.inode != ca->dev_idx) - break; + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_freespace, + POS(ca->dev_idx, alloc_cursor), + POS(ca->dev_idx, U64_MAX), + 0, k, ret) { + /* + * peek normally dosen't trim extents - they can span iter.pos, + * which is not what we want here: + */ + iter.k.size = iter.k.p.offset - iter.pos.offset; - for (alloc_cursor = max(alloc_cursor, bkey_start_offset(k.k)); - alloc_cursor < k.k->p.offset; - alloc_cursor++) { + while (iter.k.size) { s->buckets_seen++; - u64 bucket = alloc_cursor & ~(~0ULL << 56); + u64 bucket = iter.pos.offset & ~(~0ULL << 56); if (s->btree_bitmap != BTREE_BITMAP_ANY && s->btree_bitmap != bch2_dev_btree_bitmap_marked_sectors(ca, bucket_to_sector(ca, bucket), ca->mi.bucket_size)) { @@ -511,32 +426,36 @@ again: goto fail; bucket = sector_to_bucket(ca, - round_up(bucket_to_sector(ca, bucket) + 1, + round_up(bucket_to_sector(ca, bucket + 1), 1ULL << ca->mi.btree_bitmap_shift)); - u64 genbits = alloc_cursor >> 56; - alloc_cursor = bucket | (genbits << 56); + alloc_cursor = bucket|(iter.pos.offset & (~0ULL << 56)); - if (alloc_cursor > k.k->p.offset) - bch2_btree_iter_set_pos(&iter, POS(ca->dev_idx, alloc_cursor)); + bch2_btree_iter_set_pos(&iter, POS(ca->dev_idx, alloc_cursor)); s->skipped_mi_btree_bitmap++; - continue; + goto next; } - ob = try_alloc_bucket(trans, ca, watermark, - alloc_cursor, s, k, cl); + ob = try_alloc_bucket(trans, ca, watermark, s, &iter, cl); if (ob) { + if (!IS_ERR(ob)) + *dev_alloc_cursor = iter.pos.offset; bch2_set_btree_iter_dontneed(&iter); break; } - } + iter.k.size--; + iter.pos.offset++; + } +next: if (ob || ret) break; } fail: bch2_trans_iter_exit(trans, &iter); - if (!ob && ret) + BUG_ON(ob && ret); + + if (ret) ob = ERR_PTR(ret); if (!ob && alloc_start > ca->mi.first_bucket) { @@ -544,8 +463,6 @@ fail: goto again; } - *dev_alloc_cursor = alloc_cursor; - return ob; } @@ -595,6 +512,7 @@ static noinline void trace_bucket_alloc2(struct bch_fs *c, struct bch_dev *ca, * @watermark: how important is this allocation? * @data_type: BCH_DATA_journal, btree, user... * @cl: if not NULL, closure to be used to wait if buckets not available + * @nowait: if true, do not wait for buckets to become available * @usage: for secondarily also returning the current device usage * * Returns: an open_bucket on success, or an ERR_PTR() on failure. @@ -629,6 +547,10 @@ again: bch2_dev_do_invalidates(ca); if (!avail) { + if (watermark > BCH_WATERMARK_normal && + c->curr_recovery_pass <= BCH_RECOVERY_PASS_check_allocations) + goto alloc; + if (cl && !waiting) { closure_wait(&c->freelist_wait, cl); waiting = true; @@ -711,9 +633,9 @@ struct dev_alloc_list bch2_dev_alloc_list(struct bch_fs *c, unsigned i; for_each_set_bit(i, devs->d, BCH_SB_MEMBERS_MAX) - ret.devs[ret.nr++] = i; + ret.data[ret.nr++] = i; - bubble_sort(ret.devs, ret.nr, dev_stripe_cmp); + bubble_sort(ret.data, ret.nr, dev_stripe_cmp); return ret; } @@ -785,18 +707,13 @@ int bch2_bucket_alloc_set_trans(struct btree_trans *trans, struct closure *cl) { struct bch_fs *c = trans->c; - struct dev_alloc_list devs_sorted = - bch2_dev_alloc_list(c, stripe, devs_may_alloc); int ret = -BCH_ERR_insufficient_devices; BUG_ON(*nr_effective >= nr_replicas); - for (unsigned i = 0; i < devs_sorted.nr; i++) { - struct bch_dev_usage usage; - struct open_bucket *ob; - - unsigned dev = devs_sorted.devs[i]; - struct bch_dev *ca = bch2_dev_tryget_noerror(c, dev); + struct dev_alloc_list devs_sorted = bch2_dev_alloc_list(c, stripe, devs_may_alloc); + darray_for_each(devs_sorted, i) { + struct bch_dev *ca = bch2_dev_tryget_noerror(c, *i); if (!ca) continue; @@ -805,8 +722,9 @@ int bch2_bucket_alloc_set_trans(struct btree_trans *trans, continue; } - ob = bch2_bucket_alloc_trans(trans, ca, watermark, data_type, - cl, flags & BCH_WRITE_ALLOC_NOWAIT, &usage); + struct bch_dev_usage usage; + struct open_bucket *ob = bch2_bucket_alloc_trans(trans, ca, watermark, data_type, + cl, flags & BCH_WRITE_ALLOC_NOWAIT, &usage); if (!IS_ERR(ob)) bch2_dev_stripe_increment_inlined(ca, stripe, &usage); bch2_dev_put(ca); @@ -850,10 +768,6 @@ static int bucket_alloc_from_stripe(struct btree_trans *trans, struct closure *cl) { struct bch_fs *c = trans->c; - struct dev_alloc_list devs_sorted; - struct ec_stripe_head *h; - struct open_bucket *ob; - unsigned i, ec_idx; int ret = 0; if (nr_replicas < 2) @@ -862,34 +776,32 @@ static int bucket_alloc_from_stripe(struct btree_trans *trans, if (ec_open_bucket(c, ptrs)) return 0; - h = bch2_ec_stripe_head_get(trans, target, 0, nr_replicas - 1, watermark, cl); + struct ec_stripe_head *h = + bch2_ec_stripe_head_get(trans, target, 0, nr_replicas - 1, watermark, cl); if (IS_ERR(h)) return PTR_ERR(h); if (!h) return 0; - devs_sorted = bch2_dev_alloc_list(c, &wp->stripe, devs_may_alloc); - - for (i = 0; i < devs_sorted.nr; i++) - for (ec_idx = 0; ec_idx < h->s->nr_data; ec_idx++) { + struct dev_alloc_list devs_sorted = bch2_dev_alloc_list(c, &wp->stripe, devs_may_alloc); + darray_for_each(devs_sorted, i) + for (unsigned ec_idx = 0; ec_idx < h->s->nr_data; ec_idx++) { if (!h->s->blocks[ec_idx]) continue; - ob = c->open_buckets + h->s->blocks[ec_idx]; - if (ob->dev == devs_sorted.devs[i] && - !test_and_set_bit(ec_idx, h->s->blocks_allocated)) - goto got_bucket; - } - goto out_put_head; -got_bucket: - ob->ec_idx = ec_idx; - ob->ec = h->s; - ec_stripe_new_get(h->s, STRIPE_REF_io); + struct open_bucket *ob = c->open_buckets + h->s->blocks[ec_idx]; + if (ob->dev == *i && !test_and_set_bit(ec_idx, h->s->blocks_allocated)) { + ob->ec_idx = ec_idx; + ob->ec = h->s; + ec_stripe_new_get(h->s, STRIPE_REF_io); - ret = add_new_bucket(c, ptrs, devs_may_alloc, - nr_replicas, nr_effective, - have_cache, ob); -out_put_head: + ret = add_new_bucket(c, ptrs, devs_may_alloc, + nr_replicas, nr_effective, + have_cache, ob); + goto out; + } + } +out: bch2_ec_stripe_head_put(c, h); return ret; } diff --git a/fs/bcachefs/alloc_foreground.h b/fs/bcachefs/alloc_foreground.h index 1a16fd5bd4f8..f25481a0d1a0 100644 --- a/fs/bcachefs/alloc_foreground.h +++ b/fs/bcachefs/alloc_foreground.h @@ -20,7 +20,7 @@ void bch2_reset_alloc_cursors(struct bch_fs *); struct dev_alloc_list { unsigned nr; - u8 devs[BCH_SB_MEMBERS_MAX]; + u8 data[BCH_SB_MEMBERS_MAX]; }; struct dev_alloc_list bch2_dev_alloc_list(struct bch_fs *, @@ -28,8 +28,6 @@ struct dev_alloc_list bch2_dev_alloc_list(struct bch_fs *, struct bch_devs_mask *); void bch2_dev_stripe_increment(struct bch_dev *, struct dev_stripe_state *); -long bch2_bucket_alloc_new_fs(struct bch_dev *); - static inline struct bch_dev *ob_dev(struct bch_fs *c, struct open_bucket *ob) { return bch2_dev_have_ref(c, ob->dev); diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index 654a58132a4d..ebeb6a5ff9d2 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -14,42 +14,8 @@ #include -static bool extent_matches_bp(struct bch_fs *c, - enum btree_id btree_id, unsigned level, - struct bkey_s_c k, - struct bpos bucket, - struct bch_backpointer bp) -{ - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - const union bch_extent_entry *entry; - struct extent_ptr_decoded p; - - rcu_read_lock(); - bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - struct bpos bucket2; - struct bch_backpointer bp2; - - if (p.ptr.cached) - continue; - - struct bch_dev *ca = bch2_dev_rcu(c, p.ptr.dev); - if (!ca) - continue; - - bch2_extent_ptr_to_bp(c, ca, btree_id, level, k, p, entry, &bucket2, &bp2); - if (bpos_eq(bucket, bucket2) && - !memcmp(&bp, &bp2, sizeof(bp))) { - rcu_read_unlock(); - return true; - } - } - rcu_read_unlock(); - - return false; -} - int bch2_backpointer_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k); int ret = 0; @@ -59,67 +25,70 @@ int bch2_backpointer_validate(struct bch_fs *c, struct bkey_s_c k, "backpointer level bad: %u >= %u", bp.v->level, BTREE_MAX_DEPTH); - rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu_noerror(c, bp.k->p.inode); - if (!ca) { - /* these will be caught by fsck */ - rcu_read_unlock(); - return 0; - } - - struct bpos bucket = bp_pos_to_bucket(ca, bp.k->p); - struct bpos bp_pos = bucket_pos_to_bp_noerror(ca, bucket, bp.v->bucket_offset); - rcu_read_unlock(); - - bkey_fsck_err_on((bp.v->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT) >= ca->mi.bucket_size || - !bpos_eq(bp.k->p, bp_pos), - c, backpointer_bucket_offset_wrong, - "backpointer bucket_offset wrong"); + bkey_fsck_err_on(bp.k->p.inode == BCH_SB_MEMBER_INVALID, + c, backpointer_dev_bad, + "backpointer for BCH_SB_MEMBER_INVALID"); fsck_err: return ret; } -void bch2_backpointer_to_text(struct printbuf *out, const struct bch_backpointer *bp) +void bch2_backpointer_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { - prt_printf(out, "btree=%s l=%u offset=%llu:%u len=%u pos=", - bch2_btree_id_str(bp->btree_id), - bp->level, - (u64) (bp->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT), - (u32) bp->bucket_offset & ~(~0U << MAX_EXTENT_COMPRESS_RATIO_SHIFT), - bp->bucket_len); - bch2_bpos_to_text(out, bp->pos); -} + struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k); -void bch2_backpointer_k_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) -{ rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu_noerror(c, k.k->p.inode); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, bp.k->p.inode); if (ca) { - struct bpos bucket = bp_pos_to_bucket(ca, k.k->p); + u32 bucket_offset; + struct bpos bucket = bp_pos_to_bucket_and_offset(ca, bp.k->p, &bucket_offset); rcu_read_unlock(); - prt_str(out, "bucket="); - bch2_bpos_to_text(out, bucket); - prt_str(out, " "); + prt_printf(out, "bucket=%llu:%llu:%u ", bucket.inode, bucket.offset, bucket_offset); } else { rcu_read_unlock(); + prt_printf(out, "sector=%llu:%llu ", bp.k->p.inode, bp.k->p.offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT); } - bch2_backpointer_to_text(out, bkey_s_c_to_backpointer(k).v); + bch2_btree_id_level_to_text(out, bp.v->btree_id, bp.v->level); + prt_printf(out, " suboffset=%u len=%u gen=%u pos=", + (u32) bp.k->p.offset & ~(~0U << MAX_EXTENT_COMPRESS_RATIO_SHIFT), + bp.v->bucket_len, + bp.v->bucket_gen); + bch2_bpos_to_text(out, bp.v->pos); } void bch2_backpointer_swab(struct bkey_s k) { struct bkey_s_backpointer bp = bkey_s_to_backpointer(k); - bp.v->bucket_offset = swab40(bp.v->bucket_offset); bp.v->bucket_len = swab32(bp.v->bucket_len); bch2_bpos_swab(&bp.v->pos); } +static bool extent_matches_bp(struct bch_fs *c, + enum btree_id btree_id, unsigned level, + struct bkey_s_c k, + struct bkey_s_c_backpointer bp) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { + struct bkey_i_backpointer bp2; + bch2_extent_ptr_to_bp(c, btree_id, level, k, p, entry, &bp2); + + if (bpos_eq(bp.k->p, bp2.k.p) && + !memcmp(bp.v, &bp2.v, sizeof(bp2.v))) + return true; + } + + return false; +} + static noinline int backpointer_mod_err(struct btree_trans *trans, - struct bch_backpointer bp, - struct bkey_s_c bp_k, struct bkey_s_c orig_k, + struct bkey_i_backpointer *new_bp, + struct bkey_s_c found_bp, bool insert) { struct bch_fs *c = trans->c; @@ -127,12 +96,12 @@ static noinline int backpointer_mod_err(struct btree_trans *trans, if (insert) { prt_printf(&buf, "existing backpointer found when inserting "); - bch2_backpointer_to_text(&buf, &bp); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&new_bp->k_i)); prt_newline(&buf); printbuf_indent_add(&buf, 2); prt_printf(&buf, "found "); - bch2_bkey_val_to_text(&buf, c, bp_k); + bch2_bkey_val_to_text(&buf, c, found_bp); prt_newline(&buf); prt_printf(&buf, "for "); @@ -144,11 +113,11 @@ static noinline int backpointer_mod_err(struct btree_trans *trans, printbuf_indent_add(&buf, 2); prt_printf(&buf, "searching for "); - bch2_backpointer_to_text(&buf, &bp); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&new_bp->k_i)); prt_newline(&buf); prt_printf(&buf, "got "); - bch2_bkey_val_to_text(&buf, c, bp_k); + bch2_bkey_val_to_text(&buf, c, found_bp); prt_newline(&buf); prt_printf(&buf, "for "); @@ -167,161 +136,118 @@ static noinline int backpointer_mod_err(struct btree_trans *trans, } int bch2_bucket_backpointer_mod_nowritebuffer(struct btree_trans *trans, - struct bch_dev *ca, - struct bpos bucket, - struct bch_backpointer bp, struct bkey_s_c orig_k, + struct bkey_i_backpointer *bp, bool insert) { struct btree_iter bp_iter; - struct bkey_s_c k; - struct bkey_i_backpointer *bp_k; - int ret; - - bp_k = bch2_trans_kmalloc_nomemzero(trans, sizeof(struct bkey_i_backpointer)); - ret = PTR_ERR_OR_ZERO(bp_k); - if (ret) - return ret; - - bkey_backpointer_init(&bp_k->k_i); - bp_k->k.p = bucket_pos_to_bp(ca, bucket, bp.bucket_offset); - bp_k->v = bp; - - if (!insert) { - bp_k->k.type = KEY_TYPE_deleted; - set_bkey_val_u64s(&bp_k->k, 0); - } - - k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers, - bp_k->k.p, + struct bkey_s_c k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers, + bp->k.p, BTREE_ITER_intent| BTREE_ITER_slots| BTREE_ITER_with_updates); - ret = bkey_err(k); + int ret = bkey_err(k); if (ret) - goto err; + return ret; if (insert ? k.k->type : (k.k->type != KEY_TYPE_backpointer || - memcmp(bkey_s_c_to_backpointer(k).v, &bp, sizeof(bp)))) { - ret = backpointer_mod_err(trans, bp, k, orig_k, insert); + memcmp(bkey_s_c_to_backpointer(k).v, &bp->v, sizeof(bp->v)))) { + ret = backpointer_mod_err(trans, orig_k, bp, k, insert); if (ret) goto err; } - ret = bch2_trans_update(trans, &bp_iter, &bp_k->k_i, 0); + if (!insert) { + bp->k.type = KEY_TYPE_deleted; + set_bkey_val_u64s(&bp->k, 0); + } + + ret = bch2_trans_update(trans, &bp_iter, &bp->k_i, 0); err: bch2_trans_iter_exit(trans, &bp_iter); return ret; } -/* - * Find the next backpointer >= *bp_offset: - */ -int bch2_get_next_backpointer(struct btree_trans *trans, - struct bch_dev *ca, - struct bpos bucket, int gen, - struct bpos *bp_pos, - struct bch_backpointer *bp, - unsigned iter_flags) +static int bch2_backpointer_del(struct btree_trans *trans, struct bpos pos) { - struct bpos bp_end_pos = bucket_pos_to_bp(ca, bpos_nosnap_successor(bucket), 0); - struct btree_iter alloc_iter = { NULL }, bp_iter = { NULL }; - struct bkey_s_c k; - int ret = 0; - - if (bpos_ge(*bp_pos, bp_end_pos)) - goto done; - - if (gen >= 0) { - k = bch2_bkey_get_iter(trans, &alloc_iter, BTREE_ID_alloc, - bucket, BTREE_ITER_cached|iter_flags); - ret = bkey_err(k); - if (ret) - goto out; - - if (k.k->type != KEY_TYPE_alloc_v4 || - bkey_s_c_to_alloc_v4(k).v->gen != gen) - goto done; - } - - *bp_pos = bpos_max(*bp_pos, bucket_pos_to_bp(ca, bucket, 0)); - - for_each_btree_key_norestart(trans, bp_iter, BTREE_ID_backpointers, - *bp_pos, iter_flags, k, ret) { - if (bpos_ge(k.k->p, bp_end_pos)) - break; - - *bp_pos = k.k->p; - *bp = *bkey_s_c_to_backpointer(k).v; - goto out; - } -done: - *bp_pos = SPOS_MAX; -out: - bch2_trans_iter_exit(trans, &bp_iter); - bch2_trans_iter_exit(trans, &alloc_iter); - return ret; + return (likely(!bch2_backpointers_no_use_write_buffer) + ? bch2_btree_delete_at_buffered(trans, BTREE_ID_backpointers, pos) + : bch2_btree_delete(trans, BTREE_ID_backpointers, pos, 0)) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); } -static void backpointer_not_found(struct btree_trans *trans, - struct bpos bp_pos, - struct bch_backpointer bp, - struct bkey_s_c k) +static inline int bch2_backpointers_maybe_flush(struct btree_trans *trans, + struct bkey_s_c visiting_k, + struct bkey_buf *last_flushed) +{ + return likely(!bch2_backpointers_no_use_write_buffer) + ? bch2_btree_write_buffer_maybe_flush(trans, visiting_k, last_flushed) + : 0; +} + +static int backpointer_target_not_found(struct btree_trans *trans, + struct bkey_s_c_backpointer bp, + struct bkey_s_c target_k, + struct bkey_buf *last_flushed) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; + int ret = 0; /* * If we're using the btree write buffer, the backpointer we were * looking at may have already been deleted - failure to find what it * pointed to is not an error: */ - if (likely(!bch2_backpointers_no_use_write_buffer)) - return; - - struct bpos bucket; - if (!bp_pos_to_bucket_nodev(c, bp_pos, &bucket)) - return; + ret = last_flushed + ? bch2_backpointers_maybe_flush(trans, bp.s_c, last_flushed) + : 0; + if (ret) + return ret; prt_printf(&buf, "backpointer doesn't match %s it points to:\n ", - bp.level ? "btree node" : "extent"); - prt_printf(&buf, "bucket: "); - bch2_bpos_to_text(&buf, bucket); - prt_printf(&buf, "\n "); + bp.v->level ? "btree node" : "extent"); + bch2_bkey_val_to_text(&buf, c, bp.s_c); - prt_printf(&buf, "backpointer pos: "); - bch2_bpos_to_text(&buf, bp_pos); prt_printf(&buf, "\n "); + bch2_bkey_val_to_text(&buf, c, target_k); - bch2_backpointer_to_text(&buf, &bp); - prt_printf(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, k); - if (c->curr_recovery_pass >= BCH_RECOVERY_PASS_check_extents_to_backpointers) - bch_err_ratelimited(c, "%s", buf.buf); - else - bch2_trans_inconsistent(trans, "%s", buf.buf); + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(target_k); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + bkey_for_each_ptr_decode(target_k.k, ptrs, p, entry) + if (p.ptr.dev == bp.k->p.inode) { + prt_printf(&buf, "\n "); + struct bkey_i_backpointer bp2; + bch2_extent_ptr_to_bp(c, bp.v->btree_id, bp.v->level, target_k, p, entry, &bp2); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&bp2.k_i)); + } + if (fsck_err(trans, backpointer_to_missing_ptr, + "%s", buf.buf)) + ret = bch2_backpointer_del(trans, bp.k->p); +fsck_err: printbuf_exit(&buf); + return ret; } struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans, + struct bkey_s_c_backpointer bp, struct btree_iter *iter, - struct bpos bp_pos, - struct bch_backpointer bp, - unsigned iter_flags) + unsigned iter_flags, + struct bkey_buf *last_flushed) { - if (likely(!bp.level)) { - struct bch_fs *c = trans->c; + struct bch_fs *c = trans->c; - struct bpos bucket; - if (!bp_pos_to_bucket_nodev(c, bp_pos, &bucket)) - return bkey_s_c_err(-EIO); + if (unlikely(bp.v->btree_id >= btree_id_nr_alive(c))) + return bkey_s_c_null; + if (likely(!bp.v->level)) { bch2_trans_node_iter_init(trans, iter, - bp.btree_id, - bp.pos, + bp.v->btree_id, + bp.v->pos, 0, 0, iter_flags); struct bkey_s_c k = bch2_btree_iter_peek_slot(iter); @@ -330,67 +256,64 @@ struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans, return k; } - if (k.k && extent_matches_bp(c, bp.btree_id, bp.level, k, bucket, bp)) + if (k.k && + extent_matches_bp(c, bp.v->btree_id, bp.v->level, k, bp)) return k; bch2_trans_iter_exit(trans, iter); - backpointer_not_found(trans, bp_pos, bp, k); - return bkey_s_c_null; + int ret = backpointer_target_not_found(trans, bp, k, last_flushed); + return ret ? bkey_s_c_err(ret) : bkey_s_c_null; } else { - struct btree *b = bch2_backpointer_get_node(trans, iter, bp_pos, bp); + struct btree *b = bch2_backpointer_get_node(trans, bp, iter, last_flushed); + if (IS_ERR_OR_NULL(b)) + return ((struct bkey_s_c) { .k = ERR_CAST(b) }); - if (IS_ERR_OR_NULL(b)) { - bch2_trans_iter_exit(trans, iter); - return IS_ERR(b) ? bkey_s_c_err(PTR_ERR(b)) : bkey_s_c_null; - } return bkey_i_to_s_c(&b->key); } } struct btree *bch2_backpointer_get_node(struct btree_trans *trans, + struct bkey_s_c_backpointer bp, struct btree_iter *iter, - struct bpos bp_pos, - struct bch_backpointer bp) + struct bkey_buf *last_flushed) { struct bch_fs *c = trans->c; - BUG_ON(!bp.level); - - struct bpos bucket; - if (!bp_pos_to_bucket_nodev(c, bp_pos, &bucket)) - return ERR_PTR(-EIO); + BUG_ON(!bp.v->level); bch2_trans_node_iter_init(trans, iter, - bp.btree_id, - bp.pos, + bp.v->btree_id, + bp.v->pos, 0, - bp.level - 1, + bp.v->level - 1, 0); struct btree *b = bch2_btree_iter_peek_node(iter); if (IS_ERR_OR_NULL(b)) goto err; - BUG_ON(b->c.level != bp.level - 1); + BUG_ON(b->c.level != bp.v->level - 1); - if (extent_matches_bp(c, bp.btree_id, bp.level, - bkey_i_to_s_c(&b->key), - bucket, bp)) + if (extent_matches_bp(c, bp.v->btree_id, bp.v->level, + bkey_i_to_s_c(&b->key), bp)) return b; if (btree_node_will_make_reachable(b)) { b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node); } else { - backpointer_not_found(trans, bp_pos, bp, bkey_i_to_s_c(&b->key)); - b = NULL; + int ret = backpointer_target_not_found(trans, bp, bkey_i_to_s_c(&b->key), last_flushed); + b = ret ? ERR_PTR(ret) : NULL; } err: bch2_trans_iter_exit(trans, iter); return b; } -static int bch2_check_btree_backpointer(struct btree_trans *trans, struct btree_iter *bp_iter, - struct bkey_s_c k) +static int bch2_check_backpointer_has_valid_bucket(struct btree_trans *trans, struct bkey_s_c k, + struct bkey_buf *last_flushed) { + if (k.k->type != KEY_TYPE_backpointer) + return 0; + struct bch_fs *c = trans->c; struct btree_iter alloc_iter = { NULL }; struct bkey_s_c alloc_k; @@ -399,10 +322,14 @@ static int bch2_check_btree_backpointer(struct btree_trans *trans, struct btree_ struct bpos bucket; if (!bp_pos_to_bucket_nodev_noerror(c, k.k->p, &bucket)) { + ret = bch2_backpointers_maybe_flush(trans, k, last_flushed); + if (ret) + goto out; + if (fsck_err(trans, backpointer_to_missing_device, "backpointer for missing device:\n%s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - ret = bch2_btree_delete_at(trans, bp_iter, 0); + ret = bch2_backpointer_del(trans, k.k->p); goto out; } @@ -411,13 +338,16 @@ static int bch2_check_btree_backpointer(struct btree_trans *trans, struct btree_ if (ret) goto out; - if (fsck_err_on(alloc_k.k->type != KEY_TYPE_alloc_v4, - trans, backpointer_to_missing_alloc, - "backpointer for nonexistent alloc key: %llu:%llu:0\n%s", - alloc_iter.pos.inode, alloc_iter.pos.offset, - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - ret = bch2_btree_delete_at(trans, bp_iter, 0); - goto out; + if (alloc_k.k->type != KEY_TYPE_alloc_v4) { + ret = bch2_backpointers_maybe_flush(trans, k, last_flushed); + if (ret) + goto out; + + if (fsck_err(trans, backpointer_to_missing_alloc, + "backpointer for nonexistent alloc key: %llu:%llu:0\n%s", + alloc_iter.pos.inode, alloc_iter.pos.offset, + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + ret = bch2_backpointer_del(trans, k.k->p); } out: fsck_err: @@ -429,18 +359,24 @@ fsck_err: /* verify that every backpointer has a corresponding alloc key */ int bch2_check_btree_backpointers(struct bch_fs *c) { + struct bkey_buf last_flushed; + bch2_bkey_buf_init(&last_flushed); + bkey_init(&last_flushed.k->k); + int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_backpointers, POS_MIN, 0, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - bch2_check_btree_backpointer(trans, &iter, k))); + bch2_check_backpointer_has_valid_bucket(trans, k, &last_flushed))); + + bch2_bkey_buf_exit(&last_flushed, c); bch_err_fn(c, ret); return ret; } struct extents_to_bp_state { - struct bpos bucket_start; - struct bpos bucket_end; + struct bpos bp_start; + struct bpos bp_end; struct bkey_buf last_flushed; }; @@ -501,9 +437,13 @@ found: goto err; prt_str(&buf, "extents pointing to same space, but first extent checksum bad:"); - prt_printf(&buf, "\n %s ", bch2_btree_id_str(btree)); + prt_printf(&buf, "\n "); + bch2_btree_id_to_text(&buf, btree); + prt_str(&buf, " "); bch2_bkey_val_to_text(&buf, c, extent); - prt_printf(&buf, "\n %s ", bch2_btree_id_str(o_btree)); + prt_printf(&buf, "\n "); + bch2_btree_id_to_text(&buf, o_btree); + prt_str(&buf, " "); bch2_bkey_val_to_text(&buf, c, extent2); struct nonce nonce = extent_nonce(extent.k->bversion, p.crc); @@ -524,41 +464,25 @@ err: static int check_bp_exists(struct btree_trans *trans, struct extents_to_bp_state *s, - struct bpos bucket, - struct bch_backpointer bp, + struct bkey_i_backpointer *bp, struct bkey_s_c orig_k) { struct bch_fs *c = trans->c; - struct btree_iter bp_iter = {}; struct btree_iter other_extent_iter = {}; struct printbuf buf = PRINTBUF; - struct bkey_s_c bp_k; - int ret = 0; - struct bch_dev *ca = bch2_dev_bucket_tryget(c, bucket); - if (!ca) { - prt_str(&buf, "extent for nonexistent device:bucket "); - bch2_bpos_to_text(&buf, bucket); - prt_str(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, orig_k); - bch_err(c, "%s", buf.buf); - ret = -BCH_ERR_fsck_repair_unimplemented; - goto err; - } + if (bpos_lt(bp->k.p, s->bp_start) || + bpos_gt(bp->k.p, s->bp_end)) + return 0; - if (bpos_lt(bucket, s->bucket_start) || - bpos_gt(bucket, s->bucket_end)) - goto out; - - bp_k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers, - bucket_pos_to_bp(ca, bucket, bp.bucket_offset), - 0); - ret = bkey_err(bp_k); + struct btree_iter bp_iter; + struct bkey_s_c bp_k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers, bp->k.p, 0); + int ret = bkey_err(bp_k); if (ret) goto err; if (bp_k.k->type != KEY_TYPE_backpointer || - memcmp(bkey_s_c_to_backpointer(bp_k).v, &bp, sizeof(bp))) { + memcmp(bkey_s_c_to_backpointer(bp_k).v, &bp->v, sizeof(bp->v))) { ret = bch2_btree_write_buffer_maybe_flush(trans, orig_k, &s->last_flushed); if (ret) goto err; @@ -570,7 +494,6 @@ err: fsck_err: bch2_trans_iter_exit(trans, &other_extent_iter); bch2_trans_iter_exit(trans, &bp_iter); - bch2_dev_put(ca); printbuf_exit(&buf); return ret; check_existing_bp: @@ -578,10 +501,10 @@ check_existing_bp: if (bp_k.k->type != KEY_TYPE_backpointer) goto missing; - struct bch_backpointer other_bp = *bkey_s_c_to_backpointer(bp_k).v; + struct bkey_s_c_backpointer other_bp = bkey_s_c_to_backpointer(bp_k); struct bkey_s_c other_extent = - bch2_backpointer_get_key(trans, &other_extent_iter, bp_k.k->p, other_bp, 0); + bch2_backpointer_get_key(trans, other_bp, &other_extent_iter, 0, NULL); ret = bkey_err(other_extent); if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node) ret = 0; @@ -600,19 +523,23 @@ check_existing_bp: bch_err(c, "%s", buf.buf); if (other_extent.k->size <= orig_k.k->size) { - ret = drop_dev_and_update(trans, other_bp.btree_id, other_extent, bucket.inode); + ret = drop_dev_and_update(trans, other_bp.v->btree_id, + other_extent, bp->k.p.inode); if (ret) goto err; goto out; } else { - ret = drop_dev_and_update(trans, bp.btree_id, orig_k, bucket.inode); + ret = drop_dev_and_update(trans, bp->v.btree_id, orig_k, bp->k.p.inode); if (ret) goto err; goto missing; } } - ret = check_extent_checksum(trans, other_bp.btree_id, other_extent, bp.btree_id, orig_k, bucket.inode); + ret = check_extent_checksum(trans, + other_bp.v->btree_id, other_extent, + bp->v.btree_id, orig_k, + bp->k.p.inode); if (ret < 0) goto err; if (ret) { @@ -620,7 +547,8 @@ check_existing_bp: goto missing; } - ret = check_extent_checksum(trans, bp.btree_id, orig_k, other_bp.btree_id, other_extent, bucket.inode); + ret = check_extent_checksum(trans, bp->v.btree_id, orig_k, + other_bp.v->btree_id, other_extent, bp->k.p.inode); if (ret < 0) goto err; if (ret) { @@ -629,7 +557,7 @@ check_existing_bp: } printbuf_reset(&buf); - prt_printf(&buf, "duplicate extents pointing to same space on dev %llu\n ", bucket.inode); + prt_printf(&buf, "duplicate extents pointing to same space on dev %llu\n ", bp->k.p.inode); bch2_bkey_val_to_text(&buf, c, orig_k); prt_str(&buf, "\n "); bch2_bkey_val_to_text(&buf, c, other_extent); @@ -638,21 +566,15 @@ check_existing_bp: goto err; missing: printbuf_reset(&buf); - prt_printf(&buf, "missing backpointer for btree=%s l=%u ", - bch2_btree_id_str(bp.btree_id), bp.level); + prt_str(&buf, "missing backpointer\n for: "); bch2_bkey_val_to_text(&buf, c, orig_k); - prt_printf(&buf, "\n got: "); + prt_printf(&buf, "\n want: "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&bp->k_i)); + prt_printf(&buf, "\n got: "); bch2_bkey_val_to_text(&buf, c, bp_k); - struct bkey_i_backpointer n_bp_k; - bkey_backpointer_init(&n_bp_k.k_i); - n_bp_k.k.p = bucket_pos_to_bp(ca, bucket, bp.bucket_offset); - n_bp_k.v = bp; - prt_printf(&buf, "\n want: "); - bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&n_bp_k.k_i)); - if (fsck_err(trans, ptr_to_missing_backpointer, "%s", buf.buf)) - ret = bch2_bucket_backpointer_mod(trans, ca, bucket, bp, orig_k, true); + ret = bch2_bucket_backpointer_mod(trans, orig_k, bp, true); goto out; } @@ -663,31 +585,33 @@ static int check_extent_to_backpointers(struct btree_trans *trans, struct bkey_s_c k) { struct bch_fs *c = trans->c; - struct bkey_ptrs_c ptrs; + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; struct extent_ptr_decoded p; - int ret; - ptrs = bch2_bkey_ptrs_c(k); bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - struct bpos bucket_pos = POS_MIN; - struct bch_backpointer bp; - if (p.ptr.cached) continue; + if (p.ptr.dev == BCH_SB_MEMBER_INVALID) + continue; + rcu_read_lock(); struct bch_dev *ca = bch2_dev_rcu_noerror(c, p.ptr.dev); - if (ca) - bch2_extent_ptr_to_bp(c, ca, btree, level, k, p, entry, &bucket_pos, &bp); + bool check = ca && test_bit(PTR_BUCKET_NR(ca, &p.ptr), ca->bucket_backpointer_mismatches); + bool empty = ca && test_bit(PTR_BUCKET_NR(ca, &p.ptr), ca->bucket_backpointer_empty); rcu_read_unlock(); - if (!ca) - continue; + if (check || empty) { + struct bkey_i_backpointer bp; + bch2_extent_ptr_to_bp(c, btree, level, k, p, entry, &bp); - ret = check_bp_exists(trans, s, bucket_pos, bp, k); - if (ret) - return ret; + int ret = check + ? check_bp_exists(trans, s, &bp, k) + : bch2_bucket_backpointer_mod(trans, k, &bp, true); + if (ret) + return ret; + } } return 0; @@ -896,54 +820,330 @@ static int bch2_check_extents_to_backpointers_pass(struct btree_trans *trans, return 0; } +enum alloc_sector_counter { + ALLOC_dirty, + ALLOC_cached, + ALLOC_stripe, + ALLOC_SECTORS_NR +}; + +static enum alloc_sector_counter data_type_to_alloc_counter(enum bch_data_type t) +{ + switch (t) { + case BCH_DATA_btree: + case BCH_DATA_user: + return ALLOC_dirty; + case BCH_DATA_cached: + return ALLOC_cached; + case BCH_DATA_stripe: + return ALLOC_stripe; + default: + BUG(); + } +} + +static int check_bucket_backpointers_to_extents(struct btree_trans *, struct bch_dev *, struct bpos); + +static int check_bucket_backpointer_mismatch(struct btree_trans *trans, struct bkey_s_c alloc_k, + struct bkey_buf *last_flushed) +{ + struct bch_fs *c = trans->c; + struct bch_alloc_v4 a_convert; + const struct bch_alloc_v4 *a = bch2_alloc_to_v4(alloc_k, &a_convert); + bool need_commit = false; + + if (a->data_type == BCH_DATA_sb || + a->data_type == BCH_DATA_journal || + a->data_type == BCH_DATA_parity) + return 0; + + u32 sectors[ALLOC_SECTORS_NR]; + memset(sectors, 0, sizeof(sectors)); + + struct bch_dev *ca = bch2_dev_bucket_tryget_noerror(trans->c, alloc_k.k->p); + if (!ca) + return 0; + + struct btree_iter iter; + struct bkey_s_c bp_k; + int ret = 0; + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_backpointers, + bucket_pos_to_bp_start(ca, alloc_k.k->p), + bucket_pos_to_bp_end(ca, alloc_k.k->p), 0, bp_k, ret) { + if (bp_k.k->type != KEY_TYPE_backpointer) + continue; + + struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(bp_k); + + if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_backpointer_bucket_gen && + (bp.v->bucket_gen != a->gen || + bp.v->pad)) { + ret = bch2_backpointer_del(trans, bp_k.k->p); + if (ret) + break; + + need_commit = true; + continue; + } + + if (bp.v->bucket_gen != a->gen) + continue; + + sectors[data_type_to_alloc_counter(bp.v->data_type)] += bp.v->bucket_len; + }; + bch2_trans_iter_exit(trans, &iter); + if (ret) + goto err; + + if (need_commit) { + ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + } + + /* Cached pointers don't have backpointers: */ + + if (sectors[ALLOC_dirty] != a->dirty_sectors || + sectors[ALLOC_stripe] != a->stripe_sectors) { + if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_backpointer_bucket_gen) { + ret = bch2_backpointers_maybe_flush(trans, alloc_k, last_flushed); + if (ret) + goto err; + } + + if (sectors[ALLOC_dirty] > a->dirty_sectors || + sectors[ALLOC_stripe] > a->stripe_sectors) { + ret = check_bucket_backpointers_to_extents(trans, ca, alloc_k.k->p) ?: + -BCH_ERR_transaction_restart_nested; + goto err; + } + + if (!sectors[ALLOC_dirty] && + !sectors[ALLOC_stripe]) + __set_bit(alloc_k.k->p.offset, ca->bucket_backpointer_empty); + else + __set_bit(alloc_k.k->p.offset, ca->bucket_backpointer_mismatches); + } +err: + bch2_dev_put(ca); + return ret; +} + +static bool backpointer_node_has_missing(struct bch_fs *c, struct bkey_s_c k) +{ + switch (k.k->type) { + case KEY_TYPE_btree_ptr_v2: { + bool ret = false; + + rcu_read_lock(); + struct bpos pos = bkey_s_c_to_btree_ptr_v2(k).v->min_key; + while (pos.inode <= k.k->p.inode) { + if (pos.inode >= c->sb.nr_devices) + break; + + struct bch_dev *ca = bch2_dev_rcu_noerror(c, pos.inode); + if (!ca) + goto next; + + struct bpos bucket = bp_pos_to_bucket(ca, pos); + bucket.offset = find_next_bit(ca->bucket_backpointer_mismatches, + ca->mi.nbuckets, bucket.offset); + if (bucket.offset == ca->mi.nbuckets) + goto next; + + ret = bpos_le(bucket_pos_to_bp_end(ca, bucket), k.k->p); + if (ret) + break; +next: + pos = SPOS(pos.inode + 1, 0, 0); + } + rcu_read_unlock(); + + return ret; + } + case KEY_TYPE_btree_ptr: + return true; + default: + return false; + } +} + +static int btree_node_get_and_pin(struct btree_trans *trans, struct bkey_i *k, + enum btree_id btree, unsigned level) +{ + struct btree_iter iter; + bch2_trans_node_iter_init(trans, &iter, btree, k->k.p, 0, level, 0); + struct btree *b = bch2_btree_iter_peek_node(&iter); + int ret = PTR_ERR_OR_ZERO(b); + if (ret) + goto err; + + if (b) + bch2_node_pin(trans->c, b); +err: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +static int bch2_pin_backpointer_nodes_with_missing(struct btree_trans *trans, + struct bpos start, struct bpos *end) +{ + struct bch_fs *c = trans->c; + int ret = 0; + + struct bkey_buf tmp; + bch2_bkey_buf_init(&tmp); + + bch2_btree_cache_unpin(c); + + *end = SPOS_MAX; + + s64 mem_may_pin = mem_may_pin_bytes(c); + struct btree_iter iter; + bch2_trans_node_iter_init(trans, &iter, BTREE_ID_backpointers, start, + 0, 1, BTREE_ITER_prefetch); + ret = for_each_btree_key_continue(trans, iter, 0, k, ({ + if (!backpointer_node_has_missing(c, k)) + continue; + + mem_may_pin -= c->opts.btree_node_size; + if (mem_may_pin <= 0) + break; + + bch2_bkey_buf_reassemble(&tmp, c, k); + struct btree_path *path = btree_iter_path(trans, &iter); + + BUG_ON(path->level != 1); + + bch2_btree_node_prefetch(trans, path, tmp.k, path->btree_id, path->level - 1); + })); + if (ret) + return ret; + + struct bpos pinned = SPOS_MAX; + mem_may_pin = mem_may_pin_bytes(c); + bch2_trans_node_iter_init(trans, &iter, BTREE_ID_backpointers, start, + 0, 1, BTREE_ITER_prefetch); + ret = for_each_btree_key_continue(trans, iter, 0, k, ({ + if (!backpointer_node_has_missing(c, k)) + continue; + + mem_may_pin -= c->opts.btree_node_size; + if (mem_may_pin <= 0) { + *end = pinned; + break; + } + + bch2_bkey_buf_reassemble(&tmp, c, k); + struct btree_path *path = btree_iter_path(trans, &iter); + + BUG_ON(path->level != 1); + + int ret2 = btree_node_get_and_pin(trans, tmp.k, path->btree_id, path->level - 1); + + if (!ret2) + pinned = tmp.k->k.p; + + ret; + })); + if (ret) + return ret; + + return ret; +} + int bch2_check_extents_to_backpointers(struct bch_fs *c) { + int ret = 0; + + /* + * Can't allow devices to come/go/resize while we have bucket bitmaps + * allocated + */ + lockdep_assert_held(&c->state_lock); + + for_each_member_device(c, ca) { + BUG_ON(ca->bucket_backpointer_mismatches); + ca->bucket_backpointer_mismatches = kvcalloc(BITS_TO_LONGS(ca->mi.nbuckets), + sizeof(unsigned long), + GFP_KERNEL); + ca->bucket_backpointer_empty = kvcalloc(BITS_TO_LONGS(ca->mi.nbuckets), + sizeof(unsigned long), + GFP_KERNEL); + if (!ca->bucket_backpointer_mismatches || + !ca->bucket_backpointer_empty) { + bch2_dev_put(ca); + ret = -BCH_ERR_ENOMEM_backpointer_mismatches_bitmap; + goto err_free_bitmaps; + } + } + struct btree_trans *trans = bch2_trans_get(c); - struct extents_to_bp_state s = { .bucket_start = POS_MIN }; - int ret; + struct extents_to_bp_state s = { .bp_start = POS_MIN }; bch2_bkey_buf_init(&s.last_flushed); bkey_init(&s.last_flushed.k->k); + ret = for_each_btree_key(trans, iter, BTREE_ID_alloc, + POS_MIN, BTREE_ITER_prefetch, k, ({ + check_bucket_backpointer_mismatch(trans, k, &s.last_flushed); + })); + if (ret) + goto err; + + u64 nr_buckets = 0, nr_mismatches = 0, nr_empty = 0; + for_each_member_device(c, ca) { + nr_buckets += ca->mi.nbuckets; + nr_mismatches += bitmap_weight(ca->bucket_backpointer_mismatches, ca->mi.nbuckets); + nr_empty += bitmap_weight(ca->bucket_backpointer_empty, ca->mi.nbuckets); + } + + if (!nr_mismatches && !nr_empty) + goto err; + + bch_info(c, "scanning for missing backpointers in %llu/%llu buckets", + nr_mismatches + nr_empty, nr_buckets); + while (1) { - struct bbpos end; - ret = bch2_get_btree_in_memory_pos(trans, - BIT_ULL(BTREE_ID_backpointers), - BIT_ULL(BTREE_ID_backpointers), - BBPOS(BTREE_ID_backpointers, s.bucket_start), &end); + ret = bch2_pin_backpointer_nodes_with_missing(trans, s.bp_start, &s.bp_end); if (ret) break; - s.bucket_end = end.pos; - - if ( bpos_eq(s.bucket_start, POS_MIN) && - !bpos_eq(s.bucket_end, SPOS_MAX)) + if ( bpos_eq(s.bp_start, POS_MIN) && + !bpos_eq(s.bp_end, SPOS_MAX)) bch_verbose(c, "%s(): alloc info does not fit in ram, running in multiple passes with %zu nodes per pass", __func__, btree_nodes_fit_in_ram(c)); - if (!bpos_eq(s.bucket_start, POS_MIN) || - !bpos_eq(s.bucket_end, SPOS_MAX)) { + if (!bpos_eq(s.bp_start, POS_MIN) || + !bpos_eq(s.bp_end, SPOS_MAX)) { struct printbuf buf = PRINTBUF; prt_str(&buf, "check_extents_to_backpointers(): "); - bch2_bpos_to_text(&buf, s.bucket_start); + bch2_bpos_to_text(&buf, s.bp_start); prt_str(&buf, "-"); - bch2_bpos_to_text(&buf, s.bucket_end); + bch2_bpos_to_text(&buf, s.bp_end); bch_verbose(c, "%s", buf.buf); printbuf_exit(&buf); } ret = bch2_check_extents_to_backpointers_pass(trans, &s); - if (ret || bpos_eq(s.bucket_end, SPOS_MAX)) + if (ret || bpos_eq(s.bp_end, SPOS_MAX)) break; - s.bucket_start = bpos_successor(s.bucket_end); + s.bp_start = bpos_successor(s.bp_end); } +err: bch2_trans_put(trans); bch2_bkey_buf_exit(&s.last_flushed, c); - bch2_btree_cache_unpin(c); +err_free_bitmaps: + for_each_member_device(c, ca) { + kvfree(ca->bucket_backpointer_empty); + ca->bucket_backpointer_empty = NULL; + kvfree(ca->bucket_backpointer_mismatches); + ca->bucket_backpointer_mismatches = NULL; + } bch_err_fn(c, ret); return ret; @@ -959,44 +1159,43 @@ static int check_one_backpointer(struct btree_trans *trans, return 0; struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(bp_k); - struct bch_fs *c = trans->c; - struct btree_iter iter; struct bbpos pos = bp_to_bbpos(*bp.v); - struct bkey_s_c k; - struct printbuf buf = PRINTBUF; - int ret; if (bbpos_cmp(pos, start) < 0 || bbpos_cmp(pos, end) > 0) return 0; - k = bch2_backpointer_get_key(trans, &iter, bp.k->p, *bp.v, 0); - ret = bkey_err(k); + struct btree_iter iter; + struct bkey_s_c k = bch2_backpointer_get_key(trans, bp, &iter, 0, last_flushed); + int ret = bkey_err(k); if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node) return 0; if (ret) return ret; - if (!k.k) { - ret = bch2_btree_write_buffer_maybe_flush(trans, bp.s_c, last_flushed); - if (ret) - goto out; - - if (fsck_err(trans, backpointer_to_missing_ptr, - "backpointer for missing %s\n %s", - bp.v->level ? "btree node" : "extent", - (bch2_bkey_val_to_text(&buf, c, bp.s_c), buf.buf))) { - ret = bch2_btree_delete_at_buffered(trans, BTREE_ID_backpointers, bp.k->p); - goto out; - } - } -out: -fsck_err: bch2_trans_iter_exit(trans, &iter); - printbuf_exit(&buf); return ret; } +static int check_bucket_backpointers_to_extents(struct btree_trans *trans, + struct bch_dev *ca, struct bpos bucket) +{ + u32 restart_count = trans->restart_count; + struct bkey_buf last_flushed; + bch2_bkey_buf_init(&last_flushed); + bkey_init(&last_flushed.k->k); + + int ret = for_each_btree_key_max(trans, iter, BTREE_ID_backpointers, + bucket_pos_to_bp_start(ca, bucket), + bucket_pos_to_bp_end(ca, bucket), + 0, k, + check_one_backpointer(trans, BBPOS_MIN, BBPOS_MAX, k, &last_flushed) + ); + + bch2_bkey_buf_exit(&last_flushed, trans->c); + return ret ?: trans_was_restarted(trans, restart_count); +} + static int bch2_check_backpointers_to_extents_pass(struct btree_trans *trans, struct bbpos start, struct bbpos end) @@ -1009,9 +1208,8 @@ static int bch2_check_backpointers_to_extents_pass(struct btree_trans *trans, bkey_init(&last_flushed.k->k); progress_init(&progress, trans->c, BIT_ULL(BTREE_ID_backpointers)); - int ret = for_each_btree_key_commit(trans, iter, BTREE_ID_backpointers, - POS_MIN, BTREE_ITER_prefetch, k, - NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ + int ret = for_each_btree_key(trans, iter, BTREE_ID_backpointers, + POS_MIN, BTREE_ITER_prefetch, k, ({ progress_update_iter(trans, &progress, &iter, "backpointers_to_extents"); check_one_backpointer(trans, start, end, k, &last_flushed); })); diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h index 3b29fdf519dd..060dad1521ee 100644 --- a/fs/bcachefs/backpointers.h +++ b/fs/bcachefs/backpointers.h @@ -18,14 +18,14 @@ static inline u64 swab40(u64 x) ((x & 0xff00000000ULL) >> 32)); } -int bch2_backpointer_validate(struct bch_fs *, struct bkey_s_c k, enum bch_validate_flags); -void bch2_backpointer_to_text(struct printbuf *, const struct bch_backpointer *); -void bch2_backpointer_k_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); +int bch2_backpointer_validate(struct bch_fs *, struct bkey_s_c k, + struct bkey_validate_context); +void bch2_backpointer_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_backpointer_swab(struct bkey_s); #define bch2_bkey_ops_backpointer ((struct bkey_ops) { \ .key_validate = bch2_backpointer_validate, \ - .val_to_text = bch2_backpointer_k_to_text, \ + .val_to_text = bch2_backpointer_to_text, \ .swab = bch2_backpointer_swab, \ .min_val_size = 32, \ }) @@ -43,22 +43,24 @@ static inline struct bpos bp_pos_to_bucket(const struct bch_dev *ca, struct bpos return POS(bp_pos.inode, sector_to_bucket(ca, bucket_sector)); } +static inline struct bpos bp_pos_to_bucket_and_offset(const struct bch_dev *ca, struct bpos bp_pos, + u32 *bucket_offset) +{ + u64 bucket_sector = bp_pos.offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT; + + return POS(bp_pos.inode, sector_to_bucket_and_offset(ca, bucket_sector, bucket_offset)); +} + static inline bool bp_pos_to_bucket_nodev_noerror(struct bch_fs *c, struct bpos bp_pos, struct bpos *bucket) { rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu(c, bp_pos.inode); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, bp_pos.inode); if (ca) *bucket = bp_pos_to_bucket(ca, bp_pos); rcu_read_unlock(); return ca != NULL; } -static inline bool bp_pos_to_bucket_nodev(struct bch_fs *c, struct bpos bp_pos, struct bpos *bucket) -{ - return !bch2_fs_inconsistent_on(!bp_pos_to_bucket_nodev_noerror(c, bp_pos, bucket), - c, "backpointer for missing device %llu", bp_pos.inode); -} - static inline struct bpos bucket_pos_to_bp_noerror(const struct bch_dev *ca, struct bpos bucket, u64 bucket_offset) @@ -80,31 +82,35 @@ static inline struct bpos bucket_pos_to_bp(const struct bch_dev *ca, return ret; } -int bch2_bucket_backpointer_mod_nowritebuffer(struct btree_trans *, struct bch_dev *, - struct bpos bucket, struct bch_backpointer, struct bkey_s_c, bool); +static inline struct bpos bucket_pos_to_bp_start(const struct bch_dev *ca, struct bpos bucket) +{ + return bucket_pos_to_bp(ca, bucket, 0); +} + +static inline struct bpos bucket_pos_to_bp_end(const struct bch_dev *ca, struct bpos bucket) +{ + return bpos_nosnap_predecessor(bucket_pos_to_bp(ca, bpos_nosnap_successor(bucket), 0)); +} + +int bch2_bucket_backpointer_mod_nowritebuffer(struct btree_trans *, + struct bkey_s_c, + struct bkey_i_backpointer *, + bool); static inline int bch2_bucket_backpointer_mod(struct btree_trans *trans, - struct bch_dev *ca, - struct bpos bucket, - struct bch_backpointer bp, struct bkey_s_c orig_k, + struct bkey_i_backpointer *bp, bool insert) { if (unlikely(bch2_backpointers_no_use_write_buffer)) - return bch2_bucket_backpointer_mod_nowritebuffer(trans, ca, bucket, bp, orig_k, insert); - - struct bkey_i_backpointer bp_k; - - bkey_backpointer_init(&bp_k.k_i); - bp_k.k.p = bucket_pos_to_bp(ca, bucket, bp.bucket_offset); - bp_k.v = bp; + return bch2_bucket_backpointer_mod_nowritebuffer(trans, orig_k, bp, insert); if (!insert) { - bp_k.k.type = KEY_TYPE_deleted; - set_bkey_val_u64s(&bp_k.k, 0); + bp->k.type = KEY_TYPE_deleted; + set_bkey_val_u64s(&bp->k, 0); } - return bch2_trans_update_buffered(trans, BTREE_ID_backpointers, &bp_k.k_i); + return bch2_trans_update_buffered(trans, BTREE_ID_backpointers, &bp->k_i); } static inline enum bch_data_type bch2_bkey_ptr_data_type(struct bkey_s_c k, @@ -134,44 +140,29 @@ static inline enum bch_data_type bch2_bkey_ptr_data_type(struct bkey_s_c k, } } -static inline void __bch2_extent_ptr_to_bp(struct bch_fs *c, struct bch_dev *ca, +static inline void bch2_extent_ptr_to_bp(struct bch_fs *c, enum btree_id btree_id, unsigned level, struct bkey_s_c k, struct extent_ptr_decoded p, const union bch_extent_entry *entry, - struct bpos *bucket_pos, struct bch_backpointer *bp, - u64 sectors) + struct bkey_i_backpointer *bp) { - u32 bucket_offset; - *bucket_pos = PTR_BUCKET_POS_OFFSET(ca, &p.ptr, &bucket_offset); - *bp = (struct bch_backpointer) { + bkey_backpointer_init(&bp->k_i); + bp->k.p = POS(p.ptr.dev, ((u64) p.ptr.offset << MAX_EXTENT_COMPRESS_RATIO_SHIFT) + p.crc.offset); + bp->v = (struct bch_backpointer) { .btree_id = btree_id, .level = level, .data_type = bch2_bkey_ptr_data_type(k, p, entry), - .bucket_offset = ((u64) bucket_offset << MAX_EXTENT_COMPRESS_RATIO_SHIFT) + - p.crc.offset, - .bucket_len = sectors, + .bucket_gen = p.ptr.gen, + .bucket_len = ptr_disk_sectors(level ? btree_sectors(c) : k.k->size, p), .pos = k.k->p, }; } -static inline void bch2_extent_ptr_to_bp(struct bch_fs *c, struct bch_dev *ca, - enum btree_id btree_id, unsigned level, - struct bkey_s_c k, struct extent_ptr_decoded p, - const union bch_extent_entry *entry, - struct bpos *bucket_pos, struct bch_backpointer *bp) -{ - u64 sectors = ptr_disk_sectors(level ? btree_sectors(c) : k.k->size, p); - - __bch2_extent_ptr_to_bp(c, ca, btree_id, level, k, p, entry, bucket_pos, bp, sectors); -} - -int bch2_get_next_backpointer(struct btree_trans *, struct bch_dev *ca, struct bpos, int, - struct bpos *, struct bch_backpointer *, unsigned); -struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *, struct btree_iter *, - struct bpos, struct bch_backpointer, - unsigned); -struct btree *bch2_backpointer_get_node(struct btree_trans *, struct btree_iter *, - struct bpos, struct bch_backpointer); +struct bkey_buf; +struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *, struct bkey_s_c_backpointer, + struct btree_iter *, unsigned, struct bkey_buf *); +struct btree *bch2_backpointer_get_node(struct btree_trans *, struct bkey_s_c_backpointer, + struct btree_iter *, struct bkey_buf *); int bch2_check_btree_backpointers(struct bch_fs *); int bch2_check_extents_to_backpointers(struct bch_fs *); diff --git a/fs/bcachefs/bbpos.h b/fs/bcachefs/bbpos.h index be2edced5213..63abe17f35ea 100644 --- a/fs/bcachefs/bbpos.h +++ b/fs/bcachefs/bbpos.h @@ -29,7 +29,7 @@ static inline struct bbpos bbpos_successor(struct bbpos pos) static inline void bch2_bbpos_to_text(struct printbuf *out, struct bbpos pos) { - prt_str(out, bch2_btree_id_str(pos.btree)); + bch2_btree_id_to_text(out, pos.btree); prt_char(out, ':'); bch2_bpos_to_text(out, pos.pos); } diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index e94a83b8113e..161cf2f05d2a 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -205,6 +205,7 @@ #include #include "bcachefs_format.h" +#include "btree_journal_iter_types.h" #include "disk_accounting_types.h" #include "errcode.h" #include "fifo.h" @@ -293,6 +294,8 @@ do { \ #define bch_info(c, fmt, ...) \ bch2_print(c, KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__) +#define bch_info_ratelimited(c, fmt, ...) \ + bch2_print_ratelimited(c, KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_notice(c, fmt, ...) \ bch2_print(c, KERN_NOTICE bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_warn(c, fmt, ...) \ @@ -352,6 +355,12 @@ do { \ bch_info(c, fmt, ##__VA_ARGS__); \ } while (0) +#define bch_verbose_ratelimited(c, fmt, ...) \ +do { \ + if ((c)->opts.verbose) \ + bch_info_ratelimited(c, fmt, ##__VA_ARGS__); \ +} while (0) + #define pr_verbose_init(opts, fmt, ...) \ do { \ if (opt_get(opts, verbose)) \ @@ -538,20 +547,20 @@ struct bch_dev { /* * Buckets: - * Per-bucket arrays are protected by c->mark_lock, bucket_lock and - * gc_gens_lock, for device resize - holding any is sufficient for - * access: Or rcu_read_lock(), but only for dev_ptr_stale(): + * Per-bucket arrays are protected by either rcu_read_lock or + * state_lock, for device resize. */ GENRADIX(struct bucket) buckets_gc; struct bucket_gens __rcu *bucket_gens; u8 *oldest_gen; unsigned long *buckets_nouse; - struct rw_semaphore bucket_lock; + + unsigned long *bucket_backpointer_mismatches; + unsigned long *bucket_backpointer_empty; struct bch_dev_usage __percpu *usage; /* Allocator: */ - u64 new_fs_bucket_idx; u64 alloc_cursor[3]; unsigned nr_open_buckets; @@ -606,6 +615,7 @@ struct bch_dev { x(going_ro) \ x(write_disable_complete) \ x(clean_shutdown) \ + x(recovery_running) \ x(fsck_running) \ x(initial_gc_unfixed) \ x(need_delete_dead_snapshots) \ @@ -650,28 +660,6 @@ struct journal_seq_blacklist_table { } entries[]; }; -struct journal_keys { - /* must match layout in darray_types.h */ - size_t nr, size; - struct journal_key { - u64 journal_seq; - u32 journal_offset; - enum btree_id btree_id:8; - unsigned level:8; - bool allocated; - bool overwritten; - struct bkey_i *k; - } *data; - /* - * Gap buffer: instead of all the empty space in the array being at the - * end of the buffer - from @nr to @size - the empty space is at @gap. - * This means that sequential insertions are O(n) instead of O(n^2). - */ - size_t gap; - atomic_t ref; - bool initial_ref_held; -}; - struct btree_trans_buf { struct btree_trans *trans; }; @@ -680,6 +668,7 @@ struct btree_trans_buf { ((subvol_inum) { BCACHEFS_ROOT_SUBVOL, BCACHEFS_ROOT_INO }) #define BCH_WRITE_REFS() \ + x(journal) \ x(trans) \ x(write) \ x(promote) \ @@ -692,6 +681,7 @@ struct btree_trans_buf { x(dio_write) \ x(discard) \ x(discard_fast) \ + x(check_discard_freespace_key) \ x(invalidate) \ x(delete_dead_snapshots) \ x(gc_gens) \ @@ -734,6 +724,12 @@ struct bch_fs { #else struct percpu_ref writes; #endif + /* + * Certain operations are only allowed in single threaded mode, during + * recovery, and we want to assert that this is the case: + */ + struct task_struct *recovery_task; + /* * Analagous to c->writes, for asynchronous ops that don't necessarily * need fs to be read-write @@ -764,6 +760,8 @@ struct bch_fs { __uuid_t user_uuid; u16 version; + u16 version_incompat; + u16 version_incompat_allowed; u16 version_min; u16 version_upgrade_complete; @@ -834,9 +832,10 @@ struct bch_fs { struct work_struct btree_interior_update_work; struct workqueue_struct *btree_node_rewrite_worker; - - struct list_head pending_node_rewrites; - struct mutex pending_node_rewrites_lock; + struct list_head btree_node_rewrites; + struct list_head btree_node_rewrites_pending; + spinlock_t btree_node_rewrites_lock; + struct closure_waitlist btree_node_rewrites_wait; /* btree_io.c: */ spinlock_t btree_write_error_lock; @@ -967,8 +966,7 @@ struct bch_fs { struct rhashtable promote_table; mempool_t compression_bounce[2]; - mempool_t compress_workspace[BCH_COMPRESSION_TYPE_NR]; - mempool_t decompress_workspace; + mempool_t compress_workspace[BCH_COMPRESSION_OPT_NR]; size_t zstd_workspace_size; struct crypto_shash *sha256; @@ -1027,6 +1025,7 @@ struct bch_fs { struct list_head vfs_inodes_list; struct mutex vfs_inodes_lock; struct rhashtable vfs_inodes_table; + struct rhltable vfs_inodes_by_inum_table; /* VFS IO PATH - fs-io.c */ struct bio_set writepage_bioset; @@ -1048,10 +1047,12 @@ struct bch_fs { * for signaling to the toplevel code which pass we want to run now. */ enum bch_recovery_pass curr_recovery_pass; + enum bch_recovery_pass next_recovery_pass; /* bitmask of recovery passes that we actually ran */ u64 recovery_passes_complete; /* never rewinds version of curr_recovery_pass */ enum bch_recovery_pass recovery_pass_done; + spinlock_t recovery_pass_lock; struct semaphore online_fsck_mutex; /* DEBUG JUNK */ @@ -1062,9 +1063,6 @@ struct bch_fs { struct btree_node *verify_ondisk; struct mutex verify_lock; - u64 *unused_inode_hints; - unsigned inode_shard_bits; - /* * A btree node on disk could have too many bsets for an iterator to fit * on the stack - have to dynamically allocate them @@ -1086,8 +1084,6 @@ struct bch_fs { u64 counters_on_mount[BCH_COUNTER_NR]; u64 __percpu *counters; - unsigned copy_gc_enabled:1; - struct bch2_time_stats times[BCH_TIME_STAT_NR]; struct btree_transaction_stats btree_transaction_stats[BCH_TRANSACTIONS_NR]; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 5004f6ba997c..f70f0108401f 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -418,7 +418,8 @@ static inline void bkey_init(struct bkey *k) x(snapshot_tree, 31) \ x(logged_op_truncate, 32) \ x(logged_op_finsert, 33) \ - x(accounting, 34) + x(accounting, 34) \ + x(inode_alloc_cursor, 35) enum bch_bkey_type { #define x(name, nr) KEY_TYPE_##name = nr, @@ -463,7 +464,8 @@ struct bch_backpointer { __u8 btree_id; __u8 level; __u8 data_type; - __u64 bucket_offset:40; + __u8 bucket_gen; + __u32 pad; __u32 bucket_len; struct bpos pos; } __packed __aligned(8); @@ -499,8 +501,6 @@ struct bch_sb_field { #include "disk_groups_format.h" #include "extents_format.h" #include "ec_format.h" -#include "dirent_format.h" -#include "disk_groups_format.h" #include "inode_format.h" #include "journal_seq_blacklist_format.h" #include "logged_ops_format.h" @@ -679,7 +679,14 @@ struct bch_sb_field_ext { x(disk_accounting_v3, BCH_VERSION(1, 10)) \ x(disk_accounting_inum, BCH_VERSION(1, 11)) \ x(rebalance_work_acct_fix, BCH_VERSION(1, 12)) \ - x(inode_has_child_snapshots, BCH_VERSION(1, 13)) + x(inode_has_child_snapshots, BCH_VERSION(1, 13)) \ + x(backpointer_bucket_gen, BCH_VERSION(1, 14)) \ + x(disk_accounting_big_endian, BCH_VERSION(1, 15)) \ + x(reflink_p_may_update_opts, BCH_VERSION(1, 16)) \ + x(inode_depth, BCH_VERSION(1, 17)) \ + x(persistent_inode_cursors, BCH_VERSION(1, 18)) \ + x(autofix_errors, BCH_VERSION(1, 19)) \ + x(directory_size, BCH_VERSION(1, 20)) enum bcachefs_metadata_version { bcachefs_metadata_version_min = 9, @@ -844,6 +851,10 @@ LE64_BITMASK(BCH_SB_VERSION_UPGRADE_COMPLETE, struct bch_sb, flags[5], 0, 16); LE64_BITMASK(BCH_SB_ALLOCATOR_STUCK_TIMEOUT, struct bch_sb, flags[5], 16, 32); +LE64_BITMASK(BCH_SB_VERSION_INCOMPAT, struct bch_sb, flags[5], 32, 48); +LE64_BITMASK(BCH_SB_VERSION_INCOMPAT_ALLOWED, + struct bch_sb, flags[5], 48, 64); +LE64_BITMASK(BCH_SB_SHARD_INUMS_NBITS, struct bch_sb, flags[6], 0, 4); static inline __u64 BCH_SB_COMPRESSION_TYPE(const struct bch_sb *sb) { @@ -896,21 +907,22 @@ static inline void SET_BCH_SB_BACKGROUND_COMPRESSION_TYPE(struct bch_sb *sb, __u x(new_varint, 15) \ x(journal_no_flush, 16) \ x(alloc_v2, 17) \ - x(extents_across_btree_nodes, 18) + x(extents_across_btree_nodes, 18) \ + x(incompat_version_field, 19) #define BCH_SB_FEATURES_ALWAYS \ - ((1ULL << BCH_FEATURE_new_extent_overwrite)| \ - (1ULL << BCH_FEATURE_extents_above_btree_updates)|\ - (1ULL << BCH_FEATURE_btree_updates_journalled)|\ - (1ULL << BCH_FEATURE_alloc_v2)|\ - (1ULL << BCH_FEATURE_extents_across_btree_nodes)) + (BIT_ULL(BCH_FEATURE_new_extent_overwrite)| \ + BIT_ULL(BCH_FEATURE_extents_above_btree_updates)|\ + BIT_ULL(BCH_FEATURE_btree_updates_journalled)|\ + BIT_ULL(BCH_FEATURE_alloc_v2)|\ + BIT_ULL(BCH_FEATURE_extents_across_btree_nodes)) #define BCH_SB_FEATURES_ALL \ (BCH_SB_FEATURES_ALWAYS| \ - (1ULL << BCH_FEATURE_new_siphash)| \ - (1ULL << BCH_FEATURE_btree_ptr_v2)| \ - (1ULL << BCH_FEATURE_new_varint)| \ - (1ULL << BCH_FEATURE_journal_no_flush)) + BIT_ULL(BCH_FEATURE_new_siphash)| \ + BIT_ULL(BCH_FEATURE_btree_ptr_v2)| \ + BIT_ULL(BCH_FEATURE_new_varint)| \ + BIT_ULL(BCH_FEATURE_journal_no_flush)) enum bch_sb_feature { #define x(f, n) BCH_FEATURE_##f, @@ -1032,7 +1044,7 @@ static inline _Bool bch2_csum_type_is_encryption(enum bch_csum_type type) x(crc64, 2) \ x(xxhash, 3) -enum bch_csum_opts { +enum bch_csum_opt { #define x(t, n) BCH_CSUM_OPT_##t = n, BCH_CSUM_OPTS() #undef x @@ -1221,6 +1233,15 @@ struct jset_entry_log { u8 d[]; } __packed __aligned(8); +static inline unsigned jset_entry_log_msg_bytes(struct jset_entry_log *l) +{ + unsigned b = vstruct_bytes(&l->entry) - offsetof(struct jset_entry_log, d); + + while (b && !l->d[b - 1]) + --b; + return b; +} + struct jset_entry_datetime { struct jset_entry entry; __le64 seconds; @@ -1268,14 +1289,18 @@ LE32_BITMASK(JSET_NO_FLUSH, struct jset, flags, 5, 6); /* Btree: */ enum btree_id_flags { - BTREE_ID_EXTENTS = BIT(0), - BTREE_ID_SNAPSHOTS = BIT(1), - BTREE_ID_SNAPSHOT_FIELD = BIT(2), - BTREE_ID_DATA = BIT(3), + BTREE_IS_extents = BIT(0), + BTREE_IS_snapshots = BIT(1), + BTREE_IS_snapshot_field = BIT(2), + BTREE_IS_data = BIT(3), + BTREE_IS_write_buffer = BIT(4), }; #define BCH_BTREE_IDS() \ - x(extents, 0, BTREE_ID_EXTENTS|BTREE_ID_SNAPSHOTS|BTREE_ID_DATA,\ + x(extents, 0, \ + BTREE_IS_extents| \ + BTREE_IS_snapshots| \ + BTREE_IS_data, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_error)| \ BIT_ULL(KEY_TYPE_cookie)| \ @@ -1283,17 +1308,20 @@ enum btree_id_flags { BIT_ULL(KEY_TYPE_reservation)| \ BIT_ULL(KEY_TYPE_reflink_p)| \ BIT_ULL(KEY_TYPE_inline_data)) \ - x(inodes, 1, BTREE_ID_SNAPSHOTS, \ + x(inodes, 1, \ + BTREE_IS_snapshots, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_inode)| \ BIT_ULL(KEY_TYPE_inode_v2)| \ BIT_ULL(KEY_TYPE_inode_v3)| \ BIT_ULL(KEY_TYPE_inode_generation)) \ - x(dirents, 2, BTREE_ID_SNAPSHOTS, \ + x(dirents, 2, \ + BTREE_IS_snapshots, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_hash_whiteout)| \ BIT_ULL(KEY_TYPE_dirent)) \ - x(xattrs, 3, BTREE_ID_SNAPSHOTS, \ + x(xattrs, 3, \ + BTREE_IS_snapshots, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_cookie)| \ BIT_ULL(KEY_TYPE_hash_whiteout)| \ @@ -1307,7 +1335,9 @@ enum btree_id_flags { BIT_ULL(KEY_TYPE_quota)) \ x(stripes, 6, 0, \ BIT_ULL(KEY_TYPE_stripe)) \ - x(reflink, 7, BTREE_ID_EXTENTS|BTREE_ID_DATA, \ + x(reflink, 7, \ + BTREE_IS_extents| \ + BTREE_IS_data, \ BIT_ULL(KEY_TYPE_reflink_v)| \ BIT_ULL(KEY_TYPE_indirect_inline_data)| \ BIT_ULL(KEY_TYPE_error)) \ @@ -1315,28 +1345,38 @@ enum btree_id_flags { BIT_ULL(KEY_TYPE_subvolume)) \ x(snapshots, 9, 0, \ BIT_ULL(KEY_TYPE_snapshot)) \ - x(lru, 10, 0, \ + x(lru, 10, \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_set)) \ - x(freespace, 11, BTREE_ID_EXTENTS, \ + x(freespace, 11, \ + BTREE_IS_extents, \ BIT_ULL(KEY_TYPE_set)) \ x(need_discard, 12, 0, \ BIT_ULL(KEY_TYPE_set)) \ - x(backpointers, 13, 0, \ + x(backpointers, 13, \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_backpointer)) \ x(bucket_gens, 14, 0, \ BIT_ULL(KEY_TYPE_bucket_gens)) \ x(snapshot_trees, 15, 0, \ BIT_ULL(KEY_TYPE_snapshot_tree)) \ - x(deleted_inodes, 16, BTREE_ID_SNAPSHOT_FIELD, \ + x(deleted_inodes, 16, \ + BTREE_IS_snapshot_field| \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_set)) \ x(logged_ops, 17, 0, \ BIT_ULL(KEY_TYPE_logged_op_truncate)| \ - BIT_ULL(KEY_TYPE_logged_op_finsert)) \ - x(rebalance_work, 18, BTREE_ID_SNAPSHOT_FIELD, \ + BIT_ULL(KEY_TYPE_logged_op_finsert)| \ + BIT_ULL(KEY_TYPE_inode_alloc_cursor)) \ + x(rebalance_work, 18, \ + BTREE_IS_snapshot_field| \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_set)|BIT_ULL(KEY_TYPE_cookie)) \ x(subvolume_children, 19, 0, \ BIT_ULL(KEY_TYPE_set)) \ - x(accounting, 20, BTREE_ID_SNAPSHOT_FIELD, \ + x(accounting, 20, \ + BTREE_IS_snapshot_field| \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_accounting)) \ enum btree_id { @@ -1361,6 +1401,8 @@ static inline bool btree_id_is_alloc(enum btree_id id) case BTREE_ID_need_discard: case BTREE_ID_freespace: case BTREE_ID_bucket_gens: + case BTREE_ID_lru: + case BTREE_ID_accounting: return true; default: return false; diff --git a/fs/bcachefs/bkey.h b/fs/bcachefs/bkey.h index 41df24a53d97..054e2d5e8448 100644 --- a/fs/bcachefs/bkey.h +++ b/fs/bcachefs/bkey.h @@ -9,13 +9,6 @@ #include "util.h" #include "vstructs.h" -enum bch_validate_flags { - BCH_VALIDATE_write = BIT(0), - BCH_VALIDATE_commit = BIT(1), - BCH_VALIDATE_journal = BIT(2), - BCH_VALIDATE_silent = BIT(3), -}; - #if 0 /* diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c index e7ac227ba7e8..15c93576b5c2 100644 --- a/fs/bcachefs/bkey_methods.c +++ b/fs/bcachefs/bkey_methods.c @@ -28,7 +28,7 @@ const char * const bch2_bkey_types[] = { }; static int deleted_key_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return 0; } @@ -42,7 +42,7 @@ static int deleted_key_validate(struct bch_fs *c, struct bkey_s_c k, }) static int empty_val_key_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -59,7 +59,7 @@ fsck_err: }) static int key_type_cookie_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return 0; } @@ -83,7 +83,7 @@ static void key_type_cookie_to_text(struct printbuf *out, struct bch_fs *c, }) static int key_type_inline_data_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return 0; } @@ -124,7 +124,7 @@ const struct bkey_ops bch2_bkey_null_ops = { }; int bch2_bkey_val_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { if (test_bit(BCH_FS_no_invalid_checks, &c->flags)) return 0; @@ -140,7 +140,7 @@ int bch2_bkey_val_validate(struct bch_fs *c, struct bkey_s_c k, if (!ops->key_validate) return 0; - ret = ops->key_validate(c, k, flags); + ret = ops->key_validate(c, k, from); fsck_err: return ret; } @@ -161,9 +161,10 @@ const char *bch2_btree_node_type_str(enum btree_node_type type) } int __bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k, - enum btree_node_type type, - enum bch_validate_flags flags) + struct bkey_validate_context from) { + enum btree_node_type type = __btree_node_type(from.level, from.btree); + if (test_bit(BCH_FS_no_invalid_checks, &c->flags)) return 0; @@ -177,7 +178,7 @@ int __bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k, return 0; bkey_fsck_err_on(k.k->type < KEY_TYPE_MAX && - (type == BKEY_TYPE_btree || (flags & BCH_VALIDATE_commit)) && + (type == BKEY_TYPE_btree || (from.flags & BCH_VALIDATE_commit)) && !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)), c, bkey_invalid_type_for_btree, "invalid key type for btree %s (%s)", @@ -228,15 +229,15 @@ fsck_err: } int bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k, - enum btree_node_type type, - enum bch_validate_flags flags) + struct bkey_validate_context from) { - return __bch2_bkey_validate(c, k, type, flags) ?: - bch2_bkey_val_validate(c, k, flags); + return __bch2_bkey_validate(c, k, from) ?: + bch2_bkey_val_validate(c, k, from); } int bch2_bkey_in_btree_node(struct bch_fs *c, struct btree *b, - struct bkey_s_c k, enum bch_validate_flags flags) + struct bkey_s_c k, + struct bkey_validate_context from) { int ret = 0; diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h index 018fb72e32d3..bf34111cdf00 100644 --- a/fs/bcachefs/bkey_methods.h +++ b/fs/bcachefs/bkey_methods.h @@ -22,7 +22,7 @@ extern const struct bkey_ops bch2_bkey_null_ops; */ struct bkey_ops { int (*key_validate)(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags); + struct bkey_validate_context from); void (*val_to_text)(struct printbuf *, struct bch_fs *, struct bkey_s_c); void (*swab)(struct bkey_s); @@ -48,13 +48,14 @@ static inline const struct bkey_ops *bch2_bkey_type_ops(enum bch_bkey_type type) : &bch2_bkey_null_ops; } -int bch2_bkey_val_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); -int __bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, enum btree_node_type, - enum bch_validate_flags); -int bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, enum btree_node_type, - enum bch_validate_flags); +int bch2_bkey_val_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int __bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); int bch2_bkey_in_btree_node(struct bch_fs *, struct btree *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context from); void bch2_bpos_to_text(struct printbuf *, struct bpos); void bch2_bkey_to_text(struct printbuf *, const struct bkey *); diff --git a/fs/bcachefs/bkey_types.h b/fs/bcachefs/bkey_types.h index c9ae9e42b385..b4f328f9853c 100644 --- a/fs/bcachefs/bkey_types.h +++ b/fs/bcachefs/bkey_types.h @@ -210,4 +210,32 @@ static inline struct bkey_i_##name *bkey_##name##_init(struct bkey_i *_k)\ BCH_BKEY_TYPES(); #undef x +enum bch_validate_flags { + BCH_VALIDATE_write = BIT(0), + BCH_VALIDATE_commit = BIT(1), + BCH_VALIDATE_silent = BIT(2), +}; + +#define BKEY_VALIDATE_CONTEXTS() \ + x(unknown) \ + x(superblock) \ + x(journal) \ + x(btree_root) \ + x(btree_node) \ + x(commit) + +struct bkey_validate_context { + enum { +#define x(n) BKEY_VALIDATE_##n, + BKEY_VALIDATE_CONTEXTS() +#undef x + } from:8; + enum bch_validate_flags flags:8; + u8 level; + enum btree_id btree; + bool root:1; + unsigned journal_offset; + u64 journal_seq; +}; + #endif /* _BCACHEFS_BKEY_TYPES_H */ diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 7123019ab3bc..ca755e8d1a37 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -24,7 +24,10 @@ do { \ } while (0) const char * const bch2_btree_node_flags[] = { -#define x(f) #f, + "typebit", + "typebit", + "typebit", +#define x(f) [BTREE_NODE_##f] = #f, BTREE_FLAGS() #undef x NULL @@ -222,7 +225,6 @@ void bch2_node_pin(struct bch_fs *c, struct btree *b) struct btree_cache *bc = &c->btree_cache; mutex_lock(&bc->lock); - BUG_ON(!__btree_node_pinned(bc, b)); if (b != btree_node_root(c, b) && !btree_node_pinned(b)) { set_btree_node_pinned(b); list_move(&b->list, &bc->live[1].list); @@ -326,7 +328,7 @@ void bch2_btree_node_update_key_early(struct btree_trans *trans, if (!IS_ERR_OR_NULL(b)) { mutex_lock(&c->btree_cache.lock); - bch2_btree_node_hash_remove(&c->btree_cache, b); + __bch2_btree_node_hash_remove(&c->btree_cache, b); bkey_copy(&b->key, new); ret = __bch2_btree_node_hash_insert(&c->btree_cache, b); @@ -1004,16 +1006,14 @@ static noinline void btree_bad_header(struct bch_fs *c, struct btree *b) return; prt_printf(&buf, - "btree node header doesn't match ptr\n" - "btree %s level %u\n" - "ptr: ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + "btree node header doesn't match ptr: "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, "\nptr: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); - prt_printf(&buf, "\nheader: btree %s level %llu\n" - "min ", - bch2_btree_id_str(BTREE_NODE_ID(b->data)), - BTREE_NODE_LEVEL(b->data)); + prt_str(&buf, "\nheader: "); + bch2_btree_id_level_to_text(&buf, BTREE_NODE_ID(b->data), BTREE_NODE_LEVEL(b->data)); + prt_str(&buf, "\nmin "); bch2_bpos_to_text(&buf, b->data->min_key); prt_printf(&buf, "\nmax "); @@ -1133,7 +1133,7 @@ retry: if (unlikely(btree_node_read_error(b))) { six_unlock_type(&b->c.lock, lock_type); - return ERR_PTR(-BCH_ERR_btree_node_read_error); + return ERR_PTR(-BCH_ERR_btree_node_read_err_cached); } EBUG_ON(b->c.btree_id != path->btree_id); @@ -1223,7 +1223,7 @@ struct btree *bch2_btree_node_get(struct btree_trans *trans, struct btree_path * if (unlikely(btree_node_read_error(b))) { six_unlock_type(&b->c.lock, lock_type); - return ERR_PTR(-BCH_ERR_btree_node_read_error); + return ERR_PTR(-BCH_ERR_btree_node_read_err_cached); } EBUG_ON(b->c.btree_id != path->btree_id); @@ -1305,7 +1305,7 @@ lock_node: if (unlikely(btree_node_read_error(b))) { six_unlock_read(&b->c.lock); - b = ERR_PTR(-BCH_ERR_btree_node_read_error); + b = ERR_PTR(-BCH_ERR_btree_node_read_err_cached); goto out; } @@ -1398,13 +1398,31 @@ void bch2_btree_id_to_text(struct printbuf *out, enum btree_id btree) prt_printf(out, "(unknown btree %u)", btree); } +void bch2_btree_id_level_to_text(struct printbuf *out, enum btree_id btree, unsigned level) +{ + prt_str(out, "btree="); + bch2_btree_id_to_text(out, btree); + prt_printf(out, " level=%u", level); +} + +void __bch2_btree_pos_to_text(struct printbuf *out, struct bch_fs *c, + enum btree_id btree, unsigned level, struct bkey_s_c k) +{ + bch2_btree_id_to_text(out, btree); + prt_printf(out, " level %u/", level); + struct btree_root *r = bch2_btree_id_root(c, btree); + if (r) + prt_printf(out, "%u", r->level); + else + prt_printf(out, "(unknown)"); + prt_printf(out, "\n "); + + bch2_bkey_val_to_text(out, c, k); +} + void bch2_btree_pos_to_text(struct printbuf *out, struct bch_fs *c, const struct btree *b) { - prt_printf(out, "%s level %u/%u\n ", - bch2_btree_id_str(b->c.btree_id), - b->c.level, - bch2_btree_id_root(c, b->c.btree_id)->level); - bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(&b->key)); + __bch2_btree_pos_to_text(out, c, b->c.btree_id, b->c.level, bkey_i_to_s_c(&b->key)); } void bch2_btree_node_to_text(struct printbuf *out, struct bch_fs *c, const struct btree *b) @@ -1478,8 +1496,12 @@ void bch2_btree_cache_to_text(struct printbuf *out, const struct btree_cache *bc prt_printf(out, "cannibalize lock:\t%p\n", bc->alloc_lock); prt_newline(out); - for (unsigned i = 0; i < ARRAY_SIZE(bc->nr_by_btree); i++) - prt_btree_cache_line(out, c, bch2_btree_id_str(i), bc->nr_by_btree[i]); + for (unsigned i = 0; i < ARRAY_SIZE(bc->nr_by_btree); i++) { + bch2_btree_id_to_text(out, i); + prt_printf(out, "\t"); + prt_human_readable_u64(out, bc->nr_by_btree[i] * c->opts.btree_node_size); + prt_printf(out, " (%zu)\n", bc->nr_by_btree[i]); + } prt_newline(out); prt_printf(out, "freed:\t%zu\n", bc->nr_freed); diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h index 66e86d1a178d..ca3c1b145330 100644 --- a/fs/bcachefs/btree_cache.h +++ b/fs/bcachefs/btree_cache.h @@ -128,19 +128,27 @@ static inline struct btree_root *bch2_btree_id_root(struct bch_fs *c, unsigned i } else { unsigned idx = id - BTREE_ID_NR; - EBUG_ON(idx >= c->btree_roots_extra.nr); + /* This can happen when we're called from btree_node_scan */ + if (idx >= c->btree_roots_extra.nr) + return NULL; + return &c->btree_roots_extra.data[idx]; } } static inline struct btree *btree_node_root(struct bch_fs *c, struct btree *b) { - return bch2_btree_id_root(c, b->c.btree_id)->b; + struct btree_root *r = bch2_btree_id_root(c, b->c.btree_id); + + return r ? r->b : NULL; } -const char *bch2_btree_id_str(enum btree_id); +const char *bch2_btree_id_str(enum btree_id); /* avoid */ void bch2_btree_id_to_text(struct printbuf *, enum btree_id); +void bch2_btree_id_level_to_text(struct printbuf *, enum btree_id, unsigned); +void __bch2_btree_pos_to_text(struct printbuf *, struct bch_fs *, + enum btree_id, unsigned, struct bkey_s_c); void bch2_btree_pos_to_text(struct printbuf *, struct bch_fs *, const struct btree *); void bch2_btree_node_to_text(struct printbuf *, struct bch_fs *, const struct btree *); void bch2_btree_cache_to_text(struct printbuf *, const struct btree_cache *); diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index 81dcf9e512c0..dd1d9b74076e 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -29,6 +29,7 @@ #include "move.h" #include "recovery_passes.h" #include "reflink.h" +#include "recovery.h" #include "replicas.h" #include "super-io.h" #include "trace.h" @@ -56,8 +57,8 @@ void bch2_gc_pos_to_text(struct printbuf *out, struct gc_pos *p) { prt_str(out, bch2_gc_phase_strs[p->phase]); prt_char(out, ' '); - bch2_btree_id_to_text(out, p->btree); - prt_printf(out, " l=%u ", p->level); + bch2_btree_id_level_to_text(out, p->btree, p->level); + prt_char(out, ' '); bch2_bpos_to_text(out, p->pos); } @@ -209,8 +210,9 @@ static int btree_check_node_boundaries(struct btree_trans *trans, struct btree * if (bpos_eq(expected_start, cur->data->min_key)) return 0; - prt_printf(&buf, " at btree %s level %u:\n parent: ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_printf(&buf, " at "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_printf(&buf, ":\n parent: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); if (prev) { @@ -277,8 +279,9 @@ static int btree_repair_node_end(struct btree_trans *trans, struct btree *b, if (bpos_eq(child->key.k.p, b->key.k.p)) return 0; - prt_printf(&buf, "at btree %s level %u:\n parent: ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_printf(&buf, " at "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_printf(&buf, ":\n parent: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n child: "); @@ -341,14 +344,14 @@ again: ret = PTR_ERR_OR_ZERO(cur); printbuf_reset(&buf); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level - 1); + prt_char(&buf, ' '); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(cur_k.k)); if (mustfix_fsck_err_on(bch2_err_matches(ret, EIO), - trans, btree_node_unreadable, - "Topology repair: unreadable btree node at btree %s level %u:\n" + trans, btree_node_read_error, + "Topology repair: unreadable btree node at\n" " %s", - bch2_btree_id_str(b->c.btree_id), - b->c.level - 1, buf.buf)) { bch2_btree_node_evict(trans, cur_k.k); cur = NULL; @@ -357,11 +360,9 @@ again: if (ret) break; - if (!btree_id_is_alloc(b->c.btree_id)) { - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); - if (ret) - break; - } + ret = bch2_btree_lost_data(c, b->c.btree_id); + if (ret) + break; continue; } @@ -370,7 +371,7 @@ again: break; if (bch2_btree_node_is_stale(c, cur)) { - bch_info(c, "btree node %s older than nodes found by scanning", buf.buf); + bch_info(c, "btree node older than nodes found by scanning\n %s", buf.buf); six_unlock_read(&cur->c.lock); bch2_btree_node_evict(trans, cur_k.k); ret = bch2_journal_key_delete(c, b->c.btree_id, @@ -478,14 +479,13 @@ again: } printbuf_reset(&buf); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); if (mustfix_fsck_err_on(!have_child, trans, btree_node_topology_interior_node_empty, - "empty interior btree node at btree %s level %u\n" - " %s", - bch2_btree_id_str(b->c.btree_id), - b->c.level, buf.buf)) + "empty interior btree node at %s", buf.buf)) ret = DROP_THIS_NODE; err: fsck_err: @@ -511,6 +511,7 @@ int bch2_check_topology(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); struct bpos pulled_from_scan = POS_MIN; + struct printbuf buf = PRINTBUF; int ret = 0; bch2_trans_srcu_unlock(trans); @@ -519,19 +520,22 @@ int bch2_check_topology(struct bch_fs *c) struct btree_root *r = bch2_btree_id_root(c, i); bool reconstructed_root = false; + printbuf_reset(&buf); + bch2_btree_id_to_text(&buf, i); + if (r->error) { - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); + ret = bch2_btree_lost_data(c, i); if (ret) break; reconstruct_root: - bch_info(c, "btree root %s unreadable, must recover from scan", bch2_btree_id_str(i)); + bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf); r->alive = false; r->error = 0; if (!bch2_btree_has_scanned_nodes(c, i)) { mustfix_fsck_err(trans, btree_root_unreadable_and_scan_found_nothing, - "no nodes found for btree %s, continue?", bch2_btree_id_str(i)); + "no nodes found for btree %s, continue?", buf.buf); bch2_btree_root_alloc_fake_trans(trans, i, 0); } else { bch2_btree_root_alloc_fake_trans(trans, i, 1); @@ -560,13 +564,14 @@ reconstruct_root: if (!reconstructed_root) goto reconstruct_root; - bch_err(c, "empty btree root %s", bch2_btree_id_str(i)); + bch_err(c, "empty btree root %s", buf.buf); bch2_btree_root_alloc_fake_trans(trans, i, 0); r->alive = false; ret = 0; } } fsck_err: + printbuf_exit(&buf); bch2_trans_put(trans); return ret; } @@ -713,6 +718,7 @@ static int bch2_gc_btrees(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); enum btree_id ids[BTREE_ID_NR]; + struct printbuf buf = PRINTBUF; unsigned i; int ret = 0; @@ -727,14 +733,9 @@ static int bch2_gc_btrees(struct bch_fs *c) continue; ret = bch2_gc_btree(trans, btree, true); - - if (mustfix_fsck_err_on(bch2_err_matches(ret, EIO), - trans, btree_node_read_error, - "btree node read error for %s", - bch2_btree_id_str(btree))) - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology); } -fsck_err: + + printbuf_exit(&buf); bch2_trans_put(trans); bch_err_fn(c, ret); return ret; @@ -802,7 +803,6 @@ static int bch2_alloc_write_key(struct btree_trans *trans, old = bch2_alloc_to_v4(k, &old_convert); gc = new = *old; - percpu_down_read(&c->mark_lock); __bucket_m_to_alloc(&gc, *gc_bucket(ca, iter->pos.offset)); old_gc = gc; @@ -813,7 +813,6 @@ static int bch2_alloc_write_key(struct btree_trans *trans, gc.data_type = old->data_type; gc.dirty_sectors = old->dirty_sectors; } - percpu_up_read(&c->mark_lock); /* * gc.data_type doesn't yet include need_discard & need_gc_gen states - @@ -831,11 +830,9 @@ static int bch2_alloc_write_key(struct btree_trans *trans, * safe w.r.t. transaction restarts, so fixup the gc_bucket so * we don't run it twice: */ - percpu_down_read(&c->mark_lock); struct bucket *gc_m = gc_bucket(ca, iter->pos.offset); gc_m->data_type = gc.data_type; gc_m->dirty_sectors = gc.dirty_sectors; - percpu_up_read(&c->mark_lock); } if (fsck_err_on(new.data_type != gc.data_type, @@ -895,11 +892,11 @@ static int bch2_gc_alloc_done(struct bch_fs *c) for_each_member_device(c, ca) { ret = bch2_trans_run(c, - for_each_btree_key_upto_commit(trans, iter, BTREE_ID_alloc, + for_each_btree_key_max_commit(trans, iter, BTREE_ID_alloc, POS(ca->dev_idx, ca->mi.first_bucket), POS(ca->dev_idx, ca->mi.nbuckets - 1), BTREE_ITER_slots|BTREE_ITER_prefetch, k, - NULL, NULL, BCH_TRANS_COMMIT_lazy_rw, + NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_alloc_write_key(trans, &iter, ca, k))); if (ret) { bch2_dev_put(ca); @@ -928,98 +925,6 @@ static int bch2_gc_alloc_start(struct bch_fs *c) return ret; } -static int bch2_gc_write_reflink_key(struct btree_trans *trans, - struct btree_iter *iter, - struct bkey_s_c k, - size_t *idx) -{ - struct bch_fs *c = trans->c; - const __le64 *refcount = bkey_refcount_c(k); - struct printbuf buf = PRINTBUF; - struct reflink_gc *r; - int ret = 0; - - if (!refcount) - return 0; - - while ((r = genradix_ptr(&c->reflink_gc_table, *idx)) && - r->offset < k.k->p.offset) - ++*idx; - - if (!r || - r->offset != k.k->p.offset || - r->size != k.k->size) { - bch_err(c, "unexpected inconsistency walking reflink table at gc finish"); - return -EINVAL; - } - - if (fsck_err_on(r->refcount != le64_to_cpu(*refcount), - trans, reflink_v_refcount_wrong, - "reflink key has wrong refcount:\n" - " %s\n" - " should be %u", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf), - r->refcount)) { - struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); - ret = PTR_ERR_OR_ZERO(new); - if (ret) - goto out; - - if (!r->refcount) - new->k.type = KEY_TYPE_deleted; - else - *bkey_refcount(bkey_i_to_s(new)) = cpu_to_le64(r->refcount); - ret = bch2_trans_update(trans, iter, new, 0); - } -out: -fsck_err: - printbuf_exit(&buf); - return ret; -} - -static int bch2_gc_reflink_done(struct bch_fs *c) -{ - size_t idx = 0; - - int ret = bch2_trans_run(c, - for_each_btree_key_commit(trans, iter, - BTREE_ID_reflink, POS_MIN, - BTREE_ITER_prefetch, k, - NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - bch2_gc_write_reflink_key(trans, &iter, k, &idx))); - c->reflink_gc_nr = 0; - return ret; -} - -static int bch2_gc_reflink_start(struct bch_fs *c) -{ - c->reflink_gc_nr = 0; - - int ret = bch2_trans_run(c, - for_each_btree_key(trans, iter, BTREE_ID_reflink, POS_MIN, - BTREE_ITER_prefetch, k, ({ - const __le64 *refcount = bkey_refcount_c(k); - - if (!refcount) - continue; - - struct reflink_gc *r = genradix_ptr_alloc(&c->reflink_gc_table, - c->reflink_gc_nr++, GFP_KERNEL); - if (!r) { - ret = -BCH_ERR_ENOMEM_gc_reflink_start; - break; - } - - r->offset = k.k->p.offset; - r->size = k.k->size; - r->refcount = 0; - 0; - }))); - - bch_err_fn(c, ret); - return ret; -} - static int bch2_gc_write_stripes_key(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) @@ -1171,7 +1076,6 @@ static int gc_btree_gens_key(struct btree_trans *trans, if (unlikely(test_bit(BCH_FS_going_ro, &c->flags))) return -EROFS; - percpu_down_read(&c->mark_lock); rcu_read_lock(); bkey_for_each_ptr(ptrs, ptr) { struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev); @@ -1180,7 +1084,6 @@ static int gc_btree_gens_key(struct btree_trans *trans, if (dev_ptr_stale(ca, ptr) > 16) { rcu_read_unlock(); - percpu_up_read(&c->mark_lock); goto update; } } @@ -1195,7 +1098,6 @@ static int gc_btree_gens_key(struct btree_trans *trans, *gen = ptr->gen; } rcu_read_unlock(); - percpu_up_read(&c->mark_lock); return 0; update: u = bch2_bkey_make_mut(trans, iter, &k, 0); @@ -1224,7 +1126,6 @@ static int bch2_alloc_write_oldest_gen(struct btree_trans *trans, struct bch_dev return ret; a_mut->v.oldest_gen = ca->oldest_gen[iter->pos.offset]; - alloc_data_type_set(&a_mut->v, a_mut->v.data_type); return bch2_trans_update(trans, iter, &a_mut->k_i, 0); } @@ -1337,9 +1238,16 @@ void bch2_gc_gens_async(struct bch_fs *c) bch2_write_ref_put(c, BCH_WRITE_REF_gc_gens); } -void bch2_fs_gc_init(struct bch_fs *c) +void bch2_fs_btree_gc_exit(struct bch_fs *c) +{ +} + +int bch2_fs_btree_gc_init(struct bch_fs *c) { seqcount_init(&c->gc_pos_lock); - INIT_WORK(&c->gc_gens_work, bch2_gc_gens_work); + + init_rwsem(&c->gc_lock); + mutex_init(&c->gc_gens_lock); + return 0; } diff --git a/fs/bcachefs/btree_gc.h b/fs/bcachefs/btree_gc.h index 8a47e8bd0791..9693a90a48a2 100644 --- a/fs/bcachefs/btree_gc.h +++ b/fs/bcachefs/btree_gc.h @@ -82,6 +82,8 @@ void bch2_gc_pos_to_text(struct printbuf *, struct gc_pos *); int bch2_gc_gens(struct bch_fs *); void bch2_gc_gens_async(struct bch_fs *); -void bch2_fs_gc_init(struct bch_fs *); + +void bch2_fs_btree_gc_exit(struct bch_fs *); +int bch2_fs_btree_gc_init(struct bch_fs *); #endif /* _BCACHEFS_BTREE_GC_H */ diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 839d68802e42..e371e60e3133 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -25,9 +25,8 @@ static void bch2_btree_node_header_to_text(struct printbuf *out, struct btree_node *bn) { - prt_printf(out, "btree=%s l=%u seq %llux\n", - bch2_btree_id_str(BTREE_NODE_ID(bn)), - (unsigned) BTREE_NODE_LEVEL(bn), bn->keys.seq); + bch2_btree_id_level_to_text(out, BTREE_NODE_ID(bn), BTREE_NODE_LEVEL(bn)); + prt_printf(out, " seq %llx %llu\n", bn->keys.seq, BTREE_NODE_SEQ(bn)); prt_str(out, "min: "); bch2_bpos_to_text(out, bn->min_key); prt_newline(out); @@ -490,8 +489,8 @@ void bch2_btree_init_next(struct btree_trans *trans, struct btree *b) if (b->nsets == MAX_BSETS && !btree_node_write_in_flight(b) && should_compact_all(c, b)) { - bch2_btree_node_write(c, b, SIX_LOCK_write, - BTREE_WRITE_init_next_bset); + bch2_btree_node_write_trans(trans, b, SIX_LOCK_write, + BTREE_WRITE_init_next_bset); reinit_iter = true; } @@ -832,13 +831,32 @@ fsck_err: return ret; } +static int btree_node_bkey_val_validate(struct bch_fs *c, struct btree *b, + struct bkey_s_c k, + enum bch_validate_flags flags) +{ + return bch2_bkey_val_validate(c, k, (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level, + .btree = b->c.btree_id, + .flags = flags + }); +} + static int bset_key_validate(struct bch_fs *c, struct btree *b, struct bkey_s_c k, - bool updated_range, int rw) + bool updated_range, + enum bch_validate_flags flags) { - return __bch2_bkey_validate(c, k, btree_node_type(b), 0) ?: - (!updated_range ? bch2_bkey_in_btree_node(c, b, k, 0) : 0) ?: - (rw == WRITE ? bch2_bkey_val_validate(c, k, 0) : 0); + struct bkey_validate_context from = (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level, + .btree = b->c.btree_id, + .flags = flags, + }; + return __bch2_bkey_validate(c, k, from) ?: + (!updated_range ? bch2_bkey_in_btree_node(c, b, k, from) : 0) ?: + (flags & BCH_VALIDATE_write ? btree_node_bkey_val_validate(c, b, k, flags) : 0); } static bool bkey_packed_valid(struct bch_fs *c, struct btree *b, @@ -855,7 +873,21 @@ static bool bkey_packed_valid(struct bch_fs *c, struct btree *b, struct bkey tmp; struct bkey_s u = __bkey_disassemble(b, k, &tmp); - return !__bch2_bkey_validate(c, u.s_c, btree_node_type(b), BCH_VALIDATE_silent); + return !__bch2_bkey_validate(c, u.s_c, + (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level, + .btree = b->c.btree_id, + .flags = BCH_VALIDATE_silent + }); +} + +static inline int btree_node_read_bkey_cmp(const struct btree *b, + const struct bkey_packed *l, + const struct bkey_packed *r) +{ + return bch2_bkey_cmp_packed(b, l, r) + ?: (int) bkey_deleted(r) - (int) bkey_deleted(l); } static int validate_bset_keys(struct bch_fs *c, struct btree *b, @@ -918,7 +950,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, BSET_BIG_ENDIAN(i), write, &b->format, k); - if (prev && bkey_iter_cmp(b, prev, k) > 0) { + if (prev && btree_node_read_bkey_cmp(b, prev, k) >= 0) { struct bkey up = bkey_unpack_key(b, prev); printbuf_reset(&buf); @@ -965,6 +997,7 @@ drop_this_key: got_good_key: le16_add_cpu(&i->u64s, -next_good_key); memmove_u64s_down(k, bkey_p_next(k), (u64 *) vstruct_end(i) - (u64 *) k); + set_btree_node_need_rewrite(b); } fsck_err: printbuf_exit(&buf); @@ -1038,39 +1071,51 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, while (b->written < (ptr_written ?: btree_sectors(c))) { unsigned sectors; - struct nonce nonce; bool first = !b->written; - bool csum_bad; - if (!b->written) { + if (first) { + bne = NULL; i = &b->data->keys; + } else { + bne = write_block(b); + i = &bne->keys; - btree_err_on(!bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)), - -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, NULL, - bset_unknown_csum, - "unknown checksum type %llu", BSET_CSUM_TYPE(i)); + if (i->seq != b->data->keys.seq) + break; + } - nonce = btree_nonce(i, b->written << 9); + struct nonce nonce = btree_nonce(i, b->written << 9); + bool good_csum_type = bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)); - struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data); - csum_bad = bch2_crc_cmp(b->data->csum, csum); - if (csum_bad) - bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); + btree_err_on(!good_csum_type, + bch2_csum_type_is_encryption(BSET_CSUM_TYPE(i)) + ? -BCH_ERR_btree_node_read_err_must_retry + : -BCH_ERR_btree_node_read_err_want_retry, + c, ca, b, i, NULL, + bset_unknown_csum, + "unknown checksum type %llu", BSET_CSUM_TYPE(i)); - btree_err_on(csum_bad, - -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, NULL, - bset_bad_csum, - "%s", - (printbuf_reset(&buf), - bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), b->data->csum, csum), - buf.buf)); + if (first) { + if (good_csum_type) { + struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data); + bool csum_bad = bch2_crc_cmp(b->data->csum, csum); + if (csum_bad) + bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); - ret = bset_encrypt(c, i, b->written << 9); - if (bch2_fs_fatal_err_on(ret, c, - "decrypting btree node: %s", bch2_err_str(ret))) - goto fsck_err; + btree_err_on(csum_bad, + -BCH_ERR_btree_node_read_err_want_retry, + c, ca, b, i, NULL, + bset_bad_csum, + "%s", + (printbuf_reset(&buf), + bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), b->data->csum, csum), + buf.buf)); + + ret = bset_encrypt(c, i, b->written << 9); + if (bch2_fs_fatal_err_on(ret, c, + "decrypting btree node: %s", bch2_err_str(ret))) + goto fsck_err; + } btree_err_on(btree_node_type_is_extents(btree_node_type(b)) && !BTREE_NODE_NEW_EXTENT_OVERWRITE(b->data), @@ -1081,37 +1126,26 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, sectors = vstruct_sectors(b->data, c->block_bits); } else { - bne = write_block(b); - i = &bne->keys; + if (good_csum_type) { + struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne); + bool csum_bad = bch2_crc_cmp(bne->csum, csum); + if (ca && csum_bad) + bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); - if (i->seq != b->data->keys.seq) - break; + btree_err_on(csum_bad, + -BCH_ERR_btree_node_read_err_want_retry, + c, ca, b, i, NULL, + bset_bad_csum, + "%s", + (printbuf_reset(&buf), + bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), bne->csum, csum), + buf.buf)); - btree_err_on(!bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)), - -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, NULL, - bset_unknown_csum, - "unknown checksum type %llu", BSET_CSUM_TYPE(i)); - - nonce = btree_nonce(i, b->written << 9); - struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne); - csum_bad = bch2_crc_cmp(bne->csum, csum); - if (ca && csum_bad) - bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); - - btree_err_on(csum_bad, - -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, NULL, - bset_bad_csum, - "%s", - (printbuf_reset(&buf), - bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), bne->csum, csum), - buf.buf)); - - ret = bset_encrypt(c, i, b->written << 9); - if (bch2_fs_fatal_err_on(ret, c, - "decrypting btree node: %s", bch2_err_str(ret))) - goto fsck_err; + ret = bset_encrypt(c, i, b->written << 9); + if (bch2_fs_fatal_err_on(ret, c, + "decrypting btree node: %s", bch2_err_str(ret))) + goto fsck_err; + } sectors = vstruct_sectors(bne, c->block_bits); } @@ -1216,7 +1250,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, struct bkey tmp; struct bkey_s u = __bkey_disassemble(b, k, &tmp); - ret = bch2_bkey_val_validate(c, u.s_c, READ); + ret = btree_node_bkey_val_validate(c, b, u.s_c, READ); if (ret == -BCH_ERR_fsck_delete_bkey || (bch2_inject_invalid_keys && !bversion_cmp(u.k->bversion, MAX_VERSION))) { @@ -1226,6 +1260,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, memmove_u64s_down(k, bkey_p_next(k), (u64 *) vstruct_end(i) - (u64 *) k); set_btree_bset_end(b, b->set); + set_btree_node_need_rewrite(b); continue; } if (ret) @@ -1339,13 +1374,18 @@ start: rb->start_time); bio_put(&rb->bio); - if (saw_error && + if ((saw_error || + btree_node_need_rewrite(b)) && !btree_node_read_error(b) && c->curr_recovery_pass != BCH_RECOVERY_PASS_scan_for_btree_nodes) { - printbuf_reset(&buf); - bch2_bpos_to_text(&buf, b->key.k.p); - bch_err_ratelimited(c, "%s: rewriting btree node at btree=%s level=%u %s due to error", - __func__, bch2_btree_id_str(b->c.btree_id), b->c.level, buf.buf); + if (saw_error) { + printbuf_reset(&buf); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, " "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + bch_err_ratelimited(c, "%s: rewriting btree node at due to error\n %s", + __func__, buf.buf); + } bch2_btree_node_rewrite_async(c, b); } @@ -1933,7 +1973,12 @@ static int validate_bset_for_write(struct bch_fs *c, struct btree *b, bool saw_error; int ret = bch2_bkey_validate(c, bkey_i_to_s_c(&b->key), - BKEY_TYPE_btree, WRITE); + (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level + 1, + .btree = b->c.btree_id, + .flags = BCH_VALIDATE_write, + }); if (ret) { bch2_fs_inconsistent(c, "invalid btree node key before write"); return ret; @@ -2300,6 +2345,34 @@ void bch2_btree_node_write(struct bch_fs *c, struct btree *b, } } +void bch2_btree_node_write_trans(struct btree_trans *trans, struct btree *b, + enum six_lock_type lock_type_held, + unsigned flags) +{ + struct bch_fs *c = trans->c; + + if (lock_type_held == SIX_LOCK_intent || + (lock_type_held == SIX_LOCK_read && + six_lock_tryupgrade(&b->c.lock))) { + __bch2_btree_node_write(c, b, flags); + + /* don't cycle lock unnecessarily: */ + if (btree_node_just_written(b) && + six_trylock_write(&b->c.lock)) { + bch2_btree_post_write_cleanup(c, b); + __bch2_btree_node_unlock_write(trans, b); + } + + if (lock_type_held == SIX_LOCK_read) + six_lock_downgrade(&b->c.lock); + } else { + __bch2_btree_node_write(c, b, flags); + if (lock_type_held == SIX_LOCK_write && + btree_node_just_written(b)) + bch2_btree_post_write_cleanup(c, b); + } +} + static bool __bch2_btree_flush_all(struct bch_fs *c, unsigned flag) { struct bucket_table *tbl; diff --git a/fs/bcachefs/btree_io.h b/fs/bcachefs/btree_io.h index 9b01ca3de907..6f9e4a6dacf7 100644 --- a/fs/bcachefs/btree_io.h +++ b/fs/bcachefs/btree_io.h @@ -144,11 +144,13 @@ enum btree_write_flags { void __bch2_btree_node_write(struct bch_fs *, struct btree *, unsigned); void bch2_btree_node_write(struct bch_fs *, struct btree *, enum six_lock_type, unsigned); +void bch2_btree_node_write_trans(struct btree_trans *, struct btree *, + enum six_lock_type, unsigned); -static inline void btree_node_write_if_need(struct bch_fs *c, struct btree *b, +static inline void btree_node_write_if_need(struct btree_trans *trans, struct btree *b, enum six_lock_type lock_held) { - bch2_btree_node_write(c, b, lock_held, BTREE_WRITE_ONLY_IF_NEED); + bch2_btree_node_write_trans(trans, b, lock_held, BTREE_WRITE_ONLY_IF_NEED); } bool bch2_btree_flush_all_reads(struct bch_fs *); diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index eef9b89c561d..5988219c6908 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -270,8 +270,10 @@ static void bch2_btree_iter_verify_entry_exit(struct btree_iter *iter) BUG_ON(!(iter->flags & BTREE_ITER_all_snapshots) && iter->pos.snapshot != iter->snapshot); - BUG_ON(bkey_lt(iter->pos, bkey_start_pos(&iter->k)) || - bkey_gt(iter->pos, iter->k.p)); + BUG_ON(iter->flags & BTREE_ITER_all_snapshots ? !bpos_eq(iter->pos, iter->k.p) : + !(iter->flags & BTREE_ITER_is_extents) ? !bkey_eq(iter->pos, iter->k.p) : + (bkey_lt(iter->pos, bkey_start_pos(&iter->k)) || + bkey_gt(iter->pos, iter->k.p))); } static int bch2_btree_iter_verify_ret(struct btree_iter *iter, struct bkey_s_c k) @@ -327,7 +329,7 @@ out: void bch2_assert_pos_locked(struct btree_trans *trans, enum btree_id id, struct bpos pos) { - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); struct btree_path *path; struct trans_for_each_path_inorder_iter iter; @@ -697,6 +699,19 @@ void bch2_trans_node_add(struct btree_trans *trans, bch2_trans_revalidate_updates_in_node(trans, b); } +void bch2_trans_node_drop(struct btree_trans *trans, + struct btree *b) +{ + struct btree_path *path; + unsigned i, level = b->c.level; + + trans_for_each_path(trans, path, i) + if (path->l[level].b == b) { + btree_node_unlock(trans, path, level); + path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init); + } +} + /* * A btree node has been modified in such a way as to invalidate iterators - fix * them: @@ -720,7 +735,7 @@ static inline int btree_path_lock_root(struct btree_trans *trans, unsigned long trace_ip) { struct bch_fs *c = trans->c; - struct btree *b, **rootp = &bch2_btree_id_root(c, path->btree_id)->b; + struct btree_root *r = bch2_btree_id_root(c, path->btree_id); enum six_lock_type lock_type; unsigned i; int ret; @@ -728,7 +743,12 @@ static inline int btree_path_lock_root(struct btree_trans *trans, EBUG_ON(path->nodes_locked); while (1) { - b = READ_ONCE(*rootp); + struct btree *b = READ_ONCE(r->b); + if (unlikely(!b)) { + BUG_ON(!r->error); + return r->error; + } + path->level = READ_ONCE(b->c.level); if (unlikely(path->level < depth_want)) { @@ -748,14 +768,12 @@ static inline int btree_path_lock_root(struct btree_trans *trans, ret = btree_node_lock(trans, path, &b->c, path->level, lock_type, trace_ip); if (unlikely(ret)) { - if (bch2_err_matches(ret, BCH_ERR_lock_fail_root_changed)) - continue; if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) return ret; BUG(); } - if (likely(b == READ_ONCE(*rootp) && + if (likely(b == READ_ONCE(r->b) && b->c.level == path->level && !race_fault())) { for (i = 0; i < path->level; i++) @@ -825,6 +843,8 @@ static int btree_path_prefetch_j(struct btree_trans *trans, struct btree_path *p bch2_bkey_buf_init(&tmp); + jiter->fail_if_too_many_whiteouts = true; + while (nr-- && !ret) { if (!bch2_btree_node_relock(trans, path, path->level)) break; @@ -1000,7 +1020,7 @@ retry_all: bch2_trans_unlock(trans); cond_resched(); - trans_set_locked(trans); + trans_set_locked(trans, false); if (unlikely(trans->memory_allocation_failure)) { struct closure cl; @@ -1267,7 +1287,7 @@ __bch2_btree_path_set_pos(struct btree_trans *trans, { int cmp = bpos_cmp(new_pos, trans->paths[path_idx].pos); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); EBUG_ON(!trans->paths[path_idx].ref); trace_btree_path_set_pos(trans, trans->paths + path_idx, &new_pos); @@ -1427,17 +1447,31 @@ void __noreturn bch2_trans_restart_error(struct btree_trans *trans, u32 restart_ (void *) trans->last_begin_ip); } -void __noreturn bch2_trans_in_restart_error(struct btree_trans *trans) +static void __noreturn bch2_trans_in_restart_error(struct btree_trans *trans) { +#ifdef CONFIG_BCACHEFS_DEBUG + struct printbuf buf = PRINTBUF; + bch2_prt_backtrace(&buf, &trans->last_restarted_trace); + panic("in transaction restart: %s, last restarted by\n%s", + bch2_err_str(trans->restarted), + buf.buf); +#else panic("in transaction restart: %s, last restarted by %pS\n", bch2_err_str(trans->restarted), (void *) trans->last_restarted_ip); +#endif } -void __noreturn bch2_trans_unlocked_error(struct btree_trans *trans) +void __noreturn bch2_trans_unlocked_or_in_restart_error(struct btree_trans *trans) { - panic("trans should be locked, unlocked by %pS\n", - (void *) trans->last_unlock_ip); + if (trans->restarted) + bch2_trans_in_restart_error(trans); + + if (!trans->locked) + panic("trans should be locked, unlocked by %pS\n", + (void *) trans->last_unlock_ip); + + BUG(); } noinline __cold @@ -1450,10 +1484,11 @@ void bch2_trans_updates_to_text(struct printbuf *buf, struct btree_trans *trans) trans_for_each_update(trans, i) { struct bkey_s_c old = { &i->old_k, i->old_v }; - prt_printf(buf, "update: btree=%s cached=%u %pS\n", - bch2_btree_id_str(i->btree_id), - i->cached, - (void *) i->ip_allocated); + prt_str(buf, "update: btree="); + bch2_btree_id_to_text(buf, i->btree_id); + prt_printf(buf, " cached=%u %pS\n", + i->cached, + (void *) i->ip_allocated); prt_printf(buf, " old "); bch2_bkey_val_to_text(buf, trans->c, old); @@ -1486,13 +1521,13 @@ static void bch2_btree_path_to_text_short(struct printbuf *out, struct btree_tra { struct btree_path *path = trans->paths + path_idx; - prt_printf(out, "path: idx %3u ref %u:%u %c %c %c btree=%s l=%u pos ", + prt_printf(out, "path: idx %3u ref %u:%u %c %c %c ", path_idx, path->ref, path->intent_ref, path->preserve ? 'P' : ' ', path->should_be_locked ? 'S' : ' ', - path->cached ? 'C' : 'B', - bch2_btree_id_str(path->btree_id), - path->level); + path->cached ? 'C' : 'B'); + bch2_btree_id_level_to_text(out, path->btree_id, path->level); + prt_str(out, " pos "); bch2_bpos_to_text(out, path->pos); if (!path->cached && btree_node_locked(path, path->level)) { @@ -1717,8 +1752,7 @@ btree_path_idx_t bch2_path_get(struct btree_trans *trans, struct trans_for_each_path_inorder_iter iter; btree_path_idx_t path_pos = 0, path_idx; - bch2_trans_verify_not_unlocked(trans); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); bch2_trans_verify_locks(trans); btree_trans_sort_paths(trans); @@ -1833,7 +1867,7 @@ struct bkey_s_c bch2_btree_path_peek_slot(struct btree_path *path, struct bkey * !bkey_eq(path->pos, ck->key.pos)); *u = ck->k->k; - k = bkey_i_to_s_c(ck->k); + k = (struct bkey_s_c) { u, &ck->k->v }; } return k; @@ -1843,7 +1877,6 @@ hole: return (struct bkey_s_c) { u, NULL }; } - void bch2_set_btree_iter_dontneed(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; @@ -1870,7 +1903,7 @@ bch2_btree_iter_traverse(struct btree_iter *iter) struct btree_trans *trans = iter->trans; int ret; - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); iter->path = bch2_btree_path_set_pos(trans, iter->path, btree_iter_search_key(iter), @@ -1945,7 +1978,7 @@ struct btree *bch2_btree_iter_next_node(struct btree_iter *iter) int ret; EBUG_ON(trans->paths[iter->path].cached); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); bch2_btree_iter_verify(iter); ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); @@ -2101,7 +2134,7 @@ static struct bkey_i *bch2_btree_journal_peek(struct btree_trans *trans, { struct btree_path *path = btree_iter_path(trans, iter); - return bch2_journal_keys_peek_upto(trans->c, iter->btree_id, + return bch2_journal_keys_peek_max(trans->c, iter->btree_id, path->level, path->pos, end_pos, @@ -2124,21 +2157,47 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans, } static noinline -struct bkey_s_c btree_trans_peek_journal(struct btree_trans *trans, - struct btree_iter *iter, - struct bkey_s_c k) +void btree_trans_peek_journal(struct btree_trans *trans, + struct btree_iter *iter, + struct bkey_s_c *k) { struct btree_path *path = btree_iter_path(trans, iter); struct bkey_i *next_journal = bch2_btree_journal_peek(trans, iter, - k.k ? k.k->p : path_l(path)->b->key.k.p); + k->k ? k->k->p : path_l(path)->b->key.k.p); + if (next_journal) { + iter->k = next_journal->k; + *k = bkey_i_to_s_c(next_journal); + } +} + +static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans, + struct btree_iter *iter, + struct bpos end_pos) +{ + struct btree_path *path = btree_iter_path(trans, iter); + + return bch2_journal_keys_peek_prev_min(trans->c, iter->btree_id, + path->level, + path->pos, + end_pos, + &iter->journal_idx); +} + +static noinline +void btree_trans_peek_prev_journal(struct btree_trans *trans, + struct btree_iter *iter, + struct bkey_s_c *k) +{ + struct btree_path *path = btree_iter_path(trans, iter); + struct bkey_i *next_journal = + bch2_btree_journal_peek_prev(trans, iter, + k->k ? k->k->p : path_l(path)->b->key.k.p); if (next_journal) { iter->k = next_journal->k; - k = bkey_i_to_s_c(next_journal); + *k = bkey_i_to_s_c(next_journal); } - - return k; } /* @@ -2154,8 +2213,7 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos struct bkey_s_c k; int ret; - bch2_trans_verify_not_in_restart(trans); - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if ((iter->flags & BTREE_ITER_key_cache_fill) && bpos_eq(iter->pos, pos)) @@ -2181,13 +2239,17 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos if (unlikely(ret)) return bkey_s_c_err(ret); - btree_path_set_should_be_locked(trans, trans->paths + iter->key_cache_path); - k = bch2_btree_path_peek_slot(trans->paths + iter->key_cache_path, &u); - if (k.k && !bkey_err(k)) { - iter->k = u; - k.k = &iter->k; - } + if (!k.k) + return k; + + if ((iter->flags & BTREE_ITER_all_snapshots) && + !bpos_eq(pos, k.k->p)) + return bkey_s_c_null; + + iter->k = u; + k.k = &iter->k; + btree_path_set_should_be_locked(trans, trans->paths + iter->key_cache_path); return k; } @@ -2201,8 +2263,6 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp bch2_btree_iter_verify(iter); while (1) { - struct btree_path_level *l; - iter->path = bch2_btree_path_set_pos(trans, iter->path, search_key, iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); @@ -2212,17 +2272,17 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp /* ensure that iter->k is consistent with iter->pos: */ bch2_btree_iter_set_pos(iter, iter->pos); k = bkey_s_c_err(ret); - goto out; + break; } struct btree_path *path = btree_iter_path(trans, iter); - l = path_l(path); + struct btree_path_level *l = path_l(path); if (unlikely(!l->b)) { /* No btree nodes at requested level: */ bch2_btree_iter_set_pos(iter, SPOS_MAX); k = bkey_s_c_null; - goto out; + break; } btree_path_set_should_be_locked(trans, path); @@ -2233,15 +2293,14 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp k.k && (k2 = btree_trans_peek_key_cache(iter, k.k->p)).k) { k = k2; - ret = bkey_err(k); - if (ret) { + if (bkey_err(k)) { bch2_btree_iter_set_pos(iter, iter->pos); - goto out; + break; } } if (unlikely(iter->flags & BTREE_ITER_with_journal)) - k = btree_trans_peek_journal(trans, iter, k); + btree_trans_peek_journal(trans, iter, &k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) @@ -2270,32 +2329,32 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp /* End of btree: */ bch2_btree_iter_set_pos(iter, SPOS_MAX); k = bkey_s_c_null; - goto out; + break; } } -out: - bch2_btree_iter_verify(iter); + bch2_btree_iter_verify(iter); return k; } /** - * bch2_btree_iter_peek_upto() - returns first key greater than or equal to + * bch2_btree_iter_peek_max() - returns first key greater than or equal to * iterator's current position * @iter: iterator to peek from * @end: search limit: returns keys less than or equal to @end * * Returns: key if found, or an error extractable with bkey_err(). */ -struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos end) +struct bkey_s_c bch2_btree_iter_peek_max(struct btree_iter *iter, struct bpos end) { struct btree_trans *trans = iter->trans; struct bpos search_key = btree_iter_search_key(iter); struct bkey_s_c k; - struct bpos iter_pos; + struct bpos iter_pos = iter->pos; int ret; - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); + bch2_btree_iter_verify_entry_exit(iter); EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bkey_eq(end, POS_MAX)); if (iter->update_path) { @@ -2304,8 +2363,6 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e iter->update_path = 0; } - bch2_btree_iter_verify_entry_exit(iter); - while (1) { k = __bch2_btree_iter_peek(iter, search_key); if (unlikely(!k.k)) @@ -2313,77 +2370,77 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e if (unlikely(bkey_err(k))) goto out_no_locked; - /* - * We need to check against @end before FILTER_SNAPSHOTS because - * if we get to a different inode that requested we might be - * seeing keys for a different snapshot tree that will all be - * filtered out. - * - * But we can't do the full check here, because bkey_start_pos() - * isn't monotonically increasing before FILTER_SNAPSHOTS, and - * that's what we check against in extents mode: - */ - if (unlikely(!(iter->flags & BTREE_ITER_is_extents) - ? bkey_gt(k.k->p, end) - : k.k->p.inode > end.inode)) - goto end; + if (iter->flags & BTREE_ITER_filter_snapshots) { + /* + * We need to check against @end before FILTER_SNAPSHOTS because + * if we get to a different inode that requested we might be + * seeing keys for a different snapshot tree that will all be + * filtered out. + * + * But we can't do the full check here, because bkey_start_pos() + * isn't monotonically increasing before FILTER_SNAPSHOTS, and + * that's what we check against in extents mode: + */ + if (unlikely(!(iter->flags & BTREE_ITER_is_extents) + ? bkey_gt(k.k->p, end) + : k.k->p.inode > end.inode)) + goto end; - if (iter->update_path && - !bkey_eq(trans->paths[iter->update_path].pos, k.k->p)) { - bch2_path_put_nokeep(trans, iter->update_path, - iter->flags & BTREE_ITER_intent); - iter->update_path = 0; - } + if (iter->update_path && + !bkey_eq(trans->paths[iter->update_path].pos, k.k->p)) { + bch2_path_put_nokeep(trans, iter->update_path, + iter->flags & BTREE_ITER_intent); + iter->update_path = 0; + } - if ((iter->flags & BTREE_ITER_filter_snapshots) && - (iter->flags & BTREE_ITER_intent) && - !(iter->flags & BTREE_ITER_is_extents) && - !iter->update_path) { - struct bpos pos = k.k->p; + if ((iter->flags & BTREE_ITER_intent) && + !(iter->flags & BTREE_ITER_is_extents) && + !iter->update_path) { + struct bpos pos = k.k->p; - if (pos.snapshot < iter->snapshot) { + if (pos.snapshot < iter->snapshot) { + search_key = bpos_successor(k.k->p); + continue; + } + + pos.snapshot = iter->snapshot; + + /* + * advance, same as on exit for iter->path, but only up + * to snapshot + */ + __btree_path_get(trans, trans->paths + iter->path, iter->flags & BTREE_ITER_intent); + iter->update_path = iter->path; + + iter->update_path = bch2_btree_path_set_pos(trans, + iter->update_path, pos, + iter->flags & BTREE_ITER_intent, + _THIS_IP_); + ret = bch2_btree_path_traverse(trans, iter->update_path, iter->flags); + if (unlikely(ret)) { + k = bkey_s_c_err(ret); + goto out_no_locked; + } + } + + /* + * We can never have a key in a leaf node at POS_MAX, so + * we don't have to check these successor() calls: + */ + if (!bch2_snapshot_is_ancestor(trans->c, + iter->snapshot, + k.k->p.snapshot)) { search_key = bpos_successor(k.k->p); continue; } - pos.snapshot = iter->snapshot; - - /* - * advance, same as on exit for iter->path, but only up - * to snapshot - */ - __btree_path_get(trans, trans->paths + iter->path, iter->flags & BTREE_ITER_intent); - iter->update_path = iter->path; - - iter->update_path = bch2_btree_path_set_pos(trans, - iter->update_path, pos, - iter->flags & BTREE_ITER_intent, - _THIS_IP_); - ret = bch2_btree_path_traverse(trans, iter->update_path, iter->flags); - if (unlikely(ret)) { - k = bkey_s_c_err(ret); - goto out_no_locked; + if (bkey_whiteout(k.k) && + !(iter->flags & BTREE_ITER_key_cache_fill)) { + search_key = bkey_successor(iter, k.k->p); + continue; } } - /* - * We can never have a key in a leaf node at POS_MAX, so - * we don't have to check these successor() calls: - */ - if ((iter->flags & BTREE_ITER_filter_snapshots) && - !bch2_snapshot_is_ancestor(trans->c, - iter->snapshot, - k.k->p.snapshot)) { - search_key = bpos_successor(k.k->p); - continue; - } - - if (bkey_whiteout(k.k) && - !(iter->flags & BTREE_ITER_all_snapshots)) { - search_key = bkey_successor(iter, k.k->p); - continue; - } - /* * iter->pos should be mononotically increasing, and always be * equal to the key we just returned - except extents can @@ -2451,111 +2508,66 @@ struct bkey_s_c bch2_btree_iter_next(struct btree_iter *iter) return bch2_btree_iter_peek(iter); } -/** - * bch2_btree_iter_peek_prev() - returns first key less than or equal to - * iterator's current position - * @iter: iterator to peek from - * - * Returns: key if found, or an error extractable with bkey_err(). - */ -struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *iter) +static struct bkey_s_c __bch2_btree_iter_peek_prev(struct btree_iter *iter, struct bpos search_key) { struct btree_trans *trans = iter->trans; - struct bpos search_key = iter->pos; - struct bkey_s_c k; - struct bkey saved_k; - const struct bch_val *saved_v; - btree_path_idx_t saved_path = 0; - int ret; - - bch2_trans_verify_not_unlocked(trans); - EBUG_ON(btree_iter_path(trans, iter)->cached || - btree_iter_path(trans, iter)->level); - - if (iter->flags & BTREE_ITER_with_journal) - return bkey_s_c_err(-BCH_ERR_btree_iter_with_journal_not_supported); + struct bkey_s_c k, k2; bch2_btree_iter_verify(iter); - bch2_btree_iter_verify_entry_exit(iter); - - if (iter->flags & BTREE_ITER_filter_snapshots) - search_key.snapshot = U32_MAX; while (1) { iter->path = bch2_btree_path_set_pos(trans, iter->path, search_key, - iter->flags & BTREE_ITER_intent, - btree_iter_ip_allocated(iter)); + iter->flags & BTREE_ITER_intent, + btree_iter_ip_allocated(iter)); - ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); + int ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); if (unlikely(ret)) { /* ensure that iter->k is consistent with iter->pos: */ bch2_btree_iter_set_pos(iter, iter->pos); k = bkey_s_c_err(ret); - goto out_no_locked; + break; } struct btree_path *path = btree_iter_path(trans, iter); + struct btree_path_level *l = path_l(path); - k = btree_path_level_peek(trans, path, &path->l[0], &iter->k); - if (!k.k || - ((iter->flags & BTREE_ITER_is_extents) - ? bpos_ge(bkey_start_pos(k.k), search_key) - : bpos_gt(k.k->p, search_key))) - k = btree_path_level_prev(trans, path, &path->l[0], &iter->k); + if (unlikely(!l->b)) { + /* No btree nodes at requested level: */ + bch2_btree_iter_set_pos(iter, SPOS_MAX); + k = bkey_s_c_null; + break; + } + + btree_path_set_should_be_locked(trans, path); + + k = btree_path_level_peek_all(trans->c, l, &iter->k); + if (!k.k || bpos_gt(k.k->p, search_key)) { + k = btree_path_level_prev(trans, path, l, &iter->k); + + BUG_ON(k.k && bpos_gt(k.k->p, search_key)); + } + + if (unlikely(iter->flags & BTREE_ITER_with_key_cache) && + k.k && + (k2 = btree_trans_peek_key_cache(iter, k.k->p)).k) { + k = k2; + if (bkey_err(k2)) { + bch2_btree_iter_set_pos(iter, iter->pos); + break; + } + } + + if (unlikely(iter->flags & BTREE_ITER_with_journal)) + btree_trans_peek_prev_journal(trans, iter, &k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) bch2_btree_trans_peek_prev_updates(trans, iter, &k); - if (likely(k.k)) { - if (iter->flags & BTREE_ITER_filter_snapshots) { - if (k.k->p.snapshot == iter->snapshot) - goto got_key; - - /* - * If we have a saved candidate, and we're no - * longer at the same _key_ (not pos), return - * that candidate - */ - if (saved_path && !bkey_eq(k.k->p, saved_k.p)) { - bch2_path_put_nokeep(trans, iter->path, - iter->flags & BTREE_ITER_intent); - iter->path = saved_path; - saved_path = 0; - iter->k = saved_k; - k.v = saved_v; - goto got_key; - } - - if (bch2_snapshot_is_ancestor(trans->c, - iter->snapshot, - k.k->p.snapshot)) { - if (saved_path) - bch2_path_put_nokeep(trans, saved_path, - iter->flags & BTREE_ITER_intent); - saved_path = btree_path_clone(trans, iter->path, - iter->flags & BTREE_ITER_intent, - _THIS_IP_); - path = btree_iter_path(trans, iter); - trace_btree_path_save_pos(trans, path, trans->paths + saved_path); - saved_k = *k.k; - saved_v = k.v; - } - - search_key = bpos_predecessor(k.k->p); - continue; - } -got_key: - if (bkey_whiteout(k.k) && - !(iter->flags & BTREE_ITER_all_snapshots)) { - search_key = bkey_predecessor(iter, k.k->p); - if (iter->flags & BTREE_ITER_filter_snapshots) - search_key.snapshot = U32_MAX; - continue; - } - - btree_path_set_should_be_locked(trans, path); + if (likely(k.k && !bkey_deleted(k.k))) { break; + } else if (k.k) { + search_key = bpos_predecessor(k.k->p); } else if (likely(!bpos_eq(path->l[0].b->data->min_key, POS_MIN))) { /* Advance to previous leaf node: */ search_key = bpos_predecessor(path->l[0].b->data->min_key); @@ -2563,15 +2575,137 @@ got_key: /* Start of btree: */ bch2_btree_iter_set_pos(iter, POS_MIN); k = bkey_s_c_null; - goto out_no_locked; + break; } } - EBUG_ON(bkey_gt(bkey_start_pos(k.k), iter->pos)); + bch2_btree_iter_verify(iter); + return k; +} + +/** + * bch2_btree_iter_peek_prev_min() - returns first key less than or equal to + * iterator's current position + * @iter: iterator to peek from + * @end: search limit: returns keys greater than or equal to @end + * + * Returns: key if found, or an error extractable with bkey_err(). + */ +struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_iter *iter, struct bpos end) +{ + if ((iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots)) && + !bkey_eq(iter->pos, POS_MAX)) { + /* + * bkey_start_pos(), for extents, is not monotonically + * increasing until after filtering for snapshots: + * + * Thus, for extents we need to search forward until we find a + * real visible extents - easiest to just use peek_slot() (which + * internally uses peek() for extents) + */ + struct bkey_s_c k = bch2_btree_iter_peek_slot(iter); + if (bkey_err(k)) + return k; + + if (!bkey_deleted(k.k) && + (!(iter->flags & BTREE_ITER_is_extents) || + bkey_lt(bkey_start_pos(k.k), iter->pos))) + return k; + } + + struct btree_trans *trans = iter->trans; + struct bpos search_key = iter->pos; + struct bkey_s_c k; + btree_path_idx_t saved_path = 0; + + bch2_trans_verify_not_unlocked_or_in_restart(trans); + bch2_btree_iter_verify_entry_exit(iter); + EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bpos_eq(end, POS_MIN)); + + while (1) { + k = __bch2_btree_iter_peek_prev(iter, search_key); + if (unlikely(!k.k)) + goto end; + if (unlikely(bkey_err(k))) + goto out_no_locked; + + if (iter->flags & BTREE_ITER_filter_snapshots) { + struct btree_path *s = saved_path ? trans->paths + saved_path : NULL; + if (s && bpos_lt(k.k->p, SPOS(s->pos.inode, s->pos.offset, iter->snapshot))) { + /* + * If we have a saved candidate, and we're past + * the last possible snapshot overwrite, return + * it: + */ + bch2_path_put_nokeep(trans, iter->path, + iter->flags & BTREE_ITER_intent); + iter->path = saved_path; + saved_path = 0; + k = bch2_btree_path_peek_slot(btree_iter_path(trans, iter), &iter->k); + break; + } + + /* + * We need to check against @end before FILTER_SNAPSHOTS because + * if we get to a different inode that requested we might be + * seeing keys for a different snapshot tree that will all be + * filtered out. + */ + if (unlikely(bkey_lt(k.k->p, end))) + goto end; + + if (!bch2_snapshot_is_ancestor(trans->c, iter->snapshot, k.k->p.snapshot)) { + search_key = bpos_predecessor(k.k->p); + continue; + } + + if (k.k->p.snapshot != iter->snapshot) { + /* + * Have a key visible in iter->snapshot, but + * might have overwrites: - save it and keep + * searching. Unless it's a whiteout - then drop + * our previous saved candidate: + */ + if (saved_path) { + bch2_path_put_nokeep(trans, saved_path, + iter->flags & BTREE_ITER_intent); + saved_path = 0; + } + + if (!bkey_whiteout(k.k)) { + saved_path = btree_path_clone(trans, iter->path, + iter->flags & BTREE_ITER_intent, + _THIS_IP_); + trace_btree_path_save_pos(trans, + trans->paths + iter->path, + trans->paths + saved_path); + } + + search_key = bpos_predecessor(k.k->p); + continue; + } + + if (bkey_whiteout(k.k)) { + search_key = bkey_predecessor(iter, k.k->p); + search_key.snapshot = U32_MAX; + continue; + } + } + + EBUG_ON(iter->flags & BTREE_ITER_all_snapshots ? bpos_gt(k.k->p, iter->pos) : + iter->flags & BTREE_ITER_is_extents ? bkey_ge(bkey_start_pos(k.k), iter->pos) : + bkey_gt(k.k->p, iter->pos)); + + if (unlikely(iter->flags & BTREE_ITER_all_snapshots ? bpos_lt(k.k->p, end) : + iter->flags & BTREE_ITER_is_extents ? bkey_le(k.k->p, end) : + bkey_lt(k.k->p, end))) + goto end; + + break; + } /* Extents can straddle iter->pos: */ - if (bkey_lt(k.k->p, iter->pos)) - iter->pos = k.k->p; + iter->pos = bpos_min(iter->pos, k.k->p);; if (iter->flags & BTREE_ITER_filter_snapshots) iter->pos.snapshot = iter->snapshot; @@ -2581,8 +2715,11 @@ out_no_locked: bch2_btree_iter_verify_entry_exit(iter); bch2_btree_iter_verify(iter); - return k; +end: + bch2_btree_iter_set_pos(iter, end); + k = bkey_s_c_null; + goto out_no_locked; } /** @@ -2607,7 +2744,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) struct bkey_s_c k; int ret; - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); bch2_btree_iter_verify(iter); bch2_btree_iter_verify_entry_exit(iter); EBUG_ON(btree_iter_path(trans, iter)->level && (iter->flags & BTREE_ITER_with_key_cache)); @@ -2632,6 +2769,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) goto out_no_locked; } + struct btree_path *path = btree_iter_path(trans, iter); + if (unlikely(!btree_path_node(path, path->level))) + return bkey_s_c_null; + if ((iter->flags & BTREE_ITER_cached) || !(iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots))) { k = bkey_s_c_null; @@ -2658,6 +2799,11 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) k = bch2_btree_path_peek_slot(trans->paths + iter->path, &iter->k); if (unlikely(!k.k)) goto out_no_locked; + + if (unlikely(k.k->type == KEY_TYPE_whiteout && + (iter->flags & BTREE_ITER_filter_snapshots) && + !(iter->flags & BTREE_ITER_key_cache_fill))) + iter->k.type = KEY_TYPE_deleted; } else { struct bpos next; struct bpos end = iter->pos; @@ -2671,7 +2817,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) struct btree_iter iter2; bch2_trans_copy_iter(&iter2, iter); - k = bch2_btree_iter_peek_upto(&iter2, end); + k = bch2_btree_iter_peek_max(&iter2, end); if (k.k && !bkey_err(k)) { swap(iter->key_cache_path, iter2.key_cache_path); @@ -2682,7 +2828,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) } else { struct bpos pos = iter->pos; - k = bch2_btree_iter_peek_upto(iter, end); + k = bch2_btree_iter_peek_max(iter, end); if (unlikely(bkey_err(k))) bch2_btree_iter_set_pos(iter, pos); else @@ -2902,7 +3048,7 @@ void bch2_trans_iter_init_outlined(struct btree_trans *trans, unsigned flags) { bch2_trans_iter_init_common(trans, iter, btree_id, pos, 0, 0, - bch2_btree_iter_flags(trans, btree_id, flags), + bch2_btree_iter_flags(trans, btree_id, 0, flags), _RET_IP_); } @@ -2918,8 +3064,11 @@ void bch2_trans_node_iter_init(struct btree_trans *trans, flags |= BTREE_ITER_snapshot_field; flags |= BTREE_ITER_all_snapshots; + if (!depth && btree_id_cached(trans->c, btree_id)) + flags |= BTREE_ITER_with_key_cache; + bch2_trans_iter_init_common(trans, iter, btree_id, pos, locks_want, depth, - __bch2_btree_iter_flags(trans, btree_id, flags), + bch2_btree_iter_flags(trans, btree_id, depth, flags), _RET_IP_); iter->min_depth = depth; @@ -3122,14 +3271,14 @@ u32 bch2_trans_begin(struct btree_trans *trans) trans->last_begin_ip = _RET_IP_; - trans_set_locked(trans); + trans_set_locked(trans, false); if (trans->restarted) { bch2_btree_path_traverse_all(trans); trans->notrace_relock_fail = false; } - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); return trans->restart_count; } @@ -3228,7 +3377,7 @@ got_trans: trans->srcu_idx = srcu_read_lock(&c->btree_trans_barrier); trans->srcu_lock_time = jiffies; trans->srcu_held = true; - trans_set_locked(trans); + trans_set_locked(trans, false); closure_init_stack_release(&trans->ref); return trans; @@ -3262,6 +3411,9 @@ void bch2_trans_put(struct btree_trans *trans) { struct bch_fs *c = trans->c; + if (trans->restarted) + bch2_trans_in_restart_error(trans); + bch2_trans_unlock(trans); trans_for_each_update(trans, i) @@ -3285,6 +3437,10 @@ void bch2_trans_put(struct btree_trans *trans) closure_return_sync(&trans->ref); trans->locking_wait.task = NULL; +#ifdef CONFIG_BCACHEFS_DEBUG + darray_exit(&trans->last_restarted_trace); +#endif + unsigned long *paths_allocated = trans->paths_allocated; trans->paths_allocated = NULL; trans->paths = NULL; @@ -3338,8 +3494,9 @@ bch2_btree_bkey_cached_common_to_text(struct printbuf *out, pid = owner ? owner->pid : 0; rcu_read_unlock(); - prt_printf(out, "\t%px %c l=%u %s:", b, b->cached ? 'c' : 'b', - b->level, bch2_btree_id_str(b->btree_id)); + prt_printf(out, "\t%px %c ", b, b->cached ? 'c' : 'b'); + bch2_btree_id_to_text(out, b->btree_id); + prt_printf(out, " l=%u:", b->level); bch2_bpos_to_text(out, btree_node_pos(b)); prt_printf(out, "\t locks %u:%u:%u held by pid %u", @@ -3378,11 +3535,11 @@ void bch2_btree_trans_to_text(struct printbuf *out, struct btree_trans *trans) if (!path->nodes_locked) continue; - prt_printf(out, " path %u %c l=%u %s:", - idx, - path->cached ? 'c' : 'b', - path->level, - bch2_btree_id_str(path->btree_id)); + prt_printf(out, " path %u %c ", + idx, + path->cached ? 'c' : 'b'); + bch2_btree_id_to_text(out, path->btree_id); + prt_printf(out, " l=%u:", path->level); bch2_bpos_to_text(out, path->pos); prt_newline(out); @@ -3488,7 +3645,7 @@ int bch2_fs_btree_iter_init(struct bch_fs *c) #ifdef CONFIG_LOCKDEP fs_reclaim_acquire(GFP_KERNEL); struct btree_trans *trans = bch2_trans_get(c); - trans_set_locked(trans); + trans_set_locked(trans, false); bch2_trans_put(trans); fs_reclaim_release(GFP_KERNEL); #endif diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h index 0bda054f80d7..b9538e6e6d65 100644 --- a/fs/bcachefs/btree_iter.h +++ b/fs/bcachefs/btree_iter.h @@ -23,6 +23,7 @@ static inline void __btree_path_get(struct btree_trans *trans, struct btree_path { unsigned idx = path - trans->paths; + EBUG_ON(idx >= trans->nr_paths); EBUG_ON(!test_bit(idx, trans->paths_allocated)); if (unlikely(path->ref == U8_MAX)) { bch2_dump_trans_paths_updates(trans); @@ -36,6 +37,7 @@ static inline void __btree_path_get(struct btree_trans *trans, struct btree_path static inline bool __btree_path_put(struct btree_trans *trans, struct btree_path *path, bool intent) { + EBUG_ON(path - trans->paths >= trans->nr_paths); EBUG_ON(!test_bit(path - trans->paths, trans->paths_allocated)); EBUG_ON(!path->ref); EBUG_ON(!path->intent_ref && intent); @@ -234,12 +236,12 @@ int __must_check bch2_btree_path_traverse_one(struct btree_trans *, btree_path_idx_t, unsigned, unsigned long); -static inline void bch2_trans_verify_not_unlocked(struct btree_trans *); +static inline void bch2_trans_verify_not_unlocked_or_in_restart(struct btree_trans *); static inline int __must_check bch2_btree_path_traverse(struct btree_trans *trans, btree_path_idx_t path, unsigned flags) { - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (trans->paths[path].uptodate < BTREE_ITER_NEED_RELOCK) return 0; @@ -324,38 +326,33 @@ static inline void bch2_trans_verify_not_restarted(struct btree_trans *trans, bch2_trans_restart_error(trans, restart_count); } -void __noreturn bch2_trans_in_restart_error(struct btree_trans *); +void __noreturn bch2_trans_unlocked_or_in_restart_error(struct btree_trans *); -static inline void bch2_trans_verify_not_in_restart(struct btree_trans *trans) +static inline void bch2_trans_verify_not_unlocked_or_in_restart(struct btree_trans *trans) { - if (trans->restarted) - bch2_trans_in_restart_error(trans); -} - -void __noreturn bch2_trans_unlocked_error(struct btree_trans *); - -static inline void bch2_trans_verify_not_unlocked(struct btree_trans *trans) -{ - if (!trans->locked) - bch2_trans_unlocked_error(trans); + if (trans->restarted || !trans->locked) + bch2_trans_unlocked_or_in_restart_error(trans); } __always_inline -static int btree_trans_restart_nounlock(struct btree_trans *trans, int err) +static int btree_trans_restart_ip(struct btree_trans *trans, int err, unsigned long ip) { BUG_ON(err <= 0); BUG_ON(!bch2_err_matches(-err, BCH_ERR_transaction_restart)); trans->restarted = err; - trans->last_restarted_ip = _THIS_IP_; + trans->last_restarted_ip = ip; +#ifdef CONFIG_BCACHEFS_DEBUG + darray_exit(&trans->last_restarted_trace); + bch2_save_backtrace(&trans->last_restarted_trace, current, 0, GFP_NOWAIT); +#endif return -err; } __always_inline static int btree_trans_restart(struct btree_trans *trans, int err) { - btree_trans_restart_nounlock(trans, err); - return -err; + return btree_trans_restart_ip(trans, err, _THIS_IP_); } bool bch2_btree_node_upgrade(struct btree_trans *, @@ -375,6 +372,7 @@ static inline void bch2_btree_path_downgrade(struct btree_trans *trans, void bch2_trans_downgrade(struct btree_trans *); void bch2_trans_node_add(struct btree_trans *trans, struct btree_path *, struct btree *); +void bch2_trans_node_drop(struct btree_trans *trans, struct btree *); void bch2_trans_node_reinit_iter(struct btree_trans *, struct btree *); int __must_check __bch2_btree_iter_traverse(struct btree_iter *iter); @@ -384,15 +382,21 @@ struct btree *bch2_btree_iter_peek_node(struct btree_iter *); struct btree *bch2_btree_iter_peek_node_and_restart(struct btree_iter *); struct btree *bch2_btree_iter_next_node(struct btree_iter *); -struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *, struct bpos); +struct bkey_s_c bch2_btree_iter_peek_max(struct btree_iter *, struct bpos); struct bkey_s_c bch2_btree_iter_next(struct btree_iter *); static inline struct bkey_s_c bch2_btree_iter_peek(struct btree_iter *iter) { - return bch2_btree_iter_peek_upto(iter, SPOS_MAX); + return bch2_btree_iter_peek_max(iter, SPOS_MAX); +} + +struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_iter *, struct bpos); + +static inline struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *iter) +{ + return bch2_btree_iter_peek_prev_min(iter, POS_MIN); } -struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *); struct bkey_s_c bch2_btree_iter_prev(struct btree_iter *); struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *); @@ -443,10 +447,17 @@ static inline void bch2_btree_iter_set_snapshot(struct btree_iter *iter, u32 sna void bch2_trans_iter_exit(struct btree_trans *, struct btree_iter *); -static inline unsigned __bch2_btree_iter_flags(struct btree_trans *trans, - unsigned btree_id, - unsigned flags) +static inline unsigned bch2_btree_iter_flags(struct btree_trans *trans, + unsigned btree_id, + unsigned level, + unsigned flags) { + if (level || !btree_id_cached(trans->c, btree_id)) { + flags &= ~BTREE_ITER_cached; + flags &= ~BTREE_ITER_with_key_cache; + } else if (!(flags & BTREE_ITER_cached)) + flags |= BTREE_ITER_with_key_cache; + if (!(flags & (BTREE_ITER_all_snapshots|BTREE_ITER_not_extents)) && btree_id_is_extents(btree_id)) flags |= BTREE_ITER_is_extents; @@ -465,19 +476,6 @@ static inline unsigned __bch2_btree_iter_flags(struct btree_trans *trans, return flags; } -static inline unsigned bch2_btree_iter_flags(struct btree_trans *trans, - unsigned btree_id, - unsigned flags) -{ - if (!btree_id_cached(trans->c, btree_id)) { - flags &= ~BTREE_ITER_cached; - flags &= ~BTREE_ITER_with_key_cache; - } else if (!(flags & BTREE_ITER_cached)) - flags |= BTREE_ITER_with_key_cache; - - return __bch2_btree_iter_flags(trans, btree_id, flags); -} - static inline void bch2_trans_iter_init_common(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, @@ -514,7 +512,7 @@ static inline void bch2_trans_iter_init(struct btree_trans *trans, if (__builtin_constant_p(btree_id) && __builtin_constant_p(flags)) bch2_trans_iter_init_common(trans, iter, btree_id, pos, 0, 0, - bch2_btree_iter_flags(trans, btree_id, flags), + bch2_btree_iter_flags(trans, btree_id, 0, flags), _THIS_IP_); else bch2_trans_iter_init_outlined(trans, iter, btree_id, pos, flags); @@ -593,13 +591,18 @@ static inline struct bkey_s_c bch2_bkey_get_iter(struct btree_trans *trans, bkey_s_c_to_##_type(__bch2_bkey_get_iter(_trans, _iter, \ _btree_id, _pos, _flags, KEY_TYPE_##_type)) +static inline void __bkey_val_copy(void *dst_v, unsigned dst_size, struct bkey_s_c src_k) +{ + unsigned b = min_t(unsigned, dst_size, bkey_val_bytes(src_k.k)); + memcpy(dst_v, src_k.v, b); + if (unlikely(b < dst_size)) + memset(dst_v + b, 0, dst_size - b); +} + #define bkey_val_copy(_dst_v, _src_k) \ do { \ - unsigned b = min_t(unsigned, sizeof(*_dst_v), \ - bkey_val_bytes(_src_k.k)); \ - memcpy(_dst_v, _src_k.v, b); \ - if (b < sizeof(*_dst_v)) \ - memset((void *) (_dst_v) + b, 0, sizeof(*_dst_v) - b); \ + BUILD_BUG_ON(!__typecheck(*_dst_v, *_src_k.v)); \ + __bkey_val_copy(_dst_v, sizeof(*_dst_v), _src_k.s_c); \ } while (0) static inline int __bch2_bkey_get_val_typed(struct btree_trans *trans, @@ -608,17 +611,10 @@ static inline int __bch2_bkey_get_val_typed(struct btree_trans *trans, unsigned val_size, void *val) { struct btree_iter iter; - struct bkey_s_c k; - int ret; - - k = __bch2_bkey_get_iter(trans, &iter, btree_id, pos, flags, type); - ret = bkey_err(k); + struct bkey_s_c k = __bch2_bkey_get_iter(trans, &iter, btree_id, pos, flags, type); + int ret = bkey_err(k); if (!ret) { - unsigned b = min_t(unsigned, bkey_val_bytes(k.k), val_size); - - memcpy(val, k.v, b); - if (unlikely(b < sizeof(*val))) - memset((void *) val + b, 0, sizeof(*val) - b); + __bkey_val_copy(val, val_size, k); bch2_trans_iter_exit(trans, &iter); } @@ -677,12 +673,12 @@ static inline struct bkey_s_c bch2_btree_iter_peek_type(struct btree_iter *iter, bch2_btree_iter_peek(iter); } -static inline struct bkey_s_c bch2_btree_iter_peek_upto_type(struct btree_iter *iter, +static inline struct bkey_s_c bch2_btree_iter_peek_max_type(struct btree_iter *iter, struct bpos end, unsigned flags) { if (!(flags & BTREE_ITER_slots)) - return bch2_btree_iter_peek_upto(iter, end); + return bch2_btree_iter_peek_max(iter, end); if (bkey_gt(iter->pos, end)) return bkey_s_c_null; @@ -746,7 +742,7 @@ transaction_restart: \ _ret2 ?: trans_was_restarted(_trans, _restart_count); \ }) -#define for_each_btree_key_upto_continue(_trans, _iter, \ +#define for_each_btree_key_max_continue(_trans, _iter, \ _end, _flags, _k, _do) \ ({ \ struct bkey_s_c _k; \ @@ -754,7 +750,7 @@ transaction_restart: \ \ do { \ _ret3 = lockrestart_do(_trans, ({ \ - (_k) = bch2_btree_iter_peek_upto_type(&(_iter), \ + (_k) = bch2_btree_iter_peek_max_type(&(_iter), \ _end, (_flags)); \ if (!(_k).k) \ break; \ @@ -768,9 +764,9 @@ transaction_restart: \ }) #define for_each_btree_key_continue(_trans, _iter, _flags, _k, _do) \ - for_each_btree_key_upto_continue(_trans, _iter, SPOS_MAX, _flags, _k, _do) + for_each_btree_key_max_continue(_trans, _iter, SPOS_MAX, _flags, _k, _do) -#define for_each_btree_key_upto(_trans, _iter, _btree_id, \ +#define for_each_btree_key_max(_trans, _iter, _btree_id, \ _start, _end, _flags, _k, _do) \ ({ \ bch2_trans_begin(trans); \ @@ -779,12 +775,12 @@ transaction_restart: \ bch2_trans_iter_init((_trans), &(_iter), (_btree_id), \ (_start), (_flags)); \ \ - for_each_btree_key_upto_continue(_trans, _iter, _end, _flags, _k, _do);\ + for_each_btree_key_max_continue(_trans, _iter, _end, _flags, _k, _do);\ }) #define for_each_btree_key(_trans, _iter, _btree_id, \ _start, _flags, _k, _do) \ - for_each_btree_key_upto(_trans, _iter, _btree_id, _start, \ + for_each_btree_key_max(_trans, _iter, _btree_id, _start, \ SPOS_MAX, _flags, _k, _do) #define for_each_btree_key_reverse(_trans, _iter, _btree_id, \ @@ -828,33 +824,33 @@ transaction_restart: \ (_do) ?: bch2_trans_commit(_trans, (_disk_res),\ (_journal_seq), (_commit_flags))) -#define for_each_btree_key_upto_commit(_trans, _iter, _btree_id, \ +#define for_each_btree_key_max_commit(_trans, _iter, _btree_id, \ _start, _end, _iter_flags, _k, \ _disk_res, _journal_seq, _commit_flags,\ _do) \ - for_each_btree_key_upto(_trans, _iter, _btree_id, _start, _end, _iter_flags, _k,\ + for_each_btree_key_max(_trans, _iter, _btree_id, _start, _end, _iter_flags, _k,\ (_do) ?: bch2_trans_commit(_trans, (_disk_res),\ (_journal_seq), (_commit_flags))) struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *); -#define for_each_btree_key_upto_norestart(_trans, _iter, _btree_id, \ +#define for_each_btree_key_max_norestart(_trans, _iter, _btree_id, \ _start, _end, _flags, _k, _ret) \ for (bch2_trans_iter_init((_trans), &(_iter), (_btree_id), \ (_start), (_flags)); \ - (_k) = bch2_btree_iter_peek_upto_type(&(_iter), _end, _flags),\ + (_k) = bch2_btree_iter_peek_max_type(&(_iter), _end, _flags),\ !((_ret) = bkey_err(_k)) && (_k).k; \ bch2_btree_iter_advance(&(_iter))) -#define for_each_btree_key_upto_continue_norestart(_iter, _end, _flags, _k, _ret)\ +#define for_each_btree_key_max_continue_norestart(_iter, _end, _flags, _k, _ret)\ for (; \ - (_k) = bch2_btree_iter_peek_upto_type(&(_iter), _end, _flags), \ + (_k) = bch2_btree_iter_peek_max_type(&(_iter), _end, _flags), \ !((_ret) = bkey_err(_k)) && (_k).k; \ bch2_btree_iter_advance(&(_iter))) #define for_each_btree_key_norestart(_trans, _iter, _btree_id, \ _start, _flags, _k, _ret) \ - for_each_btree_key_upto_norestart(_trans, _iter, _btree_id, _start,\ + for_each_btree_key_max_norestart(_trans, _iter, _btree_id, _start,\ SPOS_MAX, _flags, _k, _ret) #define for_each_btree_key_reverse_norestart(_trans, _iter, _btree_id, \ @@ -866,7 +862,7 @@ struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *); bch2_btree_iter_rewind(&(_iter))) #define for_each_btree_key_continue_norestart(_iter, _flags, _k, _ret) \ - for_each_btree_key_upto_continue_norestart(_iter, SPOS_MAX, _flags, _k, _ret) + for_each_btree_key_max_continue_norestart(_iter, SPOS_MAX, _flags, _k, _ret) /* * This should not be used in a fastpath, without first trying _do in diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c index c1657182c275..6d25e3f85ce8 100644 --- a/fs/bcachefs/btree_journal_iter.c +++ b/fs/bcachefs/btree_journal_iter.c @@ -16,6 +16,17 @@ * operations for the regular btree iter code to use: */ +static inline size_t pos_to_idx(struct journal_keys *keys, size_t pos) +{ + size_t gap_size = keys->size - keys->nr; + + BUG_ON(pos >= keys->gap && pos < keys->gap + gap_size); + + if (pos >= keys->gap) + pos -= gap_size; + return pos; +} + static inline size_t idx_to_pos(struct journal_keys *keys, size_t idx) { size_t gap_size = keys->size - keys->nr; @@ -61,7 +72,7 @@ static size_t bch2_journal_key_search(struct journal_keys *keys, } /* Returns first non-overwritten key >= search key: */ -struct bkey_i *bch2_journal_keys_peek_upto(struct bch_fs *c, enum btree_id btree_id, +struct bkey_i *bch2_journal_keys_peek_max(struct bch_fs *c, enum btree_id btree_id, unsigned level, struct bpos pos, struct bpos end_pos, size_t *idx) { @@ -84,18 +95,54 @@ search: } } + struct bkey_i *ret = NULL; + rcu_read_lock(); /* for overwritten_ranges */ + while ((k = *idx < keys->nr ? idx_to_key(keys, *idx) : NULL)) { if (__journal_key_cmp(btree_id, level, end_pos, k) < 0) - return NULL; + break; if (k->overwritten) { - (*idx)++; + if (k->overwritten_range) + *idx = rcu_dereference(k->overwritten_range)->end; + else + *idx += 1; continue; } - if (__journal_key_cmp(btree_id, level, pos, k) <= 0) - return k->k; + if (__journal_key_cmp(btree_id, level, pos, k) <= 0) { + ret = k->k; + break; + } + (*idx)++; + iters++; + if (iters == 10) { + *idx = 0; + rcu_read_unlock(); + goto search; + } + } + + rcu_read_unlock(); + return ret; +} + +struct bkey_i *bch2_journal_keys_peek_prev_min(struct bch_fs *c, enum btree_id btree_id, + unsigned level, struct bpos pos, + struct bpos end_pos, size_t *idx) +{ + struct journal_keys *keys = &c->journal_keys; + unsigned iters = 0; + struct journal_key *k; + + BUG_ON(*idx > keys->nr); +search: + if (!*idx) + *idx = __bch2_journal_key_search(keys, btree_id, level, pos); + + while (*idx && + __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) <= 0) { (*idx)++; iters++; if (iters == 10) { @@ -104,7 +151,36 @@ search: } } - return NULL; + struct bkey_i *ret = NULL; + rcu_read_lock(); /* for overwritten_ranges */ + + while ((k = *idx < keys->nr ? idx_to_key(keys, *idx) : NULL)) { + if (__journal_key_cmp(btree_id, level, end_pos, k) > 0) + break; + + if (k->overwritten) { + if (k->overwritten_range) + *idx = rcu_dereference(k->overwritten_range)->start - 1; + else + *idx -= 1; + continue; + } + + if (__journal_key_cmp(btree_id, level, pos, k) >= 0) { + ret = k->k; + break; + } + + --(*idx); + iters++; + if (iters == 10) { + *idx = 0; + goto search; + } + } + + rcu_read_unlock(); + return ret; } struct bkey_i *bch2_journal_keys_peek_slot(struct bch_fs *c, enum btree_id btree_id, @@ -112,11 +188,12 @@ struct bkey_i *bch2_journal_keys_peek_slot(struct bch_fs *c, enum btree_id btree { size_t idx = 0; - return bch2_journal_keys_peek_upto(c, btree_id, level, pos, pos, &idx); + return bch2_journal_keys_peek_max(c, btree_id, level, pos, pos, &idx); } static void journal_iter_verify(struct journal_iter *iter) { +#ifdef CONFIG_BCACHEFS_DEBUG struct journal_keys *keys = iter->keys; size_t gap_size = keys->size - keys->nr; @@ -126,10 +203,10 @@ static void journal_iter_verify(struct journal_iter *iter) if (iter->idx < keys->size) { struct journal_key *k = keys->data + iter->idx; - int cmp = cmp_int(k->btree_id, iter->btree_id) ?: - cmp_int(k->level, iter->level); - BUG_ON(cmp < 0); + int cmp = __journal_key_btree_cmp(iter->btree_id, iter->level, k); + BUG_ON(cmp > 0); } +#endif } static void journal_iters_fix(struct bch_fs *c) @@ -182,7 +259,7 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id, * Ensure these keys are done last by journal replay, to unblock * journal reclaim: */ - .journal_seq = U32_MAX, + .journal_seq = U64_MAX, }; struct journal_keys *keys = &c->journal_keys; size_t idx = bch2_journal_key_search(keys, id, level, k->k.p); @@ -290,6 +367,68 @@ bool bch2_key_deleted_in_journal(struct btree_trans *trans, enum btree_id btree, bkey_deleted(&keys->data[idx].k->k)); } +static void __bch2_journal_key_overwritten(struct journal_keys *keys, size_t pos) +{ + struct journal_key *k = keys->data + pos; + size_t idx = pos_to_idx(keys, pos); + + k->overwritten = true; + + struct journal_key *prev = idx > 0 ? keys->data + idx_to_pos(keys, idx - 1) : NULL; + struct journal_key *next = idx + 1 < keys->nr ? keys->data + idx_to_pos(keys, idx + 1) : NULL; + + bool prev_overwritten = prev && prev->overwritten; + bool next_overwritten = next && next->overwritten; + + struct journal_key_range_overwritten *prev_range = + prev_overwritten ? prev->overwritten_range : NULL; + struct journal_key_range_overwritten *next_range = + next_overwritten ? next->overwritten_range : NULL; + + BUG_ON(prev_range && prev_range->end != idx); + BUG_ON(next_range && next_range->start != idx + 1); + + if (prev_range && next_range) { + prev_range->end = next_range->end; + + keys->data[pos].overwritten_range = prev_range; + for (size_t i = next_range->start; i < next_range->end; i++) { + struct journal_key *ip = keys->data + idx_to_pos(keys, i); + BUG_ON(ip->overwritten_range != next_range); + ip->overwritten_range = prev_range; + } + + kfree_rcu_mightsleep(next_range); + } else if (prev_range) { + prev_range->end++; + k->overwritten_range = prev_range; + if (next_overwritten) { + prev_range->end++; + next->overwritten_range = prev_range; + } + } else if (next_range) { + next_range->start--; + k->overwritten_range = next_range; + if (prev_overwritten) { + next_range->start--; + prev->overwritten_range = next_range; + } + } else if (prev_overwritten || next_overwritten) { + struct journal_key_range_overwritten *r = kmalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return; + + r->start = idx - (size_t) prev_overwritten; + r->end = idx + 1 + (size_t) next_overwritten; + + rcu_assign_pointer(k->overwritten_range, r); + if (prev_overwritten) + prev->overwritten_range = r; + if (next_overwritten) + next->overwritten_range = r; + } +} + void bch2_journal_key_overwritten(struct bch_fs *c, enum btree_id btree, unsigned level, struct bpos pos) { @@ -299,8 +438,12 @@ void bch2_journal_key_overwritten(struct bch_fs *c, enum btree_id btree, if (idx < keys->size && keys->data[idx].btree_id == btree && keys->data[idx].level == level && - bpos_eq(keys->data[idx].k->k.p, pos)) - keys->data[idx].overwritten = true; + bpos_eq(keys->data[idx].k->k.p, pos) && + !keys->data[idx].overwritten) { + mutex_lock(&keys->overwrite_lock); + __bch2_journal_key_overwritten(keys, idx); + mutex_unlock(&keys->overwrite_lock); + } } static void bch2_journal_iter_advance(struct journal_iter *iter) @@ -314,24 +457,32 @@ static void bch2_journal_iter_advance(struct journal_iter *iter) static struct bkey_s_c bch2_journal_iter_peek(struct journal_iter *iter) { + struct bkey_s_c ret = bkey_s_c_null; + journal_iter_verify(iter); + rcu_read_lock(); while (iter->idx < iter->keys->size) { struct journal_key *k = iter->keys->data + iter->idx; - int cmp = cmp_int(k->btree_id, iter->btree_id) ?: - cmp_int(k->level, iter->level); - if (cmp > 0) + int cmp = __journal_key_btree_cmp(iter->btree_id, iter->level, k); + if (cmp < 0) break; BUG_ON(cmp); - if (!k->overwritten) - return bkey_i_to_s_c(k->k); + if (!k->overwritten) { + ret = bkey_i_to_s_c(k->k); + break; + } - bch2_journal_iter_advance(iter); + if (k->overwritten_range) + iter->idx = idx_to_pos(iter->keys, rcu_dereference(k->overwritten_range)->end); + else + bch2_journal_iter_advance(iter); } + rcu_read_unlock(); - return bkey_s_c_null; + return ret; } static void bch2_journal_iter_exit(struct journal_iter *iter) @@ -382,6 +533,7 @@ static void btree_and_journal_iter_prefetch(struct btree_and_journal_iter *_iter : (level > 1 ? 1 : 16); iter.prefetch = false; + iter.fail_if_too_many_whiteouts = true; bch2_bkey_buf_init(&tmp); while (nr--) { @@ -400,6 +552,7 @@ static void btree_and_journal_iter_prefetch(struct btree_and_journal_iter *_iter struct bkey_s_c bch2_btree_and_journal_iter_peek(struct btree_and_journal_iter *iter) { struct bkey_s_c btree_k, journal_k = bkey_s_c_null, ret; + size_t iters = 0; if (iter->prefetch && iter->journal.level) btree_and_journal_iter_prefetch(iter); @@ -407,6 +560,11 @@ again: if (iter->at_end) return bkey_s_c_null; + iters++; + + if (iters > 20 && iter->fail_if_too_many_whiteouts) + return bkey_s_c_null; + while ((btree_k = bch2_journal_iter_peek_btree(iter)).k && bpos_lt(btree_k.k->p, iter->pos)) bch2_journal_iter_advance_btree(iter); @@ -481,16 +639,6 @@ void bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *trans, /* sort and dedup all keys in the journal: */ -void bch2_journal_entries_free(struct bch_fs *c) -{ - struct journal_replay **i; - struct genradix_iter iter; - - genradix_for_each(&c->journal_entries, iter, i) - kvfree(*i); - genradix_free(&c->journal_entries); -} - /* * When keys compare equal, oldest compares first: */ @@ -515,15 +663,26 @@ void bch2_journal_keys_put(struct bch_fs *c) move_gap(keys, keys->nr); - darray_for_each(*keys, i) + darray_for_each(*keys, i) { + if (i->overwritten_range && + (i == &darray_last(*keys) || + i->overwritten_range != i[1].overwritten_range)) + kfree(i->overwritten_range); + if (i->allocated) kfree(i->k); + } kvfree(keys->data); keys->data = NULL; keys->nr = keys->gap = keys->size = 0; - bch2_journal_entries_free(c); + struct journal_replay **i; + struct genradix_iter iter; + + genradix_for_each(&c->journal_entries, iter, i) + kvfree(*i); + genradix_free(&c->journal_entries); } static void __journal_keys_sort(struct journal_keys *keys) @@ -628,8 +787,20 @@ void bch2_journal_keys_dump(struct bch_fs *c) darray_for_each(*keys, i) { printbuf_reset(&buf); + prt_printf(&buf, "btree="); + bch2_btree_id_to_text(&buf, i->btree_id); + prt_printf(&buf, " l=%u ", i->level); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(i->k)); - pr_err("%s l=%u %s", bch2_btree_id_str(i->btree_id), i->level, buf.buf); + pr_err("%s", buf.buf); } printbuf_exit(&buf); } + +void bch2_fs_journal_keys_init(struct bch_fs *c) +{ + struct journal_keys *keys = &c->journal_keys; + + atomic_set(&keys->ref, 1); + keys->initial_ref_held = true; + mutex_init(&keys->overwrite_lock); +} diff --git a/fs/bcachefs/btree_journal_iter.h b/fs/bcachefs/btree_journal_iter.h index 1653de9d609b..2a3082919b8d 100644 --- a/fs/bcachefs/btree_journal_iter.h +++ b/fs/bcachefs/btree_journal_iter.h @@ -26,16 +26,24 @@ struct btree_and_journal_iter { struct bpos pos; bool at_end; bool prefetch; + bool fail_if_too_many_whiteouts; }; +static inline int __journal_key_btree_cmp(enum btree_id l_btree_id, + unsigned l_level, + const struct journal_key *r) +{ + return -cmp_int(l_level, r->level) ?: + cmp_int(l_btree_id, r->btree_id); +} + static inline int __journal_key_cmp(enum btree_id l_btree_id, unsigned l_level, struct bpos l_pos, const struct journal_key *r) { - return (cmp_int(l_btree_id, r->btree_id) ?: - cmp_int(l_level, r->level) ?: - bpos_cmp(l_pos, r->k->k.p)); + return __journal_key_btree_cmp(l_btree_id, l_level, r) ?: + bpos_cmp(l_pos, r->k->k.p); } static inline int journal_key_cmp(const struct journal_key *l, const struct journal_key *r) @@ -43,7 +51,9 @@ static inline int journal_key_cmp(const struct journal_key *l, const struct jour return __journal_key_cmp(l->btree_id, l->level, l->k->k.p, r); } -struct bkey_i *bch2_journal_keys_peek_upto(struct bch_fs *, enum btree_id, +struct bkey_i *bch2_journal_keys_peek_max(struct bch_fs *, enum btree_id, + unsigned, struct bpos, struct bpos, size_t *); +struct bkey_i *bch2_journal_keys_peek_prev_min(struct bch_fs *, enum btree_id, unsigned, struct bpos, struct bpos, size_t *); struct bkey_i *bch2_journal_keys_peek_slot(struct bch_fs *, enum btree_id, unsigned, struct bpos); @@ -79,8 +89,6 @@ static inline void bch2_journal_keys_put_initial(struct bch_fs *c) c->journal_keys.initial_ref_held = false; } -void bch2_journal_entries_free(struct bch_fs *); - int bch2_journal_keys_sort(struct bch_fs *); void bch2_shoot_down_journal_keys(struct bch_fs *, enum btree_id, @@ -89,4 +97,6 @@ void bch2_shoot_down_journal_keys(struct bch_fs *, enum btree_id, void bch2_journal_keys_dump(struct bch_fs *); +void bch2_fs_journal_keys_init(struct bch_fs *); + #endif /* _BCACHEFS_BTREE_JOURNAL_ITER_H */ diff --git a/fs/bcachefs/btree_journal_iter_types.h b/fs/bcachefs/btree_journal_iter_types.h new file mode 100644 index 000000000000..8b773823704f --- /dev/null +++ b/fs/bcachefs/btree_journal_iter_types.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_BTREE_JOURNAL_ITER_TYPES_H +#define _BCACHEFS_BTREE_JOURNAL_ITER_TYPES_H + +struct journal_key_range_overwritten { + size_t start, end; +}; + +struct journal_key { + u64 journal_seq; + u32 journal_offset; + enum btree_id btree_id:8; + unsigned level:8; + bool allocated; + bool overwritten; + struct journal_key_range_overwritten __rcu * + overwritten_range; + struct bkey_i *k; +}; + +struct journal_keys { + /* must match layout in darray_types.h */ + size_t nr, size; + struct journal_key *data; + /* + * Gap buffer: instead of all the empty space in the array being at the + * end of the buffer - from @nr to @size - the empty space is at @gap. + * This means that sequential insertions are O(n) instead of O(n^2). + */ + size_t gap; + atomic_t ref; + bool initial_ref_held; + struct mutex overwrite_lock; +}; + +#endif /* _BCACHEFS_BTREE_JOURNAL_ITER_TYPES_H */ diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 244610b1d0b5..c378b97ebeca 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -197,7 +197,9 @@ out: return ck; } -static int btree_key_cache_create(struct btree_trans *trans, struct btree_path *path, +static int btree_key_cache_create(struct btree_trans *trans, + struct btree_path *path, + struct btree_path *ck_path, struct bkey_s_c k) { struct bch_fs *c = trans->c; @@ -217,7 +219,7 @@ static int btree_key_cache_create(struct btree_trans *trans, struct btree_path * key_u64s = min(256U, (key_u64s * 3) / 2); key_u64s = roundup_pow_of_two(key_u64s); - struct bkey_cached *ck = bkey_cached_alloc(trans, path, key_u64s); + struct bkey_cached *ck = bkey_cached_alloc(trans, ck_path, key_u64s); int ret = PTR_ERR_OR_ZERO(ck); if (ret) return ret; @@ -226,19 +228,19 @@ static int btree_key_cache_create(struct btree_trans *trans, struct btree_path * ck = bkey_cached_reuse(bc); if (unlikely(!ck)) { bch_err(c, "error allocating memory for key cache item, btree %s", - bch2_btree_id_str(path->btree_id)); + bch2_btree_id_str(ck_path->btree_id)); return -BCH_ERR_ENOMEM_btree_key_cache_create; } } ck->c.level = 0; - ck->c.btree_id = path->btree_id; - ck->key.btree_id = path->btree_id; - ck->key.pos = path->pos; + ck->c.btree_id = ck_path->btree_id; + ck->key.btree_id = ck_path->btree_id; + ck->key.pos = ck_path->pos; ck->flags = 1U << BKEY_CACHED_ACCESSED; if (unlikely(key_u64s > ck->u64s)) { - mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED); + mark_btree_node_locked_noreset(ck_path, 0, BTREE_NODE_UNLOCKED); struct bkey_i *new_k = allocate_dropping_locks(trans, ret, kmalloc(key_u64s * sizeof(u64), _gfp)); @@ -258,22 +260,29 @@ static int btree_key_cache_create(struct btree_trans *trans, struct btree_path * bkey_reassemble(ck->k, k); + ret = bch2_btree_node_lock_write(trans, path, &path_l(path)->b->c); + if (unlikely(ret)) + goto err; + ret = rhashtable_lookup_insert_fast(&bc->table, &ck->hash, bch2_btree_key_cache_params); + + bch2_btree_node_unlock_write(trans, path, path_l(path)->b); + if (unlikely(ret)) /* raced with another fill? */ goto err; atomic_long_inc(&bc->nr_keys); six_unlock_write(&ck->c.lock); - enum six_lock_type lock_want = __btree_lock_want(path, 0); + enum six_lock_type lock_want = __btree_lock_want(ck_path, 0); if (lock_want == SIX_LOCK_read) six_lock_downgrade(&ck->c.lock); - btree_path_cached_set(trans, path, ck, (enum btree_node_locked_type) lock_want); - path->uptodate = BTREE_ITER_UPTODATE; + btree_path_cached_set(trans, ck_path, ck, (enum btree_node_locked_type) lock_want); + ck_path->uptodate = BTREE_ITER_UPTODATE; return 0; err: bkey_cached_free(bc, ck); - mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED); + mark_btree_node_locked_noreset(ck_path, 0, BTREE_NODE_UNLOCKED); return ret; } @@ -283,7 +292,7 @@ static noinline int btree_key_cache_fill(struct btree_trans *trans, unsigned flags) { if (flags & BTREE_ITER_cached_nofill) { - ck_path->uptodate = BTREE_ITER_UPTODATE; + ck_path->l[0].b = NULL; return 0; } @@ -293,6 +302,7 @@ static noinline int btree_key_cache_fill(struct btree_trans *trans, int ret; bch2_trans_iter_init(trans, &iter, ck_path->btree_id, ck_path->pos, + BTREE_ITER_intent| BTREE_ITER_key_cache_fill| BTREE_ITER_cached_nofill); iter.flags &= ~BTREE_ITER_with_journal; @@ -306,9 +316,19 @@ static noinline int btree_key_cache_fill(struct btree_trans *trans, if (unlikely(ret)) goto out; - ret = btree_key_cache_create(trans, ck_path, k); + ret = btree_key_cache_create(trans, btree_iter_path(trans, &iter), ck_path, k); if (ret) goto err; + + if (trace_key_cache_fill_enabled()) { + struct printbuf buf = PRINTBUF; + + bch2_bpos_to_text(&buf, ck_path->pos); + prt_char(&buf, ' '); + bch2_bkey_val_to_text(&buf, trans->c, k); + trace_key_cache_fill(trans, buf.buf); + printbuf_exit(&buf); + } out: /* We're not likely to need this iterator again: */ bch2_set_btree_iter_dontneed(&iter); @@ -424,8 +444,15 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans, !test_bit(JOURNAL_space_low, &c->journal.flags)) commit_flags |= BCH_TRANS_COMMIT_no_journal_res; - ret = bch2_btree_iter_traverse(&b_iter) ?: - bch2_trans_update(trans, &b_iter, ck->k, + struct bkey_s_c btree_k = bch2_btree_iter_peek_slot(&b_iter); + ret = bkey_err(btree_k); + if (ret) + goto err; + + /* * Check that we're not violating cache coherency rules: */ + BUG_ON(bkey_deleted(btree_k.k)); + + ret = bch2_trans_update(trans, &b_iter, ck->k, BTREE_UPDATE_key_cache_reclaim| BTREE_UPDATE_internal_snapshot_node| BTREE_TRIGGER_norun) ?: @@ -433,7 +460,7 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans, BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_no_enospc| commit_flags); - +err: bch2_fs_fatal_err_on(ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart) && !bch2_err_matches(ret, BCH_ERR_journal_reclaim_would_deadlock) && @@ -586,8 +613,18 @@ void bch2_btree_key_cache_drop(struct btree_trans *trans, bkey_cached_free(bc, ck); mark_btree_node_locked(trans, path, 0, BTREE_NODE_UNLOCKED); - btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE); - path->should_be_locked = false; + + struct btree_path *path2; + unsigned i; + trans_for_each_path(trans, path2, i) + if (path2->l[0].b == (void *) ck) { + __bch2_btree_path_unlock(trans, path2); + path2->l[0].b = ERR_PTR(-BCH_ERR_no_btree_node_drop); + path2->should_be_locked = false; + btree_path_set_dirty(path2, BTREE_ITER_NEED_TRAVERSE); + } + + bch2_trans_verify_locks(trans); } static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c index efe2a007b482..10b805a60f52 100644 --- a/fs/bcachefs/btree_locking.c +++ b/fs/bcachefs/btree_locking.c @@ -109,6 +109,12 @@ static noinline void lock_graph_pop_all(struct lock_graph *g) lock_graph_up(g); } +static noinline void lock_graph_pop_from(struct lock_graph *g, struct trans_waiting_for_lock *i) +{ + while (g->g + g->nr > i) + lock_graph_up(g); +} + static void __lock_graph_down(struct lock_graph *g, struct btree_trans *trans) { g->g[g->nr++] = (struct trans_waiting_for_lock) { @@ -124,15 +130,20 @@ static void lock_graph_down(struct lock_graph *g, struct btree_trans *trans) __lock_graph_down(g, trans); } -static bool lock_graph_remove_non_waiters(struct lock_graph *g) +static bool lock_graph_remove_non_waiters(struct lock_graph *g, + struct trans_waiting_for_lock *from) { struct trans_waiting_for_lock *i; - for (i = g->g + 1; i < g->g + g->nr; i++) + if (from->trans->locking != from->node_want) { + lock_graph_pop_from(g, from); + return true; + } + + for (i = from + 1; i < g->g + g->nr; i++) if (i->trans->locking != i->node_want || i->trans->locking_wait.start_time != i[-1].lock_start_time) { - while (g->g + g->nr > i) - lock_graph_up(g); + lock_graph_pop_from(g, i); return true; } @@ -179,13 +190,14 @@ static int btree_trans_abort_preference(struct btree_trans *trans) return 3; } -static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle) +static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle, + struct trans_waiting_for_lock *from) { struct trans_waiting_for_lock *i, *abort = NULL; unsigned best = 0, pref; int ret; - if (lock_graph_remove_non_waiters(g)) + if (lock_graph_remove_non_waiters(g, from)) return 0; /* Only checking, for debugfs: */ @@ -195,7 +207,7 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle) goto out; } - for (i = g->g; i < g->g + g->nr; i++) { + for (i = from; i < g->g + g->nr; i++) { pref = btree_trans_abort_preference(i->trans); if (pref > best) { abort = i; @@ -229,8 +241,9 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle) ret = abort_lock(g, abort); out: if (ret) - while (g->nr) - lock_graph_up(g); + lock_graph_pop_all(g); + else + lock_graph_pop_from(g, abort); return ret; } @@ -243,7 +256,7 @@ static int lock_graph_descend(struct lock_graph *g, struct btree_trans *trans, for (i = g->g; i < g->g + g->nr; i++) if (i->trans == trans) { closure_put(&trans->ref); - return break_cycle(g, cycle); + return break_cycle(g, cycle, i); } if (g->nr == ARRAY_SIZE(g->g)) { @@ -252,8 +265,7 @@ static int lock_graph_descend(struct lock_graph *g, struct btree_trans *trans, if (orig_trans->lock_may_not_fail) return 0; - while (g->nr) - lock_graph_up(g); + lock_graph_pop_all(g); if (cycle) return 0; @@ -281,7 +293,7 @@ int bch2_check_for_deadlock(struct btree_trans *trans, struct printbuf *cycle) g.nr = 0; - if (trans->lock_must_abort) { + if (trans->lock_must_abort && !trans->lock_may_not_fail) { if (cycle) return -1; @@ -336,7 +348,7 @@ next: * structures - which means it can't be blocked * waiting on a lock: */ - if (!lock_graph_remove_non_waiters(&g)) { + if (!lock_graph_remove_non_waiters(&g, g.g)) { /* * If lock_graph_remove_non_waiters() * didn't do anything, it must be @@ -512,7 +524,6 @@ bool bch2_btree_node_upgrade(struct btree_trans *trans, struct btree_path *path, unsigned level) { struct btree *b = path->l[level].b; - struct six_lock_count count = bch2_btree_node_lock_counts(trans, path, &b->c, level); if (!is_btree_node(path, level)) return false; @@ -536,24 +547,11 @@ bool bch2_btree_node_upgrade(struct btree_trans *trans, if (race_fault()) return false; - if (btree_node_locked(path, level)) { - bool ret; + if (btree_node_locked(path, level) + ? six_lock_tryupgrade(&b->c.lock) + : six_relock_type(&b->c.lock, SIX_LOCK_intent, path->l[level].lock_seq)) + goto success; - six_lock_readers_add(&b->c.lock, -count.n[SIX_LOCK_read]); - ret = six_lock_tryupgrade(&b->c.lock); - six_lock_readers_add(&b->c.lock, count.n[SIX_LOCK_read]); - - if (ret) - goto success; - } else { - if (six_relock_type(&b->c.lock, SIX_LOCK_intent, path->l[level].lock_seq)) - goto success; - } - - /* - * Do we already have an intent lock via another path? If so, just bump - * lock count: - */ if (btree_node_lock_seq_matches(path, b, level) && btree_node_lock_increment(trans, &b->c, level, BTREE_NODE_INTENT_LOCKED)) { btree_node_unlock(trans, path, level); @@ -782,7 +780,7 @@ static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace) return bch2_trans_relock_fail(trans, path, &f, trace); } - trans_set_locked(trans); + trans_set_locked(trans, true); out: bch2_trans_verify_locks(trans); return 0; @@ -818,6 +816,17 @@ void bch2_trans_unlock_long(struct btree_trans *trans) bch2_trans_srcu_unlock(trans); } +void bch2_trans_unlock_write(struct btree_trans *trans) +{ + struct btree_path *path; + unsigned i; + + trans_for_each_path(trans, path, i) + for (unsigned l = 0; l < BTREE_MAX_DEPTH; l++) + if (btree_node_write_locked(path, l)) + bch2_btree_node_unlock_write(trans, path, path->l[l].b); +} + int __bch2_trans_mutex_lock(struct btree_trans *trans, struct mutex *lock) { @@ -856,6 +865,9 @@ void bch2_btree_path_verify_locks(struct btree_path *path) (want == BTREE_NODE_UNLOCKED || have != BTREE_NODE_WRITE_LOCKED) && want != have); + + BUG_ON(btree_node_locked(path, l) && + path->l[l].lock_seq != six_lock_seq(&path->l[l].b->c.lock)); } } diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h index 7c07f9fa9add..b54ef48eb8cc 100644 --- a/fs/bcachefs/btree_locking.h +++ b/fs/bcachefs/btree_locking.h @@ -16,6 +16,7 @@ void bch2_btree_lock_init(struct btree_bkey_cached_common *, enum six_lock_init_flags); void bch2_trans_unlock_noassert(struct btree_trans *); +void bch2_trans_unlock_write(struct btree_trans *); static inline bool is_btree_node(struct btree_path *path, unsigned l) { @@ -75,13 +76,6 @@ static inline void mark_btree_node_locked_noreset(struct btree_path *path, path->nodes_locked |= (type + 1) << (level << 1); } -static inline void mark_btree_node_unlocked(struct btree_path *path, - unsigned level) -{ - EBUG_ON(btree_node_write_locked(path, level)); - mark_btree_node_locked_noreset(path, level, BTREE_NODE_UNLOCKED); -} - static inline void mark_btree_node_locked(struct btree_trans *trans, struct btree_path *path, unsigned level, @@ -124,19 +118,25 @@ static void btree_trans_lock_hold_time_update(struct btree_trans *trans, /* unlock: */ +void bch2_btree_node_unlock_write(struct btree_trans *, + struct btree_path *, struct btree *); + static inline void btree_node_unlock(struct btree_trans *trans, struct btree_path *path, unsigned level) { int lock_type = btree_node_locked_type(path, level); EBUG_ON(level >= BTREE_MAX_DEPTH); - EBUG_ON(lock_type == BTREE_NODE_WRITE_LOCKED); if (lock_type != BTREE_NODE_UNLOCKED) { + if (unlikely(lock_type == BTREE_NODE_WRITE_LOCKED)) { + bch2_btree_node_unlock_write(trans, path, path->l[level].b); + lock_type = BTREE_NODE_INTENT_LOCKED; + } six_unlock_type(&path->l[level].b->c.lock, lock_type); btree_trans_lock_hold_time_update(trans, path, level); + mark_btree_node_locked_noreset(path, level, BTREE_NODE_UNLOCKED); } - mark_btree_node_unlocked(path, level); } static inline int btree_path_lowest_level_locked(struct btree_path *path) @@ -162,36 +162,40 @@ static inline void __bch2_btree_path_unlock(struct btree_trans *trans, * Updates the saved lock sequence number, so that bch2_btree_node_relock() will * succeed: */ +static inline void +__bch2_btree_node_unlock_write(struct btree_trans *trans, struct btree *b) +{ + if (!b->c.lock.write_lock_recurse) { + struct btree_path *linked; + unsigned i; + + trans_for_each_path_with_node(trans, b, linked, i) + linked->l[b->c.level].lock_seq++; + } + + six_unlock_write(&b->c.lock); +} + static inline void bch2_btree_node_unlock_write_inlined(struct btree_trans *trans, struct btree_path *path, struct btree *b) { - struct btree_path *linked; - unsigned i; - EBUG_ON(path->l[b->c.level].b != b); EBUG_ON(path->l[b->c.level].lock_seq != six_lock_seq(&b->c.lock)); EBUG_ON(btree_node_locked_type(path, b->c.level) != SIX_LOCK_write); mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED); - - trans_for_each_path_with_node(trans, b, linked, i) - linked->l[b->c.level].lock_seq++; - - six_unlock_write(&b->c.lock); + __bch2_btree_node_unlock_write(trans, b); } -void bch2_btree_node_unlock_write(struct btree_trans *, - struct btree_path *, struct btree *); - int bch2_six_check_for_deadlock(struct six_lock *lock, void *p); /* lock: */ -static inline void trans_set_locked(struct btree_trans *trans) +static inline void trans_set_locked(struct btree_trans *trans, bool try) { if (!trans->locked) { - lock_acquire_exclusive(&trans->dep_map, 0, 0, NULL, _THIS_IP_); + lock_acquire_exclusive(&trans->dep_map, 0, try, NULL, _THIS_IP_); trans->locked = true; trans->last_unlock_ip = 0; @@ -282,7 +286,7 @@ static inline int btree_node_lock(struct btree_trans *trans, int ret = 0; EBUG_ON(level >= BTREE_MAX_DEPTH); - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (likely(six_trylock_type(&b->lock, type)) || btree_node_lock_increment(trans, b, level, (enum btree_node_locked_type) type) || diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index 30131c3bdd97..a7f06deee13c 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -12,6 +12,7 @@ #include "recovery_passes.h" #include +#include #include struct find_btree_nodes_worker { @@ -22,17 +23,15 @@ struct find_btree_nodes_worker { static void found_btree_node_to_text(struct printbuf *out, struct bch_fs *c, const struct found_btree_node *n) { - prt_printf(out, "%s l=%u seq=%u journal_seq=%llu cookie=%llx ", - bch2_btree_id_str(n->btree_id), n->level, n->seq, - n->journal_seq, n->cookie); + bch2_btree_id_level_to_text(out, n->btree_id, n->level); + prt_printf(out, " seq=%u journal_seq=%llu cookie=%llx ", + n->seq, n->journal_seq, n->cookie); bch2_bpos_to_text(out, n->min_key); prt_str(out, "-"); bch2_bpos_to_text(out, n->max_key); if (n->range_updated) prt_str(out, " range updated"); - if (n->overwritten) - prt_str(out, " overwritten"); for (unsigned i = 0; i < n->nr_ptrs; i++) { prt_char(out, ' '); @@ -140,6 +139,24 @@ static int found_btree_node_cmp_pos(const void *_l, const void *_r) -found_btree_node_cmp_time(l, r); } +static inline bool found_btree_node_cmp_pos_less(const void *l, const void *r, void *arg) +{ + return found_btree_node_cmp_pos(l, r) < 0; +} + +static inline void found_btree_node_swap(void *_l, void *_r, void *arg) +{ + struct found_btree_node *l = _l; + struct found_btree_node *r = _r; + + swap(*l, *r); +} + +static const struct min_heap_callbacks found_btree_node_heap_cbs = { + .less = found_btree_node_cmp_pos_less, + .swp = found_btree_node_swap, +}; + static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, struct bio *bio, struct btree_node *bn, u64 offset) { @@ -159,6 +176,9 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, return; if (bch2_csum_type_is_encryption(BSET_CSUM_TYPE(&bn->keys))) { + if (!c->chacha20) + return; + struct nonce nonce = btree_nonce(&bn->keys, 0); unsigned bytes = (void *) &bn->keys - (void *) &bn->flags; @@ -292,55 +312,48 @@ err: return f->ret ?: ret; } -static void bubble_up(struct found_btree_node *n, struct found_btree_node *end) +static bool nodes_overlap(const struct found_btree_node *l, + const struct found_btree_node *r) { - while (n + 1 < end && - found_btree_node_cmp_pos(n, n + 1) > 0) { - swap(n[0], n[1]); - n++; - } + return (l->btree_id == r->btree_id && + l->level == r->level && + bpos_gt(l->max_key, r->min_key)); } static int handle_overwrites(struct bch_fs *c, - struct found_btree_node *start, - struct found_btree_node *end) + struct found_btree_node *l, + found_btree_nodes *nodes_heap) { - struct found_btree_node *n; -again: - for (n = start + 1; - n < end && - n->btree_id == start->btree_id && - n->level == start->level && - bpos_lt(n->min_key, start->max_key); - n++) { - int cmp = found_btree_node_cmp_time(start, n); + struct found_btree_node *r; + + while ((r = min_heap_peek(nodes_heap)) && + nodes_overlap(l, r)) { + int cmp = found_btree_node_cmp_time(l, r); if (cmp > 0) { - if (bpos_cmp(start->max_key, n->max_key) >= 0) - n->overwritten = true; + if (bpos_cmp(l->max_key, r->max_key) >= 0) + min_heap_pop(nodes_heap, &found_btree_node_heap_cbs, NULL); else { - n->range_updated = true; - n->min_key = bpos_successor(start->max_key); - n->range_updated = true; - bubble_up(n, end); - goto again; + r->range_updated = true; + r->min_key = bpos_successor(l->max_key); + r->range_updated = true; + min_heap_sift_down(nodes_heap, 0, &found_btree_node_heap_cbs, NULL); } } else if (cmp < 0) { - BUG_ON(bpos_cmp(n->min_key, start->min_key) <= 0); + BUG_ON(bpos_eq(l->min_key, r->min_key)); - start->max_key = bpos_predecessor(n->min_key); - start->range_updated = true; - } else if (n->level) { - n->overwritten = true; + l->max_key = bpos_predecessor(r->min_key); + l->range_updated = true; + } else if (r->level) { + min_heap_pop(nodes_heap, &found_btree_node_heap_cbs, NULL); } else { - if (bpos_cmp(start->max_key, n->max_key) >= 0) - n->overwritten = true; + if (bpos_cmp(l->max_key, r->max_key) >= 0) + min_heap_pop(nodes_heap, &found_btree_node_heap_cbs, NULL); else { - n->range_updated = true; - n->min_key = bpos_successor(start->max_key); - n->range_updated = true; - bubble_up(n, end); - goto again; + r->range_updated = true; + r->min_key = bpos_successor(l->max_key); + r->range_updated = true; + min_heap_sift_down(nodes_heap, 0, &found_btree_node_heap_cbs, NULL); } } } @@ -352,6 +365,7 @@ int bch2_scan_for_btree_nodes(struct bch_fs *c) { struct find_btree_nodes *f = &c->found_btree_nodes; struct printbuf buf = PRINTBUF; + found_btree_nodes nodes_heap = {}; size_t dst; int ret = 0; @@ -406,29 +420,57 @@ int bch2_scan_for_btree_nodes(struct bch_fs *c) bch2_print_string_as_lines(KERN_INFO, buf.buf); } - dst = 0; - darray_for_each(f->nodes, i) { - if (i->overwritten) - continue; + swap(nodes_heap, f->nodes); - ret = handle_overwrites(c, i, &darray_top(f->nodes)); + { + /* darray must have same layout as a heap */ + min_heap_char real_heap; + BUILD_BUG_ON(sizeof(nodes_heap.nr) != sizeof(real_heap.nr)); + BUILD_BUG_ON(sizeof(nodes_heap.size) != sizeof(real_heap.size)); + BUILD_BUG_ON(offsetof(found_btree_nodes, nr) != offsetof(min_heap_char, nr)); + BUILD_BUG_ON(offsetof(found_btree_nodes, size) != offsetof(min_heap_char, size)); + } + + min_heapify_all(&nodes_heap, &found_btree_node_heap_cbs, NULL); + + if (nodes_heap.nr) { + ret = darray_push(&f->nodes, *min_heap_peek(&nodes_heap)); if (ret) goto err; - BUG_ON(i->overwritten); - f->nodes.data[dst++] = *i; + min_heap_pop(&nodes_heap, &found_btree_node_heap_cbs, NULL); } - f->nodes.nr = dst; - if (c->opts.verbose) { + while (true) { + ret = handle_overwrites(c, &darray_last(f->nodes), &nodes_heap); + if (ret) + goto err; + + if (!nodes_heap.nr) + break; + + ret = darray_push(&f->nodes, *min_heap_peek(&nodes_heap)); + if (ret) + goto err; + + min_heap_pop(&nodes_heap, &found_btree_node_heap_cbs, NULL); + } + + for (struct found_btree_node *n = f->nodes.data; n < &darray_last(f->nodes); n++) + BUG_ON(nodes_overlap(n, n + 1)); + + if (0 && c->opts.verbose) { printbuf_reset(&buf); prt_printf(&buf, "%s: nodes found after overwrites:\n", __func__); found_btree_nodes_to_text(&buf, c, f->nodes); bch2_print_string_as_lines(KERN_INFO, buf.buf); + } else { + bch_info(c, "btree node scan found %zu nodes after overwrites", f->nodes.nr); } eytzinger0_sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL); err: + darray_exit(&nodes_heap); printbuf_exit(&buf); return ret; } @@ -499,7 +541,9 @@ int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree, if (c->opts.verbose) { struct printbuf buf = PRINTBUF; - prt_printf(&buf, "recovering %s l=%u ", bch2_btree_id_str(btree), level); + prt_str(&buf, "recovery "); + bch2_btree_id_level_to_text(&buf, btree, level); + prt_str(&buf, " "); bch2_bpos_to_text(&buf, node_min); prt_str(&buf, " - "); bch2_bpos_to_text(&buf, node_max); @@ -533,7 +577,12 @@ int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree, bch_verbose(c, "%s(): recovering %s", __func__, buf.buf); printbuf_exit(&buf); - BUG_ON(bch2_bkey_validate(c, bkey_i_to_s_c(&tmp.k), BKEY_TYPE_btree, 0)); + BUG_ON(bch2_bkey_validate(c, bkey_i_to_s_c(&tmp.k), + (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = level + 1, + .btree = btree, + })); ret = bch2_journal_key_insert(c, btree, level + 1, &tmp.k); if (ret) diff --git a/fs/bcachefs/btree_node_scan_types.h b/fs/bcachefs/btree_node_scan_types.h index b6c36c45d0be..2811b6857c97 100644 --- a/fs/bcachefs/btree_node_scan_types.h +++ b/fs/bcachefs/btree_node_scan_types.h @@ -6,7 +6,6 @@ struct found_btree_node { bool range_updated:1; - bool overwritten:1; u8 btree_id; u8 level; unsigned sectors_written; diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index 9bf471fa4361..2760dd9569ed 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -133,7 +133,7 @@ static inline int bch2_trans_lock_write(struct btree_trans *trans) return 0; } -static inline void bch2_trans_unlock_write(struct btree_trans *trans) +static inline void bch2_trans_unlock_updates_write(struct btree_trans *trans) { if (likely(trans->write_locked)) { trans_for_each_update(trans, i) @@ -249,7 +249,7 @@ static int __btree_node_flush(struct journal *j, struct journal_entry_pin *pin, new |= 1 << BTREE_NODE_need_write; } while (!try_cmpxchg(&b->flags, &old, new)); - btree_node_write_if_need(c, b, SIX_LOCK_read); + btree_node_write_if_need(trans, b, SIX_LOCK_read); six_unlock_read(&b->c.lock); bch2_trans_put(trans); @@ -348,7 +348,7 @@ static __always_inline int bch2_trans_journal_res_get(struct btree_trans *trans, unsigned flags) { return bch2_journal_res_get(&trans->c->journal, &trans->journal_res, - trans->journal_u64s, flags); + trans->journal_u64s, flags, trans); } #define JSET_ENTRY_LOG_U64s 4 @@ -384,7 +384,7 @@ btree_key_can_insert_cached_slowpath(struct btree_trans *trans, unsigned flags, struct bkey_i *new_k; int ret; - bch2_trans_unlock_write(trans); + bch2_trans_unlock_updates_write(trans); bch2_trans_unlock(trans); new_k = kmalloc(new_u64s * sizeof(u64), GFP_KERNEL); @@ -479,8 +479,7 @@ static int run_one_mem_trigger(struct btree_trans *trans, old, flags); } -static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_entry *i, - bool overwrite) +static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_entry *i) { verify_update_old_key(trans, i); @@ -507,10 +506,10 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_ return bch2_key_trigger(trans, i->btree_id, i->level, old, bkey_i_to_s(i->k), BTREE_TRIGGER_insert| BTREE_TRIGGER_overwrite|flags) ?: 1; - } else if (overwrite && !i->overwrite_trigger_run) { + } else if (!i->overwrite_trigger_run) { i->overwrite_trigger_run = true; return bch2_key_trigger_old(trans, i->btree_id, i->level, old, flags) ?: 1; - } else if (!overwrite && !i->insert_trigger_run) { + } else if (!i->insert_trigger_run) { i->insert_trigger_run = true; return bch2_key_trigger_new(trans, i->btree_id, i->level, bkey_i_to_s(i->k), flags) ?: 1; } else { @@ -519,39 +518,45 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_ } static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, - unsigned btree_id_start) + unsigned *btree_id_updates_start) { - for (int overwrite = 1; overwrite >= 0; --overwrite) { - bool trans_trigger_run; + bool trans_trigger_run; - /* - * Running triggers will append more updates to the list of updates as - * we're walking it: - */ - do { - trans_trigger_run = false; + /* + * Running triggers will append more updates to the list of updates as + * we're walking it: + */ + do { + trans_trigger_run = false; - for (unsigned i = btree_id_start; - i < trans->nr_updates && trans->updates[i].btree_id <= btree_id; - i++) { - if (trans->updates[i].btree_id != btree_id) - continue; - - int ret = run_one_trans_trigger(trans, trans->updates + i, overwrite); - if (ret < 0) - return ret; - if (ret) - trans_trigger_run = true; + for (unsigned i = *btree_id_updates_start; + i < trans->nr_updates && trans->updates[i].btree_id <= btree_id; + i++) { + if (trans->updates[i].btree_id < btree_id) { + *btree_id_updates_start = i; + continue; } - } while (trans_trigger_run); - } + + int ret = run_one_trans_trigger(trans, trans->updates + i); + if (ret < 0) + return ret; + if (ret) + trans_trigger_run = true; + } + } while (trans_trigger_run); + + trans_for_each_update(trans, i) + BUG_ON(!(i->flags & BTREE_TRIGGER_norun) && + i->btree_id == btree_id && + btree_node_type_has_trans_triggers(i->bkey_type) && + (!i->insert_trigger_run || !i->overwrite_trigger_run)); return 0; } static int bch2_trans_commit_run_triggers(struct btree_trans *trans) { - unsigned btree_id = 0, btree_id_start = 0; + unsigned btree_id = 0, btree_id_updates_start = 0; int ret = 0; /* @@ -565,27 +570,15 @@ static int bch2_trans_commit_run_triggers(struct btree_trans *trans) if (btree_id == BTREE_ID_alloc) continue; - while (btree_id_start < trans->nr_updates && - trans->updates[btree_id_start].btree_id < btree_id) - btree_id_start++; - - ret = run_btree_triggers(trans, btree_id, btree_id_start); + ret = run_btree_triggers(trans, btree_id, &btree_id_updates_start); if (ret) return ret; } - for (unsigned idx = 0; idx < trans->nr_updates; idx++) { - struct btree_insert_entry *i = trans->updates + idx; - - if (i->btree_id > BTREE_ID_alloc) - break; - if (i->btree_id == BTREE_ID_alloc) { - ret = run_btree_triggers(trans, BTREE_ID_alloc, idx); - if (ret) - return ret; - break; - } - } + btree_id_updates_start = 0; + ret = run_btree_triggers(trans, BTREE_ID_alloc, &btree_id_updates_start); + if (ret) + return ret; #ifdef CONFIG_BCACHEFS_DEBUG trans_for_each_update(trans, i) @@ -609,14 +602,6 @@ static noinline int bch2_trans_commit_run_gc_triggers(struct btree_trans *trans) return 0; } -static struct bversion journal_pos_to_bversion(struct journal_res *res, unsigned offset) -{ - return (struct bversion) { - .hi = res->seq >> 32, - .lo = (res->seq << 32) | (res->offset + offset), - }; -} - static inline int bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, struct btree_insert_entry **stopped_at, @@ -627,12 +612,11 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, unsigned u64s = 0; int ret = 0; - bch2_trans_verify_not_unlocked(trans); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (race_fault()) { trace_and_count(c, trans_restart_fault_inject, trans, trace_ip); - return btree_trans_restart_nounlock(trans, BCH_ERR_transaction_restart_fault_inject); + return btree_trans_restart(trans, BCH_ERR_transaction_restart_fault_inject); } /* @@ -701,25 +685,14 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, struct jset_entry *entry = trans->journal_entries; percpu_down_read(&c->mark_lock); - for (entry = trans->journal_entries; entry != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); entry = vstruct_next(entry)) if (entry->type == BCH_JSET_ENTRY_write_buffer_keys && entry->start->k.type == KEY_TYPE_accounting) { - BUG_ON(!trans->journal_res.ref); - - struct bkey_i_accounting *a = bkey_i_to_accounting(entry->start); - - a->k.bversion = journal_pos_to_bversion(&trans->journal_res, - (u64 *) entry - (u64 *) trans->journal_entries); - BUG_ON(bversion_zero(a->k.bversion)); - - if (likely(!(flags & BCH_TRANS_COMMIT_skip_accounting_apply))) { - ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal); - if (ret) - goto revert_fs_usage; - } + ret = bch2_accounting_trans_commit_hook(trans, bkey_i_to_accounting(entry->start), flags); + if (ret) + goto revert_fs_usage; } percpu_up_read(&c->mark_lock); @@ -739,14 +712,29 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, goto fatal_err; } + struct bkey_validate_context validate_context = { .from = BKEY_VALIDATE_commit }; + + if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) + validate_context.flags = BCH_VALIDATE_write|BCH_VALIDATE_commit; + + for (struct jset_entry *i = trans->journal_entries; + i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); + i = vstruct_next(i)) { + ret = bch2_journal_entry_validate(c, NULL, i, + bcachefs_metadata_version_current, + CPU_BIG_ENDIAN, validate_context); + if (unlikely(ret)) { + bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n", + trans->fn); + goto fatal_err; + } + } + trans_for_each_update(trans, i) { - enum bch_validate_flags invalid_flags = 0; + validate_context.level = i->level; + validate_context.btree = i->btree_id; - if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) - invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - - ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), - i->bkey_type, invalid_flags); + ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), validate_context); if (unlikely(ret)){ bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n", trans->fn, (void *) i->ip_allocated); @@ -755,24 +743,6 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, btree_insert_entry_checks(trans, i); } - for (struct jset_entry *i = trans->journal_entries; - i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); - i = vstruct_next(i)) { - enum bch_validate_flags invalid_flags = 0; - - if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) - invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - - ret = bch2_journal_entry_validate(c, NULL, i, - bcachefs_metadata_version_current, - CPU_BIG_ENDIAN, invalid_flags); - if (unlikely(ret)) { - bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n", - trans->fn); - goto fatal_err; - } - } - if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) { struct journal *j = &c->journal; struct jset_entry *entry; @@ -833,13 +803,9 @@ revert_fs_usage: entry2 != entry; entry2 = vstruct_next(entry2)) if (entry2->type == BCH_JSET_ENTRY_write_buffer_keys && - entry2->start->k.type == KEY_TYPE_accounting) { - struct bkey_s_accounting a = bkey_i_to_s_accounting(entry2->start); - - bch2_accounting_neg(a); - bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal); - bch2_accounting_neg(a); - } + entry2->start->k.type == KEY_TYPE_accounting) + bch2_accounting_trans_commit_revert(trans, + bkey_i_to_accounting(entry2->start), flags); percpu_up_read(&c->mark_lock); return ret; } @@ -902,7 +868,7 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags if (!ret && unlikely(trans->journal_replay_not_finished)) bch2_drop_overwrites_from_journal(trans); - bch2_trans_unlock_write(trans); + bch2_trans_unlock_updates_write(trans); if (!ret && trans->journal_pin) bch2_journal_pin_add(&c->journal, trans->journal_res.seq, @@ -994,24 +960,6 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags, return ret; } -static noinline int -bch2_trans_commit_get_rw_cold(struct btree_trans *trans, unsigned flags) -{ - struct bch_fs *c = trans->c; - int ret; - - if (likely(!(flags & BCH_TRANS_COMMIT_lazy_rw)) || - test_bit(BCH_FS_started, &c->flags)) - return -BCH_ERR_erofs_trans_commit; - - ret = drop_locks_do(trans, bch2_fs_read_write_early(c)); - if (ret) - return ret; - - bch2_write_ref_get(c, BCH_WRITE_REF_trans); - return 0; -} - /* * This is for updates done in the early part of fsck - btree_gc - before we've * gone RW. we only add the new key to the list of keys for journal replay to @@ -1022,6 +970,8 @@ do_bch2_trans_commit_to_journal_replay(struct btree_trans *trans) { struct bch_fs *c = trans->c; + BUG_ON(current != c->recovery_task); + trans_for_each_update(trans, i) { int ret = bch2_journal_key_insert(c, i->btree_id, i->level, i->k); if (ret) @@ -1047,8 +997,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) struct bch_fs *c = trans->c; int ret = 0; - bch2_trans_verify_not_unlocked(trans); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (!trans->nr_updates && !trans->journal_entries_u64s) @@ -1058,16 +1007,13 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) if (ret) goto out_reset; - if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) { - ret = do_bch2_trans_commit_to_journal_replay(trans); - goto out_reset; - } - if (!(flags & BCH_TRANS_COMMIT_no_check_rw) && unlikely(!bch2_write_ref_tryget(c, BCH_WRITE_REF_trans))) { - ret = bch2_trans_commit_get_rw_cold(trans, flags); - if (ret) - goto out_reset; + if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) + ret = do_bch2_trans_commit_to_journal_replay(trans); + else + ret = -BCH_ERR_erofs_trans_commit; + goto out_reset; } EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags)); @@ -1112,8 +1058,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) } retry: errored_at = NULL; - bch2_trans_verify_not_unlocked(trans); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) memset(&trans->journal_res, 0, sizeof(trans->journal_res)); memset(&trans->fs_usage_delta, 0, sizeof(trans->fs_usage_delta)); diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index 4568a41fefaf..a6f251eb4164 100644 --- a/fs/bcachefs/btree_types.h +++ b/fs/bcachefs/btree_types.h @@ -513,6 +513,9 @@ struct btree_trans { u64 last_begin_time; unsigned long last_begin_ip; unsigned long last_restarted_ip; +#ifdef CONFIG_BCACHEFS_DEBUG + bch_stacktrace last_restarted_trace; +#endif unsigned long last_unlock_ip; unsigned long srcu_lock_time; @@ -787,53 +790,64 @@ static inline bool btree_node_type_has_triggers(enum btree_node_type type) return BIT_ULL(type) & BTREE_NODE_TYPE_HAS_TRIGGERS; } -static inline bool btree_node_type_is_extents(enum btree_node_type type) -{ - const u64 mask = 0 -#define x(name, nr, flags, ...) |((!!((flags) & BTREE_ID_EXTENTS)) << (nr + 1)) - BCH_BTREE_IDS() -#undef x - ; - - return BIT_ULL(type) & mask; -} - static inline bool btree_id_is_extents(enum btree_id btree) -{ - return btree_node_type_is_extents(__btree_node_type(0, btree)); -} - -static inline bool btree_type_has_snapshots(enum btree_id id) { const u64 mask = 0 -#define x(name, nr, flags, ...) |((!!((flags) & BTREE_ID_SNAPSHOTS)) << nr) +#define x(name, nr, flags, ...) |((!!((flags) & BTREE_IS_extents)) << nr) BCH_BTREE_IDS() #undef x ; - return BIT_ULL(id) & mask; + return BIT_ULL(btree) & mask; } -static inline bool btree_type_has_snapshot_field(enum btree_id id) +static inline bool btree_node_type_is_extents(enum btree_node_type type) +{ + return type != BKEY_TYPE_btree && btree_id_is_extents(type - 1); +} + +static inline bool btree_type_has_snapshots(enum btree_id btree) { const u64 mask = 0 -#define x(name, nr, flags, ...) |((!!((flags) & (BTREE_ID_SNAPSHOT_FIELD|BTREE_ID_SNAPSHOTS))) << nr) +#define x(name, nr, flags, ...) |((!!((flags) & BTREE_IS_snapshots)) << nr) BCH_BTREE_IDS() #undef x ; - return BIT_ULL(id) & mask; + return BIT_ULL(btree) & mask; } -static inline bool btree_type_has_ptrs(enum btree_id id) +static inline bool btree_type_has_snapshot_field(enum btree_id btree) { const u64 mask = 0 -#define x(name, nr, flags, ...) |((!!((flags) & BTREE_ID_DATA)) << nr) +#define x(name, nr, flags, ...) |((!!((flags) & (BTREE_IS_snapshot_field|BTREE_IS_snapshots))) << nr) BCH_BTREE_IDS() #undef x ; - return BIT_ULL(id) & mask; + return BIT_ULL(btree) & mask; +} + +static inline bool btree_type_has_ptrs(enum btree_id btree) +{ + const u64 mask = 0 +#define x(name, nr, flags, ...) |((!!((flags) & BTREE_IS_data)) << nr) + BCH_BTREE_IDS() +#undef x + ; + + return BIT_ULL(btree) & mask; +} + +static inline bool btree_type_uses_write_buffer(enum btree_id btree) +{ + const u64 mask = 0 +#define x(name, nr, flags, ...) |((!!((flags) & BTREE_IS_write_buffer)) << nr) + BCH_BTREE_IDS() +#undef x + ; + + return BIT_ULL(btree) & mask; } struct btree_root { diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c index 5d809e8bd170..13d794f201a5 100644 --- a/fs/bcachefs/btree_update.c +++ b/fs/bcachefs/btree_update.c @@ -144,7 +144,7 @@ int __bch2_insert_snapshot_whiteouts(struct btree_trans *trans, !(ret = bkey_err(old_k)) && bkey_eq(old_pos, old_k.k->p)) { struct bpos whiteout_pos = - SPOS(new_pos.inode, new_pos.offset, old_k.k->p.snapshot);; + SPOS(new_pos.inode, new_pos.offset, old_k.k->p.snapshot); if (!bch2_snapshot_is_ancestor(c, old_k.k->p.snapshot, old_pos.snapshot) || snapshot_list_has_ancestor(c, &s, old_k.k->p.snapshot)) @@ -296,7 +296,7 @@ static int bch2_trans_update_extent(struct btree_trans *trans, BTREE_ITER_intent| BTREE_ITER_with_updates| BTREE_ITER_not_extents); - k = bch2_btree_iter_peek_upto(&iter, POS(insert->k.p.inode, U64_MAX)); + k = bch2_btree_iter_peek_max(&iter, POS(insert->k.p.inode, U64_MAX)); if ((ret = bkey_err(k))) goto err; if (!k.k) @@ -323,7 +323,7 @@ static int bch2_trans_update_extent(struct btree_trans *trans, goto out; next: bch2_btree_iter_advance(&iter); - k = bch2_btree_iter_peek_upto(&iter, POS(insert->k.p.inode, U64_MAX)); + k = bch2_btree_iter_peek_max(&iter, POS(insert->k.p.inode, U64_MAX)); if ((ret = bkey_err(k))) goto err; if (!k.k) @@ -588,12 +588,9 @@ struct jset_entry *__bch2_trans_jset_entry_alloc(struct btree_trans *trans, unsi int bch2_bkey_get_empty_slot(struct btree_trans *trans, struct btree_iter *iter, enum btree_id btree, struct bpos end) { - struct bkey_s_c k; - int ret = 0; - - bch2_trans_iter_init(trans, iter, btree, POS_MAX, BTREE_ITER_intent); - k = bch2_btree_iter_prev(iter); - ret = bkey_err(k); + bch2_trans_iter_init(trans, iter, btree, end, BTREE_ITER_intent); + struct bkey_s_c k = bch2_btree_iter_peek_prev(iter); + int ret = bkey_err(k); if (ret) goto err; @@ -672,25 +669,17 @@ int bch2_btree_insert(struct bch_fs *c, enum btree_id id, struct bkey_i *k, bch2_btree_insert_trans(trans, id, k, iter_flags)); } -int bch2_btree_delete_extent_at(struct btree_trans *trans, struct btree_iter *iter, - unsigned len, unsigned update_flags) -{ - struct bkey_i *k; - - k = bch2_trans_kmalloc(trans, sizeof(*k)); - if (IS_ERR(k)) - return PTR_ERR(k); - - bkey_init(&k->k); - k->k.p = iter->pos; - bch2_key_resize(&k->k, len); - return bch2_trans_update(trans, iter, k, update_flags); -} - int bch2_btree_delete_at(struct btree_trans *trans, struct btree_iter *iter, unsigned update_flags) { - return bch2_btree_delete_extent_at(trans, iter, 0, update_flags); + struct bkey_i *k = bch2_trans_kmalloc(trans, sizeof(*k)); + int ret = PTR_ERR_OR_ZERO(k); + if (ret) + return ret; + + bkey_init(&k->k); + k->k.p = iter->pos; + return bch2_trans_update(trans, iter, k, update_flags); } int bch2_btree_delete(struct btree_trans *trans, @@ -721,7 +710,7 @@ int bch2_btree_delete_range_trans(struct btree_trans *trans, enum btree_id id, int ret = 0; bch2_trans_iter_init(trans, &iter, id, start, BTREE_ITER_intent); - while ((k = bch2_btree_iter_peek_upto(&iter, end)).k) { + while ((k = bch2_btree_iter_peek_max(&iter, end)).k) { struct disk_reservation disk_res = bch2_disk_reservation_init(trans->c, 0); struct bkey_i delete; @@ -794,8 +783,7 @@ int bch2_btree_delete_range(struct bch_fs *c, enum btree_id id, return ret; } -int bch2_btree_bit_mod(struct btree_trans *trans, enum btree_id btree, - struct bpos pos, bool set) +int bch2_btree_bit_mod_iter(struct btree_trans *trans, struct btree_iter *iter, bool set) { struct bkey_i *k = bch2_trans_kmalloc(trans, sizeof(*k)); int ret = PTR_ERR_OR_ZERO(k); @@ -804,13 +792,21 @@ int bch2_btree_bit_mod(struct btree_trans *trans, enum btree_id btree, bkey_init(&k->k); k->k.type = set ? KEY_TYPE_set : KEY_TYPE_deleted; - k->k.p = pos; + k->k.p = iter->pos; + if (iter->flags & BTREE_ITER_is_extents) + bch2_key_resize(&k->k, 1); + return bch2_trans_update(trans, iter, k, 0); +} + +int bch2_btree_bit_mod(struct btree_trans *trans, enum btree_id btree, + struct bpos pos, bool set) +{ struct btree_iter iter; bch2_trans_iter_init(trans, &iter, btree, pos, BTREE_ITER_intent); - ret = bch2_btree_iter_traverse(&iter) ?: - bch2_trans_update(trans, &iter, k, 0); + int ret = bch2_btree_iter_traverse(&iter) ?: + bch2_btree_bit_mod_iter(trans, &iter, set); bch2_trans_iter_exit(trans, &iter); return ret; } @@ -827,10 +823,17 @@ int bch2_btree_bit_mod_buffered(struct btree_trans *trans, enum btree_id btree, return bch2_trans_update_buffered(trans, btree, &k); } -static int __bch2_trans_log_msg(struct btree_trans *trans, struct printbuf *buf, unsigned u64s) +int bch2_trans_log_msg(struct btree_trans *trans, struct printbuf *buf) { + unsigned u64s = DIV_ROUND_UP(buf->pos, sizeof(u64)); + prt_chars(buf, '\0', u64s * sizeof(u64) - buf->pos); + + int ret = buf->allocation_failure ? -BCH_ERR_ENOMEM_trans_log_msg : 0; + if (ret) + return ret; + struct jset_entry *e = bch2_trans_jset_entry_alloc(trans, jset_u64s(u64s)); - int ret = PTR_ERR_OR_ZERO(e); + ret = PTR_ERR_OR_ZERO(e); if (ret) return ret; @@ -865,9 +868,8 @@ __bch2_fs_log_msg(struct bch_fs *c, unsigned commit_flags, const char *fmt, memcpy(l->d, buf.buf, buf.pos); c->journal.early_journal_entries.nr += jset_u64s(u64s); } else { - ret = bch2_trans_commit_do(c, NULL, NULL, - BCH_TRANS_COMMIT_lazy_rw|commit_flags, - __bch2_trans_log_msg(trans, &buf, u64s)); + ret = bch2_trans_commit_do(c, NULL, NULL, commit_flags, + bch2_trans_log_msg(trans, &buf)); } err: printbuf_exit(&buf); diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h index 70b3c989fac2..8f22ef9a7651 100644 --- a/fs/bcachefs/btree_update.h +++ b/fs/bcachefs/btree_update.h @@ -24,7 +24,6 @@ void bch2_btree_insert_key_leaf(struct btree_trans *, struct btree_path *, #define BCH_TRANS_COMMIT_FLAGS() \ x(no_enospc, "don't check for enospc") \ x(no_check_rw, "don't attempt to take a ref on c->writes") \ - x(lazy_rw, "go read-write if we haven't yet - only for use in recovery") \ x(no_journal_res, "don't take a journal reservation, instead " \ "pin journal entry referred to by trans->journal_res.seq") \ x(journal_reclaim, "operation required for journal reclaim; may return error" \ @@ -47,8 +46,6 @@ enum bch_trans_commit_flags { void bch2_trans_commit_flags_to_text(struct printbuf *, enum bch_trans_commit_flags); -int bch2_btree_delete_extent_at(struct btree_trans *, struct btree_iter *, - unsigned, unsigned); int bch2_btree_delete_at(struct btree_trans *, struct btree_iter *, unsigned); int bch2_btree_delete(struct btree_trans *, enum btree_id, struct bpos, unsigned); @@ -66,6 +63,7 @@ int bch2_btree_delete_range_trans(struct btree_trans *, enum btree_id, int bch2_btree_delete_range(struct bch_fs *, enum btree_id, struct bpos, struct bpos, unsigned, u64 *); +int bch2_btree_bit_mod_iter(struct btree_trans *, struct btree_iter *, bool); int bch2_btree_bit_mod(struct btree_trans *, enum btree_id, struct bpos, bool); int bch2_btree_bit_mod_buffered(struct btree_trans *, enum btree_id, struct bpos, bool); @@ -161,6 +159,7 @@ void bch2_trans_commit_hook(struct btree_trans *, struct btree_trans_commit_hook *); int __bch2_trans_commit(struct btree_trans *, unsigned); +int bch2_trans_log_msg(struct btree_trans *, struct printbuf *); __printf(2, 3) int bch2_fs_log_msg(struct bch_fs *, const char *, ...); __printf(2, 3) int bch2_journal_log_msg(struct bch_fs *, const char *, ...); @@ -244,7 +243,8 @@ static inline struct bkey_i *bch2_bkey_make_mut_noupdate(struct btree_trans *tra KEY_TYPE_##_type, sizeof(struct bkey_i_##_type))) static inline struct bkey_i *__bch2_bkey_make_mut(struct btree_trans *trans, struct btree_iter *iter, - struct bkey_s_c *k, unsigned flags, + struct bkey_s_c *k, + enum btree_iter_update_trigger_flags flags, unsigned type, unsigned min_bytes) { struct bkey_i *mut = __bch2_bkey_make_mut_noupdate(trans, *k, type, min_bytes); @@ -261,8 +261,9 @@ static inline struct bkey_i *__bch2_bkey_make_mut(struct btree_trans *trans, str return mut; } -static inline struct bkey_i *bch2_bkey_make_mut(struct btree_trans *trans, struct btree_iter *iter, - struct bkey_s_c *k, unsigned flags) +static inline struct bkey_i *bch2_bkey_make_mut(struct btree_trans *trans, + struct btree_iter *iter, struct bkey_s_c *k, + enum btree_iter_update_trigger_flags flags) { return __bch2_bkey_make_mut(trans, iter, k, flags, 0, 0); } @@ -274,7 +275,8 @@ static inline struct bkey_i *bch2_bkey_make_mut(struct btree_trans *trans, struc static inline struct bkey_i *__bch2_bkey_get_mut_noupdate(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags, unsigned type, unsigned min_bytes) + enum btree_iter_update_trigger_flags flags, + unsigned type, unsigned min_bytes) { struct bkey_s_c k = __bch2_bkey_get_iter(trans, iter, btree_id, pos, flags|BTREE_ITER_intent, type); @@ -289,7 +291,7 @@ static inline struct bkey_i *__bch2_bkey_get_mut_noupdate(struct btree_trans *tr static inline struct bkey_i *bch2_bkey_get_mut_noupdate(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags) + enum btree_iter_update_trigger_flags flags) { return __bch2_bkey_get_mut_noupdate(trans, iter, btree_id, pos, flags, 0, 0); } @@ -297,7 +299,8 @@ static inline struct bkey_i *bch2_bkey_get_mut_noupdate(struct btree_trans *tran static inline struct bkey_i *__bch2_bkey_get_mut(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags, unsigned type, unsigned min_bytes) + enum btree_iter_update_trigger_flags flags, + unsigned type, unsigned min_bytes) { struct bkey_i *mut = __bch2_bkey_get_mut_noupdate(trans, iter, btree_id, pos, flags|BTREE_ITER_intent, type, min_bytes); @@ -318,7 +321,8 @@ static inline struct bkey_i *__bch2_bkey_get_mut(struct btree_trans *trans, static inline struct bkey_i *bch2_bkey_get_mut_minsize(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags, unsigned min_bytes) + enum btree_iter_update_trigger_flags flags, + unsigned min_bytes) { return __bch2_bkey_get_mut(trans, iter, btree_id, pos, flags, 0, min_bytes); } @@ -326,7 +330,7 @@ static inline struct bkey_i *bch2_bkey_get_mut_minsize(struct btree_trans *trans static inline struct bkey_i *bch2_bkey_get_mut(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags) + enum btree_iter_update_trigger_flags flags) { return __bch2_bkey_get_mut(trans, iter, btree_id, pos, flags, 0, 0); } @@ -337,7 +341,8 @@ static inline struct bkey_i *bch2_bkey_get_mut(struct btree_trans *trans, KEY_TYPE_##_type, sizeof(struct bkey_i_##_type))) static inline struct bkey_i *__bch2_bkey_alloc(struct btree_trans *trans, struct btree_iter *iter, - unsigned flags, unsigned type, unsigned val_size) + enum btree_iter_update_trigger_flags flags, + unsigned type, unsigned val_size) { struct bkey_i *k = bch2_trans_kmalloc(trans, sizeof(*k) + val_size); int ret; diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index d596ef93239f..f4aeadbe53c1 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -58,11 +58,15 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key, b->data->min_key)); + bch2_bkey_buf_init(&prev); + bkey_init(&prev.k->k); + bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); + if (b == btree_node_root(c, b)) { if (!bpos_eq(b->data->min_key, POS_MIN)) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->data->min_key); - need_fsck_err(trans, btree_root_bad_min_key, + log_fsck_err(trans, btree_root_bad_min_key, "btree root with incorrect min_key: %s", buf.buf); goto topology_repair; } @@ -70,18 +74,14 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) if (!bpos_eq(b->data->max_key, SPOS_MAX)) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->data->max_key); - need_fsck_err(trans, btree_root_bad_max_key, + log_fsck_err(trans, btree_root_bad_max_key, "btree root with incorrect max_key: %s", buf.buf); goto topology_repair; } } if (!b->c.level) - return 0; - - bch2_bkey_buf_init(&prev); - bkey_init(&prev.k->k); - bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); + goto out; while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) { if (k.k->type != KEY_TYPE_btree_ptr_v2) @@ -97,16 +97,16 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) bch2_topology_error(c); printbuf_reset(&buf); - prt_str(&buf, "end of prev node doesn't match start of next node\n"), - prt_printf(&buf, " in btree %s level %u node ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_str(&buf, "end of prev node doesn't match start of next node\n in "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, " node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n prev "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); prt_str(&buf, "\n next "); bch2_bkey_val_to_text(&buf, c, k); - need_fsck_err(trans, btree_node_topology_bad_min_key, "%s", buf.buf); + log_fsck_err(trans, btree_node_topology_bad_min_key, "%s", buf.buf); goto topology_repair; } @@ -118,25 +118,25 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) bch2_topology_error(c); printbuf_reset(&buf); - prt_str(&buf, "empty interior node\n"); - prt_printf(&buf, " in btree %s level %u node ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_str(&buf, "empty interior node\n in "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, " node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); - need_fsck_err(trans, btree_node_topology_empty_interior_node, "%s", buf.buf); + log_fsck_err(trans, btree_node_topology_empty_interior_node, "%s", buf.buf); goto topology_repair; } else if (!bpos_eq(prev.k->k.p, b->key.k.p)) { bch2_topology_error(c); printbuf_reset(&buf); - prt_str(&buf, "last child node doesn't end at end of parent node\n"); - prt_printf(&buf, " in btree %s level %u node ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_str(&buf, "last child node doesn't end at end of parent node\n in "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, " node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n last key "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); - need_fsck_err(trans, btree_node_topology_bad_max_key, "%s", buf.buf); + log_fsck_err(trans, btree_node_topology_bad_max_key, "%s", buf.buf); goto topology_repair; } out: @@ -146,13 +146,7 @@ fsck_err: printbuf_exit(&buf); return ret; topology_repair: - if ((c->opts.recovery_passes & BIT_ULL(BCH_RECOVERY_PASS_check_topology)) && - c->curr_recovery_pass > BCH_RECOVERY_PASS_check_topology) { - bch2_inconsistent_error(c); - ret = -BCH_ERR_btree_need_topology_repair; - } else { - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology); - } + ret = bch2_topology_error(c); goto out; } @@ -244,7 +238,6 @@ static void bch2_btree_node_free_inmem(struct btree_trans *trans, struct btree *b) { struct bch_fs *c = trans->c; - unsigned i, level = b->c.level; bch2_btree_node_lock_write_nofail(trans, path, &b->c); @@ -255,13 +248,9 @@ static void bch2_btree_node_free_inmem(struct btree_trans *trans, mutex_unlock(&c->btree_cache.lock); six_unlock_write(&b->c.lock); - mark_btree_node_locked_noreset(path, level, BTREE_NODE_INTENT_LOCKED); + mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED); - trans_for_each_path(trans, path, i) - if (path->l[level].b == b) { - btree_node_unlock(trans, path, level); - path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init); - } + bch2_trans_node_drop(trans, b); } static void bch2_btree_node_free_never_used(struct btree_update *as, @@ -270,8 +259,6 @@ static void bch2_btree_node_free_never_used(struct btree_update *as, { struct bch_fs *c = as->c; struct prealloc_nodes *p = &as->prealloc_nodes[b->c.lock.readers != NULL]; - struct btree_path *path; - unsigned i, level = b->c.level; BUG_ON(!list_empty(&b->write_blocked)); BUG_ON(b->will_make_reachable != (1UL|(unsigned long) as)); @@ -293,11 +280,7 @@ static void bch2_btree_node_free_never_used(struct btree_update *as, six_unlock_intent(&b->c.lock); - trans_for_each_path(trans, path, i) - if (path->l[level].b == b) { - btree_node_unlock(trans, path, level); - path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init); - } + bch2_trans_node_drop(trans, b); } static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans, @@ -809,7 +792,7 @@ err: mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED); six_unlock_write(&b->c.lock); - btree_node_write_if_need(c, b, SIX_LOCK_intent); + btree_node_write_if_need(trans, b, SIX_LOCK_intent); btree_node_unlock(trans, path, b->c.level); bch2_path_put(trans, path_idx, true); } @@ -830,7 +813,7 @@ err: b = as->new_nodes[i]; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); - btree_node_write_if_need(c, b, SIX_LOCK_read); + btree_node_write_if_need(trans, b, SIX_LOCK_read); six_unlock_read(&b->c.lock); } @@ -1366,9 +1349,14 @@ static void bch2_insert_fixup_btree_ptr(struct btree_update *as, if (unlikely(!test_bit(JOURNAL_replay_done, &c->journal.flags))) bch2_journal_key_overwritten(c, b->c.btree_id, b->c.level, insert->k.p); - if (bch2_bkey_validate(c, bkey_i_to_s_c(insert), - btree_node_type(b), BCH_VALIDATE_write) ?: - bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), BCH_VALIDATE_write)) { + struct bkey_validate_context from = (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level, + .btree = b->c.btree_id, + .flags = BCH_VALIDATE_commit, + }; + if (bch2_bkey_validate(c, bkey_i_to_s_c(insert), from) ?: + bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), from)) { bch2_fs_inconsistent(c, "%s: inserting invalid bkey", __func__); dump_stack(); } @@ -1418,15 +1406,26 @@ bch2_btree_insert_keys_interior(struct btree_update *as, (bkey_cmp_left_packed(b, k, &insert->k.p) >= 0)) ; - while (!bch2_keylist_empty(keys)) { - insert = bch2_keylist_front(keys); - - if (bpos_gt(insert->k.p, b->key.k.p)) - break; - + for (; + insert != keys->top && bpos_le(insert->k.p, b->key.k.p); + insert = bkey_next(insert)) bch2_insert_fixup_btree_ptr(as, trans, path, b, &node_iter, insert); - bch2_keylist_pop_front(keys); + + if (bch2_btree_node_check_topology(trans, b)) { + struct printbuf buf = PRINTBUF; + + for (struct bkey_i *k = keys->keys; + k != insert; + k = bkey_next(k)) { + bch2_bkey_val_to_text(&buf, trans->c, bkey_i_to_s_c(k)); + prt_newline(&buf); + } + + panic("%s(): check_topology error: inserted keys\n%s", __func__, buf.buf); } + + memmove_u64s_down(keys->keys, insert, keys->top_p - insert->_data); + keys->top_p -= insert->_data - keys->keys_p; } static bool key_deleted_in_insert(struct keylist *insert_keys, struct bpos pos) @@ -1575,8 +1574,6 @@ static void btree_split_insert_keys(struct btree_update *as, bch2_btree_node_iter_init(&node_iter, b, &bch2_keylist_front(keys)->k.p); bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys); - - BUG_ON(bch2_btree_node_check_topology(trans, b)); } } @@ -1599,8 +1596,6 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans, if (ret) return ret; - bch2_btree_interior_update_will_free_node(as, b); - if (b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c)) { struct btree *n[2]; @@ -1699,16 +1694,18 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans, if (ret) goto err; + bch2_btree_interior_update_will_free_node(as, b); + if (n3) { bch2_btree_update_get_open_buckets(as, n3); - bch2_btree_node_write(c, n3, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n3, SIX_LOCK_intent, 0); } if (n2) { bch2_btree_update_get_open_buckets(as, n2); - bch2_btree_node_write(c, n2, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n2, SIX_LOCK_intent, 0); } bch2_btree_update_get_open_buckets(as, n1); - bch2_btree_node_write(c, n1, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n1, SIX_LOCK_intent, 0); /* * The old node must be freed (in memory) _before_ unlocking the new @@ -1827,8 +1824,6 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t btree_update_updated_node(as, b); bch2_btree_node_unlock_write(trans, path, b); - - BUG_ON(bch2_btree_node_check_topology(trans, b)); return 0; split: /* @@ -1905,7 +1900,7 @@ static void __btree_increase_depth(struct btree_update *as, struct btree_trans * BUG_ON(ret); bch2_btree_update_get_open_buckets(as, n); - bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n, SIX_LOCK_intent, 0); bch2_trans_node_add(trans, path, n); six_unlock_intent(&n->c.lock); @@ -1953,8 +1948,7 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, u64 start_time = local_clock(); int ret = 0; - bch2_trans_verify_not_in_restart(trans); - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); BUG_ON(!trans->paths[path].should_be_locked); BUG_ON(!btree_node_locked(&trans->paths[path], level)); @@ -2058,9 +2052,6 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, trace_and_count(c, btree_node_merge, trans, b); - bch2_btree_interior_update_will_free_node(as, b); - bch2_btree_interior_update_will_free_node(as, m); - n = bch2_btree_node_alloc(as, trans, b->c.level); SET_BTREE_NODE_SEQ(n->data, @@ -2096,10 +2087,13 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, if (ret) goto err_free_update; + bch2_btree_interior_update_will_free_node(as, b); + bch2_btree_interior_update_will_free_node(as, m); + bch2_trans_verify_paths(trans); bch2_btree_update_get_open_buckets(as, n); - bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n, SIX_LOCK_intent, 0); bch2_btree_node_free_inmem(trans, trans->paths + path, b); bch2_btree_node_free_inmem(trans, trans->paths + sib_path, m); @@ -2150,8 +2144,6 @@ int bch2_btree_node_rewrite(struct btree_trans *trans, if (ret) goto out; - bch2_btree_interior_update_will_free_node(as, b); - n = bch2_btree_node_alloc_replacement(as, trans, b); bch2_btree_build_aux_trees(n); @@ -2175,8 +2167,10 @@ int bch2_btree_node_rewrite(struct btree_trans *trans, if (ret) goto err; + bch2_btree_interior_update_will_free_node(as, b); + bch2_btree_update_get_open_buckets(as, n); - bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n, SIX_LOCK_intent, 0); bch2_btree_node_free_inmem(trans, btree_iter_path(trans, iter), b); @@ -2201,42 +2195,50 @@ struct async_btree_rewrite { struct list_head list; enum btree_id btree_id; unsigned level; - struct bpos pos; - __le64 seq; + struct bkey_buf key; }; static int async_btree_node_rewrite_trans(struct btree_trans *trans, struct async_btree_rewrite *a) { - struct bch_fs *c = trans->c; struct btree_iter iter; - struct btree *b; - int ret; - - bch2_trans_node_iter_init(trans, &iter, a->btree_id, a->pos, + bch2_trans_node_iter_init(trans, &iter, + a->btree_id, a->key.k->k.p, BTREE_MAX_DEPTH, a->level, 0); - b = bch2_btree_iter_peek_node(&iter); - ret = PTR_ERR_OR_ZERO(b); + struct btree *b = bch2_btree_iter_peek_node(&iter); + int ret = PTR_ERR_OR_ZERO(b); if (ret) goto out; - if (!b || b->data->keys.seq != a->seq) { + bool found = b && btree_ptr_hash_val(&b->key) == btree_ptr_hash_val(a->key.k); + ret = found + ? bch2_btree_node_rewrite(trans, &iter, b, 0) + : -ENOENT; + +#if 0 + /* Tracepoint... */ + if (!ret || ret == -ENOENT) { + struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; - if (b) - bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); - else - prt_str(&buf, "(null"); - bch_info(c, "%s: node to rewrite not found:, searching for seq %llu, got\n%s", - __func__, a->seq, buf.buf); + if (!ret) { + prt_printf(&buf, "rewrite node:\n "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(a->key.k)); + } else { + prt_printf(&buf, "node to rewrite not found:\n want: "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(a->key.k)); + prt_printf(&buf, "\n got: "); + if (b) + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + else + prt_str(&buf, "(null)"); + } + bch_info(c, "%s", buf.buf); printbuf_exit(&buf); - goto out; } - - ret = bch2_btree_node_rewrite(trans, &iter, b, 0); +#endif out: bch2_trans_iter_exit(trans, &iter); - return ret; } @@ -2247,81 +2249,97 @@ static void async_btree_node_rewrite_work(struct work_struct *work) struct bch_fs *c = a->c; int ret = bch2_trans_do(c, async_btree_node_rewrite_trans(trans, a)); - bch_err_fn_ratelimited(c, ret); + if (ret != -ENOENT) + bch_err_fn_ratelimited(c, ret); + + spin_lock(&c->btree_node_rewrites_lock); + list_del(&a->list); + spin_unlock(&c->btree_node_rewrites_lock); + + closure_wake_up(&c->btree_node_rewrites_wait); + + bch2_bkey_buf_exit(&a->key, c); bch2_write_ref_put(c, BCH_WRITE_REF_node_rewrite); kfree(a); } void bch2_btree_node_rewrite_async(struct bch_fs *c, struct btree *b) { - struct async_btree_rewrite *a; - int ret; - - a = kmalloc(sizeof(*a), GFP_NOFS); - if (!a) { - bch_err(c, "%s: error allocating memory", __func__); + struct async_btree_rewrite *a = kmalloc(sizeof(*a), GFP_NOFS); + if (!a) return; - } a->c = c; a->btree_id = b->c.btree_id; a->level = b->c.level; - a->pos = b->key.k.p; - a->seq = b->data->keys.seq; INIT_WORK(&a->work, async_btree_node_rewrite_work); - if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) { - mutex_lock(&c->pending_node_rewrites_lock); - list_add(&a->list, &c->pending_node_rewrites); - mutex_unlock(&c->pending_node_rewrites_lock); - return; + bch2_bkey_buf_init(&a->key); + bch2_bkey_buf_copy(&a->key, c, &b->key); + + bool now = false, pending = false; + + spin_lock(&c->btree_node_rewrites_lock); + if (c->curr_recovery_pass > BCH_RECOVERY_PASS_journal_replay && + bch2_write_ref_tryget(c, BCH_WRITE_REF_node_rewrite)) { + list_add(&a->list, &c->btree_node_rewrites); + now = true; + } else if (!test_bit(BCH_FS_may_go_rw, &c->flags)) { + list_add(&a->list, &c->btree_node_rewrites_pending); + pending = true; } + spin_unlock(&c->btree_node_rewrites_lock); - if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_node_rewrite)) { - if (test_bit(BCH_FS_started, &c->flags)) { - bch_err(c, "%s: error getting c->writes ref", __func__); - kfree(a); - return; - } - - ret = bch2_fs_read_write_early(c); - bch_err_msg(c, ret, "going read-write"); - if (ret) { - kfree(a); - return; - } - - bch2_write_ref_get(c, BCH_WRITE_REF_node_rewrite); + if (now) { + queue_work(c->btree_node_rewrite_worker, &a->work); + } else if (pending) { + /* bch2_do_pending_node_rewrites will execute */ + } else { + bch2_bkey_buf_exit(&a->key, c); + kfree(a); } +} - queue_work(c->btree_node_rewrite_worker, &a->work); +void bch2_async_btree_node_rewrites_flush(struct bch_fs *c) +{ + closure_wait_event(&c->btree_node_rewrites_wait, + list_empty(&c->btree_node_rewrites)); } void bch2_do_pending_node_rewrites(struct bch_fs *c) { - struct async_btree_rewrite *a, *n; + while (1) { + spin_lock(&c->btree_node_rewrites_lock); + struct async_btree_rewrite *a = + list_pop_entry(&c->btree_node_rewrites_pending, + struct async_btree_rewrite, list); + if (a) + list_add(&a->list, &c->btree_node_rewrites); + spin_unlock(&c->btree_node_rewrites_lock); - mutex_lock(&c->pending_node_rewrites_lock); - list_for_each_entry_safe(a, n, &c->pending_node_rewrites, list) { - list_del(&a->list); + if (!a) + break; bch2_write_ref_get(c, BCH_WRITE_REF_node_rewrite); queue_work(c->btree_node_rewrite_worker, &a->work); } - mutex_unlock(&c->pending_node_rewrites_lock); } void bch2_free_pending_node_rewrites(struct bch_fs *c) { - struct async_btree_rewrite *a, *n; + while (1) { + spin_lock(&c->btree_node_rewrites_lock); + struct async_btree_rewrite *a = + list_pop_entry(&c->btree_node_rewrites_pending, + struct async_btree_rewrite, list); + spin_unlock(&c->btree_node_rewrites_lock); - mutex_lock(&c->pending_node_rewrites_lock); - list_for_each_entry_safe(a, n, &c->pending_node_rewrites, list) { - list_del(&a->list); + if (!a) + break; + bch2_bkey_buf_exit(&a->key, c); kfree(a); } - mutex_unlock(&c->pending_node_rewrites_lock); } static int __bch2_btree_node_update_key(struct btree_trans *trans, @@ -2575,8 +2593,9 @@ static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update prt_printf(out, "%ps: ", (void *) as->ip_started); bch2_trans_commit_flags_to_text(out, as->flags); - prt_printf(out, " btree=%s l=%u-%u mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n", - bch2_btree_id_str(as->btree_id), + prt_str(out, " "); + bch2_btree_id_to_text(out, as->btree_id); + prt_printf(out, " l=%u-%u mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n", as->update_level_start, as->update_level_end, bch2_btree_update_modes[as->mode], @@ -2677,6 +2696,9 @@ void bch2_btree_reserve_cache_to_text(struct printbuf *out, struct bch_fs *c) void bch2_fs_btree_interior_update_exit(struct bch_fs *c) { + WARN_ON(!list_empty(&c->btree_node_rewrites)); + WARN_ON(!list_empty(&c->btree_node_rewrites_pending)); + if (c->btree_node_rewrite_worker) destroy_workqueue(c->btree_node_rewrite_worker); if (c->btree_interior_update_worker) @@ -2692,8 +2714,9 @@ void bch2_fs_btree_interior_update_init_early(struct bch_fs *c) mutex_init(&c->btree_interior_update_lock); INIT_WORK(&c->btree_interior_update_work, btree_interior_update_work); - INIT_LIST_HEAD(&c->pending_node_rewrites); - mutex_init(&c->pending_node_rewrites_lock); + INIT_LIST_HEAD(&c->btree_node_rewrites); + INIT_LIST_HEAD(&c->btree_node_rewrites_pending); + spin_lock_init(&c->btree_node_rewrites_lock); } int bch2_fs_btree_interior_update_init(struct bch_fs *c) diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h index 10f400957f21..7930ffea3075 100644 --- a/fs/bcachefs/btree_update_interior.h +++ b/fs/bcachefs/btree_update_interior.h @@ -159,7 +159,7 @@ static inline int bch2_foreground_maybe_merge(struct btree_trans *trans, unsigned level, unsigned flags) { - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); return bch2_foreground_maybe_merge_sibling(trans, path, level, flags, btree_prev_sib) ?: @@ -334,6 +334,7 @@ void bch2_journal_entry_to_btree_root(struct bch_fs *, struct jset_entry *); struct jset_entry *bch2_btree_roots_to_journal_entries(struct bch_fs *, struct jset_entry *, unsigned long); +void bch2_async_btree_node_rewrites_flush(struct bch_fs *); void bch2_do_pending_node_rewrites(struct bch_fs *); void bch2_free_pending_node_rewrites(struct bch_fs *); diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c index 1639c60dffa0..b56c4987b8c9 100644 --- a/fs/bcachefs/btree_write_buffer.c +++ b/fs/bcachefs/btree_write_buffer.c @@ -19,8 +19,6 @@ static int bch2_btree_write_buffer_journal_flush(struct journal *, struct journal_entry_pin *, u64); -static int bch2_journal_keys_to_write_buffer(struct bch_fs *, struct journal_buf *); - static inline bool __wb_key_ref_cmp(const struct wb_key_ref *l, const struct wb_key_ref *r) { return (cmp_int(l->hi, r->hi) ?: @@ -314,6 +312,8 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) darray_for_each(wb->sorted, i) { struct btree_write_buffered_key *k = &wb->flushing.keys.data[i->idx]; + BUG_ON(!btree_type_uses_write_buffer(k->btree)); + for (struct wb_key_ref *n = i + 1; n < min(i + 4, &darray_top(wb->sorted)); n++) prefetch(&wb->flushing.keys.data[n->idx]); @@ -481,21 +481,55 @@ err: return ret; } -static int fetch_wb_keys_from_journal(struct bch_fs *c, u64 seq) +static int bch2_journal_keys_to_write_buffer(struct bch_fs *c, struct journal_buf *buf) +{ + struct journal_keys_to_wb dst; + int ret = 0; + + bch2_journal_keys_to_write_buffer_start(c, &dst, le64_to_cpu(buf->data->seq)); + + for_each_jset_entry_type(entry, buf->data, BCH_JSET_ENTRY_write_buffer_keys) { + jset_entry_for_each_key(entry, k) { + ret = bch2_journal_key_to_wb(c, &dst, entry->btree_id, k); + if (ret) + goto out; + } + + entry->type = BCH_JSET_ENTRY_btree_keys; + } +out: + ret = bch2_journal_keys_to_write_buffer_end(c, &dst) ?: ret; + return ret; +} + +static int fetch_wb_keys_from_journal(struct bch_fs *c, u64 max_seq) { struct journal *j = &c->journal; struct journal_buf *buf; + bool blocked; int ret = 0; - while (!ret && (buf = bch2_next_write_buffer_flush_journal_buf(j, seq))) { + while (!ret && (buf = bch2_next_write_buffer_flush_journal_buf(j, max_seq, &blocked))) { ret = bch2_journal_keys_to_write_buffer(c, buf); + + if (!blocked && !ret) { + spin_lock(&j->lock); + buf->need_flush_to_write_buffer = false; + spin_unlock(&j->lock); + } + mutex_unlock(&j->buf_lock); + + if (blocked) { + bch2_journal_unblock(j); + break; + } } return ret; } -static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq, +static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 max_seq, bool *did_work) { struct bch_fs *c = trans->c; @@ -505,7 +539,7 @@ static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq, do { bch2_trans_unlock(trans); - fetch_from_journal_err = fetch_wb_keys_from_journal(c, seq); + fetch_from_journal_err = fetch_wb_keys_from_journal(c, max_seq); *did_work |= wb->inc.keys.nr || wb->flushing.keys.nr; @@ -518,8 +552,8 @@ static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq, mutex_unlock(&wb->flushing.lock); } while (!ret && (fetch_from_journal_err || - (wb->inc.pin.seq && wb->inc.pin.seq <= seq) || - (wb->flushing.pin.seq && wb->flushing.pin.seq <= seq))); + (wb->inc.pin.seq && wb->inc.pin.seq <= max_seq) || + (wb->flushing.pin.seq && wb->flushing.pin.seq <= max_seq))); return ret; } @@ -600,6 +634,14 @@ int bch2_btree_write_buffer_maybe_flush(struct btree_trans *trans, bch2_bkey_buf_init(&tmp); if (!bkey_and_val_eq(referring_k, bkey_i_to_s_c(last_flushed->k))) { + if (trace_write_buffer_maybe_flush_enabled()) { + struct printbuf buf = PRINTBUF; + + bch2_bkey_val_to_text(&buf, c, referring_k); + trace_write_buffer_maybe_flush(trans, _RET_IP_, buf.buf); + printbuf_exit(&buf); + } + bch2_bkey_buf_reassemble(&tmp, c, referring_k); if (bkey_is_btree_ptr(referring_k.k)) { @@ -771,31 +813,6 @@ int bch2_journal_keys_to_write_buffer_end(struct bch_fs *c, struct journal_keys_ return ret; } -static int bch2_journal_keys_to_write_buffer(struct bch_fs *c, struct journal_buf *buf) -{ - struct journal_keys_to_wb dst; - int ret = 0; - - bch2_journal_keys_to_write_buffer_start(c, &dst, le64_to_cpu(buf->data->seq)); - - for_each_jset_entry_type(entry, buf->data, BCH_JSET_ENTRY_write_buffer_keys) { - jset_entry_for_each_key(entry, k) { - ret = bch2_journal_key_to_wb(c, &dst, entry->btree_id, k); - if (ret) - goto out; - } - - entry->type = BCH_JSET_ENTRY_btree_keys; - } - - spin_lock(&c->journal.lock); - buf->need_flush_to_write_buffer = false; - spin_unlock(&c->journal.lock); -out: - ret = bch2_journal_keys_to_write_buffer_end(c, &dst) ?: ret; - return ret; -} - static int wb_keys_resize(struct btree_write_buffer_keys *wb, size_t new_size) { if (wb->keys.size >= new_size) diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index ec7d9a59bea9..345b117a4a4a 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -18,7 +18,9 @@ #include "error.h" #include "inode.h" #include "movinggc.h" +#include "rebalance.h" #include "recovery.h" +#include "recovery_passes.h" #include "reflink.h" #include "replicas.h" #include "subvolume.h" @@ -260,8 +262,6 @@ int bch2_check_fix_ptrs(struct btree_trans *trans, struct printbuf buf = PRINTBUF; int ret = 0; - percpu_down_read(&c->mark_lock); - bkey_for_each_ptr_decode(k.k, ptrs_c, p, entry_c) { ret = bch2_check_fix_ptr(trans, k, p, entry_c, &do_update); if (ret) @@ -362,7 +362,6 @@ found: bch_info(c, "new key %s", buf.buf); } - percpu_up_read(&c->mark_lock); struct btree_iter iter; bch2_trans_node_iter_init(trans, &iter, btree, new->k.p, 0, level, BTREE_ITER_intent|BTREE_ITER_all_snapshots); @@ -371,8 +370,6 @@ found: BTREE_UPDATE_internal_snapshot_node| BTREE_TRIGGER_norun); bch2_trans_iter_exit(trans, &iter); - percpu_down_read(&c->mark_lock); - if (ret) goto err; @@ -380,7 +377,6 @@ found: bch2_btree_node_update_key_early(trans, btree, level - 1, k, new); } err: - percpu_up_read(&c->mark_lock); printbuf_exit(&buf); return ret; } @@ -401,8 +397,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, BUG_ON(!sectors); if (gen_after(ptr->gen, b_gen)) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - ptr_gen_newer_than_bucket_gen, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, ptr_gen_newer_than_bucket_gen, "bucket %u:%zu gen %u data type %s: ptr gen %u newer than bucket gen\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -415,8 +411,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, } if (gen_cmp(b_gen, ptr->gen) > BUCKET_GC_GEN_MAX) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - ptr_too_stale, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, ptr_too_stale, "bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -435,8 +431,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, } if (b_gen != ptr->gen) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - stale_dirty_ptr, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, stale_dirty_ptr, "bucket %u:%zu gen %u (mem gen %u) data type %s: stale dirty ptr (gen %u)\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -451,8 +447,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, } if (bucket_data_type_mismatch(bucket_data_type, ptr_data_type)) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - ptr_bucket_data_type_mismatch, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, ptr_bucket_data_type_mismatch, "bucket %u:%zu gen %u different types of data in same bucket: %s, %s\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -466,8 +462,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, } if ((u64) *bucket_sectors + sectors > U32_MAX) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - bucket_sector_count_overflow, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, bucket_sector_count_overflow, "bucket %u:%zu gen %u data type %s sector count overflow: %u + %lli > U32_MAX\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -485,7 +481,9 @@ out: printbuf_exit(&buf); return ret; err: +fsck_err: bch2_dump_trans_updates(trans); + bch2_inconsistent_error(c); ret = -BCH_ERR_bucket_ref_update; goto out; } @@ -543,7 +541,8 @@ static int __mark_pointer(struct btree_trans *trans, struct bch_dev *ca, struct bkey_s_c k, const struct extent_ptr_decoded *p, s64 sectors, enum bch_data_type ptr_data_type, - struct bch_alloc_v4 *a) + struct bch_alloc_v4 *a, + bool insert) { u32 *dst_sectors = p->has_ec ? &a->stripe_sectors : !p->ptr.cached ? &a->dirty_sectors : @@ -553,8 +552,8 @@ static int __mark_pointer(struct btree_trans *trans, struct bch_dev *ca, if (ret) return ret; - - alloc_data_type_set(a, ptr_data_type); + if (insert) + alloc_data_type_set(a, ptr_data_type); return 0; } @@ -570,8 +569,10 @@ static int bch2_trigger_pointer(struct btree_trans *trans, struct printbuf buf = PRINTBUF; int ret = 0; - u64 abs_sectors = ptr_disk_sectors(level ? btree_sectors(c) : k.k->size, p); - *sectors = insert ? abs_sectors : -abs_sectors; + struct bkey_i_backpointer bp; + bch2_extent_ptr_to_bp(c, btree_id, level, k, p, entry, &bp); + + *sectors = insert ? bp.v.bucket_len : -(s64) bp.v.bucket_len; struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev); if (unlikely(!ca)) { @@ -580,41 +581,36 @@ static int bch2_trigger_pointer(struct btree_trans *trans, goto err; } - struct bpos bucket; - struct bch_backpointer bp; - __bch2_extent_ptr_to_bp(trans->c, ca, btree_id, level, k, p, entry, &bucket, &bp, abs_sectors); + struct bpos bucket = PTR_BUCKET_POS(ca, &p.ptr); if (flags & BTREE_TRIGGER_transactional) { struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update(trans, bucket, 0); ret = PTR_ERR_OR_ZERO(a) ?: - __mark_pointer(trans, ca, k, &p, *sectors, bp.data_type, &a->v); + __mark_pointer(trans, ca, k, &p, *sectors, bp.v.data_type, &a->v, insert); if (ret) goto err; if (!p.ptr.cached) { - ret = bch2_bucket_backpointer_mod(trans, ca, bucket, bp, k, insert); + ret = bch2_bucket_backpointer_mod(trans, k, &bp, insert); if (ret) goto err; } } if (flags & BTREE_TRIGGER_gc) { - percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, bucket.offset); if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u\n %s", p.ptr.dev, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = -BCH_ERR_trigger_pointer; - goto err_unlock; + goto err; } bucket_lock(g); struct bch_alloc_v4 old = bucket_m_to_alloc(*g), new = old; - ret = __mark_pointer(trans, ca, k, &p, *sectors, bp.data_type, &new); + ret = __mark_pointer(trans, ca, k, &p, *sectors, bp.v.data_type, &new, insert); alloc_to_bucket(g, new); bucket_unlock(g); -err_unlock: - percpu_up_read(&c->mark_lock); if (!ret) ret = bch2_alloc_key_to_dev_counters(trans, ca, &old, &new, flags); @@ -951,6 +947,7 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans, enum bch_data_type type, unsigned sectors) { + struct bch_fs *c = trans->c; struct btree_iter iter; int ret = 0; @@ -960,8 +957,8 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans, return PTR_ERR(a); if (a->v.data_type && type && a->v.data_type != type) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - bucket_metadata_type_mismatch, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, bucket_metadata_type_mismatch, "bucket %llu:%llu gen %u different types of data in same bucket: %s, %s\n" "while marking %s", iter.pos.inode, iter.pos.offset, a->v.gen, @@ -979,6 +976,7 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans, ret = bch2_trans_update(trans, &iter, &a->k_i, 0); } err: +fsck_err: bch2_trans_iter_exit(trans, &iter); return ret; } @@ -990,11 +988,10 @@ static int bch2_mark_metadata_bucket(struct btree_trans *trans, struct bch_dev * struct bch_fs *c = trans->c; int ret = 0; - percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, b); if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u when marking metadata type %s", ca->dev_idx, bch2_data_type_str(data_type))) - goto err_unlock; + goto err; bucket_lock(g); struct bch_alloc_v4 old = bucket_m_to_alloc(*g); @@ -1004,26 +1001,24 @@ static int bch2_mark_metadata_bucket(struct btree_trans *trans, struct bch_dev * "different types of data in same bucket: %s, %s", bch2_data_type_str(g->data_type), bch2_data_type_str(data_type))) - goto err; + goto err_unlock; if (bch2_fs_inconsistent_on((u64) g->dirty_sectors + sectors > ca->mi.bucket_size, c, "bucket %u:%llu gen %u data type %s sector count overflow: %u + %u > bucket size", ca->dev_idx, b, g->gen, bch2_data_type_str(g->data_type ?: data_type), g->dirty_sectors, sectors)) - goto err; + goto err_unlock; g->data_type = data_type; g->dirty_sectors += sectors; struct bch_alloc_v4 new = bucket_m_to_alloc(*g); bucket_unlock(g); - percpu_up_read(&c->mark_lock); ret = bch2_alloc_key_to_dev_counters(trans, ca, &old, &new, flags); return ret; -err: - bucket_unlock(g); err_unlock: - percpu_up_read(&c->mark_lock); + bucket_unlock(g); +err: return -BCH_ERR_metadata_bucket_inconsistency; } @@ -1155,6 +1150,31 @@ int bch2_trans_mark_dev_sbs(struct bch_fs *c) return bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_transactional); } +bool bch2_is_superblock_bucket(struct bch_dev *ca, u64 b) +{ + struct bch_sb_layout *layout = &ca->disk_sb.sb->layout; + u64 b_offset = bucket_to_sector(ca, b); + u64 b_end = bucket_to_sector(ca, b + 1); + unsigned i; + + if (!b) + return true; + + for (i = 0; i < layout->nr_superblocks; i++) { + u64 offset = le64_to_cpu(layout->sb_offset[i]); + u64 end = offset + (1 << layout->sb_max_size_bits); + + if (!(offset >= b_end || end <= b_offset)) + return true; + } + + for (i = 0; i < ca->journal.nr; i++) + if (b == ca->journal.buckets[i]) + return true; + + return false; +} + /* Disk reservations: */ #define SECTORS_CACHE 1024 @@ -1238,7 +1258,7 @@ int bch2_buckets_nouse_alloc(struct bch_fs *c) for_each_member_device(c, ca) { BUG_ON(ca->buckets_nouse); - ca->buckets_nouse = kvmalloc(BITS_TO_LONGS(ca->mi.nbuckets) * + ca->buckets_nouse = bch2_kvmalloc(BITS_TO_LONGS(ca->mi.nbuckets) * sizeof(unsigned long), GFP_KERNEL|__GFP_ZERO); if (!ca->buckets_nouse) { @@ -1264,10 +1284,15 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets) bool resize = ca->bucket_gens != NULL; int ret; - BUG_ON(resize && ca->buckets_nouse); + if (resize) + lockdep_assert_held(&c->state_lock); - if (!(bucket_gens = kvmalloc(sizeof(struct bucket_gens) + nbuckets, - GFP_KERNEL|__GFP_ZERO))) { + if (resize && ca->buckets_nouse) + return -BCH_ERR_no_resize_with_buckets_nouse; + + bucket_gens = bch2_kvmalloc(struct_size(bucket_gens, b, nbuckets), + GFP_KERNEL|__GFP_ZERO); + if (!bucket_gens) { ret = -BCH_ERR_ENOMEM_bucket_gens; goto err; } @@ -1277,19 +1302,16 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets) bucket_gens->nbuckets_minus_first = bucket_gens->nbuckets - bucket_gens->first_bucket; - if (resize) { - down_write(&ca->bucket_lock); - percpu_down_write(&c->mark_lock); - } - old_bucket_gens = rcu_dereference_protected(ca->bucket_gens, 1); if (resize) { - size_t n = min(bucket_gens->nbuckets, old_bucket_gens->nbuckets); - + bucket_gens->nbuckets = min(bucket_gens->nbuckets, + old_bucket_gens->nbuckets); + bucket_gens->nbuckets_minus_first = + bucket_gens->nbuckets - bucket_gens->first_bucket; memcpy(bucket_gens->b, old_bucket_gens->b, - n); + bucket_gens->nbuckets); } rcu_assign_pointer(ca->bucket_gens, bucket_gens); @@ -1297,11 +1319,6 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets) nbuckets = ca->mi.nbuckets; - if (resize) { - percpu_up_write(&c->mark_lock); - up_write(&ca->bucket_lock); - } - ret = 0; err: if (bucket_gens) diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h index ccc78bfe2fd4..a9acdd6c0c86 100644 --- a/fs/bcachefs/buckets.h +++ b/fs/bcachefs/buckets.h @@ -82,16 +82,15 @@ static inline void bucket_lock(struct bucket *b) static inline struct bucket *gc_bucket(struct bch_dev *ca, size_t b) { - return genradix_ptr(&ca->buckets_gc, b); + return bucket_valid(ca, b) + ? genradix_ptr(&ca->buckets_gc, b) + : NULL; } static inline struct bucket_gens *bucket_gens(struct bch_dev *ca) { return rcu_dereference_check(ca->bucket_gens, - !ca->fs || - percpu_rwsem_is_held(&ca->fs->mark_lock) || - lockdep_is_held(&ca->fs->state_lock) || - lockdep_is_held(&ca->bucket_lock)); + lockdep_is_held(&ca->fs->state_lock)); } static inline u8 *bucket_gen(struct bch_dev *ca, size_t b) @@ -308,26 +307,7 @@ int bch2_trans_mark_dev_sbs_flags(struct bch_fs *, enum btree_iter_update_trigger_flags); int bch2_trans_mark_dev_sbs(struct bch_fs *); -static inline bool is_superblock_bucket(struct bch_dev *ca, u64 b) -{ - struct bch_sb_layout *layout = &ca->disk_sb.sb->layout; - u64 b_offset = bucket_to_sector(ca, b); - u64 b_end = bucket_to_sector(ca, b + 1); - unsigned i; - - if (!b) - return true; - - for (i = 0; i < layout->nr_superblocks; i++) { - u64 offset = le64_to_cpu(layout->sb_offset[i]); - u64 end = offset + (1 << layout->sb_max_size_bits); - - if (!(offset >= b_end || end <= b_offset)) - return true; - } - - return false; -} +bool bch2_is_superblock_bucket(struct bch_dev *, u64); static inline const char *bch2_data_type_str(enum bch_data_type type) { diff --git a/fs/bcachefs/buckets_types.h b/fs/bcachefs/buckets_types.h index 28bd09a253c8..7174047b8e92 100644 --- a/fs/bcachefs/buckets_types.h +++ b/fs/bcachefs/buckets_types.h @@ -24,7 +24,7 @@ struct bucket_gens { u16 first_bucket; size_t nbuckets; size_t nbuckets_minus_first; - u8 b[]; + u8 b[] __counted_by(nbuckets); }; struct bch_dev_usage { diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index 2182b555c112..46e9e32105a9 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -6,11 +6,11 @@ #include "buckets.h" #include "chardev.h" #include "disk_accounting.h" +#include "fsck.h" #include "journal.h" #include "move.h" #include "recovery_passes.h" #include "replicas.h" -#include "super.h" #include "super-io.h" #include "thread_with_file.h" @@ -127,130 +127,6 @@ static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg } #endif -struct fsck_thread { - struct thread_with_stdio thr; - struct bch_fs *c; - struct bch_opts opts; -}; - -static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr) -{ - struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr); - kfree(thr); -} - -static int bch2_fsck_offline_thread_fn(struct thread_with_stdio *stdio) -{ - struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); - struct bch_fs *c = thr->c; - - int ret = PTR_ERR_OR_ZERO(c); - if (ret) - return ret; - - ret = bch2_fs_start(thr->c); - if (ret) - goto err; - - if (test_bit(BCH_FS_errors_fixed, &c->flags)) { - bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: errors fixed\n", c->name); - ret |= 1; - } - if (test_bit(BCH_FS_error, &c->flags)) { - bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: still has errors\n", c->name); - ret |= 4; - } -err: - bch2_fs_stop(c); - return ret; -} - -static const struct thread_with_stdio_ops bch2_offline_fsck_ops = { - .exit = bch2_fsck_thread_exit, - .fn = bch2_fsck_offline_thread_fn, -}; - -static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_arg) -{ - struct bch_ioctl_fsck_offline arg; - struct fsck_thread *thr = NULL; - darray_str(devs) = {}; - long ret = 0; - - if (copy_from_user(&arg, user_arg, sizeof(arg))) - return -EFAULT; - - if (arg.flags) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - for (size_t i = 0; i < arg.nr_devs; i++) { - u64 dev_u64; - ret = copy_from_user_errcode(&dev_u64, &user_arg->devs[i], sizeof(u64)); - if (ret) - goto err; - - char *dev_str = strndup_user((char __user *)(unsigned long) dev_u64, PATH_MAX); - ret = PTR_ERR_OR_ZERO(dev_str); - if (ret) - goto err; - - ret = darray_push(&devs, dev_str); - if (ret) { - kfree(dev_str); - goto err; - } - } - - thr = kzalloc(sizeof(*thr), GFP_KERNEL); - if (!thr) { - ret = -ENOMEM; - goto err; - } - - thr->opts = bch2_opts_empty(); - - if (arg.opts) { - char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); - ret = PTR_ERR_OR_ZERO(optstr) ?: - bch2_parse_mount_opts(NULL, &thr->opts, NULL, optstr); - if (!IS_ERR(optstr)) - kfree(optstr); - - if (ret) - goto err; - } - - opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio); - opt_set(thr->opts, read_only, 1); - opt_set(thr->opts, ratelimit_errors, 0); - - /* We need request_key() to be called before we punt to kthread: */ - opt_set(thr->opts, nostart, true); - - bch2_thread_with_stdio_init(&thr->thr, &bch2_offline_fsck_ops); - - thr->c = bch2_fs_open(devs.data, arg.nr_devs, thr->opts); - - if (!IS_ERR(thr->c) && - thr->c->opts.errors == BCH_ON_ERROR_panic) - thr->c->opts.errors = BCH_ON_ERROR_ro; - - ret = __bch2_run_thread_with_stdio(&thr->thr); -out: - darray_for_each(devs, i) - kfree(*i); - darray_exit(&devs); - return ret; -err: - if (thr) - bch2_fsck_thread_exit(&thr->thr); - pr_err("ret %s", bch2_err_str(ret)); - goto out; -} - static long bch2_global_ioctl(unsigned cmd, void __user *arg) { long ret; @@ -775,99 +651,6 @@ static long bch2_ioctl_disk_resize_journal(struct bch_fs *c, return ret; } -static int bch2_fsck_online_thread_fn(struct thread_with_stdio *stdio) -{ - struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); - struct bch_fs *c = thr->c; - - c->stdio_filter = current; - c->stdio = &thr->thr.stdio; - - /* - * XXX: can we figure out a way to do this without mucking with c->opts? - */ - unsigned old_fix_errors = c->opts.fix_errors; - if (opt_defined(thr->opts, fix_errors)) - c->opts.fix_errors = thr->opts.fix_errors; - else - c->opts.fix_errors = FSCK_FIX_ask; - - c->opts.fsck = true; - set_bit(BCH_FS_fsck_running, &c->flags); - - c->curr_recovery_pass = BCH_RECOVERY_PASS_check_alloc_info; - int ret = bch2_run_online_recovery_passes(c); - - clear_bit(BCH_FS_fsck_running, &c->flags); - bch_err_fn(c, ret); - - c->stdio = NULL; - c->stdio_filter = NULL; - c->opts.fix_errors = old_fix_errors; - - up(&c->online_fsck_mutex); - bch2_ro_ref_put(c); - return ret; -} - -static const struct thread_with_stdio_ops bch2_online_fsck_ops = { - .exit = bch2_fsck_thread_exit, - .fn = bch2_fsck_online_thread_fn, -}; - -static long bch2_ioctl_fsck_online(struct bch_fs *c, - struct bch_ioctl_fsck_online arg) -{ - struct fsck_thread *thr = NULL; - long ret = 0; - - if (arg.flags) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (!bch2_ro_ref_tryget(c)) - return -EROFS; - - if (down_trylock(&c->online_fsck_mutex)) { - bch2_ro_ref_put(c); - return -EAGAIN; - } - - thr = kzalloc(sizeof(*thr), GFP_KERNEL); - if (!thr) { - ret = -ENOMEM; - goto err; - } - - thr->c = c; - thr->opts = bch2_opts_empty(); - - if (arg.opts) { - char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); - - ret = PTR_ERR_OR_ZERO(optstr) ?: - bch2_parse_mount_opts(c, &thr->opts, NULL, optstr); - if (!IS_ERR(optstr)) - kfree(optstr); - - if (ret) - goto err; - } - - ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_online_fsck_ops); -err: - if (ret < 0) { - bch_err_fn(c, ret); - if (thr) - bch2_fsck_thread_exit(&thr->thr); - up(&c->online_fsck_mutex); - bch2_ro_ref_put(c); - } - return ret; -} - #define BCH_IOCTL(_name, _argtype) \ do { \ _argtype i; \ diff --git a/fs/bcachefs/checksum.c b/fs/bcachefs/checksum.c index ce8fc677bef9..23a383577d4c 100644 --- a/fs/bcachefs/checksum.c +++ b/fs/bcachefs/checksum.c @@ -2,6 +2,7 @@ #include "bcachefs.h" #include "checksum.h" #include "errcode.h" +#include "error.h" #include "super.h" #include "super-io.h" @@ -252,6 +253,10 @@ int bch2_encrypt(struct bch_fs *c, unsigned type, if (!bch2_csum_type_is_encryption(type)) return 0; + if (bch2_fs_inconsistent_on(!c->chacha20, + c, "attempting to encrypt without encryption key")) + return -BCH_ERR_no_encryption_key; + return do_encrypt(c->chacha20, nonce, data, len); } @@ -337,8 +342,9 @@ int __bch2_encrypt_bio(struct bch_fs *c, unsigned type, size_t sgl_len = 0; int ret = 0; - if (!bch2_csum_type_is_encryption(type)) - return 0; + if (bch2_fs_inconsistent_on(!c->chacha20, + c, "attempting to encrypt without encryption key")) + return -BCH_ERR_no_encryption_key; darray_init(&sgl); diff --git a/fs/bcachefs/checksum.h b/fs/bcachefs/checksum.h index e40499fde9a4..43b9d71f2f2b 100644 --- a/fs/bcachefs/checksum.h +++ b/fs/bcachefs/checksum.h @@ -109,7 +109,7 @@ int bch2_enable_encryption(struct bch_fs *, bool); void bch2_fs_encryption_exit(struct bch_fs *); int bch2_fs_encryption_init(struct bch_fs *); -static inline enum bch_csum_type bch2_csum_opt_to_type(enum bch_csum_opts type, +static inline enum bch_csum_type bch2_csum_opt_to_type(enum bch_csum_opt type, bool data) { switch (type) { diff --git a/fs/bcachefs/compress.c b/fs/bcachefs/compress.c index 1410365a8891..114bf2f3879f 100644 --- a/fs/bcachefs/compress.c +++ b/fs/bcachefs/compress.c @@ -2,13 +2,34 @@ #include "bcachefs.h" #include "checksum.h" #include "compress.h" +#include "error.h" #include "extents.h" +#include "io_write.h" +#include "opts.h" #include "super-io.h" #include #include #include +static inline enum bch_compression_opts bch2_compression_type_to_opt(enum bch_compression_type type) +{ + switch (type) { + case BCH_COMPRESSION_TYPE_none: + case BCH_COMPRESSION_TYPE_incompressible: + return BCH_COMPRESSION_OPT_none; + case BCH_COMPRESSION_TYPE_lz4_old: + case BCH_COMPRESSION_TYPE_lz4: + return BCH_COMPRESSION_OPT_lz4; + case BCH_COMPRESSION_TYPE_gzip: + return BCH_COMPRESSION_OPT_gzip; + case BCH_COMPRESSION_TYPE_zstd: + return BCH_COMPRESSION_OPT_zstd; + default: + BUG(); + } +} + /* Bounce buffer: */ struct bbuf { void *b; @@ -158,6 +179,19 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src, void *workspace; int ret; + enum bch_compression_opts opt = bch2_compression_type_to_opt(crc.compression_type); + mempool_t *workspace_pool = &c->compress_workspace[opt]; + if (unlikely(!mempool_initialized(workspace_pool))) { + if (fsck_err(c, compression_type_not_marked_in_sb, + "compression type %s set but not marked in superblock", + __bch2_compression_types[crc.compression_type])) + ret = bch2_check_set_has_compressed_data(c, opt); + else + ret = -BCH_ERR_compression_workspace_not_initialized; + if (ret) + goto out; + } + src_data = bio_map_or_bounce(c, src, READ); switch (crc.compression_type) { @@ -176,13 +210,13 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src, .avail_out = dst_len, }; - workspace = mempool_alloc(&c->decompress_workspace, GFP_NOFS); + workspace = mempool_alloc(workspace_pool, GFP_NOFS); zlib_set_workspace(&strm, workspace); zlib_inflateInit2(&strm, -MAX_WBITS); ret = zlib_inflate(&strm, Z_FINISH); - mempool_free(workspace, &c->decompress_workspace); + mempool_free(workspace, workspace_pool); if (ret != Z_STREAM_END) goto err; @@ -195,14 +229,14 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src, if (real_src_len > src_len - 4) goto err; - workspace = mempool_alloc(&c->decompress_workspace, GFP_NOFS); + workspace = mempool_alloc(workspace_pool, GFP_NOFS); ctx = zstd_init_dctx(workspace, zstd_dctx_workspace_bound()); ret = zstd_decompress_dctx(ctx, dst_data, dst_len, src_data.b + 4, real_src_len); - mempool_free(workspace, &c->decompress_workspace); + mempool_free(workspace, workspace_pool); if (ret != dst_len) goto err; @@ -212,6 +246,7 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src, BUG(); } ret = 0; +fsck_err: out: bio_unmap_or_unbounce(c, src_data); return ret; @@ -220,11 +255,14 @@ err: goto out; } -int bch2_bio_uncompress_inplace(struct bch_fs *c, struct bio *bio, - struct bch_extent_crc_unpacked *crc) +int bch2_bio_uncompress_inplace(struct bch_write_op *op, + struct bio *bio) { + struct bch_fs *c = op->c; + struct bch_extent_crc_unpacked *crc = &op->crc; struct bbuf data = { NULL }; size_t dst_len = crc->uncompressed_size << 9; + int ret = 0; /* bio must own its pages: */ BUG_ON(!bio->bi_vcnt); @@ -232,17 +270,26 @@ int bch2_bio_uncompress_inplace(struct bch_fs *c, struct bio *bio, if (crc->uncompressed_size << 9 > c->opts.encoded_extent_max || crc->compressed_size << 9 > c->opts.encoded_extent_max) { - bch_err(c, "error rewriting existing data: extent too big"); + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "error rewriting existing data: extent too big"); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); return -EIO; } data = __bounce_alloc(c, dst_len, WRITE); if (__bio_uncompress(c, bio, data.b, *crc)) { - if (!c->opts.no_data_io) - bch_err(c, "error rewriting existing data: decompression error"); - bio_unmap_or_unbounce(c, data); - return -EIO; + if (!c->opts.no_data_io) { + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "error rewriting existing data: decompression error"); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + } + ret = -EIO; + goto err; } /* @@ -259,9 +306,9 @@ int bch2_bio_uncompress_inplace(struct bch_fs *c, struct bio *bio, crc->uncompressed_size = crc->live_size; crc->offset = 0; crc->csum = (struct bch_csum) { 0, 0 }; - +err: bio_unmap_or_unbounce(c, data); - return 0; + return ret; } int bch2_bio_uncompress(struct bch_fs *c, struct bio *src, @@ -394,8 +441,21 @@ static unsigned __bio_compress(struct bch_fs *c, unsigned pad; int ret = 0; - BUG_ON(compression_type >= BCH_COMPRESSION_TYPE_NR); - BUG_ON(!mempool_initialized(&c->compress_workspace[compression_type])); + /* bch2_compression_decode catches unknown compression types: */ + BUG_ON(compression.type >= BCH_COMPRESSION_OPT_NR); + + mempool_t *workspace_pool = &c->compress_workspace[compression.type]; + if (unlikely(!mempool_initialized(workspace_pool))) { + if (fsck_err(c, compression_opt_not_marked_in_sb, + "compression opt %s set but not marked in superblock", + bch2_compression_opts[compression.type])) { + ret = bch2_check_set_has_compressed_data(c, compression.type); + if (ret) /* memory allocation failure, don't compress */ + return 0; + } else { + return 0; + } + } /* If it's only one block, don't bother trying to compress: */ if (src->bi_iter.bi_size <= c->opts.block_size) @@ -404,7 +464,7 @@ static unsigned __bio_compress(struct bch_fs *c, dst_data = bio_map_or_bounce(c, dst, WRITE); src_data = bio_map_or_bounce(c, src, READ); - workspace = mempool_alloc(&c->compress_workspace[compression_type], GFP_NOFS); + workspace = mempool_alloc(workspace_pool, GFP_NOFS); *src_len = src->bi_iter.bi_size; *dst_len = dst->bi_iter.bi_size; @@ -447,7 +507,7 @@ static unsigned __bio_compress(struct bch_fs *c, *src_len = round_down(*src_len, block_bytes(c)); } - mempool_free(workspace, &c->compress_workspace[compression_type]); + mempool_free(workspace, workspace_pool); if (ret) goto err; @@ -477,6 +537,9 @@ out: err: ret = BCH_COMPRESSION_TYPE_incompressible; goto out; +fsck_err: + ret = 0; + goto out; } unsigned bch2_bio_compress(struct bch_fs *c, @@ -559,7 +622,6 @@ void bch2_fs_compress_exit(struct bch_fs *c) { unsigned i; - mempool_exit(&c->decompress_workspace); for (i = 0; i < ARRAY_SIZE(c->compress_workspace); i++) mempool_exit(&c->compress_workspace[i]); mempool_exit(&c->compression_bounce[WRITE]); @@ -568,7 +630,6 @@ void bch2_fs_compress_exit(struct bch_fs *c) static int __bch2_fs_compress_init(struct bch_fs *c, u64 features) { - size_t decompress_workspace_size = 0; ZSTD_parameters params = zstd_get_params(zstd_max_clevel(), c->opts.encoded_extent_max); @@ -576,19 +637,17 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features) struct { unsigned feature; - enum bch_compression_type type; + enum bch_compression_opts type; size_t compress_workspace; - size_t decompress_workspace; } compression_types[] = { - { BCH_FEATURE_lz4, BCH_COMPRESSION_TYPE_lz4, - max_t(size_t, LZ4_MEM_COMPRESS, LZ4HC_MEM_COMPRESS), - 0 }, - { BCH_FEATURE_gzip, BCH_COMPRESSION_TYPE_gzip, - zlib_deflate_workspacesize(MAX_WBITS, DEF_MEM_LEVEL), - zlib_inflate_workspacesize(), }, - { BCH_FEATURE_zstd, BCH_COMPRESSION_TYPE_zstd, - c->zstd_workspace_size, - zstd_dctx_workspace_bound() }, + { BCH_FEATURE_lz4, BCH_COMPRESSION_OPT_lz4, + max_t(size_t, LZ4_MEM_COMPRESS, LZ4HC_MEM_COMPRESS) }, + { BCH_FEATURE_gzip, BCH_COMPRESSION_OPT_gzip, + max(zlib_deflate_workspacesize(MAX_WBITS, DEF_MEM_LEVEL), + zlib_inflate_workspacesize()) }, + { BCH_FEATURE_zstd, BCH_COMPRESSION_OPT_zstd, + max(c->zstd_workspace_size, + zstd_dctx_workspace_bound()) }, }, *i; bool have_compressed = false; @@ -613,9 +672,6 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features) for (i = compression_types; i < compression_types + ARRAY_SIZE(compression_types); i++) { - decompress_workspace_size = - max(decompress_workspace_size, i->decompress_workspace); - if (!(features & (1 << i->feature))) continue; @@ -628,11 +684,6 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features) return -BCH_ERR_ENOMEM_compression_workspace_init; } - if (!mempool_initialized(&c->decompress_workspace) && - mempool_init_kvmalloc_pool(&c->decompress_workspace, - 1, decompress_workspace_size)) - return -BCH_ERR_ENOMEM_decompression_workspace_init; - return 0; } diff --git a/fs/bcachefs/compress.h b/fs/bcachefs/compress.h index 607fd5e232c9..bec2f05bfd52 100644 --- a/fs/bcachefs/compress.h +++ b/fs/bcachefs/compress.h @@ -47,8 +47,8 @@ static inline enum bch_compression_type bch2_compression_opt_to_type(unsigned v) return __bch2_compression_opt_to_type[bch2_compression_decode(v).type]; } -int bch2_bio_uncompress_inplace(struct bch_fs *, struct bio *, - struct bch_extent_crc_unpacked *); +struct bch_write_op; +int bch2_bio_uncompress_inplace(struct bch_write_op *, struct bio *); int bch2_bio_uncompress(struct bch_fs *, struct bio *, struct bio *, struct bvec_iter, struct bch_extent_crc_unpacked); unsigned bch2_bio_compress(struct bch_fs *, struct bio *, size_t *, diff --git a/fs/bcachefs/darray.h b/fs/bcachefs/darray.h index 8f4c3f0665c4..c6151495985f 100644 --- a/fs/bcachefs/darray.h +++ b/fs/bcachefs/darray.h @@ -83,7 +83,7 @@ int __bch2_darray_resize_noprof(darray_char *, size_t, size_t, gfp_t); for (typeof(&(_d).data[0]) _i = (_d).data; _i < (_d).data + (_d).nr; _i++) #define darray_for_each_reverse(_d, _i) \ - for (typeof(&(_d).data[0]) _i = (_d).data + (_d).nr - 1; _i >= (_d).data; --_i) + for (typeof(&(_d).data[0]) _i = (_d).data + (_d).nr - 1; _i >= (_d).data && (_d).nr; --_i) #define darray_init(_d) \ do { \ diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 8e75a852b358..337494facac6 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -91,15 +91,28 @@ static bool bkey_nocow_lock(struct bch_fs *c, struct moving_context *ctxt, struc return true; } -static void trace_move_extent_finish2(struct bch_fs *c, struct bkey_s_c k) +static noinline void trace_move_extent_finish2(struct data_update *u, + struct bkey_i *new, + struct bkey_i *insert) { - if (trace_move_extent_finish_enabled()) { - struct printbuf buf = PRINTBUF; + struct bch_fs *c = u->op.c; + struct printbuf buf = PRINTBUF; - bch2_bkey_val_to_text(&buf, c, k); - trace_move_extent_finish(c, buf.buf); - printbuf_exit(&buf); - } + prt_newline(&buf); + + bch2_data_update_to_text(&buf, u); + prt_newline(&buf); + + prt_str_indented(&buf, "new replicas:\t"); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(new)); + prt_newline(&buf); + + prt_str_indented(&buf, "insert:\t"); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert)); + prt_newline(&buf); + + trace_move_extent_finish(c, buf.buf); + printbuf_exit(&buf); } static void trace_move_extent_fail2(struct data_update *m, @@ -110,11 +123,8 @@ static void trace_move_extent_fail2(struct data_update *m, { struct bch_fs *c = m->op.c; struct bkey_s_c old = bkey_i_to_s_c(m->k.k); - const union bch_extent_entry *entry; - struct bch_extent_ptr *ptr; - struct extent_ptr_decoded p; struct printbuf buf = PRINTBUF; - unsigned i, rewrites_found = 0; + unsigned rewrites_found = 0; if (!trace_move_extent_fail_enabled()) return; @@ -122,27 +132,25 @@ static void trace_move_extent_fail2(struct data_update *m, prt_str(&buf, msg); if (insert) { - i = 0; + const union bch_extent_entry *entry; + struct bch_extent_ptr *ptr; + struct extent_ptr_decoded p; + + unsigned ptr_bit = 1; bkey_for_each_ptr_decode(old.k, bch2_bkey_ptrs_c(old), p, entry) { - if (((1U << i) & m->data_opts.rewrite_ptrs) && + if ((ptr_bit & m->data_opts.rewrite_ptrs) && (ptr = bch2_extent_has_ptr(old, p, bkey_i_to_s(insert))) && !ptr->cached) - rewrites_found |= 1U << i; - i++; + rewrites_found |= ptr_bit; + ptr_bit <<= 1; } } - prt_printf(&buf, "\nrewrite ptrs: %u%u%u%u", - (m->data_opts.rewrite_ptrs & (1 << 0)) != 0, - (m->data_opts.rewrite_ptrs & (1 << 1)) != 0, - (m->data_opts.rewrite_ptrs & (1 << 2)) != 0, - (m->data_opts.rewrite_ptrs & (1 << 3)) != 0); + prt_str(&buf, "rewrites found:\t"); + bch2_prt_u64_base2(&buf, rewrites_found); + prt_newline(&buf); - prt_printf(&buf, "\nrewrites found: %u%u%u%u", - (rewrites_found & (1 << 0)) != 0, - (rewrites_found & (1 << 1)) != 0, - (rewrites_found & (1 << 2)) != 0, - (rewrites_found & (1 << 3)) != 0); + bch2_data_update_opts_to_text(&buf, c, &m->op.opts, &m->data_opts); prt_str(&buf, "\nold: "); bch2_bkey_val_to_text(&buf, c, old); @@ -194,7 +202,7 @@ static int __bch2_data_update_index_update(struct btree_trans *trans, struct bpos next_pos; bool should_check_enospc; s64 i_sectors_delta = 0, disk_sectors_delta = 0; - unsigned rewrites_found = 0, durability, i; + unsigned rewrites_found = 0, durability, ptr_bit; bch2_trans_begin(trans); @@ -231,16 +239,16 @@ static int __bch2_data_update_index_update(struct btree_trans *trans, * * Fist, drop rewrite_ptrs from @new: */ - i = 0; + ptr_bit = 1; bkey_for_each_ptr_decode(old.k, bch2_bkey_ptrs_c(old), p, entry_c) { - if (((1U << i) & m->data_opts.rewrite_ptrs) && + if ((ptr_bit & m->data_opts.rewrite_ptrs) && (ptr = bch2_extent_has_ptr(old, p, bkey_i_to_s(insert))) && !ptr->cached) { bch2_extent_ptr_set_cached(c, &m->op.opts, bkey_i_to_s(insert), ptr); - rewrites_found |= 1U << i; + rewrites_found |= ptr_bit; } - i++; + ptr_bit <<= 1; } if (m->data_opts.rewrite_ptrs && @@ -323,8 +331,11 @@ restart_drop_extra_replicas: * it's been hard to reproduce, so this should give us some more * information when it does occur: */ - int invalid = bch2_bkey_validate(c, bkey_i_to_s_c(insert), __btree_node_type(0, m->btree_id), - BCH_VALIDATE_commit); + int invalid = bch2_bkey_validate(c, bkey_i_to_s_c(insert), + (struct bkey_validate_context) { + .btree = m->btree_id, + .flags = BCH_VALIDATE_commit, + }); if (invalid) { struct printbuf buf = PRINTBUF; @@ -362,7 +373,7 @@ restart_drop_extra_replicas: k.k->p, bkey_start_pos(&insert->k)) ?: bch2_insert_snapshot_whiteouts(trans, m->btree_id, k.k->p, insert->k.p) ?: - bch2_bkey_set_needs_rebalance(c, insert, &op->opts) ?: + bch2_bkey_set_needs_rebalance(c, &op->opts, insert) ?: bch2_trans_update(trans, &iter, insert, BTREE_UPDATE_internal_snapshot_node) ?: bch2_trans_commit(trans, &op->res, @@ -374,7 +385,8 @@ restart_drop_extra_replicas: bch2_btree_iter_set_pos(&iter, next_pos); this_cpu_add(c->counters[BCH_COUNTER_move_extent_finish], new->k.size); - trace_move_extent_finish2(c, bkey_i_to_s_c(&new->k_i)); + if (trace_move_extent_finish_enabled()) + trace_move_extent_finish2(m, &new->k_i, insert); } err: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) @@ -527,34 +539,38 @@ void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c, struct data_update_opts *data_opts) { printbuf_tabstop_push(out, 20); - prt_str(out, "rewrite ptrs:\t"); + + prt_str_indented(out, "rewrite ptrs:\t"); bch2_prt_u64_base2(out, data_opts->rewrite_ptrs); prt_newline(out); - prt_str(out, "kill ptrs:\t"); + prt_str_indented(out, "kill ptrs:\t"); bch2_prt_u64_base2(out, data_opts->kill_ptrs); prt_newline(out); - prt_str(out, "target:\t"); + prt_str_indented(out, "target:\t"); bch2_target_to_text(out, c, data_opts->target); prt_newline(out); - prt_str(out, "compression:\t"); - bch2_compression_opt_to_text(out, background_compression(*io_opts)); + prt_str_indented(out, "compression:\t"); + bch2_compression_opt_to_text(out, io_opts->background_compression); prt_newline(out); - prt_str(out, "opts.replicas:\t"); + prt_str_indented(out, "opts.replicas:\t"); prt_u64(out, io_opts->data_replicas); + prt_newline(out); - prt_str(out, "extra replicas:\t"); + prt_str_indented(out, "extra replicas:\t"); prt_u64(out, data_opts->extra_replicas); } void bch2_data_update_to_text(struct printbuf *out, struct data_update *m) { - bch2_bkey_val_to_text(out, m->op.c, bkey_i_to_s_c(m->k.k)); - prt_newline(out); bch2_data_update_opts_to_text(out, m->op.c, &m->op.opts, &m->data_opts); + prt_newline(out); + + prt_str_indented(out, "old key:\t"); + bch2_bkey_val_to_text(out, m->op.c, bkey_i_to_s_c(m->k.k)); } int bch2_extent_drop_ptrs(struct btree_trans *trans, @@ -614,7 +630,7 @@ int bch2_data_update_init(struct btree_trans *trans, struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; struct extent_ptr_decoded p; - unsigned i, reserve_sectors = k.k->size * data_opts.extra_replicas; + unsigned reserve_sectors = k.k->size * data_opts.extra_replicas; int ret = 0; /* @@ -622,7 +638,7 @@ int bch2_data_update_init(struct btree_trans *trans, * and we have to check for this because we go rw before repairing the * snapshots table - just skip it, we can move it later. */ - if (unlikely(k.k->p.snapshot && !bch2_snapshot_equiv(c, k.k->p.snapshot))) + if (unlikely(k.k->p.snapshot && !bch2_snapshot_exists(c, k.k->p.snapshot))) return -BCH_ERR_data_update_done; if (!bkey_get_dev_refs(c, k)) @@ -652,22 +668,22 @@ int bch2_data_update_init(struct btree_trans *trans, BCH_WRITE_DATA_ENCODED| BCH_WRITE_MOVE| m->data_opts.write_flags; - m->op.compression_opt = background_compression(io_opts); + m->op.compression_opt = io_opts.background_compression; m->op.watermark = m->data_opts.btree_insert_flags & BCH_WATERMARK_MASK; unsigned durability_have = 0, durability_removing = 0; - i = 0; + unsigned ptr_bit = 1; bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { if (!p.ptr.cached) { rcu_read_lock(); - if (BIT(i) & m->data_opts.rewrite_ptrs) { + if (ptr_bit & m->data_opts.rewrite_ptrs) { if (crc_is_compressed(p.crc)) reserve_sectors += k.k->size; m->op.nr_replicas += bch2_extent_ptr_desired_durability(c, &p); durability_removing += bch2_extent_ptr_desired_durability(c, &p); - } else if (!(BIT(i) & m->data_opts.kill_ptrs)) { + } else if (!(ptr_bit & m->data_opts.kill_ptrs)) { bch2_dev_list_add_dev(&m->op.devs_have, p.ptr.dev); durability_have += bch2_extent_ptr_durability(c, &p); } @@ -687,7 +703,7 @@ int bch2_data_update_init(struct btree_trans *trans, if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible) m->op.incompressible = true; - i++; + ptr_bit <<= 1; } unsigned durability_required = max(0, (int) (io_opts.data_replicas - durability_have)); @@ -750,14 +766,14 @@ out: void bch2_data_update_opts_normalize(struct bkey_s_c k, struct data_update_opts *opts) { struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - unsigned i = 0; + unsigned ptr_bit = 1; bkey_for_each_ptr(ptrs, ptr) { - if ((opts->rewrite_ptrs & (1U << i)) && ptr->cached) { - opts->kill_ptrs |= 1U << i; - opts->rewrite_ptrs ^= 1U << i; + if ((opts->rewrite_ptrs & ptr_bit) && ptr->cached) { + opts->kill_ptrs |= ptr_bit; + opts->rewrite_ptrs ^= ptr_bit; } - i++; + ptr_bit <<= 1; } } diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c index 45aec1afdb0e..55333e82d1fe 100644 --- a/fs/bcachefs/debug.c +++ b/fs/bcachefs/debug.c @@ -20,6 +20,7 @@ #include "extents.h" #include "fsck.h" #include "inode.h" +#include "journal_reclaim.h" #include "super.h" #include @@ -472,7 +473,9 @@ static void bch2_cached_btree_node_to_text(struct printbuf *out, struct bch_fs * if (!out->nr_tabstops) printbuf_tabstop_push(out, 32); - prt_printf(out, "%px btree=%s l=%u\n", b, bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_printf(out, "%px ", b); + bch2_btree_id_level_to_text(out, b->c.btree_id, b->c.level); + prt_printf(out, "\n"); printbuf_indent_add(out, 2); diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c index faffc98d5605..600eee936f13 100644 --- a/fs/bcachefs/dirent.c +++ b/fs/bcachefs/dirent.c @@ -101,7 +101,7 @@ const struct bch_hash_desc bch2_dirent_hash_desc = { }; int bch2_dirent_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); struct qstr d_name = bch2_dirent_get_name(d); @@ -120,7 +120,7 @@ int bch2_dirent_validate(struct bch_fs *c, struct bkey_s_c k, * Check new keys don't exceed the max length * (older keys may be larger.) */ - bkey_fsck_err_on((flags & BCH_VALIDATE_commit) && d_name.len > BCH_NAME_MAX, + bkey_fsck_err_on((from.flags & BCH_VALIDATE_commit) && d_name.len > BCH_NAME_MAX, c, dirent_name_too_long, "dirent name too big (%u > %u)", d_name.len, BCH_NAME_MAX); @@ -266,7 +266,7 @@ int bch2_dirent_read_target(struct btree_trans *trans, subvol_inum dir, } else { target->subvol = le32_to_cpu(d.v->d_child_subvol); - ret = bch2_subvolume_get(trans, target->subvol, true, BTREE_ITER_cached, &s); + ret = bch2_subvolume_get(trans, target->subvol, true, &s); target->inum = le64_to_cpu(s.inode); } @@ -500,7 +500,7 @@ int bch2_empty_dir_snapshot(struct btree_trans *trans, u64 dir, u32 subvol, u32 struct bkey_s_c k; int ret; - for_each_btree_key_upto_norestart(trans, iter, BTREE_ID_dirents, + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_dirents, SPOS(dir, 0, snapshot), POS(dir, U64_MAX), 0, k, ret) if (k.k->type == KEY_TYPE_dirent) { @@ -549,7 +549,7 @@ int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx) bch2_bkey_buf_init(&sk); int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_dirents, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_dirents, POS(inum.inum, ctx->pos), POS(inum.inum, U64_MAX), inum.subvol, 0, k, ({ diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h index 53ad99666022..a633f83c1ac7 100644 --- a/fs/bcachefs/dirent.h +++ b/fs/bcachefs/dirent.h @@ -4,10 +4,10 @@ #include "str_hash.h" -enum bch_validate_flags; extern const struct bch_hash_desc bch2_dirent_hash_desc; -int bch2_dirent_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_dirent_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_dirent_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_dirent ((struct bkey_ops) { \ @@ -31,6 +31,11 @@ static inline unsigned dirent_val_u64s(unsigned len) sizeof(u64)); } +static inline unsigned int dirent_occupied_size(const struct qstr *name) +{ + return (BKEY_U64s + dirent_val_u64s(name->len)) * sizeof(u64); +} + int bch2_dirent_read_target(struct btree_trans *, subvol_inum, struct bkey_s_c_dirent, subvol_inum *); diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index 07eb8fa1b026..b32e91ba8be8 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -79,6 +79,8 @@ static inline void accounting_key_init(struct bkey_i *k, struct disk_accounting_ memcpy_u64s_small(acc->v.d, d, nr); } +static int bch2_accounting_update_sb_one(struct bch_fs *, struct bpos); + int bch2_disk_accounting_mod(struct btree_trans *trans, struct disk_accounting_pos *k, s64 *d, unsigned nr, bool gc) @@ -96,9 +98,16 @@ int bch2_disk_accounting_mod(struct btree_trans *trans, accounting_key_init(&k_i.k, k, d, nr); - return likely(!gc) - ? bch2_trans_update_buffered(trans, BTREE_ID_accounting, &k_i.k) - : bch2_accounting_mem_add(trans, bkey_i_to_s_c_accounting(&k_i.k), true); + if (unlikely(gc)) { + int ret = bch2_accounting_mem_add(trans, bkey_i_to_s_c_accounting(&k_i.k), true); + if (ret == -BCH_ERR_btree_insert_need_mark_replicas) + ret = drop_locks_do(trans, + bch2_accounting_update_sb_one(trans->c, disk_accounting_pos_to_bpos(k))) ?: + bch2_accounting_mem_add(trans, bkey_i_to_s_c_accounting(&k_i.k), true); + return ret; + } else { + return bch2_trans_update_buffered(trans, BTREE_ID_accounting, &k_i.k); + } } int bch2_mod_dev_cached_sectors(struct btree_trans *trans, @@ -127,14 +136,15 @@ static inline bool is_zero(char *start, char *end) #define field_end(p, member) (((void *) (&p.member)) + sizeof(p.member)) int bch2_accounting_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct disk_accounting_pos acc_k; bpos_to_disk_accounting_pos(&acc_k, k.k->p); void *end = &acc_k + 1; int ret = 0; - bkey_fsck_err_on(bversion_zero(k.k->bversion), + bkey_fsck_err_on((from.flags & BCH_VALIDATE_commit) && + bversion_zero(k.k->bversion), c, accounting_key_version_0, "accounting key with version=0"); @@ -217,7 +227,8 @@ void bch2_accounting_key_to_text(struct printbuf *out, struct disk_accounting_po prt_printf(out, "id=%u", k->snapshot.id); break; case BCH_DISK_ACCOUNTING_btree: - prt_printf(out, "btree=%s", bch2_btree_id_str(k->btree.id)); + prt_str(out, "btree="); + bch2_btree_id_to_text(out, k->btree.id); break; } } @@ -243,10 +254,10 @@ void bch2_accounting_swab(struct bkey_s k) } static inline void __accounting_to_replicas(struct bch_replicas_entry_v1 *r, - struct disk_accounting_pos acc) + struct disk_accounting_pos *acc) { - unsafe_memcpy(r, &acc.replicas, - replicas_entry_bytes(&acc.replicas), + unsafe_memcpy(r, &acc->replicas, + replicas_entry_bytes(&acc->replicas), "variable length struct"); } @@ -257,7 +268,7 @@ static inline bool accounting_to_replicas(struct bch_replicas_entry_v1 *r, struc switch (acc_k.type) { case BCH_DISK_ACCOUNTING_replicas: - __accounting_to_replicas(r, acc_k); + __accounting_to_replicas(r, &acc_k); return true; default: return false; @@ -322,6 +333,14 @@ static int __bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accoun eytzinger0_sort(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), accounting_pos_cmp, NULL); + + if (trace_accounting_mem_insert_enabled()) { + struct printbuf buf = PRINTBUF; + + bch2_accounting_to_text(&buf, c, a.s_c); + trace_accounting_mem_insert(c, buf.buf); + printbuf_exit(&buf); + } return 0; err: free_percpu(n.v[1]); @@ -461,32 +480,6 @@ int bch2_fs_accounting_read(struct bch_fs *c, darray_char *out_buf, unsigned acc return ret; } -void bch2_fs_accounting_to_text(struct printbuf *out, struct bch_fs *c) -{ - struct bch_accounting_mem *acc = &c->accounting; - - percpu_down_read(&c->mark_lock); - out->atomic++; - - eytzinger0_for_each(i, acc->k.nr) { - struct disk_accounting_pos acc_k; - bpos_to_disk_accounting_pos(&acc_k, acc->k.data[i].pos); - - bch2_accounting_key_to_text(out, &acc_k); - - u64 v[BCH_ACCOUNTING_MAX_COUNTERS]; - bch2_accounting_mem_read_counters(acc, i, v, ARRAY_SIZE(v), false); - - prt_str(out, ":"); - for (unsigned j = 0; j < acc->k.data[i].nr_counters; j++) - prt_printf(out, " %llu", v[j]); - prt_newline(out); - } - - --out->atomic; - percpu_up_read(&c->mark_lock); -} - static void bch2_accounting_free_counters(struct bch_accounting_mem *acc, bool gc) { darray_for_each(acc->k, e) { @@ -625,7 +618,7 @@ static int bch2_disk_accounting_validate_late(struct btree_trans *trans, switch (acc.type) { case BCH_DISK_ACCOUNTING_replicas: { struct bch_replicas_padded r; - __accounting_to_replicas(&r.e, acc); + __accounting_to_replicas(&r.e, &acc); for (unsigned i = 0; i < r.e.nr_devs; i++) if (r.e.devs[i] != BCH_SB_MEMBER_INVALID && @@ -699,11 +692,45 @@ int bch2_accounting_read(struct bch_fs *c) struct btree_trans *trans = bch2_trans_get(c); struct printbuf buf = PRINTBUF; - int ret = for_each_btree_key(trans, iter, - BTREE_ID_accounting, POS_MIN, + /* + * We might run more than once if we rewind to start topology repair or + * btree node scan - and those might cause us to get different results, + * so we can't just skip if we've already run. + * + * Instead, zero out any accounting we have: + */ + percpu_down_write(&c->mark_lock); + darray_for_each(acc->k, e) + percpu_memset(e->v[0], 0, sizeof(u64) * e->nr_counters); + for_each_member_device(c, ca) + percpu_memset(ca->usage, 0, sizeof(*ca->usage)); + percpu_memset(c->usage, 0, sizeof(*c->usage)); + percpu_up_write(&c->mark_lock); + + struct btree_iter iter; + bch2_trans_iter_init(trans, &iter, BTREE_ID_accounting, POS_MIN, + BTREE_ITER_prefetch|BTREE_ITER_all_snapshots); + iter.flags &= ~BTREE_ITER_with_journal; + int ret = for_each_btree_key_continue(trans, iter, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, ({ struct bkey u; struct bkey_s_c k = bch2_btree_path_peek_slot_exact(btree_iter_path(trans, &iter), &u); + + if (k.k->type != KEY_TYPE_accounting) + continue; + + struct disk_accounting_pos acc_k; + bpos_to_disk_accounting_pos(&acc_k, k.k->p); + + if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR) + break; + + if (!bch2_accounting_is_mem(acc_k)) { + struct disk_accounting_pos next = { .type = acc_k.type + 1 }; + bch2_btree_iter_set_pos(&iter, disk_accounting_pos_to_bpos(&next)); + continue; + } + accounting_read_key(trans, k); })); if (ret) @@ -715,6 +742,12 @@ int bch2_accounting_read(struct bch_fs *c) darray_for_each(*keys, i) { if (i->k->k.type == KEY_TYPE_accounting) { + struct disk_accounting_pos acc_k; + bpos_to_disk_accounting_pos(&acc_k, i->k->k.p); + + if (!bch2_accounting_is_mem(acc_k)) + continue; + struct bkey_s_c k = bkey_i_to_s_c(i->k); unsigned idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), @@ -748,15 +781,16 @@ int bch2_accounting_read(struct bch_fs *c) keys->gap = keys->nr = dst - keys->data; percpu_down_write(&c->mark_lock); - unsigned i = 0; - while (i < acc->k.nr) { - unsigned idx = inorder_to_eytzinger0(i, acc->k.nr); + darray_for_each_reverse(acc->k, i) { struct disk_accounting_pos acc_k; - bpos_to_disk_accounting_pos(&acc_k, acc->k.data[idx].pos); + bpos_to_disk_accounting_pos(&acc_k, i->pos); u64 v[BCH_ACCOUNTING_MAX_COUNTERS]; - bch2_accounting_mem_read_counters(acc, idx, v, ARRAY_SIZE(v), false); + memset(v, 0, sizeof(v)); + + for (unsigned j = 0; j < i->nr_counters; j++) + v[j] = percpu_u64_get(i->v[0] + j); /* * If the entry counters are zeroed, it should be treated as @@ -765,26 +799,25 @@ int bch2_accounting_read(struct bch_fs *c) * Remove it, so that if it's re-added it gets re-marked in the * superblock: */ - ret = bch2_is_zero(v, sizeof(v[0]) * acc->k.data[idx].nr_counters) + ret = bch2_is_zero(v, sizeof(v[0]) * i->nr_counters) ? -BCH_ERR_remove_disk_accounting_entry - : bch2_disk_accounting_validate_late(trans, acc_k, - v, acc->k.data[idx].nr_counters); + : bch2_disk_accounting_validate_late(trans, acc_k, v, i->nr_counters); if (ret == -BCH_ERR_remove_disk_accounting_entry) { - free_percpu(acc->k.data[idx].v[0]); - free_percpu(acc->k.data[idx].v[1]); - darray_remove_item(&acc->k, &acc->k.data[idx]); - eytzinger0_sort(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), - accounting_pos_cmp, NULL); + free_percpu(i->v[0]); + free_percpu(i->v[1]); + darray_remove_item(&acc->k, i); ret = 0; continue; } if (ret) goto fsck_err; - i++; } + eytzinger0_sort(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), + accounting_pos_cmp, NULL); + preempt_disable(); struct bch_fs_usage_base *usage = this_cpu_ptr(c->usage); @@ -804,7 +837,7 @@ int bch2_accounting_read(struct bch_fs *c) break; case BCH_DISK_ACCOUNTING_dev_data_type: rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu(c, k.dev_data_type.dev); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, k.dev_data_type.dev); if (ca) { struct bch_dev_usage_type __percpu *d = &ca->usage->d[k.dev_data_type.data_type]; percpu_u64_set(&d->buckets, v[0]); @@ -881,10 +914,13 @@ void bch2_verify_accounting_clean(struct bch_fs *c) bpos_to_disk_accounting_pos(&acc_k, k.k->p); if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR) - continue; + break; - if (acc_k.type == BCH_DISK_ACCOUNTING_inum) + if (!bch2_accounting_is_mem(acc_k)) { + struct disk_accounting_pos next = { .type = acc_k.type + 1 }; + bch2_btree_iter_set_pos(&iter, disk_accounting_pos_to_bpos(&next)); continue; + } bch2_accounting_mem_read(c, k.k->p, v, nr); @@ -910,7 +946,7 @@ void bch2_verify_accounting_clean(struct bch_fs *c) break; case BCH_DISK_ACCOUNTING_dev_data_type: { rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu(c, acc_k.dev_data_type.dev); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, acc_k.dev_data_type.dev); if (!ca) { rcu_read_unlock(); continue; diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h index 4ea6c8a092bc..5360cbb3ec29 100644 --- a/fs/bcachefs/disk_accounting.h +++ b/fs/bcachefs/disk_accounting.h @@ -2,6 +2,7 @@ #ifndef _BCACHEFS_DISK_ACCOUNTING_H #define _BCACHEFS_DISK_ACCOUNTING_H +#include "btree_update.h" #include "eytzinger.h" #include "sb-members.h" @@ -62,27 +63,32 @@ static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage static inline void bpos_to_disk_accounting_pos(struct disk_accounting_pos *acc, struct bpos p) { - acc->_pad = p; + BUILD_BUG_ON(sizeof(*acc) != sizeof(p)); + #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - bch2_bpos_swab(&acc->_pad); + acc->_pad = p; +#else + memcpy_swab(acc, &p, sizeof(p)); #endif } -static inline struct bpos disk_accounting_pos_to_bpos(struct disk_accounting_pos *k) +static inline struct bpos disk_accounting_pos_to_bpos(struct disk_accounting_pos *acc) { - struct bpos ret = k->_pad; - + struct bpos p; #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - bch2_bpos_swab(&ret); + p = acc->_pad; +#else + memcpy_swab(&p, acc, sizeof(p)); #endif - return ret; + return p; } int bch2_disk_accounting_mod(struct btree_trans *, struct disk_accounting_pos *, s64 *, unsigned, bool); int bch2_mod_dev_cached_sectors(struct btree_trans *, unsigned, s64, bool); -int bch2_accounting_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_accounting_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_accounting_key_to_text(struct printbuf *, struct disk_accounting_pos *); void bch2_accounting_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_accounting_swab(struct bkey_s); @@ -112,6 +118,12 @@ enum bch_accounting_mode { int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode); void bch2_accounting_mem_gc(struct bch_fs *); +static inline bool bch2_accounting_is_mem(struct disk_accounting_pos acc) +{ + return acc.type < BCH_DISK_ACCOUNTING_TYPE_NR && + acc.type != BCH_DISK_ACCOUNTING_inum; +} + /* * Update in memory counters so they match the btree update we're doing; called * from transaction commit path @@ -126,9 +138,10 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, bpos_to_disk_accounting_pos(&acc_k, a.k->p); bool gc = mode == BCH_ACCOUNTING_gc; - EBUG_ON(gc && !acc->gc_running); + if (gc && !acc->gc_running) + return 0; - if (acc_k.type == BCH_DISK_ACCOUNTING_inum) + if (!bch2_accounting_is_mem(acc_k)) return 0; if (mode == BCH_ACCOUNTING_normal) { @@ -141,7 +154,7 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, break; case BCH_DISK_ACCOUNTING_dev_data_type: rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu(c, acc_k.dev_data_type.dev); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, acc_k.dev_data_type.dev); if (ca) { this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].buckets, a.v->d[0]); this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].sectors, a.v->d[1]); @@ -204,9 +217,45 @@ static inline void bch2_accounting_mem_read(struct bch_fs *c, struct bpos p, bch2_accounting_mem_read_counters(acc, idx, v, nr, false); } +static inline struct bversion journal_pos_to_bversion(struct journal_res *res, unsigned offset) +{ + EBUG_ON(!res->ref); + + return (struct bversion) { + .hi = res->seq >> 32, + .lo = (res->seq << 32) | (res->offset + offset), + }; +} + +static inline int bch2_accounting_trans_commit_hook(struct btree_trans *trans, + struct bkey_i_accounting *a, + unsigned commit_flags) +{ + a->k.bversion = journal_pos_to_bversion(&trans->journal_res, + (u64 *) a - (u64 *) trans->journal_entries); + + EBUG_ON(bversion_zero(a->k.bversion)); + + return likely(!(commit_flags & BCH_TRANS_COMMIT_skip_accounting_apply)) + ? bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal) + : 0; +} + +static inline void bch2_accounting_trans_commit_revert(struct btree_trans *trans, + struct bkey_i_accounting *a_i, + unsigned commit_flags) +{ + if (likely(!(commit_flags & BCH_TRANS_COMMIT_skip_accounting_apply))) { + struct bkey_s_accounting a = accounting_i_to_s(a_i); + + bch2_accounting_neg(a); + bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal); + bch2_accounting_neg(a); + } +} + int bch2_fs_replicas_usage_read(struct bch_fs *, darray_char *); int bch2_fs_accounting_read(struct bch_fs *, darray_char *, unsigned); -void bch2_fs_accounting_to_text(struct printbuf *, struct bch_fs *); int bch2_gc_accounting_start(struct bch_fs *); int bch2_gc_accounting_done(struct bch_fs *); diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index 6094afb0c6be..d2a5e76e6479 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -26,6 +26,7 @@ #include "util.h" #include +#include #ifdef __KERNEL__ @@ -109,7 +110,7 @@ struct ec_bio { /* Stripes btree keys: */ int bch2_stripe_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { const struct bch_stripe *s = bkey_s_c_to_stripe(k).v; int ret = 0; @@ -129,7 +130,7 @@ int bch2_stripe_validate(struct bch_fs *c, struct bkey_s_c k, "invalid csum granularity (%u >= 64)", s->csum_granularity_bits); - ret = bch2_bkey_ptrs_validate(c, k, flags); + ret = bch2_bkey_ptrs_validate(c, k, from); fsck_err: return ret; } @@ -304,13 +305,12 @@ static int mark_stripe_bucket(struct btree_trans *trans, } if (flags & BTREE_TRIGGER_gc) { - percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, bucket.offset); if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u\n %s", ptr->dev, (bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) { ret = -BCH_ERR_mark_stripe; - goto err_unlock; + goto err; } bucket_lock(g); @@ -318,8 +318,7 @@ static int mark_stripe_bucket(struct btree_trans *trans, ret = __mark_stripe_bucket(trans, ca, s, ptr_idx, deleting, bucket, &new, flags); alloc_to_bucket(g, new); bucket_unlock(g); -err_unlock: - percpu_up_read(&c->mark_lock); + if (!ret) ret = bch2_alloc_key_to_dev_counters(trans, ca, &old, &new, flags); } @@ -732,7 +731,7 @@ static void ec_block_endio(struct bio *bio) ? BCH_MEMBER_ERROR_write : BCH_MEMBER_ERROR_read, "erasure coding %s error: %s", - bio_data_dir(bio) ? "write" : "read", + str_write_read(bio_data_dir(bio)), bch2_blk_status_to_str(bio->bi_status))) clear_bit(ec_bio->idx, ec_bio->buf->valid); @@ -909,7 +908,7 @@ err: bch2_bkey_val_to_text(&msgbuf, c, orig_k); bch_err_ratelimited(c, "error doing reconstruct read: %s\n %s", msg, msgbuf.buf); - printbuf_exit(&msgbuf);; + printbuf_exit(&msgbuf); ret = -BCH_ERR_stripe_reconstruct; goto out; } @@ -1266,11 +1265,11 @@ static int ec_stripe_update_extent(struct btree_trans *trans, struct bch_dev *ca, struct bpos bucket, u8 gen, struct ec_stripe_buf *s, - struct bpos *bp_pos) + struct bkey_s_c_backpointer bp, + struct bkey_buf *last_flushed) { struct bch_stripe *v = &bkey_i_to_stripe(&s->key)->v; struct bch_fs *c = trans->c; - struct bch_backpointer bp; struct btree_iter iter; struct bkey_s_c k; const struct bch_extent_ptr *ptr_c; @@ -1279,33 +1278,26 @@ static int ec_stripe_update_extent(struct btree_trans *trans, struct bkey_i *n; int ret, dev, block; - ret = bch2_get_next_backpointer(trans, ca, bucket, gen, - bp_pos, &bp, BTREE_ITER_cached); - if (ret) - return ret; - if (bpos_eq(*bp_pos, SPOS_MAX)) - return 0; - - if (bp.level) { + if (bp.v->level) { struct printbuf buf = PRINTBUF; struct btree_iter node_iter; struct btree *b; - b = bch2_backpointer_get_node(trans, &node_iter, *bp_pos, bp); + b = bch2_backpointer_get_node(trans, bp, &node_iter, last_flushed); bch2_trans_iter_exit(trans, &node_iter); if (!b) return 0; prt_printf(&buf, "found btree node in erasure coded bucket: b=%px\n", b); - bch2_backpointer_to_text(&buf, &bp); + bch2_bkey_val_to_text(&buf, c, bp.s_c); bch2_fs_inconsistent(c, "%s", buf.buf); printbuf_exit(&buf); return -EIO; } - k = bch2_backpointer_get_key(trans, &iter, *bp_pos, bp, BTREE_ITER_intent); + k = bch2_backpointer_get_key(trans, bp, &iter, BTREE_ITER_intent, last_flushed); ret = bkey_err(k); if (ret) return ret; @@ -1364,7 +1356,6 @@ static int ec_stripe_update_bucket(struct btree_trans *trans, struct ec_stripe_b struct bch_fs *c = trans->c; struct bch_stripe *v = &bkey_i_to_stripe(&s->key)->v; struct bch_extent_ptr ptr = v->ptrs[block]; - struct bpos bp_pos = POS_MIN; int ret = 0; struct bch_dev *ca = bch2_dev_tryget(c, ptr.dev); @@ -1373,19 +1364,27 @@ static int ec_stripe_update_bucket(struct btree_trans *trans, struct ec_stripe_b struct bpos bucket_pos = PTR_BUCKET_POS(ca, &ptr); - while (1) { - ret = commit_do(trans, NULL, NULL, - BCH_TRANS_COMMIT_no_check_rw| - BCH_TRANS_COMMIT_no_enospc, - ec_stripe_update_extent(trans, ca, bucket_pos, ptr.gen, s, &bp_pos)); - if (ret) - break; - if (bkey_eq(bp_pos, POS_MAX)) + struct bkey_buf last_flushed; + bch2_bkey_buf_init(&last_flushed); + bkey_init(&last_flushed.k->k); + + ret = for_each_btree_key_max_commit(trans, bp_iter, BTREE_ID_backpointers, + bucket_pos_to_bp_start(ca, bucket_pos), + bucket_pos_to_bp_end(ca, bucket_pos), 0, bp_k, + NULL, NULL, + BCH_TRANS_COMMIT_no_check_rw| + BCH_TRANS_COMMIT_no_enospc, ({ + if (bkey_ge(bp_k.k->p, bucket_pos_to_bp(ca, bpos_nosnap_successor(bucket_pos), 0))) break; - bp_pos = bpos_nosnap_successor(bp_pos); - } + if (bp_k.k->type != KEY_TYPE_backpointer) + continue; + ec_stripe_update_extent(trans, ca, bucket_pos, ptr.gen, s, + bkey_s_c_to_backpointer(bp_k), &last_flushed); + })); + + bch2_bkey_buf_exit(&last_flushed, c); bch2_dev_put(ca); return ret; } @@ -1707,7 +1706,7 @@ static void ec_stripe_key_init(struct bch_fs *c, set_bkey_val_u64s(&s->k, u64s); } -static int ec_new_stripe_alloc(struct bch_fs *c, struct ec_stripe_head *h) +static struct ec_stripe_new *ec_new_stripe_alloc(struct bch_fs *c, struct ec_stripe_head *h) { struct ec_stripe_new *s; @@ -1715,7 +1714,7 @@ static int ec_new_stripe_alloc(struct bch_fs *c, struct ec_stripe_head *h) s = kzalloc(sizeof(*s), GFP_KERNEL); if (!s) - return -BCH_ERR_ENOMEM_ec_new_stripe_alloc; + return NULL; mutex_init(&s->lock); closure_init(&s->iodone, NULL); @@ -1730,10 +1729,7 @@ static int ec_new_stripe_alloc(struct bch_fs *c, struct ec_stripe_head *h) ec_stripe_key_init(c, &s->new_stripe.key, s->nr_data, s->nr_parity, h->blocksize, h->disk_label); - - h->s = s; - h->nr_created++; - return 0; + return s; } static void ec_stripe_head_devs_update(struct bch_fs *c, struct ec_stripe_head *h) @@ -1878,25 +1874,26 @@ err: return h; } -static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_head *h, +static int new_stripe_alloc_buckets(struct btree_trans *trans, + struct ec_stripe_head *h, struct ec_stripe_new *s, enum bch_watermark watermark, struct closure *cl) { struct bch_fs *c = trans->c; struct bch_devs_mask devs = h->devs; struct open_bucket *ob; struct open_buckets buckets; - struct bch_stripe *v = &bkey_i_to_stripe(&h->s->new_stripe.key)->v; + struct bch_stripe *v = &bkey_i_to_stripe(&s->new_stripe.key)->v; unsigned i, j, nr_have_parity = 0, nr_have_data = 0; bool have_cache = true; int ret = 0; - BUG_ON(v->nr_blocks != h->s->nr_data + h->s->nr_parity); - BUG_ON(v->nr_redundant != h->s->nr_parity); + BUG_ON(v->nr_blocks != s->nr_data + s->nr_parity); + BUG_ON(v->nr_redundant != s->nr_parity); /* * We bypass the sector allocator which normally does this: */ bitmap_and(devs.d, devs.d, c->rw_devs[BCH_DATA_user].d, BCH_SB_MEMBERS_MAX); - for_each_set_bit(i, h->s->blocks_gotten, v->nr_blocks) { + for_each_set_bit(i, s->blocks_gotten, v->nr_blocks) { /* * Note: we don't yet repair invalid blocks (failed/removed * devices) when reusing stripes - we still need a codepath to @@ -1906,21 +1903,21 @@ static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_ if (v->ptrs[i].dev != BCH_SB_MEMBER_INVALID) __clear_bit(v->ptrs[i].dev, devs.d); - if (i < h->s->nr_data) + if (i < s->nr_data) nr_have_data++; else nr_have_parity++; } - BUG_ON(nr_have_data > h->s->nr_data); - BUG_ON(nr_have_parity > h->s->nr_parity); + BUG_ON(nr_have_data > s->nr_data); + BUG_ON(nr_have_parity > s->nr_parity); buckets.nr = 0; - if (nr_have_parity < h->s->nr_parity) { + if (nr_have_parity < s->nr_parity) { ret = bch2_bucket_alloc_set_trans(trans, &buckets, &h->parity_stripe, &devs, - h->s->nr_parity, + s->nr_parity, &nr_have_parity, &have_cache, 0, BCH_DATA_parity, @@ -1928,14 +1925,14 @@ static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_ cl); open_bucket_for_each(c, &buckets, ob, i) { - j = find_next_zero_bit(h->s->blocks_gotten, - h->s->nr_data + h->s->nr_parity, - h->s->nr_data); - BUG_ON(j >= h->s->nr_data + h->s->nr_parity); + j = find_next_zero_bit(s->blocks_gotten, + s->nr_data + s->nr_parity, + s->nr_data); + BUG_ON(j >= s->nr_data + s->nr_parity); - h->s->blocks[j] = buckets.v[i]; + s->blocks[j] = buckets.v[i]; v->ptrs[j] = bch2_ob_ptr(c, ob); - __set_bit(j, h->s->blocks_gotten); + __set_bit(j, s->blocks_gotten); } if (ret) @@ -1943,11 +1940,11 @@ static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_ } buckets.nr = 0; - if (nr_have_data < h->s->nr_data) { + if (nr_have_data < s->nr_data) { ret = bch2_bucket_alloc_set_trans(trans, &buckets, &h->block_stripe, &devs, - h->s->nr_data, + s->nr_data, &nr_have_data, &have_cache, 0, BCH_DATA_user, @@ -1955,13 +1952,13 @@ static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_ cl); open_bucket_for_each(c, &buckets, ob, i) { - j = find_next_zero_bit(h->s->blocks_gotten, - h->s->nr_data, 0); - BUG_ON(j >= h->s->nr_data); + j = find_next_zero_bit(s->blocks_gotten, + s->nr_data, 0); + BUG_ON(j >= s->nr_data); - h->s->blocks[j] = buckets.v[i]; + s->blocks[j] = buckets.v[i]; v->ptrs[j] = bch2_ob_ptr(c, ob); - __set_bit(j, h->s->blocks_gotten); + __set_bit(j, s->blocks_gotten); } if (ret) @@ -2007,12 +2004,54 @@ static s64 get_existing_stripe(struct bch_fs *c, return ret; } -static int __bch2_ec_stripe_head_reuse(struct btree_trans *trans, struct ec_stripe_head *h) +static int init_new_stripe_from_existing(struct bch_fs *c, struct ec_stripe_new *s) +{ + struct bch_stripe *new_v = &bkey_i_to_stripe(&s->new_stripe.key)->v; + struct bch_stripe *existing_v = &bkey_i_to_stripe(&s->existing_stripe.key)->v; + unsigned i; + + BUG_ON(existing_v->nr_redundant != s->nr_parity); + s->nr_data = existing_v->nr_blocks - + existing_v->nr_redundant; + + int ret = ec_stripe_buf_init(&s->existing_stripe, 0, le16_to_cpu(existing_v->sectors)); + if (ret) { + bch2_stripe_close(c, s); + return ret; + } + + BUG_ON(s->existing_stripe.size != le16_to_cpu(existing_v->sectors)); + + /* + * Free buckets we initially allocated - they might conflict with + * blocks from the stripe we're reusing: + */ + for_each_set_bit(i, s->blocks_gotten, new_v->nr_blocks) { + bch2_open_bucket_put(c, c->open_buckets + s->blocks[i]); + s->blocks[i] = 0; + } + memset(s->blocks_gotten, 0, sizeof(s->blocks_gotten)); + memset(s->blocks_allocated, 0, sizeof(s->blocks_allocated)); + + for (unsigned i = 0; i < existing_v->nr_blocks; i++) { + if (stripe_blockcount_get(existing_v, i)) { + __set_bit(i, s->blocks_gotten); + __set_bit(i, s->blocks_allocated); + } + + ec_block_io(c, &s->existing_stripe, READ, i, &s->iodone); + } + + bkey_copy(&s->new_stripe.key, &s->existing_stripe.key); + s->have_existing_stripe = true; + + return 0; +} + +static int __bch2_ec_stripe_head_reuse(struct btree_trans *trans, struct ec_stripe_head *h, + struct ec_stripe_new *s) { struct bch_fs *c = trans->c; - struct bch_stripe *new_v = &bkey_i_to_stripe(&h->s->new_stripe.key)->v; - struct bch_stripe *existing_v; - unsigned i; s64 idx; int ret; @@ -2024,56 +2063,19 @@ static int __bch2_ec_stripe_head_reuse(struct btree_trans *trans, struct ec_stri if (idx < 0) return -BCH_ERR_stripe_alloc_blocked; - ret = get_stripe_key_trans(trans, idx, &h->s->existing_stripe); + ret = get_stripe_key_trans(trans, idx, &s->existing_stripe); bch2_fs_fatal_err_on(ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart), c, "reading stripe key: %s", bch2_err_str(ret)); if (ret) { - bch2_stripe_close(c, h->s); + bch2_stripe_close(c, s); return ret; } - existing_v = &bkey_i_to_stripe(&h->s->existing_stripe.key)->v; - - BUG_ON(existing_v->nr_redundant != h->s->nr_parity); - h->s->nr_data = existing_v->nr_blocks - - existing_v->nr_redundant; - - ret = ec_stripe_buf_init(&h->s->existing_stripe, 0, h->blocksize); - if (ret) { - bch2_stripe_close(c, h->s); - return ret; - } - - BUG_ON(h->s->existing_stripe.size != h->blocksize); - BUG_ON(h->s->existing_stripe.size != le16_to_cpu(existing_v->sectors)); - - /* - * Free buckets we initially allocated - they might conflict with - * blocks from the stripe we're reusing: - */ - for_each_set_bit(i, h->s->blocks_gotten, new_v->nr_blocks) { - bch2_open_bucket_put(c, c->open_buckets + h->s->blocks[i]); - h->s->blocks[i] = 0; - } - memset(h->s->blocks_gotten, 0, sizeof(h->s->blocks_gotten)); - memset(h->s->blocks_allocated, 0, sizeof(h->s->blocks_allocated)); - - for (i = 0; i < existing_v->nr_blocks; i++) { - if (stripe_blockcount_get(existing_v, i)) { - __set_bit(i, h->s->blocks_gotten); - __set_bit(i, h->s->blocks_allocated); - } - - ec_block_io(c, &h->s->existing_stripe, READ, i, &h->s->iodone); - } - - bkey_copy(&h->s->new_stripe.key, &h->s->existing_stripe.key); - h->s->have_existing_stripe = true; - - return 0; + return init_new_stripe_from_existing(c, s); } -static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_stripe_head *h) +static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_stripe_head *h, + struct ec_stripe_new *s) { struct bch_fs *c = trans->c; struct btree_iter iter; @@ -2082,15 +2084,19 @@ static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_st struct bpos start_pos = bpos_max(min_pos, POS(0, c->ec_stripe_hint)); int ret; - if (!h->s->res.sectors) { - ret = bch2_disk_reservation_get(c, &h->s->res, + if (!s->res.sectors) { + ret = bch2_disk_reservation_get(c, &s->res, h->blocksize, - h->s->nr_parity, + s->nr_parity, BCH_DISK_RESERVATION_NOFAIL); if (ret) return ret; } + /* + * Allocate stripe slot + * XXX: we're going to need a bitrange btree of free stripes + */ for_each_btree_key_norestart(trans, iter, BTREE_ID_stripes, start_pos, BTREE_ITER_slots|BTREE_ITER_intent, k, ret) { if (bkey_gt(k.k->p, POS(0, U32_MAX))) { @@ -2105,7 +2111,7 @@ static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_st } if (bkey_deleted(k.k) && - bch2_try_open_stripe(c, h->s, k.k->p.offset)) + bch2_try_open_stripe(c, s, k.k->p.offset)) break; } @@ -2116,16 +2122,16 @@ static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_st ret = ec_stripe_mem_alloc(trans, &iter); if (ret) { - bch2_stripe_close(c, h->s); + bch2_stripe_close(c, s); goto err; } - h->s->new_stripe.key.k.p = iter.pos; + s->new_stripe.key.k.p = iter.pos; out: bch2_trans_iter_exit(trans, &iter); return ret; err: - bch2_disk_reservation_put(c, &h->s->res); + bch2_disk_reservation_put(c, &s->res); goto out; } @@ -2156,22 +2162,27 @@ struct ec_stripe_head *bch2_ec_stripe_head_get(struct btree_trans *trans, return h; if (!h->s) { - ret = ec_new_stripe_alloc(c, h); - if (ret) { + h->s = ec_new_stripe_alloc(c, h); + if (!h->s) { + ret = -BCH_ERR_ENOMEM_ec_new_stripe_alloc; bch_err(c, "failed to allocate new stripe"); goto err; } + + h->nr_created++; } - if (h->s->allocated) + struct ec_stripe_new *s = h->s; + + if (s->allocated) goto allocated; - if (h->s->have_existing_stripe) + if (s->have_existing_stripe) goto alloc_existing; /* First, try to allocate a full stripe: */ - ret = new_stripe_alloc_buckets(trans, h, BCH_WATERMARK_stripe, NULL) ?: - __bch2_ec_stripe_head_reserve(trans, h); + ret = new_stripe_alloc_buckets(trans, h, s, BCH_WATERMARK_stripe, NULL) ?: + __bch2_ec_stripe_head_reserve(trans, h, s); if (!ret) goto allocate_buf; if (bch2_err_matches(ret, BCH_ERR_transaction_restart) || @@ -2183,15 +2194,15 @@ struct ec_stripe_head *bch2_ec_stripe_head_get(struct btree_trans *trans, * existing stripe: */ while (1) { - ret = __bch2_ec_stripe_head_reuse(trans, h); + ret = __bch2_ec_stripe_head_reuse(trans, h, s); if (!ret) break; if (waiting || !cl || ret != -BCH_ERR_stripe_alloc_blocked) goto err; if (watermark == BCH_WATERMARK_copygc) { - ret = new_stripe_alloc_buckets(trans, h, watermark, NULL) ?: - __bch2_ec_stripe_head_reserve(trans, h); + ret = new_stripe_alloc_buckets(trans, h, s, watermark, NULL) ?: + __bch2_ec_stripe_head_reserve(trans, h, s); if (ret) goto err; goto allocate_buf; @@ -2209,19 +2220,19 @@ alloc_existing: * Retry allocating buckets, with the watermark for this * particular write: */ - ret = new_stripe_alloc_buckets(trans, h, watermark, cl); + ret = new_stripe_alloc_buckets(trans, h, s, watermark, cl); if (ret) goto err; allocate_buf: - ret = ec_stripe_buf_init(&h->s->new_stripe, 0, h->blocksize); + ret = ec_stripe_buf_init(&s->new_stripe, 0, h->blocksize); if (ret) goto err; - h->s->allocated = true; + s->allocated = true; allocated: - BUG_ON(!h->s->idx); - BUG_ON(!h->s->new_stripe.data[0]); + BUG_ON(!s->idx); + BUG_ON(!s->new_stripe.data[0]); BUG_ON(trans->restarted); return h; err: @@ -2286,7 +2297,7 @@ err: int bch2_dev_remove_stripes(struct bch_fs *c, unsigned dev_idx) { return bch2_trans_run(c, - for_each_btree_key_upto_commit(trans, iter, + for_each_btree_key_max_commit(trans, iter, BTREE_ID_alloc, POS(dev_idx, 0), POS(dev_idx, U64_MAX), BTREE_ITER_intent, k, NULL, NULL, 0, ({ @@ -2449,11 +2460,9 @@ void bch2_fs_ec_exit(struct bch_fs *c) while (1) { mutex_lock(&c->ec_stripe_head_lock); - h = list_first_entry_or_null(&c->ec_stripe_head_list, - struct ec_stripe_head, list); - if (h) - list_del(&h->list); + h = list_pop_entry(&c->ec_stripe_head_list, struct ec_stripe_head, list); mutex_unlock(&c->ec_stripe_head_lock); + if (!h) break; diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h index 43326370b410..583ca6a226da 100644 --- a/fs/bcachefs/ec.h +++ b/fs/bcachefs/ec.h @@ -6,9 +6,8 @@ #include "buckets_types.h" #include "extents_types.h" -enum bch_validate_flags; - -int bch2_stripe_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_stripe_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_stripe_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_stripe(struct btree_trans *, enum btree_id, unsigned, diff --git a/fs/bcachefs/ec_format.h b/fs/bcachefs/ec_format.h index 64ef52e00078..b9770f24f213 100644 --- a/fs/bcachefs/ec_format.h +++ b/fs/bcachefs/ec_format.h @@ -20,6 +20,23 @@ struct bch_stripe { */ __u8 disk_label; + /* + * Variable length sections: + * - Pointers + * - Checksums + * 2D array of [stripe block/device][csum block], with checksum block + * size given by csum_granularity_bits + * - Block sector counts: per-block array of u16s + * + * XXX: + * Either checksums should have come last, or we should have included a + * checksum_size field (the size in bytes of the checksum itself, not + * the blocksize the checksum covers). + * + * Currently we aren't able to access the block sector counts if the + * checksum type is unknown. + */ + struct bch_extent_ptr ptrs[]; } __packed __aligned(8); diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index 9c4fe5cdbfb7..4590cd0c7c90 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -54,7 +54,8 @@ x(ENOMEM, ENOMEM_compression_bounce_read_init) \ x(ENOMEM, ENOMEM_compression_bounce_write_init) \ x(ENOMEM, ENOMEM_compression_workspace_init) \ - x(ENOMEM, ENOMEM_decompression_workspace_init) \ + x(ENOMEM, ENOMEM_backpointer_mismatches_bitmap) \ + x(EIO, compression_workspace_not_initialized) \ x(ENOMEM, ENOMEM_bucket_gens) \ x(ENOMEM, ENOMEM_buckets_nouse) \ x(ENOMEM, ENOMEM_usage_init) \ @@ -116,6 +117,8 @@ x(ENOENT, ENOENT_dirent_doesnt_match_inode) \ x(ENOENT, ENOENT_dev_not_found) \ x(ENOENT, ENOENT_dev_idx_not_found) \ + x(ENOENT, ENOENT_inode_no_backpointer) \ + x(ENOENT, ENOENT_no_snapshot_tree_subvol) \ x(ENOTEMPTY, ENOTEMPTY_dir_not_empty) \ x(ENOTEMPTY, ENOTEMPTY_subvol_not_empty) \ x(EEXIST, EEXIST_str_hash_set) \ @@ -148,6 +151,7 @@ x(BCH_ERR_transaction_restart, transaction_restart_split_race) \ x(BCH_ERR_transaction_restart, transaction_restart_write_buffer_flush) \ x(BCH_ERR_transaction_restart, transaction_restart_nested) \ + x(BCH_ERR_transaction_restart, transaction_restart_commit) \ x(0, no_btree_node) \ x(BCH_ERR_no_btree_node, no_btree_node_relock) \ x(BCH_ERR_no_btree_node, no_btree_node_upgrade) \ @@ -164,7 +168,6 @@ x(BCH_ERR_btree_insert_fail, btree_insert_need_journal_res) \ x(BCH_ERR_btree_insert_fail, btree_insert_need_journal_reclaim) \ x(0, backpointer_to_overwritten_btree_node) \ - x(0, lock_fail_root_changed) \ x(0, journal_reclaim_would_deadlock) \ x(EINVAL, fsck) \ x(BCH_ERR_fsck, fsck_fix) \ @@ -173,7 +176,9 @@ x(BCH_ERR_fsck, fsck_errors_not_fixed) \ x(BCH_ERR_fsck, fsck_repair_unimplemented) \ x(BCH_ERR_fsck, fsck_repair_impossible) \ - x(0, restart_recovery) \ + x(EINVAL, restart_recovery) \ + x(EINVAL, not_in_recovery) \ + x(EINVAL, cannot_rewind_recovery) \ x(0, data_update_done) \ x(EINVAL, device_state_not_allowed) \ x(EINVAL, member_info_missing) \ @@ -192,7 +197,9 @@ x(EINVAL, opt_parse_error) \ x(EINVAL, remove_with_metadata_missing_unimplemented)\ x(EINVAL, remove_would_lose_data) \ - x(EINVAL, btree_iter_with_journal_not_supported) \ + x(EINVAL, no_resize_with_buckets_nouse) \ + x(EINVAL, inode_unpack_error) \ + x(EINVAL, varint_decode_error) \ x(EROFS, erofs_trans_commit) \ x(EROFS, erofs_no_writes) \ x(EROFS, erofs_journal_err) \ @@ -241,7 +248,10 @@ x(BCH_ERR_invalid_sb, invalid_sb_downgrade) \ x(BCH_ERR_invalid, invalid_bkey) \ x(BCH_ERR_operation_blocked, nocow_lock_blocked) \ + x(EIO, journal_shutdown) \ + x(EIO, journal_flush_err) \ x(EIO, btree_node_read_err) \ + x(BCH_ERR_btree_node_read_err, btree_node_read_err_cached) \ x(EIO, sb_not_downgraded) \ x(EIO, btree_node_write_all_failed) \ x(EIO, btree_node_read_error) \ @@ -257,6 +267,8 @@ x(EIO, no_device_to_read_from) \ x(EIO, missing_indirect_extent) \ x(EIO, invalidate_stripe_to_dev) \ + x(EIO, no_encryption_key) \ + x(EIO, insufficient_journal_devices) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_fixable) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_want_retry) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_must_retry) \ @@ -305,6 +317,7 @@ static inline long bch2_err_class(long err) #define BLK_STS_REMOVED ((__force blk_status_t)128) +#include const char *bch2_blk_status_to_str(blk_status_t); #endif /* _BCACHFES_ERRCODE_H */ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index b679def8fb98..038da6a61f6b 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" +#include "btree_cache.h" #include "btree_iter.h" #include "error.h" +#include "fs-common.h" #include "journal.h" #include "recovery_passes.h" #include "super.h" @@ -33,7 +35,7 @@ bool bch2_inconsistent_error(struct bch_fs *c) int bch2_topology_error(struct bch_fs *c) { set_bit(BCH_FS_topology_error, &c->flags); - if (!test_bit(BCH_FS_fsck_running, &c->flags)) { + if (!test_bit(BCH_FS_recovery_running, &c->flags)) { bch2_inconsistent_error(c); return -BCH_ERR_btree_need_topology_repair; } else { @@ -218,6 +220,30 @@ static const u8 fsck_flags_extra[] = { #undef x }; +static int do_fsck_ask_yn(struct bch_fs *c, + struct btree_trans *trans, + struct printbuf *question, + const char *action) +{ + prt_str(question, ", "); + prt_str(question, action); + + if (bch2_fs_stdio_redirect(c)) + bch2_print(c, "%s", question->buf); + else + bch2_print_string_as_lines(KERN_ERR, question->buf); + + int ask = bch2_fsck_ask_yn(c, trans); + + if (trans) { + int ret = bch2_trans_relock(trans); + if (ret) + return ret; + } + + return ask; +} + int __bch2_fsck_err(struct bch_fs *c, struct btree_trans *trans, enum bch_fsck_flags flags, @@ -226,7 +252,7 @@ int __bch2_fsck_err(struct bch_fs *c, { struct fsck_err_state *s = NULL; va_list args; - bool print = true, suppressing = false, inconsistent = false; + bool print = true, suppressing = false, inconsistent = false, exiting = false; struct printbuf buf = PRINTBUF, *out = &buf; int ret = -BCH_ERR_fsck_ignore; const char *action_orig = "fix?", *action = action_orig; @@ -256,9 +282,10 @@ int __bch2_fsck_err(struct bch_fs *c, !trans && bch2_current_has_btree_trans(c)); - if ((flags & FSCK_CAN_FIX) && - test_bit(err, c->sb.errors_silent)) - return -BCH_ERR_fsck_fix; + if (test_bit(err, c->sb.errors_silent)) + return flags & FSCK_CAN_FIX + ? -BCH_ERR_fsck_fix + : -BCH_ERR_fsck_ignore; bch2_sb_error_count(c, err); @@ -289,16 +316,14 @@ int __bch2_fsck_err(struct bch_fs *c, */ if (s->last_msg && !strcmp(buf.buf, s->last_msg)) { ret = s->ret; - mutex_unlock(&c->fsck_error_msgs_lock); - goto err; + goto err_unlock; } kfree(s->last_msg); s->last_msg = kstrdup(buf.buf, GFP_KERNEL); if (!s->last_msg) { - mutex_unlock(&c->fsck_error_msgs_lock); ret = -ENOMEM; - goto err; + goto err_unlock; } if (c->opts.ratelimit_errors && @@ -318,13 +343,19 @@ int __bch2_fsck_err(struct bch_fs *c, prt_printf(out, bch2_log_msg(c, "")); #endif - if ((flags & FSCK_CAN_FIX) && - (flags & FSCK_AUTOFIX) && + if ((flags & FSCK_AUTOFIX) && (c->opts.errors == BCH_ON_ERROR_continue || c->opts.errors == BCH_ON_ERROR_fix_safe)) { prt_str(out, ", "); - prt_actioning(out, action); - ret = -BCH_ERR_fsck_fix; + if (flags & FSCK_CAN_FIX) { + prt_actioning(out, action); + ret = -BCH_ERR_fsck_fix; + } else { + prt_str(out, ", continuing"); + ret = -BCH_ERR_fsck_ignore; + } + + goto print; } else if (!test_bit(BCH_FS_fsck_running, &c->flags)) { if (c->opts.errors != BCH_ON_ERROR_continue || !(flags & (FSCK_CAN_FIX|FSCK_CAN_IGNORE))) { @@ -348,31 +379,18 @@ int __bch2_fsck_err(struct bch_fs *c, : c->opts.fix_errors; if (fix == FSCK_FIX_ask) { - prt_str(out, ", "); - prt_str(out, action); - - if (bch2_fs_stdio_redirect(c)) - bch2_print(c, "%s", out->buf); - else - bch2_print_string_as_lines(KERN_ERR, out->buf); print = false; - int ask = bch2_fsck_ask_yn(c, trans); + ret = do_fsck_ask_yn(c, trans, out, action); + if (ret < 0) + goto err_unlock; - if (trans) { - ret = bch2_trans_relock(trans); - if (ret) { - mutex_unlock(&c->fsck_error_msgs_lock); - goto err; - } - } - - if (ask >= YN_ALLNO && s) - s->fix = ask == YN_ALLNO + if (ret >= YN_ALLNO && s) + s->fix = ret == YN_ALLNO ? FSCK_FIX_no : FSCK_FIX_yes; - ret = ask & 1 + ret = ret & 1 ? -BCH_ERR_fsck_fix : -BCH_ERR_fsck_ignore; } else if (fix == FSCK_FIX_yes || @@ -385,9 +403,7 @@ int __bch2_fsck_err(struct bch_fs *c, prt_str(out, ", not "); prt_actioning(out, action); } - } else if (flags & FSCK_NEED_FSCK) { - prt_str(out, " (run fsck to correct)"); - } else { + } else if (!(flags & FSCK_CAN_IGNORE)) { prt_str(out, " (repair unimplemented)"); } @@ -396,14 +412,13 @@ int __bch2_fsck_err(struct bch_fs *c, !(flags & FSCK_CAN_IGNORE))) ret = -BCH_ERR_fsck_errors_not_fixed; - bool exiting = - test_bit(BCH_FS_fsck_running, &c->flags) && - (ret != -BCH_ERR_fsck_fix && - ret != -BCH_ERR_fsck_ignore); - - if (exiting) + if (test_bit(BCH_FS_fsck_running, &c->flags) && + (ret != -BCH_ERR_fsck_fix && + ret != -BCH_ERR_fsck_ignore)) { + exiting = true; print = true; - + } +print: if (print) { if (bch2_fs_stdio_redirect(c)) bch2_print(c, "%s\n", out->buf); @@ -419,17 +434,24 @@ int __bch2_fsck_err(struct bch_fs *c, if (s) s->ret = ret; - mutex_unlock(&c->fsck_error_msgs_lock); - if (inconsistent) bch2_inconsistent_error(c); - if (ret == -BCH_ERR_fsck_fix) { - set_bit(BCH_FS_errors_fixed, &c->flags); - } else { - set_bit(BCH_FS_errors_not_fixed, &c->flags); - set_bit(BCH_FS_error, &c->flags); + /* + * We don't yet track whether the filesystem currently has errors, for + * log_fsck_err()s: that would require us to track for every error type + * which recovery pass corrects it, to get the fsck exit status correct: + */ + if (flags & FSCK_CAN_FIX) { + if (ret == -BCH_ERR_fsck_fix) { + set_bit(BCH_FS_errors_fixed, &c->flags); + } else { + set_bit(BCH_FS_errors_not_fixed, &c->flags); + set_bit(BCH_FS_error, &c->flags); + } } +err_unlock: + mutex_unlock(&c->fsck_error_msgs_lock); err: if (action != action_orig) kfree(action); @@ -437,28 +459,52 @@ err: return ret; } +static const char * const bch2_bkey_validate_contexts[] = { +#define x(n) #n, + BKEY_VALIDATE_CONTEXTS() +#undef x + NULL +}; + int __bch2_bkey_fsck_err(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags validate_flags, + struct bkey_validate_context from, enum bch_sb_error_id err, const char *fmt, ...) { - if (validate_flags & BCH_VALIDATE_silent) + if (from.flags & BCH_VALIDATE_silent) return -BCH_ERR_fsck_delete_bkey; unsigned fsck_flags = 0; - if (!(validate_flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit))) + if (!(from.flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit))) { + if (test_bit(err, c->sb.errors_silent)) + return -BCH_ERR_fsck_delete_bkey; + fsck_flags |= FSCK_AUTOFIX|FSCK_CAN_FIX; + } + if (!WARN_ON(err >= ARRAY_SIZE(fsck_flags_extra))) + fsck_flags |= fsck_flags_extra[err]; struct printbuf buf = PRINTBUF; - va_list args; + prt_printf(&buf, "invalid bkey in %s", + bch2_bkey_validate_contexts[from.from]); + + if (from.from == BKEY_VALIDATE_journal) + prt_printf(&buf, " journal seq=%llu offset=%u", + from.journal_seq, from.journal_offset); + + prt_str(&buf, " btree="); + bch2_btree_id_to_text(&buf, from.btree); + prt_printf(&buf, " level=%u: ", from.level); - prt_str(&buf, "invalid bkey "); bch2_bkey_val_to_text(&buf, c, k); prt_str(&buf, "\n "); + + va_list args; va_start(args, fmt); prt_vprintf(&buf, fmt, args); va_end(args); + prt_str(&buf, ": delete?"); int ret = __bch2_fsck_err(c, NULL, fsck_flags, err, "%s", buf.buf); @@ -483,3 +529,36 @@ void bch2_flush_fsck_errs(struct bch_fs *c) mutex_unlock(&c->fsck_error_msgs_lock); } + +int bch2_inum_err_msg_trans(struct btree_trans *trans, struct printbuf *out, subvol_inum inum) +{ + u32 restart_count = trans->restart_count; + int ret = 0; + + /* XXX: we don't yet attempt to print paths when we don't know the subvol */ + if (inum.subvol) + ret = lockrestart_do(trans, bch2_inum_to_path(trans, inum, out)); + if (!inum.subvol || ret) + prt_printf(out, "inum %llu:%llu", inum.subvol, inum.inum); + + return trans_was_restarted(trans, restart_count); +} + +int bch2_inum_offset_err_msg_trans(struct btree_trans *trans, struct printbuf *out, + subvol_inum inum, u64 offset) +{ + int ret = bch2_inum_err_msg_trans(trans, out, inum); + prt_printf(out, " offset %llu: ", offset); + return ret; +} + +void bch2_inum_err_msg(struct bch_fs *c, struct printbuf *out, subvol_inum inum) +{ + bch2_trans_run(c, bch2_inum_err_msg_trans(trans, out, inum)); +} + +void bch2_inum_offset_err_msg(struct bch_fs *c, struct printbuf *out, + subvol_inum inum, u64 offset) +{ + bch2_trans_run(c, bch2_inum_offset_err_msg_trans(trans, out, inum, offset)); +} diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h index 6551ada926b6..7acf2a27ca28 100644 --- a/fs/bcachefs/error.h +++ b/fs/bcachefs/error.h @@ -45,32 +45,11 @@ int bch2_topology_error(struct bch_fs *); bch2_inconsistent_error(c); \ }) -#define bch2_fs_inconsistent_on(cond, c, ...) \ +#define bch2_fs_inconsistent_on(cond, ...) \ ({ \ bool _ret = unlikely(!!(cond)); \ - \ if (_ret) \ - bch2_fs_inconsistent(c, __VA_ARGS__); \ - _ret; \ -}) - -/* - * Later we might want to mark only the particular device inconsistent, not the - * entire filesystem: - */ - -#define bch2_dev_inconsistent(ca, ...) \ -do { \ - bch_err(ca, __VA_ARGS__); \ - bch2_inconsistent_error((ca)->fs); \ -} while (0) - -#define bch2_dev_inconsistent_on(cond, ca, ...) \ -({ \ - bool _ret = unlikely(!!(cond)); \ - \ - if (_ret) \ - bch2_dev_inconsistent(ca, __VA_ARGS__); \ + bch2_fs_inconsistent(__VA_ARGS__); \ _ret; \ }) @@ -123,9 +102,9 @@ int __bch2_fsck_err(struct bch_fs *, struct btree_trans *, void bch2_flush_fsck_errs(struct bch_fs *); -#define __fsck_err(c, _flags, _err_type, ...) \ +#define fsck_err_wrap(_do) \ ({ \ - int _ret = bch2_fsck_err(c, _flags, _err_type, __VA_ARGS__); \ + int _ret = _do; \ if (_ret != -BCH_ERR_fsck_fix && \ _ret != -BCH_ERR_fsck_ignore) { \ ret = _ret; \ @@ -135,6 +114,8 @@ void bch2_flush_fsck_errs(struct bch_fs *); _ret == -BCH_ERR_fsck_fix; \ }) +#define __fsck_err(...) fsck_err_wrap(bch2_fsck_err(__VA_ARGS__)) + /* These macros return true if error should be fixed: */ /* XXX: mark in superblock that filesystem contains errors, if we ignore: */ @@ -149,12 +130,6 @@ void bch2_flush_fsck_errs(struct bch_fs *); (unlikely(cond) ? __fsck_err(c, _flags, _err_type, __VA_ARGS__) : false);\ }) -#define need_fsck_err_on(cond, c, _err_type, ...) \ - __fsck_err_on(cond, c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, _err_type, __VA_ARGS__) - -#define need_fsck_err(c, _err_type, ...) \ - __fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, _err_type, __VA_ARGS__) - #define mustfix_fsck_err(c, _err_type, ...) \ __fsck_err(c, FSCK_CAN_FIX, _err_type, __VA_ARGS__) @@ -167,11 +142,22 @@ void bch2_flush_fsck_errs(struct bch_fs *); #define fsck_err_on(cond, c, _err_type, ...) \ __fsck_err_on(cond, c, FSCK_CAN_FIX|FSCK_CAN_IGNORE, _err_type, __VA_ARGS__) +#define log_fsck_err(c, _err_type, ...) \ + __fsck_err(c, FSCK_CAN_IGNORE, _err_type, __VA_ARGS__) + +#define log_fsck_err_on(cond, ...) \ +({ \ + bool _ret = unlikely(!!(cond)); \ + if (_ret) \ + log_fsck_err(__VA_ARGS__); \ + _ret; \ +}) + enum bch_validate_flags; __printf(5, 6) int __bch2_bkey_fsck_err(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, + struct bkey_validate_context from, enum bch_sb_error_id, const char *, ...); @@ -181,7 +167,7 @@ int __bch2_bkey_fsck_err(struct bch_fs *, */ #define bkey_fsck_err(c, _err_type, _err_msg, ...) \ do { \ - int _ret = __bch2_bkey_fsck_err(c, k, flags, \ + int _ret = __bch2_bkey_fsck_err(c, k, from, \ BCH_FSCK_ERR_##_err_type, \ _err_msg, ##__VA_ARGS__); \ if (_ret != -BCH_ERR_fsck_fix && \ @@ -252,4 +238,10 @@ void bch2_io_error(struct bch_dev *, enum bch_member_error_type); _ret; \ }) +int bch2_inum_err_msg_trans(struct btree_trans *, struct printbuf *, subvol_inum); +int bch2_inum_offset_err_msg_trans(struct btree_trans *, struct printbuf *, subvol_inum, u64); + +void bch2_inum_err_msg(struct bch_fs *, struct printbuf *, subvol_inum); +void bch2_inum_offset_err_msg(struct bch_fs *, struct printbuf *, subvol_inum, u64); + #endif /* _BCACHEFS_ERROR_H */ diff --git a/fs/bcachefs/extent_update.c b/fs/bcachefs/extent_update.c index 5f4fecb358da..6aac579a692a 100644 --- a/fs/bcachefs/extent_update.c +++ b/fs/bcachefs/extent_update.c @@ -64,7 +64,7 @@ static int count_iters_for_insert(struct btree_trans *trans, break; case KEY_TYPE_reflink_p: { struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); - u64 idx = le64_to_cpu(p.v->idx); + u64 idx = REFLINK_P_IDX(p.v); unsigned sectors = bpos_min(*end, p.k->p).offset - bkey_start_offset(p.k); struct btree_iter iter; @@ -128,7 +128,7 @@ int bch2_extent_atomic_end(struct btree_trans *trans, bch2_trans_copy_iter(©, iter); - for_each_btree_key_upto_continue_norestart(copy, insert->k.p, 0, k, ret) { + for_each_btree_key_max_continue_norestart(copy, insert->k.p, 0, k, ret) { unsigned offset = 0; if (bkey_gt(bkey_start_pos(&insert->k), bkey_start_pos(k.k))) diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 37e3d69bec06..05d5f71a7ca9 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -21,6 +21,7 @@ #include "extents.h" #include "inode.h" #include "journal.h" +#include "rebalance.h" #include "replicas.h" #include "super.h" #include "super-io.h" @@ -88,6 +89,14 @@ static inline bool ptr_better(struct bch_fs *c, u64 l1 = dev_latency(c, p1.ptr.dev); u64 l2 = dev_latency(c, p2.ptr.dev); + /* + * Square the latencies, to bias more in favor of the faster + * device - we never want to stop issuing reads to the slower + * device altogether, so that we can update our latency numbers: + */ + l1 *= l1; + l2 *= l2; + /* Pick at random, biased in favor of the faster device: */ return bch2_rand_range(l1 + l2) > l1; @@ -169,7 +178,7 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k, /* KEY_TYPE_btree_ptr: */ int bch2_btree_ptr_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -177,7 +186,7 @@ int bch2_btree_ptr_validate(struct bch_fs *c, struct bkey_s_c k, c, btree_ptr_val_too_big, "value too big (%zu > %u)", bkey_val_u64s(k.k), BCH_REPLICAS_MAX); - ret = bch2_bkey_ptrs_validate(c, k, flags); + ret = bch2_bkey_ptrs_validate(c, k, from); fsck_err: return ret; } @@ -189,7 +198,7 @@ void bch2_btree_ptr_to_text(struct printbuf *out, struct bch_fs *c, } int bch2_btree_ptr_v2_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k); int ret = 0; @@ -203,12 +212,13 @@ int bch2_btree_ptr_v2_validate(struct bch_fs *c, struct bkey_s_c k, c, btree_ptr_v2_min_key_bad, "min_key > key"); - if (flags & BCH_VALIDATE_write) + if ((from.flags & BCH_VALIDATE_write) && + c->sb.version_min >= bcachefs_metadata_version_btree_ptr_sectors_written) bkey_fsck_err_on(!bp.v->sectors_written, c, btree_ptr_v2_written_0, "sectors_written == 0"); - ret = bch2_bkey_ptrs_validate(c, k, flags); + ret = bch2_bkey_ptrs_validate(c, k, from); fsck_err: return ret; } @@ -395,7 +405,7 @@ bool bch2_extent_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_c r) /* KEY_TYPE_reservation: */ int bch2_reservation_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_reservation r = bkey_s_c_to_reservation(k); int ret = 0; @@ -1120,6 +1130,57 @@ void bch2_extent_crc_unpacked_to_text(struct printbuf *out, struct bch_extent_cr bch2_prt_compression_type(out, crc->compression_type); } +static void bch2_extent_rebalance_to_text(struct printbuf *out, struct bch_fs *c, + const struct bch_extent_rebalance *r) +{ + prt_str(out, "rebalance:"); + + prt_printf(out, " replicas=%u", r->data_replicas); + if (r->data_replicas_from_inode) + prt_str(out, " (inode)"); + + prt_str(out, " checksum="); + bch2_prt_csum_opt(out, r->data_checksum); + if (r->data_checksum_from_inode) + prt_str(out, " (inode)"); + + if (r->background_compression || r->background_compression_from_inode) { + prt_str(out, " background_compression="); + bch2_compression_opt_to_text(out, r->background_compression); + + if (r->background_compression_from_inode) + prt_str(out, " (inode)"); + } + + if (r->background_target || r->background_target_from_inode) { + prt_str(out, " background_target="); + if (c) + bch2_target_to_text(out, c, r->background_target); + else + prt_printf(out, "%u", r->background_target); + + if (r->background_target_from_inode) + prt_str(out, " (inode)"); + } + + if (r->promote_target || r->promote_target_from_inode) { + prt_str(out, " promote_target="); + if (c) + bch2_target_to_text(out, c, r->promote_target); + else + prt_printf(out, "%u", r->promote_target); + + if (r->promote_target_from_inode) + prt_str(out, " (inode)"); + } + + if (r->erasure_code || r->erasure_code_from_inode) { + prt_printf(out, " ec=%u", r->erasure_code); + if (r->erasure_code_from_inode) + prt_str(out, " (inode)"); + } +} + void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { @@ -1155,18 +1216,10 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, (u64) ec->idx, ec->block); break; } - case BCH_EXTENT_ENTRY_rebalance: { - const struct bch_extent_rebalance *r = &entry->rebalance; - - prt_str(out, "rebalance: target "); - if (c) - bch2_target_to_text(out, c, r->target); - else - prt_printf(out, "%u", r->target); - prt_str(out, " compression "); - bch2_compression_opt_to_text(out, r->compression); + case BCH_EXTENT_ENTRY_rebalance: + bch2_extent_rebalance_to_text(out, c, &entry->rebalance); break; - } + default: prt_printf(out, "(invalid extent entry %.16llx)", *((u64 *) entry)); return; @@ -1178,13 +1231,19 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, static int extent_ptr_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, + struct bkey_validate_context from, const struct bch_extent_ptr *ptr, unsigned size_ondisk, bool metadata) { int ret = 0; + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + bkey_for_each_ptr(ptrs, ptr2) + bkey_fsck_err_on(ptr != ptr2 && ptr->dev == ptr2->dev, + c, ptr_to_duplicate_device, + "multiple pointers to same device (%u)", ptr->dev); + /* bad pointers are repaired by check_fix_ptrs(): */ rcu_read_lock(); struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev); @@ -1199,13 +1258,6 @@ static int extent_ptr_validate(struct bch_fs *c, unsigned bucket_size = ca->mi.bucket_size; rcu_read_unlock(); - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - bkey_for_each_ptr(ptrs, ptr2) - bkey_fsck_err_on(ptr != ptr2 && ptr->dev == ptr2->dev, - c, ptr_to_duplicate_device, - "multiple pointers to same device (%u)", ptr->dev); - - bkey_fsck_err_on(bucket >= nbuckets, c, ptr_after_last_bucket, "pointer past last bucket (%llu > %llu)", bucket, nbuckets); @@ -1221,7 +1273,7 @@ fsck_err: } int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; @@ -1248,7 +1300,7 @@ int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, switch (extent_entry_type(entry)) { case BCH_EXTENT_ENTRY_ptr: - ret = extent_ptr_validate(c, k, flags, &entry->ptr, size_ondisk, false); + ret = extent_ptr_validate(c, k, from, &entry->ptr, size_ondisk, false); if (ret) return ret; @@ -1270,9 +1322,6 @@ int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, case BCH_EXTENT_ENTRY_crc128: crc = bch2_extent_crc_unpack(k.k, entry_to_crc(entry)); - bkey_fsck_err_on(crc.offset + crc.live_size > crc.uncompressed_size, - c, ptr_crc_uncompressed_size_too_small, - "checksum offset + key size > uncompressed size"); bkey_fsck_err_on(!bch2_checksum_type_valid(c, crc.csum_type), c, ptr_crc_csum_type_unknown, "invalid checksum type"); @@ -1280,6 +1329,19 @@ int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, c, ptr_crc_compression_type_unknown, "invalid compression type"); + bkey_fsck_err_on(crc.offset + crc.live_size > crc.uncompressed_size, + c, ptr_crc_uncompressed_size_too_small, + "checksum offset + key size > uncompressed size"); + bkey_fsck_err_on(crc_is_encoded(crc) && + (crc.uncompressed_size > c->opts.encoded_extent_max >> 9) && + (from.flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit)), + c, ptr_crc_uncompressed_size_too_big, + "too large encoded extent"); + bkey_fsck_err_on(!crc_is_compressed(crc) && + crc.compressed_size != crc.uncompressed_size, + c, ptr_crc_uncompressed_size_mismatch, + "not compressed but compressed != uncompressed size"); + if (bch2_csum_type_is_encryption(crc.csum_type)) { if (nonce == UINT_MAX) nonce = crc.offset + crc.nonce; @@ -1293,12 +1355,6 @@ int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, "redundant crc entry"); crc_since_last_ptr = true; - bkey_fsck_err_on(crc_is_encoded(crc) && - (crc.uncompressed_size > c->opts.encoded_extent_max >> 9) && - (flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit)), - c, ptr_crc_uncompressed_size_too_big, - "too large encoded extent"); - size_ondisk = crc.compressed_size; break; case BCH_EXTENT_ENTRY_stripe_ptr: @@ -1391,166 +1447,6 @@ void bch2_ptr_swab(struct bkey_s k) } } -const struct bch_extent_rebalance *bch2_bkey_rebalance_opts(struct bkey_s_c k) -{ - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - const union bch_extent_entry *entry; - - bkey_extent_entry_for_each(ptrs, entry) - if (__extent_entry_type(entry) == BCH_EXTENT_ENTRY_rebalance) - return &entry->rebalance; - - return NULL; -} - -unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *c, struct bkey_s_c k, - unsigned target, unsigned compression) -{ - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - unsigned rewrite_ptrs = 0; - - if (compression) { - unsigned compression_type = bch2_compression_opt_to_type(compression); - const union bch_extent_entry *entry; - struct extent_ptr_decoded p; - unsigned i = 0; - - bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || - p.ptr.unwritten) { - rewrite_ptrs = 0; - goto incompressible; - } - - if (!p.ptr.cached && p.crc.compression_type != compression_type) - rewrite_ptrs |= 1U << i; - i++; - } - } -incompressible: - if (target && bch2_target_accepts_data(c, BCH_DATA_user, target)) { - unsigned i = 0; - - bkey_for_each_ptr(ptrs, ptr) { - if (!ptr->cached && !bch2_dev_in_target(c, ptr->dev, target)) - rewrite_ptrs |= 1U << i; - i++; - } - } - - return rewrite_ptrs; -} - -bool bch2_bkey_needs_rebalance(struct bch_fs *c, struct bkey_s_c k) -{ - const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k); - - /* - * If it's an indirect extent, we don't delete the rebalance entry when - * done so that we know what options were applied - check if it still - * needs work done: - */ - if (r && - k.k->type == KEY_TYPE_reflink_v && - !bch2_bkey_ptrs_need_rebalance(c, k, r->target, r->compression)) - r = NULL; - - return r != NULL; -} - -static u64 __bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k, - unsigned target, unsigned compression) -{ - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - const union bch_extent_entry *entry; - struct extent_ptr_decoded p; - u64 sectors = 0; - - if (compression) { - unsigned compression_type = bch2_compression_opt_to_type(compression); - - bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || - p.ptr.unwritten) { - sectors = 0; - goto incompressible; - } - - if (!p.ptr.cached && p.crc.compression_type != compression_type) - sectors += p.crc.compressed_size; - } - } -incompressible: - if (target && bch2_target_accepts_data(c, BCH_DATA_user, target)) { - bkey_for_each_ptr_decode(k.k, ptrs, p, entry) - if (!p.ptr.cached && !bch2_dev_in_target(c, p.ptr.dev, target)) - sectors += p.crc.compressed_size; - } - - return sectors; -} - -u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k) -{ - const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k); - - return r ? __bch2_bkey_sectors_need_rebalance(c, k, r->target, r->compression) : 0; -} - -int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bkey_i *_k, - struct bch_io_opts *opts) -{ - struct bkey_s k = bkey_i_to_s(_k); - struct bch_extent_rebalance *r; - unsigned target = opts->background_target; - unsigned compression = background_compression(*opts); - bool needs_rebalance; - - if (!bkey_extent_is_direct_data(k.k)) - return 0; - - /* get existing rebalance entry: */ - r = (struct bch_extent_rebalance *) bch2_bkey_rebalance_opts(k.s_c); - if (r) { - if (k.k->type == KEY_TYPE_reflink_v) { - /* - * indirect extents: existing options take precedence, - * so that we don't move extents back and forth if - * they're referenced by different inodes with different - * options: - */ - if (r->target) - target = r->target; - if (r->compression) - compression = r->compression; - } - - r->target = target; - r->compression = compression; - } - - needs_rebalance = bch2_bkey_ptrs_need_rebalance(c, k.s_c, target, compression); - - if (needs_rebalance && !r) { - union bch_extent_entry *new = bkey_val_end(k); - - new->rebalance.type = 1U << BCH_EXTENT_ENTRY_rebalance; - new->rebalance.compression = compression; - new->rebalance.target = target; - new->rebalance.unused = 0; - k.k->u64s += extent_entry_u64s(new); - } else if (!needs_rebalance && r && k.k->type != KEY_TYPE_reflink_v) { - /* - * For indirect extents, don't delete the rebalance entry when - * we're finished so that we know we specifically moved it or - * compressed it to its current location/compression type - */ - extent_entry_drop(k, (union bch_extent_entry *) r); - } - - return 0; -} - /* Generic extent code: */ int bch2_cut_front_s(struct bpos where, struct bkey_s k) @@ -1610,7 +1506,7 @@ int bch2_cut_front_s(struct bpos where, struct bkey_s k) case KEY_TYPE_reflink_p: { struct bkey_s_reflink_p p = bkey_s_to_reflink_p(k); - le64_add_cpu(&p.v->idx, sub); + SET_REFLINK_P_IDX(p.v, REFLINK_P_IDX(p.v) + sub); break; } case KEY_TYPE_inline_data: diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h index bcffcf60aaaf..620b284aa34f 100644 --- a/fs/bcachefs/extents.h +++ b/fs/bcachefs/extents.h @@ -8,7 +8,6 @@ struct bch_fs; struct btree_trans; -enum bch_validate_flags; /* extent entries: */ @@ -410,12 +409,12 @@ int bch2_bkey_pick_read_device(struct bch_fs *, struct bkey_s_c, /* KEY_TYPE_btree_ptr: */ int bch2_btree_ptr_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_btree_ptr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_btree_ptr_v2_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_btree_ptr_v2_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned, int, struct bkey_s); @@ -452,7 +451,7 @@ bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); /* KEY_TYPE_reservation: */ int bch2_reservation_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_reservation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); bool bch2_reservation_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); @@ -696,7 +695,7 @@ void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_bkey_ptrs_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); static inline bool bch2_extent_ptr_eq(struct bch_extent_ptr ptr1, struct bch_extent_ptr ptr2) @@ -710,15 +709,6 @@ static inline bool bch2_extent_ptr_eq(struct bch_extent_ptr ptr1, void bch2_ptr_swab(struct bkey_s); -const struct bch_extent_rebalance *bch2_bkey_rebalance_opts(struct bkey_s_c); -unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *, struct bkey_s_c, - unsigned, unsigned); -bool bch2_bkey_needs_rebalance(struct bch_fs *, struct bkey_s_c); -u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *, struct bkey_s_c); - -int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bkey_i *, - struct bch_io_opts *); - /* Generic extent code: */ enum bch_extent_overlap { diff --git a/fs/bcachefs/extents_format.h b/fs/bcachefs/extents_format.h index 3bd2fdbb0817..c198dfc376d6 100644 --- a/fs/bcachefs/extents_format.h +++ b/fs/bcachefs/extents_format.h @@ -201,19 +201,8 @@ struct bch_extent_stripe_ptr { #endif }; -struct bch_extent_rebalance { -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u64 type:6, - unused:34, - compression:8, /* enum bch_compression_opt */ - target:16; -#elif defined (__BIG_ENDIAN_BITFIELD) - __u64 target:16, - compression:8, - unused:34, - type:6; -#endif -}; +/* bch_extent_rebalance: */ +#include "rebalance_format.h" union bch_extent_entry { #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ || __BITS_PER_LONG == 64 diff --git a/fs/bcachefs/fs-common.c b/fs/bcachefs/fs-common.c index 7e10a9ddcfd9..d70d9f634cea 100644 --- a/fs/bcachefs/fs-common.c +++ b/fs/bcachefs/fs-common.c @@ -69,9 +69,7 @@ int bch2_create_trans(struct btree_trans *trans, if (!snapshot_src.inum) { /* Inode wasn't specified, just snapshot: */ struct bch_subvolume s; - - ret = bch2_subvolume_get(trans, snapshot_src.subvol, true, - BTREE_ITER_cached, &s); + ret = bch2_subvolume_get(trans, snapshot_src.subvol, true, &s); if (ret) goto err; @@ -154,6 +152,7 @@ int bch2_create_trans(struct btree_trans *trans, if (is_subdir_for_nlink(new_inode)) dir_u->bi_nlink++; dir_u->bi_mtime = dir_u->bi_ctime = now; + dir_u->bi_size += dirent_occupied_size(name); ret = bch2_inode_write(trans, &dir_iter, dir_u); if (ret) @@ -172,6 +171,10 @@ int bch2_create_trans(struct btree_trans *trans, new_inode->bi_dir_offset = dir_offset; } + if (S_ISDIR(mode) && + !new_inode->bi_subvol) + new_inode->bi_depth = dir_u->bi_depth + 1; + inode_iter.flags &= ~BTREE_ITER_all_snapshots; bch2_btree_iter_set_snapshot(&inode_iter, snapshot); @@ -218,6 +221,7 @@ int bch2_link_trans(struct btree_trans *trans, } dir_u->bi_mtime = dir_u->bi_ctime = now; + dir_u->bi_size += dirent_occupied_size(name); dir_hash = bch2_hash_info_init(c, dir_u); @@ -320,6 +324,7 @@ int bch2_unlink_trans(struct btree_trans *trans, dir_u->bi_mtime = dir_u->bi_ctime = inode_u->bi_ctime = now; dir_u->bi_nlink -= is_subdir_for_nlink(inode_u); + dir_u->bi_size -= dirent_occupied_size(name); ret = bch2_hash_delete_at(trans, bch2_dirent_hash_desc, &dir_hash, &dirent_iter, @@ -458,6 +463,14 @@ int bch2_rename_trans(struct btree_trans *trans, goto err; } + if (mode == BCH_RENAME) { + src_dir_u->bi_size -= dirent_occupied_size(src_name); + dst_dir_u->bi_size += dirent_occupied_size(dst_name); + } + + if (mode == BCH_RENAME_OVERWRITE) + src_dir_u->bi_size -= dirent_occupied_size(src_name); + if (src_inode_u->bi_parent_subvol) src_inode_u->bi_parent_subvol = dst_dir.subvol; @@ -512,6 +525,15 @@ int bch2_rename_trans(struct btree_trans *trans, dst_dir_u->bi_nlink++; } + if (S_ISDIR(src_inode_u->bi_mode) && + !src_inode_u->bi_subvol) + src_inode_u->bi_depth = dst_dir_u->bi_depth + 1; + + if (mode == BCH_RENAME_EXCHANGE && + S_ISDIR(dst_inode_u->bi_mode) && + !dst_inode_u->bi_subvol) + dst_inode_u->bi_depth = src_dir_u->bi_depth + 1; + if (dst_inum.inum && is_subdir_for_nlink(dst_inode_u)) { dst_dir_u->bi_nlink--; src_dir_u->bi_nlink += mode == BCH_RENAME_EXCHANGE; @@ -548,3 +570,94 @@ err: bch2_trans_iter_exit(trans, &src_dir_iter); return ret; } + +static inline void prt_bytes_reversed(struct printbuf *out, const void *b, unsigned n) +{ + bch2_printbuf_make_room(out, n); + + unsigned can_print = min(n, printbuf_remaining(out)); + + b += n; + + for (unsigned i = 0; i < can_print; i++) + out->buf[out->pos++] = *((char *) --b); + + printbuf_nul_terminate(out); +} + +static inline void prt_str_reversed(struct printbuf *out, const char *s) +{ + prt_bytes_reversed(out, s, strlen(s)); +} + +static inline void reverse_bytes(void *b, size_t n) +{ + char *e = b + n, *s = b; + + while (s < e) { + --e; + swap(*s, *e); + s++; + } +} + +/* XXX: we don't yet attempt to print paths when we don't know the subvol */ +int bch2_inum_to_path(struct btree_trans *trans, subvol_inum inum, struct printbuf *path) +{ + unsigned orig_pos = path->pos; + int ret = 0; + + while (!(inum.subvol == BCACHEFS_ROOT_SUBVOL && + inum.inum == BCACHEFS_ROOT_INO)) { + struct bch_inode_unpacked inode; + ret = bch2_inode_find_by_inum_trans(trans, inum, &inode); + if (ret) + goto disconnected; + + if (!inode.bi_dir && !inode.bi_dir_offset) { + ret = -BCH_ERR_ENOENT_inode_no_backpointer; + goto disconnected; + } + + inum.subvol = inode.bi_parent_subvol ?: inum.subvol; + inum.inum = inode.bi_dir; + + u32 snapshot; + ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot); + if (ret) + goto disconnected; + + struct btree_iter d_iter; + struct bkey_s_c_dirent d = bch2_bkey_get_iter_typed(trans, &d_iter, + BTREE_ID_dirents, SPOS(inode.bi_dir, inode.bi_dir_offset, snapshot), + 0, dirent); + ret = bkey_err(d.s_c); + if (ret) + goto disconnected; + + struct qstr dirent_name = bch2_dirent_get_name(d); + prt_bytes_reversed(path, dirent_name.name, dirent_name.len); + + prt_char(path, '/'); + + bch2_trans_iter_exit(trans, &d_iter); + } + + if (orig_pos == path->pos) + prt_char(path, '/'); +out: + ret = path->allocation_failure ? -ENOMEM : 0; + if (ret) + goto err; + + reverse_bytes(path->buf + orig_pos, path->pos - orig_pos); + return 0; +err: + return ret; +disconnected: + if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) + goto err; + + prt_str_reversed(path, "(disconnected)"); + goto out; +} diff --git a/fs/bcachefs/fs-common.h b/fs/bcachefs/fs-common.h index c934e807b380..2b59210bb5e8 100644 --- a/fs/bcachefs/fs-common.h +++ b/fs/bcachefs/fs-common.h @@ -42,4 +42,6 @@ int bch2_rename_trans(struct btree_trans *, bool bch2_reinherit_attrs(struct bch_inode_unpacked *, struct bch_inode_unpacked *); +int bch2_inum_to_path(struct btree_trans *, subvol_inum, struct printbuf *); + #endif /* _BCACHEFS_FS_COMMON_H */ diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c index 95972809e76d..ab1d5db2fa56 100644 --- a/fs/bcachefs/fs-io-buffered.c +++ b/fs/bcachefs/fs-io-buffered.c @@ -164,7 +164,8 @@ static void bchfs_read(struct btree_trans *trans, BTREE_ITER_slots); while (1) { struct bkey_s_c k; - unsigned bytes, sectors, offset_into_extent; + unsigned bytes, sectors; + s64 offset_into_extent; enum btree_id data_btree = BTREE_ID_extents; bch2_trans_begin(trans); @@ -197,7 +198,7 @@ static void bchfs_read(struct btree_trans *trans, k = bkey_i_to_s_c(sk.k); - sectors = min(sectors, k.k->size - offset_into_extent); + sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent); if (readpages_iter) { ret = readpage_bio_extend(trans, readpages_iter, &rbio->bio, sectors, @@ -230,10 +231,12 @@ err: bch2_trans_iter_exit(trans, &iter); if (ret) { - bch_err_inum_offset_ratelimited(c, - iter.pos.inode, - iter.pos.offset << 9, - "read error %i from btree lookup", ret); + struct printbuf buf = PRINTBUF; + bch2_inum_offset_err_msg_trans(trans, &buf, inum, iter.pos.offset << 9); + prt_printf(&buf, "read error %i from btree lookup", ret); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + rbio->bio.bi_status = BLK_STS_IOERR; bio_endio(&rbio->bio); } @@ -248,6 +251,7 @@ void bch2_readahead(struct readahead_control *ractl) struct bch_io_opts opts; struct folio *folio; struct readpages_iter readpages_iter; + struct blk_plug plug; bch2_inode_opts_get(&opts, c, &inode->ei_inode); @@ -255,6 +259,16 @@ void bch2_readahead(struct readahead_control *ractl) if (ret) return; + /* + * Besides being a general performance optimization, plugging helps with + * avoiding btree transaction srcu warnings - submitting a bio can + * block, and we don't want todo that with the transaction locked. + * + * However, plugged bios are submitted when we schedule; we ideally + * would have our own scheduler hook to call unlock_long() before + * scheduling. + */ + blk_start_plug(&plug); bch2_pagecache_add_get(inode); struct btree_trans *trans = bch2_trans_get(c); @@ -281,7 +295,7 @@ void bch2_readahead(struct readahead_control *ractl) bch2_trans_put(trans); bch2_pagecache_add_put(inode); - + blk_finish_plug(&plug); darray_exit(&readpages_iter.folios); } @@ -296,9 +310,13 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping) struct bch_fs *c = inode->v.i_sb->s_fs_info; struct bch_read_bio *rbio; struct bch_io_opts opts; + struct blk_plug plug; int ret; DECLARE_COMPLETION_ONSTACK(done); + BUG_ON(folio_test_uptodate(folio)); + BUG_ON(folio_test_dirty(folio)); + if (!bch2_folio_create(folio, GFP_KERNEL)) return -ENOMEM; @@ -313,7 +331,9 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping) rbio->bio.bi_iter.bi_sector = folio_sector(folio); BUG_ON(!bio_add_folio(&rbio->bio, folio, folio_size(folio), 0)); + blk_start_plug(&plug); bch2_trans_run(c, (bchfs_read(trans, rbio, inode_inum(inode), NULL), 0)); + blk_finish_plug(&plug); wait_for_completion(&done); ret = blk_status_to_errno(rbio->bio.bi_status); @@ -605,15 +625,6 @@ do_io: BUG_ON(!bio_add_folio(&w->io->op.wbio.bio, folio, sectors << 9, offset << 9)); - /* Check for writing past i_size: */ - WARN_ONCE((bio_end_sector(&w->io->op.wbio.bio) << 9) > - round_up(i_size, block_bytes(c)) && - !test_bit(BCH_FS_emergency_ro, &c->flags), - "writing past i_size: %llu > %llu (unrounded %llu)\n", - bio_end_sector(&w->io->op.wbio.bio) << 9, - round_up(i_size, block_bytes(c)), - i_size); - w->io->op.res.sectors += reserved_sectors; w->io->op.i_sectors_delta -= dirty_sectors; w->io->op.new_i_size = i_size; @@ -669,7 +680,7 @@ int bch2_write_begin(struct file *file, struct address_space *mapping, folio = __filemap_get_folio(mapping, pos >> PAGE_SHIFT, FGP_WRITEBEGIN | fgf_set_order(len), mapping_gfp_mask(mapping)); - if (IS_ERR_OR_NULL(folio)) + if (IS_ERR(folio)) goto err_unlock; offset = pos - folio_pos(folio); diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c index 6d3a05ae5da8..2089c36b5866 100644 --- a/fs/bcachefs/fs-io-direct.c +++ b/fs/bcachefs/fs-io-direct.c @@ -70,6 +70,7 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter) struct bch_io_opts opts; struct dio_read *dio; struct bio *bio; + struct blk_plug plug; loff_t offset = req->ki_pos; bool sync = is_sync_kiocb(req); size_t shorten; @@ -128,6 +129,8 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter) */ dio->should_dirty = iter_is_iovec(iter); + blk_start_plug(&plug); + goto start; while (iter->count) { bio = bio_alloc_bioset(NULL, @@ -160,6 +163,8 @@ start: bch2_read(c, rbio_init(bio, opts), inode_inum(inode)); } + blk_finish_plug(&plug); + iter->count += shorten; if (sync) { diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c index 1d4910ea0f1d..e072900e6a5b 100644 --- a/fs/bcachefs/fs-io-pagecache.c +++ b/fs/bcachefs/fs-io-pagecache.c @@ -29,7 +29,7 @@ int bch2_filemap_get_contig_folios_d(struct address_space *mapping, break; f = __filemap_get_folio(mapping, pos >> PAGE_SHIFT, fgp_flags, gfp); - if (IS_ERR_OR_NULL(f)) + if (IS_ERR(f)) break; BUG_ON(fs->nr && folio_pos(f) != pos); @@ -199,7 +199,7 @@ int bch2_folio_set(struct bch_fs *c, subvol_inum inum, unsigned folio_idx = 0; return bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, POS(inum.inum, offset), POS(inum.inum, U64_MAX), inum.subvol, BTREE_ITER_slots, k, ({ diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c index 2456c41b215e..94bf34b9b65f 100644 --- a/fs/bcachefs/fs-io.c +++ b/fs/bcachefs/fs-io.c @@ -167,6 +167,34 @@ void __bch2_i_sectors_acct(struct bch_fs *c, struct bch_inode_info *inode, /* fsync: */ +static int bch2_get_inode_journal_seq_trans(struct btree_trans *trans, subvol_inum inum, + u64 *seq) +{ + struct printbuf buf = PRINTBUF; + struct bch_inode_unpacked u; + struct btree_iter iter; + int ret = bch2_inode_peek(trans, &iter, &u, inum, 0); + if (ret) + return ret; + + u64 cur_seq = journal_cur_seq(&trans->c->journal); + *seq = min(cur_seq, u.bi_journal_seq); + + if (fsck_err_on(u.bi_journal_seq > cur_seq, + trans, inode_journal_seq_in_future, + "inode journal seq in future (currently at %llu)\n%s", + cur_seq, + (bch2_inode_unpacked_to_text(&buf, &u), + buf.buf))) { + u.bi_journal_seq = cur_seq; + ret = bch2_inode_write(trans, &iter, &u); + } +fsck_err: + bch2_trans_iter_exit(trans, &iter); + printbuf_exit(&buf); + return ret; +} + /* * inode->ei_inode.bi_journal_seq won't be up to date since it's set in an * insert trigger: look up the btree inode instead @@ -180,9 +208,10 @@ static int bch2_flush_inode(struct bch_fs *c, if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync)) return -EROFS; - struct bch_inode_unpacked u; - int ret = bch2_inode_find_by_inum(c, inode_inum(inode), &u) ?: - bch2_journal_flush_seq(&c->journal, u.bi_journal_seq, TASK_INTERRUPTIBLE) ?: + u64 seq; + int ret = bch2_trans_commit_do(c, NULL, NULL, 0, + bch2_get_inode_journal_seq_trans(trans, inode_inum(inode), &seq)) ?: + bch2_journal_flush_seq(&c->journal, seq, TASK_INTERRUPTIBLE) ?: bch2_inode_flush_nocow_writes(c, inode); bch2_write_ref_put(c, BCH_WRITE_REF_fsync); return ret; @@ -222,7 +251,7 @@ static inline int range_has_data(struct bch_fs *c, u32 subvol, struct bpos end) { return bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_extents, start, end, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, start, end, subvol, 0, k, ({ bkey_extent_is_data(k.k) && !bkey_extent_is_unwritten(k); }))); @@ -256,7 +285,7 @@ static int __bch2_truncate_folio(struct bch_inode_info *inode, folio = __filemap_get_folio(mapping, index, FGP_LOCK|FGP_CREAT, GFP_KERNEL); - if (IS_ERR_OR_NULL(folio)) { + if (IS_ERR(folio)) { ret = -ENOMEM; goto out; } @@ -806,7 +835,7 @@ static int quota_reserve_range(struct bch_inode_info *inode, u64 sectors = end - start; int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, POS(inode->v.i_ino, start), POS(inode->v.i_ino, end - 1), @@ -877,11 +906,18 @@ loff_t bch2_remap_file_range(struct file *file_src, loff_t pos_src, bch2_mark_pagecache_unallocated(src, pos_src >> 9, (pos_src + aligned_len) >> 9); + /* + * XXX: we'd like to be telling bch2_remap_range() if we have + * permission to write to the source file, and thus if io path option + * changes should be propagated through the copy, but we need mnt_idmap + * from the pathwalk, awkward + */ ret = bch2_remap_range(c, inode_inum(dst), pos_dst >> 9, inode_inum(src), pos_src >> 9, aligned_len >> 9, - pos_dst + len, &i_sectors_delta); + pos_dst + len, &i_sectors_delta, + false); if (ret < 0) goto err; @@ -922,7 +958,7 @@ static loff_t bch2_seek_data(struct file *file, u64 offset) return -ENXIO; int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, POS(inode->v.i_ino, offset >> 9), POS(inode->v.i_ino, U64_MAX), inum.subvol, 0, k, ({ @@ -958,7 +994,7 @@ static loff_t bch2_seek_hole(struct file *file, u64 offset) return -ENXIO; int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, POS(inode->v.i_ino, offset >> 9), POS(inode->v.i_ino, U64_MAX), inum.subvol, BTREE_ITER_slots, k, ({ diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c index 405cf08bda34..15725b4ce393 100644 --- a/fs/bcachefs/fs-ioctl.c +++ b/fs/bcachefs/fs-ioctl.c @@ -406,7 +406,7 @@ static long bch2_ioctl_subvolume_create(struct bch_fs *c, struct file *filp, sync_inodes_sb(c->vfs_sb); up_read(&c->vfs_sb->s_umount); } -retry: + if (arg.src_ptr) { error = user_path_at(arg.dirfd, (const char __user *)(unsigned long)arg.src_ptr, @@ -486,11 +486,6 @@ err3: err2: if (arg.src_ptr) path_put(&src_path); - - if (retry_estale(error, lookup_flags)) { - lookup_flags |= LOOKUP_REVAL; - goto retry; - } err1: return error; } diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index a41d0d8a2f7b..90ade8f648d9 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -23,6 +23,7 @@ #include "journal.h" #include "keylist.h" #include "quota.h" +#include "rebalance.h" #include "snapshot.h" #include "super.h" #include "xattr.h" @@ -38,6 +39,7 @@ #include #include #include +#include #include #include #include @@ -65,6 +67,9 @@ void bch2_inode_update_after_write(struct btree_trans *trans, i_gid_write(&inode->v, bi->bi_gid); inode->v.i_mode = bi->bi_mode; + if (fields & ATTR_SIZE) + i_size_write(&inode->v, bi->bi_size); + if (fields & ATTR_ATIME) inode_set_atime_to_ts(&inode->v, bch2_time_to_timespec(c, bi->bi_atime)); if (fields & ATTR_MTIME) @@ -89,10 +94,25 @@ int __must_check bch2_write_inode(struct bch_fs *c, retry: bch2_trans_begin(trans); - ret = bch2_inode_peek(trans, &iter, &inode_u, inode_inum(inode), - BTREE_ITER_intent) ?: - (set ? set(trans, inode, &inode_u, p) : 0) ?: - bch2_inode_write(trans, &iter, &inode_u) ?: + ret = bch2_inode_peek(trans, &iter, &inode_u, inode_inum(inode), BTREE_ITER_intent); + if (ret) + goto err; + + struct bch_extent_rebalance old_r = bch2_inode_rebalance_opts_get(c, &inode_u); + + ret = (set ? set(trans, inode, &inode_u, p) : 0); + if (ret) + goto err; + + struct bch_extent_rebalance new_r = bch2_inode_rebalance_opts_get(c, &inode_u); + + if (memcmp(&old_r, &new_r, sizeof(new_r))) { + ret = bch2_set_rebalance_needs_scan_trans(trans, inode_u.bi_inum); + if (ret) + goto err; + } + + ret = bch2_inode_write(trans, &iter, &inode_u) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); /* @@ -101,7 +121,7 @@ retry: */ if (!ret) bch2_inode_update_after_write(trans, inode, &inode_u, fields); - +err: bch2_trans_iter_exit(trans, &iter); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) @@ -160,8 +180,9 @@ static bool subvol_inum_eq(subvol_inum a, subvol_inum b) static u32 bch2_vfs_inode_hash_fn(const void *data, u32 len, u32 seed) { const subvol_inum *inum = data; + siphash_key_t k = { .key[0] = seed }; - return jhash(&inum->inum, sizeof(inum->inum), seed); + return siphash_2u64(inum->subvol, inum->inum, &k); } static u32 bch2_vfs_inode_obj_hash_fn(const void *data, u32 len, u32 seed) @@ -190,11 +211,18 @@ static const struct rhashtable_params bch2_vfs_inodes_params = { .automatic_shrinking = true, }; +static const struct rhashtable_params bch2_vfs_inodes_by_inum_params = { + .head_offset = offsetof(struct bch_inode_info, by_inum_hash), + .key_offset = offsetof(struct bch_inode_info, ei_inum.inum), + .key_len = sizeof(u64), + .automatic_shrinking = true, +}; + int bch2_inode_or_descendents_is_open(struct btree_trans *trans, struct bpos p) { struct bch_fs *c = trans->c; - struct rhashtable *ht = &c->vfs_inodes_table; - subvol_inum inum = (subvol_inum) { .inum = p.offset }; + struct rhltable *ht = &c->vfs_inodes_by_inum_table; + u64 inum = p.offset; DARRAY(u32) subvols; int ret = 0; @@ -219,15 +247,15 @@ restart_from_top: struct rhash_lock_head __rcu *const *bkt; struct rhash_head *he; unsigned int hash; - struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); + struct bucket_table *tbl = rht_dereference_rcu(ht->ht.tbl, &ht->ht); restart: - hash = rht_key_hashfn(ht, tbl, &inum, bch2_vfs_inodes_params); + hash = rht_key_hashfn(&ht->ht, tbl, &inum, bch2_vfs_inodes_by_inum_params); bkt = rht_bucket(tbl, hash); do { struct bch_inode_info *inode; rht_for_each_entry_rcu_from(inode, he, rht_ptr_rcu(bkt), tbl, hash, hash) { - if (inode->ei_inum.inum == inum.inum) { + if (inode->ei_inum.inum == inum) { ret = darray_push_gfp(&subvols, inode->ei_inum.subvol, GFP_NOWAIT|__GFP_NOWARN); if (ret) { @@ -248,7 +276,7 @@ restart: /* Ensure we see any new tables. */ smp_rmb(); - tbl = rht_dereference_rcu(tbl->future_tbl, ht); + tbl = rht_dereference_rcu(tbl->future_tbl, &ht->ht); if (unlikely(tbl)) goto restart; rcu_read_unlock(); @@ -327,7 +355,11 @@ static void bch2_inode_hash_remove(struct bch_fs *c, struct bch_inode_info *inod spin_unlock(&inode->v.i_lock); if (remove) { - int ret = rhashtable_remove_fast(&c->vfs_inodes_table, + int ret = rhltable_remove(&c->vfs_inodes_by_inum_table, + &inode->by_inum_hash, bch2_vfs_inodes_by_inum_params); + BUG_ON(ret); + + ret = rhashtable_remove_fast(&c->vfs_inodes_table, &inode->hash, bch2_vfs_inodes_params); BUG_ON(ret); inode->v.i_hash.pprev = NULL; @@ -372,6 +404,11 @@ retry: discard_new_inode(&inode->v); return old; } else { + int ret = rhltable_insert(&c->vfs_inodes_by_inum_table, + &inode->by_inum_hash, + bch2_vfs_inodes_by_inum_params); + BUG_ON(ret); + inode_fake_hash(&inode->v); inode_sb_list_add(&inode->v); @@ -465,7 +502,7 @@ struct inode *bch2_vfs_inode_get(struct bch_fs *c, subvol_inum inum) struct bch_inode_unpacked inode_u; struct bch_subvolume subvol; int ret = lockrestart_do(trans, - bch2_subvolume_get(trans, inum.subvol, true, 0, &subvol) ?: + bch2_subvolume_get(trans, inum.subvol, true, &subvol) ?: bch2_inode_find_by_inum_trans(trans, inum, &inode_u)) ?: PTR_ERR_OR_ZERO(inode = bch2_inode_hash_init_insert(trans, inum, &inode_u, &subvol)); bch2_trans_put(trans); @@ -535,8 +572,7 @@ retry: inum.subvol = inode_u.bi_subvol ?: dir->ei_inum.subvol; inum.inum = inode_u.bi_inum; - ret = bch2_subvolume_get(trans, inum.subvol, true, - BTREE_ITER_with_updates, &subvol) ?: + ret = bch2_subvolume_get(trans, inum.subvol, true, &subvol) ?: bch2_trans_commit(trans, NULL, &journal_seq, 0); if (unlikely(ret)) { bch2_quota_acct(c, bch_qid(&inode_u), Q_INO, -1, @@ -549,7 +585,7 @@ err_before_quota: if (!(flags & BCH_CREATE_TMPFILE)) { bch2_inode_update_after_write(trans, dir, &dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); mutex_unlock(&dir->ei_update_lock); } @@ -617,7 +653,7 @@ static struct bch_inode_info *bch2_lookup_trans(struct btree_trans *trans, struct bch_subvolume subvol; struct bch_inode_unpacked inode_u; - ret = bch2_subvolume_get(trans, inum.subvol, true, 0, &subvol) ?: + ret = bch2_subvolume_get(trans, inum.subvol, true, &subvol) ?: bch2_inode_find_by_inum_nowarn_trans(trans, inum, &inode_u) ?: PTR_ERR_OR_ZERO(inode = bch2_inode_hash_init_insert(trans, inum, &inode_u, &subvol)); @@ -628,7 +664,7 @@ static struct bch_inode_info *bch2_lookup_trans(struct btree_trans *trans, goto err; /* regular files may have hardlinks: */ - if (bch2_fs_inconsistent_on(bch2_inode_should_have_bp(&inode_u) && + if (bch2_fs_inconsistent_on(bch2_inode_should_have_single_bp(&inode_u) && !bkey_eq(k.k->p, POS(inode_u.bi_dir, inode_u.bi_dir_offset)), c, "dirent points to inode that does not point back:\n %s", @@ -706,7 +742,7 @@ static int __bch2_link(struct bch_fs *c, if (likely(!ret)) { bch2_inode_update_after_write(trans, dir, &dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); bch2_inode_update_after_write(trans, inode, &inode_u, ATTR_CTIME); } @@ -759,7 +795,7 @@ int __bch2_unlink(struct inode *vdir, struct dentry *dentry, goto err; bch2_inode_update_after_write(trans, dir, &dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); bch2_inode_update_after_write(trans, inode, &inode_u, ATTR_MTIME); @@ -937,11 +973,11 @@ err_tx_restart: dst_inode->v.i_ino != dst_inode_u.bi_inum); bch2_inode_update_after_write(trans, src_dir, &src_dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); if (src_dir != dst_dir) bch2_inode_update_after_write(trans, dst_dir, &dst_dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); bch2_inode_update_after_write(trans, src_inode, &src_inode_u, ATTR_CTIME); @@ -1245,7 +1281,6 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info, struct btree_iter iter; struct bkey_s_c k; struct bkey_buf cur, prev; - unsigned offset_into_extent, sectors; bool have_extent = false; int ret = 0; @@ -1278,7 +1313,7 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info, bch2_btree_iter_set_snapshot(&iter, snapshot); - k = bch2_btree_iter_peek_upto(&iter, end); + k = bch2_btree_iter_peek_max(&iter, end); ret = bkey_err(k); if (ret) continue; @@ -1292,9 +1327,8 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info, continue; } - offset_into_extent = iter.pos.offset - - bkey_start_offset(k.k); - sectors = k.k->size - offset_into_extent; + s64 offset_into_extent = iter.pos.offset - bkey_start_offset(k.k); + unsigned sectors = k.k->size - offset_into_extent; bch2_bkey_buf_reassemble(&cur, c, k); @@ -1306,7 +1340,7 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info, k = bkey_i_to_s_c(cur.k); bch2_bkey_buf_realloc(&prev, c, k.k->u64s); - sectors = min(sectors, k.k->size - offset_into_extent); + sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent); bch2_cut_front(POS(k.k->p.inode, bkey_start_offset(k.k) + @@ -1736,7 +1770,6 @@ static void bch2_vfs_inode_init(struct btree_trans *trans, bch2_inode_update_after_write(trans, inode, bi, ~0); inode->v.i_blocks = bi->bi_sectors; - inode->v.i_ino = bi->bi_inum; inode->v.i_rdev = bi->bi_dev; inode->v.i_generation = bi->bi_generation; inode->v.i_size = bi->bi_size; @@ -2200,7 +2233,8 @@ got_sb: sb->s_time_gran = c->sb.nsec_per_time_unit; sb->s_time_min = div_s64(S64_MIN, c->sb.time_units_per_sec) + 1; sb->s_time_max = div_s64(S64_MAX, c->sb.time_units_per_sec); - sb->s_uuid = c->sb.user_uuid; + super_set_uuid(sb, c->sb.user_uuid.b, sizeof(c->sb.user_uuid)); + super_set_sysfs_name_uuid(sb); sb->s_shrink->seeks = 0; c->vfs_sb = sb; strscpy(sb->s_id, c->name, sizeof(sb->s_id)); @@ -2345,13 +2379,16 @@ static int bch2_init_fs_context(struct fs_context *fc) void bch2_fs_vfs_exit(struct bch_fs *c) { + if (c->vfs_inodes_by_inum_table.ht.tbl) + rhltable_destroy(&c->vfs_inodes_by_inum_table); if (c->vfs_inodes_table.tbl) rhashtable_destroy(&c->vfs_inodes_table); } int bch2_fs_vfs_init(struct bch_fs *c) { - return rhashtable_init(&c->vfs_inodes_table, &bch2_vfs_inodes_params); + return rhashtable_init(&c->vfs_inodes_table, &bch2_vfs_inodes_params) ?: + rhltable_init(&c->vfs_inodes_by_inum_table, &bch2_vfs_inodes_by_inum_params); } static struct file_system_type bcache_fs_type = { diff --git a/fs/bcachefs/fs.h b/fs/bcachefs/fs.h index 59f9f7ae728d..dd2198541455 100644 --- a/fs/bcachefs/fs.h +++ b/fs/bcachefs/fs.h @@ -14,6 +14,7 @@ struct bch_inode_info { struct inode v; struct rhash_head hash; + struct rhlist_head by_inum_hash; subvol_inum ei_inum; struct list_head ei_vfs_inode_list; diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 75c8a97a6954..53a421ff136d 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" +#include "bcachefs_ioctl.h" #include "bkey_buf.h" #include "btree_cache.h" #include "btree_update.h" @@ -16,6 +17,7 @@ #include "recovery_passes.h" #include "snapshot.h" #include "super.h" +#include "thread_with_file.h" #include "xattr.h" #include @@ -73,7 +75,7 @@ static s64 bch2_count_inode_sectors(struct btree_trans *trans, u64 inum, { u64 sectors = 0; - int ret = for_each_btree_key_upto(trans, iter, BTREE_ID_extents, + int ret = for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(inum, 0, snapshot), POS(inum, U64_MAX), 0, k, ({ @@ -90,7 +92,7 @@ static s64 bch2_count_subdirs(struct btree_trans *trans, u64 inum, { u64 subdirs = 0; - int ret = for_each_btree_key_upto(trans, iter, BTREE_ID_dirents, + int ret = for_each_btree_key_max(trans, iter, BTREE_ID_dirents, SPOS(inum, 0, snapshot), POS(inum, U64_MAX), 0, k, ({ @@ -107,7 +109,7 @@ static int subvol_lookup(struct btree_trans *trans, u32 subvol, u32 *snapshot, u64 *inum) { struct bch_subvolume s; - int ret = bch2_subvolume_get(trans, subvol, false, 0, &s); + int ret = bch2_subvolume_get(trans, subvol, false, &s); *snapshot = le32_to_cpu(s.snapshot); *inum = le64_to_cpu(s.inode); @@ -170,7 +172,7 @@ static int lookup_dirent_in_snapshot(struct btree_trans *trans, if (ret) return ret; - struct bkey_s_c_dirent d = bkey_s_c_to_dirent(bch2_btree_iter_peek_slot(&iter)); + struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); *target = le64_to_cpu(d.v->d_inum); *type = d.v->d_type; bch2_trans_iter_exit(trans, &iter); @@ -203,6 +205,36 @@ err: return ret; } +/* + * Find any subvolume associated with a tree of snapshots + * We can't rely on master_subvol - it might have been deleted. + */ +static int find_snapshot_tree_subvol(struct btree_trans *trans, + u32 tree_id, u32 *subvol) +{ + struct btree_iter iter; + struct bkey_s_c k; + int ret; + + for_each_btree_key_norestart(trans, iter, BTREE_ID_snapshots, POS_MIN, 0, k, ret) { + if (k.k->type != KEY_TYPE_snapshot) + continue; + + struct bkey_s_c_snapshot s = bkey_s_c_to_snapshot(k); + if (le32_to_cpu(s.v->tree) != tree_id) + continue; + + if (s.v->subvol) { + *subvol = le32_to_cpu(s.v->subvol); + goto found; + } + } + ret = -BCH_ERR_ENOENT_no_snapshot_tree_subvol; +found: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + /* Get lost+found, create if it doesn't exist: */ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, struct bch_inode_unpacked *lostfound, @@ -210,6 +242,7 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, { struct bch_fs *c = trans->c; struct qstr lostfound_str = QSTR("lost+found"); + struct btree_iter lostfound_iter = { NULL }; u64 inum = 0; unsigned d_type = 0; int ret; @@ -220,20 +253,24 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, if (ret) return ret; - subvol_inum root_inum = { .subvol = le32_to_cpu(st.master_subvol) }; + u32 subvolid; + ret = find_snapshot_tree_subvol(trans, + bch2_snapshot_tree(c, snapshot), &subvolid); + bch_err_msg(c, ret, "finding subvol associated with snapshot tree %u", + bch2_snapshot_tree(c, snapshot)); + if (ret) + return ret; struct bch_subvolume subvol; - ret = bch2_subvolume_get(trans, le32_to_cpu(st.master_subvol), - false, 0, &subvol); - bch_err_msg(c, ret, "looking up root subvol %u for snapshot %u", - le32_to_cpu(st.master_subvol), snapshot); + ret = bch2_subvolume_get(trans, subvolid, false, &subvol); + bch_err_msg(c, ret, "looking up subvol %u for snapshot %u", subvolid, snapshot); if (ret) return ret; if (!subvol.inode) { struct btree_iter iter; struct bkey_i_subvolume *subvol = bch2_bkey_get_mut_typed(trans, &iter, - BTREE_ID_subvolumes, POS(0, le32_to_cpu(st.master_subvol)), + BTREE_ID_subvolumes, POS(0, subvolid), 0, subvolume); ret = PTR_ERR_OR_ZERO(subvol); if (ret) @@ -243,13 +280,16 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, bch2_trans_iter_exit(trans, &iter); } - root_inum.inum = le64_to_cpu(subvol.inode); + subvol_inum root_inum = { + .subvol = subvolid, + .inum = le64_to_cpu(subvol.inode) + }; struct bch_inode_unpacked root_inode; struct bch_hash_info root_hash_info; ret = lookup_inode(trans, root_inum.inum, snapshot, &root_inode); bch_err_msg(c, ret, "looking up root inode %llu for subvol %u", - root_inum.inum, le32_to_cpu(st.master_subvol)); + root_inum.inum, subvolid); if (ret) return ret; @@ -288,11 +328,16 @@ create_lostfound: * XXX: we could have a nicer log message here if we had a nice way to * walk backpointers to print a path */ - bch_notice(c, "creating lost+found in subvol %llu snapshot %u", - root_inum.subvol, le32_to_cpu(st.root_snapshot)); + struct printbuf path = PRINTBUF; + ret = bch2_inum_to_path(trans, root_inum, &path); + if (ret) + goto err; + + bch_notice(c, "creating %s/lost+found in subvol %llu snapshot %u", + path.buf, root_inum.subvol, snapshot); + printbuf_exit(&path); u64 now = bch2_current_time(c); - struct btree_iter lostfound_iter = { NULL }; u64 cpu = raw_smp_processor_id(); bch2_inode_init_early(c, lostfound); @@ -405,7 +450,7 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * return ret; struct bch_hash_info dir_hash = bch2_hash_info_init(c, &lostfound); - struct qstr name = (struct qstr) QSTR(name_buf); + struct qstr name = QSTR(name_buf); inode->bi_dir = lostfound.bi_inum; @@ -451,7 +496,9 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * continue; struct bch_inode_unpacked child_inode; - bch2_inode_unpack(k, &child_inode); + ret = bch2_inode_unpack(k, &child_inode); + if (ret) + break; if (!inode_should_reattach(&child_inode)) { ret = maybe_delete_dirent(trans, @@ -482,6 +529,13 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * return ret; } +static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans, + struct btree_iter *iter, + struct bpos pos) +{ + return bch2_bkey_get_iter_typed(trans, iter, BTREE_ID_dirents, pos, 0, dirent); +} + static int remove_backpointer(struct btree_trans *trans, struct bch_inode_unpacked *inode) { @@ -490,13 +544,11 @@ static int remove_backpointer(struct btree_trans *trans, struct bch_fs *c = trans->c; struct btree_iter iter; - struct bkey_s_c_dirent d = - bch2_bkey_get_iter_typed(trans, &iter, BTREE_ID_dirents, - SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot), 0, - dirent); - int ret = bkey_err(d) ?: - dirent_points_to_inode(c, d, inode) ?: - __remove_dirent(trans, d.k->p); + struct bkey_s_c_dirent d = dirent_get_by_pos(trans, &iter, + SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot)); + int ret = bkey_err(d) ?: + dirent_points_to_inode(c, d, inode) ?: + __remove_dirent(trans, d.k->p); bch2_trans_iter_exit(trans, &iter); return ret; } @@ -613,7 +665,7 @@ static int reconstruct_inode(struct btree_trans *trans, enum btree_id btree, u32 struct btree_iter iter = {}; bch2_trans_iter_init(trans, &iter, BTREE_ID_extents, SPOS(inum, U64_MAX, snapshot), 0); - struct bkey_s_c k = bch2_btree_iter_peek_prev(&iter); + struct bkey_s_c k = bch2_btree_iter_peek_prev_min(&iter, POS(inum, 0)); bch2_trans_iter_exit(trans, &iter); int ret = bkey_err(k); if (ret) @@ -780,11 +832,13 @@ struct inode_walker { struct bpos last_pos; DARRAY(struct inode_walker_entry) inodes; + snapshot_id_list deletes; }; static void inode_walker_exit(struct inode_walker *w) { darray_exit(&w->inodes); + darray_exit(&w->deletes); } static struct inode_walker inode_walker_init(void) @@ -797,9 +851,8 @@ static int add_inode(struct bch_fs *c, struct inode_walker *w, { struct bch_inode_unpacked u; - BUG_ON(bch2_inode_unpack(inode, &u)); - - return darray_push(&w->inodes, ((struct inode_walker_entry) { + return bch2_inode_unpack(inode, &u) ?: + darray_push(&w->inodes, ((struct inode_walker_entry) { .inode = u, .snapshot = inode.k->p.snapshot, })); @@ -909,8 +962,9 @@ static int get_visible_inodes(struct btree_trans *trans, int ret; w->inodes.nr = 0; + w->deletes.nr = 0; - for_each_btree_key_norestart(trans, iter, BTREE_ID_inodes, POS(0, inum), + for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inum, s->pos.snapshot), BTREE_ITER_all_snapshots, k, ret) { if (k.k->p.offset != inum) break; @@ -918,10 +972,13 @@ static int get_visible_inodes(struct btree_trans *trans, if (!ref_visible(c, s, s->pos.snapshot, k.k->p.snapshot)) continue; - if (bkey_is_inode(k.k)) - add_inode(c, w, k); + if (snapshot_list_has_ancestor(c, &w->deletes, k.k->p.snapshot)) + continue; - if (k.k->p.snapshot >= s->pos.snapshot) + ret = bkey_is_inode(k.k) + ? add_inode(c, w, k) + : snapshot_list_add(c, &w->deletes, k.k->p.snapshot); + if (ret) break; } bch2_trans_iter_exit(trans, &iter); @@ -929,69 +986,16 @@ static int get_visible_inodes(struct btree_trans *trans, return ret; } -static int dirent_has_target(struct btree_trans *trans, struct bkey_s_c_dirent d) -{ - if (d.v->d_type == DT_SUBVOL) { - u32 snap; - u64 inum; - int ret = subvol_lookup(trans, le32_to_cpu(d.v->d_child_subvol), &snap, &inum); - if (ret && !bch2_err_matches(ret, ENOENT)) - return ret; - return !ret; - } else { - struct btree_iter iter; - struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, - SPOS(0, le64_to_cpu(d.v->d_inum), d.k->p.snapshot), 0); - int ret = bkey_err(k); - if (ret) - return ret; - - ret = bkey_is_inode(k.k); - bch2_trans_iter_exit(trans, &iter); - return ret; - } -} - /* * Prefer to delete the first one, since that will be the one at the wrong * offset: * return value: 0 -> delete k1, 1 -> delete k2 */ -static int hash_pick_winner(struct btree_trans *trans, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct bkey_s_c k1, - struct bkey_s_c k2) -{ - if (bkey_val_bytes(k1.k) == bkey_val_bytes(k2.k) && - !memcmp(k1.v, k2.v, bkey_val_bytes(k1.k))) - return 0; - - switch (desc.btree_id) { - case BTREE_ID_dirents: { - int ret = dirent_has_target(trans, bkey_s_c_to_dirent(k1)); - if (ret < 0) - return ret; - if (!ret) - return 0; - - ret = dirent_has_target(trans, bkey_s_c_to_dirent(k2)); - if (ret < 0) - return ret; - if (!ret) - return 1; - return 2; - } - default: - return 0; - } -} - -static int fsck_update_backpointers(struct btree_trans *trans, - struct snapshots_seen *s, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct bkey_i *new) +int bch2_fsck_update_backpointers(struct btree_trans *trans, + struct snapshots_seen *s, + const struct bch_hash_desc desc, + struct bch_hash_info *hash_info, + struct bkey_i *new) { if (new->k.type != KEY_TYPE_dirent) return 0; @@ -1019,160 +1023,6 @@ err: return ret; } -static int fsck_rename_dirent(struct btree_trans *trans, - struct snapshots_seen *s, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct bkey_s_c_dirent old) -{ - struct qstr old_name = bch2_dirent_get_name(old); - struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, bkey_bytes(old.k) + 32); - int ret = PTR_ERR_OR_ZERO(new); - if (ret) - return ret; - - bkey_dirent_init(&new->k_i); - dirent_copy_target(new, old); - new->k.p = old.k->p; - - for (unsigned i = 0; i < 1000; i++) { - unsigned len = sprintf(new->v.d_name, "%.*s.fsck_renamed-%u", - old_name.len, old_name.name, i); - unsigned u64s = BKEY_U64s + dirent_val_u64s(len); - - if (u64s > U8_MAX) - return -EINVAL; - - new->k.u64s = u64s; - - ret = bch2_hash_set_in_snapshot(trans, bch2_dirent_hash_desc, hash_info, - (subvol_inum) { 0, old.k->p.inode }, - old.k->p.snapshot, &new->k_i, - BTREE_UPDATE_internal_snapshot_node); - if (!bch2_err_matches(ret, EEXIST)) - break; - } - - if (ret) - return ret; - - return fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i); -} - -static int hash_check_key(struct btree_trans *trans, - struct snapshots_seen *s, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct btree_iter *k_iter, struct bkey_s_c hash_k) -{ - struct bch_fs *c = trans->c; - struct btree_iter iter = { NULL }; - struct printbuf buf = PRINTBUF; - struct bkey_s_c k; - u64 hash; - int ret = 0; - - if (hash_k.k->type != desc.key_type) - return 0; - - hash = desc.hash_bkey(hash_info, hash_k); - - if (likely(hash == hash_k.k->p.offset)) - return 0; - - if (hash_k.k->p.offset < hash) - goto bad_hash; - - for_each_btree_key_norestart(trans, iter, desc.btree_id, - SPOS(hash_k.k->p.inode, hash, hash_k.k->p.snapshot), - BTREE_ITER_slots, k, ret) { - if (bkey_eq(k.k->p, hash_k.k->p)) - break; - - if (k.k->type == desc.key_type && - !desc.cmp_bkey(k, hash_k)) - goto duplicate_entries; - - if (bkey_deleted(k.k)) { - bch2_trans_iter_exit(trans, &iter); - goto bad_hash; - } - } -out: - bch2_trans_iter_exit(trans, &iter); - printbuf_exit(&buf); - return ret; -bad_hash: - if (fsck_err(trans, hash_table_key_wrong_offset, - "hash table key at wrong offset: btree %s inode %llu offset %llu, hashed to %llu\n %s", - bch2_btree_id_str(desc.btree_id), hash_k.k->p.inode, hash_k.k->p.offset, hash, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, hash_k), buf.buf))) { - struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, hash_k); - if (IS_ERR(new)) - return PTR_ERR(new); - - k = bch2_hash_set_or_get_in_snapshot(trans, &iter, desc, hash_info, - (subvol_inum) { 0, hash_k.k->p.inode }, - hash_k.k->p.snapshot, new, - STR_HASH_must_create| - BTREE_ITER_with_updates| - BTREE_UPDATE_internal_snapshot_node); - ret = bkey_err(k); - if (ret) - goto out; - if (k.k) - goto duplicate_entries; - - ret = bch2_hash_delete_at(trans, desc, hash_info, k_iter, - BTREE_UPDATE_internal_snapshot_node) ?: - fsck_update_backpointers(trans, s, desc, hash_info, new) ?: - bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: - -BCH_ERR_transaction_restart_nested; - goto out; - } -fsck_err: - goto out; -duplicate_entries: - ret = hash_pick_winner(trans, desc, hash_info, hash_k, k); - if (ret < 0) - goto out; - - if (!fsck_err(trans, hash_table_key_duplicate, - "duplicate hash table keys%s:\n%s", - ret != 2 ? "" : ", both point to valid inodes", - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, hash_k), - prt_newline(&buf), - bch2_bkey_val_to_text(&buf, c, k), - buf.buf))) - goto out; - - switch (ret) { - case 0: - ret = bch2_hash_delete_at(trans, desc, hash_info, k_iter, 0); - break; - case 1: - ret = bch2_hash_delete_at(trans, desc, hash_info, &iter, 0); - break; - case 2: - ret = fsck_rename_dirent(trans, s, desc, hash_info, bkey_s_c_to_dirent(hash_k)) ?: - bch2_hash_delete_at(trans, desc, hash_info, k_iter, 0); - goto out; - } - - ret = bch2_trans_commit(trans, NULL, NULL, 0) ?: - -BCH_ERR_transaction_restart_nested; - goto out; -} - -static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans, - struct btree_iter *iter, - struct bpos pos) -{ - return bch2_bkey_get_iter_typed(trans, iter, BTREE_ID_dirents, pos, 0, dirent); -} - static struct bkey_s_c_dirent inode_get_dirent(struct btree_trans *trans, struct btree_iter *iter, struct bch_inode_unpacked *inode, @@ -1260,12 +1110,43 @@ static int get_snapshot_root_inode(struct btree_trans *trans, goto err; BUG(); found_root: - BUG_ON(bch2_inode_unpack(k, root)); + ret = bch2_inode_unpack(k, root); err: bch2_trans_iter_exit(trans, &iter); return ret; } +static int check_directory_size(struct btree_trans *trans, + struct bch_inode_unpacked *inode_u, + struct bkey_s_c inode_k, bool *write_inode) +{ + struct btree_iter iter; + struct bkey_s_c k; + u64 new_size = 0; + int ret; + + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_dirents, + SPOS(inode_k.k->p.offset, 0, inode_k.k->p.snapshot), + POS(inode_k.k->p.offset, U64_MAX), + 0, k, ret) { + if (k.k->type != KEY_TYPE_dirent) + continue; + + struct bkey_s_c_dirent dirent = bkey_s_c_to_dirent(k); + struct qstr name = bch2_dirent_get_name(dirent); + + new_size += dirent_occupied_size(&name); + } + bch2_trans_iter_exit(trans, &iter); + + if (!ret && inode_u->bi_size != new_size) { + inode_u->bi_size = new_size; + *write_inode = true; + } + + return ret; +} + static int check_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, @@ -1291,7 +1172,9 @@ static int check_inode(struct btree_trans *trans, if (!bkey_is_inode(k.k)) return 0; - BUG_ON(bch2_inode_unpack(k, &u)); + ret = bch2_inode_unpack(k, &u); + if (ret) + goto err; if (snapshot_root->bi_inum != u.bi_inum) { ret = get_snapshot_root_inode(trans, snapshot_root, u.bi_inum); @@ -1302,7 +1185,7 @@ static int check_inode(struct btree_trans *trans, if (fsck_err_on(u.bi_hash_seed != snapshot_root->bi_hash_seed || INODE_STR_HASH(&u) != INODE_STR_HASH(snapshot_root), trans, inode_snapshot_mismatch, - "inodes in different snapshots don't match")) { + "inode hash info in different snapshots don't match")) { u.bi_hash_seed = snapshot_root->bi_hash_seed; SET_INODE_STR_HASH(&u, INODE_STR_HASH(snapshot_root)); do_update = true; @@ -1392,7 +1275,7 @@ static int check_inode(struct btree_trans *trans, if (fsck_err_on(!ret, trans, inode_unlinked_and_not_open, - "inode %llu%u unlinked and not open", + "inode %llu:%u unlinked and not open", u.bi_inum, u.bi_snapshot)) { ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot); bch_err_msg(c, ret, "in fsck deleting inode"); @@ -1415,7 +1298,7 @@ static int check_inode(struct btree_trans *trans, if (u.bi_subvol) { struct bch_subvolume s; - ret = bch2_subvolume_get(trans, u.bi_subvol, false, 0, &s); + ret = bch2_subvolume_get(trans, u.bi_subvol, false, &s); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; @@ -1441,6 +1324,27 @@ static int check_inode(struct btree_trans *trans, do_update = true; } } + + if (fsck_err_on(u.bi_journal_seq > journal_cur_seq(&c->journal), + trans, inode_journal_seq_in_future, + "inode journal seq in future (currently at %llu)\n%s", + journal_cur_seq(&c->journal), + (printbuf_reset(&buf), + bch2_inode_unpacked_to_text(&buf, &u), + buf.buf))) { + u.bi_journal_seq = journal_cur_seq(&c->journal); + do_update = true; + } + + if (S_ISDIR(u.bi_mode)) { + ret = check_directory_size(trans, &u, k, &do_update); + + fsck_err_on(ret, + trans, directory_size_mismatch, + "directory inode %llu:%u with the mismatch directory size", + u.bi_inum, k.k->p.snapshot); + ret = 0; + } do_update: if (do_update) { ret = __bch2_fsck_write_inode(trans, &u); @@ -1502,7 +1406,9 @@ static int find_oldest_inode_needs_reattach(struct btree_trans *trans, break; struct bch_inode_unpacked parent_inode; - bch2_inode_unpack(k, &parent_inode); + ret = bch2_inode_unpack(k, &parent_inode); + if (ret) + break; if (!inode_should_reattach(&parent_inode)) break; @@ -1525,7 +1431,9 @@ static int check_unreachable_inode(struct btree_trans *trans, return 0; struct bch_inode_unpacked inode; - BUG_ON(bch2_inode_unpack(k, &inode)); + ret = bch2_inode_unpack(k, &inode); + if (ret) + return ret; if (!inode_should_reattach(&inode)) return 0; @@ -1649,7 +1557,7 @@ static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_wal if (i->count != count2) { bch_err_ratelimited(c, "fsck counted i_sectors wrong for inode %llu:%u: got %llu should be %llu", w->last_pos.inode, i->snapshot, i->count, count2); - return -BCH_ERR_internal_fsck_err; + i->count = count2; } if (fsck_err_on(!(i->inode.bi_flags & BCH_INODE_i_sectors_dirty), @@ -1753,7 +1661,7 @@ static int overlapping_extents_found(struct btree_trans *trans, bch2_trans_iter_init(trans, &iter1, btree, pos1, BTREE_ITER_all_snapshots| BTREE_ITER_not_extents); - k1 = bch2_btree_iter_peek_upto(&iter1, POS(pos1.inode, U64_MAX)); + k1 = bch2_btree_iter_peek_max(&iter1, POS(pos1.inode, U64_MAX)); ret = bkey_err(k1); if (ret) goto err; @@ -1778,7 +1686,7 @@ static int overlapping_extents_found(struct btree_trans *trans, while (1) { bch2_btree_iter_advance(&iter2); - k2 = bch2_btree_iter_peek_upto(&iter2, POS(pos1.inode, U64_MAX)); + k2 = bch2_btree_iter_peek_max(&iter2, POS(pos1.inode, U64_MAX)); ret = bkey_err(k2); if (ret) goto err; @@ -2156,7 +2064,7 @@ static int check_dirent_inode_dirent(struct btree_trans *trans, return __bch2_fsck_write_inode(trans, target); } - if (bch2_inode_should_have_bp(target) && + if (bch2_inode_should_have_single_bp(target) && !fsck_err(trans, inode_wrong_backpointer, "dirent points to inode that does not point back:\n %s", (bch2_bkey_val_to_text(&buf, c, d.s_c), @@ -2480,7 +2388,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, *hash_info = bch2_hash_info_init(c, &i->inode); dir->first_this_inode = false; - ret = hash_check_key(trans, s, bch2_dirent_hash_desc, hash_info, iter, k); + ret = bch2_str_hash_check_key(trans, s, &bch2_dirent_hash_desc, hash_info, iter, k); if (ret < 0) goto err; if (ret) { @@ -2519,6 +2427,30 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, if (ret) goto err; } + + darray_for_each(target->deletes, i) + if (fsck_err_on(!snapshot_list_has_id(&s->ids, *i), + trans, dirent_to_overwritten_inode, + "dirent points to inode overwritten in snapshot %u:\n%s", + *i, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), + buf.buf))) { + struct btree_iter delete_iter; + bch2_trans_iter_init(trans, &delete_iter, + BTREE_ID_dirents, + SPOS(k.k->p.inode, k.k->p.offset, *i), + BTREE_ITER_intent); + ret = bch2_btree_iter_traverse(&delete_iter) ?: + bch2_hash_delete_at(trans, bch2_dirent_hash_desc, + hash_info, + &delete_iter, + BTREE_UPDATE_internal_snapshot_node); + bch2_trans_iter_exit(trans, &delete_iter); + if (ret) + goto err; + + } } ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); @@ -2594,7 +2526,7 @@ static int check_xattr(struct btree_trans *trans, struct btree_iter *iter, *hash_info = bch2_hash_info_init(c, &i->inode); inode->first_this_inode = false; - ret = hash_check_key(trans, NULL, bch2_xattr_hash_desc, hash_info, iter, k); + ret = bch2_str_hash_check_key(trans, NULL, &bch2_xattr_hash_desc, hash_info, iter, k); bch_err_fn(c, ret); return ret; } @@ -2774,6 +2706,48 @@ struct pathbuf_entry { typedef DARRAY(struct pathbuf_entry) pathbuf; +static int bch2_bi_depth_renumber_one(struct btree_trans *trans, struct pathbuf_entry *p, + u32 new_depth) +{ + struct btree_iter iter; + struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, + SPOS(0, p->inum, p->snapshot), 0); + + struct bch_inode_unpacked inode; + int ret = bkey_err(k) ?: + !bkey_is_inode(k.k) ? -BCH_ERR_ENOENT_inode + : bch2_inode_unpack(k, &inode); + if (ret) + goto err; + + if (inode.bi_depth != new_depth) { + inode.bi_depth = new_depth; + ret = __bch2_fsck_write_inode(trans, &inode) ?: + bch2_trans_commit(trans, NULL, NULL, 0); + } +err: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32 new_bi_depth) +{ + u32 restart_count = trans->restart_count; + int ret = 0; + + darray_for_each_reverse(*path, i) { + ret = nested_lockrestart_do(trans, + bch2_bi_depth_renumber_one(trans, i, new_bi_depth)); + bch_err_fn(trans->c, ret); + if (ret) + break; + + new_bi_depth++; + } + + return ret ?: trans_was_restarted(trans, restart_count); +} + static bool path_is_dup(pathbuf *p, u64 inum, u32 snapshot) { darray_for_each(*p, i) @@ -2783,21 +2757,21 @@ static bool path_is_dup(pathbuf *p, u64 inum, u32 snapshot) return false; } -static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c inode_k) +static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) { struct bch_fs *c = trans->c; struct btree_iter inode_iter = {}; - struct bch_inode_unpacked inode; + pathbuf path = {}; struct printbuf buf = PRINTBUF; u32 snapshot = inode_k.k->p.snapshot; + bool redo_bi_depth = false; + u32 min_bi_depth = U32_MAX; int ret = 0; - p->nr = 0; - - BUG_ON(bch2_inode_unpack(inode_k, &inode)); - - if (!S_ISDIR(inode.bi_mode)) - return 0; + struct bch_inode_unpacked inode; + ret = bch2_inode_unpack(inode_k, &inode); + if (ret) + return ret; while (!inode.bi_subvol) { struct btree_iter dirent_iter; @@ -2807,7 +2781,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino d = inode_get_dirent(trans, &dirent_iter, &inode, &parent_snapshot); ret = bkey_err(d.s_c); if (ret && !bch2_err_matches(ret, ENOENT)) - break; + goto out; if (!ret && (ret = dirent_points_to_inode(c, d, &inode))) bch2_trans_iter_exit(trans, &dirent_iter); @@ -2822,7 +2796,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino bch2_trans_iter_exit(trans, &dirent_iter); - ret = darray_push(p, ((struct pathbuf_entry) { + ret = darray_push(&path, ((struct pathbuf_entry) { .inum = inode.bi_inum, .snapshot = snapshot, })); @@ -2834,22 +2808,32 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino bch2_trans_iter_exit(trans, &inode_iter); inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, SPOS(0, inode.bi_dir, snapshot), 0); + + struct bch_inode_unpacked parent_inode; ret = bkey_err(inode_k) ?: !bkey_is_inode(inode_k.k) ? -BCH_ERR_ENOENT_inode - : bch2_inode_unpack(inode_k, &inode); + : bch2_inode_unpack(inode_k, &parent_inode); if (ret) { /* Should have been caught in dirents pass */ bch_err_msg(c, ret, "error looking up parent directory"); - break; + goto out; } - snapshot = inode_k.k->p.snapshot; + min_bi_depth = parent_inode.bi_depth; - if (path_is_dup(p, inode.bi_inum, snapshot)) { + if (parent_inode.bi_depth < inode.bi_depth && + min_bi_depth < U16_MAX) + break; + + inode = parent_inode; + snapshot = inode_k.k->p.snapshot; + redo_bi_depth = true; + + if (path_is_dup(&path, inode.bi_inum, snapshot)) { /* XXX print path */ bch_err(c, "directory structure loop"); - darray_for_each(*p, i) + darray_for_each(path, i) pr_err("%llu:%u", i->inum, i->snapshot); pr_err("%llu:%u", inode.bi_inum, snapshot); @@ -2862,12 +2846,20 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino ret = reattach_inode(trans, &inode); bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum); } - break; + + goto out; } } + + if (inode.bi_subvol) + min_bi_depth = 0; + + if (redo_bi_depth) + ret = bch2_bi_depth_renumber(trans, &path, min_bi_depth); out: fsck_err: bch2_trans_iter_exit(trans, &inode_iter); + darray_exit(&path); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; @@ -2879,24 +2871,20 @@ fsck_err: */ int bch2_check_directory_structure(struct bch_fs *c) { - pathbuf path = { 0, }; - int ret; - - ret = bch2_trans_run(c, + int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ - if (!bkey_is_inode(k.k)) + if (!S_ISDIR(bkey_inode_mode(k))) continue; if (bch2_inode_flags(k) & BCH_INODE_unlinked) continue; - check_path(trans, &path, k); + check_path_loop(trans, k); }))); - darray_exit(&path); bch_err_fn(c, ret); return ret; @@ -2994,7 +2982,9 @@ static int check_nlinks_find_hardlinks(struct bch_fs *c, /* Should never fail, checked by bch2_inode_invalid: */ struct bch_inode_unpacked u; - BUG_ON(bch2_inode_unpack(k, &u)); + _ret3 = bch2_inode_unpack(k, &u); + if (_ret3) + break; /* * Backpointer and directory structure checks are sufficient for @@ -3072,7 +3062,9 @@ static int check_nlinks_update_inode(struct btree_trans *trans, struct btree_ite if (!bkey_is_inode(k.k)) return 0; - BUG_ON(bch2_inode_unpack(k, &u)); + ret = bch2_inode_unpack(k, &u); + if (ret) + return ret; if (S_ISDIR(u.bi_mode)) return 0; @@ -3194,3 +3186,223 @@ int bch2_fix_reflink_p(struct bch_fs *c) bch_err_fn(c, ret); return ret; } + +#ifndef NO_BCACHEFS_CHARDEV + +struct fsck_thread { + struct thread_with_stdio thr; + struct bch_fs *c; + struct bch_opts opts; +}; + +static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr) +{ + struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr); + kfree(thr); +} + +static int bch2_fsck_offline_thread_fn(struct thread_with_stdio *stdio) +{ + struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); + struct bch_fs *c = thr->c; + + int ret = PTR_ERR_OR_ZERO(c); + if (ret) + return ret; + + ret = bch2_fs_start(thr->c); + if (ret) + goto err; + + if (test_bit(BCH_FS_errors_fixed, &c->flags)) { + bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: errors fixed\n", c->name); + ret |= 1; + } + if (test_bit(BCH_FS_error, &c->flags)) { + bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: still has errors\n", c->name); + ret |= 4; + } +err: + bch2_fs_stop(c); + return ret; +} + +static const struct thread_with_stdio_ops bch2_offline_fsck_ops = { + .exit = bch2_fsck_thread_exit, + .fn = bch2_fsck_offline_thread_fn, +}; + +long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_arg) +{ + struct bch_ioctl_fsck_offline arg; + struct fsck_thread *thr = NULL; + darray_str(devs) = {}; + long ret = 0; + + if (copy_from_user(&arg, user_arg, sizeof(arg))) + return -EFAULT; + + if (arg.flags) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + for (size_t i = 0; i < arg.nr_devs; i++) { + u64 dev_u64; + ret = copy_from_user_errcode(&dev_u64, &user_arg->devs[i], sizeof(u64)); + if (ret) + goto err; + + char *dev_str = strndup_user((char __user *)(unsigned long) dev_u64, PATH_MAX); + ret = PTR_ERR_OR_ZERO(dev_str); + if (ret) + goto err; + + ret = darray_push(&devs, dev_str); + if (ret) { + kfree(dev_str); + goto err; + } + } + + thr = kzalloc(sizeof(*thr), GFP_KERNEL); + if (!thr) { + ret = -ENOMEM; + goto err; + } + + thr->opts = bch2_opts_empty(); + + if (arg.opts) { + char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); + ret = PTR_ERR_OR_ZERO(optstr) ?: + bch2_parse_mount_opts(NULL, &thr->opts, NULL, optstr); + if (!IS_ERR(optstr)) + kfree(optstr); + + if (ret) + goto err; + } + + opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio); + opt_set(thr->opts, read_only, 1); + opt_set(thr->opts, ratelimit_errors, 0); + + /* We need request_key() to be called before we punt to kthread: */ + opt_set(thr->opts, nostart, true); + + bch2_thread_with_stdio_init(&thr->thr, &bch2_offline_fsck_ops); + + thr->c = bch2_fs_open(devs.data, arg.nr_devs, thr->opts); + + if (!IS_ERR(thr->c) && + thr->c->opts.errors == BCH_ON_ERROR_panic) + thr->c->opts.errors = BCH_ON_ERROR_ro; + + ret = __bch2_run_thread_with_stdio(&thr->thr); +out: + darray_for_each(devs, i) + kfree(*i); + darray_exit(&devs); + return ret; +err: + if (thr) + bch2_fsck_thread_exit(&thr->thr); + pr_err("ret %s", bch2_err_str(ret)); + goto out; +} + +static int bch2_fsck_online_thread_fn(struct thread_with_stdio *stdio) +{ + struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); + struct bch_fs *c = thr->c; + + c->stdio_filter = current; + c->stdio = &thr->thr.stdio; + + /* + * XXX: can we figure out a way to do this without mucking with c->opts? + */ + unsigned old_fix_errors = c->opts.fix_errors; + if (opt_defined(thr->opts, fix_errors)) + c->opts.fix_errors = thr->opts.fix_errors; + else + c->opts.fix_errors = FSCK_FIX_ask; + + c->opts.fsck = true; + set_bit(BCH_FS_fsck_running, &c->flags); + + c->curr_recovery_pass = BCH_RECOVERY_PASS_check_alloc_info; + int ret = bch2_run_online_recovery_passes(c); + + clear_bit(BCH_FS_fsck_running, &c->flags); + bch_err_fn(c, ret); + + c->stdio = NULL; + c->stdio_filter = NULL; + c->opts.fix_errors = old_fix_errors; + + up(&c->online_fsck_mutex); + bch2_ro_ref_put(c); + return ret; +} + +static const struct thread_with_stdio_ops bch2_online_fsck_ops = { + .exit = bch2_fsck_thread_exit, + .fn = bch2_fsck_online_thread_fn, +}; + +long bch2_ioctl_fsck_online(struct bch_fs *c, struct bch_ioctl_fsck_online arg) +{ + struct fsck_thread *thr = NULL; + long ret = 0; + + if (arg.flags) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!bch2_ro_ref_tryget(c)) + return -EROFS; + + if (down_trylock(&c->online_fsck_mutex)) { + bch2_ro_ref_put(c); + return -EAGAIN; + } + + thr = kzalloc(sizeof(*thr), GFP_KERNEL); + if (!thr) { + ret = -ENOMEM; + goto err; + } + + thr->c = c; + thr->opts = bch2_opts_empty(); + + if (arg.opts) { + char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); + + ret = PTR_ERR_OR_ZERO(optstr) ?: + bch2_parse_mount_opts(c, &thr->opts, NULL, optstr); + if (!IS_ERR(optstr)) + kfree(optstr); + + if (ret) + goto err; + } + + ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_online_fsck_ops); +err: + if (ret < 0) { + bch_err_fn(c, ret); + if (thr) + bch2_fsck_thread_exit(&thr->thr); + up(&c->online_fsck_mutex); + bch2_ro_ref_put(c); + } + return ret; +} + +#endif /* NO_BCACHEFS_CHARDEV */ diff --git a/fs/bcachefs/fsck.h b/fs/bcachefs/fsck.h index 1cca31011530..574948278cd4 100644 --- a/fs/bcachefs/fsck.h +++ b/fs/bcachefs/fsck.h @@ -2,6 +2,14 @@ #ifndef _BCACHEFS_FSCK_H #define _BCACHEFS_FSCK_H +#include "str_hash.h" + +int bch2_fsck_update_backpointers(struct btree_trans *, + struct snapshots_seen *, + const struct bch_hash_desc, + struct bch_hash_info *, + struct bkey_i *); + int bch2_check_inodes(struct bch_fs *); int bch2_check_extents(struct bch_fs *); int bch2_check_indirect_extents(struct bch_fs *); @@ -14,4 +22,7 @@ int bch2_check_directory_structure(struct bch_fs *); int bch2_check_nlinks(struct bch_fs *); int bch2_fix_reflink_p(struct bch_fs *); +long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *); +long bch2_ioctl_fsck_online(struct bch_fs *, struct bch_ioctl_fsck_online); + #endif /* _BCACHEFS_FSCK_H */ diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index 039cb7a22244..04ec05206f8c 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -14,6 +14,7 @@ #include "extent_update.h" #include "fs.h" #include "inode.h" +#include "opts.h" #include "str_hash.h" #include "snapshot.h" #include "subvolume.h" @@ -47,10 +48,10 @@ static int inode_decode_field(const u8 *in, const u8 *end, u8 *p; if (in >= end) - return -1; + return -BCH_ERR_inode_unpack_error; if (!*in) - return -1; + return -BCH_ERR_inode_unpack_error; /* * position of highest set bit indicates number of bytes: @@ -60,7 +61,7 @@ static int inode_decode_field(const u8 *in, const u8 *end, bytes = byte_table[shift - 1]; if (in + bytes > end) - return -1; + return -BCH_ERR_inode_unpack_error; p = (u8 *) be + 16 - bytes; memcpy(p, in, bytes); @@ -176,7 +177,7 @@ static noinline int bch2_inode_unpack_v1(struct bkey_s_c_inode inode, return ret; \ \ if (field_bits > sizeof(unpacked->_name) * 8) \ - return -1; \ + return -BCH_ERR_inode_unpack_error; \ \ unpacked->_name = field[1]; \ in += ret; @@ -217,7 +218,7 @@ static int bch2_inode_unpack_v2(struct bch_inode_unpacked *unpacked, \ unpacked->_name = v[0]; \ if (v[1] || v[0] != unpacked->_name) \ - return -1; \ + return -BCH_ERR_inode_unpack_error; \ fieldnr++; BCH_INODE_FIELDS_v2() @@ -268,7 +269,7 @@ static int bch2_inode_unpack_v3(struct bkey_s_c k, \ unpacked->_name = v[0]; \ if (v[1] || v[0] != unpacked->_name) \ - return -1; \ + return -BCH_ERR_inode_unpack_error; \ fieldnr++; BCH_INODE_FIELDS_v3() @@ -428,7 +429,7 @@ struct bkey_i *bch2_inode_to_v3(struct btree_trans *trans, struct bkey_i *k) } static int __bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bch_inode_unpacked unpacked; int ret = 0; @@ -468,7 +469,7 @@ fsck_err: } int bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_inode inode = bkey_s_c_to_inode(k); int ret = 0; @@ -478,13 +479,13 @@ int bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, "invalid str hash type (%llu >= %u)", INODEv1_STR_HASH(inode.v), BCH_STR_HASH_NR); - ret = __bch2_inode_validate(c, k, flags); + ret = __bch2_inode_validate(c, k, from); fsck_err: return ret; } int bch2_inode_v2_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_inode_v2 inode = bkey_s_c_to_inode_v2(k); int ret = 0; @@ -494,13 +495,13 @@ int bch2_inode_v2_validate(struct bch_fs *c, struct bkey_s_c k, "invalid str hash type (%llu >= %u)", INODEv2_STR_HASH(inode.v), BCH_STR_HASH_NR); - ret = __bch2_inode_validate(c, k, flags); + ret = __bch2_inode_validate(c, k, from); fsck_err: return ret; } int bch2_inode_v3_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_inode_v3 inode = bkey_s_c_to_inode_v3(k); int ret = 0; @@ -518,7 +519,7 @@ int bch2_inode_v3_validate(struct bch_fs *c, struct bkey_s_c k, "invalid str hash type (%llu >= %u)", INODEv3_STR_HASH(inode.v), BCH_STR_HASH_NR); - ret = __bch2_inode_validate(c, k, flags); + ret = __bch2_inode_validate(c, k, from); fsck_err: return ret; } @@ -617,7 +618,7 @@ bch2_bkey_get_iter_snapshot_parent(struct btree_trans *trans, struct btree_iter struct bkey_s_c k; int ret = 0; - for_each_btree_key_upto_norestart(trans, *iter, btree, + for_each_btree_key_max_norestart(trans, *iter, btree, bpos_successor(pos), SPOS(pos.inode, pos.offset, U32_MAX), flags|BTREE_ITER_all_snapshots, k, ret) @@ -652,7 +653,7 @@ int __bch2_inode_has_child_snapshots(struct btree_trans *trans, struct bpos pos) struct bkey_s_c k; int ret = 0; - for_each_btree_key_upto_norestart(trans, iter, + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_inodes, POS(0, pos.offset), bpos_predecessor(pos), BTREE_ITER_all_snapshots| BTREE_ITER_with_updates, k, ret) @@ -779,7 +780,7 @@ int bch2_trigger_inode(struct btree_trans *trans, } int bch2_inode_generation_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -798,6 +799,28 @@ void bch2_inode_generation_to_text(struct printbuf *out, struct bch_fs *c, prt_printf(out, "generation: %u", le32_to_cpu(gen.v->bi_generation)); } +int bch2_inode_alloc_cursor_validate(struct bch_fs *c, struct bkey_s_c k, + struct bkey_validate_context from) +{ + int ret = 0; + + bkey_fsck_err_on(k.k->p.inode != LOGGED_OPS_INUM_inode_cursors, + c, inode_alloc_cursor_inode_bad, + "k.p.inode bad"); +fsck_err: + return ret; +} + +void bch2_inode_alloc_cursor_to_text(struct printbuf *out, struct bch_fs *c, + struct bkey_s_c k) +{ + struct bkey_s_c_inode_alloc_cursor i = bkey_s_c_to_inode_alloc_cursor(k); + + prt_printf(out, "idx %llu generation %llu", + le64_to_cpu(i.v->idx), + le64_to_cpu(i.v->gen)); +} + void bch2_inode_init_early(struct bch_fs *c, struct bch_inode_unpacked *inode_u) { @@ -858,6 +881,56 @@ static inline u32 bkey_generation(struct bkey_s_c k) } } +static struct bkey_i_inode_alloc_cursor * +bch2_inode_alloc_cursor_get(struct btree_trans *trans, u64 cpu, u64 *min, u64 *max) +{ + struct bch_fs *c = trans->c; + + u64 cursor_idx = c->opts.inodes_32bit ? 0 : cpu + 1; + + cursor_idx &= ~(~0ULL << c->opts.shard_inode_numbers_bits); + + struct btree_iter iter; + struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, + BTREE_ID_logged_ops, + POS(LOGGED_OPS_INUM_inode_cursors, cursor_idx), + BTREE_ITER_cached); + int ret = bkey_err(k); + if (ret) + return ERR_PTR(ret); + + struct bkey_i_inode_alloc_cursor *cursor = + k.k->type == KEY_TYPE_inode_alloc_cursor + ? bch2_bkey_make_mut_typed(trans, &iter, &k, 0, inode_alloc_cursor) + : bch2_bkey_alloc(trans, &iter, 0, inode_alloc_cursor); + ret = PTR_ERR_OR_ZERO(cursor); + if (ret) + goto err; + + if (c->opts.inodes_32bit) { + *min = BLOCKDEV_INODE_MAX; + *max = INT_MAX; + } else { + cursor->v.bits = c->opts.shard_inode_numbers_bits; + + unsigned bits = 63 - c->opts.shard_inode_numbers_bits; + + *min = max(cpu << bits, (u64) INT_MAX + 1); + *max = (cpu << bits) | ~(ULLONG_MAX << bits); + } + + if (le64_to_cpu(cursor->v.idx) < *min) + cursor->v.idx = cpu_to_le64(*min); + + if (le64_to_cpu(cursor->v.idx) >= *max) { + cursor->v.idx = cpu_to_le64(*min); + le32_add_cpu(&cursor->v.gen, 1); + } +err: + bch2_trans_iter_exit(trans, &iter); + return ret ? ERR_PTR(ret) : cursor; +} + /* * This just finds an empty slot: */ @@ -866,35 +939,20 @@ int bch2_inode_create(struct btree_trans *trans, struct bch_inode_unpacked *inode_u, u32 snapshot, u64 cpu) { - struct bch_fs *c = trans->c; - struct bkey_s_c k; - u64 min, max, start, pos, *hint; - int ret = 0; - unsigned bits = (c->opts.inodes_32bit ? 31 : 63); + u64 min, max; + struct bkey_i_inode_alloc_cursor *cursor = + bch2_inode_alloc_cursor_get(trans, cpu, &min, &max); + int ret = PTR_ERR_OR_ZERO(cursor); + if (ret) + return ret; - if (c->opts.shard_inode_numbers) { - bits -= c->inode_shard_bits; + u64 start = le64_to_cpu(cursor->v.idx); + u64 pos = start; - min = (cpu << bits); - max = (cpu << bits) | ~(ULLONG_MAX << bits); - - min = max_t(u64, min, BLOCKDEV_INODE_MAX); - hint = c->unused_inode_hints + cpu; - } else { - min = BLOCKDEV_INODE_MAX; - max = ~(ULLONG_MAX << bits); - hint = c->unused_inode_hints; - } - - start = READ_ONCE(*hint); - - if (start >= max || start < min) - start = min; - - pos = start; bch2_trans_iter_init(trans, iter, BTREE_ID_inodes, POS(0, pos), BTREE_ITER_all_snapshots| BTREE_ITER_intent); + struct bkey_s_c k; again: while ((k = bch2_btree_iter_peek(iter)).k && !(ret = bkey_err(k)) && @@ -924,6 +982,7 @@ again: /* Retry from start */ pos = start = min; bch2_btree_iter_set_pos(iter, POS(0, pos)); + le32_add_cpu(&cursor->v.gen, 1); goto again; found_slot: bch2_btree_iter_set_pos(iter, SPOS(0, pos, snapshot)); @@ -934,9 +993,9 @@ found_slot: return ret; } - *hint = k.k->p.offset; inode_u->bi_inum = k.k->p.offset; - inode_u->bi_generation = bkey_generation(k); + inode_u->bi_generation = le64_to_cpu(cursor->v.gen); + cursor->v.idx = cpu_to_le64(k.k->p.offset + 1); return 0; } @@ -966,7 +1025,7 @@ static int bch2_inode_delete_keys(struct btree_trans *trans, bch2_btree_iter_set_snapshot(&iter, snapshot); - k = bch2_btree_iter_peek_upto(&iter, end); + k = bch2_btree_iter_peek_max(&iter, end); ret = bkey_err(k); if (ret) goto err; @@ -998,8 +1057,6 @@ int bch2_inode_rm(struct bch_fs *c, subvol_inum inum) { struct btree_trans *trans = bch2_trans_get(c); struct btree_iter iter = { NULL }; - struct bkey_i_inode_generation delete; - struct bch_inode_unpacked inode_u; struct bkey_s_c k; u32 snapshot; int ret; @@ -1039,13 +1096,7 @@ retry: goto err; } - bch2_inode_unpack(k, &inode_u); - - bkey_inode_generation_init(&delete.k_i); - delete.k.p = iter.pos; - delete.v.bi_generation = cpu_to_le32(inode_u.bi_generation + 1); - - ret = bch2_trans_update(trans, &iter, &delete.k_i, 0) ?: + ret = bch2_btree_delete_at(trans, &iter, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); err: @@ -1141,12 +1192,17 @@ struct bch_opts bch2_inode_opts_to_opts(struct bch_inode_unpacked *inode) void bch2_inode_opts_get(struct bch_io_opts *opts, struct bch_fs *c, struct bch_inode_unpacked *inode) { -#define x(_name, _bits) opts->_name = inode_opt_get(c, inode, _name); +#define x(_name, _bits) \ + if ((inode)->bi_##_name) { \ + opts->_name = inode->bi_##_name - 1; \ + opts->_name##_from_inode = true; \ + } else { \ + opts->_name = c->opts._name; \ + } BCH_INODE_OPTS() #undef x - if (opts->nocow) - opts->compression = opts->background_compression = opts->data_checksum = opts->erasure_code = 0; + bch2_io_opts_fixups(opts); } int bch2_inum_opts_get(struct btree_trans *trans, subvol_inum inum, struct bch_io_opts *opts) @@ -1380,7 +1436,8 @@ again: NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ ret = may_delete_deleted_inode(trans, &iter, k.k->p, &need_another_pass); if (ret > 0) { - bch_verbose(c, "deleting unlinked inode %llu:%u", k.k->p.offset, k.k->p.snapshot); + bch_verbose_ratelimited(c, "deleting unlinked inode %llu:%u", + k.k->p.offset, k.k->p.snapshot); ret = bch2_inode_rm_snapshot(trans, k.k->p.offset, k.k->p.snapshot); /* diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h index eab82b5eb897..d2e134528f0e 100644 --- a/fs/bcachefs/inode.h +++ b/fs/bcachefs/inode.h @@ -7,15 +7,14 @@ #include "opts.h" #include "snapshot.h" -enum bch_validate_flags; extern const char * const bch2_inode_opts[]; int bch2_inode_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); int bch2_inode_v2_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); int bch2_inode_v3_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_inode_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int __bch2_inode_has_child_snapshots(struct btree_trans *, struct bpos); @@ -60,7 +59,7 @@ static inline bool bkey_is_inode(const struct bkey *k) } int bch2_inode_generation_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_inode_generation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_inode_generation ((struct bkey_ops) { \ @@ -69,6 +68,16 @@ void bch2_inode_generation_to_text(struct printbuf *, struct bch_fs *, struct bk .min_val_size = 8, \ }) +int bch2_inode_alloc_cursor_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +void bch2_inode_alloc_cursor_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); + +#define bch2_bkey_ops_inode_alloc_cursor ((struct bkey_ops) { \ + .key_validate = bch2_inode_alloc_cursor_validate, \ + .val_to_text = bch2_inode_alloc_cursor_to_text, \ + .min_val_size = 16, \ +}) + #if 0 typedef struct { u64 lo; @@ -220,6 +229,20 @@ static inline u32 bch2_inode_flags(struct bkey_s_c k) } } +static inline unsigned bkey_inode_mode(struct bkey_s_c k) +{ + switch (k.k->type) { + case KEY_TYPE_inode: + return le16_to_cpu(bkey_s_c_to_inode(k).v->bi_mode); + case KEY_TYPE_inode_v2: + return le16_to_cpu(bkey_s_c_to_inode_v2(k).v->bi_mode); + case KEY_TYPE_inode_v3: + return INODEv3_MODE(bkey_s_c_to_inode_v3(k).v); + default: + return 0; + } +} + /* i_nlink: */ static inline unsigned nlink_bias(umode_t mode) @@ -249,7 +272,7 @@ static inline void bch2_inode_nlink_set(struct bch_inode_unpacked *bi, int bch2_inode_nlink_inc(struct bch_inode_unpacked *); void bch2_inode_nlink_dec(struct btree_trans *, struct bch_inode_unpacked *); -static inline bool bch2_inode_should_have_bp(struct bch_inode_unpacked *inode) +static inline bool bch2_inode_should_have_single_bp(struct bch_inode_unpacked *inode) { bool inode_has_bp = inode->bi_dir || inode->bi_dir_offset; @@ -262,6 +285,14 @@ void bch2_inode_opts_get(struct bch_io_opts *, struct bch_fs *, struct bch_inode_unpacked *); int bch2_inum_opts_get(struct btree_trans*, subvol_inum, struct bch_io_opts *); +static inline struct bch_extent_rebalance +bch2_inode_rebalance_opts_get(struct bch_fs *c, struct bch_inode_unpacked *inode) +{ + struct bch_io_opts io_opts; + bch2_inode_opts_get(&io_opts, c, inode); + return io_opts_to_rebalance_opts(&io_opts); +} + int bch2_inode_rm_snapshot(struct btree_trans *, u64, u32); int bch2_delete_dead_inodes(struct bch_fs *); diff --git a/fs/bcachefs/inode_format.h b/fs/bcachefs/inode_format.h index 7928d0c6954f..b99a5bf1a75e 100644 --- a/fs/bcachefs/inode_format.h +++ b/fs/bcachefs/inode_format.h @@ -101,7 +101,9 @@ struct bch_inode_generation { x(bi_dir_offset, 64) \ x(bi_subvol, 32) \ x(bi_parent_subvol, 32) \ - x(bi_nocow, 8) + x(bi_nocow, 8) \ + x(bi_depth, 32) \ + x(bi_inodes_32bit, 8) /* subset of BCH_INODE_FIELDS */ #define BCH_INODE_OPTS() \ @@ -114,7 +116,8 @@ struct bch_inode_generation { x(foreground_target, 16) \ x(background_target, 16) \ x(erasure_code, 16) \ - x(nocow, 8) + x(nocow, 8) \ + x(inodes_32bit, 8) enum inode_opt_id { #define x(name, ...) \ @@ -164,4 +167,12 @@ LE64_BITMASK(INODEv3_FIELDS_START, struct bch_inode_v3, bi_flags, 31, 36); LE64_BITMASK(INODEv3_MODE, struct bch_inode_v3, bi_flags, 36, 52); +struct bch_inode_alloc_cursor { + struct bch_val v; + __u8 bits; + __u8 pad; + __le32 gen; + __le64 idx; +}; + #endif /* _BCACHEFS_INODE_FORMAT_H */ diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c index f283051758d6..5353979117b0 100644 --- a/fs/bcachefs/io_misc.c +++ b/fs/bcachefs/io_misc.c @@ -113,11 +113,13 @@ int bch2_extent_fallocate(struct btree_trans *trans, err: if (!ret && sectors_allocated) bch2_increment_clock(c, sectors_allocated, WRITE); - if (should_print_err(ret)) - bch_err_inum_offset_ratelimited(c, - inum.inum, - iter->pos.offset << 9, - "%s(): error: %s", __func__, bch2_err_str(ret)); + if (should_print_err(ret)) { + struct printbuf buf = PRINTBUF; + bch2_inum_offset_err_msg_trans(trans, &buf, inum, iter->pos.offset << 9); + prt_printf(&buf, "fallocate error: %s", bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + } err_noprint: bch2_open_buckets_put(c, &open_buckets); bch2_disk_reservation_put(c, &disk_res); @@ -164,9 +166,9 @@ int bch2_fpunch_at(struct btree_trans *trans, struct btree_iter *iter, bch2_btree_iter_set_snapshot(iter, snapshot); /* - * peek_upto() doesn't have ideal semantics for extents: + * peek_max() doesn't have ideal semantics for extents: */ - k = bch2_btree_iter_peek_upto(iter, end_pos); + k = bch2_btree_iter_peek_max(iter, end_pos); if (!k.k) break; @@ -426,8 +428,8 @@ case LOGGED_OP_FINSERT_shift_extents: bch2_btree_iter_set_pos(&iter, SPOS(inum.inum, pos, snapshot)); k = insert - ? bch2_btree_iter_peek_prev(&iter) - : bch2_btree_iter_peek_upto(&iter, POS(inum.inum, U64_MAX)); + ? bch2_btree_iter_peek_prev_min(&iter, POS(inum.inum, 0)) + : bch2_btree_iter_peek_max(&iter, POS(inum.inum, U64_MAX)); if ((ret = bkey_err(k))) goto btree_err; @@ -461,7 +463,7 @@ case LOGGED_OP_FINSERT_shift_extents: op->v.pos = cpu_to_le64(insert ? bkey_start_offset(&delete.k) : delete.k.p.offset); - ret = bch2_bkey_set_needs_rebalance(c, copy, &opts) ?: + ret = bch2_bkey_set_needs_rebalance(c, &opts, copy) ?: bch2_btree_insert_trans(trans, BTREE_ID_extents, &delete, 0) ?: bch2_btree_insert_trans(trans, BTREE_ID_extents, copy, 0) ?: bch2_logged_op_update(trans, &op->k_i) ?: diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index b3b934a87c6d..8c7b2d3d779d 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -21,6 +21,7 @@ #include "io_read.h" #include "io_misc.h" #include "io_write.h" +#include "reflink.h" #include "subvolume.h" #include "trace.h" @@ -90,13 +91,18 @@ static const struct rhashtable_params bch_promote_params = { .automatic_shrinking = true, }; +static inline bool have_io_error(struct bch_io_failures *failed) +{ + return failed && failed->nr; +} + static inline int should_promote(struct bch_fs *c, struct bkey_s_c k, struct bpos pos, struct bch_io_opts opts, unsigned flags, struct bch_io_failures *failed) { - if (!failed) { + if (!have_io_error(failed)) { BUG_ON(!opts.promote_target); if (!(flags & BCH_READ_MAY_PROMOTE)) @@ -223,7 +229,7 @@ static struct promote_op *__promote_alloc(struct btree_trans *trans, struct data_update_opts update_opts = {}; - if (!failed) { + if (!have_io_error(failed)) { update_opts.target = opts.promote_target; update_opts.extra_replicas = 1; update_opts.write_flags = BCH_WRITE_ALLOC_NOWAIT|BCH_WRITE_CACHED; @@ -231,11 +237,11 @@ static struct promote_op *__promote_alloc(struct btree_trans *trans, update_opts.target = opts.foreground_target; struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - unsigned i = 0; + unsigned ptr_bit = 1; bkey_for_each_ptr(ptrs, ptr) { if (bch2_dev_io_failures(failed, ptr->dev)) - update_opts.rewrite_ptrs |= BIT(i); - i++; + update_opts.rewrite_ptrs |= ptr_bit; + ptr_bit <<= 1; } } @@ -285,7 +291,7 @@ static struct promote_op *promote_alloc(struct btree_trans *trans, * if failed != NULL we're not actually doing a promote, we're * recovering from an io/checksum error */ - bool promote_full = (failed || + bool promote_full = (have_io_error(failed) || *read_full || READ_ONCE(c->opts.promote_whole_extents)); /* data might have to be decompressed in the write path: */ @@ -321,6 +327,20 @@ nopromote: /* Read */ +static int bch2_read_err_msg_trans(struct btree_trans *trans, struct printbuf *out, + struct bch_read_bio *rbio, struct bpos read_pos) +{ + return bch2_inum_offset_err_msg_trans(trans, out, + (subvol_inum) { rbio->subvol, read_pos.inode }, + read_pos.offset << 9); +} + +static void bch2_read_err_msg(struct bch_fs *c, struct printbuf *out, + struct bch_read_bio *rbio, struct bpos read_pos) +{ + bch2_trans_run(c, bch2_read_err_msg_trans(trans, out, rbio, read_pos)); +} + #define READ_RETRY_AVOID 1 #define READ_RETRY 2 #define READ_ERR 3 @@ -499,6 +519,29 @@ static void bch2_rbio_error(struct bch_read_bio *rbio, int retry, } } +static void bch2_read_io_err(struct work_struct *work) +{ + struct bch_read_bio *rbio = + container_of(work, struct bch_read_bio, work); + struct bio *bio = &rbio->bio; + struct bch_fs *c = rbio->c; + struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; + struct printbuf buf = PRINTBUF; + + bch2_read_err_msg(c, &buf, rbio, rbio->read_pos); + prt_printf(&buf, "data read error: %s", bch2_blk_status_to_str(bio->bi_status)); + + if (ca) { + bch2_io_error(ca, BCH_MEMBER_ERROR_read); + bch_err_ratelimited(ca, "%s", buf.buf); + } else { + bch_err_ratelimited(c, "%s", buf.buf); + } + + printbuf_exit(&buf); + bch2_rbio_error(rbio, READ_RETRY_AVOID, bio->bi_status); +} + static int __bch2_rbio_narrow_crcs(struct btree_trans *trans, struct bch_read_bio *rbio) { @@ -562,6 +605,73 @@ static noinline void bch2_rbio_narrow_crcs(struct bch_read_bio *rbio) __bch2_rbio_narrow_crcs(trans, rbio)); } +static void bch2_read_csum_err(struct work_struct *work) +{ + struct bch_read_bio *rbio = + container_of(work, struct bch_read_bio, work); + struct bch_fs *c = rbio->c; + struct bio *src = &rbio->bio; + struct bch_extent_crc_unpacked crc = rbio->pick.crc; + struct nonce nonce = extent_nonce(rbio->version, crc); + struct bch_csum csum = bch2_checksum_bio(c, crc.csum_type, nonce, src); + struct printbuf buf = PRINTBUF; + + bch2_read_err_msg(c, &buf, rbio, rbio->read_pos); + prt_str(&buf, "data "); + bch2_csum_err_msg(&buf, crc.csum_type, rbio->pick.crc.csum, csum); + + struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; + if (ca) { + bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); + bch_err_ratelimited(ca, "%s", buf.buf); + } else { + bch_err_ratelimited(c, "%s", buf.buf); + } + + bch2_rbio_error(rbio, READ_RETRY_AVOID, BLK_STS_IOERR); + printbuf_exit(&buf); +} + +static void bch2_read_decompress_err(struct work_struct *work) +{ + struct bch_read_bio *rbio = + container_of(work, struct bch_read_bio, work); + struct bch_fs *c = rbio->c; + struct printbuf buf = PRINTBUF; + + bch2_read_err_msg(c, &buf, rbio, rbio->read_pos); + prt_str(&buf, "decompression error"); + + struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; + if (ca) + bch_err_ratelimited(ca, "%s", buf.buf); + else + bch_err_ratelimited(c, "%s", buf.buf); + + bch2_rbio_error(rbio, READ_ERR, BLK_STS_IOERR); + printbuf_exit(&buf); +} + +static void bch2_read_decrypt_err(struct work_struct *work) +{ + struct bch_read_bio *rbio = + container_of(work, struct bch_read_bio, work); + struct bch_fs *c = rbio->c; + struct printbuf buf = PRINTBUF; + + bch2_read_err_msg(c, &buf, rbio, rbio->read_pos); + prt_str(&buf, "decrypt error"); + + struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; + if (ca) + bch_err_ratelimited(ca, "%s", buf.buf); + else + bch_err_ratelimited(c, "%s", buf.buf); + + bch2_rbio_error(rbio, READ_ERR, BLK_STS_IOERR); + printbuf_exit(&buf); +} + /* Inner part that may run in process context */ static void __bch2_read_endio(struct work_struct *work) { @@ -668,33 +778,13 @@ csum_err: goto out; } - struct printbuf buf = PRINTBUF; - buf.atomic++; - prt_str(&buf, "data "); - bch2_csum_err_msg(&buf, crc.csum_type, rbio->pick.crc.csum, csum); - - struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; - if (ca) { - bch_err_inum_offset_ratelimited(ca, - rbio->read_pos.inode, - rbio->read_pos.offset << 9, - "data %s", buf.buf); - bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); - } - printbuf_exit(&buf); - bch2_rbio_error(rbio, READ_RETRY_AVOID, BLK_STS_IOERR); + bch2_rbio_punt(rbio, bch2_read_csum_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq); goto out; decompression_err: - bch_err_inum_offset_ratelimited(c, rbio->read_pos.inode, - rbio->read_pos.offset << 9, - "decompression error"); - bch2_rbio_error(rbio, READ_ERR, BLK_STS_IOERR); + bch2_rbio_punt(rbio, bch2_read_decompress_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq); goto out; decrypt_err: - bch_err_inum_offset_ratelimited(c, rbio->read_pos.inode, - rbio->read_pos.offset << 9, - "decrypt error"); - bch2_rbio_error(rbio, READ_ERR, BLK_STS_IOERR); + bch2_rbio_punt(rbio, bch2_read_decrypt_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq); goto out; } @@ -715,16 +805,8 @@ static void bch2_read_endio(struct bio *bio) if (!rbio->split) rbio->bio.bi_end_io = rbio->end_io; - if (bio->bi_status) { - if (ca) { - bch_err_inum_offset_ratelimited(ca, - rbio->read_pos.inode, - rbio->read_pos.offset, - "data read error: %s", - bch2_blk_status_to_str(bio->bi_status)); - bch2_io_error(ca, BCH_MEMBER_ERROR_read); - } - bch2_rbio_error(rbio, READ_RETRY_AVOID, bio->bi_status); + if (unlikely(bio->bi_status)) { + bch2_rbio_punt(rbio, bch2_read_io_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq); return; } @@ -750,45 +832,6 @@ static void bch2_read_endio(struct bio *bio) bch2_rbio_punt(rbio, __bch2_read_endio, context, wq); } -int __bch2_read_indirect_extent(struct btree_trans *trans, - unsigned *offset_into_extent, - struct bkey_buf *orig_k) -{ - struct btree_iter iter; - struct bkey_s_c k; - u64 reflink_offset; - int ret; - - reflink_offset = le64_to_cpu(bkey_i_to_reflink_p(orig_k->k)->v.idx) + - *offset_into_extent; - - k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_reflink, - POS(0, reflink_offset), 0); - ret = bkey_err(k); - if (ret) - goto err; - - if (k.k->type != KEY_TYPE_reflink_v && - k.k->type != KEY_TYPE_indirect_inline_data) { - bch_err_inum_offset_ratelimited(trans->c, - orig_k->k->k.p.inode, - orig_k->k->k.p.offset << 9, - "%llu len %u points to nonexistent indirect extent %llu", - orig_k->k->k.p.offset, - orig_k->k->k.size, - reflink_offset); - bch2_inconsistent_error(trans->c); - ret = -BCH_ERR_missing_indirect_extent; - goto err; - } - - *offset_into_extent = iter.pos.offset - bkey_start_offset(k.k); - bch2_bkey_buf_reassemble(orig_k, trans->c, k); -err: - bch2_trans_iter_exit(trans, &iter); - return ret; -} - static noinline void read_from_stale_dirty_pointer(struct btree_trans *trans, struct bch_dev *ca, struct bkey_s_c k, @@ -868,15 +911,24 @@ retry_pick: if (!pick_ret) goto hole; - if (pick_ret < 0) { + if (unlikely(pick_ret < 0)) { struct printbuf buf = PRINTBUF; + bch2_read_err_msg_trans(trans, &buf, orig, read_pos); + prt_printf(&buf, "no device to read from: %s\n ", bch2_err_str(pick_ret)); bch2_bkey_val_to_text(&buf, c, k); - bch_err_inum_offset_ratelimited(c, - read_pos.inode, read_pos.offset << 9, - "no device to read from: %s\n %s", - bch2_err_str(pick_ret), - buf.buf); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + goto err; + } + + if (unlikely(bch2_csum_type_is_encryption(pick.crc.csum_type)) && !c->chacha20) { + struct printbuf buf = PRINTBUF; + bch2_read_err_msg_trans(trans, &buf, orig, read_pos); + prt_printf(&buf, "attempting to read encrypted data without encryption key\n "); + bch2_bkey_val_to_text(&buf, c, k); + + bch_err_ratelimited(c, "%s", buf.buf); printbuf_exit(&buf); goto err; } @@ -942,7 +994,7 @@ retry_pick: bounce = true; } - if (orig->opts.promote_target)// || failed) + if (orig->opts.promote_target || have_io_error(failed)) promote = promote_alloc(trans, iter, k, &pick, orig->opts, flags, &rbio, &bounce, &read_full, failed); @@ -1062,11 +1114,15 @@ get_bio: } if (!rbio->pick.idx) { - if (!rbio->have_ioref) { - bch_err_inum_offset_ratelimited(c, - read_pos.inode, - read_pos.offset << 9, - "no device to read from"); + if (unlikely(!rbio->have_ioref)) { + struct printbuf buf = PRINTBUF; + bch2_read_err_msg_trans(trans, &buf, rbio, read_pos); + prt_printf(&buf, "no device to read from:\n "); + bch2_bkey_val_to_text(&buf, c, k); + + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + bch2_rbio_error(rbio, READ_RETRY_AVOID, BLK_STS_IOERR); goto out; } @@ -1164,7 +1220,6 @@ void __bch2_read(struct bch_fs *c, struct bch_read_bio *rbio, BTREE_ITER_slots); while (1) { - unsigned bytes, sectors, offset_into_extent; enum btree_id data_btree = BTREE_ID_extents; bch2_trans_begin(trans); @@ -1184,9 +1239,9 @@ void __bch2_read(struct bch_fs *c, struct bch_read_bio *rbio, if (ret) goto err; - offset_into_extent = iter.pos.offset - + s64 offset_into_extent = iter.pos.offset - bkey_start_offset(k.k); - sectors = k.k->size - offset_into_extent; + unsigned sectors = k.k->size - offset_into_extent; bch2_bkey_buf_reassemble(&sk, c, k); @@ -1201,9 +1256,9 @@ void __bch2_read(struct bch_fs *c, struct bch_read_bio *rbio, * With indirect extents, the amount of data to read is the min * of the original extent and the indirect extent: */ - sectors = min(sectors, k.k->size - offset_into_extent); + sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent); - bytes = min(sectors, bvec_iter_sectors(bvec_iter)) << 9; + unsigned bytes = min(sectors, bvec_iter_sectors(bvec_iter)) << 9; swap(bvec_iter.bi_size, bytes); if (bvec_iter.bi_size == bytes) @@ -1229,16 +1284,20 @@ err: } bch2_trans_iter_exit(trans, &iter); - bch2_trans_put(trans); - bch2_bkey_buf_exit(&sk, c); if (ret) { - bch_err_inum_offset_ratelimited(c, inum.inum, - bvec_iter.bi_sector << 9, - "read error %i from btree lookup", ret); + struct printbuf buf = PRINTBUF; + bch2_inum_offset_err_msg_trans(trans, &buf, inum, bvec_iter.bi_sector << 9); + prt_printf(&buf, "read error %i from btree lookup", ret); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + rbio->bio.bi_status = BLK_STS_IOERR; bch2_rbio_done(rbio); } + + bch2_trans_put(trans); + bch2_bkey_buf_exit(&sk, c); } void bch2_fs_io_read_exit(struct bch_fs *c) diff --git a/fs/bcachefs/io_read.h b/fs/bcachefs/io_read.h index d9c18bb7d403..a82e8a94ccb6 100644 --- a/fs/bcachefs/io_read.h +++ b/fs/bcachefs/io_read.h @@ -3,6 +3,7 @@ #define _BCACHEFS_IO_READ_H #include "bkey_buf.h" +#include "reflink.h" struct bch_read_bio { struct bch_fs *c; @@ -79,19 +80,32 @@ struct bch_devs_mask; struct cache_promote_op; struct extent_ptr_decoded; -int __bch2_read_indirect_extent(struct btree_trans *, unsigned *, - struct bkey_buf *); - static inline int bch2_read_indirect_extent(struct btree_trans *trans, enum btree_id *data_btree, - unsigned *offset_into_extent, - struct bkey_buf *k) + s64 *offset_into_extent, + struct bkey_buf *extent) { - if (k->k->k.type != KEY_TYPE_reflink_p) + if (extent->k->k.type != KEY_TYPE_reflink_p) return 0; *data_btree = BTREE_ID_reflink; - return __bch2_read_indirect_extent(trans, offset_into_extent, k); + struct btree_iter iter; + struct bkey_s_c k = bch2_lookup_indirect_extent(trans, &iter, + offset_into_extent, + bkey_i_to_s_c_reflink_p(extent->k), + true, 0); + int ret = bkey_err(k); + if (ret) + return ret; + + if (bkey_deleted(k.k)) { + bch2_trans_iter_exit(trans, &iter); + return -BCH_ERR_missing_indirect_extent; + } + + bch2_bkey_buf_reassemble(extent, trans->c, k); + bch2_trans_iter_exit(trans, &iter); + return 0; } enum bch_read_flags { diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index 96720adcfee0..dd508d93e9fc 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -164,7 +164,7 @@ int bch2_sum_sector_overwrites(struct btree_trans *trans, bch2_trans_copy_iter(&iter, extent_iter); - for_each_btree_key_upto_continue_norestart(iter, + for_each_btree_key_max_continue_norestart(iter, new->k.p, BTREE_ITER_slots, old, ret) { s64 sectors = min(new->k.p.offset, old.k->p.offset) - max(bkey_start_offset(&new->k), @@ -216,6 +216,7 @@ static inline int bch2_extent_update_i_size_sectors(struct btree_trans *trans, SPOS(0, extent_iter->pos.inode, extent_iter->snapshot), + BTREE_ITER_intent| BTREE_ITER_cached); int ret = bkey_err(k); if (unlikely(ret)) @@ -369,7 +370,7 @@ static int bch2_write_index_default(struct bch_write_op *op) bkey_start_pos(&sk.k->k), BTREE_ITER_slots|BTREE_ITER_intent); - ret = bch2_bkey_set_needs_rebalance(c, sk.k, &op->opts) ?: + ret = bch2_bkey_set_needs_rebalance(c, &op->opts, sk.k) ?: bch2_extent_update(trans, inum, &iter, sk.k, &op->res, op->new_i_size, &op->i_sectors_delta, @@ -395,6 +396,21 @@ static int bch2_write_index_default(struct bch_write_op *op) /* Writes */ +static void __bch2_write_op_error(struct printbuf *out, struct bch_write_op *op, + u64 offset) +{ + bch2_inum_offset_err_msg(op->c, out, + (subvol_inum) { op->subvol, op->pos.inode, }, + offset << 9); + prt_printf(out, "write error%s: ", + op->flags & BCH_WRITE_MOVE ? "(internal move)" : ""); +} + +void bch2_write_op_error(struct printbuf *out, struct bch_write_op *op) +{ + __bch2_write_op_error(out, op, op->pos.offset); +} + void bch2_submit_wbio_replicas(struct bch_write_bio *wbio, struct bch_fs *c, enum bch_data_type type, const struct bkey_i *k, @@ -531,14 +547,14 @@ static void __bch2_write_index(struct bch_write_op *op) op->written += sectors_start - keylist_sectors(keys); - if (ret && !bch2_err_matches(ret, EROFS)) { + if (unlikely(ret && !bch2_err_matches(ret, EROFS))) { struct bkey_i *insert = bch2_keylist_front(&op->insert_keys); - bch_err_inum_offset_ratelimited(c, - insert->k.p.inode, insert->k.p.offset << 9, - "%s write error while doing btree update: %s", - op->flags & BCH_WRITE_MOVE ? "move" : "user", - bch2_err_str(ret)); + struct printbuf buf = PRINTBUF; + __bch2_write_op_error(&buf, op, bkey_start_offset(&insert->k)); + prt_printf(&buf, "btree update error: %s", bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); } if (ret) @@ -621,9 +637,7 @@ void bch2_write_point_do_index_updates(struct work_struct *work) while (1) { spin_lock_irq(&wp->writes_lock); - op = list_first_entry_or_null(&wp->writes, struct bch_write_op, wp_list); - if (op) - list_del(&op->wp_list); + op = list_pop_entry(&wp->writes, struct bch_write_op, wp_list); wp_update_state(wp, op != NULL); spin_unlock_irq(&wp->writes_lock); @@ -859,7 +873,7 @@ static enum prep_encoded_ret { if (bch2_crc_cmp(op->crc.csum, csum) && !c->opts.no_data_io) return PREP_ENCODED_CHECKSUM_ERR; - if (bch2_bio_uncompress_inplace(c, bio, &op->crc)) + if (bch2_bio_uncompress_inplace(op, bio)) return PREP_ENCODED_ERR; } @@ -1080,11 +1094,14 @@ do_write: *_dst = dst; return more; csum_err: - bch_err_inum_offset_ratelimited(c, - op->pos.inode, - op->pos.offset << 9, - "%s write error: error verifying existing checksum while rewriting existing data (memory corruption?)", - op->flags & BCH_WRITE_MOVE ? "move" : "user"); + { + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "error verifying existing checksum while rewriting existing data (memory corruption?)"); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + } + ret = -EIO; err: if (to_wbio(dst)->bounce) @@ -1165,7 +1182,7 @@ static void bch2_nocow_write_convert_unwritten(struct bch_write_op *op) struct btree_trans *trans = bch2_trans_get(c); for_each_keylist_key(&op->insert_keys, orig) { - int ret = for_each_btree_key_upto_commit(trans, iter, BTREE_ID_extents, + int ret = for_each_btree_key_max_commit(trans, iter, BTREE_ID_extents, bkey_start_pos(&orig->k), orig->k.p, BTREE_ITER_intent, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ @@ -1175,11 +1192,11 @@ static void bch2_nocow_write_convert_unwritten(struct bch_write_op *op) if (ret && !bch2_err_matches(ret, EROFS)) { struct bkey_i *insert = bch2_keylist_front(&op->insert_keys); - bch_err_inum_offset_ratelimited(c, - insert->k.p.inode, insert->k.p.offset << 9, - "%s write error while doing btree update: %s", - op->flags & BCH_WRITE_MOVE ? "move" : "user", - bch2_err_str(ret)); + struct printbuf buf = PRINTBUF; + __bch2_write_op_error(&buf, op, bkey_start_offset(&insert->k)); + prt_printf(&buf, "btree update error: %s", bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); } if (ret) { @@ -1339,17 +1356,19 @@ err: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) goto retry; + bch2_trans_put(trans); + darray_exit(&buckets); + if (ret) { - bch_err_inum_offset_ratelimited(c, - op->pos.inode, op->pos.offset << 9, - "%s: btree lookup error %s", __func__, bch2_err_str(ret)); + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "%s(): btree lookup error: %s", __func__, bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); op->error = ret; op->flags |= BCH_WRITE_SUBMITTED; } - bch2_trans_put(trans); - darray_exit(&buckets); - /* fallback to cow write path? */ if (!(op->flags & BCH_WRITE_SUBMITTED)) { closure_sync(&op->cl); @@ -1462,14 +1481,14 @@ err: if (ret <= 0) { op->flags |= BCH_WRITE_SUBMITTED; - if (ret < 0) { - if (!(op->flags & BCH_WRITE_ALLOC_NOWAIT)) - bch_err_inum_offset_ratelimited(c, - op->pos.inode, - op->pos.offset << 9, - "%s(): %s error: %s", __func__, - op->flags & BCH_WRITE_MOVE ? "move" : "user", - bch2_err_str(ret)); + if (unlikely(ret < 0)) { + if (!(op->flags & BCH_WRITE_ALLOC_NOWAIT)) { + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "%s(): %s", __func__, bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + } op->error = ret; break; } @@ -1595,12 +1614,11 @@ CLOSURE_CALLBACK(bch2_write) bch2_keylist_init(&op->insert_keys, op->inline_keys); wbio_init(bio)->put_bio = false; - if (bio->bi_iter.bi_size & (c->opts.block_size - 1)) { - bch_err_inum_offset_ratelimited(c, - op->pos.inode, - op->pos.offset << 9, - "%s write error: misaligned write", - op->flags & BCH_WRITE_MOVE ? "move" : "user"); + if (unlikely(bio->bi_iter.bi_size & (c->opts.block_size - 1))) { + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "misaligned write"); + printbuf_exit(&buf); op->error = -EIO; goto err; } diff --git a/fs/bcachefs/io_write.h b/fs/bcachefs/io_write.h index 5400ce94ee57..b4626013abc8 100644 --- a/fs/bcachefs/io_write.h +++ b/fs/bcachefs/io_write.h @@ -20,6 +20,8 @@ static inline void bch2_latency_acct(struct bch_dev *ca, u64 submit_time, int rw void bch2_submit_wbio_replicas(struct bch_write_bio *, struct bch_fs *, enum bch_data_type, const struct bkey_i *, bool); +void bch2_write_op_error(struct printbuf *out, struct bch_write_op *op); + #define BCH_WRITE_FLAGS() \ x(ALLOC_NOWAIT) \ x(CACHED) \ diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index 2dc0d60c1745..cb2c3722f674 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -113,11 +113,10 @@ journal_seq_to_buf(struct journal *j, u64 seq) static void journal_pin_list_init(struct journal_entry_pin_list *p, int count) { - unsigned i; - - for (i = 0; i < ARRAY_SIZE(p->list); i++) - INIT_LIST_HEAD(&p->list[i]); - INIT_LIST_HEAD(&p->flushed); + for (unsigned i = 0; i < ARRAY_SIZE(p->unflushed); i++) + INIT_LIST_HEAD(&p->unflushed[i]); + for (unsigned i = 0; i < ARRAY_SIZE(p->flushed); i++) + INIT_LIST_HEAD(&p->flushed[i]); atomic_set(&p->count, count); p->devs.nr = 0; } @@ -217,6 +216,12 @@ void bch2_journal_buf_put_final(struct journal *j, u64 seq) if (__bch2_journal_pin_put(j, seq)) bch2_journal_reclaim_fast(j); bch2_journal_do_writes(j); + + /* + * for __bch2_next_write_buffer_flush_journal_buf(), when quiescing an + * open journal entry + */ + wake_up(&j->wait); } /* @@ -251,6 +256,9 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val, bool t if (!__journal_entry_is_open(old)) return; + if (old.cur_entry_offset == JOURNAL_ENTRY_BLOCKED_VAL) + old.cur_entry_offset = j->cur_entry_offset_if_blocked; + /* Close out old buffer: */ buf->data->u64s = cpu_to_le32(old.cur_entry_offset); @@ -373,6 +381,10 @@ static int journal_entry_open(struct journal *j) if (nr_unwritten_journal_entries(j) == ARRAY_SIZE(j->buf)) return JOURNAL_ERR_max_in_flight; + if (bch2_fs_fatal_err_on(journal_cur_seq(j) >= JOURNAL_SEQ_MAX, + c, "cannot start: journal seq overflow")) + return JOURNAL_ERR_insufficient_devices; /* -EROFS */ + BUG_ON(!j->cur_entry_sectors); buf->expires = @@ -588,6 +600,16 @@ out: : -BCH_ERR_journal_res_get_blocked; } +static unsigned max_dev_latency(struct bch_fs *c) +{ + u64 nsecs = 0; + + for_each_rw_member(c, ca) + nsecs = max(nsecs, ca->io_latency[WRITE].stats.max_duration); + + return nsecs_to_jiffies(nsecs); +} + /* * Essentially the entry function to the journaling code. When bcachefs is doing * a btree insert, it calls this function to get the current journal write. @@ -599,17 +621,31 @@ out: * btree node write locks. */ int bch2_journal_res_get_slowpath(struct journal *j, struct journal_res *res, - unsigned flags) + unsigned flags, + struct btree_trans *trans) { int ret; if (closure_wait_event_timeout(&j->async_wait, (ret = __journal_res_get(j, res, flags)) != -BCH_ERR_journal_res_get_blocked || (flags & JOURNAL_RES_GET_NONBLOCK), - HZ * 10)) + HZ)) return ret; + if (trans) + bch2_trans_unlock_long(trans); + struct bch_fs *c = container_of(j, struct bch_fs, journal); + int remaining_wait = max(max_dev_latency(c) * 2, HZ * 10); + + remaining_wait = max(0, remaining_wait - HZ); + + if (closure_wait_event_timeout(&j->async_wait, + (ret = __journal_res_get(j, res, flags)) != -BCH_ERR_journal_res_get_blocked || + (flags & JOURNAL_RES_GET_NONBLOCK), + remaining_wait)) + return ret; + struct printbuf buf = PRINTBUF; bch2_journal_debug_to_text(&buf, j); bch_err(c, "Journal stuck? Waited for 10 seconds...\n%s", @@ -664,7 +700,7 @@ out: * @seq: seq to flush * @parent: closure object to wait with * Returns: 1 if @seq has already been flushed, 0 if @seq is being flushed, - * -EIO if @seq will never be flushed + * -BCH_ERR_journal_flush_err if @seq will never be flushed * * Like bch2_journal_wait_on_seq, except that it triggers a write immediately if * necessary @@ -687,7 +723,7 @@ int bch2_journal_flush_seq_async(struct journal *j, u64 seq, /* Recheck under lock: */ if (j->err_seq && seq >= j->err_seq) { - ret = -EIO; + ret = -BCH_ERR_journal_flush_err; goto out; } @@ -714,7 +750,7 @@ recheck_need_open: * livelock: */ sched_annotate_sleep(); - ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0); + ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0, NULL); if (ret) return ret; @@ -794,10 +830,11 @@ int bch2_journal_flush(struct journal *j) } /* - * bch2_journal_noflush_seq - tell the journal not to issue any flushes before + * bch2_journal_noflush_seq - ask the journal not to issue any flushes in the + * range [start, end) * @seq */ -bool bch2_journal_noflush_seq(struct journal *j, u64 seq) +bool bch2_journal_noflush_seq(struct journal *j, u64 start, u64 end) { struct bch_fs *c = container_of(j, struct bch_fs, journal); u64 unwritten_seq; @@ -806,15 +843,15 @@ bool bch2_journal_noflush_seq(struct journal *j, u64 seq) if (!(c->sb.features & (1ULL << BCH_FEATURE_journal_no_flush))) return false; - if (seq <= c->journal.flushed_seq_ondisk) + if (c->journal.flushed_seq_ondisk >= start) return false; spin_lock(&j->lock); - if (seq <= c->journal.flushed_seq_ondisk) + if (c->journal.flushed_seq_ondisk >= start) goto out; for (unwritten_seq = journal_last_unwritten_seq(j); - unwritten_seq < seq; + unwritten_seq < end; unwritten_seq++) { struct journal_buf *buf = journal_seq_to_buf(j, unwritten_seq); @@ -831,19 +868,14 @@ out: return ret; } -int bch2_journal_meta(struct journal *j) +static int __bch2_journal_meta(struct journal *j) { - struct journal_buf *buf; - struct journal_res res; - int ret; - - memset(&res, 0, sizeof(res)); - - ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0); + struct journal_res res = {}; + int ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0, NULL); if (ret) return ret; - buf = j->buf + (res.seq & JOURNAL_BUF_MASK); + struct journal_buf *buf = j->buf + (res.seq & JOURNAL_BUF_MASK); buf->must_flush = true; if (!buf->flush_time) { @@ -856,27 +888,70 @@ int bch2_journal_meta(struct journal *j) return bch2_journal_flush_seq(j, res.seq, TASK_UNINTERRUPTIBLE); } +int bch2_journal_meta(struct journal *j) +{ + struct bch_fs *c = container_of(j, struct bch_fs, journal); + + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_journal)) + return -EROFS; + + int ret = __bch2_journal_meta(j); + bch2_write_ref_put(c, BCH_WRITE_REF_journal); + return ret; +} + /* block/unlock the journal: */ void bch2_journal_unblock(struct journal *j) { spin_lock(&j->lock); - j->blocked--; + if (!--j->blocked && + j->cur_entry_offset_if_blocked < JOURNAL_ENTRY_CLOSED_VAL && + j->reservations.cur_entry_offset == JOURNAL_ENTRY_BLOCKED_VAL) { + union journal_res_state old, new; + + old.v = atomic64_read(&j->reservations.counter); + do { + new.v = old.v; + new.cur_entry_offset = j->cur_entry_offset_if_blocked; + } while (!atomic64_try_cmpxchg(&j->reservations.counter, &old.v, new.v)); + } spin_unlock(&j->lock); journal_wake(j); } +static void __bch2_journal_block(struct journal *j) +{ + if (!j->blocked++) { + union journal_res_state old, new; + + old.v = atomic64_read(&j->reservations.counter); + do { + j->cur_entry_offset_if_blocked = old.cur_entry_offset; + + if (j->cur_entry_offset_if_blocked >= JOURNAL_ENTRY_CLOSED_VAL) + break; + + new.v = old.v; + new.cur_entry_offset = JOURNAL_ENTRY_BLOCKED_VAL; + } while (!atomic64_try_cmpxchg(&j->reservations.counter, &old.v, new.v)); + + journal_cur_buf(j)->data->u64s = cpu_to_le32(old.cur_entry_offset); + } +} + void bch2_journal_block(struct journal *j) { spin_lock(&j->lock); - j->blocked++; + __bch2_journal_block(j); spin_unlock(&j->lock); journal_quiesce(j); } -static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq) +static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct journal *j, + u64 max_seq, bool *blocked) { struct journal_buf *ret = NULL; @@ -893,13 +968,17 @@ static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct jou struct journal_buf *buf = j->buf + idx; if (buf->need_flush_to_write_buffer) { - if (seq == journal_cur_seq(j)) - __journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true); - union journal_res_state s; s.v = atomic64_read_acquire(&j->reservations.counter); - ret = journal_state_count(s, idx) + unsigned open = seq == journal_cur_seq(j) && __journal_entry_is_open(s); + + if (open && !*blocked) { + __bch2_journal_block(j); + *blocked = true; + } + + ret = journal_state_count(s, idx) > open ? ERR_PTR(-EAGAIN) : buf; break; @@ -912,11 +991,17 @@ static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct jou return ret; } -struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq) +struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, + u64 max_seq, bool *blocked) { struct journal_buf *ret; + *blocked = false; + + wait_event(j->wait, (ret = __bch2_next_write_buffer_flush_journal_buf(j, + max_seq, blocked)) != ERR_PTR(-EAGAIN)); + if (IS_ERR_OR_NULL(ret) && *blocked) + bch2_journal_unblock(j); - wait_event(j->wait, (ret = __bch2_next_write_buffer_flush_journal_buf(j, max_seq)) != ERR_PTR(-EAGAIN)); return ret; } @@ -945,19 +1030,17 @@ static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr, } for (nr_got = 0; nr_got < nr_want; nr_got++) { - if (new_fs) { - bu[nr_got] = bch2_bucket_alloc_new_fs(ca); - if (bu[nr_got] < 0) { - ret = -BCH_ERR_ENOSPC_bucket_alloc; - break; - } - } else { - ob[nr_got] = bch2_bucket_alloc(c, ca, BCH_WATERMARK_normal, - BCH_DATA_journal, cl); - ret = PTR_ERR_OR_ZERO(ob[nr_got]); - if (ret) - break; + enum bch_watermark watermark = new_fs + ? BCH_WATERMARK_btree + : BCH_WATERMARK_normal; + ob[nr_got] = bch2_bucket_alloc(c, ca, watermark, + BCH_DATA_journal, cl); + ret = PTR_ERR_OR_ZERO(ob[nr_got]); + if (ret) + break; + + if (!new_fs) { ret = bch2_trans_run(c, bch2_trans_mark_metadata_bucket(trans, ca, ob[nr_got]->bucket, BCH_DATA_journal, @@ -967,9 +1050,9 @@ static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr, bch_err_msg(c, ret, "marking new journal buckets"); break; } - - bu[nr_got] = ob[nr_got]->bucket; } + + bu[nr_got] = ob[nr_got]->bucket; } if (!nr_got) @@ -1009,8 +1092,7 @@ static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr, if (ret) goto err_unblock; - if (!new_fs) - bch2_write_super(c); + bch2_write_super(c); /* Commit: */ if (c) @@ -1044,9 +1126,8 @@ err_unblock: bu[i], BCH_DATA_free, 0, BTREE_TRIGGER_transactional)); err_free: - if (!new_fs) - for (i = 0; i < nr_got; i++) - bch2_open_bucket_put(c, ob[i]); + for (i = 0; i < nr_got; i++) + bch2_open_bucket_put(c, ob[i]); kfree(new_bucket_seq); kfree(new_buckets); @@ -1193,7 +1274,7 @@ void bch2_fs_journal_stop(struct journal *j) * Always write a new journal entry, to make sure the clock hands are up * to date (and match the superblock) */ - bch2_journal_meta(j); + __bch2_journal_meta(j); journal_quiesce(j); cancel_delayed_work_sync(&j->write_work); @@ -1217,6 +1298,11 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq) bool had_entries = false; u64 last_seq = cur_seq, nr, seq; + if (cur_seq >= JOURNAL_SEQ_MAX) { + bch_err(c, "cannot start: journal seq overflow"); + return -EINVAL; + } + genradix_for_each_reverse(&c->journal_entries, iter, _i) { i = *_i; @@ -1474,6 +1560,9 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) case JOURNAL_ENTRY_CLOSED_VAL: prt_printf(out, "closed\n"); break; + case JOURNAL_ENTRY_BLOCKED_VAL: + prt_printf(out, "blocked\n"); + break; default: prt_printf(out, "%u/%u\n", s.cur_entry_offset, j->cur_entry_u64s); break; @@ -1499,6 +1588,9 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) printbuf_indent_sub(out, 2); for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) { + if (!ca->mi.durability) + continue; + struct journal_device *ja = &ca->journal; if (!test_bit(ca->dev_idx, c->rw_devs[BCH_DATA_journal].d)) @@ -1508,6 +1600,7 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) continue; prt_printf(out, "dev %u:\n", ca->dev_idx); + prt_printf(out, "durability %u:\n", ca->mi.durability); printbuf_indent_add(out, 2); prt_printf(out, "nr\t%u\n", ja->nr); prt_printf(out, "bucket size\t%u\n", ca->mi.bucket_size); @@ -1519,6 +1612,8 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) printbuf_indent_sub(out, 2); } + prt_printf(out, "replicas want %u need %u\n", c->opts.metadata_replicas, c->opts.metadata_replicas_required); + rcu_read_unlock(); --out->atomic; @@ -1530,54 +1625,3 @@ void bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) __bch2_journal_debug_to_text(out, j); spin_unlock(&j->lock); } - -bool bch2_journal_seq_pins_to_text(struct printbuf *out, struct journal *j, u64 *seq) -{ - struct journal_entry_pin_list *pin_list; - struct journal_entry_pin *pin; - - spin_lock(&j->lock); - if (!test_bit(JOURNAL_running, &j->flags)) { - spin_unlock(&j->lock); - return true; - } - - *seq = max(*seq, j->pin.front); - - if (*seq >= j->pin.back) { - spin_unlock(&j->lock); - return true; - } - - out->atomic++; - - pin_list = journal_seq_pin(j, *seq); - - prt_printf(out, "%llu: count %u\n", *seq, atomic_read(&pin_list->count)); - printbuf_indent_add(out, 2); - - for (unsigned i = 0; i < ARRAY_SIZE(pin_list->list); i++) - list_for_each_entry(pin, &pin_list->list[i], list) - prt_printf(out, "\t%px %ps\n", pin, pin->flush); - - if (!list_empty(&pin_list->flushed)) - prt_printf(out, "flushed:\n"); - - list_for_each_entry(pin, &pin_list->flushed, list) - prt_printf(out, "\t%px %ps\n", pin, pin->flush); - - printbuf_indent_sub(out, 2); - - --out->atomic; - spin_unlock(&j->lock); - - return false; -} - -void bch2_journal_pins_to_text(struct printbuf *out, struct journal *j) -{ - u64 seq = 0; - - while (!bch2_journal_seq_pins_to_text(out, j, &seq)) - seq++; -} diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h index 2762be6f9814..dccddd5420ad 100644 --- a/fs/bcachefs/journal.h +++ b/fs/bcachefs/journal.h @@ -285,7 +285,8 @@ static inline void bch2_journal_buf_put(struct journal *j, unsigned idx, u64 seq spin_lock(&j->lock); bch2_journal_buf_put_final(j, seq); spin_unlock(&j->lock); - } + } else if (unlikely(s.cur_entry_offset == JOURNAL_ENTRY_BLOCKED_VAL)) + wake_up(&j->wait); } /* @@ -311,7 +312,7 @@ static inline void bch2_journal_res_put(struct journal *j, } int bch2_journal_res_get_slowpath(struct journal *, struct journal_res *, - unsigned); + unsigned, struct btree_trans *); /* First bits for BCH_WATERMARK: */ enum journal_res_flags { @@ -367,7 +368,8 @@ static inline int journal_res_get_fast(struct journal *j, } static inline int bch2_journal_res_get(struct journal *j, struct journal_res *res, - unsigned u64s, unsigned flags) + unsigned u64s, unsigned flags, + struct btree_trans *trans) { int ret; @@ -379,7 +381,7 @@ static inline int bch2_journal_res_get(struct journal *j, struct journal_res *re if (journal_res_get_fast(j, res, flags)) goto out; - ret = bch2_journal_res_get_slowpath(j, res, flags); + ret = bch2_journal_res_get_slowpath(j, res, flags, trans); if (ret) return ret; out: @@ -403,7 +405,7 @@ void bch2_journal_flush_async(struct journal *, struct closure *); int bch2_journal_flush_seq(struct journal *, u64, unsigned); int bch2_journal_flush(struct journal *); -bool bch2_journal_noflush_seq(struct journal *, u64); +bool bch2_journal_noflush_seq(struct journal *, u64, u64); int bch2_journal_meta(struct journal *); void bch2_journal_halt(struct journal *); @@ -411,7 +413,7 @@ void bch2_journal_halt(struct journal *); static inline int bch2_journal_error(struct journal *j) { return j->reservations.cur_entry_offset == JOURNAL_ENTRY_ERROR_VAL - ? -EIO : 0; + ? -BCH_ERR_journal_shutdown : 0; } struct bch_dev; @@ -424,12 +426,10 @@ static inline void bch2_journal_set_replay_done(struct journal *j) void bch2_journal_unblock(struct journal *); void bch2_journal_block(struct journal *); -struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq); +struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *, u64, bool *); void __bch2_journal_debug_to_text(struct printbuf *, struct journal *); void bch2_journal_debug_to_text(struct printbuf *, struct journal *); -void bch2_journal_pins_to_text(struct printbuf *, struct journal *); -bool bch2_journal_seq_pins_to_text(struct printbuf *, struct journal *, u64 *); int bch2_set_nr_journal_buckets(struct bch_fs *, struct bch_dev *, unsigned nr); diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index fb35dd336331..11c39e0c34f4 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -17,6 +17,9 @@ #include "sb-clean.h" #include "trace.h" +#include +#include + void bch2_journal_pos_from_member_info_set(struct bch_fs *c) { lockdep_assert_held(&c->sb_lock); @@ -299,7 +302,7 @@ static void journal_entry_err_msg(struct printbuf *out, journal_entry_err_msg(&_buf, version, jset, entry); \ prt_printf(&_buf, msg, ##__VA_ARGS__); \ \ - switch (flags & BCH_VALIDATE_write) { \ + switch (from.flags & BCH_VALIDATE_write) { \ case READ: \ mustfix_fsck_err(c, _err, "%s", _buf.buf); \ break; \ @@ -325,11 +328,11 @@ static void journal_entry_err_msg(struct printbuf *out, static int journal_validate_key(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, - unsigned level, enum btree_id btree_id, struct bkey_i *k, - unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from, + unsigned version, int big_endian) { + enum bch_validate_flags flags = from.flags; int write = flags & BCH_VALIDATE_write; void *next = vstruct_next(entry); int ret = 0; @@ -364,11 +367,10 @@ static int journal_validate_key(struct bch_fs *c, } if (!write) - bch2_bkey_compat(level, btree_id, version, big_endian, + bch2_bkey_compat(from.level, from.btree, version, big_endian, write, NULL, bkey_to_packed(k)); - ret = bch2_bkey_validate(c, bkey_i_to_s_c(k), - __btree_node_type(level, btree_id), write); + ret = bch2_bkey_validate(c, bkey_i_to_s_c(k), from); if (ret == -BCH_ERR_fsck_delete_bkey) { le16_add_cpu(&entry->u64s, -((u16) k->k.u64s)); memmove(k, bkey_next(k), next - (void *) bkey_next(k)); @@ -379,7 +381,7 @@ static int journal_validate_key(struct bch_fs *c, goto fsck_err; if (write) - bch2_bkey_compat(level, btree_id, version, big_endian, + bch2_bkey_compat(from.level, from.btree, version, big_endian, write, NULL, bkey_to_packed(k)); fsck_err: return ret; @@ -389,16 +391,15 @@ static int journal_entry_btree_keys_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_i *k = entry->start; + from.level = entry->level; + from.btree = entry->btree_id; + while (k != vstruct_last(entry)) { - int ret = journal_validate_key(c, jset, entry, - entry->level, - entry->btree_id, - k, version, big_endian, - flags|BCH_VALIDATE_journal); + int ret = journal_validate_key(c, jset, entry, k, from, version, big_endian); if (ret == FSCK_DELETED_KEY) continue; else if (ret) @@ -421,7 +422,8 @@ static void journal_entry_btree_keys_to_text(struct printbuf *out, struct bch_fs bch2_prt_jset_entry_type(out, entry->type); prt_str(out, ": "); } - prt_printf(out, "btree=%s l=%u ", bch2_btree_id_str(entry->btree_id), entry->level); + bch2_btree_id_level_to_text(out, entry->btree_id, entry->level); + prt_char(out, ' '); bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(k)); first = false; } @@ -431,11 +433,15 @@ static int journal_entry_btree_root_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_i *k = entry->start; int ret = 0; + from.root = true; + from.level = entry->level + 1; + from.btree = entry->btree_id; + if (journal_entry_err_on(!entry->u64s || le16_to_cpu(entry->u64s) != k->k.u64s, c, version, jset, entry, @@ -452,8 +458,7 @@ static int journal_entry_btree_root_validate(struct bch_fs *c, return 0; } - ret = journal_validate_key(c, jset, entry, 1, entry->btree_id, k, - version, big_endian, flags); + ret = journal_validate_key(c, jset, entry, k, from, version, big_endian); if (ret == FSCK_DELETED_KEY) ret = 0; fsck_err: @@ -470,7 +475,7 @@ static int journal_entry_prio_ptrs_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { /* obsolete, don't care: */ return 0; @@ -485,7 +490,7 @@ static int journal_entry_blacklist_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -512,7 +517,7 @@ static int journal_entry_blacklist_v2_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_blacklist_v2 *bl_entry; int ret = 0; @@ -554,7 +559,7 @@ static int journal_entry_usage_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_usage *u = container_of(entry, struct jset_entry_usage, entry); @@ -588,7 +593,7 @@ static int journal_entry_data_usage_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_data_usage *u = container_of(entry, struct jset_entry_data_usage, entry); @@ -632,7 +637,7 @@ static int journal_entry_clock_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_clock *clock = container_of(entry, struct jset_entry_clock, entry); @@ -665,14 +670,14 @@ static void journal_entry_clock_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry_clock *clock = container_of(entry, struct jset_entry_clock, entry); - prt_printf(out, "%s=%llu", clock->rw ? "write" : "read", le64_to_cpu(clock->time)); + prt_printf(out, "%s=%llu", str_write_read(clock->rw), le64_to_cpu(clock->time)); } static int journal_entry_dev_usage_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_dev_usage *u = container_of(entry, struct jset_entry_dev_usage, entry); @@ -729,7 +734,7 @@ static int journal_entry_log_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return 0; } @@ -738,19 +743,19 @@ static void journal_entry_log_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_log *l = container_of(entry, struct jset_entry_log, entry); - unsigned bytes = vstruct_bytes(entry) - offsetof(struct jset_entry_log, d); - prt_printf(out, "%.*s", bytes, l->d); + prt_printf(out, "%.*s", jset_entry_log_msg_bytes(l), l->d); } static int journal_entry_overwrite_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { + from.flags = 0; return journal_entry_btree_keys_validate(c, jset, entry, - version, big_endian, READ); + version, big_endian, from); } static void journal_entry_overwrite_to_text(struct printbuf *out, struct bch_fs *c, @@ -763,10 +768,10 @@ static int journal_entry_write_buffer_keys_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return journal_entry_btree_keys_validate(c, jset, entry, - version, big_endian, READ); + version, big_endian, from); } static void journal_entry_write_buffer_keys_to_text(struct printbuf *out, struct bch_fs *c, @@ -779,7 +784,7 @@ static int journal_entry_datetime_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { unsigned bytes = vstruct_bytes(entry); unsigned expected = 16; @@ -809,7 +814,7 @@ static void journal_entry_datetime_to_text(struct printbuf *out, struct bch_fs * struct jset_entry_ops { int (*validate)(struct bch_fs *, struct jset *, struct jset_entry *, unsigned, int, - enum bch_validate_flags); + struct bkey_validate_context); void (*to_text)(struct printbuf *, struct bch_fs *, struct jset_entry *); }; @@ -827,11 +832,11 @@ int bch2_journal_entry_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return entry->type < BCH_JSET_ENTRY_NR ? bch2_jset_entry_ops[entry->type].validate(c, jset, entry, - version, big_endian, flags) + version, big_endian, from) : 0; } @@ -849,10 +854,18 @@ void bch2_journal_entry_to_text(struct printbuf *out, struct bch_fs *c, static int jset_validate_entries(struct bch_fs *c, struct jset *jset, enum bch_validate_flags flags) { + struct bkey_validate_context from = { + .flags = flags, + .from = BKEY_VALIDATE_journal, + .journal_seq = le64_to_cpu(jset->seq), + }; + unsigned version = le32_to_cpu(jset->version); int ret = 0; vstruct_for_each(jset, entry) { + from.journal_offset = (u64 *) entry - jset->_data; + if (journal_entry_err_on(vstruct_next(entry) > vstruct_last(jset), c, version, jset, entry, journal_entry_past_jset_end, @@ -861,8 +874,8 @@ static int jset_validate_entries(struct bch_fs *c, struct jset *jset, break; } - ret = bch2_journal_entry_validate(c, jset, entry, - version, JSET_BIG_ENDIAN(jset), flags); + ret = bch2_journal_entry_validate(c, jset, entry, version, + JSET_BIG_ENDIAN(jset), from); if (ret) break; } @@ -875,13 +888,17 @@ static int jset_validate(struct bch_fs *c, struct jset *jset, u64 sector, enum bch_validate_flags flags) { - unsigned version; + struct bkey_validate_context from = { + .flags = flags, + .from = BKEY_VALIDATE_journal, + .journal_seq = le64_to_cpu(jset->seq), + }; int ret = 0; if (le64_to_cpu(jset->magic) != jset_magic(c)) return JOURNAL_ENTRY_NONE; - version = le32_to_cpu(jset->version); + unsigned version = le32_to_cpu(jset->version); if (journal_entry_err_on(!bch2_version_compatible(version), c, version, jset, NULL, jset_unsupported_version, @@ -926,15 +943,16 @@ static int jset_validate_early(struct bch_fs *c, unsigned bucket_sectors_left, unsigned sectors_read) { - size_t bytes = vstruct_bytes(jset); - unsigned version; - enum bch_validate_flags flags = BCH_VALIDATE_journal; + struct bkey_validate_context from = { + .from = BKEY_VALIDATE_journal, + .journal_seq = le64_to_cpu(jset->seq), + }; int ret = 0; if (le64_to_cpu(jset->magic) != jset_magic(c)) return JOURNAL_ENTRY_NONE; - version = le32_to_cpu(jset->version); + unsigned version = le32_to_cpu(jset->version); if (journal_entry_err_on(!bch2_version_compatible(version), c, version, jset, NULL, jset_unsupported_version, @@ -947,6 +965,7 @@ static int jset_validate_early(struct bch_fs *c, return -EINVAL; } + size_t bytes = vstruct_bytes(jset); if (bytes > (sectors_read << 9) && sectors_read < bucket_sectors_left) return JOURNAL_ENTRY_REREAD; @@ -1231,8 +1250,6 @@ int bch2_journal_read(struct bch_fs *c, * those entries will be blacklisted: */ genradix_for_each_reverse(&c->journal_entries, radix_iter, _i) { - enum bch_validate_flags flags = BCH_VALIDATE_journal; - i = *_i; if (journal_replay_ignore(i)) @@ -1252,6 +1269,10 @@ int bch2_journal_read(struct bch_fs *c, continue; } + struct bkey_validate_context from = { + .from = BKEY_VALIDATE_journal, + .journal_seq = le64_to_cpu(i->j.seq), + }; if (journal_entry_err_on(le64_to_cpu(i->j.last_seq) > le64_to_cpu(i->j.seq), c, le32_to_cpu(i->j.version), &i->j, NULL, jset_last_seq_newer_than_seq, @@ -1411,27 +1432,50 @@ fsck_err: /* journal write: */ +static void journal_advance_devs_to_next_bucket(struct journal *j, + struct dev_alloc_list *devs, + unsigned sectors, u64 seq) +{ + struct bch_fs *c = container_of(j, struct bch_fs, journal); + + darray_for_each(*devs, i) { + struct bch_dev *ca = rcu_dereference(c->devs[*i]); + if (!ca) + continue; + + struct journal_device *ja = &ca->journal; + + if (sectors > ja->sectors_free && + sectors <= ca->mi.bucket_size && + bch2_journal_dev_buckets_available(j, ja, + journal_space_discarded)) { + ja->cur_idx = (ja->cur_idx + 1) % ja->nr; + ja->sectors_free = ca->mi.bucket_size; + + /* + * ja->bucket_seq[ja->cur_idx] must always have + * something sensible: + */ + ja->bucket_seq[ja->cur_idx] = le64_to_cpu(seq); + } + } +} + static void __journal_write_alloc(struct journal *j, struct journal_buf *w, - struct dev_alloc_list *devs_sorted, + struct dev_alloc_list *devs, unsigned sectors, unsigned *replicas, unsigned replicas_want) { struct bch_fs *c = container_of(j, struct bch_fs, journal); - struct journal_device *ja; - struct bch_dev *ca; - unsigned i; - if (*replicas >= replicas_want) - return; - - for (i = 0; i < devs_sorted->nr; i++) { - ca = rcu_dereference(c->devs[devs_sorted->devs[i]]); + darray_for_each(*devs, i) { + struct bch_dev *ca = rcu_dereference(c->devs[*i]); if (!ca) continue; - ja = &ca->journal; + struct journal_device *ja = &ca->journal; /* * Check that we can use this device, and aren't already using @@ -1477,65 +1521,53 @@ static int journal_write_alloc(struct journal *j, struct journal_buf *w) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct bch_devs_mask devs; - struct journal_device *ja; - struct bch_dev *ca; struct dev_alloc_list devs_sorted; unsigned sectors = vstruct_sectors(w->data, c->block_bits); unsigned target = c->opts.metadata_target ?: c->opts.foreground_target; - unsigned i, replicas = 0, replicas_want = + unsigned replicas = 0, replicas_want = READ_ONCE(c->opts.metadata_replicas); unsigned replicas_need = min_t(unsigned, replicas_want, READ_ONCE(c->opts.metadata_replicas_required)); + bool advance_done = false; rcu_read_lock(); -retry: - devs = target_rw_devs(c, BCH_DATA_journal, target); - devs_sorted = bch2_dev_alloc_list(c, &j->wp.stripe, &devs); - - __journal_write_alloc(j, w, &devs_sorted, - sectors, &replicas, replicas_want); - - if (replicas >= replicas_want) - goto done; - - for (i = 0; i < devs_sorted.nr; i++) { - ca = rcu_dereference(c->devs[devs_sorted.devs[i]]); - if (!ca) - continue; - - ja = &ca->journal; - - if (sectors > ja->sectors_free && - sectors <= ca->mi.bucket_size && - bch2_journal_dev_buckets_available(j, ja, - journal_space_discarded)) { - ja->cur_idx = (ja->cur_idx + 1) % ja->nr; - ja->sectors_free = ca->mi.bucket_size; - - /* - * ja->bucket_seq[ja->cur_idx] must always have - * something sensible: - */ - ja->bucket_seq[ja->cur_idx] = le64_to_cpu(w->data->seq); - } + /* We might run more than once if we have to stop and do discards: */ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(bkey_i_to_s_c(&w->key)); + bkey_for_each_ptr(ptrs, p) { + struct bch_dev *ca = bch2_dev_rcu_noerror(c, p->dev); + if (ca) + replicas += ca->mi.durability; } - __journal_write_alloc(j, w, &devs_sorted, - sectors, &replicas, replicas_want); +retry_target: + devs = target_rw_devs(c, BCH_DATA_journal, target); + devs_sorted = bch2_dev_alloc_list(c, &j->wp.stripe, &devs); +retry_alloc: + __journal_write_alloc(j, w, &devs_sorted, sectors, &replicas, replicas_want); + + if (likely(replicas >= replicas_want)) + goto done; + + if (!advance_done) { + journal_advance_devs_to_next_bucket(j, &devs_sorted, sectors, w->data->seq); + advance_done = true; + goto retry_alloc; + } if (replicas < replicas_want && target) { /* Retry from all devices: */ target = 0; - goto retry; + advance_done = false; + goto retry_target; } done: rcu_read_unlock(); BUG_ON(bkey_val_u64s(&w->key.k) > BCH_REPLICAS_MAX); - return replicas >= replicas_need ? 0 : -EROFS; + return replicas >= replicas_need ? 0 : -BCH_ERR_insufficient_journal_devices; } static void journal_buf_realloc(struct journal *j, struct journal_buf *buf) @@ -1732,6 +1764,7 @@ static CLOSURE_CALLBACK(journal_write_submit) bio->bi_iter.bi_sector = ptr->offset; bio->bi_end_io = journal_write_endio; bio->bi_private = ca; + bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 0); BUG_ON(bio->bi_iter.bi_sector == ca->prev_journal_sector); ca->prev_journal_sector = bio->bi_iter.bi_sector; @@ -2023,19 +2056,21 @@ CLOSURE_CALLBACK(bch2_journal_write) bch2_journal_do_discards(j); } - if (ret) { + if (ret && !bch2_journal_error(j)) { struct printbuf buf = PRINTBUF; buf.atomic++; - prt_printf(&buf, bch2_fmt(c, "Unable to allocate journal write at seq %llu: %s"), + prt_printf(&buf, bch2_fmt(c, "Unable to allocate journal write at seq %llu for %zu sectors: %s"), le64_to_cpu(w->data->seq), + vstruct_sectors(w->data, c->block_bits), bch2_err_str(ret)); __bch2_journal_debug_to_text(&buf, j); spin_unlock(&j->lock); bch2_print_string_as_lines(KERN_ERR, buf.buf); printbuf_exit(&buf); - goto err; } + if (ret) + goto err; /* * write is allocated, no longer need to account for it in diff --git a/fs/bcachefs/journal_io.h b/fs/bcachefs/journal_io.h index 2ca9cde30ea8..12b39fcb4424 100644 --- a/fs/bcachefs/journal_io.h +++ b/fs/bcachefs/journal_io.h @@ -63,7 +63,7 @@ static inline struct jset_entry *__jset_entry_type_next(struct jset *jset, int bch2_journal_entry_validate(struct bch_fs *, struct jset *, struct jset_entry *, unsigned, int, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_journal_entry_to_text(struct printbuf *, struct bch_fs *, struct jset_entry *); diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index ace291f175dd..6a9cefb635d6 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -38,6 +38,9 @@ unsigned bch2_journal_dev_buckets_available(struct journal *j, struct journal_device *ja, enum journal_space_from from) { + if (!ja->nr) + return 0; + unsigned available = (journal_space_from(ja, from) - ja->cur_idx - 1 + ja->nr) % ja->nr; @@ -137,14 +140,18 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne struct bch_fs *c = container_of(j, struct bch_fs, journal); unsigned pos, nr_devs = 0; struct journal_space space, dev_space[BCH_SB_MEMBERS_MAX]; + unsigned min_bucket_size = U32_MAX; BUG_ON(nr_devs_want > ARRAY_SIZE(dev_space)); rcu_read_lock(); for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) { - if (!ca->journal.nr) + if (!ca->journal.nr || + !ca->mi.durability) continue; + min_bucket_size = min(min_bucket_size, ca->mi.bucket_size); + space = journal_dev_space_available(j, ca, from); if (!space.next_entry) continue; @@ -164,7 +171,9 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne * We sorted largest to smallest, and we want the smallest out of the * @nr_devs_want largest devices: */ - return dev_space[nr_devs_want - 1]; + space = dev_space[nr_devs_want - 1]; + space.next_entry = min(space.next_entry, min_bucket_size); + return space; } void bch2_journal_space_available(struct journal *j) @@ -318,8 +327,10 @@ void bch2_journal_reclaim_fast(struct journal *j) popped = true; } - if (popped) + if (popped) { bch2_journal_space_available(j); + __closure_wake_up(&j->reclaim_flush_wait); + } } bool __bch2_journal_pin_put(struct journal *j, u64 seq) @@ -353,6 +364,9 @@ static inline bool __journal_pin_drop(struct journal *j, pin->seq = 0; list_del_init(&pin->list); + if (j->reclaim_flush_wait.list.first) + __closure_wake_up(&j->reclaim_flush_wait); + /* * Unpinning a journal entry may make journal_next_bucket() succeed, if * writing a new last_seq will now make another bucket available: @@ -374,11 +388,11 @@ static enum journal_pin_type journal_pin_type(journal_pin_flush_fn fn) { if (fn == bch2_btree_node_flush0 || fn == bch2_btree_node_flush1) - return JOURNAL_PIN_btree; + return JOURNAL_PIN_TYPE_btree; else if (fn == bch2_btree_key_cache_journal_flush) - return JOURNAL_PIN_key_cache; + return JOURNAL_PIN_TYPE_key_cache; else - return JOURNAL_PIN_other; + return JOURNAL_PIN_TYPE_other; } static inline void bch2_journal_pin_set_locked(struct journal *j, u64 seq, @@ -397,7 +411,12 @@ static inline void bch2_journal_pin_set_locked(struct journal *j, u64 seq, atomic_inc(&pin_list->count); pin->seq = seq; pin->flush = flush_fn; - list_add(&pin->list, &pin_list->list[type]); + + if (list_empty(&pin_list->unflushed[type]) && + j->reclaim_flush_wait.list.first) + __closure_wake_up(&j->reclaim_flush_wait); + + list_add(&pin->list, &pin_list->unflushed[type]); } void bch2_journal_pin_copy(struct journal *j, @@ -490,16 +509,15 @@ journal_get_next_pin(struct journal *j, { struct journal_entry_pin_list *pin_list; struct journal_entry_pin *ret = NULL; - unsigned i; fifo_for_each_entry_ptr(pin_list, &j->pin, *seq) { if (*seq > seq_to_flush && !allowed_above_seq) break; - for (i = 0; i < JOURNAL_PIN_NR; i++) - if ((((1U << i) & allowed_below_seq) && *seq <= seq_to_flush) || - ((1U << i) & allowed_above_seq)) { - ret = list_first_entry_or_null(&pin_list->list[i], + for (unsigned i = 0; i < JOURNAL_PIN_TYPE_NR; i++) + if (((BIT(i) & allowed_below_seq) && *seq <= seq_to_flush) || + (BIT(i) & allowed_above_seq)) { + ret = list_first_entry_or_null(&pin_list->unflushed[i], struct journal_entry_pin, list); if (ret) return ret; @@ -535,8 +553,8 @@ static size_t journal_flush_pins(struct journal *j, } if (min_key_cache) { - allowed_above |= 1U << JOURNAL_PIN_key_cache; - allowed_below |= 1U << JOURNAL_PIN_key_cache; + allowed_above |= BIT(JOURNAL_PIN_TYPE_key_cache); + allowed_below |= BIT(JOURNAL_PIN_TYPE_key_cache); } cond_resched(); @@ -544,7 +562,9 @@ static size_t journal_flush_pins(struct journal *j, j->last_flushed = jiffies; spin_lock(&j->lock); - pin = journal_get_next_pin(j, seq_to_flush, allowed_below, allowed_above, &seq); + pin = journal_get_next_pin(j, seq_to_flush, + allowed_below, + allowed_above, &seq); if (pin) { BUG_ON(j->flush_in_progress); j->flush_in_progress = pin; @@ -567,7 +587,7 @@ static size_t journal_flush_pins(struct journal *j, spin_lock(&j->lock); /* Pin might have been dropped or rearmed: */ if (likely(!err && !j->flush_in_progress_dropped)) - list_move(&pin->list, &journal_seq_pin(j, seq)->flushed); + list_move(&pin->list, &journal_seq_pin(j, seq)->flushed[journal_pin_type(flush_fn)]); j->flush_in_progress = NULL; j->flush_in_progress_dropped = false; spin_unlock(&j->lock); @@ -758,10 +778,12 @@ static int bch2_journal_reclaim_thread(void *arg) journal_empty = fifo_empty(&j->pin); spin_unlock(&j->lock); + long timeout = j->next_reclaim - jiffies; + if (journal_empty) schedule(); - else if (time_after(j->next_reclaim, jiffies)) - schedule_timeout(j->next_reclaim - jiffies); + else if (timeout > 0) + schedule_timeout(timeout); else break; } @@ -805,10 +827,41 @@ int bch2_journal_reclaim_start(struct journal *j) return 0; } +static bool journal_pins_still_flushing(struct journal *j, u64 seq_to_flush, + unsigned types) +{ + struct journal_entry_pin_list *pin_list; + u64 seq; + + spin_lock(&j->lock); + fifo_for_each_entry_ptr(pin_list, &j->pin, seq) { + if (seq > seq_to_flush) + break; + + for (unsigned i = 0; i < JOURNAL_PIN_TYPE_NR; i++) + if ((BIT(i) & types) && + (!list_empty(&pin_list->unflushed[i]) || + !list_empty(&pin_list->flushed[i]))) { + spin_unlock(&j->lock); + return true; + } + } + spin_unlock(&j->lock); + + return false; +} + +static bool journal_flush_pins_or_still_flushing(struct journal *j, u64 seq_to_flush, + unsigned types) +{ + return journal_flush_pins(j, seq_to_flush, types, 0, 0, 0) || + journal_pins_still_flushing(j, seq_to_flush, types); +} + static int journal_flush_done(struct journal *j, u64 seq_to_flush, bool *did_work) { - int ret; + int ret = 0; ret = bch2_journal_error(j); if (ret) @@ -816,12 +869,18 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush, mutex_lock(&j->reclaim_lock); - if (journal_flush_pins(j, seq_to_flush, - (1U << JOURNAL_PIN_key_cache)| - (1U << JOURNAL_PIN_other), 0, 0, 0) || - journal_flush_pins(j, seq_to_flush, - (1U << JOURNAL_PIN_btree), 0, 0, 0)) + if (journal_flush_pins_or_still_flushing(j, seq_to_flush, + BIT(JOURNAL_PIN_TYPE_key_cache)| + BIT(JOURNAL_PIN_TYPE_other))) { *did_work = true; + goto unlock; + } + + if (journal_flush_pins_or_still_flushing(j, seq_to_flush, + BIT(JOURNAL_PIN_TYPE_btree))) { + *did_work = true; + goto unlock; + } if (seq_to_flush > journal_cur_seq(j)) bch2_journal_entry_close(j); @@ -836,6 +895,7 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush, !fifo_used(&j->pin); spin_unlock(&j->lock); +unlock: mutex_unlock(&j->reclaim_lock); return ret; @@ -849,7 +909,7 @@ bool bch2_journal_flush_pins(struct journal *j, u64 seq_to_flush) if (!test_bit(JOURNAL_running, &j->flags)) return false; - closure_wait_event(&j->async_wait, + closure_wait_event(&j->reclaim_flush_wait, journal_flush_done(j, seq_to_flush, &did_work)); return did_work; @@ -915,3 +975,54 @@ err: return ret; } + +bool bch2_journal_seq_pins_to_text(struct printbuf *out, struct journal *j, u64 *seq) +{ + struct journal_entry_pin_list *pin_list; + struct journal_entry_pin *pin; + + spin_lock(&j->lock); + if (!test_bit(JOURNAL_running, &j->flags)) { + spin_unlock(&j->lock); + return true; + } + + *seq = max(*seq, j->pin.front); + + if (*seq >= j->pin.back) { + spin_unlock(&j->lock); + return true; + } + + out->atomic++; + + pin_list = journal_seq_pin(j, *seq); + + prt_printf(out, "%llu: count %u\n", *seq, atomic_read(&pin_list->count)); + printbuf_indent_add(out, 2); + + prt_printf(out, "unflushed:\n"); + for (unsigned i = 0; i < ARRAY_SIZE(pin_list->unflushed); i++) + list_for_each_entry(pin, &pin_list->unflushed[i], list) + prt_printf(out, "\t%px %ps\n", pin, pin->flush); + + prt_printf(out, "flushed:\n"); + for (unsigned i = 0; i < ARRAY_SIZE(pin_list->flushed); i++) + list_for_each_entry(pin, &pin_list->flushed[i], list) + prt_printf(out, "\t%px %ps\n", pin, pin->flush); + + printbuf_indent_sub(out, 2); + + --out->atomic; + spin_unlock(&j->lock); + + return false; +} + +void bch2_journal_pins_to_text(struct printbuf *out, struct journal *j) +{ + u64 seq = 0; + + while (!bch2_journal_seq_pins_to_text(out, j, &seq)) + seq++; +} diff --git a/fs/bcachefs/journal_reclaim.h b/fs/bcachefs/journal_reclaim.h index ec84c3345281..0a73d7134e1c 100644 --- a/fs/bcachefs/journal_reclaim.h +++ b/fs/bcachefs/journal_reclaim.h @@ -78,4 +78,7 @@ static inline bool bch2_journal_flush_all_pins(struct journal *j) int bch2_journal_flush_device_pins(struct journal *, int); +void bch2_journal_pins_to_text(struct printbuf *, struct journal *); +bool bch2_journal_seq_pins_to_text(struct printbuf *, struct journal *, u64 *); + #endif /* _BCACHEFS_JOURNAL_RECLAIM_H */ diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h index 19183fcf7ad7..3ba433a48eb8 100644 --- a/fs/bcachefs/journal_types.h +++ b/fs/bcachefs/journal_types.h @@ -9,6 +9,9 @@ #include "super_types.h" #include "fifo.h" +/* btree write buffer steals 8 bits for its own purposes: */ +#define JOURNAL_SEQ_MAX ((1ULL << 56) - 1) + #define JOURNAL_BUF_BITS 2 #define JOURNAL_BUF_NR (1U << JOURNAL_BUF_BITS) #define JOURNAL_BUF_MASK (JOURNAL_BUF_NR - 1) @@ -50,15 +53,15 @@ struct journal_buf { */ enum journal_pin_type { - JOURNAL_PIN_btree, - JOURNAL_PIN_key_cache, - JOURNAL_PIN_other, - JOURNAL_PIN_NR, + JOURNAL_PIN_TYPE_btree, + JOURNAL_PIN_TYPE_key_cache, + JOURNAL_PIN_TYPE_other, + JOURNAL_PIN_TYPE_NR, }; struct journal_entry_pin_list { - struct list_head list[JOURNAL_PIN_NR]; - struct list_head flushed; + struct list_head unflushed[JOURNAL_PIN_TYPE_NR]; + struct list_head flushed[JOURNAL_PIN_TYPE_NR]; atomic_t count; struct bch_devs_list devs; }; @@ -112,6 +115,7 @@ union journal_res_state { */ #define JOURNAL_ENTRY_OFFSET_MAX ((1U << 20) - 1) +#define JOURNAL_ENTRY_BLOCKED_VAL (JOURNAL_ENTRY_OFFSET_MAX - 2) #define JOURNAL_ENTRY_CLOSED_VAL (JOURNAL_ENTRY_OFFSET_MAX - 1) #define JOURNAL_ENTRY_ERROR_VAL (JOURNAL_ENTRY_OFFSET_MAX) @@ -193,6 +197,7 @@ struct journal { * insufficient devices: */ enum journal_errors cur_entry_error; + unsigned cur_entry_offset_if_blocked; unsigned buf_size_want; /* @@ -221,6 +226,7 @@ struct journal { /* Used when waiting because the journal was full */ wait_queue_head_t wait; struct closure_waitlist async_wait; + struct closure_waitlist reclaim_flush_wait; struct delayed_work write_work; struct workqueue_struct *wq; diff --git a/fs/bcachefs/logged_ops.c b/fs/bcachefs/logged_ops.c index 60e00702d1a4..75f27ec26f85 100644 --- a/fs/bcachefs/logged_ops.c +++ b/fs/bcachefs/logged_ops.c @@ -63,8 +63,10 @@ fsck_err: int bch2_resume_logged_ops(struct bch_fs *c) { int ret = bch2_trans_run(c, - for_each_btree_key(trans, iter, - BTREE_ID_logged_ops, POS_MIN, + for_each_btree_key_max(trans, iter, + BTREE_ID_logged_ops, + POS(LOGGED_OPS_INUM_logged_ops, 0), + POS(LOGGED_OPS_INUM_logged_ops, U64_MAX), BTREE_ITER_prefetch, k, resume_logged_op(trans, &iter, k))); bch_err_fn(c, ret); @@ -74,9 +76,8 @@ int bch2_resume_logged_ops(struct bch_fs *c) static int __bch2_logged_op_start(struct btree_trans *trans, struct bkey_i *k) { struct btree_iter iter; - int ret; - - ret = bch2_bkey_get_empty_slot(trans, &iter, BTREE_ID_logged_ops, POS_MAX); + int ret = bch2_bkey_get_empty_slot(trans, &iter, + BTREE_ID_logged_ops, POS(LOGGED_OPS_INUM_logged_ops, U64_MAX)); if (ret) return ret; diff --git a/fs/bcachefs/logged_ops_format.h b/fs/bcachefs/logged_ops_format.h index 6a4bf7129dba..cfb67c95d4c8 100644 --- a/fs/bcachefs/logged_ops_format.h +++ b/fs/bcachefs/logged_ops_format.h @@ -2,6 +2,11 @@ #ifndef _BCACHEFS_LOGGED_OPS_FORMAT_H #define _BCACHEFS_LOGGED_OPS_FORMAT_H +enum logged_ops_inums { + LOGGED_OPS_INUM_logged_ops, + LOGGED_OPS_INUM_inode_cursors, +}; + struct bch_logged_op_truncate { struct bch_val v; __le32 subvol; diff --git a/fs/bcachefs/lru.c b/fs/bcachefs/lru.c index 10857eccdeaf..ce794d55818f 100644 --- a/fs/bcachefs/lru.c +++ b/fs/bcachefs/lru.c @@ -12,7 +12,7 @@ /* KEY_TYPE_lru is obsolete: */ int bch2_lru_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -192,7 +192,7 @@ int bch2_check_lrus(struct bch_fs *c) int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_lru, POS_MIN, BTREE_ITER_prefetch, k, - NULL, NULL, BCH_TRANS_COMMIT_no_enospc|BCH_TRANS_COMMIT_lazy_rw, + NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_check_lru_key(trans, &iter, k, &last_flushed))); bch2_bkey_buf_exit(&last_flushed, c); diff --git a/fs/bcachefs/lru.h b/fs/bcachefs/lru.h index e6a7d8241bb8..f31a6cf1514c 100644 --- a/fs/bcachefs/lru.h +++ b/fs/bcachefs/lru.h @@ -33,7 +33,7 @@ static inline enum bch_lru_type lru_type(struct bkey_s_c l) return BCH_LRU_read; } -int bch2_lru_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_lru_validate(struct bch_fs *, struct bkey_s_c, struct bkey_validate_context); void bch2_lru_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_lru_pos_to_text(struct printbuf *, struct bpos); diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c index 0ef4a86850bb..160b4374160a 100644 --- a/fs/bcachefs/move.c +++ b/fs/bcachefs/move.c @@ -21,6 +21,8 @@ #include "journal_reclaim.h" #include "keylist.h" #include "move.h" +#include "rebalance.h" +#include "reflink.h" #include "replicas.h" #include "snapshot.h" #include "super-io.h" @@ -196,6 +198,13 @@ void bch2_moving_ctxt_exit(struct moving_context *ctxt) list_del(&ctxt->list); mutex_unlock(&c->moving_context_lock); + /* + * Generally, releasing a transaction within a transaction restart means + * an unhandled transaction restart: but this can happen legitimately + * within the move code, e.g. when bch2_move_ratelimit() tells us to + * exit before we've retried + */ + bch2_trans_begin(ctxt->trans); bch2_trans_put(ctxt->trans); memset(ctxt, 0, sizeof(*ctxt)); } @@ -292,8 +301,8 @@ int bch2_move_extent(struct moving_context *ctxt, io->write_sectors = k.k->size; bio_init(&io->write.op.wbio.bio, NULL, io->bi_inline_vecs, pages, 0); - bio_set_prio(&io->write.op.wbio.bio, - IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); + io->write.op.wbio.bio.bi_ioprio = + IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0); if (bch2_bio_alloc_pages(&io->write.op.wbio.bio, sectors << 9, GFP_KERNEL)) @@ -303,7 +312,7 @@ int bch2_move_extent(struct moving_context *ctxt, io->rbio.opts = io_opts; bio_init(&io->rbio.bio, NULL, io->bi_inline_vecs, pages, 0); io->rbio.bio.bi_vcnt = pages; - bio_set_prio(&io->rbio.bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); + io->rbio.bio.bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0); io->rbio.bio.bi_iter.bi_size = sectors << 9; io->rbio.bio.bi_opf = REQ_OP_READ; @@ -379,34 +388,42 @@ err: return ret; } -struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans, +static struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans, struct per_snapshot_io_opts *io_opts, + struct bpos extent_pos, /* extent_iter, extent_k may be in reflink btree */ + struct btree_iter *extent_iter, struct bkey_s_c extent_k) { struct bch_fs *c = trans->c; u32 restart_count = trans->restart_count; + struct bch_io_opts *opts_ret = &io_opts->fs_io_opts; int ret = 0; - if (io_opts->cur_inum != extent_k.k->p.inode) { + if (extent_k.k->type == KEY_TYPE_reflink_v) + goto out; + + if (io_opts->cur_inum != extent_pos.inode) { io_opts->d.nr = 0; - ret = for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, extent_k.k->p.inode), + ret = for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, extent_pos.inode), BTREE_ITER_all_snapshots, k, ({ - if (k.k->p.offset != extent_k.k->p.inode) + if (k.k->p.offset != extent_pos.inode) break; if (!bkey_is_inode(k.k)) continue; struct bch_inode_unpacked inode; - BUG_ON(bch2_inode_unpack(k, &inode)); + _ret3 = bch2_inode_unpack(k, &inode); + if (_ret3) + break; struct snapshot_io_opts_entry e = { .snapshot = k.k->p.snapshot }; bch2_inode_opts_get(&e.io_opts, trans->c, &inode); darray_push(&io_opts->d, e); })); - io_opts->cur_inum = extent_k.k->p.inode; + io_opts->cur_inum = extent_pos.inode; } ret = ret ?: trans_was_restarted(trans, restart_count); @@ -415,43 +432,46 @@ struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans, if (extent_k.k->p.snapshot) darray_for_each(io_opts->d, i) - if (bch2_snapshot_is_ancestor(c, extent_k.k->p.snapshot, i->snapshot)) - return &i->io_opts; - - return &io_opts->fs_io_opts; + if (bch2_snapshot_is_ancestor(c, extent_k.k->p.snapshot, i->snapshot)) { + opts_ret = &i->io_opts; + break; + } +out: + ret = bch2_get_update_rebalance_opts(trans, opts_ret, extent_iter, extent_k); + if (ret) + return ERR_PTR(ret); + return opts_ret; } int bch2_move_get_io_opts_one(struct btree_trans *trans, struct bch_io_opts *io_opts, + struct btree_iter *extent_iter, struct bkey_s_c extent_k) { - struct btree_iter iter; - struct bkey_s_c k; - int ret; + struct bch_fs *c = trans->c; + + *io_opts = bch2_opts_to_inode_opts(c->opts); /* reflink btree? */ - if (!extent_k.k->p.inode) { - *io_opts = bch2_opts_to_inode_opts(trans->c->opts); - return 0; - } + if (!extent_k.k->p.inode) + goto out; - k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, + struct btree_iter inode_iter; + struct bkey_s_c inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, SPOS(0, extent_k.k->p.inode, extent_k.k->p.snapshot), BTREE_ITER_cached); - ret = bkey_err(k); + int ret = bkey_err(inode_k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) return ret; - if (!ret && bkey_is_inode(k.k)) { + if (!ret && bkey_is_inode(inode_k.k)) { struct bch_inode_unpacked inode; - bch2_inode_unpack(k, &inode); - bch2_inode_opts_get(io_opts, trans->c, &inode); - } else { - *io_opts = bch2_opts_to_inode_opts(trans->c->opts); + bch2_inode_unpack(inode_k, &inode); + bch2_inode_opts_get(io_opts, c, &inode); } - - bch2_trans_iter_exit(trans, &iter); - return 0; + bch2_trans_iter_exit(trans, &inode_iter); +out: + return bch2_get_update_rebalance_opts(trans, io_opts, extent_iter, extent_k); } int bch2_move_ratelimit(struct moving_context *ctxt) @@ -509,9 +529,15 @@ static int bch2_move_data_btree(struct moving_context *ctxt, struct per_snapshot_io_opts snapshot_io_opts; struct bch_io_opts *io_opts; struct bkey_buf sk; - struct btree_iter iter; + struct btree_iter iter, reflink_iter = {}; struct bkey_s_c k; struct data_update_opts data_opts; + /* + * If we're moving a single file, also process reflinked data it points + * to (this includes propagating changed io_opts from the inode to the + * extent): + */ + bool walk_indirect = start.inode == end.inode; int ret = 0, ret2; per_snapshot_io_opts_init(&snapshot_io_opts, c); @@ -531,6 +557,8 @@ static int bch2_move_data_btree(struct moving_context *ctxt, bch2_ratelimit_reset(ctxt->rate); while (!bch2_move_ratelimit(ctxt)) { + struct btree_iter *extent_iter = &iter; + bch2_trans_begin(trans); k = bch2_btree_iter_peek(&iter); @@ -549,10 +577,36 @@ static int bch2_move_data_btree(struct moving_context *ctxt, if (ctxt->stats) ctxt->stats->pos = BBPOS(iter.btree_id, iter.pos); + if (walk_indirect && + k.k->type == KEY_TYPE_reflink_p && + REFLINK_P_MAY_UPDATE_OPTIONS(bkey_s_c_to_reflink_p(k).v)) { + struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); + s64 offset_into_extent = iter.pos.offset - bkey_start_offset(k.k); + + bch2_trans_iter_exit(trans, &reflink_iter); + k = bch2_lookup_indirect_extent(trans, &reflink_iter, &offset_into_extent, p, true, 0); + ret = bkey_err(k); + if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) + continue; + if (ret) + break; + + if (bkey_deleted(k.k)) + goto next_nondata; + + /* + * XXX: reflink pointers may point to multiple indirect + * extents, so don't advance past the entire reflink + * pointer - need to fixup iter->k + */ + extent_iter = &reflink_iter; + } + if (!bkey_extent_is_direct_data(k.k)) goto next_nondata; - io_opts = bch2_move_get_io_opts(trans, &snapshot_io_opts, k); + io_opts = bch2_move_get_io_opts(trans, &snapshot_io_opts, + iter.pos, extent_iter, k); ret = PTR_ERR_OR_ZERO(io_opts); if (ret) continue; @@ -568,7 +622,7 @@ static int bch2_move_data_btree(struct moving_context *ctxt, bch2_bkey_buf_reassemble(&sk, c, k); k = bkey_i_to_s_c(sk.k); - ret2 = bch2_move_extent(ctxt, NULL, &iter, k, *io_opts, data_opts); + ret2 = bch2_move_extent(ctxt, NULL, extent_iter, k, *io_opts, data_opts); if (ret2) { if (bch2_err_matches(ret2, BCH_ERR_transaction_restart)) continue; @@ -589,6 +643,7 @@ next_nondata: bch2_btree_iter_advance(&iter); } + bch2_trans_iter_exit(trans, &reflink_iter); bch2_trans_iter_exit(trans, &iter); bch2_bkey_buf_exit(&sk, c); per_snapshot_io_opts_exit(&snapshot_io_opts); @@ -654,16 +709,12 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, struct bch_fs *c = trans->c; bool is_kthread = current->flags & PF_KTHREAD; struct bch_io_opts io_opts = bch2_opts_to_inode_opts(c->opts); - struct btree_iter iter; + struct btree_iter iter = {}, bp_iter = {}; struct bkey_buf sk; - struct bch_backpointer bp; - struct bch_alloc_v4 a_convert; - const struct bch_alloc_v4 *a; struct bkey_s_c k; struct data_update_opts data_opts; - unsigned dirty_sectors, bucket_size; - u64 fragmentation; - struct bpos bp_pos = POS_MIN; + unsigned sectors_moved = 0; + struct bkey_buf last_flushed; int ret = 0; struct bch_dev *ca = bch2_dev_tryget(c, bucket.inode); @@ -672,6 +723,8 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, trace_bucket_evacuate(c, &bucket); + bch2_bkey_buf_init(&last_flushed); + bkey_init(&last_flushed.k->k); bch2_bkey_buf_init(&sk); /* @@ -679,21 +732,13 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, */ bch2_trans_begin(trans); - bch2_trans_iter_init(trans, &iter, BTREE_ID_alloc, - bucket, BTREE_ITER_cached); - ret = lockrestart_do(trans, - bkey_err(k = bch2_btree_iter_peek_slot(&iter))); - bch2_trans_iter_exit(trans, &iter); + bch2_trans_iter_init(trans, &bp_iter, BTREE_ID_backpointers, + bucket_pos_to_bp_start(ca, bucket), 0); bch_err_msg(c, ret, "looking up alloc key"); if (ret) goto err; - a = bch2_alloc_to_v4(k, &a_convert); - dirty_sectors = bch2_bucket_sectors_dirty(*a); - bucket_size = ca->mi.bucket_size; - fragmentation = alloc_lru_idx_fragmentation(*a, ca); - ret = bch2_btree_write_buffer_tryflush(trans); bch_err_msg(c, ret, "flushing btree write buffer"); if (ret) @@ -705,18 +750,23 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, bch2_trans_begin(trans); - ret = bch2_get_next_backpointer(trans, ca, bucket, gen, - &bp_pos, &bp, - BTREE_ITER_cached); + k = bch2_btree_iter_peek(&bp_iter); + ret = bkey_err(k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) goto err; - if (bkey_eq(bp_pos, POS_MAX)) + + if (!k.k || bkey_gt(k.k->p, bucket_pos_to_bp_end(ca, bucket))) break; - if (!bp.level) { - k = bch2_backpointer_get_key(trans, &iter, bp_pos, bp, 0); + if (k.k->type != KEY_TYPE_backpointer) + goto next; + + struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k); + + if (!bp.v->level) { + k = bch2_backpointer_get_key(trans, bp, &iter, 0, &last_flushed); ret = bkey_err(k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; @@ -728,7 +778,7 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, bch2_bkey_buf_reassemble(&sk, c, k); k = bkey_i_to_s_c(sk.k); - ret = bch2_move_get_io_opts_one(trans, &io_opts, k); + ret = bch2_move_get_io_opts_one(trans, &io_opts, &iter, k); if (ret) { bch2_trans_iter_exit(trans, &iter); continue; @@ -738,14 +788,18 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, data_opts.target = io_opts.background_target; data_opts.rewrite_ptrs = 0; + unsigned sectors = bp.v->bucket_len; /* move_extent will drop locks */ unsigned i = 0; - bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr) { - if (ptr->dev == bucket.inode) { - data_opts.rewrite_ptrs |= 1U << i; - if (ptr->cached) { + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + bkey_for_each_ptr_decode(k.k, bch2_bkey_ptrs_c(k), p, entry) { + if (p.ptr.dev == bucket.inode) { + if (p.ptr.cached) { bch2_trans_iter_exit(trans, &iter); goto next; } + data_opts.rewrite_ptrs |= 1U << i; + break; } i++; } @@ -765,14 +819,15 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, goto err; if (ctxt->stats) - atomic64_add(k.k->size, &ctxt->stats->sectors_seen); + atomic64_add(sectors, &ctxt->stats->sectors_seen); + sectors_moved += sectors; } else { struct btree *b; - b = bch2_backpointer_get_node(trans, &iter, bp_pos, bp); + b = bch2_backpointer_get_node(trans, bp, &iter, &last_flushed); ret = PTR_ERR_OR_ZERO(b); if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node) - continue; + goto next; if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) @@ -796,15 +851,18 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, atomic64_add(sectors, &ctxt->stats->sectors_seen); atomic64_add(sectors, &ctxt->stats->sectors_moved); } + sectors_moved += btree_sectors(c); } next: - bp_pos = bpos_nosnap_successor(bp_pos); + bch2_btree_iter_advance(&bp_iter); } - trace_evacuate_bucket(c, &bucket, dirty_sectors, bucket_size, fragmentation, ret); + trace_evacuate_bucket(c, &bucket, sectors_moved, ca->mi.bucket_size, ret); err: + bch2_trans_iter_exit(trans, &bp_iter); bch2_dev_put(ca); bch2_bkey_buf_exit(&sk, c); + bch2_bkey_buf_exit(&last_flushed, c); return ret; } diff --git a/fs/bcachefs/move.h b/fs/bcachefs/move.h index 9baf3093a678..51e0505a8156 100644 --- a/fs/bcachefs/move.h +++ b/fs/bcachefs/move.h @@ -110,9 +110,8 @@ static inline void per_snapshot_io_opts_exit(struct per_snapshot_io_opts *io_opt darray_exit(&io_opts->d); } -struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *, - struct per_snapshot_io_opts *, struct bkey_s_c); -int bch2_move_get_io_opts_one(struct btree_trans *, struct bch_io_opts *, struct bkey_s_c); +int bch2_move_get_io_opts_one(struct btree_trans *, struct bch_io_opts *, + struct btree_iter *, struct bkey_s_c); int bch2_scan_old_btree_nodes(struct bch_fs *, struct bch_move_stats *); diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c index d658be90f737..21805509ab9e 100644 --- a/fs/bcachefs/movinggc.c +++ b/fs/bcachefs/movinggc.c @@ -167,7 +167,7 @@ static int bch2_copygc_get_buckets(struct moving_context *ctxt, bch2_trans_begin(trans); - ret = for_each_btree_key_upto(trans, iter, BTREE_ID_lru, + ret = for_each_btree_key_max(trans, iter, BTREE_ID_lru, lru_pos(BCH_LRU_FRAGMENTATION_START, 0, 0), lru_pos(BCH_LRU_FRAGMENTATION_START, U64_MAX, LRU_TIME_MAX), 0, k, ({ @@ -215,7 +215,8 @@ static int bch2_copygc(struct moving_context *ctxt, }; move_buckets buckets = { 0 }; struct move_bucket_in_flight *f; - u64 moved = atomic64_read(&ctxt->stats->sectors_moved); + u64 sectors_seen = atomic64_read(&ctxt->stats->sectors_seen); + u64 sectors_moved = atomic64_read(&ctxt->stats->sectors_moved); int ret = 0; ret = bch2_copygc_get_buckets(ctxt, buckets_in_flight, &buckets); @@ -245,7 +246,6 @@ static int bch2_copygc(struct moving_context *ctxt, *did_work = true; } err: - darray_exit(&buckets); /* no entries in LRU btree found, or got to end: */ if (bch2_err_matches(ret, ENOENT)) @@ -254,8 +254,11 @@ err: if (ret < 0 && !bch2_err_matches(ret, EROFS)) bch_err_msg(c, ret, "from bch2_move_data()"); - moved = atomic64_read(&ctxt->stats->sectors_moved) - moved; - trace_and_count(c, copygc, c, moved, 0, 0, 0); + sectors_seen = atomic64_read(&ctxt->stats->sectors_seen) - sectors_seen; + sectors_moved = atomic64_read(&ctxt->stats->sectors_moved) - sectors_moved; + trace_and_count(c, copygc, c, buckets.nr, sectors_seen, sectors_moved); + + darray_exit(&buckets); return ret; } @@ -350,9 +353,9 @@ static int bch2_copygc_thread(void *arg) bch2_trans_unlock_long(ctxt.trans); cond_resched(); - if (!c->copy_gc_enabled) { + if (!c->opts.copygc_enabled) { move_buckets_wait(&ctxt, buckets, true); - kthread_wait_freezable(c->copy_gc_enabled || + kthread_wait_freezable(c->opts.copygc_enabled || kthread_should_stop()); } diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c index 0e2ee262fbd4..6772faf385a5 100644 --- a/fs/bcachefs/opts.c +++ b/fs/bcachefs/opts.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include "bcachefs.h" #include "compress.h" @@ -48,12 +49,12 @@ static const char * const __bch2_csum_types[] = { NULL }; -const char * const bch2_csum_opts[] = { +const char * const __bch2_csum_opts[] = { BCH_CSUM_OPTS() NULL }; -static const char * const __bch2_compression_types[] = { +const char * const __bch2_compression_types[] = { BCH_COMPRESSION_TYPES() NULL }; @@ -113,6 +114,7 @@ void bch2_prt_##name(struct printbuf *out, type t) \ PRT_STR_OPT_BOUNDSCHECKED(jset_entry_type, enum bch_jset_entry_type); PRT_STR_OPT_BOUNDSCHECKED(fs_usage_type, enum bch_fs_usage_type); PRT_STR_OPT_BOUNDSCHECKED(data_type, enum bch_data_type); +PRT_STR_OPT_BOUNDSCHECKED(csum_opt, enum bch_csum_opt); PRT_STR_OPT_BOUNDSCHECKED(csum_type, enum bch_csum_type); PRT_STR_OPT_BOUNDSCHECKED(compression_type, enum bch_compression_type); PRT_STR_OPT_BOUNDSCHECKED(str_hash_type, enum bch_str_hash_type); @@ -333,17 +335,18 @@ int bch2_opt_parse(struct bch_fs *c, switch (opt->type) { case BCH_OPT_BOOL: if (val) { - ret = kstrtou64(val, 10, res); + ret = lookup_constant(bool_names, val, -BCH_ERR_option_not_bool); + if (ret != -BCH_ERR_option_not_bool) { + *res = ret; + } else { + if (err) + prt_printf(err, "%s: must be bool", opt->attr.name); + return ret; + } } else { - ret = 0; *res = 1; } - if (ret < 0 || (*res != 0 && *res != 1)) { - if (err) - prt_printf(err, "%s: must be bool", opt->attr.name); - return ret < 0 ? ret : -BCH_ERR_option_not_bool; - } break; case BCH_OPT_UINT: if (!val) { @@ -710,11 +713,14 @@ void bch2_opt_set_sb(struct bch_fs *c, struct bch_dev *ca, struct bch_io_opts bch2_opts_to_inode_opts(struct bch_opts src) { - return (struct bch_io_opts) { + struct bch_io_opts opts = { #define x(_name, _bits) ._name = src._name, BCH_INODE_OPTS() #undef x }; + + bch2_io_opts_fixups(&opts); + return opts; } bool bch2_opt_is_inode_opt(enum bch_opt_id id) diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index 23dda014e331..a182b5d454ba 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -16,7 +16,8 @@ extern const char * const bch2_version_upgrade_opts[]; extern const char * const bch2_sb_features[]; extern const char * const bch2_sb_compat[]; extern const char * const __bch2_btree_ids[]; -extern const char * const bch2_csum_opts[]; +extern const char * const __bch2_csum_opts[]; +extern const char * const __bch2_compression_types[]; extern const char * const bch2_compression_opts[]; extern const char * const __bch2_str_hash_types[]; extern const char * const bch2_str_hash_opts[]; @@ -27,6 +28,7 @@ extern const char * const bch2_d_types[]; void bch2_prt_jset_entry_type(struct printbuf *, enum bch_jset_entry_type); void bch2_prt_fs_usage_type(struct printbuf *, enum bch_fs_usage_type); void bch2_prt_data_type(struct printbuf *, enum bch_data_type); +void bch2_prt_csum_opt(struct printbuf *, enum bch_csum_opt); void bch2_prt_csum_type(struct printbuf *, enum bch_csum_type); void bch2_prt_compression_type(struct printbuf *, enum bch_compression_type); void bch2_prt_str_hash_type(struct printbuf *, enum bch_str_hash_type); @@ -171,12 +173,12 @@ enum fsck_err_opts { "size", "Maximum size of checksummed/compressed extents")\ x(metadata_checksum, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ - OPT_STR(bch2_csum_opts), \ + OPT_STR(__bch2_csum_opts), \ BCH_SB_META_CSUM_TYPE, BCH_CSUM_OPT_crc32c, \ NULL, NULL) \ x(data_checksum, u8, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ - OPT_STR(bch2_csum_opts), \ + OPT_STR(__bch2_csum_opts), \ BCH_SB_DATA_CSUM_TYPE, BCH_CSUM_OPT_crc32c, \ NULL, NULL) \ x(compression, u8, \ @@ -220,14 +222,14 @@ enum fsck_err_opts { BCH_SB_ERASURE_CODE, false, \ NULL, "Enable erasure coding (DO NOT USE YET)") \ x(inodes_32bit, u8, \ - OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ + OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH_SB_INODE_32BIT, true, \ NULL, "Constrain inode numbers to 32 bits") \ - x(shard_inode_numbers, u8, \ - OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ - OPT_BOOL(), \ - BCH_SB_SHARD_INUMS, true, \ + x(shard_inode_numbers_bits, u8, \ + OPT_FS|OPT_FORMAT, \ + OPT_UINT(0, 8), \ + BCH_SB_SHARD_INUMS_NBITS, 0, \ NULL, "Shard new inode numbers by CPU id") \ x(inodes_use_key_cache, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ @@ -473,6 +475,18 @@ enum fsck_err_opts { BCH2_NO_SB_OPT, true, \ NULL, "Enable nocow mode: enables runtime locking in\n"\ "data move path needed if nocow will ever be in use\n")\ + x(copygc_enabled, u8, \ + OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ + OPT_BOOL(), \ + BCH2_NO_SB_OPT, true, \ + NULL, "Enable copygc: disable for debugging, or to\n"\ + "quiet the system when doing performance testing\n")\ + x(rebalance_enabled, u8, \ + OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ + OPT_BOOL(), \ + BCH2_NO_SB_OPT, true, \ + NULL, "Enable rebalance: disable for debugging, or to\n"\ + "quiet the system when doing performance testing\n")\ x(no_data_io, u8, \ OPT_MOUNT, \ OPT_BOOL(), \ @@ -488,7 +502,7 @@ enum fsck_err_opts { OPT_DEVICE, \ OPT_UINT(0, S64_MAX), \ BCH2_NO_SB_OPT, 0, \ - "size", "Size of filesystem on device") \ + "size", "Specifies the bucket size; must be greater than the btree node size")\ x(durability, u8, \ OPT_DEVICE|OPT_SB_FIELD_ONE_BIAS, \ OPT_UINT(0, BCH_REPLICAS_MAX), \ @@ -624,14 +638,39 @@ struct bch_io_opts { #define x(_name, _bits) u##_bits _name; BCH_INODE_OPTS() #undef x +#define x(_name, _bits) u64 _name##_from_inode:1; + BCH_INODE_OPTS() +#undef x }; -static inline unsigned background_compression(struct bch_io_opts opts) +static inline void bch2_io_opts_fixups(struct bch_io_opts *opts) { - return opts.background_compression ?: opts.compression; + if (!opts->background_target) + opts->background_target = opts->foreground_target; + if (!opts->background_compression) + opts->background_compression = opts->compression; + if (opts->nocow) { + opts->compression = opts->background_compression = 0; + opts->data_checksum = 0; + opts->erasure_code = 0; + } } struct bch_io_opts bch2_opts_to_inode_opts(struct bch_opts); bool bch2_opt_is_inode_opt(enum bch_opt_id); +/* rebalance opts: */ + +static inline struct bch_extent_rebalance io_opts_to_rebalance_opts(struct bch_io_opts *opts) +{ + return (struct bch_extent_rebalance) { + .type = BIT(BCH_EXTENT_ENTRY_rebalance), +#define x(_name) \ + ._name = opts->_name, \ + ._name##_from_inode = opts->_name##_from_inode, + BCH_REBALANCE_OPTS() +#undef x + }; +}; + #endif /* _BCACHEFS_OPTS_H */ diff --git a/fs/bcachefs/printbuf.h b/fs/bcachefs/printbuf.h index 1d570387b77f..d0dd398baa2b 100644 --- a/fs/bcachefs/printbuf.h +++ b/fs/bcachefs/printbuf.h @@ -251,16 +251,23 @@ static inline void prt_hex_byte_upper(struct printbuf *out, u8 byte) printbuf_nul_terminate_reserved(out); } +static inline void printbuf_reset_keep_tabstops(struct printbuf *buf) +{ + buf->pos = 0; + buf->allocation_failure = 0; + buf->last_newline = 0; + buf->last_field = 0; + buf->indent = 0; + buf->cur_tabstop = 0; +} + /** * printbuf_reset - re-use a printbuf without freeing and re-initializing it: */ static inline void printbuf_reset(struct printbuf *buf) { - buf->pos = 0; - buf->allocation_failure = 0; - buf->indent = 0; + printbuf_reset_keep_tabstops(buf); buf->nr_tabstops = 0; - buf->cur_tabstop = 0; } /** diff --git a/fs/bcachefs/quota.c b/fs/bcachefs/quota.c index 74f45a8162ad..8b857fc33244 100644 --- a/fs/bcachefs/quota.c +++ b/fs/bcachefs/quota.c @@ -60,7 +60,7 @@ const struct bch_sb_field_ops bch_sb_field_ops_quota = { }; int bch2_quota_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; diff --git a/fs/bcachefs/quota.h b/fs/bcachefs/quota.h index a62abcc5332a..1551800ff44c 100644 --- a/fs/bcachefs/quota.h +++ b/fs/bcachefs/quota.h @@ -5,10 +5,10 @@ #include "inode.h" #include "quota_types.h" -enum bch_validate_flags; extern const struct bch_sb_field_ops bch_sb_field_ops_quota; -int bch2_quota_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_quota_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_quota_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_quota ((struct bkey_ops) { \ diff --git a/fs/bcachefs/rcu_pending.c b/fs/bcachefs/rcu_pending.c index 40a20192eee8..bef2aa1b8bcd 100644 --- a/fs/bcachefs/rcu_pending.c +++ b/fs/bcachefs/rcu_pending.c @@ -25,21 +25,37 @@ enum rcu_pending_special { #define RCU_PENDING_KVFREE_FN ((rcu_pending_process_fn) (ulong) RCU_PENDING_KVFREE) #define RCU_PENDING_CALL_RCU_FN ((rcu_pending_process_fn) (ulong) RCU_PENDING_CALL_RCU) -static inline unsigned long __get_state_synchronize_rcu(struct srcu_struct *ssp) +#ifdef __KERNEL__ +typedef unsigned long rcu_gp_poll_state_t; + +static inline bool rcu_gp_poll_cookie_eq(rcu_gp_poll_state_t l, rcu_gp_poll_state_t r) +{ + return l == r; +} +#else +typedef struct urcu_gp_poll_state rcu_gp_poll_state_t; + +static inline bool rcu_gp_poll_cookie_eq(rcu_gp_poll_state_t l, rcu_gp_poll_state_t r) +{ + return l.grace_period_id == r.grace_period_id; +} +#endif + +static inline rcu_gp_poll_state_t __get_state_synchronize_rcu(struct srcu_struct *ssp) { return ssp ? get_state_synchronize_srcu(ssp) : get_state_synchronize_rcu(); } -static inline unsigned long __start_poll_synchronize_rcu(struct srcu_struct *ssp) +static inline rcu_gp_poll_state_t __start_poll_synchronize_rcu(struct srcu_struct *ssp) { return ssp ? start_poll_synchronize_srcu(ssp) : start_poll_synchronize_rcu(); } -static inline bool __poll_state_synchronize_rcu(struct srcu_struct *ssp, unsigned long cookie) +static inline bool __poll_state_synchronize_rcu(struct srcu_struct *ssp, rcu_gp_poll_state_t cookie) { return ssp ? poll_state_synchronize_srcu(ssp, cookie) @@ -71,13 +87,13 @@ struct rcu_pending_seq { GENRADIX(struct rcu_head *) objs; size_t nr; struct rcu_head **cursor; - unsigned long seq; + rcu_gp_poll_state_t seq; }; struct rcu_pending_list { struct rcu_head *head; struct rcu_head *tail; - unsigned long seq; + rcu_gp_poll_state_t seq; }; struct rcu_pending_pcpu { @@ -316,10 +332,10 @@ static void rcu_pending_rcu_cb(struct rcu_head *rcu) } static __always_inline struct rcu_pending_seq * -get_object_radix(struct rcu_pending_pcpu *p, unsigned long seq) +get_object_radix(struct rcu_pending_pcpu *p, rcu_gp_poll_state_t seq) { darray_for_each_reverse(p->objs, objs) - if (objs->seq == seq) + if (rcu_gp_poll_cookie_eq(objs->seq, seq)) return objs; if (darray_push_gfp(&p->objs, ((struct rcu_pending_seq) { .seq = seq }), GFP_ATOMIC)) @@ -329,7 +345,7 @@ get_object_radix(struct rcu_pending_pcpu *p, unsigned long seq) } static noinline bool -rcu_pending_enqueue_list(struct rcu_pending_pcpu *p, unsigned long seq, +rcu_pending_enqueue_list(struct rcu_pending_pcpu *p, rcu_gp_poll_state_t seq, struct rcu_head *head, void *ptr, unsigned long *flags) { @@ -364,7 +380,7 @@ rcu_pending_enqueue_list(struct rcu_pending_pcpu *p, unsigned long seq, again: for (struct rcu_pending_list *i = p->lists; i < p->lists + NUM_ACTIVE_RCU_POLL_OLDSTATE; i++) { - if (i->seq == seq) { + if (rcu_gp_poll_cookie_eq(i->seq, seq)) { rcu_pending_list_add(i, head); return false; } @@ -408,7 +424,7 @@ __rcu_pending_enqueue(struct rcu_pending *pending, struct rcu_head *head, struct rcu_pending_pcpu *p; struct rcu_pending_seq *objs; struct genradix_node *new_node = NULL; - unsigned long seq, flags; + unsigned long flags; bool start_gp = false; BUG_ON((ptr != NULL) != (pending->process == RCU_PENDING_KVFREE_FN)); @@ -416,7 +432,7 @@ __rcu_pending_enqueue(struct rcu_pending *pending, struct rcu_head *head, local_irq_save(flags); p = this_cpu_ptr(pending->p); spin_lock(&p->lock); - seq = __get_state_synchronize_rcu(pending->srcu); + rcu_gp_poll_state_t seq = __get_state_synchronize_rcu(pending->srcu); restart: if (may_sleep && unlikely(process_finished_items(pending, p, flags))) diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c index cd6647374353..4adc74cd3f70 100644 --- a/fs/bcachefs/rebalance.c +++ b/fs/bcachefs/rebalance.c @@ -24,6 +24,192 @@ #include #include +/* bch_extent_rebalance: */ + +static const struct bch_extent_rebalance *bch2_bkey_rebalance_opts(struct bkey_s_c k) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + const union bch_extent_entry *entry; + + bkey_extent_entry_for_each(ptrs, entry) + if (__extent_entry_type(entry) == BCH_EXTENT_ENTRY_rebalance) + return &entry->rebalance; + + return NULL; +} + +static inline unsigned bch2_bkey_ptrs_need_compress(struct bch_fs *c, + struct bch_io_opts *opts, + struct bkey_s_c k, + struct bkey_ptrs_c ptrs) +{ + if (!opts->background_compression) + return 0; + + unsigned compression_type = bch2_compression_opt_to_type(opts->background_compression); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + unsigned ptr_bit = 1; + unsigned rewrite_ptrs = 0; + + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { + if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || + p.ptr.unwritten) + return 0; + + if (!p.ptr.cached && p.crc.compression_type != compression_type) + rewrite_ptrs |= ptr_bit; + ptr_bit <<= 1; + } + + return rewrite_ptrs; +} + +static inline unsigned bch2_bkey_ptrs_need_move(struct bch_fs *c, + struct bch_io_opts *opts, + struct bkey_ptrs_c ptrs) +{ + if (!opts->background_target || + !bch2_target_accepts_data(c, BCH_DATA_user, opts->background_target)) + return 0; + + unsigned ptr_bit = 1; + unsigned rewrite_ptrs = 0; + + bkey_for_each_ptr(ptrs, ptr) { + if (!ptr->cached && !bch2_dev_in_target(c, ptr->dev, opts->background_target)) + rewrite_ptrs |= ptr_bit; + ptr_bit <<= 1; + } + + return rewrite_ptrs; +} + +static unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *c, + struct bch_io_opts *opts, + struct bkey_s_c k) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + + return bch2_bkey_ptrs_need_compress(c, opts, k, ptrs) | + bch2_bkey_ptrs_need_move(c, opts, ptrs); +} + +u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k) +{ + const struct bch_extent_rebalance *opts = bch2_bkey_rebalance_opts(k); + if (!opts) + return 0; + + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + u64 sectors = 0; + + if (opts->background_compression) { + unsigned compression_type = bch2_compression_opt_to_type(opts->background_compression); + + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { + if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || + p.ptr.unwritten) { + sectors = 0; + goto incompressible; + } + + if (!p.ptr.cached && p.crc.compression_type != compression_type) + sectors += p.crc.compressed_size; + } + } +incompressible: + if (opts->background_target && + bch2_target_accepts_data(c, BCH_DATA_user, opts->background_target)) { + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) + if (!p.ptr.cached && !bch2_dev_in_target(c, p.ptr.dev, opts->background_target)) + sectors += p.crc.compressed_size; + } + + return sectors; +} + +static bool bch2_bkey_rebalance_needs_update(struct bch_fs *c, struct bch_io_opts *opts, + struct bkey_s_c k) +{ + if (!bkey_extent_is_direct_data(k.k)) + return 0; + + const struct bch_extent_rebalance *old = bch2_bkey_rebalance_opts(k); + + if (k.k->type == KEY_TYPE_reflink_v || bch2_bkey_ptrs_need_rebalance(c, opts, k)) { + struct bch_extent_rebalance new = io_opts_to_rebalance_opts(opts); + return old == NULL || memcmp(old, &new, sizeof(new)); + } else { + return old != NULL; + } +} + +int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bch_io_opts *opts, + struct bkey_i *_k) +{ + if (!bkey_extent_is_direct_data(&_k->k)) + return 0; + + struct bkey_s k = bkey_i_to_s(_k); + struct bch_extent_rebalance *old = + (struct bch_extent_rebalance *) bch2_bkey_rebalance_opts(k.s_c); + + if (k.k->type == KEY_TYPE_reflink_v || bch2_bkey_ptrs_need_rebalance(c, opts, k.s_c)) { + if (!old) { + old = bkey_val_end(k); + k.k->u64s += sizeof(*old) / sizeof(u64); + } + + *old = io_opts_to_rebalance_opts(opts); + } else { + if (old) + extent_entry_drop(k, (union bch_extent_entry *) old); + } + + return 0; +} + +int bch2_get_update_rebalance_opts(struct btree_trans *trans, + struct bch_io_opts *io_opts, + struct btree_iter *iter, + struct bkey_s_c k) +{ + BUG_ON(iter->flags & BTREE_ITER_is_extents); + BUG_ON(iter->flags & BTREE_ITER_filter_snapshots); + + const struct bch_extent_rebalance *r = k.k->type == KEY_TYPE_reflink_v + ? bch2_bkey_rebalance_opts(k) : NULL; + if (r) { +#define x(_name) \ + if (r->_name##_from_inode) { \ + io_opts->_name = r->_name; \ + io_opts->_name##_from_inode = true; \ + } + BCH_REBALANCE_OPTS() +#undef x + } + + if (!bch2_bkey_rebalance_needs_update(trans->c, io_opts, k)) + return 0; + + struct bkey_i *n = bch2_trans_kmalloc(trans, bkey_bytes(k.k) + 8); + int ret = PTR_ERR_OR_ZERO(n); + if (ret) + return ret; + + bkey_reassemble(n, k); + + /* On successfull transaction commit, @k was invalidated: */ + + return bch2_bkey_set_needs_rebalance(trans->c, io_opts, n) ?: + bch2_trans_update(trans, iter, n, BTREE_UPDATE_internal_snapshot_node) ?: + bch2_trans_commit(trans, NULL, NULL, 0) ?: + -BCH_ERR_transaction_restart_nested; +} + #define REBALANCE_WORK_SCAN_OFFSET (U64_MAX - 1) static const char * const bch2_rebalance_state_strs[] = { @@ -33,7 +219,7 @@ static const char * const bch2_rebalance_state_strs[] = { #undef x }; -static int __bch2_set_rebalance_needs_scan(struct btree_trans *trans, u64 inum) +int bch2_set_rebalance_needs_scan_trans(struct btree_trans *trans, u64 inum) { struct btree_iter iter; struct bkey_s_c k; @@ -71,9 +257,8 @@ err: int bch2_set_rebalance_needs_scan(struct bch_fs *c, u64 inum) { int ret = bch2_trans_commit_do(c, NULL, NULL, - BCH_TRANS_COMMIT_no_enospc| - BCH_TRANS_COMMIT_lazy_rw, - __bch2_set_rebalance_needs_scan(trans, inum)); + BCH_TRANS_COMMIT_no_enospc, + bch2_set_rebalance_needs_scan_trans(trans, inum)); rebalance_wakeup(c); return ret; } @@ -121,6 +306,9 @@ static int bch2_bkey_clear_needs_rebalance(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { + if (!bch2_bkey_rebalance_opts(k)) + return 0; + struct bkey_i *n = bch2_bkey_make_mut(trans, iter, &k, 0); int ret = PTR_ERR_OR_ZERO(n); if (ret) @@ -134,31 +322,27 @@ static int bch2_bkey_clear_needs_rebalance(struct btree_trans *trans, static struct bkey_s_c next_rebalance_extent(struct btree_trans *trans, struct bpos work_pos, struct btree_iter *extent_iter, + struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { struct bch_fs *c = trans->c; - struct bkey_s_c k; bch2_trans_iter_exit(trans, extent_iter); bch2_trans_iter_init(trans, extent_iter, work_pos.inode ? BTREE_ID_extents : BTREE_ID_reflink, work_pos, BTREE_ITER_all_snapshots); - k = bch2_btree_iter_peek_slot(extent_iter); + struct bkey_s_c k = bch2_btree_iter_peek_slot(extent_iter); if (bkey_err(k)) return k; - const struct bch_extent_rebalance *r = k.k ? bch2_bkey_rebalance_opts(k) : NULL; - if (!r) { - /* raced due to btree write buffer, nothing to do */ - return bkey_s_c_null; - } + int ret = bch2_move_get_io_opts_one(trans, io_opts, extent_iter, k); + if (ret) + return bkey_s_c_err(ret); memset(data_opts, 0, sizeof(*data_opts)); - - data_opts->rewrite_ptrs = - bch2_bkey_ptrs_need_rebalance(c, k, r->target, r->compression); - data_opts->target = r->target; + data_opts->rewrite_ptrs = bch2_bkey_ptrs_need_rebalance(c, io_opts, k); + data_opts->target = io_opts->background_target; data_opts->write_flags |= BCH_WRITE_ONLY_SPECIFIED_DEVS; if (!data_opts->rewrite_ptrs) { @@ -178,12 +362,28 @@ static struct bkey_s_c next_rebalance_extent(struct btree_trans *trans, if (trace_rebalance_extent_enabled()) { struct printbuf buf = PRINTBUF; - prt_str(&buf, "target="); - bch2_target_to_text(&buf, c, r->target); - prt_str(&buf, " compression="); - bch2_compression_opt_to_text(&buf, r->compression); - prt_str(&buf, " "); bch2_bkey_val_to_text(&buf, c, k); + prt_newline(&buf); + + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + + unsigned p = bch2_bkey_ptrs_need_compress(c, io_opts, k, ptrs); + if (p) { + prt_str(&buf, "compression="); + bch2_compression_opt_to_text(&buf, io_opts->background_compression); + prt_str(&buf, " "); + bch2_prt_u64_base2(&buf, p); + prt_newline(&buf); + } + + p = bch2_bkey_ptrs_need_move(c, io_opts, ptrs); + if (p) { + prt_str(&buf, "move="); + bch2_target_to_text(&buf, c, io_opts->background_target); + prt_str(&buf, " "); + bch2_prt_u64_base2(&buf, p); + prt_newline(&buf); + } trace_rebalance_extent(c, buf.buf); printbuf_exit(&buf); @@ -212,14 +412,10 @@ static int do_rebalance_extent(struct moving_context *ctxt, bch2_bkey_buf_init(&sk); ret = bkey_err(k = next_rebalance_extent(trans, work_pos, - extent_iter, &data_opts)); + extent_iter, &io_opts, &data_opts)); if (ret || !k.k) goto out; - ret = bch2_move_get_io_opts_one(trans, &io_opts, k); - if (ret) - goto out; - atomic64_add(k.k->size, &ctxt->stats->sectors_seen); /* @@ -253,20 +449,8 @@ static bool rebalance_pred(struct bch_fs *c, void *arg, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { - unsigned target, compression; - - if (k.k->p.inode) { - target = io_opts->background_target; - compression = background_compression(*io_opts); - } else { - const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k); - - target = r ? r->target : io_opts->background_target; - compression = r ? r->compression : background_compression(*io_opts); - } - - data_opts->rewrite_ptrs = bch2_bkey_ptrs_need_rebalance(c, k, target, compression); - data_opts->target = target; + data_opts->rewrite_ptrs = bch2_bkey_ptrs_need_rebalance(c, io_opts, k); + data_opts->target = io_opts->background_target; data_opts->write_flags |= BCH_WRITE_ONLY_SPECIFIED_DEVS; return data_opts->rewrite_ptrs != 0; } @@ -338,9 +522,9 @@ static int do_rebalance(struct moving_context *ctxt) BTREE_ITER_all_snapshots); while (!bch2_move_ratelimit(ctxt)) { - if (!r->enabled) { + if (!c->opts.rebalance_enabled) { bch2_moving_ctxt_flush_all(ctxt); - kthread_wait_freezable(r->enabled || + kthread_wait_freezable(c->opts.rebalance_enabled || kthread_should_stop()); } diff --git a/fs/bcachefs/rebalance.h b/fs/bcachefs/rebalance.h index 28a52638f16c..0a0821ab895d 100644 --- a/fs/bcachefs/rebalance.h +++ b/fs/bcachefs/rebalance.h @@ -2,8 +2,18 @@ #ifndef _BCACHEFS_REBALANCE_H #define _BCACHEFS_REBALANCE_H +#include "compress.h" +#include "disk_groups.h" #include "rebalance_types.h" +u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *, struct bkey_s_c); +int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bch_io_opts *, struct bkey_i *); +int bch2_get_update_rebalance_opts(struct btree_trans *, + struct bch_io_opts *, + struct btree_iter *, + struct bkey_s_c); + +int bch2_set_rebalance_needs_scan_trans(struct btree_trans *, u64); int bch2_set_rebalance_needs_scan(struct bch_fs *, u64 inum); int bch2_set_fs_needs_rebalance(struct bch_fs *); diff --git a/fs/bcachefs/rebalance_format.h b/fs/bcachefs/rebalance_format.h new file mode 100644 index 000000000000..ff9a1342a22b --- /dev/null +++ b/fs/bcachefs/rebalance_format.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_REBALANCE_FORMAT_H +#define _BCACHEFS_REBALANCE_FORMAT_H + +struct bch_extent_rebalance { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u64 type:6, + unused:3, + + promote_target_from_inode:1, + erasure_code_from_inode:1, + data_checksum_from_inode:1, + background_compression_from_inode:1, + data_replicas_from_inode:1, + background_target_from_inode:1, + + promote_target:16, + erasure_code:1, + data_checksum:4, + data_replicas:4, + background_compression:8, /* enum bch_compression_opt */ + background_target:16; +#elif defined (__BIG_ENDIAN_BITFIELD) + __u64 background_target:16, + background_compression:8, + data_replicas:4, + data_checksum:4, + erasure_code:1, + promote_target:16, + + background_target_from_inode:1, + data_replicas_from_inode:1, + background_compression_from_inode:1, + data_checksum_from_inode:1, + erasure_code_from_inode:1, + promote_target_from_inode:1, + + unused:3, + type:6; +#endif +}; + +/* subset of BCH_INODE_OPTS */ +#define BCH_REBALANCE_OPTS() \ + x(data_checksum) \ + x(background_compression) \ + x(data_replicas) \ + x(promote_target) \ + x(background_target) \ + x(erasure_code) + +#endif /* _BCACHEFS_REBALANCE_FORMAT_H */ + diff --git a/fs/bcachefs/rebalance_types.h b/fs/bcachefs/rebalance_types.h index 0fffb536c1d0..fe5098c17dfc 100644 --- a/fs/bcachefs/rebalance_types.h +++ b/fs/bcachefs/rebalance_types.h @@ -30,8 +30,6 @@ struct bch_fs_rebalance { struct bbpos scan_start; struct bbpos scan_end; struct bch_move_stats scan_stats; - - unsigned enabled:1; }; #endif /* _BCACHEFS_REBALANCE_TYPES_H */ diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 3c7f941dde39..71c786cdb192 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -32,23 +32,84 @@ #include #include -#define QSTR(n) { { { .len = strlen(n) } }, .name = n } -void bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree) +int bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree) { - if (btree >= BTREE_ID_NR_MAX) - return; - u64 b = BIT_ULL(btree); + int ret = 0; + + mutex_lock(&c->sb_lock); + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); if (!(c->sb.btrees_lost_data & b)) { - bch_err(c, "flagging btree %s lost data", bch2_btree_id_str(btree)); - - mutex_lock(&c->sb_lock); - bch2_sb_field_get(c->disk_sb.sb, ext)->btrees_lost_data |= cpu_to_le64(b); - bch2_write_super(c); - mutex_unlock(&c->sb_lock); + struct printbuf buf = PRINTBUF; + bch2_btree_id_to_text(&buf, btree); + bch_err(c, "flagging btree %s lost data", buf.buf); + printbuf_exit(&buf); + ext->btrees_lost_data |= cpu_to_le64(b); } + + /* Once we have runtime self healing for topology errors we won't need this: */ + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_topology) ?: ret; + + /* Btree node accounting will be off: */ + __set_bit_le64(BCH_FSCK_ERR_accounting_mismatch, ext->errors_silent); + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_allocations) ?: ret; + +#ifdef CONFIG_BCACHEFS_DEBUG + /* + * These are much more minor, and don't need to be corrected right away, + * but in debug mode we want the next fsck run to be clean: + */ + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_lrus) ?: ret; + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_backpointers_to_extents) ?: ret; +#endif + + switch (btree) { + case BTREE_ID_alloc: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + + __set_bit_le64(BCH_FSCK_ERR_alloc_key_data_type_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_gen_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_dirty_sectors_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_cached_sectors_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_stripe_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_stripe_redundancy_wrong, ext->errors_silent); + goto out; + case BTREE_ID_backpointers: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_btree_backpointers) ?: ret; + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_extents_to_backpointers) ?: ret; + goto out; + case BTREE_ID_need_discard: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + goto out; + case BTREE_ID_freespace: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + goto out; + case BTREE_ID_bucket_gens: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + goto out; + case BTREE_ID_lru: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + goto out; + case BTREE_ID_accounting: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_allocations) ?: ret; + goto out; + default: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_scan_for_btree_nodes) ?: ret; + goto out; + } +out: + bch2_write_super(c); + mutex_unlock(&c->sb_lock); + + return ret; +} + +static void kill_btree(struct bch_fs *c, enum btree_id btree) +{ + bch2_btree_id_root(c, btree)->alive = false; + bch2_shoot_down_journal_keys(c, btree, 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); } /* for -o reconstruct_alloc: */ @@ -79,6 +140,8 @@ static void bch2_reconstruct_alloc(struct bch_fs *c) __set_bit_le64(BCH_FSCK_ERR_fs_usage_persistent_reserved_wrong, ext->errors_silent); __set_bit_le64(BCH_FSCK_ERR_fs_usage_replicas_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_to_missing_lru_entry, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_data_type_wrong, ext->errors_silent); __set_bit_le64(BCH_FSCK_ERR_alloc_key_gen_wrong, ext->errors_silent); __set_bit_le64(BCH_FSCK_ERR_alloc_key_dirty_sectors_wrong, ext->errors_silent); @@ -99,16 +162,9 @@ static void bch2_reconstruct_alloc(struct bch_fs *c) bch2_write_super(c); mutex_unlock(&c->sb_lock); - bch2_shoot_down_journal_keys(c, BTREE_ID_alloc, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - bch2_shoot_down_journal_keys(c, BTREE_ID_backpointers, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - bch2_shoot_down_journal_keys(c, BTREE_ID_need_discard, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - bch2_shoot_down_journal_keys(c, BTREE_ID_freespace, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - bch2_shoot_down_journal_keys(c, BTREE_ID_bucket_gens, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); + for (unsigned i = 0; i < btree_id_nr_alive(c); i++) + if (btree_id_is_alloc(i)) + kill_btree(c, i); } /* @@ -354,10 +410,13 @@ int bch2_journal_replay(struct bch_fs *c) ? BCH_TRANS_COMMIT_no_journal_res|BCH_WATERMARK_reclaim : 0), bch2_journal_replay_key(trans, k)); - bch_err_msg(c, ret, "while replaying key at btree %s level %u:", - bch2_btree_id_str(k->btree_id), k->level); - if (ret) + if (ret) { + struct printbuf buf = PRINTBUF; + bch2_btree_id_level_to_text(&buf, k->btree_id, k->level); + bch_err_msg(c, ret, "while replaying key at %s:", buf.buf); + printbuf_exit(&buf); goto err; + } BUG_ON(k->btree_id != BTREE_ID_accounting && !k->overwritten); } @@ -403,7 +462,9 @@ static int journal_replay_entry_early(struct bch_fs *c, switch (entry->type) { case BCH_JSET_ENTRY_btree_root: { - struct btree_root *r; + + if (unlikely(!entry->u64s)) + return 0; if (fsck_err_on(entry->btree_id >= BTREE_ID_NR_MAX, c, invalid_btree_id, @@ -417,15 +478,11 @@ static int journal_replay_entry_early(struct bch_fs *c, return ret; } - r = bch2_btree_id_root(c, entry->btree_id); + struct btree_root *r = bch2_btree_id_root(c, entry->btree_id); - if (entry->u64s) { - r->level = entry->level; - bkey_copy(&r->key, (struct bkey_i *) entry->start); - r->error = 0; - } else { - r->error = -BCH_ERR_btree_node_read_error; - } + r->level = entry->level; + bkey_copy(&r->key, (struct bkey_i *) entry->start); + r->error = 0; r->alive = true; break; } @@ -505,6 +562,7 @@ static int journal_replay_early(struct bch_fs *c, static int read_btree_roots(struct bch_fs *c) { + struct printbuf buf = PRINTBUF; int ret = 0; for (unsigned i = 0; i < btree_id_nr_alive(c); i++) { @@ -513,33 +571,22 @@ static int read_btree_roots(struct bch_fs *c) if (!r->alive) continue; - if (btree_id_is_alloc(i) && c->opts.reconstruct_alloc) - continue; + printbuf_reset(&buf); + bch2_btree_id_level_to_text(&buf, i, r->level); if (mustfix_fsck_err_on((ret = r->error), c, btree_root_bkey_invalid, "invalid btree root %s", - bch2_btree_id_str(i)) || + buf.buf) || mustfix_fsck_err_on((ret = r->error = bch2_btree_root_read(c, i, &r->key, r->level)), c, btree_root_read_error, - "error reading btree root %s l=%u: %s", - bch2_btree_id_str(i), r->level, bch2_err_str(ret))) { - if (btree_id_is_alloc(i)) { - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_allocations); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_info); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_lrus); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_to_lru_refs); - c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info); + "error reading btree root %s: %s", + buf.buf, bch2_err_str(ret))) { + if (btree_id_is_alloc(i)) r->error = 0; - } else if (!(c->opts.recovery_passes & BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes))) { - bch_info(c, "will run btree node scan"); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_topology); - } - ret = 0; - bch2_btree_lost_data(c, i); + ret = bch2_btree_lost_data(c, i); + BUG_ON(ret); } } @@ -553,6 +600,7 @@ static int read_btree_roots(struct bch_fs *c) } } fsck_err: + printbuf_exit(&buf); return ret; } @@ -563,6 +611,7 @@ static bool check_version_upgrade(struct bch_fs *c) bch2_latest_compatible_version(c->sb.version)); unsigned old_version = c->sb.version_upgrade_complete ?: c->sb.version; unsigned new_version = 0; + bool ret = false; if (old_version < bcachefs_metadata_required_upgrade_below) { if (c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible || @@ -618,14 +667,32 @@ static bool check_version_upgrade(struct bch_fs *c) } bch_info(c, "%s", buf.buf); - - bch2_sb_upgrade(c, new_version); - printbuf_exit(&buf); - return true; + + ret = true; } - return false; + if (new_version > c->sb.version_incompat && + c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible) { + struct printbuf buf = PRINTBUF; + + prt_str(&buf, "Now allowing incompatible features up to "); + bch2_version_to_text(&buf, new_version); + prt_str(&buf, ", previously allowed up to "); + bch2_version_to_text(&buf, c->sb.version_incompat_allowed); + prt_newline(&buf); + + bch_info(c, "%s", buf.buf); + printbuf_exit(&buf); + + ret = true; + } + + if (ret) + bch2_sb_upgrade(c, new_version, + c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible); + + return ret; } int bch2_fs_recovery(struct bch_fs *c) @@ -660,8 +727,13 @@ int bch2_fs_recovery(struct bch_fs *c) goto err; } - if (c->opts.norecovery) - c->opts.recovery_pass_last = BCH_RECOVERY_PASS_journal_replay - 1; + if (c->opts.norecovery) { + c->opts.recovery_pass_last = c->opts.recovery_pass_last + ? min(c->opts.recovery_pass_last, BCH_RECOVERY_PASS_snapshots_read) + : BCH_RECOVERY_PASS_snapshots_read; + c->opts.nochanges = true; + c->opts.read_only = true; + } mutex_lock(&c->sb_lock); struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); @@ -708,17 +780,20 @@ int bch2_fs_recovery(struct bch_fs *c) c->opts.recovery_passes |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); + if (c->sb.version_upgrade_complete < bcachefs_metadata_version_autofix_errors) { + SET_BCH_SB_ERROR_ACTION(c->disk_sb.sb, BCH_ON_ERROR_fix_safe); + write_sb = true; + } + if (write_sb) bch2_write_super(c); mutex_unlock(&c->sb_lock); - if (c->opts.fsck && IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_topology); - if (c->opts.fsck) set_bit(BCH_FS_fsck_running, &c->flags); if (c->sb.clean) set_bit(BCH_FS_clean_recovery, &c->flags); + set_bit(BCH_FS_recovery_running, &c->flags); ret = bch2_blacklist_table_initialize(c); if (ret) { @@ -807,15 +882,15 @@ use_clean: c->journal_replay_seq_start = last_seq; c->journal_replay_seq_end = blacklist_seq - 1; - if (c->opts.reconstruct_alloc) - bch2_reconstruct_alloc(c); - zero_out_btree_mem_ptr(&c->journal_keys); ret = journal_replay_early(c, clean); if (ret) goto err; + if (c->opts.reconstruct_alloc) + bch2_reconstruct_alloc(c); + /* * After an unclean shutdown, skip then next few journal sequence * numbers as they may have been referenced by btree writes that @@ -870,16 +945,17 @@ use_clean: */ set_bit(BCH_FS_may_go_rw, &c->flags); clear_bit(BCH_FS_fsck_running, &c->flags); + clear_bit(BCH_FS_recovery_running, &c->flags); /* in case we don't run journal replay, i.e. norecovery mode */ set_bit(BCH_FS_accounting_replay_done, &c->flags); + bch2_async_btree_node_rewrites_flush(c); + /* fsync if we fixed errors */ - if (test_bit(BCH_FS_errors_fixed, &c->flags) && - bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync)) { + if (test_bit(BCH_FS_errors_fixed, &c->flags)) { bch2_journal_flush_all_pins(&c->journal); bch2_journal_meta(&c->journal); - bch2_write_ref_put(c, BCH_WRITE_REF_fsync); } /* If we fixed errors, verify that fs is actually clean now: */ @@ -1021,7 +1097,7 @@ int bch2_fs_initialize(struct bch_fs *c) bch2_check_version_downgrade(c); if (c->opts.version_upgrade != BCH_VERSION_UPGRADE_none) { - bch2_sb_upgrade(c, bcachefs_metadata_version_current); + bch2_sb_upgrade(c, bcachefs_metadata_version_current, false); SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current); bch2_write_super(c); } @@ -1035,7 +1111,6 @@ int bch2_fs_initialize(struct bch_fs *c) bch2_write_super(c); mutex_unlock(&c->sb_lock); - c->curr_recovery_pass = BCH_RECOVERY_PASS_NR; set_bit(BCH_FS_btree_running, &c->flags); set_bit(BCH_FS_may_go_rw, &c->flags); @@ -1076,9 +1151,6 @@ int bch2_fs_initialize(struct bch_fs *c) if (ret) goto err; - for_each_online_member(c, ca) - ca->new_fs_bucket_idx = 0; - ret = bch2_fs_freespace_init(c); if (ret) goto err; @@ -1137,6 +1209,7 @@ int bch2_fs_initialize(struct bch_fs *c) bch2_write_super(c); mutex_unlock(&c->sb_lock); + c->curr_recovery_pass = BCH_RECOVERY_PASS_NR; return 0; err: bch_err_fn(c, ret); diff --git a/fs/bcachefs/recovery.h b/fs/bcachefs/recovery.h index 4bf818de1f2f..b0d55754b21b 100644 --- a/fs/bcachefs/recovery.h +++ b/fs/bcachefs/recovery.h @@ -2,7 +2,7 @@ #ifndef _BCACHEFS_RECOVERY_H #define _BCACHEFS_RECOVERY_H -void bch2_btree_lost_data(struct bch_fs *, enum btree_id); +int bch2_btree_lost_data(struct bch_fs *, enum btree_id); int bch2_journal_replay(struct bch_fs *); diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c index dff589ddc984..0b3c951c32da 100644 --- a/fs/bcachefs/recovery_passes.c +++ b/fs/bcachefs/recovery_passes.c @@ -46,7 +46,7 @@ static int bch2_set_may_go_rw(struct bch_fs *c) set_bit(BCH_FS_may_go_rw, &c->flags); - if (keys->nr || c->opts.fsck || !c->sb.clean || c->opts.recovery_passes) + if (keys->nr || !c->opts.read_only || c->opts.fsck || !c->sb.clean || c->opts.recovery_passes) return bch2_fs_read_write_early(c); return 0; } @@ -100,20 +100,34 @@ u64 bch2_recovery_passes_from_stable(u64 v) /* * For when we need to rewind recovery passes and run a pass we skipped: */ -int bch2_run_explicit_recovery_pass(struct bch_fs *c, - enum bch_recovery_pass pass) +static int __bch2_run_explicit_recovery_pass(struct bch_fs *c, + enum bch_recovery_pass pass) { - if (c->opts.recovery_passes & BIT_ULL(pass)) + if (c->curr_recovery_pass == ARRAY_SIZE(recovery_pass_fns)) + return -BCH_ERR_not_in_recovery; + + if (c->recovery_passes_complete & BIT_ULL(pass)) return 0; - bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)", - bch2_recovery_passes[pass], pass, - bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass); + bool print = !(c->opts.recovery_passes & BIT_ULL(pass)); + + if (pass < BCH_RECOVERY_PASS_set_may_go_rw && + c->curr_recovery_pass >= BCH_RECOVERY_PASS_set_may_go_rw) { + if (print) + bch_info(c, "need recovery pass %s (%u), but already rw", + bch2_recovery_passes[pass], pass); + return -BCH_ERR_cannot_rewind_recovery; + } + + if (print) + bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)", + bch2_recovery_passes[pass], pass, + bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass); c->opts.recovery_passes |= BIT_ULL(pass); - if (c->curr_recovery_pass >= pass) { - c->curr_recovery_pass = pass; + if (c->curr_recovery_pass > pass) { + c->next_recovery_pass = pass; c->recovery_passes_complete &= (1ULL << pass) >> 1; return -BCH_ERR_restart_recovery; } else { @@ -121,6 +135,27 @@ int bch2_run_explicit_recovery_pass(struct bch_fs *c, } } +int bch2_run_explicit_recovery_pass(struct bch_fs *c, + enum bch_recovery_pass pass) +{ + unsigned long flags; + spin_lock_irqsave(&c->recovery_pass_lock, flags); + int ret = __bch2_run_explicit_recovery_pass(c, pass); + spin_unlock_irqrestore(&c->recovery_pass_lock, flags); + return ret; +} + +int bch2_run_explicit_recovery_pass_persistent_locked(struct bch_fs *c, + enum bch_recovery_pass pass) +{ + lockdep_assert_held(&c->sb_lock); + + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); + __set_bit_le64(bch2_recovery_pass_to_stable(pass), ext->recovery_passes_required); + + return bch2_run_explicit_recovery_pass(c, pass); +} + int bch2_run_explicit_recovery_pass_persistent(struct bch_fs *c, enum bch_recovery_pass pass) { @@ -233,31 +268,48 @@ int bch2_run_recovery_passes(struct bch_fs *c) */ c->opts.recovery_passes_exclude &= ~BCH_RECOVERY_PASS_set_may_go_rw; - while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) { + while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) { + c->next_recovery_pass = c->curr_recovery_pass + 1; + + spin_lock_irq(&c->recovery_pass_lock); + unsigned pass = c->curr_recovery_pass; + if (c->opts.recovery_pass_last && - c->curr_recovery_pass > c->opts.recovery_pass_last) + c->curr_recovery_pass > c->opts.recovery_pass_last) { + spin_unlock_irq(&c->recovery_pass_lock); break; - - if (should_run_recovery_pass(c, c->curr_recovery_pass)) { - unsigned pass = c->curr_recovery_pass; - - ret = bch2_run_recovery_pass(c, c->curr_recovery_pass) ?: - bch2_journal_flush(&c->journal); - if (bch2_err_matches(ret, BCH_ERR_restart_recovery) || - (ret && c->curr_recovery_pass < pass)) - continue; - if (ret) - break; - - c->recovery_passes_complete |= BIT_ULL(c->curr_recovery_pass); } - c->recovery_pass_done = max(c->recovery_pass_done, c->curr_recovery_pass); + if (!should_run_recovery_pass(c, pass)) { + c->curr_recovery_pass++; + c->recovery_pass_done = max(c->recovery_pass_done, pass); + spin_unlock_irq(&c->recovery_pass_lock); + continue; + } + spin_unlock_irq(&c->recovery_pass_lock); - if (!test_bit(BCH_FS_error, &c->flags)) - bch2_clear_recovery_pass_required(c, c->curr_recovery_pass); + ret = bch2_run_recovery_pass(c, pass) ?: + bch2_journal_flush(&c->journal); - c->curr_recovery_pass++; + if (!ret && !test_bit(BCH_FS_error, &c->flags)) + bch2_clear_recovery_pass_required(c, pass); + + spin_lock_irq(&c->recovery_pass_lock); + if (c->next_recovery_pass < c->curr_recovery_pass) { + /* + * bch2_run_explicit_recovery_pass() was called: we + * can't always catch -BCH_ERR_restart_recovery because + * it may have been called from another thread (btree + * node read completion) + */ + ret = 0; + c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass); + } else { + c->recovery_passes_complete |= BIT_ULL(pass); + c->recovery_pass_done = max(c->recovery_pass_done, pass); + } + c->curr_recovery_pass = c->next_recovery_pass; + spin_unlock_irq(&c->recovery_pass_lock); } return ret; diff --git a/fs/bcachefs/recovery_passes.h b/fs/bcachefs/recovery_passes.h index 99b464e127b8..7d7339c8fa29 100644 --- a/fs/bcachefs/recovery_passes.h +++ b/fs/bcachefs/recovery_passes.h @@ -9,6 +9,7 @@ u64 bch2_recovery_passes_from_stable(u64 v); u64 bch2_fsck_recovery_passes(void); int bch2_run_explicit_recovery_pass(struct bch_fs *, enum bch_recovery_pass); +int bch2_run_explicit_recovery_pass_persistent_locked(struct bch_fs *, enum bch_recovery_pass); int bch2_run_explicit_recovery_pass_persistent(struct bch_fs *, enum bch_recovery_pass); int bch2_run_online_recovery_passes(struct bch_fs *); diff --git a/fs/bcachefs/recovery_passes_types.h b/fs/bcachefs/recovery_passes_types.h index 94dc20ca2065..418557960ed6 100644 --- a/fs/bcachefs/recovery_passes_types.h +++ b/fs/bcachefs/recovery_passes_types.h @@ -8,53 +8,59 @@ #define PASS_ALWAYS BIT(3) #define PASS_ONLINE BIT(4) +#ifdef CONFIG_BCACHEFS_DEBUG +#define PASS_FSCK_DEBUG BIT(1) +#else +#define PASS_FSCK_DEBUG 0 +#endif + /* * Passes may be reordered, but the second field is a persistent identifier and * must never change: */ -#define BCH_RECOVERY_PASSES() \ - x(recovery_pass_empty, 41, PASS_SILENT) \ - x(scan_for_btree_nodes, 37, 0) \ - x(check_topology, 4, 0) \ - x(accounting_read, 39, PASS_ALWAYS) \ - x(alloc_read, 0, PASS_ALWAYS) \ - x(stripes_read, 1, PASS_ALWAYS) \ - x(initialize_subvolumes, 2, 0) \ - x(snapshots_read, 3, PASS_ALWAYS) \ - x(check_allocations, 5, PASS_FSCK) \ - x(trans_mark_dev_sbs, 6, PASS_ALWAYS|PASS_SILENT) \ - x(fs_journal_alloc, 7, PASS_ALWAYS|PASS_SILENT) \ - x(set_may_go_rw, 8, PASS_ALWAYS|PASS_SILENT) \ - x(journal_replay, 9, PASS_ALWAYS) \ - x(check_alloc_info, 10, PASS_ONLINE|PASS_FSCK) \ - x(check_lrus, 11, PASS_ONLINE|PASS_FSCK) \ - x(check_btree_backpointers, 12, PASS_ONLINE|PASS_FSCK) \ - x(check_backpointers_to_extents, 13, PASS_ONLINE|PASS_FSCK) \ - x(check_extents_to_backpointers, 14, PASS_ONLINE|PASS_FSCK) \ - x(check_alloc_to_lru_refs, 15, PASS_ONLINE|PASS_FSCK) \ - x(fs_freespace_init, 16, PASS_ALWAYS|PASS_SILENT) \ - x(bucket_gens_init, 17, 0) \ - x(reconstruct_snapshots, 38, 0) \ - x(check_snapshot_trees, 18, PASS_ONLINE|PASS_FSCK) \ - x(check_snapshots, 19, PASS_ONLINE|PASS_FSCK) \ - x(check_subvols, 20, PASS_ONLINE|PASS_FSCK) \ - x(check_subvol_children, 35, PASS_ONLINE|PASS_FSCK) \ - x(delete_dead_snapshots, 21, PASS_ONLINE|PASS_FSCK) \ - x(fs_upgrade_for_subvolumes, 22, 0) \ - x(check_inodes, 24, PASS_FSCK) \ - x(check_extents, 25, PASS_FSCK) \ - x(check_indirect_extents, 26, PASS_FSCK) \ - x(check_dirents, 27, PASS_FSCK) \ - x(check_xattrs, 28, PASS_FSCK) \ - x(check_root, 29, PASS_ONLINE|PASS_FSCK) \ - x(check_unreachable_inodes, 40, PASS_ONLINE|PASS_FSCK) \ - x(check_subvolume_structure, 36, PASS_ONLINE|PASS_FSCK) \ - x(check_directory_structure, 30, PASS_ONLINE|PASS_FSCK) \ - x(check_nlinks, 31, PASS_FSCK) \ - x(resume_logged_ops, 23, PASS_ALWAYS) \ - x(delete_dead_inodes, 32, PASS_ALWAYS) \ - x(fix_reflink_p, 33, 0) \ - x(set_fs_needs_rebalance, 34, 0) \ +#define BCH_RECOVERY_PASSES() \ + x(recovery_pass_empty, 41, PASS_SILENT) \ + x(scan_for_btree_nodes, 37, 0) \ + x(check_topology, 4, 0) \ + x(accounting_read, 39, PASS_ALWAYS) \ + x(alloc_read, 0, PASS_ALWAYS) \ + x(stripes_read, 1, PASS_ALWAYS) \ + x(initialize_subvolumes, 2, 0) \ + x(snapshots_read, 3, PASS_ALWAYS) \ + x(check_allocations, 5, PASS_FSCK) \ + x(trans_mark_dev_sbs, 6, PASS_ALWAYS|PASS_SILENT) \ + x(fs_journal_alloc, 7, PASS_ALWAYS|PASS_SILENT) \ + x(set_may_go_rw, 8, PASS_ALWAYS|PASS_SILENT) \ + x(journal_replay, 9, PASS_ALWAYS) \ + x(check_alloc_info, 10, PASS_ONLINE|PASS_FSCK) \ + x(check_lrus, 11, PASS_ONLINE|PASS_FSCK) \ + x(check_btree_backpointers, 12, PASS_ONLINE|PASS_FSCK) \ + x(check_backpointers_to_extents, 13, PASS_ONLINE|PASS_FSCK_DEBUG) \ + x(check_extents_to_backpointers, 14, PASS_ONLINE|PASS_FSCK) \ + x(check_alloc_to_lru_refs, 15, PASS_ONLINE|PASS_FSCK) \ + x(fs_freespace_init, 16, PASS_ALWAYS|PASS_SILENT) \ + x(bucket_gens_init, 17, 0) \ + x(reconstruct_snapshots, 38, 0) \ + x(check_snapshot_trees, 18, PASS_ONLINE|PASS_FSCK) \ + x(check_snapshots, 19, PASS_ONLINE|PASS_FSCK) \ + x(check_subvols, 20, PASS_ONLINE|PASS_FSCK) \ + x(check_subvol_children, 35, PASS_ONLINE|PASS_FSCK) \ + x(delete_dead_snapshots, 21, PASS_ONLINE|PASS_FSCK) \ + x(fs_upgrade_for_subvolumes, 22, 0) \ + x(check_inodes, 24, PASS_FSCK) \ + x(check_extents, 25, PASS_FSCK) \ + x(check_indirect_extents, 26, PASS_ONLINE|PASS_FSCK) \ + x(check_dirents, 27, PASS_FSCK) \ + x(check_xattrs, 28, PASS_FSCK) \ + x(check_root, 29, PASS_ONLINE|PASS_FSCK) \ + x(check_unreachable_inodes, 40, PASS_FSCK) \ + x(check_subvolume_structure, 36, PASS_ONLINE|PASS_FSCK) \ + x(check_directory_structure, 30, PASS_ONLINE|PASS_FSCK) \ + x(check_nlinks, 31, PASS_FSCK) \ + x(resume_logged_ops, 23, PASS_ALWAYS) \ + x(delete_dead_inodes, 32, PASS_ALWAYS) \ + x(fix_reflink_p, 33, 0) \ + x(set_fs_needs_rebalance, 34, 0) /* We normally enumerate recovery passes in the order we run them: */ enum bch_recovery_pass { diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index f457925fa362..93ba4f4e47ca 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -15,6 +15,17 @@ #include +static inline bool bkey_extent_is_reflink_data(const struct bkey *k) +{ + switch (k->type) { + case KEY_TYPE_reflink_v: + case KEY_TYPE_indirect_inline_data: + return true; + default: + return false; + } +} + static inline unsigned bkey_type_to_indirect(const struct bkey *k) { switch (k->type) { @@ -30,15 +41,15 @@ static inline unsigned bkey_type_to_indirect(const struct bkey *k) /* reflink pointers */ int bch2_reflink_p_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); int ret = 0; - bkey_fsck_err_on(le64_to_cpu(p.v->idx) < le32_to_cpu(p.v->front_pad), + bkey_fsck_err_on(REFLINK_P_IDX(p.v) < le32_to_cpu(p.v->front_pad), c, reflink_p_front_pad_bad, "idx < front_pad (%llu < %u)", - le64_to_cpu(p.v->idx), le32_to_cpu(p.v->front_pad)); + REFLINK_P_IDX(p.v), le32_to_cpu(p.v->front_pad)); fsck_err: return ret; } @@ -49,7 +60,7 @@ void bch2_reflink_p_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); prt_printf(out, "idx %llu front_pad %u back_pad %u", - le64_to_cpu(p.v->idx), + REFLINK_P_IDX(p.v), le32_to_cpu(p.v->front_pad), le32_to_cpu(p.v->back_pad)); } @@ -65,49 +76,250 @@ bool bch2_reflink_p_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r */ return false; - if (le64_to_cpu(l.v->idx) + l.k->size != le64_to_cpu(r.v->idx)) + if (REFLINK_P_IDX(l.v) + l.k->size != REFLINK_P_IDX(r.v)) + return false; + + if (REFLINK_P_ERROR(l.v) != REFLINK_P_ERROR(r.v)) return false; bch2_key_resize(l.k, l.k->size + r.k->size); return true; } +/* indirect extents */ + +int bch2_reflink_v_validate(struct bch_fs *c, struct bkey_s_c k, + struct bkey_validate_context from) +{ + int ret = 0; + + bkey_fsck_err_on(bkey_gt(k.k->p, POS(0, REFLINK_P_IDX_MAX)), + c, reflink_v_pos_bad, + "indirect extent above maximum position 0:%llu", + REFLINK_P_IDX_MAX); + + ret = bch2_bkey_ptrs_validate(c, k, from); +fsck_err: + return ret; +} + +void bch2_reflink_v_to_text(struct printbuf *out, struct bch_fs *c, + struct bkey_s_c k) +{ + struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(k); + + prt_printf(out, "refcount: %llu ", le64_to_cpu(r.v->refcount)); + + bch2_bkey_ptrs_to_text(out, c, k); +} + +#if 0 +Currently disabled, needs to be debugged: + +bool bch2_reflink_v_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r) +{ + struct bkey_s_reflink_v l = bkey_s_to_reflink_v(_l); + struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(_r); + + return l.v->refcount == r.v->refcount && bch2_extent_merge(c, _l, _r); +} +#endif + +/* indirect inline data */ + +int bch2_indirect_inline_data_validate(struct bch_fs *c, struct bkey_s_c k, + struct bkey_validate_context from) +{ + return 0; +} + +void bch2_indirect_inline_data_to_text(struct printbuf *out, + struct bch_fs *c, struct bkey_s_c k) +{ + struct bkey_s_c_indirect_inline_data d = bkey_s_c_to_indirect_inline_data(k); + unsigned datalen = bkey_inline_data_bytes(k.k); + + prt_printf(out, "refcount %llu datalen %u: %*phN", + le64_to_cpu(d.v->refcount), datalen, + min(datalen, 32U), d.v->data); +} + +/* lookup */ + +static int bch2_indirect_extent_not_missing(struct btree_trans *trans, struct bkey_s_c_reflink_p p, + bool should_commit) +{ + struct bkey_i_reflink_p *new = bch2_bkey_make_mut_noupdate_typed(trans, p.s_c, reflink_p); + int ret = PTR_ERR_OR_ZERO(new); + if (ret) + return ret; + + SET_REFLINK_P_ERROR(&new->v, false); + ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, &new->k_i, BTREE_TRIGGER_norun); + if (ret) + return ret; + + if (!should_commit) + return 0; + + return bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_nested; +} + +static int bch2_indirect_extent_missing_error(struct btree_trans *trans, + struct bkey_s_c_reflink_p p, + u64 missing_start, u64 missing_end, + bool should_commit) +{ + if (REFLINK_P_ERROR(p.v)) + return -BCH_ERR_missing_indirect_extent; + + struct bch_fs *c = trans->c; + u64 live_start = REFLINK_P_IDX(p.v); + u64 live_end = REFLINK_P_IDX(p.v) + p.k->size; + u64 refd_start = live_start - le32_to_cpu(p.v->front_pad); + u64 refd_end = live_end + le32_to_cpu(p.v->back_pad); + struct printbuf buf = PRINTBUF; + int ret = 0; + + BUG_ON(missing_start < refd_start); + BUG_ON(missing_end > refd_end); + + if (fsck_err(trans, reflink_p_to_missing_reflink_v, + "pointer to missing indirect extent\n" + " %s\n" + " missing range %llu-%llu", + (bch2_bkey_val_to_text(&buf, c, p.s_c), buf.buf), + missing_start, missing_end)) { + struct bkey_i_reflink_p *new = bch2_bkey_make_mut_noupdate_typed(trans, p.s_c, reflink_p); + ret = PTR_ERR_OR_ZERO(new); + if (ret) + goto err; + + /* + * Is the missing range not actually needed? + * + * p.v->idx refers to the data that we actually want, but if the + * indirect extent we point to was bigger, front_pad and back_pad + * indicate the range we took a reference on. + */ + + if (missing_end <= live_start) { + new->v.front_pad = cpu_to_le32(live_start - missing_end); + } else if (missing_start >= live_end) { + new->v.back_pad = cpu_to_le32(missing_start - live_end); + } else { + struct bpos new_start = bkey_start_pos(&new->k); + struct bpos new_end = new->k.p; + + if (missing_start > live_start) + new_start.offset += missing_start - live_start; + if (missing_end < live_end) + new_end.offset -= live_end - missing_end; + + bch2_cut_front(new_start, &new->k_i); + bch2_cut_back(new_end, &new->k_i); + + SET_REFLINK_P_ERROR(&new->v, true); + } + + ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, &new->k_i, BTREE_TRIGGER_norun); + if (ret) + goto err; + + if (should_commit) + ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_nested; + } +err: +fsck_err: + printbuf_exit(&buf); + return ret; +} + +/* + * This is used from the read path, which doesn't expect to have to do a + * transaction commit, and from triggers, which should not be doing a commit: + */ +struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, + struct btree_iter *iter, + s64 *offset_into_extent, + struct bkey_s_c_reflink_p p, + bool should_commit, + unsigned iter_flags) +{ + BUG_ON(*offset_into_extent < -((s64) le32_to_cpu(p.v->front_pad))); + BUG_ON(*offset_into_extent >= p.k->size + le32_to_cpu(p.v->back_pad)); + + u64 reflink_offset = REFLINK_P_IDX(p.v) + *offset_into_extent; + + struct bkey_s_c k = bch2_bkey_get_iter(trans, iter, BTREE_ID_reflink, + POS(0, reflink_offset), iter_flags); + if (bkey_err(k)) + return k; + + if (unlikely(!bkey_extent_is_reflink_data(k.k))) { + bch2_trans_iter_exit(trans, iter); + + unsigned size = min((u64) k.k->size, + REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad) - + reflink_offset); + bch2_key_resize(&iter->k, size); + + int ret = bch2_indirect_extent_missing_error(trans, p, reflink_offset, + k.k->p.offset, should_commit); + if (ret) + return bkey_s_c_err(ret); + } else if (unlikely(REFLINK_P_ERROR(p.v))) { + bch2_trans_iter_exit(trans, iter); + + int ret = bch2_indirect_extent_not_missing(trans, p, should_commit); + if (ret) + return bkey_s_c_err(ret); + } + + *offset_into_extent = reflink_offset - bkey_start_offset(k.k); + return k; +} + +/* reflink pointer trigger */ + static int trans_trigger_reflink_p_segment(struct btree_trans *trans, struct bkey_s_c_reflink_p p, u64 *idx, enum btree_iter_update_trigger_flags flags) { struct bch_fs *c = trans->c; - struct btree_iter iter; - struct bkey_i *k; - __le64 *refcount; - int add = !(flags & BTREE_TRIGGER_overwrite) ? 1 : -1; struct printbuf buf = PRINTBUF; - int ret; - k = bch2_bkey_get_mut_noupdate(trans, &iter, - BTREE_ID_reflink, POS(0, *idx), - BTREE_ITER_with_updates); - ret = PTR_ERR_OR_ZERO(k); + s64 offset_into_extent = *idx - REFLINK_P_IDX(p.v); + struct btree_iter iter; + struct bkey_s_c k = bch2_lookup_indirect_extent(trans, &iter, &offset_into_extent, p, false, + BTREE_ITER_intent| + BTREE_ITER_with_updates); + int ret = bkey_err(k); + if (ret) + return ret; + + if (bkey_deleted(k.k)) { + if (!(flags & BTREE_TRIGGER_overwrite)) + ret = -BCH_ERR_missing_indirect_extent; + goto next; + } + + struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); + ret = PTR_ERR_OR_ZERO(new); if (ret) goto err; - refcount = bkey_refcount(bkey_i_to_s(k)); - if (!refcount) { - bch2_bkey_val_to_text(&buf, c, p.s_c); - bch2_trans_inconsistent(trans, - "nonexistent indirect extent at %llu while marking\n %s", - *idx, buf.buf); - ret = -EIO; - goto err; - } - + __le64 *refcount = bkey_refcount(bkey_i_to_s(new)); if (!*refcount && (flags & BTREE_TRIGGER_overwrite)) { bch2_bkey_val_to_text(&buf, c, p.s_c); - bch2_trans_inconsistent(trans, - "indirect extent refcount underflow at %llu while marking\n %s", - *idx, buf.buf); - ret = -EIO; - goto err; + prt_printf(&buf, "\n "); + bch2_bkey_val_to_text(&buf, c, k); + log_fsck_err(trans, reflink_refcount_underflow, + "indirect extent refcount underflow while marking\n %s", + buf.buf); + goto next; } if (flags & BTREE_TRIGGER_insert) { @@ -115,25 +327,26 @@ static int trans_trigger_reflink_p_segment(struct btree_trans *trans, u64 pad; pad = max_t(s64, le32_to_cpu(v->front_pad), - le64_to_cpu(v->idx) - bkey_start_offset(&k->k)); + REFLINK_P_IDX(v) - bkey_start_offset(&new->k)); BUG_ON(pad > U32_MAX); v->front_pad = cpu_to_le32(pad); pad = max_t(s64, le32_to_cpu(v->back_pad), - k->k.p.offset - p.k->size - le64_to_cpu(v->idx)); + new->k.p.offset - p.k->size - REFLINK_P_IDX(v)); BUG_ON(pad > U32_MAX); v->back_pad = cpu_to_le32(pad); } - le64_add_cpu(refcount, add); + le64_add_cpu(refcount, !(flags & BTREE_TRIGGER_overwrite) ? 1 : -1); bch2_btree_iter_set_pos_to_extent_start(&iter); - ret = bch2_trans_update(trans, &iter, k, 0); + ret = bch2_trans_update(trans, &iter, new, 0); if (ret) goto err; - - *idx = k->k.p.offset; +next: + *idx = k.k->p.offset; err: +fsck_err: bch2_trans_iter_exit(trans, &iter); printbuf_exit(&buf); return ret; @@ -147,9 +360,7 @@ static s64 gc_trigger_reflink_p_segment(struct btree_trans *trans, struct bch_fs *c = trans->c; struct reflink_gc *r; int add = !(flags & BTREE_TRIGGER_overwrite) ? 1 : -1; - u64 start = le64_to_cpu(p.v->idx); - u64 end = le64_to_cpu(p.v->idx) + p.k->size; - u64 next_idx = end + le32_to_cpu(p.v->back_pad); + u64 next_idx = REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad); s64 ret = 0; struct printbuf buf = PRINTBUF; @@ -168,36 +379,14 @@ static s64 gc_trigger_reflink_p_segment(struct btree_trans *trans, *idx = r->offset; return 0; not_found: - BUG_ON(!(flags & BTREE_TRIGGER_check_repair)); - - if (fsck_err(trans, reflink_p_to_missing_reflink_v, - "pointer to missing indirect extent\n" - " %s\n" - " missing range %llu-%llu", - (bch2_bkey_val_to_text(&buf, c, p.s_c), buf.buf), - *idx, next_idx)) { - struct bkey_i *update = bch2_bkey_make_mut_noupdate(trans, p.s_c); - ret = PTR_ERR_OR_ZERO(update); + if (flags & BTREE_TRIGGER_check_repair) { + ret = bch2_indirect_extent_missing_error(trans, p, *idx, next_idx, false); if (ret) goto err; - - if (next_idx <= start) { - bkey_i_to_reflink_p(update)->v.front_pad = cpu_to_le32(start - next_idx); - } else if (*idx >= end) { - bkey_i_to_reflink_p(update)->v.back_pad = cpu_to_le32(*idx - end); - } else { - bkey_error_init(update); - update->k.p = p.k->p; - update->k.size = p.k->size; - set_bkey_val_u64s(&update->k, 0); - } - - ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, update, BTREE_TRIGGER_norun); } *idx = next_idx; err: -fsck_err: printbuf_exit(&buf); return ret; } @@ -210,8 +399,8 @@ static int __trigger_reflink_p(struct btree_trans *trans, struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); int ret = 0; - u64 idx = le64_to_cpu(p.v->idx) - le32_to_cpu(p.v->front_pad); - u64 end = le64_to_cpu(p.v->idx) + p.k->size + le32_to_cpu(p.v->back_pad); + u64 idx = REFLINK_P_IDX(p.v) - le32_to_cpu(p.v->front_pad); + u64 end = REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad); if (flags & BTREE_TRIGGER_transactional) { while (idx < end && !ret) @@ -253,35 +442,7 @@ int bch2_trigger_reflink_p(struct btree_trans *trans, return trigger_run_overwrite_then_insert(__trigger_reflink_p, trans, btree_id, level, old, new, flags); } -/* indirect extents */ - -int bch2_reflink_v_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) -{ - return bch2_bkey_ptrs_validate(c, k, flags); -} - -void bch2_reflink_v_to_text(struct printbuf *out, struct bch_fs *c, - struct bkey_s_c k) -{ - struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(k); - - prt_printf(out, "refcount: %llu ", le64_to_cpu(r.v->refcount)); - - bch2_bkey_ptrs_to_text(out, c, k); -} - -#if 0 -Currently disabled, needs to be debugged: - -bool bch2_reflink_v_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r) -{ - struct bkey_s_reflink_v l = bkey_s_to_reflink_v(_l); - struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(_r); - - return l.v->refcount == r.v->refcount && bch2_extent_merge(c, _l, _r); -} -#endif +/* indirect extent trigger */ static inline void check_indirect_extent_deleting(struct bkey_s new, @@ -307,25 +468,6 @@ int bch2_trigger_reflink_v(struct btree_trans *trans, return bch2_trigger_extent(trans, btree_id, level, old, new, flags); } -/* indirect inline data */ - -int bch2_indirect_inline_data_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) -{ - return 0; -} - -void bch2_indirect_inline_data_to_text(struct printbuf *out, - struct bch_fs *c, struct bkey_s_c k) -{ - struct bkey_s_c_indirect_inline_data d = bkey_s_c_to_indirect_inline_data(k); - unsigned datalen = bkey_inline_data_bytes(k.k); - - prt_printf(out, "refcount %llu datalen %u: %*phN", - le64_to_cpu(d.v->refcount), datalen, - min(datalen, 32U), d.v->data); -} - int bch2_trigger_indirect_inline_data(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c old, struct bkey_s new, @@ -336,9 +478,12 @@ int bch2_trigger_indirect_inline_data(struct btree_trans *trans, return 0; } +/* create */ + static int bch2_make_extent_indirect(struct btree_trans *trans, struct btree_iter *extent_iter, - struct bkey_i *orig) + struct bkey_i *orig, + bool reflink_p_may_update_opts_field) { struct bch_fs *c = trans->c; struct btree_iter reflink_iter = { NULL }; @@ -358,6 +503,14 @@ static int bch2_make_extent_indirect(struct btree_trans *trans, if (ret) goto err; + /* + * XXX: we're assuming that 56 bits will be enough for the life of the + * filesystem: we need to implement wraparound, with a cursor in the + * logged ops btree: + */ + if (bkey_ge(reflink_iter.pos, POS(0, REFLINK_P_IDX_MAX - orig->k.size))) + return -ENOSPC; + r_v = bch2_trans_kmalloc(trans, sizeof(__le64) + bkey_bytes(&orig->k)); ret = PTR_ERR_OR_ZERO(r_v); if (ret) @@ -394,7 +547,10 @@ static int bch2_make_extent_indirect(struct btree_trans *trans, memset(&r_p->v, 0, sizeof(r_p->v)); #endif - r_p->v.idx = cpu_to_le64(bkey_start_offset(&r_v->k)); + SET_REFLINK_P_IDX(&r_p->v, bkey_start_offset(&r_v->k)); + + if (reflink_p_may_update_opts_field) + SET_REFLINK_P_MAY_UPDATE_OPTIONS(&r_p->v, true); ret = bch2_trans_update(trans, extent_iter, &r_p->k_i, BTREE_UPDATE_internal_snapshot_node); @@ -409,7 +565,7 @@ static struct bkey_s_c get_next_src(struct btree_iter *iter, struct bpos end) struct bkey_s_c k; int ret; - for_each_btree_key_upto_continue_norestart(*iter, end, 0, k, ret) { + for_each_btree_key_max_continue_norestart(*iter, end, 0, k, ret) { if (bkey_extent_is_unwritten(k)) continue; @@ -426,7 +582,8 @@ s64 bch2_remap_range(struct bch_fs *c, subvol_inum dst_inum, u64 dst_offset, subvol_inum src_inum, u64 src_offset, u64 remap_sectors, - u64 new_i_size, s64 *i_sectors_delta) + u64 new_i_size, s64 *i_sectors_delta, + bool may_change_src_io_path_opts) { struct btree_trans *trans; struct btree_iter dst_iter, src_iter; @@ -439,6 +596,8 @@ s64 bch2_remap_range(struct bch_fs *c, struct bpos src_want; u64 dst_done = 0; u32 dst_snapshot, src_snapshot; + bool reflink_p_may_update_opts_field = + bch2_request_incompat_feature(c, bcachefs_metadata_version_reflink_p_may_update_opts); int ret = 0, ret2 = 0; if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_reflink)) @@ -520,7 +679,8 @@ s64 bch2_remap_range(struct bch_fs *c, src_k = bkey_i_to_s_c(new_src.k); ret = bch2_make_extent_indirect(trans, &src_iter, - new_src.k); + new_src.k, + reflink_p_may_update_opts_field); if (ret) continue; @@ -533,11 +693,15 @@ s64 bch2_remap_range(struct bch_fs *c, struct bkey_i_reflink_p *dst_p = bkey_reflink_p_init(new_dst.k); - u64 offset = le64_to_cpu(src_p.v->idx) + + u64 offset = REFLINK_P_IDX(src_p.v) + (src_want.offset - bkey_start_offset(src_k.k)); - dst_p->v.idx = cpu_to_le64(offset); + SET_REFLINK_P_IDX(&dst_p->v, offset); + + if (reflink_p_may_update_opts_field && + may_change_src_io_path_opts) + SET_REFLINK_P_MAY_UPDATE_OPTIONS(&dst_p->v, true); } else { BUG(); } @@ -547,7 +711,7 @@ s64 bch2_remap_range(struct bch_fs *c, min(src_k.k->p.offset - src_want.offset, dst_end.offset - dst_iter.pos.offset)); - ret = bch2_bkey_set_needs_rebalance(c, new_dst.k, &opts) ?: + ret = bch2_bkey_set_needs_rebalance(c, &opts, new_dst.k) ?: bch2_extent_update(trans, dst_inum, &dst_iter, new_dst.k, &disk_res, new_i_size, i_sectors_delta, @@ -591,3 +755,97 @@ err: return dst_done ?: ret ?: ret2; } + +/* fsck */ + +static int bch2_gc_write_reflink_key(struct btree_trans *trans, + struct btree_iter *iter, + struct bkey_s_c k, + size_t *idx) +{ + struct bch_fs *c = trans->c; + const __le64 *refcount = bkey_refcount_c(k); + struct printbuf buf = PRINTBUF; + struct reflink_gc *r; + int ret = 0; + + if (!refcount) + return 0; + + while ((r = genradix_ptr(&c->reflink_gc_table, *idx)) && + r->offset < k.k->p.offset) + ++*idx; + + if (!r || + r->offset != k.k->p.offset || + r->size != k.k->size) { + bch_err(c, "unexpected inconsistency walking reflink table at gc finish"); + return -EINVAL; + } + + if (fsck_err_on(r->refcount != le64_to_cpu(*refcount), + trans, reflink_v_refcount_wrong, + "reflink key has wrong refcount:\n" + " %s\n" + " should be %u", + (bch2_bkey_val_to_text(&buf, c, k), buf.buf), + r->refcount)) { + struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); + ret = PTR_ERR_OR_ZERO(new); + if (ret) + goto out; + + if (!r->refcount) + new->k.type = KEY_TYPE_deleted; + else + *bkey_refcount(bkey_i_to_s(new)) = cpu_to_le64(r->refcount); + ret = bch2_trans_update(trans, iter, new, 0); + } +out: +fsck_err: + printbuf_exit(&buf); + return ret; +} + +int bch2_gc_reflink_done(struct bch_fs *c) +{ + size_t idx = 0; + + int ret = bch2_trans_run(c, + for_each_btree_key_commit(trans, iter, + BTREE_ID_reflink, POS_MIN, + BTREE_ITER_prefetch, k, + NULL, NULL, BCH_TRANS_COMMIT_no_enospc, + bch2_gc_write_reflink_key(trans, &iter, k, &idx))); + c->reflink_gc_nr = 0; + return ret; +} + +int bch2_gc_reflink_start(struct bch_fs *c) +{ + c->reflink_gc_nr = 0; + + int ret = bch2_trans_run(c, + for_each_btree_key(trans, iter, BTREE_ID_reflink, POS_MIN, + BTREE_ITER_prefetch, k, ({ + const __le64 *refcount = bkey_refcount_c(k); + + if (!refcount) + continue; + + struct reflink_gc *r = genradix_ptr_alloc(&c->reflink_gc_table, + c->reflink_gc_nr++, GFP_KERNEL); + if (!r) { + ret = -BCH_ERR_ENOMEM_gc_reflink_start; + break; + } + + r->offset = k.k->p.offset; + r->size = k.k->size; + r->refcount = 0; + 0; + }))); + + bch_err_fn(c, ret); + return ret; +} diff --git a/fs/bcachefs/reflink.h b/fs/bcachefs/reflink.h index 51afe11d8ed6..1632780bdf18 100644 --- a/fs/bcachefs/reflink.h +++ b/fs/bcachefs/reflink.h @@ -2,9 +2,8 @@ #ifndef _BCACHEFS_REFLINK_H #define _BCACHEFS_REFLINK_H -enum bch_validate_flags; - -int bch2_reflink_p_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_reflink_p_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_reflink_p_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); bool bch2_reflink_p_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); int bch2_trigger_reflink_p(struct btree_trans *, enum btree_id, unsigned, @@ -19,7 +18,8 @@ int bch2_trigger_reflink_p(struct btree_trans *, enum btree_id, unsigned, .min_val_size = 16, \ }) -int bch2_reflink_v_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_reflink_v_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_reflink_v(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, @@ -34,7 +34,7 @@ int bch2_trigger_reflink_v(struct btree_trans *, enum btree_id, unsigned, }) int bch2_indirect_inline_data_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_indirect_inline_data_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_indirect_inline_data(struct btree_trans *, @@ -73,7 +73,15 @@ static inline __le64 *bkey_refcount(struct bkey_s k) } } +struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *, struct btree_iter *, + s64 *, struct bkey_s_c_reflink_p, + bool, unsigned); + s64 bch2_remap_range(struct bch_fs *, subvol_inum, u64, - subvol_inum, u64, u64, u64, s64 *); + subvol_inum, u64, u64, u64, s64 *, + bool); + +int bch2_gc_reflink_done(struct bch_fs *); +int bch2_gc_reflink_start(struct bch_fs *); #endif /* _BCACHEFS_REFLINK_H */ diff --git a/fs/bcachefs/reflink_format.h b/fs/bcachefs/reflink_format.h index 6772eebb1fc6..92995e4f898e 100644 --- a/fs/bcachefs/reflink_format.h +++ b/fs/bcachefs/reflink_format.h @@ -4,7 +4,7 @@ struct bch_reflink_p { struct bch_val v; - __le64 idx; + __le64 idx_flags; /* * A reflink pointer might point to an indirect extent which is then * later split (by copygc or rebalance). If we only pointed to part of @@ -17,6 +17,11 @@ struct bch_reflink_p { __le32 back_pad; } __packed __aligned(8); +LE64_BITMASK(REFLINK_P_IDX, struct bch_reflink_p, idx_flags, 0, 56); +LE64_BITMASK(REFLINK_P_ERROR, struct bch_reflink_p, idx_flags, 56, 57); +LE64_BITMASK(REFLINK_P_MAY_UPDATE_OPTIONS, + struct bch_reflink_p, idx_flags, 57, 58); + struct bch_reflink_v { struct bch_val v; __le64 refcount; diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c index 005275281804..59c8770e4a0e 100644 --- a/fs/bcachefs/sb-clean.c +++ b/fs/bcachefs/sb-clean.c @@ -23,6 +23,10 @@ int bch2_sb_clean_validate_late(struct bch_fs *c, struct bch_sb_field_clean *clean, int write) { + struct bkey_validate_context from = { + .flags = write, + .from = BKEY_VALIDATE_superblock, + }; struct jset_entry *entry; int ret; @@ -40,7 +44,7 @@ int bch2_sb_clean_validate_late(struct bch_fs *c, struct bch_sb_field_clean *cle ret = bch2_journal_entry_validate(c, NULL, entry, le16_to_cpu(c->disk_sb.sb->version), BCH_SB_BIG_ENDIAN(c->disk_sb.sb), - write); + from); if (ret) return ret; } diff --git a/fs/bcachefs/sb-counters_format.h b/fs/bcachefs/sb-counters_format.h index 62ea478215d0..fdcf598f08b1 100644 --- a/fs/bcachefs/sb-counters_format.h +++ b/fs/bcachefs/sb-counters_format.h @@ -2,86 +2,91 @@ #ifndef _BCACHEFS_SB_COUNTERS_FORMAT_H #define _BCACHEFS_SB_COUNTERS_FORMAT_H -#define BCH_PERSISTENT_COUNTERS() \ - x(io_read, 0) \ - x(io_write, 1) \ - x(io_move, 2) \ - x(bucket_invalidate, 3) \ - x(bucket_discard, 4) \ - x(bucket_alloc, 5) \ - x(bucket_alloc_fail, 6) \ - x(btree_cache_scan, 7) \ - x(btree_cache_reap, 8) \ - x(btree_cache_cannibalize, 9) \ - x(btree_cache_cannibalize_lock, 10) \ - x(btree_cache_cannibalize_lock_fail, 11) \ - x(btree_cache_cannibalize_unlock, 12) \ - x(btree_node_write, 13) \ - x(btree_node_read, 14) \ - x(btree_node_compact, 15) \ - x(btree_node_merge, 16) \ - x(btree_node_split, 17) \ - x(btree_node_rewrite, 18) \ - x(btree_node_alloc, 19) \ - x(btree_node_free, 20) \ - x(btree_node_set_root, 21) \ - x(btree_path_relock_fail, 22) \ - x(btree_path_upgrade_fail, 23) \ - x(btree_reserve_get_fail, 24) \ - x(journal_entry_full, 25) \ - x(journal_full, 26) \ - x(journal_reclaim_finish, 27) \ - x(journal_reclaim_start, 28) \ - x(journal_write, 29) \ - x(read_promote, 30) \ - x(read_bounce, 31) \ - x(read_split, 33) \ - x(read_retry, 32) \ - x(read_reuse_race, 34) \ - x(move_extent_read, 35) \ - x(move_extent_write, 36) \ - x(move_extent_finish, 37) \ - x(move_extent_fail, 38) \ - x(move_extent_start_fail, 39) \ - x(copygc, 40) \ - x(copygc_wait, 41) \ - x(gc_gens_end, 42) \ - x(gc_gens_start, 43) \ - x(trans_blocked_journal_reclaim, 44) \ - x(trans_restart_btree_node_reused, 45) \ - x(trans_restart_btree_node_split, 46) \ - x(trans_restart_fault_inject, 47) \ - x(trans_restart_iter_upgrade, 48) \ - x(trans_restart_journal_preres_get, 49) \ - x(trans_restart_journal_reclaim, 50) \ - x(trans_restart_journal_res_get, 51) \ - x(trans_restart_key_cache_key_realloced, 52) \ - x(trans_restart_key_cache_raced, 53) \ - x(trans_restart_mark_replicas, 54) \ - x(trans_restart_mem_realloced, 55) \ - x(trans_restart_memory_allocation_failure, 56) \ - x(trans_restart_relock, 57) \ - x(trans_restart_relock_after_fill, 58) \ - x(trans_restart_relock_key_cache_fill, 59) \ - x(trans_restart_relock_next_node, 60) \ - x(trans_restart_relock_parent_for_fill, 61) \ - x(trans_restart_relock_path, 62) \ - x(trans_restart_relock_path_intent, 63) \ - x(trans_restart_too_many_iters, 64) \ - x(trans_restart_traverse, 65) \ - x(trans_restart_upgrade, 66) \ - x(trans_restart_would_deadlock, 67) \ - x(trans_restart_would_deadlock_write, 68) \ - x(trans_restart_injected, 69) \ - x(trans_restart_key_cache_upgrade, 70) \ - x(trans_traverse_all, 71) \ - x(transaction_commit, 72) \ - x(write_super, 73) \ - x(trans_restart_would_deadlock_recursion_limit, 74) \ - x(trans_restart_write_buffer_flush, 75) \ - x(trans_restart_split_race, 76) \ - x(write_buffer_flush_slowpath, 77) \ - x(write_buffer_flush_sync, 78) +enum counters_flags { + TYPE_COUNTER = BIT(0), /* event counters */ + TYPE_SECTORS = BIT(1), /* amount counters, the unit is sectors */ +}; + +#define BCH_PERSISTENT_COUNTERS() \ + x(io_read, 0, TYPE_SECTORS) \ + x(io_write, 1, TYPE_SECTORS) \ + x(io_move, 2, TYPE_SECTORS) \ + x(bucket_invalidate, 3, TYPE_COUNTER) \ + x(bucket_discard, 4, TYPE_COUNTER) \ + x(bucket_alloc, 5, TYPE_COUNTER) \ + x(bucket_alloc_fail, 6, TYPE_COUNTER) \ + x(btree_cache_scan, 7, TYPE_COUNTER) \ + x(btree_cache_reap, 8, TYPE_COUNTER) \ + x(btree_cache_cannibalize, 9, TYPE_COUNTER) \ + x(btree_cache_cannibalize_lock, 10, TYPE_COUNTER) \ + x(btree_cache_cannibalize_lock_fail, 11, TYPE_COUNTER) \ + x(btree_cache_cannibalize_unlock, 12, TYPE_COUNTER) \ + x(btree_node_write, 13, TYPE_COUNTER) \ + x(btree_node_read, 14, TYPE_COUNTER) \ + x(btree_node_compact, 15, TYPE_COUNTER) \ + x(btree_node_merge, 16, TYPE_COUNTER) \ + x(btree_node_split, 17, TYPE_COUNTER) \ + x(btree_node_rewrite, 18, TYPE_COUNTER) \ + x(btree_node_alloc, 19, TYPE_COUNTER) \ + x(btree_node_free, 20, TYPE_COUNTER) \ + x(btree_node_set_root, 21, TYPE_COUNTER) \ + x(btree_path_relock_fail, 22, TYPE_COUNTER) \ + x(btree_path_upgrade_fail, 23, TYPE_COUNTER) \ + x(btree_reserve_get_fail, 24, TYPE_COUNTER) \ + x(journal_entry_full, 25, TYPE_COUNTER) \ + x(journal_full, 26, TYPE_COUNTER) \ + x(journal_reclaim_finish, 27, TYPE_COUNTER) \ + x(journal_reclaim_start, 28, TYPE_COUNTER) \ + x(journal_write, 29, TYPE_COUNTER) \ + x(read_promote, 30, TYPE_COUNTER) \ + x(read_bounce, 31, TYPE_COUNTER) \ + x(read_split, 33, TYPE_COUNTER) \ + x(read_retry, 32, TYPE_COUNTER) \ + x(read_reuse_race, 34, TYPE_COUNTER) \ + x(move_extent_read, 35, TYPE_SECTORS) \ + x(move_extent_write, 36, TYPE_SECTORS) \ + x(move_extent_finish, 37, TYPE_SECTORS) \ + x(move_extent_fail, 38, TYPE_COUNTER) \ + x(move_extent_start_fail, 39, TYPE_COUNTER) \ + x(copygc, 40, TYPE_COUNTER) \ + x(copygc_wait, 41, TYPE_COUNTER) \ + x(gc_gens_end, 42, TYPE_COUNTER) \ + x(gc_gens_start, 43, TYPE_COUNTER) \ + x(trans_blocked_journal_reclaim, 44, TYPE_COUNTER) \ + x(trans_restart_btree_node_reused, 45, TYPE_COUNTER) \ + x(trans_restart_btree_node_split, 46, TYPE_COUNTER) \ + x(trans_restart_fault_inject, 47, TYPE_COUNTER) \ + x(trans_restart_iter_upgrade, 48, TYPE_COUNTER) \ + x(trans_restart_journal_preres_get, 49, TYPE_COUNTER) \ + x(trans_restart_journal_reclaim, 50, TYPE_COUNTER) \ + x(trans_restart_journal_res_get, 51, TYPE_COUNTER) \ + x(trans_restart_key_cache_key_realloced, 52, TYPE_COUNTER) \ + x(trans_restart_key_cache_raced, 53, TYPE_COUNTER) \ + x(trans_restart_mark_replicas, 54, TYPE_COUNTER) \ + x(trans_restart_mem_realloced, 55, TYPE_COUNTER) \ + x(trans_restart_memory_allocation_failure, 56, TYPE_COUNTER) \ + x(trans_restart_relock, 57, TYPE_COUNTER) \ + x(trans_restart_relock_after_fill, 58, TYPE_COUNTER) \ + x(trans_restart_relock_key_cache_fill, 59, TYPE_COUNTER) \ + x(trans_restart_relock_next_node, 60, TYPE_COUNTER) \ + x(trans_restart_relock_parent_for_fill, 61, TYPE_COUNTER) \ + x(trans_restart_relock_path, 62, TYPE_COUNTER) \ + x(trans_restart_relock_path_intent, 63, TYPE_COUNTER) \ + x(trans_restart_too_many_iters, 64, TYPE_COUNTER) \ + x(trans_restart_traverse, 65, TYPE_COUNTER) \ + x(trans_restart_upgrade, 66, TYPE_COUNTER) \ + x(trans_restart_would_deadlock, 67, TYPE_COUNTER) \ + x(trans_restart_would_deadlock_write, 68, TYPE_COUNTER) \ + x(trans_restart_injected, 69, TYPE_COUNTER) \ + x(trans_restart_key_cache_upgrade, 70, TYPE_COUNTER) \ + x(trans_traverse_all, 71, TYPE_COUNTER) \ + x(transaction_commit, 72, TYPE_COUNTER) \ + x(write_super, 73, TYPE_COUNTER) \ + x(trans_restart_would_deadlock_recursion_limit, 74, TYPE_COUNTER) \ + x(trans_restart_write_buffer_flush, 75, TYPE_COUNTER) \ + x(trans_restart_split_race, 76, TYPE_COUNTER) \ + x(write_buffer_flush_slowpath, 77, TYPE_COUNTER) \ + x(write_buffer_flush_sync, 78, TYPE_COUNTER) enum bch_persistent_counters { #define x(t, n, ...) BCH_COUNTER_##t, diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 8767c33c2b51..14f6b6a5fb38 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -81,7 +81,19 @@ BCH_FSCK_ERR_accounting_mismatch) \ x(inode_has_child_snapshots, \ BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ - BCH_FSCK_ERR_inode_has_child_snapshots_wrong) + BCH_FSCK_ERR_inode_has_child_snapshots_wrong) \ + x(backpointer_bucket_gen, \ + BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\ + BCH_FSCK_ERR_backpointer_to_missing_ptr, \ + BCH_FSCK_ERR_ptr_to_missing_backpointer) \ + x(disk_accounting_big_endian, \ + BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ + BCH_FSCK_ERR_accounting_mismatch, \ + BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ + BCH_FSCK_ERR_accounting_key_junk_at_end) \ + x(directory_size, \ + BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ + BCH_FSCK_ERR_directory_size_mismatch) \ #define DOWNGRADE_TABLE() \ x(bucket_stripe_sectors, \ @@ -117,7 +129,19 @@ BCH_FSCK_ERR_bkey_version_in_future) \ x(rebalance_work_acct_fix, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ - BCH_FSCK_ERR_accounting_mismatch) + BCH_FSCK_ERR_accounting_mismatch, \ + BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ + BCH_FSCK_ERR_accounting_key_junk_at_end) \ + x(backpointer_bucket_gen, \ + BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\ + BCH_FSCK_ERR_backpointer_bucket_offset_wrong, \ + BCH_FSCK_ERR_backpointer_to_missing_ptr, \ + BCH_FSCK_ERR_ptr_to_missing_backpointer) \ + x(disk_accounting_big_endian, \ + BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ + BCH_FSCK_ERR_accounting_mismatch, \ + BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ + BCH_FSCK_ERR_accounting_key_junk_at_end) struct upgrade_downgrade_entry { u64 recovery_passes; diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index 9feb6739f77a..ea0a18364751 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -5,9 +5,8 @@ enum bch_fsck_flags { FSCK_CAN_FIX = 1 << 0, FSCK_CAN_IGNORE = 1 << 1, - FSCK_NEED_FSCK = 1 << 2, - FSCK_NO_RATELIMIT = 1 << 3, - FSCK_AUTOFIX = 1 << 4, + FSCK_NO_RATELIMIT = 1 << 2, + FSCK_AUTOFIX = 1 << 3, }; #define BCH_SB_ERRS() \ @@ -58,8 +57,8 @@ enum bch_fsck_flags { x(bset_wrong_sector_offset, 44, 0) \ x(bset_empty, 45, 0) \ x(bset_bad_seq, 46, 0) \ - x(bset_blacklisted_journal_seq, 47, 0) \ - x(first_bset_blacklisted_journal_seq, 48, 0) \ + x(bset_blacklisted_journal_seq, 47, FSCK_AUTOFIX) \ + x(first_bset_blacklisted_journal_seq, 48, FSCK_AUTOFIX) \ x(btree_node_bad_btree, 49, 0) \ x(btree_node_bad_level, 50, 0) \ x(btree_node_bad_min_key, 51, 0) \ @@ -68,17 +67,17 @@ enum bch_fsck_flags { x(btree_node_bkey_past_bset_end, 54, 0) \ x(btree_node_bkey_bad_format, 55, 0) \ x(btree_node_bad_bkey, 56, 0) \ - x(btree_node_bkey_out_of_order, 57, 0) \ - x(btree_root_bkey_invalid, 58, 0) \ - x(btree_root_read_error, 59, 0) \ + x(btree_node_bkey_out_of_order, 57, FSCK_AUTOFIX) \ + x(btree_root_bkey_invalid, 58, FSCK_AUTOFIX) \ + x(btree_root_read_error, 59, FSCK_AUTOFIX) \ x(btree_root_bad_min_key, 60, 0) \ x(btree_root_bad_max_key, 61, 0) \ - x(btree_node_read_error, 62, 0) \ - x(btree_node_topology_bad_min_key, 63, 0) \ - x(btree_node_topology_bad_max_key, 64, 0) \ - x(btree_node_topology_overwritten_by_prev_node, 65, 0) \ - x(btree_node_topology_overwritten_by_next_node, 66, 0) \ - x(btree_node_topology_interior_node_empty, 67, 0) \ + x(btree_node_read_error, 62, FSCK_AUTOFIX) \ + x(btree_node_topology_bad_min_key, 63, FSCK_AUTOFIX) \ + x(btree_node_topology_bad_max_key, 64, FSCK_AUTOFIX) \ + x(btree_node_topology_overwritten_by_prev_node, 65, FSCK_AUTOFIX) \ + x(btree_node_topology_overwritten_by_next_node, 66, FSCK_AUTOFIX) \ + x(btree_node_topology_interior_node_empty, 67, FSCK_AUTOFIX) \ x(fs_usage_hidden_wrong, 68, FSCK_AUTOFIX) \ x(fs_usage_btree_wrong, 69, FSCK_AUTOFIX) \ x(fs_usage_data_wrong, 70, FSCK_AUTOFIX) \ @@ -123,11 +122,12 @@ enum bch_fsck_flags { x(alloc_key_cached_sectors_wrong, 109, FSCK_AUTOFIX) \ x(alloc_key_stripe_wrong, 110, FSCK_AUTOFIX) \ x(alloc_key_stripe_redundancy_wrong, 111, FSCK_AUTOFIX) \ + x(alloc_key_journal_seq_in_future, 298, FSCK_AUTOFIX) \ x(bucket_sector_count_overflow, 112, 0) \ x(bucket_metadata_type_mismatch, 113, 0) \ - x(need_discard_key_wrong, 114, 0) \ - x(freespace_key_wrong, 115, 0) \ - x(freespace_hole_missing, 116, 0) \ + x(need_discard_key_wrong, 114, FSCK_AUTOFIX) \ + x(freespace_key_wrong, 115, FSCK_AUTOFIX) \ + x(freespace_hole_missing, 116, FSCK_AUTOFIX) \ x(bucket_gens_val_size_bad, 117, 0) \ x(bucket_gens_key_wrong, 118, FSCK_AUTOFIX) \ x(bucket_gens_hole_wrong, 119, FSCK_AUTOFIX) \ @@ -139,9 +139,10 @@ enum bch_fsck_flags { x(discarding_bucket_not_in_need_discard_btree, 291, 0) \ x(backpointer_bucket_offset_wrong, 125, 0) \ x(backpointer_level_bad, 294, 0) \ - x(backpointer_to_missing_device, 126, 0) \ - x(backpointer_to_missing_alloc, 127, 0) \ - x(backpointer_to_missing_ptr, 128, 0) \ + x(backpointer_dev_bad, 297, 0) \ + x(backpointer_to_missing_device, 126, FSCK_AUTOFIX) \ + x(backpointer_to_missing_alloc, 127, FSCK_AUTOFIX) \ + x(backpointer_to_missing_ptr, 128, FSCK_AUTOFIX) \ x(lru_entry_at_time_0, 129, FSCK_AUTOFIX) \ x(lru_entry_to_invalid_bucket, 130, FSCK_AUTOFIX) \ x(lru_entry_bad, 131, FSCK_AUTOFIX) \ @@ -167,14 +168,15 @@ enum bch_fsck_flags { x(ptr_to_incorrect_stripe, 151, 0) \ x(ptr_gen_newer_than_bucket_gen, 152, 0) \ x(ptr_too_stale, 153, 0) \ - x(stale_dirty_ptr, 154, 0) \ + x(stale_dirty_ptr, 154, FSCK_AUTOFIX) \ x(ptr_bucket_data_type_mismatch, 155, 0) \ x(ptr_cached_and_erasure_coded, 156, 0) \ x(ptr_crc_uncompressed_size_too_small, 157, 0) \ + x(ptr_crc_uncompressed_size_too_big, 161, 0) \ + x(ptr_crc_uncompressed_size_mismatch, 300, 0) \ x(ptr_crc_csum_type_unknown, 158, 0) \ x(ptr_crc_compression_type_unknown, 159, 0) \ x(ptr_crc_redundant, 160, 0) \ - x(ptr_crc_uncompressed_size_too_big, 161, 0) \ x(ptr_crc_nonce_mismatch, 162, 0) \ x(ptr_stripe_redundant, 163, 0) \ x(reservation_key_nr_replicas_invalid, 164, 0) \ @@ -209,6 +211,7 @@ enum bch_fsck_flags { x(bkey_in_missing_snapshot, 190, 0) \ x(inode_pos_inode_nonzero, 191, 0) \ x(inode_pos_blockdev_range, 192, 0) \ + x(inode_alloc_cursor_inode_bad, 301, 0) \ x(inode_unpack_error, 193, 0) \ x(inode_str_hash_invalid, 194, 0) \ x(inode_v3_fields_start_bad, 195, 0) \ @@ -232,6 +235,7 @@ enum bch_fsck_flags { x(inode_wrong_nlink, 209, FSCK_AUTOFIX) \ x(inode_has_child_snapshots_wrong, 287, 0) \ x(inode_unreachable, 210, FSCK_AUTOFIX) \ + x(inode_journal_seq_in_future, 299, FSCK_AUTOFIX) \ x(deleted_inode_but_clean, 211, FSCK_AUTOFIX) \ x(deleted_inode_missing, 212, FSCK_AUTOFIX) \ x(deleted_inode_is_dir, 213, FSCK_AUTOFIX) \ @@ -252,6 +256,7 @@ enum bch_fsck_flags { x(dirent_in_missing_dir_inode, 227, 0) \ x(dirent_in_non_dir_inode, 228, 0) \ x(dirent_to_missing_inode, 229, 0) \ + x(dirent_to_overwritten_inode, 302, 0) \ x(dirent_to_missing_subvol, 230, 0) \ x(dirent_to_itself, 231, 0) \ x(quota_type_invalid, 232, 0) \ @@ -288,7 +293,7 @@ enum bch_fsck_flags { x(btree_root_unreadable_and_scan_found_nothing, 263, 0) \ x(snapshot_node_missing, 264, 0) \ x(dup_backpointer_to_bad_csum_extent, 265, 0) \ - x(btree_bitmap_not_marked, 266, 0) \ + x(btree_bitmap_not_marked, 266, FSCK_AUTOFIX) \ x(sb_clean_entry_overrun, 267, 0) \ x(btree_ptr_v2_written_0, 268, 0) \ x(subvol_snapshot_bad, 269, 0) \ @@ -306,7 +311,10 @@ enum bch_fsck_flags { x(accounting_key_replicas_devs_unsorted, 280, FSCK_AUTOFIX) \ x(accounting_key_version_0, 282, FSCK_AUTOFIX) \ x(logged_op_but_clean, 283, FSCK_AUTOFIX) \ - x(MAX, 295, 0) + x(compression_opt_not_marked_in_sb, 295, FSCK_AUTOFIX) \ + x(compression_type_not_marked_in_sb, 296, FSCK_AUTOFIX) \ + x(directory_size_mismatch, 303, FSCK_AUTOFIX) \ + x(MAX, 304, 0) enum bch_sb_error_id { #define x(t, n, ...) BCH_FSCK_ERR_##t = n, diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c index 617d07e53b20..7e7c66a1e1a6 100644 --- a/fs/bcachefs/six.c +++ b/fs/bcachefs/six.c @@ -491,8 +491,12 @@ static int six_lock_slowpath(struct six_lock *lock, enum six_lock_type type, list_del(&wait->list); raw_spin_unlock(&lock->wait_lock); - if (unlikely(acquired)) + if (unlikely(acquired)) { do_six_unlock_type(lock, type); + } else if (type == SIX_LOCK_write) { + six_clear_bitmask(lock, SIX_LOCK_HELD_write); + six_lock_wakeup(lock, atomic_read(&lock->state), SIX_LOCK_read); + } break; } @@ -501,10 +505,6 @@ static int six_lock_slowpath(struct six_lock *lock, enum six_lock_type type, __set_current_state(TASK_RUNNING); out: - if (ret && type == SIX_LOCK_write) { - six_clear_bitmask(lock, SIX_LOCK_HELD_write); - six_lock_wakeup(lock, atomic_read(&lock->state), SIX_LOCK_read); - } trace_contention_end(lock, 0); return ret; @@ -616,8 +616,6 @@ void six_unlock_ip(struct six_lock *lock, enum six_lock_type type, unsigned long if (type != SIX_LOCK_write) six_release(&lock->dep_map, ip); - else - lock->seq++; if (type == SIX_LOCK_intent && lock->intent_lock_recurse) { @@ -625,6 +623,15 @@ void six_unlock_ip(struct six_lock *lock, enum six_lock_type type, unsigned long return; } + if (type == SIX_LOCK_write && + lock->write_lock_recurse) { + --lock->write_lock_recurse; + return; + } + + if (type == SIX_LOCK_write) + lock->seq++; + do_six_unlock_type(lock, type); } EXPORT_SYMBOL_GPL(six_unlock_ip); @@ -735,13 +742,13 @@ void six_lock_increment(struct six_lock *lock, enum six_lock_type type) atomic_add(l[type].lock_val, &lock->state); } break; + case SIX_LOCK_write: + lock->write_lock_recurse++; + fallthrough; case SIX_LOCK_intent: EBUG_ON(!(atomic_read(&lock->state) & SIX_LOCK_HELD_intent)); lock->intent_lock_recurse++; break; - case SIX_LOCK_write: - BUG(); - break; } } EXPORT_SYMBOL_GPL(six_lock_increment); diff --git a/fs/bcachefs/six.h b/fs/bcachefs/six.h index 68d46fd7f391..c142e06b7a3a 100644 --- a/fs/bcachefs/six.h +++ b/fs/bcachefs/six.h @@ -137,6 +137,7 @@ struct six_lock { atomic_t state; u32 seq; unsigned intent_lock_recurse; + unsigned write_lock_recurse; struct task_struct *owner; unsigned __percpu *readers; raw_spinlock_t wait_lock; diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index ae57638506c3..c54091a28909 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -2,6 +2,7 @@ #include "bcachefs.h" #include "bkey_buf.h" +#include "btree_cache.h" #include "btree_key_cache.h" #include "btree_update.h" #include "buckets.h" @@ -32,7 +33,7 @@ void bch2_snapshot_tree_to_text(struct printbuf *out, struct bch_fs *c, } int bch2_snapshot_tree_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -225,7 +226,7 @@ void bch2_snapshot_to_text(struct printbuf *out, struct bch_fs *c, } int bch2_snapshot_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_snapshot s; u32 i, id; @@ -279,23 +280,6 @@ fsck_err: return ret; } -static void __set_is_ancestor_bitmap(struct bch_fs *c, u32 id) -{ - struct snapshot_t *t = snapshot_t_mut(c, id); - u32 parent = id; - - while ((parent = bch2_snapshot_parent_early(c, parent)) && - parent - id - 1 < IS_ANCESTOR_BITMAP) - __set_bit(parent - id - 1, t->is_ancestor); -} - -static void set_is_ancestor_bitmap(struct bch_fs *c, u32 id) -{ - mutex_lock(&c->snapshot_table_lock); - __set_is_ancestor_bitmap(c, id); - mutex_unlock(&c->snapshot_table_lock); -} - static int __bch2_mark_snapshot(struct btree_trans *trans, enum btree_id btree, unsigned level, struct bkey_s_c old, struct bkey_s_c new, @@ -317,6 +301,7 @@ static int __bch2_mark_snapshot(struct btree_trans *trans, if (new.k->type == KEY_TYPE_snapshot) { struct bkey_s_c_snapshot s = bkey_s_c_to_snapshot(new); + t->live = true; t->parent = le32_to_cpu(s.v->parent); t->children[0] = le32_to_cpu(s.v->children[0]); t->children[1] = le32_to_cpu(s.v->children[1]); @@ -335,7 +320,11 @@ static int __bch2_mark_snapshot(struct btree_trans *trans, t->skip[2] = 0; } - __set_is_ancestor_bitmap(c, id); + u32 parent = id; + + while ((parent = bch2_snapshot_parent_early(c, parent)) && + parent - id - 1 < IS_ANCESTOR_BITMAP) + __set_bit(parent - id - 1, t->is_ancestor); if (BCH_SNAPSHOT_DELETED(s.v)) { set_bit(BCH_FS_need_delete_dead_snapshots, &c->flags); @@ -365,70 +354,6 @@ int bch2_snapshot_lookup(struct btree_trans *trans, u32 id, BTREE_ITER_with_updates, snapshot, s); } -static int bch2_snapshot_live(struct btree_trans *trans, u32 id) -{ - struct bch_snapshot v; - int ret; - - if (!id) - return 0; - - ret = bch2_snapshot_lookup(trans, id, &v); - if (bch2_err_matches(ret, ENOENT)) - bch_err(trans->c, "snapshot node %u not found", id); - if (ret) - return ret; - - return !BCH_SNAPSHOT_DELETED(&v); -} - -/* - * If @k is a snapshot with just one live child, it's part of a linear chain, - * which we consider to be an equivalence class: and then after snapshot - * deletion cleanup, there should only be a single key at a given position in - * this equivalence class. - * - * This sets the equivalence class of @k to be the child's equivalence class, if - * it's part of such a linear chain: this correctly sets equivalence classes on - * startup if we run leaf to root (i.e. in natural key order). - */ -static int bch2_snapshot_set_equiv(struct btree_trans *trans, struct bkey_s_c k) -{ - struct bch_fs *c = trans->c; - unsigned i, nr_live = 0, live_idx = 0; - struct bkey_s_c_snapshot snap; - u32 id = k.k->p.offset, child[2]; - - if (k.k->type != KEY_TYPE_snapshot) - return 0; - - snap = bkey_s_c_to_snapshot(k); - - child[0] = le32_to_cpu(snap.v->children[0]); - child[1] = le32_to_cpu(snap.v->children[1]); - - for (i = 0; i < 2; i++) { - int ret = bch2_snapshot_live(trans, child[i]); - - if (ret < 0) - return ret; - - if (ret) - live_idx = i; - nr_live += ret; - } - - mutex_lock(&c->snapshot_table_lock); - - snapshot_t_mut(c, id)->equiv = nr_live == 1 - ? snapshot_t_mut(c, child[live_idx])->equiv - : id; - - mutex_unlock(&c->snapshot_table_lock); - - return 0; -} - /* fsck: */ static u32 bch2_snapshot_child(struct bch_fs *c, u32 id, unsigned child) @@ -506,7 +431,6 @@ static int bch2_snapshot_tree_master_subvol(struct btree_trans *trans, break; } } - bch2_trans_iter_exit(trans, &iter); if (!ret && !found) { @@ -536,6 +460,7 @@ static int check_snapshot_tree(struct btree_trans *trans, struct bch_snapshot s; struct bch_subvolume subvol; struct printbuf buf = PRINTBUF; + struct btree_iter snapshot_iter = {}; u32 root_id; int ret; @@ -545,22 +470,35 @@ static int check_snapshot_tree(struct btree_trans *trans, st = bkey_s_c_to_snapshot_tree(k); root_id = le32_to_cpu(st.v->root_snapshot); - ret = bch2_snapshot_lookup(trans, root_id, &s); + struct bkey_s_c_snapshot snapshot_k = + bch2_bkey_get_iter_typed(trans, &snapshot_iter, BTREE_ID_snapshots, + POS(0, root_id), 0, snapshot); + ret = bkey_err(snapshot_k); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; + if (!ret) + bkey_val_copy(&s, snapshot_k); + if (fsck_err_on(ret || root_id != bch2_snapshot_root(c, root_id) || st.k->p.offset != le32_to_cpu(s.tree), trans, snapshot_tree_to_missing_snapshot, "snapshot tree points to missing/incorrect snapshot:\n %s", - (bch2_bkey_val_to_text(&buf, c, st.s_c), buf.buf))) { + (bch2_bkey_val_to_text(&buf, c, st.s_c), + prt_newline(&buf), + ret + ? prt_printf(&buf, "(%s)", bch2_err_str(ret)) + : bch2_bkey_val_to_text(&buf, c, snapshot_k.s_c), + buf.buf))) { ret = bch2_btree_delete_at(trans, iter, 0); goto err; } - ret = bch2_subvolume_get(trans, le32_to_cpu(st.v->master_subvol), - false, 0, &subvol); + if (!st.v->master_subvol) + goto out; + + ret = bch2_subvolume_get(trans, le32_to_cpu(st.v->master_subvol), false, &subvol); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; @@ -603,8 +541,10 @@ static int check_snapshot_tree(struct btree_trans *trans, u->v.master_subvol = cpu_to_le32(subvol_id); st = snapshot_tree_i_to_s_c(u); } +out: err: fsck_err: + bch2_trans_iter_exit(trans, &snapshot_iter); printbuf_exit(&buf); return ret; } @@ -799,7 +739,7 @@ static int check_snapshot(struct btree_trans *trans, if (should_have_subvol) { id = le32_to_cpu(s.subvol); - ret = bch2_subvolume_get(trans, id, 0, false, &subvol); + ret = bch2_subvolume_get(trans, id, false, &subvol); if (bch2_err_matches(ret, ENOENT)) bch_err(c, "snapshot points to nonexistent subvolume:\n %s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf)); @@ -902,7 +842,7 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id) { struct bch_fs *c = trans->c; - if (bch2_snapshot_equiv(c, id)) + if (bch2_snapshot_exists(c, id)) return 0; /* Do we need to reconstruct the snapshot_tree entry as well? */ @@ -951,8 +891,7 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id) return bch2_btree_insert_trans(trans, BTREE_ID_snapshots, &snapshot->k_i, 0) ?: bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0, - bkey_s_c_null, bkey_i_to_s(&snapshot->k_i), 0) ?: - bch2_snapshot_set_equiv(trans, bkey_i_to_s_c(&snapshot->k_i)); + bkey_s_c_null, bkey_i_to_s(&snapshot->k_i), 0); } /* Figure out which snapshot nodes belong in the same tree: */ @@ -1050,7 +989,7 @@ int bch2_reconstruct_snapshots(struct bch_fs *c) snapshot_id_list_to_text(&buf, t); darray_for_each(*t, id) { - if (fsck_err_on(!bch2_snapshot_equiv(c, *id), + if (fsck_err_on(!bch2_snapshot_exists(c, *id), trans, snapshot_node_missing, "snapshot node %u from tree %s missing, recreate?", *id, buf.buf)) { if (t->nr > 1) { @@ -1083,10 +1022,12 @@ int bch2_check_key_has_snapshot(struct btree_trans *trans, struct printbuf buf = PRINTBUF; int ret = 0; - if (fsck_err_on(!bch2_snapshot_equiv(c, k.k->p.snapshot), + if (fsck_err_on(!bch2_snapshot_exists(c, k.k->p.snapshot), trans, bkey_in_missing_snapshot, "key in missing snapshot %s, delete?", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + (bch2_btree_id_to_text(&buf, iter->btree_id), + prt_char(&buf, ' '), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) ret = bch2_btree_delete_at(trans, iter, BTREE_UPDATE_internal_snapshot_node) ?: 1; fsck_err: @@ -1100,13 +1041,11 @@ fsck_err: int bch2_snapshot_node_set_deleted(struct btree_trans *trans, u32 id) { struct btree_iter iter; - struct bkey_i_snapshot *s; - int ret = 0; - - s = bch2_bkey_get_mut_typed(trans, &iter, + struct bkey_i_snapshot *s = + bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_snapshots, POS(0, id), 0, snapshot); - ret = PTR_ERR_OR_ZERO(s); + int ret = PTR_ERR_OR_ZERO(s); if (unlikely(ret)) { bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, "missing snapshot %u", id); @@ -1294,10 +1233,6 @@ static int create_snapids(struct btree_trans *trans, u32 parent, u32 tree, goto err; new_snapids[i] = iter.pos.offset; - - mutex_lock(&c->snapshot_table_lock); - snapshot_t_mut(c, new_snapids[i])->equiv = new_snapids[i]; - mutex_unlock(&c->snapshot_table_lock); } err: bch2_trans_iter_exit(trans, &iter); @@ -1403,102 +1338,95 @@ int bch2_snapshot_node_create(struct btree_trans *trans, u32 parent, * that key to snapshot leaf nodes, where we can mutate it */ -static int delete_dead_snapshots_process_key(struct btree_trans *trans, - struct btree_iter *iter, - struct bkey_s_c k, - snapshot_id_list *deleted, - snapshot_id_list *equiv_seen, - struct bpos *last_pos) -{ - int ret = bch2_check_key_has_snapshot(trans, iter, k); - if (ret) - return ret < 0 ? ret : 0; +struct snapshot_interior_delete { + u32 id; + u32 live_child; +}; +typedef DARRAY(struct snapshot_interior_delete) interior_delete_list; - struct bch_fs *c = trans->c; - u32 equiv = bch2_snapshot_equiv(c, k.k->p.snapshot); - if (!equiv) /* key for invalid snapshot node, but we chose not to delete */ +static inline u32 interior_delete_has_id(interior_delete_list *l, u32 id) +{ + darray_for_each(*l, i) + if (i->id == id) + return i->live_child; + return 0; +} + +static unsigned __live_child(struct snapshot_table *t, u32 id, + snapshot_id_list *delete_leaves, + interior_delete_list *delete_interior) +{ + struct snapshot_t *s = __snapshot_t(t, id); + if (!s) return 0; - if (!bkey_eq(k.k->p, *last_pos)) - equiv_seen->nr = 0; + for (unsigned i = 0; i < ARRAY_SIZE(s->children); i++) + if (s->children[i] && + !snapshot_list_has_id(delete_leaves, s->children[i]) && + !interior_delete_has_id(delete_interior, s->children[i])) + return s->children[i]; - if (snapshot_list_has_id(deleted, k.k->p.snapshot)) - return bch2_btree_delete_at(trans, iter, - BTREE_UPDATE_internal_snapshot_node); - - if (!bpos_eq(*last_pos, k.k->p) && - snapshot_list_has_id(equiv_seen, equiv)) - return bch2_btree_delete_at(trans, iter, - BTREE_UPDATE_internal_snapshot_node); - - *last_pos = k.k->p; - - ret = snapshot_list_add_nodup(c, equiv_seen, equiv); - if (ret) - return ret; - - /* - * When we have a linear chain of snapshot nodes, we consider - * those to form an equivalence class: we're going to collapse - * them all down to a single node, and keep the leaf-most node - - * which has the same id as the equivalence class id. - * - * If there are multiple keys in different snapshots at the same - * position, we're only going to keep the one in the newest - * snapshot (we delete the others above) - the rest have been - * overwritten and are redundant, and for the key we're going to keep we - * need to move it to the equivalance class ID if it's not there - * already. - */ - if (equiv != k.k->p.snapshot) { - struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); - int ret = PTR_ERR_OR_ZERO(new); - if (ret) - return ret; - - new->k.p.snapshot = equiv; - - struct btree_iter new_iter; - bch2_trans_iter_init(trans, &new_iter, iter->btree_id, new->k.p, - BTREE_ITER_all_snapshots| - BTREE_ITER_cached| - BTREE_ITER_intent); - - ret = bch2_btree_iter_traverse(&new_iter) ?: - bch2_trans_update(trans, &new_iter, new, - BTREE_UPDATE_internal_snapshot_node) ?: - bch2_btree_delete_at(trans, iter, - BTREE_UPDATE_internal_snapshot_node); - bch2_trans_iter_exit(trans, &new_iter); - if (ret) - return ret; + for (unsigned i = 0; i < ARRAY_SIZE(s->children); i++) { + u32 live_child = s->children[i] + ? __live_child(t, s->children[i], delete_leaves, delete_interior) + : 0; + if (live_child) + return live_child; } return 0; } -static int bch2_snapshot_needs_delete(struct btree_trans *trans, struct bkey_s_c k) +static unsigned live_child(struct bch_fs *c, u32 id, + snapshot_id_list *delete_leaves, + interior_delete_list *delete_interior) { - struct bkey_s_c_snapshot snap; - u32 children[2]; - int ret; + rcu_read_lock(); + u32 ret = __live_child(rcu_dereference(c->snapshots), id, + delete_leaves, delete_interior); + rcu_read_unlock(); + return ret; +} - if (k.k->type != KEY_TYPE_snapshot) - return 0; +static int delete_dead_snapshots_process_key(struct btree_trans *trans, + struct btree_iter *iter, + struct bkey_s_c k, + snapshot_id_list *delete_leaves, + interior_delete_list *delete_interior) +{ + if (snapshot_list_has_id(delete_leaves, k.k->p.snapshot)) + return bch2_btree_delete_at(trans, iter, + BTREE_UPDATE_internal_snapshot_node); - snap = bkey_s_c_to_snapshot(k); - if (BCH_SNAPSHOT_DELETED(snap.v) || - BCH_SNAPSHOT_SUBVOL(snap.v)) - return 0; + u32 live_child = interior_delete_has_id(delete_interior, k.k->p.snapshot); + if (live_child) { + struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); + int ret = PTR_ERR_OR_ZERO(new); + if (ret) + return ret; - children[0] = le32_to_cpu(snap.v->children[0]); - children[1] = le32_to_cpu(snap.v->children[1]); + new->k.p.snapshot = live_child; - ret = bch2_snapshot_live(trans, children[0]) ?: - bch2_snapshot_live(trans, children[1]); - if (ret < 0) + struct btree_iter dst_iter; + struct bkey_s_c dst_k = bch2_bkey_get_iter(trans, &dst_iter, + iter->btree_id, new->k.p, + BTREE_ITER_all_snapshots| + BTREE_ITER_intent); + ret = bkey_err(dst_k); + if (ret) + return ret; + + ret = (bkey_deleted(dst_k.k) + ? bch2_trans_update(trans, &dst_iter, new, + BTREE_UPDATE_internal_snapshot_node) + : 0) ?: + bch2_btree_delete_at(trans, iter, + BTREE_UPDATE_internal_snapshot_node); + bch2_trans_iter_exit(trans, &dst_iter); return ret; - return !ret; + } + + return 0; } /* @@ -1506,26 +1434,57 @@ static int bch2_snapshot_needs_delete(struct btree_trans *trans, struct bkey_s_c * it doesn't have child snapshot nodes - it's now redundant and we can mark it * as deleted. */ -static int bch2_delete_redundant_snapshot(struct btree_trans *trans, struct bkey_s_c k) +static int check_should_delete_snapshot(struct btree_trans *trans, struct bkey_s_c k, + snapshot_id_list *delete_leaves, + interior_delete_list *delete_interior) { - int ret = bch2_snapshot_needs_delete(trans, k); + if (k.k->type != KEY_TYPE_snapshot) + return 0; - return ret <= 0 - ? ret - : bch2_snapshot_node_set_deleted(trans, k.k->p.offset); + struct bch_fs *c = trans->c; + struct bkey_s_c_snapshot s = bkey_s_c_to_snapshot(k); + unsigned live_children = 0; + + if (BCH_SNAPSHOT_SUBVOL(s.v)) + return 0; + + for (unsigned i = 0; i < 2; i++) { + u32 child = le32_to_cpu(s.v->children[i]); + + live_children += child && + !snapshot_list_has_id(delete_leaves, child); + } + + if (live_children == 0) { + return snapshot_list_add(c, delete_leaves, s.k->p.offset); + } else if (live_children == 1) { + struct snapshot_interior_delete d = { + .id = s.k->p.offset, + .live_child = live_child(c, s.k->p.offset, delete_leaves, delete_interior), + }; + + if (!d.live_child) { + bch_err(c, "error finding live child of snapshot %u", d.id); + return -EINVAL; + } + + return darray_push(delete_interior, d); + } else { + return 0; + } } static inline u32 bch2_snapshot_nth_parent_skip(struct bch_fs *c, u32 id, u32 n, - snapshot_id_list *skip) + interior_delete_list *skip) { rcu_read_lock(); - while (snapshot_list_has_id(skip, id)) + while (interior_delete_has_id(skip, id)) id = __bch2_snapshot_parent(c, id); while (n--) { do { id = __bch2_snapshot_parent(c, id); - } while (snapshot_list_has_id(skip, id)); + } while (interior_delete_has_id(skip, id)); } rcu_read_unlock(); @@ -1534,7 +1493,7 @@ static inline u32 bch2_snapshot_nth_parent_skip(struct bch_fs *c, u32 id, u32 n, static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, - snapshot_id_list *deleted) + interior_delete_list *deleted) { struct bch_fs *c = trans->c; u32 nr_deleted_ancestors = 0; @@ -1544,7 +1503,7 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, if (k.k->type != KEY_TYPE_snapshot) return 0; - if (snapshot_list_has_id(deleted, k.k->p.offset)) + if (interior_delete_has_id(deleted, k.k->p.offset)) return 0; s = bch2_bkey_make_mut_noupdate_typed(trans, k, snapshot); @@ -1553,7 +1512,7 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, return ret; darray_for_each(*deleted, i) - nr_deleted_ancestors += bch2_snapshot_is_ancestor(c, s->k.p.offset, *i); + nr_deleted_ancestors += bch2_snapshot_is_ancestor(c, s->k.p.offset, i->id); if (!nr_deleted_ancestors) return 0; @@ -1571,7 +1530,7 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, for (unsigned j = 0; j < ARRAY_SIZE(s->v.skip); j++) { u32 id = le32_to_cpu(s->v.skip[j]); - if (snapshot_list_has_id(deleted, id)) { + if (interior_delete_has_id(deleted, id)) { id = bch2_snapshot_nth_parent_skip(c, parent, depth > 1 @@ -1590,51 +1549,45 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, int bch2_delete_dead_snapshots(struct bch_fs *c) { - struct btree_trans *trans; - snapshot_id_list deleted = { 0 }; - snapshot_id_list deleted_interior = { 0 }; - int ret = 0; - if (!test_and_clear_bit(BCH_FS_need_delete_dead_snapshots, &c->flags)) return 0; - trans = bch2_trans_get(c); + struct btree_trans *trans = bch2_trans_get(c); + snapshot_id_list delete_leaves = {}; + interior_delete_list delete_interior = {}; + int ret = 0; /* * For every snapshot node: If we have no live children and it's not * pointed to by a subvolume, delete it: */ - ret = for_each_btree_key_commit(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, - NULL, NULL, 0, - bch2_delete_redundant_snapshot(trans, k)); - bch_err_msg(c, ret, "deleting redundant snapshots"); + ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots, POS_MIN, 0, k, + check_should_delete_snapshot(trans, k, &delete_leaves, &delete_interior)); + if (!bch2_err_matches(ret, EROFS)) + bch_err_msg(c, ret, "walking snapshots"); if (ret) goto err; - ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, - bch2_snapshot_set_equiv(trans, k)); - bch_err_msg(c, ret, "in bch2_snapshots_set_equiv"); - if (ret) + if (!delete_leaves.nr && !delete_interior.nr) goto err; - ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, ({ - if (k.k->type != KEY_TYPE_snapshot) - continue; + { + struct printbuf buf = PRINTBUF; + prt_printf(&buf, "deleting leaves"); + darray_for_each(delete_leaves, i) + prt_printf(&buf, " %u", *i); - BCH_SNAPSHOT_DELETED(bkey_s_c_to_snapshot(k).v) - ? snapshot_list_add(c, &deleted, k.k->p.offset) - : 0; - })); - bch_err_msg(c, ret, "walking snapshots"); - if (ret) - goto err; + prt_printf(&buf, " interior"); + darray_for_each(delete_interior, i) + prt_printf(&buf, " %u->%u", i->id, i->live_child); + + ret = commit_do(trans, NULL, NULL, 0, bch2_trans_log_msg(trans, &buf)); + printbuf_exit(&buf); + if (ret) + goto err; + } for (unsigned btree = 0; btree < BTREE_ID_NR; btree++) { - struct bpos last_pos = POS_MIN; - snapshot_id_list equiv_seen = { 0 }; struct disk_reservation res = { 0 }; if (!btree_type_has_snapshots(btree)) @@ -1644,33 +1597,26 @@ int bch2_delete_dead_snapshots(struct bch_fs *c) btree, POS_MIN, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, &res, NULL, BCH_TRANS_COMMIT_no_enospc, - delete_dead_snapshots_process_key(trans, &iter, k, &deleted, - &equiv_seen, &last_pos)); + delete_dead_snapshots_process_key(trans, &iter, k, + &delete_leaves, + &delete_interior)); bch2_disk_reservation_put(c, &res); - darray_exit(&equiv_seen); - bch_err_msg(c, ret, "deleting keys from dying snapshots"); + if (!bch2_err_matches(ret, EROFS)) + bch_err_msg(c, ret, "deleting keys from dying snapshots"); if (ret) goto err; } - bch2_trans_unlock(trans); - down_write(&c->snapshot_create_lock); - - ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, ({ - u32 snapshot = k.k->p.offset; - u32 equiv = bch2_snapshot_equiv(c, snapshot); - - equiv != snapshot - ? snapshot_list_add(c, &deleted_interior, snapshot) - : 0; - })); - - bch_err_msg(c, ret, "walking snapshots"); - if (ret) - goto err_create_lock; + darray_for_each(delete_leaves, i) { + ret = commit_do(trans, NULL, NULL, 0, + bch2_snapshot_node_delete(trans, *i)); + if (!bch2_err_matches(ret, EROFS)) + bch_err_msg(c, ret, "deleting snapshot %u", *i); + if (ret) + goto err; + } /* * Fixing children of deleted snapshots can't be done completely @@ -1680,32 +1626,24 @@ int bch2_delete_dead_snapshots(struct bch_fs *c) ret = for_each_btree_key_commit(trans, iter, BTREE_ID_snapshots, POS_MIN, BTREE_ITER_intent, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - bch2_fix_child_of_deleted_snapshot(trans, &iter, k, &deleted_interior)); + bch2_fix_child_of_deleted_snapshot(trans, &iter, k, &delete_interior)); if (ret) - goto err_create_lock; + goto err; - darray_for_each(deleted, i) { + darray_for_each(delete_interior, i) { ret = commit_do(trans, NULL, NULL, 0, - bch2_snapshot_node_delete(trans, *i)); - bch_err_msg(c, ret, "deleting snapshot %u", *i); + bch2_snapshot_node_delete(trans, i->id)); + if (!bch2_err_matches(ret, EROFS)) + bch_err_msg(c, ret, "deleting snapshot %u", i->id); if (ret) - goto err_create_lock; + goto err; } - - darray_for_each(deleted_interior, i) { - ret = commit_do(trans, NULL, NULL, 0, - bch2_snapshot_node_delete(trans, *i)); - bch_err_msg(c, ret, "deleting snapshot %u", *i); - if (ret) - goto err_create_lock; - } -err_create_lock: - up_write(&c->snapshot_create_lock); err: - darray_exit(&deleted_interior); - darray_exit(&deleted); + darray_exit(&delete_interior); + darray_exit(&delete_leaves); bch2_trans_put(trans); - bch_err_fn(c, ret); + if (!bch2_err_matches(ret, EROFS)) + bch_err_fn(c, ret); return ret; } @@ -1721,8 +1659,12 @@ void bch2_delete_dead_snapshots_work(struct work_struct *work) void bch2_delete_dead_snapshots_async(struct bch_fs *c) { - if (bch2_write_ref_tryget(c, BCH_WRITE_REF_delete_dead_snapshots) && - !queue_work(c->write_ref_wq, &c->snapshot_delete_work)) + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_delete_dead_snapshots)) + return; + + BUG_ON(!test_bit(BCH_FS_may_go_rw, &c->flags)); + + if (!queue_work(c->write_ref_wq, &c->snapshot_delete_work)) bch2_write_ref_put(c, BCH_WRITE_REF_delete_dead_snapshots); } @@ -1735,18 +1677,10 @@ int __bch2_key_has_snapshot_overwrites(struct btree_trans *trans, struct bkey_s_c k; int ret; - bch2_trans_iter_init(trans, &iter, id, pos, - BTREE_ITER_not_extents| - BTREE_ITER_all_snapshots); - while (1) { - k = bch2_btree_iter_prev(&iter); - ret = bkey_err(k); - if (ret) - break; - - if (!k.k) - break; - + for_each_btree_key_reverse_norestart(trans, iter, id, bpos_predecessor(pos), + BTREE_ITER_not_extents| + BTREE_ITER_all_snapshots, + k, ret) { if (!bkey_eq(pos, k.k->p)) break; @@ -1760,37 +1694,36 @@ int __bch2_key_has_snapshot_overwrites(struct btree_trans *trans, return ret; } +static bool interior_snapshot_needs_delete(struct bkey_s_c_snapshot snap) +{ + /* If there's one child, it's redundant and keys will be moved to the child */ + return !!snap.v->children[0] + !!snap.v->children[1] == 1; +} + static int bch2_check_snapshot_needs_deletion(struct btree_trans *trans, struct bkey_s_c k) { - struct bch_fs *c = trans->c; - struct bkey_s_c_snapshot snap; - int ret = 0; - if (k.k->type != KEY_TYPE_snapshot) return 0; - snap = bkey_s_c_to_snapshot(k); + struct bkey_s_c_snapshot snap = bkey_s_c_to_snapshot(k); if (BCH_SNAPSHOT_DELETED(snap.v) || - bch2_snapshot_equiv(c, k.k->p.offset) != k.k->p.offset || - (ret = bch2_snapshot_needs_delete(trans, k)) > 0) { - set_bit(BCH_FS_need_delete_dead_snapshots, &c->flags); - return 0; - } + interior_snapshot_needs_delete(snap)) + set_bit(BCH_FS_need_delete_dead_snapshots, &trans->c->flags); - return ret; + return 0; } int bch2_snapshots_read(struct bch_fs *c) { + /* + * Initializing the is_ancestor bitmaps requires ancestors to already be + * initialized - so mark in reverse: + */ int ret = bch2_trans_run(c, - for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, + for_each_btree_key_reverse(trans, iter, BTREE_ID_snapshots, + POS_MAX, 0, k, __bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0, bkey_s_c_null, k, 0) ?: - bch2_snapshot_set_equiv(trans, k) ?: - bch2_check_snapshot_needs_deletion(trans, k)) ?: - for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, - (set_is_ancestor_bitmap(c, k.k->p.offset), 0))); + bch2_check_snapshot_needs_deletion(trans, k))); bch_err_fn(c, ret); /* diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h index 29c94716293e..00373cf32e7b 100644 --- a/fs/bcachefs/snapshot.h +++ b/fs/bcachefs/snapshot.h @@ -2,11 +2,9 @@ #ifndef _BCACHEFS_SNAPSHOT_H #define _BCACHEFS_SNAPSHOT_H -enum bch_validate_flags; - void bch2_snapshot_tree_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_snapshot_tree_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); #define bch2_bkey_ops_snapshot_tree ((struct bkey_ops) { \ .key_validate = bch2_snapshot_tree_validate, \ @@ -19,7 +17,8 @@ struct bkey_i_snapshot_tree *__bch2_snapshot_tree_create(struct btree_trans *); int bch2_snapshot_tree_lookup(struct btree_trans *, u32, struct bch_snapshot_tree *); void bch2_snapshot_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); -int bch2_snapshot_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_snapshot_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); int bch2_mark_snapshot(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); @@ -120,19 +119,19 @@ static inline u32 bch2_snapshot_root(struct bch_fs *c, u32 id) return id; } -static inline u32 __bch2_snapshot_equiv(struct bch_fs *c, u32 id) +static inline bool __bch2_snapshot_exists(struct bch_fs *c, u32 id) { const struct snapshot_t *s = snapshot_t(c, id); - return s ? s->equiv : 0; + return s ? s->live : 0; } -static inline u32 bch2_snapshot_equiv(struct bch_fs *c, u32 id) +static inline bool bch2_snapshot_exists(struct bch_fs *c, u32 id) { rcu_read_lock(); - id = __bch2_snapshot_equiv(c, id); + bool ret = __bch2_snapshot_exists(c, id); rcu_read_unlock(); - return id; + return ret; } static inline int bch2_snapshot_is_internal_node(struct bch_fs *c, u32 id) diff --git a/fs/bcachefs/str_hash.c b/fs/bcachefs/str_hash.c new file mode 100644 index 000000000000..d78451c2a0c6 --- /dev/null +++ b/fs/bcachefs/str_hash.c @@ -0,0 +1,295 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "bcachefs.h" +#include "btree_cache.h" +#include "btree_update.h" +#include "dirent.h" +#include "fsck.h" +#include "str_hash.h" +#include "subvolume.h" + +static int bch2_dirent_has_target(struct btree_trans *trans, struct bkey_s_c_dirent d) +{ + if (d.v->d_type == DT_SUBVOL) { + struct bch_subvolume subvol; + int ret = bch2_subvolume_get(trans, le32_to_cpu(d.v->d_child_subvol), + false, &subvol); + if (ret && !bch2_err_matches(ret, ENOENT)) + return ret; + return !ret; + } else { + struct btree_iter iter; + struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, + SPOS(0, le64_to_cpu(d.v->d_inum), d.k->p.snapshot), 0); + int ret = bkey_err(k); + if (ret) + return ret; + + ret = bkey_is_inode(k.k); + bch2_trans_iter_exit(trans, &iter); + return ret; + } +} + +static noinline int fsck_rename_dirent(struct btree_trans *trans, + struct snapshots_seen *s, + const struct bch_hash_desc desc, + struct bch_hash_info *hash_info, + struct bkey_s_c_dirent old) +{ + struct qstr old_name = bch2_dirent_get_name(old); + struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, bkey_bytes(old.k) + 32); + int ret = PTR_ERR_OR_ZERO(new); + if (ret) + return ret; + + bkey_dirent_init(&new->k_i); + dirent_copy_target(new, old); + new->k.p = old.k->p; + + for (unsigned i = 0; i < 1000; i++) { + unsigned len = sprintf(new->v.d_name, "%.*s.fsck_renamed-%u", + old_name.len, old_name.name, i); + unsigned u64s = BKEY_U64s + dirent_val_u64s(len); + + if (u64s > U8_MAX) + return -EINVAL; + + new->k.u64s = u64s; + + ret = bch2_hash_set_in_snapshot(trans, bch2_dirent_hash_desc, hash_info, + (subvol_inum) { 0, old.k->p.inode }, + old.k->p.snapshot, &new->k_i, + BTREE_UPDATE_internal_snapshot_node); + if (!bch2_err_matches(ret, EEXIST)) + break; + } + + if (ret) + return ret; + + return bch2_fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i); +} + +static noinline int hash_pick_winner(struct btree_trans *trans, + const struct bch_hash_desc desc, + struct bch_hash_info *hash_info, + struct bkey_s_c k1, + struct bkey_s_c k2) +{ + if (bkey_val_bytes(k1.k) == bkey_val_bytes(k2.k) && + !memcmp(k1.v, k2.v, bkey_val_bytes(k1.k))) + return 0; + + switch (desc.btree_id) { + case BTREE_ID_dirents: { + int ret = bch2_dirent_has_target(trans, bkey_s_c_to_dirent(k1)); + if (ret < 0) + return ret; + if (!ret) + return 0; + + ret = bch2_dirent_has_target(trans, bkey_s_c_to_dirent(k2)); + if (ret < 0) + return ret; + if (!ret) + return 1; + return 2; + } + default: + return 0; + } +} + +static int repair_inode_hash_info(struct btree_trans *trans, + struct bch_inode_unpacked *snapshot_root) +{ + struct btree_iter iter; + struct bkey_s_c k; + int ret = 0; + + for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, + SPOS(0, snapshot_root->bi_inum, snapshot_root->bi_snapshot - 1), + BTREE_ITER_all_snapshots, k, ret) { + if (k.k->p.offset != snapshot_root->bi_inum) + break; + if (!bkey_is_inode(k.k)) + continue; + + struct bch_inode_unpacked inode; + ret = bch2_inode_unpack(k, &inode); + if (ret) + break; + + if (fsck_err_on(inode.bi_hash_seed != snapshot_root->bi_hash_seed || + INODE_STR_HASH(&inode) != INODE_STR_HASH(snapshot_root), + trans, inode_snapshot_mismatch, + "inode hash info in different snapshots don't match")) { + inode.bi_hash_seed = snapshot_root->bi_hash_seed; + SET_INODE_STR_HASH(&inode, INODE_STR_HASH(snapshot_root)); + ret = __bch2_fsck_write_inode(trans, &inode) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_nested; + break; + } + } +fsck_err: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +/* + * All versions of the same inode in different snapshots must have the same hash + * seed/type: verify that the hash info we're using matches the root + */ +static noinline int check_inode_hash_info_matches_root(struct btree_trans *trans, u64 inum, + struct bch_hash_info *hash_info) +{ + struct bch_fs *c = trans->c; + struct btree_iter iter; + struct bkey_s_c k; + int ret = 0; + + for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inum, U32_MAX), + BTREE_ITER_all_snapshots, k, ret) { + if (k.k->p.offset != inum) + break; + if (bkey_is_inode(k.k)) + goto found; + } + bch_err(c, "%s(): inum %llu not found", __func__, inum); + ret = -BCH_ERR_fsck_repair_unimplemented; + goto err; +found:; + struct bch_inode_unpacked inode; + ret = bch2_inode_unpack(k, &inode); + if (ret) + goto err; + + struct bch_hash_info hash2 = bch2_hash_info_init(c, &inode); + if (hash_info->type != hash2.type || + memcmp(&hash_info->siphash_key, &hash2.siphash_key, sizeof(hash2.siphash_key))) { + ret = repair_inode_hash_info(trans, &inode); + if (!ret) { + bch_err(c, "inode hash info mismatch with root, but mismatch not found\n" + "%u %llx %llx\n" + "%u %llx %llx", + hash_info->type, + hash_info->siphash_key.k0, + hash_info->siphash_key.k1, + hash2.type, + hash2.siphash_key.k0, + hash2.siphash_key.k1); + ret = -BCH_ERR_fsck_repair_unimplemented; + } + } +err: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +int __bch2_str_hash_check_key(struct btree_trans *trans, + struct snapshots_seen *s, + const struct bch_hash_desc *desc, + struct bch_hash_info *hash_info, + struct btree_iter *k_iter, struct bkey_s_c hash_k) +{ + struct bch_fs *c = trans->c; + struct btree_iter iter = { NULL }; + struct printbuf buf = PRINTBUF; + struct bkey_s_c k; + int ret = 0; + + u64 hash = desc->hash_bkey(hash_info, hash_k); + if (hash_k.k->p.offset < hash) + goto bad_hash; + + for_each_btree_key_norestart(trans, iter, desc->btree_id, + SPOS(hash_k.k->p.inode, hash, hash_k.k->p.snapshot), + BTREE_ITER_slots, k, ret) { + if (bkey_eq(k.k->p, hash_k.k->p)) + break; + + if (k.k->type == desc->key_type && + !desc->cmp_bkey(k, hash_k)) + goto duplicate_entries; + + if (bkey_deleted(k.k)) { + bch2_trans_iter_exit(trans, &iter); + goto bad_hash; + } + } +out: + bch2_trans_iter_exit(trans, &iter); + printbuf_exit(&buf); + return ret; +bad_hash: + /* + * Before doing any repair, check hash_info itself: + */ + ret = check_inode_hash_info_matches_root(trans, hash_k.k->p.inode, hash_info); + if (ret) + goto out; + + if (fsck_err(trans, hash_table_key_wrong_offset, + "hash table key at wrong offset: btree %s inode %llu offset %llu, hashed to %llu\n %s", + bch2_btree_id_str(desc->btree_id), hash_k.k->p.inode, hash_k.k->p.offset, hash, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, hash_k), buf.buf))) { + struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, hash_k); + if (IS_ERR(new)) + return PTR_ERR(new); + + k = bch2_hash_set_or_get_in_snapshot(trans, &iter, *desc, hash_info, + (subvol_inum) { 0, hash_k.k->p.inode }, + hash_k.k->p.snapshot, new, + STR_HASH_must_create| + BTREE_ITER_with_updates| + BTREE_UPDATE_internal_snapshot_node); + ret = bkey_err(k); + if (ret) + goto out; + if (k.k) + goto duplicate_entries; + + ret = bch2_hash_delete_at(trans, *desc, hash_info, k_iter, + BTREE_UPDATE_internal_snapshot_node) ?: + bch2_fsck_update_backpointers(trans, s, *desc, hash_info, new) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_nested; + goto out; + } +fsck_err: + goto out; +duplicate_entries: + ret = hash_pick_winner(trans, *desc, hash_info, hash_k, k); + if (ret < 0) + goto out; + + if (!fsck_err(trans, hash_table_key_duplicate, + "duplicate hash table keys%s:\n%s", + ret != 2 ? "" : ", both point to valid inodes", + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, hash_k), + prt_newline(&buf), + bch2_bkey_val_to_text(&buf, c, k), + buf.buf))) + goto out; + + switch (ret) { + case 0: + ret = bch2_hash_delete_at(trans, *desc, hash_info, k_iter, 0); + break; + case 1: + ret = bch2_hash_delete_at(trans, *desc, hash_info, &iter, 0); + break; + case 2: + ret = fsck_rename_dirent(trans, s, *desc, hash_info, bkey_s_c_to_dirent(hash_k)) ?: + bch2_hash_delete_at(trans, *desc, hash_info, k_iter, 0); + goto out; + } + + ret = bch2_trans_commit(trans, NULL, NULL, 0) ?: + -BCH_ERR_transaction_restart_nested; + goto out; +} diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h index ec2b1feea520..55a4ac7bf220 100644 --- a/fs/bcachefs/str_hash.h +++ b/fs/bcachefs/str_hash.h @@ -160,7 +160,7 @@ bch2_hash_lookup_in_snapshot(struct btree_trans *trans, struct bkey_s_c k; int ret; - for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id, + for_each_btree_key_max_norestart(trans, *iter, desc.btree_id, SPOS(inum.inum, desc.hash_key(info, key), snapshot), POS(inum.inum, U64_MAX), BTREE_ITER_slots|flags, k, ret) { @@ -210,7 +210,7 @@ bch2_hash_hole(struct btree_trans *trans, if (ret) return ret; - for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id, + for_each_btree_key_max_norestart(trans, *iter, desc.btree_id, SPOS(inum.inum, desc.hash_key(info, key), snapshot), POS(inum.inum, U64_MAX), BTREE_ITER_slots|BTREE_ITER_intent, k, ret) @@ -265,7 +265,7 @@ struct bkey_s_c bch2_hash_set_or_get_in_snapshot(struct btree_trans *trans, bool found = false; int ret; - for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id, + for_each_btree_key_max_norestart(trans, *iter, desc.btree_id, SPOS(insert->k.p.inode, desc.hash_bkey(info, bkey_i_to_s_c(insert)), snapshot), @@ -393,4 +393,26 @@ int bch2_hash_delete(struct btree_trans *trans, return ret; } +struct snapshots_seen; +int __bch2_str_hash_check_key(struct btree_trans *, + struct snapshots_seen *, + const struct bch_hash_desc *, + struct bch_hash_info *, + struct btree_iter *, struct bkey_s_c); + +static inline int bch2_str_hash_check_key(struct btree_trans *trans, + struct snapshots_seen *s, + const struct bch_hash_desc *desc, + struct bch_hash_info *hash_info, + struct btree_iter *k_iter, struct bkey_s_c hash_k) +{ + if (hash_k.k->type != desc->key_type) + return 0; + + if (likely(desc->hash_bkey(hash_info, hash_k) == hash_k.k->p.offset)) + return 0; + + return __bch2_str_hash_check_key(trans, s, desc, hash_info, k_iter, hash_k); +} + #endif /* _BCACHEFS_STR_HASH_H */ diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index 80e5efaff524..e3d0475232e5 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -207,7 +207,7 @@ int bch2_check_subvol_children(struct bch_fs *c) /* Subvolumes: */ int bch2_subvolume_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_subvolume subvol = bkey_s_c_to_subvolume(k); int ret = 0; @@ -286,11 +286,11 @@ int bch2_subvol_has_children(struct btree_trans *trans, u32 subvol) static __always_inline int bch2_subvolume_get_inlined(struct btree_trans *trans, unsigned subvol, bool inconsistent_if_not_found, - int iter_flags, struct bch_subvolume *s) { int ret = bch2_bkey_get_val_typed(trans, BTREE_ID_subvolumes, POS(0, subvol), - iter_flags, subvolume, s); + BTREE_ITER_cached| + BTREE_ITER_with_updates, subvolume, s); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT) && inconsistent_if_not_found, trans->c, "missing subvolume %u", subvol); @@ -299,16 +299,15 @@ bch2_subvolume_get_inlined(struct btree_trans *trans, unsigned subvol, int bch2_subvolume_get(struct btree_trans *trans, unsigned subvol, bool inconsistent_if_not_found, - int iter_flags, struct bch_subvolume *s) { - return bch2_subvolume_get_inlined(trans, subvol, inconsistent_if_not_found, iter_flags, s); + return bch2_subvolume_get_inlined(trans, subvol, inconsistent_if_not_found, s); } int bch2_subvol_is_ro_trans(struct btree_trans *trans, u32 subvol) { struct bch_subvolume s; - int ret = bch2_subvolume_get_inlined(trans, subvol, true, 0, &s); + int ret = bch2_subvolume_get_inlined(trans, subvol, true, &s); if (ret) return ret; @@ -328,7 +327,7 @@ int bch2_snapshot_get_subvol(struct btree_trans *trans, u32 snapshot, struct bch_snapshot snap; return bch2_snapshot_lookup(trans, snapshot, &snap) ?: - bch2_subvolume_get(trans, le32_to_cpu(snap.subvol), true, 0, subvol); + bch2_subvolume_get(trans, le32_to_cpu(snap.subvol), true, subvol); } int __bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid, @@ -396,8 +395,7 @@ static int bch2_subvolumes_reparent(struct btree_trans *trans, u32 subvolid_to_d struct bch_subvolume s; return lockrestart_do(trans, - bch2_subvolume_get(trans, subvolid_to_delete, true, - BTREE_ITER_cached, &s)) ?: + bch2_subvolume_get(trans, subvolid_to_delete, true, &s)) ?: for_each_btree_key_commit(trans, iter, BTREE_ID_subvolumes, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, @@ -411,26 +409,56 @@ static int bch2_subvolumes_reparent(struct btree_trans *trans, u32 subvolid_to_d */ static int __bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid) { - struct btree_iter iter; - struct bkey_s_c_subvolume subvol; - u32 snapid; - int ret = 0; + struct btree_iter subvol_iter = {}, snapshot_iter = {}, snapshot_tree_iter = {}; - subvol = bch2_bkey_get_iter_typed(trans, &iter, + struct bkey_s_c_subvolume subvol = + bch2_bkey_get_iter_typed(trans, &subvol_iter, BTREE_ID_subvolumes, POS(0, subvolid), BTREE_ITER_cached|BTREE_ITER_intent, subvolume); - ret = bkey_err(subvol); + int ret = bkey_err(subvol); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, "missing subvolume %u", subvolid); if (ret) - return ret; + goto err; - snapid = le32_to_cpu(subvol.v->snapshot); + u32 snapid = le32_to_cpu(subvol.v->snapshot); - ret = bch2_btree_delete_at(trans, &iter, 0) ?: + struct bkey_s_c_snapshot snapshot = + bch2_bkey_get_iter_typed(trans, &snapshot_iter, + BTREE_ID_snapshots, POS(0, snapid), + 0, snapshot); + ret = bkey_err(subvol); + bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, + "missing snapshot %u", snapid); + if (ret) + goto err; + + u32 treeid = le32_to_cpu(snapshot.v->tree); + + struct bkey_s_c_snapshot_tree snapshot_tree = + bch2_bkey_get_iter_typed(trans, &snapshot_tree_iter, + BTREE_ID_snapshot_trees, POS(0, treeid), + 0, snapshot_tree); + + if (le32_to_cpu(snapshot_tree.v->master_subvol) == subvolid) { + struct bkey_i_snapshot_tree *snapshot_tree_mut = + bch2_bkey_make_mut_typed(trans, &snapshot_tree_iter, + &snapshot_tree.s_c, + 0, snapshot_tree); + ret = PTR_ERR_OR_ZERO(snapshot_tree_mut); + if (ret) + goto err; + + snapshot_tree_mut->v.master_subvol = 0; + } + + ret = bch2_btree_delete_at(trans, &subvol_iter, 0) ?: bch2_snapshot_node_set_deleted(trans, snapid); - bch2_trans_iter_exit(trans, &iter); +err: + bch2_trans_iter_exit(trans, &snapshot_tree_iter); + bch2_trans_iter_exit(trans, &snapshot_iter); + bch2_trans_iter_exit(trans, &subvol_iter); return ret; } @@ -675,7 +703,7 @@ err: /* set bi_subvol on root inode */ int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c) { - int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw, + int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, __bch2_fs_upgrade_for_subvolumes(trans)); bch_err_fn(c, ret); return ret; diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h index f897d106e142..910f6196700e 100644 --- a/fs/bcachefs/subvolume.h +++ b/fs/bcachefs/subvolume.h @@ -5,12 +5,11 @@ #include "darray.h" #include "subvolume_types.h" -enum bch_validate_flags; - int bch2_check_subvols(struct bch_fs *); int bch2_check_subvol_children(struct bch_fs *); -int bch2_subvolume_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_subvolume_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_subvolume_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_subvolume_trigger(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, @@ -25,7 +24,7 @@ int bch2_subvolume_trigger(struct btree_trans *, enum btree_id, unsigned, int bch2_subvol_has_children(struct btree_trans *, u32); int bch2_subvolume_get(struct btree_trans *, unsigned, - bool, int, struct bch_subvolume *); + bool, struct bch_subvolume *); int __bch2_subvolume_get_snapshot(struct btree_trans *, u32, u32 *, bool); int bch2_subvolume_get_snapshot(struct btree_trans *, u32, u32 *); @@ -34,7 +33,7 @@ int bch2_subvol_is_ro_trans(struct btree_trans *, u32); int bch2_subvol_is_ro(struct bch_fs *, u32); static inline struct bkey_s_c -bch2_btree_iter_peek_in_subvolume_upto_type(struct btree_iter *iter, struct bpos end, +bch2_btree_iter_peek_in_subvolume_max_type(struct btree_iter *iter, struct bpos end, u32 subvolid, unsigned flags) { u32 snapshot; @@ -43,10 +42,10 @@ bch2_btree_iter_peek_in_subvolume_upto_type(struct btree_iter *iter, struct bpos return bkey_s_c_err(ret); bch2_btree_iter_set_snapshot(iter, snapshot); - return bch2_btree_iter_peek_upto_type(iter, end, flags); + return bch2_btree_iter_peek_max_type(iter, end, flags); } -#define for_each_btree_key_in_subvolume_upto_continue(_trans, _iter, \ +#define for_each_btree_key_in_subvolume_max_continue(_trans, _iter, \ _end, _subvolid, _flags, _k, _do) \ ({ \ struct bkey_s_c _k; \ @@ -54,7 +53,7 @@ bch2_btree_iter_peek_in_subvolume_upto_type(struct btree_iter *iter, struct bpos \ do { \ _ret3 = lockrestart_do(_trans, ({ \ - (_k) = bch2_btree_iter_peek_in_subvolume_upto_type(&(_iter), \ + (_k) = bch2_btree_iter_peek_in_subvolume_max_type(&(_iter), \ _end, _subvolid, (_flags)); \ if (!(_k).k) \ break; \ @@ -67,14 +66,14 @@ bch2_btree_iter_peek_in_subvolume_upto_type(struct btree_iter *iter, struct bpos _ret3; \ }) -#define for_each_btree_key_in_subvolume_upto(_trans, _iter, _btree_id, \ +#define for_each_btree_key_in_subvolume_max(_trans, _iter, _btree_id, \ _start, _end, _subvolid, _flags, _k, _do) \ ({ \ struct btree_iter _iter; \ bch2_trans_iter_init((_trans), &(_iter), (_btree_id), \ (_start), (_flags)); \ \ - for_each_btree_key_in_subvolume_upto_continue(_trans, _iter, \ + for_each_btree_key_in_subvolume_max_continue(_trans, _iter, \ _end, _subvolid, _flags, _k, _do); \ }) diff --git a/fs/bcachefs/subvolume_types.h b/fs/bcachefs/subvolume_types.h index f2ec4277c2a5..1549d6daf7af 100644 --- a/fs/bcachefs/subvolume_types.h +++ b/fs/bcachefs/subvolume_types.h @@ -9,13 +9,13 @@ typedef DARRAY(u32) snapshot_id_list; #define IS_ANCESTOR_BITMAP 128 struct snapshot_t { + bool live; u32 parent; u32 skip[3]; u32 depth; u32 children[2]; u32 subvol; /* Nonzero only if a subvolume points to this node: */ u32 tree; - u32 equiv; unsigned long is_ancestor[BITS_TO_LONGS(IS_ANCESTOR_BITMAP)]; }; diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index 7c71594f6a8b..8037ccbacf6a 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -23,6 +23,7 @@ #include #include +#include static const struct blk_holder_ops bch2_sb_handle_bdev_ops = { }; @@ -41,7 +42,7 @@ static const struct bch2_metadata_version bch2_metadata_versions[] = { #undef x }; -void bch2_version_to_text(struct printbuf *out, unsigned v) +void bch2_version_to_text(struct printbuf *out, enum bcachefs_metadata_version v) { const char *str = "(unknown version)"; @@ -54,7 +55,7 @@ void bch2_version_to_text(struct printbuf *out, unsigned v) prt_printf(out, "%u.%u: %s", BCH_VERSION_MAJOR(v), BCH_VERSION_MINOR(v), str); } -unsigned bch2_latest_compatible_version(unsigned v) +enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_metadata_version v) { if (!BCH_VERSION_MAJOR(v)) return v; @@ -68,6 +69,16 @@ unsigned bch2_latest_compatible_version(unsigned v) return v; } +void bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version version) +{ + mutex_lock(&c->sb_lock); + SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb, + max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version)); + c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_FEATURE_incompat_version_field); + bch2_write_super(c); + mutex_unlock(&c->sb_lock); +} + const char * const bch2_sb_fields[] = { #define x(name, nr) #name, BCH_SB_FIELDS() @@ -368,6 +379,12 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, return -BCH_ERR_invalid_sb_features; } + if (BCH_VERSION_MAJOR(le16_to_cpu(sb->version)) > BCH_VERSION_MAJOR(bcachefs_metadata_version_current) || + BCH_SB_VERSION_INCOMPAT(sb) > bcachefs_metadata_version_current) { + prt_printf(out, "Filesystem has incompatible version"); + return -BCH_ERR_invalid_sb_features; + } + block_size = le16_to_cpu(sb->block_size); if (block_size > PAGE_SECTORS) { @@ -406,6 +423,21 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, return -BCH_ERR_invalid_sb_time_precision; } + /* old versions didn't know to downgrade this field */ + if (BCH_SB_VERSION_INCOMPAT_ALLOWED(sb) > le16_to_cpu(sb->version)) + SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(sb, le16_to_cpu(sb->version)); + + if (BCH_SB_VERSION_INCOMPAT(sb) > BCH_SB_VERSION_INCOMPAT_ALLOWED(sb)) { + prt_printf(out, "Invalid version_incompat "); + bch2_version_to_text(out, BCH_SB_VERSION_INCOMPAT(sb)); + prt_str(out, " > incompat_allowed "); + bch2_version_to_text(out, BCH_SB_VERSION_INCOMPAT_ALLOWED(sb)); + if (flags & BCH_VALIDATE_write) + return -BCH_ERR_invalid_sb_version; + else + SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(sb, BCH_SB_VERSION_INCOMPAT(sb)); + } + if (!flags) { /* * Been seeing a bug where these are getting inexplicably @@ -428,6 +460,11 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, SET_BCH_SB_PROMOTE_WHOLE_EXTENTS(sb, true); } +#ifdef __KERNEL__ + if (!BCH_SB_SHARD_INUMS_NBITS(sb)) + SET_BCH_SB_SHARD_INUMS_NBITS(sb, ilog2(roundup_pow_of_two(num_online_cpus()))); +#endif + for (opt_id = 0; opt_id < bch2_opts_nr; opt_id++) { const struct bch_option *opt = bch2_opt_table + opt_id; @@ -519,6 +556,9 @@ static void bch2_sb_update(struct bch_fs *c) c->sb.uuid = src->uuid; c->sb.user_uuid = src->user_uuid; c->sb.version = le16_to_cpu(src->version); + c->sb.version_incompat = BCH_SB_VERSION_INCOMPAT(src); + c->sb.version_incompat_allowed + = BCH_SB_VERSION_INCOMPAT_ALLOWED(src); c->sb.version_min = le16_to_cpu(src->version_min); c->sb.version_upgrade_complete = BCH_SB_VERSION_UPGRADE_COMPLETE(src); c->sb.nr_devices = src->nr_devices; @@ -676,7 +716,8 @@ reread: } enum bch_csum_type csum_type = BCH_SB_CSUM_TYPE(sb->sb); - if (csum_type >= BCH_CSUM_NR) { + if (csum_type >= BCH_CSUM_NR || + bch2_csum_type_is_encryption(csum_type)) { prt_printf(err, "unknown checksum type %llu", BCH_SB_CSUM_TYPE(sb->sb)); return -BCH_ERR_invalid_sb_csum_type; } @@ -878,7 +919,7 @@ static void write_super_endio(struct bio *bio) ? BCH_MEMBER_ERROR_write : BCH_MEMBER_ERROR_read, "superblock %s error: %s", - bio_data_dir(bio) ? "write" : "read", + str_write_read(bio_data_dir(bio)), bch2_blk_status_to_str(bio->bi_status))) ca->sb_write_error = 1; @@ -891,14 +932,15 @@ static void read_back_super(struct bch_fs *c, struct bch_dev *ca) struct bch_sb *sb = ca->disk_sb.sb; struct bio *bio = ca->disk_sb.bio; + memset(ca->sb_read_scratch, 0, BCH_SB_READ_SCRATCH_BUF_SIZE); + bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ|REQ_SYNC|REQ_META); bio->bi_iter.bi_sector = le64_to_cpu(sb->layout.sb_offset[0]); bio->bi_end_io = write_super_endio; bio->bi_private = ca; - bch2_bio_map(bio, ca->sb_read_scratch, PAGE_SIZE); + bch2_bio_map(bio, ca->sb_read_scratch, BCH_SB_READ_SCRATCH_BUF_SIZE); - this_cpu_add(ca->io_done->sectors[READ][BCH_DATA_sb], - bio_sectors(bio)); + this_cpu_add(ca->io_done->sectors[READ][BCH_DATA_sb], bio_sectors(bio)); percpu_ref_get(&ca->io_ref); closure_bio_submit(bio, &c->sb_write); @@ -1042,9 +1084,16 @@ int bch2_write_super(struct bch_fs *c) ": Superblock write was silently dropped! (seq %llu expected %llu)", le64_to_cpu(ca->sb_read_scratch->seq), ca->disk_sb.seq); - bch2_fs_fatal_error(c, "%s", buf.buf); + + if (c->opts.errors != BCH_ON_ERROR_continue && + c->opts.errors != BCH_ON_ERROR_fix_safe) { + ret = -BCH_ERR_erofs_sb_err; + bch2_fs_fatal_error(c, "%s", buf.buf); + } else { + bch_err(c, "%s", buf.buf); + } + printbuf_exit(&buf); - ret = -BCH_ERR_erofs_sb_err; } if (le64_to_cpu(ca->sb_read_scratch->seq) > ca->disk_sb.seq) { @@ -1149,6 +1198,8 @@ bool bch2_check_version_downgrade(struct bch_fs *c) */ if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current) SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current); + if (BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb) > bcachefs_metadata_version_current) + SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb, bcachefs_metadata_version_current); if (c->sb.version > bcachefs_metadata_version_current) c->disk_sb.sb->version = cpu_to_le16(bcachefs_metadata_version_current); if (c->sb.version_min > bcachefs_metadata_version_current) @@ -1157,7 +1208,7 @@ bool bch2_check_version_downgrade(struct bch_fs *c) return ret; } -void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version) +void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version, bool incompat) { lockdep_assert_held(&c->sb_lock); @@ -1167,6 +1218,10 @@ void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version) c->disk_sb.sb->version = cpu_to_le16(new_version); c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALL); + + if (incompat) + SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb, + max(BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb), new_version)); } static int bch2_sb_ext_validate(struct bch_sb *sb, struct bch_sb_field *f, @@ -1331,6 +1386,14 @@ void bch2_sb_to_text(struct printbuf *out, struct bch_sb *sb, bch2_version_to_text(out, le16_to_cpu(sb->version)); prt_newline(out); + prt_printf(out, "Incompatible features allowed:\t"); + bch2_version_to_text(out, BCH_SB_VERSION_INCOMPAT_ALLOWED(sb)); + prt_newline(out); + + prt_printf(out, "Incompatible features in use:\t"); + bch2_version_to_text(out, BCH_SB_VERSION_INCOMPAT(sb)); + prt_newline(out); + prt_printf(out, "Version upgrade complete:\t"); bch2_version_to_text(out, BCH_SB_VERSION_UPGRADE_COMPLETE(sb)); prt_newline(out); diff --git a/fs/bcachefs/super-io.h b/fs/bcachefs/super-io.h index fadd364e2802..f1ab4f943720 100644 --- a/fs/bcachefs/super-io.h +++ b/fs/bcachefs/super-io.h @@ -10,14 +10,29 @@ #include +#define BCH_SB_READ_SCRATCH_BUF_SIZE 4096 + static inline bool bch2_version_compatible(u16 version) { return BCH_VERSION_MAJOR(version) <= BCH_VERSION_MAJOR(bcachefs_metadata_version_current) && version >= bcachefs_metadata_version_min; } -void bch2_version_to_text(struct printbuf *, unsigned); -unsigned bch2_latest_compatible_version(unsigned); +void bch2_version_to_text(struct printbuf *, enum bcachefs_metadata_version); +enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_metadata_version); + +void bch2_set_version_incompat(struct bch_fs *, enum bcachefs_metadata_version); + +static inline bool bch2_request_incompat_feature(struct bch_fs *c, + enum bcachefs_metadata_version version) +{ + if (unlikely(version > c->sb.version_incompat)) { + if (version > c->sb.version_incompat_allowed) + return false; + bch2_set_version_incompat(c, version); + } + return true; +} static inline size_t bch2_sb_field_bytes(struct bch_sb_field *f) { @@ -92,7 +107,7 @@ static inline void bch2_check_set_feature(struct bch_fs *c, unsigned feat) } bool bch2_check_version_downgrade(struct bch_fs *); -void bch2_sb_upgrade(struct bch_fs *, unsigned); +void bch2_sb_upgrade(struct bch_fs *, unsigned, bool); void __bch2_sb_field_to_text(struct printbuf *, struct bch_sb *, struct bch_sb_field *); diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index a6ed9a0bf1c7..d97ea7bd1171 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -290,7 +290,7 @@ static void __bch2_fs_read_only(struct bch_fs *c) bch2_fs_journal_stop(&c->journal); - bch_info(c, "%sshutdown complete, journal seq %llu", + bch_info(c, "%sclean shutdown complete, journal seq %llu", test_bit(BCH_FS_clean_shutdown, &c->flags) ? "" : "un", c->journal.seq_ondisk); @@ -441,6 +441,8 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early) { int ret; + BUG_ON(!test_bit(BCH_FS_may_go_rw, &c->flags)); + if (test_bit(BCH_FS_initial_gc_unfixed, &c->flags)) { bch_err(c, "cannot go rw, unfixed btree errors"); return -BCH_ERR_erofs_unfixed_errors; @@ -561,6 +563,7 @@ static void __bch2_fs_free(struct bch_fs *c) bch2_io_clock_exit(&c->io_clock[WRITE]); bch2_io_clock_exit(&c->io_clock[READ]); bch2_fs_compress_exit(c); + bch2_fs_btree_gc_exit(c); bch2_journal_keys_put_initial(c); bch2_find_btree_nodes_exit(&c->found_btree_nodes); BUG_ON(atomic_read(&c->journal_keys.ref)); @@ -584,7 +587,6 @@ static void __bch2_fs_free(struct bch_fs *c) #endif kfree(rcu_dereference_protected(c->disk_groups, 1)); kfree(c->journal_seq_blacklist_table); - kfree(c->unused_inode_hints); if (c->write_ref_wq) destroy_workqueue(c->write_ref_wq); @@ -766,21 +768,17 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) refcount_set(&c->ro_ref, 1); init_waitqueue_head(&c->ro_ref_wait); + spin_lock_init(&c->recovery_pass_lock); sema_init(&c->online_fsck_mutex, 1); - init_rwsem(&c->gc_lock); - mutex_init(&c->gc_gens_lock); - atomic_set(&c->journal_keys.ref, 1); - c->journal_keys.initial_ref_held = true; - for (i = 0; i < BCH_TIME_STAT_NR; i++) bch2_time_stats_init(&c->times[i]); - bch2_fs_gc_init(c); bch2_fs_copygc_init(c); bch2_fs_btree_key_cache_init_early(&c->btree_key_cache); bch2_fs_btree_iter_init_early(c); bch2_fs_btree_interior_update_init_early(c); + bch2_fs_journal_keys_init(c); bch2_fs_allocator_background_init(c); bch2_fs_allocator_foreground_init(c); bch2_fs_rebalance_init(c); @@ -809,9 +807,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) INIT_LIST_HEAD(&c->vfs_inodes_list); mutex_init(&c->vfs_inodes_lock); - c->copy_gc_enabled = 1; - c->rebalance.enabled = 1; - c->journal.flush_write_time = &c->times[BCH_TIME_journal_flush_write]; c->journal.noflush_write_time = &c->times[BCH_TIME_journal_noflush_write]; c->journal.flush_seq_time = &c->times[BCH_TIME_journal_flush_seq]; @@ -873,8 +868,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) (btree_blocks(c) + 1) * 2 * sizeof(struct sort_iter_set); - c->inode_shard_bits = ilog2(roundup_pow_of_two(num_possible_cpus())); - if (!(c->btree_update_wq = alloc_workqueue("bcachefs", WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_UNBOUND, 512)) || !(c->btree_io_complete_wq = alloc_workqueue("bcachefs_btree_io", @@ -901,9 +894,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) !(c->online_reserved = alloc_percpu(u64)) || mempool_init_kvmalloc_pool(&c->btree_bounce_pool, 1, c->opts.btree_node_size) || - mempool_init_kmalloc_pool(&c->large_bkey_pool, 1, 2048) || - !(c->unused_inode_hints = kcalloc(1U << c->inode_shard_bits, - sizeof(u64), GFP_KERNEL))) { + mempool_init_kmalloc_pool(&c->large_bkey_pool, 1, 2048)) { ret = -BCH_ERR_ENOMEM_fs_other_alloc; goto err; } @@ -917,6 +908,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) bch2_fs_btree_cache_init(c) ?: bch2_fs_btree_key_cache_init(&c->btree_key_cache) ?: bch2_fs_btree_interior_update_init(c) ?: + bch2_fs_btree_gc_init(c) ?: bch2_fs_buckets_waiting_for_journal_init(c) ?: bch2_fs_btree_write_buffer_init(c) ?: bch2_fs_subvolumes_init(c) ?: @@ -1033,9 +1025,12 @@ int bch2_fs_start(struct bch_fs *c) bch2_dev_allocator_add(c, ca); bch2_recalc_capacity(c); + c->recovery_task = current; ret = BCH_SB_INITIALIZED(c->disk_sb.sb) ? bch2_fs_recovery(c) : bch2_fs_initialize(c); + c->recovery_task = NULL; + if (ret) goto err; @@ -1120,12 +1115,12 @@ static int bch2_dev_in_fs(struct bch_sb_handle *fs, prt_bdevname(&buf, fs->bdev); prt_char(&buf, ' '); - bch2_prt_datetime(&buf, le64_to_cpu(fs->sb->write_time));; + bch2_prt_datetime(&buf, le64_to_cpu(fs->sb->write_time)); prt_newline(&buf); prt_bdevname(&buf, sb->bdev); prt_char(&buf, ' '); - bch2_prt_datetime(&buf, le64_to_cpu(sb->sb->write_time));; + bch2_prt_datetime(&buf, le64_to_cpu(sb->sb->write_time)); prt_newline(&buf); if (!opts->no_splitbrain_check) @@ -1198,7 +1193,7 @@ static void bch2_dev_free(struct bch_dev *ca) free_percpu(ca->io_done); bch2_dev_buckets_free(ca); - free_page((unsigned long) ca->sb_read_scratch); + kfree(ca->sb_read_scratch); bch2_time_stats_quantiles_exit(&ca->io_latency[WRITE]); bch2_time_stats_quantiles_exit(&ca->io_latency[READ]); @@ -1309,8 +1304,6 @@ static struct bch_dev *__bch2_dev_alloc(struct bch_fs *c, init_completion(&ca->ref_completion); init_completion(&ca->io_ref_completion); - init_rwsem(&ca->bucket_lock); - INIT_WORK(&ca->io_error_work, bch2_io_error_work); bch2_time_stats_quantiles_init(&ca->io_latency[READ]); @@ -1337,7 +1330,7 @@ static struct bch_dev *__bch2_dev_alloc(struct bch_fs *c, if (percpu_ref_init(&ca->io_ref, bch2_dev_io_ref_complete, PERCPU_REF_INIT_DEAD, GFP_KERNEL) || - !(ca->sb_read_scratch = (void *) __get_free_page(GFP_KERNEL)) || + !(ca->sb_read_scratch = kmalloc(BCH_SB_READ_SCRATCH_BUF_SIZE, GFP_KERNEL)) || bch2_dev_buckets_alloc(c, ca) || !(ca->io_done = alloc_percpu(*ca->io_done))) goto err; @@ -1366,7 +1359,6 @@ static int bch2_dev_alloc(struct bch_fs *c, unsigned dev_idx) { struct bch_member member = bch2_sb_member_get(c->disk_sb.sb, dev_idx); struct bch_dev *ca = NULL; - int ret = 0; if (bch2_fs_init_fault("dev_alloc")) goto err; @@ -1378,10 +1370,8 @@ static int bch2_dev_alloc(struct bch_fs *c, unsigned dev_idx) ca->fs = c; bch2_dev_attach(c, ca, dev_idx); - return ret; + return 0; err: - if (ca) - bch2_dev_free(ca); return -BCH_ERR_ENOMEM_dev_alloc; } @@ -1751,11 +1741,6 @@ int bch2_dev_add(struct bch_fs *c, const char *path) if (ret) goto err; - ret = bch2_dev_journal_alloc(ca, true); - bch_err_msg(c, ret, "allocating journal"); - if (ret) - goto err; - down_write(&c->state_lock); mutex_lock(&c->sb_lock); @@ -1806,11 +1791,14 @@ int bch2_dev_add(struct bch_fs *c, const char *path) if (ret) goto err_late; - ca->new_fs_bucket_idx = 0; - if (ca->mi.state == BCH_MEMBER_STATE_rw) __bch2_dev_read_write(c, ca); + ret = bch2_dev_journal_alloc(ca, false); + bch_err_msg(c, ret, "allocating journal"); + if (ret) + goto err_late; + up_write(&c->state_lock); return 0; diff --git a/fs/bcachefs/super.h b/fs/bcachefs/super.h index dada09331d2e..fa6d52216510 100644 --- a/fs/bcachefs/super.h +++ b/fs/bcachefs/super.h @@ -34,16 +34,6 @@ void bch2_fs_read_only(struct bch_fs *); int bch2_fs_read_write(struct bch_fs *); int bch2_fs_read_write_early(struct bch_fs *); -/* - * Only for use in the recovery/fsck path: - */ -static inline void bch2_fs_lazy_rw(struct bch_fs *c) -{ - if (!test_bit(BCH_FS_rw, &c->flags) && - !test_bit(BCH_FS_was_rw, &c->flags)) - bch2_fs_read_write_early(c); -} - void __bch2_fs_stop(struct bch_fs *); void bch2_fs_free(struct bch_fs *); void bch2_fs_stop(struct bch_fs *); diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c index 03e59f86f360..a7eb1f511484 100644 --- a/fs/bcachefs/sysfs.c +++ b/fs/bcachefs/sysfs.c @@ -146,7 +146,7 @@ write_attribute(trigger_journal_writes); write_attribute(trigger_btree_cache_shrink); write_attribute(trigger_btree_key_cache_shrink); write_attribute(trigger_freelist_wakeup); -rw_attribute(gc_gens_pos); +read_attribute(gc_gens_pos); read_attribute(uuid); read_attribute(minor); @@ -203,7 +203,6 @@ read_attribute(disk_groups); read_attribute(has_data); read_attribute(alloc_debug); -read_attribute(accounting); read_attribute(usage_base); #define x(t, n, ...) read_attribute(t); @@ -211,12 +210,11 @@ BCH_PERSISTENT_COUNTERS() #undef x rw_attribute(discard); +read_attribute(state); rw_attribute(label); -rw_attribute(copy_gc_enabled); read_attribute(copy_gc_wait); -rw_attribute(rebalance_enabled); sysfs_pd_controller_attribute(rebalance); read_attribute(rebalance_status); @@ -237,11 +235,6 @@ write_attribute(perf_test); BCH_TIME_STATS() #undef x -static struct attribute sysfs_state_rw = { - .name = "state", - .mode = 0444, -}; - static size_t bch2_btree_cache_size(struct bch_fs *c) { struct btree_cache *bc = &c->btree_cache; @@ -302,7 +295,8 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c static void bch2_gc_gens_pos_to_text(struct printbuf *out, struct bch_fs *c) { - prt_printf(out, "%s: ", bch2_btree_id_str(c->gc_gens_btree)); + bch2_btree_id_to_text(out, c->gc_gens_btree); + prt_printf(out, ": "); bch2_bpos_to_text(out, c->gc_gens_pos); prt_printf(out, "\n"); } @@ -339,9 +333,6 @@ SHOW(bch2_fs) if (attr == &sysfs_gc_gens_pos) bch2_gc_gens_pos_to_text(out, c); - sysfs_printf(copy_gc_enabled, "%i", c->copy_gc_enabled); - - sysfs_printf(rebalance_enabled, "%i", c->rebalance.enabled); sysfs_pd_controller_show(rebalance, &c->rebalance.pd); /* XXX */ if (attr == &sysfs_copy_gc_wait) @@ -405,9 +396,6 @@ SHOW(bch2_fs) if (attr == &sysfs_alloc_debug) bch2_fs_alloc_debug_to_text(out, c); - if (attr == &sysfs_accounting) - bch2_fs_accounting_to_text(out, c); - if (attr == &sysfs_usage_base) bch2_fs_usage_base_to_text(out, c); @@ -418,23 +406,6 @@ STORE(bch2_fs) { struct bch_fs *c = container_of(kobj, struct bch_fs, kobj); - if (attr == &sysfs_copy_gc_enabled) { - ssize_t ret = strtoul_safe(buf, c->copy_gc_enabled) - ?: (ssize_t) size; - - if (c->copygc_thread) - wake_up_process(c->copygc_thread); - return ret; - } - - if (attr == &sysfs_rebalance_enabled) { - ssize_t ret = strtoul_safe(buf, c->rebalance.enabled) - ?: (ssize_t) size; - - rebalance_wakeup(c); - return ret; - } - sysfs_pd_controller_store(rebalance, &c->rebalance.pd); /* Debugging: */ @@ -534,15 +505,22 @@ SHOW(bch2_fs_counters) printbuf_tabstop_push(out, 32); - #define x(t, ...) \ + #define x(t, n, f, ...) \ if (attr == &sysfs_##t) { \ counter = percpu_u64_get(&c->counters[BCH_COUNTER_##t]);\ counter_since_mount = counter - c->counters_on_mount[BCH_COUNTER_##t];\ + if (f & TYPE_SECTORS) { \ + counter <<= 9; \ + counter_since_mount <<= 9; \ + } \ + \ prt_printf(out, "since mount:\t"); \ + (f & TYPE_COUNTER) ? prt_u64(out, counter_since_mount) :\ prt_human_readable_u64(out, counter_since_mount); \ prt_newline(out); \ \ prt_printf(out, "since filesystem creation:\t"); \ + (f & TYPE_COUNTER) ? prt_u64(out, counter) : \ prt_human_readable_u64(out, counter); \ prt_newline(out); \ } @@ -610,10 +588,8 @@ struct attribute *bch2_fs_internal_files[] = { &sysfs_gc_gens_pos, - &sysfs_copy_gc_enabled, &sysfs_copy_gc_wait, - &sysfs_rebalance_enabled, sysfs_pd_controller_files(rebalance), &sysfs_moving_ctxts, @@ -622,7 +598,6 @@ struct attribute *bch2_fs_internal_files[] = { &sysfs_disk_groups, &sysfs_alloc_debug, - &sysfs_accounting, &sysfs_usage_base, NULL }; @@ -682,6 +657,13 @@ STORE(bch2_fs_opts_dir) (id == Opt_compression && !c->opts.background_compression))) bch2_set_rebalance_needs_scan(c, 0); + if (v && id == Opt_rebalance_enabled) + rebalance_wakeup(c); + + if (v && id == Opt_copygc_enabled && + c->copygc_thread) + wake_up_process(c->copygc_thread); + ret = size; err: bch2_write_ref_put(c, BCH_WRITE_REF_sysfs); @@ -790,7 +772,7 @@ SHOW(bch2_dev) prt_char(out, '\n'); } - if (attr == &sysfs_state_rw) { + if (attr == &sysfs_state) { prt_string_option(out, bch2_member_states, ca->mi.state); prt_char(out, '\n'); } @@ -870,7 +852,7 @@ struct attribute *bch2_dev_files[] = { /* settings: */ &sysfs_discard, - &sysfs_state_rw, + &sysfs_state, &sysfs_label, &sysfs_has_data, diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c index fb5c1543e52f..6c6469814637 100644 --- a/fs/bcachefs/tests.c +++ b/fs/bcachefs/tests.c @@ -131,7 +131,7 @@ static int test_iterate(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_max(trans, iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, ({ BUG_ON(k.k->p.offset != i++); @@ -186,7 +186,7 @@ static int test_iterate_extents(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, ({ BUG_ON(bkey_start_offset(k.k) != i); @@ -242,7 +242,7 @@ static int test_iterate_slots(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_max(trans, iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, ({ BUG_ON(k.k->p.offset != i); @@ -259,7 +259,7 @@ static int test_iterate_slots(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_max(trans, iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), BTREE_ITER_slots, k, ({ if (i >= nr * 2) @@ -302,7 +302,7 @@ static int test_iterate_slots_extents(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, ({ BUG_ON(bkey_start_offset(k.k) != i + 8); @@ -320,7 +320,7 @@ static int test_iterate_slots_extents(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), BTREE_ITER_slots, k, ({ if (i == nr) @@ -349,10 +349,10 @@ static int test_peek_end(struct bch_fs *c, u64 nr) bch2_trans_iter_init(trans, &iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), 0); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k); bch2_trans_iter_exit(trans, &iter); @@ -369,10 +369,10 @@ static int test_peek_end_extents(struct bch_fs *c, u64 nr) bch2_trans_iter_init(trans, &iter, BTREE_ID_extents, SPOS(0, 0, U32_MAX), 0); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k); bch2_trans_iter_exit(trans, &iter); @@ -488,7 +488,7 @@ static int test_snapshot_filter(struct bch_fs *c, u32 snapid_lo, u32 snapid_hi) trans = bch2_trans_get(c); bch2_trans_iter_init(trans, &iter, BTREE_ID_xattrs, SPOS(0, 0, snapid_lo), 0); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k->p.snapshot != U32_MAX); @@ -672,7 +672,7 @@ static int __do_delete(struct btree_trans *trans, struct bpos pos) bch2_trans_iter_init(trans, &iter, BTREE_ID_xattrs, pos, BTREE_ITER_intent); - k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)); + k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)); ret = bkey_err(k); if (ret) goto err; @@ -726,7 +726,7 @@ static int seq_insert(struct bch_fs *c, u64 nr) static int seq_lookup(struct bch_fs *c, u64 nr) { return bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_max(trans, iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, 0)); diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h index 5597b9d6297f..56a5a7fbc0fd 100644 --- a/fs/bcachefs/trace.h +++ b/fs/bcachefs/trace.h @@ -199,6 +199,30 @@ DECLARE_EVENT_CLASS(bio, (unsigned long long)__entry->sector, __entry->nr_sector) ); +/* disk_accounting.c */ + +TRACE_EVENT(accounting_mem_insert, + TP_PROTO(struct bch_fs *c, const char *acc), + TP_ARGS(c, acc), + + TP_STRUCT__entry( + __field(dev_t, dev ) + __field(unsigned, new_nr ) + __string(acc, acc ) + ), + + TP_fast_assign( + __entry->dev = c->dev; + __entry->new_nr = c->accounting.k.nr; + __assign_str(acc); + ), + + TP_printk("%d,%d entries %u added %s", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->new_nr, + __get_str(acc)) +); + /* fs.c: */ TRACE_EVENT(bch2_sync_fs, TP_PROTO(struct super_block *sb, int wait), @@ -848,8 +872,8 @@ TRACE_EVENT(move_data, TRACE_EVENT(evacuate_bucket, TP_PROTO(struct bch_fs *c, struct bpos *bucket, unsigned sectors, unsigned bucket_size, - u64 fragmentation, int ret), - TP_ARGS(c, bucket, sectors, bucket_size, fragmentation, ret), + int ret), + TP_ARGS(c, bucket, sectors, bucket_size, ret), TP_STRUCT__entry( __field(dev_t, dev ) @@ -857,7 +881,6 @@ TRACE_EVENT(evacuate_bucket, __field(u64, bucket ) __field(u32, sectors ) __field(u32, bucket_size ) - __field(u64, fragmentation ) __field(int, ret ) ), @@ -867,45 +890,42 @@ TRACE_EVENT(evacuate_bucket, __entry->bucket = bucket->offset; __entry->sectors = sectors; __entry->bucket_size = bucket_size; - __entry->fragmentation = fragmentation; __entry->ret = ret; ), - TP_printk("%d,%d %llu:%llu sectors %u/%u fragmentation %llu ret %i", + TP_printk("%d,%d %llu:%llu sectors %u/%u ret %i", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->member, __entry->bucket, __entry->sectors, __entry->bucket_size, - __entry->fragmentation, __entry->ret) + __entry->ret) ); TRACE_EVENT(copygc, TP_PROTO(struct bch_fs *c, - u64 sectors_moved, u64 sectors_not_moved, - u64 buckets_moved, u64 buckets_not_moved), - TP_ARGS(c, - sectors_moved, sectors_not_moved, - buckets_moved, buckets_not_moved), + u64 buckets, + u64 sectors_seen, + u64 sectors_moved), + TP_ARGS(c, buckets, sectors_seen, sectors_moved), TP_STRUCT__entry( __field(dev_t, dev ) + __field(u64, buckets ) + __field(u64, sectors_seen ) __field(u64, sectors_moved ) - __field(u64, sectors_not_moved ) - __field(u64, buckets_moved ) - __field(u64, buckets_not_moved ) ), TP_fast_assign( __entry->dev = c->dev; + __entry->buckets = buckets; + __entry->sectors_seen = sectors_seen; __entry->sectors_moved = sectors_moved; - __entry->sectors_not_moved = sectors_not_moved; - __entry->buckets_moved = buckets_moved; - __entry->buckets_not_moved = buckets_moved; ), - TP_printk("%d,%d sectors moved %llu remain %llu buckets moved %llu remain %llu", + TP_printk("%d,%d buckets %llu sectors seen %llu moved %llu", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->sectors_moved, __entry->sectors_not_moved, - __entry->buckets_moved, __entry->buckets_not_moved) + __entry->buckets, + __entry->sectors_seen, + __entry->sectors_moved) ); TRACE_EVENT(copygc_wait, @@ -1316,6 +1336,12 @@ TRACE_EVENT(trans_restart_key_cache_key_realloced, __entry->new_u64s) ); +DEFINE_EVENT(transaction_event, trans_restart_write_buffer_flush, + TP_PROTO(struct btree_trans *trans, + unsigned long caller_ip), + TP_ARGS(trans, caller_ip) +); + TRACE_EVENT(path_downgrade, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, @@ -1352,10 +1378,21 @@ TRACE_EVENT(path_downgrade, __entry->pos_snapshot) ); -DEFINE_EVENT(transaction_event, trans_restart_write_buffer_flush, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip), - TP_ARGS(trans, caller_ip) +TRACE_EVENT(key_cache_fill, + TP_PROTO(struct btree_trans *trans, const char *key), + TP_ARGS(trans, key), + + TP_STRUCT__entry( + __array(char, trans_fn, 32 ) + __string(key, key ) + ), + + TP_fast_assign( + strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn)); + __assign_str(key); + ), + + TP_printk("%s %s", __entry->trans_fn, __get_str(key)) ); TRACE_EVENT(write_buffer_flush, @@ -1414,6 +1451,24 @@ TRACE_EVENT(write_buffer_flush_slowpath, TP_printk("%zu/%zu", __entry->slowpath, __entry->total) ); +TRACE_EVENT(write_buffer_maybe_flush, + TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, const char *key), + TP_ARGS(trans, caller_ip, key), + + TP_STRUCT__entry( + __array(char, trans_fn, 32 ) + __field(unsigned long, caller_ip ) + __string(key, key ) + ), + + TP_fast_assign( + strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn)); + __assign_str(key); + ), + + TP_printk("%s %pS %s", __entry->trans_fn, (void *) __entry->caller_ip, __get_str(key)) +); + DEFINE_EVENT(fs_str, rebalance_extent, TP_PROTO(struct bch_fs *c, const char *str), TP_ARGS(c, str) diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h index fb02c1c36004..e7c3541b38f3 100644 --- a/fs/bcachefs/util.h +++ b/fs/bcachefs/util.h @@ -55,6 +55,16 @@ static inline size_t buf_pages(void *p, size_t len) PAGE_SIZE); } +static inline void *bch2_kvmalloc(size_t n, gfp_t flags) +{ + void *p = unlikely(n >= INT_MAX) + ? vmalloc(n) + : kvmalloc(n, flags & ~__GFP_ZERO); + if (p && (flags & __GFP_ZERO)) + memset(p, 0, n); + return p; +} + #define init_heap(heap, _size, gfp) \ ({ \ (heap)->nr = 0; \ @@ -317,6 +327,19 @@ do { \ _ptr ? container_of(_ptr, type, member) : NULL; \ }) +static inline struct list_head *list_pop(struct list_head *head) +{ + if (list_empty(head)) + return NULL; + + struct list_head *ret = head->next; + list_del_init(ret); + return ret; +} + +#define list_pop_entry(head, type, member) \ + container_of_or_null(list_pop(head), type, member) + /* Does linear interpolation between powers of two */ static inline unsigned fract_exp_two(unsigned x, unsigned fract_bits) { @@ -647,8 +670,6 @@ static inline int cmp_le32(__le32 l, __le32 r) #include -#define QSTR(n) { { { .len = strlen(n) } }, .name = n } - static inline bool qstr_eq(const struct qstr l, const struct qstr r) { return l.len == r.len && !memcmp(l.name, r.name, l.len); @@ -696,4 +717,13 @@ static inline bool test_bit_le64(size_t bit, __le64 *addr) return (addr[bit / 64] & cpu_to_le64(BIT_ULL(bit % 64))) != 0; } +static inline void memcpy_swab(void *_dst, void *_src, size_t len) +{ + u8 *dst = _dst + len; + u8 *src = _src; + + while (len--) + *--dst = *src++; +} + #endif /* _BCACHEFS_UTIL_H */ diff --git a/fs/bcachefs/varint.c b/fs/bcachefs/varint.c index 6a78553d9b0c..6620ecae26af 100644 --- a/fs/bcachefs/varint.c +++ b/fs/bcachefs/varint.c @@ -9,6 +9,7 @@ #include #endif +#include "errcode.h" #include "varint.h" /** @@ -53,7 +54,7 @@ int bch2_varint_decode(const u8 *in, const u8 *end, u64 *out) u64 v; if (unlikely(in + bytes > end)) - return -1; + return -BCH_ERR_varint_decode_error; if (likely(bytes < 9)) { __le64 v_le = 0; @@ -115,7 +116,7 @@ int bch2_varint_decode_fast(const u8 *in, const u8 *end, u64 *out) unsigned bytes = ffz(*in) + 1; if (unlikely(in + bytes > end)) - return -1; + return -BCH_ERR_varint_decode_error; if (likely(bytes < 9)) { v >>= bytes; diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c index 952aca400faf..aed7c6984173 100644 --- a/fs/bcachefs/xattr.c +++ b/fs/bcachefs/xattr.c @@ -71,7 +71,7 @@ const struct bch_hash_desc bch2_xattr_hash_desc = { }; int bch2_xattr_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_xattr xattr = bkey_s_c_to_xattr(k); unsigned val_u64s = xattr_val_u64s(xattr.v->x_name_len, @@ -309,7 +309,7 @@ ssize_t bch2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size) u64 offset = 0, inum = inode->ei_inode.bi_inum; int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_xattrs, POS(inum, offset), POS(inum, U64_MAX), inode->ei_inum.subvol, 0, k, ({ @@ -565,13 +565,6 @@ static int bch2_xattr_bcachefs_set(const struct xattr_handler *handler, ret = bch2_write_inode(c, inode, inode_opt_set_fn, &s, 0); err: mutex_unlock(&inode->ei_update_lock); - - if (value && - (opt_id == Opt_background_target || - opt_id == Opt_background_compression || - (opt_id == Opt_compression && !inode_opt_get(c, &inode->ei_inode, background_compression)))) - bch2_set_rebalance_needs_scan(c, inode->ei_inode.bi_inum); - err_class_exit: return bch2_err_class(ret); } @@ -609,7 +602,7 @@ static const struct xattr_handler bch_xattr_bcachefs_effective_handler = { #endif /* NO_BCACHEFS_FS */ -const struct xattr_handler *bch2_xattr_handlers[] = { +const struct xattr_handler * const bch2_xattr_handlers[] = { &bch_xattr_user_handler, &bch_xattr_trusted_handler, &bch_xattr_security_handler, diff --git a/fs/bcachefs/xattr.h b/fs/bcachefs/xattr.h index c188a5ad64ce..132fbbd15a66 100644 --- a/fs/bcachefs/xattr.h +++ b/fs/bcachefs/xattr.h @@ -6,7 +6,8 @@ extern const struct bch_hash_desc bch2_xattr_hash_desc; -int bch2_xattr_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_xattr_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_xattr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_xattr ((struct bkey_ops) { \ @@ -44,6 +45,6 @@ int bch2_xattr_set(struct btree_trans *, subvol_inum, ssize_t bch2_xattr_list(struct dentry *, char *, size_t); -extern const struct xattr_handler *bch2_xattr_handlers[]; +extern const struct xattr_handler * const bch2_xattr_handlers[]; #endif /* _BCACHEFS_XATTR_H */ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 106f0e8af177..8054f44d39cf 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1257,7 +1257,7 @@ out_free_interp: } reloc_func_desc = interp_load_addr; - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); fput(interpreter); kfree(interp_elf_ex); @@ -1354,7 +1354,7 @@ out_free_dentry: kfree(interp_elf_ex); kfree(interp_elf_phdata); out_free_file: - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); if (interpreter) fput(interpreter); out_free_ph: diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index f1a7c4875c4a..c13ee8180b17 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -394,7 +394,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) goto error; } - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); fput(interpreter); interpreter = NULL; } @@ -467,7 +467,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) error: if (interpreter) { - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); fput(interpreter); } kfree(interpreter_name); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 390808ce935d..b5b5ca1a44f7 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -478,7 +478,7 @@ static int load_flat_file(struct linux_binprm *bprm, * 28 bits (256 MB) is way more than reasonable in this case. * If some top bits are set we have probable binary corruption. */ - if ((text_len | data_len | bss_len | stack_len | full_data) >> 28) { + if ((text_len | data_len | bss_len | stack_len | relocs | full_data) >> 28) { pr_err("bad header\n"); ret = -ENOEXEC; goto err; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 6a3a16f91051..5a7ebd160724 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -1001,7 +1001,7 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc) /* * If it turns out that most user namespaces actually want to * register their own binary type handler and therefore all - * create their own separate binfm_misc mounts we should + * create their own separate binfmt_misc mounts we should * consider turning this into a kmem cache. */ misc = kzalloc(sizeof(struct binfmt_misc), GFP_KERNEL); diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 3cfc440c636c..2d5f0482678b 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -44,4 +44,4 @@ btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \ tests/extent-buffer-tests.o tests/btrfs-tests.o \ tests/extent-io-tests.o tests/inode-tests.o tests/qgroup-tests.o \ tests/free-space-tree-tests.o tests/extent-map-tests.o \ - tests/raid-stripe-tree-tests.o + tests/raid-stripe-tree-tests.o tests/delayed-refs-tests.o diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 361a866c1995..a4c51600a408 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -18,7 +18,7 @@ enum { }; #define NO_THRESHOLD (-1) -#define DFT_THRESHOLD (32) +#define DEFAULT_THRESHOLD (32) struct btrfs_workqueue { struct workqueue_struct *normal_wq; @@ -94,9 +94,9 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, ret->limit_active = limit_active; if (thresh == 0) - thresh = DFT_THRESHOLD; + thresh = DEFAULT_THRESHOLD; /* For low threshold, disabling threshold is a better choice */ - if (thresh < DFT_THRESHOLD) { + if (thresh < DEFAULT_THRESHOLD) { ret->current_active = limit_active; ret->thresh = NO_THRESHOLD; } else { diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 04f53ca548e1..3d3923cfc357 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -250,6 +250,21 @@ static int prelim_ref_compare(const struct prelim_ref *ref1, return 0; } +static int prelim_ref_rb_add_cmp(const struct rb_node *new, + const struct rb_node *exist) +{ + const struct prelim_ref *ref_new = + rb_entry(new, struct prelim_ref, rbnode); + const struct prelim_ref *ref_exist = + rb_entry(exist, struct prelim_ref, rbnode); + + /* + * prelim_ref_compare() expects the first parameter as the existing one, + * different from the rb_find_add_cached() order. + */ + return prelim_ref_compare(ref_exist, ref_new); +} + static void update_share_count(struct share_check *sc, int oldcount, int newcount, const struct prelim_ref *newref) { @@ -278,55 +293,39 @@ static void prelim_ref_insert(const struct btrfs_fs_info *fs_info, struct share_check *sc) { struct rb_root_cached *root; - struct rb_node **p; - struct rb_node *parent = NULL; - struct prelim_ref *ref; - int result; - bool leftmost = true; + struct rb_node *exist; root = &preftree->root; - p = &root->rb_root.rb_node; + exist = rb_find_add_cached(&newref->rbnode, root, prelim_ref_rb_add_cmp); + if (exist) { + struct prelim_ref *ref = rb_entry(exist, struct prelim_ref, rbnode); + /* Identical refs, merge them and free @newref */ + struct extent_inode_elem *eie = ref->inode_list; - while (*p) { - parent = *p; - ref = rb_entry(parent, struct prelim_ref, rbnode); - result = prelim_ref_compare(ref, newref); - if (result < 0) { - p = &(*p)->rb_left; - } else if (result > 0) { - p = &(*p)->rb_right; - leftmost = false; - } else { - /* Identical refs, merge them and free @newref */ - struct extent_inode_elem *eie = ref->inode_list; + while (eie && eie->next) + eie = eie->next; - while (eie && eie->next) - eie = eie->next; - - if (!eie) - ref->inode_list = newref->inode_list; - else - eie->next = newref->inode_list; - trace_btrfs_prelim_ref_merge(fs_info, ref, newref, - preftree->count); - /* - * A delayed ref can have newref->count < 0. - * The ref->count is updated to follow any - * BTRFS_[ADD|DROP]_DELAYED_REF actions. - */ - update_share_count(sc, ref->count, - ref->count + newref->count, newref); - ref->count += newref->count; - free_pref(newref); - return; - } + if (!eie) + ref->inode_list = newref->inode_list; + else + eie->next = newref->inode_list; + trace_btrfs_prelim_ref_merge(fs_info, ref, newref, + preftree->count); + /* + * A delayed ref can have newref->count < 0. + * The ref->count is updated to follow any + * BTRFS_[ADD|DROP]_DELAYED_REF actions. + */ + update_share_count(sc, ref->count, + ref->count + newref->count, newref); + ref->count += newref->count; + free_pref(newref); + return; } update_share_count(sc, 0, newref->count, newref); preftree->count++; trace_btrfs_prelim_ref_insert(fs_info, newref, NULL, preftree->count); - rb_link_node(&newref->rbnode, parent, p); - rb_insert_color_cached(&newref->rbnode, root, leftmost); } /* @@ -3022,9 +3021,6 @@ void btrfs_backref_init_cache(struct btrfs_fs_info *fs_info, cache->rb_root = RB_ROOT; for (i = 0; i < BTRFS_MAX_LEVEL; i++) INIT_LIST_HEAD(&cache->pending[i]); - INIT_LIST_HEAD(&cache->changed); - INIT_LIST_HEAD(&cache->detached); - INIT_LIST_HEAD(&cache->leaves); INIT_LIST_HEAD(&cache->pending_edge); INIT_LIST_HEAD(&cache->useless_node); cache->fs_info = fs_info; @@ -3132,29 +3128,17 @@ void btrfs_backref_drop_node(struct btrfs_backref_cache *tree, void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache, struct btrfs_backref_node *node) { - struct btrfs_backref_node *upper; struct btrfs_backref_edge *edge; if (!node) return; - BUG_ON(!node->lowest && !node->detached); while (!list_empty(&node->upper)) { edge = list_entry(node->upper.next, struct btrfs_backref_edge, list[LOWER]); - upper = edge->node[UPPER]; list_del(&edge->list[LOWER]); list_del(&edge->list[UPPER]); btrfs_backref_free_edge(cache, edge); - - /* - * Add the node to leaf node list if no other child block - * cached. - */ - if (list_empty(&upper->lower)) { - list_add_tail(&upper->lower, &cache->leaves); - upper->lowest = 1; - } } btrfs_backref_drop_node(cache, node); @@ -3166,33 +3150,13 @@ void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache, void btrfs_backref_release_cache(struct btrfs_backref_cache *cache) { struct btrfs_backref_node *node; - int i; - while (!list_empty(&cache->detached)) { - node = list_entry(cache->detached.next, - struct btrfs_backref_node, list); + while ((node = rb_entry_safe(rb_first(&cache->rb_root), + struct btrfs_backref_node, rb_node))) btrfs_backref_cleanup_node(cache, node); - } - while (!list_empty(&cache->leaves)) { - node = list_entry(cache->leaves.next, - struct btrfs_backref_node, lower); - btrfs_backref_cleanup_node(cache, node); - } - - for (i = 0; i < BTRFS_MAX_LEVEL; i++) { - while (!list_empty(&cache->pending[i])) { - node = list_first_entry(&cache->pending[i], - struct btrfs_backref_node, - list); - btrfs_backref_cleanup_node(cache, node); - } - } ASSERT(list_empty(&cache->pending_edge)); ASSERT(list_empty(&cache->useless_node)); - ASSERT(list_empty(&cache->changed)); - ASSERT(list_empty(&cache->detached)); - ASSERT(RB_EMPTY_ROOT(&cache->rb_root)); ASSERT(!cache->nr_nodes); ASSERT(!cache->nr_edges); } @@ -3316,8 +3280,12 @@ static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans, root = btrfs_get_fs_root(fs_info, ref_key->offset, false); if (IS_ERR(root)) return PTR_ERR(root); - if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) - cur->cowonly = 1; + + /* We shouldn't be using backref cache for non-shareable roots. */ + if (unlikely(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))) { + btrfs_put_root(root); + return -EUCLEAN; + } if (btrfs_root_level(&root->root_item) == cur->level) { /* Tree root */ @@ -3403,8 +3371,15 @@ static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans, goto out; } upper->owner = btrfs_header_owner(eb); - if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) - upper->cowonly = 1; + + /* We shouldn't be using backref cache for non shareable roots. */ + if (unlikely(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))) { + btrfs_put_root(root); + btrfs_backref_free_edge(cache, edge); + btrfs_backref_free_node(cache, upper); + ret = -EUCLEAN; + goto out; + } /* * If we know the block isn't shared we can avoid @@ -3595,15 +3570,9 @@ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache, ASSERT(start->checked); - /* Insert this node to cache if it's not COW-only */ - if (!start->cowonly) { - rb_node = rb_simple_insert(&cache->rb_root, start->bytenr, - &start->rb_node); - if (rb_node) - btrfs_backref_panic(cache->fs_info, start->bytenr, - -EEXIST); - list_add_tail(&start->lower, &cache->leaves); - } + rb_node = rb_simple_insert(&cache->rb_root, start->bytenr, &start->rb_node); + if (rb_node) + btrfs_backref_panic(cache->fs_info, start->bytenr, -EEXIST); /* * Use breadth first search to iterate all related edges. @@ -3642,11 +3611,6 @@ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache, * parents have already been linked. */ if (!RB_EMPTY_NODE(&upper->rb_node)) { - if (upper->lowest) { - list_del_init(&upper->lower); - upper->lowest = 0; - } - list_add_tail(&edge->list[UPPER], &upper->lower); continue; } @@ -3657,23 +3621,13 @@ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache, return -EUCLEAN; } - /* Sanity check, COW-only node has non-COW-only parent */ - if (start->cowonly != upper->cowonly) { - ASSERT(0); + rb_node = rb_simple_insert(&cache->rb_root, upper->bytenr, + &upper->rb_node); + if (unlikely(rb_node)) { + btrfs_backref_panic(cache->fs_info, upper->bytenr, -EEXIST); return -EUCLEAN; } - /* Only cache non-COW-only (subvolume trees) tree blocks */ - if (!upper->cowonly) { - rb_node = rb_simple_insert(&cache->rb_root, upper->bytenr, - &upper->rb_node); - if (rb_node) { - btrfs_backref_panic(cache->fs_info, - upper->bytenr, -EEXIST); - return -EUCLEAN; - } - } - list_add_tail(&edge->list[UPPER], &upper->lower); /* diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index e8c22cccb5c1..74e614031274 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -318,6 +318,12 @@ struct btrfs_backref_node { u64 bytenr; }; /* Use rb_simple_node for search/insert */ + /* + * This is a sanity check, whenever we COW a block we will update + * new_bytenr with it's current location, and we will check this in + * various places to validate that the cache makes sense, it shouldn't + * be used for anything else. + */ u64 new_bytenr; /* Objectid of tree block owner, can be not uptodate */ u64 owner; @@ -335,10 +341,6 @@ struct btrfs_backref_node { struct extent_buffer *eb; /* Level of the tree block */ unsigned int level:8; - /* Is the block in a non-shareable tree */ - unsigned int cowonly:1; - /* 1 if no child node is in the cache */ - unsigned int lowest:1; /* Is the extent buffer locked */ unsigned int locked:1; /* Has the block been processed */ @@ -391,12 +393,6 @@ struct btrfs_backref_cache { * level blocks may not reflect the new location */ struct list_head pending[BTRFS_MAX_LEVEL]; - /* List of backref nodes with no child node */ - struct list_head leaves; - /* List of blocks that have been COWed in current transaction */ - struct list_head changed; - /* List of detached backref node. */ - struct list_head detached; u64 last_trans; diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index af3db0a7ae4d..bc2555c44a12 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -358,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio) INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_bio_end_io(bbio, bbio->bio.bi_status); } @@ -401,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio) else bio->bi_status = BLK_STS_OK; - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; btrfs_bio_end_io(bbio, bbio->bio.bi_status); @@ -415,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio) if (bio->bi_status) { atomic_inc(&stripe->bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); - } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + } else if (bio_is_zone_append(bio)) { stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; } @@ -453,6 +453,14 @@ static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio) (unsigned long)dev->bdev->bd_dev, btrfs_dev_name(dev), dev->devid, bio->bi_iter.bi_size); + /* + * Track reads if tracking is enabled; ignore I/O operations before the + * filesystem is fully initialized. + */ + if (dev->fs_devices->collect_fs_stats && bio_op(bio) == REQ_OP_READ && dev->fs_info) + percpu_counter_add(&dev->fs_info->stats_read_blocks, + bio->bi_iter.bi_size >> dev->fs_info->sectorsize_bits); + if (bio->bi_opf & REQ_BTRFS_CGROUP_PUNT) blkcg_punt_bio_submit(bio); else @@ -652,8 +660,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) map_length = min(map_length, bbio->fs_info->max_zone_append_size); sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, &nr_segs, map_length); - if (sector_offset) - return sector_offset << SECTOR_SHIFT; + if (sector_offset) { + /* + * bio_split_rw_at() could split at a size smaller than our + * sectorsize and thus cause unaligned I/Os. Fix that by + * always rounding down to the nearest boundary. + */ + return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); + } return map_length; } @@ -719,8 +733,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) bio->bi_opf |= REQ_OP_ZONE_APPEND; } - if (is_data_bbio(bbio) && bioc && - btrfs_need_stripe_tree_update(bioc->fs_info, bioc->map_type)) { + if (is_data_bbio(bbio) && bioc && bioc->use_rst) { /* * No locking for the list update, as we only add to * the list in the I/O submission path, and list diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 4427c1b835e8..c0a8f7d92acc 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -173,43 +173,41 @@ void btrfs_put_block_group(struct btrfs_block_group *cache) } } +static int btrfs_bg_start_cmp(const struct rb_node *new, + const struct rb_node *exist) +{ + const struct btrfs_block_group *new_bg = + rb_entry(new, struct btrfs_block_group, cache_node); + const struct btrfs_block_group *exist_bg = + rb_entry(exist, struct btrfs_block_group, cache_node); + + if (new_bg->start < exist_bg->start) + return -1; + if (new_bg->start > exist_bg->start) + return 1; + return 0; +} + /* * This adds the block group to the fs_info rb tree for the block group cache */ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info, struct btrfs_block_group *block_group) { - struct rb_node **p; - struct rb_node *parent = NULL; - struct btrfs_block_group *cache; - bool leftmost = true; + struct rb_node *exist; + int ret = 0; ASSERT(block_group->length != 0); write_lock(&info->block_group_cache_lock); - p = &info->block_group_cache_tree.rb_root.rb_node; - - while (*p) { - parent = *p; - cache = rb_entry(parent, struct btrfs_block_group, cache_node); - if (block_group->start < cache->start) { - p = &(*p)->rb_left; - } else if (block_group->start > cache->start) { - p = &(*p)->rb_right; - leftmost = false; - } else { - write_unlock(&info->block_group_cache_lock); - return -EEXIST; - } - } - - rb_link_node(&block_group->cache_node, parent, p); - rb_insert_color_cached(&block_group->cache_node, - &info->block_group_cache_tree, leftmost); + exist = rb_find_add_cached(&block_group->cache_node, + &info->block_group_cache_tree, btrfs_bg_start_cmp); + if (exist) + ret = -EEXIST; write_unlock(&info->block_group_cache_lock); - return 0; + return ret; } /* @@ -1223,7 +1221,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, block_group->space_info->total_bytes -= block_group->length; block_group->space_info->bytes_readonly -= (block_group->length - block_group->zone_unusable); - btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info, + btrfs_space_info_update_bytes_zone_unusable(block_group->space_info, -block_group->zone_unusable); block_group->space_info->disk_total -= block_group->length * factor; @@ -1396,8 +1394,7 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes to readonly */ sinfo->bytes_readonly += cache->zone_unusable; - btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, - -cache->zone_unusable); + btrfs_space_info_update_bytes_zone_unusable(sinfo, -cache->zone_unusable); cache->zone_unusable = 0; } cache->ro++; @@ -1645,8 +1642,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) spin_lock(&space_info->lock); spin_lock(&block_group->lock); - btrfs_space_info_update_bytes_pinned(fs_info, space_info, - -block_group->pinned); + btrfs_space_info_update_bytes_pinned(space_info, -block_group->pinned); space_info->bytes_readonly += block_group->pinned; block_group->pinned = 0; @@ -2672,7 +2668,6 @@ static int insert_dev_extent(struct btrfs_trans_handle *trans, btrfs_set_dev_extent_chunk_offset(leaf, extent, chunk_offset); btrfs_set_dev_extent_length(leaf, extent, num_bytes); - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -3060,8 +3055,7 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) (cache->alloc_offset - cache->used - cache->pinned - cache->reserved) + (cache->length - cache->zone_capacity); - btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, - cache->zone_unusable); + btrfs_space_info_update_bytes_zone_unusable(sinfo, cache->zone_unusable); sinfo->bytes_readonly -= cache->zone_unusable; } num_bytes = cache->length - cache->reserved - @@ -3123,7 +3117,6 @@ static int update_block_group_item(struct btrfs_trans_handle *trans, cache->global_root_id); btrfs_set_stack_block_group_flags(&bgi, cache->flags); write_extent_buffer(leaf, &bgi, bi, sizeof(bgi)); - btrfs_mark_buffer_dirty(trans, leaf); fail: btrfs_release_path(path); /* @@ -3699,7 +3692,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, old_val -= num_bytes; cache->used = old_val; cache->pinned += num_bytes; - btrfs_space_info_update_bytes_pinned(info, space_info, num_bytes); + btrfs_space_info_update_bytes_pinned(space_info, num_bytes); space_info->bytes_used -= num_bytes; space_info->disk_used -= num_bytes * factor; if (READ_ONCE(space_info->periodic_reclaim)) @@ -3781,8 +3774,7 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group *cache, space_info->bytes_reserved += num_bytes; trace_btrfs_space_reservation(cache->fs_info, "space_info", space_info->flags, num_bytes, 1); - btrfs_space_info_update_bytes_may_use(cache->fs_info, - space_info, -ram_bytes); + btrfs_space_info_update_bytes_may_use(space_info, -ram_bytes); if (delalloc) cache->delalloc_bytes += num_bytes; diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index a07b9594dc70..3f3608299c0b 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -150,9 +150,7 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info, spin_unlock(&dest->lock); } if (num_bytes) - btrfs_space_info_free_bytes_may_use(fs_info, - space_info, - num_bytes); + btrfs_space_info_free_bytes_may_use(space_info, num_bytes); } if (qgroup_to_release_ret) *qgroup_to_release_ret = qgroup_to_release; @@ -383,13 +381,11 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info) if (block_rsv->reserved < block_rsv->size) { num_bytes = block_rsv->size - block_rsv->reserved; - btrfs_space_info_update_bytes_may_use(fs_info, sinfo, - num_bytes); + btrfs_space_info_update_bytes_may_use(sinfo, num_bytes); block_rsv->reserved = block_rsv->size; } else if (block_rsv->reserved > block_rsv->size) { num_bytes = block_rsv->reserved - block_rsv->size; - btrfs_space_info_update_bytes_may_use(fs_info, sinfo, - -num_bytes); + btrfs_space_info_update_bytes_may_use(sinfo, -num_bytes); block_rsv->reserved = block_rsv->size; btrfs_try_granting_tickets(fs_info, sinfo); } diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index aa1f55cd81b7..b2fa33911c28 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -526,7 +526,7 @@ bool btrfs_data_csum_ok(struct btrfs_bio *bbio, struct btrfs_device *dev, u32 bio_offset, struct bio_vec *bv); noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, struct btrfs_file_extent *file_extent, - bool nowait, bool strict); + bool nowait); void btrfs_del_delalloc_inode(struct btrfs_inode *inode); struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 693dc27ffb89..92071ca0655f 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -37,19 +37,6 @@ static int push_node_left(struct btrfs_trans_handle *trans, static int balance_node_right(struct btrfs_trans_handle *trans, struct extent_buffer *dst_buf, struct extent_buffer *src_buf); - -static const struct btrfs_csums { - u16 size; - const char name[10]; - const char driver[12]; -} btrfs_csums[] = { - [BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" }, - [BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" }, - [BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" }, - [BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b", - .driver = "blake2b-256" }, -}; - /* * The leaf data grows from end-to-front in the node. this returns the address * of the start of the last item, which is the stop of the leaf data stack. @@ -148,44 +135,6 @@ static inline void copy_leaf_items(const struct extent_buffer *dst, nr_items * sizeof(struct btrfs_item)); } -/* This exists for btrfs-progs usages. */ -u16 btrfs_csum_type_size(u16 type) -{ - return btrfs_csums[type].size; -} - -int btrfs_super_csum_size(const struct btrfs_super_block *s) -{ - u16 t = btrfs_super_csum_type(s); - /* - * csum type is validated at mount time - */ - return btrfs_csum_type_size(t); -} - -const char *btrfs_super_csum_name(u16 csum_type) -{ - /* csum type is validated at mount time */ - return btrfs_csums[csum_type].name; -} - -/* - * Return driver name if defined, otherwise the name that's also a valid driver - * name - */ -const char *btrfs_super_csum_driver(u16 csum_type) -{ - /* csum type is validated at mount time */ - return btrfs_csums[csum_type].driver[0] ? - btrfs_csums[csum_type].driver : - btrfs_csums[csum_type].name; -} - -size_t __attribute_const__ btrfs_get_num_csums(void) -{ - return ARRAY_SIZE(btrfs_csums); -} - struct btrfs_path *btrfs_alloc_path(void) { might_sleep(); @@ -225,22 +174,6 @@ noinline void btrfs_release_path(struct btrfs_path *p) } } -/* - * We want the transaction abort to print stack trace only for errors where the - * cause could be a bug, eg. due to ENOSPC, and not for common errors that are - * caused by external factors. - */ -bool __cold abort_should_print_stack(int error) -{ - switch (error) { - case -EIO: - case -EROFS: - case -ENOMEM: - return false; - } - return true; -} - /* * safely gets a reference on the root node of a tree. A lock * is not taken, so a concurrent writer may put a different node @@ -654,6 +587,8 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans, goto error_unlock_cow; } } + + trace_btrfs_cow_block(root, buf, cow); if (unlock_orig) btrfs_tree_unlock(buf); free_extent_buffer_stale(buf); @@ -710,7 +645,6 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; u64 search_start; - int ret; if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) { btrfs_abort_transaction(trans, -EUCLEAN); @@ -751,12 +685,8 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, * Also We don't care about the error, as it's handled internally. */ btrfs_qgroup_trace_subtree_after_cow(trans, root, buf); - ret = btrfs_force_cow_block(trans, root, buf, parent, parent_slot, - cow_ret, search_start, 0, nest); - - trace_btrfs_cow_block(root, buf, *cow_ret); - - return ret; + return btrfs_force_cow_block(trans, root, buf, parent, parent_slot, + cow_ret, search_start, 0, nest); } ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); @@ -3903,6 +3833,7 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); BUG_ON(key.type != BTRFS_EXTENT_DATA_KEY && + key.type != BTRFS_RAID_STRIPE_KEY && key.type != BTRFS_EXTENT_CSUM_KEY); if (btrfs_leaf_free_space(leaf) >= ins_len) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 307dedf95c70..1096a80a64e7 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -7,7 +7,6 @@ #define BTRFS_CTREE_H #include "linux/cleanup.h" -#include #include #include #include @@ -370,6 +369,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi WRITE_ONCE(root->last_trans, transid); } +/* + * Return the generation this root started with. + * + * Every normal root that is created with root->root_key.offset set to it's + * originating generation. If it is a snapshot it is the generation when the + * snapshot was created. + * + * However for TREE_RELOC roots root_key.offset is the objectid of the owning + * tree root. Thankfully we copy the root item of the owning tree root, which + * has it's last_snapshot set to what we would have root_key.offset set to, so + * return that if this is a TREE_RELOC root. + */ +static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root) +{ + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) + return btrfs_root_last_snapshot(&root->root_item); + return root->root_key.offset; +} + /* * Structure that conveys information about an extent that is going to replace * all the extents in a file range. @@ -487,20 +505,6 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info) return BTRFS_MAX_ITEM_SIZE(info) - sizeof(struct btrfs_dir_item); } -#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \ - ((bytes) >> (fs_info)->sectorsize_bits) - -static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) -{ - return mapping_gfp_constraint(mapping, ~__GFP_FS); -} - -void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end); -int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, - u64 num_bytes, u64 *actual_bytes); -int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range); - -/* ctree.c */ int __init btrfs_ctree_init(void); void __cold btrfs_ctree_exit(void); @@ -737,18 +741,4 @@ static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root) return root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID; } -u16 btrfs_csum_type_size(u16 type); -int btrfs_super_csum_size(const struct btrfs_super_block *s); -const char *btrfs_super_csum_name(u16 csum_type); -const char *btrfs_super_csum_driver(u16 csum_type); -size_t __attribute_const__ btrfs_get_num_csums(void); - -/* - * We use folio flag owner_2 to indicate there is an ordered extent with - * unfinished IO. - */ -#define folio_test_ordered(folio) folio_test_owner_2(folio) -#define folio_set_ordered(folio) folio_set_owner_2(folio) -#define folio_clear_ordered(folio) folio_clear_owner_2(folio) - #endif diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 7aa8a395d838..88e900e5a43d 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -176,7 +176,7 @@ void btrfs_free_reserved_data_space_noquota(struct btrfs_fs_info *fs_info, ASSERT(IS_ALIGNED(len, fs_info->sectorsize)); data_sinfo = fs_info->data_sinfo; - btrfs_space_info_free_bytes_may_use(fs_info, data_sinfo, len); + btrfs_space_info_free_bytes_may_use(data_sinfo, len); } /* diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 508bdbae29a0..0b4933c6a889 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -366,40 +366,35 @@ static struct btrfs_delayed_item *__btrfs_lookup_delayed_item( return NULL; } +static int btrfs_delayed_item_cmp(const struct rb_node *new, + const struct rb_node *exist) +{ + const struct btrfs_delayed_item *new_item = + rb_entry(new, struct btrfs_delayed_item, rb_node); + const struct btrfs_delayed_item *exist_item = + rb_entry(exist, struct btrfs_delayed_item, rb_node); + + if (new_item->index < exist_item->index) + return -1; + if (new_item->index > exist_item->index) + return 1; + return 0; +} + static int __btrfs_add_delayed_item(struct btrfs_delayed_node *delayed_node, struct btrfs_delayed_item *ins) { - struct rb_node **p, *node; - struct rb_node *parent_node = NULL; struct rb_root_cached *root; - struct btrfs_delayed_item *item; - bool leftmost = true; + struct rb_node *exist; if (ins->type == BTRFS_DELAYED_INSERTION_ITEM) root = &delayed_node->ins_root; else root = &delayed_node->del_root; - p = &root->rb_root.rb_node; - node = &ins->rb_node; - - while (*p) { - parent_node = *p; - item = rb_entry(parent_node, struct btrfs_delayed_item, - rb_node); - - if (item->index < ins->index) { - p = &(*p)->rb_right; - leftmost = false; - } else if (item->index > ins->index) { - p = &(*p)->rb_left; - } else { - return -EEXIST; - } - } - - rb_link_node(node, parent_node, p); - rb_insert_color_cached(node, root, leftmost); + exist = rb_find_add_cached(&ins->rb_node, root, btrfs_delayed_item_cmp); + if (exist) + return -EEXIST; if (ins->type == BTRFS_DELAYED_INSERTION_ITEM && ins->index >= delayed_node->index_cnt) @@ -1038,7 +1033,6 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans, struct btrfs_inode_item); write_extent_buffer(leaf, &node->inode_item, (unsigned long)inode_item, sizeof(struct btrfs_inode_item)); - btrfs_mark_buffer_dirty(trans, leaf); if (!test_bit(BTRFS_DELAYED_NODE_DEL_IREF, &node->flags)) goto out; @@ -1561,8 +1555,7 @@ release_node: return ret; } -static int btrfs_delete_delayed_insertion_item(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_node *node, +static int btrfs_delete_delayed_insertion_item(struct btrfs_delayed_node *node, u64 index) { struct btrfs_delayed_item *item; @@ -1620,7 +1613,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans, if (IS_ERR(node)) return PTR_ERR(node); - ret = btrfs_delete_delayed_insertion_item(trans->fs_info, node, index); + ret = btrfs_delete_delayed_insertion_item(node, index); if (!ret) goto end; diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 0d878dbbabba..98c5b61dabe8 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -93,6 +93,9 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans) u64 num_bytes; u64 reserved_bytes; + if (btrfs_is_testing(fs_info)) + return; + num_bytes = btrfs_calc_delayed_ref_bytes(fs_info, trans->delayed_ref_updates); num_bytes += btrfs_calc_delayed_ref_csum_bytes(fs_info, trans->delayed_ref_csum_deletions); @@ -254,7 +257,7 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, spin_unlock(&block_rsv->lock); if (to_free > 0) - btrfs_space_info_free_bytes_may_use(fs_info, space_info, to_free); + btrfs_space_info_free_bytes_may_use(space_info, to_free); if (refilled_bytes > 0) trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0, @@ -265,8 +268,8 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, /* * compare two delayed data backrefs with same bytenr and type */ -static int comp_data_refs(struct btrfs_delayed_ref_node *ref1, - struct btrfs_delayed_ref_node *ref2) +static int comp_data_refs(const struct btrfs_delayed_ref_node *ref1, + const struct btrfs_delayed_ref_node *ref2) { if (ref1->data_ref.objectid < ref2->data_ref.objectid) return -1; @@ -279,8 +282,8 @@ static int comp_data_refs(struct btrfs_delayed_ref_node *ref1, return 0; } -static int comp_refs(struct btrfs_delayed_ref_node *ref1, - struct btrfs_delayed_ref_node *ref2, +static int comp_refs(const struct btrfs_delayed_ref_node *ref1, + const struct btrfs_delayed_ref_node *ref2, bool check_seq) { int ret = 0; @@ -314,34 +317,25 @@ static int comp_refs(struct btrfs_delayed_ref_node *ref1, return 0; } +static int cmp_refs_node(const struct rb_node *new, const struct rb_node *exist) +{ + const struct btrfs_delayed_ref_node *new_node = + rb_entry(new, struct btrfs_delayed_ref_node, ref_node); + const struct btrfs_delayed_ref_node *exist_node = + rb_entry(exist, struct btrfs_delayed_ref_node, ref_node); + + return comp_refs(new_node, exist_node, true); +} + static struct btrfs_delayed_ref_node* tree_insert(struct rb_root_cached *root, struct btrfs_delayed_ref_node *ins) { - struct rb_node **p = &root->rb_root.rb_node; struct rb_node *node = &ins->ref_node; - struct rb_node *parent_node = NULL; - struct btrfs_delayed_ref_node *entry; - bool leftmost = true; + struct rb_node *exist; - while (*p) { - int comp; - - parent_node = *p; - entry = rb_entry(parent_node, struct btrfs_delayed_ref_node, - ref_node); - comp = comp_refs(ins, entry, true); - if (comp < 0) { - p = &(*p)->rb_left; - } else if (comp > 0) { - p = &(*p)->rb_right; - leftmost = false; - } else { - return entry; - } - } - - rb_link_node(node, parent_node, p); - rb_insert_color_cached(node, root, leftmost); + exist = rb_find_add_cached(node, root, cmp_refs_node); + if (exist) + return rb_entry(exist, struct btrfs_delayed_ref_node, ref_node); return NULL; } @@ -555,6 +549,32 @@ void btrfs_delete_ref_head(const struct btrfs_fs_info *fs_info, delayed_refs->num_heads_ready--; } +struct btrfs_delayed_ref_node *btrfs_select_delayed_ref(struct btrfs_delayed_ref_head *head) +{ + struct btrfs_delayed_ref_node *ref; + + lockdep_assert_held(&head->mutex); + lockdep_assert_held(&head->lock); + + if (RB_EMPTY_ROOT(&head->ref_tree.rb_root)) + return NULL; + + /* + * Select a delayed ref of type BTRFS_ADD_DELAYED_REF first. + * This is to prevent a ref count from going down to zero, which deletes + * the extent item from the extent tree, when there still are references + * to add, which would fail because they would not find the extent item. + */ + if (!list_empty(&head->ref_add_list)) + return list_first_entry(&head->ref_add_list, + struct btrfs_delayed_ref_node, add_list); + + ref = rb_entry(rb_first_cached(&head->ref_tree), + struct btrfs_delayed_ref_node, ref_node); + ASSERT(list_empty(&ref->add_list)); + return ref; +} + /* * Helper to insert the ref_node to the tail or merge with tail. * @@ -1234,6 +1254,7 @@ void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans) { struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs; struct btrfs_fs_info *fs_info = trans->fs_info; + bool testing = btrfs_is_testing(fs_info); spin_lock(&delayed_refs->lock); while (true) { @@ -1263,7 +1284,7 @@ void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans) spin_unlock(&delayed_refs->lock); mutex_unlock(&head->mutex); - if (pin_bytes) { + if (!testing && pin_bytes) { struct btrfs_block_group *bg; bg = btrfs_lookup_block_group(fs_info, head->bytenr); @@ -1281,8 +1302,7 @@ void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans) spin_lock(&bg->space_info->lock); spin_lock(&bg->lock); bg->pinned += head->num_bytes; - btrfs_space_info_update_bytes_pinned(fs_info, - bg->space_info, + btrfs_space_info_update_bytes_pinned(bg->space_info, head->num_bytes); bg->reserved -= head->num_bytes; bg->space_info->bytes_reserved -= head->num_bytes; @@ -1295,12 +1315,15 @@ void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans) btrfs_error_unpin_extent_range(fs_info, head->bytenr, head->bytenr + head->num_bytes - 1); } - btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); + if (!testing) + btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); btrfs_put_delayed_ref_head(head); cond_resched(); spin_lock(&delayed_refs->lock); } - btrfs_qgroup_destroy_extent_records(trans); + + if (!testing) + btrfs_qgroup_destroy_extent_records(trans); spin_unlock(&delayed_refs->lock); } diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 611fb3388f82..a35067cebb97 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -402,6 +402,7 @@ struct btrfs_delayed_ref_head *btrfs_select_ref_head( struct btrfs_delayed_ref_root *delayed_refs); void btrfs_unselect_ref_head(struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head); +struct btrfs_delayed_ref_node *btrfs_select_delayed_ref(struct btrfs_delayed_ref_head *head); int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index ac8e97ed13f7..f86fbea0b3de 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -440,9 +440,6 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans) dev_replace->cursor_right); dev_replace->item_needs_writeback = 0; up_write(&dev_replace->rwsem); - - btrfs_mark_buffer_dirty(trans, eb); - out: btrfs_free_path(path); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 1ea5d8fcfbf7..ccf91de29f80 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -92,7 +92,6 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans, write_extent_buffer(leaf, name, name_ptr, name_len); write_extent_buffer(leaf, data, data_ptr, data_len); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); return ret; } @@ -152,7 +151,6 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, name_ptr = (unsigned long)(dir_item + 1); write_extent_buffer(leaf, name->name, name_ptr, name->len); - btrfs_mark_buffer_dirty(trans, leaf); second_insert: /* FIXME, use some real flag for selecting the extra index */ diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c index a7c3e221378d..8567af46e16f 100644 --- a/fs/btrfs/direct-io.c +++ b/fs/btrfs/direct-io.c @@ -248,8 +248,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, len = min(len, em->len - (start - em->start)); block_start = extent_map_block_start(em) + (start - em->start); - if (can_nocow_extent(inode, start, &len, - &file_extent, false, false) == 1) { + if (can_nocow_extent(inode, start, &len, &file_extent, false) == 1) { bg = btrfs_inc_nocow_writers(fs_info, block_start); if (bg) can_nocow = true; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index eff0dd1ae62f..f09db62e61a1 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -226,7 +226,7 @@ int btrfs_read_extent_buffer(struct extent_buffer *eb, while (1) { clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); - ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num, check); + ret = read_extent_buffer_pages(eb, mirror_num, check); if (!ret) break; @@ -1258,6 +1258,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) { struct percpu_counter *em_counter = &fs_info->evictable_extent_maps; + percpu_counter_destroy(&fs_info->stats_read_blocks); percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); percpu_counter_destroy(&fs_info->ordered_bytes); @@ -2327,6 +2328,71 @@ out: return ret; } +static int validate_sys_chunk_array(const struct btrfs_fs_info *fs_info, + const struct btrfs_super_block *sb) +{ + unsigned int cur = 0; /* Offset inside the sys chunk array */ + /* + * At sb read time, fs_info is not fully initialized. Thus we have + * to use super block sectorsize, which should have been validated. + */ + const u32 sectorsize = btrfs_super_sectorsize(sb); + u32 sys_array_size = btrfs_super_sys_array_size(sb); + + if (sys_array_size > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) { + btrfs_err(fs_info, "system chunk array too big %u > %u", + sys_array_size, BTRFS_SYSTEM_CHUNK_ARRAY_SIZE); + return -EUCLEAN; + } + + while (cur < sys_array_size) { + struct btrfs_disk_key *disk_key; + struct btrfs_chunk *chunk; + struct btrfs_key key; + u64 type; + u16 num_stripes; + u32 len; + int ret; + + disk_key = (struct btrfs_disk_key *)(sb->sys_chunk_array + cur); + len = sizeof(*disk_key); + + if (cur + len > sys_array_size) + goto short_read; + cur += len; + + btrfs_disk_key_to_cpu(&key, disk_key); + if (key.type != BTRFS_CHUNK_ITEM_KEY) { + btrfs_err(fs_info, + "unexpected item type %u in sys_array at offset %u", + key.type, cur); + return -EUCLEAN; + } + chunk = (struct btrfs_chunk *)(sb->sys_chunk_array + cur); + num_stripes = btrfs_stack_chunk_num_stripes(chunk); + if (cur + btrfs_chunk_item_size(num_stripes) > sys_array_size) + goto short_read; + type = btrfs_stack_chunk_type(chunk); + if (!(type & BTRFS_BLOCK_GROUP_SYSTEM)) { + btrfs_err(fs_info, + "invalid chunk type %llu in sys_array at offset %u", + type, cur); + return -EUCLEAN; + } + ret = btrfs_check_chunk_valid(fs_info, NULL, chunk, key.offset, + sectorsize); + if (ret < 0) + return ret; + cur += btrfs_chunk_item_size(num_stripes); + } + return 0; +short_read: + btrfs_err(fs_info, + "super block sys chunk array short read, cur=%u sys_array_size=%u", + cur, sys_array_size); + return -EUCLEAN; +} + /* * Real super block validation * NOTE: super csum type and incompat features will not be checked here. @@ -2495,6 +2561,8 @@ int btrfs_validate_super(const struct btrfs_fs_info *fs_info, ret = -EINVAL; } + ret = validate_sys_chunk_array(fs_info, sb); + /* * Obvious sys_chunk_array corruptions, it must hold at least one key * and one chunk @@ -2856,6 +2924,10 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block if (ret) return ret; + ret = percpu_counter_init(&fs_info->stats_read_blocks, 0, GFP_KERNEL); + if (ret) + return ret; + fs_info->dirty_metadata_batch = PAGE_SIZE * (1 + ilog2(nr_cpu_ids)); @@ -3321,6 +3393,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->sectors_per_page = (PAGE_SIZE >> fs_info->sectorsize_bits); fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; fs_info->stripesize = stripesize; + fs_info->fs_devices->fs_info = fs_info; /* * Handle the space caching options appropriately now that we have the diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index a7051e2570c1..587842991b24 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -96,9 +96,6 @@ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info); /* * This function is used to grab the root, and avoid it is freed when we * access it. But it doesn't ensure that the tree is not dropped. - * - * If you want to ensure the whole tree is safe, you should use - * fs_info->subvol_srcu */ static inline struct btrfs_root *btrfs_grab_root(struct btrfs_root *root) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index bd09dd3ad1a0..3014a1a23efd 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -570,7 +570,6 @@ static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans, btrfs_set_extent_data_ref_count(leaf, ref, num_refs); } } - btrfs_mark_buffer_dirty(trans, leaf); ret = 0; fail: btrfs_release_path(path); @@ -618,7 +617,6 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans, btrfs_set_extent_data_ref_count(leaf, ref1, num_refs); else if (key.type == BTRFS_SHARED_DATA_REF_KEY) btrfs_set_shared_data_ref_count(leaf, ref2, num_refs); - btrfs_mark_buffer_dirty(trans, leaf); } return ret; } @@ -1050,7 +1048,6 @@ void setup_inline_extent_backref(struct btrfs_trans_handle *trans, } else { btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid); } - btrfs_mark_buffer_dirty(trans, leaf); } static int lookup_extent_backref(struct btrfs_trans_handle *trans, @@ -1195,7 +1192,6 @@ static noinline_for_stack int update_inline_extent_backref( item_size -= size; btrfs_truncate_item(trans, path, item_size, 1); } - btrfs_mark_buffer_dirty(trans, leaf); return 0; } @@ -1260,12 +1256,12 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, { int j, ret = 0; u64 bytes_left, end; - u64 aligned_start = ALIGN(start, 1 << SECTOR_SHIFT); + u64 aligned_start = ALIGN(start, SECTOR_SIZE); /* Adjust the range to be aligned to 512B sectors if necessary. */ if (start != aligned_start) { len -= aligned_start - start; - len = round_down(len, 1 << SECTOR_SHIFT); + len = round_down(len, SECTOR_SIZE); start = aligned_start; } @@ -1527,7 +1523,6 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, if (extent_op) __run_delayed_extent_op(extent_op, leaf, item); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); /* now insert the actual backref */ @@ -1711,8 +1706,6 @@ again: ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); __run_delayed_extent_op(extent_op, leaf, ei); - - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -1803,30 +1796,6 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, return ret; } -static inline struct btrfs_delayed_ref_node * -select_delayed_ref(struct btrfs_delayed_ref_head *head) -{ - struct btrfs_delayed_ref_node *ref; - - if (RB_EMPTY_ROOT(&head->ref_tree.rb_root)) - return NULL; - - /* - * Select a delayed ref of type BTRFS_ADD_DELAYED_REF first. - * This is to prevent a ref count from going down to zero, which deletes - * the extent item from the extent tree, when there still are references - * to add, which would fail because they would not find the extent item. - */ - if (!list_empty(&head->ref_add_list)) - return list_first_entry(&head->ref_add_list, - struct btrfs_delayed_ref_node, add_list); - - ref = rb_entry(rb_first_cached(&head->ref_tree), - struct btrfs_delayed_ref_node, ref_node); - ASSERT(list_empty(&ref->add_list)); - return ref; -} - static struct btrfs_delayed_extent_op *cleanup_extent_op( struct btrfs_delayed_ref_head *head) { @@ -1959,7 +1928,7 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, lockdep_assert_held(&locked_ref->mutex); lockdep_assert_held(&locked_ref->lock); - while ((ref = select_delayed_ref(locked_ref))) { + while ((ref = btrfs_select_delayed_ref(locked_ref))) { if (ref->seq && btrfs_check_delayed_seq(fs_info, ref->seq)) { spin_unlock(&locked_ref->lock); @@ -2230,10 +2199,11 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, return ret; } -static noinline int check_delayed_ref(struct btrfs_root *root, +static noinline int check_delayed_ref(struct btrfs_inode *inode, struct btrfs_path *path, - u64 objectid, u64 offset, u64 bytenr) + u64 offset, u64 bytenr) { + struct btrfs_root *root = inode->root; struct btrfs_delayed_ref_head *head; struct btrfs_delayed_ref_node *ref; struct btrfs_delayed_ref_root *delayed_refs; @@ -2307,7 +2277,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root, * then we have a cross reference. */ if (ref->ref_root != btrfs_root_id(root) || - ref_owner != objectid || ref_offset != offset) { + ref_owner != btrfs_ino(inode) || ref_offset != offset) { ret = 1; break; } @@ -2318,11 +2288,53 @@ static noinline int check_delayed_ref(struct btrfs_root *root, return ret; } -static noinline int check_committed_ref(struct btrfs_root *root, +/* + * Check if there are references for a data extent other than the one belonging + * to the given inode and offset. + * + * @inode: The only inode we expect to find associated with the data extent. + * @path: A path to use for searching the extent tree. + * @offset: The only offset we expect to find associated with the data extent. + * @bytenr: The logical address of the data extent. + * + * When the extent does not have any other references other than the one we + * expect to find, we always return a value of 0 with the path having a locked + * leaf that contains the extent's extent item - this is necessary to ensure + * we don't race with a task running delayed references, and our caller must + * have such a path when calling check_delayed_ref() - it must lock a delayed + * ref head while holding the leaf locked. In case the extent item is not found + * in the extent tree, we return -ENOENT with the path having the leaf (locked) + * where the extent item should be, in order to prevent races with another task + * running delayed references, so that we don't miss any reference when calling + * check_delayed_ref(). + * + * Note: this may return false positives, and this is because we want to be + * quick here as we're called in write paths (when flushing delalloc and + * in the direct IO write path). For example we can have an extent with + * a single reference but that reference is not inlined, or we may have + * many references in the extent tree but we also have delayed references + * that cancel all the reference except the one for our inode and offset, + * but it would be expensive to do such checks and complex due to all + * locking to avoid races between the checks and flushing delayed refs, + * plus non-inline references may be located on leaves other than the one + * that contains the extent item in the extent tree. The important thing + * here is to not return false negatives and that the false positives are + * not very common. + * + * Returns: 0 if there are no cross references and with the path having a locked + * leaf from the extent tree that contains the extent's extent item. + * + * 1 if there are cross references (false positives can happen). + * + * < 0 in case of an error. In case of -ENOENT the leaf in the extent + * tree where the extent item should be located at is read locked and + * accessible in the given path. + */ +static noinline int check_committed_ref(struct btrfs_inode *inode, struct btrfs_path *path, - u64 objectid, u64 offset, u64 bytenr, - bool strict) + u64 offset, u64 bytenr) { + struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *extent_root = btrfs_extent_root(fs_info, bytenr); struct extent_buffer *leaf; @@ -2341,35 +2353,32 @@ static noinline int check_committed_ref(struct btrfs_root *root, ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); if (ret < 0) - goto out; + return ret; if (ret == 0) { /* * Key with offset -1 found, there would have to exist an extent * item with such offset, but this is out of the valid range. */ - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } - ret = -ENOENT; if (path->slots[0] == 0) - goto out; + return -ENOENT; path->slots[0]--; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != bytenr || key.type != BTRFS_EXTENT_ITEM_KEY) - goto out; + return -ENOENT; - ret = 1; item_size = btrfs_item_size(leaf, path->slots[0]); ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); expected_size = sizeof(*ei) + btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY); /* No inline refs; we need to bail before checking for owner ref. */ if (item_size == sizeof(*ei)) - goto out; + return 1; /* Check for an owner ref; skip over it to the real inline refs. */ iref = (struct btrfs_extent_inline_ref *)(ei + 1); @@ -2377,56 +2386,69 @@ static noinline int check_committed_ref(struct btrfs_root *root, if (btrfs_fs_incompat(fs_info, SIMPLE_QUOTA) && type == BTRFS_EXTENT_OWNER_REF_KEY) { expected_size += btrfs_extent_inline_ref_size(BTRFS_EXTENT_OWNER_REF_KEY); iref = (struct btrfs_extent_inline_ref *)(iref + 1); + type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); } /* If extent item has more than 1 inline ref then it's shared */ if (item_size != expected_size) - goto out; - - /* - * If extent created before last snapshot => it's shared unless the - * snapshot has been deleted. Use the heuristic if strict is false. - */ - if (!strict && - (btrfs_extent_generation(leaf, ei) <= - btrfs_root_last_snapshot(&root->root_item))) - goto out; + return 1; /* If this extent has SHARED_DATA_REF then it's shared */ - type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); if (type != BTRFS_EXTENT_DATA_REF_KEY) - goto out; + return 1; ref = (struct btrfs_extent_data_ref *)(&iref->offset); if (btrfs_extent_refs(leaf, ei) != btrfs_extent_data_ref_count(leaf, ref) || btrfs_extent_data_ref_root(leaf, ref) != btrfs_root_id(root) || - btrfs_extent_data_ref_objectid(leaf, ref) != objectid || + btrfs_extent_data_ref_objectid(leaf, ref) != btrfs_ino(inode) || btrfs_extent_data_ref_offset(leaf, ref) != offset) - goto out; + return 1; - ret = 0; -out: - return ret; + return 0; } -int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, - u64 bytenr, bool strict, struct btrfs_path *path) +int btrfs_cross_ref_exist(struct btrfs_inode *inode, u64 offset, + u64 bytenr, struct btrfs_path *path) { int ret; do { - ret = check_committed_ref(root, path, objectid, - offset, bytenr, strict); + ret = check_committed_ref(inode, path, offset, bytenr); if (ret && ret != -ENOENT) goto out; - ret = check_delayed_ref(root, path, objectid, offset, bytenr); + /* + * The path must have a locked leaf from the extent tree where + * the extent item for our extent is located, in case it exists, + * or where it should be located in case it doesn't exist yet + * because it's new and its delayed ref was not yet flushed. + * We need to lock the delayed ref head at check_delayed_ref(), + * if one exists, while holding the leaf locked in order to not + * race with delayed ref flushing, missing references and + * incorrectly reporting that the extent is not shared. + */ + if (IS_ENABLED(CONFIG_BTRFS_ASSERT)) { + struct extent_buffer *leaf = path->nodes[0]; + + ASSERT(leaf != NULL); + btrfs_assert_tree_read_locked(leaf); + + if (ret != -ENOENT) { + struct btrfs_key key; + + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); + ASSERT(key.objectid == bytenr); + ASSERT(key.type == BTRFS_EXTENT_ITEM_KEY); + } + } + + ret = check_delayed_ref(inode, path, offset, bytenr); } while (ret == -EAGAIN && !path->nowait); out: btrfs_release_path(path); - if (btrfs_is_data_reloc_root(root)) + if (btrfs_is_data_reloc_root(inode->root)) WARN_ON(ret > 0); return ret; } @@ -2571,13 +2593,10 @@ static int pin_down_extent(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache, u64 bytenr, u64 num_bytes, int reserved) { - struct btrfs_fs_info *fs_info = cache->fs_info; - spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); cache->pinned += num_bytes; - btrfs_space_info_update_bytes_pinned(fs_info, cache->space_info, - num_bytes); + btrfs_space_info_update_bytes_pinned(cache->space_info, num_bytes); if (reserved) { cache->reserved -= num_bytes; cache->space_info->bytes_reserved -= num_bytes; @@ -2724,15 +2743,15 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, { struct btrfs_block_group *cache = NULL; struct btrfs_space_info *space_info; - struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; struct btrfs_free_cluster *cluster = NULL; - u64 len; u64 total_unpinned = 0; u64 empty_cluster = 0; bool readonly; int ret = 0; while (start <= end) { + u64 len; + readonly = false; if (!cache || start >= cache->start + cache->length) { @@ -2778,37 +2797,19 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, spin_lock(&space_info->lock); spin_lock(&cache->lock); cache->pinned -= len; - btrfs_space_info_update_bytes_pinned(fs_info, space_info, -len); + btrfs_space_info_update_bytes_pinned(space_info, -len); space_info->max_extent_size = 0; if (cache->ro) { space_info->bytes_readonly += len; readonly = true; } else if (btrfs_is_zoned(fs_info)) { /* Need reset before reusing in a zoned block group */ - btrfs_space_info_update_bytes_zone_unusable(fs_info, space_info, - len); + btrfs_space_info_update_bytes_zone_unusable(space_info, len); readonly = true; } spin_unlock(&cache->lock); - if (!readonly && return_free_space && - global_rsv->space_info == space_info) { - spin_lock(&global_rsv->lock); - if (!global_rsv->full) { - u64 to_add = min(len, global_rsv->size - - global_rsv->reserved); - - global_rsv->reserved += to_add; - btrfs_space_info_update_bytes_may_use(fs_info, - space_info, to_add); - if (global_rsv->reserved >= global_rsv->size) - global_rsv->full = 1; - len -= to_add; - } - spin_unlock(&global_rsv->lock); - } - /* Add to any tickets we may have */ - if (!readonly && return_free_space && len) - btrfs_try_granting_tickets(fs_info, space_info); + if (!readonly && return_free_space) + btrfs_return_free_space(space_info, len); spin_unlock(&space_info->lock); } @@ -3259,7 +3260,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, } } else { btrfs_set_extent_refs(leaf, ei, refs); - btrfs_mark_buffer_dirty(trans, leaf); } if (found_extent) { ret = remove_extent_backref(trans, extent_root, path, @@ -4827,7 +4827,6 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, btrfs_set_extent_data_ref_count(leaf, ref, ref_mod); } - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_free_path(path); return alloc_reserved_extent(trans, ins->objectid, ins->offset); @@ -4902,7 +4901,6 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, btrfs_set_extent_inline_ref_offset(leaf, iref, node->ref_root); } - btrfs_mark_buffer_dirty(trans, leaf); btrfs_free_path(path); return alloc_reserved_extent(trans, node->bytenr, fs_info->nodesize); @@ -5285,7 +5283,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control * * reference to it. */ generation = btrfs_node_ptr_generation(eb, slot); - if (!wc->update_ref || generation <= root->root_key.offset) + if (!wc->update_ref || generation <= btrfs_root_origin_generation(root)) return false; /* @@ -5340,7 +5338,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, goto reada; if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) + generation <= btrfs_root_origin_generation(root)) continue; /* We don't lock the tree block, it's OK to be racy here */ @@ -5683,7 +5681,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, * for the subtree */ if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) { + generation <= btrfs_root_origin_generation(root)) { wc->lookup_info = 1; return 1; } diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h index 2ad51130c037..cfa52264f678 100644 --- a/fs/btrfs/extent-tree.h +++ b/fs/btrfs/extent-tree.h @@ -116,8 +116,7 @@ int btrfs_pin_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num, int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, const struct extent_buffer *eb); int btrfs_exclude_logged_extents(struct extent_buffer *eb); -int btrfs_cross_ref_exist(struct btrfs_root *root, - u64 objectid, u64 offset, u64 bytenr, bool strict, +int btrfs_cross_ref_exist(struct btrfs_inode *inode, u64 offset, u64 bytenr, struct btrfs_path *path); struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -163,5 +162,9 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *node, struct extent_buffer *parent); +void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end); +int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, + u64 num_bytes, u64 *actual_bytes); +int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range); #endif diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index b923d0cec61c..a2cac9d0a1a9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -198,9 +198,8 @@ static void __process_folios_contig(struct address_space *mapping, u64 end, unsigned long page_ops) { struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); - pgoff_t start_index = start >> PAGE_SHIFT; + pgoff_t index = start >> PAGE_SHIFT; pgoff_t end_index = end >> PAGE_SHIFT; - pgoff_t index = start_index; struct folio_batch fbatch; int i; @@ -221,7 +220,7 @@ static void __process_folios_contig(struct address_space *mapping, } } -static noinline void __unlock_for_delalloc(const struct inode *inode, +static noinline void unlock_delalloc_folio(const struct inode *inode, const struct folio *locked_folio, u64 start, u64 end) { @@ -242,9 +241,8 @@ static noinline int lock_delalloc_folios(struct inode *inode, { struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct address_space *mapping = inode->i_mapping; - pgoff_t start_index = start >> PAGE_SHIFT; + pgoff_t index = start >> PAGE_SHIFT; pgoff_t end_index = end >> PAGE_SHIFT; - pgoff_t index = start_index; u64 processed_end = start; struct folio_batch fbatch; @@ -288,8 +286,7 @@ static noinline int lock_delalloc_folios(struct inode *inode, out: folio_batch_release(&fbatch); if (processed_end > start) - __unlock_for_delalloc(inode, locked_folio, start, - processed_end); + unlock_delalloc_folio(inode, locked_folio, start, processed_end); return -EAGAIN; } @@ -390,7 +387,7 @@ again: unlock_extent(tree, delalloc_start, delalloc_end, &cached_state); if (!ret) { - __unlock_for_delalloc(inode, locked_folio, delalloc_start, + unlock_delalloc_folio(inode, locked_folio, delalloc_start, delalloc_end); cond_resched(); goto again; @@ -632,7 +629,7 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, for (allocated = 0; allocated < nr_pages;) { unsigned int last = allocated; - allocated = alloc_pages_bulk_array(gfp, nr_pages, page_array); + allocated = alloc_pages_bulk(gfp, nr_pages, page_array); if (unlikely(allocated == last)) { /* No progress, fail and do cleanup. */ for (int i = 0; i < allocated; i++) { @@ -710,6 +707,7 @@ static void alloc_new_bio(struct btrfs_inode *inode, bbio = btrfs_bio_alloc(BIO_MAX_VECS, bio_ctrl->opf, fs_info, bio_ctrl->end_io_func, NULL); bbio->bio.bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT; + bbio->bio.bi_write_hint = inode->vfs_inode.i_write_hint; bbio->inode = inode; bbio->file_offset = file_offset; bio_ctrl->bbio = bbio; @@ -862,11 +860,6 @@ static int attach_extent_buffer_folio(struct extent_buffer *eb, return ret; } -int set_page_extent_mapped(struct page *page) -{ - return set_folio_extent_mapped(page_folio(page)); -} - int set_folio_extent_mapped(struct folio *folio) { struct btrfs_fs_info *fs_info; @@ -901,9 +894,9 @@ void clear_folio_extent_mapped(struct folio *folio) folio_detach_private(folio); } -static struct extent_map *__get_extent_map(struct inode *inode, - struct folio *folio, u64 start, - u64 len, struct extent_map **em_cached) +static struct extent_map *get_extent_map(struct btrfs_inode *inode, + struct folio *folio, u64 start, + u64 len, struct extent_map **em_cached) { struct extent_map *em; struct extent_state *cached_state = NULL; @@ -922,14 +915,14 @@ static struct extent_map *__get_extent_map(struct inode *inode, *em_cached = NULL; } - btrfs_lock_and_flush_ordered_range(BTRFS_I(inode), start, start + len - 1, &cached_state); - em = btrfs_get_extent(BTRFS_I(inode), folio, start, len); + btrfs_lock_and_flush_ordered_range(inode, start, start + len - 1, &cached_state); + em = btrfs_get_extent(inode, folio, start, len); if (!IS_ERR(em)) { BUG_ON(*em_cached); refcount_inc(&em->refs); *em_cached = em; } - unlock_extent(&BTRFS_I(inode)->io_tree, start, start + len - 1, &cached_state); + unlock_extent(&inode->io_tree, start, start + len - 1, &cached_state); return em; } @@ -985,8 +978,7 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, end_folio_read(folio, true, cur, iosize); break; } - em = __get_extent_map(inode, folio, cur, end - cur + 1, - em_cached); + em = get_extent_map(BTRFS_I(inode), folio, cur, end - cur + 1, em_cached); if (IS_ERR(em)) { end_folio_read(folio, false, cur, end + 1 - cur); return PTR_ERR(em); @@ -1142,14 +1134,19 @@ static bool find_next_delalloc_bitmap(struct folio *folio, } /* - * helper for extent_writepage(), doing all of the delayed allocation setup. + * Do all of the delayed allocation setup. * - * This returns 1 if btrfs_run_delalloc_range function did all the work required - * to write the page (copy into inline extent). In this case the IO has - * been started and the page is already unlocked. + * Return >0 if all the dirty blocks are submitted async (compression) or inlined. + * The @folio should no longer be touched (treat it as already unlocked). * - * This returns 0 if all went well (page still locked) - * This returns < 0 if there were errors (page still locked) + * Return 0 if there is still dirty block that needs to be submitted through + * extent_writepage_io(). + * bio_ctrl->submit_bitmap will indicate which blocks of the folio should be + * submitted, and @folio is still kept locked. + * + * Return <0 if there is any error hit. + * Any allocated ordered extent range covering this folio will be marked + * finished (IOERR), and @folio is still kept locked. */ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, struct folio *folio, @@ -1167,6 +1164,16 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, * last delalloc end. */ u64 last_delalloc_end = 0; + /* + * The range end (exclusive) of the last successfully finished delalloc + * range. + * Any range covered by ordered extent must either be manually marked + * finished (error handling), or has IO submitted (and finish the + * ordered extent normally). + * + * This records the end of ordered extent cleanup if we hit an error. + */ + u64 last_finished_delalloc_end = page_start; u64 delalloc_start = page_start; u64 delalloc_end = page_end; u64 delalloc_to_write = 0; @@ -1235,11 +1242,28 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, found_len = last_delalloc_end + 1 - found_start; if (ret >= 0) { + /* + * Some delalloc range may be created by previous folios. + * Thus we still need to clean up this range during error + * handling. + */ + last_finished_delalloc_end = found_start; /* No errors hit so far, run the current delalloc range. */ ret = btrfs_run_delalloc_range(inode, folio, found_start, found_start + found_len - 1, wbc); + if (ret >= 0) + last_finished_delalloc_end = found_start + found_len; + if (unlikely(ret < 0)) + btrfs_err_rl(fs_info, +"failed to run delalloc range, root=%lld ino=%llu folio=%llu submit_bitmap=%*pbl start=%llu len=%u: %d", + btrfs_root_id(inode->root), + btrfs_ino(inode), + folio_pos(folio), + fs_info->sectors_per_page, + &bio_ctrl->submit_bitmap, + found_start, found_len, ret); } else { /* * We've hit an error during previous delalloc range, @@ -1247,7 +1271,7 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, */ unlock_extent(&inode->io_tree, found_start, found_start + found_len - 1, NULL); - __unlock_for_delalloc(&inode->vfs_inode, folio, + unlock_delalloc_folio(&inode->vfs_inode, folio, found_start, found_start + found_len - 1); } @@ -1274,8 +1298,22 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, delalloc_start = found_start + found_len; } - if (ret < 0) + /* + * It's possible we had some ordered extents created before we hit + * an error, cleanup non-async successfully created delalloc ranges. + */ + if (unlikely(ret < 0)) { + unsigned int bitmap_size = min( + (last_finished_delalloc_end - page_start) >> + fs_info->sectorsize_bits, + fs_info->sectors_per_page); + + for_each_set_bit(bit, &bio_ctrl->submit_bitmap, bitmap_size) + btrfs_mark_ordered_io_finished(inode, folio, + page_start + (bit << fs_info->sectorsize_bits), + fs_info->sectorsize, false); return ret; + } out: if (last_delalloc_end) delalloc_end = last_delalloc_end; @@ -1335,7 +1373,7 @@ static int submit_one_sector(struct btrfs_inode *inode, em = btrfs_get_extent(inode, NULL, filepos, sectorsize); if (IS_ERR(em)) - return PTR_ERR_OR_ZERO(em); + return PTR_ERR(em); extent_offset = filepos - em->start; em_end = extent_map_end(em); @@ -1391,6 +1429,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, struct btrfs_fs_info *fs_info = inode->root->fs_info; unsigned long range_bitmap = 0; bool submitted_io = false; + bool error = false; const u64 folio_start = folio_pos(folio); u64 cur; int bit; @@ -1433,11 +1472,26 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, break; } ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size); - if (ret < 0) - goto out; + if (unlikely(ret < 0)) { + /* + * bio_ctrl may contain a bio crossing several folios. + * Submit it immediately so that the bio has a chance + * to finish normally, other than marked as error. + */ + submit_one_bio(bio_ctrl); + /* + * Failed to grab the extent map which should be very rare. + * Since there is no bio submitted to finish the ordered + * extent, we have to manually finish this sector. + */ + btrfs_mark_ordered_io_finished(inode, folio, cur, + fs_info->sectorsize, false); + error = true; + continue; + } submitted_io = true; } -out: + /* * If we didn't submitted any sector (>= i_size), folio dirty get * cleared but PAGECACHE_TAG_DIRTY is not cleared (only cleared @@ -1445,8 +1499,11 @@ out: * * Here we set writeback and clear for the range. If the full folio * is no longer dirty then we clear the PAGECACHE_TAG_DIRTY tag. + * + * If we hit any error, the corresponding sector will still be dirty + * thus no need to clear PAGECACHE_TAG_DIRTY. */ - if (!submitted_io) { + if (!submitted_io && !error) { btrfs_folio_set_writeback(fs_info, folio, start, len); btrfs_folio_clear_writeback(fs_info, folio, start, len); } @@ -1464,15 +1521,14 @@ out: */ static int extent_writepage(struct folio *folio, struct btrfs_bio_ctrl *bio_ctrl) { - struct inode *inode = folio->mapping->host; - struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); - const u64 page_start = folio_pos(folio); + struct btrfs_inode *inode = BTRFS_I(folio->mapping->host); + struct btrfs_fs_info *fs_info = inode->root->fs_info; int ret; size_t pg_offset; - loff_t i_size = i_size_read(inode); + loff_t i_size = i_size_read(&inode->vfs_inode); unsigned long end_index = i_size >> PAGE_SHIFT; - trace_extent_writepage(folio, inode, bio_ctrl->wbc); + trace_extent_writepage(folio, &inode->vfs_inode, bio_ctrl->wbc); WARN_ON(!folio_test_locked(folio)); @@ -1496,26 +1552,28 @@ static int extent_writepage(struct folio *folio, struct btrfs_bio_ctrl *bio_ctrl if (ret < 0) goto done; - ret = writepage_delalloc(BTRFS_I(inode), folio, bio_ctrl); + ret = writepage_delalloc(inode, folio, bio_ctrl); if (ret == 1) return 0; if (ret) goto done; - ret = extent_writepage_io(BTRFS_I(inode), folio, folio_pos(folio), + ret = extent_writepage_io(inode, folio, folio_pos(folio), PAGE_SIZE, bio_ctrl, i_size); if (ret == 1) return 0; + if (ret < 0) + btrfs_err_rl(fs_info, +"failed to submit blocks, root=%lld inode=%llu folio=%llu submit_bitmap=%*pbl: %d", + btrfs_root_id(inode->root), btrfs_ino(inode), + folio_pos(folio), fs_info->sectors_per_page, + &bio_ctrl->submit_bitmap, ret); bio_ctrl->wbc->nr_to_write--; done: - if (ret) { - btrfs_mark_ordered_io_finished(BTRFS_I(inode), folio, - page_start, PAGE_SIZE, !ret); + if (ret < 0) mapping_set_error(folio->mapping, ret); - } - /* * Only unlock ranges that are submitted. As there can be some async * submitted ranges inside the folio. @@ -1525,12 +1583,6 @@ done: return ret; } -void wait_on_extent_buffer_writeback(struct extent_buffer *eb) -{ - wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK, - TASK_UNINTERRUPTIBLE); -} - /* * Lock extent buffer status and pages for writeback. * @@ -1671,11 +1723,10 @@ static void end_bbio_meta_write(struct btrfs_bio *bbio) { struct extent_buffer *eb = bbio->private; struct btrfs_fs_info *fs_info = eb->fs_info; - bool uptodate = !bbio->bio.bi_status; struct folio_iter fi; u32 bio_offset = 0; - if (!uptodate) + if (bbio->bio.bi_status != BLK_STS_OK) set_btree_ioerr(eb); bio_for_each_folio_all(fi, &bbio->bio) { @@ -2292,11 +2343,8 @@ void extent_write_locked_range(struct inode *inode, const struct folio *locked_f if (ret == 1) goto next_page; - if (ret) { - btrfs_mark_ordered_io_finished(BTRFS_I(inode), folio, - cur, cur_len, !ret); + if (ret) mapping_set_error(mapping, ret); - } btrfs_folio_end_lock(fs_info, folio, cur, cur_len); if (ret < 0) found_error = true; @@ -2495,11 +2543,6 @@ next: return try_release_extent_state(io_tree, folio); } -static void __free_extent_buffer(struct extent_buffer *eb) -{ - kmem_cache_free(extent_buffer_cache, eb); -} - static int extent_buffer_under_io(const struct extent_buffer *eb) { return (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) || @@ -2580,8 +2623,8 @@ static void detach_extent_buffer_folio(const struct extent_buffer *eb, struct fo spin_unlock(&folio->mapping->i_private_lock); } -/* Release all pages attached to the extent buffer */ -static void btrfs_release_extent_buffer_pages(const struct extent_buffer *eb) +/* Release all folios attached to the extent buffer */ +static void btrfs_release_extent_buffer_folios(const struct extent_buffer *eb) { ASSERT(!extent_buffer_under_io(eb)); @@ -2603,9 +2646,9 @@ static void btrfs_release_extent_buffer_pages(const struct extent_buffer *eb) */ static inline void btrfs_release_extent_buffer(struct extent_buffer *eb) { - btrfs_release_extent_buffer_pages(eb); + btrfs_release_extent_buffer_folios(eb); btrfs_leak_debug_del_eb(eb); - __free_extent_buffer(eb); + kmem_cache_free(extent_buffer_cache, eb); } static struct extent_buffer * @@ -2703,7 +2746,7 @@ err: folio_put(eb->folios[i]); } } - __free_extent_buffer(eb); + kmem_cache_free(extent_buffer_cache, eb); return NULL; } @@ -2830,13 +2873,12 @@ free_eb: } #endif -static struct extent_buffer *grab_extent_buffer( - struct btrfs_fs_info *fs_info, struct page *page) +static struct extent_buffer *grab_extent_buffer(struct btrfs_fs_info *fs_info, + struct folio *folio) { - struct folio *folio = page_folio(page); struct extent_buffer *exists; - lockdep_assert_held(&page->mapping->i_private_lock); + lockdep_assert_held(&folio->mapping->i_private_lock); /* * For subpage case, we completely rely on radix tree to ensure we @@ -2851,7 +2893,7 @@ static struct extent_buffer *grab_extent_buffer( return NULL; /* - * We could have already allocated an eb for this page and attached one + * We could have already allocated an eb for this folio and attached one * so lets see if we can get a ref on the existing eb, and if we can we * know it's good and we can just return that one, else we know we can * just overwrite folio private. @@ -2860,16 +2902,19 @@ static struct extent_buffer *grab_extent_buffer( if (atomic_inc_not_zero(&exists->refs)) return exists; - WARN_ON(PageDirty(page)); + WARN_ON(folio_test_dirty(folio)); folio_detach_private(folio); return NULL; } -static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) +/* + * Validate alignment constraints of eb at logical address @start. + */ +static bool check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) { if (!IS_ALIGNED(start, fs_info->sectorsize)) { btrfs_err(fs_info, "bad tree block start %llu", start); - return -EINVAL; + return true; } if (fs_info->nodesize < PAGE_SIZE && @@ -2877,14 +2922,14 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) btrfs_err(fs_info, "tree block crosses page boundary, start %llu nodesize %u", start, fs_info->nodesize); - return -EINVAL; + return true; } if (fs_info->nodesize >= PAGE_SIZE && !PAGE_ALIGNED(start)) { btrfs_err(fs_info, "tree block is not page aligned, start %llu nodesize %u", start, fs_info->nodesize); - return -EINVAL; + return true; } if (!IS_ALIGNED(start, fs_info->nodesize) && !test_and_set_bit(BTRFS_FS_UNALIGNED_TREE_BLOCK, &fs_info->flags)) { @@ -2892,10 +2937,9 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) "tree block not nodesize aligned, start %llu nodesize %u, can be resolved by a full metadata balance", start, fs_info->nodesize); } - return 0; + return false; } - /* * Return 0 if eb->folios[i] is attached to btree inode successfully. * Return >0 if there is already another extent buffer for the range, @@ -2951,8 +2995,7 @@ finish: } else if (existing_folio) { struct extent_buffer *existing_eb; - existing_eb = grab_extent_buffer(fs_info, - folio_page(existing_folio, 0)); + existing_eb = grab_extent_buffer(fs_info, existing_folio); if (existing_eb) { /* The extent buffer still exists, we can use it directly. */ *found_eb_ret = existing_eb; @@ -3149,7 +3192,7 @@ again: * live buffer and won't free them prematurely. */ for (int i = 0; i < num_folios; i++) - unlock_page(folio_page(eb->folios[i], 0)); + folio_unlock(eb->folios[i]); return eb; out: @@ -3173,7 +3216,7 @@ out: for (int i = 0; i < attached; i++) { ASSERT(eb->folios[i]); detach_extent_buffer_folio(eb, eb->folios[i]); - unlock_page(folio_page(eb->folios[i], 0)); + folio_unlock(eb->folios[i]); folio_put(eb->folios[i]); eb->folios[i] = NULL; } @@ -3195,7 +3238,7 @@ static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head) struct extent_buffer *eb = container_of(head, struct extent_buffer, rcu_head); - __free_extent_buffer(eb); + kmem_cache_free(extent_buffer_cache, eb); } static int release_extent_buffer(struct extent_buffer *eb) @@ -3219,11 +3262,11 @@ static int release_extent_buffer(struct extent_buffer *eb) } btrfs_leak_debug_del_eb(eb); - /* Should be safe to release our pages at this point */ - btrfs_release_extent_buffer_pages(eb); + /* Should be safe to release folios at this point. */ + btrfs_release_extent_buffer_folios(eb); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))) { - __free_extent_buffer(eb); + kmem_cache_free(extent_buffer_cache, eb); return 1; } #endif @@ -3382,12 +3425,12 @@ void set_extent_buffer_dirty(struct extent_buffer *eb) * the above race. */ if (subpage) - lock_page(folio_page(eb->folios[0], 0)); + folio_lock(eb->folios[0]); for (int i = 0; i < num_folios; i++) btrfs_folio_set_dirty(eb->fs_info, eb->folios[i], eb->start, eb->len); if (subpage) - unlock_page(folio_page(eb->folios[0], 0)); + folio_unlock(eb->folios[0]); percpu_counter_add_batch(&eb->fs_info->dirty_metadata_bytes, eb->len, eb->fs_info->dirty_metadata_batch); @@ -3497,8 +3540,8 @@ static void end_bbio_meta_read(struct btrfs_bio *bbio) bio_put(&bbio->bio); } -int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, - const struct btrfs_tree_parent_check *check) +int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num, + const struct btrfs_tree_parent_check *check) { struct btrfs_bio *bbio; bool ret; @@ -3516,7 +3559,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, /* Someone else is already reading the buffer, just wait for it. */ if (test_and_set_bit(EXTENT_BUFFER_READING, &eb->bflags)) - goto done; + return 0; /* * Between the initial test_bit(EXTENT_BUFFER_UPTODATE) and the above @@ -3556,14 +3599,21 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, } } btrfs_submit_bbio(bbio, mirror_num); + return 0; +} -done: - if (wait == WAIT_COMPLETE) { - wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING, TASK_UNINTERRUPTIBLE); - if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) - return -EIO; - } +int read_extent_buffer_pages(struct extent_buffer *eb, int mirror_num, + const struct btrfs_tree_parent_check *check) +{ + int ret; + ret = read_extent_buffer_pages_nowait(eb, mirror_num, check); + if (ret < 0) + return ret; + + wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING, TASK_UNINTERRUPTIBLE); + if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) + return -EIO; return 0; } @@ -4294,7 +4344,7 @@ void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, return; } - ret = read_extent_buffer_pages(eb, WAIT_NONE, 0, &check); + ret = read_extent_buffer_pages_nowait(eb, 0, &check); if (ret < 0) free_extent_buffer_stale(eb); else diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 8a36117ed453..6c5328bfabc2 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -248,7 +248,6 @@ int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc); void btrfs_readahead(struct readahead_control *rac); int set_folio_extent_mapped(struct folio *folio); -int set_page_extent_mapped(struct page *page); void clear_folio_extent_mapped(struct folio *folio); struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, @@ -262,12 +261,17 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, u64 start); void free_extent_buffer(struct extent_buffer *eb); void free_extent_buffer_stale(struct extent_buffer *eb); -#define WAIT_NONE 0 -#define WAIT_COMPLETE 1 -#define WAIT_PAGE_LOCK 2 -int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, +int read_extent_buffer_pages(struct extent_buffer *eb, int mirror_num, const struct btrfs_tree_parent_check *parent_check); -void wait_on_extent_buffer_writeback(struct extent_buffer *eb); +int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num, + const struct btrfs_tree_parent_check *parent_check); + +static inline void wait_on_extent_buffer_writeback(struct extent_buffer *eb) +{ + wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK, + TASK_UNINTERRUPTIBLE); +} + void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, u64 owner_root, u64 gen, int level); void btrfs_readahead_node_child(struct extent_buffer *node, int slot); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 886749b39672..d04a3b47b1fb 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -190,8 +190,6 @@ int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans, btrfs_set_file_extent_compression(leaf, item, 0); btrfs_set_file_extent_encryption(leaf, item, 0); btrfs_set_file_extent_other_encoding(leaf, item, 0); - - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -1259,7 +1257,6 @@ found: ins_size /= csum_size; total_bytes += ins_size * fs_info->sectorsize; - btrfs_mark_buffer_dirty(trans, path->nodes[0]); if (total_bytes < sums->len) { btrfs_release_path(path); cond_resched(); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 14e27473c5bc..36f51c311bb1 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -36,52 +36,7 @@ #include "ioctl.h" #include "file.h" #include "super.h" - -/* - * Helper to fault in page and copy. This should go away and be replaced with - * calls into generic code. - */ -static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes, - struct folio *folio, struct iov_iter *i) -{ - size_t copied = 0; - size_t total_copied = 0; - int offset = offset_in_page(pos); - - while (write_bytes > 0) { - size_t count = min_t(size_t, PAGE_SIZE - offset, write_bytes); - /* - * Copy data from userspace to the current page - */ - copied = copy_folio_from_iter_atomic(folio, offset, count, i); - - /* Flush processor's dcache for this page */ - flush_dcache_folio(folio); - - /* - * if we get a partial write, we can end up with - * partially up to date page. These add - * a lot of complexity, so make sure they don't - * happen by forcing this copy to be retried. - * - * The rest of the btrfs_file_write code will fall - * back to page at a time copies after we return 0. - */ - if (unlikely(copied < count)) { - if (!folio_test_uptodate(folio)) { - iov_iter_revert(i, copied); - copied = 0; - } - if (!copied) - break; - } - - write_bytes -= copied; - total_copied += copied; - offset += copied; - } - return total_copied; -} +#include "print-tree.h" /* * Unlock folio after btrfs_file_write() is done with it. @@ -106,7 +61,7 @@ static void btrfs_drop_folio(struct btrfs_fs_info *fs_info, struct folio *folio, } /* - * After btrfs_copy_from_user(), update the following things for delalloc: + * After copy_folio_from_iter_atomic(), update the following things for delalloc: * - Mark newly dirtied folio as DELALLOC in the io tree. * Used to advise which range is to be written back. * - Mark modified folio as Uptodate/Dirty and not needing COW fixup @@ -224,7 +179,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, if (args->drop_cache) btrfs_drop_extent_map_range(inode, args->start, args->end - 1, false); - if (args->start >= inode->disk_i_size && !args->replace_extent) + if (data_race(args->start >= inode->disk_i_size) && !args->replace_extent) modify_tree = 0; update_refs = (btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID); @@ -245,7 +200,11 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, next_slot: leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { - BUG_ON(del_nr > 0); + if (WARN_ON(del_nr > 0)) { + btrfs_print_leaf(leaf); + ret = -EINVAL; + break; + } ret = btrfs_next_leaf(root, path); if (ret < 0) break; @@ -321,7 +280,11 @@ next_slot: * | -------- extent -------- | */ if (args->start > key.offset && args->end < extent_end) { - BUG_ON(del_nr > 0); + if (WARN_ON(del_nr > 0)) { + btrfs_print_leaf(leaf); + ret = -EINVAL; + break; + } if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; break; @@ -351,7 +314,6 @@ next_slot: btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - args->start); - btrfs_mark_buffer_dirty(trans, leaf); if (update_refs && disk_bytenr > 0) { struct btrfs_ref ref = { @@ -397,7 +359,6 @@ next_slot: btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - args->end); - btrfs_mark_buffer_dirty(trans, leaf); if (update_refs && disk_bytenr > 0) args->bytes_found += args->end - key.offset; break; @@ -409,7 +370,11 @@ next_slot: * | -------- extent -------- | */ if (args->start > key.offset && args->end >= extent_end) { - BUG_ON(del_nr > 0); + if (WARN_ON(del_nr > 0)) { + btrfs_print_leaf(leaf); + ret = -EINVAL; + break; + } if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; break; @@ -417,7 +382,6 @@ next_slot: btrfs_set_file_extent_num_bytes(leaf, fi, args->start - key.offset); - btrfs_mark_buffer_dirty(trans, leaf); if (update_refs && disk_bytenr > 0) args->bytes_found += extent_end - args->start; if (args->end == extent_end) @@ -437,7 +401,11 @@ delete_extent_item: del_slot = path->slots[0]; del_nr = 1; } else { - BUG_ON(del_slot + del_nr != path->slots[0]); + if (WARN_ON(del_slot + del_nr != path->slots[0])) { + btrfs_print_leaf(leaf); + ret = -EINVAL; + break; + } del_nr++; } @@ -668,7 +636,6 @@ again: trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, end - other_start); - btrfs_mark_buffer_dirty(trans, leaf); goto out; } } @@ -697,7 +664,6 @@ again: other_end - start); btrfs_set_file_extent_offset(leaf, fi, start - orig_offset); - btrfs_mark_buffer_dirty(trans, leaf); goto out; } } @@ -731,7 +697,6 @@ again: btrfs_set_file_extent_offset(leaf, fi, split - orig_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - split); - btrfs_mark_buffer_dirty(trans, leaf); ref.action = BTRFS_ADD_DELAYED_REF; ref.bytenr = bytenr; @@ -810,7 +775,6 @@ again: btrfs_set_file_extent_type(leaf, fi, BTRFS_FILE_EXTENT_REG); btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); } else { fi = btrfs_item_ptr(leaf, del_slot - 1, struct btrfs_file_extent_item); @@ -819,7 +783,6 @@ again: btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - key.offset); - btrfs_mark_buffer_dirty(trans, leaf); ret = btrfs_del_items(trans, root, path, del_slot, del_nr); if (ret < 0) { @@ -1052,7 +1015,7 @@ int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos, &cached_state); } ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, - NULL, nowait, false); + NULL, nowait); if (ret <= 0) btrfs_drew_write_unlock(&root->snapshot_lock); else @@ -1252,7 +1215,23 @@ again: break; } - copied = btrfs_copy_from_user(pos, write_bytes, folio, i); + copied = copy_folio_from_iter_atomic(folio, + offset_in_folio(folio, pos), write_bytes, i); + flush_dcache_folio(folio); + + /* + * If we get a partial write, we can end up with partially + * uptodate page. Although if sector size < page size we can + * handle it, but if it's not sector aligned it can cause + * a lot of complexity, so make sure they don't happen by + * forcing retry this copy. + */ + if (unlikely(copied < write_bytes)) { + if (!folio_test_uptodate(folio)) { + iov_iter_revert(i, copied); + copied = 0; + } + } num_sectors = BTRFS_BYTES_TO_BLKS(fs_info, reserve_bytes); dirty_sectors = round_up(copied + sector_offset, @@ -2029,7 +2008,6 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); goto out; } @@ -2046,7 +2024,6 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); goto out; } btrfs_release_path(path); @@ -2194,7 +2171,6 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, extent, replace_len); if (extent_info->is_new_extent) btrfs_set_file_extent_generation(leaf, extent, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); ret = btrfs_inode_set_file_extent_range(inode, extent_info->file_offset, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index cfa52ef40b06..d42b6f882f57 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -12,7 +12,7 @@ #include #include #include -#include "ctree.h" +#include "extent-tree.h" #include "fs.h" #include "messages.h" #include "misc.h" @@ -198,7 +198,6 @@ static int __create_free_space_inode(struct btrfs_root *root, btrfs_set_inode_nlink(leaf, inode_item, 1); btrfs_set_inode_transid(leaf, inode_item, trans->transid); btrfs_set_inode_block_group(leaf, inode_item, offset); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); key.objectid = BTRFS_FREE_SPACE_OBJECTID; @@ -216,7 +215,6 @@ static int __create_free_space_inode(struct btrfs_root *root, struct btrfs_free_space_header); memzero_extent_buffer(leaf, (unsigned long)header, sizeof(*header)); btrfs_set_free_space_key(leaf, header, &disk_key); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return 0; @@ -463,7 +461,7 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) return -ENOMEM; } - ret = set_page_extent_mapped(page); + ret = set_folio_extent_mapped(page_folio(page)); if (ret < 0) { unlock_page(page); put_page(page); @@ -1189,7 +1187,6 @@ update_cache_item(struct btrfs_trans_handle *trans, btrfs_set_free_space_entries(leaf, header, entries); btrfs_set_free_space_bitmaps(leaf, header, bitmaps); btrfs_set_free_space_generation(leaf, header, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return 0; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 7ba50e133921..cae540ec15ed 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -89,7 +89,6 @@ static int add_new_free_space_info(struct btrfs_trans_handle *trans, struct btrfs_free_space_info); btrfs_set_free_space_extent_count(leaf, info, 0); btrfs_set_free_space_flags(leaf, info, 0); - btrfs_mark_buffer_dirty(trans, leaf); ret = 0; out: @@ -287,7 +286,6 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, flags |= BTRFS_FREE_SPACE_USING_BITMAPS; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); if (extent_count != expected_extent_count) { @@ -324,7 +322,6 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); write_extent_buffer(leaf, bitmap_cursor, ptr, data_size); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); i += extent_size; @@ -430,7 +427,6 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, flags &= ~BTRFS_FREE_SPACE_USING_BITMAPS; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); nrbits = block_group->length >> block_group->fs_info->sectorsize_bits; @@ -495,7 +491,6 @@ static int update_free_space_extent_count(struct btrfs_trans_handle *trans, extent_count += new_extents; btrfs_set_free_space_extent_count(path->nodes[0], info, extent_count); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); if (!(flags & BTRFS_FREE_SPACE_USING_BITMAPS) && @@ -1350,6 +1345,12 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_end_transaction(trans); return ret; } + if (btrfs_should_end_transaction(trans)) { + btrfs_end_transaction(trans); + trans = btrfs_start_transaction(free_space_root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); + } node = rb_next(node); } diff --git a/fs/btrfs/fs.c b/fs/btrfs/fs.c index 31c1648bc0b4..09cfb43580cb 100644 --- a/fs/btrfs/fs.c +++ b/fs/btrfs/fs.c @@ -4,6 +4,136 @@ #include "ctree.h" #include "fs.h" #include "accessors.h" +#include "volumes.h" + +static const struct btrfs_csums { + u16 size; + const char name[10]; + const char driver[12]; +} btrfs_csums[] = { + [BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" }, + [BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" }, + [BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" }, + [BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b", + .driver = "blake2b-256" }, +}; + +/* This exists for btrfs-progs usages. */ +u16 btrfs_csum_type_size(u16 type) +{ + return btrfs_csums[type].size; +} + +int btrfs_super_csum_size(const struct btrfs_super_block *s) +{ + u16 t = btrfs_super_csum_type(s); + + /* csum type is validated at mount time. */ + return btrfs_csum_type_size(t); +} + +const char *btrfs_super_csum_name(u16 csum_type) +{ + /* csum type is validated at mount time. */ + return btrfs_csums[csum_type].name; +} + +/* + * Return driver name if defined, otherwise the name that's also a valid driver + * name. + */ +const char *btrfs_super_csum_driver(u16 csum_type) +{ + /* csum type is validated at mount time */ + return btrfs_csums[csum_type].driver[0] ? + btrfs_csums[csum_type].driver : + btrfs_csums[csum_type].name; +} + +size_t __attribute_const__ btrfs_get_num_csums(void) +{ + return ARRAY_SIZE(btrfs_csums); +} + +/* + * Start exclusive operation @type, return true on success. + */ +bool btrfs_exclop_start(struct btrfs_fs_info *fs_info, + enum btrfs_exclusive_operation type) +{ + bool ret = false; + + spin_lock(&fs_info->super_lock); + if (fs_info->exclusive_operation == BTRFS_EXCLOP_NONE) { + fs_info->exclusive_operation = type; + ret = true; + } + spin_unlock(&fs_info->super_lock); + + return ret; +} + +/* + * Conditionally allow to enter the exclusive operation in case it's compatible + * with the running one. This must be paired with btrfs_exclop_start_unlock() + * and btrfs_exclop_finish(). + * + * Compatibility: + * - the same type is already running + * - when trying to add a device and balance has been paused + * - not BTRFS_EXCLOP_NONE - this is intentionally incompatible and the caller + * must check the condition first that would allow none -> @type + */ +bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info, + enum btrfs_exclusive_operation type) +{ + spin_lock(&fs_info->super_lock); + if (fs_info->exclusive_operation == type || + (fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED && + type == BTRFS_EXCLOP_DEV_ADD)) + return true; + + spin_unlock(&fs_info->super_lock); + return false; +} + +void btrfs_exclop_start_unlock(struct btrfs_fs_info *fs_info) +{ + spin_unlock(&fs_info->super_lock); +} + +void btrfs_exclop_finish(struct btrfs_fs_info *fs_info) +{ + spin_lock(&fs_info->super_lock); + WRITE_ONCE(fs_info->exclusive_operation, BTRFS_EXCLOP_NONE); + spin_unlock(&fs_info->super_lock); + sysfs_notify(&fs_info->fs_devices->fsid_kobj, NULL, "exclusive_operation"); +} + +void btrfs_exclop_balance(struct btrfs_fs_info *fs_info, + enum btrfs_exclusive_operation op) +{ + switch (op) { + case BTRFS_EXCLOP_BALANCE_PAUSED: + spin_lock(&fs_info->super_lock); + ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE || + fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD || + fs_info->exclusive_operation == BTRFS_EXCLOP_NONE || + fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); + fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED; + spin_unlock(&fs_info->super_lock); + break; + case BTRFS_EXCLOP_BALANCE: + spin_lock(&fs_info->super_lock); + ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); + fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE; + spin_unlock(&fs_info->super_lock); + break; + default: + btrfs_warn(fs_info, + "invalid exclop balance operation %d requested", op); + } +} void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag, const char *name) diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 79a1a3d6f04d..b572d6b9730b 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -14,10 +14,10 @@ #include #include #include -#include #include #include #include +#include #include #include #include @@ -627,6 +627,9 @@ struct btrfs_fs_info { struct kobject *qgroups_kobj; struct kobject *discard_kobj; + /* Track the number of blocks (sectors) read by the filesystem. */ + struct percpu_counter stats_read_blocks; + /* Used to keep from writing metadata until there is a nice batch */ struct percpu_counter dirty_metadata_bytes; struct percpu_counter delalloc_bytes; @@ -887,6 +890,11 @@ struct btrfs_fs_info { #define inode_to_fs_info(_inode) (BTRFS_I(_Generic((_inode), \ struct inode *: (_inode)))->root->fs_info) +static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) +{ + return mapping_gfp_constraint(mapping, ~__GFP_FS); +} + static inline u64 btrfs_get_fs_generation(const struct btrfs_fs_info *fs_info) { return READ_ONCE(fs_info->generation); @@ -953,6 +961,8 @@ static inline u64 btrfs_calc_metadata_size(const struct btrfs_fs_info *fs_info, #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \ sizeof(struct btrfs_item)) +#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) ((bytes) >> (fs_info)->sectorsize_bits) + static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info) { return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && fs_info->zone_size > 0; @@ -982,6 +992,17 @@ void btrfs_exclop_balance(struct btrfs_fs_info *fs_info, int btrfs_check_ioctl_vol_args_path(const struct btrfs_ioctl_vol_args *vol_args); +u16 btrfs_csum_type_size(u16 type); +int btrfs_super_csum_size(const struct btrfs_super_block *s); +const char *btrfs_super_csum_name(u16 csum_type); +const char *btrfs_super_csum_driver(u16 csum_type); +size_t __attribute_const__ btrfs_get_num_csums(void); + +static inline bool btrfs_is_empty_uuid(const u8 *uuid) +{ + return uuid_is_null((const uuid_t *)uuid); +} + /* Compatibility and incompatibility defines */ void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag, const char *name); @@ -1058,6 +1079,14 @@ static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info) (unlikely(test_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR, \ &(fs_info)->fs_state))) +/* + * We use folio flag owner_2 to indicate there is an ordered extent with + * unfinished IO. + */ +#define folio_test_ordered(folio) folio_test_owner_2(folio) +#define folio_set_ordered(folio) folio_set_owner_2(folio) +#define folio_clear_ordered(folio) folio_clear_owner_2(folio) + #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS #define EXPORT_FOR_TESTS diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 29572dfaf878..448aa1a682d6 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -298,8 +298,6 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, ptr = (unsigned long)&extref->name; write_extent_buffer(path->nodes[0], name->name, ptr, name->len); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); - out: btrfs_free_path(path); return ret; @@ -363,8 +361,6 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, ptr = (unsigned long)(ref + 1); } write_extent_buffer(path->nodes[0], name->name, ptr, name->len); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); - out: btrfs_free_path(path); @@ -590,7 +586,6 @@ search_again: num_dec = (orig_num_bytes - extent_num_bytes); if (extent_start != 0) control->sub_bytes += num_dec; - btrfs_mark_buffer_dirty(trans, leaf); } else { extent_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 488edca8333a..a9322601ab5c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -393,34 +393,13 @@ void btrfs_inode_unlock(struct btrfs_inode *inode, unsigned int ilock_flags) * extent (btrfs_finish_ordered_io()). */ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, - struct folio *locked_folio, u64 offset, u64 bytes) { unsigned long index = offset >> PAGE_SHIFT; unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT; - u64 page_start = 0, page_end = 0; struct folio *folio; - if (locked_folio) { - page_start = folio_pos(locked_folio); - page_end = page_start + folio_size(locked_folio) - 1; - } - while (index <= end_index) { - /* - * For locked page, we will call btrfs_mark_ordered_io_finished - * through btrfs_mark_ordered_io_finished() on it - * in run_delalloc_range() for the error handling, which will - * clear page Ordered and run the ordered extent accounting. - * - * Here we can't just clear the Ordered bit, or - * btrfs_mark_ordered_io_finished() would skip the accounting - * for the page range, and the ordered extent will never finish. - */ - if (locked_folio && index == (page_start >> PAGE_SHIFT)) { - index++; - continue; - } folio = filemap_get_folio(inode->vfs_inode.i_mapping, index); index++; if (IS_ERR(folio)) @@ -436,23 +415,6 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, folio_put(folio); } - if (locked_folio) { - /* The locked page covers the full range, nothing needs to be done */ - if (bytes + offset <= page_start + folio_size(locked_folio)) - return; - /* - * In case this page belongs to the delalloc range being - * instantiated then skip it, since the first page of a range is - * going to be properly cleaned up by the caller of - * run_delalloc_range - */ - if (page_start >= offset && page_end <= (offset + bytes - 1)) { - bytes = offset + bytes - folio_pos(locked_folio) - - folio_size(locked_folio); - offset = folio_pos(locked_folio) + folio_size(locked_folio); - } - } - return btrfs_mark_ordered_io_finished(inode, NULL, offset, bytes, false); } @@ -564,7 +526,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, kunmap_local(kaddr); folio_put(folio); } - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); /* @@ -1129,19 +1090,14 @@ static void submit_uncompressed_range(struct btrfs_inode *inode, &wbc, false); wbc_detach_inode(&wbc); if (ret < 0) { - btrfs_cleanup_ordered_extents(inode, locked_folio, - start, end - start + 1); - if (locked_folio) { - const u64 page_start = folio_pos(locked_folio); - - folio_start_writeback(locked_folio); - folio_end_writeback(locked_folio); - btrfs_mark_ordered_io_finished(inode, locked_folio, - page_start, PAGE_SIZE, - !ret); - mapping_set_error(locked_folio->mapping, ret); - folio_unlock(locked_folio); - } + btrfs_cleanup_ordered_extents(inode, start, end - start + 1); + if (locked_folio) + btrfs_folio_end_lock(inode->root->fs_info, locked_folio, + start, async_extent->ram_size); + btrfs_err_rl(inode->root->fs_info, + "%s failed, root=%llu inode=%llu start=%llu len=%llu: %d", + __func__, btrfs_root_id(inode->root), + btrfs_ino(inode), start, async_extent->ram_size, ret); } } @@ -1372,6 +1328,17 @@ static noinline int cow_file_range(struct btrfs_inode *inode, alloc_hint = btrfs_get_extent_allocation_hint(inode, start, num_bytes); + /* + * We're not doing compressed IO, don't unlock the first page (which + * the caller expects to stay locked), don't clear any dirty bits and + * don't set any writeback bits. + * + * Do set the Ordered (Private2) bit so we know this page was properly + * setup for writepage. + */ + page_ops = (keep_locked ? 0 : PAGE_UNLOCK); + page_ops |= PAGE_SET_ORDERED; + /* * Relocation relies on the relocated extents to have exactly the same * size as the original extents. Normally writeback for relocation data @@ -1431,6 +1398,10 @@ static noinline int cow_file_range(struct btrfs_inode *inode, file_extent.offset = 0; file_extent.compression = BTRFS_COMPRESS_NONE; + /* + * Locked range will be released either during error clean up or + * after the whole range is finished. + */ lock_extent(&inode->io_tree, start, start + cur_alloc_size - 1, &cached); @@ -1476,21 +1447,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode, btrfs_dec_block_group_reservations(fs_info, ins.objectid); - /* - * We're not doing compressed IO, don't unlock the first page - * (which the caller expects to stay locked), don't clear any - * dirty bits and don't set any writeback bits - * - * Do set the Ordered flag so we know this page was - * properly setup for writepage. - */ - page_ops = (keep_locked ? 0 : PAGE_UNLOCK); - page_ops |= PAGE_SET_ORDERED; - - extent_clear_unlock_delalloc(inode, start, start + cur_alloc_size - 1, - locked_folio, &cached, - EXTENT_LOCKED | EXTENT_DELALLOC, - page_ops); if (num_bytes < cur_alloc_size) num_bytes = 0; else @@ -1507,6 +1463,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode, if (ret) goto out_unlock; } + extent_clear_unlock_delalloc(inode, orig_start, end, locked_folio, &cached, + EXTENT_LOCKED | EXTENT_DELALLOC, page_ops); done: if (done_offset) *done_offset = end; @@ -1527,35 +1485,30 @@ out_unlock: * We process each region below. */ - clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | - EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV; - page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK; - /* * For the range (1). We have already instantiated the ordered extents * for this region. They are cleaned up by * btrfs_cleanup_ordered_extents() in e.g, - * btrfs_run_delalloc_range(). EXTENT_LOCKED | EXTENT_DELALLOC are - * already cleared in the above loop. And, EXTENT_DELALLOC_NEW | - * EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV are handled by the cleanup - * function. + * btrfs_run_delalloc_range(). + * EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV + * are also handled by the cleanup function. * - * However, in case of @keep_locked, we still need to unlock the pages - * (except @locked_folio) to ensure all the pages are unlocked. + * So here we only clear EXTENT_LOCKED and EXTENT_DELALLOC flag, and + * finish the writeback of the involved folios, which will be never submitted. */ - if (keep_locked && orig_start < start) { + if (orig_start < start) { + clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC; + page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK; + if (!locked_folio) mapping_set_error(inode->vfs_inode.i_mapping, ret); extent_clear_unlock_delalloc(inode, orig_start, start - 1, - locked_folio, NULL, 0, page_ops); + locked_folio, NULL, clear_bits, page_ops); } - /* - * At this point we're unlocked, we want to make sure we're only - * clearing these flags under the extent lock, so lock the rest of the - * range and clear everything up. - */ - lock_extent(&inode->io_tree, start, end, NULL); + clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV; + page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK; /* * For the range (2). If we reserved an extent for our delalloc range @@ -1589,6 +1542,10 @@ out_unlock: btrfs_qgroup_free_data(inode, NULL, start + cur_alloc_size, end - start - cur_alloc_size + 1, NULL); } + btrfs_err_rl(fs_info, + "%s failed, root=%llu inode=%llu start=%llu len=%llu: %d", + __func__, btrfs_root_id(inode->root), + btrfs_ino(inode), orig_start, end + 1 - orig_start, ret); return ret; } @@ -1809,7 +1766,7 @@ static int fallback_to_cow(struct btrfs_inode *inode, bytes = range_bytes; spin_lock(&sinfo->lock); - btrfs_space_info_update_bytes_may_use(fs_info, sinfo, bytes); + btrfs_space_info_update_bytes_may_use(sinfo, bytes); spin_unlock(&sinfo->lock); if (count > 0) @@ -1837,7 +1794,6 @@ struct can_nocow_file_extent_args { /* End file offset (inclusive) of the range we want to NOCOW. */ u64 end; bool writeback_path; - bool strict; /* * Free the path passed to can_nocow_file_extent() once it's not needed * anymore. @@ -1892,8 +1848,7 @@ static int can_nocow_file_extent(struct btrfs_path *path, * for its subvolume was created, then this implies the extent is shared, * hence we must COW. */ - if (!args->strict && - btrfs_file_extent_generation(leaf, fi) <= + if (btrfs_file_extent_generation(leaf, fi) <= btrfs_root_last_snapshot(&root->root_item)) goto out; @@ -1922,9 +1877,8 @@ static int can_nocow_file_extent(struct btrfs_path *path, */ btrfs_release_path(path); - ret = btrfs_cross_ref_exist(root, btrfs_ino(inode), - key->offset - args->file_extent.offset, - args->file_extent.disk_bytenr, args->strict, path); + ret = btrfs_cross_ref_exist(inode, key->offset - args->file_extent.offset, + args->file_extent.disk_bytenr, path); WARN_ON_ONCE(ret > 0 && is_freespace_inode); if (ret != 0) goto out; @@ -1970,6 +1924,53 @@ static int can_nocow_file_extent(struct btrfs_path *path, return ret < 0 ? ret : can_nocow; } +/* + * Cleanup the dirty folios which will never be submitted due to error. + * + * When running a delalloc range, we may need to split the ranges (due to + * fragmentation or NOCOW). If we hit an error in the later part, we will error + * out and previously successfully executed range will never be submitted, thus + * we have to cleanup those folios by clearing their dirty flag, starting and + * finishing the writeback. + */ +static void cleanup_dirty_folios(struct btrfs_inode *inode, + struct folio *locked_folio, + u64 start, u64 end, int error) +{ + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct address_space *mapping = inode->vfs_inode.i_mapping; + pgoff_t start_index = start >> PAGE_SHIFT; + pgoff_t end_index = end >> PAGE_SHIFT; + u32 len; + + ASSERT(end + 1 - start < U32_MAX); + ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && + IS_ALIGNED(end + 1, fs_info->sectorsize)); + len = end + 1 - start; + + /* + * Handle the locked folio first. + * The btrfs_folio_clamp_*() helpers can handle range out of the folio case. + */ + btrfs_folio_clamp_finish_io(fs_info, locked_folio, start, len); + + for (pgoff_t index = start_index; index <= end_index; index++) { + struct folio *folio; + + /* Already handled at the beginning. */ + if (index == locked_folio->index) + continue; + folio = __filemap_get_folio(mapping, index, FGP_LOCK, GFP_NOFS); + /* Cache already dropped, no need to do any cleanup. */ + if (IS_ERR(folio)) + continue; + btrfs_folio_clamp_finish_io(fs_info, locked_folio, start, len); + folio_unlock(folio); + folio_put(folio); + } + mapping_set_error(mapping, error); +} + /* * when nowcow writeback call back. This checks for snapshots or COW copies * of the extents that exist in the file, and COWs the file as required. @@ -1985,6 +1986,11 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, struct btrfs_root *root = inode->root; struct btrfs_path *path; u64 cow_start = (u64)-1; + /* + * If not 0, represents the inclusive end of the last fallback_to_cow() + * range. Only for error handling. + */ + u64 cow_end = 0; u64 cur_offset = start; int ret; bool check_prev = true; @@ -2145,6 +2151,7 @@ must_cow: found_key.offset - 1); cow_start = (u64)-1; if (ret) { + cow_end = found_key.offset - 1; btrfs_dec_nocow_writers(nocow_bg); goto error; } @@ -2218,11 +2225,12 @@ must_cow: cow_start = cur_offset; if (cow_start != (u64)-1) { - cur_offset = end; ret = fallback_to_cow(inode, locked_folio, cow_start, end); cow_start = (u64)-1; - if (ret) + if (ret) { + cow_end = end; goto error; + } } btrfs_free_path(path); @@ -2230,12 +2238,41 @@ must_cow: error: /* - * If an error happened while a COW region is outstanding, cur_offset - * needs to be reset to cow_start to ensure the COW region is unlocked - * as well. + * There are several error cases: + * + * 1) Failed without falling back to COW + * start cur_offset end + * |/////////////| | + * + * For range [start, cur_offset) the folios are already unlocked (except + * @locked_folio), EXTENT_DELALLOC already removed. + * Only need to clear the dirty flag as they will never be submitted. + * Ordered extent and extent maps are handled by + * btrfs_mark_ordered_io_finished() inside run_delalloc_range(). + * + * 2) Failed with error from fallback_to_cow() + * start cur_offset cow_end end + * |/////////////|-----------| | + * + * For range [start, cur_offset) it's the same as case 1). + * But for range [cur_offset, cow_end), the folios have dirty flag + * cleared and unlocked, EXTENT_DEALLLOC cleared by cow_file_range(). + * + * Thus we should not call extent_clear_unlock_delalloc() on range + * [cur_offset, cow_end), as the folios are already unlocked. + * + * So clear the folio dirty flags for [start, cur_offset) first. */ - if (cow_start != (u64)-1) - cur_offset = cow_start; + if (cur_offset > start) + cleanup_dirty_folios(inode, locked_folio, start, cur_offset - 1, ret); + + /* + * If an error happened while a COW region is outstanding, cur_offset + * needs to be reset to @cow_end + 1 to skip the COW range, as + * cow_file_range() will do the proper cleanup at error. + */ + if (cow_end) + cur_offset = cow_end + 1; /* * We need to lock the extent here because we're clearing DELALLOC and @@ -2255,6 +2292,10 @@ error: btrfs_qgroup_free_data(inode, NULL, cur_offset, end - cur_offset + 1, NULL); } btrfs_free_path(path); + btrfs_err_rl(fs_info, + "%s failed, root=%llu inode=%llu start=%llu len=%llu: %d", + __func__, btrfs_root_id(inode->root), + btrfs_ino(inode), start, end + 1 - start, ret); return ret; } @@ -2305,8 +2346,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct folio *locked_fol out: if (ret < 0) - btrfs_cleanup_ordered_extents(inode, locked_folio, start, - end - start + 1); + btrfs_cleanup_ordered_extents(inode, start, end - start + 1); return ret; } @@ -2921,7 +2961,6 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(struct btrfs_file_extent_item)); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); /* @@ -4085,7 +4124,6 @@ static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans, struct btrfs_inode_item); fill_inode_item(trans, leaf, inode_item, &inode->vfs_inode); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_set_inode_last_trans(trans, inode); ret = 0; failed: @@ -6380,7 +6418,6 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, } } - btrfs_mark_buffer_dirty(trans, path->nodes[0]); /* * We don't need the path anymore, plus inheriting properties, adding * ACLs, security xattrs, orphan item or adding the link, will result in @@ -7011,8 +7048,6 @@ static bool btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr) * @orig_start: (optional) Return the original file offset of the file extent * @orig_len: (optional) Return the original on-disk length of the file extent * @ram_bytes: (optional) Return the ram_bytes of the file extent - * @strict: if true, omit optimizations that might force us into unnecessary - * cow. e.g., don't trust generation number. * * Return: * >0 and update @len if we can do nocow write @@ -7024,7 +7059,7 @@ static bool btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr) */ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, struct btrfs_file_extent *file_extent, - bool nowait, bool strict) + bool nowait) { struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct can_nocow_file_extent_args nocow_args = { 0 }; @@ -7077,7 +7112,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, nocow_args.start = offset; nocow_args.end = offset + *len - 1; - nocow_args.strict = strict; nocow_args.free_path = true; ret = can_nocow_file_extent(path, &key, BTRFS_I(inode), &nocow_args); @@ -8027,31 +8061,45 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* src is a subvolume */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_unlink_subvol(trans, BTRFS_I(old_dir), old_dentry); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } else { /* src is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), BTRFS_I(old_dentry->d_inode), old_name, &old_rename_ctx); - if (!ret) - ret = btrfs_update_inode(trans, BTRFS_I(old_inode)); - } - if (ret) { - btrfs_abort_transaction(trans, ret); - goto out_fail; + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } + ret = btrfs_update_inode(trans, BTRFS_I(old_inode)); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } /* dest is a subvolume */ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_unlink_subvol(trans, BTRFS_I(new_dir), new_dentry); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } else { /* dest is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(new_dentry->d_inode), new_name, &new_rename_ctx); - if (!ret) - ret = btrfs_update_inode(trans, BTRFS_I(new_inode)); - } - if (ret) { - btrfs_abort_transaction(trans, ret); - goto out_fail; + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } + ret = btrfs_update_inode(trans, BTRFS_I(new_inode)); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), @@ -8287,16 +8335,23 @@ static int btrfs_rename(struct mnt_idmap *idmap, if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) { ret = btrfs_unlink_subvol(trans, BTRFS_I(old_dir), old_dentry); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } else { ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), BTRFS_I(d_inode(old_dentry)), &old_fname.disk_name, &rename_ctx); - if (!ret) - ret = btrfs_update_inode(trans, BTRFS_I(old_inode)); - } - if (ret) { - btrfs_abort_transaction(trans, ret); - goto out_fail; + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } + ret = btrfs_update_inode(trans, BTRFS_I(old_inode)); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } if (new_inode) { @@ -8304,18 +8359,27 @@ static int btrfs_rename(struct mnt_idmap *idmap, if (unlikely(btrfs_ino(BTRFS_I(new_inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) { ret = btrfs_unlink_subvol(trans, BTRFS_I(new_dir), new_dentry); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } BUG_ON(new_inode->i_nlink == 0); } else { ret = btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(d_inode(new_dentry)), &new_fname.disk_name); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } - if (!ret && new_inode->i_nlink == 0) + if (new_inode->i_nlink == 0) { ret = btrfs_orphan_add(trans, BTRFS_I(d_inode(new_dentry))); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto out_fail; + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } } @@ -8655,7 +8719,6 @@ static int btrfs_symlink(struct mnt_idmap *idmap, struct inode *dir, ptr = btrfs_file_extent_inline_start(ei); write_extent_buffer(leaf, symname, ptr, name_len); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_free_path(path); d_instantiate_new(dentry, inode); @@ -9078,9 +9141,9 @@ out: } struct btrfs_encoded_read_private { - wait_queue_head_t wait; + struct completion done; void *uring_ctx; - atomic_t pending; + refcount_t pending_refs; blk_status_t status; }; @@ -9099,14 +9162,14 @@ static void btrfs_encoded_read_endio(struct btrfs_bio *bbio) */ WRITE_ONCE(priv->status, bbio->bio.bi_status); } - if (atomic_dec_and_test(&priv->pending)) { + if (refcount_dec_and_test(&priv->pending_refs)) { int err = blk_status_to_errno(READ_ONCE(priv->status)); if (priv->uring_ctx) { btrfs_uring_read_extent_endio(priv->uring_ctx, err); kfree(priv); } else { - wake_up(&priv->wait); + complete(&priv->done); } } bio_put(&bbio->bio); @@ -9126,8 +9189,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, if (!priv) return -ENOMEM; - init_waitqueue_head(&priv->wait); - atomic_set(&priv->pending, 1); + init_completion(&priv->done); + refcount_set(&priv->pending_refs, 1); priv->status = 0; priv->uring_ctx = uring_ctx; @@ -9140,7 +9203,7 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, size_t bytes = min_t(u64, disk_io_size, PAGE_SIZE); if (bio_add_page(&bbio->bio, pages[i], bytes, 0) < bytes) { - atomic_inc(&priv->pending); + refcount_inc(&priv->pending_refs); btrfs_submit_bbio(bbio, 0); bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info, @@ -9155,11 +9218,11 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, disk_io_size -= bytes; } while (disk_io_size); - atomic_inc(&priv->pending); + refcount_inc(&priv->pending_refs); btrfs_submit_bbio(bbio, 0); if (uring_ctx) { - if (atomic_dec_return(&priv->pending) == 0) { + if (refcount_dec_and_test(&priv->pending_refs)) { ret = blk_status_to_errno(READ_ONCE(priv->status)); btrfs_uring_read_extent_endio(uring_ctx, ret); kfree(priv); @@ -9168,8 +9231,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, return -EIOCBQUEUED; } else { - if (atomic_dec_return(&priv->pending) != 0) - io_wait_event(priv->wait, !atomic_read(&priv->pending)); + if (!refcount_dec_and_test(&priv->pending_refs)) + wait_for_completion_io(&priv->done); /* See btrfs_encoded_read_endio() for ordering. */ ret = blk_status_to_errno(READ_ONCE(priv->status)); kfree(priv); @@ -9799,15 +9862,25 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; + + /* + * Acquire the inode's mmap lock to prevent races with memory mapped + * writes, as they could happen after we flush delalloc below and before + * we lock the extent range further below. The inode was already locked + * up in the call chain. + */ + btrfs_assert_inode_locked(BTRFS_I(inode)); + down_write(&BTRFS_I(inode)->i_mmap_lock); /* * If the swap file was just created, make sure delalloc is done. If the @@ -9816,22 +9889,32 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, */ ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1); if (ret) - return ret; + goto out_unlock_mmap; /* * The inode is locked, so these flags won't change after we check them. */ if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) { btrfs_warn(fs_info, "swapfile must not be compressed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { btrfs_warn(fs_info, "swapfile must not be checksummed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; + } + + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; } /* @@ -9846,7 +9929,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) { btrfs_warn(fs_info, "cannot activate swapfile while exclusive operation is running"); - return -EBUSY; + ret = -EBUSY; + goto out_unlock_mmap; } /* @@ -9860,7 +9944,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_exclop_finish(fs_info); btrfs_warn(fs_info, "cannot activate swapfile because snapshot creation is in progress"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } /* * Snapshots can create extents which require COW even if NODATACOW is @@ -9881,7 +9966,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_warn(fs_info, "cannot activate swapfile because subvolume %llu is being deleted", btrfs_root_id(root)); - return -EPERM; + ret = -EPERM; + goto out_unlock_mmap; } atomic_inc(&root->nr_swapfiles); spin_unlock(&root->root_item_lock); @@ -9889,24 +9975,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9918,23 +10019,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); + + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; + + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9969,7 +10092,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -10010,20 +10132,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - start += len; + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } + + cond_resched(); } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10036,6 +10161,10 @@ out: btrfs_exclop_finish(fs_info); +out_unlock_mmap: + up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret; @@ -10044,7 +10173,6 @@ out: *span = bsi.highest_ppage - bsi.lowest_ppage + 1; sis->max = bsi.nr_pages; sis->pages = bsi.nr_pages - 1; - sis->highest_bit = bsi.nr_pages - 1; return bsi.nr_extents; } #else diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3af8bb0c8d75..6c18bad53cd3 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -403,86 +403,6 @@ update_flags: return ret; } -/* - * Start exclusive operation @type, return true on success - */ -bool btrfs_exclop_start(struct btrfs_fs_info *fs_info, - enum btrfs_exclusive_operation type) -{ - bool ret = false; - - spin_lock(&fs_info->super_lock); - if (fs_info->exclusive_operation == BTRFS_EXCLOP_NONE) { - fs_info->exclusive_operation = type; - ret = true; - } - spin_unlock(&fs_info->super_lock); - - return ret; -} - -/* - * Conditionally allow to enter the exclusive operation in case it's compatible - * with the running one. This must be paired with btrfs_exclop_start_unlock and - * btrfs_exclop_finish. - * - * Compatibility: - * - the same type is already running - * - when trying to add a device and balance has been paused - * - not BTRFS_EXCLOP_NONE - this is intentionally incompatible and the caller - * must check the condition first that would allow none -> @type - */ -bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info, - enum btrfs_exclusive_operation type) -{ - spin_lock(&fs_info->super_lock); - if (fs_info->exclusive_operation == type || - (fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED && - type == BTRFS_EXCLOP_DEV_ADD)) - return true; - - spin_unlock(&fs_info->super_lock); - return false; -} - -void btrfs_exclop_start_unlock(struct btrfs_fs_info *fs_info) -{ - spin_unlock(&fs_info->super_lock); -} - -void btrfs_exclop_finish(struct btrfs_fs_info *fs_info) -{ - spin_lock(&fs_info->super_lock); - WRITE_ONCE(fs_info->exclusive_operation, BTRFS_EXCLOP_NONE); - spin_unlock(&fs_info->super_lock); - sysfs_notify(&fs_info->fs_devices->fsid_kobj, NULL, "exclusive_operation"); -} - -void btrfs_exclop_balance(struct btrfs_fs_info *fs_info, - enum btrfs_exclusive_operation op) -{ - switch (op) { - case BTRFS_EXCLOP_BALANCE_PAUSED: - spin_lock(&fs_info->super_lock); - ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE || - fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD || - fs_info->exclusive_operation == BTRFS_EXCLOP_NONE || - fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); - fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED; - spin_unlock(&fs_info->super_lock); - break; - case BTRFS_EXCLOP_BALANCE: - spin_lock(&fs_info->super_lock); - ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); - fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE; - spin_unlock(&fs_info->super_lock); - break; - default: - btrfs_warn(fs_info, - "invalid exclop balance operation %d requested", op); - } -} - static int btrfs_ioctl_getversion(struct inode *inode, int __user *arg) { return put_user(inode->i_generation, arg); @@ -551,17 +471,6 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, return ret; } -int __pure btrfs_is_empty_uuid(const u8 *uuid) -{ - int i; - - for (i = 0; i < BTRFS_UUID_SIZE; i++) { - if (uuid[i]) - return 0; - } - return 1; -} - /* * Calculate the number of transaction items to reserve for creating a subvolume * or snapshot, not including the inode, directory entries, or parent directory. @@ -2635,6 +2544,15 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) goto out; } + /* + * Don't allow defrag on pre-content watched files, as it could + * populate the page cache with 0's via readahead. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + ret = -EINVAL; + goto out; + } + if (argp) { if (copy_from_user(&range, argp, sizeof(range))) { ret = -EFAULT; @@ -3007,7 +2925,6 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) btrfs_cpu_key_to_disk(&disk_key, &new_root->root_key); btrfs_set_dir_item_key(path->nodes[0], di, &disk_key); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); btrfs_set_fs_incompat(fs_info, DEFAULT_SUBVOL); @@ -4878,25 +4795,29 @@ out_fail: return ret; } +struct btrfs_uring_encoded_data { + struct btrfs_ioctl_encoded_io_args args; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov; + struct iov_iter iter; +}; + static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue_flags) { size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags); size_t copy_end; - struct btrfs_ioctl_encoded_io_args args = { 0 }; int ret; u64 disk_bytenr, disk_io_size; struct file *file; struct btrfs_inode *inode; struct btrfs_fs_info *fs_info; struct extent_io_tree *io_tree; - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - struct iov_iter iter; loff_t pos; struct kiocb kiocb; struct extent_state *cached_state = NULL; u64 start, lockend; void __user *sqe_addr; + struct btrfs_uring_encoded_data *data = io_uring_cmd_get_async_data(cmd)->op_data; if (!capable(CAP_SYS_ADMIN)) { ret = -EPERM; @@ -4910,43 +4831,64 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue if (issue_flags & IO_URING_F_COMPAT) { #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) - struct btrfs_ioctl_encoded_io_args_32 args32; - copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, flags); - if (copy_from_user(&args32, sqe_addr, copy_end)) { - ret = -EFAULT; - goto out_acct; - } - args.iov = compat_ptr(args32.iov); - args.iovcnt = args32.iovcnt; - args.offset = args32.offset; - args.flags = args32.flags; #else return -ENOTTY; #endif } else { copy_end = copy_end_kernel; - if (copy_from_user(&args, sqe_addr, copy_end)) { - ret = -EFAULT; + } + + if (!data) { + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + ret = -ENOMEM; goto out_acct; } + + io_uring_cmd_get_async_data(cmd)->op_data = data; + + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; + + if (copy_from_user(&args32, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + + data->args.iov = compat_ptr(args32.iov); + data->args.iovcnt = args32.iovcnt; + data->args.offset = args32.offset; + data->args.flags = args32.flags; +#endif + } else { + if (copy_from_user(&data->args, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + } + + if (data->args.flags != 0) { + ret = -EINVAL; + goto out_acct; + } + + data->iov = data->iovstack; + ret = import_iovec(ITER_DEST, data->args.iov, data->args.iovcnt, + ARRAY_SIZE(data->iovstack), &data->iov, + &data->iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&data->iter) == 0) { + ret = 0; + goto out_free; + } } - if (args.flags != 0) - return -EINVAL; - - ret = import_iovec(ITER_DEST, args.iov, args.iovcnt, ARRAY_SIZE(iovstack), - &iov, &iter); - if (ret < 0) - goto out_acct; - - if (iov_iter_count(&iter) == 0) { - ret = 0; - goto out_free; - } - - pos = args.offset; - ret = rw_verify_area(READ, file, &pos, args.len); + pos = data->args.offset; + ret = rw_verify_area(READ, file, &pos, data->args.len); if (ret < 0) goto out_free; @@ -4959,15 +4901,16 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue start = ALIGN_DOWN(pos, fs_info->sectorsize); lockend = start + BTRFS_MAX_UNCOMPRESSED - 1; - ret = btrfs_encoded_read(&kiocb, &iter, &args, &cached_state, + ret = btrfs_encoded_read(&kiocb, &data->iter, &data->args, &cached_state, &disk_bytenr, &disk_io_size); if (ret < 0 && ret != -EIOCBQUEUED) goto out_free; file_accessed(file); - if (copy_to_user(sqe_addr + copy_end, (const char *)&args + copy_end_kernel, - sizeof(args) - copy_end_kernel)) { + if (copy_to_user(sqe_addr + copy_end, + (const char *)&data->args + copy_end_kernel, + sizeof(data->args) - copy_end_kernel)) { if (ret == -EIOCBQUEUED) { unlock_extent(io_tree, start, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); @@ -4977,40 +4920,22 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue } if (ret == -EIOCBQUEUED) { - u64 count; - - /* - * If we've optimized things by storing the iovecs on the stack, - * undo this. - */ - if (!iov) { - iov = kmalloc(sizeof(struct iovec) * args.iovcnt, GFP_NOFS); - if (!iov) { - unlock_extent(io_tree, start, lockend, &cached_state); - btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); - ret = -ENOMEM; - goto out_acct; - } - - memcpy(iov, iovstack, sizeof(struct iovec) * args.iovcnt); - } - - count = min_t(u64, iov_iter_count(&iter), disk_io_size); + u64 count = min_t(u64, iov_iter_count(&data->iter), disk_io_size); /* Match ioctl by not returning past EOF if uncompressed. */ - if (!args.compression) - count = min_t(u64, count, args.len); + if (!data->args.compression) + count = min_t(u64, count, data->args.len); - ret = btrfs_uring_read_extent(&kiocb, &iter, start, lockend, - cached_state, disk_bytenr, - disk_io_size, count, - args.compression, iov, cmd); + ret = btrfs_uring_read_extent(&kiocb, &data->iter, start, lockend, + cached_state, disk_bytenr, disk_io_size, + count, data->args.compression, + data->iov, cmd); goto out_acct; } out_free: - kfree(iov); + kfree(data->iov); out_acct: if (ret > 0) @@ -5020,6 +4945,128 @@ out_acct: return ret; } +static int btrfs_uring_encoded_write(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + loff_t pos; + struct kiocb kiocb; + struct file *file; + ssize_t ret; + void __user *sqe_addr; + struct btrfs_uring_encoded_data *data = io_uring_cmd_get_async_data(cmd)->op_data; + + if (!capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_acct; + } + + file = cmd->file; + sqe_addr = u64_to_user_ptr(READ_ONCE(cmd->sqe->addr)); + + if (!(file->f_mode & FMODE_WRITE)) { + ret = -EBADF; + goto out_acct; + } + + if (!data) { + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + ret = -ENOMEM; + goto out_acct; + } + + io_uring_cmd_get_async_data(cmd)->op_data = data; + + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; + + if (copy_from_user(&args32, sqe_addr, sizeof(args32))) { + ret = -EFAULT; + goto out_acct; + } + data->args.iov = compat_ptr(args32.iov); + data->args.iovcnt = args32.iovcnt; + data->args.offset = args32.offset; + data->args.flags = args32.flags; + data->args.len = args32.len; + data->args.unencoded_len = args32.unencoded_len; + data->args.unencoded_offset = args32.unencoded_offset; + data->args.compression = args32.compression; + data->args.encryption = args32.encryption; + memcpy(data->args.reserved, args32.reserved, + sizeof(data->args.reserved)); +#else + ret = -ENOTTY; + goto out_acct; +#endif + } else { + if (copy_from_user(&data->args, sqe_addr, sizeof(data->args))) { + ret = -EFAULT; + goto out_acct; + } + } + + ret = -EINVAL; + if (data->args.flags != 0) + goto out_acct; + if (memchr_inv(data->args.reserved, 0, sizeof(data->args.reserved))) + goto out_acct; + if (data->args.compression == BTRFS_ENCODED_IO_COMPRESSION_NONE && + data->args.encryption == BTRFS_ENCODED_IO_ENCRYPTION_NONE) + goto out_acct; + if (data->args.compression >= BTRFS_ENCODED_IO_COMPRESSION_TYPES || + data->args.encryption >= BTRFS_ENCODED_IO_ENCRYPTION_TYPES) + goto out_acct; + if (data->args.unencoded_offset > data->args.unencoded_len) + goto out_acct; + if (data->args.len > data->args.unencoded_len - data->args.unencoded_offset) + goto out_acct; + + data->iov = data->iovstack; + ret = import_iovec(ITER_SOURCE, data->args.iov, data->args.iovcnt, + ARRAY_SIZE(data->iovstack), &data->iov, + &data->iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&data->iter) == 0) { + ret = 0; + goto out_iov; + } + } + + if (issue_flags & IO_URING_F_NONBLOCK) { + ret = -EAGAIN; + goto out_acct; + } + + pos = data->args.offset; + ret = rw_verify_area(WRITE, file, &pos, data->args.len); + if (ret < 0) + goto out_iov; + + init_sync_kiocb(&kiocb, file); + ret = kiocb_set_rw_flags(&kiocb, 0, WRITE); + if (ret) + goto out_iov; + kiocb.ki_pos = pos; + + file_start_write(file); + + ret = btrfs_do_write_iter(&kiocb, &data->iter, &data->args); + if (ret > 0) + fsnotify_modify(file); + + file_end_write(file); +out_iov: + kfree(data->iov); +out_acct: + if (ret > 0) + add_wchar(current, ret); + inc_syscw(current); + return ret; +} + int btrfs_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { switch (cmd->cmd_op) { @@ -5028,6 +5075,12 @@ int btrfs_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) case BTRFS_IOC_ENCODED_READ_32: #endif return btrfs_uring_encoded_read(cmd, issue_flags); + + case BTRFS_IOC_ENCODED_WRITE: +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + case BTRFS_IOC_ENCODED_WRITE_32: +#endif + return btrfs_uring_encoded_write(cmd, issue_flags); } return -EINVAL; @@ -5300,6 +5353,8 @@ long btrfs_ioctl(struct file *file, unsigned int return fsverity_ioctl_enable(file, (const void __user *)argp); case FS_IOC_MEASURE_VERITY: return fsverity_ioctl_measure(file, argp); + case FS_IOC_READ_VERITY_METADATA: + return fsverity_ioctl_read_metadata(file, argp); case BTRFS_IOC_ENCODED_READ: return btrfs_ioctl_encoded_read(file, argp, false); case BTRFS_IOC_ENCODED_WRITE: diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 2b760c8778f8..ce915fcda43b 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -19,7 +19,6 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int btrfs_ioctl_get_supported_features(void __user *arg); void btrfs_sync_inode_flags_to_i_flags(struct inode *inode); -int __pure btrfs_is_empty_uuid(const u8 *uuid); void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_balance_args *bargs); int btrfs_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags); diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index 35036b151bf5..c69e57ff804b 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -199,8 +199,13 @@ static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb) { lockdep_assert_held_write(&eb->lock); } +static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb) +{ + lockdep_assert_held_read(&eb->lock); +} #else static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb) { } +static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { } #endif void btrfs_unlock_up_safe(struct btrfs_path *path, int level); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a6f92836c9b1..b90fabe302e6 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -673,9 +673,6 @@ static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, key.offset = dst; ret = btrfs_insert_empty_item(trans, quota_root, path, &key, 0); - - btrfs_mark_buffer_dirty(trans, path->nodes[0]); - btrfs_free_path(path); return ret; } @@ -752,8 +749,6 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_info_excl(leaf, qgroup_info, 0); btrfs_set_qgroup_info_excl_cmpr(leaf, qgroup_info, 0); - btrfs_mark_buffer_dirty(trans, leaf); - btrfs_release_path(path); key.type = BTRFS_QGROUP_LIMIT_KEY; @@ -771,8 +766,6 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_limit_rsv_rfer(leaf, qgroup_limit, 0); btrfs_set_qgroup_limit_rsv_excl(leaf, qgroup_limit, 0); - btrfs_mark_buffer_dirty(trans, leaf); - ret = 0; out: btrfs_free_path(path); @@ -859,9 +852,6 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_limit_max_excl(l, qgroup_limit, qgroup->max_excl); btrfs_set_qgroup_limit_rsv_rfer(l, qgroup_limit, qgroup->rsv_rfer); btrfs_set_qgroup_limit_rsv_excl(l, qgroup_limit, qgroup->rsv_excl); - - btrfs_mark_buffer_dirty(trans, l); - out: btrfs_free_path(path); return ret; @@ -905,9 +895,6 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_info_rfer_cmpr(l, qgroup_info, qgroup->rfer_cmpr); btrfs_set_qgroup_info_excl(l, qgroup_info, qgroup->excl); btrfs_set_qgroup_info_excl_cmpr(l, qgroup_info, qgroup->excl_cmpr); - - btrfs_mark_buffer_dirty(trans, l); - out: btrfs_free_path(path); return ret; @@ -947,9 +934,6 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans) btrfs_set_qgroup_status_generation(l, ptr, trans->transid); btrfs_set_qgroup_status_rescan(l, ptr, fs_info->qgroup_rescan_progress.objectid); - - btrfs_mark_buffer_dirty(trans, l); - out: btrfs_free_path(path); return ret; @@ -1121,6 +1105,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON; if (simple) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; + btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid); } else { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; @@ -1129,8 +1114,6 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, BTRFS_QGROUP_STATUS_FLAGS_MASK); btrfs_set_qgroup_status_rescan(leaf, ptr, 0); - btrfs_mark_buffer_dirty(trans, leaf); - key.objectid = 0; key.type = BTRFS_ROOT_REF_KEY; key.offset = 0; @@ -1254,8 +1237,6 @@ out_add_root: spin_lock(&fs_info->qgroup_lock); fs_info->quota_root = quota_root; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (simple) - btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); spin_unlock(&fs_info->qgroup_lock); /* Skip rescan for simple qgroups. */ @@ -1839,9 +1820,19 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) * Thus its reserved space should all be zero, no matter if qgroup * is consistent or the mode. */ - WARN_ON(qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] || - qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] || - qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]); + if (qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]) { + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + btrfs_warn_rl(fs_info, +"to be deleted qgroup %u/%llu has non-zero numbers, data %llu meta prealloc %llu meta pertrans %llu", + btrfs_qgroup_level(qgroup->qgroupid), + btrfs_qgroup_subvolid(qgroup->qgroupid), + qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA], + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC], + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]); + + } /* * The same for rfer/excl numbers, but that's only if our qgroup is * consistent and if it's in regular qgroup mode. @@ -1850,8 +1841,9 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) */ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL && !(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT)) { - if (WARN_ON(qgroup->rfer || qgroup->excl || - qgroup->rfer_cmpr || qgroup->excl_cmpr)) { + if (qgroup->rfer || qgroup->excl || + qgroup->rfer_cmpr || qgroup->excl_cmpr) { + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); btrfs_warn_rl(fs_info, "to be deleted qgroup %u/%llu has non-zero numbers, rfer %llu rfer_cmpr %llu excl %llu excl_cmpr %llu", btrfs_qgroup_level(qgroup->qgroupid), diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index 9ffc79f250fb..1834011ccc49 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -13,12 +13,13 @@ #include "volumes.h" #include "print-tree.h" -static void btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans, +static int btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_path *path, const struct btrfs_key *oldkey, u64 newlen, u64 frontpad) { - struct btrfs_stripe_extent *extent; + struct btrfs_root *stripe_root = trans->fs_info->stripe_root; + struct btrfs_stripe_extent *extent, *newitem; struct extent_buffer *leaf; int slot; size_t item_size; @@ -27,23 +28,39 @@ static void btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans, .type = BTRFS_RAID_STRIPE_KEY, .offset = newlen, }; + int ret; + ASSERT(newlen > 0); ASSERT(oldkey->type == BTRFS_RAID_STRIPE_KEY); leaf = path->nodes[0]; slot = path->slots[0]; item_size = btrfs_item_size(leaf, slot); + + newitem = kzalloc(item_size, GFP_NOFS); + if (!newitem) + return -ENOMEM; + extent = btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent); for (int i = 0; i < btrfs_num_raid_stripes(item_size); i++) { struct btrfs_raid_stride *stride = &extent->strides[i]; u64 phys; - phys = btrfs_raid_stride_physical(leaf, stride); - btrfs_set_raid_stride_physical(leaf, stride, phys + frontpad); + phys = btrfs_raid_stride_physical(leaf, stride) + frontpad; + btrfs_set_stack_raid_stride_physical(&newitem->strides[i], phys); } - btrfs_set_item_key_safe(trans, path, &newkey); + ret = btrfs_del_item(trans, stripe_root, path); + if (ret) + goto out; + + btrfs_release_path(path); + ret = btrfs_insert_item(trans, stripe_root, &newkey, newitem, item_size); + +out: + kfree(newitem); + return ret; } int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 length) @@ -59,9 +76,22 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le int slot; int ret; - if (!stripe_root) + if (!btrfs_fs_incompat(fs_info, RAID_STRIPE_TREE) || !stripe_root) return 0; + if (!btrfs_is_testing(fs_info)) { + struct btrfs_chunk_map *map; + bool use_rst; + + map = btrfs_find_chunk_map(fs_info, start, length); + if (!map) + return -EINVAL; + use_rst = btrfs_need_stripe_tree_update(fs_info, map->type); + btrfs_free_chunk_map(map); + if (!use_rst) + return 0; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -85,6 +115,37 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le found_end = found_start + key.offset; ret = 0; + /* + * The stripe extent starts before the range we want to delete, + * but the range spans more than one stripe extent: + * + * |--- RAID Stripe Extent ---||--- RAID Stripe Extent ---| + * |--- keep ---|--- drop ---| + * + * This means we have to get the previous item, truncate its + * length and then restart the search. + */ + if (found_start > start) { + if (slot == 0) { + ret = btrfs_previous_item(stripe_root, path, start, + BTRFS_RAID_STRIPE_KEY); + if (ret) { + if (ret > 0) + ret = -ENOENT; + break; + } + } else { + path->slots[0]--; + } + + leaf = path->nodes[0]; + slot = path->slots[0]; + btrfs_item_key_to_cpu(leaf, &key, slot); + found_start = key.objectid; + found_end = found_start + key.offset; + ASSERT(found_start <= start); + } + if (key.type != BTRFS_RAID_STRIPE_KEY) break; @@ -95,6 +156,54 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le trace_btrfs_raid_extent_delete(fs_info, start, end, found_start, found_end); + /* + * The stripe extent starts before the range we want to delete + * and ends after the range we want to delete, i.e. we're + * punching a hole in the stripe extent: + * + * |--- RAID Stripe Extent ---| + * | keep |--- drop ---| keep | + * + * This means we need to a) truncate the existing item and b) + * create a second item for the remaining range. + */ + if (found_start < start && found_end > end) { + size_t item_size; + u64 diff_start = start - found_start; + u64 diff_end = found_end - end; + struct btrfs_stripe_extent *extent; + struct btrfs_key newkey = { + .objectid = end, + .type = BTRFS_RAID_STRIPE_KEY, + .offset = diff_end, + }; + + /* The "right" item. */ + ret = btrfs_duplicate_item(trans, stripe_root, path, &newkey); + if (ret) + break; + + item_size = btrfs_item_size(leaf, path->slots[0]); + extent = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_stripe_extent); + + for (int i = 0; i < btrfs_num_raid_stripes(item_size); i++) { + struct btrfs_raid_stride *stride = &extent->strides[i]; + u64 phys; + + phys = btrfs_raid_stride_physical(leaf, stride); + phys += diff_start + length; + btrfs_set_raid_stride_physical(leaf, stride, phys); + } + + /* The "left" item. */ + path->slots[0]--; + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); + btrfs_partially_delete_raid_extent(trans, path, &key, + diff_start, 0); + break; + } + /* * The stripe extent starts before the range we want to delete: * @@ -105,11 +214,18 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le * length to the new size and then re-insert the item. */ if (found_start < start) { - u64 diff = start - found_start; + u64 diff_start = start - found_start; btrfs_partially_delete_raid_extent(trans, path, &key, - diff, 0); - break; + diff_start, 0); + + start += (key.offset - diff_start); + length -= (key.offset - diff_start); + if (length == 0) + break; + + btrfs_release_path(path); + continue; } /* @@ -122,13 +238,16 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le * length to the new size and then re-insert the item. */ if (found_end > end) { - u64 diff = found_end - end; + u64 diff_end = found_end - end; btrfs_partially_delete_raid_extent(trans, path, &key, - diff, diff); + key.offset - length, + length); + ASSERT(key.offset - diff_end == length); break; } + /* Finally we can delete the whole item, no more special cases. */ ret = btrfs_del_item(trans, stripe_root, path); if (ret) break; @@ -169,7 +288,6 @@ static int update_raid_extent_item(struct btrfs_trans_handle *trans, write_extent_buffer(leaf, stripe_extent, btrfs_item_ptr_offset(leaf, slot), item_size); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_free_path(path); return ret; @@ -199,12 +317,8 @@ int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, for (int i = 0; i < num_stripes; i++) { u64 devid = bioc->stripes[i].dev->devid; u64 physical = bioc->stripes[i].physical; - u64 length = bioc->stripes[i].length; struct btrfs_raid_stride *raid_stride = &stripe_extent->strides[i]; - if (length == 0) - length = bioc->size; - btrfs_set_stack_raid_stride_devid(raid_stride, devid); btrfs_set_stack_raid_stride_physical(raid_stride, physical); } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index bf267bdfa8f8..af0969b70b53 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -342,12 +342,6 @@ static bool handle_useless_nodes(struct reloc_control *rc, if (cur == node) ret = true; - /* The node is the lowest node */ - if (cur->lowest) { - list_del_init(&cur->lower); - cur->lowest = 0; - } - /* Cleanup the lower edges */ while (!list_empty(&cur->lower)) { struct btrfs_backref_edge *edge; @@ -373,7 +367,6 @@ static bool handle_useless_nodes(struct reloc_control *rc, * cache to avoid unnecessary backref lookup. */ if (cur->level > 0) { - list_add(&cur->list, &cache->detached); cur->detached = 1; } else { rb_erase(&cur->rb_node, &cache->rb_root); @@ -426,7 +419,6 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree( goto out; } - node->lowest = 1; cur = node; /* Breadth-first search to build backref cache */ @@ -469,92 +461,6 @@ out: return node; } -/* - * helper to add backref node for the newly created snapshot. - * the backref node is created by cloning backref node that - * corresponds to root of source tree - */ -static int clone_backref_node(struct btrfs_trans_handle *trans, - struct reloc_control *rc, - const struct btrfs_root *src, - struct btrfs_root *dest) -{ - struct btrfs_root *reloc_root = src->reloc_root; - struct btrfs_backref_cache *cache = &rc->backref_cache; - struct btrfs_backref_node *node = NULL; - struct btrfs_backref_node *new_node; - struct btrfs_backref_edge *edge; - struct btrfs_backref_edge *new_edge; - struct rb_node *rb_node; - - rb_node = rb_simple_search(&cache->rb_root, src->commit_root->start); - if (rb_node) { - node = rb_entry(rb_node, struct btrfs_backref_node, rb_node); - if (node->detached) - node = NULL; - else - BUG_ON(node->new_bytenr != reloc_root->node->start); - } - - if (!node) { - rb_node = rb_simple_search(&cache->rb_root, - reloc_root->commit_root->start); - if (rb_node) { - node = rb_entry(rb_node, struct btrfs_backref_node, - rb_node); - BUG_ON(node->detached); - } - } - - if (!node) - return 0; - - new_node = btrfs_backref_alloc_node(cache, dest->node->start, - node->level); - if (!new_node) - return -ENOMEM; - - new_node->lowest = node->lowest; - new_node->checked = 1; - new_node->root = btrfs_grab_root(dest); - ASSERT(new_node->root); - - if (!node->lowest) { - list_for_each_entry(edge, &node->lower, list[UPPER]) { - new_edge = btrfs_backref_alloc_edge(cache); - if (!new_edge) - goto fail; - - btrfs_backref_link_edge(new_edge, edge->node[LOWER], - new_node, LINK_UPPER); - } - } else { - list_add_tail(&new_node->lower, &cache->leaves); - } - - rb_node = rb_simple_insert(&cache->rb_root, new_node->bytenr, - &new_node->rb_node); - if (rb_node) - btrfs_backref_panic(trans->fs_info, new_node->bytenr, -EEXIST); - - if (!new_node->lowest) { - list_for_each_entry(new_edge, &new_node->lower, list[UPPER]) { - list_add_tail(&new_edge->list[LOWER], - &new_edge->node[LOWER]->upper); - } - } - return 0; -fail: - while (!list_empty(&new_node->lower)) { - new_edge = list_entry(new_node->lower.next, - struct btrfs_backref_edge, list[UPPER]); - list_del(&new_edge->list[UPPER]); - btrfs_backref_free_edge(cache, new_edge); - } - btrfs_backref_free_node(cache, new_node); - return -ENOMEM; -} - /* * helper to add 'address of tree root -> reloc tree' mapping */ @@ -950,7 +856,6 @@ int replace_file_extents(struct btrfs_trans_handle *trans, u32 i; int ret = 0; int first = 1; - int dirty = 0; if (rc->stage != UPDATE_DATA_PTRS) return 0; @@ -1030,7 +935,6 @@ int replace_file_extents(struct btrfs_trans_handle *trans, } btrfs_set_file_extent_disk_bytenr(leaf, fi, new_bytenr); - dirty = 1; key.offset -= btrfs_file_extent_offset(leaf, fi); ref.action = BTRFS_ADD_DELAYED_REF; @@ -1061,8 +965,6 @@ int replace_file_extents(struct btrfs_trans_handle *trans, break; } } - if (dirty) - btrfs_mark_buffer_dirty(trans, leaf); if (inode) btrfs_add_delayed_iput(inode); return ret; @@ -1255,13 +1157,11 @@ again: */ btrfs_set_node_blockptr(parent, slot, new_bytenr); btrfs_set_node_ptr_generation(parent, slot, new_ptr_gen); - btrfs_mark_buffer_dirty(trans, parent); btrfs_set_node_blockptr(path->nodes[level], path->slots[level], old_bytenr); btrfs_set_node_ptr_generation(path->nodes[level], path->slots[level], old_ptr_gen); - btrfs_mark_buffer_dirty(trans, path->nodes[level]); ref.action = BTRFS_ADD_DELAYED_REF; ref.bytenr = old_bytenr; @@ -2058,100 +1958,72 @@ struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans, int index = 0; int ret; - next = node; - while (1) { - cond_resched(); - next = walk_up_backref(next, edges, &index); - root = next->root; + next = walk_up_backref(node, edges, &index); + root = next->root; - /* - * If there is no root, then our references for this block are - * incomplete, as we should be able to walk all the way up to a - * block that is owned by a root. - * - * This path is only for SHAREABLE roots, so if we come upon a - * non-SHAREABLE root then we have backrefs that resolve - * improperly. - * - * Both of these cases indicate file system corruption, or a bug - * in the backref walking code. - */ - if (!root) { - ASSERT(0); - btrfs_err(trans->fs_info, - "bytenr %llu doesn't have a backref path ending in a root", - node->bytenr); - return ERR_PTR(-EUCLEAN); - } - if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) { - ASSERT(0); - btrfs_err(trans->fs_info, - "bytenr %llu has multiple refs with one ending in a non-shareable root", - node->bytenr); - return ERR_PTR(-EUCLEAN); - } + /* + * If there is no root, then our references for this block are + * incomplete, as we should be able to walk all the way up to a block + * that is owned by a root. + * + * This path is only for SHAREABLE roots, so if we come upon a + * non-SHAREABLE root then we have backrefs that resolve improperly. + * + * Both of these cases indicate file system corruption, or a bug in the + * backref walking code. + */ + if (unlikely(!root)) { + btrfs_err(trans->fs_info, + "bytenr %llu doesn't have a backref path ending in a root", + node->bytenr); + return ERR_PTR(-EUCLEAN); + } + if (unlikely(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))) { + btrfs_err(trans->fs_info, + "bytenr %llu has multiple refs with one ending in a non-shareable root", + node->bytenr); + return ERR_PTR(-EUCLEAN); + } - if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) { - ret = record_reloc_root_in_trans(trans, root); - if (ret) - return ERR_PTR(ret); - break; - } - - ret = btrfs_record_root_in_trans(trans, root); + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) { + ret = record_reloc_root_in_trans(trans, root); if (ret) return ERR_PTR(ret); - root = root->reloc_root; - - /* - * We could have raced with another thread which failed, so - * root->reloc_root may not be set, return ENOENT in this case. - */ - if (!root) - return ERR_PTR(-ENOENT); - - if (next->new_bytenr != root->node->start) { - /* - * We just created the reloc root, so we shouldn't have - * ->new_bytenr set and this shouldn't be in the changed - * list. If it is then we have multiple roots pointing - * at the same bytenr which indicates corruption, or - * we've made a mistake in the backref walking code. - */ - ASSERT(next->new_bytenr == 0); - ASSERT(list_empty(&next->list)); - if (next->new_bytenr || !list_empty(&next->list)) { - btrfs_err(trans->fs_info, - "bytenr %llu possibly has multiple roots pointing at the same bytenr %llu", - node->bytenr, next->bytenr); - return ERR_PTR(-EUCLEAN); - } - - next->new_bytenr = root->node->start; - btrfs_put_root(next->root); - next->root = btrfs_grab_root(root); - ASSERT(next->root); - list_add_tail(&next->list, - &rc->backref_cache.changed); - mark_block_processed(rc, next); - break; - } - - WARN_ON(1); - root = NULL; - next = walk_down_backref(edges, &index); - if (!next || next->level <= node->level) - break; + goto found; } - if (!root) { - /* - * This can happen if there's fs corruption or if there's a bug - * in the backref lookup code. - */ - ASSERT(0); + + ret = btrfs_record_root_in_trans(trans, root); + if (ret) + return ERR_PTR(ret); + root = root->reloc_root; + + /* + * We could have raced with another thread which failed, so + * root->reloc_root may not be set, return ENOENT in this case. + */ + if (!root) return ERR_PTR(-ENOENT); + + if (next->new_bytenr) { + /* + * We just created the reloc root, so we shouldn't have + * ->new_bytenr set yet. If it is then we have multiple roots + * pointing at the same bytenr which indicates corruption, or + * we've made a mistake in the backref walking code. + */ + ASSERT(next->new_bytenr == 0); + btrfs_err(trans->fs_info, + "bytenr %llu possibly has multiple roots pointing at the same bytenr %llu", + node->bytenr, next->bytenr); + return ERR_PTR(-EUCLEAN); } + next->new_bytenr = root->node->start; + btrfs_put_root(next->root); + next->root = btrfs_grab_root(root); + ASSERT(next->root); + mark_block_processed(rc, next); +found: next = node; /* setup backref node path for btrfs_reloc_cow_block */ while (1) { @@ -2247,17 +2119,11 @@ static noinline_for_stack u64 calcu_metadata_size(struct reloc_control *rc, return num_bytes; } -static int reserve_metadata_space(struct btrfs_trans_handle *trans, - struct reloc_control *rc, - struct btrfs_backref_node *node) +static int refill_metadata_space(struct btrfs_trans_handle *trans, + struct reloc_control *rc, u64 num_bytes) { - struct btrfs_root *root = rc->extent_root; - struct btrfs_fs_info *fs_info = root->fs_info; - u64 num_bytes; + struct btrfs_fs_info *fs_info = trans->fs_info; int ret; - u64 tmp; - - num_bytes = calcu_metadata_size(rc, node) * 2; trans->block_rsv = rc->block_rsv; rc->reserved_bytes += num_bytes; @@ -2270,7 +2136,8 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans, ret = btrfs_block_rsv_refill(fs_info, rc->block_rsv, num_bytes, BTRFS_RESERVE_FLUSH_LIMIT); if (ret) { - tmp = fs_info->nodesize * RELOCATION_RESERVED_NODES; + u64 tmp = fs_info->nodesize * RELOCATION_RESERVED_NODES; + while (tmp <= rc->reserved_bytes) tmp <<= 1; /* @@ -2288,6 +2155,16 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans, return 0; } +static int reserve_metadata_space(struct btrfs_trans_handle *trans, + struct reloc_control *rc, + struct btrfs_backref_node *node) +{ + u64 num_bytes; + + num_bytes = calcu_metadata_size(rc, node) * 2; + return refill_metadata_space(trans, rc, num_bytes); +} + /* * relocate a block tree, and then update pointers in upper level * blocks that reference the block to point to the new location. @@ -2442,7 +2319,7 @@ next: if (!ret && node->pending) { btrfs_backref_drop_node_buffer(node); - list_move_tail(&node->list, &rc->backref_cache.changed); + list_del_init(&node->list); node->pending = 0; } @@ -2605,8 +2482,7 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans, /* * This block was the root block of a root, and this is * the first time we're processing the block and thus it - * should not have had the ->new_bytenr modified and - * should have not been included on the changed list. + * should not have had the ->new_bytenr modified. * * However in the case of corruption we could have * multiple refs pointing to the same block improperly, @@ -2616,8 +2492,7 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans, * normal user in the case of corruption. */ ASSERT(node->new_bytenr == 0); - ASSERT(list_empty(&node->list)); - if (node->new_bytenr || !list_empty(&node->list)) { + if (node->new_bytenr) { btrfs_err(root->fs_info, "bytenr %llu has improper references to it", node->bytenr); @@ -2640,17 +2515,12 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans, btrfs_put_root(node->root); node->root = btrfs_grab_root(root); ASSERT(node->root); - list_add_tail(&node->list, &rc->backref_cache.changed); } else { - path->lowest_level = node->level; - if (root == root->fs_info->chunk_root) - btrfs_reserve_chunk_metadata(trans, false); - ret = btrfs_search_slot(trans, root, key, path, 0, 1); - btrfs_release_path(path); - if (root == root->fs_info->chunk_root) - btrfs_trans_release_chunk_metadata(trans); - if (ret > 0) - ret = 0; + btrfs_err(root->fs_info, + "bytenr %llu resolved to a non-shareable root", + node->bytenr); + ret = -EUCLEAN; + goto out; } if (!ret) update_processed_blocks(rc, node); @@ -2658,11 +2528,50 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans, ret = do_relocation(trans, rc, node, key, path, 1); } out: - if (ret || node->level == 0 || node->cowonly) + if (ret || node->level == 0) btrfs_backref_cleanup_node(&rc->backref_cache, node); return ret; } +static int relocate_cowonly_block(struct btrfs_trans_handle *trans, + struct reloc_control *rc, struct tree_block *block, + struct btrfs_path *path) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_root *root; + u64 num_bytes; + int nr_levels; + int ret; + + root = btrfs_get_fs_root(fs_info, block->owner, true); + if (IS_ERR(root)) + return PTR_ERR(root); + + nr_levels = max(btrfs_header_level(root->node) - block->level, 0) + 1; + + num_bytes = fs_info->nodesize * nr_levels; + ret = refill_metadata_space(trans, rc, num_bytes); + if (ret) { + btrfs_put_root(root); + return ret; + } + path->lowest_level = block->level; + if (root == root->fs_info->chunk_root) + btrfs_reserve_chunk_metadata(trans, false); + + ret = btrfs_search_slot(trans, root, &block->key, path, 0, 1); + path->lowest_level = 0; + btrfs_release_path(path); + + if (root == root->fs_info->chunk_root) + btrfs_trans_release_chunk_metadata(trans); + if (ret > 0) + ret = 0; + btrfs_put_root(root); + + return ret; +} + /* * relocate a list of blocks */ @@ -2702,6 +2611,20 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, /* Do tree relocation */ rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { + /* + * For COWonly blocks, or the data reloc tree, we only need to + * COW down to the block, there's no need to generate a backref + * tree. + */ + if (block->owner && + (!is_fstree(block->owner) || + block->owner == BTRFS_DATA_RELOC_TREE_OBJECTID)) { + ret = relocate_cowonly_block(trans, rc, block, path); + if (ret) + break; + continue; + } + node = build_backref_tree(trans, rc, &block->key, block->level, block->bytenr); if (IS_ERR(node)) { @@ -2902,6 +2825,7 @@ static int relocate_one_folio(struct reloc_control *rc, const bool use_rst = btrfs_need_stripe_tree_update(fs_info, rc->block_group->flags); ASSERT(index <= last_index); +again: folio = filemap_lock_folio(inode->i_mapping, index); if (IS_ERR(folio)) { @@ -2937,11 +2861,16 @@ static int relocate_one_folio(struct reloc_control *rc, ret = -EIO; goto release_folio; } + if (folio->mapping != inode->i_mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } /* * We could have lost folio private when we dropped the lock to read the - * folio above, make sure we set_page_extent_mapped here so we have any + * folio above, make sure we set_folio_extent_mapped() here so we have any * of the subpage blocksize stuff we need in place. */ ret = set_folio_extent_mapped(folio); @@ -3793,7 +3722,6 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, btrfs_set_inode_mode(leaf, item, S_IFREG | 0600); btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC); - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -4399,8 +4327,18 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, WARN_ON(!first_cow && level == 0); node = rc->backref_cache.path[level]; - BUG_ON(node->bytenr != buf->start && - node->new_bytenr != buf->start); + + /* + * If node->bytenr != buf->start and node->new_bytenr != + * buf->start then we've got the wrong backref node for what we + * expected to see here and the cache is incorrect. + */ + if (unlikely(node->bytenr != buf->start && node->new_bytenr != buf->start)) { + btrfs_err(fs_info, +"bytenr %llu was found but our backref cache was expecting %llu or %llu", + buf->start, node->bytenr, node->new_bytenr); + return -EUCLEAN; + } btrfs_backref_drop_node_buffer(node); atomic_inc(&cow->refs); @@ -4500,10 +4438,7 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans, return ret; } new_root->reloc_root = btrfs_grab_root(reloc_root); - - if (rc->create_reloc_tree) - ret = clone_backref_node(trans, rc, root, reloc_root); - return ret; + return 0; } /* diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 33962671a96c..e22e6b06927a 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -197,7 +197,6 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root btrfs_set_root_generation_v2(item, btrfs_root_generation(item)); write_extent_buffer(l, item, ptr, sizeof(*item)); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); out: btrfs_free_path(path); return ret; @@ -447,7 +446,6 @@ again: btrfs_set_root_ref_name_len(leaf, ref, name->len); ptr = (unsigned long)(ref + 1); write_extent_buffer(leaf, name->name, ptr, name->len); - btrfs_mark_buffer_dirty(trans, leaf); if (key.type == BTRFS_ROOT_BACKREF_KEY) { btrfs_release_path(path); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 204c928beaf9..531312efee8d 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1541,6 +1541,10 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg, u64 extent_gen; int ret; + if (unlikely(!extent_root)) { + btrfs_err(fs_info, "no valid extent root for scrub"); + return -EUCLEAN; + } memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) * stripe->nr_sectors); scrub_stripe_reset_bitmaps(stripe); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7254279c3cc9..f437138fefbc 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5280,6 +5280,7 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) unsigned cur_len = min_t(unsigned, len, PAGE_SIZE - pg_offset); +again: folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { page_cache_sync_readahead(mapping, @@ -5312,6 +5313,11 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) ret = -EIO; break; } + if (folio->mapping != mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } memcpy_from_folio(sctx->send_buf + sctx->send_size, folio, @@ -7253,7 +7259,7 @@ static int changed_cb(struct btrfs_path *left_path, enum btrfs_compare_tree_result result, struct send_ctx *sctx) { - int ret = 0; + int ret; /* * We can not hold the commit root semaphore here. This is because in @@ -7313,7 +7319,6 @@ static int changed_cb(struct btrfs_path *left_path, return 0; } result = BTRFS_COMPARE_TREE_CHANGED; - ret = 0; } sctx->left_path = left_path; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 255e85f78313..a341d087567a 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -14,6 +14,7 @@ #include "fs.h" #include "accessors.h" #include "extent-tree.h" +#include "zoned.h" /* * HOW DOES SPACE RESERVATION WORK @@ -127,6 +128,14 @@ * churn a lot and we can avoid making some extent tree modifications if we * are able to delay for as long as possible. * + * RESET_ZONES + * This state works only for the zoned mode. On the zoned mode, we cannot + * reuse once allocated then freed region until we reset the zone, due to + * the sequential write zone requirement. The RESET_ZONES state resets the + * zones of an unused block group and let us reuse the space. The reusing + * is faster than removing the block group and allocating another block + * group on the zones. + * * ALLOC_CHUNK * We will skip this the first time through space reservation, because of * overcommit and we don't want to have a lot of useless metadata space when @@ -316,7 +325,7 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, found->bytes_used += block_group->used; found->disk_used += block_group->used * factor; found->bytes_readonly += block_group->bytes_super; - btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable); + btrfs_space_info_update_bytes_zone_unusable(found, block_group->zone_unusable); if (block_group->length > 0) found->full = 0; btrfs_try_granting_tickets(info, found); @@ -489,9 +498,7 @@ again: if ((used + ticket->bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, ticket->bytes, flush)) { - btrfs_space_info_update_bytes_may_use(fs_info, - space_info, - ticket->bytes); + btrfs_space_info_update_bytes_may_use(space_info, ticket->bytes); remove_ticket(space_info, ticket); ticket->bytes = 0; space_info->tickets_id++; @@ -834,6 +841,9 @@ static void flush_space(struct btrfs_fs_info *fs_info, */ ret = btrfs_commit_current_transaction(root); break; + case RESET_ZONES: + ret = btrfs_reset_unused_block_groups(space_info, num_bytes); + break; default: ret = -ENOSPC; break; @@ -1086,9 +1096,14 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) enum btrfs_flush_state flush_state; int commit_cycles = 0; u64 last_tickets_id; + enum btrfs_flush_state final_state; fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work); space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); + if (btrfs_is_zoned(fs_info)) + final_state = RESET_ZONES; + else + final_state = COMMIT_TRANS; spin_lock(&space_info->lock); to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info); @@ -1141,7 +1156,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) if (flush_state == ALLOC_CHUNK_FORCE && !commit_cycles) flush_state++; - if (flush_state > COMMIT_TRANS) { + if (flush_state > final_state) { commit_cycles++; if (commit_cycles > 2) { if (maybe_fail_all_tickets(fs_info, space_info)) { @@ -1155,7 +1170,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) } } spin_unlock(&space_info->lock); - } while (flush_state <= COMMIT_TRANS); + } while (flush_state <= final_state); } /* @@ -1286,6 +1301,10 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) * This is where we reclaim all of the pinned space generated by running the * iputs * + * RESET_ZONES + * This state works only for the zoned mode. We scan the unused block group + * list and reset the zones and reuse the block group. + * * ALLOC_CHUNK_FORCE * For data we start with alloc chunk force, however we could have been full * before, and then the transaction commit could have freed new block groups, @@ -1295,6 +1314,7 @@ static const enum btrfs_flush_state data_flush_states[] = { FLUSH_DELALLOC_FULL, RUN_DELAYED_IPUTS, COMMIT_TRANS, + RESET_ZONES, ALLOC_CHUNK_FORCE, }; @@ -1386,6 +1406,7 @@ void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info) static const enum btrfs_flush_state priority_flush_states[] = { FLUSH_DELAYED_ITEMS_NR, FLUSH_DELAYED_ITEMS, + RESET_ZONES, ALLOC_CHUNK, }; @@ -1399,6 +1420,7 @@ static const enum btrfs_flush_state evict_flush_states[] = { FLUSH_DELALLOC_FULL, ALLOC_CHUNK, COMMIT_TRANS, + RESET_ZONES, }; static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, @@ -1690,8 +1712,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, if (!pending_tickets && ((used + orig_bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) { - btrfs_space_info_update_bytes_may_use(fs_info, space_info, - orig_bytes); + btrfs_space_info_update_bytes_may_use(space_info, orig_bytes); ret = 0; } @@ -1703,8 +1724,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, if (ret && unlikely(flush == BTRFS_RESERVE_FLUSH_EMERGENCY)) { used = btrfs_space_info_used(space_info, false); if (used + orig_bytes <= space_info->total_bytes) { - btrfs_space_info_update_bytes_may_use(fs_info, space_info, - orig_bytes); + btrfs_space_info_update_bytes_may_use(space_info, orig_bytes); ret = 0; } } @@ -2082,3 +2102,32 @@ void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info) do_reclaim_sweep(space_info, raid); } } + +void btrfs_return_free_space(struct btrfs_space_info *space_info, u64 len) +{ + struct btrfs_fs_info *fs_info = space_info->fs_info; + struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; + + lockdep_assert_held(&space_info->lock); + + /* Prioritize the global reservation to receive the freed space. */ + if (global_rsv->space_info != space_info) + goto grant; + + spin_lock(&global_rsv->lock); + if (!global_rsv->full) { + u64 to_add = min(len, global_rsv->size - global_rsv->reserved); + + global_rsv->reserved += to_add; + btrfs_space_info_update_bytes_may_use(space_info, to_add); + if (global_rsv->reserved >= global_rsv->size) + global_rsv->full = 1; + len -= to_add; + } + spin_unlock(&global_rsv->lock); + +grant: + /* Add to any tickets we may have. */ + if (len) + btrfs_try_granting_tickets(fs_info, space_info); +} diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index efbecc0c5258..a96efdb5e681 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -79,6 +79,10 @@ enum btrfs_reserve_flush_enum { BTRFS_RESERVE_FLUSH_EMERGENCY, }; +/* + * Please be aware that the order of enum values will be the order of the reclaim + * process in btrfs_async_reclaim_metadata_space(). + */ enum btrfs_flush_state { FLUSH_DELAYED_ITEMS_NR = 1, FLUSH_DELAYED_ITEMS = 2, @@ -91,6 +95,7 @@ enum btrfs_flush_state { ALLOC_CHUNK_FORCE = 9, RUN_DELAYED_IPUTS = 10, COMMIT_TRANS = 11, + RESET_ZONES = 12, }; struct btrfs_space_info { @@ -229,10 +234,10 @@ static inline bool btrfs_mixed_space_info(const struct btrfs_space_info *space_i */ #define DECLARE_SPACE_INFO_UPDATE(name, trace_name) \ static inline void \ -btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \ - struct btrfs_space_info *sinfo, \ +btrfs_space_info_update_##name(struct btrfs_space_info *sinfo, \ s64 bytes) \ { \ + struct btrfs_fs_info *fs_info = sinfo->fs_info; \ const u64 abs_bytes = (bytes < 0) ? -bytes : bytes; \ lockdep_assert_held(&sinfo->lock); \ trace_update_##name(fs_info, sinfo, sinfo->name, bytes); \ @@ -275,13 +280,12 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, enum btrfs_reserve_flush_enum flush); static inline void btrfs_space_info_free_bytes_may_use( - struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes) { spin_lock(&space_info->lock); - btrfs_space_info_update_bytes_may_use(fs_info, space_info, -num_bytes); - btrfs_try_granting_tickets(fs_info, space_info); + btrfs_space_info_update_bytes_may_use(space_info, -num_bytes); + btrfs_try_granting_tickets(space_info->fs_info, space_info); spin_unlock(&space_info->lock); } int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, @@ -295,5 +299,6 @@ void btrfs_set_periodic_reclaim_ready(struct btrfs_space_info *space_info, bool bool btrfs_should_periodic_reclaim(struct btrfs_space_info *space_info); int btrfs_calc_reclaim_threshold(const struct btrfs_space_info *space_info); void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info); +void btrfs_return_free_space(struct btrfs_space_info *space_info, u64 len); #endif /* BTRFS_SPACE_INFO_H */ diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index 8c68059ac1b0..722acf768396 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -635,6 +635,28 @@ IMPLEMENT_BTRFS_PAGE_OPS(ordered, folio_set_ordered, folio_clear_ordered, IMPLEMENT_BTRFS_PAGE_OPS(checked, folio_set_checked, folio_clear_checked, folio_test_checked); +#define GET_SUBPAGE_BITMAP(subpage, fs_info, name, dst) \ +{ \ + const int sectors_per_page = fs_info->sectors_per_page; \ + \ + ASSERT(sectors_per_page < BITS_PER_LONG); \ + *dst = bitmap_read(subpage->bitmaps, \ + sectors_per_page * btrfs_bitmap_nr_##name, \ + sectors_per_page); \ +} + +#define SUBPAGE_DUMP_BITMAP(fs_info, folio, name, start, len) \ +{ \ + const struct btrfs_subpage *subpage = folio_get_private(folio); \ + unsigned long bitmap; \ + \ + GET_SUBPAGE_BITMAP(subpage, fs_info, name, &bitmap); \ + btrfs_warn(fs_info, \ + "dumpping bitmap start=%llu len=%u folio=%llu " #name "_bitmap=%*pbl", \ + start, len, folio_pos(folio), \ + fs_info->sectors_per_page, &bitmap); \ +} + /* * Make sure not only the page dirty bit is cleared, but also subpage dirty bit * is cleared. @@ -660,6 +682,10 @@ void btrfs_folio_assert_not_dirty(const struct btrfs_fs_info *fs_info, subpage = folio_get_private(folio); ASSERT(subpage); spin_lock_irqsave(&subpage->lock, flags); + if (unlikely(!bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits))) { + SUBPAGE_DUMP_BITMAP(fs_info, folio, dirty, start, len); + ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); + } ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); spin_unlock_irqrestore(&subpage->lock, flags); } @@ -689,23 +715,16 @@ void btrfs_folio_set_lock(const struct btrfs_fs_info *fs_info, nbits = len >> fs_info->sectorsize_bits; spin_lock_irqsave(&subpage->lock, flags); /* Target range should not yet be locked. */ - ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); + if (unlikely(!bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits))) { + SUBPAGE_DUMP_BITMAP(fs_info, folio, locked, start, len); + ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); + } bitmap_set(subpage->bitmaps, start_bit, nbits); ret = atomic_add_return(nbits, &subpage->nr_locked); ASSERT(ret <= fs_info->sectors_per_page); spin_unlock_irqrestore(&subpage->lock, flags); } -#define GET_SUBPAGE_BITMAP(subpage, fs_info, name, dst) \ -{ \ - const int sectors_per_page = fs_info->sectors_per_page; \ - \ - ASSERT(sectors_per_page < BITS_PER_LONG); \ - *dst = bitmap_read(subpage->bitmaps, \ - sectors_per_page * btrfs_bitmap_nr_##name, \ - sectors_per_page); \ -} - void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { @@ -716,6 +735,7 @@ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, unsigned long writeback_bitmap; unsigned long ordered_bitmap; unsigned long checked_bitmap; + unsigned long locked_bitmap; unsigned long flags; ASSERT(folio_test_private(folio) && folio_get_private(folio)); @@ -728,15 +748,16 @@ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, GET_SUBPAGE_BITMAP(subpage, fs_info, writeback, &writeback_bitmap); GET_SUBPAGE_BITMAP(subpage, fs_info, ordered, &ordered_bitmap); GET_SUBPAGE_BITMAP(subpage, fs_info, checked, &checked_bitmap); - GET_SUBPAGE_BITMAP(subpage, fs_info, locked, &checked_bitmap); + GET_SUBPAGE_BITMAP(subpage, fs_info, locked, &locked_bitmap); spin_unlock_irqrestore(&subpage->lock, flags); dump_page(folio_page(folio, 0), "btrfs subpage dump"); btrfs_warn(fs_info, -"start=%llu len=%u page=%llu, bitmaps uptodate=%*pbl dirty=%*pbl writeback=%*pbl ordered=%*pbl checked=%*pbl", +"start=%llu len=%u page=%llu, bitmaps uptodate=%*pbl dirty=%*pbl locked=%*pbl writeback=%*pbl ordered=%*pbl checked=%*pbl", start, len, folio_pos(folio), sectors_per_page, &uptodate_bitmap, sectors_per_page, &dirty_bitmap, + sectors_per_page, &locked_bitmap, sectors_per_page, &writeback_bitmap, sectors_per_page, &ordered_bitmap, sectors_per_page, &checked_bitmap); diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h index 428fa9389fd4..44fff1f4eac4 100644 --- a/fs/btrfs/subpage.h +++ b/fs/btrfs/subpage.h @@ -137,6 +137,19 @@ DECLARE_BTRFS_SUBPAGE_OPS(writeback); DECLARE_BTRFS_SUBPAGE_OPS(ordered); DECLARE_BTRFS_SUBPAGE_OPS(checked); +/* + * Helper for error cleanup, where a folio will have its dirty flag cleared, + * with writeback started and finished. + */ +static inline void btrfs_folio_clamp_finish_io(struct btrfs_fs_info *fs_info, + struct folio *locked_folio, + u64 start, u32 len) +{ + btrfs_folio_clamp_clear_dirty(fs_info, locked_folio, start, len); + btrfs_folio_clamp_set_writeback(fs_info, locked_folio, start, len); + btrfs_folio_clamp_clear_writeback(fs_info, locked_folio, start, len); +} + bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 7dfe5005129a..dc4fee519ca6 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -961,7 +961,7 @@ static int btrfs_fill_super(struct super_block *sb, #endif sb->s_xattr = btrfs_xattr_handlers; sb->s_time_gran = 1; - sb->s_iflags |= SB_I_CGROUPWB; + sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM; err = super_setup_bdi(sb); if (err) { @@ -971,7 +971,7 @@ static int btrfs_fill_super(struct super_block *sb, err = open_ctree(sb, fs_devices); if (err) { - btrfs_err(fs_info, "open_ctree failed"); + btrfs_err(fs_info, "open_ctree failed: %d", err); return err; } @@ -2446,6 +2446,9 @@ static __cold void btrfs_interface_exit(void) static int __init btrfs_print_mod_info(void) { static const char options[] = "" +#ifdef CONFIG_BTRFS_EXPERIMENTAL + ", experimental=on" +#endif #ifdef CONFIG_BTRFS_DEBUG ", debug=on" #endif @@ -2466,7 +2469,17 @@ static int __init btrfs_print_mod_info(void) ", fsverity=no" #endif ; + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + if (btrfs_get_mod_read_policy() == NULL) + pr_info("Btrfs loaded%s\n", options); + else + pr_info("Btrfs loaded%s, read_policy=%s\n", + options, btrfs_get_mod_read_policy()); +#else pr_info("Btrfs loaded%s\n", options); +#endif + return 0; } @@ -2524,6 +2537,11 @@ static const struct init_sequence mod_init_seq[] = { }, { .init_func = extent_map_init, .exit_func = extent_map_exit, +#ifdef CONFIG_BTRFS_EXPERIMENTAL + }, { + .init_func = btrfs_read_policy_init, + .exit_func = NULL, +#endif }, { .init_func = ordered_data_init, .exit_func = ordered_data_exit, diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index fdcbf650ac31..53b846d99ece 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1118,7 +1118,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->nodesize); + return sysfs_emit(buf, "%u\n", fs_info->nodesize); } BTRFS_ATTR(, nodesize, btrfs_nodesize_show); @@ -1128,7 +1128,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show); @@ -1180,7 +1180,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show); @@ -1305,7 +1305,73 @@ static ssize_t btrfs_temp_fsid_show(struct kobject *kobj, } BTRFS_ATTR(, temp_fsid, btrfs_temp_fsid_show); -static const char * const btrfs_read_policy_name[] = { "pid" }; +static const char *btrfs_read_policy_name[] = { + "pid", +#ifdef CONFIG_BTRFS_EXPERIMENTAL + "round-robin", + "devid", +#endif +}; + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + +/* Global module configuration parameters. */ +static char *read_policy; +char *btrfs_get_mod_read_policy(void) +{ + return read_policy; +} + +/* Set perms to 0, disable /sys/module/btrfs/parameter/read_policy interface. */ +module_param(read_policy, charp, 0); +MODULE_PARM_DESC(read_policy, +"Global read policy: pid (default), round-robin[:], devid[:]"); +#endif + +int btrfs_read_policy_to_enum(const char *str, s64 *value_ret) +{ + char param[32] = { 0 }; + char __maybe_unused *value_str; + + if (!str || strlen(str) == 0) + return 0; + + strncpy(param, str, sizeof(param) - 1); + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + /* Separate value from input in policy:value format. */ + value_str = strchr(param, ':'); + if (value_str) { + int ret; + + *value_str = 0; + value_str++; + if (!value_ret) + return -EINVAL; + ret = kstrtos64(value_str, 10, value_ret); + if (ret) + return -EINVAL; + if (*value_ret < 0) + return -ERANGE; + } +#endif + + return sysfs_match_string(btrfs_read_policy_name, param); +} + +#ifdef CONFIG_BTRFS_EXPERIMENTAL +int __init btrfs_read_policy_init(void) +{ + s64 value; + + if (btrfs_read_policy_to_enum(read_policy, &value) == -EINVAL) { + btrfs_err(NULL, "invalid read policy or value %s", read_policy); + return -EINVAL; + } + + return 0; +} +#endif static ssize_t btrfs_read_policy_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) @@ -1316,14 +1382,25 @@ static ssize_t btrfs_read_policy_show(struct kobject *kobj, int i; for (i = 0; i < BTRFS_NR_READ_POLICY; i++) { - if (policy == i) - ret += sysfs_emit_at(buf, ret, "%s[%s]", - (ret == 0 ? "" : " "), - btrfs_read_policy_name[i]); - else - ret += sysfs_emit_at(buf, ret, "%s%s", - (ret == 0 ? "" : " "), - btrfs_read_policy_name[i]); + if (ret != 0) + ret += sysfs_emit_at(buf, ret, " "); + + if (i == policy) + ret += sysfs_emit_at(buf, ret, "["); + + ret += sysfs_emit_at(buf, ret, "%s", btrfs_read_policy_name[i]); + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + if (i == BTRFS_READ_POLICY_RR) + ret += sysfs_emit_at(buf, ret, ":%u", + READ_ONCE(fs_devices->rr_min_contig_read)); + + if (i == BTRFS_READ_POLICY_DEVID) + ret += sysfs_emit_at(buf, ret, ":%llu", + READ_ONCE(fs_devices->read_devid)); +#endif + if (i == policy) + ret += sysfs_emit_at(buf, ret, "]"); } ret += sysfs_emit_at(buf, ret, "\n"); @@ -1336,21 +1413,80 @@ static ssize_t btrfs_read_policy_store(struct kobject *kobj, const char *buf, size_t len) { struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj); - int i; + int index; + s64 value = -1; - for (i = 0; i < BTRFS_NR_READ_POLICY; i++) { - if (sysfs_streq(buf, btrfs_read_policy_name[i])) { - if (i != READ_ONCE(fs_devices->read_policy)) { - WRITE_ONCE(fs_devices->read_policy, i); - btrfs_info(fs_devices->fs_info, - "read policy set to '%s'", - btrfs_read_policy_name[i]); + index = btrfs_read_policy_to_enum(buf, &value); + if (index < 0) + return -EINVAL; + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + /* If moving from RR then disable collecting fs stats. */ + if (fs_devices->read_policy == BTRFS_READ_POLICY_RR && index != BTRFS_READ_POLICY_RR) + fs_devices->collect_fs_stats = false; + + if (index == BTRFS_READ_POLICY_RR) { + if (value != -1) { + const u32 sectorsize = fs_devices->fs_info->sectorsize; + + if (!IS_ALIGNED(value, sectorsize)) { + u64 temp_value = round_up(value, sectorsize); + + btrfs_debug(fs_devices->fs_info, +"read_policy: min contig read %lld should be multiple of sectorsize %u, rounded to %llu", + value, sectorsize, temp_value); + value = temp_value; } - return len; + } else { + value = BTRFS_DEFAULT_RR_MIN_CONTIG_READ; } + + if (index != READ_ONCE(fs_devices->read_policy) || + value != READ_ONCE(fs_devices->rr_min_contig_read)) { + WRITE_ONCE(fs_devices->read_policy, index); + WRITE_ONCE(fs_devices->rr_min_contig_read, value); + + btrfs_info(fs_devices->fs_info, "read policy set to '%s:%lld'", + btrfs_read_policy_name[index], value); + } + + fs_devices->collect_fs_stats = true; + + return len; } - return -EINVAL; + if (index == BTRFS_READ_POLICY_DEVID) { + if (value != -1) { + BTRFS_DEV_LOOKUP_ARGS(args); + + /* Validate input devid. */ + args.devid = value; + if (btrfs_find_device(fs_devices, &args) == NULL) + return -EINVAL; + } else { + /* Set default devid to the devid of the latest device. */ + value = fs_devices->latest_dev->devid; + } + + if (index != READ_ONCE(fs_devices->read_policy) || + value != READ_ONCE(fs_devices->read_devid)) { + WRITE_ONCE(fs_devices->read_policy, index); + WRITE_ONCE(fs_devices->read_devid, value); + + btrfs_info(fs_devices->fs_info, "read policy set to '%s:%llu'", + btrfs_read_policy_name[index], value); + } + + return len; + } +#endif + if (index != READ_ONCE(fs_devices->read_policy)) { + WRITE_ONCE(fs_devices->read_policy, index); + btrfs_info(fs_devices->fs_info, "read policy set to '%s'", + btrfs_read_policy_name[index]); + } + + return len; } BTRFS_ATTR_RW(, read_policy, btrfs_read_policy_show, btrfs_read_policy_store); diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index e6a284c59809..3fc5c6f90dc4 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -47,5 +47,11 @@ void btrfs_sysfs_del_qgroups(struct btrfs_fs_info *fs_info); int btrfs_sysfs_add_qgroups(struct btrfs_fs_info *fs_info); void btrfs_sysfs_del_one_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup); +int btrfs_read_policy_to_enum(const char *str, s64 *value); + +#ifdef CONFIG_BTRFS_EXPERIMENTAL +int __init btrfs_read_policy_init(void); +char *btrfs_get_mod_read_policy(void); +#endif #endif diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index e607b5d52fb1..5eff8d7d2360 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -30,6 +30,7 @@ const char *test_error[] = { [TEST_ALLOC_EXTENT_MAP] = "cannot allocate extent map", [TEST_ALLOC_CHUNK_MAP] = "cannot allocate chunk map", [TEST_ALLOC_IO_CONTEXT] = "cannot allocate io context", + [TEST_ALLOC_TRANSACTION] = "cannot allocate transaction", }; static const struct super_operations btrfs_test_super_ops = { @@ -142,6 +143,11 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize) fs_info->nodesize = nodesize; fs_info->sectorsize = sectorsize; fs_info->sectorsize_bits = ilog2(sectorsize); + + /* CRC32C csum size. */ + fs_info->csum_size = 4; + fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / + fs_info->csum_size; set_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state); test_mnt->mnt_sb->s_fs_info = fs_info; @@ -247,6 +253,15 @@ void btrfs_free_dummy_block_group(struct btrfs_block_group *cache) kfree(cache); } +void btrfs_init_dummy_transaction(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info) +{ + memset(trans, 0, sizeof(*trans)); + trans->fs_info = fs_info; + xa_init(&trans->delayed_refs.head_refs); + xa_init(&trans->delayed_refs.dirty_extents); + spin_lock_init(&trans->delayed_refs.lock); +} + void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { @@ -295,6 +310,9 @@ int btrfs_run_sanity_tests(void) ret = btrfs_test_raid_stripe_tree(sectorsize, nodesize); if (ret) goto out; + ret = btrfs_test_delayed_refs(sectorsize, nodesize); + if (ret) + goto out; } } ret = btrfs_test_extent_map(); diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h index b524ecf2f452..4307bdaa6749 100644 --- a/fs/btrfs/tests/btrfs-tests.h +++ b/fs/btrfs/tests/btrfs-tests.h @@ -6,6 +6,8 @@ #ifndef BTRFS_TESTS_H #define BTRFS_TESTS_H +#include + #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int btrfs_run_sanity_tests(void); @@ -25,12 +27,14 @@ enum { TEST_ALLOC_EXTENT_MAP, TEST_ALLOC_CHUNK_MAP, TEST_ALLOC_IO_CONTEXT, + TEST_ALLOC_TRANSACTION, }; extern const char *test_error[]; struct btrfs_root; struct btrfs_trans_handle; +struct btrfs_transaction; int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize); int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize); @@ -40,6 +44,7 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize); int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize); int btrfs_test_raid_stripe_tree(u32 sectorsize, u32 nodesize); int btrfs_test_extent_map(void); +int btrfs_test_delayed_refs(u32 sectorsize, u32 nodesize); struct inode *btrfs_new_test_inode(void); struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize); void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info); @@ -49,6 +54,7 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long lengt void btrfs_free_dummy_block_group(struct btrfs_block_group *cache); void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); +void btrfs_init_dummy_transaction(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info); struct btrfs_device *btrfs_alloc_dummy_device(struct btrfs_fs_info *fs_info); #else static inline int btrfs_run_sanity_tests(void) diff --git a/fs/btrfs/tests/delayed-refs-tests.c b/fs/btrfs/tests/delayed-refs-tests.c new file mode 100644 index 000000000000..6558508c2ddf --- /dev/null +++ b/fs/btrfs/tests/delayed-refs-tests.c @@ -0,0 +1,1015 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include "btrfs-tests.h" +#include "../transaction.h" +#include "../delayed-ref.h" +#include "../extent-tree.h" + +#define FAKE_ROOT_OBJECTID 256 +#define FAKE_BYTENR 0 +#define FAKE_LEVEL 1 +#define FAKE_INO 256 +#define FAKE_FILE_OFFSET 0 +#define FAKE_PARENT SZ_1M + +struct ref_head_check { + u64 bytenr; + u64 num_bytes; + int ref_mod; + int total_ref_mod; + int must_insert; +}; + +struct ref_node_check { + u64 bytenr; + u64 num_bytes; + int ref_mod; + enum btrfs_delayed_ref_action action; + u8 type; + u64 parent; + u64 root; + u64 owner; + u64 offset; +}; + +static enum btrfs_ref_type ref_type_from_disk_ref_type(u8 type) +{ + if ((type == BTRFS_TREE_BLOCK_REF_KEY) || + (type == BTRFS_SHARED_BLOCK_REF_KEY)) + return BTRFS_REF_METADATA; + return BTRFS_REF_DATA; +} + +static void delete_delayed_ref_head(struct btrfs_trans_handle *trans, + struct btrfs_delayed_ref_head *head) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_delayed_ref_root *delayed_refs = + &trans->transaction->delayed_refs; + + spin_lock(&delayed_refs->lock); + spin_lock(&head->lock); + btrfs_delete_ref_head(fs_info, delayed_refs, head); + spin_unlock(&head->lock); + spin_unlock(&delayed_refs->lock); + + btrfs_delayed_ref_unlock(head); + btrfs_put_delayed_ref_head(head); +} + +static void delete_delayed_ref_node(struct btrfs_delayed_ref_head *head, + struct btrfs_delayed_ref_node *node) +{ + rb_erase_cached(&node->ref_node, &head->ref_tree); + RB_CLEAR_NODE(&node->ref_node); + if (!list_empty(&node->add_list)) + list_del_init(&node->add_list); + btrfs_put_delayed_ref(node); +} + +static int validate_ref_head(struct btrfs_delayed_ref_head *head, + struct ref_head_check *check) +{ + if (head->bytenr != check->bytenr) { + test_err("invalid bytenr have: %llu want: %llu", head->bytenr, + check->bytenr); + return -EINVAL; + } + + if (head->num_bytes != check->num_bytes) { + test_err("invalid num_bytes have: %llu want: %llu", + head->num_bytes, check->num_bytes); + return -EINVAL; + } + + if (head->ref_mod != check->ref_mod) { + test_err("invalid ref_mod have: %d want: %d", head->ref_mod, + check->ref_mod); + return -EINVAL; + } + + if (head->total_ref_mod != check->total_ref_mod) { + test_err("invalid total_ref_mod have: %d want: %d", + head->total_ref_mod, check->total_ref_mod); + return -EINVAL; + } + + if (head->must_insert_reserved != check->must_insert) { + test_err("invalid must_insert have: %d want: %d", + head->must_insert_reserved, check->must_insert); + return -EINVAL; + } + + return 0; +} + +static int validate_ref_node(struct btrfs_delayed_ref_node *node, + struct ref_node_check *check) +{ + if (node->bytenr != check->bytenr) { + test_err("invalid bytenr have: %llu want: %llu", node->bytenr, + check->bytenr); + return -EINVAL; + } + + if (node->num_bytes != check->num_bytes) { + test_err("invalid num_bytes have: %llu want: %llu", + node->num_bytes, check->num_bytes); + return -EINVAL; + } + + if (node->ref_mod != check->ref_mod) { + test_err("invalid ref_mod have: %d want: %d", node->ref_mod, + check->ref_mod); + return -EINVAL; + } + + if (node->action != check->action) { + test_err("invalid action have: %d want: %d", node->action, + check->action); + return -EINVAL; + } + + if (node->parent != check->parent) { + test_err("invalid parent have: %llu want: %llu", node->parent, + check->parent); + return -EINVAL; + } + + if (node->ref_root != check->root) { + test_err("invalid root have: %llu want: %llu", node->ref_root, + check->root); + return -EINVAL; + } + + if (node->type != check->type) { + test_err("invalid type have: %d want: %d", node->type, + check->type); + return -EINVAL; + } + + if (btrfs_delayed_ref_owner(node) != check->owner) { + test_err("invalid owner have: %llu want: %llu", + btrfs_delayed_ref_owner(node), check->owner); + return -EINVAL; + } + + if (btrfs_delayed_ref_offset(node) != check->offset) { + test_err("invalid offset have: %llu want: %llu", + btrfs_delayed_ref_offset(node), check->offset); + return -EINVAL; + } + + return 0; +} + +static int simple_test(struct btrfs_trans_handle *trans, + struct ref_head_check *head_check, + struct ref_node_check *node_check) +{ + struct btrfs_delayed_ref_root *delayed_refs = + &trans->transaction->delayed_refs; + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_delayed_ref_head *head; + struct btrfs_delayed_ref_node *node; + struct btrfs_ref ref = { + .type = ref_type_from_disk_ref_type(node_check->type), + .action = node_check->action, + .parent = node_check->parent, + .ref_root = node_check->root, + .bytenr = node_check->bytenr, + .num_bytes = fs_info->nodesize, + }; + int ret; + + if (ref.type == BTRFS_REF_METADATA) + btrfs_init_tree_ref(&ref, node_check->owner, node_check->root, + false); + else + btrfs_init_data_ref(&ref, node_check->owner, node_check->offset, + node_check->root, true); + + if (ref.type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + return ret; + } + + head = btrfs_select_ref_head(fs_info, delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + return -EINVAL; + } + + ret = -EINVAL; + if (validate_ref_head(head, head_check)) + goto out; + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, node_check)) + goto out; + ret = 0; +out: + btrfs_unselect_ref_head(delayed_refs, head); + btrfs_destroy_delayed_refs(trans->transaction); + return ret; +} + +/* + * These are simple tests, make sure that our btrfs_ref's get turned into the + * appropriate btrfs_delayed_ref_node based on their settings and action. + */ +static int simple_tests(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct ref_head_check head_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 1, + .total_ref_mod = 1, + }; + struct ref_node_check node_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 1, + .action = BTRFS_ADD_DELAYED_REF, + .type = BTRFS_TREE_BLOCK_REF_KEY, + .parent = 0, + .root = FAKE_ROOT_OBJECTID, + .owner = FAKE_LEVEL, + .offset = 0, + }; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single add tree block failed"); + return -EINVAL; + } + + node_check.type = BTRFS_EXTENT_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single add extent data failed"); + return -EINVAL; + } + + node_check.parent = FAKE_PARENT; + node_check.type = BTRFS_SHARED_BLOCK_REF_KEY; + node_check.owner = FAKE_LEVEL; + node_check.offset = 0; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single add shared block failed"); + return -EINVAL; + } + + node_check.type = BTRFS_SHARED_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single add shared data failed"); + return -EINVAL; + } + + head_check.ref_mod = -1; + head_check.total_ref_mod = -1; + node_check.action = BTRFS_DROP_DELAYED_REF; + node_check.type = BTRFS_TREE_BLOCK_REF_KEY; + node_check.owner = FAKE_LEVEL; + node_check.offset = 0; + node_check.parent = 0; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single drop tree block failed"); + return -EINVAL; + } + + node_check.type = BTRFS_EXTENT_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single drop extent data failed"); + return -EINVAL; + } + + node_check.parent = FAKE_PARENT; + node_check.type = BTRFS_SHARED_BLOCK_REF_KEY; + node_check.owner = FAKE_LEVEL; + node_check.offset = 0; + if (simple_test(trans, &head_check, &node_check)) { + test_err("single drop shared block failed"); + return -EINVAL; + } + + node_check.type = BTRFS_SHARED_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + if (simple_test(trans, &head_check, &node_check)) { + test_err("single drop shared data failed"); + return -EINVAL; + } + + return 0; +} + +/* + * Merge tests, validate that we do delayed ref merging properly, the ref counts + * all end up properly, and delayed refs are deleted once they're no longer + * needed. + */ +static int merge_tests(struct btrfs_trans_handle *trans, + enum btrfs_ref_type type) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_delayed_ref_head *head = NULL; + struct btrfs_delayed_ref_node *node; + struct btrfs_ref ref = { + .type = type, + .action = BTRFS_ADD_DELAYED_REF, + .parent = 0, + .ref_root = FAKE_ROOT_OBJECTID, + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + }; + struct ref_head_check head_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 0, + .total_ref_mod = 0, + }; + struct ref_node_check node_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 2, + .action = BTRFS_ADD_DELAYED_REF, + .parent = 0, + .root = FAKE_ROOT_OBJECTID, + }; + int ret; + + /* + * First add a ref and then drop it, make sure we get a head ref with a + * 0 total ref mod and no nodes. + */ + if (type == BTRFS_REF_METADATA) { + node_check.type = BTRFS_TREE_BLOCK_REF_KEY; + node_check.owner = FAKE_LEVEL; + btrfs_init_tree_ref(&ref, FAKE_LEVEL, FAKE_ROOT_OBJECTID, false); + } else { + node_check.type = BTRFS_EXTENT_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + btrfs_init_data_ref(&ref, FAKE_INO, FAKE_FILE_OFFSET, + FAKE_ROOT_OBJECTID, true); + } + + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + return ret; + } + + ref.action = BTRFS_DROP_DELAYED_REF; + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + goto out; + } + + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("single add and drop failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + + delete_delayed_ref_head(trans, head); + head = NULL; + + /* + * Add a ref, then add another ref, make sure we get a head ref with a + * 2 total ref mod and 1 node. + */ + ref.action = BTRFS_ADD_DELAYED_REF; + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + goto out; + } + + head_check.ref_mod = 2; + head_check.total_ref_mod = 2; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("double add failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + delete_delayed_ref_head(trans, head); + head = NULL; + + /* Add two drop refs, make sure they are merged properly. */ + ref.action = BTRFS_DROP_DELAYED_REF; + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + goto out; + } + + head_check.ref_mod = -2; + head_check.total_ref_mod = -2; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("double drop failed"); + goto out; + } + + node_check.action = BTRFS_DROP_DELAYED_REF; + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + delete_delayed_ref_head(trans, head); + head = NULL; + + /* Add multiple refs, then drop until we go negative again. */ + ref.action = BTRFS_ADD_DELAYED_REF; + for (int i = 0; i < 10; i++) { + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + ref.action = BTRFS_DROP_DELAYED_REF; + for (int i = 0; i < 12; i++) { + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + goto out; + } + + head_check.ref_mod = -2; + head_check.total_ref_mod = -2; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("double drop failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + + delete_delayed_ref_head(trans, head); + head = NULL; + + /* Drop multiple refs, then add until we go positive again. */ + ref.action = BTRFS_DROP_DELAYED_REF; + for (int i = 0; i < 10; i++) { + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + ref.action = BTRFS_ADD_DELAYED_REF; + for (int i = 0; i < 12; i++) { + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + goto out; + } + + head_check.ref_mod = 2; + head_check.total_ref_mod = 2; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("add and drop to positive failed"); + goto out; + } + + node_check.action = BTRFS_ADD_DELAYED_REF; + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + delete_delayed_ref_head(trans, head); + head = NULL; + + /* + * Add a bunch of refs with different roots and parents, then drop them + * all, make sure everything is properly merged. + */ + ref.action = BTRFS_ADD_DELAYED_REF; + for (int i = 0; i < 50; i++) { + if (!(i % 2)) { + ref.parent = 0; + ref.ref_root = FAKE_ROOT_OBJECTID + i; + } else { + ref.parent = FAKE_PARENT + (i * fs_info->nodesize); + } + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + ref.action = BTRFS_DROP_DELAYED_REF; + for (int i = 0; i < 50; i++) { + if (!(i % 2)) { + ref.parent = 0; + ref.ref_root = FAKE_ROOT_OBJECTID + i; + } else { + ref.parent = FAKE_PARENT + (i * fs_info->nodesize); + } + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + goto out; + } + + head_check.ref_mod = 0; + head_check.total_ref_mod = 0; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("add and drop multiple failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + ret = 0; +out: + if (!IS_ERR_OR_NULL(head)) + btrfs_unselect_ref_head(&trans->transaction->delayed_refs, head); + btrfs_destroy_delayed_refs(trans->transaction); + return ret; +} + +/* + * Basic test to validate we always get the add operations first followed by any + * delete operations. + */ +static int select_delayed_refs_test(struct btrfs_trans_handle *trans) +{ + struct btrfs_delayed_ref_root *delayed_refs = + &trans->transaction->delayed_refs; + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_delayed_ref_head *head = NULL; + struct btrfs_delayed_ref_node *node; + struct btrfs_ref ref = { + .type = BTRFS_REF_METADATA, + .action = BTRFS_DROP_DELAYED_REF, + .parent = 0, + .ref_root = FAKE_ROOT_OBJECTID, + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + }; + struct ref_head_check head_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 0, + .total_ref_mod = 0, + }; + struct ref_node_check node_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 1, + .action = BTRFS_ADD_DELAYED_REF, + .type = BTRFS_TREE_BLOCK_REF_KEY, + .parent = 0, + .owner = FAKE_LEVEL, + .offset = 0, + }; + int ret; + + /* Add the drop first. */ + btrfs_init_tree_ref(&ref, FAKE_LEVEL, FAKE_ROOT_OBJECTID, false); + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + return ret; + } + + /* + * Now add the add, and make it a different root so it's logically later + * in the rb tree. + */ + ref.action = BTRFS_ADD_DELAYED_REF; + ref.ref_root = FAKE_ROOT_OBJECTID + 1; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + head = NULL; + goto out; + } + + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("head check failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + node_check.root = FAKE_ROOT_OBJECTID + 1; + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + node_check.action = BTRFS_DROP_DELAYED_REF; + node_check.root = FAKE_ROOT_OBJECTID; + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + delete_delayed_ref_node(head, node); + delete_delayed_ref_head(trans, head); + head = NULL; + + /* + * Now we're going to do the same thing, but we're going to have an add + * that gets deleted because of a merge, and make sure we still have + * another add in place. + */ + ref.action = BTRFS_DROP_DELAYED_REF; + ref.ref_root = FAKE_ROOT_OBJECTID; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + ref.action = BTRFS_ADD_DELAYED_REF; + ref.ref_root = FAKE_ROOT_OBJECTID + 1; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + ref.action = BTRFS_DROP_DELAYED_REF; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + ref.action = BTRFS_ADD_DELAYED_REF; + ref.ref_root = FAKE_ROOT_OBJECTID + 2; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + head = NULL; + goto out; + } + + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("head check failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + node_check.action = BTRFS_ADD_DELAYED_REF; + node_check.root = FAKE_ROOT_OBJECTID + 2; + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + node_check.action = BTRFS_DROP_DELAYED_REF; + node_check.root = FAKE_ROOT_OBJECTID; + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + delete_delayed_ref_node(head, node); + ret = 0; +out: + if (head) + btrfs_unselect_ref_head(delayed_refs, head); + btrfs_destroy_delayed_refs(trans->transaction); + return ret; +} + +int btrfs_test_delayed_refs(u32 sectorsize, u32 nodesize) +{ + struct btrfs_transaction *transaction; + struct btrfs_trans_handle trans; + struct btrfs_fs_info *fs_info; + int ret; + + test_msg("running delayed refs tests"); + + fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); + if (!fs_info) { + test_std_err(TEST_ALLOC_FS_INFO); + return -ENOMEM; + } + transaction = kmalloc(sizeof(*transaction), GFP_KERNEL); + if (!transaction) { + test_std_err(TEST_ALLOC_TRANSACTION); + ret = -ENOMEM; + goto out_free_fs_info; + } + btrfs_init_dummy_trans(&trans, fs_info); + btrfs_init_dummy_transaction(transaction, fs_info); + trans.transaction = transaction; + + ret = simple_tests(&trans); + if (!ret) { + test_msg("running delayed refs merg tests on metadata refs"); + ret = merge_tests(&trans, BTRFS_REF_METADATA); + } + + if (!ret) { + test_msg("running delayed refs merg tests on data refs"); + ret = merge_tests(&trans, BTRFS_REF_DATA); + } + + if (!ret) + ret = select_delayed_refs_test(&trans); + +out_free_fs_info: + btrfs_free_dummy_fs_info(fs_info); + return ret; +} diff --git a/fs/btrfs/tests/raid-stripe-tree-tests.c b/fs/btrfs/tests/raid-stripe-tree-tests.c index 30f17eb7b6a8..a7bc58a5c1e2 100644 --- a/fs/btrfs/tests/raid-stripe-tree-tests.c +++ b/fs/btrfs/tests/raid-stripe-tree-tests.c @@ -14,6 +14,8 @@ #define RST_TEST_NUM_DEVICES (2) #define RST_TEST_RAID1_TYPE (BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_RAID1) +#define SZ_48K (SZ_32K + SZ_16K) + typedef int (*test_func_t)(struct btrfs_trans_handle *trans); static struct btrfs_device *btrfs_device_by_devid(struct btrfs_fs_devices *fs_devices, @@ -29,6 +31,613 @@ static struct btrfs_device *btrfs_device_by_devid(struct btrfs_fs_devices *fs_de return NULL; } +/* + * Test creating a range of three extents and then punch a hole in the middle, + * deleting all of the middle extents and partially deleting the "book ends". + */ +static int test_punch_hole_3extents(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_io_context *bioc; + struct btrfs_io_stripe io_stripe = { 0 }; + u64 map_type = RST_TEST_RAID1_TYPE; + u64 logical1 = SZ_1M; + u64 len1 = SZ_1M; + u64 logical2 = logical1 + len1; + u64 len2 = SZ_1M; + u64 logical3 = logical2 + len2; + u64 len3 = SZ_1M; + u64 hole_start = logical1 + SZ_256K; + u64 hole_len = SZ_2M; + int ret; + + bioc = alloc_btrfs_io_context(fs_info, logical1, RST_TEST_NUM_DEVICES); + if (!bioc) { + test_std_err(TEST_ALLOC_IO_CONTEXT); + ret = -ENOMEM; + goto out; + } + + io_stripe.dev = btrfs_device_by_devid(fs_info->fs_devices, 0); + + /* Prepare for the test, 1st create 3 x 1M extents. */ + bioc->map_type = map_type; + bioc->size = len1; + + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical1 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical2; + bioc->size = len2; + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical2 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical3; + bioc->size = len3; + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical3 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + /* + * Delete a range starting at logical1 + 256K and 2M in length. Extent + * 1 is truncated to 256k length, extent 2 is completely dropped and + * extent 3 is moved 256K to the right. + */ + ret = btrfs_delete_raid_extent(trans, hole_start, hole_len); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + hole_start, hole_start + hole_len); + goto out; + } + + /* Get the first extent and check its size. */ + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len1, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical1, logical1 + len1); + goto out; + } + + if (io_stripe.physical != logical1) { + test_err("invalid physical address, expected %llu, got %llu", + logical1, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len1 != SZ_256K) { + test_err("invalid stripe length, expected %llu, got %llu", + (u64)SZ_256K, len1); + ret = -EINVAL; + goto out; + } + + /* Get the second extent and check it's absent. */ + ret = btrfs_get_raid_extent_offset(fs_info, logical2, &len2, map_type, + 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID extent [%llu, %llu] succeeded should fail", + logical2, logical2 + len2); + ret = -EINVAL; + goto out; + } + + /* Get the third extent and check its size. */ + logical3 += SZ_256K; + ret = btrfs_get_raid_extent_offset(fs_info, logical3, &len3, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical3, logical3 + len3); + goto out; + } + + if (io_stripe.physical != logical3) { + test_err("invalid physical address, expected %llu, got %llu", + logical3 + SZ_256K, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len3 != SZ_1M - SZ_256K) { + test_err("invalid stripe length, expected %llu, got %llu", + (u64)SZ_1M - SZ_256K, len3); + ret = -EINVAL; + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical1, len1); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + logical1, logical1 + len1); + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical3, len3); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + logical1, logical1 + len1); + goto out; + } + +out: + btrfs_put_bioc(bioc); + return ret; +} + +static int test_delete_two_extents(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_io_context *bioc; + struct btrfs_io_stripe io_stripe = { 0 }; + u64 map_type = RST_TEST_RAID1_TYPE; + u64 logical1 = SZ_1M; + u64 len1 = SZ_1M; + u64 logical2 = logical1 + len1; + u64 len2 = SZ_1M; + u64 logical3 = logical2 + len2; + u64 len3 = SZ_1M; + int ret; + + bioc = alloc_btrfs_io_context(fs_info, logical1, RST_TEST_NUM_DEVICES); + if (!bioc) { + test_std_err(TEST_ALLOC_IO_CONTEXT); + ret = -ENOMEM; + goto out; + } + + io_stripe.dev = btrfs_device_by_devid(fs_info->fs_devices, 0); + + /* Prepare for the test, 1st create 3 x 1M extents. */ + bioc->map_type = map_type; + bioc->size = len1; + + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical1 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical2; + bioc->size = len2; + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical2 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical3; + bioc->size = len3; + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical3 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + /* + * Delete a range starting at logical1 and 2M in length. Extents 1 + * and 2 are dropped and extent 3 is kept as is. + */ + ret = btrfs_delete_raid_extent(trans, logical1, len1 + len2); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + logical1, logical1 + len1 + len2); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len1, map_type, + 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID extent [%llu, %llu] succeeded, should fail", + logical1, len1); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical2, &len2, map_type, + 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID extent [%llu, %llu] succeeded, should fail", + logical2, len2); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical3, &len3, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical3, len3); + goto out; + } + + if (io_stripe.physical != logical3) { + test_err("invalid physical address, expected %llu, got %llu", + logical3, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len3 != SZ_1M) { + test_err("invalid stripe length, expected %llu, got %llu", + (u64)SZ_1M, len3); + ret = -EINVAL; + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical3, len3); +out: + btrfs_put_bioc(bioc); + return ret; +} + +/* Test punching a hole into a single RAID stripe-extent. */ +static int test_punch_hole(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_io_context *bioc; + struct btrfs_io_stripe io_stripe = { 0 }; + u64 map_type = RST_TEST_RAID1_TYPE; + u64 logical1 = SZ_1M; + u64 hole_start = logical1 + SZ_32K; + u64 hole_len = SZ_64K; + u64 logical2 = hole_start + hole_len; + u64 len = SZ_1M; + u64 len1 = SZ_32K; + u64 len2 = len - len1 - hole_len; + int ret; + + bioc = alloc_btrfs_io_context(fs_info, logical1, RST_TEST_NUM_DEVICES); + if (!bioc) { + test_std_err(TEST_ALLOC_IO_CONTEXT); + ret = -ENOMEM; + goto out; + } + + io_stripe.dev = btrfs_device_by_devid(fs_info->fs_devices, 0); + bioc->map_type = map_type; + bioc->size = len; + + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical1 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len, map_type, 0, + &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", logical1, + logical1 + len); + goto out; + } + + if (io_stripe.physical != logical1) { + test_err("invalid physical address, expected %llu got %llu", + logical1, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len != SZ_1M) { + test_err("invalid stripe length, expected %llu got %llu", + (u64)SZ_1M, len); + ret = -EINVAL; + goto out; + } + + ret = btrfs_delete_raid_extent(trans, hole_start, hole_len); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + hole_start, hole_start + hole_len); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len1, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical1, logical1 + len1); + goto out; + } + + if (io_stripe.physical != logical1) { + test_err("invalid physical address, expected %llu, got %llu", + logical1, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len1 != SZ_32K) { + test_err("invalid stripe length, expected %llu, got %llu", + (u64)SZ_32K, len1); + ret = -EINVAL; + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical2, &len2, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", logical2, + logical2 + len2); + goto out; + } + + if (io_stripe.physical != logical2) { + test_err("invalid physical address, expected %llu, got %llu", + logical2, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len2 != len - len1 - hole_len) { + test_err("invalid length, expected %llu, got %llu", + len - len1 - hole_len, len2); + ret = -EINVAL; + goto out; + } + + /* Check for the absence of the hole. */ + ret = btrfs_get_raid_extent_offset(fs_info, hole_start, &hole_len, + map_type, 0, &io_stripe); + if (ret != -ENODATA) { + ret = -EINVAL; + test_err("lookup of RAID extent [%llu, %llu] succeeded, should fail", + hole_start, hole_start + SZ_64K); + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical1, len1); + if (ret) + goto out; + + ret = btrfs_delete_raid_extent(trans, logical2, len2); +out: + btrfs_put_bioc(bioc); + return ret; +} + +/* + * Test a 1M RST write that spans two adjacent RST items on disk and then + * delete a portion starting in the first item and spanning into the second + * item. This is similar to test_front_delete(), but spanning multiple items. + */ +static int test_front_delete_prev_item(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_io_context *bioc; + struct btrfs_io_stripe io_stripe = { 0 }; + u64 map_type = RST_TEST_RAID1_TYPE; + u64 logical1 = SZ_1M; + u64 logical2 = SZ_2M; + u64 len = SZ_1M; + int ret; + + bioc = alloc_btrfs_io_context(fs_info, logical1, RST_TEST_NUM_DEVICES); + if (!bioc) { + test_std_err(TEST_ALLOC_IO_CONTEXT); + ret = -ENOMEM; + goto out; + } + + io_stripe.dev = btrfs_device_by_devid(fs_info->fs_devices, 0); + bioc->map_type = map_type; + bioc->size = len; + + /* Insert RAID extent 1. */ + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical1 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical2; + /* Insert RAID extent 2, directly adjacent to it. */ + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical2 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical1 + SZ_512K, SZ_1M); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + logical1 + SZ_512K, (u64)SZ_1M); + goto out; + } + + /* Verify item 1 is truncated to 512K. */ + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len, map_type, 0, + &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", logical1, + logical1 + len); + goto out; + } + + if (io_stripe.physical != logical1) { + test_err("invalid physical address, expected %llu got %llu", + logical1, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len != SZ_512K) { + test_err("invalid stripe length, expected %llu got %llu", + (u64)SZ_512K, len); + ret = -EINVAL; + goto out; + } + + /* Verify item 2's start is moved by 512K. */ + ret = btrfs_get_raid_extent_offset(fs_info, logical2 + SZ_512K, &len, + map_type, 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical2 + SZ_512K, logical2 + len); + goto out; + } + + if (io_stripe.physical != logical2 + SZ_512K) { + test_err("invalid physical address, expected %llu got %llu", + logical2 + SZ_512K, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len != SZ_512K) { + test_err("invalid stripe length, expected %llu got %llu", + (u64)SZ_512K, len); + ret = -EINVAL; + goto out; + } + + /* Verify there's a hole at [1M+512K, 2M+512K] . */ + len = SZ_1M; + ret = btrfs_get_raid_extent_offset(fs_info, logical1 + SZ_512K, &len, + map_type, 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID [%llu, %llu] succeeded, should fail", + logical1 + SZ_512K, logical1 + SZ_512K + len); + goto out; + } + + /* Clean up after us. */ + ret = btrfs_delete_raid_extent(trans, logical1, SZ_512K); + if (ret) + goto out; + + ret = btrfs_delete_raid_extent(trans, logical2 + SZ_512K, SZ_512K); + +out: + btrfs_put_bioc(bioc); + return ret; +} + /* * Test a 64K RST write on a 2 disk RAID1 at a logical address of 1M and then * delete the 1st 32K, making the new start address 1M+32K. @@ -94,45 +703,45 @@ static int test_front_delete(struct btrfs_trans_handle *trans) goto out; } - ret = btrfs_delete_raid_extent(trans, logical, SZ_32K); + ret = btrfs_delete_raid_extent(trans, logical, SZ_16K); if (ret) { test_err("deleting RAID extent [%llu, %llu] failed", logical, - logical + SZ_32K); + logical + SZ_16K); goto out; } - len = SZ_32K; - ret = btrfs_get_raid_extent_offset(fs_info, logical + SZ_32K, &len, + len -= SZ_16K; + ret = btrfs_get_raid_extent_offset(fs_info, logical + SZ_16K, &len, map_type, 0, &io_stripe); if (ret) { test_err("lookup of RAID extent [%llu, %llu] failed", - logical + SZ_32K, logical + SZ_32K + len); + logical + SZ_16K, logical + SZ_64K); goto out; } - if (io_stripe.physical != logical + SZ_32K) { + if (io_stripe.physical != logical + SZ_16K) { test_err("invalid physical address, expected %llu, got %llu", - logical + SZ_32K, io_stripe.physical); + logical + SZ_16K, io_stripe.physical); ret = -EINVAL; goto out; } - if (len != SZ_32K) { + if (len != SZ_48K) { test_err("invalid stripe length, expected %llu, got %llu", - (u64)SZ_32K, len); + (u64)SZ_48K, len); ret = -EINVAL; goto out; } ret = btrfs_get_raid_extent_offset(fs_info, logical, &len, map_type, 0, &io_stripe); - if (!ret) { + if (ret != -ENODATA) { ret = -EINVAL; test_err("lookup of RAID extent [%llu, %llu] succeeded, should fail", - logical, logical + SZ_32K); + logical, logical + SZ_16K); goto out; } - ret = btrfs_delete_raid_extent(trans, logical + SZ_32K, SZ_32K); + ret = btrfs_delete_raid_extent(trans, logical + SZ_16K, SZ_48K); out: btrfs_put_bioc(bioc); return ret; @@ -209,14 +818,14 @@ static int test_tail_delete(struct btrfs_trans_handle *trans) goto out; } - ret = btrfs_delete_raid_extent(trans, logical + SZ_32K, SZ_32K); + ret = btrfs_delete_raid_extent(trans, logical + SZ_48K, SZ_16K); if (ret) { test_err("deleting RAID extent [%llu, %llu] failed", - logical + SZ_32K, logical + SZ_64K); + logical + SZ_48K, logical + SZ_64K); goto out; } - len = SZ_32K; + len = SZ_48K; ret = btrfs_get_raid_extent_offset(fs_info, logical, &len, map_type, 0, &io_stripe); if (ret) { test_err("lookup of RAID extent [%llu, %llu] failed", logical, @@ -231,9 +840,19 @@ static int test_tail_delete(struct btrfs_trans_handle *trans) goto out; } - if (len != SZ_32K) { + if (len != SZ_48K) { test_err("invalid stripe length, expected %llu, got %llu", - (u64)SZ_32K, len); + (u64)SZ_48K, len); + ret = -EINVAL; + goto out; + } + + len = SZ_16K; + ret = btrfs_get_raid_extent_offset(fs_info, logical + SZ_48K, &len, + map_type, 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID extent [%llu, %llu] succeeded should fail", + logical + SZ_48K, logical + SZ_64K); ret = -EINVAL; goto out; } @@ -456,6 +1075,10 @@ static const test_func_t tests[] = { test_create_update_delete, test_tail_delete, test_front_delete, + test_front_delete_prev_item, + test_punch_hole, + test_punch_hole_3extents, + test_delete_two_extents, }; static int run_test(test_func_t test, u32 sectorsize, u32 nodesize) @@ -478,8 +1101,8 @@ static int run_test(test_func_t test, u32 sectorsize, u32 nodesize) ret = PTR_ERR(root); goto out; } - btrfs_set_super_compat_ro_flags(root->fs_info->super_copy, - BTRFS_FEATURE_INCOMPAT_RAID_STRIPE_TREE); + btrfs_set_super_incompat_flags(root->fs_info->super_copy, + BTRFS_FEATURE_INCOMPAT_RAID_STRIPE_TREE); root->root_key.objectid = BTRFS_RAID_STRIPE_TREE_OBJECTID; root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = 0; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index dc0b837efd5d..15312013f2a3 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -795,8 +795,7 @@ alloc_fail: if (num_bytes) btrfs_block_rsv_release(fs_info, trans_rsv, num_bytes, NULL); if (delayed_refs_bytes) - btrfs_space_info_free_bytes_may_use(fs_info, trans_rsv->space_info, - delayed_refs_bytes); + btrfs_space_info_free_bytes_may_use(trans_rsv->space_info, delayed_refs_bytes); reserve_fail: btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); return ERR_PTR(ret); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 184fa5c0062a..9f7c777af635 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -227,7 +227,21 @@ static inline void btrfs_clear_skip_qgroup(struct btrfs_trans_handle *trans) delayed_refs->qgroup_to_skip = 0; } -bool __cold abort_should_print_stack(int error); +/* + * We want the transaction abort to print stack trace only for errors where the + * cause could be a bug, eg. due to ENOSPC, and not for common errors that are + * caused by external factors. + */ +static inline bool btrfs_abort_should_print_stack(int error) +{ + switch (error) { + case -EIO: + case -EROFS: + case -ENOMEM: + return false; + } + return true; +} /* * Call btrfs_abort_transaction as early as possible when an error condition is @@ -240,7 +254,7 @@ do { \ if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \ &((trans)->fs_info->fs_state))) { \ __first = true; \ - if (WARN(abort_should_print_stack(error), \ + if (WARN(btrfs_abort_should_print_stack(error), \ KERN_ERR \ "BTRFS: Transaction aborted (error %d)\n", \ (error))) { \ diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 148d8cefa40e..43979891f7c8 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -764,22 +764,19 @@ static int check_block_group_item(struct extent_buffer *leaf, return 0; } -__printf(4, 5) +__printf(5, 6) __cold -static void chunk_err(const struct extent_buffer *leaf, +static void chunk_err(const struct btrfs_fs_info *fs_info, + const struct extent_buffer *leaf, const struct btrfs_chunk *chunk, u64 logical, const char *fmt, ...) { - const struct btrfs_fs_info *fs_info = leaf->fs_info; - bool is_sb; + bool is_sb = !leaf; struct va_format vaf; va_list args; int i; int slot = -1; - /* Only superblock eb is able to have such small offset */ - is_sb = (leaf->start == BTRFS_SUPER_INFO_OFFSET); - if (!is_sb) { /* * Get the slot number by iterating through all slots, this @@ -812,13 +809,17 @@ static void chunk_err(const struct extent_buffer *leaf, /* * The common chunk check which could also work on super block sys chunk array. * + * If @leaf is NULL, then @chunk must be an on-stack chunk item. + * (For superblock sys_chunk array, and fs_info->sectorsize is unreliable) + * * Return -EUCLEAN if anything is corrupted. * Return 0 if everything is OK. */ -int btrfs_check_chunk_valid(struct extent_buffer *leaf, - struct btrfs_chunk *chunk, u64 logical) +int btrfs_check_chunk_valid(const struct btrfs_fs_info *fs_info, + const struct extent_buffer *leaf, + const struct btrfs_chunk *chunk, u64 logical, + u32 sectorsize) { - struct btrfs_fs_info *fs_info = leaf->fs_info; u64 length; u64 chunk_end; u64 stripe_len; @@ -826,63 +827,73 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, u16 sub_stripes; u64 type; u64 features; + u32 chunk_sector_size; bool mixed = false; int raid_index; int nparity; int ncopies; - length = btrfs_chunk_length(leaf, chunk); - stripe_len = btrfs_chunk_stripe_len(leaf, chunk); - num_stripes = btrfs_chunk_num_stripes(leaf, chunk); - sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); - type = btrfs_chunk_type(leaf, chunk); + if (leaf) { + length = btrfs_chunk_length(leaf, chunk); + stripe_len = btrfs_chunk_stripe_len(leaf, chunk); + num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); + type = btrfs_chunk_type(leaf, chunk); + chunk_sector_size = btrfs_chunk_sector_size(leaf, chunk); + } else { + length = btrfs_stack_chunk_length(chunk); + stripe_len = btrfs_stack_chunk_stripe_len(chunk); + num_stripes = btrfs_stack_chunk_num_stripes(chunk); + sub_stripes = btrfs_stack_chunk_sub_stripes(chunk); + type = btrfs_stack_chunk_type(chunk); + chunk_sector_size = btrfs_stack_chunk_sector_size(chunk); + } raid_index = btrfs_bg_flags_to_raid_index(type); ncopies = btrfs_raid_array[raid_index].ncopies; nparity = btrfs_raid_array[raid_index].nparity; if (unlikely(!num_stripes)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk num_stripes, have %u", num_stripes); return -EUCLEAN; } if (unlikely(num_stripes < ncopies)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk num_stripes < ncopies, have %u < %d", num_stripes, ncopies); return -EUCLEAN; } if (unlikely(nparity && num_stripes == nparity)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk num_stripes == nparity, have %u == %d", num_stripes, nparity); return -EUCLEAN; } - if (unlikely(!IS_ALIGNED(logical, fs_info->sectorsize))) { - chunk_err(leaf, chunk, logical, + if (unlikely(!IS_ALIGNED(logical, sectorsize))) { + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk logical, have %llu should aligned to %u", - logical, fs_info->sectorsize); + logical, sectorsize); return -EUCLEAN; } - if (unlikely(btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize)) { - chunk_err(leaf, chunk, logical, + if (unlikely(chunk_sector_size != sectorsize)) { + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk sectorsize, have %u expect %u", - btrfs_chunk_sector_size(leaf, chunk), - fs_info->sectorsize); + chunk_sector_size, sectorsize); return -EUCLEAN; } - if (unlikely(!length || !IS_ALIGNED(length, fs_info->sectorsize))) { - chunk_err(leaf, chunk, logical, + if (unlikely(!length || !IS_ALIGNED(length, sectorsize))) { + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk length, have %llu", length); return -EUCLEAN; } if (unlikely(check_add_overflow(logical, length, &chunk_end))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk logical start and length, have logical start %llu length %llu", logical, length); return -EUCLEAN; } if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk stripe length: %llu", stripe_len); return -EUCLEAN; @@ -896,30 +907,29 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, * Thus it should be a good way to catch obvious bitflips. */ if (unlikely(length >= btrfs_stripe_nr_to_offset(U32_MAX))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "chunk length too large: have %llu limit %llu", length, btrfs_stripe_nr_to_offset(U32_MAX)); return -EUCLEAN; } if (unlikely(type & ~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "unrecognized chunk type: 0x%llx", ~(BTRFS_BLOCK_GROUP_TYPE_MASK | - BTRFS_BLOCK_GROUP_PROFILE_MASK) & - btrfs_chunk_type(leaf, chunk)); + BTRFS_BLOCK_GROUP_PROFILE_MASK) & type); return -EUCLEAN; } if (unlikely(!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) && (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set", type & BTRFS_BLOCK_GROUP_PROFILE_MASK); return -EUCLEAN; } if (unlikely((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "missing chunk type flag, have 0x%llx one bit must be set in 0x%llx", type, BTRFS_BLOCK_GROUP_TYPE_MASK); return -EUCLEAN; @@ -928,7 +938,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, if (unlikely((type & BTRFS_BLOCK_GROUP_SYSTEM) && (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA)))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "system chunk with data or metadata type: 0x%llx", type); return -EUCLEAN; @@ -941,7 +951,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, if (!mixed) { if (unlikely((type & BTRFS_BLOCK_GROUP_METADATA) && (type & BTRFS_BLOCK_GROUP_DATA))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "mixed chunk type in non-mixed mode: 0x%llx", type); return -EUCLEAN; } @@ -963,7 +973,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, num_stripes != btrfs_raid_array[BTRFS_RAID_DUP].dev_stripes) || ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && num_stripes != btrfs_raid_array[BTRFS_RAID_SINGLE].dev_stripes))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid num_stripes:sub_stripes %u:%u for profile %llu", num_stripes, sub_stripes, type & BTRFS_BLOCK_GROUP_PROFILE_MASK); @@ -983,14 +993,15 @@ static int check_leaf_chunk_item(struct extent_buffer *leaf, struct btrfs_chunk *chunk, struct btrfs_key *key, int slot) { + struct btrfs_fs_info *fs_info = leaf->fs_info; int num_stripes; if (unlikely(btrfs_item_size(leaf, slot) < sizeof(struct btrfs_chunk))) { - chunk_err(leaf, chunk, key->offset, + chunk_err(fs_info, leaf, chunk, key->offset, "invalid chunk item size: have %u expect [%zu, %u)", btrfs_item_size(leaf, slot), sizeof(struct btrfs_chunk), - BTRFS_LEAF_DATA_SIZE(leaf->fs_info)); + BTRFS_LEAF_DATA_SIZE(fs_info)); return -EUCLEAN; } @@ -1001,14 +1012,15 @@ static int check_leaf_chunk_item(struct extent_buffer *leaf, if (unlikely(btrfs_chunk_item_size(num_stripes) != btrfs_item_size(leaf, slot))) { - chunk_err(leaf, chunk, key->offset, + chunk_err(fs_info, leaf, chunk, key->offset, "invalid chunk item size: have %u expect %lu", btrfs_item_size(leaf, slot), btrfs_chunk_item_size(num_stripes)); return -EUCLEAN; } out: - return btrfs_check_chunk_valid(leaf, chunk, key->offset); + return btrfs_check_chunk_valid(fs_info, leaf, chunk, key->offset, + fs_info->sectorsize); } __printf(3, 4) @@ -1527,6 +1539,11 @@ static int check_extent_item(struct extent_buffer *leaf, dref_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_extent_data_ref_count(leaf, dref); break; /* Contains parent bytenr and ref count */ @@ -1539,6 +1556,11 @@ static int check_extent_item(struct extent_buffer *leaf, inline_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_shared_data_ref_count(leaf, sref); break; case BTRFS_EXTENT_OWNER_REF_KEY: @@ -1611,8 +1633,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf, { u32 expect_item_size = 0; - if (key->type == BTRFS_SHARED_DATA_REF_KEY) + if (key->type == BTRFS_SHARED_DATA_REF_KEY) { + struct btrfs_shared_data_ref *sref; + + sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data backref count, should have non-zero value"); + return -EUCLEAN; + } + expect_item_size = sizeof(struct btrfs_shared_data_ref); + } if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) { generic_err(leaf, slot, @@ -1689,6 +1721,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf, offset, leaf->fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid extent data backref count, should have non-zero value"); + return -EUCLEAN; + } } return 0; } diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h index db67f96cbe4b..eb201f4ec3c7 100644 --- a/fs/btrfs/tree-checker.h +++ b/fs/btrfs/tree-checker.h @@ -10,6 +10,7 @@ #include struct extent_buffer; +struct btrfs_fs_info; struct btrfs_chunk; struct btrfs_key; @@ -66,8 +67,10 @@ enum btrfs_tree_block_status __btrfs_check_node(struct extent_buffer *node); int btrfs_check_leaf(struct extent_buffer *leaf); int btrfs_check_node(struct extent_buffer *node); -int btrfs_check_chunk_valid(struct extent_buffer *leaf, - struct btrfs_chunk *chunk, u64 logical); +int btrfs_check_chunk_valid(const struct btrfs_fs_info *fs_info, + const struct extent_buffer *leaf, + const struct btrfs_chunk *chunk, u64 logical, + u32 sectorsize); int btrfs_check_eb_owner(const struct extent_buffer *eb, u64 root_owner); int btrfs_verify_level_key(struct extent_buffer *eb, const struct btrfs_tree_parent_check *check); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c8d6587688b3..955d1677e865 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -590,7 +590,6 @@ insert: } } no_copy: - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } @@ -3588,7 +3587,6 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, last_offset = max(last_offset, curr_end); } btrfs_set_dir_log_end(path->nodes[0], item, last_offset); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } @@ -4566,7 +4564,6 @@ copy_item: dst_index++; } - btrfs_mark_buffer_dirty(trans, dst_path->nodes[0]); btrfs_release_path(dst_path); out: kfree(ins_data); @@ -4776,7 +4773,6 @@ static int log_one_extent(struct btrfs_trans_handle *trans, write_extent_buffer(leaf, &fi, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(fi)); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index aca2861f2187..17b5e81123a1 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -140,8 +140,6 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, const u8 *uuid, u8 typ ret = 0; subid_le = cpu_to_le64(subid_cpu); write_extent_buffer(eb, &subid_le, offset, sizeof(subid_le)); - btrfs_mark_buffer_dirty(trans, eb); - out: btrfs_free_path(path); return ret; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1cccaf9c2b0d..0a0776489055 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -13,8 +13,8 @@ #include #include #include "misc.h" -#include "ctree.h" #include "disk-io.h" +#include "extent-tree.h" #include "transaction.h" #include "volumes.h" #include "raid56.h" @@ -48,6 +48,7 @@ struct btrfs_io_geometry { u64 raid56_full_stripe_start; int max_errors; enum btrfs_map_op op; + bool use_rst; }; const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { @@ -797,6 +798,10 @@ static int get_canonical_dev_path(const char *dev_path, char *canonical) if (ret) goto out; resolved_path = d_path(&path, path_buf, PATH_MAX); + if (IS_ERR(resolved_path)) { + ret = PTR_ERR(resolved_path); + goto out; + } ret = strscpy(canonical, resolved_path, PATH_MAX); out: kfree(path_buf); @@ -1298,6 +1303,7 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices, struct btrfs_device *device; struct btrfs_device *latest_dev = NULL; struct btrfs_device *tmp_device; + s64 __maybe_unused value = 0; int ret = 0; list_for_each_entry_safe(device, tmp_device, &fs_devices->devices, @@ -1327,7 +1333,23 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices, fs_devices->latest_dev = latest_dev; fs_devices->total_rw_bytes = 0; fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_REGULAR; +#ifdef CONFIG_BTRFS_EXPERIMENTAL + fs_devices->rr_min_contig_read = BTRFS_DEFAULT_RR_MIN_CONTIG_READ; + fs_devices->read_devid = latest_dev->devid; + fs_devices->read_policy = btrfs_read_policy_to_enum(btrfs_get_mod_read_policy(), + &value); + if (fs_devices->read_policy == BTRFS_READ_POLICY_RR) + fs_devices->collect_fs_stats = true; + + if (value) { + if (fs_devices->read_policy == BTRFS_READ_POLICY_RR) + fs_devices->rr_min_contig_read = value; + if (fs_devices->read_policy == BTRFS_READ_POLICY_DEVID) + fs_devices->read_devid = value; + } +#else fs_devices->read_policy = BTRFS_READ_POLICY_PID; +#endif return 0; } @@ -2045,7 +2067,6 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans, ptr = btrfs_device_fsid(dev_item); write_extent_buffer(leaf, trans->fs_info->fs_devices->metadata_uuid, ptr, BTRFS_FSID_SIZE); - btrfs_mark_buffer_dirty(trans, leaf); ret = 0; out: @@ -2741,11 +2762,9 @@ next_slot: device = btrfs_find_device(fs_info->fs_devices, &args); BUG_ON(!device); /* Logic error */ - if (device->fs_devices->seeding) { + if (device->fs_devices->seeding) btrfs_set_device_generation(leaf, dev_item, device->generation); - btrfs_mark_buffer_dirty(trans, leaf); - } path->slots[0]++; goto next_slot; @@ -3038,8 +3057,6 @@ static noinline int btrfs_update_device(struct btrfs_trans_handle *trans, btrfs_device_get_disk_total_bytes(device)); btrfs_set_device_bytes_used(leaf, dev_item, btrfs_device_get_bytes_used(device)); - btrfs_mark_buffer_dirty(trans, leaf); - out: btrfs_free_path(path); return ret; @@ -3748,10 +3765,7 @@ static int insert_balance_item(struct btrfs_fs_info *fs_info, btrfs_set_balance_meta(leaf, item, &disk_bargs); btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->sys); btrfs_set_balance_sys(leaf, item, &disk_bargs); - btrfs_set_balance_flags(leaf, item, bctl->flags); - - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); err = btrfs_commit_transaction(trans); @@ -5513,33 +5527,34 @@ void btrfs_remove_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_ma btrfs_free_chunk_map(map); } +static int btrfs_chunk_map_cmp(const struct rb_node *new, + const struct rb_node *exist) +{ + const struct btrfs_chunk_map *new_map = + rb_entry(new, struct btrfs_chunk_map, rb_node); + const struct btrfs_chunk_map *exist_map = + rb_entry(exist, struct btrfs_chunk_map, rb_node); + + if (new_map->start == exist_map->start) + return 0; + if (new_map->start < exist_map->start) + return -1; + return 1; +} + EXPORT_FOR_TESTS int btrfs_add_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map) { - struct rb_node **p; - struct rb_node *parent = NULL; - bool leftmost = true; + struct rb_node *exist; write_lock(&fs_info->mapping_tree_lock); - p = &fs_info->mapping_tree.rb_root.rb_node; - while (*p) { - struct btrfs_chunk_map *entry; + exist = rb_find_add_cached(&map->rb_node, &fs_info->mapping_tree, + btrfs_chunk_map_cmp); - parent = *p; - entry = rb_entry(parent, struct btrfs_chunk_map, rb_node); - - if (map->start < entry->start) { - p = &(*p)->rb_left; - } else if (map->start > entry->start) { - p = &(*p)->rb_right; - leftmost = false; - } else { - write_unlock(&fs_info->mapping_tree_lock); - return -EEXIST; - } + if (exist) { + write_unlock(&fs_info->mapping_tree_lock); + return -EEXIST; } - rb_link_node(&map->rb_node, parent, p); - rb_insert_color_cached(&map->rb_node, &fs_info->mapping_tree, leftmost); chunk_map_device_set_bits(map, CHUNK_ALLOCATED); chunk_map_device_clear_bits(map, CHUNK_TRIMMED); write_unlock(&fs_info->mapping_tree_lock); @@ -5959,6 +5974,76 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info, return len; } +#ifdef CONFIG_BTRFS_EXPERIMENTAL +static int btrfs_read_preferred(struct btrfs_chunk_map *map, int first, int num_stripes) +{ + for (int index = first; index < first + num_stripes; index++) { + const struct btrfs_device *device = map->stripes[index].dev; + + if (device->devid == READ_ONCE(device->fs_devices->read_devid)) + return index; + } + + /* If no read-preferred device is set use the first stripe. */ + return first; +} + +struct stripe_mirror { + u64 devid; + int num; +}; + +static int btrfs_cmp_devid(const void *a, const void *b) +{ + const struct stripe_mirror *s1 = (const struct stripe_mirror *)a; + const struct stripe_mirror *s2 = (const struct stripe_mirror *)b; + + if (s1->devid < s2->devid) + return -1; + if (s1->devid > s2->devid) + return 1; + return 0; +} + +/* + * Select a stripe for reading using the round-robin algorithm. + * + * 1. Compute the read cycle as the total sectors read divided by the minimum + * sectors per device. + * 2. Determine the stripe number for the current read by taking the modulus + * of the read cycle with the total number of stripes: + * + * stripe index = (total sectors / min sectors per dev) % num stripes + * + * The calculated stripe index is then used to select the corresponding device + * from the list of devices, which is ordered by devid. + */ +static int btrfs_read_rr(const struct btrfs_chunk_map *map, int first, int num_stripes) +{ + struct stripe_mirror stripes[BTRFS_RAID1_MAX_MIRRORS] = { 0 }; + struct btrfs_device *device = map->stripes[first].dev; + struct btrfs_fs_info *fs_info = device->fs_devices->fs_info; + unsigned int read_cycle; + unsigned int total_reads; + unsigned int min_reads_per_dev; + + total_reads = percpu_counter_sum(&fs_info->stats_read_blocks); + min_reads_per_dev = READ_ONCE(fs_info->fs_devices->rr_min_contig_read) >> + fs_info->sectorsize_bits; + + for (int index = 0, i = first; i < first + num_stripes; i++) { + stripes[index].devid = map->stripes[i].dev->devid; + stripes[index].num = i; + index++; + } + sort(stripes, num_stripes, sizeof(struct stripe_mirror), + btrfs_cmp_devid, NULL); + + read_cycle = total_reads / min_reads_per_dev; + return stripes[read_cycle % num_stripes].num; +} +#endif + static int find_live_mirror(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map, int first, int dev_replace_is_ongoing) @@ -5988,6 +6073,14 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, case BTRFS_READ_POLICY_PID: preferred_mirror = first + (current->pid % num_stripes); break; +#ifdef CONFIG_BTRFS_EXPERIMENTAL + case BTRFS_READ_POLICY_RR: + preferred_mirror = btrfs_read_rr(map, first, num_stripes); + break; + case BTRFS_READ_POLICY_DEVID: + preferred_mirror = btrfs_read_preferred(map, first, num_stripes); + break; +#endif } if (dev_replace_is_ongoing && @@ -6346,8 +6439,7 @@ static int set_io_stripe(struct btrfs_fs_info *fs_info, u64 logical, { dst->dev = map->stripes[io_geom->stripe_index].dev; - if (io_geom->op == BTRFS_MAP_READ && - btrfs_need_stripe_tree_update(fs_info, map->type)) + if (io_geom->op == BTRFS_MAP_READ && io_geom->use_rst) return btrfs_get_raid_extent_offset(fs_info, logical, length, map->type, io_geom->stripe_index, dst); @@ -6362,7 +6454,7 @@ static bool is_single_device_io(struct btrfs_fs_info *fs_info, const struct btrfs_io_stripe *smap, const struct btrfs_chunk_map *map, int num_alloc_stripes, - enum btrfs_map_op op, int mirror_num) + struct btrfs_io_geometry *io_geom) { if (!smap) return false; @@ -6370,10 +6462,10 @@ static bool is_single_device_io(struct btrfs_fs_info *fs_info, if (num_alloc_stripes != 1) return false; - if (btrfs_need_stripe_tree_update(fs_info, map->type) && op != BTRFS_MAP_READ) + if (io_geom->use_rst && io_geom->op != BTRFS_MAP_READ) return false; - if ((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) && mirror_num > 1) + if ((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) && io_geom->mirror_num > 1) return false; return true; @@ -6579,6 +6671,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom.raid56_full_stripe_start = (u64)-1; max_len = btrfs_max_io_len(map, map_offset, &io_geom); *length = min_t(u64, map->chunk_len - map_offset, max_len); + io_geom.use_rst = btrfs_need_stripe_tree_update(fs_info, map->type); if (dev_replace->replace_task != current) down_read(&dev_replace->rwsem); @@ -6647,8 +6740,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, * physical block information on the stack instead of allocating an * I/O context structure. */ - if (is_single_device_io(fs_info, smap, map, num_alloc_stripes, op, - io_geom.mirror_num)) { + if (is_single_device_io(fs_info, smap, map, num_alloc_stripes, &io_geom)) { ret = set_io_stripe(fs_info, logical, length, smap, map, &io_geom); if (mirror_num_ret) *mirror_num_ret = io_geom.mirror_num; @@ -6662,6 +6754,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, goto out; } bioc->map_type = map->type; + bioc->use_rst = io_geom.use_rst; /* * For RAID56 full map, we need to make sure the stripes[] follows the @@ -7002,16 +7095,6 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf, warn_32bit_meta_chunk(fs_info, logical, length, type); #endif - /* - * Only need to verify chunk item if we're reading from sys chunk array, - * as chunk item in tree block is already verified by tree-checker. - */ - if (leaf->start == BTRFS_SUPER_INFO_OFFSET) { - ret = btrfs_check_chunk_valid(leaf, chunk, logical); - if (ret) - return ret; - } - map = btrfs_find_chunk_map(fs_info, logical, 1); /* already mapped? */ @@ -7269,16 +7352,11 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) { struct btrfs_super_block *super_copy = fs_info->super_copy; struct extent_buffer *sb; - struct btrfs_disk_key *disk_key; - struct btrfs_chunk *chunk; u8 *array_ptr; unsigned long sb_array_offset; int ret = 0; - u32 num_stripes; u32 array_size; - u32 len = 0; u32 cur_offset; - u64 type; struct btrfs_key key; ASSERT(BTRFS_SUPER_INFO_SIZE <= fs_info->nodesize); @@ -7301,10 +7379,15 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) cur_offset = 0; while (cur_offset < array_size) { - disk_key = (struct btrfs_disk_key *)array_ptr; - len = sizeof(*disk_key); - if (cur_offset + len > array_size) - goto out_short_read; + struct btrfs_chunk *chunk; + struct btrfs_disk_key *disk_key = (struct btrfs_disk_key *)array_ptr; + u32 len = sizeof(*disk_key); + + /* + * The sys_chunk_array has been already verified at super block + * read time. Only do ASSERT()s for basic checks. + */ + ASSERT(cur_offset + len <= array_size); btrfs_disk_key_to_cpu(&key, disk_key); @@ -7312,44 +7395,14 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) sb_array_offset += len; cur_offset += len; - if (key.type != BTRFS_CHUNK_ITEM_KEY) { - btrfs_err(fs_info, - "unexpected item type %u in sys_array at offset %u", - (u32)key.type, cur_offset); - ret = -EIO; - break; - } + ASSERT(key.type == BTRFS_CHUNK_ITEM_KEY); chunk = (struct btrfs_chunk *)sb_array_offset; - /* - * At least one btrfs_chunk with one stripe must be present, - * exact stripe count check comes afterwards - */ - len = btrfs_chunk_item_size(1); - if (cur_offset + len > array_size) - goto out_short_read; + ASSERT(btrfs_chunk_type(sb, chunk) & BTRFS_BLOCK_GROUP_SYSTEM); - num_stripes = btrfs_chunk_num_stripes(sb, chunk); - if (!num_stripes) { - btrfs_err(fs_info, - "invalid number of stripes %u in sys_array at offset %u", - num_stripes, cur_offset); - ret = -EIO; - break; - } + len = btrfs_chunk_item_size(btrfs_chunk_num_stripes(sb, chunk)); - type = btrfs_chunk_type(sb, chunk); - if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) { - btrfs_err(fs_info, - "invalid chunk type %llu in sys_array at offset %u", - type, cur_offset); - ret = -EIO; - break; - } - - len = btrfs_chunk_item_size(num_stripes); - if (cur_offset + len > array_size) - goto out_short_read; + ASSERT(cur_offset + len <= array_size); ret = read_one_chunk(&key, sb, chunk); if (ret) @@ -7362,13 +7415,6 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) clear_extent_buffer_uptodate(sb); free_extent_buffer_stale(sb); return ret; - -out_short_read: - btrfs_err(fs_info, "sys_array too short to read %u bytes at offset %u", - len, cur_offset); - clear_extent_buffer_uptodate(sb); - free_extent_buffer_stale(sb); - return -EIO; } /* @@ -7568,8 +7614,6 @@ int btrfs_init_devices_late(struct btrfs_fs_info *fs_info) struct btrfs_device *device; int ret = 0; - fs_devices->fs_info = fs_info; - mutex_lock(&fs_devices->device_list_mutex); list_for_each_entry(device, &fs_devices->devices, dev_list) device->fs_info = fs_info; @@ -7745,8 +7789,6 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) btrfs_set_dev_stats_value(eb, ptr, i, btrfs_dev_stat_read(device, i)); - btrfs_mark_buffer_dirty(trans, eb); - out: btrfs_free_path(path); return ret; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 3a416b1bc24c..120f65e21eeb 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -296,6 +296,9 @@ enum btrfs_chunk_allocation_policy { BTRFS_CHUNK_ALLOC_ZONED, }; +#define BTRFS_DEFAULT_RR_MIN_CONTIG_READ (SZ_256K) +/* Keep in sync with raid_attr table, current maximum is RAID1C4. */ +#define BTRFS_RAID1_MAX_MIRRORS (4) /* * Read policies for mirrored block group profiles, read picks the stripe based * on these policies. @@ -303,6 +306,12 @@ enum btrfs_chunk_allocation_policy { enum btrfs_read_policy { /* Use process PID to choose the stripe */ BTRFS_READ_POLICY_PID, +#ifdef CONFIG_BTRFS_EXPERIMENTAL + /* Balancing RAID1 reads across all striped devices (round-robin). */ + BTRFS_READ_POLICY_RR, + /* Read from a specific device. */ + BTRFS_READ_POLICY_DEVID, +#endif BTRFS_NR_READ_POLICY, }; @@ -417,6 +426,8 @@ struct btrfs_fs_devices { bool seeding; /* The mount needs to use a randomly generated fsid. */ bool temp_fsid; + /* Enable/disable the filesystem stats tracking. */ + bool collect_fs_stats; struct btrfs_fs_info *fs_info; /* sysfs kobjects */ @@ -431,6 +442,15 @@ struct btrfs_fs_devices { enum btrfs_read_policy read_policy; #ifdef CONFIG_BTRFS_EXPERIMENTAL + /* + * Minimum contiguous reads before switching to next device, the unit + * is one block/sectorsize. + */ + u32 rr_min_contig_read; + + /* Device to be used for reading in case of RAID1. */ + u64 read_devid; + /* Checksum mode - offload it or do it synchronously. */ enum btrfs_offload_csum_mode offload_csum_mode; #endif @@ -485,6 +505,7 @@ struct btrfs_io_context { struct bio *orig_bio; atomic_t error; u16 max_errors; + bool use_rst; u64 logical; u64 size; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index bc18710d1dcf..3e0edbcf73e1 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -204,7 +204,6 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, btrfs_set_dir_data_len(leaf, di, size); data_ptr = ((unsigned long)(di + 1)) + name_len; write_extent_buffer(leaf, value, data_ptr, size); - btrfs_mark_buffer_dirty(trans, leaf); } else { /* * Insert, and we had space for the xattr, so path->slots[0] is diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index ddf0d5a448a7..c9e92c6941ec 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -174,10 +174,10 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, copy_page(workspace->buf + i * PAGE_SIZE, data_in); start += PAGE_SIZE; - workspace->strm.avail_in = - (in_buf_folios << PAGE_SHIFT); } workspace->strm.next_in = workspace->buf; + workspace->strm.avail_in = min(bytes_left, + in_buf_folios << PAGE_SHIFT); } else { unsigned int pg_off; unsigned int cur_len; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 11ed523e528e..73e0aa9fc08a 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -748,8 +748,9 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) (u64)lim->max_segments << PAGE_SHIFT), fs_info->sectorsize); fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED; - if (fs_info->max_zone_append_size < fs_info->max_extent_size) - fs_info->max_extent_size = fs_info->max_zone_append_size; + + fs_info->max_extent_size = min_not_zero(fs_info->max_extent_size, + fs_info->max_zone_append_size); /* * Check mount options here, because we might change fs_info->zoned @@ -2651,3 +2652,127 @@ void btrfs_check_active_zone_reservation(struct btrfs_fs_info *fs_info) } spin_unlock(&fs_info->zone_active_bgs_lock); } + +/* + * Reset the zones of unused block groups from @space_info->bytes_zone_unusable. + * + * @space_info: the space to work on + * @num_bytes: targeting reclaim bytes + * + * This one resets the zones of a block group, so we can reuse the region + * without removing the block group. On the other hand, btrfs_delete_unused_bgs() + * just removes a block group and frees up the underlying zones. So, we still + * need to allocate a new block group to reuse the zones. + * + * Resetting is faster than deleting/recreating a block group. It is similar + * to freeing the logical space on the regular mode. However, we cannot change + * the block group's profile with this operation. + */ +int btrfs_reset_unused_block_groups(struct btrfs_space_info *space_info, u64 num_bytes) +{ + struct btrfs_fs_info *fs_info = space_info->fs_info; + const sector_t zone_size_sectors = fs_info->zone_size >> SECTOR_SHIFT; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + while (num_bytes > 0) { + struct btrfs_chunk_map *map; + struct btrfs_block_group *bg = NULL; + bool found = false; + u64 reclaimed = 0; + + /* + * Here, we choose a fully zone_unusable block group. It's + * technically possible to reset a partly zone_unusable block + * group, which still has some free space left. However, + * handling that needs to cope with the allocation side, which + * makes the logic more complex. So, let's handle the easy case + * for now. + */ + spin_lock(&fs_info->unused_bgs_lock); + list_for_each_entry(bg, &fs_info->unused_bgs, bg_list) { + if ((bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) != space_info->flags) + continue; + + /* + * Use trylock to avoid locking order violation. In + * btrfs_reclaim_bgs_work(), the lock order is + * &bg->lock -> &fs_info->unused_bgs_lock. We skip a + * block group if we cannot take its lock. + */ + if (!spin_trylock(&bg->lock)) + continue; + if (btrfs_is_block_group_used(bg) || bg->zone_unusable < bg->length) { + spin_unlock(&bg->lock); + continue; + } + spin_unlock(&bg->lock); + found = true; + break; + } + if (!found) { + spin_unlock(&fs_info->unused_bgs_lock); + return 0; + } + + list_del_init(&bg->bg_list); + btrfs_put_block_group(bg); + spin_unlock(&fs_info->unused_bgs_lock); + + /* + * Since the block group is fully zone_unusable and we cannot + * allocate from this block group anymore, we don't need to set + * this block group read-only. + */ + + down_read(&fs_info->dev_replace.rwsem); + map = bg->physical_map; + for (int i = 0; i < map->num_stripes; i++) { + struct btrfs_io_stripe *stripe = &map->stripes[i]; + unsigned int nofs_flags; + int ret; + + nofs_flags = memalloc_nofs_save(); + ret = blkdev_zone_mgmt(stripe->dev->bdev, REQ_OP_ZONE_RESET, + stripe->physical >> SECTOR_SHIFT, + zone_size_sectors); + memalloc_nofs_restore(nofs_flags); + + if (ret) { + up_read(&fs_info->dev_replace.rwsem); + return ret; + } + } + up_read(&fs_info->dev_replace.rwsem); + + spin_lock(&space_info->lock); + spin_lock(&bg->lock); + ASSERT(!btrfs_is_block_group_used(bg)); + if (bg->ro) { + spin_unlock(&bg->lock); + spin_unlock(&space_info->lock); + continue; + } + + reclaimed = bg->alloc_offset; + bg->zone_unusable = bg->length - bg->zone_capacity; + bg->alloc_offset = 0; + /* + * This holds because we currently reset fully used then freed + * block group. + */ + ASSERT(reclaimed == bg->zone_capacity); + bg->free_space_ctl->free_space += reclaimed; + space_info->bytes_zone_unusable -= reclaimed; + spin_unlock(&bg->lock); + btrfs_return_free_space(space_info, reclaimed); + spin_unlock(&space_info->lock); + + if (num_bytes <= reclaimed) + break; + num_bytes -= reclaimed; + } + + return 0; +} diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 7612e6572605..9672bf4c3335 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -96,6 +96,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info); int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, bool do_finish); void btrfs_check_active_zone_reservation(struct btrfs_fs_info *fs_info); +int btrfs_reset_unused_block_groups(struct btrfs_space_info *space_info, u64 num_bytes); #else /* CONFIG_BLK_DEV_ZONED */ static inline int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) @@ -265,6 +266,12 @@ static inline int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info, static inline void btrfs_check_active_zone_reservation(struct btrfs_fs_info *fs_info) { } +static inline int btrfs_reset_unused_block_groups(struct btrfs_space_info *space_info, + u64 num_bytes) +{ + return 0; +} + #endif static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos) diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 89b11336a836..1806bff8e59b 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -576,7 +577,7 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args) */ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) { - char *secctx; + int err; _enter(",%s", args); @@ -585,16 +586,16 @@ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) return -EINVAL; } - if (cache->secctx) { + if (cache->have_secid) { pr_err("Second security context specified\n"); return -EINVAL; } - secctx = kstrdup(args, GFP_KERNEL); - if (!secctx) - return -ENOMEM; + err = security_secctx_to_secid(args, strlen(args), &cache->secid); + if (err) + return err; - cache->secctx = secctx; + cache->have_secid = true; return 0; } @@ -820,7 +821,6 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) put_cred(cache->cache_cred); kfree(cache->rootdirname); - kfree(cache->secctx); kfree(cache->tag); _leave(""); diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c index 1715d5ca2b2d..e341ade47dd8 100644 --- a/fs/cachefiles/error_inject.c +++ b/fs/cachefiles/error_inject.c @@ -11,7 +11,7 @@ unsigned int cachefiles_error_injection_state; static struct ctl_table_header *cachefiles_sysctl; -static struct ctl_table cachefiles_sysctls[] = { +static const struct ctl_table cachefiles_sysctls[] = { { .procname = "error_injection", .data = &cachefiles_error_injection_state, diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 7b99bd98de75..38c236e38cef 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -122,7 +122,6 @@ struct cachefiles_cache { #define CACHEFILES_STATE_CHANGED 3 /* T if state changed (poll trigger) */ #define CACHEFILES_ONDEMAND_MODE 4 /* T if in on-demand read mode */ char *rootdirname; /* name of cache root directory */ - char *secctx; /* LSM security context */ char *tag; /* cache binding tag */ refcount_t unbind_pincount;/* refcount to do daemon unbind */ struct xarray reqs; /* xarray of pending on-demand requests */ @@ -130,6 +129,8 @@ struct cachefiles_cache { struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ u32 ondemand_id_next; u32 msg_id_next; + u32 secid; /* LSM security id */ + bool have_secid; /* whether "secid" was set */ }; static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache) diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 6a821a959b59..92058ae43488 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "internal.h" struct cachefiles_kiocb { @@ -366,6 +367,7 @@ static int cachefiles_write(struct netfs_cache_resources *cres, if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) { if (term_func) term_func(term_func_priv, -ENOBUFS, false); + trace_netfs_sreq(term_func_priv, netfs_sreq_trace_cache_nowrite); return -ENOBUFS; } @@ -695,6 +697,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) iov_iter_truncate(&subreq->io_iter, len); } + trace_netfs_sreq(subreq, netfs_sreq_trace_cache_prepare); cachefiles_begin_secure(cache, &saved_cred); ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres), &start, &len, len, true); @@ -704,6 +707,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) return; } + trace_netfs_sreq(subreq, netfs_sreq_trace_cache_write); cachefiles_write(&subreq->rreq->cache_resources, subreq->start, &subreq->io_iter, netfs_write_subrequest_terminated, subreq); diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c index fe777164f1d8..fc6611886b3b 100644 --- a/fs/cachefiles/security.c +++ b/fs/cachefiles/security.c @@ -18,7 +18,7 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) struct cred *new; int ret; - _enter("{%s}", cache->secctx); + _enter("{%u}", cache->have_secid ? cache->secid : 0); new = prepare_kernel_cred(current); if (!new) { @@ -26,8 +26,8 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) goto error; } - if (cache->secctx) { - ret = set_security_override_from_ctx(new, cache->secctx); + if (cache->have_secid) { + ret = set_security_override(new, cache->secid); if (ret < 0) { put_cred(new); pr_err("Security denies permission to nominate security context: error %d\n", diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 7c6f260a3be5..52383b1d0ba6 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -77,6 +77,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) trace_cachefiles_vfs_error(object, file_inode(file), ret, cachefiles_trace_setxattr_error); trace_cachefiles_coherency(object, file_inode(file)->i_ino, + be64_to_cpup((__be64 *)buf->data), buf->content, cachefiles_coherency_set_fail); if (ret != -ENOMEM) @@ -85,6 +86,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) "Failed to set xattr with error %d", ret); } else { trace_cachefiles_coherency(object, file_inode(file)->i_ino, + be64_to_cpup((__be64 *)buf->data), buf->content, cachefiles_coherency_set_ok); } @@ -126,7 +128,10 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file object, "Failed to read aux with error %zd", xlen); why = cachefiles_coherency_check_xattr; - } else if (buf->type != CACHEFILES_COOKIE_TYPE_DATA) { + goto out; + } + + if (buf->type != CACHEFILES_COOKIE_TYPE_DATA) { why = cachefiles_coherency_check_type; } else if (memcmp(buf->data, p, len) != 0) { why = cachefiles_coherency_check_aux; @@ -141,7 +146,9 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file ret = 0; } +out: trace_cachefiles_coherency(object, file_inode(file)->i_ino, + be64_to_cpup((__be64 *)buf->data), buf->content, why); kfree(buf); return ret; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 85936f6d2bf7..f5224a566b69 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -223,10 +223,13 @@ static void finish_netfs_read(struct ceph_osd_request *req) subreq->len, i_size_read(req->r_inode)); /* no object means success but no data */ - if (err == -ENOENT) + if (err == -ENOENT) { + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); err = 0; - else if (err == -EBLOCKLISTED) + } else if (err == -EBLOCKLISTED) { fsc->blocklisted = true; + } if (err >= 0) { if (sparse && err > 0) @@ -242,6 +245,8 @@ static void finish_netfs_read(struct ceph_osd_request *req) if (err > subreq->len) err = subreq->len; } + if (err > 0) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); } if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) { @@ -253,8 +258,9 @@ static void finish_netfs_read(struct ceph_osd_request *req) subreq->transferred = err; err = 0; } + subreq->error = err; trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress); - netfs_read_subreq_terminated(subreq, err, false); + netfs_read_subreq_terminated(subreq); iput(req->r_inode); ceph_dec_osd_stopping_blocker(fsc->mdsc); } @@ -314,7 +320,9 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) ceph_mdsc_put_request(req); out: - netfs_read_subreq_terminated(subreq, err, false); + subreq->error = err; + trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress); + netfs_read_subreq_terminated(subreq); return true; } @@ -426,8 +434,10 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) ceph_osdc_start_request(req->r_osdc, req); out: ceph_osdc_put_request(req); - if (err) - netfs_read_subreq_terminated(subreq, err, false); + if (err) { + subreq->error = err; + netfs_read_subreq_terminated(subreq); + } doutc(cl, "%llx.%llx result %d\n", ceph_vinop(inode), err); } diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index fdf9dc15eafa..fdd404fc8112 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -412,7 +412,7 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc) void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) { - char name[100]; + char name[NAME_MAX]; doutc(fsc->client, "begin\n"); fsc->debugfs_congestion_kb = diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 0bf388e07a02..62e99e65250d 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1940,29 +1940,19 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry, /* * Check if cached dentry can be trusted. */ -static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) +static int ceph_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(dentry->d_sb)->mdsc; struct ceph_client *cl = mdsc->fsc->client; int valid = 0; - struct dentry *parent; - struct inode *dir, *inode; + struct inode *inode; - valid = fscrypt_d_revalidate(dentry, flags); + valid = fscrypt_d_revalidate(dir, name, dentry, flags); if (valid <= 0) return valid; - if (flags & LOOKUP_RCU) { - parent = READ_ONCE(dentry->d_parent); - dir = d_inode_rcu(parent); - if (!dir) - return -ECHILD; - inode = d_inode_rcu(dentry); - } else { - parent = dget_parent(dentry); - dir = d_inode(parent); - inode = d_inode(dentry); - } + inode = d_inode_rcu(dentry); doutc(cl, "%p '%pd' inode %p offset 0x%llx nokey %d\n", dentry, dentry, inode, ceph_dentry(dentry)->offset, @@ -2008,6 +1998,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) req->r_parent = dir; ihold(dir); + req->r_dname = name; + mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED; if (ceph_security_xattr_wanted(dir)) mask |= CEPH_CAP_XATTR_SHARED; @@ -2038,9 +2030,6 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) doutc(cl, "%p '%pd' %s\n", dentry, dentry, valid ? "valid" : "invalid"); if (!valid) ceph_dir_clear_complete(dir); - - if (!(flags & LOOKUP_RCU)) - dput(parent); return valid; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 4b8d59ebda00..851d70200c6b 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1066,7 +1066,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, if (ceph_inode_is_shutdown(inode)) return -EIO; - if (!len) + if (!len || !i_size) return 0; /* * flush any page cache pages in this range. this @@ -1086,7 +1086,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, int num_pages; size_t page_off; bool more; - int idx; + int idx = 0; size_t left; struct ceph_osd_req_op *op; u64 read_off = off; @@ -1116,6 +1116,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, len = read_off + read_len - off; more = len < iov_iter_count(to); + op = &req->r_ops[0]; + if (sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + num_pages = calc_pages_for(read_off, read_len); page_off = offset_in_page(off); pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL); @@ -1127,17 +1137,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, osd_req_op_extent_osd_data_pages(req, 0, pages, read_len, offset_in_page(read_off), - false, false); - - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } + false, true); ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); @@ -1160,7 +1160,14 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, else if (ret == -ENOENT) ret = 0; - if (ret > 0 && IS_ENCRYPTED(inode)) { + if (ret < 0) { + ceph_osdc_put_request(req); + if (ret == -EBLOCKLISTED) + fsc->blocklisted = true; + break; + } + + if (IS_ENCRYPTED(inode)) { int fret; fret = ceph_fscrypt_decrypt_extents(inode, pages, @@ -1186,10 +1193,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret = min_t(ssize_t, fret, len); } - ceph_osdc_put_request(req); - /* Short read but not EOF? Zero out the remainder. */ - if (ret >= 0 && ret < len && (off + ret < i_size)) { + if (ret < len && (off + ret < i_size)) { int zlen = min(len - ret, i_size - off - ret); int zoff = page_off + ret; @@ -1199,13 +1204,11 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret += zlen; } - idx = 0; - if (ret <= 0) - left = 0; - else if (off + ret > i_size) - left = i_size - off; + if (off + ret > i_size) + left = (i_size > off) ? i_size - off : 0; else left = ret; + while (left > 0) { size_t plen, copied; @@ -1221,13 +1224,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, break; } } - ceph_release_page_vector(pages, num_pages); - if (ret < 0) { - if (ret == -EBLOCKLISTED) - fsc->blocklisted = true; - break; - } + ceph_osdc_put_request(req); if (off >= i_size || !more) break; @@ -1553,6 +1551,16 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, break; } + op = &req->r_ops[0]; + if (!write && sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, size); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages); if (len < 0) { ceph_osdc_put_request(req); @@ -1562,6 +1570,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (len != size) osd_req_op_extent_update(req, 0, len); + osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); + /* * To simplify error handling, allow AIO when IO within i_size * or IO can be satisfied by single OSD request. @@ -1593,17 +1603,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, req->r_mtime = mtime; } - osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, size); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } - if (aio_req) { aio_req->total_len += len; aio_req->num_reqs++; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 219a2cc2bf3c..54b3421501e9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2621,6 +2621,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) { struct inode *dir = req->r_parent; struct dentry *dentry = req->r_dentry; + const struct qstr *name = req->r_dname; u8 *cryptbuf = NULL; u32 len = 0; int ret = 0; @@ -2641,8 +2642,10 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) if (!fscrypt_has_encryption_key(dir)) goto success; - if (!fscrypt_fname_encrypted_size(dir, dentry->d_name.len, NAME_MAX, - &len)) { + if (!name) + name = &dentry->d_name; + + if (!fscrypt_fname_encrypted_size(dir, name->len, NAME_MAX, &len)) { WARN_ON_ONCE(1); return ERR_PTR(-ENAMETOOLONG); } @@ -2657,7 +2660,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) if (!cryptbuf) return ERR_PTR(-ENOMEM); - ret = fscrypt_fname_encrypt(dir, &dentry->d_name, cryptbuf, len); + ret = fscrypt_fname_encrypt(dir, name, cryptbuf, len); if (ret) { kfree(cryptbuf); return ERR_PTR(ret); @@ -2800,12 +2803,11 @@ retry: if (pos < 0) { /* - * A rename didn't occur, but somehow we didn't end up where - * we thought we would. Throw a warning and try again. + * The path is longer than PATH_MAX and this function + * cannot ever succeed. Creating paths that long is + * possible with Ceph, but Linux cannot use them. */ - pr_warn_client(cl, "did not end path lookup where expected (pos = %d)\n", - pos); - goto retry; + return ERR_PTR(-ENAMETOOLONG); } *pbase = base; @@ -2946,12 +2948,12 @@ static struct ceph_mds_request_head_legacy * find_legacy_request_head(void *p, u64 features) { bool legacy = !(features & CEPH_FEATURE_FS_BTIME); - struct ceph_mds_request_head_old *ohead; + struct ceph_mds_request_head *head; if (legacy) return (struct ceph_mds_request_head_legacy *)p; - ohead = (struct ceph_mds_request_head_old *)p; - return (struct ceph_mds_request_head_legacy *)&ohead->oldest_client_tid; + head = (struct ceph_mds_request_head *)p; + return (struct ceph_mds_request_head_legacy *)&head->oldest_client_tid; } /* @@ -3021,7 +3023,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, if (legacy) len = sizeof(struct ceph_mds_request_head_legacy); else if (request_head_version == 1) - len = sizeof(struct ceph_mds_request_head_old); + len = offsetofend(struct ceph_mds_request_head, args); else if (request_head_version == 2) len = offsetofend(struct ceph_mds_request_head, ext_num_fwd); else @@ -3105,11 +3107,11 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, msg->hdr.version = cpu_to_le16(3); p = msg->front.iov_base + sizeof(*lhead); } else if (request_head_version == 1) { - struct ceph_mds_request_head_old *ohead = msg->front.iov_base; + struct ceph_mds_request_head *nhead = msg->front.iov_base; msg->hdr.version = cpu_to_le16(4); - ohead->version = cpu_to_le16(1); - p = msg->front.iov_base + sizeof(*ohead); + nhead->version = cpu_to_le16(1); + p = msg->front.iov_base + offsetofend(struct ceph_mds_request_head, args); } else if (request_head_version == 2) { struct ceph_mds_request_head *nhead = msg->front.iov_base; @@ -3266,7 +3268,7 @@ static int __prepare_send_request(struct ceph_mds_session *session, * so we limit to retry at most 256 times. */ if (req->r_attempts) { - old_max_retry = sizeof_field(struct ceph_mds_request_head_old, + old_max_retry = sizeof_field(struct ceph_mds_request_head, num_retry); old_max_retry = 1 << (old_max_retry * BITS_PER_BYTE); if ((old_version && req->r_attempts >= old_max_retry) || @@ -5691,18 +5693,18 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, * * All the other cases --> mismatch */ + bool path_matched = true; char *first = strstr(_tpath, auth->match.path); - if (first != _tpath) { - if (free_tpath) - kfree(_tpath); - return 0; + if (first != _tpath || + (tlen > len && _tpath[len] != '/')) { + path_matched = false; } - if (tlen > len && _tpath[len] != '/') { - if (free_tpath) - kfree(_tpath); + if (free_tpath) + kfree(_tpath); + + if (!path_matched) return 0; - } } } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 38bb7e0d2d79..7c9fee9e80d4 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -299,6 +299,8 @@ struct ceph_mds_request { struct inode *r_target_inode; /* resulting inode */ struct inode *r_new_inode; /* new inode (for creates) */ + const struct qstr *r_dname; /* stable name (for ->d_revalidate) */ + #define CEPH_MDS_R_DIRECT_IS_HASH (1) /* r_direct_hash is valid */ #define CEPH_MDS_R_ABORTED (2) /* call was aborted */ #define CEPH_MDS_R_GOT_UNSAFE (3) /* got an unsafe reply */ diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 06ee397e0c3a..d90eda19bcc4 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -166,7 +166,7 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc, if (IS_ERR(in)) { doutc(cl, "Can't lookup inode %llx (err: %ld)\n", realm->ino, PTR_ERR(in)); - qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */ + qri->timeout = jiffies + secs_to_jiffies(60); /* XXX */ } else { qri->timeout = 0; qri->inode = in; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index de03cd6eb86e..4344e1f11806 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -431,6 +431,8 @@ static int ceph_parse_mount_param(struct fs_context *fc, switch (token) { case Opt_snapdirname: + if (strlen(param->string) > NAME_MAX) + return invalfc(fc, "snapdirname too long"); kfree(fsopt->snapdir_name); fsopt->snapdir_name = param->string; param->string = NULL; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index af14ec382246..7fa1e7be50e4 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1132,8 +1132,7 @@ struct ceph_acl_sec_ctx { void *acl; #endif #ifdef CONFIG_CEPH_FS_SECURITY_LABEL - void *sec_ctx; - u32 sec_ctxlen; + struct lsm_context lsmctx; #endif #ifdef CONFIG_FS_ENCRYPTION struct ceph_fscrypt_auth *fscrypt_auth; diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 1a9f12204666..537165db4519 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1383,8 +1383,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, int err; err = security_dentry_init_security(dentry, mode, &dentry->d_name, - &name, &as_ctx->sec_ctx, - &as_ctx->sec_ctxlen); + &name, &as_ctx->lsmctx); if (err < 0) { WARN_ON_ONCE(err != -EOPNOTSUPP); err = 0; /* do nothing */ @@ -1409,7 +1408,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, */ name_len = strlen(name); err = ceph_pagelist_reserve(pagelist, - 4 * 2 + name_len + as_ctx->sec_ctxlen); + 4 * 2 + name_len + as_ctx->lsmctx.len); if (err) goto out; @@ -1432,8 +1431,9 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, ceph_pagelist_encode_32(pagelist, name_len); ceph_pagelist_append(pagelist, name, name_len); - ceph_pagelist_encode_32(pagelist, as_ctx->sec_ctxlen); - ceph_pagelist_append(pagelist, as_ctx->sec_ctx, as_ctx->sec_ctxlen); + ceph_pagelist_encode_32(pagelist, as_ctx->lsmctx.len); + ceph_pagelist_append(pagelist, as_ctx->lsmctx.context, + as_ctx->lsmctx.len); err = 0; out: @@ -1451,7 +1451,7 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx) posix_acl_release(as_ctx->default_acl); #endif #ifdef CONFIG_CEPH_FS_SECURITY_LABEL - security_release_secctx(as_ctx->sec_ctx, as_ctx->sec_ctxlen); + security_release_secctx(&as_ctx->lsmctx); #endif #ifdef CONFIG_FS_ENCRYPTION kfree(as_ctx->fscrypt_auth); diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 4e552ba7bd43..a3e2dfeedfbf 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -445,7 +445,8 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx) } /* called when a cache lookup succeeds */ -static int coda_dentry_revalidate(struct dentry *de, unsigned int flags) +static int coda_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *de, unsigned int flags) { struct inode *inode; struct coda_inode_info *cii; diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c index 9f2d5743e2c8..0df46f09b6cc 100644 --- a/fs/coda/sysctl.c +++ b/fs/coda/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *fs_table_header; -static struct ctl_table coda_table[] = { +static const struct ctl_table coda_table[] = { { .procname = "timeout", .data = &coda_timeout, diff --git a/fs/coredump.c b/fs/coredump.c index d48edb37bc35..591700e1b2ce 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -995,7 +995,7 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write, static const unsigned int core_file_note_size_min = CORE_FILE_NOTE_SIZE_DEFAULT; static const unsigned int core_file_note_size_max = CORE_FILE_NOTE_SIZE_MAX; -static struct ctl_table coredump_sysctls[] = { +static const struct ctl_table coredump_sysctls[] = { { .procname = "core_uses_pid", .data = &core_uses_pid, diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 0ad52fbe51c9..010f9c0a4c2f 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -574,11 +574,10 @@ EXPORT_SYMBOL_GPL(fscrypt_fname_siphash); * Validate dentries in encrypted directories to make sure we aren't potentially * caching stale dentries after a key has been added. */ -int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) +int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - struct dentry *dir; int err; - int valid; /* * Plaintext names are always valid, since fscrypt doesn't support @@ -591,30 +590,21 @@ int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) /* * No-key name; valid if the directory's key is still unavailable. * - * Although fscrypt forbids rename() on no-key names, we still must use - * dget_parent() here rather than use ->d_parent directly. That's - * because a corrupted fs image may contain directory hard links, which - * the VFS handles by moving the directory's dentry tree in the dcache - * each time ->lookup() finds the directory and it already has a dentry - * elsewhere. Thus ->d_parent can be changing, and we must safely grab - * a reference to some ->d_parent to prevent it from being freed. + * Note in RCU mode we have to bail if we get here - + * fscrypt_get_encryption_info() may block. */ if (flags & LOOKUP_RCU) return -ECHILD; - dir = dget_parent(dentry); /* * Pass allow_unsupported=true, so that files with an unsupported * encryption policy can be deleted. */ - err = fscrypt_get_encryption_info(d_inode(dir), true); - valid = !fscrypt_has_encryption_key(d_inode(dir)); - dput(dir); - + err = fscrypt_get_encryption_info(dir, true); if (err < 0) return err; - return valid; + return !fscrypt_has_encryption_key(dir); } EXPORT_SYMBOL_GPL(fscrypt_d_revalidate); diff --git a/fs/dcache.c b/fs/dcache.c index b4d5e9e1e43d..9cc0d47da321 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -192,7 +192,7 @@ static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_dcache_sysctls[] = { +static const struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, @@ -295,12 +295,16 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c return dentry_string_cmp(cs, ct, tcount); } +/* + * long names are allocated separately from dentry and never modified. + * Refcounted, freeing is RCU-delayed. See take_dentry_name_snapshot() + * for the reason why ->count and ->head can't be combined into a union. + * dentry_string_cmp() relies upon ->name[] being word-aligned. + */ struct external_name { - union { - atomic_t count; - struct rcu_head head; - } u; - unsigned char name[]; + atomic_t count; + struct rcu_head head; + unsigned char name[] __aligned(sizeof(unsigned long)); }; static inline struct external_name *external_name(struct dentry *dentry) @@ -324,31 +328,45 @@ static void __d_free_external(struct rcu_head *head) static inline int dname_external(const struct dentry *dentry) { - return dentry->d_name.name != dentry->d_iname; + return dentry->d_name.name != dentry->d_shortname.string; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { - spin_lock(&dentry->d_lock); - name->name = dentry->d_name; - if (unlikely(dname_external(dentry))) { - atomic_inc(&external_name(dentry)->u.count); + unsigned seq; + const unsigned char *s; + + rcu_read_lock(); +retry: + seq = read_seqcount_begin(&dentry->d_seq); + s = READ_ONCE(dentry->d_name.name); + name->name.hash_len = dentry->d_name.hash_len; + name->name.name = name->inline_name.string; + if (likely(s == dentry->d_shortname.string)) { + name->inline_name = dentry->d_shortname; } else { - memcpy(name->inline_name, dentry->d_iname, - dentry->d_name.len + 1); - name->name.name = name->inline_name; + struct external_name *p; + p = container_of(s, struct external_name, name[0]); + // get a valid reference + if (unlikely(!atomic_inc_not_zero(&p->count))) + goto retry; + name->name.name = s; } - spin_unlock(&dentry->d_lock); + if (read_seqcount_retry(&dentry->d_seq, seq)) { + release_dentry_name_snapshot(name); + goto retry; + } + rcu_read_unlock(); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { - if (unlikely(name->name.name != name->inline_name)) { + if (unlikely(name->name.name != name->inline_name.string)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); - if (unlikely(atomic_dec_and_test(&p->u.count))) - kfree_rcu(p, u.head); + if (unlikely(atomic_dec_and_test(&p->count))) + kfree_rcu(p, head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); @@ -386,7 +404,7 @@ static void dentry_free(struct dentry *dentry) WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); - if (likely(atomic_dec_and_test(&p->u.count))) { + if (likely(atomic_dec_and_test(&p->count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } @@ -1654,10 +1672,10 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ - dentry->d_iname[DNAME_INLINE_LEN-1] = 0; + dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; - dname = dentry->d_iname; + dname = dentry->d_shortname.string; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, @@ -1667,10 +1685,10 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) kmem_cache_free(dentry_cache, dentry); return NULL; } - atomic_set(&p->u.count, 1); + atomic_set(&p->count, 1); dname = p->name; } else { - dname = dentry->d_iname; + dname = dentry->d_shortname.string; } dentry->d_name.len = name->len; @@ -1681,9 +1699,8 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ - dentry->d_lockref.count = 1; dentry->d_flags = 0; - spin_lock_init(&dentry->d_lock); + lockref_init(&dentry->d_lockref, 1); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; @@ -2729,10 +2746,9 @@ static void swap_names(struct dentry *dentry, struct dentry *target) * dentry:internal, target:external. Steal target's * storage and make target internal. */ - memcpy(target->d_iname, dentry->d_name.name, - dentry->d_name.len + 1); dentry->d_name.name = target->d_name.name; - target->d_name.name = target->d_iname; + target->d_shortname = dentry->d_shortname; + target->d_name.name = target->d_shortname.string; } } else { if (unlikely(dname_external(dentry))) { @@ -2740,20 +2756,16 @@ static void swap_names(struct dentry *dentry, struct dentry *target) * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ - memcpy(dentry->d_iname, target->d_name.name, - target->d_name.len + 1); target->d_name.name = dentry->d_name.name; - dentry->d_name.name = dentry->d_iname; + dentry->d_shortname = target->d_shortname; + dentry->d_name.name = dentry->d_shortname.string; } else { /* * Both are internal. */ - unsigned int i; - BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); - for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { - swap(((long *) &dentry->d_iname)[i], - ((long *) &target->d_iname)[i]); - } + for (int i = 0; i < DNAME_INLINE_WORDS; i++) + swap(dentry->d_shortname.words[i], + target->d_shortname.words[i]); } } swap(dentry->d_name.hash_len, target->d_name.hash_len); @@ -2765,16 +2777,15 @@ static void copy_name(struct dentry *dentry, struct dentry *target) if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { - atomic_inc(&external_name(target)->u.count); + atomic_inc(&external_name(target)->count); dentry->d_name = target->d_name; } else { - memcpy(dentry->d_iname, target->d_name.name, - target->d_name.len + 1); - dentry->d_name.name = dentry->d_iname; + dentry->d_shortname = target->d_shortname; + dentry->d_name.name = dentry->d_shortname.string; dentry->d_name.hash_len = target->d_name.hash_len; } - if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) - kfree_rcu(old_name, u.head); + if (old_name && likely(atomic_dec_and_test(&old_name->count))) + kfree_rcu(old_name, head); } /* @@ -2955,7 +2966,12 @@ static int __d_unalias(struct dentry *dentry, struct dentry *alias) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: + if (alias->d_op->d_unalias_trylock && + !alias->d_op->d_unalias_trylock(alias)) + goto out_err; __d_move(alias, dentry, false); + if (alias->d_op->d_unalias_unlock) + alias->d_op->d_unalias_unlock(alias); ret = 0; out_err: if (m2) @@ -3103,12 +3119,12 @@ void d_mark_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; - BUG_ON(dentry->d_name.name != dentry->d_iname || + BUG_ON(dname_external(dentry) || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - dentry->d_name.len = sprintf(dentry->d_iname, "#%llu", + dentry->d_name.len = sprintf(dentry->d_shortname.string, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); @@ -3196,7 +3212,7 @@ static void __init dcache_init(void) */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, - d_iname); + d_shortname.string); /* Hash may have been set up in dcache_init_early */ if (!hashdist) diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 47dc96dfe386..69e9ddcb113d 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -47,11 +47,17 @@ const struct file_operations debugfs_noop_file_operations = { #define F_DENTRY(filp) ((filp)->f_path.dentry) +const void *debugfs_get_aux(const struct file *file) +{ + return DEBUGFS_I(file_inode(file))->aux; +} +EXPORT_SYMBOL_GPL(debugfs_get_aux); + const struct file_operations *debugfs_real_fops(const struct file *filp) { struct debugfs_fsdata *fsd = F_DENTRY(filp)->d_fsdata; - if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) { + if (!fsd) { /* * Urgh, we've been called w/o a protecting * debugfs_file_get(). @@ -64,22 +70,13 @@ const struct file_operations *debugfs_real_fops(const struct file *filp) } EXPORT_SYMBOL_GPL(debugfs_real_fops); -/** - * debugfs_file_get - mark the beginning of file data access - * @dentry: the dentry object whose data is being accessed. - * - * Up to a matching call to debugfs_file_put(), any successive call - * into the file removing functions debugfs_remove() and - * debugfs_remove_recursive() will block. Since associated private - * file data may only get freed after a successful return of any of - * the removal functions, you may safely access it after a successful - * call to debugfs_file_get() without worrying about lifetime issues. - * - * If -%EIO is returned, the file has already been removed and thus, - * it is not safe to access any of its data. If, on the other hand, - * it is allowed to access the file data, zero is returned. - */ -int debugfs_file_get(struct dentry *dentry) +enum dbgfs_get_mode { + DBGFS_GET_ALREADY, + DBGFS_GET_REGULAR, + DBGFS_GET_SHORT, +}; + +static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode) { struct debugfs_fsdata *fsd; void *d_fsd; @@ -93,32 +90,55 @@ int debugfs_file_get(struct dentry *dentry) return -EINVAL; d_fsd = READ_ONCE(dentry->d_fsdata); - if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) { + if (d_fsd) { fsd = d_fsd; } else { + struct inode *inode = dentry->d_inode; + unsigned int methods = 0; + + if (WARN_ON(mode == DBGFS_GET_ALREADY)) + return -EINVAL; + fsd = kmalloc(sizeof(*fsd), GFP_KERNEL); if (!fsd) return -ENOMEM; - if ((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT) { + if (mode == DBGFS_GET_SHORT) { + const struct debugfs_short_fops *ops; + ops = fsd->short_fops = DEBUGFS_I(inode)->short_fops; + if (ops->llseek) + methods |= HAS_LSEEK; + if (ops->read) + methods |= HAS_READ; + if (ops->write) + methods |= HAS_WRITE; fsd->real_fops = NULL; - fsd->short_fops = (void *)((unsigned long)d_fsd & - ~(DEBUGFS_FSDATA_IS_REAL_FOPS_BIT | - DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT)); } else { - fsd->real_fops = (void *)((unsigned long)d_fsd & - ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); + const struct file_operations *ops; + ops = fsd->real_fops = DEBUGFS_I(inode)->real_fops; + if (ops->llseek) + methods |= HAS_LSEEK; + if (ops->read) + methods |= HAS_READ; + if (ops->write) + methods |= HAS_WRITE; + if (ops->unlocked_ioctl) + methods |= HAS_IOCTL; + if (ops->poll) + methods |= HAS_POLL; fsd->short_fops = NULL; } + fsd->methods = methods; refcount_set(&fsd->active_users, 1); init_completion(&fsd->active_users_drained); INIT_LIST_HEAD(&fsd->cancellations); mutex_init(&fsd->cancellations_mtx); - if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd) { + d_fsd = cmpxchg(&dentry->d_fsdata, NULL, fsd); + if (d_fsd) { mutex_destroy(&fsd->cancellations_mtx); kfree(fsd); - fsd = READ_ONCE(dentry->d_fsdata); + fsd = d_fsd; } } @@ -138,6 +158,26 @@ int debugfs_file_get(struct dentry *dentry) return 0; } + +/** + * debugfs_file_get - mark the beginning of file data access + * @dentry: the dentry object whose data is being accessed. + * + * Up to a matching call to debugfs_file_put(), any successive call + * into the file removing functions debugfs_remove() and + * debugfs_remove_recursive() will block. Since associated private + * file data may only get freed after a successful return of any of + * the removal functions, you may safely access it after a successful + * call to debugfs_file_get() without worrying about lifetime issues. + * + * If -%EIO is returned, the file has already been removed and thus, + * it is not safe to access any of its data. If, on the other hand, + * it is allowed to access the file data, zero is returned. + */ +int debugfs_file_get(struct dentry *dentry) +{ + return __debugfs_file_get(dentry, DBGFS_GET_ALREADY); +} EXPORT_SYMBOL_GPL(debugfs_file_get); /** @@ -195,8 +235,7 @@ void debugfs_enter_cancellation(struct file *file, return; fsd = READ_ONCE(dentry->d_fsdata); - if (WARN_ON(!fsd || - ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + if (WARN_ON(!fsd)) return; mutex_lock(&fsd->cancellations_mtx); @@ -227,8 +266,7 @@ void debugfs_leave_cancellation(struct file *file, return; fsd = READ_ONCE(dentry->d_fsdata); - if (WARN_ON(!fsd || - ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + if (WARN_ON(!fsd)) return; mutex_lock(&fsd->cancellations_mtx); @@ -267,7 +305,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp) const struct file_operations *real_fops = NULL; int r; - r = debugfs_file_get(dentry); + r = __debugfs_file_get(dentry, DBGFS_GET_REGULAR); if (r) return r == -EIO ? -ENOENT : r; @@ -309,13 +347,16 @@ const struct file_operations debugfs_open_proxy_file_operations = { #define PROTO(args...) args #define ARGS(args...) args -#define FULL_PROXY_FUNC(name, ret_type, filp, proto, args) \ +#define FULL_PROXY_FUNC(name, ret_type, filp, proto, args, bit, ret) \ static ret_type full_proxy_ ## name(proto) \ { \ - struct dentry *dentry = F_DENTRY(filp); \ + struct dentry *dentry = F_DENTRY(filp); \ + struct debugfs_fsdata *fsd = dentry->d_fsdata; \ const struct file_operations *real_fops; \ ret_type r; \ \ + if (!(fsd->methods & bit)) \ + return ret; \ r = debugfs_file_get(dentry); \ if (unlikely(r)) \ return r; \ @@ -325,17 +366,18 @@ static ret_type full_proxy_ ## name(proto) \ return r; \ } -#define FULL_PROXY_FUNC_BOTH(name, ret_type, filp, proto, args) \ +#define FULL_PROXY_FUNC_BOTH(name, ret_type, filp, proto, args, bit, ret) \ static ret_type full_proxy_ ## name(proto) \ { \ struct dentry *dentry = F_DENTRY(filp); \ - struct debugfs_fsdata *fsd; \ + struct debugfs_fsdata *fsd = dentry->d_fsdata; \ ret_type r; \ \ + if (!(fsd->methods & bit)) \ + return ret; \ r = debugfs_file_get(dentry); \ if (unlikely(r)) \ return r; \ - fsd = dentry->d_fsdata; \ if (fsd->real_fops) \ r = fsd->real_fops->name(args); \ else \ @@ -346,29 +388,32 @@ static ret_type full_proxy_ ## name(proto) \ FULL_PROXY_FUNC_BOTH(llseek, loff_t, filp, PROTO(struct file *filp, loff_t offset, int whence), - ARGS(filp, offset, whence)); + ARGS(filp, offset, whence), HAS_LSEEK, -ESPIPE); FULL_PROXY_FUNC_BOTH(read, ssize_t, filp, PROTO(struct file *filp, char __user *buf, size_t size, loff_t *ppos), - ARGS(filp, buf, size, ppos)); + ARGS(filp, buf, size, ppos), HAS_READ, -EINVAL); FULL_PROXY_FUNC_BOTH(write, ssize_t, filp, PROTO(struct file *filp, const char __user *buf, size_t size, loff_t *ppos), - ARGS(filp, buf, size, ppos)); + ARGS(filp, buf, size, ppos), HAS_WRITE, -EINVAL); FULL_PROXY_FUNC(unlocked_ioctl, long, filp, PROTO(struct file *filp, unsigned int cmd, unsigned long arg), - ARGS(filp, cmd, arg)); + ARGS(filp, cmd, arg), HAS_IOCTL, -ENOTTY); static __poll_t full_proxy_poll(struct file *filp, struct poll_table_struct *wait) { struct dentry *dentry = F_DENTRY(filp); + struct debugfs_fsdata *fsd = dentry->d_fsdata; __poll_t r = 0; const struct file_operations *real_fops; + if (!(fsd->methods & HAS_POLL)) + return DEFAULT_POLLMASK; if (debugfs_file_get(dentry)) return EPOLLHUP; @@ -380,9 +425,7 @@ static __poll_t full_proxy_poll(struct file *filp, static int full_proxy_release(struct inode *inode, struct file *filp) { - const struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = debugfs_real_fops(filp); - const struct file_operations *proxy_fops = filp->f_op; int r = 0; /* @@ -391,48 +434,21 @@ static int full_proxy_release(struct inode *inode, struct file *filp) * not to leak any resources. Releasers must not assume that * ->i_private is still being meaningful here. */ - if (real_fops && real_fops->release) + if (real_fops->release) r = real_fops->release(inode, filp); - replace_fops(filp, d_inode(dentry)->i_fop); - kfree(proxy_fops); fops_put(real_fops); return r; } -static void __full_proxy_fops_init(struct file_operations *proxy_fops, - struct debugfs_fsdata *fsd) -{ - proxy_fops->release = full_proxy_release; - - if ((fsd->real_fops && fsd->real_fops->llseek) || - (fsd->short_fops && fsd->short_fops->llseek)) - proxy_fops->llseek = full_proxy_llseek; - - if ((fsd->real_fops && fsd->real_fops->read) || - (fsd->short_fops && fsd->short_fops->read)) - proxy_fops->read = full_proxy_read; - - if ((fsd->real_fops && fsd->real_fops->write) || - (fsd->short_fops && fsd->short_fops->write)) - proxy_fops->write = full_proxy_write; - - if (fsd->real_fops && fsd->real_fops->poll) - proxy_fops->poll = full_proxy_poll; - - if (fsd->real_fops && fsd->real_fops->unlocked_ioctl) - proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl; -} - -static int full_proxy_open(struct inode *inode, struct file *filp) +static int full_proxy_open_regular(struct inode *inode, struct file *filp) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops; - struct file_operations *proxy_fops = NULL; struct debugfs_fsdata *fsd; int r; - r = debugfs_file_get(dentry); + r = __debugfs_file_get(dentry, DBGFS_GET_REGULAR); if (r) return r == -EIO ? -ENOENT : r; @@ -442,7 +458,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp) if (r) goto out; - if (real_fops && !fops_get(real_fops)) { + if (!fops_get(real_fops)) { #ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) { @@ -458,41 +474,52 @@ static int full_proxy_open(struct inode *inode, struct file *filp) goto out; } - proxy_fops = kzalloc(sizeof(*proxy_fops), GFP_KERNEL); - if (!proxy_fops) { - r = -ENOMEM; - goto free_proxy; - } - __full_proxy_fops_init(proxy_fops, fsd); - replace_fops(filp, proxy_fops); - - if (!real_fops || real_fops->open) { - if (real_fops) - r = real_fops->open(inode, filp); - else - r = simple_open(inode, filp); + if (real_fops->open) { + r = real_fops->open(inode, filp); if (r) { - replace_fops(filp, d_inode(dentry)->i_fop); - goto free_proxy; - } else if (filp->f_op != proxy_fops) { + fops_put(real_fops); + } else if (filp->f_op != &debugfs_full_proxy_file_operations) { /* No protection against file removal anymore. */ WARN(1, "debugfs file owner replaced proxy fops: %pd", dentry); - goto free_proxy; + fops_put(real_fops); } } - - goto out; -free_proxy: - kfree(proxy_fops); - fops_put(real_fops); out: debugfs_file_put(dentry); return r; } const struct file_operations debugfs_full_proxy_file_operations = { - .open = full_proxy_open, + .open = full_proxy_open_regular, + .release = full_proxy_release, + .llseek = full_proxy_llseek, + .read = full_proxy_read, + .write = full_proxy_write, + .poll = full_proxy_poll, + .unlocked_ioctl = full_proxy_unlocked_ioctl +}; + +static int full_proxy_open_short(struct inode *inode, struct file *filp) +{ + struct dentry *dentry = F_DENTRY(filp); + int r; + + r = __debugfs_file_get(dentry, DBGFS_GET_SHORT); + if (r) + return r == -EIO ? -ENOENT : r; + r = debugfs_locked_down(inode, filp, NULL); + if (!r) + r = simple_open(inode, filp); + debugfs_file_put(dentry); + return r; +} + +const struct file_operations debugfs_full_short_proxy_file_operations = { + .open = full_proxy_open_short, + .llseek = full_proxy_llseek, + .read = full_proxy_read, + .write = full_proxy_write, }; ssize_t debugfs_attr_read(struct file *file, char __user *buf, diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 38a9c7eb97e6..75715d8877ee 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -208,16 +208,34 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } +static struct kmem_cache *debugfs_inode_cachep __ro_after_init; + +static void init_once(void *foo) +{ + struct debugfs_inode_info *info = foo; + inode_init_once(&info->vfs_inode); +} + +static struct inode *debugfs_alloc_inode(struct super_block *sb) +{ + struct debugfs_inode_info *info; + info = alloc_inode_sb(sb, debugfs_inode_cachep, GFP_KERNEL); + if (!info) + return NULL; + return &info->vfs_inode; +} + static void debugfs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); - free_inode_nonrcu(inode); + kmem_cache_free(debugfs_inode_cachep, DEBUGFS_I(inode)); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .show_options = debugfs_show_options, + .alloc_inode = debugfs_alloc_inode, .free_inode = debugfs_free_inode, }; @@ -225,23 +243,18 @@ static void debugfs_release_dentry(struct dentry *dentry) { struct debugfs_fsdata *fsd = dentry->d_fsdata; - if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) - return; - - /* check it wasn't a dir (no fsdata) or automount (no real_fops) */ - if (fsd && fsd->real_fops) { + if (fsd) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } - kfree(fsd); } static struct vfsmount *debugfs_automount(struct path *path) { - struct debugfs_fsdata *fsd = path->dentry->d_fsdata; + struct inode *inode = path->dentry->d_inode; - return fsd->automount(path->dentry, d_inode(path->dentry)->i_private); + return DEBUGFS_I(inode)->automount(path->dentry, inode->i_private); } static const struct dentry_operations debugfs_dops = { @@ -411,6 +424,7 @@ static struct dentry *end_creating(struct dentry *dentry) static struct dentry *__debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, + const void *aux, const struct file_operations *proxy_fops, const void *real_fops) { @@ -441,9 +455,11 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, inode->i_private = data; inode->i_op = &debugfs_file_inode_operations; + if (!real_fops) + proxy_fops = &debugfs_noop_file_operations; inode->i_fop = proxy_fops; - dentry->d_fsdata = (void *)((unsigned long)real_fops | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); + DEBUGFS_I(inode)->raw = real_fops; + DEBUGFS_I(inode)->aux = aux; d_instantiate(dentry, inode); fsnotify_create(d_inode(dentry->d_parent), dentry); @@ -452,34 +468,23 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, struct dentry *debugfs_create_file_full(const char *name, umode_t mode, struct dentry *parent, void *data, + const void *aux, const struct file_operations *fops) { - if (WARN_ON((unsigned long)fops & - (DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) - return ERR_PTR(-EINVAL); - - return __debugfs_create_file(name, mode, parent, data, - fops ? &debugfs_full_proxy_file_operations : - &debugfs_noop_file_operations, + return __debugfs_create_file(name, mode, parent, data, aux, + &debugfs_full_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_full); struct dentry *debugfs_create_file_short(const char *name, umode_t mode, - struct dentry *parent, void *data, - const struct debugfs_short_fops *fops) + struct dentry *parent, void *data, + const void *aux, + const struct debugfs_short_fops *fops) { - if (WARN_ON((unsigned long)fops & - (DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) - return ERR_PTR(-EINVAL); - - return __debugfs_create_file(name, mode, parent, data, - fops ? &debugfs_full_proxy_file_operations : - &debugfs_noop_file_operations, - (const void *)((unsigned long)fops | - DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT)); + return __debugfs_create_file(name, mode, parent, data, aux, + &debugfs_full_short_proxy_file_operations, + fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_short); @@ -515,9 +520,8 @@ struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, const struct file_operations *fops) { - return __debugfs_create_file(name, mode, parent, data, - fops ? &debugfs_open_proxy_file_operations : - &debugfs_noop_file_operations, + return __debugfs_create_file(name, mode, parent, data, NULL, + &debugfs_open_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); @@ -627,23 +631,13 @@ struct dentry *debugfs_create_automount(const char *name, void *data) { struct dentry *dentry = start_creating(name, parent); - struct debugfs_fsdata *fsd; struct inode *inode; if (IS_ERR(dentry)) return dentry; - fsd = kzalloc(sizeof(*fsd), GFP_KERNEL); - if (!fsd) { - failed_creating(dentry); - return ERR_PTR(-ENOMEM); - } - - fsd->automount = f; - if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); - kfree(fsd); return ERR_PTR(-EPERM); } @@ -651,14 +645,13 @@ struct dentry *debugfs_create_automount(const char *name, if (unlikely(!inode)) { pr_err("out of free dentries, can not create automount '%s'\n", name); - kfree(fsd); return failed_creating(dentry); } make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; - dentry->d_fsdata = fsd; + DEBUGFS_I(inode)->automount = f; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); @@ -733,7 +726,7 @@ static void __debugfs_file_removed(struct dentry *dentry) */ smp_mb(); fsd = READ_ONCE(dentry->d_fsdata); - if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) + if (!fsd) return; /* if this was the last reference, we're done */ @@ -837,76 +830,70 @@ void debugfs_lookup_and_remove(const char *name, struct dentry *parent) EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); /** - * debugfs_rename - rename a file/directory in the debugfs filesystem - * @old_dir: a pointer to the parent dentry for the renamed object. This - * should be a directory dentry. - * @old_dentry: dentry of an object to be renamed. - * @new_dir: a pointer to the parent dentry where the object should be - * moved. This should be a directory dentry. - * @new_name: a pointer to a string containing the target name. + * debugfs_change_name - rename a file/directory in the debugfs filesystem + * @dentry: dentry of an object to be renamed. + * @fmt: format for new name * * This function renames a file/directory in debugfs. The target must not * exist for rename to succeed. * - * This function will return a pointer to old_dentry (which is updated to - * reflect renaming) if it succeeds. If an error occurs, ERR_PTR(-ERROR) - * will be returned. + * This function will return 0 on success and -E... on failure. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ -struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, - struct dentry *new_dir, const char *new_name) +int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, ...) { - int error; - struct dentry *dentry = NULL, *trap; + int error = 0; + const char *new_name; struct name_snapshot old_name; + struct dentry *parent, *target; + struct inode *dir; + va_list ap; - if (IS_ERR(old_dir)) - return old_dir; - if (IS_ERR(new_dir)) - return new_dir; - if (IS_ERR_OR_NULL(old_dentry)) - return old_dentry; + if (IS_ERR_OR_NULL(dentry)) + return 0; - trap = lock_rename(new_dir, old_dir); - /* Source or destination directories don't exist? */ - if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir)) - goto exit; - /* Source does not exist, cyclic rename, or mountpoint? */ - if (d_really_is_negative(old_dentry) || old_dentry == trap || - d_mountpoint(old_dentry)) - goto exit; - dentry = lookup_one_len(new_name, new_dir, strlen(new_name)); - /* Lookup failed, cyclic rename or target exists? */ - if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry)) - goto exit; + va_start(ap, fmt); + new_name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!new_name) + return -ENOMEM; - take_dentry_name_snapshot(&old_name, old_dentry); + parent = dget_parent(dentry); + dir = d_inode(parent); + inode_lock(dir); - error = simple_rename(&nop_mnt_idmap, d_inode(old_dir), old_dentry, - d_inode(new_dir), dentry, 0); - if (error) { - release_dentry_name_snapshot(&old_name); - goto exit; + take_dentry_name_snapshot(&old_name, dentry); + + if (WARN_ON_ONCE(dentry->d_parent != parent)) { + error = -EINVAL; + goto out; } - d_move(old_dentry, dentry); - fsnotify_move(d_inode(old_dir), d_inode(new_dir), &old_name.name, - d_is_dir(old_dentry), - NULL, old_dentry); + if (strcmp(old_name.name.name, new_name) == 0) + goto out; + target = lookup_one_len(new_name, parent, strlen(new_name)); + if (IS_ERR(target)) { + error = PTR_ERR(target); + goto out; + } + if (d_really_is_positive(target)) { + dput(target); + error = -EINVAL; + goto out; + } + simple_rename_timestamp(dir, dentry, dir, target); + d_move(dentry, target); + dput(target); + fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry); +out: release_dentry_name_snapshot(&old_name); - unlock_rename(new_dir, old_dir); - dput(dentry); - return old_dentry; -exit: - if (dentry && !IS_ERR(dentry)) - dput(dentry); - unlock_rename(new_dir, old_dir); - if (IS_ERR(dentry)) - return dentry; - return ERR_PTR(-EINVAL); + inode_unlock(dir); + dput(parent); + kfree_const(new_name); + return error; } -EXPORT_SYMBOL_GPL(debugfs_rename); +EXPORT_SYMBOL_GPL(debugfs_change_name); /** * debugfs_initialized - Tells whether debugfs has been registered @@ -942,12 +929,22 @@ static int __init debugfs_init(void) if (retval) return retval; - retval = register_filesystem(&debug_fs_type); - if (retval) + debugfs_inode_cachep = kmem_cache_create("debugfs_inode_cache", + sizeof(struct debugfs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, + init_once); + if (debugfs_inode_cachep == NULL) { sysfs_remove_mount_point(kernel_kobj, "debug"); - else - debugfs_registered = true; + return -ENOMEM; + } - return retval; + retval = register_filesystem(&debug_fs_type); + if (retval) { // Really not going to happen + sysfs_remove_mount_point(kernel_kobj, "debug"); + kmem_cache_destroy(debugfs_inode_cachep); + return retval; + } + debugfs_registered = true; + return 0; } core_initcall(debugfs_init); diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h index a3edfa4f0d8e..93483fe84425 100644 --- a/fs/debugfs/internal.h +++ b/fs/debugfs/internal.h @@ -11,42 +11,50 @@ struct file_operations; +struct debugfs_inode_info { + struct inode vfs_inode; + union { + const void *raw; + const struct file_operations *real_fops; + const struct debugfs_short_fops *short_fops; + debugfs_automount_t automount; + }; + const void *aux; +}; + +static inline struct debugfs_inode_info *DEBUGFS_I(struct inode *inode) +{ + return container_of(inode, struct debugfs_inode_info, vfs_inode); +} + /* declared over in file.c */ extern const struct file_operations debugfs_noop_file_operations; extern const struct file_operations debugfs_open_proxy_file_operations; extern const struct file_operations debugfs_full_proxy_file_operations; +extern const struct file_operations debugfs_full_short_proxy_file_operations; struct debugfs_fsdata { const struct file_operations *real_fops; const struct debugfs_short_fops *short_fops; - union { - /* automount_fn is used when real_fops is NULL */ - debugfs_automount_t automount; - struct { - refcount_t active_users; - struct completion active_users_drained; + struct { + refcount_t active_users; + struct completion active_users_drained; - /* protect cancellations */ - struct mutex cancellations_mtx; - struct list_head cancellations; - }; + /* protect cancellations */ + struct mutex cancellations_mtx; + struct list_head cancellations; + unsigned int methods; }; }; -/* - * A dentry's ->d_fsdata either points to the real fops or to a - * dynamically allocated debugfs_fsdata instance. - * In order to distinguish between these two cases, a real fops - * pointer gets its lowest bit set. - */ -#define DEBUGFS_FSDATA_IS_REAL_FOPS_BIT BIT(0) -/* - * A dentry's ->d_fsdata, when pointing to real fops, is with - * short fops instead of full fops. - */ -#define DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT BIT(1) +enum { + HAS_READ = 1, + HAS_WRITE = 2, + HAS_LSEEK = 4, + HAS_POLL = 8, + HAS_IOCTL = 16 +}; -/* Access BITS */ #define DEBUGFS_ALLOW_API BIT(0) #define DEBUGFS_ALLOW_MOUNT BIT(1) diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index b20e565b9c5e..1096ff8562fa 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -45,7 +45,7 @@ static int pty_limit_min; static int pty_limit_max = INT_MAX; static atomic_t pty_count = ATOMIC_INIT(0); -static struct ctl_table pty_table[] = { +static const struct ctl_table pty_table[] = { { .procname = "max", .maxlen = sizeof(int), diff --git a/fs/dlm/config.c b/fs/dlm/config.c index b2f21aa00719..cf9ba6fd7a28 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -935,7 +935,7 @@ int dlm_comm_seq(int nodeid, uint32_t *seq, bool locked) mutex_unlock(&clusters_root.subsys.su_mutex); } if (!cm) - return -EEXIST; + return -ENOENT; *seq = cm->seq; put_comm(cm); diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index fc1d710166e9..c8ff88f1cdcf 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -824,9 +824,12 @@ static int find_rsb_dir(struct dlm_ls *ls, const void *name, int len, r->res_first_lkid = 0; } - /* A dir record will not be on the scan list. */ - if (r->res_dir_nodeid != our_nodeid) - del_scan(ls, r); + /* we always deactivate scan timer for the rsb, when + * we move it out of the inactive state as rsb state + * can be changed and scan timers are only for inactive + * rsbs. + */ + del_scan(ls, r); list_move(&r->res_slow_list, &ls->ls_slow_active); rsb_clear_flag(r, RSB_INACTIVE); kref_init(&r->res_ref); /* ref is now used in active state */ @@ -989,10 +992,10 @@ static int find_rsb_nodir(struct dlm_ls *ls, const void *name, int len, r->res_nodeid = 0; } + del_scan(ls, r); list_move(&r->res_slow_list, &ls->ls_slow_active); rsb_clear_flag(r, RSB_INACTIVE); kref_init(&r->res_ref); - del_scan(ls, r); write_unlock_bh(&ls->ls_rsbtbl_lock); goto out; @@ -1337,9 +1340,13 @@ static int _dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, const char *na __dlm_master_lookup(ls, r, our_nodeid, from_nodeid, true, flags, r_nodeid, result); - /* A dir record rsb should never be on scan list. */ - /* Try to fix this with del_scan? */ - WARN_ON(!list_empty(&r->res_scan_list)); + /* A dir record rsb should never be on scan list. + * Except when we are the dir and master node. + * This function should only be called by the dir + * node. + */ + WARN_ON(!list_empty(&r->res_scan_list) && + r->res_master_nodeid != our_nodeid); write_unlock_bh(&ls->ls_rsbtbl_lock); @@ -1430,16 +1437,23 @@ static void deactivate_rsb(struct kref *kref) list_move(&r->res_slow_list, &ls->ls_slow_inactive); /* - * When the rsb becomes unused: - * - If it's not a dir record for a remote master rsb, - * then it is put on the scan list to be freed. - * - If it's a dir record for a remote master rsb, - * then it is kept in the inactive state until - * receive_remove() from the master node. + * When the rsb becomes unused, there are two possibilities: + * 1. Leave the inactive rsb in place (don't remove it). + * 2. Add it to the scan list to be removed. + * + * 1 is done when the rsb is acting as the dir record + * for a remotely mastered rsb. The rsb must be left + * in place as an inactive rsb to act as the dir record. + * + * 2 is done when a) the rsb is not the master and not the + * dir record, b) when the rsb is both the master and the + * dir record, c) when the rsb is master but not dir record. + * + * (If no directory is used, the rsb can always be removed.) */ - if (!dlm_no_directory(ls) && - (r->res_master_nodeid != our_nodeid) && - (dlm_dir_nodeid(r) != our_nodeid)) + if (dlm_no_directory(ls) || + (r->res_master_nodeid == our_nodeid || + dlm_dir_nodeid(r) != our_nodeid)) add_scan(ls, r); if (r->res_lvbptr) { diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index df40c3fd1070..d28141829c05 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -462,7 +462,8 @@ static bool dlm_lowcomms_con_has_addr(const struct connection *con, int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr) { struct connection *con; - bool ret, idx; + bool ret; + int idx; idx = srcu_read_lock(&connections_srcu); con = nodeid2con(nodeid, GFP_NOFS); diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c index acaa0825e9bb..1dfd5b81d831 100644 --- a/fs/ecryptfs/dentry.c +++ b/fs/ecryptfs/dentry.c @@ -17,7 +17,9 @@ /** * ecryptfs_d_revalidate - revalidate an ecryptfs dentry - * @dentry: The ecryptfs dentry + * @dir: inode of expected parent + * @name: expected name + * @dentry: dentry to revalidate * @flags: lookup flags * * Called when the VFS needs to revalidate a dentry. This @@ -28,7 +30,8 @@ * Returns 1 if valid, 0 otherwise. * */ -static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags) +static int ecryptfs_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry); int rc = 1; @@ -36,8 +39,15 @@ static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags) if (flags & LOOKUP_RCU) return -ECHILD; - if (lower_dentry->d_flags & DCACHE_OP_REVALIDATE) - rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags); + if (lower_dentry->d_flags & DCACHE_OP_REVALIDATE) { + struct inode *lower_dir = ecryptfs_inode_to_lower(dir); + struct name_snapshot n; + + take_dentry_name_snapshot(&n, lower_dentry); + rc = lower_dentry->d_op->d_revalidate(lower_dir, &n.name, + lower_dentry, flags); + release_dentry_name_snapshot(&n); + } if (d_really_is_positive(dentry)) { struct inode *inode = d_inode(dentry); diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 23c51d62f902..cb1b6d0c3454 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -36,28 +36,41 @@ static ssize_t efivarfs_file_write(struct file *file, if (IS_ERR(data)) return PTR_ERR(data); + inode_lock(inode); + if (var->removed) { + /* + * file got removed; don't allow a set. Caused by an + * unsuccessful create or successful delete write + * racing with us. + */ + bytes = -EIO; + goto out; + } + bytes = efivar_entry_set_get_size(var, attributes, &datasize, data, &set); - if (!set && bytes) { + if (!set) { if (bytes == -ENOENT) bytes = -EIO; goto out; } if (bytes == -ENOENT) { - drop_nlink(inode); - d_delete(file->f_path.dentry); - dput(file->f_path.dentry); + /* + * zero size signals to release that the write deleted + * the variable + */ + i_size_write(inode, 0); } else { - inode_lock(inode); i_size_write(inode, datasize + sizeof(attributes)); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); - inode_unlock(inode); } bytes = count; out: + inode_unlock(inode); + kfree(data); return bytes; @@ -106,8 +119,36 @@ out_free: return size; } +static int efivarfs_file_release(struct inode *inode, struct file *file) +{ + struct efivar_entry *var = inode->i_private; + + inode_lock(inode); + var->removed = (--var->open_count == 0 && i_size_read(inode) == 0); + inode_unlock(inode); + + if (var->removed) + simple_recursive_removal(file->f_path.dentry, NULL); + + return 0; +} + +static int efivarfs_file_open(struct inode *inode, struct file *file) +{ + struct efivar_entry *entry = inode->i_private; + + file->private_data = entry; + + inode_lock(inode); + entry->open_count++; + inode_unlock(inode); + + return 0; +} + const struct file_operations efivarfs_file_operations = { - .open = simple_open, - .read = efivarfs_file_read, - .write = efivarfs_file_write, + .open = efivarfs_file_open, + .read = efivarfs_file_read, + .write = efivarfs_file_write, + .release = efivarfs_file_release, }; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index ec23da8405ff..98a7299a9ee9 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -77,39 +77,34 @@ static bool efivarfs_valid_name(const char *str, int len) static int efivarfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - struct efivarfs_fs_info *info = dir->i_sb->s_fs_info; struct inode *inode = NULL; struct efivar_entry *var; int namelen, i = 0, err = 0; bool is_removable = false; + efi_guid_t vendor; if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len)) return -EINVAL; - var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); - if (!var) - return -ENOMEM; - /* length of the variable name itself: remove GUID and separator */ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; - err = guid_parse(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + err = guid_parse(dentry->d_name.name + namelen + 1, &vendor); if (err) - goto out; - if (guid_equal(&var->var.VendorGuid, &LINUX_EFI_RANDOM_SEED_TABLE_GUID)) { - err = -EPERM; - goto out; - } + return err; + if (guid_equal(&vendor, &LINUX_EFI_RANDOM_SEED_TABLE_GUID)) + return -EPERM; - if (efivar_variable_is_removable(var->var.VendorGuid, + if (efivar_variable_is_removable(vendor, dentry->d_name.name, namelen)) is_removable = true; inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable); - if (!inode) { - err = -ENOMEM; - goto out; - } + if (!inode) + return -ENOMEM; + var = efivar_entry(inode); + + var->var.VendorGuid = vendor; for (i = 0; i < namelen; i++) var->var.VariableName[i] = dentry->d_name.name[i]; @@ -117,21 +112,11 @@ static int efivarfs_create(struct mnt_idmap *idmap, struct inode *dir, var->var.VariableName[i] = '\0'; inode->i_private = var; - kmemleak_ignore(var); - - err = efivar_entry_add(var, &info->efivarfs_list); - if (err) - goto out; d_instantiate(dentry, inode); dget(dentry); -out: - if (err) { - kfree(var); - if (inode) - iput(inode); - } - return err; + + return 0; } static int efivarfs_unlink(struct inode *dir, struct dentry *dentry) @@ -187,7 +172,24 @@ efivarfs_fileattr_set(struct mnt_idmap *idmap, return 0; } +/* copy of simple_setattr except that it doesn't do i_size updates */ +static int efivarfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *iattr) +{ + struct inode *inode = d_inode(dentry); + int error; + + error = setattr_prepare(idmap, dentry, iattr); + if (error) + return error; + + setattr_copy(idmap, inode, iattr); + mark_inode_dirty(inode); + return 0; +} + static const struct inode_operations efivarfs_file_inode_operations = { .fileattr_get = efivarfs_fileattr_get, .fileattr_set = efivarfs_fileattr_set, + .setattr = efivarfs_setattr, }; diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index 74f0602a9e01..ac6a1dd0a6a5 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -6,7 +6,6 @@ #ifndef EFIVAR_FS_INTERNAL_H #define EFIVAR_FS_INTERNAL_H -#include #include struct efivarfs_mount_opts { @@ -16,30 +15,31 @@ struct efivarfs_mount_opts { struct efivarfs_fs_info { struct efivarfs_mount_opts mount_opts; - struct list_head efivarfs_list; struct super_block *sb; struct notifier_block nb; + struct notifier_block pm_nb; }; struct efi_variable { efi_char16_t VariableName[EFI_VAR_NAME_LEN/sizeof(efi_char16_t)]; efi_guid_t VendorGuid; - __u32 Attributes; }; struct efivar_entry { struct efi_variable var; - struct list_head list; - struct kobject kobj; + struct inode vfs_inode; + unsigned long open_count; + bool removed; }; -int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, - struct list_head *), - void *data, struct list_head *head); +static inline struct efivar_entry *efivar_entry(struct inode *inode) +{ + return container_of(inode, struct efivar_entry, vfs_inode); +} + +int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), + void *data, bool duplicate_check); -int efivar_entry_add(struct efivar_entry *entry, struct list_head *head); -void __efivar_entry_add(struct efivar_entry *entry, struct list_head *head); -void efivar_entry_remove(struct efivar_entry *entry); int efivar_entry_delete(struct efivar_entry *entry); int efivar_entry_size(struct efivar_entry *entry, unsigned long *size); @@ -50,13 +50,14 @@ int efivar_entry_get(struct efivar_entry *entry, u32 *attributes, int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, unsigned long *size, void *data, bool *set); -int efivar_entry_iter(int (*func)(struct efivar_entry *, void *), - struct list_head *head, void *data); bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, unsigned long data_size); bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, size_t len); +char *efivar_get_utf8name(const efi_char16_t *name16, efi_guid_t *vendor); +bool efivarfs_variable_is_present(efi_char16_t *variable_name, + efi_guid_t *vendor, void *data); extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index beba15673be8..09fcf731e65d 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -39,9 +40,24 @@ static int efivarfs_ops_notifier(struct notifier_block *nb, unsigned long event, return NOTIFY_OK; } -static void efivarfs_evict_inode(struct inode *inode) +static struct inode *efivarfs_alloc_inode(struct super_block *sb) { - clear_inode(inode); + struct efivar_entry *entry = kzalloc(sizeof(*entry), GFP_KERNEL); + + if (!entry) + return NULL; + + inode_init_once(&entry->vfs_inode); + entry->removed = false; + + return &entry->vfs_inode; +} + +static void efivarfs_free_inode(struct inode *inode) +{ + struct efivar_entry *entry = efivar_entry(inode); + + kfree(entry); } static int efivarfs_show_options(struct seq_file *m, struct dentry *root) @@ -106,7 +122,8 @@ static int efivarfs_statfs(struct dentry *dentry, struct kstatfs *buf) static const struct super_operations efivarfs_ops = { .statfs = efivarfs_statfs, .drop_inode = generic_delete_inode, - .evict_inode = efivarfs_evict_inode, + .alloc_inode = efivarfs_alloc_inode, + .free_inode = efivarfs_free_inode, .show_options = efivarfs_show_options, }; @@ -181,56 +198,63 @@ static struct dentry *efivarfs_alloc_dentry(struct dentry *parent, char *name) return ERR_PTR(-ENOMEM); } -static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, - unsigned long name_size, void *data, - struct list_head *list) +bool efivarfs_variable_is_present(efi_char16_t *variable_name, + efi_guid_t *vendor, void *data) +{ + char *name = efivar_get_utf8name(variable_name, vendor); + struct super_block *sb = data; + struct dentry *dentry; + struct qstr qstr; + + if (!name) + /* + * If the allocation failed there'll already be an + * error in the log (and likely a huge and growing + * number of them since they system will be under + * extreme memory pressure), so simply assume + * collision for safety but don't add to the log + * flood. + */ + return true; + + qstr.name = name; + qstr.len = strlen(name); + dentry = d_hash_and_lookup(sb->s_root, &qstr); + kfree(name); + if (!IS_ERR_OR_NULL(dentry)) + dput(dentry); + + return dentry != NULL; +} + +static int efivarfs_create_dentry(struct super_block *sb, efi_char16_t *name16, + unsigned long name_size, efi_guid_t vendor, + char *name) { - struct super_block *sb = (struct super_block *)data; struct efivar_entry *entry; - struct inode *inode = NULL; + struct inode *inode; struct dentry *dentry, *root = sb->s_root; unsigned long size = 0; - char *name; int len; int err = -ENOMEM; bool is_removable = false; - if (guid_equal(&vendor, &LINUX_EFI_RANDOM_SEED_TABLE_GUID)) - return 0; + /* length of the variable name itself: remove GUID and separator */ + len = strlen(name) - EFI_VARIABLE_GUID_LEN - 1; - entry = kzalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - return err; - - memcpy(entry->var.VariableName, name16, name_size); - memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t)); - - len = ucs2_utf8size(entry->var.VariableName); - - /* name, plus '-', plus GUID, plus NUL*/ - name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL); - if (!name) - goto fail; - - ucs2_as_utf8(name, entry->var.VariableName, len); - - if (efivar_variable_is_removable(entry->var.VendorGuid, name, len)) + if (efivar_variable_is_removable(vendor, name, len)) is_removable = true; - name[len] = '-'; - - efi_guid_to_str(&entry->var.VendorGuid, name + len + 1); - - name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; - - /* replace invalid slashes like kobject_set_name_vargs does for /sys/firmware/efi/vars. */ - strreplace(name, '/', '!'); - inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0, is_removable); if (!inode) goto fail_name; + entry = efivar_entry(inode); + + memcpy(entry->var.VariableName, name16, name_size); + memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t)); + dentry = efivarfs_alloc_dentry(root, name); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); @@ -238,14 +262,13 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, } __efivar_entry_get(entry, NULL, &size, NULL); - __efivar_entry_add(entry, list); /* copied by the above to local storage in the dentry. */ kfree(name); inode_lock(inode); inode->i_private = entry; - i_size_write(inode, size + sizeof(entry->var.Attributes)); + i_size_write(inode, size + sizeof(__u32)); /* attributes + data */ inode_unlock(inode); d_add(dentry, inode); @@ -255,16 +278,24 @@ fail_inode: iput(inode); fail_name: kfree(name); -fail: - kfree(entry); + return err; } -static int efivarfs_destroy(struct efivar_entry *entry, void *data) +static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, + unsigned long name_size, void *data) { - efivar_entry_remove(entry); - kfree(entry); - return 0; + struct super_block *sb = (struct super_block *)data; + char *name; + + if (guid_equal(&vendor, &LINUX_EFI_RANDOM_SEED_TABLE_GUID)) + return 0; + + name = efivar_get_utf8name(name16, &vendor); + if (!name) + return -ENOMEM; + + return efivarfs_create_dentry(sb, name16, name_size, vendor, name); } enum { @@ -336,7 +367,7 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; - return efivar_init(efivarfs_callback, sb, &sfi->efivarfs_list); + return efivar_init(efivarfs_callback, sb, true); } static int efivarfs_get_tree(struct fs_context *fc) @@ -360,6 +391,148 @@ static const struct fs_context_operations efivarfs_context_ops = { .reconfigure = efivarfs_reconfigure, }; +struct efivarfs_ctx { + struct dir_context ctx; + struct super_block *sb; + struct dentry *dentry; +}; + +static bool efivarfs_actor(struct dir_context *ctx, const char *name, int len, + loff_t offset, u64 ino, unsigned mode) +{ + unsigned long size; + struct efivarfs_ctx *ectx = container_of(ctx, struct efivarfs_ctx, ctx); + struct qstr qstr = { .name = name, .len = len }; + struct dentry *dentry = d_hash_and_lookup(ectx->sb->s_root, &qstr); + struct inode *inode; + struct efivar_entry *entry; + int err; + + if (IS_ERR_OR_NULL(dentry)) + return true; + + inode = d_inode(dentry); + entry = efivar_entry(inode); + + err = efivar_entry_size(entry, &size); + size += sizeof(__u32); /* attributes */ + if (err) + size = 0; + + inode_lock(inode); + i_size_write(inode, size); + inode_unlock(inode); + + if (!size) { + ectx->dentry = dentry; + return false; + } + + dput(dentry); + + return true; +} + +static int efivarfs_check_missing(efi_char16_t *name16, efi_guid_t vendor, + unsigned long name_size, void *data) +{ + char *name; + struct super_block *sb = data; + struct dentry *dentry; + struct qstr qstr; + int err; + + if (guid_equal(&vendor, &LINUX_EFI_RANDOM_SEED_TABLE_GUID)) + return 0; + + name = efivar_get_utf8name(name16, &vendor); + if (!name) + return -ENOMEM; + + qstr.name = name; + qstr.len = strlen(name); + dentry = d_hash_and_lookup(sb->s_root, &qstr); + if (IS_ERR(dentry)) { + err = PTR_ERR(dentry); + goto out; + } + + if (!dentry) { + /* found missing entry */ + pr_info("efivarfs: creating variable %s\n", name); + return efivarfs_create_dentry(sb, name16, name_size, vendor, name); + } + + dput(dentry); + err = 0; + + out: + kfree(name); + + return err; +} + +static int efivarfs_pm_notify(struct notifier_block *nb, unsigned long action, + void *ptr) +{ + struct efivarfs_fs_info *sfi = container_of(nb, struct efivarfs_fs_info, + pm_nb); + struct path path = { .mnt = NULL, .dentry = sfi->sb->s_root, }; + struct efivarfs_ctx ectx = { + .ctx = { + .actor = efivarfs_actor, + }, + .sb = sfi->sb, + }; + struct file *file; + static bool rescan_done = true; + + if (action == PM_HIBERNATION_PREPARE) { + rescan_done = false; + return NOTIFY_OK; + } else if (action != PM_POST_HIBERNATION) { + return NOTIFY_DONE; + } + + if (rescan_done) + return NOTIFY_DONE; + + pr_info("efivarfs: resyncing variable state\n"); + + /* O_NOATIME is required to prevent oops on NULL mnt */ + file = kernel_file_open(&path, O_RDONLY | O_DIRECTORY | O_NOATIME, + current_cred()); + if (IS_ERR(file)) + return NOTIFY_DONE; + + rescan_done = true; + + /* + * First loop over the directory and verify each entry exists, + * removing it if it doesn't + */ + file->f_pos = 2; /* skip . and .. */ + do { + ectx.dentry = NULL; + iterate_dir(file, &ectx.ctx); + if (ectx.dentry) { + pr_info("efivarfs: removing variable %pd\n", + ectx.dentry); + simple_recursive_removal(ectx.dentry, NULL); + dput(ectx.dentry); + } + } while (ectx.dentry); + fput(file); + + /* + * then loop over variables, creating them if there's no matching + * dentry + */ + efivar_init(efivarfs_check_missing, sfi->sb, false); + + return NOTIFY_OK; +} + static int efivarfs_init_fs_context(struct fs_context *fc) { struct efivarfs_fs_info *sfi; @@ -371,13 +544,16 @@ static int efivarfs_init_fs_context(struct fs_context *fc) if (!sfi) return -ENOMEM; - INIT_LIST_HEAD(&sfi->efivarfs_list); - sfi->mount_opts.uid = GLOBAL_ROOT_UID; sfi->mount_opts.gid = GLOBAL_ROOT_GID; fc->s_fs_info = sfi; fc->ops = &efivarfs_context_ops; + + sfi->pm_nb.notifier_call = efivarfs_pm_notify; + sfi->pm_nb.priority = 0; + register_pm_notifier(&sfi->pm_nb); + return 0; } @@ -387,9 +563,8 @@ static void efivarfs_kill_sb(struct super_block *sb) blocking_notifier_chain_unregister(&efivar_ops_nh, &sfi->nb); kill_litter_super(sb); + unregister_pm_notifier(&sfi->pm_nb); - /* Remove all entries and destroy */ - efivar_entry_iter(efivarfs_destroy, &sfi->efivarfs_list, NULL); kfree(sfi); } diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c index f7d43c847ee9..6edc10958ecf 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -225,6 +225,31 @@ variable_matches(const char *var_name, size_t len, const char *match_name, } } +char * +efivar_get_utf8name(const efi_char16_t *name16, efi_guid_t *vendor) +{ + int len = ucs2_utf8size(name16); + char *name; + + /* name, plus '-', plus GUID, plus NUL*/ + name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL); + if (!name) + return NULL; + + ucs2_as_utf8(name, name16, len); + + name[len] = '-'; + + efi_guid_to_str(vendor, name + len + 1); + + name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; + + /* replace invalid slashes like kobject_set_name_vargs does for /sys/firmware/efi/vars. */ + strreplace(name, '/', '!'); + + return name; +} + bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, unsigned long data_size) @@ -288,28 +313,6 @@ efivar_variable_is_removable(efi_guid_t vendor, const char *var_name, return found; } -static bool variable_is_present(efi_char16_t *variable_name, efi_guid_t *vendor, - struct list_head *head) -{ - struct efivar_entry *entry, *n; - unsigned long strsize1, strsize2; - bool found = false; - - strsize1 = ucs2_strsize(variable_name, EFI_VAR_NAME_LEN); - list_for_each_entry_safe(entry, n, head, list) { - strsize2 = ucs2_strsize(entry->var.VariableName, EFI_VAR_NAME_LEN); - if (strsize1 == strsize2 && - !memcmp(variable_name, &(entry->var.VariableName), - strsize2) && - !efi_guidcmp(entry->var.VendorGuid, - *vendor)) { - found = true; - break; - } - } - return found; -} - /* * Returns the size of variable_name, in bytes, including the * terminating NULL character, or variable_name_size if no NULL @@ -361,16 +364,15 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid, * efivar_init - build the initial list of EFI variables * @func: callback function to invoke for every variable * @data: function-specific data to pass to @func - * @head: initialised head of variable list + * @duplicate_check: fail if a duplicate variable is found * * Get every EFI variable from the firmware and invoke @func. @func - * should call efivar_entry_add() to build the list of variables. + * should populate the initial dentry and inode tree. * * Returns 0 on success, or a kernel error code on failure. */ -int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, - struct list_head *), - void *data, struct list_head *head) +int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), + void *data, bool duplicate_check) { unsigned long variable_name_size = 512; efi_char16_t *variable_name; @@ -414,14 +416,15 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, * we'll ever see a different variable name, * and may end up looping here forever. */ - if (variable_is_present(variable_name, &vendor_guid, - head)) { + if (duplicate_check && + efivarfs_variable_is_present(variable_name, + &vendor_guid, data)) { dup_variable_bug(variable_name, &vendor_guid, variable_name_size); status = EFI_NOT_FOUND; } else { err = func(variable_name, vendor_guid, - variable_name_size, data, head); + variable_name_size, data); if (err) status = EFI_NOT_FOUND; } @@ -453,70 +456,12 @@ free: } /** - * efivar_entry_add - add entry to variable list - * @entry: entry to add to list - * @head: list head - * - * Returns 0 on success, or a kernel error code on failure. - */ -int efivar_entry_add(struct efivar_entry *entry, struct list_head *head) -{ - int err; - - err = efivar_lock(); - if (err) - return err; - list_add(&entry->list, head); - efivar_unlock(); - - return 0; -} - -/** - * __efivar_entry_add - add entry to variable list - * @entry: entry to add to list - * @head: list head - */ -void __efivar_entry_add(struct efivar_entry *entry, struct list_head *head) -{ - list_add(&entry->list, head); -} - -/** - * efivar_entry_remove - remove entry from variable list - * @entry: entry to remove from list - * - * Returns 0 on success, or a kernel error code on failure. - */ -void efivar_entry_remove(struct efivar_entry *entry) -{ - list_del(&entry->list); -} - -/* - * efivar_entry_list_del_unlock - remove entry from variable list - * @entry: entry to remove - * - * Remove @entry from the variable list and release the list lock. - * - * NOTE: slightly weird locking semantics here - we expect to be - * called with the efivars lock already held, and we release it before - * returning. This is because this function is usually called after - * set_variable() while the lock is still held. - */ -static void efivar_entry_list_del_unlock(struct efivar_entry *entry) -{ - list_del(&entry->list); - efivar_unlock(); -} - -/** - * efivar_entry_delete - delete variable and remove entry from list + * efivar_entry_delete - delete variable * @entry: entry containing variable to delete * - * Delete the variable from the firmware and remove @entry from the - * variable list. It is the caller's responsibility to free @entry - * once we return. + * Delete the variable from the firmware. It is the caller's + * responsibility to free @entry (by deleting the dentry/inode) once + * we return. * * Returns 0 on success, -EINTR if we can't grab the semaphore, * converted EFI status code if set_variable() fails. @@ -533,12 +478,10 @@ int efivar_entry_delete(struct efivar_entry *entry) status = efivar_set_variable_locked(entry->var.VariableName, &entry->var.VendorGuid, 0, 0, NULL, false); - if (!(status == EFI_SUCCESS || status == EFI_NOT_FOUND)) { - efivar_unlock(); + efivar_unlock(); + if (!(status == EFI_SUCCESS || status == EFI_NOT_FOUND)) return efi_status_to_err(status); - } - efivar_entry_list_del_unlock(entry); return 0; } @@ -632,7 +575,7 @@ int efivar_entry_get(struct efivar_entry *entry, u32 *attributes, * get_variable() fail. * * If the EFI variable does not exist when calling set_variable() - * (EFI_NOT_FOUND), @entry is removed from the variable list. + * (EFI_NOT_FOUND). */ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, unsigned long *size, void *data, bool *set) @@ -648,9 +591,8 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, return -EINVAL; /* - * The lock here protects the get_variable call, the conditional - * set_variable call, and removal of the variable from the efivars - * list (in the case of an authenticated delete). + * The lock here protects the get_variable call and the + * conditional set_variable call */ err = efivar_lock(); if (err) @@ -676,10 +618,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, &entry->var.VendorGuid, NULL, size, NULL); - if (status == EFI_NOT_FOUND) - efivar_entry_list_del_unlock(entry); - else - efivar_unlock(); + efivar_unlock(); if (status && status != EFI_BUFFER_TOO_SMALL) return efi_status_to_err(status); @@ -691,37 +630,3 @@ out: return err; } - -/** - * efivar_entry_iter - iterate over variable list - * @func: callback function - * @head: head of variable list - * @data: function-specific data to pass to callback - * - * Iterate over the list of EFI variables and call @func with every - * entry on the list. It is safe for @func to remove entries in the - * list via efivar_entry_delete() while iterating. - * - * Some notes for the callback function: - * - a non-zero return value indicates an error and terminates the loop - * - @func is called from atomic context - */ -int efivar_entry_iter(int (*func)(struct efivar_entry *, void *), - struct list_head *head, void *data) -{ - struct efivar_entry *entry, *n; - int err = 0; - - err = efivar_lock(); - if (err) - return err; - - list_for_each_entry_safe(entry, n, head, list) { - err = func(entry, data); - if (err) - break; - } - efivar_unlock(); - - return err; -} diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h index 7bfe251680ec..65ff39401020 100644 --- a/fs/erofs/compress.h +++ b/fs/erofs/compress.h @@ -29,29 +29,8 @@ struct z_erofs_decompressor { char *name; }; -/* some special page->private (unsigned long, see below) */ #define Z_EROFS_SHORTLIVED_PAGE (-1UL << 2) -#define Z_EROFS_PREALLOCATED_PAGE (-2UL << 2) - -/* - * For all pages in a pcluster, page->private should be one of - * Type Last 2bits page->private - * short-lived page 00 Z_EROFS_SHORTLIVED_PAGE - * preallocated page (tryalloc) 00 Z_EROFS_PREALLOCATED_PAGE - * cached/managed page 00 pointer to z_erofs_pcluster - * online page (file-backed, 01/10/11 sub-index << 2 | count - * some pages can be used for inplace I/O) - * - * page->mapping should be one of - * Type page->mapping - * short-lived page NULL - * preallocated page NULL - * cached/managed page non-NULL or NULL (invalidated/truncated page) - * online page non-NULL - * - * For all managed pages, PG_private should be set with 1 extra refcount, - * which is used for page reclaim / migration. - */ +#define Z_EROFS_PREALLOCATED_FOLIO ((void *)(-2UL << 2)) /* * Currently, short-lived pages are pages directly from buddy system diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 1c49f8962021..0cd6b5c4df98 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -56,10 +56,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) buf->file = NULL; if (erofs_is_fileio_mode(sbi)) { - buf->file = sbi->fdev; /* some fs like FUSE needs it */ + buf->file = sbi->dif0.file; /* some fs like FUSE needs it */ buf->mapping = buf->file->f_mapping; } else if (erofs_is_fscache_mode(sb)) - buf->mapping = sbi->s_fscache->inode->i_mapping; + buf->mapping = sbi->dif0.fscache->inode->i_mapping; else buf->mapping = sb->s_bdev->bd_mapping; } @@ -179,19 +179,13 @@ out: } static void erofs_fill_from_devinfo(struct erofs_map_dev *map, - struct erofs_device_info *dif) + struct super_block *sb, struct erofs_device_info *dif) { + map->m_sb = sb; + map->m_dif = dif; map->m_bdev = NULL; - map->m_fp = NULL; - if (dif->file) { - if (S_ISBLK(file_inode(dif->file)->i_mode)) - map->m_bdev = file_bdev(dif->file); - else - map->m_fp = dif->file; - } - map->m_daxdev = dif->dax_dev; - map->m_dax_part_off = dif->dax_part_off; - map->m_fscache = dif->fscache; + if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode)) + map->m_bdev = file_bdev(dif->file); } int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) @@ -201,12 +195,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) erofs_off_t startoff, length; int id; - map->m_bdev = sb->s_bdev; - map->m_daxdev = EROFS_SB(sb)->dax_dev; - map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; - map->m_fscache = EROFS_SB(sb)->s_fscache; - map->m_fp = EROFS_SB(sb)->fdev; - + erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0); + map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */ if (map->m_deviceid) { down_read(&devs->rwsem); dif = idr_find(&devs->tree, map->m_deviceid - 1); @@ -219,7 +209,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); up_read(&devs->rwsem); } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); @@ -232,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); break; } } @@ -302,7 +292,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->offset = map.m_la; if (flags & IOMAP_DAX) - iomap->dax_dev = mdev.m_daxdev; + iomap->dax_dev = mdev.m_dif->dax_dev; else iomap->bdev = mdev.m_bdev; iomap->length = map.m_llen; @@ -331,7 +321,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->type = IOMAP_MAPPED; iomap->addr = mdev.m_pa; if (flags & IOMAP_DAX) - iomap->addr += mdev.m_dax_part_off; + iomap->addr += mdev.m_dif->dax_part_off; } return 0; } diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index eb318c7ddd80..2b123b070a42 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -7,14 +7,7 @@ #include "compress.h" #include -#ifndef LZ4_DISTANCE_MAX /* history window size */ -#define LZ4_DISTANCE_MAX 65535 /* set to maximum value by default */ -#endif - #define LZ4_MAX_DISTANCE_PAGES (DIV_ROUND_UP(LZ4_DISTANCE_MAX, PAGE_SIZE) + 1) -#ifndef LZ4_DECOMPRESS_INPLACE_MARGIN -#define LZ4_DECOMPRESS_INPLACE_MARGIN(srcsize) (((srcsize) >> 8) + 32) -#endif struct z_erofs_lz4_decompress_ctx { struct z_erofs_decompress_req *rq; diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index c8f2ae845bd2..199395ed1c1f 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -9,6 +9,7 @@ #ifndef __EROFS_FS_H #define __EROFS_FS_H +/* to allow for x86 boot sectors and other oddities. */ #define EROFS_SUPER_OFFSET 1024 #define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001 @@ -54,7 +55,7 @@ struct erofs_deviceslot { /* erofs on-disk super block (currently 128 bytes) */ struct erofs_super_block { __le32 magic; /* file system magic number */ - __le32 checksum; /* crc32c(super_block) */ + __le32 checksum; /* crc32c to avoid unexpected on-disk overlap */ __le32 feature_compat; __u8 blkszbits; /* filesystem block size in bit shift */ __u8 sb_extslots; /* superblock size = 128 + sb_extslots * 16 */ diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index 3af96b1e2c2a..0ffd1c63beeb 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -6,9 +6,10 @@ #include struct erofs_fileio_rq { - struct bio_vec bvecs[BIO_MAX_VECS]; + struct bio_vec bvecs[16]; struct bio bio; struct kiocb iocb; + struct super_block *sb; }; struct erofs_fileio { @@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT; rq->iocb.ki_ioprio = get_current_ioprio(); rq->iocb.ki_complete = erofs_fileio_ki_complete; - rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ? - IOCB_DIRECT : 0; + if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) && + rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) + rq->iocb.ki_flags = IOCB_DIRECT; iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt, rq->bio.bi_iter.bi_size); ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); @@ -66,8 +68,9 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) struct erofs_fileio_rq *rq = kzalloc(sizeof(*rq), GFP_KERNEL | __GFP_NOFAIL); - bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ); - rq->iocb.ki_filp = mdev->m_fp; + bio_init(&rq->bio, NULL, rq->bvecs, ARRAY_SIZE(rq->bvecs), REQ_OP_READ); + rq->iocb.ki_filp = mdev->m_dif->file; + rq->sb = mdev->m_sb; return rq; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index fda16eedafb5..ce3d8737df85 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL); bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ); - io->io.private = mdev->m_fscache->cookie; + io->io.private = mdev->m_dif->fscache->cookie; io->io.end_io = erofs_fscache_bio_endio; refcount_set(&io->io.ref, 1); return &io->bio; @@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req) if (!io) return -ENOMEM; iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count); - ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie, + ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie, mdev.m_pa + (pos - map.m_la), io); erofs_fscache_req_io_put(io); @@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb) if (IS_ERR(fscache)) return PTR_ERR(fscache); - sbi->s_fscache = fscache; + sbi->dif0.fscache = fscache; return 0; } @@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - erofs_fscache_unregister_cookie(sbi->s_fscache); + erofs_fscache_unregister_cookie(sbi->dif0.fscache); if (sbi->domain) erofs_fscache_domain_put(sbi->domain); else fscache_relinquish_volume(sbi->volume, NULL, false); - sbi->s_fscache = NULL; + sbi->dif0.fscache = NULL; sbi->volume = NULL; sbi->domain = NULL; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1c847c30a918..686d835eb533 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -107,6 +107,7 @@ struct erofs_xattr_prefix_item { }; struct erofs_sb_info { + struct erofs_device_info dif0; struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP /* list for all registered superblocks, mainly for shrinker */ @@ -124,13 +125,9 @@ struct erofs_sb_info { struct erofs_sb_lz4_info lz4; #endif /* CONFIG_EROFS_FS_ZIP */ - struct file *fdev; struct inode *packed_inode; struct erofs_dev_context *devs; - struct dax_device *dax_dev; - u64 dax_part_off; u64 total_blocks; - u32 primarydevice_blocks; u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR @@ -166,7 +163,6 @@ struct erofs_sb_info { /* fscache support */ struct fscache_volume *volume; - struct erofs_fscache *s_fscache; struct erofs_domain *domain; char *fsid; char *domain_id; @@ -180,6 +176,7 @@ struct erofs_sb_info { #define EROFS_MOUNT_POSIX_ACL 0x00000020 #define EROFS_MOUNT_DAX_ALWAYS 0x00000040 #define EROFS_MOUNT_DAX_NEVER 0x00000080 +#define EROFS_MOUNT_DIRECT_IO 0x00000100 #define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option) #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) @@ -187,7 +184,7 @@ struct erofs_sb_info { static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi) { - return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev; + return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file; } static inline bool erofs_is_fscache_mode(struct super_block *sb) @@ -357,11 +354,9 @@ enum { }; struct erofs_map_dev { - struct erofs_fscache *m_fscache; + struct super_block *m_sb; + struct erofs_device_info *m_dif; struct block_device *m_bdev; - struct dax_device *m_daxdev; - struct file *m_fp; - u64 m_dax_part_off; erofs_off_t m_pa; unsigned int m_deviceid; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c235a8e4315e..827b62665649 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -39,29 +39,21 @@ void _erofs_printk(struct super_block *sb, const char *fmt, ...) static int erofs_superblock_csum_verify(struct super_block *sb, void *sbdata) { - size_t len = 1 << EROFS_SB(sb)->blkszbits; - struct erofs_super_block *dsb; - u32 expected_crc, crc; + struct erofs_super_block *dsb = sbdata + EROFS_SUPER_OFFSET; + u32 len = 1 << EROFS_SB(sb)->blkszbits, crc; if (len > EROFS_SUPER_OFFSET) len -= EROFS_SUPER_OFFSET; + len -= offsetof(struct erofs_super_block, checksum) + + sizeof(dsb->checksum); - dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET, len, GFP_KERNEL); - if (!dsb) - return -ENOMEM; - - expected_crc = le32_to_cpu(dsb->checksum); - dsb->checksum = 0; - /* to allow for x86 boot sectors and other oddities. */ - crc = crc32c(~0, dsb, len); - kfree(dsb); - - if (crc != expected_crc) { - erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected", - crc, expected_crc); - return -EBADMSG; - } - return 0; + /* skip .magic(pre-verified) and .checksum(0) fields */ + crc = crc32c(0x5045B54A, (&dsb->checksum) + 1, len); + if (crc == le32_to_cpu(dsb->checksum)) + return 0; + erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected", + crc, le32_to_cpu(dsb->checksum)); + return -EBADMSG; } static void erofs_inode_init_once(void *ptr) @@ -203,7 +195,7 @@ static int erofs_scan_devices(struct super_block *sb, struct erofs_device_info *dif; int id, err = 0; - sbi->total_blocks = sbi->primarydevice_blocks; + sbi->total_blocks = sbi->dif0.blocks; if (!erofs_sb_has_device_table(sbi)) ondisk_extradevs = 0; else @@ -307,7 +299,7 @@ static int erofs_read_superblock(struct super_block *sb) sbi->sb_size); goto out; } - sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks); + sbi->dif0.blocks = le32_to_cpu(dsb->blocks); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); @@ -364,14 +356,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi) } enum { - Opt_user_xattr, - Opt_acl, - Opt_cache_strategy, - Opt_dax, - Opt_dax_enum, - Opt_device, - Opt_fsid, - Opt_domain_id, + Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, + Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_err }; @@ -398,6 +384,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_string("device", Opt_device), fsparam_string("fsid", Opt_fsid), fsparam_string("domain_id", Opt_domain_id), + fsparam_flag_no("directio", Opt_directio), {} }; @@ -511,8 +498,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; #endif - default: - return -ENOPARAM; + case Opt_directio: +#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE + if (result.boolean) + set_opt(&sbi->opt, DIRECT_IO); + else + clear_opt(&sbi->opt, DIRECT_IO); +#else + errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); +#endif + break; } return 0; } @@ -602,9 +597,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return -EINVAL; } - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off, - NULL, NULL); + sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dif0.dax_part_off, NULL, NULL); } err = erofs_read_superblock(sb); @@ -627,7 +621,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dax_dev) { + if (!sbi->dif0.dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); } else if (sbi->blkszbits != PAGE_SHIFT) { @@ -703,16 +697,18 @@ static int erofs_fc_get_tree(struct fs_context *fc) GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { + struct file *file; + if (!fc->source) return invalf(fc, "No source specified"); - sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); - if (IS_ERR(sbi->fdev)) - return PTR_ERR(sbi->fdev); + file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + sbi->dif0.file = file; - if (S_ISREG(file_inode(sbi->fdev)->i_mode) && - sbi->fdev->f_mapping->a_ops->read_folio) + if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) && + sbi->dif0.file->f_mapping->a_ops->read_folio) return get_tree_nodev(fc, erofs_fc_fill_super); - fput(sbi->fdev); } #endif return ret; @@ -763,17 +759,22 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) kfree(devs); } +static void erofs_sb_free(struct erofs_sb_info *sbi) +{ + erofs_free_dev_context(sbi->devs); + kfree(sbi->fsid); + kfree(sbi->domain_id); + if (sbi->dif0.file) + fput(sbi->dif0.file); + kfree(sbi); +} + static void erofs_fc_free(struct fs_context *fc) { struct erofs_sb_info *sbi = fc->s_fs_info; - if (!sbi) - return; - - erofs_free_dev_context(sbi->devs); - kfree(sbi->fsid); - kfree(sbi->domain_id); - kfree(sbi); + if (sbi) /* free here if an error occurs before transferring to sb */ + erofs_sb_free(sbi); } static const struct fs_context_operations erofs_context_ops = { @@ -809,19 +810,14 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev) + if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || + sbi->dif0.file) kill_anon_super(sb); else kill_block_super(sb); - - erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev, NULL); + fs_put_dax(sbi->dif0.dax_dev, NULL); erofs_fscache_unregister_fs(sb); - kfree(sbi->fsid); - kfree(sbi->domain_id); - if (sbi->fdev) - fput(sbi->fdev); - kfree(sbi); + erofs_sb_free(sbi); sb->s_fs_info = NULL; } @@ -947,6 +943,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); + if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO)) + seq_puts(seq, ",directio"); #ifdef CONFIG_EROFS_FS_ONDEMAND if (sbi->fsid) seq_printf(seq, ",fsid=%s", sbi->fsid); diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index a90d7d649739..df2777e05661 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -407,7 +407,7 @@ int erofs_getxattr(struct inode *inode, int index, const char *name, } it.index = index; - it.name = (struct qstr)QSTR_INIT(name, strlen(name)); + it.name = QSTR(name); if (it.name.len > EROFS_NAME_LEN) return -ERANGE; @@ -478,7 +478,7 @@ int erofs_xattr_prefixes_init(struct super_block *sb) if (!sbi->xattr_prefix_count) return 0; - pfs = kzalloc(sbi->xattr_prefix_count * sizeof(*pfs), GFP_KERNEL); + pfs = kcalloc(sbi->xattr_prefix_count, sizeof(*pfs), GFP_KERNEL); if (!pfs) return -ENOMEM; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 01f147505487..29f8963bb523 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -12,12 +12,6 @@ #define Z_EROFS_PCLUSTER_MAX_PAGES (Z_EROFS_PCLUSTER_MAX_SIZE / PAGE_SIZE) #define Z_EROFS_INLINE_BVECS 2 -/* - * let's leave a type here in case of introducing - * another tagged pointer later. - */ -typedef void *z_erofs_next_pcluster_t; - struct z_erofs_bvec { struct page *page; int offset; @@ -48,7 +42,7 @@ struct z_erofs_pcluster { struct lockref lockref; /* A: point to next chained pcluster or TAILs */ - z_erofs_next_pcluster_t next; + struct z_erofs_pcluster *next; /* I: start block address of this pcluster */ erofs_off_t index; @@ -94,12 +88,11 @@ struct z_erofs_pcluster { /* the end of a chain of pclusters */ #define Z_EROFS_PCLUSTER_TAIL ((void *) 0x700 + POISON_POINTER_DELTA) -#define Z_EROFS_PCLUSTER_NIL (NULL) struct z_erofs_decompressqueue { struct super_block *sb; + struct z_erofs_pcluster *head; atomic_t pending_bios; - z_erofs_next_pcluster_t head; union { struct completion done; @@ -320,7 +313,7 @@ static void erofs_destroy_percpu_workers(void) static struct kthread_worker *erofs_init_percpu_worker(int cpu) { struct kthread_worker *worker = - kthread_create_worker_on_cpu(cpu, 0, "erofs_worker/%u", cpu); + kthread_run_worker_on_cpu(cpu, 0, "erofs_worker/%u"); if (IS_ERR(worker)) return worker; @@ -462,39 +455,32 @@ err_decompressor: } enum z_erofs_pclustermode { + /* It has previously been linked into another processing chain */ Z_EROFS_PCLUSTER_INFLIGHT, /* - * a weak form of Z_EROFS_PCLUSTER_FOLLOWED, the difference is that it - * could be dispatched into bypass queue later due to uptodated managed - * pages. All related online pages cannot be reused for inplace I/O (or - * bvpage) since it can be directly decoded without I/O submission. + * A weaker form of Z_EROFS_PCLUSTER_FOLLOWED; the difference is that it + * may be dispatched to the bypass queue later due to uptodated managed + * folios. All file-backed folios related to this pcluster cannot be + * reused for in-place I/O (or bvpage) since the pcluster may be decoded + * in a separate queue (and thus out of order). */ Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE, /* - * The pcluster was just linked to a decompression chain by us. It can - * also be linked with the remaining pclusters, which means if the - * processing page is the tail page of a pcluster, this pcluster can - * safely use the whole page (since the previous pcluster is within the - * same chain) for in-place I/O, as illustrated below: - * ___________________________________________________ - * | tail (partial) page | head (partial) page | - * | (of the current pcl) | (of the previous pcl) | - * |___PCLUSTER_FOLLOWED___|_____PCLUSTER_FOLLOWED_____| - * - * [ (*) the page above can be used as inplace I/O. ] + * The pcluster has just been linked to our processing chain. + * File-backed folios (except for the head page) related to it can be + * used for in-place I/O (or bvpage). */ Z_EROFS_PCLUSTER_FOLLOWED, }; -struct z_erofs_decompress_frontend { +struct z_erofs_frontend { struct inode *const inode; struct erofs_map_blocks map; struct z_erofs_bvec_iter biter; struct page *pagepool; struct page *candidate_bvpage; - struct z_erofs_pcluster *pcl; - z_erofs_next_pcluster_t owned_head; + struct z_erofs_pcluster *pcl, *head; enum z_erofs_pclustermode mode; erofs_off_t headoffset; @@ -503,11 +489,11 @@ struct z_erofs_decompress_frontend { unsigned int icur; }; -#define DECOMPRESS_FRONTEND_INIT(__i) { \ - .inode = __i, .owned_head = Z_EROFS_PCLUSTER_TAIL, \ - .mode = Z_EROFS_PCLUSTER_FOLLOWED } +#define Z_EROFS_DEFINE_FRONTEND(fe, i, ho) struct z_erofs_frontend fe = { \ + .inode = i, .head = Z_EROFS_PCLUSTER_TAIL, \ + .mode = Z_EROFS_PCLUSTER_FOLLOWED, .headoffset = ho } -static bool z_erofs_should_alloc_cache(struct z_erofs_decompress_frontend *fe) +static bool z_erofs_should_alloc_cache(struct z_erofs_frontend *fe) { unsigned int cachestrategy = EROFS_I_SB(fe->inode)->opt.cache_strategy; @@ -524,19 +510,17 @@ static bool z_erofs_should_alloc_cache(struct z_erofs_decompress_frontend *fe) return false; } -static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe) +static void z_erofs_bind_cache(struct z_erofs_frontend *fe) { struct address_space *mc = MNGD_MAPPING(EROFS_I_SB(fe->inode)); struct z_erofs_pcluster *pcl = fe->pcl; unsigned int pclusterpages = z_erofs_pclusterpages(pcl); bool shouldalloc = z_erofs_should_alloc_cache(fe); - bool standalone = true; - /* - * optimistic allocation without direct reclaim since inplace I/O - * can be used if low memory otherwise. - */ + bool may_bypass = true; + /* Optimistic allocation, as in-place I/O can be used as a fallback */ gfp_t gfp = (mapping_gfp_mask(mc) & ~__GFP_DIRECT_RECLAIM) | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; + struct folio *folio, *newfolio; unsigned int i; if (i_blocksize(fe->inode) != PAGE_SIZE || @@ -544,47 +528,42 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe) return; for (i = 0; i < pclusterpages; ++i) { - struct page *page, *newpage; - /* Inaccurate check w/o locking to avoid unneeded lookups */ if (READ_ONCE(pcl->compressed_bvecs[i].page)) continue; - page = find_get_page(mc, pcl->index + i); - if (!page) { - /* I/O is needed, no possible to decompress directly */ - standalone = false; + folio = filemap_get_folio(mc, pcl->index + i); + if (IS_ERR(folio)) { + may_bypass = false; if (!shouldalloc) continue; /* - * Try cached I/O if allocation succeeds or fallback to - * in-place I/O instead to avoid any direct reclaim. + * Allocate a managed folio for cached I/O, or it may be + * then filled with a file-backed folio for in-place I/O */ - newpage = erofs_allocpage(&fe->pagepool, gfp); - if (!newpage) + newfolio = filemap_alloc_folio(gfp, 0); + if (!newfolio) continue; - set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE); + newfolio->private = Z_EROFS_PREALLOCATED_FOLIO; + folio = NULL; } spin_lock(&pcl->lockref.lock); if (!pcl->compressed_bvecs[i].page) { - pcl->compressed_bvecs[i].page = page ? page : newpage; + pcl->compressed_bvecs[i].page = + folio_page(folio ?: newfolio, 0); spin_unlock(&pcl->lockref.lock); continue; } spin_unlock(&pcl->lockref.lock); - - if (page) - put_page(page); - else if (newpage) - erofs_pagepool_add(&fe->pagepool, newpage); + folio_put(folio ?: newfolio); } /* - * don't do inplace I/O if all compressed pages are available in - * managed cache since it can be moved to the bypass queue instead. + * Don't perform in-place I/O if all compressed pages are available in + * the managed cache, as the pcluster can be moved to the bypass queue. */ - if (standalone) + if (may_bypass) fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE; } @@ -681,7 +660,7 @@ int erofs_init_managed_cache(struct super_block *sb) } /* callers must be with pcluster lock held */ -static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe, +static int z_erofs_attach_page(struct z_erofs_frontend *fe, struct z_erofs_bvec *bvec, bool exclusive) { struct z_erofs_pcluster *pcl = fe->pcl; @@ -727,7 +706,7 @@ static bool z_erofs_get_pcluster(struct z_erofs_pcluster *pcl) return true; } -static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) +static int z_erofs_register_pcluster(struct z_erofs_frontend *fe) { struct erofs_map_blocks *map = &fe->map; struct super_block *sb = fe->inode->i_sb; @@ -747,14 +726,11 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) if (IS_ERR(pcl)) return PTR_ERR(pcl); - spin_lock_init(&pcl->lockref.lock); - pcl->lockref.count = 1; /* one ref for this request */ + lockref_init(&pcl->lockref, 1); /* one ref for this request */ pcl->algorithmformat = map->m_algorithmformat; pcl->length = 0; pcl->partial = true; - - /* new pclusters should be claimed as type 1, primary and followed */ - pcl->next = fe->owned_head; + pcl->next = fe->head; pcl->pageofs_out = map->m_la & ~PAGE_MASK; fe->mode = Z_EROFS_PCLUSTER_FOLLOWED; @@ -790,8 +766,7 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) goto err_out; } } - fe->owned_head = &pcl->next; - fe->pcl = pcl; + fe->head = fe->pcl = pcl; return 0; err_out: @@ -800,7 +775,7 @@ err_out: return err; } -static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe) +static int z_erofs_pcluster_begin(struct z_erofs_frontend *fe) { struct erofs_map_blocks *map = &fe->map; struct super_block *sb = fe->inode->i_sb; @@ -810,7 +785,7 @@ static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe) DBG_BUGON(fe->pcl); /* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous pcluster */ - DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_NIL); + DBG_BUGON(!fe->head); if (!(map->m_flags & EROFS_MAP_META)) { while (1) { @@ -838,10 +813,9 @@ static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe) if (ret == -EEXIST) { mutex_lock(&fe->pcl->lock); /* check if this pcluster hasn't been linked into any chain. */ - if (cmpxchg(&fe->pcl->next, Z_EROFS_PCLUSTER_NIL, - fe->owned_head) == Z_EROFS_PCLUSTER_NIL) { + if (!cmpxchg(&fe->pcl->next, NULL, fe->head)) { /* .. so it can be attached to our submission chain */ - fe->owned_head = &fe->pcl->next; + fe->head = fe->pcl; fe->mode = Z_EROFS_PCLUSTER_FOLLOWED; } else { /* otherwise, it belongs to an inflight chain */ fe->mode = Z_EROFS_PCLUSTER_INFLIGHT; @@ -874,14 +848,9 @@ static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe) return 0; } -/* - * keep in mind that no referenced pclusters will be freed - * only after a RCU grace period. - */ static void z_erofs_rcu_callback(struct rcu_head *head) { - z_erofs_free_pcluster(container_of(head, - struct z_erofs_pcluster, rcu)); + z_erofs_free_pcluster(container_of(head, struct z_erofs_pcluster, rcu)); } static bool __erofs_try_to_release_pcluster(struct erofs_sb_info *sbi, @@ -923,12 +892,10 @@ static bool erofs_try_to_release_pcluster(struct erofs_sb_info *sbi, return free; } -unsigned long z_erofs_shrink_scan(struct erofs_sb_info *sbi, - unsigned long nr_shrink) +unsigned long z_erofs_shrink_scan(struct erofs_sb_info *sbi, unsigned long nr) { struct z_erofs_pcluster *pcl; - unsigned int freed = 0; - unsigned long index; + unsigned long index, freed = 0; xa_lock(&sbi->managed_pslots); xa_for_each(&sbi->managed_pslots, index, pcl) { @@ -938,7 +905,7 @@ unsigned long z_erofs_shrink_scan(struct erofs_sb_info *sbi, xa_unlock(&sbi->managed_pslots); ++freed; - if (!--nr_shrink) + if (!--nr) return freed; xa_lock(&sbi->managed_pslots); } @@ -967,7 +934,7 @@ static void z_erofs_put_pcluster(struct erofs_sb_info *sbi, call_rcu(&pcl->rcu, z_erofs_rcu_callback); } -static void z_erofs_pcluster_end(struct z_erofs_decompress_frontend *fe) +static void z_erofs_pcluster_end(struct z_erofs_frontend *fe) { struct z_erofs_pcluster *pcl = fe->pcl; @@ -980,13 +947,9 @@ static void z_erofs_pcluster_end(struct z_erofs_decompress_frontend *fe) if (fe->candidate_bvpage) fe->candidate_bvpage = NULL; - /* - * if all pending pages are added, don't hold its reference - * any longer if the pcluster isn't hosted by ourselves. - */ + /* Drop refcount if it doesn't belong to our processing chain */ if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE) z_erofs_put_pcluster(EROFS_I_SB(fe->inode), pcl, false); - fe->pcl = NULL; } @@ -1015,7 +978,7 @@ static int z_erofs_read_fragment(struct super_block *sb, struct folio *folio, return 0; } -static int z_erofs_scan_folio(struct z_erofs_decompress_frontend *f, +static int z_erofs_scan_folio(struct z_erofs_frontend *f, struct folio *folio, bool ra) { struct inode *const inode = f->inode; @@ -1130,7 +1093,7 @@ static bool z_erofs_page_is_invalidated(struct page *page) return !page_folio(page)->mapping && !z_erofs_is_shortlived_page(page); } -struct z_erofs_decompress_backend { +struct z_erofs_backend { struct page *onstack_pages[Z_EROFS_ONSTACK_PAGES]; struct super_block *sb; struct z_erofs_pcluster *pcl; @@ -1150,7 +1113,7 @@ struct z_erofs_bvec_item { struct list_head list; }; -static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be, +static void z_erofs_do_decompressed_bvec(struct z_erofs_backend *be, struct z_erofs_bvec *bvec) { struct z_erofs_bvec_item *item; @@ -1173,8 +1136,7 @@ static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be, list_add(&item->list, &be->decompressed_secondary_bvecs); } -static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be, - int err) +static void z_erofs_fill_other_copies(struct z_erofs_backend *be, int err) { unsigned int off0 = be->pcl->pageofs_out; struct list_head *p, *n; @@ -1215,7 +1177,7 @@ static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be, } } -static void z_erofs_parse_out_bvecs(struct z_erofs_decompress_backend *be) +static void z_erofs_parse_out_bvecs(struct z_erofs_backend *be) { struct z_erofs_pcluster *pcl = be->pcl; struct z_erofs_bvec_iter biter; @@ -1240,8 +1202,7 @@ static void z_erofs_parse_out_bvecs(struct z_erofs_decompress_backend *be) z_erofs_put_shortlivedpage(be->pagepool, old_bvpage); } -static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be, - bool *overlapped) +static int z_erofs_parse_in_bvecs(struct z_erofs_backend *be, bool *overlapped) { struct z_erofs_pcluster *pcl = be->pcl; unsigned int pclusterpages = z_erofs_pclusterpages(pcl); @@ -1276,8 +1237,7 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be, return err; } -static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be, - int err) +static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err) { struct erofs_sb_info *const sbi = EROFS_SB(be->sb); struct z_erofs_pcluster *pcl = be->pcl; @@ -1394,7 +1354,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be, pcl->vcnt = 0; /* pcluster lock MUST be taken before the following line */ - WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_NIL); + WRITE_ONCE(pcl->next, NULL); mutex_unlock(&pcl->lock); if (z_erofs_is_inline_pcluster(pcl)) @@ -1407,21 +1367,19 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be, static int z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io, struct page **pagepool) { - struct z_erofs_decompress_backend be = { + struct z_erofs_backend be = { .sb = io->sb, .pagepool = pagepool, .decompressed_secondary_bvecs = LIST_HEAD_INIT(be.decompressed_secondary_bvecs), + .pcl = io->head, }; - z_erofs_next_pcluster_t owned = io->head; + struct z_erofs_pcluster *next; int err = io->eio ? -EIO : 0; - while (owned != Z_EROFS_PCLUSTER_TAIL) { - DBG_BUGON(owned == Z_EROFS_PCLUSTER_NIL); - - be.pcl = container_of(owned, struct z_erofs_pcluster, next); - owned = READ_ONCE(be.pcl->next); - + for (; be.pcl != Z_EROFS_PCLUSTER_TAIL; be.pcl = next) { + DBG_BUGON(!be.pcl); + next = READ_ONCE(be.pcl->next); err = z_erofs_decompress_pcluster(&be, err) ?: err; } return err; @@ -1487,7 +1445,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, } static void z_erofs_fill_bio_vec(struct bio_vec *bvec, - struct z_erofs_decompress_frontend *f, + struct z_erofs_frontend *f, struct z_erofs_pcluster *pcl, unsigned int nr, struct address_space *mc) @@ -1514,12 +1472,8 @@ repeat: DBG_BUGON(z_erofs_is_shortlived_page(bvec->bv_page)); folio = page_folio(zbv.page); - /* - * Handle preallocated cached folios. We tried to allocate such folios - * without triggering direct reclaim. If allocation failed, inplace - * file-backed folios will be used instead. - */ - if (folio->private == (void *)Z_EROFS_PREALLOCATED_PAGE) { + /* For preallocated managed folios, add them to page cache here */ + if (folio->private == Z_EROFS_PREALLOCATED_FOLIO) { tocache = true; goto out_tocache; } @@ -1631,18 +1585,13 @@ enum { NR_JOBQUEUES, }; -static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl, - z_erofs_next_pcluster_t qtail[], - z_erofs_next_pcluster_t owned_head) +static void z_erofs_move_to_bypass_queue(struct z_erofs_pcluster *pcl, + struct z_erofs_pcluster *next, + struct z_erofs_pcluster **qtail[]) { - z_erofs_next_pcluster_t *const submit_qtail = qtail[JQ_SUBMIT]; - z_erofs_next_pcluster_t *const bypass_qtail = qtail[JQ_BYPASS]; - WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_TAIL); - - WRITE_ONCE(*submit_qtail, owned_head); - WRITE_ONCE(*bypass_qtail, &pcl->next); - + WRITE_ONCE(*qtail[JQ_SUBMIT], next); + WRITE_ONCE(*qtail[JQ_BYPASS], pcl); qtail[JQ_BYPASS] = &pcl->next; } @@ -1671,15 +1620,15 @@ static void z_erofs_endio(struct bio *bio) bio_put(bio); } -static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, +static void z_erofs_submit_queue(struct z_erofs_frontend *f, struct z_erofs_decompressqueue *fgq, bool *force_fg, bool readahead) { struct super_block *sb = f->inode->i_sb; struct address_space *mc = MNGD_MAPPING(EROFS_SB(sb)); - z_erofs_next_pcluster_t qtail[NR_JOBQUEUES]; + struct z_erofs_pcluster **qtail[NR_JOBQUEUES]; struct z_erofs_decompressqueue *q[NR_JOBQUEUES]; - z_erofs_next_pcluster_t owned_head = f->owned_head; + struct z_erofs_pcluster *pcl, *next; /* bio is NULL initially, so no need to initialize last_{index,bdev} */ erofs_off_t last_pa; unsigned int nr_bios = 0; @@ -1695,22 +1644,19 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, qtail[JQ_SUBMIT] = &q[JQ_SUBMIT]->head; /* by default, all need io submission */ - q[JQ_SUBMIT]->head = owned_head; + q[JQ_SUBMIT]->head = next = f->head; do { struct erofs_map_dev mdev; - struct z_erofs_pcluster *pcl; erofs_off_t cur, end; struct bio_vec bvec; unsigned int i = 0; bool bypass = true; - DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_NIL); - pcl = container_of(owned_head, struct z_erofs_pcluster, next); - owned_head = READ_ONCE(pcl->next); - + pcl = next; + next = READ_ONCE(pcl->next); if (z_erofs_is_inline_pcluster(pcl)) { - move_to_bypass_jobqueue(pcl, qtail, owned_head); + z_erofs_move_to_bypass_queue(pcl, next, qtail); continue; } @@ -1782,8 +1728,8 @@ drain_io: if (!bypass) qtail[JQ_SUBMIT] = &pcl->next; else - move_to_bypass_jobqueue(pcl, qtail, owned_head); - } while (owned_head != Z_EROFS_PCLUSTER_TAIL); + z_erofs_move_to_bypass_queue(pcl, next, qtail); + } while (next != Z_EROFS_PCLUSTER_TAIL); if (bio) { if (erofs_is_fileio_mode(EROFS_SB(sb))) @@ -1792,9 +1738,9 @@ drain_io: erofs_fscache_submit_bio(bio); else submit_bio(bio); - if (memstall) - psi_memstall_leave(&pflags); } + if (memstall) + psi_memstall_leave(&pflags); /* * although background is preferred, no one is pending for submission. @@ -1807,17 +1753,16 @@ drain_io: z_erofs_decompress_kickoff(q[JQ_SUBMIT], nr_bios); } -static int z_erofs_runqueue(struct z_erofs_decompress_frontend *f, - unsigned int ra_folios) +static int z_erofs_runqueue(struct z_erofs_frontend *f, unsigned int rapages) { struct z_erofs_decompressqueue io[NR_JOBQUEUES]; struct erofs_sb_info *sbi = EROFS_I_SB(f->inode); - bool force_fg = z_erofs_is_sync_decompress(sbi, ra_folios); + bool force_fg = z_erofs_is_sync_decompress(sbi, rapages); int err; - if (f->owned_head == Z_EROFS_PCLUSTER_TAIL) + if (f->head == Z_EROFS_PCLUSTER_TAIL) return 0; - z_erofs_submit_queue(f, io, &force_fg, !!ra_folios); + z_erofs_submit_queue(f, io, &force_fg, !!rapages); /* handle bypass queue (no i/o pclusters) immediately */ err = z_erofs_decompress_queue(&io[JQ_BYPASS], &f->pagepool); @@ -1835,7 +1780,7 @@ static int z_erofs_runqueue(struct z_erofs_decompress_frontend *f, * Since partial uptodate is still unimplemented for now, we have to use * approximate readmore strategies as a start. */ -static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f, +static void z_erofs_pcluster_readmore(struct z_erofs_frontend *f, struct readahead_control *rac, bool backmost) { struct inode *inode = f->inode; @@ -1890,12 +1835,10 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f, static int z_erofs_read_folio(struct file *file, struct folio *folio) { struct inode *const inode = folio->mapping->host; - struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode); + Z_EROFS_DEFINE_FRONTEND(f, inode, folio_pos(folio)); int err; trace_erofs_read_folio(folio, false); - f.headoffset = (erofs_off_t)folio->index << PAGE_SHIFT; - z_erofs_pcluster_readmore(&f, NULL, true); err = z_erofs_scan_folio(&f, folio, false); z_erofs_pcluster_readmore(&f, NULL, false); @@ -1915,17 +1858,14 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio) static void z_erofs_readahead(struct readahead_control *rac) { struct inode *const inode = rac->mapping->host; - struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode); + Z_EROFS_DEFINE_FRONTEND(f, inode, readahead_pos(rac)); struct folio *head = NULL, *folio; - unsigned int nr_folios; + unsigned int nrpages = readahead_count(rac); int err; - f.headoffset = readahead_pos(rac); - z_erofs_pcluster_readmore(&f, rac, true); - nr_folios = readahead_count(rac); - trace_erofs_readpages(inode, readahead_index(rac), nr_folios, false); - + nrpages = readahead_count(rac); + trace_erofs_readpages(inode, readahead_index(rac), nrpages, false); while ((folio = readahead_folio(rac))) { folio->private = head; head = folio; @@ -1944,7 +1884,7 @@ static void z_erofs_readahead(struct readahead_control *rac) z_erofs_pcluster_readmore(&f, rac, false); z_erofs_pcluster_end(&f); - (void)z_erofs_runqueue(&f, nr_folios); + (void)z_erofs_runqueue(&f, nrpages); erofs_put_metabuf(&f.map.buf); erofs_release_pages(&f.pagepool); } diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 4535f2f0a014..689437e99a5a 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -97,17 +97,48 @@ static int get_compacted_la_distance(unsigned int lobits, return d1; } -static int unpack_compacted_index(struct z_erofs_maprecorder *m, - unsigned int amortizedshift, - erofs_off_t pos, bool lookahead) +static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m, + unsigned long lcn, bool lookahead) { - struct erofs_inode *const vi = EROFS_I(m->inode); + struct inode *const inode = m->inode; + struct erofs_inode *const vi = EROFS_I(inode); + const erofs_off_t ebase = sizeof(struct z_erofs_map_header) + + ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); const unsigned int lclusterbits = vi->z_logical_clusterbits; + const unsigned int totalidx = erofs_iblks(inode); + unsigned int compacted_4b_initial, compacted_2b, amortizedshift; unsigned int vcnt, lo, lobits, encodebits, nblk, bytes; - bool big_pcluster; + bool big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1; + erofs_off_t pos; u8 *in, type; int i; + if (lcn >= totalidx || lclusterbits > 14) + return -EINVAL; + + m->lcn = lcn; + /* used to align to 32-byte (compacted_2b) alignment */ + compacted_4b_initial = ((32 - ebase % 32) / 4) & 7; + compacted_2b = 0; + if ((vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) && + compacted_4b_initial < totalidx) + compacted_2b = rounddown(totalidx - compacted_4b_initial, 16); + + pos = ebase; + amortizedshift = 2; /* compact_4b */ + if (lcn >= compacted_4b_initial) { + pos += compacted_4b_initial * 4; + lcn -= compacted_4b_initial; + if (lcn < compacted_2b) { + amortizedshift = 1; + } else { + pos += compacted_2b * 2; + lcn -= compacted_2b; + } + } + pos += lcn * (1 << amortizedshift); + + /* figure out the lcluster count in this pack */ if (1 << amortizedshift == 4 && lclusterbits <= 14) vcnt = 2; else if (1 << amortizedshift == 2 && lclusterbits <= 12) @@ -122,7 +153,6 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, /* it doesn't equal to round_up(..) */ m->nextpackoff = round_down(pos, vcnt << amortizedshift) + (vcnt << amortizedshift); - big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1; lobits = max(lclusterbits, ilog2(Z_EROFS_LI_D0_CBLKCNT) + 1U); encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt; bytes = pos & ((vcnt << amortizedshift) - 1); @@ -207,53 +237,6 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, return 0; } -static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m, - unsigned long lcn, bool lookahead) -{ - struct inode *const inode = m->inode; - struct erofs_inode *const vi = EROFS_I(inode); - const erofs_off_t ebase = sizeof(struct z_erofs_map_header) + - ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); - unsigned int totalidx = erofs_iblks(inode); - unsigned int compacted_4b_initial, compacted_2b; - unsigned int amortizedshift; - erofs_off_t pos; - - if (lcn >= totalidx || vi->z_logical_clusterbits > 14) - return -EINVAL; - - m->lcn = lcn; - /* used to align to 32-byte (compacted_2b) alignment */ - compacted_4b_initial = (32 - ebase % 32) / 4; - if (compacted_4b_initial == 32 / 4) - compacted_4b_initial = 0; - - if ((vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) && - compacted_4b_initial < totalidx) - compacted_2b = rounddown(totalidx - compacted_4b_initial, 16); - else - compacted_2b = 0; - - pos = ebase; - if (lcn < compacted_4b_initial) { - amortizedshift = 2; - goto out; - } - pos += compacted_4b_initial * 4; - lcn -= compacted_4b_initial; - - if (lcn < compacted_2b) { - amortizedshift = 1; - goto out; - } - pos += compacted_2b * 2; - lcn -= compacted_2b; - amortizedshift = 2; -out: - pos += lcn * (1 << amortizedshift); - return unpack_compacted_index(m, amortizedshift, pos, lookahead); -} - static int z_erofs_load_lcluster_from_disk(struct z_erofs_maprecorder *m, unsigned int lcn, bool lookahead) { @@ -311,27 +294,23 @@ err_bogus: static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, unsigned int initial_lcn) { - struct super_block *sb = m->inode->i_sb; - struct erofs_inode *const vi = EROFS_I(m->inode); - struct erofs_map_blocks *const map = m->map; - const unsigned int lclusterbits = vi->z_logical_clusterbits; - unsigned long lcn; + struct inode *inode = m->inode; + struct super_block *sb = inode->i_sb; + struct erofs_inode *vi = EROFS_I(inode); + bool bigpcl1 = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1; + bool bigpcl2 = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2; + unsigned long lcn = m->lcn + 1; int err; - DBG_BUGON(m->type != Z_EROFS_LCLUSTER_TYPE_PLAIN && - m->type != Z_EROFS_LCLUSTER_TYPE_HEAD1 && - m->type != Z_EROFS_LCLUSTER_TYPE_HEAD2); + DBG_BUGON(m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD); DBG_BUGON(m->type != m->headtype); - if (m->headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN || - ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD1) && - !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) || - ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) && - !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2))) { - map->m_plen = 1ULL << lclusterbits; - return 0; - } - lcn = m->lcn + 1; + if ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD1 && !bigpcl1) || + ((m->headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN || + m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) && !bigpcl2) || + (lcn << vi->z_logical_clusterbits) >= inode->i_size) + m->compressedblks = 1; + if (m->compressedblks) goto out; @@ -356,9 +335,9 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, case Z_EROFS_LCLUSTER_TYPE_HEAD2: /* * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type - * rather than CBLKCNT, it's a 1 lcluster-sized pcluster. + * rather than CBLKCNT, it's a 1 block-sized pcluster. */ - m->compressedblks = 1 << (lclusterbits - sb->s_blocksize_bits); + m->compressedblks = 1; break; case Z_EROFS_LCLUSTER_TYPE_NONHEAD: if (m->delta[0] != 1) @@ -373,7 +352,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, return -EFSCORRUPTED; } out: - map->m_plen = erofs_pos(sb, m->compressedblks); + m->map->m_plen = erofs_pos(sb, m->compressedblks); return 0; err_bonus_cblkcnt: erofs_err(sb, "bogus CBLKCNT @ lcn %lu of nid %llu", lcn, vi->nid); diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c index 75704f58ecfa..55ff2ab5128e 100644 --- a/fs/erofs/zutil.c +++ b/fs/erofs/zutil.c @@ -87,8 +87,8 @@ int z_erofs_gbuf_growsize(unsigned int nrpages) tmp_pages[j] = gbuf->pages[j]; do { last = j; - j = alloc_pages_bulk_array(GFP_KERNEL, nrpages, - tmp_pages); + j = alloc_pages_bulk(GFP_KERNEL, nrpages, + tmp_pages); if (last == j) goto out; } while (j != nrpages); @@ -230,9 +230,10 @@ void erofs_shrinker_unregister(struct super_block *sb) struct erofs_sb_info *const sbi = EROFS_SB(sb); mutex_lock(&sbi->umount_mutex); - /* clean up all remaining pclusters in memory */ - z_erofs_shrink_scan(sbi, ~0UL); - + while (!xa_empty(&sbi->managed_pslots)) { + z_erofs_shrink_scan(sbi, ~0UL); + cond_resched(); + } spin_lock(&erofs_sb_list_lock); list_del(&sbi->list); spin_unlock(&erofs_sb_list_lock); @@ -242,7 +243,7 @@ void erofs_shrinker_unregister(struct super_block *sb) static unsigned long erofs_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { - return atomic_long_read(&erofs_global_shrink_cnt); + return atomic_long_read(&erofs_global_shrink_cnt) ?: SHRINK_EMPTY; } static unsigned long erofs_shrink_scan(struct shrinker *shrink, diff --git a/fs/eventpoll.c b/fs/eventpoll.c index f9898e60dd8b..7c0980db77b3 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -318,7 +318,7 @@ static void unlist_file(struct epitems_head *head) static long long_zero; static long long_max = LONG_MAX; -static struct ctl_table epoll_table[] = { +static const struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, diff --git a/fs/exec.c b/fs/exec.c index 98cb7ba9983c..506cd411f4ac 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -205,18 +205,10 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, /* * Avoid relying on expanding the stack down in GUP (which * does not work for STACK_GROWSUP anyway), and just do it - * by hand ahead of time. + * ahead of time. */ - if (write && pos < vma->vm_start) { - mmap_write_lock(mm); - ret = expand_downwards(vma, pos); - if (unlikely(ret < 0)) { - mmap_write_unlock(mm); - return NULL; - } - mmap_write_downgrade(mm); - } else - mmap_read_lock(mm); + if (!mmap_read_lock_maybe_expand(mm, vma, pos, write)) + return NULL; /* * We are doing an exec(). 'current' is the process @@ -892,7 +884,8 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) .lookup_flags = LOOKUP_FOLLOW, }; - if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) + if ((flags & + ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH | AT_EXECVE_CHECK)) != 0) return ERR_PTR(-EINVAL); if (flags & AT_SYMLINK_NOFOLLOW) open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW; @@ -912,7 +905,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) path_noexec(&file->f_path)) return ERR_PTR(-EACCES); - err = deny_write_access(file); + err = exe_file_deny_write_access(file); if (err) return ERR_PTR(err); @@ -927,7 +920,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) * Returns ERR_PTR on failure or allocated struct file on success. * * As this is a wrapper for the internal do_open_execat(), callers - * must call allow_write_access() before fput() on release. Also see + * must call exe_file_allow_write_access() before fput() on release. Also see * do_close_execat(). */ struct file *open_exec(const char *name) @@ -1194,16 +1187,16 @@ static int unshare_sighand(struct task_struct *me) } /* - * These functions flushes out all traces of the currently running executable - * so that a new one can be started + * This is unlocked -- the string will always be NUL-terminated, but + * may show overlapping contents if racing concurrent reads. */ - void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { - task_lock(tsk); + size_t len = min(strlen(buf), sizeof(tsk->comm) - 1); + trace_task_rename(tsk, buf); - strscpy_pad(tsk->comm, buf, sizeof(tsk->comm)); - task_unlock(tsk); + memcpy(tsk->comm, buf, len); + memset(&tsk->comm[len], 0, sizeof(tsk->comm) - len); perf_event_comm(tsk, exec); } @@ -1341,7 +1334,28 @@ int begin_new_exec(struct linux_binprm * bprm) set_dumpable(current->mm, SUID_DUMP_USER); perf_event_exec(); - __set_task_comm(me, kbasename(bprm->filename), true); + + /* + * If the original filename was empty, alloc_bprm() made up a path + * that will probably not be useful to admins running ps or similar. + * Let's fix it up to be something reasonable. + */ + if (bprm->comm_from_dentry) { + /* + * Hold RCU lock to keep the name from being freed behind our back. + * Use acquire semantics to make sure the terminating NUL from + * __d_alloc() is seen. + * + * Note, we're deliberately sloppy here. We don't need to care about + * detecting a concurrent rename and just want a terminated name. + */ + rcu_read_lock(); + __set_task_comm(me, smp_load_acquire(&bprm->file->f_path.dentry->d_name.name), + true); + rcu_read_unlock(); + } else { + __set_task_comm(me, kbasename(bprm->filename), true); + } /* An exec changes our domain. We are no longer part of the thread group */ @@ -1471,7 +1485,7 @@ static void do_close_execat(struct file *file) { if (!file) return; - allow_write_access(file); + exe_file_allow_write_access(file); fput(file); } @@ -1517,11 +1531,13 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int fl if (fd == AT_FDCWD || filename->name[0] == '/') { bprm->filename = filename->name; } else { - if (filename->name[0] == '\0') + if (filename->name[0] == '\0') { bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); - else + bprm->comm_from_dentry = 1; + } else { bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", fd, filename->name); + } if (!bprm->fdpath) goto out_free; @@ -1541,6 +1557,21 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int fl } bprm->interp = bprm->filename; + /* + * At this point, security_file_open() has already been called (with + * __FMODE_EXEC) and access control checks for AT_EXECVE_CHECK will + * stop just after the security_bprm_creds_for_exec() call in + * bprm_execve(). Indeed, the kernel should not try to parse the + * content of the file with exec_binprm() nor change the calling + * thread, which means that the following security functions will not + * be called: + * - security_bprm_check() + * - security_bprm_creds_from_file() + * - security_bprm_committing_creds() + * - security_bprm_committed_creds() + */ + bprm->is_check = !!(flags & AT_EXECVE_CHECK); + retval = bprm_mm_init(bprm); if (!retval) return bprm; @@ -1719,13 +1750,11 @@ int remove_arg_zero(struct linux_binprm *bprm) } EXPORT_SYMBOL(remove_arg_zero); -#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) /* * cycle the list of binary formats handler, until one recognizes the image */ static int search_binary_handler(struct linux_binprm *bprm) { - bool need_retry = IS_ENABLED(CONFIG_MODULES); struct linux_binfmt *fmt; int retval; @@ -1737,8 +1766,6 @@ static int search_binary_handler(struct linux_binprm *bprm) if (retval) return retval; - retval = -ENOENT; - retry: read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!try_module_get(fmt->module)) @@ -1756,17 +1783,7 @@ static int search_binary_handler(struct linux_binprm *bprm) } read_unlock(&binfmt_lock); - if (need_retry) { - if (printable(bprm->buf[0]) && printable(bprm->buf[1]) && - printable(bprm->buf[2]) && printable(bprm->buf[3])) - return retval; - if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0) - return retval; - need_retry = false; - goto retry; - } - - return retval; + return -ENOEXEC; } /* binfmt handlers will call back into begin_new_exec() on success. */ @@ -1797,7 +1814,7 @@ static int exec_binprm(struct linux_binprm *bprm) bprm->file = bprm->interpreter; bprm->interpreter = NULL; - allow_write_access(exec); + exe_file_allow_write_access(exec); if (unlikely(bprm->have_execfd)) { if (bprm->executable) { fput(exec); @@ -1836,7 +1853,7 @@ static int bprm_execve(struct linux_binprm *bprm) /* Set the unchanging part of bprm->cred */ retval = security_bprm_creds_for_exec(bprm); - if (retval) + if (retval || bprm->is_check) goto out; retval = exec_binprm(bprm); @@ -1904,9 +1921,6 @@ static int do_execveat_common(int fd, struct filename *filename, } retval = count(argv, MAX_ARG_STRINGS); - if (retval == 0) - pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", - current->comm, bprm->filename); if (retval < 0) goto out_free; bprm->argc = retval; @@ -1944,6 +1958,9 @@ static int do_execveat_common(int fd, struct filename *filename, if (retval < 0) goto out_free; bprm->argc = 1; + + pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", + current->comm, bprm->filename); } retval = bprm_execve(bprm); @@ -2142,7 +2159,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ return error; } -static struct ctl_table fs_exec_sysctls[] = { +static const struct ctl_table fs_exec_sysctls[] = { { .procname = "suid_dumpable", .data = &suid_dumpable, diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index fe0a9b8a0cd0..3103b932b674 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -122,7 +122,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent type = exfat_get_entry_type(ep); if (type == TYPE_UNUSED) { brelse(bh); - break; + goto out; } if (type != TYPE_FILE && type != TYPE_DIR) { @@ -170,6 +170,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent } } +out: dir_entry->namebuf.lfn[0] = '\0'; *cpos = EXFAT_DEN_TO_B(dentry); return 0; diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 773c320d68f3..9e5492ac409b 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -216,6 +216,16 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain if (err) goto dec_used_clus; + + if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) { + /* + * The cluster chain includes a loop, scan the + * bitmap to get the number of used clusters. + */ + exfat_count_used_clusters(sb, &sbi->used_clusters); + + return 0; + } } while (clu != EXFAT_EOF_CLUSTER); } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index fb38769c3e39..05b51e721783 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -545,6 +545,7 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) while (pos < new_valid_size) { u32 len; struct folio *folio; + unsigned long off; len = PAGE_SIZE - (pos & (PAGE_SIZE - 1)); if (pos + len > new_valid_size) @@ -554,6 +555,9 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) if (err) goto out; + off = offset_in_folio(folio, pos); + folio_zero_new_buffers(folio, off, off + len); + err = ops->write_end(file, mapping, pos, len, len, folio, NULL); if (err < 0) goto out; @@ -563,6 +567,8 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) cond_resched(); } + return 0; + out: return err; } diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 97d2774760fe..691dd77b6ab5 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -31,10 +31,9 @@ static inline void exfat_d_version_set(struct dentry *dentry, * If it happened, the negative dentry isn't actually negative anymore. So, * drop it. */ -static int exfat_d_revalidate(struct dentry *dentry, unsigned int flags) +static int exfat_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - int ret; - if (flags & LOOKUP_RCU) return -ECHILD; @@ -58,11 +57,7 @@ static int exfat_d_revalidate(struct dentry *dentry, unsigned int flags) if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; - spin_lock(&dentry->d_lock); - ret = inode_eq_iversion(d_inode(dentry->d_parent), - exfat_d_version(dentry)); - spin_unlock(&dentry->d_lock); - return ret; + return inode_eq_iversion(dir, exfat_d_version(dentry)); } /* returns the length of a struct qstr, ignoring trailing dots if necessary */ @@ -330,8 +325,8 @@ static int exfat_find_empty_entry(struct inode *inode, while ((dentry = exfat_search_empty_slot(sb, &hint_femp, p_dir, num_entries, es)) < 0) { - if (dentry == -EIO) - break; + if (dentry != -ENOSPC) + return dentry; if (exfat_check_max_dentries(inode)) return -ENOSPC; diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index e20d59221fc0..c9ca41d91a6c 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -31,8 +31,7 @@ config EXT4_FS select BUFFER_HEAD select JBD2 select CRC16 - select CRYPTO - select CRYPTO_CRC32C + select CRC32 select FS_IOMAP select FS_ENCRYPTION_ALGS if FS_ENCRYPTION help diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 74f2071189b2..4e7de7eaa374 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include #include @@ -1662,9 +1662,6 @@ struct ext4_sb_info { /* record the last minlen when FITRIM is called. */ unsigned long s_last_trim_minblks; - /* Reference to checksum algorithm driver via cryptoapi */ - struct crypto_shash *s_chksum_driver; - /* Precomputed FS UUID checksum for seeding other checksums */ __u32 s_csum_seed; @@ -2463,19 +2460,7 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, const void *address, unsigned int length) { - struct { - struct shash_desc shash; - char ctx[4]; - } desc; - - BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx)); - - desc.shash.tfm = sbi->s_chksum_driver; - *(u32 *)desc.ctx = crc; - - BUG_ON(crypto_shash_update(&desc.shash, address, length)); - - return *(u32 *)desc.ctx; + return crc32c(crc, address, length); } #ifdef __KERNEL__ @@ -3276,11 +3261,7 @@ extern int ext4_register_li_request(struct super_block *sb, static inline int ext4_has_metadata_csum(struct super_block *sb) { - WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) && - !EXT4_SB(sb)->s_chksum_driver); - - return ext4_has_feature_metadata_csum(sb) && - (EXT4_SB(sb)->s_chksum_driver != NULL); + return ext4_has_feature_metadata_csum(sb); } static inline int ext4_has_group_desc_csum(struct super_block *sb) diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 26c4fc37edcf..da4263a14a20 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -322,9 +322,7 @@ restart: WARN_ON(!list_empty(&ei->i_fc_dilist)); spin_unlock(&sbi->s_fc_lock); - if (fc_dentry->fcd_name.name && - fc_dentry->fcd_name.len > DNAME_INLINE_LEN) - kfree(fc_dentry->fcd_name.name); + release_dentry_name_snapshot(&fc_dentry->fcd_name); kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry); return; @@ -449,22 +447,7 @@ static int __track_dentry_update(handle_t *handle, struct inode *inode, node->fcd_op = dentry_update->op; node->fcd_parent = dir->i_ino; node->fcd_ino = inode->i_ino; - if (dentry->d_name.len > DNAME_INLINE_LEN) { - node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS); - if (!node->fcd_name.name) { - kmem_cache_free(ext4_fc_dentry_cachep, node); - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle); - mutex_lock(&ei->i_fc_lock); - return -ENOMEM; - } - memcpy((u8 *)node->fcd_name.name, dentry->d_name.name, - dentry->d_name.len); - } else { - memcpy(node->fcd_iname, dentry->d_name.name, - dentry->d_name.len); - node->fcd_name.name = node->fcd_iname; - } - node->fcd_name.len = dentry->d_name.len; + take_dentry_name_snapshot(&node->fcd_name, dentry); INIT_LIST_HEAD(&node->fcd_dilist); spin_lock(&sbi->s_fc_lock); if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || @@ -832,7 +815,7 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc, { struct ext4_fc_dentry_info fcd; struct ext4_fc_tl tl; - int dlen = fc_dentry->fcd_name.len; + int dlen = fc_dentry->fcd_name.name.len; u8 *dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + sizeof(fcd) + dlen, crc); @@ -847,7 +830,7 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc, dst += EXT4_FC_TAG_BASE_LEN; memcpy(dst, &fcd, sizeof(fcd)); dst += sizeof(fcd); - memcpy(dst, fc_dentry->fcd_name.name, dlen); + memcpy(dst, fc_dentry->fcd_name.name.name, dlen); return true; } @@ -1328,9 +1311,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) list_del_init(&fc_dentry->fcd_dilist); spin_unlock(&sbi->s_fc_lock); - if (fc_dentry->fcd_name.name && - fc_dentry->fcd_name.len > DNAME_INLINE_LEN) - kfree(fc_dentry->fcd_name.name); + release_dentry_name_snapshot(&fc_dentry->fcd_name); kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry); spin_lock(&sbi->s_fc_lock); } diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h index 2fadb2c4780c..3bd534e4dbbf 100644 --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -109,8 +109,7 @@ struct ext4_fc_dentry_update { int fcd_op; /* Type of update create / unlink / link */ int fcd_parent; /* Parent inode number */ int fcd_ino; /* Inode number */ - struct qstr fcd_name; /* Dirent name */ - unsigned char fcd_iname[DNAME_INLINE_LEN]; /* Dirent name string */ + struct name_snapshot fcd_name; /* Dirent name */ struct list_head fcd_list; struct list_head fcd_dilist; }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 3bd96c3d4cd0..a5205149adba 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -756,6 +756,9 @@ retry: return VM_FAULT_SIGBUS; } } else { + result = filemap_fsnotify_fault(vmf); + if (unlikely(result)) + return result; filemap_invalidate_lock_shared(mapping); } result = dax_iomap_fault(vmf, order, &pfn, &error, &ext4_iomap_ops); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 89aade6f45f6..7c54ae5fcbd4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5006,10 +5006,11 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, if (IS_ENCRYPTED(inode)) { inode->i_op = &ext4_encrypted_symlink_inode_operations; } else if (ext4_inode_is_fast_symlink(inode)) { - inode->i_link = (char *)ei->i_data; inode->i_op = &ext4_fast_symlink_inode_operations; nd_terminate_link(ei->i_data, inode->i_size, sizeof(ei->i_data) - 1); + inode_set_cached_link(inode, (char *)ei->i_data, + inode->i_size); } else { inode->i_op = &ext4_symlink_inode_operations; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index bcf2737078b8..536d56d15072 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3418,7 +3418,6 @@ retry: inode->i_op = &ext4_symlink_inode_operations; } else { inode->i_op = &ext4_fast_symlink_inode_operations; - inode->i_link = (char *)&EXT4_I(inode)->i_data; } } @@ -3434,6 +3433,9 @@ retry: disk_link.len); inode->i_size = disk_link.len - 1; EXT4_I(inode)->i_disksize = inode->i_size; + if (!IS_ENCRYPTED(inode)) + inode_set_cached_link(inode, (char *)&EXT4_I(inode)->i_data, + inode->i_size); } err = ext4_add_nondir(handle, dentry, &inode); if (handle) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 785809f33ff4..a50e5c31b937 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1380,8 +1380,6 @@ static void ext4_put_super(struct super_block *sb) */ kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); - if (sbi->s_chksum_driver) - crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); @@ -4634,15 +4632,6 @@ static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_blo ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE, ext4_orphan_file_block_trigger); - /* Load the checksum driver */ - sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); - if (IS_ERR(sbi->s_chksum_driver)) { - int ret = PTR_ERR(sbi->s_chksum_driver); - ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); - sbi->s_chksum_driver = NULL; - return ret; - } - /* Check superblock checksum */ if (!ext4_superblock_csum_verify(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " @@ -5312,6 +5301,9 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) /* i_version is always enabled now */ sb->s_flags |= SB_I_VERSION; + /* HSM events are allowed by default. */ + sb->s_iflags |= SB_I_ALLOW_HSM; + err = ext4_check_feature_compatibility(sb, es, silent); if (err) goto failed_mount; @@ -5687,9 +5679,6 @@ failed_mount3: del_timer_sync(&sbi->s_err_report); ext4_group_desc_free(sbi); failed_mount: - if (sbi->s_chksum_driver) - crypto_free_shash(sbi->s_chksum_driver); - #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif @@ -7494,6 +7483,5 @@ static void __exit ext4_exit_fs(void) MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: crc32c"); module_init(ext4_init_fs) module_exit(ext4_exit_fs) diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index 68a1e23e1557..5916a02fb46d 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -4,8 +4,7 @@ config F2FS_FS depends on BLOCK select BUFFER_HEAD select NLS - select CRYPTO - select CRYPTO_CRC32 + select CRC32 select F2FS_FS_XATTR if FS_ENCRYPTION select FS_ENCRYPTION_ALGS if FS_ENCRYPTION select FS_IOMAP diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 7f26440e8595..985690d81a82 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -846,7 +846,7 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index) bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages, int index, int nr_pages, bool uptodate) { - unsigned long pgidx = pages[index]->index; + unsigned long pgidx = page_folio(pages[index])->index; int i = uptodate ? 0 : 1; /* @@ -860,9 +860,11 @@ bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages, return false; for (; i < cc->cluster_size; i++) { - if (pages[index + i]->index != pgidx + i) + struct folio *folio = page_folio(pages[index + i]); + + if (folio->index != pgidx + i) return false; - if (uptodate && !PageUptodate(pages[index + i])) + if (uptodate && !folio_test_uptodate(folio)) return false; } @@ -1195,7 +1197,8 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata, .cluster_size = F2FS_I(inode)->i_cluster_size, .rpages = fsdata, }; - bool first_index = (index == cc.rpages[0]->index); + struct folio *folio = page_folio(cc.rpages[0]); + bool first_index = (index == folio->index); if (copied) set_cluster_dirty(&cc); @@ -1239,13 +1242,14 @@ int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock) int i; for (i = cluster_size - 1; i >= 0; i--) { - loff_t start = rpages[i]->index << PAGE_SHIFT; + struct folio *folio = page_folio(rpages[i]); + loff_t start = folio->index << PAGE_SHIFT; if (from <= start) { - zero_user_segment(rpages[i], 0, PAGE_SIZE); + folio_zero_segment(folio, 0, folio_size(folio)); } else { - zero_user_segment(rpages[i], from - start, - PAGE_SIZE); + folio_zero_segment(folio, from - start, + folio_size(folio)); break; } } @@ -1278,6 +1282,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode) ? 1 : 0, }; + struct folio *folio; struct dnode_of_data dn; struct node_info ni; struct compress_io_ctx *cic; @@ -1289,7 +1294,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, /* we should bypass data pages to proceed the kworker jobs */ if (unlikely(f2fs_cp_error(sbi))) { - mapping_set_error(cc->rpages[0]->mapping, -EIO); + mapping_set_error(inode->i_mapping, -EIO); goto out_free; } @@ -1316,7 +1321,8 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, goto out_put_dnode; } - psize = (loff_t)(cc->rpages[last_index]->index + 1) << PAGE_SHIFT; + folio = page_folio(cc->rpages[last_index]); + psize = folio_pos(folio) + folio_size(folio); err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false); if (err) @@ -1339,7 +1345,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, for (i = 0; i < cc->valid_nr_cpages; i++) { f2fs_set_compressed_page(cc->cpages[i], inode, - cc->rpages[i + 1]->index, cic); + page_folio(cc->rpages[i + 1])->index, cic); fio.compressed_page = cc->cpages[i]; fio.old_blkaddr = data_blkaddr(dn.inode, dn.node_page, @@ -1374,7 +1380,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, if (blkaddr == COMPRESS_ADDR) fio.compr_blocks++; if (__is_valid_data_blkaddr(blkaddr)) - f2fs_invalidate_blocks(sbi, blkaddr); + f2fs_invalidate_blocks(sbi, blkaddr, 1); f2fs_update_data_blkaddr(&dn, COMPRESS_ADDR); goto unlock_continue; } @@ -1384,7 +1390,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, if (i > cc->valid_nr_cpages) { if (__is_valid_data_blkaddr(blkaddr)) { - f2fs_invalidate_blocks(sbi, blkaddr); + f2fs_invalidate_blocks(sbi, blkaddr, 1); f2fs_update_data_blkaddr(&dn, NEW_ADDR); } goto unlock_continue; @@ -1545,6 +1551,7 @@ continue_unlock: if (!clear_page_dirty_for_io(cc->rpages[i])) goto continue_unlock; + submitted = 0; ret = f2fs_write_single_data_page(page_folio(cc->rpages[i]), &submitted, NULL, NULL, wbc, io_type, @@ -1903,11 +1910,12 @@ struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi) return sbi->compress_inode->i_mapping; } -void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr) +void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi, + block_t blkaddr, unsigned int len) { if (!sbi->compress_inode) return; - invalidate_mapping_pages(COMPRESS_MAPPING(sbi), blkaddr, blkaddr); + invalidate_mapping_pages(COMPRESS_MAPPING(sbi), blkaddr, blkaddr + len - 1); } void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page, diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index a2478c2afb3a..de4da6d9cd93 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -70,9 +70,9 @@ bool f2fs_is_cp_guaranteed(struct page *page) return false; } -static enum count_type __read_io_type(struct page *page) +static enum count_type __read_io_type(struct folio *folio) { - struct address_space *mapping = page_file_mapping(page); + struct address_space *mapping = folio->mapping; if (mapping) { struct inode *inode = mapping->host; @@ -136,27 +136,22 @@ struct bio_post_read_ctx { */ static void f2fs_finish_read_bio(struct bio *bio, bool in_task) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; + struct folio_iter fi; struct bio_post_read_ctx *ctx = bio->bi_private; - bio_for_each_segment_all(bv, bio, iter_all) { - struct page *page = bv->bv_page; + bio_for_each_folio_all(fi, bio) { + struct folio *folio = fi.folio; - if (f2fs_is_compressed_page(page)) { + if (f2fs_is_compressed_page(&folio->page)) { if (ctx && !ctx->decompression_attempted) - f2fs_end_read_compressed_page(page, true, 0, + f2fs_end_read_compressed_page(&folio->page, true, 0, in_task); - f2fs_put_page_dic(page, in_task); + f2fs_put_page_dic(&folio->page, in_task); continue; } - if (bio->bi_status) - ClearPageUptodate(page); - else - SetPageUptodate(page); - dec_page_count(F2FS_P_SB(page), __read_io_type(page)); - unlock_page(page); + dec_page_count(F2FS_F_SB(folio), __read_io_type(folio)); + folio_end_read(folio, bio->bi_status == 0); } if (ctx) @@ -516,10 +511,6 @@ static void f2fs_submit_write_bio(struct f2fs_sb_info *sbi, struct bio *bio, enum page_type type) { WARN_ON_ONCE(is_read_io(bio_op(bio))); - - if (f2fs_lfs_mode(sbi) && current->plug && PAGE_TYPE_ON_MAIN(type)) - blk_finish_plug(current->plug); - trace_f2fs_submit_write_bio(sbi->sb, type, bio); iostat_update_submit_ctx(bio, type); submit_bio(bio); @@ -689,33 +680,29 @@ void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi) int f2fs_submit_page_bio(struct f2fs_io_info *fio) { struct bio *bio; - struct page *page = fio->encrypted_page ? - fio->encrypted_page : fio->page; + struct folio *fio_folio = page_folio(fio->page); + struct folio *data_folio = fio->encrypted_page ? + page_folio(fio->encrypted_page) : fio_folio; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, fio->is_por ? META_POR : (__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC_ENHANCE))) return -EFSCORRUPTED; - trace_f2fs_submit_page_bio(page, fio); + trace_f2fs_submit_folio_bio(data_folio, fio); /* Allocate a new bio */ bio = __bio_alloc(fio, 1); - f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host, - page_folio(fio->page)->index, fio, GFP_NOIO); - - if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { - bio_put(bio); - return -EFAULT; - } + f2fs_set_bio_crypt_ctx(bio, fio_folio->mapping->host, + fio_folio->index, fio, GFP_NOIO); + bio_add_folio_nofail(bio, data_folio, folio_size(data_folio), 0); if (fio->io_wbc && !is_read_io(fio->op)) - wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page), - PAGE_SIZE); + wbc_account_cgroup_owner(fio->io_wbc, fio_folio, PAGE_SIZE); inc_page_count(fio->sbi, is_read_io(fio->op) ? - __read_io_type(page) : WB_DATA_TYPE(fio->page, false)); + __read_io_type(data_folio) : WB_DATA_TYPE(fio->page, false)); if (is_read_io(bio_op(bio))) f2fs_submit_read_bio(fio->sbi, bio, fio->type); @@ -894,7 +881,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio) __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) return -EFSCORRUPTED; - trace_f2fs_submit_page_bio(page, fio); + trace_f2fs_submit_folio_bio(page_folio(page), fio); if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block, fio->new_blkaddr)) @@ -1018,7 +1005,7 @@ alloc_new: io->last_block_in_bio = fio->new_blkaddr; - trace_f2fs_submit_page_write(fio->page, fio); + trace_f2fs_submit_folio_write(page_folio(fio->page), fio); #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && btype < META && is_end_zone_blkaddr(sbi, fio->new_blkaddr)) { @@ -1289,7 +1276,7 @@ struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index, struct address_space *mapping = inode->i_mapping; struct page *page; - page = find_get_page(mapping, index); + page = find_get_page_flags(mapping, index, FGP_ACCESSED); if (page && PageUptodate(page)) return page; f2fs_put_page(page, 0); @@ -1423,7 +1410,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) return err; if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) - f2fs_invalidate_internal_cache(sbi, old_blkaddr); + f2fs_invalidate_internal_cache(sbi, old_blkaddr, 1); f2fs_update_data_blkaddr(dn, dn->data_blkaddr); return 0; @@ -2464,7 +2451,7 @@ next_page: static int f2fs_read_data_folio(struct file *file, struct folio *folio) { - struct inode *inode = folio_file_mapping(folio)->host; + struct inode *inode = folio->mapping->host; int ret = -EAGAIN; trace_f2fs_readpage(folio, DATA); @@ -3163,6 +3150,7 @@ continue_unlock: continue; } #endif + submitted = 0; ret = f2fs_write_single_data_page(folio, &submitted, &bio, &last_block, wbc, io_type, 0, true); @@ -4043,7 +4031,6 @@ retry: cur_lblock = 1; /* force Empty message */ sis->max = cur_lblock; sis->pages = cur_lblock - 1; - sis->highest_bit = cur_lblock - 1; out: if (not_aligned) f2fs_warn(sbi, "Swapfile (%u) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(%lu * N)", diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 47a5c806cf16..54dd52de7269 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -175,7 +175,8 @@ static unsigned long dir_block_index(unsigned int level, static struct f2fs_dir_entry *find_in_block(struct inode *dir, struct page *dentry_page, const struct f2fs_filename *fname, - int *max_slots) + int *max_slots, + bool use_hash) { struct f2fs_dentry_block *dentry_blk; struct f2fs_dentry_ptr d; @@ -183,7 +184,7 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir, dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page); make_dentry_ptr_block(dir, &d, dentry_blk); - return f2fs_find_target_dentry(&d, fname, max_slots); + return f2fs_find_target_dentry(&d, fname, max_slots, use_hash); } static inline int f2fs_match_name(const struct inode *dir, @@ -208,7 +209,8 @@ static inline int f2fs_match_name(const struct inode *dir, } struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d, - const struct f2fs_filename *fname, int *max_slots) + const struct f2fs_filename *fname, int *max_slots, + bool use_hash) { struct f2fs_dir_entry *de; unsigned long bit_pos = 0; @@ -231,7 +233,7 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d, continue; } - if (de->hash_code == fname->hash) { + if (!use_hash || de->hash_code == fname->hash) { res = f2fs_match_name(d->inode, fname, d->filename[bit_pos], le16_to_cpu(de->name_len)); @@ -258,11 +260,12 @@ found: static struct f2fs_dir_entry *find_in_level(struct inode *dir, unsigned int level, const struct f2fs_filename *fname, - struct page **res_page) + struct page **res_page, + bool use_hash) { int s = GET_DENTRY_SLOTS(fname->disk_name.len); unsigned int nbucket, nblock; - unsigned int bidx, end_block; + unsigned int bidx, end_block, bucket_no; struct page *dentry_page; struct f2fs_dir_entry *de = NULL; pgoff_t next_pgofs; @@ -272,8 +275,11 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level); nblock = bucket_blocks(level); + bucket_no = use_hash ? le32_to_cpu(fname->hash) % nbucket : 0; + +start_find_bucket: bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level, - le32_to_cpu(fname->hash) % nbucket); + bucket_no); end_block = bidx + nblock; while (bidx < end_block) { @@ -290,7 +296,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, } } - de = find_in_block(dir, dentry_page, fname, &max_slots); + de = find_in_block(dir, dentry_page, fname, &max_slots, use_hash); if (IS_ERR(de)) { *res_page = ERR_CAST(de); de = NULL; @@ -307,12 +313,18 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, bidx++; } - if (!de && room && F2FS_I(dir)->chash != fname->hash) { - F2FS_I(dir)->chash = fname->hash; - F2FS_I(dir)->clevel = level; - } + if (de) + return de; - return de; + if (likely(use_hash)) { + if (room && F2FS_I(dir)->chash != fname->hash) { + F2FS_I(dir)->chash = fname->hash; + F2FS_I(dir)->clevel = level; + } + } else if (++bucket_no < nbucket) { + goto start_find_bucket; + } + return NULL; } struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, @@ -323,11 +335,15 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, struct f2fs_dir_entry *de = NULL; unsigned int max_depth; unsigned int level; + bool use_hash = true; *res_page = NULL; +#if IS_ENABLED(CONFIG_UNICODE) +start_find_entry: +#endif if (f2fs_has_inline_dentry(dir)) { - de = f2fs_find_in_inline_dir(dir, fname, res_page); + de = f2fs_find_in_inline_dir(dir, fname, res_page, use_hash); goto out; } @@ -343,11 +359,18 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, } for (level = 0; level < max_depth; level++) { - de = find_in_level(dir, level, fname, res_page); + de = find_in_level(dir, level, fname, res_page, use_hash); if (de || IS_ERR(*res_page)) break; } + out: +#if IS_ENABLED(CONFIG_UNICODE) + if (IS_CASEFOLDED(dir) && !de && use_hash) { + use_hash = false; + goto start_find_entry; + } +#endif /* This is to increase the speed of f2fs_create */ if (!de) F2FS_I(dir)->task = current; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 6f2cbf4c5740..1afa7be16e7d 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -24,7 +24,6 @@ #include #include #include -#include #include #include @@ -1768,9 +1767,6 @@ struct f2fs_sb_info { u64 sectors_written_start; u64 kbytes_written; - /* Reference to checksum algorithm driver via cryptoapi */ - struct crypto_shash *s_chksum_driver; - /* Precomputed FS UUID checksum for seeding other checksums */ __u32 s_chksum_seed; @@ -1948,21 +1944,7 @@ static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi, static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc, const void *address, unsigned int length) { - struct { - struct shash_desc shash; - char ctx[4]; - } desc; - int err; - - BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx)); - - desc.shash.tfm = sbi->s_chksum_driver; - *(u32 *)desc.ctx = crc; - - err = crypto_shash_update(&desc.shash, address, length); - BUG_ON(err); - - return *(u32 *)desc.ctx; + return crc32(crc, address, length); } static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, @@ -2003,9 +1985,14 @@ static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping) return F2FS_I_SB(mapping->host); } +static inline struct f2fs_sb_info *F2FS_F_SB(struct folio *folio) +{ + return F2FS_M_SB(folio->mapping); +} + static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page) { - return F2FS_M_SB(page_file_mapping(page)); + return F2FS_F_SB(page_folio(page)); } static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi) @@ -3583,7 +3570,8 @@ int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry, struct f2fs_filename *fname); void f2fs_free_filename(struct f2fs_filename *fname); struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d, - const struct f2fs_filename *fname, int *max_slots); + const struct f2fs_filename *fname, int *max_slots, + bool use_hash); int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, unsigned int start_pos, struct fscrypt_str *fstr); void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent, @@ -3718,7 +3706,8 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino); int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi); int f2fs_flush_device_cache(struct f2fs_sb_info *sbi); void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free); -void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); +void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr, + unsigned int len); bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); int f2fs_start_discard_thread(struct f2fs_sb_info *sbi); void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi); @@ -4219,7 +4208,8 @@ int f2fs_write_inline_data(struct inode *inode, struct folio *folio); int f2fs_recover_inline_data(struct inode *inode, struct page *npage); struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, const struct f2fs_filename *fname, - struct page **res_page); + struct page **res_page, + bool use_hash); int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, struct page *ipage); int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname, @@ -4386,7 +4376,8 @@ void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi); int __init f2fs_init_compress_cache(void); void f2fs_destroy_compress_cache(void); struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi); -void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr); +void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi, + block_t blkaddr, unsigned int len); void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page, nid_t ino, block_t blkaddr); bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page, @@ -4441,8 +4432,8 @@ static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { } static inline int __init f2fs_init_compress_cache(void) { return 0; } static inline void f2fs_destroy_compress_cache(void) { } -static inline void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, - block_t blkaddr) { } +static inline void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi, + block_t blkaddr, unsigned int len) { } static inline void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page, nid_t ino, block_t blkaddr) { } static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, @@ -4758,10 +4749,10 @@ static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi, } static inline void f2fs_invalidate_internal_cache(struct f2fs_sb_info *sbi, - block_t blkaddr) + block_t blkaddr, unsigned int len) { - f2fs_truncate_meta_inode_pages(sbi, blkaddr, 1); - f2fs_invalidate_compress_page(sbi, blkaddr); + f2fs_truncate_meta_inode_pages(sbi, blkaddr, len); + f2fs_invalidate_compress_pages_range(sbi, blkaddr, len); } #define EFSBADCRC EBADMSG /* Bad CRC detected */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index aa9679b3d8e4..f92a9fba9991 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -621,8 +621,11 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) int cluster_index = 0, valid_blocks = 0; int cluster_size = F2FS_I(dn->inode)->i_cluster_size; bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks); + block_t blkstart; + int blklen = 0; addr = get_dnode_addr(dn->inode, dn->node_page) + ofs; + blkstart = le32_to_cpu(*addr); /* Assumption: truncation starts with cluster */ for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) { @@ -638,26 +641,44 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) } if (blkaddr == NULL_ADDR) - continue; + goto next; f2fs_set_data_blkaddr(dn, NULL_ADDR); if (__is_valid_data_blkaddr(blkaddr)) { if (time_to_inject(sbi, FAULT_BLKADDR_CONSISTENCE)) - continue; + goto next; if (!f2fs_is_valid_blkaddr_raw(sbi, blkaddr, DATA_GENERIC_ENHANCE)) - continue; + goto next; if (compressed_cluster) valid_blocks++; } - f2fs_invalidate_blocks(sbi, blkaddr); + if (blkstart + blklen == blkaddr) { + blklen++; + } else { + f2fs_invalidate_blocks(sbi, blkstart, blklen); + blkstart = blkaddr; + blklen = 1; + } if (!released || blkaddr != COMPRESS_ADDR) nr_free++; + + continue; + +next: + if (blklen) + f2fs_invalidate_blocks(sbi, blkstart, blklen); + + blkstart = le32_to_cpu(*(addr + 1)); + blklen = 0; } + if (blklen) + f2fs_invalidate_blocks(sbi, blkstart, blklen); + if (compressed_cluster) f2fs_i_compr_blocks_update(dn->inode, valid_blocks, false); @@ -747,10 +768,8 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock) if (IS_DEVICE_ALIASING(inode)) { struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ]; struct extent_info ei = et->largest; - unsigned int i; - for (i = 0; i < ei.len; i++) - f2fs_invalidate_blocks(sbi, ei.blk + i); + f2fs_invalidate_blocks(sbi, ei.blk, ei.len); dec_valid_block_count(sbi, inode, ei.len); f2fs_update_time(sbi, REQ_TIME); @@ -1323,7 +1342,7 @@ static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr, ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA); if (ret) { dec_valid_block_count(sbi, inode, 1); - f2fs_invalidate_blocks(sbi, *blkaddr); + f2fs_invalidate_blocks(sbi, *blkaddr, 1); } else { f2fs_update_data_blkaddr(&dn, *blkaddr); } @@ -1575,7 +1594,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, break; } - f2fs_invalidate_blocks(sbi, dn->data_blkaddr); + f2fs_invalidate_blocks(sbi, dn->data_blkaddr, 1); f2fs_set_data_blkaddr(dn, NEW_ADDR); } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 3e1b6d2ff3a7..faf9fa1c804d 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -806,11 +806,14 @@ retry: goto out; } - if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result))) + if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result))) { ret = -EBUSY; - else - p.min_segno = *result; - goto out; + goto out; + } + if (gc_type == FG_GC) + clear_bit(GET_SEC_FROM_SEG(sbi, *result), dirty_i->victim_secmap); + p.min_segno = *result; + goto got_result; } ret = -ENODATA; @@ -1412,7 +1415,7 @@ static int move_data_block(struct inode *inode, block_t bidx, page_address(mpage), PAGE_SIZE); f2fs_put_page(mpage, 1); - f2fs_invalidate_internal_cache(fio.sbi, fio.old_blkaddr); + f2fs_invalidate_internal_cache(fio.sbi, fio.old_blkaddr, 1); set_page_dirty(fio.encrypted_page); if (clear_page_dirty_for_io(fio.encrypted_page)) diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 005babf1bed1..3e3c35d4c98b 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -81,7 +81,7 @@ bool f2fs_may_inline_dentry(struct inode *inode) void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage) { - struct inode *inode = folio_file_mapping(folio)->host; + struct inode *inode = folio->mapping->host; if (folio_test_uptodate(folio)) return; @@ -352,7 +352,8 @@ process_inline: struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, const struct f2fs_filename *fname, - struct page **res_page) + struct page **res_page, + bool use_hash) { struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); struct f2fs_dir_entry *de; @@ -369,7 +370,7 @@ struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, inline_dentry = inline_data_addr(dir, ipage); make_dentry_ptr_inline(dir, &d, inline_dentry); - de = f2fs_find_target_dentry(&d, fname, NULL); + de = f2fs_find_target_dentry(&d, fname, NULL, use_hash); unlock_page(ipage); if (IS_ERR(de)) { *res_page = ERR_CAST(de); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 282fd320bdb3..3dd25f64d6f1 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -302,15 +302,6 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) F2FS_TOTAL_EXTRA_ATTR_SIZE); return false; } - if (f2fs_sb_has_flexible_inline_xattr(sbi) && - f2fs_has_inline_xattr(inode) && - (!fi->i_inline_xattr_size || - fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { - f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, max: %lu", - __func__, inode->i_ino, fi->i_inline_xattr_size, - MAX_INLINE_XATTR_SIZE); - return false; - } if (f2fs_sb_has_compression(sbi) && fi->i_flags & F2FS_COMPR_FL && F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, @@ -320,6 +311,16 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) } } + if (f2fs_sb_has_flexible_inline_xattr(sbi) && + f2fs_has_inline_xattr(inode) && + (fi->i_inline_xattr_size < MIN_INLINE_XATTR_SIZE || + fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { + f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, min: %zu, max: %lu", + __func__, inode->i_ino, fi->i_inline_xattr_size, + MIN_INLINE_XATTR_SIZE, MAX_INLINE_XATTR_SIZE); + return false; + } + if (!f2fs_sb_has_extra_attr(sbi)) { if (f2fs_sb_has_project_quota(sbi)) { f2fs_warn(sbi, "%s: corrupted inode ino=%lx, wrong feature flag: %u, run fsck to fix.", diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 57d46e1439de..a278c7da8177 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -341,6 +341,7 @@ fail_drop: trace_f2fs_new_inode(inode, err); dquot_drop(inode); inode->i_flags |= S_NOQUOTA; + make_bad_inode(inode); if (nid_free) set_inode_flag(inode, FI_FREE_NID); clear_nlink(inode); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 0b900a7a48e5..f88392fc4ba9 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -558,6 +558,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, block_t blkaddr; int i; + ni->flag = 0; ni->nid = nid; retry: /* Check nat cache */ @@ -916,7 +917,7 @@ static int truncate_node(struct dnode_of_data *dn) } /* Deallocate node address */ - f2fs_invalidate_blocks(sbi, ni.blk_addr); + f2fs_invalidate_blocks(sbi, ni.blk_addr, 1); dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino); set_node_addr(sbi, &ni, NULL_ADDR, false); @@ -1274,8 +1275,9 @@ int f2fs_remove_inode_page(struct inode *inode) } /* remove potential inline_data blocks */ - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode)) + if (!IS_DEVICE_ALIASING(inode) && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) f2fs_truncate_data_blocks_range(&dn, 1); /* 0 is possible, after f2fs_new_inode() has failed */ @@ -2763,7 +2765,7 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page) if (err) return err; - f2fs_invalidate_blocks(sbi, ni.blk_addr); + f2fs_invalidate_blocks(sbi, ni.blk_addr, 1); dec_valid_node_count(sbi, inode, false); set_node_addr(sbi, &ni, NULL_ADDR, false); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index f35be2c48e3c..69a2027e3ebc 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -899,10 +899,8 @@ skip: * and the f2fs is not read only, check and fix zoned block devices' * write pointer consistency. */ - if (!err) { + if (!err) err = f2fs_check_and_fix_write_pointer(sbi); - ret = err; - } if (!err) clear_sbi_flag(sbi, SBI_POR_DOING); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index eade36c5ef13..c282e8a0a2ec 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -201,6 +201,12 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) clear_inode_flag(inode, FI_ATOMIC_FILE); if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) { clear_inode_flag(inode, FI_ATOMIC_DIRTIED); + /* + * The vfs inode keeps clean during commit, but the f2fs inode + * doesn't. So clear the dirty state after commit and let + * f2fs_mark_inode_dirty_sync ensure a consistent dirty state. + */ + f2fs_inode_synced(inode); f2fs_mark_inode_dirty_sync(inode, true); } stat_dec_atomic_inode(inode); @@ -245,7 +251,7 @@ retry: if (!__is_valid_data_blkaddr(new_addr)) { if (new_addr == NULL_ADDR) dec_valid_block_count(sbi, inode, 1); - f2fs_invalidate_blocks(sbi, dn.data_blkaddr); + f2fs_invalidate_blocks(sbi, dn.data_blkaddr, 1); f2fs_update_data_blkaddr(&dn, new_addr); } else { f2fs_replace_block(sbi, &dn, dn.data_blkaddr, @@ -2426,15 +2432,117 @@ static void update_segment_mtime(struct f2fs_sb_info *sbi, block_t blkaddr, SIT_I(sbi)->max_mtime = ctime; } +/* + * NOTE: when updating multiple blocks at the same time, please ensure + * that the consecutive input blocks belong to the same segment. + */ +static int update_sit_entry_for_release(struct f2fs_sb_info *sbi, struct seg_entry *se, + block_t blkaddr, unsigned int offset, int del) +{ + bool exist; +#ifdef CONFIG_F2FS_CHECK_FS + bool mir_exist; +#endif + int i; + int del_count = -del; + + f2fs_bug_on(sbi, GET_SEGNO(sbi, blkaddr) != GET_SEGNO(sbi, blkaddr + del_count - 1)); + + for (i = 0; i < del_count; i++) { + exist = f2fs_test_and_clear_bit(offset + i, se->cur_valid_map); +#ifdef CONFIG_F2FS_CHECK_FS + mir_exist = f2fs_test_and_clear_bit(offset + i, + se->cur_valid_map_mir); + if (unlikely(exist != mir_exist)) { + f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d", + blkaddr + i, exist); + f2fs_bug_on(sbi, 1); + } +#endif + if (unlikely(!exist)) { + f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u", blkaddr + i); + f2fs_bug_on(sbi, 1); + se->valid_blocks++; + del += 1; + } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + /* + * If checkpoints are off, we must not reuse data that + * was used in the previous checkpoint. If it was used + * before, we must track that to know how much space we + * really have. + */ + if (f2fs_test_bit(offset + i, se->ckpt_valid_map)) { + spin_lock(&sbi->stat_lock); + sbi->unusable_block_count++; + spin_unlock(&sbi->stat_lock); + } + } + + if (f2fs_block_unit_discard(sbi) && + f2fs_test_and_clear_bit(offset + i, se->discard_map)) + sbi->discard_blks++; + + if (!f2fs_test_bit(offset + i, se->ckpt_valid_map)) + se->ckpt_valid_blocks -= 1; + } + + return del; +} + +static int update_sit_entry_for_alloc(struct f2fs_sb_info *sbi, struct seg_entry *se, + block_t blkaddr, unsigned int offset, int del) +{ + bool exist; +#ifdef CONFIG_F2FS_CHECK_FS + bool mir_exist; +#endif + + exist = f2fs_test_and_set_bit(offset, se->cur_valid_map); +#ifdef CONFIG_F2FS_CHECK_FS + mir_exist = f2fs_test_and_set_bit(offset, + se->cur_valid_map_mir); + if (unlikely(exist != mir_exist)) { + f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d", + blkaddr, exist); + f2fs_bug_on(sbi, 1); + } +#endif + if (unlikely(exist)) { + f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", blkaddr); + f2fs_bug_on(sbi, 1); + se->valid_blocks--; + del = 0; + } + + if (f2fs_block_unit_discard(sbi) && + !f2fs_test_and_set_bit(offset, se->discard_map)) + sbi->discard_blks--; + + /* + * SSR should never reuse block which is checkpointed + * or newly invalidated. + */ + if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { + if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) + se->ckpt_valid_blocks++; + } + + if (!f2fs_test_bit(offset, se->ckpt_valid_map)) + se->ckpt_valid_blocks += del; + + return del; +} + +/* + * If releasing blocks, this function supports updating multiple consecutive blocks + * at one time, but please note that these consecutive blocks need to belong to the + * same segment. + */ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) { struct seg_entry *se; unsigned int segno, offset; long int new_vblocks; - bool exist; -#ifdef CONFIG_F2FS_CHECK_FS - bool mir_exist; -#endif segno = GET_SEGNO(sbi, blkaddr); if (segno == NULL_SEGNO) @@ -2451,73 +2559,10 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) /* Update valid block bitmap */ if (del > 0) { - exist = f2fs_test_and_set_bit(offset, se->cur_valid_map); -#ifdef CONFIG_F2FS_CHECK_FS - mir_exist = f2fs_test_and_set_bit(offset, - se->cur_valid_map_mir); - if (unlikely(exist != mir_exist)) { - f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d", - blkaddr, exist); - f2fs_bug_on(sbi, 1); - } -#endif - if (unlikely(exist)) { - f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", - blkaddr); - f2fs_bug_on(sbi, 1); - se->valid_blocks--; - del = 0; - } - - if (f2fs_block_unit_discard(sbi) && - !f2fs_test_and_set_bit(offset, se->discard_map)) - sbi->discard_blks--; - - /* - * SSR should never reuse block which is checkpointed - * or newly invalidated. - */ - if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { - if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) - se->ckpt_valid_blocks++; - } + del = update_sit_entry_for_alloc(sbi, se, blkaddr, offset, del); } else { - exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map); -#ifdef CONFIG_F2FS_CHECK_FS - mir_exist = f2fs_test_and_clear_bit(offset, - se->cur_valid_map_mir); - if (unlikely(exist != mir_exist)) { - f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d", - blkaddr, exist); - f2fs_bug_on(sbi, 1); - } -#endif - if (unlikely(!exist)) { - f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u", - blkaddr); - f2fs_bug_on(sbi, 1); - se->valid_blocks++; - del = 0; - } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { - /* - * If checkpoints are off, we must not reuse data that - * was used in the previous checkpoint. If it was used - * before, we must track that to know how much space we - * really have. - */ - if (f2fs_test_bit(offset, se->ckpt_valid_map)) { - spin_lock(&sbi->stat_lock); - sbi->unusable_block_count++; - spin_unlock(&sbi->stat_lock); - } - } - - if (f2fs_block_unit_discard(sbi) && - f2fs_test_and_clear_bit(offset, se->discard_map)) - sbi->discard_blks++; + del = update_sit_entry_for_release(sbi, se, blkaddr, offset, del); } - if (!f2fs_test_bit(offset, se->ckpt_valid_map)) - se->ckpt_valid_blocks += del; __mark_sit_entry_dirty(sbi, segno); @@ -2528,25 +2573,43 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) get_sec_entry(sbi, segno)->valid_blocks += del; } -void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) +void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr, + unsigned int len) { unsigned int segno = GET_SEGNO(sbi, addr); struct sit_info *sit_i = SIT_I(sbi); + block_t addr_start = addr, addr_end = addr + len - 1; + unsigned int seg_num = GET_SEGNO(sbi, addr_end) - segno + 1; + unsigned int i = 1, max_blocks = sbi->blocks_per_seg, cnt; f2fs_bug_on(sbi, addr == NULL_ADDR); if (addr == NEW_ADDR || addr == COMPRESS_ADDR) return; - f2fs_invalidate_internal_cache(sbi, addr); + f2fs_invalidate_internal_cache(sbi, addr, len); /* add it into sit main buffer */ down_write(&sit_i->sentry_lock); - update_segment_mtime(sbi, addr, 0); - update_sit_entry(sbi, addr, -1); + if (seg_num == 1) + cnt = len; + else + cnt = max_blocks - GET_BLKOFF_FROM_SEG0(sbi, addr); - /* add it into dirty seglist */ - locate_dirty_segment(sbi, segno); + do { + update_segment_mtime(sbi, addr_start, 0); + update_sit_entry(sbi, addr_start, -cnt); + + /* add it into dirty seglist */ + locate_dirty_segment(sbi, segno); + + /* update @addr_start and @cnt and @segno */ + addr_start = START_BLOCK(sbi, ++segno); + if (++i == seg_num) + cnt = GET_BLKOFF_FROM_SEG0(sbi, addr_end) + 1; + else + cnt = max_blocks; + } while (i <= seg_num); up_write(&sit_i->sentry_lock); } @@ -3857,7 +3920,7 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) goto out; } if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) - f2fs_invalidate_internal_cache(fio->sbi, fio->old_blkaddr); + f2fs_invalidate_internal_cache(fio->sbi, fio->old_blkaddr, 1); /* writeout dirty page into bdev */ f2fs_submit_page_write(fio); @@ -4049,7 +4112,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, update_sit_entry(sbi, new_blkaddr, 1); } if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) { - f2fs_invalidate_internal_cache(sbi, old_blkaddr); + f2fs_invalidate_internal_cache(sbi, old_blkaddr, 1); if (!from_gc) update_segment_mtime(sbi, old_blkaddr, 0); update_sit_entry(sbi, old_blkaddr, -1); @@ -5405,7 +5468,8 @@ int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi) { int ret; - if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb)) + if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb) || + f2fs_hw_is_readonly(sbi)) return 0; f2fs_notice(sbi, "Checking entire write pointers"); @@ -5492,8 +5556,10 @@ unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi, secno = GET_SEC_FROM_SEG(sbi, segno); start = GET_SEG_FROM_SEC(sbi, secno); - if (!__is_large_section(sbi)) - return get_seg_entry(sbi, start + i)->mtime; + if (!__is_large_section(sbi)) { + mtime = get_seg_entry(sbi, start + i)->mtime; + goto out; + } for (i = 0; i < usable_segs_per_sec; i++) { /* for large section, only check the mtime of valid segments */ @@ -5506,7 +5572,11 @@ unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi, if (total_valid_blocks == 0) return INVALID_MTIME; - return div_u64(mtime, total_valid_blocks); + mtime = div_u64(mtime, total_valid_blocks); +out: + if (unlikely(mtime == INVALID_MTIME)) + mtime -= 1; + return mtime; } /* diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index fc7d463dee15..19b67828ae32 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1694,8 +1694,6 @@ static void f2fs_put_super(struct super_block *sb) kvfree(sbi->ckpt); - if (sbi->s_chksum_driver) - crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->raw_super); f2fs_destroy_page_array_cache(sbi); @@ -4466,15 +4464,6 @@ try_onemore: } mutex_init(&sbi->flush_lock); - /* Load the checksum driver */ - sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0); - if (IS_ERR(sbi->s_chksum_driver)) { - f2fs_err(sbi, "Cannot load crc32 driver."); - err = PTR_ERR(sbi->s_chksum_driver); - sbi->s_chksum_driver = NULL; - goto free_sbi; - } - /* set a block size */ if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) { f2fs_err(sbi, "unable to set blocksize"); @@ -4919,8 +4908,6 @@ free_options: free_sb_buf: kfree(raw_super); free_sbi: - if (sbi->s_chksum_driver) - crypto_free_shash(sbi->s_chksum_driver); kfree(sbi); sb->s_fs_info = NULL; @@ -5127,5 +5114,3 @@ module_exit(exit_f2fs_fs) MODULE_AUTHOR("Samsung Electronics's Praesto Team"); MODULE_DESCRIPTION("Flash Friendly File System"); MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: crc32"); - diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 6b99dc49f776..d15c68b28952 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -1472,7 +1472,7 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq, le32_to_cpu(sbi->raw_super->segment_count_main); int i, j; - seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n" + seq_puts(seq, "format: segment_type|valid_blocks|bitmaps|mtime\n" "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n"); for (i = 0; i < total_segs; i++) { @@ -1482,6 +1482,7 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq, seq_printf(seq, "%d|%-3u|", se->type, se->valid_blocks); for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++) seq_printf(seq, " %.2x", se->cur_valid_map[j]); + seq_printf(seq, "| %llx", se->mtime); seq_putc(seq, '\n'); } return 0; diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 15bf32c21ac0..926c26e90ef8 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -43,17 +43,13 @@ static inline void vfat_d_version_set(struct dentry *dentry, * If it happened, the negative dentry isn't actually negative * anymore. So, drop it. */ -static int vfat_revalidate_shortname(struct dentry *dentry) +static bool vfat_revalidate_shortname(struct dentry *dentry, struct inode *dir) { - int ret = 1; - spin_lock(&dentry->d_lock); - if (!inode_eq_iversion(d_inode(dentry->d_parent), vfat_d_version(dentry))) - ret = 0; - spin_unlock(&dentry->d_lock); - return ret; + return inode_eq_iversion(dir, vfat_d_version(dentry)); } -static int vfat_revalidate(struct dentry *dentry, unsigned int flags) +static int vfat_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; @@ -61,10 +57,11 @@ static int vfat_revalidate(struct dentry *dentry, unsigned int flags) /* This is not negative dentry. Always valid. */ if (d_really_is_positive(dentry)) return 1; - return vfat_revalidate_shortname(dentry); + return vfat_revalidate_shortname(dentry, dir); } -static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) +static int vfat_revalidate_ci(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; @@ -97,7 +94,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; - return vfat_revalidate_shortname(dentry); + return vfat_revalidate_shortname(dentry, dir); } /* returns the length of a struct qstr, ignoring trailing dots */ diff --git a/fs/fcntl.c b/fs/fcntl.c index 49884fa3c81d..5598e4d57422 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -1158,10 +1158,10 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != + BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | - __FMODE_EXEC | __FMODE_NONOTIFY)); + __FMODE_EXEC)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, diff --git a/fs/fhandle.c b/fs/fhandle.c index ec9145047dfc..3e092ae6d142 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -187,17 +187,6 @@ static int get_path_from_fd(int fd, struct path *root) return 0; } -enum handle_to_path_flags { - HANDLE_CHECK_PERMS = (1 << 0), - HANDLE_CHECK_SUBTREE = (1 << 1), -}; - -struct handle_to_path_ctx { - struct path root; - enum handle_to_path_flags flags; - unsigned int fh_flags; -}; - static int vfs_dentry_acceptable(void *context, struct dentry *dentry) { struct handle_to_path_ctx *ctx = context; @@ -261,50 +250,55 @@ static int do_handle_to_path(struct file_handle *handle, struct path *path, { int handle_dwords; struct vfsmount *mnt = ctx->root.mnt; + struct dentry *dentry; /* change the handle size to multiple of sizeof(u32) */ handle_dwords = handle->handle_bytes >> 2; - path->dentry = exportfs_decode_fh_raw(mnt, - (struct fid *)handle->f_handle, - handle_dwords, handle->handle_type, - ctx->fh_flags, - vfs_dentry_acceptable, ctx); - if (IS_ERR_OR_NULL(path->dentry)) { - if (path->dentry == ERR_PTR(-ENOMEM)) + dentry = exportfs_decode_fh_raw(mnt, (struct fid *)handle->f_handle, + handle_dwords, handle->handle_type, + ctx->fh_flags, vfs_dentry_acceptable, + ctx); + if (IS_ERR_OR_NULL(dentry)) { + if (dentry == ERR_PTR(-ENOMEM)) return -ENOMEM; return -ESTALE; } + path->dentry = dentry; path->mnt = mntget(mnt); return 0; } -/* - * Allow relaxed permissions of file handles if the caller has the - * ability to mount the filesystem or create a bind-mount of the - * provided @mountdirfd. - * - * In both cases the caller may be able to get an unobstructed way to - * the encoded file handle. If the caller is only able to create a - * bind-mount we need to verify that there are no locked mounts on top - * of it that could prevent us from getting to the encoded file. - * - * In principle, locked mounts can prevent the caller from mounting the - * filesystem but that only applies to procfs and sysfs neither of which - * support decoding file handles. - */ -static inline bool may_decode_fh(struct handle_to_path_ctx *ctx, - unsigned int o_flags) +static inline int may_decode_fh(struct handle_to_path_ctx *ctx, + unsigned int o_flags) { struct path *root = &ctx->root; + if (capable(CAP_DAC_READ_SEARCH)) + return 0; + /* - * Restrict to O_DIRECTORY to provide a deterministic API that avoids a - * confusing api in the face of disconnected non-dir dentries. + * Allow relaxed permissions of file handles if the caller has + * the ability to mount the filesystem or create a bind-mount of + * the provided @mountdirfd. + * + * In both cases the caller may be able to get an unobstructed + * way to the encoded file handle. If the caller is only able to + * create a bind-mount we need to verify that there are no + * locked mounts on top of it that could prevent us from getting + * to the encoded file. + * + * In principle, locked mounts can prevent the caller from + * mounting the filesystem but that only applies to procfs and + * sysfs neither of which support decoding file handles. + * + * Restrict to O_DIRECTORY to provide a deterministic API that + * avoids a confusing api in the face of disconnected non-dir + * dentries. * * There's only one dentry for each directory inode (VFS rule)... */ if (!(o_flags & O_DIRECTORY)) - return false; + return -EPERM; if (ns_capable(root->mnt->mnt_sb->s_user_ns, CAP_SYS_ADMIN)) ctx->flags = HANDLE_CHECK_PERMS; @@ -314,14 +308,14 @@ static inline bool may_decode_fh(struct handle_to_path_ctx *ctx, !has_locked_children(real_mount(root->mnt), root->dentry)) ctx->flags = HANDLE_CHECK_PERMS | HANDLE_CHECK_SUBTREE; else - return false; + return -EPERM; /* Are we able to override DAC permissions? */ if (!ns_capable(current_user_ns(), CAP_DAC_READ_SEARCH)) - return false; + return -EPERM; ctx->fh_flags = EXPORT_FH_DIR_ONLY; - return true; + return 0; } static int handle_to_path(int mountdirfd, struct file_handle __user *ufh, @@ -331,15 +325,19 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh, struct file_handle f_handle; struct file_handle *handle = NULL; struct handle_to_path_ctx ctx = {}; + const struct export_operations *eops; retval = get_path_from_fd(mountdirfd, &ctx.root); if (retval) goto out_err; - if (!capable(CAP_DAC_READ_SEARCH) && !may_decode_fh(&ctx, o_flags)) { - retval = -EPERM; + eops = ctx.root.mnt->mnt_sb->s_export_op; + if (eops && eops->permission) + retval = eops->permission(&ctx, o_flags); + else + retval = may_decode_fh(&ctx, o_flags); + if (retval) goto out_path; - } if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) { retval = -EFAULT; @@ -398,29 +396,28 @@ static long do_handle_open(int mountdirfd, struct file_handle __user *ufh, int open_flag) { long retval = 0; - struct path path; + struct path path __free(path_put) = {}; struct file *file; - int fd; + const struct export_operations *eops; retval = handle_to_path(mountdirfd, ufh, &path, open_flag); if (retval) return retval; - fd = get_unused_fd_flags(open_flag); - if (fd < 0) { - path_put(&path); + CLASS(get_unused_fd, fd)(O_CLOEXEC); + if (fd < 0) return fd; - } - file = file_open_root(&path, "", open_flag, 0); - if (IS_ERR(file)) { - put_unused_fd(fd); - retval = PTR_ERR(file); - } else { - retval = fd; - fd_install(fd, file); - } - path_put(&path); - return retval; + + eops = path.mnt->mnt_sb->s_export_op; + if (eops->open) + file = eops->open(&path, open_flag); + else + file = file_open_root(&path, "", open_flag, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + + fd_install(fd, file); + return take_fd(fd); } /** diff --git a/fs/file.c b/fs/file.c index fb1011cf6b4a..d868cdb95d1e 100644 --- a/fs/file.c +++ b/fs/file.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "internal.h" @@ -278,10 +279,6 @@ repeat: if (nr < fdt->max_fds) return 0; - /* Can we expand? */ - if (nr >= sysctl_nr_open) - return -EMFILE; - if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); @@ -289,6 +286,10 @@ repeat: goto repeat; } + /* Can we expand? */ + if (unlikely(nr >= sysctl_nr_open)) + return -EMFILE; + /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); @@ -1230,17 +1231,9 @@ __releases(&files->file_lock) /* * We need to detect attempts to do dup2() over allocated but still - * not finished descriptor. NB: OpenBSD avoids that at the price of - * extra work in their equivalent of fget() - they insert struct - * file immediately after grabbing descriptor, mark it larval if - * more work (e.g. actual opening) is needed and make sure that - * fget() treats larval files as absent. Potentially interesting, - * but while extra work in fget() is trivial, locking implications - * and amount of surgery on open()-related paths in VFS are not. - * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" - * deadlocks in rather amusing ways, AFAICS. All of that is out of - * scope of POSIX or SUS, since neither considers shared descriptor - * tables and this condition does not arise without those. + * not finished descriptor. + * + * POSIX is silent on the issue, we return -EBUSY. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); diff --git a/fs/file_table.c b/fs/file_table.c index 976736be47cb..f0291a66f9db 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -106,7 +106,7 @@ static int proc_nr_files(const struct ctl_table *table, int write, void *buffer, return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_stat_sysctls[] = { +static const struct ctl_table fs_stat_sysctls[] = { { .procname = "file-nr", .data = &files_stat, @@ -128,7 +128,7 @@ static struct ctl_table fs_stat_sysctls[] = { .data = &sysctl_nr_open, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_douintvec_minmax, .extra1 = &sysctl_nr_open_min, .extra2 = &sysctl_nr_open_max, }, @@ -351,9 +351,7 @@ static struct file *alloc_file(const struct path *path, int flags, static inline int alloc_path_pseudo(const char *name, struct inode *inode, struct vfsmount *mnt, struct path *path) { - struct qstr this = QSTR_INIT(name, strlen(name)); - - path->dentry = d_alloc_pseudo(mnt->mnt_sb, &this); + path->dentry = d_alloc_pseudo(mnt->mnt_sb, &QSTR(name)); if (!path->dentry) return -ENOMEM; path->mnt = mntget(mnt); @@ -478,6 +476,8 @@ static void ____fput(struct callback_head *work) __fput(container_of(work, struct file, f_task_work)); } +static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); + /* * If kernel thread really needs to have the final fput() it has done * to complete, call this. The only user right now is the boot - we @@ -491,11 +491,10 @@ static void ____fput(struct callback_head *work) void flush_delayed_fput(void) { delayed_fput(NULL); + flush_delayed_work(&delayed_fput_work); } EXPORT_SYMBOL_GPL(flush_delayed_fput); -static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); - void fput(struct file *file) { if (file_ref_put(&file->f_ref)) { diff --git a/fs/fs_context.c b/fs/fs_context.c index 98589aae5208..582d33e81117 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -493,7 +493,7 @@ static void put_fc_log(struct fs_context *fc) if (log) { if (refcount_dec_and_test(&log->usage)) { fc->log.log = NULL; - for (i = 0; i <= 7; i++) + for (i = 0; i < ARRAY_SIZE(log->buffer) ; i++) if (log->need_free & (1 << i)) kfree(log->buffer[i]); kfree(log); diff --git a/fs/fs_parser.c b/fs/fs_parser.c index 16fa61ef56bf..e635a81e17d9 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -13,7 +13,7 @@ #include #include "internal.h" -static const struct constant_table bool_names[] = { +const struct constant_table bool_names[] = { { "0", false }, { "1", true }, { "false", false }, @@ -22,6 +22,7 @@ static const struct constant_table bool_names[] = { { "yes", true }, { }, }; +EXPORT_SYMBOL(bool_names); static const struct constant_table * __lookup_constant(const struct constant_table *tbl, const char *name) diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index 8674dbfbe59d..ca215a3cba3e 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -63,3 +63,15 @@ config FUSE_PASSTHROUGH to be performed directly on a backing file. If you want to allow passthrough operations, answer Y. + +config FUSE_IO_URING + bool "FUSE communication over io-uring" + default y + depends on FUSE_FS + depends on IO_URING + help + This allows sending FUSE requests over the io-uring interface and + also adds request core affinity. + + If you want to allow fuse server/client communication through io-uring, + answer Y diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile index 2c372180d631..3f0f312a31c1 100644 --- a/fs/fuse/Makefile +++ b/fs/fuse/Makefile @@ -15,5 +15,6 @@ fuse-y += iomode.o fuse-$(CONFIG_FUSE_DAX) += dax.o fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o fuse-$(CONFIG_SYSCTL) += sysctl.o +fuse-$(CONFIG_FUSE_IO_URING) += dev_uring.o virtiofs-y := virtio_fs.o diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index 9abbc2f2894f..0b6ee6dd1fd6 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -240,11 +240,12 @@ static int fuse_send_removemapping(struct inode *inode, args.opcode = FUSE_REMOVEMAPPING; args.nodeid = fi->nodeid; - args.in_numargs = 2; - args.in_args[0].size = sizeof(*inargp); - args.in_args[0].value = inargp; - args.in_args[1].size = inargp->count * sizeof(*remove_one); - args.in_args[1].value = remove_one; + args.in_numargs = 3; + fuse_set_zero_arg0(&args); + args.in_args[1].size = sizeof(*inargp); + args.in_args[1].value = inargp; + args.in_args[2].size = inargp->count * sizeof(*remove_one); + args.in_args[2].value = remove_one; return fuse_simple_request(fm, &args); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 27ccae63495d..5b5f789b37eb 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -6,7 +6,9 @@ See the file COPYING. */ +#include "dev_uring_i.h" #include "fuse_i.h" +#include "fuse_dev_i.h" #include #include @@ -28,23 +30,8 @@ MODULE_ALIAS_MISCDEV(FUSE_MINOR); MODULE_ALIAS("devname:fuse"); -/* Ordinary requests have even IDs, while interrupts IDs are odd */ -#define FUSE_INT_REQ_BIT (1ULL << 0) -#define FUSE_REQ_ID_STEP (1ULL << 1) - static struct kmem_cache *fuse_req_cachep; -static void end_requests(struct list_head *head); - -static struct fuse_dev *fuse_get_dev(struct file *file) -{ - /* - * Lockless access is OK, because file->private data is set - * once during mount and is valid until the file is released. - */ - return READ_ONCE(file->private_data); -} - static void fuse_request_init(struct fuse_mount *fm, struct fuse_req *req) { INIT_LIST_HEAD(&req->list); @@ -89,7 +76,8 @@ void fuse_set_initialized(struct fuse_conn *fc) static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background) { - return !fc->initialized || (for_background && fc->blocked); + return !fc->initialized || (for_background && fc->blocked) || + (fc->io_uring && !fuse_uring_ready(fc)); } static void fuse_drop_waiting(struct fuse_conn *fc) @@ -234,7 +222,7 @@ u64 fuse_get_unique(struct fuse_iqueue *fiq) } EXPORT_SYMBOL_GPL(fuse_get_unique); -static unsigned int fuse_req_hash(u64 unique) +unsigned int fuse_req_hash(u64 unique) { return hash_long(unique & ~FUSE_INT_REQ_BIT, FUSE_PQ_HASH_BITS); } @@ -250,7 +238,8 @@ __releases(fiq->lock) spin_unlock(&fiq->lock); } -static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_link *forget) +void fuse_dev_queue_forget(struct fuse_iqueue *fiq, + struct fuse_forget_link *forget) { spin_lock(&fiq->lock); if (fiq->connected) { @@ -263,7 +252,7 @@ static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_li } } -static void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) +void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) { spin_lock(&fiq->lock); if (list_empty(&req->intr_entry)) { @@ -580,7 +569,25 @@ ssize_t __fuse_simple_request(struct mnt_idmap *idmap, return ret; } -static bool fuse_request_queue_background(struct fuse_req *req) +#ifdef CONFIG_FUSE_IO_URING +static bool fuse_request_queue_background_uring(struct fuse_conn *fc, + struct fuse_req *req) +{ + struct fuse_iqueue *fiq = &fc->iq; + + req->in.h.unique = fuse_get_unique(fiq); + req->in.h.len = sizeof(struct fuse_in_header) + + fuse_len_args(req->args->in_numargs, + (struct fuse_arg *) req->args->in_args); + + return fuse_uring_queue_bq_req(req); +} +#endif + +/* + * @return true if queued + */ +static int fuse_request_queue_background(struct fuse_req *req) { struct fuse_mount *fm = req->fm; struct fuse_conn *fc = fm->fc; @@ -592,6 +599,12 @@ static bool fuse_request_queue_background(struct fuse_req *req) atomic_inc(&fc->num_waiting); } __set_bit(FR_ISREPLY, &req->flags); + +#ifdef CONFIG_FUSE_IO_URING + if (fuse_uring_ready(fc)) + return fuse_request_queue_background_uring(fc, req); +#endif + spin_lock(&fc->bg_lock); if (likely(fc->connected)) { fc->num_background++; @@ -692,22 +705,8 @@ static int unlock_request(struct fuse_req *req) return err; } -struct fuse_copy_state { - int write; - struct fuse_req *req; - struct iov_iter *iter; - struct pipe_buffer *pipebufs; - struct pipe_buffer *currbuf; - struct pipe_inode_info *pipe; - unsigned long nr_segs; - struct page *pg; - unsigned len; - unsigned offset; - unsigned move_pages:1; -}; - -static void fuse_copy_init(struct fuse_copy_state *cs, int write, - struct iov_iter *iter) +void fuse_copy_init(struct fuse_copy_state *cs, int write, + struct iov_iter *iter) { memset(cs, 0, sizeof(*cs)); cs->write = write; @@ -814,6 +813,9 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size) *size -= ncpy; cs->len -= ncpy; cs->offset += ncpy; + if (cs->is_uring) + cs->ring.copied_sz += ncpy; + return ncpy; } @@ -1068,9 +1070,9 @@ static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size) } /* Copy request arguments to/from userspace buffer */ -static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs, - unsigned argpages, struct fuse_arg *args, - int zeroing) +int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs, + unsigned argpages, struct fuse_arg *args, + int zeroing) { int err = 0; unsigned i; @@ -1760,7 +1762,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode, args = &ap->args; args->nodeid = outarg->nodeid; args->opcode = FUSE_NOTIFY_REPLY; - args->in_numargs = 2; + args->in_numargs = 3; args->in_pages = true; args->end = fuse_retrieve_end; @@ -1788,9 +1790,10 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode, } ra->inarg.offset = outarg->offset; ra->inarg.size = total_len; - args->in_args[0].size = sizeof(ra->inarg); - args->in_args[0].value = &ra->inarg; - args->in_args[1].size = total_len; + fuse_set_zero_arg0(args); + args->in_args[1].size = sizeof(ra->inarg); + args->in_args[1].value = &ra->inarg; + args->in_args[2].size = total_len; err = fuse_simple_notify_reply(fm, args, outarg->notify_unique); if (err) @@ -1885,7 +1888,7 @@ static void fuse_resend(struct fuse_conn *fc) spin_unlock(&fiq->lock); list_for_each_entry(req, &to_queue, list) clear_bit(FR_PENDING, &req->flags); - end_requests(&to_queue); + fuse_dev_end_requests(&to_queue); return; } /* iq and pq requests are both oldest to newest */ @@ -1934,7 +1937,7 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, } /* Look up request on processing list by unique ID */ -static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique) +struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique) { unsigned int hash = fuse_req_hash(unique); struct fuse_req *req; @@ -1946,10 +1949,17 @@ static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique) return NULL; } -static int copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args, - unsigned nbytes) +int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args, + unsigned nbytes) { - unsigned reqsize = sizeof(struct fuse_out_header); + + unsigned int reqsize = 0; + + /* + * Uring has all headers separated from args - args is payload only + */ + if (!cs->is_uring) + reqsize = sizeof(struct fuse_out_header); reqsize += fuse_len_args(args->out_numargs, args->out_args); @@ -2011,7 +2021,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, spin_lock(&fpq->lock); req = NULL; if (fpq->connected) - req = request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT); + req = fuse_request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT); err = -ENOENT; if (!req) { @@ -2049,7 +2059,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, if (oh.error) err = nbytes != sizeof(oh) ? -EINVAL : 0; else - err = copy_out_args(cs, req->args, nbytes); + err = fuse_copy_out_args(cs, req->args, nbytes); fuse_copy_finish(cs); spin_lock(&fpq->lock); @@ -2204,7 +2214,7 @@ static __poll_t fuse_dev_poll(struct file *file, poll_table *wait) } /* Abort all requests on the given list (pending or processing) */ -static void end_requests(struct list_head *head) +void fuse_dev_end_requests(struct list_head *head) { while (!list_empty(head)) { struct fuse_req *req; @@ -2307,7 +2317,13 @@ void fuse_abort_conn(struct fuse_conn *fc) wake_up_all(&fc->blocked_waitq); spin_unlock(&fc->lock); - end_requests(&to_end); + fuse_dev_end_requests(&to_end); + + /* + * fc->lock must not be taken to avoid conflicts with io-uring + * locks + */ + fuse_uring_abort(fc); } else { spin_unlock(&fc->lock); } @@ -2319,6 +2335,8 @@ void fuse_wait_aborted(struct fuse_conn *fc) /* matches implicit memory barrier in fuse_drop_waiting() */ smp_mb(); wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0); + + fuse_uring_wait_stopped_queues(fc); } int fuse_dev_release(struct inode *inode, struct file *file) @@ -2337,7 +2355,7 @@ int fuse_dev_release(struct inode *inode, struct file *file) list_splice_init(&fpq->processing[i], &to_end); spin_unlock(&fpq->lock); - end_requests(&to_end); + fuse_dev_end_requests(&to_end); /* Are we the last open device? */ if (atomic_dec_and_test(&fc->dev_count)) { @@ -2475,6 +2493,9 @@ const struct file_operations fuse_dev_operations = { .fasync = fuse_dev_fasync, .unlocked_ioctl = fuse_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, +#ifdef CONFIG_FUSE_IO_URING + .uring_cmd = fuse_uring_cmd, +#endif }; EXPORT_SYMBOL_GPL(fuse_dev_operations); diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c new file mode 100644 index 000000000000..ebd2931b4f2a --- /dev/null +++ b/fs/fuse/dev_uring.c @@ -0,0 +1,1319 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * FUSE: Filesystem in Userspace + * Copyright (c) 2023-2024 DataDirect Networks. + */ + +#include "fuse_i.h" +#include "dev_uring_i.h" +#include "fuse_dev_i.h" + +#include +#include + +static bool __read_mostly enable_uring; +module_param(enable_uring, bool, 0644); +MODULE_PARM_DESC(enable_uring, + "Enable userspace communication through io-uring"); + +#define FUSE_URING_IOV_SEGS 2 /* header and payload */ + + +bool fuse_uring_enabled(void) +{ + return enable_uring; +} + +struct fuse_uring_pdu { + struct fuse_ring_ent *ent; +}; + +static const struct fuse_iqueue_ops fuse_io_uring_ops; + +static void uring_cmd_set_ring_ent(struct io_uring_cmd *cmd, + struct fuse_ring_ent *ring_ent) +{ + struct fuse_uring_pdu *pdu = + io_uring_cmd_to_pdu(cmd, struct fuse_uring_pdu); + + pdu->ent = ring_ent; +} + +static struct fuse_ring_ent *uring_cmd_to_ring_ent(struct io_uring_cmd *cmd) +{ + struct fuse_uring_pdu *pdu = + io_uring_cmd_to_pdu(cmd, struct fuse_uring_pdu); + + return pdu->ent; +} + +static void fuse_uring_flush_bg(struct fuse_ring_queue *queue) +{ + struct fuse_ring *ring = queue->ring; + struct fuse_conn *fc = ring->fc; + + lockdep_assert_held(&queue->lock); + lockdep_assert_held(&fc->bg_lock); + + /* + * Allow one bg request per queue, ignoring global fc limits. + * This prevents a single queue from consuming all resources and + * eliminates the need for remote queue wake-ups when global + * limits are met but this queue has no more waiting requests. + */ + while ((fc->active_background < fc->max_background || + !queue->active_background) && + (!list_empty(&queue->fuse_req_bg_queue))) { + struct fuse_req *req; + + req = list_first_entry(&queue->fuse_req_bg_queue, + struct fuse_req, list); + fc->active_background++; + queue->active_background++; + + list_move_tail(&req->list, &queue->fuse_req_queue); + } +} + +static void fuse_uring_req_end(struct fuse_ring_ent *ent, struct fuse_req *req, + int error) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_ring *ring = queue->ring; + struct fuse_conn *fc = ring->fc; + + lockdep_assert_not_held(&queue->lock); + spin_lock(&queue->lock); + ent->fuse_req = NULL; + if (test_bit(FR_BACKGROUND, &req->flags)) { + queue->active_background--; + spin_lock(&fc->bg_lock); + fuse_uring_flush_bg(queue); + spin_unlock(&fc->bg_lock); + } + + spin_unlock(&queue->lock); + + if (error) + req->out.h.error = error; + + clear_bit(FR_SENT, &req->flags); + fuse_request_end(req); +} + +/* Abort all list queued request on the given ring queue */ +static void fuse_uring_abort_end_queue_requests(struct fuse_ring_queue *queue) +{ + struct fuse_req *req; + LIST_HEAD(req_list); + + spin_lock(&queue->lock); + list_for_each_entry(req, &queue->fuse_req_queue, list) + clear_bit(FR_PENDING, &req->flags); + list_splice_init(&queue->fuse_req_queue, &req_list); + spin_unlock(&queue->lock); + + /* must not hold queue lock to avoid order issues with fi->lock */ + fuse_dev_end_requests(&req_list); +} + +void fuse_uring_abort_end_requests(struct fuse_ring *ring) +{ + int qid; + struct fuse_ring_queue *queue; + struct fuse_conn *fc = ring->fc; + + for (qid = 0; qid < ring->nr_queues; qid++) { + queue = READ_ONCE(ring->queues[qid]); + if (!queue) + continue; + + queue->stopped = true; + + WARN_ON_ONCE(ring->fc->max_background != UINT_MAX); + spin_lock(&queue->lock); + spin_lock(&fc->bg_lock); + fuse_uring_flush_bg(queue); + spin_unlock(&fc->bg_lock); + spin_unlock(&queue->lock); + fuse_uring_abort_end_queue_requests(queue); + } +} + +void fuse_uring_destruct(struct fuse_conn *fc) +{ + struct fuse_ring *ring = fc->ring; + int qid; + + if (!ring) + return; + + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = ring->queues[qid]; + struct fuse_ring_ent *ent, *next; + + if (!queue) + continue; + + WARN_ON(!list_empty(&queue->ent_avail_queue)); + WARN_ON(!list_empty(&queue->ent_w_req_queue)); + WARN_ON(!list_empty(&queue->ent_commit_queue)); + WARN_ON(!list_empty(&queue->ent_in_userspace)); + + list_for_each_entry_safe(ent, next, &queue->ent_released, + list) { + list_del_init(&ent->list); + kfree(ent); + } + + kfree(queue->fpq.processing); + kfree(queue); + ring->queues[qid] = NULL; + } + + kfree(ring->queues); + kfree(ring); + fc->ring = NULL; +} + +/* + * Basic ring setup for this connection based on the provided configuration + */ +static struct fuse_ring *fuse_uring_create(struct fuse_conn *fc) +{ + struct fuse_ring *ring; + size_t nr_queues = num_possible_cpus(); + struct fuse_ring *res = NULL; + size_t max_payload_size; + + ring = kzalloc(sizeof(*fc->ring), GFP_KERNEL_ACCOUNT); + if (!ring) + return NULL; + + ring->queues = kcalloc(nr_queues, sizeof(struct fuse_ring_queue *), + GFP_KERNEL_ACCOUNT); + if (!ring->queues) + goto out_err; + + max_payload_size = max(FUSE_MIN_READ_BUFFER, fc->max_write); + max_payload_size = max(max_payload_size, fc->max_pages * PAGE_SIZE); + + spin_lock(&fc->lock); + if (fc->ring) { + /* race, another thread created the ring in the meantime */ + spin_unlock(&fc->lock); + res = fc->ring; + goto out_err; + } + + init_waitqueue_head(&ring->stop_waitq); + + fc->ring = ring; + ring->nr_queues = nr_queues; + ring->fc = fc; + ring->max_payload_sz = max_payload_size; + atomic_set(&ring->queue_refs, 0); + + spin_unlock(&fc->lock); + return ring; + +out_err: + kfree(ring->queues); + kfree(ring); + return res; +} + +static struct fuse_ring_queue *fuse_uring_create_queue(struct fuse_ring *ring, + int qid) +{ + struct fuse_conn *fc = ring->fc; + struct fuse_ring_queue *queue; + struct list_head *pq; + + queue = kzalloc(sizeof(*queue), GFP_KERNEL_ACCOUNT); + if (!queue) + return NULL; + pq = kcalloc(FUSE_PQ_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); + if (!pq) { + kfree(queue); + return NULL; + } + + queue->qid = qid; + queue->ring = ring; + spin_lock_init(&queue->lock); + + INIT_LIST_HEAD(&queue->ent_avail_queue); + INIT_LIST_HEAD(&queue->ent_commit_queue); + INIT_LIST_HEAD(&queue->ent_w_req_queue); + INIT_LIST_HEAD(&queue->ent_in_userspace); + INIT_LIST_HEAD(&queue->fuse_req_queue); + INIT_LIST_HEAD(&queue->fuse_req_bg_queue); + INIT_LIST_HEAD(&queue->ent_released); + + queue->fpq.processing = pq; + fuse_pqueue_init(&queue->fpq); + + spin_lock(&fc->lock); + if (ring->queues[qid]) { + spin_unlock(&fc->lock); + kfree(queue->fpq.processing); + kfree(queue); + return ring->queues[qid]; + } + + /* + * write_once and lock as the caller mostly doesn't take the lock at all + */ + WRITE_ONCE(ring->queues[qid], queue); + spin_unlock(&fc->lock); + + return queue; +} + +static void fuse_uring_stop_fuse_req_end(struct fuse_req *req) +{ + clear_bit(FR_SENT, &req->flags); + req->out.h.error = -ECONNABORTED; + fuse_request_end(req); +} + +/* + * Release a request/entry on connection tear down + */ +static void fuse_uring_entry_teardown(struct fuse_ring_ent *ent) +{ + struct fuse_req *req; + struct io_uring_cmd *cmd; + + struct fuse_ring_queue *queue = ent->queue; + + spin_lock(&queue->lock); + cmd = ent->cmd; + ent->cmd = NULL; + req = ent->fuse_req; + ent->fuse_req = NULL; + if (req) { + /* remove entry from queue->fpq->processing */ + list_del_init(&req->list); + } + + /* + * The entry must not be freed immediately, due to access of direct + * pointer access of entries through IO_URING_F_CANCEL - there is a risk + * of race between daemon termination (which triggers IO_URING_F_CANCEL + * and accesses entries without checking the list state first + */ + list_move(&ent->list, &queue->ent_released); + ent->state = FRRS_RELEASED; + spin_unlock(&queue->lock); + + if (cmd) + io_uring_cmd_done(cmd, -ENOTCONN, 0, IO_URING_F_UNLOCKED); + + if (req) + fuse_uring_stop_fuse_req_end(req); +} + +static void fuse_uring_stop_list_entries(struct list_head *head, + struct fuse_ring_queue *queue, + enum fuse_ring_req_state exp_state) +{ + struct fuse_ring *ring = queue->ring; + struct fuse_ring_ent *ent, *next; + ssize_t queue_refs = SSIZE_MAX; + LIST_HEAD(to_teardown); + + spin_lock(&queue->lock); + list_for_each_entry_safe(ent, next, head, list) { + if (ent->state != exp_state) { + pr_warn("entry teardown qid=%d state=%d expected=%d", + queue->qid, ent->state, exp_state); + continue; + } + + ent->state = FRRS_TEARDOWN; + list_move(&ent->list, &to_teardown); + } + spin_unlock(&queue->lock); + + /* no queue lock to avoid lock order issues */ + list_for_each_entry_safe(ent, next, &to_teardown, list) { + fuse_uring_entry_teardown(ent); + queue_refs = atomic_dec_return(&ring->queue_refs); + WARN_ON_ONCE(queue_refs < 0); + } +} + +static void fuse_uring_teardown_entries(struct fuse_ring_queue *queue) +{ + fuse_uring_stop_list_entries(&queue->ent_in_userspace, queue, + FRRS_USERSPACE); + fuse_uring_stop_list_entries(&queue->ent_avail_queue, queue, + FRRS_AVAILABLE); +} + +/* + * Log state debug info + */ +static void fuse_uring_log_ent_state(struct fuse_ring *ring) +{ + int qid; + struct fuse_ring_ent *ent; + + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = ring->queues[qid]; + + if (!queue) + continue; + + spin_lock(&queue->lock); + /* + * Log entries from the intermediate queue, the other queues + * should be empty + */ + list_for_each_entry(ent, &queue->ent_w_req_queue, list) { + pr_info(" ent-req-queue ring=%p qid=%d ent=%p state=%d\n", + ring, qid, ent, ent->state); + } + list_for_each_entry(ent, &queue->ent_commit_queue, list) { + pr_info(" ent-commit-queue ring=%p qid=%d ent=%p state=%d\n", + ring, qid, ent, ent->state); + } + spin_unlock(&queue->lock); + } + ring->stop_debug_log = 1; +} + +static void fuse_uring_async_stop_queues(struct work_struct *work) +{ + int qid; + struct fuse_ring *ring = + container_of(work, struct fuse_ring, async_teardown_work.work); + + /* XXX code dup */ + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = READ_ONCE(ring->queues[qid]); + + if (!queue) + continue; + + fuse_uring_teardown_entries(queue); + } + + /* + * Some ring entries might be in the middle of IO operations, + * i.e. in process to get handled by file_operations::uring_cmd + * or on the way to userspace - we could handle that with conditions in + * run time code, but easier/cleaner to have an async tear down handler + * If there are still queue references left + */ + if (atomic_read(&ring->queue_refs) > 0) { + if (time_after(jiffies, + ring->teardown_time + FUSE_URING_TEARDOWN_TIMEOUT)) + fuse_uring_log_ent_state(ring); + + schedule_delayed_work(&ring->async_teardown_work, + FUSE_URING_TEARDOWN_INTERVAL); + } else { + wake_up_all(&ring->stop_waitq); + } +} + +/* + * Stop the ring queues + */ +void fuse_uring_stop_queues(struct fuse_ring *ring) +{ + int qid; + + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = READ_ONCE(ring->queues[qid]); + + if (!queue) + continue; + + fuse_uring_teardown_entries(queue); + } + + if (atomic_read(&ring->queue_refs) > 0) { + ring->teardown_time = jiffies; + INIT_DELAYED_WORK(&ring->async_teardown_work, + fuse_uring_async_stop_queues); + schedule_delayed_work(&ring->async_teardown_work, + FUSE_URING_TEARDOWN_INTERVAL); + } else { + wake_up_all(&ring->stop_waitq); + } +} + +/* + * Handle IO_URING_F_CANCEL, typically should come on daemon termination. + * + * Releasing the last entry should trigger fuse_dev_release() if + * the daemon was terminated + */ +static void fuse_uring_cancel(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd); + struct fuse_ring_queue *queue; + bool need_cmd_done = false; + + /* + * direct access on ent - it must not be destructed as long as + * IO_URING_F_CANCEL might come up + */ + queue = ent->queue; + spin_lock(&queue->lock); + if (ent->state == FRRS_AVAILABLE) { + ent->state = FRRS_USERSPACE; + list_move(&ent->list, &queue->ent_in_userspace); + need_cmd_done = true; + ent->cmd = NULL; + } + spin_unlock(&queue->lock); + + if (need_cmd_done) { + /* no queue lock to avoid lock order issues */ + io_uring_cmd_done(cmd, -ENOTCONN, 0, issue_flags); + } +} + +static void fuse_uring_prepare_cancel(struct io_uring_cmd *cmd, int issue_flags, + struct fuse_ring_ent *ring_ent) +{ + uring_cmd_set_ring_ent(cmd, ring_ent); + io_uring_cmd_mark_cancelable(cmd, issue_flags); +} + +/* + * Checks for errors and stores it into the request + */ +static int fuse_uring_out_header_has_err(struct fuse_out_header *oh, + struct fuse_req *req, + struct fuse_conn *fc) +{ + int err; + + err = -EINVAL; + if (oh->unique == 0) { + /* Not supported through io-uring yet */ + pr_warn_once("notify through fuse-io-uring not supported\n"); + goto err; + } + + if (oh->error <= -ERESTARTSYS || oh->error > 0) + goto err; + + if (oh->error) { + err = oh->error; + goto err; + } + + err = -ENOENT; + if ((oh->unique & ~FUSE_INT_REQ_BIT) != req->in.h.unique) { + pr_warn_ratelimited("unique mismatch, expected: %llu got %llu\n", + req->in.h.unique, + oh->unique & ~FUSE_INT_REQ_BIT); + goto err; + } + + /* + * Is it an interrupt reply ID? + * XXX: Not supported through fuse-io-uring yet, it should not even + * find the request - should not happen. + */ + WARN_ON_ONCE(oh->unique & FUSE_INT_REQ_BIT); + + err = 0; +err: + return err; +} + +static int fuse_uring_copy_from_ring(struct fuse_ring *ring, + struct fuse_req *req, + struct fuse_ring_ent *ent) +{ + struct fuse_copy_state cs; + struct fuse_args *args = req->args; + struct iov_iter iter; + int err; + struct fuse_uring_ent_in_out ring_in_out; + + err = copy_from_user(&ring_in_out, &ent->headers->ring_ent_in_out, + sizeof(ring_in_out)); + if (err) + return -EFAULT; + + err = import_ubuf(ITER_SOURCE, ent->payload, ring->max_payload_sz, + &iter); + if (err) + return err; + + fuse_copy_init(&cs, 0, &iter); + cs.is_uring = 1; + cs.req = req; + + return fuse_copy_out_args(&cs, args, ring_in_out.payload_sz); +} + + /* + * Copy data from the req to the ring buffer + */ +static int fuse_uring_args_to_ring(struct fuse_ring *ring, struct fuse_req *req, + struct fuse_ring_ent *ent) +{ + struct fuse_copy_state cs; + struct fuse_args *args = req->args; + struct fuse_in_arg *in_args = args->in_args; + int num_args = args->in_numargs; + int err; + struct iov_iter iter; + struct fuse_uring_ent_in_out ent_in_out = { + .flags = 0, + .commit_id = req->in.h.unique, + }; + + err = import_ubuf(ITER_DEST, ent->payload, ring->max_payload_sz, &iter); + if (err) { + pr_info_ratelimited("fuse: Import of user buffer failed\n"); + return err; + } + + fuse_copy_init(&cs, 1, &iter); + cs.is_uring = 1; + cs.req = req; + + if (num_args > 0) { + /* + * Expectation is that the first argument is the per op header. + * Some op code have that as zero size. + */ + if (args->in_args[0].size > 0) { + err = copy_to_user(&ent->headers->op_in, in_args->value, + in_args->size); + if (err) { + pr_info_ratelimited( + "Copying the header failed.\n"); + return -EFAULT; + } + } + in_args++; + num_args--; + } + + /* copy the payload */ + err = fuse_copy_args(&cs, num_args, args->in_pages, + (struct fuse_arg *)in_args, 0); + if (err) { + pr_info_ratelimited("%s fuse_copy_args failed\n", __func__); + return err; + } + + ent_in_out.payload_sz = cs.ring.copied_sz; + err = copy_to_user(&ent->headers->ring_ent_in_out, &ent_in_out, + sizeof(ent_in_out)); + return err ? -EFAULT : 0; +} + +static int fuse_uring_copy_to_ring(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_ring *ring = queue->ring; + int err; + + err = -EIO; + if (WARN_ON(ent->state != FRRS_FUSE_REQ)) { + pr_err("qid=%d ring-req=%p invalid state %d on send\n", + queue->qid, ent, ent->state); + return err; + } + + err = -EINVAL; + if (WARN_ON(req->in.h.unique == 0)) + return err; + + /* copy the request */ + err = fuse_uring_args_to_ring(ring, req, ent); + if (unlikely(err)) { + pr_info_ratelimited("Copy to ring failed: %d\n", err); + return err; + } + + /* copy fuse_in_header */ + err = copy_to_user(&ent->headers->in_out, &req->in.h, + sizeof(req->in.h)); + if (err) { + err = -EFAULT; + return err; + } + + return 0; +} + +static int fuse_uring_prepare_send(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + int err; + + err = fuse_uring_copy_to_ring(ent, req); + if (!err) + set_bit(FR_SENT, &req->flags); + else + fuse_uring_req_end(ent, req, err); + + return err; +} + +/* + * Write data to the ring buffer and send the request to userspace, + * userspace will read it + * This is comparable with classical read(/dev/fuse) + */ +static int fuse_uring_send_next_to_ring(struct fuse_ring_ent *ent, + struct fuse_req *req, + unsigned int issue_flags) +{ + struct fuse_ring_queue *queue = ent->queue; + int err; + struct io_uring_cmd *cmd; + + err = fuse_uring_prepare_send(ent, req); + if (err) + return err; + + spin_lock(&queue->lock); + cmd = ent->cmd; + ent->cmd = NULL; + ent->state = FRRS_USERSPACE; + list_move(&ent->list, &queue->ent_in_userspace); + spin_unlock(&queue->lock); + + io_uring_cmd_done(cmd, 0, 0, issue_flags); + return 0; +} + +/* + * Make a ring entry available for fuse_req assignment + */ +static void fuse_uring_ent_avail(struct fuse_ring_ent *ent, + struct fuse_ring_queue *queue) +{ + WARN_ON_ONCE(!ent->cmd); + list_move(&ent->list, &queue->ent_avail_queue); + ent->state = FRRS_AVAILABLE; +} + +/* Used to find the request on SQE commit */ +static void fuse_uring_add_to_pq(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_pqueue *fpq = &queue->fpq; + unsigned int hash; + + req->ring_entry = ent; + hash = fuse_req_hash(req->in.h.unique); + list_move_tail(&req->list, &fpq->processing[hash]); +} + +/* + * Assign a fuse queue entry to the given entry + */ +static void fuse_uring_add_req_to_ring_ent(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_conn *fc = req->fm->fc; + struct fuse_iqueue *fiq = &fc->iq; + + lockdep_assert_held(&queue->lock); + + if (WARN_ON_ONCE(ent->state != FRRS_AVAILABLE && + ent->state != FRRS_COMMIT)) { + pr_warn("%s qid=%d state=%d\n", __func__, ent->queue->qid, + ent->state); + } + + spin_lock(&fiq->lock); + clear_bit(FR_PENDING, &req->flags); + spin_unlock(&fiq->lock); + ent->fuse_req = req; + ent->state = FRRS_FUSE_REQ; + list_move(&ent->list, &queue->ent_w_req_queue); + fuse_uring_add_to_pq(ent, req); +} + +/* Fetch the next fuse request if available */ +static struct fuse_req *fuse_uring_ent_assign_req(struct fuse_ring_ent *ent) + __must_hold(&queue->lock) +{ + struct fuse_req *req; + struct fuse_ring_queue *queue = ent->queue; + struct list_head *req_queue = &queue->fuse_req_queue; + + lockdep_assert_held(&queue->lock); + + /* get and assign the next entry while it is still holding the lock */ + req = list_first_entry_or_null(req_queue, struct fuse_req, list); + if (req) + fuse_uring_add_req_to_ring_ent(ent, req); + + return req; +} + +/* + * Read data from the ring buffer, which user space has written to + * This is comparible with handling of classical write(/dev/fuse). + * Also make the ring request available again for new fuse requests. + */ +static void fuse_uring_commit(struct fuse_ring_ent *ent, struct fuse_req *req, + unsigned int issue_flags) +{ + struct fuse_ring *ring = ent->queue->ring; + struct fuse_conn *fc = ring->fc; + ssize_t err = 0; + + err = copy_from_user(&req->out.h, &ent->headers->in_out, + sizeof(req->out.h)); + if (err) { + req->out.h.error = -EFAULT; + goto out; + } + + err = fuse_uring_out_header_has_err(&req->out.h, req, fc); + if (err) { + /* req->out.h.error already set */ + goto out; + } + + err = fuse_uring_copy_from_ring(ring, req, ent); +out: + fuse_uring_req_end(ent, req, err); +} + +/* + * Get the next fuse req and send it + */ +static void fuse_uring_next_fuse_req(struct fuse_ring_ent *ent, + struct fuse_ring_queue *queue, + unsigned int issue_flags) +{ + int err; + struct fuse_req *req; + +retry: + spin_lock(&queue->lock); + fuse_uring_ent_avail(ent, queue); + req = fuse_uring_ent_assign_req(ent); + spin_unlock(&queue->lock); + + if (req) { + err = fuse_uring_send_next_to_ring(ent, req, issue_flags); + if (err) + goto retry; + } +} + +static int fuse_ring_ent_set_commit(struct fuse_ring_ent *ent) +{ + struct fuse_ring_queue *queue = ent->queue; + + lockdep_assert_held(&queue->lock); + + if (WARN_ON_ONCE(ent->state != FRRS_USERSPACE)) + return -EIO; + + ent->state = FRRS_COMMIT; + list_move(&ent->list, &queue->ent_commit_queue); + + return 0; +} + +/* FUSE_URING_CMD_COMMIT_AND_FETCH handler */ +static int fuse_uring_commit_fetch(struct io_uring_cmd *cmd, int issue_flags, + struct fuse_conn *fc) +{ + const struct fuse_uring_cmd_req *cmd_req = io_uring_sqe_cmd(cmd->sqe); + struct fuse_ring_ent *ent; + int err; + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + uint64_t commit_id = READ_ONCE(cmd_req->commit_id); + unsigned int qid = READ_ONCE(cmd_req->qid); + struct fuse_pqueue *fpq; + struct fuse_req *req; + + err = -ENOTCONN; + if (!ring) + return err; + + if (qid >= ring->nr_queues) + return -EINVAL; + + queue = ring->queues[qid]; + if (!queue) + return err; + fpq = &queue->fpq; + + if (!READ_ONCE(fc->connected) || READ_ONCE(queue->stopped)) + return err; + + spin_lock(&queue->lock); + /* Find a request based on the unique ID of the fuse request + * This should get revised, as it needs a hash calculation and list + * search. And full struct fuse_pqueue is needed (memory overhead). + * As well as the link from req to ring_ent. + */ + req = fuse_request_find(fpq, commit_id); + err = -ENOENT; + if (!req) { + pr_info("qid=%d commit_id %llu not found\n", queue->qid, + commit_id); + spin_unlock(&queue->lock); + return err; + } + list_del_init(&req->list); + ent = req->ring_entry; + req->ring_entry = NULL; + + err = fuse_ring_ent_set_commit(ent); + if (err != 0) { + pr_info_ratelimited("qid=%d commit_id %llu state %d", + queue->qid, commit_id, ent->state); + spin_unlock(&queue->lock); + req->out.h.error = err; + clear_bit(FR_SENT, &req->flags); + fuse_request_end(req); + return err; + } + + ent->cmd = cmd; + spin_unlock(&queue->lock); + + /* without the queue lock, as other locks are taken */ + fuse_uring_prepare_cancel(cmd, issue_flags, ent); + fuse_uring_commit(ent, req, issue_flags); + + /* + * Fetching the next request is absolutely required as queued + * fuse requests would otherwise not get processed - committing + * and fetching is done in one step vs legacy fuse, which has separated + * read (fetch request) and write (commit result). + */ + fuse_uring_next_fuse_req(ent, queue, issue_flags); + return 0; +} + +static bool is_ring_ready(struct fuse_ring *ring, int current_qid) +{ + int qid; + struct fuse_ring_queue *queue; + bool ready = true; + + for (qid = 0; qid < ring->nr_queues && ready; qid++) { + if (current_qid == qid) + continue; + + queue = ring->queues[qid]; + if (!queue) { + ready = false; + break; + } + + spin_lock(&queue->lock); + if (list_empty(&queue->ent_avail_queue)) + ready = false; + spin_unlock(&queue->lock); + } + + return ready; +} + +/* + * fuse_uring_req_fetch command handling + */ +static void fuse_uring_do_register(struct fuse_ring_ent *ent, + struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_ring *ring = queue->ring; + struct fuse_conn *fc = ring->fc; + struct fuse_iqueue *fiq = &fc->iq; + + fuse_uring_prepare_cancel(cmd, issue_flags, ent); + + spin_lock(&queue->lock); + ent->cmd = cmd; + fuse_uring_ent_avail(ent, queue); + spin_unlock(&queue->lock); + + if (!ring->ready) { + bool ready = is_ring_ready(ring, queue->qid); + + if (ready) { + WRITE_ONCE(fiq->ops, &fuse_io_uring_ops); + WRITE_ONCE(ring->ready, true); + wake_up_all(&fc->blocked_waitq); + } + } +} + +/* + * sqe->addr is a ptr to an iovec array, iov[0] has the headers, iov[1] + * the payload + */ +static int fuse_uring_get_iovec_from_sqe(const struct io_uring_sqe *sqe, + struct iovec iov[FUSE_URING_IOV_SEGS]) +{ + struct iovec __user *uiov = u64_to_user_ptr(READ_ONCE(sqe->addr)); + struct iov_iter iter; + ssize_t ret; + + if (sqe->len != FUSE_URING_IOV_SEGS) + return -EINVAL; + + /* + * Direction for buffer access will actually be READ and WRITE, + * using write for the import should include READ access as well. + */ + ret = import_iovec(WRITE, uiov, FUSE_URING_IOV_SEGS, + FUSE_URING_IOV_SEGS, &iov, &iter); + if (ret < 0) + return ret; + + return 0; +} + +static struct fuse_ring_ent * +fuse_uring_create_ring_ent(struct io_uring_cmd *cmd, + struct fuse_ring_queue *queue) +{ + struct fuse_ring *ring = queue->ring; + struct fuse_ring_ent *ent; + size_t payload_size; + struct iovec iov[FUSE_URING_IOV_SEGS]; + int err; + + err = fuse_uring_get_iovec_from_sqe(cmd->sqe, iov); + if (err) { + pr_info_ratelimited("Failed to get iovec from sqe, err=%d\n", + err); + return ERR_PTR(err); + } + + err = -EINVAL; + if (iov[0].iov_len < sizeof(struct fuse_uring_req_header)) { + pr_info_ratelimited("Invalid header len %zu\n", iov[0].iov_len); + return ERR_PTR(err); + } + + payload_size = iov[1].iov_len; + if (payload_size < ring->max_payload_sz) { + pr_info_ratelimited("Invalid req payload len %zu\n", + payload_size); + return ERR_PTR(err); + } + + err = -ENOMEM; + ent = kzalloc(sizeof(*ent), GFP_KERNEL_ACCOUNT); + if (!ent) + return ERR_PTR(err); + + INIT_LIST_HEAD(&ent->list); + + ent->queue = queue; + ent->headers = iov[0].iov_base; + ent->payload = iov[1].iov_base; + + atomic_inc(&ring->queue_refs); + return ent; +} + +/* + * Register header and payload buffer with the kernel and puts the + * entry as "ready to get fuse requests" on the queue + */ +static int fuse_uring_register(struct io_uring_cmd *cmd, + unsigned int issue_flags, struct fuse_conn *fc) +{ + const struct fuse_uring_cmd_req *cmd_req = io_uring_sqe_cmd(cmd->sqe); + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + struct fuse_ring_ent *ent; + int err; + unsigned int qid = READ_ONCE(cmd_req->qid); + + err = -ENOMEM; + if (!ring) { + ring = fuse_uring_create(fc); + if (!ring) + return err; + } + + if (qid >= ring->nr_queues) { + pr_info_ratelimited("fuse: Invalid ring qid %u\n", qid); + return -EINVAL; + } + + queue = ring->queues[qid]; + if (!queue) { + queue = fuse_uring_create_queue(ring, qid); + if (!queue) + return err; + } + + /* + * The created queue above does not need to be destructed in + * case of entry errors below, will be done at ring destruction time. + */ + + ent = fuse_uring_create_ring_ent(cmd, queue); + if (IS_ERR(ent)) + return PTR_ERR(ent); + + fuse_uring_do_register(ent, cmd, issue_flags); + + return 0; +} + +/* + * Entry function from io_uring to handle the given passthrough command + * (op code IORING_OP_URING_CMD) + */ +int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + struct fuse_dev *fud; + struct fuse_conn *fc; + u32 cmd_op = cmd->cmd_op; + int err; + + if ((unlikely(issue_flags & IO_URING_F_CANCEL))) { + fuse_uring_cancel(cmd, issue_flags); + return 0; + } + + /* This extra SQE size holds struct fuse_uring_cmd_req */ + if (!(issue_flags & IO_URING_F_SQE128)) + return -EINVAL; + + fud = fuse_get_dev(cmd->file); + if (!fud) { + pr_info_ratelimited("No fuse device found\n"); + return -ENOTCONN; + } + fc = fud->fc; + + /* Once a connection has io-uring enabled on it, it can't be disabled */ + if (!enable_uring && !fc->io_uring) { + pr_info_ratelimited("fuse-io-uring is disabled\n"); + return -EOPNOTSUPP; + } + + if (fc->aborted) + return -ECONNABORTED; + if (!fc->connected) + return -ENOTCONN; + + /* + * fuse_uring_register() needs the ring to be initialized, + * we need to know the max payload size + */ + if (!fc->initialized) + return -EAGAIN; + + switch (cmd_op) { + case FUSE_IO_URING_CMD_REGISTER: + err = fuse_uring_register(cmd, issue_flags, fc); + if (err) { + pr_info_once("FUSE_IO_URING_CMD_REGISTER failed err=%d\n", + err); + fc->io_uring = 0; + wake_up_all(&fc->blocked_waitq); + return err; + } + break; + case FUSE_IO_URING_CMD_COMMIT_AND_FETCH: + err = fuse_uring_commit_fetch(cmd, issue_flags, fc); + if (err) { + pr_info_once("FUSE_IO_URING_COMMIT_AND_FETCH failed err=%d\n", + err); + return err; + } + break; + default: + return -EINVAL; + } + + return -EIOCBQUEUED; +} + +static void fuse_uring_send(struct fuse_ring_ent *ent, struct io_uring_cmd *cmd, + ssize_t ret, unsigned int issue_flags) +{ + struct fuse_ring_queue *queue = ent->queue; + + spin_lock(&queue->lock); + ent->state = FRRS_USERSPACE; + list_move(&ent->list, &queue->ent_in_userspace); + ent->cmd = NULL; + spin_unlock(&queue->lock); + + io_uring_cmd_done(cmd, ret, 0, issue_flags); +} + +/* + * This prepares and sends the ring request in fuse-uring task context. + * User buffers are not mapped yet - the application does not have permission + * to write to it - this has to be executed in ring task context. + */ +static void fuse_uring_send_in_task(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd); + struct fuse_ring_queue *queue = ent->queue; + int err; + + if (!(issue_flags & IO_URING_F_TASK_DEAD)) { + err = fuse_uring_prepare_send(ent, ent->fuse_req); + if (err) { + fuse_uring_next_fuse_req(ent, queue, issue_flags); + return; + } + } else { + err = -ECANCELED; + } + + fuse_uring_send(ent, cmd, err, issue_flags); +} + +static struct fuse_ring_queue *fuse_uring_task_to_queue(struct fuse_ring *ring) +{ + unsigned int qid; + struct fuse_ring_queue *queue; + + qid = task_cpu(current); + + if (WARN_ONCE(qid >= ring->nr_queues, + "Core number (%u) exceeds nr queues (%zu)\n", qid, + ring->nr_queues)) + qid = 0; + + queue = ring->queues[qid]; + WARN_ONCE(!queue, "Missing queue for qid %d\n", qid); + + return queue; +} + +static void fuse_uring_dispatch_ent(struct fuse_ring_ent *ent) +{ + struct io_uring_cmd *cmd = ent->cmd; + + uring_cmd_set_ring_ent(cmd, ent); + io_uring_cmd_complete_in_task(cmd, fuse_uring_send_in_task); +} + +/* queue a fuse request and send it if a ring entry is available */ +void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req) +{ + struct fuse_conn *fc = req->fm->fc; + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + struct fuse_ring_ent *ent = NULL; + int err; + + err = -EINVAL; + queue = fuse_uring_task_to_queue(ring); + if (!queue) + goto err; + + if (req->in.h.opcode != FUSE_NOTIFY_REPLY) + req->in.h.unique = fuse_get_unique(fiq); + + spin_lock(&queue->lock); + err = -ENOTCONN; + if (unlikely(queue->stopped)) + goto err_unlock; + + ent = list_first_entry_or_null(&queue->ent_avail_queue, + struct fuse_ring_ent, list); + if (ent) + fuse_uring_add_req_to_ring_ent(ent, req); + else + list_add_tail(&req->list, &queue->fuse_req_queue); + spin_unlock(&queue->lock); + + if (ent) + fuse_uring_dispatch_ent(ent); + + return; + +err_unlock: + spin_unlock(&queue->lock); +err: + req->out.h.error = err; + clear_bit(FR_PENDING, &req->flags); + fuse_request_end(req); +} + +bool fuse_uring_queue_bq_req(struct fuse_req *req) +{ + struct fuse_conn *fc = req->fm->fc; + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + struct fuse_ring_ent *ent = NULL; + + queue = fuse_uring_task_to_queue(ring); + if (!queue) + return false; + + spin_lock(&queue->lock); + if (unlikely(queue->stopped)) { + spin_unlock(&queue->lock); + return false; + } + + list_add_tail(&req->list, &queue->fuse_req_bg_queue); + + ent = list_first_entry_or_null(&queue->ent_avail_queue, + struct fuse_ring_ent, list); + spin_lock(&fc->bg_lock); + fc->num_background++; + if (fc->num_background == fc->max_background) + fc->blocked = 1; + fuse_uring_flush_bg(queue); + spin_unlock(&fc->bg_lock); + + /* + * Due to bg_queue flush limits there might be other bg requests + * in the queue that need to be handled first. Or no further req + * might be available. + */ + req = list_first_entry_or_null(&queue->fuse_req_queue, struct fuse_req, + list); + if (ent && req) { + fuse_uring_add_req_to_ring_ent(ent, req); + spin_unlock(&queue->lock); + + fuse_uring_dispatch_ent(ent); + } else { + spin_unlock(&queue->lock); + } + + return true; +} + +static const struct fuse_iqueue_ops fuse_io_uring_ops = { + /* should be send over io-uring as enhancement */ + .send_forget = fuse_dev_queue_forget, + + /* + * could be send over io-uring, but interrupts should be rare, + * no need to make the code complex + */ + .send_interrupt = fuse_dev_queue_interrupt, + .send_req = fuse_uring_queue_fuse_req, +}; diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h new file mode 100644 index 000000000000..2102b3d0c1ae --- /dev/null +++ b/fs/fuse/dev_uring_i.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * FUSE: Filesystem in Userspace + * Copyright (c) 2023-2024 DataDirect Networks. + */ + +#ifndef _FS_FUSE_DEV_URING_I_H +#define _FS_FUSE_DEV_URING_I_H + +#include "fuse_i.h" + +#ifdef CONFIG_FUSE_IO_URING + +#define FUSE_URING_TEARDOWN_TIMEOUT (5 * HZ) +#define FUSE_URING_TEARDOWN_INTERVAL (HZ/20) + +enum fuse_ring_req_state { + FRRS_INVALID = 0, + + /* The ring entry received from userspace and it is being processed */ + FRRS_COMMIT, + + /* The ring entry is waiting for new fuse requests */ + FRRS_AVAILABLE, + + /* The ring entry got assigned a fuse req */ + FRRS_FUSE_REQ, + + /* The ring entry is in or on the way to user space */ + FRRS_USERSPACE, + + /* The ring entry is in teardown */ + FRRS_TEARDOWN, + + /* The ring entry is released, but not freed yet */ + FRRS_RELEASED, +}; + +/** A fuse ring entry, part of the ring queue */ +struct fuse_ring_ent { + /* userspace buffer */ + struct fuse_uring_req_header __user *headers; + void __user *payload; + + /* the ring queue that owns the request */ + struct fuse_ring_queue *queue; + + /* fields below are protected by queue->lock */ + + struct io_uring_cmd *cmd; + + struct list_head list; + + enum fuse_ring_req_state state; + + struct fuse_req *fuse_req; +}; + +struct fuse_ring_queue { + /* + * back pointer to the main fuse uring structure that holds this + * queue + */ + struct fuse_ring *ring; + + /* queue id, corresponds to the cpu core */ + unsigned int qid; + + /* + * queue lock, taken when any value in the queue changes _and_ also + * a ring entry state changes. + */ + spinlock_t lock; + + /* available ring entries (struct fuse_ring_ent) */ + struct list_head ent_avail_queue; + + /* + * entries in the process of being committed or in the process + * to be sent to userspace + */ + struct list_head ent_w_req_queue; + struct list_head ent_commit_queue; + + /* entries in userspace */ + struct list_head ent_in_userspace; + + /* entries that are released */ + struct list_head ent_released; + + /* fuse requests waiting for an entry slot */ + struct list_head fuse_req_queue; + + /* background fuse requests */ + struct list_head fuse_req_bg_queue; + + struct fuse_pqueue fpq; + + unsigned int active_background; + + bool stopped; +}; + +/** + * Describes if uring is for communication and holds alls the data needed + * for uring communication + */ +struct fuse_ring { + /* back pointer */ + struct fuse_conn *fc; + + /* number of ring queues */ + size_t nr_queues; + + /* maximum payload/arg size */ + size_t max_payload_sz; + + struct fuse_ring_queue **queues; + + /* + * Log ring entry states on stop when entries cannot be released + */ + unsigned int stop_debug_log : 1; + + wait_queue_head_t stop_waitq; + + /* async tear down */ + struct delayed_work async_teardown_work; + + /* log */ + unsigned long teardown_time; + + atomic_t queue_refs; + + bool ready; +}; + +bool fuse_uring_enabled(void); +void fuse_uring_destruct(struct fuse_conn *fc); +void fuse_uring_stop_queues(struct fuse_ring *ring); +void fuse_uring_abort_end_requests(struct fuse_ring *ring); +int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags); +void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req); +bool fuse_uring_queue_bq_req(struct fuse_req *req); + +static inline void fuse_uring_abort(struct fuse_conn *fc) +{ + struct fuse_ring *ring = fc->ring; + + if (ring == NULL) + return; + + if (atomic_read(&ring->queue_refs) > 0) { + fuse_uring_abort_end_requests(ring); + fuse_uring_stop_queues(ring); + } +} + +static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc) +{ + struct fuse_ring *ring = fc->ring; + + if (ring) + wait_event(ring->stop_waitq, + atomic_read(&ring->queue_refs) == 0); +} + +static inline bool fuse_uring_ready(struct fuse_conn *fc) +{ + return fc->ring && fc->ring->ready; +} + +#else /* CONFIG_FUSE_IO_URING */ + +struct fuse_ring; + +static inline void fuse_uring_create(struct fuse_conn *fc) +{ +} + +static inline void fuse_uring_destruct(struct fuse_conn *fc) +{ +} + +static inline bool fuse_uring_enabled(void) +{ + return false; +} + +static inline void fuse_uring_abort(struct fuse_conn *fc) +{ +} + +static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc) +{ +} + +static inline bool fuse_uring_ready(struct fuse_conn *fc) +{ + return false; +} + +#endif /* CONFIG_FUSE_IO_URING */ + +#endif /* _FS_FUSE_DEV_URING_I_H */ diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 494ac372ace0..198862b086ff 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -175,9 +175,12 @@ static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args, memset(outarg, 0, sizeof(struct fuse_entry_out)); args->opcode = FUSE_LOOKUP; args->nodeid = nodeid; - args->in_numargs = 1; - args->in_args[0].size = name->len + 1; - args->in_args[0].value = name->name; + args->in_numargs = 3; + fuse_set_zero_arg0(args); + args->in_args[1].size = name->len; + args->in_args[1].value = name->name; + args->in_args[2].size = 1; + args->in_args[2].value = ""; args->out_numargs = 1; args->out_args[0].size = sizeof(struct fuse_entry_out); args->out_args[0].value = outarg; @@ -192,10 +195,10 @@ static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args, * the lookup once more. If the lookup results in the same inode, * then refresh the attributes, timeouts and mark the dentry valid. */ -static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) +static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *entry, unsigned int flags) { struct inode *inode; - struct dentry *parent; struct fuse_mount *fm; struct fuse_inode *fi; int ret; @@ -227,11 +230,9 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) attr_version = fuse_get_attr_version(fm->fc); - parent = dget_parent(entry); - fuse_lookup_init(fm->fc, &args, get_node_id(d_inode(parent)), - &entry->d_name, &outarg); + fuse_lookup_init(fm->fc, &args, get_node_id(dir), + name, &outarg); ret = fuse_simple_request(fm, &args); - dput(parent); /* Zero nodeid is same as -ENOENT */ if (!ret && !outarg.nodeid) ret = -ENOENT; @@ -265,9 +266,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) if (test_bit(FUSE_I_INIT_RDPLUS, &fi->state)) return -ECHILD; } else if (test_and_clear_bit(FUSE_I_INIT_RDPLUS, &fi->state)) { - parent = dget_parent(entry); - fuse_advise_use_readdirplus(d_inode(parent)); - dput(parent); + fuse_advise_use_readdirplus(dir); } } ret = 1; @@ -467,29 +466,29 @@ static int get_security_context(struct dentry *entry, umode_t mode, { struct fuse_secctx *fctx; struct fuse_secctx_header *header; - void *ctx = NULL, *ptr; - u32 ctxlen, total_len = sizeof(*header); + struct lsm_context lsmctx = { }; + void *ptr; + u32 total_len = sizeof(*header); int err, nr_ctx = 0; - const char *name; + const char *name = NULL; size_t namelen; err = security_dentry_init_security(entry, mode, &entry->d_name, - &name, &ctx, &ctxlen); - if (err) { - if (err != -EOPNOTSUPP) - goto out_err; - /* No LSM is supporting this security hook. Ignore error */ - ctxlen = 0; - ctx = NULL; - } + &name, &lsmctx); - if (ctxlen) { + /* If no LSM is supporting this security hook ignore error */ + if (err && err != -EOPNOTSUPP) + goto out_err; + + if (lsmctx.len) { nr_ctx = 1; namelen = strlen(name) + 1; err = -EIO; - if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || ctxlen > S32_MAX)) + if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || + lsmctx.len > S32_MAX)) goto out_err; - total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + ctxlen); + total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + + lsmctx.len); } err = -ENOMEM; @@ -502,19 +501,20 @@ static int get_security_context(struct dentry *entry, umode_t mode, ptr += sizeof(*header); if (nr_ctx) { fctx = ptr; - fctx->size = ctxlen; + fctx->size = lsmctx.len; ptr += sizeof(*fctx); strcpy(ptr, name); ptr += namelen; - memcpy(ptr, ctx, ctxlen); + memcpy(ptr, lsmctx.context, lsmctx.len); } ext->size = total_len; ext->value = header; err = 0; out_err: - kfree(ctx); + if (nr_ctx) + security_release_secctx(&lsmctx); return err; } @@ -928,11 +928,12 @@ static int fuse_symlink(struct mnt_idmap *idmap, struct inode *dir, FUSE_ARGS(args); args.opcode = FUSE_SYMLINK; - args.in_numargs = 2; - args.in_args[0].size = entry->d_name.len + 1; - args.in_args[0].value = entry->d_name.name; - args.in_args[1].size = len; - args.in_args[1].value = link; + args.in_numargs = 3; + fuse_set_zero_arg0(&args); + args.in_args[1].size = entry->d_name.len + 1; + args.in_args[1].value = entry->d_name.name; + args.in_args[2].size = len; + args.in_args[2].value = link; return create_new_entry(idmap, fm, &args, dir, entry, S_IFLNK); } @@ -992,9 +993,10 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) args.opcode = FUSE_UNLINK; args.nodeid = get_node_id(dir); - args.in_numargs = 1; - args.in_args[0].size = entry->d_name.len + 1; - args.in_args[0].value = entry->d_name.name; + args.in_numargs = 2; + fuse_set_zero_arg0(&args); + args.in_args[1].size = entry->d_name.len + 1; + args.in_args[1].value = entry->d_name.name; err = fuse_simple_request(fm, &args); if (!err) { fuse_dir_changed(dir); @@ -1015,9 +1017,10 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) args.opcode = FUSE_RMDIR; args.nodeid = get_node_id(dir); - args.in_numargs = 1; - args.in_args[0].size = entry->d_name.len + 1; - args.in_args[0].value = entry->d_name.name; + args.in_numargs = 2; + fuse_set_zero_arg0(&args); + args.in_args[1].size = entry->d_name.len + 1; + args.in_args[1].value = entry->d_name.name; err = fuse_simple_request(fm, &args); if (!err) { fuse_dir_changed(dir); @@ -1681,6 +1684,8 @@ static int fuse_dir_open(struct inode *inode, struct file *file) */ if (ff->open_flags & (FOPEN_STREAM | FOPEN_NONSEEKABLE)) nonseekable_open(inode, file); + if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); } return err; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 88d0946b5bc9..7d92a5479998 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1541,8 +1541,10 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, */ struct page **pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); - if (!pages) - return -ENOMEM; + if (!pages) { + ret = -ENOMEM; + goto out; + } while (nbytes < *nbytesp && nr_pages < max_pages) { unsigned nfolios, i; @@ -1557,18 +1559,22 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, nbytes += ret; - ret += start; - /* Currently, all folios in FUSE are one page */ - nfolios = DIV_ROUND_UP(ret, PAGE_SIZE); + nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE); - ap->descs[ap->num_folios].offset = start; - fuse_folio_descs_length_init(ap->descs, ap->num_folios, nfolios); - for (i = 0; i < nfolios; i++) - ap->folios[i + ap->num_folios] = page_folio(pages[i]); + for (i = 0; i < nfolios; i++) { + struct folio *folio = page_folio(pages[i]); + unsigned int offset = start + + (folio_page_idx(folio, pages[i]) << PAGE_SHIFT); + unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start); + + ap->descs[ap->num_folios].offset = offset; + ap->descs[ap->num_folios].length = len; + ap->folios[ap->num_folios] = folio; + start = 0; + ret -= len; + ap->num_folios++; + } - ap->num_folios += nfolios; - ap->descs[ap->num_folios - 1].length -= - (PAGE_SIZE - ret) & (PAGE_SIZE - 1); nr_pages += nfolios; } kfree(pages); @@ -1584,6 +1590,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, else ap->args.out_pages = true; +out: *nbytesp = nbytes; return ret < 0 ? ret : 0; diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h new file mode 100644 index 000000000000..3b2bfe1248d3 --- /dev/null +++ b/fs/fuse/fuse_dev_i.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * FUSE: Filesystem in Userspace + * Copyright (C) 2001-2008 Miklos Szeredi + */ +#ifndef _FS_FUSE_DEV_I_H +#define _FS_FUSE_DEV_I_H + +#include + +/* Ordinary requests have even IDs, while interrupts IDs are odd */ +#define FUSE_INT_REQ_BIT (1ULL << 0) +#define FUSE_REQ_ID_STEP (1ULL << 1) + +struct fuse_arg; +struct fuse_args; +struct fuse_pqueue; +struct fuse_req; +struct fuse_iqueue; +struct fuse_forget_link; + +struct fuse_copy_state { + int write; + struct fuse_req *req; + struct iov_iter *iter; + struct pipe_buffer *pipebufs; + struct pipe_buffer *currbuf; + struct pipe_inode_info *pipe; + unsigned long nr_segs; + struct page *pg; + unsigned int len; + unsigned int offset; + unsigned int move_pages:1; + unsigned int is_uring:1; + struct { + unsigned int copied_sz; /* copied size into the user buffer */ + } ring; +}; + +static inline struct fuse_dev *fuse_get_dev(struct file *file) +{ + /* + * Lockless access is OK, because file->private data is set + * once during mount and is valid until the file is released. + */ + return READ_ONCE(file->private_data); +} + +unsigned int fuse_req_hash(u64 unique); +struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique); + +void fuse_dev_end_requests(struct list_head *head); + +void fuse_copy_init(struct fuse_copy_state *cs, int write, + struct iov_iter *iter); +int fuse_copy_args(struct fuse_copy_state *cs, unsigned int numargs, + unsigned int argpages, struct fuse_arg *args, + int zeroing); +int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args, + unsigned int nbytes); +void fuse_dev_queue_forget(struct fuse_iqueue *fiq, + struct fuse_forget_link *forget); +void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req); + +#endif + diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 74744c6f2860..fee96fe7887b 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -310,7 +310,7 @@ struct fuse_args { bool is_ext:1; bool is_pinned:1; bool invalidate_vmap:1; - struct fuse_in_arg in_args[3]; + struct fuse_in_arg in_args[4]; struct fuse_arg out_args[2]; void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error); /* Used for kvec iter backed by vmalloc address */ @@ -438,6 +438,10 @@ struct fuse_req { /** fuse_mount this request belongs to */ struct fuse_mount *fm; + +#ifdef CONFIG_FUSE_IO_URING + void *ring_entry; +#endif }; struct fuse_iqueue; @@ -863,6 +867,9 @@ struct fuse_conn { /* Use pages instead of pointer for kernel I/O */ unsigned int use_pages_for_kvec_io:1; + /* Use io_uring for communication */ + unsigned int io_uring; + /** Maximum stack depth for passthrough backing files */ int max_stack_depth; @@ -923,6 +930,11 @@ struct fuse_conn { /** IDR for backing files ids */ struct idr backing_files_map; #endif + +#ifdef CONFIG_FUSE_IO_URING + /** uring connection information*/ + struct fuse_ring *ring; +#endif }; /* @@ -947,6 +959,19 @@ struct fuse_mount { struct rcu_head rcu; }; +/* + * Empty header for FUSE opcodes without specific header needs. + * Used as a placeholder in args->in_args[0] for consistency + * across all FUSE operations, simplifying request handling. + */ +struct fuse_zero_header {}; + +static inline void fuse_set_zero_arg0(struct fuse_args *args) +{ + args->in_args[0].size = sizeof(struct fuse_zero_header); + args->in_args[0].value = NULL; +} + static inline struct fuse_mount *get_fuse_mount_super(struct super_block *sb) { return sb->s_fs_info; @@ -1219,6 +1244,11 @@ void fuse_change_entry_timeout(struct dentry *entry, struct fuse_entry_out *o); */ struct fuse_conn *fuse_conn_get(struct fuse_conn *fc); +/** + * Initialize the fuse processing queue + */ +void fuse_pqueue_init(struct fuse_pqueue *fpq); + /** * Initialize fuse_conn */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 3ce4f4e81d09..e9db2cb8c150 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -7,6 +7,7 @@ */ #include "fuse_i.h" +#include "dev_uring_i.h" #include #include @@ -937,7 +938,7 @@ static void fuse_iqueue_init(struct fuse_iqueue *fiq, fiq->priv = priv; } -static void fuse_pqueue_init(struct fuse_pqueue *fpq) +void fuse_pqueue_init(struct fuse_pqueue *fpq) { unsigned int i; @@ -992,6 +993,8 @@ static void delayed_release(struct rcu_head *p) { struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu); + fuse_uring_destruct(fc); + put_user_ns(fc->user_ns); fc->release(fc); } @@ -1387,6 +1390,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, else ok = false; } + if (flags & FUSE_OVER_IO_URING && fuse_uring_enabled()) + fc->io_uring = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1446,6 +1451,13 @@ void fuse_send_init(struct fuse_mount *fm) if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) flags |= FUSE_PASSTHROUGH; + /* + * This is just an information flag for fuse server. No need to check + * the reply - server is either sending IORING_OP_URING_CMD or not. + */ + if (fuse_uring_enabled()) + flags |= FUSE_OVER_IO_URING; + ia->in.flags = flags; ia->in.flags2 = flags >> 32; diff --git a/fs/fuse/sysctl.c b/fs/fuse/sysctl.c index b272bb333005..63fb1e5bee30 100644 --- a/fs/fuse/sysctl.c +++ b/fs/fuse/sysctl.c @@ -13,7 +13,7 @@ static struct ctl_table_header *fuse_table_header; /* Bound by fuse_init_out max_pages, which is a u16 */ static unsigned int sysctl_fuse_max_pages_limit = 65535; -static struct ctl_table fuse_sysctl_table[] = { +static const struct ctl_table fuse_sysctl_table[] = { { .procname = "max_pages_limit", .data = &fuse_max_pages_limit, diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 9f568d345c51..93dfb06b6cea 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -164,9 +164,10 @@ int fuse_removexattr(struct inode *inode, const char *name) args.opcode = FUSE_REMOVEXATTR; args.nodeid = get_node_id(inode); - args.in_numargs = 1; - args.in_args[0].size = strlen(name) + 1; - args.in_args[0].value = name; + args.in_numargs = 2; + fuse_set_zero_arg0(&args); + args.in_args[1].size = strlen(name) + 1; + args.in_args[1].value = name; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fm->fc->no_removexattr = 1; diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index 2e215e8c3c88..95050e719233 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -21,7 +21,9 @@ /** * gfs2_drevalidate - Check directory lookup consistency - * @dentry: the mapping to check + * @dir: expected parent directory inode + * @name: expexted name + * @dentry: dentry to check * @flags: lookup flags * * Check to make sure the lookup necessary to arrive at this inode from its @@ -30,50 +32,43 @@ * Returns: 1 if the dentry is ok, 0 if it isn't */ -static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags) +static int gfs2_drevalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - struct dentry *parent; - struct gfs2_sbd *sdp; - struct gfs2_inode *dip; + struct gfs2_sbd *sdp = GFS2_SB(dir); + struct gfs2_inode *dip = GFS2_I(dir); struct inode *inode; struct gfs2_holder d_gh; struct gfs2_inode *ip = NULL; - int error, valid = 0; + int error, valid; int had_lock = 0; if (flags & LOOKUP_RCU) return -ECHILD; - parent = dget_parent(dentry); - sdp = GFS2_SB(d_inode(parent)); - dip = GFS2_I(d_inode(parent)); inode = d_inode(dentry); if (inode) { if (is_bad_inode(inode)) - goto out; + return 0; ip = GFS2_I(inode); } - if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL) { - valid = 1; - goto out; - } + if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL) + return 1; had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL); if (!had_lock) { error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh); if (error) - goto out; + return 0; } - error = gfs2_dir_check(d_inode(parent), &dentry->d_name, ip); + error = gfs2_dir_check(dir, name, ip); valid = inode ? !error : (error == -ENOENT); if (!had_lock) gfs2_glock_dq_uninit(&d_gh); -out: - dput(parent); return valid; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 1e73cf87ff88..c9bb3be21d2b 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -251,6 +251,7 @@ static int do_gfs2_set_flags(struct inode *inode, u32 reqflags, u32 mask) error = filemap_fdatawait(inode->i_mapping); if (error) goto out; + truncate_inode_pages(inode->i_mapping, 0); if (new_flags & GFS2_DIF_JDATA) gfs2_ordered_del_inode(ip); } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 72b48f6f5561..58bc5013ca49 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -236,8 +236,7 @@ static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, str return NULL; qd->qd_sbd = sdp; - qd->qd_lockref.count = 0; - spin_lock_init(&qd->qd_lockref.lock); + lockref_init(&qd->qd_lockref, 0); qd->qd_id = qid; qd->qd_slot = -1; INIT_LIST_HEAD(&qd->qd_lru); diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index f462d9cb3087..988f38dc5b2c 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -44,8 +44,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip, int ret; ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ - if (capable(CAP_SYS_RESOURCE) || - sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF || + capable(CAP_SYS_RESOURCE)) return 0; ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); if (ret) diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 3bee9b5dba5e..fe09c2093a93 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -349,11 +349,13 @@ static int hfs_fill_super(struct super_block *sb, struct fs_context *fc) goto bail_no_root; res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd); if (!res) { - if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { + if (fd.entrylength != sizeof(rec.dir)) { res = -EIO; goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); + if (rec.type != HFS_CDR_DIR) + res = -EIO; } if (res) goto bail_hfs_find; diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c index 76fa02e3835b..ef54fc8093cf 100644 --- a/fs/hfs/sysdep.c +++ b/fs/hfs/sysdep.c @@ -13,7 +13,8 @@ /* dentry case-handling: just lowercase everything */ -static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags) +static int hfs_revalidate_dentry(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; int diff; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 7e51d2cec64b..e0741e468956 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -95,32 +95,17 @@ __uml_setup("hostfs=", hostfs_args, static char *__dentry_name(struct dentry *dentry, char *name) { char *p = dentry_path_raw(dentry, name, PATH_MAX); - char *root; - size_t len; - struct hostfs_fs_info *fsi; + struct hostfs_fs_info *fsi = dentry->d_sb->s_fs_info; + char *root = fsi->host_root_path; + size_t len = strlen(root); - fsi = dentry->d_sb->s_fs_info; - root = fsi->host_root_path; - len = strlen(root); - if (IS_ERR(p)) { + if (IS_ERR(p) || len > p - name) { __putname(name); return NULL; } - /* - * This function relies on the fact that dentry_path_raw() will place - * the path name at the end of the provided buffer. - */ - BUG_ON(p + strlen(p) + 1 != name + PATH_MAX); - - strscpy(name, root, PATH_MAX); - if (len > p - name) { - __putname(name); - return NULL; - } - - if (p > name + len) - strcpy(name + len, p); + memcpy(name, root, len); + memmove(name + len, p, name + PATH_MAX - p); return name; } @@ -410,38 +395,33 @@ static const struct file_operations hostfs_dir_fops = { .fsync = hostfs_fsync, }; -static int hostfs_writepage(struct page *page, struct writeback_control *wbc) +static int hostfs_writepages(struct address_space *mapping, + struct writeback_control *wbc) { - struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; - char *buffer; - loff_t base = page_offset(page); - int count = PAGE_SIZE; - int end_index = inode->i_size >> PAGE_SHIFT; - int err; + struct folio *folio = NULL; + loff_t i_size = i_size_read(inode); + int err = 0; - if (page->index >= end_index) - count = inode->i_size & (PAGE_SIZE-1); + while ((folio = writeback_iter(mapping, wbc, folio, &err))) { + loff_t pos = folio_pos(folio); + size_t count = folio_size(folio); + char *buffer; + int ret; - buffer = kmap_local_page(page); + if (count > i_size - pos) + count = i_size - pos; - err = write_file(HOSTFS_I(inode)->fd, &base, buffer, count); - if (err != count) { - if (err >= 0) - err = -EIO; - mapping_set_error(mapping, err); - goto out; + buffer = kmap_local_folio(folio, 0); + ret = write_file(HOSTFS_I(inode)->fd, &pos, buffer, count); + kunmap_local(buffer); + folio_unlock(folio); + if (ret != count) { + err = ret < 0 ? ret : -EIO; + mapping_set_error(mapping, err); + } } - if (base > inode->i_size) - inode->i_size = base; - - err = 0; - - out: - kunmap_local(buffer); - unlock_page(page); - return err; } @@ -506,11 +486,12 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping, } static const struct address_space_operations hostfs_aops = { - .writepage = hostfs_writepage, + .writepages = hostfs_writepages, .read_folio = hostfs_read_folio, .dirty_folio = filemap_dirty_folio, .write_begin = hostfs_write_begin, .write_end = hostfs_write_end, + .migrate_folio = filemap_migrate_folio, }; static int hostfs_inode_update(struct inode *ino, const struct hostfs_stat *st) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 90f883d6b8fd..0fc179a59830 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -99,7 +99,6 @@ static const struct fs_parameter_spec hugetlb_fs_parameters[] = { static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); - struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); @@ -116,10 +115,6 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND); vma->vm_ops = &hugetlb_vm_ops; - ret = seal_check_write(info->seals, vma); - if (ret) - return ret; - /* * page based offset in vm_pgoff could be sufficiently large to * overflow a loff_t when converted to byte offset. This can @@ -819,13 +814,13 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, * folios in these areas, we need to consume the reserves * to keep reservation accounting consistent. */ - folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0); + folio = alloc_hugetlb_folio(&pseudo_vma, addr, false); if (IS_ERR(folio)) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); error = PTR_ERR(folio); goto out; } - folio_zero_user(folio, ALIGN_DOWN(addr, hpage_size)); + folio_zero_user(folio, addr); __folio_mark_uptodate(folio); error = hugetlb_add_to_page_cache(folio, mapping, index); if (unlikely(error)) { diff --git a/fs/inode.c b/fs/inode.c index 6b4c77268fc0..5587aabdaa5e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -184,7 +184,7 @@ static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table inodes_sysctls[] = { +static const struct ctl_table inodes_sysctls[] = { { .procname = "inode-nr", .data = &inodes_stat, diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 955f19e27e47..d303e6c8900c 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1138,7 +1138,7 @@ static void iomap_write_delalloc_scan(struct inode *inode, start_byte, end_byte, iomap, punch); /* move offset to start of next folio in range */ - start_byte = folio_next_index(folio) << PAGE_SHIFT; + start_byte = folio_pos(folio) + folio_size(folio); folio_unlock(folio); folio_put(folio); } @@ -1774,7 +1774,8 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos) */ static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, loff_t pos, unsigned len) + struct inode *inode, loff_t pos, loff_t end_pos, + unsigned len) { struct iomap_folio_state *ifs = folio->private; size_t poff = offset_in_folio(folio, pos); @@ -1793,15 +1794,60 @@ new_ioend: if (ifs) atomic_add(len, &ifs->write_bytes_pending); + + /* + * Clamp io_offset and io_size to the incore EOF so that ondisk + * file size updates in the ioend completion are byte-accurate. + * This avoids recovering files with zeroed tail regions when + * writeback races with appending writes: + * + * Thread 1: Thread 2: + * ------------ ----------- + * write [A, A+B] + * update inode size to A+B + * submit I/O [A, A+BS] + * write [A+B, A+B+C] + * update inode size to A+B+C + * + * + * + * After reboot: + * 1) with A+B+C < A+BS, the file has zero padding in range + * [A+B, A+B+C] + * + * |< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000| + * ^ ^ ^ + * A A+B A+B+C + * (EOF) + * + * 2) with A+B+C > A+BS, the file has zero padding in range + * [A+B, A+BS] + * + * |< Block Size (BS) >|< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000|00000000000000000000000000| + * ^ ^ ^ ^ + * A A+B A+BS A+B+C + * (EOF) + * + * D = Valid Data + * 0 = Zero Padding + * + * Note that this defeats the ability to chain the ioends of + * appending writes. + */ wpc->ioend->io_size += len; + if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos) + wpc->ioend->io_size = end_pos - wpc->ioend->io_offset; + wbc_account_cgroup_owner(wbc, folio, len); return 0; } static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, u64 pos, unsigned dirty_len, - unsigned *count) + struct inode *inode, u64 pos, u64 end_pos, + unsigned dirty_len, unsigned *count) { int error; @@ -1826,7 +1872,7 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, break; default: error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos, - map_len); + end_pos, map_len); if (!error) (*count)++; break; @@ -1897,11 +1943,11 @@ static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode, * remaining memory is zeroed when mapped, and writes to that * region are not written out to the file. * - * Also adjust the writeback range to skip all blocks entirely - * beyond i_size. + * Also adjust the end_pos to the end of file and skip writeback + * for all blocks entirely beyond i_size. */ folio_zero_segment(folio, poff, folio_size(folio)); - *end_pos = round_up(isize, i_blocksize(inode)); + *end_pos = isize; } return true; @@ -1914,6 +1960,7 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, struct inode *inode = folio->mapping->host; u64 pos = folio_pos(folio); u64 end_pos = pos + folio_size(folio); + u64 end_aligned = 0; unsigned count = 0; int error = 0; u32 rlen; @@ -1955,9 +2002,10 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, /* * Walk through the folio to find dirty areas to write back. */ - while ((rlen = iomap_find_dirty_range(folio, &pos, end_pos))) { + end_aligned = round_up(end_pos, i_blocksize(inode)); + while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) { error = iomap_writepage_map_blocks(wpc, wbc, folio, inode, - pos, rlen, &count); + pos, end_pos, rlen, &count); if (error) break; pos += rlen; diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c index 5fc0ac36dee3..b90d0eda9e51 100644 --- a/fs/iomap/swapfile.c +++ b/fs/iomap/swapfile.c @@ -189,7 +189,6 @@ int iomap_swapfile_activate(struct swap_info_struct *sis, *pagespan = 1 + isi.highest_ppage - isi.lowest_ppage; sis->max = isi.nr_pages; sis->pages = isi.nr_pages - 1; - sis->highest_bit = isi.nr_pages - 1; return isi.nr_extents; } EXPORT_SYMBOL_GPL(iomap_swapfile_activate); diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c index 34d5baa5d88a..5f3b6da0e022 100644 --- a/fs/isofs/compress.c +++ b/fs/isofs/compress.c @@ -301,7 +301,6 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount, */ static int zisofs_read_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; int err; @@ -311,16 +310,15 @@ static int zisofs_read_folio(struct file *file, struct folio *folio) PAGE_SHIFT <= zisofs_block_shift ? (1 << (zisofs_block_shift - PAGE_SHIFT)) : 0; struct page **pages; - pgoff_t index = page->index, end_index; + pgoff_t index = folio->index, end_index; end_index = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; /* - * If this page is wholly outside i_size we just return zero; + * If this folio is wholly outside i_size we just return zero; * do_generic_file_read() will handle this for us */ if (index >= end_index) { - SetPageUptodate(page); - unlock_page(page); + folio_end_read(folio, true); return 0; } @@ -338,10 +336,10 @@ static int zisofs_read_folio(struct file *file, struct folio *folio) pages = kcalloc(max_t(unsigned int, zisofs_pages_per_cblock, 1), sizeof(*pages), GFP_KERNEL); if (!pages) { - unlock_page(page); + folio_unlock(folio); return -ENOMEM; } - pages[full_page] = page; + pages[full_page] = &folio->page; for (i = 0; i < pcount; i++, index++) { if (i != full_page) diff --git a/fs/jbd2/Kconfig b/fs/jbd2/Kconfig index 4ad2c67f93f1..9c19e1512101 100644 --- a/fs/jbd2/Kconfig +++ b/fs/jbd2/Kconfig @@ -2,8 +2,6 @@ config JBD2 tristate select CRC32 - select CRYPTO - select CRYPTO_CRC32C help This is a generic journaling layer for block devices that support both 32-bit and 64-bit block numbers. It is currently used by diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 9153ff3a08e7..e8e80761ac73 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -772,9 +772,9 @@ start_journal_io: /* * If the journal is not located on the file system device, * then we must flush the file system device before we issue - * the commit record + * the commit record and update the journal tail sequence. */ - if (commit_transaction->t_need_data_flush && + if ((commit_transaction->t_need_data_flush || update_tail) && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) blkdev_issue_flush(journal->j_fs_dev); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 7e49d912b091..d8084b31b361 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1369,20 +1369,12 @@ static int journal_check_superblock(journal_t *journal) return err; } - /* Load the checksum driver */ if (jbd2_journal_has_csum_v2or3_feature(journal)) { if (sb->s_checksum_type != JBD2_CRC32C_CHKSUM) { printk(KERN_ERR "JBD2: Unknown checksum type\n"); return err; } - journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); - if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); - err = PTR_ERR(journal->j_chksum_driver); - journal->j_chksum_driver = NULL; - return err; - } /* Check superblock checksum */ if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) { printk(KERN_ERR "JBD2: journal checksum error\n"); @@ -1608,8 +1600,6 @@ static journal_t *journal_init_common(struct block_device *bdev, err_cleanup: percpu_counter_destroy(&journal->j_checkpoint_jh_count); - if (journal->j_chksum_driver) - crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); journal_fail_superblock(journal); @@ -2191,8 +2181,6 @@ int jbd2_journal_destroy(journal_t *journal) iput(journal->j_inode); if (journal->j_revoke) jbd2_journal_destroy_revoke(journal); - if (journal->j_chksum_driver) - crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_fc_wbuf); kfree(journal->j_wbuf); kfree(journal); @@ -2337,27 +2325,15 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, } } - /* Load the checksum driver if necessary */ - if ((journal->j_chksum_driver == NULL) && - INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { - journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); - if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); - journal->j_chksum_driver = NULL; - return 0; - } - /* Precompute checksum seed for all metadata */ - journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, - sizeof(sb->s_uuid)); - } - lock_buffer(journal->j_sb_buffer); - /* If enabling v3 checksums, update superblock */ + /* If enabling v3 checksums, update superblock and precompute seed */ if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { sb->s_checksum_type = JBD2_CRC32C_CHKSUM; sb->s_feature_compat &= ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); + journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, + sizeof(sb->s_uuid)); } /* If enabling v1 checksums, downgrade superblock */ diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 4556e4689024..ce63d5fde9c3 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -654,7 +654,7 @@ static void flush_descriptor(journal_t *journal, set_buffer_jwrite(descriptor); BUFFER_TRACE(descriptor, "write"); set_buffer_dirty(descriptor); - write_dirty_buffer(descriptor, REQ_SYNC); + write_dirty_buffer(descriptor, JBD2_JOURNAL_REQ_FLAGS); } #endif diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index d68a4e6ac345..fc8ede43afde 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1576,7 +1576,8 @@ out: return result; } -static int jfs_ci_revalidate(struct dentry *dentry, unsigned int flags) +static int jfs_ci_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { /* * This is not negative dentry. Always valid. diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 458519e416fe..5f0f8b95f44c 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1109,7 +1109,8 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, return ERR_PTR(rc); } -static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) +static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct kernfs_node *kn; struct kernfs_root *root; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 8502ef68459b..0eb320617d7b 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -927,7 +927,7 @@ repeat: if (!inode) continue; - name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name)); + name = QSTR(kn->name); parent = kernfs_get_parent(kn); if (parent) { p_inode = ilookup(info->sb, kernfs_ino(parent)); diff --git a/fs/libfs.c b/fs/libfs.c index 748ac5923154..8444f5cc4064 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -245,9 +245,16 @@ const struct inode_operations simple_dir_inode_operations = { }; EXPORT_SYMBOL(simple_dir_inode_operations); -/* 0 is '.', 1 is '..', so always start with offset 2 or more */ +/* simple_offset_add() never assigns these to a dentry */ enum { - DIR_OFFSET_MIN = 2, + DIR_OFFSET_FIRST = 2, /* Find first real entry */ + DIR_OFFSET_EOD = S32_MAX, +}; + +/* simple_offset_add() allocation range */ +enum { + DIR_OFFSET_MIN = DIR_OFFSET_FIRST + 1, + DIR_OFFSET_MAX = DIR_OFFSET_EOD - 1, }; static void offset_set(struct dentry *dentry, long offset) @@ -291,9 +298,10 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) return -EBUSY; ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN, - LONG_MAX, &octx->next_offset, GFP_KERNEL); - if (ret < 0) - return ret; + DIR_OFFSET_MAX, &octx->next_offset, + GFP_KERNEL); + if (unlikely(ret < 0)) + return ret == -EBUSY ? -ENOSPC : ret; offset_set(dentry, offset); return 0; @@ -329,38 +337,6 @@ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) offset_set(dentry, 0); } -/** - * simple_offset_empty - Check if a dentry can be unlinked - * @dentry: dentry to be tested - * - * Returns 0 if @dentry is a non-empty directory; otherwise returns 1. - */ -int simple_offset_empty(struct dentry *dentry) -{ - struct inode *inode = d_inode(dentry); - struct offset_ctx *octx; - struct dentry *child; - unsigned long index; - int ret = 1; - - if (!inode || !S_ISDIR(inode->i_mode)) - return ret; - - index = DIR_OFFSET_MIN; - octx = inode->i_op->get_offset_ctx(inode); - mt_for_each(&octx->mt, child, index, LONG_MAX) { - spin_lock(&child->d_lock); - if (simple_positive(child)) { - spin_unlock(&child->d_lock); - ret = 0; - break; - } - spin_unlock(&child->d_lock); - } - - return ret; -} - /** * simple_offset_rename - handle directory offsets for rename * @old_dir: parent directory of source entry @@ -454,14 +430,6 @@ void simple_offset_destroy(struct offset_ctx *octx) mtree_destroy(&octx->mt); } -static int offset_dir_open(struct inode *inode, struct file *file) -{ - struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); - - file->private_data = (void *)ctx->next_offset; - return 0; -} - /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated @@ -475,9 +443,6 @@ static int offset_dir_open(struct inode *inode, struct file *file) */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { - struct inode *inode = file->f_inode; - struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); - switch (whence) { case SEEK_CUR: offset += file->f_pos; @@ -490,62 +455,89 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) return -EINVAL; } - /* In this case, ->private_data is protected by f_pos_lock */ - if (!offset) - file->private_data = (void *)ctx->next_offset; return vfs_setpos(file, offset, LONG_MAX); } -static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset) +static struct dentry *find_positive_dentry(struct dentry *parent, + struct dentry *dentry, + bool next) { - MA_STATE(mas, &octx->mt, offset, offset); + struct dentry *found = NULL; + + spin_lock(&parent->d_lock); + if (next) + dentry = d_next_sibling(dentry); + else if (!dentry) + dentry = d_first_child(parent); + hlist_for_each_entry_from(dentry, d_sib) { + if (!simple_positive(dentry)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + if (simple_positive(dentry)) + found = dget_dlock(dentry); + spin_unlock(&dentry->d_lock); + if (likely(found)) + break; + } + spin_unlock(&parent->d_lock); + return found; +} + +static noinline_for_stack struct dentry * +offset_dir_lookup(struct dentry *parent, loff_t offset) +{ + struct inode *inode = d_inode(parent); + struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *child, *found = NULL; - rcu_read_lock(); - child = mas_find(&mas, LONG_MAX); - if (!child) - goto out; - spin_lock(&child->d_lock); - if (simple_positive(child)) - found = dget_dlock(child); - spin_unlock(&child->d_lock); -out: - rcu_read_unlock(); + MA_STATE(mas, &octx->mt, offset, offset); + + if (offset == DIR_OFFSET_FIRST) + found = find_positive_dentry(parent, NULL, false); + else { + rcu_read_lock(); + child = mas_find(&mas, DIR_OFFSET_MAX); + found = find_positive_dentry(parent, child, false); + rcu_read_unlock(); + } return found; } static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { struct inode *inode = d_inode(dentry); - long offset = dentry2offset(dentry); - return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset, - inode->i_ino, fs_umode_to_dtype(inode->i_mode)); + return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len, + inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index) +static void offset_iterate_dir(struct file *file, struct dir_context *ctx) { - struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); + struct dentry *dir = file->f_path.dentry; struct dentry *dentry; + dentry = offset_dir_lookup(dir, ctx->pos); + if (!dentry) + goto out_eod; while (true) { - dentry = offset_find_next(octx, ctx->pos); - if (!dentry) - return; + struct dentry *next; - if (dentry2offset(dentry) >= last_index) { - dput(dentry); - return; - } + ctx->pos = dentry2offset(dentry); + if (!offset_dir_emit(ctx, dentry)) + break; - if (!offset_dir_emit(ctx, dentry)) { - dput(dentry); - return; - } - - ctx->pos = dentry2offset(dentry) + 1; + next = find_positive_dentry(dir, dentry, true); dput(dentry); + + if (!next) + goto out_eod; + dentry = next; } + dput(dentry); + return; + +out_eod: + ctx->pos = DIR_OFFSET_EOD; } /** @@ -565,6 +557,8 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon * * On return, @ctx->pos contains an offset that will read the next entry * in this directory when offset_readdir() is called again with @ctx. + * Caller places this value in the d_off field of the last entry in the + * user's buffer. * * Return values: * %0 - Complete @@ -572,19 +566,17 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; - long last_index = (long)file->private_data; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; - - offset_iterate_dir(d_inode(dir), ctx, last_index); + if (ctx->pos != DIR_OFFSET_EOD) + offset_iterate_dir(file, ctx); return 0; } const struct file_operations simple_offset_dir_operations = { - .open = offset_dir_open, .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, @@ -673,6 +665,7 @@ static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = ctx->magic; s->s_op = ctx->ops ?: &simple_super_operations; + s->s_export_op = ctx->eops; s->s_xattr = ctx->xattr; s->s_time_gran = 1; root = new_inode(s); @@ -1789,7 +1782,7 @@ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, { const struct dentry *parent; const struct inode *dir; - char strbuf[DNAME_INLINE_LEN]; + union shortname_store strbuf; struct qstr qstr; /* @@ -1809,22 +1802,23 @@ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, if (!dir || !IS_CASEFOLDED(dir)) return 1; + qstr.len = len; + qstr.name = str; /* * If the dentry name is stored in-line, then it may be concurrently * modified by a rename. If this happens, the VFS will eventually retry * the lookup, so it doesn't matter what ->d_compare() returns. * However, it's unsafe to call utf8_strncasecmp() with an unstable * string. Therefore, we have to copy the name into a temporary buffer. + * As above, len is guaranteed to match str, so the shortname case + * is exactly when str points to ->d_shortname. */ - if (len <= DNAME_INLINE_LEN - 1) { - memcpy(strbuf, str, len); - strbuf[len] = 0; - str = strbuf; + if (qstr.name == dentry->d_shortname.string) { + strbuf = dentry->d_shortname; // NUL is guaranteed to be in there + qstr.name = strbuf.string; /* prevent compiler from optimizing out the temporary buffer */ barrier(); } - qstr.len = len; - qstr.name = str; return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr); } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 4ec22c2f2ea3..2c8eedc6c2cc 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -70,9 +70,6 @@ static unsigned long nlm_grace_period; unsigned long nlm_timeout = LOCKD_DFLT_TIMEO; static int nlm_udpport, nlm_tcpport; -/* RLIM_NOFILE defaults to 1024. That seems like a reasonable default here. */ -static unsigned int nlm_max_connections = 1024; - /* * Constants needed for the sysctl interface. */ @@ -136,9 +133,6 @@ lockd(void *vrqstp) * NFS mount or NFS daemon has gone away. */ while (!svc_thread_should_stop(rqstp)) { - /* update sv_maxconn if it has changed */ - rqstp->rq_server->sv_maxconn = nlm_max_connections; - nlmsvc_retry_blocked(rqstp); svc_recv(rqstp); } @@ -340,7 +334,6 @@ static int lockd_get(void) return -ENOMEM; } - serv->sv_maxconn = nlm_max_connections; error = svc_set_num_threads(serv, NULL, 1); if (error < 0) { svc_destroy(&serv); @@ -419,7 +412,7 @@ EXPORT_SYMBOL_GPL(lockd_down); * Sysctl parameters (same as module parameters, different interface). */ -static struct ctl_table nlm_sysctls[] = { +static const struct ctl_table nlm_sysctls[] = { { .procname = "nlm_grace_period", .data = &nlm_grace_period, @@ -542,7 +535,6 @@ module_param_call(nlm_udpport, param_set_port, param_get_int, module_param_call(nlm_tcpport, param_set_port, param_get_int, &nlm_tcpport, 0644); module_param(nsm_use_hostnames, bool, 0644); -module_param(nlm_max_connections, uint, 0644); static int lockd_init_net(struct net *net) { diff --git a/fs/locks.c b/fs/locks.c index 25afc8d9c9d1..1619cddfa7a4 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -97,7 +97,7 @@ static int leases_enable = 1; static int lease_break_time = 45; #ifdef CONFIG_SYSCTL -static struct ctl_table locks_sysctls[] = { +static const struct ctl_table locks_sysctls[] = { { .procname = "leases-enable", .data = &leases_enable, diff --git a/fs/mount.h b/fs/mount.h index 185fc56afc13..ffb613cdfeee 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -8,15 +8,23 @@ struct mnt_namespace { struct ns_common ns; struct mount * root; - struct rb_root mounts; /* Protected by namespace_sem */ + struct { + struct rb_root mounts; /* Protected by namespace_sem */ + struct rb_node *mnt_last_node; /* last (rightmost) mount in the rbtree */ + struct rb_node *mnt_first_node; /* first (leftmost) mount in the rbtree */ + }; struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ - wait_queue_head_t poll; + union { + wait_queue_head_t poll; + struct rcu_head mnt_ns_rcu; + }; u64 event; unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; struct rb_node mnt_ns_tree_node; /* node in the mnt_ns_tree */ + struct list_head mnt_ns_list; /* entry in the sequential list of mounts namespace */ refcount_t passive; /* number references not pinning @mounts */ } __randomize_layout; @@ -38,6 +46,7 @@ struct mount { struct dentry *mnt_mountpoint; struct vfsmount mnt; union { + struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; @@ -51,10 +60,7 @@ struct mount { struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ - union { - struct rb_node mnt_node; /* Under ns->mounts */ - struct list_head mnt_list; - }; + struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ @@ -145,24 +151,28 @@ static inline bool is_anon_ns(struct mnt_namespace *ns) return ns->seq == 0; } +static inline bool mnt_ns_attached(const struct mount *mnt) +{ + return !RB_EMPTY_NODE(&mnt->mnt_node); +} + static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { - WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB)); - mnt->mnt.mnt_flags &= ~MNT_ONRB; - rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts); + struct mnt_namespace *ns = mnt->mnt_ns; + WARN_ON(!mnt_ns_attached(mnt)); + if (ns->mnt_last_node == &mnt->mnt_node) + ns->mnt_last_node = rb_prev(&mnt->mnt_node); + if (ns->mnt_first_node == &mnt->mnt_node) + ns->mnt_first_node = rb_next(&mnt->mnt_node); + rb_erase(&mnt->mnt_node, &ns->mounts); + RB_CLEAR_NODE(&mnt->mnt_node); list_add_tail(&mnt->mnt_list, dt_list); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); -struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); -static inline struct mnt_namespace *lookup_next_mnt_ns(struct mnt_namespace *mntns) -{ - return __lookup_next_mnt_ns(mntns, false); -} -static inline struct mnt_namespace *lookup_prev_mnt_ns(struct mnt_namespace *mntns) -{ - return __lookup_next_mnt_ns(mntns, true); -} +struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mnt_ns, + bool previous); + static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); diff --git a/fs/namei.c b/fs/namei.c index 9d30c7aa9aa6..3ab9440c5b93 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -921,10 +921,11 @@ out_dput: return false; } -static inline int d_revalidate(struct dentry *dentry, unsigned int flags) +static inline int d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) - return dentry->d_op->d_revalidate(dentry, flags); + return dentry->d_op->d_revalidate(dir, name, dentry, flags); else return 1; } @@ -1099,7 +1100,7 @@ static int sysctl_protected_fifos __read_mostly; static int sysctl_protected_regular __read_mostly; #ifdef CONFIG_SYSCTL -static struct ctl_table namei_sysctls[] = { +static const struct ctl_table namei_sysctls[] = { { .procname = "protected_symlinks", .data = &sysctl_protected_symlinks, @@ -1652,7 +1653,7 @@ static struct dentry *lookup_dcache(const struct qstr *name, { struct dentry *dentry = d_lookup(dir, name); if (dentry) { - int error = d_revalidate(dentry, flags); + int error = d_revalidate(dir->d_inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) d_invalidate(dentry); @@ -1737,19 +1738,20 @@ static struct dentry *lookup_fast(struct nameidata *nd) if (read_seqcount_retry(&parent->d_seq, nd->seq)) return ERR_PTR(-ECHILD); - status = d_revalidate(dentry, nd->flags); + status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); if (likely(status > 0)) return dentry; if (!try_to_unlazy_next(nd, dentry)) return ERR_PTR(-ECHILD); if (status == -ECHILD) /* we'd been told to redo it in non-rcu mode */ - status = d_revalidate(dentry, nd->flags); + status = d_revalidate(nd->inode, &nd->last, + dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return NULL; - status = d_revalidate(dentry, nd->flags); + status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) @@ -1777,7 +1779,7 @@ again: if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { - int error = d_revalidate(dentry, flags); + int error = d_revalidate(inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) { d_invalidate(dentry); @@ -3575,7 +3577,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, if (d_in_lookup(dentry)) break; - error = d_revalidate(dentry, nd->flags); + error = d_revalidate(dir_inode, &nd->last, dentry, nd->flags); if (likely(error > 0)) break; if (error) @@ -5272,19 +5274,16 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna getname(newname), 0); } -int readlink_copy(char __user *buffer, int buflen, const char *link) +int readlink_copy(char __user *buffer, int buflen, const char *link, int linklen) { - int len = PTR_ERR(link); - if (IS_ERR(link)) - goto out; + int copylen; - len = strlen(link); - if (len > (unsigned) buflen) - len = buflen; - if (copy_to_user(buffer, link, len)) - len = -EFAULT; -out: - return len; + copylen = linklen; + if (unlikely(copylen > (unsigned) buflen)) + copylen = buflen; + if (copy_to_user(buffer, link, copylen)) + copylen = -EFAULT; + return copylen; } /** @@ -5304,6 +5303,9 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) const char *link; int res; + if (inode->i_opflags & IOP_CACHED_LINK) + return readlink_copy(buffer, buflen, inode->i_link, inode->i_linklen); + if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) { if (unlikely(inode->i_op->readlink)) return inode->i_op->readlink(dentry, buffer, buflen); @@ -5322,7 +5324,7 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) if (IS_ERR(link)) return PTR_ERR(link); } - res = readlink_copy(buffer, buflen, link); + res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } @@ -5391,10 +5393,14 @@ EXPORT_SYMBOL(page_put_link); int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { + const char *link; + int res; + DEFINE_DELAYED_CALL(done); - int res = readlink_copy(buffer, buflen, - page_get_link(dentry, d_inode(dentry), - &done)); + link = page_get_link(dentry, d_inode(dentry), &done); + res = PTR_ERR(link); + if (!IS_ERR(link)) + res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } diff --git a/fs/namespace.c b/fs/namespace.c index 23e81c2a1e3f..a3ed3f2980cb 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include "pnode.h" #include "internal.h" @@ -66,12 +66,12 @@ static int __init set_mphash_entries(char *str) __setup("mphash_entries=", set_mphash_entries); static u64 event; -static DEFINE_IDA(mnt_id_ida); +static DEFINE_XARRAY_FLAGS(mnt_id_xa, XA_FLAGS_ALLOC); static DEFINE_IDA(mnt_group_ida); /* Don't allow confusion with old 32bit mount ID */ #define MNT_UNIQUE_ID_OFFSET (1ULL << 31) -static atomic64_t mnt_id_ctr = ATOMIC64_INIT(MNT_UNIQUE_ID_OFFSET); +static u64 mnt_id_ctr = MNT_UNIQUE_ID_OFFSET; static struct hlist_head *mount_hashtable __ro_after_init; static struct hlist_head *mountpoint_hashtable __ro_after_init; @@ -79,8 +79,10 @@ static struct kmem_cache *mnt_cache __ro_after_init; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ -static DEFINE_RWLOCK(mnt_ns_tree_lock); +static DEFINE_SEQLOCK(mnt_ns_tree_lock); + static struct rb_root mnt_ns_tree = RB_ROOT; /* protected by mnt_ns_tree_lock */ +static LIST_HEAD(mnt_ns_list); /* protected by mnt_ns_tree_lock */ struct mount_kattr { unsigned int attr_set; @@ -106,17 +108,6 @@ EXPORT_SYMBOL_GPL(fs_kobj); */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); -static int mnt_ns_cmp(u64 seq, const struct mnt_namespace *ns) -{ - u64 seq_b = ns->seq; - - if (seq < seq_b) - return -1; - if (seq > seq_b) - return 1; - return 0; -} - static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node) { if (!node) @@ -124,25 +115,52 @@ static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node) return rb_entry(node, struct mnt_namespace, mnt_ns_tree_node); } -static bool mnt_ns_less(struct rb_node *a, const struct rb_node *b) +static int mnt_ns_cmp(struct rb_node *a, const struct rb_node *b) { struct mnt_namespace *ns_a = node_to_mnt_ns(a); struct mnt_namespace *ns_b = node_to_mnt_ns(b); u64 seq_a = ns_a->seq; + u64 seq_b = ns_b->seq; - return mnt_ns_cmp(seq_a, ns_b) < 0; + if (seq_a < seq_b) + return -1; + if (seq_a > seq_b) + return 1; + return 0; +} + +static inline void mnt_ns_tree_write_lock(void) +{ + write_seqlock(&mnt_ns_tree_lock); +} + +static inline void mnt_ns_tree_write_unlock(void) +{ + write_sequnlock(&mnt_ns_tree_lock); } static void mnt_ns_tree_add(struct mnt_namespace *ns) { - guard(write_lock)(&mnt_ns_tree_lock); - rb_add(&ns->mnt_ns_tree_node, &mnt_ns_tree, mnt_ns_less); + struct rb_node *node, *prev; + + mnt_ns_tree_write_lock(); + node = rb_find_add_rcu(&ns->mnt_ns_tree_node, &mnt_ns_tree, mnt_ns_cmp); + /* + * If there's no previous entry simply add it after the + * head and if there is add it after the previous entry. + */ + prev = rb_prev(&ns->mnt_ns_tree_node); + if (!prev) + list_add_rcu(&ns->mnt_ns_list, &mnt_ns_list); + else + list_add_rcu(&ns->mnt_ns_list, &node_to_mnt_ns(prev)->mnt_ns_list); + mnt_ns_tree_write_unlock(); + + WARN_ON_ONCE(node); } static void mnt_ns_release(struct mnt_namespace *ns) { - lockdep_assert_not_held(&mnt_ns_tree_lock); - /* keep alive for {list,stat}mount() */ if (refcount_dec_and_test(&ns->passive)) { put_user_ns(ns->user_ns); @@ -151,41 +169,34 @@ static void mnt_ns_release(struct mnt_namespace *ns) } DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T)) +static void mnt_ns_release_rcu(struct rcu_head *rcu) +{ + mnt_ns_release(container_of(rcu, struct mnt_namespace, mnt_ns_rcu)); +} + static void mnt_ns_tree_remove(struct mnt_namespace *ns) { /* remove from global mount namespace list */ if (!is_anon_ns(ns)) { - guard(write_lock)(&mnt_ns_tree_lock); + mnt_ns_tree_write_lock(); rb_erase(&ns->mnt_ns_tree_node, &mnt_ns_tree); + list_bidir_del_rcu(&ns->mnt_ns_list); + mnt_ns_tree_write_unlock(); } - mnt_ns_release(ns); + call_rcu(&ns->mnt_ns_rcu, mnt_ns_release_rcu); } -/* - * Returns the mount namespace which either has the specified id, or has the - * next smallest id afer the specified one. - */ -static struct mnt_namespace *mnt_ns_find_id_at(u64 mnt_ns_id) +static int mnt_ns_find(const void *key, const struct rb_node *node) { - struct rb_node *node = mnt_ns_tree.rb_node; - struct mnt_namespace *ret = NULL; + const u64 mnt_ns_id = *(u64 *)key; + const struct mnt_namespace *ns = node_to_mnt_ns(node); - lockdep_assert_held(&mnt_ns_tree_lock); - - while (node) { - struct mnt_namespace *n = node_to_mnt_ns(node); - - if (mnt_ns_id <= n->seq) { - ret = node_to_mnt_ns(node); - if (mnt_ns_id == n->seq) - break; - node = node->rb_left; - } else { - node = node->rb_right; - } - } - return ret; + if (mnt_ns_id < ns->seq) + return -1; + if (mnt_ns_id > ns->seq) + return 1; + return 0; } /* @@ -195,18 +206,37 @@ static struct mnt_namespace *mnt_ns_find_id_at(u64 mnt_ns_id) * namespace the @namespace_sem must first be acquired. If the namespace has * already shut down before acquiring @namespace_sem, {list,stat}mount() will * see that the mount rbtree of the namespace is empty. + * + * Note the lookup is lockless protected by a sequence counter. We only + * need to guard against false negatives as false positives aren't + * possible. So if we didn't find a mount namespace and the sequence + * counter has changed we need to retry. If the sequence counter is + * still the same we know the search actually failed. */ static struct mnt_namespace *lookup_mnt_ns(u64 mnt_ns_id) { - struct mnt_namespace *ns; + struct mnt_namespace *ns; + struct rb_node *node; + unsigned int seq; - guard(read_lock)(&mnt_ns_tree_lock); - ns = mnt_ns_find_id_at(mnt_ns_id); - if (!ns || ns->seq != mnt_ns_id) - return NULL; + guard(rcu)(); + do { + seq = read_seqbegin(&mnt_ns_tree_lock); + node = rb_find_rcu(&mnt_ns_id, &mnt_ns_tree, mnt_ns_find); + if (node) + break; + } while (read_seqretry(&mnt_ns_tree_lock, seq)); - refcount_inc(&ns->passive); - return ns; + if (!node) + return NULL; + + /* + * The last reference count is put with RCU delay so we can + * unconditonally acquire a reference here. + */ + ns = node_to_mnt_ns(node); + refcount_inc(&ns->passive); + return ns; } static inline void lock_mount_hash(void) @@ -236,18 +266,19 @@ static inline struct hlist_head *mp_hash(struct dentry *dentry) static int mnt_alloc_id(struct mount *mnt) { - int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); + int res; - if (res < 0) - return res; - mnt->mnt_id = res; - mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr); - return 0; + xa_lock(&mnt_id_xa); + res = __xa_alloc(&mnt_id_xa, &mnt->mnt_id, mnt, XA_LIMIT(1, INT_MAX), GFP_KERNEL); + if (!res) + mnt->mnt_id_unique = ++mnt_id_ctr; + xa_unlock(&mnt_id_xa); + return res; } static void mnt_free_id(struct mount *mnt) { - ida_free(&mnt_id_ida, mnt->mnt_id); + xa_erase(&mnt_id_xa, mnt->mnt_id); } /* @@ -344,6 +375,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); + RB_CLEAR_NODE(&mnt->mnt_node); mnt->mnt.mnt_idmap = &nop_mnt_idmap; } return mnt; @@ -1123,19 +1155,27 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) { struct rb_node **link = &ns->mounts.rb_node; struct rb_node *parent = NULL; + bool mnt_first_node = true, mnt_last_node = true; - WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB); + WARN_ON(mnt_ns_attached(mnt)); mnt->mnt_ns = ns; while (*link) { parent = *link; - if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) + if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) { link = &parent->rb_left; - else + mnt_last_node = false; + } else { link = &parent->rb_right; + mnt_first_node = false; + } } + + if (mnt_last_node) + ns->mnt_last_node = &mnt->mnt_node; + if (mnt_first_node) + ns->mnt_first_node = &mnt->mnt_node; rb_link_node(&mnt->mnt_node, parent, link); rb_insert_color(&mnt->mnt_node, &ns->mounts); - mnt->mnt.mnt_flags |= MNT_ONRB; } /* @@ -1305,7 +1345,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, } mnt->mnt.mnt_flags = old->mnt.mnt_flags; - mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB); + mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); @@ -1763,7 +1803,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; - if (p->mnt.mnt_flags & MNT_ONRB) + if (mnt_ns_attached(p)) move_from_ns(p, &tmp_list); else list_move(&p->mnt_list, &tmp_list); @@ -1912,16 +1952,14 @@ static int do_umount(struct mount *mnt, int flags) event++; if (flags & MNT_DETACH) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } @@ -2055,9 +2093,15 @@ SYSCALL_DEFINE1(oldumount, char __user *, name) static bool is_mnt_ns_file(struct dentry *dentry) { + struct ns_common *ns; + /* Is this a proxy for a mount namespace? */ - return dentry->d_op == &ns_dentry_operations && - dentry->d_fsdata == &mntns_operations; + if (dentry->d_op != &ns_dentry_operations) + return false; + + ns = d_inode(dentry)->i_private; + + return ns->ops == &mntns_operations; } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) @@ -2065,30 +2109,34 @@ struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) return &mnt->ns; } -struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mntns, bool previous) +struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mntns, bool previous) { - guard(read_lock)(&mnt_ns_tree_lock); + guard(rcu)(); + for (;;) { - struct rb_node *node; + struct list_head *list; if (previous) - node = rb_prev(&mntns->mnt_ns_tree_node); + list = rcu_dereference(list_bidir_prev_rcu(&mntns->mnt_ns_list)); else - node = rb_next(&mntns->mnt_ns_tree_node); - if (!node) + list = rcu_dereference(list_next_rcu(&mntns->mnt_ns_list)); + if (list_is_head(list, &mnt_ns_list)) return ERR_PTR(-ENOENT); - mntns = node_to_mnt_ns(node); - node = &mntns->mnt_ns_tree_node; + mntns = list_entry_rcu(list, struct mnt_namespace, mnt_ns_list); + /* + * The last passive reference count is put with RCU + * delay so accessing the mount namespace is not just + * safe but all relevant members are still valid. + */ if (!ns_capable_noaudit(mntns->user_ns, CAP_SYS_ADMIN)) continue; /* - * Holding mnt_ns_tree_lock prevents the mount namespace from - * being freed but it may well be on it's deathbed. We want an - * active reference, not just a passive one here as we're - * persisting the mount namespace. + * We need an active reference count as we're persisting + * the mount namespace and it might already be on its + * deathbed. */ if (!refcount_inc_not_zero(&mntns->ns.count)) continue; @@ -2732,8 +2780,13 @@ static struct mount *__do_loopback(struct path *old_path, int recurse) if (IS_MNT_UNBINDABLE(old)) return mnt; - if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) - return mnt; + if (!check_mnt(old)) { + const struct dentry_operations *d_op = old_path->dentry->d_op; + + if (d_op != &ns_dentry_operations && + d_op != &pidfs_dentry_operations) + return mnt; + } if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; @@ -3835,7 +3888,7 @@ int path_mount(const char *dev_name, struct path *path, data_page); } -long do_mount(const char *dev_name, const char __user *dir_name, +int do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; @@ -3905,6 +3958,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a refcount_set(&new_ns->ns.count, 1); refcount_set(&new_ns->passive, 1); new_ns->mounts = RB_ROOT; + INIT_LIST_HEAD(&new_ns->mnt_ns_list); RB_CLEAR_NODE(&new_ns->mnt_ns_tree_node); init_waitqueue_head(&new_ns->poll); new_ns->user_ns = get_user_ns(user_ns); @@ -3984,7 +4038,6 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(skip_mnt_tree(p), old); } - mnt_ns_tree_add(new_ns); namespace_unlock(); if (rootmnt) @@ -3992,6 +4045,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, if (pwdmnt) mntput(pwdmnt); + mnt_ns_tree_add(new_ns); return new_ns; } @@ -5038,6 +5092,10 @@ static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq) if (sb->s_op->show_options) { size_t start = seq->count; + err = security_sb_show_options(seq, sb); + if (err) + return err; + err = sb->s_op->show_options(seq, mnt->mnt_root); if (err) return err; @@ -5525,9 +5583,9 @@ static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id, if (!last_mnt_id) { if (reverse) - first = node_to_mount(rb_last(&ns->mounts)); + first = node_to_mount(ns->mnt_last_node); else - first = node_to_mount(rb_first(&ns->mounts)); + first = node_to_mount(ns->mnt_first_node); } else { if (reverse) first = mnt_find_id_at_reverse(ns, last_mnt_id - 1); @@ -5927,7 +5985,7 @@ const struct proc_ns_operations mntns_operations = { }; #ifdef CONFIG_SYSCTL -static struct ctl_table fs_namespace_sysctls[] = { +static const struct ctl_table fs_namespace_sysctls[] = { { .procname = "mount-max", .data = &sysctl_mount_max, diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index d08b0bfb6756..b43188d64bd8 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -13,8 +13,11 @@ netfs-y := \ read_collect.o \ read_pgpriv2.o \ read_retry.o \ + read_single.o \ + rolling_buffer.o \ write_collect.o \ - write_issue.o + write_issue.o \ + write_retry.o netfs-$(CONFIG_NETFS_STATS) += stats.o diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7ac34550c403..f761d44b3436 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -63,37 +63,6 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx)); } -/* - * Decant the list of folios to read into a rolling buffer. - */ -static size_t netfs_load_buffer_from_ra(struct netfs_io_request *rreq, - struct folio_queue *folioq, - struct folio_batch *put_batch) -{ - unsigned int order, nr; - size_t size = 0; - - nr = __readahead_batch(rreq->ractl, (struct page **)folioq->vec.folios, - ARRAY_SIZE(folioq->vec.folios)); - folioq->vec.nr = nr; - for (int i = 0; i < nr; i++) { - struct folio *folio = folioq_folio(folioq, i); - - trace_netfs_folio(folio, netfs_folio_trace_read); - order = folio_order(folio); - folioq->orders[i] = order; - size += PAGE_SIZE << order; - - if (!folio_batch_add(put_batch, folio)) - folio_batch_release(put_batch); - } - - for (int i = nr; i < folioq_nr_slots(folioq); i++) - folioq_clear(folioq, i); - - return size; -} - /* * netfs_prepare_read_iterator - Prepare the subreq iterator for I/O * @subreq: The subrequest to be set up @@ -128,19 +97,12 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) folio_batch_init(&put_batch); while (rreq->submitted < subreq->start + rsize) { - struct folio_queue *tail = rreq->buffer_tail, *new; - size_t added; + ssize_t added; - new = kmalloc(sizeof(*new), GFP_NOFS); - if (!new) - return -ENOMEM; - netfs_stat(&netfs_n_folioq); - folioq_init(new); - new->prev = tail; - tail->next = new; - rreq->buffer_tail = new; - added = netfs_load_buffer_from_ra(rreq, new, &put_batch); - rreq->iter.count += added; + added = rolling_buffer_load_from_ra(&rreq->buffer, rreq->ractl, + &put_batch); + if (added < 0) + return added; rreq->submitted += added; } folio_batch_release(&put_batch); @@ -148,7 +110,7 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) subreq->len = rsize; if (unlikely(rreq->io_streams[0].sreq_max_segs)) { - size_t limit = netfs_limit_iter(&rreq->iter, 0, rsize, + size_t limit = netfs_limit_iter(&rreq->buffer.iter, 0, rsize, rreq->io_streams[0].sreq_max_segs); if (limit < rsize) { @@ -157,20 +119,10 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) } } - subreq->io_iter = rreq->iter; - - if (iov_iter_is_folioq(&subreq->io_iter)) { - if (subreq->io_iter.folioq_slot >= folioq_nr_slots(subreq->io_iter.folioq)) { - subreq->io_iter.folioq = subreq->io_iter.folioq->next; - subreq->io_iter.folioq_slot = 0; - } - subreq->curr_folioq = (struct folio_queue *)subreq->io_iter.folioq; - subreq->curr_folioq_slot = subreq->io_iter.folioq_slot; - subreq->curr_folio_order = subreq->curr_folioq->orders[subreq->curr_folioq_slot]; - } + subreq->io_iter = rreq->buffer.iter; iov_iter_truncate(&subreq->io_iter, subreq->len); - iov_iter_advance(&rreq->iter, subreq->len); + rolling_buffer_advance(&rreq->buffer, subreq->len); return subreq->len; } @@ -179,25 +131,14 @@ static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_request *rr loff_t i_size) { struct netfs_cache_resources *cres = &rreq->cache_resources; + enum netfs_io_source source; if (!cres->ops) return NETFS_DOWNLOAD_FROM_SERVER; - return cres->ops->prepare_read(subreq, i_size); -} + source = cres->ops->prepare_read(subreq, i_size); + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + return source; -static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_io_subrequest *subreq = priv; - - if (transferred_or_error < 0) { - netfs_read_subreq_terminated(subreq, transferred_or_error, was_async); - return; - } - - if (transferred_or_error > 0) - subreq->transferred += transferred_or_error; - netfs_read_subreq_terminated(subreq, 0, was_async); } /* @@ -214,6 +155,47 @@ static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq, netfs_cache_read_terminated, subreq); } +static void netfs_issue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct netfs_io_stream *stream = &rreq->io_streams[0]; + + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + + /* We add to the end of the list whilst the collector may be walking + * the list. The collector only goes nextwards and uses the lock to + * remove entries off of the front. + */ + spin_lock(&rreq->lock); + list_add_tail(&subreq->rreq_link, &stream->subrequests); + if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { + stream->front = subreq; + if (!stream->active) { + stream->collected_to = stream->front->start; + /* Store list pointers before active flag */ + smp_store_release(&stream->active, true); + } + } + + spin_unlock(&rreq->lock); + + switch (subreq->source) { + case NETFS_DOWNLOAD_FROM_SERVER: + rreq->netfs_ops->issue_read(subreq); + break; + case NETFS_READ_FROM_CACHE: + netfs_read_cache_to_pagecache(rreq, subreq); + break; + default: + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + subreq->error = 0; + iov_iter_zero(subreq->len, &subreq->io_iter); + subreq->transferred = subreq->len; + netfs_read_subreq_terminated(subreq); + break; + } +} + /* * Perform a read to the pagecache from a series of sources of different types, * slicing up the region to be read according to available cache blocks and @@ -226,11 +208,9 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) ssize_t size = rreq->len; int ret = 0; - atomic_inc(&rreq->nr_outstanding); - do { struct netfs_io_subrequest *subreq; - enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER; + enum netfs_io_source source = NETFS_SOURCE_UNKNOWN; ssize_t slice; subreq = netfs_alloc_subrequest(rreq); @@ -242,20 +222,14 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) subreq->start = start; subreq->len = size; - atomic_inc(&rreq->nr_outstanding); - spin_lock_bh(&rreq->lock); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - subreq->prev_donated = rreq->prev_donated; - rreq->prev_donated = 0; - trace_netfs_sreq(subreq, netfs_sreq_trace_added); - spin_unlock_bh(&rreq->lock); - source = netfs_cache_prepare_read(rreq, subreq, rreq->i_size); subreq->source = source; if (source == NETFS_DOWNLOAD_FROM_SERVER) { unsigned long long zp = umin(ictx->zero_point, rreq->i_size); size_t len = subreq->len; + if (unlikely(rreq->origin == NETFS_READ_SINGLE)) + zp = rreq->i_size; if (subreq->start >= zp) { subreq->source = source = NETFS_FILL_WITH_ZEROES; goto fill_with_zeroes; @@ -276,24 +250,17 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); if (ret < 0) { - atomic_dec(&rreq->nr_outstanding); + subreq->error = ret; + /* Not queued - release both refs. */ + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_cancel); netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); break; } trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); } - - slice = netfs_prepare_read_iterator(subreq); - if (slice < 0) { - atomic_dec(&rreq->nr_outstanding); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); - ret = slice; - break; - } - - rreq->netfs_ops->issue_read(subreq); - goto done; + goto issue; } fill_with_zeroes: @@ -301,82 +268,50 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) subreq->source = NETFS_FILL_WITH_ZEROES; trace_netfs_sreq(subreq, netfs_sreq_trace_submit); netfs_stat(&netfs_n_rh_zero); - slice = netfs_prepare_read_iterator(subreq); - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - netfs_read_subreq_terminated(subreq, 0, false); - goto done; + goto issue; } if (source == NETFS_READ_FROM_CACHE) { trace_netfs_sreq(subreq, netfs_sreq_trace_submit); - slice = netfs_prepare_read_iterator(subreq); - netfs_read_cache_to_pagecache(rreq, subreq); - goto done; + goto issue; } pr_err("Unexpected read source %u\n", source); WARN_ON_ONCE(1); break; - done: + issue: + slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) { + ret = slice; + subreq->error = ret; + trace_netfs_sreq(subreq, netfs_sreq_trace_cancel); + /* Not queued - release both refs. */ + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + break; + } size -= slice; start += slice; + if (size <= 0) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + } + + netfs_issue_read(rreq, subreq); cond_resched(); } while (size > 0); - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_terminated(rreq, false); + if (unlikely(size > 0)) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + netfs_wake_read_collector(rreq); + } /* Defer error return as we may need to wait for outstanding I/O. */ cmpxchg(&rreq->error, 0, ret); } -/* - * Wait for the read operation to complete, successfully or otherwise. - */ -static int netfs_wait_for_read(struct netfs_io_request *rreq) -{ - int ret; - - trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); - wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); - ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); - ret = -EIO; - } - - return ret; -} - -/* - * Set up the initial folioq of buffer folios in the rolling buffer and set the - * iterator to refer to it. - */ -static int netfs_prime_buffer(struct netfs_io_request *rreq) -{ - struct folio_queue *folioq; - struct folio_batch put_batch; - size_t added; - - folioq = kmalloc(sizeof(*folioq), GFP_KERNEL); - if (!folioq) - return -ENOMEM; - netfs_stat(&netfs_n_folioq); - folioq_init(folioq); - rreq->buffer = folioq; - rreq->buffer_tail = folioq; - rreq->submitted = rreq->start; - iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, 0); - - folio_batch_init(&put_batch); - added = netfs_load_buffer_from_ra(rreq, folioq, &put_batch); - folio_batch_release(&put_batch); - rreq->iter.count += added; - rreq->submitted += added; - return 0; -} - /** * netfs_readahead - Helper to manage a read request * @ractl: The description of the readahead request @@ -405,6 +340,8 @@ void netfs_readahead(struct readahead_control *ractl) if (IS_ERR(rreq)) return; + __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags); + ret = netfs_begin_cache_read(rreq, ictx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) goto cleanup_free; @@ -416,7 +353,8 @@ void netfs_readahead(struct readahead_control *ractl) netfs_rreq_expand(rreq, ractl); rreq->ractl = ractl; - if (netfs_prime_buffer(rreq) < 0) + rreq->submitted = rreq->start; + if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST) < 0) goto cleanup_free; netfs_read_to_pagecache(rreq); @@ -432,23 +370,18 @@ EXPORT_SYMBOL(netfs_readahead); /* * Create a rolling buffer with a single occupying folio. */ -static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct folio *folio) +static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct folio *folio, + unsigned int rollbuf_flags) { - struct folio_queue *folioq; + ssize_t added; - folioq = kmalloc(sizeof(*folioq), GFP_KERNEL); - if (!folioq) + if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST) < 0) return -ENOMEM; - netfs_stat(&netfs_n_folioq); - folioq_init(folioq); - folioq_append(folioq, folio); - BUG_ON(folioq_folio(folioq, 0) != folio); - BUG_ON(folioq_folio_order(folioq, 0) != folio_order(folio)); - rreq->buffer = folioq; - rreq->buffer_tail = folioq; - rreq->submitted = rreq->start + rreq->len; - iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, rreq->len); + added = rolling_buffer_append(&rreq->buffer, folio, rollbuf_flags); + if (added < 0) + return added; + rreq->submitted = rreq->start + added; rreq->ractl = (struct readahead_control *)1UL; return 0; } @@ -516,7 +449,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) } if (to < flen) bvec_set_folio(&bvec[i++], folio, flen - to, to); - iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len); + iov_iter_bvec(&rreq->buffer.iter, ITER_DEST, bvec, i, rreq->len); rreq->submitted = rreq->start + flen; netfs_read_to_pagecache(rreq); @@ -525,7 +458,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) folio_put(sink); ret = netfs_wait_for_read(rreq); - if (ret == 0) { + if (ret >= 0) { flush_dcache_folio(folio); folio_mark_uptodate(folio); } @@ -584,7 +517,7 @@ int netfs_read_folio(struct file *file, struct folio *folio) trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); /* Set up the output buffer */ - ret = netfs_create_singular_buffer(rreq, folio); + ret = netfs_create_singular_buffer(rreq, folio, 0); if (ret < 0) goto discard; @@ -741,7 +674,7 @@ retry: trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); /* Set up the output buffer */ - ret = netfs_create_singular_buffer(rreq, folio); + ret = netfs_create_singular_buffer(rreq, folio, 0); if (ret < 0) goto error_put; @@ -806,15 +739,14 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, trace_netfs_read(rreq, start, flen, netfs_read_trace_prefetch_for_write); /* Set up the output buffer */ - ret = netfs_create_singular_buffer(rreq, folio); + ret = netfs_create_singular_buffer(rreq, folio, NETFS_ROLLBUF_PAGECACHE_MARK); if (ret < 0) goto error_put; - folioq_mark2(rreq->buffer, 0); netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, false, netfs_rreq_trace_put_return); - return ret; + return ret < 0 ? ret : 0; error_put: netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c index b1a66a6e6bc2..0bf3c2f5a710 100644 --- a/fs/netfs/direct_read.c +++ b/fs/netfs/direct_read.c @@ -25,7 +25,7 @@ static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) subreq->len = rsize; if (unlikely(rreq->io_streams[0].sreq_max_segs)) { - size_t limit = netfs_limit_iter(&rreq->iter, 0, rsize, + size_t limit = netfs_limit_iter(&rreq->buffer.iter, 0, rsize, rreq->io_streams[0].sreq_max_segs); if (limit < rsize) { @@ -36,9 +36,9 @@ static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); - subreq->io_iter = rreq->iter; + subreq->io_iter = rreq->buffer.iter; iov_iter_truncate(&subreq->io_iter, subreq->len); - iov_iter_advance(&rreq->iter, subreq->len); + iov_iter_advance(&rreq->buffer.iter, subreq->len); } /* @@ -47,12 +47,11 @@ static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) */ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) { + struct netfs_io_stream *stream = &rreq->io_streams[0]; unsigned long long start = rreq->start; ssize_t size = rreq->len; int ret = 0; - atomic_set(&rreq->nr_outstanding, 1); - do { struct netfs_io_subrequest *subreq; ssize_t slice; @@ -67,19 +66,25 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) subreq->start = start; subreq->len = size; - atomic_inc(&rreq->nr_outstanding); - spin_lock_bh(&rreq->lock); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - subreq->prev_donated = rreq->prev_donated; - rreq->prev_donated = 0; + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + + spin_lock(&rreq->lock); + list_add_tail(&subreq->rreq_link, &stream->subrequests); + if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { + stream->front = subreq; + if (!stream->active) { + stream->collected_to = stream->front->start; + /* Store list pointers before active flag */ + smp_store_release(&stream->active, true); + } + } trace_netfs_sreq(subreq, netfs_sreq_trace_added); - spin_unlock_bh(&rreq->lock); + spin_unlock(&rreq->lock); netfs_stat(&netfs_n_rh_download); if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); if (ret < 0) { - atomic_dec(&rreq->nr_outstanding); netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); break; } @@ -87,20 +92,32 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) netfs_prepare_dio_read_iterator(subreq); slice = subreq->len; - rreq->netfs_ops->issue_read(subreq); - size -= slice; start += slice; rreq->submitted += slice; + if (size <= 0) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + } + rreq->netfs_ops->issue_read(subreq); + + if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) + netfs_wait_for_pause(rreq); + if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) + break; if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) && test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags)) break; cond_resched(); } while (size > 0); - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_terminated(rreq, false); + if (unlikely(size > 0)) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + netfs_wake_read_collector(rreq); + } + return ret; } @@ -133,21 +150,10 @@ static int netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync) goto out; } - if (sync) { - trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); - wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, - TASK_UNINTERRUPTIBLE); - - ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len && - rreq->origin != NETFS_DIO_READ) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); - ret = -EIO; - } - } else { + if (sync) + ret = netfs_wait_for_read(rreq); + else ret = -EIOCBQUEUED; - } - out: _leave(" = %d", ret); return ret; @@ -199,15 +205,15 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i * the request. */ if (user_backed_iter(iter)) { - ret = netfs_extract_user_iter(iter, rreq->len, &rreq->iter, 0); + ret = netfs_extract_user_iter(iter, rreq->len, &rreq->buffer.iter, 0); if (ret < 0) goto out; - rreq->direct_bv = (struct bio_vec *)rreq->iter.bvec; + rreq->direct_bv = (struct bio_vec *)rreq->buffer.iter.bvec; rreq->direct_bv_count = ret; rreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); - rreq->len = iov_iter_count(&rreq->iter); + rreq->len = iov_iter_count(&rreq->buffer.iter); } else { - rreq->iter = *iter; + rreq->buffer.iter = *iter; rreq->len = orig_count; rreq->direct_bv_unpin = false; iov_iter_advance(iter, orig_count); @@ -215,8 +221,10 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i // TODO: Set up bounce buffer if needed - if (!sync) + if (!sync) { rreq->iocb = iocb; + __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags); + } ret = netfs_unbuffered_read(rreq, sync); if (ret < 0) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 88f2adfab75e..42ce53cc216e 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -67,20 +67,23 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * * allocate a sufficiently large bvec array and may shorten the * request. */ - if (async || user_backed_iter(iter)) { - n = netfs_extract_user_iter(iter, len, &wreq->iter, 0); + if (user_backed_iter(iter)) { + n = netfs_extract_user_iter(iter, len, &wreq->buffer.iter, 0); if (n < 0) { ret = n; goto out; } - wreq->direct_bv = (struct bio_vec *)wreq->iter.bvec; + wreq->direct_bv = (struct bio_vec *)wreq->buffer.iter.bvec; wreq->direct_bv_count = n; wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); } else { - wreq->iter = *iter; + /* If this is a kernel-generated async DIO request, + * assume that any resources the iterator points to + * (eg. a bio_vec array) will persist till the end of + * the op. + */ + wreq->buffer.iter = *iter; } - - wreq->io_iter = wreq->iter; } __set_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags); @@ -92,7 +95,7 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * __set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags); if (async) wreq->iocb = iocb; - wreq->len = iov_iter_count(&wreq->io_iter); + wreq->len = iov_iter_count(&wreq->buffer.iter); wreq->cleanup = netfs_cleanup_dio_write; ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len); if (ret < 0) { @@ -104,7 +107,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip); wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); - smp_rmb(); /* Read error/transferred after RIP flag */ ret = wreq->error; if (ret == 0) { ret = wreq->transferred; diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index c562aec3b483..eb76f98c894b 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -23,6 +23,7 @@ /* * buffered_read.c */ +void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool was_async); int netfs_prefetch_for_write(struct file *file, struct folio *folio, size_t offset, size_t len); @@ -58,11 +59,8 @@ static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {} /* * misc.c */ -struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq); -int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, - bool needs_put); -struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq); -void netfs_clear_buffer(struct netfs_io_request *rreq); +struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq, + enum netfs_folioq_trace trace); void netfs_reset_iter(struct netfs_io_subrequest *subreq); /* @@ -84,20 +82,27 @@ static inline void netfs_see_request(struct netfs_io_request *rreq, trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), what); } +static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what) +{ + trace_netfs_sreq_ref(subreq->rreq->debug_id, subreq->debug_index, + refcount_read(&subreq->ref), what); +} + /* * read_collect.c */ -void netfs_read_termination_worker(struct work_struct *work); -void netfs_rreq_terminated(struct netfs_io_request *rreq, bool was_async); +void netfs_read_collection_worker(struct work_struct *work); +void netfs_wake_read_collector(struct netfs_io_request *rreq); +void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool was_async); +ssize_t netfs_wait_for_read(struct netfs_io_request *rreq); +void netfs_wait_for_pause(struct netfs_io_request *rreq); /* * read_pgpriv2.c */ -void netfs_pgpriv2_mark_copy_to_cache(struct netfs_io_subrequest *subreq, - struct netfs_io_request *rreq, - struct folio_queue *folioq, - int slot); -void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq); +void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio); +void netfs_pgpriv2_end_copy_to_cache(struct netfs_io_request *rreq); bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq); /* @@ -113,6 +118,7 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq); extern atomic_t netfs_n_rh_dio_read; extern atomic_t netfs_n_rh_readahead; extern atomic_t netfs_n_rh_read_folio; +extern atomic_t netfs_n_rh_read_single; extern atomic_t netfs_n_rh_rreq; extern atomic_t netfs_n_rh_sreq; extern atomic_t netfs_n_rh_download; @@ -181,9 +187,9 @@ void netfs_reissue_write(struct netfs_io_stream *stream, struct iov_iter *source); void netfs_issue_write(struct netfs_io_request *wreq, struct netfs_io_stream *stream); -int netfs_advance_write(struct netfs_io_request *wreq, - struct netfs_io_stream *stream, - loff_t start, size_t len, bool to_eof); +size_t netfs_advance_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start, size_t len, bool to_eof); struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len); int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc, struct folio *folio, size_t copied, bool to_page_end, @@ -192,6 +198,11 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr struct folio *writethrough_cache); int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len); +/* + * write_retry.c + */ +void netfs_retry_writes(struct netfs_io_request *wreq); + /* * Miscellaneous functions. */ diff --git a/fs/netfs/main.c b/fs/netfs/main.c index 6c7be1377ee0..4e3e62040831 100644 --- a/fs/netfs/main.c +++ b/fs/netfs/main.c @@ -37,9 +37,11 @@ static const char *netfs_origins[nr__netfs_io_origin] = { [NETFS_READAHEAD] = "RA", [NETFS_READPAGE] = "RP", [NETFS_READ_GAPS] = "RG", + [NETFS_READ_SINGLE] = "R1", [NETFS_READ_FOR_WRITE] = "RW", [NETFS_DIO_READ] = "DR", [NETFS_WRITEBACK] = "WB", + [NETFS_WRITEBACK_SINGLE] = "W1", [NETFS_WRITETHROUGH] = "WT", [NETFS_UNBUFFERED_WRITE] = "UW", [NETFS_DIO_WRITE] = "DW", @@ -69,7 +71,7 @@ static int netfs_requests_seq_show(struct seq_file *m, void *v) refcount_read(&rreq->ref), rreq->flags, rreq->error, - atomic_read(&rreq->nr_outstanding), + 0, rreq->start, rreq->submitted, rreq->len); seq_putc(m, '\n'); return 0; @@ -116,7 +118,7 @@ static int __init netfs_init(void) goto error_reqpool; netfs_subrequest_slab = kmem_cache_create("netfs_subrequest", - sizeof(struct netfs_io_subrequest), 0, + sizeof(struct netfs_io_subrequest) + 16, 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!netfs_subrequest_slab) diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 78fe5796b2b2..7099aa07737a 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -8,113 +8,101 @@ #include #include "internal.h" -/* - * Make sure there's space in the rolling queue. +/** + * netfs_alloc_folioq_buffer - Allocate buffer space into a folio queue + * @mapping: Address space to set on the folio (or NULL). + * @_buffer: Pointer to the folio queue to add to (may point to a NULL; updated). + * @_cur_size: Current size of the buffer (updated). + * @size: Target size of the buffer. + * @gfp: The allocation constraints. */ -struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq) +int netfs_alloc_folioq_buffer(struct address_space *mapping, + struct folio_queue **_buffer, + size_t *_cur_size, ssize_t size, gfp_t gfp) { - struct folio_queue *tail = rreq->buffer_tail, *prev; - unsigned int prev_nr_slots = 0; + struct folio_queue *tail = *_buffer, *p; - if (WARN_ON_ONCE(!rreq->buffer && tail) || - WARN_ON_ONCE(rreq->buffer && !tail)) - return ERR_PTR(-EIO); + size = round_up(size, PAGE_SIZE); + if (*_cur_size >= size) + return 0; - prev = tail; - if (prev) { - if (!folioq_full(tail)) - return tail; - prev_nr_slots = folioq_nr_slots(tail); - } + if (tail) + while (tail->next) + tail = tail->next; - tail = kmalloc(sizeof(*tail), GFP_NOFS); - if (!tail) - return ERR_PTR(-ENOMEM); - netfs_stat(&netfs_n_folioq); - folioq_init(tail); - tail->prev = prev; - if (prev) - /* [!] NOTE: After we set prev->next, the consumer is entirely - * at liberty to delete prev. - */ - WRITE_ONCE(prev->next, tail); + do { + struct folio *folio; + int order = 0, slot; - rreq->buffer_tail = tail; - if (!rreq->buffer) { - rreq->buffer = tail; - iov_iter_folio_queue(&rreq->io_iter, ITER_SOURCE, tail, 0, 0, 0); - } else { - /* Make sure we don't leave the master iterator pointing to a - * block that might get immediately consumed. - */ - if (rreq->io_iter.folioq == prev && - rreq->io_iter.folioq_slot == prev_nr_slots) { - rreq->io_iter.folioq = tail; - rreq->io_iter.folioq_slot = 0; + if (!tail || folioq_full(tail)) { + p = netfs_folioq_alloc(0, GFP_NOFS, netfs_trace_folioq_alloc_buffer); + if (!p) + return -ENOMEM; + if (tail) { + tail->next = p; + p->prev = tail; + } else { + *_buffer = p; + } + tail = p; } - } - rreq->buffer_tail_slot = 0; - return tail; -} -/* - * Append a folio to the rolling queue. - */ -int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, - bool needs_put) -{ - struct folio_queue *tail; - unsigned int slot, order = folio_order(folio); + if (size - *_cur_size > PAGE_SIZE) + order = umin(ilog2(size - *_cur_size) - PAGE_SHIFT, + MAX_PAGECACHE_ORDER); - tail = netfs_buffer_make_space(rreq); - if (IS_ERR(tail)) - return PTR_ERR(tail); + folio = folio_alloc(gfp, order); + if (!folio && order > 0) + folio = folio_alloc(gfp, 0); + if (!folio) + return -ENOMEM; - rreq->io_iter.count += PAGE_SIZE << order; + folio->mapping = mapping; + folio->index = *_cur_size / PAGE_SIZE; + trace_netfs_folio(folio, netfs_folio_trace_alloc_buffer); + slot = folioq_append_mark(tail, folio); + *_cur_size += folioq_folio_size(tail, slot); + } while (*_cur_size < size); - slot = folioq_append(tail, folio); - /* Store the counter after setting the slot. */ - smp_store_release(&rreq->buffer_tail_slot, slot); return 0; } +EXPORT_SYMBOL(netfs_alloc_folioq_buffer); -/* - * Delete the head of a rolling queue. +/** + * netfs_free_folioq_buffer - Free a folio queue. + * @fq: The start of the folio queue to free + * + * Free up a chain of folio_queues and, if marked, the marked folios they point + * to. */ -struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq) +void netfs_free_folioq_buffer(struct folio_queue *fq) { - struct folio_queue *head = wreq->buffer, *next = head->next; + struct folio_queue *next; + struct folio_batch fbatch; - if (next) - next->prev = NULL; - netfs_stat_d(&netfs_n_folioq); - kfree(head); - wreq->buffer = next; - return next; -} + folio_batch_init(&fbatch); -/* - * Clear out a rolling queue. - */ -void netfs_clear_buffer(struct netfs_io_request *rreq) -{ - struct folio_queue *p; + for (; fq; fq = next) { + for (int slot = 0; slot < folioq_count(fq); slot++) { + struct folio *folio = folioq_folio(fq, slot); - while ((p = rreq->buffer)) { - rreq->buffer = p->next; - for (int slot = 0; slot < folioq_count(p); slot++) { - struct folio *folio = folioq_folio(p, slot); - if (!folio) + if (!folio || + !folioq_is_marked(fq, slot)) continue; - if (folioq_is_marked(p, slot)) { - trace_netfs_folio(folio, netfs_folio_trace_put); - folio_put(folio); - } + + trace_netfs_folio(folio, netfs_folio_trace_put); + if (folio_batch_add(&fbatch, folio)) + folio_batch_release(&fbatch); } + netfs_stat_d(&netfs_n_folioq); - kfree(p); + next = fq->next; + kfree(fq); } + + folio_batch_release(&fbatch); } +EXPORT_SYMBOL(netfs_free_folioq_buffer); /* * Reset the subrequest iterator to refer just to the region remaining to be diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index 31e388ec6e48..dc6b41ef18b0 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -48,17 +48,20 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, spin_lock_init(&rreq->lock); INIT_LIST_HEAD(&rreq->io_streams[0].subrequests); INIT_LIST_HEAD(&rreq->io_streams[1].subrequests); - INIT_LIST_HEAD(&rreq->subrequests); + init_waitqueue_head(&rreq->waitq); refcount_set(&rreq->ref, 1); if (origin == NETFS_READAHEAD || origin == NETFS_READPAGE || origin == NETFS_READ_GAPS || + origin == NETFS_READ_SINGLE || origin == NETFS_READ_FOR_WRITE || - origin == NETFS_DIO_READ) - INIT_WORK(&rreq->work, netfs_read_termination_worker); - else + origin == NETFS_DIO_READ) { + INIT_WORK(&rreq->work, netfs_read_collection_worker); + rreq->io_streams[0].avail = true; + } else { INIT_WORK(&rreq->work, netfs_write_collection_worker); + } __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); if (file && file->f_flags & O_NONBLOCK) @@ -92,14 +95,6 @@ void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async) struct netfs_io_stream *stream; int s; - while (!list_empty(&rreq->subrequests)) { - subreq = list_first_entry(&rreq->subrequests, - struct netfs_io_subrequest, rreq_link); - list_del(&subreq->rreq_link); - netfs_put_subrequest(subreq, was_async, - netfs_sreq_trace_put_clear); - } - for (s = 0; s < ARRAY_SIZE(rreq->io_streams); s++) { stream = &rreq->io_streams[s]; while (!list_empty(&stream->subrequests)) { @@ -143,7 +138,7 @@ static void netfs_free_request(struct work_struct *work) } kvfree(rreq->direct_bv); } - netfs_clear_buffer(rreq); + rolling_buffer_clear(&rreq->buffer); if (atomic_dec_and_test(&ictx->io_count)) wake_up_var(&ictx->io_count); diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3cbb289535a8..f65affa5a9e4 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -14,6 +14,14 @@ #include #include "internal.h" +/* Notes made in the collector */ +#define HIT_PENDING 0x01 /* A front op was still pending */ +#define MADE_PROGRESS 0x04 /* Made progress cleaning up a stream or the folio set */ +#define BUFFERED 0x08 /* The pagecache needs cleaning up */ +#define NEED_RETRY 0x10 /* A front op requests retrying */ +#define COPY_TO_CACHE 0x40 /* Need to copy subrequest to cache */ +#define ABANDON_SREQ 0x80 /* Need to abandon untransferred part of subrequest */ + /* * Clear the unread part of an I/O request. */ @@ -31,14 +39,18 @@ static void netfs_clear_unread(struct netfs_io_subrequest *subreq) * cache the folio, we set the group to NETFS_FOLIO_COPY_TO_CACHE, mark it * dirty and let writeback handle it. */ -static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, - struct netfs_io_request *rreq, +static void netfs_unlock_read_folio(struct netfs_io_request *rreq, struct folio_queue *folioq, int slot) { struct netfs_folio *finfo; struct folio *folio = folioq_folio(folioq, slot); + if (unlikely(folio_pos(folio) < rreq->abandon_to)) { + trace_netfs_folio(folio, netfs_folio_trace_abandon); + goto just_unlock; + } + flush_dcache_folio(folio); folio_mark_uptodate(folio); @@ -53,7 +65,7 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, kfree(finfo); } - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) { if (!WARN_ON_ONCE(folio_get_private(folio) != NULL)) { trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); @@ -62,12 +74,15 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, } else { trace_netfs_folio(folio, netfs_folio_trace_read_done); } + + folioq_clear(folioq, slot); } else { // TODO: Use of PG_private_2 is deprecated. - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) - netfs_pgpriv2_mark_copy_to_cache(subreq, rreq, folioq, slot); + if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) + netfs_pgpriv2_copy_to_cache(rreq, folio); } +just_unlock: if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { if (folio->index == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { @@ -82,234 +97,244 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, } /* - * Unlock any folios that are now completely read. Returns true if the - * subrequest is removed from the list. + * Unlock any folios we've finished with. */ -static bool netfs_consume_read_data(struct netfs_io_subrequest *subreq, bool was_async) +static void netfs_read_unlock_folios(struct netfs_io_request *rreq, + unsigned int *notes) { - struct netfs_io_subrequest *prev, *next; - struct netfs_io_request *rreq = subreq->rreq; - struct folio_queue *folioq = subreq->curr_folioq; - size_t avail, prev_donated, next_donated, fsize, part, excess; - loff_t fpos, start; - loff_t fend; - int slot = subreq->curr_folioq_slot; + struct folio_queue *folioq = rreq->buffer.tail; + unsigned long long collected_to = rreq->collected_to; + unsigned int slot = rreq->buffer.first_tail_slot; - if (WARN(subreq->transferred > subreq->len, - "Subreq overread: R%x[%x] %zu > %zu", - rreq->debug_id, subreq->debug_index, - subreq->transferred, subreq->len)) - subreq->transferred = subreq->len; + if (rreq->cleaned_to >= rreq->collected_to) + return; -next_folio: - fsize = PAGE_SIZE << subreq->curr_folio_order; - fpos = round_down(subreq->start + subreq->consumed, fsize); - fend = fpos + fsize; + // TODO: Begin decryption - if (WARN_ON_ONCE(!folioq) || - WARN_ON_ONCE(!folioq_folio(folioq, slot)) || - WARN_ON_ONCE(folioq_folio(folioq, slot)->index != fpos / PAGE_SIZE)) { - pr_err("R=%08x[%x] s=%llx-%llx ctl=%zx/%zx/%zx sl=%u\n", - rreq->debug_id, subreq->debug_index, - subreq->start, subreq->start + subreq->transferred - 1, - subreq->consumed, subreq->transferred, subreq->len, - slot); - if (folioq) { - struct folio *folio = folioq_folio(folioq, slot); - - pr_err("folioq: orders=%02x%02x%02x%02x\n", - folioq->orders[0], folioq->orders[1], - folioq->orders[2], folioq->orders[3]); - if (folio) - pr_err("folio: %llx-%llx ix=%llx o=%u qo=%u\n", - fpos, fend - 1, folio_pos(folio), folio_order(folio), - folioq_folio_order(folioq, slot)); + if (slot >= folioq_nr_slots(folioq)) { + folioq = rolling_buffer_delete_spent(&rreq->buffer); + if (!folioq) { + rreq->front_folio_order = 0; + return; } + slot = 0; } -donation_changed: - /* Try to consume the current folio if we've hit or passed the end of - * it. There's a possibility that this subreq doesn't start at the - * beginning of the folio, in which case we need to donate to/from the - * preceding subreq. - * - * We also need to include any potential donation back from the - * following subreq. - */ - prev_donated = READ_ONCE(subreq->prev_donated); - next_donated = READ_ONCE(subreq->next_donated); - if (prev_donated || next_donated) { - spin_lock_bh(&rreq->lock); - prev_donated = subreq->prev_donated; - next_donated = subreq->next_donated; - subreq->start -= prev_donated; - subreq->len += prev_donated; - subreq->transferred += prev_donated; - prev_donated = subreq->prev_donated = 0; - if (subreq->transferred == subreq->len) { - subreq->len += next_donated; - subreq->transferred += next_donated; - next_donated = subreq->next_donated = 0; - } - trace_netfs_sreq(subreq, netfs_sreq_trace_add_donations); - spin_unlock_bh(&rreq->lock); - } + for (;;) { + struct folio *folio; + unsigned long long fpos, fend; + unsigned int order; + size_t fsize; - avail = subreq->transferred; - if (avail == subreq->len) - avail += next_donated; - start = subreq->start; - if (subreq->consumed == 0) { - start -= prev_donated; - avail += prev_donated; - } else { - start += subreq->consumed; - avail -= subreq->consumed; - } - part = umin(avail, fsize); + if (*notes & COPY_TO_CACHE) + set_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); - trace_netfs_progress(subreq, start, avail, part); + folio = folioq_folio(folioq, slot); + if (WARN_ONCE(!folio_test_locked(folio), + "R=%08x: folio %lx is not locked\n", + rreq->debug_id, folio->index)) + trace_netfs_folio(folio, netfs_folio_trace_not_locked); - if (start + avail >= fend) { - if (fpos == start) { - /* Flush, unlock and mark for caching any folio we've just read. */ - subreq->consumed = fend - subreq->start; - netfs_unlock_read_folio(subreq, rreq, folioq, slot); - folioq_mark2(folioq, slot); - if (subreq->consumed >= subreq->len) - goto remove_subreq; - } else if (fpos < start) { - excess = fend - subreq->start; + order = folioq_folio_order(folioq, slot); + rreq->front_folio_order = order; + fsize = PAGE_SIZE << order; + fpos = folio_pos(folio); + fend = umin(fpos + fsize, rreq->i_size); - spin_lock_bh(&rreq->lock); - /* If we complete first on a folio split with the - * preceding subreq, donate to that subreq - otherwise - * we get the responsibility. - */ - if (subreq->prev_donated != prev_donated) { - spin_unlock_bh(&rreq->lock); - goto donation_changed; - } + trace_netfs_collect_folio(rreq, folio, fend, collected_to); - if (list_is_first(&subreq->rreq_link, &rreq->subrequests)) { - spin_unlock_bh(&rreq->lock); - pr_err("Can't donate prior to front\n"); - goto bad; - } + /* Unlock any folio we've transferred all of. */ + if (collected_to < fend) + break; - prev = list_prev_entry(subreq, rreq_link); - WRITE_ONCE(prev->next_donated, prev->next_donated + excess); - subreq->start += excess; - subreq->len -= excess; - subreq->transferred -= excess; - trace_netfs_donate(rreq, subreq, prev, excess, - netfs_trace_donate_tail_to_prev); - trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_prev); + netfs_unlock_read_folio(rreq, folioq, slot); + WRITE_ONCE(rreq->cleaned_to, fpos + fsize); + *notes |= MADE_PROGRESS; - if (subreq->consumed >= subreq->len) - goto remove_subreq_locked; - spin_unlock_bh(&rreq->lock); - } else { - pr_err("fpos > start\n"); - goto bad; - } + clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); - /* Advance the rolling buffer to the next folio. */ + /* Clean up the head folioq. If we clear an entire folioq, then + * we can get rid of it provided it's not also the tail folioq + * being filled by the issuer. + */ + folioq_clear(folioq, slot); slot++; if (slot >= folioq_nr_slots(folioq)) { + folioq = rolling_buffer_delete_spent(&rreq->buffer); + if (!folioq) + goto done; slot = 0; - folioq = folioq->next; - subreq->curr_folioq = folioq; + trace_netfs_folioq(folioq, netfs_trace_folioq_read_progress); } - subreq->curr_folioq_slot = slot; - if (folioq && folioq_folio(folioq, slot)) - subreq->curr_folio_order = folioq->orders[slot]; - if (!was_async) - cond_resched(); - goto next_folio; + + if (fpos + fsize >= collected_to) + break; } - /* Deal with partial progress. */ - if (subreq->transferred < subreq->len) - return false; + rreq->buffer.tail = folioq; +done: + rreq->buffer.first_tail_slot = slot; +} - /* Donate the remaining downloaded data to one of the neighbouring - * subrequests. Note that we may race with them doing the same thing. +/* + * Collect and assess the results of various read subrequests. We may need to + * retry some of the results. + * + * Note that we have a sequence of subrequests, which may be drawing on + * different sources and may or may not be the same size or starting position + * and may not even correspond in boundary alignment. + */ +static void netfs_collect_read_results(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *front, *remove; + struct netfs_io_stream *stream = &rreq->io_streams[0]; + unsigned int notes; + + _enter("%llx-%llx", rreq->start, rreq->start + rreq->len); + trace_netfs_rreq(rreq, netfs_rreq_trace_collect); + trace_netfs_collect(rreq); + +reassess: + if (rreq->origin == NETFS_READAHEAD || + rreq->origin == NETFS_READPAGE || + rreq->origin == NETFS_READ_FOR_WRITE) + notes = BUFFERED; + else + notes = 0; + + /* Remove completed subrequests from the front of the stream and + * advance the completion point. We stop when we hit something that's + * in progress. The issuer thread may be adding stuff to the tail + * whilst we're doing this. */ - spin_lock_bh(&rreq->lock); + front = READ_ONCE(stream->front); + while (front) { + size_t transferred; - if (subreq->prev_donated != prev_donated || - subreq->next_donated != next_donated) { - spin_unlock_bh(&rreq->lock); - cond_resched(); - goto donation_changed; + trace_netfs_collect_sreq(rreq, front); + _debug("sreq [%x] %llx %zx/%zx", + front->debug_index, front->start, front->transferred, front->len); + + if (stream->collected_to < front->start) { + trace_netfs_collect_gap(rreq, stream, front->start, 'F'); + stream->collected_to = front->start; + } + + if (test_bit(NETFS_SREQ_IN_PROGRESS, &front->flags)) + notes |= HIT_PENDING; + smp_rmb(); /* Read counters after IN_PROGRESS flag. */ + transferred = READ_ONCE(front->transferred); + + /* If we can now collect the next folio, do so. We don't want + * to defer this as we have to decide whether we need to copy + * to the cache or not, and that may differ between adjacent + * subreqs. + */ + if (notes & BUFFERED) { + size_t fsize = PAGE_SIZE << rreq->front_folio_order; + + /* Clear the tail of a short read. */ + if (!(notes & HIT_PENDING) && + front->error == 0 && + transferred < front->len && + (test_bit(NETFS_SREQ_HIT_EOF, &front->flags) || + test_bit(NETFS_SREQ_CLEAR_TAIL, &front->flags))) { + netfs_clear_unread(front); + transferred = front->transferred = front->len; + trace_netfs_sreq(front, netfs_sreq_trace_clear); + } + + stream->collected_to = front->start + transferred; + rreq->collected_to = stream->collected_to; + + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &front->flags)) + notes |= COPY_TO_CACHE; + + if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { + rreq->abandon_to = front->start + front->len; + front->transferred = front->len; + transferred = front->len; + trace_netfs_rreq(rreq, netfs_rreq_trace_set_abandon); + } + if (front->start + transferred >= rreq->cleaned_to + fsize || + test_bit(NETFS_SREQ_HIT_EOF, &front->flags)) + netfs_read_unlock_folios(rreq, ¬es); + } else { + stream->collected_to = front->start + transferred; + rreq->collected_to = stream->collected_to; + } + + /* Stall if the front is still undergoing I/O. */ + if (notes & HIT_PENDING) + break; + + if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { + if (!stream->failed) { + stream->error = front->error; + rreq->error = front->error; + set_bit(NETFS_RREQ_FAILED, &rreq->flags); + stream->failed = true; + } + notes |= MADE_PROGRESS | ABANDON_SREQ; + } else if (test_bit(NETFS_SREQ_NEED_RETRY, &front->flags)) { + stream->need_retry = true; + notes |= NEED_RETRY | MADE_PROGRESS; + break; + } else { + if (!stream->failed) + stream->transferred = stream->collected_to - rreq->start; + notes |= MADE_PROGRESS; + } + + /* Remove if completely consumed. */ + stream->source = front->source; + spin_lock(&rreq->lock); + + remove = front; + trace_netfs_sreq(front, netfs_sreq_trace_discard); + list_del_init(&front->rreq_link); + front = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + stream->front = front; + spin_unlock(&rreq->lock); + netfs_put_subrequest(remove, false, + notes & ABANDON_SREQ ? + netfs_sreq_trace_put_abandon : + netfs_sreq_trace_put_done); } - /* Deal with the trickiest case: that this subreq is in the middle of a - * folio, not touching either edge, but finishes first. In such a - * case, we donate to the previous subreq, if there is one, so that the - * donation is only handled when that completes - and remove this - * subreq from the list. - * - * If the previous subreq finished first, we will have acquired their - * donation and should be able to unlock folios and/or donate nextwards. + trace_netfs_collect_stream(rreq, stream); + trace_netfs_collect_state(rreq, rreq->collected_to, notes); + + if (!(notes & BUFFERED)) + rreq->cleaned_to = rreq->collected_to; + + if (notes & NEED_RETRY) + goto need_retry; + if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) { + trace_netfs_rreq(rreq, netfs_rreq_trace_unpause); + clear_bit_unlock(NETFS_RREQ_PAUSE, &rreq->flags); + smp_mb__after_atomic(); /* Set PAUSE before task state */ + wake_up(&rreq->waitq); + } + + if (notes & MADE_PROGRESS) { + //cond_resched(); + goto reassess; + } + +out: + _leave(" = %x", notes); + return; + +need_retry: + /* Okay... We're going to have to retry parts of the stream. Note + * that any partially completed op will have had any wholly transferred + * folios removed from it. */ - if (!subreq->consumed && - !prev_donated && - !list_is_first(&subreq->rreq_link, &rreq->subrequests)) { - prev = list_prev_entry(subreq, rreq_link); - WRITE_ONCE(prev->next_donated, prev->next_donated + subreq->len); - subreq->start += subreq->len; - subreq->len = 0; - subreq->transferred = 0; - trace_netfs_donate(rreq, subreq, prev, subreq->len, - netfs_trace_donate_to_prev); - trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_prev); - goto remove_subreq_locked; - } - - /* If we can't donate down the chain, donate up the chain instead. */ - excess = subreq->len - subreq->consumed + next_donated; - - if (!subreq->consumed) - excess += prev_donated; - - if (list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - rreq->prev_donated = excess; - trace_netfs_donate(rreq, subreq, NULL, excess, - netfs_trace_donate_to_deferred_next); - } else { - next = list_next_entry(subreq, rreq_link); - WRITE_ONCE(next->prev_donated, excess); - trace_netfs_donate(rreq, subreq, next, excess, - netfs_trace_donate_to_next); - } - trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_next); - subreq->len = subreq->consumed; - subreq->transferred = subreq->consumed; - goto remove_subreq_locked; - -remove_subreq: - spin_lock_bh(&rreq->lock); -remove_subreq_locked: - subreq->consumed = subreq->len; - list_del(&subreq->rreq_link); - spin_unlock_bh(&rreq->lock); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_consumed); - return true; - -bad: - /* Errr... prev and next both donated to us, but insufficient to finish - * the folio. - */ - printk("R=%08x[%x] s=%llx-%llx %zx/%zx/%zx\n", - rreq->debug_id, subreq->debug_index, - subreq->start, subreq->start + subreq->transferred - 1, - subreq->consumed, subreq->transferred, subreq->len); - printk("folio: %llx-%llx\n", fpos, fend - 1); - printk("donated: prev=%zx next=%zx\n", prev_donated, next_donated); - printk("s=%llx av=%zx part=%zx\n", start, avail, part); - BUG(); + _debug("retry"); + netfs_retry_reads(rreq); + goto out; } /* @@ -318,12 +343,13 @@ bad: static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) { struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; unsigned int i; /* Collect unbuffered reads and direct reads, adding up the transfer * sizes until we find the first short or failed subrequest. */ - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { rreq->transferred += subreq->transferred; if (subreq->transferred < subreq->len || @@ -356,89 +382,135 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) } /* - * Assess the state of a read request and decide what to do next. + * Do processing after reading a monolithic single object. + */ +static void netfs_rreq_assess_single(struct netfs_io_request *rreq) +{ + struct netfs_io_stream *stream = &rreq->io_streams[0]; + + if (!rreq->error && stream->source == NETFS_DOWNLOAD_FROM_SERVER && + fscache_resources_valid(&rreq->cache_resources)) { + trace_netfs_rreq(rreq, netfs_rreq_trace_dirty); + netfs_single_mark_inode_dirty(rreq->inode); + } + + if (rreq->iocb) { + rreq->iocb->ki_pos += rreq->transferred; + if (rreq->iocb->ki_complete) + rreq->iocb->ki_complete( + rreq->iocb, rreq->error ? rreq->error : rreq->transferred); + } + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); +} + +/* + * Perform the collection of subrequests and folios. * * Note that we're in normal kernel thread context at this point, possibly * running on a workqueue. */ -static void netfs_rreq_assess(struct netfs_io_request *rreq) +static void netfs_read_collection(struct netfs_io_request *rreq) { - trace_netfs_rreq(rreq, netfs_rreq_trace_assess); + struct netfs_io_stream *stream = &rreq->io_streams[0]; + + netfs_collect_read_results(rreq); + + /* We're done when the app thread has finished posting subreqs and the + * queue is empty. + */ + if (!test_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags)) + return; + smp_rmb(); /* Read ALL_QUEUED before subreq lists. */ + + if (!list_empty(&stream->subrequests)) + return; + + /* Okay, declare that all I/O is complete. */ + rreq->transferred = stream->transferred; + trace_netfs_rreq(rreq, netfs_rreq_trace_complete); //netfs_rreq_is_still_valid(rreq); - if (test_and_clear_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags)) { - netfs_retry_reads(rreq); - return; - } - - if (rreq->origin == NETFS_DIO_READ || - rreq->origin == NETFS_READ_GAPS) + switch (rreq->origin) { + case NETFS_DIO_READ: + case NETFS_READ_GAPS: netfs_rreq_assess_dio(rreq); + break; + case NETFS_READ_SINGLE: + netfs_rreq_assess_single(rreq); + break; + default: + break; + } task_io_account_read(rreq->transferred); trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); trace_netfs_rreq(rreq, netfs_rreq_trace_done); netfs_clear_subrequests(rreq, false); netfs_unlock_abandoned_read_pages(rreq); - if (unlikely(test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))) - netfs_pgpriv2_write_to_the_cache(rreq); + if (unlikely(rreq->copy_to_cache)) + netfs_pgpriv2_end_copy_to_cache(rreq); } -void netfs_read_termination_worker(struct work_struct *work) +void netfs_read_collection_worker(struct work_struct *work) { - struct netfs_io_request *rreq = - container_of(work, struct netfs_io_request, work); + struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); + netfs_see_request(rreq, netfs_rreq_trace_see_work); - netfs_rreq_assess(rreq); - netfs_put_request(rreq, false, netfs_rreq_trace_put_work_complete); + if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) + netfs_read_collection(rreq); + netfs_put_request(rreq, false, netfs_rreq_trace_put_work); } /* - * Handle the completion of all outstanding I/O operations on a read request. - * We inherit a ref from the caller. + * Wake the collection work item. */ -void netfs_rreq_terminated(struct netfs_io_request *rreq, bool was_async) +void netfs_wake_read_collector(struct netfs_io_request *rreq) { - if (!was_async) - return netfs_rreq_assess(rreq); - if (!work_pending(&rreq->work)) { - netfs_get_request(rreq, netfs_rreq_trace_get_work); - if (!queue_work(system_unbound_wq, &rreq->work)) - netfs_put_request(rreq, was_async, netfs_rreq_trace_put_work_nq); + if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) { + if (!work_pending(&rreq->work)) { + netfs_get_request(rreq, netfs_rreq_trace_get_work); + if (!queue_work(system_unbound_wq, &rreq->work)) + netfs_put_request(rreq, true, netfs_rreq_trace_put_work_nq); + } + } else { + trace_netfs_rreq(rreq, netfs_rreq_trace_wake_queue); + wake_up(&rreq->waitq); } } /** * netfs_read_subreq_progress - Note progress of a read operation. * @subreq: The read request that has terminated. - * @was_async: True if we're in an asynchronous context. * * This tells the read side of netfs lib that a contributory I/O operation has * made some progress and that it may be possible to unlock some folios. * * Before calling, the filesystem should update subreq->transferred to track * the amount of data copied into the output buffer. - * - * If @was_async is true, the caller might be running in softirq or interrupt - * context and we can't sleep. */ -void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq, - bool was_async) +void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; + size_t fsize = PAGE_SIZE << rreq->front_folio_order; trace_netfs_sreq(subreq, netfs_sreq_trace_progress); - if (subreq->transferred > subreq->consumed && + /* If we are at the head of the queue, wake up the collector, + * getting a ref to it if we were the ones to do so. + */ + if (subreq->start + subreq->transferred > rreq->cleaned_to + fsize && (rreq->origin == NETFS_READAHEAD || rreq->origin == NETFS_READPAGE || - rreq->origin == NETFS_READ_FOR_WRITE)) { - netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + rreq->origin == NETFS_READ_FOR_WRITE) && + list_is_first(&subreq->rreq_link, &stream->subrequests) + ) { + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + netfs_wake_read_collector(rreq); } } EXPORT_SYMBOL(netfs_read_subreq_progress); @@ -446,27 +518,23 @@ EXPORT_SYMBOL(netfs_read_subreq_progress); /** * netfs_read_subreq_terminated - Note the termination of an I/O operation. * @subreq: The I/O request that has terminated. - * @error: Error code indicating type of completion. - * @was_async: The termination was asynchronous * * This tells the read helper that a contributory I/O operation has terminated, * one way or another, and that it should integrate the results. * - * The caller indicates the outcome of the operation through @error, supplying - * 0 to indicate a successful or retryable transfer (if NETFS_SREQ_NEED_RETRY - * is set) or a negative error code. The helper will look after reissuing I/O - * operations as appropriate and writing downloaded data to the cache. + * The caller indicates the outcome of the operation through @subreq->error, + * supplying 0 to indicate a successful or retryable transfer (if + * NETFS_SREQ_NEED_RETRY is set) or a negative error code. The helper will + * look after reissuing I/O operations as appropriate and writing downloaded + * data to the cache. * * Before calling, the filesystem should update subreq->transferred to track * the amount of data copied into the output buffer. - * - * If @was_async is true, the caller might be running in softirq or interrupt - * context and we can't sleep. */ -void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, - int error, bool was_async) +void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; switch (subreq->source) { case NETFS_READ_FROM_CACHE: @@ -479,68 +547,156 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, break; } - if (rreq->origin != NETFS_DIO_READ) { - /* Collect buffered reads. - * - * If the read completed validly short, then we can clear the - * tail before going on to unlock the folios. - */ - if (error == 0 && subreq->transferred < subreq->len && - (test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags) || - test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags))) { - netfs_clear_unread(subreq); - subreq->transferred = subreq->len; - trace_netfs_sreq(subreq, netfs_sreq_trace_clear); - } - if (subreq->transferred > subreq->consumed && - (rreq->origin == NETFS_READAHEAD || - rreq->origin == NETFS_READPAGE || - rreq->origin == NETFS_READ_FOR_WRITE)) { - netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - } - rreq->transferred += subreq->transferred; - } - /* Deal with retry requests, short reads and errors. If we retry * but don't make progress, we abandon the attempt. */ - if (!error && subreq->transferred < subreq->len) { + if (!subreq->error && subreq->transferred < subreq->len) { if (test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) { trace_netfs_sreq(subreq, netfs_sreq_trace_hit_eof); + } else if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { + trace_netfs_sreq(subreq, netfs_sreq_trace_need_clear); + } else if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + trace_netfs_sreq(subreq, netfs_sreq_trace_need_retry); + } else if (test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags)) { + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + trace_netfs_sreq(subreq, netfs_sreq_trace_partial_read); } else { + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + subreq->error = -ENODATA; trace_netfs_sreq(subreq, netfs_sreq_trace_short); - if (subreq->transferred > subreq->consumed) { - __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); - } else if (!__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { - __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); - } else { - __set_bit(NETFS_SREQ_FAILED, &subreq->flags); - error = -ENODATA; - } } } - subreq->error = error; - trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - - if (unlikely(error < 0)) { - trace_netfs_failure(rreq, subreq, error, netfs_fail_read); + if (unlikely(subreq->error < 0)) { + trace_netfs_failure(rreq, subreq, subreq->error, netfs_fail_read); if (subreq->source == NETFS_READ_FROM_CACHE) { netfs_stat(&netfs_n_rh_read_failed); + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); } else { netfs_stat(&netfs_n_rh_download_failed); - set_bit(NETFS_RREQ_FAILED, &rreq->flags); - rreq->error = subreq->error; + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + } + trace_netfs_rreq(rreq, netfs_rreq_trace_set_pause); + set_bit(NETFS_RREQ_PAUSE, &rreq->flags); + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); + + clear_bit_unlock(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + smp_mb__after_atomic(); /* Clear IN_PROGRESS before task state */ + + /* If we are at the head of the queue, wake up the collector. */ + if (list_is_first(&subreq->rreq_link, &stream->subrequests)) + netfs_wake_read_collector(rreq); + + netfs_put_subrequest(subreq, true, netfs_sreq_trace_put_terminated); +} +EXPORT_SYMBOL(netfs_read_subreq_terminated); + +/* + * Handle termination of a read from the cache. + */ +void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + + if (transferred_or_error > 0) { + subreq->error = 0; + if (transferred_or_error > 0) { + subreq->transferred += transferred_or_error; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + } + } else { + subreq->error = transferred_or_error; + } + netfs_read_subreq_terminated(subreq); +} + +/* + * Wait for the read operation to complete, successfully or otherwise. + */ +ssize_t netfs_wait_for_read(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; + DEFINE_WAIT(myself); + ssize_t ret; + + for (;;) { + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + + subreq = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + if (subreq && + (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) || + test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) { + __set_current_state(TASK_RUNNING); + netfs_read_collection(rreq); + continue; + } + + if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) + break; + + schedule(); + trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); + } + + finish_wait(&rreq->waitq, &myself); + + ret = rreq->error; + if (ret == 0) { + ret = rreq->transferred; + switch (rreq->origin) { + case NETFS_DIO_READ: + case NETFS_READ_SINGLE: + ret = rreq->transferred; + break; + default: + if (rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } + break; } } - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_terminated(rreq, was_async); + return ret; +} - netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +/* + * Wait for a paused read operation to unpause or complete in some manner. + */ +void netfs_wait_for_pause(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; + DEFINE_WAIT(myself); + + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause); + + for (;;) { + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + + subreq = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + if (subreq && + (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) || + test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) { + __set_current_state(TASK_RUNNING); + netfs_read_collection(rreq); + continue; + } + + if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags) || + !test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) + break; + + schedule(); + trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); + } + + finish_wait(&rreq->waitq, &myself); } -EXPORT_SYMBOL(netfs_read_subreq_terminated); diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index ba5af89d37fa..cf7727060215 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -13,53 +13,12 @@ #include #include "internal.h" -/* - * [DEPRECATED] Mark page as requiring copy-to-cache using PG_private_2. The - * third mark in the folio queue is used to indicate that this folio needs - * writing. - */ -void netfs_pgpriv2_mark_copy_to_cache(struct netfs_io_subrequest *subreq, - struct netfs_io_request *rreq, - struct folio_queue *folioq, - int slot) -{ - struct folio *folio = folioq_folio(folioq, slot); - - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); - folioq_mark3(folioq, slot); -} - -/* - * [DEPRECATED] Cancel PG_private_2 on all marked folios in the event of an - * unrecoverable error. - */ -static void netfs_pgpriv2_cancel(struct folio_queue *folioq) -{ - struct folio *folio; - int slot; - - while (folioq) { - if (!folioq->marks3) { - folioq = folioq->next; - continue; - } - - slot = __ffs(folioq->marks3); - folio = folioq_folio(folioq, slot); - - trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); - folio_end_private_2(folio); - folioq_unmark3(folioq, slot); - } -} - /* * [DEPRECATED] Copy a folio to the cache with PG_private_2 set. */ -static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio *folio) +static void netfs_pgpriv2_copy_folio(struct netfs_io_request *creq, struct folio *folio) { - struct netfs_io_stream *cache = &wreq->io_streams[1]; + struct netfs_io_stream *cache = &creq->io_streams[1]; size_t fsize = folio_size(folio), flen = fsize; loff_t fpos = folio_pos(folio), i_size; bool to_eof = false; @@ -70,17 +29,17 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio * of the page to beyond it, but cannot move i_size into or through the * page since we have it locked. */ - i_size = i_size_read(wreq->inode); + i_size = i_size_read(creq->inode); if (fpos >= i_size) { /* mmap beyond eof. */ _debug("beyond eof"); folio_end_private_2(folio); - return 0; + return; } - if (fpos + fsize > wreq->i_size) - wreq->i_size = i_size; + if (fpos + fsize > creq->i_size) + creq->i_size = i_size; if (flen > i_size - fpos) { flen = i_size - fpos; @@ -94,8 +53,10 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio trace_netfs_folio(folio, netfs_folio_trace_store_copy); /* Attach the folio to the rolling buffer. */ - if (netfs_buffer_append_folio(wreq, folio, false) < 0) - return -ENOMEM; + if (rolling_buffer_append(&creq->buffer, folio, 0) < 0) { + clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &creq->flags); + return; + } cache->submit_extendable_to = fsize; cache->submit_off = 0; @@ -109,11 +70,11 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio do { ssize_t part; - wreq->io_iter.iov_offset = cache->submit_off; + creq->buffer.iter.iov_offset = cache->submit_off; - atomic64_set(&wreq->issued_to, fpos + cache->submit_off); + atomic64_set(&creq->issued_to, fpos + cache->submit_off); cache->submit_extendable_to = fsize - cache->submit_off; - part = netfs_advance_write(wreq, cache, fpos + cache->submit_off, + part = netfs_advance_write(creq, cache, fpos + cache->submit_off, cache->submit_len, to_eof); cache->submit_off += part; if (part > cache->submit_len) @@ -122,94 +83,95 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio cache->submit_len -= part; } while (cache->submit_len > 0); - wreq->io_iter.iov_offset = 0; - iov_iter_advance(&wreq->io_iter, fsize); - atomic64_set(&wreq->issued_to, fpos + fsize); + creq->buffer.iter.iov_offset = 0; + rolling_buffer_advance(&creq->buffer, fsize); + atomic64_set(&creq->issued_to, fpos + fsize); if (flen < fsize) - netfs_issue_write(wreq, cache); - - _leave(" = 0"); - return 0; + netfs_issue_write(creq, cache); } /* - * [DEPRECATED] Go through the buffer and write any folios that are marked with - * the third mark to the cache. + * [DEPRECATED] Set up copying to the cache. */ -void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq) +static struct netfs_io_request *netfs_pgpriv2_begin_copy_to_cache( + struct netfs_io_request *rreq, struct folio *folio) { - struct netfs_io_request *wreq; - struct folio_queue *folioq; - struct folio *folio; - int error = 0; - int slot = 0; - - _enter(""); + struct netfs_io_request *creq; if (!fscache_resources_valid(&rreq->cache_resources)) - goto couldnt_start; + goto cancel; - /* Need the first folio to be able to set up the op. */ - for (folioq = rreq->buffer; folioq; folioq = folioq->next) { - if (folioq->marks3) { - slot = __ffs(folioq->marks3); - break; - } - } - if (!folioq) - return; - folio = folioq_folio(folioq, slot); - - wreq = netfs_create_write_req(rreq->mapping, NULL, folio_pos(folio), + creq = netfs_create_write_req(rreq->mapping, NULL, folio_pos(folio), NETFS_PGPRIV2_COPY_TO_CACHE); - if (IS_ERR(wreq)) { - kleave(" [create %ld]", PTR_ERR(wreq)); - goto couldnt_start; - } + if (IS_ERR(creq)) + goto cancel; - trace_netfs_write(wreq, netfs_write_trace_copy_to_cache); + if (!creq->io_streams[1].avail) + goto cancel_put; + + trace_netfs_write(creq, netfs_write_trace_copy_to_cache); netfs_stat(&netfs_n_wh_copy_to_cache); + rreq->copy_to_cache = creq; + return creq; - for (;;) { - error = netfs_pgpriv2_copy_folio(wreq, folio); - if (error < 0) - break; +cancel_put: + netfs_put_request(creq, false, netfs_rreq_trace_put_return); +cancel: + rreq->copy_to_cache = ERR_PTR(-ENOBUFS); + clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); + return ERR_PTR(-ENOBUFS); +} - folioq_unmark3(folioq, slot); - if (!folioq->marks3) { - folioq = folioq->next; - if (!folioq) - break; - } +/* + * [DEPRECATED] Mark page as requiring copy-to-cache using PG_private_2 and add + * it to the copy write request. + */ +void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio) +{ + struct netfs_io_request *creq = rreq->copy_to_cache; - slot = __ffs(folioq->marks3); - folio = folioq_folio(folioq, slot); - } + if (!creq) + creq = netfs_pgpriv2_begin_copy_to_cache(rreq, folio); + if (IS_ERR(creq)) + return; - netfs_issue_write(wreq, &wreq->io_streams[1]); + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_start_private_2(folio); + netfs_pgpriv2_copy_folio(creq, folio); +} + +/* + * [DEPRECATED] End writing to the cache, flushing out any outstanding writes. + */ +void netfs_pgpriv2_end_copy_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_io_request *creq = rreq->copy_to_cache; + + if (IS_ERR_OR_NULL(creq)) + return; + + netfs_issue_write(creq, &creq->io_streams[1]); smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); + set_bit(NETFS_RREQ_ALL_QUEUED, &creq->flags); - netfs_put_request(wreq, false, netfs_rreq_trace_put_return); - _leave(" = %d", error); -couldnt_start: - netfs_pgpriv2_cancel(rreq->buffer); + netfs_put_request(creq, false, netfs_rreq_trace_put_return); + creq->copy_to_cache = NULL; } /* * [DEPRECATED] Remove the PG_private_2 mark from any folios we've finished * copying. */ -bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) +bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *creq) { - struct folio_queue *folioq = wreq->buffer; - unsigned long long collected_to = wreq->collected_to; - unsigned int slot = wreq->buffer_head_slot; + struct folio_queue *folioq = creq->buffer.tail; + unsigned long long collected_to = creq->collected_to; + unsigned int slot = creq->buffer.first_tail_slot; bool made_progress = false; if (slot >= folioq_nr_slots(folioq)) { - folioq = netfs_delete_buffer_head(wreq); + folioq = rolling_buffer_delete_spent(&creq->buffer); slot = 0; } @@ -221,16 +183,16 @@ bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) folio = folioq_folio(folioq, slot); if (WARN_ONCE(!folio_test_private_2(folio), "R=%08x: folio %lx is not marked private_2\n", - wreq->debug_id, folio->index)) + creq->debug_id, folio->index)) trace_netfs_folio(folio, netfs_folio_trace_not_under_wback); fpos = folio_pos(folio); fsize = folio_size(folio); flen = fsize; - fend = min_t(unsigned long long, fpos + flen, wreq->i_size); + fend = min_t(unsigned long long, fpos + flen, creq->i_size); - trace_netfs_collect_folio(wreq, folio, fend, collected_to); + trace_netfs_collect_folio(creq, folio, fend, collected_to); /* Unlock any folio we've transferred all of. */ if (collected_to < fend) @@ -238,7 +200,7 @@ bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) trace_netfs_folio(folio, netfs_folio_trace_end_copy); folio_end_private_2(folio); - wreq->cleaned_to = fpos + fsize; + creq->cleaned_to = fpos + fsize; made_progress = true; /* Clean up the head folioq. If we clear an entire folioq, then @@ -248,9 +210,9 @@ bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) folioq_clear(folioq, slot); slot++; if (slot >= folioq_nr_slots(folioq)) { - if (READ_ONCE(wreq->buffer_tail) == folioq) - break; - folioq = netfs_delete_buffer_head(wreq); + folioq = rolling_buffer_delete_spent(&creq->buffer); + if (!folioq) + goto done; slot = 0; } @@ -258,7 +220,8 @@ bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) break; } - wreq->buffer = folioq; - wreq->buffer_head_slot = slot; + creq->buffer.tail = folioq; +done: + creq->buffer.first_tail_slot = slot; return made_progress; } diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 0350592ea804..2290af0d51ac 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -12,15 +12,7 @@ static void netfs_reissue_read(struct netfs_io_request *rreq, struct netfs_io_subrequest *subreq) { - struct iov_iter *io_iter = &subreq->io_iter; - - if (iov_iter_is_folioq(io_iter)) { - subreq->curr_folioq = (struct folio_queue *)io_iter->folioq; - subreq->curr_folioq_slot = io_iter->folioq_slot; - subreq->curr_folio_order = subreq->curr_folioq->orders[subreq->curr_folioq_slot]; - } - - atomic_inc(&rreq->nr_outstanding); + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); subreq->rreq->netfs_ops->issue_read(subreq); @@ -33,13 +25,12 @@ static void netfs_reissue_read(struct netfs_io_request *rreq, static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) { struct netfs_io_subrequest *subreq; - struct netfs_io_stream *stream0 = &rreq->io_streams[0]; - LIST_HEAD(sublist); - LIST_HEAD(queue); + struct netfs_io_stream *stream = &rreq->io_streams[0]; + struct list_head *next; _enter("R=%x", rreq->debug_id); - if (list_empty(&rreq->subrequests)) + if (list_empty(&stream->subrequests)) return; if (rreq->netfs_ops->retry_request) @@ -49,13 +40,13 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) * up to the first permanently failed one. */ if (!rreq->netfs_ops->prepare_read && - !test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) { - struct netfs_io_subrequest *subreq; - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + !rreq->cache_resources.ops) { + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) break; if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; netfs_reset_iter(subreq); netfs_reissue_read(rreq, subreq); } @@ -73,48 +64,44 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) * populating with smaller subrequests. In the event that the subreq * we just launched finishes before we insert the next subreq, it'll * fill in rreq->prev_donated instead. - + * * Note: Alternatively, we could split the tail subrequest right before * we reissue it and fix up the donations under lock. */ - list_splice_init(&rreq->subrequests, &queue); + next = stream->subrequests.next; do { - struct netfs_io_subrequest *from; + struct netfs_io_subrequest *from, *to, *tmp; struct iov_iter source; unsigned long long start, len; - size_t part, deferred_next_donated = 0; + size_t part; bool boundary = false; /* Go through the subreqs and find the next span of contiguous * buffer that we then rejig (cifs, for example, needs the * rsize renegotiating) and reissue. */ - from = list_first_entry(&queue, struct netfs_io_subrequest, rreq_link); - list_move_tail(&from->rreq_link, &sublist); + from = list_entry(next, struct netfs_io_subrequest, rreq_link); + to = from; start = from->start + from->transferred; len = from->len - from->transferred; - _debug("from R=%08x[%x] s=%llx ctl=%zx/%zx/%zx", + _debug("from R=%08x[%x] s=%llx ctl=%zx/%zx", rreq->debug_id, from->debug_index, - from->start, from->consumed, from->transferred, from->len); + from->start, from->transferred, from->len); if (test_bit(NETFS_SREQ_FAILED, &from->flags) || !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) goto abandon; - deferred_next_donated = from->next_donated; - while ((subreq = list_first_entry_or_null( - &queue, struct netfs_io_subrequest, rreq_link))) { - if (subreq->start != start + len || - subreq->transferred > 0 || + list_for_each_continue(next, &stream->subrequests) { + subreq = list_entry(next, struct netfs_io_subrequest, rreq_link); + if (subreq->start + subreq->transferred != start + len || + test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags) || !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) break; - list_move_tail(&subreq->rreq_link, &sublist); - len += subreq->len; - deferred_next_donated = subreq->next_donated; - if (test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags)) - break; + to = subreq; + len += to->len; } _debug(" - range: %llx-%llx %llx", start, start + len - 1, len); @@ -127,36 +114,31 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) source.count = len; /* Work through the sublist. */ - while ((subreq = list_first_entry_or_null( - &sublist, struct netfs_io_subrequest, rreq_link))) { - list_del(&subreq->rreq_link); - + subreq = from; + list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { + if (!len) + break; subreq->source = NETFS_DOWNLOAD_FROM_SERVER; subreq->start = start - subreq->transferred; subreq->len = len + subreq->transferred; - stream0->sreq_max_len = subreq->len; - __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; - spin_lock_bh(&rreq->lock); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - subreq->prev_donated += rreq->prev_donated; - rreq->prev_donated = 0; trace_netfs_sreq(subreq, netfs_sreq_trace_retry); - spin_unlock_bh(&rreq->lock); - - BUG_ON(!len); /* Renegotiate max_len (rsize) */ - if (rreq->netfs_ops->prepare_read(subreq) < 0) { + stream->sreq_max_len = subreq->len; + if (rreq->netfs_ops->prepare_read && + rreq->netfs_ops->prepare_read(subreq) < 0) { trace_netfs_sreq(subreq, netfs_sreq_trace_reprep_failed); __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + goto abandon; } - part = umin(len, stream0->sreq_max_len); - if (unlikely(rreq->io_streams[0].sreq_max_segs)) - part = netfs_limit_iter(&source, 0, part, stream0->sreq_max_segs); + part = umin(len, stream->sreq_max_len); + if (unlikely(stream->sreq_max_segs)) + part = netfs_limit_iter(&source, 0, part, stream->sreq_max_segs); subreq->len = subreq->transferred + part; subreq->io_iter = source; iov_iter_truncate(&subreq->io_iter, part); @@ -166,58 +148,105 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) if (!len) { if (boundary) __set_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); - subreq->next_donated = deferred_next_donated; } else { __clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); - subreq->next_donated = 0; } + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_read(rreq, subreq); - if (!len) + if (subreq == to) break; - - /* If we ran out of subrequests, allocate another. */ - if (list_empty(&sublist)) { - subreq = netfs_alloc_subrequest(rreq); - if (!subreq) - goto abandon; - subreq->source = NETFS_DOWNLOAD_FROM_SERVER; - subreq->start = start; - - /* We get two refs, but need just one. */ - netfs_put_subrequest(subreq, false, netfs_sreq_trace_new); - trace_netfs_sreq(subreq, netfs_sreq_trace_split); - list_add_tail(&subreq->rreq_link, &sublist); - } } /* If we managed to use fewer subreqs, we can discard the - * excess. + * excess; if we used the same number, then we're done. */ - while ((subreq = list_first_entry_or_null( - &sublist, struct netfs_io_subrequest, rreq_link))) { - trace_netfs_sreq(subreq, netfs_sreq_trace_discard); - list_del(&subreq->rreq_link); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); + if (!len) { + if (subreq == to) + continue; + list_for_each_entry_safe_from(subreq, tmp, + &stream->subrequests, rreq_link) { + trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + list_del(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); + if (subreq == to) + break; + } + continue; } - } while (!list_empty(&queue)); + /* We ran out of subrequests, so we need to allocate some more + * and insert them after. + */ + do { + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) { + subreq = to; + goto abandon_after; + } + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->start = start; + subreq->len = len; + subreq->debug_index = atomic_inc_return(&rreq->subreq_counter); + subreq->stream_nr = stream->stream_nr; + subreq->retry_count = 1; + + trace_netfs_sreq_ref(rreq->debug_id, subreq->debug_index, + refcount_read(&subreq->ref), + netfs_sreq_trace_new); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + + list_add(&subreq->rreq_link, &to->rreq_link); + to = list_next_entry(to, rreq_link); + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + + stream->sreq_max_len = umin(len, rreq->rsize); + stream->sreq_max_segs = 0; + if (unlikely(stream->sreq_max_segs)) + part = netfs_limit_iter(&source, 0, part, stream->sreq_max_segs); + + netfs_stat(&netfs_n_rh_download); + if (rreq->netfs_ops->prepare_read(subreq) < 0) { + trace_netfs_sreq(subreq, netfs_sreq_trace_reprep_failed); + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + goto abandon; + } + + part = umin(len, stream->sreq_max_len); + subreq->len = subreq->transferred + part; + subreq->io_iter = source; + iov_iter_truncate(&subreq->io_iter, part); + iov_iter_advance(&source, part); + + len -= part; + start += part; + if (!len && boundary) { + __set_bit(NETFS_SREQ_BOUNDARY, &to->flags); + boundary = false; + } + + netfs_reissue_read(rreq, subreq); + } while (len); + + } while (!list_is_head(next, &stream->subrequests)); return; - /* If we hit ENOMEM, fail all remaining subrequests */ + /* If we hit an error, fail all remaining incomplete subrequests */ +abandon_after: + if (list_is_last(&subreq->rreq_link, &stream->subrequests)) + return; + subreq = list_next_entry(subreq, rreq_link); abandon: - list_splice_init(&sublist, &queue); - list_for_each_entry(subreq, &queue, rreq_link) { - if (!subreq->error) - subreq->error = -ENOMEM; - __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); + list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { + if (!subreq->error && + !test_bit(NETFS_SREQ_FAILED, &subreq->flags) && + !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) + continue; + subreq->error = -ENOMEM; + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_RETRYING, &subreq->flags); } - spin_lock_bh(&rreq->lock); - list_splice_tail_init(&queue, &rreq->subrequests); - spin_unlock_bh(&rreq->lock); } /* @@ -225,14 +254,19 @@ abandon: */ void netfs_retry_reads(struct netfs_io_request *rreq) { + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; + + /* Wait for all outstanding I/O to quiesce before performing retries as + * we may need to renegotiate the I/O sizes. + */ + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { + wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); + } + trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); - - atomic_inc(&rreq->nr_outstanding); - netfs_retry_read_subrequests(rreq); - - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_terminated(rreq, false); } /* @@ -243,7 +277,7 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) { struct folio_queue *p; - for (p = rreq->buffer; p; p = p->next) { + for (p = rreq->buffer.tail; p; p = p->next) { for (int slot = 0; slot < folioq_count(p); slot++) { struct folio *folio = folioq_folio(p, slot); diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c new file mode 100644 index 000000000000..fea0ecdecc53 --- /dev/null +++ b/fs/netfs/read_single.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Single, monolithic object support (e.g. AFS directory). + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +/** + * netfs_single_mark_inode_dirty - Mark a single, monolithic object inode dirty + * @inode: The inode to mark + * + * Mark an inode that contains a single, monolithic object as dirty so that its + * writepages op will get called. If set, the SINGLE_NO_UPLOAD flag indicates + * that the object will only be written to the cache and not uploaded (e.g. AFS + * directory contents). + */ +void netfs_single_mark_inode_dirty(struct inode *inode) +{ + struct netfs_inode *ictx = netfs_inode(inode); + bool cache_only = test_bit(NETFS_ICTX_SINGLE_NO_UPLOAD, &ictx->flags); + bool caching = fscache_cookie_enabled(netfs_i_cookie(netfs_inode(inode))); + + if (cache_only && !caching) + return; + + mark_inode_dirty(inode); + + if (caching && !(inode->i_state & I_PINNING_NETFS_WB)) { + bool need_use = false; + + spin_lock(&inode->i_lock); + if (!(inode->i_state & I_PINNING_NETFS_WB)) { + inode->i_state |= I_PINNING_NETFS_WB; + need_use = true; + } + spin_unlock(&inode->i_lock); + + if (need_use) + fscache_use_cookie(netfs_i_cookie(ictx), true); + } + +} +EXPORT_SYMBOL(netfs_single_mark_inode_dirty); + +static int netfs_single_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx) +{ + return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx)); +} + +static void netfs_single_cache_prepare_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + + if (!cres->ops) { + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + return; + } + subreq->source = cres->ops->prepare_read(subreq, rreq->i_size); + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + +} + +static void netfs_single_read_cache(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + + _enter("R=%08x[%x]", rreq->debug_id, subreq->debug_index); + netfs_stat(&netfs_n_rh_read); + cres->ops->read(cres, subreq->start, &subreq->io_iter, NETFS_READ_HOLE_FAIL, + netfs_cache_read_terminated, subreq); +} + +/* + * Perform a read to a buffer from the cache or the server. Only a single + * subreq is permitted as the object must be fetched in a single transaction. + */ +static int netfs_single_dispatch_read(struct netfs_io_request *rreq) +{ + struct netfs_io_stream *stream = &rreq->io_streams[0]; + struct netfs_io_subrequest *subreq; + int ret = 0; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) + return -ENOMEM; + + subreq->source = NETFS_SOURCE_UNKNOWN; + subreq->start = 0; + subreq->len = rreq->len; + subreq->io_iter = rreq->buffer.iter; + + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + + spin_lock(&rreq->lock); + list_add_tail(&subreq->rreq_link, &stream->subrequests); + trace_netfs_sreq(subreq, netfs_sreq_trace_added); + stream->front = subreq; + /* Store list pointers before active flag */ + smp_store_release(&stream->active, true); + spin_unlock(&rreq->lock); + + netfs_single_cache_prepare_read(rreq, subreq); + switch (subreq->source) { + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_stat(&netfs_n_rh_download); + if (rreq->netfs_ops->prepare_read) { + ret = rreq->netfs_ops->prepare_read(subreq); + if (ret < 0) + goto cancel; + } + + rreq->netfs_ops->issue_read(subreq); + rreq->submitted += subreq->len; + break; + case NETFS_READ_FROM_CACHE: + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + netfs_single_read_cache(rreq, subreq); + rreq->submitted += subreq->len; + ret = 0; + break; + default: + pr_warn("Unexpected single-read source %u\n", subreq->source); + WARN_ON_ONCE(true); + ret = -EIO; + break; + } + + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + return ret; +cancel: + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + return ret; +} + +/** + * netfs_read_single - Synchronously read a single blob of pages. + * @inode: The inode to read from. + * @file: The file we're using to read or NULL. + * @iter: The buffer we're reading into. + * + * Fulfil a read request for a single monolithic object by drawing data from + * the cache if possible, or the netfs if not. The buffer may be larger than + * the file content; unused beyond the EOF will be zero-filled. The content + * will be read with a single I/O request (though this may be retried). + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. If caching is enabled, + * the data will be stored as a single object into the cache. + */ +ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_iter *iter) +{ + struct netfs_io_request *rreq; + struct netfs_inode *ictx = netfs_inode(inode); + ssize_t ret; + + rreq = netfs_alloc_request(inode->i_mapping, file, 0, iov_iter_count(iter), + NETFS_READ_SINGLE); + if (IS_ERR(rreq)) + return PTR_ERR(rreq); + + ret = netfs_single_begin_cache_read(rreq, ictx); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto cleanup_free; + + netfs_stat(&netfs_n_rh_read_single); + trace_netfs_read(rreq, 0, rreq->len, netfs_read_trace_read_single); + + rreq->buffer.iter = *iter; + netfs_single_dispatch_read(rreq); + + ret = netfs_wait_for_read(rreq); + netfs_put_request(rreq, true, netfs_rreq_trace_put_return); + return ret; + +cleanup_free: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); + return ret; +} +EXPORT_SYMBOL(netfs_read_single); diff --git a/fs/netfs/rolling_buffer.c b/fs/netfs/rolling_buffer.c new file mode 100644 index 000000000000..75d97af14b4a --- /dev/null +++ b/fs/netfs/rolling_buffer.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Rolling buffer helpers + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include "internal.h" + +static atomic_t debug_ids; + +/** + * netfs_folioq_alloc - Allocate a folio_queue struct + * @rreq_id: Associated debugging ID for tracing purposes + * @gfp: Allocation constraints + * @trace: Trace tag to indicate the purpose of the allocation + * + * Allocate, initialise and account the folio_queue struct and log a trace line + * to mark the allocation. + */ +struct folio_queue *netfs_folioq_alloc(unsigned int rreq_id, gfp_t gfp, + unsigned int /*enum netfs_folioq_trace*/ trace) +{ + struct folio_queue *fq; + + fq = kmalloc(sizeof(*fq), gfp); + if (fq) { + netfs_stat(&netfs_n_folioq); + folioq_init(fq, rreq_id); + fq->debug_id = atomic_inc_return(&debug_ids); + trace_netfs_folioq(fq, trace); + } + return fq; +} +EXPORT_SYMBOL(netfs_folioq_alloc); + +/** + * netfs_folioq_free - Free a folio_queue struct + * @folioq: The object to free + * @trace: Trace tag to indicate which free + * + * Free and unaccount the folio_queue struct. + */ +void netfs_folioq_free(struct folio_queue *folioq, + unsigned int /*enum netfs_trace_folioq*/ trace) +{ + trace_netfs_folioq(folioq, trace); + netfs_stat_d(&netfs_n_folioq); + kfree(folioq); +} +EXPORT_SYMBOL(netfs_folioq_free); + +/* + * Initialise a rolling buffer. We allocate an empty folio queue struct to so + * that the pointers can be independently driven by the producer and the + * consumer. + */ +int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, + unsigned int direction) +{ + struct folio_queue *fq; + + fq = netfs_folioq_alloc(rreq_id, GFP_NOFS, netfs_trace_folioq_rollbuf_init); + if (!fq) + return -ENOMEM; + + roll->head = fq; + roll->tail = fq; + iov_iter_folio_queue(&roll->iter, direction, fq, 0, 0, 0); + return 0; +} + +/* + * Add another folio_queue to a rolling buffer if there's no space left. + */ +int rolling_buffer_make_space(struct rolling_buffer *roll) +{ + struct folio_queue *fq, *head = roll->head; + + if (!folioq_full(head)) + return 0; + + fq = netfs_folioq_alloc(head->rreq_id, GFP_NOFS, netfs_trace_folioq_make_space); + if (!fq) + return -ENOMEM; + fq->prev = head; + + roll->head = fq; + if (folioq_full(head)) { + /* Make sure we don't leave the master iterator pointing to a + * block that might get immediately consumed. + */ + if (roll->iter.folioq == head && + roll->iter.folioq_slot == folioq_nr_slots(head)) { + roll->iter.folioq = fq; + roll->iter.folioq_slot = 0; + } + } + + /* Make sure the initialisation is stored before the next pointer. + * + * [!] NOTE: After we set head->next, the consumer is at liberty to + * immediately delete the old head. + */ + smp_store_release(&head->next, fq); + return 0; +} + +/* + * Decant the list of folios to read into a rolling buffer. + */ +ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, + struct readahead_control *ractl, + struct folio_batch *put_batch) +{ + struct folio_queue *fq; + struct page **vec; + int nr, ix, to; + ssize_t size = 0; + + if (rolling_buffer_make_space(roll) < 0) + return -ENOMEM; + + fq = roll->head; + vec = (struct page **)fq->vec.folios; + nr = __readahead_batch(ractl, vec + folio_batch_count(&fq->vec), + folio_batch_space(&fq->vec)); + ix = fq->vec.nr; + to = ix + nr; + fq->vec.nr = to; + for (; ix < to; ix++) { + struct folio *folio = folioq_folio(fq, ix); + unsigned int order = folio_order(folio); + + fq->orders[ix] = order; + size += PAGE_SIZE << order; + trace_netfs_folio(folio, netfs_folio_trace_read); + if (!folio_batch_add(put_batch, folio)) + folio_batch_release(put_batch); + } + WRITE_ONCE(roll->iter.count, roll->iter.count + size); + + /* Store the counter after setting the slot. */ + smp_store_release(&roll->next_head_slot, to); + + for (; ix < folioq_nr_slots(fq); ix++) + folioq_clear(fq, ix); + + return size; +} + +/* + * Append a folio to the rolling buffer. + */ +ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio, + unsigned int flags) +{ + ssize_t size = folio_size(folio); + int slot; + + if (rolling_buffer_make_space(roll) < 0) + return -ENOMEM; + + slot = folioq_append(roll->head, folio); + if (flags & ROLLBUF_MARK_1) + folioq_mark(roll->head, slot); + if (flags & ROLLBUF_MARK_2) + folioq_mark2(roll->head, slot); + + WRITE_ONCE(roll->iter.count, roll->iter.count + size); + + /* Store the counter after setting the slot. */ + smp_store_release(&roll->next_head_slot, slot); + return size; +} + +/* + * Delete a spent buffer from a rolling queue and return the next in line. We + * don't return the last buffer to keep the pointers independent, but return + * NULL instead. + */ +struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll) +{ + struct folio_queue *spent = roll->tail, *next = READ_ONCE(spent->next); + + if (!next) + return NULL; + next->prev = NULL; + netfs_folioq_free(spent, netfs_trace_folioq_delete); + roll->tail = next; + return next; +} + +/* + * Clear out a rolling queue. Folios that have mark 1 set are put. + */ +void rolling_buffer_clear(struct rolling_buffer *roll) +{ + struct folio_batch fbatch; + struct folio_queue *p; + + folio_batch_init(&fbatch); + + while ((p = roll->tail)) { + roll->tail = p->next; + for (int slot = 0; slot < folioq_count(p); slot++) { + struct folio *folio = folioq_folio(p, slot); + + if (!folio) + continue; + if (folioq_is_marked(p, slot)) { + trace_netfs_folio(folio, netfs_folio_trace_put); + if (!folio_batch_add(&fbatch, folio)) + folio_batch_release(&fbatch); + } + } + + netfs_folioq_free(p, netfs_trace_folioq_clear); + } + + folio_batch_release(&fbatch); +} diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index 8e63516b40f6..f1af344266cc 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -12,6 +12,7 @@ atomic_t netfs_n_rh_dio_read; atomic_t netfs_n_rh_readahead; atomic_t netfs_n_rh_read_folio; +atomic_t netfs_n_rh_read_single; atomic_t netfs_n_rh_rreq; atomic_t netfs_n_rh_sreq; atomic_t netfs_n_rh_download; @@ -46,10 +47,11 @@ atomic_t netfs_n_folioq; int netfs_stats_show(struct seq_file *m, void *v) { - seq_printf(m, "Reads : DR=%u RA=%u RF=%u WB=%u WBZ=%u\n", + seq_printf(m, "Reads : DR=%u RA=%u RF=%u RS=%u WB=%u WBZ=%u\n", atomic_read(&netfs_n_rh_dio_read), atomic_read(&netfs_n_rh_readahead), atomic_read(&netfs_n_rh_read_folio), + atomic_read(&netfs_n_rh_read_single), atomic_read(&netfs_n_rh_write_begin), atomic_read(&netfs_n_rh_write_zskip)); seq_printf(m, "Writes : BW=%u WT=%u DW=%u WP=%u 2C=%u\n", diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 1d438be2e1b4..294f67795f79 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -17,10 +17,38 @@ #define HIT_PENDING 0x01 /* A front op was still pending */ #define NEED_REASSESS 0x02 /* Need to loop round and reassess */ #define MADE_PROGRESS 0x04 /* Made progress cleaning up a stream or the folio set */ -#define BUFFERED 0x08 /* The pagecache needs cleaning up */ +#define NEED_UNLOCK 0x08 /* The pagecache needs unlocking */ #define NEED_RETRY 0x10 /* A front op requests retrying */ #define SAW_FAILURE 0x20 /* One stream or hit a permanent failure */ +static void netfs_dump_request(const struct netfs_io_request *rreq) +{ + pr_err("Request R=%08x r=%d fl=%lx or=%x e=%ld\n", + rreq->debug_id, refcount_read(&rreq->ref), rreq->flags, + rreq->origin, rreq->error); + pr_err(" st=%llx tsl=%zx/%llx/%llx\n", + rreq->start, rreq->transferred, rreq->submitted, rreq->len); + pr_err(" cci=%llx/%llx/%llx\n", + rreq->cleaned_to, rreq->collected_to, atomic64_read(&rreq->issued_to)); + pr_err(" iw=%pSR\n", rreq->netfs_ops->issue_write); + for (int i = 0; i < NR_IO_STREAMS; i++) { + const struct netfs_io_subrequest *sreq; + const struct netfs_io_stream *s = &rreq->io_streams[i]; + + pr_err(" str[%x] s=%x e=%d acnf=%u,%u,%u,%u\n", + s->stream_nr, s->source, s->error, + s->avail, s->active, s->need_retry, s->failed); + pr_err(" str[%x] ct=%llx t=%zx\n", + s->stream_nr, s->collected_to, s->transferred); + list_for_each_entry(sreq, &s->subrequests, rreq_link) { + pr_err(" sreq[%x:%x] sc=%u s=%llx t=%zx/%zx r=%d f=%lx\n", + sreq->stream_nr, sreq->debug_index, sreq->source, + sreq->start, sreq->transferred, sreq->len, + refcount_read(&sreq->ref), sreq->flags); + } + } +} + /* * Successful completion of write of a folio to the server and/or cache. Note * that we are not allowed to lock the folio here on pain of deadlocking with @@ -83,9 +111,15 @@ end_wb: static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, unsigned int *notes) { - struct folio_queue *folioq = wreq->buffer; + struct folio_queue *folioq = wreq->buffer.tail; unsigned long long collected_to = wreq->collected_to; - unsigned int slot = wreq->buffer_head_slot; + unsigned int slot = wreq->buffer.first_tail_slot; + + if (WARN_ON_ONCE(!folioq)) { + pr_err("[!] Writeback unlock found empty rolling buffer!\n"); + netfs_dump_request(wreq); + return; + } if (wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE) { if (netfs_pgpriv2_unlock_copied_folios(wreq)) @@ -94,7 +128,9 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, } if (slot >= folioq_nr_slots(folioq)) { - folioq = netfs_delete_buffer_head(wreq); + folioq = rolling_buffer_delete_spent(&wreq->buffer); + if (!folioq) + return; slot = 0; } @@ -134,9 +170,9 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, folioq_clear(folioq, slot); slot++; if (slot >= folioq_nr_slots(folioq)) { - if (READ_ONCE(wreq->buffer_tail) == folioq) - break; - folioq = netfs_delete_buffer_head(wreq); + folioq = rolling_buffer_delete_spent(&wreq->buffer); + if (!folioq) + goto done; slot = 0; } @@ -144,223 +180,9 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, break; } - wreq->buffer = folioq; - wreq->buffer_head_slot = slot; -} - -/* - * Perform retries on the streams that need it. - */ -static void netfs_retry_write_stream(struct netfs_io_request *wreq, - struct netfs_io_stream *stream) -{ - struct list_head *next; - - _enter("R=%x[%x:]", wreq->debug_id, stream->stream_nr); - - if (list_empty(&stream->subrequests)) - return; - - if (stream->source == NETFS_UPLOAD_TO_SERVER && - wreq->netfs_ops->retry_request) - wreq->netfs_ops->retry_request(wreq, stream); - - if (unlikely(stream->failed)) - return; - - /* If there's no renegotiation to do, just resend each failed subreq. */ - if (!stream->prepare_write) { - struct netfs_io_subrequest *subreq; - - list_for_each_entry(subreq, &stream->subrequests, rreq_link) { - if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) - break; - if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { - struct iov_iter source = subreq->io_iter; - - iov_iter_revert(&source, subreq->len - source.count); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - netfs_reissue_write(stream, subreq, &source); - } - } - return; - } - - next = stream->subrequests.next; - - do { - struct netfs_io_subrequest *subreq = NULL, *from, *to, *tmp; - struct iov_iter source; - unsigned long long start, len; - size_t part; - bool boundary = false; - - /* Go through the stream and find the next span of contiguous - * data that we then rejig (cifs, for example, needs the wsize - * renegotiating) and reissue. - */ - from = list_entry(next, struct netfs_io_subrequest, rreq_link); - to = from; - start = from->start + from->transferred; - len = from->len - from->transferred; - - if (test_bit(NETFS_SREQ_FAILED, &from->flags) || - !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) - return; - - list_for_each_continue(next, &stream->subrequests) { - subreq = list_entry(next, struct netfs_io_subrequest, rreq_link); - if (subreq->start + subreq->transferred != start + len || - test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags) || - !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) - break; - to = subreq; - len += to->len; - } - - /* Determine the set of buffers we're going to use. Each - * subreq gets a subset of a single overall contiguous buffer. - */ - netfs_reset_iter(from); - source = from->io_iter; - source.count = len; - - /* Work through the sublist. */ - subreq = from; - list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { - if (!len) - break; - /* Renegotiate max_len (wsize) */ - trace_netfs_sreq(subreq, netfs_sreq_trace_retry); - __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); - stream->prepare_write(subreq); - - part = min(len, stream->sreq_max_len); - subreq->len = part; - subreq->start = start; - subreq->transferred = 0; - len -= part; - start += part; - if (len && subreq == to && - __test_and_clear_bit(NETFS_SREQ_BOUNDARY, &to->flags)) - boundary = true; - - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - netfs_reissue_write(stream, subreq, &source); - if (subreq == to) - break; - } - - /* If we managed to use fewer subreqs, we can discard the - * excess; if we used the same number, then we're done. - */ - if (!len) { - if (subreq == to) - continue; - list_for_each_entry_safe_from(subreq, tmp, - &stream->subrequests, rreq_link) { - trace_netfs_sreq(subreq, netfs_sreq_trace_discard); - list_del(&subreq->rreq_link); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); - if (subreq == to) - break; - } - continue; - } - - /* We ran out of subrequests, so we need to allocate some more - * and insert them after. - */ - do { - subreq = netfs_alloc_subrequest(wreq); - subreq->source = to->source; - subreq->start = start; - subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); - subreq->stream_nr = to->stream_nr; - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); - - trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, - refcount_read(&subreq->ref), - netfs_sreq_trace_new); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - - list_add(&subreq->rreq_link, &to->rreq_link); - to = list_next_entry(to, rreq_link); - trace_netfs_sreq(subreq, netfs_sreq_trace_retry); - - stream->sreq_max_len = len; - stream->sreq_max_segs = INT_MAX; - switch (stream->source) { - case NETFS_UPLOAD_TO_SERVER: - netfs_stat(&netfs_n_wh_upload); - stream->sreq_max_len = umin(len, wreq->wsize); - break; - case NETFS_WRITE_TO_CACHE: - netfs_stat(&netfs_n_wh_write); - break; - default: - WARN_ON_ONCE(1); - } - - stream->prepare_write(subreq); - - part = umin(len, stream->sreq_max_len); - subreq->len = subreq->transferred + part; - len -= part; - start += part; - if (!len && boundary) { - __set_bit(NETFS_SREQ_BOUNDARY, &to->flags); - boundary = false; - } - - netfs_reissue_write(stream, subreq, &source); - if (!len) - break; - - } while (len); - - } while (!list_is_head(next, &stream->subrequests)); -} - -/* - * Perform retries on the streams that need it. If we're doing content - * encryption and the server copy changed due to a third-party write, we may - * need to do an RMW cycle and also rewrite the data to the cache. - */ -static void netfs_retry_writes(struct netfs_io_request *wreq) -{ - struct netfs_io_subrequest *subreq; - struct netfs_io_stream *stream; - int s; - - /* Wait for all outstanding I/O to quiesce before performing retries as - * we may need to renegotiate the I/O sizes. - */ - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (!stream->active) - continue; - - list_for_each_entry(subreq, &stream->subrequests, rreq_link) { - wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS, - TASK_UNINTERRUPTIBLE); - } - } - - // TODO: Enc: Fetch changed partial pages - // TODO: Enc: Reencrypt content if needed. - // TODO: Enc: Wind back transferred point. - // TODO: Enc: Mark cache pages for retry. - - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->need_retry) { - stream->need_retry = false; - netfs_retry_write_stream(wreq, stream); - } - } + wreq->buffer.tail = folioq; +done: + wreq->buffer.first_tail_slot = slot; } /* @@ -391,7 +213,7 @@ reassess_streams: if (wreq->origin == NETFS_WRITEBACK || wreq->origin == NETFS_WRITETHROUGH || wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE) - notes = BUFFERED; + notes = NEED_UNLOCK; else notes = 0; @@ -450,14 +272,14 @@ reassess_streams: cancel: /* Remove if completely consumed. */ - spin_lock_bh(&wreq->lock); + spin_lock(&wreq->lock); remove = front; list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); stream->front = front; - spin_unlock_bh(&wreq->lock); + spin_unlock(&wreq->lock); netfs_put_subrequest(remove, false, notes & SAW_FAILURE ? netfs_sreq_trace_put_cancel : @@ -488,7 +310,7 @@ reassess_streams: trace_netfs_collect_state(wreq, wreq->collected_to, notes); /* Unlock any folios that we have now finished with. */ - if (notes & BUFFERED) { + if (notes & NEED_UNLOCK) { if (wreq->cleaned_to < wreq->collected_to) netfs_writeback_unlock_folios(wreq, ¬es); } else { @@ -502,7 +324,8 @@ reassess_streams: if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { trace_netfs_rreq(wreq, netfs_rreq_trace_unpause); clear_bit_unlock(NETFS_RREQ_PAUSE, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_PAUSE); + smp_mb__after_atomic(); /* Set PAUSE before task state */ + wake_up(&wreq->waitq); } if (notes & NEED_REASSESS) { @@ -605,8 +428,7 @@ void netfs_write_collection_worker(struct work_struct *work) _debug("finished"); trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags); if (wreq->iocb) { size_t written = min(wreq->transferred, wreq->len); @@ -714,8 +536,7 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - clear_bit_unlock(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - wake_up_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); /* If we are at the head of the queue, wake up the collector, * transferring a ref to it if we were the ones to do so. diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index bf6d507578e5..69727411683e 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -94,9 +94,10 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, { struct netfs_io_request *wreq; struct netfs_inode *ictx; - bool is_buffered = (origin == NETFS_WRITEBACK || - origin == NETFS_WRITETHROUGH || - origin == NETFS_PGPRIV2_COPY_TO_CACHE); + bool is_cacheable = (origin == NETFS_WRITEBACK || + origin == NETFS_WRITEBACK_SINGLE || + origin == NETFS_WRITETHROUGH || + origin == NETFS_PGPRIV2_COPY_TO_CACHE); wreq = netfs_alloc_request(mapping, file, start, 0, origin); if (IS_ERR(wreq)) @@ -105,8 +106,10 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, _enter("R=%x", wreq->debug_id); ictx = netfs_inode(wreq->inode); - if (is_buffered && netfs_is_cache_enabled(ictx)) + if (is_cacheable && netfs_is_cache_enabled(ictx)) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); + if (rolling_buffer_init(&wreq->buffer, wreq->debug_id, ITER_SOURCE) < 0) + goto nomem; wreq->cleaned_to = wreq->start; @@ -129,6 +132,10 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, } return wreq; +nomem: + wreq->error = -ENOMEM; + netfs_put_request(wreq, false, netfs_rreq_trace_put_failed); + return ERR_PTR(-ENOMEM); } /** @@ -153,16 +160,15 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, loff_t start) { struct netfs_io_subrequest *subreq; - struct iov_iter *wreq_iter = &wreq->io_iter; + struct iov_iter *wreq_iter = &wreq->buffer.iter; /* Make sure we don't point the iterator at a used-up folio_queue * struct being used as a placeholder to prevent the queue from * collapsing. In such a case, extend the queue. */ if (iov_iter_is_folioq(wreq_iter) && - wreq_iter->folioq_slot >= folioq_nr_slots(wreq_iter->folioq)) { - netfs_buffer_make_space(wreq); - } + wreq_iter->folioq_slot >= folioq_nr_slots(wreq_iter->folioq)) + rolling_buffer_make_space(&wreq->buffer); subreq = netfs_alloc_subrequest(wreq); subreq->source = stream->source; @@ -198,7 +204,7 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, * the list. The collector only goes nextwards and uses the lock to * remove entries off of the front. */ - spin_lock_bh(&wreq->lock); + spin_lock(&wreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { stream->front = subreq; @@ -209,7 +215,7 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, } } - spin_unlock_bh(&wreq->lock); + spin_unlock(&wreq->lock); stream->construct = subreq; } @@ -244,6 +250,8 @@ void netfs_reissue_write(struct netfs_io_stream *stream, iov_iter_advance(source, size); iov_iter_truncate(&subreq->io_iter, size); + subreq->retry_count++; + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); netfs_do_issue_write(stream, subreq); } @@ -266,9 +274,9 @@ void netfs_issue_write(struct netfs_io_request *wreq, * we can avoid overrunning the credits obtained (cifs) and try to parallelise * content-crypto preparation with network writes. */ -int netfs_advance_write(struct netfs_io_request *wreq, - struct netfs_io_stream *stream, - loff_t start, size_t len, bool to_eof) +size_t netfs_advance_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start, size_t len, bool to_eof) { struct netfs_io_subrequest *subreq = stream->construct; size_t part; @@ -325,6 +333,9 @@ static int netfs_write_folio(struct netfs_io_request *wreq, _enter(""); + if (rolling_buffer_make_space(&wreq->buffer) < 0) + return -ENOMEM; + /* netfs_perform_write() may shift i_size around the page or from out * of the page to beyond it, but cannot move i_size into or through the * page since we have it locked. @@ -429,7 +440,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, } /* Attach the folio to the rolling buffer. */ - netfs_buffer_append_folio(wreq, folio, false); + rolling_buffer_append(&wreq->buffer, folio, 0); /* Move the submission point forward to allow for write-streaming data * not starting at the front of the page. We don't do write-streaming @@ -442,7 +453,8 @@ static int netfs_write_folio(struct netfs_io_request *wreq, stream = &wreq->io_streams[s]; stream->submit_off = foff; stream->submit_len = flen; - if ((stream->source == NETFS_WRITE_TO_CACHE && streamw) || + if (!stream->avail || + (stream->source == NETFS_WRITE_TO_CACHE && streamw) || (stream->source == NETFS_UPLOAD_TO_SERVER && fgroup == NETFS_FOLIO_COPY_TO_CACHE)) { stream->submit_off = UINT_MAX; @@ -476,7 +488,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, /* Advance the iterator(s). */ if (stream->submit_off > iter_off) { - iov_iter_advance(&wreq->io_iter, stream->submit_off - iter_off); + rolling_buffer_advance(&wreq->buffer, stream->submit_off - iter_off); iter_off = stream->submit_off; } @@ -494,7 +506,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, } if (fsize > iter_off) - iov_iter_advance(&wreq->io_iter, fsize - iter_off); + rolling_buffer_advance(&wreq->buffer, fsize - iter_off); atomic64_set(&wreq->issued_to, fpos + fsize); if (!debug) @@ -633,7 +645,7 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c struct folio **writethrough_cache) { _enter("R=%x ic=%zu ws=%u cp=%zu tp=%u", - wreq->debug_id, wreq->iter.count, wreq->wsize, copied, to_page_end); + wreq->debug_id, wreq->buffer.iter.count, wreq->wsize, copied, to_page_end); if (!*writethrough_cache) { if (folio_test_dirty(folio)) @@ -708,10 +720,10 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t part = netfs_advance_write(wreq, upload, start, len, false); start += part; len -= part; - iov_iter_advance(&wreq->io_iter, part); + rolling_buffer_advance(&wreq->buffer, part); if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { trace_netfs_rreq(wreq, netfs_rreq_trace_wait_pause); - wait_on_bit(&wreq->flags, NETFS_RREQ_PAUSE, TASK_UNINTERRUPTIBLE); + wait_event(wreq->waitq, !test_bit(NETFS_RREQ_PAUSE, &wreq->flags)); } if (test_bit(NETFS_RREQ_FAILED, &wreq->flags)) break; @@ -721,3 +733,194 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t _leave(" = %d", error); return error; } + +/* + * Write some of a pending folio data back to the server and/or the cache. + */ +static int netfs_write_folio_single(struct netfs_io_request *wreq, + struct folio *folio) +{ + struct netfs_io_stream *upload = &wreq->io_streams[0]; + struct netfs_io_stream *cache = &wreq->io_streams[1]; + struct netfs_io_stream *stream; + size_t iter_off = 0; + size_t fsize = folio_size(folio), flen; + loff_t fpos = folio_pos(folio); + bool to_eof = false; + bool no_debug = false; + + _enter(""); + + flen = folio_size(folio); + if (flen > wreq->i_size - fpos) { + flen = wreq->i_size - fpos; + folio_zero_segment(folio, flen, fsize); + to_eof = true; + } else if (flen == wreq->i_size - fpos) { + to_eof = true; + } + + _debug("folio %zx/%zx", flen, fsize); + + if (!upload->avail && !cache->avail) { + trace_netfs_folio(folio, netfs_folio_trace_cancel_store); + return 0; + } + + if (!upload->construct) + trace_netfs_folio(folio, netfs_folio_trace_store); + else + trace_netfs_folio(folio, netfs_folio_trace_store_plus); + + /* Attach the folio to the rolling buffer. */ + folio_get(folio); + rolling_buffer_append(&wreq->buffer, folio, NETFS_ROLLBUF_PUT_MARK); + + /* Move the submission point forward to allow for write-streaming data + * not starting at the front of the page. We don't do write-streaming + * with the cache as the cache requires DIO alignment. + * + * Also skip uploading for data that's been read and just needs copying + * to the cache. + */ + for (int s = 0; s < NR_IO_STREAMS; s++) { + stream = &wreq->io_streams[s]; + stream->submit_off = 0; + stream->submit_len = flen; + if (!stream->avail) { + stream->submit_off = UINT_MAX; + stream->submit_len = 0; + } + } + + /* Attach the folio to one or more subrequests. For a big folio, we + * could end up with thousands of subrequests if the wsize is small - + * but we might need to wait during the creation of subrequests for + * network resources (eg. SMB credits). + */ + for (;;) { + ssize_t part; + size_t lowest_off = ULONG_MAX; + int choose_s = -1; + + /* Always add to the lowest-submitted stream first. */ + for (int s = 0; s < NR_IO_STREAMS; s++) { + stream = &wreq->io_streams[s]; + if (stream->submit_len > 0 && + stream->submit_off < lowest_off) { + lowest_off = stream->submit_off; + choose_s = s; + } + } + + if (choose_s < 0) + break; + stream = &wreq->io_streams[choose_s]; + + /* Advance the iterator(s). */ + if (stream->submit_off > iter_off) { + rolling_buffer_advance(&wreq->buffer, stream->submit_off - iter_off); + iter_off = stream->submit_off; + } + + atomic64_set(&wreq->issued_to, fpos + stream->submit_off); + stream->submit_extendable_to = fsize - stream->submit_off; + part = netfs_advance_write(wreq, stream, fpos + stream->submit_off, + stream->submit_len, to_eof); + stream->submit_off += part; + if (part > stream->submit_len) + stream->submit_len = 0; + else + stream->submit_len -= part; + if (part > 0) + no_debug = true; + } + + wreq->buffer.iter.iov_offset = 0; + if (fsize > iter_off) + rolling_buffer_advance(&wreq->buffer, fsize - iter_off); + atomic64_set(&wreq->issued_to, fpos + fsize); + + if (!no_debug) + kdebug("R=%x: No submit", wreq->debug_id); + _leave(" = 0"); + return 0; +} + +/** + * netfs_writeback_single - Write back a monolithic payload + * @mapping: The mapping to write from + * @wbc: Hints from the VM + * @iter: Data to write, must be ITER_FOLIOQ. + * + * Write a monolithic, non-pagecache object back to the server and/or + * the cache. + */ +int netfs_writeback_single(struct address_space *mapping, + struct writeback_control *wbc, + struct iov_iter *iter) +{ + struct netfs_io_request *wreq; + struct netfs_inode *ictx = netfs_inode(mapping->host); + struct folio_queue *fq; + size_t size = iov_iter_count(iter); + int ret; + + if (WARN_ON_ONCE(!iov_iter_is_folioq(iter))) + return -EIO; + + if (!mutex_trylock(&ictx->wb_lock)) { + if (wbc->sync_mode == WB_SYNC_NONE) { + netfs_stat(&netfs_n_wb_lock_skip); + return 0; + } + netfs_stat(&netfs_n_wb_lock_wait); + mutex_lock(&ictx->wb_lock); + } + + wreq = netfs_create_write_req(mapping, NULL, 0, NETFS_WRITEBACK_SINGLE); + if (IS_ERR(wreq)) { + ret = PTR_ERR(wreq); + goto couldnt_start; + } + + trace_netfs_write(wreq, netfs_write_trace_writeback); + netfs_stat(&netfs_n_wh_writepages); + + if (__test_and_set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags)) + wreq->netfs_ops->begin_writeback(wreq); + + for (fq = (struct folio_queue *)iter->folioq; fq; fq = fq->next) { + for (int slot = 0; slot < folioq_count(fq); slot++) { + struct folio *folio = folioq_folio(fq, slot); + size_t part = umin(folioq_folio_size(fq, slot), size); + + _debug("wbiter %lx %llx", folio->index, atomic64_read(&wreq->issued_to)); + + ret = netfs_write_folio_single(wreq, folio); + if (ret < 0) + goto stop; + size -= part; + if (size <= 0) + goto stop; + } + } + +stop: + for (int s = 0; s < NR_IO_STREAMS; s++) + netfs_issue_write(wreq, &wreq->io_streams[s]); + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); + + mutex_unlock(&ictx->wb_lock); + + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + _leave(" = %d", ret); + return ret; + +couldnt_start: + mutex_unlock(&ictx->wb_lock); + _leave(" = %d", ret); + return ret; +} +EXPORT_SYMBOL(netfs_writeback_single); diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c new file mode 100644 index 000000000000..c841a851dd73 --- /dev/null +++ b/fs/netfs/write_retry.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Network filesystem write retrying. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include "internal.h" + +/* + * Perform retries on the streams that need it. + */ +static void netfs_retry_write_stream(struct netfs_io_request *wreq, + struct netfs_io_stream *stream) +{ + struct list_head *next; + + _enter("R=%x[%x:]", wreq->debug_id, stream->stream_nr); + + if (list_empty(&stream->subrequests)) + return; + + if (stream->source == NETFS_UPLOAD_TO_SERVER && + wreq->netfs_ops->retry_request) + wreq->netfs_ops->retry_request(wreq, stream); + + if (unlikely(stream->failed)) + return; + + /* If there's no renegotiation to do, just resend each failed subreq. */ + if (!stream->prepare_write) { + struct netfs_io_subrequest *subreq; + + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { + if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) + break; + if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + struct iov_iter source = subreq->io_iter; + + iov_iter_revert(&source, subreq->len - source.count); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + netfs_reissue_write(stream, subreq, &source); + } + } + return; + } + + next = stream->subrequests.next; + + do { + struct netfs_io_subrequest *subreq = NULL, *from, *to, *tmp; + struct iov_iter source; + unsigned long long start, len; + size_t part; + bool boundary = false; + + /* Go through the stream and find the next span of contiguous + * data that we then rejig (cifs, for example, needs the wsize + * renegotiating) and reissue. + */ + from = list_entry(next, struct netfs_io_subrequest, rreq_link); + to = from; + start = from->start + from->transferred; + len = from->len - from->transferred; + + if (test_bit(NETFS_SREQ_FAILED, &from->flags) || + !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) + return; + + list_for_each_continue(next, &stream->subrequests) { + subreq = list_entry(next, struct netfs_io_subrequest, rreq_link); + if (subreq->start + subreq->transferred != start + len || + test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags) || + !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) + break; + to = subreq; + len += to->len; + } + + /* Determine the set of buffers we're going to use. Each + * subreq gets a subset of a single overall contiguous buffer. + */ + netfs_reset_iter(from); + source = from->io_iter; + source.count = len; + + /* Work through the sublist. */ + subreq = from; + list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { + if (!len) + break; + + subreq->start = start; + subreq->len = len; + __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + subreq->retry_count++; + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + + /* Renegotiate max_len (wsize) */ + stream->sreq_max_len = len; + stream->prepare_write(subreq); + + part = umin(len, stream->sreq_max_len); + if (unlikely(stream->sreq_max_segs)) + part = netfs_limit_iter(&source, 0, part, stream->sreq_max_segs); + subreq->len = part; + subreq->transferred = 0; + len -= part; + start += part; + if (len && subreq == to && + __test_and_clear_bit(NETFS_SREQ_BOUNDARY, &to->flags)) + boundary = true; + + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + netfs_reissue_write(stream, subreq, &source); + if (subreq == to) + break; + } + + /* If we managed to use fewer subreqs, we can discard the + * excess; if we used the same number, then we're done. + */ + if (!len) { + if (subreq == to) + continue; + list_for_each_entry_safe_from(subreq, tmp, + &stream->subrequests, rreq_link) { + trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + list_del(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); + if (subreq == to) + break; + } + continue; + } + + /* We ran out of subrequests, so we need to allocate some more + * and insert them after. + */ + do { + subreq = netfs_alloc_subrequest(wreq); + subreq->source = to->source; + subreq->start = start; + subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); + subreq->stream_nr = to->stream_nr; + subreq->retry_count = 1; + + trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, + refcount_read(&subreq->ref), + netfs_sreq_trace_new); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + + list_add(&subreq->rreq_link, &to->rreq_link); + to = list_next_entry(to, rreq_link); + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + + stream->sreq_max_len = len; + stream->sreq_max_segs = INT_MAX; + switch (stream->source) { + case NETFS_UPLOAD_TO_SERVER: + netfs_stat(&netfs_n_wh_upload); + stream->sreq_max_len = umin(len, wreq->wsize); + break; + case NETFS_WRITE_TO_CACHE: + netfs_stat(&netfs_n_wh_write); + break; + default: + WARN_ON_ONCE(1); + } + + stream->prepare_write(subreq); + + part = umin(len, stream->sreq_max_len); + subreq->len = subreq->transferred + part; + len -= part; + start += part; + if (!len && boundary) { + __set_bit(NETFS_SREQ_BOUNDARY, &to->flags); + boundary = false; + } + + netfs_reissue_write(stream, subreq, &source); + if (!len) + break; + + } while (len); + + } while (!list_is_head(next, &stream->subrequests)); +} + +/* + * Perform retries on the streams that need it. If we're doing content + * encryption and the server copy changed due to a third-party write, we may + * need to do an RMW cycle and also rewrite the data to the cache. + */ +void netfs_retry_writes(struct netfs_io_request *wreq) +{ + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream; + int s; + + /* Wait for all outstanding I/O to quiesce before performing retries as + * we may need to renegotiate the I/O sizes. + */ + for (s = 0; s < NR_IO_STREAMS; s++) { + stream = &wreq->io_streams[s]; + if (!stream->active) + continue; + + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { + wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); + } + } + + // TODO: Enc: Fetch changed partial pages + // TODO: Enc: Reencrypt content if needed. + // TODO: Enc: Wind back transferred point. + // TODO: Enc: Mark cache pages for retry. + + for (s = 0; s < NR_IO_STREAMS; s++) { + stream = &wreq->io_streams[s]; + if (stream->need_retry) { + stream->need_retry = false; + netfs_retry_write_stream(wreq, stream); + } + } +} diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 0eb20012792f..d3f76101ad4b 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -170,7 +170,8 @@ config ROOT_NFS config NFS_FSCACHE bool "Provide NFS client caching support" - depends on NFS_FS=m && NETFS_SUPPORT || NFS_FS=y && NETFS_SUPPORT=y + depends on NFS_FS + select NETFS_SUPPORT select FSCACHE help Say Y here if you want NFS data to be cached locally on disc through diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 6cf92498a5ac..86bdc7d23fb9 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -211,10 +211,6 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion) return ERR_PTR(-ENOMEM); } cb_info->serv = serv; - /* As there is only one thread we need to over-ride the - * default maximum of 80 connections - */ - serv->sv_maxconn = 1024; dprintk("nfs_callback_create_svc: service created\n"); return serv; } diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 7832fb0369a1..8397c43358bd 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -718,7 +718,7 @@ __be32 nfs4_callback_offload(void *data, void *dummy, copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_KERNEL); if (!copy) - return htonl(NFS4ERR_SERVERFAULT); + return cpu_to_be32(NFS4ERR_DELAY); spin_lock(&cps->clp->cl_lock); rcu_read_lock(); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index fdeb0b34a3d3..4254ba3ee7c5 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -984,6 +984,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp) nfs_put_client(cps.clp); goto out_invalidcred; } + svc_xprt_set_valid(rqstp->rq_xprt); } cps.minorversion = hdr_arg.minorversion; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 550ca934c9cf..3b0918ade53c 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -38,7 +38,7 @@ #include #include #include - +#include #include "nfs4_fs.h" #include "callback.h" @@ -186,7 +186,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) seqlock_init(&clp->cl_boot_lock); ktime_get_real_ts64(&clp->cl_nfssvc_boot); nfs_uuid_init(&clp->cl_uuid); - spin_lock_init(&clp->cl_localio_lock); + INIT_WORK(&clp->cl_local_probe_work, nfs_local_probe_async_work); #endif /* CONFIG_NFS_LOCALIO */ clp->cl_principal = "*"; @@ -244,7 +244,7 @@ static void pnfs_init_server(struct nfs_server *server) */ void nfs_free_client(struct nfs_client *clp) { - nfs_local_disable(clp); + nfs_localio_disable_client(clp); /* -EIO all pending I/O */ if (!IS_ERR(clp->cl_rpcclient)) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 492cffd9d3d8..2b04038b0e40 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1672,7 +1672,7 @@ nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry, return nfs_lookup_revalidate_done(dir, dentry, inode, 1); } -static int nfs_lookup_revalidate_dentry(struct inode *dir, +static int nfs_lookup_revalidate_dentry(struct inode *dir, const struct qstr *name, struct dentry *dentry, struct inode *inode, unsigned int flags) { @@ -1690,7 +1690,7 @@ static int nfs_lookup_revalidate_dentry(struct inode *dir, goto out; dir_verifier = nfs_save_change_attribute(dir); - ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); + ret = NFS_PROTO(dir)->lookup(dir, dentry, name, fhandle, fattr); if (ret < 0) goto out; @@ -1732,8 +1732,8 @@ out: * cached dentry and do a new lookup. */ static int -nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, - unsigned int flags) +nfs_do_lookup_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; int error = 0; @@ -1775,7 +1775,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, if (NFS_STALE(inode)) goto out_bad; - return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags); + return nfs_lookup_revalidate_dentry(dir, name, dentry, inode, flags); out_valid: return nfs_lookup_revalidate_done(dir, dentry, inode, 1); out_bad: @@ -1785,38 +1785,26 @@ out_bad: } static int -__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags, - int (*reval)(struct inode *, struct dentry *, unsigned int)) +__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { - struct dentry *parent; - struct inode *dir; - int ret; - if (flags & LOOKUP_RCU) { if (dentry->d_fsdata == NFS_FSDATA_BLOCKED) return -ECHILD; - parent = READ_ONCE(dentry->d_parent); - dir = d_inode_rcu(parent); - if (!dir) - return -ECHILD; - ret = reval(dir, dentry, flags); - if (parent != READ_ONCE(dentry->d_parent)) - return -ECHILD; } else { /* Wait for unlink to complete - see unblock_revalidate() */ wait_var_event(&dentry->d_fsdata, smp_load_acquire(&dentry->d_fsdata) != NFS_FSDATA_BLOCKED); - parent = dget_parent(dentry); - ret = reval(d_inode(parent), dentry, flags); - dput(parent); } - return ret; + return 0; } -static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) +static int nfs_lookup_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate); + if (__nfs_lookup_revalidate(dentry, flags)) + return -ECHILD; + return nfs_do_lookup_revalidate(dir, name, dentry, flags); } static void block_revalidate(struct dentry *dentry) @@ -1982,7 +1970,8 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in dir_verifier = nfs_save_change_attribute(dir); trace_nfs_lookup_enter(dir, dentry, flags); - error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, dentry, &dentry->d_name, + fhandle, fattr); if (error == -ENOENT) { if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) dir_verifier = inode_peek_iversion_raw(dir); @@ -2025,7 +2014,8 @@ void nfs_d_prune_case_insensitive_aliases(struct inode *inode) EXPORT_SYMBOL_GPL(nfs_d_prune_case_insensitive_aliases); #if IS_ENABLED(CONFIG_NFS_V4) -static int nfs4_lookup_revalidate(struct dentry *, unsigned int); +static int nfs4_lookup_revalidate(struct inode *, const struct qstr *, + struct dentry *, unsigned int); const struct dentry_operations nfs4_dentry_operations = { .d_revalidate = nfs4_lookup_revalidate, @@ -2214,11 +2204,14 @@ no_open: EXPORT_SYMBOL_GPL(nfs_atomic_open); static int -nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, - unsigned int flags) +nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; + if (__nfs_lookup_revalidate(dentry, flags)) + return -ECHILD; + trace_nfs_lookup_revalidate_enter(dir, dentry, flags); if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY)) @@ -2254,16 +2247,10 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, reval_dentry: if (flags & LOOKUP_RCU) return -ECHILD; - return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags); + return nfs_lookup_revalidate_dentry(dir, name, dentry, inode, flags); full_reval: - return nfs_do_lookup_revalidate(dir, dentry, flags); -} - -static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) -{ - return __nfs_lookup_revalidate(dentry, flags, - nfs4_do_lookup_revalidate); + return nfs_do_lookup_revalidate(dir, name, dentry, flags); } #endif /* CONFIG_NFSV4 */ @@ -2319,7 +2306,8 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, d_drop(dentry); if (fhandle->size == 0) { - error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, dentry, &dentry->d_name, + fhandle, fattr); if (error) goto out_error; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index b08dbe96bc57..f45beea92d03 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -303,6 +303,7 @@ static void nfs_read_sync_pgio_error(struct list_head *head, int error) static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr) { get_dreq(hdr->dreq); + set_bit(NFS_IOHDR_ODIRECT, &hdr->flags); } static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = { diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index f78115c6c2c1..98b45b636be3 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -164,18 +164,17 @@ decode_name(struct xdr_stream *xdr, u32 *id) } static struct nfsd_file * -ff_local_open_fh(struct nfs_client *clp, const struct cred *cred, +ff_local_open_fh(struct pnfs_layout_segment *lseg, u32 ds_idx, + struct nfs_client *clp, const struct cred *cred, struct nfs_fh *fh, fmode_t mode) { - if (mode & FMODE_WRITE) { - /* - * Always request read and write access since this corresponds - * to a rw layout. - */ - mode |= FMODE_READ; - } +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); - return nfs_local_open_fh(clp, cred, fh, mode); + return nfs_local_open_fh(clp, cred, fh, &mirror->nfl, mode); +#else + return NULL; +#endif } static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1, @@ -247,6 +246,7 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags) spin_lock_init(&mirror->lock); refcount_set(&mirror->ref, 1); INIT_LIST_HEAD(&mirror->mirrors); + nfs_localio_file_init(&mirror->nfl); } return mirror; } @@ -257,6 +257,7 @@ static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror) ff_layout_remove_mirror(mirror); kfree(mirror->fh_versions); + nfs_close_local_fh(&mirror->nfl); cred = rcu_access_pointer(mirror->ro_cred); put_cred(cred); cred = rcu_access_pointer(mirror->rw_cred); @@ -847,6 +848,9 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs4_pnfs_ds *ds; u32 ds_idx; + if (NFS_SERVER(pgio->pg_inode)->flags & + (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) + pgio->pg_maxretrans = io_maxretrans; retry: pnfs_generic_pg_check_layout(pgio, req); /* Use full layout for now */ @@ -860,6 +864,8 @@ retry: if (!pgio->pg_lseg) goto out_nolseg; } + /* Reset wb_nio, since getting layout segment was successful */ + req->wb_nio = 0; ds = ff_layout_get_ds_for_read(pgio, &ds_idx); if (!ds) { @@ -876,14 +882,24 @@ retry: pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; pgio->pg_mirror_idx = ds_idx; - - if (NFS_SERVER(pgio->pg_inode)->flags & - (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) - pgio->pg_maxretrans = io_maxretrans; return; out_nolseg: - if (pgio->pg_error < 0) - return; + if (pgio->pg_error < 0) { + if (pgio->pg_error != -EAGAIN) + return; + /* Retry getting layout segment if lower layer returned -EAGAIN */ + if (pgio->pg_maxretrans && req->wb_nio++ > pgio->pg_maxretrans) { + if (NFS_SERVER(pgio->pg_inode)->flags & NFS_MOUNT_SOFTERR) + pgio->pg_error = -ETIMEDOUT; + else + pgio->pg_error = -EIO; + return; + } + pgio->pg_error = 0; + /* Sleep for 1 second before retrying */ + ssleep(1); + goto retry; + } out_mds: trace_pnfs_mds_fallback_pg_init_read(pgio->pg_inode, 0, NFS4_MAX_UINT64, IOMODE_READ, @@ -1820,7 +1836,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) hdr->mds_offset = offset; /* Start IO accounting for local read */ - localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, FMODE_READ); + localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh, FMODE_READ); if (localio) { hdr->task.tk_start = ktime_get(); ff_layout_read_record_layoutstats_start(&hdr->task, hdr); @@ -1896,7 +1912,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) hdr->args.offset = offset; /* Start IO accounting for local write */ - localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, + localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh, FMODE_READ|FMODE_WRITE); if (localio) { hdr->task.tk_start = ktime_get(); @@ -1981,7 +1997,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) data->args.fh = fh; /* Start IO accounting for local commit */ - localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, + localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh, FMODE_READ|FMODE_WRITE); if (localio) { data->task.tk_start = ktime_get(); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index f84b3fb0dddd..095df09017a5 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -83,6 +83,7 @@ struct nfs4_ff_layout_mirror { nfs4_stateid stateid; const struct cred __rcu *ro_cred; const struct cred __rcu *rw_cred; + struct nfs_file_localio nfl; refcount_t ref; spinlock_t lock; unsigned long flags; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 810269ee0a50..e278a1ad1ca3 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -263,6 +263,12 @@ int nfs_netfs_readahead(struct readahead_control *ractl) static atomic_t nfs_netfs_debug_id; static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *file) { + if (!file) { + if (WARN_ON_ONCE(rreq->origin != NETFS_PGPRIV2_COPY_TO_CACHE)) + return -EIO; + return 0; + } + rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ @@ -274,7 +280,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi static void nfs_netfs_free_request(struct netfs_io_request *rreq) { - put_nfs_open_context(rreq->netfs_priv); + if (rreq->netfs_priv) + put_nfs_open_context(rreq->netfs_priv); } static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq) @@ -307,8 +314,10 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) &nfs_async_read_completion_ops); netfs = nfs_netfs_alloc(sreq); - if (!netfs) - return netfs_read_subreq_terminated(sreq, -ENOMEM, false); + if (!netfs) { + sreq->error = -ENOMEM; + return netfs_read_subreq_terminated(sreq); + } pgio.pg_netfs = netfs; /* used in completion */ diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 772d485e96d3..9d86868f4998 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -74,7 +74,8 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) */ netfs->sreq->transferred = min_t(s64, netfs->sreq->len, atomic64_read(&netfs->transferred)); - netfs_read_subreq_terminated(netfs->sreq, netfs->error, false); + netfs->sreq->error = netfs->error; + netfs_read_subreq_terminated(netfs->sreq); kfree(netfs); } static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 596f35170137..1aa67fca69b2 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1137,6 +1137,8 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); ctx->mdsthreshold = NULL; + nfs_localio_file_init(&ctx->nfl); + return ctx; } EXPORT_SYMBOL_GPL(alloc_nfs_open_context); @@ -1168,6 +1170,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) nfs_sb_deactive(sb); put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1)); kfree(ctx->mdsthreshold); + nfs_close_local_fh(&ctx->nfl); kfree_rcu(ctx, rcu_head); } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index e564bd11ba60..fae2c7ae4acc 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -455,11 +455,13 @@ extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); #if IS_ENABLED(CONFIG_NFS_LOCALIO) /* localio.c */ -extern void nfs_local_disable(struct nfs_client *); extern void nfs_local_probe(struct nfs_client *); +extern void nfs_local_probe_async(struct nfs_client *); +extern void nfs_local_probe_async_work(struct work_struct *); extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *, const struct cred *, struct nfs_fh *, + struct nfs_file_localio *, const fmode_t); extern int nfs_local_doio(struct nfs_client *, struct nfsd_file *, @@ -471,11 +473,12 @@ extern int nfs_local_commit(struct nfsd_file *, extern bool nfs_server_is_local(const struct nfs_client *clp); #else /* CONFIG_NFS_LOCALIO */ -static inline void nfs_local_disable(struct nfs_client *clp) {} static inline void nfs_local_probe(struct nfs_client *clp) {} +static inline void nfs_local_probe_async(struct nfs_client *clp) {} static inline struct nfsd_file * nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, - struct nfs_fh *fh, const fmode_t mode) + struct nfs_fh *fh, struct nfs_file_localio *nfl, + const fmode_t mode) { return NULL; } diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index 4b8618cf114c..5c21caeae075 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -35,6 +35,7 @@ struct nfs_local_kiocb { struct bio_vec *bvec; struct nfs_pgio_header *hdr; struct work_struct work; + void (*aio_complete_work)(struct work_struct *); struct nfsd_file *localio; }; @@ -48,9 +49,14 @@ struct nfs_local_fsync_ctx { static bool localio_enabled __read_mostly = true; module_param(localio_enabled, bool, 0644); +static bool localio_O_DIRECT_semantics __read_mostly = false; +module_param(localio_O_DIRECT_semantics, bool, 0644); +MODULE_PARM_DESC(localio_O_DIRECT_semantics, + "LOCALIO will use O_DIRECT semantics to filesystem."); + static inline bool nfs_client_is_local(const struct nfs_client *clp) { - return !!test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags); + return !!rcu_access_pointer(clp->cl_uuid.net); } bool nfs_server_is_local(const struct nfs_client *clp) @@ -115,30 +121,6 @@ const struct rpc_program nfslocalio_program = { .stats = &nfslocalio_rpcstat, }; -/* - * nfs_local_enable - enable local i/o for an nfs_client - */ -static void nfs_local_enable(struct nfs_client *clp) -{ - spin_lock(&clp->cl_localio_lock); - set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags); - trace_nfs_local_enable(clp); - spin_unlock(&clp->cl_localio_lock); -} - -/* - * nfs_local_disable - disable local i/o for an nfs_client - */ -void nfs_local_disable(struct nfs_client *clp) -{ - spin_lock(&clp->cl_localio_lock); - if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) { - trace_nfs_local_disable(clp); - nfs_uuid_invalidate_one_client(&clp->cl_uuid); - } - spin_unlock(&clp->cl_localio_lock); -} - /* * nfs_init_localioclient - Initialise an NFS localio client connection */ @@ -178,7 +160,7 @@ static bool nfs_server_uuid_is_local(struct nfs_client *clp) rpc_shutdown_client(rpcclient_localio); /* Server is only local if it initialized required struct members */ - if (status || !clp->cl_uuid.net || !clp->cl_uuid.dom) + if (status || !rcu_access_pointer(clp->cl_uuid.net) || !clp->cl_uuid.dom) return false; return true; @@ -194,44 +176,64 @@ void nfs_local_probe(struct nfs_client *clp) /* Disallow localio if disabled via sysfs or AUTH_SYS isn't used */ if (!localio_enabled || clp->cl_rpcclient->cl_auth->au_flavor != RPC_AUTH_UNIX) { - nfs_local_disable(clp); + nfs_localio_disable_client(clp); return; } if (nfs_client_is_local(clp)) { /* If already enabled, disable and re-enable */ - nfs_local_disable(clp); + nfs_localio_disable_client(clp); } if (!nfs_uuid_begin(&clp->cl_uuid)) return; if (nfs_server_uuid_is_local(clp)) - nfs_local_enable(clp); + nfs_localio_enable_client(clp); nfs_uuid_end(&clp->cl_uuid); } EXPORT_SYMBOL_GPL(nfs_local_probe); +void nfs_local_probe_async_work(struct work_struct *work) +{ + struct nfs_client *clp = + container_of(work, struct nfs_client, cl_local_probe_work); + + nfs_local_probe(clp); +} + +void nfs_local_probe_async(struct nfs_client *clp) +{ + queue_work(nfsiod_workqueue, &clp->cl_local_probe_work); +} +EXPORT_SYMBOL_GPL(nfs_local_probe_async); + +static inline struct nfsd_file *nfs_local_file_get(struct nfsd_file *nf) +{ + return nfs_to->nfsd_file_get(nf); +} + +static inline void nfs_local_file_put(struct nfsd_file *nf) +{ + nfs_to->nfsd_file_put(nf); +} + /* - * nfs_local_open_fh - open a local filehandle in terms of nfsd_file + * __nfs_local_open_fh - open a local filehandle in terms of nfsd_file. * - * Returns a pointer to a struct nfsd_file or NULL + * Returns a pointer to a struct nfsd_file or ERR_PTR. + * Caller must release returned nfsd_file with nfs_to_nfsd_file_put_local(). */ -struct nfsd_file * -nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, - struct nfs_fh *fh, const fmode_t mode) +static struct nfsd_file * +__nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, struct nfs_file_localio *nfl, + const fmode_t mode) { struct nfsd_file *localio; - int status; - - if (!nfs_server_is_local(clp)) - return NULL; - if (mode & ~(FMODE_READ | FMODE_WRITE)) - return NULL; localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient, - cred, fh, mode); + cred, fh, nfl, mode); if (IS_ERR(localio)) { - status = PTR_ERR(localio); + int status = PTR_ERR(localio); trace_nfs_local_open_fh(fh, mode, status); switch (status) { case -ENOMEM: @@ -240,10 +242,59 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, /* Revalidate localio, will disable if unsupported */ nfs_local_probe(clp); } - return NULL; } return localio; } + +/* + * nfs_local_open_fh - open a local filehandle in terms of nfsd_file. + * First checking if the open nfsd_file is already cached, otherwise + * must __nfs_local_open_fh and insert the nfsd_file in nfs_file_localio. + * + * Returns a pointer to a struct nfsd_file or NULL. + */ +struct nfsd_file * +nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, struct nfs_file_localio *nfl, + const fmode_t mode) +{ + struct nfsd_file *nf, *new, __rcu **pnf; + + if (!nfs_server_is_local(clp)) + return NULL; + if (mode & ~(FMODE_READ | FMODE_WRITE)) + return NULL; + + if (mode & FMODE_WRITE) + pnf = &nfl->rw_file; + else + pnf = &nfl->ro_file; + + new = NULL; + rcu_read_lock(); + nf = rcu_dereference(*pnf); + if (!nf) { + rcu_read_unlock(); + new = __nfs_local_open_fh(clp, cred, fh, nfl, mode); + if (IS_ERR(new)) + return NULL; + /* try to swap in the pointer */ + spin_lock(&clp->cl_uuid.lock); + nf = rcu_dereference_protected(*pnf, 1); + if (!nf) { + nf = new; + new = NULL; + rcu_assign_pointer(*pnf, nf); + } + spin_unlock(&clp->cl_uuid.lock); + rcu_read_lock(); + } + nf = nfs_local_file_get(nf); + rcu_read_unlock(); + if (new) + nfs_to_nfsd_file_put_local(new); + return nf; +} EXPORT_SYMBOL_GPL(nfs_local_open_fh); static struct bio_vec * @@ -285,10 +336,19 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, kfree(iocb); return NULL; } - init_sync_kiocb(&iocb->kiocb, file); + + if (localio_O_DIRECT_semantics && + test_bit(NFS_IOHDR_ODIRECT, &hdr->flags)) { + iocb->kiocb.ki_filp = file; + iocb->kiocb.ki_flags = IOCB_DIRECT; + } else + init_sync_kiocb(&iocb->kiocb, file); + iocb->kiocb.ki_pos = hdr->args.offset; iocb->hdr = hdr; iocb->kiocb.ki_flags &= ~IOCB_APPEND; + iocb->aio_complete_work = NULL; + return iocb; } @@ -328,7 +388,7 @@ nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status) hdr->res.op_status = NFS4_OK; hdr->task.tk_status = 0; } else { - hdr->res.op_status = nfs4_stat_to_errno(status); + hdr->res.op_status = nfs_localio_errno_to_nfs4_stat(status); hdr->task.tk_status = status; } } @@ -338,11 +398,23 @@ nfs_local_pgio_release(struct nfs_local_kiocb *iocb) { struct nfs_pgio_header *hdr = iocb->hdr; - nfs_to_nfsd_file_put_local(iocb->localio); + nfs_local_file_put(iocb->localio); nfs_local_iocb_free(iocb); nfs_local_hdr_release(hdr, hdr->task.tk_ops); } +/* + * Complete the I/O from iocb->kiocb.ki_complete() + * + * Note that this function can be called from a bottom half context, + * hence we need to queue the rpc_call_done() etc to a workqueue + */ +static inline void nfs_local_pgio_aio_complete(struct nfs_local_kiocb *iocb) +{ + INIT_WORK(&iocb->work, iocb->aio_complete_work); + queue_work(nfsiod_workqueue, &iocb->work); +} + static void nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) { @@ -365,6 +437,23 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) status > 0 ? status : 0, hdr->res.eof); } +static void nfs_local_read_aio_complete_work(struct work_struct *work) +{ + struct nfs_local_kiocb *iocb = + container_of(work, struct nfs_local_kiocb, work); + + nfs_local_pgio_release(iocb); +} + +static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret) +{ + struct nfs_local_kiocb *iocb = + container_of(kiocb, struct nfs_local_kiocb, kiocb); + + nfs_local_read_done(iocb, ret); + nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_read_aio_complete_work */ +} + static void nfs_local_call_read(struct work_struct *work) { struct nfs_local_kiocb *iocb = @@ -379,10 +468,10 @@ static void nfs_local_call_read(struct work_struct *work) nfs_local_iter_init(&iter, iocb, READ); status = filp->f_op->read_iter(&iocb->kiocb, &iter); - WARN_ON_ONCE(status == -EIOCBQUEUED); - - nfs_local_read_done(iocb, status); - nfs_local_pgio_release(iocb); + if (status != -EIOCBQUEUED) { + nfs_local_read_done(iocb, status); + nfs_local_pgio_release(iocb); + } revert_creds(save_cred); } @@ -410,6 +499,11 @@ nfs_do_local_read(struct nfs_pgio_header *hdr, nfs_local_pgio_init(hdr, call_ops); hdr->res.eof = false; + if (iocb->kiocb.ki_flags & IOCB_DIRECT) { + iocb->kiocb.ki_complete = nfs_local_read_aio_complete; + iocb->aio_complete_work = nfs_local_read_aio_complete_work; + } + INIT_WORK(&iocb->work, nfs_local_call_read); queue_work(nfslocaliod_workqueue, &iocb->work); @@ -534,6 +628,24 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status) nfs_local_pgio_done(hdr, status); } +static void nfs_local_write_aio_complete_work(struct work_struct *work) +{ + struct nfs_local_kiocb *iocb = + container_of(work, struct nfs_local_kiocb, work); + + nfs_local_vfs_getattr(iocb); + nfs_local_pgio_release(iocb); +} + +static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret) +{ + struct nfs_local_kiocb *iocb = + container_of(kiocb, struct nfs_local_kiocb, kiocb); + + nfs_local_write_done(iocb, ret); + nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_write_aio_complete_work */ +} + static void nfs_local_call_write(struct work_struct *work) { struct nfs_local_kiocb *iocb = @@ -552,11 +664,11 @@ static void nfs_local_call_write(struct work_struct *work) file_start_write(filp); status = filp->f_op->write_iter(&iocb->kiocb, &iter); file_end_write(filp); - WARN_ON_ONCE(status == -EIOCBQUEUED); - - nfs_local_write_done(iocb, status); - nfs_local_vfs_getattr(iocb); - nfs_local_pgio_release(iocb); + if (status != -EIOCBQUEUED) { + nfs_local_write_done(iocb, status); + nfs_local_vfs_getattr(iocb); + nfs_local_pgio_release(iocb); + } revert_creds(save_cred); current->flags = old_flags; @@ -592,10 +704,16 @@ nfs_do_local_write(struct nfs_pgio_header *hdr, case NFS_FILE_SYNC: iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC; } + nfs_local_pgio_init(hdr, call_ops); nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable); + if (iocb->kiocb.ki_flags & IOCB_DIRECT) { + iocb->kiocb.ki_complete = nfs_local_write_aio_complete; + iocb->aio_complete_work = nfs_local_write_aio_complete_work; + } + INIT_WORK(&iocb->work, nfs_local_call_write); queue_work(nfslocaliod_workqueue, &iocb->work); @@ -626,8 +744,8 @@ int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio, if (status != 0) { if (status == -EAGAIN) - nfs_local_disable(clp); - nfs_to_nfsd_file_put_local(localio); + nfs_localio_disable_client(clp); + nfs_local_file_put(localio); hdr->task.tk_status = status; nfs_local_hdr_release(hdr, call_ops); } @@ -668,7 +786,7 @@ nfs_local_commit_done(struct nfs_commit_data *data, int status) data->task.tk_status = 0; } else { nfs_reset_boot_verifier(data->inode); - data->res.op_status = nfs4_stat_to_errno(status); + data->res.op_status = nfs_localio_errno_to_nfs4_stat(status); data->task.tk_status = status; } } @@ -678,7 +796,7 @@ nfs_local_release_commit_data(struct nfsd_file *localio, struct nfs_commit_data *data, const struct rpc_call_ops *call_ops) { - nfs_to_nfsd_file_put_local(localio); + nfs_local_file_put(localio); call_ops->rpc_call_done(&data->task, data); call_ops->rpc_release(data); } diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 2d53574da605..973aed9cc5fe 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -308,7 +308,7 @@ int nfs_submount(struct fs_context *fc, struct nfs_server *server) int err; /* Look it up again to get its attributes */ - err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, + err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, &dentry->d_name, ctx->mntfh, ctx->clone_data.fattr); dput(parent); if (err != 0) diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 1566163c6d85..0c3bc98cd999 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -192,7 +192,7 @@ __nfs3_proc_lookup(struct inode *dir, const char *name, size_t len, } static int -nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, +nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { unsigned short task_flags = 0; @@ -202,8 +202,7 @@ nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, task_flags |= RPC_TASK_TIMEOUT; dprintk("NFS call lookup %pd2\n", dentry); - return __nfs3_proc_lookup(dir, dentry->d_name.name, - dentry->d_name.len, fhandle, fattr, + return __nfs3_proc_lookup(dir, name->name, name->len, fhandle, fattr, task_flags); } @@ -844,6 +843,41 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, return status; } +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + +static unsigned nfs3_localio_probe_throttle __read_mostly = 0; +module_param(nfs3_localio_probe_throttle, uint, 0644); +MODULE_PARM_DESC(nfs3_localio_probe_throttle, + "Probe for NFSv3 LOCALIO every N IO requests. Must be power-of-2, defaults to 0 (probing disabled)."); + +static void nfs3_localio_probe(struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + + /* Throttled to reduce nfs_local_probe_async() frequency */ + if (!nfs3_localio_probe_throttle || nfs_server_is_local(clp)) + return; + + /* + * Try (re)enabling LOCALIO if isn't enabled -- admin deems + * it worthwhile to periodically check if LOCALIO possible by + * setting the 'nfs3_localio_probe_throttle' module parameter. + * + * This is useful if LOCALIO was previously enabled, but was + * disabled due to server restart, and IO has successfully + * completed in terms of normal RPC. + */ + if ((clp->cl_uuid.nfs3_localio_probe_count++ & + (nfs3_localio_probe_throttle - 1)) == 0) { + if (!nfs_server_is_local(clp)) + nfs_local_probe_async(clp); + } +} + +#else +static void nfs3_localio_probe(struct nfs_server *server) {} +#endif + static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { struct inode *inode = hdr->inode; @@ -855,8 +889,11 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; - if (task->tk_status >= 0 && !server->read_hdrsize) - cmpxchg(&server->read_hdrsize, 0, hdr->res.replen); + if (task->tk_status >= 0) { + if (!server->read_hdrsize) + cmpxchg(&server->read_hdrsize, 0, hdr->res.replen); + nfs3_localio_probe(server); + } nfs_invalidate_atime(inode); nfs_refresh_inode(inode, &hdr->fattr); @@ -886,8 +923,10 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr) if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; - if (task->tk_status >= 0) + if (task->tk_status >= 0) { nfs_writeback_update_inode(hdr); + nfs3_localio_probe(NFS_SERVER(inode)); + } return 0; } diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 531c9c20ef1d..1924c4a2077b 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -498,15 +498,15 @@ out_put_src_lock: return err; } -struct nfs42_offloadcancel_data { +struct nfs42_offload_data { struct nfs_server *seq_server; struct nfs42_offload_status_args args; struct nfs42_offload_status_res res; }; -static void nfs42_offload_cancel_prepare(struct rpc_task *task, void *calldata) +static void nfs42_offload_prepare(struct rpc_task *task, void *calldata) { - struct nfs42_offloadcancel_data *data = calldata; + struct nfs42_offload_data *data = calldata; nfs4_setup_sequence(data->seq_server->nfs_client, &data->args.osa_seq_args, @@ -515,7 +515,7 @@ static void nfs42_offload_cancel_prepare(struct rpc_task *task, void *calldata) static void nfs42_offload_cancel_done(struct rpc_task *task, void *calldata) { - struct nfs42_offloadcancel_data *data = calldata; + struct nfs42_offload_data *data = calldata; trace_nfs4_offload_cancel(&data->args, task->tk_status); nfs41_sequence_done(task, &data->res.osr_seq_res); @@ -525,22 +525,22 @@ static void nfs42_offload_cancel_done(struct rpc_task *task, void *calldata) rpc_restart_call_prepare(task); } -static void nfs42_free_offloadcancel_data(void *data) +static void nfs42_offload_release(void *data) { kfree(data); } static const struct rpc_call_ops nfs42_offload_cancel_ops = { - .rpc_call_prepare = nfs42_offload_cancel_prepare, + .rpc_call_prepare = nfs42_offload_prepare, .rpc_call_done = nfs42_offload_cancel_done, - .rpc_release = nfs42_free_offloadcancel_data, + .rpc_release = nfs42_offload_release, }; static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *stateid) { struct nfs_server *dst_server = NFS_SERVER(file_inode(dst)); - struct nfs42_offloadcancel_data *data = NULL; + struct nfs42_offload_data *data = NULL; struct nfs_open_context *ctx = nfs_file_open_context(dst); struct rpc_task *task; struct rpc_message msg = { @@ -552,14 +552,14 @@ static int nfs42_do_offload_cancel_async(struct file *dst, .rpc_message = &msg, .callback_ops = &nfs42_offload_cancel_ops, .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, + .flags = RPC_TASK_ASYNC | RPC_TASK_MOVEABLE, }; int status; if (!(dst_server->caps & NFS_CAP_OFFLOAD_CANCEL)) return -EOPNOTSUPP; - data = kzalloc(sizeof(struct nfs42_offloadcancel_data), GFP_KERNEL); + data = kzalloc(sizeof(struct nfs42_offload_data), GFP_KERNEL); if (data == NULL) return -ENOMEM; @@ -861,7 +861,7 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server, .rpc_message = &msg, .callback_ops = &nfs42_layoutstat_ops, .callback_data = data, - .flags = RPC_TASK_ASYNC, + .flags = RPC_TASK_ASYNC | RPC_TASK_MOVEABLE, }; struct rpc_task *task; @@ -1016,7 +1016,7 @@ int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg, struct rpc_task_setup task_setup = { .rpc_message = &msg, .callback_ops = &nfs42_layouterror_ops, - .flags = RPC_TASK_ASYNC, + .flags = RPC_TASK_ASYNC | RPC_TASK_MOVEABLE, }; unsigned int i; diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 9e3ae53e2205..5072d7ea72e9 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -144,9 +144,11 @@ decode_putfh_maxsz + \ decode_offload_cancel_maxsz) #define NFS4_enc_copy_notify_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_copy_notify_maxsz) #define NFS4_dec_copy_notify_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_copy_notify_maxsz) #define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \ @@ -549,7 +551,7 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req, } /* - * Encode OFFLOAD_CANEL request + * Encode OFFLOAD_CANCEL request */ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req, struct xdr_stream *xdr, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 405f17e6e0b4..df9669d4ded7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -114,6 +114,7 @@ static inline struct nfs4_label * nfs4_label_init_security(struct inode *dir, struct dentry *dentry, struct iattr *sattr, struct nfs4_label *label) { + struct lsm_context shim; int err; if (label == NULL) @@ -128,18 +129,25 @@ nfs4_label_init_security(struct inode *dir, struct dentry *dentry, label->label = NULL; err = security_dentry_init_security(dentry, sattr->ia_mode, - &dentry->d_name, NULL, - (void **)&label->label, &label->len); - if (err == 0) - return label; + &dentry->d_name, NULL, &shim); + if (err) + return NULL; - return NULL; + label->label = shim.context; + label->len = shim.len; + return label; } static inline void nfs4_label_release_security(struct nfs4_label *label) { - if (label) - security_release_secctx(label->label, label->len); + struct lsm_context shim; + + if (label) { + shim.context = label->label; + shim.len = label->len; + shim.id = LSM_ID_UNDEF; + security_release_secctx(&shim); + } } static inline u32 *nfs4_bitmask(struct nfs_server *server, struct nfs4_label *label) { @@ -4536,15 +4544,15 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, - struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr) + struct dentry *dentry, const struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_server *server = NFS_SERVER(dir); int status; struct nfs4_lookup_arg args = { .bitmask = server->attr_bitmask, .dir_fh = NFS_FH(dir), - .name = &dentry->d_name, + .name = name, }; struct nfs4_lookup_res res = { .server = server, @@ -4586,17 +4594,16 @@ static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr) } static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, - struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr) + struct dentry *dentry, const struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs4_exception exception = { .interruptible = true, }; struct rpc_clnt *client = *clnt; - const struct qstr *name = &dentry->d_name; int err; do { - err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr); + err = _nfs4_proc_lookup(client, dir, dentry, name, fhandle, fattr); trace_nfs4_lookup(dir, name, err); switch (err) { case -NFS4ERR_BADNAME: @@ -4631,13 +4638,13 @@ out: return err; } -static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry, +static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { int status; struct rpc_clnt *client = NFS_CLIENT(dir); - status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr); + status = nfs4_proc_lookup_common(&client, dir, dentry, name, fhandle, fattr); if (client != NFS_CLIENT(dir)) { rpc_shutdown_client(client); nfs_fixup_secinfo_attributes(fattr); @@ -4652,7 +4659,8 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, struct dentry *dentry, struct rpc_clnt *client = NFS_CLIENT(dir); int status; - status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr); + status = nfs4_proc_lookup_common(&client, dir, dentry, &dentry->d_name, + fhandle, fattr); if (status < 0) return ERR_PTR(status); return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 9a9f60a2291b..542cdf71229f 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1955,6 +1955,7 @@ restart: } rcu_read_unlock(); nfs4_free_state_owners(&freeme); + nfs_local_probe_async(clp); if (lost_locks) pr_warn("NFS: %s: lost %d locks\n", clp->cl_hostname, lost_locks); diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c index 886a7c4c60b3..d1a92d8f8ba4 100644 --- a/fs/nfs/nfs4sysctl.c +++ b/fs/nfs/nfs4sysctl.c @@ -17,7 +17,7 @@ static const int nfs_set_port_min; static const int nfs_set_port_max = 65535; static struct ctl_table_header *nfs4_callback_sysctl_table; -static struct ctl_table nfs4_cb_sysctls[] = { +static const struct ctl_table nfs4_cb_sysctls[] = { { .procname = "nfs_callback_tcpport", .data = &nfs_callback_set_tcpport, diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 1eab98c277fa..7a058bd8c566 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1714,38 +1714,6 @@ TRACE_EVENT(nfs_local_open_fh, ) ); -DECLARE_EVENT_CLASS(nfs_local_client_event, - TP_PROTO( - const struct nfs_client *clp - ), - - TP_ARGS(clp), - - TP_STRUCT__entry( - __field(unsigned int, protocol) - __string(server, clp->cl_hostname) - ), - - TP_fast_assign( - __entry->protocol = clp->rpc_ops->version; - __assign_str(server); - ), - - TP_printk( - "server=%s NFSv%u", __get_str(server), __entry->protocol - ) -); - -#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \ - DEFINE_EVENT(nfs_local_client_event, name, \ - TP_PROTO( \ - const struct nfs_client *clp \ - ), \ - TP_ARGS(clp)) - -DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_enable); -DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_disable); - DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index e27c07bd8929..11968dcb7243 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -961,8 +961,9 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) struct nfs_client *clp = NFS_SERVER(hdr->inode)->nfs_client; struct nfsd_file *localio = - nfs_local_open_fh(clp, hdr->cred, - hdr->args.fh, hdr->args.context->mode); + nfs_local_open_fh(clp, hdr->cred, hdr->args.fh, + &hdr->args.context->nfl, + hdr->args.context->mode); if (NFS_SERVER(hdr->inode)->nfs_client->cl_minorversion) task_flags = RPC_TASK_MOVEABLE; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0d16b383a452..5f582713bf05 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1308,7 +1308,7 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo, enum pnfs_iomode *iomode) { /* Serialise LAYOUTGET/LAYOUTRETURN */ - if (atomic_read(&lo->plh_outstanding) != 0) + if (atomic_read(&lo->plh_outstanding) != 0 && lo->plh_return_seq == 0) return false; if (test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) return false; diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 6c09cd090c34..77920a2e3cef 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -153,13 +153,13 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs_proc_lookup(struct inode *dir, struct dentry *dentry, +nfs_proc_lookup(struct inode *dir, struct dentry *dentry, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_diropargs arg = { .fh = NFS_FH(dir), - .name = dentry->d_name.name, - .len = dentry->d_name.len + .name = name->name, + .len = name->len }; struct nfs_diropok res = { .fh = fhandle, diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ae5c5e39afa0..aeb715b4a690 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -73,6 +73,7 @@ #include "nfs.h" #include "netns.h" #include "sysfs.h" +#include "nfs4idmap.h" #define NFSDBG_FACILITY NFSDBG_VFS diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index e645be1a3381..f579df0e8d67 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *nfs_callback_sysctl_table; -static struct ctl_table nfs_cb_sysctls[] = { +static const struct ctl_table nfs_cb_sysctls[] = { { .procname = "nfs_mountpoint_timeout", .data = &nfs_mountpoint_expiry_timeout, diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c index bf378ecd5d9f..7b59a40d40c0 100644 --- a/fs/nfs/sysfs.c +++ b/fs/nfs/sysfs.c @@ -280,9 +280,9 @@ void nfs_sysfs_link_rpc_client(struct nfs_server *server, char name[RPC_CLIENT_NAME_SIZE]; int ret; - strcpy(name, clnt->cl_program->name); - strcat(name, uniq ? uniq : ""); - strcat(name, "_client"); + strscpy(name, clnt->cl_program->name, sizeof(name)); + strncat(name, uniq ? uniq : "", sizeof(name) - strlen(name) - 1); + strncat(name, "_client", sizeof(name) - strlen(name) - 1); ret = sysfs_create_link_nowarn(&server->kobj, &clnt->cl_sysfs->kobject, name); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 50fa539611f5..aa3d8bea3ec0 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1826,7 +1826,8 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, task_flags = RPC_TASK_MOVEABLE; localio = nfs_local_open_fh(NFS_SERVER(inode)->nfs_client, data->cred, - data->args.fh, data->context->mode); + data->args.fh, &data->context->nfl, + data->context->mode); return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), data->mds_ops, how, RPC_TASK_CRED_NOREF | task_flags, localio); diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile index a5e54809701e..c10ead273ff2 100644 --- a/fs/nfs_common/Makefile +++ b/fs/nfs_common/Makefile @@ -6,8 +6,9 @@ obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o nfs_acl-objs := nfsacl.o +CFLAGS_localio_trace.o += -I$(src) obj-$(CONFIG_NFS_COMMON_LOCALIO_SUPPORT) += nfs_localio.o -nfs_localio-objs := nfslocalio.o +nfs_localio-objs := nfslocalio.o localio_trace.o obj-$(CONFIG_GRACE_PERIOD) += grace.o obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c index 34a115176f97..af09aed09fd2 100644 --- a/fs/nfs_common/common.c +++ b/fs/nfs_common/common.c @@ -15,7 +15,7 @@ static const struct { { NFS_OK, 0 }, { NFSERR_PERM, -EPERM }, { NFSERR_NOENT, -ENOENT }, - { NFSERR_IO, -errno_NFSERR_IO}, + { NFSERR_IO, -EIO }, { NFSERR_NXIO, -ENXIO }, /* { NFSERR_EAGAIN, -EAGAIN }, */ { NFSERR_ACCES, -EACCES }, @@ -45,7 +45,6 @@ static const struct { { NFSERR_SERVERFAULT, -EREMOTEIO }, { NFSERR_BADTYPE, -EBADTYPE }, { NFSERR_JUKEBOX, -EJUKEBOX }, - { -1, -EIO } }; /** @@ -59,26 +58,29 @@ int nfs_stat_to_errno(enum nfs_stat status) { int i; - for (i = 0; nfs_errtbl[i].stat != -1; i++) { + for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { if (nfs_errtbl[i].stat == (int)status) return nfs_errtbl[i].errno; } - return nfs_errtbl[i].errno; + return -EIO; } EXPORT_SYMBOL_GPL(nfs_stat_to_errno); /* * We need to translate between nfs v4 status return values and * the local errno values which may not be the same. + * + * nfs4_errtbl_common[] is used before more specialized mappings + * available in nfs4_errtbl[] or nfs4_errtbl_localio[]. */ static const struct { int stat; int errno; -} nfs4_errtbl[] = { +} nfs4_errtbl_common[] = { { NFS4_OK, 0 }, { NFS4ERR_PERM, -EPERM }, { NFS4ERR_NOENT, -ENOENT }, - { NFS4ERR_IO, -errno_NFSERR_IO}, + { NFS4ERR_IO, -EIO }, { NFS4ERR_NXIO, -ENXIO }, { NFS4ERR_ACCESS, -EACCES }, { NFS4ERR_EXIST, -EEXIST }, @@ -98,15 +100,20 @@ static const struct { { NFS4ERR_BAD_COOKIE, -EBADCOOKIE }, { NFS4ERR_NOTSUPP, -ENOTSUPP }, { NFS4ERR_TOOSMALL, -ETOOSMALL }, - { NFS4ERR_SERVERFAULT, -EREMOTEIO }, { NFS4ERR_BADTYPE, -EBADTYPE }, - { NFS4ERR_LOCKED, -EAGAIN }, { NFS4ERR_SYMLINK, -ELOOP }, - { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, { NFS4ERR_DEADLOCK, -EDEADLK }, +}; + +static const struct { + int stat; + int errno; +} nfs4_errtbl[] = { + { NFS4ERR_SERVERFAULT, -EREMOTEIO }, + { NFS4ERR_LOCKED, -EAGAIN }, + { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, { NFS4ERR_NOXATTR, -ENODATA }, { NFS4ERR_XATTR2BIG, -E2BIG }, - { -1, -EIO } }; /* @@ -116,7 +123,14 @@ static const struct { int nfs4_stat_to_errno(int stat) { int i; - for (i = 0; nfs4_errtbl[i].stat != -1; i++) { + + /* First check nfs4_errtbl_common */ + for (i = 0; i < ARRAY_SIZE(nfs4_errtbl_common); i++) { + if (nfs4_errtbl_common[i].stat == stat) + return nfs4_errtbl_common[i].errno; + } + /* Then check nfs4_errtbl */ + for (i = 0; i < ARRAY_SIZE(nfs4_errtbl); i++) { if (nfs4_errtbl[i].stat == stat) return nfs4_errtbl[i].errno; } @@ -132,3 +146,56 @@ int nfs4_stat_to_errno(int stat) return -stat; } EXPORT_SYMBOL_GPL(nfs4_stat_to_errno); + +/* + * This table is useful for conversion from local errno to NFS error. + * It provides more logically correct mappings for use with LOCALIO + * (which is focused on converting from errno to NFS status). + */ +static const struct { + int stat; + int errno; +} nfs4_errtbl_localio[] = { + /* Map errors differently than nfs4_errtbl */ + { NFS4ERR_IO, -EREMOTEIO }, + { NFS4ERR_DELAY, -EAGAIN }, + { NFS4ERR_FBIG, -E2BIG }, + /* Map errors not handled by nfs4_errtbl */ + { NFS4ERR_STALE, -EBADF }, + { NFS4ERR_STALE, -EOPENSTALE }, + { NFS4ERR_DELAY, -ETIMEDOUT }, + { NFS4ERR_DELAY, -ERESTARTSYS }, + { NFS4ERR_DELAY, -ENOMEM }, + { NFS4ERR_IO, -ETXTBSY }, + { NFS4ERR_IO, -EBUSY }, + { NFS4ERR_SERVERFAULT, -ESERVERFAULT }, + { NFS4ERR_SERVERFAULT, -ENFILE }, + { NFS4ERR_IO, -EUCLEAN }, + { NFS4ERR_PERM, -ENOKEY }, +}; + +/* + * Convert an errno to an NFS error code for LOCALIO. + */ +__u32 nfs_localio_errno_to_nfs4_stat(int errno) +{ + int i; + + /* First check nfs4_errtbl_common */ + for (i = 0; i < ARRAY_SIZE(nfs4_errtbl_common); i++) { + if (nfs4_errtbl_common[i].errno == errno) + return nfs4_errtbl_common[i].stat; + } + /* Then check nfs4_errtbl_localio */ + for (i = 0; i < ARRAY_SIZE(nfs4_errtbl_localio); i++) { + if (nfs4_errtbl_localio[i].errno == errno) + return nfs4_errtbl_localio[i].stat; + } + /* If we cannot translate the error, the recovery routines should + * handle it. + * Note: remaining NFSv4 error codes have values > 10000, so should + * not conflict with native Linux error codes. + */ + return NFS4ERR_SERVERFAULT; +} +EXPORT_SYMBOL_GPL(nfs_localio_errno_to_nfs4_stat); diff --git a/fs/nfs_common/localio_trace.c b/fs/nfs_common/localio_trace.c new file mode 100644 index 000000000000..7decfe57abeb --- /dev/null +++ b/fs/nfs_common/localio_trace.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024 Trond Myklebust + * Copyright (C) 2024 Mike Snitzer + */ +#include +#include + +#define CREATE_TRACE_POINTS +#include "localio_trace.h" diff --git a/fs/nfs_common/localio_trace.h b/fs/nfs_common/localio_trace.h new file mode 100644 index 000000000000..4055aec9ff8d --- /dev/null +++ b/fs/nfs_common/localio_trace.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Trond Myklebust + * Copyright (C) 2024 Mike Snitzer + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nfs_localio + +#if !defined(_TRACE_NFS_COMMON_LOCALIO_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NFS_COMMON_LOCALIO_H + +#include + +#include +#include +#include + +DECLARE_EVENT_CLASS(nfs_local_client_event, + TP_PROTO( + const struct nfs_client *clp + ), + + TP_ARGS(clp), + + TP_STRUCT__entry( + __field(unsigned int, protocol) + __string(server, clp->cl_hostname) + ), + + TP_fast_assign( + __entry->protocol = clp->rpc_ops->version; + __assign_str(server); + ), + + TP_printk( + "server=%s NFSv%u", __get_str(server), __entry->protocol + ) +); + +#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \ + DEFINE_EVENT(nfs_local_client_event, name, \ + TP_PROTO( \ + const struct nfs_client *clp \ + ), \ + TP_ARGS(clp)) + +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_localio_enable_client); +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_localio_disable_client); + +#endif /* _TRACE_NFS_COMMON_LOCALIO_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE localio_trace +/* This part must be outside protection */ +#include diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c index a74ec08f6c96..6a0bdea6d644 100644 --- a/fs/nfs_common/nfslocalio.c +++ b/fs/nfs_common/nfslocalio.c @@ -7,38 +7,67 @@ #include #include #include +#include +#include +#include #include +#include "localio_trace.h" + MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("NFS localio protocol bypass support"); -static DEFINE_SPINLOCK(nfs_uuid_lock); +static DEFINE_SPINLOCK(nfs_uuids_lock); /* * Global list of nfs_uuid_t instances - * that is protected by nfs_uuid_lock. + * that is protected by nfs_uuids_lock. */ static LIST_HEAD(nfs_uuids); +/* + * Lock ordering: + * 1: nfs_uuid->lock + * 2: nfs_uuids_lock + * 3: nfs_uuid->list_lock (aka nn->local_clients_lock) + * + * May skip locks in select cases, but never hold multiple + * locks out of order. + */ + void nfs_uuid_init(nfs_uuid_t *nfs_uuid) { - nfs_uuid->net = NULL; + RCU_INIT_POINTER(nfs_uuid->net, NULL); nfs_uuid->dom = NULL; + nfs_uuid->list_lock = NULL; INIT_LIST_HEAD(&nfs_uuid->list); + INIT_LIST_HEAD(&nfs_uuid->files); + spin_lock_init(&nfs_uuid->lock); + nfs_uuid->nfs3_localio_probe_count = 0; } EXPORT_SYMBOL_GPL(nfs_uuid_init); bool nfs_uuid_begin(nfs_uuid_t *nfs_uuid) { - spin_lock(&nfs_uuid_lock); - /* Is this nfs_uuid already in use? */ + spin_lock(&nfs_uuid->lock); + if (rcu_access_pointer(nfs_uuid->net)) { + /* This nfs_uuid is already in use */ + spin_unlock(&nfs_uuid->lock); + return false; + } + + spin_lock(&nfs_uuids_lock); if (!list_empty(&nfs_uuid->list)) { - spin_unlock(&nfs_uuid_lock); + /* This nfs_uuid is already in use */ + spin_unlock(&nfs_uuids_lock); + spin_unlock(&nfs_uuid->lock); return false; } - uuid_gen(&nfs_uuid->uuid); list_add_tail(&nfs_uuid->list, &nfs_uuids); - spin_unlock(&nfs_uuid_lock); + spin_unlock(&nfs_uuids_lock); + + uuid_gen(&nfs_uuid->uuid); + spin_unlock(&nfs_uuid->lock); return true; } @@ -46,12 +75,16 @@ EXPORT_SYMBOL_GPL(nfs_uuid_begin); void nfs_uuid_end(nfs_uuid_t *nfs_uuid) { - if (nfs_uuid->net == NULL) { - spin_lock(&nfs_uuid_lock); - if (nfs_uuid->net == NULL) + if (!rcu_access_pointer(nfs_uuid->net)) { + spin_lock(&nfs_uuid->lock); + if (!rcu_access_pointer(nfs_uuid->net)) { + /* Not local, remove from nfs_uuids */ + spin_lock(&nfs_uuids_lock); list_del_init(&nfs_uuid->list); - spin_unlock(&nfs_uuid_lock); - } + spin_unlock(&nfs_uuids_lock); + } + spin_unlock(&nfs_uuid->lock); + } } EXPORT_SYMBOL_GPL(nfs_uuid_end); @@ -69,68 +102,142 @@ static nfs_uuid_t * nfs_uuid_lookup_locked(const uuid_t *uuid) static struct module *nfsd_mod; void nfs_uuid_is_local(const uuid_t *uuid, struct list_head *list, - struct net *net, struct auth_domain *dom, - struct module *mod) + spinlock_t *list_lock, struct net *net, + struct auth_domain *dom, struct module *mod) { nfs_uuid_t *nfs_uuid; - spin_lock(&nfs_uuid_lock); + spin_lock(&nfs_uuids_lock); nfs_uuid = nfs_uuid_lookup_locked(uuid); - if (nfs_uuid) { - kref_get(&dom->ref); - nfs_uuid->dom = dom; - /* - * We don't hold a ref on the net, but instead put - * ourselves on a list so the net pointer can be - * invalidated. - */ - list_move(&nfs_uuid->list, list); - rcu_assign_pointer(nfs_uuid->net, net); - - __module_get(mod); - nfsd_mod = mod; + if (!nfs_uuid) { + spin_unlock(&nfs_uuids_lock); + return; } - spin_unlock(&nfs_uuid_lock); + + /* + * We don't hold a ref on the net, but instead put + * ourselves on @list (nn->local_clients) so the net + * pointer can be invalidated. + */ + spin_lock(list_lock); /* list_lock is nn->local_clients_lock */ + list_move(&nfs_uuid->list, list); + spin_unlock(list_lock); + + spin_unlock(&nfs_uuids_lock); + /* Once nfs_uuid is parented to @list, avoid global nfs_uuids_lock */ + spin_lock(&nfs_uuid->lock); + + __module_get(mod); + nfsd_mod = mod; + + nfs_uuid->list_lock = list_lock; + kref_get(&dom->ref); + nfs_uuid->dom = dom; + rcu_assign_pointer(nfs_uuid->net, net); + spin_unlock(&nfs_uuid->lock); } EXPORT_SYMBOL_GPL(nfs_uuid_is_local); -static void nfs_uuid_put_locked(nfs_uuid_t *nfs_uuid) +void nfs_localio_enable_client(struct nfs_client *clp) { - if (nfs_uuid->net) { - module_put(nfsd_mod); - nfs_uuid->net = NULL; + /* nfs_uuid_is_local() does the actual enablement */ + trace_nfs_localio_enable_client(clp); +} +EXPORT_SYMBOL_GPL(nfs_localio_enable_client); + +/* + * Cleanup the nfs_uuid_t embedded in an nfs_client. + * This is the long-form of nfs_uuid_init(). + */ +static bool nfs_uuid_put(nfs_uuid_t *nfs_uuid) +{ + LIST_HEAD(local_files); + struct nfs_file_localio *nfl, *tmp; + + spin_lock(&nfs_uuid->lock); + if (unlikely(!rcu_access_pointer(nfs_uuid->net))) { + spin_unlock(&nfs_uuid->lock); + return false; } + RCU_INIT_POINTER(nfs_uuid->net, NULL); + if (nfs_uuid->dom) { auth_domain_put(nfs_uuid->dom); nfs_uuid->dom = NULL; } - list_del_init(&nfs_uuid->list); + + list_splice_init(&nfs_uuid->files, &local_files); + spin_unlock(&nfs_uuid->lock); + + /* Walk list of files and ensure their last references dropped */ + list_for_each_entry_safe(nfl, tmp, &local_files, list) { + nfs_close_local_fh(nfl); + cond_resched(); + } + + spin_lock(&nfs_uuid->lock); + BUG_ON(!list_empty(&nfs_uuid->files)); + + /* Remove client from nn->local_clients */ + if (nfs_uuid->list_lock) { + spin_lock(nfs_uuid->list_lock); + BUG_ON(list_empty(&nfs_uuid->list)); + list_del_init(&nfs_uuid->list); + spin_unlock(nfs_uuid->list_lock); + nfs_uuid->list_lock = NULL; + } + + module_put(nfsd_mod); + spin_unlock(&nfs_uuid->lock); + + return true; } -void nfs_uuid_invalidate_clients(struct list_head *list) +void nfs_localio_disable_client(struct nfs_client *clp) { + if (nfs_uuid_put(&clp->cl_uuid)) + trace_nfs_localio_disable_client(clp); +} +EXPORT_SYMBOL_GPL(nfs_localio_disable_client); + +void nfs_localio_invalidate_clients(struct list_head *nn_local_clients, + spinlock_t *nn_local_clients_lock) +{ + LIST_HEAD(local_clients); nfs_uuid_t *nfs_uuid, *tmp; + struct nfs_client *clp; - spin_lock(&nfs_uuid_lock); - list_for_each_entry_safe(nfs_uuid, tmp, list, list) - nfs_uuid_put_locked(nfs_uuid); - spin_unlock(&nfs_uuid_lock); -} -EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_clients); - -void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid) -{ - if (nfs_uuid->net) { - spin_lock(&nfs_uuid_lock); - nfs_uuid_put_locked(nfs_uuid); - spin_unlock(&nfs_uuid_lock); + spin_lock(nn_local_clients_lock); + list_splice_init(nn_local_clients, &local_clients); + spin_unlock(nn_local_clients_lock); + list_for_each_entry_safe(nfs_uuid, tmp, &local_clients, list) { + if (WARN_ON(nfs_uuid->list_lock != nn_local_clients_lock)) + break; + clp = container_of(nfs_uuid, struct nfs_client, cl_uuid); + nfs_localio_disable_client(clp); } } -EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_one_client); +EXPORT_SYMBOL_GPL(nfs_localio_invalidate_clients); +static void nfs_uuid_add_file(nfs_uuid_t *nfs_uuid, struct nfs_file_localio *nfl) +{ + /* Add nfl to nfs_uuid->files if it isn't already */ + spin_lock(&nfs_uuid->lock); + if (list_empty(&nfl->list)) { + rcu_assign_pointer(nfl->nfs_uuid, nfs_uuid); + list_add_tail(&nfl->list, &nfs_uuid->files); + } + spin_unlock(&nfs_uuid->lock); +} + +/* + * Caller is responsible for calling nfsd_net_put and + * nfsd_file_put (via nfs_to_nfsd_file_put_local). + */ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, struct rpc_clnt *rpc_clnt, const struct cred *cred, - const struct nfs_fh *nfs_fh, const fmode_t fmode) + const struct nfs_fh *nfs_fh, struct nfs_file_localio *nfl, + const fmode_t fmode) { struct net *net; struct nfsd_file *localio; @@ -139,7 +246,7 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, * Not running in nfsd context, so must safely get reference on nfsd_serv. * But the server may already be shutting down, if so disallow new localio. * uuid->net is NOT a counted reference, but rcu_read_lock() ensures that - * if uuid->net is not NULL, then calling nfsd_serv_try_get() is safe + * if uuid->net is not NULL, then calling nfsd_net_try_get() is safe * and if it succeeds we will have an implied reference to the net. * * Otherwise NFS may not have ref on NFSD and therefore cannot safely @@ -147,21 +254,62 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, */ rcu_read_lock(); net = rcu_dereference(uuid->net); - if (!net || !nfs_to->nfsd_serv_try_get(net)) { + if (!net || !nfs_to->nfsd_net_try_get(net)) { rcu_read_unlock(); return ERR_PTR(-ENXIO); } rcu_read_unlock(); - /* We have an implied reference to net thanks to nfsd_serv_try_get */ + /* We have an implied reference to net thanks to nfsd_net_try_get */ localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt, cred, nfs_fh, fmode); if (IS_ERR(localio)) nfs_to_nfsd_net_put(net); + else + nfs_uuid_add_file(uuid, nfl); return localio; } EXPORT_SYMBOL_GPL(nfs_open_local_fh); +void nfs_close_local_fh(struct nfs_file_localio *nfl) +{ + struct nfsd_file *ro_nf = NULL; + struct nfsd_file *rw_nf = NULL; + nfs_uuid_t *nfs_uuid; + + rcu_read_lock(); + nfs_uuid = rcu_dereference(nfl->nfs_uuid); + if (!nfs_uuid) { + /* regular (non-LOCALIO) NFS will hammer this */ + rcu_read_unlock(); + return; + } + + ro_nf = rcu_access_pointer(nfl->ro_file); + rw_nf = rcu_access_pointer(nfl->rw_file); + if (ro_nf || rw_nf) { + spin_lock(&nfs_uuid->lock); + if (ro_nf) + ro_nf = rcu_dereference_protected(xchg(&nfl->ro_file, NULL), 1); + if (rw_nf) + rw_nf = rcu_dereference_protected(xchg(&nfl->rw_file, NULL), 1); + + /* Remove nfl from nfs_uuid->files list */ + RCU_INIT_POINTER(nfl->nfs_uuid, NULL); + list_del_init(&nfl->list); + spin_unlock(&nfs_uuid->lock); + rcu_read_unlock(); + + if (ro_nf) + nfs_to_nfsd_file_put_local(ro_nf); + if (rw_nf) + nfs_to_nfsd_file_put_local(rw_nf); + return; + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(nfs_close_local_fh); + /* * The NFS LOCALIO code needs to call into NFSD using various symbols, * but cannot be statically linked, because that will make the NFS diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 18cbd3fa7691..2f687619f65b 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -18,9 +18,23 @@ nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ - nfs4acl.o nfs4callback.o nfs4recover.o + nfs4acl.o nfs4callback.o nfs4recover.o nfs4xdr_gen.o nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o nfsd-$(CONFIG_NFS_LOCALIO) += localio.o + + +.PHONY: xdrgen + +xdrgen: ../../include/linux/sunrpc/xdrgen/nfs4_1.h nfs4xdr_gen.h nfs4xdr_gen.c + +../../include/linux/sunrpc/xdrgen/nfs4_1.h: ../../Documentation/sunrpc/xdr/nfs4_1.x + ../../tools/net/sunrpc/xdrgen/xdrgen definitions $< > $@ + +nfs4xdr_gen.h: ../../Documentation/sunrpc/xdr/nfs4_1.x + ../../tools/net/sunrpc/xdrgen/xdrgen declarations $< > $@ + +nfs4xdr_gen.c: ../../Documentation/sunrpc/xdr/nfs4_1.x + ../../tools/net/sunrpc/xdrgen/xdrgen source $< > $@ diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 93e33d1ee891..4dc327e02456 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -27,7 +27,7 @@ int nfsd_setuser(struct svc_cred *cred, struct svc_export *exp) int flags = nfsexp_flags(cred, exp); /* discard any old override before preparing the new set */ - revert_creds(get_cred(current_real_cred())); + put_cred(revert_creds(get_cred(current_real_cred()))); new = prepare_creds(); if (!new) return -ENOMEM; @@ -80,7 +80,6 @@ int nfsd_setuser(struct svc_cred *cred, struct svc_export *exp) new->cap_effective = cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); put_cred(override_creds(new)); - put_cred(new); return 0; oom: diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index eacafe46e3b6..0363720280d4 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -40,24 +40,15 @@ #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) -static void expkey_put_work(struct work_struct *work) +static void expkey_put(struct kref *ref) { - struct svc_expkey *key = - container_of(to_rcu_work(work), struct svc_expkey, ek_rcu_work); + struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); if (test_bit(CACHE_VALID, &key->h.flags) && !test_bit(CACHE_NEGATIVE, &key->h.flags)) path_put(&key->ek_path); auth_domain_put(key->ek_client); - kfree(key); -} - -static void expkey_put(struct kref *ref) -{ - struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); - - INIT_RCU_WORK(&key->ek_rcu_work, expkey_put_work); - queue_rcu_work(system_wq, &key->ek_rcu_work); + kfree_rcu(key, ek_rcu); } static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) @@ -364,13 +355,11 @@ static void export_stats_destroy(struct export_stats *stats) EXP_STATS_COUNTERS_NUM); } -static void svc_export_put_work(struct work_struct *work) +static void svc_export_release(struct rcu_head *rcu_head) { - struct svc_export *exp = - container_of(to_rcu_work(work), struct svc_export, ex_rcu_work); + struct svc_export *exp = container_of(rcu_head, struct svc_export, + ex_rcu); - path_put(&exp->ex_path); - auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); export_stats_destroy(exp->ex_stats); kfree(exp->ex_stats); @@ -382,8 +371,9 @@ static void svc_export_put(struct kref *ref) { struct svc_export *exp = container_of(ref, struct svc_export, h.ref); - INIT_RCU_WORK(&exp->ex_rcu_work, svc_export_put_work); - queue_rcu_work(system_wq, &exp->ex_rcu_work); + path_put(&exp->ex_path); + auth_domain_put(exp->ex_client); + call_rcu(&exp->ex_rcu, svc_export_release); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) @@ -1444,13 +1434,9 @@ static int e_show(struct seq_file *m, void *p) return 0; } - if (!cache_get_rcu(&exp->h)) + if (cache_check_rcu(cd, &exp->h, NULL)) return 0; - if (cache_check(cd, &exp->h, NULL)) - return 0; - - exp_put(exp); return svc_export_show(m, cd, cp); } diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index 6f2fbaae01fa..4d92b99c1ffd 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -75,7 +75,7 @@ struct svc_export { u32 ex_layout_types; struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; - struct rcu_work ex_rcu_work; + struct rcu_head ex_rcu; unsigned long ex_xprtsec_modes; struct export_stats *ex_stats; }; @@ -92,7 +92,7 @@ struct svc_expkey { u32 ek_fsid[6]; struct path ek_path; - struct rcu_work ek_rcu_work; + struct rcu_head ek_rcu; }; #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index a1cdba42c4fa..0e552d873eaa 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "vfs.h" #include "nfsd.h" @@ -391,7 +392,7 @@ nfsd_file_put(struct nfsd_file *nf) } /** - * nfsd_file_put_local - put nfsd_file reference and arm nfsd_serv_put in caller + * nfsd_file_put_local - put nfsd_file reference and arm nfsd_net_put in caller * @nf: nfsd_file of which to put the reference * * First save the associated net to return to caller, then put @@ -833,6 +834,14 @@ __nfsd_file_cache_purge(struct net *net) struct nfsd_file *nf; LIST_HEAD(dispose); +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + if (net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + nfs_localio_invalidate_clients(&nn->local_clients, + &nn->local_clients_lock); + } +#endif + rhltable_walk_enter(&nfsd_file_rhltable, &iter); do { rhashtable_walk_start(&iter); @@ -1222,10 +1231,9 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, * a file. The security implications of this should be carefully * considered before use. * - * The nfsd_file object returned by this API is reference-counted - * and garbage-collected. The object is retained for a few - * seconds after the final nfsd_file_put() in case the caller - * wants to re-use it. + * The nfsd_file_object returned by this API is reference-counted + * but not garbage-collected. The object is unhashed after the + * final nfsd_file_put(). * * Return values: * %nfs_ok - @pnf points to an nfsd_file with its reference @@ -1247,8 +1255,8 @@ nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, __be32 beres; beres = nfsd_file_do_acquire(NULL, net, cred, client, - fhp, may_flags, NULL, pnf, true); - revert_creds(save_cred); + fhp, may_flags, NULL, pnf, false); + put_cred(revert_creds(save_cred)); return beres; } diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index f441cb9f74d5..238647fa379e 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -25,10 +25,12 @@ #include "cache.h" static const struct nfsd_localio_operations nfsd_localio_ops = { - .nfsd_serv_try_get = nfsd_serv_try_get, - .nfsd_serv_put = nfsd_serv_put, + .nfsd_net_try_get = nfsd_net_try_get, + .nfsd_net_put = nfsd_net_put, .nfsd_open_local_fh = nfsd_open_local_fh, .nfsd_file_put_local = nfsd_file_put_local, + .nfsd_file_get = nfsd_file_get, + .nfsd_file_put = nfsd_file_put, .nfsd_file_file = nfsd_file_file, }; @@ -52,7 +54,7 @@ void nfsd_localio_ops_init(void) * avoid all the NFS overhead with reads, writes and commits. * * On successful return, returned nfsd_file will have its nf_net member - * set. Caller (NFS client) is responsible for calling nfsd_serv_put and + * set. Caller (NFS client) is responsible for calling nfsd_net_put and * nfsd_file_put (via nfs_to_nfsd_file_put_local). */ struct nfsd_file * @@ -114,6 +116,7 @@ static __be32 localio_proc_uuid_is_local(struct svc_rqst *rqstp) struct nfsd_net *nn = net_generic(net, nfsd_net_id); nfs_uuid_is_local(&argp->uuid, &nn->local_clients, + &nn->local_clients_lock, net, rqstp->rq_client, THIS_MODULE); return rpc_success; diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 26f7b34d1a03..3e2d0fde80a7 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -128,21 +128,16 @@ struct nfsd_net { seqlock_t writeverf_lock; unsigned char writeverf[8]; - /* - * Max number of connections this nfsd container will allow. Defaults - * to '0' which is means that it bases this on the number of threads. - */ - unsigned int max_connections; - u32 clientid_base; u32 clientid_counter; u32 clverifier_counter; struct svc_info nfsd_info; #define nfsd_serv nfsd_info.serv - struct percpu_ref nfsd_serv_ref; - struct completion nfsd_serv_confirm_done; - struct completion nfsd_serv_free_done; + + struct percpu_ref nfsd_net_ref; + struct completion nfsd_net_confirm_done; + struct completion nfsd_net_free_done; /* * clientid and stateid data for construction of net unique COPY @@ -219,6 +214,7 @@ struct nfsd_net { #if IS_ENABLED(CONFIG_NFS_LOCALIO) /* Local clients to be invalidated when net is shut down */ + spinlock_t local_clients_lock; struct list_head local_clients; #endif }; @@ -229,8 +225,8 @@ struct nfsd_net { extern bool nfsd_support_version(int vers); extern unsigned int nfsd_net_id; -bool nfsd_serv_try_get(struct net *net); -void nfsd_serv_put(struct net *net); +bool nfsd_net_try_get(struct net *net); +void nfsd_net_put(struct net *net); void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn); void nfsd_reset_write_verifier(struct nfsd_net *nn); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 3877b53e429f..50e468bdb8d4 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -42,6 +42,7 @@ #include "trace.h" #include "xdr4cb.h" #include "xdr4.h" +#include "nfs4xdr_gen.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -93,12 +94,35 @@ static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, { fattr->ncf_cb_change = 0; fattr->ncf_cb_fsize = 0; + fattr->ncf_cb_atime.tv_sec = 0; + fattr->ncf_cb_atime.tv_nsec = 0; + fattr->ncf_cb_mtime.tv_sec = 0; + fattr->ncf_cb_mtime.tv_nsec = 0; + if (bitmap[0] & FATTR4_WORD0_CHANGE) if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0) return -NFSERR_BAD_XDR; if (bitmap[0] & FATTR4_WORD0_SIZE) if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0) return -NFSERR_BAD_XDR; + if (bitmap[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) { + fattr4_time_deleg_access access; + + if (!xdrgen_decode_fattr4_time_deleg_access(xdr, &access)) + return -NFSERR_BAD_XDR; + fattr->ncf_cb_atime.tv_sec = access.seconds; + fattr->ncf_cb_atime.tv_nsec = access.nseconds; + + } + if (bitmap[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) { + fattr4_time_deleg_modify modify; + + if (!xdrgen_decode_fattr4_time_deleg_modify(xdr, &modify)) + return -NFSERR_BAD_XDR; + fattr->ncf_cb_mtime.tv_sec = modify.seconds; + fattr->ncf_cb_mtime.tv_nsec = modify.nseconds; + + } return 0; } @@ -361,16 +385,24 @@ static void encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr, struct nfs4_cb_fattr *fattr) { - struct nfs4_delegation *dp = - container_of(fattr, struct nfs4_delegation, dl_cb_fattr); + struct nfs4_delegation *dp = container_of(fattr, struct nfs4_delegation, dl_cb_fattr); struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle; - u32 bmap[1]; + struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; + u32 bmap_size = 1; + u32 bmap[3]; - bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE; + bmap[0] = FATTR4_WORD0_SIZE; + if (!ncf->ncf_file_modified) + bmap[0] |= FATTR4_WORD0_CHANGE; + if (deleg_attrs_deleg(dp->dl_type)) { + bmap[1] = 0; + bmap[2] = FATTR4_WORD2_TIME_DELEG_ACCESS | FATTR4_WORD2_TIME_DELEG_MODIFY; + bmap_size = 3; + } encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR); encode_nfs_fh4(xdr, fh); - encode_bitmap4(xdr, bmap, ARRAY_SIZE(bmap)); + encode_bitmap4(xdr, bmap, bmap_size); hdr->nops++; } @@ -634,7 +666,7 @@ static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp, struct nfs4_cb_compound_hdr hdr; int status; u32 bitmap[3] = {0}; - u32 attrlen; + u32 attrlen, maxlen; struct nfs4_cb_fattr *ncf = container_of(cb, struct nfs4_cb_fattr, ncf_getattr); @@ -647,13 +679,17 @@ static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp, return status; status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status); - if (status) + if (unlikely(status || cb->cb_seq_status)) return status; if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0) return -NFSERR_BAD_XDR; if (xdr_stream_decode_u32(xdr, &attrlen) < 0) return -NFSERR_BAD_XDR; - if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize))) + maxlen = sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize); + if (bitmap[2] != 0) + maxlen += (sizeof(ncf->ncf_cb_mtime.tv_sec) + + sizeof(ncf->ncf_cb_mtime.tv_nsec)) * 2; + if (attrlen > maxlen) return -NFSERR_BAD_XDR; status = decode_cb_fattr4(xdr, bitmap, ncf); return status; @@ -1036,8 +1072,7 @@ static void nfsd41_cb_inflight_begin(struct nfs4_client *clp) static void nfsd41_cb_inflight_end(struct nfs4_client *clp) { - if (atomic_dec_and_test(&clp->cl_cb_inflight)) - wake_up_var(&clp->cl_cb_inflight); + atomic_dec_and_wake_up(&clp->cl_cb_inflight); } static void nfsd41_cb_inflight_wait_complete(struct nfs4_client *clp) @@ -1100,7 +1135,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) + if (!conn->cb_xprt || !ses) return -EINVAL; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; @@ -1397,8 +1432,9 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) return; if (cb->cb_status) { - WARN_ONCE(task->tk_status, "cb_status=%d tk_status=%d", - cb->cb_status, task->tk_status); + WARN_ONCE(task->tk_status, + "cb_status=%d tk_status=%d cb_opcode=%d", + cb->cb_status, task->tk_status, cb->cb_ops->opcode); task->tk_status = cb->cb_status; } @@ -1522,8 +1558,6 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) ses = c->cn_session; } spin_unlock(&clp->cl_lock); - if (!c) - return; err = setup_callback_client(clp, &conn, ses); if (err) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f8a10f90bc7a..f6e06c779d09 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1135,18 +1135,43 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, .na_iattr = &setattr->sa_iattr, .na_seclabel = &setattr->sa_label, }; + bool save_no_wcc, deleg_attrs; + struct nfs4_stid *st = NULL; struct inode *inode; __be32 status = nfs_ok; - bool save_no_wcc; int err; - if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { + deleg_attrs = setattr->sa_bmval[2] & (FATTR4_WORD2_TIME_DELEG_ACCESS | + FATTR4_WORD2_TIME_DELEG_MODIFY); + + if (deleg_attrs || (setattr->sa_iattr.ia_valid & ATTR_SIZE)) { + int flags = WR_STATE; + + if (setattr->sa_bmval[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) + flags |= RD_STATE; + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &setattr->sa_stateid, - WR_STATE, NULL, NULL); + flags, NULL, &st); if (status) return status; } + + if (deleg_attrs) { + status = nfserr_bad_stateid; + if (st->sc_type & SC_TYPE_DELEG) { + struct nfs4_delegation *dp = delegstateid(st); + + /* Only for *_ATTRS_DELEG flavors */ + if (deleg_attrs_deleg(dp->dl_type)) + status = nfs_ok; + } + } + if (st) + nfs4_put_stid(st); + if (status) + return status; + err = fh_want_write(&cstate->current_fh); if (err) return nfserrno(err); @@ -1347,7 +1372,6 @@ static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; - atomic_dec(©->cp_nn->pending_async_copies); kfree(copy->cp_src); kfree(copy); } @@ -1870,6 +1894,7 @@ do_callback: set_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags); trace_nfsd_copy_async_done(copy); nfsd4_send_cb_offload(copy); + atomic_dec(©->cp_nn->pending_async_copies); return 0; } @@ -1927,19 +1952,19 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* Arbitrary cap on number of pending async copy operations */ if (atomic_inc_return(&nn->pending_async_copies) > (int)rqstp->rq_pool->sp_nrthreads) - goto out_err; + goto out_dec_async_copy_err; async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) - goto out_err; + goto out_dec_async_copy_err; if (!nfs4_init_copy_state(nn, copy)) - goto out_err; + goto out_dec_async_copy_err; memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, sizeof(result->cb_stateid)); dup_copy_fields(copy, async_copy); async_copy->copy_task = kthread_create(nfsd4_do_async_copy, async_copy, "%s", "copy thread"); if (IS_ERR(async_copy->copy_task)) - goto out_err; + goto out_dec_async_copy_err; spin_lock(&async_copy->cp_clp->async_lock); list_add(&async_copy->copies, &async_copy->cp_clp->async_copies); @@ -1954,6 +1979,9 @@ out: trace_nfsd_copy_done(copy, status); release_copy_files(copy); return status; +out_dec_async_copy_err: + if (async_copy) + atomic_dec(&nn->pending_async_copies); out_err: if (nfsd4_ssc_is_inter(copy)) { /* diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 4a765555bf84..28f4d5311c40 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -82,14 +82,13 @@ nfs4_save_creds(const struct cred **original_creds) new->fsuid = GLOBAL_ROOT_UID; new->fsgid = GLOBAL_ROOT_GID; *original_creds = override_creds(new); - put_cred(new); return 0; } static void nfs4_reset_creds(const struct cred *original) { - revert_creds(original); + put_cred(revert_creds(original)); } static void @@ -2052,7 +2051,6 @@ static inline int check_for_legacy_methods(int status, struct net *net) path_put(&path); if (status) return -ENOTDIR; - status = nn->client_tracking_ops->init(net); } return status; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 741b9449f727..b7a0cfd05401 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1909,15 +1909,84 @@ gen_sessionid(struct nfsd4_session *ses) */ #define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44) +static struct shrinker *nfsd_slot_shrinker; +static DEFINE_SPINLOCK(nfsd_session_list_lock); +static LIST_HEAD(nfsd_session_list); +/* The sum of "target_slots-1" on every session. The shrinker can push this + * down, though it can take a little while for the memory to actually + * be freed. The "-1" is because we can never free slot 0 while the + * session is active. + */ +static atomic_t nfsd_total_target_slots = ATOMIC_INIT(0); + static void -free_session_slots(struct nfsd4_session *ses) +free_session_slots(struct nfsd4_session *ses, int from) { int i; - for (i = 0; i < ses->se_fchannel.maxreqs; i++) { - free_svc_cred(&ses->se_slots[i]->sl_cred); - kfree(ses->se_slots[i]); + if (from >= ses->se_fchannel.maxreqs) + return; + + for (i = from; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + + /* + * Save the seqid in case we reactivate this slot. + * This will never require a memory allocation so GFP + * flag is irrelevant + */ + xa_store(&ses->se_slots, i, xa_mk_value(slot->sl_seqid), 0); + free_svc_cred(&slot->sl_cred); + kfree(slot); } + ses->se_fchannel.maxreqs = from; + if (ses->se_target_maxslots > from) { + int new_target = from ?: 1; + atomic_sub(ses->se_target_maxslots - new_target, &nfsd_total_target_slots); + ses->se_target_maxslots = new_target; + } +} + +/** + * reduce_session_slots - reduce the target max-slots of a session if possible + * @ses: The session to affect + * @dec: how much to decrease the target by + * + * This interface can be used by a shrinker to reduce the target max-slots + * for a session so that some slots can eventually be freed. + * It uses spin_trylock() as it may be called in a context where another + * spinlock is held that has a dependency on client_lock. As shrinkers are + * best-effort, skiping a session is client_lock is already held has no + * great coast + * + * Return value: + * The number of slots that the target was reduced by. + */ +static int +reduce_session_slots(struct nfsd4_session *ses, int dec) +{ + struct nfsd_net *nn = net_generic(ses->se_client->net, + nfsd_net_id); + int ret = 0; + + if (ses->se_target_maxslots <= 1) + return ret; + if (!spin_trylock(&nn->client_lock)) + return ret; + ret = min(dec, ses->se_target_maxslots-1); + ses->se_target_maxslots -= ret; + atomic_sub(ret, &nfsd_total_target_slots); + ses->se_slot_gen += 1; + if (ses->se_slot_gen == 0) { + int i; + ses->se_slot_gen = 1; + for (i = 0; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + slot->sl_generation = 0; + } + } + spin_unlock(&nn->client_lock); + return ret; } /* @@ -1935,89 +2004,46 @@ static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca) return size + sizeof(struct nfsd4_slot); } -/* - * XXX: If we run out of reserved DRC memory we could (up to a point) - * re-negotiate active sessions and reduce their slot usage to make - * room for new connections. For now we just fail the create session. - */ -static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn) -{ - u32 slotsize = slot_bytes(ca); - u32 num = ca->maxreqs; - unsigned long avail, total_avail; - unsigned int scale_factor; - - spin_lock(&nfsd_drc_lock); - if (nfsd_drc_max_mem > nfsd_drc_mem_used) - total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used; - else - /* We have handed out more space than we chose in - * set_max_drc() to allow. That isn't really a - * problem as long as that doesn't make us think we - * have lots more due to integer overflow. - */ - total_avail = 0; - avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail); - /* - * Never use more than a fraction of the remaining memory, - * unless it's the only way to give this client a slot. - * The chosen fraction is either 1/8 or 1/number of threads, - * whichever is smaller. This ensures there are adequate - * slots to support multiple clients per thread. - * Give the client one slot even if that would require - * over-allocation--it is better than failure. - */ - scale_factor = max_t(unsigned int, 8, nn->nfsd_serv->sv_nrthreads); - - avail = clamp_t(unsigned long, avail, slotsize, - total_avail/scale_factor); - num = min_t(int, num, avail / slotsize); - num = max_t(int, num, 1); - nfsd_drc_mem_used += num * slotsize; - spin_unlock(&nfsd_drc_lock); - - return num; -} - -static void nfsd4_put_drc_mem(struct nfsd4_channel_attrs *ca) -{ - int slotsize = slot_bytes(ca); - - spin_lock(&nfsd_drc_lock); - nfsd_drc_mem_used -= slotsize * ca->maxreqs; - spin_unlock(&nfsd_drc_lock); -} - static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, struct nfsd4_channel_attrs *battrs) { int numslots = fattrs->maxreqs; int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; + struct nfsd4_slot *slot; int i; - BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION) - > PAGE_SIZE); - - new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL); + new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; + xa_init(&new->se_slots); /* allocate each struct nfsd4_slot and data cache in one piece */ - for (i = 0; i < numslots; i++) { - new->se_slots[i] = kzalloc(slotsize, GFP_KERNEL); - if (!new->se_slots[i]) - goto out_free; - } + slot = kzalloc(slotsize, GFP_KERNEL); + if (!slot || xa_is_err(xa_store(&new->se_slots, 0, slot, GFP_KERNEL))) + goto out_free; + for (i = 1; i < numslots; i++) { + const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + slot = kzalloc(slotsize, gfp); + if (!slot) + break; + if (xa_is_err(xa_store(&new->se_slots, i, slot, gfp))) { + kfree(slot); + break; + } + } + fattrs->maxreqs = i; memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs)); + new->se_target_maxslots = i; + atomic_add(i - 1, &nfsd_total_target_slots); new->se_cb_slot_avail = ~0U; new->se_cb_highest_slot = min(battrs->maxreqs - 1, NFSD_BC_SLOT_TABLE_SIZE - 1); spin_lock_init(&new->se_lock); return new; out_free: - while (i--) - kfree(new->se_slots[i]); + kfree(slot); + xa_destroy(&new->se_slots); kfree(new); return NULL; } @@ -2123,17 +2149,47 @@ static void nfsd4_del_conns(struct nfsd4_session *s) static void __free_session(struct nfsd4_session *ses) { - free_session_slots(ses); + free_session_slots(ses, 0); + xa_destroy(&ses->se_slots); kfree(ses); } static void free_session(struct nfsd4_session *ses) { nfsd4_del_conns(ses); - nfsd4_put_drc_mem(&ses->se_fchannel); __free_session(ses); } +static unsigned long +nfsd_slot_count(struct shrinker *s, struct shrink_control *sc) +{ + unsigned long cnt = atomic_read(&nfsd_total_target_slots); + + return cnt ? cnt : SHRINK_EMPTY; +} + +static unsigned long +nfsd_slot_scan(struct shrinker *s, struct shrink_control *sc) +{ + struct nfsd4_session *ses; + unsigned long scanned = 0; + unsigned long freed = 0; + + spin_lock(&nfsd_session_list_lock); + list_for_each_entry(ses, &nfsd_session_list, se_all_sessions) { + freed += reduce_session_slots(ses, 1); + scanned += 1; + if (scanned >= sc->nr_to_scan) { + /* Move starting point for next scan */ + list_move(&nfsd_session_list, &ses->se_all_sessions); + break; + } + } + spin_unlock(&nfsd_session_list_lock); + sc->nr_scanned = scanned; + return freed; +} + static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses) { int idx; @@ -2158,6 +2214,10 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru list_add(&new->se_perclnt, &clp->cl_sessions); spin_unlock(&clp->cl_lock); + spin_lock(&nfsd_session_list_lock); + list_add_tail(&new->se_all_sessions, &nfsd_session_list); + spin_unlock(&nfsd_session_list_lock); + { struct sockaddr *sa = svc_addr(rqstp); /* @@ -2227,6 +2287,9 @@ unhash_session(struct nfsd4_session *ses) spin_lock(&ses->se_client->cl_lock); list_del(&ses->se_perclnt); spin_unlock(&ses->se_client->cl_lock); + spin_lock(&nfsd_session_list_lock); + list_del(&ses->se_all_sessions); + spin_unlock(&nfsd_session_list_lock); } /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */ @@ -2362,8 +2425,12 @@ unhash_client_locked(struct nfs4_client *clp) } list_del_init(&clp->cl_lru); spin_lock(&clp->cl_lock); - list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + spin_lock(&nfsd_session_list_lock); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) { list_del_init(&ses->se_hash); + list_del_init(&ses->se_all_sessions); + } + spin_unlock(&nfsd_session_list_lock); spin_unlock(&clp->cl_lock); } @@ -2685,6 +2752,7 @@ static const char *cb_state2str(int state) static int client_info_show(struct seq_file *m, void *v) { struct inode *inode = file_inode(m->file); + struct nfsd4_session *ses; struct nfs4_client *clp; u64 clid; @@ -2721,6 +2789,16 @@ static int client_info_show(struct seq_file *m, void *v) seq_printf(m, "callback address: \"%pISpc\"\n", &clp->cl_cb_conn.cb_addr); seq_printf(m, "admin-revoked states: %d\n", atomic_read(&clp->cl_admin_revoked)); + spin_lock(&clp->cl_lock); + seq_printf(m, "session slots:"); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + seq_printf(m, " %u", ses->se_fchannel.maxreqs); + seq_printf(m, "\nsession target slots:"); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + seq_printf(m, " %u", ses->se_target_maxslots); + spin_unlock(&clp->cl_lock); + seq_puts(m, "\n"); + drop_client(clp); return 0; @@ -2873,6 +2951,21 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) return 0; } +static char *nfs4_show_deleg_type(u32 dl_type) +{ + switch (dl_type) { + case OPEN_DELEGATE_READ: + return "r"; + case OPEN_DELEGATE_WRITE: + return "w"; + case OPEN_DELEGATE_READ_ATTRS_DELEG: + return "ra"; + case OPEN_DELEGATE_WRITE_ATTRS_DELEG: + return "wa"; + } + return "?"; +} + static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_delegation *ds; @@ -2886,8 +2979,7 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: deleg, "); - seq_printf(s, "access: %s", - ds->dl_type == NFS4_OPEN_DELEGATE_READ ? "r" : "w"); + seq_printf(s, "access: %s", nfs4_show_deleg_type(ds->dl_type)); /* XXX: lease time, whether it's being recalled. */ @@ -3708,10 +3800,10 @@ nfsd4_exchange_id_release(union nfsd4_op_u *u) kfree(exid->server_impl_name); } -static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, bool slot_inuse) +static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, u8 flags) { /* The slot is in use, and no response has been sent. */ - if (slot_inuse) { + if (flags & NFSD4_SLOT_INUSE) { if (seqid == slot_seqid) return nfserr_jukebox; else @@ -3720,6 +3812,8 @@ static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, bool slot_inuse) /* Note unsigned 32-bit arithmetic handles wraparound: */ if (likely(seqid == slot_seqid + 1)) return nfs_ok; + if ((flags & NFSD4_SLOT_REUSED) && seqid == 1) + return nfs_ok; if (seqid == slot_seqid) return nfserr_replay_cache; return nfserr_seq_misordered; @@ -3778,17 +3872,6 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs ca->maxresp_cached = min_t(u32, ca->maxresp_cached, NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ); ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION); - /* - * Note decreasing slot size below client's request may make it - * difficult for client to function correctly, whereas - * decreasing the number of slots will (just?) affect - * performance. When short on memory we therefore prefer to - * decrease number of slots instead of their size. Clients that - * request larger slots than they need will get poor results: - * Note that we always allow at least one slot, because our - * accounting is soft and provides no guarantees either way. - */ - ca->maxreqs = nfsd4_get_drc_mem(ca, nn); return nfs_ok; } @@ -3866,11 +3949,11 @@ nfsd4_create_session(struct svc_rqst *rqstp, return status; status = check_backchannel_attrs(&cr_ses->back_channel); if (status) - goto out_release_drc_mem; + goto out_err; status = nfserr_jukebox; new = alloc_session(&cr_ses->fore_channel, &cr_ses->back_channel); if (!new) - goto out_release_drc_mem; + goto out_err; conn = alloc_conn_from_crses(rqstp, cr_ses); if (!conn) goto out_free_session; @@ -3979,8 +4062,7 @@ out_free_conn: free_conn(conn); out_free_session: __free_session(new); -out_release_drc_mem: - nfsd4_put_drc_mem(&cr_ses->fore_channel); +out_err: return status; } @@ -4278,17 +4360,11 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (seq->slotid >= session->se_fchannel.maxreqs) goto out_put_session; - slot = session->se_slots[seq->slotid]; + slot = xa_load(&session->se_slots, seq->slotid); dprintk("%s: slotid %d\n", __func__, seq->slotid); - /* We do not negotiate the number of slots yet, so set the - * maxslots to the session maxreqs which is used to encode - * sr_highest_slotid and the sr_target_slot id to maxslots */ - seq->maxslots = session->se_fchannel.maxreqs; - trace_nfsd_slot_seqid_sequence(clp, seq, slot); - status = check_slot_seqid(seq->seqid, slot->sl_seqid, - slot->sl_flags & NFSD4_SLOT_INUSE); + status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags); if (status == nfserr_replay_cache) { status = nfserr_seq_misordered; if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED)) @@ -4313,6 +4389,12 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out_put_session; + if (session->se_target_maxslots < session->se_fchannel.maxreqs && + slot->sl_generation == session->se_slot_gen && + seq->maxslots <= session->se_target_maxslots) + /* Client acknowledged our reduce maxreqs */ + free_session_slots(session, session->se_target_maxslots); + buflen = (seq->cachethis) ? session->se_fchannel.maxresp_cached : session->se_fchannel.maxresp_sz; @@ -4323,9 +4405,11 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, svc_reserve(rqstp, buflen); status = nfs_ok; - /* Success! bump slot seqid */ + /* Success! accept new slot seqid */ slot->sl_seqid = seq->seqid; + slot->sl_flags &= ~NFSD4_SLOT_REUSED; slot->sl_flags |= NFSD4_SLOT_INUSE; + slot->sl_generation = session->se_slot_gen; if (seq->cachethis) slot->sl_flags |= NFSD4_SLOT_CACHETHIS; else @@ -4335,6 +4419,49 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cstate->session = session; cstate->clp = clp; + /* + * If the client ever uses the highest available slot, + * gently try to allocate another 20%. This allows + * fairly quick growth without grossly over-shooting what + * the client might use. + */ + if (seq->slotid == session->se_fchannel.maxreqs - 1 && + session->se_target_maxslots >= session->se_fchannel.maxreqs && + session->se_fchannel.maxreqs < NFSD_MAX_SLOTS_PER_SESSION) { + int s = session->se_fchannel.maxreqs; + int cnt = DIV_ROUND_UP(s, 5); + void *prev_slot; + + do { + /* + * GFP_NOWAIT both allows allocation under a + * spinlock, and only succeeds if there is + * plenty of memory. + */ + slot = kzalloc(slot_bytes(&session->se_fchannel), + GFP_NOWAIT); + prev_slot = xa_load(&session->se_slots, s); + if (xa_is_value(prev_slot) && slot) { + slot->sl_seqid = xa_to_value(prev_slot); + slot->sl_flags |= NFSD4_SLOT_REUSED; + } + if (slot && + !xa_is_err(xa_store(&session->se_slots, s, slot, + GFP_NOWAIT))) { + s += 1; + session->se_fchannel.maxreqs = s; + atomic_add(s - session->se_target_maxslots, + &nfsd_total_target_slots); + session->se_target_maxslots = s; + } else { + kfree(slot); + slot = NULL; + } + } while (slot && --cnt > 0); + } + seq->maxslots = max(session->se_target_maxslots, seq->maxslots); + seq->target_maxslots = session->se_target_maxslots; + out: switch (clp->cl_cb_state) { case NFSD4_CB_DOWN: @@ -4739,7 +4866,7 @@ static void init_nfs4_replay(struct nfs4_replay *rp) rp->rp_status = nfserr_serverfault; rp->rp_buflen = 0; rp->rp_buf = rp->rp_ibuf; - atomic_set(&rp->rp_locked, RP_UNLOCKED); + rp->rp_locked = RP_UNLOCKED; } static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, @@ -4747,9 +4874,9 @@ static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, { if (!nfsd4_has_session(cstate)) { wait_var_event(&so->so_replay.rp_locked, - atomic_cmpxchg(&so->so_replay.rp_locked, - RP_UNLOCKED, RP_LOCKED) != RP_LOCKED); - if (atomic_read(&so->so_replay.rp_locked) == RP_UNHASHED) + cmpxchg(&so->so_replay.rp_locked, + RP_UNLOCKED, RP_LOCKED) != RP_LOCKED); + if (so->so_replay.rp_locked == RP_UNHASHED) return -EAGAIN; cstate->replay_owner = nfs4_get_stateowner(so); } @@ -4762,9 +4889,7 @@ void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) if (so != NULL) { cstate->replay_owner = NULL; - atomic_set(&so->so_replay.rp_locked, RP_UNLOCKED); - smp_mb__after_atomic(); - wake_up_var(&so->so_replay.rp_locked); + store_release_wake_up(&so->so_replay.rp_locked, RP_UNLOCKED); nfs4_put_stateowner(so); } } @@ -5069,9 +5194,7 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) * Some threads with a reference might be waiting for rp_locked, * so tell them to stop waiting. */ - atomic_set(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED); - smp_mb__after_atomic(); - wake_up_var(&oo->oo_owner.so_replay.rp_locked); + store_release_wake_up(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED); wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2); release_all_access(s); @@ -5472,7 +5595,7 @@ retry: static inline __be32 nfs4_check_delegmode(struct nfs4_delegation *dp, int flags) { - if ((flags & WR_STATE) && (dp->dl_type == NFS4_OPEN_DELEGATE_READ)) + if (!(flags & RD_STATE) && deleg_is_read(dp->dl_type)) return nfserr_openmode; else return nfs_ok; @@ -5704,8 +5827,7 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp) return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN; } -static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp, - int flag) +static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp) { struct file_lease *fl; @@ -5714,7 +5836,7 @@ static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp, return NULL; fl->fl_lmops = &nfsd_lease_mng_ops; fl->c.flc_flags = FL_DELEG; - fl->c.flc_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; + fl->c.flc_type = deleg_is_read(dp->dl_type) ? F_RDLCK : F_WRLCK; fl->c.flc_owner = (fl_owner_t)dp; fl->c.flc_pid = current->tgid; fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file; @@ -5829,13 +5951,14 @@ static struct nfs4_delegation * nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *parent) { - int status = 0; + bool deleg_ts = open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS; struct nfs4_client *clp = stp->st_stid.sc_client; struct nfs4_file *fp = stp->st_stid.sc_file; struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate; struct nfs4_delegation *dp; struct nfsd_file *nf = NULL; struct file_lease *fl; + int status = 0; u32 dl_type; /* @@ -5860,7 +5983,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, */ if ((open->op_share_access & NFS4_SHARE_ACCESS_BOTH) == NFS4_SHARE_ACCESS_BOTH) { nf = find_rw_file(fp); - dl_type = NFS4_OPEN_DELEGATE_WRITE; + dl_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE; } /* @@ -5869,7 +5992,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, */ if (!nf && (open->op_share_access & NFS4_SHARE_ACCESS_READ)) { nf = find_readable_file(fp); - dl_type = NFS4_OPEN_DELEGATE_READ; + dl_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; } if (!nf) @@ -5901,7 +6024,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (!dp) goto out_delegees; - fl = nfs4_alloc_init_lease(dp, dl_type); + fl = nfs4_alloc_init_lease(dp); if (!fl) goto out_clnt_odstate; @@ -5958,20 +6081,20 @@ out_delegees: static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; if (status == -EAGAIN) open->op_why_no_deleg = WND4_CONTENTION; else { open->op_why_no_deleg = WND4_RESOURCE; switch (open->op_deleg_want) { - case NFS4_SHARE_WANT_READ_DELEG: - case NFS4_SHARE_WANT_WRITE_DELEG: - case NFS4_SHARE_WANT_ANY_DELEG: + case OPEN4_SHARE_ACCESS_WANT_READ_DELEG: + case OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG: + case OPEN4_SHARE_ACCESS_WANT_ANY_DELEG: break; - case NFS4_SHARE_WANT_CANCEL: + case OPEN4_SHARE_ACCESS_WANT_CANCEL: open->op_why_no_deleg = WND4_CANCELLED; break; - case NFS4_SHARE_WANT_NO_DELEG: + case OPEN4_SHARE_ACCESS_WANT_NO_DELEG: WARN_ON_ONCE(1); } } @@ -6027,13 +6150,14 @@ static void nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *currentfh) { - struct nfs4_delegation *dp; + bool deleg_ts = open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS; struct nfs4_openowner *oo = openowner(stp->st_stateowner); struct nfs4_client *clp = stp->st_stid.sc_client; struct svc_fh *parent = NULL; - int cb_up; - int status = 0; + struct nfs4_delegation *dp; struct kstat stat; + int status = 0; + int cb_up; cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client); open->op_recall = false; @@ -6074,20 +6198,22 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, destroy_delegation(dp); goto out_no_deleg; } - open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE; + open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : + OPEN_DELEGATE_WRITE; dp->dl_cb_fattr.ncf_cur_fsize = stat.size; dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat); trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); } else { - open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; + open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG : + OPEN_DELEGATE_READ; trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); } nfs4_put_stid(&dp->dl_stid); return; out_no_deleg: - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE; + open->op_delegate_type = OPEN_DELEGATE_NONE; if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && - open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) { + open->op_delegate_type != OPEN_DELEGATE_NONE) { dprintk("NFSD: WARNING: refusing delegation reclaim\n"); open->op_recall = true; } @@ -6101,21 +6227,32 @@ out_no_deleg: static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open, struct nfs4_delegation *dp) { - if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG && - dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; - open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; - } else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG && - dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; - open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; + if (deleg_is_write(dp->dl_type)) { + if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_READ_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; + open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; + } else if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; + open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; + } } /* Otherwise the client must be confused wanting a delegation * it already has, therefore we don't return - * NFS4_OPEN_DELEGATE_NONE_EXT and reason. + * OPEN_DELEGATE_NONE_EXT and reason. */ } +/* Are we returning only a delegation stateid? */ +static bool open_xor_delegation(struct nfsd4_open *open) +{ + if (!(open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION)) + return false; + /* Did we actually get a delegation? */ + if (!deleg_is_read(open->op_delegate_type) && !deleg_is_write(open->op_delegate_type)) + return false; + return true; +} + /** * nfsd4_process_open2 - finish open processing * @rqstp: the RPC transaction being executed @@ -6201,8 +6338,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf mutex_unlock(&stp->st_mutex); if (nfsd4_has_session(&resp->cstate)) { - if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; + if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_NO_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_WANTED; goto nodeleg; } @@ -6213,12 +6350,23 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * OPEN succeeds even if we fail. */ nfs4_open_delegation(open, stp, &resp->cstate.current_fh); + + /* + * If there is an existing open stateid, it must be updated and + * returned. Only respect WANT_OPEN_XOR_DELEGATION when a new + * open stateid would have to be created. + */ + if (new_stp && open_xor_delegation(open)) { + memcpy(&open->op_stateid, &zero_stateid, sizeof(open->op_stateid)); + open->op_rflags |= OPEN4_RESULT_NO_OPEN_STATEID; + release_open_stateid(stp); + } nodeleg: status = nfs_ok; trace_nfsd_open(&stp->st_stid.sc_stateid); out: /* 4.1 client trying to upgrade/downgrade delegation? */ - if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp && + if (open->op_delegate_type == OPEN_DELEGATE_NONE && dp && open->op_deleg_want) nfsd4_deleg_xgrade_none_ext(open, dp); @@ -6229,7 +6377,7 @@ out: /* * To finish the open response, we just need to set the rflags. */ - open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX; + open->op_rflags |= NFS4_OPEN_RESULT_LOCKTYPE_POSIX; if (nfsd4_has_session(&resp->cstate)) open->op_rflags |= NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK; else if (!(open->op_openowner->oo_flags & NFS4_OO_CONFIRMED)) @@ -7966,7 +8114,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_blocked_lock *nbl = NULL; struct file_lock *file_lock = NULL; struct file_lock *conflock = NULL; - struct super_block *sb; __be32 status = 0; int lkflg; int err; @@ -7986,7 +8133,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0); if (status != nfs_ok) return status; - sb = cstate->current_fh.fh_dentry->d_sb; if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) @@ -8721,7 +8867,6 @@ skip_grace: } /* initialization to perform when the nfsd service is started: */ - int nfs4_state_start(void) { @@ -8731,6 +8876,15 @@ nfs4_state_start(void) if (ret) return ret; + nfsd_slot_shrinker = shrinker_alloc(0, "nfsd-DRC-slot"); + if (!nfsd_slot_shrinker) { + rhltable_destroy(&nfs4_file_rhltable); + return -ENOMEM; + } + nfsd_slot_shrinker->count_objects = nfsd_slot_count; + nfsd_slot_shrinker->scan_objects = nfsd_slot_scan; + shrinker_register(nfsd_slot_shrinker); + set_max_delegations(); return 0; } @@ -8772,6 +8926,7 @@ void nfs4_state_shutdown(void) { rhltable_destroy(&nfs4_file_rhltable); + shrinker_free(nfsd_slot_shrinker); } static void @@ -8888,6 +9043,78 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, get_stateid(cstate, &u->write.wr_stateid); } +/** + * set_cb_time - vet and set the timespec for a cb_getattr update + * @cb: timestamp from the CB_GETATTR response + * @orig: original timestamp in the inode + * @now: current time + * + * Given a timestamp in a CB_GETATTR response, check it against the + * current timestamp in the inode and the current time. Returns true + * if the inode's timestamp needs to be updated, and false otherwise. + * @cb may also be changed if the timestamp needs to be clamped. + */ +static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig, + const struct timespec64 *now) +{ + + /* + * "When the time presented is before the original time, then the + * update is ignored." Also no need to update if there is no change. + */ + if (timespec64_compare(cb, orig) <= 0) + return false; + + /* + * "When the time presented is in the future, the server can either + * clamp the new time to the current time, or it may + * return NFS4ERR_DELAY to the client, allowing it to retry." + */ + if (timespec64_compare(cb, now) > 0) { + /* clamp it */ + *cb = *now; + } + + return true; +} + +static int cb_getattr_update_times(struct dentry *dentry, struct nfs4_delegation *dp) +{ + struct inode *inode = d_inode(dentry); + struct timespec64 now = current_time(inode); + struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; + struct iattr attrs = { }; + int ret; + + if (deleg_attrs_deleg(dp->dl_type)) { + struct timespec64 atime = inode_get_atime(inode); + struct timespec64 mtime = inode_get_mtime(inode); + + attrs.ia_atime = ncf->ncf_cb_atime; + attrs.ia_mtime = ncf->ncf_cb_mtime; + + if (set_cb_time(&attrs.ia_atime, &atime, &now)) + attrs.ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; + + if (set_cb_time(&attrs.ia_mtime, &mtime, &now)) { + attrs.ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_SET; + attrs.ia_ctime = attrs.ia_mtime; + } + } else { + attrs.ia_valid |= ATTR_MTIME | ATTR_CTIME; + attrs.ia_mtime = attrs.ia_ctime = now; + } + + if (!attrs.ia_valid) + return 0; + + attrs.ia_valid |= ATTR_DELEG; + inode_lock(inode); + ret = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL); + inode_unlock(inode); + return ret; +} + /** * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict * @rqstp: RPC transaction context @@ -8914,7 +9141,6 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, struct file_lock_context *ctx; struct nfs4_delegation *dp = NULL; struct file_lease *fl; - struct iattr attrs; struct nfs4_cb_fattr *ncf; struct inode *inode = d_inode(dentry); @@ -8976,11 +9202,7 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, * not update the file's metadata with the client's * modified size */ - attrs.ia_mtime = attrs.ia_ctime = current_time(inode); - attrs.ia_valid = ATTR_MTIME | ATTR_CTIME | ATTR_DELEG; - inode_lock(inode); - err = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL); - inode_unlock(inode); + err = cb_getattr_update_times(dentry, dp); if (err) { status = nfserrno(err); goto out_status; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 53fac037611c..e67420729ecd 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -55,6 +55,7 @@ #include "netns.h" #include "pnfs.h" #include "filecache.h" +#include "nfs4xdr_gen.h" #include "trace.h" @@ -520,6 +521,26 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, *umask = mask & S_IRWXUGO; iattr->ia_valid |= ATTR_MODE; } + if (bmval[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) { + fattr4_time_deleg_access access; + + if (!xdrgen_decode_fattr4_time_deleg_access(argp->xdr, &access)) + return nfserr_bad_xdr; + iattr->ia_atime.tv_sec = access.seconds; + iattr->ia_atime.tv_nsec = access.nseconds; + iattr->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET | ATTR_DELEG; + } + if (bmval[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) { + fattr4_time_deleg_modify modify; + + if (!xdrgen_decode_fattr4_time_deleg_modify(argp->xdr, &modify)) + return nfserr_bad_xdr; + iattr->ia_mtime.tv_sec = modify.seconds; + iattr->ia_mtime.tv_nsec = modify.nseconds; + iattr->ia_ctime.tv_sec = modify.seconds; + iattr->ia_ctime.tv_nsec = modify.seconds; + iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_SET | ATTR_DELEG; + } /* request sanity: did attrlist4 contain the expected number of words? */ if (attrlist4_count != xdr_stream_pos(argp->xdr) - starting_pos) @@ -1066,13 +1087,13 @@ static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *sh return nfs_ok; if (!argp->minorversion) return nfserr_bad_xdr; - switch (w & NFS4_SHARE_WANT_MASK) { - case NFS4_SHARE_WANT_NO_PREFERENCE: - case NFS4_SHARE_WANT_READ_DELEG: - case NFS4_SHARE_WANT_WRITE_DELEG: - case NFS4_SHARE_WANT_ANY_DELEG: - case NFS4_SHARE_WANT_NO_DELEG: - case NFS4_SHARE_WANT_CANCEL: + switch (w & NFS4_SHARE_WANT_TYPE_MASK) { + case OPEN4_SHARE_ACCESS_WANT_NO_PREFERENCE: + case OPEN4_SHARE_ACCESS_WANT_READ_DELEG: + case OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG: + case OPEN4_SHARE_ACCESS_WANT_ANY_DELEG: + case OPEN4_SHARE_ACCESS_WANT_NO_DELEG: + case OPEN4_SHARE_ACCESS_WANT_CANCEL: break; default: return nfserr_bad_xdr; @@ -1884,7 +1905,8 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, return nfserr_bad_xdr; seq->seqid = be32_to_cpup(p++); seq->slotid = be32_to_cpup(p++); - seq->maxslots = be32_to_cpup(p++); + /* sa_highest_slotid counts from 0 but maxslots counts from 1 ... */ + seq->maxslots = be32_to_cpup(p++) + 1; seq->cachethis = be32_to_cpup(p); seq->status_flags = 0; @@ -2818,11 +2840,11 @@ static __be32 nfsd4_encode_nfsace4(struct xdr_stream *xdr, struct svc_rqst *rqst #ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, - void *context, int len) + const struct lsm_context *context) { __be32 *p; - p = xdr_reserve_space(xdr, len + 4 + 4 + 4); + p = xdr_reserve_space(xdr, context->len + 4 + 4 + 4); if (!p) return nfserr_resource; @@ -2832,13 +2854,13 @@ nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, */ *p++ = cpu_to_be32(0); /* lfs */ *p++ = cpu_to_be32(0); /* pi */ - p = xdr_encode_opaque(p, context, len); + p = xdr_encode_opaque(p, context->context, context->len); return 0; } #else static inline __be32 nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, - void *context, int len) + struct lsm_context *context) { return 0; } #endif @@ -2919,9 +2941,9 @@ struct nfsd4_fattr_args { struct kstat stat; struct kstatfs statfs; struct nfs4_acl *acl; + u64 change_attr; #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - void *context; - int contextlen; + struct lsm_context context; #endif u32 rdattr_err; bool contextsupport; @@ -3018,7 +3040,6 @@ static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr, const struct nfsd4_fattr_args *args) { const struct svc_export *exp = args->exp; - u64 c; if (unlikely(exp->ex_flags & NFSEXP_V4ROOT)) { u32 flush_time = convert_to_wallclock(exp->cd->flush_time); @@ -3029,9 +3050,7 @@ static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr, return nfserr_resource; return nfs_ok; } - - c = nfsd4_change_attribute(&args->stat); - return nfsd4_encode_changeid4(xdr, c); + return nfsd4_encode_changeid4(xdr, args->change_attr); } static __be32 nfsd4_encode_fattr4_size(struct xdr_stream *xdr, @@ -3376,8 +3395,7 @@ static __be32 nfsd4_encode_fattr4_suppattr_exclcreat(struct xdr_stream *xdr, static __be32 nfsd4_encode_fattr4_sec_label(struct xdr_stream *xdr, const struct nfsd4_fattr_args *args) { - return nfsd4_encode_security_label(xdr, args->rqstp, - args->context, args->contextlen); + return nfsd4_encode_security_label(xdr, args->rqstp, &args->context); } #endif @@ -3389,6 +3407,56 @@ static __be32 nfsd4_encode_fattr4_xattr_support(struct xdr_stream *xdr, return nfsd4_encode_bool(xdr, err == 0); } +#define NFSD_OA_SHARE_ACCESS (BIT(OPEN_ARGS_SHARE_ACCESS_READ) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WRITE) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_BOTH)) + +#define NFSD_OA_SHARE_DENY (BIT(OPEN_ARGS_SHARE_DENY_NONE) | \ + BIT(OPEN_ARGS_SHARE_DENY_READ) | \ + BIT(OPEN_ARGS_SHARE_DENY_WRITE) | \ + BIT(OPEN_ARGS_SHARE_DENY_BOTH)) + +#define NFSD_OA_SHARE_ACCESS_WANT (BIT(OPEN_ARGS_SHARE_ACCESS_WANT_ANY_DELEG) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WANT_NO_DELEG) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WANT_CANCEL) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS) | \ + BIT(OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION)) + +#define NFSD_OA_OPEN_CLAIM (BIT(OPEN_ARGS_OPEN_CLAIM_NULL) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_PREVIOUS) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_DELEGATE_CUR) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_DELEGATE_PREV)| \ + BIT(OPEN_ARGS_OPEN_CLAIM_FH) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH) | \ + BIT(OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH)) + +#define NFSD_OA_CREATE_MODE (BIT(OPEN_ARGS_CREATEMODE_UNCHECKED4) | \ + BIT(OPEN_ARGS_CREATE_MODE_GUARDED) | \ + BIT(OPEN_ARGS_CREATEMODE_EXCLUSIVE4) | \ + BIT(OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1)) + +static uint32_t oa_share_access = NFSD_OA_SHARE_ACCESS; +static uint32_t oa_share_deny = NFSD_OA_SHARE_DENY; +static uint32_t oa_share_access_want = NFSD_OA_SHARE_ACCESS_WANT; +static uint32_t oa_open_claim = NFSD_OA_OPEN_CLAIM; +static uint32_t oa_create_mode = NFSD_OA_CREATE_MODE; + +static const struct open_arguments4 nfsd_open_arguments = { + .oa_share_access = { .count = 1, .element = &oa_share_access }, + .oa_share_deny = { .count = 1, .element = &oa_share_deny }, + .oa_share_access_want = { .count = 1, .element = &oa_share_access_want }, + .oa_open_claim = { .count = 1, .element = &oa_open_claim }, + .oa_create_mode = { .count = 1, .element = &oa_create_mode }, +}; + +static __be32 nfsd4_encode_fattr4_open_arguments(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + if (!xdrgen_encode_fattr4_open_arguments(xdr, &nfsd_open_arguments)) + return nfserr_resource; + return nfs_ok; +} + static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = { [FATTR4_SUPPORTED_ATTRS] = nfsd4_encode_fattr4_supported_attrs, [FATTR4_TYPE] = nfsd4_encode_fattr4_type, @@ -3489,6 +3557,7 @@ static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = { [FATTR4_MODE_UMASK] = nfsd4_encode_fattr4__noop, [FATTR4_XATTR_SUPPORT] = nfsd4_encode_fattr4_xattr_support, + [FATTR4_OPEN_ARGUMENTS] = nfsd4_encode_fattr4_open_arguments, }; /* @@ -3506,8 +3575,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct nfsd4_fattr_args args; struct svc_fh *tempfh = NULL; int starting_len = xdr->buf->len; - __be32 *attrlen_p, status; - int attrlen_offset; + unsigned int attrlen_offset; + __be32 attrlen, status; u32 attrmask[3]; int err; struct nfsd4_compoundres *resp = rqstp->rq_resp; @@ -3527,7 +3596,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, args.ignore_crossmnt = (ignore_crossmnt != 0); args.acl = NULL; #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - args.context = NULL; + args.context.context = NULL; #endif /* @@ -3544,7 +3613,11 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; } - if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { + if ((attrmask[0] & (FATTR4_WORD0_CHANGE | + FATTR4_WORD0_SIZE)) || + (attrmask[1] & (FATTR4_WORD1_TIME_ACCESS | + FATTR4_WORD1_TIME_MODIFY | + FATTR4_WORD1_TIME_METADATA))) { status = nfsd4_deleg_getattr_conflict(rqstp, dentry, &dp); if (status) goto out; @@ -3556,11 +3629,22 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (dp) { struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; - if (ncf->ncf_file_modified) + if (ncf->ncf_file_modified) { + ++ncf->ncf_initial_cinfo; args.stat.size = ncf->ncf_cur_fsize; + if (!timespec64_is_epoch(&ncf->ncf_cb_mtime)) + args.stat.mtime = ncf->ncf_cb_mtime; + } + args.change_attr = ncf->ncf_initial_cinfo; + + if (!timespec64_is_epoch(&ncf->ncf_cb_atime)) + args.stat.atime = ncf->ncf_cb_atime; nfs4_put_stid(&dp->dl_stid); + } else { + args.change_attr = nfsd4_change_attribute(&args.stat); } + if (err) goto out_nfserr; @@ -3607,7 +3691,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { if (exp->ex_flags & NFSEXP_SECURITY_LABEL) err = security_inode_getsecctx(d_inode(dentry), - &args.context, &args.contextlen); + &args.context); else err = -EOPNOTSUPP; args.contextsupport = (err == 0); @@ -3628,8 +3712,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, /* attr_vals */ attrlen_offset = xdr->buf->len; - attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); - if (!attrlen_p) + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT))) goto out_resource; bitmap_from_arr32(attr_bitmap, attrmask, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); @@ -3639,13 +3722,14 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (status != nfs_ok) goto out; } - *attrlen_p = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT); + attrlen = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT); + write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, XDR_UNIT); status = nfs_ok; out: #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if (args.context) - security_release_secctx(args.context, args.contextlen); + if (args.context.context) + security_release_secctx(&args.context); #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ kfree(args.acl); if (tempfh) { @@ -4229,18 +4313,20 @@ nfsd4_encode_open_delegation4(struct xdr_stream *xdr, struct nfsd4_open *open) if (xdr_stream_encode_u32(xdr, open->op_delegate_type) != XDR_UNIT) return nfserr_resource; switch (open->op_delegate_type) { - case NFS4_OPEN_DELEGATE_NONE: + case OPEN_DELEGATE_NONE: status = nfs_ok; break; - case NFS4_OPEN_DELEGATE_READ: + case OPEN_DELEGATE_READ: + case OPEN_DELEGATE_READ_ATTRS_DELEG: /* read */ status = nfsd4_encode_open_read_delegation4(xdr, open); break; - case NFS4_OPEN_DELEGATE_WRITE: + case OPEN_DELEGATE_WRITE: + case OPEN_DELEGATE_WRITE_ATTRS_DELEG: /* write */ status = nfsd4_encode_open_write_delegation4(xdr, open); break; - case NFS4_OPEN_DELEGATE_NONE_EXT: + case OPEN_DELEGATE_NONE_EXT: /* od_whynone */ status = nfsd4_encode_open_none_delegation4(xdr, open); break; @@ -4316,6 +4402,15 @@ static __be32 nfsd4_encode_splice_read( int status, space_left; __be32 nfserr; + /* + * Splice read doesn't work if encoding has already wandered + * into the XDR buf's page array. + */ + if (unlikely(xdr->buf->page_len)) { + WARN_ON_ONCE(1); + return nfserr_serverfault; + } + /* * Make sure there is room at the end of buf->head for * svcxdr_encode_opaque_pages() to create a tail buffer @@ -4398,25 +4493,23 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp; struct nfsd4_read *read = &u->read; struct xdr_stream *xdr = resp->xdr; - int starting_len = xdr->buf->len; bool splice_ok = argp->splice_ok; + unsigned int eof_offset; unsigned long maxcount; + __be32 wire_data[2]; struct file *file; - __be32 *p; if (nfserr) return nfserr; + + eof_offset = xdr->buf->len; file = read->rd_nf->nf_file; - p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ - if (!p) { + /* Reserve space for the eof flag and byte count */ + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT * 2))) { WARN_ON_ONCE(splice_ok); return nfserr_resource; } - if (resp->xdr->buf->page_len && splice_ok) { - WARN_ON_ONCE(1); - return nfserr_serverfault; - } xdr_commit_encode(xdr); maxcount = min_t(unsigned long, read->rd_length, @@ -4427,12 +4520,13 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, else nfserr = nfsd4_encode_readv(resp, read, file, maxcount); if (nfserr) { - xdr_truncate_encode(xdr, starting_len); + xdr_truncate_encode(xdr, eof_offset); return nfserr; } - p = xdr_encode_bool(p, read->rd_eof); - *p = cpu_to_be32(read->rd_length); + wire_data[0] = read->rd_eof ? xdr_one : xdr_zero; + wire_data[1] = cpu_to_be32(read->rd_length); + write_bytes_to_xdr_buf(xdr->buf, eof_offset, &wire_data, XDR_UNIT * 2); return nfs_ok; } @@ -4441,25 +4535,21 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_readlink *readlink = &u->readlink; - __be32 *p, *maxcount_p, zero = xdr_zero; + __be32 *p, wire_count, zero = xdr_zero; struct xdr_stream *xdr = resp->xdr; - int length_offset = xdr->buf->len; + unsigned int length_offset; int maxcount, status; - maxcount_p = xdr_reserve_space(xdr, XDR_UNIT); - if (!maxcount_p) + /* linktext4.count */ + length_offset = xdr->buf->len; + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT))) return nfserr_resource; - maxcount = PAGE_SIZE; + /* linktext4.data */ + maxcount = PAGE_SIZE; p = xdr_reserve_space(xdr, maxcount); if (!p) return nfserr_resource; - /* - * XXX: By default, vfs_readlink() will truncate symlinks if they - * would overflow the buffer. Is this kosher in NFSv4? If not, one - * easy fix is: if vfs_readlink() precisely fills the buffer, assume - * that truncation occurred, and return NFS4ERR_RESOURCE. - */ nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp, (char *)p, &maxcount); if (nfserr == nfserr_isdir) @@ -4472,7 +4562,9 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, nfserr = nfserrno(status); goto out_err; } - *maxcount_p = cpu_to_be32(maxcount); + + wire_count = cpu_to_be32(maxcount); + write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, XDR_UNIT); xdr_truncate_encode(xdr, length_offset + 4 + xdr_align_size(maxcount)); write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, &zero, xdr_pad_size(maxcount)); @@ -4607,14 +4699,42 @@ nfsd4_encode_rpcsec_gss_info(struct xdr_stream *xdr, } static __be32 -nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) +nfsd4_encode_secinfo4(struct xdr_stream *xdr, rpc_authflavor_t pf, + u32 *supported) +{ + struct rpcsec_gss_info info; + __be32 status; + + if (rpcauth_get_gssinfo(pf, &info) == 0) { + (*supported)++; + + /* flavor */ + status = nfsd4_encode_uint32_t(xdr, RPC_AUTH_GSS); + if (status != nfs_ok) + return status; + /* flavor_info */ + status = nfsd4_encode_rpcsec_gss_info(xdr, &info); + if (status != nfs_ok) + return status; + } else if (pf < RPC_AUTH_MAXFLAVOR) { + (*supported)++; + + /* flavor */ + status = nfsd4_encode_uint32_t(xdr, pf); + if (status != nfs_ok) + return status; + } + return nfs_ok; +} + +static __be32 +nfsd4_encode_SECINFO4resok(struct xdr_stream *xdr, struct svc_export *exp) { u32 i, nflavs, supported; struct exp_flavor_info *flavs; struct exp_flavor_info def_flavs[2]; - static bool report = true; - __be32 *flavorsp; - __be32 status; + unsigned int count_offset; + __be32 status, wire_count; if (exp->ex_nflavors) { flavs = exp->ex_flavors; @@ -4636,43 +4756,20 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) } } - supported = 0; - flavorsp = xdr_reserve_space(xdr, XDR_UNIT); - if (!flavorsp) + count_offset = xdr->buf->len; + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT))) return nfserr_resource; - for (i = 0; i < nflavs; i++) { - rpc_authflavor_t pf = flavs[i].pseudoflavor; - struct rpcsec_gss_info info; - - if (rpcauth_get_gssinfo(pf, &info) == 0) { - supported++; - - /* flavor */ - status = nfsd4_encode_uint32_t(xdr, RPC_AUTH_GSS); - if (status != nfs_ok) - return status; - /* flavor_info */ - status = nfsd4_encode_rpcsec_gss_info(xdr, &info); - if (status != nfs_ok) - return status; - } else if (pf < RPC_AUTH_MAXFLAVOR) { - supported++; - - /* flavor */ - status = nfsd4_encode_uint32_t(xdr, pf); - if (status != nfs_ok) - return status; - } else { - if (report) - pr_warn("NFS: SECINFO: security flavor %u " - "is not supported\n", pf); - } + for (i = 0, supported = 0; i < nflavs; i++) { + status = nfsd4_encode_secinfo4(xdr, flavs[i].pseudoflavor, + &supported); + if (status != nfs_ok) + return status; } - if (nflavs != supported) - report = false; - *flavorsp = cpu_to_be32(supported); + wire_count = cpu_to_be32(supported); + write_bytes_to_xdr_buf(xdr->buf, count_offset, &wire_count, + XDR_UNIT); return 0; } @@ -4683,7 +4780,7 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_secinfo *secinfo = &u->secinfo; struct xdr_stream *xdr = resp->xdr; - return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp); + return nfsd4_encode_SECINFO4resok(xdr, secinfo->si_exp); } static __be32 @@ -4693,7 +4790,7 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_secinfo_no_name *secinfo = &u->secinfo_no_name; struct xdr_stream *xdr = resp->xdr; - return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp); + return nfsd4_encode_SECINFO4resok(xdr, secinfo->sin_exp); } static __be32 @@ -4968,7 +5065,7 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, if (nfserr != nfs_ok) return nfserr; /* sr_target_highest_slotid */ - nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots - 1); + nfserr = nfsd4_encode_slotid4(xdr, seq->target_maxslots - 1); if (nfserr != nfs_ok) return nfserr; /* sr_status_flags */ @@ -5296,17 +5393,20 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, struct file *file = read->rd_nf->nf_file; struct xdr_stream *xdr = resp->xdr; bool splice_ok = argp->splice_ok; + unsigned int offset_offset; + __be32 nfserr, wire_count; unsigned long maxcount; - __be32 nfserr, *p; + __be64 wire_offset; - /* Content type, offset, byte count */ - p = xdr_reserve_space(xdr, 4 + 8 + 4); - if (!p) + if (xdr_stream_encode_u32(xdr, NFS4_CONTENT_DATA) != XDR_UNIT) return nfserr_io; - if (resp->xdr->buf->page_len && splice_ok) { - WARN_ON_ONCE(splice_ok); - return nfserr_serverfault; - } + + offset_offset = xdr->buf->len; + + /* Reserve space for the byte offset and count */ + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT * 3))) + return nfserr_io; + xdr_commit_encode(xdr); maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); @@ -5318,10 +5418,12 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, if (nfserr) return nfserr; - *p++ = cpu_to_be32(NFS4_CONTENT_DATA); - p = xdr_encode_hyper(p, read->rd_offset); - *p = cpu_to_be32(read->rd_length); - + wire_offset = cpu_to_be64(read->rd_offset); + write_bytes_to_xdr_buf(xdr->buf, offset_offset, &wire_offset, + XDR_UNIT * 2); + wire_count = cpu_to_be32(read->rd_length); + write_bytes_to_xdr_buf(xdr->buf, offset_offset + XDR_UNIT * 2, + &wire_count, XDR_UNIT); return nfs_ok; } @@ -5332,16 +5434,17 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_read *read = &u->read; struct file *file = read->rd_nf->nf_file; struct xdr_stream *xdr = resp->xdr; - int starting_len = xdr->buf->len; + unsigned int eof_offset; + __be32 wire_data[2]; u32 segments = 0; - __be32 *p; if (nfserr) return nfserr; - /* eof flag, segment count */ - p = xdr_reserve_space(xdr, 4 + 4); - if (!p) + eof_offset = xdr->buf->len; + + /* Reserve space for the eof flag and segment count */ + if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT * 2))) return nfserr_io; xdr_commit_encode(xdr); @@ -5351,15 +5454,16 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, nfserr = nfsd4_encode_read_plus_data(resp, read); if (nfserr) { - xdr_truncate_encode(xdr, starting_len); + xdr_truncate_encode(xdr, eof_offset); return nfserr; } segments++; out: - p = xdr_encode_bool(p, read->rd_eof); - *p = cpu_to_be32(segments); + wire_data[0] = read->rd_eof ? xdr_one : xdr_zero; + wire_data[1] = cpu_to_be32(segments); + write_bytes_to_xdr_buf(xdr->buf, eof_offset, &wire_data, XDR_UNIT * 2); return nfserr; } @@ -5760,15 +5864,14 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) struct nfs4_stateowner *so = resp->cstate.replay_owner; struct svc_rqst *rqstp = resp->rqstp; const struct nfsd4_operation *opdesc = op->opdesc; - int post_err_offset; + unsigned int op_status_offset; nfsd4_enc encoder; - __be32 *p; - p = xdr_reserve_space(xdr, 8); - if (!p) + if (xdr_stream_encode_u32(xdr, op->opnum) != XDR_UNIT) + goto release; + op_status_offset = xdr->buf->len; + if (!xdr_reserve_space(xdr, XDR_UNIT)) goto release; - *p++ = cpu_to_be32(op->opnum); - post_err_offset = xdr->buf->len; if (op->opnum == OP_ILLEGAL) goto status; @@ -5809,20 +5912,21 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) * bug if we had to do this on a non-idempotent op: */ warn_on_nonidempotent_op(op); - xdr_truncate_encode(xdr, post_err_offset); + xdr_truncate_encode(xdr, op_status_offset + XDR_UNIT); } if (so) { - int len = xdr->buf->len - post_err_offset; + int len = xdr->buf->len - (op_status_offset + XDR_UNIT); so->so_replay.rp_status = op->status; so->so_replay.rp_buflen = len; - read_bytes_from_xdr_buf(xdr->buf, post_err_offset, + read_bytes_from_xdr_buf(xdr->buf, op_status_offset + XDR_UNIT, so->so_replay.rp_buf, len); } status: op->status = nfsd4_map_status(op->status, resp->cstate.minorversion); - *p = op->status; + write_bytes_to_xdr_buf(xdr->buf, op_status_offset, + &op->status, XDR_UNIT); release: if (opdesc && opdesc->op_release) opdesc->op_release(&op->u); diff --git a/fs/nfsd/nfs4xdr_gen.c b/fs/nfsd/nfs4xdr_gen.c new file mode 100644 index 000000000000..a17b5d8e60b3 --- /dev/null +++ b/fs/nfsd/nfs4xdr_gen.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0 +// Generated by xdrgen. Manual edits will be lost. +// XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x +// XDR specification modification time: Mon Oct 14 09:10:13 2024 + +#include + +#include "nfs4xdr_gen.h" + +static bool __maybe_unused +xdrgen_decode_int64_t(struct xdr_stream *xdr, int64_t *ptr) +{ + return xdrgen_decode_hyper(xdr, ptr); +}; + +static bool __maybe_unused +xdrgen_decode_uint32_t(struct xdr_stream *xdr, uint32_t *ptr) +{ + return xdrgen_decode_unsigned_int(xdr, ptr); +}; + +static bool __maybe_unused +xdrgen_decode_bitmap4(struct xdr_stream *xdr, bitmap4 *ptr) +{ + if (xdr_stream_decode_u32(xdr, &ptr->count) < 0) + return false; + for (u32 i = 0; i < ptr->count; i++) + if (!xdrgen_decode_uint32_t(xdr, &ptr->element[i])) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_decode_nfstime4(struct xdr_stream *xdr, struct nfstime4 *ptr) +{ + if (!xdrgen_decode_int64_t(xdr, &ptr->seconds)) + return false; + if (!xdrgen_decode_uint32_t(xdr, &ptr->nseconds)) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_decode_fattr4_offline(struct xdr_stream *xdr, fattr4_offline *ptr) +{ + return xdrgen_decode_bool(xdr, ptr); +}; + +static bool __maybe_unused +xdrgen_decode_open_arguments4(struct xdr_stream *xdr, struct open_arguments4 *ptr) +{ + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_access)) + return false; + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_deny)) + return false; + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_access_want)) + return false; + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_open_claim)) + return false; + if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_create_mode)) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_decode_open_args_share_access4(struct xdr_stream *xdr, open_args_share_access4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_decode_open_args_share_deny4(struct xdr_stream *xdr, open_args_share_deny4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_decode_open_args_share_access_want4(struct xdr_stream *xdr, open_args_share_access_want4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_decode_open_args_open_claim4(struct xdr_stream *xdr, open_args_open_claim4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_decode_open_args_createmode4(struct xdr_stream *xdr, open_args_createmode4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +bool +xdrgen_decode_fattr4_open_arguments(struct xdr_stream *xdr, fattr4_open_arguments *ptr) +{ + return xdrgen_decode_open_arguments4(xdr, ptr); +}; + +bool +xdrgen_decode_fattr4_time_deleg_access(struct xdr_stream *xdr, fattr4_time_deleg_access *ptr) +{ + return xdrgen_decode_nfstime4(xdr, ptr); +}; + +bool +xdrgen_decode_fattr4_time_deleg_modify(struct xdr_stream *xdr, fattr4_time_deleg_modify *ptr) +{ + return xdrgen_decode_nfstime4(xdr, ptr); +}; + +static bool __maybe_unused +xdrgen_decode_open_delegation_type4(struct xdr_stream *xdr, open_delegation_type4 *ptr) +{ + u32 val; + + if (xdr_stream_decode_u32(xdr, &val) < 0) + return false; + *ptr = val; + return true; +} + +static bool __maybe_unused +xdrgen_encode_int64_t(struct xdr_stream *xdr, const int64_t value) +{ + return xdrgen_encode_hyper(xdr, value); +}; + +static bool __maybe_unused +xdrgen_encode_uint32_t(struct xdr_stream *xdr, const uint32_t value) +{ + return xdrgen_encode_unsigned_int(xdr, value); +}; + +static bool __maybe_unused +xdrgen_encode_bitmap4(struct xdr_stream *xdr, const bitmap4 value) +{ + if (xdr_stream_encode_u32(xdr, value.count) != XDR_UNIT) + return false; + for (u32 i = 0; i < value.count; i++) + if (!xdrgen_encode_uint32_t(xdr, value.element[i])) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_encode_nfstime4(struct xdr_stream *xdr, const struct nfstime4 *value) +{ + if (!xdrgen_encode_int64_t(xdr, value->seconds)) + return false; + if (!xdrgen_encode_uint32_t(xdr, value->nseconds)) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_encode_fattr4_offline(struct xdr_stream *xdr, const fattr4_offline value) +{ + return xdrgen_encode_bool(xdr, value); +}; + +static bool __maybe_unused +xdrgen_encode_open_arguments4(struct xdr_stream *xdr, const struct open_arguments4 *value) +{ + if (!xdrgen_encode_bitmap4(xdr, value->oa_share_access)) + return false; + if (!xdrgen_encode_bitmap4(xdr, value->oa_share_deny)) + return false; + if (!xdrgen_encode_bitmap4(xdr, value->oa_share_access_want)) + return false; + if (!xdrgen_encode_bitmap4(xdr, value->oa_open_claim)) + return false; + if (!xdrgen_encode_bitmap4(xdr, value->oa_create_mode)) + return false; + return true; +}; + +static bool __maybe_unused +xdrgen_encode_open_args_share_access4(struct xdr_stream *xdr, open_args_share_access4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +static bool __maybe_unused +xdrgen_encode_open_args_share_deny4(struct xdr_stream *xdr, open_args_share_deny4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +static bool __maybe_unused +xdrgen_encode_open_args_share_access_want4(struct xdr_stream *xdr, open_args_share_access_want4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +static bool __maybe_unused +xdrgen_encode_open_args_open_claim4(struct xdr_stream *xdr, open_args_open_claim4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +static bool __maybe_unused +xdrgen_encode_open_args_createmode4(struct xdr_stream *xdr, open_args_createmode4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} + +bool +xdrgen_encode_fattr4_open_arguments(struct xdr_stream *xdr, const fattr4_open_arguments *value) +{ + return xdrgen_encode_open_arguments4(xdr, value); +}; + +bool +xdrgen_encode_fattr4_time_deleg_access(struct xdr_stream *xdr, const fattr4_time_deleg_access *value) +{ + return xdrgen_encode_nfstime4(xdr, value); +}; + +bool +xdrgen_encode_fattr4_time_deleg_modify(struct xdr_stream *xdr, const fattr4_time_deleg_modify *value) +{ + return xdrgen_encode_nfstime4(xdr, value); +}; + +static bool __maybe_unused +xdrgen_encode_open_delegation_type4(struct xdr_stream *xdr, open_delegation_type4 value) +{ + return xdr_stream_encode_u32(xdr, value) == XDR_UNIT; +} diff --git a/fs/nfsd/nfs4xdr_gen.h b/fs/nfsd/nfs4xdr_gen.h new file mode 100644 index 000000000000..41a0033b7256 --- /dev/null +++ b/fs/nfsd/nfs4xdr_gen.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Generated by xdrgen. Manual edits will be lost. */ +/* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */ +/* XDR specification modification time: Mon Oct 14 09:10:13 2024 */ + +#ifndef _LINUX_XDRGEN_NFS4_1_DECL_H +#define _LINUX_XDRGEN_NFS4_1_DECL_H + +#include + +#include +#include +#include +#include + +bool xdrgen_decode_fattr4_open_arguments(struct xdr_stream *xdr, fattr4_open_arguments *ptr); +bool xdrgen_encode_fattr4_open_arguments(struct xdr_stream *xdr, const fattr4_open_arguments *value); + +bool xdrgen_decode_fattr4_time_deleg_access(struct xdr_stream *xdr, fattr4_time_deleg_access *ptr); +bool xdrgen_encode_fattr4_time_deleg_access(struct xdr_stream *xdr, const fattr4_time_deleg_access *value); + +bool xdrgen_decode_fattr4_time_deleg_modify(struct xdr_stream *xdr, fattr4_time_deleg_modify *ptr); +bool xdrgen_encode_fattr4_time_deleg_modify(struct xdr_stream *xdr, const fattr4_time_deleg_modify *value); + +#endif /* _LINUX_XDRGEN_NFS4_1_DECL_H */ diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 3adbc05ebaac..ce2a71e4904c 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -48,7 +48,6 @@ enum { NFSD_Versions, NFSD_Ports, NFSD_MaxBlkSize, - NFSD_MaxConnections, NFSD_Filecache, NFSD_Leasetime, NFSD_Gracetime, @@ -68,7 +67,6 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size); static ssize_t write_versions(struct file *file, char *buf, size_t size); static ssize_t write_ports(struct file *file, char *buf, size_t size); static ssize_t write_maxblksize(struct file *file, char *buf, size_t size); -static ssize_t write_maxconn(struct file *file, char *buf, size_t size); #ifdef CONFIG_NFSD_V4 static ssize_t write_leasetime(struct file *file, char *buf, size_t size); static ssize_t write_gracetime(struct file *file, char *buf, size_t size); @@ -87,7 +85,6 @@ static ssize_t (*const write_op[])(struct file *, char *, size_t) = { [NFSD_Versions] = write_versions, [NFSD_Ports] = write_ports, [NFSD_MaxBlkSize] = write_maxblksize, - [NFSD_MaxConnections] = write_maxconn, #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = write_leasetime, [NFSD_Gracetime] = write_gracetime, @@ -902,44 +899,6 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) nfsd_max_blksize); } -/* - * write_maxconn - Set or report the current max number of connections - * - * Input: - * buf: ignored - * size: zero - * OR - * - * Input: - * buf: C string containing an unsigned - * integer value representing the new - * number of max connections - * size: non-zero length of C string in @buf - * Output: - * On success: passed-in buffer filled with '\n'-terminated C string - * containing numeric value of max_connections setting - * for this net namespace; - * return code is the size in bytes of the string - * On error: return code is zero or a negative errno value - */ -static ssize_t write_maxconn(struct file *file, char *buf, size_t size) -{ - char *mesg = buf; - struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); - unsigned int maxconn = nn->max_connections; - - if (size > 0) { - int rv = get_uint(&mesg, &maxconn); - - if (rv) - return rv; - trace_nfsd_ctl_maxconn(netns(file), maxconn); - nn->max_connections = maxconn; - } - - return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%u\n", maxconn); -} - #ifdef CONFIG_NFSD_V4 static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, time64_t *time, struct nfsd_net *nn) @@ -1372,7 +1331,6 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) [NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO}, - [NFSD_MaxConnections] = {"max_connections", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_Filecache] = {"filecache", &nfsd_file_cache_stats_fops, S_IRUGO}, #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR}, @@ -2259,6 +2217,7 @@ static __net_init int nfsd_net_init(struct net *net) seqlock_init(&nn->writeverf_lock); nfsd_proc_stat_init(net); #if IS_ENABLED(CONFIG_NFS_LOCALIO) + spin_lock_init(&nn->local_clients_lock); INIT_LIST_HEAD(&nn->local_clients); #endif return 0; @@ -2276,14 +2235,15 @@ out_export_error: * nfsd_net_pre_exit - Disconnect localio clients from net namespace * @net: a network namespace that is about to be destroyed * - * This invalidated ->net pointers held by localio clients + * This invalidates ->net pointers held by localio clients * while they can still safely access nn->counter. */ static __net_exit void nfsd_net_pre_exit(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nfs_uuid_invalidate_clients(&nn->local_clients); + nfs_localio_invalidate_clients(&nn->local_clients, + &nn->local_clients_lock); } #endif diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 4b56ba1e8e48..e2997f0ffbc5 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -88,9 +88,6 @@ struct nfsd_genl_rqstp { extern struct svc_program nfsd_programs[]; extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; -extern spinlock_t nfsd_drc_lock; -extern unsigned long nfsd_drc_max_mem; -extern unsigned long nfsd_drc_mem_used; extern atomic_t nfsd_th_cnt; /* number of available threads */ extern const struct seq_operations nfs_exports_op; @@ -458,7 +455,10 @@ enum { (NFSD4_1_SUPPORTED_ATTRS_WORD2 | \ FATTR4_WORD2_MODE_UMASK | \ NFSD4_2_SECURITY_ATTRS | \ - FATTR4_WORD2_XATTR_SUPPORT) + FATTR4_WORD2_XATTR_SUPPORT | \ + FATTR4_WORD2_TIME_DELEG_ACCESS | \ + FATTR4_WORD2_TIME_DELEG_MODIFY | \ + FATTR4_WORD2_OPEN_ARGUMENTS) extern const u32 nfsd_suppattrs[3][3]; @@ -528,7 +528,10 @@ static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval) #endif #define NFSD_WRITEABLE_ATTRS_WORD2 \ (FATTR4_WORD2_MODE_UMASK \ - | MAYBE_FATTR4_WORD2_SECURITY_LABEL) + | MAYBE_FATTR4_WORD2_SECURITY_LABEL \ + | FATTR4_WORD2_TIME_DELEG_ACCESS \ + | FATTR4_WORD2_TIME_DELEG_MODIFY \ + ) #define NFSD_SUPPATTR_EXCLCREAT_WORD0 \ NFSD_WRITEABLE_ATTRS_WORD0 diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 6a831cb242df..32019751a41e 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -222,7 +222,6 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); put_cred(override_creds(new)); - put_cred(new); } else { error = nfsd_setuser_and_check_port(rqstp, cred, exp); if (error) @@ -382,6 +381,8 @@ __fh_verify(struct svc_rqst *rqstp, if (error) goto out; + svc_xprt_set_valid(rqstp->rq_xprt); + /* Finally, check access permissions. */ error = nfsd_permission(cred, exp, dentry, access); out: diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 49e2f32102ab..9b3d6cff0e1e 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -70,16 +70,6 @@ static __be32 nfsd_init_request(struct svc_rqst *, */ DEFINE_MUTEX(nfsd_mutex); -/* - * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used. - * nfsd_drc_max_pages limits the total amount of memory available for - * version 4.1 DRC caches. - * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage. - */ -DEFINE_SPINLOCK(nfsd_drc_lock); -unsigned long nfsd_drc_max_mem; -unsigned long nfsd_drc_mem_used; - #if IS_ENABLED(CONFIG_NFS_LOCALIO) static const struct svc_version *localio_versions[] = { [1] = &localio_version1, @@ -214,32 +204,32 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change return 0; } -bool nfsd_serv_try_get(struct net *net) __must_hold(rcu) +bool nfsd_net_try_get(struct net *net) __must_hold(rcu) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - return (nn && percpu_ref_tryget_live(&nn->nfsd_serv_ref)); + return (nn && percpu_ref_tryget_live(&nn->nfsd_net_ref)); } -void nfsd_serv_put(struct net *net) __must_hold(rcu) +void nfsd_net_put(struct net *net) __must_hold(rcu) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - percpu_ref_put(&nn->nfsd_serv_ref); + percpu_ref_put(&nn->nfsd_net_ref); } -static void nfsd_serv_done(struct percpu_ref *ref) +static void nfsd_net_done(struct percpu_ref *ref) { - struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref); + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref); - complete(&nn->nfsd_serv_confirm_done); + complete(&nn->nfsd_net_confirm_done); } -static void nfsd_serv_free(struct percpu_ref *ref) +static void nfsd_net_free(struct percpu_ref *ref) { - struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref); + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref); - complete(&nn->nfsd_serv_free_done); + complete(&nn->nfsd_net_free_done); } /* @@ -436,6 +426,10 @@ static void nfsd_shutdown_net(struct net *net) if (!nn->nfsd_net_up) return; + + percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); + wait_for_completion(&nn->nfsd_net_confirm_done); + nfsd_export_flush(net); nfs4_state_shutdown_net(net); nfsd_reply_cache_shutdown(nn); @@ -444,7 +438,10 @@ static void nfsd_shutdown_net(struct net *net) lockd_down(net); nn->lockd_up = false; } - percpu_ref_exit(&nn->nfsd_serv_ref); + + wait_for_completion(&nn->nfsd_net_free_done); + percpu_ref_exit(&nn->nfsd_net_ref); + nn->nfsd_net_up = false; nfsd_shutdown_generic(); } @@ -526,11 +523,6 @@ void nfsd_destroy_serv(struct net *net) lockdep_assert_held(&nfsd_mutex); - percpu_ref_kill_and_confirm(&nn->nfsd_serv_ref, nfsd_serv_done); - wait_for_completion(&nn->nfsd_serv_confirm_done); - wait_for_completion(&nn->nfsd_serv_free_done); - /* percpu_ref_exit is called in nfsd_shutdown_net */ - spin_lock(&nfsd_notifier_lock); nn->nfsd_serv = NULL; spin_unlock(&nfsd_notifier_lock); @@ -575,27 +567,6 @@ void nfsd_reset_versions(struct nfsd_net *nn) } } -/* - * Each session guarantees a negotiated per slot memory cache for replies - * which in turn consumes memory beyond the v2/v3/v4.0 server. A dedicated - * NFSv4.1 server might want to use more memory for a DRC than a machine - * with mutiple services. - * - * Impose a hard limit on the number of pages for the DRC which varies - * according to the machines free pages. This is of course only a default. - * - * For now this is a #defined shift which could be under admin control - * in the future. - */ -static void set_max_drc(void) -{ - #define NFSD_DRC_SIZE_SHIFT 7 - nfsd_drc_max_mem = (nr_free_buffer_pages() - >> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE; - nfsd_drc_mem_used = 0; - dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem); -} - static int nfsd_get_default_max_blksize(void) { struct sysinfo i; @@ -652,12 +623,12 @@ int nfsd_create_serv(struct net *net) if (nn->nfsd_serv) return 0; - error = percpu_ref_init(&nn->nfsd_serv_ref, nfsd_serv_free, + error = percpu_ref_init(&nn->nfsd_net_ref, nfsd_net_free, 0, GFP_KERNEL); if (error) return error; - init_completion(&nn->nfsd_serv_free_done); - init_completion(&nn->nfsd_serv_confirm_done); + init_completion(&nn->nfsd_net_free_done); + init_completion(&nn->nfsd_net_confirm_done); if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); @@ -668,7 +639,6 @@ int nfsd_create_serv(struct net *net) if (serv == NULL) return -ENOMEM; - serv->sv_maxconn = nn->max_connections; error = svc_bind(serv, net); if (error < 0) { svc_destroy(&serv); @@ -678,7 +648,6 @@ int nfsd_create_serv(struct net *net) nn->nfsd_serv = serv; spin_unlock(&nfsd_notifier_lock); - set_max_drc(); /* check if the notifier is already set */ if (atomic_inc_return(&nfsd_notifier_refcount) == 1) { register_inetaddr_notifier(&nfsd_inetaddr_notifier); @@ -954,11 +923,7 @@ nfsd(void *vrqstp) * The main request loop */ while (!svc_thread_should_stop(rqstp)) { - /* Update sv_maxconn if it has changed */ - rqstp->rq_server->sv_maxconn = nn->max_connections; - svc_recv(rqstp); - nfsd_file_net_dispose(nn); } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e16bb3717fb9..74d2d7b42676 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -159,6 +159,8 @@ struct nfs4_cb_fattr { /* from CB_GETATTR reply */ u64 ncf_cb_change; u64 ncf_cb_fsize; + struct timespec64 ncf_cb_mtime; + struct timespec64 ncf_cb_atime; unsigned long ncf_cb_flags; bool ncf_file_modified; @@ -207,6 +209,22 @@ struct nfs4_delegation { struct nfs4_cb_fattr dl_cb_fattr; }; +static inline bool deleg_is_read(u32 dl_type) +{ + return (dl_type == OPEN_DELEGATE_READ || dl_type == OPEN_DELEGATE_READ_ATTRS_DELEG); +} + +static inline bool deleg_is_write(u32 dl_type) +{ + return (dl_type == OPEN_DELEGATE_WRITE || dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG); +} + +static inline bool deleg_attrs_deleg(u32 dl_type) +{ + return dl_type == OPEN_DELEGATE_READ_ATTRS_DELEG || + dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG; +} + #define cb_to_delegation(cb) \ container_of(cb, struct nfs4_delegation, dl_recall) @@ -227,8 +245,11 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s) return container_of(s, struct nfs4_delegation, dl_stid); } -/* Maximum number of slots per session. 160 is useful for long haul TCP */ -#define NFSD_MAX_SLOTS_PER_SESSION 160 +/* Maximum number of slots per session. This is for sanity-check only. + * It could be increased if we had a mechanism to shutdown misbehaving clients. + * A large number can be needed to get good throughput on high-latency servers. + */ +#define NFSD_MAX_SLOTS_PER_SESSION 2048 /* Maximum session per slot cache size */ #define NFSD_SLOT_CACHE_SIZE 2048 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */ @@ -242,10 +263,12 @@ struct nfsd4_slot { struct svc_cred sl_cred; u32 sl_datalen; u16 sl_opcnt; + u16 sl_generation; #define NFSD4_SLOT_INUSE (1 << 0) #define NFSD4_SLOT_CACHETHIS (1 << 1) #define NFSD4_SLOT_INITIALIZED (1 << 2) #define NFSD4_SLOT_CACHED (1 << 3) +#define NFSD4_SLOT_REUSED (1 << 4) u8 sl_flags; char sl_data[]; }; @@ -318,16 +341,19 @@ struct nfsd4_session { u32 se_cb_slot_avail; /* bitmap of available slots */ u32 se_cb_highest_slot; /* highest slot client wants */ u32 se_cb_prog; - bool se_dead; struct list_head se_hash; /* hash by sessionid */ struct list_head se_perclnt; + struct list_head se_all_sessions;/* global list of sessions */ struct nfs4_client *se_client; struct nfs4_sessionid se_sessionid; struct nfsd4_channel_attrs se_fchannel; struct nfsd4_cb_sec se_cb_sec; struct list_head se_conns; u32 se_cb_seq_nr[NFSD_BC_SLOT_TABLE_SIZE]; - struct nfsd4_slot *se_slots[]; /* forward channel slots */ + struct xarray se_slots; /* forward channel slots */ + u16 se_slot_gen; + bool se_dead; + u32 se_target_maxslots; }; /* formatted contents of nfs4_sessionid */ @@ -505,7 +531,7 @@ struct nfs4_replay { unsigned int rp_buflen; char *rp_buf; struct knfsd_fh rp_openfh; - atomic_t rp_locked; + int rp_locked; char rp_ibuf[NFSD4_REPLAY_ISIZE]; }; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 696c89f68a9e..ad2c0c432d08 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -626,7 +626,6 @@ DEFINE_STATEID_EVENT(open); DEFINE_STATEID_EVENT(deleg_read); DEFINE_STATEID_EVENT(deleg_write); DEFINE_STATEID_EVENT(deleg_return); -DEFINE_STATEID_EVENT(deleg_recall); DECLARE_EVENT_CLASS(nfsd_stateseqid_class, TP_PROTO(u32 seqid, const stateid_t *stp), diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 382cc1389396..c26ba86dbdfd 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -576,9 +576,7 @@ struct nfsd4_sequence { u32 slotid; /* request/response */ u32 maxslots; /* request/response */ u32 cachethis; /* request */ -#if 0 u32 target_maxslots; /* response */ -#endif /* not yet */ u32 status_flags; /* response */ }; diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index e8b00309c449..f1a315cd31b7 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -59,16 +59,20 @@ * 1: CB_GETATTR opcode (32-bit) * N: file_handle * 1: number of entry in attribute array (32-bit) - * 1: entry 0 in attribute array (32-bit) + * 3: entry 0-2 in attribute array (32-bit * 3) */ #define NFS4_enc_cb_getattr_sz (cb_compound_enc_hdr_sz + \ cb_sequence_enc_sz + \ - 1 + enc_nfs4_fh_sz + 1 + 1) + 1 + enc_nfs4_fh_sz + 1 + 3) /* * 4: fattr_bitmap_maxsz * 1: attribute array len * 2: change attr (64-bit) * 2: size (64-bit) + * 2: atime.seconds (64-bit) + * 1: atime.nanoseconds (32-bit) + * 2: mtime.seconds (64-bit) + * 1: mtime.nanoseconds (32-bit) */ #define NFS4_dec_cb_getattr_sz (cb_compound_dec_hdr_sz + \ - cb_sequence_dec_sz + 4 + 1 + 2 + 2 + op_dec_sz) + cb_sequence_dec_sz + 4 + 1 + 2 + 2 + 2 + 1 + 2 + 1 + op_dec_sz) diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index ba3e1f591f36..6b506995818d 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -21,6 +21,8 @@ * nilfs_palloc_groups_per_desc_block - get the number of groups that a group * descriptor block can maintain * @inode: inode of metadata file using this allocator + * + * Return: Number of groups that a group descriptor block can maintain. */ static inline unsigned long nilfs_palloc_groups_per_desc_block(const struct inode *inode) @@ -32,6 +34,8 @@ nilfs_palloc_groups_per_desc_block(const struct inode *inode) /** * nilfs_palloc_groups_count - get maximum number of groups * @inode: inode of metadata file using this allocator + * + * Return: Maximum number of groups. */ static inline unsigned long nilfs_palloc_groups_count(const struct inode *inode) @@ -43,6 +47,8 @@ nilfs_palloc_groups_count(const struct inode *inode) * nilfs_palloc_init_blockgroup - initialize private variables for allocator * @inode: inode of metadata file using this allocator * @entry_size: size of the persistent object + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned int entry_size) { @@ -78,6 +84,9 @@ int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned int entry_size) * @inode: inode of metadata file using this allocator * @nr: serial number of the entry (e.g. inode number) * @offset: pointer to store offset number in the group + * + * Return: Number of the group that contains the entry with the index + * specified by @nr. */ static unsigned long nilfs_palloc_group(const struct inode *inode, __u64 nr, unsigned long *offset) @@ -93,8 +102,8 @@ static unsigned long nilfs_palloc_group(const struct inode *inode, __u64 nr, * @inode: inode of metadata file using this allocator * @group: group number * - * nilfs_palloc_desc_blkoff() returns block offset of the descriptor - * block which contains a descriptor of the specified group. + * Return: Index number in the metadata file of the descriptor block of + * the group specified by @group. */ static unsigned long nilfs_palloc_desc_blkoff(const struct inode *inode, unsigned long group) @@ -111,6 +120,9 @@ nilfs_palloc_desc_blkoff(const struct inode *inode, unsigned long group) * * nilfs_palloc_bitmap_blkoff() returns block offset of the bitmap * block used to allocate/deallocate entries in the specified group. + * + * Return: Index number in the metadata file of the bitmap block of + * the group specified by @group. */ static unsigned long nilfs_palloc_bitmap_blkoff(const struct inode *inode, unsigned long group) @@ -125,6 +137,8 @@ nilfs_palloc_bitmap_blkoff(const struct inode *inode, unsigned long group) * nilfs_palloc_group_desc_nfrees - get the number of free entries in a group * @desc: pointer to descriptor structure for the group * @lock: spin lock protecting @desc + * + * Return: Number of free entries written in the group descriptor @desc. */ static unsigned long nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc, @@ -143,6 +157,9 @@ nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc, * @desc: pointer to descriptor structure for the group * @lock: spin lock protecting @desc * @n: delta to be added + * + * Return: Number of free entries after adjusting the group descriptor + * @desc. */ static u32 nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc, @@ -161,6 +178,9 @@ nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc, * nilfs_palloc_entry_blkoff - get block offset of an entry block * @inode: inode of metadata file using this allocator * @nr: serial number of the entry (e.g. inode number) + * + * Return: Index number in the metadata file of the block containing + * the entry specified by @nr. */ static unsigned long nilfs_palloc_entry_blkoff(const struct inode *inode, __u64 nr) @@ -238,6 +258,12 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff, * @blkoff: block offset * @prev: nilfs_bh_assoc struct of the last used buffer * @lock: spin lock protecting @prev + * + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - Non-existent block. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_palloc_delete_block(struct inode *inode, unsigned long blkoff, struct nilfs_bh_assoc *prev, @@ -258,6 +284,8 @@ static int nilfs_palloc_delete_block(struct inode *inode, unsigned long blkoff, * @group: group number * @create: create flag * @bhp: pointer to store the resultant buffer head + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_palloc_get_desc_block(struct inode *inode, unsigned long group, @@ -277,6 +305,8 @@ static int nilfs_palloc_get_desc_block(struct inode *inode, * @group: group number * @create: create flag * @bhp: pointer to store the resultant buffer head + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_palloc_get_bitmap_block(struct inode *inode, unsigned long group, @@ -294,6 +324,8 @@ static int nilfs_palloc_get_bitmap_block(struct inode *inode, * nilfs_palloc_delete_bitmap_block - delete a bitmap block * @inode: inode of metadata file using this allocator * @group: group number + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_palloc_delete_bitmap_block(struct inode *inode, unsigned long group) @@ -312,6 +344,8 @@ static int nilfs_palloc_delete_bitmap_block(struct inode *inode, * @nr: serial number of the entry (e.g. inode number) * @create: create flag * @bhp: pointer to store the resultant buffer head + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_palloc_get_entry_block(struct inode *inode, __u64 nr, int create, struct buffer_head **bhp) @@ -328,6 +362,8 @@ int nilfs_palloc_get_entry_block(struct inode *inode, __u64 nr, * nilfs_palloc_delete_entry_block - delete an entry block * @inode: inode of metadata file using this allocator * @nr: serial number of the entry + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_palloc_delete_entry_block(struct inode *inode, __u64 nr) { @@ -397,6 +433,9 @@ size_t nilfs_palloc_entry_offset(const struct inode *inode, __u64 nr, * @bsize: size in bits * @lock: spin lock protecting @bitmap * @wrap: whether to wrap around + * + * Return: Offset number within the group of the found free entry, or + * %-ENOSPC if not found. */ static int nilfs_palloc_find_available_slot(unsigned char *bitmap, unsigned long target, @@ -438,6 +477,9 @@ static int nilfs_palloc_find_available_slot(unsigned char *bitmap, * @inode: inode of metadata file using this allocator * @curr: current group number * @max: maximum number of groups + * + * Return: Number of remaining descriptors (= groups) managed by the descriptor + * block. */ static unsigned long nilfs_palloc_rest_groups_in_desc_block(const struct inode *inode, @@ -453,6 +495,8 @@ nilfs_palloc_rest_groups_in_desc_block(const struct inode *inode, * nilfs_palloc_count_desc_blocks - count descriptor blocks number * @inode: inode of metadata file using this allocator * @desc_blocks: descriptor blocks number [out] + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_palloc_count_desc_blocks(struct inode *inode, unsigned long *desc_blocks) @@ -473,6 +517,8 @@ static int nilfs_palloc_count_desc_blocks(struct inode *inode, * MDT file growing * @inode: inode of metadata file using this allocator * @desc_blocks: known current descriptor blocks count + * + * Return: true if a group can be added in the metadata file, false if not. */ static inline bool nilfs_palloc_mdt_file_can_grow(struct inode *inode, unsigned long desc_blocks) @@ -487,6 +533,12 @@ static inline bool nilfs_palloc_mdt_file_can_grow(struct inode *inode, * @inode: inode of metadata file using this allocator * @nused: current number of used entries * @nmaxp: max number of entries [out] + * + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. + * * %-ERANGE - Number of entries in use is out of range. */ int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp) { @@ -518,6 +570,13 @@ int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp) * @inode: inode of metadata file using this allocator * @req: nilfs_palloc_req structure exchanged for the allocation * @wrap: whether to wrap around + * + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. + * * %-ENOSPC - Entries exhausted (No entries available for allocation). + * * %-EROFS - Read only filesystem */ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, struct nilfs_palloc_req *req, bool wrap) @@ -710,6 +769,8 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, * nilfs_palloc_prepare_free_entry - prepare to deallocate a persistent object * @inode: inode of metadata file using this allocator * @req: nilfs_palloc_req structure exchanged for the removal + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_palloc_prepare_free_entry(struct inode *inode, struct nilfs_palloc_req *req) @@ -754,6 +815,8 @@ void nilfs_palloc_abort_free_entry(struct inode *inode, * @inode: inode of metadata file using this allocator * @entry_nrs: array of entry numbers to be deallocated * @nitems: number of entries stored in @entry_nrs + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) { diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index 3f115ab7e9a7..046d876ea3e0 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -21,6 +21,8 @@ * * The number of entries per group is defined by the number of bits * that a bitmap block can maintain. + * + * Return: Number of entries per group. */ static inline unsigned long nilfs_palloc_entries_per_group(const struct inode *inode) diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index c9e8d9a7d820..ccc1a7aa52d2 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -47,17 +47,14 @@ static int nilfs_bmap_convert_error(struct nilfs_bmap *bmap, * @ptrp: place to store the value associated to @key * * Description: nilfs_bmap_lookup_at_level() finds a record whose key - * matches @key in the block at @level of the bmap. + * matches @key in the block at @level of the bmap. The record associated + * with @key is stored in the place pointed to by @ptrp. * - * Return Value: On success, 0 is returned and the record associated with @key - * is stored in the place pointed by @ptrp. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - A record associated with @key does not exist. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - A record associated with @key does not exist. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level, __u64 *ptrp) @@ -138,14 +135,11 @@ static int nilfs_bmap_do_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr) * Description: nilfs_bmap_insert() inserts the new key-record pair specified * by @key and @rec into @bmap. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EEXIST - A record associated with @key already exist. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EEXIST - A record associated with @key already exists. + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_bmap_insert(struct nilfs_bmap *bmap, __u64 key, unsigned long rec) { @@ -193,14 +187,11 @@ static int nilfs_bmap_do_delete(struct nilfs_bmap *bmap, __u64 key) * Description: nilfs_bmap_seek_key() seeks a valid key on @bmap * starting from @start, and stores it to @keyp if found. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - No valid entry was found + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - No valid entry was found. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_bmap_seek_key(struct nilfs_bmap *bmap, __u64 start, __u64 *keyp) { @@ -236,14 +227,11 @@ int nilfs_bmap_last_key(struct nilfs_bmap *bmap, __u64 *keyp) * Description: nilfs_bmap_delete() deletes the key-record pair specified by * @key from @bmap. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - A record associated with @key does not exist. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - A record associated with @key does not exist. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_bmap_delete(struct nilfs_bmap *bmap, __u64 key) { @@ -290,12 +278,10 @@ static int nilfs_bmap_do_truncate(struct nilfs_bmap *bmap, __u64 key) * Description: nilfs_bmap_truncate() removes key-record pairs whose keys are * greater than or equal to @key from @bmap. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_bmap_truncate(struct nilfs_bmap *bmap, __u64 key) { @@ -330,12 +316,10 @@ void nilfs_bmap_clear(struct nilfs_bmap *bmap) * Description: nilfs_bmap_propagate() marks the buffers that directly or * indirectly refer to the block specified by @bh dirty. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_bmap_propagate(struct nilfs_bmap *bmap, struct buffer_head *bh) { @@ -362,22 +346,22 @@ void nilfs_bmap_lookup_dirty_buffers(struct nilfs_bmap *bmap, /** * nilfs_bmap_assign - assign a new block number to a block - * @bmap: bmap - * @bh: pointer to buffer head + * @bmap: bmap + * @bh: place to store a pointer to the buffer head to which a block + * address is assigned (in/out) * @blocknr: block number - * @binfo: block information + * @binfo: block information * * Description: nilfs_bmap_assign() assigns the block number @blocknr to the - * buffer specified by @bh. + * buffer specified by @bh. The block information is stored in the memory + * pointed to by @binfo, and the buffer head may be replaced as a block + * address is assigned, in which case a pointer to the new buffer head is + * stored in the memory pointed to by @bh. * - * Return Value: On success, 0 is returned and the buffer head of a newly - * create buffer and the block information associated with the buffer are - * stored in the place pointed by @bh and @binfo, respectively. On error, one - * of the following negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_bmap_assign(struct nilfs_bmap *bmap, struct buffer_head **bh, @@ -402,12 +386,10 @@ int nilfs_bmap_assign(struct nilfs_bmap *bmap, * Description: nilfs_bmap_mark() marks the block specified by @key and @level * as dirty. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_bmap_mark(struct nilfs_bmap *bmap, __u64 key, int level) { @@ -430,7 +412,7 @@ int nilfs_bmap_mark(struct nilfs_bmap *bmap, __u64 key, int level) * Description: nilfs_test_and_clear() is the atomic operation to test and * clear the dirty state of @bmap. * - * Return Value: 1 is returned if @bmap is dirty, or 0 if clear. + * Return: 1 if @bmap is dirty, or 0 if clear. */ int nilfs_bmap_test_and_clear_dirty(struct nilfs_bmap *bmap) { @@ -490,10 +472,10 @@ static struct lock_class_key nilfs_bmap_mdt_lock_key; * * Description: nilfs_bmap_read() initializes the bmap @bmap. * - * Return Value: On success, 0 is returned. On error, the following negative - * error code is returned. - * - * %-ENOMEM - Insufficient amount of memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (corrupted bmap). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_bmap_read(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode) { diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 501ad7be5174..568367129092 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -35,6 +35,7 @@ void nilfs_init_btnc_inode(struct inode *btnc_inode) ii->i_flags = 0; memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS); + btnc_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; } void nilfs_btnode_cache_clear(struct address_space *btnc) @@ -200,7 +201,8 @@ void nilfs_btnode_delete(struct buffer_head *bh) * Note that the current implementation does not support folio sizes larger * than the page size. * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-EIO - I/O error (metadata corruption). * * %-ENOMEM - Insufficient memory available. */ diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index ef5061bb56da..0d8f7fb15c2e 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -334,7 +334,7 @@ static int nilfs_btree_node_lookup(const struct nilfs_btree_node *node, * @inode: host inode of btree * @blocknr: block number * - * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned. + * Return: 0 if normal, 1 if the node is broken. */ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node, size_t size, struct inode *inode, @@ -366,7 +366,7 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node, * @node: btree root node to be examined * @inode: host inode of btree * - * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned. + * Return: 0 if normal, 1 if the root node is broken. */ static int nilfs_btree_root_broken(const struct nilfs_btree_node *node, struct inode *inode) @@ -652,8 +652,7 @@ static int nilfs_btree_do_lookup_last(const struct nilfs_bmap *btree, * @minlevel: start level * @nextkey: place to store the next valid key * - * Return Value: If a next key was found, 0 is returned. Otherwise, - * -ENOENT is returned. + * Return: 0 if the next key was found, %-ENOENT if not found. */ static int nilfs_btree_get_next_key(const struct nilfs_bmap *btree, const struct nilfs_btree_path *path, diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c index c20207d7a989..bcc7d76269ac 100644 --- a/fs/nilfs2/cpfile.c +++ b/fs/nilfs2/cpfile.c @@ -191,14 +191,11 @@ static inline int nilfs_cpfile_get_checkpoint_block(struct inode *cpfile, * @cnop: place to store the next checkpoint number * @bhp: place to store a pointer to buffer_head struct * - * Return Value: On success, it returns 0. On error, the following negative - * error code is returned. - * - * %-ENOMEM - Insufficient memory available. - * - * %-EIO - I/O error - * - * %-ENOENT - no block exists in the range. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - no block exists in the range. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_cpfile_find_checkpoint_block(struct inode *cpfile, __u64 start_cno, __u64 end_cno, @@ -239,7 +236,8 @@ static inline int nilfs_cpfile_delete_checkpoint_block(struct inode *cpfile, * stores it to the inode file given by @ifile and the nilfs root object * given by @root. * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-EINVAL - Invalid checkpoint. * * %-ENOMEM - Insufficient memory available. * * %-EIO - I/O error (including metadata corruption). @@ -307,7 +305,8 @@ out_sem: * In either case, the buffer of the block containing the checkpoint entry * and the cpfile inode are made dirty for inclusion in the write log. * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-ENOMEM - Insufficient memory available. * * %-EIO - I/O error (including metadata corruption). * * %-EROFS - Read only filesystem @@ -376,7 +375,8 @@ out_sem: * cpfile with the data given by the arguments @root, @blkinc, @ctime, and * @minor. * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-ENOMEM - Insufficient memory available. * * %-EIO - I/O error (including metadata corruption). */ @@ -447,14 +447,11 @@ error: * the period from @start to @end, excluding @end itself. The checkpoints * which have been already deleted are ignored. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EINVAL - invalid checkpoints. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EINVAL - Invalid checkpoints. + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile, __u64 start, @@ -718,7 +715,7 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop, * number to continue searching. * * Return: Count of checkpoint info items stored in the output buffer on - * success, or the following negative error code on failure. + * success, or one of the following negative error codes on failure: * * %-EINVAL - Invalid checkpoint mode. * * %-ENOMEM - Insufficient memory available. * * %-EIO - I/O error (including metadata corruption). @@ -743,7 +740,8 @@ ssize_t nilfs_cpfile_get_cpinfo(struct inode *cpfile, __u64 *cnop, int mode, * @cpfile: checkpoint file inode * @cno: checkpoint number to delete * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-EBUSY - Checkpoint in use (snapshot specified). * * %-EIO - I/O error (including metadata corruption). * * %-ENOENT - No valid checkpoint found. @@ -1011,7 +1009,7 @@ static int nilfs_cpfile_clear_snapshot(struct inode *cpfile, __u64 cno) * @cno: checkpoint number * * Return: 1 if the checkpoint specified by @cno is a snapshot, 0 if not, or - * the following negative error code on failure. + * one of the following negative error codes on failure: * * %-EIO - I/O error (including metadata corruption). * * %-ENOENT - No such checkpoint. * * %-ENOMEM - Insufficient memory available. @@ -1058,14 +1056,11 @@ int nilfs_cpfile_is_snapshot(struct inode *cpfile, __u64 cno) * Description: nilfs_change_cpmode() changes the mode of the checkpoint * specified by @cno. The mode @mode is NILFS_CHECKPOINT or NILFS_SNAPSHOT. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - No such checkpoint. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - No such checkpoint. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_cpfile_change_cpmode(struct inode *cpfile, __u64 cno, int mode) { @@ -1097,14 +1092,12 @@ int nilfs_cpfile_change_cpmode(struct inode *cpfile, __u64 cno, int mode) * @cpstat: pointer to a structure of checkpoint statistics * * Description: nilfs_cpfile_get_stat() returns information about checkpoints. + * The checkpoint statistics are stored in the location pointed to by @cpstat. * - * Return Value: On success, 0 is returned, and checkpoints information is - * stored in the place pointed by @cpstat. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_cpfile_get_stat(struct inode *cpfile, struct nilfs_cpstat *cpstat) { @@ -1135,6 +1128,8 @@ int nilfs_cpfile_get_stat(struct inode *cpfile, struct nilfs_cpstat *cpstat) * @cpsize: size of a checkpoint entry * @raw_inode: on-disk cpfile inode * @inodep: buffer to store the inode + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize, struct nilfs_inode *raw_inode, struct inode **inodep) diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index e220dcb08aa6..c664daba56ae 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -276,7 +276,8 @@ void nilfs_dat_abort_update(struct inode *dat, * @dat: DAT file inode * @vblocknr: virtual block number * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-EINVAL - Invalid DAT entry (internal code). * * %-EIO - I/O error (including metadata corruption). * * %-ENOMEM - Insufficient memory available. @@ -302,14 +303,11 @@ int nilfs_dat_mark_dirty(struct inode *dat, __u64 vblocknr) * Description: nilfs_dat_freev() frees the virtual block numbers specified by * @vblocknrs and @nitems. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - The virtual block number have not been allocated. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - The virtual block number have not been allocated. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_dat_freev(struct inode *dat, __u64 *vblocknrs, size_t nitems) { @@ -325,12 +323,10 @@ int nilfs_dat_freev(struct inode *dat, __u64 *vblocknrs, size_t nitems) * Description: nilfs_dat_move() changes the block number associated with * @vblocknr to @blocknr. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr) { @@ -390,17 +386,14 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr) * @blocknrp: pointer to a block number * * Description: nilfs_dat_translate() maps the virtual block number @vblocknr - * to the corresponding block number. + * to the corresponding block number. The block number associated with + * @vblocknr is stored in the place pointed to by @blocknrp. * - * Return Value: On success, 0 is returned and the block number associated - * with @vblocknr is stored in the place pointed by @blocknrp. On error, one - * of the following negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - A block number associated with @vblocknr does not exist. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - A block number associated with @vblocknr does not exist. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp) { @@ -489,6 +482,8 @@ ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned int visz, * @entry_size: size of a dat entry * @raw_inode: on-disk dat inode * @inodep: buffer to store the inode + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_dat_read(struct super_block *sb, size_t entry_size, struct nilfs_inode *raw_inode, struct inode **inodep) diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 0a3aea6c416b..9b7f8e9655a2 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -400,7 +400,7 @@ int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino) return 0; } -void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, +int nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, struct folio *folio, struct inode *inode) { size_t from = offset_in_folio(folio, de); @@ -410,11 +410,15 @@ void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, folio_lock(folio); err = nilfs_prepare_chunk(folio, from, to); - BUG_ON(err); + if (unlikely(err)) { + folio_unlock(folio); + return err; + } de->inode = cpu_to_le64(inode->i_ino); de->file_type = fs_umode_to_ftype(inode->i_mode); nilfs_commit_chunk(folio, mapping, from, to); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); + return 0; } /* @@ -543,7 +547,10 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct folio *folio) from = (char *)pde - kaddr; folio_lock(folio); err = nilfs_prepare_chunk(folio, from, to); - BUG_ON(err); + if (unlikely(err)) { + folio_unlock(folio); + goto out; + } if (pde) pde->rec_len = nilfs_rec_len_to_disk(to - from); dir->inode = 0; diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index ace22253fed0..561c220799c7 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -46,14 +46,11 @@ * specified by @pbn to the GC pagecache with the key @blkoff. * This function sets @vbn (@pbn if @vbn is zero) in b_blocknr of the buffer. * - * Return Value: On success, 0 is returned. On Error, one of the following - * negative error code is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - The block specified with @pbn does not exist. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - The block specified with @pbn does not exist. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, sector_t pbn, __u64 vbn, @@ -114,12 +111,11 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, * specified by @vbn to the GC pagecache. @pbn can be supplied by the * caller to avoid translation of the disk block address. * - * Return Value: On success, 0 is returned. On Error, one of the following - * negative error code is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - Invalid virtual block address. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn, __u64 vbn, struct buffer_head **out_bh) @@ -163,7 +159,7 @@ int nilfs_init_gcinode(struct inode *inode) inode->i_mode = S_IFREG; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); - inode->i_mapping->a_ops = &empty_aops; + inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap); diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c index e7339eb3c08a..c4cd4a4dedd0 100644 --- a/fs/nilfs2/ifile.c +++ b/fs/nilfs2/ifile.c @@ -38,17 +38,16 @@ static inline struct nilfs_ifile_info *NILFS_IFILE_I(struct inode *ifile) * @out_ino: pointer to a variable to store inode number * @out_bh: buffer_head contains newly allocated disk inode * - * Return Value: On success, 0 is returned and the newly allocated inode - * number is stored in the place pointed by @ino, and buffer_head pointer - * that contains newly allocated disk inode structure is stored in the - * place pointed by @out_bh - * On error, one of the following negative error codes is returned. + * nilfs_ifile_create_inode() allocates a new inode in the ifile metadata + * file and stores the inode number in the variable pointed to by @out_ino, + * as well as storing the ifile's buffer with the disk inode in the location + * pointed to by @out_bh. * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOSPC - No inode left. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. + * * %-ENOSPC - No inode left. */ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino, struct buffer_head **out_bh) @@ -83,14 +82,11 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino, * @ifile: ifile inode * @ino: inode number * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - The inode number @ino have not been allocated. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - Inode number unallocated. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_ifile_delete_inode(struct inode *ifile, ino_t ino) { @@ -150,6 +146,8 @@ int nilfs_ifile_get_inode_block(struct inode *ifile, ino_t ino, * @ifile: ifile inode * @nmaxinodes: current maximum of available inodes count [out] * @nfreeinodes: free inodes count [out] + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_ifile_count_free_inodes(struct inode *ifile, u64 *nmaxinodes, u64 *nfreeinodes) @@ -174,7 +172,8 @@ int nilfs_ifile_count_free_inodes(struct inode *ifile, * @cno: number of checkpoint entry to read * @inode_size: size of an inode * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-EINVAL - Invalid checkpoint. * * %-ENOMEM - Insufficient memory available. * * %-EIO - I/O error (including metadata corruption). diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index cf9ba481ae37..6613b8fcceb0 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -68,6 +68,8 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n) * * This function does not issue actual read request of the specified data * block. It is done by VFS. + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_get_block(struct inode *inode, sector_t blkoff, struct buffer_head *bh_result, int create) @@ -141,6 +143,8 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, * address_space_operations. * @file: file struct of the file to be read * @folio: the folio to be read + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_read_folio(struct file *file, struct folio *folio) { @@ -276,6 +280,10 @@ const struct address_space_operations nilfs_aops = { .is_partially_uptodate = block_is_partially_uptodate, }; +const struct address_space_operations nilfs_buffer_cache_aops = { + .invalidate_folio = block_invalidate_folio, +}; + static int nilfs_insert_inode_locked(struct inode *inode, struct nilfs_root *root, unsigned long ino) @@ -544,8 +552,14 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, inode = nilfs_iget_locked(sb, root, ino); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + + if (!(inode->i_state & I_NEW)) { + if (!inode->i_nlink) { + iput(inode); + return ERR_PTR(-ESTALE); + } return inode; + } err = __nilfs_read_inode(sb, root, ino, inode); if (unlikely(err)) { @@ -588,10 +602,7 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, * or does nothing if the inode already has it. This function allocates * an additional inode to maintain page cache of B-tree nodes one-on-one. * - * Return Value: On success, 0 is returned. On errors, one of the following - * negative error code is returned. - * - * %-ENOMEM - Insufficient memory available. + * Return: 0 on success, or %-ENOMEM if memory is insufficient. */ int nilfs_attach_btree_node_cache(struct inode *inode) { @@ -650,11 +661,8 @@ void nilfs_detach_btree_node_cache(struct inode *inode) * in one inode and the one for b-tree node pages is set up in the * other inode, which is attached to the former inode. * - * Return Value: On success, a pointer to the inode for data pages is - * returned. On errors, one of the following negative error code is returned - * in a pointer type. - * - * %-ENOMEM - Insufficient memory available. + * Return: a pointer to the inode for data pages on success, or %-ENOMEM + * if memory is insufficient. */ struct inode *nilfs_iget_for_shadow(struct inode *inode) { @@ -675,6 +683,7 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode) NILFS_I(s_inode)->i_flags = 0; memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS); + s_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; err = nilfs_attach_btree_node_cache(s_inode); if (unlikely(err)) { @@ -1177,7 +1186,7 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (size) { if (phys && blkphy << blkbits == phys + size) { /* The current extent goes on */ - size += n << blkbits; + size += (u64)n << blkbits; } else { /* Terminate the current extent */ ret = fiemap_fill_next_extent( @@ -1190,14 +1199,14 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, flags = FIEMAP_EXTENT_MERGED; logical = blkoff << blkbits; phys = blkphy << blkbits; - size = n << blkbits; + size = (u64)n << blkbits; } } else { /* Start a new extent */ flags = FIEMAP_EXTENT_MERGED; logical = blkoff << blkbits; phys = blkphy << blkbits; - size = n << blkbits; + size = (u64)n << blkbits; } blkoff += n; } diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index fa77f78df681..a66d62a51f77 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -33,17 +33,14 @@ * @dofunc: concrete function of get/set metadata info * * Description: nilfs_ioctl_wrap_copy() gets/sets metadata info by means of - * calling dofunc() function on the basis of @argv argument. + * calling dofunc() function on the basis of @argv argument. If successful, + * the requested metadata information is copied to userspace memory. * - * Return Value: On success, 0 is returned and requested metadata info - * is copied into userspace. On error, one of the following - * negative error codes is returned. - * - * %-EINVAL - Invalid arguments from userspace. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EFAULT - Failure during execution of requested operation. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EFAULT - Failure during execution of requested operation. + * * %-EINVAL - Invalid arguments from userspace. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs, struct nilfs_argv *argv, int dir, @@ -190,13 +187,10 @@ static int nilfs_ioctl_getversion(struct inode *inode, void __user *argp) * given checkpoint between checkpoint and snapshot state. This ioctl * is used in chcp and mkcp utilities. * - * Return Value: On success, 0 is returned and mode of a checkpoint is - * changed. On error, one of the following negative error codes - * is returned. - * - * %-EPERM - Operation not permitted. - * - * %-EFAULT - Failure during checkpoint mode changing. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * %-EFAULT - Failure during checkpoint mode changing. + * %-EPERM - Operation not permitted. */ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) @@ -244,13 +238,10 @@ out: * checkpoint from NILFS2 file system. This ioctl is used in rmcp * utility. * - * Return Value: On success, 0 is returned and a checkpoint is - * removed. On error, one of the following negative error codes - * is returned. - * - * %-EPERM - Operation not permitted. - * - * %-EFAULT - Failure during checkpoint removing. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * %-EFAULT - Failure during checkpoint removing. + * %-EPERM - Operation not permitted. */ static int nilfs_ioctl_delete_checkpoint(struct inode *inode, struct file *filp, @@ -296,7 +287,7 @@ out: * requested checkpoints. The NILFS_IOCTL_GET_CPINFO ioctl is used in * lscp utility and by nilfs_cleanerd daemon. * - * Return value: count of nilfs_cpinfo structures in output buffer. + * Return: Count of nilfs_cpinfo structures in output buffer. */ static ssize_t nilfs_ioctl_do_get_cpinfo(struct the_nilfs *nilfs, __u64 *posp, int flags, @@ -320,17 +311,14 @@ nilfs_ioctl_do_get_cpinfo(struct the_nilfs *nilfs, __u64 *posp, int flags, * * Description: nilfs_ioctl_get_cpstat() returns information about checkpoints. * The NILFS_IOCTL_GET_CPSTAT ioctl is used by lscp, rmcp utilities - * and by nilfs_cleanerd daemon. + * and by nilfs_cleanerd daemon. The checkpoint statistics are copied to + * the userspace memory pointed to by @argp. * - * Return Value: On success, 0 is returned, and checkpoints information is - * copied into userspace pointer @argp. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EFAULT - Failure during getting checkpoints statistics. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EFAULT - Failure during getting checkpoints statistics. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_ioctl_get_cpstat(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) @@ -363,7 +351,8 @@ static int nilfs_ioctl_get_cpstat(struct inode *inode, struct file *filp, * info about requested segments. The NILFS_IOCTL_GET_SUINFO ioctl is used * in lssu, nilfs_resize utilities and by nilfs_cleanerd daemon. * - * Return value: count of nilfs_suinfo structures in output buffer. + * Return: Count of nilfs_suinfo structures in output buffer on success, + * or a negative error code on failure. */ static ssize_t nilfs_ioctl_do_get_suinfo(struct the_nilfs *nilfs, __u64 *posp, int flags, @@ -387,17 +376,14 @@ nilfs_ioctl_do_get_suinfo(struct the_nilfs *nilfs, __u64 *posp, int flags, * * Description: nilfs_ioctl_get_sustat() returns segment usage statistics. * The NILFS_IOCTL_GET_SUSTAT ioctl is used in lssu, nilfs_resize utilities - * and by nilfs_cleanerd daemon. + * and by nilfs_cleanerd daemon. The requested segment usage information is + * copied to the userspace memory pointed to by @argp. * - * Return Value: On success, 0 is returned, and segment usage information is - * copied into userspace pointer @argp. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EFAULT - Failure during getting segment usage statistics. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EFAULT - Failure during getting segment usage statistics. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_ioctl_get_sustat(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) @@ -430,7 +416,8 @@ static int nilfs_ioctl_get_sustat(struct inode *inode, struct file *filp, * on virtual block addresses. The NILFS_IOCTL_GET_VINFO ioctl is used * by nilfs_cleanerd daemon. * - * Return value: count of nilfs_vinfo structures in output buffer. + * Return: Count of nilfs_vinfo structures in output buffer on success, or + * a negative error code on failure. */ static ssize_t nilfs_ioctl_do_get_vinfo(struct the_nilfs *nilfs, __u64 *posp, int flags, @@ -457,7 +444,8 @@ nilfs_ioctl_do_get_vinfo(struct the_nilfs *nilfs, __u64 *posp, int flags, * about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl * is used by nilfs_cleanerd daemon. * - * Return value: count of nilfs_bdescs structures in output buffer. + * Return: Count of nilfs_bdescs structures in output buffer on success, or + * a negative error code on failure. */ static ssize_t nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags, @@ -494,19 +482,15 @@ nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags, * * Description: nilfs_ioctl_do_get_bdescs() function returns information * about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl - * is used by nilfs_cleanerd daemon. + * is used by nilfs_cleanerd daemon. If successful, disk block descriptors + * are copied to userspace pointer @argp. * - * Return Value: On success, 0 is returned, and disk block descriptors are - * copied into userspace pointer @argp. On error, one of the following - * negative error codes is returned. - * - * %-EINVAL - Invalid arguments from userspace. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EFAULT - Failure during getting disk block descriptors. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EFAULT - Failure during getting disk block descriptors. + * * %-EINVAL - Invalid arguments from userspace. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_ioctl_get_bdescs(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) @@ -540,16 +524,12 @@ static int nilfs_ioctl_get_bdescs(struct inode *inode, struct file *filp, * Description: nilfs_ioctl_move_inode_block() function registers data/node * buffer in the GC pagecache and submit read request. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - Requested block doesn't exist. - * - * %-EEXIST - Blocks conflict is detected. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EEXIST - Block conflict detected. + * * %-EIO - I/O error. + * * %-ENOENT - Requested block doesn't exist. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_ioctl_move_inode_block(struct inode *inode, struct nilfs_vdesc *vdesc, @@ -604,8 +584,8 @@ static int nilfs_ioctl_move_inode_block(struct inode *inode, * blocks that garbage collector specified with the array of nilfs_vdesc * structures and stores them into page caches of GC inodes. * - * Return Value: Number of processed nilfs_vdesc structures or - * error code, otherwise. + * Return: Number of processed nilfs_vdesc structures on success, or + * a negative error code on failure. */ static int nilfs_ioctl_move_blocks(struct super_block *sb, struct nilfs_argv *argv, void *buf) @@ -682,14 +662,11 @@ static int nilfs_ioctl_move_blocks(struct super_block *sb, * in the period from p_start to p_end, excluding p_end itself. The checkpoints * which have been already deleted are ignored. * - * Return Value: Number of processed nilfs_period structures or - * error code, otherwise. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EINVAL - invalid checkpoints. + * Return: Number of processed nilfs_period structures on success, or one of + * the following negative error codes on failure: + * * %-EINVAL - invalid checkpoints. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_ioctl_delete_checkpoints(struct the_nilfs *nilfs, struct nilfs_argv *argv, void *buf) @@ -717,14 +694,11 @@ static int nilfs_ioctl_delete_checkpoints(struct the_nilfs *nilfs, * Description: nilfs_ioctl_free_vblocknrs() function frees * the virtual block numbers specified by @buf and @argv->v_nmembs. * - * Return Value: Number of processed virtual block numbers or - * error code, otherwise. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - The virtual block number have not been allocated. + * Return: Number of processed virtual block numbers on success, or one of the + * following negative error codes on failure: + * * %-EIO - I/O error. + * * %-ENOENT - Unallocated virtual block number. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_ioctl_free_vblocknrs(struct the_nilfs *nilfs, struct nilfs_argv *argv, void *buf) @@ -746,14 +720,11 @@ static int nilfs_ioctl_free_vblocknrs(struct the_nilfs *nilfs, * Description: nilfs_ioctl_mark_blocks_dirty() function marks * metadata file or data blocks as dirty. * - * Return Value: Number of processed block descriptors or - * error code, otherwise. - * - * %-ENOMEM - Insufficient memory available. - * - * %-EIO - I/O error - * - * %-ENOENT - the specified block does not exist (hole block) + * Return: Number of processed block descriptors on success, or one of the + * following negative error codes on failure: + * * %-EIO - I/O error. + * * %-ENOENT - Non-existent block (hole block). + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs, struct nilfs_argv *argv, void *buf) @@ -852,7 +823,7 @@ int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *nilfs, * from userspace. The NILFS_IOCTL_CLEAN_SEGMENTS ioctl is used by * nilfs_cleanerd daemon. * - * Return Value: On success, 0 is returned or error code, otherwise. + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) @@ -976,20 +947,14 @@ out: * and metadata are written out to the device when it successfully * returned. * - * Return Value: On success, 0 is retured. On errors, one of the following - * negative error code is returned. - * - * %-EROFS - Read only filesystem. - * - * %-EIO - I/O error - * - * %-ENOSPC - No space left on device (only in a panic state). - * - * %-ERESTARTSYS - Interrupted. - * - * %-ENOMEM - Insufficient memory available. - * - * %-EFAULT - Failure during execution of requested operation. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EFAULT - Failure during execution of requested operation. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. + * * %-ENOSPC - No space left on device (only in a panic state). + * * %-ERESTARTSYS - Interrupted. + * * %-EROFS - Read only filesystem. */ static int nilfs_ioctl_sync(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) @@ -1023,7 +988,7 @@ static int nilfs_ioctl_sync(struct inode *inode, struct file *filp, * @filp: file object * @argp: pointer on argument from userspace * - * Return Value: On success, 0 is returned or error code, otherwise. + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_ioctl_resize(struct inode *inode, struct file *filp, void __user *argp) @@ -1059,7 +1024,7 @@ out: * checks the arguments from userspace and calls nilfs_sufile_trim_fs, which * performs the actual trim operation. * - * Return Value: On success, 0 is returned or negative error code, otherwise. + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp) { @@ -1101,7 +1066,7 @@ static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp) * of segments in bytes and upper limit of segments in bytes. * The NILFS_IOCTL_SET_ALLOC_RANGE is used by nilfs_resize utility. * - * Return Value: On success, 0 is returned or error code, otherwise. + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp) { @@ -1152,17 +1117,15 @@ out: * @dofunc: concrete function of getting metadata info * * Description: nilfs_ioctl_get_info() gets metadata info by means of - * calling dofunc() function. + * calling dofunc() function. The requested metadata information is copied + * to userspace memory @argp. * - * Return Value: On success, 0 is returned and requested metadata info - * is copied into userspace. On error, one of the following - * negative error codes is returned. - * - * %-EINVAL - Invalid arguments from userspace. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EFAULT - Failure during execution of requested operation. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EFAULT - Failure during execution of requested operation. + * * %-EINVAL - Invalid arguments from userspace. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp, @@ -1202,18 +1165,14 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp, * encapsulated in nilfs_argv and updates the segment usage info * according to the flags in nilfs_suinfo_update. * - * Return Value: On success, 0 is returned. On error, one of the - * following negative error codes is returned. - * - * %-EPERM - Not enough permissions - * - * %-EFAULT - Error copying input data - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EINVAL - Invalid values in input (segment number, flags or nblocks) + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EEXIST - Block conflict detected. + * * %-EFAULT - Error copying input data. + * * %-EINVAL - Invalid values in input (segment number, flags or nblocks). + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. + * * %-EPERM - Not enough permissions. */ static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp, unsigned int cmd, void __user *argp) @@ -1309,7 +1268,8 @@ static int nilfs_ioctl_get_fslabel(struct super_block *sb, void __user *argp) * @filp: file object * @argp: pointer to userspace memory that contains the volume name * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-EFAULT - Error copying input data. * * %-EINVAL - Label length exceeds record size in superblock. * * %-EIO - I/O error. diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 965b5ad1c0df..2f850a18d6e7 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -226,20 +226,21 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block, * @out_bh: output of a pointer to the buffer_head * * nilfs_mdt_get_block() looks up the specified buffer and tries to create - * a new buffer if @create is not zero. On success, the returned buffer is - * assured to be either existing or formatted using a buffer lock on success. - * @out_bh is substituted only when zero is returned. + * a new buffer if @create is not zero. If (and only if) this function + * succeeds, it stores a pointer to the retrieved buffer head in the location + * pointed to by @out_bh. * - * Return Value: On success, it returns 0. On error, the following negative - * error code is returned. + * The retrieved buffer may be either an existing one or a newly allocated one. + * For a newly created buffer, if the callback function argument @init_block + * is non-NULL, the callback will be called with the buffer locked to format + * the block. * - * %-ENOMEM - Insufficient memory available. - * - * %-EIO - I/O error - * - * %-ENOENT - the specified block does not exist (hole block) - * - * %-EROFS - Read only filesystem (for create mode) + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - The specified block does not exist (hole block). + * * %-ENOMEM - Insufficient memory available. + * * %-EROFS - Read only filesystem (for create mode). */ int nilfs_mdt_get_block(struct inode *inode, unsigned long blkoff, int create, void (*init_block)(struct inode *, @@ -275,14 +276,11 @@ int nilfs_mdt_get_block(struct inode *inode, unsigned long blkoff, int create, * @out_bh, and block offset to @blkoff, respectively. @out_bh and * @blkoff are substituted only when zero is returned. * - * Return Value: On success, it returns 0. On error, the following negative - * error code is returned. - * - * %-ENOMEM - Insufficient memory available. - * - * %-EIO - I/O error - * - * %-ENOENT - no block was found in the range + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - No block was found in the range. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_mdt_find_block(struct inode *inode, unsigned long start, unsigned long end, unsigned long *blkoff, @@ -321,12 +319,11 @@ out: * @inode: inode of the meta data file * @block: block offset * - * Return Value: On success, zero is returned. - * On error, one of the following negative error code is returned. - * - * %-ENOMEM - Insufficient memory available. - * - * %-EIO - I/O error + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - Non-existent block. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_mdt_delete_block(struct inode *inode, unsigned long block) { @@ -349,12 +346,10 @@ int nilfs_mdt_delete_block(struct inode *inode, unsigned long block) * nilfs_mdt_forget_block() clears a dirty flag of the specified buffer, and * tries to release the page including the buffer from a page cache. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error code is returned. - * - * %-EBUSY - page has an active buffer. - * - * %-ENOENT - page cache has no page addressed by the offset. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EBUSY - Page has an active buffer. + * * %-ENOENT - Page cache has no page addressed by the offset. */ int nilfs_mdt_forget_block(struct inode *inode, unsigned long block) { @@ -524,6 +519,8 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned int entry_size, * nilfs_mdt_setup_shadow_map - setup shadow map and bind it to metadata file * @inode: inode of the metadata file * @shadow: shadow mapping + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_mdt_setup_shadow_map(struct inode *inode, struct nilfs_shadow_map *shadow) @@ -545,6 +542,8 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode, /** * nilfs_mdt_save_to_shadow_map - copy bmap and dirty pages to shadow map * @inode: inode of the metadata file + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_mdt_save_to_shadow_map(struct inode *inode) { diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9b108052d9f7..953fbd5f0851 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -67,6 +67,11 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) inode = NULL; } else { inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + if (inode == ERR_PTR(-ESTALE)) { + nilfs_error(dir->i_sb, + "deleted inode referenced: %lu", ino); + return ERR_PTR(-EIO); + } } return d_splice_alias(inode, dentry); @@ -365,6 +370,7 @@ static int nilfs_rename(struct mnt_idmap *idmap, struct folio *old_folio; struct nilfs_dir_entry *old_de; struct nilfs_transaction_info ti; + bool old_is_dir = S_ISDIR(old_inode->i_mode); int err; if (flags & ~RENAME_NOREPLACE) @@ -380,7 +386,7 @@ static int nilfs_rename(struct mnt_idmap *idmap, goto out; } - if (S_ISDIR(old_inode->i_mode)) { + if (old_is_dir && old_dir != new_dir) { err = -EIO; dir_de = nilfs_dotdot(old_inode, &dir_folio); if (!dir_de) @@ -392,7 +398,7 @@ static int nilfs_rename(struct mnt_idmap *idmap, struct nilfs_dir_entry *new_de; err = -ENOTEMPTY; - if (dir_de && !nilfs_empty_dir(new_inode)) + if (old_is_dir && !nilfs_empty_dir(new_inode)) goto out_dir; new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, @@ -401,11 +407,13 @@ static int nilfs_rename(struct mnt_idmap *idmap, err = PTR_ERR(new_de); goto out_dir; } - nilfs_set_link(new_dir, new_de, new_folio, old_inode); + err = nilfs_set_link(new_dir, new_de, new_folio, old_inode); folio_release_kmap(new_folio, new_de); + if (unlikely(err)) + goto out_dir; nilfs_mark_inode_dirty(new_dir); inode_set_ctime_current(new_inode); - if (dir_de) + if (old_is_dir) drop_nlink(new_inode); drop_nlink(new_inode); nilfs_mark_inode_dirty(new_inode); @@ -413,7 +421,7 @@ static int nilfs_rename(struct mnt_idmap *idmap, err = nilfs_add_link(new_dentry, old_inode); if (err) goto out_dir; - if (dir_de) { + if (old_is_dir) { inc_nlink(new_dir); nilfs_mark_inode_dirty(new_dir); } @@ -425,28 +433,28 @@ static int nilfs_rename(struct mnt_idmap *idmap, */ inode_set_ctime_current(old_inode); - nilfs_delete_entry(old_de, old_folio); - - if (dir_de) { - nilfs_set_link(old_inode, dir_de, dir_folio, new_dir); - folio_release_kmap(dir_folio, dir_de); - drop_nlink(old_dir); + err = nilfs_delete_entry(old_de, old_folio); + if (likely(!err)) { + if (old_is_dir) { + if (old_dir != new_dir) + err = nilfs_set_link(old_inode, dir_de, + dir_folio, new_dir); + drop_nlink(old_dir); + } + nilfs_mark_inode_dirty(old_dir); } - folio_release_kmap(old_folio, old_de); - - nilfs_mark_inode_dirty(old_dir); nilfs_mark_inode_dirty(old_inode); - err = nilfs_transaction_commit(old_dir->i_sb); - return err; - out_dir: if (dir_de) folio_release_kmap(dir_folio, dir_de); out_old: folio_release_kmap(old_folio, old_de); out: - nilfs_transaction_abort(old_dir->i_sb); + if (likely(!err)) + err = nilfs_transaction_commit(old_dir->i_sb); + else + nilfs_transaction_abort(old_dir->i_sb); return err; } diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 45d03826eaf1..cb6ed54accd7 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -261,8 +261,8 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *, const struct qstr *, int nilfs_delete_entry(struct nilfs_dir_entry *, struct folio *); int nilfs_empty_dir(struct inode *); struct nilfs_dir_entry *nilfs_dotdot(struct inode *, struct folio **); -void nilfs_set_link(struct inode *, struct nilfs_dir_entry *, - struct folio *, struct inode *); +int nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, + struct folio *folio, struct inode *inode); /* file.c */ extern int nilfs_sync_file(struct file *, loff_t, loff_t, int); @@ -401,6 +401,7 @@ extern const struct file_operations nilfs_dir_operations; extern const struct inode_operations nilfs_file_inode_operations; extern const struct file_operations nilfs_file_operations; extern const struct address_space_operations nilfs_aops; +extern const struct address_space_operations nilfs_buffer_cache_aops; extern const struct inode_operations nilfs_dir_inode_operations; extern const struct inode_operations nilfs_special_inode_operations; extern const struct inode_operations nilfs_symlink_inode_operations; diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 9de2a494a069..806b056d2260 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -135,8 +135,7 @@ void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh) * nilfs_folio_buffers_clean - Check if a folio has dirty buffers or not. * @folio: Folio to be checked. * - * nilfs_folio_buffers_clean() returns false if the folio has dirty buffers. - * Otherwise, it returns true. + * Return: false if the folio has dirty buffers, true otherwise. */ bool nilfs_folio_buffers_clean(struct folio *folio) { @@ -392,6 +391,11 @@ void nilfs_clear_dirty_pages(struct address_space *mapping) /** * nilfs_clear_folio_dirty - discard dirty folio * @folio: dirty folio that will be discarded + * + * nilfs_clear_folio_dirty() clears working states including dirty state for + * the folio and its buffers. If the folio has buffers, clear only if it is + * confirmed that none of the buffer heads are busy (none have valid + * references and none are locked). */ void nilfs_clear_folio_dirty(struct folio *folio) { @@ -399,10 +403,6 @@ void nilfs_clear_folio_dirty(struct folio *folio) BUG_ON(!folio_test_locked(folio)); - folio_clear_uptodate(folio); - folio_clear_mappedtodisk(folio); - folio_clear_checked(folio); - head = folio_buffers(folio); if (head) { const unsigned long clear_bits = @@ -410,6 +410,25 @@ void nilfs_clear_folio_dirty(struct folio *folio) BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) | BIT(BH_Delay)); + bool busy, invalidated = false; + +recheck_buffers: + busy = false; + bh = head; + do { + if (atomic_read(&bh->b_count) | buffer_locked(bh)) { + busy = true; + break; + } + } while (bh = bh->b_this_page, bh != head); + + if (busy) { + if (invalidated) + return; + invalidate_bh_lrus(); + invalidated = true; + goto recheck_buffers; + } bh = head; do { @@ -419,6 +438,9 @@ void nilfs_clear_folio_dirty(struct folio *folio) } while (bh = bh->b_this_page, bh != head); } + folio_clear_uptodate(folio); + folio_clear_mappedtodisk(folio); + folio_clear_checked(folio); __nilfs_clear_folio_dirty(folio); } @@ -477,8 +499,9 @@ void __nilfs_clear_folio_dirty(struct folio *folio) * This function searches an extent of buffers marked "delayed" which * starts from a block offset equal to or larger than @start_blk. If * such an extent was found, this will store the start offset in - * @blkoff and return its length in blocks. Otherwise, zero is - * returned. + * @blkoff and return its length in blocks. + * + * Return: Length in blocks of found extent, 0 otherwise. */ unsigned long nilfs_find_uncommitted_extent(struct inode *inode, sector_t start_blk, diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index e43405bf521e..22aecf6e2344 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -88,6 +88,8 @@ static int nilfs_warn_segment_error(struct super_block *sb, int err) * @check_bytes: number of bytes to be checked * @start: DBN of start block * @nblock: number of blocks to be checked + * + * Return: 0 on success, or %-EIO if an I/O error occurs. */ static int nilfs_compute_checksum(struct the_nilfs *nilfs, struct buffer_head *bhs, u32 *sum, @@ -126,6 +128,11 @@ static int nilfs_compute_checksum(struct the_nilfs *nilfs, * @sr_block: disk block number of the super root block * @pbh: address of a buffer_head pointer to return super root buffer * @check: CRC check flag + * + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EINVAL - Super root block corrupted. + * * %-EIO - I/O error. */ int nilfs_read_super_root_block(struct the_nilfs *nilfs, sector_t sr_block, struct buffer_head **pbh, int check) @@ -176,6 +183,8 @@ int nilfs_read_super_root_block(struct the_nilfs *nilfs, sector_t sr_block, * @nilfs: nilfs object * @start_blocknr: start block number of the log * @sum: pointer to return segment summary structure + * + * Return: Buffer head pointer, or NULL if an I/O error occurs. */ static struct buffer_head * nilfs_read_log_header(struct the_nilfs *nilfs, sector_t start_blocknr, @@ -195,6 +204,13 @@ nilfs_read_log_header(struct the_nilfs *nilfs, sector_t start_blocknr, * @seg_seq: sequence number of segment * @bh_sum: buffer head of summary block * @sum: segment summary struct + * + * Return: 0 on success, or one of the following internal codes on failure: + * * %NILFS_SEG_FAIL_MAGIC - Magic number mismatch. + * * %NILFS_SEG_FAIL_SEQ - Sequence number mismatch. + * * %NIFLS_SEG_FAIL_CONSISTENCY - Block count out of range. + * * %NILFS_SEG_FAIL_IO - I/O error. + * * %NILFS_SEG_FAIL_CHECKSUM_FULL - Full log checksum verification failed. */ static int nilfs_validate_log(struct the_nilfs *nilfs, u64 seg_seq, struct buffer_head *bh_sum, @@ -238,6 +254,9 @@ out: * @pbh: the current buffer head on summary blocks [in, out] * @offset: the current byte offset on summary blocks [in, out] * @bytes: byte size of the item to be read + * + * Return: Kernel space address of current segment summary entry, or + * NULL if an I/O error occurs. */ static void *nilfs_read_summary_info(struct the_nilfs *nilfs, struct buffer_head **pbh, @@ -300,6 +319,11 @@ static void nilfs_skip_summary_info(struct the_nilfs *nilfs, * @start_blocknr: start block number of the log * @sum: log summary information * @head: list head to add nilfs_recovery_block struct + * + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_scan_dsync_log(struct the_nilfs *nilfs, sector_t start_blocknr, struct nilfs_segment_summary *sum, @@ -571,6 +595,12 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, * @sb: super block instance * @root: NILFS root instance * @ri: pointer to a nilfs_recovery_info + * + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EINVAL - Log format error. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_do_roll_forward(struct the_nilfs *nilfs, struct super_block *sb, @@ -754,18 +784,13 @@ static void nilfs_abort_roll_forward(struct the_nilfs *nilfs) * @sb: super block instance * @ri: pointer to a nilfs_recovery_info struct to store search results. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error code is returned. - * - * %-EINVAL - Inconsistent filesystem state. - * - * %-EIO - I/O error - * - * %-ENOSPC - No space left on device (only in a panic state). - * - * %-ERESTARTSYS - Interrupted. - * - * %-ENOMEM - Insufficient memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EINVAL - Inconsistent filesystem state. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. + * * %-ENOSPC - No space left on device (only in a panic state). + * * %-ERESTARTSYS - Interrupted. */ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs, struct super_block *sb, @@ -830,14 +855,11 @@ failed: * segment pointed by the superblock. It sets up struct the_nilfs through * this search. It fills nilfs_recovery_info (ri) required for recovery. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error code is returned. - * - * %-EINVAL - No valid segment found - * - * %-EIO - I/O error - * - * %-ENOMEM - Insufficient memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EINVAL - No valid segment found. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. */ int nilfs_search_super_root(struct the_nilfs *nilfs, struct nilfs_recovery_info *ri) diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index e08cab03366b..a8bdf3d318ea 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -406,12 +406,7 @@ static int nilfs_segbuf_submit_bh(struct nilfs_segment_buffer *segbuf, * @segbuf: buffer storing a log to be written * @nilfs: nilfs object * - * Return Value: On Success, 0 is returned. On Error, one of the following - * negative error code is returned. - * - * %-EIO - I/O error - * - * %-ENOMEM - Insufficient memory available. + * Return: Always 0. */ static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf, struct the_nilfs *nilfs) @@ -452,10 +447,7 @@ static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf, * nilfs_segbuf_wait - wait for completion of requested BIOs * @segbuf: segment buffer * - * Return Value: On Success, 0 is returned. On Error, one of the following - * negative error code is returned. - * - * %-EIO - I/O error + * Return: 0 on success, or %-EIO if I/O error is detected. */ static int nilfs_segbuf_wait(struct nilfs_segment_buffer *segbuf) { diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 587251830897..3a202e51b360 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -191,12 +191,10 @@ static int nilfs_prepare_segment_lock(struct super_block *sb, * When @vacancy_check flag is set, this function will check the amount of * free space, and will wait for the GC to reclaim disk space if low capacity. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error code is returned. - * - * %-ENOMEM - Insufficient memory available. - * - * %-ENOSPC - No space left on device + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-ENOMEM - Insufficient memory available. + * * %-ENOSPC - No space left on device (if checking free space). */ int nilfs_transaction_begin(struct super_block *sb, struct nilfs_transaction_info *ti, @@ -252,6 +250,8 @@ int nilfs_transaction_begin(struct super_block *sb, * nilfs_transaction_commit() sets a timer to start the segment * constructor. If a sync flag is set, it starts construction * directly. + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_transaction_commit(struct super_block *sb) { @@ -407,6 +407,8 @@ static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, /** * nilfs_segctor_reset_segment_buffer - reset the current segment buffer * @sci: nilfs_sc_info + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci) { @@ -734,7 +736,6 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, if (!head) head = create_empty_buffers(folio, i_blocksize(inode), 0); - folio_unlock(folio); bh = head; do { @@ -744,11 +745,14 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, list_add_tail(&bh->b_assoc_buffers, listp); ndirties++; if (unlikely(ndirties >= nlimit)) { + folio_unlock(folio); folio_batch_release(&fbatch); cond_resched(); return ndirties; } } while (bh = bh->b_this_page, bh != head); + + folio_unlock(folio); } folio_batch_release(&fbatch); cond_resched(); @@ -1118,7 +1122,8 @@ static int nilfs_segctor_scan_file_dsync(struct nilfs_sc_info *sci, * a super root block containing this sufile change is complete, and it can * be canceled with nilfs_sufile_cancel_freev() until then. * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-EINVAL - Invalid segment number. * * %-EIO - I/O error (including metadata corruption). * * %-ENOMEM - Insufficient memory available. @@ -1315,6 +1320,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) * nilfs_segctor_begin_construction - setup segment buffer to make a new log * @sci: nilfs_sc_info * @nilfs: nilfs object + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_segctor_begin_construction(struct nilfs_sc_info *sci, struct the_nilfs *nilfs) @@ -2312,18 +2319,13 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err, bool force) * nilfs_construct_segment - construct a logical segment * @sb: super block * - * Return Value: On success, 0 is returned. On errors, one of the following - * negative error code is returned. - * - * %-EROFS - Read only filesystem. - * - * %-EIO - I/O error - * - * %-ENOSPC - No space left on device (only in a panic state). - * - * %-ERESTARTSYS - Interrupted. - * - * %-ENOMEM - Insufficient memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. + * * %-ENOSPC - No space left on device (only in a panic state). + * * %-ERESTARTSYS - Interrupted. + * * %-EROFS - Read only filesystem. */ int nilfs_construct_segment(struct super_block *sb) { @@ -2347,18 +2349,13 @@ int nilfs_construct_segment(struct super_block *sb) * @start: start byte offset * @end: end byte offset (inclusive) * - * Return Value: On success, 0 is returned. On errors, one of the following - * negative error code is returned. - * - * %-EROFS - Read only filesystem. - * - * %-EIO - I/O error - * - * %-ENOSPC - No space left on device (only in a panic state). - * - * %-ERESTARTSYS - Interrupted. - * - * %-ENOMEM - Insufficient memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. + * * %-ENOSPC - No space left on device (only in a panic state). + * * %-ERESTARTSYS - Interrupted. + * * %-EROFS - Read only filesystem. */ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode, loff_t start, loff_t end) @@ -2464,6 +2461,8 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err) * nilfs_segctor_construct - form logs and write them to disk * @sci: segment constructor object * @mode: mode of log forming + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_segctor_construct(struct nilfs_sc_info *sci, int mode) { @@ -2836,7 +2835,8 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) * This allocates a log writer object, initializes it, and starts the * log writer. * - * Return: 0 on success, or the following negative error code on failure. + * Return: 0 on success, or one of the following negative error codes on + * failure: * * %-EINTR - Log writer thread creation failed due to interruption. * * %-ENOMEM - Insufficient memory available. */ diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index d3ecc813d633..330f269abedf 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -133,6 +133,8 @@ static void nilfs_sufile_mod_counter(struct buffer_head *header_bh, /** * nilfs_sufile_get_ncleansegs - return the number of clean segments * @sufile: inode of segment usage file + * + * Return: Number of clean segments. */ unsigned long nilfs_sufile_get_ncleansegs(struct inode *sufile) { @@ -155,17 +157,13 @@ unsigned long nilfs_sufile_get_ncleansegs(struct inode *sufile) * of successfully modified segments from the head is stored in the * place @ndone points to. * - * Return Value: On success, zero is returned. On error, one of the - * following negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOENT - Given segment usage is in hole block (may be returned if - * @create is zero) - * - * %-EINVAL - Invalid segment usage number + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EINVAL - Invalid segment usage number + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOENT - Given segment usage is in hole block (may be returned if + * @create is zero) + * * %-ENOMEM - Insufficient memory available. */ int nilfs_sufile_updatev(struct inode *sufile, __u64 *segnumv, size_t nsegs, int create, size_t *ndone, @@ -272,10 +270,7 @@ int nilfs_sufile_update(struct inode *sufile, __u64 segnum, int create, * @start: minimum segment number of allocatable region (inclusive) * @end: maximum segment number of allocatable region (inclusive) * - * Return Value: On success, 0 is returned. On error, one of the - * following negative error codes is returned. - * - * %-ERANGE - invalid segment region + * Return: 0 on success, or %-ERANGE if segment range is invalid. */ int nilfs_sufile_set_alloc_range(struct inode *sufile, __u64 start, __u64 end) { @@ -300,17 +295,14 @@ int nilfs_sufile_set_alloc_range(struct inode *sufile, __u64 start, __u64 end) * @sufile: inode of segment usage file * @segnump: pointer to segment number * - * Description: nilfs_sufile_alloc() allocates a clean segment. + * Description: nilfs_sufile_alloc() allocates a clean segment, and stores + * its segment number in the place pointed to by @segnump. * - * Return Value: On success, 0 is returned and the segment number of the - * allocated segment is stored in the place pointed by @segnump. On error, one - * of the following negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOSPC - No clean segment left. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. + * * %-ENOSPC - No clean segment left. */ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) { @@ -510,6 +502,8 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, * nilfs_sufile_mark_dirty - mark the buffer having a segment usage dirty * @sufile: inode of segment usage file * @segnum: segment number + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum) { @@ -569,6 +563,8 @@ out_sem: * @segnum: segment number * @nblocks: number of live blocks in the segment * @modtime: modification time (option) + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum, unsigned long nblocks, time64_t modtime) @@ -610,16 +606,13 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum, * @sufile: inode of segment usage file * @sustat: pointer to a structure of segment usage statistics * - * Description: nilfs_sufile_get_stat() returns information about segment - * usage. + * Description: nilfs_sufile_get_stat() retrieves segment usage statistics + * and stores them in the location pointed to by @sustat. * - * Return Value: On success, 0 is returned, and segment usage information is - * stored in the place pointed by @sustat. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat) { @@ -683,16 +676,12 @@ void nilfs_sufile_do_set_error(struct inode *sufile, __u64 segnum, * @start: start segment number (inclusive) * @end: end segment number (inclusive) * - * Return Value: On success, 0 is returned. On error, one of the - * following negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EINVAL - Invalid number of segments specified - * - * %-EBUSY - Dirty or active segments are present in the range + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EBUSY - Dirty or active segments are present in the range. + * * %-EINVAL - Invalid number of segments specified. + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ static int nilfs_sufile_truncate_range(struct inode *sufile, __u64 start, __u64 end) @@ -787,16 +776,12 @@ out: * @sufile: inode of segment usage file * @newnsegs: new number of segments * - * Return Value: On success, 0 is returned. On error, one of the - * following negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-ENOSPC - Enough free space is not left for shrinking - * - * %-EBUSY - Dirty or active segments exist in the region to be truncated + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EBUSY - Dirty or active segments exist in the region to be truncated. + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. + * * %-ENOSPC - Enough free space is not left for shrinking. */ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs) { @@ -865,7 +850,7 @@ out: * @nsi: size of suinfo array * * Return: Count of segment usage info items stored in the output buffer on - * success, or the following negative error code on failure. + * success, or one of the following negative error codes on failure: * * %-EIO - I/O error (including metadata corruption). * * %-ENOMEM - Insufficient memory available. */ @@ -939,14 +924,11 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf, * segment usage accordingly. Only the fields indicated by the sup_flags * are updated. * - * Return Value: On success, 0 is returned. On error, one of the - * following negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EINVAL - Invalid values in input (segment number, flags or nblocks) + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EINVAL - Invalid values in input (segment number, flags or nblocks). + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf, unsigned int supsz, size_t nsup) @@ -1073,7 +1055,7 @@ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf, * and start+len is rounded down. For each clean segment blkdev_issue_discard * function is invoked. * - * Return Value: On success, 0 is returned or negative error code, otherwise. + * Return: 0 on success, or a negative error code on failure. */ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range) { @@ -1219,6 +1201,8 @@ out_sem: * @susize: size of a segment usage entry * @raw_inode: on-disk sufile inode * @inodep: buffer to store the inode + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_sufile_read(struct super_block *sb, size_t susize, struct nilfs_inode *raw_inode, struct inode **inodep) diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h index 8e8a1a5a0402..cd6f28ab3521 100644 --- a/fs/nilfs2/sufile.h +++ b/fs/nilfs2/sufile.h @@ -58,6 +58,8 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range); * nilfs_sufile_scrap - make a segment garbage * @sufile: inode of segment usage file * @segnum: segment number to be freed + * + * Return: 0 on success, or a negative error code on failure. */ static inline int nilfs_sufile_scrap(struct inode *sufile, __u64 segnum) { @@ -68,6 +70,8 @@ static inline int nilfs_sufile_scrap(struct inode *sufile, __u64 segnum) * nilfs_sufile_free - free segment * @sufile: inode of segment usage file * @segnum: segment number to be freed + * + * Return: 0 on success, or a negative error code on failure. */ static inline int nilfs_sufile_free(struct inode *sufile, __u64 segnum) { @@ -80,6 +84,8 @@ static inline int nilfs_sufile_free(struct inode *sufile, __u64 segnum) * @segnumv: array of segment numbers * @nsegs: size of @segnumv array * @ndone: place to store the number of freed segments + * + * Return: 0 on success, or a negative error code on failure. */ static inline int nilfs_sufile_freev(struct inode *sufile, __u64 *segnumv, size_t nsegs, size_t *ndone) @@ -95,8 +101,7 @@ static inline int nilfs_sufile_freev(struct inode *sufile, __u64 *segnumv, * @nsegs: size of @segnumv array * @ndone: place to store the number of cancelled segments * - * Return Value: On success, 0 is returned. On error, a negative error codes - * is returned. + * Return: 0 on success, or a negative error code on failure. */ static inline int nilfs_sufile_cancel_freev(struct inode *sufile, __u64 *segnumv, size_t nsegs, @@ -114,14 +119,11 @@ static inline int nilfs_sufile_cancel_freev(struct inode *sufile, * Description: nilfs_sufile_set_error() marks the segment specified by * @segnum as erroneous. The error segment will never be used again. * - * Return Value: On success, 0 is returned. On error, one of the following - * negative error codes is returned. - * - * %-EIO - I/O error. - * - * %-ENOMEM - Insufficient amount of memory available. - * - * %-EINVAL - Invalid segment usage number. + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EINVAL - Invalid segment usage number. + * * %-EIO - I/O error (including metadata corruption). + * * %-ENOMEM - Insufficient memory available. */ static inline int nilfs_sufile_set_error(struct inode *sufile, __u64 segnum) { diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index eca79cca3803..badc2cbc895e 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -309,6 +309,8 @@ int nilfs_commit_super(struct super_block *sb, int flag) * This function restores state flags in the on-disk super block. * This will set "clean" flag (i.e. NILFS_VALID_FS) unless the * filesystem was not clean previously. + * + * Return: 0 on success, %-EIO if I/O error or superblock is corrupted. */ int nilfs_cleanup_super(struct super_block *sb) { @@ -339,6 +341,8 @@ int nilfs_cleanup_super(struct super_block *sb) * nilfs_move_2nd_super - relocate secondary super block * @sb: super block instance * @sb2off: new offset of the secondary super block (in bytes) + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) { @@ -420,6 +424,8 @@ out: * nilfs_resize_fs - resize the filesystem * @sb: super block instance * @newsize: new size of the filesystem (in bytes) + * + * Return: 0 on success, or a negative error code on failure. */ int nilfs_resize_fs(struct super_block *sb, __u64 newsize) { @@ -987,7 +993,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno, * nilfs_tree_is_busy() - try to shrink dentries of a checkpoint * @root_dentry: root dentry of the tree to be shrunk * - * This function returns true if the tree was in-use. + * Return: true if the tree was in-use, false otherwise. */ static bool nilfs_tree_is_busy(struct dentry *root_dentry) { @@ -1033,6 +1039,8 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno) * * This function is called exclusively by nilfs->ns_mount_mutex. * So, the recovery process is protected from other simultaneous mounts. + * + * Return: 0 on success, or a negative error code on failure. */ static int nilfs_fill_super(struct super_block *sb, struct fs_context *fc) diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index ac03fd3c330c..cb01ea81724d 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -49,8 +49,8 @@ void nilfs_set_last_segment(struct the_nilfs *nilfs, * alloc_nilfs - allocate a nilfs object * @sb: super block instance * - * Return Value: On success, pointer to the_nilfs is returned. - * On error, NULL is returned. + * Return: a pointer to the allocated nilfs object on success, or NULL on + * failure. */ struct the_nilfs *alloc_nilfs(struct super_block *sb) { @@ -165,6 +165,9 @@ static void nilfs_clear_recovery_info(struct nilfs_recovery_info *ri) * containing a super root from a given super block, and initializes * relevant information on the nilfs object preparatory for log * scanning and recovery. + * + * Return: 0 on success, or %-EINVAL if current segment number is out + * of range. */ static int nilfs_store_log_cursor(struct the_nilfs *nilfs, struct nilfs_super_block *sbp) @@ -200,8 +203,7 @@ static int nilfs_store_log_cursor(struct the_nilfs *nilfs, * exponent information written in @sbp and stores it in @blocksize, * or aborts with an error message if it's too large. * - * Return Value: On success, 0 is returned. If the block size is too - * large, -EINVAL is returned. + * Return: 0 on success, or %-EINVAL if the block size is too large. */ static int nilfs_get_blocksize(struct super_block *sb, struct nilfs_super_block *sbp, int *blocksize) @@ -226,6 +228,13 @@ static int nilfs_get_blocksize(struct super_block *sb, * load_nilfs() searches and load the latest super root, * attaches the last segment, and does recovery if needed. * The caller must call this exclusively for simultaneous mounts. + * + * Return: 0 on success, or one of the following negative error codes on + * failure: + * * %-EINVAL - No valid segment found. + * * %-EIO - I/O error. + * * %-ENOMEM - Insufficient memory available. + * * %-EROFS - Read only device or RO compat mode (if recovery is required) */ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) { @@ -395,6 +404,8 @@ static unsigned long long nilfs_max_size(unsigned int blkbits) * nilfs_nrsvsegs - calculate the number of reserved segments * @nilfs: nilfs object * @nsegs: total number of segments + * + * Return: Number of reserved segments. */ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs) { @@ -406,6 +417,8 @@ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs) /** * nilfs_max_segment_count - calculate the maximum number of segments * @nilfs: nilfs object + * + * Return: Maximum number of segments */ static u64 nilfs_max_segment_count(struct the_nilfs *nilfs) { @@ -538,7 +551,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp) * area, or if the parameters themselves are not normal, it is * determined to be invalid. * - * Return Value: true if invalid, false if valid. + * Return: true if invalid, false if valid. */ static bool nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset) { @@ -684,8 +697,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, * reading the super block, getting disk layout information, initializing * shared fields in the_nilfs). * - * Return Value: On success, 0 is returned. On error, a negative error - * code is returned. + * Return: 0 on success, or a negative error code on failure. */ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb) { diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 6004dfdfdf0f..c4cdaf5fa7ed 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -20,7 +20,7 @@ static int dir_notify_enable __read_mostly = 1; #ifdef CONFIG_SYSCTL -static struct ctl_table dnotify_sysctls[] = { +static const struct ctl_table dnotify_sysctls[] = { { .procname = "dir-notify-enable", .data = &dir_notify_enable, diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 24c7c5df4998..95646f7c46ca 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -223,7 +223,7 @@ static int fanotify_get_response(struct fsnotify_group *group, struct fanotify_perm_event *event, struct fsnotify_iter_info *iter_info) { - int ret; + int ret, errno; pr_debug("%s: group=%p event=%p\n", __func__, group, event); @@ -262,14 +262,23 @@ static int fanotify_get_response(struct fsnotify_group *group, ret = 0; break; case FAN_DENY: + /* Check custom errno from pre-content events */ + errno = fanotify_get_response_errno(event->response); + if (errno) { + ret = -errno; + break; + } + fallthrough; default: ret = -EPERM; } /* Check if the response should be audited */ - if (event->response & FAN_AUDIT) - audit_fanotify(event->response & ~FAN_AUDIT, - &event->audit_rule); + if (event->response & FAN_AUDIT) { + u32 response = event->response & + (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS); + audit_fanotify(response & ~FAN_AUDIT, &event->audit_rule); + } pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__, group, event, ret); @@ -548,9 +557,13 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path, return &pevent->fae; } -static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, +static struct fanotify_event *fanotify_alloc_perm_event(const void *data, + int data_type, gfp_t gfp) { + const struct path *path = fsnotify_data_path(data, data_type); + const struct file_range *range = + fsnotify_data_file_range(data, data_type); struct fanotify_perm_event *pevent; pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp); @@ -564,6 +577,9 @@ static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, pevent->hdr.len = 0; pevent->state = FAN_EVENT_INIT; pevent->path = *path; + /* NULL ppos means no range info */ + pevent->ppos = range ? &range->pos : NULL; + pevent->count = range ? range->count : 0; path_get(path); return &pevent->fae; @@ -801,7 +817,7 @@ static struct fanotify_event *fanotify_alloc_event( old_memcg = set_active_memcg(group->memcg); if (fanotify_is_perm_event(mask)) { - event = fanotify_alloc_perm_event(path, gfp); + event = fanotify_alloc_perm_event(data, data_type, gfp); } else if (fanotify_is_error_event(mask)) { event = fanotify_alloc_error_event(group, fsid, data, data_type, &hash); @@ -909,8 +925,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); BUILD_BUG_ON(FAN_RENAME != FS_RENAME); + BUILD_BUG_ON(FAN_PRE_ACCESS != FS_PRE_ACCESS); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 22); mask = fanotify_group_event_mask(group, iter_info, &match_mask, mask, data, data_type, dir); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index e5ab33cae6a7..c12cbc270539 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -425,6 +425,8 @@ FANOTIFY_PE(struct fanotify_event *event) struct fanotify_perm_event { struct fanotify_event fae; struct path path; + const loff_t *ppos; /* optional file range info */ + size_t count; u32 response; /* userspace answer to the event */ unsigned short state; /* state of the event */ int fd; /* fd we passed to userspace for this event */ @@ -446,6 +448,14 @@ static inline bool fanotify_is_perm_event(u32 mask) mask & FANOTIFY_PERM_EVENTS; } +static inline bool fanotify_event_has_access_range(struct fanotify_event *event) +{ + if (!(event->mask & FANOTIFY_PRE_CONTENT_EVENTS)) + return false; + + return FANOTIFY_PERM(event)->ppos; +} + static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse) { return container_of(fse, struct fanotify_event, fse); @@ -518,3 +528,8 @@ static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark) return mflags; } + +static inline u32 fanotify_get_response_errno(int res) +{ + return (res >> FAN_ERRNO_SHIFT) & FAN_ERRNO_MASK; +} diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 2d85c71717d6..ba3e2d09eb44 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -58,7 +58,7 @@ static int fanotify_max_queued_events __read_mostly; static long ft_zero = 0; static long ft_int_max = INT_MAX; -static struct ctl_table fanotify_table[] = { +static const struct ctl_table fanotify_table[] = { { .procname = "max_user_groups", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS], @@ -100,8 +100,7 @@ static void __init fanotify_sysctls_init(void) * * Internal and external open flags are stored together in field f_flags of * struct file. Only external open flags shall be allowed in event_f_flags. - * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be - * excluded. + * Internal flags like FMODE_EXEC shall be excluded. */ #define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \ O_ACCMODE | O_APPEND | O_NONBLOCK | \ @@ -118,10 +117,12 @@ struct kmem_cache *fanotify_perm_event_cachep __ro_after_init; #define FANOTIFY_EVENT_ALIGN 4 #define FANOTIFY_FID_INFO_HDR_LEN \ (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle)) -#define FANOTIFY_PIDFD_INFO_HDR_LEN \ +#define FANOTIFY_PIDFD_INFO_LEN \ sizeof(struct fanotify_event_info_pidfd) #define FANOTIFY_ERROR_INFO_LEN \ (sizeof(struct fanotify_event_info_error)) +#define FANOTIFY_RANGE_INFO_LEN \ + (sizeof(struct fanotify_event_info_range)) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -159,9 +160,6 @@ static size_t fanotify_event_len(unsigned int info_mode, int fh_len; int dot_len = 0; - if (!info_mode) - return event_len; - if (fanotify_is_error_event(event->mask)) event_len += FANOTIFY_ERROR_INFO_LEN; @@ -176,14 +174,17 @@ static size_t fanotify_event_len(unsigned int info_mode, dot_len = 1; } - if (info_mode & FAN_REPORT_PIDFD) - event_len += FANOTIFY_PIDFD_INFO_HDR_LEN; - if (fanotify_event_has_object_fh(event)) { fh_len = fanotify_event_object_fh_len(event); event_len += fanotify_fid_info_len(fh_len, dot_len); } + if (info_mode & FAN_REPORT_PIDFD) + event_len += FANOTIFY_PIDFD_INFO_LEN; + + if (fanotify_event_has_access_range(event)) + event_len += FANOTIFY_RANGE_INFO_LEN; + return event_len; } @@ -258,12 +259,11 @@ static int create_fd(struct fsnotify_group *group, const struct path *path, return client_fd; /* - * we need a new file handle for the userspace program so it can read even if it was - * originally opened O_WRONLY. + * We provide an fd for the userspace program, so it could access the + * file without generating fanotify events itself. */ - new_file = dentry_open(path, - group->fanotify_data.f_flags | __FMODE_NONOTIFY, - current_cred()); + new_file = dentry_open_nonotify(path, group->fanotify_data.f_flags, + current_cred()); if (IS_ERR(new_file)) { put_unused_fd(client_fd); client_fd = PTR_ERR(new_file); @@ -327,11 +327,12 @@ static int process_access_response(struct fsnotify_group *group, struct fanotify_perm_event *event; int fd = response_struct->fd; u32 response = response_struct->response; + int errno = fanotify_get_response_errno(response); int ret = info_len; struct fanotify_response_info_audit_rule friar; - pr_debug("%s: group=%p fd=%d response=%u buf=%p size=%zu\n", __func__, - group, fd, response, info, info_len); + pr_debug("%s: group=%p fd=%d response=%x errno=%d buf=%p size=%zu\n", + __func__, group, fd, response, errno, info, info_len); /* * make sure the response is valid, if invalid we do nothing and either * userspace can send a valid response or we will clean it up after the @@ -342,7 +343,31 @@ static int process_access_response(struct fsnotify_group *group, switch (response & FANOTIFY_RESPONSE_ACCESS) { case FAN_ALLOW: + if (errno) + return -EINVAL; + break; case FAN_DENY: + /* Custom errno is supported only for pre-content groups */ + if (errno && group->priority != FSNOTIFY_PRIO_PRE_CONTENT) + return -EINVAL; + + /* + * Limit errno to values expected on open(2)/read(2)/write(2) + * of regular files. + */ + switch (errno) { + case 0: + case EIO: + case EPERM: + case EBUSY: + case ETXTBSY: + case EAGAIN: + case ENOSPC: + case EDQUOT: + break; + default: + return -EINVAL; + } break; default: return -EINVAL; @@ -506,7 +531,7 @@ static int copy_pidfd_info_to_user(int pidfd, size_t count) { struct fanotify_event_info_pidfd info = { }; - size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN; + size_t info_len = FANOTIFY_PIDFD_INFO_LEN; if (WARN_ON_ONCE(info_len > count)) return -EFAULT; @@ -521,6 +546,30 @@ static int copy_pidfd_info_to_user(int pidfd, return info_len; } +static size_t copy_range_info_to_user(struct fanotify_event *event, + char __user *buf, int count) +{ + struct fanotify_perm_event *pevent = FANOTIFY_PERM(event); + struct fanotify_event_info_range info = { }; + size_t info_len = FANOTIFY_RANGE_INFO_LEN; + + if (WARN_ON_ONCE(info_len > count)) + return -EFAULT; + + if (WARN_ON_ONCE(!pevent->ppos)) + return -EINVAL; + + info.hdr.info_type = FAN_EVENT_INFO_TYPE_RANGE; + info.hdr.len = info_len; + info.offset = *(pevent->ppos); + info.count = pevent->count; + + if (copy_to_user(buf, &info, info_len)) + return -EFAULT; + + return info_len; +} + static int copy_info_records_to_user(struct fanotify_event *event, struct fanotify_info *info, unsigned int info_mode, int pidfd, @@ -642,6 +691,15 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + if (fanotify_event_has_access_range(event)) { + ret = copy_range_info_to_user(event, buf, count); + if (ret < 0) + return ret; + buf += ret; + count -= ret; + total_bytes += ret; + } + return total_bytes; } @@ -756,12 +814,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, buf += FAN_EVENT_METADATA_LEN; count -= FAN_EVENT_METADATA_LEN; - if (info_mode) { - ret = copy_info_records_to_user(event, info, info_mode, pidfd, - buf, count); - if (ret < 0) - goto out_close_fd; - } + ret = copy_info_records_to_user(event, info, info_mode, pidfd, + buf, count); + if (ret < 0) + goto out_close_fd; if (f) fd_install(fd, f); @@ -1294,7 +1350,7 @@ static int fanotify_group_init_error_pool(struct fsnotify_group *group) } static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark, - unsigned int fan_flags) + __u32 mask, unsigned int fan_flags) { /* * Non evictable mark cannot be downgraded to evictable mark. @@ -1321,6 +1377,11 @@ static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark, fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY) return -EEXIST; + /* For now pre-content events are not generated for directories */ + mask |= fsn_mark->mask; + if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR) + return -EEXIST; + return 0; } @@ -1347,7 +1408,7 @@ static int fanotify_add_mark(struct fsnotify_group *group, /* * Check if requested mark flags conflict with an existing mark flags. */ - ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags); + ret = fanotify_may_update_existing_mark(fsn_mark, mask, fan_flags); if (ret) goto out; @@ -1409,6 +1470,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) unsigned int fid_mode = flags & FANOTIFY_FID_BITS; unsigned int class = flags & FANOTIFY_CLASS_BITS; unsigned int internal_flags = 0; + struct file *file; pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); @@ -1477,7 +1539,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID))) return -EINVAL; - f_flags = O_RDWR | __FMODE_NONOTIFY; + f_flags = O_RDWR; if (flags & FAN_CLOEXEC) f_flags |= O_CLOEXEC; if (flags & FAN_NONBLOCK) @@ -1555,10 +1617,18 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) goto out_destroy_group; } - fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags); + fd = get_unused_fd_flags(f_flags); if (fd < 0) goto out_destroy_group; + file = anon_inode_getfile_fmode("[fanotify]", &fanotify_fops, group, + f_flags, FMODE_NONOTIFY); + if (IS_ERR(file)) { + put_unused_fd(fd); + fd = PTR_ERR(file); + goto out_destroy_group; + } + fd_install(fd, file); return fd; out_destroy_group: @@ -1638,11 +1708,23 @@ static int fanotify_events_supported(struct fsnotify_group *group, unsigned int flags) { unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; + bool is_dir = d_is_dir(path->dentry); /* Strict validation of events in non-dir inode mask with v5.17+ APIs */ bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) || (mask & FAN_RENAME) || (flags & FAN_MARK_IGNORE); + /* + * Filesystems need to opt-into pre-content evnets (a.k.a HSM) + * and they are only supported on regular files and directories. + */ + if (mask & FANOTIFY_PRE_CONTENT_EVENTS) { + if (!(path->mnt->mnt_sb->s_iflags & SB_I_ALLOW_HSM)) + return -EOPNOTSUPP; + if (!is_dir && !d_is_reg(path->dentry)) + return -EINVAL; + } + /* * Some filesystems such as 'proc' acquire unusual locks when opening * files. For them fanotify permission events have high chances of @@ -1675,7 +1757,7 @@ static int fanotify_events_supported(struct fsnotify_group *group, * but because we always allowed it, error only when using new APIs. */ if (strict_dir_events && mark_type == FAN_MARK_INODE && - !d_is_dir(path->dentry) && (mask & FANOTIFY_DIRONLY_EVENT_BITS)) + !is_dir && (mask & FANOTIFY_DIRONLY_EVENT_BITS)) return -ENOTDIR; return 0; @@ -1776,10 +1858,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, return -EPERM; /* - * Permission events require minimum priority FAN_CLASS_CONTENT. + * Permission events are not allowed for FAN_CLASS_NOTIF. + * Pre-content permission events are not allowed for FAN_CLASS_CONTENT. */ if (mask & FANOTIFY_PERM_EVENTS && - group->priority < FSNOTIFY_PRIO_CONTENT) + group->priority == FSNOTIFY_PRIO_NORMAL) + return -EINVAL; + else if (mask & FANOTIFY_PRE_CONTENT_EVENTS && + group->priority == FSNOTIFY_PRIO_CONTENT) return -EINVAL; if (mask & FAN_FS_ERROR && @@ -1814,6 +1900,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME)) return -EINVAL; + /* Pre-content events are not currently generated for directories. */ + if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR) + return -EINVAL; + if (mark_cmd == FAN_MARK_FLUSH) { if (mark_type == FAN_MARK_MOUNT) fsnotify_clear_vfsmount_marks_by_group(group); diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index dec553034027..e933f9c65d90 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -47,10 +47,8 @@ static void show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f->handle_bytes >> 2; ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size); - if ((ret == FILEID_INVALID) || (ret < 0)) { - WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); + if ((ret == FILEID_INVALID) || (ret < 0)) return; - } f->handle_type = ret; f->handle_bytes = size * sizeof(u32); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index f976949d2634..8ee495a58d0a 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -193,7 +193,7 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, return mask & marks_mask; } -/* Are there any inode/mount/sb objects that are interested in this event? */ +/* Are there any inode/mount/sb objects that watch for these events? */ static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, __u32 mask) { @@ -203,6 +203,24 @@ static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, return mask & marks_mask & ALL_FSNOTIFY_EVENTS; } +/* Report pre-content event with optional range info */ +int fsnotify_pre_content(const struct path *path, const loff_t *ppos, + size_t count) +{ + struct file_range range; + + /* Report page aligned range only when pos is known */ + if (!ppos) + return fsnotify_path(path, FS_PRE_ACCESS); + + range.path = path; + range.pos = PAGE_ALIGN_DOWN(*ppos); + range.count = PAGE_ALIGN(*ppos + count) - range.pos; + + return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range, + FSNOTIFY_EVENT_FILE_RANGE); +} + /* * Notify this dentry's parent about a child's events with child name info * if parent is watching or if inode/sb/mount are interested in events with @@ -623,11 +641,72 @@ out: } EXPORT_SYMBOL_GPL(fsnotify); +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS +/* + * At open time we check fsnotify_sb_has_priority_watchers() and set the + * FMODE_NONOTIFY_ mode bits accordignly. + * Later, fsnotify permission hooks do not check if there are permission event + * watches, but that there were permission event watches at open time. + */ +void file_set_fsnotify_mode(struct file *file) +{ + struct dentry *dentry = file->f_path.dentry, *parent; + struct super_block *sb = dentry->d_sb; + __u32 mnt_mask, p_mask; + + /* Is it a file opened by fanotify? */ + if (FMODE_FSNOTIFY_NONE(file->f_mode)) + return; + + /* + * Permission events is a super set of pre-content events, so if there + * are no permission event watchers, there are also no pre-content event + * watchers and this is implied from the single FMODE_NONOTIFY_PERM bit. + */ + if (likely(!fsnotify_sb_has_priority_watchers(sb, + FSNOTIFY_PRIO_CONTENT))) { + file->f_mode |= FMODE_NONOTIFY_PERM; + return; + } + + /* + * If there are permission event watchers but no pre-content event + * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that. + */ + if ((!d_is_dir(dentry) && !d_is_reg(dentry)) || + likely(!fsnotify_sb_has_priority_watchers(sb, + FSNOTIFY_PRIO_PRE_CONTENT))) { + file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM; + return; + } + + /* + * OK, there are some pre-content watchers. Check if anybody is + * watching for pre-content events on *this* file. + */ + mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask); + if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask, + FSNOTIFY_PRE_CONTENT_EVENTS))) + return; + + /* Is parent watching for pre-content events on this file? */ + if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) { + parent = dget_parent(dentry); + p_mask = fsnotify_inode_watches_children(d_inode(parent)); + dput(parent); + if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) + return; + } + /* Nobody watching for pre-content events from this file */ + file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM; +} +#endif + static __init int fsnotify_init(void) { int ret; - BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23); + BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 24); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 993375f0db67..cd7d11b0eb08 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -121,7 +121,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, event->sync_cookie = cookie; event->name_len = len; if (len) - strcpy(event->name, name->name); + strscpy(event->name, name->name, event->name_len + 1); ret = fsnotify_add_event(group, fsn_event, inotify_merge); if (ret) { diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index e0c48956608a..b372fb2c56bd 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -58,7 +58,7 @@ struct kmem_cache *inotify_inode_mark_cachep __ro_after_init; static long it_zero = 0; static long it_int_max = INT_MAX; -static struct ctl_table inotify_table[] = { +static const struct ctl_table inotify_table[] = { { .procname = "max_user_instances", .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES], diff --git a/fs/nsfs.c b/fs/nsfs.c index c675fc40ce2d..663f8656158d 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -274,10 +274,7 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, if (usize < MNT_NS_INFO_SIZE_VER0) return -EINVAL; - if (previous) - mnt_ns = lookup_prev_mnt_ns(to_mnt_ns(ns)); - else - mnt_ns = lookup_next_mnt_ns(to_mnt_ns(ns)); + mnt_ns = get_sequential_mnt_ns(to_mnt_ns(ns), previous); if (IS_ERR(mnt_ns)) return PTR_ERR(mnt_ns); diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 8d789b017fa9..af94e3737470 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -787,7 +787,8 @@ pack_runs: if (err) goto out; - attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); + attr = mi_find_attr(ni, mi, NULL, type, name, name_len, + &le->id); if (!attr) { err = -EINVAL; goto bad_inode; @@ -1181,7 +1182,7 @@ repack: goto out; } - attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, &le->id); + attr = mi_find_attr(ni, mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; @@ -1406,7 +1407,7 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, */ if (!attr->non_res) { if (vbo[1] + bytes_per_off > le32_to_cpu(attr->res.data_size)) { - ntfs_inode_err(&ni->vfs_inode, "is corrupted"); + _ntfs_bad_inode(&ni->vfs_inode); return -EINVAL; } addr = resident_data(attr); @@ -1796,7 +1797,7 @@ repack: goto out; } - attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, + attr = mi_find_attr(ni, mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; @@ -2041,8 +2042,8 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) } /* Look for required attribute. */ - attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, - 0, &le->id); + attr = mi_find_attr(ni, mi, NULL, ATTR_DATA, + NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; @@ -2587,7 +2588,7 @@ int attr_force_nonresident(struct ntfs_inode *ni) attr = ni_find_attr(ni, NULL, &le, ATTR_DATA, NULL, 0, NULL, &mi); if (!attr) { - ntfs_bad_inode(&ni->vfs_inode, "no data attribute"); + _ntfs_bad_inode(&ni->vfs_inode); return -ENOENT; } diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index fc6a8aa29e3a..b6da80c69ca6 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -512,7 +512,7 @@ out: ctx->pos = pos; } else if (err < 0) { if (err == -EINVAL) - ntfs_inode_err(dir, "directory corrupted"); + _ntfs_bad_inode(dir); ctx->pos = eod; } diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 8b39d0ce5f28..5df6a0b5add9 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -75,7 +75,7 @@ struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni) { const struct ATTRIB *attr; - attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); + attr = mi_find_attr(ni, &ni->mi, NULL, ATTR_STD, NULL, 0, NULL); return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO)) : NULL; } @@ -89,7 +89,7 @@ struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni) { const struct ATTRIB *attr; - attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); + attr = mi_find_attr(ni, &ni->mi, NULL, ATTR_STD, NULL, 0, NULL); return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO5)) : NULL; @@ -148,8 +148,10 @@ int ni_load_mi_ex(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi) goto out; err = mi_get(ni->mi.sbi, rno, &r); - if (err) + if (err) { + _ntfs_bad_inode(&ni->vfs_inode); return err; + } ni_add_mi(ni, r); @@ -201,7 +203,8 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, *mi = &ni->mi; /* Look for required attribute in primary record. */ - return mi_find_attr(&ni->mi, attr, type, name, name_len, NULL); + return mi_find_attr(ni, &ni->mi, attr, type, name, name_len, + NULL); } /* First look for list entry of required type. */ @@ -217,7 +220,7 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, return NULL; /* Look for required attribute. */ - attr = mi_find_attr(m, NULL, type, name, name_len, &le->id); + attr = mi_find_attr(ni, m, NULL, type, name, name_len, &le->id); if (!attr) goto out; @@ -238,8 +241,7 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, return attr; out: - ntfs_inode_err(&ni->vfs_inode, "failed to parse mft record"); - ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(&ni->vfs_inode); return NULL; } @@ -259,7 +261,7 @@ struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr, if (mi) *mi = &ni->mi; /* Enum attributes in primary record. */ - return mi_enum_attr(&ni->mi, attr); + return mi_enum_attr(ni, &ni->mi, attr); } /* Get next list entry. */ @@ -275,7 +277,7 @@ struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr, *mi = mi2; /* Find attribute in loaded record. */ - return rec_find_attr_le(mi2, le2); + return rec_find_attr_le(ni, mi2, le2); } /* @@ -293,7 +295,8 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, if (!ni->attr_list.size) { if (pmi) *pmi = &ni->mi; - return mi_find_attr(&ni->mi, NULL, type, name, name_len, NULL); + return mi_find_attr(ni, &ni->mi, NULL, type, name, name_len, + NULL); } le = al_find_ex(ni, NULL, type, name, name_len, NULL); @@ -319,7 +322,7 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, if (pmi) *pmi = mi; - attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); + attr = mi_find_attr(ni, mi, NULL, type, name, name_len, &le->id); if (!attr) return NULL; @@ -330,6 +333,7 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, vcn <= le64_to_cpu(attr->nres.evcn)) return attr; + _ntfs_bad_inode(&ni->vfs_inode); return NULL; } @@ -398,7 +402,8 @@ int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, int diff; if (base_only || type == ATTR_LIST || !ni->attr_list.size) { - attr = mi_find_attr(&ni->mi, NULL, type, name, name_len, id); + attr = mi_find_attr(ni, &ni->mi, NULL, type, name, name_len, + id); if (!attr) return -ENOENT; @@ -437,7 +442,7 @@ next_le2: al_remove_le(ni, le); - attr = mi_find_attr(mi, NULL, type, name, name_len, id); + attr = mi_find_attr(ni, mi, NULL, type, name, name_len, id); if (!attr) return -ENOENT; @@ -485,7 +490,7 @@ ni_ins_new_attr(struct ntfs_inode *ni, struct mft_inode *mi, name = le->name; } - attr = mi_insert_attr(mi, type, name, name_len, asize, name_off); + attr = mi_insert_attr(ni, mi, type, name, name_len, asize, name_off); if (!attr) { if (le_added) al_remove_le(ni, le); @@ -673,7 +678,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) if (err) return err; - attr_list = mi_find_attr(&ni->mi, NULL, ATTR_LIST, NULL, 0, NULL); + attr_list = mi_find_attr(ni, &ni->mi, NULL, ATTR_LIST, NULL, 0, NULL); if (!attr_list) return 0; @@ -695,7 +700,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) if (!mi) return 0; - attr = mi_find_attr(mi, NULL, le->type, le_name(le), + attr = mi_find_attr(ni, mi, NULL, le->type, le_name(le), le->name_len, &le->id); if (!attr) return 0; @@ -731,7 +736,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) goto out; } - attr = mi_find_attr(mi, NULL, le->type, le_name(le), + attr = mi_find_attr(ni, mi, NULL, le->type, le_name(le), le->name_len, &le->id); if (!attr) { /* Should never happened, 'cause already checked. */ @@ -740,7 +745,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) asize = le32_to_cpu(attr->size); /* Insert into primary record. */ - attr_ins = mi_insert_attr(&ni->mi, le->type, le_name(le), + attr_ins = mi_insert_attr(ni, &ni->mi, le->type, le_name(le), le->name_len, asize, le16_to_cpu(attr->name_off)); if (!attr_ins) { @@ -768,7 +773,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) if (!mi) continue; - attr = mi_find_attr(mi, NULL, le->type, le_name(le), + attr = mi_find_attr(ni, mi, NULL, le->type, le_name(le), le->name_len, &le->id); if (!attr) continue; @@ -831,7 +836,7 @@ int ni_create_attr_list(struct ntfs_inode *ni) free_b = 0; attr = NULL; - for (; (attr = mi_enum_attr(&ni->mi, attr)); le = Add2Ptr(le, sz)) { + for (; (attr = mi_enum_attr(ni, &ni->mi, attr)); le = Add2Ptr(le, sz)) { sz = le_size(attr->name_len); le->type = attr->type; le->size = cpu_to_le16(sz); @@ -886,7 +891,7 @@ int ni_create_attr_list(struct ntfs_inode *ni) u32 asize = le32_to_cpu(b->size); u16 name_off = le16_to_cpu(b->name_off); - attr = mi_insert_attr(mi, b->type, Add2Ptr(b, name_off), + attr = mi_insert_attr(ni, mi, b->type, Add2Ptr(b, name_off), b->name_len, asize, name_off); if (!attr) goto out; @@ -909,7 +914,7 @@ int ni_create_attr_list(struct ntfs_inode *ni) goto out; } - attr = mi_insert_attr(&ni->mi, ATTR_LIST, NULL, 0, + attr = mi_insert_attr(ni, &ni->mi, ATTR_LIST, NULL, 0, lsize + SIZEOF_RESIDENT, SIZEOF_RESIDENT); if (!attr) goto out; @@ -993,13 +998,13 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, mi = rb_entry(node, struct mft_inode, node); if (is_mft_data && - (mi_enum_attr(mi, NULL) || + (mi_enum_attr(ni, mi, NULL) || vbo <= ((u64)mi->rno << sbi->record_bits))) { /* We can't accept this record 'cause MFT's bootstrapping. */ continue; } if (is_mft && - mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, NULL)) { + mi_find_attr(ni, mi, NULL, ATTR_DATA, NULL, 0, NULL)) { /* * This child record already has a ATTR_DATA. * So it can't accept any other records. @@ -1008,7 +1013,7 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, } if ((type != ATTR_NAME || name_len) && - mi_find_attr(mi, NULL, type, name, name_len, NULL)) { + mi_find_attr(ni, mi, NULL, type, name, name_len, NULL)) { /* Only indexed attributes can share same record. */ continue; } @@ -1157,7 +1162,7 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, /* Estimate the result of moving all possible attributes away. */ attr = NULL; - while ((attr = mi_enum_attr(&ni->mi, attr))) { + while ((attr = mi_enum_attr(ni, &ni->mi, attr))) { if (attr->type == ATTR_STD) continue; if (attr->type == ATTR_LIST) @@ -1175,7 +1180,7 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, attr = NULL; for (;;) { - attr = mi_enum_attr(&ni->mi, attr); + attr = mi_enum_attr(ni, &ni->mi, attr); if (!attr) { /* We should never be here 'cause we have already check this case. */ err = -EINVAL; @@ -1259,7 +1264,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) for (node = rb_first(&ni->mi_tree); node; node = rb_next(node)) { mi = rb_entry(node, struct mft_inode, node); - attr = mi_enum_attr(mi, NULL); + attr = mi_enum_attr(ni, mi, NULL); if (!attr) { mft_min = mi->rno; @@ -1280,7 +1285,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) ni_remove_mi(ni, mi_new); } - attr = mi_find_attr(&ni->mi, NULL, ATTR_DATA, NULL, 0, NULL); + attr = mi_find_attr(ni, &ni->mi, NULL, ATTR_DATA, NULL, 0, NULL); if (!attr) { err = -EINVAL; goto out; @@ -1397,7 +1402,7 @@ int ni_expand_list(struct ntfs_inode *ni) continue; /* Find attribute in primary record. */ - attr = rec_find_attr_le(&ni->mi, le); + attr = rec_find_attr_le(ni, &ni->mi, le); if (!attr) { err = -EINVAL; goto out; @@ -1604,8 +1609,8 @@ int ni_delete_all(struct ntfs_inode *ni) roff = le16_to_cpu(attr->nres.run_off); if (roff > asize) { - _ntfs_bad_inode(&ni->vfs_inode); - return -EINVAL; + /* ni_enum_attr_ex checks this case. */ + continue; } /* run==1 means unpack and deallocate. */ @@ -2726,9 +2731,10 @@ int ni_write_frame(struct ntfs_inode *ni, struct page **pages, { int err; struct ntfs_sb_info *sbi = ni->mi.sbi; + struct folio *folio = page_folio(pages[0]); u8 frame_bits = NTFS_LZNT_CUNIT + sbi->cluster_bits; u32 frame_size = sbi->cluster_size << NTFS_LZNT_CUNIT; - u64 frame_vbo = (u64)pages[0]->index << PAGE_SHIFT; + u64 frame_vbo = folio_pos(folio); CLST frame = frame_vbo >> frame_bits; char *frame_ondisk = NULL; struct page **pages_disk = NULL; @@ -3343,7 +3349,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) if (!mi->dirty) continue; - is_empty = !mi_enum_attr(mi, NULL); + is_empty = !mi_enum_attr(ni, mi, NULL); if (is_empty) clear_rec_inuse(mi->mrec); diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 03471bc9371c..938d351ebac7 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -908,7 +908,11 @@ void ntfs_bad_inode(struct inode *inode, const char *hint) ntfs_inode_err(inode, "%s", hint); make_bad_inode(inode); - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + /* Avoid recursion if bad inode is $Volume. */ + if (inode->i_ino != MFT_REC_VOL && + !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING)) { + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + } } /* diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 9089c58a005c..7eb9fae22f8d 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1094,8 +1094,7 @@ int indx_read(struct ntfs_index *indx, struct ntfs_inode *ni, CLST vbn, ok: if (!index_buf_check(ib, bytes, &vbn)) { - ntfs_inode_err(&ni->vfs_inode, "directory corrupted"); - ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(&ni->vfs_inode); err = -EINVAL; goto out; } @@ -1117,8 +1116,7 @@ ok: out: if (err == -E_NTFS_CORRUPT) { - ntfs_inode_err(&ni->vfs_inode, "directory corrupted"); - ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(&ni->vfs_inode); err = -EINVAL; } diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index be04d2845bb7..a1e11228dafd 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -410,6 +410,9 @@ end_enum: if (!std5) goto out; + if (is_bad_inode(inode)) + goto out; + if (!is_match && name) { err = -ENOENT; goto out; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index cd8e8374bb5a..382820464dee 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -745,23 +745,24 @@ int mi_get(struct ntfs_sb_info *sbi, CLST rno, struct mft_inode **mi); void mi_put(struct mft_inode *mi); int mi_init(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno); int mi_read(struct mft_inode *mi, bool is_mft); -struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr); -// TODO: id? -struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr, - enum ATTR_TYPE type, const __le16 *name, - u8 name_len, const __le16 *id); -static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec, +struct ATTRIB *mi_enum_attr(struct ntfs_inode *ni, struct mft_inode *mi, + struct ATTRIB *attr); +struct ATTRIB *mi_find_attr(struct ntfs_inode *ni, struct mft_inode *mi, + struct ATTRIB *attr, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, const __le16 *id); +static inline struct ATTRIB *rec_find_attr_le(struct ntfs_inode *ni, + struct mft_inode *rec, struct ATTR_LIST_ENTRY *le) { - return mi_find_attr(rec, NULL, le->type, le_name(le), le->name_len, + return mi_find_attr(ni, rec, NULL, le->type, le_name(le), le->name_len, &le->id); } int mi_write(struct mft_inode *mi, int wait); int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, __le16 flags, bool is_mft); -struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, - const __le16 *name, u8 name_len, u32 asize, - u16 name_off); +struct ATTRIB *mi_insert_attr(struct ntfs_inode *ni, struct mft_inode *mi, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, u32 asize, u16 name_off); bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi, struct ATTRIB *attr); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 61d53d39f3b9..714c7ecedca8 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -31,7 +31,7 @@ static inline int compare_attr(const struct ATTRIB *left, enum ATTR_TYPE type, * * Return: Unused attribute id that is less than mrec->next_attr_id. */ -static __le16 mi_new_attt_id(struct mft_inode *mi) +static __le16 mi_new_attt_id(struct ntfs_inode *ni, struct mft_inode *mi) { u16 free_id, max_id, t16; struct MFT_REC *rec = mi->mrec; @@ -52,7 +52,7 @@ static __le16 mi_new_attt_id(struct mft_inode *mi) attr = NULL; for (;;) { - attr = mi_enum_attr(mi, attr); + attr = mi_enum_attr(ni, mi, attr); if (!attr) { rec->next_attr_id = cpu_to_le16(max_id + 1); mi->dirty = true; @@ -195,7 +195,8 @@ out: * NOTE: mi->mrec - memory of size sbi->record_size * here we sure that mi->mrec->total == sbi->record_size (see mi_read) */ -struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) +struct ATTRIB *mi_enum_attr(struct ntfs_inode *ni, struct mft_inode *mi, + struct ATTRIB *attr) { const struct MFT_REC *rec = mi->mrec; u32 used = le32_to_cpu(rec->used); @@ -209,11 +210,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) off = le16_to_cpu(rec->attr_off); if (used > total) - return NULL; + goto out; if (off >= used || off < MFTRECORD_FIXUP_OFFSET_1 || !IS_ALIGNED(off, 8)) { - return NULL; + goto out; } /* Skip non-resident records. */ @@ -243,7 +244,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) */ if (off + 8 > used) { static_assert(ALIGN(sizeof(enum ATTR_TYPE), 8) == 8); - return NULL; + goto out; } if (attr->type == ATTR_END) { @@ -254,112 +255,116 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) /* 0x100 is last known attribute for now. */ t32 = le32_to_cpu(attr->type); if (!t32 || (t32 & 0xf) || (t32 > 0x100)) - return NULL; + goto out; /* attributes in record must be ordered by type */ if (t32 < prev_type) - return NULL; + goto out; asize = le32_to_cpu(attr->size); if (!IS_ALIGNED(asize, 8)) - return NULL; + goto out; /* Check overflow and boundary. */ if (off + asize < off || off + asize > used) - return NULL; + goto out; /* Can we use the field attr->non_res. */ if (off + 9 > used) - return NULL; + goto out; /* Check size of attribute. */ if (!attr->non_res) { /* Check resident fields. */ if (asize < SIZEOF_RESIDENT) - return NULL; + goto out; t16 = le16_to_cpu(attr->res.data_off); if (t16 > asize) - return NULL; + goto out; if (le32_to_cpu(attr->res.data_size) > asize - t16) - return NULL; + goto out; t32 = sizeof(short) * attr->name_len; if (t32 && le16_to_cpu(attr->name_off) + t32 > t16) - return NULL; + goto out; return attr; } /* Check nonresident fields. */ if (attr->non_res != 1) - return NULL; + goto out; /* Can we use memory including attr->nres.valid_size? */ if (asize < SIZEOF_NONRESIDENT) - return NULL; + goto out; t16 = le16_to_cpu(attr->nres.run_off); if (t16 > asize) - return NULL; + goto out; t32 = sizeof(short) * attr->name_len; if (t32 && le16_to_cpu(attr->name_off) + t32 > t16) - return NULL; + goto out; /* Check start/end vcn. */ if (le64_to_cpu(attr->nres.svcn) > le64_to_cpu(attr->nres.evcn) + 1) - return NULL; + goto out; data_size = le64_to_cpu(attr->nres.data_size); if (le64_to_cpu(attr->nres.valid_size) > data_size) - return NULL; + goto out; alloc_size = le64_to_cpu(attr->nres.alloc_size); if (data_size > alloc_size) - return NULL; + goto out; t32 = mi->sbi->cluster_mask; if (alloc_size & t32) - return NULL; + goto out; if (!attr->nres.svcn && is_attr_ext(attr)) { /* First segment of sparse/compressed attribute */ /* Can we use memory including attr->nres.total_size? */ if (asize < SIZEOF_NONRESIDENT_EX) - return NULL; + goto out; tot_size = le64_to_cpu(attr->nres.total_size); if (tot_size & t32) - return NULL; + goto out; if (tot_size > alloc_size) - return NULL; + goto out; } else { if (attr->nres.c_unit) - return NULL; + goto out; if (alloc_size > mi->sbi->volume.size) - return NULL; + goto out; } return attr; + +out: + _ntfs_bad_inode(&ni->vfs_inode); + return NULL; } /* * mi_find_attr - Find the attribute by type and name and id. */ -struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr, - enum ATTR_TYPE type, const __le16 *name, - u8 name_len, const __le16 *id) +struct ATTRIB *mi_find_attr(struct ntfs_inode *ni, struct mft_inode *mi, + struct ATTRIB *attr, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, const __le16 *id) { u32 type_in = le32_to_cpu(type); u32 atype; next_attr: - attr = mi_enum_attr(mi, attr); + attr = mi_enum_attr(ni, mi, attr); if (!attr) return NULL; @@ -467,9 +472,9 @@ int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, * * Return: Not full constructed attribute or NULL if not possible to create. */ -struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, - const __le16 *name, u8 name_len, u32 asize, - u16 name_off) +struct ATTRIB *mi_insert_attr(struct ntfs_inode *ni, struct mft_inode *mi, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, u32 asize, u16 name_off) { size_t tail; struct ATTRIB *attr; @@ -488,7 +493,7 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, * at which we should insert it. */ attr = NULL; - while ((attr = mi_enum_attr(mi, attr))) { + while ((attr = mi_enum_attr(ni, mi, attr))) { int diff = compare_attr(attr, type, name, name_len, upcase); if (diff < 0) @@ -508,7 +513,7 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, tail = used - PtrOffset(rec, attr); } - id = mi_new_attt_id(mi); + id = mi_new_attt_id(ni, mi); memmove(Add2Ptr(attr, asize), attr, tail); memset(attr, 0, asize); diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 395e23920632..4414743b638e 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -566,7 +566,7 @@ static void ocfs2_adjust_rightmost_records(handle_t *handle, struct ocfs2_path *path, struct ocfs2_extent_rec *insert_rec); /* - * Reset the actual path elements so that we can re-use the structure + * Reset the actual path elements so that we can reuse the structure * to build another path. Generally, this involves freeing the buffer * heads. */ @@ -1182,7 +1182,7 @@ static int ocfs2_add_branch(handle_t *handle, /* * If there is a gap before the root end and the real end - * of the righmost leaf block, we need to remove the gap + * of the rightmost leaf block, we need to remove the gap * between new_cpos and root_end first so that the tree * is consistent after we add a new branch(it will start * from new_cpos). @@ -1238,7 +1238,7 @@ static int ocfs2_add_branch(handle_t *handle, /* Note: new_eb_bhs[new_blocks - 1] is the guy which will be * linked with the rest of the tree. - * conversly, new_eb_bhs[0] is the new bottommost leaf. + * conversely, new_eb_bhs[0] is the new bottommost leaf. * * when we leave the loop, new_last_eb_blk will point to the * newest leaf, and next_blkno will point to the topmost extent @@ -3712,7 +3712,7 @@ static int ocfs2_try_to_merge_extent(handle_t *handle, * update split_index here. * * When the split_index is zero, we need to merge it to the - * prevoius extent block. It is more efficient and easier + * previous extent block. It is more efficient and easier * if we do merge_right first and merge_left later. */ ret = ocfs2_merge_rec_right(path, handle, et, split_rec, @@ -4517,7 +4517,7 @@ static void ocfs2_figure_contig_type(struct ocfs2_extent_tree *et, } /* - * This should only be called against the righmost leaf extent list. + * This should only be called against the rightmost leaf extent list. * * ocfs2_figure_appending_type() will figure out whether we'll have to * insert at the tail of the rightmost leaf. @@ -6154,6 +6154,9 @@ static int ocfs2_get_truncate_log_info(struct ocfs2_super *osb, int status; struct inode *inode = NULL; struct buffer_head *bh = NULL; + struct ocfs2_dinode *di; + struct ocfs2_truncate_log *tl; + unsigned int tl_count; inode = ocfs2_get_system_file_inode(osb, TRUNCATE_LOG_SYSTEM_INODE, @@ -6171,6 +6174,18 @@ static int ocfs2_get_truncate_log_info(struct ocfs2_super *osb, goto bail; } + di = (struct ocfs2_dinode *)bh->b_data; + tl = &di->id2.i_dealloc; + tl_count = le16_to_cpu(tl->tl_count); + if (unlikely(tl_count > ocfs2_truncate_recs_per_inode(osb->sb) || + tl_count == 0)) { + status = -EFSCORRUPTED; + iput(inode); + brelse(bh); + mlog_errno(status); + goto bail; + } + *tl_inode = inode; *tl_bh = bh; bail: @@ -6808,27 +6823,27 @@ static int ocfs2_zero_func(handle_t *handle, struct buffer_head *bh) return 0; } -void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle, - unsigned int from, unsigned int to, - struct page *page, int zero, u64 *phys) +void ocfs2_map_and_dirty_folio(struct inode *inode, handle_t *handle, + size_t from, size_t to, struct folio *folio, int zero, + u64 *phys) { int ret, partial = 0; - loff_t start_byte = ((loff_t)page->index << PAGE_SHIFT) + from; + loff_t start_byte = folio_pos(folio) + from; loff_t length = to - from; - ret = ocfs2_map_page_blocks(page, phys, inode, from, to, 0); + ret = ocfs2_map_folio_blocks(folio, phys, inode, from, to, 0); if (ret) mlog_errno(ret); if (zero) - zero_user_segment(page, from, to); + folio_zero_segment(folio, from, to); /* * Need to set the buffers we zero'd into uptodate * here if they aren't - ocfs2_map_page_blocks() * might've skipped some */ - ret = walk_page_buffers(handle, page_buffers(page), + ret = walk_page_buffers(handle, folio_buffers(folio), from, to, &partial, ocfs2_zero_func); if (ret < 0) @@ -6841,92 +6856,88 @@ void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle, } if (!partial) - SetPageUptodate(page); + folio_mark_uptodate(folio); - flush_dcache_page(page); + flush_dcache_folio(folio); } -static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start, - loff_t end, struct page **pages, - int numpages, u64 phys, handle_t *handle) +static void ocfs2_zero_cluster_folios(struct inode *inode, loff_t start, + loff_t end, struct folio **folios, int numfolios, + u64 phys, handle_t *handle) { int i; - struct page *page; - unsigned int from, to = PAGE_SIZE; struct super_block *sb = inode->i_sb; BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(sb))); - if (numpages == 0) + if (numfolios == 0) goto out; - to = PAGE_SIZE; - for(i = 0; i < numpages; i++) { - page = pages[i]; + for (i = 0; i < numfolios; i++) { + struct folio *folio = folios[i]; + size_t to = folio_size(folio); + size_t from = offset_in_folio(folio, start); - from = start & (PAGE_SIZE - 1); - if ((end >> PAGE_SHIFT) == page->index) - to = end & (PAGE_SIZE - 1); + if (to > end - folio_pos(folio)) + to = end - folio_pos(folio); - BUG_ON(from > PAGE_SIZE); - BUG_ON(to > PAGE_SIZE); + ocfs2_map_and_dirty_folio(inode, handle, from, to, folio, 1, + &phys); - ocfs2_map_and_dirty_page(inode, handle, from, to, page, 1, - &phys); - - start = (page->index + 1) << PAGE_SHIFT; + start = folio_next_index(folio) << PAGE_SHIFT; } out: - if (pages) - ocfs2_unlock_and_free_pages(pages, numpages); + if (folios) + ocfs2_unlock_and_free_folios(folios, numfolios); } -int ocfs2_grab_pages(struct inode *inode, loff_t start, loff_t end, - struct page **pages, int *num) +static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end, + struct folio **folios, int *num) { - int numpages, ret = 0; + int numfolios, ret = 0; struct address_space *mapping = inode->i_mapping; unsigned long index; loff_t last_page_bytes; BUG_ON(start > end); - numpages = 0; + numfolios = 0; last_page_bytes = PAGE_ALIGN(end); index = start >> PAGE_SHIFT; do { - pages[numpages] = find_or_create_page(mapping, index, GFP_NOFS); - if (!pages[numpages]) { - ret = -ENOMEM; + folios[numfolios] = __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); + if (IS_ERR(folios[numfolios])) { + ret = PTR_ERR(folios[numfolios]); mlog_errno(ret); goto out; } - numpages++; - index++; + index = folio_next_index(folios[numfolios]); + numfolios++; } while (index < (last_page_bytes >> PAGE_SHIFT)); out: if (ret != 0) { - if (pages) - ocfs2_unlock_and_free_pages(pages, numpages); - numpages = 0; + if (folios) + ocfs2_unlock_and_free_folios(folios, numfolios); + numfolios = 0; } - *num = numpages; + *num = numfolios; return ret; } -static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end, - struct page **pages, int *num) +static int ocfs2_grab_eof_folios(struct inode *inode, loff_t start, loff_t end, + struct folio **folios, int *num) { struct super_block *sb = inode->i_sb; BUG_ON(start >> OCFS2_SB(sb)->s_clustersize_bits != (end - 1) >> OCFS2_SB(sb)->s_clustersize_bits); - return ocfs2_grab_pages(inode, start, end, pages, num); + return ocfs2_grab_folios(inode, start, end, folios, num); } /* @@ -6940,8 +6951,8 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end, int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle, u64 range_start, u64 range_end) { - int ret = 0, numpages; - struct page **pages = NULL; + int ret = 0, numfolios; + struct folio **folios = NULL; u64 phys; unsigned int ext_flags; struct super_block *sb = inode->i_sb; @@ -6954,17 +6965,17 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle, return 0; /* - * Avoid zeroing pages fully beyond current i_size. It is pointless as - * underlying blocks of those pages should be already zeroed out and + * Avoid zeroing folios fully beyond current i_size. It is pointless as + * underlying blocks of those folios should be already zeroed out and * page writeback will skip them anyway. */ range_end = min_t(u64, range_end, i_size_read(inode)); if (range_start >= range_end) return 0; - pages = kcalloc(ocfs2_pages_per_cluster(sb), - sizeof(struct page *), GFP_NOFS); - if (pages == NULL) { + folios = kcalloc(ocfs2_pages_per_cluster(sb), + sizeof(struct folio *), GFP_NOFS); + if (folios == NULL) { ret = -ENOMEM; mlog_errno(ret); goto out; @@ -6985,18 +6996,18 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle, if (phys == 0 || ext_flags & OCFS2_EXT_UNWRITTEN) goto out; - ret = ocfs2_grab_eof_pages(inode, range_start, range_end, pages, - &numpages); + ret = ocfs2_grab_eof_folios(inode, range_start, range_end, folios, + &numfolios); if (ret) { mlog_errno(ret); goto out; } - ocfs2_zero_cluster_pages(inode, range_start, range_end, pages, - numpages, phys, handle); + ocfs2_zero_cluster_folios(inode, range_start, range_end, folios, + numfolios, phys, handle); /* - * Initiate writeout of the pages we zero'd here. We don't + * Initiate writeout of the folios we zero'd here. We don't * wait on them - the truncate_inode_pages() call later will * do that for us. */ @@ -7006,7 +7017,7 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle, mlog_errno(ret); out: - kfree(pages); + kfree(folios); return ret; } @@ -7059,7 +7070,7 @@ void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di) int ocfs2_convert_inline_data_to_extents(struct inode *inode, struct buffer_head *di_bh) { - int ret, has_data, num_pages = 0; + int ret, has_data, num_folios = 0; int need_free = 0; u32 bit_off, num; handle_t *handle; @@ -7068,7 +7079,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_alloc_context *data_ac = NULL; - struct page *page = NULL; + struct folio *folio = NULL; struct ocfs2_extent_tree et; int did_quota = 0; @@ -7119,12 +7130,12 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, /* * Save two copies, one for insert, and one that can - * be changed by ocfs2_map_and_dirty_page() below. + * be changed by ocfs2_map_and_dirty_folio() below. */ block = phys = ocfs2_clusters_to_blocks(inode->i_sb, bit_off); - ret = ocfs2_grab_eof_pages(inode, 0, page_end, &page, - &num_pages); + ret = ocfs2_grab_eof_folios(inode, 0, page_end, &folio, + &num_folios); if (ret) { mlog_errno(ret); need_free = 1; @@ -7135,15 +7146,15 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, * This should populate the 1st page for us and mark * it up to date. */ - ret = ocfs2_read_inline_data(inode, page, di_bh); + ret = ocfs2_read_inline_data(inode, folio, di_bh); if (ret) { mlog_errno(ret); need_free = 1; goto out_unlock; } - ocfs2_map_and_dirty_page(inode, handle, 0, page_end, page, 0, - &phys); + ocfs2_map_and_dirty_folio(inode, handle, 0, page_end, folio, 0, + &phys); } spin_lock(&oi->ip_lock); @@ -7174,8 +7185,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, } out_unlock: - if (page) - ocfs2_unlock_and_free_pages(&page, num_pages); + if (folio) + ocfs2_unlock_and_free_folios(&folio, num_folios); out_commit: if (ret < 0 && did_quota) diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h index 4af7abaa6e40..1c0c83362904 100644 --- a/fs/ocfs2/alloc.h +++ b/fs/ocfs2/alloc.h @@ -254,11 +254,9 @@ static inline int ocfs2_is_empty_extent(struct ocfs2_extent_rec *rec) return !rec->e_leaf_clusters; } -int ocfs2_grab_pages(struct inode *inode, loff_t start, loff_t end, - struct page **pages, int *num); -void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle, - unsigned int from, unsigned int to, - struct page *page, int zero, u64 *phys); +void ocfs2_map_and_dirty_folio(struct inode *inode, handle_t *handle, + size_t from, size_t to, struct folio *folio, int zero, + u64 *phys); /* * Structures which describe a path through a btree, and functions to * manipulate them. diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index db72b3e924b3..5bbeb6fbb1ac 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -215,10 +215,9 @@ bail: return err; } -int ocfs2_read_inline_data(struct inode *inode, struct page *page, +int ocfs2_read_inline_data(struct inode *inode, struct folio *folio, struct buffer_head *di_bh) { - void *kaddr; loff_t size; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; @@ -230,7 +229,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page, size = i_size_read(inode); - if (size > PAGE_SIZE || + if (size > folio_size(folio) || size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) { ocfs2_error(inode->i_sb, "Inode %llu has with inline data has bad size: %Lu\n", @@ -239,25 +238,18 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page, return -EROFS; } - kaddr = kmap_atomic(page); - if (size) - memcpy(kaddr, di->id2.i_data.id_data, size); - /* Clear the remaining part of the page */ - memset(kaddr + size, 0, PAGE_SIZE - size); - flush_dcache_page(page); - kunmap_atomic(kaddr); - - SetPageUptodate(page); + folio_fill_tail(folio, 0, di->id2.i_data.id_data, size); + folio_mark_uptodate(folio); return 0; } -static int ocfs2_readpage_inline(struct inode *inode, struct page *page) +static int ocfs2_readpage_inline(struct inode *inode, struct folio *folio) { int ret; struct buffer_head *di_bh = NULL; - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)); ret = ocfs2_read_inode_block(inode, &di_bh); @@ -266,9 +258,9 @@ static int ocfs2_readpage_inline(struct inode *inode, struct page *page) goto out; } - ret = ocfs2_read_inline_data(inode, page, di_bh); + ret = ocfs2_read_inline_data(inode, folio, di_bh); out: - unlock_page(page); + folio_unlock(folio); brelse(di_bh); return ret; @@ -283,7 +275,7 @@ static int ocfs2_read_folio(struct file *file, struct folio *folio) trace_ocfs2_readpage((unsigned long long)oi->ip_blkno, folio->index); - ret = ocfs2_inode_lock_with_page(inode, NULL, 0, &folio->page); + ret = ocfs2_inode_lock_with_folio(inode, NULL, 0, folio); if (ret != 0) { if (ret == AOP_TRUNCATED_PAGE) unlock = 0; @@ -305,7 +297,7 @@ static int ocfs2_read_folio(struct file *file, struct folio *folio) } /* - * i_size might have just been updated as we grabed the meta lock. We + * i_size might have just been updated as we grabbed the meta lock. We * might now be discovering a truncate that hit on another node. * block_read_full_folio->get_block freaks out if it is asked to read * beyond the end of a file, so we check here. Callers @@ -322,7 +314,7 @@ static int ocfs2_read_folio(struct file *file, struct folio *folio) } if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) - ret = ocfs2_readpage_inline(inode, &folio->page); + ret = ocfs2_readpage_inline(inode, folio); else ret = block_read_full_folio(folio, ocfs2_get_block); unlock = 0; @@ -534,7 +526,7 @@ static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb, * * from == to == 0 is code for "zero the entire cluster region" */ -static void ocfs2_clear_page_regions(struct page *page, +static void ocfs2_clear_folio_regions(struct folio *folio, struct ocfs2_super *osb, u32 cpos, unsigned from, unsigned to) { @@ -543,7 +535,7 @@ static void ocfs2_clear_page_regions(struct page *page, ocfs2_figure_cluster_boundaries(osb, cpos, &cluster_start, &cluster_end); - kaddr = kmap_atomic(page); + kaddr = kmap_local_folio(folio, 0); if (from || to) { if (from > cluster_start) @@ -554,13 +546,13 @@ static void ocfs2_clear_page_regions(struct page *page, memset(kaddr + cluster_start, 0, cluster_end - cluster_start); } - kunmap_atomic(kaddr); + kunmap_local(kaddr); } /* * Nonsparse file systems fully allocate before we get to the write * code. This prevents ocfs2_write() from tagging the write as an - * allocating one, which means ocfs2_map_page_blocks() might try to + * allocating one, which means ocfs2_map_folio_blocks() might try to * read-in the blocks at the tail of our file. Avoid reading them by * testing i_size against each block offset. */ @@ -585,11 +577,10 @@ static int ocfs2_should_read_blk(struct inode *inode, struct folio *folio, * * This will also skip zeroing, which is handled externally. */ -int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, +int ocfs2_map_folio_blocks(struct folio *folio, u64 *p_blkno, struct inode *inode, unsigned int from, unsigned int to, int new) { - struct folio *folio = page_folio(page); int ret = 0; struct buffer_head *head, *bh, *wait[2], **wait_bh = wait; unsigned int block_end, block_start; @@ -729,24 +720,24 @@ struct ocfs2_write_ctxt { unsigned int w_large_pages; /* - * Pages involved in this write. + * Folios involved in this write. * - * w_target_page is the page being written to by the user. + * w_target_folio is the folio being written to by the user. * - * w_pages is an array of pages which always contains - * w_target_page, and in the case of an allocating write with + * w_folios is an array of folios which always contains + * w_target_folio, and in the case of an allocating write with * page_size < cluster size, it will contain zero'd and mapped - * pages adjacent to w_target_page which need to be written + * pages adjacent to w_target_folio which need to be written * out in so that future reads from that region will get * zero's. */ - unsigned int w_num_pages; - struct page *w_pages[OCFS2_MAX_CTXT_PAGES]; - struct page *w_target_page; + unsigned int w_num_folios; + struct folio *w_folios[OCFS2_MAX_CTXT_PAGES]; + struct folio *w_target_folio; /* * w_target_locked is used for page_mkwrite path indicating no unlocking - * against w_target_page in ocfs2_write_end_nolock. + * against w_target_folio in ocfs2_write_end_nolock. */ unsigned int w_target_locked:1; @@ -771,40 +762,40 @@ struct ocfs2_write_ctxt { unsigned int w_unwritten_count; }; -void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) +void ocfs2_unlock_and_free_folios(struct folio **folios, int num_folios) { int i; - for(i = 0; i < num_pages; i++) { - if (pages[i]) { - unlock_page(pages[i]); - mark_page_accessed(pages[i]); - put_page(pages[i]); - } + for(i = 0; i < num_folios; i++) { + if (!folios[i]) + continue; + folio_unlock(folios[i]); + folio_mark_accessed(folios[i]); + folio_put(folios[i]); } } -static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc) +static void ocfs2_unlock_folios(struct ocfs2_write_ctxt *wc) { int i; /* * w_target_locked is only set to true in the page_mkwrite() case. * The intent is to allow us to lock the target page from write_begin() - * to write_end(). The caller must hold a ref on w_target_page. + * to write_end(). The caller must hold a ref on w_target_folio. */ if (wc->w_target_locked) { - BUG_ON(!wc->w_target_page); - for (i = 0; i < wc->w_num_pages; i++) { - if (wc->w_target_page == wc->w_pages[i]) { - wc->w_pages[i] = NULL; + BUG_ON(!wc->w_target_folio); + for (i = 0; i < wc->w_num_folios; i++) { + if (wc->w_target_folio == wc->w_folios[i]) { + wc->w_folios[i] = NULL; break; } } - mark_page_accessed(wc->w_target_page); - put_page(wc->w_target_page); + folio_mark_accessed(wc->w_target_folio); + folio_put(wc->w_target_folio); } - ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); + ocfs2_unlock_and_free_folios(wc->w_folios, wc->w_num_folios); } static void ocfs2_free_unwritten_list(struct inode *inode, @@ -826,7 +817,7 @@ static void ocfs2_free_write_ctxt(struct inode *inode, struct ocfs2_write_ctxt *wc) { ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list); - ocfs2_unlock_pages(wc); + ocfs2_unlock_folios(wc); brelse(wc->w_di_bh); kfree(wc); } @@ -869,29 +860,30 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp, * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ -static void ocfs2_zero_new_buffers(struct page *page, unsigned from, unsigned to) +static void ocfs2_zero_new_buffers(struct folio *folio, size_t from, size_t to) { unsigned int block_start, block_end; struct buffer_head *head, *bh; - BUG_ON(!PageLocked(page)); - if (!page_has_buffers(page)) + BUG_ON(!folio_test_locked(folio)); + head = folio_buffers(folio); + if (!head) return; - bh = head = page_buffers(page); + bh = head; block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { unsigned start, end; start = max(from, block_start); end = min(to, block_end); - zero_user_segment(page, start, end); + folio_zero_segment(folio, start, end); set_buffer_uptodate(bh); } @@ -916,29 +908,26 @@ static void ocfs2_write_failure(struct inode *inode, int i; unsigned from = user_pos & (PAGE_SIZE - 1), to = user_pos + user_len; - struct page *tmppage; - if (wc->w_target_page) - ocfs2_zero_new_buffers(wc->w_target_page, from, to); + if (wc->w_target_folio) + ocfs2_zero_new_buffers(wc->w_target_folio, from, to); - for(i = 0; i < wc->w_num_pages; i++) { - tmppage = wc->w_pages[i]; + for (i = 0; i < wc->w_num_folios; i++) { + struct folio *folio = wc->w_folios[i]; - if (tmppage && page_has_buffers(tmppage)) { + if (folio && folio_buffers(folio)) { if (ocfs2_should_order_data(inode)) ocfs2_jbd2_inode_add_write(wc->w_handle, inode, user_pos, user_len); - block_commit_write(tmppage, from, to); + block_commit_write(&folio->page, from, to); } } } -static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno, - struct ocfs2_write_ctxt *wc, - struct page *page, u32 cpos, - loff_t user_pos, unsigned user_len, - int new) +static int ocfs2_prepare_folio_for_write(struct inode *inode, u64 *p_blkno, + struct ocfs2_write_ctxt *wc, struct folio *folio, u32 cpos, + loff_t user_pos, unsigned user_len, int new) { int ret; unsigned int map_from = 0, map_to = 0; @@ -951,20 +940,19 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno, /* treat the write as new if the a hole/lseek spanned across * the page boundary. */ - new = new | ((i_size_read(inode) <= page_offset(page)) && - (page_offset(page) <= user_pos)); + new = new | ((i_size_read(inode) <= folio_pos(folio)) && + (folio_pos(folio) <= user_pos)); - if (page == wc->w_target_page) { + if (folio == wc->w_target_folio) { map_from = user_pos & (PAGE_SIZE - 1); map_to = map_from + user_len; if (new) - ret = ocfs2_map_page_blocks(page, p_blkno, inode, - cluster_start, cluster_end, - new); + ret = ocfs2_map_folio_blocks(folio, p_blkno, inode, + cluster_start, cluster_end, new); else - ret = ocfs2_map_page_blocks(page, p_blkno, inode, - map_from, map_to, new); + ret = ocfs2_map_folio_blocks(folio, p_blkno, inode, + map_from, map_to, new); if (ret) { mlog_errno(ret); goto out; @@ -978,7 +966,7 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno, } } else { /* - * If we haven't allocated the new page yet, we + * If we haven't allocated the new folio yet, we * shouldn't be writing it out without copying user * data. This is likely a math error from the caller. */ @@ -987,8 +975,8 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno, map_from = cluster_start; map_to = cluster_end; - ret = ocfs2_map_page_blocks(page, p_blkno, inode, - cluster_start, cluster_end, new); + ret = ocfs2_map_folio_blocks(folio, p_blkno, inode, + cluster_start, cluster_end, new); if (ret) { mlog_errno(ret); goto out; @@ -996,20 +984,20 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno, } /* - * Parts of newly allocated pages need to be zero'd. + * Parts of newly allocated folios need to be zero'd. * * Above, we have also rewritten 'to' and 'from' - as far as * the rest of the function is concerned, the entire cluster - * range inside of a page needs to be written. + * range inside of a folio needs to be written. * - * We can skip this if the page is up to date - it's already + * We can skip this if the folio is uptodate - it's already * been zero'd from being read in as a hole. */ - if (new && !PageUptodate(page)) - ocfs2_clear_page_regions(page, OCFS2_SB(inode->i_sb), + if (new && !folio_test_uptodate(folio)) + ocfs2_clear_folio_regions(folio, OCFS2_SB(inode->i_sb), cpos, user_data_from, user_data_to); - flush_dcache_page(page); + flush_dcache_folio(folio); out: return ret; @@ -1018,11 +1006,9 @@ out: /* * This function will only grab one clusters worth of pages. */ -static int ocfs2_grab_pages_for_write(struct address_space *mapping, - struct ocfs2_write_ctxt *wc, - u32 cpos, loff_t user_pos, - unsigned user_len, int new, - struct page *mmap_page) +static int ocfs2_grab_folios_for_write(struct address_space *mapping, + struct ocfs2_write_ctxt *wc, u32 cpos, loff_t user_pos, + unsigned user_len, int new, struct folio *mmap_folio) { int ret = 0, i; unsigned long start, target_index, end_index, index; @@ -1039,7 +1025,7 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, * last page of the write. */ if (new) { - wc->w_num_pages = ocfs2_pages_per_cluster(inode->i_sb); + wc->w_num_folios = ocfs2_pages_per_cluster(inode->i_sb); start = ocfs2_align_clusters_to_page_index(inode->i_sb, cpos); /* * We need the index *past* the last page we could possibly @@ -1049,15 +1035,15 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, last_byte = max(user_pos + user_len, i_size_read(inode)); BUG_ON(last_byte < 1); end_index = ((last_byte - 1) >> PAGE_SHIFT) + 1; - if ((start + wc->w_num_pages) > end_index) - wc->w_num_pages = end_index - start; + if ((start + wc->w_num_folios) > end_index) + wc->w_num_folios = end_index - start; } else { - wc->w_num_pages = 1; + wc->w_num_folios = 1; start = target_index; } end_index = (user_pos + user_len - 1) >> PAGE_SHIFT; - for(i = 0; i < wc->w_num_pages; i++) { + for(i = 0; i < wc->w_num_folios; i++) { index = start + i; if (index >= target_index && index <= end_index && @@ -1067,37 +1053,38 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, * and wants us to directly use the page * passed in. */ - lock_page(mmap_page); + folio_lock(mmap_folio); /* Exit and let the caller retry */ - if (mmap_page->mapping != mapping) { - WARN_ON(mmap_page->mapping); - unlock_page(mmap_page); + if (mmap_folio->mapping != mapping) { + WARN_ON(mmap_folio->mapping); + folio_unlock(mmap_folio); ret = -EAGAIN; goto out; } - get_page(mmap_page); - wc->w_pages[i] = mmap_page; + folio_get(mmap_folio); + wc->w_folios[i] = mmap_folio; wc->w_target_locked = true; } else if (index >= target_index && index <= end_index && wc->w_type == OCFS2_WRITE_DIRECT) { /* Direct write has no mapping page. */ - wc->w_pages[i] = NULL; + wc->w_folios[i] = NULL; continue; } else { - wc->w_pages[i] = find_or_create_page(mapping, index, - GFP_NOFS); - if (!wc->w_pages[i]) { - ret = -ENOMEM; + wc->w_folios[i] = __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + GFP_NOFS); + if (IS_ERR(wc->w_folios[i])) { + ret = PTR_ERR(wc->w_folios[i]); mlog_errno(ret); goto out; } } - wait_for_stable_page(wc->w_pages[i]); + folio_wait_stable(wc->w_folios[i]); if (index == target_index) - wc->w_target_page = wc->w_pages[i]; + wc->w_target_folio = wc->w_folios[i]; } out: if (ret) @@ -1181,19 +1168,18 @@ static int ocfs2_write_cluster(struct address_space *mapping, if (!should_zero) p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1); - for(i = 0; i < wc->w_num_pages; i++) { + for (i = 0; i < wc->w_num_folios; i++) { int tmpret; /* This is the direct io target page. */ - if (wc->w_pages[i] == NULL) { + if (wc->w_folios[i] == NULL) { p_blkno += (1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits)); continue; } - tmpret = ocfs2_prepare_page_for_write(inode, &p_blkno, wc, - wc->w_pages[i], cpos, - user_pos, user_len, - should_zero); + tmpret = ocfs2_prepare_folio_for_write(inode, &p_blkno, wc, + wc->w_folios[i], cpos, user_pos, user_len, + should_zero); if (tmpret) { mlog_errno(tmpret); if (ret == 0) @@ -1472,7 +1458,7 @@ static int ocfs2_write_begin_inline(struct address_space *mapping, { int ret; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - struct page *page; + struct folio *folio; handle_t *handle; struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; @@ -1483,19 +1469,21 @@ static int ocfs2_write_begin_inline(struct address_space *mapping, goto out; } - page = find_or_create_page(mapping, 0, GFP_NOFS); - if (!page) { + folio = __filemap_get_folio(mapping, 0, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); + if (IS_ERR(folio)) { ocfs2_commit_trans(osb, handle); - ret = -ENOMEM; + ret = PTR_ERR(folio); mlog_errno(ret); goto out; } /* - * If we don't set w_num_pages then this page won't get unlocked + * If we don't set w_num_folios then this folio won't get unlocked * and freed on cleanup of the write context. */ - wc->w_pages[0] = wc->w_target_page = page; - wc->w_num_pages = 1; + wc->w_target_folio = folio; + wc->w_folios[0] = folio; + wc->w_num_folios = 1; ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE); @@ -1509,8 +1497,8 @@ static int ocfs2_write_begin_inline(struct address_space *mapping, if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) ocfs2_set_inode_data_inline(inode, di); - if (!PageUptodate(page)) { - ret = ocfs2_read_inline_data(inode, page, wc->w_di_bh); + if (!folio_test_uptodate(folio)) { + ret = ocfs2_read_inline_data(inode, folio, wc->w_di_bh); if (ret) { ocfs2_commit_trans(osb, handle); @@ -1533,9 +1521,8 @@ int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size) } static int ocfs2_try_to_write_inline_data(struct address_space *mapping, - struct inode *inode, loff_t pos, - unsigned len, struct page *mmap_page, - struct ocfs2_write_ctxt *wc) + struct inode *inode, loff_t pos, size_t len, + struct folio *mmap_folio, struct ocfs2_write_ctxt *wc) { int ret, written = 0; loff_t end = pos + len; @@ -1550,7 +1537,7 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping, * Handle inodes which already have inline data 1st. */ if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) { - if (mmap_page == NULL && + if (mmap_folio == NULL && ocfs2_size_fits_inline_data(wc->w_di_bh, end)) goto do_inline_write; @@ -1574,7 +1561,7 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping, * Check whether the write can fit. */ di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; - if (mmap_page || + if (mmap_folio || end > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) return 0; @@ -1641,9 +1628,9 @@ static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh, } int ocfs2_write_begin_nolock(struct address_space *mapping, - loff_t pos, unsigned len, ocfs2_write_type_t type, - struct folio **foliop, void **fsdata, - struct buffer_head *di_bh, struct page *mmap_page) + loff_t pos, unsigned len, ocfs2_write_type_t type, + struct folio **foliop, void **fsdata, + struct buffer_head *di_bh, struct folio *mmap_folio) { int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS; unsigned int clusters_to_alloc, extents_to_split, clusters_need = 0; @@ -1666,7 +1653,7 @@ try_again: if (ocfs2_supports_inline_data(osb)) { ret = ocfs2_try_to_write_inline_data(mapping, inode, pos, len, - mmap_page, wc); + mmap_folio, wc); if (ret == 1) { ret = 0; goto success; @@ -1718,7 +1705,7 @@ try_again: (unsigned long long)OCFS2_I(inode)->ip_blkno, (long long)i_size_read(inode), le32_to_cpu(di->i_clusters), - pos, len, type, mmap_page, + pos, len, type, mmap_folio, clusters_to_alloc, extents_to_split); /* @@ -1789,21 +1776,21 @@ try_again: } /* - * Fill our page array first. That way we've grabbed enough so + * Fill our folio array first. That way we've grabbed enough so * that we can zero and flush if we error after adding the * extent. */ - ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len, - cluster_of_pages, mmap_page); + ret = ocfs2_grab_folios_for_write(mapping, wc, wc->w_cpos, pos, len, + cluster_of_pages, mmap_folio); if (ret) { /* - * ocfs2_grab_pages_for_write() returns -EAGAIN if it could not lock - * the target page. In this case, we exit with no error and no target - * page. This will trigger the caller, page_mkwrite(), to re-try - * the operation. + * ocfs2_grab_folios_for_write() returns -EAGAIN if it + * could not lock the target folio. In this case, we exit + * with no error and no target folio. This will trigger + * the caller, page_mkwrite(), to re-try the operation. */ if (type == OCFS2_WRITE_MMAP && ret == -EAGAIN) { - BUG_ON(wc->w_target_page); + BUG_ON(wc->w_target_folio); ret = 0; goto out_quota; } @@ -1826,7 +1813,7 @@ try_again: success: if (foliop) - *foliop = page_folio(wc->w_target_page); + *foliop = wc->w_target_folio; *fsdata = wc; return 0; out_quota: @@ -1845,7 +1832,7 @@ out: * to VM code. */ if (wc->w_target_locked) - unlock_page(mmap_page); + folio_unlock(mmap_folio); ocfs2_free_write_ctxt(inode, wc); @@ -1924,18 +1911,15 @@ static void ocfs2_write_end_inline(struct inode *inode, loff_t pos, struct ocfs2_dinode *di, struct ocfs2_write_ctxt *wc) { - void *kaddr; - if (unlikely(*copied < len)) { - if (!PageUptodate(wc->w_target_page)) { + if (!folio_test_uptodate(wc->w_target_folio)) { *copied = 0; return; } } - kaddr = kmap_atomic(wc->w_target_page); - memcpy(di->id2.i_data.id_data + pos, kaddr + pos, *copied); - kunmap_atomic(kaddr); + memcpy_from_folio(di->id2.i_data.id_data + pos, wc->w_target_folio, + pos, *copied); trace_ocfs2_write_end_inline( (unsigned long long)OCFS2_I(inode)->ip_blkno, @@ -1944,17 +1928,16 @@ static void ocfs2_write_end_inline(struct inode *inode, loff_t pos, le16_to_cpu(di->i_dyn_features)); } -int ocfs2_write_end_nolock(struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, void *fsdata) +int ocfs2_write_end_nolock(struct address_space *mapping, loff_t pos, + unsigned len, unsigned copied, void *fsdata) { int i, ret; - unsigned from, to, start = pos & (PAGE_SIZE - 1); + size_t from, to, start = pos & (PAGE_SIZE - 1); struct inode *inode = mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_write_ctxt *wc = fsdata; struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; handle_t *handle = wc->w_handle; - struct page *tmppage; BUG_ON(!list_empty(&wc->w_unwritten_list)); @@ -1973,44 +1956,44 @@ int ocfs2_write_end_nolock(struct address_space *mapping, goto out_write_size; } - if (unlikely(copied < len) && wc->w_target_page) { + if (unlikely(copied < len) && wc->w_target_folio) { loff_t new_isize; - if (!PageUptodate(wc->w_target_page)) + if (!folio_test_uptodate(wc->w_target_folio)) copied = 0; new_isize = max_t(loff_t, i_size_read(inode), pos + copied); - if (new_isize > page_offset(wc->w_target_page)) - ocfs2_zero_new_buffers(wc->w_target_page, start+copied, + if (new_isize > folio_pos(wc->w_target_folio)) + ocfs2_zero_new_buffers(wc->w_target_folio, start+copied, start+len); else { /* - * When page is fully beyond new isize (data copy - * failed), do not bother zeroing the page. Invalidate + * When folio is fully beyond new isize (data copy + * failed), do not bother zeroing the folio. Invalidate * it instead so that writeback does not get confused * put page & buffer dirty bits into inconsistent * state. */ - block_invalidate_folio(page_folio(wc->w_target_page), - 0, PAGE_SIZE); + block_invalidate_folio(wc->w_target_folio, 0, + folio_size(wc->w_target_folio)); } } - if (wc->w_target_page) - flush_dcache_page(wc->w_target_page); + if (wc->w_target_folio) + flush_dcache_folio(wc->w_target_folio); - for(i = 0; i < wc->w_num_pages; i++) { - tmppage = wc->w_pages[i]; + for (i = 0; i < wc->w_num_folios; i++) { + struct folio *folio = wc->w_folios[i]; - /* This is the direct io target page. */ - if (tmppage == NULL) + /* This is the direct io target folio */ + if (folio == NULL) continue; - if (tmppage == wc->w_target_page) { + if (folio == wc->w_target_folio) { from = wc->w_target_from; to = wc->w_target_to; - BUG_ON(from > PAGE_SIZE || - to > PAGE_SIZE || + BUG_ON(from > folio_size(folio) || + to > folio_size(folio) || to < from); } else { /* @@ -2019,19 +2002,17 @@ int ocfs2_write_end_nolock(struct address_space *mapping, * to flush their entire range. */ from = 0; - to = PAGE_SIZE; + to = folio_size(folio); } - if (page_has_buffers(tmppage)) { + if (folio_buffers(folio)) { if (handle && ocfs2_should_order_data(inode)) { - loff_t start_byte = - ((loff_t)tmppage->index << PAGE_SHIFT) + - from; + loff_t start_byte = folio_pos(folio) + from; loff_t length = to - from; ocfs2_jbd2_inode_add_write(handle, inode, start_byte, length); } - block_commit_write(tmppage, from, to); + block_commit_write(&folio->page, from, to); } } @@ -2060,7 +2041,7 @@ out: * this lock and will ask for the page lock when flushing the data. * put it here to preserve the unlock order. */ - ocfs2_unlock_pages(wc); + ocfs2_unlock_folios(wc); if (handle) ocfs2_commit_trans(osb, handle); diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 1d1b4b7edba0..114efc9111e4 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -8,16 +8,11 @@ #include -handle_t *ocfs2_start_walk_page_trans(struct inode *inode, - struct page *page, - unsigned from, - unsigned to); - -int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, +int ocfs2_map_folio_blocks(struct folio *folio, u64 *p_blkno, struct inode *inode, unsigned int from, unsigned int to, int new); -void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages); +void ocfs2_unlock_and_free_folios(struct folio **folios, int num_folios); int walk_page_buffers( handle_t *handle, struct buffer_head *head, @@ -37,11 +32,11 @@ typedef enum { } ocfs2_write_type_t; int ocfs2_write_begin_nolock(struct address_space *mapping, - loff_t pos, unsigned len, ocfs2_write_type_t type, - struct folio **foliop, void **fsdata, - struct buffer_head *di_bh, struct page *mmap_page); + loff_t pos, unsigned len, ocfs2_write_type_t type, + struct folio **foliop, void **fsdata, + struct buffer_head *di_bh, struct folio *mmap_folio); -int ocfs2_read_inline_data(struct inode *inode, struct page *page, +int ocfs2_read_inline_data(struct inode *inode, struct folio *folio, struct buffer_head *di_bh); int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size); diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 4200a0341343..724350925aff 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -3,6 +3,7 @@ * Copyright (C) 2004, 2005 Oracle. All rights reserved. */ +#include "linux/kstrtox.h" #include #include #include @@ -1020,7 +1021,7 @@ fire_callbacks: if (list_empty(&slot->ds_live_item)) goto out; - /* live nodes only go dead after enough consequtive missed + /* live nodes only go dead after enough consecutive missed * samples.. reset the missed counter whenever we see * activity */ if (slot->ds_equal_samples >= o2hb_dead_threshold || gen_changed) { @@ -1535,10 +1536,11 @@ static int o2hb_read_block_input(struct o2hb_region *reg, { unsigned long bytes; char *p = (char *)page; + int ret; - bytes = simple_strtoul(p, &p, 0); - if (!p || (*p && (*p != '\n'))) - return -EINVAL; + ret = kstrtoul(p, 0, &bytes); + if (ret) + return ret; /* Heartbeat and fs min / max block sizes are the same. */ if (bytes > 4096 || bytes < 512) @@ -1622,13 +1624,14 @@ static ssize_t o2hb_region_blocks_store(struct config_item *item, struct o2hb_region *reg = to_o2hb_region(item); unsigned long tmp; char *p = (char *)page; + int ret; if (reg->hr_bdev_file) return -EINVAL; - tmp = simple_strtoul(p, &p, 0); - if (!p || (*p && (*p != '\n'))) - return -EINVAL; + ret = kstrtoul(p, 0, &tmp); + if (ret) + return ret; if (tmp > O2NM_MAX_NODES || tmp == 0) return -ERANGE; @@ -1776,8 +1779,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, if (o2nm_this_node() == O2NM_MAX_NODES) return -EINVAL; - fd = simple_strtol(p, &p, 0); - if (!p || (*p && (*p != '\n'))) + ret = kstrtol(p, 0, &fd); + if (ret < 0) return -EINVAL; if (fd < 0 || fd >= INT_MAX) @@ -2136,10 +2139,11 @@ static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *ite { unsigned long tmp; char *p = (char *)page; + int ret; - tmp = simple_strtoul(p, &p, 10); - if (!p || (*p && (*p != '\n'))) - return -EINVAL; + ret = kstrtoul(p, 10, &tmp); + if (ret) + return ret; /* this will validate ranges for us. */ o2hb_dead_threshold_set((unsigned int) tmp); diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h index b73fc42e46ff..630bd5a3dd0d 100644 --- a/fs/ocfs2/cluster/masklog.h +++ b/fs/ocfs2/cluster/masklog.h @@ -29,7 +29,7 @@ * just calling printk() so that this can eventually make its way through * relayfs along with the debugging messages. Everything else gets KERN_DEBUG. * The inline tests and macro dance give GCC the opportunity to quite cleverly - * only emit the appropriage printk() when the caller passes in a constant + * only emit the appropriate printk() when the caller passes in a constant * mask, as is almost always the case. * * All this bitmask nonsense is managed from the files under diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c index 8bf17231d7b7..bfb8b456876c 100644 --- a/fs/ocfs2/cluster/quorum.c +++ b/fs/ocfs2/cluster/quorum.c @@ -23,7 +23,7 @@ * race between when we see a node start heartbeating and when we connect * to it. * - * So nodes that are in this transtion put a hold on the quorum decision + * So nodes that are in this transition put a hold on the quorum decision * with a counter. As they fall out of this transition they drop the count * and if they're the last, they fire off the decision. */ @@ -189,7 +189,7 @@ static void o2quo_clear_hold(struct o2quo_state *qs, u8 node) } /* as a node comes up we delay the quorum decision until we know the fate of - * the connection. the hold will be droped in conn_up or hb_down. it might be + * the connection. the hold will be dropped in conn_up or hb_down. it might be * perpetuated by con_err until hb_down. if we already have a conn, we might * be dropping a hold that conn_up got. */ void o2quo_hb_up(u8 node) @@ -256,7 +256,7 @@ void o2quo_hb_still_up(u8 node) } /* This is analogous to hb_up. as a node's connection comes up we delay the - * quorum decision until we see it heartbeating. the hold will be droped in + * quorum decision until we see it heartbeating. the hold will be dropped in * hb_up or hb_down. it might be perpetuated by con_err until hb_down. if * it's already heartbeating we might be dropping a hold that conn_up got. * */ diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 2b8fa3e782fb..0f46b22561d6 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -5,13 +5,13 @@ * * ---- * - * Callers for this were originally written against a very simple synchronus + * Callers for this were originally written against a very simple synchronous * API. This implementation reflects those simple callers. Some day I'm sure * we'll need to move to a more robust posting/callback mechanism. * * Transmit calls pass in kernel virtual addresses and block copying this into * the socket's tx buffers via a usual blocking sendmsg. They'll block waiting - * for a failed socket to timeout. TX callers can also pass in a poniter to an + * for a failed socket to timeout. TX callers can also pass in a pointer to an * 'int' which gets filled with an errno off the wire in response to the * message they send. * @@ -101,7 +101,7 @@ static struct socket *o2net_listen_sock; * o2net_wq. teardown detaches the callbacks before destroying the workqueue. * quorum work is queued as sock containers are shutdown.. stop_listening * tears down all the node's sock containers, preventing future shutdowns - * and queued quroum work, before canceling delayed quorum work and + * and queued quorum work, before canceling delayed quorum work and * destroying the work queue. */ static struct workqueue_struct *o2net_wq; @@ -1419,7 +1419,7 @@ out: return ret; } -/* this work func is triggerd by data ready. it reads until it can read no +/* this work func is triggered by data ready. it reads until it can read no * more. it interprets 0, eof, as fatal. if data_ready hits while we're doing * our work the work struct will be marked and we'll be called again. */ static void o2net_rx_until_empty(struct work_struct *work) diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index a9b8688aaf30..1873bbbb7e5b 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -32,7 +32,8 @@ void ocfs2_dentry_attach_gen(struct dentry *dentry) } -static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) +static int ocfs2_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; int ret = 0; /* if all else fails, just return false */ @@ -44,8 +45,7 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) inode = d_inode(dentry); osb = OCFS2_SB(dentry->d_sb); - trace_ocfs2_dentry_revalidate(dentry, dentry->d_name.len, - dentry->d_name.name); + trace_ocfs2_dentry_revalidate(dentry, name->len, name->name); /* For a negative dentry - * check the generation number of the parent and compare with the @@ -53,12 +53,8 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) */ if (inode == NULL) { unsigned long gen = (unsigned long) dentry->d_fsdata; - unsigned long pgen; - spin_lock(&dentry->d_lock); - pgen = OCFS2_I(d_inode(dentry->d_parent))->ip_dir_lock_gen; - spin_unlock(&dentry->d_lock); - trace_ocfs2_dentry_revalidate_negative(dentry->d_name.len, - dentry->d_name.name, + unsigned long pgen = OCFS2_I(dir)->ip_dir_lock_gen; + trace_ocfs2_dentry_revalidate_negative(name->len, name->name, pgen, gen); if (gen != pgen) goto bail; diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 213206ebdd58..7799f4d16ce9 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1065,26 +1065,39 @@ int ocfs2_find_entry(const char *name, int namelen, { struct buffer_head *bh; struct ocfs2_dir_entry *res_dir = NULL; + int ret = 0; if (ocfs2_dir_indexed(dir)) return ocfs2_find_entry_dx(name, namelen, dir, lookup); + if (unlikely(i_size_read(dir) <= 0)) { + ret = -EFSCORRUPTED; + mlog_errno(ret); + goto out; + } /* * The unindexed dir code only uses part of the lookup * structure, so there's no reason to push it down further * than this. */ - if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + if (unlikely(i_size_read(dir) > dir->i_sb->s_blocksize)) { + ret = -EFSCORRUPTED; + mlog_errno(ret); + goto out; + } bh = ocfs2_find_entry_id(name, namelen, dir, &res_dir); - else + } else { bh = ocfs2_find_entry_el(name, namelen, dir, &res_dir); + } if (bh == NULL) return -ENOENT; lookup->dl_leaf_bh = bh; lookup->dl_entry = res_dir; - return 0; +out: + return ret; } /* @@ -2010,6 +2023,7 @@ int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name, * * Return 0 if the name does not exist * Return -EEXIST if the directory contains the name + * Return -EFSCORRUPTED if found corruption * * Callers should have i_rwsem + a cluster lock on dir */ @@ -2023,9 +2037,12 @@ int ocfs2_check_dir_for_entry(struct inode *dir, trace_ocfs2_check_dir_for_entry( (unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name); - if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0) { + ret = ocfs2_find_entry(name, namelen, dir, &lookup); + if (ret == 0) { ret = -EEXIST; mlog_errno(ret); + } else if (ret == -ENOENT) { + ret = 0; } ocfs2_free_dir_lookup_result(&lookup); diff --git a/fs/ocfs2/dlm/dlmapi.h b/fs/ocfs2/dlm/dlmapi.h index 847a52dcbe7d..1969db8ffa9c 100644 --- a/fs/ocfs2/dlm/dlmapi.h +++ b/fs/ocfs2/dlm/dlmapi.h @@ -118,7 +118,7 @@ struct dlm_lockstatus { #define LKM_VALBLK 0x00000100 /* lock value block request */ #define LKM_NOQUEUE 0x00000200 /* non blocking request */ #define LKM_CONVERT 0x00000400 /* conversion request */ -#define LKM_NODLCKWT 0x00000800 /* this lock wont deadlock (U) */ +#define LKM_NODLCKWT 0x00000800 /* this lock won't deadlock (U) */ #define LKM_UNLOCK 0x00001000 /* deallocate this lock */ #define LKM_CANCEL 0x00002000 /* cancel conversion request */ #define LKM_DEQALL 0x00004000 /* remove all locks held by proc (U) */ diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index e9ef4e2b0e75..fe4fdd09bae3 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "../cluster/heartbeat.h" #include "../cluster/nodemanager.h" @@ -90,12 +91,12 @@ void __dlm_print_one_lock_resource(struct dlm_lock_resource *res) buf, res->owner, res->state); printk(" last used: %lu, refcnt: %u, on purge list: %s\n", res->last_used, kref_read(&res->refs), - list_empty(&res->purge) ? "no" : "yes"); + str_no_yes(list_empty(&res->purge))); printk(" on dirty list: %s, on reco list: %s, " "migrating pending: %s\n", - list_empty(&res->dirty) ? "no" : "yes", - list_empty(&res->recovering) ? "no" : "yes", - res->migration_pending ? "yes" : "no"); + str_no_yes(list_empty(&res->dirty)), + str_no_yes(list_empty(&res->recovering)), + str_yes_no(res->migration_pending)); printk(" inflight locks: %d, asts reserved: %d\n", res->inflight_locks, atomic_read(&res->asts_reserved)); dlm_print_lockres_refmap(res); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index d610da8e2f24..86bb1a03bcc1 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -21,7 +21,7 @@ #include #include #include - +#include #include "../cluster/heartbeat.h" #include "../cluster/nodemanager.h" @@ -2859,7 +2859,7 @@ static int dlm_mark_lockres_migrating(struct dlm_ctxt *dlm, dlm_lockres_release_ast(dlm, res); mlog(0, "about to wait on migration_wq, dirty=%s\n", - res->state & DLM_LOCK_RES_DIRTY ? "yes" : "no"); + str_yes_no(res->state & DLM_LOCK_RES_DIRTY)); /* if the extra ref we just put was the final one, this * will pass thru immediately. otherwise, we need to wait * for the last ast to finish. */ @@ -2869,12 +2869,12 @@ again: msecs_to_jiffies(1000)); if (ret < 0) { mlog(0, "woken again: migrating? %s, dead? %s\n", - res->state & DLM_LOCK_RES_MIGRATING ? "yes":"no", - test_bit(target, dlm->domain_map) ? "no":"yes"); + str_yes_no(res->state & DLM_LOCK_RES_MIGRATING), + str_no_yes(test_bit(target, dlm->domain_map))); } else { mlog(0, "all is well: migrating? %s, dead? %s\n", - res->state & DLM_LOCK_RES_MIGRATING ? "yes":"no", - test_bit(target, dlm->domain_map) ? "no":"yes"); + str_yes_no(res->state & DLM_LOCK_RES_MIGRATING), + str_no_yes(test_bit(target, dlm->domain_map))); } if (!dlm_migration_can_proceed(dlm, res, target)) { mlog(0, "trying again...\n"); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 50da8af988c1..67fc62a49a76 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -22,7 +22,7 @@ #include #include #include - +#include #include "../cluster/heartbeat.h" #include "../cluster/nodemanager.h" @@ -207,7 +207,7 @@ void dlm_complete_recovery_thread(struct dlm_ctxt *dlm) * 1) all recovery threads cluster wide will work on recovering * ONE node at a time * 2) negotiate who will take over all the locks for the dead node. - * thats right... ALL the locks. + * that's right... ALL the locks. * 3) once a new master is chosen, everyone scans all locks * and moves aside those mastered by the dead guy * 4) each of these locks should be locked until recovery is done @@ -581,8 +581,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) msecs_to_jiffies(1000)); mlog(0, "waited 1 sec for %u, " "dead? %s\n", ndata->node_num, - dlm_is_node_dead(dlm, ndata->node_num) ? - "yes" : "no"); + str_yes_no(dlm_is_node_dead(dlm, ndata->node_num))); } else { /* -ENOMEM on the other node */ mlog(0, "%s: node %u returned " @@ -677,7 +676,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) spin_unlock(&dlm_reco_state_lock); mlog(0, "pass #%d, all_nodes_done?: %s\n", ++pass, - all_nodes_done?"yes":"no"); + str_yes_no(all_nodes_done)); if (all_nodes_done) { int ret; @@ -1469,7 +1468,7 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, * The first one is handled at the end of this function. The * other two are handled in the worker thread after locks have * been attached. Yes, we don't wait for purge time to match - * kref_init. The lockres will still have atleast one ref + * kref_init. The lockres will still have at least one ref * added because it is in the hash __dlm_insert_lockres() */ extra_refs++; @@ -1735,7 +1734,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, spin_unlock(&res->spinlock); } } else { - /* put.. incase we are not the master */ + /* put.. in case we are not the master */ spin_unlock(&res->spinlock); dlm_lockres_put(res); } diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 7fc0e920eda7..2a7f36643895 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -20,6 +20,7 @@ #include #include +#include #include #include #include @@ -506,9 +507,7 @@ bail: return status; } -static int dlmfs_fill_super(struct super_block * sb, - void * data, - int silent) +static int dlmfs_fill_super(struct super_block *sb, struct fs_context *fc) { sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_SIZE; @@ -556,17 +555,27 @@ static const struct inode_operations dlmfs_file_inode_operations = { .setattr = dlmfs_file_setattr, }; -static struct dentry *dlmfs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int dlmfs_get_tree(struct fs_context *fc) { - return mount_nodev(fs_type, flags, data, dlmfs_fill_super); + return get_tree_nodev(fc, dlmfs_fill_super); +} + +static const struct fs_context_operations dlmfs_context_ops = { + .get_tree = dlmfs_get_tree, +}; + +static int dlmfs_init_fs_context(struct fs_context *fc) +{ + fc->ops = &dlmfs_context_ops; + + return 0; } static struct file_system_type dlmfs_fs_type = { .owner = THIS_MODULE, .name = "ocfs2_dlmfs", - .mount = dlmfs_mount, .kill_sb = kill_litter_super, + .init_fs_context = dlmfs_init_fs_context, }; MODULE_ALIAS_FS("ocfs2_dlmfs"); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 764ecbd5ad41..92a6149da9c1 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -19,6 +19,7 @@ #include #include #include +#include #define MLOG_MASK_PREFIX ML_DLM_GLUE #include @@ -794,7 +795,7 @@ void ocfs2_lock_res_free(struct ocfs2_lock_res *res) /* * Keep a list of processes who have interest in a lockres. - * Note: this is now only uesed for check recursive cluster locking. + * Note: this is now only used for check recursive cluster locking. */ static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres, struct ocfs2_lock_holder *oh) @@ -2529,30 +2530,28 @@ bail: /* * This is working around a lock inversion between tasks acquiring DLM - * locks while holding a page lock and the downconvert thread which - * blocks dlm lock acquiry while acquiring page locks. + * locks while holding a folio lock and the downconvert thread which + * blocks dlm lock acquiry while acquiring folio locks. * - * ** These _with_page variantes are only intended to be called from aop - * methods that hold page locks and return a very specific *positive* error + * ** These _with_folio variants are only intended to be called from aop + * methods that hold folio locks and return a very specific *positive* error * code that aop methods pass up to the VFS -- test for errors with != 0. ** * * The DLM is called such that it returns -EAGAIN if it would have * blocked waiting for the downconvert thread. In that case we unlock - * our page so the downconvert thread can make progress. Once we've + * our folio so the downconvert thread can make progress. Once we've * done this we have to return AOP_TRUNCATED_PAGE so the aop method * that called us can bubble that back up into the VFS who will then * immediately retry the aop call. */ -int ocfs2_inode_lock_with_page(struct inode *inode, - struct buffer_head **ret_bh, - int ex, - struct page *page) +int ocfs2_inode_lock_with_folio(struct inode *inode, + struct buffer_head **ret_bh, int ex, struct folio *folio) { int ret; ret = ocfs2_inode_lock_full(inode, ret_bh, ex, OCFS2_LOCK_NONBLOCK); if (ret == -EAGAIN) { - unlock_page(page); + folio_unlock(folio); /* * If we can't get inode lock immediately, we should not return * directly here, since this will lead to a softlockup problem. @@ -2630,7 +2629,7 @@ void ocfs2_inode_unlock(struct inode *inode, } /* - * This _tracker variantes are introduced to deal with the recursive cluster + * This _tracker variants are introduced to deal with the recursive cluster * locking issue. The idea is to keep track of a lock holder on the stack of * the current process. If there's a lock holder on the stack, we know the * task context is already protected by cluster locking. Currently, they're @@ -2735,7 +2734,7 @@ void ocfs2_inode_unlock_tracker(struct inode *inode, struct ocfs2_lock_res *lockres; lockres = &OCFS2_I(inode)->ip_inode_lockres; - /* had_lock means that the currect process already takes the cluster + /* had_lock means that the current process already takes the cluster * lock previously. * If had_lock is 1, we have nothing to do here. * If had_lock is 0, we will release the lock. @@ -3802,9 +3801,9 @@ recheck: * set when the ast is received for an upconvert just before the * OCFS2_LOCK_BUSY flag is cleared. Now if the fs received a bast * on the heels of the ast, we want to delay the downconvert just - * enough to allow the up requestor to do its task. Because this + * enough to allow the up requester to do its task. Because this * lock is in the blocked queue, the lock will be downconverted - * as soon as the requestor is done with the lock. + * as soon as the requester is done with the lock. */ if (lockres->l_flags & OCFS2_LOCK_UPCONVERT_FINISHING) goto leave_requeue; @@ -4339,7 +4338,7 @@ unqueue: ocfs2_schedule_blocked_lock(osb, lockres); mlog(ML_BASTS, "lockres %s, requeue = %s.\n", lockres->l_name, - ctl.requeue ? "yes" : "no"); + str_yes_no(ctl.requeue)); spin_unlock_irqrestore(&lockres->l_lock, flags); if (ctl.unblock_action != UNBLOCK_CONTINUE diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index e5da5809ed95..a3ebd7303ea2 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -137,10 +137,8 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, int ex, int arg_flags, int subclass); -int ocfs2_inode_lock_with_page(struct inode *inode, - struct buffer_head **ret_bh, - int ex, - struct page *page); +int ocfs2_inode_lock_with_folio(struct inode *inode, + struct buffer_head **ret_bh, int ex, struct folio *folio); /* Variants without special locking class or flags */ #define ocfs2_inode_lock_full(i, r, e, f)\ ocfs2_inode_lock_full_nested(i, r, e, f, OI_LS_NORMAL) diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index f7672472fa82..930150ed5db1 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -435,6 +435,16 @@ static int ocfs2_get_clusters_nocache(struct inode *inode, } } + if (le16_to_cpu(el->l_next_free_rec) > le16_to_cpu(el->l_count)) { + ocfs2_error(inode->i_sb, + "Inode %lu has an invalid extent (next_free_rec %u, count %u)\n", + inode->i_ino, + le16_to_cpu(el->l_next_free_rec), + le16_to_cpu(el->l_count)); + ret = -EROFS; + goto out; + } + i = ocfs2_search_extent_list(el, v_cluster); if (i == -1) { /* diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 957ced628eb1..e54f2c4b5a90 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -782,11 +782,11 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, goto out_commit_trans; } - /* Get the offsets within the page that we want to zero */ - zero_from = abs_from & (PAGE_SIZE - 1); - zero_to = abs_to & (PAGE_SIZE - 1); + /* Get the offsets within the folio that we want to zero */ + zero_from = offset_in_folio(folio, abs_from); + zero_to = offset_in_folio(folio, abs_to); if (!zero_to) - zero_to = PAGE_SIZE; + zero_to = folio_size(folio); trace_ocfs2_write_zero_page( (unsigned long long)OCFS2_I(inode)->ip_blkno, diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 2cc5c99fe941..12e5d1f73325 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -200,6 +200,20 @@ bail: return inode; } +static int ocfs2_dinode_has_extents(struct ocfs2_dinode *di) +{ + /* inodes flagged with other stuff in id2 */ + if (di->i_flags & (OCFS2_SUPER_BLOCK_FL | OCFS2_LOCAL_ALLOC_FL | + OCFS2_CHAIN_FL | OCFS2_DEALLOC_FL)) + return 0; + /* i_flags doesn't indicate when id2 is a fast symlink */ + if (S_ISLNK(di->i_mode) && di->i_size && di->i_clusters == 0) + return 0; + if (di->i_dyn_features & OCFS2_INLINE_DATA_FL) + return 0; + + return 1; +} /* * here's how inodes get read from disk: @@ -1122,7 +1136,7 @@ static void ocfs2_clear_inode(struct inode *inode) dquot_drop(inode); - /* To preven remote deletes we hold open lock before, now it + /* To prevent remote deletes we hold open lock before, now it * is time to unlock PR and EX open locks. */ ocfs2_open_unlock(inode); @@ -1437,7 +1451,7 @@ static int ocfs2_filecheck_validate_inode_block(struct super_block *sb, * Call ocfs2_validate_meta_ecc() first since it has ecc repair * function, but we should not return error immediately when ecc * validation fails, because the reason is quite likely the invalid - * inode number inputed. + * inode number inputted. */ rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check); if (rc) { @@ -1547,6 +1561,16 @@ static int ocfs2_filecheck_repair_inode_block(struct super_block *sb, le32_to_cpu(di->i_fs_generation)); } + if (ocfs2_dinode_has_extents(di) && + le16_to_cpu(di->id2.i_list.l_next_free_rec) > le16_to_cpu(di->id2.i_list.l_count)) { + di->id2.i_list.l_next_free_rec = di->id2.i_list.l_count; + changed = 1; + mlog(ML_ERROR, + "Filecheck: reset dinode #%llu: l_next_free_rec to %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(di->id2.i_list.l_next_free_rec)); + } + if (changed || ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check)) { ocfs2_compute_meta_ecc(sb, bh->b_data, &di->i_check); mark_buffer_dirty(bh); diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 71beef7f8a60..7ae96fb8807a 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -796,7 +796,7 @@ bail: /* * OCFS2_IOC_INFO handles an array of requests passed from userspace. * - * ocfs2_info_handle() recevies a large info aggregation, grab and + * ocfs2_info_handle() receives a large info aggregation, grab and * validate the request count from header, then break it into small * pieces, later specific handlers can handle them one by one. * diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 1bf188b6866a..f1b4b3e611cb 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1956,7 +1956,7 @@ bail: /* * Scan timer should get fired every ORPHAN_SCAN_SCHEDULE_TIMEOUT. Add some - * randomness to the timeout to minimize multple nodes firing the timer at the + * randomness to the timeout to minimize multiple nodes firing the timer at the * same time. */ static inline unsigned long ocfs2_orphan_scan_timeout(void) diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 8ac42ea81a17..d1aa04a5af1b 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -971,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, start = count = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); - while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) < - left) { - if (bit_off == start) { + while (1) { + bit_off = ocfs2_find_next_zero_bit(bitmap, left, start); + if ((bit_off < left) && (bit_off == start)) { count++; start++; continue; @@ -998,29 +998,12 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, } } + if (bit_off >= left) + break; count = 1; start = bit_off + 1; } - /* clear the contiguous bits until the end boundary */ - if (count) { - blkno = la_start_blk + - ocfs2_clusters_to_blocks(osb->sb, - start - count); - - trace_ocfs2_sync_local_to_main_free( - count, start - count, - (unsigned long long)la_start_blk, - (unsigned long long)blkno); - - status = ocfs2_release_clusters(handle, - main_bm_inode, - main_bm_bh, blkno, - count); - if (status < 0) - mlog_errno(status); - } - bail: if (status) mlog_errno(status); diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 6ef4cb045ccd..6a314e9f2b49 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -44,13 +44,13 @@ static vm_fault_t ocfs2_fault(struct vm_fault *vmf) } static vm_fault_t __ocfs2_page_mkwrite(struct file *file, - struct buffer_head *di_bh, struct page *page) + struct buffer_head *di_bh, struct folio *folio) { int err; vm_fault_t ret = VM_FAULT_NOPAGE; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; - loff_t pos = page_offset(page); + loff_t pos = folio_pos(folio); unsigned int len = PAGE_SIZE; pgoff_t last_index; struct folio *locked_folio = NULL; @@ -72,9 +72,9 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file, * * Let VM retry with these cases. */ - if ((page->mapping != inode->i_mapping) || - (!PageUptodate(page)) || - (page_offset(page) >= size)) + if ((folio->mapping != inode->i_mapping) || + !folio_test_uptodate(folio) || + (pos >= size)) goto out; /* @@ -87,11 +87,11 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file, * worry about ocfs2_write_begin() skipping some buffer reads * because the "write" would invalidate their data. */ - if (page->index == last_index) + if (folio->index == last_index) len = ((size - 1) & ~PAGE_MASK) + 1; err = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP, - &locked_folio, &fsdata, di_bh, page); + &locked_folio, &fsdata, di_bh, folio); if (err) { if (err != -ENOSPC) mlog_errno(err); @@ -112,7 +112,7 @@ out: static vm_fault_t ocfs2_page_mkwrite(struct vm_fault *vmf) { - struct page *page = vmf->page; + struct folio *folio = page_folio(vmf->page); struct inode *inode = file_inode(vmf->vma->vm_file); struct buffer_head *di_bh = NULL; sigset_t oldset; @@ -141,7 +141,7 @@ static vm_fault_t ocfs2_page_mkwrite(struct vm_fault *vmf) */ down_write(&OCFS2_I(inode)->ip_alloc_sem); - ret = __ocfs2_page_mkwrite(vmf->vma->vm_file, di_bh, page); + ret = __ocfs2_page_mkwrite(vmf->vma->vm_file, di_bh, folio); up_write(&OCFS2_I(inode)->ip_alloc_sem); diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index f9d6a4f9ca92..369c7d27befd 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -492,7 +492,7 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode, bg = (struct ocfs2_group_desc *)gd_bh->b_data; /* - * moving goal is not allowd to start with a group desc blok(#0 blk) + * moving goal is not allowed to start with a group desc blok(#0 blk) * let's compromise to the latter cluster. */ if (range->me_goal == le64_to_cpu(bg->bg_blkno)) @@ -658,7 +658,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context, /* * probe the victim cluster group to find a proper - * region to fit wanted movement, it even will perfrom + * region to fit wanted movement, it even will perform * a best-effort attempt by compromising to a threshold * around the goal. */ @@ -920,7 +920,7 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context) } /* - * rememer ip_xattr_sem also needs to be held if necessary + * remember ip_xattr_sem also needs to be held if necessary */ down_write(&OCFS2_I(inode)->ip_alloc_sem); @@ -1022,7 +1022,7 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) context->range = ⦥ /* - * ok, the default theshold for the defragmentation + * ok, the default threshold for the defragmentation * is 1M, since our maximum clustersize was 1M also. * any thought? */ diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 5550f8afa438..0ec63a1a94b8 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -508,7 +508,6 @@ static int __ocfs2_mknod_locked(struct inode *dir, struct inode *inode, dev_t dev, struct buffer_head **new_fe_bh, - struct buffer_head *parent_fe_bh, handle_t *handle, struct ocfs2_alloc_context *inode_ac, u64 fe_blkno, u64 suballoc_loc, u16 suballoc_bit) @@ -641,8 +640,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, } return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, - parent_fe_bh, handle, inode_ac, - fe_blkno, suballoc_loc, suballoc_bit); + handle, inode_ac, fe_blkno, + suballoc_loc, suballoc_bit); } static int ocfs2_mkdir(struct mnt_idmap *idmap, @@ -2576,7 +2575,7 @@ int ocfs2_create_inode_in_orphan(struct inode *dir, clear_nlink(inode); /* do the real work now. */ status = __ocfs2_mknod_locked(dir, inode, - 0, &new_di_bh, parent_di_bh, handle, + 0, &new_di_bh, handle, inode_ac, di_blkno, suballoc_loc, suballoc_bit); if (status < 0) { diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index c93689b568fe..e8e94599e907 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -132,7 +132,7 @@ * well as the name of the cluster being joined. * mount.ocfs2 must pass in a matching stack name. * - * If not set, the classic stack will be used. This is compatbile with + * If not set, the classic stack will be used. This is compatible with * all older versions. */ #define OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK 0x0080 @@ -143,7 +143,7 @@ /* Support for extended attributes */ #define OCFS2_FEATURE_INCOMPAT_XATTR 0x0200 -/* Support for indexed directores */ +/* Support for indexed directories */ #define OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS 0x0400 /* Metadata checksum and error correction */ @@ -156,7 +156,7 @@ #define OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG 0x2000 /* - * Incompat bit to indicate useable clusterinfo with stackflags for all + * Incompat bit to indicate usable clusterinfo with stackflags for all * cluster stacks (userspace adnd o2cb). If this bit is set, * INCOMPAT_USERSPACE_STACK becomes superfluous and thus should not be set. */ @@ -1083,7 +1083,7 @@ struct ocfs2_xattr_block { struct ocfs2_xattr_header xb_header; /* xattr header if this block contains xattr */ struct ocfs2_xattr_tree_root xb_root;/* xattr tree root if this - block cotains xattr + block contains xattr tree. */ } xb_attrs; }; diff --git a/fs/ocfs2/ocfs2_ioctl.h b/fs/ocfs2/ocfs2_ioctl.h index 9680797bc531..2de2f8733283 100644 --- a/fs/ocfs2/ocfs2_ioctl.h +++ b/fs/ocfs2/ocfs2_ioctl.h @@ -215,7 +215,7 @@ struct ocfs2_move_extents { movement less likely to fail, may make fs even more fragmented */ -#define OCFS2_MOVE_EXT_FL_COMPLETE (0x00000004) /* Move or defragmenation +#define OCFS2_MOVE_EXT_FL_COMPLETE (0x00000004) /* Move or defragmentation completely gets done. */ diff --git a/fs/ocfs2/ocfs2_lockid.h b/fs/ocfs2/ocfs2_lockid.h index 8ac357ce6a30..9b234c03d693 100644 --- a/fs/ocfs2/ocfs2_lockid.h +++ b/fs/ocfs2/ocfs2_lockid.h @@ -93,7 +93,7 @@ static char *ocfs2_lock_type_strings[] = { [OCFS2_LOCK_TYPE_DATA] = "Data", [OCFS2_LOCK_TYPE_SUPER] = "Super", [OCFS2_LOCK_TYPE_RENAME] = "Rename", - /* Need to differntiate from [R]ename.. serializing writes is the + /* Need to differentiate from [R]ename.. serializing writes is the * important job it does, anyway. */ [OCFS2_LOCK_TYPE_RW] = "Write/Read", [OCFS2_LOCK_TYPE_DENTRY] = "Dentry", diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 0511c69c9fde..54ed1495de9a 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -1658,34 +1658,34 @@ TRACE_EVENT(ocfs2_remount, ); TRACE_EVENT(ocfs2_fill_super, - TP_PROTO(void *sb, void *data, int silent), - TP_ARGS(sb, data, silent), + TP_PROTO(void *sb, void *fc, int silent), + TP_ARGS(sb, fc, silent), TP_STRUCT__entry( __field(void *, sb) - __field(void *, data) + __field(void *, fc) __field(int, silent) ), TP_fast_assign( __entry->sb = sb; - __entry->data = data; + __entry->fc = fc; __entry->silent = silent; ), TP_printk("%p %p %d", __entry->sb, - __entry->data, __entry->silent) + __entry->fc, __entry->silent) ); TRACE_EVENT(ocfs2_parse_options, - TP_PROTO(int is_remount, char *options), - TP_ARGS(is_remount, options), + TP_PROTO(int is_remount, const char *option), + TP_ARGS(is_remount, option), TP_STRUCT__entry( __field(int, is_remount) - __string(options, options) + __string(option, option) ), TP_fast_assign( __entry->is_remount = is_remount; - __assign_str(options); + __assign_str(option); ), - TP_printk("%d %s", __entry->is_remount, __get_str(options)) + TP_printk("%d %s", __entry->is_remount, __get_str(option)) ); DEFINE_OCFS2_POINTER_EVENT(ocfs2_put_super); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 2b0daced98eb..15d9acd456ec 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -761,6 +761,11 @@ static int ocfs2_release_dquot(struct dquot *dquot) handle = ocfs2_start_trans(osb, ocfs2_calc_qdel_credits(dquot->dq_sb, dquot->dq_id.type)); if (IS_ERR(handle)) { + /* + * Mark dquot as inactive to avoid endless cycle in + * quota_release_workfn(). + */ + clear_bit(DQ_ACTIVE_B, &dquot->dq_flags); status = PTR_ERR(handle); mlog_errno(status); goto out_ilock; @@ -893,7 +898,7 @@ static int ocfs2_get_next_id(struct super_block *sb, struct kqid *qid) int status = 0; trace_ocfs2_get_next_id(from_kqid(&init_user_ns, *qid), type); - if (!sb_has_quota_loaded(sb, type)) { + if (!sb_has_quota_active(sb, type)) { status = -ESRCH; goto out; } diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 73d3367c533b..2956d888c131 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -867,6 +867,7 @@ out: brelse(oinfo->dqi_libh); brelse(oinfo->dqi_lqi_bh); kfree(oinfo); + info->dqi_priv = NULL; return status; } diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 004393b13c0a..8f732742b26e 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2420,7 +2420,7 @@ static int ocfs2_calc_refcount_meta_credits(struct super_block *sb, * * If we will insert a new one, this is easy and only happens * during adding refcounted flag to the extent, so we don't - * have a chance of spliting. We just need one record. + * have a chance of splitting. We just need one record. * * If the refcount rec already exists, that would be a little * complicated. we may have to: @@ -2610,11 +2610,11 @@ static inline unsigned int ocfs2_cow_align_length(struct super_block *sb, /* * Calculate out the start and number of virtual clusters we need to CoW. * - * cpos is vitual start cluster position we want to do CoW in a + * cpos is virtual start cluster position we want to do CoW in a * file and write_len is the cluster length. * max_cpos is the place where we want to stop CoW intentionally. * - * Normal we will start CoW from the beginning of extent record cotaining cpos. + * Normal we will start CoW from the beginning of extent record containing cpos. * We try to break up extents on boundaries of MAX_CONTIG_BYTES so that we * get good I/O from the resulting extent tree. */ @@ -2902,7 +2902,6 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, int ret = 0, partial; struct super_block *sb = inode->i_sb; u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster); - struct page *page; pgoff_t page_index; unsigned int from, to; loff_t offset, end, map_end; @@ -2921,6 +2920,7 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, end = i_size_read(inode); while (offset < end) { + struct folio *folio; page_index = offset >> PAGE_SHIFT; map_end = ((loff_t)page_index + 1) << PAGE_SHIFT; if (map_end > end) @@ -2933,9 +2933,10 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, to = map_end & (PAGE_SIZE - 1); retry: - page = find_or_create_page(mapping, page_index, GFP_NOFS); - if (!page) { - ret = -ENOMEM; + folio = __filemap_get_folio(mapping, page_index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); + if (IS_ERR(folio)) { + ret = PTR_ERR(folio); mlog_errno(ret); break; } @@ -2945,9 +2946,9 @@ retry: * page, so write it back. */ if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) { - if (PageDirty(page)) { - unlock_page(page); - put_page(page); + if (folio_test_dirty(folio)) { + folio_unlock(folio); + folio_put(folio); ret = filemap_write_and_wait_range(mapping, offset, map_end - 1); @@ -2955,9 +2956,7 @@ retry: } } - if (!PageUptodate(page)) { - struct folio *folio = page_folio(page); - + if (!folio_test_uptodate(folio)) { ret = block_read_full_folio(folio, ocfs2_get_block); if (ret) { mlog_errno(ret); @@ -2966,8 +2965,8 @@ retry: folio_lock(folio); } - if (page_has_buffers(page)) { - ret = walk_page_buffers(handle, page_buffers(page), + if (folio_buffers(folio)) { + ret = walk_page_buffers(handle, folio_buffers(folio), from, to, &partial, ocfs2_clear_cow_buffer); if (ret) { @@ -2976,14 +2975,12 @@ retry: } } - ocfs2_map_and_dirty_page(inode, - handle, from, to, - page, 0, &new_block); - mark_page_accessed(page); + ocfs2_map_and_dirty_folio(inode, handle, from, to, + folio, 0, &new_block); + folio_mark_accessed(folio); unlock: - unlock_page(page); - put_page(page); - page = NULL; + folio_unlock(folio); + folio_put(folio); offset = map_end; if (ret) break; diff --git a/fs/ocfs2/reservations.h b/fs/ocfs2/reservations.h index ec8101ef5717..4fce17180342 100644 --- a/fs/ocfs2/reservations.h +++ b/fs/ocfs2/reservations.h @@ -31,7 +31,7 @@ struct ocfs2_alloc_reservation { #define OCFS2_RESV_FLAG_INUSE 0x01 /* Set when r_node is part of a btree */ #define OCFS2_RESV_FLAG_TMP 0x02 /* Temporary reservation, will be - * destroyed immedately after use */ + * destroyed immediately after use */ #define OCFS2_RESV_FLAG_DIR 0x04 /* Reservation is for an unindexed * directory btree */ @@ -125,7 +125,7 @@ int ocfs2_resmap_resv_bits(struct ocfs2_reservation_map *resmap, /** * ocfs2_resmap_claimed_bits() - Tell the reservation code that bits were used. * @resmap: reservations bitmap - * @resv: optional reservation to recalulate based on new bitmap + * @resv: optional reservation to recalculate based on new bitmap * @cstart: start of allocation in clusters * @clen: end of allocation in clusters. * diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c index 10157d9d7a9c..f58e891aa2da 100644 --- a/fs/ocfs2/stack_o2cb.c +++ b/fs/ocfs2/stack_o2cb.c @@ -227,7 +227,7 @@ static int o2cb_dlm_lock_status(struct ocfs2_dlm_lksb *lksb) } /* - * o2dlm aways has a "valid" LVB. If the dlm loses track of the LVB + * o2dlm always has a "valid" LVB. If the dlm loses track of the LVB * contents, it will zero out the LVB. Thus the caller can always trust * the contents. */ diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 20aa37b67cfb..ddd761cf44c8 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -650,7 +650,7 @@ error: * and easier to preserve the name. */ -static struct ctl_table ocfs2_nm_table[] = { +static const struct ctl_table ocfs2_nm_table[] = { { .procname = "hb_ctl_path", .data = ocfs2_hb_ctl_path, diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index 02ab072c528a..5486a6dce70a 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -210,7 +210,7 @@ struct ocfs2_stack_operations { struct file_lock *fl); /* - * This is an optoinal debugging hook. If provided, the + * This is an optional debugging hook. If provided, the * stack can dump debugging information about this lock. */ void (*dump_lksb)(struct ocfs2_dlm_lksb *lksb); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index c79b4291777f..8bb5022f3082 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -19,10 +19,10 @@ #include #include #include -#include +#include +#include #include #include -#include #include #include #include @@ -80,17 +80,15 @@ struct mount_options unsigned int resv_level; int dir_resv_level; char cluster_stack[OCFS2_STACK_LABEL_LEN + 1]; + bool user_stack; }; -static int ocfs2_parse_options(struct super_block *sb, char *options, - struct mount_options *mopt, - int is_remount); +static int ocfs2_parse_param(struct fs_context *fc, struct fs_parameter *param); static int ocfs2_check_set_options(struct super_block *sb, struct mount_options *options); static int ocfs2_show_options(struct seq_file *s, struct dentry *root); static void ocfs2_put_super(struct super_block *sb); static int ocfs2_mount_volume(struct super_block *sb); -static int ocfs2_remount(struct super_block *sb, int *flags, char *data); static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err); static int ocfs2_initialize_mem_caches(void); static void ocfs2_free_mem_caches(void); @@ -135,7 +133,6 @@ static const struct super_operations ocfs2_sops = { .evict_inode = ocfs2_evict_inode, .sync_fs = ocfs2_sync_fs, .put_super = ocfs2_put_super, - .remount_fs = ocfs2_remount, .show_options = ocfs2_show_options, .quota_read = ocfs2_quota_read, .quota_write = ocfs2_quota_write, @@ -144,15 +141,10 @@ static const struct super_operations ocfs2_sops = { enum { Opt_barrier, - Opt_err_panic, - Opt_err_ro, + Opt_errors, Opt_intr, - Opt_nointr, - Opt_hb_none, - Opt_hb_local, - Opt_hb_global, - Opt_data_ordered, - Opt_data_writeback, + Opt_heartbeat, + Opt_data, Opt_atime_quantum, Opt_slot, Opt_commit, @@ -160,52 +152,64 @@ enum { Opt_localflocks, Opt_stack, Opt_user_xattr, - Opt_nouser_xattr, Opt_inode64, Opt_acl, - Opt_noacl, Opt_usrquota, Opt_grpquota, - Opt_coherency_buffered, - Opt_coherency_full, + Opt_coherency, Opt_resv_level, Opt_dir_resv_level, Opt_journal_async_commit, - Opt_err_cont, - Opt_err, }; -static const match_table_t tokens = { - {Opt_barrier, "barrier=%u"}, - {Opt_err_panic, "errors=panic"}, - {Opt_err_ro, "errors=remount-ro"}, - {Opt_intr, "intr"}, - {Opt_nointr, "nointr"}, - {Opt_hb_none, OCFS2_HB_NONE}, - {Opt_hb_local, OCFS2_HB_LOCAL}, - {Opt_hb_global, OCFS2_HB_GLOBAL}, - {Opt_data_ordered, "data=ordered"}, - {Opt_data_writeback, "data=writeback"}, - {Opt_atime_quantum, "atime_quantum=%u"}, - {Opt_slot, "preferred_slot=%u"}, - {Opt_commit, "commit=%u"}, - {Opt_localalloc, "localalloc=%d"}, - {Opt_localflocks, "localflocks"}, - {Opt_stack, "cluster_stack=%s"}, - {Opt_user_xattr, "user_xattr"}, - {Opt_nouser_xattr, "nouser_xattr"}, - {Opt_inode64, "inode64"}, - {Opt_acl, "acl"}, - {Opt_noacl, "noacl"}, - {Opt_usrquota, "usrquota"}, - {Opt_grpquota, "grpquota"}, - {Opt_coherency_buffered, "coherency=buffered"}, - {Opt_coherency_full, "coherency=full"}, - {Opt_resv_level, "resv_level=%u"}, - {Opt_dir_resv_level, "dir_resv_level=%u"}, - {Opt_journal_async_commit, "journal_async_commit"}, - {Opt_err_cont, "errors=continue"}, - {Opt_err, NULL} +static const struct constant_table ocfs2_param_errors[] = { + {"panic", OCFS2_MOUNT_ERRORS_PANIC}, + {"remount-ro", OCFS2_MOUNT_ERRORS_ROFS}, + {"continue", OCFS2_MOUNT_ERRORS_CONT}, + {} +}; + +static const struct constant_table ocfs2_param_heartbeat[] = { + {"local", OCFS2_MOUNT_HB_LOCAL}, + {"none", OCFS2_MOUNT_HB_NONE}, + {"global", OCFS2_MOUNT_HB_GLOBAL}, + {} +}; + +static const struct constant_table ocfs2_param_data[] = { + {"writeback", OCFS2_MOUNT_DATA_WRITEBACK}, + {"ordered", 0}, + {} +}; + +static const struct constant_table ocfs2_param_coherency[] = { + {"buffered", OCFS2_MOUNT_COHERENCY_BUFFERED}, + {"full", 0}, + {} +}; + +static const struct fs_parameter_spec ocfs2_param_spec[] = { + fsparam_u32 ("barrier", Opt_barrier), + fsparam_enum ("errors", Opt_errors, ocfs2_param_errors), + fsparam_flag_no ("intr", Opt_intr), + fsparam_enum ("heartbeat", Opt_heartbeat, ocfs2_param_heartbeat), + fsparam_enum ("data", Opt_data, ocfs2_param_data), + fsparam_u32 ("atime_quantum", Opt_atime_quantum), + fsparam_u32 ("preferred_slot", Opt_slot), + fsparam_u32 ("commit", Opt_commit), + fsparam_s32 ("localalloc", Opt_localalloc), + fsparam_flag ("localflocks", Opt_localflocks), + fsparam_string ("cluster_stack", Opt_stack), + fsparam_flag_no ("user_xattr", Opt_user_xattr), + fsparam_flag ("inode64", Opt_inode64), + fsparam_flag_no ("acl", Opt_acl), + fsparam_flag ("usrquota", Opt_usrquota), + fsparam_flag ("grpquota", Opt_grpquota), + fsparam_enum ("coherency", Opt_coherency, ocfs2_param_coherency), + fsparam_u32 ("resv_level", Opt_resv_level), + fsparam_u32 ("dir_resv_level", Opt_dir_resv_level), + fsparam_flag ("journal_async_commit", Opt_journal_async_commit), + {} }; #ifdef CONFIG_DEBUG_FS @@ -600,32 +604,32 @@ static unsigned long long ocfs2_max_file_offset(unsigned int bbits, return (((unsigned long long)bytes) << bitshift) - trim; } -static int ocfs2_remount(struct super_block *sb, int *flags, char *data) +static int ocfs2_reconfigure(struct fs_context *fc) { int incompat_features; int ret = 0; - struct mount_options parsed_options; + struct mount_options *parsed_options = fc->fs_private; + struct super_block *sb = fc->root->d_sb; struct ocfs2_super *osb = OCFS2_SB(sb); u32 tmp; sync_filesystem(sb); - if (!ocfs2_parse_options(sb, data, &parsed_options, 1) || - !ocfs2_check_set_options(sb, &parsed_options)) { + if (!ocfs2_check_set_options(sb, parsed_options)) { ret = -EINVAL; goto out; } tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL | OCFS2_MOUNT_HB_NONE; - if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) { + if ((osb->s_mount_opt & tmp) != (parsed_options->mount_opt & tmp)) { ret = -EINVAL; mlog(ML_ERROR, "Cannot change heartbeat mode on remount\n"); goto out; } if ((osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK) != - (parsed_options.mount_opt & OCFS2_MOUNT_DATA_WRITEBACK)) { + (parsed_options->mount_opt & OCFS2_MOUNT_DATA_WRITEBACK)) { ret = -EINVAL; mlog(ML_ERROR, "Cannot change data mode on remount\n"); goto out; @@ -634,16 +638,16 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data) /* Probably don't want this on remount; it might * mess with other nodes */ if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64) && - (parsed_options.mount_opt & OCFS2_MOUNT_INODE64)) { + (parsed_options->mount_opt & OCFS2_MOUNT_INODE64)) { ret = -EINVAL; mlog(ML_ERROR, "Cannot enable inode64 on remount\n"); goto out; } /* We're going to/from readonly mode. */ - if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { + if ((bool)(fc->sb_flags & SB_RDONLY) != sb_rdonly(sb)) { /* Disable quota accounting before remounting RO */ - if (*flags & SB_RDONLY) { + if (fc->sb_flags & SB_RDONLY) { ret = ocfs2_susp_quotas(osb, 0); if (ret < 0) goto out; @@ -657,7 +661,7 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data) goto unlock_osb; } - if (*flags & SB_RDONLY) { + if (fc->sb_flags & SB_RDONLY) { sb->s_flags |= SB_RDONLY; osb->osb_flags |= OCFS2_OSB_SOFT_RO; } else { @@ -678,11 +682,11 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data) sb->s_flags &= ~SB_RDONLY; osb->osb_flags &= ~OCFS2_OSB_SOFT_RO; } - trace_ocfs2_remount(sb->s_flags, osb->osb_flags, *flags); + trace_ocfs2_remount(sb->s_flags, osb->osb_flags, fc->sb_flags); unlock_osb: spin_unlock(&osb->osb_lock); /* Enable quota accounting after remounting RW */ - if (!ret && !(*flags & SB_RDONLY)) { + if (!ret && !(fc->sb_flags & SB_RDONLY)) { if (sb_any_quota_suspended(sb)) ret = ocfs2_susp_quotas(osb, 1); else @@ -701,11 +705,11 @@ unlock_osb: if (!ret) { /* Only save off the new mount options in case of a successful * remount. */ - osb->s_mount_opt = parsed_options.mount_opt; - osb->s_atime_quantum = parsed_options.atime_quantum; - osb->preferred_slot = parsed_options.slot; - if (parsed_options.commit_interval) - osb->osb_commit_interval = parsed_options.commit_interval; + osb->s_mount_opt = parsed_options->mount_opt; + osb->s_atime_quantum = parsed_options->atime_quantum; + osb->preferred_slot = parsed_options->slot; + if (parsed_options->commit_interval) + osb->osb_commit_interval = parsed_options->commit_interval; if (!ocfs2_is_hard_readonly(osb)) ocfs2_set_journal_params(osb); @@ -966,23 +970,18 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb) } } -static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) +static int ocfs2_fill_super(struct super_block *sb, struct fs_context *fc) { struct dentry *root; int status, sector_size; - struct mount_options parsed_options; + struct mount_options *parsed_options = fc->fs_private; struct inode *inode = NULL; struct ocfs2_super *osb = NULL; struct buffer_head *bh = NULL; char nodestr[12]; struct ocfs2_blockcheck_stats stats; - trace_ocfs2_fill_super(sb, data, silent); - - if (!ocfs2_parse_options(sb, data, &parsed_options, 0)) { - status = -EINVAL; - goto out; - } + trace_ocfs2_fill_super(sb, fc, fc->sb_flags & SB_SILENT); /* probe for superblock */ status = ocfs2_sb_probe(sb, &bh, §or_size, &stats); @@ -999,24 +998,24 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) osb = OCFS2_SB(sb); - if (!ocfs2_check_set_options(sb, &parsed_options)) { + if (!ocfs2_check_set_options(sb, parsed_options)) { status = -EINVAL; goto out_super; } - osb->s_mount_opt = parsed_options.mount_opt; - osb->s_atime_quantum = parsed_options.atime_quantum; - osb->preferred_slot = parsed_options.slot; - osb->osb_commit_interval = parsed_options.commit_interval; + osb->s_mount_opt = parsed_options->mount_opt; + osb->s_atime_quantum = parsed_options->atime_quantum; + osb->preferred_slot = parsed_options->slot; + osb->osb_commit_interval = parsed_options->commit_interval; - ocfs2_la_set_sizes(osb, parsed_options.localalloc_opt); - osb->osb_resv_level = parsed_options.resv_level; - osb->osb_dir_resv_level = parsed_options.resv_level; - if (parsed_options.dir_resv_level == -1) - osb->osb_dir_resv_level = parsed_options.resv_level; + ocfs2_la_set_sizes(osb, parsed_options->localalloc_opt); + osb->osb_resv_level = parsed_options->resv_level; + osb->osb_dir_resv_level = parsed_options->resv_level; + if (parsed_options->dir_resv_level == -1) + osb->osb_dir_resv_level = parsed_options->resv_level; else - osb->osb_dir_resv_level = parsed_options.dir_resv_level; + osb->osb_dir_resv_level = parsed_options->dir_resv_level; - status = ocfs2_verify_userspace_stack(osb, &parsed_options); + status = ocfs2_verify_userspace_stack(osb, parsed_options); if (status) goto out_super; @@ -1180,27 +1179,72 @@ out: return status; } -static struct dentry *ocfs2_mount(struct file_system_type *fs_type, - int flags, - const char *dev_name, - void *data) +static int ocfs2_get_tree(struct fs_context *fc) { - return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super); + return get_tree_bdev(fc, ocfs2_fill_super); +} + +static void ocfs2_free_fc(struct fs_context *fc) +{ + kfree(fc->fs_private); +} + +static const struct fs_context_operations ocfs2_context_ops = { + .parse_param = ocfs2_parse_param, + .get_tree = ocfs2_get_tree, + .reconfigure = ocfs2_reconfigure, + .free = ocfs2_free_fc, +}; + +static int ocfs2_init_fs_context(struct fs_context *fc) +{ + struct mount_options *mopt; + + mopt = kzalloc(sizeof(struct mount_options), GFP_KERNEL); + if (!mopt) + return -EINVAL; + + mopt->commit_interval = 0; + mopt->mount_opt = OCFS2_MOUNT_NOINTR; + mopt->atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM; + mopt->slot = OCFS2_INVALID_SLOT; + mopt->localalloc_opt = -1; + mopt->cluster_stack[0] = '\0'; + mopt->resv_level = OCFS2_DEFAULT_RESV_LEVEL; + mopt->dir_resv_level = -1; + + fc->fs_private = mopt; + fc->ops = &ocfs2_context_ops; + + return 0; } static struct file_system_type ocfs2_fs_type = { .owner = THIS_MODULE, .name = "ocfs2", - .mount = ocfs2_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE, - .next = NULL + .next = NULL, + .init_fs_context = ocfs2_init_fs_context, + .parameters = ocfs2_param_spec, }; MODULE_ALIAS_FS("ocfs2"); static int ocfs2_check_set_options(struct super_block *sb, struct mount_options *options) { + if (options->user_stack == 0) { + u32 tmp; + + /* Ensure only one heartbeat mode */ + tmp = options->mount_opt & (OCFS2_MOUNT_HB_LOCAL | + OCFS2_MOUNT_HB_GLOBAL | + OCFS2_MOUNT_HB_NONE); + if (hweight32(tmp) != 1) { + mlog(ML_ERROR, "Invalid heartbeat mount options\n"); + return 0; + } + } if (options->mount_opt & OCFS2_MOUNT_USRQUOTA && !OCFS2_HAS_RO_COMPAT_FEATURE(sb, OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) { @@ -1232,241 +1276,142 @@ static int ocfs2_check_set_options(struct super_block *sb, return 1; } -static int ocfs2_parse_options(struct super_block *sb, - char *options, - struct mount_options *mopt, - int is_remount) +static int ocfs2_parse_param(struct fs_context *fc, struct fs_parameter *param) { - int status, user_stack = 0; - char *p; - u32 tmp; - int token, option; - substring_t args[MAX_OPT_ARGS]; + struct fs_parse_result result; + int opt; + struct mount_options *mopt = fc->fs_private; + bool is_remount = (fc->purpose & FS_CONTEXT_FOR_RECONFIGURE); - trace_ocfs2_parse_options(is_remount, options ? options : "(none)"); + trace_ocfs2_parse_options(is_remount, param->key); - mopt->commit_interval = 0; - mopt->mount_opt = OCFS2_MOUNT_NOINTR; - mopt->atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM; - mopt->slot = OCFS2_INVALID_SLOT; - mopt->localalloc_opt = -1; - mopt->cluster_stack[0] = '\0'; - mopt->resv_level = OCFS2_DEFAULT_RESV_LEVEL; - mopt->dir_resv_level = -1; + opt = fs_parse(fc, ocfs2_param_spec, param, &result); + if (opt < 0) + return opt; - if (!options) { - status = 1; - goto bail; - } - - while ((p = strsep(&options, ",")) != NULL) { - if (!*p) - continue; - - token = match_token(p, tokens, args); - switch (token) { - case Opt_hb_local: - mopt->mount_opt |= OCFS2_MOUNT_HB_LOCAL; - break; - case Opt_hb_none: - mopt->mount_opt |= OCFS2_MOUNT_HB_NONE; - break; - case Opt_hb_global: - mopt->mount_opt |= OCFS2_MOUNT_HB_GLOBAL; - break; - case Opt_barrier: - if (match_int(&args[0], &option)) { - status = 0; - goto bail; - } - if (option) - mopt->mount_opt |= OCFS2_MOUNT_BARRIER; - else - mopt->mount_opt &= ~OCFS2_MOUNT_BARRIER; - break; - case Opt_intr: - mopt->mount_opt &= ~OCFS2_MOUNT_NOINTR; - break; - case Opt_nointr: + switch (opt) { + case Opt_heartbeat: + mopt->mount_opt |= result.uint_32; + break; + case Opt_barrier: + if (result.uint_32) + mopt->mount_opt |= OCFS2_MOUNT_BARRIER; + else + mopt->mount_opt &= ~OCFS2_MOUNT_BARRIER; + break; + case Opt_intr: + if (result.negated) mopt->mount_opt |= OCFS2_MOUNT_NOINTR; - break; - case Opt_err_panic: - mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT; - mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS; - mopt->mount_opt |= OCFS2_MOUNT_ERRORS_PANIC; - break; - case Opt_err_ro: - mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT; - mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC; - mopt->mount_opt |= OCFS2_MOUNT_ERRORS_ROFS; - break; - case Opt_err_cont: - mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS; - mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC; - mopt->mount_opt |= OCFS2_MOUNT_ERRORS_CONT; - break; - case Opt_data_ordered: - mopt->mount_opt &= ~OCFS2_MOUNT_DATA_WRITEBACK; - break; - case Opt_data_writeback: - mopt->mount_opt |= OCFS2_MOUNT_DATA_WRITEBACK; - break; - case Opt_user_xattr: - mopt->mount_opt &= ~OCFS2_MOUNT_NOUSERXATTR; - break; - case Opt_nouser_xattr: + else + mopt->mount_opt &= ~OCFS2_MOUNT_NOINTR; + break; + case Opt_errors: + mopt->mount_opt &= ~(OCFS2_MOUNT_ERRORS_CONT | + OCFS2_MOUNT_ERRORS_ROFS | + OCFS2_MOUNT_ERRORS_PANIC); + mopt->mount_opt |= result.uint_32; + break; + case Opt_data: + mopt->mount_opt &= ~OCFS2_MOUNT_DATA_WRITEBACK; + mopt->mount_opt |= result.uint_32; + break; + case Opt_user_xattr: + if (result.negated) mopt->mount_opt |= OCFS2_MOUNT_NOUSERXATTR; - break; - case Opt_atime_quantum: - if (match_int(&args[0], &option)) { - status = 0; - goto bail; - } - if (option >= 0) - mopt->atime_quantum = option; - break; - case Opt_slot: - if (match_int(&args[0], &option)) { - status = 0; - goto bail; - } - if (option) - mopt->slot = (u16)option; - break; - case Opt_commit: - if (match_int(&args[0], &option)) { - status = 0; - goto bail; - } - if (option < 0) - return 0; - if (option == 0) - option = JBD2_DEFAULT_MAX_COMMIT_AGE; - mopt->commit_interval = HZ * option; - break; - case Opt_localalloc: - if (match_int(&args[0], &option)) { - status = 0; - goto bail; - } - if (option >= 0) - mopt->localalloc_opt = option; - break; - case Opt_localflocks: - /* - * Changing this during remount could race - * flock() requests, or "unbalance" existing - * ones (e.g., a lock is taken in one mode but - * dropped in the other). If users care enough - * to flip locking modes during remount, we - * could add a "local" flag to individual - * flock structures for proper tracking of - * state. - */ - if (!is_remount) - mopt->mount_opt |= OCFS2_MOUNT_LOCALFLOCKS; - break; - case Opt_stack: - /* Check both that the option we were passed - * is of the right length and that it is a proper - * string of the right length. - */ - if (((args[0].to - args[0].from) != - OCFS2_STACK_LABEL_LEN) || - (strnlen(args[0].from, - OCFS2_STACK_LABEL_LEN) != - OCFS2_STACK_LABEL_LEN)) { - mlog(ML_ERROR, - "Invalid cluster_stack option\n"); - status = 0; - goto bail; - } - memcpy(mopt->cluster_stack, args[0].from, - OCFS2_STACK_LABEL_LEN); - mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0'; - /* - * Open code the memcmp here as we don't have - * an osb to pass to - * ocfs2_userspace_stack(). - */ - if (memcmp(mopt->cluster_stack, - OCFS2_CLASSIC_CLUSTER_STACK, - OCFS2_STACK_LABEL_LEN)) - user_stack = 1; - break; - case Opt_inode64: - mopt->mount_opt |= OCFS2_MOUNT_INODE64; - break; - case Opt_usrquota: - mopt->mount_opt |= OCFS2_MOUNT_USRQUOTA; - break; - case Opt_grpquota: - mopt->mount_opt |= OCFS2_MOUNT_GRPQUOTA; - break; - case Opt_coherency_buffered: - mopt->mount_opt |= OCFS2_MOUNT_COHERENCY_BUFFERED; - break; - case Opt_coherency_full: - mopt->mount_opt &= ~OCFS2_MOUNT_COHERENCY_BUFFERED; - break; - case Opt_acl: - mopt->mount_opt |= OCFS2_MOUNT_POSIX_ACL; - mopt->mount_opt &= ~OCFS2_MOUNT_NO_POSIX_ACL; - break; - case Opt_noacl: + else + mopt->mount_opt &= ~OCFS2_MOUNT_NOUSERXATTR; + break; + case Opt_atime_quantum: + mopt->atime_quantum = result.uint_32; + break; + case Opt_slot: + if (result.uint_32) + mopt->slot = (u16)result.uint_32; + break; + case Opt_commit: + if (result.uint_32 == 0) + mopt->commit_interval = HZ * JBD2_DEFAULT_MAX_COMMIT_AGE; + else + mopt->commit_interval = HZ * result.uint_32; + break; + case Opt_localalloc: + if (result.int_32 >= 0) + mopt->localalloc_opt = result.int_32; + break; + case Opt_localflocks: + /* + * Changing this during remount could race flock() requests, or + * "unbalance" existing ones (e.g., a lock is taken in one mode + * but dropped in the other). If users care enough to flip + * locking modes during remount, we could add a "local" flag to + * individual flock structures for proper tracking of state. + */ + if (!is_remount) + mopt->mount_opt |= OCFS2_MOUNT_LOCALFLOCKS; + break; + case Opt_stack: + /* Check both that the option we were passed is of the right + * length and that it is a proper string of the right length. + */ + if (strlen(param->string) != OCFS2_STACK_LABEL_LEN) { + mlog(ML_ERROR, "Invalid cluster_stack option\n"); + return -EINVAL; + } + memcpy(mopt->cluster_stack, param->string, OCFS2_STACK_LABEL_LEN); + mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0'; + /* + * Open code the memcmp here as we don't have an osb to pass + * to ocfs2_userspace_stack(). + */ + if (memcmp(mopt->cluster_stack, + OCFS2_CLASSIC_CLUSTER_STACK, + OCFS2_STACK_LABEL_LEN)) + mopt->user_stack = 1; + break; + case Opt_inode64: + mopt->mount_opt |= OCFS2_MOUNT_INODE64; + break; + case Opt_usrquota: + mopt->mount_opt |= OCFS2_MOUNT_USRQUOTA; + break; + case Opt_grpquota: + mopt->mount_opt |= OCFS2_MOUNT_GRPQUOTA; + break; + case Opt_coherency: + mopt->mount_opt &= ~OCFS2_MOUNT_COHERENCY_BUFFERED; + mopt->mount_opt |= result.uint_32; + break; + case Opt_acl: + if (result.negated) { mopt->mount_opt |= OCFS2_MOUNT_NO_POSIX_ACL; mopt->mount_opt &= ~OCFS2_MOUNT_POSIX_ACL; - break; - case Opt_resv_level: - if (is_remount) - break; - if (match_int(&args[0], &option)) { - status = 0; - goto bail; - } - if (option >= OCFS2_MIN_RESV_LEVEL && - option < OCFS2_MAX_RESV_LEVEL) - mopt->resv_level = option; - break; - case Opt_dir_resv_level: - if (is_remount) - break; - if (match_int(&args[0], &option)) { - status = 0; - goto bail; - } - if (option >= OCFS2_MIN_RESV_LEVEL && - option < OCFS2_MAX_RESV_LEVEL) - mopt->dir_resv_level = option; - break; - case Opt_journal_async_commit: - mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT; - break; - default: - mlog(ML_ERROR, - "Unrecognized mount option \"%s\" " - "or missing value\n", p); - status = 0; - goto bail; + } else { + mopt->mount_opt |= OCFS2_MOUNT_POSIX_ACL; + mopt->mount_opt &= ~OCFS2_MOUNT_NO_POSIX_ACL; } + break; + case Opt_resv_level: + if (is_remount) + break; + if (result.uint_32 >= OCFS2_MIN_RESV_LEVEL && + result.uint_32 < OCFS2_MAX_RESV_LEVEL) + mopt->resv_level = result.uint_32; + break; + case Opt_dir_resv_level: + if (is_remount) + break; + if (result.uint_32 >= OCFS2_MIN_RESV_LEVEL && + result.uint_32 < OCFS2_MAX_RESV_LEVEL) + mopt->dir_resv_level = result.uint_32; + break; + case Opt_journal_async_commit: + mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT; + break; + default: + return -EINVAL; } - if (user_stack == 0) { - /* Ensure only one heartbeat mode */ - tmp = mopt->mount_opt & (OCFS2_MOUNT_HB_LOCAL | - OCFS2_MOUNT_HB_GLOBAL | - OCFS2_MOUNT_HB_NONE); - if (hweight32(tmp) != 1) { - mlog(ML_ERROR, "Invalid heartbeat mount options\n"); - status = 0; - goto bail; - } - } - - status = 1; - -bail: - return status; + return 0; } static int ocfs2_show_options(struct seq_file *s, struct dentry *root) @@ -1858,7 +1803,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) osb = OCFS2_SB(sb); BUG_ON(!osb); - /* Remove file check sysfs related directores/files, + /* Remove file check sysfs related directories/files, * and wait for the pending file check operations */ ocfs2_filecheck_remove_sysfs(osb); @@ -2340,7 +2285,7 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di, mlog(ML_ERROR, "found superblock with incorrect block " "size bits: found %u, should be 9, 10, 11, or 12\n", blksz_bits); - } else if ((1 << le32_to_cpu(blksz_bits)) != blksz) { + } else if ((1 << blksz_bits) != blksz) { mlog(ML_ERROR, "found superblock with incorrect block " "size: found %u, should be %u\n", 1 << blksz_bits, blksz); } else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) != diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c index d4c5fdcfa1e4..ad8be3300b49 100644 --- a/fs/ocfs2/symlink.c +++ b/fs/ocfs2/symlink.c @@ -54,31 +54,27 @@ static int ocfs2_fast_symlink_read_folio(struct file *f, struct folio *folio) { - struct page *page = &folio->page; - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct buffer_head *bh = NULL; int status = ocfs2_read_inode_block(inode, &bh); struct ocfs2_dinode *fe; const char *link; - void *kaddr; size_t len; if (status < 0) { mlog_errno(status); - return status; + goto out; } fe = (struct ocfs2_dinode *) bh->b_data; link = (char *) fe->id2.i_symlink; /* will be less than a page size */ len = strnlen(link, ocfs2_fast_symlink_chars(inode->i_sb)); - kaddr = kmap_atomic(page); - memcpy(kaddr, link, len + 1); - kunmap_atomic(kaddr); - SetPageUptodate(page); - unlock_page(page); + memcpy_to_folio(folio, 0, link, len + 1); +out: + folio_end_read(folio, status == 0); brelse(bh); - return 0; + return status; } const struct address_space_operations ocfs2_fast_symlink_aops = { diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 73a6f6fd8a8e..d70a20d29e3e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -648,7 +648,7 @@ int ocfs2_calc_xattr_init(struct inode *dir, * 256(name) + 80(value) + 16(entry) = 352 bytes, * The max space of acl xattr taken inline is * 80(value) + 16(entry) * 2(if directory) = 192 bytes, - * when blocksize = 512, may reserve one more cluser for + * when blocksize = 512, may reserve one more cluster for * xattr bucket, otherwise reserve one metadata block * for them is ok. * If this is a new directory with inline data, @@ -4371,7 +4371,7 @@ static int cmp_xe_offset(const void *a, const void *b) /* * defrag a xattr bucket if we find that the bucket has some - * holes beteen name/value pairs. + * holes between name/value pairs. * We will move all the name/value pairs to the end of the bucket * so that we can spare some space for insertion. */ @@ -5011,7 +5011,7 @@ static int ocfs2_divide_xattr_cluster(struct inode *inode, * 2. If cluster_size == bucket_size: * a) If the previous extent rec has more than one cluster and the insert * place isn't in the last cluster, copy the entire last cluster to the - * new one. This time, we don't need to upate the first_bh and header_bh + * new one. This time, we don't need to update the first_bh and header_bh * since they will not be moved into the new cluster. * b) Otherwise, move the bottom half of the xattrs in the last cluster into * the new one. And we set the extend flag to zero if the insert place is @@ -6189,7 +6189,7 @@ struct ocfs2_xattr_reflink { /* * Given a xattr header and xe offset, * return the proper xv and the corresponding bh. - * xattr in inode, block and xattr tree have different implementaions. + * xattr in inode, block and xattr tree have different implementations. */ typedef int (get_xattr_value_root)(struct super_block *sb, struct buffer_head *bh, @@ -6269,7 +6269,7 @@ static int ocfs2_get_xattr_value_root(struct super_block *sb, } /* - * Lock the meta_ac and caculate how much credits we need for reflink xattrs. + * Lock the meta_ac and calculate how much credits we need for reflink xattrs. * It is only used for inline xattr and xattr block. */ static int ocfs2_reflink_lock_xattr_allocators(struct ocfs2_super *osb, diff --git a/fs/open.c b/fs/open.c index e6911101fe71..932e5a6de63b 100644 --- a/fs/open.c +++ b/fs/open.c @@ -81,14 +81,18 @@ long vfs_truncate(const struct path *path, loff_t length) if (!S_ISREG(inode->i_mode)) return -EINVAL; - error = mnt_want_write(path->mnt); - if (error) - goto out; - idmap = mnt_idmap(path->mnt); error = inode_permission(idmap, inode, MAY_WRITE); if (error) - goto mnt_drop_write_and_out; + return error; + + error = fsnotify_truncate_perm(path, length); + if (error) + return error; + + error = mnt_want_write(path->mnt); + if (error) + return error; error = -EPERM; if (IS_APPEND(inode)) @@ -114,7 +118,7 @@ put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); -out: + return error; } EXPORT_SYMBOL_GPL(vfs_truncate); @@ -175,11 +179,18 @@ long do_ftruncate(struct file *file, loff_t length, int small) /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(file))) return -EPERM; - sb_start_write(inode->i_sb); + error = security_file_truncate(file); - if (!error) - error = do_truncate(file_mnt_idmap(file), dentry, length, - ATTR_MTIME | ATTR_CTIME, file); + if (error) + return error; + + error = fsnotify_truncate_perm(&file->f_path, length); + if (error) + return error; + + sb_start_write(inode->i_sb); + error = do_truncate(file_mnt_idmap(file), dentry, length, + ATTR_MTIME | ATTR_CTIME, file); sb_end_write(inode->i_sb); return error; @@ -402,7 +413,6 @@ static bool access_need_override_creds(int flags) static const struct cred *access_override_creds(void) { - const struct cred *old_cred; struct cred *override_cred; override_cred = prepare_creds(); @@ -447,13 +457,7 @@ static const struct cred *access_override_creds(void) * freeing. */ override_cred->non_rcu = 1; - - old_cred = override_creds(override_cred); - - /* override_cred() gets its own ref */ - put_cred(override_cred); - - return old_cred; + return override_creds(override_cred); } static long do_faccessat(int dfd, const char __user *filename, int mode, int flags) @@ -523,7 +527,7 @@ out_path_release: } out: if (old_cred) - revert_creds(old_cred); + put_cred(revert_creds(old_cred)); return res; } @@ -901,7 +905,7 @@ static int do_dentry_open(struct file *f, f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { - f->f_mode = FMODE_PATH | FMODE_OPENED; + f->f_mode = FMODE_PATH | FMODE_OPENED | FMODE_NONOTIFY; f->f_op = &empty_fops; return 0; } @@ -929,6 +933,12 @@ static int do_dentry_open(struct file *f, if (error) goto cleanup_all; + /* + * Set FMODE_NONOTIFY_* bits according to existing permission watches. + * If FMODE_NONOTIFY was already set for an fanotify fd, this doesn't + * change anything. + */ + file_set_fsnotify_mode(f); error = fsnotify_open_perm(f); if (error) goto cleanup_all; @@ -1105,6 +1115,23 @@ struct file *dentry_open(const struct path *path, int flags, } EXPORT_SYMBOL(dentry_open); +struct file *dentry_open_nonotify(const struct path *path, int flags, + const struct cred *cred) +{ + struct file *f = alloc_empty_file(flags, cred); + if (!IS_ERR(f)) { + int error; + + f->f_mode |= FMODE_NONOTIFY; + error = vfs_open(path, f); + if (error) { + fput(f); + f = ERR_PTR(error); + } + } + return f; +} + /** * dentry_create - Create and open a file * @path: path to create @@ -1202,7 +1229,7 @@ inline struct open_how build_open_how(int flags, umode_t mode) inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; - u64 strip = __FMODE_NONOTIFY | O_CLOEXEC; + u64 strip = O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); @@ -1210,9 +1237,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) "struct open_flags doesn't yet handle flags > 32 bits"); /* - * Strip flags that either shouldn't be set by userspace like - * FMODE_NONOTIFY or that aren't relevant in determining struct - * open_flags like O_CLOEXEC. + * Strip flags that aren't relevant in determining struct open_flags. */ flags &= ~strip; @@ -1504,7 +1529,7 @@ static int filp_flush(struct file *filp, fl_owner_t id) { int retval = 0; - if (CHECK_DATA_CORRUPTION(file_count(filp) == 0, + if (CHECK_DATA_CORRUPTION(file_count(filp) == 0, filp, "VFS: Close: file count is 0 (f_op=%ps)", filp->f_op)) { return 0; diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c index 395a00ed8ac7..a19d1ad705db 100644 --- a/fs/orangefs/dcache.c +++ b/fs/orangefs/dcache.c @@ -13,10 +13,9 @@ #include "orangefs-kernel.h" /* Returns 1 if dentry can still be trusted, else 0. */ -static int orangefs_revalidate_lookup(struct dentry *dentry) +static int orangefs_revalidate_lookup(struct inode *parent_inode, const struct qstr *name, + struct dentry *dentry) { - struct dentry *parent_dentry = dget_parent(dentry); - struct inode *parent_inode = parent_dentry->d_inode; struct orangefs_inode_s *parent = ORANGEFS_I(parent_inode); struct inode *inode = dentry->d_inode; struct orangefs_kernel_op_s *new_op; @@ -26,14 +25,14 @@ static int orangefs_revalidate_lookup(struct dentry *dentry) gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: attempting lookup.\n", __func__); new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP); - if (!new_op) { - ret = -ENOMEM; - goto out_put_parent; - } + if (!new_op) + return -ENOMEM; new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW; new_op->upcall.req.lookup.parent_refn = parent->refn; - strscpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name); + /* op_alloc() leaves ->upcall zeroed */ + memcpy(new_op->upcall.req.lookup.d_name, name->name, + min(name->len, ORANGEFS_NAME_MAX - 1)); gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d interrupt flag [%d]\n", @@ -78,8 +77,6 @@ static int orangefs_revalidate_lookup(struct dentry *dentry) ret = 1; out_release_op: op_release(new_op); -out_put_parent: - dput(parent_dentry); return ret; out_drop: gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d revalidate failed\n", @@ -92,7 +89,8 @@ out_drop: * * Should return 1 if dentry can still be trusted, else 0. */ -static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags) +static int orangefs_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { int ret; unsigned long time = (unsigned long) dentry->d_fsdata; @@ -114,7 +112,7 @@ static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags) * If this passes, the positive dentry still exists or the negative * dentry still does not exist. */ - if (!orangefs_revalidate_lookup(dentry)) + if (!orangefs_revalidate_lookup(dir, name, dentry)) return 0; /* We do not need to continue with negative dentries. */ diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 1b508f543384..f52073022fae 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -206,8 +206,8 @@ static void orangefs_kernel_debug_init(void) pr_info("%s: overflow 1!\n", __func__); } - debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE, 0444, debug_dir, k_buffer, - &kernel_debug_fops); + debugfs_create_file_aux_num(ORANGEFS_KMOD_DEBUG_FILE, 0444, debug_dir, k_buffer, + 0, &kernel_debug_fops); } @@ -306,11 +306,10 @@ static void orangefs_client_debug_init(void) pr_info("%s: overflow! 2\n", __func__); } - client_debug_dentry = debugfs_create_file(ORANGEFS_CLIENT_DEBUG_FILE, - 0444, - debug_dir, - c_buffer, - &kernel_debug_fops); + client_debug_dentry = debugfs_create_file_aux_num( + ORANGEFS_CLIENT_DEBUG_FILE, + 0444, debug_dir, c_buffer, 1, + &kernel_debug_fops); } /* open ORANGEFS_KMOD_DEBUG_FILE or ORANGEFS_CLIENT_DEBUG_FILE.*/ @@ -393,9 +392,9 @@ static ssize_t orangefs_debug_write(struct file *file, * Thwart users who try to jamb a ridiculous number * of bytes into the debug file... */ - if (count > ORANGEFS_MAX_DEBUG_STRING_LEN + 1) { + if (count > ORANGEFS_MAX_DEBUG_STRING_LEN) { silly = count; - count = ORANGEFS_MAX_DEBUG_STRING_LEN + 1; + count = ORANGEFS_MAX_DEBUG_STRING_LEN; } buf = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL); @@ -418,8 +417,7 @@ static ssize_t orangefs_debug_write(struct file *file, * A service operation is required to set a new client-side * debug mask. */ - if (!strcmp(file->f_path.dentry->d_name.name, - ORANGEFS_KMOD_DEBUG_FILE)) { + if (!debugfs_get_aux_num(file)) { // kernel-debug debug_string_to_mask(buf, &orangefs_gossip_debug_mask, 0); debug_mask_to_string(&orangefs_gossip_debug_mask, 0); debug_string = kernel_debug_string; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 3601ddfeddc2..0c28e5fa3407 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -415,13 +415,13 @@ int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry, return err; } -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper) { struct ovl_fh *fh; int fh_type, dwords; int buflen = MAX_HANDLE_SZ; - uuid_t *uuid = &real->d_sb->s_uuid; + uuid_t *uuid = &realinode->i_sb->s_uuid; int err; /* Make sure the real fid stays 32bit aligned */ @@ -438,13 +438,13 @@ struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, * the price or reconnecting the dentry. */ dwords = buflen >> 2; - fh_type = exportfs_encode_fh(real, (void *)fh->fb.fid, &dwords, 0); + fh_type = exportfs_encode_inode_fh(realinode, (void *)fh->fb.fid, + &dwords, NULL, 0); buflen = (dwords << 2); err = -EIO; - if (WARN_ON(fh_type < 0) || - WARN_ON(buflen > MAX_HANDLE_SZ) || - WARN_ON(fh_type == FILEID_INVALID)) + if (fh_type < 0 || fh_type == FILEID_INVALID || + WARN_ON(buflen > MAX_HANDLE_SZ)) goto out_err; fh->fb.version = OVL_FH_VERSION; @@ -480,7 +480,7 @@ struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin) if (!ovl_can_decode_fh(origin->d_sb)) return NULL; - return ovl_encode_real_fh(ofs, origin, false); + return ovl_encode_real_fh(ofs, d_inode(origin), false); } int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, @@ -505,7 +505,7 @@ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper, const struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, upper, true); + fh = ovl_encode_real_fh(ofs, d_inode(upper), true); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 08e683917d12..c9993ff66fc2 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -575,12 +575,12 @@ static const struct cred *ovl_setup_cred_for_create(struct dentry *dentry, } /* - * Caller is going to match this with revert_creds_light() and drop + * Caller is going to match this with revert_creds() and drop * referenec on the returned creds. * We must be called with creator creds already, otherwise we risk * leaking creds. */ - old_cred = override_creds_light(override_cred); + old_cred = override_creds(override_cred); WARN_ON_ONCE(old_cred != ovl_creds(dentry->d_sb)); return override_cred; diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 5868cb222955..444aeeccb6da 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -176,35 +176,37 @@ static int ovl_connect_layer(struct dentry *dentry) * * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error. */ -static int ovl_check_encode_origin(struct dentry *dentry) +static int ovl_check_encode_origin(struct inode *inode) { - struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + struct ovl_fs *ofs = OVL_FS(inode->i_sb); bool decodable = ofs->config.nfs_export; + struct dentry *dentry; + int err; /* No upper layer? */ if (!ovl_upper_mnt(ofs)) return 1; /* Lower file handle for non-upper non-decodable */ - if (!ovl_dentry_upper(dentry) && !decodable) + if (!ovl_inode_upper(inode) && !decodable) return 1; /* Upper file handle for pure upper */ - if (!ovl_dentry_lower(dentry)) + if (!ovl_inode_lower(inode)) return 0; /* * Root is never indexed, so if there's an upper layer, encode upper for * root. */ - if (dentry == dentry->d_sb->s_root) + if (inode == d_inode(inode->i_sb->s_root)) return 0; /* * Upper decodable file handle for non-indexed upper. */ - if (ovl_dentry_upper(dentry) && decodable && - !ovl_test_flag(OVL_INDEX, d_inode(dentry))) + if (ovl_inode_upper(inode) && decodable && + !ovl_test_flag(OVL_INDEX, inode)) return 0; /* @@ -213,14 +215,23 @@ static int ovl_check_encode_origin(struct dentry *dentry) * ovl_connect_layer() will try to make origin's layer "connected" by * copying up a "connectable" ancestor. */ - if (d_is_dir(dentry) && decodable) - return ovl_connect_layer(dentry); + if (!decodable || !S_ISDIR(inode->i_mode)) + return 1; + + dentry = d_find_any_alias(inode); + if (!dentry) + return -ENOENT; + + err = ovl_connect_layer(dentry); + dput(dentry); + if (err < 0) + return err; /* Lower file handle for indexed and non-upper dir/non-dir */ return 1; } -static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, +static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct inode *inode, u32 *fid, int buflen) { struct ovl_fh *fh = NULL; @@ -231,13 +242,13 @@ static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, * Check if we should encode a lower or upper file handle and maybe * copy up an ancestor to make lower file handle connectable. */ - err = enc_lower = ovl_check_encode_origin(dentry); + err = enc_lower = ovl_check_encode_origin(inode); if (enc_lower < 0) goto fail; /* Encode an upper or lower file handle */ - fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_dentry_lower(dentry) : - ovl_dentry_upper(dentry), !enc_lower); + fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_inode_lower(inode) : + ovl_inode_upper(inode), !enc_lower); if (IS_ERR(fh)) return PTR_ERR(fh); @@ -251,8 +262,8 @@ out: return err; fail: - pr_warn_ratelimited("failed to encode file handle (%pd2, err=%i)\n", - dentry, err); + pr_warn_ratelimited("failed to encode file handle (ino=%lu, err=%i)\n", + inode->i_ino, err); goto out; } @@ -260,19 +271,13 @@ static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len, struct inode *parent) { struct ovl_fs *ofs = OVL_FS(inode->i_sb); - struct dentry *dentry; int bytes, buflen = *max_len << 2; /* TODO: encode connectable file handles */ if (parent) return FILEID_INVALID; - dentry = d_find_any_alias(inode); - if (!dentry) - return FILEID_INVALID; - - bytes = ovl_dentry_to_fid(ofs, dentry, fid, buflen); - dput(dentry); + bytes = ovl_dentry_to_fid(ofs, inode, fid, buflen); if (bytes <= 0) return FILEID_INVALID; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 7e27b7d4adee..be5c65d6f848 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -14,8 +14,6 @@ #include #include "overlayfs.h" -#include "../internal.h" /* for vfs_path_lookup */ - struct ovl_lookup_data { struct super_block *sb; const struct ovl_layer *layer; @@ -542,7 +540,7 @@ int ovl_verify_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, real, is_upper); + fh = ovl_encode_real_fh(ofs, d_inode(real), is_upper); err = PTR_ERR(fh); if (IS_ERR(fh)) { fh = NULL; @@ -738,7 +736,7 @@ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, origin, false); + fh = ovl_encode_real_fh(ofs, d_inode(origin), false); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index b361f35762be..0021e2025020 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -865,7 +865,7 @@ int ovl_copy_up_with_data(struct dentry *dentry); int ovl_maybe_copy_up(struct dentry *dentry, int flags); int ovl_copy_xattr(struct super_block *sb, const struct path *path, struct dentry *new); int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upper, struct kstat *stat); -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper); struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin); int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index fe511192f83c..86ae6f6da36b 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -91,7 +91,24 @@ static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak) if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE) ret = d->d_op->d_weak_revalidate(d, flags); } else if (d->d_flags & DCACHE_OP_REVALIDATE) { - ret = d->d_op->d_revalidate(d, flags); + struct dentry *parent; + struct inode *dir; + struct name_snapshot n; + + if (flags & LOOKUP_RCU) { + parent = READ_ONCE(d->d_parent); + dir = d_inode_rcu(parent); + if (!dir) + return -ECHILD; + } else { + parent = dget_parent(d); + dir = d_inode(parent); + } + take_dentry_name_snapshot(&n, d); + ret = d->d_op->d_revalidate(dir, &n.name, d, flags); + release_dentry_name_snapshot(&n); + if (!(flags & LOOKUP_RCU)) + dput(parent); if (!ret) { if (!(flags & LOOKUP_RCU)) d_invalidate(d); @@ -127,7 +144,8 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry, return ret; } -static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags) +static int ovl_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { return ovl_dentry_revalidate_common(dentry, flags, false); } diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 9aa7493b1e10..0819c739cc2f 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -65,12 +65,12 @@ const struct cred *ovl_override_creds(struct super_block *sb) { struct ovl_fs *ofs = OVL_FS(sb); - return override_creds_light(ofs->creator_cred); + return override_creds(ofs->creator_cred); } void ovl_revert_creds(const struct cred *old_cred) { - revert_creds_light(old_cred); + revert_creds(old_cred); } /* diff --git a/fs/pidfs.c b/fs/pidfs.c index 618abb1fa1b8..049352f973de 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include #include @@ -23,6 +24,97 @@ #include "internal.h" #include "mount.h" +static struct rb_root pidfs_ino_tree = RB_ROOT; + +#if BITS_PER_LONG == 32 +static inline unsigned long pidfs_ino(u64 ino) +{ + return lower_32_bits(ino); +} + +/* On 32 bit the generation number are the upper 32 bits. */ +static inline u32 pidfs_gen(u64 ino) +{ + return upper_32_bits(ino); +} + +#else + +/* On 64 bit simply return ino. */ +static inline unsigned long pidfs_ino(u64 ino) +{ + return ino; +} + +/* On 64 bit the generation number is 0. */ +static inline u32 pidfs_gen(u64 ino) +{ + return 0; +} +#endif + +static int pidfs_ino_cmp(struct rb_node *a, const struct rb_node *b) +{ + struct pid *pid_a = rb_entry(a, struct pid, pidfs_node); + struct pid *pid_b = rb_entry(b, struct pid, pidfs_node); + u64 pid_ino_a = pid_a->ino; + u64 pid_ino_b = pid_b->ino; + + if (pid_ino_a < pid_ino_b) + return -1; + if (pid_ino_a > pid_ino_b) + return 1; + return 0; +} + +void pidfs_add_pid(struct pid *pid) +{ + static u64 pidfs_ino_nr = 2; + + /* + * On 64 bit nothing special happens. The 64bit number assigned + * to struct pid is the inode number. + * + * On 32 bit the 64 bit number assigned to struct pid is split + * into two 32 bit numbers. The lower 32 bits are used as the + * inode number and the upper 32 bits are used as the inode + * generation number. + * + * On 32 bit pidfs_ino() will return the lower 32 bit. When + * pidfs_ino() returns zero a wrap around happened. When a + * wraparound happens the 64 bit number will be incremented by 2 + * so inode numbering starts at 2 again. + * + * On 64 bit comparing two pidfds is as simple as comparing + * inode numbers. + * + * When a wraparound happens on 32 bit multiple pidfds with the + * same inode number are likely to exist (This isn't a problem + * since before pidfs pidfds used the anonymous inode meaning + * all pidfds had the same inode number.). Userspace can + * reconstruct the 64 bit identifier by retrieving both the + * inode number and the inode generation number to compare or + * use file handles. + */ + if (pidfs_ino(pidfs_ino_nr) == 0) + pidfs_ino_nr += 2; + + pid->ino = pidfs_ino_nr; + pid->stashed = NULL; + pidfs_ino_nr++; + + write_seqcount_begin(&pidmap_lock_seq); + rb_find_add_rcu(&pid->pidfs_node, &pidfs_ino_tree, pidfs_ino_cmp); + write_seqcount_end(&pidmap_lock_seq); +} + +void pidfs_remove_pid(struct pid *pid) +{ + write_seqcount_begin(&pidmap_lock_seq); + rb_erase(&pid->pidfs_node, &pidfs_ino_tree); + write_seqcount_end(&pidmap_lock_seq); +} + #ifdef CONFIG_PROC_FS /** * pidfd_show_fdinfo - print information about a pidfd @@ -190,6 +282,27 @@ static long pidfd_info(struct task_struct *task, unsigned int cmd, unsigned long return 0; } +static bool pidfs_ioctl_valid(unsigned int cmd) +{ + switch (cmd) { + case FS_IOC_GETVERSION: + case PIDFD_GET_CGROUP_NAMESPACE: + case PIDFD_GET_INFO: + case PIDFD_GET_IPC_NAMESPACE: + case PIDFD_GET_MNT_NAMESPACE: + case PIDFD_GET_NET_NAMESPACE: + case PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE: + case PIDFD_GET_TIME_NAMESPACE: + case PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE: + case PIDFD_GET_UTS_NAMESPACE: + case PIDFD_GET_USER_NAMESPACE: + case PIDFD_GET_PID_NAMESPACE: + return true; + } + + return false; +} + static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct task_struct *task __free(put_task) = NULL; @@ -198,6 +311,17 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct ns_common *ns_common = NULL; struct pid_namespace *pid_ns; + if (!pidfs_ioctl_valid(cmd)) + return -ENOIOCTLCMD; + + if (cmd == FS_IOC_GETVERSION) { + if (!arg) + return -EINVAL; + + __u32 __user *argp = (__u32 __user *)arg; + return put_user(file_inode(file)->i_generation, argp); + } + task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; @@ -318,40 +442,6 @@ struct pid *pidfd_pid(const struct file *file) static struct vfsmount *pidfs_mnt __ro_after_init; -#if BITS_PER_LONG == 32 -/* - * Provide a fallback mechanism for 32-bit systems so processes remain - * reliably comparable by inode number even on those systems. - */ -static DEFINE_IDA(pidfd_inum_ida); - -static int pidfs_inum(struct pid *pid, unsigned long *ino) -{ - int ret; - - ret = ida_alloc_range(&pidfd_inum_ida, RESERVED_PIDS + 1, - UINT_MAX, GFP_ATOMIC); - if (ret < 0) - return -ENOSPC; - - *ino = ret; - return 0; -} - -static inline void pidfs_free_inum(unsigned long ino) -{ - if (ino > 0) - ida_free(&pidfd_inum_ida, ino); -} -#else -static inline int pidfs_inum(struct pid *pid, unsigned long *ino) -{ - *ino = pid->ino; - return 0; -} -#define pidfs_free_inum(ino) ((void)(ino)) -#endif - /* * The vfs falls back to simple_setattr() if i_op->setattr() isn't * implemented. Let's reject it completely until we have a clean @@ -403,7 +493,6 @@ static void pidfs_evict_inode(struct inode *inode) clear_inode(inode); put_pid(pid); - pidfs_free_inum(inode->i_ino); } static const struct super_operations pidfs_sops = { @@ -421,25 +510,149 @@ static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen) return dynamic_dname(buffer, buflen, "anon_inode:[pidfd]"); } -static const struct dentry_operations pidfs_dentry_operations = { +const struct dentry_operations pidfs_dentry_operations = { .d_delete = always_delete_dentry, .d_dname = pidfs_dname, .d_prune = stashed_dentry_prune, }; +static int pidfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, + struct inode *parent) +{ + const struct pid *pid = inode->i_private; + + if (*max_len < 2) { + *max_len = 2; + return FILEID_INVALID; + } + + *max_len = 2; + *(u64 *)fh = pid->ino; + return FILEID_KERNFS; +} + +static int pidfs_ino_find(const void *key, const struct rb_node *node) +{ + const u64 pid_ino = *(u64 *)key; + const struct pid *pid = rb_entry(node, struct pid, pidfs_node); + + if (pid_ino < pid->ino) + return -1; + if (pid_ino > pid->ino) + return 1; + return 0; +} + +/* Find a struct pid based on the inode number. */ +static struct pid *pidfs_ino_get_pid(u64 ino) +{ + struct pid *pid; + struct rb_node *node; + unsigned int seq; + + guard(rcu)(); + do { + seq = read_seqcount_begin(&pidmap_lock_seq); + node = rb_find_rcu(&ino, &pidfs_ino_tree, pidfs_ino_find); + if (node) + break; + } while (read_seqcount_retry(&pidmap_lock_seq, seq)); + + if (!node) + return NULL; + + pid = rb_entry(node, struct pid, pidfs_node); + + /* Within our pid namespace hierarchy? */ + if (pid_vnr(pid) == 0) + return NULL; + + return get_pid(pid); +} + +static struct dentry *pidfs_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, + int fh_type) +{ + int ret; + u64 pid_ino; + struct path path; + struct pid *pid; + + if (fh_len < 2) + return NULL; + + switch (fh_type) { + case FILEID_KERNFS: + pid_ino = *(u64 *)fid; + break; + default: + return NULL; + } + + pid = pidfs_ino_get_pid(pid_ino); + if (!pid) + return NULL; + + ret = path_from_stashed(&pid->stashed, pidfs_mnt, pid, &path); + if (ret < 0) + return ERR_PTR(ret); + + mntput(path.mnt); + return path.dentry; +} + +/* + * Make sure that we reject any nonsensical flags that users pass via + * open_by_handle_at(). Note that PIDFD_THREAD is defined as O_EXCL, and + * PIDFD_NONBLOCK as O_NONBLOCK. + */ +#define VALID_FILE_HANDLE_OPEN_FLAGS \ + (O_RDONLY | O_WRONLY | O_RDWR | O_NONBLOCK | O_CLOEXEC | O_EXCL) + +static int pidfs_export_permission(struct handle_to_path_ctx *ctx, + unsigned int oflags) +{ + if (oflags & ~(VALID_FILE_HANDLE_OPEN_FLAGS | O_LARGEFILE)) + return -EINVAL; + + /* + * pidfd_ino_get_pid() will verify that the struct pid is part + * of the caller's pid namespace hierarchy. No further + * permission checks are needed. + */ + return 0; +} + +static struct file *pidfs_export_open(struct path *path, unsigned int oflags) +{ + /* + * Clear O_LARGEFILE as open_by_handle_at() forces it and raise + * O_RDWR as pidfds always are. + */ + oflags &= ~O_LARGEFILE; + return dentry_open(path, oflags | O_RDWR, current_cred()); +} + +static const struct export_operations pidfs_export_operations = { + .encode_fh = pidfs_encode_fh, + .fh_to_dentry = pidfs_fh_to_dentry, + .open = pidfs_export_open, + .permission = pidfs_export_permission, +}; + static int pidfs_init_inode(struct inode *inode, void *data) { + const struct pid *pid = data; + inode->i_private = data; inode->i_flags |= S_PRIVATE; inode->i_mode |= S_IRWXU; inode->i_op = &pidfs_inode_operations; inode->i_fop = &pidfs_file_operations; - /* - * Inode numbering for pidfs start at RESERVED_PIDS + 1. This - * avoids collisions with the root inode which is 1 for pseudo - * filesystems. - */ - return pidfs_inum(data, &inode->i_ino); + inode->i_ino = pidfs_ino(pid->ino); + inode->i_generation = pidfs_gen(pid->ino); + return 0; } static void pidfs_put_data(void *data) @@ -462,6 +675,7 @@ static int pidfs_init_fs_context(struct fs_context *fc) return -ENOMEM; ctx->ops = &pidfs_sops; + ctx->eops = &pidfs_export_operations; ctx->dops = &pidfs_dentry_operations; fc->s_fs_info = (void *)&pidfs_stashed_ops; return 0; diff --git a/fs/pipe.c b/fs/pipe.c index 12b22c2723b7..94b59045ab44 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -253,7 +253,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; - bool was_full, wake_next_reader = false; + bool wake_writer = false, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ @@ -264,14 +264,13 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) mutex_lock(&pipe->mutex); /* - * We only wake up writers if the pipe was full when we started - * reading in order to avoid unnecessary wakeups. + * We only wake up writers if the pipe was full when we started reading + * and it is no longer full after reading to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ - was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); @@ -340,8 +339,10 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) buf->len = 0; } - if (!buf->len) + if (!buf->len) { + wake_writer |= pipe_full(head, tail, pipe->max_usage); tail = pipe_update_tail(pipe, buf, tail); + } total_len -= chars; if (!total_len) break; /* common path: read succeeded */ @@ -377,7 +378,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) * _very_ unlikely case that the pipe was full, but we got * no data. */ - if (unlikely(was_full)) + if (unlikely(wake_writer)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); @@ -390,15 +391,15 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; - mutex_lock(&pipe->mutex); - was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); + wake_writer = false; wake_next_reader = true; + mutex_lock(&pipe->mutex); } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); - if (was_full) + if (wake_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); @@ -1477,7 +1478,7 @@ static int proc_dopipe_max_size(const struct ctl_table *table, int write, do_proc_dopipe_max_size_conv, NULL); } -static struct ctl_table fs_pipe_sysctls[] = { +static const struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, diff --git a/fs/pnode.c b/fs/pnode.c index a799e0315cc9..ef048f008bdd 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -611,10 +611,10 @@ int propagate_umount(struct list_head *list) continue; } else if (child->mnt.mnt_flags & MNT_UMOUNT) { /* - * We have come accross an partially unmounted - * mount in list that has not been visited yet. - * Remember it has been visited and continue - * about our merry way. + * We have come across a partially unmounted + * mount in a list that has not been visited + * yet. Remember it has been visited and + * continue about our merry way. */ list_add_tail(&child->mnt_umounting, &visited); continue; diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index d80a1431ef7b..6ae966c561e7 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -61,6 +61,25 @@ config PROC_VMCORE_DEVICE_DUMP as ELF notes to /proc/vmcore. You can still disable device dump using the kernel command line option 'novmcoredd'. +config NEED_PROC_VMCORE_DEVICE_RAM + bool + +config PROC_VMCORE_DEVICE_RAM + def_bool y + depends on PROC_VMCORE && NEED_PROC_VMCORE_DEVICE_RAM + depends on VIRTIO_MEM + help + If the elfcore hdr is allocated and prepared by the dump kernel + ("2nd kernel") instead of the crashed kernel, RAM provided by memory + devices such as virtio-mem will not be included in the dump + image, because only the device driver can properly detect them. + + With this config enabled, these RAM ranges will be queried from the + device drivers once the device gets probed, so they can be included + in the crash dump. + + Relevant architectures should select NEED_PROC_VMCORE_DEVICE_RAM. + config PROC_SYSCTL bool "Sysctl support (/proc/sys)" if EXPERT depends on PROC_FS diff --git a/fs/proc/array.c b/fs/proc/array.c index 55ed3510d2bb..d6a0369caa93 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -500,7 +500,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * a program is not able to use ptrace(2) in that case. It is * safe because the task has stopped executing permanently. */ - if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) { + if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE|PF_POSTCOREDUMP))) { if (try_get_task_stack(task)) { eip = KSTK_EIP(task); esp = KSTK_ESP(task); diff --git a/fs/proc/base.c b/fs/proc/base.c index 0edf14a9840e..cd89e956c322 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2058,7 +2058,8 @@ void pid_update_inode(struct task_struct *task, struct inode *inode) * performed a setuid(), etc. * */ -static int pid_revalidate(struct dentry *dentry, unsigned int flags) +static int pid_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; @@ -2191,7 +2192,8 @@ static int dname_to_vma_addr(struct dentry *dentry, return 0; } -static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) +static int map_files_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; bool exact_vma_exists = false; @@ -3269,6 +3271,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm; + int ret = 0; mm = get_task_mm(task); if (mm) { @@ -3276,6 +3279,16 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm)); seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); + seq_printf(m, "ksm_merge_any: %s\n", + test_bit(MMF_VM_MERGE_ANY, &mm->flags) ? "yes" : "no"); + ret = mmap_read_lock_killable(mm); + if (ret) { + mmput(mm); + return ret; + } + seq_printf(m, "ksm_mergeable: %s\n", + ksm_process_mergeable(mm) ? "yes" : "no"); + mmap_read_unlock(mm); mmput(mm); } diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 24baf23e864f..37aa778d1af7 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -140,7 +140,8 @@ static void tid_fd_update_inode(struct task_struct *task, struct inode *inode, security_task_to_inode(task, inode); } -static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) +static int tid_fd_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct task_struct *task; struct inode *inode; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index dbe82cf23ee4..8ec90826a49e 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -216,7 +216,8 @@ void proc_free_inum(unsigned int inum) ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); } -static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags) +static int proc_misc_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; @@ -343,7 +344,8 @@ static const struct file_operations proc_dir_operations = { .iterate_shared = proc_readdir, }; -static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) +static int proc_net_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { return 0; } diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e376f48c4b8b..1cb33771bf9f 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -65,7 +65,11 @@ static inline void kc_unxlate_dev_mem_ptr(phys_addr_t phys, void *virt) #endif static LIST_HEAD(kclist_head); -static DECLARE_RWSEM(kclist_lock); +static int kcore_nphdr; +static size_t kcore_phdrs_len; +static size_t kcore_notes_len; +static size_t kcore_data_offset; +DEFINE_STATIC_PERCPU_RWSEM(kclist_lock); static int kcore_need_update = 1; /* @@ -101,33 +105,32 @@ void __init kclist_add(struct kcore_list *new, void *addr, size_t size, list_add_tail(&new->list, &kclist_head); } -static size_t get_kcore_size(int *nphdr, size_t *phdrs_len, size_t *notes_len, - size_t *data_offset) +static void update_kcore_size(void) { size_t try, size; struct kcore_list *m; - *nphdr = 1; /* PT_NOTE */ + kcore_nphdr = 1; /* PT_NOTE */ size = 0; list_for_each_entry(m, &kclist_head, list) { try = kc_vaddr_to_offset((size_t)m->addr + m->size); if (try > size) size = try; - *nphdr = *nphdr + 1; + kcore_nphdr++; } - *phdrs_len = *nphdr * sizeof(struct elf_phdr); - *notes_len = (4 * sizeof(struct elf_note) + - 3 * ALIGN(sizeof(CORE_STR), 4) + - VMCOREINFO_NOTE_NAME_BYTES + - ALIGN(sizeof(struct elf_prstatus), 4) + - ALIGN(sizeof(struct elf_prpsinfo), 4) + - ALIGN(arch_task_struct_size, 4) + - ALIGN(vmcoreinfo_size, 4)); - *data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + *phdrs_len + - *notes_len); - return *data_offset + size; + kcore_phdrs_len = kcore_nphdr * sizeof(struct elf_phdr); + kcore_notes_len = (4 * sizeof(struct elf_note) + + 3 * ALIGN(sizeof(CORE_STR), 4) + + VMCOREINFO_NOTE_NAME_BYTES + + ALIGN(sizeof(struct elf_prstatus), 4) + + ALIGN(sizeof(struct elf_prpsinfo), 4) + + ALIGN(arch_task_struct_size, 4) + + ALIGN(vmcoreinfo_size, 4)); + kcore_data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + kcore_phdrs_len + + kcore_notes_len); + proc_root_kcore->size = kcore_data_offset + size; } #ifdef CONFIG_HIGHMEM @@ -270,12 +273,10 @@ static int kcore_update_ram(void) { LIST_HEAD(list); LIST_HEAD(garbage); - int nphdr; - size_t phdrs_len, notes_len, data_offset; struct kcore_list *tmp, *pos; int ret = 0; - down_write(&kclist_lock); + percpu_down_write(&kclist_lock); if (!xchg(&kcore_need_update, 0)) goto out; @@ -293,11 +294,10 @@ static int kcore_update_ram(void) } list_splice_tail(&list, &kclist_head); - proc_root_kcore->size = get_kcore_size(&nphdr, &phdrs_len, ¬es_len, - &data_offset); + update_kcore_size(); out: - up_write(&kclist_lock); + percpu_up_write(&kclist_lock); list_for_each_entry_safe(pos, tmp, &garbage, list) { list_del(&pos->list); kfree(pos); @@ -326,27 +326,24 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) struct file *file = iocb->ki_filp; char *buf = file->private_data; loff_t *fpos = &iocb->ki_pos; - size_t phdrs_offset, notes_offset, data_offset; + size_t phdrs_offset, notes_offset; size_t page_offline_frozen = 1; - size_t phdrs_len, notes_len; struct kcore_list *m; size_t tsz; - int nphdr; unsigned long start; size_t buflen = iov_iter_count(iter); size_t orig_buflen = buflen; int ret = 0; - down_read(&kclist_lock); + percpu_down_read(&kclist_lock); /* * Don't race against drivers that set PageOffline() and expect no * further page access. */ page_offline_freeze(); - get_kcore_size(&nphdr, &phdrs_len, ¬es_len, &data_offset); phdrs_offset = sizeof(struct elfhdr); - notes_offset = phdrs_offset + phdrs_len; + notes_offset = phdrs_offset + kcore_phdrs_len; /* ELF file header. */ if (buflen && *fpos < sizeof(struct elfhdr)) { @@ -368,7 +365,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) .e_flags = ELF_CORE_EFLAGS, .e_ehsize = sizeof(struct elfhdr), .e_phentsize = sizeof(struct elf_phdr), - .e_phnum = nphdr, + .e_phnum = kcore_nphdr, }; tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos); @@ -382,10 +379,10 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) } /* ELF program headers. */ - if (buflen && *fpos < phdrs_offset + phdrs_len) { + if (buflen && *fpos < phdrs_offset + kcore_phdrs_len) { struct elf_phdr *phdrs, *phdr; - phdrs = kzalloc(phdrs_len, GFP_KERNEL); + phdrs = kzalloc(kcore_phdrs_len, GFP_KERNEL); if (!phdrs) { ret = -ENOMEM; goto out; @@ -393,13 +390,14 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) phdrs[0].p_type = PT_NOTE; phdrs[0].p_offset = notes_offset; - phdrs[0].p_filesz = notes_len; + phdrs[0].p_filesz = kcore_notes_len; phdr = &phdrs[1]; list_for_each_entry(m, &kclist_head, list) { phdr->p_type = PT_LOAD; phdr->p_flags = PF_R | PF_W | PF_X; - phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset; + phdr->p_offset = kc_vaddr_to_offset(m->addr) + + kcore_data_offset; phdr->p_vaddr = (size_t)m->addr; if (m->type == KCORE_RAM) phdr->p_paddr = __pa(m->addr); @@ -412,7 +410,8 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) phdr++; } - tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos); + tsz = min_t(size_t, buflen, + phdrs_offset + kcore_phdrs_len - *fpos); if (copy_to_iter((char *)phdrs + *fpos - phdrs_offset, tsz, iter) != tsz) { kfree(phdrs); @@ -426,7 +425,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) } /* ELF note segment. */ - if (buflen && *fpos < notes_offset + notes_len) { + if (buflen && *fpos < notes_offset + kcore_notes_len) { struct elf_prstatus prstatus = {}; struct elf_prpsinfo prpsinfo = { .pr_sname = 'R', @@ -438,7 +437,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) strscpy(prpsinfo.pr_psargs, saved_command_line, sizeof(prpsinfo.pr_psargs)); - notes = kzalloc(notes_len, GFP_KERNEL); + notes = kzalloc(kcore_notes_len, GFP_KERNEL); if (!notes) { ret = -ENOMEM; goto out; @@ -459,9 +458,10 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) */ append_kcore_note(notes, &i, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, - min(vmcoreinfo_size, notes_len - i)); + min(vmcoreinfo_size, kcore_notes_len - i)); - tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos); + tsz = min_t(size_t, buflen, + notes_offset + kcore_notes_len - *fpos); if (copy_to_iter(notes + *fpos - notes_offset, tsz, iter) != tsz) { kfree(notes); ret = -EFAULT; @@ -477,7 +477,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) * Check to see if our file offset matches with any of * the addresses in the elf_phdr on our list. */ - start = kc_offset_to_vaddr(*fpos - data_offset); + start = kc_offset_to_vaddr(*fpos - kcore_data_offset); if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen) tsz = buflen; @@ -626,7 +626,7 @@ skip: out: page_offline_thaw(); - up_read(&kclist_lock); + percpu_up_read(&kclist_lock); if (ret) return ret; return orig_buflen - buflen; @@ -663,6 +663,7 @@ static int release_kcore(struct inode *inode, struct file *file) } static const struct proc_ops kcore_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_read_iter = read_kcore_iter, .proc_open = open_kcore, .proc_release = release_kcore, diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 8e159fc78c0a..c610224faf10 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -83,7 +83,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { res = ns_get_name(name, sizeof(name), task, ns_ops); if (res >= 0) - res = readlink_copy(buffer, buflen, name); + res = readlink_copy(buffer, buflen, name, strlen(name)); } put_task_struct(task); return res; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 27a283d85a6e..cc9d74a06ff0 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -884,7 +884,8 @@ static const struct inode_operations proc_sys_dir_operations = { .getattr = proc_sys_getattr, }; -static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags) +static int proc_sys_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 38a5a3e9cba2..f02cd362309a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1810,7 +1810,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, } for (; addr != end; addr += PAGE_SIZE, idx++) { - unsigned long cur_flags = flags; + u64 cur_flags = flags; pagemap_entry_t pme; if (folio && (flags & PM_PRESENT) && diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 3d8a82cee63e..a00120a3c099 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -8,6 +8,8 @@ * */ +#define pr_fmt(fmt) "vmcore: " fmt + #include #include #include @@ -51,9 +53,14 @@ static u64 vmcore_size; static struct proc_dir_entry *proc_vmcore; #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP +struct vmcoredd_node { + struct list_head list; /* List of dumps */ + void *buf; /* Buffer containing device's dump */ + unsigned int size; /* Size of the buffer */ +}; + /* Device Dump list and mutex to synchronize access to list */ static LIST_HEAD(vmcoredd_list); -static DEFINE_MUTEX(vmcoredd_mutex); static bool vmcoredd_disabled; core_param(novmcoredd, vmcoredd_disabled, bool, 0); @@ -62,17 +69,22 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0); /* Device Dump Size */ static size_t vmcoredd_orig_sz; -static DEFINE_SPINLOCK(vmcore_cb_lock); +static DEFINE_MUTEX(vmcore_mutex); + DEFINE_STATIC_SRCU(vmcore_cb_srcu); /* List of registered vmcore callbacks. */ static LIST_HEAD(vmcore_cb_list); /* Whether the vmcore has been opened once. */ static bool vmcore_opened; +/* Whether the vmcore is currently open. */ +static unsigned int vmcore_open; + +static void vmcore_process_device_ram(struct vmcore_cb *cb); void register_vmcore_cb(struct vmcore_cb *cb) { INIT_LIST_HEAD(&cb->next); - spin_lock(&vmcore_cb_lock); + mutex_lock(&vmcore_mutex); list_add_tail(&cb->next, &vmcore_cb_list); /* * Registering a vmcore callback after the vmcore was opened is @@ -80,13 +92,15 @@ void register_vmcore_cb(struct vmcore_cb *cb) */ if (vmcore_opened) pr_warn_once("Unexpected vmcore callback registration\n"); - spin_unlock(&vmcore_cb_lock); + if (!vmcore_open && cb->get_device_ram) + vmcore_process_device_ram(cb); + mutex_unlock(&vmcore_mutex); } EXPORT_SYMBOL_GPL(register_vmcore_cb); void unregister_vmcore_cb(struct vmcore_cb *cb) { - spin_lock(&vmcore_cb_lock); + mutex_lock(&vmcore_mutex); list_del_rcu(&cb->next); /* * Unregistering a vmcore callback after the vmcore was opened is @@ -95,7 +109,7 @@ void unregister_vmcore_cb(struct vmcore_cb *cb) */ if (vmcore_opened) pr_warn_once("Unexpected vmcore callback unregistration\n"); - spin_unlock(&vmcore_cb_lock); + mutex_unlock(&vmcore_mutex); synchronize_srcu(&vmcore_cb_srcu); } @@ -120,9 +134,23 @@ static bool pfn_is_ram(unsigned long pfn) static int open_vmcore(struct inode *inode, struct file *file) { - spin_lock(&vmcore_cb_lock); + mutex_lock(&vmcore_mutex); vmcore_opened = true; - spin_unlock(&vmcore_cb_lock); + if (vmcore_open + 1 == 0) { + mutex_unlock(&vmcore_mutex); + return -EBUSY; + } + vmcore_open++; + mutex_unlock(&vmcore_mutex); + + return 0; +} + +static int release_vmcore(struct inode *inode, struct file *file) +{ + mutex_lock(&vmcore_mutex); + vmcore_open--; + mutex_unlock(&vmcore_mutex); return 0; } @@ -243,33 +271,27 @@ static int vmcoredd_copy_dumps(struct iov_iter *iter, u64 start, size_t size) { struct vmcoredd_node *dump; u64 offset = 0; - int ret = 0; size_t tsz; char *buf; - mutex_lock(&vmcoredd_mutex); list_for_each_entry(dump, &vmcoredd_list, list) { if (start < offset + dump->size) { tsz = min(offset + (u64)dump->size - start, (u64)size); buf = dump->buf + start - offset; - if (copy_to_iter(buf, tsz, iter) < tsz) { - ret = -EFAULT; - goto out_unlock; - } + if (copy_to_iter(buf, tsz, iter) < tsz) + return -EFAULT; size -= tsz; start += tsz; /* Leave now if buffer filled already */ if (!size) - goto out_unlock; + return 0; } offset += dump->size; } -out_unlock: - mutex_unlock(&vmcoredd_mutex); - return ret; + return 0; } #ifdef CONFIG_MMU @@ -278,20 +300,16 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst, { struct vmcoredd_node *dump; u64 offset = 0; - int ret = 0; size_t tsz; char *buf; - mutex_lock(&vmcoredd_mutex); list_for_each_entry(dump, &vmcoredd_list, list) { if (start < offset + dump->size) { tsz = min(offset + (u64)dump->size - start, (u64)size); buf = dump->buf + start - offset; if (remap_vmalloc_range_partial(vma, dst, buf, 0, - tsz)) { - ret = -EFAULT; - goto out_unlock; - } + tsz)) + return -EFAULT; size -= tsz; start += tsz; @@ -299,14 +317,12 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst, /* Leave now if buffer filled already */ if (!size) - goto out_unlock; + return 0; } offset += dump->size; } -out_unlock: - mutex_unlock(&vmcoredd_mutex); - return ret; + return 0; } #endif /* CONFIG_MMU */ #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ @@ -316,10 +332,10 @@ out_unlock: */ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) { + struct vmcore_range *m = NULL; ssize_t acc = 0, tmp; size_t tsz; u64 start; - struct vmcore *m = NULL; if (!iov_iter_count(iter) || *fpos >= vmcore_size) return 0; @@ -404,6 +420,8 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) if (!iov_iter_count(iter)) return acc; } + + cond_resched(); } return acc; @@ -574,7 +592,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) { size_t size = vma->vm_end - vma->vm_start; u64 start, end, len, tsz; - struct vmcore *m; + struct vmcore_range *m; start = (u64)vma->vm_pgoff << PAGE_SHIFT; end = start + size; @@ -691,21 +709,17 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) static const struct proc_ops vmcore_proc_ops = { .proc_open = open_vmcore, + .proc_release = release_vmcore, .proc_read_iter = read_vmcore, .proc_lseek = default_llseek, .proc_mmap = mmap_vmcore, }; -static struct vmcore* __init get_new_element(void) -{ - return kzalloc(sizeof(struct vmcore), GFP_KERNEL); -} - static u64 get_vmcore_size(size_t elfsz, size_t elfnotesegsz, struct list_head *vc_list) { + struct vmcore_range *m; u64 size; - struct vmcore *m; size = elfsz + elfnotesegsz; list_for_each_entry(m, vc_list, list) { @@ -1107,7 +1121,6 @@ static int __init process_ptload_program_headers_elf64(char *elfptr, Elf64_Ehdr *ehdr_ptr; Elf64_Phdr *phdr_ptr; loff_t vmcore_off; - struct vmcore *new; ehdr_ptr = (Elf64_Ehdr *)elfptr; phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */ @@ -1126,13 +1139,8 @@ static int __init process_ptload_program_headers_elf64(char *elfptr, end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE); size = end - start; - /* Add this contiguous chunk of memory to vmcore list.*/ - new = get_new_element(); - if (!new) + if (vmcore_alloc_add_range(vc_list, start, size)) return -ENOMEM; - new->paddr = start; - new->size = size; - list_add_tail(&new->list, vc_list); /* Update the program header offset. */ phdr_ptr->p_offset = vmcore_off + (paddr - start); @@ -1150,7 +1158,6 @@ static int __init process_ptload_program_headers_elf32(char *elfptr, Elf32_Ehdr *ehdr_ptr; Elf32_Phdr *phdr_ptr; loff_t vmcore_off; - struct vmcore *new; ehdr_ptr = (Elf32_Ehdr *)elfptr; phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */ @@ -1169,13 +1176,8 @@ static int __init process_ptload_program_headers_elf32(char *elfptr, end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE); size = end - start; - /* Add this contiguous chunk of memory to vmcore list.*/ - new = get_new_element(); - if (!new) + if (vmcore_alloc_add_range(vc_list, start, size)) return -ENOMEM; - new->paddr = start; - new->size = size; - list_add_tail(&new->list, vc_list); /* Update the program header offset */ phdr_ptr->p_offset = vmcore_off + (paddr - start); @@ -1188,8 +1190,8 @@ static int __init process_ptload_program_headers_elf32(char *elfptr, static void set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz, struct list_head *vc_list) { + struct vmcore_range *m; loff_t vmcore_off; - struct vmcore *m; /* Skip ELF header, program headers and ELF note segment. */ vmcore_off = elfsz + elfnotes_sz; @@ -1516,12 +1518,18 @@ int vmcore_add_device_dump(struct vmcoredd_data *data) dump->buf = buf; dump->size = data_size; - /* Add the dump to driver sysfs list */ - mutex_lock(&vmcoredd_mutex); - list_add_tail(&dump->list, &vmcoredd_list); - mutex_unlock(&vmcoredd_mutex); + /* Add the dump to driver sysfs list and update the elfcore hdr */ + mutex_lock(&vmcore_mutex); + if (vmcore_opened) + pr_warn_once("Unexpected adding of device dump\n"); + if (vmcore_open) { + ret = -EBUSY; + goto out_err; + } + list_add_tail(&dump->list, &vmcoredd_list); vmcoredd_update_size(data_size); + mutex_unlock(&vmcore_mutex); return 0; out_err: @@ -1533,11 +1541,163 @@ out_err: EXPORT_SYMBOL(vmcore_add_device_dump); #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ +#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM +static int vmcore_realloc_elfcore_buffer_elf64(size_t new_size) +{ + char *elfcorebuf_new; + + if (WARN_ON_ONCE(new_size < elfcorebuf_sz)) + return -EINVAL; + if (get_order(elfcorebuf_sz_orig) == get_order(new_size)) { + elfcorebuf_sz_orig = new_size; + return 0; + } + + elfcorebuf_new = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(new_size)); + if (!elfcorebuf_new) + return -ENOMEM; + memcpy(elfcorebuf_new, elfcorebuf, elfcorebuf_sz); + free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig)); + elfcorebuf = elfcorebuf_new; + elfcorebuf_sz_orig = new_size; + return 0; +} + +static void vmcore_reset_offsets_elf64(void) +{ + Elf64_Phdr *phdr_start = (Elf64_Phdr *)(elfcorebuf + sizeof(Elf64_Ehdr)); + loff_t vmcore_off = elfcorebuf_sz + elfnotes_sz; + Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfcorebuf; + Elf64_Phdr *phdr; + int i; + + for (i = 0, phdr = phdr_start; i < ehdr->e_phnum; i++, phdr++) { + u64 start, end; + + /* + * After merge_note_headers_elf64() we should only have a single + * PT_NOTE entry that starts immediately after elfcorebuf_sz. + */ + if (phdr->p_type == PT_NOTE) { + phdr->p_offset = elfcorebuf_sz; + continue; + } + + start = rounddown(phdr->p_offset, PAGE_SIZE); + end = roundup(phdr->p_offset + phdr->p_memsz, PAGE_SIZE); + phdr->p_offset = vmcore_off + (phdr->p_offset - start); + vmcore_off = vmcore_off + end - start; + } + set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list); +} + +static int vmcore_add_device_ram_elf64(struct list_head *list, size_t count) +{ + Elf64_Phdr *phdr_start = (Elf64_Phdr *)(elfcorebuf + sizeof(Elf64_Ehdr)); + Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfcorebuf; + struct vmcore_range *cur; + Elf64_Phdr *phdr; + size_t new_size; + int rc; + + if ((Elf32_Half)(ehdr->e_phnum + count) != ehdr->e_phnum + count) { + pr_err("too many device ram ranges\n"); + return -ENOSPC; + } + + /* elfcorebuf_sz must always cover full pages. */ + new_size = sizeof(Elf64_Ehdr) + + (ehdr->e_phnum + count) * sizeof(Elf64_Phdr); + new_size = roundup(new_size, PAGE_SIZE); + + /* + * Make sure we have sufficient space to include the new PT_LOAD + * entries. + */ + rc = vmcore_realloc_elfcore_buffer_elf64(new_size); + if (rc) { + pr_err("resizing elfcore failed\n"); + return rc; + } + + /* Modify our used elfcore buffer size to cover the new entries. */ + elfcorebuf_sz = new_size; + + /* Fill the added PT_LOAD entries. */ + phdr = phdr_start + ehdr->e_phnum; + list_for_each_entry(cur, list, list) { + WARN_ON_ONCE(!IS_ALIGNED(cur->paddr | cur->size, PAGE_SIZE)); + elfcorehdr_fill_device_ram_ptload_elf64(phdr, cur->paddr, cur->size); + + /* p_offset will be adjusted later. */ + phdr++; + ehdr->e_phnum++; + } + list_splice_tail(list, &vmcore_list); + + /* We changed elfcorebuf_sz and added new entries; reset all offsets. */ + vmcore_reset_offsets_elf64(); + + /* Finally, recalculate the total vmcore size. */ + vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz, + &vmcore_list); + proc_vmcore->size = vmcore_size; + return 0; +} + +static void vmcore_process_device_ram(struct vmcore_cb *cb) +{ + unsigned char *e_ident = (unsigned char *)elfcorebuf; + struct vmcore_range *first, *m; + LIST_HEAD(list); + int count; + + /* We only support Elf64 dumps for now. */ + if (WARN_ON_ONCE(e_ident[EI_CLASS] != ELFCLASS64)) { + pr_err("device ram ranges only support Elf64\n"); + return; + } + + if (cb->get_device_ram(cb, &list)) { + pr_err("obtaining device ram ranges failed\n"); + return; + } + count = list_count_nodes(&list); + if (!count) + return; + + /* + * For some reason these ranges are already know? Might happen + * with unusual register->unregister->register sequences; we'll simply + * sanity check using the first range. + */ + first = list_first_entry(&list, struct vmcore_range, list); + list_for_each_entry(m, &vmcore_list, list) { + unsigned long long m_end = m->paddr + m->size; + unsigned long long first_end = first->paddr + first->size; + + if (first->paddr < m_end && m->paddr < first_end) + goto out_free; + } + + /* If adding the mem nodes succeeds, they must not be freed. */ + if (!vmcore_add_device_ram_elf64(&list, count)) + return; +out_free: + vmcore_free_ranges(&list); +} +#else /* !CONFIG_PROC_VMCORE_DEVICE_RAM */ +static void vmcore_process_device_ram(struct vmcore_cb *cb) +{ +} +#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */ + /* Free all dumps in vmcore device dump list */ static void vmcore_free_device_dumps(void) { #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP - mutex_lock(&vmcoredd_mutex); + mutex_lock(&vmcore_mutex); while (!list_empty(&vmcoredd_list)) { struct vmcoredd_node *dump; @@ -1547,7 +1707,7 @@ static void vmcore_free_device_dumps(void) vfree(dump->buf); vfree(dump); } - mutex_unlock(&vmcoredd_mutex); + mutex_unlock(&vmcore_mutex); #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ } @@ -1569,7 +1729,7 @@ static int __init vmcore_init(void) rc = parse_crash_elf_headers(); if (rc) { elfcorehdr_free(elfcorehdr_addr); - pr_warn("Kdump: vmcore not initialized\n"); + pr_warn("not initialized\n"); return rc; } elfcorehdr_free(elfcorehdr_addr); @@ -1590,14 +1750,7 @@ void vmcore_cleanup(void) proc_vmcore = NULL; } - /* clear the vmcore list. */ - while (!list_empty(&vmcore_list)) { - struct vmcore *m; - - m = list_first_entry(&vmcore_list, struct vmcore, list); - list_del(&m->list); - kfree(m); - } + vmcore_free_ranges(&vmcore_list); free_elfcorebuf(); /* clear vmcore device dump list */ diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c index 65b2473e22ff..fa6b8cb788a1 100644 --- a/fs/pstore/blk.c +++ b/fs/pstore/blk.c @@ -89,7 +89,7 @@ static struct pstore_device_info *pstore_device_info; _##name_ = check_size(name, alignsize); \ else \ _##name_ = 0; \ - /* Synchronize module parameters with resuls. */ \ + /* Synchronize module parameters with results. */ \ name = _##name_ / 1024; \ dev->zone.name = _##name_; \ } @@ -121,7 +121,7 @@ static int __register_pstore_device(struct pstore_device_info *dev) if (pstore_device_info) return -EBUSY; - /* zero means not limit on which backends to attempt to store. */ + /* zero means no limit on which backends attempt to store. */ if (!dev->flags) dev->flags = UINT_MAX; diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c index 694db616663f..ceb5639a0629 100644 --- a/fs/pstore/zone.c +++ b/fs/pstore/zone.c @@ -1212,6 +1212,11 @@ static struct pstore_zone **psz_init_zones(enum pstore_type_id type, } c = total_size / record_size; + if (unlikely(!c)) { + pr_err("zone %s total_size too small\n", name); + return ERR_PTR(-EINVAL); + } + zones = kcalloc(c, sizeof(*zones), GFP_KERNEL); if (!zones) { pr_err("allocate for zones %s failed\n", name); diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 85925ec0051a..3310d1ad4d0e 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -179,8 +179,7 @@ static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf) */ static const char *qnx6_checkroot(struct super_block *s) { - static char match_root[2][3] = {".\0\0", "..\0"}; - int i, error = 0; + int error = 0; struct qnx6_dir_entry *dir_entry; struct inode *root = d_inode(s->s_root); struct address_space *mapping = root->i_mapping; @@ -189,11 +188,9 @@ static const char *qnx6_checkroot(struct super_block *s) if (IS_ERR(folio)) return "error reading root directory"; dir_entry = kmap_local_folio(folio, 0); - for (i = 0; i < 2; i++) { - /* maximum 3 bytes - due to match_root limitation */ - if (strncmp(dir_entry[i].de_fname, match_root[i], 3)) - error = 1; - } + if (memcmp(dir_entry[0].de_fname, ".", 2) || + memcmp(dir_entry[1].de_fname, "..", 3)) + error = 1; folio_release_kmap(folio, dir_entry); if (error) return "error reading root directory."; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index f9578918cfb2..825c5c2e0962 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2926,7 +2926,7 @@ static int do_proc_dqstats(const struct ctl_table *table, int write, return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_dqstats_table[] = { +static const struct ctl_table fs_dqstats_table[] = { { .procname = "lookups", .data = &dqstats.stat[DQST_LOOKUPS], diff --git a/fs/select.c b/fs/select.c index e223d1fe9d55..7da531b1cf6b 100644 --- a/fs/select.c +++ b/fs/select.c @@ -786,7 +786,7 @@ static inline int get_sigset_argpack(struct sigset_argpack *to, } return 0; Efault: - user_access_end(); + user_read_access_end(); return -EFAULT; } @@ -1355,7 +1355,7 @@ static inline int get_compat_sigset_argpack(struct compat_sigset_argpack *to, } return 0; Efault: - user_access_end(); + user_read_access_end(); return -EFAULT; } diff --git a/fs/smb/client/Kconfig b/fs/smb/client/Kconfig index 2aff6d1395ce..9f05f94e265a 100644 --- a/fs/smb/client/Kconfig +++ b/fs/smb/client/Kconfig @@ -2,7 +2,6 @@ config CIFS tristate "SMB3 and CIFS support (advanced network filesystem)" depends on INET - select NETFS_SUPPORT select NLS select NLS_UCS2_UTILS select CRYPTO diff --git a/fs/smb/client/asn1.c b/fs/smb/client/asn1.c index b5724ef9f182..214a44509e7b 100644 --- a/fs/smb/client/asn1.c +++ b/fs/smb/client/asn1.c @@ -52,6 +52,8 @@ int cifs_neg_token_init_mech_type(void *context, size_t hdrlen, server->sec_kerberos = true; else if (oid == OID_ntlmssp) server->sec_ntlmssp = true; + else if (oid == OID_IAKerb) + server->sec_iakerb = true; else { char buf[50]; diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 28f568b5fc27..bc1c1e9b288a 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -138,11 +138,13 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo, dp = description + strlen(description); - /* for now, only sec=krb5 and sec=mskrb5 are valid */ + /* for now, only sec=krb5 and sec=mskrb5 and iakerb are valid */ if (server->sec_kerberos) sprintf(dp, ";sec=krb5"); else if (server->sec_mskerberos) sprintf(dp, ";sec=mskrb5"); + else if (server->sec_iakerb) + sprintf(dp, ";sec=iakerb"); else { cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n"); sprintf(dp, ";sec=krb5"); diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index ba79aa2107cc..699a3f76d083 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1395,7 +1395,7 @@ chown_chgrp_exit: #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY struct smb_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, const struct cifs_fid *cifsfid, u32 *pacllen, - u32 __maybe_unused unused) + u32 info) { struct smb_ntsd *pntsd = NULL; unsigned int xid; @@ -1407,7 +1407,7 @@ struct smb_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, xid = get_xid(); rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), cifsfid->netfid, &pntsd, - pacllen); + pacllen, info); free_xid(xid); cifs_put_tlink(tlink); @@ -1419,7 +1419,7 @@ struct smb_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, } static struct smb_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, - const char *path, u32 *pacllen) + const char *path, u32 *pacllen, u32 info) { struct smb_ntsd *pntsd = NULL; int oplock = 0; @@ -1446,9 +1446,12 @@ static struct smb_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, .fid = &fid, }; + if (info & SACL_SECINFO) + oparms.desired_access |= SYSTEM_SECURITY; + rc = CIFS_open(xid, &oparms, &oplock, NULL); if (!rc) { - rc = CIFSSMBGetCIFSACL(xid, tcon, fid.netfid, &pntsd, pacllen); + rc = CIFSSMBGetCIFSACL(xid, tcon, fid.netfid, &pntsd, pacllen, info); CIFSSMBClose(xid, tcon, fid.netfid); } @@ -1472,7 +1475,7 @@ struct smb_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, if (inode) open_file = find_readable_file(CIFS_I(inode), true); if (!open_file) - return get_cifs_acl_by_path(cifs_sb, path, pacllen); + return get_cifs_acl_by_path(cifs_sb, path, pacllen, info); pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen, info); cifsFileInfo_put(open_file); @@ -1485,7 +1488,7 @@ int set_cifs_acl(struct smb_ntsd *pnntsd, __u32 acllen, { int oplock = 0; unsigned int xid; - int rc, access_flags; + int rc, access_flags = 0; struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); @@ -1498,10 +1501,12 @@ int set_cifs_acl(struct smb_ntsd *pnntsd, __u32 acllen, tcon = tlink_tcon(tlink); xid = get_xid(); - if (aclflag == CIFS_ACL_OWNER || aclflag == CIFS_ACL_GROUP) - access_flags = WRITE_OWNER; - else - access_flags = WRITE_DAC; + if (aclflag & CIFS_ACL_OWNER || aclflag & CIFS_ACL_GROUP) + access_flags |= WRITE_OWNER; + if (aclflag & CIFS_ACL_SACL) + access_flags |= SYSTEM_SECURITY; + if (aclflag & CIFS_ACL_DACL) + access_flags |= WRITE_DAC; oparms = (struct cifs_open_parms) { .tcon = tcon, diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index 7a43daacc815..e69968e88fe7 100644 --- a/fs/smb/client/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -315,59 +315,72 @@ build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp) return 0; } -/* Server has provided av pairs/target info in the type 2 challenge - * packet and we have plucked it and stored within smb session. - * We parse that blob here to find netbios domain name to be used - * as part of ntlmv2 authentication (in Target String), if not already - * specified on the command line. - * If this function returns without any error but without fetching - * domain name, authentication may fail against some server but - * may not fail against other (those who are not very particular - * about target string i.e. for some, just user name might suffice. - */ -static int -find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp) +#define AV_TYPE(av) (le16_to_cpu(av->type)) +#define AV_LEN(av) (le16_to_cpu(av->length)) +#define AV_DATA_PTR(av) ((void *)av->data) + +#define av_for_each_entry(ses, av) \ + for (av = NULL; (av = find_next_av(ses, av));) + +static struct ntlmssp2_name *find_next_av(struct cifs_ses *ses, + struct ntlmssp2_name *av) { - unsigned int attrsize; - unsigned int type; - unsigned int onesize = sizeof(struct ntlmssp2_name); - unsigned char *blobptr; - unsigned char *blobend; - struct ntlmssp2_name *attrptr; + u16 len; + u8 *end; - if (!ses->auth_key.len || !ses->auth_key.response) - return 0; - - blobptr = ses->auth_key.response; - blobend = blobptr + ses->auth_key.len; - - while (blobptr + onesize < blobend) { - attrptr = (struct ntlmssp2_name *) blobptr; - type = le16_to_cpu(attrptr->type); - if (type == NTLMSSP_AV_EOL) - break; - blobptr += 2; /* advance attr type */ - attrsize = le16_to_cpu(attrptr->length); - blobptr += 2; /* advance attr size */ - if (blobptr + attrsize > blobend) - break; - if (type == NTLMSSP_AV_NB_DOMAIN_NAME) { - if (!attrsize || attrsize >= CIFS_MAX_DOMAINNAME_LEN) - break; - if (!ses->domainName) { - ses->domainName = - kmalloc(attrsize + 1, GFP_KERNEL); - if (!ses->domainName) - return -ENOMEM; - cifs_from_utf16(ses->domainName, - (__le16 *)blobptr, attrsize, attrsize, - nls_cp, NO_MAP_UNI_RSVD); - break; - } - } - blobptr += attrsize; /* advance attr value */ + end = (u8 *)ses->auth_key.response + ses->auth_key.len; + if (!av) { + if (unlikely(!ses->auth_key.response || !ses->auth_key.len)) + return NULL; + av = (void *)ses->auth_key.response; + } else { + av = (void *)((u8 *)av + sizeof(*av) + AV_LEN(av)); } + if ((u8 *)av + sizeof(*av) > end) + return NULL; + + len = AV_LEN(av); + if (AV_TYPE(av) == NTLMSSP_AV_EOL) + return NULL; + if (!len || (u8 *)av + sizeof(*av) + len > end) + return NULL; + return av; +} + +/* + * Check if server has provided av pair of @type in the NTLMSSP + * CHALLENGE_MESSAGE blob. + */ +static int find_av_name(struct cifs_ses *ses, u16 type, char **name, u16 maxlen) +{ + const struct nls_table *nlsc = ses->local_nls; + struct ntlmssp2_name *av; + u16 len, nlen; + + if (*name) + return 0; + + av_for_each_entry(ses, av) { + len = AV_LEN(av); + if (AV_TYPE(av) != type) + continue; + if (!IS_ALIGNED(len, sizeof(__le16))) { + cifs_dbg(VFS | ONCE, "%s: bad length(%u) for type %u\n", + __func__, len, type); + continue; + } + nlen = len / sizeof(__le16); + if (nlen <= maxlen) { + ++nlen; + *name = kmalloc(nlen, GFP_KERNEL); + if (!*name) + return -ENOMEM; + cifs_from_utf16(*name, AV_DATA_PTR(av), nlen, + len, nlsc, NO_MAP_UNI_RSVD); + break; + } + } return 0; } @@ -377,40 +390,16 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp) * as part of ntlmv2 authentication (or local current time as * default in case of failure) */ -static __le64 -find_timestamp(struct cifs_ses *ses) +static __le64 find_timestamp(struct cifs_ses *ses) { - unsigned int attrsize; - unsigned int type; - unsigned int onesize = sizeof(struct ntlmssp2_name); - unsigned char *blobptr; - unsigned char *blobend; - struct ntlmssp2_name *attrptr; + struct ntlmssp2_name *av; struct timespec64 ts; - if (!ses->auth_key.len || !ses->auth_key.response) - return 0; - - blobptr = ses->auth_key.response; - blobend = blobptr + ses->auth_key.len; - - while (blobptr + onesize < blobend) { - attrptr = (struct ntlmssp2_name *) blobptr; - type = le16_to_cpu(attrptr->type); - if (type == NTLMSSP_AV_EOL) - break; - blobptr += 2; /* advance attr type */ - attrsize = le16_to_cpu(attrptr->length); - blobptr += 2; /* advance attr size */ - if (blobptr + attrsize > blobend) - break; - if (type == NTLMSSP_AV_TIMESTAMP) { - if (attrsize == sizeof(u64)) - return *((__le64 *)blobptr); - } - blobptr += attrsize; /* advance attr value */ + av_for_each_entry(ses, av) { + if (AV_TYPE(av) == NTLMSSP_AV_TIMESTAMP && + AV_LEN(av) == sizeof(u64)) + return *((__le64 *)AV_DATA_PTR(av)); } - ktime_get_real_ts64(&ts); return cpu_to_le64(cifs_UnixTimeToNT(ts)); } @@ -563,16 +552,29 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) { if (!ses->domainName) { if (ses->domainAuto) { - rc = find_domain_name(ses, nls_cp); - if (rc) { - cifs_dbg(VFS, "error %d finding domain name\n", - rc); + /* + * Domain (workgroup) hasn't been specified in + * mount options, so try to find it in + * CHALLENGE_MESSAGE message and then use it as + * part of NTLMv2 authentication. + */ + rc = find_av_name(ses, NTLMSSP_AV_NB_DOMAIN_NAME, + &ses->domainName, + CIFS_MAX_DOMAINNAME_LEN); + if (rc) goto setup_ntlmv2_rsp_ret; - } } else { ses->domainName = kstrdup("", GFP_KERNEL); + if (!ses->domainName) { + rc = -ENOMEM; + goto setup_ntlmv2_rsp_ret; + } } } + rc = find_av_name(ses, NTLMSSP_AV_DNS_DOMAIN_NAME, + &ses->dns_dom, CIFS_MAX_DOMAINNAME_LEN); + if (rc) + goto setup_ntlmv2_rsp_ret; } else { rc = build_avpair_blob(ses, nls_cp); if (rc) { diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 9d96b833015c..6a3bd652d251 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -398,7 +398,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode = alloc_inode_sb(sb, cifs_inode_cachep, GFP_KERNEL); if (!cifs_inode) return NULL; - cifs_inode->cifsAttrs = 0x20; /* default */ + cifs_inode->cifsAttrs = ATTR_ARCHIVE; /* default */ cifs_inode->time = 0; /* * Until the file is open and we have gotten oplock info back from the @@ -715,6 +715,12 @@ cifs_show_options(struct seq_file *s, struct dentry *root) cifs_sb->ctx->backupgid)); seq_show_option(s, "reparse", cifs_reparse_type_str(cifs_sb->ctx->reparse_type)); + if (cifs_sb->ctx->nonativesocket) + seq_puts(s, ",nonativesocket"); + else + seq_puts(s, ",nativesocket"); + seq_show_option(s, "symlink", + cifs_symlink_type_str(get_cifs_symlink_type(cifs_sb))); seq_printf(s, ",rsize=%u", cifs_sb->ctx->rsize); seq_printf(s, ",wsize=%u", cifs_sb->ctx->wsize); diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index a762dbbbd959..831fee962c4d 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -146,6 +146,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 52 -#define CIFS_VERSION "2.52" +#define SMB3_PRODUCT_BUILD 53 +#define CIFS_VERSION "2.53" #endif /* _CIFSFS_H */ diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 6e63abe461fd..a68434ad744a 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -151,6 +151,7 @@ enum securityEnum { NTLMv2, /* Legacy NTLM auth with NTLMv2 hash */ RawNTLMSSP, /* NTLMSSP without SPNEGO, NTLMv2 hash */ Kerberos, /* Kerberos via SPNEGO */ + IAKerb, /* Kerberos proxy */ }; enum upcall_target_enum { @@ -160,6 +161,7 @@ enum upcall_target_enum { }; enum cifs_reparse_type { + CIFS_REPARSE_TYPE_NONE, CIFS_REPARSE_TYPE_NFS, CIFS_REPARSE_TYPE_WSL, CIFS_REPARSE_TYPE_DEFAULT = CIFS_REPARSE_TYPE_NFS, @@ -168,6 +170,8 @@ enum cifs_reparse_type { static inline const char *cifs_reparse_type_str(enum cifs_reparse_type type) { switch (type) { + case CIFS_REPARSE_TYPE_NONE: + return "none"; case CIFS_REPARSE_TYPE_NFS: return "nfs"; case CIFS_REPARSE_TYPE_WSL: @@ -177,6 +181,39 @@ static inline const char *cifs_reparse_type_str(enum cifs_reparse_type type) } } +enum cifs_symlink_type { + CIFS_SYMLINK_TYPE_DEFAULT, + CIFS_SYMLINK_TYPE_NONE, + CIFS_SYMLINK_TYPE_NATIVE, + CIFS_SYMLINK_TYPE_UNIX, + CIFS_SYMLINK_TYPE_MFSYMLINKS, + CIFS_SYMLINK_TYPE_SFU, + CIFS_SYMLINK_TYPE_NFS, + CIFS_SYMLINK_TYPE_WSL, +}; + +static inline const char *cifs_symlink_type_str(enum cifs_symlink_type type) +{ + switch (type) { + case CIFS_SYMLINK_TYPE_NONE: + return "none"; + case CIFS_SYMLINK_TYPE_NATIVE: + return "native"; + case CIFS_SYMLINK_TYPE_UNIX: + return "unix"; + case CIFS_SYMLINK_TYPE_MFSYMLINKS: + return "mfsymlinks"; + case CIFS_SYMLINK_TYPE_SFU: + return "sfu"; + case CIFS_SYMLINK_TYPE_NFS: + return "nfs"; + case CIFS_SYMLINK_TYPE_WSL: + return "wsl"; + default: + return "unknown"; + } +} + struct session_key { unsigned int len; char *response; @@ -215,10 +252,7 @@ struct cifs_cred { struct cifs_open_info_data { bool adjust_tz; - union { - bool reparse_point; - bool symlink; - }; + bool reparse_point; struct { /* ioctl response buffer */ struct { @@ -226,10 +260,7 @@ struct cifs_open_info_data { struct kvec iov; } io; __u32 tag; - union { - struct reparse_data_buffer *buf; - struct reparse_posix_data *posix; - }; + struct reparse_data_buffer *buf; } reparse; struct { __u8 eas[SMB2_WSL_MAX_QUERY_EA_RESP_SIZE]; @@ -751,6 +782,7 @@ struct TCP_Server_Info { bool sec_kerberosu2u; /* supports U2U Kerberos */ bool sec_kerberos; /* supports plain Kerberos */ bool sec_mskerberos; /* supports legacy MS Kerberos */ + bool sec_iakerb; /* supports pass-through auth for Kerberos (krb5 proxy) */ bool large_buf; /* is current buffer large? */ /* use SMBD connection instead of socket */ bool rdma; @@ -811,23 +843,15 @@ struct TCP_Server_Info { bool use_swn_dstaddr; struct sockaddr_storage swn_dstaddr; #endif - struct mutex refpath_lock; /* protects leaf_fullpath */ /* - * leaf_fullpath: Canonical DFS referral path related to this - * connection. - * It is used in DFS cache refresher, reconnect and may - * change due to nested DFS links. - * - * Protected by @refpath_lock and @srv_lock. The @refpath_lock is - * mostly used for not requiring a copy of @leaf_fullpath when getting - * cached or new DFS referrals (which might also sleep during I/O). - * While @srv_lock is held for making string and NULL comparisons against - * both fields as in mount(2) and cache refresh. + * Canonical DFS referral path used in cifs_reconnect() for failover as + * well as in DFS cache refresher. * * format: \\HOST\SHARE[\OPTIONAL PATH] */ char *leaf_fullpath; bool dfs_conn:1; + char dns_dom[CIFS_MAX_DOMAINNAME_LEN + 1]; }; static inline bool is_smb1(struct TCP_Server_Info *server) @@ -1154,6 +1178,7 @@ struct cifs_ses { /* ========= end: protected by chan_lock ======== */ struct cifs_ses *dfs_root_ses; struct nls_table *local_nls; + char *dns_dom; /* FQDN of the domain */ }; static inline bool @@ -2125,6 +2150,8 @@ static inline char *get_security_type_str(enum securityEnum sectype) return "Kerberos"; case NTLMv2: return "NTLMv2"; + case IAKerb: + return "IAKerb"; default: return "Unknown"; } @@ -2180,11 +2207,13 @@ static inline size_t ntlmssp_workstation_name_size(const struct cifs_ses *ses) static inline void move_cifs_info_to_smb2(struct smb2_file_all_info *dst, const FILE_ALL_INFO *src) { - memcpy(dst, src, (size_t)((u8 *)&src->AccessFlags - (u8 *)src)); - dst->AccessFlags = src->AccessFlags; - dst->CurrentByteOffset = src->CurrentByteOffset; - dst->Mode = src->Mode; - dst->AlignmentRequirement = src->AlignmentRequirement; + memcpy(dst, src, (size_t)((u8 *)&src->EASize - (u8 *)src)); + dst->IndexNumber = 0; + dst->EASize = src->EASize; + dst->AccessFlags = 0; + dst->CurrentByteOffset = 0; + dst->Mode = 0; + dst->AlignmentRequirement = 0; dst->FileNameLength = src->FileNameLength; } @@ -2311,4 +2340,24 @@ static inline bool cifs_ses_exiting(struct cifs_ses *ses) return ret; } +static inline bool cifs_netbios_name(const char *name, size_t namelen) +{ + bool ret = false; + size_t i; + + if (namelen >= 1 && namelen <= RFC1001_NAME_LEN) { + for (i = 0; i < namelen; i++) { + const unsigned char c = name[i]; + + if (c == '\\' || c == '/' || c == ':' || c == '*' || + c == '?' || c == '"' || c == '<' || c == '>' || + c == '|' || c == '.') + return false; + if (!ret && isalpha(c)) + ret = true; + } + } + return ret; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index ee78bb6741d6..48d0d6f439cf 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -190,42 +190,82 @@ */ #define FILE_READ_DATA 0x00000001 /* Data can be read from the file */ + /* or directory child entries can */ + /* be listed together with the */ + /* associated child attributes */ + /* (so the FILE_READ_ATTRIBUTES on */ + /* the child entry is not needed) */ #define FILE_WRITE_DATA 0x00000002 /* Data can be written to the file */ + /* or new file can be created in */ + /* the directory */ #define FILE_APPEND_DATA 0x00000004 /* Data can be appended to the file */ + /* (for non-local files over SMB it */ + /* is same as FILE_WRITE_DATA) */ + /* or new subdirectory can be */ + /* created in the directory */ #define FILE_READ_EA 0x00000008 /* Extended attributes associated */ /* with the file can be read */ #define FILE_WRITE_EA 0x00000010 /* Extended attributes associated */ /* with the file can be written */ #define FILE_EXECUTE 0x00000020 /*Data can be read into memory from */ /* the file using system paging I/O */ -#define FILE_DELETE_CHILD 0x00000040 + /* for executing the file / script */ + /* or right to traverse directory */ + /* (but by default all users have */ + /* directory bypass traverse */ + /* privilege and do not need this */ + /* permission on directories at all)*/ +#define FILE_DELETE_CHILD 0x00000040 /* Child entry can be deleted from */ + /* the directory (so the DELETE on */ + /* the child entry is not needed) */ #define FILE_READ_ATTRIBUTES 0x00000080 /* Attributes associated with the */ - /* file can be read */ + /* file or directory can be read */ #define FILE_WRITE_ATTRIBUTES 0x00000100 /* Attributes associated with the */ - /* file can be written */ -#define DELETE 0x00010000 /* The file can be deleted */ -#define READ_CONTROL 0x00020000 /* The access control list and */ - /* ownership associated with the */ - /* file can be read */ -#define WRITE_DAC 0x00040000 /* The access control list and */ - /* ownership associated with the */ - /* file can be written. */ + /* file or directory can be written */ +#define DELETE 0x00010000 /* The file or dir can be deleted */ +#define READ_CONTROL 0x00020000 /* The discretionary access control */ + /* list and ownership associated */ + /* with the file or dir can be read */ +#define WRITE_DAC 0x00040000 /* The discretionary access control */ + /* list associated with the file or */ + /* directory can be written */ #define WRITE_OWNER 0x00080000 /* Ownership information associated */ - /* with the file can be written */ + /* with the file/dir can be written */ #define SYNCHRONIZE 0x00100000 /* The file handle can waited on to */ /* synchronize with the completion */ /* of an input/output request */ #define SYSTEM_SECURITY 0x01000000 /* The system access control list */ - /* can be read and changed */ -#define GENERIC_ALL 0x10000000 -#define GENERIC_EXECUTE 0x20000000 -#define GENERIC_WRITE 0x40000000 -#define GENERIC_READ 0x80000000 - /* In summary - Relevant file */ - /* access flags from CIFS are */ - /* file_read_data, file_write_data */ - /* file_execute, file_read_attributes*/ - /* write_dac, and delete. */ + /* associated with the file or */ + /* directory can be read or written */ + /* (cannot be in DACL, can in SACL) */ +#define MAXIMUM_ALLOWED 0x02000000 /* Maximal subset of GENERIC_ALL */ + /* permissions which can be granted */ + /* (cannot be in DACL nor SACL) */ +#define GENERIC_ALL 0x10000000 /* Same as: GENERIC_EXECUTE | */ + /* GENERIC_WRITE | */ + /* GENERIC_READ | */ + /* FILE_DELETE_CHILD | */ + /* DELETE | */ + /* WRITE_DAC | */ + /* WRITE_OWNER */ + /* So GENERIC_ALL contains all bits */ + /* mentioned above except these two */ + /* SYSTEM_SECURITY MAXIMUM_ALLOWED */ +#define GENERIC_EXECUTE 0x20000000 /* Same as: FILE_EXECUTE | */ + /* FILE_READ_ATTRIBUTES | */ + /* READ_CONTROL | */ + /* SYNCHRONIZE */ +#define GENERIC_WRITE 0x40000000 /* Same as: FILE_WRITE_DATA | */ + /* FILE_APPEND_DATA | */ + /* FILE_WRITE_EA | */ + /* FILE_WRITE_ATTRIBUTES | */ + /* READ_CONTROL | */ + /* SYNCHRONIZE */ +#define GENERIC_READ 0x80000000 /* Same as: FILE_READ_DATA | */ + /* FILE_READ_EA | */ + /* FILE_READ_ATTRIBUTES | */ + /* READ_CONTROL | */ + /* SYNCHRONIZE */ #define FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA | FILE_READ_ATTRIBUTES) #define FILE_WRITE_RIGHTS (FILE_WRITE_DATA | FILE_APPEND_DATA \ @@ -649,7 +689,7 @@ typedef union smb_com_session_setup_andx { struct ntlmssp2_name { __le16 type; __le16 length; -/* char name[length]; */ + __u8 data[]; } __attribute__((packed)); struct ntlmv2_resp { @@ -1484,36 +1524,6 @@ struct file_notify_information { __u8 FileName[]; } __attribute__((packed)); -/* For IO_REPARSE_TAG_SYMLINK */ -struct reparse_symlink_data { - __le32 ReparseTag; - __le16 ReparseDataLength; - __u16 Reserved; - __le16 SubstituteNameOffset; - __le16 SubstituteNameLength; - __le16 PrintNameOffset; - __le16 PrintNameLength; - __le32 Flags; - char PathBuffer[]; -} __attribute__((packed)); - -/* Flag above */ -#define SYMLINK_FLAG_RELATIVE 0x00000001 - -/* For IO_REPARSE_TAG_NFS */ -#define NFS_SPECFILE_LNK 0x00000000014B4E4C -#define NFS_SPECFILE_CHR 0x0000000000524843 -#define NFS_SPECFILE_BLK 0x00000000004B4C42 -#define NFS_SPECFILE_FIFO 0x000000004F464946 -#define NFS_SPECFILE_SOCK 0x000000004B434F53 -struct reparse_posix_data { - __le32 ReparseTag; - __le16 ReparseDataLength; - __u16 Reserved; - __le64 InodeType; /* LNK, FIFO, CHR etc. */ - __u8 DataBuffer[]; -} __attribute__((packed)); - struct cifs_quota_data { __u32 rsrvd1; /* 0 */ __u32 sid_size; @@ -2280,13 +2290,7 @@ typedef struct { /* data block encoding of response to level 263 QPathInfo */ __u8 DeletePending; __u8 Directory; __u16 Pad2; - __le64 IndexNumber; __le32 EASize; - __le32 AccessFlags; - __u64 IndexNumber1; - __le64 CurrentByteOffset; - __le32 Mode; - __le32 AlignmentRequirement; __le32 FileNameLength; union { char __pad; diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 754417cb3294..81680001944d 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -474,9 +474,6 @@ extern int cifs_query_reparse_point(const unsigned int xid, const char *full_path, u32 *tag, struct kvec *rsp, int *rsp_buftype); -extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, - __u16 fid, char **symlinkinfo, - const struct nls_table *nls_codepage); extern int CIFSSMB_set_compression(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid); extern int CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms, @@ -560,7 +557,7 @@ extern int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nls_codepage, struct cifs_sb_info *cifs_sb); extern int CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, - __u16 fid, struct smb_ntsd **acl_inf, __u32 *buflen); + __u16 fid, struct smb_ntsd **acl_inf, __u32 *buflen, __u32 info); extern int CIFSSMBSetCIFSACL(const unsigned int, struct cifs_tcon *, __u16, struct smb_ntsd *pntsd, __u32 len, int aclflag); extern int cifs_do_get_acl(const unsigned int xid, struct cifs_tcon *tcon, @@ -614,8 +611,6 @@ int cifs_alloc_hash(const char *name, struct shash_desc **sdesc); void cifs_free_hash(struct shash_desc **sdesc); int cifs_try_adding_channels(struct cifs_ses *ses); -bool is_server_using_iface(struct TCP_Server_Info *server, - struct cifs_server_iface *iface); bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface); void cifs_ses_mark_for_reconnect(struct cifs_ses *ses); @@ -661,7 +656,7 @@ char *extract_sharename(const char *unc); int parse_reparse_point(struct reparse_data_buffer *buf, u32 plen, struct cifs_sb_info *cifs_sb, const char *full_path, - bool unicode, struct cifs_open_info_data *data); + struct cifs_open_info_data *data); int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, const char *full_path, umode_t mode, dev_t dev, @@ -682,7 +677,7 @@ static inline int get_dfs_path(const unsigned int xid, struct cifs_ses *ses, } int match_target_ip(struct TCP_Server_Info *server, - const char *share, size_t share_len, + const char *host, size_t hostlen, bool *result); int cifs_inval_name_dfs_link_error(const unsigned int xid, struct cifs_tcon *tcon, diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index bd42a419458e..3feaa0f68169 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -152,8 +152,17 @@ again: spin_unlock(&ses->ses_lock); rc = cifs_negotiate_protocol(0, ses, server); - if (!rc) + if (!rc) { rc = cifs_setup_session(0, ses, server, ses->local_nls); + if ((rc == -EACCES) || (rc == -EHOSTDOWN) || (rc == -EKEYREVOKED)) { + /* + * Try alternate password for next reconnect if an alternate + * password is available. + */ + if (ses->password2) + swap(ses->password2, ses->password); + } + } /* do we need to reconnect tcon? */ if (rc || !tcon->need_reconnect) { @@ -1258,14 +1267,6 @@ openRetry: return rc; } -static void cifs_readv_worker(struct work_struct *work) -{ - struct cifs_io_subrequest *rdata = - container_of(work, struct cifs_io_subrequest, subreq.work); - - netfs_read_subreq_terminated(&rdata->subreq, rdata->result, false); -} - static void cifs_readv_callback(struct mid_q_entry *mid) { @@ -1319,20 +1320,24 @@ cifs_readv_callback(struct mid_q_entry *mid) } if (rdata->result == -ENODATA) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && rdata->subreq.start + trans == ictx->remote_i_size) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + } else if (rdata->got_bytes > 0) { + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } + if (rdata->got_bytes) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } rdata->credits.value = 0; + rdata->subreq.error = rdata->result; rdata->subreq.transferred += rdata->got_bytes; - INIT_WORK(&rdata->subreq.work, cifs_readv_worker); queue_work(cifsiod_wq, &rdata->subreq.work); release_mid(mid); add_credits(server, &credits, 0); @@ -1670,10 +1675,13 @@ cifs_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->subreq.len) + if (written < wdata->subreq.len) { result = -ENOSPC; - else + } else { result = written; + if (written > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: @@ -3361,7 +3369,7 @@ validate_ntransact(char *buf, char **ppparm, char **ppdata, /* Get Security Descriptor (by handle) from remote server for a file or dir */ int CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid, - struct smb_ntsd **acl_inf, __u32 *pbuflen) + struct smb_ntsd **acl_inf, __u32 *pbuflen, __u32 info) { int rc = 0; int buf_type = 0; @@ -3384,7 +3392,7 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid, pSMB->MaxSetupCount = 0; pSMB->Fid = fid; /* file handle always le */ pSMB->AclFlags = cpu_to_le32(CIFS_ACL_OWNER | CIFS_ACL_GROUP | - CIFS_ACL_DACL); + CIFS_ACL_DACL | info); pSMB->ByteCount = cpu_to_le16(11); /* 3 bytes pad + 8 bytes parm */ inc_rfc1001_len(pSMB, 11); iov[0].iov_base = (char *)pSMB; diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 2372538a1211..f917de020dd5 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -72,10 +72,8 @@ static void cifs_prune_tlinks(struct work_struct *work); */ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) { - int rc; - int len; - char *unc; struct sockaddr_storage ss; + int rc; if (!server->hostname) return -EINVAL; @@ -84,32 +82,18 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) if (server->hostname[0] == '\0') return 0; - len = strlen(server->hostname) + 3; - - unc = kmalloc(len, GFP_KERNEL); - if (!unc) { - cifs_dbg(FYI, "%s: failed to create UNC path\n", __func__); - return -ENOMEM; - } - scnprintf(unc, len, "\\\\%s", server->hostname); - spin_lock(&server->srv_lock); ss = server->dstaddr; spin_unlock(&server->srv_lock); - rc = dns_resolve_server_name_to_ip(unc, (struct sockaddr *)&ss, NULL); - kfree(unc); - - if (rc < 0) { - cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n", - __func__, server->hostname, rc); - } else { + rc = dns_resolve_name(server->dns_dom, server->hostname, + strlen(server->hostname), + (struct sockaddr *)&ss); + if (!rc) { spin_lock(&server->srv_lock); memcpy(&server->dstaddr, &ss, sizeof(server->dstaddr)); spin_unlock(&server->srv_lock); - rc = 0; } - return rc; } @@ -438,7 +422,8 @@ static int __cifs_reconnect(struct TCP_Server_Info *server, } #ifdef CONFIG_CIFS_DFS_UPCALL -static int __reconnect_target_unlocked(struct TCP_Server_Info *server, const char *target) +static int __reconnect_target_locked(struct TCP_Server_Info *server, + const char *target) { int rc; char *hostname; @@ -471,34 +456,43 @@ static int __reconnect_target_unlocked(struct TCP_Server_Info *server, const cha return rc; } -static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_cache_tgt_list *tl, - struct dfs_cache_tgt_iterator **target_hint) +static int reconnect_target_locked(struct TCP_Server_Info *server, + struct dfs_cache_tgt_list *tl, + struct dfs_cache_tgt_iterator **target_hint) { - int rc; struct dfs_cache_tgt_iterator *tit; + int rc; *target_hint = NULL; /* If dfs target list is empty, then reconnect to last server */ tit = dfs_cache_get_tgt_iterator(tl); if (!tit) - return __reconnect_target_unlocked(server, server->hostname); + return __reconnect_target_locked(server, server->hostname); /* Otherwise, try every dfs target in @tl */ - for (; tit; tit = dfs_cache_get_next_tgt(tl, tit)) { - rc = __reconnect_target_unlocked(server, dfs_cache_get_tgt_name(tit)); + do { + const char *target = dfs_cache_get_tgt_name(tit); + + spin_lock(&server->srv_lock); + if (server->tcpStatus != CifsNeedReconnect) { + spin_unlock(&server->srv_lock); + return -ECONNRESET; + } + spin_unlock(&server->srv_lock); + rc = __reconnect_target_locked(server, target); if (!rc) { *target_hint = tit; break; } - } + } while ((tit = dfs_cache_get_next_tgt(tl, tit))); return rc; } static int reconnect_dfs_server(struct TCP_Server_Info *server) { struct dfs_cache_tgt_iterator *target_hint = NULL; - + const char *ref_path = server->leaf_fullpath + 1; DFS_CACHE_TGT_LIST(tl); int num_targets = 0; int rc = 0; @@ -511,10 +505,8 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) * through /proc/fs/cifs/dfscache or the target list is empty due to server settings after * refreshing the referral, so, in this case, default it to 1. */ - mutex_lock(&server->refpath_lock); - if (!dfs_cache_noreq_find(server->leaf_fullpath + 1, NULL, &tl)) + if (!dfs_cache_noreq_find(ref_path, NULL, &tl)) num_targets = dfs_cache_get_nr_tgts(&tl); - mutex_unlock(&server->refpath_lock); if (!num_targets) num_targets = 1; @@ -534,7 +526,7 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) try_to_freeze(); cifs_server_lock(server); - rc = reconnect_target_unlocked(server, &tl, &target_hint); + rc = reconnect_target_locked(server, &tl, &target_hint); if (rc) { /* Failed to reconnect socket */ cifs_server_unlock(server); @@ -558,9 +550,7 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) mod_delayed_work(cifsiod_wq, &server->reconnect, 0); } while (server->tcpStatus == CifsNeedReconnect); - mutex_lock(&server->refpath_lock); - dfs_cache_noreq_update_tgthint(server->leaf_fullpath + 1, target_hint); - mutex_unlock(&server->refpath_lock); + dfs_cache_noreq_update_tgthint(ref_path, target_hint); dfs_cache_free_tgts(&tl); /* Need to set up echo worker again once connection has been established */ @@ -575,13 +565,8 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) { - mutex_lock(&server->refpath_lock); - if (!server->leaf_fullpath) { - mutex_unlock(&server->refpath_lock); + if (!server->leaf_fullpath) return __cifs_reconnect(server, mark_smb_session); - } - mutex_unlock(&server->refpath_lock); - return reconnect_dfs_server(server); } #else @@ -987,9 +972,13 @@ clean_demultiplex_info(struct TCP_Server_Info *server) msleep(125); if (cifs_rdma_enabled(server)) smbd_destroy(server); + if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; + + /* Release netns reference for the socket. */ + put_net(cifs_net_ns(server)); } if (!list_empty(&server->pending_mid_q)) { @@ -1037,8 +1026,10 @@ clean_demultiplex_info(struct TCP_Server_Info *server) */ } + /* Release netns reference for this server. */ put_net(cifs_net_ns(server)); kfree(server->leaf_fullpath); + kfree(server->hostname); kfree(server); length = atomic_dec_return(&tcpSesAllocCount); @@ -1535,42 +1526,10 @@ static int match_server(struct TCP_Server_Info *server, if (!cifs_match_ipaddr((struct sockaddr *)&ctx->srcaddr, (struct sockaddr *)&server->srcaddr)) return 0; - /* - * When matching cifs.ko superblocks (@match_super == true), we can't - * really match either @server->leaf_fullpath or @server->dstaddr - * directly since this @server might belong to a completely different - * server -- in case of domain-based DFS referrals or DFS links -- as - * provided earlier by mount(2) through 'source' and 'ip' options. - * - * Otherwise, match the DFS referral in @server->leaf_fullpath or the - * destination address in @server->dstaddr. - * - * When using 'nodfs' mount option, we avoid sharing it with DFS - * connections as they might failover. - */ - if (!match_super) { - if (!ctx->nodfs) { - if (server->leaf_fullpath) { - if (!ctx->leaf_fullpath || - strcasecmp(server->leaf_fullpath, - ctx->leaf_fullpath)) - return 0; - } else if (ctx->leaf_fullpath) { - return 0; - } - } else if (server->leaf_fullpath) { - return 0; - } - } - /* - * Match for a regular connection (address/hostname/port) which has no - * DFS referrals set. - */ - if (!server->leaf_fullpath && - (strcasecmp(server->hostname, ctx->server_hostname) || - !match_server_address(server, addr) || - !match_port(server, addr))) + if (strcasecmp(server->hostname, ctx->server_hostname) || + !match_server_address(server, addr) || + !match_port(server, addr)) return 0; if (!match_security(server, ctx)) @@ -1665,8 +1624,6 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) kfree_sensitive(server->session_key.response); server->session_key.response = NULL; server->session_key.len = 0; - kfree(server->hostname); - server->hostname = NULL; task = xchg(&server->tsk, NULL); if (task) @@ -1706,6 +1663,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, goto out_err; } } + if (ctx->dns_dom) + strscpy(tcp_ses->dns_dom, ctx->dns_dom); if (ctx->nosharesock) tcp_ses->nosharesock = true; @@ -1713,6 +1672,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->ops = ctx->ops; tcp_ses->vals = ctx->vals; + + /* Grab netns reference for this server. */ cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); tcp_ses->conn_id = atomic_inc_return(&tcpSesNextId); @@ -1752,9 +1713,6 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server); mutex_init(&tcp_ses->reconnect_mutex); -#ifdef CONFIG_CIFS_DFS_UPCALL - mutex_init(&tcp_ses->refpath_lock); -#endif memcpy(&tcp_ses->srcaddr, &ctx->srcaddr, sizeof(tcp_ses->srcaddr)); memcpy(&tcp_ses->dstaddr, &ctx->dstaddr, @@ -1844,6 +1802,7 @@ smbd_connected: out_err_crypto_release: cifs_crypto_secmech_release(tcp_ses); + /* Release netns reference for this server. */ put_net(cifs_net_ns(tcp_ses)); out_err: @@ -1852,8 +1811,10 @@ out_err: cifs_put_tcp_session(tcp_ses->primary_server, false); kfree(tcp_ses->hostname); kfree(tcp_ses->leaf_fullpath); - if (tcp_ses->ssocket) + if (tcp_ses->ssocket) { sock_release(tcp_ses->ssocket); + put_net(cifs_net_ns(tcp_ses)); + } kfree(tcp_ses); } return ERR_PTR(rc); @@ -2267,12 +2228,13 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx __attribute__((unused)), struct cifs_ses * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { - int rc = 0; - int retries = 0; - unsigned int xid; - struct cifs_ses *ses; - struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)&server->dstaddr; + struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; + struct cifs_ses *ses; + unsigned int xid; + int retries = 0; + size_t len; + int rc = 0; xid = get_xid(); @@ -2362,6 +2324,14 @@ retry_old_session: ses->domainName = kstrdup(ctx->domainname, GFP_KERNEL); if (!ses->domainName) goto get_ses_fail; + + len = strnlen(ctx->domainname, CIFS_MAX_DOMAINNAME_LEN); + if (!cifs_netbios_name(ctx->domainname, len)) { + ses->dns_dom = kstrndup(ctx->domainname, + len, GFP_KERNEL); + if (!ses->dns_dom) + goto get_ses_fail; + } } strscpy(ses->workstation_name, ctx->workstation_name, sizeof(ses->workstation_name)); @@ -2879,6 +2849,10 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data) return 0; if (old->ctx->reparse_type != new->ctx->reparse_type) return 0; + if (old->ctx->nonativesocket != new->ctx->nonativesocket) + return 0; + if (old->ctx->symlink_type != new->ctx->symlink_type) + return 0; return 1; } @@ -3131,20 +3105,20 @@ generic_ip_connect(struct TCP_Server_Info *server) socket = server->ssocket; } else { struct net *net = cifs_net_ns(server); - struct sock *sk; - rc = __sock_create(net, sfamily, SOCK_STREAM, - IPPROTO_TCP, &server->ssocket, 1); + rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket); if (rc < 0) { cifs_server_dbg(VFS, "Error %d creating socket\n", rc); return rc; } - sk = server->ssocket->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + /* + * Grab netns reference for the socket. + * + * It'll be released here, on error, or in clean_demultiplex_info() upon server + * teardown. + */ + get_net(net); /* BB other socket options to set KEEPALIVE, NODELAY? */ cifs_dbg(FYI, "Socket created\n"); @@ -3158,8 +3132,10 @@ generic_ip_connect(struct TCP_Server_Info *server) } rc = bind_socket(server); - if (rc < 0) + if (rc < 0) { + put_net(cifs_net_ns(server)); return rc; + } /* * Eventually check for other socket options to change from @@ -3196,6 +3172,7 @@ generic_ip_connect(struct TCP_Server_Info *server) if (rc < 0) { cifs_dbg(FYI, "Error %d connecting to server\n", rc); trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc); + put_net(cifs_net_ns(server)); sock_release(socket); server->ssocket = NULL; return rc; @@ -3204,6 +3181,9 @@ generic_ip_connect(struct TCP_Server_Info *server) if (sport == htons(RFC1001_PORT)) rc = ip_rfc1001_connect(server); + if (rc < 0) + put_net(cifs_net_ns(server)); + return rc; } diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index 4647df9e1e3b..dad521336b5e 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -9,6 +9,8 @@ #include "fs_context.h" #include "dfs.h" +#define DFS_DOM(ctx) (ctx->dfs_root_ses ? ctx->dfs_root_ses->dns_dom : NULL) + /** * dfs_parse_target_referral - set fs context for dfs target referral * @@ -46,8 +48,8 @@ int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_para if (rc) goto out; - rc = dns_resolve_server_name_to_ip(path, (struct sockaddr *)&ctx->dstaddr, NULL); - + rc = dns_resolve_unc(DFS_DOM(ctx), path, + (struct sockaddr *)&ctx->dstaddr); out: kfree(path); return rc; @@ -59,8 +61,9 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path) int rc; ctx->leaf_fullpath = (char *)full_path; + ctx->dns_dom = DFS_DOM(ctx); rc = cifs_mount_get_session(mnt_ctx); - ctx->leaf_fullpath = NULL; + ctx->leaf_fullpath = ctx->dns_dom = NULL; return rc; } @@ -95,15 +98,16 @@ static inline int parse_dfs_target(struct smb3_fs_context *ctx, return rc; } -static int setup_dfs_ref(struct cifs_mount_ctx *mnt_ctx, - struct dfs_info3_param *tgt, - struct dfs_ref_walk *rw) +static int setup_dfs_ref(struct dfs_info3_param *tgt, struct dfs_ref_walk *rw) { - struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; - struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct cifs_sb_info *cifs_sb = rw->mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = rw->mnt_ctx->fs_ctx; char *ref_path, *full_path; int rc; + set_root_smb_session(rw->mnt_ctx); + ref_walk_ses(rw) = ctx->dfs_root_ses; + full_path = smb3_fs_context_fullpath(ctx, CIFS_DIR_SEP(cifs_sb)); if (IS_ERR(full_path)) return PTR_ERR(full_path); @@ -120,35 +124,22 @@ static int setup_dfs_ref(struct cifs_mount_ctx *mnt_ctx, } ref_walk_path(rw) = ref_path; ref_walk_fpath(rw) = full_path; - ref_walk_ses(rw) = ctx->dfs_root_ses; - return 0; + + return dfs_get_referral(rw->mnt_ctx, + ref_walk_path(rw) + 1, + ref_walk_tl(rw)); } -static int __dfs_referral_walk(struct cifs_mount_ctx *mnt_ctx, - struct dfs_ref_walk *rw) +static int __dfs_referral_walk(struct dfs_ref_walk *rw) { - struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct smb3_fs_context *ctx = rw->mnt_ctx->fs_ctx; + struct cifs_mount_ctx *mnt_ctx = rw->mnt_ctx; struct dfs_info3_param tgt = {}; int rc = -ENOENT; again: do { ctx->dfs_root_ses = ref_walk_ses(rw); - if (ref_walk_empty(rw)) { - rc = dfs_get_referral(mnt_ctx, ref_walk_path(rw) + 1, - NULL, ref_walk_tl(rw)); - if (rc) { - rc = cifs_mount_get_tcon(mnt_ctx); - if (!rc) - rc = cifs_is_path_remote(mnt_ctx); - continue; - } - if (!ref_walk_num_tgts(rw)) { - rc = -ENOENT; - continue; - } - } - while (ref_walk_next_tgt(rw)) { rc = parse_dfs_target(ctx, rw, &tgt); if (rc) @@ -159,32 +150,29 @@ again: if (rc) continue; - ref_walk_set_tgt_hint(rw); if (tgt.flags & DFSREF_STORAGE_SERVER) { rc = cifs_mount_get_tcon(mnt_ctx); if (!rc) rc = cifs_is_path_remote(mnt_ctx); - if (!rc) + if (!rc) { + ref_walk_set_tgt_hint(rw); break; + } if (rc != -EREMOTE) continue; } - set_root_smb_session(mnt_ctx); rc = ref_walk_advance(rw); if (!rc) { - rc = setup_dfs_ref(mnt_ctx, &tgt, rw); - if (!rc) { - rc = -EREMOTE; - goto again; - } + rc = setup_dfs_ref(&tgt, rw); + if (rc) + break; + ref_walk_mark_end(rw); + goto again; } - if (rc != -ELOOP) - goto out; } } while (rc && ref_walk_descend(rw)); -out: free_dfs_info_param(&tgt); return rc; } @@ -201,10 +189,10 @@ static int dfs_referral_walk(struct cifs_mount_ctx *mnt_ctx, return rc; } - ref_walk_init(*rw); - rc = setup_dfs_ref(mnt_ctx, NULL, *rw); + ref_walk_init(*rw, mnt_ctx); + rc = setup_dfs_ref(NULL, *rw); if (!rc) - rc = __dfs_referral_walk(mnt_ctx, *rw); + rc = __dfs_referral_walk(*rw); return rc; } @@ -264,7 +252,7 @@ static int update_fs_context_dstaddr(struct smb3_fs_context *ctx) int rc = 0; if (!ctx->nodfs && ctx->dfs_automount) { - rc = dns_resolve_server_name_to_ip(ctx->source, addr, NULL); + rc = dns_resolve_unc(NULL, ctx->source, addr); if (!rc) cifs_set_port(addr, ctx->port); ctx->dfs_automount = false; @@ -294,7 +282,7 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) * to respond with PATH_NOT_COVERED to requests that include the prefix. */ if (!nodfs) { - rc = dfs_get_referral(mnt_ctx, ctx->UNC + 1, NULL, NULL); + rc = dfs_get_referral(mnt_ctx, ctx->UNC + 1, NULL); if (rc) { cifs_dbg(FYI, "%s: no dfs referral for %s: %d\n", __func__, ctx->UNC + 1, rc); @@ -314,10 +302,8 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) cifs_mount_put_conns(mnt_ctx); rc = get_session(mnt_ctx, NULL); } - if (!rc) { - set_root_smb_session(mnt_ctx); + if (!rc) rc = __dfs_mount_share(mnt_ctx); - } return rc; } diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h index 1aa2bc65b3bc..ed4cd7cf1ec6 100644 --- a/fs/smb/client/dfs.h +++ b/fs/smb/client/dfs.h @@ -12,6 +12,7 @@ #include "dfs_cache.h" #include "cifs_unicode.h" #include +#include #define DFS_INTERLINK(v) \ (((v) & DFSREF_REFERRAL_SERVER) && !((v) & DFSREF_STORAGE_SERVER)) @@ -25,8 +26,9 @@ struct dfs_ref { }; struct dfs_ref_walk { - struct dfs_ref *ref; - struct dfs_ref refs[MAX_NESTED_LINKS]; + struct cifs_mount_ctx *mnt_ctx; + struct dfs_ref *ref; + struct dfs_ref refs[MAX_NESTED_LINKS]; }; #define ref_walk_start(w) ((w)->refs) @@ -35,7 +37,6 @@ struct dfs_ref_walk { #define ref_walk_descend(w) (--ref_walk_cur(w) >= ref_walk_start(w)) #define ref_walk_tit(w) (ref_walk_cur(w)->tit) -#define ref_walk_empty(w) (!ref_walk_tit(w)) #define ref_walk_path(w) (ref_walk_cur(w)->path) #define ref_walk_fpath(w) (ref_walk_cur(w)->full_path) #define ref_walk_tl(w) (&ref_walk_cur(w)->tl) @@ -51,9 +52,11 @@ static inline struct dfs_ref_walk *ref_walk_alloc(void) return rw; } -static inline void ref_walk_init(struct dfs_ref_walk *rw) +static inline void ref_walk_init(struct dfs_ref_walk *rw, + struct cifs_mount_ctx *mnt_ctx) { memset(rw, 0, sizeof(*rw)); + rw->mnt_ctx = mnt_ctx; ref_walk_cur(rw) = ref_walk_start(rw); } @@ -93,15 +96,23 @@ static inline int ref_walk_advance(struct dfs_ref_walk *rw) static inline struct dfs_cache_tgt_iterator * ref_walk_next_tgt(struct dfs_ref_walk *rw) { - struct dfs_cache_tgt_iterator *tit; struct dfs_ref *ref = ref_walk_cur(rw); + struct dfs_cache_tgt_iterator *tit; + + if (IS_ERR(ref->tit)) + return NULL; if (!ref->tit) tit = dfs_cache_get_tgt_iterator(&ref->tl); else tit = dfs_cache_get_next_tgt(&ref->tl, ref->tit); + + if (!tit) { + ref->tit = ERR_PTR(-ENOENT); + return NULL; + } ref->tit = tit; - return tit; + return ref->tit; } static inline int ref_walk_get_tgt(struct dfs_ref_walk *rw, @@ -112,11 +123,6 @@ static inline int ref_walk_get_tgt(struct dfs_ref_walk *rw, ref_walk_tit(rw), tgt); } -static inline int ref_walk_num_tgts(struct dfs_ref_walk *rw) -{ - return dfs_cache_get_nr_tgts(ref_walk_tl(rw)); -} - static inline void ref_walk_set_tgt_hint(struct dfs_ref_walk *rw) { dfs_cache_noreq_update_tgthint(ref_walk_path(rw) + 1, @@ -136,6 +142,15 @@ static inline void ref_walk_set_tcon(struct dfs_ref_walk *rw, } } +static inline void ref_walk_mark_end(struct dfs_ref_walk *rw) +{ + struct dfs_ref *ref = ref_walk_cur(rw) - 1; + + WARN_ON_ONCE(ref < ref_walk_start(rw)); + dfs_cache_noreq_update_tgthint(ref->path + 1, ref->tit); + ref->tit = ERR_PTR(-ENOENT); /* end marker */ +} + int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref, struct smb3_fs_context *ctx); int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx); @@ -145,15 +160,16 @@ static inline char *dfs_get_path(struct cifs_sb_info *cifs_sb, const char *path) return dfs_cache_canonical_path(path, cifs_sb->local_nls, cifs_remap(cifs_sb)); } -static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *path, - struct dfs_info3_param *ref, struct dfs_cache_tgt_list *tl) +static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, + const char *path, + struct dfs_cache_tgt_list *tl) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; struct cifs_ses *rses = ctx->dfs_root_ses ?: mnt_ctx->ses; return dfs_cache_find(mnt_ctx->xid, rses, cifs_sb->local_nls, - cifs_remap(cifs_sb), path, ref, tl); + cifs_remap(cifs_sb), path, NULL, tl); } /* diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 541608b0267e..5022bb1f122a 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -1096,11 +1096,8 @@ int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, static bool target_share_equal(struct cifs_tcon *tcon, const char *s1) { struct TCP_Server_Info *server = tcon->ses->server; - struct sockaddr_storage ss; - const char *host; const char *s2 = &tcon->tree_name[1]; - size_t hostlen; - char unc[sizeof("\\\\") + SERVER_NAME_LENGTH] = {0}; + struct sockaddr_storage ss; bool match; int rc; @@ -1111,18 +1108,13 @@ static bool target_share_equal(struct cifs_tcon *tcon, const char *s1) * Resolve share's hostname and check if server address matches. Otherwise just ignore it * as we could not have upcall to resolve hostname or failed to convert ip address. */ - extract_unc_hostname(s1, &host, &hostlen); - scnprintf(unc, sizeof(unc), "\\\\%.*s", (int)hostlen, host); - - rc = dns_resolve_server_name_to_ip(unc, (struct sockaddr *)&ss, NULL); - if (rc < 0) { - cifs_dbg(FYI, "%s: could not resolve %.*s. assuming server address matches.\n", - __func__, (int)hostlen, host); + rc = dns_resolve_unc(server->dns_dom, s1, (struct sockaddr *)&ss); + if (rc < 0) return true; - } cifs_server_lock(server); match = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, (struct sockaddr *)&ss); + cifs_dbg(FYI, "%s: [share=%s] ipaddr matched: %s\n", __func__, s1, str_yes_no(match)); cifs_server_unlock(server); return match; @@ -1149,13 +1141,11 @@ static char *get_ses_refpath(struct cifs_ses *ses) struct TCP_Server_Info *server = ses->server; char *path = ERR_PTR(-ENOENT); - mutex_lock(&server->refpath_lock); if (server->leaf_fullpath) { - path = kstrdup(server->leaf_fullpath + 1, GFP_ATOMIC); + path = kstrdup(server->leaf_fullpath + 1, GFP_KERNEL); if (!path) path = ERR_PTR(-ENOMEM); } - mutex_unlock(&server->refpath_lock); return path; } diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 864b194dbaa0..d1e95632ac54 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -627,7 +627,7 @@ int cifs_mknod(struct mnt_idmap *idmap, struct inode *inode, goto mknod_out; } - trace_smb3_mknod_enter(xid, tcon->ses->Suid, tcon->tid, full_path); + trace_smb3_mknod_enter(xid, tcon->tid, tcon->ses->Suid, full_path); rc = tcon->ses->server->ops->make_node(xid, inode, direntry, tcon, full_path, mode, @@ -635,9 +635,9 @@ int cifs_mknod(struct mnt_idmap *idmap, struct inode *inode, mknod_out: if (rc) - trace_smb3_mknod_err(xid, tcon->ses->Suid, tcon->tid, rc); + trace_smb3_mknod_err(xid, tcon->tid, tcon->ses->Suid, rc); else - trace_smb3_mknod_done(xid, tcon->ses->Suid, tcon->tid); + trace_smb3_mknod_done(xid, tcon->tid, tcon->ses->Suid); free_dentry_path(page); free_xid(xid); @@ -737,7 +737,8 @@ again: } static int -cifs_d_revalidate(struct dentry *direntry, unsigned int flags) +cifs_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *direntry, unsigned int flags) { struct inode *inode; int rc; diff --git a/fs/smb/client/dns_resolve.c b/fs/smb/client/dns_resolve.c index 8bf8978bc5d6..de7f4b384718 100644 --- a/fs/smb/client/dns_resolve.c +++ b/fs/smb/client/dns_resolve.c @@ -20,69 +20,77 @@ #include "cifsproto.h" #include "cifs_debug.h" -/** - * dns_resolve_server_name_to_ip - Resolve UNC server name to ip address. - * @unc: UNC path specifying the server (with '/' as delimiter) - * @ip_addr: Where to return the IP address. - * @expiry: Where to return the expiry time for the dns record. - * - * Returns zero success, -ve on error. - */ -int -dns_resolve_server_name_to_ip(const char *unc, struct sockaddr *ip_addr, time64_t *expiry) +static int resolve_name(const char *name, size_t namelen, struct sockaddr *addr) { - const char *hostname, *sep; char *ip; - int len, rc; + int rc; - if (!ip_addr || !unc) - return -EINVAL; - - len = strlen(unc); - if (len < 3) { - cifs_dbg(FYI, "%s: unc is too short: %s\n", __func__, unc); - return -EINVAL; - } - - /* Discount leading slashes for cifs */ - len -= 2; - hostname = unc + 2; - - /* Search for server name delimiter */ - sep = memchr(hostname, '/', len); - if (sep) - len = sep - hostname; - else - cifs_dbg(FYI, "%s: probably server name is whole unc: %s\n", - __func__, unc); - - /* Try to interpret hostname as an IPv4 or IPv6 address */ - rc = cifs_convert_address(ip_addr, hostname, len); - if (rc > 0) { - cifs_dbg(FYI, "%s: unc is IP, skipping dns upcall: %*.*s\n", __func__, len, len, - hostname); - return 0; - } - - /* Perform the upcall */ - rc = dns_query(current->nsproxy->net_ns, NULL, hostname, len, - NULL, &ip, expiry, false); + rc = dns_query(current->nsproxy->net_ns, NULL, name, + namelen, NULL, &ip, NULL, false); if (rc < 0) { cifs_dbg(FYI, "%s: unable to resolve: %*.*s\n", - __func__, len, len, hostname); + __func__, (int)namelen, (int)namelen, name); } else { - cifs_dbg(FYI, "%s: resolved: %*.*s to %s expiry %llu\n", - __func__, len, len, hostname, ip, - expiry ? (*expiry) : 0); + cifs_dbg(FYI, "%s: resolved: %*.*s to %s\n", + __func__, (int)namelen, (int)namelen, name, ip); - rc = cifs_convert_address(ip_addr, ip, strlen(ip)); + rc = cifs_convert_address(addr, ip, strlen(ip)); kfree(ip); - if (!rc) { - cifs_dbg(FYI, "%s: unable to determine ip address\n", __func__); + cifs_dbg(FYI, "%s: unable to determine ip address\n", + __func__); rc = -EHOSTUNREACH; - } else + } else { rc = 0; + } } return rc; } + +/** + * dns_resolve_name - Perform an upcall to resolve hostname to an ip address. + * @dom: DNS domain name (or NULL) + * @name: Name to look up + * @namelen: Length of name + * @ip_addr: Where to return the IP address + * + * Returns zero on success, -ve code otherwise. + */ +int dns_resolve_name(const char *dom, const char *name, + size_t namelen, struct sockaddr *ip_addr) +{ + size_t len; + char *s; + int rc; + + cifs_dbg(FYI, "%s: dom=%s name=%.*s\n", __func__, dom, (int)namelen, name); + if (!ip_addr || !name || !*name || !namelen) + return -EINVAL; + + cifs_dbg(FYI, "%s: hostname=%.*s\n", __func__, (int)namelen, name); + /* Try to interpret hostname as an IPv4 or IPv6 address */ + rc = cifs_convert_address(ip_addr, name, namelen); + if (rc > 0) { + cifs_dbg(FYI, "%s: unc is IP, skipping dns upcall: %*.*s\n", + __func__, (int)namelen, (int)namelen, name); + return 0; + } + + /* + * If @name contains a NetBIOS name and @dom has been specified, then + * convert @name to an FQDN and try resolving it first. + */ + if (dom && *dom && cifs_netbios_name(name, namelen)) { + len = strnlen(dom, CIFS_MAX_DOMAINNAME_LEN) + namelen + 2; + s = kmalloc(len, GFP_KERNEL); + if (!s) + return -ENOMEM; + + scnprintf(s, len, "%.*s.%s", (int)namelen, name, dom); + rc = resolve_name(s, len - 1, ip_addr); + kfree(s); + if (!rc) + return 0; + } + return resolve_name(name, namelen, ip_addr); +} diff --git a/fs/smb/client/dns_resolve.h b/fs/smb/client/dns_resolve.h index 6eb0c15a2440..0dc706f2c422 100644 --- a/fs/smb/client/dns_resolve.h +++ b/fs/smb/client/dns_resolve.h @@ -12,9 +12,30 @@ #define _DNS_RESOLVE_H #include +#include "cifsglob.h" +#include "cifsproto.h" #ifdef __KERNEL__ -int dns_resolve_server_name_to_ip(const char *unc, struct sockaddr *ip_addr, time64_t *expiry); + +int dns_resolve_name(const char *dom, const char *name, + size_t namelen, struct sockaddr *ip_addr); + +static inline int dns_resolve_unc(const char *dom, const char *unc, + struct sockaddr *ip_addr) +{ + const char *name; + size_t namelen; + + if (!unc || strlen(unc) < 3) + return -EINVAL; + + extract_unc_hostname(unc, &name, &namelen); + if (!namelen) + return -EINVAL; + + return dns_resolve_name(dom, name, namelen, ip_addr); +} + #endif /* KERNEL */ #endif /* _DNS_RESOLVE_H */ diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index a58a3333ecc3..79de2f2f9c41 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -227,7 +227,8 @@ static void cifs_issue_read(struct netfs_io_subrequest *subreq) return; failed: - netfs_read_subreq_terminated(subreq, rc, false); + subreq->error = rc; + netfs_read_subreq_terminated(subreq); } /* @@ -990,7 +991,11 @@ int cifs_open(struct inode *inode, struct file *file) } /* Get the cached handle as SMB2 close is deferred */ - rc = cifs_get_readable_path(tcon, full_path, &cfile); + if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { + rc = cifs_get_writable_path(tcon, full_path, FIND_WR_FSUID_ONLY, &cfile); + } else { + rc = cifs_get_readable_path(tcon, full_path, &cfile); + } if (rc == 0) { if (file->f_flags == cfile->f_flags) { file->private_data = cfile; diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 49123f458d0c..e9b286d9a7ba 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -133,6 +133,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_flag("rootfs", Opt_rootfs), fsparam_flag("compress", Opt_compress), fsparam_flag("witness", Opt_witness), + fsparam_flag_no("nativesocket", Opt_nativesocket), /* Mount options which take uid or gid */ fsparam_uid("backupuid", Opt_backupuid), @@ -185,6 +186,8 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_string("cache", Opt_cache), fsparam_string("reparse", Opt_reparse), fsparam_string("upcall_target", Opt_upcalltarget), + fsparam_string("symlink", Opt_symlink), + fsparam_string("symlinkroot", Opt_symlinkroot), /* Arguments that should be ignored */ fsparam_flag("guest", Opt_ignore), @@ -332,6 +335,7 @@ cifs_parse_cache_flavor(struct fs_context *fc, char *value, struct smb3_fs_conte static const match_table_t reparse_flavor_tokens = { { Opt_reparse_default, "default" }, + { Opt_reparse_none, "none" }, { Opt_reparse_nfs, "nfs" }, { Opt_reparse_wsl, "wsl" }, { Opt_reparse_err, NULL }, @@ -346,6 +350,9 @@ static int parse_reparse_flavor(struct fs_context *fc, char *value, case Opt_reparse_default: ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; break; + case Opt_reparse_none: + ctx->reparse_type = CIFS_REPARSE_TYPE_NONE; + break; case Opt_reparse_nfs: ctx->reparse_type = CIFS_REPARSE_TYPE_NFS; break; @@ -359,6 +366,55 @@ static int parse_reparse_flavor(struct fs_context *fc, char *value, return 0; } +static const match_table_t symlink_flavor_tokens = { + { Opt_symlink_default, "default" }, + { Opt_symlink_none, "none" }, + { Opt_symlink_native, "native" }, + { Opt_symlink_unix, "unix" }, + { Opt_symlink_mfsymlinks, "mfsymlinks" }, + { Opt_symlink_sfu, "sfu" }, + { Opt_symlink_nfs, "nfs" }, + { Opt_symlink_wsl, "wsl" }, + { Opt_symlink_err, NULL }, +}; + +static int parse_symlink_flavor(struct fs_context *fc, char *value, + struct smb3_fs_context *ctx) +{ + substring_t args[MAX_OPT_ARGS]; + + switch (match_token(value, symlink_flavor_tokens, args)) { + case Opt_symlink_default: + ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT; + break; + case Opt_symlink_none: + ctx->symlink_type = CIFS_SYMLINK_TYPE_NONE; + break; + case Opt_symlink_native: + ctx->symlink_type = CIFS_SYMLINK_TYPE_NATIVE; + break; + case Opt_symlink_unix: + ctx->symlink_type = CIFS_SYMLINK_TYPE_UNIX; + break; + case Opt_symlink_mfsymlinks: + ctx->symlink_type = CIFS_SYMLINK_TYPE_MFSYMLINKS; + break; + case Opt_symlink_sfu: + ctx->symlink_type = CIFS_SYMLINK_TYPE_SFU; + break; + case Opt_symlink_nfs: + ctx->symlink_type = CIFS_SYMLINK_TYPE_NFS; + break; + case Opt_symlink_wsl: + ctx->symlink_type = CIFS_SYMLINK_TYPE_WSL; + break; + default: + cifs_errorf(fc, "bad symlink= option: %s\n", value); + return 1; + } + return 0; +} + #define DUP_CTX_STR(field) \ do { \ if (ctx->field) { \ @@ -385,6 +441,8 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->source = NULL; new_ctx->iocharset = NULL; new_ctx->leaf_fullpath = NULL; + new_ctx->dns_dom = NULL; + new_ctx->symlinkroot = NULL; /* * Make sure to stay in sync with smb3_cleanup_fs_context_contents() */ @@ -399,6 +457,8 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(nodename); DUP_CTX_STR(iocharset); DUP_CTX_STR(leaf_fullpath); + DUP_CTX_STR(dns_dom); + DUP_CTX_STR(symlinkroot); return 0; } @@ -1725,6 +1785,23 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, if (parse_reparse_flavor(fc, param->string, ctx)) goto cifs_parse_mount_err; break; + case Opt_nativesocket: + ctx->nonativesocket = result.negated; + break; + case Opt_symlink: + if (parse_symlink_flavor(fc, param->string, ctx)) + goto cifs_parse_mount_err; + break; + case Opt_symlinkroot: + if (param->string[0] != '/') { + cifs_errorf(fc, "symlinkroot mount options must be absolute path\n"); + goto cifs_parse_mount_err; + } + kfree(ctx->symlinkroot); + ctx->symlinkroot = kstrdup(param->string, GFP_KERNEL); + if (!ctx->symlinkroot) + goto cifs_parse_mount_err; + break; } /* case Opt_ignore: - is ignored as expected ... */ @@ -1733,6 +1810,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, goto cifs_parse_mount_err; } + /* + * By default resolve all native absolute symlinks relative to "/mnt/". + * Same default has drvfs driver running in WSL for resolving SMB shares. + */ + if (!ctx->symlinkroot) + ctx->symlinkroot = kstrdup("/mnt/", GFP_KERNEL); + return 0; cifs_parse_mount_err: @@ -1743,6 +1827,24 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, return -EINVAL; } +enum cifs_symlink_type get_cifs_symlink_type(struct cifs_sb_info *cifs_sb) +{ + if (cifs_sb->ctx->symlink_type == CIFS_SYMLINK_TYPE_DEFAULT) { + if (cifs_sb->ctx->mfsymlinks) + return CIFS_SYMLINK_TYPE_MFSYMLINKS; + else if (cifs_sb->ctx->sfu_emul) + return CIFS_SYMLINK_TYPE_SFU; + else if (cifs_sb->ctx->linux_ext && !cifs_sb->ctx->no_linux_ext) + return CIFS_SYMLINK_TYPE_UNIX; + else if (cifs_sb->ctx->reparse_type != CIFS_REPARSE_TYPE_NONE) + return CIFS_SYMLINK_TYPE_NATIVE; + else + return CIFS_SYMLINK_TYPE_NONE; + } else { + return cifs_sb->ctx->symlink_type; + } +} + int smb3_init_fs_context(struct fs_context *fc) { struct smb3_fs_context *ctx; @@ -1819,6 +1921,8 @@ int smb3_init_fs_context(struct fs_context *fc) ctx->retrans = 1; ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; + ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT; + ctx->nonativesocket = 0; /* * short int override_uid = -1; @@ -1863,6 +1967,10 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->prepath = NULL; kfree(ctx->leaf_fullpath); ctx->leaf_fullpath = NULL; + kfree(ctx->dns_dom); + ctx->dns_dom = NULL; + kfree(ctx->symlinkroot); + ctx->symlinkroot = NULL; } void diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index ac6baa774ad3..881bfc08667e 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -43,11 +43,24 @@ enum { enum cifs_reparse_parm { Opt_reparse_default, + Opt_reparse_none, Opt_reparse_nfs, Opt_reparse_wsl, Opt_reparse_err }; +enum cifs_symlink_parm { + Opt_symlink_default, + Opt_symlink_none, + Opt_symlink_native, + Opt_symlink_unix, + Opt_symlink_mfsymlinks, + Opt_symlink_sfu, + Opt_symlink_nfs, + Opt_symlink_wsl, + Opt_symlink_err +}; + enum cifs_sec_param { Opt_sec_krb5, Opt_sec_krb5i, @@ -166,6 +179,9 @@ enum cifs_param { Opt_cache, Opt_reparse, Opt_upcalltarget, + Opt_nativesocket, + Opt_symlink, + Opt_symlinkroot, /* Mount options to be ignored */ Opt_ignore, @@ -294,11 +310,17 @@ struct smb3_fs_context { struct cifs_ses *dfs_root_ses; bool dfs_automount:1; /* set for dfs automount only */ enum cifs_reparse_type reparse_type; + enum cifs_symlink_type symlink_type; + bool nonativesocket:1; bool dfs_conn:1; /* set for dfs mounts */ + char *dns_dom; + char *symlinkroot; /* top level directory for native SMB symlinks in absolute format */ }; extern const struct fs_parameter_spec smb3_fs_parameters[]; +extern enum cifs_symlink_type get_cifs_symlink_type(struct cifs_sb_info *cifs_sb); + extern int smb3_init_fs_context(struct fs_context *fc); extern void smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx); extern void smb3_cleanup_fs_context(struct smb3_fs_context *ctx); diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index f146e06c97eb..9cc31cf6ebd0 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -990,7 +990,7 @@ cifs_get_file_info(struct file *filp) /* TODO: add support to query reparse tag */ data.adjust_tz = false; if (data.symlink_target) { - data.symlink = true; + data.reparse_point = true; data.reparse.tag = IO_REPARSE_TAG_SYMLINK; } path = build_path_from_dentry(dentry, page); @@ -1216,6 +1216,11 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data, full_path, iov, data); } + + if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) { + bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY; + rc = smb2_fix_symlink_target_type(&data->symlink_target, directory, cifs_sb); + } break; } @@ -2392,6 +2397,13 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit; + /* + * CIFSSMBRenameOpenFile() uses SMB_SET_FILE_RENAME_INFORMATION + * which is SMB PASSTHROUGH level. + */ + if (!(tcon->ses->capabilities & CAP_INFOLEVEL_PASSTHRU)) + goto do_rename_exit; + oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c index 47ddeb7fa111..6e6c09cc5ce7 100644 --- a/fs/smb/client/link.c +++ b/fs/smb/client/link.c @@ -18,6 +18,7 @@ #include "cifs_unicode.h" #include "smb2proto.h" #include "cifs_ioctl.h" +#include "fs_context.h" /* * M-F Symlink Functions - Begin @@ -604,22 +605,53 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, cifs_dbg(FYI, "symname is %s\n", symname); /* BB what if DFS and this volume is on different share? BB */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { - rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname); - } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { - rc = __cifs_sfu_make_node(xid, inode, direntry, pTcon, - full_path, S_IFLNK, 0, symname); + rc = -EOPNOTSUPP; + switch (get_cifs_symlink_type(cifs_sb)) { + case CIFS_SYMLINK_TYPE_DEFAULT: + /* should not happen, get_cifs_symlink_type() resolves the default */ + break; + + case CIFS_SYMLINK_TYPE_NONE: + break; + + case CIFS_SYMLINK_TYPE_UNIX: #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY - } else if (pTcon->unix_ext) { - rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname, - cifs_sb->local_nls, - cifs_remap(cifs_sb)); + if (pTcon->unix_ext) { + rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, + symname, + cifs_sb->local_nls, + cifs_remap(cifs_sb)); + } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - } else if (server->ops->create_reparse_symlink) { - rc = server->ops->create_reparse_symlink(xid, inode, direntry, - pTcon, full_path, - symname); - goto symlink_exit; + break; + + case CIFS_SYMLINK_TYPE_MFSYMLINKS: + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { + rc = create_mf_symlink(xid, pTcon, cifs_sb, + full_path, symname); + } + break; + + case CIFS_SYMLINK_TYPE_SFU: + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { + rc = __cifs_sfu_make_node(xid, inode, direntry, pTcon, + full_path, S_IFLNK, + 0, symname); + } + break; + + case CIFS_SYMLINK_TYPE_NATIVE: + case CIFS_SYMLINK_TYPE_NFS: + case CIFS_SYMLINK_TYPE_WSL: + if (server->ops->create_reparse_symlink) { + rc = server->ops->create_reparse_symlink(xid, inode, + direntry, + pTcon, + full_path, + symname); + goto symlink_exit; + } + break; } if (rc == 0) { diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 4373dd64b66d..b328dc5c7988 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -101,6 +101,7 @@ sesInfoFree(struct cifs_ses *buf_to_free) kfree_sensitive(buf_to_free->password2); kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); + kfree(buf_to_free->dns_dom); kfree_sensitive(buf_to_free->auth_key.response); spin_lock(&buf_to_free->iface_lock); list_for_each_entry_safe(iface, niface, &buf_to_free->iface_list, @@ -908,9 +909,9 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, *num_of_nodes = le16_to_cpu(rsp->NumberOfReferrals); if (*num_of_nodes < 1) { - cifs_dbg(VFS, "num_referrals: must be at least > 0, but we get num_referrals = %d\n", - *num_of_nodes); - rc = -EINVAL; + cifs_dbg(VFS | ONCE, "%s: [path=%s] num_referrals must be at least > 0, but we got %d\n", + __func__, searchName, *num_of_nodes); + rc = -ENOENT; goto parse_DFS_referrals_exit; } @@ -1171,33 +1172,25 @@ void cifs_put_tcp_super(struct super_block *sb) #ifdef CONFIG_CIFS_DFS_UPCALL int match_target_ip(struct TCP_Server_Info *server, - const char *share, size_t share_len, + const char *host, size_t hostlen, bool *result) { - int rc; - char *target; struct sockaddr_storage ss; + int rc; + + cifs_dbg(FYI, "%s: hostname=%.*s\n", __func__, (int)hostlen, host); *result = false; - target = kzalloc(share_len + 3, GFP_KERNEL); - if (!target) - return -ENOMEM; - - scnprintf(target, share_len + 3, "\\\\%.*s", (int)share_len, share); - - cifs_dbg(FYI, "%s: target name: %s\n", __func__, target + 2); - - rc = dns_resolve_server_name_to_ip(target, (struct sockaddr *)&ss, NULL); - kfree(target); - + rc = dns_resolve_name(server->dns_dom, host, hostlen, + (struct sockaddr *)&ss); if (rc < 0) return rc; spin_lock(&server->srv_lock); *result = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, (struct sockaddr *)&ss); spin_unlock(&server->srv_lock); - cifs_dbg(FYI, "%s: ip addresses match: %u\n", __func__, *result); + cifs_dbg(FYI, "%s: ip addresses matched: %s\n", __func__, str_yes_no(*result)); return 0; } diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c index 0f788031b740..e3f9213131c4 100644 --- a/fs/smb/client/namespace.c +++ b/fs/smb/client/namespace.c @@ -196,11 +196,28 @@ static struct vfsmount *cifs_do_automount(struct path *path) struct smb3_fs_context tmp; char *full_path; struct vfsmount *mnt; + struct cifs_sb_info *mntpt_sb; + struct cifs_ses *ses; if (IS_ROOT(mntpt)) return ERR_PTR(-ESTALE); - cur_ctx = CIFS_SB(mntpt->d_sb)->ctx; + mntpt_sb = CIFS_SB(mntpt->d_sb); + ses = cifs_sb_master_tcon(mntpt_sb)->ses; + cur_ctx = mntpt_sb->ctx; + + /* + * At this point, the root session should be in the mntpt sb. We should + * bring the sb context passwords in sync with the root session's + * passwords. This would help prevent unnecessary retries and password + * swaps for automounts. + */ + mutex_lock(&ses->session_mutex); + rc = smb3_sync_session_ctx_passwords(mntpt_sb, ses); + mutex_unlock(&ses->session_mutex); + + if (rc) + return ERR_PTR(rc); fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, mntpt); if (IS_ERR(fc)) diff --git a/fs/smb/client/netmisc.c b/fs/smb/client/netmisc.c index 2a8d71221e5e..9ec20601cee2 100644 --- a/fs/smb/client/netmisc.c +++ b/fs/smb/client/netmisc.c @@ -313,7 +313,6 @@ static const struct { ERRDOS, 2215, NT_STATUS_NO_LOGON_SERVERS}, { ERRHRD, ERRgeneral, NT_STATUS_NO_SUCH_LOGON_SESSION}, { ERRHRD, ERRgeneral, NT_STATUS_NO_SUCH_PRIVILEGE}, { - ERRDOS, ERRnoaccess, NT_STATUS_PRIVILEGE_NOT_HELD}, { ERRHRD, ERRgeneral, NT_STATUS_INVALID_ACCOUNT_NAME}, { ERRHRD, ERRgeneral, NT_STATUS_USER_EXISTS}, /* { This NT error code was 'sqashed' @@ -775,10 +774,10 @@ cifs_print_status(__u32 status_code) int idx = 0; while (nt_errs[idx].nt_errstr != NULL) { - if (((nt_errs[idx].nt_errcode) & 0xFFFFFF) == - (status_code & 0xFFFFFF)) { + if (nt_errs[idx].nt_errcode == status_code) { pr_notice("Status code returned 0x%08x %s\n", status_code, nt_errs[idx].nt_errstr); + return; } idx++; } @@ -871,6 +870,15 @@ map_smb_to_linux_error(char *buf, bool logErr) } /* else ERRHRD class errors or junk - return EIO */ + /* special cases for NT status codes which cannot be translated to DOS codes */ + if (smb->Flags2 & SMBFLG2_ERR_STATUS) { + __u32 err = le32_to_cpu(smb->Status.CifsError); + if (err == (NT_STATUS_NOT_A_REPARSE_POINT)) + rc = -ENODATA; + else if (err == (NT_STATUS_PRIVILEGE_NOT_HELD)) + rc = -EPERM; + } + cifs_dbg(FYI, "Mapping smb error code 0x%x to POSIX err %d\n", le32_to_cpu(smb->Status.CifsError), rc); diff --git a/fs/smb/client/nterr.c b/fs/smb/client/nterr.c index 358a766375b4..8f0bc441295e 100644 --- a/fs/smb/client/nterr.c +++ b/fs/smb/client/nterr.c @@ -13,6 +13,13 @@ const struct nt_err_code_struct nt_errs[] = { {"NT_STATUS_OK", NT_STATUS_OK}, + {"NT_STATUS_MEDIA_CHANGED", NT_STATUS_MEDIA_CHANGED}, + {"NT_STATUS_END_OF_MEDIA", NT_STATUS_END_OF_MEDIA}, + {"NT_STATUS_MEDIA_CHECK", NT_STATUS_MEDIA_CHECK}, + {"NT_STATUS_NO_DATA_DETECTED", NT_STATUS_NO_DATA_DETECTED}, + {"NT_STATUS_STOPPED_ON_SYMLINK", NT_STATUS_STOPPED_ON_SYMLINK}, + {"NT_STATUS_DEVICE_REQUIRES_CLEANING", NT_STATUS_DEVICE_REQUIRES_CLEANING}, + {"NT_STATUS_DEVICE_DOOR_OPEN", NT_STATUS_DEVICE_DOOR_OPEN}, {"NT_STATUS_UNSUCCESSFUL", NT_STATUS_UNSUCCESSFUL}, {"NT_STATUS_NOT_IMPLEMENTED", NT_STATUS_NOT_IMPLEMENTED}, {"NT_STATUS_INVALID_INFO_CLASS", NT_STATUS_INVALID_INFO_CLASS}, @@ -667,8 +674,10 @@ const struct nt_err_code_struct nt_errs[] = { {"NT_STATUS_QUOTA_LIST_INCONSISTENT", NT_STATUS_QUOTA_LIST_INCONSISTENT}, {"NT_STATUS_FILE_IS_OFFLINE", NT_STATUS_FILE_IS_OFFLINE}, + {"NT_STATUS_NOT_A_REPARSE_POINT", NT_STATUS_NOT_A_REPARSE_POINT}, {"NT_STATUS_NO_MORE_ENTRIES", NT_STATUS_NO_MORE_ENTRIES}, {"NT_STATUS_MORE_ENTRIES", NT_STATUS_MORE_ENTRIES}, {"NT_STATUS_SOME_UNMAPPED", NT_STATUS_SOME_UNMAPPED}, + {"NT_STATUS_NO_SUCH_JOB", NT_STATUS_NO_SUCH_JOB}, {NULL, 0} }; diff --git a/fs/smb/client/nterr.h b/fs/smb/client/nterr.h index edd4741cab0a..180602c22355 100644 --- a/fs/smb/client/nterr.h +++ b/fs/smb/client/nterr.h @@ -546,6 +546,7 @@ extern const struct nt_err_code_struct nt_errs[]; #define NT_STATUS_TOO_MANY_LINKS 0xC0000000 | 0x0265 #define NT_STATUS_QUOTA_LIST_INCONSISTENT 0xC0000000 | 0x0266 #define NT_STATUS_FILE_IS_OFFLINE 0xC0000000 | 0x0267 +#define NT_STATUS_NOT_A_REPARSE_POINT 0xC0000000 | 0x0275 #define NT_STATUS_NO_SUCH_JOB 0xC0000000 | 0xEDE /* scheduler */ #endif /* _NTERR_H */ diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 273358d20a46..50f96259d9ad 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -413,7 +413,7 @@ ffirst_retry: cifsFile->invalidHandle = false; } else if ((rc == -EOPNOTSUPP) && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) { - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM; + cifs_autodisable_serverino(cifs_sb); goto ffirst_retry; } error_exit: diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index d88b41133e00..0a5a52a8a7dd 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -14,6 +14,20 @@ #include "fs_context.h" #include "reparse.h" +static int mknod_nfs(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev, + const char *symname); + +static int mknod_wsl(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev, + const char *symname); + +static int create_native_symlink(const unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, const char *symname); + static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb, const unsigned int xid, const char *full_path, @@ -23,38 +37,149 @@ static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb, int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, const char *full_path, const char *symname) +{ + switch (get_cifs_symlink_type(CIFS_SB(inode->i_sb))) { + case CIFS_SYMLINK_TYPE_NATIVE: + return create_native_symlink(xid, inode, dentry, tcon, full_path, symname); + case CIFS_SYMLINK_TYPE_NFS: + return mknod_nfs(xid, inode, dentry, tcon, full_path, S_IFLNK, 0, symname); + case CIFS_SYMLINK_TYPE_WSL: + return mknod_wsl(xid, inode, dentry, tcon, full_path, S_IFLNK, 0, symname); + default: + return -EOPNOTSUPP; + } +} + +static int create_native_symlink(const unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, const char *symname) { struct reparse_symlink_data_buffer *buf = NULL; - struct cifs_open_info_data data; + struct cifs_open_info_data data = {}; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct inode *new; struct kvec iov; - __le16 *path; + __le16 *path = NULL; bool directory; - char *sym, sep = CIFS_DIR_SEP(cifs_sb); - u16 len, plen; + char *symlink_target = NULL; + char *sym = NULL; + char sep = CIFS_DIR_SEP(cifs_sb); + u16 len, plen, poff, slen; int rc = 0; if (strlen(symname) > REPARSE_SYM_PATH_MAX) return -ENAMETOOLONG; - sym = kstrdup(symname, GFP_KERNEL); - if (!sym) - return -ENOMEM; + symlink_target = kstrdup(symname, GFP_KERNEL); + if (!symlink_target) { + rc = -ENOMEM; + goto out; + } data = (struct cifs_open_info_data) { .reparse_point = true, .reparse = { .tag = IO_REPARSE_TAG_SYMLINK, }, - .symlink_target = sym, + .symlink_target = symlink_target, }; - convert_delimiter(sym, sep); + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { + /* + * This is a request to create an absolute symlink on the server + * which does not support POSIX paths, and expects symlink in + * NT-style path. So convert absolute Linux symlink target path + * to the absolute NT-style path. Root of the NT-style path for + * symlinks is specified in "symlinkroot" mount option. This will + * ensure compatibility of this symlink stored in absolute form + * on the SMB server. + */ + if (!strstarts(symname, cifs_sb->ctx->symlinkroot)) { + /* + * If the absolute Linux symlink target path is not + * inside "symlinkroot" location then there is no way + * to convert such Linux symlink to NT-style path. + */ + cifs_dbg(VFS, + "absolute symlink '%s' cannot be converted to NT format " + "because it is outside of symlinkroot='%s'\n", + symname, cifs_sb->ctx->symlinkroot); + rc = -EINVAL; + goto out; + } + len = strlen(cifs_sb->ctx->symlinkroot); + if (cifs_sb->ctx->symlinkroot[len-1] != '/') + len++; + if (symname[len] >= 'a' && symname[len] <= 'z' && + (symname[len+1] == '/' || symname[len+1] == '\0')) { + /* + * Symlink points to Linux target /symlinkroot/x/path/... + * where 'x' is the lowercase local Windows drive. + * NT-style path for 'x' has common form \??\X:\path\... + * with uppercase local Windows drive. + */ + int common_path_len = strlen(symname+len+1)+1; + sym = kzalloc(6+common_path_len, GFP_KERNEL); + if (!sym) { + rc = -ENOMEM; + goto out; + } + memcpy(sym, "\\??\\", 4); + sym[4] = symname[len] - ('a'-'A'); + sym[5] = ':'; + memcpy(sym+6, symname+len+1, common_path_len); + } else { + /* Unhandled absolute symlink. Report an error. */ + cifs_dbg( + VFS, + "absolute symlink '%s' cannot be converted to NT format " + "because it points to unknown target\n", + symname); + rc = -EINVAL; + goto out; + } + } else { + /* + * This is request to either create an absolute symlink on + * server which expects POSIX paths or it is an request to + * create a relative symlink from the current directory. + * These paths have same format as relative SMB symlinks, + * so no conversion is needed. So just take symname as-is. + */ + sym = kstrdup(symname, GFP_KERNEL); + if (!sym) { + rc = -ENOMEM; + goto out; + } + } + + if (sep == '\\') + convert_delimiter(sym, sep); + + /* + * For absolute NT symlinks it is required to pass also leading + * backslash and to not mangle NT object prefix "\\??\\" and not to + * mangle colon in drive letter. But cifs_convert_path_to_utf16() + * removes leading backslash and replaces '?' and ':'. So temporary + * mask these characters in NT object prefix by '_' and then change + * them back. + */ + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') + sym[0] = sym[1] = sym[2] = sym[5] = '_'; + path = cifs_convert_path_to_utf16(sym, cifs_sb); if (!path) { rc = -ENOMEM; goto out; } + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { + sym[0] = '\\'; + sym[1] = sym[2] = '?'; + sym[5] = ':'; + path[0] = cpu_to_le16('\\'); + path[1] = path[2] = cpu_to_le16('?'); + path[5] = cpu_to_le16(':'); + } + /* * SMB distinguish between symlink to directory and symlink to file. * They cannot be exchanged (symlink of file type which points to @@ -67,8 +192,18 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, if (rc < 0) goto out; - plen = 2 * UniStrnlen((wchar_t *)path, REPARSE_SYM_PATH_MAX); - len = sizeof(*buf) + plen * 2; + slen = 2 * UniStrnlen((wchar_t *)path, REPARSE_SYM_PATH_MAX); + poff = 0; + plen = slen; + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { + /* + * For absolute NT symlinks skip leading "\\??\\" in PrintName as + * PrintName is user visible location in DOS/Win32 format (not in NT format). + */ + poff = 4; + plen -= 2 * poff; + } + len = sizeof(*buf) + plen + slen; buf = kzalloc(len, GFP_KERNEL); if (!buf) { rc = -ENOMEM; @@ -77,17 +212,17 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, buf->ReparseTag = cpu_to_le32(IO_REPARSE_TAG_SYMLINK); buf->ReparseDataLength = cpu_to_le16(len - sizeof(struct reparse_data_buffer)); + buf->SubstituteNameOffset = cpu_to_le16(plen); - buf->SubstituteNameLength = cpu_to_le16(plen); - memcpy(&buf->PathBuffer[plen], path, plen); + buf->SubstituteNameLength = cpu_to_le16(slen); + memcpy(&buf->PathBuffer[plen], path, slen); + buf->PrintNameOffset = 0; buf->PrintNameLength = cpu_to_le16(plen); - memcpy(buf->PathBuffer, path, plen); + memcpy(buf->PathBuffer, path+poff, plen); + buf->Flags = cpu_to_le32(*symname != '/' ? SYMLINK_FLAG_RELATIVE : 0); - if (*sym != sep) - buf->Flags = cpu_to_le32(SYMLINK_FLAG_RELATIVE); - convert_delimiter(sym, '/'); iov.iov_base = buf; iov.iov_len = len; new = smb2_get_reparse_inode(&data, inode->i_sb, xid, @@ -98,6 +233,7 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, else rc = PTR_ERR(new); out: + kfree(sym); kfree(path); cifs_free_open_info(&data); kfree(buf); @@ -242,8 +378,39 @@ static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb, return 0; } -static int nfs_set_reparse_buf(struct reparse_posix_data *buf, +static int create_native_socket(const unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path) +{ + struct reparse_data_buffer buf = { + .ReparseTag = cpu_to_le32(IO_REPARSE_TAG_AF_UNIX), + .ReparseDataLength = cpu_to_le16(0), + }; + struct cifs_open_info_data data = { + .reparse_point = true, + .reparse = { .tag = IO_REPARSE_TAG_AF_UNIX, .buf = &buf, }, + }; + struct kvec iov = { + .iov_base = &buf, + .iov_len = sizeof(buf), + }; + struct inode *new; + int rc = 0; + + new = smb2_get_reparse_inode(&data, inode->i_sb, xid, + tcon, full_path, false, &iov, NULL); + if (!IS_ERR(new)) + d_instantiate(dentry, new); + else + rc = PTR_ERR(new); + cifs_free_open_info(&data); + return rc; +} + +static int nfs_set_reparse_buf(struct reparse_nfs_data_buffer *buf, mode_t mode, dev_t dev, + __le16 *symname_utf16, + int symname_utf16_len, struct kvec *iov) { u64 type; @@ -254,7 +421,13 @@ static int nfs_set_reparse_buf(struct reparse_posix_data *buf, switch ((type = reparse_mode_nfs_type(mode))) { case NFS_SPECFILE_BLK: case NFS_SPECFILE_CHR: - dlen = sizeof(__le64); + dlen = 2 * sizeof(__le32); + ((__le32 *)buf->DataBuffer)[0] = cpu_to_le32(MAJOR(dev)); + ((__le32 *)buf->DataBuffer)[1] = cpu_to_le32(MINOR(dev)); + break; + case NFS_SPECFILE_LNK: + dlen = symname_utf16_len; + memcpy(buf->DataBuffer, symname_utf16, symname_utf16_len); break; case NFS_SPECFILE_FIFO: case NFS_SPECFILE_SOCK: @@ -269,8 +442,6 @@ static int nfs_set_reparse_buf(struct reparse_posix_data *buf, buf->InodeType = cpu_to_le64(type); buf->ReparseDataLength = cpu_to_le16(len + dlen - sizeof(struct reparse_data_buffer)); - *(__le64 *)buf->DataBuffer = cpu_to_le64(((u64)MINOR(dev) << 32) | - MAJOR(dev)); iov->iov_base = buf; iov->iov_len = len + dlen; return 0; @@ -278,23 +449,45 @@ static int nfs_set_reparse_buf(struct reparse_posix_data *buf, static int mknod_nfs(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, - const char *full_path, umode_t mode, dev_t dev) + const char *full_path, umode_t mode, dev_t dev, + const char *symname) { + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_open_info_data data; - struct reparse_posix_data *p; + struct reparse_nfs_data_buffer *p = NULL; + __le16 *symname_utf16 = NULL; + int symname_utf16_len = 0; struct inode *new; struct kvec iov; __u8 buf[sizeof(*p) + sizeof(__le64)]; int rc; - p = (struct reparse_posix_data *)buf; - rc = nfs_set_reparse_buf(p, mode, dev, &iov); + if (S_ISLNK(mode)) { + symname_utf16 = cifs_strndup_to_utf16(symname, strlen(symname), + &symname_utf16_len, + cifs_sb->local_nls, + NO_MAP_UNI_RSVD); + if (!symname_utf16) { + rc = -ENOMEM; + goto out; + } + symname_utf16_len -= 2; /* symlink is without trailing wide-nul */ + p = kzalloc(sizeof(*p) + symname_utf16_len, GFP_KERNEL); + if (!p) { + rc = -ENOMEM; + goto out; + } + } else { + p = (struct reparse_nfs_data_buffer *)buf; + } + rc = nfs_set_reparse_buf(p, mode, dev, symname_utf16, symname_utf16_len, &iov); if (rc) - return rc; + goto out; data = (struct cifs_open_info_data) { .reparse_point = true, - .reparse = { .tag = IO_REPARSE_TAG_NFS, .posix = p, }, + .reparse = { .tag = IO_REPARSE_TAG_NFS, .buf = (struct reparse_data_buffer *)p, }, + .symlink_target = kstrdup(symname, GFP_KERNEL), }; new = smb2_get_reparse_inode(&data, inode->i_sb, xid, @@ -304,12 +497,25 @@ static int mknod_nfs(unsigned int xid, struct inode *inode, else rc = PTR_ERR(new); cifs_free_open_info(&data); +out: + if (S_ISLNK(mode)) { + kfree(symname_utf16); + kfree(p); + } return rc; } -static int wsl_set_reparse_buf(struct reparse_data_buffer *buf, - mode_t mode, struct kvec *iov) +static int wsl_set_reparse_buf(struct reparse_data_buffer **buf, + mode_t mode, const char *symname, + struct cifs_sb_info *cifs_sb, + struct kvec *iov) { + struct reparse_wsl_symlink_data_buffer *symlink_buf; + __le16 *symname_utf16; + int symname_utf16_len; + int symname_utf8_maxlen; + int symname_utf8_len; + size_t buf_len; u32 tag; switch ((tag = reparse_mode_wsl_tag(mode))) { @@ -317,16 +523,45 @@ static int wsl_set_reparse_buf(struct reparse_data_buffer *buf, case IO_REPARSE_TAG_LX_CHR: case IO_REPARSE_TAG_LX_FIFO: case IO_REPARSE_TAG_AF_UNIX: + buf_len = sizeof(struct reparse_data_buffer); + *buf = kzalloc(buf_len, GFP_KERNEL); + if (!*buf) + return -ENOMEM; + break; + case IO_REPARSE_TAG_LX_SYMLINK: + symname_utf16 = cifs_strndup_to_utf16(symname, strlen(symname), + &symname_utf16_len, + cifs_sb->local_nls, + NO_MAP_UNI_RSVD); + if (!symname_utf16) + return -ENOMEM; + symname_utf8_maxlen = symname_utf16_len/2*3; + symlink_buf = kzalloc(sizeof(struct reparse_wsl_symlink_data_buffer) + + symname_utf8_maxlen, GFP_KERNEL); + if (!symlink_buf) { + kfree(symname_utf16); + return -ENOMEM; + } + /* Flag 0x02000000 is unknown, but all wsl symlinks have this value */ + symlink_buf->Flags = cpu_to_le32(0x02000000); + /* PathBuffer is in UTF-8 but without trailing null-term byte */ + symname_utf8_len = utf16s_to_utf8s((wchar_t *)symname_utf16, symname_utf16_len/2, + UTF16_LITTLE_ENDIAN, + symlink_buf->PathBuffer, + symname_utf8_maxlen); + *buf = (struct reparse_data_buffer *)symlink_buf; + buf_len = sizeof(struct reparse_wsl_symlink_data_buffer) + symname_utf8_len; + kfree(symname_utf16); break; default: return -EOPNOTSUPP; } - buf->ReparseTag = cpu_to_le32(tag); - buf->Reserved = 0; - buf->ReparseDataLength = 0; - iov->iov_base = buf; - iov->iov_len = sizeof(*buf); + (*buf)->ReparseTag = cpu_to_le32(tag); + (*buf)->Reserved = 0; + (*buf)->ReparseDataLength = cpu_to_le16(buf_len - sizeof(struct reparse_data_buffer)); + iov->iov_base = *buf; + iov->iov_len = buf_len; return 0; } @@ -415,27 +650,32 @@ static int wsl_set_xattrs(struct inode *inode, umode_t _mode, static int mknod_wsl(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, - const char *full_path, umode_t mode, dev_t dev) + const char *full_path, umode_t mode, dev_t dev, + const char *symname) { + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_open_info_data data; - struct reparse_data_buffer buf; + struct reparse_data_buffer *buf; struct smb2_create_ea_ctx *cc; struct inode *new; unsigned int len; struct kvec reparse_iov, xattr_iov; int rc; - rc = wsl_set_reparse_buf(&buf, mode, &reparse_iov); + rc = wsl_set_reparse_buf(&buf, mode, symname, cifs_sb, &reparse_iov); if (rc) return rc; rc = wsl_set_xattrs(inode, mode, dev, &xattr_iov); - if (rc) + if (rc) { + kfree(buf); return rc; + } data = (struct cifs_open_info_data) { .reparse_point = true, - .reparse = { .tag = le32_to_cpu(buf.ReparseTag), .buf = &buf, }, + .reparse = { .tag = le32_to_cpu(buf->ReparseTag), .buf = buf, }, + .symlink_target = kstrdup(symname, GFP_KERNEL), }; cc = xattr_iov.iov_base; @@ -452,6 +692,7 @@ static int mknod_wsl(unsigned int xid, struct inode *inode, rc = PTR_ERR(new); cifs_free_open_info(&data); kfree(xattr_iov.iov_base); + kfree(buf); return rc; } @@ -460,21 +701,22 @@ int smb2_mknod_reparse(unsigned int xid, struct inode *inode, const char *full_path, umode_t mode, dev_t dev) { struct smb3_fs_context *ctx = CIFS_SB(inode->i_sb)->ctx; - int rc = -EOPNOTSUPP; + + if (S_ISSOCK(mode) && !ctx->nonativesocket && ctx->reparse_type != CIFS_REPARSE_TYPE_NONE) + return create_native_socket(xid, inode, dentry, tcon, full_path); switch (ctx->reparse_type) { case CIFS_REPARSE_TYPE_NFS: - rc = mknod_nfs(xid, inode, dentry, tcon, full_path, mode, dev); - break; + return mknod_nfs(xid, inode, dentry, tcon, full_path, mode, dev, NULL); case CIFS_REPARSE_TYPE_WSL: - rc = mknod_wsl(xid, inode, dentry, tcon, full_path, mode, dev); - break; + return mknod_wsl(xid, inode, dentry, tcon, full_path, mode, dev, NULL); + default: + return -EOPNOTSUPP; } - return rc; } /* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */ -static int parse_reparse_posix(struct reparse_posix_data *buf, +static int parse_reparse_nfs(struct reparse_nfs_data_buffer *buf, struct cifs_sb_info *cifs_sb, struct cifs_open_info_data *data) { @@ -536,43 +778,160 @@ static int parse_reparse_posix(struct reparse_posix_data *buf, } int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len, - bool unicode, bool relative, + bool relative, const char *full_path, struct cifs_sb_info *cifs_sb) { char sep = CIFS_DIR_SEP(cifs_sb); char *linux_target = NULL; char *smb_target = NULL; + int symlinkroot_len; + int abs_path_len; + char *abs_path; int levels; int rc; int i; - /* Check that length it valid for unicode/non-unicode mode */ - if (!len || (unicode && (len % 2))) { + /* Check that length it valid */ + if (!len || (len % 2)) { cifs_dbg(VFS, "srv returned malformed symlink buffer\n"); rc = -EIO; goto out; } /* - * Check that buffer does not contain UTF-16 null codepoint in unicode - * mode or null byte in non-unicode mode because Linux cannot process - * symlink with null byte. + * Check that buffer does not contain UTF-16 null codepoint + * because Linux cannot process symlink with null byte. */ - if ((unicode && UniStrnlen((wchar_t *)buf, len/2) != len/2) || - (!unicode && strnlen(buf, len) != len)) { + if (UniStrnlen((wchar_t *)buf, len/2) != len/2) { cifs_dbg(VFS, "srv returned null byte in native symlink target location\n"); rc = -EIO; goto out; } - smb_target = cifs_strndup_from_utf16(buf, len, unicode, cifs_sb->local_nls); + smb_target = cifs_strndup_from_utf16(buf, len, true, cifs_sb->local_nls); if (!smb_target) { rc = -ENOMEM; goto out; } - if (smb_target[0] == sep && relative) { + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && !relative) { + /* + * This is an absolute symlink from the server which does not + * support POSIX paths, so the symlink is in NT-style path. + * So convert it to absolute Linux symlink target path. Root of + * the NT-style path for symlinks is specified in "symlinkroot" + * mount option. + * + * Root of the DOS and Win32 paths is at NT path \??\ + * It means that DOS/Win32 path C:\folder\file.txt is + * NT path \??\C:\folder\file.txt + * + * NT systems have some well-known object symlinks in their NT + * hierarchy, which is needed to take into account when resolving + * other symlinks. Most commonly used symlink paths are: + * \?? -> \GLOBAL?? + * \DosDevices -> \?? + * \GLOBAL??\GLOBALROOT -> \ + * \GLOBAL??\Global -> \GLOBAL?? + * \GLOBAL??\NUL -> \Device\Null + * \GLOBAL??\UNC -> \Device\Mup + * \GLOBAL??\PhysicalDrive0 -> \Device\Harddisk0\DR0 (for each harddisk) + * \GLOBAL??\A: -> \Device\Floppy0 (if A: is the first floppy) + * \GLOBAL??\C: -> \Device\HarddiskVolume1 (if C: is the first harddisk) + * \GLOBAL??\D: -> \Device\CdRom0 (if D: is first cdrom) + * \SystemRoot -> \Device\Harddisk0\Partition1\WINDOWS (or where is NT system installed) + * \Volume{...} -> \Device\HarddiskVolume1 (where ... is system generated guid) + * + * In most common cases, absolute NT symlinks points to path on + * DOS/Win32 drive letter, system-specific Volume or on UNC share. + * Here are few examples of commonly used absolute NT symlinks + * created by mklink.exe tool: + * \??\C:\folder\file.txt + * \??\\C:\folder\file.txt + * \??\UNC\server\share\file.txt + * \??\\UNC\server\share\file.txt + * \??\Volume{b75e2c83-0000-0000-0000-602f00000000}\folder\file.txt + * + * It means that the most common path prefix \??\ is also NT path + * symlink (to \GLOBAL??). It is less common that second path + * separator is double backslash, but it is valid. + * + * Volume guid is randomly generated by the target system and so + * only the target system knows the mapping between guid and the + * hardisk number. Over SMB it is not possible to resolve this + * mapping, therefore symlinks pointing to target location of + * volume guids are totally unusable over SMB. + * + * For now parse only symlink paths available for DOS and Win32. + * Those are paths with \??\ prefix or paths which points to \??\ + * via other NT symlink (\DosDevices\, \GLOBAL??\, ...). + */ + abs_path = smb_target; +globalroot: + if (strstarts(abs_path, "\\??\\")) + abs_path += sizeof("\\??\\")-1; + else if (strstarts(abs_path, "\\DosDevices\\")) + abs_path += sizeof("\\DosDevices\\")-1; + else if (strstarts(abs_path, "\\GLOBAL??\\")) + abs_path += sizeof("\\GLOBAL??\\")-1; + else { + /* Unhandled absolute symlink, points outside of DOS/Win32 */ + cifs_dbg(VFS, + "absolute symlink '%s' cannot be converted from NT format " + "because points to unknown target\n", + smb_target); + rc = -EIO; + goto out; + } + + /* Sometimes path separator after \?? is double backslash */ + if (abs_path[0] == '\\') + abs_path++; + + while (strstarts(abs_path, "Global\\")) + abs_path += sizeof("Global\\")-1; + + if (strstarts(abs_path, "GLOBALROOT\\")) { + /* Label globalroot requires path with leading '\\', so do not trim '\\' */ + abs_path += sizeof("GLOBALROOT")-1; + goto globalroot; + } + + /* For now parse only paths to drive letters */ + if (((abs_path[0] >= 'A' && abs_path[0] <= 'Z') || + (abs_path[0] >= 'a' && abs_path[0] <= 'z')) && + abs_path[1] == ':' && + (abs_path[2] == '\\' || abs_path[2] == '\0')) { + /* Convert drive letter to lowercase and drop colon */ + char drive_letter = abs_path[0]; + if (drive_letter >= 'A' && drive_letter <= 'Z') + drive_letter += 'a'-'A'; + abs_path++; + abs_path[0] = drive_letter; + } else { + /* Unhandled absolute symlink. Report an error. */ + cifs_dbg(VFS, + "absolute symlink '%s' cannot be converted from NT format " + "because points to unknown target\n", + smb_target); + rc = -EIO; + goto out; + } + + abs_path_len = strlen(abs_path)+1; + symlinkroot_len = strlen(cifs_sb->ctx->symlinkroot); + if (cifs_sb->ctx->symlinkroot[symlinkroot_len-1] == '/') + symlinkroot_len--; + linux_target = kmalloc(symlinkroot_len + 1 + abs_path_len, GFP_KERNEL); + if (!linux_target) { + rc = -ENOMEM; + goto out; + } + memcpy(linux_target, cifs_sb->ctx->symlinkroot, symlinkroot_len); + linux_target[symlinkroot_len] = '/'; + memcpy(linux_target + symlinkroot_len + 1, abs_path, abs_path_len); + } else if (smb_target[0] == sep && relative) { /* * This is a relative SMB symlink from the top of the share, * which is the top level directory of the Linux mount point. @@ -601,6 +960,12 @@ int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len, } memcpy(linux_target + levels*3, smb_target+1, smb_target_len); /* +1 to skip leading sep */ } else { + /* + * This is either an absolute symlink in POSIX-style format + * or relative SMB symlink from the current directory. + * These paths have same format as Linux symlinks, so no + * conversion is needed. + */ linux_target = smb_target; smb_target = NULL; } @@ -620,8 +985,8 @@ out: return rc; } -static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym, - u32 plen, bool unicode, +static int parse_reparse_native_symlink(struct reparse_symlink_data_buffer *sym, + u32 plen, struct cifs_sb_info *cifs_sb, const char *full_path, struct cifs_open_info_data *data) @@ -641,7 +1006,6 @@ static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym, return smb2_parse_native_symlink(&data->symlink_target, sym->PathBuffer + offs, len, - unicode, le32_to_cpu(sym->Flags) & SYMLINK_FLAG_RELATIVE, full_path, cifs_sb); @@ -696,7 +1060,7 @@ static int parse_reparse_wsl_symlink(struct reparse_wsl_symlink_data_buffer *buf int parse_reparse_point(struct reparse_data_buffer *buf, u32 plen, struct cifs_sb_info *cifs_sb, const char *full_path, - bool unicode, struct cifs_open_info_data *data) + struct cifs_open_info_data *data) { struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); @@ -705,12 +1069,12 @@ int parse_reparse_point(struct reparse_data_buffer *buf, /* See MS-FSCC 2.1.2 */ switch (le32_to_cpu(buf->ReparseTag)) { case IO_REPARSE_TAG_NFS: - return parse_reparse_posix((struct reparse_posix_data *)buf, + return parse_reparse_nfs((struct reparse_nfs_data_buffer *)buf, cifs_sb, data); case IO_REPARSE_TAG_SYMLINK: - return parse_reparse_symlink( + return parse_reparse_native_symlink( (struct reparse_symlink_data_buffer *)buf, - plen, unicode, cifs_sb, full_path, data); + plen, cifs_sb, full_path, data); case IO_REPARSE_TAG_LX_SYMLINK: return parse_reparse_wsl_symlink( (struct reparse_wsl_symlink_data_buffer *)buf, @@ -744,14 +1108,15 @@ int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, buf = (struct reparse_data_buffer *)((u8 *)io + le32_to_cpu(io->OutputOffset)); - return parse_reparse_point(buf, plen, cifs_sb, full_path, true, data); + return parse_reparse_point(buf, plen, cifs_sb, full_path, data); } -static void wsl_to_fattr(struct cifs_open_info_data *data, +static bool wsl_to_fattr(struct cifs_open_info_data *data, struct cifs_sb_info *cifs_sb, u32 tag, struct cifs_fattr *fattr) { struct smb2_file_full_ea_info *ea; + bool have_xattr_dev = false; u32 next = 0; switch (tag) { @@ -794,21 +1159,31 @@ static void wsl_to_fattr(struct cifs_open_info_data *data, fattr->cf_uid = wsl_make_kuid(cifs_sb, v); else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen)) fattr->cf_gid = wsl_make_kgid(cifs_sb, v); - else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) + else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) { + /* File type in reparse point tag and in xattr mode must match. */ + if (S_DT(fattr->cf_mode) != S_DT(le32_to_cpu(*(__le32 *)v))) + return false; fattr->cf_mode = (umode_t)le32_to_cpu(*(__le32 *)v); - else if (!strncmp(name, SMB2_WSL_XATTR_DEV, nlen)) + } else if (!strncmp(name, SMB2_WSL_XATTR_DEV, nlen)) { fattr->cf_rdev = reparse_mkdev(v); + have_xattr_dev = true; + } } while (next); out: + + /* Major and minor numbers for char and block devices are mandatory. */ + if (!have_xattr_dev && (tag == IO_REPARSE_TAG_LX_CHR || tag == IO_REPARSE_TAG_LX_BLK)) + return false; + fattr->cf_dtype = S_DT(fattr->cf_mode); + return true; } static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, struct cifs_open_info_data *data) { - struct reparse_posix_data *buf = data->reparse.posix; - + struct reparse_nfs_data_buffer *buf = (struct reparse_nfs_data_buffer *)data->reparse.buf; if (buf == NULL) return true; @@ -874,7 +1249,9 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, case IO_REPARSE_TAG_AF_UNIX: case IO_REPARSE_TAG_LX_CHR: case IO_REPARSE_TAG_LX_BLK: - wsl_to_fattr(data, cifs_sb, tag, fattr); + ok = wsl_to_fattr(data, cifs_sb, tag, fattr); + if (!ok) + return false; break; case IO_REPARSE_TAG_NFS: ok = posix_reparse_to_fattr(cifs_sb, fattr, data); diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h index ff05b0e75c92..5a753fec7e2c 100644 --- a/fs/smb/client/reparse.h +++ b/fs/smb/client/reparse.h @@ -50,6 +50,7 @@ static inline kgid_t wsl_make_kgid(struct cifs_sb_info *cifs_sb, static inline u64 reparse_mode_nfs_type(mode_t mode) { switch (mode & S_IFMT) { + case S_IFLNK: return NFS_SPECFILE_LNK; case S_IFBLK: return NFS_SPECFILE_BLK; case S_IFCHR: return NFS_SPECFILE_CHR; case S_IFIFO: return NFS_SPECFILE_FIFO; @@ -61,6 +62,7 @@ static inline u64 reparse_mode_nfs_type(mode_t mode) static inline u32 reparse_mode_wsl_tag(mode_t mode) { switch (mode & S_IFMT) { + case S_IFLNK: return IO_REPARSE_TAG_LX_SYMLINK; case S_IFBLK: return IO_REPARSE_TAG_LX_BLK; case S_IFCHR: return IO_REPARSE_TAG_LX_CHR; case S_IFIFO: return IO_REPARSE_TAG_LX_FIFO; diff --git a/fs/smb/client/rfc1002pdu.h b/fs/smb/client/rfc1002pdu.h index ae1d025da294..ac82c2f3a4a2 100644 --- a/fs/smb/client/rfc1002pdu.h +++ b/fs/smb/client/rfc1002pdu.h @@ -24,7 +24,7 @@ struct rfc1002_session_packet { __u8 type; __u8 flags; - __u16 length; + __be16 length; union { struct { __u8 called_len; @@ -35,8 +35,8 @@ struct rfc1002_session_packet { __u8 scope2; /* null */ } __attribute__((packed)) session_req; struct { - __u32 retarget_ip_addr; - __u16 port; + __be32 retarget_ip_addr; + __be16 port; } __attribute__((packed)) retarget_resp; __u8 neg_ses_resp_error_code; /* POSITIVE_SESSION_RESPONSE packet does not include trailer. diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 3306fb655136..faa80e7d54a6 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -27,31 +27,6 @@ static int cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface); -bool -is_server_using_iface(struct TCP_Server_Info *server, - struct cifs_server_iface *iface) -{ - struct sockaddr_in *i4 = (struct sockaddr_in *)&iface->sockaddr; - struct sockaddr_in6 *i6 = (struct sockaddr_in6 *)&iface->sockaddr; - struct sockaddr_in *s4 = (struct sockaddr_in *)&server->dstaddr; - struct sockaddr_in6 *s6 = (struct sockaddr_in6 *)&server->dstaddr; - - if (server->dstaddr.ss_family != iface->sockaddr.ss_family) - return false; - if (server->dstaddr.ss_family == AF_INET) { - if (s4->sin_addr.s_addr != i4->sin_addr.s_addr) - return false; - } else if (server->dstaddr.ss_family == AF_INET6) { - if (memcmp(&s6->sin6_addr, &i6->sin6_addr, - sizeof(i6->sin6_addr)) != 0) - return false; - } else { - /* unknown family.. */ - return false; - } - return true; -} - bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface) { int i; @@ -1260,12 +1235,13 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) switch (requested) { case Kerberos: case RawNTLMSSP: + case IAKerb: return requested; case Unspecified: if (server->sec_ntlmssp && (global_secflags & CIFSSEC_MAY_NTLMSSP)) return RawNTLMSSP; - if ((server->sec_kerberos || server->sec_mskerberos) && + if ((server->sec_kerberos || server->sec_mskerberos || server->sec_iakerb) && (global_secflags & CIFSSEC_MAY_KRB5)) return Kerberos; fallthrough; diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index db3695eddcf9..9756b876a75e 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -551,7 +551,7 @@ static int cifs_query_path_info(const unsigned int xid, int rc; FILE_ALL_INFO fi = {}; - data->symlink = false; + data->reparse_point = false; data->adjust_tz = false; /* could do find first instead but this returns more info */ @@ -569,32 +569,8 @@ static int cifs_query_path_info(const unsigned int xid, } if (!rc) { - int tmprc; - int oplock = 0; - struct cifs_fid fid; - struct cifs_open_parms oparms; - move_cifs_info_to_smb2(&data->fi, &fi); - - if (!(le32_to_cpu(fi.Attributes) & ATTR_REPARSE)) - return 0; - - oparms = (struct cifs_open_parms) { - .tcon = tcon, - .cifs_sb = cifs_sb, - .desired_access = FILE_READ_ATTRIBUTES, - .create_options = cifs_create_options(cifs_sb, 0), - .disposition = FILE_OPEN, - .path = full_path, - .fid = &fid, - }; - - /* Need to check if this is a symbolic link or not */ - tmprc = CIFS_open(xid, &oparms, &oplock, NULL); - if (tmprc == -EOPNOTSUPP) - data->symlink = true; - else if (tmprc == 0) - CIFSSMBClose(xid, tcon, fid.netfid); + data->reparse_point = le32_to_cpu(fi.Attributes) & ATTR_REPARSE; } return rc; @@ -614,7 +590,13 @@ static int cifs_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, * There may be higher info levels that work but are there Windows * server or network appliances for which IndexNumber field is not * guaranteed unique? + * + * CIFSGetSrvInodeNumber() uses SMB_QUERY_FILE_INTERNAL_INFO + * which is SMB PASSTHROUGH level therefore check for capability. + * Note that this function can be called with tcon == NULL. */ + if (tcon && !(tcon->ses->capabilities & CAP_INFOLEVEL_PASSTHRU)) + return -EOPNOTSUPP; return CIFSGetSrvInodeNumber(xid, tcon, full_path, uniqueid, cifs_sb->local_nls, cifs_remap(cifs_sb)); @@ -1004,7 +986,7 @@ static int cifs_parse_reparse_point(struct cifs_sb_info *cifs_sb, buf = (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol + le32_to_cpu(io->DataOffset)); - return parse_reparse_point(buf, plen, cifs_sb, full_path, true, data); + return parse_reparse_point(buf, plen, cifs_sb, full_path, data); } static bool diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index e836bc2193dd..d609a20fb98a 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -42,14 +42,14 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) end = (struct smb2_error_context_rsp *)((u8 *)err + iov->iov_len); do { if (le32_to_cpu(p->ErrorId) == SMB2_ERROR_ID_DEFAULT) { - sym = (struct smb2_symlink_err_rsp *)&p->ErrorContextData; + sym = (struct smb2_symlink_err_rsp *)p->ErrorContextData; break; } cifs_dbg(FYI, "%s: skipping unhandled error context: 0x%x\n", __func__, le32_to_cpu(p->ErrorId)); len = ALIGN(le32_to_cpu(p->ErrorDataLength), 8); - p = (struct smb2_error_context_rsp *)((u8 *)&p->ErrorContextData + len); + p = (struct smb2_error_context_rsp *)(p->ErrorContextData + len); } while (p < end); } else if (le32_to_cpu(err->ByteCount) >= sizeof(*sym) && iov->iov_len >= SMB2_SYMLINK_STRUCT_SIZE) { @@ -63,6 +63,52 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) return sym; } +int smb2_fix_symlink_target_type(char **target, bool directory, struct cifs_sb_info *cifs_sb) +{ + char *buf; + int len; + + /* + * POSIX server does not distinguish between symlinks to file and + * symlink directory. So nothing is needed to fix on the client side. + */ + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) + return 0; + + if (!*target) + return -EIO; + + len = strlen(*target); + if (!len) + return -EIO; + + /* + * If this is directory symlink and it does not have trailing slash then + * append it. Trailing slash simulates Windows/SMB behavior which do not + * allow resolving directory symlink to file. + */ + if (directory && (*target)[len-1] != '/') { + buf = krealloc(*target, len+2, GFP_KERNEL); + if (!buf) + return -ENOMEM; + buf[len] = '/'; + buf[len+1] = '\0'; + *target = buf; + len++; + } + + /* + * If this is a file (non-directory) symlink and it points to path name + * with trailing slash then this is an invalid symlink because file name + * cannot contain slash character. File name with slash is invalid on + * both Windows and Linux systems. So return an error for such symlink. + */ + if (!directory && (*target)[len-1] == '/') + return -EIO; + + return 0; +} + int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec *iov, const char *full_path, char **path) { @@ -89,7 +135,6 @@ int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec return smb2_parse_native_symlink(path, (char *)sym->PathBuffer + sub_offs, sub_len, - true, le32_to_cpu(sym->Flags) & SYMLINK_FLAG_RELATIVE, full_path, cifs_sb); @@ -133,6 +178,11 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 NULL, NULL, NULL); oparms->create_options &= ~OPEN_REPARSE_POINT; } + if (!rc) { + bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY; + rc = smb2_fix_symlink_target_type(&data->symlink_target, + directory, oparms->cifs_sb); + } } } diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index a55f0044d30b..5dfb30b0a852 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -176,27 +176,27 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, struct kvec *out_iov, int *out_buftype, struct dentry *dentry) { - struct reparse_data_buffer *rbuf; - struct smb2_compound_vars *vars = NULL; - struct kvec *rsp_iov, *iov; - struct smb_rqst *rqst; - int rc; - __le16 *utf16_path = NULL; - __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; - struct cifs_fid fid; - struct cifs_ses *ses = tcon->ses; - struct TCP_Server_Info *server; - int num_rqst = 0, i; - int resp_buftype[MAX_COMPOUND]; struct smb2_query_info_rsp *qi_rsp = NULL; + struct smb2_compound_vars *vars = NULL; + __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; struct cifs_open_info_data *idata; - struct inode *inode = NULL; - int flags = 0; - __u8 delete_pending[8] = {1, 0, 0, 0, 0, 0, 0, 0}; - unsigned int size[2]; - void *data[2]; - unsigned int len; + struct cifs_ses *ses = tcon->ses; + struct reparse_data_buffer *rbuf; + struct TCP_Server_Info *server; + int resp_buftype[MAX_COMPOUND]; int retries = 0, cur_sleep = 1; + __u8 delete_pending[8] = {1,}; + struct kvec *rsp_iov, *iov; + struct inode *inode = NULL; + __le16 *utf16_path = NULL; + struct smb_rqst *rqst; + unsigned int size[2]; + struct cifs_fid fid; + int num_rqst = 0, i; + unsigned int len; + int tmp_rc, rc; + int flags = 0; + void *data[2]; replay_again: /* reinitialize for possible replay */ @@ -298,8 +298,8 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_query_info_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_query_info_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_POSIX_QUERY_INFO: rqst[num_rqst].rq_iov = &vars->qi_iov; @@ -334,18 +334,18 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_posix_query_info_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_posix_query_info_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_DELETE: - trace_smb3_delete_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_delete_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_MKDIR: /* * Directories are created through parameters in the * SMB2_open() call. */ - trace_smb3_mkdir_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_mkdir_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_RMDIR: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -363,7 +363,7 @@ replay_again: goto finished; smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); - trace_smb3_rmdir_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_rmdir_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_SET_EOF: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -398,7 +398,7 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_set_eof_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_SET_INFO: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -429,8 +429,8 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_set_info_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_set_info_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_RENAME: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -469,7 +469,7 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_rename_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_rename_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_HARDLINK: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -496,7 +496,7 @@ replay_again: goto finished; smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); - trace_smb3_hardlink_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_hardlink_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_SET_REPARSE: rqst[num_rqst].rq_iov = vars->io_iov; @@ -523,8 +523,8 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_set_reparse_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_set_reparse_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_GET_REPARSE: rqst[num_rqst].rq_iov = vars->io_iov; @@ -549,8 +549,8 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_get_reparse_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_get_reparse_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_QUERY_WSL_EA: rqst[num_rqst].rq_iov = &vars->ea_iov; @@ -584,6 +584,8 @@ replay_again: goto finished; } num_rqst++; + trace_smb3_query_wsl_ea_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; default: cifs_dbg(VFS, "Invalid command\n"); @@ -637,7 +639,14 @@ finished: tcon->need_reconnect = true; } + tmp_rc = rc; for (i = 0; i < num_cmds; i++) { + char *buf = rsp_iov[i + i].iov_base; + + if (buf && resp_buftype[i + 1] != CIFS_NO_BUFFER) + rc = server->ops->map_error(buf, false); + else + rc = tmp_rc; switch (cmds[i]) { case SMB2_OP_QUERY_INFO: idata = in_iov[i].iov_base; @@ -656,11 +665,11 @@ finished: } SMB2_query_info_free(&rqst[num_rqst++]); if (rc) - trace_smb3_query_info_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_query_info_compound_err(xid, tcon->tid, + ses->Suid, rc); else - trace_smb3_query_info_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_query_info_compound_done(xid, tcon->tid, + ses->Suid); break; case SMB2_OP_POSIX_QUERY_INFO: idata = in_iov[i].iov_base; @@ -683,15 +692,15 @@ finished: SMB2_query_info_free(&rqst[num_rqst++]); if (rc) - trace_smb3_posix_query_info_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_posix_query_info_compound_err(xid, tcon->tid, + ses->Suid, rc); else - trace_smb3_posix_query_info_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_posix_query_info_compound_done(xid, tcon->tid, + ses->Suid); break; case SMB2_OP_DELETE: if (rc) - trace_smb3_delete_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_delete_err(xid, tcon->tid, ses->Suid, rc); else { /* * If dentry (hence, inode) is NULL, lease break is going to @@ -699,59 +708,59 @@ finished: */ if (inode) cifs_mark_open_handles_for_deleted_file(inode, full_path); - trace_smb3_delete_done(xid, ses->Suid, tcon->tid); + trace_smb3_delete_done(xid, tcon->tid, ses->Suid); } break; case SMB2_OP_MKDIR: if (rc) - trace_smb3_mkdir_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_mkdir_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_mkdir_done(xid, ses->Suid, tcon->tid); + trace_smb3_mkdir_done(xid, tcon->tid, ses->Suid); break; case SMB2_OP_HARDLINK: if (rc) - trace_smb3_hardlink_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_hardlink_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_hardlink_done(xid, ses->Suid, tcon->tid); + trace_smb3_hardlink_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_RENAME: if (rc) - trace_smb3_rename_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_rename_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_rename_done(xid, ses->Suid, tcon->tid); + trace_smb3_rename_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_RMDIR: if (rc) - trace_smb3_rmdir_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_rmdir_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_rmdir_done(xid, ses->Suid, tcon->tid); + trace_smb3_rmdir_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_SET_EOF: if (rc) - trace_smb3_set_eof_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_set_eof_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_set_eof_done(xid, ses->Suid, tcon->tid); + trace_smb3_set_eof_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_SET_INFO: if (rc) - trace_smb3_set_info_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_set_info_compound_err(xid, tcon->tid, + ses->Suid, rc); else - trace_smb3_set_info_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_set_info_compound_done(xid, tcon->tid, + ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_SET_REPARSE: if (rc) { - trace_smb3_set_reparse_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_set_reparse_compound_err(xid, tcon->tid, + ses->Suid, rc); } else { - trace_smb3_set_reparse_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_set_reparse_compound_done(xid, tcon->tid, + ses->Suid); } SMB2_ioctl_free(&rqst[num_rqst++]); break; @@ -764,18 +773,18 @@ finished: rbuf = reparse_buf_ptr(iov); if (IS_ERR(rbuf)) { rc = PTR_ERR(rbuf); - trace_smb3_set_reparse_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_get_reparse_compound_err(xid, tcon->tid, + ses->Suid, rc); } else { idata->reparse.tag = le32_to_cpu(rbuf->ReparseTag); - trace_smb3_set_reparse_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_get_reparse_compound_done(xid, tcon->tid, + ses->Suid); } memset(iov, 0, sizeof(*iov)); resp_buftype[i + 1] = CIFS_NO_BUFFER; } else { - trace_smb3_set_reparse_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_get_reparse_compound_err(xid, tcon->tid, + ses->Suid, rc); } SMB2_ioctl_free(&rqst[num_rqst++]); break; @@ -792,17 +801,18 @@ finished: } } if (!rc) { - trace_smb3_query_wsl_ea_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_query_wsl_ea_compound_done(xid, tcon->tid, + ses->Suid); } else { - trace_smb3_query_wsl_ea_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_query_wsl_ea_compound_err(xid, tcon->tid, + ses->Suid, rc); } SMB2_query_info_free(&rqst[num_rqst++]); break; } } SMB2_close_free(&rqst[num_rqst]); + rc = tmp_rc; num_cmds += 2; if (out_iov && out_buftype) { @@ -858,22 +868,52 @@ static int parse_create_response(struct cifs_open_info_data *data, return rc; } +/* Check only if SMB2_OP_QUERY_WSL_EA command failed in the compound chain */ +static bool ea_unsupported(int *cmds, int num_cmds, + struct kvec *out_iov, int *out_buftype) +{ + int i; + + if (cmds[num_cmds - 1] != SMB2_OP_QUERY_WSL_EA) + return false; + + for (i = 1; i < num_cmds - 1; i++) { + struct smb2_hdr *hdr = out_iov[i].iov_base; + + if (out_buftype[i] == CIFS_NO_BUFFER || !hdr || + hdr->Status != STATUS_SUCCESS) + return false; + } + return true; +} + +static inline void free_rsp_iov(struct kvec *iovs, int *buftype, int count) +{ + int i; + + for (i = 0; i < count; i++) { + free_rsp_buf(buftype[i], iovs[i].iov_base); + memset(&iovs[i], 0, sizeof(*iovs)); + buftype[i] = CIFS_NO_BUFFER; + } +} + int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, struct cifs_open_info_data *data) { - struct cifs_open_parms oparms; - __u32 create_options = 0; - struct cifsFileInfo *cfile; + struct kvec in_iov[3], out_iov[5] = {}; struct cached_fid *cfid = NULL; + struct cifs_open_parms oparms; + struct cifsFileInfo *cfile; + __u32 create_options = 0; + int out_buftype[5] = {}; struct smb2_hdr *hdr; - struct kvec in_iov[3], out_iov[3] = {}; - int out_buftype[3] = {}; + int num_cmds = 0; int cmds[3]; bool islink; - int i, num_cmds = 0; int rc, rc2; data->adjust_tz = false; @@ -943,14 +983,14 @@ int smb2_query_path_info(const unsigned int xid, if (rc || !data->reparse_point) goto out; - if (!tcon->posix_extensions) - cmds[num_cmds++] = SMB2_OP_QUERY_WSL_EA; /* * Skip SMB2_OP_GET_REPARSE if symlink already parsed in create * response. */ if (data->reparse.tag != IO_REPARSE_TAG_SYMLINK) cmds[num_cmds++] = SMB2_OP_GET_REPARSE; + if (!tcon->posix_extensions) + cmds[num_cmds++] = SMB2_OP_QUERY_WSL_EA; oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_READ_ATTRIBUTES | @@ -958,9 +998,23 @@ int smb2_query_path_info(const unsigned int xid, FILE_OPEN, create_options | OPEN_REPARSE_POINT, ACL_NO_MODE); cifs_get_readable_path(tcon, full_path, &cfile); + free_rsp_iov(out_iov, out_buftype, ARRAY_SIZE(out_iov)); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, in_iov, cmds, num_cmds, - cfile, NULL, NULL, NULL); + cfile, out_iov, out_buftype, NULL); + if (rc && ea_unsupported(cmds, num_cmds, + out_iov, out_buftype)) { + if (data->reparse.tag != IO_REPARSE_TAG_LX_BLK && + data->reparse.tag != IO_REPARSE_TAG_LX_CHR) + rc = 0; + else + rc = -EOPNOTSUPP; + } + + if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) { + bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY; + rc = smb2_fix_symlink_target_type(&data->symlink_target, directory, cifs_sb); + } break; case -EREMOTE: break; @@ -978,8 +1032,7 @@ int smb2_query_path_info(const unsigned int xid, } out: - for (i = 0; i < ARRAY_SIZE(out_buftype); i++) - free_rsp_buf(out_buftype[i], out_iov[i].iov_base); + free_rsp_iov(out_iov, out_buftype, ARRAY_SIZE(out_iov)); return rc; } diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c index b05313acf9b2..12c2b868789f 100644 --- a/fs/smb/client/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c @@ -380,7 +380,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_NO_LOGON_SERVERS, -EIO, "STATUS_NO_LOGON_SERVERS"}, {STATUS_NO_SUCH_LOGON_SESSION, -EIO, "STATUS_NO_SUCH_LOGON_SESSION"}, {STATUS_NO_SUCH_PRIVILEGE, -EIO, "STATUS_NO_SUCH_PRIVILEGE"}, - {STATUS_PRIVILEGE_NOT_HELD, -EIO, "STATUS_PRIVILEGE_NOT_HELD"}, + {STATUS_PRIVILEGE_NOT_HELD, -EPERM, "STATUS_PRIVILEGE_NOT_HELD"}, {STATUS_INVALID_ACCOUNT_NAME, -EIO, "STATUS_INVALID_ACCOUNT_NAME"}, {STATUS_USER_EXISTS, -EIO, "STATUS_USER_EXISTS"}, {STATUS_NO_SUCH_USER, -EIO, "STATUS_NO_SUCH_USER"}, @@ -871,7 +871,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_VALIDATE_CONTINUE, -EIO, "STATUS_VALIDATE_CONTINUE"}, {STATUS_NO_MATCH, -EIO, "STATUS_NO_MATCH"}, {STATUS_NO_MORE_MATCHES, -EIO, "STATUS_NO_MORE_MATCHES"}, - {STATUS_NOT_A_REPARSE_POINT, -EIO, "STATUS_NOT_A_REPARSE_POINT"}, + {STATUS_NOT_A_REPARSE_POINT, -ENODATA, "STATUS_NOT_A_REPARSE_POINT"}, {STATUS_IO_REPARSE_TAG_INVALID, -EIO, "STATUS_IO_REPARSE_TAG_INVALID"}, {STATUS_IO_REPARSE_TAG_MISMATCH, -EIO, "STATUS_IO_REPARSE_TAG_MISMATCH"}, diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 87cb1872db28..77309217dab4 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -658,7 +658,8 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, while (bytes_left >= (ssize_t)sizeof(*p)) { memset(&tmp_iface, 0, sizeof(tmp_iface)); - tmp_iface.speed = le64_to_cpu(p->LinkSpeed); + /* default to 1Gbps when link speed is unset */ + tmp_iface.speed = le64_to_cpu(p->LinkSpeed) ?: 1000000000; tmp_iface.rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0; tmp_iface.rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE) ? 1 : 0; @@ -3007,9 +3008,9 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, num_of_nodes, target_nodes, nls_codepage, remap, search_name, true /* is_unicode */); - if (rc) { - cifs_tcon_dbg(VFS, "parse error in %s rc=%d\n", __func__, rc); - goto out; + if (rc && rc != -ENOENT) { + cifs_tcon_dbg(VFS, "%s: failed to parse DFS referral %s: %d\n", + __func__, search_name, rc); } out: @@ -4388,7 +4389,7 @@ static struct folio_queue *cifs_alloc_folioq_buffer(ssize_t size) p = kmalloc(sizeof(*p), GFP_NOFS); if (!p) goto nomem; - folioq_init(p); + folioq_init(p, 0); if (tail) { tail->next = p; p->prev = tail; @@ -5076,6 +5077,7 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, { struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + struct cifs_open_info_data idata; struct cifs_io_parms io_parms = {}; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_fid fid; @@ -5145,10 +5147,20 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, CREATE_OPTION_SPECIAL, ACL_NO_MODE); oparms.fid = &fid; - rc = server->ops->open(xid, &oparms, &oplock, NULL); + rc = server->ops->open(xid, &oparms, &oplock, &idata); if (rc) goto out; + /* + * Check if the server honored ATTR_SYSTEM flag by CREATE_OPTION_SPECIAL + * option. If not then server does not support ATTR_SYSTEM and newly + * created file is not SFU compatible, which means that the call failed. + */ + if (!(le32_to_cpu(idata.fi.Attributes) & ATTR_SYSTEM)) { + rc = -EOPNOTSUPP; + goto out_close; + } + if (type_len + data_len > 0) { io_parms.pid = current->tgid; io_parms.tcon = tcon; @@ -5163,8 +5175,18 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, iov, ARRAY_SIZE(iov)-1); } +out_close: server->ops->close(xid, tcon, &fid); + /* + * If CREATE was successful but either setting ATTR_SYSTEM failed or + * writing type/data information failed then remove the intermediate + * object created by CREATE. Otherwise intermediate empty object stay + * on the server. + */ + if (rc) + server->ops->unlink(xid, tcon, full_path, cifs_sb, NULL); + out: kfree(symname_utf16); return rc; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 010eae9d6c47..40ad9e79437a 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1429,7 +1429,7 @@ smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) if (server->sec_ntlmssp && (global_secflags & CIFSSEC_MAY_NTLMSSP)) return RawNTLMSSP; - if ((server->sec_kerberos || server->sec_mskerberos) && + if ((server->sec_kerberos || server->sec_mskerberos || server->sec_iakerb) && (global_secflags & CIFSSEC_MAY_KRB5)) return Kerberos; fallthrough; @@ -4500,14 +4500,6 @@ smb2_new_read_req(void **buf, unsigned int *total_len, return rc; } -static void smb2_readv_worker(struct work_struct *work) -{ - struct cifs_io_subrequest *rdata = - container_of(work, struct cifs_io_subrequest, subreq.work); - - netfs_read_subreq_terminated(&rdata->subreq, rdata->result, false); -} - static void smb2_readv_callback(struct mid_q_entry *mid) { @@ -4615,15 +4607,17 @@ smb2_readv_callback(struct mid_q_entry *mid) __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } + if (rdata->got_bytes) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, server->credits, server->in_flight, 0, cifs_trace_rw_credits_read_response_clear); rdata->credits.value = 0; + rdata->subreq.error = rdata->result; rdata->subreq.transferred += rdata->got_bytes; trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress); - INIT_WORK(&rdata->subreq.work, smb2_readv_worker); - queue_work(cifsiod_wq, &rdata->subreq.work); + netfs_read_subreq_terminated(&rdata->subreq); release_mid(mid); trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0, server->credits, server->in_flight, @@ -4840,10 +4834,14 @@ smb2_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->subreq.len) + cifs_stats_bytes_written(tcon, written); + + if (written < wdata->subreq.len) { wdata->result = -ENOSPC; - else + } else if (written > 0) { wdata->subreq.len = written; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: @@ -5012,7 +5010,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata) } #endif - if (test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags)) + if (wdata->subreq.retry_count > 0) smb2_set_replay(server, &rqst); cifs_dbg(FYI, "async write at %llu %u bytes iter=%zx\n", @@ -5156,6 +5154,7 @@ replay_again: cifs_dbg(VFS, "Send error in write = %d\n", rc); } else { *nbytes = le32_to_cpu(rsp->DataLength); + cifs_stats_bytes_written(io_parms->tcon, *nbytes); trace_smb3_write_done(0, 0, xid, req->PersistentFileId, io_parms->tcon->tid, @@ -6204,7 +6203,7 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, req->StructureSize = cpu_to_le16(36); total_len += 12; - memcpy(req->LeaseKey, lease_key, 16); + memcpy(req->LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE); req->LeaseState = lease_state; flags |= CIFS_NO_RSP_BUF; diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index 076d9e83e1a0..3c09a58dfd07 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -79,7 +79,7 @@ struct smb2_symlink_err_rsp { struct smb2_error_context_rsp { __le32 ErrorDataLength; __le32 ErrorId; - __u8 ErrorContextData; /* ErrorDataLength long array */ + __u8 ErrorContextData[] __counted_by_le(ErrorDataLength); } __packed; /* ErrorId values */ diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 09349fa8da03..2336dfb23f36 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -111,8 +111,9 @@ extern int smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const unsigned char *path, char *pbuf, unsigned int *pbytes_read); +int smb2_fix_symlink_target_type(char **target, bool directory, struct cifs_sb_info *cifs_sb); int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len, - bool unicode, bool relative, + bool relative, const char *full_path, struct cifs_sb_info *cifs_sb); int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 12cbd3428a6d..52bcb55d9952 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -674,6 +674,7 @@ DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_eof_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_reparse_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(get_reparse_compound_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_wsl_ea_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(tdis_enter); diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 3c7c706c797d..3336df2ea5d4 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1550,7 +1550,19 @@ struct reparse_symlink_data_buffer { __u8 PathBuffer[]; /* Variable Length */ } __packed; -/* See MS-FSCC 2.1.2.6 and cifspdu.h for struct reparse_posix_data */ +/* For IO_REPARSE_TAG_NFS - see MS-FSCC 2.1.2.6 */ +#define NFS_SPECFILE_LNK 0x00000000014B4E4C +#define NFS_SPECFILE_CHR 0x0000000000524843 +#define NFS_SPECFILE_BLK 0x00000000004B4C42 +#define NFS_SPECFILE_FIFO 0x000000004F464946 +#define NFS_SPECFILE_SOCK 0x000000004B434F53 +struct reparse_nfs_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __le64 InodeType; /* NFS_SPECFILE_* */ + __u8 DataBuffer[]; +} __packed; /* For IO_REPARSE_TAG_LX_SYMLINK */ struct reparse_wsl_symlink_data_buffer { diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index c14dd72e1b30..f8a40f65db6a 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -70,7 +70,6 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); atomic_set(&conn->refcnt, 1); - atomic_set(&conn->mux_smb_requests, 0); conn->total_credits = 1; conn->outstanding_credits = 0; @@ -120,8 +119,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; + atomic_inc(&conn->req_running); if (requests_queue) { - atomic_inc(&conn->req_running); spin_lock(&conn->request_lock); list_add_tail(&work->request_entry, requests_queue); spin_unlock(&conn->request_lock); @@ -132,11 +131,14 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + atomic_dec(&conn->req_running); + if (waitqueue_active(&conn->req_running_q)) + wake_up(&conn->req_running_q); + if (list_empty(&work->request_entry) && list_empty(&work->async_request_entry)) return; - atomic_dec(&conn->req_running); spin_lock(&conn->request_lock); list_del_init(&work->request_entry); spin_unlock(&conn->request_lock); @@ -308,7 +310,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size, max_allowed_pdu_size; + unsigned int pdu_size, max_allowed_pdu_size, max_req; char hdr_buf[4] = {0,}; int size; @@ -318,6 +320,7 @@ int ksmbd_conn_handler_loop(void *p) if (t->ops->prepare && t->ops->prepare(t)) goto out; + max_req = server_conf.max_inflight_req; conn->last_active = jiffies; set_freezable(); while (ksmbd_conn_alive(conn)) { @@ -327,6 +330,13 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL; +recheck: + if (atomic_read(&conn->req_running) + 1 > max_req) { + wait_event_interruptible(conn->req_running_q, + atomic_read(&conn->req_running) < max_req); + goto recheck; + } + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 8ddd5a3c7baf..b379ae4fdcdf 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -107,7 +107,6 @@ struct ksmbd_conn { __le16 signing_algorithm; bool binding; atomic_t refcnt; - atomic_t mux_smb_requests; }; struct ksmbd_conn_ops { diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index 3d01d9d15293..3f07a612c05b 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -111,7 +111,8 @@ struct ksmbd_startup_request { __u32 smb2_max_credits; /* MAX credits */ __u32 smbd_max_io_size; /* smbd read write size */ __u32 max_connections; /* Number of maximum simultaneous connections */ - __u32 reserved[126]; /* Reserved room */ + __s8 bind_interfaces_only; + __s8 reserved[503]; /* Reserved room */ __u32 ifc_list_sz; /* interfaces list size */ __s8 ____payload[]; }; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 3ba95bd8edeb..601e7fcbcf1e 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -270,7 +270,6 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - atomic_dec(&conn->mux_smb_requests); /* * Checking waitqueue to dropping pending requests on * disconnection. waitqueue_active is safe because it @@ -300,11 +299,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) if (err) return 0; - if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) { - atomic_dec_return(&conn->mux_smb_requests); - return -ENOSPC; - } - work = ksmbd_alloc_work_struct(); if (!work) { pr_err("allocation for work failed\n"); @@ -367,6 +361,7 @@ static int server_conf_init(void) server_conf.auth_mechs |= KSMBD_AUTH_KRB5 | KSMBD_AUTH_MSKRB5; #endif + server_conf.max_inflight_req = SMB2_MAX_CREDITS; return 0; } diff --git a/fs/smb/server/server.h b/fs/smb/server/server.h index 4fc529335271..995555febe7d 100644 --- a/fs/smb/server/server.h +++ b/fs/smb/server/server.h @@ -42,9 +42,11 @@ struct ksmbd_server_config { struct smb_sid domain_sid; unsigned int auth_mechs; unsigned int max_connections; + unsigned int max_inflight_req; char *conf[SERVER_CONF_WORK_GROUP + 1]; struct task_struct *dh_task; + bool bind_interfaces_only; }; extern struct ksmbd_server_config server_conf; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 803b35b89513..f1efcd027475 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -38,6 +38,7 @@ #include "mgmt/user_session.h" #include "mgmt/ksmbd_ida.h" #include "ndr.h" +#include "transport_tcp.h" static void __wbuf(struct ksmbd_work *work, void **req, void **rsp) { @@ -695,6 +696,9 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) struct smb2_hdr *rsp_hdr; struct ksmbd_work *in_work = ksmbd_alloc_work_struct(); + if (!in_work) + return; + if (allocate_interim_rsp_buf(in_work)) { pr_err("smb_allocate_rsp_buf failed!\n"); ksmbd_free_work_struct(in_work); @@ -1097,6 +1101,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } + ksmbd_conn_lock(conn); smb2_buf_len = get_rfc1002_len(work->request_buf); smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { @@ -1247,6 +1252,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_conn_set_need_negotiate(conn); err_out: + ksmbd_conn_unlock(conn); if (rc) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; @@ -3989,6 +3995,26 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, posix_info->DeviceId = cpu_to_le32(ksmbd_kstat->kstat->rdev); posix_info->HardLinks = cpu_to_le32(ksmbd_kstat->kstat->nlink); posix_info->Mode = cpu_to_le32(ksmbd_kstat->kstat->mode & 0777); + switch (ksmbd_kstat->kstat->mode & S_IFMT) { + case S_IFDIR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + posix_info->Inode = cpu_to_le64(ksmbd_kstat->kstat->ino); posix_info->DosAttributes = S_ISDIR(ksmbd_kstat->kstat->mode) ? @@ -5179,6 +5205,26 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); file_info->HardLinks = cpu_to_le32(stat.nlink); file_info->Mode = cpu_to_le32(stat.mode & 0777); + switch (stat.mode & S_IFMT) { + case S_IFDIR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + file_info->DeviceId = cpu_to_le32(stat.rdev); /* @@ -7714,6 +7760,9 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn, if (netdev->type == ARPHRD_LOOPBACK) continue; + if (!ksmbd_find_netdev_name_iface_list(netdev->name)) + continue; + flags = dev_get_flags(netdev); if (!(flags & IFF_RUNNING)) continue; diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 649dacf7e8c4..17a0b18a8406 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -502,4 +502,14 @@ static inline void *smb2_get_msg(void *buf) return buf + 4; } +#define POSIX_TYPE_FILE 0 +#define POSIX_TYPE_DIR 1 +#define POSIX_TYPE_SYMLINK 2 +#define POSIX_TYPE_CHARDEV 3 +#define POSIX_TYPE_BLKDEV 4 +#define POSIX_TYPE_FIFO 5 +#define POSIX_TYPE_SOCKET 6 + +#define POSIX_FILETYPE_SHIFT 12 + #endif /* _SMB2PDU_H */ diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index f51cd0816b1a..425c756bcfb8 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -781,10 +781,6 @@ int __ksmbd_override_fsids(struct ksmbd_work *work, WARN_ON(work->saved_cred); work->saved_cred = override_creds(cred); - if (!work->saved_cred) { - abort_creds(cred); - return -EINVAL; - } return 0; } @@ -796,13 +792,11 @@ int ksmbd_override_fsids(struct ksmbd_work *work) void ksmbd_revert_fsids(struct ksmbd_work *work) { const struct cred *cred; - WARN_ON(!work->saved_cred); - cred = current_cred(); - revert_creds(work->saved_cred); - put_cred(cred); + cred = revert_creds(work->saved_cred); work->saved_cred = NULL; + put_cred(cred); } __le32 smb_map_generic_desired_access(__le32 daccess) diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 48cda3350e5a..0460ebea6ff0 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -319,8 +319,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) init_smb2_max_write_size(req->smb2_max_write); if (req->smb2_max_trans) init_smb2_max_trans_size(req->smb2_max_trans); - if (req->smb2_max_credits) + if (req->smb2_max_credits) { init_smb2_max_credits(req->smb2_max_credits); + server_conf.max_inflight_req = + req->smb2_max_credits; + } if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); @@ -330,6 +333,7 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) ret = ksmbd_set_netbios_name(req->netbios_name); ret |= ksmbd_set_server_string(req->server_string); ret |= ksmbd_set_work_group(req->work_group); + server_conf.bind_interfaces_only = req->bind_interfaces_only; ret |= ksmbd_tcp_set_interfaces(KSMBD_STARTUP_CONFIG_INTERFACES(req), req->ifc_list_sz); if (ret) { @@ -623,6 +627,9 @@ ksmbd_ipc_spnego_authen_request(const char *spnego_blob, int blob_len) struct ksmbd_spnego_authen_request *req; struct ksmbd_spnego_authen_response *resp; + if (blob_len > KSMBD_IPC_MAX_PAYLOAD) + return NULL; + msg = ipc_msg_alloc(sizeof(struct ksmbd_spnego_authen_request) + blob_len + 1); if (!msg) @@ -802,6 +809,9 @@ struct ksmbd_rpc_command *ksmbd_rpc_write(struct ksmbd_session *sess, int handle struct ksmbd_rpc_command *req; struct ksmbd_rpc_command *resp; + if (payload_sz > KSMBD_IPC_MAX_PAYLOAD) + return NULL; + msg = ipc_msg_alloc(sizeof(struct ksmbd_rpc_command) + payload_sz + 1); if (!msg) return NULL; @@ -850,6 +860,9 @@ struct ksmbd_rpc_command *ksmbd_rpc_ioctl(struct ksmbd_session *sess, int handle struct ksmbd_rpc_command *req; struct ksmbd_rpc_command *resp; + if (payload_sz > KSMBD_IPC_MAX_PAYLOAD) + return NULL; + msg = ipc_msg_alloc(sizeof(struct ksmbd_rpc_command) + payload_sz + 1); if (!msg) return NULL; @@ -868,31 +881,6 @@ struct ksmbd_rpc_command *ksmbd_rpc_ioctl(struct ksmbd_session *sess, int handle return resp; } -struct ksmbd_rpc_command *ksmbd_rpc_rap(struct ksmbd_session *sess, void *payload, - size_t payload_sz) -{ - struct ksmbd_ipc_msg *msg; - struct ksmbd_rpc_command *req; - struct ksmbd_rpc_command *resp; - - msg = ipc_msg_alloc(sizeof(struct ksmbd_rpc_command) + payload_sz + 1); - if (!msg) - return NULL; - - msg->type = KSMBD_EVENT_RPC_REQUEST; - req = (struct ksmbd_rpc_command *)msg->payload; - req->handle = ksmbd_acquire_id(&ipc_ida); - req->flags = rpc_context_flags(sess); - req->flags |= KSMBD_RPC_RAP_METHOD; - req->payload_sz = payload_sz; - memcpy(req->payload, payload, payload_sz); - - resp = ipc_msg_send_request(msg, req->handle); - ipc_msg_handle_free(req->handle); - ipc_msg_free(msg); - return resp; -} - static int __ipc_heartbeat(void) { unsigned long delta; diff --git a/fs/smb/server/transport_ipc.h b/fs/smb/server/transport_ipc.h index d9b6737f8cd0..e51850f1423b 100644 --- a/fs/smb/server/transport_ipc.h +++ b/fs/smb/server/transport_ipc.h @@ -41,8 +41,6 @@ struct ksmbd_rpc_command *ksmbd_rpc_write(struct ksmbd_session *sess, int handle struct ksmbd_rpc_command *ksmbd_rpc_read(struct ksmbd_session *sess, int handle); struct ksmbd_rpc_command *ksmbd_rpc_ioctl(struct ksmbd_session *sess, int handle, void *payload, size_t payload_sz); -struct ksmbd_rpc_command *ksmbd_rpc_rap(struct ksmbd_session *sess, void *payload, - size_t payload_sz); void ksmbd_ipc_release(void); void ksmbd_ipc_soft_reset(void); int ksmbd_ipc_init(void); diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 0ef3c9f0bfeb..c3785a5434f9 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2283,8 +2283,7 @@ out: ibdev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_UNKNOWN); if (ibdev) { - if (rdma_frwr_is_supported(&ibdev->attrs)) - rdma_capable = true; + rdma_capable = rdma_frwr_is_supported(&ibdev->attrs); ib_device_put(ibdev); } } diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 0d9007285e30..7f38a3c3f5bd 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -504,32 +504,37 @@ out_clear: return ret; } +struct interface *ksmbd_find_netdev_name_iface_list(char *netdev_name) +{ + struct interface *iface; + + list_for_each_entry(iface, &iface_list, entry) + if (!strcmp(iface->name, netdev_name)) + return iface; + return NULL; +} + static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct interface *iface; - int ret, found = 0; + int ret; switch (event) { case NETDEV_UP: if (netif_is_bridge_port(netdev)) return NOTIFY_OK; - list_for_each_entry(iface, &iface_list, entry) { - if (!strcmp(iface->name, netdev->name)) { - found = 1; - if (iface->state != IFACE_STATE_DOWN) - break; - ksmbd_debug(CONN, "netdev-up event: netdev(%s) is going up\n", - iface->name); - ret = create_socket(iface); - if (ret) - return NOTIFY_OK; - break; - } + iface = ksmbd_find_netdev_name_iface_list(netdev->name); + if (iface && iface->state == IFACE_STATE_DOWN) { + ksmbd_debug(CONN, "netdev-up event: netdev(%s) is going up\n", + iface->name); + ret = create_socket(iface); + if (ret) + return NOTIFY_OK; } - if (!found && bind_additional_ifaces) { + if (!iface && bind_additional_ifaces) { iface = alloc_iface(kstrdup(netdev->name, KSMBD_DEFAULT_GFP)); if (!iface) return NOTIFY_OK; @@ -541,21 +546,19 @@ static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, } break; case NETDEV_DOWN: - list_for_each_entry(iface, &iface_list, entry) { - if (!strcmp(iface->name, netdev->name) && - iface->state == IFACE_STATE_CONFIGURED) { - ksmbd_debug(CONN, "netdev-down event: netdev(%s) is going down\n", - iface->name); - tcp_stop_kthread(iface->ksmbd_kthread); - iface->ksmbd_kthread = NULL; - mutex_lock(&iface->sock_release_lock); - tcp_destroy_socket(iface->ksmbd_socket); - iface->ksmbd_socket = NULL; - mutex_unlock(&iface->sock_release_lock); + iface = ksmbd_find_netdev_name_iface_list(netdev->name); + if (iface && iface->state == IFACE_STATE_CONFIGURED) { + ksmbd_debug(CONN, "netdev-down event: netdev(%s) is going down\n", + iface->name); + tcp_stop_kthread(iface->ksmbd_kthread); + iface->ksmbd_kthread = NULL; + mutex_lock(&iface->sock_release_lock); + tcp_destroy_socket(iface->ksmbd_socket); + iface->ksmbd_socket = NULL; + mutex_unlock(&iface->sock_release_lock); - iface->state = IFACE_STATE_DOWN; - break; - } + iface->state = IFACE_STATE_DOWN; + break; } break; } @@ -624,18 +627,6 @@ int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz) int sz = 0; if (!ifc_list_sz) { - struct net_device *netdev; - - rtnl_lock(); - for_each_netdev(&init_net, netdev) { - if (netif_is_bridge_port(netdev)) - continue; - if (!alloc_iface(kstrdup(netdev->name, KSMBD_DEFAULT_GFP))) { - rtnl_unlock(); - return -ENOMEM; - } - } - rtnl_unlock(); bind_additional_ifaces = 1; return 0; } diff --git a/fs/smb/server/transport_tcp.h b/fs/smb/server/transport_tcp.h index e338bebe322f..8c9aa624cfe3 100644 --- a/fs/smb/server/transport_tcp.h +++ b/fs/smb/server/transport_tcp.h @@ -7,6 +7,7 @@ #define __KSMBD_TRANSPORT_TCP_H__ int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz); +struct interface *ksmbd_find_netdev_name_iface_list(char *netdev_name); int ksmbd_tcp_init(void); void ksmbd_tcp_destroy(void); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 88d167a5f8b7..6890016e1923 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1264,6 +1264,8 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, filepath, flags, path); + if (!is_last) + next[0] = '/'; if (err) goto out2; else if (is_last) @@ -1271,7 +1273,6 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, path_put(parent_path); *parent_path = *path; - next[0] = '/'; remain_len -= filename_len + 1; } @@ -1855,13 +1856,6 @@ void ksmbd_vfs_posix_lock_wait(struct file_lock *flock) wait_event(flock->c.flc_wait, !flock->c.flc_blocker); } -int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout) -{ - return wait_event_interruptible_timeout(flock->c.flc_wait, - !flock->c.flc_blocker, - timeout); -} - void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock) { locks_delete_block(flock); diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index 06903024a2d8..2893f59803a6 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -140,7 +140,6 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, struct dentry *dentry, struct ksmbd_kstat *ksmbd_kstat); void ksmbd_vfs_posix_lock_wait(struct file_lock *flock); -int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout); void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock); int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, const struct path *path); diff --git a/fs/splice.c b/fs/splice.c index 2898fa1e9e63..28cfa63aa236 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -342,7 +342,7 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos, return -ENOMEM; pages = (struct page **)(bv + npages); - npages = alloc_pages_bulk_array(GFP_USER, npages, pages); + npages = alloc_pages_bulk(GFP_USER, npages, pages); if (!npages) { kfree(bv); return -ENOMEM; diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig index 60fc98bdf421..b1091e70434a 100644 --- a/fs/squashfs/Kconfig +++ b/fs/squashfs/Kconfig @@ -5,8 +5,8 @@ config SQUASHFS help Saying Y here includes support for SquashFS 4.0 (a Compressed Read-Only File System). Squashfs is a highly compressed read-only - filesystem for Linux. It uses zlib, lzo or xz compression to - compress both files, inodes and directories. Inodes in the system + filesystem for Linux. It uses zlib, lz4, lzo, xz or zstd compression + to compress both files, inodes and directories. Inodes in the system are very small and all blocks are packed to minimise data overhead. Block sizes greater than 4K are supported up to a maximum of 1 Mbytes (default block size 128K). SquashFS 4.0 supports 64 bit filesystems @@ -16,7 +16,7 @@ config SQUASHFS Squashfs is intended for general read-only filesystem use, for archival use (i.e. in cases where a .tar.gz file may be used), and in embedded systems where low overhead is needed. Further information - and tools are available from http://squashfs.sourceforge.net. + and tools are available from github.com/plougher/squashfs-tools. If you want to compile this as a module ( = code which can be inserted in and removed from the running kernel whenever you want), diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index 5062326d0efb..4db0d2b0aab8 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -224,11 +224,15 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries, int block_size) { int i, j; - struct squashfs_cache *cache = kzalloc(sizeof(*cache), GFP_KERNEL); + struct squashfs_cache *cache; + if (entries == 0) + return NULL; + + cache = kzalloc(sizeof(*cache), GFP_KERNEL); if (cache == NULL) { ERROR("Failed to allocate %s cache\n", name); - return NULL; + return ERR_PTR(-ENOMEM); } cache->entry = kcalloc(entries, sizeof(*(cache->entry)), GFP_KERNEL); @@ -281,7 +285,7 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries, cleanup: squashfs_cache_delete(cache); - return NULL; + return ERR_PTR(-ENOMEM); } diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 21aaa96856c1..5ca2baa16dc2 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -362,29 +362,33 @@ static int read_blocklist(struct inode *inode, int index, u64 *block) return squashfs_block_size(size); } -void squashfs_fill_page(struct page *page, struct squashfs_cache_entry *buffer, int offset, int avail) +static bool squashfs_fill_page(struct folio *folio, + struct squashfs_cache_entry *buffer, size_t offset, + size_t avail) { - int copied; + size_t copied; void *pageaddr; - pageaddr = kmap_atomic(page); + pageaddr = kmap_local_folio(folio, 0); copied = squashfs_copy_data(pageaddr, buffer, offset, avail); memset(pageaddr + copied, 0, PAGE_SIZE - copied); - kunmap_atomic(pageaddr); + kunmap_local(pageaddr); - flush_dcache_page(page); - if (copied == avail) - SetPageUptodate(page); + flush_dcache_folio(folio); + + return copied == avail; } /* Copy data into page cache */ -void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, - int bytes, int offset) +void squashfs_copy_cache(struct folio *folio, + struct squashfs_cache_entry *buffer, size_t bytes, + size_t offset) { - struct inode *inode = page->mapping->host; + struct address_space *mapping = folio->mapping; + struct inode *inode = mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; - int start_index = page->index & ~mask, end_index = start_index | mask; + int start_index = folio->index & ~mask, end_index = start_index | mask; /* * Loop copying datablock into pages. As the datablock likely covers @@ -394,32 +398,35 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, */ for (i = start_index; i <= end_index && bytes > 0; i++, bytes -= PAGE_SIZE, offset += PAGE_SIZE) { - struct page *push_page; - int avail = buffer ? min_t(int, bytes, PAGE_SIZE) : 0; + struct folio *push_folio; + size_t avail = buffer ? min(bytes, PAGE_SIZE) : 0; + bool updated = false; - TRACE("bytes %d, i %d, available_bytes %d\n", bytes, i, avail); + TRACE("bytes %zu, i %d, available_bytes %zu\n", bytes, i, avail); - push_page = (i == page->index) ? page : - grab_cache_page_nowait(page->mapping, i); + push_folio = (i == folio->index) ? folio : + __filemap_get_folio(mapping, i, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + mapping_gfp_mask(mapping)); - if (!push_page) + if (IS_ERR(push_folio)) continue; - if (PageUptodate(push_page)) - goto skip_page; + if (folio_test_uptodate(push_folio)) + goto skip_folio; - squashfs_fill_page(push_page, buffer, offset, avail); -skip_page: - unlock_page(push_page); - if (i != page->index) - put_page(push_page); + updated = squashfs_fill_page(push_folio, buffer, offset, avail); +skip_folio: + folio_end_read(push_folio, updated); + if (i != folio->index) + folio_put(push_folio); } } /* Read datablock stored packed inside a fragment (tail-end packed block) */ -static int squashfs_readpage_fragment(struct page *page, int expected) +static int squashfs_readpage_fragment(struct folio *folio, int expected) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, squashfs_i(inode)->fragment_block, squashfs_i(inode)->fragment_size); @@ -430,36 +437,34 @@ static int squashfs_readpage_fragment(struct page *page, int expected) squashfs_i(inode)->fragment_block, squashfs_i(inode)->fragment_size); else - squashfs_copy_cache(page, buffer, expected, + squashfs_copy_cache(folio, buffer, expected, squashfs_i(inode)->fragment_offset); squashfs_cache_put(buffer); return res; } -static int squashfs_readpage_sparse(struct page *page, int expected) +static int squashfs_readpage_sparse(struct folio *folio, int expected) { - squashfs_copy_cache(page, NULL, expected, 0); + squashfs_copy_cache(folio, NULL, expected, 0); return 0; } static int squashfs_read_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - int index = page->index >> (msblk->block_log - PAGE_SHIFT); + int index = folio->index >> (msblk->block_log - PAGE_SHIFT); int file_end = i_size_read(inode) >> msblk->block_log; int expected = index == file_end ? (i_size_read(inode) & (msblk->block_size - 1)) : msblk->block_size; int res = 0; - void *pageaddr; TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n", - page->index, squashfs_i(inode)->start); + folio->index, squashfs_i(inode)->start); - if (page->index >= ((i_size_read(inode) + PAGE_SIZE - 1) >> + if (folio->index >= ((i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT)) goto out; @@ -472,23 +477,18 @@ static int squashfs_read_folio(struct file *file, struct folio *folio) goto out; if (res == 0) - res = squashfs_readpage_sparse(page, expected); + res = squashfs_readpage_sparse(folio, expected); else - res = squashfs_readpage_block(page, block, res, expected); + res = squashfs_readpage_block(folio, block, res, expected); } else - res = squashfs_readpage_fragment(page, expected); + res = squashfs_readpage_fragment(folio, expected); if (!res) return 0; out: - pageaddr = kmap_atomic(page); - memset(pageaddr, 0, PAGE_SIZE); - kunmap_atomic(pageaddr); - flush_dcache_page(page); - if (res == 0) - SetPageUptodate(page); - unlock_page(page); + folio_zero_segment(folio, 0, folio_size(folio)); + folio_end_read(folio, res == 0); return res; } diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c index 54c17b7c85fd..40e59a43d098 100644 --- a/fs/squashfs/file_cache.c +++ b/fs/squashfs/file_cache.c @@ -18,9 +18,9 @@ #include "squashfs.h" /* Read separately compressed datablock and memcopy into page cache */ -int squashfs_readpage_block(struct page *page, u64 block, int bsize, int expected) +int squashfs_readpage_block(struct folio *folio, u64 block, int bsize, int expected) { - struct inode *i = page->mapping->host; + struct inode *i = folio->mapping->host; struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, block, bsize); int res = buffer->error; @@ -29,7 +29,7 @@ int squashfs_readpage_block(struct page *page, u64 block, int bsize, int expecte ERROR("Unable to read page, block %llx, size %x\n", block, bsize); else - squashfs_copy_cache(page, buffer, expected, 0); + squashfs_copy_cache(folio, buffer, expected, 0); squashfs_cache_put(buffer); return res; diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index d19d4db74af8..2c3e809d6891 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -19,12 +19,11 @@ #include "page_actor.h" /* Read separately compressed datablock directly into page cache */ -int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, - int expected) - +int squashfs_readpage_block(struct folio *folio, u64 block, int bsize, + int expected) { - struct folio *folio = page_folio(target_page); - struct inode *inode = target_page->mapping->host; + struct page *target_page = &folio->page; + struct inode *inode = folio->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; loff_t file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT; int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; @@ -48,7 +47,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, /* Try to grab all the pages covered by the Squashfs block */ for (i = 0, index = start_index; index <= end_index; index++) { page[i] = (index == folio->index) ? target_page : - grab_cache_page_nowait(target_page->mapping, index); + grab_cache_page_nowait(folio->mapping, index); if (page[i] == NULL) continue; diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index 5a756e6790b5..218868b20f16 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -14,6 +14,12 @@ #define WARNING(s, args...) pr_warn("SQUASHFS: "s, ## args) +#ifdef CONFIG_SQUASHFS_FILE_CACHE +#define SQUASHFS_READ_PAGES msblk->max_thread_num +#else +#define SQUASHFS_READ_PAGES 0 +#endif + /* block.c */ extern int squashfs_read_data(struct super_block *, u64, int, u64 *, struct squashfs_page_actor *); @@ -67,12 +73,11 @@ extern __le64 *squashfs_read_fragment_index_table(struct super_block *, u64, u64, unsigned int); /* file.c */ -void squashfs_fill_page(struct page *, struct squashfs_cache_entry *, int, int); -void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int, - int); +void squashfs_copy_cache(struct folio *, struct squashfs_cache_entry *, + size_t bytes, size_t offset); /* file_xxx.c */ -extern int squashfs_readpage_block(struct page *, u64, int, int); +int squashfs_readpage_block(struct folio *, u64 block, int bsize, int expected); /* id.c */ extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *); diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 22e812808e5c..67c55fe32ce8 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -314,26 +314,29 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_flags |= SB_RDONLY; sb->s_op = &squashfs_super_ops; - err = -ENOMEM; - msblk->block_cache = squashfs_cache_init("metadata", SQUASHFS_CACHED_BLKS, SQUASHFS_METADATA_SIZE); - if (msblk->block_cache == NULL) + if (IS_ERR(msblk->block_cache)) { + err = PTR_ERR(msblk->block_cache); goto failed_mount; + } /* Allocate read_page block */ msblk->read_page = squashfs_cache_init("data", - msblk->max_thread_num, msblk->block_size); - if (msblk->read_page == NULL) { + SQUASHFS_READ_PAGES, msblk->block_size); + if (IS_ERR(msblk->read_page)) { errorf(fc, "Failed to allocate read_page block"); + err = PTR_ERR(msblk->read_page); goto failed_mount; } if (msblk->devblksize == PAGE_SIZE) { struct inode *cache = new_inode(sb); - if (cache == NULL) + if (cache == NULL) { + err = -ENOMEM; goto failed_mount; + } set_nlink(cache, 1); cache->i_size = OFFSET_MAX; @@ -405,9 +408,9 @@ handle_fragments: goto check_directory_table; msblk->fragment_cache = squashfs_cache_init("fragment", - SQUASHFS_CACHED_FRAGMENTS, msblk->block_size); - if (msblk->fragment_cache == NULL) { - err = -ENOMEM; + min(SQUASHFS_CACHED_FRAGMENTS, fragments), msblk->block_size); + if (IS_ERR(msblk->fragment_cache)) { + err = PTR_ERR(msblk->fragment_cache); goto failed_mount; } diff --git a/fs/stat.c b/fs/stat.c index 0870e969a8a0..2c0e111a098a 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -725,6 +725,7 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_mnt_id = stat->mnt_id; tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; + tmp.stx_dio_read_offset_align = stat->dio_read_offset_align; tmp.stx_subvol = stat->subvol; tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min; tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max; diff --git a/fs/super.c b/fs/super.c index c9c7223bc2a2..5a7db4a556e3 100644 --- a/fs/super.c +++ b/fs/super.c @@ -647,7 +647,7 @@ void generic_shutdown_super(struct super_block *sb) */ fscrypt_destroy_keyring(sb); - if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes), + if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes), NULL, "VFS: Busy inodes after unmount of %s (%s)", sb->s_id, sb->s_type->name)) { /* diff --git a/fs/sysctls.c b/fs/sysctls.c index 8dbde9a802fa..ad429dffeb4b 100644 --- a/fs/sysctls.c +++ b/fs/sysctls.c @@ -7,7 +7,7 @@ #include #include -static struct ctl_table fs_shared_sysctls[] = { +static const struct ctl_table fs_shared_sysctls[] = { { .procname = "overflowuid", .data = &fs_overflowuid, diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 785408861c01..6931308876c4 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -817,7 +817,7 @@ EXPORT_SYMBOL_GPL(sysfs_emit_at); * Returns number of bytes written to @buf. */ ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { memcpy(buf, attr->private + off, count); diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index cfc614c638da..53214499e384 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -457,7 +457,8 @@ static void tracefs_d_release(struct dentry *dentry) eventfs_d_release(dentry); } -static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags) +static int tracefs_d_revalidate(struct inode *inode, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct eventfs_inode *ei = dentry->d_fsdata; diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 5cc69beaa62e..b01f382ce8db 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -863,7 +863,6 @@ void ubifs_dump_leb(const struct ubifs_info *c, int lnum) out: vfree(buf); - return; } void ubifs_dump_znode(const struct ubifs_info *c, @@ -946,16 +945,20 @@ void ubifs_dump_tnc(struct ubifs_info *c) pr_err("\n"); pr_err("(pid %d) start dumping TNC tree\n", current->pid); - znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, NULL); - level = znode->level; - pr_err("== Level %d ==\n", level); - while (znode) { - if (level != znode->level) { - level = znode->level; - pr_err("== Level %d ==\n", level); + if (c->zroot.znode) { + znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, NULL); + level = znode->level; + pr_err("== Level %d ==\n", level); + while (znode) { + if (level != znode->level) { + level = znode->level; + pr_err("== Level %d ==\n", level); + } + ubifs_dump_znode(c, znode); + znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, znode); } - ubifs_dump_znode(c, znode); - znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, znode); + } else { + pr_err("empty TNC tree in memory\n"); } pr_err("(pid %d) finish dumping TNC tree\n", current->pid); } diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index aa8837e6247c..f2cb214581fd 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -1932,7 +1932,6 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum) pr_err("(pid %d) finish dumping LEB %d\n", current->pid, lnum); out: vfree(buf); - return; } /** diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 7c0bd0b55f88..97c4d71115d8 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -36,7 +36,7 @@ static int sysctl_unprivileged_userfaultfd __read_mostly; #ifdef CONFIG_SYSCTL -static struct ctl_table vm_userfaultfd_table[] = { +static const struct ctl_table vm_userfaultfd_table[] = { { .procname = "unprivileged_userfaultfd", .data = &sysctl_unprivileged_userfaultfd, diff --git a/fs/vboxsf/Kconfig b/fs/vboxsf/Kconfig index b84586ae08b3..d4694026db8b 100644 --- a/fs/vboxsf/Kconfig +++ b/fs/vboxsf/Kconfig @@ -1,6 +1,6 @@ config VBOXSF_FS tristate "VirtualBox guest shared folder (vboxsf) support" - depends on X86 && VBOXGUEST + depends on (ARM64 || X86) && VBOXGUEST select NLS help VirtualBox hosts can share folders with guests, this driver diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 5f1a14d5b927..a859ac9b74ba 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -192,7 +192,8 @@ const struct file_operations vboxsf_dir_fops = { * This is called during name resolution/lookup to check if the @dentry in * the cache is still valid. the job is handled by vboxsf_inode_revalidate. */ -static int vboxsf_dentry_revalidate(struct dentry *dentry, unsigned int flags) +static int vboxsf_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; diff --git a/fs/verity/init.c b/fs/verity/init.c index f440f0e61e3e..6e8d33b50240 100644 --- a/fs/verity/init.c +++ b/fs/verity/init.c @@ -10,7 +10,7 @@ #include #ifdef CONFIG_SYSCTL -static struct ctl_table fsverity_sysctl_table[] = { +static const struct ctl_table fsverity_sysctl_table[] = { #ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES { .procname = "require_signatures", diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index ed9b0dabc1f1..7afa51e41427 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -51,6 +51,8 @@ xfs-y += $(addprefix libxfs/, \ xfs_rmap_btree.o \ xfs_refcount.o \ xfs_refcount_btree.o \ + xfs_rtrefcount_btree.o \ + xfs_rtrmap_btree.o \ xfs_sb.o \ xfs_symlink_remote.o \ xfs_trans_inode.o \ @@ -193,6 +195,8 @@ xfs-$(CONFIG_XFS_ONLINE_SCRUB_STATS) += scrub/stats.o xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \ rgsuper.o \ rtbitmap.o \ + rtrefcount.o \ + rtrmap.o \ rtsummary.o \ ) @@ -232,6 +236,8 @@ xfs-y += $(addprefix scrub/, \ xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \ rtbitmap_repair.o \ + rtrefcount_repair.o \ + rtrmap_repair.o \ rtsummary_repair.o \ ) diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index f5d853089019..fb79215a509d 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -114,6 +114,7 @@ xfs_ag_resv_needed( case XFS_AG_RESV_RMAPBT: len -= xfs_perag_resv(pag, type)->ar_reserved; break; + case XFS_AG_RESV_METAFILE: case XFS_AG_RESV_NONE: /* empty */ break; @@ -347,6 +348,7 @@ xfs_ag_resv_alloc_extent( switch (type) { case XFS_AG_RESV_AGFL: + case XFS_AG_RESV_METAFILE: return; case XFS_AG_RESV_METADATA: case XFS_AG_RESV_RMAPBT: @@ -389,6 +391,7 @@ xfs_ag_resv_free_extent( switch (type) { case XFS_AG_RESV_AGFL: + case XFS_AG_RESV_METAFILE: return; case XFS_AG_RESV_METADATA: case XFS_AG_RESV_RMAPBT: diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 17875ad865f5..8c04acd30d48 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -1004,9 +1004,7 @@ xfs_attr_add_fork( unsigned int blks; /* space reservation */ int error; /* error return value */ - if (xfs_is_metadir_inode(ip)) - ASSERT(XFS_IS_DQDETACHED(ip)); - else + if (!xfs_is_metadir_inode(ip)) ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); blks = XFS_ADDAFORK_SPACE_RES(mp); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 5255f93bae31..40ad22fb808b 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -615,7 +615,7 @@ xfs_bmap_btree_to_extents( xfs_trans_binval(tp, cbp); if (cur->bc_levels[0].bp == cbp) cur->bc_levels[0].bp = NULL; - xfs_iroot_realloc(ip, -1, whichfork); + xfs_bmap_broot_realloc(ip, whichfork, 0); ASSERT(ifp->if_broot == NULL); ifp->if_format = XFS_DINODE_FMT_EXTENTS; *logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork); @@ -659,12 +659,11 @@ xfs_bmap_extents_to_btree( * Make space in the inode incore. This needs to be undone if we fail * to expand the root. */ - xfs_iroot_realloc(ip, 1, whichfork); + block = xfs_bmap_broot_realloc(ip, whichfork, 1); /* * Fill in the root. */ - block = ifp->if_broot; xfs_bmbt_init_block(ip, block, NULL, 1, 1); /* * Need a cursor. Can't allocate until bb_level is filled in. @@ -746,7 +745,7 @@ xfs_bmap_extents_to_btree( out_unreserve_dquot: xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); out_root_realloc: - xfs_iroot_realloc(ip, -1, whichfork); + xfs_bmap_broot_realloc(ip, whichfork, 0); ifp->if_format = XFS_DINODE_FMT_EXTENTS; ASSERT(ifp->if_broot == NULL); xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); @@ -1043,9 +1042,7 @@ xfs_bmap_add_attrfork( int error; /* error return value */ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); - if (xfs_is_metadir_inode(ip)) - ASSERT(XFS_IS_DQDETACHED(ip)); - else + if (!xfs_is_metadir_inode(ip)) ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); ASSERT(!xfs_inode_has_attr_fork(ip)); @@ -4567,8 +4564,9 @@ xfs_bmapi_write( * the refcount btree for orphan recovery. */ if (whichfork == XFS_COW_FORK) - xfs_refcount_alloc_cow_extent(tp, bma.blkno, - bma.length); + xfs_refcount_alloc_cow_extent(tp, + XFS_IS_REALTIME_INODE(ip), + bma.blkno, bma.length); } /* Deal with the allocated space we found. */ @@ -4743,7 +4741,8 @@ xfs_bmapi_convert_one_delalloc( *seq = READ_ONCE(ifp->if_seq); if (whichfork == XFS_COW_FORK) - xfs_refcount_alloc_cow_extent(tp, bma.blkno, bma.length); + xfs_refcount_alloc_cow_extent(tp, XFS_IS_REALTIME_INODE(ip), + bma.blkno, bma.length); error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, &bma.logflags, whichfork); @@ -5391,7 +5390,7 @@ xfs_bmap_del_extent_real( bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) { - xfs_refcount_decrease_extent(tp, del); + xfs_refcount_decrease_extent(tp, isrt, del); } else if (isrt && !xfs_has_rtgroups(mp)) { error = xfs_bmap_free_rtblocks(tp, del); } else { @@ -6501,9 +6500,8 @@ xfs_get_extsz_hint( * No point in aligning allocations if we need to COW to actually * write to them. */ - if (xfs_is_always_cow_inode(ip)) - return 0; - if ((ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize) + if (!xfs_is_always_cow_inode(ip) && + (ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize) return ip->i_extsize; if (XFS_IS_REALTIME_INODE(ip) && ip->i_mount->m_sb.sb_rextsize > 1) @@ -6526,7 +6524,13 @@ xfs_get_cowextsz_hint( a = 0; if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) a = ip->i_cowextsize; - b = xfs_get_extsz_hint(ip); + if (XFS_IS_REALTIME_INODE(ip)) { + b = 0; + if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) + b = ip->i_extsize; + } else { + b = xfs_get_extsz_hint(ip); + } a = max(a, b); if (a == 0) diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 3464be771f95..908d7b050e9c 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -516,6 +516,116 @@ xfs_bmbt_keys_contiguous( be64_to_cpu(key2->bmbt.br_startoff)); } +static inline void +xfs_bmbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_bmbt_ptr_t)); +} + +/* + * Reallocate the space for if_broot based on the number of records. Move the + * records and pointers in if_broot to fit the new size. When shrinking this + * will eliminate holes between the records and pointers created by the caller. + * When growing this will create holes to be filled in by the caller. + * + * The caller must not request to add more records than would fit in the + * on-disk inode root. If the if_broot is currently NULL, then if we are + * adding records, one will be allocated. The caller must also not request + * that the number of records go below zero, although it can go to zero. + * + * ip -- the inode whose if_broot area is changing + * whichfork -- which inode fork to change + * new_numrecs -- the new number of records requested for the if_broot array + * + * Returns the incore btree root block. + */ +struct xfs_btree_block * +xfs_bmap_broot_realloc( + struct xfs_inode *ip, + int whichfork, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + + /* + * Block mapping btrees do not support storing zero records; if this + * happens, the fork is being changed to FMT_EXTENTS. Free the broot + * and get out. + */ + if (new_numrecs == 0) + return xfs_broot_realloc(ifp, 0); + + new_size = xfs_bmap_broot_space_calc(mp, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just + * allocate it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need + * to realloc() it and shift the pointers to their new + * location. The records don't change location because + * they are kept butted up against the btree block header. + */ + old_numrecs = xfs_bmbt_maxrecs(mp, old_size, false); + broot = xfs_broot_realloc(ifp, new_size); + ASSERT(xfs_bmap_bmdr_space(broot) <= + xfs_inode_fork_size(ip, whichfork)); + xfs_bmbt_move_ptrs(mp, broot, old_size, new_size, old_numrecs); + return broot; + } + + /* + * We're reducing, but not totally eliminating, numrecs. In this case, + * we are shrinking the if_broot buffer, so it must already exist. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0 && new_size > 0); + + /* + * Shrink the btree root by moving the bmbt pointers, since they are + * not butted up against the btree block header, then reallocating + * broot. + */ + xfs_bmbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + ASSERT(xfs_bmap_bmdr_space(broot) <= + xfs_inode_fork_size(ip, whichfork)); + return broot; +} + +static struct xfs_btree_block * +xfs_bmbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + return xfs_bmap_broot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, + new_numrecs); +} + const struct xfs_btree_ops xfs_bmbt_ops = { .name = "bmap", .type = XFS_BTREE_TYPE_INODE, @@ -543,6 +653,7 @@ const struct xfs_btree_ops xfs_bmbt_ops = { .keys_inorder = xfs_bmbt_keys_inorder, .recs_inorder = xfs_bmbt_recs_inorder, .keys_contiguous = xfs_bmbt_keys_contiguous, + .broot_realloc = xfs_bmbt_broot_realloc, }; /* diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h index 49a3bae3f6ec..b238d559ab03 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.h +++ b/fs/xfs/libxfs/xfs_bmap_btree.h @@ -198,4 +198,7 @@ xfs_bmap_bmdr_space(struct xfs_btree_block *bb) return xfs_bmdr_space_calc(be16_to_cpu(bb->bb_numrecs)); } +struct xfs_btree_block *xfs_bmap_broot_realloc(struct xfs_inode *ip, + int whichfork, unsigned int new_numrecs); + #endif /* __XFS_BMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 68ee1c299c25..299ce7fd11b0 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -30,6 +30,12 @@ #include "xfs_health.h" #include "xfs_buf_mem.h" #include "xfs_btree_mem.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_bmap.h" +#include "xfs_rmap.h" +#include "xfs_quota.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" /* * Btree magic numbers. @@ -1537,12 +1543,16 @@ xfs_btree_log_recs( int first, int last) { + if (!bp) { + xfs_trans_log_inode(cur->bc_tp, cur->bc_ino.ip, + xfs_ilog_fbroot(cur->bc_ino.whichfork)); + return; + } xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF); xfs_trans_log_buf(cur->bc_tp, bp, xfs_btree_rec_offset(cur, first), xfs_btree_rec_offset(cur, last + 1) - 1); - } /* @@ -3078,6 +3088,131 @@ xfs_btree_split( #define xfs_btree_split __xfs_btree_split #endif /* __KERNEL__ */ +/* Move the records from a root leaf block to a separate block. */ +STATIC void +xfs_btree_promote_leaf_iroot( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + struct xfs_buf *cbp, + union xfs_btree_ptr *cptr, + struct xfs_btree_block *cblock) +{ + union xfs_btree_rec *rp; + union xfs_btree_rec *crp; + union xfs_btree_key *kp; + union xfs_btree_ptr *pp; + struct xfs_btree_block *broot; + int numrecs = xfs_btree_get_numrecs(block); + + /* Copy the records from the leaf broot into the new child block. */ + rp = xfs_btree_rec_addr(cur, 1, block); + crp = xfs_btree_rec_addr(cur, 1, cblock); + xfs_btree_copy_recs(cur, crp, rp, numrecs); + + /* + * Increment the tree height. + * + * Trickery here: The amount of memory that we need per record for the + * ifork's btree root block may change when we convert the broot from a + * leaf to a node block. Free the existing leaf broot so that nobody + * thinks we need to migrate node pointers when we realloc the broot + * buffer after bumping nlevels. + */ + cur->bc_ops->broot_realloc(cur, 0); + cur->bc_nlevels++; + cur->bc_levels[1].ptr = 1; + + /* + * Allocate a new node broot and initialize it to point to the new + * child block. + */ + broot = cur->bc_ops->broot_realloc(cur, 1); + xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, + cur->bc_nlevels - 1, 1, cur->bc_ino.ip->i_ino); + + pp = xfs_btree_ptr_addr(cur, 1, broot); + kp = xfs_btree_key_addr(cur, 1, broot); + xfs_btree_copy_ptrs(cur, pp, cptr, 1); + xfs_btree_get_keys(cur, cblock, kp); + + /* Attach the new block to the cursor and log it. */ + xfs_btree_setbuf(cur, 0, cbp); + xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); + xfs_btree_log_recs(cur, cbp, 1, numrecs); +} + +/* + * Move the keys and pointers from a root block to a separate block. + * + * Since the keyptr size does not change, all we have to do is increase the + * tree height, copy the keyptrs to the new internal node (cblock), shrink + * the root, and copy the pointers there. + */ +STATIC int +xfs_btree_promote_node_iroot( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + int level, + struct xfs_buf *cbp, + union xfs_btree_ptr *cptr, + struct xfs_btree_block *cblock) +{ + union xfs_btree_key *ckp; + union xfs_btree_key *kp; + union xfs_btree_ptr *cpp; + union xfs_btree_ptr *pp; + int i; + int error; + int numrecs = xfs_btree_get_numrecs(block); + + /* + * Increase tree height, adjusting the root block level to match. + * We cannot change the root btree node size until we've copied the + * block contents to the new child block. + */ + be16_add_cpu(&block->bb_level, 1); + cur->bc_nlevels++; + cur->bc_levels[level + 1].ptr = 1; + + /* + * Adjust the root btree record count, then copy the keys from the old + * root to the new child block. + */ + xfs_btree_set_numrecs(block, 1); + kp = xfs_btree_key_addr(cur, 1, block); + ckp = xfs_btree_key_addr(cur, 1, cblock); + xfs_btree_copy_keys(cur, ckp, kp, numrecs); + + /* Check the pointers and copy them to the new child block. */ + pp = xfs_btree_ptr_addr(cur, 1, block); + cpp = xfs_btree_ptr_addr(cur, 1, cblock); + for (i = 0; i < numrecs; i++) { + error = xfs_btree_debug_check_ptr(cur, pp, i, level); + if (error) + return error; + } + xfs_btree_copy_ptrs(cur, cpp, pp, numrecs); + + /* + * Set the first keyptr to point to the new child block, then shrink + * the memory buffer for the root block. + */ + error = xfs_btree_debug_check_ptr(cur, cptr, 0, level); + if (error) + return error; + xfs_btree_copy_ptrs(cur, pp, cptr, 1); + xfs_btree_get_keys(cur, cblock, kp); + + cur->bc_ops->broot_realloc(cur, 1); + + /* Attach the new block to the cursor and log it. */ + xfs_btree_setbuf(cur, level, cbp); + xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); + xfs_btree_log_keys(cur, cbp, 1, numrecs); + xfs_btree_log_ptrs(cur, cbp, 1, numrecs); + return 0; +} + /* * Copy the old inode root contents into a real block and make the * broot point to it. @@ -3091,14 +3226,10 @@ xfs_btree_new_iroot( struct xfs_buf *cbp; /* buffer for cblock */ struct xfs_btree_block *block; /* btree block */ struct xfs_btree_block *cblock; /* child btree block */ - union xfs_btree_key *ckp; /* child key pointer */ - union xfs_btree_ptr *cpp; /* child ptr pointer */ - union xfs_btree_key *kp; /* pointer to btree key */ - union xfs_btree_ptr *pp; /* pointer to block addr */ + union xfs_btree_ptr aptr; union xfs_btree_ptr nptr; /* new block addr */ int level; /* btree level */ int error; /* error return code */ - int i; /* loop counter */ XFS_BTREE_STATS_INC(cur, newroot); @@ -3107,10 +3238,15 @@ xfs_btree_new_iroot( level = cur->bc_nlevels - 1; block = xfs_btree_get_iroot(cur); - pp = xfs_btree_ptr_addr(cur, 1, block); + ASSERT(level > 0 || (cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)); + if (level > 0) + aptr = *xfs_btree_ptr_addr(cur, 1, block); + else + aptr.l = cpu_to_be64(XFS_INO_TO_FSB(cur->bc_mp, + cur->bc_ino.ip->i_ino)); /* Allocate the new block. If we can't do it, we're toast. Give up. */ - error = xfs_btree_alloc_block(cur, pp, &nptr, stat); + error = xfs_btree_alloc_block(cur, &aptr, &nptr, stat); if (error) goto error0; if (*stat == 0) @@ -3136,47 +3272,16 @@ xfs_btree_new_iroot( cblock->bb_u.s.bb_blkno = bno; } - be16_add_cpu(&block->bb_level, 1); - xfs_btree_set_numrecs(block, 1); - cur->bc_nlevels++; - ASSERT(cur->bc_nlevels <= cur->bc_maxlevels); - cur->bc_levels[level + 1].ptr = 1; - - kp = xfs_btree_key_addr(cur, 1, block); - ckp = xfs_btree_key_addr(cur, 1, cblock); - xfs_btree_copy_keys(cur, ckp, kp, xfs_btree_get_numrecs(cblock)); - - cpp = xfs_btree_ptr_addr(cur, 1, cblock); - for (i = 0; i < be16_to_cpu(cblock->bb_numrecs); i++) { - error = xfs_btree_debug_check_ptr(cur, pp, i, level); + if (level > 0) { + error = xfs_btree_promote_node_iroot(cur, block, level, cbp, + &nptr, cblock); if (error) goto error0; + } else { + xfs_btree_promote_leaf_iroot(cur, block, cbp, &nptr, cblock); } - xfs_btree_copy_ptrs(cur, cpp, pp, xfs_btree_get_numrecs(cblock)); - - error = xfs_btree_debug_check_ptr(cur, &nptr, 0, level); - if (error) - goto error0; - - xfs_btree_copy_ptrs(cur, pp, &nptr, 1); - - xfs_iroot_realloc(cur->bc_ino.ip, - 1 - xfs_btree_get_numrecs(cblock), - cur->bc_ino.whichfork); - - xfs_btree_setbuf(cur, level, cbp); - - /* - * Do all this logging at the end so that - * the root is at the right level. - */ - xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); - xfs_btree_log_keys(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs)); - xfs_btree_log_ptrs(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs)); - - *logflags |= - XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork); + *logflags |= XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork); *stat = 1; return 0; error0: @@ -3347,7 +3452,7 @@ xfs_btree_make_block_unfull( if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) { /* A root block that can be made bigger. */ - xfs_iroot_realloc(ip, 1, cur->bc_ino.whichfork); + cur->bc_ops->broot_realloc(cur, numrecs + 1); *stat = 1; } else { /* A root block that needs replacing */ @@ -3693,6 +3798,97 @@ error0: return error; } +/* Move the records from a child leaf block to the root block. */ +STATIC void +xfs_btree_demote_leaf_child( + struct xfs_btree_cur *cur, + struct xfs_btree_block *cblock, + int numrecs) +{ + union xfs_btree_rec *rp; + union xfs_btree_rec *crp; + struct xfs_btree_block *broot; + + /* + * Decrease the tree height. + * + * Trickery here: The amount of memory that we need per record for the + * ifork's btree root block may change when we convert the broot from a + * node to a leaf. Free the old node broot so that we can get a fresh + * leaf broot. + */ + cur->bc_ops->broot_realloc(cur, 0); + cur->bc_nlevels--; + + /* + * Allocate a new leaf broot and copy the records from the old child. + * Detach the old child from the cursor. + */ + broot = cur->bc_ops->broot_realloc(cur, numrecs); + xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, 0, numrecs, + cur->bc_ino.ip->i_ino); + + rp = xfs_btree_rec_addr(cur, 1, broot); + crp = xfs_btree_rec_addr(cur, 1, cblock); + xfs_btree_copy_recs(cur, rp, crp, numrecs); + + cur->bc_levels[0].bp = NULL; +} + +/* + * Move the keyptrs from a child node block to the root block. + * + * Since the keyptr size does not change, all we have to do is increase the + * tree height, copy the keyptrs to the new internal node (cblock), shrink + * the root, and copy the pointers there. + */ +STATIC int +xfs_btree_demote_node_child( + struct xfs_btree_cur *cur, + struct xfs_btree_block *cblock, + int level, + int numrecs) +{ + struct xfs_btree_block *block; + union xfs_btree_key *ckp; + union xfs_btree_key *kp; + union xfs_btree_ptr *cpp; + union xfs_btree_ptr *pp; + int i; + int error; + + /* + * Adjust the root btree node size and the record count to match the + * doomed child so that we can copy the keyptrs ahead of changing the + * tree shape. + */ + block = cur->bc_ops->broot_realloc(cur, numrecs); + + xfs_btree_set_numrecs(block, numrecs); + ASSERT(block->bb_numrecs == cblock->bb_numrecs); + + /* Copy keys from the doomed block. */ + kp = xfs_btree_key_addr(cur, 1, block); + ckp = xfs_btree_key_addr(cur, 1, cblock); + xfs_btree_copy_keys(cur, kp, ckp, numrecs); + + /* Copy pointers from the doomed block. */ + pp = xfs_btree_ptr_addr(cur, 1, block); + cpp = xfs_btree_ptr_addr(cur, 1, cblock); + for (i = 0; i < numrecs; i++) { + error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1); + if (error) + return error; + } + xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); + + /* Decrease tree height, adjusting the root block level to match. */ + cur->bc_levels[level - 1].bp = NULL; + be16_add_cpu(&block->bb_level, -1); + cur->bc_nlevels--; + return 0; +} + /* * Try to merge a non-leaf block back into the inode root. * @@ -3705,34 +3901,31 @@ STATIC int xfs_btree_kill_iroot( struct xfs_btree_cur *cur) { - int whichfork = cur->bc_ino.whichfork; struct xfs_inode *ip = cur->bc_ino.ip; - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_block *block; struct xfs_btree_block *cblock; - union xfs_btree_key *kp; - union xfs_btree_key *ckp; - union xfs_btree_ptr *pp; - union xfs_btree_ptr *cpp; struct xfs_buf *cbp; int level; - int index; int numrecs; int error; #ifdef DEBUG union xfs_btree_ptr ptr; #endif - int i; ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); - ASSERT(cur->bc_nlevels > 1); + ASSERT((cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS) || + cur->bc_nlevels > 1); /* * Don't deal with the root block needs to be a leaf case. * We're just going to turn the thing back into extents anyway. */ level = cur->bc_nlevels - 1; - if (level == 1) + if (level == 1 && !(cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)) + goto out0; + + /* If we're already a leaf, jump out. */ + if (level == 0) goto out0; /* @@ -3762,40 +3955,20 @@ xfs_btree_kill_iroot( ASSERT(xfs_btree_ptr_is_null(cur, &ptr)); #endif - index = numrecs - cur->bc_ops->get_maxrecs(cur, level); - if (index) { - xfs_iroot_realloc(cur->bc_ino.ip, index, - cur->bc_ino.whichfork); - block = ifp->if_broot; - } - - be16_add_cpu(&block->bb_numrecs, index); - ASSERT(block->bb_numrecs == cblock->bb_numrecs); - - kp = xfs_btree_key_addr(cur, 1, block); - ckp = xfs_btree_key_addr(cur, 1, cblock); - xfs_btree_copy_keys(cur, kp, ckp, numrecs); - - pp = xfs_btree_ptr_addr(cur, 1, block); - cpp = xfs_btree_ptr_addr(cur, 1, cblock); - - for (i = 0; i < numrecs; i++) { - error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1); + if (level > 1) { + error = xfs_btree_demote_node_child(cur, cblock, level, + numrecs); if (error) return error; - } - - xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); + } else + xfs_btree_demote_leaf_child(cur, cblock, numrecs); error = xfs_btree_free_block(cur, cbp); if (error) return error; - cur->bc_levels[level - 1].bp = NULL; - be16_add_cpu(&block->bb_level, -1); xfs_trans_log_inode(cur->bc_tp, ip, XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork)); - cur->bc_nlevels--; out0: return 0; } @@ -3949,10 +4122,10 @@ xfs_btree_delrec( /* * We're at the root level. First, shrink the root block in-memory. * Try to get rid of the next level down. If we can't then there's - * nothing left to do. + * nothing left to do. numrecs was decremented above. */ if (xfs_btree_at_iroot(cur, level)) { - xfs_iroot_realloc(cur->bc_ino.ip, -1, cur->bc_ino.whichfork); + cur->bc_ops->broot_realloc(cur, numrecs); error = xfs_btree_kill_iroot(cur); if (error) @@ -5358,6 +5531,12 @@ xfs_btree_init_cur_caches(void) if (error) goto err; error = xfs_refcountbt_init_cur_cache(); + if (error) + goto err; + error = xfs_rtrmapbt_init_cur_cache(); + if (error) + goto err; + error = xfs_rtrefcountbt_init_cur_cache(); if (error) goto err; @@ -5376,6 +5555,8 @@ xfs_btree_destroy_cur_caches(void) xfs_bmbt_destroy_cur_cache(); xfs_rmapbt_destroy_cur_cache(); xfs_refcountbt_destroy_cur_cache(); + xfs_rtrmapbt_destroy_cur_cache(); + xfs_rtrefcountbt_destroy_cur_cache(); } /* Move the btree cursor before the first record. */ @@ -5404,3 +5585,67 @@ xfs_btree_goto_left_edge( return 0; } + +/* Allocate a block for an inode-rooted metadata btree. */ +int +xfs_btree_alloc_metafile_block( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, + union xfs_btree_ptr *new, + int *stat) +{ + struct xfs_alloc_arg args = { + .mp = cur->bc_mp, + .tp = cur->bc_tp, + .resv = XFS_AG_RESV_METAFILE, + .minlen = 1, + .maxlen = 1, + .prod = 1, + }; + struct xfs_inode *ip = cur->bc_ino.ip; + int error; + + ASSERT(xfs_is_metadir_inode(ip)); + + xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, cur->bc_ino.whichfork); + error = xfs_alloc_vextent_start_ag(&args, + XFS_INO_TO_FSB(cur->bc_mp, ip->i_ino)); + if (error) + return error; + if (args.fsbno == NULLFSBLOCK) { + *stat = 0; + return 0; + } + ASSERT(args.len == 1); + + xfs_metafile_resv_alloc_space(ip, &args); + + new->l = cpu_to_be64(args.fsbno); + *stat = 1; + return 0; +} + +/* Free a block from an inode-rooted metadata btree. */ +int +xfs_btree_free_metafile_block( + struct xfs_btree_cur *cur, + struct xfs_buf *bp) +{ + struct xfs_owner_info oinfo; + struct xfs_mount *mp = cur->bc_mp; + struct xfs_inode *ip = cur->bc_ino.ip; + struct xfs_trans *tp = cur->bc_tp; + xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); + int error; + + ASSERT(xfs_is_metadir_inode(ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); + error = xfs_free_extent_later(tp, fsbno, 1, &oinfo, XFS_AG_RESV_METAFILE, + 0); + if (error) + return error; + + xfs_metafile_resv_free_space(ip, tp, 1); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index c5bff273cae2..355b304696e6 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -135,7 +135,7 @@ struct xfs_btree_ops { /* offset of btree stats array */ unsigned int statoff; - /* sick mask for health reporting (only for XFS_BTREE_TYPE_AG) */ + /* sick mask for health reporting (not for bmap btrees) */ unsigned int sick_mask; /* cursor operations */ @@ -213,11 +213,27 @@ struct xfs_btree_ops { const union xfs_btree_key *key1, const union xfs_btree_key *key2, const union xfs_btree_key *mask); + + /* + * Reallocate the space for if_broot to fit the number of records. + * Move the records and pointers in if_broot to fit the new size. When + * shrinking this will eliminate holes between the records and pointers + * created by the caller. When growing this will create holes to be + * filled in by the caller. + * + * The caller must not request to add more records than would fit in + * the on-disk inode root. If the if_broot is currently NULL, then if + * we are adding records, one will be allocated. The caller must also + * not request that the number of records go below zero, although it + * can go to zero. + */ + struct xfs_btree_block *(*broot_realloc)(struct xfs_btree_cur *cur, + unsigned int new_numrecs); }; /* btree geometry flags */ #define XFS_BTGEO_OVERLAPPING (1U << 0) /* overlapping intervals */ - +#define XFS_BTGEO_IROOT_RECORDS (1U << 1) /* iroot can store records */ union xfs_btree_irec { struct xfs_alloc_rec_incore a; @@ -281,7 +297,7 @@ struct xfs_btree_cur struct { unsigned int nr_ops; /* # record updates */ unsigned int shape_changes; /* # of extent splits */ - } bc_refc; /* refcountbt */ + } bc_refc; /* refcountbt/rtrefcountbt */ }; /* Must be at the end of the struct! */ @@ -687,4 +703,10 @@ xfs_btree_at_iroot( level == cur->bc_nlevels - 1; } +int xfs_btree_alloc_metafile_block(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, union xfs_btree_ptr *newp, + int *stat); +int xfs_btree_free_metafile_block(struct xfs_btree_cur *cur, + struct xfs_buf *bp); + #endif /* __XFS_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c index df3d613675a1..f2f7b4305413 100644 --- a/fs/xfs/libxfs/xfs_btree_mem.c +++ b/fs/xfs/libxfs/xfs_btree_mem.c @@ -18,6 +18,7 @@ #include "xfs_ag.h" #include "xfs_buf_item.h" #include "xfs_trace.h" +#include "xfs_rtgroup.h" /* Set the root of an in-memory btree. */ void diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c index 694929703152..5ed84f9cc877 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.c +++ b/fs/xfs/libxfs/xfs_btree_staging.c @@ -134,6 +134,7 @@ xfs_btree_stage_ifakeroot( cur->bc_ino.ifake = ifake; cur->bc_nlevels = ifake->if_levels; cur->bc_ino.forksize = ifake->if_fork_size; + cur->bc_ino.whichfork = XFS_STAGING_FORK; cur->bc_flags |= XFS_BTREE_STAGING; } @@ -573,6 +574,7 @@ xfs_btree_bload_compute_geometry( struct xfs_btree_bload *bbl, uint64_t nr_records) { + const struct xfs_btree_ops *ops = cur->bc_ops; uint64_t nr_blocks = 0; uint64_t nr_this_level; @@ -599,7 +601,7 @@ xfs_btree_bload_compute_geometry( xfs_btree_bload_level_geometry(cur, bbl, level, nr_this_level, &avg_per_block, &level_blocks, &dontcare64); - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { + if (ops->type == XFS_BTREE_TYPE_INODE) { /* * If all the items we want to store at this level * would fit in the inode root block, then we have our @@ -607,7 +609,9 @@ xfs_btree_bload_compute_geometry( * * Note that bmap btrees forbid records in the root. */ - if (level != 0 && nr_this_level <= avg_per_block) { + if ((level != 0 || + (ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)) && + nr_this_level <= avg_per_block) { nr_blocks++; break; } @@ -658,7 +662,7 @@ xfs_btree_bload_compute_geometry( return -EOVERFLOW; bbl->btree_height = cur->bc_nlevels; - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) + if (ops->type == XFS_BTREE_TYPE_INODE) bbl->nr_blocks = nr_blocks - 1; else bbl->nr_blocks = nr_blocks; diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index ec51b8465e61..9effd95ddcd4 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -68,7 +68,9 @@ struct xfs_defer_op_type { extern const struct xfs_defer_op_type xfs_bmap_update_defer_type; extern const struct xfs_defer_op_type xfs_refcount_update_defer_type; +extern const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type; extern const struct xfs_defer_op_type xfs_rmap_update_defer_type; +extern const struct xfs_defer_op_type xfs_rtrmap_update_defer_type; extern const struct xfs_defer_op_type xfs_extent_free_defer_type; extern const struct xfs_defer_op_type xfs_agfl_free_defer_type; extern const struct xfs_defer_op_type xfs_rtextent_free_defer_type; diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 202468223bf9..1775abcfa04d 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -197,7 +197,7 @@ xfs_da_unmount( /* * Return 1 if directory contains only "." and "..". */ -int +static bool xfs_dir_isempty( xfs_inode_t *dp) { @@ -205,9 +205,9 @@ xfs_dir_isempty( ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); if (dp->i_disk_size == 0) /* might happen during shutdown. */ - return 1; + return true; if (dp->i_disk_size > xfs_inode_data_fork_size(dp)) - return 0; + return false; sfp = dp->i_df.if_data; return !sfp->count; } @@ -379,12 +379,11 @@ xfs_dir_cilookup_result( !(args->op_flags & XFS_DA_OP_CILOOKUP)) return -EEXIST; - args->value = kmalloc(len, + args->value = kmemdup(name, len, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_RETRY_MAYFAIL); if (!args->value) return -ENOMEM; - memcpy(args->value, name, len); args->valuelen = len; return -EEXIST; } diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index 576068ed81fa..a6594a5a941d 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -58,7 +58,6 @@ extern void xfs_dir_startup(void); extern int xfs_da_mount(struct xfs_mount *mp); extern void xfs_da_unmount(struct xfs_mount *mp); -extern int xfs_dir_isempty(struct xfs_inode *dp); extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_inode *pdp); extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp, diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h index 7002d7676a78..a53c5d40e084 100644 --- a/fs/xfs/libxfs/xfs_errortag.h +++ b/fs/xfs/libxfs/xfs_errortag.h @@ -64,7 +64,8 @@ #define XFS_ERRTAG_WB_DELAY_MS 42 #define XFS_ERRTAG_WRITE_DELAY_MS 43 #define XFS_ERRTAG_EXCHMAPS_FINISH_ONE 44 -#define XFS_ERRTAG_MAX 45 +#define XFS_ERRTAG_METAFILE_RESV_CRITICAL 45 +#define XFS_ERRTAG_MAX 46 /* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. @@ -113,5 +114,6 @@ #define XFS_RANDOM_WB_DELAY_MS 3000 #define XFS_RANDOM_WRITE_DELAY_MS 3000 #define XFS_RANDOM_EXCHMAPS_FINISH_ONE 1 +#define XFS_RANDOM_METAFILE_RESV_CRITICAL 4 #endif /* __XFS_ERRORTAG_H_ */ diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c index 2021396651de..3f1d6a98c118 100644 --- a/fs/xfs/libxfs/xfs_exchmaps.c +++ b/fs/xfs/libxfs/xfs_exchmaps.c @@ -662,7 +662,9 @@ xfs_exchmaps_rmapbt_blocks( if (!xfs_has_rmapbt(mp)) return 0; if (XFS_IS_REALTIME_INODE(req->ip1)) - return 0; + return howmany_64(req->nr_exchanges, + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) * + XFS_RTRMAPADD_SPACE_RES(mp); return howmany_64(req->nr_exchanges, XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 4d47a3e723aa..b1007fb661ba 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -857,6 +857,8 @@ enum xfs_metafile_type { XFS_METAFILE_PRJQUOTA, /* project quota */ XFS_METAFILE_RTBITMAP, /* rt bitmap */ XFS_METAFILE_RTSUMMARY, /* rt summary */ + XFS_METAFILE_RTRMAP, /* rt rmap */ + XFS_METAFILE_RTREFCOUNT, /* rt refcount */ XFS_METAFILE_MAX } __packed; @@ -868,7 +870,9 @@ enum xfs_metafile_type { { XFS_METAFILE_GRPQUOTA, "grpquota" }, \ { XFS_METAFILE_PRJQUOTA, "prjquota" }, \ { XFS_METAFILE_RTBITMAP, "rtbitmap" }, \ - { XFS_METAFILE_RTSUMMARY, "rtsummary" } + { XFS_METAFILE_RTSUMMARY, "rtsummary" }, \ + { XFS_METAFILE_RTRMAP, "rtrmap" }, \ + { XFS_METAFILE_RTREFCOUNT, "rtrefcount" } /* * On-disk inode structure. @@ -997,7 +1001,8 @@ enum xfs_dinode_fmt { XFS_DINODE_FMT_LOCAL, /* bulk data */ XFS_DINODE_FMT_EXTENTS, /* struct xfs_bmbt_rec */ XFS_DINODE_FMT_BTREE, /* struct xfs_bmdr_block */ - XFS_DINODE_FMT_UUID /* added long ago, but never used */ + XFS_DINODE_FMT_UUID, /* added long ago, but never used */ + XFS_DINODE_FMT_META_BTREE, /* metadata btree */ }; #define XFS_INODE_FORMAT_STR \ @@ -1005,7 +1010,8 @@ enum xfs_dinode_fmt { { XFS_DINODE_FMT_LOCAL, "local" }, \ { XFS_DINODE_FMT_EXTENTS, "extent" }, \ { XFS_DINODE_FMT_BTREE, "btree" }, \ - { XFS_DINODE_FMT_UUID, "uuid" } + { XFS_DINODE_FMT_UUID, "uuid" }, \ + { XFS_DINODE_FMT_META_BTREE, "meta_btree" } /* * Max values for extnum and aextnum. @@ -1725,6 +1731,24 @@ typedef __be32 xfs_rmap_ptr_t; XFS_FIBT_BLOCK(mp) + 1 : \ XFS_IBT_BLOCK(mp) + 1) +/* + * Realtime Reverse mapping btree format definitions + * + * This is a btree for reverse mapping records for realtime volumes + */ +#define XFS_RTRMAP_CRC_MAGIC 0x4d415052 /* 'MAPR' */ + +/* + * rtrmap root header, on-disk form only. + */ +struct xfs_rtrmap_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + +/* inode-based btree pointer type */ +typedef __be64 xfs_rtrmap_ptr_t; + /* * Reference Count Btree format definitions * @@ -1768,12 +1792,29 @@ struct xfs_refcount_key { __be32 rc_startblock; /* starting block number */ }; -#define MAXREFCOUNT ((xfs_nlink_t)~0U) -#define MAXREFCEXTLEN ((xfs_extlen_t)~0U) +#define XFS_REFC_REFCOUNT_MAX ((xfs_nlink_t)~0U) +#define XFS_REFC_LEN_MAX ((xfs_extlen_t)~0U) /* btree pointer type */ typedef __be32 xfs_refcount_ptr_t; +/* + * Realtime Reference Count btree format definitions + * + * This is a btree for reference count records for realtime volumes + */ +#define XFS_RTREFC_CRC_MAGIC 0x52434e54 /* 'RCNT' */ + +/* + * rt refcount root header, on-disk form only. + */ +struct xfs_rtrefcount_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + +/* inode-rooted btree pointer type */ +typedef __be64 xfs_rtrefcount_ptr_t; /* * BMAP Btree format definitions diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 41ce4d3d650e..2c3171262b44 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -737,9 +737,11 @@ struct xfs_scrub_metadata { #define XFS_SCRUB_TYPE_DIRTREE 28 /* directory tree structure */ #define XFS_SCRUB_TYPE_METAPATH 29 /* metadata directory tree paths */ #define XFS_SCRUB_TYPE_RGSUPER 30 /* realtime superblock */ +#define XFS_SCRUB_TYPE_RTRMAPBT 31 /* rtgroup reverse mapping btree */ +#define XFS_SCRUB_TYPE_RTREFCBT 32 /* realtime reference count btree */ /* Number of scrub subcommands. */ -#define XFS_SCRUB_TYPE_NR 31 +#define XFS_SCRUB_TYPE_NR 33 /* * This special type code only applies to the vectored scrub implementation. @@ -829,9 +831,11 @@ struct xfs_scrub_vec_head { #define XFS_SCRUB_METAPATH_USRQUOTA (5) /* user quota */ #define XFS_SCRUB_METAPATH_GRPQUOTA (6) /* group quota */ #define XFS_SCRUB_METAPATH_PRJQUOTA (7) /* project quota */ +#define XFS_SCRUB_METAPATH_RTRMAPBT (8) /* realtime reverse mapping */ +#define XFS_SCRUB_METAPATH_RTREFCOUNTBT (9) /* realtime refcount */ /* Number of metapath sm_ino values */ -#define XFS_SCRUB_METAPATH_NR (8) +#define XFS_SCRUB_METAPATH_NR (10) /* * ioctl limits @@ -993,6 +997,8 @@ struct xfs_rtgroup_geometry { #define XFS_RTGROUP_GEOM_SICK_SUPER (1U << 0) /* superblock */ #define XFS_RTGROUP_GEOM_SICK_BITMAP (1U << 1) /* rtbitmap */ #define XFS_RTGROUP_GEOM_SICK_SUMMARY (1U << 2) /* rtsummary */ +#define XFS_RTGROUP_GEOM_SICK_RMAPBT (1U << 3) /* reverse mappings */ +#define XFS_RTGROUP_GEOM_SICK_REFCNTBT (1U << 4) /* reference counts */ /* * ioctl commands that are used by Linux filesystems diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h index d34986ac18c3..b31000f7190c 100644 --- a/fs/xfs/libxfs/xfs_health.h +++ b/fs/xfs/libxfs/xfs_health.h @@ -70,6 +70,8 @@ struct xfs_rtgroup; #define XFS_SICK_RG_SUPER (1 << 0) /* rt group superblock */ #define XFS_SICK_RG_BITMAP (1 << 1) /* rt group bitmap */ #define XFS_SICK_RG_SUMMARY (1 << 2) /* rt groups summary */ +#define XFS_SICK_RG_RMAPBT (1 << 3) /* reverse mappings */ +#define XFS_SICK_RG_REFCNTBT (1 << 4) /* reference counts */ /* Observable health issues for AG metadata. */ #define XFS_SICK_AG_SB (1 << 0) /* superblock */ @@ -115,7 +117,9 @@ struct xfs_rtgroup; #define XFS_SICK_RG_PRIMARY (XFS_SICK_RG_SUPER | \ XFS_SICK_RG_BITMAP | \ - XFS_SICK_RG_SUMMARY) + XFS_SICK_RG_SUMMARY | \ + XFS_SICK_RG_RMAPBT | \ + XFS_SICK_RG_REFCNTBT) #define XFS_SICK_AG_PRIMARY (XFS_SICK_AG_SB | \ XFS_SICK_AG_AGF | \ diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 424861fbf1bd..f24fa628fecf 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -441,6 +441,30 @@ xfs_dinode_verify_fork( if (di_nextents > max_extents) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp)) + return __this_address; + if (!(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA))) + return __this_address; + switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use + * the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(mp)) + return __this_address; + break; + case XFS_METAFILE_RTREFCOUNT: + /* same comment about growfs and rmap inodes applies */ + if (!xfs_has_reflink(mp)) + return __this_address; + break; + default: + return __this_address; + } + break; default: return __this_address; } @@ -460,6 +484,10 @@ xfs_dinode_verify_forkoff( if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3)) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp) || !xfs_has_parent(mp)) + return __this_address; + fallthrough; case XFS_DINODE_FMT_LOCAL: /* fall through ... */ case XFS_DINODE_FMT_EXTENTS: /* fall through ... */ case XFS_DINODE_FMT_BTREE: @@ -637,9 +665,6 @@ xfs_dinode_verify( if (mode && nextents + naextents > nblocks) return __this_address; - if (nextents + naextents == 0 && nblocks != 0) - return __this_address; - if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents) return __this_address; @@ -723,7 +748,8 @@ xfs_dinode_verify( return __this_address; /* don't let reflink and realtime mix */ - if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME)) + if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME) && + !xfs_has_rtreflink(mp)) return __this_address; /* COW extent size hint validation */ @@ -743,6 +769,12 @@ xfs_dinode_verify( return fa; } + /* metadata inodes containing btrees always have zero extent count */ + if (XFS_DFORK_FORMAT(dip, XFS_DATA_FORK) != XFS_DINODE_FMT_META_BTREE) { + if (nextents + naextents == 0 && nblocks != 0) + return __this_address; + } + return NULL; } @@ -878,11 +910,29 @@ xfs_inode_validate_cowextsize( bool rt_flag; bool hint_flag; uint32_t cowextsize_bytes; + uint32_t blocksize_bytes; rt_flag = (flags & XFS_DIFLAG_REALTIME); hint_flag = (flags2 & XFS_DIFLAG2_COWEXTSIZE); cowextsize_bytes = XFS_FSB_TO_B(mp, cowextsize); + /* + * Similar to extent size hints, a directory can be configured to + * propagate realtime status and a CoW extent size hint to newly + * created files even if there is no realtime device, and the hints on + * disk can become misaligned if the sysadmin changes the rt extent + * size while adding the realtime device. + * + * Therefore, we can only enforce the rextsize alignment check against + * regular realtime files, and rely on callers to decide when alignment + * checks are appropriate, and fix things up as needed. + */ + + if (rt_flag) + blocksize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); + else + blocksize_bytes = mp->m_sb.sb_blocksize; + if (hint_flag && !xfs_has_reflink(mp)) return __this_address; @@ -896,16 +946,13 @@ xfs_inode_validate_cowextsize( if (mode && !hint_flag && cowextsize != 0) return __this_address; - if (hint_flag && rt_flag) - return __this_address; - - if (cowextsize_bytes % mp->m_sb.sb_blocksize) + if (cowextsize_bytes % blocksize_bytes) return __this_address; if (cowextsize > XFS_MAX_BMBT_EXTLEN) return __this_address; - if (cowextsize > mp->m_sb.sb_agblocks / 2) + if (!rt_flag && cowextsize > mp->m_sb.sb_agblocks / 2) return __this_address; return NULL; diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 1158ca48626b..4f99b90add55 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -27,6 +27,8 @@ #include "xfs_errortag.h" #include "xfs_health.h" #include "xfs_symlink_remote.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_ifork_cache; @@ -178,7 +180,7 @@ xfs_iformat_btree( struct xfs_mount *mp = ip->i_mount; xfs_bmdr_block_t *dfp; struct xfs_ifork *ifp; - /* REFERENCED */ + struct xfs_btree_block *broot; int nrecs; int size; int level; @@ -211,16 +213,13 @@ xfs_iformat_btree( return -EFSCORRUPTED; } - ifp->if_broot_bytes = size; - ifp->if_broot = kmalloc(size, - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); - ASSERT(ifp->if_broot != NULL); + broot = xfs_broot_alloc(ifp, size); /* * Copy and convert from the on-disk structure * to the in-memory structure. */ xfs_bmdr_to_bmbt(ip, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork), - ifp->if_broot, size); + broot, size); ifp->if_bytes = 0; ifp->if_data = NULL; @@ -270,6 +269,16 @@ xfs_iformat_data_fork( return xfs_iformat_extents(ip, dip, XFS_DATA_FORK); case XFS_DINODE_FMT_BTREE: return xfs_iformat_btree(ip, dip, XFS_DATA_FORK); + case XFS_DINODE_FMT_META_BTREE: + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + return xfs_iformat_rtrmap(ip, dip); + case XFS_METAFILE_RTREFCOUNT: + return xfs_iformat_rtrefcount(ip, dip); + default: + break; + } + fallthrough; default: xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, sizeof(*dip), __this_address); @@ -363,134 +372,67 @@ xfs_iformat_attr_fork( } /* - * Reallocate the space for if_broot based on the number of records - * being added or deleted as indicated in rec_diff. Move the records - * and pointers in if_broot to fit the new size. When shrinking this - * will eliminate holes between the records and pointers created by - * the caller. When growing this will create holes to be filled in - * by the caller. - * - * The caller must not request to add more records than would fit in - * the on-disk inode root. If the if_broot is currently NULL, then - * if we are adding records, one will be allocated. The caller must also - * not request that the number of records go below zero, although - * it can go to zero. - * - * ip -- the inode whose if_broot area is changing - * ext_diff -- the change in the number of records, positive or negative, - * requested for the if_broot array. + * Allocate the if_broot component of an inode fork so that it is @new_size + * bytes in size, using __GFP_NOLOCKDEP like all the other code that + * initializes a broot during inode load. Returns if_broot. */ -void -xfs_iroot_realloc( - xfs_inode_t *ip, - int rec_diff, - int whichfork) +struct xfs_btree_block * +xfs_broot_alloc( + struct xfs_ifork *ifp, + size_t new_size) { - struct xfs_mount *mp = ip->i_mount; - int cur_max; - struct xfs_ifork *ifp; - struct xfs_btree_block *new_broot; - int new_max; - size_t new_size; - char *np; - char *op; + ASSERT(ifp->if_broot == NULL); - /* - * Handle the degenerate case quietly. - */ - if (rec_diff == 0) { - return; - } - - ifp = xfs_ifork_ptr(ip, whichfork); - if (rec_diff > 0) { - /* - * If there wasn't any memory allocated before, just - * allocate it now and get out. - */ - if (ifp->if_broot_bytes == 0) { - new_size = xfs_bmap_broot_space_calc(mp, rec_diff); - ifp->if_broot = kmalloc(new_size, - GFP_KERNEL | __GFP_NOFAIL); - ifp->if_broot_bytes = (int)new_size; - return; - } - - /* - * If there is already an existing if_broot, then we need - * to realloc() it and shift the pointers to their new - * location. The records don't change location because - * they are kept butted up against the btree block header. - */ - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false); - new_max = cur_max + rec_diff; - new_size = xfs_bmap_broot_space_calc(mp, new_max); - ifp->if_broot = krealloc(ifp->if_broot, new_size, - GFP_KERNEL | __GFP_NOFAIL); - op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); - np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - (int)new_size); - ifp->if_broot_bytes = (int)new_size; - ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t)); - return; - } - - /* - * rec_diff is less than 0. In this case, we are shrinking the - * if_broot buffer. It must already exist. If we go to zero - * records, just get rid of the root and clear the status bit. - */ - ASSERT((ifp->if_broot != NULL) && (ifp->if_broot_bytes > 0)); - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false); - new_max = cur_max + rec_diff; - ASSERT(new_max >= 0); - if (new_max > 0) - new_size = xfs_bmap_broot_space_calc(mp, new_max); - else - new_size = 0; - if (new_size > 0) { - new_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); - /* - * First copy over the btree block header. - */ - memcpy(new_broot, ifp->if_broot, - xfs_bmbt_block_len(ip->i_mount)); - } else { - new_broot = NULL; - } - - /* - * Only copy the keys and pointers if there are any. - */ - if (new_max > 0) { - /* - * First copy the keys. - */ - op = (char *)xfs_bmbt_key_addr(mp, ifp->if_broot, 1); - np = (char *)xfs_bmbt_key_addr(mp, new_broot, 1); - memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_key_t)); - - /* - * Then copy the pointers. - */ - op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); - np = (char *)xfs_bmap_broot_ptr_addr(mp, new_broot, 1, - (int)new_size); - memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t)); - } - kfree(ifp->if_broot); - ifp->if_broot = new_broot; - ifp->if_broot_bytes = (int)new_size; - if (ifp->if_broot) - ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - return; + ifp->if_broot = kmalloc(new_size, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; } +/* + * Reallocate the if_broot component of an inode fork so that it is @new_size + * bytes in size. Returns if_broot. + */ +struct xfs_btree_block * +xfs_broot_realloc( + struct xfs_ifork *ifp, + size_t new_size) +{ + /* No size change? No action needed. */ + if (new_size == ifp->if_broot_bytes) + return ifp->if_broot; + + /* New size is zero, free it. */ + if (new_size == 0) { + ifp->if_broot_bytes = 0; + kfree(ifp->if_broot); + ifp->if_broot = NULL; + return NULL; + } + + /* + * Shrinking the iroot means we allocate a new smaller object and copy + * it. We don't trust krealloc not to nop on realloc-down. + */ + if (ifp->if_broot_bytes > 0 && ifp->if_broot_bytes > new_size) { + struct xfs_btree_block *old_broot = ifp->if_broot; + + ifp->if_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + memcpy(ifp->if_broot, old_broot, new_size); + kfree(old_broot); + return ifp->if_broot; + } + + /* + * Growing the iroot means we can krealloc. This may get us the same + * object. + */ + ifp->if_broot = krealloc(ifp->if_broot, new_size, + GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; +} /* * This is called when the amount of space needed for if_data @@ -671,6 +613,25 @@ xfs_iflush_fork( } break; + case XFS_DINODE_FMT_META_BTREE: + ASSERT(whichfork == XFS_DATA_FORK); + + if (!(iip->ili_fields & brootflag[whichfork])) + break; + + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + xfs_iflush_rtrmap(ip, dip); + break; + case XFS_METAFILE_RTREFCOUNT: + xfs_iflush_rtrefcount(ip, dip); + break; + default: + ASSERT(0); + break; + } + break; + default: ASSERT(0); break; diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 2373d12fd474..69ed0919d60b 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -170,7 +170,11 @@ void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, void xfs_idestroy_fork(struct xfs_ifork *ifp); void * xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff, int whichfork); -void xfs_iroot_realloc(struct xfs_inode *, int, int); +struct xfs_btree_block *xfs_broot_alloc(struct xfs_ifork *ifp, + size_t new_size); +struct xfs_btree_block *xfs_broot_realloc(struct xfs_ifork *ifp, + size_t new_size); + int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, int); diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 15dec19b6c32..a472ac2e45d0 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -250,6 +250,10 @@ typedef struct xfs_trans_header { #define XFS_LI_XMD 0x1249 /* mapping exchange done */ #define XFS_LI_EFI_RT 0x124a /* realtime extent free intent */ #define XFS_LI_EFD_RT 0x124b /* realtime extent free done */ +#define XFS_LI_RUI_RT 0x124c /* realtime rmap update intent */ +#define XFS_LI_RUD_RT 0x124d /* realtime rmap update done */ +#define XFS_LI_CUI_RT 0x124e /* realtime refcount update intent */ +#define XFS_LI_CUD_RT 0x124f /* realtime refcount update done */ #define XFS_LI_TYPE_DESC \ { XFS_LI_EFI, "XFS_LI_EFI" }, \ @@ -271,7 +275,11 @@ typedef struct xfs_trans_header { { XFS_LI_XMI, "XFS_LI_XMI" }, \ { XFS_LI_XMD, "XFS_LI_XMD" }, \ { XFS_LI_EFI_RT, "XFS_LI_EFI_RT" }, \ - { XFS_LI_EFD_RT, "XFS_LI_EFD_RT" } + { XFS_LI_EFD_RT, "XFS_LI_EFD_RT" }, \ + { XFS_LI_RUI_RT, "XFS_LI_RUI_RT" }, \ + { XFS_LI_RUD_RT, "XFS_LI_RUD_RT" }, \ + { XFS_LI_CUI_RT, "XFS_LI_CUI_RT" }, \ + { XFS_LI_CUD_RT, "XFS_LI_CUD_RT" } /* * Inode Log Item Format definitions. @@ -351,12 +359,6 @@ struct xfs_inode_log_format_32 { */ #define XFS_ILOG_IVERSION 0x8000 -#define XFS_ILOG_NONCORE (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \ - XFS_ILOG_DBROOT | XFS_ILOG_DEV | \ - XFS_ILOG_ADATA | XFS_ILOG_AEXT | \ - XFS_ILOG_ABROOT | XFS_ILOG_DOWNER | \ - XFS_ILOG_AOWNER) - #define XFS_ILOG_DFORK (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \ XFS_ILOG_DBROOT) diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 5397a8ff004d..66c7916fb5cd 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -79,6 +79,10 @@ extern const struct xlog_recover_item_ops xlog_xmi_item_ops; extern const struct xlog_recover_item_ops xlog_xmd_item_ops; extern const struct xlog_recover_item_ops xlog_rtefi_item_ops; extern const struct xlog_recover_item_ops xlog_rtefd_item_ops; +extern const struct xlog_recover_item_ops xlog_rtrui_item_ops; +extern const struct xlog_recover_item_ops xlog_rtrud_item_ops; +extern const struct xlog_recover_item_ops xlog_rtcui_item_ops; +extern const struct xlog_recover_item_ops xlog_rtcud_item_ops; /* * Macros, structures, prototypes for internal log manager use. diff --git a/fs/xfs/libxfs/xfs_metadir.c b/fs/xfs/libxfs/xfs_metadir.c index bae7377c0f22..178e89711cb7 100644 --- a/fs/xfs/libxfs/xfs_metadir.c +++ b/fs/xfs/libxfs/xfs_metadir.c @@ -29,6 +29,10 @@ #include "xfs_dir2_priv.h" #include "xfs_parent.h" #include "xfs_health.h" +#include "xfs_errortag.h" +#include "xfs_error.h" +#include "xfs_btree.h" +#include "xfs_alloc.h" /* * Metadata Directory Tree diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c index adeb25d1a444..2f5f554a36d4 100644 --- a/fs/xfs/libxfs/xfs_metafile.c +++ b/fs/xfs/libxfs/xfs_metafile.c @@ -17,6 +17,28 @@ #include "xfs_metafile.h" #include "xfs_trace.h" #include "xfs_inode.h" +#include "xfs_quota.h" +#include "xfs_errortag.h" +#include "xfs_error.h" +#include "xfs_alloc.h" + +static const struct { + enum xfs_metafile_type mtype; + const char *name; +} xfs_metafile_type_strs[] = { XFS_METAFILE_TYPE_STR }; + +const char * +xfs_metafile_type_str(enum xfs_metafile_type metatype) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(xfs_metafile_type_strs); i++) { + if (xfs_metafile_type_strs[i].mtype == metatype) + return xfs_metafile_type_strs[i].name; + } + + return NULL; +} /* Set up an inode to be recognized as a metadata directory inode. */ void @@ -50,3 +72,204 @@ xfs_metafile_clear_iflag( ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } + +/* + * Is the amount of space that could be allocated towards a given metadata + * file at or beneath a certain threshold? + */ +static inline bool +xfs_metafile_resv_can_cover( + struct xfs_inode *ip, + int64_t rhs) +{ + /* + * The amount of space that can be allocated to this metadata file is + * the remaining reservation for the particular metadata file + the + * global free block count. Take care of the first case to avoid + * touching the per-cpu counter. + */ + if (ip->i_delayed_blks >= rhs) + return true; + + /* + * There aren't enough blocks left in the inode's reservation, but it + * isn't critical unless there also isn't enough free space. + */ + return __percpu_counter_compare(&ip->i_mount->m_fdblocks, + rhs - ip->i_delayed_blks, 2048) >= 0; +} + +/* + * Is this metadata file critically low on blocks? For now we'll define that + * as the number of blocks we can get our hands on being less than 10% of what + * we reserved or less than some arbitrary number (maximum btree height). + */ +bool +xfs_metafile_resv_critical( + struct xfs_inode *ip) +{ + uint64_t asked_low_water; + + if (!ip) + return false; + + ASSERT(xfs_is_metadir_inode(ip)); + trace_xfs_metafile_resv_critical(ip, 0); + + if (!xfs_metafile_resv_can_cover(ip, ip->i_mount->m_rtbtree_maxlevels)) + return true; + + asked_low_water = div_u64(ip->i_meta_resv_asked, 10); + if (!xfs_metafile_resv_can_cover(ip, asked_low_water)) + return true; + + return XFS_TEST_ERROR(false, ip->i_mount, + XFS_ERRTAG_METAFILE_RESV_CRITICAL); +} + +/* Allocate a block from the metadata file's reservation. */ +void +xfs_metafile_resv_alloc_space( + struct xfs_inode *ip, + struct xfs_alloc_arg *args) +{ + int64_t len = args->len; + + ASSERT(xfs_is_metadir_inode(ip)); + ASSERT(args->resv == XFS_AG_RESV_METAFILE); + + trace_xfs_metafile_resv_alloc_space(ip, args->len); + + /* + * Allocate the blocks from the metadata inode's block reservation + * and update the ondisk sb counter. + */ + if (ip->i_delayed_blks > 0) { + int64_t from_resv; + + from_resv = min_t(int64_t, len, ip->i_delayed_blks); + ip->i_delayed_blks -= from_resv; + xfs_mod_delalloc(ip, 0, -from_resv); + xfs_trans_mod_sb(args->tp, XFS_TRANS_SB_RES_FDBLOCKS, + -from_resv); + len -= from_resv; + } + + /* + * Any allocation in excess of the reservation requires in-core and + * on-disk fdblocks updates. If we can grab @len blocks from the + * in-core fdblocks then all we need to do is update the on-disk + * superblock; if not, then try to steal some from the transaction's + * block reservation. Overruns are only expected for rmap btrees. + */ + if (len) { + unsigned int field; + int error; + + error = xfs_dec_fdblocks(ip->i_mount, len, true); + if (error) + field = XFS_TRANS_SB_FDBLOCKS; + else + field = XFS_TRANS_SB_RES_FDBLOCKS; + + xfs_trans_mod_sb(args->tp, field, -len); + } + + ip->i_nblocks += args->len; + xfs_trans_log_inode(args->tp, ip, XFS_ILOG_CORE); +} + +/* Free a block to the metadata file's reservation. */ +void +xfs_metafile_resv_free_space( + struct xfs_inode *ip, + struct xfs_trans *tp, + xfs_filblks_t len) +{ + int64_t to_resv; + + ASSERT(xfs_is_metadir_inode(ip)); + trace_xfs_metafile_resv_free_space(ip, len); + + ip->i_nblocks -= len; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + /* + * Add the freed blocks back into the inode's delalloc reservation + * until it reaches the maximum size. Update the ondisk fdblocks only. + */ + to_resv = ip->i_meta_resv_asked - (ip->i_nblocks + ip->i_delayed_blks); + if (to_resv > 0) { + to_resv = min_t(int64_t, to_resv, len); + ip->i_delayed_blks += to_resv; + xfs_mod_delalloc(ip, 0, to_resv); + xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FDBLOCKS, to_resv); + len -= to_resv; + } + + /* + * Everything else goes back to the filesystem, so update the in-core + * and on-disk counters. + */ + if (len) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, len); +} + +/* Release a metadata file's space reservation. */ +void +xfs_metafile_resv_free( + struct xfs_inode *ip) +{ + /* Non-btree metadata inodes don't need space reservations. */ + if (!ip || !ip->i_meta_resv_asked) + return; + + ASSERT(xfs_is_metadir_inode(ip)); + trace_xfs_metafile_resv_free(ip, 0); + + if (ip->i_delayed_blks) { + xfs_mod_delalloc(ip, 0, -ip->i_delayed_blks); + xfs_add_fdblocks(ip->i_mount, ip->i_delayed_blks); + ip->i_delayed_blks = 0; + } + ip->i_meta_resv_asked = 0; +} + +/* Set up a metadata file's space reservation. */ +int +xfs_metafile_resv_init( + struct xfs_inode *ip, + xfs_filblks_t ask) +{ + xfs_filblks_t hidden_space; + xfs_filblks_t used; + int error; + + if (!ip || ip->i_meta_resv_asked > 0) + return 0; + + ASSERT(xfs_is_metadir_inode(ip)); + + /* + * Space taken by all other metadata btrees are accounted on-disk as + * used space. We therefore only hide the space that is reserved but + * not used by the trees. + */ + used = ip->i_nblocks; + if (used > ask) + ask = used; + hidden_space = ask - used; + + error = xfs_dec_fdblocks(ip->i_mount, hidden_space, true); + if (error) { + trace_xfs_metafile_resv_init_error(ip, error, _RET_IP_); + return error; + } + + xfs_mod_delalloc(ip, 0, hidden_space); + ip->i_delayed_blks = hidden_space; + ip->i_meta_resv_asked = ask; + + trace_xfs_metafile_resv_init(ip, ask); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_metafile.h b/fs/xfs/libxfs/xfs_metafile.h index acec400123db..95af4b52e5a7 100644 --- a/fs/xfs/libxfs/xfs_metafile.h +++ b/fs/xfs/libxfs/xfs_metafile.h @@ -6,6 +6,8 @@ #ifndef __XFS_METAFILE_H__ #define __XFS_METAFILE_H__ +const char *xfs_metafile_type_str(enum xfs_metafile_type metatype); + /* All metadata files must have these flags set. */ #define XFS_METAFILE_DIFLAGS (XFS_DIFLAG_IMMUTABLE | \ XFS_DIFLAG_SYNC | \ @@ -21,6 +23,17 @@ void xfs_metafile_set_iflag(struct xfs_trans *tp, struct xfs_inode *ip, enum xfs_metafile_type metafile_type); void xfs_metafile_clear_iflag(struct xfs_trans *tp, struct xfs_inode *ip); +/* Space reservations for metadata inodes. */ +struct xfs_alloc_arg; + +bool xfs_metafile_resv_critical(struct xfs_inode *ip); +void xfs_metafile_resv_alloc_space(struct xfs_inode *ip, + struct xfs_alloc_arg *args); +void xfs_metafile_resv_free_space(struct xfs_inode *ip, struct xfs_trans *tp, + xfs_filblks_t len); +void xfs_metafile_resv_free(struct xfs_inode *ip); +int xfs_metafile_resv_init(struct xfs_inode *ip, xfs_filblks_t ask); + /* Code specific to kernel/userspace; must be provided externally. */ int xfs_trans_metafile_iget(struct xfs_trans *tp, xfs_ino_t ino, diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h index ad0dedf00f18..a85ecddaa48e 100644 --- a/fs/xfs/libxfs/xfs_ondisk.h +++ b/fs/xfs/libxfs/xfs_ondisk.h @@ -83,6 +83,10 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(union xfs_rtword_raw, 4); XFS_CHECK_STRUCT_SIZE(union xfs_suminfo_raw, 4); XFS_CHECK_STRUCT_SIZE(struct xfs_rtbuf_blkinfo, 48); + XFS_CHECK_STRUCT_SIZE(xfs_rtrmap_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrmap_root, 4); + XFS_CHECK_STRUCT_SIZE(xfs_rtrefcount_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrefcount_root, 4); /* * m68k has problems with struct xfs_attr_leaf_name_remote, but we pad diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 2dbab68b4fe6..cebe83f7842a 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -25,6 +25,9 @@ #include "xfs_ag.h" #include "xfs_health.h" #include "xfs_refcount_item.h" +#include "xfs_rtgroup.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_refcount_intent_cache; @@ -128,7 +131,7 @@ xfs_refcount_check_irec( struct xfs_perag *pag, const struct xfs_refcount_irec *irec) { - if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) + if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) return __this_address; if (!xfs_refcount_check_domain(irec)) @@ -138,12 +141,43 @@ xfs_refcount_check_irec( if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) return __this_address; - if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) + if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) return __this_address; return NULL; } +xfs_failaddr_t +xfs_rtrefcount_check_irec( + struct xfs_rtgroup *rtg, + const struct xfs_refcount_irec *irec) +{ + if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) + return __this_address; + + if (!xfs_refcount_check_domain(irec)) + return __this_address; + + /* check for valid extent range, including overflow */ + if (!xfs_verify_rgbext(rtg, irec->rc_startblock, irec->rc_blockcount)) + return __this_address; + + if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) + return __this_address; + + return NULL; +} + +static inline xfs_failaddr_t +xfs_refcount_check_btrec( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *irec) +{ + if (xfs_btree_is_rtrefcount(cur->bc_ops)) + return xfs_rtrefcount_check_irec(to_rtg(cur->bc_group), irec); + return xfs_refcount_check_irec(to_perag(cur->bc_group), irec); +} + static inline int xfs_refcount_complain_bad_rec( struct xfs_btree_cur *cur, @@ -152,9 +186,15 @@ xfs_refcount_complain_bad_rec( { struct xfs_mount *mp = cur->bc_mp; - xfs_warn(mp, + if (xfs_btree_is_rtrefcount(cur->bc_ops)) { + xfs_warn(mp, + "RT Refcount BTree record corruption in rtgroup %u detected at %pS!", + cur->bc_group->xg_gno, fa); + } else { + xfs_warn(mp, "Refcount BTree record corruption in AG %d detected at %pS!", cur->bc_group->xg_gno, fa); + } xfs_warn(mp, "Start block 0x%x, block count 0x%x, references 0x%x", irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); @@ -180,7 +220,7 @@ xfs_refcount_get_rec( return error; xfs_refcount_btrec_to_irec(rec, irec); - fa = xfs_refcount_check_irec(to_perag(cur->bc_group), irec); + fa = xfs_refcount_check_btrec(cur, irec); if (fa) return xfs_refcount_complain_bad_rec(cur, fa, irec); @@ -853,9 +893,9 @@ xfs_refc_merge_refcount( const struct xfs_refcount_irec *irec, enum xfs_refc_adjust_op adjust) { - /* Once a record hits MAXREFCOUNT, it is pinned there forever */ - if (irec->rc_refcount == MAXREFCOUNT) - return MAXREFCOUNT; + /* Once a record hits XFS_REFC_REFCOUNT_MAX, it is pinned forever */ + if (irec->rc_refcount == XFS_REFC_REFCOUNT_MAX) + return XFS_REFC_REFCOUNT_MAX; return irec->rc_refcount + adjust; } @@ -898,7 +938,7 @@ xfs_refc_want_merge_center( * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount + right->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; *ulenp = ulen; @@ -933,7 +973,7 @@ xfs_refc_want_merge_left( * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; return true; @@ -967,7 +1007,7 @@ xfs_refc_want_merge_right( * hence we need to catch u32 addition overflows here. */ ulen += cright->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; return true; @@ -1065,7 +1105,7 @@ xfs_refcount_still_have_space( */ overhead = xfs_allocfree_block_count(cur->bc_mp, cur->bc_refc.shape_changes); - overhead += cur->bc_mp->m_refc_maxlevels; + overhead += cur->bc_maxlevels; overhead *= cur->bc_mp->m_sb.sb_blocksize; /* @@ -1085,6 +1125,22 @@ xfs_refcount_still_have_space( cur->bc_refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; } +/* Schedule an extent free. */ +static int +xrefc_free_extent( + struct xfs_btree_cur *cur, + struct xfs_refcount_irec *rec) +{ + unsigned int flags = 0; + + if (xfs_btree_is_rtrefcount(cur->bc_ops)) + flags |= XFS_FREE_EXTENT_REALTIME; + + return xfs_free_extent_later(cur->bc_tp, + xfs_gbno_to_fsb(cur->bc_group, rec->rc_startblock), + rec->rc_blockcount, NULL, XFS_AG_RESV_NONE, flags); +} + /* * Adjust the refcounts of middle extents. At this point we should have * split extents that crossed the adjustment range; merged with adjacent @@ -1101,7 +1157,6 @@ xfs_refcount_adjust_extents( struct xfs_refcount_irec ext, tmp; int error; int found_rec, found_tmp; - xfs_fsblock_t fsbno; /* Merging did all the work already. */ if (*aglen == 0) @@ -1117,7 +1172,7 @@ xfs_refcount_adjust_extents( if (error) goto out_error; if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; + ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_SHARED; @@ -1154,11 +1209,7 @@ xfs_refcount_adjust_extents( goto out_error; } } else { - fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group), - tmp.rc_startblock); - error = xfs_free_extent_later(cur->bc_tp, fsbno, - tmp.rc_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + error = xrefc_free_extent(cur, &tmp); if (error) goto out_error; } @@ -1196,7 +1247,7 @@ xfs_refcount_adjust_extents( * Adjust the reference count and either update the tree * (incr) or free the blocks (decr). */ - if (ext.rc_refcount == MAXREFCOUNT) + if (ext.rc_refcount == XFS_REFC_REFCOUNT_MAX) goto skip; ext.rc_refcount += adj; trace_xfs_refcount_modify_extent(cur, &ext); @@ -1216,11 +1267,7 @@ xfs_refcount_adjust_extents( } goto advloop; } else { - fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group), - ext.rc_startblock); - error = xfs_free_extent_later(cur->bc_tp, fsbno, - ext.rc_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + error = xrefc_free_extent(cur, &ext); if (error) goto out_error; } @@ -1416,6 +1463,115 @@ xfs_refcount_finish_one( return error; } +/* + * Set up a continuation a deferred rtrefcount operation by updating the + * intent. Checks to make sure we're not going to run off the end of the + * rtgroup. + */ +static inline int +xfs_rtrefcount_continue_op( + struct xfs_btree_cur *cur, + struct xfs_refcount_intent *ri, + xfs_agblock_t new_agbno) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + + if (XFS_IS_CORRUPT(mp, !xfs_verify_rgbext(rtg, new_agbno, + ri->ri_blockcount))) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + + ri->ri_startblock = xfs_rgbno_to_rtb(rtg, new_agbno); + + ASSERT(xfs_verify_rtbext(mp, ri->ri_startblock, ri->ri_blockcount)); + return 0; +} + +/* + * Process one of the deferred realtime refcount operations. We pass back the + * btree cursor to maintain our lock on the btree between calls. + */ +int +xfs_rtrefcount_finish_one( + struct xfs_trans *tp, + struct xfs_refcount_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + struct xfs_btree_cur *rcur = *pcur; + int error = 0; + xfs_rgblock_t bno; + unsigned long nr_ops = 0; + int shape_changes = 0; + + bno = xfs_rtb_to_rgbno(mp, ri->ri_startblock); + + trace_xfs_refcount_deferred(mp, ri); + + if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) + return -EIO; + + /* + * If we haven't gotten a cursor or the cursor AG doesn't match + * the startblock, get one now. + */ + if (rcur != NULL && rcur->bc_group != ri->ri_group) { + nr_ops = rcur->bc_refc.nr_ops; + shape_changes = rcur->bc_refc.shape_changes; + xfs_btree_del_cursor(rcur, 0); + rcur = NULL; + *pcur = NULL; + } + if (rcur == NULL) { + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_REFCOUNT); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_REFCOUNT); + *pcur = rcur = xfs_rtrefcountbt_init_cursor(tp, rtg); + + rcur->bc_refc.nr_ops = nr_ops; + rcur->bc_refc.shape_changes = shape_changes; + } + + switch (ri->ri_type) { + case XFS_REFCOUNT_INCREASE: + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_INCREASE); + if (error) + return error; + if (ri->ri_blockcount > 0) + error = xfs_rtrefcount_continue_op(rcur, ri, bno); + break; + case XFS_REFCOUNT_DECREASE: + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_DECREASE); + if (error) + return error; + if (ri->ri_blockcount > 0) + error = xfs_rtrefcount_continue_op(rcur, ri, bno); + break; + case XFS_REFCOUNT_ALLOC_COW: + error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; + break; + case XFS_REFCOUNT_FREE_COW: + error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + if (!error && ri->ri_blockcount > 0) + trace_xfs_refcount_finish_one_leftover(mp, ri); + return error; +} + /* * Record a refcount intent for later processing. */ @@ -1423,6 +1579,7 @@ static void __xfs_refcount_add( struct xfs_trans *tp, enum xfs_refcount_intent_type type, + bool isrt, xfs_fsblock_t startblock, xfs_extlen_t blockcount) { @@ -1434,6 +1591,7 @@ __xfs_refcount_add( ri->ri_type = type; ri->ri_startblock = startblock; ri->ri_blockcount = blockcount; + ri->ri_realtime = isrt; xfs_refcount_defer_add(tp, ri); } @@ -1444,12 +1602,13 @@ __xfs_refcount_add( void xfs_refcount_increase_extent( struct xfs_trans *tp, + bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, PREV->br_startblock, + __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } @@ -1459,12 +1618,13 @@ xfs_refcount_increase_extent( void xfs_refcount_decrease_extent( struct xfs_trans *tp, + bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, PREV->br_startblock, + __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } @@ -1666,7 +1826,7 @@ xfs_refcount_adjust_cow_extents( goto out_error; } if (!found_rec) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; + ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_COW; @@ -1820,6 +1980,7 @@ __xfs_refcount_cow_free( void xfs_refcount_alloc_cow_extent( struct xfs_trans *tp, + bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { @@ -1828,17 +1989,17 @@ xfs_refcount_alloc_cow_extent( if (!xfs_has_reflink(mp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len); + __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, isrt, fsb, len); /* Add rmap entry */ - xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), - XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); + xfs_rmap_alloc_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); } /* Forget a CoW staging event in the refcount btree. */ void xfs_refcount_free_cow_extent( struct xfs_trans *tp, + bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { @@ -1848,9 +2009,8 @@ xfs_refcount_free_cow_extent( return; /* Remove rmap entry */ - xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), - XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); - __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len); + xfs_rmap_free_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); + __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, isrt, fsb, len); } struct xfs_refcount_recovery { @@ -1879,8 +2039,7 @@ xfs_refcount_recover_extent( INIT_LIST_HEAD(&rr->rr_list); xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); - if (xfs_refcount_check_irec(to_perag(cur->bc_group), &rr->rr_rrec) != - NULL || + if (xfs_refcount_check_btrec(cur, &rr->rr_rrec) != NULL || XFS_IS_CORRUPT(cur->bc_mp, rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) { xfs_btree_mark_sick(cur); @@ -1895,12 +2054,13 @@ xfs_refcount_recover_extent( /* Find and remove leftover CoW reservations. */ int xfs_refcount_recover_cow_leftovers( - struct xfs_mount *mp, - struct xfs_perag *pag) + struct xfs_group *xg) { + struct xfs_mount *mp = xg->xg_mount; + bool isrt = xg->xg_type == XG_TYPE_RTG; struct xfs_trans *tp; struct xfs_btree_cur *cur; - struct xfs_buf *agbp; + struct xfs_buf *agbp = NULL; struct xfs_refcount_recovery *rr, *n; struct list_head debris; union xfs_btree_irec low = { @@ -1913,10 +2073,19 @@ xfs_refcount_recover_cow_leftovers( xfs_fsblock_t fsb; int error; - /* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */ + /* reflink filesystems must not have groups larger than 2^31-1 blocks */ + BUILD_BUG_ON(XFS_MAX_RGBLOCKS >= XFS_REFC_COWFLAG); BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG); - if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS) - return -EOPNOTSUPP; + + if (isrt) { + if (!xfs_has_rtgroups(mp)) + return 0; + if (xfs_group_max_blocks(xg) >= XFS_MAX_RGBLOCKS) + return -EOPNOTSUPP; + } else { + if (xfs_group_max_blocks(xg) > XFS_MAX_CRC_AG_BLOCKS) + return -EOPNOTSUPP; + } INIT_LIST_HEAD(&debris); @@ -1934,16 +2103,24 @@ xfs_refcount_recover_cow_leftovers( if (error) return error; - error = xfs_alloc_read_agf(pag, tp, 0, &agbp); - if (error) - goto out_trans; - cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); + if (isrt) { + xfs_rtgroup_lock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); + cur = xfs_rtrefcountbt_init_cursor(tp, to_rtg(xg)); + } else { + error = xfs_alloc_read_agf(to_perag(xg), tp, 0, &agbp); + if (error) + goto out_trans; + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, to_perag(xg)); + } /* Find all the leftover CoW staging extents. */ error = xfs_btree_query_range(cur, &low, &high, xfs_refcount_recover_extent, &debris); xfs_btree_del_cursor(cur, error); - xfs_trans_brelse(tp, agbp); + if (agbp) + xfs_trans_brelse(tp, agbp); + else + xfs_rtgroup_unlock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); xfs_trans_cancel(tp); if (error) goto out_free; @@ -1956,14 +2133,15 @@ xfs_refcount_recover_cow_leftovers( goto out_free; /* Free the orphan record */ - fsb = xfs_agbno_to_fsb(pag, rr->rr_rrec.rc_startblock); - xfs_refcount_free_cow_extent(tp, fsb, + fsb = xfs_gbno_to_fsb(xg, rr->rr_rrec.rc_startblock); + xfs_refcount_free_cow_extent(tp, isrt, fsb, rr->rr_rrec.rc_blockcount); /* Free the block. */ error = xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + XFS_AG_RESV_NONE, + isrt ? XFS_FREE_EXTENT_REALTIME : 0); if (error) goto out_trans; @@ -2028,7 +2206,7 @@ xfs_refcount_query_range_helper( xfs_failaddr_t fa; xfs_refcount_btrec_to_irec(rec, &irec); - fa = xfs_refcount_check_irec(to_perag(cur->bc_group), &irec); + fa = xfs_refcount_check_btrec(cur, &irec); if (fa) return xfs_refcount_complain_bad_rec(cur, fa, &irec); diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index 62d78afcf1f3..f2e299a716a4 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -12,6 +12,7 @@ struct xfs_perag; struct xfs_btree_cur; struct xfs_bmbt_irec; struct xfs_refcount_irec; +struct xfs_rtgroup; extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); @@ -60,6 +61,7 @@ struct xfs_refcount_intent { enum xfs_refcount_intent_type ri_type; xfs_extlen_t ri_blockcount; xfs_fsblock_t ri_startblock; + bool ri_realtime; }; /* Check that the refcount is appropriate for the record domain. */ @@ -74,24 +76,25 @@ xfs_refcount_check_domain( return true; } -void xfs_refcount_increase_extent(struct xfs_trans *tp, +void xfs_refcount_increase_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); -void xfs_refcount_decrease_extent(struct xfs_trans *tp, +void xfs_refcount_decrease_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); -extern int xfs_refcount_finish_one(struct xfs_trans *tp, +int xfs_refcount_finish_one(struct xfs_trans *tp, + struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); +int xfs_rtrefcount_finish_one(struct xfs_trans *tp, struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur, xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_end_of_shared); -void xfs_refcount_alloc_cow_extent(struct xfs_trans *tp, xfs_fsblock_t fsb, - xfs_extlen_t len); -void xfs_refcount_free_cow_extent(struct xfs_trans *tp, xfs_fsblock_t fsb, - xfs_extlen_t len); -extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, - struct xfs_perag *pag); +void xfs_refcount_alloc_cow_extent(struct xfs_trans *tp, bool isrt, + xfs_fsblock_t fsb, xfs_extlen_t len); +void xfs_refcount_free_cow_extent(struct xfs_trans *tp, bool isrt, + xfs_fsblock_t fsb, xfs_extlen_t len); +int xfs_refcount_recover_cow_leftovers(struct xfs_group *xg); /* * While we're adjusting the refcounts records of an extent, we have @@ -120,6 +123,8 @@ extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec); xfs_failaddr_t xfs_refcount_check_irec(struct xfs_perag *pag, const struct xfs_refcount_irec *irec); +xfs_failaddr_t xfs_rtrefcount_check_irec(struct xfs_rtgroup *rtg, + const struct xfs_refcount_irec *irec); extern int xfs_refcount_insert(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat); diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index d0df68dc3131..3cdf50563fec 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -25,6 +25,8 @@ #include "xfs_ag.h" #include "xfs_health.h" #include "xfs_rmap_item.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" struct kmem_cache *xfs_rmap_intent_cache; @@ -264,11 +266,77 @@ xfs_rmap_check_irec( return NULL; } +static xfs_failaddr_t +xfs_rtrmap_check_meta_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (irec->rm_offset != 0) + return __this_address; + if (irec->rm_flags & XFS_RMAP_UNWRITTEN) + return __this_address; + + switch (irec->rm_owner) { + case XFS_RMAP_OWN_FS: + if (irec->rm_startblock != 0) + return __this_address; + if (irec->rm_blockcount != mp->m_sb.sb_rextsize) + return __this_address; + return NULL; + case XFS_RMAP_OWN_COW: + if (!xfs_has_rtreflink(mp)) + return __this_address; + if (!xfs_verify_rgbext(rtg, irec->rm_startblock, + irec->rm_blockcount)) + return __this_address; + return NULL; + default: + return __this_address; + } + + return NULL; +} + +static xfs_failaddr_t +xfs_rtrmap_check_inode_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (!xfs_verify_ino(mp, irec->rm_owner)) + return __this_address; + if (!xfs_verify_rgbext(rtg, irec->rm_startblock, irec->rm_blockcount)) + return __this_address; + if (!xfs_verify_fileext(mp, irec->rm_offset, irec->rm_blockcount)) + return __this_address; + return NULL; +} + +xfs_failaddr_t +xfs_rtrmap_check_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + if (irec->rm_blockcount == 0) + return __this_address; + if (irec->rm_flags & (XFS_RMAP_BMBT_BLOCK | XFS_RMAP_ATTR_FORK)) + return __this_address; + if (XFS_RMAP_NON_INODE_OWNER(irec->rm_owner)) + return xfs_rtrmap_check_meta_irec(rtg, irec); + return xfs_rtrmap_check_inode_irec(rtg, irec); +} + static inline xfs_failaddr_t xfs_rmap_check_btrec( struct xfs_btree_cur *cur, const struct xfs_rmap_irec *irec) { + if (xfs_btree_is_rtrmap(cur->bc_ops) || + xfs_btree_is_mem_rtrmap(cur->bc_ops)) + return xfs_rtrmap_check_irec(to_rtg(cur->bc_group), irec); return xfs_rmap_check_irec(to_perag(cur->bc_group), irec); } @@ -283,6 +351,10 @@ xfs_rmap_complain_bad_rec( if (xfs_btree_is_mem_rmap(cur->bc_ops)) xfs_warn(mp, "In-Memory Reverse Mapping BTree record corruption detected at %pS!", fa); + else if (xfs_btree_is_rtrmap(cur->bc_ops)) + xfs_warn(mp, + "RT Reverse Mapping BTree record corruption in rtgroup %u detected at %pS!", + cur->bc_group->xg_gno, fa); else xfs_warn(mp, "Reverse Mapping BTree record corruption in AG %d detected at %pS!", @@ -525,7 +597,7 @@ xfs_rmap_free_check_owner( struct xfs_btree_cur *cur, uint64_t ltoff, struct xfs_rmap_irec *rec, - xfs_filblks_t len, + xfs_extlen_t len, uint64_t owner, uint64_t offset, unsigned int flags) @@ -2556,6 +2628,47 @@ __xfs_rmap_finish_intent( } } +static int +xfs_rmap_finish_init_cursor( + struct xfs_trans *tp, + struct xfs_rmap_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_perag *pag = to_perag(ri->ri_group); + struct xfs_buf *agbp = NULL; + int error; + + /* + * Refresh the freelist before we start changing the rmapbt, because a + * shape change could cause us to allocate blocks. + */ + error = xfs_free_extent_fix_freelist(tp, pag, &agbp); + if (error) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + return error; + } + if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + return -EFSCORRUPTED; + } + *pcur = xfs_rmapbt_init_cursor(tp->t_mountp, tp, agbp, pag); + return 0; +} + +static int +xfs_rtrmap_finish_init_cursor( + struct xfs_trans *tp, + struct xfs_rmap_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); + *pcur = xfs_rtrmapbt_init_cursor(tp, rtg); + return 0; +} + /* * Process one of the deferred rmap operations. We pass back the * btree cursor to maintain our lock on the rmapbt between calls. @@ -2571,8 +2684,6 @@ xfs_rmap_finish_one( { struct xfs_owner_info oinfo; struct xfs_mount *mp = tp->t_mountp; - struct xfs_btree_cur *rcur = *pcur; - struct xfs_buf *agbp = NULL; xfs_agblock_t bno; bool unwritten; int error = 0; @@ -2586,38 +2697,26 @@ xfs_rmap_finish_one( * If we haven't gotten a cursor or the cursor AG doesn't match * the startblock, get one now. */ - if (rcur != NULL && rcur->bc_group != ri->ri_group) { - xfs_btree_del_cursor(rcur, 0); - rcur = NULL; + if (*pcur != NULL && (*pcur)->bc_group != ri->ri_group) { + xfs_btree_del_cursor(*pcur, 0); *pcur = NULL; } - if (rcur == NULL) { - struct xfs_perag *pag = to_perag(ri->ri_group); - - /* - * Refresh the freelist before we start changing the - * rmapbt, because a shape change could cause us to - * allocate blocks. - */ - error = xfs_free_extent_fix_freelist(tp, pag, &agbp); - if (error) { - xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + if (*pcur == NULL) { + if (ri->ri_group->xg_type == XG_TYPE_RTG) + error = xfs_rtrmap_finish_init_cursor(tp, ri, pcur); + else + error = xfs_rmap_finish_init_cursor(tp, ri, pcur); + if (error) return error; - } - if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) { - xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); - return -EFSCORRUPTED; - } - - *pcur = rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag); } xfs_rmap_ino_owner(&oinfo, ri->ri_owner, ri->ri_whichfork, ri->ri_bmap.br_startoff); unwritten = ri->ri_bmap.br_state == XFS_EXT_UNWRITTEN; - bno = XFS_FSB_TO_AGBNO(rcur->bc_mp, ri->ri_bmap.br_startblock); - error = __xfs_rmap_finish_intent(rcur, ri->ri_type, bno, + bno = xfs_fsb_to_gbno(mp, ri->ri_bmap.br_startblock, + ri->ri_group->xg_type); + error = __xfs_rmap_finish_intent(*pcur, ri->ri_type, bno, ri->ri_bmap.br_blockcount, &oinfo, unwritten); if (error) return error; @@ -2647,6 +2746,7 @@ __xfs_rmap_add( struct xfs_trans *tp, enum xfs_rmap_intent_type type, uint64_t owner, + bool isrt, int whichfork, struct xfs_bmbt_irec *bmap) { @@ -2658,6 +2758,7 @@ __xfs_rmap_add( ri->ri_owner = owner; ri->ri_whichfork = whichfork; ri->ri_bmap = *bmap; + ri->ri_realtime = isrt; xfs_rmap_defer_add(tp, ri); } @@ -2671,6 +2772,7 @@ xfs_rmap_map_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_MAP; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork)) return; @@ -2678,7 +2780,7 @@ xfs_rmap_map_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_MAP_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* Unmap an extent out of a file. */ @@ -2690,6 +2792,7 @@ xfs_rmap_unmap_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_UNMAP; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork)) return; @@ -2697,7 +2800,7 @@ xfs_rmap_unmap_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_UNMAP_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* @@ -2715,6 +2818,7 @@ xfs_rmap_convert_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_CONVERT; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(mp, whichfork)) return; @@ -2722,15 +2826,15 @@ xfs_rmap_convert_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_CONVERT_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* Schedule the creation of an rmap for non-file data. */ void xfs_rmap_alloc_extent( struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t bno, + bool isrt, + xfs_fsblock_t fsbno, xfs_extlen_t len, uint64_t owner) { @@ -2739,20 +2843,20 @@ xfs_rmap_alloc_extent( if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK)) return; - bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno); + bmap.br_startblock = fsbno; bmap.br_blockcount = len; bmap.br_startoff = 0; bmap.br_state = XFS_EXT_NORM; - __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, XFS_DATA_FORK, &bmap); + __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, isrt, XFS_DATA_FORK, &bmap); } /* Schedule the deletion of an rmap for non-file data. */ void xfs_rmap_free_extent( struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t bno, + bool isrt, + xfs_fsblock_t fsbno, xfs_extlen_t len, uint64_t owner) { @@ -2761,12 +2865,12 @@ xfs_rmap_free_extent( if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK)) return; - bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno); + bmap.br_startblock = fsbno; bmap.br_blockcount = len; bmap.br_startoff = 0; bmap.br_state = XFS_EXT_NORM; - __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, XFS_DATA_FORK, &bmap); + __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, isrt, XFS_DATA_FORK, &bmap); } /* Compare rmap records. Returns -1 if a < b, 1 if a > b, and 0 if equal. */ diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 96b4321d8310..5f39f6e53cd1 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -7,6 +7,7 @@ #define __XFS_RMAP_H__ struct xfs_perag; +struct xfs_rtgroup; static inline void xfs_rmap_ino_bmbt_owner( @@ -174,6 +175,7 @@ struct xfs_rmap_intent { uint64_t ri_owner; struct xfs_bmbt_irec ri_bmap; struct xfs_group *ri_group; + bool ri_realtime; }; /* functions for updating the rmapbt based on bmbt map/unmap operations */ @@ -184,10 +186,10 @@ void xfs_rmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip, void xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, struct xfs_bmbt_irec *imap); -void xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner); -void xfs_rmap_free_extent(struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner); +void xfs_rmap_alloc_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno, + xfs_extlen_t len, uint64_t owner); +void xfs_rmap_free_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno, + xfs_extlen_t len, uint64_t owner); int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri, struct xfs_btree_cur **pcur); @@ -206,6 +208,8 @@ xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_rmap_irec *irec); xfs_failaddr_t xfs_rmap_check_irec(struct xfs_perag *pag, const struct xfs_rmap_irec *irec); +xfs_failaddr_t xfs_rtrmap_check_irec(struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec); int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, enum xbtree_recpacking *outcome); diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 4ddfb7e395b3..770adf60dd73 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -1055,7 +1055,7 @@ xfs_rtfree_extent( xfs_rtxlen_t len) /* length of extent freed */ { struct xfs_mount *mp = tp->t_mountp; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); struct xfs_rtalloc_args args = { .mp = mp, .tp = tp, diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h index 16563a44bd13..22e5d9cd95f4 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.h +++ b/fs/xfs/libxfs/xfs_rtbitmap.h @@ -135,6 +135,15 @@ xfs_rtb_to_rtx( return div_u64(rtbno, mp->m_sb.sb_rextsize); } +/* Return the offset of a rtgroup block number within an rt extent. */ +static inline xfs_extlen_t +xfs_rgbno_to_rtxoff( + struct xfs_mount *mp, + xfs_rgblock_t rgbno) +{ + return rgbno % mp->m_sb.sb_rextsize; +} + /* Return the offset of an rt block number within an rt extent. */ static inline xfs_extlen_t xfs_rtb_to_rtxoff( diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index 4f3bfc884aff..d84d32f1b48f 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -33,6 +33,8 @@ #include "xfs_rtbitmap.h" #include "xfs_metafile.h" #include "xfs_metadir.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* Find the first usable fsblock in this rtgroup. */ static inline uint32_t @@ -197,11 +199,17 @@ xfs_rtgroup_lock( * Lock both realtime free space metadata inodes for a freespace * update. */ - xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL); - xfs_ilock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL); + xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); + xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL); } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { - xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED); + xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); } + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_ilock(rtg_refcount(rtg), XFS_ILOCK_EXCL); } /* Unlock metadata inodes associated with this rt group. */ @@ -214,11 +222,17 @@ xfs_rtgroup_unlock( ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) || !(rtglock_flags & XFS_RTGLOCK_BITMAP)); + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_iunlock(rtg_refcount(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_EXCL); + if (rtglock_flags & XFS_RTGLOCK_BITMAP) { - xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL); - xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL); + xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL); + xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { - xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED); + xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); } } @@ -236,11 +250,15 @@ xfs_rtgroup_trans_join( ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED)); if (rtglock_flags & XFS_RTGLOCK_BITMAP) { - xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_BITMAP], - XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_SUMMARY], - XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, rtg_bitmap(rtg), XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, rtg_summary(rtg), XFS_ILOCK_EXCL); } + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_trans_ijoin(tp, rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_trans_ijoin(tp, rtg_refcount(rtg), XFS_ILOCK_EXCL); } /* Retrieve rt group geometry. */ @@ -284,7 +302,8 @@ xfs_rtginode_ilock_print_fn( const struct xfs_inode *ip = container_of(m, struct xfs_inode, i_lock.dep_map); - printk(KERN_CONT " rgno=%u", ip->i_projid); + printk(KERN_CONT " rgno=%u metatype=%s", ip->i_projid, + xfs_metafile_type_str(ip->i_metatype)); } /* @@ -316,8 +335,10 @@ struct xfs_rtginode_ops { unsigned int sick; /* rtgroup sickness flag */ + unsigned int fmt_mask; /* all valid data fork formats */ + /* Does the fs have this feature? */ - bool (*enabled)(struct xfs_mount *mp); + bool (*enabled)(const struct xfs_mount *mp); /* Create this rtgroup metadata inode and initialize it. */ int (*create)(struct xfs_rtgroup *rtg, @@ -331,14 +352,40 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = { .name = "bitmap", .metafile_type = XFS_METAFILE_RTBITMAP, .sick = XFS_SICK_RG_BITMAP, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), .create = xfs_rtbitmap_create, }, [XFS_RTGI_SUMMARY] = { .name = "summary", .metafile_type = XFS_METAFILE_RTSUMMARY, .sick = XFS_SICK_RG_SUMMARY, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), .create = xfs_rtsummary_create, }, + [XFS_RTGI_RMAP] = { + .name = "rmap", + .metafile_type = XFS_METAFILE_RTRMAP, + .sick = XFS_SICK_RG_RMAPBT, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use the + * rtrmapbt predicate here. + */ + .enabled = xfs_has_rmapbt, + .create = xfs_rtrmapbt_create, + }, + [XFS_RTGI_REFCOUNT] = { + .name = "refcount", + .metafile_type = XFS_METAFILE_RTREFCOUNT, + .sick = XFS_SICK_RG_REFCNTBT, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* same comment about growfs and rmap inodes applies here */ + .enabled = xfs_has_reflink, + .create = xfs_rtrefcountbt_create, + }, }; /* Return the shortname of this rtgroup inode. */ @@ -435,8 +482,7 @@ xfs_rtginode_load( return error; } - if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && - ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) { + if (XFS_IS_CORRUPT(mp, !((1U << ip->i_df.if_format) & ops->fmt_mask))) { xfs_irele(ip); xfs_rtginode_mark_sick(rtg, type); return -EFSCORRUPTED; diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 7e7e491ff06f..03f39d4e43fc 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -14,6 +14,8 @@ struct xfs_trans; enum xfs_rtg_inodes { XFS_RTGI_BITMAP, /* allocation bitmap */ XFS_RTGI_SUMMARY, /* allocation summary */ + XFS_RTGI_RMAP, /* rmap btree inode */ + XFS_RTGI_REFCOUNT, /* refcount btree inode */ XFS_RTGI_MAX, }; @@ -64,6 +66,26 @@ static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg) return rtg->rtg_group.xg_gno; } +static inline struct xfs_inode *rtg_bitmap(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_BITMAP]; +} + +static inline struct xfs_inode *rtg_summary(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_SUMMARY]; +} + +static inline struct xfs_inode *rtg_rmap(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_RMAP]; +} + +static inline struct xfs_inode *rtg_refcount(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_REFCOUNT]; +} + /* Passive rtgroup references */ static inline struct xfs_rtgroup * xfs_rtgroup_get( @@ -122,6 +144,32 @@ xfs_rtgroup_next( return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1); } +static inline bool +xfs_verify_rgbno( + struct xfs_rtgroup *rtg, + xfs_rgblock_t rgbno) +{ + ASSERT(xfs_has_rtgroups(rtg_mount(rtg))); + + return xfs_verify_gbno(rtg_group(rtg), rgbno); +} + +/* + * Check that [@rgbno,@len] is a valid extent range in @rtg. + * + * Must only be used for RTG-enabled file systems. + */ +static inline bool +xfs_verify_rgbext( + struct xfs_rtgroup *rtg, + xfs_rgblock_t rgbno, + xfs_extlen_t len) +{ + ASSERT(xfs_has_rtgroups(rtg_mount(rtg))); + + return xfs_verify_gbext(rtg_group(rtg), rgbno, len); +} + static inline xfs_rtblock_t xfs_rgbno_to_rtb( struct xfs_rtgroup *rtg, @@ -223,9 +271,15 @@ int xfs_update_last_rtgroup_size(struct xfs_mount *mp, #define XFS_RTGLOCK_BITMAP (1U << 0) /* Lock the rt bitmap inode in shared mode */ #define XFS_RTGLOCK_BITMAP_SHARED (1U << 1) +/* Lock the rt rmap inode in exclusive mode */ +#define XFS_RTGLOCK_RMAP (1U << 2) +/* Lock the rt refcount inode in exclusive mode */ +#define XFS_RTGLOCK_REFCOUNT (1U << 3) #define XFS_RTGLOCK_ALL_FLAGS (XFS_RTGLOCK_BITMAP | \ - XFS_RTGLOCK_BITMAP_SHARED) + XFS_RTGLOCK_BITMAP_SHARED | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) void xfs_rtgroup_lock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags); void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags); @@ -248,6 +302,8 @@ int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type, bool init); void xfs_rtginode_irele(struct xfs_inode **ipp); +void xfs_rtginode_irele(struct xfs_inode **ipp); + static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno, enum xfs_rtg_inodes type) { @@ -272,7 +328,7 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, } # define xfs_rtgroup_extents(mp, rgno) (0) -# define xfs_update_last_rtgroup_size(mp, rgno) (-EOPNOTSUPP) +# define xfs_update_last_rtgroup_size(mp, rgno) (0) # define xfs_rtgroup_lock(rtg, gf) ((void)0) # define xfs_rtgroup_unlock(rtg, gf) ((void)0) # define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c new file mode 100644 index 000000000000..3db5e7a4a945 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c @@ -0,0 +1,757 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_alloc.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_refcount.h" +#include "xfs_trace.h" +#include "xfs_cksum.h" +#include "xfs_error.h" +#include "xfs_extent_busy.h" +#include "xfs_rtgroup.h" +#include "xfs_rtbitmap.h" +#include "xfs_metafile.h" +#include "xfs_health.h" + +static struct kmem_cache *xfs_rtrefcountbt_cur_cache; + +/* + * Realtime Reference Count btree. + * + * This is a btree used to track the owner(s) of a given extent in the realtime + * device. See the comments in xfs_refcount_btree.c for more information. + * + * This tree is basically the same as the regular refcount btree except that + * it's rooted in an inode. + */ + +static struct xfs_btree_cur * +xfs_rtrefcountbt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_rtrefcountbt_init_cursor(cur->bc_tp, to_rtg(cur->bc_group)); +} + +STATIC int +xfs_rtrefcountbt_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrefcountbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0) / 2; + } + + return cur->bc_mp->m_rtrefc_mnr[level != 0]; +} + +STATIC int +xfs_rtrefcountbt_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrefcountbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0); + } + + return cur->bc_mp->m_rtrefc_mxr[level != 0]; +} + +/* + * Calculate number of records in a realtime refcount btree inode root. + */ +unsigned int +xfs_rtrefcountbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrefcount_root); + + if (leaf) + return blocklen / sizeof(struct xfs_refcount_rec); + return blocklen / (2 * sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrefcountbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork so that + * we can resize the in-memory buffer to match it. After a resize to the + * maximum size this function returns the same value as + * xfs_rtrefcountbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrefcountbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrefc_mxr[level != 0]; + return xfs_rtrefcountbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + +STATIC void +xfs_rtrefcountbt_init_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + key->refc.rc_startblock = rec->refc.rc_startblock; +} + +STATIC void +xfs_rtrefcountbt_init_high_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + __u32 x; + + x = be32_to_cpu(rec->refc.rc_startblock); + x += be32_to_cpu(rec->refc.rc_blockcount) - 1; + key->refc.rc_startblock = cpu_to_be32(x); +} + +STATIC void +xfs_rtrefcountbt_init_rec_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_rec *rec) +{ + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + rec->refc.rc_startblock = cpu_to_be32(start); + rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount); + rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount); +} + +STATIC void +xfs_rtrefcountbt_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ptr->l = 0; +} + +STATIC int64_t +xfs_rtrefcountbt_key_diff( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key) +{ + const struct xfs_refcount_key *kp = &key->refc; + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + return (int64_t)be32_to_cpu(kp->rc_startblock) - start; +} + +STATIC int64_t +xfs_rtrefcountbt_diff_two_keys( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->refc.rc_startblock); + + return (int64_t)be32_to_cpu(k1->refc.rc_startblock) - + be32_to_cpu(k2->refc.rc_startblock); +} + +static xfs_failaddr_t +xfs_rtrefcountbt_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + int level; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + if (!xfs_has_reflink(mp)) + return __this_address; + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + level = be16_to_cpu(block->bb_level); + if (level > mp->m_rtrefc_maxlevels) + return __this_address; + + return xfs_btree_fsblock_verify(bp, mp->m_rtrefc_mxr[level != 0]); +} + +static void +xfs_rtrefcountbt_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_btree_fsblock_verify_crc(bp)) + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + else { + fa = xfs_rtrefcountbt_verify(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + } + + if (bp->b_error) + trace_xfs_btree_corrupt(bp, _RET_IP_); +} + +static void +xfs_rtrefcountbt_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtrefcountbt_verify(bp); + if (fa) { + trace_xfs_btree_corrupt(bp, _RET_IP_); + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + xfs_btree_fsblock_calc_crc(bp); + +} + +const struct xfs_buf_ops xfs_rtrefcountbt_buf_ops = { + .name = "xfs_rtrefcountbt", + .magic = { 0, cpu_to_be32(XFS_RTREFC_CRC_MAGIC) }, + .verify_read = xfs_rtrefcountbt_read_verify, + .verify_write = xfs_rtrefcountbt_write_verify, + .verify_struct = xfs_rtrefcountbt_verify, +}; + +STATIC int +xfs_rtrefcountbt_keys_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2) +{ + return be32_to_cpu(k1->refc.rc_startblock) < + be32_to_cpu(k2->refc.rc_startblock); +} + +STATIC int +xfs_rtrefcountbt_recs_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *r1, + const union xfs_btree_rec *r2) +{ + return be32_to_cpu(r1->refc.rc_startblock) + + be32_to_cpu(r1->refc.rc_blockcount) <= + be32_to_cpu(r2->refc.rc_startblock); +} + +STATIC enum xbtree_key_contig +xfs_rtrefcountbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->refc.rc_startblock); + + return xbtree_key_contig(be32_to_cpu(key1->refc.rc_startblock), + be32_to_cpu(key2->refc.rc_startblock)); +} + +static inline void +xfs_rtrefcountbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrefcount_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrefcountbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrefcount_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrefcountbt_maxrecs(mp, old_size, level); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, broot, old_size, + new_size, old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, ifp->if_broot, old_size, + new_size, new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrefcount_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + +const struct xfs_btree_ops xfs_rtrefcountbt_ops = { + .name = "rtrefcount", + .type = XFS_BTREE_TYPE_INODE, + .geom_flags = XFS_BTGEO_IROOT_RECORDS, + + .rec_len = sizeof(struct xfs_refcount_rec), + .key_len = sizeof(struct xfs_refcount_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_REFC_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrefcbt_2), + .sick_mask = XFS_SICK_RG_REFCNTBT, + + .dup_cursor = xfs_rtrefcountbt_dup_cursor, + .alloc_block = xfs_btree_alloc_metafile_block, + .free_block = xfs_btree_free_metafile_block, + .get_minrecs = xfs_rtrefcountbt_get_minrecs, + .get_maxrecs = xfs_rtrefcountbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrefcountbt_get_dmaxrecs, + .init_key_from_rec = xfs_rtrefcountbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrefcountbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrefcountbt_init_rec_from_cur, + .init_ptr_from_cur = xfs_rtrefcountbt_init_ptr_from_cur, + .key_diff = xfs_rtrefcountbt_key_diff, + .buf_ops = &xfs_rtrefcountbt_buf_ops, + .diff_two_keys = xfs_rtrefcountbt_diff_two_keys, + .keys_inorder = xfs_rtrefcountbt_keys_inorder, + .recs_inorder = xfs_rtrefcountbt_recs_inorder, + .keys_contiguous = xfs_rtrefcountbt_keys_contiguous, + .broot_realloc = xfs_rtrefcountbt_broot_realloc, +}; + +/* Allocate a new rt refcount btree cursor. */ +struct xfs_btree_cur * +xfs_rtrefcountbt_init_cursor( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg) +{ + struct xfs_inode *ip = rtg_refcount(rtg); + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrefcountbt_ops, + mp->m_rtrefc_maxlevels, xfs_rtrefcountbt_cur_cache); + + cur->bc_ino.ip = ip; + cur->bc_refc.nr_ops = 0; + cur->bc_refc.shape_changes = 0; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + cur->bc_nlevels = be16_to_cpu(ip->i_df.if_broot->bb_level) + 1; + cur->bc_ino.forksize = xfs_inode_fork_size(ip, XFS_DATA_FORK); + cur->bc_ino.whichfork = XFS_DATA_FORK; + return cur; +} + +/* + * Install a new rt reverse mapping btree root. Caller is responsible for + * invalidating and freeing the old btree blocks. + */ +void +xfs_rtrefcountbt_commit_staged_btree( + struct xfs_btree_cur *cur, + struct xfs_trans *tp) +{ + struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; + struct xfs_ifork *ifp; + int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; + + ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); + + /* + * Free any resources hanging off the real fork, then shallow-copy the + * staging fork's contents into the real fork to transfer everything + * we just built. + */ + ifp = xfs_ifork_ptr(cur->bc_ino.ip, XFS_DATA_FORK); + xfs_idestroy_fork(ifp); + memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); + + cur->bc_ino.ip->i_projid = cur->bc_group->xg_gno; + xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); + xfs_btree_commit_ifakeroot(cur, tp, XFS_DATA_FORK); +} + +/* Calculate number of records in a realtime refcount btree block. */ +static inline unsigned int +xfs_rtrefcountbt_block_maxrecs( + unsigned int blocklen, + bool leaf) +{ + + if (leaf) + return blocklen / sizeof(struct xfs_refcount_rec); + return blocklen / (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Calculate number of records in an refcount btree block. + */ +unsigned int +xfs_rtrefcountbt_maxrecs( + struct xfs_mount *mp, + unsigned int blocklen, + bool leaf) +{ + blocklen -= XFS_RTREFCOUNT_BLOCK_LEN; + return xfs_rtrefcountbt_block_maxrecs(blocklen, leaf); +} + +/* Compute the max possible height for realtime refcount btrees. */ +unsigned int +xfs_rtrefcountbt_maxlevels_ondisk(void) +{ + unsigned int minrecs[2]; + unsigned int blocklen; + + blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; + + minrecs[0] = xfs_rtrefcountbt_block_maxrecs(blocklen, true) / 2; + minrecs[1] = xfs_rtrefcountbt_block_maxrecs(blocklen, false) / 2; + + /* We need at most one record for every block in an rt group. */ + return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS); +} + +int __init +xfs_rtrefcountbt_init_cur_cache(void) +{ + xfs_rtrefcountbt_cur_cache = kmem_cache_create("xfs_rtrefcountbt_cur", + xfs_btree_cur_sizeof( + xfs_rtrefcountbt_maxlevels_ondisk()), + 0, 0, NULL); + + if (!xfs_rtrefcountbt_cur_cache) + return -ENOMEM; + return 0; +} + +void +xfs_rtrefcountbt_destroy_cur_cache(void) +{ + kmem_cache_destroy(xfs_rtrefcountbt_cur_cache); + xfs_rtrefcountbt_cur_cache = NULL; +} + +/* Compute the maximum height of a realtime refcount btree. */ +void +xfs_rtrefcountbt_compute_maxlevels( + struct xfs_mount *mp) +{ + unsigned int d_maxlevels, r_maxlevels; + + if (!xfs_has_rtreflink(mp)) { + mp->m_rtrefc_maxlevels = 0; + return; + } + + /* + * The realtime refcountbt lives on the data device, which means that + * its maximum height is constrained by the size of the data device and + * the height required to store one refcount record for each rtextent + * in an rt group. + */ + d_maxlevels = xfs_btree_space_to_height(mp->m_rtrefc_mnr, + mp->m_sb.sb_dblocks); + r_maxlevels = xfs_btree_compute_maxlevels(mp->m_rtrefc_mnr, + mp->m_sb.sb_rgextents); + + /* Add one level to handle the inode root level. */ + mp->m_rtrefc_maxlevels = min(d_maxlevels, r_maxlevels) + 1; +} + +/* Calculate the rtrefcount btree size for some records. */ +unsigned long long +xfs_rtrefcountbt_calc_size( + struct xfs_mount *mp, + unsigned long long len) +{ + return xfs_btree_calc_size(mp->m_rtrefc_mnr, len); +} + +/* + * Calculate the maximum refcount btree size. + */ +static unsigned long long +xfs_rtrefcountbt_max_size( + struct xfs_mount *mp, + xfs_rtblock_t rtblocks) +{ + /* Bail out if we're uninitialized, which can happen in mkfs. */ + if (mp->m_rtrefc_mxr[0] == 0) + return 0; + + return xfs_rtrefcountbt_calc_size(mp, rtblocks); +} + +/* + * Figure out how many blocks to reserve and how many are used by this btree. + * We need enough space to hold one record for every rt extent in the rtgroup. + */ +xfs_filblks_t +xfs_rtrefcountbt_calc_reserves( + struct xfs_mount *mp) +{ + if (!xfs_has_rtreflink(mp)) + return 0; + + return xfs_rtrefcountbt_max_size(mp, mp->m_sb.sb_rgextents); +} + +/* + * Convert on-disk form of btree root to in-memory form. + */ +STATIC void +xfs_rtrefcountbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrefcount_root *dblock, + int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + unsigned int rblocklen; + + rblocklen = xfs_rtrefcount_broot_space(mp, dblock); + + xfs_btree_init_block(mp, rblock, &xfs_rtrefcountbt_ops, 0, 0, + ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + tkp = xfs_rtrefcount_key_addr(rblock, 1); + fpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + trp = xfs_rtrefcount_rec_addr(rblock, 1); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reference count btree root in from disk. */ +int +xfs_iformat_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrefcount inodes before adding a realtime + * volume to the filesystem, so we cannot use the rtrefcount predicate + * here. + */ + if (!xfs_has_reflink(ip->i_mount)) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrefc_maxlevels || + xfs_rtrefcount_droot_space_calc(level, numrecs) > dsize) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrefcount_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrefcountbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* + * Convert in-memory form of btree root to on-disk form. + */ +void +xfs_rtrefcountbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + int rblocklen, + struct xfs_rtrefcount_root *dblock, + int dblocklen) +{ + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int maxrecs; + unsigned int numrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTREFC_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_key_addr(rblock, 1); + tkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + fpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_rec_addr(rblock, 1); + trp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reference count btree root out to disk. */ +void +xfs_iflush_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrefcount_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrefcountbt_to_disk(ip->i_mount, ifp->if_broot, + ifp->if_broot_bytes, dfp, + XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} + +/* + * Create a realtime refcount btree inode. + */ +int +xfs_rtrefcountbt_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_block *broot; + + ifp->if_format = XFS_DINODE_FMT_META_BTREE; + ASSERT(ifp->if_broot_bytes == 0); + ASSERT(ifp->if_bytes == 0); + + /* Initialize the empty incore btree root. */ + broot = xfs_broot_realloc(ifp, + xfs_rtrefcount_broot_space_calc(mp, 0, 0)); + if (broot) + xfs_btree_init_block(mp, broot, &xfs_rtrefcountbt_ops, 0, 0, + ip->i_ino); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE | XFS_ILOG_DBROOT); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.h b/fs/xfs/libxfs/xfs_rtrefcount_btree.h new file mode 100644 index 000000000000..a99b7a8aec86 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.h @@ -0,0 +1,189 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#ifndef __XFS_RTREFCOUNT_BTREE_H__ +#define __XFS_RTREFCOUNT_BTREE_H__ + +struct xfs_buf; +struct xfs_btree_cur; +struct xfs_mount; +struct xbtree_ifakeroot; +struct xfs_rtgroup; + +/* refcounts only exist on crc enabled filesystems */ +#define XFS_RTREFCOUNT_BLOCK_LEN XFS_BTREE_LBLOCK_CRC_LEN + +struct xfs_btree_cur *xfs_rtrefcountbt_init_cursor(struct xfs_trans *tp, + struct xfs_rtgroup *rtg); +struct xfs_btree_cur *xfs_rtrefcountbt_stage_cursor(struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xbtree_ifakeroot *ifake); +void xfs_rtrefcountbt_commit_staged_btree(struct xfs_btree_cur *cur, + struct xfs_trans *tp); +unsigned int xfs_rtrefcountbt_maxrecs(struct xfs_mount *mp, + unsigned int blocklen, bool leaf); +void xfs_rtrefcountbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrefcountbt_droot_maxrecs(unsigned int blocklen, bool leaf); + +/* + * Addresses of records, keys, and pointers within an incore rtrefcountbt block. + * + * (note that some of these may appear unused, but they are used in userspace) + */ +static inline struct xfs_refcount_rec * +xfs_rtrefcount_rec_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_refcount_rec *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_refcount_rec)); +} + +static inline struct xfs_refcount_key * +xfs_rtrefcount_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_refcount_key *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_refcount_key)); +} + +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_ptr_addr( + struct xfs_btree_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrefcount_ptr_t *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + maxrecs * sizeof(struct xfs_refcount_key) + + (index - 1) * sizeof(xfs_rtrefcount_ptr_t)); +} + +unsigned int xfs_rtrefcountbt_maxlevels_ondisk(void); +int __init xfs_rtrefcountbt_init_cur_cache(void); +void xfs_rtrefcountbt_destroy_cur_cache(void); + +xfs_filblks_t xfs_rtrefcountbt_calc_reserves(struct xfs_mount *mp); +unsigned long long xfs_rtrefcountbt_calc_size(struct xfs_mount *mp, + unsigned long long len); + +/* Addresses of key, pointers, and records within an ondisk rtrefcount block. */ + +static inline struct xfs_refcount_rec * +xfs_rtrefcount_droot_rec_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_rec)); +} + +static inline struct xfs_refcount_key * +xfs_rtrefcount_droot_key_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_key *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_key)); +} + +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_droot_ptr_addr( + struct xfs_rtrefcount_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrefcount_ptr_t *) + ((char *)(block + 1) + + maxrecs * sizeof(struct xfs_refcount_key) + + (index - 1) * sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrefcount_ptr_addr(bb, index, + xfs_rtrefcountbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrefcount_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTREFCOUNT_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrefcount_broot_space(struct xfs_mount *mp, struct xfs_rtrefcount_root *bb) +{ + return xfs_rtrefcount_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrefcount_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrefcount_root); + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrefcount_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrefcount_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrefcountbt_to_disk(struct xfs_mount *mp, + struct xfs_btree_block *rblock, int rblocklen, + struct xfs_rtrefcount_root *dblock, int dblocklen); +void xfs_iflush_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); + +int xfs_rtrefcountbt_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); + +#endif /* __XFS_RTREFCOUNT_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c new file mode 100644 index 000000000000..e4ec36943cb7 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -0,0 +1,1035 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_alloc.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_metafile.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_trace.h" +#include "xfs_cksum.h" +#include "xfs_error.h" +#include "xfs_extent_busy.h" +#include "xfs_rtgroup.h" +#include "xfs_bmap.h" +#include "xfs_health.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" + +static struct kmem_cache *xfs_rtrmapbt_cur_cache; + +/* + * Realtime Reverse Map btree. + * + * This is a btree used to track the owner(s) of a given extent in the realtime + * device. See the comments in xfs_rmap_btree.c for more information. + * + * This tree is basically the same as the regular rmap btree except that it + * is rooted in an inode and does not live in free space. + */ + +static struct xfs_btree_cur * +xfs_rtrmapbt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_rtrmapbt_init_cursor(cur->bc_tp, to_rtg(cur->bc_group)); +} + +STATIC int +xfs_rtrmapbt_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0) / 2; + } + + return cur->bc_mp->m_rtrmap_mnr[level != 0]; +} + +STATIC int +xfs_rtrmapbt_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0); + } + + return cur->bc_mp->m_rtrmap_mxr[level != 0]; +} + +/* Calculate number of records in the ondisk realtime rmap btree inode root. */ +unsigned int +xfs_rtrmapbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrmap_root); + + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrmapbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork + * so that we can resize the in-memory buffer to match it. After a + * resize to the maximum size this function returns the same value + * as xfs_rtrmapbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrmapbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrmap_mxr[level != 0]; + return xfs_rtrmapbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + +/* + * Convert the ondisk record's offset field into the ondisk key's offset field. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline __be64 ondisk_rec_offset_to_key(const union xfs_btree_rec *rec) +{ + return rec->rmap.rm_offset & ~cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN); +} + +STATIC void +xfs_rtrmapbt_init_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + key->rmap.rm_startblock = rec->rmap.rm_startblock; + key->rmap.rm_owner = rec->rmap.rm_owner; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); +} + +STATIC void +xfs_rtrmapbt_init_high_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + uint64_t off; + int adj; + + adj = be32_to_cpu(rec->rmap.rm_blockcount) - 1; + + key->rmap.rm_startblock = rec->rmap.rm_startblock; + be32_add_cpu(&key->rmap.rm_startblock, adj); + key->rmap.rm_owner = rec->rmap.rm_owner; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); + if (XFS_RMAP_NON_INODE_OWNER(be64_to_cpu(rec->rmap.rm_owner)) || + XFS_RMAP_IS_BMBT_BLOCK(be64_to_cpu(rec->rmap.rm_offset))) + return; + off = be64_to_cpu(key->rmap.rm_offset); + off = (XFS_RMAP_OFF(off) + adj) | (off & ~XFS_RMAP_OFF_MASK); + key->rmap.rm_offset = cpu_to_be64(off); +} + +STATIC void +xfs_rtrmapbt_init_rec_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_rec *rec) +{ + rec->rmap.rm_startblock = cpu_to_be32(cur->bc_rec.r.rm_startblock); + rec->rmap.rm_blockcount = cpu_to_be32(cur->bc_rec.r.rm_blockcount); + rec->rmap.rm_owner = cpu_to_be64(cur->bc_rec.r.rm_owner); + rec->rmap.rm_offset = cpu_to_be64( + xfs_rmap_irec_offset_pack(&cur->bc_rec.r)); +} + +STATIC void +xfs_rtrmapbt_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ptr->l = 0; +} + +/* + * Mask the appropriate parts of the ondisk key field for a key comparison. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline uint64_t offset_keymask(uint64_t offset) +{ + return offset & ~XFS_RMAP_OFF_UNWRITTEN; +} + +STATIC int64_t +xfs_rtrmapbt_key_diff( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key) +{ + struct xfs_rmap_irec *rec = &cur->bc_rec.r; + const struct xfs_rmap_key *kp = &key->rmap; + __u64 x, y; + int64_t d; + + d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock; + if (d) + return d; + + x = be64_to_cpu(kp->rm_owner); + y = rec->rm_owner; + if (x > y) + return 1; + else if (y > x) + return -1; + + x = offset_keymask(be64_to_cpu(kp->rm_offset)); + y = offset_keymask(xfs_rmap_irec_offset_pack(rec)); + if (x > y) + return 1; + else if (y > x) + return -1; + return 0; +} + +STATIC int64_t +xfs_rtrmapbt_diff_two_keys( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) +{ + const struct xfs_rmap_key *kp1 = &k1->rmap; + const struct xfs_rmap_key *kp2 = &k2->rmap; + int64_t d; + __u64 x, y; + + /* Doesn't make sense to mask off the physical space part */ + ASSERT(!mask || mask->rmap.rm_startblock); + + d = (int64_t)be32_to_cpu(kp1->rm_startblock) - + be32_to_cpu(kp2->rm_startblock); + if (d) + return d; + + if (!mask || mask->rmap.rm_owner) { + x = be64_to_cpu(kp1->rm_owner); + y = be64_to_cpu(kp2->rm_owner); + if (x > y) + return 1; + else if (y > x) + return -1; + } + + if (!mask || mask->rmap.rm_offset) { + /* Doesn't make sense to allow offset but not owner */ + ASSERT(!mask || mask->rmap.rm_owner); + + x = offset_keymask(be64_to_cpu(kp1->rm_offset)); + y = offset_keymask(be64_to_cpu(kp2->rm_offset)); + if (x > y) + return 1; + else if (y > x) + return -1; + } + + return 0; +} + +static xfs_failaddr_t +xfs_rtrmapbt_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + int level; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + if (!xfs_has_rmapbt(mp)) + return __this_address; + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + level = be16_to_cpu(block->bb_level); + if (level > mp->m_rtrmap_maxlevels) + return __this_address; + + return xfs_btree_fsblock_verify(bp, mp->m_rtrmap_mxr[level != 0]); +} + +static void +xfs_rtrmapbt_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_btree_fsblock_verify_crc(bp)) + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + else { + fa = xfs_rtrmapbt_verify(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + } + + if (bp->b_error) + trace_xfs_btree_corrupt(bp, _RET_IP_); +} + +static void +xfs_rtrmapbt_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtrmapbt_verify(bp); + if (fa) { + trace_xfs_btree_corrupt(bp, _RET_IP_); + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + xfs_btree_fsblock_calc_crc(bp); + +} + +const struct xfs_buf_ops xfs_rtrmapbt_buf_ops = { + .name = "xfs_rtrmapbt", + .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, + .verify_read = xfs_rtrmapbt_read_verify, + .verify_write = xfs_rtrmapbt_write_verify, + .verify_struct = xfs_rtrmapbt_verify, +}; + +STATIC int +xfs_rtrmapbt_keys_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2) +{ + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; + + x = be32_to_cpu(k1->rmap.rm_startblock); + y = be32_to_cpu(k2->rmap.rm_startblock); + if (x < y) + return 1; + else if (x > y) + return 0; + a = be64_to_cpu(k1->rmap.rm_owner); + b = be64_to_cpu(k2->rmap.rm_owner); + if (a < b) + return 1; + else if (a > b) + return 0; + a = offset_keymask(be64_to_cpu(k1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(k2->rmap.rm_offset)); + if (a <= b) + return 1; + return 0; +} + +STATIC int +xfs_rtrmapbt_recs_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *r1, + const union xfs_btree_rec *r2) +{ + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; + + x = be32_to_cpu(r1->rmap.rm_startblock); + y = be32_to_cpu(r2->rmap.rm_startblock); + if (x < y) + return 1; + else if (x > y) + return 0; + a = be64_to_cpu(r1->rmap.rm_owner); + b = be64_to_cpu(r2->rmap.rm_owner); + if (a < b) + return 1; + else if (a > b) + return 0; + a = offset_keymask(be64_to_cpu(r1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(r2->rmap.rm_offset)); + if (a <= b) + return 1; + return 0; +} + +STATIC enum xbtree_key_contig +xfs_rtrmapbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->rmap.rm_startblock); + + /* + * We only support checking contiguity of the physical space component. + * If any callers ever need more specificity than that, they'll have to + * implement it here. + */ + ASSERT(!mask || (!mask->rmap.rm_owner && !mask->rmap.rm_offset)); + + return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock), + be32_to_cpu(key2->rmap.rm_startblock)); +} + +static inline void +xfs_rtrmapbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrmap_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrmapbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrmap_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrmapbt_maxrecs(mp, old_size, level == 0); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, broot, old_size, new_size, + old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, + new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrmap_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + +const struct xfs_btree_ops xfs_rtrmapbt_ops = { + .name = "rtrmap", + .type = XFS_BTREE_TYPE_INODE, + .geom_flags = XFS_BTGEO_OVERLAPPING | + XFS_BTGEO_IROOT_RECORDS, + + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ + .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_2), + .sick_mask = XFS_SICK_RG_RMAPBT, + + .dup_cursor = xfs_rtrmapbt_dup_cursor, + .alloc_block = xfs_btree_alloc_metafile_block, + .free_block = xfs_btree_free_metafile_block, + .get_minrecs = xfs_rtrmapbt_get_minrecs, + .get_maxrecs = xfs_rtrmapbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrmapbt_get_dmaxrecs, + .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, + .init_ptr_from_cur = xfs_rtrmapbt_init_ptr_from_cur, + .key_diff = xfs_rtrmapbt_key_diff, + .buf_ops = &xfs_rtrmapbt_buf_ops, + .diff_two_keys = xfs_rtrmapbt_diff_two_keys, + .keys_inorder = xfs_rtrmapbt_keys_inorder, + .recs_inorder = xfs_rtrmapbt_recs_inorder, + .keys_contiguous = xfs_rtrmapbt_keys_contiguous, + .broot_realloc = xfs_rtrmapbt_broot_realloc, +}; + +/* Allocate a new rt rmap btree cursor. */ +struct xfs_btree_cur * +xfs_rtrmapbt_init_cursor( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg) +{ + struct xfs_inode *ip = rtg_rmap(rtg); + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_ops, + mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + + cur->bc_ino.ip = ip; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + cur->bc_ino.whichfork = XFS_DATA_FORK; + cur->bc_nlevels = be16_to_cpu(ip->i_df.if_broot->bb_level) + 1; + cur->bc_ino.forksize = xfs_inode_fork_size(ip, XFS_DATA_FORK); + + return cur; +} + +#ifdef CONFIG_XFS_BTREE_IN_MEM +/* + * Validate an in-memory realtime rmap btree block. Callers are allowed to + * generate an in-memory btree even if the ondisk feature is not enabled. + */ +static xfs_failaddr_t +xfs_rtrmapbt_mem_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + unsigned int level; + unsigned int maxrecs; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + + level = be16_to_cpu(block->bb_level); + if (xfs_has_rmapbt(mp)) { + if (level >= mp->m_rtrmap_maxlevels) + return __this_address; + } else { + if (level >= xfs_rtrmapbt_maxlevels_ondisk()) + return __this_address; + } + + maxrecs = xfs_rtrmapbt_maxrecs(mp, XFBNO_BLOCKSIZE, level == 0); + return xfs_btree_memblock_verify(bp, maxrecs); +} + +static void +xfs_rtrmapbt_mem_rw_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa = xfs_rtrmapbt_mem_verify(bp); + + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); +} + +/* skip crc checks on in-memory btrees to save time */ +static const struct xfs_buf_ops xfs_rtrmapbt_mem_buf_ops = { + .name = "xfs_rtrmapbt_mem", + .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, + .verify_read = xfs_rtrmapbt_mem_rw_verify, + .verify_write = xfs_rtrmapbt_mem_rw_verify, + .verify_struct = xfs_rtrmapbt_mem_verify, +}; + +const struct xfs_btree_ops xfs_rtrmapbt_mem_ops = { + .type = XFS_BTREE_TYPE_MEM, + .geom_flags = XFS_BTGEO_OVERLAPPING, + + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ + .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_mem_2), + + .dup_cursor = xfbtree_dup_cursor, + .set_root = xfbtree_set_root, + .alloc_block = xfbtree_alloc_block, + .free_block = xfbtree_free_block, + .get_minrecs = xfbtree_get_minrecs, + .get_maxrecs = xfbtree_get_maxrecs, + .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, + .init_ptr_from_cur = xfbtree_init_ptr_from_cur, + .key_diff = xfs_rtrmapbt_key_diff, + .buf_ops = &xfs_rtrmapbt_mem_buf_ops, + .diff_two_keys = xfs_rtrmapbt_diff_two_keys, + .keys_inorder = xfs_rtrmapbt_keys_inorder, + .recs_inorder = xfs_rtrmapbt_recs_inorder, + .keys_contiguous = xfs_rtrmapbt_keys_contiguous, +}; + +/* Create a cursor for an in-memory btree. */ +struct xfs_btree_cur * +xfs_rtrmapbt_mem_cursor( + struct xfs_rtgroup *rtg, + struct xfs_trans *tp, + struct xfbtree *xfbt) +{ + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_mem_ops, + mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + cur->bc_mem.xfbtree = xfbt; + cur->bc_nlevels = xfbt->nlevels; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + return cur; +} + +/* Create an in-memory realtime rmap btree. */ +int +xfs_rtrmapbt_mem_init( + struct xfs_mount *mp, + struct xfbtree *xfbt, + struct xfs_buftarg *btp, + xfs_rgnumber_t rgno) +{ + xfbt->owner = rgno; + return xfbtree_init(mp, xfbt, btp, &xfs_rtrmapbt_mem_ops); +} +#endif /* CONFIG_XFS_BTREE_IN_MEM */ + +/* + * Install a new rt reverse mapping btree root. Caller is responsible for + * invalidating and freeing the old btree blocks. + */ +void +xfs_rtrmapbt_commit_staged_btree( + struct xfs_btree_cur *cur, + struct xfs_trans *tp) +{ + struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; + struct xfs_ifork *ifp; + int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; + + ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); + + /* + * Free any resources hanging off the real fork, then shallow-copy the + * staging fork's contents into the real fork to transfer everything + * we just built. + */ + ifp = xfs_ifork_ptr(cur->bc_ino.ip, XFS_DATA_FORK); + xfs_idestroy_fork(ifp); + memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); + + cur->bc_ino.ip->i_projid = cur->bc_group->xg_gno; + xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); + xfs_btree_commit_ifakeroot(cur, tp, XFS_DATA_FORK); +} + +/* Calculate number of records in a rt reverse mapping btree block. */ +static inline unsigned int +xfs_rtrmapbt_block_maxrecs( + unsigned int blocklen, + bool leaf) +{ + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / + (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Calculate number of records in an rt reverse mapping btree block. + */ +unsigned int +xfs_rtrmapbt_maxrecs( + struct xfs_mount *mp, + unsigned int blocklen, + bool leaf) +{ + blocklen -= XFS_RTRMAP_BLOCK_LEN; + return xfs_rtrmapbt_block_maxrecs(blocklen, leaf); +} + +/* Compute the max possible height for realtime reverse mapping btrees. */ +unsigned int +xfs_rtrmapbt_maxlevels_ondisk(void) +{ + unsigned long long max_dblocks; + unsigned int minrecs[2]; + unsigned int blocklen; + + blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; + + minrecs[0] = xfs_rtrmapbt_block_maxrecs(blocklen, true) / 2; + minrecs[1] = xfs_rtrmapbt_block_maxrecs(blocklen, false) / 2; + + /* + * Compute the asymptotic maxlevels for an rtrmapbt on any rtreflink fs. + * + * On a reflink filesystem, each block in an rtgroup can have up to + * 2^32 (per the refcount record format) owners, which means that + * theoretically we could face up to 2^64 rmap records. However, we're + * likely to run out of blocks in the data device long before that + * happens, which means that we must compute the max height based on + * what the btree will look like if it consumes almost all the blocks + * in the data device due to maximal sharing factor. + */ + max_dblocks = -1U; /* max ag count */ + max_dblocks *= XFS_MAX_CRC_AG_BLOCKS; + return xfs_btree_space_to_height(minrecs, max_dblocks); +} + +int __init +xfs_rtrmapbt_init_cur_cache(void) +{ + xfs_rtrmapbt_cur_cache = kmem_cache_create("xfs_rtrmapbt_cur", + xfs_btree_cur_sizeof(xfs_rtrmapbt_maxlevels_ondisk()), + 0, 0, NULL); + + if (!xfs_rtrmapbt_cur_cache) + return -ENOMEM; + return 0; +} + +void +xfs_rtrmapbt_destroy_cur_cache(void) +{ + kmem_cache_destroy(xfs_rtrmapbt_cur_cache); + xfs_rtrmapbt_cur_cache = NULL; +} + +/* Compute the maximum height of an rt reverse mapping btree. */ +void +xfs_rtrmapbt_compute_maxlevels( + struct xfs_mount *mp) +{ + unsigned int d_maxlevels, r_maxlevels; + + if (!xfs_has_rtrmapbt(mp)) { + mp->m_rtrmap_maxlevels = 0; + return; + } + + /* + * The realtime rmapbt lives on the data device, which means that its + * maximum height is constrained by the size of the data device and + * the height required to store one rmap record for each block in an + * rt group. + * + * On a reflink filesystem, each rt block can have up to 2^32 (per the + * refcount record format) owners, which means that theoretically we + * could face up to 2^64 rmap records. This makes the computation of + * maxlevels based on record count meaningless, so we only consider the + * size of the data device. + */ + d_maxlevels = xfs_btree_space_to_height(mp->m_rtrmap_mnr, + mp->m_sb.sb_dblocks); + if (xfs_has_rtreflink(mp)) { + mp->m_rtrmap_maxlevels = d_maxlevels + 1; + return; + } + + r_maxlevels = xfs_btree_compute_maxlevels(mp->m_rtrmap_mnr, + mp->m_groups[XG_TYPE_RTG].blocks); + + /* Add one level to handle the inode root level. */ + mp->m_rtrmap_maxlevels = min(d_maxlevels, r_maxlevels) + 1; +} + +/* Calculate the rtrmap btree size for some records. */ +unsigned long long +xfs_rtrmapbt_calc_size( + struct xfs_mount *mp, + unsigned long long len) +{ + return xfs_btree_calc_size(mp->m_rtrmap_mnr, len); +} + +/* + * Calculate the maximum rmap btree size. + */ +static unsigned long long +xfs_rtrmapbt_max_size( + struct xfs_mount *mp, + xfs_rtblock_t rtblocks) +{ + /* Bail out if we're uninitialized, which can happen in mkfs. */ + if (mp->m_rtrmap_mxr[0] == 0) + return 0; + + return xfs_rtrmapbt_calc_size(mp, rtblocks); +} + +/* + * Figure out how many blocks to reserve and how many are used by this btree. + */ +xfs_filblks_t +xfs_rtrmapbt_calc_reserves( + struct xfs_mount *mp) +{ + uint32_t blocks = mp->m_groups[XG_TYPE_RTG].blocks; + + if (!xfs_has_rtrmapbt(mp)) + return 0; + + /* Reserve 1% of the rtgroup or enough for 1 block per record. */ + return max_t(xfs_filblks_t, blocks / 100, + xfs_rtrmapbt_max_size(mp, blocks)); +} + +/* Convert on-disk form of btree root to in-memory form. */ +STATIC void +xfs_rtrmapbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int rblocklen = xfs_rtrmap_broot_space(mp, dblock); + unsigned int numrecs; + unsigned int maxrecs; + + xfs_btree_init_block(mp, rblock, &xfs_rtrmapbt_ops, 0, 0, ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + numrecs = be16_to_cpu(dblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_droot_key_addr(dblock, 1); + tkp = xfs_rtrmap_key_addr(rblock, 1); + fpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_droot_rec_addr(dblock, 1); + trp = xfs_rtrmap_rec_addr(rblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reverse mapping btree root in from disk. */ +int +xfs_iformat_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrmap inodes before adding a realtime volume + * to the filesystem, so we cannot use the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(ip->i_mount)) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrmap_maxlevels || + xfs_rtrmap_droot_space_calc(level, numrecs) > dsize) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrmap_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrmapbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* Convert in-memory form of btree root to on-disk form. */ +void +xfs_rtrmapbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + unsigned int rblocklen, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen) +{ + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTRMAP_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + numrecs = be16_to_cpu(rblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_key_addr(rblock, 1); + tkp = xfs_rtrmap_droot_key_addr(dblock, 1); + fpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_rec_addr(rblock, 1); + trp = xfs_rtrmap_droot_rec_addr(dblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reverse mapping btree root out to disk. */ +void +xfs_iflush_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrmap_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrmapbt_to_disk(ip->i_mount, ifp->if_broot, ifp->if_broot_bytes, + dfp, XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} + +/* + * Create a realtime rmap btree inode. + */ +int +xfs_rtrmapbt_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_block *broot; + + ifp->if_format = XFS_DINODE_FMT_META_BTREE; + ASSERT(ifp->if_broot_bytes == 0); + ASSERT(ifp->if_bytes == 0); + + /* Initialize the empty incore btree root. */ + broot = xfs_broot_realloc(ifp, xfs_rtrmap_broot_space_calc(mp, 0, 0)); + if (broot) + xfs_btree_init_block(mp, broot, &xfs_rtrmapbt_ops, 0, 0, + ip->i_ino); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE | XFS_ILOG_DBROOT); + + return 0; +} + +/* + * Initialize an rmap for a realtime superblock using the potentially updated + * rt geometry in the provided @mp. + */ +int +xfs_rtrmapbt_init_rtsb( + struct xfs_mount *mp, + struct xfs_rtgroup *rtg, + struct xfs_trans *tp) +{ + struct xfs_rmap_irec rmap = { + .rm_blockcount = mp->m_sb.sb_rextsize, + .rm_owner = XFS_RMAP_OWN_FS, + }; + struct xfs_btree_cur *cur; + int error; + + ASSERT(xfs_has_rtsb(mp)); + ASSERT(rtg_rgno(rtg) == 0); + + cur = xfs_rtrmapbt_init_cursor(tp, rtg); + error = xfs_rmap_map_raw(cur, &rmap); + xfs_btree_del_cursor(cur, error); + return error; +} diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.h b/fs/xfs/libxfs/xfs_rtrmap_btree.h new file mode 100644 index 000000000000..9d0915089891 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.h @@ -0,0 +1,210 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#ifndef __XFS_RTRMAP_BTREE_H__ +#define __XFS_RTRMAP_BTREE_H__ + +struct xfs_buf; +struct xfs_btree_cur; +struct xfs_mount; +struct xbtree_ifakeroot; +struct xfs_rtgroup; +struct xfbtree; + +/* rmaps only exist on crc enabled filesystems */ +#define XFS_RTRMAP_BLOCK_LEN XFS_BTREE_LBLOCK_CRC_LEN + +struct xfs_btree_cur *xfs_rtrmapbt_init_cursor(struct xfs_trans *tp, + struct xfs_rtgroup *rtg); +struct xfs_btree_cur *xfs_rtrmapbt_stage_cursor(struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xbtree_ifakeroot *ifake); +void xfs_rtrmapbt_commit_staged_btree(struct xfs_btree_cur *cur, + struct xfs_trans *tp); +unsigned int xfs_rtrmapbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, + bool leaf); +void xfs_rtrmapbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrmapbt_droot_maxrecs(unsigned int blocklen, bool leaf); + +/* + * Addresses of records, keys, and pointers within an incore rtrmapbt block. + * + * (note that some of these may appear unused, but they are used in userspace) + */ +static inline struct xfs_rmap_rec * +xfs_rtrmap_rec_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_rec *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_rmap_rec)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_high_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + sizeof(struct xfs_rmap_key) + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_ptr_addr( + struct xfs_btree_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrmap_ptr_t *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + maxrecs * 2 * sizeof(struct xfs_rmap_key) + + (index - 1) * sizeof(xfs_rtrmap_ptr_t)); +} + +unsigned int xfs_rtrmapbt_maxlevels_ondisk(void); + +int __init xfs_rtrmapbt_init_cur_cache(void); +void xfs_rtrmapbt_destroy_cur_cache(void); + +xfs_filblks_t xfs_rtrmapbt_calc_reserves(struct xfs_mount *mp); + +/* Addresses of key, pointers, and records within an ondisk rtrmapbt block. */ + +static inline struct xfs_rmap_rec * +xfs_rtrmap_droot_rec_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_rmap_rec)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_droot_key_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)(block + 1) + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_droot_ptr_addr( + struct xfs_rtrmap_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrmap_ptr_t *) + ((char *)(block + 1) + + maxrecs * 2 * sizeof(struct xfs_rmap_key) + + (index - 1) * sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrmap_ptr_addr(bb, index, + xfs_rtrmapbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrmap_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTRMAP_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrmap_broot_space(struct xfs_mount *mp, struct xfs_rtrmap_root *bb) +{ + return xfs_rtrmap_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrmap_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrmap_root); + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrmap_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrmap_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrmapbt_to_disk(struct xfs_mount *mp, struct xfs_btree_block *rblock, + unsigned int rblocklen, struct xfs_rtrmap_root *dblock, + unsigned int dblocklen); +void xfs_iflush_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); + +int xfs_rtrmapbt_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); +int xfs_rtrmapbt_init_rtsb(struct xfs_mount *mp, struct xfs_rtgroup *rtg, + struct xfs_trans *tp); + +unsigned long long xfs_rtrmapbt_calc_size(struct xfs_mount *mp, + unsigned long long len); + +struct xfs_btree_cur *xfs_rtrmapbt_mem_cursor(struct xfs_rtgroup *rtg, + struct xfs_trans *tp, struct xfbtree *xfbtree); +int xfs_rtrmapbt_mem_init(struct xfs_mount *mp, struct xfbtree *xfbtree, + struct xfs_buftarg *btp, xfs_rgnumber_t rgno); + +#endif /* __XFS_RTRMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 3b5623611eba..3dc5f5dba162 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -28,6 +28,8 @@ #include "xfs_rtbitmap.h" #include "xfs_exchrange.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* * Physical superblock buffer manipulations. Shared with libxfs in userspace. @@ -1215,11 +1217,23 @@ xfs_sb_mount_common( mp->m_rmap_mnr[0] = mp->m_rmap_mxr[0] / 2; mp->m_rmap_mnr[1] = mp->m_rmap_mxr[1] / 2; + mp->m_rtrmap_mxr[0] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, true); + mp->m_rtrmap_mxr[1] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, false); + mp->m_rtrmap_mnr[0] = mp->m_rtrmap_mxr[0] / 2; + mp->m_rtrmap_mnr[1] = mp->m_rtrmap_mxr[1] / 2; + mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_refc_mnr[0] = mp->m_refc_mxr[0] / 2; mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2; + mp->m_rtrefc_mxr[0] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, + true); + mp->m_rtrefc_mxr[1] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, + false); + mp->m_rtrefc_mnr[0] = mp->m_rtrefc_mxr[0] / 2; + mp->m_rtrefc_mnr[1] = mp->m_rtrefc_mxr[1] / 2; + mp->m_bsize = XFS_FSB_TO_BB(mp, 1); mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp); diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index e7efdb9ceaf3..b1e0d9bc1f7d 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -42,6 +42,8 @@ extern const struct xfs_buf_ops xfs_rtbitmap_buf_ops; extern const struct xfs_buf_ops xfs_rtsummary_buf_ops; extern const struct xfs_buf_ops xfs_rtbuf_ops; extern const struct xfs_buf_ops xfs_rtsb_buf_ops; +extern const struct xfs_buf_ops xfs_rtrefcountbt_buf_ops; +extern const struct xfs_buf_ops xfs_rtrmapbt_buf_ops; extern const struct xfs_buf_ops xfs_sb_buf_ops; extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops; extern const struct xfs_buf_ops xfs_symlink_buf_ops; @@ -55,6 +57,9 @@ extern const struct xfs_btree_ops xfs_bmbt_ops; extern const struct xfs_btree_ops xfs_refcountbt_ops; extern const struct xfs_btree_ops xfs_rmapbt_ops; extern const struct xfs_btree_ops xfs_rmapbt_mem_ops; +extern const struct xfs_btree_ops xfs_rtrmapbt_ops; +extern const struct xfs_btree_ops xfs_rtrmapbt_mem_ops; +extern const struct xfs_btree_ops xfs_rtrefcountbt_ops; static inline bool xfs_btree_is_bno(const struct xfs_btree_ops *ops) { @@ -96,10 +101,26 @@ static inline bool xfs_btree_is_mem_rmap(const struct xfs_btree_ops *ops) { return ops == &xfs_rmapbt_mem_ops; } + +static inline bool xfs_btree_is_mem_rtrmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrmapbt_mem_ops; +} #else # define xfs_btree_is_mem_rmap(...) (false) +# define xfs_btree_is_mem_rtrmap(...) (false) #endif +static inline bool xfs_btree_is_rtrmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrmapbt_ops; +} + +static inline bool xfs_btree_is_rtrefcount(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrefcountbt_ops; +} + /* log size calculation functions */ int xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes); int xfs_log_calc_minimum_size(struct xfs_mount *); diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index bab402340b5d..13d00c7166e1 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -92,6 +92,14 @@ xfs_refcountbt_block_count( return num_ops * (2 * mp->m_refc_maxlevels - 1); } +static unsigned int +xfs_rtrefcountbt_block_count( + struct xfs_mount *mp, + unsigned int num_ops) +{ + return num_ops * (2 * mp->m_rtrefc_maxlevels - 1); +} + /* * Logging inodes is really tricksy. They are logged in memory format, * which means that what we write into the log doesn't directly translate into @@ -213,7 +221,9 @@ xfs_calc_inode_chunk_res( * Per-extent log reservation for the btree changes involved in freeing or * allocating a realtime extent. We have to be able to log as many rtbitmap * blocks as needed to mark inuse XFS_BMBT_MAX_EXTLEN blocks' worth of realtime - * extents, as well as the realtime summary block. + * extents, as well as the realtime summary block (t1). Realtime rmap btree + * operations happen in a second transaction, so factor in a couple of rtrmapbt + * splits (t2). */ static unsigned int xfs_rtalloc_block_count( @@ -222,10 +232,16 @@ xfs_rtalloc_block_count( { unsigned int rtbmp_blocks; xfs_rtxlen_t rtxlen; + unsigned int t1, t2 = 0; rtxlen = xfs_extlen_to_rtxlen(mp, XFS_MAX_BMBT_EXTLEN); rtbmp_blocks = xfs_rtbitmap_blockcount_len(mp, rtxlen); - return (rtbmp_blocks + 1) * num_ops; + t1 = (rtbmp_blocks + 1) * num_ops; + + if (xfs_has_rmapbt(mp)) + t2 = num_ops * (2 * mp->m_rtrmap_maxlevels - 1); + + return max(t1, t2); } /* @@ -251,10 +267,13 @@ xfs_rtalloc_block_count( * Compute the log reservation required to handle the refcount update * transaction. Refcount updates are always done via deferred log items. * - * This is calculated as: + * This is calculated as the max of: * Data device refcount updates (t1): * the agfs of the ags containing the blocks: nr_ops * sector size * the refcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size + * Realtime refcount updates (t2); + * the rt refcount inode + * the rtrefcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size */ static unsigned int xfs_calc_refcountbt_reservation( @@ -262,12 +281,20 @@ xfs_calc_refcountbt_reservation( unsigned int nr_ops) { unsigned int blksz = XFS_FSB_TO_B(mp, 1); + unsigned int t1, t2 = 0; if (!xfs_has_reflink(mp)) return 0; - return xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz); + t1 = xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz); + + if (xfs_has_realtime(mp)) + t2 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(xfs_rtrefcountbt_block_count(mp, nr_ops), + blksz); + + return max(t1, t2); } /* diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h index 1155ff2d37e2..d89b570aafcc 100644 --- a/fs/xfs/libxfs/xfs_trans_space.h +++ b/fs/xfs/libxfs/xfs_trans_space.h @@ -14,6 +14,19 @@ #define XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp) \ (((mp)->m_bmap_dmxr[0]) - ((mp)->m_bmap_dmnr[0])) +/* Worst case number of realtime rmaps that can be held in a block. */ +#define XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp) \ + (((mp)->m_rtrmap_mxr[0]) - ((mp)->m_rtrmap_mnr[0])) + +/* Adding one realtime rmap could split every level to the top of the tree. */ +#define XFS_RTRMAPADD_SPACE_RES(mp) ((mp)->m_rtrmap_maxlevels) + +/* Blocks we might need to add "b" realtime rmaps to a tree. */ +#define XFS_NRTRMAPADD_SPACE_RES(mp, b) \ + ((((b) + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp) - 1) / \ + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) * \ + XFS_RTRMAPADD_SPACE_RES(mp)) + /* Worst case number of rmaps that can be held in a block. */ #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) \ (((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0])) diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index bf33c2b1e43e..ca2401c1facd 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -202,6 +202,13 @@ enum xfs_ag_resv_type { * altering fdblocks. If you think you need this you're wrong. */ XFS_AG_RESV_IGNORE, + + /* + * This allocation activity is being done on behalf of a metadata file. + * These files maintain their own permanent space reservations and are + * required to adjust fdblocks using the xfs_metafile_resv_* helpers. + */ + XFS_AG_RESV_METAFILE, }; /* Results of scanning a btree keyspace to check occupancy. */ diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index b45d2b32051a..cd6f0223879f 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -647,7 +647,7 @@ xrep_agfl_fill( xfs_agblock_t agbno = start; int error; - trace_xrep_agfl_insert(sc->sa.pag, agbno, len); + trace_xrep_agfl_insert(pag_group(sc->sa.pag), agbno, len); while (agbno < start + len && af->fl_off < af->flcount) af->agfl_bno[af->fl_off++] = cpu_to_be32(agbno++); diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c index 0433363a90b6..bed6a09aa791 100644 --- a/fs/xfs/scrub/alloc_repair.c +++ b/fs/xfs/scrub/alloc_repair.c @@ -542,8 +542,9 @@ xrep_abt_dispose_one( /* Add a deferred rmap for each extent we used. */ if (resv->used > 0) - xfs_rmap_alloc_extent(sc->tp, pag_agno(pag), resv->agbno, - resv->used, XFS_RMAP_OWN_AG); + xfs_rmap_alloc_extent(sc->tp, false, + xfs_agbno_to_fsb(pag, resv->agbno), resv->used, + XFS_RMAP_OWN_AG); /* * For each reserved btree block we didn't use, add it to the free diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 7e00312225ed..66da7d4d56ba 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -21,6 +21,8 @@ #include "xfs_rmap_btree.h" #include "xfs_rtgroup.h" #include "xfs_health.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrmap_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -143,15 +145,22 @@ static inline bool xchk_bmap_get_rmap( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec, - xfs_agblock_t agbno, + xfs_agblock_t bno, uint64_t owner, struct xfs_rmap_irec *rmap) { + struct xfs_btree_cur **curp = &info->sc->sa.rmap_cur; xfs_fileoff_t offset; unsigned int rflags = 0; int has_rmap; int error; + if (xfs_ifork_is_realtime(info->sc->ip, info->whichfork)) + curp = &info->sc->sr.rmap_cur; + + if (*curp == NULL) + return false; + if (info->whichfork == XFS_ATTR_FORK) rflags |= XFS_RMAP_ATTR_FORK; if (irec->br_state == XFS_EXT_UNWRITTEN) @@ -172,13 +181,13 @@ xchk_bmap_get_rmap( * range rmap lookup to make sure we get the correct owner/offset. */ if (info->is_shared) { - error = xfs_rmap_lookup_le_range(info->sc->sa.rmap_cur, agbno, - owner, offset, rflags, rmap, &has_rmap); + error = xfs_rmap_lookup_le_range(*curp, bno, owner, offset, + rflags, rmap, &has_rmap); } else { - error = xfs_rmap_lookup_le(info->sc->sa.rmap_cur, agbno, - owner, offset, rflags, rmap, &has_rmap); + error = xfs_rmap_lookup_le(*curp, bno, owner, offset, + rflags, rmap, &has_rmap); } - if (!xchk_should_check_xref(info->sc, &error, &info->sc->sa.rmap_cur)) + if (!xchk_should_check_xref(info->sc, &error, curp)) return false; if (!has_rmap) @@ -192,29 +201,29 @@ STATIC void xchk_bmap_xref_rmap( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec, - xfs_agblock_t agbno) + xfs_agblock_t bno) { struct xfs_rmap_irec rmap; unsigned long long rmap_end; uint64_t owner = info->sc->ip->i_ino; - if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm)) + if (xchk_skip_xref(info->sc->sm)) return; /* Find the rmap record for this irec. */ - if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap)) + if (!xchk_bmap_get_rmap(info, irec, bno, owner, &rmap)) return; /* * The rmap must be an exact match for this incore file mapping record, * which may have arisen from multiple ondisk records. */ - if (rmap.rm_startblock != agbno) + if (rmap.rm_startblock != bno) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount; - if (rmap_end != agbno + irec->br_blockcount) + if (rmap_end != bno + irec->br_blockcount) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -259,7 +268,7 @@ STATIC void xchk_bmap_xref_rmap_cow( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec, - xfs_agblock_t agbno) + xfs_agblock_t bno) { struct xfs_rmap_irec rmap; unsigned long long rmap_end; @@ -269,7 +278,7 @@ xchk_bmap_xref_rmap_cow( return; /* Find the rmap record for this irec. */ - if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap)) + if (!xchk_bmap_get_rmap(info, irec, bno, owner, &rmap)) return; /* @@ -277,12 +286,12 @@ xchk_bmap_xref_rmap_cow( * can start before and end after the physical space allocated to this * mapping. There are no offsets to check. */ - if (rmap.rm_startblock > agbno) + if (rmap.rm_startblock > bno) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount; - if (rmap_end < agbno + irec->br_blockcount) + if (rmap_end < bno + irec->br_blockcount) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -315,6 +324,8 @@ xchk_bmap_rt_iextent_xref( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec) { + struct xfs_owner_info oinfo; + xfs_rgblock_t rgbno; int error; error = xchk_rtgroup_init_existing(info->sc, @@ -324,10 +335,46 @@ xchk_bmap_rt_iextent_xref( irec->br_startoff, &error)) return; - xchk_rtgroup_lock(&info->sc->sr, XCHK_RTGLOCK_ALL); + error = xchk_rtgroup_lock(info->sc, &info->sc->sr, XCHK_RTGLOCK_ALL); + if (!xchk_fblock_process_error(info->sc, info->whichfork, + irec->br_startoff, &error)) + goto out_free; + xchk_xref_is_used_rt_space(info->sc, irec->br_startblock, irec->br_blockcount); + if (!xfs_has_rtrmapbt(info->sc->mp)) + goto out_cur; + + rgbno = xfs_rtb_to_rgbno(info->sc->mp, irec->br_startblock); + + switch (info->whichfork) { + case XFS_DATA_FORK: + xchk_bmap_xref_rmap(info, irec, rgbno); + if (!xfs_is_reflink_inode(info->sc->ip)) { + xfs_rmap_ino_owner(&oinfo, info->sc->ip->i_ino, + info->whichfork, irec->br_startoff); + xchk_xref_is_only_rt_owned_by(info->sc, rgbno, + irec->br_blockcount, &oinfo); + xchk_xref_is_not_rt_shared(info->sc, rgbno, + irec->br_blockcount); + } + xchk_xref_is_not_rt_cow_staging(info->sc, rgbno, + irec->br_blockcount); + break; + case XFS_COW_FORK: + xchk_bmap_xref_rmap_cow(info, irec, rgbno); + xchk_xref_is_only_rt_owned_by(info->sc, rgbno, + irec->br_blockcount, &XFS_RMAP_OINFO_COW); + xchk_xref_is_rt_cow_staging(info->sc, rgbno, + irec->br_blockcount); + xchk_xref_is_not_rt_shared(info->sc, rgbno, + irec->br_blockcount); + break; + } +out_cur: + xchk_rtgroup_btcur_free(&info->sc->sr); +out_free: xchk_rtgroup_free(info->sc, &info->sc->sr); } @@ -614,8 +661,7 @@ xchk_bmap_check_rmap( xchk_fblock_set_corrupt(sc, sbcri->whichfork, check_rec.rm_offset); if (irec.br_startblock != - xfs_agbno_to_fsb(to_perag(cur->bc_group), - check_rec.rm_startblock)) + xfs_gbno_to_fsb(cur->bc_group, check_rec.rm_startblock)) xchk_fblock_set_corrupt(sc, sbcri->whichfork, check_rec.rm_offset); if (irec.br_blockcount > check_rec.rm_blockcount) @@ -669,6 +715,30 @@ xchk_bmap_check_ag_rmaps( return error; } +/* Make sure each rt rmap has a corresponding bmbt entry. */ +STATIC int +xchk_bmap_check_rt_rmaps( + struct xfs_scrub *sc, + struct xfs_rtgroup *rtg) +{ + struct xchk_bmap_check_rmap_info sbcri; + struct xfs_btree_cur *cur; + int error; + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + cur = xfs_rtrmapbt_init_cursor(sc->tp, rtg); + + sbcri.sc = sc; + sbcri.whichfork = XFS_DATA_FORK; + error = xfs_rmap_query_all(cur, xchk_bmap_check_rmap, &sbcri); + if (error == -ECANCELED) + error = 0; + + xfs_btree_del_cursor(cur, error); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + return error; +} + /* * Decide if we want to scan the reverse mappings to determine if the attr * fork /really/ has zero space mappings. @@ -723,10 +793,6 @@ xchk_bmap_check_empty_datafork( { struct xfs_ifork *ifp = &ip->i_df; - /* Don't support realtime rmap checks yet. */ - if (XFS_IS_REALTIME_INODE(ip)) - return false; - /* * If the dinode repair found a bad data fork, it will reset the fork * to extents format with zero records and wait for the this scrubber @@ -777,6 +843,21 @@ xchk_bmap_check_rmaps( struct xfs_perag *pag = NULL; int error; + if (xfs_ifork_is_realtime(sc->ip, whichfork)) { + struct xfs_rtgroup *rtg = NULL; + + while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) { + error = xchk_bmap_check_rt_rmaps(sc, rtg); + if (error || + (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) { + xfs_rtgroup_rele(rtg); + return error; + } + } + + return 0; + } + while ((pag = xfs_perag_next(sc->mp, pag))) { error = xchk_bmap_check_ag_rmaps(sc, whichfork, pag); if (error || @@ -983,6 +1064,7 @@ xchk_bmap( case XFS_DINODE_FMT_UUID: case XFS_DINODE_FMT_DEV: case XFS_DINODE_FMT_LOCAL: + case XFS_DINODE_FMT_META_BTREE: /* No mappings to check. */ if (whichfork == XFS_COW_FORK) xchk_fblock_set_corrupt(sc, whichfork, 0); diff --git a/fs/xfs/scrub/bmap_repair.c b/fs/xfs/scrub/bmap_repair.c index 7c4955482641..1084213b8e9b 100644 --- a/fs/xfs/scrub/bmap_repair.c +++ b/fs/xfs/scrub/bmap_repair.c @@ -25,11 +25,13 @@ #include "xfs_bmap_btree.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" #include "xfs_refcount.h" #include "xfs_quota.h" #include "xfs_ialloc.h" #include "xfs_ag.h" #include "xfs_reflink.h" +#include "xfs_rtgroup.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -99,14 +101,21 @@ xrep_bmap_discover_shared( xfs_filblks_t blockcount) { struct xfs_scrub *sc = rb->sc; + struct xfs_btree_cur *cur; xfs_agblock_t agbno; xfs_agblock_t fbno; xfs_extlen_t flen; int error; - agbno = XFS_FSB_TO_AGBNO(sc->mp, startblock); - error = xfs_refcount_find_shared(sc->sa.refc_cur, agbno, blockcount, - &fbno, &flen, false); + if (XFS_IS_REALTIME_INODE(sc->ip)) { + agbno = xfs_rtb_to_rgbno(sc->mp, startblock); + cur = sc->sr.refc_cur; + } else { + agbno = XFS_FSB_TO_AGBNO(sc->mp, startblock); + cur = sc->sa.refc_cur; + } + error = xfs_refcount_find_shared(cur, agbno, blockcount, &fbno, &flen, + false); if (error) return error; @@ -359,6 +368,114 @@ xrep_bmap_scan_ag( return error; } +#ifdef CONFIG_XFS_RT +/* Check for any obvious errors or conflicts in the file mapping. */ +STATIC int +xrep_bmap_check_rtfork_rmap( + struct xfs_scrub *sc, + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec) +{ + /* xattr extents are never stored on realtime devices */ + if (rec->rm_flags & XFS_RMAP_ATTR_FORK) + return -EFSCORRUPTED; + + /* bmbt blocks are never stored on realtime devices */ + if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK) + return -EFSCORRUPTED; + + /* Data extents for non-rt files are never stored on the rt device. */ + if (!XFS_IS_REALTIME_INODE(sc->ip)) + return -EFSCORRUPTED; + + /* Check the file offsets and physical extents. */ + if (!xfs_verify_fileext(sc->mp, rec->rm_offset, rec->rm_blockcount)) + return -EFSCORRUPTED; + + /* Check that this is within the rtgroup. */ + if (!xfs_verify_rgbext(to_rtg(cur->bc_group), rec->rm_startblock, + rec->rm_blockcount)) + return -EFSCORRUPTED; + + /* Make sure this isn't free space. */ + return xrep_require_rtext_inuse(sc, rec->rm_startblock, + rec->rm_blockcount); +} + +/* Record realtime extents that belong to this inode's fork. */ +STATIC int +xrep_bmap_walk_rtrmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_bmap *rb = priv; + int error = 0; + + if (xchk_should_terminate(rb->sc, &error)) + return error; + + /* Skip extents which are not owned by this inode and fork. */ + if (rec->rm_owner != rb->sc->ip->i_ino) + return 0; + + error = xrep_bmap_check_rtfork_rmap(rb->sc, cur, rec); + if (error) + return error; + + /* + * Record all blocks allocated to this file even if the extent isn't + * for the fork we're rebuilding so that we can reset di_nblocks later. + */ + rb->nblocks += rec->rm_blockcount; + + /* If this rmap isn't for the fork we want, we're done. */ + if (rb->whichfork == XFS_DATA_FORK && + (rec->rm_flags & XFS_RMAP_ATTR_FORK)) + return 0; + if (rb->whichfork == XFS_ATTR_FORK && + !(rec->rm_flags & XFS_RMAP_ATTR_FORK)) + return 0; + + return xrep_bmap_from_rmap(rb, rec->rm_offset, + xfs_rgbno_to_rtb(to_rtg(cur->bc_group), + rec->rm_startblock), + rec->rm_blockcount, + rec->rm_flags & XFS_RMAP_UNWRITTEN); +} + +/* Scan the realtime reverse mappings to build the new extent map. */ +STATIC int +xrep_bmap_scan_rtgroup( + struct xrep_bmap *rb, + struct xfs_rtgroup *rtg) +{ + struct xfs_scrub *sc = rb->sc; + int error; + + if (!xfs_has_rtrmapbt(sc->mp)) + return 0; + + error = xrep_rtgroup_init(sc, rtg, &sc->sr, + XFS_RTGLOCK_RMAP | + XFS_RTGLOCK_REFCOUNT | + XFS_RTGLOCK_BITMAP_SHARED); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_bmap_walk_rtrmap, rb); + xchk_rtgroup_btcur_free(&sc->sr); + xchk_rtgroup_free(sc, &sc->sr); + return error; +} +#else +static inline int +xrep_bmap_scan_rtgroup(struct xrep_bmap *rb, struct xfs_rtgroup *rtg) +{ + return -EFSCORRUPTED; +} +#endif + /* Find the delalloc extents from the old incore extent tree. */ STATIC int xrep_bmap_find_delalloc( @@ -410,6 +527,22 @@ xrep_bmap_find_mappings( struct xfs_perag *pag = NULL; int error = 0; + /* + * Iterate the rtrmaps for extents. Metadata files never have content + * on the realtime device, so there's no need to scan them. + */ + if (!xfs_is_metadir_inode(sc->ip)) { + struct xfs_rtgroup *rtg = NULL; + + while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) { + error = xrep_bmap_scan_rtgroup(rb, rtg); + if (error) { + xfs_rtgroup_rele(rtg); + return error; + } + } + } + /* Iterate the rmaps for extents. */ while ((pag = xfs_perag_next(sc->mp, pag))) { error = xrep_bmap_scan_ag(rb, pag); @@ -731,6 +864,7 @@ xrep_bmap_check_inputs( case XFS_DINODE_FMT_DEV: case XFS_DINODE_FMT_LOCAL: case XFS_DINODE_FMT_UUID: + case XFS_DINODE_FMT_META_BTREE: return -ECANCELED; case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: @@ -753,10 +887,6 @@ xrep_bmap_check_inputs( return -EINVAL; } - /* Don't know how to rebuild realtime data forks. */ - if (XFS_IS_REALTIME_INODE(sc->ip)) - return -EOPNOTSUPP; - return 0; } @@ -782,10 +912,6 @@ xrep_bmap_init_reflink_scan( if (whichfork != XFS_DATA_FORK) return RLS_IRRELEVANT; - /* cannot share realtime extents */ - if (XFS_IS_REALTIME_INODE(sc->ip)) - return RLS_IRRELEVANT; - return RLS_UNKNOWN; } diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 5cbd94b56582..28ad341df8ee 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -35,6 +35,9 @@ #include "xfs_exchmaps.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_bmap_util.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -719,20 +722,111 @@ xchk_rtgroup_init( return 0; } -void +/* Lock all the rt group metadata inode ILOCKs and wait for intents. */ +int xchk_rtgroup_lock( + struct xfs_scrub *sc, struct xchk_rt *sr, unsigned int rtglock_flags) { - xfs_rtgroup_lock(sr->rtg, rtglock_flags); + int error = 0; + + ASSERT(sr->rtg != NULL); + + /* + * If we're /only/ locking the rtbitmap in shared mode, then we're + * obviously not trying to compare records in two metadata inodes. + * There's no need to drain intents here because the caller (most + * likely the rgsuper scanner) doesn't need that level of consistency. + */ + if (rtglock_flags == XFS_RTGLOCK_BITMAP_SHARED) { + xfs_rtgroup_lock(sr->rtg, rtglock_flags); + sr->rtlock_flags = rtglock_flags; + return 0; + } + + do { + if (xchk_should_terminate(sc, &error)) + return error; + + xfs_rtgroup_lock(sr->rtg, rtglock_flags); + + /* + * If we've grabbed a non-metadata file for scrubbing, we + * assume that holding its ILOCK will suffice to coordinate + * with any rt intent chains involving this inode. + */ + if (sc->ip && !xfs_is_internal_inode(sc->ip)) + break; + + /* + * Decide if the rt group is quiet enough for all metadata to + * be consistent with each other. Regular file IO doesn't get + * to lock all the rt inodes at the same time, which means that + * there could be other threads in the middle of processing a + * chain of deferred ops. + * + * We just locked all the metadata inodes for this rt group; + * now take a look to see if there are any intents in progress. + * If there are, drop the rt group inode locks and wait for the + * intents to drain. Since we hold the rt group inode locks + * for the duration of the scrub, this is the only time we have + * to sample the intents counter; any threads increasing it + * after this point can't possibly be in the middle of a chain + * of rt metadata updates. + * + * Obviously, this should be slanted against scrub and in favor + * of runtime threads. + */ + if (!xfs_group_intent_busy(rtg_group(sr->rtg))) + break; + + xfs_rtgroup_unlock(sr->rtg, rtglock_flags); + + if (!(sc->flags & XCHK_FSGATES_DRAIN)) + return -ECHRNG; + error = xfs_group_intent_drain(rtg_group(sr->rtg)); + if (error) { + if (error == -ERESTARTSYS) + error = -EINTR; + return error; + } + } while (1); + sr->rtlock_flags = rtglock_flags; + + if (xfs_has_rtrmapbt(sc->mp) && (rtglock_flags & XFS_RTGLOCK_RMAP)) + sr->rmap_cur = xfs_rtrmapbt_init_cursor(sc->tp, sr->rtg); + + if (xfs_has_rtreflink(sc->mp) && (rtglock_flags & XFS_RTGLOCK_REFCOUNT)) + sr->refc_cur = xfs_rtrefcountbt_init_cursor(sc->tp, sr->rtg); + + return 0; +} + +/* + * Free all the btree cursors and other incore data relating to the realtime + * group. This has to be done /before/ committing (or cancelling) the scrub + * transaction. + */ +void +xchk_rtgroup_btcur_free( + struct xchk_rt *sr) +{ + if (sr->rmap_cur) + xfs_btree_del_cursor(sr->rmap_cur, XFS_BTREE_ERROR); + if (sr->refc_cur) + xfs_btree_del_cursor(sr->refc_cur, XFS_BTREE_ERROR); + + sr->refc_cur = NULL; + sr->rmap_cur = NULL; } /* * Unlock the realtime group. This must be done /after/ committing (or * cancelling) the scrub transaction. */ -static void +void xchk_rtgroup_unlock( struct xchk_rt *sr) { @@ -812,6 +906,14 @@ xchk_setup_fs( return xchk_trans_alloc(sc, resblks); } +/* Set us up with a transaction and an empty context to repair rt metadata. */ +int +xchk_setup_rt( + struct xfs_scrub *sc) +{ + return xchk_trans_alloc(sc, xrep_calc_rtgroup_resblks(sc)); +} + /* Set us up with AG headers and btree cursors. */ int xchk_setup_ag_btree( @@ -1379,7 +1481,7 @@ xchk_fsgates_enable( trace_xchk_fsgates_enable(sc, scrub_fsgates); if (scrub_fsgates & XCHK_FSGATES_DRAIN) - xfs_drain_wait_enable(); + xfs_defer_drain_wait_enable(); if (scrub_fsgates & XCHK_FSGATES_QUOTA) xfs_dqtrx_hook_enable(); @@ -1573,3 +1675,63 @@ xchk_inode_rootdir_inum(const struct xfs_inode *ip) return mp->m_metadirip->i_ino; return mp->m_rootip->i_ino; } + +static int +xchk_meta_btree_count_blocks( + struct xfs_scrub *sc, + xfs_extnum_t *nextents, + xfs_filblks_t *count) +{ + struct xfs_btree_cur *cur; + int error; + + if (!sc->sr.rtg) { + ASSERT(0); + return -EFSCORRUPTED; + } + + switch (sc->ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + cur = xfs_rtrmapbt_init_cursor(sc->tp, sc->sr.rtg); + break; + case XFS_METAFILE_RTREFCOUNT: + cur = xfs_rtrefcountbt_init_cursor(sc->tp, sc->sr.rtg); + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + error = xfs_btree_count_blocks(cur, count); + xfs_btree_del_cursor(cur, error); + if (!error) { + *nextents = 0; + (*count)--; /* don't count the btree iroot */ + } + return error; +} + +/* Count the blocks used by a file, even if it's a metadata inode. */ +int +xchk_inode_count_blocks( + struct xfs_scrub *sc, + int whichfork, + xfs_extnum_t *nextents, + xfs_filblks_t *count) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, whichfork); + + if (!ifp) { + *nextents = 0; + *count = 0; + return 0; + } + + if (ifp->if_format == XFS_DINODE_FMT_META_BTREE) { + ASSERT(whichfork == XFS_DATA_FORK); + return xchk_meta_btree_count_blocks(sc, nextents, count); + } + + return xfs_bmap_count_blocks(sc->tp, sc->ip, whichfork, nextents, + count); +} diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 9ff3cafd8679..bdcd40f0ec74 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -63,6 +63,7 @@ static inline int xchk_setup_nothing(struct xfs_scrub *sc) /* Setup functions */ int xchk_setup_agheader(struct xfs_scrub *sc); int xchk_setup_fs(struct xfs_scrub *sc); +int xchk_setup_rt(struct xfs_scrub *sc); int xchk_setup_ag_allocbt(struct xfs_scrub *sc); int xchk_setup_ag_iallocbt(struct xfs_scrub *sc); int xchk_setup_ag_rmapbt(struct xfs_scrub *sc); @@ -80,10 +81,14 @@ int xchk_setup_metapath(struct xfs_scrub *sc); int xchk_setup_rtbitmap(struct xfs_scrub *sc); int xchk_setup_rtsummary(struct xfs_scrub *sc); int xchk_setup_rgsuperblock(struct xfs_scrub *sc); +int xchk_setup_rtrmapbt(struct xfs_scrub *sc); +int xchk_setup_rtrefcountbt(struct xfs_scrub *sc); #else # define xchk_setup_rtbitmap xchk_setup_nothing # define xchk_setup_rtsummary xchk_setup_nothing # define xchk_setup_rgsuperblock xchk_setup_nothing +# define xchk_setup_rtrmapbt xchk_setup_nothing +# define xchk_setup_rtrefcountbt xchk_setup_nothing #endif #ifdef CONFIG_XFS_QUOTA int xchk_ino_dqattach(struct xfs_scrub *sc); @@ -125,7 +130,9 @@ xchk_ag_init_existing( #ifdef CONFIG_XFS_RT /* All the locks we need to check an rtgroup. */ -#define XCHK_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP) +#define XCHK_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) int xchk_rtgroup_init(struct xfs_scrub *sc, xfs_rgnumber_t rgno, struct xchk_rt *sr); @@ -141,12 +148,17 @@ xchk_rtgroup_init_existing( return error == -ENOENT ? -EFSCORRUPTED : error; } -void xchk_rtgroup_lock(struct xchk_rt *sr, unsigned int rtglock_flags); +int xchk_rtgroup_lock(struct xfs_scrub *sc, struct xchk_rt *sr, + unsigned int rtglock_flags); +void xchk_rtgroup_unlock(struct xchk_rt *sr); +void xchk_rtgroup_btcur_free(struct xchk_rt *sr); void xchk_rtgroup_free(struct xfs_scrub *sc, struct xchk_rt *sr); #else # define xchk_rtgroup_init(sc, rgno, sr) (-EFSCORRUPTED) # define xchk_rtgroup_init_existing(sc, rgno, sr) (-EFSCORRUPTED) -# define xchk_rtgroup_lock(sc, lockflags) do { } while (0) +# define xchk_rtgroup_lock(sc, sr, lockflags) (-EFSCORRUPTED) +# define xchk_rtgroup_unlock(sr) do { } while (0) +# define xchk_rtgroup_btcur_free(sr) do { } while (0) # define xchk_rtgroup_free(sc, sr) do { } while (0) #endif /* CONFIG_XFS_RT */ @@ -257,6 +269,12 @@ int xchk_metadata_inode_forks(struct xfs_scrub *sc); (sc)->mp->m_super->s_id, \ (sc)->ip ? (sc)->ip->i_ino : (sc)->sm->sm_ino, \ ##__VA_ARGS__) +#define xchk_xfile_rtgroup_descr(sc, fmt, ...) \ + kasprintf(XCHK_GFP_FLAGS, "XFS (%s): rtgroup 0x%x " fmt, \ + (sc)->mp->m_super->s_id, \ + (sc)->sa.pag ? \ + rtg_rgno((sc)->sr.rtg) : (sc)->sm->sm_agno, \ + ##__VA_ARGS__) /* * Setting up a hook to wait for intents to drain is costly -- we have to take @@ -274,6 +292,8 @@ void xchk_fsgates_enable(struct xfs_scrub *sc, unsigned int scrub_fshooks); int xchk_inode_is_allocated(struct xfs_scrub *sc, xfs_agino_t agino, bool *inuse); +int xchk_inode_count_blocks(struct xfs_scrub *sc, int whichfork, + xfs_extnum_t *nextents, xfs_filblks_t *count); bool xchk_inode_is_dirtree_root(const struct xfs_inode *ip); bool xchk_inode_is_sb_rooted(const struct xfs_inode *ip); diff --git a/fs/xfs/scrub/cow_repair.c b/fs/xfs/scrub/cow_repair.c index 5b6194cef3e5..38a246b8bf11 100644 --- a/fs/xfs/scrub/cow_repair.c +++ b/fs/xfs/scrub/cow_repair.c @@ -26,6 +26,9 @@ #include "xfs_errortag.h" #include "xfs_icache.h" #include "xfs_refcount_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -34,6 +37,7 @@ #include "scrub/bitmap.h" #include "scrub/off_bitmap.h" #include "scrub/fsb_bitmap.h" +#include "scrub/rtb_bitmap.h" #include "scrub/reap.h" /* @@ -61,7 +65,10 @@ struct xrep_cow { struct xoff_bitmap bad_fileoffs; /* Bitmap of fsblocks that were removed from the CoW fork. */ - struct xfsb_bitmap old_cowfork_fsblocks; + union { + struct xfsb_bitmap old_cowfork_fsblocks; + struct xrtb_bitmap old_cowfork_rtblocks; + }; /* CoW fork mappings used to scan for bad CoW staging extents. */ struct xfs_bmbt_irec irec; @@ -145,8 +152,7 @@ xrep_cow_mark_shared_staging( xrep_cow_trim_refcount(xc, &rrec, rec); return xrep_cow_mark_file_range(xc, - xfs_agbno_to_fsb(to_perag(cur->bc_group), - rrec.rc_startblock), + xfs_gbno_to_fsb(cur->bc_group, rrec.rc_startblock), rrec.rc_blockcount); } @@ -177,9 +183,8 @@ xrep_cow_mark_missing_staging( if (xc->next_bno >= rrec.rc_startblock) goto next; - error = xrep_cow_mark_file_range(xc, - xfs_agbno_to_fsb(to_perag(cur->bc_group), xc->next_bno), + xfs_gbno_to_fsb(cur->bc_group, xc->next_bno), rrec.rc_startblock - xc->next_bno); if (error) return error; @@ -222,8 +227,7 @@ xrep_cow_mark_missing_staging_rmap( } return xrep_cow_mark_file_range(xc, - xfs_agbno_to_fsb(to_perag(cur->bc_group), rec_bno), - rec_len); + xfs_gbno_to_fsb(cur->bc_group, rec_bno), rec_len); } /* @@ -310,6 +314,92 @@ out_pag: return 0; } +/* + * Find any part of the CoW fork mapping that isn't a single-owner CoW staging + * extent and mark the corresponding part of the file range in the bitmap. + */ +STATIC int +xrep_cow_find_bad_rt( + struct xrep_cow *xc) +{ + struct xfs_refcount_irec rc_low = { 0 }; + struct xfs_refcount_irec rc_high = { 0 }; + struct xfs_rmap_irec rm_low = { 0 }; + struct xfs_rmap_irec rm_high = { 0 }; + struct xfs_scrub *sc = xc->sc; + struct xfs_rtgroup *rtg; + int error = 0; + + xc->irec_startbno = xfs_rtb_to_rgbno(sc->mp, xc->irec.br_startblock); + + rtg = xfs_rtgroup_get(sc->mp, + xfs_rtb_to_rgno(sc->mp, xc->irec.br_startblock)); + if (!rtg) + return -EFSCORRUPTED; + + error = xrep_rtgroup_init(sc, rtg, &sc->sr, + XFS_RTGLOCK_RMAP | XFS_RTGLOCK_REFCOUNT); + if (error) + goto out_rtg; + + /* Mark any CoW fork extents that are shared. */ + rc_low.rc_startblock = xc->irec_startbno; + rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1; + rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_SHARED; + error = xfs_refcount_query_range(sc->sr.refc_cur, &rc_low, &rc_high, + xrep_cow_mark_shared_staging, xc); + if (error) + goto out_sr; + + /* Make sure there are CoW staging extents for the whole mapping. */ + rc_low.rc_startblock = xc->irec_startbno; + rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1; + rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_COW; + xc->next_bno = xc->irec_startbno; + error = xfs_refcount_query_range(sc->sr.refc_cur, &rc_low, &rc_high, + xrep_cow_mark_missing_staging, xc); + if (error) + goto out_sr; + + if (xc->next_bno < xc->irec_startbno + xc->irec.br_blockcount) { + error = xrep_cow_mark_file_range(xc, + xfs_rgbno_to_rtb(rtg, xc->next_bno), + xc->irec_startbno + xc->irec.br_blockcount - + xc->next_bno); + if (error) + goto out_sr; + } + + /* Mark any area has an rmap that isn't a COW staging extent. */ + rm_low.rm_startblock = xc->irec_startbno; + memset(&rm_high, 0xFF, sizeof(rm_high)); + rm_high.rm_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1; + error = xfs_rmap_query_range(sc->sr.rmap_cur, &rm_low, &rm_high, + xrep_cow_mark_missing_staging_rmap, xc); + if (error) + goto out_sr; + + /* + * If userspace is forcing us to rebuild the CoW fork or someone + * turned on the debugging knob, replace everything in the + * CoW fork and then scan for staging extents in the refcountbt. + */ + if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) || + XFS_TEST_ERROR(false, sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR)) { + error = xrep_cow_mark_file_range(xc, xc->irec.br_startblock, + xc->irec.br_blockcount); + if (error) + goto out_rtg; + } + +out_sr: + xchk_rtgroup_btcur_free(&sc->sr); + xchk_rtgroup_free(sc, &sc->sr); +out_rtg: + xfs_rtgroup_put(rtg); + return error; +} + /* * Allocate a replacement CoW staging extent of up to the given number of * blocks, and fill out the mapping. @@ -343,13 +433,39 @@ xrep_cow_alloc( if (args.fsbno == NULLFSBLOCK) return -ENOSPC; - xfs_refcount_alloc_cow_extent(sc->tp, args.fsbno, args.len); + xfs_refcount_alloc_cow_extent(sc->tp, false, args.fsbno, args.len); repl->fsbno = args.fsbno; repl->len = args.len; return 0; } +/* + * Allocate a replacement rt CoW staging extent of up to the given number of + * blocks, and fill out the mapping. + */ +STATIC int +xrep_cow_alloc_rt( + struct xfs_scrub *sc, + xfs_extlen_t maxlen, + struct xrep_cow_extent *repl) +{ + xfs_rtxlen_t maxrtx = xfs_rtb_to_rtx(sc->mp, maxlen); + int error; + + error = xfs_trans_reserve_more(sc->tp, 0, maxrtx); + if (error) + return error; + + error = xfs_rtallocate_rtgs(sc->tp, NULLRTBLOCK, 1, maxrtx, 1, false, + false, &repl->fsbno, &repl->len); + if (error) + return error; + + xfs_refcount_alloc_cow_extent(sc->tp, true, repl->fsbno, repl->len); + return 0; +} + /* * Look up the current CoW fork mapping so that we only allocate enough to * replace a single mapping. If we don't find a mapping that covers the start @@ -467,7 +583,10 @@ xrep_cow_replace_range( */ alloc_len = min_t(xfs_fileoff_t, XFS_MAX_BMBT_EXTLEN, nextoff - startoff); - error = xrep_cow_alloc(sc, alloc_len, &repl); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrep_cow_alloc_rt(sc, alloc_len, &repl); + else + error = xrep_cow_alloc(sc, alloc_len, &repl); if (error) return error; @@ -483,8 +602,12 @@ xrep_cow_replace_range( return error; /* Note the old CoW staging extents; we'll reap them all later. */ - error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, got.br_startblock, - repl.len); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrtb_bitmap_set(&xc->old_cowfork_rtblocks, + got.br_startblock, repl.len); + else + error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, + got.br_startblock, repl.len); if (error) return error; @@ -540,8 +663,16 @@ xrep_bmap_cow( if (!ifp) return 0; - /* realtime files aren't supported yet */ - if (XFS_IS_REALTIME_INODE(sc->ip)) + /* + * Realtime files with large extent sizes are not supported because + * we could encounter an CoW mapping that has been partially written + * out *and* requires replacement, and there's no solution to that. + */ + if (xfs_inode_has_bigrtalloc(sc->ip)) + return -EOPNOTSUPP; + + /* Metadata inodes aren't supposed to have data on the rt volume. */ + if (xfs_is_metadir_inode(sc->ip) && XFS_IS_REALTIME_INODE(sc->ip)) return -EOPNOTSUPP; /* @@ -562,7 +693,10 @@ xrep_bmap_cow( xc->sc = sc; xoff_bitmap_init(&xc->bad_fileoffs); - xfsb_bitmap_init(&xc->old_cowfork_fsblocks); + if (XFS_IS_REALTIME_INODE(sc->ip)) + xrtb_bitmap_init(&xc->old_cowfork_rtblocks); + else + xfsb_bitmap_init(&xc->old_cowfork_fsblocks); for_each_xfs_iext(ifp, &icur, &xc->irec) { if (xchk_should_terminate(sc, &error)) @@ -585,7 +719,10 @@ xrep_bmap_cow( if (xfs_bmap_is_written_extent(&xc->irec)) continue; - error = xrep_cow_find_bad(xc); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrep_cow_find_bad_rt(xc); + else + error = xrep_cow_find_bad(xc); if (error) goto out_bitmap; } @@ -600,13 +737,20 @@ xrep_bmap_cow( * by the refcount btree, not the inode, so it is correct to treat them * like inode metadata. */ - error = xrep_reap_fsblocks(sc, &xc->old_cowfork_fsblocks, - &XFS_RMAP_OINFO_COW); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrep_reap_rtblocks(sc, &xc->old_cowfork_rtblocks, + &XFS_RMAP_OINFO_COW); + else + error = xrep_reap_fsblocks(sc, &xc->old_cowfork_fsblocks, + &XFS_RMAP_OINFO_COW); if (error) goto out_bitmap; out_bitmap: - xfsb_bitmap_destroy(&xc->old_cowfork_fsblocks); + if (XFS_IS_REALTIME_INODE(sc->ip)) + xrtb_bitmap_destroy(&xc->old_cowfork_rtblocks); + else + xfsb_bitmap_destroy(&xc->old_cowfork_fsblocks); xoff_bitmap_destroy(&xc->bad_fileoffs); kfree(xc); return error; diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index ccc6ca5934ca..3c0f25098b69 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -114,6 +114,8 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = { [XFS_SCRUB_TYPE_DIRTREE] = { XHG_INO, XFS_SICK_INO_DIRTREE }, [XFS_SCRUB_TYPE_METAPATH] = { XHG_FS, XFS_SICK_FS_METAPATH }, [XFS_SCRUB_TYPE_RGSUPER] = { XHG_RTGROUP, XFS_SICK_RG_SUPER }, + [XFS_SCRUB_TYPE_RTRMAPBT] = { XHG_RTGROUP, XFS_SICK_RG_RMAPBT }, + [XFS_SCRUB_TYPE_RTREFCBT] = { XHG_RTGROUP, XFS_SICK_RG_REFCNTBT }, }; /* Return the health status mask for this scrub type. */ diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 25ee66e7649d..db6edd5a5fe5 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -260,12 +260,7 @@ xchk_inode_extsize( xchk_ino_set_warning(sc, ino); } -/* - * Validate di_cowextsize hint. - * - * The rules are documented at xfs_ioctl_setattr_check_cowextsize(). - * These functions must be kept in sync with each other. - */ +/* Validate di_cowextsize hint. */ STATIC void xchk_inode_cowextsize( struct xfs_scrub *sc, @@ -276,12 +271,25 @@ xchk_inode_cowextsize( uint64_t flags2) { xfs_failaddr_t fa; + uint32_t value = be32_to_cpu(dip->di_cowextsize); - fa = xfs_inode_validate_cowextsize(sc->mp, - be32_to_cpu(dip->di_cowextsize), mode, flags, - flags2); + fa = xfs_inode_validate_cowextsize(sc->mp, value, mode, flags, flags2); if (fa) xchk_ino_set_corrupt(sc, ino); + + /* + * XFS allows a sysadmin to change the rt extent size when adding a rt + * section to a filesystem after formatting. If there are any + * directories with cowextsize and rtinherit set, the hint could become + * misaligned with the new rextsize. The verifier doesn't check this, + * because we allow rtinherit directories even without an rt device. + * Flag this as an administrative warning since we will clean this up + * eventually. + */ + if ((flags & XFS_DIFLAG_RTINHERIT) && + (flags2 & XFS_DIFLAG2_COWEXTSIZE) && + value % sc->mp->m_sb.sb_rextsize > 0) + xchk_ino_set_warning(sc, ino); } /* Make sure the di_flags make sense for the inode. */ @@ -360,8 +368,9 @@ xchk_inode_flags2( if ((flags2 & XFS_DIFLAG2_REFLINK) && !S_ISREG(mode)) goto bad; - /* realtime and reflink make no sense, currently */ - if ((flags & XFS_DIFLAG_REALTIME) && (flags2 & XFS_DIFLAG2_REFLINK)) + /* realtime and reflink don't always go together */ + if ((flags & XFS_DIFLAG_REALTIME) && (flags2 & XFS_DIFLAG2_REFLINK) && + !xfs_has_rtreflink(mp)) goto bad; /* no bigtime iflag without the bigtime feature */ @@ -502,6 +511,10 @@ xchk_dinode( if (!S_ISREG(mode) && !S_ISDIR(mode)) xchk_ino_set_corrupt(sc, ino); break; + case XFS_DINODE_FMT_META_BTREE: + if (!S_ISREG(mode)) + xchk_ino_set_corrupt(sc, ino); + break; case XFS_DINODE_FMT_UUID: default: xchk_ino_set_corrupt(sc, ino); @@ -686,15 +699,13 @@ xchk_inode_xref_bmap( return; /* Walk all the extents to check nextents/naextents/nblocks. */ - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK, - &nextents, &count); + error = xchk_inode_count_blocks(sc, XFS_DATA_FORK, &nextents, &count); if (!xchk_should_check_xref(sc, &error, NULL)) return; if (nextents < xfs_dfork_data_extents(dip)) xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino); - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK, - &nextents, &acount); + error = xchk_inode_count_blocks(sc, XFS_ATTR_FORK, &nextents, &acount); if (!xchk_should_check_xref(sc, &error, NULL)) return; if (nextents != xfs_dfork_attr_extents(dip)) diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 5a58ddd27bd2..2f641b6d663e 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -38,6 +38,9 @@ #include "xfs_log_priv.h" #include "xfs_health.h" #include "xfs_symlink_remote.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -562,8 +565,6 @@ xrep_dinode_flags( flags2 |= XFS_DIFLAG2_REFLINK; else flags2 &= ~(XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE); - if (flags & XFS_DIFLAG_REALTIME) - flags2 &= ~XFS_DIFLAG2_REFLINK; if (!xfs_has_bigtime(mp)) flags2 &= ~XFS_DIFLAG2_BIGTIME; if (!xfs_has_large_extent_counts(mp)) @@ -773,17 +774,71 @@ xrep_dinode_count_ag_rmaps( return error; } +/* Count extents and blocks for an inode given an rt rmap. */ +STATIC int +xrep_dinode_walk_rtrmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_inode *ri = priv; + int error = 0; + + if (xchk_should_terminate(ri->sc, &error)) + return error; + + /* We only care about this inode. */ + if (rec->rm_owner != ri->sc->sm->sm_ino) + return 0; + + if (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)) + return -EFSCORRUPTED; + + ri->rt_blocks += rec->rm_blockcount; + ri->rt_extents++; + return 0; +} + +/* Count extents and blocks for an inode from all realtime rmap data. */ +STATIC int +xrep_dinode_count_rtgroup_rmaps( + struct xrep_inode *ri, + struct xfs_rtgroup *rtg) +{ + struct xfs_scrub *sc = ri->sc; + int error; + + error = xrep_rtgroup_init(sc, rtg, &sc->sr, XFS_RTGLOCK_RMAP); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_dinode_walk_rtrmap, + ri); + xchk_rtgroup_btcur_free(&sc->sr); + xchk_rtgroup_free(sc, &sc->sr); + return error; +} + /* Count extents and blocks for a given inode from all rmap data. */ STATIC int xrep_dinode_count_rmaps( struct xrep_inode *ri) { struct xfs_perag *pag = NULL; + struct xfs_rtgroup *rtg = NULL; int error; - if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp)) + if (!xfs_has_rmapbt(ri->sc->mp)) return -EOPNOTSUPP; + while ((rtg = xfs_rtgroup_next(ri->sc->mp, rtg))) { + error = xrep_dinode_count_rtgroup_rmaps(ri, rtg); + if (error) { + xfs_rtgroup_rele(rtg); + return error; + } + } + while ((pag = xfs_perag_next(ri->sc->mp, pag))) { error = xrep_dinode_count_ag_rmaps(ri, pag); if (error) { @@ -888,6 +943,85 @@ xrep_dinode_bad_bmbt_fork( return false; } +/* Return true if this rmap-format ifork looks like garbage. */ +STATIC bool +xrep_dinode_bad_rtrmapbt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size) +{ + struct xfs_rtrmap_root *dfp; + unsigned int nrecs; + unsigned int level; + + if (dfork_size < sizeof(struct xfs_rtrmap_root)) + return true; + + dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + nrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > sc->mp->m_rtrmap_maxlevels) + return true; + if (xfs_rtrmap_droot_space_calc(level, nrecs) > dfork_size) + return true; + if (level > 0 && nrecs == 0) + return true; + + return false; +} + +/* Return true if this refcount-format ifork looks like garbage. */ +STATIC bool +xrep_dinode_bad_rtrefcountbt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size) +{ + struct xfs_rtrefcount_root *dfp; + unsigned int nrecs; + unsigned int level; + + if (dfork_size < sizeof(struct xfs_rtrefcount_root)) + return true; + + dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + nrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > sc->mp->m_rtrefc_maxlevels) + return true; + if (xfs_rtrefcount_droot_space_calc(level, nrecs) > dfork_size) + return true; + if (level > 0 && nrecs == 0) + return true; + + return false; +} + +/* Check a metadata-btree fork. */ +STATIC bool +xrep_dinode_bad_metabt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size, + int whichfork) +{ + if (whichfork != XFS_DATA_FORK) + return true; + + switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + return xrep_dinode_bad_rtrmapbt_fork(sc, dip, dfork_size); + case XFS_METAFILE_RTREFCOUNT: + return xrep_dinode_bad_rtrefcountbt_fork(sc, dip, dfork_size); + default: + return true; + } + + return false; +} + /* * Check the data fork for things that will fail the ifork verifiers or the * ifork formatters. @@ -968,6 +1102,11 @@ xrep_dinode_check_dfork( XFS_DATA_FORK)) return true; break; + case XFS_DINODE_FMT_META_BTREE: + if (xrep_dinode_bad_metabt_fork(sc, dip, dfork_size, + XFS_DATA_FORK)) + return true; + break; default: return true; } @@ -1088,6 +1227,11 @@ xrep_dinode_check_afork( XFS_ATTR_FORK)) return true; break; + case XFS_DINODE_FMT_META_BTREE: + if (xrep_dinode_bad_metabt_fork(sc, dip, afork_size, + XFS_ATTR_FORK)) + return true; + break; default: return true; } @@ -1135,6 +1279,8 @@ xrep_dinode_ensure_forkoff( uint16_t mode) { struct xfs_bmdr_block *bmdr; + struct xfs_rtrmap_root *rmdr; + struct xfs_rtrefcount_root *rcdr; struct xfs_scrub *sc = ri->sc; xfs_extnum_t attr_extents, data_extents; size_t bmdr_minsz = xfs_bmdr_space_calc(1); @@ -1241,6 +1387,21 @@ xrep_dinode_ensure_forkoff( bmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); dfork_min = xfs_bmap_broot_space(sc->mp, bmdr); break; + case XFS_DINODE_FMT_META_BTREE: + switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + rmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + dfork_min = xfs_rtrmap_broot_space(sc->mp, rmdr); + break; + case XFS_METAFILE_RTREFCOUNT: + rcdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + dfork_min = xfs_rtrefcount_broot_space(sc->mp, rcdr); + break; + default: + dfork_min = 0; + break; + } + break; default: dfork_min = 0; break; @@ -1500,8 +1661,7 @@ xrep_inode_blockcounts( trace_xrep_inode_blockcounts(sc); /* Set data fork counters from the data fork mappings. */ - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK, - &nextents, &count); + error = xchk_inode_count_blocks(sc, XFS_DATA_FORK, &nextents, &count); if (error) return error; if (xfs_is_reflink_inode(sc->ip)) { @@ -1525,8 +1685,8 @@ xrep_inode_blockcounts( /* Set attr fork counters from the attr fork mappings. */ ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK); if (ifp) { - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK, - &nextents, &acount); + error = xchk_inode_count_blocks(sc, XFS_ATTR_FORK, &nextents, + &acount); if (error) return error; if (count >= sc->mp->m_sb.sb_dblocks) @@ -1664,10 +1824,6 @@ xrep_inode_flags( /* DAX only applies to files and dirs. */ if (!(S_ISREG(mode) || S_ISDIR(mode))) sc->ip->i_diflags2 &= ~XFS_DIFLAG2_DAX; - - /* No reflink files on the realtime device. */ - if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME) - sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; } /* @@ -1783,6 +1939,20 @@ xrep_inode_pptr( sizeof(struct xfs_attr_sf_hdr), true); } +/* Fix COW extent size hint problems. */ +STATIC void +xrep_inode_cowextsize( + struct xfs_scrub *sc) +{ + /* Fix misaligned CoW extent size hints on a directory. */ + if ((sc->ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + (sc->ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) && + sc->ip->i_extsize % sc->mp->m_sb.sb_rextsize > 0) { + sc->ip->i_cowextsize = 0; + sc->ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + } +} + /* Fix any irregularities in an inode that the verifiers don't catch. */ STATIC int xrep_inode_problems( @@ -1806,6 +1976,7 @@ xrep_inode_problems( if (S_ISDIR(VFS_I(sc->ip)->i_mode)) xrep_inode_dir_size(sc); xrep_inode_extsize(sc); + xrep_inode_cowextsize(sc); trace_xrep_inode_fixed(sc); xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE); diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index c678cba1ffc3..e21c16fbd15d 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -21,6 +21,8 @@ #include "xfs_trans_space.h" #include "xfs_attr.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -246,6 +248,10 @@ xchk_setup_metapath( return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_GROUP); case XFS_SCRUB_METAPATH_PRJQUOTA: return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_PROJ); + case XFS_SCRUB_METAPATH_RTRMAPBT: + return xchk_setup_metapath_rtginode(sc, XFS_RTGI_RMAP); + case XFS_SCRUB_METAPATH_RTREFCOUNTBT: + return xchk_setup_metapath_rtginode(sc, XFS_RTGI_REFCOUNT); default: return -ENOENT; } diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c index 70af27d98734..ac38f5843090 100644 --- a/fs/xfs/scrub/newbt.c +++ b/fs/xfs/scrub/newbt.c @@ -19,6 +19,8 @@ #include "xfs_rmap.h" #include "xfs_ag.h" #include "xfs_defer.h" +#include "xfs_metafile.h" +#include "xfs_quota.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -120,6 +122,43 @@ xrep_newbt_init_inode( return 0; } +/* + * Initialize accounting resources for staging a new metadata inode btree. + * If the metadata file has a space reservation, the caller must adjust that + * reservation when committing the new ondisk btree. + */ +int +xrep_newbt_init_metadir_inode( + struct xrep_newbt *xnr, + struct xfs_scrub *sc) +{ + struct xfs_owner_info oinfo; + struct xfs_ifork *ifp; + + ASSERT(xfs_is_metadir_inode(sc->ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, XFS_DATA_FORK); + + ifp = kmem_cache_zalloc(xfs_ifork_cache, XCHK_GFP_FLAGS); + if (!ifp) + return -ENOMEM; + + /* + * Allocate new metadir btree blocks with XFS_AG_RESV_NONE because the + * inode metadata space reservations can only account allocated space + * to the i_nblocks. We do not want to change the inode core fields + * until we're ready to commit the new tree, so we allocate the blocks + * as if they were regular file blocks. This exposes us to a higher + * risk of the repair being cancelled due to ENOSPC. + */ + xrep_newbt_init_ag(xnr, sc, &oinfo, + XFS_INO_TO_FSB(sc->mp, sc->ip->i_ino), + XFS_AG_RESV_NONE); + xnr->ifake.if_fork = ifp; + xnr->ifake.if_fork_size = xfs_inode_fork_size(sc->ip, XFS_DATA_FORK); + return 0; +} + /* * Initialize accounting resources for staging a new btree. Callers are * expected to add their own reservations (and clean them up) manually. @@ -224,6 +263,7 @@ xrep_newbt_alloc_ag_blocks( int error = 0; ASSERT(sc->sa.pag != NULL); + ASSERT(xnr->resv != XFS_AG_RESV_METAFILE); while (nr_blocks > 0) { struct xfs_alloc_arg args = { @@ -297,6 +337,8 @@ xrep_newbt_alloc_file_blocks( struct xfs_mount *mp = sc->mp; int error = 0; + ASSERT(xnr->resv != XFS_AG_RESV_METAFILE); + while (nr_blocks > 0) { struct xfs_alloc_arg args = { .tp = sc->tp, diff --git a/fs/xfs/scrub/newbt.h b/fs/xfs/scrub/newbt.h index 3d804d31af24..5ce785599287 100644 --- a/fs/xfs/scrub/newbt.h +++ b/fs/xfs/scrub/newbt.h @@ -63,6 +63,7 @@ void xrep_newbt_init_ag(struct xrep_newbt *xnr, struct xfs_scrub *sc, enum xfs_ag_resv_type resv); int xrep_newbt_init_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc, int whichfork, const struct xfs_owner_info *oinfo); +int xrep_newbt_init_metadir_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc); int xrep_newbt_alloc_blocks(struct xrep_newbt *xnr, uint64_t nr_blocks); int xrep_newbt_add_extent(struct xrep_newbt *xnr, struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len); diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 183d531875ea..58d6d4ed2853 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -212,12 +212,18 @@ xchk_quota_item( if (mp->m_sb.sb_dblocks < dq->q_blk.count) xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset); + if (mp->m_sb.sb_rblocks < dq->q_rtb.count) + xchk_fblock_set_warning(sc, XFS_DATA_FORK, + offset); } else { if (mp->m_sb.sb_dblocks < dq->q_blk.count) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); + if (mp->m_sb.sb_rblocks < dq->q_rtb.count) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, + offset); } - if (dq->q_ino.count > fs_icount || dq->q_rtb.count > mp->m_sb.sb_rblocks) + if (dq->q_ino.count > fs_icount) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); /* diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c index cd51f10f2920..8f4c8d41f308 100644 --- a/fs/xfs/scrub/quota_repair.c +++ b/fs/xfs/scrub/quota_repair.c @@ -233,7 +233,7 @@ xrep_quota_item( rqi->need_quotacheck = true; dirty = true; } - if (dq->q_rtb.count > mp->m_sb.sb_rblocks) { + if (!xfs_has_reflink(mp) && dq->q_rtb.count > mp->m_sb.sb_rblocks) { dq->q_rtb.reserved -= dq->q_rtb.count; dq->q_rtb.reserved += mp->m_sb.sb_rblocks; dq->q_rtb.count = mp->m_sb.sb_rblocks; diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c index 08230952053b..b32fb233cf84 100644 --- a/fs/xfs/scrub/reap.c +++ b/fs/xfs/scrub/reap.c @@ -33,6 +33,9 @@ #include "xfs_attr.h" #include "xfs_attr_remote.h" #include "xfs_defer.h" +#include "xfs_metafile.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -40,6 +43,7 @@ #include "scrub/bitmap.h" #include "scrub/agb_bitmap.h" #include "scrub/fsb_bitmap.h" +#include "scrub/rtb_bitmap.h" #include "scrub/reap.h" /* @@ -310,7 +314,7 @@ xreap_agextent_binval( } out: - trace_xreap_agextent_binval(sc->sa.pag, agbno, *aglenp); + trace_xreap_agextent_binval(pag_group(sc->sa.pag), agbno, *aglenp); } /* @@ -369,7 +373,8 @@ xreap_agextent_select( out_found: *aglenp = len; - trace_xreap_agextent_select(sc->sa.pag, agbno, len, *crosslinked); + trace_xreap_agextent_select(pag_group(sc->sa.pag), agbno, len, + *crosslinked); out_cur: xfs_btree_del_cursor(cur, error); return error; @@ -390,6 +395,8 @@ xreap_agextent_iter( xfs_fsblock_t fsbno; int error = 0; + ASSERT(rs->resv != XFS_AG_RESV_METAFILE); + fsbno = xfs_agbno_to_fsb(sc->sa.pag, agbno); /* @@ -406,7 +413,8 @@ xreap_agextent_iter( * to run xfs_repair. */ if (crosslinked) { - trace_xreap_dispose_unmap_extent(sc->sa.pag, agbno, *aglenp); + trace_xreap_dispose_unmap_extent(pag_group(sc->sa.pag), agbno, + *aglenp); rs->force_roll = true; @@ -416,7 +424,8 @@ xreap_agextent_iter( * records from the refcountbt, which will remove the * rmap record as well. */ - xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp); + xfs_refcount_free_cow_extent(sc->tp, false, fsbno, + *aglenp); return 0; } @@ -424,7 +433,7 @@ xreap_agextent_iter( *aglenp, rs->oinfo); } - trace_xreap_dispose_free_extent(sc->sa.pag, agbno, *aglenp); + trace_xreap_dispose_free_extent(pag_group(sc->sa.pag), agbno, *aglenp); /* * Invalidate as many buffers as we can, starting at agbno. If this @@ -448,7 +457,7 @@ xreap_agextent_iter( if (rs->oinfo == &XFS_RMAP_OINFO_COW) { ASSERT(rs->resv == XFS_AG_RESV_NONE); - xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp); + xfs_refcount_free_cow_extent(sc->tp, false, fsbno, *aglenp); error = xfs_free_extent_later(sc->tp, fsbno, *aglenp, NULL, rs->resv, XFS_FREE_EXTENT_SKIP_DISCARD); if (error) @@ -675,6 +684,263 @@ xrep_reap_fsblocks( return 0; } +#ifdef CONFIG_XFS_RT +/* + * Figure out the longest run of blocks that we can dispose of with a single + * call. Cross-linked blocks should have their reverse mappings removed, but + * single-owner extents can be freed. Units are rt blocks, not rt extents. + */ +STATIC int +xreap_rgextent_select( + struct xreap_state *rs, + xfs_rgblock_t rgbno, + xfs_rgblock_t rgbno_next, + bool *crosslinked, + xfs_extlen_t *rglenp) +{ + struct xfs_scrub *sc = rs->sc; + struct xfs_btree_cur *cur; + xfs_rgblock_t bno = rgbno + 1; + xfs_extlen_t len = 1; + int error; + + /* + * Determine if there are any other rmap records covering the first + * block of this extent. If so, the block is crosslinked. + */ + cur = xfs_rtrmapbt_init_cursor(sc->tp, sc->sr.rtg); + error = xfs_rmap_has_other_keys(cur, rgbno, 1, rs->oinfo, + crosslinked); + if (error) + goto out_cur; + + /* + * Figure out how many of the subsequent blocks have the same crosslink + * status. + */ + while (bno < rgbno_next) { + bool also_crosslinked; + + error = xfs_rmap_has_other_keys(cur, bno, 1, rs->oinfo, + &also_crosslinked); + if (error) + goto out_cur; + + if (*crosslinked != also_crosslinked) + break; + + len++; + bno++; + } + + *rglenp = len; + trace_xreap_agextent_select(rtg_group(sc->sr.rtg), rgbno, len, + *crosslinked); +out_cur: + xfs_btree_del_cursor(cur, error); + return error; +} + +/* + * Dispose of as much of the beginning of this rtgroup extent as possible. + * The number of blocks disposed of will be returned in @rglenp. + */ +STATIC int +xreap_rgextent_iter( + struct xreap_state *rs, + xfs_rgblock_t rgbno, + xfs_extlen_t *rglenp, + bool crosslinked) +{ + struct xfs_scrub *sc = rs->sc; + xfs_rtblock_t rtbno; + int error; + + /* + * The only caller so far is CoW fork repair, so we only know how to + * unlink or free CoW staging extents. Here we don't have to worry + * about invalidating buffers! + */ + if (rs->oinfo != &XFS_RMAP_OINFO_COW) { + ASSERT(rs->oinfo == &XFS_RMAP_OINFO_COW); + return -EFSCORRUPTED; + } + ASSERT(rs->resv == XFS_AG_RESV_NONE); + + rtbno = xfs_rgbno_to_rtb(sc->sr.rtg, rgbno); + + /* + * If there are other rmappings, this block is cross linked and must + * not be freed. Remove the forward and reverse mapping and move on. + */ + if (crosslinked) { + trace_xreap_dispose_unmap_extent(rtg_group(sc->sr.rtg), rgbno, + *rglenp); + + xfs_refcount_free_cow_extent(sc->tp, true, rtbno, *rglenp); + rs->deferred++; + return 0; + } + + trace_xreap_dispose_free_extent(rtg_group(sc->sr.rtg), rgbno, *rglenp); + + /* + * The CoW staging extent is not crosslinked. Use deferred work items + * to remove the refcountbt records (which removes the rmap records) + * and free the extent. We're not worried about the system going down + * here because log recovery walks the refcount btree to clean out the + * CoW staging extents. + */ + xfs_refcount_free_cow_extent(sc->tp, true, rtbno, *rglenp); + error = xfs_free_extent_later(sc->tp, rtbno, *rglenp, NULL, + rs->resv, + XFS_FREE_EXTENT_REALTIME | + XFS_FREE_EXTENT_SKIP_DISCARD); + if (error) + return error; + + rs->deferred++; + return 0; +} + +#define XREAP_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) + +/* + * Break a rt file metadata extent into sub-extents by fate (crosslinked, not + * crosslinked), and dispose of each sub-extent separately. The extent must + * be aligned to a realtime extent. + */ +STATIC int +xreap_rtmeta_extent( + uint64_t rtbno, + uint64_t len, + void *priv) +{ + struct xreap_state *rs = priv; + struct xfs_scrub *sc = rs->sc; + xfs_rgblock_t rgbno = xfs_rtb_to_rgbno(sc->mp, rtbno); + xfs_rgblock_t rgbno_next = rgbno + len; + int error = 0; + + ASSERT(sc->ip != NULL); + ASSERT(!sc->sr.rtg); + + /* + * We're reaping blocks after repairing file metadata, which means that + * we have to init the xchk_ag structure ourselves. + */ + sc->sr.rtg = xfs_rtgroup_get(sc->mp, xfs_rtb_to_rgno(sc->mp, rtbno)); + if (!sc->sr.rtg) + return -EFSCORRUPTED; + + xfs_rtgroup_lock(sc->sr.rtg, XREAP_RTGLOCK_ALL); + + while (rgbno < rgbno_next) { + xfs_extlen_t rglen; + bool crosslinked; + + error = xreap_rgextent_select(rs, rgbno, rgbno_next, + &crosslinked, &rglen); + if (error) + goto out_unlock; + + error = xreap_rgextent_iter(rs, rgbno, &rglen, crosslinked); + if (error) + goto out_unlock; + + if (xreap_want_defer_finish(rs)) { + error = xfs_defer_finish(&sc->tp); + if (error) + goto out_unlock; + xreap_defer_finish_reset(rs); + } else if (xreap_want_roll(rs)) { + error = xfs_trans_roll_inode(&sc->tp, sc->ip); + if (error) + goto out_unlock; + xreap_reset(rs); + } + + rgbno += rglen; + } + +out_unlock: + xfs_rtgroup_unlock(sc->sr.rtg, XREAP_RTGLOCK_ALL); + xfs_rtgroup_put(sc->sr.rtg); + sc->sr.rtg = NULL; + return error; +} + +/* + * Dispose of every block of every rt metadata extent in the bitmap. + * Do not use this to dispose of the mappings in an ondisk inode fork. + */ +int +xrep_reap_rtblocks( + struct xfs_scrub *sc, + struct xrtb_bitmap *bitmap, + const struct xfs_owner_info *oinfo) +{ + struct xreap_state rs = { + .sc = sc, + .oinfo = oinfo, + .resv = XFS_AG_RESV_NONE, + }; + int error; + + ASSERT(xfs_has_rmapbt(sc->mp)); + ASSERT(sc->ip != NULL); + + error = xrtb_bitmap_walk(bitmap, xreap_rtmeta_extent, &rs); + if (error) + return error; + + if (xreap_dirty(&rs)) + return xrep_defer_finish(sc); + + return 0; +} +#endif /* CONFIG_XFS_RT */ + +/* + * Dispose of every block of an old metadata btree that used to be rooted in a + * metadata directory file. + */ +int +xrep_reap_metadir_fsblocks( + struct xfs_scrub *sc, + struct xfsb_bitmap *bitmap) +{ + /* + * Reap old metadir btree blocks with XFS_AG_RESV_NONE because the old + * blocks are no longer mapped by the inode, and inode metadata space + * reservations can only account freed space to the i_nblocks. + */ + struct xfs_owner_info oinfo; + struct xreap_state rs = { + .sc = sc, + .oinfo = &oinfo, + .resv = XFS_AG_RESV_NONE, + }; + int error; + + ASSERT(xfs_has_rmapbt(sc->mp)); + ASSERT(sc->ip != NULL); + ASSERT(xfs_is_metadir_inode(sc->ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, XFS_DATA_FORK); + + error = xfsb_bitmap_walk(bitmap, xreap_fsmeta_extent, &rs); + if (error) + return error; + + if (xreap_dirty(&rs)) + return xrep_defer_finish(sc); + + return 0; +} + /* * Metadata files are not supposed to share blocks with anything else. * If blocks are shared, we remove the reverse mapping (thus reducing the @@ -729,7 +995,8 @@ xreap_bmapi_select( } imap->br_blockcount = len; - trace_xreap_bmapi_select(sc->sa.pag, agbno, len, *crosslinked); + trace_xreap_bmapi_select(pag_group(sc->sa.pag), agbno, len, + *crosslinked); out_cur: xfs_btree_del_cursor(cur, error); return error; @@ -868,7 +1135,8 @@ xreap_bmapi_binval( } out: - trace_xreap_bmapi_binval(sc->sa.pag, agbno, imap->br_blockcount); + trace_xreap_bmapi_binval(pag_group(sc->sa.pag), agbno, + imap->br_blockcount); return 0; } @@ -895,7 +1163,7 @@ xrep_reap_bmapi_iter( * anybody else who thinks they own the block, even though that * runs the risk of stale buffer warnings in the future. */ - trace_xreap_dispose_unmap_extent(sc->sa.pag, + trace_xreap_dispose_unmap_extent(pag_group(sc->sa.pag), XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock), imap->br_blockcount); @@ -918,7 +1186,7 @@ xrep_reap_bmapi_iter( * by a block starting before the first block of the extent but overlap * anyway. */ - trace_xreap_dispose_free_extent(sc->sa.pag, + trace_xreap_dispose_free_extent(pag_group(sc->sa.pag), XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock), imap->br_blockcount); diff --git a/fs/xfs/scrub/reap.h b/fs/xfs/scrub/reap.h index 3f2f1775e29d..4c8f62701fb3 100644 --- a/fs/xfs/scrub/reap.h +++ b/fs/xfs/scrub/reap.h @@ -14,6 +14,15 @@ int xrep_reap_agblocks(struct xfs_scrub *sc, struct xagb_bitmap *bitmap, int xrep_reap_fsblocks(struct xfs_scrub *sc, struct xfsb_bitmap *bitmap, const struct xfs_owner_info *oinfo); int xrep_reap_ifork(struct xfs_scrub *sc, struct xfs_inode *ip, int whichfork); +int xrep_reap_metadir_fsblocks(struct xfs_scrub *sc, + struct xfsb_bitmap *bitmap); + +#ifdef CONFIG_XFS_RT +int xrep_reap_rtblocks(struct xfs_scrub *sc, struct xrtb_bitmap *bitmap, + const struct xfs_owner_info *oinfo); +#else +# define xrep_reap_rtblocks(...) (-EOPNOTSUPP) +#endif /* CONFIG_XFS_RT */ /* Buffer cache scan context. */ struct xrep_bufscan { diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 1c5e45cc6419..d46528023015 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -421,7 +421,7 @@ xchk_refcount_mergeable( if (r1->rc_refcount != r2->rc_refcount) return false; if ((unsigned long long)r1->rc_blockcount + r2->rc_blockcount > - MAXREFCEXTLEN) + XFS_REFC_LEN_MAX) return false; return true; diff --git a/fs/xfs/scrub/refcount_repair.c b/fs/xfs/scrub/refcount_repair.c index 4e572b81c986..9c8cb5332da0 100644 --- a/fs/xfs/scrub/refcount_repair.c +++ b/fs/xfs/scrub/refcount_repair.c @@ -183,13 +183,13 @@ xrep_refc_stash( if (xchk_should_terminate(sc, &error)) return error; - irec.rc_refcount = min_t(uint64_t, MAXREFCOUNT, refcount); + irec.rc_refcount = min_t(uint64_t, XFS_REFC_REFCOUNT_MAX, refcount); error = xrep_refc_check_ext(rr->sc, &irec); if (error) return error; - trace_xrep_refc_found(sc->sa.pag, &irec); + trace_xrep_refc_found(pag_group(sc->sa.pag), &irec); return xfarray_append(rr->refcount_records, &irec); } @@ -422,7 +422,7 @@ xrep_refc_find_refcounts( /* * Set up a bag to store all the rmap records that we're tracking to * generate a reference count record. If the size of the bag exceeds - * MAXREFCOUNT, we clamp rc_refcount. + * XFS_REFC_REFCOUNT_MAX, we clamp rc_refcount. */ error = rcbag_init(sc->mp, sc->xmbtp, &rcstack); if (error) diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 91c8bc055a4f..3b5288d3ef4e 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -37,6 +37,12 @@ #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_dir2.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" +#include "xfs_rtalloc.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -62,6 +68,7 @@ xrep_attempt( trace_xrep_attempt(XFS_I(file_inode(sc->file)), sc->sm, error); xchk_ag_btcur_free(&sc->sa); + xchk_rtgroup_btcur_free(&sc->sr); /* Repair whatever's broken. */ ASSERT(sc->ops->repair); @@ -378,6 +385,41 @@ xrep_calc_ag_resblks( return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz)); } +#ifdef CONFIG_XFS_RT +/* + * Figure out how many blocks to reserve for a rtgroup repair. We calculate + * the worst case estimate for the number of blocks we'd need to rebuild one of + * any type of per-rtgroup btree. + */ +xfs_extlen_t +xrep_calc_rtgroup_resblks( + struct xfs_scrub *sc) +{ + struct xfs_mount *mp = sc->mp; + struct xfs_scrub_metadata *sm = sc->sm; + uint64_t usedlen; + xfs_extlen_t rmapbt_sz = 0; + + if (!(sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)) + return 0; + if (!xfs_has_rtgroups(mp)) { + ASSERT(0); + return -EFSCORRUPTED; + } + + usedlen = xfs_rtbxlen_to_blen(mp, xfs_rtgroup_extents(mp, sm->sm_agno)); + ASSERT(usedlen <= XFS_MAX_RGBLOCKS); + + if (xfs_has_rmapbt(mp)) + rmapbt_sz = xfs_rtrmapbt_calc_size(mp, usedlen); + + trace_xrep_calc_rtgroup_resblks_btsize(mp, sm->sm_agno, usedlen, + rmapbt_sz); + + return rmapbt_sz; +} +#endif /* CONFIG_XFS_RT */ + /* * Reconstructing per-AG Btrees * @@ -954,6 +996,27 @@ xrep_ag_init( } #ifdef CONFIG_XFS_RT +/* Initialize all the btree cursors for a RT repair. */ +void +xrep_rtgroup_btcur_init( + struct xfs_scrub *sc, + struct xchk_rt *sr) +{ + struct xfs_mount *mp = sc->mp; + + ASSERT(sr->rtg != NULL); + + if (sc->sm->sm_type != XFS_SCRUB_TYPE_RTRMAPBT && + (sr->rtlock_flags & XFS_RTGLOCK_RMAP) && + xfs_has_rtrmapbt(mp)) + sr->rmap_cur = xfs_rtrmapbt_init_cursor(sc->tp, sr->rtg); + + if (sc->sm->sm_type != XFS_SCRUB_TYPE_RTREFCBT && + (sr->rtlock_flags & XFS_RTGLOCK_REFCOUNT) && + xfs_has_rtreflink(mp)) + sr->refc_cur = xfs_rtrefcountbt_init_cursor(sc->tp, sr->rtg); +} + /* * Given a reference to a rtgroup structure, lock rtgroup btree inodes and * create btree cursors. Must only be called to repair a regular rt file. @@ -972,6 +1035,33 @@ xrep_rtgroup_init( /* Grab our own passive reference from the caller's ref. */ sr->rtg = xfs_rtgroup_hold(rtg); + xrep_rtgroup_btcur_init(sc, sr); + return 0; +} + +/* Ensure that all rt blocks in the given range are not marked free. */ +int +xrep_require_rtext_inuse( + struct xfs_scrub *sc, + xfs_rgblock_t rgbno, + xfs_filblks_t len) +{ + struct xfs_mount *mp = sc->mp; + xfs_rtxnum_t startrtx; + xfs_rtxnum_t endrtx; + bool is_free = false; + int error; + + startrtx = xfs_rgbno_to_rtx(mp, rgbno); + endrtx = xfs_rgbno_to_rtx(mp, rgbno + len - 1); + + error = xfs_rtalloc_extent_is_free(sc->sr.rtg, sc->tp, startrtx, + endrtx - startrtx + 1, &is_free); + if (error) + return error; + if (is_free) + return -EFSCORRUPTED; + return 0; } #endif /* CONFIG_XFS_RT */ @@ -1237,3 +1327,110 @@ xrep_buf_verify_struct( return fa == NULL; } + +/* Check the sanity of a rmap record for a metadata btree inode. */ +int +xrep_check_ino_btree_mapping( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *rec) +{ + enum xbtree_recpacking outcome; + int error; + + /* + * Metadata btree inodes never have extended attributes, and all blocks + * should have the bmbt block flag set. + */ + if ((rec->rm_flags & XFS_RMAP_ATTR_FORK) || + !(rec->rm_flags & XFS_RMAP_BMBT_BLOCK)) + return -EFSCORRUPTED; + + /* Make sure the block is within the AG. */ + if (!xfs_verify_agbext(sc->sa.pag, rec->rm_startblock, + rec->rm_blockcount)) + return -EFSCORRUPTED; + + /* Make sure this isn't free space. */ + error = xfs_alloc_has_records(sc->sa.bno_cur, rec->rm_startblock, + rec->rm_blockcount, &outcome); + if (error) + return error; + if (outcome != XBTREE_RECPACKING_EMPTY) + return -EFSCORRUPTED; + + return 0; +} + +/* + * Reset the block count of the inode being repaired, and adjust the dquot + * block usage to match. The inode must not have an xattr fork. + */ +void +xrep_inode_set_nblocks( + struct xfs_scrub *sc, + int64_t new_blocks) +{ + int64_t delta = + new_blocks - sc->ip->i_nblocks; + + sc->ip->i_nblocks = new_blocks; + + xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE); + if (delta != 0) + xfs_trans_mod_dquot_byino(sc->tp, sc->ip, XFS_TRANS_DQ_BCOUNT, + delta); +} + +/* Reset the block reservation for a metadata inode. */ +int +xrep_reset_metafile_resv( + struct xfs_scrub *sc) +{ + struct xfs_inode *ip = sc->ip; + int64_t delta; + int error; + + delta = ip->i_nblocks + ip->i_delayed_blks - ip->i_meta_resv_asked; + if (delta == 0) + return 0; + + /* + * Too many blocks have been reserved, transfer some from the incore + * reservation back to the filesystem. + */ + if (delta > 0) { + int64_t give_back; + + give_back = min_t(uint64_t, delta, ip->i_delayed_blks); + if (give_back > 0) { + xfs_mod_delalloc(ip, 0, -give_back); + xfs_add_fdblocks(ip->i_mount, give_back); + ip->i_delayed_blks -= give_back; + } + + return 0; + } + + /* + * Not enough reservation; try to take some blocks from the filesystem + * to the metadata inode. @delta is negative here, so invert the sign. + */ + delta = -delta; + error = xfs_dec_fdblocks(sc->mp, delta, true); + while (error == -ENOSPC) { + delta--; + if (delta == 0) { + xfs_warn(sc->mp, +"Insufficient free space to reset space reservation for inode 0x%llx after repair.", + ip->i_ino); + return 0; + } + error = xfs_dec_fdblocks(sc->mp, delta, true); + } + if (error) + return error; + + xfs_mod_delalloc(ip, 0, delta); + ip->i_delayed_blks += delta; + return 0; +} diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index b649da1a93eb..823c00d1a502 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -50,7 +50,9 @@ xrep_trans_commit( struct xbitmap; struct xagb_bitmap; +struct xrgb_bitmap; struct xfsb_bitmap; +struct xrtb_bitmap; int xrep_fix_freelist(struct xfs_scrub *sc, int alloc_flags); @@ -97,6 +99,8 @@ int xrep_setup_parent(struct xfs_scrub *sc); int xrep_setup_nlinks(struct xfs_scrub *sc); int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *resblks); int xrep_setup_dirtree(struct xfs_scrub *sc); +int xrep_setup_rtrmapbt(struct xfs_scrub *sc); +int xrep_setup_rtrefcountbt(struct xfs_scrub *sc); /* Repair setup functions */ int xrep_setup_ag_allocbt(struct xfs_scrub *sc); @@ -110,10 +114,18 @@ int xrep_ag_init(struct xfs_scrub *sc, struct xfs_perag *pag, #ifdef CONFIG_XFS_RT int xrep_rtgroup_init(struct xfs_scrub *sc, struct xfs_rtgroup *rtg, struct xchk_rt *sr, unsigned int rtglock_flags); +void xrep_rtgroup_btcur_init(struct xfs_scrub *sc, struct xchk_rt *sr); +int xrep_require_rtext_inuse(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_filblks_t len); +xfs_extlen_t xrep_calc_rtgroup_resblks(struct xfs_scrub *sc); #else # define xrep_rtgroup_init(sc, rtg, sr, lockflags) (-ENOSYS) +# define xrep_calc_rtgroup_resblks(sc) (0) #endif /* CONFIG_XFS_RT */ +int xrep_check_ino_btree_mapping(struct xfs_scrub *sc, + const struct xfs_rmap_irec *rec); + /* Metadata revalidators */ int xrep_revalidate_allocbt(struct xfs_scrub *sc); @@ -147,10 +159,14 @@ int xrep_metapath(struct xfs_scrub *sc); int xrep_rtbitmap(struct xfs_scrub *sc); int xrep_rtsummary(struct xfs_scrub *sc); int xrep_rgsuperblock(struct xfs_scrub *sc); +int xrep_rtrmapbt(struct xfs_scrub *sc); +int xrep_rtrefcountbt(struct xfs_scrub *sc); #else # define xrep_rtbitmap xrep_notsupported # define xrep_rtsummary xrep_notsupported # define xrep_rgsuperblock xrep_notsupported +# define xrep_rtrmapbt xrep_notsupported +# define xrep_rtrefcountbt xrep_notsupported #endif /* CONFIG_XFS_RT */ #ifdef CONFIG_XFS_QUOTA @@ -169,6 +185,8 @@ int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep, void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp); bool xrep_buf_verify_struct(struct xfs_buf *bp, const struct xfs_buf_ops *ops); +void xrep_inode_set_nblocks(struct xfs_scrub *sc, int64_t new_blocks); +int xrep_reset_metafile_resv(struct xfs_scrub *sc); #else @@ -192,6 +210,8 @@ xrep_calc_ag_resblks( return 0; } +#define xrep_calc_rtgroup_resblks xrep_calc_ag_resblks + static inline int xrep_reset_perag_resv( struct xfs_scrub *sc) @@ -219,6 +239,8 @@ xrep_setup_nothing( #define xrep_setup_nlinks xrep_setup_nothing #define xrep_setup_dirtree xrep_setup_nothing #define xrep_setup_metapath xrep_setup_nothing +#define xrep_setup_rtrmapbt xrep_setup_nothing +#define xrep_setup_rtrefcountbt xrep_setup_nothing #define xrep_setup_inode(sc, imap) ((void)0) @@ -256,6 +278,8 @@ static inline int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *x) #define xrep_dirtree xrep_notsupported #define xrep_metapath xrep_notsupported #define xrep_rgsuperblock xrep_notsupported +#define xrep_rtrmapbt xrep_notsupported +#define xrep_rtrefcountbt xrep_notsupported #endif /* CONFIG_XFS_ONLINE_REPAIR */ diff --git a/fs/xfs/scrub/rgb_bitmap.h b/fs/xfs/scrub/rgb_bitmap.h new file mode 100644 index 000000000000..4c3126b66dcb --- /dev/null +++ b/fs/xfs/scrub/rgb_bitmap.h @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2020-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#ifndef __XFS_SCRUB_RGB_BITMAP_H__ +#define __XFS_SCRUB_RGB_BITMAP_H__ + +/* Bitmaps, but for type-checked for xfs_rgblock_t */ + +struct xrgb_bitmap { + struct xbitmap32 rgbitmap; +}; + +static inline void xrgb_bitmap_init(struct xrgb_bitmap *bitmap) +{ + xbitmap32_init(&bitmap->rgbitmap); +} + +static inline void xrgb_bitmap_destroy(struct xrgb_bitmap *bitmap) +{ + xbitmap32_destroy(&bitmap->rgbitmap); +} + +static inline int xrgb_bitmap_set(struct xrgb_bitmap *bitmap, + xfs_rgblock_t start, xfs_extlen_t len) +{ + return xbitmap32_set(&bitmap->rgbitmap, start, len); +} + +static inline int xrgb_bitmap_walk(struct xrgb_bitmap *bitmap, + xbitmap32_walk_fn fn, void *priv) +{ + return xbitmap32_walk(&bitmap->rgbitmap, fn, priv); +} + +#endif /* __XFS_SCRUB_RGB_BITMAP_H__ */ diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c index 463b3573bb76..d189732d0e24 100644 --- a/fs/xfs/scrub/rgsuper.c +++ b/fs/xfs/scrub/rgsuper.c @@ -13,6 +13,7 @@ #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_sb.h" +#include "xfs_rmap.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/repair.h" @@ -34,6 +35,7 @@ xchk_rgsuperblock_xref( return; xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), 1); + xchk_xref_is_only_rt_owned_by(sc, 0, 1, &XFS_RMAP_OINFO_FS); } int @@ -61,7 +63,9 @@ xchk_rgsuperblock( if (!xchk_xref_process_error(sc, 0, 0, &error)) return error; - xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP_SHARED); + error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP_SHARED); + if (error) + return error; /* * Since we already validated the rt superblock at mount time, we don't diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c index a0a227d183d2..f5f73078ffe2 100644 --- a/fs/xfs/scrub/rmap_repair.c +++ b/fs/xfs/scrub/rmap_repair.c @@ -31,6 +31,9 @@ #include "xfs_refcount.h" #include "xfs_refcount_btree.h" #include "xfs_ag.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -499,6 +502,69 @@ xrep_rmap_scan_iext( return xrep_rmap_stash_accumulated(rf); } +static int +xrep_rmap_scan_meta_btree( + struct xrep_rmap_ifork *rf, + struct xfs_inode *ip) +{ + struct xfs_scrub *sc = rf->rr->sc; + struct xfs_rtgroup *rtg = NULL; + struct xfs_btree_cur *cur = NULL; + enum xfs_rtg_inodes type; + int error; + + if (rf->whichfork != XFS_DATA_FORK) + return -EFSCORRUPTED; + + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + type = XFS_RTGI_RMAP; + break; + case XFS_METAFILE_RTREFCOUNT: + type = XFS_RTGI_REFCOUNT; + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) { + if (ip == rtg->rtg_inodes[type]) + goto found; + } + + /* + * We should never find an rt metadata btree inode that isn't + * associated with an rtgroup yet has ondisk blocks allocated to it. + */ + if (ip->i_nblocks) { + ASSERT(0); + return -EFSCORRUPTED; + } + + return 0; + +found: + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + cur = xfs_rtrmapbt_init_cursor(sc->tp, rtg); + break; + case XFS_METAFILE_RTREFCOUNT: + cur = xfs_rtrefcountbt_init_cursor(sc->tp, rtg); + break; + default: + ASSERT(0); + error = -EFSCORRUPTED; + goto out_rtg; + } + + error = xrep_rmap_scan_iroot_btree(rf, cur); + xfs_btree_del_cursor(cur, error); +out_rtg: + xfs_rtgroup_rele(rtg); + return error; +} + /* Find all the extents from a given AG in an inode fork. */ STATIC int xrep_rmap_scan_ifork( @@ -512,14 +578,14 @@ xrep_rmap_scan_ifork( .whichfork = whichfork, }; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + bool mappings_done; int error = 0; if (!ifp) return 0; - if (ifp->if_format == XFS_DINODE_FMT_BTREE) { - bool mappings_done; - + switch (ifp->if_format) { + case XFS_DINODE_FMT_BTREE: /* * Scan the bmap btree for data device mappings. This includes * the btree blocks themselves, even if this is a realtime @@ -528,15 +594,18 @@ xrep_rmap_scan_ifork( error = xrep_rmap_scan_bmbt(&rf, ip, &mappings_done); if (error || mappings_done) return error; - } else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) { - return 0; + fallthrough; + case XFS_DINODE_FMT_EXTENTS: + /* Scan incore extent cache if this isn't a realtime file. */ + if (xfs_ifork_is_realtime(ip, whichfork)) + return 0; + + return xrep_rmap_scan_iext(&rf, ifp); + case XFS_DINODE_FMT_META_BTREE: + return xrep_rmap_scan_meta_btree(&rf, ip); } - /* Scan incore extent cache if this isn't a realtime file. */ - if (xfs_ifork_is_realtime(ip, whichfork)) - return 0; - - return xrep_rmap_scan_iext(&rf, ifp); + return 0; } /* @@ -1552,7 +1621,7 @@ xrep_rmapbt_live_update( if (!xrep_rmapbt_want_live_update(&rr->iscan, &p->oinfo)) goto out_unlock; - trace_xrep_rmap_live_update(rr->sc->sa.pag, action, p); + trace_xrep_rmap_live_update(pag_group(rr->sc->sa.pag), action, p); error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp); if (error) diff --git a/fs/xfs/scrub/rtb_bitmap.h b/fs/xfs/scrub/rtb_bitmap.h new file mode 100644 index 000000000000..1313ef605511 --- /dev/null +++ b/fs/xfs/scrub/rtb_bitmap.h @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2022-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#ifndef __XFS_SCRUB_RTB_BITMAP_H__ +#define __XFS_SCRUB_RTB_BITMAP_H__ + +/* Bitmaps, but for type-checked for xfs_rtblock_t */ + +struct xrtb_bitmap { + struct xbitmap64 rtbitmap; +}; + +static inline void xrtb_bitmap_init(struct xrtb_bitmap *bitmap) +{ + xbitmap64_init(&bitmap->rtbitmap); +} + +static inline void xrtb_bitmap_destroy(struct xrtb_bitmap *bitmap) +{ + xbitmap64_destroy(&bitmap->rtbitmap); +} + +static inline int xrtb_bitmap_set(struct xrtb_bitmap *bitmap, + xfs_rtblock_t start, xfs_filblks_t len) +{ + return xbitmap64_set(&bitmap->rtbitmap, start, len); +} + +static inline int xrtb_bitmap_walk(struct xrtb_bitmap *bitmap, + xbitmap64_walk_fn fn, void *priv) +{ + return xbitmap64_walk(&bitmap->rtbitmap, fn, priv); +} + +#endif /* __XFS_SCRUB_RTB_BITMAP_H__ */ diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c index 376a36fd9a9c..e8c776a34c1d 100644 --- a/fs/xfs/scrub/rtbitmap.c +++ b/fs/xfs/scrub/rtbitmap.c @@ -9,17 +9,24 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" +#include "xfs_btree.h" #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_rtbitmap.h" #include "xfs_inode.h" #include "xfs_bmap.h" #include "xfs_bit.h" +#include "xfs_rtgroup.h" #include "xfs_sb.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_exchmaps.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/repair.h" +#include "scrub/tempexch.h" #include "scrub/rtbitmap.h" +#include "scrub/btree.h" /* Set us up with the realtime metadata locked. */ int @@ -30,10 +37,15 @@ xchk_setup_rtbitmap( struct xchk_rtbitmap *rtb; int error; - rtb = kzalloc(sizeof(struct xchk_rtbitmap), XCHK_GFP_FLAGS); + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + + rtb = kzalloc(struct_size(rtb, words, xchk_rtbitmap_wordcnt(sc)), + XCHK_GFP_FLAGS); if (!rtb) return -ENOMEM; sc->buf = rtb; + rtb->sc = sc; error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr); if (error) @@ -49,8 +61,7 @@ xchk_setup_rtbitmap( if (error) return error; - error = xchk_install_live_inode(sc, - sc->sr.rtg->rtg_inodes[XFS_RTGI_BITMAP]); + error = xchk_install_live_inode(sc, rtg_bitmap(sc->sr.rtg)); if (error) return error; @@ -58,12 +69,15 @@ xchk_setup_rtbitmap( if (error) return error; + error = xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); + if (error) + return error; + /* * Now that we've locked the rtbitmap, we can't race with growfsrt * trying to expand the bitmap or change the size of the rt volume. * Hence it is safe to compute and check the geometry values. */ - xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP); if (mp->m_sb.sb_rblocks) { rtb->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks); rtb->rextslog = xfs_compute_rextslog(rtb->rextents); @@ -73,7 +87,32 @@ xchk_setup_rtbitmap( return 0; } -/* Realtime bitmap. */ +/* Per-rtgroup bitmap contents. */ + +/* Cross-reference rtbitmap entries with other metadata. */ +STATIC void +xchk_rtbitmap_xref( + struct xchk_rtbitmap *rtb, + xfs_rtblock_t startblock, + xfs_rtblock_t blockcount) +{ + struct xfs_scrub *sc = rtb->sc; + xfs_rgblock_t rgbno = xfs_rtb_to_rgbno(sc->mp, startblock); + + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + if (!sc->sr.rmap_cur) + return; + + xchk_xref_has_no_rt_owner(sc, rgbno, blockcount); + xchk_xref_is_not_rt_shared(sc, rgbno, blockcount); + xchk_xref_is_not_rt_cow_staging(sc, rgbno, blockcount); + + if (rtb->next_free_rgbno < rgbno) + xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno, + rgbno - rtb->next_free_rgbno); + rtb->next_free_rgbno = rgbno + blockcount; +} /* Scrub a free extent record from the realtime bitmap. */ STATIC int @@ -83,7 +122,8 @@ xchk_rtbitmap_rec( const struct xfs_rtalloc_rec *rec, void *priv) { - struct xfs_scrub *sc = priv; + struct xchk_rtbitmap *rtb = priv; + struct xfs_scrub *sc = rtb->sc; xfs_rtblock_t startblock; xfs_filblks_t blockcount; @@ -92,6 +132,12 @@ xchk_rtbitmap_rec( if (!xfs_verify_rtbext(rtg_mount(rtg), startblock, blockcount)) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); + + xchk_rtbitmap_xref(rtb, startblock, blockcount); + + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return -ECANCELED; + return 0; } @@ -139,15 +185,16 @@ xchk_rtbitmap_check_extents( return error; } -/* Scrub the realtime bitmap. */ +/* Scrub this group's realtime bitmap. */ int xchk_rtbitmap( struct xfs_scrub *sc) { struct xfs_mount *mp = sc->mp; struct xfs_rtgroup *rtg = sc->sr.rtg; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); struct xchk_rtbitmap *rtb = sc->buf; + xfs_rgblock_t last_rgbno; int error; /* Is sb_rextents correct? */ @@ -200,10 +247,20 @@ xchk_rtbitmap( if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) return error; - error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, sc); + rtb->next_free_rgbno = 0; + error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, rtb); if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error)) return error; + /* + * Check that the are rmappings for all rt extents between the end of + * the last free extent we saw and the last possible extent in the rt + * group. + */ + last_rgbno = rtg->rtg_extents * mp->m_sb.sb_rextsize - 1; + if (rtb->next_free_rgbno < last_rgbno) + xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno, + last_rgbno - rtb->next_free_rgbno); return 0; } @@ -215,7 +272,7 @@ xchk_xref_is_used_rt_space( xfs_extlen_t len) { struct xfs_rtgroup *rtg = sc->sr.rtg; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); xfs_rtxnum_t startext; xfs_rtxnum_t endext; bool is_free; diff --git a/fs/xfs/scrub/rtbitmap.h b/fs/xfs/scrub/rtbitmap.h index 85304ff019e1..fe52b877253d 100644 --- a/fs/xfs/scrub/rtbitmap.h +++ b/fs/xfs/scrub/rtbitmap.h @@ -6,17 +6,72 @@ #ifndef __XFS_SCRUB_RTBITMAP_H__ #define __XFS_SCRUB_RTBITMAP_H__ +/* + * We use an xfile to construct new bitmap blocks for the portion of the + * rtbitmap file that we're replacing. Whereas the ondisk bitmap must be + * accessed through the buffer cache, the xfile bitmap supports direct + * word-level accesses. Therefore, we create a small abstraction for linear + * access. + */ +typedef unsigned long long xrep_wordoff_t; +typedef unsigned int xrep_wordcnt_t; + +/* Mask to round an rtx down to the nearest bitmap word. */ +#define XREP_RTBMP_WORDMASK ((1ULL << XFS_NBWORDLOG) - 1) + + struct xchk_rtbitmap { + struct xfs_scrub *sc; + uint64_t rextents; uint64_t rbmblocks; unsigned int rextslog; unsigned int resblks; + + /* The next free rt group block number that we expect to see. */ + xfs_rgblock_t next_free_rgbno; + +#ifdef CONFIG_XFS_ONLINE_REPAIR + /* stuff for staging a new bitmap */ + struct xfs_rtalloc_args args; + struct xrep_tempexch tempexch; +#endif + + /* The next rtgroup block we expect to see during our rtrmapbt walk. */ + xfs_rgblock_t next_rgbno; + + /* rtgroup lock flags */ + unsigned int rtglock_flags; + + /* rtword position of xfile as we write buffers to disk. */ + xrep_wordoff_t prep_wordoff; + + /* In-Memory rtbitmap for repair. */ + union xfs_rtword_raw words[]; }; #ifdef CONFIG_XFS_ONLINE_REPAIR int xrep_setup_rtbitmap(struct xfs_scrub *sc, struct xchk_rtbitmap *rtb); + +/* + * How big should the words[] buffer be? + * + * For repairs, we want a full fsblock worth of space so that we can memcpy a + * buffer full of 1s into the xfile bitmap. The xfile bitmap doesn't have + * rtbitmap block headers, so we don't use blockwsize. Scrub doesn't use the + * words buffer at all. + */ +static inline unsigned int +xchk_rtbitmap_wordcnt( + struct xfs_scrub *sc) +{ + if (xchk_could_repair(sc)) + return sc->mp->m_sb.sb_blocksize >> XFS_WORDLOG; + return 0; +} #else # define xrep_setup_rtbitmap(sc, rtb) (0) +# define xchk_rtbitmap_wordcnt(sc) (0) #endif /* CONFIG_XFS_ONLINE_REPAIR */ #endif /* __XFS_SCRUB_RTBITMAP_H__ */ diff --git a/fs/xfs/scrub/rtbitmap_repair.c b/fs/xfs/scrub/rtbitmap_repair.c index 0fef98e9f834..203a1a97c502 100644 --- a/fs/xfs/scrub/rtbitmap_repair.c +++ b/fs/xfs/scrub/rtbitmap_repair.c @@ -12,32 +12,66 @@ #include "xfs_btree.h" #include "xfs_log_format.h" #include "xfs_trans.h" +#include "xfs_rtalloc.h" #include "xfs_inode.h" #include "xfs_bit.h" #include "xfs_bmap.h" #include "xfs_bmap_btree.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_exchmaps.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" +#include "xfs_extent_busy.h" +#include "xfs_refcount.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" #include "scrub/repair.h" #include "scrub/xfile.h" +#include "scrub/tempfile.h" +#include "scrub/tempexch.h" +#include "scrub/reap.h" #include "scrub/rtbitmap.h" -/* Set up to repair the realtime bitmap file metadata. */ +/* rt bitmap content repairs */ + +/* Set up to repair the realtime bitmap for this group. */ int xrep_setup_rtbitmap( struct xfs_scrub *sc, struct xchk_rtbitmap *rtb) { struct xfs_mount *mp = sc->mp; - unsigned long long blocks = 0; + char *descr; + unsigned long long blocks = mp->m_sb.sb_rbmblocks; + int error; + + error = xrep_tempfile_create(sc, S_IFREG); + if (error) + return error; + + /* Create an xfile to hold our reconstructed bitmap. */ + descr = xchk_xfile_rtgroup_descr(sc, "bitmap file"); + error = xfile_create(descr, blocks * mp->m_sb.sb_blocksize, &sc->xfile); + kfree(descr); + if (error) + return error; /* - * Reserve enough blocks to write out a completely new bmbt for a - * maximally fragmented bitmap file. We do not hold the rtbitmap - * ILOCK yet, so this is entirely speculative. + * Reserve enough blocks to write out a completely new bitmap file, + * plus twice as many blocks as we would need if we can only allocate + * one block per data fork mapping. This should cover the + * preallocation of the temporary file and exchanging the extent + * mappings. + * + * We cannot use xfs_exchmaps_estimate because we have not yet + * constructed the replacement bitmap and therefore do not know how + * many extents it will use. By the time we do, we will have a dirty + * transaction (which we cannot drop because we cannot drop the + * rtbitmap ILOCK) and cannot ask for more reservation. */ - blocks = xfs_bmbt_calc_size(mp, mp->m_sb.sb_rbmblocks); + blocks += xfs_bmbt_calc_size(mp, blocks) * 2; if (blocks > UINT_MAX) return -EOPNOTSUPP; @@ -45,6 +79,325 @@ xrep_setup_rtbitmap( return 0; } +static inline xrep_wordoff_t +rtx_to_wordoff( + struct xfs_mount *mp, + xfs_rtxnum_t rtx) +{ + return rtx >> XFS_NBWORDLOG; +} + +static inline xrep_wordcnt_t +rtxlen_to_wordcnt( + xfs_rtxlen_t rtxlen) +{ + return rtxlen >> XFS_NBWORDLOG; +} + +/* Helper functions to record rtwords in an xfile. */ + +static inline int +xfbmp_load( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + xfs_rtword_t *word) +{ + union xfs_rtword_raw urk; + int error; + + ASSERT(xfs_has_rtgroups(rtb->sc->mp)); + + error = xfile_load(rtb->sc->xfile, &urk, + sizeof(union xfs_rtword_raw), + wordoff << XFS_WORDLOG); + if (error) + return error; + + *word = be32_to_cpu(urk.rtg); + return 0; +} + +static inline int +xfbmp_store( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + const xfs_rtword_t word) +{ + union xfs_rtword_raw urk; + + ASSERT(xfs_has_rtgroups(rtb->sc->mp)); + + urk.rtg = cpu_to_be32(word); + return xfile_store(rtb->sc->xfile, &urk, + sizeof(union xfs_rtword_raw), + wordoff << XFS_WORDLOG); +} + +static inline int +xfbmp_copyin( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + const union xfs_rtword_raw *word, + xrep_wordcnt_t nr_words) +{ + return xfile_store(rtb->sc->xfile, word, nr_words << XFS_WORDLOG, + wordoff << XFS_WORDLOG); +} + +static inline int +xfbmp_copyout( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + union xfs_rtword_raw *word, + xrep_wordcnt_t nr_words) +{ + return xfile_load(rtb->sc->xfile, word, nr_words << XFS_WORDLOG, + wordoff << XFS_WORDLOG); +} + +/* Perform a logical OR operation on an rtword in the incore bitmap. */ +static int +xrep_rtbitmap_or( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + xfs_rtword_t mask) +{ + xfs_rtword_t word; + int error; + + error = xfbmp_load(rtb, wordoff, &word); + if (error) + return error; + + trace_xrep_rtbitmap_or(rtb->sc->mp, wordoff, mask, word); + + return xfbmp_store(rtb, wordoff, word | mask); +} + +/* + * Mark as free every rt extent between the next rt block we expected to see + * in the rtrmap records and the given rt block. + */ +STATIC int +xrep_rtbitmap_mark_free( + struct xchk_rtbitmap *rtb, + xfs_rgblock_t rgbno) +{ + struct xfs_mount *mp = rtb->sc->mp; + struct xchk_rt *sr = &rtb->sc->sr; + struct xfs_rtgroup *rtg = sr->rtg; + xfs_rtxnum_t startrtx; + xfs_rtxnum_t nextrtx; + xrep_wordoff_t wordoff, nextwordoff; + unsigned int bit; + unsigned int bufwsize; + xfs_extlen_t mod; + xfs_rtword_t mask; + enum xbtree_recpacking outcome; + int error; + + if (!xfs_verify_rgbext(rtg, rtb->next_rgbno, rgbno - rtb->next_rgbno)) + return -EFSCORRUPTED; + + /* + * Convert rt blocks to rt extents The block range we find must be + * aligned to an rtextent boundary on both ends. + */ + startrtx = xfs_rgbno_to_rtx(mp, rtb->next_rgbno); + mod = xfs_rgbno_to_rtxoff(mp, rtb->next_rgbno); + if (mod) + return -EFSCORRUPTED; + + nextrtx = xfs_rgbno_to_rtx(mp, rgbno - 1) + 1; + mod = xfs_rgbno_to_rtxoff(mp, rgbno - 1); + if (mod != mp->m_sb.sb_rextsize - 1) + return -EFSCORRUPTED; + + /* Must not be shared or CoW staging. */ + if (sr->refc_cur) { + error = xfs_refcount_has_records(sr->refc_cur, + XFS_REFC_DOMAIN_SHARED, rtb->next_rgbno, + rgbno - rtb->next_rgbno, &outcome); + if (error) + return error; + if (outcome != XBTREE_RECPACKING_EMPTY) + return -EFSCORRUPTED; + + error = xfs_refcount_has_records(sr->refc_cur, + XFS_REFC_DOMAIN_COW, rtb->next_rgbno, + rgbno - rtb->next_rgbno, &outcome); + if (error) + return error; + if (outcome != XBTREE_RECPACKING_EMPTY) + return -EFSCORRUPTED; + } + + trace_xrep_rtbitmap_record_free(mp, startrtx, nextrtx - 1); + + /* Set bits as needed to round startrtx up to the nearest word. */ + bit = startrtx & XREP_RTBMP_WORDMASK; + if (bit) { + xfs_rtblock_t len = nextrtx - startrtx; + unsigned int lastbit; + + lastbit = min(bit + len, XFS_NBWORD); + mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit; + + error = xrep_rtbitmap_or(rtb, rtx_to_wordoff(mp, startrtx), + mask); + if (error || lastbit - bit == len) + return error; + startrtx += XFS_NBWORD - bit; + } + + /* Set bits as needed to round nextrtx down to the nearest word. */ + bit = nextrtx & XREP_RTBMP_WORDMASK; + if (bit) { + mask = ((xfs_rtword_t)1 << bit) - 1; + + error = xrep_rtbitmap_or(rtb, rtx_to_wordoff(mp, nextrtx), + mask); + if (error || startrtx + bit == nextrtx) + return error; + nextrtx -= bit; + } + + trace_xrep_rtbitmap_record_free_bulk(mp, startrtx, nextrtx - 1); + + /* Set all the words in between, up to a whole fs block at once. */ + wordoff = rtx_to_wordoff(mp, startrtx); + nextwordoff = rtx_to_wordoff(mp, nextrtx); + bufwsize = mp->m_sb.sb_blocksize >> XFS_WORDLOG; + + while (wordoff < nextwordoff) { + xrep_wordoff_t rem; + xrep_wordcnt_t wordcnt; + + wordcnt = min_t(xrep_wordcnt_t, nextwordoff - wordoff, + bufwsize); + + /* + * Try to keep us aligned to the rtwords buffer to reduce the + * number of xfile writes. + */ + rem = wordoff & (bufwsize - 1); + if (rem) + wordcnt = min_t(xrep_wordcnt_t, wordcnt, + bufwsize - rem); + + error = xfbmp_copyin(rtb, wordoff, rtb->words, wordcnt); + if (error) + return error; + + wordoff += wordcnt; + } + + return 0; +} + +/* Set free space in the rtbitmap based on rtrmapbt records. */ +STATIC int +xrep_rtbitmap_walk_rtrmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xchk_rtbitmap *rtb = priv; + int error = 0; + + if (xchk_should_terminate(rtb->sc, &error)) + return error; + + if (rtb->next_rgbno < rec->rm_startblock) { + error = xrep_rtbitmap_mark_free(rtb, rec->rm_startblock); + if (error) + return error; + } + + rtb->next_rgbno = max(rtb->next_rgbno, + rec->rm_startblock + rec->rm_blockcount); + return 0; +} + +/* + * Walk the rtrmapbt to find all the gaps between records, and mark the gaps + * in the realtime bitmap that we're computing. + */ +STATIC int +xrep_rtbitmap_find_freespace( + struct xchk_rtbitmap *rtb) +{ + struct xfs_scrub *sc = rtb->sc; + struct xfs_mount *mp = sc->mp; + struct xfs_rtgroup *rtg = sc->sr.rtg; + uint64_t blockcount; + int error; + + /* Prepare a buffer of ones so that we can accelerate bulk setting. */ + memset(rtb->words, 0xFF, mp->m_sb.sb_blocksize); + + xrep_rtgroup_btcur_init(sc, &sc->sr); + error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_rtbitmap_walk_rtrmap, + rtb); + if (error) + goto out; + + /* + * Mark as free every possible rt extent from the last one we saw to + * the end of the rt group. + */ + blockcount = rtg->rtg_extents * mp->m_sb.sb_rextsize; + if (rtb->next_rgbno < blockcount) { + error = xrep_rtbitmap_mark_free(rtb, blockcount); + if (error) + goto out; + } + +out: + xchk_rtgroup_btcur_free(&sc->sr); + return error; +} + +static int +xrep_rtbitmap_prep_buf( + struct xfs_scrub *sc, + struct xfs_buf *bp, + void *data) +{ + struct xchk_rtbitmap *rtb = data; + struct xfs_mount *mp = sc->mp; + union xfs_rtword_raw *ondisk; + int error; + + rtb->args.mp = sc->mp; + rtb->args.tp = sc->tp; + rtb->args.rbmbp = bp; + ondisk = xfs_rbmblock_wordptr(&rtb->args, 0); + rtb->args.rbmbp = NULL; + + error = xfbmp_copyout(rtb, rtb->prep_wordoff, ondisk, + mp->m_blockwsize); + if (error) + return error; + + if (xfs_has_rtgroups(sc->mp)) { + struct xfs_rtbuf_blkinfo *hdr = bp->b_addr; + + hdr->rt_magic = cpu_to_be32(XFS_RTBITMAP_MAGIC); + hdr->rt_owner = cpu_to_be64(sc->ip->i_ino); + hdr->rt_blkno = cpu_to_be64(xfs_buf_daddr(bp)); + hdr->rt_lsn = 0; + uuid_copy(&hdr->rt_uuid, &sc->mp->m_sb.sb_meta_uuid); + bp->b_ops = &xfs_rtbitmap_buf_ops; + } else { + bp->b_ops = &xfs_rtbuf_ops; + } + + rtb->prep_wordoff += mp->m_blockwsize; + xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_RTBITMAP_BUF); + return 0; +} + /* * Make sure that the given range of the data fork of the realtime file is * mapped to written blocks. The caller must ensure that the inode is joined @@ -160,9 +513,18 @@ xrep_rtbitmap( { struct xchk_rtbitmap *rtb = sc->buf; struct xfs_mount *mp = sc->mp; + struct xfs_group *xg = rtg_group(sc->sr.rtg); unsigned long long blocks = 0; + unsigned int busy_gen; int error; + /* We require the realtime rmapbt to rebuild anything. */ + if (!xfs_has_rtrmapbt(sc->mp)) + return -EOPNOTSUPP; + /* We require atomic file exchange range to rebuild anything. */ + if (!xfs_has_exchange_range(sc->mp)) + return -EOPNOTSUPP; + /* Impossibly large rtbitmap means we can't touch the filesystem. */ if (rtb->rbmblocks > U32_MAX) return 0; @@ -195,6 +557,79 @@ xrep_rtbitmap( if (error) return error; - /* Fix inconsistent bitmap geometry */ - return xrep_rtbitmap_geometry(sc, rtb); + /* + * Fix inconsistent bitmap geometry. This function returns with a + * clean scrub transaction. + */ + error = xrep_rtbitmap_geometry(sc, rtb); + if (error) + return error; + + /* + * Make sure the busy extent list is clear because we can't put extents + * on there twice. + */ + if (!xfs_extent_busy_list_empty(xg, &busy_gen)) { + error = xfs_extent_busy_flush(sc->tp, xg, busy_gen, 0); + if (error) + return error; + } + + /* + * Generate the new rtbitmap data. We don't need the rtbmp information + * once this call is finished. + */ + error = xrep_rtbitmap_find_freespace(rtb); + if (error) + return error; + + /* + * Try to take ILOCK_EXCL of the temporary file. We had better be the + * only ones holding onto this inode, but we can't block while holding + * the rtbitmap file's ILOCK_EXCL. + */ + while (!xrep_tempfile_ilock_nowait(sc)) { + if (xchk_should_terminate(sc, &error)) + return error; + delay(1); + } + + /* + * Make sure we have space allocated for the part of the bitmap + * file that corresponds to this group. We already joined sc->ip. + */ + xfs_trans_ijoin(sc->tp, sc->tempip, 0); + error = xrep_tempfile_prealloc(sc, 0, rtb->rbmblocks); + if (error) + return error; + + /* Last chance to abort before we start committing fixes. */ + if (xchk_should_terminate(sc, &error)) + return error; + + /* Copy the bitmap file that we generated. */ + error = xrep_tempfile_copyin(sc, 0, rtb->rbmblocks, + xrep_rtbitmap_prep_buf, rtb); + if (error) + return error; + error = xrep_tempfile_set_isize(sc, + XFS_FSB_TO_B(sc->mp, sc->mp->m_sb.sb_rbmblocks)); + if (error) + return error; + + /* + * Now exchange the data fork contents. We're done with the temporary + * buffer, so we can reuse it for the tempfile exchmaps information. + */ + error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0, + rtb->rbmblocks, &rtb->tempexch); + if (error) + return error; + + error = xrep_tempexch_contents(sc, &rtb->tempexch); + if (error) + return error; + + /* Free the old rtbitmap blocks if they're not in use. */ + return xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK); } diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c new file mode 100644 index 000000000000..4c5dffc73641 --- /dev/null +++ b/fs/xfs/scrub/rtrefcount.c @@ -0,0 +1,661 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_trans.h" +#include "xfs_btree.h" +#include "xfs_rmap.h" +#include "xfs_refcount.h" +#include "xfs_inode.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_rtalloc.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/repair.h" + +/* Set us up with the realtime refcount metadata locked. */ +int +xchk_setup_rtrefcountbt( + struct xfs_scrub *sc) +{ + int error; + + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + + if (xchk_could_repair(sc)) { + error = xrep_setup_rtrefcountbt(sc); + if (error) + return error; + } + + error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr); + if (error) + return error; + + error = xchk_setup_rt(sc); + if (error) + return error; + + error = xchk_install_live_inode(sc, rtg_refcount(sc->sr.rtg)); + if (error) + return error; + + return xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); +} + +/* Realtime Reference count btree scrubber. */ + +/* + * Confirming Reference Counts via Reverse Mappings + * + * We want to count the reverse mappings overlapping a refcount record + * (bno, len, refcount), allowing for the possibility that some of the + * overlap may come from smaller adjoining reverse mappings, while some + * comes from single extents which overlap the range entirely. The + * outer loop is as follows: + * + * 1. For all reverse mappings overlapping the refcount extent, + * a. If a given rmap completely overlaps, mark it as seen. + * b. Otherwise, record the fragment (in agbno order) for later + * processing. + * + * Once we've seen all the rmaps, we know that for all blocks in the + * refcount record we want to find $refcount owners and we've already + * visited $seen extents that overlap all the blocks. Therefore, we + * need to find ($refcount - $seen) owners for every block in the + * extent; call that quantity $target_nr. Proceed as follows: + * + * 2. Pull the first $target_nr fragments from the list; all of them + * should start at or before the start of the extent. + * Call this subset of fragments the working set. + * 3. Until there are no more unprocessed fragments, + * a. Find the shortest fragments in the set and remove them. + * b. Note the block number of the end of these fragments. + * c. Pull the same number of fragments from the list. All of these + * fragments should start at the block number recorded in the + * previous step. + * d. Put those fragments in the set. + * 4. Check that there are $target_nr fragments remaining in the list, + * and that they all end at or beyond the end of the refcount extent. + * + * If the refcount is correct, all the check conditions in the algorithm + * should always hold true. If not, the refcount is incorrect. + */ +struct xchk_rtrefcnt_frag { + struct list_head list; + struct xfs_rmap_irec rm; +}; + +struct xchk_rtrefcnt_check { + struct xfs_scrub *sc; + struct list_head fragments; + + /* refcount extent we're examining */ + xfs_rgblock_t bno; + xfs_extlen_t len; + xfs_nlink_t refcount; + + /* number of owners seen */ + xfs_nlink_t seen; +}; + +/* + * Decide if the given rmap is large enough that we can redeem it + * towards refcount verification now, or if it's a fragment, in + * which case we'll hang onto it in the hopes that we'll later + * discover that we've collected exactly the correct number of + * fragments as the rtrefcountbt says we should have. + */ +STATIC int +xchk_rtrefcountbt_rmap_check( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xchk_rtrefcnt_check *refchk = priv; + struct xchk_rtrefcnt_frag *frag; + xfs_rgblock_t rm_last; + xfs_rgblock_t rc_last; + int error = 0; + + if (xchk_should_terminate(refchk->sc, &error)) + return error; + + rm_last = rec->rm_startblock + rec->rm_blockcount - 1; + rc_last = refchk->bno + refchk->len - 1; + + /* Confirm that a single-owner refc extent is a CoW stage. */ + if (refchk->refcount == 1 && rec->rm_owner != XFS_RMAP_OWN_COW) { + xchk_btree_xref_set_corrupt(refchk->sc, cur, 0); + return 0; + } + + if (rec->rm_startblock <= refchk->bno && rm_last >= rc_last) { + /* + * The rmap overlaps the refcount record, so we can confirm + * one refcount owner seen. + */ + refchk->seen++; + } else { + /* + * This rmap covers only part of the refcount record, so + * save the fragment for later processing. If the rmapbt + * is healthy each rmap_irec we see will be in agbno order + * so we don't need insertion sort here. + */ + frag = kmalloc(sizeof(struct xchk_rtrefcnt_frag), + XCHK_GFP_FLAGS); + if (!frag) + return -ENOMEM; + memcpy(&frag->rm, rec, sizeof(frag->rm)); + list_add_tail(&frag->list, &refchk->fragments); + } + + return 0; +} + +/* + * Given a bunch of rmap fragments, iterate through them, keeping + * a running tally of the refcount. If this ever deviates from + * what we expect (which is the rtrefcountbt's refcount minus the + * number of extents that totally covered the rtrefcountbt extent), + * we have a rtrefcountbt error. + */ +STATIC void +xchk_rtrefcountbt_process_rmap_fragments( + struct xchk_rtrefcnt_check *refchk) +{ + struct list_head worklist; + struct xchk_rtrefcnt_frag *frag; + struct xchk_rtrefcnt_frag *n; + xfs_rgblock_t bno; + xfs_rgblock_t rbno; + xfs_rgblock_t next_rbno; + xfs_nlink_t nr; + xfs_nlink_t target_nr; + + target_nr = refchk->refcount - refchk->seen; + if (target_nr == 0) + return; + + /* + * There are (refchk->rc.rc_refcount - refchk->nr refcount) + * references we haven't found yet. Pull that many off the + * fragment list and figure out where the smallest rmap ends + * (and therefore the next rmap should start). All the rmaps + * we pull off should start at or before the beginning of the + * refcount record's range. + */ + INIT_LIST_HEAD(&worklist); + rbno = NULLRGBLOCK; + + /* Make sure the fragments actually /are/ in bno order. */ + bno = 0; + list_for_each_entry(frag, &refchk->fragments, list) { + if (frag->rm.rm_startblock < bno) + goto done; + bno = frag->rm.rm_startblock; + } + + /* + * Find all the rmaps that start at or before the refc extent, + * and put them on the worklist. + */ + nr = 0; + list_for_each_entry_safe(frag, n, &refchk->fragments, list) { + if (frag->rm.rm_startblock > refchk->bno || nr > target_nr) + break; + bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; + if (bno < rbno) + rbno = bno; + list_move_tail(&frag->list, &worklist); + nr++; + } + + /* + * We should have found exactly $target_nr rmap fragments starting + * at or before the refcount extent. + */ + if (nr != target_nr) + goto done; + + while (!list_empty(&refchk->fragments)) { + /* Discard any fragments ending at rbno from the worklist. */ + nr = 0; + next_rbno = NULLRGBLOCK; + list_for_each_entry_safe(frag, n, &worklist, list) { + bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; + if (bno != rbno) { + if (bno < next_rbno) + next_rbno = bno; + continue; + } + list_del(&frag->list); + kfree(frag); + nr++; + } + + /* Try to add nr rmaps starting at rbno to the worklist. */ + list_for_each_entry_safe(frag, n, &refchk->fragments, list) { + bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; + if (frag->rm.rm_startblock != rbno) + goto done; + list_move_tail(&frag->list, &worklist); + if (next_rbno > bno) + next_rbno = bno; + nr--; + if (nr == 0) + break; + } + + /* + * If we get here and nr > 0, this means that we added fewer + * items to the worklist than we discarded because the fragment + * list ran out of items. Therefore, we cannot maintain the + * required refcount. Something is wrong, so we're done. + */ + if (nr) + goto done; + + rbno = next_rbno; + } + + /* + * Make sure the last extent we processed ends at or beyond + * the end of the refcount extent. + */ + if (rbno < refchk->bno + refchk->len) + goto done; + + /* Actually record us having seen the remaining refcount. */ + refchk->seen = refchk->refcount; +done: + /* Delete fragments and work list. */ + list_for_each_entry_safe(frag, n, &worklist, list) { + list_del(&frag->list); + kfree(frag); + } + list_for_each_entry_safe(frag, n, &refchk->fragments, list) { + list_del(&frag->list); + kfree(frag); + } +} + +/* Use the rmap entries covering this extent to verify the refcount. */ +STATIC void +xchk_rtrefcountbt_xref_rmap( + struct xfs_scrub *sc, + const struct xfs_refcount_irec *irec) +{ + struct xchk_rtrefcnt_check refchk = { + .sc = sc, + .bno = irec->rc_startblock, + .len = irec->rc_blockcount, + .refcount = irec->rc_refcount, + .seen = 0, + }; + struct xfs_rmap_irec low; + struct xfs_rmap_irec high; + struct xchk_rtrefcnt_frag *frag; + struct xchk_rtrefcnt_frag *n; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + /* Cross-reference with the rmapbt to confirm the refcount. */ + memset(&low, 0, sizeof(low)); + low.rm_startblock = irec->rc_startblock; + memset(&high, 0xFF, sizeof(high)); + high.rm_startblock = irec->rc_startblock + irec->rc_blockcount - 1; + + INIT_LIST_HEAD(&refchk.fragments); + error = xfs_rmap_query_range(sc->sr.rmap_cur, &low, &high, + xchk_rtrefcountbt_rmap_check, &refchk); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + goto out_free; + + xchk_rtrefcountbt_process_rmap_fragments(&refchk); + if (irec->rc_refcount != refchk.seen) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + +out_free: + list_for_each_entry_safe(frag, n, &refchk.fragments, list) { + list_del(&frag->list); + kfree(frag); + } +} + +/* Cross-reference with the other btrees. */ +STATIC void +xchk_rtrefcountbt_xref( + struct xfs_scrub *sc, + const struct xfs_refcount_irec *irec) +{ + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + xchk_xref_is_used_rt_space(sc, + xfs_rgbno_to_rtb(sc->sr.rtg, irec->rc_startblock), + irec->rc_blockcount); + xchk_rtrefcountbt_xref_rmap(sc, irec); +} + +struct xchk_rtrefcbt_records { + /* Previous refcount record. */ + struct xfs_refcount_irec prev_rec; + + /* The next rtgroup block where we aren't expecting shared extents. */ + xfs_rgblock_t next_unshared_rgbno; + + /* Number of CoW blocks we expect. */ + xfs_extlen_t cow_blocks; + + /* Was the last record a shared or CoW staging extent? */ + enum xfs_refc_domain prev_domain; +}; + +static inline bool +xchk_rtrefcount_mergeable( + struct xchk_rtrefcbt_records *rrc, + const struct xfs_refcount_irec *r2) +{ + const struct xfs_refcount_irec *r1 = &rrc->prev_rec; + + /* Ignore if prev_rec is not yet initialized. */ + if (r1->rc_blockcount > 0) + return false; + + if (r1->rc_startblock + r1->rc_blockcount != r2->rc_startblock) + return false; + if (r1->rc_refcount != r2->rc_refcount) + return false; + if ((unsigned long long)r1->rc_blockcount + r2->rc_blockcount > + XFS_REFC_LEN_MAX) + return false; + + return true; +} + +/* Flag failures for records that could be merged. */ +STATIC void +xchk_rtrefcountbt_check_mergeable( + struct xchk_btree *bs, + struct xchk_rtrefcbt_records *rrc, + const struct xfs_refcount_irec *irec) +{ + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + if (xchk_rtrefcount_mergeable(rrc, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + memcpy(&rrc->prev_rec, irec, sizeof(struct xfs_refcount_irec)); +} + +STATIC int +xchk_rtrefcountbt_rmap_check_gap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + xfs_rgblock_t *next_bno = priv; + + if (*next_bno != NULLRGBLOCK && rec->rm_startblock < *next_bno) + return -ECANCELED; + + *next_bno = rec->rm_startblock + rec->rm_blockcount; + return 0; +} + +/* + * Make sure that a gap in the reference count records does not correspond to + * overlapping records (i.e. shared extents) in the reverse mappings. + */ +static inline void +xchk_rtrefcountbt_xref_gaps( + struct xfs_scrub *sc, + struct xchk_rtrefcbt_records *rrc, + xfs_rtblock_t bno) +{ + struct xfs_rmap_irec low; + struct xfs_rmap_irec high; + xfs_rgblock_t next_bno = NULLRGBLOCK; + int error; + + if (bno <= rrc->next_unshared_rgbno || !sc->sr.rmap_cur || + xchk_skip_xref(sc->sm)) + return; + + memset(&low, 0, sizeof(low)); + low.rm_startblock = rrc->next_unshared_rgbno; + memset(&high, 0xFF, sizeof(high)); + high.rm_startblock = bno - 1; + + error = xfs_rmap_query_range(sc->sr.rmap_cur, &low, &high, + xchk_rtrefcountbt_rmap_check_gap, &next_bno); + if (error == -ECANCELED) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + else + xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur); +} + +/* Scrub a rtrefcountbt record. */ +STATIC int +xchk_rtrefcountbt_rec( + struct xchk_btree *bs, + const union xfs_btree_rec *rec) +{ + struct xfs_mount *mp = bs->cur->bc_mp; + struct xchk_rtrefcbt_records *rrc = bs->private; + struct xfs_refcount_irec irec; + u32 mod; + + xfs_refcount_btrec_to_irec(rec, &irec); + if (xfs_rtrefcount_check_irec(to_rtg(bs->cur->bc_group), &irec) != + NULL) { + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } + + /* We can only share full rt extents. */ + mod = xfs_rgbno_to_rtxoff(mp, irec.rc_startblock); + if (mod) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + mod = xfs_extlen_to_rtxmod(mp, irec.rc_blockcount); + if (mod) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + if (irec.rc_domain == XFS_REFC_DOMAIN_COW) + rrc->cow_blocks += irec.rc_blockcount; + + /* Shared records always come before CoW records. */ + if (irec.rc_domain == XFS_REFC_DOMAIN_SHARED && + rrc->prev_domain == XFS_REFC_DOMAIN_COW) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + rrc->prev_domain = irec.rc_domain; + + xchk_rtrefcountbt_check_mergeable(bs, rrc, &irec); + xchk_rtrefcountbt_xref(bs->sc, &irec); + + /* + * If this is a record for a shared extent, check that all blocks + * between the previous record and this one have at most one reverse + * mapping. + */ + if (irec.rc_domain == XFS_REFC_DOMAIN_SHARED) { + xchk_rtrefcountbt_xref_gaps(bs->sc, rrc, irec.rc_startblock); + rrc->next_unshared_rgbno = irec.rc_startblock + + irec.rc_blockcount; + } + + return 0; +} + +/* Make sure we have as many refc blocks as the rmap says. */ +STATIC void +xchk_refcount_xref_rmap( + struct xfs_scrub *sc, + const struct xfs_owner_info *btree_oinfo, + xfs_extlen_t cow_blocks) +{ + xfs_filblks_t refcbt_blocks = 0; + xfs_filblks_t blocks; + int error; + + if (!sc->sr.rmap_cur || !sc->sa.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + /* Check that we saw as many refcbt blocks as the rmap knows about. */ + error = xfs_btree_count_blocks(sc->sr.refc_cur, &refcbt_blocks); + if (!xchk_btree_process_error(sc, sc->sr.refc_cur, 0, &error)) + return; + error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, btree_oinfo, + &blocks); + if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur)) + return; + if (blocks != refcbt_blocks) + xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + + /* Check that we saw as many cow blocks as the rmap knows about. */ + error = xchk_count_rmap_ownedby_ag(sc, sc->sr.rmap_cur, + &XFS_RMAP_OINFO_COW, &blocks); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (blocks != cow_blocks) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} + +/* Scrub the refcount btree for some AG. */ +int +xchk_rtrefcountbt( + struct xfs_scrub *sc) +{ + struct xfs_owner_info btree_oinfo; + struct xchk_rtrefcbt_records rrc = { + .cow_blocks = 0, + .next_unshared_rgbno = 0, + .prev_domain = XFS_REFC_DOMAIN_SHARED, + }; + int error; + + error = xchk_metadata_inode_forks(sc); + if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + return error; + + xfs_rmap_ino_bmbt_owner(&btree_oinfo, rtg_refcount(sc->sr.rtg)->i_ino, + XFS_DATA_FORK); + error = xchk_btree(sc, sc->sr.refc_cur, xchk_rtrefcountbt_rec, + &btree_oinfo, &rrc); + if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + return error; + + /* + * Check that all blocks between the last refcount > 1 record and the + * end of the rt volume have at most one reverse mapping. + */ + xchk_rtrefcountbt_xref_gaps(sc, &rrc, sc->mp->m_sb.sb_rblocks); + + xchk_refcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); + + return 0; +} + +/* xref check that a cow staging extent is marked in the rtrefcountbt. */ +void +xchk_xref_is_rt_cow_staging( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + struct xfs_refcount_irec rc; + int has_refcount; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + /* Find the CoW staging extent. */ + error = xfs_refcount_lookup_le(sc->sr.refc_cur, XFS_REFC_DOMAIN_COW, + bno, &has_refcount); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (!has_refcount) { + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + return; + } + + error = xfs_refcount_get_rec(sc->sr.refc_cur, &rc, &has_refcount); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (!has_refcount) { + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + return; + } + + /* CoW lookup returned a shared extent record? */ + if (rc.rc_domain != XFS_REFC_DOMAIN_COW) + xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + + /* Must be at least as long as what was passed in */ + if (rc.rc_blockcount < len) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} + +/* + * xref check that the extent is not shared. Only file data blocks + * can have multiple owners. + */ +void +xchk_xref_is_not_rt_shared( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_refcount_has_records(sc->sr.refc_cur, + XFS_REFC_DOMAIN_SHARED, bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} + +/* xref check that the extent is not being used for CoW staging. */ +void +xchk_xref_is_not_rt_cow_staging( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_refcount_has_records(sc->sr.refc_cur, XFS_REFC_DOMAIN_COW, + bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} diff --git a/fs/xfs/scrub/rtrefcount_repair.c b/fs/xfs/scrub/rtrefcount_repair.c new file mode 100644 index 000000000000..257cfb24beb4 --- /dev/null +++ b/fs/xfs/scrub/rtrefcount_repair.c @@ -0,0 +1,783 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_alloc.h" +#include "xfs_ialloc.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_refcount.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_error.h" +#include "xfs_health.h" +#include "xfs_inode.h" +#include "xfs_quota.h" +#include "xfs_rtalloc.h" +#include "xfs_ag.h" +#include "xfs_rtgroup.h" +#include "xfs_rtbitmap.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/trace.h" +#include "scrub/repair.h" +#include "scrub/bitmap.h" +#include "scrub/fsb_bitmap.h" +#include "scrub/xfile.h" +#include "scrub/xfarray.h" +#include "scrub/newbt.h" +#include "scrub/reap.h" +#include "scrub/rcbag.h" + +/* + * Rebuilding the Reference Count Btree + * ==================================== + * + * This algorithm is "borrowed" from xfs_repair. Imagine the rmap + * entries as rectangles representing extents of physical blocks, and + * that the rectangles can be laid down to allow them to overlap each + * other; then we know that we must emit a refcnt btree entry wherever + * the amount of overlap changes, i.e. the emission stimulus is + * level-triggered: + * + * - --- + * -- ----- ---- --- ------ + * -- ---- ----------- ---- --------- + * -------------------------------- ----------- + * ^ ^ ^^ ^^ ^ ^^ ^^^ ^^^^ ^ ^^ ^ ^ ^ + * 2 1 23 21 3 43 234 2123 1 01 2 3 0 + * + * For our purposes, a rmap is a tuple (startblock, len, fileoff, owner). + * + * Note that in the actual refcnt btree we don't store the refcount < 2 + * cases because the bnobt tells us which blocks are free; single-use + * blocks aren't recorded in the bnobt or the refcntbt. If the rmapbt + * supports storing multiple entries covering a given block we could + * theoretically dispense with the refcntbt and simply count rmaps, but + * that's inefficient in the (hot) write path, so we'll take the cost of + * the extra tree to save time. Also there's no guarantee that rmap + * will be enabled. + * + * Given an array of rmaps sorted by physical block number, a starting + * physical block (sp), a bag to hold rmaps that cover sp, and the next + * physical block where the level changes (np), we can reconstruct the + * rt refcount btree as follows: + * + * While there are still unprocessed rmaps in the array, + * - Set sp to the physical block (pblk) of the next unprocessed rmap. + * - Add to the bag all rmaps in the array where startblock == sp. + * - Set np to the physical block where the bag size will change. This + * is the minimum of (the pblk of the next unprocessed rmap) and + * (startblock + len of each rmap in the bag). + * - Record the bag size as old_bag_size. + * + * - While the bag isn't empty, + * - Remove from the bag all rmaps where startblock + len == np. + * - Add to the bag all rmaps in the array where startblock == np. + * - If the bag size isn't old_bag_size, store the refcount entry + * (sp, np - sp, bag_size) in the refcnt btree. + * - If the bag is empty, break out of the inner loop. + * - Set old_bag_size to the bag size + * - Set sp = np. + * - Set np to the physical block where the bag size will change. + * This is the minimum of (the pblk of the next unprocessed rmap) + * and (startblock + len of each rmap in the bag). + * + * Like all the other repairers, we make a list of all the refcount + * records we need, then reinitialize the rt refcount btree root and + * insert all the records. + */ + +struct xrep_rtrefc { + /* refcount extents */ + struct xfarray *refcount_records; + + /* new refcountbt information */ + struct xrep_newbt new_btree; + + /* old refcountbt blocks */ + struct xfsb_bitmap old_rtrefcountbt_blocks; + + struct xfs_scrub *sc; + + /* get_records()'s position in the rt refcount record array. */ + xfarray_idx_t array_cur; + + /* # of refcountbt blocks */ + xfs_filblks_t btblocks; +}; + +/* Set us up to repair refcount btrees. */ +int +xrep_setup_rtrefcountbt( + struct xfs_scrub *sc) +{ + char *descr; + int error; + + descr = xchk_xfile_ag_descr(sc, "rmap record bag"); + error = xrep_setup_xfbtree(sc, descr); + kfree(descr); + return error; +} + +/* Check for any obvious conflicts with this shared/CoW staging extent. */ +STATIC int +xrep_rtrefc_check_ext( + struct xfs_scrub *sc, + const struct xfs_refcount_irec *rec) +{ + xfs_rgblock_t last; + + if (xfs_rtrefcount_check_irec(sc->sr.rtg, rec) != NULL) + return -EFSCORRUPTED; + + if (xfs_rgbno_to_rtxoff(sc->mp, rec->rc_startblock) != 0) + return -EFSCORRUPTED; + + last = rec->rc_startblock + rec->rc_blockcount - 1; + if (xfs_rgbno_to_rtxoff(sc->mp, last) != sc->mp->m_sb.sb_rextsize - 1) + return -EFSCORRUPTED; + + /* Make sure this isn't free space or misaligned. */ + return xrep_require_rtext_inuse(sc, rec->rc_startblock, + rec->rc_blockcount); +} + +/* Record a reference count extent. */ +STATIC int +xrep_rtrefc_stash( + struct xrep_rtrefc *rr, + enum xfs_refc_domain domain, + xfs_rgblock_t bno, + xfs_extlen_t len, + uint64_t refcount) +{ + struct xfs_refcount_irec irec = { + .rc_startblock = bno, + .rc_blockcount = len, + .rc_refcount = refcount, + .rc_domain = domain, + }; + int error = 0; + + if (xchk_should_terminate(rr->sc, &error)) + return error; + + irec.rc_refcount = min_t(uint64_t, XFS_REFC_REFCOUNT_MAX, refcount); + + error = xrep_rtrefc_check_ext(rr->sc, &irec); + if (error) + return error; + + trace_xrep_refc_found(rtg_group(rr->sc->sr.rtg), &irec); + + return xfarray_append(rr->refcount_records, &irec); +} + +/* Record a CoW staging extent. */ +STATIC int +xrep_rtrefc_stash_cow( + struct xrep_rtrefc *rr, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + return xrep_rtrefc_stash(rr, XFS_REFC_DOMAIN_COW, bno, len, 1); +} + +/* Decide if an rmap could describe a shared extent. */ +static inline bool +xrep_rtrefc_rmap_shareable( + const struct xfs_rmap_irec *rmap) +{ + /* rt metadata are never sharable */ + if (XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner)) + return false; + + /* Unwritten file blocks are not shareable. */ + if (rmap->rm_flags & XFS_RMAP_UNWRITTEN) + return false; + + return true; +} + +/* Grab the next (abbreviated) rmap record from the rmapbt. */ +STATIC int +xrep_rtrefc_walk_rmaps( + struct xrep_rtrefc *rr, + struct xfs_rmap_irec *rmap, + bool *have_rec) +{ + struct xfs_btree_cur *cur = rr->sc->sr.rmap_cur; + struct xfs_mount *mp = cur->bc_mp; + int have_gt; + int error = 0; + + *have_rec = false; + + /* + * Loop through the remaining rmaps. Remember CoW staging + * extents and the refcountbt blocks from the old tree for later + * disposal. We can only share written data fork extents, so + * keep looping until we find an rmap for one. + */ + do { + if (xchk_should_terminate(rr->sc, &error)) + return error; + + error = xfs_btree_increment(cur, 0, &have_gt); + if (error) + return error; + if (!have_gt) + return 0; + + error = xfs_rmap_get_rec(cur, rmap, &have_gt); + if (error) + return error; + if (XFS_IS_CORRUPT(mp, !have_gt)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + + if (rmap->rm_owner == XFS_RMAP_OWN_COW) { + error = xrep_rtrefc_stash_cow(rr, rmap->rm_startblock, + rmap->rm_blockcount); + if (error) + return error; + } else if (xfs_is_sb_inum(mp, rmap->rm_owner) || + (rmap->rm_flags & (XFS_RMAP_ATTR_FORK | + XFS_RMAP_BMBT_BLOCK))) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + } while (!xrep_rtrefc_rmap_shareable(rmap)); + + *have_rec = true; + return 0; +} + +static inline uint32_t +xrep_rtrefc_encode_startblock( + const struct xfs_refcount_irec *irec) +{ + uint32_t start; + + start = irec->rc_startblock & ~XFS_REFC_COWFLAG; + if (irec->rc_domain == XFS_REFC_DOMAIN_COW) + start |= XFS_REFC_COWFLAG; + + return start; +} + +/* + * Compare two refcount records. We want to sort in order of increasing block + * number. + */ +static int +xrep_rtrefc_extent_cmp( + const void *a, + const void *b) +{ + const struct xfs_refcount_irec *ap = a; + const struct xfs_refcount_irec *bp = b; + uint32_t sa, sb; + + sa = xrep_rtrefc_encode_startblock(ap); + sb = xrep_rtrefc_encode_startblock(bp); + + if (sa > sb) + return 1; + if (sa < sb) + return -1; + return 0; +} + +/* + * Sort the refcount extents by startblock or else the btree records will be in + * the wrong order. Make sure the records do not overlap in physical space. + */ +STATIC int +xrep_rtrefc_sort_records( + struct xrep_rtrefc *rr) +{ + struct xfs_refcount_irec irec; + xfarray_idx_t cur; + enum xfs_refc_domain dom = XFS_REFC_DOMAIN_SHARED; + xfs_rgblock_t next_rgbno = 0; + int error; + + error = xfarray_sort(rr->refcount_records, xrep_rtrefc_extent_cmp, + XFARRAY_SORT_KILLABLE); + if (error) + return error; + + foreach_xfarray_idx(rr->refcount_records, cur) { + if (xchk_should_terminate(rr->sc, &error)) + return error; + + error = xfarray_load(rr->refcount_records, cur, &irec); + if (error) + return error; + + if (dom == XFS_REFC_DOMAIN_SHARED && + irec.rc_domain == XFS_REFC_DOMAIN_COW) { + dom = irec.rc_domain; + next_rgbno = 0; + } + + if (dom != irec.rc_domain) + return -EFSCORRUPTED; + if (irec.rc_startblock < next_rgbno) + return -EFSCORRUPTED; + + next_rgbno = irec.rc_startblock + irec.rc_blockcount; + } + + return error; +} + +/* Record extents that belong to the realtime refcount inode. */ +STATIC int +xrep_rtrefc_walk_rmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_rtrefc *rr = priv; + int error = 0; + + if (xchk_should_terminate(rr->sc, &error)) + return error; + + /* Skip extents which are not owned by this inode and fork. */ + if (rec->rm_owner != rr->sc->ip->i_ino) + return 0; + + error = xrep_check_ino_btree_mapping(rr->sc, rec); + if (error) + return error; + + return xfsb_bitmap_set(&rr->old_rtrefcountbt_blocks, + xfs_gbno_to_fsb(cur->bc_group, rec->rm_startblock), + rec->rm_blockcount); +} + +/* + * Walk forward through the rmap btree to collect all rmaps starting at + * @bno in @rmap_bag. These represent the file(s) that share ownership of + * the current block. Upon return, the rmap cursor points to the last record + * satisfying the startblock constraint. + */ +static int +xrep_rtrefc_push_rmaps_at( + struct xrep_rtrefc *rr, + struct rcbag *rcstack, + xfs_rgblock_t bno, + struct xfs_rmap_irec *rmap, + bool *have) +{ + struct xfs_scrub *sc = rr->sc; + int have_gt; + int error; + + while (*have && rmap->rm_startblock == bno) { + error = rcbag_add(rcstack, rr->sc->tp, rmap); + if (error) + return error; + + error = xrep_rtrefc_walk_rmaps(rr, rmap, have); + if (error) + return error; + } + + error = xfs_btree_decrement(sc->sr.rmap_cur, 0, &have_gt); + if (error) + return error; + if (XFS_IS_CORRUPT(sc->mp, !have_gt)) { + xfs_btree_mark_sick(sc->sr.rmap_cur); + return -EFSCORRUPTED; + } + + return 0; +} + +/* Scan one AG for reverse mappings for the realtime refcount btree. */ +STATIC int +xrep_rtrefc_scan_ag( + struct xrep_rtrefc *rr, + struct xfs_perag *pag) +{ + struct xfs_scrub *sc = rr->sc; + int error; + + error = xrep_ag_init(sc, pag, &sc->sa); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_rtrefc_walk_rmap, rr); + xchk_ag_free(sc, &sc->sa); + return error; +} + +/* Iterate all the rmap records to generate reference count data. */ +STATIC int +xrep_rtrefc_find_refcounts( + struct xrep_rtrefc *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct rcbag *rcstack; + struct xfs_perag *pag = NULL; + uint64_t old_stack_height; + xfs_rgblock_t sbno; + xfs_rgblock_t cbno; + xfs_rgblock_t nbno; + bool have; + int error; + + /* Scan for old rtrefc btree blocks. */ + while ((pag = xfs_perag_next(sc->mp, pag))) { + error = xrep_rtrefc_scan_ag(rr, pag); + if (error) { + xfs_perag_rele(pag); + return error; + } + } + + xrep_rtgroup_btcur_init(sc, &sc->sr); + + /* + * Set up a bag to store all the rmap records that we're tracking to + * generate a reference count record. If this exceeds + * XFS_REFC_REFCOUNT_MAX, we clamp rc_refcount. + */ + error = rcbag_init(sc->mp, sc->xmbtp, &rcstack); + if (error) + goto out_cur; + + /* Start the rtrmapbt cursor to the left of all records. */ + error = xfs_btree_goto_left_edge(sc->sr.rmap_cur); + if (error) + goto out_bag; + + /* Process reverse mappings into refcount data. */ + while (xfs_btree_has_more_records(sc->sr.rmap_cur)) { + struct xfs_rmap_irec rmap; + + /* Push all rmaps with pblk == sbno onto the stack */ + error = xrep_rtrefc_walk_rmaps(rr, &rmap, &have); + if (error) + goto out_bag; + if (!have) + break; + sbno = cbno = rmap.rm_startblock; + error = xrep_rtrefc_push_rmaps_at(rr, rcstack, sbno, &rmap, + &have); + if (error) + goto out_bag; + + /* Set nbno to the bno of the next refcount change */ + error = rcbag_next_edge(rcstack, sc->tp, &rmap, have, &nbno); + if (error) + goto out_bag; + + ASSERT(nbno > sbno); + old_stack_height = rcbag_count(rcstack); + + /* While stack isn't empty... */ + while (rcbag_count(rcstack) > 0) { + /* Pop all rmaps that end at nbno */ + error = rcbag_remove_ending_at(rcstack, sc->tp, nbno); + if (error) + goto out_bag; + + /* Push array items that start at nbno */ + error = xrep_rtrefc_walk_rmaps(rr, &rmap, &have); + if (error) + goto out_bag; + if (have) { + error = xrep_rtrefc_push_rmaps_at(rr, rcstack, + nbno, &rmap, &have); + if (error) + goto out_bag; + } + + /* Emit refcount if necessary */ + ASSERT(nbno > cbno); + if (rcbag_count(rcstack) != old_stack_height) { + if (old_stack_height > 1) { + error = xrep_rtrefc_stash(rr, + XFS_REFC_DOMAIN_SHARED, + cbno, nbno - cbno, + old_stack_height); + if (error) + goto out_bag; + } + cbno = nbno; + } + + /* Stack empty, go find the next rmap */ + if (rcbag_count(rcstack) == 0) + break; + old_stack_height = rcbag_count(rcstack); + sbno = nbno; + + /* Set nbno to the bno of the next refcount change */ + error = rcbag_next_edge(rcstack, sc->tp, &rmap, have, + &nbno); + if (error) + goto out_bag; + + ASSERT(nbno > sbno); + } + } + + ASSERT(rcbag_count(rcstack) == 0); +out_bag: + rcbag_free(&rcstack); +out_cur: + xchk_rtgroup_btcur_free(&sc->sr); + return error; +} + +/* Retrieve refcountbt data for bulk load. */ +STATIC int +xrep_rtrefc_get_records( + struct xfs_btree_cur *cur, + unsigned int idx, + struct xfs_btree_block *block, + unsigned int nr_wanted, + void *priv) +{ + struct xrep_rtrefc *rr = priv; + union xfs_btree_rec *block_rec; + unsigned int loaded; + int error; + + for (loaded = 0; loaded < nr_wanted; loaded++, idx++) { + error = xfarray_load(rr->refcount_records, rr->array_cur++, + &cur->bc_rec.rc); + if (error) + return error; + + block_rec = xfs_btree_rec_addr(cur, idx, block); + cur->bc_ops->init_rec_from_cur(cur, block_rec); + } + + return loaded; +} + +/* Feed one of the new btree blocks to the bulk loader. */ +STATIC int +xrep_rtrefc_claim_block( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr, + void *priv) +{ + struct xrep_rtrefc *rr = priv; + + return xrep_newbt_claim_block(cur, &rr->new_btree, ptr); +} + +/* Figure out how much space we need to create the incore btree root block. */ +STATIC size_t +xrep_rtrefc_iroot_size( + struct xfs_btree_cur *cur, + unsigned int level, + unsigned int nr_this_level, + void *priv) +{ + return xfs_rtrefcount_broot_space_calc(cur->bc_mp, level, + nr_this_level); +} + +/* + * Use the collected refcount information to stage a new rt refcount btree. If + * this is successful we'll return with the new btree root information logged + * to the repair transaction but not yet committed. + */ +STATIC int +xrep_rtrefc_build_new_tree( + struct xrep_rtrefc *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct xfs_rtgroup *rtg = sc->sr.rtg; + struct xfs_btree_cur *refc_cur; + int error; + + error = xrep_rtrefc_sort_records(rr); + if (error) + return error; + + /* + * Prepare to construct the new btree by reserving disk space for the + * new btree and setting up all the accounting information we'll need + * to root the new btree while it's under construction and before we + * attach it to the realtime refcount inode. + */ + error = xrep_newbt_init_metadir_inode(&rr->new_btree, sc); + if (error) + return error; + + rr->new_btree.bload.get_records = xrep_rtrefc_get_records; + rr->new_btree.bload.claim_block = xrep_rtrefc_claim_block; + rr->new_btree.bload.iroot_size = xrep_rtrefc_iroot_size; + + refc_cur = xfs_rtrefcountbt_init_cursor(NULL, rtg); + xfs_btree_stage_ifakeroot(refc_cur, &rr->new_btree.ifake); + + /* Compute how many blocks we'll need. */ + error = xfs_btree_bload_compute_geometry(refc_cur, &rr->new_btree.bload, + xfarray_length(rr->refcount_records)); + if (error) + goto err_cur; + + /* Last chance to abort before we start committing fixes. */ + if (xchk_should_terminate(sc, &error)) + goto err_cur; + + /* + * Guess how many blocks we're going to need to rebuild an entire + * rtrefcountbt from the number of extents we found, and pump up our + * transaction to have sufficient block reservation. We're allowed + * to exceed quota to repair inconsistent metadata, though this is + * unlikely. + */ + error = xfs_trans_reserve_more_inode(sc->tp, rtg_refcount(rtg), + rr->new_btree.bload.nr_blocks, 0, true); + if (error) + goto err_cur; + + /* Reserve the space we'll need for the new btree. */ + error = xrep_newbt_alloc_blocks(&rr->new_btree, + rr->new_btree.bload.nr_blocks); + if (error) + goto err_cur; + + /* Add all observed refcount records. */ + rr->new_btree.ifake.if_fork->if_format = XFS_DINODE_FMT_META_BTREE; + rr->array_cur = XFARRAY_CURSOR_INIT; + error = xfs_btree_bload(refc_cur, &rr->new_btree.bload, rr); + if (error) + goto err_cur; + + /* + * Install the new rtrefc btree in the inode. After this point the old + * btree is no longer accessible, the new tree is live, and we can + * delete the cursor. + */ + xfs_rtrefcountbt_commit_staged_btree(refc_cur, sc->tp); + xrep_inode_set_nblocks(rr->sc, rr->new_btree.ifake.if_blocks); + xfs_btree_del_cursor(refc_cur, 0); + + /* Dispose of any unused blocks and the accounting information. */ + error = xrep_newbt_commit(&rr->new_btree); + if (error) + return error; + + return xrep_roll_trans(sc); +err_cur: + xfs_btree_del_cursor(refc_cur, error); + xrep_newbt_cancel(&rr->new_btree); + return error; +} + +/* + * Now that we've logged the roots of the new btrees, invalidate all of the + * old blocks and free them. + */ +STATIC int +xrep_rtrefc_remove_old_tree( + struct xrep_rtrefc *rr) +{ + int error; + + /* + * Free all the extents that were allocated to the former rtrefcountbt + * and aren't cross-linked with something else. + */ + error = xrep_reap_metadir_fsblocks(rr->sc, + &rr->old_rtrefcountbt_blocks); + if (error) + return error; + + /* + * Ensure the proper reservation for the rtrefcount inode so that we + * don't fail to expand the btree. + */ + return xrep_reset_metafile_resv(rr->sc); +} + +/* Rebuild the rt refcount btree. */ +int +xrep_rtrefcountbt( + struct xfs_scrub *sc) +{ + struct xrep_rtrefc *rr; + struct xfs_mount *mp = sc->mp; + char *descr; + int error; + + /* We require the rmapbt to rebuild anything. */ + if (!xfs_has_rtrmapbt(mp)) + return -EOPNOTSUPP; + + /* Make sure any problems with the fork are fixed. */ + error = xrep_metadata_inode_forks(sc); + if (error) + return error; + + rr = kzalloc(sizeof(struct xrep_rtrefc), XCHK_GFP_FLAGS); + if (!rr) + return -ENOMEM; + rr->sc = sc; + + /* Set up enough storage to handle one refcount record per rt extent. */ + descr = xchk_xfile_ag_descr(sc, "reference count records"); + error = xfarray_create(descr, mp->m_sb.sb_rextents, + sizeof(struct xfs_refcount_irec), + &rr->refcount_records); + kfree(descr); + if (error) + goto out_rr; + + /* Collect all reference counts. */ + xfsb_bitmap_init(&rr->old_rtrefcountbt_blocks); + error = xrep_rtrefc_find_refcounts(rr); + if (error) + goto out_bitmap; + + xfs_trans_ijoin(sc->tp, sc->ip, 0); + + /* Rebuild the refcount information. */ + error = xrep_rtrefc_build_new_tree(rr); + if (error) + goto out_bitmap; + + /* Kill the old tree. */ + error = xrep_rtrefc_remove_old_tree(rr); + if (error) + goto out_bitmap; + +out_bitmap: + xfsb_bitmap_destroy(&rr->old_rtrefcountbt_blocks); + xfarray_destroy(rr->refcount_records); +out_rr: + kfree(rr); + return error; +} diff --git a/fs/xfs/scrub/rtrmap.c b/fs/xfs/scrub/rtrmap.c new file mode 100644 index 000000000000..12989fe80e8b --- /dev/null +++ b/fs/xfs/scrub/rtrmap.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_inode.h" +#include "xfs_rtalloc.h" +#include "xfs_rtgroup.h" +#include "xfs_metafile.h" +#include "xfs_refcount.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/trace.h" +#include "scrub/repair.h" + +/* Set us up with the realtime metadata locked. */ +int +xchk_setup_rtrmapbt( + struct xfs_scrub *sc) +{ + int error; + + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + + if (xchk_could_repair(sc)) { + error = xrep_setup_rtrmapbt(sc); + if (error) + return error; + } + + error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr); + if (error) + return error; + + error = xchk_setup_rt(sc); + if (error) + return error; + + error = xchk_install_live_inode(sc, rtg_rmap(sc->sr.rtg)); + if (error) + return error; + + return xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); +} + +/* Realtime reverse mapping. */ + +struct xchk_rtrmap { + /* + * The furthest-reaching of the rmapbt records that we've already + * processed. This enables us to detect overlapping records for space + * allocations that cannot be shared. + */ + struct xfs_rmap_irec overlap_rec; + + /* + * The previous rmapbt record, so that we can check for two records + * that could be one. + */ + struct xfs_rmap_irec prev_rec; +}; + +static inline bool +xchk_rtrmapbt_is_shareable( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *irec) +{ + if (!xfs_has_rtreflink(sc->mp)) + return false; + if (irec->rm_flags & XFS_RMAP_UNWRITTEN) + return false; + return true; +} + +/* Flag failures for records that overlap but cannot. */ +STATIC void +xchk_rtrmapbt_check_overlapping( + struct xchk_btree *bs, + struct xchk_rtrmap *cr, + const struct xfs_rmap_irec *irec) +{ + xfs_rtblock_t pnext, inext; + + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + /* No previous record? */ + if (cr->overlap_rec.rm_blockcount == 0) + goto set_prev; + + /* Do overlap_rec and irec overlap? */ + pnext = cr->overlap_rec.rm_startblock + cr->overlap_rec.rm_blockcount; + if (pnext <= irec->rm_startblock) + goto set_prev; + + /* Overlap is only allowed if both records are data fork mappings. */ + if (!xchk_rtrmapbt_is_shareable(bs->sc, &cr->overlap_rec) || + !xchk_rtrmapbt_is_shareable(bs->sc, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + /* Save whichever rmap record extends furthest. */ + inext = irec->rm_startblock + irec->rm_blockcount; + if (pnext > inext) + return; + +set_prev: + memcpy(&cr->overlap_rec, irec, sizeof(struct xfs_rmap_irec)); +} + +/* Decide if two reverse-mapping records can be merged. */ +static inline bool +xchk_rtrmap_mergeable( + struct xchk_rtrmap *cr, + const struct xfs_rmap_irec *r2) +{ + const struct xfs_rmap_irec *r1 = &cr->prev_rec; + + /* Ignore if prev_rec is not yet initialized. */ + if (cr->prev_rec.rm_blockcount == 0) + return false; + + if (r1->rm_owner != r2->rm_owner) + return false; + if (r1->rm_startblock + r1->rm_blockcount != r2->rm_startblock) + return false; + if ((unsigned long long)r1->rm_blockcount + r2->rm_blockcount > + XFS_RMAP_LEN_MAX) + return false; + if (r1->rm_flags != r2->rm_flags) + return false; + return r1->rm_offset + r1->rm_blockcount == r2->rm_offset; +} + +/* Flag failures for records that could be merged. */ +STATIC void +xchk_rtrmapbt_check_mergeable( + struct xchk_btree *bs, + struct xchk_rtrmap *cr, + const struct xfs_rmap_irec *irec) +{ + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + if (xchk_rtrmap_mergeable(cr, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + memcpy(&cr->prev_rec, irec, sizeof(struct xfs_rmap_irec)); +} + +/* Cross-reference a rmap against the refcount btree. */ +STATIC void +xchk_rtrmapbt_xref_rtrefc( + struct xfs_scrub *sc, + struct xfs_rmap_irec *irec) +{ + xfs_rgblock_t fbno; + xfs_extlen_t flen; + bool is_inode; + bool is_bmbt; + bool is_attr; + bool is_unwritten; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + is_inode = !XFS_RMAP_NON_INODE_OWNER(irec->rm_owner); + is_bmbt = irec->rm_flags & XFS_RMAP_BMBT_BLOCK; + is_attr = irec->rm_flags & XFS_RMAP_ATTR_FORK; + is_unwritten = irec->rm_flags & XFS_RMAP_UNWRITTEN; + + /* If this is shared, must be a data fork extent. */ + error = xfs_refcount_find_shared(sc->sr.refc_cur, irec->rm_startblock, + irec->rm_blockcount, &fbno, &flen, false); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (flen != 0 && (!is_inode || is_attr || is_bmbt || is_unwritten)) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} + +/* Cross-reference with other metadata. */ +STATIC void +xchk_rtrmapbt_xref( + struct xfs_scrub *sc, + struct xfs_rmap_irec *irec) +{ + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + xchk_xref_is_used_rt_space(sc, + xfs_rgbno_to_rtb(sc->sr.rtg, irec->rm_startblock), + irec->rm_blockcount); + if (irec->rm_owner == XFS_RMAP_OWN_COW) + xchk_xref_is_cow_staging(sc, irec->rm_startblock, + irec->rm_blockcount); + else + xchk_rtrmapbt_xref_rtrefc(sc, irec); +} + +/* Scrub a realtime rmapbt record. */ +STATIC int +xchk_rtrmapbt_rec( + struct xchk_btree *bs, + const union xfs_btree_rec *rec) +{ + struct xchk_rtrmap *cr = bs->private; + struct xfs_rmap_irec irec; + + if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL || + xfs_rtrmap_check_irec(to_rtg(bs->cur->bc_group), &irec) != NULL) { + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } + + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return 0; + + xchk_rtrmapbt_check_mergeable(bs, cr, &irec); + xchk_rtrmapbt_check_overlapping(bs, cr, &irec); + xchk_rtrmapbt_xref(bs->sc, &irec); + return 0; +} + +/* Scrub the realtime rmap btree. */ +int +xchk_rtrmapbt( + struct xfs_scrub *sc) +{ + struct xfs_inode *ip = rtg_rmap(sc->sr.rtg); + struct xfs_owner_info oinfo; + struct xchk_rtrmap cr = { }; + int error; + + error = xchk_metadata_inode_forks(sc); + if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + return error; + + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, XFS_DATA_FORK); + return xchk_btree(sc, sc->sr.rmap_cur, xchk_rtrmapbt_rec, &oinfo, &cr); +} + +/* xref check that the extent has no realtime reverse mapping at all */ +void +xchk_xref_has_no_rt_owner( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_has_records(sc->sr.rmap_cur, bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} + +/* xref check that the extent is completely mapped */ +void +xchk_xref_has_rt_owner( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_has_records(sc->sr.rmap_cur, bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (outcome != XBTREE_RECPACKING_FULL) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} + +/* xref check that the extent is only owned by a given owner */ +void +xchk_xref_is_only_rt_owned_by( + struct xfs_scrub *sc, + xfs_agblock_t bno, + xfs_extlen_t len, + const struct xfs_owner_info *oinfo) +{ + struct xfs_rmap_matches res; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_count_owners(sc->sr.rmap_cur, bno, len, oinfo, &res); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (res.matches != 1) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + if (res.bad_non_owner_matches) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + if (res.non_owner_matches) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} diff --git a/fs/xfs/scrub/rtrmap_repair.c b/fs/xfs/scrub/rtrmap_repair.c new file mode 100644 index 000000000000..f2fdd7a9fc24 --- /dev/null +++ b/fs/xfs/scrub/rtrmap_repair.c @@ -0,0 +1,1006 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2020-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_alloc.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_inode.h" +#include "xfs_icache.h" +#include "xfs_bmap.h" +#include "xfs_bmap_btree.h" +#include "xfs_quota.h" +#include "xfs_rtalloc.h" +#include "xfs_ag.h" +#include "xfs_rtgroup.h" +#include "xfs_refcount.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/trace.h" +#include "scrub/repair.h" +#include "scrub/bitmap.h" +#include "scrub/fsb_bitmap.h" +#include "scrub/rgb_bitmap.h" +#include "scrub/xfile.h" +#include "scrub/xfarray.h" +#include "scrub/iscan.h" +#include "scrub/newbt.h" +#include "scrub/reap.h" + +/* + * Realtime Reverse Mapping Btree Repair + * ===================================== + * + * This isn't quite as difficult as repairing the rmap btree on the data + * device, since we only store the data fork extents of realtime files on the + * realtime device. We still have to freeze the filesystem and stop the + * background threads like we do for the rmap repair, but we only have to scan + * realtime inodes. + * + * Collecting entries for the new realtime rmap btree is easy -- all we have + * to do is generate rtrmap entries from the data fork mappings of all realtime + * files in the filesystem. We then scan the rmap btrees of the data device + * looking for extents belonging to the old btree and note them in a bitmap. + * + * To rebuild the realtime rmap btree, we bulk-load the collected mappings into + * a new btree cursor and atomically swap that into the realtime inode. Then + * we can free the blocks from the old btree. + * + * We use the 'xrep_rtrmap' prefix for all the rmap functions. + */ + +/* Context for collecting rmaps */ +struct xrep_rtrmap { + /* new rtrmapbt information */ + struct xrep_newbt new_btree; + + /* lock for the xfbtree and xfile */ + struct mutex lock; + + /* rmap records generated from primary metadata */ + struct xfbtree rtrmap_btree; + + struct xfs_scrub *sc; + + /* bitmap of old rtrmapbt blocks */ + struct xfsb_bitmap old_rtrmapbt_blocks; + + /* Hooks into rtrmap update code. */ + struct xfs_rmap_hook rhook; + + /* inode scan cursor */ + struct xchk_iscan iscan; + + /* in-memory btree cursor for the ->get_blocks walk */ + struct xfs_btree_cur *mcur; + + /* Number of records we're staging in the new btree. */ + uint64_t nr_records; +}; + +/* Set us up to repair rt reverse mapping btrees. */ +int +xrep_setup_rtrmapbt( + struct xfs_scrub *sc) +{ + struct xrep_rtrmap *rr; + char *descr; + int error; + + xchk_fsgates_enable(sc, XCHK_FSGATES_RMAP); + + descr = xchk_xfile_rtgroup_descr(sc, "reverse mapping records"); + error = xrep_setup_xfbtree(sc, descr); + kfree(descr); + if (error) + return error; + + rr = kzalloc(sizeof(struct xrep_rtrmap), XCHK_GFP_FLAGS); + if (!rr) + return -ENOMEM; + + rr->sc = sc; + sc->buf = rr; + return 0; +} + +/* Make sure there's nothing funny about this mapping. */ +STATIC int +xrep_rtrmap_check_mapping( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *rec) +{ + if (xfs_rtrmap_check_irec(sc->sr.rtg, rec) != NULL) + return -EFSCORRUPTED; + + /* Make sure this isn't free space. */ + return xrep_require_rtext_inuse(sc, rec->rm_startblock, + rec->rm_blockcount); +} + +/* Store a reverse-mapping record. */ +static inline int +xrep_rtrmap_stash( + struct xrep_rtrmap *rr, + xfs_rgblock_t startblock, + xfs_extlen_t blockcount, + uint64_t owner, + uint64_t offset, + unsigned int flags) +{ + struct xfs_rmap_irec rmap = { + .rm_startblock = startblock, + .rm_blockcount = blockcount, + .rm_owner = owner, + .rm_offset = offset, + .rm_flags = flags, + }; + struct xfs_scrub *sc = rr->sc; + struct xfs_btree_cur *mcur; + int error = 0; + + if (xchk_should_terminate(sc, &error)) + return error; + + if (xchk_iscan_aborted(&rr->iscan)) + return -EFSCORRUPTED; + + trace_xrep_rtrmap_found(sc->mp, &rmap); + + /* Add entry to in-memory btree. */ + mutex_lock(&rr->lock); + mcur = xfs_rtrmapbt_mem_cursor(sc->sr.rtg, sc->tp, &rr->rtrmap_btree); + error = xfs_rmap_map_raw(mcur, &rmap); + xfs_btree_del_cursor(mcur, error); + if (error) + goto out_cancel; + + error = xfbtree_trans_commit(&rr->rtrmap_btree, sc->tp); + if (error) + goto out_abort; + + mutex_unlock(&rr->lock); + return 0; + +out_cancel: + xfbtree_trans_cancel(&rr->rtrmap_btree, sc->tp); +out_abort: + xchk_iscan_abort(&rr->iscan); + mutex_unlock(&rr->lock); + return error; +} + +/* Finding all file and bmbt extents. */ + +/* Context for accumulating rmaps for an inode fork. */ +struct xrep_rtrmap_ifork { + /* + * Accumulate rmap data here to turn multiple adjacent bmaps into a + * single rmap. + */ + struct xfs_rmap_irec accum; + + struct xrep_rtrmap *rr; +}; + +/* Stash an rmap that we accumulated while walking an inode fork. */ +STATIC int +xrep_rtrmap_stash_accumulated( + struct xrep_rtrmap_ifork *rf) +{ + if (rf->accum.rm_blockcount == 0) + return 0; + + return xrep_rtrmap_stash(rf->rr, rf->accum.rm_startblock, + rf->accum.rm_blockcount, rf->accum.rm_owner, + rf->accum.rm_offset, rf->accum.rm_flags); +} + +/* Accumulate a bmbt record. */ +STATIC int +xrep_rtrmap_visit_bmbt( + struct xfs_btree_cur *cur, + struct xfs_bmbt_irec *rec, + void *priv) +{ + struct xrep_rtrmap_ifork *rf = priv; + struct xfs_rmap_irec *accum = &rf->accum; + struct xfs_mount *mp = rf->rr->sc->mp; + xfs_rgblock_t rgbno; + unsigned int rmap_flags = 0; + int error; + + if (xfs_rtb_to_rgno(mp, rec->br_startblock) != + rtg_rgno(rf->rr->sc->sr.rtg)) + return 0; + + if (rec->br_state == XFS_EXT_UNWRITTEN) + rmap_flags |= XFS_RMAP_UNWRITTEN; + + /* If this bmap is adjacent to the previous one, just add it. */ + rgbno = xfs_rtb_to_rgbno(mp, rec->br_startblock); + if (accum->rm_blockcount > 0 && + rec->br_startoff == accum->rm_offset + accum->rm_blockcount && + rgbno == accum->rm_startblock + accum->rm_blockcount && + rmap_flags == accum->rm_flags) { + accum->rm_blockcount += rec->br_blockcount; + return 0; + } + + /* Otherwise stash the old rmap and start accumulating a new one. */ + error = xrep_rtrmap_stash_accumulated(rf); + if (error) + return error; + + accum->rm_startblock = rgbno; + accum->rm_blockcount = rec->br_blockcount; + accum->rm_offset = rec->br_startoff; + accum->rm_flags = rmap_flags; + return 0; +} + +/* + * Iterate the block mapping btree to collect rmap records for anything in this + * fork that maps to the rt volume. Sets @mappings_done to true if we've + * scanned the block mappings in this fork. + */ +STATIC int +xrep_rtrmap_scan_bmbt( + struct xrep_rtrmap_ifork *rf, + struct xfs_inode *ip, + bool *mappings_done) +{ + struct xrep_rtrmap *rr = rf->rr; + struct xfs_btree_cur *cur; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + int error = 0; + + *mappings_done = false; + + /* + * If the incore extent cache is already loaded, we'll just use the + * incore extent scanner to record mappings. Don't bother walking the + * ondisk extent tree. + */ + if (!xfs_need_iread_extents(ifp)) + return 0; + + /* Accumulate all the mappings in the bmap btree. */ + cur = xfs_bmbt_init_cursor(rr->sc->mp, rr->sc->tp, ip, XFS_DATA_FORK); + error = xfs_bmap_query_all(cur, xrep_rtrmap_visit_bmbt, rf); + xfs_btree_del_cursor(cur, error); + if (error) + return error; + + /* Stash any remaining accumulated rmaps and exit. */ + *mappings_done = true; + return xrep_rtrmap_stash_accumulated(rf); +} + +/* + * Iterate the in-core extent cache to collect rmap records for anything in + * this fork that matches the AG. + */ +STATIC int +xrep_rtrmap_scan_iext( + struct xrep_rtrmap_ifork *rf, + struct xfs_ifork *ifp) +{ + struct xfs_bmbt_irec rec; + struct xfs_iext_cursor icur; + int error; + + for_each_xfs_iext(ifp, &icur, &rec) { + if (isnullstartblock(rec.br_startblock)) + continue; + error = xrep_rtrmap_visit_bmbt(NULL, &rec, rf); + if (error) + return error; + } + + return xrep_rtrmap_stash_accumulated(rf); +} + +/* Find all the extents on the realtime device mapped by an inode fork. */ +STATIC int +xrep_rtrmap_scan_dfork( + struct xrep_rtrmap *rr, + struct xfs_inode *ip) +{ + struct xrep_rtrmap_ifork rf = { + .accum = { .rm_owner = ip->i_ino, }, + .rr = rr, + }; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + int error = 0; + + if (ifp->if_format == XFS_DINODE_FMT_BTREE) { + bool mappings_done; + + /* + * Scan the bmbt for mappings. If the incore extent tree is + * loaded, we want to scan the cached mappings since that's + * faster when the extent counts are very high. + */ + error = xrep_rtrmap_scan_bmbt(&rf, ip, &mappings_done); + if (error || mappings_done) + return error; + } else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) { + /* realtime data forks should only be extents or btree */ + return -EFSCORRUPTED; + } + + /* Scan incore extent cache. */ + return xrep_rtrmap_scan_iext(&rf, ifp); +} + +/* Record reverse mappings for a file. */ +STATIC int +xrep_rtrmap_scan_inode( + struct xrep_rtrmap *rr, + struct xfs_inode *ip) +{ + unsigned int lock_mode; + int error = 0; + + /* Skip the rt rmap btree inode. */ + if (rr->sc->ip == ip) + return 0; + + lock_mode = xfs_ilock_data_map_shared(ip); + + /* Check the data fork if it's on the realtime device. */ + if (XFS_IS_REALTIME_INODE(ip)) { + error = xrep_rtrmap_scan_dfork(rr, ip); + if (error) + goto out_unlock; + } + + xchk_iscan_mark_visited(&rr->iscan, ip); +out_unlock: + xfs_iunlock(ip, lock_mode); + return error; +} + +/* Record extents that belong to the realtime rmap inode. */ +STATIC int +xrep_rtrmap_walk_rmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + int error = 0; + + if (xchk_should_terminate(rr->sc, &error)) + return error; + + /* Skip extents which are not owned by this inode and fork. */ + if (rec->rm_owner != rr->sc->ip->i_ino) + return 0; + + error = xrep_check_ino_btree_mapping(rr->sc, rec); + if (error) + return error; + + return xfsb_bitmap_set(&rr->old_rtrmapbt_blocks, + xfs_gbno_to_fsb(cur->bc_group, rec->rm_startblock), + rec->rm_blockcount); +} + +/* Scan one AG for reverse mappings for the realtime rmap btree. */ +STATIC int +xrep_rtrmap_scan_ag( + struct xrep_rtrmap *rr, + struct xfs_perag *pag) +{ + struct xfs_scrub *sc = rr->sc; + int error; + + error = xrep_ag_init(sc, pag, &sc->sa); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_rtrmap_walk_rmap, rr); + xchk_ag_free(sc, &sc->sa); + return error; +} + +struct xrep_rtrmap_stash_run { + struct xrep_rtrmap *rr; + uint64_t owner; +}; + +static int +xrep_rtrmap_stash_run( + uint32_t start, + uint32_t len, + void *priv) +{ + struct xrep_rtrmap_stash_run *rsr = priv; + struct xrep_rtrmap *rr = rsr->rr; + xfs_rgblock_t rgbno = start; + + return xrep_rtrmap_stash(rr, rgbno, len, rsr->owner, 0, 0); +} + +/* + * Emit rmaps for every extent of bits set in the bitmap. Caller must ensure + * that the ranges are in units of FS blocks. + */ +STATIC int +xrep_rtrmap_stash_bitmap( + struct xrep_rtrmap *rr, + struct xrgb_bitmap *bitmap, + const struct xfs_owner_info *oinfo) +{ + struct xrep_rtrmap_stash_run rsr = { + .rr = rr, + .owner = oinfo->oi_owner, + }; + + return xrgb_bitmap_walk(bitmap, xrep_rtrmap_stash_run, &rsr); +} + +/* Record a CoW staging extent. */ +STATIC int +xrep_rtrmap_walk_cowblocks( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *irec, + void *priv) +{ + struct xrgb_bitmap *bitmap = priv; + + if (!xfs_refcount_check_domain(irec) || + irec->rc_domain != XFS_REFC_DOMAIN_COW) + return -EFSCORRUPTED; + + return xrgb_bitmap_set(bitmap, irec->rc_startblock, + irec->rc_blockcount); +} + +/* + * Collect rmaps for the blocks containing the refcount btree, and all CoW + * staging extents. + */ +STATIC int +xrep_rtrmap_find_refcount_rmaps( + struct xrep_rtrmap *rr) +{ + struct xrgb_bitmap cow_blocks; /* COWBIT */ + struct xfs_refcount_irec low = { + .rc_startblock = 0, + .rc_domain = XFS_REFC_DOMAIN_COW, + }; + struct xfs_refcount_irec high = { + .rc_startblock = -1U, + .rc_domain = XFS_REFC_DOMAIN_COW, + }; + struct xfs_scrub *sc = rr->sc; + int error; + + if (!xfs_has_rtreflink(sc->mp)) + return 0; + + xrgb_bitmap_init(&cow_blocks); + + /* Collect rmaps for CoW staging extents. */ + error = xfs_refcount_query_range(sc->sr.refc_cur, &low, &high, + xrep_rtrmap_walk_cowblocks, &cow_blocks); + if (error) + goto out_bitmap; + + /* Generate rmaps for everything. */ + error = xrep_rtrmap_stash_bitmap(rr, &cow_blocks, &XFS_RMAP_OINFO_COW); + if (error) + goto out_bitmap; + +out_bitmap: + xrgb_bitmap_destroy(&cow_blocks); + return error; +} + +/* Count and check all collected records. */ +STATIC int +xrep_rtrmap_check_record( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + int error; + + error = xrep_rtrmap_check_mapping(rr->sc, rec); + if (error) + return error; + + rr->nr_records++; + return 0; +} + +/* Generate all the reverse-mappings for the realtime device. */ +STATIC int +xrep_rtrmap_find_rmaps( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct xfs_perag *pag = NULL; + struct xfs_inode *ip; + struct xfs_btree_cur *mcur; + int error; + + /* Generate rmaps for the realtime superblock */ + if (xfs_has_rtsb(sc->mp) && rtg_rgno(rr->sc->sr.rtg) == 0) { + error = xrep_rtrmap_stash(rr, 0, sc->mp->m_sb.sb_rextsize, + XFS_RMAP_OWN_FS, 0, 0); + if (error) + return error; + } + + /* Find CoW staging extents. */ + xrep_rtgroup_btcur_init(sc, &sc->sr); + error = xrep_rtrmap_find_refcount_rmaps(rr); + xchk_rtgroup_btcur_free(&sc->sr); + if (error) + return error; + + /* + * Set up for a potentially lengthy filesystem scan by reducing our + * transaction resource usage for the duration. Specifically: + * + * Unlock the realtime metadata inodes and cancel the transaction to + * release the log grant space while we scan the filesystem. + * + * Create a new empty transaction to eliminate the possibility of the + * inode scan deadlocking on cyclical metadata. + * + * We pass the empty transaction to the file scanning function to avoid + * repeatedly cycling empty transactions. This can be done even though + * we take the IOLOCK to quiesce the file because empty transactions + * do not take sb_internal. + */ + xchk_trans_cancel(sc); + xchk_rtgroup_unlock(&sc->sr); + error = xchk_trans_alloc_empty(sc); + if (error) + return error; + + while ((error = xchk_iscan_iter(&rr->iscan, &ip)) == 1) { + error = xrep_rtrmap_scan_inode(rr, ip); + xchk_irele(sc, ip); + if (error) + break; + + if (xchk_should_terminate(sc, &error)) + break; + } + xchk_iscan_iter_finish(&rr->iscan); + if (error) + return error; + + /* + * Switch out for a real transaction and lock the RT metadata in + * preparation for building a new tree. + */ + xchk_trans_cancel(sc); + error = xchk_setup_rt(sc); + if (error) + return error; + error = xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); + if (error) + return error; + + /* + * If a hook failed to update the in-memory btree, we lack the data to + * continue the repair. + */ + if (xchk_iscan_aborted(&rr->iscan)) + return -EFSCORRUPTED; + + /* Scan for old rtrmap blocks. */ + while ((pag = xfs_perag_next(sc->mp, pag))) { + error = xrep_rtrmap_scan_ag(rr, pag); + if (error) { + xfs_perag_rele(pag); + return error; + } + } + + /* + * Now that we have everything locked again, we need to count the + * number of rmap records stashed in the btree. This should reflect + * all actively-owned rt files in the filesystem. At the same time, + * check all our records before we start building a new btree, which + * requires the rtbitmap lock. + */ + mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, NULL, &rr->rtrmap_btree); + rr->nr_records = 0; + error = xfs_rmap_query_all(mcur, xrep_rtrmap_check_record, rr); + xfs_btree_del_cursor(mcur, error); + + return error; +} + +/* Building the new rtrmap btree. */ + +/* Retrieve rtrmapbt data for bulk load. */ +STATIC int +xrep_rtrmap_get_records( + struct xfs_btree_cur *cur, + unsigned int idx, + struct xfs_btree_block *block, + unsigned int nr_wanted, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + union xfs_btree_rec *block_rec; + unsigned int loaded; + int error; + + for (loaded = 0; loaded < nr_wanted; loaded++, idx++) { + int stat = 0; + + error = xfs_btree_increment(rr->mcur, 0, &stat); + if (error) + return error; + if (!stat) + return -EFSCORRUPTED; + + error = xfs_rmap_get_rec(rr->mcur, &cur->bc_rec.r, &stat); + if (error) + return error; + if (!stat) + return -EFSCORRUPTED; + + block_rec = xfs_btree_rec_addr(cur, idx, block); + cur->bc_ops->init_rec_from_cur(cur, block_rec); + } + + return loaded; +} + +/* Feed one of the new btree blocks to the bulk loader. */ +STATIC int +xrep_rtrmap_claim_block( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + + return xrep_newbt_claim_block(cur, &rr->new_btree, ptr); +} + +/* Figure out how much space we need to create the incore btree root block. */ +STATIC size_t +xrep_rtrmap_iroot_size( + struct xfs_btree_cur *cur, + unsigned int level, + unsigned int nr_this_level, + void *priv) +{ + return xfs_rtrmap_broot_space_calc(cur->bc_mp, level, nr_this_level); +} + +/* + * Use the collected rmap information to stage a new rmap btree. If this is + * successful we'll return with the new btree root information logged to the + * repair transaction but not yet committed. This implements section (III) + * above. + */ +STATIC int +xrep_rtrmap_build_new_tree( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct xfs_rtgroup *rtg = sc->sr.rtg; + struct xfs_btree_cur *rmap_cur; + int error; + + /* + * Prepare to construct the new btree by reserving disk space for the + * new btree and setting up all the accounting information we'll need + * to root the new btree while it's under construction and before we + * attach it to the realtime rmapbt inode. + */ + error = xrep_newbt_init_metadir_inode(&rr->new_btree, sc); + if (error) + return error; + + rr->new_btree.bload.get_records = xrep_rtrmap_get_records; + rr->new_btree.bload.claim_block = xrep_rtrmap_claim_block; + rr->new_btree.bload.iroot_size = xrep_rtrmap_iroot_size; + + rmap_cur = xfs_rtrmapbt_init_cursor(NULL, rtg); + xfs_btree_stage_ifakeroot(rmap_cur, &rr->new_btree.ifake); + + /* Compute how many blocks we'll need for the rmaps collected. */ + error = xfs_btree_bload_compute_geometry(rmap_cur, + &rr->new_btree.bload, rr->nr_records); + if (error) + goto err_cur; + + /* Last chance to abort before we start committing fixes. */ + if (xchk_should_terminate(sc, &error)) + goto err_cur; + + /* + * Guess how many blocks we're going to need to rebuild an entire + * rtrmapbt from the number of extents we found, and pump up our + * transaction to have sufficient block reservation. We're allowed + * to exceed quota to repair inconsistent metadata, though this is + * unlikely. + */ + error = xfs_trans_reserve_more_inode(sc->tp, rtg_rmap(rtg), + rr->new_btree.bload.nr_blocks, 0, true); + if (error) + goto err_cur; + + /* Reserve the space we'll need for the new btree. */ + error = xrep_newbt_alloc_blocks(&rr->new_btree, + rr->new_btree.bload.nr_blocks); + if (error) + goto err_cur; + + /* + * Create a cursor to the in-memory btree so that we can bulk load the + * new btree. + */ + rr->mcur = xfs_rtrmapbt_mem_cursor(sc->sr.rtg, NULL, &rr->rtrmap_btree); + error = xfs_btree_goto_left_edge(rr->mcur); + if (error) + goto err_mcur; + + /* Add all observed rmap records. */ + rr->new_btree.ifake.if_fork->if_format = XFS_DINODE_FMT_META_BTREE; + error = xfs_btree_bload(rmap_cur, &rr->new_btree.bload, rr); + if (error) + goto err_mcur; + + /* + * Install the new rtrmap btree in the inode. After this point the old + * btree is no longer accessible, the new tree is live, and we can + * delete the cursor. + */ + xfs_rtrmapbt_commit_staged_btree(rmap_cur, sc->tp); + xrep_inode_set_nblocks(rr->sc, rr->new_btree.ifake.if_blocks); + xfs_btree_del_cursor(rmap_cur, 0); + xfs_btree_del_cursor(rr->mcur, 0); + rr->mcur = NULL; + + /* + * Now that we've written the new btree to disk, we don't need to keep + * updating the in-memory btree. Abort the scan to stop live updates. + */ + xchk_iscan_abort(&rr->iscan); + + /* Dispose of any unused blocks and the accounting information. */ + error = xrep_newbt_commit(&rr->new_btree); + if (error) + return error; + + return xrep_roll_trans(sc); + +err_mcur: + xfs_btree_del_cursor(rr->mcur, error); +err_cur: + xfs_btree_del_cursor(rmap_cur, error); + xrep_newbt_cancel(&rr->new_btree); + return error; +} + +/* Reaping the old btree. */ + +/* Reap the old rtrmapbt blocks. */ +STATIC int +xrep_rtrmap_remove_old_tree( + struct xrep_rtrmap *rr) +{ + int error; + + /* + * Free all the extents that were allocated to the former rtrmapbt and + * aren't cross-linked with something else. + */ + error = xrep_reap_metadir_fsblocks(rr->sc, &rr->old_rtrmapbt_blocks); + if (error) + return error; + + /* + * Ensure the proper reservation for the rtrmap inode so that we don't + * fail to expand the new btree. + */ + return xrep_reset_metafile_resv(rr->sc); +} + +static inline bool +xrep_rtrmapbt_want_live_update( + struct xchk_iscan *iscan, + const struct xfs_owner_info *oi) +{ + if (xchk_iscan_aborted(iscan)) + return false; + + /* + * We scanned the CoW staging extents before we started the iscan, so + * we need all the updates. + */ + if (XFS_RMAP_NON_INODE_OWNER(oi->oi_owner)) + return true; + + /* Ignore updates to files that the scanner hasn't visited yet. */ + return xchk_iscan_want_live_update(iscan, oi->oi_owner); +} + +/* + * Apply a rtrmapbt update from the regular filesystem into our shadow btree. + * We're running from the thread that owns the rtrmap ILOCK and is generating + * the update, so we must be careful about which parts of the struct + * xrep_rtrmap that we change. + */ +static int +xrep_rtrmapbt_live_update( + struct notifier_block *nb, + unsigned long action, + void *data) +{ + struct xfs_rmap_update_params *p = data; + struct xrep_rtrmap *rr; + struct xfs_mount *mp; + struct xfs_btree_cur *mcur; + struct xfs_trans *tp; + void *txcookie; + int error; + + rr = container_of(nb, struct xrep_rtrmap, rhook.rmap_hook.nb); + mp = rr->sc->mp; + + if (!xrep_rtrmapbt_want_live_update(&rr->iscan, &p->oinfo)) + goto out_unlock; + + trace_xrep_rmap_live_update(rtg_group(rr->sc->sr.rtg), action, p); + + error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp); + if (error) + goto out_abort; + + mutex_lock(&rr->lock); + mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, tp, &rr->rtrmap_btree); + error = __xfs_rmap_finish_intent(mcur, action, p->startblock, + p->blockcount, &p->oinfo, p->unwritten); + xfs_btree_del_cursor(mcur, error); + if (error) + goto out_cancel; + + error = xfbtree_trans_commit(&rr->rtrmap_btree, tp); + if (error) + goto out_cancel; + + xrep_trans_cancel_hook_dummy(&txcookie, tp); + mutex_unlock(&rr->lock); + return NOTIFY_DONE; + +out_cancel: + xfbtree_trans_cancel(&rr->rtrmap_btree, tp); + xrep_trans_cancel_hook_dummy(&txcookie, tp); +out_abort: + xchk_iscan_abort(&rr->iscan); + mutex_unlock(&rr->lock); +out_unlock: + return NOTIFY_DONE; +} + +/* Set up the filesystem scan components. */ +STATIC int +xrep_rtrmap_setup_scan( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + int error; + + mutex_init(&rr->lock); + xfsb_bitmap_init(&rr->old_rtrmapbt_blocks); + + /* Set up some storage */ + error = xfs_rtrmapbt_mem_init(sc->mp, &rr->rtrmap_btree, sc->xmbtp, + rtg_rgno(sc->sr.rtg)); + if (error) + goto out_bitmap; + + /* Retry iget every tenth of a second for up to 30 seconds. */ + xchk_iscan_start(sc, 30000, 100, &rr->iscan); + + /* + * Hook into live rtrmap operations so that we can update our in-memory + * btree to reflect live changes on the filesystem. Since we drop the + * rtrmap ILOCK to scan all the inodes, we need this piece to avoid + * installing a stale btree. + */ + ASSERT(sc->flags & XCHK_FSGATES_RMAP); + xfs_rmap_hook_setup(&rr->rhook, xrep_rtrmapbt_live_update); + error = xfs_rmap_hook_add(rtg_group(sc->sr.rtg), &rr->rhook); + if (error) + goto out_iscan; + return 0; + +out_iscan: + xchk_iscan_teardown(&rr->iscan); + xfbtree_destroy(&rr->rtrmap_btree); +out_bitmap: + xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks); + mutex_destroy(&rr->lock); + return error; +} + +/* Tear down scan components. */ +STATIC void +xrep_rtrmap_teardown( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + + xchk_iscan_abort(&rr->iscan); + xfs_rmap_hook_del(rtg_group(sc->sr.rtg), &rr->rhook); + xchk_iscan_teardown(&rr->iscan); + xfbtree_destroy(&rr->rtrmap_btree); + xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks); + mutex_destroy(&rr->lock); +} + +/* Repair the realtime rmap btree. */ +int +xrep_rtrmapbt( + struct xfs_scrub *sc) +{ + struct xrep_rtrmap *rr = sc->buf; + int error; + + /* Make sure any problems with the fork are fixed. */ + error = xrep_metadata_inode_forks(sc); + if (error) + return error; + + error = xrep_rtrmap_setup_scan(rr); + if (error) + return error; + + /* Collect rmaps for realtime files. */ + error = xrep_rtrmap_find_rmaps(rr); + if (error) + goto out_records; + + xfs_trans_ijoin(sc->tp, sc->ip, 0); + + /* Rebuild the rtrmap information. */ + error = xrep_rtrmap_build_new_tree(rr); + if (error) + goto out_records; + + /* Kill the old tree. */ + error = xrep_rtrmap_remove_old_tree(rr); + if (error) + goto out_records; + +out_records: + xrep_rtrmap_teardown(rr); + return error; +} diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c index 49fc6250bafc..4ac679c1bd29 100644 --- a/fs/xfs/scrub/rtsummary.c +++ b/fs/xfs/scrub/rtsummary.c @@ -81,8 +81,7 @@ xchk_setup_rtsummary( if (error) return error; - error = xchk_install_live_inode(sc, - sc->sr.rtg->rtg_inodes[XFS_RTGI_SUMMARY]); + error = xchk_install_live_inode(sc, rtg_summary(sc->sr.rtg)); if (error) return error; @@ -90,6 +89,10 @@ xchk_setup_rtsummary( if (error) return error; + error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP); + if (error) + return error; + /* * Now that we've locked the rtbitmap and rtsummary, we can't race with * growfsrt trying to expand the summary or change the size of the rt @@ -100,7 +103,6 @@ xchk_setup_rtsummary( * exclusively here. If we ever start caring about running concurrent * fsmap with scrub this could be changed. */ - xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP); if (mp->m_sb.sb_rblocks) { rts->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks); rts->rbmblocks = xfs_rtbitmap_blockcount(mp); @@ -191,8 +193,7 @@ xchk_rtsum_record_free( rtlen = xfs_rtxlen_to_extlen(mp, rec->ar_extcount); if (!xfs_verify_rtbext(mp, rtbno, rtlen)) { - xchk_ino_xref_set_corrupt(sc, - rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_ino); + xchk_ino_xref_set_corrupt(sc, rtg_bitmap(rtg)->i_ino); return -EFSCORRUPTED; } @@ -218,7 +219,7 @@ xchk_rtsum_compute( /* If the bitmap size doesn't match the computed size, bail. */ if (XFS_FSB_TO_B(mp, xfs_rtbitmap_blockcount(mp)) != - rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_disk_size) + rtg_bitmap(rtg)->i_disk_size) return -EFSCORRUPTED; return xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtsum_record_free, sc); @@ -310,8 +311,8 @@ xchk_rtsummary( { struct xfs_mount *mp = sc->mp; struct xfs_rtgroup *rtg = sc->sr.rtg; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; - struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_inode *rsumip = rtg_summary(rtg); struct xchk_rtsummary *rts = sc->buf; int error; diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c index 8198ea84ad70..d593977d70df 100644 --- a/fs/xfs/scrub/rtsummary_repair.c +++ b/fs/xfs/scrub/rtsummary_repair.c @@ -165,7 +165,8 @@ xrep_rtsummary( * Now exchange the contents. Nothing in repair uses the temporary * buffer, so we can reuse it for the tempfile exchrange information. */ - error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, &rts->tempexch); + error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0, + rts->rsumblocks, &rts->tempexch); if (error) return error; diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 950f5a58dcd9..7567dd5cad14 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -164,7 +164,7 @@ xchk_fsgates_disable( trace_xchk_fsgates_disable(sc, sc->flags & XCHK_FSGATES_ALL); if (sc->flags & XCHK_FSGATES_DRAIN) - xfs_drain_wait_disable(); + xfs_defer_drain_wait_disable(); if (sc->flags & XCHK_FSGATES_QUOTA) xfs_dqtrx_hook_disable(); @@ -218,6 +218,8 @@ xchk_teardown( int error) { xchk_ag_free(sc, &sc->sa); + xchk_rtgroup_btcur_free(&sc->sr); + if (sc->tp) { if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)) error = xfs_trans_commit(sc->tp); @@ -458,6 +460,20 @@ static const struct xchk_meta_ops meta_scrub_ops[] = { .has = xfs_has_rtsb, .repair = xrep_rgsuperblock, }, + [XFS_SCRUB_TYPE_RTRMAPBT] = { /* realtime group rmapbt */ + .type = ST_RTGROUP, + .setup = xchk_setup_rtrmapbt, + .scrub = xchk_rtrmapbt, + .has = xfs_has_rtrmapbt, + .repair = xrep_rtrmapbt, + }, + [XFS_SCRUB_TYPE_RTREFCBT] = { /* realtime refcountbt */ + .type = ST_RTGROUP, + .setup = xchk_setup_rtrefcountbt, + .scrub = xchk_rtrefcountbt, + .has = xfs_has_rtreflink, + .repair = xrep_rtrefcountbt, + }, }; static int diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index 5dbbe93cb49b..a3f1abc91390 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -96,7 +96,7 @@ struct xchk_meta_ops { int (*repair_eval)(struct xfs_scrub *sc); /* Decide if we even have this piece of metadata. */ - bool (*has)(struct xfs_mount *); + bool (*has)(const struct xfs_mount *); /* type describing required/allowed inputs */ enum xchk_type type; @@ -126,6 +126,10 @@ struct xchk_rt { /* XFS_RTGLOCK_* lock state if locked */ unsigned int rtlock_flags; + + /* rtgroup btrees */ + struct xfs_btree_cur *rmap_cur; + struct xfs_btree_cur *refc_cur; }; struct xfs_scrub { @@ -280,10 +284,14 @@ int xchk_metapath(struct xfs_scrub *sc); int xchk_rtbitmap(struct xfs_scrub *sc); int xchk_rtsummary(struct xfs_scrub *sc); int xchk_rgsuperblock(struct xfs_scrub *sc); +int xchk_rtrmapbt(struct xfs_scrub *sc); +int xchk_rtrefcountbt(struct xfs_scrub *sc); #else # define xchk_rtbitmap xchk_nothing # define xchk_rtsummary xchk_nothing # define xchk_rgsuperblock xchk_nothing +# define xchk_rtrmapbt xchk_nothing +# define xchk_rtrefcountbt xchk_nothing #endif #ifdef CONFIG_XFS_QUOTA int xchk_quota(struct xfs_scrub *sc); @@ -317,8 +325,26 @@ void xchk_xref_is_not_cow_staging(struct xfs_scrub *sc, xfs_agblock_t bno, #ifdef CONFIG_XFS_RT void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno, xfs_extlen_t len); +void xchk_xref_has_no_rt_owner(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_has_rt_owner(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_is_only_rt_owned_by(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len, const struct xfs_owner_info *oinfo); +void xchk_xref_is_rt_cow_staging(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_is_not_rt_shared(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_is_not_rt_cow_staging(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); #else # define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0) +# define xchk_xref_has_no_rt_owner(sc, rtbno, len) do { } while (0) +# define xchk_xref_has_rt_owner(sc, rtbno, len) do { } while (0) +# define xchk_xref_is_only_rt_owned_by(sc, bno, len, oinfo) do { } while (0) +# define xchk_xref_is_rt_cow_staging(sc, bno, len) do { } while (0) +# define xchk_xref_is_not_rt_shared(sc, bno, len) do { } while (0) +# define xchk_xref_is_not_rt_cow_staging(sc, bno, len) do { } while (0) #endif #endif /* __XFS_SCRUB_SCRUB_H__ */ diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index a476c7b2ab75..f8a37ea97791 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -82,6 +82,8 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = { [XFS_SCRUB_TYPE_DIRTREE] = "dirtree", [XFS_SCRUB_TYPE_METAPATH] = "metapath", [XFS_SCRUB_TYPE_RGSUPER] = "rgsuper", + [XFS_SCRUB_TYPE_RTRMAPBT] = "rtrmapbt", + [XFS_SCRUB_TYPE_RTREFCBT] = "rtrefcountbt", }; /* Format the scrub stats into a text buffer, similar to pcp style. */ diff --git a/fs/xfs/scrub/tempexch.h b/fs/xfs/scrub/tempexch.h index 995ba187c5aa..eccda720c2ca 100644 --- a/fs/xfs/scrub/tempexch.h +++ b/fs/xfs/scrub/tempexch.h @@ -12,7 +12,7 @@ struct xrep_tempexch { }; int xrep_tempexch_trans_reserve(struct xfs_scrub *sc, int whichfork, - struct xrep_tempexch *ti); + xfs_fileoff_t off, xfs_filblks_t len, struct xrep_tempexch *ti); int xrep_tempexch_trans_alloc(struct xfs_scrub *sc, int whichfork, struct xrep_tempexch *ti); diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c index 2d7ca7e1bbca..cf99e0ca51b0 100644 --- a/fs/xfs/scrub/tempfile.c +++ b/fs/xfs/scrub/tempfile.c @@ -606,6 +606,8 @@ STATIC int xrep_tempexch_prep_request( struct xfs_scrub *sc, int whichfork, + xfs_fileoff_t off, + xfs_filblks_t len, struct xrep_tempexch *tx) { struct xfs_exchmaps_req *req = &tx->req; @@ -629,18 +631,19 @@ xrep_tempexch_prep_request( /* Exchange all mappings in both forks. */ req->ip1 = sc->tempip; req->ip2 = sc->ip; - req->startoff1 = 0; - req->startoff2 = 0; + req->startoff1 = off; + req->startoff2 = off; switch (whichfork) { case XFS_ATTR_FORK: req->flags |= XFS_EXCHMAPS_ATTR_FORK; break; case XFS_DATA_FORK: - /* Always exchange sizes when exchanging data fork mappings. */ - req->flags |= XFS_EXCHMAPS_SET_SIZES; + /* Exchange sizes when exchanging all data fork mappings. */ + if (off == 0 && len == XFS_MAX_FILEOFF) + req->flags |= XFS_EXCHMAPS_SET_SIZES; break; } - req->blockcount = XFS_MAX_FILEOFF; + req->blockcount = len; return 0; } @@ -749,6 +752,7 @@ xrep_tempexch_reserve_quota( * or the two inodes have the same dquots. */ if (!XFS_IS_QUOTA_ON(tp->t_mountp) || req->ip1 == req->ip2 || + xfs_is_metadir_inode(req->ip1) || (req->ip1->i_udquot == req->ip2->i_udquot && req->ip1->i_gdquot == req->ip2->i_gdquot && req->ip1->i_pdquot == req->ip2->i_pdquot)) @@ -795,6 +799,8 @@ int xrep_tempexch_trans_reserve( struct xfs_scrub *sc, int whichfork, + xfs_fileoff_t off, + xfs_filblks_t len, struct xrep_tempexch *tx) { int error; @@ -803,7 +809,7 @@ xrep_tempexch_trans_reserve( xfs_assert_ilocked(sc->ip, XFS_ILOCK_EXCL); xfs_assert_ilocked(sc->tempip, XFS_ILOCK_EXCL); - error = xrep_tempexch_prep_request(sc, whichfork, tx); + error = xrep_tempexch_prep_request(sc, whichfork, off, len, tx); if (error) return error; @@ -841,7 +847,8 @@ xrep_tempexch_trans_alloc( ASSERT(sc->tp == NULL); ASSERT(xfs_has_exchange_range(sc->mp)); - error = xrep_tempexch_prep_request(sc, whichfork, tx); + error = xrep_tempexch_prep_request(sc, whichfork, 0, XFS_MAX_FILEOFF, + tx); if (error) return error; diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c index 98f923ae664d..2450e214103f 100644 --- a/fs/xfs/scrub/trace.c +++ b/fs/xfs/scrub/trace.c @@ -21,6 +21,7 @@ #include "xfs_rmap.h" #include "xfs_parent.h" #include "xfs_metafile.h" +#include "xfs_rtgroup.h" #include "scrub/scrub.h" #include "scrub/xfile.h" #include "scrub/xfarray.h" diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index d2ae7e93acb0..d7c4ced47c15 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -17,6 +17,7 @@ #include "xfs_bit.h" #include "xfs_quota_defs.h" +struct xfs_rtgroup; struct xfs_scrub; struct xfile; struct xfarray; @@ -40,6 +41,9 @@ struct xchk_dirtree_outcomes; TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED); TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW); +TRACE_DEFINE_ENUM(XG_TYPE_AG); +TRACE_DEFINE_ENUM(XG_TYPE_RTG); + TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PROBE); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_SB); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_AGF); @@ -72,6 +76,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_DIRTREE); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_BARRIER); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_METAPATH); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RGSUPER); +TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTRMAPBT); +TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTREFCBT); #define XFS_SCRUB_TYPE_STRINGS \ { XFS_SCRUB_TYPE_PROBE, "probe" }, \ @@ -105,7 +111,9 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RGSUPER); { XFS_SCRUB_TYPE_DIRTREE, "dirtree" }, \ { XFS_SCRUB_TYPE_BARRIER, "barrier" }, \ { XFS_SCRUB_TYPE_METAPATH, "metapath" }, \ - { XFS_SCRUB_TYPE_RGSUPER, "rgsuper" } + { XFS_SCRUB_TYPE_RGSUPER, "rgsuper" }, \ + { XFS_SCRUB_TYPE_RTRMAPBT, "rtrmapbt" }, \ + { XFS_SCRUB_TYPE_RTREFCBT, "rtrefcountbt" } #define XFS_SCRUB_FLAG_STRINGS \ { XFS_SCRUB_IFLAG_REPAIR, "repair" }, \ @@ -1956,32 +1964,36 @@ DEFINE_XCHK_METAPATH_EVENT(xchk_metapath_lookup); #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) DECLARE_EVENT_CLASS(xrep_extent_class, - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, xfs_extlen_t len), - TP_ARGS(pag, agbno, len), + TP_ARGS(xg, agbno, len), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->type = xg->xg_type; + __entry->agno = xg->xg_gno; __entry->agbno = agbno; __entry->len = len; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x", + TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len) ); #define DEFINE_REPAIR_EXTENT_EVENT(name) \ DEFINE_EVENT(xrep_extent_class, name, \ - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \ + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, \ xfs_extlen_t len), \ - TP_ARGS(pag, agbno, len)) + TP_ARGS(xg, agbno, len)) DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_unmap_extent); DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_free_extent); DEFINE_REPAIR_EXTENT_EVENT(xreap_agextent_binval); @@ -1989,35 +2001,39 @@ DEFINE_REPAIR_EXTENT_EVENT(xreap_bmapi_binval); DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert); DECLARE_EVENT_CLASS(xrep_reap_find_class, - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, xfs_extlen_t len, bool crosslinked), - TP_ARGS(pag, agbno, len, crosslinked), + TP_ARGS(xg, agbno, len, crosslinked), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) __field(bool, crosslinked) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->type = xg->xg_type; + __entry->agno = xg->xg_gno; __entry->agbno = agbno; __entry->len = len; __entry->crosslinked = crosslinked; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x crosslinked %d", + TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x crosslinked %d", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len, __entry->crosslinked ? 1 : 0) ); #define DEFINE_REPAIR_REAP_FIND_EVENT(name) \ DEFINE_EVENT(xrep_reap_find_class, name, \ - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \ + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, \ xfs_extlen_t len, bool crosslinked), \ - TP_ARGS(pag, agbno, len, crosslinked)) + TP_ARGS(xg, agbno, len, crosslinked)) DEFINE_REPAIR_REAP_FIND_EVENT(xreap_agextent_select); DEFINE_REPAIR_REAP_FIND_EVENT(xreap_bmapi_select); @@ -2108,29 +2124,33 @@ TRACE_EVENT(xrep_ibt_found, ) TRACE_EVENT(xrep_refc_found, - TP_PROTO(const struct xfs_perag *pag, + TP_PROTO(const struct xfs_group *xg, const struct xfs_refcount_irec *rec), - TP_ARGS(pag, rec), + TP_ARGS(xg, rec), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) + __field(enum xfs_group_type, type) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->agno = xg->xg_gno; + __entry->type = xg->xg_type; __entry->domain = rec->rc_domain; __entry->startblock = rec->rc_startblock; __entry->blockcount = rec->rc_blockcount; __entry->refcount = rec->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s %sbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount) @@ -2282,6 +2302,32 @@ TRACE_EVENT(xrep_calc_ag_resblks_btsize, __entry->rmapbt_sz, __entry->refcbt_sz) ) + +#ifdef CONFIG_XFS_RT +TRACE_EVENT(xrep_calc_rtgroup_resblks_btsize, + TP_PROTO(struct xfs_mount *mp, xfs_rgnumber_t rgno, + xfs_rgblock_t usedlen, xfs_rgblock_t rmapbt_sz), + TP_ARGS(mp, rgno, usedlen, rmapbt_sz), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_rgblock_t, usedlen) + __field(xfs_rgblock_t, rmapbt_sz) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rgno = rgno; + __entry->usedlen = usedlen; + __entry->rmapbt_sz = rmapbt_sz; + ), + TP_printk("dev %d:%d rgno 0x%x usedlen %u rmapbt %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rgno, + __entry->usedlen, + __entry->rmapbt_sz) +); +#endif /* CONFIG_XFS_RT */ + TRACE_EVENT(xrep_reset_counters, TP_PROTO(struct xfs_mount *mp, struct xchk_fscounters *fsc), TP_ARGS(mp, fsc), @@ -2680,11 +2726,12 @@ DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_update_inode); DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_unfixable_inode); TRACE_EVENT(xrep_rmap_live_update, - TP_PROTO(const struct xfs_perag *pag, unsigned int op, + TP_PROTO(const struct xfs_group *xg, unsigned int op, const struct xfs_rmap_update_params *p), - TP_ARGS(pag, op, p), + TP_ARGS(xg, op, p), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(unsigned int, op) __field(xfs_agblock_t, agbno) @@ -2694,8 +2741,9 @@ TRACE_EVENT(xrep_rmap_live_update, __field(unsigned int, flags) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->type = xg->xg_type; + __entry->agno = xg->xg_gno; __entry->op = op; __entry->agbno = p->startblock; __entry->len = p->blockcount; @@ -2704,10 +2752,12 @@ TRACE_EVENT(xrep_rmap_live_update, if (p->unwritten) __entry->flags |= XFS_RMAP_UNWRITTEN; ), - TP_printk("dev %d:%d agno 0x%x op %d agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", + TP_printk("dev %d:%d %sno 0x%x op %d %sbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->op, + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len, __entry->owner, @@ -3605,6 +3655,186 @@ DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_try_unlink); DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_unlink); DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_link); +#ifdef CONFIG_XFS_RT +DECLARE_EVENT_CLASS(xrep_rtbitmap_class, + TP_PROTO(struct xfs_mount *mp, xfs_rtxnum_t start, xfs_rtxnum_t end), + TP_ARGS(mp, start, end), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_rtxnum_t, start) + __field(xfs_rtxnum_t, end) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->start = start; + __entry->end = end; + ), + TP_printk("dev %d:%d rtdev %d:%d startrtx 0x%llx endrtx 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->start, + __entry->end) +); +#define DEFINE_REPAIR_RGBITMAP_EVENT(name) \ +DEFINE_EVENT(xrep_rtbitmap_class, name, \ + TP_PROTO(struct xfs_mount *mp, xfs_rtxnum_t start, \ + xfs_rtxnum_t end), \ + TP_ARGS(mp, start, end)) +DEFINE_REPAIR_RGBITMAP_EVENT(xrep_rtbitmap_record_free); +DEFINE_REPAIR_RGBITMAP_EVENT(xrep_rtbitmap_record_free_bulk); + +TRACE_EVENT(xrep_rtbitmap_or, + TP_PROTO(struct xfs_mount *mp, unsigned long long wordoff, + xfs_rtword_t mask, xfs_rtword_t word), + TP_ARGS(mp, wordoff, mask, word), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(unsigned long long, wordoff) + __field(unsigned int, mask) + __field(unsigned int, word) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->wordoff = wordoff; + __entry->mask = mask; + __entry->word = word; + ), + TP_printk("dev %d:%d rtdev %d:%d wordoff 0x%llx mask 0x%x word 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->wordoff, + __entry->mask, + __entry->word) +); + +TRACE_EVENT(xrep_rtbitmap_load, + TP_PROTO(struct xfs_rtgroup *rtg, xfs_fileoff_t rbmoff, + xfs_rtxnum_t rtx, xfs_rtxnum_t len), + TP_ARGS(rtg, rbmoff, rtx, len), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_fileoff_t, rbmoff) + __field(xfs_rtxnum_t, rtx) + __field(xfs_rtxnum_t, len) + ), + TP_fast_assign( + __entry->dev = rtg_mount(rtg)->m_super->s_dev; + __entry->rtdev = rtg_mount(rtg)->m_rtdev_targp->bt_dev; + __entry->rgno = rtg_rgno(rtg); + __entry->rbmoff = rbmoff; + __entry->rtx = rtx; + __entry->len = len; + ), + TP_printk("dev %d:%d rtdev %d:%d rgno 0x%x rbmoff 0x%llx rtx 0x%llx rtxcount 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->rgno, + __entry->rbmoff, + __entry->rtx, + __entry->len) +); + +TRACE_EVENT(xrep_rtbitmap_load_words, + TP_PROTO(struct xfs_mount *mp, xfs_fileoff_t rbmoff, + unsigned long long wordoff, unsigned int wordcnt), + TP_ARGS(mp, rbmoff, wordoff, wordcnt), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_fileoff_t, rbmoff) + __field(unsigned long long, wordoff) + __field(unsigned int, wordcnt) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->rbmoff = rbmoff; + __entry->wordoff = wordoff; + __entry->wordcnt = wordcnt; + ), + TP_printk("dev %d:%d rtdev %d:%d rbmoff 0x%llx wordoff 0x%llx wordcnt 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->rbmoff, + __entry->wordoff, + __entry->wordcnt) +); + +TRACE_EVENT(xrep_rtbitmap_load_word, + TP_PROTO(struct xfs_mount *mp, unsigned long long wordoff, + unsigned int bit, xfs_rtword_t ondisk_word, + xfs_rtword_t xfile_word, xfs_rtword_t word_mask), + TP_ARGS(mp, wordoff, bit, ondisk_word, xfile_word, word_mask), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(unsigned long long, wordoff) + __field(unsigned int, bit) + __field(xfs_rtword_t, ondisk_word) + __field(xfs_rtword_t, xfile_word) + __field(xfs_rtword_t, word_mask) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->wordoff = wordoff; + __entry->bit = bit; + __entry->ondisk_word = ondisk_word; + __entry->xfile_word = xfile_word; + __entry->word_mask = word_mask; + ), + TP_printk("dev %d:%d rtdev %d:%d wordoff 0x%llx bit %u ondisk 0x%x(0x%x) inmem 0x%x(0x%x) result 0x%x mask 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->wordoff, + __entry->bit, + __entry->ondisk_word, + __entry->ondisk_word & __entry->word_mask, + __entry->xfile_word, + __entry->xfile_word & ~__entry->word_mask, + (__entry->xfile_word & ~__entry->word_mask) | + (__entry->ondisk_word & __entry->word_mask), + __entry->word_mask) +); + +TRACE_EVENT(xrep_rtrmap_found, + TP_PROTO(struct xfs_mount *mp, const struct xfs_rmap_irec *rec), + TP_ARGS(mp, rec), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_rgblock_t, rgbno) + __field(xfs_extlen_t, len) + __field(uint64_t, owner) + __field(uint64_t, offset) + __field(unsigned int, flags) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->rgbno = rec->rm_startblock; + __entry->len = rec->rm_blockcount; + __entry->owner = rec->rm_owner; + __entry->offset = rec->rm_offset; + __entry->flags = rec->rm_flags; + ), + TP_printk("dev %d:%d rtdev %d:%d rgbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->rgbno, + __entry->len, + __entry->owner, + __entry->offset, + __entry->flags) +); +#endif /* CONFIG_XFS_RT */ + #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */ #endif /* _TRACE_XFS_SCRUB_TRACE_H */ diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 559a3a577097..67877c36ed11 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -131,7 +131,7 @@ xfs_end_ioend( error = xfs_iomap_write_unwritten(ip, offset, size, false); if (!error && xfs_ioend_is_append(ioend)) - error = xfs_setfilesize(ip, ioend->io_offset, ioend->io_size); + error = xfs_setfilesize(ip, offset, size); done: iomap_finish_ioends(ioend, error); memalloc_nofs_restore(nofs_flag); diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 24fb12986a56..319004bf089f 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -305,11 +305,6 @@ xfs_attr3_root_inactive( XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, &bp); if (error) return error; - error = bp->b_error; - if (error) { - xfs_trans_brelse(*trans, bp); - return error; - } xfs_trans_binval(*trans, bp); /* remove from cache */ /* * Commit the invalidate and start the next transaction. diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index aa63b8efd782..d1d4a0a22e13 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -22,6 +22,7 @@ #include "xfs_error.h" #include "xfs_ag.h" #include "xfs_buf_mem.h" +#include "xfs_notify_failure.h" struct kmem_cache *xfs_buf_cache; @@ -52,14 +53,8 @@ struct kmem_cache *xfs_buf_cache; * b_lock (trylock due to inversion) */ -static int __xfs_buf_submit(struct xfs_buf *bp, bool wait); - -static inline int -xfs_buf_submit( - struct xfs_buf *bp) -{ - return __xfs_buf_submit(bp, !(bp->b_flags & XBF_ASYNC)); -} +static void xfs_buf_submit(struct xfs_buf *bp); +static int xfs_buf_iowait(struct xfs_buf *bp); static inline bool xfs_buf_is_uncached(struct xfs_buf *bp) { @@ -132,15 +127,6 @@ __xfs_buf_ioacct_dec( } } -static inline void -xfs_buf_ioacct_dec( - struct xfs_buf *bp) -{ - spin_lock(&bp->b_lock); - __xfs_buf_ioacct_dec(bp); - spin_unlock(&bp->b_lock); -} - /* * When we mark a buffer stale, we remove the buffer from the LRU and clear the * b_lru_ref count so that the buffer is freed immediately when the buffer @@ -176,9 +162,9 @@ xfs_buf_stale( atomic_set(&bp->b_lru_ref, 0); if (!(bp->b_state & XFS_BSTATE_DISPOSE) && (list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru))) - atomic_dec(&bp->b_hold); + bp->b_hold--; - ASSERT(atomic_read(&bp->b_hold) >= 1); + ASSERT(bp->b_hold >= 1); spin_unlock(&bp->b_lock); } @@ -202,9 +188,6 @@ xfs_buf_get_maps( return 0; } -/* - * Frees b_pages if it was allocated. - */ static void xfs_buf_free_maps( struct xfs_buf *bp) @@ -237,14 +220,14 @@ _xfs_buf_alloc( */ flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD); - atomic_set(&bp->b_hold, 1); + spin_lock_init(&bp->b_lock); + bp->b_hold = 1; atomic_set(&bp->b_lru_ref, 1); init_completion(&bp->b_iowait); INIT_LIST_HEAD(&bp->b_lru); INIT_LIST_HEAD(&bp->b_list); INIT_LIST_HEAD(&bp->b_li_list); sema_init(&bp->b_sema, 0); /* held, no waiters */ - spin_lock_init(&bp->b_lock); bp->b_target = target; bp->b_mount = target->bt_mount; bp->b_flags = flags; @@ -395,8 +378,8 @@ xfs_buf_alloc_pages( for (;;) { long last = filled; - filled = alloc_pages_bulk_array(gfp_mask, bp->b_page_count, - bp->b_pages); + filled = alloc_pages_bulk(gfp_mask, bp->b_page_count, + bp->b_pages); if (filled == bp->b_page_count) { XFS_STATS_INC(bp->b_mount, xb_page_found); break; @@ -588,6 +571,20 @@ xfs_buf_find_lock( return 0; } +static bool +xfs_buf_try_hold( + struct xfs_buf *bp) +{ + spin_lock(&bp->b_lock); + if (bp->b_hold == 0) { + spin_unlock(&bp->b_lock); + return false; + } + bp->b_hold++; + spin_unlock(&bp->b_lock); + return true; +} + static inline int xfs_buf_lookup( struct xfs_buf_cache *bch, @@ -600,7 +597,7 @@ xfs_buf_lookup( rcu_read_lock(); bp = rhashtable_lookup(&bch->bc_hash, map, xfs_buf_hash_params); - if (!bp || !atomic_inc_not_zero(&bp->b_hold)) { + if (!bp || !xfs_buf_try_hold(bp)) { rcu_read_unlock(); return -ENOENT; } @@ -663,9 +660,8 @@ xfs_buf_find_insert( spin_unlock(&bch->bc_lock); goto out_free_buf; } - if (bp) { + if (bp && xfs_buf_try_hold(bp)) { /* found an existing buffer */ - atomic_inc(&bp->b_hold); spin_unlock(&bch->bc_lock); error = xfs_buf_find_lock(bp, flags); if (error) @@ -806,7 +802,10 @@ _xfs_buf_read( bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD | XBF_DONE); bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD); - return xfs_buf_submit(bp); + xfs_buf_submit(bp); + if (flags & XBF_ASYNC) + return 0; + return xfs_buf_iowait(bp); } /* @@ -982,8 +981,8 @@ xfs_buf_read_uncached( bp->b_ops = ops; xfs_buf_submit(bp); - if (bp->b_error) { - error = bp->b_error; + error = xfs_buf_iowait(bp); + if (error) { xfs_buf_relse(bp); return error; } @@ -1043,7 +1042,10 @@ xfs_buf_hold( struct xfs_buf *bp) { trace_xfs_buf_hold(bp, _RET_IP_); - atomic_inc(&bp->b_hold); + + spin_lock(&bp->b_lock); + bp->b_hold++; + spin_unlock(&bp->b_lock); } static void @@ -1051,10 +1053,15 @@ xfs_buf_rele_uncached( struct xfs_buf *bp) { ASSERT(list_empty(&bp->b_lru)); - if (atomic_dec_and_test(&bp->b_hold)) { - xfs_buf_ioacct_dec(bp); - xfs_buf_free(bp); + + spin_lock(&bp->b_lock); + if (--bp->b_hold) { + spin_unlock(&bp->b_lock); + return; } + __xfs_buf_ioacct_dec(bp); + spin_unlock(&bp->b_lock); + xfs_buf_free(bp); } static void @@ -1064,51 +1071,40 @@ xfs_buf_rele_cached( struct xfs_buftarg *btp = bp->b_target; struct xfs_perag *pag = bp->b_pag; struct xfs_buf_cache *bch = xfs_buftarg_buf_cache(btp, pag); - bool release; bool freebuf = false; trace_xfs_buf_rele(bp, _RET_IP_); - ASSERT(atomic_read(&bp->b_hold) > 0); - - /* - * We grab the b_lock here first to serialise racing xfs_buf_rele() - * calls. The pag_buf_lock being taken on the last reference only - * serialises against racing lookups in xfs_buf_find(). IOWs, the second - * to last reference we drop here is not serialised against the last - * reference until we take bp->b_lock. Hence if we don't grab b_lock - * first, the last "release" reference can win the race to the lock and - * free the buffer before the second-to-last reference is processed, - * leading to a use-after-free scenario. - */ spin_lock(&bp->b_lock); - release = atomic_dec_and_lock(&bp->b_hold, &bch->bc_lock); - if (!release) { + ASSERT(bp->b_hold >= 1); + if (bp->b_hold > 1) { /* * Drop the in-flight state if the buffer is already on the LRU * and it holds the only reference. This is racy because we * haven't acquired the pag lock, but the use of _XBF_IN_FLIGHT * ensures the decrement occurs only once per-buf. */ - if ((atomic_read(&bp->b_hold) == 1) && !list_empty(&bp->b_lru)) + if (--bp->b_hold == 1 && !list_empty(&bp->b_lru)) __xfs_buf_ioacct_dec(bp); goto out_unlock; } - /* the last reference has been dropped ... */ + /* we are asked to drop the last reference */ + spin_lock(&bch->bc_lock); __xfs_buf_ioacct_dec(bp); if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) { /* - * If the buffer is added to the LRU take a new reference to the + * If the buffer is added to the LRU, keep the reference to the * buffer for the LRU and clear the (now stale) dispose list - * state flag + * state flag, else drop the reference. */ - if (list_lru_add_obj(&btp->bt_lru, &bp->b_lru)) { + if (list_lru_add_obj(&btp->bt_lru, &bp->b_lru)) bp->b_state &= ~XFS_BSTATE_DISPOSE; - atomic_inc(&bp->b_hold); - } + else + bp->b_hold--; spin_unlock(&bch->bc_lock); } else { + bp->b_hold--; /* * most of the time buffers will already be removed from the * LRU, so optimise that case by checking for the @@ -1291,6 +1287,7 @@ xfs_buf_ioend_handle_error( { struct xfs_mount *mp = bp->b_mount; struct xfs_error_cfg *cfg; + struct xfs_log_item *lip; /* * If we've already shutdown the journal because of I/O errors, there's @@ -1338,12 +1335,11 @@ xfs_buf_ioend_handle_error( } /* Still considered a transient error. Caller will schedule retries. */ - if (bp->b_flags & _XBF_INODES) - xfs_buf_inode_io_fail(bp); - else if (bp->b_flags & _XBF_DQUOTS) - xfs_buf_dquot_io_fail(bp); - else - ASSERT(list_empty(&bp->b_li_list)); + list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { + set_bit(XFS_LI_FAILED, &lip->li_flags); + clear_bit(XFS_LI_FLUSHING, &lip->li_flags); + } + xfs_buf_ioerror(bp, 0); xfs_buf_relse(bp); return true; @@ -1367,14 +1363,10 @@ xfs_buf_ioend( { trace_xfs_buf_iodone(bp, _RET_IP_); - /* - * Pull in IO completion errors now. We are guaranteed to be running - * single threaded, so we don't need the lock to read b_io_error. - */ - if (!bp->b_error && bp->b_io_error) - xfs_buf_ioerror(bp, bp->b_io_error); - if (bp->b_flags & XBF_READ) { + if (!bp->b_error && xfs_buf_is_vmapped(bp)) + invalidate_kernel_vmap_range(bp->b_addr, + xfs_buf_vmap_len(bp)); if (!bp->b_error && bp->b_ops) bp->b_ops->verify_read(bp); if (!bp->b_error) @@ -1401,11 +1393,8 @@ xfs_buf_ioend( if (bp->b_log_item) xfs_buf_item_done(bp); - if (bp->b_flags & _XBF_INODES) - xfs_buf_inode_iodone(bp); - else if (bp->b_flags & _XBF_DQUOTS) - xfs_buf_dquot_iodone(bp); - + if (bp->b_iodone) + bp->b_iodone(bp); } bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD | @@ -1485,7 +1474,8 @@ xfs_bwrite( bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_DONE); - error = xfs_buf_submit(bp); + xfs_buf_submit(bp); + error = xfs_buf_iowait(bp); if (error) xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR); return error; @@ -1495,188 +1485,79 @@ static void xfs_buf_bio_end_io( struct bio *bio) { - struct xfs_buf *bp = (struct xfs_buf *)bio->bi_private; + struct xfs_buf *bp = bio->bi_private; - if (!bio->bi_status && - (bp->b_flags & XBF_WRITE) && (bp->b_flags & XBF_ASYNC) && - XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR)) - bio->bi_status = BLK_STS_IOERR; + if (bio->bi_status) + xfs_buf_ioerror(bp, blk_status_to_errno(bio->bi_status)); + else if ((bp->b_flags & XBF_WRITE) && (bp->b_flags & XBF_ASYNC) && + XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR)) + xfs_buf_ioerror(bp, -EIO); - /* - * don't overwrite existing errors - otherwise we can lose errors on - * buffers that require multiple bios to complete. - */ - if (bio->bi_status) { - int error = blk_status_to_errno(bio->bi_status); - - cmpxchg(&bp->b_io_error, 0, error); - } - - if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) - invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); - - if (atomic_dec_and_test(&bp->b_io_remaining) == 1) - xfs_buf_ioend_async(bp); + xfs_buf_ioend_async(bp); bio_put(bio); } -static void -xfs_buf_ioapply_map( - struct xfs_buf *bp, - int map, - int *buf_offset, - int *count, - blk_opf_t op) +static inline blk_opf_t +xfs_buf_bio_op( + struct xfs_buf *bp) { - int page_index; - unsigned int total_nr_pages = bp->b_page_count; - int nr_pages; - struct bio *bio; - sector_t sector = bp->b_maps[map].bm_bn; - int size; - int offset; - - /* skip the pages in the buffer before the start offset */ - page_index = 0; - offset = *buf_offset; - while (offset >= PAGE_SIZE) { - page_index++; - offset -= PAGE_SIZE; - } - - /* - * Limit the IO size to the length of the current vector, and update the - * remaining IO count for the next time around. - */ - size = min_t(int, BBTOB(bp->b_maps[map].bm_len), *count); - *count -= size; - *buf_offset += size; - -next_chunk: - atomic_inc(&bp->b_io_remaining); - nr_pages = bio_max_segs(total_nr_pages); - - bio = bio_alloc(bp->b_target->bt_bdev, nr_pages, op, GFP_NOIO); - bio->bi_iter.bi_sector = sector; - bio->bi_end_io = xfs_buf_bio_end_io; - bio->bi_private = bp; - - for (; size && nr_pages; nr_pages--, page_index++) { - int rbytes, nbytes = PAGE_SIZE - offset; - - if (nbytes > size) - nbytes = size; - - rbytes = bio_add_page(bio, bp->b_pages[page_index], nbytes, - offset); - if (rbytes < nbytes) - break; - - offset = 0; - sector += BTOBB(nbytes); - size -= nbytes; - total_nr_pages--; - } - - if (likely(bio->bi_iter.bi_size)) { - if (xfs_buf_is_vmapped(bp)) { - flush_kernel_vmap_range(bp->b_addr, - xfs_buf_vmap_len(bp)); - } - submit_bio(bio); - if (size) - goto next_chunk; - } else { - /* - * This is guaranteed not to be the last io reference count - * because the caller (xfs_buf_submit) holds a count itself. - */ - atomic_dec(&bp->b_io_remaining); - xfs_buf_ioerror(bp, -EIO); - bio_put(bio); - } - -} - -STATIC void -_xfs_buf_ioapply( - struct xfs_buf *bp) -{ - struct blk_plug plug; - blk_opf_t op; - int offset; - int size; - int i; - - /* - * Make sure we capture only current IO errors rather than stale errors - * left over from previous use of the buffer (e.g. failed readahead). - */ - bp->b_error = 0; + blk_opf_t op; if (bp->b_flags & XBF_WRITE) { op = REQ_OP_WRITE; - - /* - * Run the write verifier callback function if it exists. If - * this function fails it will mark the buffer with an error and - * the IO should not be dispatched. - */ - if (bp->b_ops) { - bp->b_ops->verify_write(bp); - if (bp->b_error) { - xfs_force_shutdown(bp->b_mount, - SHUTDOWN_CORRUPT_INCORE); - return; - } - } else if (bp->b_rhash_key != XFS_BUF_DADDR_NULL) { - struct xfs_mount *mp = bp->b_mount; - - /* - * non-crc filesystems don't attach verifiers during - * log recovery, so don't warn for such filesystems. - */ - if (xfs_has_crc(mp)) { - xfs_warn(mp, - "%s: no buf ops on daddr 0x%llx len %d", - __func__, xfs_buf_daddr(bp), - bp->b_length); - xfs_hex_dump(bp->b_addr, - XFS_CORRUPTION_DUMP_LEN); - dump_stack(); - } - } } else { op = REQ_OP_READ; if (bp->b_flags & XBF_READ_AHEAD) op |= REQ_RAHEAD; } - /* we only use the buffer cache for meta-data */ - op |= REQ_META; + return op | REQ_META; +} - /* in-memory targets are directly mapped, no IO required. */ - if (xfs_buftarg_is_mem(bp->b_target)) { - xfs_buf_ioend(bp); - return; +static void +xfs_buf_submit_bio( + struct xfs_buf *bp) +{ + unsigned int size = BBTOB(bp->b_length); + unsigned int map = 0, p; + struct blk_plug plug; + struct bio *bio; + + bio = bio_alloc(bp->b_target->bt_bdev, bp->b_page_count, + xfs_buf_bio_op(bp), GFP_NOIO); + bio->bi_private = bp; + bio->bi_end_io = xfs_buf_bio_end_io; + + if (bp->b_flags & _XBF_KMEM) { + __bio_add_page(bio, virt_to_page(bp->b_addr), size, + bp->b_offset); + } else { + for (p = 0; p < bp->b_page_count; p++) + __bio_add_page(bio, bp->b_pages[p], PAGE_SIZE, 0); + bio->bi_iter.bi_size = size; /* limit to the actual size used */ + + if (xfs_buf_is_vmapped(bp)) + flush_kernel_vmap_range(bp->b_addr, + xfs_buf_vmap_len(bp)); } /* - * Walk all the vectors issuing IO on them. Set up the initial offset - * into the buffer and the desired IO size before we start - - * _xfs_buf_ioapply_vec() will modify them appropriately for each - * subsequent call. + * If there is more than one map segment, split out a new bio for each + * map except of the last one. The last map is handled by the + * remainder of the original bio outside the loop. */ - offset = bp->b_offset; - size = BBTOB(bp->b_length); blk_start_plug(&plug); - for (i = 0; i < bp->b_map_count; i++) { - xfs_buf_ioapply_map(bp, i, &offset, &size, op); - if (bp->b_error) - break; - if (size <= 0) - break; /* all done */ + for (map = 0; map < bp->b_map_count - 1; map++) { + struct bio *split; + + split = bio_split(bio, bp->b_maps[map].bm_len, GFP_NOFS, + &fs_bio_set); + split->bi_iter.bi_sector = bp->b_maps[map].bm_bn; + bio_chain(split, bio); + submit_bio(split); } + bio->bi_iter.bi_sector = bp->b_maps[map].bm_bn; + submit_bio(bio); blk_finish_plug(&plug); } @@ -1696,19 +1577,46 @@ xfs_buf_iowait( return bp->b_error; } +/* + * Run the write verifier callback function if it exists. If this fails, mark + * the buffer with an error and do not dispatch the I/O. + */ +static bool +xfs_buf_verify_write( + struct xfs_buf *bp) +{ + if (bp->b_ops) { + bp->b_ops->verify_write(bp); + if (bp->b_error) + return false; + } else if (bp->b_rhash_key != XFS_BUF_DADDR_NULL) { + /* + * Non-crc filesystems don't attach verifiers during log + * recovery, so don't warn for such filesystems. + */ + if (xfs_has_crc(bp->b_mount)) { + xfs_warn(bp->b_mount, + "%s: no buf ops on daddr 0x%llx len %d", + __func__, xfs_buf_daddr(bp), + bp->b_length); + xfs_hex_dump(bp->b_addr, XFS_CORRUPTION_DUMP_LEN); + dump_stack(); + } + } + + return true; +} + /* * Buffer I/O submission path, read or write. Asynchronous submission transfers * the buffer lock ownership and the current reference to the IO. It is not * safe to reference the buffer after a call to this function unless the caller * holds an additional reference itself. */ -static int -__xfs_buf_submit( - struct xfs_buf *bp, - bool wait) +static void +xfs_buf_submit( + struct xfs_buf *bp) { - int error = 0; - trace_xfs_buf_submit(bp, _RET_IP_); ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); @@ -1728,57 +1636,36 @@ __xfs_buf_submit( * state here rather than mount state to avoid corrupting the log tail * on shutdown. */ - if (bp->b_mount->m_log && - xlog_is_shutdown(bp->b_mount->m_log)) { + if (bp->b_mount->m_log && xlog_is_shutdown(bp->b_mount->m_log)) { xfs_buf_ioend_fail(bp); - return -EIO; + return; } - /* - * Grab a reference so the buffer does not go away underneath us. For - * async buffers, I/O completion drops the callers reference, which - * could occur before submission returns. - */ - xfs_buf_hold(bp); - if (bp->b_flags & XBF_WRITE) xfs_buf_wait_unpin(bp); - /* clear the internal error state to avoid spurious errors */ - bp->b_io_error = 0; - /* - * Set the count to 1 initially, this will stop an I/O completion - * callout which happens before we have started all the I/O from calling - * xfs_buf_ioend too early. + * Make sure we capture only current IO errors rather than stale errors + * left over from previous use of the buffer (e.g. failed readahead). */ - atomic_set(&bp->b_io_remaining, 1); + bp->b_error = 0; + if (bp->b_flags & XBF_ASYNC) xfs_buf_ioacct_inc(bp); - _xfs_buf_ioapply(bp); - /* - * If _xfs_buf_ioapply failed, we can get back here with only the IO - * reference we took above. If we drop it to zero, run completion so - * that we don't return to the caller with completion still pending. - */ - if (atomic_dec_and_test(&bp->b_io_remaining) == 1) { - if (bp->b_error || !(bp->b_flags & XBF_ASYNC)) - xfs_buf_ioend(bp); - else - xfs_buf_ioend_async(bp); + if ((bp->b_flags & XBF_WRITE) && !xfs_buf_verify_write(bp)) { + xfs_force_shutdown(bp->b_mount, SHUTDOWN_CORRUPT_INCORE); + xfs_buf_ioend(bp); + return; } - if (wait) - error = xfs_buf_iowait(bp); + /* In-memory targets are directly mapped, no I/O required. */ + if (xfs_buftarg_is_mem(bp->b_target)) { + xfs_buf_ioend(bp); + return; + } - /* - * Release the hold that keeps the buffer referenced for the entire - * I/O. Note that if the buffer is async, it is not safe to reference - * after this release. - */ - xfs_buf_rele(bp); - return error; + xfs_buf_submit_bio(bp); } void * @@ -1863,13 +1750,14 @@ xfs_buftarg_drain_rele( struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); struct list_head *dispose = arg; - if (atomic_read(&bp->b_hold) > 1) { + if (!spin_trylock(&bp->b_lock)) + return LRU_SKIP; + if (bp->b_hold > 1) { /* need to wait, so skip it this pass */ + spin_unlock(&bp->b_lock); trace_xfs_buf_drain_buftarg(bp, _RET_IP_); return LRU_SKIP; } - if (!spin_trylock(&bp->b_lock)) - return LRU_SKIP; /* * clear the LRU reference count so the buffer doesn't get @@ -2208,7 +2096,7 @@ xfs_buf_delwri_queue( */ bp->b_flags |= _XBF_DELWRI_Q; if (list_empty(&bp->b_list)) { - atomic_inc(&bp->b_hold); + xfs_buf_hold(bp); list_add_tail(&bp->b_list, list); } @@ -2266,72 +2154,26 @@ xfs_buf_cmp( return 0; } -/* - * Submit buffers for write. If wait_list is specified, the buffers are - * submitted using sync I/O and placed on the wait list such that the caller can - * iowait each buffer. Otherwise async I/O is used and the buffers are released - * at I/O completion time. In either case, buffers remain locked until I/O - * completes and the buffer is released from the queue. - */ -static int -xfs_buf_delwri_submit_buffers( - struct list_head *buffer_list, - struct list_head *wait_list) +static bool +xfs_buf_delwri_submit_prep( + struct xfs_buf *bp) { - struct xfs_buf *bp, *n; - int pinned = 0; - struct blk_plug plug; - - list_sort(NULL, buffer_list, xfs_buf_cmp); - - blk_start_plug(&plug); - list_for_each_entry_safe(bp, n, buffer_list, b_list) { - if (!wait_list) { - if (!xfs_buf_trylock(bp)) - continue; - if (xfs_buf_ispinned(bp)) { - xfs_buf_unlock(bp); - pinned++; - continue; - } - } else { - xfs_buf_lock(bp); - } - - /* - * Someone else might have written the buffer synchronously or - * marked it stale in the meantime. In that case only the - * _XBF_DELWRI_Q flag got cleared, and we have to drop the - * reference and remove it from the list here. - */ - if (!(bp->b_flags & _XBF_DELWRI_Q)) { - xfs_buf_list_del(bp); - xfs_buf_relse(bp); - continue; - } - - trace_xfs_buf_delwri_split(bp, _RET_IP_); - - /* - * If we have a wait list, each buffer (and associated delwri - * queue reference) transfers to it and is submitted - * synchronously. Otherwise, drop the buffer from the delwri - * queue and submit async. - */ - bp->b_flags &= ~_XBF_DELWRI_Q; - bp->b_flags |= XBF_WRITE; - if (wait_list) { - bp->b_flags &= ~XBF_ASYNC; - list_move_tail(&bp->b_list, wait_list); - } else { - bp->b_flags |= XBF_ASYNC; - xfs_buf_list_del(bp); - } - __xfs_buf_submit(bp, false); + /* + * Someone else might have written the buffer synchronously or marked it + * stale in the meantime. In that case only the _XBF_DELWRI_Q flag got + * cleared, and we have to drop the reference and remove it from the + * list here. + */ + if (!(bp->b_flags & _XBF_DELWRI_Q)) { + xfs_buf_list_del(bp); + xfs_buf_relse(bp); + return false; } - blk_finish_plug(&plug); - return pinned; + trace_xfs_buf_delwri_split(bp, _RET_IP_); + bp->b_flags &= ~_XBF_DELWRI_Q; + bp->b_flags |= XBF_WRITE; + return true; } /* @@ -2354,7 +2196,30 @@ int xfs_buf_delwri_submit_nowait( struct list_head *buffer_list) { - return xfs_buf_delwri_submit_buffers(buffer_list, NULL); + struct xfs_buf *bp, *n; + int pinned = 0; + struct blk_plug plug; + + list_sort(NULL, buffer_list, xfs_buf_cmp); + + blk_start_plug(&plug); + list_for_each_entry_safe(bp, n, buffer_list, b_list) { + if (!xfs_buf_trylock(bp)) + continue; + if (xfs_buf_ispinned(bp)) { + xfs_buf_unlock(bp); + pinned++; + continue; + } + if (!xfs_buf_delwri_submit_prep(bp)) + continue; + bp->b_flags |= XBF_ASYNC; + xfs_buf_list_del(bp); + xfs_buf_submit(bp); + } + blk_finish_plug(&plug); + + return pinned; } /* @@ -2371,9 +2236,21 @@ xfs_buf_delwri_submit( { LIST_HEAD (wait_list); int error = 0, error2; - struct xfs_buf *bp; + struct xfs_buf *bp, *n; + struct blk_plug plug; - xfs_buf_delwri_submit_buffers(buffer_list, &wait_list); + list_sort(NULL, buffer_list, xfs_buf_cmp); + + blk_start_plug(&plug); + list_for_each_entry_safe(bp, n, buffer_list, b_list) { + xfs_buf_lock(bp); + if (!xfs_buf_delwri_submit_prep(bp)) + continue; + bp->b_flags &= ~XBF_ASYNC; + list_move_tail(&bp->b_list, &wait_list); + xfs_buf_submit(bp); + } + blk_finish_plug(&plug); /* Wait for IO to complete. */ while (!list_empty(&wait_list)) { @@ -2398,14 +2275,9 @@ xfs_buf_delwri_submit( * Push a single buffer on a delwri queue. * * The purpose of this function is to submit a single buffer of a delwri queue - * and return with the buffer still on the original queue. The waiting delwri - * buffer submission infrastructure guarantees transfer of the delwri queue - * buffer reference to a temporary wait list. We reuse this infrastructure to - * transfer the buffer back to the original queue. + * and return with the buffer still on the original queue. * - * Note the buffer transitions from the queued state, to the submitted and wait - * listed state and back to the queued state during this call. The buffer - * locking and queue management logic between _delwri_pushbuf() and + * The buffer locking and queue management logic between _delwri_pushbuf() and * _delwri_queue() guarantee that the buffer cannot be queued to another list * before returning. */ @@ -2414,33 +2286,21 @@ xfs_buf_delwri_pushbuf( struct xfs_buf *bp, struct list_head *buffer_list) { - LIST_HEAD (submit_list); int error; ASSERT(bp->b_flags & _XBF_DELWRI_Q); trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_); - /* - * Isolate the buffer to a new local list so we can submit it for I/O - * independently from the rest of the original list. - */ xfs_buf_lock(bp); - list_move(&bp->b_list, &submit_list); - xfs_buf_unlock(bp); + bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC); + bp->b_flags |= XBF_WRITE; + xfs_buf_submit(bp); /* - * Delwri submission clears the DELWRI_Q buffer flag and returns with - * the buffer on the wait list with the original reference. Rather than - * bounce the buffer from a local wait list back to the original list - * after I/O completion, reuse the original list as the wait list. - */ - xfs_buf_delwri_submit_buffers(&submit_list, buffer_list); - - /* - * The buffer is now locked, under I/O and wait listed on the original - * delwri queue. Wait for I/O completion, restore the DELWRI_Q flag and - * return with the buffer unlocked and on the original queue. + * The buffer is now locked, under I/O but still on the original delwri + * queue. Wait for I/O completion, restore the DELWRI_Q flag and + * return with the buffer unlocked and still on the original queue. */ error = xfs_buf_iowait(bp); bp->b_flags |= _XBF_DELWRI_Q; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 3d56bc7a35cc..7e73663c5d4a 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -34,8 +34,6 @@ struct xfs_buf; #define XBF_WRITE_FAIL (1u << 7) /* async writes have failed on this buffer */ /* buffer type flags for write callbacks */ -#define _XBF_INODES (1u << 16)/* inode buffer */ -#define _XBF_DQUOTS (1u << 17)/* dquot buffer */ #define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */ /* flags used only internally */ @@ -65,8 +63,6 @@ typedef unsigned int xfs_buf_flags_t; { XBF_DONE, "DONE" }, \ { XBF_STALE, "STALE" }, \ { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ - { _XBF_INODES, "INODES" }, \ - { _XBF_DQUOTS, "DQUOTS" }, \ { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ @@ -172,7 +168,7 @@ struct xfs_buf { xfs_daddr_t b_rhash_key; /* buffer cache index */ int b_length; /* size of buffer in BBs */ - atomic_t b_hold; /* reference count */ + unsigned int b_hold; /* reference count */ atomic_t b_lru_ref; /* lru reclaim ref count */ xfs_buf_flags_t b_flags; /* status flags */ struct semaphore b_sema; /* semaphore for lockables */ @@ -184,10 +180,9 @@ struct xfs_buf { struct list_head b_lru; /* lru list */ spinlock_t b_lock; /* internal state lock */ unsigned int b_state; /* internal state flags */ - int b_io_error; /* internal IO error state */ wait_queue_head_t b_waiters; /* unpin waiters */ struct list_head b_list; - struct xfs_perag *b_pag; /* contains rbtree root */ + struct xfs_perag *b_pag; struct xfs_mount *b_mount; struct xfs_buftarg *b_target; /* buffer target (device) */ void *b_addr; /* virtual address of buffer */ @@ -202,11 +197,11 @@ struct xfs_buf { struct xfs_buf_map __b_map; /* inline compound buffer map */ int b_map_count; atomic_t b_pin_count; /* pin count */ - atomic_t b_io_remaining; /* #outstanding I/O requests */ unsigned int b_page_count; /* size of page array */ unsigned int b_offset; /* page offset of b_addr, only for _XBF_KMEM buffers */ int b_error; /* error code on I/O */ + void (*b_iodone)(struct xfs_buf *bp); /* * async write failure retry count. Initialised to zero on the first diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index 4d8a6aece995..8cde85259a58 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -54,17 +54,12 @@ bool xfs_buf_item_put(struct xfs_buf_log_item *); void xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint); bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *); void xfs_buf_inode_iodone(struct xfs_buf *); -void xfs_buf_inode_io_fail(struct xfs_buf *bp); #ifdef CONFIG_XFS_QUOTA void xfs_buf_dquot_iodone(struct xfs_buf *); -void xfs_buf_dquot_io_fail(struct xfs_buf *bp); #else static inline void xfs_buf_dquot_iodone(struct xfs_buf *bp) { } -static inline void xfs_buf_dquot_io_fail(struct xfs_buf *bp) -{ -} #endif /* CONFIG_XFS_QUOTA */ void xfs_buf_iodone(struct xfs_buf *); bool xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec); diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index 3d0c6402cb36..05a2f6927c12 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -262,12 +262,18 @@ xlog_recover_validate_buf_type( case XFS_BMAP_MAGIC: bp->b_ops = &xfs_bmbt_buf_ops; break; + case XFS_RTRMAP_CRC_MAGIC: + bp->b_ops = &xfs_rtrmapbt_buf_ops; + break; case XFS_RMAP_CRC_MAGIC: bp->b_ops = &xfs_rmapbt_buf_ops; break; case XFS_REFC_CRC_MAGIC: bp->b_ops = &xfs_refcountbt_buf_ops; break; + case XFS_RTREFC_CRC_MAGIC: + bp->b_ops = &xfs_rtrefcountbt_buf_ops; + break; default: warnmsg = "Bad btree block magic!"; break; @@ -855,6 +861,8 @@ xlog_recover_get_buf_lsn( uuid = &btb->bb_u.s.bb_uuid; break; } + case XFS_RTRMAP_CRC_MAGIC: + case XFS_RTREFC_CRC_MAGIC: case XFS_BMAP_CRC_MAGIC: case XFS_BMAP_MAGIC: { struct xfs_btree_block *btb = blk; @@ -1079,7 +1087,7 @@ xlog_recover_buf_commit_pass2( error = xlog_recover_do_primary_sb_buffer(mp, item, bp, buf_f, current_lsn); if (error) - goto out_release; + goto out_writebuf; /* Update the rt superblock if we have one. */ if (xfs_has_rtsb(mp) && mp->m_rtsb_bp) { @@ -1096,6 +1104,15 @@ xlog_recover_buf_commit_pass2( xlog_recover_do_reg_buffer(mp, item, bp, buf_f, current_lsn); } + /* + * Buffer held by buf log item during 'normal' buffer recovery must + * be committed through buffer I/O submission path to ensure proper + * release. When error occurs during sb buffer recovery, log shutdown + * will be done before submitting buffer list so that buffers can be + * released correctly through ioend failure path. + */ +out_writebuf: + /* * Perform delayed write on the buffer. Asynchronous writes will be * slower when taking into account all the buffers to be flushed. diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index c4bd145f5ec1..3f2403a7b49c 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -90,7 +90,7 @@ xfs_discard_endio_work( /* * Queue up the actual completion to a thread to avoid IRQ-safe locking for - * pagb_lock. + * eb_lock. */ static void xfs_discard_endio( diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index f11d475898f2..edbc521870a1 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -87,8 +87,9 @@ xfs_dquot_detach_buf( } spin_unlock(&qlip->qli_lock); if (bp) { + xfs_buf_lock(bp); list_del_init(&qlip->qli_item.li_bio_list); - xfs_buf_rele(bp); + xfs_buf_relse(bp); } } @@ -1229,18 +1230,6 @@ xfs_buf_dquot_iodone( } } -void -xfs_buf_dquot_io_fail( - struct xfs_buf *bp) -{ - struct xfs_log_item *lip; - - spin_lock(&bp->b_mount->m_ail->ail_lock); - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) - set_bit(XFS_LI_FAILED, &lip->li_flags); - spin_unlock(&bp->b_mount->m_ail->ail_lock); -} - /* Check incore dquot for errors before we flush. */ static xfs_failaddr_t xfs_qm_dqflush_check( @@ -1315,7 +1304,8 @@ out_abort: /* * Attach a dquot buffer to this dquot to avoid allocating a buffer during a - * dqflush, since dqflush can be called from reclaim context. + * dqflush, since dqflush can be called from reclaim context. Caller must hold + * the dqlock. */ int xfs_dquot_attach_buf( @@ -1336,13 +1326,16 @@ xfs_dquot_attach_buf( return error; /* - * Attach the dquot to the buffer so that the AIL does not have - * to read the dquot buffer to push this item. + * Hold the dquot buffer so that we retain our ref to it after + * detaching it from the transaction, then give that ref to the + * dquot log item so that the AIL does not have to read the + * dquot buffer to push this item. */ xfs_buf_hold(bp); + xfs_trans_brelse(tp, bp); + spin_lock(&qlip->qli_lock); lip->li_buf = bp; - xfs_trans_brelse(tp, bp); } qlip->qli_dirty = true; spin_unlock(&qlip->qli_lock); @@ -1458,7 +1451,7 @@ xfs_qm_dqflush( * Attach the dquot to the buffer so that we can remove this dquot from * the AIL and release the flush lock once the dquot is synced to disk. */ - bp->b_flags |= _XBF_DQUOTS; + bp->b_iodone = xfs_buf_dquot_iodone; list_add_tail(&lip->li_bio_list, &bp->b_li_list); /* diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index c617bac75361..61217adf5ba5 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -160,6 +160,9 @@ static inline struct xfs_dquot *xfs_inode_dquot( struct xfs_inode *ip, xfs_dqtype_t type) { + if (xfs_is_metadir_inode(ip)) + return NULL; + switch (type) { case XFS_DQTYPE_USER: return ip->i_udquot; diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c index 5ede81fadbd8..fa5f31931efd 100644 --- a/fs/xfs/xfs_drain.c +++ b/fs/xfs/xfs_drain.c @@ -13,28 +13,28 @@ #include "xfs_trace.h" /* - * Use a static key here to reduce the overhead of xfs_drain_rele. If the - * compiler supports jump labels, the static branch will be replaced by a nop - * sled when there are no xfs_drain_wait callers. Online fsck is currently - * the only caller, so this is a reasonable tradeoff. + * Use a static key here to reduce the overhead of xfs_defer_drain_rele. If + * the compiler supports jump labels, the static branch will be replaced by a + * nop sled when there are no xfs_defer_drain_wait callers. Online fsck is + * currently the only caller, so this is a reasonable tradeoff. * * Note: Patching the kernel code requires taking the cpu hotplug lock. Other * parts of the kernel allocate memory with that lock held, which means that * XFS callers cannot hold any locks that might be used by memory reclaim or * writeback when calling the static_branch_{inc,dec} functions. */ -static DEFINE_STATIC_KEY_FALSE(xfs_drain_waiter_gate); +static DEFINE_STATIC_KEY_FALSE(xfs_defer_drain_waiter_gate); void -xfs_drain_wait_disable(void) +xfs_defer_drain_wait_disable(void) { - static_branch_dec(&xfs_drain_waiter_gate); + static_branch_dec(&xfs_defer_drain_waiter_gate); } void -xfs_drain_wait_enable(void) +xfs_defer_drain_wait_enable(void) { - static_branch_inc(&xfs_drain_waiter_gate); + static_branch_inc(&xfs_defer_drain_waiter_gate); } void @@ -71,7 +71,7 @@ static inline bool has_waiters(struct wait_queue_head *wq_head) static inline void xfs_defer_drain_rele(struct xfs_defer_drain *dr) { if (atomic_dec_and_test(&dr->dr_count) && - static_branch_unlikely(&xfs_drain_waiter_gate) && + static_branch_unlikely(&xfs_defer_drain_waiter_gate) && has_waiters(&dr->dr_waiters)) wake_up(&dr->dr_waiters); } diff --git a/fs/xfs/xfs_drain.h b/fs/xfs/xfs_drain.h index efcf88df9a5e..4d446dbf65e5 100644 --- a/fs/xfs/xfs_drain.h +++ b/fs/xfs/xfs_drain.h @@ -26,8 +26,8 @@ struct xfs_defer_drain { void xfs_defer_drain_init(struct xfs_defer_drain *dr); void xfs_defer_drain_free(struct xfs_defer_drain *dr); -void xfs_drain_wait_disable(void); -void xfs_drain_wait_enable(void); +void xfs_defer_drain_wait_disable(void); +void xfs_defer_drain_wait_enable(void); /* * Deferred Work Intent Drains @@ -61,6 +61,9 @@ void xfs_drain_wait_enable(void); * All functions that create work items must increment the intent counter as * soon as the item is added to the transaction and cannot drop the counter * until the item is finished or cancelled. + * + * The same principles apply to realtime groups because the rt metadata inode + * ILOCKs are not held across transaction rolls. */ struct xfs_group *xfs_group_intent_get(struct xfs_mount *mp, xfs_fsblock_t fsbno, enum xfs_group_type type); diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 78cdc5064a8c..dbd87e137694 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -63,6 +63,7 @@ static unsigned int xfs_errortag_random_default[] = { XFS_RANDOM_WB_DELAY_MS, XFS_RANDOM_WRITE_DELAY_MS, XFS_RANDOM_EXCHMAPS_FINISH_ONE, + XFS_RANDOM_METAFILE_RESV_CRITICAL, }; struct xfs_errortag_attr { @@ -181,6 +182,7 @@ XFS_ERRORTAG_ATTR_RW(attr_leaf_to_node, XFS_ERRTAG_ATTR_LEAF_TO_NODE); XFS_ERRORTAG_ATTR_RW(wb_delay_ms, XFS_ERRTAG_WB_DELAY_MS); XFS_ERRORTAG_ATTR_RW(write_delay_ms, XFS_ERRTAG_WRITE_DELAY_MS); XFS_ERRORTAG_ATTR_RW(exchmaps_finish_one, XFS_ERRTAG_EXCHMAPS_FINISH_ONE); +XFS_ERRORTAG_ATTR_RW(metafile_resv_crit, XFS_ERRTAG_METAFILE_RESV_CRITICAL); static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(noerror), @@ -227,6 +229,7 @@ static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(wb_delay_ms), XFS_ERRORTAG_ATTR_LIST(write_delay_ms), XFS_ERRORTAG_ATTR_LIST(exchmaps_finish_one), + XFS_ERRORTAG_ATTR_LIST(metafile_resv_crit), NULL, }; ATTRIBUTE_GROUPS(xfs_errortag); diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index 265c42449893..f340a2015c4c 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -119,6 +119,9 @@ xfs_exchrange_reserve_quota( int ip1_error = 0; int error; + ASSERT(!xfs_is_metadir_inode(req->ip1)); + ASSERT(!xfs_is_metadir_inode(req->ip2)); + /* * Don't bother with a quota reservation if we're not enforcing them * or the two inodes have the same dquots. diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 9a435b1ff264..f7a7d89c345e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1451,6 +1451,9 @@ xfs_dax_read_fault( trace_xfs_read_fault(ip, order); + ret = filemap_fsnotify_fault(vmf); + if (unlikely(ret)) + return ret; xfs_ilock(ip, XFS_MMAPLOCK_SHARED); ret = xfs_dax_fault_locked(vmf, order, false); xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); @@ -1479,6 +1482,16 @@ xfs_write_fault( vm_fault_t ret; trace_xfs_write_fault(ip, order); + /* + * Usually we get here from ->page_mkwrite callback but in case of DAX + * we will get here also for ordinary write fault. Handle HSM + * notifications for that case. + */ + if (IS_DAX(inode)) { + ret = filemap_fsnotify_fault(vmf); + if (unlikely(ret)) + return ret; + } sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 3290dd8524a6..1dbd2d75f7ae 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -26,6 +26,8 @@ #include "xfs_rtbitmap.h" #include "xfs_ag.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* Convert an xfs_fsmap to an fsmap. */ static void @@ -211,21 +213,20 @@ xfs_getfsmap_is_shared( struct xfs_mount *mp = tp->t_mountp; struct xfs_btree_cur *cur; xfs_agblock_t fbno; - xfs_extlen_t flen; + xfs_extlen_t flen = 0; int error; *stat = false; - if (!xfs_has_reflink(mp)) - return 0; - /* rt files will have no perag structure */ - if (!info->group) + if (!xfs_has_reflink(mp) || !info->group) return 0; + if (info->group->xg_type == XG_TYPE_RTG) + cur = xfs_rtrefcountbt_init_cursor(tp, to_rtg(info->group)); + else + cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp, + to_perag(info->group)); + /* Are there any shared blocks here? */ - flen = 0; - cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp, - to_perag(info->group)); - error = xfs_refcount_find_shared(cur, frec->rec_key, XFS_BB_TO_FSBT(mp, frec->len_daddr), &fbno, &flen, false); @@ -832,6 +833,175 @@ xfs_getfsmap_rtdev_rtbitmap( return error; } + +/* Transform a realtime rmapbt record into a fsmap */ +STATIC int +xfs_getfsmap_rtdev_rmapbt_helper( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xfs_fsmap_irec frec = { + .owner = rec->rm_owner, + .offset = rec->rm_offset, + .rm_flags = rec->rm_flags, + .rec_key = rec->rm_startblock, + }; + struct xfs_getfsmap_info *info = priv; + + return xfs_getfsmap_group_helper(info, cur->bc_tp, cur->bc_group, + rec->rm_startblock, rec->rm_blockcount, &frec); +} + +/* Actually query the rtrmap btree. */ +STATIC int +xfs_getfsmap_rtdev_rmapbt_query( + struct xfs_trans *tp, + struct xfs_getfsmap_info *info, + struct xfs_btree_cur **curpp) +{ + struct xfs_rtgroup *rtg = to_rtg(info->group); + + /* Query the rtrmapbt */ + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP | XFS_RTGLOCK_REFCOUNT); + *curpp = xfs_rtrmapbt_init_cursor(tp, rtg); + return xfs_rmap_query_range(*curpp, &info->low, &info->high, + xfs_getfsmap_rtdev_rmapbt_helper, info); +} + +/* Execute a getfsmap query against the realtime device rmapbt. */ +STATIC int +xfs_getfsmap_rtdev_rmapbt( + struct xfs_trans *tp, + const struct xfs_fsmap *keys, + struct xfs_getfsmap_info *info) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rtgroup *rtg = NULL; + struct xfs_btree_cur *bt_cur = NULL; + xfs_rtblock_t start_rtb; + xfs_rtblock_t end_rtb; + xfs_rgnumber_t start_rg, end_rg; + uint64_t eofs; + int error = 0; + + eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks); + if (keys[0].fmr_physical >= eofs) + return 0; + start_rtb = xfs_daddr_to_rtb(mp, keys[0].fmr_physical); + end_rtb = xfs_daddr_to_rtb(mp, min(eofs - 1, keys[1].fmr_physical)); + + info->missing_owner = XFS_FMR_OWN_FREE; + + /* + * Convert the fsmap low/high keys to rtgroup based keys. Initialize + * low to the fsmap low key and max out the high key to the end + * of the rtgroup. + */ + info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset); + error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]); + if (error) + return error; + info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length); + xfs_getfsmap_set_irec_flags(&info->low, &keys[0]); + + /* Adjust the low key if we are continuing from where we left off. */ + if (info->low.rm_blockcount == 0) { + /* No previous record from which to continue */ + } else if (rmap_not_shareable(mp, &info->low)) { + /* Last record seen was an unshareable extent */ + info->low.rm_owner = 0; + info->low.rm_offset = 0; + + start_rtb += info->low.rm_blockcount; + if (xfs_rtb_to_daddr(mp, start_rtb) >= eofs) + return 0; + } else { + /* Last record seen was a shareable file data extent */ + info->low.rm_offset += info->low.rm_blockcount; + } + info->low.rm_startblock = xfs_rtb_to_rgbno(mp, start_rtb); + + info->high.rm_startblock = -1U; + info->high.rm_owner = ULLONG_MAX; + info->high.rm_offset = ULLONG_MAX; + info->high.rm_blockcount = 0; + info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS; + + start_rg = xfs_rtb_to_rgno(mp, start_rtb); + end_rg = xfs_rtb_to_rgno(mp, end_rtb); + + while ((rtg = xfs_rtgroup_next_range(mp, rtg, start_rg, end_rg))) { + /* + * Set the rtgroup high key from the fsmap high key if this + * is the last rtgroup that we're querying. + */ + info->group = rtg_group(rtg); + if (rtg_rgno(rtg) == end_rg) { + info->high.rm_startblock = + xfs_rtb_to_rgbno(mp, end_rtb); + info->high.rm_offset = + XFS_BB_TO_FSBT(mp, keys[1].fmr_offset); + error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]); + if (error) + break; + xfs_getfsmap_set_irec_flags(&info->high, &keys[1]); + } + + if (bt_cur) { + xfs_rtgroup_unlock(to_rtg(bt_cur->bc_group), + XFS_RTGLOCK_RMAP | + XFS_RTGLOCK_REFCOUNT); + xfs_btree_del_cursor(bt_cur, XFS_BTREE_NOERROR); + bt_cur = NULL; + } + + trace_xfs_fsmap_low_group_key(mp, info->dev, rtg_rgno(rtg), + &info->low); + trace_xfs_fsmap_high_group_key(mp, info->dev, rtg_rgno(rtg), + &info->high); + + error = xfs_getfsmap_rtdev_rmapbt_query(tp, info, &bt_cur); + if (error) + break; + + /* + * Set the rtgroup low key to the start of the rtgroup prior to + * moving on to the next rtgroup. + */ + if (rtg_rgno(rtg) == start_rg) + memset(&info->low, 0, sizeof(info->low)); + + /* + * If this is the last rtgroup, report any gap at the end of it + * before we drop the reference to the perag when the loop + * terminates. + */ + if (rtg_rgno(rtg) == end_rg) { + info->last = true; + error = xfs_getfsmap_rtdev_rmapbt_helper(bt_cur, + &info->high, info); + if (error) + break; + } + info->group = NULL; + } + + if (bt_cur) { + xfs_rtgroup_unlock(to_rtg(bt_cur->bc_group), + XFS_RTGLOCK_RMAP | XFS_RTGLOCK_REFCOUNT); + xfs_btree_del_cursor(bt_cur, error < 0 ? XFS_BTREE_ERROR : + XFS_BTREE_NOERROR); + } + + /* loop termination case */ + if (rtg) { + info->group = NULL; + xfs_rtgroup_rele(rtg); + } + + return error; +} #endif /* CONFIG_XFS_RT */ /* Do we recognize the device? */ @@ -971,7 +1141,10 @@ xfs_getfsmap( if (mp->m_rtdev_targp) { handlers[2].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks); handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev); - handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap; + if (use_rmap) + handlers[2].fn = xfs_getfsmap_rtdev_rmapbt; + else + handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap; } #endif /* CONFIG_XFS_RT */ diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 28dde215c899..455298503d01 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -21,6 +21,9 @@ #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_trace.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* * Write new AG headers to disk. Non-transactional, but need to be @@ -113,6 +116,12 @@ xfs_growfs_data_private( xfs_buf_relse(bp); } + /* Make sure the new fs size won't cause problems with the log. */ + error = xfs_growfs_check_rtgeom(mp, nb, mp->m_sb.sb_rblocks, + mp->m_sb.sb_rextsize); + if (error) + return error; + nb_div = nb; nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks); if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS) @@ -220,7 +229,12 @@ xfs_growfs_data_private( error = xfs_fs_reserve_ag_blocks(mp); if (error == -ENOSPC) error = 0; + + /* Compute new maxlevels for rt btrees. */ + xfs_rtrmapbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); } + return error; out_trans_cancel: @@ -541,6 +555,19 @@ xfs_fs_reserve_ag_blocks( xfs_warn(mp, "Error %d reserving per-AG metadata reserve pool.", error); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; + } + + if (xfs_has_realtime(mp)) { + err2 = xfs_rt_resv_init(mp); + if (err2 && err2 != -ENOSPC) { + xfs_warn(mp, + "Error %d reserving realtime metadata reserve pool.", err2); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + } + + if (err2 && !error) + error = err2; } return error; @@ -555,6 +582,9 @@ xfs_fs_unreserve_ag_blocks( { struct xfs_perag *pag = NULL; + if (xfs_has_realtime(mp)) + xfs_rt_resv_free(mp); + while ((pag = xfs_perag_next(mp, pag))) xfs_ag_resv_free(pag); } diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c index c7c2e6561998..7c541fb373d5 100644 --- a/fs/xfs/xfs_health.c +++ b/fs/xfs/xfs_health.c @@ -447,6 +447,8 @@ static const struct ioctl_sick_map rtgroup_map[] = { { XFS_SICK_RG_SUPER, XFS_RTGROUP_GEOM_SICK_SUPER }, { XFS_SICK_RG_BITMAP, XFS_RTGROUP_GEOM_SICK_BITMAP }, { XFS_SICK_RG_SUMMARY, XFS_RTGROUP_GEOM_SICK_SUMMARY }, + { XFS_SICK_RG_RMAPBT, XFS_RTGROUP_GEOM_SICK_RMAPBT }, + { XFS_SICK_RG_REFCNTBT, XFS_RTGROUP_GEOM_SICK_REFCNTBT }, }; /* Fill out rtgroup geometry health info. */ diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c8ad2606f928..c95fe1b1de4e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2382,7 +2382,16 @@ xfs_iflush( __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip); goto flush_out; } - if (S_ISREG(VFS_I(ip)->i_mode)) { + if (ip->i_df.if_format == XFS_DINODE_FMT_META_BTREE) { + if (!S_ISREG(VFS_I(ip)->i_mode) || + !(ip->i_diflags2 & XFS_DIFLAG2_METADATA)) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: Bad %s meta btree inode %Lu, ptr "PTR_FMT, + __func__, xfs_metafile_type_str(ip->i_metatype), + ip->i_ino, ip); + goto flush_out; + } + } else if (S_ISREG(VFS_I(ip)->i_mode)) { if (XFS_TEST_ERROR( ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && ip->i_df.if_format != XFS_DINODE_FMT_BTREE, @@ -2422,6 +2431,14 @@ xfs_iflush( goto flush_out; } + if (xfs_inode_has_attr_fork(ip) && + ip->i_af.if_format == XFS_DINODE_FMT_META_BTREE) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: meta btree in inode %Lu attr fork, ptr "PTR_FMT, + __func__, ip->i_ino, ip); + goto flush_out; + } + /* * Inode item log recovery for v2 inodes are dependent on the flushiter * count for correct sequencing. We bump the flush iteration count so diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 1648dc5a8068..c08093a65352 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -25,9 +25,19 @@ struct xfs_dquot; typedef struct xfs_inode { /* Inode linking and identification information. */ struct xfs_mount *i_mount; /* fs mount struct ptr */ - struct xfs_dquot *i_udquot; /* user dquot */ - struct xfs_dquot *i_gdquot; /* group dquot */ - struct xfs_dquot *i_pdquot; /* project dquot */ + union { + struct { + struct xfs_dquot *i_udquot; /* user dquot */ + struct xfs_dquot *i_gdquot; /* group dquot */ + struct xfs_dquot *i_pdquot; /* project dquot */ + }; + + /* + * Space that has been set aside to accomodate expansions of a + * metadata btree rooted in this file. + */ + uint64_t i_meta_resv_asked; + }; /* Inode location stuff */ xfs_ino_t i_ino; /* inode number (agno/agino)*/ diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 912f0b1bc3cb..35803fcf0beb 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -157,6 +157,20 @@ xfs_inode_item_precommit( if (flags & XFS_ILOG_IVERSION) flags = ((flags & ~XFS_ILOG_IVERSION) | XFS_ILOG_CORE); + /* + * Inode verifiers do not check that the CoW extent size hint is an + * integer multiple of the rt extent size on a directory with both + * rtinherit and cowextsize flags set. If we're logging a directory + * that is misconfigured in this way, clear the hint. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) && + xfs_extlen_to_rtxmod(ip->i_mount, ip->i_cowextsize) > 0) { + ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + ip->i_cowextsize = 0; + flags |= XFS_ILOG_CORE; + } + if (!iip->ili_item.li_buf) { struct xfs_buf *bp; int error; @@ -185,7 +199,7 @@ xfs_inode_item_precommit( xfs_buf_hold(bp); spin_lock(&iip->ili_lock); iip->ili_item.li_buf = bp; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); xfs_trans_brelse(tp, bp); } @@ -242,6 +256,7 @@ xfs_inode_item_data_fork_size( } break; case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: if ((iip->ili_fields & XFS_ILOG_DBROOT) && ip->i_df.if_broot_bytes > 0) { *nbytes += ip->i_df.if_broot_bytes; @@ -362,6 +377,7 @@ xfs_inode_item_format_data_fork( } break; case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: iip->ili_fields &= ~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV); @@ -1023,18 +1039,6 @@ xfs_buf_inode_iodone( list_splice_tail(&flushed_inodes, &bp->b_li_list); } -void -xfs_buf_inode_io_fail( - struct xfs_buf *bp) -{ - struct xfs_log_item *lip; - - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { - set_bit(XFS_LI_FAILED, &lip->li_flags); - clear_bit(XFS_LI_FLUSHING, &lip->li_flags); - } -} - /* * Clear the inode logging fields so no more flushes are attempted. If we are * on a buffer list, it is now safe to remove it because the buffer is diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index e70d2611456b..f3bfb814378c 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -22,6 +22,8 @@ #include "xfs_log_recover.h" #include "xfs_icache.h" #include "xfs_bmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" STATIC void xlog_recover_inode_ra_pass2( @@ -266,6 +268,41 @@ xlog_dinode_verify_extent_counts( return 0; } +static inline int +xlog_recover_inode_dbroot( + struct xfs_mount *mp, + void *src, + unsigned int len, + struct xfs_dinode *dip) +{ + void *dfork = XFS_DFORK_DPTR(dip); + unsigned int dsize = XFS_DFORK_DSIZE(dip, mp); + + switch (dip->di_format) { + case XFS_DINODE_FMT_BTREE: + xfs_bmbt_to_bmdr(mp, src, len, dfork, dsize); + break; + case XFS_DINODE_FMT_META_BTREE: + switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + xfs_rtrmapbt_to_disk(mp, src, len, dfork, dsize); + return 0; + case XFS_METAFILE_RTREFCOUNT: + xfs_rtrefcountbt_to_disk(mp, src, len, dfork, dsize); + return 0; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + return 0; +} + STATIC int xlog_recover_inode_commit_pass2( struct xlog *log, @@ -393,8 +430,9 @@ xlog_recover_inode_commit_pass2( if (unlikely(S_ISREG(ldip->di_mode))) { - if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) && - (ldip->di_format != XFS_DINODE_FMT_BTREE)) { + if (ldip->di_format != XFS_DINODE_FMT_EXTENTS && + ldip->di_format != XFS_DINODE_FMT_BTREE && + ldip->di_format != XFS_DINODE_FMT_META_BTREE) { XFS_CORRUPTION_ERROR( "Bad log dinode data fork format for regular file", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); @@ -475,9 +513,9 @@ xlog_recover_inode_commit_pass2( break; case XFS_ILOG_DBROOT: - xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src, len, - (struct xfs_bmdr_block *)XFS_DFORK_DPTR(dip), - XFS_DFORK_DSIZE(dip, mp)); + error = xlog_recover_inode_dbroot(mp, src, len, dip); + if (error) + goto out_release; break; default: diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 0789c18aaa18..ed85322507dd 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -469,8 +469,21 @@ xfs_fill_fsxattr( } } - if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) - fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); + if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) { + /* + * Don't let a misaligned CoW extent size hint on a directory + * escape to userspace if it won't pass the setattr checks + * later. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + ip->i_cowextsize % mp->m_sb.sb_rextsize > 0) { + fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; + fa->fsx_cowextsize = 0; + } else { + fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); + } + } + fa->fsx_projid = ip->i_projid; if (ifp && !xfs_need_iread_extents(ifp)) fa->fsx_nextents = xfs_iext_count(ifp); @@ -541,10 +554,6 @@ xfs_ioctl_setattr_xflags( if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 || xfs_extlen_to_rtxmod(mp, ip->i_extsize)) return -EINVAL; - - /* Clear reflink if we are actually able to set the rt flag. */ - if (xfs_is_reflink_inode(ip)) - ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; } /* diflags2 only valid for v3 inodes. */ @@ -1204,7 +1213,16 @@ xfs_file_ioctl( struct xfs_buftarg *target = xfs_inode_buftarg(ip); struct dioattr da; - da.d_mem = da.d_miniosz = target->bt_logical_sectorsize; + da.d_mem = target->bt_logical_sectorsize; + + /* + * See xfs_report_dioalign() for an explanation about why this + * reports a value larger than the sector size for COW inodes. + */ + if (xfs_is_cow_inode(ip)) + da.d_miniosz = xfs_inode_alloc_unitsize(ip); + else + da.d_miniosz = target->bt_logical_sectorsize; da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1); if (copy_to_user(arg, &da, sizeof(da))) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 207e0dadffc3..40289fe6f5b2 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -573,17 +573,43 @@ xfs_stat_blksize( } static void -xfs_get_atomic_write_attr( +xfs_report_dioalign( struct xfs_inode *ip, - unsigned int *unit_min, - unsigned int *unit_max) + struct kstat *stat) { - if (!xfs_inode_can_atomicwrite(ip)) { - *unit_min = *unit_max = 0; - return; - } + struct xfs_buftarg *target = xfs_inode_buftarg(ip); + struct block_device *bdev = target->bt_bdev; - *unit_min = *unit_max = ip->i_mount->m_sb.sb_blocksize; + stat->result_mask |= STATX_DIOALIGN | STATX_DIO_READ_ALIGN; + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + + /* + * For COW inodes, we can only perform out of place writes of entire + * allocation units (blocks or RT extents). + * For writes smaller than the allocation unit, we must fall back to + * buffered I/O to perform read-modify-write cycles. At best this is + * highly inefficient; at worst it leads to page cache invalidation + * races. Tell applications to avoid this by reporting the larger write + * alignment in dio_offset_align, and the smaller read alignment in + * dio_read_offset_align. + */ + stat->dio_read_offset_align = bdev_logical_block_size(bdev); + if (xfs_is_cow_inode(ip)) + stat->dio_offset_align = xfs_inode_alloc_unitsize(ip); + else + stat->dio_offset_align = stat->dio_read_offset_align; +} + +static void +xfs_report_atomic_write( + struct xfs_inode *ip, + struct kstat *stat) +{ + unsigned int unit_min = 0, unit_max = 0; + + if (xfs_inode_can_atomicwrite(ip)) + unit_min = unit_max = ip->i_mount->m_sb.sb_blocksize; + generic_fill_statx_atomic_writes(stat, unit_min, unit_max); } STATIC int @@ -647,22 +673,10 @@ xfs_vn_getattr( stat->rdev = inode->i_rdev; break; case S_IFREG: - if (request_mask & STATX_DIOALIGN) { - struct xfs_buftarg *target = xfs_inode_buftarg(ip); - struct block_device *bdev = target->bt_bdev; - - stat->result_mask |= STATX_DIOALIGN; - stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; - stat->dio_offset_align = bdev_logical_block_size(bdev); - } - if (request_mask & STATX_WRITE_ATOMIC) { - unsigned int unit_min, unit_max; - - xfs_get_atomic_write_attr(ip, &unit_min, - &unit_max); - generic_fill_statx_atomic_writes(stat, - unit_min, unit_max); - } + if (request_mask & (STATX_DIOALIGN | STATX_DIO_READ_ALIGN)) + xfs_report_dioalign(ip, stat); + if (request_mask & STATX_WRITE_ATOMIC) + xfs_report_atomic_write(ip, stat); fallthrough; default: stat->blksize = xfs_stat_blksize(ip); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 05daad8a8d34..f8851ff835de 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -2744,8 +2744,6 @@ xfs_log_ticket_regrant( if (!ticket->t_cnt) { xlog_grant_add_space(&log->l_reserve_head, ticket->t_unit_res); trace_xfs_log_ticket_regrant_exit(log, ticket); - - ticket->t_curr_res = ticket->t_unit_res; } xfs_log_ticket_put(ticket); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 0af3d477197b..b3c27dbccce8 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1820,6 +1820,10 @@ static const struct xlog_recover_item_ops *xlog_recover_item_ops[] = { &xlog_xmd_item_ops, &xlog_rtefi_item_ops, &xlog_rtefd_item_ops, + &xlog_rtrui_item_ops, + &xlog_rtrud_item_ops, + &xlog_rtcui_item_ops, + &xlog_rtcud_item_ops, }; static const struct xlog_recover_item_ops * diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 5918f433dba7..477c5262cf91 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -37,6 +37,8 @@ #include "xfs_rtbitmap.h" #include "xfs_metafile.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/stats.h" static DEFINE_MUTEX(xfs_uuid_table_mutex); @@ -650,6 +652,15 @@ xfs_agbtree_compute_maxlevels( mp->m_agbtree_maxlevels = max(levels, mp->m_refc_maxlevels); } +/* Compute maximum possible height for realtime btree types for this fs. */ +static inline void +xfs_rtbtree_compute_maxlevels( + struct xfs_mount *mp) +{ + mp->m_rtbtree_maxlevels = max(mp->m_rtrmap_maxlevels, + mp->m_rtrefc_maxlevels); +} + /* * This function does the following on an initial mount of a file system: * - reads the superblock from disk and init the mount struct @@ -718,9 +729,12 @@ xfs_mountfs( xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK); xfs_mount_setup_inode_geom(mp); xfs_rmapbt_compute_maxlevels(mp); + xfs_rtrmapbt_compute_maxlevels(mp); xfs_refcountbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); xfs_agbtree_compute_maxlevels(mp); + xfs_rtbtree_compute_maxlevels(mp); /* * Check if sb_agblocks is aligned at stripe boundary. If sb_agblocks diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index db9dade7d22a..fbed172d6770 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -158,13 +158,20 @@ typedef struct xfs_mount { uint m_bmap_dmnr[2]; /* min bmap btree records */ uint m_rmap_mxr[2]; /* max rmap btree records */ uint m_rmap_mnr[2]; /* min rmap btree records */ + uint m_rtrmap_mxr[2]; /* max rtrmap btree records */ + uint m_rtrmap_mnr[2]; /* min rtrmap btree records */ uint m_refc_mxr[2]; /* max refc btree records */ uint m_refc_mnr[2]; /* min refc btree records */ + uint m_rtrefc_mxr[2]; /* max rtrefc btree records */ + uint m_rtrefc_mnr[2]; /* min rtrefc btree records */ uint m_alloc_maxlevels; /* max alloc btree levels */ uint m_bm_maxlevels[2]; /* max bmap btree levels */ uint m_rmap_maxlevels; /* max rmap btree levels */ + uint m_rtrmap_maxlevels; /* max rtrmap btree level */ uint m_refc_maxlevels; /* max refcount btree level */ + uint m_rtrefc_maxlevels; /* max rtrefc btree level */ unsigned int m_agbtree_maxlevels; /* max level of all AG btrees */ + unsigned int m_rtbtree_maxlevels; /* max level of all rt btrees */ xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */ uint m_alloc_set_aside; /* space we can't use */ uint m_ag_max_usable; /* max space per AG */ @@ -350,7 +357,7 @@ typedef struct xfs_mount { #define XFS_FEAT_NOUUID (1ULL << 63) /* ignore uuid during mount */ #define __XFS_HAS_FEAT(name, NAME) \ -static inline bool xfs_has_ ## name (struct xfs_mount *mp) \ +static inline bool xfs_has_ ## name (const struct xfs_mount *mp) \ { \ return mp->m_features & XFS_FEAT_ ## NAME; \ } @@ -386,18 +393,30 @@ __XFS_HAS_FEAT(large_extent_counts, NREXT64) __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE) __XFS_HAS_FEAT(metadir, METADIR) -static inline bool xfs_has_rtgroups(struct xfs_mount *mp) +static inline bool xfs_has_rtgroups(const struct xfs_mount *mp) { /* all metadir file systems also allow rtgroups */ return xfs_has_metadir(mp); } -static inline bool xfs_has_rtsb(struct xfs_mount *mp) +static inline bool xfs_has_rtsb(const struct xfs_mount *mp) { /* all rtgroups filesystems with an rt section have an rtsb */ return xfs_has_rtgroups(mp) && xfs_has_realtime(mp); } +static inline bool xfs_has_rtrmapbt(const struct xfs_mount *mp) +{ + return xfs_has_rtgroups(mp) && xfs_has_realtime(mp) && + xfs_has_rmapbt(mp); +} + +static inline bool xfs_has_rtreflink(const struct xfs_mount *mp) +{ + return xfs_has_metadir(mp) && xfs_has_realtime(mp) && + xfs_has_reflink(mp); +} + /* * Some features are always on for v5 file systems, allow the compiler to * eliminiate dead code when building without v4 support. diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index fa50e5308292..ed8d8ed42f0a 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -19,6 +19,9 @@ #include "xfs_rtalloc.h" #include "xfs_trans.h" #include "xfs_ag.h" +#include "xfs_notify_failure.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" #include #include @@ -154,23 +157,115 @@ xfs_dax_notify_failure_thaw( } static int -xfs_dax_notify_ddev_failure( +xfs_dax_translate_range( + struct xfs_buftarg *btp, + u64 offset, + u64 len, + xfs_daddr_t *daddr, + uint64_t *bblen) +{ + u64 dev_start = btp->bt_dax_part_off; + u64 dev_len = bdev_nr_bytes(btp->bt_bdev); + u64 dev_end = dev_start + dev_len - 1; + + /* Notify failure on the whole device. */ + if (offset == 0 && len == U64_MAX) { + offset = dev_start; + len = dev_len; + } + + /* Ignore the range out of filesystem area */ + if (offset + len - 1 < dev_start) + return -ENXIO; + if (offset > dev_end) + return -ENXIO; + + /* Calculate the real range when it touches the boundary */ + if (offset > dev_start) + offset -= dev_start; + else { + len -= dev_start - offset; + offset = 0; + } + if (offset + len - 1 > dev_end) + len = dev_end - offset + 1; + + *daddr = BTOBB(offset); + *bblen = BTOBB(len); + return 0; +} + +static int +xfs_dax_notify_logdev_failure( struct xfs_mount *mp, - xfs_daddr_t daddr, - xfs_daddr_t bblen, + u64 offset, + u64 len, int mf_flags) +{ + xfs_daddr_t daddr; + uint64_t bblen; + int error; + + /* + * Return ENXIO instead of shutting down the filesystem if the failed + * region is beyond the end of the log. + */ + error = xfs_dax_translate_range(mp->m_logdev_targp, + offset, len, &daddr, &bblen); + if (error) + return error; + + /* + * In the pre-remove case the failure notification is attempting to + * trigger a force unmount. The expectation is that the device is + * still present, but its removal is in progress and can not be + * cancelled, proceed with accessing the log device. + */ + if (mf_flags & MF_MEM_PRE_REMOVE) + return 0; + + xfs_err(mp, "ondisk log corrupt, shutting down fs!"); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; +} + +static int +xfs_dax_notify_dev_failure( + struct xfs_mount *mp, + u64 offset, + u64 len, + int mf_flags, + enum xfs_group_type type) { struct xfs_failure_info notify = { .mf_flags = mf_flags }; struct xfs_trans *tp = NULL; struct xfs_btree_cur *cur = NULL; - struct xfs_buf *agf_bp = NULL; int error = 0; bool kernel_frozen = false; - xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr); - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno); - xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, - daddr + bblen - 1); - xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno); + uint32_t start_gno, end_gno; + xfs_fsblock_t start_bno, end_bno; + xfs_daddr_t daddr; + uint64_t bblen; + struct xfs_group *xg = NULL; + + if (!xfs_has_rmapbt(mp)) { + xfs_debug(mp, "notify_failure() needs rmapbt enabled!"); + return -EOPNOTSUPP; + } + + error = xfs_dax_translate_range(type == XG_TYPE_RTG ? + mp->m_rtdev_targp : mp->m_ddev_targp, + offset, len, &daddr, &bblen); + if (error) + return error; + + if (type == XG_TYPE_RTG) { + start_bno = xfs_daddr_to_rtb(mp, daddr); + end_bno = xfs_daddr_to_rtb(mp, daddr + bblen - 1); + } else { + start_bno = XFS_DADDR_TO_FSB(mp, daddr); + end_bno = XFS_DADDR_TO_FSB(mp, daddr + bblen - 1); + } if (mf_flags & MF_MEM_PRE_REMOVE) { xfs_info(mp, "Device is about to be removed!"); @@ -189,46 +284,58 @@ xfs_dax_notify_ddev_failure( if (error) goto out; - for (; agno <= end_agno; agno++) { + start_gno = xfs_fsb_to_gno(mp, start_bno, type); + end_gno = xfs_fsb_to_gno(mp, end_bno, type); + while ((xg = xfs_group_next_range(mp, xg, start_gno, end_gno, type))) { + struct xfs_buf *agf_bp = NULL; + struct xfs_rtgroup *rtg = NULL; struct xfs_rmap_irec ri_low = { }; struct xfs_rmap_irec ri_high; - struct xfs_agf *agf; - struct xfs_perag *pag; - xfs_agblock_t range_agend; - pag = xfs_perag_get(mp, agno); - error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); - if (error) { - xfs_perag_put(pag); - break; + if (type == XG_TYPE_AG) { + struct xfs_perag *pag = to_perag(xg); + + error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); + if (error) { + xfs_perag_put(pag); + break; + } + + cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag); + } else { + rtg = to_rtg(xg); + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + cur = xfs_rtrmapbt_init_cursor(tp, rtg); } - cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag); - /* * Set the rmap range from ri_low to ri_high, which represents * a [start, end] where we looking for the files or metadata. */ memset(&ri_high, 0xFF, sizeof(ri_high)); - ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno); - if (agno == end_agno) - ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); + if (xg->xg_gno == start_gno) + ri_low.rm_startblock = + xfs_fsb_to_gbno(mp, start_bno, type); + if (xg->xg_gno == end_gno) + ri_high.rm_startblock = + xfs_fsb_to_gbno(mp, end_bno, type); - agf = agf_bp->b_addr; - range_agend = min(be32_to_cpu(agf->agf_length) - 1, - ri_high.rm_startblock); notify.startblock = ri_low.rm_startblock; - notify.blockcount = range_agend + 1 - ri_low.rm_startblock; + notify.blockcount = min(xg->xg_block_count, + ri_high.rm_startblock + 1) - + ri_low.rm_startblock; error = xfs_rmap_query_range(cur, &ri_low, &ri_high, xfs_dax_failure_fn, ¬ify); xfs_btree_del_cursor(cur, error); - xfs_trans_brelse(tp, agf_bp); - xfs_perag_put(pag); - if (error) + if (agf_bp) + xfs_trans_brelse(tp, agf_bp); + if (rtg) + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + if (error) { + xfs_group_put(xg); break; - - fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0); + } } xfs_trans_cancel(tp); @@ -263,67 +370,20 @@ xfs_dax_notify_failure( int mf_flags) { struct xfs_mount *mp = dax_holder(dax_dev); - u64 ddev_start; - u64 ddev_end; if (!(mp->m_super->s_flags & SB_BORN)) { xfs_warn(mp, "filesystem is not ready for notify_failure()!"); return -EIO; } - if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) { - xfs_debug(mp, - "notify_failure() not supported on realtime device!"); - return -EOPNOTSUPP; + if (mp->m_logdev_targp != mp->m_ddev_targp && + mp->m_logdev_targp->bt_daxdev == dax_dev) { + return xfs_dax_notify_logdev_failure(mp, offset, len, mf_flags); } - if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev && - mp->m_logdev_targp != mp->m_ddev_targp) { - /* - * In the pre-remove case the failure notification is attempting - * to trigger a force unmount. The expectation is that the - * device is still present, but its removal is in progress and - * can not be cancelled, proceed with accessing the log device. - */ - if (mf_flags & MF_MEM_PRE_REMOVE) - return 0; - xfs_err(mp, "ondisk log corrupt, shutting down fs!"); - xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); - return -EFSCORRUPTED; - } - - if (!xfs_has_rmapbt(mp)) { - xfs_debug(mp, "notify_failure() needs rmapbt enabled!"); - return -EOPNOTSUPP; - } - - ddev_start = mp->m_ddev_targp->bt_dax_part_off; - ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1; - - /* Notify failure on the whole device. */ - if (offset == 0 && len == U64_MAX) { - offset = ddev_start; - len = bdev_nr_bytes(mp->m_ddev_targp->bt_bdev); - } - - /* Ignore the range out of filesystem area */ - if (offset + len - 1 < ddev_start) - return -ENXIO; - if (offset > ddev_end) - return -ENXIO; - - /* Calculate the real range when it touches the boundary */ - if (offset > ddev_start) - offset -= ddev_start; - else { - len -= ddev_start - offset; - offset = 0; - } - if (offset + len - 1 > ddev_end) - len = ddev_end - offset + 1; - - return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len), - mf_flags); + return xfs_dax_notify_dev_failure(mp, offset, len, mf_flags, + (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) ? + XG_TYPE_RTG : XG_TYPE_AG); } const struct dax_holder_operations xfs_dax_holder_operations = { diff --git a/fs/xfs/xfs_notify_failure.h b/fs/xfs/xfs_notify_failure.h new file mode 100644 index 000000000000..8d08ec29dd29 --- /dev/null +++ b/fs/xfs/xfs_notify_failure.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#ifndef __XFS_NOTIFY_FAILURE_H__ +#define __XFS_NOTIFY_FAILURE_H__ + +extern const struct dax_holder_operations xfs_dax_holder_operations; + +#endif /* __XFS_NOTIFY_FAILURE_H__ */ diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index dc8b1010d4d3..e1ba5af6250f 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -230,10 +230,10 @@ xfs_qm_unmount_rt( if (!rtg) return; - if (rtg->rtg_inodes[XFS_RTGI_BITMAP]) - xfs_qm_dqdetach(rtg->rtg_inodes[XFS_RTGI_BITMAP]); - if (rtg->rtg_inodes[XFS_RTGI_SUMMARY]) - xfs_qm_dqdetach(rtg->rtg_inodes[XFS_RTGI_SUMMARY]); + if (rtg_bitmap(rtg)) + xfs_qm_dqdetach(rtg_bitmap(rtg)); + if (rtg_summary(rtg)) + xfs_qm_dqdetach(rtg_summary(rtg)); xfs_rtgroup_rele(rtg); } @@ -428,6 +428,8 @@ void xfs_qm_dqdetach( xfs_inode_t *ip) { + if (xfs_is_metadir_inode(ip)) + return; if (!(ip->i_udquot || ip->i_gdquot || ip->i_pdquot)) return; diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 847ba29630e9..37f1230e7584 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -32,21 +32,27 @@ xfs_fill_statvfs_from_dquot( limit = blkres->softlimit ? blkres->softlimit : blkres->hardlimit; - if (limit && statp->f_blocks > limit) { - statp->f_blocks = limit; - statp->f_bfree = statp->f_bavail = - (statp->f_blocks > blkres->reserved) ? - (statp->f_blocks - blkres->reserved) : 0; + if (limit) { + uint64_t remaining = 0; + + if (limit > blkres->reserved) + remaining = limit - blkres->reserved; + + statp->f_blocks = min(statp->f_blocks, limit); + statp->f_bfree = min(statp->f_bfree, remaining); } limit = dqp->q_ino.softlimit ? dqp->q_ino.softlimit : dqp->q_ino.hardlimit; - if (limit && statp->f_files > limit) { - statp->f_files = limit; - statp->f_ffree = - (statp->f_files > dqp->q_ino.reserved) ? - (statp->f_files - dqp->q_ino.reserved) : 0; + if (limit) { + uint64_t remaining = 0; + + if (limit > dqp->q_ino.reserved) + remaining = limit - dqp->q_ino.reserved; + + statp->f_files = min(statp->f_files, limit); + statp->f_ffree = min(statp->f_ffree, remaining); } } diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index d7565462af3d..105e6eb57620 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -29,11 +29,6 @@ struct xfs_buf; (XFS_IS_GQUOTA_ON(mp) && (ip)->i_gdquot == NULL) || \ (XFS_IS_PQUOTA_ON(mp) && (ip)->i_pdquot == NULL)) -#define XFS_IS_DQDETACHED(ip) \ - ((ip)->i_udquot == NULL && \ - (ip)->i_gdquot == NULL && \ - (ip)->i_pdquot == NULL) - #define XFS_QM_NEED_QUOTACHECK(mp) \ ((XFS_IS_UQUOTA_ON(mp) && \ (mp->m_sb.sb_qflags & XFS_UQUOTA_CHKD) == 0) || \ diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index bede1c96c330..fe2d7aab8554 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -23,6 +23,7 @@ #include "xfs_ag.h" #include "xfs_btree.h" #include "xfs_trace.h" +#include "xfs_rtgroup.h" struct kmem_cache *xfs_cui_cache; struct kmem_cache *xfs_cud_cache; @@ -94,8 +95,9 @@ xfs_cui_item_format( ASSERT(atomic_read(&cuip->cui_next_extent) == cuip->cui_format.cui_nextents); + ASSERT(lip->li_type == XFS_LI_CUI || lip->li_type == XFS_LI_CUI_RT); - cuip->cui_format.cui_type = XFS_LI_CUI; + cuip->cui_format.cui_type = lip->li_type; cuip->cui_format.cui_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_CUI_FORMAT, &cuip->cui_format, @@ -138,12 +140,14 @@ xfs_cui_item_release( STATIC struct xfs_cui_log_item * xfs_cui_init( struct xfs_mount *mp, + unsigned short item_type, uint nextents) - { struct xfs_cui_log_item *cuip; ASSERT(nextents > 0); + ASSERT(item_type == XFS_LI_CUI || item_type == XFS_LI_CUI_RT); + if (nextents > XFS_CUI_MAX_FAST_EXTENTS) cuip = kzalloc(xfs_cui_log_item_sizeof(nextents), GFP_KERNEL | __GFP_NOFAIL); @@ -151,7 +155,7 @@ xfs_cui_init( cuip = kmem_cache_zalloc(xfs_cui_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(mp, &cuip->cui_item, XFS_LI_CUI, &xfs_cui_item_ops); + xfs_log_item_init(mp, &cuip->cui_item, item_type, &xfs_cui_item_ops); cuip->cui_format.cui_nextents = nextents; cuip->cui_format.cui_id = (uintptr_t)(void *)cuip; atomic_set(&cuip->cui_next_extent, 0); @@ -190,7 +194,9 @@ xfs_cud_item_format( struct xfs_cud_log_item *cudp = CUD_ITEM(lip); struct xfs_log_iovec *vecp = NULL; - cudp->cud_format.cud_type = XFS_LI_CUD; + ASSERT(lip->li_type == XFS_LI_CUD || lip->li_type == XFS_LI_CUD_RT); + + cudp->cud_format.cud_type = lip->li_type; cudp->cud_format.cud_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_CUD_FORMAT, &cudp->cud_format, @@ -234,6 +240,14 @@ static inline struct xfs_refcount_intent *ci_entry(const struct list_head *e) return list_entry(e, struct xfs_refcount_intent, ri_list); } +static inline bool +xfs_cui_item_isrt(const struct xfs_log_item *lip) +{ + ASSERT(lip->li_type == XFS_LI_CUI || lip->li_type == XFS_LI_CUI_RT); + + return lip->li_type == XFS_LI_CUI_RT; +} + /* Sort refcount intents by AG. */ static int xfs_refcount_update_diff_items( @@ -281,6 +295,28 @@ xfs_refcount_update_log_item( } } +static struct xfs_log_item * +__xfs_refcount_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort, + unsigned short item_type) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_cui_log_item *cuip; + struct xfs_refcount_intent *ri; + + ASSERT(count > 0); + + cuip = xfs_cui_init(mp, item_type, count); + if (sort) + list_sort(mp, items, xfs_refcount_update_diff_items); + list_for_each_entry(ri, items, ri_list) + xfs_refcount_update_log_item(tp, cuip, ri); + return &cuip->cui_item; +} + static struct xfs_log_item * xfs_refcount_update_create_intent( struct xfs_trans *tp, @@ -288,17 +324,14 @@ xfs_refcount_update_create_intent( unsigned int count, bool sort) { - struct xfs_mount *mp = tp->t_mountp; - struct xfs_cui_log_item *cuip = xfs_cui_init(mp, count); - struct xfs_refcount_intent *ri; + return __xfs_refcount_update_create_intent(tp, items, count, sort, + XFS_LI_CUI); +} - ASSERT(count > 0); - - if (sort) - list_sort(mp, items, xfs_refcount_update_diff_items); - list_for_each_entry(ri, items, ri_list) - xfs_refcount_update_log_item(tp, cuip, ri); - return &cuip->cui_item; +static inline unsigned short +xfs_cud_type_from_cui(const struct xfs_cui_log_item *cuip) +{ + return xfs_cui_item_isrt(&cuip->cui_item) ? XFS_LI_CUD_RT : XFS_LI_CUD; } /* Get an CUD so we can process all the deferred refcount updates. */ @@ -312,8 +345,8 @@ xfs_refcount_update_create_done( struct xfs_cud_log_item *cudp; cudp = kmem_cache_zalloc(xfs_cud_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD, - &xfs_cud_item_ops); + xfs_log_item_init(tp->t_mountp, &cudp->cud_item, + xfs_cud_type_from_cui(cuip), &xfs_cud_item_ops); cudp->cud_cuip = cuip; cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id; @@ -328,10 +361,20 @@ xfs_refcount_defer_add( { struct xfs_mount *mp = tp->t_mountp; - trace_xfs_refcount_defer(mp, ri); + /* + * Deferred refcount updates for the realtime and data sections must + * use separate transactions to finish deferred work because updates to + * realtime metadata files can lock AGFs to allocate btree blocks and + * we don't want that mixing with the AGF locks taken to finish data + * section updates. + */ + ri->ri_group = xfs_group_intent_get(mp, ri->ri_startblock, + ri->ri_realtime ? XG_TYPE_RTG : XG_TYPE_AG); - ri->ri_group = xfs_group_intent_get(mp, ri->ri_startblock, XG_TYPE_AG); - xfs_defer_add(tp, &ri->ri_list, &xfs_refcount_update_defer_type); + trace_xfs_refcount_defer(mp, ri); + xfs_defer_add(tp, &ri->ri_list, ri->ri_realtime ? + &xfs_rtrefcount_update_defer_type : + &xfs_refcount_update_defer_type); } /* Cancel a deferred refcount update. */ @@ -381,7 +424,7 @@ xfs_refcount_finish_one_cleanup( return; agbp = rcur->bc_ag.agbp; xfs_btree_del_cursor(rcur, error); - if (error) + if (error && agbp) xfs_trans_brelse(tp, agbp); } @@ -397,6 +440,7 @@ xfs_refcount_update_abort_intent( static inline bool xfs_cui_validate_phys( struct xfs_mount *mp, + bool isrt, struct xfs_phys_extent *pmap) { if (!xfs_has_reflink(mp)) @@ -415,6 +459,9 @@ xfs_cui_validate_phys( return false; } + if (isrt) + return xfs_verify_rtbext(mp, pmap->pe_startblock, pmap->pe_len); + return xfs_verify_fsbext(mp, pmap->pe_startblock, pmap->pe_len); } @@ -422,6 +469,7 @@ static inline void xfs_cui_recover_work( struct xfs_mount *mp, struct xfs_defer_pending *dfp, + bool isrt, struct xfs_phys_extent *pmap) { struct xfs_refcount_intent *ri; @@ -432,7 +480,8 @@ xfs_cui_recover_work( ri->ri_startblock = pmap->pe_startblock; ri->ri_blockcount = pmap->pe_len; ri->ri_group = xfs_group_intent_get(mp, pmap->pe_startblock, - XG_TYPE_AG); + isrt ? XG_TYPE_RTG : XG_TYPE_AG); + ri->ri_realtime = isrt; xfs_defer_add_item(dfp, &ri->ri_list); } @@ -451,6 +500,7 @@ xfs_refcount_recover_work( struct xfs_cui_log_item *cuip = CUI_ITEM(lip); struct xfs_trans *tp; struct xfs_mount *mp = lip->li_log->l_mp; + bool isrt = xfs_cui_item_isrt(lip); int i; int error = 0; @@ -460,7 +510,7 @@ xfs_refcount_recover_work( * just toss the CUI. */ for (i = 0; i < cuip->cui_format.cui_nextents; i++) { - if (!xfs_cui_validate_phys(mp, + if (!xfs_cui_validate_phys(mp, isrt, &cuip->cui_format.cui_extents[i])) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &cuip->cui_format, @@ -468,7 +518,8 @@ xfs_refcount_recover_work( return -EFSCORRUPTED; } - xfs_cui_recover_work(mp, dfp, &cuip->cui_format.cui_extents[i]); + xfs_cui_recover_work(mp, dfp, isrt, + &cuip->cui_format.cui_extents[i]); } /* @@ -515,10 +566,13 @@ xfs_refcount_relog_intent( struct xfs_phys_extent *pmap; unsigned int count; + ASSERT(intent->li_type == XFS_LI_CUI || + intent->li_type == XFS_LI_CUI_RT); + count = CUI_ITEM(intent)->cui_format.cui_nextents; pmap = CUI_ITEM(intent)->cui_format.cui_extents; - cuip = xfs_cui_init(tp->t_mountp, count); + cuip = xfs_cui_init(tp->t_mountp, intent->li_type, count); memcpy(cuip->cui_format.cui_extents, pmap, count * sizeof(*pmap)); atomic_set(&cuip->cui_next_extent, count); @@ -538,6 +592,71 @@ const struct xfs_defer_op_type xfs_refcount_update_defer_type = { .relog_intent = xfs_refcount_relog_intent, }; +#ifdef CONFIG_XFS_RT +static struct xfs_log_item * +xfs_rtrefcount_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_refcount_update_create_intent(tp, items, count, sort, + XFS_LI_CUI_RT); +} + +/* Process a deferred realtime refcount update. */ +STATIC int +xfs_rtrefcount_update_finish_item( + struct xfs_trans *tp, + struct xfs_log_item *done, + struct list_head *item, + struct xfs_btree_cur **state) +{ + struct xfs_refcount_intent *ri = ci_entry(item); + int error; + + error = xfs_rtrefcount_finish_one(tp, ri, state); + + /* Did we run out of reservation? Requeue what we didn't finish. */ + if (!error && ri->ri_blockcount > 0) { + ASSERT(ri->ri_type == XFS_REFCOUNT_INCREASE || + ri->ri_type == XFS_REFCOUNT_DECREASE); + return -EAGAIN; + } + + xfs_refcount_update_cancel_item(item); + return error; +} + +/* Clean up after calling xfs_rtrefcount_finish_one. */ +STATIC void +xfs_rtrefcount_finish_one_cleanup( + struct xfs_trans *tp, + struct xfs_btree_cur *rcur, + int error) +{ + if (rcur) + xfs_btree_del_cursor(rcur, error); +} + +const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type = { + .name = "rtrefcount", + .max_items = XFS_CUI_MAX_FAST_EXTENTS, + .create_intent = xfs_rtrefcount_update_create_intent, + .abort_intent = xfs_refcount_update_abort_intent, + .create_done = xfs_refcount_update_create_done, + .finish_item = xfs_rtrefcount_update_finish_item, + .finish_cleanup = xfs_rtrefcount_finish_one_cleanup, + .cancel_item = xfs_refcount_update_cancel_item, + .recover_work = xfs_refcount_recover_work, + .relog_intent = xfs_refcount_relog_intent, +}; +#else +const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type = { + .name = "rtrefcount", +}; +#endif /* CONFIG_XFS_RT */ + STATIC bool xfs_cui_item_match( struct xfs_log_item *lip, @@ -603,7 +722,7 @@ xlog_recover_cui_commit_pass2( return -EFSCORRUPTED; } - cuip = xfs_cui_init(mp, cui_formatp->cui_nextents); + cuip = xfs_cui_init(mp, ITEM_TYPE(item), cui_formatp->cui_nextents); xfs_cui_copy_format(&cuip->cui_format, cui_formatp); atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents); @@ -617,6 +736,61 @@ const struct xlog_recover_item_ops xlog_cui_item_ops = { .commit_pass2 = xlog_recover_cui_commit_pass2, }; +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtcui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_mount *mp = log->l_mp; + struct xfs_cui_log_item *cuip; + struct xfs_cui_log_format *cui_formatp; + size_t len; + + cui_formatp = item->ri_buf[0].i_addr; + + if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + cuip = xfs_cui_init(mp, ITEM_TYPE(item), cui_formatp->cui_nextents); + xfs_cui_copy_format(&cuip->cui_format, cui_formatp); + atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents); + + xlog_recover_intent_item(log, &cuip->cui_item, lsn, + &xfs_rtrefcount_update_defer_type); + return 0; +} +#else +STATIC int +xlog_recover_rtcui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; +} +#endif + +const struct xlog_recover_item_ops xlog_rtcui_item_ops = { + .item_type = XFS_LI_CUI_RT, + .commit_pass2 = xlog_recover_rtcui_commit_pass2, +}; + /* * This routine is called when an CUD format structure is found in a committed * transaction in the log. Its purpose is to cancel the corresponding CUI if it @@ -648,3 +822,33 @@ const struct xlog_recover_item_ops xlog_cud_item_ops = { .item_type = XFS_LI_CUD, .commit_pass2 = xlog_recover_cud_commit_pass2, }; + +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtcud_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_cud_log_format *cud_formatp; + + cud_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + xlog_recover_release_intent(log, XFS_LI_CUI_RT, + cud_formatp->cud_cui_id); + return 0; +} +#else +# define xlog_recover_rtcud_commit_pass2 xlog_recover_rtcui_commit_pass2 +#endif + +const struct xlog_recover_item_ops xlog_rtcud_item_ops = { + .item_type = XFS_LI_CUD_RT, + .commit_pass2 = xlog_recover_rtcud_commit_pass2, +}; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index b11769c009ef..59f7fc16eb80 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -30,6 +30,10 @@ #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_health.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_rtgroup.h" +#include "xfs_metafile.h" /* * Copy on Write of Shared Blocks @@ -120,38 +124,93 @@ */ /* - * Given an AG extent, find the lowest-numbered run of shared blocks - * within that range and return the range in fbno/flen. If - * find_end_of_shared is true, return the longest contiguous extent of - * shared blocks. If there are no shared extents, fbno and flen will - * be set to NULLAGBLOCK and 0, respectively. + * Given a file mapping for the data device, find the lowest-numbered run of + * shared blocks within that mapping and return it in shared_offset/shared_len. + * The offset is relative to the start of irec. + * + * If find_end_of_shared is true, return the longest contiguous extent of shared + * blocks. If there are no shared extents, shared_offset and shared_len will be + * set to 0; */ static int xfs_reflink_find_shared( - struct xfs_perag *pag, + struct xfs_mount *mp, struct xfs_trans *tp, - xfs_agblock_t agbno, - xfs_extlen_t aglen, - xfs_agblock_t *fbno, - xfs_extlen_t *flen, + const struct xfs_bmbt_irec *irec, + xfs_extlen_t *shared_offset, + xfs_extlen_t *shared_len, bool find_end_of_shared) { struct xfs_buf *agbp; + struct xfs_perag *pag; struct xfs_btree_cur *cur; int error; + xfs_agblock_t orig_bno, found_bno; + + pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, irec->br_startblock)); + orig_bno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock); error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) - return error; - - cur = xfs_refcountbt_init_cursor(pag_mount(pag), tp, agbp, pag); - - error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen, - find_end_of_shared); + goto out; + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); + error = xfs_refcount_find_shared(cur, orig_bno, irec->br_blockcount, + &found_bno, shared_len, find_end_of_shared); xfs_btree_del_cursor(cur, error); - xfs_trans_brelse(tp, agbp); + + if (!error && *shared_len) + *shared_offset = found_bno - orig_bno; +out: + xfs_perag_put(pag); + return error; +} + +/* + * Given a file mapping for the rt device, find the lowest-numbered run of + * shared blocks within that mapping and return it in shared_offset/shared_len. + * The offset is relative to the start of irec. + * + * If find_end_of_shared is true, return the longest contiguous extent of shared + * blocks. If there are no shared extents, shared_offset and shared_len will be + * set to 0; + */ +static int +xfs_reflink_find_rtshared( + struct xfs_mount *mp, + struct xfs_trans *tp, + const struct xfs_bmbt_irec *irec, + xfs_extlen_t *shared_offset, + xfs_extlen_t *shared_len, + bool find_end_of_shared) +{ + struct xfs_rtgroup *rtg; + struct xfs_btree_cur *cur; + xfs_rgblock_t orig_bno; + xfs_agblock_t found_bno; + int error; + + BUILD_BUG_ON(NULLRGBLOCK != NULLAGBLOCK); + + /* + * Note: this uses the not quite correct xfs_agblock_t type because + * xfs_refcount_find_shared is shared between the RT and data device + * refcount code. + */ + orig_bno = xfs_rtb_to_rgbno(mp, irec->br_startblock); + rtg = xfs_rtgroup_get(mp, xfs_rtb_to_rgno(mp, irec->br_startblock)); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_REFCOUNT); + cur = xfs_rtrefcountbt_init_cursor(tp, rtg); + error = xfs_refcount_find_shared(cur, orig_bno, irec->br_blockcount, + &found_bno, shared_len, find_end_of_shared); + xfs_btree_del_cursor(cur, error); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_REFCOUNT); + xfs_rtgroup_put(rtg); + + if (!error && *shared_len) + *shared_offset = found_bno - orig_bno; return error; } @@ -172,11 +231,7 @@ xfs_reflink_trim_around_shared( bool *shared) { struct xfs_mount *mp = ip->i_mount; - struct xfs_perag *pag; - xfs_agblock_t agbno; - xfs_extlen_t aglen; - xfs_agblock_t fbno; - xfs_extlen_t flen; + xfs_extlen_t shared_offset, shared_len; int error = 0; /* Holes, unwritten, and delalloc extents cannot be shared */ @@ -187,41 +242,37 @@ xfs_reflink_trim_around_shared( trace_xfs_reflink_trim_around_shared(ip, irec); - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, irec->br_startblock)); - agbno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock); - aglen = irec->br_blockcount; - - error = xfs_reflink_find_shared(pag, NULL, agbno, aglen, &fbno, &flen, - true); - xfs_perag_put(pag); + if (XFS_IS_REALTIME_INODE(ip)) + error = xfs_reflink_find_rtshared(mp, NULL, irec, + &shared_offset, &shared_len, true); + else + error = xfs_reflink_find_shared(mp, NULL, irec, + &shared_offset, &shared_len, true); if (error) return error; - *shared = false; - if (fbno == NULLAGBLOCK) { + if (!shared_len) { /* No shared blocks at all. */ - return 0; - } - - if (fbno == agbno) { + *shared = false; + } else if (!shared_offset) { /* - * The start of this extent is shared. Truncate the - * mapping at the end of the shared region so that a - * subsequent iteration starts at the start of the - * unshared region. + * The start of this mapping points to shared space. Truncate + * the mapping at the end of the shared region so that a + * subsequent iteration starts at the start of the unshared + * region. */ - irec->br_blockcount = flen; + irec->br_blockcount = shared_len; *shared = true; - return 0; + } else { + /* + * There's a shared region that doesn't start at the beginning + * of the mapping. Truncate the mapping at the start of the + * shared extent so that a subsequent iteration starts at the + * start of the shared region. + */ + irec->br_blockcount = shared_offset; + *shared = false; } - - /* - * There's a shared extent midway through this extent. - * Truncate the mapping at the start of the shared - * extent so that a subsequent iteration starts at the - * start of the shared region. - */ - irec->br_blockcount = fbno - agbno; return 0; } @@ -389,20 +440,26 @@ xfs_reflink_fill_cow_hole( struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; xfs_filblks_t resaligned; - xfs_extlen_t resblks; + unsigned int dblocks = 0, rblocks = 0; int nimaps; int error; bool found; resaligned = xfs_aligned_fsb_count(imap->br_startoff, imap->br_blockcount, xfs_get_cowextsz_hint(ip)); - resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + if (XFS_IS_REALTIME_INODE(ip)) { + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0); + rblocks = resaligned; + } else { + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + rblocks = 0; + } xfs_iunlock(ip, *lockmode); *lockmode = 0; - error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, 0, - false, &tp); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks, + rblocks, false, &tp); if (error) return error; @@ -571,6 +628,7 @@ xfs_reflink_cancel_cow_blocks( struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); struct xfs_bmbt_irec got, del; struct xfs_iext_cursor icur; + bool isrt = XFS_IS_REALTIME_INODE(ip); int error = 0; if (!xfs_inode_has_cow_data(ip)) @@ -598,12 +656,13 @@ xfs_reflink_cancel_cow_blocks( ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER); /* Free the CoW orphan record. */ - xfs_refcount_free_cow_extent(*tpp, del.br_startblock, - del.br_blockcount); + xfs_refcount_free_cow_extent(*tpp, isrt, + del.br_startblock, del.br_blockcount); error = xfs_free_extent_later(*tpp, del.br_startblock, del.br_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + XFS_AG_RESV_NONE, + isrt ? XFS_FREE_EXTENT_REALTIME : 0); if (error) break; @@ -687,6 +746,35 @@ out: return error; } +#ifdef CONFIG_XFS_QUOTA +/* + * Update quota accounting for a remapping operation. When we're remapping + * something from the CoW fork to the data fork, we must update the quota + * accounting for delayed allocations. For remapping from the data fork to the + * data fork, use regular block accounting. + */ +static inline void +xfs_reflink_update_quota( + struct xfs_trans *tp, + struct xfs_inode *ip, + bool is_cow, + int64_t blocks) +{ + unsigned int qflag; + + if (XFS_IS_REALTIME_INODE(ip)) { + qflag = is_cow ? XFS_TRANS_DQ_DELRTBCOUNT : + XFS_TRANS_DQ_RTBCOUNT; + } else { + qflag = is_cow ? XFS_TRANS_DQ_DELBCOUNT : + XFS_TRANS_DQ_BCOUNT; + } + xfs_trans_mod_dquot_byino(tp, ip, qflag, blocks); +} +#else +# define xfs_reflink_update_quota(tp, ip, is_cow, blocks) ((void)0) +#endif + /* * Remap part of the CoW fork into the data fork. * @@ -710,6 +798,7 @@ xfs_reflink_end_cow_extent( struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); unsigned int resblks; int nmaps; + bool isrt = XFS_IS_REALTIME_INODE(ip); int error; resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); @@ -779,9 +868,8 @@ xfs_reflink_end_cow_extent( * or not), unmap the extent and drop its refcount. */ xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &data); - xfs_refcount_decrease_extent(tp, &data); - xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, - -data.br_blockcount); + xfs_refcount_decrease_extent(tp, isrt, &data); + xfs_reflink_update_quota(tp, ip, false, -data.br_blockcount); } else if (data.br_startblock == DELAYSTARTBLOCK) { int done; @@ -799,14 +887,14 @@ xfs_reflink_end_cow_extent( } /* Free the CoW orphan record. */ - xfs_refcount_free_cow_extent(tp, del.br_startblock, del.br_blockcount); + xfs_refcount_free_cow_extent(tp, isrt, del.br_startblock, + del.br_blockcount); /* Map the new blocks into the data fork. */ xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, &del); /* Charge this new data fork mapping to the on-disk quota. */ - xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT, - (long)del.br_blockcount); + xfs_reflink_update_quota(tp, ip, true, del.br_blockcount); /* Remove the mapping from the CoW fork. */ xfs_bmap_del_extent_cow(ip, &icur, &got, &del); @@ -895,20 +983,29 @@ xfs_reflink_recover_cow( struct xfs_mount *mp) { struct xfs_perag *pag = NULL; + struct xfs_rtgroup *rtg = NULL; int error = 0; if (!xfs_has_reflink(mp)) return 0; while ((pag = xfs_perag_next(mp, pag))) { - error = xfs_refcount_recover_cow_leftovers(mp, pag); + error = xfs_refcount_recover_cow_leftovers(pag_group(pag)); if (error) { xfs_perag_rele(pag); - break; + return error; } } - return error; + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + error = xfs_refcount_recover_cow_leftovers(rtg_group(rtg)); + if (error) { + xfs_rtgroup_rele(rtg); + return error; + } + } + + return 0; } /* @@ -1100,14 +1197,28 @@ out_error: static int xfs_reflink_ag_has_free_space( struct xfs_mount *mp, - xfs_agnumber_t agno) + struct xfs_inode *ip, + xfs_fsblock_t fsb) { struct xfs_perag *pag; + xfs_agnumber_t agno; int error = 0; if (!xfs_has_rmapbt(mp)) return 0; + if (XFS_IS_REALTIME_INODE(ip)) { + struct xfs_rtgroup *rtg; + xfs_rgnumber_t rgno; + rgno = xfs_rtb_to_rgno(mp, fsb); + rtg = xfs_rtgroup_get(mp, rgno); + if (xfs_metafile_resv_critical(rtg_rmap(rtg))) + error = -ENOSPC; + xfs_rtgroup_put(rtg); + return error; + } + + agno = XFS_FSB_TO_AGNO(mp, fsb); pag = xfs_perag_get(mp, agno); if (xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) || xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA)) @@ -1131,10 +1242,11 @@ xfs_reflink_remap_extent( struct xfs_trans *tp; xfs_off_t newlen; int64_t qdelta = 0; - unsigned int resblks; + unsigned int dblocks, rblocks, resblks; bool quota_reserved = true; bool smap_real; bool dmap_written = xfs_bmap_is_written_extent(dmap); + bool isrt = XFS_IS_REALTIME_INODE(ip); int iext_delta = 0; int nimaps; int error; @@ -1161,8 +1273,15 @@ xfs_reflink_remap_extent( * we're remapping. */ resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); + if (XFS_IS_REALTIME_INODE(ip)) { + dblocks = resblks; + rblocks = dmap->br_blockcount; + } else { + dblocks = resblks + dmap->br_blockcount; + rblocks = 0; + } error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, - resblks + dmap->br_blockcount, 0, false, &tp); + dblocks, rblocks, false, &tp); if (error == -EDQUOT || error == -ENOSPC) { quota_reserved = false; error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, @@ -1213,8 +1332,8 @@ xfs_reflink_remap_extent( /* No reflinking if the AG of the dest mapping is low on space. */ if (dmap_written) { - error = xfs_reflink_ag_has_free_space(mp, - XFS_FSB_TO_AGNO(mp, dmap->br_startblock)); + error = xfs_reflink_ag_has_free_space(mp, ip, + dmap->br_startblock); if (error) goto out_cancel; } @@ -1242,8 +1361,15 @@ xfs_reflink_remap_extent( * done. */ if (!quota_reserved && !smap_real && dmap_written) { - error = xfs_trans_reserve_quota_nblks(tp, ip, - dmap->br_blockcount, 0, false); + if (XFS_IS_REALTIME_INODE(ip)) { + dblocks = 0; + rblocks = dmap->br_blockcount; + } else { + dblocks = dmap->br_blockcount; + rblocks = 0; + } + error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, + false); if (error) goto out_cancel; } @@ -1264,7 +1390,7 @@ xfs_reflink_remap_extent( * or not), unmap the extent and drop its refcount. */ xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &smap); - xfs_refcount_decrease_extent(tp, &smap); + xfs_refcount_decrease_extent(tp, isrt, &smap); qdelta -= smap.br_blockcount; } else if (smap.br_startblock == DELAYSTARTBLOCK) { int done; @@ -1287,12 +1413,12 @@ xfs_reflink_remap_extent( * its refcount and map it into the file. */ if (dmap_written) { - xfs_refcount_increase_extent(tp, dmap); + xfs_refcount_increase_extent(tp, isrt, dmap); xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, dmap); qdelta += dmap->br_blockcount; } - xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, qdelta); + xfs_reflink_update_quota(tp, ip, false, qdelta); /* Update dest isize if needed. */ newlen = XFS_FSB_TO_B(mp, dmap->br_startoff + dmap->br_blockcount); @@ -1466,8 +1592,8 @@ xfs_reflink_remap_prep( /* Check file eligibility and prepare for block sharing. */ ret = -EINVAL; - /* Don't reflink realtime inodes */ - if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) + /* Can't reflink between data and rt volumes */ + if (XFS_IS_REALTIME_INODE(src) != XFS_IS_REALTIME_INODE(dest)) goto out_unlock; /* Don't share DAX file data with non-DAX file. */ @@ -1547,27 +1673,23 @@ xfs_reflink_inode_has_shared_extents( *has_shared = false; found = xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got); while (found) { - struct xfs_perag *pag; - xfs_agblock_t agbno; - xfs_extlen_t aglen; - xfs_agblock_t rbno; - xfs_extlen_t rlen; + xfs_extlen_t shared_offset, shared_len; if (isnullstartblock(got.br_startblock) || got.br_state != XFS_EXT_NORM) goto next; - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, got.br_startblock)); - agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock); - aglen = got.br_blockcount; - error = xfs_reflink_find_shared(pag, tp, agbno, aglen, - &rbno, &rlen, false); - xfs_perag_put(pag); + if (XFS_IS_REALTIME_INODE(ip)) + error = xfs_reflink_find_rtshared(mp, tp, &got, + &shared_offset, &shared_len, false); + else + error = xfs_reflink_find_shared(mp, tp, &got, + &shared_offset, &shared_len, false); if (error) return error; /* Is there still a shared block here? */ - if (rbno != NULLAGBLOCK) { + if (shared_len) { *has_shared = true; return 0; } @@ -1700,3 +1822,28 @@ out: trace_xfs_reflink_unshare_error(ip, error, _RET_IP_); return error; } + +/* + * Can we use reflink with this realtime extent size? Note that we don't check + * for rblocks > 0 here because this can be called as part of attaching a new + * rt section. + */ +bool +xfs_reflink_supports_rextsize( + struct xfs_mount *mp, + unsigned int rextsize) +{ + /* reflink on the realtime device requires rtgroups */ + if (!xfs_has_rtgroups(mp)) + return false; + + /* + * Reflink doesn't support rt extent size larger than a single fsblock + * because we would have to perform CoW-around for unaligned write + * requests to guarantee that we always remap entire rt extents. + */ + if (rextsize != 1) + return false; + + return true; +} diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 4a58e4533671..cc4e92278279 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -25,7 +25,7 @@ xfs_can_free_cowblocks(struct xfs_inode *ip) return true; } -extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, +int xfs_reflink_trim_around_shared(struct xfs_inode *ip, struct xfs_bmbt_irec *irec, bool *shared); int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap, bool *shared); @@ -62,4 +62,6 @@ extern int xfs_reflink_remap_blocks(struct xfs_inode *src, loff_t pos_in, extern int xfs_reflink_update_dest(struct xfs_inode *dest, xfs_off_t newlen, xfs_extlen_t cowextsize, unsigned int remap_flags); +bool xfs_reflink_supports_rextsize(struct xfs_mount *mp, unsigned int rextsize); + #endif /* __XFS_REFLINK_H */ diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 76b3c0ed3b4f..89decffe76c8 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -23,6 +23,7 @@ #include "xfs_ag.h" #include "xfs_btree.h" #include "xfs_trace.h" +#include "xfs_rtgroup.h" struct kmem_cache *xfs_rui_cache; struct kmem_cache *xfs_rud_cache; @@ -94,7 +95,9 @@ xfs_rui_item_format( ASSERT(atomic_read(&ruip->rui_next_extent) == ruip->rui_format.rui_nextents); - ruip->rui_format.rui_type = XFS_LI_RUI; + ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT); + + ruip->rui_format.rui_type = lip->li_type; ruip->rui_format.rui_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUI_FORMAT, &ruip->rui_format, @@ -137,12 +140,15 @@ xfs_rui_item_release( STATIC struct xfs_rui_log_item * xfs_rui_init( struct xfs_mount *mp, + unsigned short item_type, uint nextents) { struct xfs_rui_log_item *ruip; ASSERT(nextents > 0); + ASSERT(item_type == XFS_LI_RUI || item_type == XFS_LI_RUI_RT); + if (nextents > XFS_RUI_MAX_FAST_EXTENTS) ruip = kzalloc(xfs_rui_log_item_sizeof(nextents), GFP_KERNEL | __GFP_NOFAIL); @@ -150,7 +156,7 @@ xfs_rui_init( ruip = kmem_cache_zalloc(xfs_rui_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops); + xfs_log_item_init(mp, &ruip->rui_item, item_type, &xfs_rui_item_ops); ruip->rui_format.rui_nextents = nextents; ruip->rui_format.rui_id = (uintptr_t)(void *)ruip; atomic_set(&ruip->rui_next_extent, 0); @@ -189,7 +195,9 @@ xfs_rud_item_format( struct xfs_rud_log_item *rudp = RUD_ITEM(lip); struct xfs_log_iovec *vecp = NULL; - rudp->rud_format.rud_type = XFS_LI_RUD; + ASSERT(lip->li_type == XFS_LI_RUD || lip->li_type == XFS_LI_RUD_RT); + + rudp->rud_format.rud_type = lip->li_type; rudp->rud_format.rud_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUD_FORMAT, &rudp->rud_format, @@ -233,6 +241,14 @@ static inline struct xfs_rmap_intent *ri_entry(const struct list_head *e) return list_entry(e, struct xfs_rmap_intent, ri_list); } +static inline bool +xfs_rui_item_isrt(const struct xfs_log_item *lip) +{ + ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT); + + return lip->li_type == XFS_LI_RUI_RT; +} + /* Sort rmap intents by AG. */ static int xfs_rmap_update_diff_items( @@ -304,6 +320,28 @@ xfs_rmap_update_log_item( } } +static struct xfs_log_item * +__xfs_rmap_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort, + unsigned short item_type) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rui_log_item *ruip; + struct xfs_rmap_intent *ri; + + ASSERT(count > 0); + + ruip = xfs_rui_init(mp, item_type, count); + if (sort) + list_sort(mp, items, xfs_rmap_update_diff_items); + list_for_each_entry(ri, items, ri_list) + xfs_rmap_update_log_item(tp, ruip, ri); + return &ruip->rui_item; +} + static struct xfs_log_item * xfs_rmap_update_create_intent( struct xfs_trans *tp, @@ -311,17 +349,14 @@ xfs_rmap_update_create_intent( unsigned int count, bool sort) { - struct xfs_mount *mp = tp->t_mountp; - struct xfs_rui_log_item *ruip = xfs_rui_init(mp, count); - struct xfs_rmap_intent *ri; + return __xfs_rmap_update_create_intent(tp, items, count, sort, + XFS_LI_RUI); +} - ASSERT(count > 0); - - if (sort) - list_sort(mp, items, xfs_rmap_update_diff_items); - list_for_each_entry(ri, items, ri_list) - xfs_rmap_update_log_item(tp, ruip, ri); - return &ruip->rui_item; +static inline unsigned short +xfs_rud_type_from_rui(const struct xfs_rui_log_item *ruip) +{ + return xfs_rui_item_isrt(&ruip->rui_item) ? XFS_LI_RUD_RT : XFS_LI_RUD; } /* Get an RUD so we can process all the deferred rmap updates. */ @@ -335,8 +370,8 @@ xfs_rmap_update_create_done( struct xfs_rud_log_item *rudp; rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD, - &xfs_rud_item_ops); + xfs_log_item_init(tp->t_mountp, &rudp->rud_item, + xfs_rud_type_from_rui(ruip), &xfs_rud_item_ops); rudp->rud_ruip = ruip; rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id; @@ -351,11 +386,20 @@ xfs_rmap_defer_add( { struct xfs_mount *mp = tp->t_mountp; - trace_xfs_rmap_defer(mp, ri); - + /* + * Deferred rmap updates for the realtime and data sections must use + * separate transactions to finish deferred work because updates to + * realtime metadata files can lock AGFs to allocate btree blocks and + * we don't want that mixing with the AGF locks taken to finish data + * section updates. + */ ri->ri_group = xfs_group_intent_get(mp, ri->ri_bmap.br_startblock, - XG_TYPE_AG); - xfs_defer_add(tp, &ri->ri_list, &xfs_rmap_update_defer_type); + ri->ri_realtime ? XG_TYPE_RTG : XG_TYPE_AG); + + trace_xfs_rmap_defer(mp, ri); + xfs_defer_add(tp, &ri->ri_list, ri->ri_realtime ? + &xfs_rtrmap_update_defer_type : + &xfs_rmap_update_defer_type); } /* Cancel a deferred rmap update. */ @@ -415,6 +459,7 @@ xfs_rmap_update_abort_intent( static inline bool xfs_rui_validate_map( struct xfs_mount *mp, + bool isrt, struct xfs_map_extent *map) { if (!xfs_has_rmapbt(mp)) @@ -444,6 +489,9 @@ xfs_rui_validate_map( if (!xfs_verify_fileext(mp, map->me_startoff, map->me_len)) return false; + if (isrt) + return xfs_verify_rtbext(mp, map->me_startblock, map->me_len); + return xfs_verify_fsbext(mp, map->me_startblock, map->me_len); } @@ -451,6 +499,7 @@ static inline void xfs_rui_recover_work( struct xfs_mount *mp, struct xfs_defer_pending *dfp, + bool isrt, const struct xfs_map_extent *map) { struct xfs_rmap_intent *ri; @@ -495,7 +544,9 @@ xfs_rui_recover_work( ri->ri_bmap.br_blockcount = map->me_len; ri->ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ? XFS_EXT_UNWRITTEN : XFS_EXT_NORM; - ri->ri_group = xfs_group_intent_get(mp, map->me_startblock, XG_TYPE_AG); + ri->ri_group = xfs_group_intent_get(mp, map->me_startblock, + isrt ? XG_TYPE_RTG : XG_TYPE_AG); + ri->ri_realtime = isrt; xfs_defer_add_item(dfp, &ri->ri_list); } @@ -514,6 +565,7 @@ xfs_rmap_recover_work( struct xfs_rui_log_item *ruip = RUI_ITEM(lip); struct xfs_trans *tp; struct xfs_mount *mp = lip->li_log->l_mp; + bool isrt = xfs_rui_item_isrt(lip); int i; int error = 0; @@ -523,7 +575,7 @@ xfs_rmap_recover_work( * just toss the RUI. */ for (i = 0; i < ruip->rui_format.rui_nextents; i++) { - if (!xfs_rui_validate_map(mp, + if (!xfs_rui_validate_map(mp, isrt, &ruip->rui_format.rui_extents[i])) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &ruip->rui_format, @@ -531,7 +583,8 @@ xfs_rmap_recover_work( return -EFSCORRUPTED; } - xfs_rui_recover_work(mp, dfp, &ruip->rui_format.rui_extents[i]); + xfs_rui_recover_work(mp, dfp, isrt, + &ruip->rui_format.rui_extents[i]); } resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); @@ -566,10 +619,13 @@ xfs_rmap_relog_intent( struct xfs_map_extent *map; unsigned int count; + ASSERT(intent->li_type == XFS_LI_RUI || + intent->li_type == XFS_LI_RUI_RT); + count = RUI_ITEM(intent)->rui_format.rui_nextents; map = RUI_ITEM(intent)->rui_format.rui_extents; - ruip = xfs_rui_init(tp->t_mountp, count); + ruip = xfs_rui_init(tp->t_mountp, intent->li_type, count); memcpy(ruip->rui_format.rui_extents, map, count * sizeof(*map)); atomic_set(&ruip->rui_next_extent, count); @@ -589,6 +645,47 @@ const struct xfs_defer_op_type xfs_rmap_update_defer_type = { .relog_intent = xfs_rmap_relog_intent, }; +#ifdef CONFIG_XFS_RT +static struct xfs_log_item * +xfs_rtrmap_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_rmap_update_create_intent(tp, items, count, sort, + XFS_LI_RUI_RT); +} + +/* Clean up after calling xfs_rmap_finish_one. */ +STATIC void +xfs_rtrmap_finish_one_cleanup( + struct xfs_trans *tp, + struct xfs_btree_cur *rcur, + int error) +{ + if (rcur) + xfs_btree_del_cursor(rcur, error); +} + +const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = { + .name = "rtrmap", + .max_items = XFS_RUI_MAX_FAST_EXTENTS, + .create_intent = xfs_rtrmap_update_create_intent, + .abort_intent = xfs_rmap_update_abort_intent, + .create_done = xfs_rmap_update_create_done, + .finish_item = xfs_rmap_update_finish_item, + .finish_cleanup = xfs_rtrmap_finish_one_cleanup, + .cancel_item = xfs_rmap_update_cancel_item, + .recover_work = xfs_rmap_recover_work, + .relog_intent = xfs_rmap_relog_intent, +}; +#else +const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = { + .name = "rtrmap", +}; +#endif + STATIC bool xfs_rui_item_match( struct xfs_log_item *lip, @@ -654,7 +751,7 @@ xlog_recover_rui_commit_pass2( return -EFSCORRUPTED; } - ruip = xfs_rui_init(mp, rui_formatp->rui_nextents); + ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents); xfs_rui_copy_format(&ruip->rui_format, rui_formatp); atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents); @@ -668,6 +765,61 @@ const struct xlog_recover_item_ops xlog_rui_item_ops = { .commit_pass2 = xlog_recover_rui_commit_pass2, }; +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtrui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_mount *mp = log->l_mp; + struct xfs_rui_log_item *ruip; + struct xfs_rui_log_format *rui_formatp; + size_t len; + + rui_formatp = item->ri_buf[0].i_addr; + + if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents); + xfs_rui_copy_format(&ruip->rui_format, rui_formatp); + atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents); + + xlog_recover_intent_item(log, &ruip->rui_item, lsn, + &xfs_rtrmap_update_defer_type); + return 0; +} +#else +STATIC int +xlog_recover_rtrui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; +} +#endif + +const struct xlog_recover_item_ops xlog_rtrui_item_ops = { + .item_type = XFS_LI_RUI_RT, + .commit_pass2 = xlog_recover_rtrui_commit_pass2, +}; + /* * This routine is called when an RUD format structure is found in a committed * transaction in the log. Its purpose is to cancel the corresponding RUI if it @@ -699,3 +851,33 @@ const struct xlog_recover_item_ops xlog_rud_item_ops = { .item_type = XFS_LI_RUD, .commit_pass2 = xlog_recover_rud_commit_pass2, }; + +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtrud_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_rud_log_format *rud_formatp; + + rud_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + rud_formatp, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + xlog_recover_release_intent(log, XFS_LI_RUI_RT, + rud_formatp->rud_rui_id); + return 0; +} +#else +# define xlog_recover_rtrud_commit_pass2 xlog_recover_rtrui_commit_pass2 +#endif + +const struct xlog_recover_item_ops xlog_rtrud_item_ops = { + .item_type = XFS_LI_RUD_RT, + .commit_pass2 = xlog_recover_rtrud_commit_pass2, +}; diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index fcfa6e0eb3ad..d8e6d073d64d 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -22,6 +22,7 @@ #include "xfs_rtalloc.h" #include "xfs_sb.h" #include "xfs_rtbitmap.h" +#include "xfs_rtrmap_btree.h" #include "xfs_quota.h" #include "xfs_log_priv.h" #include "xfs_health.h" @@ -30,6 +31,8 @@ #include "xfs_rtgroup.h" #include "xfs_error.h" #include "xfs_trace.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_reflink.h" /* * Return whether there are any free extents in the size range given @@ -592,7 +595,7 @@ xfs_rtalloc_sumlevel( * specified. If we don't get maxlen then use prod to trim * the length, if given. The lengths are all in rtextents. */ -STATIC int +static int xfs_rtallocate_extent_size( struct xfs_rtalloc_args *args, xfs_rtxlen_t minlen, /* minimum length to allocate */ @@ -845,6 +848,13 @@ xfs_growfs_rt_init_rtsb( mp->m_rtsb_bp = rtsb_bp; error = xfs_bwrite(rtsb_bp); xfs_buf_unlock(rtsb_bp); + if (error) + return error; + + /* Initialize the rtrmap to reflect the rtsb. */ + if (rtg_rmap(args->rtg) != NULL) + error = xfs_rtrmapbt_init_rtsb(nargs->mp, args->rtg, args->tp); + return error; } @@ -856,8 +866,8 @@ xfs_growfs_rt_bmblock( xfs_fileoff_t bmbno) { struct xfs_mount *mp = rtg_mount(rtg); - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; - struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_inode *rsumip = rtg_summary(rtg); struct xfs_rtalloc_args args = { .mp = mp, .rtg = rtg, @@ -893,8 +903,9 @@ xfs_growfs_rt_bmblock( goto out_free; nargs.tp = args.tp; - xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP); - xfs_rtgroup_trans_join(args.tp, args.rtg, XFS_RTGLOCK_BITMAP); + xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP); + xfs_rtgroup_trans_join(args.tp, args.rtg, + XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP); /* * Update the bitmap inode's size ondisk and incore. We need to update @@ -980,9 +991,12 @@ xfs_growfs_rt_bmblock( goto out_free; /* - * Ensure the mount RT feature flag is now set. + * Ensure the mount RT feature flag is now set, and compute new + * maxlevels for rt btrees. */ mp->m_features |= XFS_FEAT_REALTIME; + xfs_rtrmapbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); kfree(nmp); return 0; @@ -1041,8 +1055,8 @@ xfs_growfs_rt_alloc_blocks( xfs_extlen_t *nrbmblocks) { struct xfs_mount *mp = rtg_mount(rtg); - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; - struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_inode *rsumip = rtg_summary(rtg); xfs_extlen_t orbmblocks = 0; xfs_extlen_t orsumblocks = 0; struct xfs_mount *nmp; @@ -1150,29 +1164,38 @@ out_rele: return error; } -static int +int xfs_growfs_check_rtgeom( const struct xfs_mount *mp, + xfs_rfsblock_t dblocks, xfs_rfsblock_t rblocks, xfs_extlen_t rextsize) { + xfs_extlen_t min_logfsbs; struct xfs_mount *nmp; - int error = 0; nmp = xfs_growfs_rt_alloc_fake_mount(mp, rblocks, rextsize); if (!nmp) return -ENOMEM; + nmp->m_sb.sb_dblocks = dblocks; + + xfs_rtrmapbt_compute_maxlevels(nmp); + xfs_rtrefcountbt_compute_maxlevels(nmp); + xfs_trans_resv_calc(nmp, M_RES(nmp)); /* * New summary size can't be more than half the size of the log. This * prevents us from getting a log overflow, since we'll log basically * the whole summary file at once. */ - if (nmp->m_rsumblocks > (mp->m_sb.sb_logblocks >> 1)) - error = -EINVAL; + min_logfsbs = min_t(xfs_extlen_t, xfs_log_calc_minimum_size(nmp), + nmp->m_rsumblocks * 2); kfree(nmp); - return error; + + if (min_logfsbs > mp->m_sb.sb_logblocks) + return -EINVAL; + return 0; } /* @@ -1263,11 +1286,17 @@ xfs_growfs_rt( XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE) goto out_unlock; - /* Unsupported realtime features. */ + /* Check for features supported only on rtgroups filesystems. */ error = -EOPNOTSUPP; - if (xfs_has_quota(mp) && !xfs_has_rtgroups(mp)) - goto out_unlock; - if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp)) + if (!xfs_has_rtgroups(mp)) { + if (xfs_has_rmapbt(mp)) + goto out_unlock; + if (xfs_has_quota(mp)) + goto out_unlock; + if (xfs_has_reflink(mp)) + goto out_unlock; + } else if (xfs_has_reflink(mp) && + !xfs_reflink_supports_rextsize(mp, in->extsize)) goto out_unlock; error = xfs_sb_validate_fsb_count(&mp->m_sb, in->newblocks); @@ -1291,7 +1320,8 @@ xfs_growfs_rt( goto out_unlock; /* Make sure the new fs size won't cause problems with the log. */ - error = xfs_growfs_check_rtgeom(mp, in->newblocks, in->extsize); + error = xfs_growfs_check_rtgeom(mp, mp->m_sb.sb_dblocks, in->newblocks, + in->extsize); if (error) goto out_unlock; @@ -1344,6 +1374,12 @@ xfs_growfs_rt( if (!error) error = error2; + + /* Reset the rt metadata btree space reservations. */ + xfs_rt_resv_free(mp); + error2 = xfs_rt_resv_init(mp); + if (error2 && error2 != -ENOSPC) + error = error2; } out_unlock: @@ -1487,6 +1523,46 @@ xfs_rtalloc_reinit_frextents( return 0; } +/* Free space reservations for rt metadata inodes. */ +void +xfs_rt_resv_free( + struct xfs_mount *mp) +{ + struct xfs_rtgroup *rtg = NULL; + unsigned int i; + + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + for (i = 0; i < XFS_RTGI_MAX; i++) + xfs_metafile_resv_free(rtg->rtg_inodes[i]); + } +} + +/* Reserve space for rt metadata inodes' space expansion. */ +int +xfs_rt_resv_init( + struct xfs_mount *mp) +{ + struct xfs_rtgroup *rtg = NULL; + xfs_filblks_t ask; + int error = 0; + + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + int err2; + + ask = xfs_rtrmapbt_calc_reserves(mp); + err2 = xfs_metafile_resv_init(rtg_rmap(rtg), ask); + if (err2 && !error) + error = err2; + + ask = xfs_rtrefcountbt_calc_reserves(mp); + err2 = xfs_metafile_resv_init(rtg_refcount(rtg), ask); + if (err2 && !error) + error = err2; + } + + return error; +} + /* * Read in the bmbt of an rt metadata inode so that we never have to load them * at runtime. This enables the use of shared ILOCKs for rtbitmap scans. Use @@ -1601,7 +1677,7 @@ xfs_rtpick_extent( xfs_rtxlen_t len) /* allocation length (rtextents) */ { struct xfs_mount *mp = rtg_mount(rtg); - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); xfs_rtxnum_t b = 0; /* result rtext */ int log2; /* log of sequence number */ uint64_t resid; /* residual after log removed */ @@ -1885,7 +1961,7 @@ out_unlock: goto out_release; } -static int +int xfs_rtallocate_rtgs( struct xfs_trans *tp, xfs_fsblock_t bno_hint, @@ -1950,7 +2026,10 @@ xfs_rtallocate_align( if (*noalign) { align = mp->m_sb.sb_rextsize; } else { - align = xfs_get_extsz_hint(ap->ip); + if (ap->flags & XFS_BMAPI_COWFORK) + align = xfs_get_cowextsz_hint(ap->ip); + else + align = xfs_get_extsz_hint(ap->ip); if (!align) align = 1; if (align == mp->m_sb.sb_rextsize) diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h index 8e2a07b8174b..0d95b29092c9 100644 --- a/fs/xfs/xfs_rtalloc.h +++ b/fs/xfs/xfs_rtalloc.h @@ -34,6 +34,9 @@ int /* error */ xfs_rtmount_inodes( struct xfs_mount *mp); /* file system mount structure */ +void xfs_rt_resv_free(struct xfs_mount *mp); +int xfs_rt_resv_init(struct xfs_mount *mp); + /* * Grow the realtime area of the filesystem. */ @@ -43,6 +46,8 @@ xfs_growfs_rt( xfs_growfs_rt_t *in); /* user supplied growfs struct */ int xfs_rtalloc_reinit_frextents(struct xfs_mount *mp); +int xfs_growfs_check_rtgeom(const struct xfs_mount *mp, xfs_rfsblock_t dblocks, + xfs_rfsblock_t rblocks, xfs_agblock_t rextsize); #else # define xfs_growfs_rt(mp,in) (-ENOSYS) # define xfs_rtalloc_reinit_frextents(m) (0) @@ -60,6 +65,21 @@ xfs_rtmount_init( } # define xfs_rtmount_inodes(m) (((mp)->m_sb.sb_rblocks == 0)? 0 : (-ENOSYS)) # define xfs_rtunmount_inodes(m) +# define xfs_rt_resv_free(mp) ((void)0) +# define xfs_rt_resv_init(mp) (0) + +static inline int +xfs_growfs_check_rtgeom(const struct xfs_mount *mp, + xfs_rfsblock_t dblocks, xfs_rfsblock_t rblocks, + xfs_extlen_t rextsize) +{ + return 0; +} #endif /* CONFIG_XFS_RT */ +int xfs_rtallocate_rtgs(struct xfs_trans *tp, xfs_fsblock_t bno_hint, + xfs_rtxlen_t minlen, xfs_rtxlen_t maxlen, xfs_rtxlen_t prod, + bool wasdel, bool initial_user_data, xfs_rtblock_t *bno, + xfs_extlen_t *blen); + #endif /* __XFS_RTALLOC_H__ */ diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index ffb52725c2a8..35c7fb3ba324 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -52,7 +52,10 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) { "rmapbt", xfsstats_offset(xs_refcbt_2) }, { "refcntbt", xfsstats_offset(xs_rmap_mem_2) }, { "rmapbt_mem", xfsstats_offset(xs_rcbag_2) }, - { "rcbagbt", xfsstats_offset(xs_qm_dqreclaims)}, + { "rcbagbt", xfsstats_offset(xs_rtrmap_2) }, + { "rtrmapbt", xfsstats_offset(xs_rtrmap_mem_2)}, + { "rtrmapbt_mem", xfsstats_offset(xs_rtrefcbt_2) }, + { "rtrefcntbt", xfsstats_offset(xs_qm_dqreclaims)}, /* we print both series of quota information together */ { "qm", xfsstats_offset(xs_xstrat_bytes)}, }; diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h index a61fb56ed2e6..15ba1abcf253 100644 --- a/fs/xfs/xfs_stats.h +++ b/fs/xfs/xfs_stats.h @@ -127,6 +127,9 @@ struct __xfsstats { uint32_t xs_refcbt_2[__XBTS_MAX]; uint32_t xs_rmap_mem_2[__XBTS_MAX]; uint32_t xs_rcbag_2[__XBTS_MAX]; + uint32_t xs_rtrmap_2[__XBTS_MAX]; + uint32_t xs_rtrmap_mem_2[__XBTS_MAX]; + uint32_t xs_rtrefcbt_2[__XBTS_MAX]; uint32_t xs_qm_dqreclaims; uint32_t xs_qm_dqreclaim_misses; uint32_t xs_qm_dquot_dups; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 394fdf3bb535..d92d7a07ea89 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -819,20 +819,76 @@ xfs_fs_sync_fs( return 0; } +static xfs_extlen_t +xfs_internal_log_size( + struct xfs_mount *mp) +{ + if (!mp->m_sb.sb_logstart) + return 0; + return mp->m_sb.sb_logblocks; +} + +static void +xfs_statfs_data( + struct xfs_mount *mp, + struct kstatfs *st) +{ + int64_t fdblocks = + percpu_counter_sum(&mp->m_fdblocks); + + /* make sure st->f_bfree does not underflow */ + st->f_bfree = max(0LL, fdblocks - xfs_fdblocks_unavailable(mp)); + /* + * sb_dblocks can change during growfs, but nothing cares about reporting + * the old or new value during growfs. + */ + st->f_blocks = mp->m_sb.sb_dblocks - xfs_internal_log_size(mp); +} + +/* + * When stat(v)fs is called on a file with the realtime bit set or a directory + * with the rtinherit bit, report freespace information for the RT device + * instead of the main data device. + */ +static void +xfs_statfs_rt( + struct xfs_mount *mp, + struct kstatfs *st) +{ + st->f_bfree = xfs_rtbxlen_to_blen(mp, + percpu_counter_sum_positive(&mp->m_frextents)); + st->f_blocks = mp->m_sb.sb_rblocks; +} + +static void +xfs_statfs_inodes( + struct xfs_mount *mp, + struct kstatfs *st) +{ + uint64_t icount = percpu_counter_sum(&mp->m_icount); + uint64_t ifree = percpu_counter_sum(&mp->m_ifree); + uint64_t fakeinos = XFS_FSB_TO_INO(mp, st->f_bfree); + + st->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); + if (M_IGEO(mp)->maxicount) + st->f_files = min_t(typeof(st->f_files), st->f_files, + M_IGEO(mp)->maxicount); + + /* If sb_icount overshot maxicount, report actual allocation */ + st->f_files = max_t(typeof(st->f_files), st->f_files, + mp->m_sb.sb_icount); + + /* Make sure st->f_ffree does not underflow */ + st->f_ffree = max_t(int64_t, 0, st->f_files - (icount - ifree)); +} + STATIC int xfs_fs_statfs( struct dentry *dentry, - struct kstatfs *statp) + struct kstatfs *st) { struct xfs_mount *mp = XFS_M(dentry->d_sb); - xfs_sb_t *sbp = &mp->m_sb; struct xfs_inode *ip = XFS_I(d_inode(dentry)); - uint64_t fakeinos, id; - uint64_t icount; - uint64_t ifree; - uint64_t fdblocks; - xfs_extlen_t lsize; - int64_t ffree; /* * Expedite background inodegc but don't wait. We do not want to block @@ -840,58 +896,28 @@ xfs_fs_statfs( */ xfs_inodegc_push(mp); - statp->f_type = XFS_SUPER_MAGIC; - statp->f_namelen = MAXNAMELEN - 1; + st->f_type = XFS_SUPER_MAGIC; + st->f_namelen = MAXNAMELEN - 1; + st->f_bsize = mp->m_sb.sb_blocksize; + st->f_fsid = u64_to_fsid(huge_encode_dev(mp->m_ddev_targp->bt_dev)); - id = huge_encode_dev(mp->m_ddev_targp->bt_dev); - statp->f_fsid = u64_to_fsid(id); - - icount = percpu_counter_sum(&mp->m_icount); - ifree = percpu_counter_sum(&mp->m_ifree); - fdblocks = percpu_counter_sum(&mp->m_fdblocks); - - spin_lock(&mp->m_sb_lock); - statp->f_bsize = sbp->sb_blocksize; - lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0; - statp->f_blocks = sbp->sb_dblocks - lsize; - spin_unlock(&mp->m_sb_lock); - - /* make sure statp->f_bfree does not underflow */ - statp->f_bfree = max_t(int64_t, 0, - fdblocks - xfs_fdblocks_unavailable(mp)); - statp->f_bavail = statp->f_bfree; - - fakeinos = XFS_FSB_TO_INO(mp, statp->f_bfree); - statp->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); - if (M_IGEO(mp)->maxicount) - statp->f_files = min_t(typeof(statp->f_files), - statp->f_files, - M_IGEO(mp)->maxicount); - - /* If sb_icount overshot maxicount, report actual allocation */ - statp->f_files = max_t(typeof(statp->f_files), - statp->f_files, - sbp->sb_icount); - - /* make sure statp->f_ffree does not underflow */ - ffree = statp->f_files - (icount - ifree); - statp->f_ffree = max_t(int64_t, ffree, 0); + xfs_statfs_data(mp, st); + xfs_statfs_inodes(mp, st); if (XFS_IS_REALTIME_MOUNT(mp) && - (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) { - s64 freertx; - - statp->f_blocks = sbp->sb_rblocks; - freertx = percpu_counter_sum_positive(&mp->m_frextents); - statp->f_bavail = statp->f_bfree = - xfs_rtbxlen_to_blen(mp, freertx); - } + (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) + xfs_statfs_rt(mp, st); if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) && ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) == (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD)) - xfs_qm_statvfs(ip, statp); + xfs_qm_statvfs(ip, st); + /* + * XFS does not distinguish between blocks available to privileged and + * unprivileged users. + */ + st->f_bavail = st->f_bfree; return 0; } @@ -1730,7 +1756,7 @@ xfs_fs_fill_super( sb->s_time_max = XFS_LEGACY_TIME_MAX; } trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max); - sb->s_iflags |= SB_I_CGROUPWB; + sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM; set_posix_acl_flag(sb); @@ -1754,9 +1780,11 @@ xfs_fs_fill_super( xfs_warn_experimental(mp, XFS_EXPERIMENTAL_METADIR); if (xfs_has_reflink(mp)) { - if (mp->m_sb.sb_rblocks) { + if (xfs_has_realtime(mp) && + !xfs_reflink_supports_rextsize(mp, mp->m_sb.sb_rextsize)) { xfs_alert(mp, - "reflink not compatible with realtime device!"); + "reflink not compatible with realtime extent size %u!", + mp->m_sb.sb_rextsize); error = -EINVAL; goto out_filestream_unmount; } @@ -1767,12 +1795,6 @@ xfs_fs_fill_super( } } - if (xfs_has_rmapbt(mp) && mp->m_sb.sb_rblocks) { - xfs_alert(mp, - "reverse mapping btree not compatible with realtime device!"); - error = -EINVAL; - goto out_filestream_unmount; - } if (xfs_has_exchange_range(mp)) xfs_warn_experimental(mp, XFS_EXPERIMENTAL_EXCHRANGE); diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 302e6e5d6c7e..c0e85c1e42f2 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -92,7 +92,6 @@ extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *, extern const struct export_operations xfs_export_operations; extern const struct quotactl_ops xfs_quotactl_operations; -extern const struct dax_holder_operations xfs_dax_holder_operations; extern void xfs_reinit_percpu_counters(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index c84df23b494d..751dc74a3067 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -66,7 +66,7 @@ xfs_deprecated_dointvec_minmax( return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); } -static struct ctl_table xfs_table[] = { +static const struct ctl_table xfs_table[] = { { .procname = "irix_sgid_inherit", .data = &xfs_params.sgid_inherit.val, diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 7b16cdd72e9d..b29462363b81 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -14,11 +14,15 @@ * ino: filesystem inode number * * agbno: per-AG block number in fs blocks + * rgbno: per-rtgroup block number in fs blocks * startblock: physical block number for file mappings. This is either a * segmented fsblock for data device mappings, or a rfsblock * for realtime device mappings * fsbcount: number of blocks in an extent, in fs blocks * + * gbno: generic allocation group block number. This is an agbno for + * space in a per-AG or a rgbno for space in a realtime group. + * * daddr: physical block number in 512b blocks * bbcount: number of blocks in a physical extent, in 512b blocks * @@ -494,7 +498,7 @@ DECLARE_EVENT_CLASS(xfs_buf_class, __entry->dev = bp->b_target->bt_dev; __entry->bno = xfs_buf_daddr(bp); __entry->nblks = bp->b_length; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; @@ -565,7 +569,7 @@ DECLARE_EVENT_CLASS(xfs_buf_flags_class, __entry->bno = xfs_buf_daddr(bp); __entry->length = bp->b_length; __entry->flags = flags; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->caller_ip = caller_ip; @@ -608,7 +612,7 @@ TRACE_EVENT(xfs_buf_ioerror, __entry->dev = bp->b_target->bt_dev; __entry->bno = xfs_buf_daddr(bp); __entry->length = bp->b_length; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->error = error; @@ -652,7 +656,7 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class, __entry->buf_bno = xfs_buf_daddr(bip->bli_buf); __entry->buf_len = bip->bli_buf->b_length; __entry->buf_flags = bip->bli_buf->b_flags; - __entry->buf_hold = atomic_read(&bip->bli_buf->b_hold); + __entry->buf_hold = bip->bli_buf->b_hold; __entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count); __entry->buf_lockval = bip->bli_buf->b_sema.count; __entry->li_flags = bip->bli_item.li_flags; @@ -2295,6 +2299,7 @@ TRACE_DEFINE_ENUM(XFS_DINODE_FMT_LOCAL); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_EXTENTS); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_BTREE); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_UUID); +TRACE_DEFINE_ENUM(XFS_DINODE_FMT_META_BTREE); DECLARE_EVENT_CLASS(xfs_swap_extent_class, TP_PROTO(struct xfs_inode *ip, int which), @@ -2918,13 +2923,14 @@ DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_finish_item); /* rmap tracepoints */ DECLARE_EVENT_CLASS(xfs_rmap_class, TP_PROTO(struct xfs_btree_cur *cur, - xfs_agblock_t agbno, xfs_extlen_t len, bool unwritten, + xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten, const struct xfs_owner_info *oinfo), - TP_ARGS(cur, agbno, len, unwritten, oinfo), + TP_ARGS(cur, gbno, len, unwritten, oinfo), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) __field(uint64_t, owner) __field(uint64_t, offset) @@ -2932,8 +2938,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->len = len; __entry->owner = oinfo->oi_owner; __entry->offset = oinfo->oi_offset; @@ -2941,10 +2948,11 @@ DECLARE_EVENT_CLASS(xfs_rmap_class, if (unwritten) __entry->flags |= XFS_RMAP_UNWRITTEN; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%lx", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%lx", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len, __entry->owner, __entry->offset, @@ -2953,9 +2961,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_class, #define DEFINE_RMAP_EVENT(name) \ DEFINE_EVENT(xfs_rmap_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, \ - xfs_agblock_t agbno, xfs_extlen_t len, bool unwritten, \ + xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten, \ const struct xfs_owner_info *oinfo), \ - TP_ARGS(cur, agbno, len, unwritten, oinfo)) + TP_ARGS(cur, gbno, len, unwritten, oinfo)) /* btree cursor error/%ip tracepoint class */ DECLARE_EVENT_CLASS(xfs_btree_error_class, @@ -3018,47 +3026,36 @@ TRACE_EVENT(xfs_rmap_convert_state, TP_ARGS(cur, state, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_ino_t, ino) __field(int, state) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; - switch (cur->bc_ops->type) { - case XFS_BTREE_TYPE_INODE: - __entry->agno = 0; - __entry->ino = cur->bc_ino.ip->i_ino; - break; - case XFS_BTREE_TYPE_AG: - __entry->agno = cur->bc_group->xg_gno; - __entry->ino = 0; - break; - case XFS_BTREE_TYPE_MEM: - __entry->agno = 0; - __entry->ino = 0; - break; - } + __entry->type = cur->bc_group->xg_type; + __entry->agno = cur->bc_group->xg_gno; __entry->state = state; __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d agno 0x%x ino 0x%llx state %d caller %pS", + TP_printk("dev %d:%d %sno 0x%x state %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->ino, __entry->state, (char *)__entry->caller_ip) ); DECLARE_EVENT_CLASS(xfs_rmapbt_class, TP_PROTO(struct xfs_btree_cur *cur, - xfs_agblock_t agbno, xfs_extlen_t len, + xfs_agblock_t gbno, xfs_extlen_t len, uint64_t owner, uint64_t offset, unsigned int flags), - TP_ARGS(cur, agbno, len, owner, offset, flags), + TP_ARGS(cur, gbno, len, owner, offset, flags), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) __field(uint64_t, owner) __field(uint64_t, offset) @@ -3066,17 +3063,19 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->len = len; __entry->owner = owner; __entry->offset = offset; __entry->flags = flags; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len, __entry->owner, __entry->offset, @@ -3085,9 +3084,9 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class, #define DEFINE_RMAPBT_EVENT(name) \ DEFINE_EVENT(xfs_rmapbt_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, \ - xfs_agblock_t agbno, xfs_extlen_t len, \ + xfs_agblock_t gbno, xfs_extlen_t len, \ uint64_t owner, uint64_t offset, unsigned int flags), \ - TP_ARGS(cur, agbno, len, owner, offset, flags)) + TP_ARGS(cur, gbno, len, owner, offset, flags)) TRACE_DEFINE_ENUM(XFS_RMAP_MAP); TRACE_DEFINE_ENUM(XFS_RMAP_MAP_SHARED); @@ -3104,8 +3103,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long long, owner) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(int, whichfork) __field(xfs_fileoff_t, l_loff) __field(xfs_filblks_t, l_len) @@ -3114,9 +3114,11 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; - __entry->agno = XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock); - __entry->agbno = XFS_FSB_TO_AGBNO(mp, - ri->ri_bmap.br_startblock); + __entry->type = ri->ri_group->xg_type; + __entry->agno = ri->ri_group->xg_gno; + __entry->gbno = xfs_fsb_to_gbno(mp, + ri->ri_bmap.br_startblock, + ri->ri_group->xg_type); __entry->owner = ri->ri_owner; __entry->whichfork = ri->ri_whichfork; __entry->l_loff = ri->ri_bmap.br_startoff; @@ -3124,11 +3126,12 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, __entry->l_state = ri->ri_bmap.br_state; __entry->op = ri->ri_type; ), - TP_printk("dev %d:%d op %s agno 0x%x agbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d", + TP_printk("dev %d:%d op %s %sno 0x%x gbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->op, XFS_RMAP_INTENT_STRINGS), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->owner, __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS), __entry->l_loff, @@ -3302,56 +3305,62 @@ TRACE_EVENT(xfs_ag_resv_init_error, /* refcount tracepoint classes */ DECLARE_EVENT_CLASS(xfs_refcount_class, - TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t agbno, + TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_extlen_t len), - TP_ARGS(cur, agbno, len), + TP_ARGS(cur, gbno, len), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->len = len; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len) ); #define DEFINE_REFCOUNT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_class, name, \ - TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t agbno, \ + TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, \ xfs_extlen_t len), \ - TP_ARGS(cur, agbno, len)) + TP_ARGS(cur, gbno, len)) TRACE_DEFINE_ENUM(XFS_LOOKUP_EQi); TRACE_DEFINE_ENUM(XFS_LOOKUP_LEi); TRACE_DEFINE_ENUM(XFS_LOOKUP_GEi); TRACE_EVENT(xfs_refcount_lookup, - TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t agbno, + TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_lookup_t dir), - TP_ARGS(cur, agbno, dir), + TP_ARGS(cur, gbno, dir), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_lookup_t, dir) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->dir = dir; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x cmp %s(%d)", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x cmp %s(%d)", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __print_symbolic(__entry->dir, XFS_AG_BTREE_CMP_FORMAT_STR), __entry->dir) ) @@ -3362,6 +3371,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, TP_ARGS(cur, irec), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) @@ -3370,14 +3380,16 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, @@ -3393,49 +3405,53 @@ DEFINE_EVENT(xfs_refcount_extent_class, name, \ /* single-rcext and an agbno tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, - xfs_agblock_t agbno), - TP_ARGS(cur, irec, agbno), + xfs_agblock_t gbno), + TP_ARGS(cur, irec, gbno), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; - __entry->agbno = agbno; + __entry->gbno = gbno; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u @ gbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount, - __entry->agbno) + __entry->gbno) ) #define DEFINE_REFCOUNT_EXTENT_AT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_extent_at_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, \ - xfs_agblock_t agbno), \ - TP_ARGS(cur, irec, agbno)) + xfs_agblock_t gbno), \ + TP_ARGS(cur, irec, gbno)) /* double-rcext tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, - struct xfs_refcount_irec *i2), + struct xfs_refcount_irec *i2), TP_ARGS(cur, i1, i2), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) @@ -3448,6 +3464,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; @@ -3458,9 +3475,10 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, @@ -3481,10 +3499,11 @@ DEFINE_EVENT(xfs_refcount_double_extent_class, name, \ /* double-rcext and an agbno tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, - struct xfs_refcount_irec *i2, xfs_agblock_t agbno), - TP_ARGS(cur, i1, i2, agbno), + struct xfs_refcount_irec *i2, xfs_agblock_t gbno), + TP_ARGS(cur, i1, i2, gbno), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) @@ -3494,10 +3513,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; @@ -3507,11 +3527,12 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; - __entry->agbno = agbno; + __entry->gbno = gbno; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u @ gbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, @@ -3521,14 +3542,14 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount, - __entry->agbno) + __entry->gbno) ) #define DEFINE_REFCOUNT_DOUBLE_EXTENT_AT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_double_extent_at_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, \ - struct xfs_refcount_irec *i2, xfs_agblock_t agbno), \ - TP_ARGS(cur, i1, i2, agbno)) + struct xfs_refcount_irec *i2, xfs_agblock_t gbno), \ + TP_ARGS(cur, i1, i2, gbno)) /* triple-rcext tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, @@ -3537,6 +3558,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, TP_ARGS(cur, i1, i2, i3), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) @@ -3553,6 +3575,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; @@ -3567,10 +3590,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, __entry->i3_blockcount = i3->rc_blockcount; __entry->i3_refcount = i3->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, @@ -3638,23 +3662,27 @@ DECLARE_EVENT_CLASS(xfs_refcount_deferred_class, TP_ARGS(mp, refc), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(int, op) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; - __entry->agno = XFS_FSB_TO_AGNO(mp, refc->ri_startblock); + __entry->type = refc->ri_group->xg_type; + __entry->agno = refc->ri_group->xg_gno; __entry->op = refc->ri_type; - __entry->agbno = XFS_FSB_TO_AGBNO(mp, refc->ri_startblock); + __entry->gbno = xfs_fsb_to_gbno(mp, refc->ri_startblock, + refc->ri_group->xg_type); __entry->len = refc->ri_blockcount; ), - TP_printk("dev %d:%d op %s agno 0x%x agbno 0x%x fsbcount 0x%x", + TP_printk("dev %d:%d op %s %sno 0x%x gbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->op, XFS_REFCOUNT_INTENT_STRINGS), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len) ); #define DEFINE_REFCOUNT_DEFERRED_EVENT(name) \ @@ -3993,7 +4021,7 @@ TRACE_EVENT(xfs_fsmap_mapping, __entry->offset = frec->offset; __entry->flags = frec->rm_flags; ), - TP_printk("dev %d:%d keydev %d:%d agno 0x%x rmapbno 0x%x start_daddr 0x%llx len_daddr 0x%llx owner 0x%llx fileoff 0x%llx flags 0x%x", + TP_printk("dev %d:%d keydev %d:%d agno 0x%x gbno 0x%x start_daddr 0x%llx len_daddr 0x%llx owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->agno, @@ -4950,7 +4978,7 @@ DECLARE_EVENT_CLASS(xfbtree_buf_class, __entry->xfino = file_inode(xfbt->target->bt_file)->i_ino; __entry->bno = xfs_buf_daddr(bp); __entry->nblks = bp->b_length; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; @@ -5574,6 +5602,72 @@ DEFINE_EVENT(xfs_metadir_class, name, \ TP_ARGS(dp, name, ino)) DEFINE_METADIR_EVENT(xfs_metadir_lookup); +/* metadata inode space reservations */ + +DECLARE_EVENT_CLASS(xfs_metafile_resv_class, + TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len), + TP_ARGS(ip, len), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_ino_t, ino) + __field(unsigned long long, freeblks) + __field(unsigned long long, reserved) + __field(unsigned long long, asked) + __field(unsigned long long, used) + __field(unsigned long long, len) + ), + TP_fast_assign( + struct xfs_mount *mp = ip->i_mount; + + __entry->dev = mp->m_super->s_dev; + __entry->ino = ip->i_ino; + __entry->freeblks = percpu_counter_sum(&mp->m_fdblocks); + __entry->reserved = ip->i_delayed_blks; + __entry->asked = ip->i_meta_resv_asked; + __entry->used = ip->i_nblocks; + __entry->len = len; + ), + TP_printk("dev %d:%d ino 0x%llx freeblks %llu resv %llu ask %llu used %llu len %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->freeblks, + __entry->reserved, + __entry->asked, + __entry->used, + __entry->len) +) +#define DEFINE_METAFILE_RESV_EVENT(name) \ +DEFINE_EVENT(xfs_metafile_resv_class, name, \ + TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len), \ + TP_ARGS(ip, len)) +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_alloc_space); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free_space); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_critical); +DEFINE_INODE_ERROR_EVENT(xfs_metafile_resv_init_error); + +#ifdef CONFIG_XFS_RT +TRACE_EVENT(xfs_growfs_check_rtgeom, + TP_PROTO(const struct xfs_mount *mp, unsigned int min_logfsbs), + TP_ARGS(mp, min_logfsbs), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, logblocks) + __field(unsigned int, min_logfsbs) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->logblocks = mp->m_sb.sb_logblocks; + __entry->min_logfsbs = min_logfsbs; + ), + TP_printk("dev %d:%d logblocks %u min_logfsbs %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->logblocks, + __entry->min_logfsbs) +); +#endif /* CONFIG_XFS_RT */ + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 4cd25717c9d1..c6657072361a 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -100,7 +100,6 @@ xfs_trans_dup( /* * Initialize the new transaction structure. */ - ntp->t_magic = XFS_TRANS_HEADER_MAGIC; ntp->t_mountp = tp->t_mountp; INIT_LIST_HEAD(&ntp->t_items); INIT_LIST_HEAD(&ntp->t_busy); @@ -275,7 +274,6 @@ retry: ASSERT(!(flags & XFS_TRANS_RES_FDBLKS) || xfs_has_lazysbcount(mp)); - tp->t_magic = XFS_TRANS_HEADER_MAGIC; tp->t_flags = flags; tp->t_mountp = mp; INIT_LIST_HEAD(&tp->t_items); @@ -1266,6 +1264,9 @@ retry: xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + if (xfs_is_metadir_inode(ip)) + goto out; + error = xfs_qm_dqattach_locked(ip, false); if (error) { /* Caller should have allocated the dquots! */ @@ -1334,6 +1335,7 @@ retry: goto out_cancel; } +out: *tpp = tp; return 0; diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 71c2e82e4dad..2b366851e9a4 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -122,7 +122,6 @@ void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item, * This is the structure maintained for every active transaction. */ typedef struct xfs_trans { - unsigned int t_magic; /* magic number */ unsigned int t_log_res; /* amt of log space resvd */ unsigned int t_log_count; /* count for perm log res */ unsigned int t_blk_res; /* # of blocks resvd */ diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index f56d62dced97..0fcb1828e598 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -359,13 +359,8 @@ xfsaild_resubmit_item( } /* protected by ail_lock */ - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { - if (bp->b_flags & (_XBF_INODES | _XBF_DQUOTS)) - clear_bit(XFS_LI_FAILED, &lip->li_flags); - else - xfs_clear_li_failed(lip); - } - + list_for_each_entry(lip, &bp->b_li_list, li_bio_list) + clear_bit(XFS_LI_FAILED, &lip->li_flags); xfs_buf_unlock(bp); return XFS_ITEM_SUCCESS; } diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 8e886ecfd69a..53af546c0b23 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -659,7 +659,7 @@ xfs_trans_inode_buf( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_INODE_BUF; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF); } @@ -684,7 +684,7 @@ xfs_trans_stale_inode_buf( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_STALE_INODE; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF); } @@ -709,7 +709,7 @@ xfs_trans_inode_alloc_buf( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF); } @@ -820,6 +820,6 @@ xfs_trans_dquot_buf( break; } - bp->b_flags |= _XBF_DQUOTS; + bp->b_iodone = xfs_buf_dquot_iodone; xfs_trans_buf_set_type(tp, bp, type); } diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 713b6d243e56..765456bf3428 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -156,7 +156,8 @@ xfs_trans_mod_ino_dquot( unsigned int field, int64_t delta) { - ASSERT(!xfs_is_metadir_inode(ip) || XFS_IS_DQDETACHED(ip)); + if (xfs_is_metadir_inode(ip)) + return; xfs_trans_mod_dquot(tp, dqp, field, delta); @@ -246,11 +247,10 @@ xfs_trans_mod_dquot_byino( xfs_mount_t *mp = tp->t_mountp; if (!XFS_IS_QUOTA_ON(mp) || - xfs_is_quota_inode(&mp->m_sb, ip->i_ino)) + xfs_is_quota_inode(&mp->m_sb, ip->i_ino) || + xfs_is_metadir_inode(ip)) return; - ASSERT(!xfs_is_metadir_inode(ip) || XFS_IS_DQDETACHED(ip)); - if (XFS_IS_UQUOTA_ON(mp) && ip->i_udquot) xfs_trans_mod_ino_dquot(tp, ip, ip->i_udquot, field, delta); if (XFS_IS_GQUOTA_ON(mp) && ip->i_gdquot) diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index b2e377b7f337..aad1a95e6863 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -43,9 +43,6 @@ acpi_status acpi_evaluate_ost(acpi_handle handle, u32 source_event, u32 status_code, struct acpi_buffer *status_buf); -acpi_status -acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld); - bool acpi_has_method(acpi_handle handle, char *name); acpi_status acpi_execute_simple_method(acpi_handle handle, char *method, u64 arg); @@ -60,6 +57,9 @@ bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs); union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4); #ifdef CONFIG_ACPI +bool +acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld); + static inline union acpi_object * acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4, @@ -1003,6 +1003,23 @@ static inline int unregister_acpi_bus_type(void *bus) { return 0; } static inline int acpi_wait_for_acpi_ipmi(void) { return 0; } +static inline const char *acpi_device_hid(struct acpi_device *device) +{ + return ""; +} + +static inline bool +acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld) +{ + return false; +} + +#define for_each_acpi_consumer_dev(supplier, consumer) \ + for (consumer = NULL; false && (supplier);) + +#define for_each_acpi_dev_match(adev, hid, uid, hrv) \ + for (adev = NULL; false && (hid) && (uid) && (hrv); ) + #endif /* CONFIG_ACPI */ #endif /*__ACPI_BUS_H__*/ diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h index b5f594754a9e..99b960bd473c 100644 --- a/include/acpi/acpi_numa.h +++ b/include/acpi/acpi_numa.h @@ -17,11 +17,16 @@ extern int node_to_pxm(int); extern int acpi_map_pxm_to_node(int); extern unsigned char acpi_srat_revision; extern void disable_srat(void); +extern int fix_pxm_node_maps(int max_nid); extern void bad_srat(void); extern int srat_disabled(void); #else /* CONFIG_ACPI_NUMA */ +static inline int fix_pxm_node_maps(int max_nid) +{ + return 0; +} static inline void disable_srat(void) { } diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index d076ebd19a61..78b24b090488 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -763,6 +763,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status *event_status)) ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_hw_disable_all_gpes(void)) +ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_hw_enable_all_wakeup_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void)) diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h index 9d0479f50f97..5db59a1efb65 100644 --- a/include/asm-generic/early_ioremap.h +++ b/include/asm-generic/early_ioremap.h @@ -35,7 +35,7 @@ extern void early_ioremap_reset(void); /* * Early copy from unmapped memory to kernel mapped memory. */ -extern void copy_from_early_mem(void *dest, phys_addr_t src, +extern int copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size); #else diff --git a/include/asm-generic/fprobe.h b/include/asm-generic/fprobe.h new file mode 100644 index 000000000000..8659a4dc6eb6 --- /dev/null +++ b/include/asm-generic/fprobe.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Generic arch dependent fprobe macros. + */ +#ifndef __ASM_GENERIC_FPROBE_H__ +#define __ASM_GENERIC_FPROBE_H__ + +#include + +#ifdef CONFIG_64BIT +/* + * Encoding the size and the address of fprobe into one 64bit entry. + * The 32bit architectures should use 2 entries to store those info. + */ + +#define ARCH_DEFINE_ENCODE_FPROBE_HEADER + +#define FPROBE_HEADER_MSB_SIZE_SHIFT (BITS_PER_LONG - FPROBE_DATA_SIZE_BITS) +#define FPROBE_HEADER_MSB_MASK \ + GENMASK(FPROBE_HEADER_MSB_SIZE_SHIFT - 1, 0) + +/* + * By default, this expects the MSBs in the address of kprobe is 0xf. + * If any arch needs another fixed pattern (e.g. s390 is zero filled), + * override this. + */ +#define FPROBE_HEADER_MSB_PATTERN \ + GENMASK(BITS_PER_LONG - 1, FPROBE_HEADER_MSB_SIZE_SHIFT) + +#define arch_fprobe_header_encodable(fp) \ + (((unsigned long)(fp) & ~FPROBE_HEADER_MSB_MASK) == \ + FPROBE_HEADER_MSB_PATTERN) + +#define arch_encode_fprobe_header(fp, size) \ + (((unsigned long)(fp) & FPROBE_HEADER_MSB_MASK) | \ + ((unsigned long)(size) << FPROBE_HEADER_MSB_SIZE_SHIFT)) + +#define arch_decode_fprobe_header_size(val) \ + ((unsigned long)(val) >> FPROBE_HEADER_MSB_SIZE_SHIFT) + +#define arch_decode_fprobe_header_fp(val) \ + ((struct fprobe *)(((unsigned long)(val) & FPROBE_HEADER_MSB_MASK) | \ + FPROBE_HEADER_MSB_PATTERN)) +#endif /* CONFIG_64BIT */ + +#endif /* __ASM_GENERIC_FPROBE_H__ */ diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h deleted file mode 100644 index 814207e7c37f..000000000000 --- a/include/asm-generic/hyperv-tlfs.h +++ /dev/null @@ -1,874 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* - * This file contains definitions from Hyper-V Hypervisor Top-Level Functional - * Specification (TLFS): - * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs - */ - -#ifndef _ASM_GENERIC_HYPERV_TLFS_H -#define _ASM_GENERIC_HYPERV_TLFS_H - -#include -#include -#include - -/* - * While not explicitly listed in the TLFS, Hyper-V always runs with a page size - * of 4096. These definitions are used when communicating with Hyper-V using - * guest physical pages and guest physical page addresses, since the guest page - * size may not be 4096 on all architectures. - */ -#define HV_HYP_PAGE_SHIFT 12 -#define HV_HYP_PAGE_SIZE BIT(HV_HYP_PAGE_SHIFT) -#define HV_HYP_PAGE_MASK (~(HV_HYP_PAGE_SIZE - 1)) - -/* - * Hyper-V provides two categories of flags relevant to guest VMs. The - * "Features" category indicates specific functionality that is available - * to guests on this particular instance of Hyper-V. The "Features" - * are presented in four groups, each of which is 32 bits. The group A - * and B definitions are common across architectures and are listed here. - * However, not all flags are relevant on all architectures. - * - * Groups C and D vary across architectures and are listed in the - * architecture specific portion of hyperv-tlfs.h. Some of these flags exist - * on multiple architectures, but the bit positions are different so they - * cannot appear in the generic portion of hyperv-tlfs.h. - * - * The "Enlightenments" category provides recommendations on whether to use - * specific enlightenments that are available. The Enlighenments are a single - * group of 32 bits, but they vary across architectures and are listed in - * the architecture specific portion of hyperv-tlfs.h. - */ - -/* - * Group A Features. - */ - -/* VP Runtime register available */ -#define HV_MSR_VP_RUNTIME_AVAILABLE BIT(0) -/* Partition Reference Counter available*/ -#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1) -/* Basic SynIC register available */ -#define HV_MSR_SYNIC_AVAILABLE BIT(2) -/* Synthetic Timer registers available */ -#define HV_MSR_SYNTIMER_AVAILABLE BIT(3) -/* Virtual APIC assist and VP assist page registers available */ -#define HV_MSR_APIC_ACCESS_AVAILABLE BIT(4) -/* Hypercall and Guest OS ID registers available*/ -#define HV_MSR_HYPERCALL_AVAILABLE BIT(5) -/* Access virtual processor index register available*/ -#define HV_MSR_VP_INDEX_AVAILABLE BIT(6) -/* Virtual system reset register available*/ -#define HV_MSR_RESET_AVAILABLE BIT(7) -/* Access statistics page registers available */ -#define HV_MSR_STAT_PAGES_AVAILABLE BIT(8) -/* Partition reference TSC register is available */ -#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9) -/* Partition Guest IDLE register is available */ -#define HV_MSR_GUEST_IDLE_AVAILABLE BIT(10) -/* Partition local APIC and TSC frequency registers available */ -#define HV_ACCESS_FREQUENCY_MSRS BIT(11) -/* AccessReenlightenmentControls privilege */ -#define HV_ACCESS_REENLIGHTENMENT BIT(13) -/* AccessTscInvariantControls privilege */ -#define HV_ACCESS_TSC_INVARIANT BIT(15) - -/* - * Group B features. - */ -#define HV_CREATE_PARTITIONS BIT(0) -#define HV_ACCESS_PARTITION_ID BIT(1) -#define HV_ACCESS_MEMORY_POOL BIT(2) -#define HV_ADJUST_MESSAGE_BUFFERS BIT(3) -#define HV_POST_MESSAGES BIT(4) -#define HV_SIGNAL_EVENTS BIT(5) -#define HV_CREATE_PORT BIT(6) -#define HV_CONNECT_PORT BIT(7) -#define HV_ACCESS_STATS BIT(8) -#define HV_DEBUGGING BIT(11) -#define HV_CPU_MANAGEMENT BIT(12) -#define HV_ENABLE_EXTENDED_HYPERCALLS BIT(20) -#define HV_ISOLATION BIT(22) - -/* - * TSC page layout. - */ -struct ms_hyperv_tsc_page { - volatile u32 tsc_sequence; - u32 reserved1; - volatile u64 tsc_scale; - volatile s64 tsc_offset; -} __packed; - -union hv_reference_tsc_msr { - u64 as_uint64; - struct { - u64 enable:1; - u64 reserved:11; - u64 pfn:52; - } __packed; -}; - -/* - * The guest OS needs to register the guest ID with the hypervisor. - * The guest ID is a 64 bit entity and the structure of this ID is - * specified in the Hyper-V specification: - * - * msdn.microsoft.com/en-us/library/windows/hardware/ff542653%28v=vs.85%29.aspx - * - * While the current guideline does not specify how Linux guest ID(s) - * need to be generated, our plan is to publish the guidelines for - * Linux and other guest operating systems that currently are hosted - * on Hyper-V. The implementation here conforms to this yet - * unpublished guidelines. - * - * - * Bit(s) - * 63 - Indicates if the OS is Open Source or not; 1 is Open Source - * 62:56 - Os Type; Linux is 0x100 - * 55:48 - Distro specific identification - * 47:16 - Linux kernel version number - * 15:0 - Distro specific identification - * - * - */ - -#define HV_LINUX_VENDOR_ID 0x8100 - -/* - * Crash notification flags. - */ -#define HV_CRASH_CTL_CRASH_NOTIFY_MSG BIT_ULL(62) -#define HV_CRASH_CTL_CRASH_NOTIFY BIT_ULL(63) - -/* Declare the various hypercall operations. */ -#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 -#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003 -#define HVCALL_ENABLE_VP_VTL 0x000f -#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008 -#define HVCALL_SEND_IPI 0x000b -#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013 -#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014 -#define HVCALL_SEND_IPI_EX 0x0015 -#define HVCALL_GET_PARTITION_ID 0x0046 -#define HVCALL_DEPOSIT_MEMORY 0x0048 -#define HVCALL_CREATE_VP 0x004e -#define HVCALL_GET_VP_REGISTERS 0x0050 -#define HVCALL_SET_VP_REGISTERS 0x0051 -#define HVCALL_POST_MESSAGE 0x005c -#define HVCALL_SIGNAL_EVENT 0x005d -#define HVCALL_POST_DEBUG_DATA 0x0069 -#define HVCALL_RETRIEVE_DEBUG_DATA 0x006a -#define HVCALL_RESET_DEBUG_SESSION 0x006b -#define HVCALL_ADD_LOGICAL_PROCESSOR 0x0076 -#define HVCALL_MAP_DEVICE_INTERRUPT 0x007c -#define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d -#define HVCALL_RETARGET_INTERRUPT 0x007e -#define HVCALL_START_VP 0x0099 -#define HVCALL_GET_VP_ID_FROM_APIC_ID 0x009a -#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af -#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 -#define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db -#define HVCALL_MMIO_READ 0x0106 -#define HVCALL_MMIO_WRITE 0x0107 - -/* Extended hypercalls */ -#define HV_EXT_CALL_QUERY_CAPABILITIES 0x8001 -#define HV_EXT_CALL_MEMORY_HEAT_HINT 0x8003 - -#define HV_FLUSH_ALL_PROCESSORS BIT(0) -#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1) -#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2) -#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3) - -/* Extended capability bits */ -#define HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT BIT(8) - -enum HV_GENERIC_SET_FORMAT { - HV_GENERIC_SET_SPARSE_4K, - HV_GENERIC_SET_ALL, -}; - -#define HV_PARTITION_ID_SELF ((u64)-1) -#define HV_VP_INDEX_SELF ((u32)-2) - -#define HV_HYPERCALL_RESULT_MASK GENMASK_ULL(15, 0) -#define HV_HYPERCALL_FAST_BIT BIT(16) -#define HV_HYPERCALL_VARHEAD_OFFSET 17 -#define HV_HYPERCALL_VARHEAD_MASK GENMASK_ULL(26, 17) -#define HV_HYPERCALL_RSVD0_MASK GENMASK_ULL(31, 27) -#define HV_HYPERCALL_NESTED BIT_ULL(31) -#define HV_HYPERCALL_REP_COMP_OFFSET 32 -#define HV_HYPERCALL_REP_COMP_1 BIT_ULL(32) -#define HV_HYPERCALL_REP_COMP_MASK GENMASK_ULL(43, 32) -#define HV_HYPERCALL_RSVD1_MASK GENMASK_ULL(47, 44) -#define HV_HYPERCALL_REP_START_OFFSET 48 -#define HV_HYPERCALL_REP_START_MASK GENMASK_ULL(59, 48) -#define HV_HYPERCALL_RSVD2_MASK GENMASK_ULL(63, 60) -#define HV_HYPERCALL_RSVD_MASK (HV_HYPERCALL_RSVD0_MASK | \ - HV_HYPERCALL_RSVD1_MASK | \ - HV_HYPERCALL_RSVD2_MASK) - -/* hypercall status code */ -#define HV_STATUS_SUCCESS 0 -#define HV_STATUS_INVALID_HYPERCALL_CODE 2 -#define HV_STATUS_INVALID_HYPERCALL_INPUT 3 -#define HV_STATUS_INVALID_ALIGNMENT 4 -#define HV_STATUS_INVALID_PARAMETER 5 -#define HV_STATUS_ACCESS_DENIED 6 -#define HV_STATUS_OPERATION_DENIED 8 -#define HV_STATUS_INSUFFICIENT_MEMORY 11 -#define HV_STATUS_INVALID_PORT_ID 17 -#define HV_STATUS_INVALID_CONNECTION_ID 18 -#define HV_STATUS_INSUFFICIENT_BUFFERS 19 -#define HV_STATUS_TIME_OUT 120 -#define HV_STATUS_VTL_ALREADY_ENABLED 134 - -/* - * The Hyper-V TimeRefCount register and the TSC - * page provide a guest VM clock with 100ns tick rate - */ -#define HV_CLOCK_HZ (NSEC_PER_SEC/100) - -/* Define the number of synthetic interrupt sources. */ -#define HV_SYNIC_SINT_COUNT (16) -/* Define the expected SynIC version. */ -#define HV_SYNIC_VERSION_1 (0x1) -/* Valid SynIC vectors are 16-255. */ -#define HV_SYNIC_FIRST_VALID_VECTOR (16) - -#define HV_SYNIC_CONTROL_ENABLE (1ULL << 0) -#define HV_SYNIC_SIMP_ENABLE (1ULL << 0) -#define HV_SYNIC_SIEFP_ENABLE (1ULL << 0) -#define HV_SYNIC_SINT_MASKED (1ULL << 16) -#define HV_SYNIC_SINT_AUTO_EOI (1ULL << 17) -#define HV_SYNIC_SINT_VECTOR_MASK (0xFF) - -#define HV_SYNIC_STIMER_COUNT (4) - -/* Define synthetic interrupt controller message constants. */ -#define HV_MESSAGE_SIZE (256) -#define HV_MESSAGE_PAYLOAD_BYTE_COUNT (240) -#define HV_MESSAGE_PAYLOAD_QWORD_COUNT (30) - -/* - * Define hypervisor message types. Some of the message types - * are x86/x64 specific, but there's no good way to separate - * them out into the arch-specific version of hyperv-tlfs.h - * because C doesn't provide a way to extend enum types. - * Keeping them all in the arch neutral hyperv-tlfs.h seems - * the least messy compromise. - */ -enum hv_message_type { - HVMSG_NONE = 0x00000000, - - /* Memory access messages. */ - HVMSG_UNMAPPED_GPA = 0x80000000, - HVMSG_GPA_INTERCEPT = 0x80000001, - - /* Timer notification messages. */ - HVMSG_TIMER_EXPIRED = 0x80000010, - - /* Error messages. */ - HVMSG_INVALID_VP_REGISTER_VALUE = 0x80000020, - HVMSG_UNRECOVERABLE_EXCEPTION = 0x80000021, - HVMSG_UNSUPPORTED_FEATURE = 0x80000022, - - /* Trace buffer complete messages. */ - HVMSG_EVENTLOG_BUFFERCOMPLETE = 0x80000040, - - /* Platform-specific processor intercept messages. */ - HVMSG_X64_IOPORT_INTERCEPT = 0x80010000, - HVMSG_X64_MSR_INTERCEPT = 0x80010001, - HVMSG_X64_CPUID_INTERCEPT = 0x80010002, - HVMSG_X64_EXCEPTION_INTERCEPT = 0x80010003, - HVMSG_X64_APIC_EOI = 0x80010004, - HVMSG_X64_LEGACY_FP_ERROR = 0x80010005 -}; - -/* Define synthetic interrupt controller message flags. */ -union hv_message_flags { - __u8 asu8; - struct { - __u8 msg_pending:1; - __u8 reserved:7; - } __packed; -}; - -/* Define port identifier type. */ -union hv_port_id { - __u32 asu32; - struct { - __u32 id:24; - __u32 reserved:8; - } __packed u; -}; - -/* Define synthetic interrupt controller message header. */ -struct hv_message_header { - __u32 message_type; - __u8 payload_size; - union hv_message_flags message_flags; - __u8 reserved[2]; - union { - __u64 sender; - union hv_port_id port; - }; -} __packed; - -/* Define synthetic interrupt controller message format. */ -struct hv_message { - struct hv_message_header header; - union { - __u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; - } u; -} __packed; - -/* Define the synthetic interrupt message page layout. */ -struct hv_message_page { - struct hv_message sint_message[HV_SYNIC_SINT_COUNT]; -} __packed; - -/* Define timer message payload structure. */ -struct hv_timer_message_payload { - __u32 timer_index; - __u32 reserved; - __u64 expiration_time; /* When the timer expired */ - __u64 delivery_time; /* When the message was delivered */ -} __packed; - - -/* Define synthetic interrupt controller flag constants. */ -#define HV_EVENT_FLAGS_COUNT (256 * 8) -#define HV_EVENT_FLAGS_LONG_COUNT (256 / sizeof(unsigned long)) - -/* - * Synthetic timer configuration. - */ -union hv_stimer_config { - u64 as_uint64; - struct { - u64 enable:1; - u64 periodic:1; - u64 lazy:1; - u64 auto_enable:1; - u64 apic_vector:8; - u64 direct_mode:1; - u64 reserved_z0:3; - u64 sintx:4; - u64 reserved_z1:44; - } __packed; -}; - - -/* Define the synthetic interrupt controller event flags format. */ -union hv_synic_event_flags { - unsigned long flags[HV_EVENT_FLAGS_LONG_COUNT]; -}; - -/* Define SynIC control register. */ -union hv_synic_scontrol { - u64 as_uint64; - struct { - u64 enable:1; - u64 reserved:63; - } __packed; -}; - -/* Define synthetic interrupt source. */ -union hv_synic_sint { - u64 as_uint64; - struct { - u64 vector:8; - u64 reserved1:8; - u64 masked:1; - u64 auto_eoi:1; - u64 polling:1; - u64 reserved2:45; - } __packed; -}; - -/* Define the format of the SIMP register */ -union hv_synic_simp { - u64 as_uint64; - struct { - u64 simp_enabled:1; - u64 preserved:11; - u64 base_simp_gpa:52; - } __packed; -}; - -/* Define the format of the SIEFP register */ -union hv_synic_siefp { - u64 as_uint64; - struct { - u64 siefp_enabled:1; - u64 preserved:11; - u64 base_siefp_gpa:52; - } __packed; -}; - -struct hv_vpset { - u64 format; - u64 valid_bank_mask; - u64 bank_contents[]; -} __packed; - -/* The maximum number of sparse vCPU banks which can be encoded by 'struct hv_vpset' */ -#define HV_MAX_SPARSE_VCPU_BANKS (64) -/* The number of vCPUs in one sparse bank */ -#define HV_VCPUS_PER_SPARSE_BANK (64) - -/* HvCallSendSyntheticClusterIpi hypercall */ -struct hv_send_ipi { - u32 vector; - u32 reserved; - u64 cpu_mask; -} __packed; - -/* HvCallSendSyntheticClusterIpiEx hypercall */ -struct hv_send_ipi_ex { - u32 vector; - u32 reserved; - struct hv_vpset vp_set; -} __packed; - -/* HvFlushGuestPhysicalAddressSpace hypercalls */ -struct hv_guest_mapping_flush { - u64 address_space; - u64 flags; -} __packed; - -/* - * HV_MAX_FLUSH_PAGES = "additional_pages" + 1. It's limited - * by the bitwidth of "additional_pages" in union hv_gpa_page_range. - */ -#define HV_MAX_FLUSH_PAGES (2048) -#define HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB 0 -#define HV_GPA_PAGE_RANGE_PAGE_SIZE_1GB 1 - -/* HvFlushGuestPhysicalAddressList, HvExtCallMemoryHeatHint hypercall */ -union hv_gpa_page_range { - u64 address_space; - struct { - u64 additional_pages:11; - u64 largepage:1; - u64 basepfn:52; - } page; - struct { - u64 reserved:12; - u64 page_size:1; - u64 reserved1:8; - u64 base_large_pfn:43; - }; -}; - -/* - * All input flush parameters should be in single page. The max flush - * count is equal with how many entries of union hv_gpa_page_range can - * be populated into the input parameter page. - */ -#define HV_MAX_FLUSH_REP_COUNT ((HV_HYP_PAGE_SIZE - 2 * sizeof(u64)) / \ - sizeof(union hv_gpa_page_range)) - -struct hv_guest_mapping_flush_list { - u64 address_space; - u64 flags; - union hv_gpa_page_range gpa_list[HV_MAX_FLUSH_REP_COUNT]; -}; - -/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ -struct hv_tlb_flush { - u64 address_space; - u64 flags; - u64 processor_mask; - u64 gva_list[]; -} __packed; - -/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */ -struct hv_tlb_flush_ex { - u64 address_space; - u64 flags; - struct hv_vpset hv_vp_set; - u64 gva_list[]; -} __packed; - -/* HvGetPartitionId hypercall (output only) */ -struct hv_get_partition_id { - u64 partition_id; -} __packed; - -/* HvDepositMemory hypercall */ -struct hv_deposit_memory { - u64 partition_id; - u64 gpa_page_list[]; -} __packed; - -struct hv_proximity_domain_flags { - u32 proximity_preferred : 1; - u32 reserved : 30; - u32 proximity_info_valid : 1; -} __packed; - -struct hv_proximity_domain_info { - u32 domain_id; - struct hv_proximity_domain_flags flags; -} __packed; - -struct hv_lp_startup_status { - u64 hv_status; - u64 substatus1; - u64 substatus2; - u64 substatus3; - u64 substatus4; - u64 substatus5; - u64 substatus6; -} __packed; - -/* HvAddLogicalProcessor hypercall */ -struct hv_input_add_logical_processor { - u32 lp_index; - u32 apic_id; - struct hv_proximity_domain_info proximity_domain_info; -} __packed; - -struct hv_output_add_logical_processor { - struct hv_lp_startup_status startup_status; -} __packed; - -enum HV_SUBNODE_TYPE -{ - HvSubnodeAny = 0, - HvSubnodeSocket = 1, - HvSubnodeAmdNode = 2, - HvSubnodeL3 = 3, - HvSubnodeCount = 4, - HvSubnodeInvalid = -1 -}; - -/* HvCreateVp hypercall */ -struct hv_create_vp { - u64 partition_id; - u32 vp_index; - u8 padding[3]; - u8 subnode_type; - u64 subnode_id; - struct hv_proximity_domain_info proximity_domain_info; - u64 flags; -} __packed; - -enum hv_interrupt_source { - HV_INTERRUPT_SOURCE_MSI = 1, /* MSI and MSI-X */ - HV_INTERRUPT_SOURCE_IOAPIC, -}; - -union hv_ioapic_rte { - u64 as_uint64; - - struct { - u32 vector:8; - u32 delivery_mode:3; - u32 destination_mode:1; - u32 delivery_status:1; - u32 interrupt_polarity:1; - u32 remote_irr:1; - u32 trigger_mode:1; - u32 interrupt_mask:1; - u32 reserved1:15; - - u32 reserved2:24; - u32 destination_id:8; - }; - - struct { - u32 low_uint32; - u32 high_uint32; - }; -} __packed; - -struct hv_interrupt_entry { - u32 source; - u32 reserved1; - union { - union hv_msi_entry msi_entry; - union hv_ioapic_rte ioapic_rte; - }; -} __packed; - -/* - * flags for hv_device_interrupt_target.flags - */ -#define HV_DEVICE_INTERRUPT_TARGET_MULTICAST 1 -#define HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET 2 - -struct hv_device_interrupt_target { - u32 vector; - u32 flags; - union { - u64 vp_mask; - struct hv_vpset vp_set; - }; -} __packed; - -struct hv_retarget_device_interrupt { - u64 partition_id; /* use "self" */ - u64 device_id; - struct hv_interrupt_entry int_entry; - u64 reserved2; - struct hv_device_interrupt_target int_target; -} __packed __aligned(8); - -/* - * These Hyper-V registers provide information equivalent to the CPUID - * instruction on x86/x64. - */ -#define HV_REGISTER_HYPERVISOR_VERSION 0x00000100 /*CPUID 0x40000002 */ -#define HV_REGISTER_FEATURES 0x00000200 /*CPUID 0x40000003 */ -#define HV_REGISTER_ENLIGHTENMENTS 0x00000201 /*CPUID 0x40000004 */ - -/* - * Synthetic register definitions equivalent to MSRs on x86/x64 - */ -#define HV_REGISTER_GUEST_CRASH_P0 0x00000210 -#define HV_REGISTER_GUEST_CRASH_P1 0x00000211 -#define HV_REGISTER_GUEST_CRASH_P2 0x00000212 -#define HV_REGISTER_GUEST_CRASH_P3 0x00000213 -#define HV_REGISTER_GUEST_CRASH_P4 0x00000214 -#define HV_REGISTER_GUEST_CRASH_CTL 0x00000215 - -#define HV_REGISTER_GUEST_OS_ID 0x00090002 -#define HV_REGISTER_VP_INDEX 0x00090003 -#define HV_REGISTER_TIME_REF_COUNT 0x00090004 -#define HV_REGISTER_REFERENCE_TSC 0x00090017 - -#define HV_REGISTER_SINT0 0x000A0000 -#define HV_REGISTER_SCONTROL 0x000A0010 -#define HV_REGISTER_SIEFP 0x000A0012 -#define HV_REGISTER_SIMP 0x000A0013 -#define HV_REGISTER_EOM 0x000A0014 - -#define HV_REGISTER_STIMER0_CONFIG 0x000B0000 -#define HV_REGISTER_STIMER0_COUNT 0x000B0001 - -/* HvGetVpRegisters hypercall input with variable size reg name list*/ -struct hv_get_vp_registers_input { - struct { - u64 partitionid; - u32 vpindex; - u8 inputvtl; - u8 padding[3]; - } header; - struct input { - u32 name0; - u32 name1; - } element[]; -} __packed; - -/* HvGetVpRegisters returns an array of these output elements */ -struct hv_get_vp_registers_output { - union { - struct { - u32 a; - u32 b; - u32 c; - u32 d; - } as32 __packed; - struct { - u64 low; - u64 high; - } as64 __packed; - }; -}; - -/* HvSetVpRegisters hypercall with variable size reg name/value list*/ -struct hv_set_vp_registers_input { - struct { - u64 partitionid; - u32 vpindex; - u8 inputvtl; - u8 padding[3]; - } header; - struct { - u32 name; - u32 padding1; - u64 padding2; - u64 valuelow; - u64 valuehigh; - } element[]; -} __packed; - -enum hv_device_type { - HV_DEVICE_TYPE_LOGICAL = 0, - HV_DEVICE_TYPE_PCI = 1, - HV_DEVICE_TYPE_IOAPIC = 2, - HV_DEVICE_TYPE_ACPI = 3, -}; - -typedef u16 hv_pci_rid; -typedef u16 hv_pci_segment; -typedef u64 hv_logical_device_id; -union hv_pci_bdf { - u16 as_uint16; - - struct { - u8 function:3; - u8 device:5; - u8 bus; - }; -} __packed; - -union hv_pci_bus_range { - u16 as_uint16; - - struct { - u8 subordinate_bus; - u8 secondary_bus; - }; -} __packed; - -union hv_device_id { - u64 as_uint64; - - struct { - u64 reserved0:62; - u64 device_type:2; - }; - - /* HV_DEVICE_TYPE_LOGICAL */ - struct { - u64 id:62; - u64 device_type:2; - } logical; - - /* HV_DEVICE_TYPE_PCI */ - struct { - union { - hv_pci_rid rid; - union hv_pci_bdf bdf; - }; - - hv_pci_segment segment; - union hv_pci_bus_range shadow_bus_range; - - u16 phantom_function_bits:2; - u16 source_shadow:1; - - u16 rsvdz0:11; - u16 device_type:2; - } pci; - - /* HV_DEVICE_TYPE_IOAPIC */ - struct { - u8 ioapic_id; - u8 rsvdz0; - u16 rsvdz1; - u16 rsvdz2; - - u16 rsvdz3:14; - u16 device_type:2; - } ioapic; - - /* HV_DEVICE_TYPE_ACPI */ - struct { - u32 input_mapping_base; - u32 input_mapping_count:30; - u32 device_type:2; - } acpi; -} __packed; - -enum hv_interrupt_trigger_mode { - HV_INTERRUPT_TRIGGER_MODE_EDGE = 0, - HV_INTERRUPT_TRIGGER_MODE_LEVEL = 1, -}; - -struct hv_device_interrupt_descriptor { - u32 interrupt_type; - u32 trigger_mode; - u32 vector_count; - u32 reserved; - struct hv_device_interrupt_target target; -} __packed; - -struct hv_input_map_device_interrupt { - u64 partition_id; - u64 device_id; - u64 flags; - struct hv_interrupt_entry logical_interrupt_entry; - struct hv_device_interrupt_descriptor interrupt_descriptor; -} __packed; - -struct hv_output_map_device_interrupt { - struct hv_interrupt_entry interrupt_entry; -} __packed; - -struct hv_input_unmap_device_interrupt { - u64 partition_id; - u64 device_id; - struct hv_interrupt_entry interrupt_entry; -} __packed; - -#define HV_SOURCE_SHADOW_NONE 0x0 -#define HV_SOURCE_SHADOW_BRIDGE_BUS_RANGE 0x1 - -/* - * Version info reported by hypervisor - */ -union hv_hypervisor_version_info { - struct { - u32 build_number; - - u32 minor_version : 16; - u32 major_version : 16; - - u32 service_pack; - - u32 service_number : 24; - u32 service_branch : 8; - }; - struct { - u32 eax; - u32 ebx; - u32 ecx; - u32 edx; - }; -}; - -/* - * The whole argument should fit in a page to be able to pass to the hypervisor - * in one hypercall. - */ -#define HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES \ - ((HV_HYP_PAGE_SIZE - sizeof(struct hv_memory_hint)) / \ - sizeof(union hv_gpa_page_range)) - -/* HvExtCallMemoryHeatHint hypercall */ -#define HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD 2 -struct hv_memory_hint { - u64 type:2; - u64 reserved:62; - union hv_gpa_page_range ranges[]; -} __packed; - -/* Data structures for HVCALL_MMIO_READ and HVCALL_MMIO_WRITE */ -#define HV_HYPERCALL_MMIO_MAX_DATA_LENGTH 64 - -struct hv_mmio_read_input { - u64 gpa; - u32 size; - u32 reserved; -} __packed; - -struct hv_mmio_read_output { - u8 data[HV_HYPERCALL_MMIO_MAX_DATA_LENGTH]; -} __packed; - -struct hv_mmio_write_input { - u64 gpa; - u32 size; - u32 reserved; - u8 data[HV_HYPERCALL_MMIO_MAX_DATA_LENGTH]; -} __packed; - -#endif diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 8fe7aaab2599..a7bbe504e4f3 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -6,9 +6,8 @@ * independent. See arch//include/asm/mshyperv.h for definitions * that are specific to architecture . * - * Definitions that are specified in the Hyper-V Top Level Functional - * Spec (TLFS) should not go in this file, but should instead go in - * hyperv-tlfs.h. + * Definitions that are derived from Hyper-V code or headers should not go in + * this file, but should instead go in the relevant files in include/hyperv. * * Copyright (C) 2019, Microsoft, Inc. * @@ -25,7 +24,7 @@ #include #include #include -#include +#include #define VTPM_BASE_ADDRESS 0xfed40000 diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 7c48f5fbf8aa..892ece4558a2 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -109,8 +109,7 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { struct ptdesc *ptdesc = page_ptdesc(pte_page); - pagetable_pte_dtor(ptdesc); - pagetable_free(ptdesc); + pagetable_dtor_free(ptdesc); } @@ -153,8 +152,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) struct ptdesc *ptdesc = virt_to_ptdesc(pmd); BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - pagetable_pmd_dtor(ptdesc); - pagetable_free(ptdesc); + pagetable_dtor_free(ptdesc); } #endif @@ -202,8 +200,7 @@ static inline void __pud_free(struct mm_struct *mm, pud_t *pud) struct ptdesc *ptdesc = virt_to_ptdesc(pud); BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - pagetable_pud_dtor(ptdesc); - pagetable_free(ptdesc); + pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_PUD_FREE @@ -215,10 +212,82 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) #endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#if CONFIG_PGTABLE_LEVELS > 4 + +static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) +{ + gfp_t gfp = GFP_PGTABLE_USER; + struct ptdesc *ptdesc; + + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + gfp &= ~__GFP_HIGHMEM; + + ptdesc = pagetable_alloc_noprof(gfp, 0); + if (!ptdesc) + return NULL; + + pagetable_p4d_ctor(ptdesc); + return ptdesc_address(ptdesc); +} +#define __p4d_alloc_one(...) alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__)) + +#ifndef __HAVE_ARCH_P4D_ALLOC_ONE +static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) +{ + return __p4d_alloc_one_noprof(mm, addr); +} +#define p4d_alloc_one(...) alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__)) +#endif + +static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + struct ptdesc *ptdesc = virt_to_ptdesc(p4d); + + BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); + pagetable_dtor_free(ptdesc); +} + +#ifndef __HAVE_ARCH_P4D_FREE +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + if (!mm_p4d_folded(mm)) + __p4d_free(mm, p4d); +} +#endif + +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ + +static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order) +{ + gfp_t gfp = GFP_PGTABLE_USER; + struct ptdesc *ptdesc; + + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + gfp &= ~__GFP_HIGHMEM; + + ptdesc = pagetable_alloc_noprof(gfp, order); + if (!ptdesc) + return NULL; + + pagetable_pgd_ctor(ptdesc); + return ptdesc_address(ptdesc); +} +#define __pgd_alloc(...) alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__)) + +static inline void __pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + struct ptdesc *ptdesc = virt_to_ptdesc(pgd); + + BUG_ON((unsigned long)pgd & (PAGE_SIZE-1)); + pagetable_dtor_free(ptdesc); +} + #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - pagetable_free(virt_to_ptdesc(pgd)); + __pgd_free(mm, pgd); } #endif diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h index 5a80fe728dc8..182b039ce5fa 100644 --- a/include/asm-generic/syscall.h +++ b/include/asm-generic/syscall.h @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * This file is a stub providing documentation for what functions - * asm-ARCH/syscall.h files need to define. Most arch definitions + * arch/ARCH/include/asm/syscall.h files need to define. Most arch definitions * will be simple inlines. * * All of these functions expect to be called with no locks, diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 709830274b75..e402aef79c93 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -153,8 +153,9 @@ * * Useful if your architecture has non-page page directories. * - * When used, an architecture is expected to provide __tlb_remove_table() - * which does the actual freeing of these pages. + * When used, an architecture is expected to provide __tlb_remove_table() or + * use the generic __tlb_remove_table(), which does the actual freeing of these + * pages. * * MMU_GATHER_RCU_TABLE_FREE * @@ -207,16 +208,31 @@ struct mmu_table_batch { #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) +#ifndef __HAVE_ARCH_TLB_REMOVE_TABLE +static inline void __tlb_remove_table(void *table) +{ + struct ptdesc *ptdesc = (struct ptdesc *)table; + + pagetable_dtor_free(ptdesc); +} +#endif + extern void tlb_remove_table(struct mmu_gather *tlb, void *table); -#else /* !CONFIG_MMU_GATHER_HAVE_TABLE_FREE */ +#else /* !CONFIG_MMU_GATHER_TABLE_FREE */ +static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page); /* * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based * page directories and we can use the normal page batching to free them. */ -#define tlb_remove_table(tlb, page) tlb_remove_page((tlb), (page)) +static inline void tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + struct page *page = (struct page *)table; + pagetable_dtor(page_ptdesc(page)); + tlb_remove_page(tlb, page); +} #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h index cbbc9a6dc571..ce6521ad04d1 100644 --- a/include/clocksource/arm_arch_timer.h +++ b/include/clocksource/arm_arch_timer.h @@ -22,6 +22,12 @@ #define CNTHCTL_EVNTDIR (1 << 3) #define CNTHCTL_EVNTI (0xF << 4) #define CNTHCTL_ECV (1 << 12) +#define CNTHCTL_EL1TVT (1 << 13) +#define CNTHCTL_EL1TVCT (1 << 14) +#define CNTHCTL_EL1NVPCT (1 << 15) +#define CNTHCTL_EL1NVVCT (1 << 16) +#define CNTHCTL_CNTVMASK (1 << 18) +#define CNTHCTL_CNTPMASK (1 << 19) enum arch_timer_reg { ARCH_TIMER_REG_CTRL, diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..d48dd4176fd3 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -15,7 +15,7 @@ #include #include -#include +#include #define HV_MAX_MAX_DELTA_TICKS 0xffffffff #define HV_MIN_DELTA_TICKS 1 @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time) diff --git a/include/crypto/gf128mul.h b/include/crypto/gf128mul.h index 81330c6446f6..b0853f7cada0 100644 --- a/include/crypto/gf128mul.h +++ b/include/crypto/gf128mul.h @@ -158,12 +158,10 @@ 64...71 72...79 80...87 88...95 96..103 104.111 112.119 120.127 */ -/* A slow generic version of gf_mul, implemented for lle and bbe +/* A slow generic version of gf_mul, implemented for lle * It multiplies a and b and puts the result in a */ void gf128mul_lle(be128 *a, const be128 *b); -void gf128mul_bbe(be128 *a, const be128 *b); - /* * The following functions multiply a field element by x in * the polynomial field representation. They use 64-bit word operations @@ -224,9 +222,7 @@ struct gf128mul_4k { }; struct gf128mul_4k *gf128mul_init_4k_lle(const be128 *g); -struct gf128mul_4k *gf128mul_init_4k_bbe(const be128 *g); void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t); -void gf128mul_4k_bbe(be128 *a, const struct gf128mul_4k *t); void gf128mul_x8_ble(le128 *r, const le128 *x); static inline void gf128mul_free_4k(struct gf128mul_4k *t) { diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index 58967593b6b4..84da3424decc 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -12,20 +12,6 @@ #include struct ahash_request; -struct scatterlist; - -struct crypto_hash_walk { - char *data; - - unsigned int offset; - unsigned int flags; - - struct page *pg; - unsigned int entrylen; - - unsigned int total; - struct scatterlist *sg; -}; struct ahash_instance { void (*free)(struct ahash_instance *inst); @@ -57,15 +43,6 @@ struct crypto_shash_spawn { struct crypto_spawn base; }; -int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err); -int crypto_hash_walk_first(struct ahash_request *req, - struct crypto_hash_walk *walk); - -static inline int crypto_hash_walk_last(struct crypto_hash_walk *walk) -{ - return !(walk->entrylen | walk->total); -} - int crypto_register_ahash(struct ahash_alg *alg); void crypto_unregister_ahash(struct ahash_alg *alg); int crypto_register_ahashes(struct ahash_alg *algs, int count); diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index 7ae42afdcf3e..4f49621d3eb6 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -11,7 +11,6 @@ #include #include #include -#include #include /* @@ -58,12 +57,6 @@ struct crypto_lskcipher_spawn { struct skcipher_walk { union { struct { - struct page *page; - unsigned long offset; - } phys; - - struct { - u8 *page; void *addr; } virt; } src, dst; @@ -74,8 +67,6 @@ struct skcipher_walk { struct scatter_walk out; unsigned int total; - struct list_head buffers; - u8 *page; u8 *buffer; u8 *oiv; @@ -205,17 +196,14 @@ void crypto_unregister_lskciphers(struct lskcipher_alg *algs, int count); int lskcipher_register_instance(struct crypto_template *tmpl, struct lskcipher_instance *inst); -int skcipher_walk_done(struct skcipher_walk *walk, int err); +int skcipher_walk_done(struct skcipher_walk *walk, int res); int skcipher_walk_virt(struct skcipher_walk *walk, struct skcipher_request *req, bool atomic); -int skcipher_walk_async(struct skcipher_walk *walk, - struct skcipher_request *req); int skcipher_walk_aead_encrypt(struct skcipher_walk *walk, struct aead_request *req, bool atomic); int skcipher_walk_aead_decrypt(struct skcipher_walk *walk, struct aead_request *req, bool atomic); -void skcipher_walk_complete(struct skcipher_walk *walk, int err); static inline void skcipher_walk_abort(struct skcipher_walk *walk) { diff --git a/include/cxl/event.h b/include/cxl/event.h index 0bea1afbd747..04edd44bd26f 100644 --- a/include/cxl/event.h +++ b/include/cxl/event.h @@ -18,7 +18,8 @@ struct cxl_event_record_hdr { __le16 related_handle; __le64 timestamp; u8 maint_op_class; - u8 reserved[15]; + u8 maint_op_sub_class; + u8 reserved[14]; } __packed; struct cxl_event_media_hdr { @@ -44,19 +45,22 @@ struct cxl_event_generic { /* * General Media Event Record - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + * CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45 */ #define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10 struct cxl_event_gen_media { struct cxl_event_media_hdr media_hdr; u8 device[3]; u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; - u8 reserved[46]; + u8 cme_threshold_ev_flags; + u8 cme_count[3]; + u8 sub_type; + u8 reserved[41]; } __packed; /* * DRAM Event Record - DER - * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44 + * CXL rev 3.1 section 8.2.9.2.1.2; Table 8-46 */ #define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20 struct cxl_event_dram { @@ -67,12 +71,17 @@ struct cxl_event_dram { u8 row[3]; u8 column[2]; u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE]; - u8 reserved[0x17]; + u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; + u8 sub_channel; + u8 cme_threshold_ev_flags; + u8 cvme_count[3]; + u8 sub_type; + u8 reserved; } __packed; /* * Get Health Info Record - * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100 + * CXL rev 3.1 section 8.2.9.9.3.1; Table 8-133 */ struct cxl_get_health_info { u8 health_status; @@ -87,13 +96,16 @@ struct cxl_get_health_info { /* * Memory Module Event Record - * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 + * CXL rev 3.1 section 8.2.9.2.1.3; Table 8-47 */ struct cxl_event_mem_module { struct cxl_event_record_hdr hdr; u8 event_type; struct cxl_get_health_info info; - u8 reserved[0x3d]; + u8 validity_flags[2]; + u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; + u8 event_sub_type; + u8 reserved[0x2a]; } __packed; union cxl_event { diff --git a/include/drm/display/drm_hdmi_audio_helper.h b/include/drm/display/drm_hdmi_audio_helper.h new file mode 100644 index 000000000000..c9a6faef4109 --- /dev/null +++ b/include/drm/display/drm_hdmi_audio_helper.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef DRM_DISPLAY_HDMI_AUDIO_HELPER_H_ +#define DRM_DISPLAY_HDMI_AUDIO_HELPER_H_ + +#include + +struct drm_connector; +struct drm_connector_hdmi_audio_funcs; + +struct device; + +int drm_connector_hdmi_audio_init(struct drm_connector *connector, + struct device *hdmi_codec_dev, + const struct drm_connector_hdmi_audio_funcs *funcs, + unsigned int max_i2s_playback_channels, + bool spdif_playback, + int sound_dai_port); +void drm_connector_hdmi_audio_plugged_notify(struct drm_connector *connector, + bool plugged); + +#endif diff --git a/include/drm/display/drm_hdmi_state_helper.h b/include/drm/display/drm_hdmi_state_helper.h index d6d65da6d8f9..44ec5c4a7503 100644 --- a/include/drm/display/drm_hdmi_state_helper.h +++ b/include/drm/display/drm_hdmi_state_helper.h @@ -6,8 +6,11 @@ struct drm_atomic_state; struct drm_connector; struct drm_connector_state; +struct drm_display_mode; struct hdmi_audio_infoframe; +enum drm_connector_status; + void __drm_atomic_helper_connector_hdmi_reset(struct drm_connector *connector, struct drm_connector_state *new_conn_state); @@ -19,6 +22,9 @@ int drm_atomic_helper_connector_hdmi_update_audio_infoframe(struct drm_connector int drm_atomic_helper_connector_hdmi_clear_audio_infoframe(struct drm_connector *connector); int drm_atomic_helper_connector_hdmi_update_infoframes(struct drm_connector *connector, struct drm_atomic_state *state); +void drm_atomic_helper_connector_hdmi_hotplug(struct drm_connector *connector, + enum drm_connector_status status); +void drm_atomic_helper_connector_hdmi_force(struct drm_connector *connector); enum drm_mode_status drm_hdmi_connector_mode_valid(struct drm_connector *connector, diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index e8d735b7f6a4..496dbbd2ad7e 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -41,6 +41,8 @@ struct drm_display_info; struct drm_minor; struct drm_panel; struct edid; +struct hdmi_codec_daifmt; +struct hdmi_codec_params; struct i2c_adapter; /** @@ -676,6 +678,57 @@ struct drm_bridge_funcs { enum hdmi_infoframe_type type, const u8 *buffer, size_t len); + /** + * @hdmi_audio_startup: + * + * Called when ASoC starts an audio stream setup. The + * @hdmi_audio_startup() is optional. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + int (*hdmi_audio_startup)(struct drm_connector *connector, + struct drm_bridge *bridge); + + /** + * @hdmi_audio_prepare: + * Configures HDMI-encoder for audio stream. Can be called multiple + * times for each setup. Mandatory if HDMI audio is enabled in the + * bridge's configuration. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + int (*hdmi_audio_prepare)(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *fmt, + struct hdmi_codec_params *hparms); + + /** + * @hdmi_audio_shutdown: + * + * Shut down the audio stream. Mandatory if HDMI audio is enabled in + * the bridge's configuration. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + void (*hdmi_audio_shutdown)(struct drm_connector *connector, + struct drm_bridge *bridge); + + /** + * @hdmi_audio_mute_stream: + * + * Mute/unmute HDMI audio stream. The @hdmi_audio_mute_stream callback + * is optional. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + int (*hdmi_audio_mute_stream)(struct drm_connector *connector, + struct drm_bridge *bridge, + bool enable, int direction); + /** * @debugfs_init: * @@ -859,6 +912,27 @@ struct drm_bridge { * @DRM_BRIDGE_OP_HDMI is set. */ unsigned int max_bpc; + + /** + * @hdmi_audio_dev: device to be used as a parent for the HDMI Codec + */ + struct device *hdmi_audio_dev; + + /** + * @hdmi_audio_max_i2s_playback_channels: maximum number of playback + * I2S channels for the HDMI codec + */ + int hdmi_audio_max_i2s_playback_channels; + + /** + * @hdmi_audio_spdif_playback: set if HDMI codec has S/PDIF playback port + */ + unsigned int hdmi_audio_spdif_playback : 1; + + /** + * @hdmi_audio_dai_port: sound DAI port, -1 if it is not enabled + */ + int hdmi_audio_dai_port; }; static inline struct drm_bridge * diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index d1be19242a5c..f13d597370a3 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -45,7 +45,10 @@ struct drm_property; struct drm_property_blob; struct drm_printer; struct drm_privacy_screen; +struct drm_edid; struct edid; +struct hdmi_codec_daifmt; +struct hdmi_codec_params; struct i2c_adapter; enum drm_connector_force { @@ -1141,6 +1144,53 @@ struct drm_connector_state { struct drm_connector_hdmi_state hdmi; }; +struct drm_connector_hdmi_audio_funcs { + /** + * @startup: + * + * Called when ASoC starts an audio stream setup. The + * @startup() is optional. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + int (*startup)(struct drm_connector *connector); + + /** + * @prepare: + * Configures HDMI-encoder for audio stream. Can be called + * multiple times for each setup. Mandatory. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + int (*prepare)(struct drm_connector *connector, + struct hdmi_codec_daifmt *fmt, + struct hdmi_codec_params *hparms); + + /** + * @shutdown: + * + * Shut down the audio stream. Mandatory. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + void (*shutdown)(struct drm_connector *connector); + + /** + * @mute_stream: + * + * Mute/unmute HDMI audio stream. The @mute_stream callback is + * optional. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + int (*mute_stream)(struct drm_connector *connector, + bool enable, int direction); +}; + /** * struct drm_connector_hdmi_funcs - drm_hdmi_connector control functions */ @@ -1198,6 +1248,21 @@ struct drm_connector_hdmi_funcs { int (*write_infoframe)(struct drm_connector *connector, enum hdmi_infoframe_type type, const u8 *buffer, size_t len); + + /** + * @read_edid: + * + * This callback is used by the framework as a replacement for reading + * the EDID from connector->ddc. It is still recommended to provide + * connector->ddc instead of implementing this callback. Returned EDID + * should be freed via the drm_edid_free(). + * + * The @read_edid callback is optional. + * + * Returns: + * Valid EDID on success, NULL in case of failure. + */ + const struct drm_edid *(*read_edid)(struct drm_connector *connector); }; /** @@ -1660,6 +1725,68 @@ struct drm_cmdline_mode { bool tv_mode_specified; }; +/** + * struct drm_connector_hdmi_audio - DRM gemeric HDMI Codec-related structure + * + * HDMI drivers usually incorporate a HDMI Codec. This structure expresses the + * generic HDMI Codec as used by the DRM HDMI Codec framework. + */ +struct drm_connector_hdmi_audio { + /** + * @funcs: + * + * Implementation of the HDMI codec functionality to be used by the DRM + * HDMI Codec framework. + */ + const struct drm_connector_hdmi_audio_funcs *funcs; + + /** + * @codec_pdev: + * + * Platform device created to hold the HDMI Codec. It will be + * automatically unregistered during drm_connector_cleanup(). + */ + struct platform_device *codec_pdev; + + /** + * @lock: + * + * Mutex to protect @last_state, @plugged_cb and @plugged_cb_dev. + */ + struct mutex lock; + + /** + * @plugged_cb: + * + * Callback to be called when the HDMI sink get plugged to or unplugged + * from this connector. This is assigned by the framework when + * requested by the ASoC code. + */ + void (*plugged_cb)(struct device *dev, bool plugged); + + /** + * @plugged_cb_dev: + * + * The data for @plugged_cb(). It is being provided by the ASoC. + */ + struct device *plugged_cb_dev; + + /** + * @last_state: + * + * Last plugged state recored by the framework. It is used to correctly + * report the state to @plugged_cb(). + */ + bool last_state; + + /** + * @dai_port: + * + * The port in DT that is used for the Codec DAI. + */ + int dai_port; +}; + /* * struct drm_connector_hdmi - DRM Connector HDMI-related structure */ @@ -2121,6 +2248,11 @@ struct drm_connector { * @hdmi: HDMI-related variable and properties. */ struct drm_connector_hdmi hdmi; + + /** + * @hdmi_audio: HDMI codec properties and non-DRM state. + */ + struct drm_connector_hdmi_audio hdmi_audio; }; #define obj_to_connector(x) container_of(x, struct drm_connector, base) diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h index 1b6e59139e6c..9952b846c170 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -34,6 +34,7 @@ #include +struct dmem_cgroup_region; struct drm_fb_helper; struct drm_fb_helper_surface_size; struct drm_file; @@ -436,6 +437,10 @@ void *__devm_drm_dev_alloc(struct device *parent, const struct drm_driver *driver, size_t size, size_t offset); +struct dmem_cgroup_region * +drmm_cgroup_register_region(struct drm_device *dev, + const char *region_name, u64 size); + /** * devm_drm_dev_alloc - Resource managed allocation of a &drm_device instance * @parent: Parent device object diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index f0ef32e9fa5e..ef817926cddd 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -494,6 +494,7 @@ struct drm_memory_stats { enum drm_gem_object_status; +int drm_memory_stats_is_zero(const struct drm_memory_stats *stats); void drm_print_memory_stats(struct drm_printer *p, const struct drm_memory_stats *stats, enum drm_gem_object_status supported_status, diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index 5b8b1b059d32..fdae947682cd 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -48,19 +48,21 @@ struct drm_gem_object; * enum drm_gem_object_status - bitmask of object state for fdinfo reporting * @DRM_GEM_OBJECT_RESIDENT: object is resident in memory (ie. not unpinned) * @DRM_GEM_OBJECT_PURGEABLE: object marked as purgeable by userspace + * @DRM_GEM_OBJECT_ACTIVE: object is currently used by an active submission * * Bitmask of status used for fdinfo memory stats, see &drm_gem_object_funcs.status - * and drm_show_fdinfo(). Note that an object can DRM_GEM_OBJECT_PURGEABLE if - * it still active or not resident, in which case drm_show_fdinfo() will not + * and drm_show_fdinfo(). Note that an object can report DRM_GEM_OBJECT_PURGEABLE + * and be active or not resident, in which case drm_show_fdinfo() will not * account for it as purgeable. So drivers do not need to check if the buffer - * is idle and resident to return this bit. (Ie. userspace can mark a buffer - * as purgeable even while it is still busy on the GPU.. it does not _actually_ - * become puregeable until it becomes idle. The status gem object func does - * not need to consider this.) + * is idle and resident to return this bit, i.e. userspace can mark a buffer as + * purgeable even while it is still busy on the GPU. It will not get reported in + * the puregeable stats until it becomes idle. The status gem object func does + * not need to consider this. */ enum drm_gem_object_status { DRM_GEM_OBJECT_RESIDENT = BIT(0), DRM_GEM_OBJECT_PURGEABLE = BIT(1), + DRM_GEM_OBJECT_ACTIVE = BIT(2), }; /** diff --git a/include/drm/intel/pciids.h b/include/drm/intel/pciids.h index 46b05fa1f903..9c3a339e26af 100644 --- a/include/drm/intel/pciids.h +++ b/include/drm/intel/pciids.h @@ -861,6 +861,7 @@ MACRO__(0xB092, ## __VA_ARGS__), \ MACRO__(0xB0A0, ## __VA_ARGS__), \ MACRO__(0xB0A1, ## __VA_ARGS__), \ - MACRO__(0xB0A2, ## __VA_ARGS__) + MACRO__(0xB0A2, ## __VA_ARGS__), \ + MACRO__(0xB0B0, ## __VA_ARGS__) #endif /* __PCIIDS_H__ */ diff --git a/include/drm/intel/xe_pciids.h b/include/drm/intel/xe_pciids.h deleted file mode 100644 index 16d4b8bb590a..000000000000 --- a/include/drm/intel/xe_pciids.h +++ /dev/null @@ -1,235 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2022 Intel Corporation - */ - -#ifndef _XE_PCIIDS_H_ -#define _XE_PCIIDS_H_ - -/* - * Lists below can be turned into initializers for a struct pci_device_id - * by defining INTEL_VGA_DEVICE: - * - * #define INTEL_VGA_DEVICE(id, info) { \ - * 0x8086, id, \ - * ~0, ~0, \ - * 0x030000, 0xff0000, \ - * (unsigned long) info } - * - * And then calling like: - * - * XE_TGL_12_GT1_IDS(INTEL_VGA_DEVICE, ## __VA_ARGS__) - * - * To turn them into something else, just provide a different macro passed as - * first argument. - */ - -/* TGL */ -#define XE_TGL_GT1_IDS(MACRO__, ...) \ - MACRO__(0x9A60, ## __VA_ARGS__), \ - MACRO__(0x9A68, ## __VA_ARGS__), \ - MACRO__(0x9A70, ## __VA_ARGS__) - -#define XE_TGL_GT2_IDS(MACRO__, ...) \ - MACRO__(0x9A40, ## __VA_ARGS__), \ - MACRO__(0x9A49, ## __VA_ARGS__), \ - MACRO__(0x9A59, ## __VA_ARGS__), \ - MACRO__(0x9A78, ## __VA_ARGS__), \ - MACRO__(0x9AC0, ## __VA_ARGS__), \ - MACRO__(0x9AC9, ## __VA_ARGS__), \ - MACRO__(0x9AD9, ## __VA_ARGS__), \ - MACRO__(0x9AF8, ## __VA_ARGS__) - -#define XE_TGL_IDS(MACRO__, ...) \ - XE_TGL_GT1_IDS(MACRO__, ## __VA_ARGS__),\ - XE_TGL_GT2_IDS(MACRO__, ## __VA_ARGS__) - -/* RKL */ -#define XE_RKL_IDS(MACRO__, ...) \ - MACRO__(0x4C80, ## __VA_ARGS__), \ - MACRO__(0x4C8A, ## __VA_ARGS__), \ - MACRO__(0x4C8B, ## __VA_ARGS__), \ - MACRO__(0x4C8C, ## __VA_ARGS__), \ - MACRO__(0x4C90, ## __VA_ARGS__), \ - MACRO__(0x4C9A, ## __VA_ARGS__) - -/* DG1 */ -#define XE_DG1_IDS(MACRO__, ...) \ - MACRO__(0x4905, ## __VA_ARGS__), \ - MACRO__(0x4906, ## __VA_ARGS__), \ - MACRO__(0x4907, ## __VA_ARGS__), \ - MACRO__(0x4908, ## __VA_ARGS__), \ - MACRO__(0x4909, ## __VA_ARGS__) - -/* ADL-S */ -#define XE_ADLS_IDS(MACRO__, ...) \ - MACRO__(0x4680, ## __VA_ARGS__), \ - MACRO__(0x4682, ## __VA_ARGS__), \ - MACRO__(0x4688, ## __VA_ARGS__), \ - MACRO__(0x468A, ## __VA_ARGS__), \ - MACRO__(0x468B, ## __VA_ARGS__), \ - MACRO__(0x4690, ## __VA_ARGS__), \ - MACRO__(0x4692, ## __VA_ARGS__), \ - MACRO__(0x4693, ## __VA_ARGS__) - -/* ADL-P */ -#define XE_ADLP_IDS(MACRO__, ...) \ - MACRO__(0x46A0, ## __VA_ARGS__), \ - MACRO__(0x46A1, ## __VA_ARGS__), \ - MACRO__(0x46A2, ## __VA_ARGS__), \ - MACRO__(0x46A3, ## __VA_ARGS__), \ - MACRO__(0x46A6, ## __VA_ARGS__), \ - MACRO__(0x46A8, ## __VA_ARGS__), \ - MACRO__(0x46AA, ## __VA_ARGS__), \ - MACRO__(0x462A, ## __VA_ARGS__), \ - MACRO__(0x4626, ## __VA_ARGS__), \ - MACRO__(0x4628, ## __VA_ARGS__), \ - MACRO__(0x46B0, ## __VA_ARGS__), \ - MACRO__(0x46B1, ## __VA_ARGS__), \ - MACRO__(0x46B2, ## __VA_ARGS__), \ - MACRO__(0x46B3, ## __VA_ARGS__), \ - MACRO__(0x46C0, ## __VA_ARGS__), \ - MACRO__(0x46C1, ## __VA_ARGS__), \ - MACRO__(0x46C2, ## __VA_ARGS__), \ - MACRO__(0x46C3, ## __VA_ARGS__) - -/* ADL-N */ -#define XE_ADLN_IDS(MACRO__, ...) \ - MACRO__(0x46D0, ## __VA_ARGS__), \ - MACRO__(0x46D1, ## __VA_ARGS__), \ - MACRO__(0x46D2, ## __VA_ARGS__), \ - MACRO__(0x46D3, ## __VA_ARGS__), \ - MACRO__(0x46D4, ## __VA_ARGS__) - -/* RPL-S */ -#define XE_RPLS_IDS(MACRO__, ...) \ - MACRO__(0xA780, ## __VA_ARGS__), \ - MACRO__(0xA781, ## __VA_ARGS__), \ - MACRO__(0xA782, ## __VA_ARGS__), \ - MACRO__(0xA783, ## __VA_ARGS__), \ - MACRO__(0xA788, ## __VA_ARGS__), \ - MACRO__(0xA789, ## __VA_ARGS__), \ - MACRO__(0xA78A, ## __VA_ARGS__), \ - MACRO__(0xA78B, ## __VA_ARGS__) - -/* RPL-U */ -#define XE_RPLU_IDS(MACRO__, ...) \ - MACRO__(0xA721, ## __VA_ARGS__), \ - MACRO__(0xA7A1, ## __VA_ARGS__), \ - MACRO__(0xA7A9, ## __VA_ARGS__), \ - MACRO__(0xA7AC, ## __VA_ARGS__), \ - MACRO__(0xA7AD, ## __VA_ARGS__) - -/* RPL-P */ -#define XE_RPLP_IDS(MACRO__, ...) \ - MACRO__(0xA720, ## __VA_ARGS__), \ - MACRO__(0xA7A0, ## __VA_ARGS__), \ - MACRO__(0xA7A8, ## __VA_ARGS__), \ - MACRO__(0xA7AA, ## __VA_ARGS__), \ - MACRO__(0xA7AB, ## __VA_ARGS__) - -/* DG2 */ -#define XE_DG2_G10_IDS(MACRO__, ...) \ - MACRO__(0x5690, ## __VA_ARGS__), \ - MACRO__(0x5691, ## __VA_ARGS__), \ - MACRO__(0x5692, ## __VA_ARGS__), \ - MACRO__(0x56A0, ## __VA_ARGS__), \ - MACRO__(0x56A1, ## __VA_ARGS__), \ - MACRO__(0x56A2, ## __VA_ARGS__), \ - MACRO__(0x56BE, ## __VA_ARGS__), \ - MACRO__(0x56BF, ## __VA_ARGS__) - -#define XE_DG2_G11_IDS(MACRO__, ...) \ - MACRO__(0x5693, ## __VA_ARGS__), \ - MACRO__(0x5694, ## __VA_ARGS__), \ - MACRO__(0x5695, ## __VA_ARGS__), \ - MACRO__(0x56A5, ## __VA_ARGS__), \ - MACRO__(0x56A6, ## __VA_ARGS__), \ - MACRO__(0x56B0, ## __VA_ARGS__), \ - MACRO__(0x56B1, ## __VA_ARGS__), \ - MACRO__(0x56BA, ## __VA_ARGS__), \ - MACRO__(0x56BB, ## __VA_ARGS__), \ - MACRO__(0x56BC, ## __VA_ARGS__), \ - MACRO__(0x56BD, ## __VA_ARGS__) - -#define XE_DG2_G12_IDS(MACRO__, ...) \ - MACRO__(0x5696, ## __VA_ARGS__), \ - MACRO__(0x5697, ## __VA_ARGS__), \ - MACRO__(0x56A3, ## __VA_ARGS__), \ - MACRO__(0x56A4, ## __VA_ARGS__), \ - MACRO__(0x56B2, ## __VA_ARGS__), \ - MACRO__(0x56B3, ## __VA_ARGS__) - -#define XE_DG2_IDS(MACRO__, ...) \ - XE_DG2_G10_IDS(MACRO__, ## __VA_ARGS__),\ - XE_DG2_G11_IDS(MACRO__, ## __VA_ARGS__),\ - XE_DG2_G12_IDS(MACRO__, ## __VA_ARGS__) - -#define XE_ATS_M150_IDS(MACRO__, ...) \ - MACRO__(0x56C0, ## __VA_ARGS__), \ - MACRO__(0x56C2, ## __VA_ARGS__) - -#define XE_ATS_M75_IDS(MACRO__, ...) \ - MACRO__(0x56C1, ## __VA_ARGS__) - -#define XE_ATS_M_IDS(MACRO__, ...) \ - XE_ATS_M150_IDS(MACRO__, ## __VA_ARGS__),\ - XE_ATS_M75_IDS(MACRO__, ## __VA_ARGS__) - -/* ARL */ -#define XE_ARL_IDS(MACRO__, ...) \ - MACRO__(0x7D41, ## __VA_ARGS__), \ - MACRO__(0x7D51, ## __VA_ARGS__), \ - MACRO__(0x7D67, ## __VA_ARGS__), \ - MACRO__(0x7DD1, ## __VA_ARGS__), \ - MACRO__(0xB640, ## __VA_ARGS__) - -/* MTL */ -#define XE_MTL_IDS(MACRO__, ...) \ - MACRO__(0x7D40, ## __VA_ARGS__), \ - MACRO__(0x7D45, ## __VA_ARGS__), \ - MACRO__(0x7D55, ## __VA_ARGS__), \ - MACRO__(0x7D60, ## __VA_ARGS__), \ - MACRO__(0x7DD5, ## __VA_ARGS__) - -/* PVC */ -#define XE_PVC_IDS(MACRO__, ...) \ - MACRO__(0x0B69, ## __VA_ARGS__), \ - MACRO__(0x0B6E, ## __VA_ARGS__), \ - MACRO__(0x0BD4, ## __VA_ARGS__), \ - MACRO__(0x0BD5, ## __VA_ARGS__), \ - MACRO__(0x0BD6, ## __VA_ARGS__), \ - MACRO__(0x0BD7, ## __VA_ARGS__), \ - MACRO__(0x0BD8, ## __VA_ARGS__), \ - MACRO__(0x0BD9, ## __VA_ARGS__), \ - MACRO__(0x0BDA, ## __VA_ARGS__), \ - MACRO__(0x0BDB, ## __VA_ARGS__), \ - MACRO__(0x0BE0, ## __VA_ARGS__), \ - MACRO__(0x0BE1, ## __VA_ARGS__), \ - MACRO__(0x0BE5, ## __VA_ARGS__) - -#define XE_LNL_IDS(MACRO__, ...) \ - MACRO__(0x6420, ## __VA_ARGS__), \ - MACRO__(0x64A0, ## __VA_ARGS__), \ - MACRO__(0x64B0, ## __VA_ARGS__) - -#define XE_BMG_IDS(MACRO__, ...) \ - MACRO__(0xE202, ## __VA_ARGS__), \ - MACRO__(0xE20B, ## __VA_ARGS__), \ - MACRO__(0xE20C, ## __VA_ARGS__), \ - MACRO__(0xE20D, ## __VA_ARGS__), \ - MACRO__(0xE212, ## __VA_ARGS__) - -#define XE_PTL_IDS(MACRO__, ...) \ - MACRO__(0xB080, ## __VA_ARGS__), \ - MACRO__(0xB081, ## __VA_ARGS__), \ - MACRO__(0xB082, ## __VA_ARGS__), \ - MACRO__(0xB090, ## __VA_ARGS__), \ - MACRO__(0xB091, ## __VA_ARGS__), \ - MACRO__(0xB092, ## __VA_ARGS__), \ - MACRO__(0xB0A0, ## __VA_ARGS__), \ - MACRO__(0xB0A1, ## __VA_ARGS__), \ - MACRO__(0xB0A2, ## __VA_ARGS__), \ - MACRO__(0xB0B0, ## __VA_ARGS__) - -#endif diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index be034be56ba1..ee688d0c029b 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -38,6 +38,7 @@ #define TTM_MAX_BO_PRIORITY 4U #define TTM_NUM_MEM_TYPES 8 +struct dmem_cgroup_device; struct ttm_device; struct ttm_resource_manager; struct ttm_resource; @@ -211,6 +212,11 @@ struct ttm_resource_manager { * bdev->lru_lock. */ uint64_t usage; + + /** + * @cg: &dmem_cgroup_region used for memory accounting, if not NULL. + */ + struct dmem_cgroup_region *cg; }; /** @@ -239,6 +245,7 @@ struct ttm_bus_placement { * @placement: Placement flags. * @bus: Placement on io bus accessible to the CPU * @bo: weak reference to the BO, protected by ttm_device::lru_lock + * @css: cgroup state this resource is charged to * * Structure indicating the placement and space resources used by a * buffer object. @@ -251,6 +258,8 @@ struct ttm_resource { struct ttm_bus_placement bus; struct ttm_buffer_object *bo; + struct dmem_cgroup_pool_state *css; + /** * @lru: Least recently used list, see &ttm_resource_manager.lru */ @@ -432,7 +441,8 @@ void ttm_resource_fini(struct ttm_resource_manager *man, int ttm_resource_alloc(struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource **res); + struct ttm_resource **res, + struct dmem_cgroup_pool_state **ret_limit_pool); void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res); bool ttm_resource_intersects(struct ttm_device *bdev, struct ttm_resource *res, diff --git a/include/dt-bindings/arm/qcom,ids.h b/include/dt-bindings/arm/qcom,ids.h index e850dc3a1ad3..1b3e0176dcb7 100644 --- a/include/dt-bindings/arm/qcom,ids.h +++ b/include/dt-bindings/arm/qcom,ids.h @@ -284,6 +284,7 @@ #define QCOM_ID_QCS9100 667 #define QCOM_ID_QCS8300 674 #define QCOM_ID_QCS8275 675 +#define QCOM_ID_QCS9075 676 #define QCOM_ID_QCS615 680 /* diff --git a/include/dt-bindings/clock/at91.h b/include/dt-bindings/clock/at91.h index 6ede88c3992d..f2a7b7d39c0d 100644 --- a/include/dt-bindings/clock/at91.h +++ b/include/dt-bindings/clock/at91.h @@ -42,6 +42,10 @@ #define PMC_PLLADIV2 (PMC_MAIN + 11) #define PMC_LVDSPLL (PMC_MAIN + 12) +/* SAMA7D65 */ +#define PMC_MCK3 (PMC_MAIN + 13) +#define PMC_MCK5 (PMC_MAIN + 14) + #ifndef AT91_PMC_MOSCS #define AT91_PMC_MOSCS 0 /* MOSCS Flag */ #define AT91_PMC_LOCKA 1 /* PLLA Lock */ @@ -55,4 +59,8 @@ #define AT91_PMC_GCKRDY 24 /* Generated Clocks */ #endif +/* Slow clock. */ +#define SCKC_MD_SLCK 0 +#define SCKC_TD_SLCK 1 + #endif diff --git a/include/dt-bindings/clock/en7523-clk.h b/include/dt-bindings/clock/en7523-clk.h index 717d23a5e5ae..edfa64045f52 100644 --- a/include/dt-bindings/clock/en7523-clk.h +++ b/include/dt-bindings/clock/en7523-clk.h @@ -12,6 +12,6 @@ #define EN7523_CLK_CRYPTO 6 #define EN7523_CLK_PCIE 7 -#define EN7523_NUM_CLOCKS 8 +#define EN7581_CLK_EMMC 8 #endif /* _DT_BINDINGS_CLOCK_AIROHA_EN7523_H_ */ diff --git a/include/dt-bindings/clock/imx93-clock.h b/include/dt-bindings/clock/imx93-clock.h index 6c685067288b..c393fad3a346 100644 --- a/include/dt-bindings/clock/imx93-clock.h +++ b/include/dt-bindings/clock/imx93-clock.h @@ -209,5 +209,6 @@ #define IMX91_CLK_ENET2_REGULAR 204 #define IMX91_CLK_ENET2_REGULAR_GATE 205 #define IMX91_CLK_ENET1_QOS_TSN_GATE 206 +#define IMX93_CLK_SPDIF_IPG 207 #endif diff --git a/include/dt-bindings/clock/qcom,ipq-cmn-pll.h b/include/dt-bindings/clock/qcom,ipq-cmn-pll.h new file mode 100644 index 000000000000..936e92b3b62c --- /dev/null +++ b/include/dt-bindings/clock/qcom,ipq-cmn-pll.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_IPQ_CMN_PLL_H +#define _DT_BINDINGS_CLK_QCOM_IPQ_CMN_PLL_H + +/* CMN PLL core clock. */ +#define CMN_PLL_CLK 0 + +/* The output clocks from CMN PLL of IPQ9574. */ +#define XO_24MHZ_CLK 1 +#define SLEEP_32KHZ_CLK 2 +#define PCS_31P25MHZ_CLK 3 +#define NSS_1200MHZ_CLK 4 +#define PPE_353MHZ_CLK 5 +#define ETH0_50MHZ_CLK 6 +#define ETH1_50MHZ_CLK 7 +#define ETH2_50MHZ_CLK 8 +#define ETH_25MHZ_CLK 9 +#endif diff --git a/include/dt-bindings/clock/qcom,ipq5424-gcc.h b/include/dt-bindings/clock/qcom,ipq5424-gcc.h index 755ce7a71c7c..c15ad16923bd 100644 --- a/include/dt-bindings/clock/qcom,ipq5424-gcc.h +++ b/include/dt-bindings/clock/qcom,ipq5424-gcc.h @@ -12,7 +12,6 @@ #define GPLL2 2 #define GPLL2_OUT_MAIN 3 #define GCC_SLEEP_CLK_SRC 4 -#define GCC_APSS_DBG_CLK 5 #define GCC_USB0_EUD_AT_CLK 6 #define GCC_PCIE0_AXI_M_CLK_SRC 7 #define GCC_PCIE0_AXI_M_CLK 8 @@ -152,5 +151,6 @@ #define GCC_PCIE3_RCHNG_CLK_SRC 142 #define GCC_PCIE3_RCHNG_CLK 143 #define GCC_IM_SLEEP_CLK 144 +#define GCC_XO_CLK 145 #endif diff --git a/include/dt-bindings/clock/qcom,mmcc-msm8960.h b/include/dt-bindings/clock/qcom,mmcc-msm8960.h index 81714fc859c5..717431d735c1 100644 --- a/include/dt-bindings/clock/qcom,mmcc-msm8960.h +++ b/include/dt-bindings/clock/qcom,mmcc-msm8960.h @@ -133,5 +133,7 @@ #define VCAP_CLK 124 #define VCAP_NPL_CLK 125 #define PLL15 126 +#define DSI2_PIXEL_LVDS_SRC 127 +#define LVDS_CLK 128 #endif diff --git a/include/dt-bindings/clock/qcom,qcs615-gcc.h b/include/dt-bindings/clock/qcom,qcs615-gcc.h new file mode 100644 index 000000000000..9704091636b8 --- /dev/null +++ b/include/dt-bindings/clock/qcom,qcs615-gcc.h @@ -0,0 +1,211 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GCC_QCS615_H +#define _DT_BINDINGS_CLK_QCOM_GCC_QCS615_H + +/* GCC clocks */ +#define GPLL0_OUT_AUX2_DIV 0 +#define GPLL3_OUT_AUX2_DIV 1 +#define GPLL0 2 +#define GPLL3 3 +#define GPLL4 4 +#define GPLL6 5 +#define GPLL6_OUT_MAIN 6 +#define GPLL7 7 +#define GPLL8 8 +#define GPLL8_OUT_MAIN 9 +#define GCC_AGGRE_UFS_PHY_AXI_CLK 10 +#define GCC_AGGRE_USB2_SEC_AXI_CLK 11 +#define GCC_AGGRE_USB3_PRIM_AXI_CLK 12 +#define GCC_AHB2PHY_EAST_CLK 13 +#define GCC_AHB2PHY_WEST_CLK 14 +#define GCC_BOOT_ROM_AHB_CLK 15 +#define GCC_CAMERA_AHB_CLK 16 +#define GCC_CAMERA_HF_AXI_CLK 17 +#define GCC_CAMERA_XO_CLK 18 +#define GCC_CE1_AHB_CLK 19 +#define GCC_CE1_AXI_CLK 20 +#define GCC_CE1_CLK 21 +#define GCC_CFG_NOC_USB2_SEC_AXI_CLK 22 +#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK 23 +#define GCC_CPUSS_AHB_CLK 24 +#define GCC_CPUSS_AHB_CLK_SRC 25 +#define GCC_CPUSS_GNOC_CLK 26 +#define GCC_DDRSS_GPU_AXI_CLK 27 +#define GCC_DISP_AHB_CLK 28 +#define GCC_DISP_GPLL0_DIV_CLK_SRC 29 +#define GCC_DISP_HF_AXI_CLK 30 +#define GCC_DISP_XO_CLK 31 +#define GCC_EMAC_AXI_CLK 32 +#define GCC_EMAC_PTP_CLK 33 +#define GCC_EMAC_PTP_CLK_SRC 34 +#define GCC_EMAC_RGMII_CLK 35 +#define GCC_EMAC_RGMII_CLK_SRC 36 +#define GCC_EMAC_SLV_AHB_CLK 37 +#define GCC_GP1_CLK 38 +#define GCC_GP1_CLK_SRC 39 +#define GCC_GP2_CLK 40 +#define GCC_GP2_CLK_SRC 41 +#define GCC_GP3_CLK 42 +#define GCC_GP3_CLK_SRC 43 +#define GCC_GPU_CFG_AHB_CLK 44 +#define GCC_GPU_GPLL0_CLK_SRC 45 +#define GCC_GPU_GPLL0_DIV_CLK_SRC 46 +#define GCC_GPU_IREF_CLK 47 +#define GCC_GPU_MEMNOC_GFX_CLK 48 +#define GCC_GPU_SNOC_DVM_GFX_CLK 49 +#define GCC_PCIE0_PHY_REFGEN_CLK 50 +#define GCC_PCIE_0_AUX_CLK 51 +#define GCC_PCIE_0_AUX_CLK_SRC 52 +#define GCC_PCIE_0_CFG_AHB_CLK 53 +#define GCC_PCIE_0_CLKREF_CLK 54 +#define GCC_PCIE_0_MSTR_AXI_CLK 55 +#define GCC_PCIE_0_PIPE_CLK 56 +#define GCC_PCIE_0_SLV_AXI_CLK 57 +#define GCC_PCIE_0_SLV_Q2A_AXI_CLK 58 +#define GCC_PCIE_PHY_AUX_CLK 59 +#define GCC_PCIE_PHY_REFGEN_CLK_SRC 60 +#define GCC_PDM2_CLK 61 +#define GCC_PDM2_CLK_SRC 62 +#define GCC_PDM_AHB_CLK 63 +#define GCC_PDM_XO4_CLK 64 +#define GCC_PRNG_AHB_CLK 65 +#define GCC_QMIP_CAMERA_NRT_AHB_CLK 66 +#define GCC_QMIP_DISP_AHB_CLK 67 +#define GCC_QMIP_PCIE_AHB_CLK 68 +#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK 69 +#define GCC_QSPI_CNOC_PERIPH_AHB_CLK 70 +#define GCC_QSPI_CORE_CLK 71 +#define GCC_QSPI_CORE_CLK_SRC 72 +#define GCC_QUPV3_WRAP0_CORE_2X_CLK 73 +#define GCC_QUPV3_WRAP0_CORE_CLK 74 +#define GCC_QUPV3_WRAP0_S0_CLK 75 +#define GCC_QUPV3_WRAP0_S0_CLK_SRC 76 +#define GCC_QUPV3_WRAP0_S1_CLK 77 +#define GCC_QUPV3_WRAP0_S1_CLK_SRC 78 +#define GCC_QUPV3_WRAP0_S2_CLK 79 +#define GCC_QUPV3_WRAP0_S2_CLK_SRC 80 +#define GCC_QUPV3_WRAP0_S3_CLK 81 +#define GCC_QUPV3_WRAP0_S3_CLK_SRC 82 +#define GCC_QUPV3_WRAP0_S4_CLK 83 +#define GCC_QUPV3_WRAP0_S4_CLK_SRC 84 +#define GCC_QUPV3_WRAP0_S5_CLK 85 +#define GCC_QUPV3_WRAP0_S5_CLK_SRC 86 +#define GCC_QUPV3_WRAP1_CORE_2X_CLK 87 +#define GCC_QUPV3_WRAP1_CORE_CLK 88 +#define GCC_QUPV3_WRAP1_S0_CLK 89 +#define GCC_QUPV3_WRAP1_S0_CLK_SRC 90 +#define GCC_QUPV3_WRAP1_S1_CLK 91 +#define GCC_QUPV3_WRAP1_S1_CLK_SRC 92 +#define GCC_QUPV3_WRAP1_S2_CLK 93 +#define GCC_QUPV3_WRAP1_S2_CLK_SRC 94 +#define GCC_QUPV3_WRAP1_S3_CLK 95 +#define GCC_QUPV3_WRAP1_S3_CLK_SRC 96 +#define GCC_QUPV3_WRAP1_S4_CLK 97 +#define GCC_QUPV3_WRAP1_S4_CLK_SRC 98 +#define GCC_QUPV3_WRAP1_S5_CLK 99 +#define GCC_QUPV3_WRAP1_S5_CLK_SRC 100 +#define GCC_QUPV3_WRAP_0_M_AHB_CLK 101 +#define GCC_QUPV3_WRAP_0_S_AHB_CLK 102 +#define GCC_QUPV3_WRAP_1_M_AHB_CLK 103 +#define GCC_QUPV3_WRAP_1_S_AHB_CLK 104 +#define GCC_RX1_USB2_CLKREF_CLK 105 +#define GCC_RX3_USB2_CLKREF_CLK 106 +#define GCC_SDCC1_AHB_CLK 107 +#define GCC_SDCC1_APPS_CLK 108 +#define GCC_SDCC1_APPS_CLK_SRC 109 +#define GCC_SDCC1_ICE_CORE_CLK 110 +#define GCC_SDCC1_ICE_CORE_CLK_SRC 111 +#define GCC_SDCC2_AHB_CLK 112 +#define GCC_SDCC2_APPS_CLK 113 +#define GCC_SDCC2_APPS_CLK_SRC 114 +#define GCC_SDR_CORE_CLK 115 +#define GCC_SDR_CSR_HCLK 116 +#define GCC_SDR_PRI_MI2S_CLK 117 +#define GCC_SDR_SEC_MI2S_CLK 118 +#define GCC_SDR_WR0_MEM_CLK 119 +#define GCC_SDR_WR1_MEM_CLK 120 +#define GCC_SDR_WR2_MEM_CLK 121 +#define GCC_SYS_NOC_CPUSS_AHB_CLK 122 +#define GCC_UFS_CARD_CLKREF_CLK 123 +#define GCC_UFS_MEM_CLKREF_CLK 124 +#define GCC_UFS_PHY_AHB_CLK 125 +#define GCC_UFS_PHY_AXI_CLK 126 +#define GCC_UFS_PHY_AXI_CLK_SRC 127 +#define GCC_UFS_PHY_ICE_CORE_CLK 128 +#define GCC_UFS_PHY_ICE_CORE_CLK_SRC 129 +#define GCC_UFS_PHY_PHY_AUX_CLK 130 +#define GCC_UFS_PHY_PHY_AUX_CLK_SRC 131 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK 132 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK 133 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK 134 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC 135 +#define GCC_USB20_SEC_MASTER_CLK 136 +#define GCC_USB20_SEC_MASTER_CLK_SRC 137 +#define GCC_USB20_SEC_MOCK_UTMI_CLK 138 +#define GCC_USB20_SEC_MOCK_UTMI_CLK_SRC 139 +#define GCC_USB20_SEC_SLEEP_CLK 140 +#define GCC_USB2_PRIM_CLKREF_CLK 141 +#define GCC_USB2_SEC_CLKREF_CLK 142 +#define GCC_USB2_SEC_PHY_AUX_CLK 143 +#define GCC_USB2_SEC_PHY_AUX_CLK_SRC 144 +#define GCC_USB2_SEC_PHY_COM_AUX_CLK 145 +#define GCC_USB2_SEC_PHY_PIPE_CLK 146 +#define GCC_USB30_PRIM_MASTER_CLK 147 +#define GCC_USB30_PRIM_MASTER_CLK_SRC 148 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK 149 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC 150 +#define GCC_USB30_PRIM_SLEEP_CLK 151 +#define GCC_USB3_PRIM_CLKREF_CLK 152 +#define GCC_USB3_PRIM_PHY_AUX_CLK 153 +#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC 154 +#define GCC_USB3_PRIM_PHY_COM_AUX_CLK 155 +#define GCC_USB3_PRIM_PHY_PIPE_CLK 156 +#define GCC_USB3_SEC_CLKREF_CLK 157 +#define GCC_VIDEO_AHB_CLK 158 +#define GCC_VIDEO_AXI0_CLK 159 +#define GCC_VIDEO_XO_CLK 160 +#define GCC_VSENSOR_CLK_SRC 161 +#define GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK 162 +#define GCC_UFS_PHY_AXI_HW_CTL_CLK 163 +#define GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK 164 +#define GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK 165 +#define GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK 166 + +/* GCC Resets */ +#define GCC_EMAC_BCR 0 +#define GCC_QUSB2PHY_PRIM_BCR 1 +#define GCC_QUSB2PHY_SEC_BCR 2 +#define GCC_USB30_PRIM_BCR 3 +#define GCC_USB2_PHY_SEC_BCR 4 +#define GCC_USB3_DP_PHY_SEC_BCR 5 +#define GCC_USB3PHY_PHY_SEC_BCR 6 +#define GCC_PCIE_0_BCR 7 +#define GCC_PCIE_0_PHY_BCR 8 +#define GCC_PCIE_PHY_BCR 9 +#define GCC_PCIE_PHY_COM_BCR 10 +#define GCC_UFS_PHY_BCR 11 +#define GCC_USB20_SEC_BCR 12 +#define GCC_USB3_PHY_PRIM_SP0_BCR 13 +#define GCC_USB3PHY_PHY_PRIM_SP0_BCR 14 +#define GCC_SDCC1_BCR 15 +#define GCC_SDCC2_BCR 16 + +/* GCC power domains */ +#define EMAC_GDSC 0 +#define PCIE_0_GDSC 1 +#define UFS_PHY_GDSC 2 +#define USB20_SEC_GDSC 3 +#define USB30_PRIM_GDSC 4 +#define HLOS1_VOTE_AGGRE_NOC_MMU_AUDIO_TBU_GDSC 5 +#define HLOS1_VOTE_AGGRE_NOC_MMU_TBU1_GDSC 6 +#define HLOS1_VOTE_AGGRE_NOC_MMU_TBU2_GDSC 7 +#define HLOS1_VOTE_AGGRE_NOC_MMU_PCIE_TBU_GDSC 8 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC 9 +#define HLOS1_VOTE_MMNOC_MMU_TBU_SF_GDSC 10 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC 11 + +#endif diff --git a/include/dt-bindings/clock/qcom,sm6115-lpasscc.h b/include/dt-bindings/clock/qcom,sm6115-lpasscc.h new file mode 100644 index 000000000000..799274517c9a --- /dev/null +++ b/include/dt-bindings/clock/qcom,sm6115-lpasscc.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2023, Linaro Ltd. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_LPASSCC_SM6115_H +#define _DT_BINDINGS_CLK_QCOM_LPASSCC_SM6115_H + +/* LPASS CC */ +#define LPASS_SWR_TX_CONFIG_CGCR 0 + +/* LPASS_AUDIO CC */ +#define LPASS_AUDIO_SWR_RX_CGCR 0 + +#endif diff --git a/include/dt-bindings/clock/qcom,sm8750-dispcc.h b/include/dt-bindings/clock/qcom,sm8750-dispcc.h new file mode 100644 index 000000000000..dafb5069c96a --- /dev/null +++ b/include/dt-bindings/clock/qcom,sm8750-dispcc.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2022, The Linux Foundation. All rights reserved. + * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2024, Linaro Ltd. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_SM8750_DISP_CC_H +#define _DT_BINDINGS_CLK_QCOM_SM8750_DISP_CC_H + +/* DISP_CC clocks */ +#define DISP_CC_ESYNC0_CLK 0 +#define DISP_CC_ESYNC0_CLK_SRC 1 +#define DISP_CC_ESYNC1_CLK 2 +#define DISP_CC_ESYNC1_CLK_SRC 3 +#define DISP_CC_MDSS_ACCU_SHIFT_CLK 4 +#define DISP_CC_MDSS_AHB1_CLK 5 +#define DISP_CC_MDSS_AHB_CLK 6 +#define DISP_CC_MDSS_AHB_CLK_SRC 7 +#define DISP_CC_MDSS_BYTE0_CLK 8 +#define DISP_CC_MDSS_BYTE0_CLK_SRC 9 +#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC 10 +#define DISP_CC_MDSS_BYTE0_INTF_CLK 11 +#define DISP_CC_MDSS_BYTE1_CLK 12 +#define DISP_CC_MDSS_BYTE1_CLK_SRC 13 +#define DISP_CC_MDSS_BYTE1_DIV_CLK_SRC 14 +#define DISP_CC_MDSS_BYTE1_INTF_CLK 15 +#define DISP_CC_MDSS_DPTX0_AUX_CLK 16 +#define DISP_CC_MDSS_DPTX0_AUX_CLK_SRC 17 +#define DISP_CC_MDSS_DPTX0_CRYPTO_CLK 18 +#define DISP_CC_MDSS_DPTX0_LINK_CLK 19 +#define DISP_CC_MDSS_DPTX0_LINK_CLK_SRC 20 +#define DISP_CC_MDSS_DPTX0_LINK_DIV_CLK_SRC 21 +#define DISP_CC_MDSS_DPTX0_LINK_INTF_CLK 22 +#define DISP_CC_MDSS_DPTX0_PIXEL0_CLK 23 +#define DISP_CC_MDSS_DPTX0_PIXEL0_CLK_SRC 24 +#define DISP_CC_MDSS_DPTX0_PIXEL1_CLK 25 +#define DISP_CC_MDSS_DPTX0_PIXEL1_CLK_SRC 26 +#define DISP_CC_MDSS_DPTX0_USB_ROUTER_LINK_INTF_CLK 27 +#define DISP_CC_MDSS_DPTX1_AUX_CLK 28 +#define DISP_CC_MDSS_DPTX1_AUX_CLK_SRC 29 +#define DISP_CC_MDSS_DPTX1_CRYPTO_CLK 30 +#define DISP_CC_MDSS_DPTX1_LINK_CLK 31 +#define DISP_CC_MDSS_DPTX1_LINK_CLK_SRC 32 +#define DISP_CC_MDSS_DPTX1_LINK_DIV_CLK_SRC 33 +#define DISP_CC_MDSS_DPTX1_LINK_INTF_CLK 34 +#define DISP_CC_MDSS_DPTX1_PIXEL0_CLK 35 +#define DISP_CC_MDSS_DPTX1_PIXEL0_CLK_SRC 36 +#define DISP_CC_MDSS_DPTX1_PIXEL1_CLK 37 +#define DISP_CC_MDSS_DPTX1_PIXEL1_CLK_SRC 38 +#define DISP_CC_MDSS_DPTX1_USB_ROUTER_LINK_INTF_CLK 39 +#define DISP_CC_MDSS_DPTX2_AUX_CLK 40 +#define DISP_CC_MDSS_DPTX2_AUX_CLK_SRC 41 +#define DISP_CC_MDSS_DPTX2_CRYPTO_CLK 42 +#define DISP_CC_MDSS_DPTX2_LINK_CLK 43 +#define DISP_CC_MDSS_DPTX2_LINK_CLK_SRC 44 +#define DISP_CC_MDSS_DPTX2_LINK_DIV_CLK_SRC 45 +#define DISP_CC_MDSS_DPTX2_LINK_INTF_CLK 46 +#define DISP_CC_MDSS_DPTX2_PIXEL0_CLK 47 +#define DISP_CC_MDSS_DPTX2_PIXEL0_CLK_SRC 48 +#define DISP_CC_MDSS_DPTX2_PIXEL1_CLK 49 +#define DISP_CC_MDSS_DPTX2_PIXEL1_CLK_SRC 50 +#define DISP_CC_MDSS_DPTX3_AUX_CLK 51 +#define DISP_CC_MDSS_DPTX3_AUX_CLK_SRC 52 +#define DISP_CC_MDSS_DPTX3_CRYPTO_CLK 53 +#define DISP_CC_MDSS_DPTX3_LINK_CLK 54 +#define DISP_CC_MDSS_DPTX3_LINK_CLK_SRC 55 +#define DISP_CC_MDSS_DPTX3_LINK_DIV_CLK_SRC 56 +#define DISP_CC_MDSS_DPTX3_LINK_INTF_CLK 57 +#define DISP_CC_MDSS_DPTX3_PIXEL0_CLK 58 +#define DISP_CC_MDSS_DPTX3_PIXEL0_CLK_SRC 59 +#define DISP_CC_MDSS_ESC0_CLK 60 +#define DISP_CC_MDSS_ESC0_CLK_SRC 61 +#define DISP_CC_MDSS_ESC1_CLK 62 +#define DISP_CC_MDSS_ESC1_CLK_SRC 63 +#define DISP_CC_MDSS_MDP1_CLK 64 +#define DISP_CC_MDSS_MDP_CLK 65 +#define DISP_CC_MDSS_MDP_CLK_SRC 66 +#define DISP_CC_MDSS_MDP_LUT1_CLK 67 +#define DISP_CC_MDSS_MDP_LUT_CLK 68 +#define DISP_CC_MDSS_NON_GDSC_AHB_CLK 69 +#define DISP_CC_MDSS_PCLK0_CLK 70 +#define DISP_CC_MDSS_PCLK0_CLK_SRC 71 +#define DISP_CC_MDSS_PCLK1_CLK 72 +#define DISP_CC_MDSS_PCLK1_CLK_SRC 73 +#define DISP_CC_MDSS_PCLK2_CLK 74 +#define DISP_CC_MDSS_PCLK2_CLK_SRC 75 +#define DISP_CC_MDSS_RSCC_AHB_CLK 76 +#define DISP_CC_MDSS_RSCC_VSYNC_CLK 77 +#define DISP_CC_MDSS_VSYNC1_CLK 78 +#define DISP_CC_MDSS_VSYNC_CLK 79 +#define DISP_CC_MDSS_VSYNC_CLK_SRC 80 +#define DISP_CC_OSC_CLK 81 +#define DISP_CC_OSC_CLK_SRC 82 +#define DISP_CC_PLL0 83 +#define DISP_CC_PLL1 84 +#define DISP_CC_PLL2 85 +#define DISP_CC_SLEEP_CLK 86 +#define DISP_CC_SLEEP_CLK_SRC 87 +#define DISP_CC_XO_CLK 88 +#define DISP_CC_XO_CLK_SRC 89 + +/* DISP_CC resets */ +#define DISP_CC_MDSS_CORE_BCR 0 +#define DISP_CC_MDSS_CORE_INT2_BCR 1 +#define DISP_CC_MDSS_RSCC_BCR 2 + +/* DISP_CC GDSCR */ +#define MDSS_GDSC 0 +#define MDSS_INT2_GDSC 1 + +#endif diff --git a/include/dt-bindings/clock/qcom,sm8750-gcc.h b/include/dt-bindings/clock/qcom,sm8750-gcc.h new file mode 100644 index 000000000000..e234595d7f42 --- /dev/null +++ b/include/dt-bindings/clock/qcom,sm8750-gcc.h @@ -0,0 +1,226 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GCC_SM8750_H +#define _DT_BINDINGS_CLK_QCOM_GCC_SM8750_H + +/* GCC clocks */ +#define GCC_AGGRE_NOC_PCIE_AXI_CLK 0 +#define GCC_AGGRE_UFS_PHY_AXI_CLK 1 +#define GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK 2 +#define GCC_AGGRE_USB3_PRIM_AXI_CLK 3 +#define GCC_BOOT_ROM_AHB_CLK 4 +#define GCC_CAM_BIST_MCLK_AHB_CLK 5 +#define GCC_CAMERA_AHB_CLK 6 +#define GCC_CAMERA_HF_AXI_CLK 7 +#define GCC_CAMERA_SF_AXI_CLK 8 +#define GCC_CAMERA_XO_CLK 9 +#define GCC_CFG_NOC_PCIE_ANOC_AHB_CLK 10 +#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK 11 +#define GCC_CNOC_PCIE_SF_AXI_CLK 12 +#define GCC_DDRSS_GPU_AXI_CLK 13 +#define GCC_DDRSS_PCIE_SF_QTB_CLK 14 +#define GCC_DISP_AHB_CLK 15 +#define GCC_DISP_HF_AXI_CLK 16 +#define GCC_EVA_AHB_CLK 17 +#define GCC_EVA_AXI0_CLK 18 +#define GCC_EVA_AXI0C_CLK 19 +#define GCC_EVA_XO_CLK 20 +#define GCC_GP1_CLK 21 +#define GCC_GP1_CLK_SRC 22 +#define GCC_GP2_CLK 23 +#define GCC_GP2_CLK_SRC 24 +#define GCC_GP3_CLK 25 +#define GCC_GP3_CLK_SRC 26 +#define GCC_GPLL0 27 +#define GCC_GPLL0_OUT_EVEN 28 +#define GCC_GPLL1 29 +#define GCC_GPLL4 30 +#define GCC_GPLL7 31 +#define GCC_GPLL9 32 +#define GCC_GPU_CFG_AHB_CLK 33 +#define GCC_GPU_GEMNOC_GFX_CLK 34 +#define GCC_GPU_GPLL0_CLK_SRC 35 +#define GCC_GPU_GPLL0_DIV_CLK_SRC 36 +#define GCC_PCIE_0_AUX_CLK 37 +#define GCC_PCIE_0_AUX_CLK_SRC 38 +#define GCC_PCIE_0_CFG_AHB_CLK 39 +#define GCC_PCIE_0_MSTR_AXI_CLK 40 +#define GCC_PCIE_0_PHY_RCHNG_CLK 41 +#define GCC_PCIE_0_PHY_RCHNG_CLK_SRC 42 +#define GCC_PCIE_0_PIPE_CLK 43 +#define GCC_PCIE_0_PIPE_CLK_SRC 44 +#define GCC_PCIE_0_SLV_AXI_CLK 45 +#define GCC_PCIE_0_SLV_Q2A_AXI_CLK 46 +#define GCC_PCIE_RSCC_CFG_AHB_CLK 47 +#define GCC_PCIE_RSCC_XO_CLK 48 +#define GCC_PDM2_CLK 49 +#define GCC_PDM2_CLK_SRC 50 +#define GCC_PDM_AHB_CLK 51 +#define GCC_PDM_XO4_CLK 52 +#define GCC_QMIP_CAMERA_CMD_AHB_CLK 53 +#define GCC_QMIP_CAMERA_NRT_AHB_CLK 54 +#define GCC_QMIP_CAMERA_RT_AHB_CLK 55 +#define GCC_QMIP_GPU_AHB_CLK 56 +#define GCC_QMIP_PCIE_AHB_CLK 57 +#define GCC_QMIP_VIDEO_CV_CPU_AHB_CLK 58 +#define GCC_QMIP_VIDEO_CVP_AHB_CLK 59 +#define GCC_QMIP_VIDEO_V_CPU_AHB_CLK 60 +#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK 61 +#define GCC_QUPV3_I2C_CORE_CLK 62 +#define GCC_QUPV3_I2C_S0_CLK 63 +#define GCC_QUPV3_I2C_S0_CLK_SRC 64 +#define GCC_QUPV3_I2C_S1_CLK 65 +#define GCC_QUPV3_I2C_S1_CLK_SRC 66 +#define GCC_QUPV3_I2C_S2_CLK 67 +#define GCC_QUPV3_I2C_S2_CLK_SRC 68 +#define GCC_QUPV3_I2C_S3_CLK 69 +#define GCC_QUPV3_I2C_S3_CLK_SRC 70 +#define GCC_QUPV3_I2C_S4_CLK 71 +#define GCC_QUPV3_I2C_S4_CLK_SRC 72 +#define GCC_QUPV3_I2C_S5_CLK 73 +#define GCC_QUPV3_I2C_S5_CLK_SRC 74 +#define GCC_QUPV3_I2C_S6_CLK 75 +#define GCC_QUPV3_I2C_S6_CLK_SRC 76 +#define GCC_QUPV3_I2C_S7_CLK 77 +#define GCC_QUPV3_I2C_S7_CLK_SRC 78 +#define GCC_QUPV3_I2C_S8_CLK 79 +#define GCC_QUPV3_I2C_S8_CLK_SRC 80 +#define GCC_QUPV3_I2C_S9_CLK 81 +#define GCC_QUPV3_I2C_S9_CLK_SRC 82 +#define GCC_QUPV3_I2C_S_AHB_CLK 83 +#define GCC_QUPV3_WRAP1_CORE_2X_CLK 84 +#define GCC_QUPV3_WRAP1_CORE_CLK 85 +#define GCC_QUPV3_WRAP1_QSPI_REF_CLK 86 +#define GCC_QUPV3_WRAP1_QSPI_REF_CLK_SRC 87 +#define GCC_QUPV3_WRAP1_S0_CLK 88 +#define GCC_QUPV3_WRAP1_S0_CLK_SRC 89 +#define GCC_QUPV3_WRAP1_S1_CLK 90 +#define GCC_QUPV3_WRAP1_S1_CLK_SRC 91 +#define GCC_QUPV3_WRAP1_S2_CLK 92 +#define GCC_QUPV3_WRAP1_S2_CLK_SRC 93 +#define GCC_QUPV3_WRAP1_S3_CLK 94 +#define GCC_QUPV3_WRAP1_S3_CLK_SRC 95 +#define GCC_QUPV3_WRAP1_S4_CLK 96 +#define GCC_QUPV3_WRAP1_S4_CLK_SRC 97 +#define GCC_QUPV3_WRAP1_S5_CLK 98 +#define GCC_QUPV3_WRAP1_S5_CLK_SRC 99 +#define GCC_QUPV3_WRAP1_S6_CLK 100 +#define GCC_QUPV3_WRAP1_S6_CLK_SRC 101 +#define GCC_QUPV3_WRAP1_S7_CLK 102 +#define GCC_QUPV3_WRAP1_S7_CLK_SRC 103 +#define GCC_QUPV3_WRAP2_CORE_2X_CLK 104 +#define GCC_QUPV3_WRAP2_CORE_CLK 105 +#define GCC_QUPV3_WRAP2_IBI_CTRL_0_CLK_SRC 106 +#define GCC_QUPV3_WRAP2_IBI_CTRL_2_CLK 107 +#define GCC_QUPV3_WRAP2_IBI_CTRL_3_CLK 108 +#define GCC_QUPV3_WRAP2_S0_CLK 109 +#define GCC_QUPV3_WRAP2_S0_CLK_SRC 110 +#define GCC_QUPV3_WRAP2_S1_CLK 111 +#define GCC_QUPV3_WRAP2_S1_CLK_SRC 112 +#define GCC_QUPV3_WRAP2_S2_CLK 113 +#define GCC_QUPV3_WRAP2_S2_CLK_SRC 114 +#define GCC_QUPV3_WRAP2_S3_CLK 115 +#define GCC_QUPV3_WRAP2_S3_CLK_SRC 116 +#define GCC_QUPV3_WRAP2_S4_CLK 117 +#define GCC_QUPV3_WRAP2_S4_CLK_SRC 118 +#define GCC_QUPV3_WRAP2_S5_CLK 119 +#define GCC_QUPV3_WRAP2_S5_CLK_SRC 120 +#define GCC_QUPV3_WRAP2_S6_CLK 121 +#define GCC_QUPV3_WRAP2_S6_CLK_SRC 122 +#define GCC_QUPV3_WRAP2_S7_CLK 123 +#define GCC_QUPV3_WRAP2_S7_CLK_SRC 124 +#define GCC_QUPV3_WRAP_1_M_AHB_CLK 125 +#define GCC_QUPV3_WRAP_1_S_AHB_CLK 126 +#define GCC_QUPV3_WRAP_2_IBI_2_AHB_CLK 127 +#define GCC_QUPV3_WRAP_2_IBI_3_AHB_CLK 128 +#define GCC_QUPV3_WRAP_2_M_AHB_CLK 129 +#define GCC_QUPV3_WRAP_2_S_AHB_CLK 130 +#define GCC_SDCC2_AHB_CLK 131 +#define GCC_SDCC2_APPS_CLK 132 +#define GCC_SDCC2_APPS_CLK_SRC 133 +#define GCC_SDCC4_AHB_CLK 134 +#define GCC_SDCC4_APPS_CLK 135 +#define GCC_SDCC4_APPS_CLK_SRC 136 +#define GCC_UFS_PHY_AHB_CLK 137 +#define GCC_UFS_PHY_AXI_CLK 138 +#define GCC_UFS_PHY_AXI_CLK_SRC 139 +#define GCC_UFS_PHY_AXI_HW_CTL_CLK 140 +#define GCC_UFS_PHY_ICE_CORE_CLK 141 +#define GCC_UFS_PHY_ICE_CORE_CLK_SRC 142 +#define GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK 143 +#define GCC_UFS_PHY_PHY_AUX_CLK 144 +#define GCC_UFS_PHY_PHY_AUX_CLK_SRC 145 +#define GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK 146 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK 147 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK_SRC 148 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK 149 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK_SRC 150 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK 151 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK_SRC 152 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK 153 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC 154 +#define GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK 155 +#define GCC_USB30_PRIM_MASTER_CLK 156 +#define GCC_USB30_PRIM_MASTER_CLK_SRC 157 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK 158 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC 159 +#define GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC 160 +#define GCC_USB30_PRIM_SLEEP_CLK 161 +#define GCC_USB3_PRIM_PHY_AUX_CLK 162 +#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC 163 +#define GCC_USB3_PRIM_PHY_COM_AUX_CLK 164 +#define GCC_USB3_PRIM_PHY_PIPE_CLK 165 +#define GCC_USB3_PRIM_PHY_PIPE_CLK_SRC 166 +#define GCC_VIDEO_AHB_CLK 167 +#define GCC_VIDEO_AXI0_CLK 168 +#define GCC_VIDEO_AXI1_CLK 169 +#define GCC_VIDEO_XO_CLK 170 + +/* GCC power domains */ +#define GCC_PCIE_0_GDSC 0 +#define GCC_PCIE_0_PHY_GDSC 1 +#define GCC_UFS_MEM_PHY_GDSC 2 +#define GCC_UFS_PHY_GDSC 3 +#define GCC_USB30_PRIM_GDSC 4 +#define GCC_USB3_PHY_GDSC 5 + +/* GCC resets */ +#define GCC_CAMERA_BCR 0 +#define GCC_DISPLAY_BCR 1 +#define GCC_EVA_BCR 2 +#define GCC_GPU_BCR 3 +#define GCC_PCIE_0_BCR 4 +#define GCC_PCIE_0_LINK_DOWN_BCR 5 +#define GCC_PCIE_0_NOCSR_COM_PHY_BCR 6 +#define GCC_PCIE_0_PHY_BCR 7 +#define GCC_PCIE_0_PHY_NOCSR_COM_PHY_BCR 8 +#define GCC_PCIE_PHY_BCR 9 +#define GCC_PCIE_PHY_CFG_AHB_BCR 10 +#define GCC_PCIE_PHY_COM_BCR 11 +#define GCC_PCIE_RSCC_BCR 12 +#define GCC_PDM_BCR 13 +#define GCC_QUPV3_WRAPPER_1_BCR 14 +#define GCC_QUPV3_WRAPPER_2_BCR 15 +#define GCC_QUPV3_WRAPPER_I2C_BCR 16 +#define GCC_QUSB2PHY_PRIM_BCR 17 +#define GCC_QUSB2PHY_SEC_BCR 18 +#define GCC_SDCC2_BCR 19 +#define GCC_SDCC4_BCR 20 +#define GCC_UFS_PHY_BCR 21 +#define GCC_USB30_PRIM_BCR 22 +#define GCC_USB3_DP_PHY_PRIM_BCR 23 +#define GCC_USB3_DP_PHY_SEC_BCR 24 +#define GCC_USB3_PHY_PRIM_BCR 25 +#define GCC_USB3_PHY_SEC_BCR 26 +#define GCC_USB3PHY_PHY_PRIM_BCR 27 +#define GCC_USB3PHY_PHY_SEC_BCR 28 +#define GCC_VIDEO_AXI0_CLK_ARES 29 +#define GCC_VIDEO_AXI1_CLK_ARES 30 +#define GCC_VIDEO_BCR 31 +#define GCC_EVA_AXI0_CLK_ARES 32 +#define GCC_EVA_AXI0C_CLK_ARES 33 + +#endif diff --git a/include/dt-bindings/clock/qcom,sm8750-tcsr.h b/include/dt-bindings/clock/qcom,sm8750-tcsr.h new file mode 100644 index 000000000000..1c502ac7c7f4 --- /dev/null +++ b/include/dt-bindings/clock/qcom,sm8750-tcsr.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_TCSR_CC_SM8750_H +#define _DT_BINDINGS_CLK_QCOM_TCSR_CC_SM8750_H + +/* TCSR_CC clocks */ +#define TCSR_PCIE_0_CLKREF_EN 0 +#define TCSR_UFS_CLKREF_EN 1 +#define TCSR_USB2_CLKREF_EN 2 +#define TCSR_USB3_CLKREF_EN 3 + +#endif diff --git a/include/dt-bindings/clock/qcom,x1e80100-gpucc.h b/include/dt-bindings/clock/qcom,x1e80100-gpucc.h index 61a3a8f3ac43..27b8f50541fd 100644 --- a/include/dt-bindings/clock/qcom,x1e80100-gpucc.h +++ b/include/dt-bindings/clock/qcom,x1e80100-gpucc.h @@ -33,9 +33,22 @@ #define GPU_CC_SLEEP_CLK 23 #define GPU_CC_XO_CLK_SRC 24 #define GPU_CC_XO_DIV_CLK_SRC 25 +#define GPU_CC_CX_ACCU_SHIFT_CLK 26 +#define GPU_CC_GX_ACCU_SHIFT_CLK 27 /* GDSCs */ #define GPU_CX_GDSC 0 #define GPU_GX_GDSC 1 +/* GPU_CC resets */ +#define GPU_CC_ACD_BCR 0 +#define GPU_CC_CB_BCR 1 +#define GPU_CC_CX_BCR 2 +#define GPU_CC_FAST_HUB_BCR 3 +#define GPU_CC_FF_BCR 4 +#define GPU_CC_GFX3D_AON_BCR 5 +#define GPU_CC_GMU_BCR 6 +#define GPU_CC_GX_BCR 7 +#define GPU_CC_XO_BCR 8 + #endif diff --git a/include/dt-bindings/clock/renesas,r9a08g045-vbattb.h b/include/dt-bindings/clock/renesas,r9a08g045-vbattb.h index 67774eafad06..4cc8fc34b23c 100644 --- a/include/dt-bindings/clock/renesas,r9a08g045-vbattb.h +++ b/include/dt-bindings/clock/renesas,r9a08g045-vbattb.h @@ -2,12 +2,12 @@ * * Copyright (C) 2024 Renesas Electronics Corp. */ -#ifndef __DT_BINDINGS_CLOCK_R9A08G045_VBATTB_H__ -#define __DT_BINDINGS_CLOCK_R9A08G045_VBATTB_H__ +#ifndef __DT_BINDINGS_CLOCK_RENESAS_R9A08G045_VBATTB_H__ +#define __DT_BINDINGS_CLOCK_RENESAS_R9A08G045_VBATTB_H__ #define VBATTB_XC 0 #define VBATTB_XBYP 1 #define VBATTB_MUX 2 #define VBATTB_VBATTCLK 3 -#endif /* __DT_BINDINGS_CLOCK_R9A08G045_VBATTB_H__ */ +#endif /* __DT_BINDINGS_CLOCK_RENESAS_R9A08G045_VBATTB_H__ */ diff --git a/include/dt-bindings/clock/renesas,r9a09g047-cpg.h b/include/dt-bindings/clock/renesas,r9a09g047-cpg.h new file mode 100644 index 000000000000..1d031bf6bf03 --- /dev/null +++ b/include/dt-bindings/clock/renesas,r9a09g047-cpg.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + * + * Copyright (C) 2024 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_CLOCK_RENESAS_R9A09G047_CPG_H__ +#define __DT_BINDINGS_CLOCK_RENESAS_R9A09G047_CPG_H__ + +#include + +/* Core Clock list */ +#define R9A09G047_SYS_0_PCLK 0 +#define R9A09G047_CA55_0_CORECLK0 1 +#define R9A09G047_CA55_0_CORECLK1 2 +#define R9A09G047_CA55_0_CORECLK2 3 +#define R9A09G047_CA55_0_CORECLK3 4 +#define R9A09G047_CA55_0_PERIPHCLK 5 +#define R9A09G047_CM33_CLK0 6 +#define R9A09G047_CST_0_SWCLKTCK 7 +#define R9A09G047_IOTOP_0_SHCLK 8 + +#endif /* __DT_BINDINGS_CLOCK_RENESAS_R9A09G047_CPG_H__ */ diff --git a/include/dt-bindings/clock/samsung,exynos990.h b/include/dt-bindings/clock/samsung,exynos990.h new file mode 100644 index 000000000000..307215a3f3ed --- /dev/null +++ b/include/dt-bindings/clock/samsung,exynos990.h @@ -0,0 +1,236 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2024 Igor Belwon + * + * Device Tree binding constants for Exynos990 clock controller. + */ + +#ifndef _DT_BINDINGS_CLOCK_EXYNOS_990_H +#define _DT_BINDINGS_CLOCK_EXYNOS_990_H + +/* CMU_TOP */ +#define CLK_FOUT_SHARED0_PLL 1 +#define CLK_FOUT_SHARED1_PLL 2 +#define CLK_FOUT_SHARED2_PLL 3 +#define CLK_FOUT_SHARED3_PLL 4 +#define CLK_FOUT_SHARED4_PLL 5 +#define CLK_FOUT_G3D_PLL 6 +#define CLK_FOUT_MMC_PLL 7 +#define CLK_MOUT_PLL_SHARED0 8 +#define CLK_MOUT_PLL_SHARED1 9 +#define CLK_MOUT_PLL_SHARED2 10 +#define CLK_MOUT_PLL_SHARED3 11 +#define CLK_MOUT_PLL_SHARED4 12 +#define CLK_MOUT_PLL_MMC 13 +#define CLK_MOUT_PLL_G3D 14 +#define CLK_MOUT_CMU_APM_BUS 15 +#define CLK_MOUT_CMU_AUD_CPU 16 +#define CLK_MOUT_CMU_BUS0_BUS 17 +#define CLK_MOUT_CMU_BUS1_BUS 18 +#define CLK_MOUT_CMU_BUS1_SSS 19 +#define CLK_MOUT_CMU_CIS_CLK0 20 +#define CLK_MOUT_CMU_CIS_CLK1 21 +#define CLK_MOUT_CMU_CIS_CLK2 22 +#define CLK_MOUT_CMU_CIS_CLK3 23 +#define CLK_MOUT_CMU_CIS_CLK4 24 +#define CLK_MOUT_CMU_CIS_CLK5 25 +#define CLK_MOUT_CMU_CMU_BOOST 26 +#define CLK_MOUT_CMU_CORE_BUS 27 +#define CLK_MOUT_CMU_CPUCL0_DBG_BUS 28 +#define CLK_MOUT_CMU_CPUCL0_SWITCH 29 +#define CLK_MOUT_CMU_CPUCL1_SWITCH 30 +#define CLK_MOUT_CMU_CPUCL2_BUSP 31 +#define CLK_MOUT_CMU_CPUCL2_SWITCH 32 +#define CLK_MOUT_CMU_CSIS_BUS 33 +#define CLK_MOUT_CMU_CSIS_OIS_MCU 34 +#define CLK_MOUT_CMU_DNC_BUS 35 +#define CLK_MOUT_CMU_DNC_BUSM 36 +#define CLK_MOUT_CMU_DNS_BUS 37 +#define CLK_MOUT_CMU_DPU 38 +#define CLK_MOUT_CMU_DPU_ALT 39 +#define CLK_MOUT_CMU_DSP_BUS 40 +#define CLK_MOUT_CMU_G2D_G2D 41 +#define CLK_MOUT_CMU_G2D_MSCL 42 +#define CLK_MOUT_CMU_HPM 43 +#define CLK_MOUT_CMU_HSI0_BUS 44 +#define CLK_MOUT_CMU_HSI0_DPGTC 45 +#define CLK_MOUT_CMU_HSI0_USB31DRD 46 +#define CLK_MOUT_CMU_HSI0_USBDP_DEBUG 47 +#define CLK_MOUT_CMU_HSI1_BUS 48 +#define CLK_MOUT_CMU_HSI1_MMC_CARD 49 +#define CLK_MOUT_CMU_HSI1_PCIE 50 +#define CLK_MOUT_CMU_HSI1_UFS_CARD 51 +#define CLK_MOUT_CMU_HSI1_UFS_EMBD 52 +#define CLK_MOUT_CMU_HSI2_BUS 53 +#define CLK_MOUT_CMU_HSI2_PCIE 54 +#define CLK_MOUT_CMU_IPP_BUS 55 +#define CLK_MOUT_CMU_ITP_BUS 56 +#define CLK_MOUT_CMU_MCSC_BUS 57 +#define CLK_MOUT_CMU_MCSC_GDC 58 +#define CLK_MOUT_CMU_CMU_BOOST_CPU 59 +#define CLK_MOUT_CMU_MFC0_MFC0 60 +#define CLK_MOUT_CMU_MFC0_WFD 61 +#define CLK_MOUT_CMU_MIF_BUSP 62 +#define CLK_MOUT_CMU_MIF_SWITCH 63 +#define CLK_MOUT_CMU_NPU_BUS 64 +#define CLK_MOUT_CMU_PERIC0_BUS 65 +#define CLK_MOUT_CMU_PERIC0_IP 66 +#define CLK_MOUT_CMU_PERIC1_BUS 67 +#define CLK_MOUT_CMU_PERIC1_IP 68 +#define CLK_MOUT_CMU_PERIS_BUS 69 +#define CLK_MOUT_CMU_SSP_BUS 70 +#define CLK_MOUT_CMU_TNR_BUS 71 +#define CLK_MOUT_CMU_VRA_BUS 72 +#define CLK_DOUT_CMU_APM_BUS 73 +#define CLK_DOUT_CMU_AUD_CPU 74 +#define CLK_DOUT_CMU_BUS0_BUS 75 +#define CLK_DOUT_CMU_BUS1_BUS 76 +#define CLK_DOUT_CMU_BUS1_SSS 77 +#define CLK_DOUT_CMU_CIS_CLK0 78 +#define CLK_DOUT_CMU_CIS_CLK1 79 +#define CLK_DOUT_CMU_CIS_CLK2 80 +#define CLK_DOUT_CMU_CIS_CLK3 81 +#define CLK_DOUT_CMU_CIS_CLK4 82 +#define CLK_DOUT_CMU_CIS_CLK5 83 +#define CLK_DOUT_CMU_CMU_BOOST 84 +#define CLK_DOUT_CMU_CORE_BUS 85 +#define CLK_DOUT_CMU_CPUCL0_DBG_BUS 86 +#define CLK_DOUT_CMU_CPUCL0_SWITCH 87 +#define CLK_DOUT_CMU_CPUCL1_SWITCH 88 +#define CLK_DOUT_CMU_CPUCL2_BUSP 89 +#define CLK_DOUT_CMU_CPUCL2_SWITCH 90 +#define CLK_DOUT_CMU_CSIS_BUS 91 +#define CLK_DOUT_CMU_CSIS_OIS_MCU 92 +#define CLK_DOUT_CMU_DNC_BUS 93 +#define CLK_DOUT_CMU_DNC_BUSM 94 +#define CLK_DOUT_CMU_DNS_BUS 95 +#define CLK_DOUT_CMU_DSP_BUS 96 +#define CLK_DOUT_CMU_G2D_G2D 97 +#define CLK_DOUT_CMU_G2D_MSCL 98 +#define CLK_DOUT_CMU_G3D_SWITCH 99 +#define CLK_DOUT_CMU_HPM 100 +#define CLK_DOUT_CMU_HSI0_BUS 101 +#define CLK_DOUT_CMU_HSI0_DPGTC 102 +#define CLK_DOUT_CMU_HSI0_USB31DRD 103 +#define CLK_DOUT_CMU_HSI0_USBDP_DEBUG 104 +#define CLK_DOUT_CMU_HSI1_BUS 105 +#define CLK_DOUT_CMU_HSI1_MMC_CARD 106 +#define CLK_DOUT_CMU_HSI1_PCIE 107 +#define CLK_DOUT_CMU_HSI1_UFS_CARD 108 +#define CLK_DOUT_CMU_HSI1_UFS_EMBD 109 +#define CLK_DOUT_CMU_HSI2_BUS 110 +#define CLK_DOUT_CMU_HSI2_PCIE 111 +#define CLK_DOUT_CMU_IPP_BUS 112 +#define CLK_DOUT_CMU_ITP_BUS 113 +#define CLK_DOUT_CMU_MCSC_BUS 114 +#define CLK_DOUT_CMU_MCSC_GDC 115 +#define CLK_DOUT_CMU_CMU_BOOST_CPU 116 +#define CLK_DOUT_CMU_MFC0_MFC0 117 +#define CLK_DOUT_CMU_MFC0_WFD 118 +#define CLK_DOUT_CMU_MIF_BUSP 119 +#define CLK_DOUT_CMU_NPU_BUS 120 +#define CLK_DOUT_CMU_OTP 121 +#define CLK_DOUT_CMU_PERIC0_BUS 122 +#define CLK_DOUT_CMU_PERIC0_IP 123 +#define CLK_DOUT_CMU_PERIC1_BUS 124 +#define CLK_DOUT_CMU_PERIC1_IP 125 +#define CLK_DOUT_CMU_PERIS_BUS 126 +#define CLK_DOUT_CMU_SSP_BUS 127 +#define CLK_DOUT_CMU_TNR_BUS 128 +#define CLK_DOUT_CMU_VRA_BUS 129 +#define CLK_DOUT_CMU_DPU 130 +#define CLK_DOUT_CMU_DPU_ALT 131 +#define CLK_DOUT_CMU_SHARED0_DIV2 132 +#define CLK_DOUT_CMU_SHARED0_DIV3 133 +#define CLK_DOUT_CMU_SHARED0_DIV4 134 +#define CLK_DOUT_CMU_SHARED1_DIV2 135 +#define CLK_DOUT_CMU_SHARED1_DIV3 136 +#define CLK_DOUT_CMU_SHARED1_DIV4 137 +#define CLK_DOUT_CMU_SHARED2_DIV2 138 +#define CLK_DOUT_CMU_SHARED4_DIV2 139 +#define CLK_DOUT_CMU_SHARED4_DIV3 140 +#define CLK_DOUT_CMU_SHARED4_DIV4 141 +#define CLK_GOUT_CMU_G3D_BUS 142 +#define CLK_GOUT_CMU_MIF_SWITCH 143 +#define CLK_GOUT_CMU_APM_BUS 144 +#define CLK_GOUT_CMU_AUD_CPU 145 +#define CLK_GOUT_CMU_BUS0_BUS 146 +#define CLK_GOUT_CMU_BUS1_BUS 147 +#define CLK_GOUT_CMU_BUS1_SSS 148 +#define CLK_GOUT_CMU_CIS_CLK0 149 +#define CLK_GOUT_CMU_CIS_CLK1 150 +#define CLK_GOUT_CMU_CIS_CLK2 151 +#define CLK_GOUT_CMU_CIS_CLK3 152 +#define CLK_GOUT_CMU_CIS_CLK4 153 +#define CLK_GOUT_CMU_CIS_CLK5 154 +#define CLK_GOUT_CMU_CORE_BUS 155 +#define CLK_GOUT_CMU_CPUCL0_DBG_BUS 156 +#define CLK_GOUT_CMU_CPUCL0_SWITCH 157 +#define CLK_GOUT_CMU_CPUCL1_SWITCH 158 +#define CLK_GOUT_CMU_CPUCL2_BUSP 159 +#define CLK_GOUT_CMU_CPUCL2_SWITCH 160 +#define CLK_GOUT_CMU_CSIS_BUS 161 +#define CLK_GOUT_CMU_CSIS_OIS_MCU 162 +#define CLK_GOUT_CMU_DNC_BUS 163 +#define CLK_GOUT_CMU_DNC_BUSM 164 +#define CLK_GOUT_CMU_DNS_BUS 165 +#define CLK_GOUT_CMU_DPU 166 +#define CLK_GOUT_CMU_DPU_BUS 167 +#define CLK_GOUT_CMU_DSP_BUS 168 +#define CLK_GOUT_CMU_G2D_G2D 169 +#define CLK_GOUT_CMU_G2D_MSCL 170 +#define CLK_GOUT_CMU_G3D_SWITCH 171 +#define CLK_GOUT_CMU_HPM 172 +#define CLK_GOUT_CMU_HSI0_BUS 173 +#define CLK_GOUT_CMU_HSI0_DPGTC 174 +#define CLK_GOUT_CMU_HSI0_USB31DRD 175 +#define CLK_GOUT_CMU_HSI0_USBDP_DEBUG 176 +#define CLK_GOUT_CMU_HSI1_BUS 177 +#define CLK_GOUT_CMU_HSI1_MMC_CARD 178 +#define CLK_GOUT_CMU_HSI1_PCIE 179 +#define CLK_GOUT_CMU_HSI1_UFS_CARD 180 +#define CLK_GOUT_CMU_HSI1_UFS_EMBD 181 +#define CLK_GOUT_CMU_HSI2_BUS 182 +#define CLK_GOUT_CMU_HSI2_PCIE 183 +#define CLK_GOUT_CMU_IPP_BUS 184 +#define CLK_GOUT_CMU_ITP_BUS 185 +#define CLK_GOUT_CMU_MCSC_BUS 186 +#define CLK_GOUT_CMU_MCSC_GDC 187 +#define CLK_GOUT_CMU_MFC0_MFC0 188 +#define CLK_GOUT_CMU_MFC0_WFD 189 +#define CLK_GOUT_CMU_MIF_BUSP 190 +#define CLK_GOUT_CMU_NPU_BUS 191 +#define CLK_GOUT_CMU_PERIC0_BUS 192 +#define CLK_GOUT_CMU_PERIC0_IP 193 +#define CLK_GOUT_CMU_PERIC1_BUS 194 +#define CLK_GOUT_CMU_PERIC1_IP 195 +#define CLK_GOUT_CMU_PERIS_BUS 196 +#define CLK_GOUT_CMU_SSP_BUS 197 +#define CLK_GOUT_CMU_TNR_BUS 198 +#define CLK_GOUT_CMU_VRA_BUS 199 + +/* CMU_HSI0 */ +#define CLK_MOUT_HSI0_BUS_USER 1 +#define CLK_MOUT_HSI0_USB31DRD_USER 2 +#define CLK_MOUT_HSI0_USBDP_DEBUG_USER 3 +#define CLK_MOUT_HSI0_DPGTC_USER 4 +#define CLK_GOUT_HSI0_DP_LINK_DP_GTC_CLK 5 +#define CLK_GOUT_HSI0_DP_LINK_PCLK 6 +#define CLK_GOUT_HSI0_D_TZPC_HSI0_PCLK 7 +#define CLK_GOUT_HSI0_LHM_AXI_P_HSI0_CLK 8 +#define CLK_GOUT_HSI0_PPMU_HSI0_BUS1_ACLK 9 +#define CLK_GOUT_HSI0_PPMU_HSI0_BUS1_PCLK 10 +#define CLK_GOUT_HSI0_CLK_HSI0_BUS_CLK 11 +#define CLK_GOUT_HSI0_SYSMMU_USB_CLK_S2 12 +#define CLK_GOUT_HSI0_SYSREG_HSI0_PCLK 13 +#define CLK_GOUT_HSI0_USB31DRD_ACLK_PHYCTRL 14 +#define CLK_GOUT_HSI0_USB31DRD_BUS_CLK_EARLY 15 +#define CLK_GOUT_HSI0_USB31DRD_USB31DRD_REF_CLK_40 16 +#define CLK_GOUT_HSI0_USB31DRD_USBDPPHY_REF_SOC_PLL 17 +#define CLK_GOUT_HSI0_USB31DRD_USBDPPHY_SCL_APB 18 +#define CLK_GOUT_HSI0_USB31DRD_USBPCS_APB_CLK 19 +#define CLK_GOUT_HSI0_VGEN_LITE_HSI0_CLK 20 +#define CLK_GOUT_HSI0_CMU_HSI0_PCLK 21 +#define CLK_GOUT_HSI0_XIU_D_HSI0_ACLK 22 + +#endif diff --git a/include/dt-bindings/clock/stm32fx-clock.h b/include/dt-bindings/clock/stm32fx-clock.h index e5dad050d518..b6ff9c68cb3f 100644 --- a/include/dt-bindings/clock/stm32fx-clock.h +++ b/include/dt-bindings/clock/stm32fx-clock.h @@ -10,7 +10,7 @@ * List of clocks which are not derived from system clock (SYSCLOCK) * * The index of these clocks is the secondary index of DT bindings - * (see Documentation/devicetree/bindings/clock/st,stm32-rcc.txt) + * (see Documentation/devicetree/bindings/clock/st,stm32-rcc.yaml) * * e.g: ; diff --git a/include/dt-bindings/clock/sun50i-a64-ccu.h b/include/dt-bindings/clock/sun50i-a64-ccu.h index 175892189e9d..4f220ea7a23c 100644 --- a/include/dt-bindings/clock/sun50i-a64-ccu.h +++ b/include/dt-bindings/clock/sun50i-a64-ccu.h @@ -44,7 +44,9 @@ #define _DT_BINDINGS_CLK_SUN50I_A64_H_ #define CLK_PLL_VIDEO0 7 +#define CLK_PLL_VIDEO0_2X 8 #define CLK_PLL_PERIPH0 11 +#define CLK_PLL_MIPI 17 #define CLK_CPUX 21 #define CLK_BUS_MIPI_DSI 28 diff --git a/include/dt-bindings/iio/adi,ad4695.h b/include/dt-bindings/iio/adc/adi,ad4695.h similarity index 100% rename from include/dt-bindings/iio/adi,ad4695.h rename to include/dt-bindings/iio/adc/adi,ad4695.h diff --git a/include/dt-bindings/interconnect/qcom,ipq5424.h b/include/dt-bindings/interconnect/qcom,ipq5424.h new file mode 100644 index 000000000000..a770356112ee --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,ipq5424.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +#ifndef INTERCONNECT_QCOM_IPQ5424_H +#define INTERCONNECT_QCOM_IPQ5424_H + +#define MASTER_ANOC_PCIE0 0 +#define SLAVE_ANOC_PCIE0 1 +#define MASTER_CNOC_PCIE0 2 +#define SLAVE_CNOC_PCIE0 3 +#define MASTER_ANOC_PCIE1 4 +#define SLAVE_ANOC_PCIE1 5 +#define MASTER_CNOC_PCIE1 6 +#define SLAVE_CNOC_PCIE1 7 +#define MASTER_ANOC_PCIE2 8 +#define SLAVE_ANOC_PCIE2 9 +#define MASTER_CNOC_PCIE2 10 +#define SLAVE_CNOC_PCIE2 11 +#define MASTER_ANOC_PCIE3 12 +#define SLAVE_ANOC_PCIE3 13 +#define MASTER_CNOC_PCIE3 14 +#define SLAVE_CNOC_PCIE3 15 +#define MASTER_CNOC_USB 16 +#define SLAVE_CNOC_USB 17 + +#endif /* INTERCONNECT_QCOM_IPQ5424_H */ diff --git a/include/dt-bindings/interconnect/qcom,sm8750-rpmh.h b/include/dt-bindings/interconnect/qcom,sm8750-rpmh.h new file mode 100644 index 000000000000..30563952a646 --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,sm8750-rpmh.h @@ -0,0 +1,143 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SM8750_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_SM8750_H + +#define MASTER_QSPI_0 0 +#define MASTER_QUP_1 1 +#define MASTER_QUP_3 2 +#define MASTER_SDCC_4 3 +#define MASTER_UFS_MEM 4 +#define MASTER_USB3_0 5 +#define SLAVE_A1NOC_SNOC 6 + +#define MASTER_QDSS_BAM 0 +#define MASTER_QUP_2 1 +#define MASTER_CRYPTO 2 +#define MASTER_IPA 3 +#define MASTER_SOCCP_AGGR_NOC 4 +#define MASTER_SP 5 +#define MASTER_QDSS_ETR 6 +#define MASTER_QDSS_ETR_1 7 +#define MASTER_SDCC_2 8 +#define SLAVE_A2NOC_SNOC 9 + +#define MASTER_QUP_CORE_0 0 +#define MASTER_QUP_CORE_1 1 +#define MASTER_QUP_CORE_2 2 +#define SLAVE_QUP_CORE_0 3 +#define SLAVE_QUP_CORE_1 4 +#define SLAVE_QUP_CORE_2 5 + +#define MASTER_CNOC_CFG 0 +#define SLAVE_AHB2PHY_SOUTH 1 +#define SLAVE_AHB2PHY_NORTH 2 +#define SLAVE_CAMERA_CFG 3 +#define SLAVE_CLK_CTL 4 +#define SLAVE_CRYPTO_0_CFG 5 +#define SLAVE_DISPLAY_CFG 6 +#define SLAVE_EVA_CFG 7 +#define SLAVE_GFX3D_CFG 8 +#define SLAVE_I2C 9 +#define SLAVE_I3C_IBI0_CFG 10 +#define SLAVE_I3C_IBI1_CFG 11 +#define SLAVE_IMEM_CFG 12 +#define SLAVE_CNOC_MSS 13 +#define SLAVE_PCIE_CFG 14 +#define SLAVE_PRNG 15 +#define SLAVE_QDSS_CFG 16 +#define SLAVE_QSPI_0 17 +#define SLAVE_QUP_3 18 +#define SLAVE_QUP_1 19 +#define SLAVE_QUP_2 20 +#define SLAVE_SDCC_2 21 +#define SLAVE_SDCC_4 22 +#define SLAVE_SPSS_CFG 23 +#define SLAVE_TCSR 24 +#define SLAVE_TLMM 25 +#define SLAVE_UFS_MEM_CFG 26 +#define SLAVE_USB3_0 27 +#define SLAVE_VENUS_CFG 28 +#define SLAVE_VSENSE_CTRL_CFG 29 +#define SLAVE_CNOC_MNOC_CFG 30 +#define SLAVE_PCIE_ANOC_CFG 31 +#define SLAVE_QDSS_STM 32 +#define SLAVE_TCU 33 + +#define MASTER_GEM_NOC_CNOC 0 +#define MASTER_GEM_NOC_PCIE_SNOC 1 +#define SLAVE_AOSS 2 +#define SLAVE_IPA_CFG 3 +#define SLAVE_IPC_ROUTER_CFG 4 +#define SLAVE_SOCCP 5 +#define SLAVE_TME_CFG 6 +#define SLAVE_APPSS 7 +#define SLAVE_CNOC_CFG 8 +#define SLAVE_DDRSS_CFG 9 +#define SLAVE_BOOT_IMEM 10 +#define SLAVE_IMEM 11 +#define SLAVE_BOOT_IMEM_2 12 +#define SLAVE_SERVICE_CNOC 13 +#define SLAVE_PCIE_0 14 + +#define MASTER_GPU_TCU 0 +#define MASTER_SYS_TCU 1 +#define MASTER_APPSS_PROC 2 +#define MASTER_GFX3D 3 +#define MASTER_LPASS_GEM_NOC 4 +#define MASTER_MSS_PROC 5 +#define MASTER_MNOC_HF_MEM_NOC 6 +#define MASTER_MNOC_SF_MEM_NOC 7 +#define MASTER_COMPUTE_NOC 8 +#define MASTER_ANOC_PCIE_GEM_NOC 9 +#define MASTER_SNOC_SF_MEM_NOC 10 +#define MASTER_UBWC_P 11 +#define MASTER_GIC 12 +#define SLAVE_UBWC_P 13 +#define SLAVE_GEM_NOC_CNOC 14 +#define SLAVE_LLCC 15 +#define SLAVE_MEM_NOC_PCIE_SNOC 16 + +#define MASTER_LPIAON_NOC 0 +#define SLAVE_LPASS_GEM_NOC 1 + +#define MASTER_LPASS_LPINOC 0 +#define SLAVE_LPIAON_NOC_LPASS_AG_NOC 1 + +#define MASTER_LPASS_PROC 0 +#define SLAVE_LPICX_NOC_LPIAON_NOC 1 + +#define MASTER_LLCC 0 +#define SLAVE_EBI1 1 + +#define MASTER_CAMNOC_HF 0 +#define MASTER_CAMNOC_NRT_ICP_SF 1 +#define MASTER_CAMNOC_RT_CDM_SF 2 +#define MASTER_CAMNOC_SF 3 +#define MASTER_MDP 4 +#define MASTER_CDSP_HCP 5 +#define MASTER_VIDEO_CV_PROC 6 +#define MASTER_VIDEO_EVA 7 +#define MASTER_VIDEO_MVP 8 +#define MASTER_VIDEO_V_PROC 9 +#define MASTER_CNOC_MNOC_CFG 10 +#define SLAVE_MNOC_HF_MEM_NOC 11 +#define SLAVE_MNOC_SF_MEM_NOC 12 +#define SLAVE_SERVICE_MNOC 13 + +#define MASTER_CDSP_PROC 0 +#define SLAVE_CDSP_MEM_NOC 1 + +#define MASTER_PCIE_ANOC_CFG 0 +#define MASTER_PCIE_0 1 +#define SLAVE_ANOC_PCIE_GEM_NOC 2 +#define SLAVE_SERVICE_PCIE_ANOC 3 + +#define MASTER_A1NOC_SNOC 0 +#define MASTER_A2NOC_SNOC 1 +#define SLAVE_SNOC_GEM_NOC_SF 2 + +#endif diff --git a/include/dt-bindings/media/video-interfaces.h b/include/dt-bindings/media/video-interfaces.h index 68ac4e05e37f..88b9d05d8075 100644 --- a/include/dt-bindings/media/video-interfaces.h +++ b/include/dt-bindings/media/video-interfaces.h @@ -13,4 +13,11 @@ #define MEDIA_BUS_TYPE_PARALLEL 5 #define MEDIA_BUS_TYPE_BT656 6 +#define MEDIA_BUS_CSI2_CPHY_LINE_ORDER_ABC 0 +#define MEDIA_BUS_CSI2_CPHY_LINE_ORDER_ACB 1 +#define MEDIA_BUS_CSI2_CPHY_LINE_ORDER_BAC 2 +#define MEDIA_BUS_CSI2_CPHY_LINE_ORDER_BCA 3 +#define MEDIA_BUS_CSI2_CPHY_LINE_ORDER_CAB 4 +#define MEDIA_BUS_CSI2_CPHY_LINE_ORDER_CBA 5 + #endif /* __DT_BINDINGS_MEDIA_VIDEO_INTERFACES_H__ */ diff --git a/include/dt-bindings/pinctrl/renesas,r9a09g047-pinctrl.h b/include/dt-bindings/pinctrl/renesas,r9a09g047-pinctrl.h new file mode 100644 index 000000000000..5917096720bd --- /dev/null +++ b/include/dt-bindings/pinctrl/renesas,r9a09g047-pinctrl.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * This header provides constants for Renesas RZ/G3E family pinctrl bindings. + * + * Copyright (C) 2024 Renesas Electronics Corp. + * + */ + +#ifndef __DT_BINDINGS_PINCTRL_RENESAS_R9A09G047_PINCTRL_H__ +#define __DT_BINDINGS_PINCTRL_RENESAS_R9A09G047_PINCTRL_H__ + +#include + +/* RZG3E_Px = Offset address of PFC_P_mn - 0x20 */ +#define RZG3E_P0 0 +#define RZG3E_P1 1 +#define RZG3E_P2 2 +#define RZG3E_P3 3 +#define RZG3E_P4 4 +#define RZG3E_P5 5 +#define RZG3E_P6 6 +#define RZG3E_P7 7 +#define RZG3E_P8 8 +#define RZG3E_PA 10 +#define RZG3E_PB 11 +#define RZG3E_PC 12 +#define RZG3E_PD 13 +#define RZG3E_PE 14 +#define RZG3E_PF 15 +#define RZG3E_PG 16 +#define RZG3E_PH 17 +#define RZG3E_PJ 19 +#define RZG3E_PK 20 +#define RZG3E_PL 21 +#define RZG3E_PM 22 +#define RZG3E_PS 28 + +#define RZG3E_PORT_PINMUX(b, p, f) RZG2L_PORT_PINMUX(RZG3E_P##b, p, f) +#define RZG3E_GPIO(port, pin) RZG2L_GPIO(RZG3E_P##port, pin) + +#endif /* __DT_BINDINGS_PINCTRL_RENESAS_R9A09G047_PINCTRL_H__ */ diff --git a/include/dt-bindings/pinctrl/renesas,r9a09g057-pinctrl.h b/include/dt-bindings/pinctrl/renesas,r9a09g057-pinctrl.h new file mode 100644 index 000000000000..2e83bf43160b --- /dev/null +++ b/include/dt-bindings/pinctrl/renesas,r9a09g057-pinctrl.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * This header provides constants for Renesas RZ/V2H family pinctrl bindings. + * + * Copyright (C) 2024 Renesas Electronics Corp. + * + */ + +#ifndef __DT_BINDINGS_PINCTRL_RENESAS_R9A09G057_PINCTRL_H__ +#define __DT_BINDINGS_PINCTRL_RENESAS_R9A09G057_PINCTRL_H__ + +#include + +/* RZV2H_Px = Offset address of PFC_P_mn - 0x20 */ +#define RZV2H_P0 0 +#define RZV2H_P1 1 +#define RZV2H_P2 2 +#define RZV2H_P3 3 +#define RZV2H_P4 4 +#define RZV2H_P5 5 +#define RZV2H_P6 6 +#define RZV2H_P7 7 +#define RZV2H_P8 8 +#define RZV2H_P9 9 +#define RZV2H_PA 10 +#define RZV2H_PB 11 + +#define RZV2H_PORT_PINMUX(b, p, f) RZG2L_PORT_PINMUX(RZV2H_P##b, p, f) +#define RZV2H_GPIO(port, pin) RZG2L_GPIO(RZV2H_P##port, pin) + +#endif /* __DT_BINDINGS_PINCTRL_RENESAS_R9A09G057_PINCTRL_H__ */ diff --git a/include/dt-bindings/reset/amlogic,meson-a1-audio-reset.h b/include/dt-bindings/reset/amlogic,meson-a1-audio-reset.h new file mode 100644 index 000000000000..7693552f1507 --- /dev/null +++ b/include/dt-bindings/reset/amlogic,meson-a1-audio-reset.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Copyright (c) 2024, SaluteDevices. All Rights Reserved. + * + * Author: Jan Dakinevich + */ + +#ifndef _DT_BINDINGS_AMLOGIC_MESON_A1_AUDIO_RESET_H +#define _DT_BINDINGS_AMLOGIC_MESON_A1_AUDIO_RESET_H + +#define AUD_RESET_DDRARB 0 +#define AUD_RESET_TDMIN_A 1 +#define AUD_RESET_TDMIN_B 2 +#define AUD_RESET_TDMIN_LB 3 +#define AUD_RESET_LOOPBACK 4 +#define AUD_RESET_TDMOUT_A 5 +#define AUD_RESET_TDMOUT_B 6 +#define AUD_RESET_FRDDR_A 7 +#define AUD_RESET_FRDDR_B 8 +#define AUD_RESET_TODDR_A 9 +#define AUD_RESET_TODDR_B 10 +#define AUD_RESET_SPDIFIN 11 +#define AUD_RESET_RESAMPLE 12 +#define AUD_RESET_EQDRC 13 +#define AUD_RESET_LOCKER 14 +#define AUD_RESET_TOACODEC 30 +#define AUD_RESET_CLKTREE 31 + +#define AUD_VAD_RESET_DDRARB 0 +#define AUD_VAD_RESET_PDM 1 +#define AUD_VAD_RESET_TDMIN_VAD 2 +#define AUD_VAD_RESET_TODDR_VAD 3 +#define AUD_VAD_RESET_TOVAD 4 +#define AUD_VAD_RESET_CLKTREE 5 + +#endif /* _DT_BINDINGS_AMLOGIC_MESON_A1_AUDIO_RESET_H */ diff --git a/include/dt-bindings/sound/qcom,wcd9335.h b/include/dt-bindings/sound/qcom,wcd9335.h index f5e9f1db091e..4fc68aeb9e04 100644 --- a/include/dt-bindings/sound/qcom,wcd9335.h +++ b/include/dt-bindings/sound/qcom,wcd9335.h @@ -10,6 +10,5 @@ #define AIF3_PB 4 #define AIF3_CAP 5 #define AIF4_PB 6 -#define NUM_CODEC_DAIS 7 #endif diff --git a/include/hyperv/hvgdk.h b/include/hyperv/hvgdk.h new file mode 100644 index 000000000000..dd6d4939ea29 --- /dev/null +++ b/include/hyperv/hvgdk.h @@ -0,0 +1,308 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Type definitions for the Microsoft Hypervisor. + */ +#ifndef _HV_HVGDK_H +#define _HV_HVGDK_H + +#include "hvgdk_mini.h" +#include "hvgdk_ext.h" + +/* + * The guest OS needs to register the guest ID with the hypervisor. + * The guest ID is a 64 bit entity and the structure of this ID is + * specified in the Hyper-V TLFS specification. + * + * While the current guideline does not specify how Linux guest ID(s) + * need to be generated, our plan is to publish the guidelines for + * Linux and other guest operating systems that currently are hosted + * on Hyper-V. The implementation here conforms to this yet + * unpublished guidelines. + * + * Bit(s) + * 63 - Indicates if the OS is Open Source or not; 1 is Open Source + * 62:56 - Os Type; Linux is 0x100 + * 55:48 - Distro specific identification + * 47:16 - Linux kernel version number + * 15:0 - Distro specific identification + */ + +#define HV_LINUX_VENDOR_ID 0x8100 + +/* HV_VMX_ENLIGHTENED_VMCS */ +struct hv_enlightened_vmcs { + u32 revision_id; + u32 abort; + + u16 host_es_selector; + u16 host_cs_selector; + u16 host_ss_selector; + u16 host_ds_selector; + u16 host_fs_selector; + u16 host_gs_selector; + u16 host_tr_selector; + + u16 padding16_1; + + u64 host_ia32_pat; + u64 host_ia32_efer; + + u64 host_cr0; + u64 host_cr3; + u64 host_cr4; + + u64 host_ia32_sysenter_esp; + u64 host_ia32_sysenter_eip; + u64 host_rip; + u32 host_ia32_sysenter_cs; + + u32 pin_based_vm_exec_control; + u32 vm_exit_controls; + u32 secondary_vm_exec_control; + + u64 io_bitmap_a; + u64 io_bitmap_b; + u64 msr_bitmap; + + u16 guest_es_selector; + u16 guest_cs_selector; + u16 guest_ss_selector; + u16 guest_ds_selector; + u16 guest_fs_selector; + u16 guest_gs_selector; + u16 guest_ldtr_selector; + u16 guest_tr_selector; + + u32 guest_es_limit; + u32 guest_cs_limit; + u32 guest_ss_limit; + u32 guest_ds_limit; + u32 guest_fs_limit; + u32 guest_gs_limit; + u32 guest_ldtr_limit; + u32 guest_tr_limit; + u32 guest_gdtr_limit; + u32 guest_idtr_limit; + + u32 guest_es_ar_bytes; + u32 guest_cs_ar_bytes; + u32 guest_ss_ar_bytes; + u32 guest_ds_ar_bytes; + u32 guest_fs_ar_bytes; + u32 guest_gs_ar_bytes; + u32 guest_ldtr_ar_bytes; + u32 guest_tr_ar_bytes; + + u64 guest_es_base; + u64 guest_cs_base; + u64 guest_ss_base; + u64 guest_ds_base; + u64 guest_fs_base; + u64 guest_gs_base; + u64 guest_ldtr_base; + u64 guest_tr_base; + u64 guest_gdtr_base; + u64 guest_idtr_base; + + u64 padding64_1[3]; + + u64 vm_exit_msr_store_addr; + u64 vm_exit_msr_load_addr; + u64 vm_entry_msr_load_addr; + + u64 cr3_target_value0; + u64 cr3_target_value1; + u64 cr3_target_value2; + u64 cr3_target_value3; + + u32 page_fault_error_code_mask; + u32 page_fault_error_code_match; + + u32 cr3_target_count; + u32 vm_exit_msr_store_count; + u32 vm_exit_msr_load_count; + u32 vm_entry_msr_load_count; + + u64 tsc_offset; + u64 virtual_apic_page_addr; + u64 vmcs_link_pointer; + + u64 guest_ia32_debugctl; + u64 guest_ia32_pat; + u64 guest_ia32_efer; + + u64 guest_pdptr0; + u64 guest_pdptr1; + u64 guest_pdptr2; + u64 guest_pdptr3; + + u64 guest_pending_dbg_exceptions; + u64 guest_sysenter_esp; + u64 guest_sysenter_eip; + + u32 guest_activity_state; + u32 guest_sysenter_cs; + + u64 cr0_guest_host_mask; + u64 cr4_guest_host_mask; + u64 cr0_read_shadow; + u64 cr4_read_shadow; + u64 guest_cr0; + u64 guest_cr3; + u64 guest_cr4; + u64 guest_dr7; + + u64 host_fs_base; + u64 host_gs_base; + u64 host_tr_base; + u64 host_gdtr_base; + u64 host_idtr_base; + u64 host_rsp; + + u64 ept_pointer; + + u16 virtual_processor_id; + u16 padding16_2[3]; + + u64 padding64_2[5]; + u64 guest_physical_address; + + u32 vm_instruction_error; + u32 vm_exit_reason; + u32 vm_exit_intr_info; + u32 vm_exit_intr_error_code; + u32 idt_vectoring_info_field; + u32 idt_vectoring_error_code; + u32 vm_exit_instruction_len; + u32 vmx_instruction_info; + + u64 exit_qualification; + u64 exit_io_instruction_ecx; + u64 exit_io_instruction_esi; + u64 exit_io_instruction_edi; + u64 exit_io_instruction_eip; + + u64 guest_linear_address; + u64 guest_rsp; + u64 guest_rflags; + + u32 guest_interruptibility_info; + u32 cpu_based_vm_exec_control; + u32 exception_bitmap; + u32 vm_entry_controls; + u32 vm_entry_intr_info_field; + u32 vm_entry_exception_error_code; + u32 vm_entry_instruction_len; + u32 tpr_threshold; + + u64 guest_rip; + + u32 hv_clean_fields; + u32 padding32_1; + u32 hv_synthetic_controls; + struct { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 reserved:30; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u32 padding32_2; + u64 hv_vm_id; + u64 partition_assist_page; + u64 padding64_4[4]; + u64 guest_bndcfgs; + u64 guest_ia32_perf_global_ctrl; + u64 guest_ia32_s_cet; + u64 guest_ssp; + u64 guest_ia32_int_ssp_table_addr; + u64 guest_ia32_lbr_ctl; + u64 padding64_5[2]; + u64 xss_exit_bitmap; + u64 encls_exiting_bitmap; + u64 host_ia32_perf_global_ctrl; + u64 tsc_multiplier; + u64 host_ia32_s_cet; + u64 host_ssp; + u64 host_ia32_int_ssp_table_addr; + u64 padding64_6; +} __packed; +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 + + +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP BIT(1) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2 BIT(2) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1 BIT(3) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC BIT(4) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT BIT(5) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY BIT(6) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN BIT(7) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR BIT(8) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT BIT(9) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC BIT(10) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1 BIT(11) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2 BIT(12) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER BIT(13) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1 BIT(14) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL BIT(15) + +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF + +/* + * Note, Hyper-V isn't actually stealing bit 28 from Intel, just abusing it by + * pairing it with architecturally impossible exit reasons. Bit 28 is set only + * on SMI exits to a SMI transfer monitor (STM) and if and only if a MTF VM-Exit + * is pending. I.e. it will never be set by hardware for non-SMI exits (there + * are only three), nor will it ever be set unless the VMM is an STM. + */ +#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031 + +/* + * Hyper-V uses the software reserved 32 bytes in VMCB control area to expose + * SVM enlightenments to guests. This is documented in the TLFS doc. + * Note on naming: SVM_NESTED_ENLIGHTENED_VMCB_FIELDS + */ +struct hv_vmcb_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall : 1; + u32 msr_bitmap : 1; + u32 enlightened_npt_tlb: 1; + u32 reserved : 29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB. + */ +#define HV_VMCB_NESTED_ENLIGHTENMENTS 31 + +/* Synthetic VM-Exit */ +#define HV_SVM_EXITCODE_ENL 0xf0000000 +#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1) + +/* VM_PARTITION_ASSIST_PAGE */ +struct hv_partition_assist_pg { + u32 tlb_lock_count; +}; + +/* Define connection identifier type. */ +union hv_connection_id { + u32 asu32; + struct { + u32 id : 24; + u32 reserved : 8; + } __packed u; +}; + +struct hv_input_unmap_gpa_pages { + u64 target_partition_id; + u64 target_gpa_base; + u32 unmap_flags; + u32 padding; +} __packed; + +#endif /* #ifndef _HV_HVGDK_H */ diff --git a/include/hyperv/hvgdk_ext.h b/include/hyperv/hvgdk_ext.h new file mode 100644 index 000000000000..641b591ee61f --- /dev/null +++ b/include/hyperv/hvgdk_ext.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Type definitions for the Microsoft Hypervisor. + */ +#ifndef _HV_HVGDK_EXT_H +#define _HV_HVGDK_EXT_H + +#include "hvgdk_mini.h" + +/* Extended hypercalls */ +#define HV_EXT_CALL_QUERY_CAPABILITIES 0x8001 +#define HV_EXT_CALL_MEMORY_HEAT_HINT 0x8003 + +/* Extended hypercalls */ +enum { /* HV_EXT_CALL */ + HV_EXTCALL_QUERY_CAPABILITIES = 0x8001, + HV_EXTCALL_MEMORY_HEAT_HINT = 0x8003, +}; + +/* HV_EXT_OUTPUT_QUERY_CAPABILITIES */ +#define HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT BIT(8) + +enum { /* HV_EXT_MEMORY_HEAT_HINT_TYPE */ + HV_EXTMEM_HEAT_HINT_COLD = 0, + HV_EXTMEM_HEAT_HINT_HOT = 1, + HV_EXTMEM_HEAT_HINT_COLD_DISCARD = 2, + HV_EXTMEM_HEAT_HINT_MAX +}; + +/* + * The whole argument should fit in a page to be able to pass to the hypervisor + * in one hypercall. + */ +#define HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES \ + ((HV_HYP_PAGE_SIZE - sizeof(struct hv_memory_hint)) / \ + sizeof(union hv_gpa_page_range)) + +/* HvExtCallMemoryHeatHint hypercall */ +#define HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD 2 +struct hv_memory_hint { /* HV_EXT_INPUT_MEMORY_HEAT_HINT */ + u64 heat_type : 2; /* HV_EXTMEM_HEAT_HINT_* */ + u64 reserved : 62; + union hv_gpa_page_range ranges[]; +} __packed; + +#endif /* _HV_HVGDK_EXT_H */ diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h new file mode 100644 index 000000000000..155615175965 --- /dev/null +++ b/include/hyperv/hvgdk_mini.h @@ -0,0 +1,1348 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Type definitions for the Microsoft hypervisor. + */ +#ifndef _HV_HVGDK_MINI_H +#define _HV_HVGDK_MINI_H + +#include +#include + +struct hv_u128 { + u64 low_part; + u64 high_part; +} __packed; + +/* NOTE: when adding below, update hv_status_to_string() */ +#define HV_STATUS_SUCCESS 0x0 +#define HV_STATUS_INVALID_HYPERCALL_CODE 0x2 +#define HV_STATUS_INVALID_HYPERCALL_INPUT 0x3 +#define HV_STATUS_INVALID_ALIGNMENT 0x4 +#define HV_STATUS_INVALID_PARAMETER 0x5 +#define HV_STATUS_ACCESS_DENIED 0x6 +#define HV_STATUS_INVALID_PARTITION_STATE 0x7 +#define HV_STATUS_OPERATION_DENIED 0x8 +#define HV_STATUS_UNKNOWN_PROPERTY 0x9 +#define HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE 0xA +#define HV_STATUS_INSUFFICIENT_MEMORY 0xB +#define HV_STATUS_INVALID_PARTITION_ID 0xD +#define HV_STATUS_INVALID_VP_INDEX 0xE +#define HV_STATUS_NOT_FOUND 0x10 +#define HV_STATUS_INVALID_PORT_ID 0x11 +#define HV_STATUS_INVALID_CONNECTION_ID 0x12 +#define HV_STATUS_INSUFFICIENT_BUFFERS 0x13 +#define HV_STATUS_NOT_ACKNOWLEDGED 0x14 +#define HV_STATUS_INVALID_VP_STATE 0x15 +#define HV_STATUS_NO_RESOURCES 0x1D +#define HV_STATUS_PROCESSOR_FEATURE_NOT_SUPPORTED 0x20 +#define HV_STATUS_INVALID_LP_INDEX 0x41 +#define HV_STATUS_INVALID_REGISTER_VALUE 0x50 +#define HV_STATUS_OPERATION_FAILED 0x71 +#define HV_STATUS_TIME_OUT 0x78 +#define HV_STATUS_CALL_PENDING 0x79 +#define HV_STATUS_VTL_ALREADY_ENABLED 0x86 + +/* + * The Hyper-V TimeRefCount register and the TSC + * page provide a guest VM clock with 100ns tick rate + */ +#define HV_CLOCK_HZ (NSEC_PER_SEC / 100) + +#define HV_HYP_PAGE_SHIFT 12 +#define HV_HYP_PAGE_SIZE BIT(HV_HYP_PAGE_SHIFT) +#define HV_HYP_PAGE_MASK (~(HV_HYP_PAGE_SIZE - 1)) + +#define HV_PARTITION_ID_INVALID ((u64)0) +#define HV_PARTITION_ID_SELF ((u64)-1) + +/* Hyper-V specific model specific registers (MSRs) */ + +#if defined(CONFIG_X86) +/* HV_X64_SYNTHETIC_MSR */ +#define HV_X64_MSR_GUEST_OS_ID 0x40000000 +#define HV_X64_MSR_HYPERCALL 0x40000001 +#define HV_X64_MSR_VP_INDEX 0x40000002 +#define HV_X64_MSR_RESET 0x40000003 +#define HV_X64_MSR_VP_RUNTIME 0x40000010 +#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 +#define HV_X64_MSR_REFERENCE_TSC 0x40000021 +#define HV_X64_MSR_TSC_FREQUENCY 0x40000022 +#define HV_X64_MSR_APIC_FREQUENCY 0x40000023 + +/* Define the virtual APIC registers */ +#define HV_X64_MSR_EOI 0x40000070 +#define HV_X64_MSR_ICR 0x40000071 +#define HV_X64_MSR_TPR 0x40000072 +#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 + +/* Define synthetic interrupt controller model specific registers. */ +#define HV_X64_MSR_SCONTROL 0x40000080 +#define HV_X64_MSR_SVERSION 0x40000081 +#define HV_X64_MSR_SIEFP 0x40000082 +#define HV_X64_MSR_SIMP 0x40000083 +#define HV_X64_MSR_EOM 0x40000084 +#define HV_X64_MSR_SIRBP 0x40000085 +#define HV_X64_MSR_SINT0 0x40000090 +#define HV_X64_MSR_SINT1 0x40000091 +#define HV_X64_MSR_SINT2 0x40000092 +#define HV_X64_MSR_SINT3 0x40000093 +#define HV_X64_MSR_SINT4 0x40000094 +#define HV_X64_MSR_SINT5 0x40000095 +#define HV_X64_MSR_SINT6 0x40000096 +#define HV_X64_MSR_SINT7 0x40000097 +#define HV_X64_MSR_SINT8 0x40000098 +#define HV_X64_MSR_SINT9 0x40000099 +#define HV_X64_MSR_SINT10 0x4000009A +#define HV_X64_MSR_SINT11 0x4000009B +#define HV_X64_MSR_SINT12 0x4000009C +#define HV_X64_MSR_SINT13 0x4000009D +#define HV_X64_MSR_SINT14 0x4000009E +#define HV_X64_MSR_SINT15 0x4000009F + +/* Define synthetic interrupt controller model specific registers for nested hypervisor */ +#define HV_X64_MSR_NESTED_SCONTROL 0x40001080 +#define HV_X64_MSR_NESTED_SVERSION 0x40001081 +#define HV_X64_MSR_NESTED_SIEFP 0x40001082 +#define HV_X64_MSR_NESTED_SIMP 0x40001083 +#define HV_X64_MSR_NESTED_EOM 0x40001084 +#define HV_X64_MSR_NESTED_SINT0 0x40001090 + +/* + * Synthetic Timer MSRs. Four timers per vcpu. + */ +#define HV_X64_MSR_STIMER0_CONFIG 0x400000B0 +#define HV_X64_MSR_STIMER0_COUNT 0x400000B1 +#define HV_X64_MSR_STIMER1_CONFIG 0x400000B2 +#define HV_X64_MSR_STIMER1_COUNT 0x400000B3 +#define HV_X64_MSR_STIMER2_CONFIG 0x400000B4 +#define HV_X64_MSR_STIMER2_COUNT 0x400000B5 +#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 +#define HV_X64_MSR_STIMER3_COUNT 0x400000B7 + +/* Hyper-V guest idle MSR */ +#define HV_X64_MSR_GUEST_IDLE 0x400000F0 + +/* Hyper-V guest crash notification MSR's */ +#define HV_X64_MSR_CRASH_P0 0x40000100 +#define HV_X64_MSR_CRASH_P1 0x40000101 +#define HV_X64_MSR_CRASH_P2 0x40000102 +#define HV_X64_MSR_CRASH_P3 0x40000103 +#define HV_X64_MSR_CRASH_P4 0x40000104 +#define HV_X64_MSR_CRASH_CTL 0x40000105 + +#define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 +#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12 +#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ + (~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1)) + +#define HV_X64_MSR_CRASH_PARAMS \ + (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) + +#define HV_IPI_LOW_VECTOR 0x10 +#define HV_IPI_HIGH_VECTOR 0xff + +#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 +#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 +#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ + (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) + +/* Hyper-V Enlightened VMCS version mask in nested features CPUID */ +#define HV_X64_ENLIGHTENED_VMCS_VERSION 0xff + +#define HV_X64_MSR_TSC_REFERENCE_ENABLE 0x00000001 +#define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT 12 + +/* Number of XMM registers used in hypercall input/output */ +#define HV_HYPERCALL_MAX_XMM_REGISTERS 6 + +struct hv_reenlightenment_control { + u64 vector : 8; + u64 reserved1 : 8; + u64 enabled : 1; + u64 reserved2 : 15; + u64 target_vp : 32; +} __packed; + +struct hv_tsc_emulation_status { /* HV_TSC_EMULATION_STATUS */ + u64 inprogress : 1; + u64 reserved : 63; +} __packed; + +struct hv_tsc_emulation_control { /* HV_TSC_INVARIANT_CONTROL */ + u64 enabled : 1; + u64 reserved : 63; +} __packed; + +/* TSC emulation after migration */ +#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 +#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 +#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 +#define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118 +#define HV_EXPOSE_INVARIANT_TSC BIT_ULL(0) + +#endif /* CONFIG_X86 */ + +struct hv_get_partition_id { /* HV_OUTPUT_GET_PARTITION_ID */ + u64 partition_id; +} __packed; + +/* HV_CRASH_CTL_REG_CONTENTS */ +#define HV_CRASH_CTL_CRASH_NOTIFY_MSG BIT_ULL(62) +#define HV_CRASH_CTL_CRASH_NOTIFY BIT_ULL(63) + +union hv_reference_tsc_msr { + u64 as_uint64; + struct { + u64 enable : 1; + u64 reserved : 11; + u64 pfn : 52; + } __packed; +}; + +/* The maximum number of sparse vCPU banks which can be encoded by 'struct hv_vpset' */ +#define HV_MAX_SPARSE_VCPU_BANKS (64) +/* The number of vCPUs in one sparse bank */ +#define HV_VCPUS_PER_SPARSE_BANK (64) + +/* Some of Hyper-V structs do not use hv_vpset where linux uses them */ +struct hv_vpset { /* HV_VP_SET */ + u64 format; + u64 valid_bank_mask; + u64 bank_contents[]; +} __packed; + +/* + * Version info reported by hypervisor + * Changed to a union for convenience + */ +union hv_hypervisor_version_info { + struct { + u32 build_number; + + u32 minor_version : 16; + u32 major_version : 16; + + u32 service_pack; + + u32 service_number : 24; + u32 service_branch : 8; + }; + struct { + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; + }; +}; + +/* HV_CPUID_FUNCTION */ +#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 0x40000000 +#define HYPERV_CPUID_INTERFACE 0x40000001 +#define HYPERV_CPUID_VERSION 0x40000002 +#define HYPERV_CPUID_FEATURES 0x40000003 +#define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004 +#define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005 +#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES 0x40000007 +#define HYPERV_CPUID_NESTED_FEATURES 0x4000000A +#define HYPERV_CPUID_ISOLATION_CONFIG 0x4000000C + +#define HYPERV_CPUID_VIRT_STACK_INTERFACE 0x40000081 +#define HYPERV_VS_INTERFACE_EAX_SIGNATURE 0x31235356 /* "VS#1" */ + +#define HYPERV_CPUID_VIRT_STACK_PROPERTIES 0x40000082 +/* Support for the extended IOAPIC RTE format */ +#define HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE BIT(2) + +#define HYPERV_HYPERVISOR_PRESENT_BIT 0x80000000 +#define HYPERV_CPUID_MIN 0x40000005 +#define HYPERV_CPUID_MAX 0x4000ffff + +/* + * HV_X64_HYPERVISOR_FEATURES (EAX), or + * HV_PARTITION_PRIVILEGE_MASK [31-0] + */ +#define HV_MSR_VP_RUNTIME_AVAILABLE BIT(0) +#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1) +#define HV_MSR_SYNIC_AVAILABLE BIT(2) +#define HV_MSR_SYNTIMER_AVAILABLE BIT(3) +#define HV_MSR_APIC_ACCESS_AVAILABLE BIT(4) +#define HV_MSR_HYPERCALL_AVAILABLE BIT(5) +#define HV_MSR_VP_INDEX_AVAILABLE BIT(6) +#define HV_MSR_RESET_AVAILABLE BIT(7) +#define HV_MSR_STAT_PAGES_AVAILABLE BIT(8) +#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9) +#define HV_MSR_GUEST_IDLE_AVAILABLE BIT(10) +#define HV_ACCESS_FREQUENCY_MSRS BIT(11) +#define HV_ACCESS_REENLIGHTENMENT BIT(13) +#define HV_ACCESS_TSC_INVARIANT BIT(15) + +/* + * HV_X64_HYPERVISOR_FEATURES (EBX), or + * HV_PARTITION_PRIVILEGE_MASK [63-32] + */ +#define HV_CREATE_PARTITIONS BIT(0) +#define HV_ACCESS_PARTITION_ID BIT(1) +#define HV_ACCESS_MEMORY_POOL BIT(2) +#define HV_ADJUST_MESSAGE_BUFFERS BIT(3) +#define HV_POST_MESSAGES BIT(4) +#define HV_SIGNAL_EVENTS BIT(5) +#define HV_CREATE_PORT BIT(6) +#define HV_CONNECT_PORT BIT(7) +#define HV_ACCESS_STATS BIT(8) +#define HV_DEBUGGING BIT(11) +#define HV_CPU_MANAGEMENT BIT(12) +#define HV_ENABLE_EXTENDED_HYPERCALLS BIT(20) +#define HV_ISOLATION BIT(22) + +#if defined(CONFIG_X86) +/* HV_X64_HYPERVISOR_FEATURES (EDX) */ +#define HV_X64_MWAIT_AVAILABLE BIT(0) +#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) +#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) +#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) +#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) +#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) +#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) +#define HV_FEATURE_EXT_GVA_RANGES_FLUSH BIT(14) +/* + * Support for returning hypercall output block via XMM + * registers is available + */ +#define HV_X64_HYPERCALL_XMM_OUTPUT_AVAILABLE BIT(15) +/* stimer Direct Mode is available */ +#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) + +/* + * Implementation recommendations. Indicates which behaviors the hypervisor + * recommends the OS implement for optimal performance. + * These are HYPERV_CPUID_ENLIGHTMENT_INFO.EAX bits. + */ +/* HV_X64_ENLIGHTENMENT_INFORMATION */ +#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) +#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) +#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) +#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) +#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) +#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) +#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) +#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) +#define HV_X64_HYPERV_NESTED BIT(12) +#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) +#define HV_X64_USE_MMIO_HYPERCALLS BIT(21) + +/* + * CPU management features identification. + * These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits. + */ +#define HV_X64_START_LOGICAL_PROCESSOR BIT(0) +#define HV_X64_CREATE_ROOT_VIRTUAL_PROCESSOR BIT(1) +#define HV_X64_PERFORMANCE_COUNTER_SYNC BIT(2) +#define HV_X64_RESERVED_IDENTITY_BIT BIT(31) + +/* + * Virtual processor will never share a physical core with another virtual + * processor, except for virtual processors that are reported as sibling SMT + * threads. + */ +#define HV_X64_NO_NONARCH_CORESHARING BIT(18) + +/* Nested features. These are HYPERV_CPUID_NESTED_FEATURES.EAX bits. */ +#define HV_X64_NESTED_DIRECT_FLUSH BIT(17) +#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) +#define HV_X64_NESTED_MSR_BITMAP BIT(19) + +/* Nested features #2. These are HYPERV_CPUID_NESTED_FEATURES.EBX bits. */ +#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL BIT(0) + +/* + * This is specific to AMD and specifies that enlightened TLB flush is + * supported. If guest opts in to this feature, ASID invalidations only + * flushes gva -> hpa mapping entries. To flush the TLB entries derived + * from NPT, hypercalls should be used (HvFlushGuestPhysicalAddressSpace + * or HvFlushGuestPhysicalAddressList). + */ +#define HV_X64_NESTED_ENLIGHTENED_TLB BIT(22) + +/* HYPERV_CPUID_ISOLATION_CONFIG.EAX bits. */ +#define HV_PARAVISOR_PRESENT BIT(0) + +/* HYPERV_CPUID_ISOLATION_CONFIG.EBX bits. */ +#define HV_ISOLATION_TYPE GENMASK(3, 0) +#define HV_SHARED_GPA_BOUNDARY_ACTIVE BIT(5) +#define HV_SHARED_GPA_BOUNDARY_BITS GENMASK(11, 6) + +enum hv_isolation_type { + HV_ISOLATION_TYPE_NONE = 0, /* HV_PARTITION_ISOLATION_TYPE_NONE */ + HV_ISOLATION_TYPE_VBS = 1, + HV_ISOLATION_TYPE_SNP = 2, + HV_ISOLATION_TYPE_TDX = 3 +}; + +union hv_x64_msr_hypercall_contents { + u64 as_uint64; + struct { + u64 enable : 1; + u64 reserved : 11; + u64 guest_physical_address : 52; + } __packed; +}; +#endif /* CONFIG_X86 */ + +#if defined(CONFIG_ARM64) +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(8) +#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(13) +#endif /* CONFIG_ARM64 */ + +#if defined(CONFIG_X86) +#define HV_MAXIMUM_PROCESSORS 2048 +#elif defined(CONFIG_ARM64) /* CONFIG_X86 */ +#define HV_MAXIMUM_PROCESSORS 320 +#endif /* CONFIG_ARM64 */ + +#define HV_MAX_VP_INDEX (HV_MAXIMUM_PROCESSORS - 1) +#define HV_VP_INDEX_SELF ((u32)-2) +#define HV_ANY_VP ((u32)-1) + +union hv_vp_assist_msr_contents { /* HV_REGISTER_VP_ASSIST_PAGE */ + u64 as_uint64; + struct { + u64 enable : 1; + u64 reserved : 11; + u64 pfn : 52; + } __packed; +}; + +/* Declare the various hypercall operations. */ +/* HV_CALL_CODE */ +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003 +#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008 +#define HVCALL_SEND_IPI 0x000b +#define HVCALL_ENABLE_VP_VTL 0x000f +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013 +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014 +#define HVCALL_SEND_IPI_EX 0x0015 +#define HVCALL_CREATE_PARTITION 0x0040 +#define HVCALL_INITIALIZE_PARTITION 0x0041 +#define HVCALL_FINALIZE_PARTITION 0x0042 +#define HVCALL_DELETE_PARTITION 0x0043 +#define HVCALL_GET_PARTITION_PROPERTY 0x0044 +#define HVCALL_SET_PARTITION_PROPERTY 0x0045 +#define HVCALL_GET_PARTITION_ID 0x0046 +#define HVCALL_DEPOSIT_MEMORY 0x0048 +#define HVCALL_WITHDRAW_MEMORY 0x0049 +#define HVCALL_MAP_GPA_PAGES 0x004b +#define HVCALL_UNMAP_GPA_PAGES 0x004c +#define HVCALL_CREATE_VP 0x004e +#define HVCALL_DELETE_VP 0x004f +#define HVCALL_GET_VP_REGISTERS 0x0050 +#define HVCALL_SET_VP_REGISTERS 0x0051 +#define HVCALL_DELETE_PORT 0x0058 +#define HVCALL_DISCONNECT_PORT 0x005b +#define HVCALL_POST_MESSAGE 0x005c +#define HVCALL_SIGNAL_EVENT 0x005d +#define HVCALL_POST_DEBUG_DATA 0x0069 +#define HVCALL_RETRIEVE_DEBUG_DATA 0x006a +#define HVCALL_RESET_DEBUG_SESSION 0x006b +#define HVCALL_ADD_LOGICAL_PROCESSOR 0x0076 +#define HVCALL_GET_SYSTEM_PROPERTY 0x007b +#define HVCALL_MAP_DEVICE_INTERRUPT 0x007c +#define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d +#define HVCALL_RETARGET_INTERRUPT 0x007e +#define HVCALL_NOTIFY_PORT_RING_EMPTY 0x008b +#define HVCALL_ASSERT_VIRTUAL_INTERRUPT 0x0094 +#define HVCALL_CREATE_PORT 0x0095 +#define HVCALL_CONNECT_PORT 0x0096 +#define HVCALL_START_VP 0x0099 +#define HVCALL_GET_VP_ID_FROM_APIC_ID 0x009a +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 +#define HVCALL_DISPATCH_VP 0x00c2 +#define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db +#define HVCALL_MAP_VP_STATE_PAGE 0x00e1 +#define HVCALL_UNMAP_VP_STATE_PAGE 0x00e2 +#define HVCALL_GET_VP_STATE 0x00e3 +#define HVCALL_SET_VP_STATE 0x00e4 +#define HVCALL_MMIO_READ 0x0106 +#define HVCALL_MMIO_WRITE 0x0107 + +/* HV_HYPERCALL_INPUT */ +#define HV_HYPERCALL_RESULT_MASK GENMASK_ULL(15, 0) +#define HV_HYPERCALL_FAST_BIT BIT(16) +#define HV_HYPERCALL_VARHEAD_OFFSET 17 +#define HV_HYPERCALL_VARHEAD_MASK GENMASK_ULL(26, 17) +#define HV_HYPERCALL_RSVD0_MASK GENMASK_ULL(31, 27) +#define HV_HYPERCALL_NESTED BIT_ULL(31) +#define HV_HYPERCALL_REP_COMP_OFFSET 32 +#define HV_HYPERCALL_REP_COMP_1 BIT_ULL(32) +#define HV_HYPERCALL_REP_COMP_MASK GENMASK_ULL(43, 32) +#define HV_HYPERCALL_RSVD1_MASK GENMASK_ULL(47, 44) +#define HV_HYPERCALL_REP_START_OFFSET 48 +#define HV_HYPERCALL_REP_START_MASK GENMASK_ULL(59, 48) +#define HV_HYPERCALL_RSVD2_MASK GENMASK_ULL(63, 60) +#define HV_HYPERCALL_RSVD_MASK (HV_HYPERCALL_RSVD0_MASK | \ + HV_HYPERCALL_RSVD1_MASK | \ + HV_HYPERCALL_RSVD2_MASK) + +/* HvFlushGuestPhysicalAddressSpace hypercalls */ +struct hv_guest_mapping_flush { + u64 address_space; + u64 flags; +} __packed; + +/* + * HV_MAX_FLUSH_PAGES = "additional_pages" + 1. It's limited + * by the bitwidth of "additional_pages" in union hv_gpa_page_range. + */ +#define HV_MAX_FLUSH_PAGES (2048) +#define HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB 0 +#define HV_GPA_PAGE_RANGE_PAGE_SIZE_1GB 1 + +#define HV_FLUSH_ALL_PROCESSORS BIT(0) +#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1) +#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2) +#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3) + +/* HvFlushGuestPhysicalAddressList, HvExtCallMemoryHeatHint hypercall */ +union hv_gpa_page_range { + u64 address_space; + struct { + u64 additional_pages : 11; + u64 largepage : 1; + u64 basepfn : 52; + } page; + struct { + u64 reserved : 12; + u64 page_size : 1; + u64 reserved1 : 8; + u64 base_large_pfn : 43; + }; +}; + +/* + * All input flush parameters should be in single page. The max flush + * count is equal with how many entries of union hv_gpa_page_range can + * be populated into the input parameter page. + */ +#define HV_MAX_FLUSH_REP_COUNT ((HV_HYP_PAGE_SIZE - 2 * sizeof(u64)) / \ + sizeof(union hv_gpa_page_range)) + +struct hv_guest_mapping_flush_list { + u64 address_space; + u64 flags; + union hv_gpa_page_range gpa_list[HV_MAX_FLUSH_REP_COUNT]; +}; + +struct hv_tlb_flush { /* HV_INPUT_FLUSH_VIRTUAL_ADDRESS_LIST */ + u64 address_space; + u64 flags; + u64 processor_mask; + u64 gva_list[]; +} __packed; + +/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */ +struct hv_tlb_flush_ex { + u64 address_space; + u64 flags; + struct hv_vpset hv_vp_set; + u64 gva_list[]; +} __packed; + +struct ms_hyperv_tsc_page { /* HV_REFERENCE_TSC_PAGE */ + volatile u32 tsc_sequence; + u32 reserved1; + volatile u64 tsc_scale; + volatile s64 tsc_offset; +} __packed; + +/* Define the number of synthetic interrupt sources. */ +#define HV_SYNIC_SINT_COUNT (16) + +/* Define the expected SynIC version. */ +#define HV_SYNIC_VERSION_1 (0x1) +/* Valid SynIC vectors are 16-255. */ +#define HV_SYNIC_FIRST_VALID_VECTOR (16) + +#define HV_SYNIC_CONTROL_ENABLE (1ULL << 0) +#define HV_SYNIC_SIMP_ENABLE (1ULL << 0) +#define HV_SYNIC_SIEFP_ENABLE (1ULL << 0) +#define HV_SYNIC_SINT_MASKED (1ULL << 16) +#define HV_SYNIC_SINT_AUTO_EOI (1ULL << 17) +#define HV_SYNIC_SINT_VECTOR_MASK (0xFF) + +# + +/* Hyper-V defined statically assigned SINTs */ +#define HV_SYNIC_INTERCEPTION_SINT_INDEX 0x00000000 +#define HV_SYNIC_IOMMU_FAULT_SINT_INDEX 0x00000001 +#define HV_SYNIC_VMBUS_SINT_INDEX 0x00000002 +#define HV_SYNIC_FIRST_UNUSED_SINT_INDEX 0x00000005 + +/* mshv assigned SINT for doorbell */ +#define HV_SYNIC_DOORBELL_SINT_INDEX HV_SYNIC_FIRST_UNUSED_SINT_INDEX + +enum hv_interrupt_type { + HV_X64_INTERRUPT_TYPE_FIXED = 0x0000, + HV_X64_INTERRUPT_TYPE_LOWESTPRIORITY = 0x0001, + HV_X64_INTERRUPT_TYPE_SMI = 0x0002, + HV_X64_INTERRUPT_TYPE_REMOTEREAD = 0x0003, + HV_X64_INTERRUPT_TYPE_NMI = 0x0004, + HV_X64_INTERRUPT_TYPE_INIT = 0x0005, + HV_X64_INTERRUPT_TYPE_SIPI = 0x0006, + HV_X64_INTERRUPT_TYPE_EXTINT = 0x0007, + HV_X64_INTERRUPT_TYPE_LOCALINT0 = 0x0008, + HV_X64_INTERRUPT_TYPE_LOCALINT1 = 0x0009, + HV_X64_INTERRUPT_TYPE_MAXIMUM = 0x000A, +}; + +/* Define synthetic interrupt source. */ +union hv_synic_sint { + u64 as_uint64; + struct { + u64 vector : 8; + u64 reserved1 : 8; + u64 masked : 1; + u64 auto_eoi : 1; + u64 polling : 1; + u64 as_intercept : 1; + u64 proxy : 1; + u64 reserved2 : 43; + } __packed; +}; + +union hv_x64_xsave_xfem_register { + u64 as_uint64; + struct { + u32 low_uint32; + u32 high_uint32; + } __packed; + struct { + u64 legacy_x87 : 1; + u64 legacy_sse : 1; + u64 avx : 1; + u64 mpx_bndreg : 1; + u64 mpx_bndcsr : 1; + u64 avx_512_op_mask : 1; + u64 avx_512_zmmhi : 1; + u64 avx_512_zmm16_31 : 1; + u64 rsvd8_9 : 2; + u64 pasid : 1; + u64 cet_u : 1; + u64 cet_s : 1; + u64 rsvd13_16 : 4; + u64 xtile_cfg : 1; + u64 xtile_data : 1; + u64 rsvd19_63 : 45; + } __packed; +}; + +/* Synthetic timer configuration */ +union hv_stimer_config { /* HV_X64_MSR_STIMER_CONFIG_CONTENTS */ + u64 as_uint64; + struct { + u64 enable : 1; + u64 periodic : 1; + u64 lazy : 1; + u64 auto_enable : 1; + u64 apic_vector : 8; + u64 direct_mode : 1; + u64 reserved_z0 : 3; + u64 sintx : 4; + u64 reserved_z1 : 44; + } __packed; +}; + +/* Define the number of synthetic timers */ +#define HV_SYNIC_STIMER_COUNT (4) + +/* Define port identifier type. */ +union hv_port_id { + u32 asu32; + struct { + u32 id : 24; + u32 reserved : 8; + } __packed u; +}; + +#define HV_MESSAGE_SIZE (256) +#define HV_MESSAGE_PAYLOAD_BYTE_COUNT (240) +#define HV_MESSAGE_PAYLOAD_QWORD_COUNT (30) + +/* Define hypervisor message types. */ +enum hv_message_type { + HVMSG_NONE = 0x00000000, + + /* Memory access messages. */ + HVMSG_UNMAPPED_GPA = 0x80000000, + HVMSG_GPA_INTERCEPT = 0x80000001, + + /* Timer notification messages. */ + HVMSG_TIMER_EXPIRED = 0x80000010, + + /* Error messages. */ + HVMSG_INVALID_VP_REGISTER_VALUE = 0x80000020, + HVMSG_UNRECOVERABLE_EXCEPTION = 0x80000021, + HVMSG_UNSUPPORTED_FEATURE = 0x80000022, + + /* + * Opaque intercept message. The original intercept message is only + * accessible from the mapped intercept message page. + */ + HVMSG_OPAQUE_INTERCEPT = 0x8000003F, + + /* Trace buffer complete messages. */ + HVMSG_EVENTLOG_BUFFERCOMPLETE = 0x80000040, + + /* Hypercall intercept */ + HVMSG_HYPERCALL_INTERCEPT = 0x80000050, + + /* SynIC intercepts */ + HVMSG_SYNIC_EVENT_INTERCEPT = 0x80000060, + HVMSG_SYNIC_SINT_INTERCEPT = 0x80000061, + HVMSG_SYNIC_SINT_DELIVERABLE = 0x80000062, + + /* Async call completion intercept */ + HVMSG_ASYNC_CALL_COMPLETION = 0x80000070, + + /* Root scheduler messages */ + HVMSG_SCHEDULER_VP_SIGNAL_BITSET = 0x80000100, + HVMSG_SCHEDULER_VP_SIGNAL_PAIR = 0x80000101, + + /* Platform-specific processor intercept messages. */ + HVMSG_X64_IO_PORT_INTERCEPT = 0x80010000, + HVMSG_X64_MSR_INTERCEPT = 0x80010001, + HVMSG_X64_CPUID_INTERCEPT = 0x80010002, + HVMSG_X64_EXCEPTION_INTERCEPT = 0x80010003, + HVMSG_X64_APIC_EOI = 0x80010004, + HVMSG_X64_LEGACY_FP_ERROR = 0x80010005, + HVMSG_X64_IOMMU_PRQ = 0x80010006, + HVMSG_X64_HALT = 0x80010007, + HVMSG_X64_INTERRUPTION_DELIVERABLE = 0x80010008, + HVMSG_X64_SIPI_INTERCEPT = 0x80010009, +}; + +/* Define the format of the SIMP register */ +union hv_synic_simp { + u64 as_uint64; + struct { + u64 simp_enabled : 1; + u64 preserved : 11; + u64 base_simp_gpa : 52; + } __packed; +}; + +union hv_message_flags { + u8 asu8; + struct { + u8 msg_pending : 1; + u8 reserved : 7; + } __packed; +}; + +struct hv_message_header { + u32 message_type; + u8 payload_size; + union hv_message_flags message_flags; + u8 reserved[2]; + union { + u64 sender; + union hv_port_id port; + }; +} __packed; + +/* + * Message format for notifications delivered via + * intercept message(as_intercept=1) + */ +struct hv_notification_message_payload { + u32 sint_index; +} __packed; + +struct hv_message { + struct hv_message_header header; + union { + u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; + } u; +} __packed; + +/* Define the synthetic interrupt message page layout. */ +struct hv_message_page { + struct hv_message sint_message[HV_SYNIC_SINT_COUNT]; +} __packed; + +/* Define timer message payload structure. */ +struct hv_timer_message_payload { + __u32 timer_index; + __u32 reserved; + __u64 expiration_time; /* When the timer expired */ + __u64 delivery_time; /* When the message was delivered */ +} __packed; + +struct hv_x64_segment_register { + u64 base; + u32 limit; + u16 selector; + union { + struct { + u16 segment_type : 4; + u16 non_system_segment : 1; + u16 descriptor_privilege_level : 2; + u16 present : 1; + u16 reserved : 4; + u16 available : 1; + u16 _long : 1; + u16 _default : 1; + u16 granularity : 1; + } __packed; + u16 attributes; + }; +} __packed; + +struct hv_x64_table_register { + u16 pad[3]; + u16 limit; + u64 base; +} __packed; + +union hv_input_vtl { + u8 as_uint8; + struct { + u8 target_vtl : 4; + u8 use_target_vtl : 1; + u8 reserved_z : 3; + }; +} __packed; + +struct hv_init_vp_context { + u64 rip; + u64 rsp; + u64 rflags; + + struct hv_x64_segment_register cs; + struct hv_x64_segment_register ds; + struct hv_x64_segment_register es; + struct hv_x64_segment_register fs; + struct hv_x64_segment_register gs; + struct hv_x64_segment_register ss; + struct hv_x64_segment_register tr; + struct hv_x64_segment_register ldtr; + + struct hv_x64_table_register idtr; + struct hv_x64_table_register gdtr; + + u64 efer; + u64 cr0; + u64 cr3; + u64 cr4; + u64 msr_cr_pat; +} __packed; + +struct hv_enable_vp_vtl { + u64 partition_id; + u32 vp_index; + union hv_input_vtl target_vtl; + u8 mbz0; + u16 mbz1; + struct hv_init_vp_context vp_context; +} __packed; + +struct hv_get_vp_from_apic_id_in { + u64 partition_id; + union hv_input_vtl target_vtl; + u8 res[7]; + u32 apic_ids[]; +} __packed; + +struct hv_nested_enlightenments_control { + struct { + u32 directhypercall : 1; + u32 reserved : 31; + } __packed features; + struct { + u32 inter_partition_comm : 1; + u32 reserved : 31; + } __packed hypercall_controls; +} __packed; + +/* Define virtual processor assist page structure. */ +struct hv_vp_assist_page { + u32 apic_assist; + u32 reserved1; + u32 vtl_entry_reason; + u32 vtl_reserved; + u64 vtl_ret_x64rax; + u64 vtl_ret_x64rcx; + struct hv_nested_enlightenments_control nested_control; + u8 enlighten_vmentry; + u8 reserved2[7]; + u64 current_nested_vmcs; + u8 synthetic_time_unhalted_timer_expired; + u8 reserved3[7]; + u8 virtualization_fault_information[40]; + u8 reserved4[8]; + u8 intercept_message[256]; + u8 vtl_ret_actions[256]; +} __packed; + +enum hv_register_name { + /* Suspend Registers */ + HV_REGISTER_EXPLICIT_SUSPEND = 0x00000000, + HV_REGISTER_INTERCEPT_SUSPEND = 0x00000001, + HV_REGISTER_DISPATCH_SUSPEND = 0x00000003, + + /* Version - 128-bit result same as CPUID 0x40000002 */ + HV_REGISTER_HYPERVISOR_VERSION = 0x00000100, + + /* Feature Access (registers are 128 bits) - same as CPUID 0x40000003 - 0x4000000B */ + HV_REGISTER_PRIVILEGES_AND_FEATURES_INFO = 0x00000200, + HV_REGISTER_FEATURES_INFO = 0x00000201, + HV_REGISTER_IMPLEMENTATION_LIMITS_INFO = 0x00000202, + HV_REGISTER_HARDWARE_FEATURES_INFO = 0x00000203, + HV_REGISTER_CPU_MANAGEMENT_FEATURES_INFO = 0x00000204, + HV_REGISTER_SVM_FEATURES_INFO = 0x00000205, + HV_REGISTER_SKIP_LEVEL_FEATURES_INFO = 0x00000206, + HV_REGISTER_NESTED_VIRT_FEATURES_INFO = 0x00000207, + HV_REGISTER_IPT_FEATURES_INFO = 0x00000208, + + /* Guest Crash Registers */ + HV_REGISTER_GUEST_CRASH_P0 = 0x00000210, + HV_REGISTER_GUEST_CRASH_P1 = 0x00000211, + HV_REGISTER_GUEST_CRASH_P2 = 0x00000212, + HV_REGISTER_GUEST_CRASH_P3 = 0x00000213, + HV_REGISTER_GUEST_CRASH_P4 = 0x00000214, + HV_REGISTER_GUEST_CRASH_CTL = 0x00000215, + + /* Misc */ + HV_REGISTER_VP_RUNTIME = 0x00090000, + HV_REGISTER_GUEST_OS_ID = 0x00090002, + HV_REGISTER_VP_INDEX = 0x00090003, + HV_REGISTER_TIME_REF_COUNT = 0x00090004, + HV_REGISTER_CPU_MANAGEMENT_VERSION = 0x00090007, + HV_REGISTER_VP_ASSIST_PAGE = 0x00090013, + HV_REGISTER_VP_ROOT_SIGNAL_COUNT = 0x00090014, + HV_REGISTER_REFERENCE_TSC = 0x00090017, + + /* Hypervisor-defined Registers (Synic) */ + HV_REGISTER_SINT0 = 0x000A0000, + HV_REGISTER_SINT1 = 0x000A0001, + HV_REGISTER_SINT2 = 0x000A0002, + HV_REGISTER_SINT3 = 0x000A0003, + HV_REGISTER_SINT4 = 0x000A0004, + HV_REGISTER_SINT5 = 0x000A0005, + HV_REGISTER_SINT6 = 0x000A0006, + HV_REGISTER_SINT7 = 0x000A0007, + HV_REGISTER_SINT8 = 0x000A0008, + HV_REGISTER_SINT9 = 0x000A0009, + HV_REGISTER_SINT10 = 0x000A000A, + HV_REGISTER_SINT11 = 0x000A000B, + HV_REGISTER_SINT12 = 0x000A000C, + HV_REGISTER_SINT13 = 0x000A000D, + HV_REGISTER_SINT14 = 0x000A000E, + HV_REGISTER_SINT15 = 0x000A000F, + HV_REGISTER_SCONTROL = 0x000A0010, + HV_REGISTER_SVERSION = 0x000A0011, + HV_REGISTER_SIEFP = 0x000A0012, + HV_REGISTER_SIMP = 0x000A0013, + HV_REGISTER_EOM = 0x000A0014, + HV_REGISTER_SIRBP = 0x000A0015, + + HV_REGISTER_NESTED_SINT0 = 0x000A1000, + HV_REGISTER_NESTED_SINT1 = 0x000A1001, + HV_REGISTER_NESTED_SINT2 = 0x000A1002, + HV_REGISTER_NESTED_SINT3 = 0x000A1003, + HV_REGISTER_NESTED_SINT4 = 0x000A1004, + HV_REGISTER_NESTED_SINT5 = 0x000A1005, + HV_REGISTER_NESTED_SINT6 = 0x000A1006, + HV_REGISTER_NESTED_SINT7 = 0x000A1007, + HV_REGISTER_NESTED_SINT8 = 0x000A1008, + HV_REGISTER_NESTED_SINT9 = 0x000A1009, + HV_REGISTER_NESTED_SINT10 = 0x000A100A, + HV_REGISTER_NESTED_SINT11 = 0x000A100B, + HV_REGISTER_NESTED_SINT12 = 0x000A100C, + HV_REGISTER_NESTED_SINT13 = 0x000A100D, + HV_REGISTER_NESTED_SINT14 = 0x000A100E, + HV_REGISTER_NESTED_SINT15 = 0x000A100F, + HV_REGISTER_NESTED_SCONTROL = 0x000A1010, + HV_REGISTER_NESTED_SVERSION = 0x000A1011, + HV_REGISTER_NESTED_SIFP = 0x000A1012, + HV_REGISTER_NESTED_SIPP = 0x000A1013, + HV_REGISTER_NESTED_EOM = 0x000A1014, + HV_REGISTER_NESTED_SIRBP = 0x000a1015, + + /* Hypervisor-defined Registers (Synthetic Timers) */ + HV_REGISTER_STIMER0_CONFIG = 0x000B0000, + HV_REGISTER_STIMER0_COUNT = 0x000B0001, + + /* VSM */ + HV_REGISTER_VSM_VP_STATUS = 0x000D0003, +}; + +/* + * Arch compatibility regs for use with hv_set/get_register + */ +#if defined(CONFIG_X86) + +/* + * To support arch-generic code calling hv_set/get_register: + * - On x86, HV_MSR_ indicates an MSR accessed via rdmsrl/wrmsrl + * - On ARM, HV_MSR_ indicates a VP register accessed via hypercall + */ +#define HV_MSR_CRASH_P0 (HV_X64_MSR_CRASH_P0) +#define HV_MSR_CRASH_P1 (HV_X64_MSR_CRASH_P1) +#define HV_MSR_CRASH_P2 (HV_X64_MSR_CRASH_P2) +#define HV_MSR_CRASH_P3 (HV_X64_MSR_CRASH_P3) +#define HV_MSR_CRASH_P4 (HV_X64_MSR_CRASH_P4) +#define HV_MSR_CRASH_CTL (HV_X64_MSR_CRASH_CTL) + +#define HV_MSR_VP_INDEX (HV_X64_MSR_VP_INDEX) +#define HV_MSR_TIME_REF_COUNT (HV_X64_MSR_TIME_REF_COUNT) +#define HV_MSR_REFERENCE_TSC (HV_X64_MSR_REFERENCE_TSC) + +#define HV_MSR_SINT0 (HV_X64_MSR_SINT0) +#define HV_MSR_SVERSION (HV_X64_MSR_SVERSION) +#define HV_MSR_SCONTROL (HV_X64_MSR_SCONTROL) +#define HV_MSR_SIEFP (HV_X64_MSR_SIEFP) +#define HV_MSR_SIMP (HV_X64_MSR_SIMP) +#define HV_MSR_EOM (HV_X64_MSR_EOM) +#define HV_MSR_SIRBP (HV_X64_MSR_SIRBP) + +#define HV_MSR_NESTED_SCONTROL (HV_X64_MSR_NESTED_SCONTROL) +#define HV_MSR_NESTED_SVERSION (HV_X64_MSR_NESTED_SVERSION) +#define HV_MSR_NESTED_SIEFP (HV_X64_MSR_NESTED_SIEFP) +#define HV_MSR_NESTED_SIMP (HV_X64_MSR_NESTED_SIMP) +#define HV_MSR_NESTED_EOM (HV_X64_MSR_NESTED_EOM) +#define HV_MSR_NESTED_SINT0 (HV_X64_MSR_NESTED_SINT0) + +#define HV_MSR_STIMER0_CONFIG (HV_X64_MSR_STIMER0_CONFIG) +#define HV_MSR_STIMER0_COUNT (HV_X64_MSR_STIMER0_COUNT) + +#elif defined(CONFIG_ARM64) /* CONFIG_X86 */ + +#define HV_MSR_CRASH_P0 (HV_REGISTER_GUEST_CRASH_P0) +#define HV_MSR_CRASH_P1 (HV_REGISTER_GUEST_CRASH_P1) +#define HV_MSR_CRASH_P2 (HV_REGISTER_GUEST_CRASH_P2) +#define HV_MSR_CRASH_P3 (HV_REGISTER_GUEST_CRASH_P3) +#define HV_MSR_CRASH_P4 (HV_REGISTER_GUEST_CRASH_P4) +#define HV_MSR_CRASH_CTL (HV_REGISTER_GUEST_CRASH_CTL) + +#define HV_MSR_VP_INDEX (HV_REGISTER_VP_INDEX) +#define HV_MSR_TIME_REF_COUNT (HV_REGISTER_TIME_REF_COUNT) +#define HV_MSR_REFERENCE_TSC (HV_REGISTER_REFERENCE_TSC) + +#define HV_MSR_SINT0 (HV_REGISTER_SINT0) +#define HV_MSR_SCONTROL (HV_REGISTER_SCONTROL) +#define HV_MSR_SIEFP (HV_REGISTER_SIEFP) +#define HV_MSR_SIMP (HV_REGISTER_SIMP) +#define HV_MSR_EOM (HV_REGISTER_EOM) +#define HV_MSR_SIRBP (HV_REGISTER_SIRBP) + +#define HV_MSR_STIMER0_CONFIG (HV_REGISTER_STIMER0_CONFIG) +#define HV_MSR_STIMER0_COUNT (HV_REGISTER_STIMER0_COUNT) + +#endif /* CONFIG_ARM64 */ + +union hv_explicit_suspend_register { + u64 as_uint64; + struct { + u64 suspended : 1; + u64 reserved : 63; + } __packed; +}; + +union hv_intercept_suspend_register { + u64 as_uint64; + struct { + u64 suspended : 1; + u64 reserved : 63; + } __packed; +}; + +union hv_dispatch_suspend_register { + u64 as_uint64; + struct { + u64 suspended : 1; + u64 reserved : 63; + } __packed; +}; + +union hv_arm64_pending_interruption_register { + u64 as_uint64; + struct { + u64 interruption_pending : 1; + u64 interruption_type: 1; + u64 reserved : 30; + u64 error_code : 32; + } __packed; +}; + +union hv_arm64_interrupt_state_register { + u64 as_uint64; + struct { + u64 interrupt_shadow : 1; + u64 reserved : 63; + } __packed; +}; + +union hv_arm64_pending_synthetic_exception_event { + u64 as_uint64[2]; + struct { + u8 event_pending : 1; + u8 event_type : 3; + u8 reserved : 4; + u8 rsvd[3]; + u32 exception_type; + u64 context; + } __packed; +}; + +union hv_x64_interrupt_state_register { + u64 as_uint64; + struct { + u64 interrupt_shadow : 1; + u64 nmi_masked : 1; + u64 reserved : 62; + } __packed; +}; + +union hv_x64_pending_interruption_register { + u64 as_uint64; + struct { + u32 interruption_pending : 1; + u32 interruption_type : 3; + u32 deliver_error_code : 1; + u32 instruction_length : 4; + u32 nested_event : 1; + u32 reserved : 6; + u32 interruption_vector : 16; + u32 error_code; + } __packed; +}; + +union hv_register_value { + struct hv_u128 reg128; + u64 reg64; + u32 reg32; + u16 reg16; + u8 reg8; + + struct hv_x64_segment_register segment; + struct hv_x64_table_register table; + union hv_explicit_suspend_register explicit_suspend; + union hv_intercept_suspend_register intercept_suspend; + union hv_dispatch_suspend_register dispatch_suspend; +#ifdef CONFIG_ARM64 + union hv_arm64_interrupt_state_register interrupt_state; + union hv_arm64_pending_interruption_register pending_interruption; +#endif +#ifdef CONFIG_X86 + union hv_x64_interrupt_state_register interrupt_state; + union hv_x64_pending_interruption_register pending_interruption; +#endif + union hv_arm64_pending_synthetic_exception_event pending_synthetic_exception_event; +}; + +/* NOTE: Linux helper struct - NOT from Hyper-V code. */ +struct hv_output_get_vp_registers { + DECLARE_FLEX_ARRAY(union hv_register_value, values); +}; + +#if defined(CONFIG_ARM64) +/* HvGetVpRegisters returns an array of these output elements */ +struct hv_get_vp_registers_output { + union { + struct { + u32 a; + u32 b; + u32 c; + u32 d; + } as32 __packed; + struct { + u64 low; + u64 high; + } as64 __packed; + }; +}; + +#endif /* CONFIG_ARM64 */ + +struct hv_register_assoc { + u32 name; /* enum hv_register_name */ + u32 reserved1; + u64 reserved2; + union hv_register_value value; +} __packed; + +struct hv_input_get_vp_registers { + u64 partition_id; + u32 vp_index; + union hv_input_vtl input_vtl; + u8 rsvd_z8; + u16 rsvd_z16; + u32 names[]; +} __packed; + +struct hv_input_set_vp_registers { + u64 partition_id; + u32 vp_index; + union hv_input_vtl input_vtl; + u8 rsvd_z8; + u16 rsvd_z16; + struct hv_register_assoc elements[]; +} __packed; + +#define HV_UNMAP_GPA_LARGE_PAGE 0x2 + +/* HvCallSendSyntheticClusterIpi hypercall */ +struct hv_send_ipi { /* HV_INPUT_SEND_SYNTHETIC_CLUSTER_IPI */ + u32 vector; + u32 reserved; + u64 cpu_mask; +} __packed; + +#define HV_X64_VTL_MASK GENMASK(3, 0) + +/* Hyper-V memory host visibility */ +enum hv_mem_host_visibility { + VMBUS_PAGE_NOT_VISIBLE = 0, + VMBUS_PAGE_VISIBLE_READ_ONLY = 1, + VMBUS_PAGE_VISIBLE_READ_WRITE = 3 +}; + +/* HvCallModifySparseGpaPageHostVisibility hypercall */ +#define HV_MAX_MODIFY_GPA_REP_COUNT ((HV_HYP_PAGE_SIZE / sizeof(u64)) - 2) +struct hv_gpa_range_for_visibility { + u64 partition_id; + u32 host_visibility : 2; + u32 reserved0 : 30; + u32 reserved1; + u64 gpa_page_list[HV_MAX_MODIFY_GPA_REP_COUNT]; +} __packed; + +#if defined(CONFIG_X86) +union hv_msi_address_register { /* HV_MSI_ADDRESS */ + u32 as_uint32; + struct { + u32 reserved1 : 2; + u32 destination_mode : 1; + u32 redirection_hint : 1; + u32 reserved2 : 8; + u32 destination_id : 8; + u32 msi_base : 12; + }; +} __packed; + +union hv_msi_data_register { /* HV_MSI_ENTRY.Data */ + u32 as_uint32; + struct { + u32 vector : 8; + u32 delivery_mode : 3; + u32 reserved1 : 3; + u32 level_assert : 1; + u32 trigger_mode : 1; + u32 reserved2 : 16; + }; +} __packed; + +union hv_msi_entry { /* HV_MSI_ENTRY */ + + u64 as_uint64; + struct { + union hv_msi_address_register address; + union hv_msi_data_register data; + } __packed; +}; + +#elif defined(CONFIG_ARM64) /* CONFIG_X86 */ + +union hv_msi_entry { + u64 as_uint64[2]; + struct { + u64 address; + u32 data; + u32 reserved; + } __packed; +}; +#endif /* CONFIG_ARM64 */ + +union hv_ioapic_rte { + u64 as_uint64; + + struct { + u32 vector : 8; + u32 delivery_mode : 3; + u32 destination_mode : 1; + u32 delivery_status : 1; + u32 interrupt_polarity : 1; + u32 remote_irr : 1; + u32 trigger_mode : 1; + u32 interrupt_mask : 1; + u32 reserved1 : 15; + + u32 reserved2 : 24; + u32 destination_id : 8; + }; + + struct { + u32 low_uint32; + u32 high_uint32; + }; +} __packed; + +enum hv_interrupt_source { /* HV_INTERRUPT_SOURCE */ + HV_INTERRUPT_SOURCE_MSI = 1, /* MSI and MSI-X */ + HV_INTERRUPT_SOURCE_IOAPIC, +}; + +struct hv_interrupt_entry { /* HV_INTERRUPT_ENTRY */ + u32 source; + u32 reserved1; + union { + union hv_msi_entry msi_entry; + union hv_ioapic_rte ioapic_rte; + }; +} __packed; + +#define HV_DEVICE_INTERRUPT_TARGET_MULTICAST 1 +#define HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET 2 + +struct hv_device_interrupt_target { /* HV_DEVICE_INTERRUPT_TARGET */ + u32 vector; + u32 flags; /* HV_DEVICE_INTERRUPT_TARGET_* above */ + union { + u64 vp_mask; + struct hv_vpset vp_set; + }; +} __packed; + +struct hv_retarget_device_interrupt { /* HV_INPUT_RETARGET_DEVICE_INTERRUPT */ + u64 partition_id; /* use "self" */ + u64 device_id; + struct hv_interrupt_entry int_entry; + u64 reserved2; + struct hv_device_interrupt_target int_target; +} __packed __aligned(8); + +/* Data structures for HVCALL_MMIO_READ and HVCALL_MMIO_WRITE */ +#define HV_HYPERCALL_MMIO_MAX_DATA_LENGTH 64 + +struct hv_mmio_read_input { /* HV_INPUT_MEMORY_MAPPED_IO_READ */ + u64 gpa; + u32 size; + u32 reserved; +} __packed; + +struct hv_mmio_read_output { + u8 data[HV_HYPERCALL_MMIO_MAX_DATA_LENGTH]; +} __packed; + +struct hv_mmio_write_input { + u64 gpa; + u32 size; + u32 reserved; + u8 data[HV_HYPERCALL_MMIO_MAX_DATA_LENGTH]; +} __packed; + +#endif /* _HV_HVGDK_MINI_H */ diff --git a/include/hyperv/hvhdk.h b/include/hyperv/hvhdk.h new file mode 100644 index 000000000000..64407c2a3809 --- /dev/null +++ b/include/hyperv/hvhdk.h @@ -0,0 +1,733 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Type definitions for the Microsoft hypervisor. + */ +#ifndef _HV_HVHDK_H +#define _HV_HVHDK_H + +#include + +#include "hvhdk_mini.h" +#include "hvgdk.h" + +/* Bits for dirty mask of hv_vp_register_page */ +#define HV_X64_REGISTER_CLASS_GENERAL 0 +#define HV_X64_REGISTER_CLASS_IP 1 +#define HV_X64_REGISTER_CLASS_XMM 2 +#define HV_X64_REGISTER_CLASS_SEGMENT 3 +#define HV_X64_REGISTER_CLASS_FLAGS 4 + +#define HV_VP_REGISTER_PAGE_VERSION_1 1u + +struct hv_vp_register_page { + u16 version; + u8 isvalid; + u8 rsvdz; + u32 dirty; + union { + struct { + /* General purpose registers + * (HV_X64_REGISTER_CLASS_GENERAL) + */ + union { + struct { + u64 rax; + u64 rcx; + u64 rdx; + u64 rbx; + u64 rsp; + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + } __packed; + + u64 gp_registers[16]; + }; + /* Instruction pointer (HV_X64_REGISTER_CLASS_IP) */ + u64 rip; + /* Flags (HV_X64_REGISTER_CLASS_FLAGS) */ + u64 rflags; + } __packed; + + u64 registers[18]; + }; + /* Volatile XMM registers (HV_X64_REGISTER_CLASS_XMM) */ + union { + struct { + struct hv_u128 xmm0; + struct hv_u128 xmm1; + struct hv_u128 xmm2; + struct hv_u128 xmm3; + struct hv_u128 xmm4; + struct hv_u128 xmm5; + } __packed; + + struct hv_u128 xmm_registers[6]; + }; + /* Segment registers (HV_X64_REGISTER_CLASS_SEGMENT) */ + union { + struct { + struct hv_x64_segment_register es; + struct hv_x64_segment_register cs; + struct hv_x64_segment_register ss; + struct hv_x64_segment_register ds; + struct hv_x64_segment_register fs; + struct hv_x64_segment_register gs; + } __packed; + + struct hv_x64_segment_register segment_registers[6]; + }; + /* Misc. control registers (cannot be set via this interface) */ + u64 cr0; + u64 cr3; + u64 cr4; + u64 cr8; + u64 efer; + u64 dr7; + union hv_x64_pending_interruption_register pending_interruption; + union hv_x64_interrupt_state_register interrupt_state; + u64 instruction_emulation_hints; +} __packed; + +#define HV_PARTITION_PROCESSOR_FEATURES_BANKS 2 + +union hv_partition_processor_features { + u64 as_uint64[HV_PARTITION_PROCESSOR_FEATURES_BANKS]; + struct { + u64 sse3_support : 1; + u64 lahf_sahf_support : 1; + u64 ssse3_support : 1; + u64 sse4_1_support : 1; + u64 sse4_2_support : 1; + u64 sse4a_support : 1; + u64 xop_support : 1; + u64 pop_cnt_support : 1; + u64 cmpxchg16b_support : 1; + u64 altmovcr8_support : 1; + u64 lzcnt_support : 1; + u64 mis_align_sse_support : 1; + u64 mmx_ext_support : 1; + u64 amd3dnow_support : 1; + u64 extended_amd3dnow_support : 1; + u64 page_1gb_support : 1; + u64 aes_support : 1; + u64 pclmulqdq_support : 1; + u64 pcid_support : 1; + u64 fma4_support : 1; + u64 f16c_support : 1; + u64 rd_rand_support : 1; + u64 rd_wr_fs_gs_support : 1; + u64 smep_support : 1; + u64 enhanced_fast_string_support : 1; + u64 bmi1_support : 1; + u64 bmi2_support : 1; + u64 hle_support_deprecated : 1; + u64 rtm_support_deprecated : 1; + u64 movbe_support : 1; + u64 npiep1_support : 1; + u64 dep_x87_fpu_save_support : 1; + u64 rd_seed_support : 1; + u64 adx_support : 1; + u64 intel_prefetch_support : 1; + u64 smap_support : 1; + u64 hle_support : 1; + u64 rtm_support : 1; + u64 rdtscp_support : 1; + u64 clflushopt_support : 1; + u64 clwb_support : 1; + u64 sha_support : 1; + u64 x87_pointers_saved_support : 1; + u64 invpcid_support : 1; + u64 ibrs_support : 1; + u64 stibp_support : 1; + u64 ibpb_support: 1; + u64 unrestricted_guest_support : 1; + u64 mdd_support : 1; + u64 fast_short_rep_mov_support : 1; + u64 l1dcache_flush_support : 1; + u64 rdcl_no_support : 1; + u64 ibrs_all_support : 1; + u64 skip_l1df_support : 1; + u64 ssb_no_support : 1; + u64 rsb_a_no_support : 1; + u64 virt_spec_ctrl_support : 1; + u64 rd_pid_support : 1; + u64 umip_support : 1; + u64 mbs_no_support : 1; + u64 mb_clear_support : 1; + u64 taa_no_support : 1; + u64 tsx_ctrl_support : 1; + /* + * N.B. The final processor feature bit in bank 0 is reserved to + * simplify potential downlevel backports. + */ + u64 reserved_bank0 : 1; + + /* N.B. Begin bank 1 processor features. */ + u64 acount_mcount_support : 1; + u64 tsc_invariant_support : 1; + u64 cl_zero_support : 1; + u64 rdpru_support : 1; + u64 la57_support : 1; + u64 mbec_support : 1; + u64 nested_virt_support : 1; + u64 psfd_support : 1; + u64 cet_ss_support : 1; + u64 cet_ibt_support : 1; + u64 vmx_exception_inject_support : 1; + u64 enqcmd_support : 1; + u64 umwait_tpause_support : 1; + u64 movdiri_support : 1; + u64 movdir64b_support : 1; + u64 cldemote_support : 1; + u64 serialize_support : 1; + u64 tsc_deadline_tmr_support : 1; + u64 tsc_adjust_support : 1; + u64 fzlrep_movsb : 1; + u64 fsrep_stosb : 1; + u64 fsrep_cmpsb : 1; + u64 reserved_bank1 : 42; + } __packed; +}; + +union hv_partition_processor_xsave_features { + struct { + u64 xsave_support : 1; + u64 xsaveopt_support : 1; + u64 avx_support : 1; + u64 reserved1 : 61; + } __packed; + u64 as_uint64; +}; + +struct hv_partition_creation_properties { + union hv_partition_processor_features disabled_processor_features; + union hv_partition_processor_xsave_features + disabled_processor_xsave_features; +} __packed; + +#define HV_PARTITION_SYNTHETIC_PROCESSOR_FEATURES_BANKS 1 + +union hv_partition_synthetic_processor_features { + u64 as_uint64[HV_PARTITION_SYNTHETIC_PROCESSOR_FEATURES_BANKS]; + + struct { + u64 hypervisor_present : 1; + /* Support for HV#1: (CPUID leaves 0x40000000 - 0x40000006)*/ + u64 hv1 : 1; + u64 access_vp_run_time_reg : 1; /* HV_X64_MSR_VP_RUNTIME */ + u64 access_partition_reference_counter : 1; /* HV_X64_MSR_TIME_REF_COUNT */ + u64 access_synic_regs : 1; /* SINT-related registers */ + /* + * Access to HV_X64_MSR_STIMER0_CONFIG through + * HV_X64_MSR_STIMER3_COUNT. + */ + u64 access_synthetic_timer_regs : 1; + u64 access_intr_ctrl_regs : 1; /* APIC MSRs and VP assist page*/ + /* HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL */ + u64 access_hypercall_regs : 1; + u64 access_vp_index : 1; + u64 access_partition_reference_tsc : 1; + u64 access_guest_idle_reg : 1; + u64 access_frequency_regs : 1; + u64 reserved_z12 : 1; + u64 reserved_z13 : 1; + u64 reserved_z14 : 1; + u64 enable_extended_gva_ranges_for_flush_virtual_address_list : 1; + u64 reserved_z16 : 1; + u64 reserved_z17 : 1; + /* Use fast hypercall output. Corresponds to privilege. */ + u64 fast_hypercall_output : 1; + u64 reserved_z19 : 1; + u64 start_virtual_processor : 1; /* Can start VPs */ + u64 reserved_z21 : 1; + /* Synthetic timers in direct mode. */ + u64 direct_synthetic_timers : 1; + u64 reserved_z23 : 1; + u64 extended_processor_masks : 1; + + /* Enable various hypercalls */ + u64 tb_flush_hypercalls : 1; + u64 synthetic_cluster_ipi : 1; + u64 notify_long_spin_wait : 1; + u64 query_numa_distance : 1; + u64 signal_events : 1; + u64 retarget_device_interrupt : 1; + u64 restore_time : 1; + + /* EnlightenedVmcs nested enlightenment is supported. */ + u64 enlightened_vmcs : 1; + u64 reserved : 31; + } __packed; +}; + +#define HV_MAKE_COMPATIBILITY_VERSION(major_, minor_) \ + ((u32)((major_) << 8 | (minor_))) + +#define HV_COMPATIBILITY_21_H2 HV_MAKE_COMPATIBILITY_VERSION(0X6, 0X9) + +union hv_partition_isolation_properties { + u64 as_uint64; + struct { + u64 isolation_type: 5; + u64 isolation_host_type : 2; + u64 rsvd_z: 5; + u64 shared_gpa_boundary_page_number: 52; + } __packed; +}; + +/* + * Various isolation types supported by MSHV. + */ +#define HV_PARTITION_ISOLATION_TYPE_NONE 0 +#define HV_PARTITION_ISOLATION_TYPE_SNP 2 +#define HV_PARTITION_ISOLATION_TYPE_TDX 3 + +/* + * Various host isolation types supported by MSHV. + */ +#define HV_PARTITION_ISOLATION_HOST_TYPE_NONE 0x0 +#define HV_PARTITION_ISOLATION_HOST_TYPE_HARDWARE 0x1 +#define HV_PARTITION_ISOLATION_HOST_TYPE_RESERVED 0x2 + +/* Note: Exo partition is enabled by default */ +#define HV_PARTITION_CREATION_FLAG_EXO_PARTITION BIT(8) +#define HV_PARTITION_CREATION_FLAG_LAPIC_ENABLED BIT(13) +#define HV_PARTITION_CREATION_FLAG_INTERCEPT_MESSAGE_PAGE_ENABLED BIT(19) +#define HV_PARTITION_CREATION_FLAG_X2APIC_CAPABLE BIT(22) + +struct hv_input_create_partition { + u64 flags; + struct hv_proximity_domain_info proximity_domain_info; + u32 compatibility_version; + u32 padding; + struct hv_partition_creation_properties partition_creation_properties; + union hv_partition_isolation_properties isolation_properties; +} __packed; + +struct hv_output_create_partition { + u64 partition_id; +} __packed; + +struct hv_input_initialize_partition { + u64 partition_id; +} __packed; + +struct hv_input_finalize_partition { + u64 partition_id; +} __packed; + +struct hv_input_delete_partition { + u64 partition_id; +} __packed; + +struct hv_input_get_partition_property { + u64 partition_id; + u32 property_code; /* enum hv_partition_property_code */ + u32 padding; +} __packed; + +struct hv_output_get_partition_property { + u64 property_value; +} __packed; + +struct hv_input_set_partition_property { + u64 partition_id; + u32 property_code; /* enum hv_partition_property_code */ + u32 padding; + u64 property_value; +} __packed; + +enum hv_vp_state_page_type { + HV_VP_STATE_PAGE_REGISTERS = 0, + HV_VP_STATE_PAGE_INTERCEPT_MESSAGE = 1, + HV_VP_STATE_PAGE_COUNT +}; + +struct hv_input_map_vp_state_page { + u64 partition_id; + u32 vp_index; + u32 type; /* enum hv_vp_state_page_type */ +} __packed; + +struct hv_output_map_vp_state_page { + u64 map_location; /* GPA page number */ +} __packed; + +struct hv_input_unmap_vp_state_page { + u64 partition_id; + u32 vp_index; + u32 type; /* enum hv_vp_state_page_type */ +} __packed; + +struct hv_opaque_intercept_message { + u32 vp_index; +} __packed; + +enum hv_port_type { + HV_PORT_TYPE_MESSAGE = 1, + HV_PORT_TYPE_EVENT = 2, + HV_PORT_TYPE_MONITOR = 3, + HV_PORT_TYPE_DOORBELL = 4 /* Root Partition only */ +}; + +struct hv_port_info { + u32 port_type; /* enum hv_port_type */ + u32 padding; + union { + struct { + u32 target_sint; + u32 target_vp; + u64 rsvdz; + } message_port_info; + struct { + u32 target_sint; + u32 target_vp; + u16 base_flag_number; + u16 flag_count; + u32 rsvdz; + } event_port_info; + struct { + u64 monitor_address; + u64 rsvdz; + } monitor_port_info; + struct { + u32 target_sint; + u32 target_vp; + u64 rsvdz; + } doorbell_port_info; + }; +} __packed; + +struct hv_connection_info { + u32 port_type; + u32 padding; + union { + struct { + u64 rsvdz; + } message_connection_info; + struct { + u64 rsvdz; + } event_connection_info; + struct { + u64 monitor_address; + } monitor_connection_info; + struct { + u64 gpa; + u64 trigger_value; + u64 flags; + } doorbell_connection_info; + }; +} __packed; + +/* Define synthetic interrupt controller flag constants. */ +#define HV_EVENT_FLAGS_COUNT (256 * 8) +#define HV_EVENT_FLAGS_BYTE_COUNT (256) +#define HV_EVENT_FLAGS32_COUNT (256 / sizeof(u32)) + +/* linux side we create long version of flags to use long bit ops on flags */ +#define HV_EVENT_FLAGS_UL_COUNT (256 / sizeof(ulong)) + +/* Define the synthetic interrupt controller event flags format. */ +union hv_synic_event_flags { + unsigned char flags8[HV_EVENT_FLAGS_BYTE_COUNT]; + u32 flags32[HV_EVENT_FLAGS32_COUNT]; + ulong flags[HV_EVENT_FLAGS_UL_COUNT]; /* linux only */ +}; + +struct hv_synic_event_flags_page { + volatile union hv_synic_event_flags event_flags[HV_SYNIC_SINT_COUNT]; +}; + +#define HV_SYNIC_EVENT_RING_MESSAGE_COUNT 63 + +struct hv_synic_event_ring { + u8 signal_masked; + u8 ring_full; + u16 reserved_z; + u32 data[HV_SYNIC_EVENT_RING_MESSAGE_COUNT]; +} __packed; + +struct hv_synic_event_ring_page { + struct hv_synic_event_ring sint_event_ring[HV_SYNIC_SINT_COUNT]; +}; + +/* Define SynIC control register. */ +union hv_synic_scontrol { + u64 as_uint64; + struct { + u64 enable : 1; + u64 reserved : 63; + } __packed; +}; + +/* Define the format of the SIEFP register */ +union hv_synic_siefp { + u64 as_uint64; + struct { + u64 siefp_enabled : 1; + u64 preserved : 11; + u64 base_siefp_gpa : 52; + } __packed; +}; + +union hv_synic_sirbp { + u64 as_uint64; + struct { + u64 sirbp_enabled : 1; + u64 preserved : 11; + u64 base_sirbp_gpa : 52; + } __packed; +}; + +union hv_interrupt_control { + u64 as_uint64; + struct { + u32 interrupt_type; /* enum hv_interrupt_type */ + u32 level_triggered : 1; + u32 logical_dest_mode : 1; + u32 rsvd : 30; + } __packed; +}; + +struct hv_stimer_state { + struct { + u32 undelivered_msg_pending : 1; + u32 reserved : 31; + } __packed flags; + u32 resvd; + u64 config; + u64 count; + u64 adjustment; + u64 undelivered_exp_time; +} __packed; + +struct hv_synthetic_timers_state { + struct hv_stimer_state timers[HV_SYNIC_STIMER_COUNT]; + u64 reserved[5]; +} __packed; + +union hv_input_delete_vp { + u64 as_uint64[2]; + struct { + u64 partition_id; + u32 vp_index; + u8 reserved[4]; + } __packed; +} __packed; + +struct hv_input_assert_virtual_interrupt { + u64 partition_id; + union hv_interrupt_control control; + u64 dest_addr; /* cpu's apic id */ + u32 vector; + u8 target_vtl; + u8 rsvd_z0; + u16 rsvd_z1; +} __packed; + +struct hv_input_create_port { + u64 port_partition_id; + union hv_port_id port_id; + u8 port_vtl; + u8 min_connection_vtl; + u16 padding; + u64 connection_partition_id; + struct hv_port_info port_info; + struct hv_proximity_domain_info proximity_domain_info; +} __packed; + +union hv_input_delete_port { + u64 as_uint64[2]; + struct { + u64 port_partition_id; + union hv_port_id port_id; + u32 reserved; + }; +} __packed; + +struct hv_input_connect_port { + u64 connection_partition_id; + union hv_connection_id connection_id; + u8 connection_vtl; + u8 rsvdz0; + u16 rsvdz1; + u64 port_partition_id; + union hv_port_id port_id; + u32 reserved2; + struct hv_connection_info connection_info; + struct hv_proximity_domain_info proximity_domain_info; +} __packed; + +union hv_input_disconnect_port { + u64 as_uint64[2]; + struct { + u64 connection_partition_id; + union hv_connection_id connection_id; + u32 is_doorbell: 1; + u32 reserved: 31; + } __packed; +} __packed; + +union hv_input_notify_port_ring_empty { + u64 as_uint64; + struct { + u32 sint_index; + u32 reserved; + }; +} __packed; + +struct hv_vp_state_data_xsave { + u64 flags; + union hv_x64_xsave_xfem_register states; +} __packed; + +/* + * For getting and setting VP state, there are two options based on the state type: + * + * 1.) Data that is accessed by PFNs in the input hypercall page. This is used + * for state which may not fit into the hypercall pages. + * 2.) Data that is accessed directly in the input\output hypercall pages. + * This is used for state that will always fit into the hypercall pages. + * + * In the future this could be dynamic based on the size if needed. + * + * Note these hypercalls have an 8-byte aligned variable header size as per the tlfs + */ + +#define HV_GET_SET_VP_STATE_TYPE_PFN BIT(31) + +enum hv_get_set_vp_state_type { + /* HvGetSetVpStateLocalInterruptControllerState - APIC/GIC state */ + HV_GET_SET_VP_STATE_LAPIC_STATE = 0 | HV_GET_SET_VP_STATE_TYPE_PFN, + HV_GET_SET_VP_STATE_XSAVE = 1 | HV_GET_SET_VP_STATE_TYPE_PFN, + HV_GET_SET_VP_STATE_SIM_PAGE = 2 | HV_GET_SET_VP_STATE_TYPE_PFN, + HV_GET_SET_VP_STATE_SIEF_PAGE = 3 | HV_GET_SET_VP_STATE_TYPE_PFN, + HV_GET_SET_VP_STATE_SYNTHETIC_TIMERS = 4, +}; + +struct hv_vp_state_data { + u32 type; + u32 rsvd; + struct hv_vp_state_data_xsave xsave; +} __packed; + +struct hv_input_get_vp_state { + u64 partition_id; + u32 vp_index; + u8 input_vtl; + u8 rsvd0; + u16 rsvd1; + struct hv_vp_state_data state_data; + u64 output_data_pfns[]; +} __packed; + +union hv_output_get_vp_state { + struct hv_synthetic_timers_state synthetic_timers_state; +} __packed; + +union hv_input_set_vp_state_data { + u64 pfns; + u8 bytes; +} __packed; + +struct hv_input_set_vp_state { + u64 partition_id; + u32 vp_index; + u8 input_vtl; + u8 rsvd0; + u16 rsvd1; + struct hv_vp_state_data state_data; + union hv_input_set_vp_state_data data[]; +} __packed; + +/* + * Dispatch state for the VP communicated by the hypervisor to the + * VP-dispatching thread in the root on return from HVCALL_DISPATCH_VP. + */ +enum hv_vp_dispatch_state { + HV_VP_DISPATCH_STATE_INVALID = 0, + HV_VP_DISPATCH_STATE_BLOCKED = 1, + HV_VP_DISPATCH_STATE_READY = 2, +}; + +/* + * Dispatch event that caused the current dispatch state on return from + * HVCALL_DISPATCH_VP. + */ +enum hv_vp_dispatch_event { + HV_VP_DISPATCH_EVENT_INVALID = 0x00000000, + HV_VP_DISPATCH_EVENT_SUSPEND = 0x00000001, + HV_VP_DISPATCH_EVENT_INTERCEPT = 0x00000002, +}; + +#define HV_ROOT_SCHEDULER_MAX_VPS_PER_CHILD_PARTITION 1024 +/* The maximum array size of HV_GENERIC_SET (vp_set) buffer */ +#define HV_GENERIC_SET_QWORD_COUNT(max) (((((max) - 1) >> 6) + 1) + 2) + +struct hv_vp_signal_bitset_scheduler_message { + u64 partition_id; + u32 overflow_count; + u16 vp_count; + u16 reserved; + +#define BITSET_BUFFER_SIZE \ + HV_GENERIC_SET_QWORD_COUNT(HV_ROOT_SCHEDULER_MAX_VPS_PER_CHILD_PARTITION) + union { + struct hv_vpset bitset; + u64 bitset_buffer[BITSET_BUFFER_SIZE]; + } vp_bitset; +#undef BITSET_BUFFER_SIZE +} __packed; + +static_assert(sizeof(struct hv_vp_signal_bitset_scheduler_message) <= + (sizeof(struct hv_message) - sizeof(struct hv_message_header))); + +#define HV_MESSAGE_MAX_PARTITION_VP_PAIR_COUNT \ + (((sizeof(struct hv_message) - sizeof(struct hv_message_header)) / \ + (sizeof(u64 /* partition id */) + sizeof(u32 /* vp index */))) - 1) + +struct hv_vp_signal_pair_scheduler_message { + u32 overflow_count; + u8 vp_count; + u8 reserved1[3]; + + u64 partition_ids[HV_MESSAGE_MAX_PARTITION_VP_PAIR_COUNT]; + u32 vp_indexes[HV_MESSAGE_MAX_PARTITION_VP_PAIR_COUNT]; + + u8 reserved2[4]; +} __packed; + +static_assert(sizeof(struct hv_vp_signal_pair_scheduler_message) == + (sizeof(struct hv_message) - sizeof(struct hv_message_header))); + +/* Input and output structures for HVCALL_DISPATCH_VP */ +#define HV_DISPATCH_VP_FLAG_CLEAR_INTERCEPT_SUSPEND 0x1 +#define HV_DISPATCH_VP_FLAG_ENABLE_CALLER_INTERRUPTS 0x2 +#define HV_DISPATCH_VP_FLAG_SET_CALLER_SPEC_CTRL 0x4 +#define HV_DISPATCH_VP_FLAG_SKIP_VP_SPEC_FLUSH 0x8 +#define HV_DISPATCH_VP_FLAG_SKIP_CALLER_SPEC_FLUSH 0x10 +#define HV_DISPATCH_VP_FLAG_SKIP_CALLER_USER_SPEC_FLUSH 0x20 + +struct hv_input_dispatch_vp { + u64 partition_id; + u32 vp_index; + u32 flags; + u64 time_slice; /* in 100ns */ + u64 spec_ctrl; +} __packed; + +struct hv_output_dispatch_vp { + u32 dispatch_state; /* enum hv_vp_dispatch_state */ + u32 dispatch_event; /* enum hv_vp_dispatch_event */ +} __packed; + +#endif /* _HV_HVHDK_H */ diff --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h new file mode 100644 index 000000000000..f8a39d3e9ce6 --- /dev/null +++ b/include/hyperv/hvhdk_mini.h @@ -0,0 +1,311 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Type definitions for the Microsoft Hypervisor. + */ +#ifndef _HV_HVHDK_MINI_H +#define _HV_HVHDK_MINI_H + +#include "hvgdk_mini.h" + +/* + * Doorbell connection_info flags. + */ +#define HV_DOORBELL_FLAG_TRIGGER_SIZE_MASK 0x00000007 +#define HV_DOORBELL_FLAG_TRIGGER_SIZE_ANY 0x00000000 +#define HV_DOORBELL_FLAG_TRIGGER_SIZE_BYTE 0x00000001 +#define HV_DOORBELL_FLAG_TRIGGER_SIZE_WORD 0x00000002 +#define HV_DOORBELL_FLAG_TRIGGER_SIZE_DWORD 0x00000003 +#define HV_DOORBELL_FLAG_TRIGGER_SIZE_QWORD 0x00000004 +#define HV_DOORBELL_FLAG_TRIGGER_ANY_VALUE 0x80000000 + +/* Each generic set contains 64 elements */ +#define HV_GENERIC_SET_SHIFT (6) +#define HV_GENERIC_SET_MASK (63) + +enum hv_generic_set_format { + HV_GENERIC_SET_SPARSE_4K, + HV_GENERIC_SET_ALL, +}; +#define HV_GENERIC_SET_FORMAT hv_generic_set_format + +enum hv_scheduler_type { + HV_SCHEDULER_TYPE_LP = 1, /* Classic scheduler w/o SMT */ + HV_SCHEDULER_TYPE_LP_SMT = 2, /* Classic scheduler w/ SMT */ + HV_SCHEDULER_TYPE_CORE_SMT = 3, /* Core scheduler */ + HV_SCHEDULER_TYPE_ROOT = 4, /* Root / integrated scheduler */ + HV_SCHEDULER_TYPE_MAX +}; + +enum hv_partition_property_code { + /* Privilege properties */ + HV_PARTITION_PROPERTY_PRIVILEGE_FLAGS = 0x00010000, + HV_PARTITION_PROPERTY_SYNTHETIC_PROC_FEATURES = 0x00010001, + + /* Resource properties */ + HV_PARTITION_PROPERTY_GPA_PAGE_ACCESS_TRACKING = 0x00050005, + HV_PARTITION_PROPERTY_UNIMPLEMENTED_MSR_ACTION = 0x00050017, + + /* Compatibility properties */ + HV_PARTITION_PROPERTY_PROCESSOR_XSAVE_FEATURES = 0x00060002, + HV_PARTITION_PROPERTY_MAX_XSAVE_DATA_SIZE = 0x00060008, + HV_PARTITION_PROPERTY_PROCESSOR_CLOCK_FREQUENCY = 0x00060009, +}; + +enum hv_system_property { + /* Add more values when needed */ + HV_SYSTEM_PROPERTY_SCHEDULER_TYPE = 15, +}; + +struct hv_input_get_system_property { + u32 property_id; /* enum hv_system_property */ + union { + u32 as_uint32; + /* More fields to be filled in when needed */ + }; +} __packed; + +struct hv_output_get_system_property { + union { + u32 scheduler_type; /* enum hv_scheduler_type */ + }; +} __packed; + +struct hv_proximity_domain_flags { + u32 proximity_preferred : 1; + u32 reserved : 30; + u32 proximity_info_valid : 1; +} __packed; + +struct hv_proximity_domain_info { + u32 domain_id; + struct hv_proximity_domain_flags flags; +} __packed; + +/* HvDepositMemory hypercall */ +struct hv_deposit_memory { /* HV_INPUT_DEPOSIT_MEMORY */ + u64 partition_id; + u64 gpa_page_list[]; +} __packed; + +struct hv_input_withdraw_memory { + u64 partition_id; + struct hv_proximity_domain_info proximity_domain_info; +} __packed; + +struct hv_output_withdraw_memory { + DECLARE_FLEX_ARRAY(u64, gpa_page_list); +} __packed; + +/* HV Map GPA (Guest Physical Address) Flags */ +#define HV_MAP_GPA_PERMISSIONS_NONE 0x0 +#define HV_MAP_GPA_READABLE 0x1 +#define HV_MAP_GPA_WRITABLE 0x2 +#define HV_MAP_GPA_KERNEL_EXECUTABLE 0x4 +#define HV_MAP_GPA_USER_EXECUTABLE 0x8 +#define HV_MAP_GPA_EXECUTABLE 0xC +#define HV_MAP_GPA_PERMISSIONS_MASK 0xF +#define HV_MAP_GPA_ADJUSTABLE 0x8000 +#define HV_MAP_GPA_NO_ACCESS 0x10000 +#define HV_MAP_GPA_NOT_CACHED 0x200000 +#define HV_MAP_GPA_LARGE_PAGE 0x80000000 + +struct hv_input_map_gpa_pages { + u64 target_partition_id; + u64 target_gpa_base; + u32 map_flags; + u32 padding; + u64 source_gpa_page_list[]; +} __packed; + +union hv_gpa_page_access_state_flags { + struct { + u64 clear_accessed : 1; + u64 set_accessed : 1; + u64 clear_dirty : 1; + u64 set_dirty : 1; + u64 reserved : 60; + } __packed; + u64 as_uint64; +}; + +struct hv_input_get_gpa_pages_access_state { + u64 partition_id; + union hv_gpa_page_access_state_flags flags; + u64 hv_gpa_page_number; +} __packed; + +union hv_gpa_page_access_state { + struct { + u8 accessed : 1; + u8 dirty : 1; + u8 reserved: 6; + }; + u8 as_uint8; +} __packed; + +struct hv_lp_startup_status { + u64 hv_status; + u64 substatus1; + u64 substatus2; + u64 substatus3; + u64 substatus4; + u64 substatus5; + u64 substatus6; +} __packed; + +struct hv_input_add_logical_processor { + u32 lp_index; + u32 apic_id; + struct hv_proximity_domain_info proximity_domain_info; +} __packed; + +struct hv_output_add_logical_processor { + struct hv_lp_startup_status startup_status; +} __packed; + +enum { /* HV_SUBNODE_TYPE */ + HV_SUBNODE_ANY = 0, + HV_SUBNODE_SOCKET, + HV_SUBNODE_CLUSTER, + HV_SUBNODE_L3, + HV_SUBNODE_COUNT, + HV_SUBNODE_INVALID = -1 +}; + +struct hv_create_vp { /* HV_INPUT_CREATE_VP */ + u64 partition_id; + u32 vp_index; + u8 padding[3]; + u8 subnode_type; + u64 subnode_id; + struct hv_proximity_domain_info proximity_domain_info; + u64 flags; +} __packed; + +/* HV_INTERRUPT_TRIGGER_MODE */ +enum hv_interrupt_trigger_mode { + HV_INTERRUPT_TRIGGER_MODE_EDGE = 0, + HV_INTERRUPT_TRIGGER_MODE_LEVEL = 1, +}; + +/* HV_DEVICE_INTERRUPT_DESCRIPTOR */ +struct hv_device_interrupt_descriptor { + u32 interrupt_type; + u32 trigger_mode; + u32 vector_count; + u32 reserved; + struct hv_device_interrupt_target target; +} __packed; + +/* HV_INPUT_MAP_DEVICE_INTERRUPT */ +struct hv_input_map_device_interrupt { + u64 partition_id; + u64 device_id; + u32 flags; + u32 base_irt_idx; + struct hv_interrupt_entry logical_interrupt_entry; + struct hv_device_interrupt_descriptor interrupt_descriptor; +} __packed; + +/* HV_OUTPUT_MAP_DEVICE_INTERRUPT */ +struct hv_output_map_device_interrupt { + struct hv_interrupt_entry interrupt_entry; +} __packed; + +/* HV_INPUT_UNMAP_DEVICE_INTERRUPT */ +struct hv_input_unmap_device_interrupt { + u64 partition_id; + u64 device_id; + struct hv_interrupt_entry interrupt_entry; + u32 flags; +} __packed; + +#define HV_SOURCE_SHADOW_NONE 0x0 +#define HV_SOURCE_SHADOW_BRIDGE_BUS_RANGE 0x1 + +struct hv_send_ipi_ex { /* HV_INPUT_SEND_SYNTHETIC_CLUSTER_IPI_EX */ + u32 vector; + u32 reserved; + struct hv_vpset vp_set; +} __packed; + +typedef u16 hv_pci_rid; /* HV_PCI_RID */ +typedef u16 hv_pci_segment; /* HV_PCI_SEGMENT */ +typedef u64 hv_logical_device_id; +union hv_pci_bdf { /* HV_PCI_BDF */ + u16 as_uint16; + + struct { + u8 function : 3; + u8 device : 5; + u8 bus; + }; +} __packed; + +union hv_pci_bus_range { + u16 as_uint16; + + struct { + u8 subordinate_bus; + u8 secondary_bus; + }; +} __packed; + +enum hv_device_type { /* HV_DEVICE_TYPE */ + HV_DEVICE_TYPE_LOGICAL = 0, + HV_DEVICE_TYPE_PCI = 1, + HV_DEVICE_TYPE_IOAPIC = 2, + HV_DEVICE_TYPE_ACPI = 3, +}; + +union hv_device_id { /* HV_DEVICE_ID */ + u64 as_uint64; + + struct { + u64 reserved0 : 62; + u64 device_type : 2; + }; + + /* HV_DEVICE_TYPE_LOGICAL */ + struct { + u64 id : 62; + u64 device_type : 2; + } logical; + + /* HV_DEVICE_TYPE_PCI */ + struct { + union { + hv_pci_rid rid; + union hv_pci_bdf bdf; + }; + + hv_pci_segment segment; + union hv_pci_bus_range shadow_bus_range; + + u16 phantom_function_bits : 2; + u16 source_shadow : 1; + + u16 rsvdz0 : 11; + u16 device_type : 2; + } pci; + + /* HV_DEVICE_TYPE_IOAPIC */ + struct { + u8 ioapic_id; + u8 rsvdz0; + u16 rsvdz1; + u16 rsvdz2; + + u16 rsvdz3 : 14; + u16 device_type : 2; + } ioapic; + + /* HV_DEVICE_TYPE_ACPI */ + struct { + u32 input_mapping_base; + u32 input_mapping_count : 30; + u32 device_type : 2; + } acpi; +} __packed; + +#endif /* _HV_HVHDK_MINI_H */ diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index 8365adf842ef..a6c2897bcc63 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -73,7 +73,6 @@ static inline void __init set_machine_trusted_keys(struct key *keyring) } #endif -extern struct pkcs7_message *pkcs7; #ifdef CONFIG_SYSTEM_BLACKLIST_KEYRING extern int mark_hash_blacklisted(const u8 *hash, size_t hash_len, enum blacklist_hash_type hash_type); @@ -93,6 +92,7 @@ static inline int is_binary_blacklisted(const u8 *hash, size_t hash_len) } #endif +struct pkcs7_message; #ifdef CONFIG_SYSTEM_REVOCATION_LIST extern int add_key_to_revocation_list(const char *data, size_t size); extern int is_key_on_revocation_list(struct pkcs7_message *pkcs7); diff --git a/include/kunit/platform_device.h b/include/kunit/platform_device.h index 0fc0999d2420..f8236a8536f7 100644 --- a/include/kunit/platform_device.h +++ b/include/kunit/platform_device.h @@ -2,6 +2,7 @@ #ifndef _KUNIT_PLATFORM_DRIVER_H #define _KUNIT_PLATFORM_DRIVER_H +struct completion; struct kunit; struct platform_device; struct platform_driver; diff --git a/include/kunit/test.h b/include/kunit/test.h index 34b71e42fb10..58dbab60f853 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -312,6 +312,7 @@ static inline void kunit_set_failure(struct kunit *test) } bool kunit_enabled(void); +bool kunit_autorun(void); const char *kunit_action(void); const char *kunit_filter_glob(void); char *kunit_filter(void); @@ -334,7 +335,8 @@ kunit_filter_suites(const struct kunit_suite_set *suite_set, int *err); void kunit_free_suite_set(struct kunit_suite_set suite_set); -int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites); +int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites, + bool run_tests); void __kunit_test_suites_exit(struct kunit_suite **suites, int num_suites); diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index fd650a8789b9..681cf0c8b9df 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -98,6 +98,7 @@ int __init kvm_timer_hyp_init(bool has_gic); int kvm_timer_enable(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu); +void kvm_timer_sync_nested(struct kvm_vcpu *vcpu); void kvm_timer_sync_user(struct kvm_vcpu *vcpu); bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu); void kvm_timer_update_run(struct kvm_vcpu *vcpu); @@ -150,9 +151,31 @@ void kvm_timer_cpu_down(void); /* CNTKCTL_EL1 valid bits as of DDI0487J.a */ #define CNTKCTL_VALID_BITS (BIT(17) | GENMASK_ULL(9, 0)) +DECLARE_STATIC_KEY_FALSE(broken_cntvoff_key); + +static inline bool has_broken_cntvoff(void) +{ + return static_branch_unlikely(&broken_cntvoff_key); +} + static inline bool has_cntpoff(void) { return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); } +static inline u64 timer_get_offset(struct arch_timer_context *ctxt) +{ + u64 offset = 0; + + if (!ctxt) + return 0; + + if (ctxt->offset.vm_offset) + offset += *ctxt->offset.vm_offset; + if (ctxt->offset.vcpu_offset) + offset += *ctxt->offset.vcpu_offset; + + return offset; +} + #endif diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index e61dd7dd2286..147bd3ee4f7b 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -53,8 +53,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1); void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu); -void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val); -void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val); +void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu); void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu); bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu); @@ -127,8 +126,7 @@ static inline u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu) static inline void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {} -static inline void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} -static inline void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} +static inline void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {} static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6adcd1b92b20..4e495b29c640 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -854,6 +854,11 @@ static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) return NULL; } +static inline acpi_handle acpi_device_handle(struct acpi_device *adev) +{ + return NULL; +} + static inline bool has_acpi_companion(struct device *dev) { return false; diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h index c637e0997f6d..abec23c7744f 100644 --- a/include/linux/adreno-smmu-priv.h +++ b/include/linux/adreno-smmu-priv.h @@ -50,6 +50,11 @@ struct adreno_smmu_fault_info { * the GPU driver must call resume_translation() * @resume_translation: Resume translation after a fault * + * @set_prr_bit: [optional] Configure the GPU's Partially Resident + * Region (PRR) bit in the ACTLR register. + * @set_prr_addr: [optional] Configure the PRR_CFG_*ADDR register with + * the physical address of PRR page passed from GPU + * driver. * * The GPU driver (drm/msm) and adreno-smmu work together for controlling * the GPU's SMMU instance. This is by necessity, as the GPU is directly @@ -67,6 +72,8 @@ struct adreno_smmu_priv { void (*get_fault_info)(const void *cookie, struct adreno_smmu_fault_info *info); void (*set_stall)(const void *cookie, bool enabled); void (*resume_translation)(const void *cookie, bool terminate); + void (*set_prr_bit)(const void *cookie, bool set); + void (*set_prr_addr)(const void *cookie, phys_addr_t page_addr); }; #endif /* __ADRENO_SMMU_PRIV_H */ diff --git a/include/linux/aer.h b/include/linux/aer.h index 4b97f38f3fcf..947b63091902 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -16,10 +16,18 @@ #define AER_CORRECTABLE 2 #define DPC_FATAL 3 +/* + * AER and DPC capabilities TLP Logging register sizes (PCIe r6.2, sec 7.8.4 + * & 7.9.14). + */ +#define PCIE_STD_NUM_TLP_HEADERLOG 4 +#define PCIE_STD_MAX_TLP_PREFIXLOG 4 + struct pci_dev; struct pcie_tlp_log { - u32 dw[4]; + u32 dw[PCIE_STD_NUM_TLP_HEADERLOG]; + u32 prefix[PCIE_STD_MAX_TLP_PREFIXLOG]; }; struct aer_capability_regs { @@ -37,8 +45,6 @@ struct aer_capability_regs { u16 uncor_err_source; }; -int pcie_read_tlp_log(struct pci_dev *dev, int where, struct pcie_tlp_log *log); - #if defined(CONFIG_PCIEAER) int pci_aer_clear_nonfatal_status(struct pci_dev *dev); int pcie_aer_is_native(struct pci_dev *dev); diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 7c0786bdf9af..a946e0203e6d 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -63,7 +63,12 @@ static inline void set_codetag_empty(union codetag_ref *ref) #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ static inline bool is_codetag_empty(union codetag_ref *ref) { return false; } -static inline void set_codetag_empty(union codetag_ref *ref) {} + +static inline void set_codetag_empty(union codetag_ref *ref) +{ + if (ref) + ref->ct = NULL; +} #endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ @@ -135,7 +140,7 @@ static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) { - WARN_ONCE(ref && ref->ct, + WARN_ONCE(ref && ref->ct && !is_codetag_empty(ref), "alloc_tag was not cleared (got tag for %s:%u)\n", ref->ct->filename, ref->ct->lineno); @@ -219,9 +224,14 @@ static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} #define alloc_hooks_tag(_tag, _do_alloc) \ ({ \ - struct alloc_tag * __maybe_unused _old = alloc_tag_save(_tag); \ - typeof(_do_alloc) _res = _do_alloc; \ - alloc_tag_restore(_tag, _old); \ + typeof(_do_alloc) _res; \ + if (mem_alloc_profiling_enabled()) { \ + struct alloc_tag * __maybe_unused _old; \ + _old = alloc_tag_save(_tag); \ + _res = _do_alloc; \ + alloc_tag_restore(_tag, _old); \ + } else \ + _res = _do_alloc; \ _res; \ }) diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index 2b90c48a6a87..062fbd4c9b77 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -31,11 +31,11 @@ struct amd_iommu_pi_data { struct task_struct; struct pci_dev; -extern int amd_iommu_detect(void); +extern void amd_iommu_detect(void); #else /* CONFIG_AMD_IOMMU */ -static inline int amd_iommu_detect(void) { return -ENODEV; } +static inline void amd_iommu_detect(void) { } #endif /* CONFIG_AMD_IOMMU */ diff --git a/include/linux/amd-pmf-io.h b/include/linux/amd-pmf-io.h index b4f818205216..6fa510f419c0 100644 --- a/include/linux/amd-pmf-io.h +++ b/include/linux/amd-pmf-io.h @@ -18,10 +18,12 @@ * enum sfh_message_type - Query the SFH message type * @MT_HPD: Message ID to know the Human presence info from MP2 FW * @MT_ALS: Message ID to know the Ambient light info from MP2 FW + * @MT_SRA: Message ID to know the SRA data from MP2 FW */ enum sfh_message_type { MT_HPD, MT_ALS, + MT_SRA, }; /** @@ -40,10 +42,23 @@ enum sfh_hpd_info { * struct amd_sfh_info - get HPD sensor info from MP2 FW * @ambient_light: Populates the ambient light information * @user_present: Populates the user presence information + * @platform_type: Operating modes (clamshell, flat, tent, etc.) + * @laptop_placement: Device states (ontable, onlap, outbag) */ struct amd_sfh_info { u32 ambient_light; u8 user_present; + u32 platform_type; + u32 laptop_placement; +}; + +enum laptop_placement { + LP_UNKNOWN = 0, + ON_TABLE, + ON_LAP_MOTION, + IN_BAG, + OUT_OF_BAG, + LP_UNDEFINED, }; int amd_get_sfh_info(struct amd_sfh_info *sfh_info, enum sfh_message_type op); diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index a28e2a6a13d0..74169dd0f659 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -166,9 +166,12 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev) return dev_get_drvdata(&fdev->dev); } +struct ffa_partition_info; + #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops); +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops); void ffa_device_unregister(struct ffa_device *ffa_dev); int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name); @@ -176,9 +179,9 @@ void ffa_driver_unregister(struct ffa_driver *driver); bool ffa_device_is_valid(struct ffa_device *ffa_dev); #else -static inline -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +static inline struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { return NULL; } diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index e6c00e860951..60d674af3080 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -42,7 +42,14 @@ struct linux_binprm { * Set when errors can no longer be returned to the * original userspace. */ - point_of_no_return:1; + point_of_no_return:1, + /* Set when "comm" must come from the dentry. */ + comm_from_dentry:1, + /* + * Set by user space to check executability according to the + * caller's environment. + */ + is_check:1; struct file *executable; /* Executable to pass to the interpreter */ struct file *interpreter; struct file *file; diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h index dbf0f74c1529..802f52e38efd 100644 --- a/include/linux/bio-integrity.h +++ b/include/linux/bio-integrity.h @@ -7,10 +7,12 @@ enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ - BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */ - BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */ - BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */ - BIP_COPY_USER = 1 << 5, /* Kernel bounce buffer in use */ + BIP_DISK_NOCHECK = 1 << 2, /* disable disk integrity checking */ + BIP_IP_CHECKSUM = 1 << 3, /* IP checksum */ + BIP_COPY_USER = 1 << 4, /* Kernel bounce buffer in use */ + BIP_CHECK_GUARD = 1 << 5, /* guard check */ + BIP_CHECK_REFTAG = 1 << 6, /* reftag check */ + BIP_CHECK_APPTAG = 1 << 7, /* apptag check */ }; struct bio_integrity_payload { @@ -21,6 +23,7 @@ struct bio_integrity_payload { unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned short bip_flags; /* control flags */ + u16 app_tag; /* application tag value */ struct bvec_iter bio_iter; /* for rewinding parent bio */ @@ -30,6 +33,9 @@ struct bio_integrity_payload { struct bio_vec bip_inline_vecs[];/* embedded bvec array */ }; +#define BIP_CLONE_FLAGS (BIP_MAPPED_INTEGRITY | BIP_IP_CHECKSUM | \ + BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG) + #ifdef CONFIG_BLK_DEV_INTEGRITY #define bip_for_each_vec(bvl, bip, iter) \ @@ -72,7 +78,8 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr); int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset); -int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len); +int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter); +int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta); void bio_integrity_unmap_user(struct bio *bio); bool bio_integrity_prep(struct bio *bio); void bio_integrity_advance(struct bio *bio, unsigned int bytes_done); @@ -98,8 +105,12 @@ static inline void bioset_integrity_free(struct bio_set *bs) { } -static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf, - ssize_t len) +static inline int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) +{ + return -EINVAL; +} + +static inline int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta) { return -EINVAL; } diff --git a/include/linux/bio.h b/include/linux/bio.h index 7a1b3b1a8fed..4b79bf50f4f0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -19,9 +19,6 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs) return min(nr_segs, BIO_MAX_VECS); } -#define bio_prio(bio) (bio)->bi_ioprio -#define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) - #define bio_iter_iovec(bio, iter) \ bvec_iter_bvec((bio)->bi_io_vec, (iter)) @@ -416,8 +413,6 @@ int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len, unsigned off); bool __must_check bio_add_folio(struct bio *bio, struct folio *folio, size_t len, size_t off); -extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, - unsigned int, unsigned int); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 262b6596eca5..2026953e2c4e 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -23,7 +23,7 @@ struct device; * * Function implementations generic to all architectures are in * lib/bitmap.c. Functions implementations that are architecture - * specific are in various include/asm-/bitops.h headers + * specific are in various arch//include/asm/bitops.h headers * and other arch/ specific files. * * See lib/bitmap.c for more details. diff --git a/include/linux/bitops.h b/include/linux/bitops.h index ba35bbf07798..c1cb53cf2f0f 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -229,6 +229,37 @@ static inline int get_count_order_long(unsigned long l) return (int)fls_long(--l); } +/** + * parity8 - get the parity of an u8 value + * @value: the value to be examined + * + * Determine the parity of the u8 argument. + * + * Returns: + * 0 for even parity, 1 for odd parity + * + * Note: This function informs you about the current parity. Example to bail + * out when parity is odd: + * + * if (parity8(val) == 1) + * return -EBADMSG; + * + * If you need to calculate a parity bit, you need to draw the conclusion from + * this result yourself. Example to enforce odd parity, parity bit is bit 7: + * + * if (parity8(val) == 0) + * val ^= BIT(7); + */ +static inline int parity8(u8 val) +{ + /* + * One explanation of this algorithm: + * https://funloop.org/codex/problem/parity/README.html + */ + val ^= val >> 4; + return (0x6996 >> (val & 0xf)) & 1; +} + /** * __ffs64 - find first set bit in a 64 bit word * @word: The 64 bit word diff --git a/include/linux/bits.h b/include/linux/bits.h index 60044b608817..61a75d3f294b 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -20,9 +20,8 @@ */ #if !defined(__ASSEMBLY__) #include -#define GENMASK_INPUT_CHECK(h, l) \ - (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ - __is_constexpr((l) > (h)), (l) > (h), 0))) +#include +#define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h))) #else /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h deleted file mode 100644 index ca544e1d3508..000000000000 --- a/include/linux/blk-mq-pci.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_BLK_MQ_PCI_H -#define _LINUX_BLK_MQ_PCI_H - -struct blk_mq_queue_map; -struct pci_dev; - -void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, - int offset); - -#endif /* _LINUX_BLK_MQ_PCI_H */ diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h deleted file mode 100644 index 13226e9b22dd..000000000000 --- a/include/linux/blk-mq-virtio.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_BLK_MQ_VIRTIO_H -#define _LINUX_BLK_MQ_VIRTIO_H - -struct blk_mq_queue_map; -struct virtio_device; - -void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, - struct virtio_device *vdev, int first_vec); - -#endif /* _LINUX_BLK_MQ_VIRTIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index c596e0e4cb75..9ebb53f031cd 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -296,13 +296,6 @@ enum blk_eh_timer_return { BLK_EH_RESET_TIMER, }; -/* Keep alloc_policy_name[] in sync with the definitions below */ -enum { - BLK_TAG_ALLOC_FIFO, /* allocate starting from 0 */ - BLK_TAG_ALLOC_RR, /* allocate starting from last allocated tag */ - BLK_TAG_ALLOC_MAX -}; - /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device @@ -668,7 +661,6 @@ struct blk_mq_ops { /* Keep hctx_flag_name[] in sync with the definitions below */ enum { - BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for @@ -677,23 +669,20 @@ enum { BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 4, - /* Do not allow an I/O scheduler to be configured. */ - BLK_MQ_F_NO_SCHED = 1 << 5, + + /* + * Alloc tags on a round-robin base instead of the first available one. + */ + BLK_MQ_F_TAG_RR = 1 << 5, /* * Select 'none' during queue registration in case of a single hwq * or shared hwqs instead of 'mq-deadline'. */ BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 6, - BLK_MQ_F_ALLOC_POLICY_START_BIT = 7, - BLK_MQ_F_ALLOC_POLICY_BITS = 1, + + BLK_MQ_F_MAX = 1 << 7, }; -#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \ - ((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \ - ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) -#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \ - ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ - << BLK_MQ_F_ALLOC_POLICY_START_BIT) #define BLK_MQ_MAX_DEPTH (10240) #define BLK_MQ_NO_HCTX_IDX (-1U) @@ -911,8 +900,22 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); -void blk_mq_freeze_queue(struct request_queue *q); -void blk_mq_unfreeze_queue(struct request_queue *q); +void blk_mq_freeze_queue_nomemsave(struct request_queue *q); +void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q); +static inline unsigned int __must_check +blk_mq_freeze_queue(struct request_queue *q) +{ + unsigned int memflags = memalloc_noio_save(); + + blk_mq_freeze_queue_nomemsave(q); + return memflags; +} +static inline void +blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags) +{ + blk_mq_unfreeze_queue_nomemrestore(q); + memalloc_noio_restore(memflags); +} void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, @@ -921,6 +924,8 @@ void blk_mq_unfreeze_queue_non_owner(struct request_queue *q); void blk_freeze_queue_start_non_owner(struct request_queue *q); void blk_mq_map_queues(struct blk_mq_queue_map *qmap); +void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, + struct device *dev, unsigned int offset); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); @@ -977,14 +982,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq) rq->q->mq_ops->cleanup_rq(rq); } -static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, - unsigned int nr_segs) -{ - rq->nr_phys_segments = nr_segs; - rq->__data_len = bio->bi_iter.bi_size; - rq->bio = rq->biotail = bio; -} - void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 378d3a1a22fc..248416ecd01c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -331,8 +331,8 @@ typedef unsigned int __bitwise blk_features_t; #define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \ ((__force blk_features_t)(1u << 15)) -/* stacked device can/does support atomic writes */ -#define BLK_FEAT_ATOMIC_WRITES_STACKED \ +/* atomic writes enabled */ +#define BLK_FEAT_ATOMIC_WRITES \ ((__force blk_features_t)(1u << 16)) /* @@ -561,7 +561,6 @@ struct request_queue { struct list_head flush_list; struct mutex sysfs_lock; - struct mutex sysfs_dir_lock; struct mutex limits_lock; /* @@ -581,6 +580,12 @@ struct request_queue { #ifdef CONFIG_LOCKDEP struct task_struct *mq_freeze_owner; int mq_freeze_owner_depth; + /* + * Records disk & queue state in current context, used in unfreeze + * queue + */ + bool mq_freeze_disk_dead; + bool mq_freeze_queue_dying; #endif wait_queue_head_t mq_freeze_wq; /* @@ -599,8 +604,6 @@ struct request_queue { * Serializes all debugfs metadata operations using the above dentries. */ struct mutex debugfs_mutex; - - bool mq_sysfs_init_done; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ @@ -938,8 +941,7 @@ static inline unsigned int blk_boundary_sectors_left(sector_t offset, * the caller can modify. The caller must call queue_limits_commit_update() * to finish the update. * - * Context: process context. The caller must have frozen the queue or ensured - * that there is outstanding I/O by other means. + * Context: process context. */ static inline struct queue_limits queue_limits_start_update(struct request_queue *q) @@ -947,6 +949,8 @@ queue_limits_start_update(struct request_queue *q) mutex_lock(&q->limits_lock); return q->limits; } +int queue_limits_commit_update_frozen(struct request_queue *q, + struct queue_limits *lim); int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim); int queue_limits_set(struct request_queue *q, struct queue_limits *lim); @@ -1699,6 +1703,15 @@ struct io_comp_batch { void (*complete)(struct io_comp_batch *); }; +static inline bool blk_atomic_write_start_sect_aligned(sector_t sector, + struct queue_limits *limits) +{ + unsigned int alignment = max(limits->atomic_write_hw_unit_min, + limits->atomic_write_hw_boundary); + + return IS_ALIGNED(sector, alignment >> SECTOR_SHIFT); +} + static inline bool bdev_can_atomic_write(struct block_device *bdev) { struct request_queue *bd_queue = bdev->bd_queue; @@ -1707,15 +1720,9 @@ static inline bool bdev_can_atomic_write(struct block_device *bdev) if (!limits->atomic_write_unit_min) return false; - if (bdev_is_partition(bdev)) { - sector_t bd_start_sect = bdev->bd_start_sect; - unsigned int alignment = - max(limits->atomic_write_unit_min, - limits->atomic_write_hw_boundary); - - if (!IS_ALIGNED(bd_start_sect, alignment >> SECTOR_SHIFT)) - return false; - } + if (bdev_is_partition(bdev)) + return blk_atomic_write_start_sect_aligned(bdev->bd_start_sect, + limits); return true; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6e63dd3443b9..f3f50e29d639 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2299,6 +2299,14 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); +/* + * The __bpf_map_get() and __btf_get_by_fd() functions parse a file + * descriptor and return a corresponding map or btf object. + * Their names are double underscored to emphasize the fact that they + * do not increase refcnt. To also increase refcnt use corresponding + * bpf_map_get() and btf_get_by_fd() functions. + */ + static inline struct bpf_map *__bpf_map_get(struct fd f) { if (fd_empty(f)) @@ -2308,6 +2316,15 @@ static inline struct bpf_map *__bpf_map_get(struct fd f) return fd_file(f)->private_data; } +static inline struct btf *__btf_get_by_fd(struct fd f) +{ + if (fd_empty(f)) + return ERR_PTR(-EBADF); + if (unlikely(fd_file(f)->f_op != &btf_fops)) + return ERR_PTR(-EINVAL); + return fd_file(f)->private_data; +} + void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); @@ -2589,10 +2606,10 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog); + const struct bpf_prog *xdp_prog); int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog, struct bpf_map *map, - bool exclude_ingress); + const struct bpf_prog *xdp_prog, + struct bpf_map *map, bool exclude_ingress); void __cpu_map_flush(struct list_head *flush_list); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, @@ -2862,15 +2879,15 @@ struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { return 0; } static inline int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog, struct bpf_map *map, - bool exclude_ingress) + const struct bpf_prog *xdp_prog, + struct bpf_map *map, bool exclude_ingress) { return 0; } diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 48b7b2eeb7e2..32c23f2a3086 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -233,6 +233,7 @@ enum bpf_stack_slot_type { */ STACK_DYNPTR, STACK_ITER, + STACK_IRQ_FLAG, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ @@ -254,8 +255,9 @@ struct bpf_reference_state { * default to pointer reference on zero initialization of a state. */ enum ref_state_type { - REF_TYPE_PTR = 0, - REF_TYPE_LOCK, + REF_TYPE_PTR = 1, + REF_TYPE_IRQ = 2, + REF_TYPE_LOCK = 3, } type; /* Track each reference created with a unique id, even if the same * instruction creates the reference multiple times (eg, via CALL). @@ -315,9 +317,6 @@ struct bpf_func_state { u32 callback_depth; /* The following fields should be last. See copy_func_state() */ - int acquired_refs; - int active_locks; - struct bpf_reference_state *refs; /* The state of the stack. Each element of the array describes BPF_REG_SIZE * (i.e. 8) bytes worth of stack memory. * stack[0] represents bytes [*(r10-8)..*(r10-1)] @@ -370,6 +369,8 @@ struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; struct bpf_verifier_state *parent; + /* Acquired reference states */ + struct bpf_reference_state *refs; /* * 'branches' field is the number of branches left to explore: * 0 - all possible paths from this state reached bpf_exit or @@ -419,9 +420,13 @@ struct bpf_verifier_state { u32 insn_idx; u32 curframe; - bool speculative; + u32 acquired_refs; + u32 active_locks; + u32 active_preempt_locks; + u32 active_irq_id; bool active_rcu_lock; - u32 active_preempt_lock; + + bool speculative; /* If this state was ever pointed-to by other state's loop_entry field * this flag would be set to true. Used to avoid freeing such states * while they are still in use. @@ -980,8 +985,9 @@ const char *dynptr_type_str(enum bpf_dynptr_type type); const char *iter_type_str(const struct btf *btf, u32 btf_id); const char *iter_state_str(enum bpf_iter_state state); -void print_verifier_state(struct bpf_verifier_env *env, - const struct bpf_func_state *state, bool print_all); -void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state); +void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, + u32 frameno, bool print_all); +void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, + u32 frameno); #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 4214e76c9168..2a08a2b55592 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -353,6 +353,11 @@ static inline bool btf_type_is_scalar(const struct btf_type *t) return btf_type_is_int(t) || btf_type_is_enum(t); } +static inline bool btf_type_is_fwd(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + static inline bool btf_type_is_typedef(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; diff --git a/include/linux/bug.h b/include/linux/bug.h index 348acf2558f3..a9948a9f1093 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -73,15 +73,23 @@ static inline void generic_bug_clear_once(void) {} #endif /* CONFIG_GENERIC_BUG */ +#ifdef CONFIG_PRINTK +void mem_dump_obj(void *object); +#else +static inline void mem_dump_obj(void *object) {} +#endif + /* * Since detected data corruption should stop operation on the affected * structures. Return value must be checked and sanely acted on by caller. */ static inline __must_check bool check_data_corruption(bool v) { return v; } -#define CHECK_DATA_CORRUPTION(condition, fmt, ...) \ +#define CHECK_DATA_CORRUPTION(condition, addr, fmt, ...) \ check_data_corruption(({ \ bool corruption = unlikely(condition); \ if (corruption) { \ + if (addr) \ + mem_dump_obj(addr); \ if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \ pr_err(fmt, ##__VA_ARGS__); \ BUG(); \ diff --git a/include/linux/bus/stm32_firewall_device.h b/include/linux/bus/stm32_firewall_device.h index 18e0a2fc3816..5178b72bc920 100644 --- a/include/linux/bus/stm32_firewall_device.h +++ b/include/linux/bus/stm32_firewall_device.h @@ -115,7 +115,7 @@ void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 su #else /* CONFIG_STM32_FIREWALL */ int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, - unsigned int nb_firewall); + unsigned int nb_firewall) { return -ENODEV; } diff --git a/include/linux/bvec.h b/include/linux/bvec.h index f41c7f0ef91e..ba8f52d48b94 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -286,12 +286,7 @@ static inline void *bvec_virt(struct bio_vec *bvec) */ static inline phys_addr_t bvec_phys(const struct bio_vec *bvec) { - /* - * Note this open codes page_to_phys because page_to_phys is defined in - * , which we don't want to pull in here. If it ever moves to - * a sensible place we should start using it. - */ - return PFN_PHYS(page_to_pfn(bvec->bv_page)) + bvec->bv_offset; + return page_to_phys(bvec->bv_page) + bvec->bv_offset; } #endif /* __LINUX_BVEC_H */ diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 108060612bb8..c8f4f0a0b874 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -147,7 +147,7 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) return ci ? ci->id : -1; } -#ifdef CONFIG_ARM64 +#if defined(CONFIG_ARM64) || defined(CONFIG_ARM) #define use_arch_cache_info() (true) #else #define use_arch_cache_info() (false) @@ -155,8 +155,14 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) #ifndef CONFIG_ARCH_HAS_CPU_CACHE_ALIASING #define cpu_dcache_is_aliasing() false +#define cpu_icache_is_aliasing() cpu_dcache_is_aliasing() #else #include + +#ifndef cpu_icache_is_aliasing +#define cpu_icache_is_aliasing() cpu_dcache_is_aliasing() +#endif + #endif #endif /* _LINUX_CACHEINFO_H */ diff --git a/include/linux/call_once.h b/include/linux/call_once.h new file mode 100644 index 000000000000..6261aa0b3fb0 --- /dev/null +++ b/include/linux/call_once.h @@ -0,0 +1,45 @@ +#ifndef _LINUX_CALL_ONCE_H +#define _LINUX_CALL_ONCE_H + +#include +#include + +#define ONCE_NOT_STARTED 0 +#define ONCE_RUNNING 1 +#define ONCE_COMPLETED 2 + +struct once { + atomic_t state; + struct mutex lock; +}; + +static inline void __once_init(struct once *once, const char *name, + struct lock_class_key *key) +{ + atomic_set(&once->state, ONCE_NOT_STARTED); + __mutex_init(&once->lock, name, key); +} + +#define once_init(once) \ +do { \ + static struct lock_class_key __key; \ + __once_init((once), #once, &__key); \ +} while (0) + +static inline void call_once(struct once *once, void (*cb)(struct once *)) +{ + /* Pairs with atomic_set_release() below. */ + if (atomic_read_acquire(&once->state) == ONCE_COMPLETED) + return; + + guard(mutex)(&once->lock); + WARN_ON(atomic_read(&once->state) == ONCE_RUNNING); + if (atomic_read(&once->state) != ONCE_NOT_STARTED) + return; + + atomic_set(&once->state, ONCE_RUNNING); + cb(once); + atomic_set_release(&once->state, ONCE_COMPLETED); +} + +#endif /* _LINUX_CALL_ONCE_H */ diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index caa4b4430634..0bf7d33a1048 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -81,6 +81,14 @@ enum cc_attr { */ CC_ATTR_GUEST_SEV_SNP, + /** + * @CC_ATTR_GUEST_SNP_SECURE_TSC: SNP Secure TSC is active. + * + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP Secure TSC feature. + */ + CC_ATTR_GUEST_SNP_SECURE_TSC, + /** * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. * diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 2d7d86f0290d..c7f2c63b3bc3 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -504,20 +504,6 @@ struct ceph_mds_request_head_legacy { #define CEPH_MDS_REQUEST_HEAD_VERSION 3 -struct ceph_mds_request_head_old { - __le16 version; /* struct version */ - __le64 oldest_client_tid; - __le32 mdsmap_epoch; /* on client */ - __le32 flags; /* CEPH_MDS_FLAG_* */ - __u8 num_retry, num_fwd; /* count retry, fwd attempts */ - __le16 num_releases; /* # include cap/lease release records */ - __le32 op; /* mds op code */ - __le32 caller_uid, caller_gid; - __le64 ino; /* use this ino for openc, mkdir, mknod, - etc. (if replaying) */ - union ceph_mds_request_args_ext args; -} __attribute__ ((packed)); - struct ceph_mds_request_head { __le16 version; /* struct version */ __le64 oldest_client_tid; diff --git a/include/linux/cgroup_dmem.h b/include/linux/cgroup_dmem.h new file mode 100644 index 000000000000..dd4869f1d736 --- /dev/null +++ b/include/linux/cgroup_dmem.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2023-2024 Intel Corporation + */ + +#ifndef _CGROUP_DMEM_H +#define _CGROUP_DMEM_H + +#include +#include + +struct dmem_cgroup_pool_state; + +/* Opaque definition of a cgroup region, used internally */ +struct dmem_cgroup_region; + +#if IS_ENABLED(CONFIG_CGROUP_DMEM) +struct dmem_cgroup_region *dmem_cgroup_register_region(u64 size, const char *name_fmt, ...) __printf(2,3); +void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region); +int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size, + struct dmem_cgroup_pool_state **ret_pool, + struct dmem_cgroup_pool_state **ret_limit_pool); +void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size); +bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool, + struct dmem_cgroup_pool_state *test_pool, + bool ignore_low, bool *ret_hit_low); + +void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool); +#else +static inline __printf(2,3) struct dmem_cgroup_region * +dmem_cgroup_register_region(u64 size, const char *name_fmt, ...) +{ + return NULL; +} + +static inline void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) +{ } + +static inline int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size, + struct dmem_cgroup_pool_state **ret_pool, + struct dmem_cgroup_pool_state **ret_limit_pool) +{ + *ret_pool = NULL; + + if (ret_limit_pool) + *ret_limit_pool = NULL; + + return 0; +} + +static inline void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size) +{ } + +static inline +bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool, + struct dmem_cgroup_pool_state *test_pool, + bool ignore_low, bool *ret_hit_low) +{ + return true; +} + +static inline void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool) +{ } + +#endif +#endif /* _CGROUP_DMEM_H */ diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 445235487230..3fd0bcbf3080 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -65,6 +65,10 @@ SUBSYS(rdma) SUBSYS(misc) #endif +#if IS_ENABLED(CONFIG_CGROUP_DMEM) +SUBSYS(dmem) +#endif + /* * The following subsystems are not supported on the default hierarchy. */ diff --git a/include/linux/clk.h b/include/linux/clk.h index 1dcee6d701e4..b607482ca77e 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -1138,15 +1138,6 @@ static inline void clk_restore_context(void) {} #endif -/* Deprecated. Use devm_clk_bulk_get_all_enabled() */ -static inline int __must_check -devm_clk_bulk_get_all_enable(struct device *dev, struct clk_bulk_data **clks) -{ - int ret = devm_clk_bulk_get_all_enabled(dev, clks); - - return ret > 0 ? 0 : ret; -} - /* clk_prepare_enable helps cases using clk_enable in non-atomic context. */ static inline int clk_prepare_enable(struct clk *clk) { diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index d0ed9583743f..c9b58188ec61 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -52,18 +52,6 @@ */ #define barrier_before_unreachable() asm volatile("") -/* - * Mark a position in code as unreachable. This can be used to - * suppress control flow warnings after asm blocks that transfer - * control elsewhere. - */ -#define unreachable() \ - do { \ - annotate_unreachable(); \ - barrier_before_unreachable(); \ - __builtin_unreachable(); \ - } while (0) - #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 469a64dd6495..b087de2f3e94 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -109,44 +109,21 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Unreachable code */ #ifdef CONFIG_OBJTOOL -/* - * These macros help objtool understand GCC code flow for unreachable code. - * The __COUNTER__ based labels are a hack to make each instance of the macros - * unique, to convince GCC not to merge duplicate inline asm statements. - */ -#define __stringify_label(n) #n - -#define __annotate_reachable(c) ({ \ - asm volatile(__stringify_label(c) ":\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t"); \ -}) -#define annotate_reachable() __annotate_reachable(__COUNTER__) - -#define __annotate_unreachable(c) ({ \ - asm volatile(__stringify_label(c) ":\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t" : : "i" (c)); \ -}) -#define annotate_unreachable() __annotate_unreachable(__COUNTER__) - /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #") - #else /* !CONFIG_OBJTOOL */ -#define annotate_reachable() -#define annotate_unreachable() #define __annotate_jump_table #endif /* CONFIG_OBJTOOL */ -#ifndef unreachable -# define unreachable() do { \ - annotate_unreachable(); \ +/* + * Mark a position in code as unreachable. This can be used to + * suppress control flow warnings after asm blocks that transfer + * control elsewhere. + */ +#define unreachable() do { \ + barrier_before_unreachable(); \ __builtin_unreachable(); \ } while (0) -#endif /* * KENTRY - kernel entry point @@ -216,18 +193,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* __KERNEL__ */ -/* - * Force the compiler to emit 'sym' as a symbol, so that we can reference - * it from inline assembler. Necessary in case 'sym' could be inlined - * otherwise, or eliminated entirely due to lack of references that are - * visible to the compiler. - */ -#define ___ADDRESSABLE(sym, __attrs) \ - static void * __used __attrs \ - __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; -#define __ADDRESSABLE(sym) \ - ___ADDRESSABLE(sym, __section(".discard.addressable")) - /** * offset_to_ptr - convert a relative memory offset to an absolute pointer * @off: the address of the 32-bit offset value @@ -239,6 +204,33 @@ static inline void *offset_to_ptr(const int *off) #endif /* __ASSEMBLY__ */ +#ifdef CONFIG_64BIT +#define ARCH_SEL(a,b) a +#else +#define ARCH_SEL(a,b) b +#endif + +/* + * Force the compiler to emit 'sym' as a symbol, so that we can reference + * it from inline assembler. Necessary in case 'sym' could be inlined + * otherwise, or eliminated entirely due to lack of references that are + * visible to the compiler. + */ +#define ___ADDRESSABLE(sym, __attrs) \ + static void * __used __attrs \ + __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; + +#define __ADDRESSABLE(sym) \ + ___ADDRESSABLE(sym, __section(".discard.addressable")) + +#define __ADDRESSABLE_ASM(sym) \ + .pushsection .discard.addressable,"aw"; \ + .align ARCH_SEL(8,4); \ + ARCH_SEL(.quad, .long) __stringify(sym); \ + .popsection; + +#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) + #ifdef __CHECKER__ #define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0) #else /* __CHECKER__ */ @@ -315,6 +307,28 @@ static inline void *offset_to_ptr(const int *off) */ #define statically_true(x) (__builtin_constant_p(x) && (x)) +/* + * Similar to statically_true() but produces a constant expression + * + * To be used in conjunction with macros, such as BUILD_BUG_ON_ZERO(), + * which require their input to be a constant expression and for which + * statically_true() would otherwise fail. + * + * This is a trade-off: const_true() requires all its operands to be + * compile time constants. Else, it would always returns false even on + * the most trivial cases like: + * + * true || non_const_var + * + * On the opposite, statically_true() is able to fold more complex + * tautologies and will return true on expressions such as: + * + * !(non_const_var * 8 % 4) + * + * For the general case, statically_true() is better. + */ +#define const_true(x) __builtin_choose_expr(__is_constexpr(x), x, false) + /* * This is needed in functions which generate the stack canary, see * arch/x86/kernel/smpboot.c::start_secondary() for an example. diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 45e598fe3476..77e6e195d1d6 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -52,8 +52,8 @@ extern void do_coredump(const kernel_siginfo_t *siginfo); #define __COREDUMP_PRINTK(Level, Format, ...) \ do { \ char comm[TASK_COMM_LEN]; \ - \ - get_task_comm(comm, current); \ + /* This will always be NUL terminated. */ \ + memcpy(comm, current->comm, sizeof(comm)); \ printk_ratelimited(Level "coredump: %d(%*pE): " Format "\n", \ task_tgid_vnr(current), (int)strlen(comm), comm, ##__VA_ARGS__); \ } while (0) \ diff --git a/include/linux/coresight.h b/include/linux/coresight.h index c13342594278..17276965ff1d 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -172,6 +172,9 @@ struct coresight_desc { * @dest_dev: a @coresight_device representation of the component connected to @src_port. NULL until the device is created * @link: Representation of the connection as a sysfs link. + * @filter_src_fwnode: filter source component's fwnode handle. + * @filter_src_dev: a @coresight_device representation of the component that + needs to be filtered. * * The full connection structure looks like this, where in_conns store * references to same connection as the source device's out_conns. @@ -200,8 +203,10 @@ struct coresight_connection { struct coresight_device *dest_dev; struct coresight_sysfs_link *link; struct coresight_device *src_dev; - atomic_t src_refcnt; - atomic_t dest_refcnt; + struct fwnode_handle *filter_src_fwnode; + struct coresight_device *filter_src_dev; + int src_refcnt; + int dest_refcnt; }; /** @@ -588,9 +593,14 @@ static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 o } #endif /* CONFIG_64BIT */ +static inline bool coresight_is_device_source(struct coresight_device *csdev) +{ + return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE); +} + static inline bool coresight_is_percpu_source(struct coresight_device *csdev) { - return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) && + return csdev && coresight_is_device_source(csdev) && (csdev->subtype.source_subtype == CORESIGHT_DEV_SUBTYPE_SOURCE_PROC); } @@ -662,6 +672,7 @@ void coresight_relaxed_write64(struct coresight_device *csdev, void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset); extern int coresight_get_cpu(struct device *dev); +extern int coresight_get_static_trace_id(struct device *dev, u32 *id); struct coresight_platform_data *coresight_get_platform_data(struct device *dev); struct coresight_connection * diff --git a/include/linux/cpu.h b/include/linux/cpu.h index bdcec1732445..6a0a8f1c7c90 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -77,6 +77,7 @@ extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index a04b73c40173..6cc5e484547c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -240,6 +240,7 @@ enum cpuhp_state { CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RANDOM_ONLINE, CPUHP_AP_RCUTREE_ONLINE, + CPUHP_AP_KTHREADS_ONLINE, CPUHP_AP_BASE_CACHEINFO_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 40, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 9278a50d514f..36a890d0dd57 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -391,7 +391,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) /** - * cpumask_any_but - return a "random" in a cpumask, but not this one. + * cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * @@ -411,7 +411,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) } /** - * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one. + * cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore @@ -840,7 +840,7 @@ void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) } /** - * cpumask_any - pick a "random" cpu from *srcp + * cpumask_any - pick an arbitrary cpu from *srcp * @srcp: the input cpumask * * Return: >= nr_cpu_ids if no cpus set. @@ -848,7 +848,7 @@ void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) #define cpumask_any(srcp) cpumask_first(srcp) /** - * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 + * cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * @@ -1043,7 +1043,6 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); -void init_cpu_online(const struct cpumask *src); #define assign_cpu(cpu, mask, val) \ assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index acc55626afdc..2f2555e6407c 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -20,6 +20,8 @@ extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); extern void elfcorehdr_free(unsigned long long addr); extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); +void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr, + unsigned long long paddr, unsigned long long size); extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot); @@ -99,6 +101,12 @@ static inline void vmcore_unusable(void) * indicated in the vmcore instead. For example, a ballooned page * contains no data and reading from such a page will cause high * load in the hypervisor. + * @get_device_ram: query RAM ranges that can only be detected by device + * drivers, such as the virtio-mem driver, so they can be included in + * the crash dump on architectures that allocate the elfcore hdr in the dump + * ("2nd") kernel. Indicated RAM ranges may contain holes to reduce the + * total number of ranges; such holes can be detected using the pfn_is_ram + * callback just like for other RAM. * @next: List head to manage registered callbacks internally; initialized by * register_vmcore_cb(). * @@ -109,11 +117,44 @@ static inline void vmcore_unusable(void) */ struct vmcore_cb { bool (*pfn_is_ram)(struct vmcore_cb *cb, unsigned long pfn); + int (*get_device_ram)(struct vmcore_cb *cb, struct list_head *list); struct list_head next; }; extern void register_vmcore_cb(struct vmcore_cb *cb); extern void unregister_vmcore_cb(struct vmcore_cb *cb); +struct vmcore_range { + struct list_head list; + unsigned long long paddr; + unsigned long long size; + loff_t offset; +}; + +/* Allocate a vmcore range and add it to the list. */ +static inline int vmcore_alloc_add_range(struct list_head *list, + unsigned long long paddr, unsigned long long size) +{ + struct vmcore_range *m = kzalloc(sizeof(*m), GFP_KERNEL); + + if (!m) + return -ENOMEM; + m->paddr = paddr; + m->size = size; + list_add_tail(&m->list, list); + return 0; +} + +/* Free a list of vmcore ranges. */ +static inline void vmcore_free_ranges(struct list_head *list) +{ + struct vmcore_range *m, *tmp; + + list_for_each_entry_safe(m, tmp, list, list) { + list_del(&m->list); + kfree(m); + } +} + #else /* !CONFIG_CRASH_DUMP */ static inline bool is_kdump_kernel(void) { return false; } #endif /* CONFIG_CRASH_DUMP */ diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h index 6bb0c0bf357b..16787c1cee21 100644 --- a/include/linux/crc-t10dif.h +++ b/include/linux/crc-t10dif.h @@ -6,11 +6,29 @@ #define CRC_T10DIF_DIGEST_SIZE 2 #define CRC_T10DIF_BLOCK_SIZE 1 -#define CRC_T10DIF_STRING "crct10dif" -extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, - size_t len); -extern __u16 crc_t10dif(unsigned char const *, size_t); -extern __u16 crc_t10dif_update(__u16 crc, unsigned char const *, size_t); +u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len); +u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len); + +static inline u16 crc_t10dif_update(u16 crc, const u8 *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC_T10DIF_ARCH)) + return crc_t10dif_arch(crc, p, len); + return crc_t10dif_generic(crc, p, len); +} + +static inline u16 crc_t10dif(const u8 *p, size_t len) +{ + return crc_t10dif_update(0, p, len); +} + +#if IS_ENABLED(CONFIG_CRC_T10DIF_ARCH) +bool crc_t10dif_is_optimized(void); +#else +static inline bool crc_t10dif_is_optimized(void) +{ + return false; +} +#endif #endif diff --git a/include/linux/crc32.h b/include/linux/crc32.h index 87f788c0d607..e9bd40056687 100644 --- a/include/linux/crc32.h +++ b/include/linux/crc32.h @@ -8,10 +8,49 @@ #include #include -u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len); -u32 __pure crc32_le_base(u32 crc, unsigned char const *p, size_t len); -u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len); -u32 __pure crc32_be_base(u32 crc, unsigned char const *p, size_t len); +u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len); +u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len); +u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len); +u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len); +u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len); +u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len); + +static inline u32 __pure crc32_le(u32 crc, const u8 *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC32_ARCH)) + return crc32_le_arch(crc, p, len); + return crc32_le_base(crc, p, len); +} + +static inline u32 __pure crc32_be(u32 crc, const u8 *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC32_ARCH)) + return crc32_be_arch(crc, p, len); + return crc32_be_base(crc, p, len); +} + +/* TODO: leading underscores should be dropped once callers have been updated */ +static inline u32 __pure __crc32c_le(u32 crc, const u8 *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC32_ARCH)) + return crc32c_le_arch(crc, p, len); + return crc32c_le_base(crc, p, len); +} + +/* + * crc32_optimizations() returns flags that indicate which CRC32 library + * functions are using architecture-specific optimizations. Unlike + * IS_ENABLED(CONFIG_CRC32_ARCH) it takes into account the different CRC32 + * variants and also whether any needed CPU features are available at runtime. + */ +#define CRC32_LE_OPTIMIZATION BIT(0) /* crc32_le() is optimized */ +#define CRC32_BE_OPTIMIZATION BIT(1) /* crc32_be() is optimized */ +#define CRC32C_OPTIMIZATION BIT(2) /* __crc32c_le() is optimized */ +#if IS_ENABLED(CONFIG_CRC32_ARCH) +u32 crc32_optimizations(void); +#else +static inline u32 crc32_optimizations(void) { return 0; } +#endif /** * crc32_le_combine - Combine two crc32 check values into one. For two @@ -38,9 +77,6 @@ static inline u32 crc32_le_combine(u32 crc1, u32 crc2, size_t len2) return crc32_le_shift(crc1, len2) ^ crc2; } -u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len); -u32 __pure __crc32c_le_base(u32 crc, unsigned char const *p, size_t len); - /** * __crc32c_le_combine - Combine two crc32c check values into one. For two * sequences of bytes, seq1 and seq2 with lengths len1 diff --git a/include/linux/crc32c.h b/include/linux/crc32c.h index 357ae4611a45..47eb78003c26 100644 --- a/include/linux/crc32c.h +++ b/include/linux/crc32c.h @@ -2,9 +2,12 @@ #ifndef _LINUX_CRC32C_H #define _LINUX_CRC32C_H -#include +#include -extern u32 crc32c(u32 crc, const void *address, unsigned int length); +static inline u32 crc32c(u32 crc, const void *address, unsigned int length) +{ + return __crc32c_le(crc, address, length); +} /* This macro exists for backwards-compatibility. */ #define crc32c_le crc32c diff --git a/include/linux/cred.h b/include/linux/cred.h index e4a3155fe409..0c3c4b16b469 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -155,8 +155,6 @@ extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); -extern const struct cred *override_creds(const struct cred *); -extern void revert_creds(const struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); @@ -172,12 +170,7 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred) cred->cap_inheritable)); } -/* - * Override creds without bumping reference count. Caller must ensure - * reference remains valid or has taken reference. Almost always not the - * interface you want. Use override_creds()/revert_creds() instead. - */ -static inline const struct cred *override_creds_light(const struct cred *override_cred) +static inline const struct cred *override_creds(const struct cred *override_cred) { const struct cred *old = current->cred; @@ -185,35 +178,12 @@ static inline const struct cred *override_creds_light(const struct cred *overrid return old; } -static inline void revert_creds_light(const struct cred *revert_cred) +static inline const struct cred *revert_creds(const struct cred *revert_cred) { + const struct cred *override_cred = current->cred; + rcu_assign_pointer(current->cred, revert_cred); -} - -/** - * get_new_cred_many - Get references on a new set of credentials - * @cred: The new credentials to reference - * @nr: Number of references to acquire - * - * Get references on the specified set of new credentials. The caller must - * release all acquired references. - */ -static inline struct cred *get_new_cred_many(struct cred *cred, int nr) -{ - atomic_long_add(nr, &cred->usage); - return cred; -} - -/** - * get_new_cred - Get a reference on a new set of credentials - * @cred: The new credentials to reference - * - * Get a reference on the specified set of new credentials. The caller must - * release the reference. - */ -static inline struct cred *get_new_cred(struct cred *cred) -{ - return get_new_cred_many(cred, 1); + return override_cred; } /** @@ -236,7 +206,8 @@ static inline const struct cred *get_cred_many(const struct cred *cred, int nr) if (!cred) return cred; nonconst_cred->non_rcu = 0; - return get_new_cred_many(nonconst_cred, nr); + atomic_long_add(nr, &nonconst_cred->usage); + return cred; } /* diff --git a/include/linux/damon.h b/include/linux/damon.h index a67f2c4940e9..af525252b853 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -193,11 +193,16 @@ struct damos_quota_goal { * size quota is set, DAMON tries to apply the action only up to &sz bytes * within &reset_interval. * - * Internally, the time quota is transformed to a size quota using estimated - * throughput of the scheme's action. DAMON then compares it against &sz and - * uses smaller one as the effective quota. + * To convince the different types of quotas and goals, DAMON internally + * converts those into one single size quota called "effective quota". DAMON + * internally uses it as the only one real quota. The conversion is made as + * follows. * - * If @goals is not empt, DAMON calculates yet another size quota based on the + * The time quota is transformed to a size quota using estimated throughput of + * the scheme's action. DAMON then compares it against &sz and uses smaller + * one as the effective quota. + * + * If @goals is not empty, DAMON calculates yet another size quota based on the * goals using its internal feedback loop algorithm, for every @reset_interval. * Then, if the new size quota is smaller than the effective quota, it uses the * new size quota as the effective quota. @@ -286,13 +291,33 @@ struct damos_watermarks { * @sz_tried: Total size of regions that the scheme is tried to be applied. * @nr_applied: Total number of regions that the scheme is applied. * @sz_applied: Total size of regions that the scheme is applied. + * @sz_ops_filter_passed: + * Total bytes that passed ops layer-handled DAMOS filters. * @qt_exceeds: Total number of times the quota of the scheme has exceeded. + * + * "Tried an action to a region" in this context means the DAMOS core logic + * determined the region as eligible to apply the action. The access pattern + * (&struct damos_access_pattern), quotas (&struct damos_quota), watermarks + * (&struct damos_watermarks) and filters (&struct damos_filter) that handled + * on core logic can affect this. The core logic asks the operation set + * (&struct damon_operations) to apply the action to the region. + * + * "Applied an action to a region" in this context means the operation set + * (&struct damon_operations) successfully applied the action to the region, at + * least to a part of the region. The filters (&struct damos_filter) that + * handled on operation set layer and type of the action and pages of the + * region can affect this. For example, if a filter is set to exclude + * anonymous pages and the region has only anonymous pages, the region will be + * failed at applying the action. If the action is &DAMOS_PAGEOUT and all + * pages of the region are already paged out, the region will be failed at + * applying the action. */ struct damos_stat { unsigned long nr_tried; unsigned long sz_tried; unsigned long nr_applied; unsigned long sz_applied; + unsigned long sz_ops_filter_passed; unsigned long qt_exceeds; }; @@ -327,8 +352,9 @@ enum damos_filter_type { /** * struct damos_filter - DAMOS action target memory filter. - * @type: Type of the page. - * @matching: If the matching page should filtered out or in. + * @type: Type of the target memory. + * @matching: Whether this is for @type-matching memory. + * @allow: Whether to include or exclude the @matching memory. * @memcg_id: Memcg id of the question if @type is DAMOS_FILTER_MEMCG. * @addr_range: Address range if @type is DAMOS_FILTER_TYPE_ADDR. * @target_idx: Index of the &struct damon_target of @@ -337,13 +363,15 @@ enum damos_filter_type { * @list: List head for siblings. * * Before applying the &damos->action to a memory region, DAMOS checks if each - * page of the region matches to this and avoid applying the action if so. - * Support of each filter type depends on the running &struct damon_operations - * and the type. Refer to &enum damos_filter_type for more detai. + * byte of the region matches to this given condition and avoid applying the + * action if so. Support of each filter type depends on the running &struct + * damon_operations and the type. Refer to &enum damos_filter_type for more + * details. */ struct damos_filter { enum damos_filter_type type; bool matching; + bool allow; union { unsigned short memcg_id; struct damon_addr_range addr_range; @@ -352,6 +380,31 @@ struct damos_filter { struct list_head list; }; +struct damon_ctx; +struct damos; + +/** + * struct damos_walk_control - Control damos_walk(). + * + * @walk_fn: Function to be called back for each region. + * @data: Data that will be passed to walk functions. + * + * Control damos_walk(), which requests specific kdamond to invoke the given + * function to each region that eligible to apply actions of the kdamond's + * schemes. Refer to damos_walk() for more details. + */ +struct damos_walk_control { + void (*walk_fn)(void *data, struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + struct damos *s, unsigned long sz_filter_passed); + void *data; +/* private: internal use only */ + /* informs if the kdamond finished handling of the walk request */ + struct completion completion; + /* informs if the walk is canceled. */ + bool canceled; +}; + /** * struct damos_access_pattern - Target access pattern of the given scheme. * @min_sz_region: Minimum size of target regions. @@ -415,6 +468,8 @@ struct damos { * @action */ unsigned long next_apply_sis; + /* informs if ongoing DAMOS walk for this scheme is finished */ + bool walk_completed; /* public: */ struct damos_quota quota; struct damos_watermarks wmarks; @@ -442,8 +497,6 @@ enum damon_ops_id { NR_DAMON_OPS, }; -struct damon_ctx; - /** * struct damon_operations - Monitoring operations for given use cases. * @@ -487,7 +540,8 @@ struct damon_ctx; * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action * to the region and return bytes of the region that the action is successfully - * applied. + * applied. It should also report how many bytes of the region has passed + * filters (&struct damos_filter) that handled by itself. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. @@ -504,7 +558,7 @@ struct damon_operations { struct damos *scheme); unsigned long (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, - struct damos *scheme); + struct damos *scheme, unsigned long *sz_filter_passed); bool (*target_valid)(struct damon_target *t); void (*cleanup)(struct damon_ctx *context); }; @@ -552,6 +606,27 @@ struct damon_callback { void (*before_terminate)(struct damon_ctx *context); }; +/* + * struct damon_call_control - Control damon_call(). + * + * @fn: Function to be called back. + * @data: Data that will be passed to @fn. + * @return_code: Return code from @fn invocation. + * + * Control damon_call(), which requests specific kdamond to invoke a given + * function. Refer to damon_call() for more details. + */ +struct damon_call_control { + int (*fn)(void *data); + void *data; + int return_code; +/* private: internal use only */ + /* informs if the kdamond finished handling of the request */ + struct completion completion; + /* informs if the kdamond canceled @fn infocation */ + bool canceled; +}; + /** * struct damon_attrs - Monitoring attributes for accuracy/overhead control. * @@ -632,6 +707,12 @@ struct damon_ctx { /* for scheme quotas prioritization */ unsigned long *regions_score_histogram; + struct damon_call_control *call_control; + struct mutex call_control_lock; + + struct damos_walk_control *walk_control; + struct mutex walk_control_lock; + /* public: */ struct task_struct *kdamond; struct mutex kdamond_lock; @@ -725,7 +806,7 @@ void damon_update_region_access_rate(struct damon_region *r, bool accessed, struct damon_attrs *attrs); struct damos_filter *damos_new_filter(enum damos_filter_type type, - bool matching); + bool matching, bool allow); void damos_add_filter(struct damos *s, struct damos_filter *f); void damos_destroy_filter(struct damos_filter *f); @@ -779,6 +860,9 @@ static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); +int damon_call(struct damon_ctx *ctx, struct damon_call_control *control); +int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control); + int damon_set_region_biggest_system_ram_default(struct damon_target *t, unsigned long *start, unsigned long *end); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bff956f7b2b9..4afb60365675 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -57,6 +57,7 @@ struct qstr { }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } +#define QSTR(n) (struct qstr)QSTR_INIT(n, strlen(n)) extern const struct qstr empty_name; extern const struct qstr slash_name; @@ -68,16 +69,24 @@ extern const struct qstr dotdot_name; * large memory footprint increase). */ #ifdef CONFIG_64BIT -# define DNAME_INLINE_LEN 40 /* 192 bytes */ +# define DNAME_INLINE_WORDS 5 /* 192 bytes */ #else # ifdef CONFIG_SMP -# define DNAME_INLINE_LEN 36 /* 128 bytes */ +# define DNAME_INLINE_WORDS 9 /* 128 bytes */ # else -# define DNAME_INLINE_LEN 44 /* 128 bytes */ +# define DNAME_INLINE_WORDS 11 /* 128 bytes */ # endif #endif +#define DNAME_INLINE_LEN (DNAME_INLINE_WORDS*sizeof(unsigned long)) + +union shortname_store { + unsigned char string[DNAME_INLINE_LEN]; + unsigned long words[DNAME_INLINE_WORDS]; +}; + #define d_lock d_lockref.lock +#define d_iname d_shortname.string struct dentry { /* RCU lookup touched fields */ @@ -88,7 +97,7 @@ struct dentry { struct qstr d_name; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ - unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ + union shortname_store d_shortname; /* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */ /* Ref lookup also touches following */ @@ -136,7 +145,8 @@ enum d_real_type { }; struct dentry_operations { - int (*d_revalidate)(struct dentry *, unsigned int); + int (*d_revalidate)(struct inode *, const struct qstr *, + struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, @@ -150,6 +160,8 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); + bool (*d_unalias_trylock)(const struct dentry *); + void (*d_unalias_unlock)(const struct dentry *); } ____cacheline_aligned; /* @@ -589,7 +601,7 @@ static inline struct inode *d_real_inode(const struct dentry *dentry) struct name_snapshot { struct qstr name; - unsigned char inline_name[DNAME_INLINE_LEN]; + union shortname_store inline_name; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 59444b495d49..fa2568b4380d 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -67,21 +67,23 @@ static const struct file_operations __fops = { \ typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); -#if defined(CONFIG_DEBUG_FS) - -struct dentry *debugfs_lookup(const char *name, struct dentry *parent); - struct debugfs_short_fops { ssize_t (*read)(struct file *, char __user *, size_t, loff_t *); ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *); loff_t (*llseek) (struct file *, loff_t, int); }; +#if defined(CONFIG_DEBUG_FS) + +struct dentry *debugfs_lookup(const char *name, struct dentry *parent); + struct dentry *debugfs_create_file_full(const char *name, umode_t mode, struct dentry *parent, void *data, + const void *aux, const struct file_operations *fops); struct dentry *debugfs_create_file_short(const char *name, umode_t mode, struct dentry *parent, void *data, + const void *aux, const struct debugfs_short_fops *fops); /** @@ -126,7 +128,15 @@ struct dentry *debugfs_create_file_short(const char *name, umode_t mode, const struct debugfs_short_fops *: debugfs_create_file_short, \ struct file_operations *: debugfs_create_file_full, \ struct debugfs_short_fops *: debugfs_create_file_short) \ - (name, mode, parent, data, fops) + (name, mode, parent, data, NULL, fops) + +#define debugfs_create_file_aux(name, mode, parent, data, aux, fops) \ + _Generic(fops, \ + const struct file_operations *: debugfs_create_file_full, \ + const struct debugfs_short_fops *: debugfs_create_file_short, \ + struct file_operations *: debugfs_create_file_full, \ + struct debugfs_short_fops *: debugfs_create_file_short) \ + (name, mode, parent, data, aux, fops) struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, struct dentry *parent, void *data, @@ -153,6 +163,7 @@ void debugfs_remove(struct dentry *dentry); void debugfs_lookup_and_remove(const char *name, struct dentry *parent); const struct file_operations *debugfs_real_fops(const struct file *filp); +const void *debugfs_get_aux(const struct file *file); int debugfs_file_get(struct dentry *dentry); void debugfs_file_put(struct dentry *dentry); @@ -164,8 +175,7 @@ ssize_t debugfs_attr_write(struct file *file, const char __user *buf, ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); -struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, - struct dentry *new_dir, const char *new_name); +int debugfs_change_name(struct dentry *dentry, const char *fmt, ...) __printf(2, 3); void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value); @@ -259,6 +269,14 @@ static inline struct dentry *debugfs_lookup(const char *name, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_file_aux(const char *name, + umode_t mode, struct dentry *parent, + void *data, void *aux, + const void *fops) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const void *fops) @@ -312,6 +330,7 @@ static inline void debugfs_lookup_and_remove(const char *name, { } const struct file_operations *debugfs_real_fops(const struct file *filp); +void *debugfs_get_aux(const struct file *file); static inline int debugfs_file_get(struct dentry *dentry) { @@ -341,10 +360,10 @@ static inline ssize_t debugfs_attr_write_signed(struct file *file, return -ENODEV; } -static inline struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, - struct dentry *new_dir, char *new_name) +static inline int __printf(2, 3) debugfs_change_name(struct dentry *dentry, + const char *fmt, ...) { - return ERR_PTR(-ENODEV); + return -ENODEV; } static inline void debugfs_create_u8(const char *name, umode_t mode, @@ -452,6 +471,11 @@ static inline ssize_t debugfs_read_file_str(struct file *file, #endif +#define debugfs_create_file_aux_num(name, mode, parent, data, n, fops) \ + debugfs_create_file_aux(name, mode, parent, data, \ + (void *)(unsigned long)n, fops) +#define debugfs_get_aux_num(f) (unsigned long)debugfs_get_aux(f) + /** * debugfs_create_xul - create a debugfs file that is used to read and write an * unsigned long value, formatted in hexadecimal diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 6639f48dac36..800dcc360db2 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -29,25 +29,39 @@ struct task_delay_info { * XXX_delay contains the accumulated delay time in nanoseconds. */ u64 blkio_start; + u64 blkio_delay_max; + u64 blkio_delay_min; u64 blkio_delay; /* wait for sync block io completion */ u64 swapin_start; + u64 swapin_delay_max; + u64 swapin_delay_min; u64 swapin_delay; /* wait for swapin */ u32 blkio_count; /* total count of the number of sync block */ /* io operations performed */ u32 swapin_count; /* total count of swapin */ u64 freepages_start; + u64 freepages_delay_max; + u64 freepages_delay_min; u64 freepages_delay; /* wait for memory reclaim */ u64 thrashing_start; + u64 thrashing_delay_max; + u64 thrashing_delay_min; u64 thrashing_delay; /* wait for thrashing page */ u64 compact_start; + u64 compact_delay_max; + u64 compact_delay_min; u64 compact_delay; /* wait for memory compact */ u64 wpcopy_start; + u64 wpcopy_delay_max; + u64 wpcopy_delay_min; u64 wpcopy_delay; /* wait for write-protect copy */ + u64 irq_delay_max; + u64 irq_delay_min; u64 irq_delay; /* wait for IRQ/SOFTIRQ */ u32 freepages_count; /* total count of memory reclaim */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8321f65897f3..bcc6d7b69470 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -299,6 +299,9 @@ struct target_type { #define dm_target_supports_mixed_zoned_model(type) (false) #endif +#define DM_TARGET_ATOMIC_WRITES 0x00000400 +#define dm_target_supports_atomic_writes(type) ((type)->features & DM_TARGET_ATOMIC_WRITES) + struct dm_target { struct dm_table *table; struct target_type *type; diff --git a/include/linux/device.h b/include/linux/device.h index 667cb6db9019..80a5b3268986 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -399,7 +399,23 @@ void __iomem *devm_of_iomap(struct device *dev, #endif /* allows to add/remove a custom action to devres stack */ -void devm_remove_action(struct device *dev, void (*action)(void *), void *data); +int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data); + +/** + * devm_remove_action() - removes previously added custom action + * @dev: Device that owns the action + * @action: Function implementing the action + * @data: Pointer to data passed to @action implementation + * + * Removes instance of @action previously added by devm_add_action(). + * Both action and data should match one of the existing entries. + */ +static inline +void devm_remove_action(struct device *dev, void (*action)(void *), void *data) +{ + WARN_ON(devm_remove_action_nowarn(dev, action, data)); +} + void devm_release_action(struct device *dev, void (*action)(void *), void *data); int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); @@ -1074,18 +1090,44 @@ void device_del(struct device *dev); DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) -int device_for_each_child(struct device *dev, void *data, - int (*fn)(struct device *dev, void *data)); -int device_for_each_child_reverse(struct device *dev, void *data, - int (*fn)(struct device *dev, void *data)); +int device_for_each_child(struct device *parent, void *data, + device_iter_t fn); +int device_for_each_child_reverse(struct device *parent, void *data, + device_iter_t fn); int device_for_each_child_reverse_from(struct device *parent, - struct device *from, const void *data, - int (*fn)(struct device *, const void *)); -struct device *device_find_child(struct device *dev, void *data, - int (*match)(struct device *dev, void *data)); -struct device *device_find_child_by_name(struct device *parent, - const char *name); -struct device *device_find_any_child(struct device *parent); + struct device *from, void *data, + device_iter_t fn); +struct device *device_find_child(struct device *parent, const void *data, + device_match_t match); +/** + * device_find_child_by_name - device iterator for locating a child device. + * @parent: parent struct device + * @name: name of the child device + * + * This is similar to the device_find_child() function above, but it + * returns a reference to a device that has the name @name. + * + * NOTE: you will need to drop the reference with put_device() after use. + */ +static inline struct device *device_find_child_by_name(struct device *parent, + const char *name) +{ + return device_find_child(parent, name, device_match_name); +} + +/** + * device_find_any_child - device iterator for locating a child device, if any. + * @parent: parent struct device + * + * This is similar to the device_find_child() function above, but it + * returns a reference to a child device, if any. + * + * NOTE: you will need to drop the reference with put_device() after use. + */ +static inline struct device *device_find_any_child(struct device *parent) +{ + return device_find_child(parent, NULL, device_match_any); +} int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index cdc4757217f9..f5a56efd2bd6 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -48,6 +48,7 @@ struct fwnode_handle; * will never get called until they do. * @remove: Called when a device removed from this bus. * @shutdown: Called at shut-down time to quiesce the device. + * @irq_get_affinity: Get IRQ affinity mask for the device on this bus. * * @online: Called to put the device back online (after offlining it). * @offline: Called to put the device offline for hot-removal. May fail. @@ -87,6 +88,8 @@ struct bus_type { void (*sync_state)(struct device *dev); void (*remove)(struct device *dev); void (*shutdown)(struct device *dev); + const struct cpumask *(*irq_get_affinity)(struct device *dev, + unsigned int irq_vec); int (*online)(struct device *dev); int (*offline)(struct device *dev); @@ -131,6 +134,7 @@ typedef int (*device_match_t)(struct device *dev, const void *data); /* Generic device matching functions that all busses can use to match with */ int device_match_name(struct device *dev, const void *name); +int device_match_type(struct device *dev, const void *type); int device_match_of_node(struct device *dev, const void *np); int device_match_fwnode(struct device *dev, const void *fwnode); int device_match_devt(struct device *dev, const void *pdevt); @@ -138,9 +142,12 @@ int device_match_acpi_dev(struct device *dev, const void *adev); int device_match_acpi_handle(struct device *dev, const void *handle); int device_match_any(struct device *dev, const void *unused); +/* Device iterating function type for various driver core for_each APIs */ +typedef int (*device_iter_t)(struct device *dev, void *data); + /* iterator helpers for buses */ -int bus_for_each_dev(const struct bus_type *bus, struct device *start, void *data, - int (*fn)(struct device *dev, void *data)); +int bus_for_each_dev(const struct bus_type *bus, struct device *start, + void *data, device_iter_t fn); struct device *bus_find_device(const struct bus_type *bus, struct device *start, const void *data, device_match_t match); /** diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 518c9c83d64b..45ee3a634999 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -82,18 +82,16 @@ bool class_is_registered(const struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); void class_compat_unregister(struct class_compat *cls); -int class_compat_create_link(struct class_compat *cls, struct device *dev, - struct device *device_link); -void class_compat_remove_link(struct class_compat *cls, struct device *dev, - struct device *device_link); +int class_compat_create_link(struct class_compat *cls, struct device *dev); +void class_compat_remove_link(struct class_compat *cls, struct device *dev); void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, const struct device *start, const struct device_type *type); struct device *class_dev_iter_next(struct class_dev_iter *iter); void class_dev_iter_exit(struct class_dev_iter *iter); -int class_for_each_device(const struct class *class, const struct device *start, void *data, - int (*fn)(struct device *dev, void *data)); +int class_for_each_device(const struct class *class, const struct device *start, + void *data, device_iter_t fn); struct device *class_find_device(const struct class *class, const struct device *start, const void *data, device_match_t match); diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 5c04b8e3833b..cd8e0f0a634b 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -154,7 +154,7 @@ void driver_remove_file(const struct device_driver *driver, int driver_set_override(struct device *dev, const char **override, const char *s, size_t len); int __must_check driver_for_each_device(struct device_driver *drv, struct device *start, - void *data, int (*fn)(struct device *dev, void *)); + void *data, device_iter_t fn); struct device *driver_find_device(const struct device_driver *drv, struct device *start, const void *data, device_match_t match); diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index b137fdb56093..346251bf1026 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -84,7 +84,7 @@ enum dma_transfer_direction { DMA_TRANS_NONE, }; -/** +/* * Interleaved Transfer Request * ---------------------------- * A chunk is collection of contiguous bytes to be transferred. @@ -223,7 +223,7 @@ enum sum_check_bits { }; /** - * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations + * enum sum_check_flags - result of async_{xor,pq}_zero_sum operations * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise */ @@ -286,7 +286,7 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; * pointer to the engine's metadata area * 4. Read out the metadata from the pointer * - * Note: the two mode is not compatible and clients must use one mode for a + * Warning: the two modes are not compatible and clients must use one mode for a * descriptor. */ enum dma_desc_metadata_mode { @@ -594,9 +594,13 @@ struct dma_descriptor_metadata_ops { * @phys: physical address of the descriptor * @chan: target channel for this operation * @tx_submit: accept the descriptor, assign ordered cookie and mark the + * @desc_free: driver's callback function to free a resusable descriptor + * after completion * descriptor pending. To be pushed on .issue_pending() call * @callback: routine to call after this operation is complete + * @callback_result: error result from a DMA transaction * @callback_param: general parameter to pass to the callback routine + * @unmap: hook for generic DMA unmap data * @desc_metadata_mode: core managed metadata mode to protect mixed use of * DESC_METADATA_CLIENT or DESC_METADATA_ENGINE. Otherwise * DESC_METADATA_NONE @@ -827,6 +831,9 @@ struct dma_filter { * @device_prep_dma_memset: prepares a memset operation * @device_prep_dma_memset_sg: prepares a memset operation over a scatter list * @device_prep_dma_interrupt: prepares an end of chain interrupt operation + * @device_prep_peripheral_dma_vec: prepares a scatter-gather DMA transfer, + * where the address and size of each segment is located in one entry of + * the dma_vec array. * @device_prep_slave_sg: prepares a slave dma operation * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio. * The function takes a buffer of size buf_len. The callback function will diff --git a/include/linux/efi.h b/include/linux/efi.h index e5815867aba9..053c57e61869 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -363,7 +363,6 @@ void efi_native_runtime_setup(void); #define ACPI_20_TABLE_GUID EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81) #define SMBIOS_TABLE_GUID EFI_GUID(0xeb9d2d31, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define SMBIOS3_TABLE_GUID EFI_GUID(0xf2fd1544, 0x9794, 0x4a2c, 0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94) -#define UGA_IO_PROTOCOL_GUID EFI_GUID(0x61a4d49e, 0x6f68, 0x4f1b, 0xb9, 0x22, 0xa8, 0x6e, 0xed, 0x0b, 0x07, 0xa2) #define EFI_GLOBAL_VARIABLE_GUID EFI_GUID(0x8be4df61, 0x93ca, 0x11d2, 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c) #define UV_SYSTEM_TABLE_GUID EFI_GUID(0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93) #define LINUX_EFI_CRASH_GUID EFI_GUID(0xcfc8fc79, 0xbe2e, 0x4ddc, 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0) @@ -373,7 +372,6 @@ void efi_native_runtime_setup(void); #define EFI_DEVICE_PATH_TO_TEXT_PROTOCOL_GUID EFI_GUID(0x8b843e20, 0x8132, 0x4852, 0x90, 0xcc, 0x55, 0x1a, 0x4e, 0x4a, 0x7f, 0x1c) #define EFI_DEVICE_PATH_FROM_TEXT_PROTOCOL_GUID EFI_GUID(0x05c99a21, 0xc70f, 0x4ad2, 0x8a, 0x5f, 0x35, 0xdf, 0x33, 0x43, 0xf5, 0x1e) #define EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID EFI_GUID(0x9042a9de, 0x23dc, 0x4a38, 0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a) -#define EFI_UGA_PROTOCOL_GUID EFI_GUID(0x982c298b, 0xf4fa, 0x41cb, 0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39) #define EFI_PCI_IO_PROTOCOL_GUID EFI_GUID(0x4cf5b200, 0x68b8, 0x4ca5, 0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x02, 0x9a) #define EFI_FILE_INFO_ID EFI_GUID(0x09576e92, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_SYSTEM_RESOURCE_TABLE_GUID EFI_GUID(0xb122a263, 0x3661, 0x4f68, 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80) @@ -1286,8 +1284,6 @@ struct linux_efi_memreserve { void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size); -char *efi_systab_show_arch(char *str); - /* * The LINUX_EFI_MOK_VARIABLE_TABLE_GUID config table can be provided * to the kernel by an EFI boot loader. The table contains a packed diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 752e0b297582..78318d49276d 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -179,6 +179,7 @@ int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, int em_dev_update_chip_binning(struct device *dev); int em_update_performance_limits(struct em_perf_domain *pd, unsigned long freq_min_khz, unsigned long freq_max_khz); +void em_rebuild_sched_domains(void); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM @@ -404,6 +405,7 @@ int em_update_performance_limits(struct em_perf_domain *pd, { return -EINVAL; } +static inline void em_rebuild_sched_domains(void) {} #endif #endif diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index ecf203f01034..9a1eacf35d37 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -81,7 +81,7 @@ static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per + * Return: true if address is link local reserved addr (01:80:c2:00:00:0X) per * IEEE 802.1Q 8.6.3 Frame filtering. * * Please note: addr must be aligned to u16. @@ -104,7 +104,7 @@ static inline bool is_link_local_ether_addr(const u8 *addr) * is_zero_ether_addr - Determine if give Ethernet address is all zeros. * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is all zeroes. + * Return: true if the address is all zeroes. * * Please note: addr must be aligned to u16. */ @@ -123,7 +123,7 @@ static inline bool is_zero_ether_addr(const u8 *addr) * is_multicast_ether_addr - Determine if the Ethernet address is a multicast. * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is a multicast address. + * Return: true if the address is a multicast address. * By definition the broadcast address is also a multicast address. */ static inline bool is_multicast_ether_addr(const u8 *addr) @@ -157,7 +157,7 @@ static inline bool is_multicast_ether_addr_64bits(const u8 *addr) * is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802). * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is a local address. + * Return: true if the address is a local address. */ static inline bool is_local_ether_addr(const u8 *addr) { @@ -168,7 +168,7 @@ static inline bool is_local_ether_addr(const u8 *addr) * is_broadcast_ether_addr - Determine if the Ethernet address is broadcast * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is the broadcast address. + * Return: true if the address is the broadcast address. * * Please note: addr must be aligned to u16. */ @@ -183,7 +183,7 @@ static inline bool is_broadcast_ether_addr(const u8 *addr) * is_unicast_ether_addr - Determine if the Ethernet address is unicast * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is a unicast address. + * Return: true if the address is a unicast address. */ static inline bool is_unicast_ether_addr(const u8 *addr) { @@ -197,7 +197,7 @@ static inline bool is_unicast_ether_addr(const u8 *addr) * Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not * a multicast address, and is not FF:FF:FF:FF:FF:FF. * - * Return true if the address is valid. + * Return: true if the address is valid. * * Please note: addr must be aligned to u16. */ @@ -214,7 +214,7 @@ static inline bool is_valid_ether_addr(const u8 *addr) * * Check that the value from the Ethertype/length field is a valid Ethertype. * - * Return true if the valid is an 802.3 supported Ethertype. + * Return: true if the valid is an 802.3 supported Ethertype. */ static inline bool eth_proto_is_802_3(__be16 proto) { @@ -458,7 +458,7 @@ static inline bool ether_addr_is_ip_mcast(const u8 *addr) * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return a u64 value of the address + * Return: a u64 value of the address */ static inline u64 ether_addr_to_u64(const u8 *addr) { diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index b8b935b52603..870994cc3ef7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -78,6 +78,9 @@ enum { * @cqe_size: Size of TX/RX completion queue event * @tx_push_buf_len: Size of TX push buffer * @tx_push_buf_max_len: Maximum allowed size of TX push buffer + * @hds_thresh: Packet size threshold for header data split (HDS) + * @hds_thresh_max: Maximum supported setting for @hds_threshold + * */ struct kernel_ethtool_ringparam { u32 rx_buf_len; @@ -87,6 +90,8 @@ struct kernel_ethtool_ringparam { u32 cqe_size; u32 tx_push_buf_len; u32 tx_push_buf_max_len; + u32 hds_thresh; + u32 hds_thresh_max; }; /** @@ -97,6 +102,7 @@ struct kernel_ethtool_ringparam { * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split + * @ETHTOOL_RING_USE_HDS_THRS: capture for setting header-data-split-thresh */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), @@ -105,6 +111,7 @@ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_PUSH = BIT(3), ETHTOOL_RING_USE_TX_PUSH_BUF_LEN = BIT(4), ETHTOOL_RING_USE_TCP_DATA_SPLIT = BIT(5), + ETHTOOL_RING_USE_HDS_THRS = BIT(6), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) @@ -257,7 +264,7 @@ struct ethtool_link_ksettings { * @mode : one of the ETHTOOL_LINK_MODE_*_BIT * (not atomic, no bound checking) * - * Returns true/false. + * Returns: true/false. */ #define ethtool_link_ksettings_test_link_mode(ptr, name, mode) \ test_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) @@ -412,6 +419,29 @@ struct ethtool_eth_phy_stats { ); }; +/** + * struct ethtool_phy_stats - PHY-level statistics counters + * @rx_packets: Total successfully received frames + * @rx_bytes: Total successfully received bytes + * @rx_errors: Total received frames with errors (e.g., CRC errors) + * @tx_packets: Total successfully transmitted frames + * @tx_bytes: Total successfully transmitted bytes + * @tx_errors: Total transmitted frames with errors + * + * This structure provides a standardized interface for reporting + * PHY-level statistics counters. It is designed to expose statistics + * commonly provided by PHYs but not explicitly defined in the IEEE + * 802.3 standard. + */ +struct ethtool_phy_stats { + u64 rx_packets; + u64 rx_bytes; + u64 rx_errors; + u64 tx_packets; + u64 tx_bytes; + u64 tx_errors; +}; + /* Basic IEEE 802.3 MAC Ctrl statistics (30.3.3.*), not otherwise exposed * via a more targeted API. */ @@ -529,6 +559,12 @@ struct ethtool_rmon_stats { /** * struct ethtool_ts_stats - HW timestamping statistics * @pkts: Number of packets successfully timestamped by the hardware. + * @onestep_pkts_unconfirmed: Number of PTP packets with one-step TX + * timestamping that were sent, but for which the + * device offers no confirmation whether they made + * it onto the wire and the timestamp was inserted + * in the originTimestamp or correctionField, or + * not. * @lost: Number of hardware timestamping requests where the timestamping * information from the hardware never arrived for submission with * the skb. @@ -541,6 +577,7 @@ struct ethtool_rmon_stats { struct ethtool_ts_stats { struct_group(tx_stats, u64 pkts; + u64 onestep_pkts_unconfirmed; u64 lost; u64 err; ); @@ -711,6 +748,7 @@ struct ethtool_rxfh_param { * @cmd: command number = %ETHTOOL_GET_TS_INFO * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags * @phc_index: device index of the associated PHC, or -1 if there is none + * @phc_qualifier: qualifier of the associated PHC * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values */ @@ -718,6 +756,7 @@ struct kernel_ethtool_ts_info { u32 cmd; u32 so_timestamping; int phc_index; + enum hwtstamp_provider_qualifier phc_qualifier; enum hwtstamp_tx_types tx_types; enum hwtstamp_rx_filters rx_filters; }; @@ -749,6 +788,7 @@ struct kernel_ethtool_ts_info { * @rss_context argument to @create_rxfh_context and friends. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. + * @supported_hwtstamp_qualifiers: bitfield of supported hwtstamp qualifier. * @get_drvinfo: Report driver/device information. Modern drivers no * longer have to implement this callback. Most fields are * correctly filled in by the core using system information, or @@ -966,6 +1006,7 @@ struct ethtool_ops { u32 rxfh_max_num_contexts; u32 supported_coalesce_params; u32 supported_ring_params; + u32 supported_hwtstamp_qualifiers; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); @@ -1199,7 +1240,7 @@ ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, * @dev: pointer to net_device structure * @vclock_index: pointer to pointer of vclock index * - * Return number of phc vclocks + * Return: number of phc vclocks */ int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index); @@ -1253,7 +1294,7 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, * ethtool_get_ts_info_by_layer - Obtains time stamping capabilities from the MAC or PHY layer. * @dev: pointer to net_device structure * @info: buffer to hold the result - * Returns zero on success, non-zero otherwise. + * Returns: zero on success, non-zero otherwise. */ int ethtool_get_ts_info_by_layer(struct net_device *dev, struct kernel_ethtool_ts_info *info); @@ -1299,24 +1340,4 @@ struct ethtool_forced_speed_map { void ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size); - -/* C33 PSE extended state and substate. */ -struct ethtool_c33_pse_ext_state_info { - enum ethtool_c33_pse_ext_state c33_pse_ext_state; - union { - enum ethtool_c33_pse_ext_substate_error_condition error_condition; - enum ethtool_c33_pse_ext_substate_mr_pse_enable mr_pse_enable; - enum ethtool_c33_pse_ext_substate_option_detect_ted option_detect_ted; - enum ethtool_c33_pse_ext_substate_option_vport_lim option_vport_lim; - enum ethtool_c33_pse_ext_substate_ovld_detected ovld_detected; - enum ethtool_c33_pse_ext_substate_power_not_available power_not_available; - enum ethtool_c33_pse_ext_substate_short_detected short_detected; - u32 __c33_pse_ext_substate; - }; -}; - -struct ethtool_c33_pse_pw_limit_range { - u32 min; - u32 max; -}; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/export.h b/include/linux/export.h index 2633df4d31e6..a8c23d945634 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -52,9 +52,24 @@ #else +#ifdef CONFIG_GENDWARFKSYMS +/* + * With CONFIG_GENDWARFKSYMS, ensure the compiler emits debugging + * information for all exported symbols, including those defined in + * different TUs, by adding a __gendwarfksyms_ptr_ pointer + * that's discarded during the final link. + */ +#define __GENDWARFKSYMS_EXPORT(sym) \ + static typeof(sym) *__gendwarfksyms_ptr_##sym __used \ + __section(".discard.gendwarfksyms") = &sym; +#else +#define __GENDWARFKSYMS_EXPORT(sym) +#endif + #define __EXPORT_SYMBOL(sym, license, ns) \ extern typeof(sym) sym; \ __ADDRESSABLE(sym) \ + __GENDWARFKSYMS_EXPORT(sym) \ asm(__stringify(___EXPORT_SYMBOL(sym, license, ns))) #endif diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 4cc8801e50e3..a087606ace19 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -3,6 +3,7 @@ #define LINUX_EXPORTFS_H 1 #include +#include struct dentry; struct iattr; @@ -156,6 +157,17 @@ struct fid { }; }; +enum handle_to_path_flags { + HANDLE_CHECK_PERMS = (1 << 0), + HANDLE_CHECK_SUBTREE = (1 << 1), +}; + +struct handle_to_path_ctx { + struct path root; + enum handle_to_path_flags flags; + unsigned int fh_flags; +}; + #define EXPORT_FH_CONNECTABLE 0x1 /* Encode file handle with parent */ #define EXPORT_FH_FID 0x2 /* File handle may be non-decodeable */ #define EXPORT_FH_DIR_ONLY 0x4 /* Only decode file handle for a directory */ @@ -225,6 +237,12 @@ struct fid { * is also a directory. In the event that it cannot be found, or storage * space cannot be allocated, a %ERR_PTR should be returned. * + * permission: + * Allow filesystems to specify a custom permission function. + * + * open: + * Allow filesystems to specify a custom open function. + * * commit_metadata: * @commit_metadata should commit metadata changes to stable storage. * @@ -251,6 +269,8 @@ struct export_operations { bool write, u32 *device_generation); int (*commit_blocks)(struct inode *inode, struct iomap *iomaps, int nr_iomaps, struct iattr *iattr); + int (*permission)(struct handle_to_path_ctx *ctx, unsigned int oflags); + struct file * (*open)(struct path *path, unsigned int oflags); #define EXPORT_OP_NOWCC (0x1) /* don't collect v3 wcc data */ #define EXPORT_OP_NOSUBTREECHK (0x2) /* no subtree checking */ #define EXPORT_OP_CLOSE_BEFORE_UNLINK (0x4) /* close files before unlink */ diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 89ff45bd6f01..78f660ebc318 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -89,6 +89,16 @@ #define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE | \ FAN_RENAME) +/* Content events can be used to inspect file content */ +#define FANOTIFY_CONTENT_PERM_EVENTS (FAN_OPEN_PERM | FAN_OPEN_EXEC_PERM | \ + FAN_ACCESS_PERM) +/* Pre-content events can be used to fill file content */ +#define FANOTIFY_PRE_CONTENT_EVENTS (FAN_PRE_ACCESS) + +/* Events that require a permission response from user */ +#define FANOTIFY_PERM_EVENTS (FANOTIFY_CONTENT_PERM_EVENTS | \ + FANOTIFY_PRE_CONTENT_EVENTS) + /* Events that can be reported with event->fd */ #define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) @@ -104,10 +114,6 @@ FANOTIFY_INODE_EVENTS | \ FANOTIFY_ERROR_EVENTS) -/* Events that require a permission response from user */ -#define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ - FAN_OPEN_EXEC_PERM) - /* Extra flags that may be reported with event or control handling of events */ #define FANOTIFY_EVENT_FLAGS (FAN_EVENT_ON_CHILD | FAN_ONDIR) @@ -126,7 +132,9 @@ /* These masks check for invalid bits in permission responses. */ #define FANOTIFY_RESPONSE_ACCESS (FAN_ALLOW | FAN_DENY) #define FANOTIFY_RESPONSE_FLAGS (FAN_AUDIT | FAN_INFO) -#define FANOTIFY_RESPONSE_VALID_MASK (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS) +#define FANOTIFY_RESPONSE_VALID_MASK \ + (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS | \ + (FAN_ERRNO_MASK << FAN_ERRNO_SHIFT)) /* Do not use these old uapi constants internally */ #undef FAN_ALL_CLASS_BITS diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h index c50882f19235..966092ffa89a 100644 --- a/include/linux/fiemap.h +++ b/include/linux/fiemap.h @@ -5,12 +5,18 @@ #include #include +/** + * struct fiemap_extent_info - fiemap request to a filesystem + * @fi_flags: Flags as passed from user + * @fi_extents_mapped: Number of mapped extents + * @fi_extents_max: Size of fiemap_extent array + * @fi_extents_start: Start of fiemap_extent array + */ struct fiemap_extent_info { - unsigned int fi_flags; /* Flags as passed from user */ - unsigned int fi_extents_mapped; /* Number of mapped extents */ - unsigned int fi_extents_max; /* Size of fiemap_extent array */ - struct fiemap_extent __user *fi_extents_start; /* Start of - fiemap_extent array */ + unsigned int fi_flags; + unsigned int fi_extents_mapped; + unsigned int fi_extents_max; + struct fiemap_extent __user *fi_extents_start; }; int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, diff --git a/include/linux/filter.h b/include/linux/filter.h index 0477254bc2d3..a3ea46281595 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1179,17 +1179,18 @@ static inline int xdp_ok_fwd_dev(const struct net_device *fwd, * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct xdp_buff *xdp, struct bpf_prog *prog); + struct xdp_buff *xdp, const struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *prog); + const struct bpf_prog *prog); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, - struct bpf_prog *prog); + const struct bpf_prog *prog); void xdp_do_flush(void); -void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act); +void bpf_warn_invalid_xdp_action(const struct net_device *dev, + const struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, diff --git a/include/linux/firmware/cirrus/cs_dsp_test_utils.h b/include/linux/firmware/cirrus/cs_dsp_test_utils.h new file mode 100644 index 000000000000..4f87a908ab4f --- /dev/null +++ b/include/linux/firmware/cirrus/cs_dsp_test_utils.h @@ -0,0 +1,160 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Support utilities for cs_dsp testing. + * + * Copyright (C) 2024 Cirrus Logic, Inc. and + * Cirrus Logic International Semiconductor Ltd. + */ + +#include +#include + +struct kunit; +struct cs_dsp_test; +struct cs_dsp_test_local; + +/** + * struct cs_dsp_test - base class for test utilities + * + * @test: Pointer to struct kunit instance. + * @dsp: Pointer to struct cs_dsp instance. + * @local: Private data for each test suite. + */ +struct cs_dsp_test { + struct kunit *test; + struct cs_dsp *dsp; + + struct cs_dsp_test_local *local; + + /* Following members are private */ + bool saw_bus_write; +}; + +/** + * struct cs_dsp_mock_alg_def - Info for creating a mock algorithm entry. + * + * @id Algorithm ID. + * @ver; Algorithm version. + * @xm_base_words XM base address in DSP words. + * @xm_size_words XM size in DSP words. + * @ym_base_words YM base address in DSP words. + * @ym_size_words YM size in DSP words. + * @zm_base_words ZM base address in DSP words. + * @zm_size_words ZM size in DSP words. + */ +struct cs_dsp_mock_alg_def { + unsigned int id; + unsigned int ver; + unsigned int xm_base_words; + unsigned int xm_size_words; + unsigned int ym_base_words; + unsigned int ym_size_words; + unsigned int zm_base_words; + unsigned int zm_size_words; +}; + +struct cs_dsp_mock_coeff_def { + const char *shortname; + const char *fullname; + const char *description; + u16 type; + u16 flags; + u16 mem_type; + unsigned int offset_dsp_words; + unsigned int length_bytes; +}; + +/** + * struct cs_dsp_mock_xm_header - XM header builder + * + * @test_priv: Pointer to the struct cs_dsp_test. + * @blob_data: Pointer to the created blob data. + * @blob_size_bytes: Size of the data at blob_data. + */ +struct cs_dsp_mock_xm_header { + struct cs_dsp_test *test_priv; + void *blob_data; + size_t blob_size_bytes; +}; + +struct cs_dsp_mock_wmfw_builder; +struct cs_dsp_mock_bin_builder; + +extern const unsigned int cs_dsp_mock_adsp2_32bit_sysbase; +extern const unsigned int cs_dsp_mock_adsp2_16bit_sysbase; +extern const unsigned int cs_dsp_mock_halo_core_base; +extern const unsigned int cs_dsp_mock_halo_sysinfo_base; + +extern const struct cs_dsp_region cs_dsp_mock_halo_dsp1_regions[]; +extern const unsigned int cs_dsp_mock_halo_dsp1_region_sizes[]; +extern const struct cs_dsp_region cs_dsp_mock_adsp2_32bit_dsp1_regions[]; +extern const unsigned int cs_dsp_mock_adsp2_32bit_dsp1_region_sizes[]; +extern const struct cs_dsp_region cs_dsp_mock_adsp2_16bit_dsp1_regions[]; +extern const unsigned int cs_dsp_mock_adsp2_16bit_dsp1_region_sizes[]; +int cs_dsp_mock_count_regions(const unsigned int *region_sizes); +unsigned int cs_dsp_mock_size_of_region(const struct cs_dsp *dsp, int mem_type); +unsigned int cs_dsp_mock_base_addr_for_mem(struct cs_dsp_test *priv, int mem_type); +unsigned int cs_dsp_mock_reg_addr_inc_per_unpacked_word(struct cs_dsp_test *priv); +unsigned int cs_dsp_mock_reg_block_length_bytes(struct cs_dsp_test *priv, int mem_type); +unsigned int cs_dsp_mock_reg_block_length_registers(struct cs_dsp_test *priv, int mem_type); +unsigned int cs_dsp_mock_reg_block_length_dsp_words(struct cs_dsp_test *priv, int mem_type); +bool cs_dsp_mock_has_zm(struct cs_dsp_test *priv); +int cs_dsp_mock_packed_to_unpacked_mem_type(int packed_mem_type); +unsigned int cs_dsp_mock_num_dsp_words_to_num_packed_regs(unsigned int num_dsp_words); +unsigned int cs_dsp_mock_xm_header_get_alg_base_in_words(struct cs_dsp_test *priv, + unsigned int alg_id, + int mem_type); +unsigned int cs_dsp_mock_xm_header_get_fw_version_from_regmap(struct cs_dsp_test *priv); +unsigned int cs_dsp_mock_xm_header_get_fw_version(struct cs_dsp_mock_xm_header *header); +void cs_dsp_mock_xm_header_drop_from_regmap_cache(struct cs_dsp_test *priv); +int cs_dsp_mock_xm_header_write_to_regmap(struct cs_dsp_mock_xm_header *header); +struct cs_dsp_mock_xm_header *cs_dsp_create_mock_xm_header(struct cs_dsp_test *priv, + const struct cs_dsp_mock_alg_def *algs, + size_t num_algs); + +int cs_dsp_mock_regmap_init(struct cs_dsp_test *priv); +void cs_dsp_mock_regmap_drop_range(struct cs_dsp_test *priv, + unsigned int first_reg, unsigned int last_reg); +void cs_dsp_mock_regmap_drop_regs(struct cs_dsp_test *priv, + unsigned int first_reg, size_t num_regs); +void cs_dsp_mock_regmap_drop_bytes(struct cs_dsp_test *priv, + unsigned int first_reg, size_t num_bytes); +void cs_dsp_mock_regmap_drop_system_regs(struct cs_dsp_test *priv); +bool cs_dsp_mock_regmap_is_dirty(struct cs_dsp_test *priv, bool drop_system_regs); + +struct cs_dsp_mock_bin_builder *cs_dsp_mock_bin_init(struct cs_dsp_test *priv, + int format_version, + unsigned int fw_version); +void cs_dsp_mock_bin_add_raw_block(struct cs_dsp_mock_bin_builder *builder, + unsigned int alg_id, unsigned int alg_ver, + int type, unsigned int offset, + const void *payload_data, size_t payload_len_bytes); +void cs_dsp_mock_bin_add_info(struct cs_dsp_mock_bin_builder *builder, + const char *info); +void cs_dsp_mock_bin_add_name(struct cs_dsp_mock_bin_builder *builder, + const char *name); +void cs_dsp_mock_bin_add_patch(struct cs_dsp_mock_bin_builder *builder, + unsigned int alg_id, unsigned int alg_ver, + int mem_region, unsigned int reg_addr_offset, + const void *payload_data, size_t payload_len_bytes); +struct firmware *cs_dsp_mock_bin_get_firmware(struct cs_dsp_mock_bin_builder *builder); + +struct cs_dsp_mock_wmfw_builder *cs_dsp_mock_wmfw_init(struct cs_dsp_test *priv, + int format_version); +void cs_dsp_mock_wmfw_add_raw_block(struct cs_dsp_mock_wmfw_builder *builder, + int mem_region, unsigned int mem_offset_dsp_words, + const void *payload_data, size_t payload_len_bytes); +void cs_dsp_mock_wmfw_add_info(struct cs_dsp_mock_wmfw_builder *builder, + const char *info); +void cs_dsp_mock_wmfw_add_data_block(struct cs_dsp_mock_wmfw_builder *builder, + int mem_region, unsigned int mem_offset_dsp_words, + const void *payload_data, size_t payload_len_bytes); +void cs_dsp_mock_wmfw_start_alg_info_block(struct cs_dsp_mock_wmfw_builder *builder, + unsigned int alg_id, + const char *name, + const char *description); +void cs_dsp_mock_wmfw_add_coeff_desc(struct cs_dsp_mock_wmfw_builder *builder, + const struct cs_dsp_mock_coeff_def *def); +void cs_dsp_mock_wmfw_end_alg_info_block(struct cs_dsp_mock_wmfw_builder *builder); +struct firmware *cs_dsp_mock_wmfw_get_firmware(struct cs_dsp_mock_wmfw_builder *builder); +int cs_dsp_mock_wmfw_format_version(struct cs_dsp_mock_wmfw_builder *builder); diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index 4621aec0328c..983e1591bbba 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -105,6 +105,14 @@ bool qcom_scm_ice_available(void); int qcom_scm_ice_invalidate_key(u32 index); int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size, enum qcom_scm_ice_cipher cipher, u32 data_unit_size); +bool qcom_scm_has_wrapped_key_support(void); +int qcom_scm_derive_sw_secret(const u8 *eph_key, size_t eph_key_size, + u8 *sw_secret, size_t sw_secret_size); +int qcom_scm_generate_ice_key(u8 *lt_key, size_t lt_key_size); +int qcom_scm_prepare_ice_key(const u8 *lt_key, size_t lt_key_size, + u8 *eph_key, size_t eph_key_size); +int qcom_scm_import_ice_key(const u8 *raw_key, size_t raw_key_size, + u8 *lt_key, size_t lt_key_size); bool qcom_scm_hdcp_available(void); int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h index 3abe614ef5f0..4d3f8074c137 100644 --- a/include/linux/folio_queue.h +++ b/include/linux/folio_queue.h @@ -37,16 +37,20 @@ struct folio_queue { #if PAGEVEC_SIZE > BITS_PER_LONG #error marks is not big enough #endif + unsigned int rreq_id; + unsigned int debug_id; }; /** * folioq_init - Initialise a folio queue segment * @folioq: The segment to initialise + * @rreq_id: The request identifier to use in tracelines. * - * Initialise a folio queue segment. Note that the folio pointers are - * left uninitialised. + * Initialise a folio queue segment and set an identifier to be used in traces. + * + * Note that the folio pointers are left uninitialised. */ -static inline void folioq_init(struct folio_queue *folioq) +static inline void folioq_init(struct folio_queue *folioq, unsigned int rreq_id) { folio_batch_init(&folioq->vec); folioq->next = NULL; @@ -54,6 +58,8 @@ static inline void folioq_init(struct folio_queue *folioq) folioq->marks = 0; folioq->marks2 = 0; folioq->marks3 = 0; + folioq->rreq_id = rreq_id; + folioq->debug_id = 0; } /** diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 0d99bf11d260..e4ce1cae03bf 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -616,6 +616,12 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, return false; } +/* + * To work around what seems to be an optimizer bug, the macro arguments + * need to have const copies or the values end up changed by the time they + * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture + * __bos() results in const temp vars") for more details. + */ #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ const size_t __fortify_size = (size_t)(size); \ @@ -623,6 +629,8 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ + /* Keep a mutable version of the size for the final copy. */ \ + size_t __copy_size = __fortify_size; \ fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ @@ -630,7 +638,11 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, __fortify_size, \ "field \"" #p "\" at " FILE_LINE, \ __p_size_field); \ - __underlying_##op(p, q, __fortify_size); \ + /* Hide only the run-time size from value range tracking to */ \ + /* silence compile-time false positive bounds warnings. */ \ + if (!__builtin_constant_p(__copy_size)) \ + OPTIMIZER_HIDE_VAR(__copy_size); \ + __underlying_##op(p, q, __copy_size); \ }) /* diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index f39869588117..702099f08929 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -5,47 +5,68 @@ #include #include -#include +#include +#include +#include struct fprobe; - typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *regs, void *entry_data); typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *regs, void *entry_data); +/** + * struct fprobe_hlist_node - address based hash list node for fprobe. + * + * @hlist: The hlist node for address search hash table. + * @addr: One of the probing address of @fp. + * @fp: The fprobe which owns this. + */ +struct fprobe_hlist_node { + struct hlist_node hlist; + unsigned long addr; + struct fprobe *fp; +}; + +/** + * struct fprobe_hlist - hash list nodes for fprobe. + * + * @hlist: The hlist node for existence checking hash table. + * @rcu: rcu_head for RCU deferred release. + * @fp: The fprobe which owns this fprobe_hlist. + * @size: The size of @array. + * @array: The fprobe_hlist_node for each address to probe. + */ +struct fprobe_hlist { + struct hlist_node hlist; + struct rcu_head rcu; + struct fprobe *fp; + int size; + struct fprobe_hlist_node array[] __counted_by(size); +}; + /** * struct fprobe - ftrace based probe. - * @ops: The ftrace_ops. + * * @nmissed: The counter for missing events. * @flags: The status flag. - * @rethook: The rethook data structure. (internal data) * @entry_data_size: The private data storage size. - * @nr_maxactive: The max number of active functions. * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. + * @hlist_array: The fprobe_hlist for fprobe search from IP hash table. */ struct fprobe { -#ifdef CONFIG_FUNCTION_TRACER - /* - * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too. - * But user of fprobe may keep embedding the struct fprobe on their own - * code. To avoid build error, this will keep the fprobe data structure - * defined here, but remove ftrace_ops data structure. - */ - struct ftrace_ops ops; -#endif unsigned long nmissed; unsigned int flags; - struct rethook *rethook; size_t entry_data_size; - int nr_maxactive; fprobe_entry_cb entry_handler; fprobe_exit_cb exit_handler; + + struct fprobe_hlist *hlist_array; }; /* This fprobe is soft-disabled. */ @@ -121,4 +142,9 @@ static inline void enable_fprobe(struct fprobe *fp) fp->flags &= ~FPROBE_FL_DISABLED; } +/* The entry data size is 4 bits (=16) * sizeof(long) in maximum */ +#define FPROBE_DATA_SIZE_BITS 4 +#define MAX_FPROBE_DATA_SIZE_WORD ((1L << FPROBE_DATA_SIZE_BITS) - 1) +#define MAX_FPROBE_DATA_SIZE (MAX_FPROBE_DATA_SIZE_WORD * sizeof(long)) + #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 7e29433c5ecc..be3ad155ec9f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -173,13 +173,20 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) -/* FMODE_* bit 24 */ - /* File is embedded in backing_file object */ -#define FMODE_BACKING ((__force fmode_t)(1 << 25)) +#define FMODE_BACKING ((__force fmode_t)(1 << 24)) -/* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) +/* + * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) + +/* + * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) @@ -190,6 +197,32 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) +/* + * The two FMODE_NONOTIFY* define which fsnotify events should not be generated + * for a file. These are the possible values of (f->f_mode & + * FMODE_FSNOTIFY_MASK) and their meaning: + * + * FMODE_NONOTIFY - suppress all (incl. non-permission) events. + * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. + * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events. + */ +#define FMODE_FSNOTIFY_MASK \ + (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) + +#define FMODE_FSNOTIFY_NONE(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS +#define FMODE_FSNOTIFY_PERM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ + (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) +#define FMODE_FSNOTIFY_HSM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0) +#else +#define FMODE_FSNOTIFY_PERM(mode) 0 +#define FMODE_FSNOTIFY_HSM(mode) 0 +#endif + + /* * Attribute flags. These should be or-ed together to figure out what * has been changed! @@ -322,6 +355,7 @@ struct readahead_control; #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC +#define IOCB_DONTCACHE (__force int) RWF_DONTCACHE /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -348,6 +382,7 @@ struct readahead_control; #define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) +#define IOCB_HAS_METADATA (1 << 24) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ @@ -356,7 +391,8 @@ struct readahead_control; { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ - { IOCB_ATOMIC, "ATOMIC"}, \ + { IOCB_ATOMIC, "ATOMIC" }, \ + { IOCB_DONTCACHE, "DONTCACHE" }, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ @@ -626,6 +662,7 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 #define IOP_MGTIME 0x0020 +#define IOP_CACHED_LINK 0x0040 /* * Keep mostly read-only and often accessed (especially for @@ -723,7 +760,10 @@ struct inode { }; struct file_lock_context *i_flctx; struct address_space i_data; - struct list_head i_devices; + union { + struct list_head i_devices; + int i_linklen; + }; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; @@ -749,6 +789,13 @@ struct inode { void *i_private; /* fs or device private pointer */ } __randomize_layout; +static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) +{ + inode->i_link = link; + inode->i_linklen = linklen; + inode->i_opflags |= IOP_CACHED_LINK; +} + /* * Get bit address from inode->i_state to use with wait_var_event() * infrastructre. @@ -1232,6 +1279,7 @@ extern int send_sigurg(struct file *file); #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ +#define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ /* Possible states of 'frozen' field */ enum { @@ -2127,6 +2175,8 @@ struct file_operations { #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Supports asynchronous lock callbacks */ #define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) +/* File system supports uncached read/write buffered IO */ +#define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, @@ -2751,6 +2801,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); +struct file *dentry_open_nonotify(const struct path *path, int flags, + const struct cred *cred); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); struct path *backing_file_user_path(struct file *f); @@ -2874,6 +2926,8 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); +int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, + loff_t end); static inline int file_write_and_wait(struct file *file) { @@ -2906,6 +2960,11 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; + } else if (iocb->ki_flags & IOCB_DONTCACHE) { + struct address_space *mapping = iocb->ki_filp->f_mapping; + + filemap_fdatawrite_range_kick(mapping, iocb->ki_pos, + iocb->ki_pos + count); } return count; @@ -3059,6 +3118,28 @@ static inline void allow_write_access(struct file *file) if (file) atomic_inc(&file_inode(file)->i_writecount); } + +/* + * Do not prevent write to executable file when watched by pre-content events. + * + * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at + * the time of file open and remains constant for entire lifetime of the file, + * so if pre-content watches are added post execution or removed before the end + * of the execution, it will not cause i_writecount reference leak. + */ +static inline int exe_file_deny_write_access(struct file *exe_file) +{ + if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return 0; + return deny_write_access(exe_file); +} +static inline void exe_file_allow_write_access(struct file *exe_file) +{ + if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return; + allow_write_access(exe_file); +} + static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; @@ -3351,7 +3432,7 @@ extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) -extern int readlink_copy(char __user *, int, const char *); +extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); @@ -3468,7 +3549,6 @@ struct offset_ctx { void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); -int simple_offset_empty(struct dentry *dentry); int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, @@ -3614,6 +3694,14 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) return -EOPNOTSUPP; } + if (flags & RWF_DONTCACHE) { + /* file system must support it */ + if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE)) + return -EOPNOTSUPP; + /* DAX mappings not supported */ + if (IS_DAX(ki->ki_filp->f_mapping->host)) + return -EOPNOTSUPP; + } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; @@ -3707,11 +3795,9 @@ struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) -#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) -#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ - (flag & __FMODE_NONOTIFY))) +#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) static inline bool is_sxid(umode_t mode) { diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 3cef566088fc..53e566efd5fd 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -84,6 +84,8 @@ extern int fs_lookup_param(struct fs_context *fc, extern int lookup_constant(const struct constant_table tbl[], const char *name, int not_found); +extern const struct constant_table bool_names[]; + #ifdef CONFIG_VALIDATE_FS_PARSER extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special); diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 772f822dc6b8..18855cb44b1c 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -192,7 +192,8 @@ struct fscrypt_operations { unsigned int *num_devs); }; -int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags); +int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags); static inline struct fscrypt_inode_info * fscrypt_get_inode_info(const struct inode *inode) @@ -711,8 +712,8 @@ static inline u64 fscrypt_fname_siphash(const struct inode *dir, return 0; } -static inline int fscrypt_d_revalidate(struct dentry *dentry, - unsigned int flags) +static inline int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { return 1; } diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index c90ec889bfc2..99f30c7d6208 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -438,21 +438,21 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, extern const struct bus_type fsl_mc_bus_type; -extern struct device_type fsl_mc_bus_dprc_type; -extern struct device_type fsl_mc_bus_dpni_type; -extern struct device_type fsl_mc_bus_dpio_type; -extern struct device_type fsl_mc_bus_dpsw_type; -extern struct device_type fsl_mc_bus_dpbp_type; -extern struct device_type fsl_mc_bus_dpcon_type; -extern struct device_type fsl_mc_bus_dpmcp_type; -extern struct device_type fsl_mc_bus_dpmac_type; -extern struct device_type fsl_mc_bus_dprtc_type; -extern struct device_type fsl_mc_bus_dpseci_type; -extern struct device_type fsl_mc_bus_dpdmux_type; -extern struct device_type fsl_mc_bus_dpdcei_type; -extern struct device_type fsl_mc_bus_dpaiop_type; -extern struct device_type fsl_mc_bus_dpci_type; -extern struct device_type fsl_mc_bus_dpdmai_type; +extern const struct device_type fsl_mc_bus_dprc_type; +extern const struct device_type fsl_mc_bus_dpni_type; +extern const struct device_type fsl_mc_bus_dpio_type; +extern const struct device_type fsl_mc_bus_dpsw_type; +extern const struct device_type fsl_mc_bus_dpbp_type; +extern const struct device_type fsl_mc_bus_dpcon_type; +extern const struct device_type fsl_mc_bus_dpmcp_type; +extern const struct device_type fsl_mc_bus_dpmac_type; +extern const struct device_type fsl_mc_bus_dprtc_type; +extern const struct device_type fsl_mc_bus_dpseci_type; +extern const struct device_type fsl_mc_bus_dpdmux_type; +extern const struct device_type fsl_mc_bus_dpdcei_type; +extern const struct device_type fsl_mc_bus_dpaiop_type; +extern const struct device_type fsl_mc_bus_dpci_type; +extern const struct device_type fsl_mc_bus_dpdmai_type; static inline bool is_fsl_mc_bus_dprc(const struct fsl_mc_device *mc_dev) { diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 278620e063ab..1a9ef8f6784d 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -108,38 +108,35 @@ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } +static inline int fsnotify_path(const struct path *path, __u32 mask) +{ + return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); +} + static inline int fsnotify_file(struct file *file, __u32 mask) { - const struct path *path; - /* * FMODE_NONOTIFY are fds generated by fanotify itself which should not * generate new events. We also don't want to generate events for * FMODE_PATH fds (involves open & close events) as they are just * handle creation / destruction events and not "real" file events. */ - if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH)) + if (FMODE_FSNOTIFY_NONE(file->f_mode)) return 0; - path = &file->f_path; - /* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */ - if (mask & ALL_FSNOTIFY_PERM_EVENTS && - !fsnotify_sb_has_priority_watchers(path->dentry->d_sb, - FSNOTIFY_PRIO_CONTENT)) - return 0; - - return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); + return fsnotify_path(&file->f_path, mask); } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + +void file_set_fsnotify_mode(struct file *file); + /* * fsnotify_file_area_perm - permission hook before access to file range */ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { - __u32 fsnotify_mask = FS_ACCESS_PERM; - /* * filesystem may be modified in the context of permission events * (e.g. by HSM filling a file on access), so sb freeze protection @@ -147,14 +144,49 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, */ lockdep_assert_once(file_write_not_started(file)); + if (!(perm_mask & (MAY_READ | MAY_WRITE | MAY_ACCESS))) + return 0; + + if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode))) + return 0; + + /* + * read()/write() and other types of access generate pre-content events. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + int ret = fsnotify_pre_content(&file->f_path, ppos, count); + + if (ret) + return ret; + } + if (!(perm_mask & MAY_READ)) return 0; - return fsnotify_file(file, fsnotify_mask); + /* + * read() also generates the legacy FS_ACCESS_PERM event, so content + * scanners can inspect the content filled by pre-content event. + */ + return fsnotify_path(&file->f_path, FS_ACCESS_PERM); } /* - * fsnotify_file_perm - permission hook before file access + * fsnotify_truncate_perm - permission hook before file truncate + */ +static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) +{ + struct inode *inode = d_inode(path->dentry); + + if (!(inode->i_sb->s_iflags & SB_I_ALLOW_HSM) || + !fsnotify_sb_has_priority_watchers(inode->i_sb, + FSNOTIFY_PRIO_PRE_CONTENT)) + return 0; + + return fsnotify_pre_content(path, &length, 0); +} + +/* + * fsnotify_file_perm - permission hook before file access (unknown range) */ static inline int fsnotify_file_perm(struct file *file, int perm_mask) { @@ -168,22 +200,34 @@ static inline int fsnotify_open_perm(struct file *file) { int ret; + if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode))) + return 0; + if (file->f_flags & __FMODE_EXEC) { - ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); + ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM); if (ret) return ret; } - return fsnotify_file(file, FS_OPEN_PERM); + return fsnotify_path(&file->f_path, FS_OPEN_PERM); } #else +static inline void file_set_fsnotify_mode(struct file *file) +{ +} + static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { return 0; } +static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) +{ + return 0; +} + static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return 0; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3ecf7768e577..0d24a21a8e60 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -55,6 +55,9 @@ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ +/* #define FS_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */ + +#define FS_PRE_ACCESS 0x00100000 /* Pre-content access hook */ /* * Set on inode mark that cares about things that happen to its children. @@ -77,8 +80,14 @@ */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) -#define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ - FS_OPEN_EXEC_PERM) +/* Content events can be used to inspect file content */ +#define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \ + FS_ACCESS_PERM) +/* Pre-content events can be used to fill file content */ +#define FSNOTIFY_PRE_CONTENT_EVENTS (FS_PRE_ACCESS) + +#define ALL_FSNOTIFY_PERM_EVENTS (FSNOTIFY_CONTENT_PERM_EVENTS | \ + FSNOTIFY_PRE_CONTENT_EVENTS) /* * This is a list of all events that may get sent to a parent that is watching @@ -285,6 +294,7 @@ static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, + FSNOTIFY_EVENT_FILE_RANGE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, @@ -297,6 +307,17 @@ struct fs_error_report { struct super_block *sb; }; +struct file_range { + const struct path *path; + loff_t pos; + size_t count; +}; + +static inline const struct path *file_range_path(const struct file_range *range) +{ + return range->path; +} + static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { @@ -306,6 +327,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); + case FSNOTIFY_EVENT_FILE_RANGE: + return d_inode(file_range_path(data)->dentry); case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *)data)->inode; default: @@ -321,6 +344,8 @@ static inline struct dentry *fsnotify_data_dentry(const void *data, int data_typ return (struct dentry *)data; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry; + case FSNOTIFY_EVENT_FILE_RANGE: + return file_range_path(data)->dentry; default: return NULL; } @@ -332,6 +357,8 @@ static inline const struct path *fsnotify_data_path(const void *data, switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; + case FSNOTIFY_EVENT_FILE_RANGE: + return file_range_path(data); default: return NULL; } @@ -347,6 +374,8 @@ static inline struct super_block *fsnotify_data_sb(const void *data, return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; + case FSNOTIFY_EVENT_FILE_RANGE: + return file_range_path(data)->dentry->d_sb; case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *) data)->sb; default: @@ -366,6 +395,18 @@ static inline struct fs_error_report *fsnotify_data_error_report( } } +static inline const struct file_range *fsnotify_data_file_range( + const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_FILE_RANGE: + return (struct file_range *)data; + default: + return NULL; + } +} + /* * Index to merged marks iterator array that correlates to a type of watch. * The type of watched object can be deduced from the iterator type, but not @@ -854,9 +895,17 @@ static inline void fsnotify_init_event(struct fsnotify_event *event) { INIT_LIST_HEAD(&event->list); } +int fsnotify_pre_content(const struct path *path, const loff_t *ppos, + size_t count); #else +static inline int fsnotify_pre_content(const struct path *path, + const loff_t *ppos, size_t count) +{ + return 0; +} + static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index aa9ddd1e4bb6..fbabc3d848b3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -43,9 +43,8 @@ struct dyn_ftrace; char *arch_ftrace_match_adjust(char *str, const char *search); -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL -struct fgraph_ret_regs; -unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs); +#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS +unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs); #else unsigned long ftrace_return_to_handler(unsigned long frame_pointer); #endif @@ -134,6 +133,13 @@ extern int ftrace_enabled; * Also, architecture dependent fields can be used for internal process. * (e.g. orig_ax on x86_64) * + * Basically, ftrace_regs stores the registers related to the context. + * On function entry, registers for function parameters and hooking the + * function call are stored, and on function exit, registers for function + * return value and frame pointers are stored. + * + * And also, it dpends on the context that which registers are restored + * from the ftrace_regs. * On the function entry, those registers will be restored except for * the stack pointer, so that user can change the function parameters * and instruction pointer (e.g. live patching.) @@ -170,6 +176,12 @@ static inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) #define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0) #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ +#ifdef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS + +static_assert(sizeof(struct pt_regs) == ftrace_regs_size()); + +#endif /* CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */ + static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs) { if (!fregs) @@ -178,6 +190,54 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs return arch_ftrace_get_regs(fregs); } +#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) || \ + defined(CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS) + +static __always_inline struct pt_regs * +ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs) +{ + /* + * If CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS=y, ftrace_regs memory + * layout is including pt_regs. So always returns that address. + * Since arch_ftrace_get_regs() will check some members and may return + * NULL, we can not use it. + */ + return &arch_ftrace_regs(fregs)->regs; +} + +#endif /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS || CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */ + +#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS + +/* + * Please define arch dependent pt_regs which compatible to the + * perf_arch_fetch_caller_regs() but based on ftrace_regs. + * This requires + * - user_mode(_regs) returns false (always kernel mode). + * - able to use the _regs for stack trace. + */ +#ifndef arch_ftrace_fill_perf_regs +/* As same as perf_arch_fetch_caller_regs(), do nothing by default */ +#define arch_ftrace_fill_perf_regs(fregs, _regs) do {} while (0) +#endif + +static __always_inline struct pt_regs * +ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs) +{ + arch_ftrace_fill_perf_regs(fregs, regs); + return regs; +} + +#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ + +static __always_inline struct pt_regs * +ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs) +{ + return &arch_ftrace_regs(fregs)->regs; +} + +#endif + /* * When true, the ftrace_regs_{get,set}_*() functions may be used on fregs. * Note: this can be true even when ftrace_get_regs() cannot provide a pt_regs. @@ -190,6 +250,23 @@ static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs) return ftrace_get_regs(fregs) != NULL; } +#ifdef CONFIG_HAVE_REGS_AND_STACK_ACCESS_API +static __always_inline unsigned long +ftrace_regs_get_kernel_stack_nth(struct ftrace_regs *fregs, unsigned int nth) +{ + unsigned long *stackp; + + stackp = (unsigned long *)ftrace_regs_get_stack_pointer(fregs); + if (((unsigned long)(stackp + nth) & ~(THREAD_SIZE - 1)) == + ((unsigned long)stackp & ~(THREAD_SIZE - 1))) + return *(stackp + nth); + + return 0; +} +#else /* !CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */ +#define ftrace_regs_get_kernel_stack_nth(fregs, nth) (0L) +#endif /* CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */ + typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); @@ -545,6 +622,19 @@ enum { FTRACE_MAY_SLEEP = (1 << 5), }; +/* Arches can override ftrace_get_symaddr() to convert fentry_ip to symaddr. */ +#ifndef ftrace_get_symaddr +/** + * ftrace_get_symaddr - return the symbol address from fentry_ip + * @fentry_ip: the address of ftrace location + * + * Get the symbol address from @fentry_ip (fast path). If there is no fast + * search path, this returns 0. + * User may need to use kallsyms API to find the symbol address. + */ +#define ftrace_get_symaddr(fentry_ip) (0) +#endif + #ifdef CONFIG_DYNAMIC_FTRACE void ftrace_arch_code_modify_prepare(void); @@ -1061,20 +1151,21 @@ struct ftrace_graph_ret { int depth; /* Number of functions that overran the depth limit for current task */ unsigned int overrun; - unsigned long long calltime; - unsigned long long rettime; } __packed; struct fgraph_ops; /* Type of the callback handlers for tracing function graph*/ typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *, - struct fgraph_ops *); /* return */ + struct fgraph_ops *, + struct ftrace_regs *); /* return */ typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *, - struct fgraph_ops *); /* entry */ + struct fgraph_ops *, + struct ftrace_regs *); /* entry */ extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops); + struct fgraph_ops *gops, + struct ftrace_regs *fregs); bool ftrace_pids_enabled(struct ftrace_ops *ops); #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -1114,8 +1205,15 @@ struct ftrace_ret_stack { extern void return_to_handler(void); extern int -function_graph_enter(unsigned long ret, unsigned long func, - unsigned long frame_pointer, unsigned long *retp); +function_graph_enter_regs(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp, + struct ftrace_regs *fregs); + +static inline int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long fp, unsigned long *retp) +{ + return function_graph_enter_regs(ret, func, fp, retp, NULL); +} struct ftrace_ret_stack * ftrace_graph_get_ret_stack(struct task_struct *task, int skip); diff --git a/include/linux/ftrace_regs.h b/include/linux/ftrace_regs.h index be1ed0c891d0..bbc1873ca6b8 100644 --- a/include/linux/ftrace_regs.h +++ b/include/linux/ftrace_regs.h @@ -30,6 +30,8 @@ struct ftrace_regs; override_function_with_return(&arch_ftrace_regs(fregs)->regs) #define ftrace_regs_query_register_offset(name) \ regs_query_register_offset(name) +#define ftrace_regs_get_frame_pointer(fregs) \ + frame_pointer(&arch_ftrace_regs(fregs)->regs) #endif /* HAVE_ARCH_FTRACE_REGS */ diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 0d79070c5a70..0731994b9d7c 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -112,6 +112,7 @@ struct fwnode_reference_args { * @device_is_available: Return true if the device is available. * @device_get_match_data: Return the device driver match data. * @property_present: Return true if a property is present. + * @property_read_bool: Return a boolean property value. * @property_read_int_array: Read an array of integer properties. Return zero on * success, a negative error code otherwise. * @property_read_string_array: Read an array of string properties. Return zero @@ -141,6 +142,8 @@ struct fwnode_operations { (*device_get_dma_attr)(const struct fwnode_handle *fwnode); bool (*property_present)(const struct fwnode_handle *fwnode, const char *propname); + bool (*property_read_bool)(const struct fwnode_handle *fwnode, + const char *propname); int (*property_read_int_array)(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, diff --git a/include/linux/gfp.h b/include/linux/gfp.h index b0fe9f62d15b..6bb1a5a7a4ae 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -212,35 +212,31 @@ struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, - struct list_head *page_list, struct page **page_array); #define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) -unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, +unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); -#define alloc_pages_bulk_array_mempolicy(...) \ - alloc_hooks(alloc_pages_bulk_array_mempolicy_noprof(__VA_ARGS__)) +#define alloc_pages_bulk_mempolicy(...) \ + alloc_hooks(alloc_pages_bulk_mempolicy_noprof(__VA_ARGS__)) /* Bulk allocate order-0 pages */ -#define alloc_pages_bulk_list(_gfp, _nr_pages, _list) \ - __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _list, NULL) - -#define alloc_pages_bulk_array(_gfp, _nr_pages, _page_array) \ - __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, NULL, _page_array) +#define alloc_pages_bulk(_gfp, _nr_pages, _page_array) \ + __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _page_array) static inline unsigned long -alloc_pages_bulk_array_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, +alloc_pages_bulk_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, NULL, page_array); + return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, page_array); } -#define alloc_pages_bulk_array_node(...) \ - alloc_hooks(alloc_pages_bulk_array_node_noprof(__VA_ARGS__)) +#define alloc_pages_bulk_node(...) \ + alloc_hooks(alloc_pages_bulk_node_noprof(__VA_ARGS__)) static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { @@ -300,8 +296,6 @@ static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); -struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, - struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); @@ -312,11 +306,6 @@ static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order { return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } -static inline struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, - struct mempolicy *mpol, pgoff_t ilx, int nid) -{ - return alloc_pages_noprof(gfp, order); -} static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node_noprof(gfp, order, numa_node_id()); @@ -331,7 +320,6 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde #endif #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) -#define alloc_pages_mpol(...) alloc_hooks(alloc_pages_mpol_noprof(__VA_ARGS__)) #define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) #define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__)) #define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 455f855bc084..96bda41d9148 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -445,7 +445,6 @@ ssize_t hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer, size_t size); ssize_t hdmi_infoframe_pack_only(const union hdmi_infoframe *frame, void *buffer, size_t size); -int hdmi_infoframe_check(union hdmi_infoframe *frame); int hdmi_infoframe_unpack(union hdmi_infoframe *frame, const void *buffer, size_t size); void hdmi_infoframe_log(const char *level, struct device *dev, diff --git a/include/linux/hid-over-i2c.h b/include/linux/hid-over-i2c.h new file mode 100644 index 000000000000..3b1a0208a6b8 --- /dev/null +++ b/include/linux/hid-over-i2c.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright 2024 Intel Corporation */ + +#include + +#ifndef _HID_OVER_I2C_H_ +#define _HID_OVER_I2C_H_ + +#define HIDI2C_REG_LEN sizeof(__le16) + +/* Input report type definition in HIDI2C protocol */ +enum hidi2c_report_type { + HIDI2C_RESERVED = 0, + HIDI2C_INPUT, + HIDI2C_OUTPUT, + HIDI2C_FEATURE, +}; + +/* Power state type definition in HIDI2C protocol */ +enum hidi2c_power_state { + HIDI2C_ON, + HIDI2C_SLEEP, +}; + +/* Opcode type definition in HIDI2C protocol */ +enum hidi2c_opcode { + HIDI2C_RESET = 1, + HIDI2C_GET_REPORT, + HIDI2C_SET_REPORT, + HIDI2C_GET_IDLE, + HIDI2C_SET_IDLE, + HIDI2C_GET_PROTOCOL, + HIDI2C_SET_PROTOCOL, + HIDI2C_SET_POWER, +}; + +/** + * struct hidi2c_report_packet - Report packet definition in HIDI2C protocol + * @len: data field length + * @data: HIDI2C report packet data + */ +struct hidi2c_report_packet { + __le16 len; + u8 data[]; +} __packed; + +#define HIDI2C_LENGTH_LEN sizeof(__le16) + +#define HIDI2C_PACKET_LEN(data_len) ((data_len) + HIDI2C_LENGTH_LEN) +#define HIDI2C_DATA_LEN(pkt_len) ((pkt_len) - HIDI2C_LENGTH_LEN) + +#define HIDI2C_CMD_MAX_RI 0x0F + +/** + * HIDI2C command data packet - Command packet definition in HIDI2C protocol + * @report_id: [0:3] report id (<15) for features or output reports + * @report_type: [4:5] indicate report type, reference to hidi2c_report_type + * @reserved0: [6:7] reserved bits + * @opcode: [8:11] command operation code, reference to hidi2c_opcode + * @reserved1: [12:15] reserved bits + * @report_id_optional: [23:16] appended 3rd byte. + * If the report_id in the low byte is set to the + * sentinel value (HIDI2C_CMD_MAX_RI), then this + * optional third byte represents the report id (>=15) + * Otherwise, not this 3rd byte. + */ + +#define HIDI2C_CMD_LEN sizeof(__le16) +#define HIDI2C_CMD_LEN_OPT (sizeof(__le16) + 1) +#define HIDI2C_CMD_REPORT_ID GENMASK(3, 0) +#define HIDI2C_CMD_REPORT_TYPE GENMASK(5, 4) +#define HIDI2C_CMD_OPCODE GENMASK(11, 8) +#define HIDI2C_CMD_OPCODE GENMASK(11, 8) +#define HIDI2C_CMD_3RD_BYTE GENMASK(23, 16) + +#define HIDI2C_HID_DESC_BCDVERSION 0x100 + +/** + * struct hidi2c_dev_descriptor - HIDI2C device descriptor definition + * @dev_desc_len: The length of the complete device descriptor, fixed to 0x1E (30). + * @bcd_ver: The version number of the HIDI2C protocol supported. + * In binary coded decimal (BCD) format. + * @report_desc_len: The length of the report descriptor + * @report_desc_reg: The register address to retrieve report descriptor + * @input_reg: the register address to retrieve input report + * @max_input_len: The length of the largest possible HID input (or feature) report + * @output_reg: the register address to send output report + * @max_output_len: The length of the largest output (or feature) report + * @cmd_reg: the register address to send command + * @data_reg: the register address to send command data + * @vendor_id: Device manufacturers vendor ID + * @product_id: Device unique model/product ID + * @version_id: Device’s unique version + * @reserved0: Reserved and should be 0 + * @reserved1: Reserved and should be 0 + */ +struct hidi2c_dev_descriptor { + __le16 dev_desc_len; + __le16 bcd_ver; + __le16 report_desc_len; + __le16 report_desc_reg; + __le16 input_reg; + __le16 max_input_len; + __le16 output_reg; + __le16 max_output_len; + __le16 cmd_reg; + __le16 data_reg; + __le16 vendor_id; + __le16 product_id; + __le16 version_id; + __le16 reserved0; + __le16 reserved1; +} __packed; + +#define HIDI2C_DEV_DESC_LEN sizeof(struct hidi2c_dev_descriptor) + +#endif /* _HID_OVER_I2C_H_ */ diff --git a/include/linux/hid-over-spi.h b/include/linux/hid-over-spi.h new file mode 100644 index 000000000000..da5a14b5e89b --- /dev/null +++ b/include/linux/hid-over-spi.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright 2024 Intel Corporation */ + +#ifndef _HID_OVER_SPI_H_ +#define _HID_OVER_SPI_H_ + +#include +#include + +/* Input report type definition in HIDSPI protocol */ +enum input_report_type { + INVALID_INPUT_REPORT_TYPE_0 = 0, + DATA = 1, + INVALID_TYPE_2 = 2, + RESET_RESPONSE = 3, + COMMAND_RESPONSE = 4, + GET_FEATURE_RESPONSE = 5, + INVALID_TYPE_6 = 6, + DEVICE_DESCRIPTOR_RESPONSE = 7, + REPORT_DESCRIPTOR_RESPONSE = 8, + SET_FEATURE_RESPONSE = 9, + OUTPUT_REPORT_RESPONSE = 10, + GET_INPUT_REPORT_RESPONSE = 11, + INVALID_INPUT_REPORT_TYPE = 0xF, +}; + +/* Output report type definition in HIDSPI protocol */ +enum output_report_type { + INVALID_OUTPUT_REPORT_TYPE_0 = 0, + DEVICE_DESCRIPTOR = 1, + REPORT_DESCRIPTOR = 2, + SET_FEATURE = 3, + GET_FEATURE = 4, + OUTPUT_REPORT = 5, + GET_INPUT_REPORT = 6, + COMMAND_CONTENT = 7, +}; + +/* Set power command ID for output report */ +#define HIDSPI_SET_POWER_CMD_ID 1 + +/* Power state definition in HIDSPI protocol */ +enum hidspi_power_state { + HIDSPI_ON = 1, + HIDSPI_SLEEP = 2, + HIDSPI_OFF = 3, +}; + +/** + * Input report header definition in HIDSPI protocol + * Report header size is 32bits, it includes: + * protocol_ver: [0:3] Current supported HIDSPI protocol version, must be 0x3 + * reserved0: [4:7] Reserved bits + * input_report_len: [8:21] Input report length in number bytes divided by 4 + * last_frag_flag: [22]Indicate if this packet is last fragment. + * 1 - indicates last fragment + * 0 - indicates additional fragments + * reserved1: [23] Reserved bits + * @sync_const: [24:31] Used to validate input report header, must be 0x5A + */ +#define HIDSPI_INPUT_HEADER_SIZE sizeof(u32) +#define HIDSPI_INPUT_HEADER_VER GENMASK(3, 0) +#define HIDSPI_INPUT_HEADER_REPORT_LEN GENMASK(21, 8) +#define HIDSPI_INPUT_HEADER_LAST_FLAG BIT(22) +#define HIDSPI_INPUT_HEADER_SYNC GENMASK(31, 24) + +/** + * struct input_report_body_header - Input report body header definition in HIDSPI protocol + * @input_report_type: indicate input report type, reference to enum input_report_type + * @content_len: this input report body packet length + * @content_id: indicate this input report's report id + */ +struct input_report_body_header { + u8 input_report_type; + __le16 content_len; + u8 content_id; +} __packed; + +#define HIDSPI_INPUT_BODY_HEADER_SIZE sizeof(struct input_report_body_header) + +/** + * struct input_report_body - Input report body definition in HIDSPI protocol + * @body_hdr: input report body header + * @content: input report body content + */ +struct input_report_body { + struct input_report_body_header body_hdr; + u8 content[]; +} __packed; + +#define HIDSPI_INPUT_BODY_SIZE(content_len) ((content_len) + HIDSPI_INPUT_BODY_HEADER_SIZE) + +/** + * struct output_report_header - Output report header definition in HIDSPI protocol + * @report_type: output report type, reference to enum output_report_type + * @content_len: length of content + * @content_id: 0x00 - descriptors + * report id - Set/Feature feature or Input/Output Reports + * command opcode - for commands + */ +struct output_report_header { + u8 report_type; + __le16 content_len; + u8 content_id; +} __packed; + +#define HIDSPI_OUTPUT_REPORT_HEADER_SIZE sizeof(struct output_report_header) + +/** + * struct output_report - Output report definition in HIDSPI protocol + * @output_hdr: output report header + * @content: output report content + */ +struct output_report { + struct output_report_header output_hdr; + u8 content[]; +} __packed; + +#define HIDSPI_OUTPUT_REPORT_SIZE(content_len) ((content_len) + HIDSPI_OUTPUT_REPORT_HEADER_SIZE) + +/** + * struct hidspi_dev_descriptor - HIDSPI device descriptor definition + * @dev_desc_len: The length of the complete device descriptor, fixed to 0x18 (24). + * @bcd_ver: The version number of the HIDSPI protocol supported. + * In binary coded decimal (BCD) format. Must be fixed to 0x0300. + * @rep_desc_len: The length of the report descriptor + * @max_input_len: The length of the largest possible HID input (or feature) report + * @max_output_len: The length of the largest output (or feature) report + * @max_frag_len: The length of the largest fragment, where a fragment represents + * the body of an input report. + * @vendor_id: Device manufacturers vendor ID + * @product_id: Device unique model/product ID + * @version_id: Device’s unique version + * @flags: Specify flags for the device’s operation + * @reserved: Reserved and should be 0 + */ +struct hidspi_dev_descriptor { + __le16 dev_desc_len; + __le16 bcd_ver; + __le16 rep_desc_len; + __le16 max_input_len; + __le16 max_output_len; + __le16 max_frag_len; + __le16 vendor_id; + __le16 product_id; + __le16 version_id; + __le16 flags; + __le32 reserved; +}; + +#define HIDSPI_DEVICE_DESCRIPTOR_SIZE sizeof(struct hidspi_dev_descriptor) +#define HIDSPI_INPUT_DEVICE_DESCRIPTOR_SIZE \ + (HIDSPI_INPUT_BODY_HEADER_SIZE + HIDSPI_DEVICE_DESCRIPTOR_SIZE) + +#endif /* _HID_OVER_SPI_H_ */ diff --git a/include/linux/hid.h b/include/linux/hid.h index d11e9c9a5f15..cdc0dc13c87f 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -218,6 +218,7 @@ struct hid_item { #define HID_GD_DOWN 0x00010091 #define HID_GD_RIGHT 0x00010092 #define HID_GD_LEFT 0x00010093 +#define HID_GD_DO_NOT_DISTURB 0x0001009b /* Microsoft Win8 Wireless Radio Controls CA usage codes */ #define HID_GD_RFKILL_BTN 0x000100c6 #define HID_GD_RFKILL_LED 0x000100c7 diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 6e452bd8e7e3..5c6bea81a90e 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -224,7 +224,13 @@ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { - return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr); + struct folio *folio; + + folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr); + if (folio && user_alloc_needs_zeroing()) + clear_user_highpage(&folio->page, vaddr); + + return folio; } #endif diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 6dbd0d49628f..99fcf65d575f 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -97,6 +97,8 @@ /* page number for queue file region */ #define QM_DOORBELL_PAGE_NR 1 +#define QM_DEV_ALG_MAX_LEN 256 + /* uacce mode of the driver */ #define UACCE_MODE_NOUACCE 0 /* don't use uacce */ #define UACCE_MODE_SVA 1 /* use uacce sva mode */ @@ -122,6 +124,7 @@ enum qm_hw_ver { QM_HW_V1 = 0x20, QM_HW_V2 = 0x21, QM_HW_V3 = 0x30, + QM_HW_V4 = 0x50, }; enum qm_fun_type { @@ -156,6 +159,7 @@ enum qm_cap_bits { QM_SUPPORT_MB_COMMAND, QM_SUPPORT_SVA_PREFETCH, QM_SUPPORT_RPM, + QM_SUPPORT_DAE, }; struct qm_dev_alg { @@ -266,6 +270,8 @@ struct hisi_qm_err_ini { void (*show_last_dfx_regs)(struct hisi_qm *qm); void (*err_info_init)(struct hisi_qm *qm); enum acc_err_result (*get_err_result)(struct hisi_qm *qm); + bool (*dev_is_abnormal)(struct hisi_qm *qm); + int (*set_priv_status)(struct hisi_qm *qm); }; struct hisi_qm_cap_info { @@ -392,6 +398,8 @@ struct hisi_qm { struct mutex mailbox_lock; + struct mutex ifc_lock; + const struct hisi_qm_hw_ops *ops; struct qm_debug debug; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 7ef5f7ef31a9..f7bfdcf0dda3 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -386,6 +386,7 @@ extern void __init hrtimers_init(void); extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); +int hrtimers_cpu_starting(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU int hrtimers_cpu_dying(unsigned int cpu); #else diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b94c2e8ee918..93e509b6c00e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -121,6 +121,8 @@ enum mthp_stat_item { MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, MTHP_STAT_ZSWPOUT, MTHP_STAT_SWPIN, + MTHP_STAT_SWPIN_FALLBACK, + MTHP_STAT_SWPIN_FALLBACK_CHARGE, MTHP_STAT_SWPOUT, MTHP_STAT_SWPOUT_FALLBACK, MTHP_STAT_SHMEM_ALLOC, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ae4fe8615bb6..ec8c0ccc8f95 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -153,11 +153,11 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -bool isolate_hugetlb(struct folio *folio, struct list_head *list); +bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); -void folio_putback_active_hugetlb(struct folio *folio); +void folio_putback_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; @@ -414,7 +414,7 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return NULL; } -static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list) +static inline bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list) { return false; } @@ -430,7 +430,7 @@ static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, return 0; } -static inline void folio_putback_active_hugetlb(struct folio *folio) +static inline void folio_putback_hugetlb(struct folio *folio) { } @@ -681,8 +681,9 @@ struct huge_bootmem_page { }; int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); +int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, - unsigned long addr, int avoid_reserve); + unsigned long addr, bool cow_from_owner); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); @@ -1059,9 +1060,15 @@ static inline int isolate_or_dissolve_huge_page(struct page *page, return -ENOMEM; } +static inline int replace_free_hugepage_folios(unsigned long start_pfn, + unsigned long end_pfn) +{ + return 0; +} + static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, - int avoid_reserve) + bool cow_from_owner) { return NULL; } diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 22c22fb91042..4179add2864b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -24,7 +24,7 @@ #include #include #include -#include +#include #define MAX_PAGE_BUFFER_COUNT 32 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ @@ -768,15 +768,6 @@ struct vmbus_close_msg { struct vmbus_channel_close_channel msg; }; -/* Define connection identifier type. */ -union hv_connection_id { - u32 asu32; - struct { - u32 id:24; - u32 reserved:8; - } u; -}; - enum vmbus_device_type { HV_IDE = 0, HV_SCSI, @@ -1559,6 +1550,7 @@ struct hv_util_service { void *channel; void (*util_cb)(void *); int (*util_init)(struct hv_util_service *); + int (*util_init_transport)(void); void (*util_deinit)(void); int (*util_pre_suspend)(void); int (*util_pre_resume)(void); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 388ce71a29a9..c31fd1dba3bd 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -244,7 +244,6 @@ enum i2c_driver_flags { * @id_table: List of I2C devices supported by this driver * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) - * @clients: List of detected clients we created (for i2c-core use only) * @flags: A bitmask of flags defined in &enum i2c_driver_flags * * The driver.owner field should be set to the module owner of this driver. @@ -299,7 +298,6 @@ struct i2c_driver { /* Device detection callback for automatic device creation */ int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; - struct list_head clients; u32 flags; }; @@ -315,12 +313,12 @@ struct i2c_driver { * @dev: Driver model device node for the slave. * @init_irq: IRQ that was set at initialization * @irq: indicates the IRQ generated by this device (if any) - * @detected: member of an i2c_driver.clients list or i2c-core's - * userspace_devices list * @slave_cb: Callback when I2C slave mode of an adapter is used. The adapter * calls it to pass on slave events to the slave driver. * @devres_group_id: id of the devres group that will be created for resources * acquired when probing this device. + * @debugfs: pointer to the debugfs subdirectory which the I2C core created + * for this client. * * An i2c_client identifies a single device (i.e. chip) connected to an * i2c bus. The behaviour exposed to Linux is defined by the driver @@ -334,6 +332,8 @@ struct i2c_client { #define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ #define I2C_CLIENT_HOST_NOTIFY 0x40 /* We want to use I2C host notify */ #define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ +#define I2C_CLIENT_AUTO 0x100 /* client was auto-detected */ +#define I2C_CLIENT_USER 0x200 /* client was userspace-created */ #define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ /* Must match I2C_M_STOP|IGNORE_NAK */ @@ -345,11 +345,11 @@ struct i2c_client { struct device dev; /* the device structure */ int init_irq; /* irq set at initialization */ int irq; /* irq issued by device */ - struct list_head detected; #if IS_ENABLED(CONFIG_I2C_SLAVE) i2c_slave_cb_t slave_cb; /* callback for slave mode */ #endif void *devres_group_id; /* ID of probe devres group */ + struct dentry *debugfs; /* per-client debugfs dir */ }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) @@ -751,9 +751,6 @@ struct i2c_adapter { char name[48]; struct completion dev_released; - struct mutex userspace_clients_lock; - struct list_head userspace_clients; - struct i2c_bus_recovery_info *bus_recovery_info; const struct i2c_adapter_quirks *quirks; diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index 0a8a44ac2f02..b674f64d0822 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -283,7 +283,7 @@ static inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv, * module_i3c_i2c_driver() - Register a module providing an I3C and an I2C * driver * @__i3cdrv: the I3C driver to register - * @__i2cdrv: the I3C driver to register + * @__i2cdrv: the I2C driver to register * * Provide generic init/exit functions that simply register/unregister an I3C * and an I2C driver. diff --git a/include/linux/i8042.h b/include/linux/i8042.h index 95b07f8b77fe..00037c13abc8 100644 --- a/include/linux/i8042.h +++ b/include/linux/i8042.h @@ -54,15 +54,29 @@ struct serio; +/** + * typedef i8042_filter_t - i8042 filter callback + * @data: Data received by the i8042 controller + * @str: Status register of the i8042 controller + * @serio: Serio of the i8042 controller + * @context: Context pointer associated with this callback + * + * This represents a i8042 filter callback which can be used with i8042_install_filter() + * and i8042_remove_filter() to filter the i8042 input for platform-specific key codes. + * + * Context: Interrupt context. + * Returns: true if the data should be filtered out, false if otherwise. + */ +typedef bool (*i8042_filter_t)(unsigned char data, unsigned char str, struct serio *serio, + void *context); + #if defined(CONFIG_SERIO_I8042) || defined(CONFIG_SERIO_I8042_MODULE) void i8042_lock_chip(void); void i8042_unlock_chip(void); int i8042_command(unsigned char *param, int command); -int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *serio)); -int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *serio)); +int i8042_install_filter(i8042_filter_t filter, void *context); +int i8042_remove_filter(i8042_filter_t filter); #else @@ -79,14 +93,12 @@ static inline int i8042_command(unsigned char *param, int command) return -ENODEV; } -static inline int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *serio)) +static inline int i8042_install_filter(i8042_filter_t filter, void *context) { return -ENODEV; } -static inline int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *serio)) +static inline int i8042_remove_filter(i8042_filter_t filter) { return -ENODEV; } diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 05dedc45505c..16741e542e81 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1532,6 +1532,17 @@ struct ieee80211_mgmt { struct { u8 action_code; } __packed ttlm_tear_down; + struct { + u8 action_code; + u8 dialog_token; + u8 variable[]; + } __packed ml_reconf_req; + struct { + u8 action_code; + u8 dialog_token; + u8 count; + u8 variable[]; + } __packed ml_reconf_resp; } u; } __packed action; DECLARE_FLEX_ARRAY(u8, body); /* Generic frame body */ @@ -1542,11 +1553,13 @@ struct ieee80211_mgmt { #define BSS_MEMBERSHIP_SELECTOR_HT_PHY 127 #define BSS_MEMBERSHIP_SELECTOR_VHT_PHY 126 #define BSS_MEMBERSHIP_SELECTOR_GLK 125 -#define BSS_MEMBERSHIP_SELECTOR_EPS 124 +#define BSS_MEMBERSHIP_SELECTOR_EPD 124 #define BSS_MEMBERSHIP_SELECTOR_SAE_H2E 123 #define BSS_MEMBERSHIP_SELECTOR_HE_PHY 122 #define BSS_MEMBERSHIP_SELECTOR_EHT_PHY 121 +#define BSS_MEMBERSHIP_SELECTOR_MIN BSS_MEMBERSHIP_SELECTOR_EHT_PHY + /* mgmt header + 1 byte category code */ #define IEEE80211_MIN_ACTION_SIZE offsetof(struct ieee80211_mgmt, u.action.u) @@ -3883,6 +3896,16 @@ enum ieee80211_protected_eht_actioncode { WLAN_PROTECTED_EHT_ACTION_TTLM_REQ = 0, WLAN_PROTECTED_EHT_ACTION_TTLM_RES = 1, WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN = 2, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_REQ = 3, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP = 4, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN = 5, + WLAN_PROTECTED_EHT_ACTION_EML_OP_MODE_NOTIF = 6, + WLAN_PROTECTED_EHT_ACTION_LINK_RECOMMEND = 7, + WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_REQ = 8, + WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_RESP = 9, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_NOTIF = 10, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_REQ = 11, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP = 12, }; /* Security key length */ @@ -4961,6 +4984,7 @@ struct ieee80211_multi_link_elem { #define IEEE80211_MLC_BASIC_PRES_EML_CAPA 0x0080 #define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP 0x0100 #define IEEE80211_MLC_BASIC_PRES_MLD_ID 0x0200 +#define IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP 0x0400 #define IEEE80211_MED_SYNC_DELAY_DURATION 0x00ff #define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH 0x0f00 @@ -5018,6 +5042,8 @@ struct ieee80211_multi_link_elem { #define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_DIFF 3 #define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 #define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 +#define IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT 0x2000 +#define IEEE80211_MLD_CAP_OP_ALIGNED_TWT_SUPPORT 0x4000 struct ieee80211_mle_basic_common_info { u8 len; @@ -5033,6 +5059,9 @@ struct ieee80211_mle_preq_common_info { } __packed; #define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR 0x0010 +#define IEEE80211_MLC_RECONF_PRES_EML_CAPA 0x0020 +#define IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP 0x0040 +#define IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP 0x0080 /* no fixed fields in RECONF */ @@ -5055,28 +5084,24 @@ static inline u8 ieee80211_mle_common_size(const u8 *data) { const struct ieee80211_multi_link_elem *mle = (const void *)data; u16 control = le16_to_cpu(mle->control); - u8 common = 0; switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { case IEEE80211_ML_CONTROL_TYPE_BASIC: case IEEE80211_ML_CONTROL_TYPE_PREQ: case IEEE80211_ML_CONTROL_TYPE_TDLS: case IEEE80211_ML_CONTROL_TYPE_RECONF: + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: /* * The length is the first octet pointed by mle->variable so no * need to add anything */ break; - case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) - common += ETH_ALEN; - return common; default: WARN_ON(1); return 0; } - return sizeof(*mle) + common + mle->variable[0]; + return sizeof(*mle) + mle->variable[0]; } /** @@ -5226,6 +5251,47 @@ static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) return get_unaligned_le16(common); } +/** + * ieee80211_mle_get_ext_mld_capa_op - returns the extended MLD capabilities + * and operations. + * @data: pointer to the multi-link element + * Return: the extended MLD capabilities and operations field value from + * the multi-link element, or 0 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_ext_mld_capa_op(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) + common += 1; + + return get_unaligned_le16(common); +} + /** * ieee80211_mle_get_mld_id - returns the MLD ID * @data: pointer to the multi-link element @@ -5298,6 +5364,8 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) common += 2; if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP) + common += 2; break; case IEEE80211_ML_CONTROL_TYPE_PREQ: common += sizeof(struct ieee80211_mle_preq_common_info); @@ -5308,14 +5376,19 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) case IEEE80211_ML_CONTROL_TYPE_RECONF: if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) common += ETH_ALEN; + if (control & IEEE80211_MLC_RECONF_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP) + common += 2; break; case IEEE80211_ML_CONTROL_TYPE_TDLS: common += sizeof(struct ieee80211_mle_tdls_common_info); check_common_len = true; break; case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) - common += ETH_ALEN; + common = ETH_ALEN + 1; break; default: /* we don't know this type */ @@ -5458,8 +5531,13 @@ ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta #define IEEE80211_MLE_STA_RECONF_CONTROL_COMPLETE_PROFILE 0x0010 #define IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 #define IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT 0x0040 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_UPDATE_TYPE 0x0780 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT 0x0800 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE 0x0780 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_AP_REM 0 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_OP_PARAM_UPDATE 1 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_ADD_LINK 2 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_DEL_LINK 3 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_NSTR_STATUS 4 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT 0x0800 /** * ieee80211_mle_reconf_sta_prof_size_ok - validate reconfiguration multi-link diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h index 0404f5bf4f30..d7941fd88032 100644 --- a/include/linux/if_hsr.h +++ b/include/linux/if_hsr.h @@ -13,6 +13,15 @@ enum hsr_version { PRP_V1, }; +enum hsr_port_type { + HSR_PT_NONE = 0, /* Must be 0, used by framereg */ + HSR_PT_SLAVE_A, + HSR_PT_SLAVE_B, + HSR_PT_INTERLINK, + HSR_PT_MASTER, + HSR_PT_PORTS, /* This must be the last item in the enum */ +}; + /* HSR Tag. * As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB, * path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest, @@ -32,6 +41,8 @@ struct hsr_tag { #if IS_ENABLED(CONFIG_HSR) extern bool is_hsr_master(struct net_device *dev); extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver); +struct net_device *hsr_get_port_ndev(struct net_device *ndev, + enum hsr_port_type pt); #else static inline bool is_hsr_master(struct net_device *dev) { @@ -42,6 +53,12 @@ static inline int hsr_get_version(struct net_device *dev, { return -EINVAL; } + +static inline struct net_device *hsr_get_port_ndev(struct net_device *ndev, + enum hsr_port_type pt) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_HSR */ #endif /*_LINUX_IF_HSR_H_*/ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index c1645c86eed9..38456b42cdb5 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -176,6 +176,7 @@ struct netpoll; * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats + * @netpoll: netpoll instance "propagated" down to @real_dev */ struct vlan_dev_priv { unsigned int nr_ingress_mappings; @@ -310,7 +311,7 @@ static inline bool vlan_uses_dev(const struct net_device *dev) * eth_type_vlan - check for valid vlan ether type. * @ethertype: ether type to check * - * Returns true if the ether type is a vlan ether type. + * Returns: true if the ether type is a vlan ether type. */ static inline bool eth_type_vlan(__be16 ethertype) { @@ -341,9 +342,9 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features, * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len - * Returns error if skb_cow_head fails. - * * Does not change skb->protocol so this function can be used during receive. + * + * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, @@ -390,9 +391,9 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload - * Returns error if skb_cow_head fails. - * * Does not change skb->protocol so this function can be used during receive. + * + * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) @@ -414,6 +415,8 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. + * + * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, @@ -443,6 +446,8 @@ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. + * + * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) @@ -461,6 +466,8 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. + * + * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, __be16 vlan_proto, @@ -533,7 +540,7 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, * @skb: skbuff to query * @vlan_tci: buffer to store value * - * Returns error if the skb is not of VLAN type + * Returns: error if the skb is not of VLAN type */ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { @@ -551,7 +558,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) * @skb: skbuff to query * @vlan_tci: buffer to store value * - * Returns error if @skb->vlan_tci is not set correctly + * Returns: error if @skb->vlan_tci is not set correctly */ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, u16 *vlan_tci) @@ -570,7 +577,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, * @skb: skbuff to query * @vlan_tci: buffer to store value * - * Returns error if the skb is not VLAN tagged + * Returns: error if the skb is not VLAN tagged */ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { @@ -582,16 +589,19 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) } /** - * vlan_get_protocol - get protocol EtherType. + * __vlan_get_protocol_offset() - get protocol EtherType. * @skb: skbuff to query * @type: first vlan protocol + * @mac_offset: MAC offset * @depth: buffer to store length of eth and vlan tags in bytes * - * Returns the EtherType of the packet, regardless of whether it is + * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, - int *depth) +static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb, + __be16 type, + int mac_offset, + int *depth) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; @@ -610,7 +620,8 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, do { struct vlan_hdr vhdr, *vh; - vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr); + vh = skb_header_pointer(skb, mac_offset + vlan_depth, + sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return 0; @@ -625,11 +636,17 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, return type; } +static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, + int *depth) +{ + return __vlan_get_protocol_offset(skb, type, 0, depth); +} + /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * - * Returns the EtherType of the packet, regardless of whether it is + * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) @@ -710,7 +727,7 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, * Expects the skb to contain a VLAN tag in the payload, and to have skb->data * pointing at the MAC header. * - * Returns a new pointer to skb->data, or NULL on failure to pull. + * Returns: a new pointer to skb->data, or NULL on failure to pull. */ static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) { @@ -727,7 +744,7 @@ static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) * skb_vlan_tagged - check if skb is vlan tagged. * @skb: skbuff to query * - * Returns true if the skb is tagged, regardless of whether it is hardware + * Returns: true if the skb is tagged, regardless of whether it is hardware * accelerated or not. */ static inline bool skb_vlan_tagged(const struct sk_buff *skb) @@ -743,7 +760,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb) * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers. * @skb: skbuff to query * - * Returns true if the skb is tagged with multiple vlan headers, regardless + * Returns: true if the skb is tagged with multiple vlan headers, regardless * of whether it is hardware accelerated or not. */ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) @@ -774,7 +791,7 @@ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) * @skb: skbuff to query * @features: features to be checked * - * Returns features without unsafe ones if the skb has multiple tags. + * Returns: features without unsafe ones if the skb has multiple tags. */ static inline netdev_features_t vlan_features_check(struct sk_buff *skb, netdev_features_t features) @@ -798,9 +815,11 @@ static inline netdev_features_t vlan_features_check(struct sk_buff *skb, * @h1: Pointer to vlan header * @h2: Pointer to vlan header * - * Compare two vlan headers, returns 0 if equal. + * Compare two vlan headers. * * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. + * + * Return: 0 if equal, arbitrary non-zero value if not equal. */ static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, const struct vlan_hdr *h2) diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 5171231f70a8..073b30a9b850 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -87,6 +87,8 @@ struct ip_mc_list { char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; + unsigned long mca_cstamp; + unsigned long mca_tstamp; struct rcu_head rcu; }; diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index f8c1d2505940..417073c52380 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -29,6 +29,7 @@ struct ad_sd_calib_data { struct ad_sigma_delta; struct device; +struct gpio_desc; struct iio_dev; /** @@ -53,6 +54,7 @@ struct iio_dev; * @irq_flags: flags for the interrupt used by the triggered buffer * @num_slots: Number of sequencer slots * @irq_line: IRQ for reading conversions. If 0, spi->irq will be used + * @num_resetclks: Number of SPI clk cycles with MOSI=1 to reset the chip. */ struct ad_sigma_delta_info { int (*set_channel)(struct ad_sigma_delta *, unsigned int channel); @@ -69,6 +71,7 @@ struct ad_sigma_delta_info { unsigned long irq_flags; unsigned int num_slots; int irq_line; + unsigned int num_resetclks; }; /** @@ -85,6 +88,7 @@ struct ad_sigma_delta { /* private: */ struct completion completion; + spinlock_t irq_lock; /* protects .irq_dis and irq en/disable state */ bool irq_dis; bool bus_locked; @@ -96,7 +100,8 @@ struct ad_sigma_delta { unsigned int active_slots; unsigned int current_slot; unsigned int num_slots; - int irq_line; + struct gpio_desc *rdy_gpiod; + int irq_line; bool status_appended; /* map slots to channels in order to know what to expect from devices */ unsigned int *slots; @@ -178,8 +183,7 @@ int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, unsigned int size, unsigned int *val); -int ad_sd_reset(struct ad_sigma_delta *sigma_delta, - unsigned int reset_length); +int ad_sd_reset(struct ad_sigma_delta *sigma_delta); int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, int *val); diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 418b1307d3f2..3b8d618bb3df 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -37,7 +37,7 @@ int iio_pop_from_buffer(struct iio_buffer *buffer, void *data); static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev, void *data, int64_t timestamp) { - if (indio_dev->scan_timestamp) { + if (ACCESS_PRIVATE(indio_dev, scan_timestamp)) { size_t ts_offset = indio_dev->scan_bytes / sizeof(int64_t) - 1; ((int64_t *)data)[ts_offset] = timestamp; } diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 333d1d8ccb37..6a4479616479 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -418,7 +418,7 @@ unsigned int iio_get_channel_ext_info_count(struct iio_channel *chan); * @chan: The channel being queried. * @attr: The ext_info attribute to read. * @buf: Where to store the attribute value. Assumed to hold - * at least PAGE_SIZE bytes. + * at least PAGE_SIZE bytes and to be aligned at PAGE_SIZE. * * Returns the number of bytes written to buf (perhaps w/o zero termination; * it need not even be a string), or an error code. @@ -445,7 +445,7 @@ ssize_t iio_write_channel_ext_info(struct iio_channel *chan, const char *attr, * iio_read_channel_label() - read label for a given channel * @chan: The channel being queried. * @buf: Where to store the attribute value. Assumed to hold - * at least PAGE_SIZE bytes. + * at least PAGE_SIZE bytes and to be aligned at PAGE_SIZE. * * Returns the number of bytes written to buf, or an error code. */ diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h index 9cb6c80dea71..e5de7a124bad 100644 --- a/include/linux/iio/iio-gts-helper.h +++ b/include/linux/iio/iio-gts-helper.h @@ -188,6 +188,9 @@ int iio_gts_total_gain_to_scale(struct iio_gts *gts, int total_gain, int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel, int scale_int, int scale_nano, int *gain_sel); +int iio_gts_find_gain_time_sel_for_scale(struct iio_gts *gts, int scale_int, + int scale_nano, int *gain_sel, + int *time_sel); int iio_gts_get_scale(struct iio_gts *gts, int gain, int time, int *scale_int, int *scale_nano); int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts, @@ -196,6 +199,9 @@ int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts, int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain, int old_time, int new_time, int *new_gain); +int iio_gts_find_new_gain_by_gain_time_min(struct iio_gts *gts, int old_gain, + int old_time, int new_time, + int *new_gain, bool *in_range); int iio_gts_avail_times(struct iio_gts *gts, const int **vals, int *type, int *length); int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type, diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index a89e7e43e441..4247497f3f8b 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -28,7 +28,7 @@ * @groupcounter: index of next attribute group * @legacy_scan_el_group: attribute group for legacy scan elements attribute group * @legacy_buffer_group: attribute group for legacy buffer attributes group - * @bounce_buffer: for devices that call iio_push_to_buffers_with_timestamp_unaligned() + * @bounce_buffer: for devices that call iio_push_to_buffers_with_ts_unaligned() * @bounce_buffer_size: size of currently allocate bounce buffer * @scan_index_timestamp: cache of the index to the timestamp * @clock_id: timestamping clock posix identifier diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index ae65890d4567..56161e02f002 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -611,7 +611,7 @@ struct iio_dev { const unsigned long *available_scan_masks; unsigned int __private masklength; const unsigned long *active_scan_mask; - bool scan_timestamp; + bool __private scan_timestamp; struct iio_trigger *trig; struct iio_poll_func *pollfunc; struct iio_poll_func *pollfunc_event; diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index e6a75356567a..4bb98d9731de 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -99,7 +99,6 @@ struct adis_data { * @spi: Reference to SPI device which owns this ADIS IIO device * @trig: IIO trigger object data * @data: ADIS chip variant specific data - * @burst: ADIS burst transfer information * @burst_extra_len: Burst extra length. Should only be used by devices that can * dynamically change their burst mode length. * @state_lock: Lock used by the device to protect state diff --git a/include/linux/iio/timer/stm32-timer-trigger.h b/include/linux/iio/timer/stm32-timer-trigger.h index 37572e4dc73a..1ee237b56183 100644 --- a/include/linux/iio/timer/stm32-timer-trigger.h +++ b/include/linux/iio/timer/stm32-timer-trigger.h @@ -72,6 +72,12 @@ #define TIM17_OC1 "tim17_oc1" +#define TIM20_OC1 "tim20_oc1" +#define TIM20_OC2 "tim20_oc2" +#define TIM20_OC3 "tim20_oc3" +#define TIM20_TRGO "tim20_trgo" +#define TIM20_TRGO2 "tim20_trgo2" + #if IS_REACHABLE(CONFIG_IIO_STM32_TIMER_TRIGGER) bool is_stm32_timer_trigger(struct iio_trigger *trig); #else diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index bc7babe91b2e..bf675a8aef8a 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -4,14 +4,14 @@ #ifdef CONFIG_NOINSTR_VALIDATION +#include #include /* Begin/end of an instrumentation safe region */ #define __instrumentation_begin(c) ({ \ asm volatile(__stringify(c) ": nop\n\t" \ - ".pushsection .discard.instr_begin\n\t" \ - ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t" : : "i" (c)); \ + ANNOTATE_INSTR_BEGIN(__ASM_BREF(c)) \ + : : "i" (c)); \ }) #define instrumentation_begin() __instrumentation_begin(__COUNTER__) @@ -48,9 +48,8 @@ */ #define __instrumentation_end(c) ({ \ asm volatile(__stringify(c) ": nop\n\t" \ - ".pushsection .discard.instr_end\n\t" \ - ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t" : : "i" (c)); \ + ANNOTATE_INSTR_END(__ASM_BREF(c)) \ + : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) #else /* !CONFIG_NOINSTR_VALIDATION */ diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 771622650247..dfbf7d9d7bb5 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -100,7 +100,6 @@ void ishtp_cl_destroy_connection(struct ishtp_cl *cl, bool reset); int ishtp_cl_send(struct ishtp_cl *cl, uint8_t *buf, size_t length); int ishtp_cl_flush_queues(struct ishtp_cl *cl); int ishtp_cl_io_rb_recycle(struct ishtp_cl_rb *rb); -bool ishtp_cl_tx_empty(struct ishtp_cl *cl); struct ishtp_cl_rb *ishtp_cl_rx_get_rb(struct ishtp_cl *cl); void *ishtp_get_client_data(struct ishtp_cl *cl); void ishtp_set_client_data(struct ishtp_cl *cl, void *data); diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ce86b09ae80f..bba2a51c87d2 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -180,12 +180,22 @@ struct io_pgtable_cfg { }; }; +/** + * struct arm_lpae_io_pgtable_walk_data - information from a pgtable walk + * + * @ptes: The recorded PTE values from the walk + */ +struct arm_lpae_io_pgtable_walk_data { + u64 ptes[4]; +}; + /** * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers. * * @map_pages: Map a physically contiguous range of pages of the same size. * @unmap_pages: Unmap a range of virtually contiguous pages of the same size. * @iova_to_phys: Translate iova to physical address. + * @pgtable_walk: (optional) Perform a page table walk for a given iova. * * These functions map directly onto the iommu_ops member functions with * the same names. @@ -199,6 +209,7 @@ struct io_pgtable_ops { struct iommu_iotlb_gather *gather); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, unsigned long iova); + int (*pgtable_walk)(struct io_pgtable_ops *ops, unsigned long iova, void *wd); int (*read_and_clear_dirty)(struct io_pgtable_ops *ops, unsigned long iova, size_t size, unsigned long flags, diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index e123d5e17b52..85fe4e6b275c 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -15,10 +15,8 @@ bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) { - if (current->io_uring) { - io_uring_unreg_ringfd(); + if (current->io_uring) __io_uring_cancel(false); - } } static inline void io_uring_task_cancel(void) { diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index 0d5448c0b86c..abd0c8bd950b 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -18,6 +18,11 @@ struct io_uring_cmd { u8 pdu[32]; /* available inline for free use */ }; +struct io_uring_cmd_data { + void *op_data; + struct io_uring_sqe sqes[2]; +}; + static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) { return sqe->cmd; @@ -113,4 +118,9 @@ static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd return cmd_to_io_kiocb(cmd)->tctx->task; } +static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_uring_cmd *cmd) +{ + return cmd_to_io_kiocb(cmd)->async_data; +} + #endif /* _LINUX_IO_URING_CMD_H */ diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 011860ade268..3def525a1da3 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -78,8 +78,9 @@ struct io_hash_table { struct io_mapped_region { struct page **pages; - void *vmap_ptr; - size_t nr_pages; + void *ptr; + unsigned nr_pages; + unsigned flags; }; /* @@ -221,7 +222,8 @@ struct io_alloc_cache { void **entries; unsigned int nr_cached; unsigned int max_cached; - size_t elem_size; + unsigned int elem_size; + unsigned int init_clear; }; struct io_ring_ctx { @@ -293,6 +295,11 @@ struct io_ring_ctx { struct io_submit_state submit_state; + /* + * Modifications are protected by ->uring_lock and ->mmap_lock. + * The flags, buf_pages and buf_nr_pages fields should be stable + * once published. + */ struct xarray io_bl_xa; struct io_hash_table cancel_table; @@ -345,7 +352,7 @@ struct io_ring_ctx { /* timeouts */ struct { - spinlock_t timeout_lock; + raw_spinlock_t timeout_lock; struct list_head timeout_list; struct list_head ltimeout_list; unsigned cq_last_tm_flush; @@ -424,17 +431,10 @@ struct io_ring_ctx { * side will need to grab this lock, to prevent either side from * being run concurrently with the other. */ - struct mutex resize_lock; - - /* - * If IORING_SETUP_NO_MMAP is used, then the below holds - * the gup'ed pages for the two rings, and the sqes. - */ - unsigned short n_ring_pages; - unsigned short n_sqe_pages; - struct page **ring_pages; - struct page **sqe_pages; + struct mutex mmap_lock; + struct io_mapped_region sq_region; + struct io_mapped_region ring_region; /* used for optimised request parameter and wait argument passing */ struct io_mapped_region param_region; }; @@ -481,6 +481,7 @@ enum { REQ_F_BL_NO_RECYCLE_BIT, REQ_F_BUFFERS_COMMIT_BIT, REQ_F_BUF_NODE_BIT, + REQ_F_HAS_METADATA_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -561,6 +562,8 @@ enum { REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT), /* buf node is valid */ REQ_F_BUF_NODE = IO_REQ_FLAG(REQ_F_BUF_NODE_BIT), + /* request has read/write metadata assigned */ + REQ_F_HAS_METADATA = IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5675af6b740c..75bf54e76f3b 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -335,7 +335,7 @@ struct iomap_ioend { u16 io_type; u16 io_flags; /* IOMAP_F_* */ struct inode *io_inode; /* file being written to */ - size_t io_size; /* size of the extent */ + size_t io_size; /* size of data within eof */ loff_t io_offset; /* offset in the file */ sector_t io_sector; /* start sector of ioend */ struct bio io_bio; /* MUST BE LAST! */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 318d27841130..38c65e92ecd0 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -587,9 +587,6 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size, * - IOMMU_DOMAIN_DMA: must use a dma domain * - 0: use the default setting * @default_domain_ops: the default ops for domains - * @remove_dev_pasid: Remove any translation configurations of a specific - * pasid, so that any DMA transactions with this pasid - * will be blocked by the hardware. * @viommu_alloc: Allocate an iommufd_viommu on a physical IOMMU instance behind * the @dev, as the set of virtualization resources shared/passed * to user space IOMMU instance. And associate it with a nesting @@ -647,8 +644,6 @@ struct iommu_ops { struct iommu_page_response *msg); int (*def_domain_type)(struct device *dev); - void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid, - struct iommu_domain *domain); struct iommufd_viommu *(*viommu_alloc)( struct device *dev, struct iommu_domain *parent_domain, diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index a1c9c0d48ebf..2f74dd90c271 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -126,7 +126,7 @@ int ipmi_create_user(unsigned int if_num, * the users before you destroy the callback structures, it should be * safe, too. */ -int ipmi_destroy_user(struct ipmi_user *user); +void ipmi_destroy_user(struct ipmi_user *user); /* Get the IPMI version of the BMC we are talking to. */ int ipmi_get_version(struct ipmi_user *user, diff --git a/include/linux/irq.h b/include/linux/irq.h index fa711f80957b..8daa17f0107a 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -64,7 +64,6 @@ enum irqchip_irq_state; * IRQ_NOAUTOEN - Interrupt is not automatically enabled in * request/setup_irq() * IRQ_NO_BALANCING - Interrupt cannot be balanced (affinity set) - * IRQ_MOVE_PCNTXT - Interrupt can be migrated from process context * IRQ_NESTED_THREAD - Interrupt nests into another thread * IRQ_PER_CPU_DEVID - Dev_id is a per-cpu variable * IRQ_IS_POLLED - Always polled by another interrupt. Exclude @@ -93,7 +92,6 @@ enum { IRQ_NOREQUEST = (1 << 11), IRQ_NOAUTOEN = (1 << 12), IRQ_NO_BALANCING = (1 << 13), - IRQ_MOVE_PCNTXT = (1 << 14), IRQ_NESTED_THREAD = (1 << 15), IRQ_NOTHREAD = (1 << 16), IRQ_PER_CPU_DEVID = (1 << 17), @@ -105,7 +103,7 @@ enum { #define IRQF_MODIFY_MASK \ (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ - IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ + IRQ_NOAUTOEN | IRQ_LEVEL | IRQ_NO_BALANCING | \ IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN) @@ -201,8 +199,6 @@ struct irq_data { * IRQD_LEVEL - Interrupt is level triggered * IRQD_WAKEUP_STATE - Interrupt is configured for wakeup * from suspend - * IRQD_MOVE_PCNTXT - Interrupt can be moved in process - * context * IRQD_IRQ_DISABLED - Disabled state of the interrupt * IRQD_IRQ_MASKED - Masked state of the interrupt * IRQD_IRQ_INPROGRESS - In progress state of the interrupt @@ -233,7 +229,6 @@ enum { IRQD_AFFINITY_SET = BIT(12), IRQD_LEVEL = BIT(13), IRQD_WAKEUP_STATE = BIT(14), - IRQD_MOVE_PCNTXT = BIT(15), IRQD_IRQ_DISABLED = BIT(16), IRQD_IRQ_MASKED = BIT(17), IRQD_IRQ_INPROGRESS = BIT(18), @@ -338,11 +333,6 @@ static inline bool irqd_is_wakeup_set(struct irq_data *d) return __irqd_to_state(d) & IRQD_WAKEUP_STATE; } -static inline bool irqd_can_move_in_process_context(struct irq_data *d) -{ - return __irqd_to_state(d) & IRQD_MOVE_PCNTXT; -} - static inline bool irqd_irq_disabled(struct irq_data *d) { return __irqd_to_state(d) & IRQD_IRQ_DISABLED; @@ -567,6 +557,7 @@ struct irq_chip { * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip + * IRQCHIP_MOVE_DEFERRED: Move the interrupt in actual interrupt context */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -581,6 +572,7 @@ enum { IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), IRQCHIP_IMMUTABLE = (1 << 11), + IRQCHIP_MOVE_DEFERRED = (1 << 12), }; #include @@ -694,6 +686,9 @@ extern int irq_chip_request_resources_parent(struct irq_data *data); extern void irq_chip_release_resources_parent(struct irq_data *data); #endif +/* Disable or mask interrupts during a kernel kexec */ +extern void machine_kexec_mask_interrupts(void); + /* Handling of unhandled and spurious interrupts: */ extern void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 50f7ea8714bf..561025b4f3d9 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -28,7 +28,7 @@ #include #include #include -#include +#include #endif #define journal_oom_retry 1 @@ -1241,13 +1241,6 @@ struct journal_s */ void *j_private; - /** - * @j_chksum_driver: - * - * Reference to checksum algorithm driver via cryptoapi. - */ - struct crypto_shash *j_chksum_driver; - /** * @j_csum_seed: * @@ -1750,10 +1743,7 @@ static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j) static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { - WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) && - journal->j_chksum_driver == NULL); - - return journal->j_chksum_driver != NULL; + return jbd2_journal_has_csum_v2or3_feature(journal); } static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) @@ -1790,27 +1780,10 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 -/* JBD uses a CRC32 checksum */ -#define JBD_MAX_CHECKSUM_SIZE 4 - static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { - DEFINE_RAW_FLEX(struct shash_desc, desc, __ctx, - DIV_ROUND_UP(JBD_MAX_CHECKSUM_SIZE, - sizeof(*((struct shash_desc *)0)->__ctx))); - int err; - - BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > - JBD_MAX_CHECKSUM_SIZE); - - desc->tfm = journal->j_chksum_driver; - *(u32 *)desc->__ctx = crc; - - err = crypto_shash_update(desc, address, length); - BUG_ON(err); - - return *(u32 *)desc->__ctx; + return crc32c(crc, address, length); } /* Return most recent uncommitted transaction */ diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index f5a2727ca4a9..fdb79dd1ebd8 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -75,6 +75,7 @@ #include #include +#include extern bool static_key_initialized; @@ -347,6 +348,8 @@ static inline void static_key_disable(struct static_key *key) #endif /* CONFIG_JUMP_LABEL */ +DEFINE_LOCK_GUARD_0(jump_label_lock, jump_label_lock(), jump_label_unlock()) + #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE #define jump_label_enabled static_key_enabled diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index c3f075e8f60c..1c6a6c1704d8 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -57,10 +57,10 @@ static inline void *dereference_symbol_descriptor(void *ptr) preempt_disable(); mod = __module_address((unsigned long)ptr); - preempt_enable(); if (mod) ptr = dereference_module_function_descriptor(mod, ptr); + preempt_enable(); #endif return ptr; } diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 6bbfc8aa42e8..890011071f2b 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -153,7 +153,7 @@ static __always_inline void kasan_unpoison_new_object(struct kmem_cache *cache, void __kasan_poison_new_object(struct kmem_cache *cache, void *object); /** - * kasan_unpoison_new_object - Repoison a new slab object. + * kasan_poison_new_object - Repoison a new slab object. * @cache: Cache the object belong to. * @object: Pointer to the object. * @@ -491,7 +491,6 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); -void kasan_record_aux_stack_noalloc(void *ptr); #else /* CONFIG_KASAN_GENERIC */ @@ -509,7 +508,6 @@ static inline void kasan_cache_create(struct kmem_cache *cache, static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} -static inline void kasan_record_aux_stack_noalloc(void *ptr) {} #endif /* CONFIG_KASAN_GENERIC */ diff --git a/include/linux/kcore.h b/include/linux/kcore.h index 86c0f1d18998..9a2fa013c91d 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -20,19 +20,6 @@ struct kcore_list { int type; }; -struct vmcore { - struct list_head list; - unsigned long long paddr; - unsigned long long size; - loff_t offset; -}; - -struct vmcoredd_node { - struct list_head list; /* List of dumps */ - void *buf; /* Buffer containing device's dump */ - unsigned int size; /* Size of the buffer */ -}; - #ifdef CONFIG_PROC_KCORE void __init kclist_add(struct kcore_list *, void *, size_t, int type); diff --git a/include/linux/kdb.h b/include/linux/kdb.h index f6c2ddb16b95..905a2e2f45f6 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -140,9 +140,6 @@ extern const char *kdb_diemsg; extern unsigned int kdb_flags; /* Global flags, see kdb_state for per cpu state */ -extern void kdb_save_flags(void); -extern void kdb_restore_flags(void); - #define KDB_FLAG(flag) (kdb_flags & KDB_FLAG_##flag) #define KDB_FLAG_SET(flag) ((void)(kdb_flags |= KDB_FLAG_##flag)) #define KDB_FLAG_CLEAR(flag) ((void)(kdb_flags &= ~KDB_FLAG_##flag)) diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 76e891ee9e37..51ef131e66b7 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -309,11 +309,9 @@ extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs); #ifdef CONFIG_SERIAL_KGDB_NMI extern int kgdb_register_nmi_console(void); extern int kgdb_unregister_nmi_console(void); -extern bool kgdb_nmi_poll_knock(void); #else static inline int kgdb_register_nmi_console(void) { return 0; } static inline int kgdb_unregister_nmi_console(void) { return 0; } -static inline bool kgdb_nmi_poll_knock(void) { return true; } #endif extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops); diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h index be707748e7ce..150fe2ae1b6b 100644 --- a/include/linux/kobject_ns.h +++ b/include/linux/kobject_ns.h @@ -52,8 +52,6 @@ const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj); bool kobj_ns_current_may_mount(enum kobj_ns_type type); void *kobj_ns_grab_current(enum kobj_ns_type type); -const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); -const void *kobj_ns_initial(enum kobj_ns_type type); void kobj_ns_drop(enum kobj_ns_type type, void *ns); #endif /* _LINUX_KOBJECT_NS_H */ diff --git a/include/linux/kref.h b/include/linux/kref.h index d32e21a2538c..88e82ab1367c 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -46,18 +46,18 @@ static inline void kref_get(struct kref *kref) } /** - * kref_put - decrement refcount for object. - * @kref: object. - * @release: pointer to the function that will clean up the object when the + * kref_put - Decrement refcount for object + * @kref: Object + * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. - * This pointer is required, and it is not acceptable to pass kfree - * in as this function. * - * Decrement the refcount, and if 0, call release(). - * Return 1 if the object was removed, otherwise return 0. Beware, if this - * function returns 0, you still can not count on the kref from remaining in - * memory. Only use the return value if you want to see if the kref is now - * gone, not present. + * Decrement the refcount, and if 0, call @release. The caller may not + * pass NULL or kfree() as the release function. + * + * Return: 1 if this call removed the object, otherwise return 0. Beware, + * if this function returns 0, another caller may have removed the object + * by the time this function returns. The return value is only certain + * if you want to see if the object is definitely released. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { @@ -68,17 +68,37 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref) return 0; } +/** + * kref_put_mutex - Decrement refcount for object + * @kref: Object + * @release: Pointer to the function that will clean up the object when the + * last reference to the object is released. + * @mutex: Mutex which protects the release function. + * + * This variant of kref_lock() calls the @release function with the @mutex + * held. The @release function will release the mutex. + */ static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), - struct mutex *lock) + struct mutex *mutex) { - if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) { + if (refcount_dec_and_mutex_lock(&kref->refcount, mutex)) { release(kref); return 1; } return 0; } +/** + * kref_put_lock - Decrement refcount for object + * @kref: Object + * @release: Pointer to the function that will clean up the object when the + * last reference to the object is released. + * @lock: Spinlock which protects the release function. + * + * This variant of kref_lock() calls the @release function with the @lock + * held. The @release function will release the lock. + */ static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) @@ -94,8 +114,6 @@ static inline int kref_put_lock(struct kref *kref, * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * - * Return non-zero if the increment succeeded. Otherwise return 0. - * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. @@ -105,6 +123,8 @@ static inline int kref_put_lock(struct kref *kref, * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. + * + * Return: non-zero if the increment succeeded. Otherwise return 0. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 6a53ac4885bb..d73095b5cd96 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -93,6 +93,7 @@ void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); +bool ksm_process_mergeable(struct mm_struct *mm); #else /* !CONFIG_KSM */ diff --git a/include/linux/kthread.h b/include/linux/kthread.h index b11f53c1ba2e..8d27403888ce 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -85,6 +85,7 @@ kthread_run_on_cpu(int (*threadfn)(void *data), void *data, void free_kthread_struct(struct task_struct *k); void kthread_bind(struct task_struct *k, unsigned int cpu); void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask); +int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask); int kthread_stop(struct task_struct *k); int kthread_stop_put(struct task_struct *k); bool kthread_should_stop(void); @@ -186,13 +187,58 @@ extern void __kthread_init_worker(struct kthread_worker *worker, int kthread_worker_fn(void *worker_ptr); -__printf(2, 3) -struct kthread_worker * -kthread_create_worker(unsigned int flags, const char namefmt[], ...); +__printf(3, 4) +struct kthread_worker *kthread_create_worker_on_node(unsigned int flags, + int node, + const char namefmt[], ...); -__printf(3, 4) struct kthread_worker * +#define kthread_create_worker(flags, namefmt, ...) \ + kthread_create_worker_on_node(flags, NUMA_NO_NODE, namefmt, ## __VA_ARGS__); + +/** + * kthread_run_worker - create and wake a kthread worker. + * @flags: flags modifying the default behavior of the worker + * @namefmt: printf-style name for the thread. + * + * Description: Convenient wrapper for kthread_create_worker() followed by + * wake_up_process(). Returns the kthread_worker or ERR_PTR(-ENOMEM). + */ +#define kthread_run_worker(flags, namefmt, ...) \ +({ \ + struct kthread_worker *__kw \ + = kthread_create_worker(flags, namefmt, ## __VA_ARGS__); \ + if (!IS_ERR(__kw)) \ + wake_up_process(__kw->task); \ + __kw; \ +}) + +struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, - const char namefmt[], ...); + const char namefmt[]); + +/** + * kthread_run_worker_on_cpu - create and wake a cpu bound kthread worker. + * @cpu: CPU number + * @flags: flags modifying the default behavior of the worker + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. + * + * Description: Convenient wrapper for kthread_create_worker_on_cpu() + * followed by wake_up_process(). Returns the kthread_worker or + * ERR_PTR(-ENOMEM). + */ +static inline struct kthread_worker * +kthread_run_worker_on_cpu(int cpu, unsigned int flags, + const char namefmt[]) +{ + struct kthread_worker *kw; + + kw = kthread_create_worker_on_cpu(cpu, flags, namefmt); + if (!IS_ERR(kw)) + wake_up_process(kw->task); + + return kw; +} bool kthread_queue_work(struct kthread_worker *worker, struct kthread_work *work); diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 3a4e723eae0f..383ed9985802 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -222,6 +222,11 @@ static inline ktime_t ns_to_ktime(u64 ns) return ns; } +static inline ktime_t us_to_ktime(u64 us) +{ + return us * NSEC_PER_USEC; +} + static inline ktime_t ms_to_ktime(u64 ms) { return ms * NSEC_PER_MSEC; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 401439bb21e3..3cb9a32a6330 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -255,11 +255,17 @@ union kvm_mmu_notifier_arg { unsigned long attributes; }; +enum kvm_gfn_range_filter { + KVM_FILTER_SHARED = BIT(0), + KVM_FILTER_PRIVATE = BIT(1), +}; + struct kvm_gfn_range { struct kvm_memory_slot *slot; gfn_t start; gfn_t end; union kvm_mmu_notifier_arg arg; + enum kvm_gfn_range_filter attr_filter; bool may_block; }; bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); @@ -596,7 +602,12 @@ struct kvm_memory_slot { #ifdef CONFIG_KVM_PRIVATE_MEM struct { - struct file __rcu *file; + /* + * Writes protected by kvm->slots_lock. Acquiring a + * reference via kvm_gmem_get_file() is protected by + * either kvm->slots_lock or kvm->srcu. + */ + struct file *file; pgoff_t pgoff; } gmem; #endif @@ -963,6 +974,15 @@ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { int num_vcpus = atomic_read(&kvm->online_vcpus); + + /* + * Explicitly verify the target vCPU is online, as the anti-speculation + * logic only limits the CPU's ability to speculate, e.g. given a "bad" + * index, clamping the index to 0 would return vCPU0, not NULL. + */ + if (i >= num_vcpus) + return NULL; + i = array_index_nospec(i, num_vcpus); /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ @@ -970,9 +990,10 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ - (atomic_read(&kvm->online_vcpus) - 1)) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + if (atomic_read(&kvm->online_vcpus)) \ + xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ + (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { @@ -1183,7 +1204,7 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn * -- just change its flags * * Since flags can be changed by some of these operations, the following - * differentiation is the best we can do for __kvm_set_memory_region(): + * differentiation is the best we can do for kvm_set_memory_region(): */ enum kvm_mr_change { KVM_MR_CREATE, @@ -1192,10 +1213,8 @@ enum kvm_mr_change { KVM_MR_FLAGS_ONLY, }; -int kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region2 *mem); -int __kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region2 *mem); +int kvm_set_internal_memslot(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, diff --git a/include/linux/libata.h b/include/linux/libata.h index c1a85d46eba6..c1c57f814b98 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1199,10 +1199,9 @@ extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, sector_t capacity, int geom[]); extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev); -extern int ata_scsi_slave_alloc(struct scsi_device *sdev); -int ata_scsi_device_configure(struct scsi_device *sdev, - struct queue_limits *lim); -extern void ata_scsi_slave_destroy(struct scsi_device *sdev); +extern int ata_scsi_sdev_init(struct scsi_device *sdev); +int ata_scsi_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim); +extern void ata_scsi_sdev_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth); extern int ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev, @@ -1301,8 +1300,8 @@ extern struct ata_port *ata_port_alloc(struct ata_host *host); extern void ata_port_free(struct ata_port *ap); extern int ata_tport_add(struct device *parent, struct ata_port *ap); extern void ata_tport_delete(struct ata_port *ap); -int ata_sas_device_configure(struct scsi_device *sdev, struct queue_limits *lim, - struct ata_port *ap); +int ata_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim, + struct ata_port *ap); extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap); extern void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis); @@ -1458,8 +1457,8 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .this_id = ATA_SHT_THIS_ID, \ .emulated = ATA_SHT_EMULATED, \ .proc_name = drv_name, \ - .slave_alloc = ata_scsi_slave_alloc, \ - .slave_destroy = ata_scsi_slave_destroy, \ + .sdev_init = ata_scsi_sdev_init, \ + .sdev_destroy = ata_scsi_sdev_destroy, \ .bios_param = ata_std_bios_param, \ .unlock_native_capacity = ata_scsi_unlock_native_capacity,\ .max_sectors = ATA_MAX_SECTORS_LBA48 @@ -1467,14 +1466,14 @@ extern const struct attribute_group *ata_common_sdev_groups[]; #define ATA_SUBBASE_SHT(drv_name) \ __ATA_BASE_SHT(drv_name), \ .can_queue = ATA_DEF_QUEUE, \ - .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .device_configure = ata_scsi_device_configure + .tag_alloc_policy_rr = true, \ + .sdev_configure = ata_scsi_sdev_configure #define ATA_SUBBASE_SHT_QD(drv_name, drv_qd) \ __ATA_BASE_SHT(drv_name), \ .can_queue = drv_qd, \ - .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .device_configure = ata_scsi_device_configure + .tag_alloc_policy_rr = true, \ + .sdev_configure = ata_scsi_sdev_configure #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ diff --git a/include/linux/libgcc.h b/include/linux/libgcc.h index fc388da6a027..0d68f9d6a6a7 100644 --- a/include/linux/libgcc.h +++ b/include/linux/libgcc.h @@ -34,4 +34,8 @@ long long notrace __lshrdi3(long long u, word_type b); long long notrace __muldi3(long long u, long long v); word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b); +#ifdef CONFIG_HAVE_ARCH_LIBGCC_H +#include +#endif + #endif /* __ASM_LIBGCC_H */ diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 05c166811f6b..fe739d35a864 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -91,13 +91,24 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren * @memcg: the cgroup of the sublist to add the item to. * * If the element is already part of a list, this function returns doing - * nothing. Therefore the caller does not need to keep state about whether or - * not the element already belongs in the list and is allowed to lazy update - * it. Note however that this is valid for *a* list, not *this* list. If - * the caller organize itself in a way that elements can be in more than - * one type of list, it is up to the caller to fully remove the item from - * the previous list (with list_lru_del() for instance) before moving it - * to @lru. + * nothing. This means that it is not necessary to keep state about whether or + * not the element already belongs in the list. That said, this logic only + * works if the item is in *this* list. If the item might be in some other + * list, then you cannot rely on this check and you must remove it from the + * other list before trying to insert it. + * + * The lru list consists of many sublists internally; the @nid and @memcg + * parameters are used to determine which sublist to insert the item into. + * It's important to use the right value of @nid and @memcg when deleting the + * item, since it might otherwise get deleted from the wrong sublist. + * + * This also applies when attempting to insert the item multiple times - if + * the item is currently in one sublist and you call list_lru_add() again, you + * must pass the right @nid and @memcg parameters so that the same sublist is + * used. + * + * You must ensure that the memcg is not freed during this call (e.g., with + * rcu or by taking a css refcnt). * * Return: true if the list was updated, false otherwise */ @@ -113,7 +124,7 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, * memcg of the sublist is determined by @item list_head. This assumption is * valid for slab objects LRU such as dentries, inodes, etc. * - * Return value: true if the list was updated, false otherwise + * Return: true if the list was updated, false otherwise */ bool list_lru_add_obj(struct list_lru *lru, struct list_head *item); @@ -125,8 +136,19 @@ bool list_lru_add_obj(struct list_lru *lru, struct list_head *item); * @memcg: the cgroup of the sublist to delete the item from. * * This function works analogously as list_lru_add() in terms of list - * manipulation. The comments about an element already pertaining to - * a list are also valid for list_lru_del(). + * manipulation. + * + * The comments in list_lru_add() about an element already being in a list are + * also valid for list_lru_del(), that is, you can delete an item that has + * already been removed or never been added. However, if the item is in a + * list, it must be in *this* list, and you must pass the right value of @nid + * and @memcg so that the right sublist is used. + * + * You must ensure that the memcg is not freed during this call (e.g., with + * rcu or by taking a css refcnt). When a memcg is deleted, list_lru entries + * are automatically moved to the parent memcg. This is done in a race-free + * way, so during deletion of an memcg both the old and new memcg will resolve + * to the same sublist internally. * * Return: true if the list was updated, false otherwise */ @@ -142,7 +164,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, * memcg of the sublist is determined by @item list_head. This assumption is * valid for slab objects LRU such as dentries, inodes, etc. * - * Return value: true if the list was updated, false otherwise. + * Return: true if the list was updated, false otherwise. */ bool list_lru_del_obj(struct list_lru *lru, struct list_head *item); diff --git a/include/linux/lockref.h b/include/linux/lockref.h index c3a1f78bc884..c39f119659ba 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -34,14 +34,24 @@ struct lockref { }; }; -extern void lockref_get(struct lockref *); -extern int lockref_put_return(struct lockref *); -extern int lockref_get_not_zero(struct lockref *); -extern int lockref_put_not_zero(struct lockref *); -extern int lockref_put_or_lock(struct lockref *); +/** + * lockref_init - Initialize a lockref + * @lockref: pointer to lockref structure + * @count: initial count + */ +static inline void lockref_init(struct lockref *lockref, unsigned int count) +{ + spin_lock_init(&lockref->lock); + lockref->count = count; +} -extern void lockref_mark_dead(struct lockref *); -extern int lockref_get_not_dead(struct lockref *); +void lockref_get(struct lockref *lockref); +int lockref_put_return(struct lockref *lockref); +bool lockref_get_not_zero(struct lockref *lockref); +bool lockref_put_or_lock(struct lockref *lockref); + +void lockref_mark_dead(struct lockref *lockref); +bool lockref_get_not_dead(struct lockref *lockref); /* Must be called under spinlock for reliable results */ static inline bool __lockref_is_dead(const struct lockref *l) diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 97a8b21eb033..e13d2f947b51 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -77,6 +77,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_LOCKDOWN 15 #define LSM_AUDIT_DATA_NOTIFICATION 16 #define LSM_AUDIT_DATA_ANONINODE 17 +#define LSM_AUDIT_DATA_NLMSGTYPE 18 union { struct path path; struct dentry *dentry; @@ -98,6 +99,7 @@ struct common_audit_data { struct lsm_ibendport_audit *ibendport; int reason; const char *anonclass; + u16 nlmsg_type; } u; /* this union contains LSM specific data */ union { @@ -116,14 +118,28 @@ struct common_audit_data { #define v4info fam.v4 #define v6info fam.v6 +#ifdef CONFIG_AUDIT + int ipv4_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto); +#if IS_ENABLED(CONFIG_IPV6) int ipv6_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto); +#endif /* IS_ENABLED(CONFIG_IPV6) */ void common_lsm_audit(struct common_audit_data *a, void (*pre_audit)(struct audit_buffer *, void *), void (*post_audit)(struct audit_buffer *, void *)); +#else /* CONFIG_AUDIT */ + +static inline void common_lsm_audit(struct common_audit_data *a, + void (*pre_audit)(struct audit_buffer *, void *), + void (*post_audit)(struct audit_buffer *, void *)) +{ +} + +#endif /* CONFIG_AUDIT */ + #endif diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index eb2937599cb0..e2f1ce37c41e 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -83,7 +83,7 @@ LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, - void **ctx, u32 *ctxlen) + struct lsm_context *cp) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) @@ -295,17 +295,16 @@ LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) -LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata, - u32 *seclen) +LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, struct lsm_context *cp) LSM_HOOK(int, -EOPNOTSUPP, lsmprop_to_secctx, struct lsm_prop *prop, - char **secdata, u32 *seclen) + struct lsm_context *cp) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) -LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) +LSM_HOOK(void, LSM_RET_VOID, release_secctx, struct lsm_context *cp) LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode) LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen) LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen) -LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, void **ctx, - u32 *ctxlen) +LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, + struct lsm_context *cp) #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) LSM_HOOK(int, 0, post_notification, const struct cred *w_cred, diff --git a/include/linux/lz4.h b/include/linux/lz4.h index b16e15b9587a..ad6042a718b5 100644 --- a/include/linux/lz4.h +++ b/include/linux/lz4.h @@ -645,4 +645,10 @@ int LZ4_decompress_safe_usingDict(const char *source, char *dest, int LZ4_decompress_fast_usingDict(const char *source, char *dest, int originalSize, const char *dictStart, int dictSize); +#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize) (((compressedSize) >> 8) + 32) + +#ifndef LZ4_DISTANCE_MAX /* history window size; can be user-defined at compile time */ +#define LZ4_DISTANCE_MAX 65535 /* set to maximum value by default */ +#endif + #endif diff --git a/include/linux/mailbox/exynos-message.h b/include/linux/mailbox/exynos-message.h new file mode 100644 index 000000000000..5a9ed5ce2046 --- /dev/null +++ b/include/linux/mailbox/exynos-message.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Exynos mailbox message. + * + * Copyright 2024 Linaro Ltd. + */ + +#ifndef _LINUX_EXYNOS_MESSAGE_H_ +#define _LINUX_EXYNOS_MESSAGE_H_ + +#define EXYNOS_MBOX_CHAN_TYPE_DOORBELL 0 +#define EXYNOS_MBOX_CHAN_TYPE_DATA 1 + +struct exynos_mbox_msg { + unsigned int chan_id; + unsigned int chan_type; +}; + +#endif /* _LINUX_EXYNOS_MESSAGE_H_ */ diff --git a/include/linux/mailbox/mchp-ipc.h b/include/linux/mailbox/mchp-ipc.h new file mode 100644 index 000000000000..f084ac9e291b --- /dev/null +++ b/include/linux/mailbox/mchp-ipc.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + *Copyright (c) 2024 Microchip Technology Inc. All rights reserved. + */ + +#ifndef _LINUX_MCHP_IPC_H_ +#define _LINUX_MCHP_IPC_H_ + +#include +#include + +struct mchp_ipc_msg { + u32 *buf; + u16 size; +}; + +struct mchp_ipc_sbi_chan { + void *buf_base_tx; + void *buf_base_rx; + void *msg_buf_tx; + void *msg_buf_rx; + phys_addr_t buf_base_tx_addr; + phys_addr_t buf_base_rx_addr; + phys_addr_t msg_buf_tx_addr; + phys_addr_t msg_buf_rx_addr; + int chan_aggregated_irq; + int mp_irq; + int mc_irq; + u32 id; + u32 max_msg_size; +}; + +#endif /* _LINUX_MCHP_IPC_H_ */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 673d5cae7c81..e79eb6ac516f 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -378,6 +378,10 @@ static inline int memblock_get_region_node(const struct memblock_region *r) /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) #define MEMBLOCK_ALLOC_ACCESSIBLE 0 +/* + * MEMBLOCK_ALLOC_NOLEAKTRACE avoids kmemleak tracing. It implies + * MEMBLOCK_ALLOC_ACCESSIBLE + */ #define MEMBLOCK_ALLOC_NOLEAKTRACE 1 /* We are using top down, so it is safe to use 0 here */ @@ -417,6 +421,12 @@ static __always_inline void *memblock_alloc(phys_addr_t size, phys_addr_t align) MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } +void *__memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align, + const char *func); + +#define memblock_alloc_or_panic(size, align) \ + __memblock_alloc_or_panic(size, align, __func__) + static inline void *memblock_alloc_raw(phys_addr_t size, phys_addr_t align) { diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5502aa8e138e..6e74b8254d9b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -620,8 +620,6 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target, page_counter_read(&memcg->memory); } -void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg); - int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); /** @@ -646,8 +644,7 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, return __mem_cgroup_charge(folio, mm, gfp); } -int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp, - long nr_pages); +int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp); int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); @@ -677,7 +674,6 @@ static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) __mem_cgroup_uncharge_folios(folios); } -void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_replace_folio(struct folio *old, struct folio *new); void mem_cgroup_migrate(struct folio *old, struct folio *new); @@ -1046,6 +1042,23 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, void split_page_memcg(struct page *head, int old_order, int new_order); +static inline u64 cgroup_id_from_mm(struct mm_struct *mm) +{ + struct mem_cgroup *memcg; + u64 id; + + if (mem_cgroup_disabled()) + return 0; + + rcu_read_lock(); + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (!memcg) + memcg = root_mem_cgroup; + id = cgroup_id(memcg->css.cgroup); + rcu_read_unlock(); + return id; +} + #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 @@ -1135,21 +1148,15 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target, return false; } -static inline void mem_cgroup_commit_charge(struct folio *folio, - struct mem_cgroup *memcg) -{ -} - static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { return 0; } -static inline int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, - gfp_t gfp, long nr_pages) +static inline int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp) { - return 0; + return 0; } static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, @@ -1170,11 +1177,6 @@ static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { } -static inline void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, - unsigned int nr_pages) -{ -} - static inline void mem_cgroup_replace_folio(struct folio *old, struct folio *new) { @@ -1466,6 +1468,11 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) static inline void split_page_memcg(struct page *head, int old_order, int new_order) { } + +static inline u64 cgroup_id_from_mm(struct mm_struct *mm) +{ + return 0; +} #endif /* CONFIG_MEMCG */ /* diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 3f2cf339ceaf..246daadbfde8 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -7,6 +7,14 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); +/* + * Check for any existing seals on mmap, return an error if access is denied due + * to sealing, or 0 otherwise. + * + * We also update VMA flags if appropriate by manipulating the VMA flags pointed + * to by vm_flags_ptr. + */ +int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { @@ -16,6 +24,11 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) { return ERR_PTR(-EINVAL); } +static inline int memfd_check_seals_mmap(struct file *file, + unsigned long *vm_flags_ptr) +{ + return 0; +} #endif #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/memory/ti-aemif.h b/include/linux/memory/ti-aemif.h new file mode 100644 index 000000000000..da94a9d985e7 --- /dev/null +++ b/include/linux/memory/ti-aemif.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __MEMORY_TI_AEMIF_H +#define __MEMORY_TI_AEMIF_H + +/** + * struct aemif_cs_timings: structure to hold CS timing configuration + * values are expressed in number of clock cycles - 1 + * @ta: minimum turn around time + * @rhold: read hold width + * @rstrobe: read strobe width + * @rsetup: read setup width + * @whold: write hold width + * @wstrobe: write strobe width + * @wsetup: write setup width + */ +struct aemif_cs_timings { + u32 ta; + u32 rhold; + u32 rstrobe; + u32 rsetup; + u32 whold; + u32 wstrobe; + u32 wsetup; +}; + +struct aemif_device; + +int aemif_set_cs_timings(struct aemif_device *aemif, u8 cs, struct aemif_cs_timings *timings); +int aemif_check_cs_timings(struct aemif_cs_timings *timings); + +#endif // __MEMORY_TI_AEMIF_H diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index b27ddce5d324..eaac5ae8c05c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -144,8 +144,6 @@ extern u64 max_mem_size; extern int mhp_online_type_from_str(const char *str); -/* Default online_type (MMOP_*) when new memory blocks are added. */ -extern int mhp_default_online_type; /* If movable_node boot option specified */ extern bool movable_node_enabled; static inline bool movable_node_is_enabled(void) @@ -303,6 +301,9 @@ static inline void __remove_memory(u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_MEMORY_HOTPLUG +/* Default online_type (MMOP_*) when new memory blocks are added. */ +extern int mhp_get_default_online_type(void); +extern void mhp_set_default_online_type(int online_type); extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat); extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index e8bcad641d8c..faeea7abd688 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -72,7 +72,7 @@ struct mfd_cell { int (*resume)(struct platform_device *dev); /* platform data passed to the sub devices drivers */ - void *platform_data; + const void *platform_data; size_t pdata_size; /* Matches ACPI */ diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h index 76feb3a7066d..9cb2fc2938ce 100644 --- a/include/linux/mfd/da9052/da9052.h +++ b/include/linux/mfd/da9052/da9052.h @@ -93,6 +93,8 @@ struct da9052 { int chip_irq; + int fault_log; + /* SOC I/O transfer related fixes for DA9052/53 */ int (*fix_io) (struct da9052 *da9052, unsigned char reg); }; diff --git a/include/linux/mfd/qnap-mcu.h b/include/linux/mfd/qnap-mcu.h new file mode 100644 index 000000000000..8d48c212fd44 --- /dev/null +++ b/include/linux/mfd/qnap-mcu.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Core definitions for QNAP MCU MFD driver. + * Copyright (C) 2024 Heiko Stuebner + */ + +#ifndef _LINUX_QNAP_MCU_H_ +#define _LINUX_QNAP_MCU_H_ + +struct qnap_mcu; + +struct qnap_mcu_variant { + u32 baud_rate; + int num_drives; + int fan_pwm_min; + int fan_pwm_max; + bool usb_led; +}; + +int qnap_mcu_exec(struct qnap_mcu *mcu, + const u8 *cmd_data, size_t cmd_data_size, + u8 *reply_data, size_t reply_data_size); +int qnap_mcu_exec_with_ack(struct qnap_mcu *mcu, + const u8 *cmd_data, size_t cmd_data_size); + +#endif /* _LINUX_QNAP_MCU_H_ */ diff --git a/include/linux/mfd/tps65219.h b/include/linux/mfd/tps65219.h index e6826e34e2a6..546bceec7173 100644 --- a/include/linux/mfd/tps65219.h +++ b/include/linux/mfd/tps65219.h @@ -10,14 +10,9 @@ #include #include +#include #include -struct regmap; -struct regmap_irq_chip_data; - -#define TPS65219_1V35 1350000 -#define TPS65219_1V8 1800000 - /* TPS chip id list */ #define TPS65219 0xF0 diff --git a/include/linux/mfd/upboard-fpga.h b/include/linux/mfd/upboard-fpga.h new file mode 100644 index 000000000000..12231e40f5da --- /dev/null +++ b/include/linux/mfd/upboard-fpga.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * UP Board CPLD/FPGA driver + * + * Copyright (c) AAEON. All rights reserved. + * Copyright (C) 2024 Bootlin + * + * Author: Gary Wang + * Author: Thomas Richard + * + */ + +#ifndef __LINUX_MFD_UPBOARD_FPGA_H +#define __LINUX_MFD_UPBOARD_FPGA_H + +#define UPBOARD_REGISTER_SIZE 16 + +enum upboard_fpgareg { + UPBOARD_REG_PLATFORM_ID = 0x10, + UPBOARD_REG_FIRMWARE_ID = 0x11, + UPBOARD_REG_FUNC_EN0 = 0x20, + UPBOARD_REG_FUNC_EN1 = 0x21, + UPBOARD_REG_GPIO_EN0 = 0x30, + UPBOARD_REG_GPIO_EN1 = 0x31, + UPBOARD_REG_GPIO_EN2 = 0x32, + UPBOARD_REG_GPIO_DIR0 = 0x40, + UPBOARD_REG_GPIO_DIR1 = 0x41, + UPBOARD_REG_GPIO_DIR2 = 0x42, + UPBOARD_REG_MAX, +}; + +enum upboard_fpga_type { + UPBOARD_UP_FPGA, + UPBOARD_UP2_FPGA, +}; + +struct upboard_fpga_data { + enum upboard_fpga_type type; + const struct regmap_config *regmap_config; +}; + +struct upboard_fpga { + struct device *dev; + struct regmap *regmap; + struct gpio_desc *enable_gpio; + struct gpio_desc *reset_gpio; + struct gpio_desc *clear_gpio; + struct gpio_desc *strobe_gpio; + struct gpio_desc *datain_gpio; + struct gpio_desc *dataout_gpio; + unsigned int firmware_version; + const struct upboard_fpga_data *fpga_data; +}; + +#endif /* __LINUX_MFD_UPBOARD_FPGA_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 002e49b2ebd9..29919faea2f1 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -144,16 +144,14 @@ const struct movable_operations *page_movable_ops(struct page *page) #ifdef CONFIG_NUMA_BALANCING int migrate_misplaced_folio_prepare(struct folio *folio, struct vm_area_struct *vma, int node); -int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, - int node); +int migrate_misplaced_folio(struct folio *folio, int node); #else static inline int migrate_misplaced_folio_prepare(struct folio *folio, struct vm_area_struct *vma, int node) { return -EAGAIN; /* can't migrate now */ } -static inline int migrate_misplaced_folio(struct folio *folio, - struct vm_area_struct *vma, int node) +static inline int migrate_misplaced_folio(struct folio *folio, int node) { return -EAGAIN; /* can't migrate now */ } diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h index e781727c8916..1160bed6579e 100644 --- a/include/linux/min_heap.h +++ b/include/linux/min_heap.h @@ -6,6 +6,17 @@ #include #include +/* + * The Min Heap API provides utilities for managing min-heaps, a binary tree + * structure where each node's value is less than or equal to its children's + * values, ensuring the smallest element is at the root. + * + * Users should avoid directly calling functions prefixed with __min_heap_*(). + * Instead, use the provided macro wrappers. + * + * For further details and examples, refer to Documentation/core-api/min_heap.rst. + */ + /** * Data structure to hold a min-heap. * @nr: Number of elements currently in the heap. @@ -15,8 +26,8 @@ */ #define MIN_HEAP_PREALLOCATED(_type, _name, _nr) \ struct _name { \ - int nr; \ - int size; \ + size_t nr; \ + size_t size; \ _type *data; \ _type preallocated[_nr]; \ } @@ -218,7 +229,7 @@ void __min_heap_init_inline(min_heap_char *heap, void *data, int size) } #define min_heap_init_inline(_heap, _data, _size) \ - __min_heap_init_inline((min_heap_char *)_heap, _data, _size) + __min_heap_init_inline(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size) /* Get the minimum element from the heap. */ static __always_inline @@ -228,7 +239,8 @@ void *__min_heap_peek_inline(struct min_heap_char *heap) } #define min_heap_peek_inline(_heap) \ - (__minheap_cast(_heap) __min_heap_peek_inline((min_heap_char *)_heap)) + (__minheap_cast(_heap) \ + __min_heap_peek_inline(container_of(&(_heap)->nr, min_heap_char, nr))) /* Check if the heap is full. */ static __always_inline @@ -238,7 +250,7 @@ bool __min_heap_full_inline(min_heap_char *heap) } #define min_heap_full_inline(_heap) \ - __min_heap_full_inline((min_heap_char *)_heap) + __min_heap_full_inline(container_of(&(_heap)->nr, min_heap_char, nr)) /* Sift the element at pos down the heap. */ static __always_inline @@ -277,8 +289,8 @@ void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size, } #define min_heap_sift_down_inline(_heap, _pos, _func, _args) \ - __min_heap_sift_down_inline((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), \ - _func, _args) + __min_heap_sift_down_inline(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \ + __minheap_obj_size(_heap), _func, _args) /* Sift up ith element from the heap, O(log2(nr)). */ static __always_inline @@ -304,8 +316,8 @@ void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx } #define min_heap_sift_up_inline(_heap, _idx, _func, _args) \ - __min_heap_sift_up_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, \ - _func, _args) + __min_heap_sift_up_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _idx, _func, _args) /* Floyd's approach to heapification that is O(nr). */ static __always_inline @@ -319,7 +331,8 @@ void __min_heapify_all_inline(min_heap_char *heap, size_t elem_size, } #define min_heapify_all_inline(_heap, _func, _args) \ - __min_heapify_all_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args) + __min_heapify_all_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _func, _args) /* Remove minimum element from the heap, O(log2(nr)). */ static __always_inline @@ -340,7 +353,8 @@ bool __min_heap_pop_inline(min_heap_char *heap, size_t elem_size, } #define min_heap_pop_inline(_heap, _func, _args) \ - __min_heap_pop_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args) + __min_heap_pop_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _func, _args) /* * Remove the minimum element and then push the given element. The @@ -356,8 +370,8 @@ void __min_heap_pop_push_inline(min_heap_char *heap, const void *element, size_t } #define min_heap_pop_push_inline(_heap, _element, _func, _args) \ - __min_heap_pop_push_inline((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), \ - _func, _args) + __min_heap_pop_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ + __minheap_obj_size(_heap), _func, _args) /* Push an element on to the heap, O(log2(nr)). */ static __always_inline @@ -382,8 +396,8 @@ bool __min_heap_push_inline(min_heap_char *heap, const void *element, size_t ele } #define min_heap_push_inline(_heap, _element, _func, _args) \ - __min_heap_push_inline((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), \ - _func, _args) + __min_heap_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ + __minheap_obj_size(_heap), _func, _args) /* Remove ith element from the heap, O(log2(nr)). */ static __always_inline @@ -411,8 +425,8 @@ bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx, } #define min_heap_del_inline(_heap, _idx, _func, _args) \ - __min_heap_del_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, \ - _func, _args) + __min_heap_del_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _idx, _func, _args) void __min_heap_init(min_heap_char *heap, void *data, int size); void *__min_heap_peek(struct min_heap_char *heap); @@ -433,25 +447,31 @@ bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args); #define min_heap_init(_heap, _data, _size) \ - __min_heap_init((min_heap_char *)_heap, _data, _size) + __min_heap_init(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size) #define min_heap_peek(_heap) \ - (__minheap_cast(_heap) __min_heap_peek((min_heap_char *)_heap)) + (__minheap_cast(_heap) __min_heap_peek(container_of(&(_heap)->nr, min_heap_char, nr))) #define min_heap_full(_heap) \ - __min_heap_full((min_heap_char *)_heap) + __min_heap_full(container_of(&(_heap)->nr, min_heap_char, nr)) #define min_heap_sift_down(_heap, _pos, _func, _args) \ - __min_heap_sift_down((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), _func, _args) + __min_heap_sift_down(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \ + __minheap_obj_size(_heap), _func, _args) #define min_heap_sift_up(_heap, _idx, _func, _args) \ - __min_heap_sift_up((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args) + __min_heap_sift_up(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _idx, _func, _args) #define min_heapify_all(_heap, _func, _args) \ - __min_heapify_all((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args) + __min_heapify_all(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _func, _args) #define min_heap_pop(_heap, _func, _args) \ - __min_heap_pop((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args) + __min_heap_pop(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _func, _args) #define min_heap_pop_push(_heap, _element, _func, _args) \ - __min_heap_pop_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), \ - _func, _args) + __min_heap_pop_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ + __minheap_obj_size(_heap), _func, _args) #define min_heap_push(_heap, _element, _func, _args) \ - __min_heap_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args) + __min_heap_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ + __minheap_obj_size(_heap), _func, _args) #define min_heap_del(_heap, _idx, _func, _args) \ - __min_heap_del((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args) + __min_heap_del(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _idx, _func, _args) #endif /* _LINUX_MIN_HEAP_H */ diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 98008dd92153..eaaf5c008e4d 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -8,13 +8,10 @@ #include /* - * min()/max()/clamp() macros must accomplish three things: + * min()/max()/clamp() macros must accomplish several things: * * - Avoid multiple evaluations of the arguments (so side-effects like * "x++" happen only once) when non-constant. - * - Retain result as a constant expressions when called with only - * constant expressions (to avoid tripping VLA warnings in stack - * allocation usage). * - Perform signed v unsigned type-checking (to generate compile * errors instead of nasty runtime surprises). * - Unsigned char/short are always promoted to signed int and can be @@ -31,58 +28,54 @@ * bit #0 set if ok for unsigned comparisons * bit #1 set if ok for signed comparisons * - * In particular, statically non-negative signed integer - * expressions are ok for both. + * In particular, statically non-negative signed integer expressions + * are ok for both. * - * NOTE! Unsigned types smaller than 'int' are implicitly - * converted to 'int' in expressions, and are accepted for - * signed conversions for now. This is debatable. + * NOTE! Unsigned types smaller than 'int' are implicitly converted to 'int' + * in expressions, and are accepted for signed conversions for now. + * This is debatable. * - * Note that 'x' is the original expression, and 'ux' is - * the unique variable that contains the value. + * Note that 'x' is the original expression, and 'ux' is the unique variable + * that contains the value. * - * We use 'ux' for pure type checking, and 'x' for when - * we need to look at the value (but without evaluating - * it for side effects! Careful to only ever evaluate it - * with sizeof() or __builtin_constant_p() etc). + * We use 'ux' for pure type checking, and 'x' for when we need to look at the + * value (but without evaluating it for side effects! + * Careful to only ever evaluate it with sizeof() or __builtin_constant_p() etc). * - * Pointers end up being checked by the normal C type - * rules at the actual comparison, and these expressions - * only need to be careful to not cause warnings for - * pointer use. + * Pointers end up being checked by the normal C type rules at the actual + * comparison, and these expressions only need to be careful to not cause + * warnings for pointer use. */ -#define __signed_type_use(x,ux) (2+__is_nonneg(x,ux)) -#define __unsigned_type_use(x,ux) (1+2*(sizeof(ux)<4)) -#define __sign_use(x,ux) (is_signed_type(typeof(ux))? \ - __signed_type_use(x,ux):__unsigned_type_use(x,ux)) +#define __sign_use(ux) (is_signed_type(typeof(ux)) ? \ + (2 + __is_nonneg(ux)) : (1 + 2 * (sizeof(ux) < 4))) /* - * To avoid warnings about casting pointers to integers - * of different sizes, we need that special sign type. + * Check whether a signed value is always non-negative. * - * On 64-bit we can just always use 'long', since any - * integer or pointer type can just be cast to that. + * A cast is needed to avoid any warnings from values that aren't signed + * integer types (in which case the result doesn't matter). * - * This does not work for 128-bit signed integers since - * the cast would truncate them, but we do not use s128 - * types in the kernel (we do use 'u128', but they will - * be handled by the !is_signed_type() case). + * On 64-bit any integer or pointer type can safely be cast to 'long long'. + * But on 32-bit we need to avoid warnings about casting pointers to integers + * of different sizes without truncating 64-bit values so 'long' or 'long long' + * must be used depending on the size of the value. * - * NOTE! The cast is there only to avoid any warnings - * from when values that aren't signed integer types. + * This does not work for 128-bit signed integers since the cast would truncate + * them, but we do not use s128 types in the kernel (we do use 'u128', + * but they are handled by the !is_signed_type() case). */ -#ifdef CONFIG_64BIT - #define __signed_type(ux) long +#if __SIZEOF_POINTER__ == __SIZEOF_LONG_LONG__ +#define __is_nonneg(ux) statically_true((long long)(ux) >= 0) #else - #define __signed_type(ux) typeof(__builtin_choose_expr(sizeof(ux)>4,1LL,1L)) +#define __is_nonneg(ux) statically_true( \ + (typeof(__builtin_choose_expr(sizeof(ux) > 4, 1LL, 1L)))(ux) >= 0) #endif -#define __is_nonneg(x,ux) statically_true((__signed_type(ux))(x)>=0) -#define __types_ok(x,y,ux,uy) \ - (__sign_use(x,ux) & __sign_use(y,uy)) +#define __types_ok(ux, uy) \ + (__sign_use(ux) & __sign_use(uy)) -#define __types_ok3(x,y,z,ux,uy,uz) \ - (__sign_use(x,ux) & __sign_use(y,uy) & __sign_use(z,uz)) +#define __types_ok3(ux, uy, uz) \ + (__sign_use(ux) & __sign_use(uy) & __sign_use(uz)) #define __cmp_op_min < #define __cmp_op_max > @@ -97,30 +90,13 @@ #define __careful_cmp_once(op, x, y, ux, uy) ({ \ __auto_type ux = (x); __auto_type uy = (y); \ - BUILD_BUG_ON_MSG(!__types_ok(x,y,ux,uy), \ + BUILD_BUG_ON_MSG(!__types_ok(ux, uy), \ #op"("#x", "#y") signedness error"); \ __cmp(op, ux, uy); }) #define __careful_cmp(op, x, y) \ __careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) -#define __clamp(val, lo, hi) \ - ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) - -#define __clamp_once(val, lo, hi, uval, ulo, uhi) ({ \ - __auto_type uval = (val); \ - __auto_type ulo = (lo); \ - __auto_type uhi = (hi); \ - static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), \ - (lo) <= (hi), true), \ - "clamp() low limit " #lo " greater than high limit " #hi); \ - BUILD_BUG_ON_MSG(!__types_ok3(val,lo,hi,uval,ulo,uhi), \ - "clamp("#val", "#lo", "#hi") signedness error"); \ - __clamp(uval, ulo, uhi); }) - -#define __careful_clamp(val, lo, hi) \ - __clamp_once(val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_)) - /** * min - return minimum of two values of the same or compatible types * @x: first value @@ -154,7 +130,7 @@ #define __careful_op3(op, x, y, z, ux, uy, uz) ({ \ __auto_type ux = (x); __auto_type uy = (y);__auto_type uz = (z);\ - BUILD_BUG_ON_MSG(!__types_ok3(x,y,z,ux,uy,uz), \ + BUILD_BUG_ON_MSG(!__types_ok3(ux, uy, uz), \ #op"3("#x", "#y", "#z") signedness error"); \ __cmp(op, ux, __cmp(op, uy, uz)); }) @@ -176,34 +152,6 @@ #define max3(x, y, z) \ __careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) -/** - * min_not_zero - return the minimum that is _not_ zero, unless both are zero - * @x: value1 - * @y: value2 - */ -#define min_not_zero(x, y) ({ \ - typeof(x) __x = (x); \ - typeof(y) __y = (y); \ - __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) - -/** - * clamp - return a value clamped to a given range with strict typechecking - * @val: current value - * @lo: lowest allowable value - * @hi: highest allowable value - * - * This macro does strict typechecking of @lo/@hi to make sure they are of the - * same type as @val. See the unnecessary pointer comparisons. - */ -#define clamp(val, lo, hi) __careful_clamp(val, lo, hi) - -/* - * ..and if you can't take the strict - * types, you can specify one yourself. - * - * Or not use min/max/clamp at all, of course. - */ - /** * min_t - return minimum of two values, using the specified type * @type: data type to use @@ -220,6 +168,68 @@ */ #define max_t(type, x, y) __cmp_once(max, type, x, y) +/** + * min_not_zero - return the minimum that is _not_ zero, unless both are zero + * @x: value1 + * @y: value2 + */ +#define min_not_zero(x, y) ({ \ + typeof(x) __x = (x); \ + typeof(y) __y = (y); \ + __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) + +#define __clamp(val, lo, hi) \ + ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) + +#define __clamp_once(type, val, lo, hi, uval, ulo, uhi) ({ \ + type uval = (val); \ + type ulo = (lo); \ + type uhi = (hi); \ + BUILD_BUG_ON_MSG(statically_true(ulo > uhi), \ + "clamp() low limit " #lo " greater than high limit " #hi); \ + BUILD_BUG_ON_MSG(!__types_ok3(uval, ulo, uhi), \ + "clamp("#val", "#lo", "#hi") signedness error"); \ + __clamp(uval, ulo, uhi); }) + +#define __careful_clamp(type, val, lo, hi) \ + __clamp_once(type, val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_)) + +/** + * clamp - return a value clamped to a given range with typechecking + * @val: current value + * @lo: lowest allowable value + * @hi: highest allowable value + * + * This macro checks @val/@lo/@hi to make sure they have compatible + * signedness. + */ +#define clamp(val, lo, hi) __careful_clamp(__auto_type, val, lo, hi) + +/** + * clamp_t - return a value clamped to a given range using a given type + * @type: the type of variable to use + * @val: current value + * @lo: minimum allowable value + * @hi: maximum allowable value + * + * This macro does no typechecking and uses temporary variables of type + * @type to make all the comparisons. + */ +#define clamp_t(type, val, lo, hi) __careful_clamp(type, val, lo, hi) + +/** + * clamp_val - return a value clamped to a given range using val's type + * @val: current value + * @lo: minimum allowable value + * @hi: maximum allowable value + * + * This macro does no typechecking and uses temporary variables of whatever + * type the input argument @val is. This is useful when @val is an unsigned + * type and @lo and @hi are literals that will otherwise be assigned a signed + * integer type. + */ +#define clamp_val(val, lo, hi) __careful_clamp(typeof(val), val, lo, hi) + /* * Do not check the array parameter using __must_be_array(). * In the following legit use-case where the "array" passed is a simple pointer, @@ -263,31 +273,6 @@ */ #define max_array(array, len) __minmax_array(max, array, len) -/** - * clamp_t - return a value clamped to a given range using a given type - * @type: the type of variable to use - * @val: current value - * @lo: minimum allowable value - * @hi: maximum allowable value - * - * This macro does no typechecking and uses temporary variables of type - * @type to make all the comparisons. - */ -#define clamp_t(type, val, lo, hi) __careful_clamp((type)(val), (type)(lo), (type)(hi)) - -/** - * clamp_val - return a value clamped to a given range using val's type - * @val: current value - * @lo: minimum allowable value - * @hi: maximum allowable value - * - * This macro does no typechecking and uses temporary variables of whatever - * type the input argument @val is. This is useful when @val is an unsigned - * type and @lo and @hi are literals that will otherwise be assigned a signed - * integer type. - */ -#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi) - static inline bool in_range64(u64 val, u64 start, u64 len) { return (val - start) < len; @@ -326,9 +311,9 @@ static inline bool in_range32(u32 val, u32 start, u32 len) * Use these carefully: no type checking, and uses the arguments * multiple times. Use for obvious constants only. */ -#define MIN(a,b) __cmp(min,a,b) -#define MAX(a,b) __cmp(max,a,b) -#define MIN_T(type,a,b) __cmp(min,(type)(a),(type)(b)) -#define MAX_T(type,a,b) __cmp(max,(type)(a),(type)(b)) +#define MIN(a, b) __cmp(min, a, b) +#define MAX(a, b) __cmp(max, a, b) +#define MIN_T(type, a, b) __cmp(min, (type)(a), (type)(b)) +#define MAX_T(type, a, b) __cmp(max, (type)(a), (type)(b)) #endif /* _LINUX_MINMAX_H */ diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index c0fea6ca5076..69e110c2b86a 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -76,7 +76,7 @@ struct device; struct attribute_group; -struct miscdevice { +struct miscdevice { int minor; const char *name; const struct file_operations *fops; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index cc647992f3d1..0c48b20f818a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1245,6 +1245,7 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_CRYPTO = 0x1a, + MLX5_CAP_SHAMPO = 0x1d, MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, @@ -1470,6 +1471,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_MACSEC(mdev, cap)\ MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap) +#define MLX5_CAP_SHAMPO(mdev, cap) \ + MLX5_GET(shampo_cap, mdev->caps.hca[MLX5_CAP_SHAMPO]->cur, cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fc7e6153b73d..af86097641b0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -160,9 +160,12 @@ enum { MLX5_REG_MIRC = 0x9162, MLX5_REG_MTPTM = 0x9180, MLX5_REG_MTCTR = 0x9181, + MLX5_REG_MRTCQ = 0x9182, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, + MLX5_REG_NIC_CAP = 0xC00D, MLX5_REG_DTOR = 0xC00E, + MLX5_REG_VHCA_ICM_CTRL = 0xC010, }; enum mlx5_qpts_trust_state { @@ -524,6 +527,7 @@ enum { * creation/deletion on drivers rescan. Unset during device attach. */ MLX5_PRIV_FLAGS_DETACH = 1 << 2, + MLX5_PRIV_FLAGS_SWITCH_LEGACY = 1 << 3, }; struct mlx5_adev { @@ -690,7 +694,6 @@ struct mlx5_timer { struct timecounter tc; u32 nominal_c_mult; unsigned long overflow_period; - struct delayed_work overflow_work; }; struct mlx5_clock { @@ -1202,6 +1205,12 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } +static inline bool mlx5_core_same_coredev_type(const struct mlx5_core_dev *dev1, + const struct mlx5_core_dev *dev2) +{ + return dev1->coredev_type == dev2->coredev_type; +} + static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 438db888bde0..2a69d9d71276 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -163,7 +163,7 @@ struct mlx5_flow_destination { u32 tir_num; u32 ft_num; struct mlx5_flow_table *ft; - u32 counter_id; + struct mlx5_fc *counter; struct { u16 num; u16 vhca_id; @@ -299,6 +299,8 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); +struct mlx5_fc *mlx5_fc_local_create(u32 counter_id, u32 offset, u32 bulk_size); +void mlx5_fc_local_destroy(struct mlx5_fc *counter); u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4fbbcf35498b..4f3716e124c9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1095,7 +1095,9 @@ struct mlx5_ifc_qos_cap_bits { u8 log_esw_max_sched_depth[0x4]; u8 reserved_at_10[0x10]; - u8 reserved_at_20[0xb]; + u8 reserved_at_20[0x9]; + u8 esw_cross_esw_sched[0x1]; + u8 reserved_at_2a[0x1]; u8 log_max_qos_nic_queue_group[0x5]; u8 reserved_at_30[0x10]; @@ -1103,7 +1105,8 @@ struct mlx5_ifc_qos_cap_bits { u8 packet_pacing_min_rate[0x20]; - u8 reserved_at_80[0x10]; + u8 reserved_at_80[0xb]; + u8 log_esw_max_rate_limit[0x5]; u8 packet_pacing_rate_table_size[0x10]; u8 esw_element_type[0x10]; @@ -1590,12 +1593,14 @@ enum { MLX5_STEERING_FORMAT_CONNECTX_5 = 0, MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, MLX5_STEERING_FORMAT_CONNECTX_7 = 2, + MLX5_STEERING_FORMAT_CONNECTX_8 = 3, }; struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x6]; u8 page_request_disable[0x1]; - u8 reserved_at_7[0x9]; + u8 abs_native_port_num[0x1]; + u8 reserved_at_8[0x8]; u8 shared_object_to_user_object_allowed[0x1]; u8 reserved_at_13[0xe]; u8 vhca_resource_manager[0x1]; @@ -1825,7 +1830,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 regexp_params[0x1]; u8 uar_sz[0x6]; u8 port_selection_cap[0x1]; - u8 reserved_at_251[0x1]; + u8 nic_cap_reg[0x1]; u8 umem_uid_0[0x1]; u8 reserved_at_253[0x5]; u8 log_pg_sz[0x8]; @@ -2119,7 +2124,9 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 migration_in_chunks[0x1]; u8 reserved_at_d1[0x1]; u8 sf_eq_usage[0x1]; - u8 reserved_at_d3[0xd]; + u8 reserved_at_d3[0x5]; + u8 multiplane[0x1]; + u8 reserved_at_d9[0x7]; u8 cross_vhca_object_to_object_supported[0x20]; @@ -2322,7 +2329,9 @@ struct mlx5_ifc_wq_bits { u8 headers_mkey[0x20]; u8 shampo_enable[0x1]; - u8 reserved_at_1e1[0x4]; + u8 reserved_at_1e1[0x1]; + u8 shampo_mode[0x2]; + u8 reserved_at_1e4[0x1]; u8 log_reservation_size[0x3]; u8 reserved_at_1e8[0x5]; u8 log_max_num_of_packets_per_reservation[0x3]; @@ -3320,6 +3329,14 @@ struct mlx5_ifc_dropped_packet_logged_bits { u8 reserved_at_0[0xe0]; }; +struct mlx5_ifc_nic_cap_reg_bits { + u8 reserved_at_0[0x1a]; + u8 vhca_icm_ctrl[0x1]; + u8 reserved_at_1b[0x5]; + + u8 reserved_at_20[0x60]; +}; + struct mlx5_ifc_default_timeout_bits { u8 to_multiplier[0x3]; u8 reserved_at_3[0x9]; @@ -3356,6 +3373,18 @@ struct mlx5_ifc_dtor_reg_bits { u8 reserved_at_1c0[0x20]; }; +struct mlx5_ifc_vhca_icm_ctrl_reg_bits { + u8 vhca_id_valid[0x1]; + u8 reserved_at_1[0xf]; + u8 vhca_id[0x10]; + + u8 reserved_at_20[0xa0]; + + u8 cur_alloc_icm[0x20]; + + u8 reserved_at_e0[0x120]; +}; + enum { MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN = 0x1, MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR = 0x2, @@ -3694,6 +3723,22 @@ struct mlx5_ifc_crypto_cap_bits { u8 reserved_at_80[0x780]; }; +struct mlx5_ifc_shampo_cap_bits { + u8 reserved_at_0[0x3]; + u8 shampo_log_max_reservation_size[0x5]; + u8 reserved_at_8[0x3]; + u8 shampo_log_min_reservation_size[0x5]; + u8 shampo_min_mss_size[0x10]; + + u8 shampo_header_split[0x1]; + u8 shampo_header_split_data_merge[0x1]; + u8 reserved_at_22[0x1]; + u8 shampo_log_max_headers_entry_size[0x5]; + u8 reserved_at_28[0x18]; + + u8 reserved_at_40[0x7c0]; +}; + union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2; @@ -4103,6 +4148,7 @@ enum { SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC = 0x2, SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP = 0x4, + SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT = 0x5, }; enum { @@ -4111,34 +4157,41 @@ enum { ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2, ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3, ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP = 1 << 4, + ELEMENT_TYPE_CAP_MASK_RATE_LIMIT = 1 << 5, }; enum { TSAR_ELEMENT_TSAR_TYPE_DWRR = 0x0, TSAR_ELEMENT_TSAR_TYPE_ROUND_ROBIN = 0x1, TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2, + TSAR_ELEMENT_TSAR_TYPE_TC_ARB = 0x3, }; enum { TSAR_TYPE_CAP_MASK_DWRR = 1 << 0, TSAR_TYPE_CAP_MASK_ROUND_ROBIN = 1 << 1, TSAR_TYPE_CAP_MASK_ETS = 1 << 2, + TSAR_TYPE_CAP_MASK_TC_ARB = 1 << 3, }; struct mlx5_ifc_tsar_element_bits { - u8 reserved_at_0[0x8]; + u8 traffic_class[0x4]; + u8 reserved_at_4[0x4]; u8 tsar_type[0x8]; u8 reserved_at_10[0x10]; }; struct mlx5_ifc_vport_element_bits { - u8 reserved_at_0[0x10]; + u8 reserved_at_0[0x4]; + u8 eswitch_owner_vhca_id_valid[0x1]; + u8 eswitch_owner_vhca_id[0xb]; u8 vport_number[0x10]; }; struct mlx5_ifc_vport_tc_element_bits { u8 traffic_class[0x4]; - u8 reserved_at_4[0xc]; + u8 eswitch_owner_vhca_id_valid[0x1]; + u8 eswitch_owner_vhca_id[0xb]; u8 vport_number[0x10]; }; @@ -4163,7 +4216,9 @@ struct mlx5_ifc_scheduling_context_bits { u8 max_average_bw[0x20]; - u8 reserved_at_e0[0x120]; + u8 max_bw_obj_id[0x20]; + + u8 reserved_at_100[0x100]; }; struct mlx5_ifc_rqtc_bits { @@ -6324,6 +6379,20 @@ struct mlx5_ifc_modify_other_hca_cap_in_bits { struct mlx5_ifc_other_hca_cap_bits other_capability; }; +struct mlx5_ifc_sw_owner_icm_root_params_bits { + u8 sw_owner_icm_root_1[0x40]; + + u8 sw_owner_icm_root_0[0x40]; +}; + +struct mlx5_ifc_rtc_params_bits { + u8 rtc_id_0[0x20]; + + u8 rtc_id_1[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_flow_table_context_bits { u8 reformat_en[0x1]; u8 decap_en[0x1]; @@ -6342,20 +6411,10 @@ struct mlx5_ifc_flow_table_context_bits { u8 lag_master_next_table_id[0x18]; u8 reserved_at_60[0x60]; + union { - struct { - u8 sw_owner_icm_root_1[0x40]; - - u8 sw_owner_icm_root_0[0x40]; - } sws; - struct { - u8 rtc_id_0[0x20]; - - u8 rtc_id_1[0x20]; - - u8 reserved_at_100[0x40]; - - } hws; + struct mlx5_ifc_sw_owner_icm_root_params_bits sws; + struct mlx5_ifc_rtc_params_bits hws; }; }; @@ -7004,6 +7063,7 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { enum { MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START = 0x1, + MLX5_REFORMAT_CONTEXT_ANCHOR_VLAN_START = 0x2, MLX5_REFORMAT_CONTEXT_ANCHOR_IP_START = 0x7, MLX5_REFORMAT_CONTEXT_ANCHOR_TCP_UDP_START = 0x9, }; @@ -10131,7 +10191,21 @@ struct mlx5_ifc_pplm_reg_bits { u8 fec_override_admin_200g_2x[0x10]; u8 fec_override_admin_100g_1x[0x10]; - u8 reserved_at_260[0x20]; + u8 reserved_at_260[0x60]; + + u8 fec_override_cap_1600g_8x[0x10]; + u8 fec_override_cap_800g_4x[0x10]; + + u8 fec_override_cap_400g_2x[0x10]; + u8 fec_override_cap_200g_1x[0x10]; + + u8 fec_override_admin_1600g_8x[0x10]; + u8 fec_override_admin_800g_4x[0x10]; + + u8 fec_override_admin_400g_2x[0x10]; + u8 fec_override_admin_200g_1x[0x10]; + + u8 reserved_at_340[0x80]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -10505,7 +10579,9 @@ struct mlx5_ifc_mtutc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x48]; + u8 reserved_at_0[0x1d]; + u8 fec_200G_per_lane_in_pplm[0x1]; + u8 reserved_at_1e[0x2a]; u8 fec_100G_per_lane_in_pplm[0x1]; u8 reserved_at_49[0x1f]; u8 fec_50G_per_lane_in_pplm[0x1]; @@ -10645,7 +10721,8 @@ struct mlx5_ifc_mcam_access_reg_bits3 { u8 regs_63_to_32[0x20]; - u8 regs_31_to_2[0x1e]; + u8 regs_31_to_3[0x1d]; + u8 mrtcq[0x1]; u8 mtctr[0x1]; u8 mtptm[0x1]; }; @@ -13136,4 +13213,12 @@ struct mlx5_ifc_msees_reg_bits { u8 reserved_at_80[0x180]; }; +struct mlx5_ifc_mrtcq_reg_bits { + u8 reserved_at_0[0x40]; + + u8 rt_clock_identity[0x40]; + + u8 reserved_at_80[0x180]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index c39c4945946c..7b1068ddcbb7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -31,6 +31,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -710,7 +711,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * we don't rely on for anything - the mm_lock_seq read against which we * need ordering is below. */ - if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq)) + if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq.sequence)) return false; if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) @@ -727,7 +728,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * after it has been unlocked. * This pairs with RELEASE semantics in vma_end_write_all(). */ - if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) { + if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&vma->vm_mm->mm_lock_seq))) { up_read(&vma->vm_lock->lock); return false; } @@ -742,7 +743,7 @@ static inline void vma_end_read(struct vm_area_struct *vma) } /* WARNING! Can only be used if mmap_lock is expected to be write-locked */ -static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) +static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq) { mmap_assert_write_locked(vma->vm_mm); @@ -750,7 +751,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ - *mm_lock_seq = vma->vm_mm->mm_lock_seq; + *mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence; return (vma->vm_lock_seq == *mm_lock_seq); } @@ -761,7 +762,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) */ static inline void vma_start_write(struct vm_area_struct *vma) { - int mm_lock_seq; + unsigned int mm_lock_seq; if (__is_vma_write_locked(vma, &mm_lock_seq)) return; @@ -779,7 +780,7 @@ static inline void vma_start_write(struct vm_area_struct *vma) static inline void vma_assert_write_locked(struct vm_area_struct *vma) { - int mm_lock_seq; + unsigned int mm_lock_seq; VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } @@ -2319,6 +2320,7 @@ extern void pagefault_out_of_memory(void); struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ + bool reclaim_pt; /* Need reclaim page tables? */ zap_flags_t zap_flags; /* Extra flags for zapping */ }; @@ -2990,18 +2992,15 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ -static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) +static inline void __pagetable_ctor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); - if (!ptlock_init(ptdesc)) - return false; __folio_set_pgtable(folio); lruvec_stat_add_folio(folio, NR_PAGETABLE); - return true; } -static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) +static inline void pagetable_dtor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); @@ -3010,7 +3009,29 @@ static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) lruvec_stat_sub_folio(folio, NR_PAGETABLE); } -pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); +static inline void pagetable_dtor_free(struct ptdesc *ptdesc) +{ + pagetable_dtor(ptdesc); + pagetable_free(ptdesc); +} + +static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) +{ + if (!ptlock_init(ptdesc)) + return false; + __pagetable_ctor(ptdesc); + return true; +} + +pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); +static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, + pmd_t *pmdvalp) +{ + pte_t *pte; + + __cond_lock(RCU, pte = ___pte_offset_map(pmd, addr, pmdvalp)); + return pte; +} static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr) { return __pte_offset_map(pmd, addr, NULL); @@ -3023,7 +3044,8 @@ static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, { pte_t *pte; - __cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)); + __cond_lock(RCU, __cond_lock(*ptlp, + pte = __pte_offset_map_lock(mm, pmd, addr, ptlp))); return pte; } @@ -3077,14 +3099,6 @@ static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) return ptlock_init(ptdesc); } -static inline void pmd_ptlock_free(struct ptdesc *ptdesc) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(ptdesc->pmd_huge_pte, ptdesc_page(ptdesc)); -#endif - ptlock_free(ptdesc); -} - #define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte) #else @@ -3095,7 +3109,6 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; } -static inline void pmd_ptlock_free(struct ptdesc *ptdesc) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) @@ -3110,24 +3123,13 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); - if (!pmd_ptlock_init(ptdesc)) return false; - __folio_set_pgtable(folio); - lruvec_stat_add_folio(folio, NR_PAGETABLE); + ptdesc_pmd_pts_init(ptdesc); + __pagetable_ctor(ptdesc); return true; } -static inline void pagetable_pmd_dtor(struct ptdesc *ptdesc) -{ - struct folio *folio = ptdesc_folio(ptdesc); - - pmd_ptlock_free(ptdesc); - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); -} - /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be @@ -3149,18 +3151,17 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); - - __folio_set_pgtable(folio); - lruvec_stat_add_folio(folio, NR_PAGETABLE); + __pagetable_ctor(ptdesc); } -static inline void pagetable_pud_dtor(struct ptdesc *ptdesc) +static inline void pagetable_p4d_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); + __pagetable_ctor(ptdesc); +} - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); +static inline void pagetable_pgd_ctor(struct ptdesc *ptdesc) +{ + __pagetable_ctor(ptdesc); } extern void __init pagecache_init(void); @@ -3313,6 +3314,8 @@ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admi extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void exit_mmap(struct mm_struct *); int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); +bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, bool write); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, @@ -3360,9 +3363,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, return __get_unmapped_area(file, addr, len, pgoff, flags, 0); } -extern unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, - struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, @@ -3420,15 +3420,13 @@ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); +extern vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ int expand_stack_locked(struct vm_area_struct *vma, unsigned long address); struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr); -/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ -int expand_downwards(struct vm_area_struct *vma, unsigned long address); - /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, @@ -4085,45 +4083,6 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, extern int sysctl_nr_trim_pages; -#ifdef CONFIG_PRINTK -void mem_dump_obj(void *object); -#else -static inline void mem_dump_obj(void *object) {} -#endif - -/** - * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and - * handle them. - * @seals: the seals to check - * @vma: the vma to operate on - * - * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper - * check/handling on the vma flags. Return 0 if check pass, or <0 for errors. - */ -static inline int seal_check_write(int seals, struct vm_area_struct *vma) -{ - if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vm_flags_clear(vma, VM_MAYWRITE); - } - - return 0; -} - #ifdef CONFIG_ANON_VMA_NAME int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, @@ -4175,6 +4134,23 @@ static inline int do_mseal(unsigned long start, size_t len_in, unsigned long fla } #endif +/* + * user_alloc_needs_zeroing checks if a user folio from page allocator needs to + * be zeroed or not. + */ +static inline bool user_alloc_needs_zeroing(void) +{ + /* + * for user folios, arch with cache aliasing requires cache flush and + * arc changes folio->flags to make icache coherent with dcache, so + * always return false to make caller use + * clear_user_page()/clear_user_highpage(). + */ + return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() || + !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, + &init_on_alloc); +} + int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 1b6a917fffa4..f9157a0c42a5 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -133,31 +133,25 @@ static inline int lru_hist_from_seq(unsigned long seq) return seq % NR_HIST_GENS; } -static inline int lru_tier_from_refs(int refs) +static inline int lru_tier_from_refs(int refs, bool workingset) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); - /* see the comment in folio_lru_refs() */ - return order_base_2(refs + 1); + /* see the comment on MAX_NR_TIERS */ + return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs); } static inline int folio_lru_refs(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); - bool workingset = flags & BIT(PG_workingset); + if (!(flags & BIT(PG_referenced))) + return 0; /* - * Return the number of accesses beyond PG_referenced, i.e., N-1 if the - * total number of accesses is N>1, since N=0,1 both map to the first - * tier. lru_tier_from_refs() will account for this off-by-one. Also see - * the comment on MAX_NR_TIERS. + * Return the total number of accesses including PG_referenced. Also see + * the comment on LRU_REFS_FLAGS. */ - return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; -} - -static inline void folio_clear_lru_refs(struct folio *folio) -{ - set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); + return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1; } static inline int folio_lru_gen(struct folio *folio) @@ -223,11 +217,43 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } +static inline unsigned long lru_gen_folio_seq(struct lruvec *lruvec, struct folio *folio, + bool reclaiming) +{ + int gen; + int type = folio_is_file_lru(folio); + struct lru_gen_folio *lrugen = &lruvec->lrugen; + + /* + * +-----------------------------------+-----------------------------------+ + * | Accessed through page tables and | Accessed through file descriptors | + * | promoted by folio_update_gen() | and protected by folio_inc_gen() | + * +-----------------------------------+-----------------------------------+ + * | PG_active (set while isolated) | | + * +-----------------+-----------------+-----------------+-----------------+ + * | PG_workingset | PG_referenced | PG_workingset | LRU_REFS_FLAGS | + * +-----------------------------------+-----------------------------------+ + * |<---------- MIN_NR_GENS ---------->| | + * |<---------------------------- MAX_NR_GENS ---------------------------->| + */ + if (folio_test_active(folio)) + gen = MIN_NR_GENS - folio_test_workingset(folio); + else if (reclaiming) + gen = MAX_NR_GENS; + else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) || + (folio_test_reclaim(folio) && + (folio_test_dirty(folio) || folio_test_writeback(folio)))) + gen = MIN_NR_GENS; + else + gen = MAX_NR_GENS - folio_test_workingset(folio); + + return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type])); +} + static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; - unsigned long mask; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); @@ -237,40 +263,12 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, if (folio_test_unevictable(folio) || !lrugen->enabled) return false; - /* - * There are four common cases for this page: - * 1. If it's hot, i.e., freshly faulted in, add it to the youngest - * generation, and it's protected over the rest below. - * 2. If it can't be evicted immediately, i.e., a dirty page pending - * writeback, add it to the second youngest generation. - * 3. If it should be evicted first, e.g., cold and clean from - * folio_rotate_reclaimable(), add it to the oldest generation. - * 4. Everything else falls between 2 & 3 above and is added to the - * second oldest generation if it's considered inactive, or the - * oldest generation otherwise. See lru_gen_is_active(). - */ - if (folio_test_active(folio)) - seq = lrugen->max_seq; - else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || - (folio_test_reclaim(folio) && - (folio_test_dirty(folio) || folio_test_writeback(folio)))) - seq = lrugen->max_seq - 1; - else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) - seq = lrugen->min_seq[type]; - else - seq = lrugen->min_seq[type] + 1; + seq = lru_gen_folio_seq(lruvec, folio, reclaiming); gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ - mask = LRU_GEN_MASK; - /* - * Don't clear PG_workingset here because it can affect PSI accounting - * if the activation is due to workingset refault. - */ - if (folio_test_active(folio)) - mask |= LRU_REFS_MASK | BIT(PG_referenced) | BIT(PG_active); - set_mask_bits(&folio->flags, mask, flags); + set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ @@ -564,9 +562,9 @@ static inline pte_marker copy_pte_marker( * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * - * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. + * Returns true if an uffd-wp pte was installed, false otherwise. */ -static inline void +static inline bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { @@ -583,7 +581,7 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) - return; + return false; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) @@ -596,10 +594,13 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; - if (unlikely(arm_uffd_pte)) + if (unlikely(arm_uffd_pte)) { set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); + return true; + } #endif + return false; } static inline bool vma_has_recency(struct vm_area_struct *vma) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..6b27db7f9496 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -438,13 +438,16 @@ FOLIO_MATCH(compound_head, _head_2a); * struct ptdesc - Memory descriptor for page tables. * @__page_flags: Same as page flags. Powerpc only. * @pt_rcu_head: For freeing page table pages. - * @pt_list: List of used page tables. Used for s390 and x86. + * @pt_list: List of used page tables. Used for s390 gmap shadow pages + * (which are not linked into the user page tables) and x86 + * pgds. * @_pt_pad_1: Padding that aliases with page's compound head. * @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs. * @__page_mapping: Aliases with page->mapping. Unused for page tables. * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +474,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +522,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ @@ -697,7 +729,7 @@ struct vm_area_struct { * counter reuse can only lead to occasional unnecessary use of the * slowpath. */ - int vm_lock_seq; + unsigned int vm_lock_seq; /* Unstable RCU readers are allowed to read this. */ struct vma_lock *vm_lock; #endif @@ -891,6 +923,9 @@ struct mm_struct { * Roughly speaking, incrementing the sequence number is * equivalent to releasing locks on VMAs; reading the sequence * number can be part of taking a read lock on a VMA. + * Incremented every time mmap_lock is write-locked/unlocked. + * Initialized to 0, therefore odd values indicate mmap_lock + * is write-locked and even values that it's released. * * Can be modified under write mmap_lock using RELEASE * semantics. @@ -899,7 +934,7 @@ struct mm_struct { * Can be read with ACQUIRE semantics if not holding write * mmap_lock. */ - int mm_lock_seq; + seqcount_t mm_lock_seq; #endif @@ -1371,6 +1406,7 @@ enum tlb_flush_reason { TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, TLB_REMOTE_SEND_IPI, + TLB_REMOTE_WRONG_CPU, NR_TLB_FLUSH_REASONS, }; diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index de9dc20b01ba..45a21faa3ff6 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -71,6 +71,91 @@ static inline void mmap_assert_write_locked(const struct mm_struct *mm) } #ifdef CONFIG_PER_VMA_LOCK + +static inline void mm_lock_seqcount_init(struct mm_struct *mm) +{ + seqcount_init(&mm->mm_lock_seq); +} + +static inline void mm_lock_seqcount_begin(struct mm_struct *mm) +{ + do_raw_write_seqcount_begin(&mm->mm_lock_seq); +} + +static inline void mm_lock_seqcount_end(struct mm_struct *mm) +{ + ASSERT_EXCLUSIVE_WRITER(mm->mm_lock_seq); + do_raw_write_seqcount_end(&mm->mm_lock_seq); +} + +static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) +{ + /* + * Since mmap_lock is a sleeping lock, and waiting for it to become + * unlocked is more or less equivalent with taking it ourselves, don't + * bother with the speculative path if mmap_lock is already write-locked + * and take the slow path, which takes the lock. + */ + return raw_seqcount_try_begin(&mm->mm_lock_seq, *seq); +} + +static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) +{ + return read_seqcount_retry(&mm->mm_lock_seq, seq); +} + +#else /* CONFIG_PER_VMA_LOCK */ + +static inline void mm_lock_seqcount_init(struct mm_struct *mm) {} +static inline void mm_lock_seqcount_begin(struct mm_struct *mm) {} +static inline void mm_lock_seqcount_end(struct mm_struct *mm) {} + +static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) +{ + return false; +} + +static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) +{ + return true; +} + +#endif /* CONFIG_PER_VMA_LOCK */ + +static inline void mmap_init_lock(struct mm_struct *mm) +{ + init_rwsem(&mm->mmap_lock); + mm_lock_seqcount_init(mm); +} + +static inline void mmap_write_lock(struct mm_struct *mm) +{ + __mmap_lock_trace_start_locking(mm, true); + down_write(&mm->mmap_lock); + mm_lock_seqcount_begin(mm); + __mmap_lock_trace_acquire_returned(mm, true, true); +} + +static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) +{ + __mmap_lock_trace_start_locking(mm, true); + down_write_nested(&mm->mmap_lock, subclass); + mm_lock_seqcount_begin(mm); + __mmap_lock_trace_acquire_returned(mm, true, true); +} + +static inline int mmap_write_lock_killable(struct mm_struct *mm) +{ + int ret; + + __mmap_lock_trace_start_locking(mm, true); + ret = down_write_killable(&mm->mmap_lock); + if (!ret) + mm_lock_seqcount_begin(mm); + __mmap_lock_trace_acquire_returned(mm, true, ret == 0); + return ret; +} + /* * Drop all currently-held per-VMA locks. * This is called from the mmap_lock implementation directly before releasing @@ -82,46 +167,7 @@ static inline void mmap_assert_write_locked(const struct mm_struct *mm) static inline void vma_end_write_all(struct mm_struct *mm) { mmap_assert_write_locked(mm); - /* - * Nobody can concurrently modify mm->mm_lock_seq due to exclusive - * mmap_lock being held. - * We need RELEASE semantics here to ensure that preceding stores into - * the VMA take effect before we unlock it with this store. - * Pairs with ACQUIRE semantics in vma_start_read(). - */ - smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1); -} -#else -static inline void vma_end_write_all(struct mm_struct *mm) {} -#endif - -static inline void mmap_init_lock(struct mm_struct *mm) -{ - init_rwsem(&mm->mmap_lock); -} - -static inline void mmap_write_lock(struct mm_struct *mm) -{ - __mmap_lock_trace_start_locking(mm, true); - down_write(&mm->mmap_lock); - __mmap_lock_trace_acquire_returned(mm, true, true); -} - -static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) -{ - __mmap_lock_trace_start_locking(mm, true); - down_write_nested(&mm->mmap_lock, subclass); - __mmap_lock_trace_acquire_returned(mm, true, true); -} - -static inline int mmap_write_lock_killable(struct mm_struct *mm) -{ - int ret; - - __mmap_lock_trace_start_locking(mm, true); - ret = down_write_killable(&mm->mmap_lock); - __mmap_lock_trace_acquire_returned(mm, true, ret == 0); - return ret; + mm_lock_seqcount_end(mm); } static inline void mmap_write_unlock(struct mm_struct *mm) diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 56972bd78462..01e0f591a20b 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -57,6 +57,7 @@ struct mmc_command { #define MMC_RSP_NONE (0) #define MMC_RSP_R1 (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE) #define MMC_RSP_R1B (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE|MMC_RSP_BUSY) +#define MMC_RSP_R1B_NO_CRC (MMC_RSP_PRESENT|MMC_RSP_OPCODE|MMC_RSP_BUSY) #define MMC_RSP_R2 (MMC_RSP_PRESENT|MMC_RSP_136|MMC_RSP_CRC) #define MMC_RSP_R3 (MMC_RSP_PRESENT) #define MMC_RSP_R4 (MMC_RSP_PRESENT) @@ -64,9 +65,6 @@ struct mmc_command { #define MMC_RSP_R6 (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE) #define MMC_RSP_R7 (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE) -/* Can be used by core to poll after switch to MMC HS mode */ -#define MMC_RSP_R1_NO_CRC (MMC_RSP_PRESENT|MMC_RSP_OPCODE) - #define mmc_resp_type(cmd) ((cmd)->flags & (MMC_RSP_PRESENT|MMC_RSP_136|MMC_RSP_CRC|MMC_RSP_BUSY|MMC_RSP_OPCODE)) /* diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f166d6611ddb..68f09a955a90 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -590,6 +590,14 @@ static inline struct mmc_host *mmc_from_priv(void *priv) return container_of(priv, struct mmc_host, private); } +#ifdef CONFIG_MMC_CRYPTO +static inline struct mmc_host * +mmc_from_crypto_profile(struct blk_crypto_profile *profile) +{ + return container_of(profile, struct mmc_host, crypto_profile); +} +#endif + #define mmc_host_is_spi(host) ((host)->caps & MMC_CAP_SPI) #define mmc_dev(x) ((x)->parent) diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index d7cb1e5ecbda..a0a3894900ed 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -9,10 +9,12 @@ struct page; struct vm_area_struct; struct mm_struct; struct vma_iterator; +struct vma_merge_struct; void dump_page(const struct page *page, const char *reason); void dump_vma(const struct vm_area_struct *vma); void dump_mm(const struct mm_struct *mm); +void dump_vmg(const struct vma_merge_struct *vmg, const char *reason); void vma_iter_dump_tree(const struct vma_iterator *vmi); #ifdef CONFIG_DEBUG_VM @@ -87,6 +89,15 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi); } \ unlikely(__ret_warn_once); \ }) +#define VM_WARN_ON_VMG(cond, vmg) ({ \ + int __ret_warn = !!(cond); \ + \ + if (unlikely(__ret_warn)) { \ + dump_vmg(vmg, "VM_WARN_ON_VMG(" __stringify(cond)")"); \ + WARN_ON(1); \ + } \ + unlikely(__ret_warn); \ +}) #define VM_WARN_ON(cond) (void)WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) @@ -104,9 +115,10 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi); #define VM_WARN_ON_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE_MM(cond, mm) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ON_VMG(cond, vmg) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) -#endif +#endif /* CONFIG_DEBUG_VM */ #ifdef CONFIG_DEBUG_VM_IRQSOFF #define VM_WARN_ON_IRQS_ENABLED() WARN_ON_ONCE(!irqs_disabled()) diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index bbaec80c78c5..ac01dc4eb2ce 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -24,6 +24,7 @@ static inline void leave_mm(void) { } #ifndef task_cpu_possible_mask # define task_cpu_possible_mask(p) cpu_possible_mask # define task_cpu_possible(cpu, p) true +# define task_cpu_fallback_mask(p) housekeeping_cpumask(HK_TYPE_TICK) #else # define task_cpu_possible(cpu, p) cpumask_test_cpu((cpu), task_cpu_possible_mask(p)) #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b36124145a16..9540b41894da 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -332,66 +332,88 @@ enum lruvec_flags { #endif /* !__GENERATING_BOUNDS_H */ /* - * Evictable pages are divided into multiple generations. The youngest and the + * Evictable folios are divided into multiple generations. The youngest and the * oldest generation numbers, max_seq and min_seq, are monotonically increasing. * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while - * a page is on one of lrugen->folios[]. Otherwise it stores 0. + * a folio is on one of lrugen->folios[]. Otherwise it stores 0. * - * A page is added to the youngest generation on faulting. The aging needs to - * check the accessed bit at least twice before handing this page over to the - * eviction. The first check takes care of the accessed bit set on the initial - * fault; the second check makes sure this page hasn't been used since then. - * This process, AKA second chance, requires a minimum of two generations, - * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive - * LRU, e.g., /proc/vmstat, these two generations are considered active; the - * rest of generations, if they exist, are considered inactive. See - * lru_gen_is_active(). + * After a folio is faulted in, the aging needs to check the accessed bit at + * least twice before handing this folio over to the eviction. The first check + * clears the accessed bit from the initial fault; the second check makes sure + * this folio hasn't been used since then. This process, AKA second chance, + * requires a minimum of two generations, hence MIN_NR_GENS. And to maintain ABI + * compatibility with the active/inactive LRU, e.g., /proc/vmstat, these two + * generations are considered active; the rest of generations, if they exist, + * are considered inactive. See lru_gen_is_active(). * - * PG_active is always cleared while a page is on one of lrugen->folios[] so - * that the aging needs not to worry about it. And it's set again when a page - * considered active is isolated for non-reclaiming purposes, e.g., migration. - * See lru_gen_add_folio() and lru_gen_del_folio(). + * PG_active is always cleared while a folio is on one of lrugen->folios[] so + * that the sliding window needs not to worry about it. And it's set again when + * a folio considered active is isolated for non-reclaiming purposes, e.g., + * migration. See lru_gen_add_folio() and lru_gen_del_folio(). * * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits - * in folio->flags. + * in folio->flags, masked by LRU_GEN_MASK. */ #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U /* - * Each generation is divided into multiple tiers. A page accessed N times - * through file descriptors is in tier order_base_2(N). A page in the first tier - * (N=0,1) is marked by PG_referenced unless it was faulted in through page - * tables or read ahead. A page in any other tier (N>1) is marked by - * PG_referenced and PG_workingset. This implies a minimum of two tiers is - * supported without using additional bits in folio->flags. + * Each generation is divided into multiple tiers. A folio accessed N times + * through file descriptors is in tier order_base_2(N). A folio in the first + * tier (N=0,1) is marked by PG_referenced unless it was faulted in through page + * tables or read ahead. A folio in the last tier (MAX_NR_TIERS-1) is marked by + * PG_workingset. A folio in any other tier (1flags. * * In contrast to moving across generations which requires the LRU lock, moving * across tiers only involves atomic operations on folio->flags and therefore * has a negligible cost in the buffered access path. In the eviction path, - * comparisons of refaulted/(evicted+protected) from the first tier and the - * rest infer whether pages accessed multiple times through file descriptors - * are statistically hot and thus worth protecting. + * comparisons of refaulted/(evicted+protected) from the first tier and the rest + * infer whether folios accessed multiple times through file descriptors are + * statistically hot and thus worth protecting. * * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in - * folio->flags. + * folio->flags, masked by LRU_REFS_MASK. */ #define MAX_NR_TIERS 4U #ifndef __GENERATING_BOUNDS_H -struct lruvec; -struct page_vma_mapped_walk; - #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) +/* + * For folios accessed multiple times through file descriptors, + * lru_gen_inc_refs() sets additional bits of LRU_REFS_WIDTH in folio->flags + * after PG_referenced, then PG_workingset after LRU_REFS_WIDTH. After all its + * bits are set, i.e., LRU_REFS_FLAGS|BIT(PG_workingset), a folio is lazily + * promoted into the second oldest generation in the eviction path. And when + * folio_inc_gen() does that, it clears LRU_REFS_FLAGS so that + * lru_gen_inc_refs() can start over. Note that for this case, LRU_REFS_MASK is + * only valid when PG_referenced is set. + * + * For folios accessed multiple times through page tables, folio_update_gen() + * from a page table walk or lru_gen_set_refs() from a rmap walk sets + * PG_referenced after the accessed bit is cleared for the first time. + * Thereafter, those two paths set PG_workingset and promote folios to the + * youngest generation. Like folio_inc_gen(), folio_update_gen() also clears + * PG_referenced. Note that for this case, LRU_REFS_MASK is not used. + * + * For both cases above, after PG_workingset is set on a folio, it remains until + * this folio is either reclaimed, or "deactivated" by lru_gen_clear_refs(). It + * can be set again if lru_gen_test_recent() returns true upon a refault. + */ +#define LRU_REFS_FLAGS (LRU_REFS_MASK | BIT(PG_referenced)) + +struct lruvec; +struct page_vma_mapped_walk; + #ifdef CONFIG_LRU_GEN enum { @@ -406,8 +428,6 @@ enum { NR_LRU_GEN_CAPS }; -#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) - #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) @@ -421,12 +441,11 @@ enum { /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are - * stored in min_seq[] separately for anon and file types as clean file pages - * can be evicted regardless of swap constraints. - * - * Normally anon and file min_seq are in sync. But if swapping is constrained, - * e.g., out of swap space, file min_seq is allowed to advance and leave anon - * min_seq behind. + * stored in min_seq[] separately for anon and file types so that they can be + * incremented independently. Ideally min_seq[] are kept in sync when both anon + * and file types are evictable. However, to adapt to situations like extreme + * swappiness, they are allowed to be out of sync by at most + * MAX_NR_GENS-MIN_NR_GENS-1. * * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. @@ -446,8 +465,8 @@ struct lru_gen_folio { unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; /* the exponential moving average of evicted+protected */ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; - /* the first tier doesn't need protection, hence the minus one */ - unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; + /* can only be modified under the LRU lock */ + unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; @@ -498,7 +517,7 @@ struct lru_gen_mm_walk { int mm_stats[NR_MM_STATS]; /* total batched items */ int batched; - bool can_swap; + int swappiness; bool force_scan; }; diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4338b1b4ac44..d67614f7b7f1 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -700,6 +700,8 @@ struct x86_cpu_id { #define X86_FAMILY_ANY 0 #define X86_MODEL_ANY 0 #define X86_STEPPING_ANY 0 +#define X86_STEP_MIN 0 +#define X86_STEP_MAX 0xf #define X86_FEATURE_ANY 0 /* Same as FPU, you can't test for that */ /* diff --git a/include/linux/module.h b/include/linux/module.h index 94acbacdcdf1..23792d5d7b74 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -52,9 +52,9 @@ struct module_kobject { struct module_attribute { struct attribute attr; - ssize_t (*show)(struct module_attribute *, struct module_kobject *, + ssize_t (*show)(const struct module_attribute *, struct module_kobject *, char *); - ssize_t (*store)(struct module_attribute *, struct module_kobject *, + ssize_t (*store)(const struct module_attribute *, struct module_kobject *, const char *, size_t count); void (*setup)(struct module *, const char *); int (*test)(struct module *); @@ -67,10 +67,10 @@ struct module_version_attribute { const char *version; }; -extern ssize_t __modver_version_show(struct module_attribute *, +extern ssize_t __modver_version_show(const struct module_attribute *, struct module_kobject *, char *); -extern struct module_attribute module_uevent; +extern const struct module_attribute module_uevent; /* These are either module local, or the kernel's dummy ones. */ extern int init_module(void); @@ -275,7 +275,7 @@ extern typeof(name) __mod_device_table__##type##__##name \ #else #define MODULE_VERSION(_version) \ MODULE_INFO(version, _version); \ - static struct module_version_attribute __modver_attr \ + static const struct module_version_attribute __modver_attr \ __used __section("__modver") \ __aligned(__alignof__(struct module_version_attribute)) \ = { \ @@ -430,7 +430,7 @@ struct module { /* Exported symbols */ const struct kernel_symbol *syms; - const s32 *crcs; + const u32 *crcs; unsigned int num_syms; #ifdef CONFIG_ARCH_USES_CFI_TRAPS @@ -448,7 +448,7 @@ struct module { /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; - const s32 *gpl_crcs; + const u32 *gpl_crcs; bool using_gplonly_symbols; #ifdef CONFIG_MODULE_SIG @@ -773,7 +773,8 @@ void *__module_writable_address(struct module *mod, void *loc); static inline void *module_writable_address(struct module *mod, void *loc) { - if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod) + if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod || + mod->state != MODULE_STATE_UNFORMED) return loc; return __module_writable_address(mod, loc); } diff --git a/include/linux/mount.h b/include/linux/mount.h index c34c18b4e8f3..dcc17ce8a959 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -50,7 +50,7 @@ struct path; #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ - MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB) + MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED) #define MNT_INTERNAL 0x4000 @@ -64,7 +64,6 @@ struct path; #define MNT_SYNC_UMOUNT 0x2000000 #define MNT_MARKED 0x4000000 #define MNT_UMOUNT 0x8000000 -#define MNT_ONRB 0x10000000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ @@ -76,7 +75,7 @@ struct vfsmount { static inline struct mnt_idmap *mnt_idmap(const struct vfsmount *mnt) { /* Pairs with smp_store_release() in do_idmap_mount(). */ - return smp_load_acquire(&mnt->mnt_idmap); + return READ_ONCE(mnt->mnt_idmap); } extern int mnt_want_write(struct vfsmount *mnt); @@ -114,7 +113,7 @@ extern struct vfsmount *kern_mount(struct file_system_type *); extern void kern_unmount(struct vfsmount *mnt); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); -extern long do_mount(const char *, const char __user *, +int do_mount(const char *, const char __user *, const char *, unsigned long, void *); extern struct vfsmount *collect_mounts(const struct path *); extern void drop_collected_mounts(struct vfsmount *); diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 9dd4bf157255..58a2401e4b55 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -146,9 +146,9 @@ struct mr_mfc { unsigned long last_assert; int minvif; int maxvif; - unsigned long bytes; - unsigned long pkt; - unsigned long wrong_if; + atomic_long_t bytes; + atomic_long_t pkt; + atomic_long_t wrong_if; unsigned long lastuse; unsigned char ttls[MAXVIFS]; refcount_t refcount; diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h new file mode 100644 index 000000000000..4d9b736ff8b7 --- /dev/null +++ b/include/linux/mtd/nand-qpic-common.h @@ -0,0 +1,478 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * QCOM QPIC common APIs header file + * + * Copyright (c) 2023 Qualcomm Inc. + * Authors: Md sadre Alam + * + */ +#ifndef __MTD_NAND_QPIC_COMMON_H__ +#define __MTD_NAND_QPIC_COMMON_H__ + +/* NANDc reg offsets */ +#define NAND_FLASH_CMD 0x00 +#define NAND_ADDR0 0x04 +#define NAND_ADDR1 0x08 +#define NAND_FLASH_CHIP_SELECT 0x0c +#define NAND_EXEC_CMD 0x10 +#define NAND_FLASH_STATUS 0x14 +#define NAND_BUFFER_STATUS 0x18 +#define NAND_DEV0_CFG0 0x20 +#define NAND_DEV0_CFG1 0x24 +#define NAND_DEV0_ECC_CFG 0x28 +#define NAND_AUTO_STATUS_EN 0x2c +#define NAND_DEV1_CFG0 0x30 +#define NAND_DEV1_CFG1 0x34 +#define NAND_READ_ID 0x40 +#define NAND_READ_STATUS 0x44 +#define NAND_DEV_CMD0 0xa0 +#define NAND_DEV_CMD1 0xa4 +#define NAND_DEV_CMD2 0xa8 +#define NAND_DEV_CMD_VLD 0xac +#define SFLASHC_BURST_CFG 0xe0 +#define NAND_ERASED_CW_DETECT_CFG 0xe8 +#define NAND_ERASED_CW_DETECT_STATUS 0xec +#define NAND_EBI2_ECC_BUF_CFG 0xf0 +#define FLASH_BUF_ACC 0x100 + +#define NAND_CTRL 0xf00 +#define NAND_VERSION 0xf08 +#define NAND_READ_LOCATION_0 0xf20 +#define NAND_READ_LOCATION_1 0xf24 +#define NAND_READ_LOCATION_2 0xf28 +#define NAND_READ_LOCATION_3 0xf2c +#define NAND_READ_LOCATION_LAST_CW_0 0xf40 +#define NAND_READ_LOCATION_LAST_CW_1 0xf44 +#define NAND_READ_LOCATION_LAST_CW_2 0xf48 +#define NAND_READ_LOCATION_LAST_CW_3 0xf4c + +/* dummy register offsets, used by qcom_write_reg_dma */ +#define NAND_DEV_CMD1_RESTORE 0xdead +#define NAND_DEV_CMD_VLD_RESTORE 0xbeef + +/* NAND_FLASH_CMD bits */ +#define PAGE_ACC BIT(4) +#define LAST_PAGE BIT(5) + +/* NAND_FLASH_CHIP_SELECT bits */ +#define NAND_DEV_SEL 0 +#define DM_EN BIT(2) + +/* NAND_FLASH_STATUS bits */ +#define FS_OP_ERR BIT(4) +#define FS_READY_BSY_N BIT(5) +#define FS_MPU_ERR BIT(8) +#define FS_DEVICE_STS_ERR BIT(16) +#define FS_DEVICE_WP BIT(23) + +/* NAND_BUFFER_STATUS bits */ +#define BS_UNCORRECTABLE_BIT BIT(8) +#define BS_CORRECTABLE_ERR_MSK 0x1f + +/* NAND_DEVn_CFG0 bits */ +#define DISABLE_STATUS_AFTER_WRITE BIT(4) +#define CW_PER_PAGE 6 +#define CW_PER_PAGE_MASK GENMASK(8, 6) +#define UD_SIZE_BYTES 9 +#define UD_SIZE_BYTES_MASK GENMASK(18, 9) +#define ECC_PARITY_SIZE_BYTES_RS GENMASK(22, 19) +#define SPARE_SIZE_BYTES 23 +#define SPARE_SIZE_BYTES_MASK GENMASK(26, 23) +#define NUM_ADDR_CYCLES 27 +#define NUM_ADDR_CYCLES_MASK GENMASK(29, 27) +#define STATUS_BFR_READ BIT(30) +#define SET_RD_MODE_AFTER_STATUS BIT(31) + +/* NAND_DEVn_CFG0 bits */ +#define DEV0_CFG1_ECC_DISABLE BIT(0) +#define WIDE_FLASH BIT(1) +#define NAND_RECOVERY_CYCLES 2 +#define NAND_RECOVERY_CYCLES_MASK GENMASK(4, 2) +#define CS_ACTIVE_BSY BIT(5) +#define BAD_BLOCK_BYTE_NUM 6 +#define BAD_BLOCK_BYTE_NUM_MASK GENMASK(15, 6) +#define BAD_BLOCK_IN_SPARE_AREA BIT(16) +#define WR_RD_BSY_GAP 17 +#define WR_RD_BSY_GAP_MASK GENMASK(22, 17) +#define ENABLE_BCH_ECC BIT(27) + +/* NAND_DEV0_ECC_CFG bits */ +#define ECC_CFG_ECC_DISABLE BIT(0) +#define ECC_SW_RESET BIT(1) +#define ECC_MODE 4 +#define ECC_MODE_MASK GENMASK(5, 4) +#define ECC_PARITY_SIZE_BYTES_BCH 8 +#define ECC_PARITY_SIZE_BYTES_BCH_MASK GENMASK(12, 8) +#define ECC_NUM_DATA_BYTES 16 +#define ECC_NUM_DATA_BYTES_MASK GENMASK(25, 16) +#define ECC_FORCE_CLK_OPEN BIT(30) + +/* NAND_DEV_CMD1 bits */ +#define READ_ADDR 0 + +/* NAND_DEV_CMD_VLD bits */ +#define READ_START_VLD BIT(0) +#define READ_STOP_VLD BIT(1) +#define WRITE_START_VLD BIT(2) +#define ERASE_START_VLD BIT(3) +#define SEQ_READ_START_VLD BIT(4) + +/* NAND_EBI2_ECC_BUF_CFG bits */ +#define NUM_STEPS 0 + +/* NAND_ERASED_CW_DETECT_CFG bits */ +#define ERASED_CW_ECC_MASK 1 +#define AUTO_DETECT_RES 0 +#define MASK_ECC BIT(ERASED_CW_ECC_MASK) +#define RESET_ERASED_DET BIT(AUTO_DETECT_RES) +#define ACTIVE_ERASED_DET (0 << AUTO_DETECT_RES) +#define CLR_ERASED_PAGE_DET (RESET_ERASED_DET | MASK_ECC) +#define SET_ERASED_PAGE_DET (ACTIVE_ERASED_DET | MASK_ECC) + +/* NAND_ERASED_CW_DETECT_STATUS bits */ +#define PAGE_ALL_ERASED BIT(7) +#define CODEWORD_ALL_ERASED BIT(6) +#define PAGE_ERASED BIT(5) +#define CODEWORD_ERASED BIT(4) +#define ERASED_PAGE (PAGE_ALL_ERASED | PAGE_ERASED) +#define ERASED_CW (CODEWORD_ALL_ERASED | CODEWORD_ERASED) + +/* NAND_READ_LOCATION_n bits */ +#define READ_LOCATION_OFFSET 0 +#define READ_LOCATION_SIZE 16 +#define READ_LOCATION_LAST 31 + +/* Version Mask */ +#define NAND_VERSION_MAJOR_MASK 0xf0000000 +#define NAND_VERSION_MAJOR_SHIFT 28 +#define NAND_VERSION_MINOR_MASK 0x0fff0000 +#define NAND_VERSION_MINOR_SHIFT 16 + +/* NAND OP_CMDs */ +#define OP_PAGE_READ 0x2 +#define OP_PAGE_READ_WITH_ECC 0x3 +#define OP_PAGE_READ_WITH_ECC_SPARE 0x4 +#define OP_PAGE_READ_ONFI_READ 0x5 +#define OP_PROGRAM_PAGE 0x6 +#define OP_PAGE_PROGRAM_WITH_ECC 0x7 +#define OP_PROGRAM_PAGE_SPARE 0x9 +#define OP_BLOCK_ERASE 0xa +#define OP_CHECK_STATUS 0xc +#define OP_FETCH_ID 0xb +#define OP_RESET_DEVICE 0xd + +/* Default Value for NAND_DEV_CMD_VLD */ +#define NAND_DEV_CMD_VLD_VAL (READ_START_VLD | WRITE_START_VLD | \ + ERASE_START_VLD | SEQ_READ_START_VLD) + +/* NAND_CTRL bits */ +#define BAM_MODE_EN BIT(0) + +/* + * the NAND controller performs reads/writes with ECC in 516 byte chunks. + * the driver calls the chunks 'step' or 'codeword' interchangeably + */ +#define NANDC_STEP_SIZE 512 + +/* + * the largest page size we support is 8K, this will have 16 steps/codewords + * of 512 bytes each + */ +#define MAX_NUM_STEPS (SZ_8K / NANDC_STEP_SIZE) + +/* we read at most 3 registers per codeword scan */ +#define MAX_REG_RD (3 * MAX_NUM_STEPS) + +/* ECC modes supported by the controller */ +#define ECC_NONE BIT(0) +#define ECC_RS_4BIT BIT(1) +#define ECC_BCH_4BIT BIT(2) +#define ECC_BCH_8BIT BIT(3) + +/* + * Returns the actual register address for all NAND_DEV_ registers + * (i.e. NAND_DEV_CMD0, NAND_DEV_CMD1, NAND_DEV_CMD2 and NAND_DEV_CMD_VLD) + */ +#define dev_cmd_reg_addr(nandc, reg) ((nandc)->props->dev_cmd_reg_start + (reg)) + +/* Returns the NAND register physical address */ +#define nandc_reg_phys(chip, offset) ((chip)->base_phys + (offset)) + +/* Returns the dma address for reg read buffer */ +#define reg_buf_dma_addr(chip, vaddr) \ + ((chip)->reg_read_dma + \ + ((u8 *)(vaddr) - (u8 *)(chip)->reg_read_buf)) + +#define QPIC_PER_CW_CMD_ELEMENTS 32 +#define QPIC_PER_CW_CMD_SGL 32 +#define QPIC_PER_CW_DATA_SGL 8 + +#define QPIC_NAND_COMPLETION_TIMEOUT msecs_to_jiffies(2000) + +/* + * Flags used in DMA descriptor preparation helper functions + * (i.e. qcom_read_reg_dma/qcom_write_reg_dma/qcom_read_data_dma/qcom_write_data_dma) + */ +/* Don't set the EOT in current tx BAM sgl */ +#define NAND_BAM_NO_EOT BIT(0) +/* Set the NWD flag in current BAM sgl */ +#define NAND_BAM_NWD BIT(1) +/* Finish writing in the current BAM sgl and start writing in another BAM sgl */ +#define NAND_BAM_NEXT_SGL BIT(2) +/* + * Erased codeword status is being used two times in single transfer so this + * flag will determine the current value of erased codeword status register + */ +#define NAND_ERASED_CW_SET BIT(4) + +#define MAX_ADDRESS_CYCLE 5 + +/* + * This data type corresponds to the BAM transaction which will be used for all + * NAND transfers. + * @bam_ce - the array of BAM command elements + * @cmd_sgl - sgl for NAND BAM command pipe + * @data_sgl - sgl for NAND BAM consumer/producer pipe + * @last_data_desc - last DMA desc in data channel (tx/rx). + * @last_cmd_desc - last DMA desc in command channel. + * @txn_done - completion for NAND transfer. + * @bam_ce_pos - the index in bam_ce which is available for next sgl + * @bam_ce_start - the index in bam_ce which marks the start position ce + * for current sgl. It will be used for size calculation + * for current sgl + * @cmd_sgl_pos - current index in command sgl. + * @cmd_sgl_start - start index in command sgl. + * @tx_sgl_pos - current index in data sgl for tx. + * @tx_sgl_start - start index in data sgl for tx. + * @rx_sgl_pos - current index in data sgl for rx. + * @rx_sgl_start - start index in data sgl for rx. + */ +struct bam_transaction { + struct bam_cmd_element *bam_ce; + struct scatterlist *cmd_sgl; + struct scatterlist *data_sgl; + struct dma_async_tx_descriptor *last_data_desc; + struct dma_async_tx_descriptor *last_cmd_desc; + struct completion txn_done; + struct_group(bam_positions, + u32 bam_ce_pos; + u32 bam_ce_start; + u32 cmd_sgl_pos; + u32 cmd_sgl_start; + u32 tx_sgl_pos; + u32 tx_sgl_start; + u32 rx_sgl_pos; + u32 rx_sgl_start; + + ); +}; + +/* + * This data type corresponds to the nand dma descriptor + * @dma_desc - low level DMA engine descriptor + * @list - list for desc_info + * + * @adm_sgl - sgl which will be used for single sgl dma descriptor. Only used by + * ADM + * @bam_sgl - sgl which will be used for dma descriptor. Only used by BAM + * @sgl_cnt - number of SGL in bam_sgl. Only used by BAM + * @dir - DMA transfer direction + */ +struct desc_info { + struct dma_async_tx_descriptor *dma_desc; + struct list_head node; + + union { + struct scatterlist adm_sgl; + struct { + struct scatterlist *bam_sgl; + int sgl_cnt; + }; + }; + enum dma_data_direction dir; +}; + +/* + * holds the current register values that we want to write. acts as a contiguous + * chunk of memory which we use to write the controller registers through DMA. + */ +struct nandc_regs { + __le32 cmd; + __le32 addr0; + __le32 addr1; + __le32 chip_sel; + __le32 exec; + + __le32 cfg0; + __le32 cfg1; + __le32 ecc_bch_cfg; + + __le32 clrflashstatus; + __le32 clrreadstatus; + + __le32 cmd1; + __le32 vld; + + __le32 orig_cmd1; + __le32 orig_vld; + + __le32 ecc_buf_cfg; + __le32 read_location0; + __le32 read_location1; + __le32 read_location2; + __le32 read_location3; + __le32 read_location_last0; + __le32 read_location_last1; + __le32 read_location_last2; + __le32 read_location_last3; + + __le32 erased_cw_detect_cfg_clr; + __le32 erased_cw_detect_cfg_set; +}; + +/* + * NAND controller data struct + * + * @dev: parent device + * + * @base: MMIO base + * + * @core_clk: controller clock + * @aon_clk: another controller clock + * + * @regs: a contiguous chunk of memory for DMA register + * writes. contains the register values to be + * written to controller + * + * @props: properties of current NAND controller, + * initialized via DT match data + * + * @controller: base controller structure + * @host_list: list containing all the chips attached to the + * controller + * + * @chan: dma channel + * @cmd_crci: ADM DMA CRCI for command flow control + * @data_crci: ADM DMA CRCI for data flow control + * + * @desc_list: DMA descriptor list (list of desc_infos) + * + * @data_buffer: our local DMA buffer for page read/writes, + * used when we can't use the buffer provided + * by upper layers directly + * @reg_read_buf: local buffer for reading back registers via DMA + * + * @base_phys: physical base address of controller registers + * @base_dma: dma base address of controller registers + * @reg_read_dma: contains dma address for register read buffer + * + * @buf_size/count/start: markers for chip->legacy.read_buf/write_buf + * functions + * @max_cwperpage: maximum QPIC codewords required. calculated + * from all connected NAND devices pagesize + * + * @reg_read_pos: marker for data read in reg_read_buf + * + * @cmd1/vld: some fixed controller register values + * + * @exec_opwrite: flag to select correct number of code word + * while reading status + */ +struct qcom_nand_controller { + struct device *dev; + + void __iomem *base; + + struct clk *core_clk; + struct clk *aon_clk; + + struct nandc_regs *regs; + struct bam_transaction *bam_txn; + + const struct qcom_nandc_props *props; + + struct nand_controller *controller; + struct list_head host_list; + + union { + /* will be used only by QPIC for BAM DMA */ + struct { + struct dma_chan *tx_chan; + struct dma_chan *rx_chan; + struct dma_chan *cmd_chan; + }; + + /* will be used only by EBI2 for ADM DMA */ + struct { + struct dma_chan *chan; + unsigned int cmd_crci; + unsigned int data_crci; + }; + }; + + struct list_head desc_list; + + u8 *data_buffer; + __le32 *reg_read_buf; + + phys_addr_t base_phys; + dma_addr_t base_dma; + dma_addr_t reg_read_dma; + + int buf_size; + int buf_count; + int buf_start; + unsigned int max_cwperpage; + + int reg_read_pos; + + u32 cmd1, vld; + bool exec_opwrite; +}; + +/* + * This data type corresponds to the NAND controller properties which varies + * among different NAND controllers. + * @ecc_modes - ecc mode for NAND + * @dev_cmd_reg_start - NAND_DEV_CMD_* registers starting offset + * @supports_bam - whether NAND controller is using BAM + * @nandc_part_of_qpic - whether NAND controller is part of qpic IP + * @qpic_version2 - flag to indicate QPIC IP version 2 + * @use_codeword_fixup - whether NAND has different layout for boot partitions + */ +struct qcom_nandc_props { + u32 ecc_modes; + u32 dev_cmd_reg_start; + bool supports_bam; + bool nandc_part_of_qpic; + bool qpic_version2; + bool use_codeword_fixup; +}; + +void qcom_free_bam_transaction(struct qcom_nand_controller *nandc); +struct bam_transaction *qcom_alloc_bam_transaction(struct qcom_nand_controller *nandc); +void qcom_clear_bam_transaction(struct qcom_nand_controller *nandc); +void qcom_qpic_bam_dma_done(void *data); +void qcom_nandc_dev_to_mem(struct qcom_nand_controller *nandc, bool is_cpu); +int qcom_prepare_bam_async_desc(struct qcom_nand_controller *nandc, + struct dma_chan *chan, unsigned long flags); +int qcom_prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read, + int reg_off, const void *vaddr, int size, unsigned int flags); +int qcom_prep_bam_dma_desc_data(struct qcom_nand_controller *nandc, bool read, + const void *vaddr, int size, unsigned int flags); +int qcom_prep_adm_dma_desc(struct qcom_nand_controller *nandc, bool read, int reg_off, + const void *vaddr, int size, bool flow_control); +int qcom_read_reg_dma(struct qcom_nand_controller *nandc, int first, int num_regs, + unsigned int flags); +int qcom_write_reg_dma(struct qcom_nand_controller *nandc, __le32 *vaddr, int first, + int num_regs, unsigned int flags); +int qcom_read_data_dma(struct qcom_nand_controller *nandc, int reg_off, const u8 *vaddr, + int size, unsigned int flags); +int qcom_write_data_dma(struct qcom_nand_controller *nandc, int reg_off, const u8 *vaddr, + int size, unsigned int flags); +int qcom_submit_descs(struct qcom_nand_controller *nandc); +void qcom_clear_read_regs(struct qcom_nand_controller *nandc); +void qcom_nandc_unalloc(struct qcom_nand_controller *nandc); +int qcom_nandc_alloc(struct qcom_nand_controller *nandc); +#endif + diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 702e5fb13dae..0da8a1c7740e 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -62,18 +62,38 @@ SPI_MEM_OP_NO_DUMMY, \ SPI_MEM_OP_NO_DATA) -#define SPINAND_PAGE_READ_FROM_CACHE_OP(fast, addr, ndummy, buf, len) \ - SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1), \ +#define SPINAND_PAGE_READ_FROM_CACHE_OP(addr, ndummy, buf, len, ...) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1), \ SPI_MEM_OP_ADDR(2, addr, 1), \ SPI_MEM_OP_DUMMY(ndummy, 1), \ - SPI_MEM_OP_DATA_IN(len, buf, 1)) + SPI_MEM_OP_DATA_IN(len, buf, 1), \ + __VA_OPT__(SPI_MEM_OP_MAX_FREQ(__VA_ARGS__))) -#define SPINAND_PAGE_READ_FROM_CACHE_OP_3A(fast, addr, ndummy, buf, len) \ - SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1), \ +#define SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1)) + +#define SPINAND_PAGE_READ_FROM_CACHE_OP_3A(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1), \ SPI_MEM_OP_ADDR(3, addr, 1), \ SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 1)) +#define SPINAND_PAGE_READ_FROM_CACHE_FAST_OP_3A(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1)) + +#define SPINAND_PAGE_READ_FROM_CACHE_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0d, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 1), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 1), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 1), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1), \ SPI_MEM_OP_ADDR(2, addr, 1), \ @@ -86,6 +106,13 @@ SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 2)) +#define SPINAND_PAGE_READ_FROM_CACHE_X2_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x3d, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 1), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 1), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 2), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1), \ SPI_MEM_OP_ADDR(2, addr, 1), \ @@ -98,6 +125,13 @@ SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 4)) +#define SPINAND_PAGE_READ_FROM_CACHE_X4_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x6d, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 1), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 1), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 4), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1), \ SPI_MEM_OP_ADDR(2, addr, 2), \ @@ -110,6 +144,13 @@ SPI_MEM_OP_DUMMY(ndummy, 2), \ SPI_MEM_OP_DATA_IN(len, buf, 2)) +#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xbd, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 2), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 2), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 2), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1), \ SPI_MEM_OP_ADDR(2, addr, 4), \ @@ -122,6 +163,13 @@ SPI_MEM_OP_DUMMY(ndummy, 4), \ SPI_MEM_OP_DATA_IN(len, buf, 4)) +#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xed, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 4), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 4), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 4), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PROG_EXEC_OP(addr) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1), \ SPI_MEM_OP_ADDR(3, addr, 1), \ @@ -268,6 +316,7 @@ extern const struct spinand_manufacturer gigadevice_spinand_manufacturer; extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer paragon_spinand_manufacturer; +extern const struct spinand_manufacturer skyhigh_spinand_manufacturer; extern const struct spinand_manufacturer toshiba_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; extern const struct spinand_manufacturer xtx_spinand_manufacturer; @@ -314,6 +363,7 @@ struct spinand_ecc_info { #define SPINAND_HAS_CR_FEAT_BIT BIT(1) #define SPINAND_HAS_PROG_PLANE_SELECT_BIT BIT(2) #define SPINAND_HAS_READ_PLANE_SELECT_BIT BIT(3) +#define SPINAND_NO_RAW_ACCESS BIT(4) /** * struct spinand_ondie_ecc_conf - private SPI-NAND on-die ECC engine structure diff --git a/include/linux/net.h b/include/linux/net.h index b75bc534c1b3..0ff950eecc6b 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -343,8 +343,6 @@ static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); -int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, - struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h index 662074b08c94..ff0758e88ea1 100644 --- a/include/linux/net_tstamp.h +++ b/include/linux/net_tstamp.h @@ -19,6 +19,33 @@ enum hwtstamp_source { HWTSTAMP_SOURCE_PHYLIB, }; +/** + * struct hwtstamp_provider_desc - hwtstamp provider description + * + * @index: index of the hwtstamp provider. + * @qualifier: hwtstamp provider qualifier. + */ +struct hwtstamp_provider_desc { + int index; + enum hwtstamp_provider_qualifier qualifier; +}; + +/** + * struct hwtstamp_provider - hwtstamp provider object + * + * @rcu_head: RCU callback used to free the struct. + * @source: source of the hwtstamp provider. + * @phydev: pointer of the phydev source in case a PTP coming from phylib + * @desc: hwtstamp provider description. + */ + +struct hwtstamp_provider { + struct rcu_head rcu_head; + enum hwtstamp_source source; + struct phy_device *phydev; + struct hwtstamp_provider_desc desc; +}; + /** * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config * @@ -31,6 +58,7 @@ enum hwtstamp_source { * copied the ioctl request back to user space * @source: indication whether timestamps should come from the netdev or from * an attached phylib PHY + * @qualifier: qualifier of the hwtstamp provider * * Prefer using this structure for in-kernel processing of hardware * timestamping configuration, over the inextensible struct hwtstamp_config @@ -43,6 +71,7 @@ struct kernel_hwtstamp_config { struct ifreq *ifr; bool copied_to_user; enum hwtstamp_source source; + enum hwtstamp_provider_qualifier qualifier; }; static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ecc686409161..2a59034a5fa2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -63,6 +63,7 @@ struct dsa_port; struct ip_tunnel_parm_kern; struct macsec_context; struct macsec_ops; +struct netdev_config; struct netdev_name_node; struct sd_flow_limit; struct sfp_bus; @@ -82,6 +83,7 @@ struct xdp_metadata_ops; struct xdp_md; struct ethtool_netdev_state; struct phy_link_topology; +struct hwtstamp_provider; typedef u32 xdp_features_t; @@ -381,8 +383,9 @@ struct napi_struct { struct sk_buff *skb; struct list_head rx_list; /* Pending GRO_NORMAL skbs */ int rx_count; /* length of rx_list */ - unsigned int napi_id; + unsigned int napi_id; /* protected by netdev_lock */ struct hrtimer timer; + /* all fields past this point are write-protected by netdev_lock */ struct task_struct *thread; unsigned long gro_flush_timeout; unsigned long irq_suspend_timeout; @@ -509,7 +512,7 @@ static inline bool napi_prefer_busy_poll(struct napi_struct *n) * is scheduled for example in the context of delayed timer * that can be skipped if a NAPI is already scheduled. * - * Return True if NAPI is scheduled, False otherwise. + * Return: True if NAPI is scheduled, False otherwise. */ static inline bool napi_is_scheduled(struct napi_struct *n) { @@ -524,7 +527,7 @@ bool napi_schedule_prep(struct napi_struct *n); * * Schedule NAPI poll routine to be called if it is not already * running. - * Return true if we schedule a NAPI or false if not. + * Return: true if we schedule a NAPI or false if not. * Refer to napi_schedule_prep() for additional reason on why * a NAPI might not be scheduled. */ @@ -558,7 +561,7 @@ static inline void napi_schedule_irqoff(struct napi_struct *n) * Mark NAPI processing as complete. Should only be called if poll budget * has not been completely consumed. * Prefer over napi_complete(). - * Return false if device should avoid rearming interrupts. + * Return: false if device should avoid rearming interrupts. */ bool napi_complete_done(struct napi_struct *n, int work_done); @@ -569,16 +572,11 @@ static inline bool napi_complete(struct napi_struct *n) int dev_set_threaded(struct net_device *dev, bool threaded); -/** - * napi_disable - prevent NAPI from scheduling - * @n: NAPI context - * - * Stop NAPI from being scheduled on this context. - * Waits till any outstanding processing completes. - */ void napi_disable(struct napi_struct *n); +void napi_disable_locked(struct napi_struct *n); void napi_enable(struct napi_struct *n); +void napi_enable_locked(struct napi_struct *n); /** * napi_synchronize - wait until NAPI is not running @@ -1087,8 +1085,8 @@ struct netdev_net_notifier { * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Old-style ioctl entry point. This is used internally by the - * appletalk and ieee802154 subsystems but is no longer called by - * the device ioctl handler. + * ieee802154 subsystem but is no longer called by the device + * ioctl handler. * * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); * Used by the bonding driver for its device specific ioctls: @@ -2045,6 +2043,7 @@ enum netdev_reg_state { * * @neighbours: List heads pointing to this device's neighbours' * dev_list, one per address-family. + * @hwprov: Tracks which PTP performs hardware packet time stamping. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2259,7 +2258,7 @@ struct net_device { void *atalk_ptr; #endif #if IS_ENABLED(CONFIG_AX25) - void *ax25_ptr; + struct ax25_dev __rcu *ax25_ptr; #endif #if IS_ENABLED(CONFIG_CFG80211) struct wireless_dev *ieee80211_ptr; @@ -2412,6 +2411,14 @@ struct net_device { const struct udp_tunnel_nic_info *udp_tunnel_nic_info; struct udp_tunnel_nic *udp_tunnel_nic; + /** @cfg: net_device queue-related configuration */ + struct netdev_config *cfg; + /** + * @cfg_pending: same as @cfg but when device is being actively + * reconfigured includes any changes to the configuration + * requested by the user, but which may or may not be rejected. + */ + struct netdev_config *cfg_pending; struct ethtool_netdev_state *ethtool; /* protected by rtnl_lock */ @@ -2442,8 +2449,27 @@ struct net_device { u32 napi_defer_hard_irqs; /** - * @lock: protects @net_shaper_hierarchy, feel free to use for other - * netdev-scope protection. Ordering: take after rtnl_lock. + * @up: copy of @state's IFF_UP, but safe to read with just @lock. + * May report false negatives while the device is being opened + * or closed (@lock does not protect .ndo_open, or .ndo_close). + */ + bool up; + + /** + * @lock: netdev-scope lock, protects a small selection of fields. + * Should always be taken using netdev_lock() / netdev_unlock() helpers. + * Drivers are free to use it for other protection. + * + * Protects: + * @gro_flush_timeout, @napi_defer_hard_irqs, @napi_list, + * @net_shaper_hierarchy, @reg_state, @threaded + * + * Partially protects (writers must hold both @lock and rtnl_lock): + * @up + * + * Also protects some fields in struct napi_struct. + * + * Ordering: take after rtnl_lock. */ struct mutex lock; @@ -2457,6 +2483,8 @@ struct net_device { struct hlist_head neighbours[NEIGH_NR_TABLES]; + struct hwtstamp_provider __rcu *hwprov; + u8 priv[] ____cacheline_aligned __counted_by(priv_len); } ____cacheline_aligned; @@ -2667,18 +2695,58 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, enum netdev_queue_type type, struct napi_struct *napi); -static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) +static inline void netdev_lock(struct net_device *dev) +{ + mutex_lock(&dev->lock); +} + +static inline void netdev_unlock(struct net_device *dev) +{ + mutex_unlock(&dev->lock); +} + +static inline void netdev_assert_locked(struct net_device *dev) +{ + lockdep_assert_held(&dev->lock); +} + +static inline void netdev_assert_locked_or_invisible(struct net_device *dev) +{ + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) + netdev_assert_locked(dev); +} + +static inline void netif_napi_set_irq_locked(struct napi_struct *napi, int irq) { napi->irq = irq; } +static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) +{ + netdev_lock(napi->dev); + netif_napi_set_irq_locked(napi, irq); + netdev_unlock(napi->dev); +} + /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ #define NAPI_POLL_WEIGHT 64 -void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight); +void netif_napi_add_weight_locked(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight); + +static inline void +netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight) +{ + netdev_lock(dev); + netif_napi_add_weight_locked(dev, napi, poll, weight); + netdev_unlock(dev); +} /** * netif_napi_add() - initialize a NAPI context @@ -2696,6 +2764,13 @@ netif_napi_add(struct net_device *dev, struct napi_struct *napi, netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } +static inline void +netif_napi_add_locked(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int)) +{ + netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); +} + static inline void netif_napi_add_tx_weight(struct net_device *dev, struct napi_struct *napi, @@ -2706,6 +2781,15 @@ netif_napi_add_tx_weight(struct net_device *dev, netif_napi_add_weight(dev, napi, poll, weight); } +static inline void +netif_napi_add_config_locked(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int index) +{ + napi->index = index; + napi->config = &dev->napi_config[index]; + netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); +} + /** * netif_napi_add_config - initialize a NAPI context with persistent config * @dev: network device @@ -2717,9 +2801,9 @@ static inline void netif_napi_add_config(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int index) { - napi->index = index; - napi->config = &dev->napi_config[index]; - netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT); + netdev_lock(dev); + netif_napi_add_config_locked(dev, napi, poll, index); + netdev_unlock(dev); } /** @@ -2739,6 +2823,8 @@ static inline void netif_napi_add_tx(struct net_device *dev, netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } +void __netif_napi_del_locked(struct napi_struct *napi); + /** * __netif_napi_del - remove a NAPI context * @napi: NAPI context @@ -2747,7 +2833,18 @@ static inline void netif_napi_add_tx(struct net_device *dev, * containing @napi. Drivers might want to call this helper to combine * all the needed RCU grace periods into a single one. */ -void __netif_napi_del(struct napi_struct *napi); +static inline void __netif_napi_del(struct napi_struct *napi) +{ + netdev_lock(napi->dev); + __netif_napi_del_locked(napi); + netdev_unlock(napi->dev); +} + +static inline void netif_napi_del_locked(struct napi_struct *napi) +{ + __netif_napi_del_locked(napi); + synchronize_net(); +} /** * netif_napi_del - remove a NAPI context @@ -2854,6 +2951,46 @@ static inline void dev_lstats_add(struct net_device *dev, unsigned int len) u64_stats_update_end(&lstats->syncp); } +static inline void dev_dstats_rx_add(struct net_device *dev, + unsigned int len) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->rx_packets); + u64_stats_add(&dstats->rx_bytes, len); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_rx_dropped(struct net_device *dev) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->rx_drops); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_tx_add(struct net_device *dev, + unsigned int len) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->tx_packets); + u64_stats_add(&dstats->tx_bytes, len); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_tx_dropped(struct net_device *dev) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->tx_drops); + u64_stats_update_end(&dstats->syncp); +} + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ @@ -3194,7 +3331,6 @@ static inline void unregister_netdevice(struct net_device *dev) int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); -void init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, @@ -3208,7 +3344,6 @@ struct net_device *netdev_get_by_index(struct net *net, int ifindex, struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); -struct net_device *dev_get_by_napi_id(unsigned int napi_id); void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, @@ -3322,6 +3457,7 @@ struct softnet_data { }; DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +DECLARE_PER_CPU(struct page_pool *, system_page_pool); #ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) @@ -3810,7 +3946,7 @@ static inline bool netif_attr_test_mask(unsigned long j, * @online_mask: bitmask for CPUs/Rx queues that are online * @nr_bits: number of bits in the bitmask * - * Returns true if a CPU/Rx queue is online. + * Returns: true if a CPU/Rx queue is online. */ static inline bool netif_attr_test_online(unsigned long j, const unsigned long *online_mask, @@ -3830,7 +3966,8 @@ static inline bool netif_attr_test_online(unsigned long j, * @srcp: the cpumask/Rx queue mask pointer * @nr_bits: number of bits in the bitmask * - * Returns >= nr_bits if no further CPUs/Rx queues set. + * Returns: next (after n) CPU/Rx queue index in the mask; + * >= nr_bits if no further CPUs/Rx queues set. */ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) @@ -3852,7 +3989,8 @@ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, * @src2p: the second CPUs/Rx queues mask pointer * @nr_bits: number of bits in the bitmask * - * Returns >= nr_bits if no further CPUs/Rx queues set in both. + * Returns: next (after n) CPU/Rx queue index set in both masks; + * >= nr_bits if no further CPUs/Rx queues set in both. */ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, @@ -3958,9 +4096,9 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog); -void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); -int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb); + const struct bpf_prog *xdp_prog); +void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog); +int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb); int netif_rx(struct sk_buff *skb); int __netif_rx(struct sk_buff *skb); @@ -4037,6 +4175,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); +u8 dev_xdp_sb_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); u32 dev_get_min_mp_channel_count(const struct net_device *dev); @@ -4248,7 +4387,7 @@ static inline bool netif_carrier_ok(const struct net_device *dev) unsigned long dev_trans_start(struct net_device *dev); -void __netdev_watchdog_up(struct net_device *dev); +void netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); void netif_carrier_off(struct net_device *dev); @@ -4642,6 +4781,9 @@ int devm_register_netdev(struct device *dev, struct net_device *ndev); /* General hardware address lists handling functions */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); +int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5897f3dbaf7c..f39f688d7285 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -357,7 +357,7 @@ extern struct static_key xt_tee_enabled; * Begin packet processing : all readers must wait the end * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) - * Returns : + * Returns: * 1 if no recursion on this cpu * 0 if recursion detected */ diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index 8676316547cc..3175073a66ba 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -66,7 +66,6 @@ static inline bool nf_hook_egress_active(void) * @rc: result code which shall be returned by __dev_queue_xmit() on failure * @dev: netdev whose egress hooks shall be applied to @skb * - * Returns @skb on success or %NULL if the packet was consumed or filtered. * Caller must hold rcu_read_lock. * * On ingress, packets are classified first by tc, then by netfilter. @@ -81,6 +80,8 @@ static inline bool nf_hook_egress_active(void) * called recursively by tunnel drivers such as vxlan, the flag is reverted to * false after sch_handle_egress(). This ensures that netfilter is applied * both on the overlay and underlying network. + * + * Returns: @skb on success or %NULL if the packet was consumed or filtered. */ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5eaceef41e6c..071d05d81d38 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -18,9 +18,11 @@ #include #include #include +#include enum netfs_sreq_ref_trace; typedef struct mempool_s mempool_t; +struct folio_queue; /** * folio_start_private_2 - Start an fscache write on a folio. [DEPRECATED] @@ -71,6 +73,7 @@ struct netfs_inode { #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ #define NETFS_ICTX_MODIFIED_ATTR 3 /* Indicate change in mtime/ctime */ +#define NETFS_ICTX_SINGLE_NO_UPLOAD 4 /* Monolithic payload, cache but no upload */ }; /* @@ -178,39 +181,35 @@ struct netfs_io_subrequest { unsigned long long start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ - size_t consumed; /* Amount of read data consumed */ - size_t prev_donated; /* Amount of data donated from previous subreq */ - size_t next_donated; /* Amount of data donated from next subreq */ refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ unsigned int nr_segs; /* Number of segs in io_iter */ + u8 retry_count; /* The number of retries (0 on initial pass) */ enum netfs_io_source source; /* Where to read from/write to */ unsigned char stream_nr; /* I/O stream this belongs to */ - unsigned char curr_folioq_slot; /* Folio currently being read */ - unsigned char curr_folio_order; /* Order of folio */ - struct folio_queue *curr_folioq; /* Queue segment in which current folio resides */ unsigned long flags; #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ -#define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +#define NETFS_SREQ_MADE_PROGRESS 4 /* Set if we transferred at least some data */ #define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ #define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ #define NETFS_SREQ_HIT_EOF 7 /* Set if short due to EOF */ #define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ #define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ -#define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ -#define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ +#define NETFS_SREQ_FAILED 10 /* Set if the subreq failed unretryably */ }; enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_GAPS, /* This read is a synchronous read to fill gaps */ + NETFS_READ_SINGLE, /* This read should be treated as a single object */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_WRITEBACK, /* This write was triggered by writepages */ + NETFS_WRITEBACK_SINGLE, /* This monolithic write was triggered by writepages */ NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ NETFS_DIO_WRITE, /* This is a direct I/O write */ @@ -231,16 +230,16 @@ struct netfs_io_request { struct address_space *mapping; /* The mapping being accessed */ struct kiocb *iocb; /* AIO completion vector */ struct netfs_cache_resources cache_resources; + struct netfs_io_request *copy_to_cache; /* Request to write just-read data to the cache */ struct readahead_control *ractl; /* Readahead descriptor */ struct list_head proc_link; /* Link in netfs_iorequests */ - struct list_head subrequests; /* Contributory I/O operations */ struct netfs_io_stream io_streams[2]; /* Streams of parallel I/O operations */ #define NR_IO_STREAMS 2 //wreq->nr_io_streams struct netfs_group *group; /* Writeback group being written back */ - struct folio_queue *buffer; /* Head of I/O buffer */ - struct folio_queue *buffer_tail; /* Tail of I/O buffer */ - struct iov_iter iter; /* Unencrypted-side iterator */ - struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ + struct rolling_buffer buffer; /* Unencrypted buffer */ +#define NETFS_ROLLBUF_PUT_MARK ROLLBUF_MARK_1 +#define NETFS_ROLLBUF_PAGECACHE_MARK ROLLBUF_MARK_2 + wait_queue_head_t waitq; /* Processor waiter */ void *netfs_priv; /* Private data for the netfs */ void *netfs_priv2; /* Private data for the netfs */ struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ @@ -251,29 +250,28 @@ struct netfs_io_request { atomic_t subreq_counter; /* Next subreq->debug_index */ unsigned int nr_group_rel; /* Number of refs to release on ->group */ spinlock_t lock; /* Lock for queuing subreqs */ - atomic_t nr_outstanding; /* Number of ops in progress */ unsigned long long submitted; /* Amount submitted for I/O so far */ unsigned long long len; /* Length of the request */ size_t transferred; /* Amount to be indicated as transferred */ long error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ - u8 buffer_head_slot; /* First slot in ->buffer */ - u8 buffer_tail_slot; /* Next slot in ->buffer_tail */ unsigned long long i_size; /* Size of the file */ unsigned long long start; /* Start position */ atomic64_t issued_to; /* Write issuer folio cursor */ unsigned long long collected_to; /* Point we've collected to */ unsigned long long cleaned_to; /* Position we've cleaned folios to */ + unsigned long long abandon_to; /* Position to abandon folios to */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ - size_t prev_donated; /* Fallback for subreq->prev_donated */ + unsigned char front_folio_order; /* Order (size) of front folio */ refcount_t ref; unsigned long flags; -#define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ +#define NETFS_RREQ_OFFLOAD_COLLECTION 0 /* Offload collection to workqueue */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ +#define NETFS_RREQ_FOLIO_COPY_TO_CACHE 6 /* Copy current folio to cache from read */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ @@ -410,6 +408,13 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * struct netfs_group *netfs_group); ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from); +/* Single, monolithic object read/write API. */ +void netfs_single_mark_inode_dirty(struct inode *inode); +ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_iter *iter); +int netfs_writeback_single(struct address_space *mapping, + struct writeback_control *wbc, + struct iov_iter *iter); + /* Address operations API */ struct readahead_control; void netfs_readahead(struct readahead_control *); @@ -429,10 +434,8 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp); vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); /* (Sub)request management API. */ -void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq, - bool was_async); -void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, - int error, bool was_async); +void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq); +void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq); void netfs_get_subrequest(struct netfs_io_subrequest *subreq, enum netfs_sreq_ref_trace what); void netfs_put_subrequest(struct netfs_io_subrequest *subreq, @@ -454,6 +457,18 @@ void netfs_end_io_write(struct inode *inode); int netfs_start_io_direct(struct inode *inode); void netfs_end_io_direct(struct inode *inode); +/* Miscellaneous APIs. */ +struct folio_queue *netfs_folioq_alloc(unsigned int rreq_id, gfp_t gfp, + unsigned int trace /*enum netfs_folioq_trace*/); +void netfs_folioq_free(struct folio_queue *folioq, + unsigned int trace /*enum netfs_trace_folioq*/); + +/* Buffer wrangling helpers API. */ +int netfs_alloc_folioq_buffer(struct address_space *mapping, + struct folio_queue **_buffer, + size_t *_cur_size, ssize_t size, gfp_t gfp); +void netfs_free_folioq_buffer(struct folio_queue *fq); + /** * netfs_inode - Get the netfs inode context from the inode * @inode: The inode to query diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index b34301650c47..f91e50a76efd 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -57,7 +57,7 @@ static inline void netpoll_poll_disable(struct net_device *dev) { return; } static inline void netpoll_poll_enable(struct net_device *dev) { return; } #endif -void netpoll_send_udp(struct netpoll *np, const char *msg, int len); +int netpoll_send_udp(struct netpoll *np, const char *msg, int len); void netpoll_print_options(struct netpoll *np); int netpoll_parse_options(struct netpoll *np, char *opt); int __netpoll_setup(struct netpoll *np, struct net_device *ndev); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 8d7430d9f218..71fbebfa43c7 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -17,6 +17,7 @@ #include #include #include +#include enum nfs4_acl_whotype { NFS4_ACL_WHO_NAMED = 0, @@ -365,7 +366,7 @@ enum limit_by4 { NFS4_LIMIT_BLOCKS = 2 }; -enum open_delegation_type4 { +enum nfs4_open_delegation_type4 { NFS4_OPEN_DELEGATE_NONE = 0, NFS4_OPEN_DELEGATE_READ = 1, NFS4_OPEN_DELEGATE_WRITE = 2, @@ -512,12 +513,6 @@ enum { FATTR4_XATTR_SUPPORT = 82, }; -enum { - FATTR4_TIME_DELEG_ACCESS = 84, - FATTR4_TIME_DELEG_MODIFY = 85, - FATTR4_OPEN_ARGUMENTS = 86, -}; - /* * The following internal definitions enable processing the above * attribute bits within 32-bit word boundaries. diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h index 5fc02df88252..a541c3a02887 100644 --- a/include/linux/nfs_common.h +++ b/include/linux/nfs_common.h @@ -9,9 +9,10 @@ #include /* Mapping from NFS error code to "errno" error code. */ -#define errno_NFSERR_IO EIO int nfs_stat_to_errno(enum nfs_stat status); int nfs4_stat_to_errno(int stat); +__u32 nfs_localio_errno_to_nfs4_stat(int errno); + #endif /* _LINUX_NFS_COMMON_H */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 039898d70954..67ae2c3f41d2 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -77,6 +77,23 @@ struct nfs_lock_context { struct rcu_head rcu_head; }; +struct nfs_file_localio { + struct nfsd_file __rcu *ro_file; + struct nfsd_file __rcu *rw_file; + struct list_head list; + void __rcu *nfs_uuid; /* opaque pointer to 'nfs_uuid_t' */ +}; + +static inline void nfs_localio_file_init(struct nfs_file_localio *nfl) +{ +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + nfl->ro_file = NULL; + nfl->rw_file = NULL; + INIT_LIST_HEAD(&nfl->list); + nfl->nfs_uuid = NULL; +#endif +} + struct nfs4_state; struct nfs_open_context { struct nfs_lock_context lock_context; @@ -87,15 +104,16 @@ struct nfs_open_context { struct nfs4_state *state; fmode_t mode; + int error; unsigned long flags; #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) #define NFS_CONTEXT_FILE_OPEN (4) - int error; - struct list_head list; struct nfs4_threshold *mdsthreshold; + struct list_head list; struct rcu_head rcu_head; + struct nfs_file_localio nfl; }; struct nfs_open_dir_context { diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index b804346a9741..f00bfcee7120 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -50,7 +50,6 @@ struct nfs_client { #define NFS_CS_DS 7 /* - Server is a DS */ #define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ #define NFS_CS_PNFS 9 /* - Server used for pnfs */ -#define NFS_CS_LOCAL_IO 10 /* - client is local */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -132,7 +131,7 @@ struct nfs_client { struct timespec64 cl_nfssvc_boot; seqlock_t cl_boot_lock; nfs_uuid_t cl_uuid; - spinlock_t cl_localio_lock; + struct work_struct cl_local_probe_work; #endif /* CONFIG_NFS_LOCALIO */ }; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 559273a0f16d..9155a6ffc370 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1315,11 +1315,6 @@ struct nfs4_fsid_present_res { #endif /* CONFIG_NFS_V4 */ -struct nfstime4 { - u64 seconds; - u32 nseconds; -}; - #ifdef CONFIG_NFS_V4_1 struct pnfs_commit_bucket { @@ -1637,6 +1632,7 @@ enum { NFS_IOHDR_RESEND_PNFS, NFS_IOHDR_RESEND_MDS, NFS_IOHDR_UNSTABLE_WRITES, + NFS_IOHDR_ODIRECT, }; struct nfs_io_completion; @@ -1785,7 +1781,7 @@ struct nfs_rpc_ops { struct nfs_fattr *, struct inode *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); - int (*lookup) (struct inode *, struct dentry *, + int (*lookup) (struct inode *, struct dentry *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *); diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index 9202f4b24343..9aa8a43843d7 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -6,9 +6,6 @@ #ifndef __LINUX_NFSLOCALIO_H #define __LINUX_NFSLOCALIO_H -/* nfsd_file structure is purposely kept opaque to NFS client */ -struct nfsd_file; - #if IS_ENABLED(CONFIG_NFS_LOCALIO) #include @@ -19,6 +16,9 @@ struct nfsd_file; #include #include +struct nfs_client; +struct nfs_file_localio; + /* * Useful to allow a client to negotiate if localio * possible with its server. @@ -27,28 +27,38 @@ struct nfsd_file; */ typedef struct { uuid_t uuid; + unsigned nfs3_localio_probe_count; + /* this struct is over a cacheline, avoid bouncing */ + spinlock_t ____cacheline_aligned lock; struct list_head list; + spinlock_t *list_lock; /* nn->local_clients_lock */ struct net __rcu *net; /* nfsd's network namespace */ struct auth_domain *dom; /* auth_domain for localio */ + /* Local files to close when net is shut down or exports change */ + struct list_head files; } nfs_uuid_t; void nfs_uuid_init(nfs_uuid_t *); bool nfs_uuid_begin(nfs_uuid_t *); void nfs_uuid_end(nfs_uuid_t *); -void nfs_uuid_is_local(const uuid_t *, struct list_head *, +void nfs_uuid_is_local(const uuid_t *, struct list_head *, spinlock_t *, struct net *, struct auth_domain *, struct module *); -void nfs_uuid_invalidate_clients(struct list_head *list); -void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid); + +void nfs_localio_enable_client(struct nfs_client *clp); +void nfs_localio_disable_client(struct nfs_client *clp); +void nfs_localio_invalidate_clients(struct list_head *nn_local_clients, + spinlock_t *nn_local_clients_lock); /* localio needs to map filehandle -> struct nfsd_file */ extern struct nfsd_file * nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *, const struct cred *, const struct nfs_fh *, const fmode_t) __must_hold(rcu); +void nfs_close_local_fh(struct nfs_file_localio *); struct nfsd_localio_operations { - bool (*nfsd_serv_try_get)(struct net *); - void (*nfsd_serv_put)(struct net *); + bool (*nfsd_net_try_get)(struct net *); + void (*nfsd_net_put)(struct net *); struct nfsd_file *(*nfsd_open_local_fh)(struct net *, struct auth_domain *, struct rpc_clnt *, @@ -56,6 +66,8 @@ struct nfsd_localio_operations { const struct nfs_fh *, const fmode_t); struct net *(*nfsd_file_put_local)(struct nfsd_file *); + struct nfsd_file *(*nfsd_file_get)(struct nfsd_file *); + void (*nfsd_file_put)(struct nfsd_file *); struct file *(*nfsd_file_file)(struct nfsd_file *); } ____cacheline_aligned; @@ -64,17 +76,18 @@ extern const struct nfsd_localio_operations *nfs_to; struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *, struct rpc_clnt *, const struct cred *, - const struct nfs_fh *, const fmode_t); + const struct nfs_fh *, struct nfs_file_localio *, + const fmode_t); static inline void nfs_to_nfsd_net_put(struct net *net) { /* - * Once reference to nfsd_serv is dropped, NFSD could be - * unloaded, so ensure safe return from nfsd_file_put_local() - * by always taking RCU. + * Once reference to net (and associated nfsd_serv) is dropped, NFSD + * could be unloaded, so ensure safe return from nfsd_net_put() by + * always taking RCU. */ rcu_read_lock(); - nfs_to->nfsd_serv_put(net); + nfs_to->nfsd_net_put(net); rcu_read_unlock(); } @@ -91,12 +104,19 @@ static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio) } #else /* CONFIG_NFS_LOCALIO */ + +struct nfs_file_localio; +static inline void nfs_close_local_fh(struct nfs_file_localio *nfl) +{ +} static inline void nfsd_localio_ops_init(void) { } -static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio) +struct nfs_client; +static inline void nfs_localio_disable_client(struct nfs_client *clp) { } + #endif /* CONFIG_NFS_LOCALIO */ #endif /* __LINUX_NFSLOCALIO_H */ diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h index cfad6ce7e1bd..dd85613cdd86 100644 --- a/include/linux/numa_memblks.h +++ b/include/linux/numa_memblks.h @@ -29,7 +29,10 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi); int __init numa_memblks_init(int (*init_func)(void), bool memblock_force_top_down); +extern int numa_distance_cnt; + #ifdef CONFIG_NUMA_EMU +extern int emu_nid_to_phys[MAX_NUMNODES]; int numa_emu_cmdline(char *str); void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys, unsigned int nr_emu_nids); diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 13377dde4527..fe3b60818fdc 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -64,6 +64,7 @@ enum { /* Transport Type codes for Discovery Log Page entry TRTYPE field */ enum { + NVMF_TRTYPE_PCI = 0, /* PCI */ NVMF_TRTYPE_RDMA = 1, /* RDMA */ NVMF_TRTYPE_FC = 2, /* Fibre Channel */ NVMF_TRTYPE_TCP = 3, /* TCP/IP */ @@ -275,6 +276,7 @@ enum nvme_ctrl_attr { NVME_CTRL_ATTR_HID_128_BIT = (1 << 0), NVME_CTRL_ATTR_TBKAS = (1 << 6), NVME_CTRL_ATTR_ELBAS = (1 << 15), + NVME_CTRL_ATTR_RHII = (1 << 18), }; struct nvme_id_ctrl { @@ -1896,6 +1898,46 @@ static inline bool nvme_is_fabrics(const struct nvme_command *cmd) return cmd->common.opcode == nvme_fabrics_command; } +#ifdef CONFIG_NVME_VERBOSE_ERRORS +const char *nvme_get_error_status_str(u16 status); +const char *nvme_get_opcode_str(u8 opcode); +const char *nvme_get_admin_opcode_str(u8 opcode); +const char *nvme_get_fabrics_opcode_str(u8 opcode); +#else /* CONFIG_NVME_VERBOSE_ERRORS */ +static inline const char *nvme_get_error_status_str(u16 status) +{ + return "I/O Error"; +} +static inline const char *nvme_get_opcode_str(u8 opcode) +{ + return "I/O Cmd"; +} +static inline const char *nvme_get_admin_opcode_str(u8 opcode) +{ + return "Admin Cmd"; +} + +static inline const char *nvme_get_fabrics_opcode_str(u8 opcode) +{ + return "Fabrics Cmd"; +} +#endif /* CONFIG_NVME_VERBOSE_ERRORS */ + +static inline const char *nvme_opcode_str(int qid, u8 opcode) +{ + return qid ? nvme_get_opcode_str(opcode) : + nvme_get_admin_opcode_str(opcode); +} + +static inline const char *nvme_fabrics_opcode_str( + int qid, const struct nvme_command *cmd) +{ + if (nvme_is_fabrics(cmd)) + return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype); + + return nvme_opcode_str(qid, cmd->common.opcode); +} + struct nvme_error_slot { __le64 error_count; __le16 sqid; diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 3ebeaa0ded00..515676ebe598 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -92,8 +92,8 @@ struct nvmem_cell_info { * @read_only: Device is read-only. * @root_only: Device is accessibly to root only. * @of_node: If given, this will be used instead of the parent's of_node. - * @reg_read: Callback to read data. - * @reg_write: Callback to write data. + * @reg_read: Callback to read data; return zero if successful. + * @reg_write: Callback to write data; return zero if successful. * @size: Device size. * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. diff --git a/include/linux/objtool.h b/include/linux/objtool.h index b3b8d3dab52d..c722a921165b 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -45,29 +45,25 @@ #define STACK_FRAME_NON_STANDARD_FP(func) #endif -#define ANNOTATE_NOENDBR \ - "986: \n\t" \ - ".pushsection .discard.noendbr\n\t" \ - ".long 986b\n\t" \ - ".popsection\n\t" - #define ASM_REACHABLE \ "998:\n\t" \ ".pushsection .discard.reachable\n\t" \ ".long 998b\n\t" \ ".popsection\n\t" -#else /* __ASSEMBLY__ */ +#define __ASM_BREF(label) label ## b -/* - * This macro indicates that the following intra-function call is valid. - * Any non-annotated intra-function call will cause objtool to issue a warning. - */ -#define ANNOTATE_INTRA_FUNCTION_CALL \ - 999: \ - .pushsection .discard.intra_function_calls; \ - .long 999b; \ - .popsection; +#define __ASM_ANNOTATE(label, type) \ + ".pushsection .discard.annotate_insn,\"M\",@progbits,8\n\t" \ + ".long " __stringify(label) " - .\n\t" \ + ".long " __stringify(type) "\n\t" \ + ".popsection\n\t" + +#define ASM_ANNOTATE(type) \ + "911:\n\t" \ + __ASM_ANNOTATE(911b, type) + +#else /* __ASSEMBLY__ */ /* * In asm, there are two kinds of code: normal C-type callable functions and @@ -115,34 +111,11 @@ #endif .endm -.macro ANNOTATE_NOENDBR +.macro ANNOTATE type:req .Lhere_\@: - .pushsection .discard.noendbr - .long .Lhere_\@ - .popsection -.endm - -/* - * Use objtool to validate the entry requirement that all code paths do - * VALIDATE_UNRET_END before RET. - * - * NOTE: The macro must be used at the beginning of a global symbol, otherwise - * it will be ignored. - */ -.macro VALIDATE_UNRET_BEGIN -#if defined(CONFIG_NOINSTR_VALIDATION) && \ - (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) -.Lhere_\@: - .pushsection .discard.validate_unret + .pushsection .discard.annotate_insn,"M",@progbits,8 .long .Lhere_\@ - . - .popsection -#endif -.endm - -.macro REACHABLE -.Lhere_\@: - .pushsection .discard.reachable - .long .Lhere_\@ + .long \type .popsection .endm @@ -155,20 +128,77 @@ #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) -#define ANNOTATE_NOENDBR -#define ASM_REACHABLE +#define __ASM_ANNOTATE(label, type) +#define ASM_ANNOTATE(type) #else -#define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm -.macro ANNOTATE_NOENDBR -.endm -.macro REACHABLE +.macro ANNOTATE type:req .endm #endif #endif /* CONFIG_OBJTOOL */ +#ifndef __ASSEMBLY__ +/* + * Annotate away the various 'relocation to !ENDBR` complaints; knowing that + * these relocations will never be used for indirect calls. + */ +#define ANNOTATE_NOENDBR ASM_ANNOTATE(ANNOTYPE_NOENDBR) +/* + * This should be used immediately before an indirect jump/call. It tells + * objtool the subsequent indirect jump/call is vouched safe for retpoline + * builds. + */ +#define ANNOTATE_RETPOLINE_SAFE ASM_ANNOTATE(ANNOTYPE_RETPOLINE_SAFE) +/* + * See linux/instrumentation.h + */ +#define ANNOTATE_INSTR_BEGIN(label) __ASM_ANNOTATE(label, ANNOTYPE_INSTR_BEGIN) +#define ANNOTATE_INSTR_END(label) __ASM_ANNOTATE(label, ANNOTYPE_INSTR_END) +/* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +#define ANNOTATE_IGNORE_ALTERNATIVE ASM_ANNOTATE(ANNOTYPE_IGNORE_ALTS) +/* + * This macro indicates that the following intra-function call is valid. + * Any non-annotated intra-function call will cause objtool to issue a warning. + */ +#define ANNOTATE_INTRA_FUNCTION_CALL ASM_ANNOTATE(ANNOTYPE_INTRA_FUNCTION_CALL) +/* + * Use objtool to validate the entry requirement that all code paths do + * VALIDATE_UNRET_END before RET. + * + * NOTE: The macro must be used at the beginning of a global symbol, otherwise + * it will be ignored. + */ +#define ANNOTATE_UNRET_BEGIN ASM_ANNOTATE(ANNOTYPE_UNRET_BEGIN) +/* + * This should be used to refer to an instruction that is considered + * terminating, like a noreturn CALL or UD2 when we know they are not -- eg + * WARN using UD2. + */ +#define ANNOTATE_REACHABLE(label) __ASM_ANNOTATE(label, ANNOTYPE_REACHABLE) + +#else +#define ANNOTATE_NOENDBR ANNOTATE type=ANNOTYPE_NOENDBR +#define ANNOTATE_RETPOLINE_SAFE ANNOTATE type=ANNOTYPE_RETPOLINE_SAFE +/* ANNOTATE_INSTR_BEGIN ANNOTATE type=ANNOTYPE_INSTR_BEGIN */ +/* ANNOTATE_INSTR_END ANNOTATE type=ANNOTYPE_INSTR_END */ +#define ANNOTATE_IGNORE_ALTERNATIVE ANNOTATE type=ANNOTYPE_IGNORE_ALTS +#define ANNOTATE_INTRA_FUNCTION_CALL ANNOTATE type=ANNOTYPE_INTRA_FUNCTION_CALL +#define ANNOTATE_UNRET_BEGIN ANNOTATE type=ANNOTYPE_UNRET_BEGIN +#define ANNOTATE_REACHABLE ANNOTATE type=ANNOTYPE_REACHABLE +#endif + +#if defined(CONFIG_NOINSTR_VALIDATION) && \ + (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) +#define VALIDATE_UNRET_BEGIN ANNOTATE_UNRET_BEGIN +#else +#define VALIDATE_UNRET_BEGIN +#endif + #endif /* _LINUX_OBJTOOL_H */ diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index 453a4f4ef39d..df5d9fa84dba 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -54,4 +54,16 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_SAVE 6 #define UNWIND_HINT_TYPE_RESTORE 7 +/* + * Annotate types + */ +#define ANNOTYPE_NOENDBR 1 +#define ANNOTYPE_RETPOLINE_SAFE 2 +#define ANNOTYPE_INSTR_BEGIN 3 +#define ANNOTYPE_INSTR_END 4 +#define ANNOTYPE_UNRET_BEGIN 5 +#define ANNOTYPE_IGNORE_ALTS 6 +#define ANNOTYPE_INTRA_FUNCTION_CALL 7 +#define ANNOTYPE_REACHABLE 8 + #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/include/linux/of.h b/include/linux/of.h index f921786cb8ac..eaf0e2a2b75c 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -311,6 +311,7 @@ extern struct device_node *of_find_node_with_property( extern struct property *of_find_property(const struct device_node *np, const char *name, int *lenp); +extern bool of_property_read_bool(const struct device_node *np, const char *propname); extern int of_property_count_elems_of_size(const struct device_node *np, const char *propname, int elem_size); extern int of_property_read_u32_index(const struct device_node *np, @@ -397,7 +398,6 @@ extern int of_phandle_iterator_args(struct of_phandle_iterator *it, uint32_t *args, int size); -extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); extern int of_alias_get_id(const struct device_node *np, const char *stem); extern int of_alias_get_highest_id(const char *stem); @@ -615,6 +615,12 @@ static inline struct device_node *of_find_compatible_node( return NULL; } +static inline bool of_property_read_bool(const struct device_node *np, + const char *propname) +{ + return false; +} + static inline int of_property_count_elems_of_size(const struct device_node *np, const char *propname, int elem_size) { @@ -1242,24 +1248,6 @@ static inline int of_property_read_string_index(const struct device_node *np, return rc < 0 ? rc : 0; } -/** - * of_property_read_bool - Find a property - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * - * Search for a boolean property in a device node. Usage on non-boolean - * property types is deprecated. - * - * Return: true if the property exists false otherwise. - */ -static inline bool of_property_read_bool(const struct device_node *np, - const char *propname) -{ - const struct property *prop = of_find_property(np, propname, NULL); - - return prop ? true : false; -} - /** * of_property_present - Test if a property is present in a node * @np: device node to search for the property. @@ -1271,7 +1259,9 @@ static inline bool of_property_read_bool(const struct device_node *np, */ static inline bool of_property_present(const struct device_node *np, const char *propname) { - return of_property_read_bool(np, propname); + struct property *prop = of_find_property(np, propname, NULL); + + return prop ? true : false; } /** diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 9e034363788a..0cff90365391 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -26,6 +26,7 @@ struct of_pci_range { u64 bus_addr; }; u64 cpu_addr; + u64 parent_bus_addr; u64 size; u32 flags; }; diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index a2ff1ad48f7f..17471ef8e092 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -47,8 +47,6 @@ struct of_dev_auxdata { { .compatible = _compat, .phys_addr = _phys, .name = _name, \ .platform_data = _pdata } -extern const struct of_device_id of_default_bus_match_table[]; - /* Platform drivers register/unregister */ extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h index c9e3843d2dd5..263b915df1fb 100644 --- a/include/linux/omap-gpmc.h +++ b/include/linux/omap-gpmc.h @@ -66,10 +66,6 @@ extern int gpmc_calc_timings(struct gpmc_timings *gpmc_t, struct device_node; -extern int gpmc_get_client_irq(unsigned irq_config); - -extern unsigned int gpmc_ticks_to_ns(unsigned int ticks); - extern void gpmc_cs_write_reg(int cs, int idx, u32 val); extern int gpmc_calc_divider(unsigned int sync_clk); extern int gpmc_cs_set_timings(int cs, const struct gpmc_timings *t, diff --git a/include/linux/packing.h b/include/linux/packing.h index 5d36dcd06f60..0589d70bbe04 100644 --- a/include/linux/packing.h +++ b/include/linux/packing.h @@ -8,6 +8,83 @@ #include #include +#define GEN_PACKED_FIELD_STRUCT(__type) \ + struct packed_field_ ## __type { \ + __type startbit; \ + __type endbit; \ + __type offset; \ + __type size; \ + } + +/* struct packed_field_u8. Use with bit offsets < 256, buffers < 32B and + * unpacked structures < 256B. + */ +GEN_PACKED_FIELD_STRUCT(u8); + +/* struct packed_field_u16. Use with bit offsets < 65536, buffers < 8KB and + * unpacked structures < 64KB. + */ +GEN_PACKED_FIELD_STRUCT(u16); + +#define PACKED_FIELD(start, end, struct_name, struct_field) \ +{ \ + (start), \ + (end), \ + offsetof(struct_name, struct_field), \ + sizeof_field(struct_name, struct_field), \ +} + +#define CHECK_PACKED_FIELD_OVERLAP(fields, index1, index2) ({ \ + typeof(&(fields)[0]) __f = (fields); \ + typeof(__f[0]) _f1 = __f[index1]; typeof(__f[0]) _f2 = __f[index2]; \ + const bool _ascending = __f[0].startbit < __f[1].startbit; \ + BUILD_BUG_ON_MSG(_ascending && _f1.startbit >= _f2.startbit, \ + __stringify(fields) " field " __stringify(index2) \ + " breaks ascending order"); \ + BUILD_BUG_ON_MSG(!_ascending && _f1.startbit <= _f2.startbit, \ + __stringify(fields) " field " __stringify(index2) \ + " breaks descending order"); \ + BUILD_BUG_ON_MSG(max(_f1.endbit, _f2.endbit) <= \ + min(_f1.startbit, _f2.startbit), \ + __stringify(fields) " field " __stringify(index2) \ + " overlaps with previous field"); \ +}) + +#define CHECK_PACKED_FIELD(fields, index) ({ \ + typeof(&(fields)[0]) _f = (fields); \ + typeof(_f[0]) __f = _f[index]; \ + BUILD_BUG_ON_MSG(__f.startbit < __f.endbit, \ + __stringify(fields) " field " __stringify(index) \ + " start bit must not be smaller than end bit"); \ + BUILD_BUG_ON_MSG(__f.size != 1 && __f.size != 2 && \ + __f.size != 4 && __f.size != 8, \ + __stringify(fields) " field " __stringify(index) \ + " has unsupported unpacked storage size"); \ + BUILD_BUG_ON_MSG(__f.startbit - __f.endbit >= BITS_PER_BYTE * __f.size, \ + __stringify(fields) " field " __stringify(index) \ + " exceeds unpacked storage size"); \ + __builtin_choose_expr(index != 0, \ + CHECK_PACKED_FIELD_OVERLAP(fields, index - 1, index), \ + 1); \ +}) + +/* Note that the packed fields may be either in ascending or descending order. + * Thus, we must check that both the first and last field wit within the + * packed buffer size. + */ +#define CHECK_PACKED_FIELDS_SIZE(fields, pbuflen) ({ \ + typeof(&(fields)[0]) _f = (fields); \ + typeof(pbuflen) _len = (pbuflen); \ + const size_t num_fields = ARRAY_SIZE(fields); \ + BUILD_BUG_ON_MSG(!__builtin_constant_p(_len), \ + __stringify(fields) " pbuflen " __stringify(pbuflen) \ + " must be a compile time constant"); \ + BUILD_BUG_ON_MSG(_f[0].startbit >= BITS_PER_BYTE * _len, \ + __stringify(fields) " first field exceeds packed buffer size"); \ + BUILD_BUG_ON_MSG(_f[num_fields - 1].startbit >= BITS_PER_BYTE * _len, \ + __stringify(fields) " last field exceeds packed buffer size"); \ +}) + #define QUIRK_MSB_ON_THE_RIGHT BIT(0) #define QUIRK_LITTLE_ENDIAN BIT(1) #define QUIRK_LSW32_IS_FIRST BIT(2) @@ -26,4 +103,352 @@ int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen, int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, size_t pbuflen, u8 quirks); +void pack_fields_u8(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks); + +void pack_fields_u16(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks); + +void unpack_fields_u8(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks); + +void unpack_fields_u16(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks); + +/* Do not hand-edit the following packed field check macros! + * + * They are generated using scripts/gen_packed_field_checks.c, which may be + * built via "make scripts_gen_packed_field_checks". If larger macro sizes are + * needed in the future, please use this program to re-generate the macros and + * insert them here. + */ + +#define CHECK_PACKED_FIELDS_1(fields) \ + CHECK_PACKED_FIELD(fields, 0) + +#define CHECK_PACKED_FIELDS_2(fields) do { \ + CHECK_PACKED_FIELDS_1(fields); \ + CHECK_PACKED_FIELD(fields, 1); \ +} while (0) + +#define CHECK_PACKED_FIELDS_3(fields) do { \ + CHECK_PACKED_FIELDS_2(fields); \ + CHECK_PACKED_FIELD(fields, 2); \ +} while (0) + +#define CHECK_PACKED_FIELDS_4(fields) do { \ + CHECK_PACKED_FIELDS_3(fields); \ + CHECK_PACKED_FIELD(fields, 3); \ +} while (0) + +#define CHECK_PACKED_FIELDS_5(fields) do { \ + CHECK_PACKED_FIELDS_4(fields); \ + CHECK_PACKED_FIELD(fields, 4); \ +} while (0) + +#define CHECK_PACKED_FIELDS_6(fields) do { \ + CHECK_PACKED_FIELDS_5(fields); \ + CHECK_PACKED_FIELD(fields, 5); \ +} while (0) + +#define CHECK_PACKED_FIELDS_7(fields) do { \ + CHECK_PACKED_FIELDS_6(fields); \ + CHECK_PACKED_FIELD(fields, 6); \ +} while (0) + +#define CHECK_PACKED_FIELDS_8(fields) do { \ + CHECK_PACKED_FIELDS_7(fields); \ + CHECK_PACKED_FIELD(fields, 7); \ +} while (0) + +#define CHECK_PACKED_FIELDS_9(fields) do { \ + CHECK_PACKED_FIELDS_8(fields); \ + CHECK_PACKED_FIELD(fields, 8); \ +} while (0) + +#define CHECK_PACKED_FIELDS_10(fields) do { \ + CHECK_PACKED_FIELDS_9(fields); \ + CHECK_PACKED_FIELD(fields, 9); \ +} while (0) + +#define CHECK_PACKED_FIELDS_11(fields) do { \ + CHECK_PACKED_FIELDS_10(fields); \ + CHECK_PACKED_FIELD(fields, 10); \ +} while (0) + +#define CHECK_PACKED_FIELDS_12(fields) do { \ + CHECK_PACKED_FIELDS_11(fields); \ + CHECK_PACKED_FIELD(fields, 11); \ +} while (0) + +#define CHECK_PACKED_FIELDS_13(fields) do { \ + CHECK_PACKED_FIELDS_12(fields); \ + CHECK_PACKED_FIELD(fields, 12); \ +} while (0) + +#define CHECK_PACKED_FIELDS_14(fields) do { \ + CHECK_PACKED_FIELDS_13(fields); \ + CHECK_PACKED_FIELD(fields, 13); \ +} while (0) + +#define CHECK_PACKED_FIELDS_15(fields) do { \ + CHECK_PACKED_FIELDS_14(fields); \ + CHECK_PACKED_FIELD(fields, 14); \ +} while (0) + +#define CHECK_PACKED_FIELDS_16(fields) do { \ + CHECK_PACKED_FIELDS_15(fields); \ + CHECK_PACKED_FIELD(fields, 15); \ +} while (0) + +#define CHECK_PACKED_FIELDS_17(fields) do { \ + CHECK_PACKED_FIELDS_16(fields); \ + CHECK_PACKED_FIELD(fields, 16); \ +} while (0) + +#define CHECK_PACKED_FIELDS_18(fields) do { \ + CHECK_PACKED_FIELDS_17(fields); \ + CHECK_PACKED_FIELD(fields, 17); \ +} while (0) + +#define CHECK_PACKED_FIELDS_19(fields) do { \ + CHECK_PACKED_FIELDS_18(fields); \ + CHECK_PACKED_FIELD(fields, 18); \ +} while (0) + +#define CHECK_PACKED_FIELDS_20(fields) do { \ + CHECK_PACKED_FIELDS_19(fields); \ + CHECK_PACKED_FIELD(fields, 19); \ +} while (0) + +#define CHECK_PACKED_FIELDS_21(fields) do { \ + CHECK_PACKED_FIELDS_20(fields); \ + CHECK_PACKED_FIELD(fields, 20); \ +} while (0) + +#define CHECK_PACKED_FIELDS_22(fields) do { \ + CHECK_PACKED_FIELDS_21(fields); \ + CHECK_PACKED_FIELD(fields, 21); \ +} while (0) + +#define CHECK_PACKED_FIELDS_23(fields) do { \ + CHECK_PACKED_FIELDS_22(fields); \ + CHECK_PACKED_FIELD(fields, 22); \ +} while (0) + +#define CHECK_PACKED_FIELDS_24(fields) do { \ + CHECK_PACKED_FIELDS_23(fields); \ + CHECK_PACKED_FIELD(fields, 23); \ +} while (0) + +#define CHECK_PACKED_FIELDS_25(fields) do { \ + CHECK_PACKED_FIELDS_24(fields); \ + CHECK_PACKED_FIELD(fields, 24); \ +} while (0) + +#define CHECK_PACKED_FIELDS_26(fields) do { \ + CHECK_PACKED_FIELDS_25(fields); \ + CHECK_PACKED_FIELD(fields, 25); \ +} while (0) + +#define CHECK_PACKED_FIELDS_27(fields) do { \ + CHECK_PACKED_FIELDS_26(fields); \ + CHECK_PACKED_FIELD(fields, 26); \ +} while (0) + +#define CHECK_PACKED_FIELDS_28(fields) do { \ + CHECK_PACKED_FIELDS_27(fields); \ + CHECK_PACKED_FIELD(fields, 27); \ +} while (0) + +#define CHECK_PACKED_FIELDS_29(fields) do { \ + CHECK_PACKED_FIELDS_28(fields); \ + CHECK_PACKED_FIELD(fields, 28); \ +} while (0) + +#define CHECK_PACKED_FIELDS_30(fields) do { \ + CHECK_PACKED_FIELDS_29(fields); \ + CHECK_PACKED_FIELD(fields, 29); \ +} while (0) + +#define CHECK_PACKED_FIELDS_31(fields) do { \ + CHECK_PACKED_FIELDS_30(fields); \ + CHECK_PACKED_FIELD(fields, 30); \ +} while (0) + +#define CHECK_PACKED_FIELDS_32(fields) do { \ + CHECK_PACKED_FIELDS_31(fields); \ + CHECK_PACKED_FIELD(fields, 31); \ +} while (0) + +#define CHECK_PACKED_FIELDS_33(fields) do { \ + CHECK_PACKED_FIELDS_32(fields); \ + CHECK_PACKED_FIELD(fields, 32); \ +} while (0) + +#define CHECK_PACKED_FIELDS_34(fields) do { \ + CHECK_PACKED_FIELDS_33(fields); \ + CHECK_PACKED_FIELD(fields, 33); \ +} while (0) + +#define CHECK_PACKED_FIELDS_35(fields) do { \ + CHECK_PACKED_FIELDS_34(fields); \ + CHECK_PACKED_FIELD(fields, 34); \ +} while (0) + +#define CHECK_PACKED_FIELDS_36(fields) do { \ + CHECK_PACKED_FIELDS_35(fields); \ + CHECK_PACKED_FIELD(fields, 35); \ +} while (0) + +#define CHECK_PACKED_FIELDS_37(fields) do { \ + CHECK_PACKED_FIELDS_36(fields); \ + CHECK_PACKED_FIELD(fields, 36); \ +} while (0) + +#define CHECK_PACKED_FIELDS_38(fields) do { \ + CHECK_PACKED_FIELDS_37(fields); \ + CHECK_PACKED_FIELD(fields, 37); \ +} while (0) + +#define CHECK_PACKED_FIELDS_39(fields) do { \ + CHECK_PACKED_FIELDS_38(fields); \ + CHECK_PACKED_FIELD(fields, 38); \ +} while (0) + +#define CHECK_PACKED_FIELDS_40(fields) do { \ + CHECK_PACKED_FIELDS_39(fields); \ + CHECK_PACKED_FIELD(fields, 39); \ +} while (0) + +#define CHECK_PACKED_FIELDS_41(fields) do { \ + CHECK_PACKED_FIELDS_40(fields); \ + CHECK_PACKED_FIELD(fields, 40); \ +} while (0) + +#define CHECK_PACKED_FIELDS_42(fields) do { \ + CHECK_PACKED_FIELDS_41(fields); \ + CHECK_PACKED_FIELD(fields, 41); \ +} while (0) + +#define CHECK_PACKED_FIELDS_43(fields) do { \ + CHECK_PACKED_FIELDS_42(fields); \ + CHECK_PACKED_FIELD(fields, 42); \ +} while (0) + +#define CHECK_PACKED_FIELDS_44(fields) do { \ + CHECK_PACKED_FIELDS_43(fields); \ + CHECK_PACKED_FIELD(fields, 43); \ +} while (0) + +#define CHECK_PACKED_FIELDS_45(fields) do { \ + CHECK_PACKED_FIELDS_44(fields); \ + CHECK_PACKED_FIELD(fields, 44); \ +} while (0) + +#define CHECK_PACKED_FIELDS_46(fields) do { \ + CHECK_PACKED_FIELDS_45(fields); \ + CHECK_PACKED_FIELD(fields, 45); \ +} while (0) + +#define CHECK_PACKED_FIELDS_47(fields) do { \ + CHECK_PACKED_FIELDS_46(fields); \ + CHECK_PACKED_FIELD(fields, 46); \ +} while (0) + +#define CHECK_PACKED_FIELDS_48(fields) do { \ + CHECK_PACKED_FIELDS_47(fields); \ + CHECK_PACKED_FIELD(fields, 47); \ +} while (0) + +#define CHECK_PACKED_FIELDS_49(fields) do { \ + CHECK_PACKED_FIELDS_48(fields); \ + CHECK_PACKED_FIELD(fields, 48); \ +} while (0) + +#define CHECK_PACKED_FIELDS_50(fields) do { \ + CHECK_PACKED_FIELDS_49(fields); \ + CHECK_PACKED_FIELD(fields, 49); \ +} while (0) + +#define CHECK_PACKED_FIELDS(fields) \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 1, ({ CHECK_PACKED_FIELDS_1(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 2, ({ CHECK_PACKED_FIELDS_2(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 3, ({ CHECK_PACKED_FIELDS_3(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 4, ({ CHECK_PACKED_FIELDS_4(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 5, ({ CHECK_PACKED_FIELDS_5(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 6, ({ CHECK_PACKED_FIELDS_6(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 7, ({ CHECK_PACKED_FIELDS_7(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 8, ({ CHECK_PACKED_FIELDS_8(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 9, ({ CHECK_PACKED_FIELDS_9(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 10, ({ CHECK_PACKED_FIELDS_10(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 11, ({ CHECK_PACKED_FIELDS_11(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 12, ({ CHECK_PACKED_FIELDS_12(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 13, ({ CHECK_PACKED_FIELDS_13(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 14, ({ CHECK_PACKED_FIELDS_14(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 15, ({ CHECK_PACKED_FIELDS_15(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 16, ({ CHECK_PACKED_FIELDS_16(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 17, ({ CHECK_PACKED_FIELDS_17(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 18, ({ CHECK_PACKED_FIELDS_18(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 19, ({ CHECK_PACKED_FIELDS_19(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 20, ({ CHECK_PACKED_FIELDS_20(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 21, ({ CHECK_PACKED_FIELDS_21(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 22, ({ CHECK_PACKED_FIELDS_22(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 23, ({ CHECK_PACKED_FIELDS_23(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 24, ({ CHECK_PACKED_FIELDS_24(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 25, ({ CHECK_PACKED_FIELDS_25(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 26, ({ CHECK_PACKED_FIELDS_26(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 27, ({ CHECK_PACKED_FIELDS_27(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 28, ({ CHECK_PACKED_FIELDS_28(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 29, ({ CHECK_PACKED_FIELDS_29(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 30, ({ CHECK_PACKED_FIELDS_30(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 31, ({ CHECK_PACKED_FIELDS_31(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 32, ({ CHECK_PACKED_FIELDS_32(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 33, ({ CHECK_PACKED_FIELDS_33(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 34, ({ CHECK_PACKED_FIELDS_34(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 35, ({ CHECK_PACKED_FIELDS_35(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 36, ({ CHECK_PACKED_FIELDS_36(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 37, ({ CHECK_PACKED_FIELDS_37(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 38, ({ CHECK_PACKED_FIELDS_38(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 39, ({ CHECK_PACKED_FIELDS_39(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 40, ({ CHECK_PACKED_FIELDS_40(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 41, ({ CHECK_PACKED_FIELDS_41(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 42, ({ CHECK_PACKED_FIELDS_42(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 43, ({ CHECK_PACKED_FIELDS_43(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 44, ({ CHECK_PACKED_FIELDS_44(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 45, ({ CHECK_PACKED_FIELDS_45(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 46, ({ CHECK_PACKED_FIELDS_46(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 47, ({ CHECK_PACKED_FIELDS_47(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 48, ({ CHECK_PACKED_FIELDS_48(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 49, ({ CHECK_PACKED_FIELDS_49(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 50, ({ CHECK_PACKED_FIELDS_50(fields); }), \ + ({ BUILD_BUG_ON_MSG(1, "CHECK_PACKED_FIELDS() must be regenerated to support array sizes larger than 50."); }) \ +)))))))))))))))))))))))))))))))))))))))))))))))))) + +/* End of generated content */ + +#define pack_fields(pbuf, pbuflen, ustruct, fields, quirks) \ + ({ \ + CHECK_PACKED_FIELDS(fields); \ + CHECK_PACKED_FIELDS_SIZE((fields), (pbuflen)); \ + _Generic((fields), \ + const struct packed_field_u8 * : pack_fields_u8, \ + const struct packed_field_u16 * : pack_fields_u16 \ + )((pbuf), (pbuflen), (ustruct), (fields), ARRAY_SIZE(fields), (quirks)); \ + }) + +#define unpack_fields(pbuf, pbuflen, ustruct, fields, quirks) \ + ({ \ + CHECK_PACKED_FIELDS(fields); \ + CHECK_PACKED_FIELDS_SIZE((fields), (pbuflen)); \ + _Generic((fields), \ + const struct packed_field_u8 * : unpack_fields_u8, \ + const struct packed_field_u16 * : unpack_fields_u16 \ + )((pbuf), (pbuflen), (ustruct), (fields), ARRAY_SIZE(fields), (quirks)); \ + }) + #endif diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index cf46ac720802..36d283552f80 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -110,6 +110,7 @@ enum pageflags { PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ + PG_dropbehind, /* drop pages on IO completion */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif @@ -562,6 +563,10 @@ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE) +FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE) + __FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE) + #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not @@ -862,18 +867,10 @@ static inline void ClearPageCompound(struct page *page) ClearPageHead(page); } FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) -FOLIO_TEST_FLAG(partially_mapped, FOLIO_SECOND_PAGE) -/* - * PG_partially_mapped is protected by deferred_split split_queue_lock, - * so its safe to use non-atomic set/clear. - */ -__FOLIO_SET_FLAG(partially_mapped, FOLIO_SECOND_PAGE) -__FOLIO_CLEAR_FLAG(partially_mapped, FOLIO_SECOND_PAGE) +FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(large_rmappable) -FOLIO_TEST_FLAG_FALSE(partially_mapped) -__FOLIO_SET_FLAG_NOOP(partially_mapped) -__FOLIO_CLEAR_FLAG_NOOP(partially_mapped) +FOLIO_FLAG_FALSE(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) @@ -902,21 +899,9 @@ static inline int PageTransCompound(const struct page *page) { return PageCompound(page); } - -/* - * PageTransTail returns true for both transparent huge pages - * and hugetlbfs pages, so it should only be called when it's known - * that hugetlbfs pages aren't involved. - */ -static inline int PageTransTail(const struct page *page) -{ - return PageTail(page); -} #else TESTPAGEFLAG_FALSE(TransHuge, transhuge) TESTPAGEFLAG_FALSE(TransCompound, transcompound) -TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap) -TESTPAGEFLAG_FALSE(TransTail, transtail) #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE) @@ -926,11 +911,9 @@ TESTPAGEFLAG_FALSE(TransTail, transtail) * * This flag is set by hwpoison handler. Cleared by THP split or free page. */ -PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) - TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) +FOLIO_FLAG(has_hwpoisoned, FOLIO_SECOND_PAGE) #else -PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) - TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) +FOLIO_FLAG_FALSE(has_hwpoisoned) #endif /* diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 73dc2c1841ec..898bb788243b 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -31,7 +31,7 @@ bool move_freepages_block_isolate(struct zone *zone, struct page *page, int migratetype); int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - int migratetype, int flags, gfp_t gfp_flags); + int migratetype, int flags); void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, int migratetype); diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 79dbd8bc35a7..46406f3fe34d 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -96,7 +96,7 @@ static inline void page_counter_reset_watermark(struct page_counter *counter) counter->watermark = usage; } -#ifdef CONFIG_MEMCG +#if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM) void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bcf0865a38ae..47bfc6b1b632 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -710,6 +710,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, * * %FGP_NOFS - __GFP_FS will get cleared in gfp. * * %FGP_NOWAIT - Don't block on the folio lock. * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) + * * %FGP_DONTCACHE - Uncached buffered IO * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin() * implementation. */ @@ -723,10 +724,21 @@ typedef unsigned int __bitwise fgf_t; #define FGP_NOWAIT ((__force fgf_t)0x00000020) #define FGP_FOR_MMAP ((__force fgf_t)0x00000040) #define FGP_STABLE ((__force fgf_t)0x00000080) +#define FGP_DONTCACHE ((__force fgf_t)0x00000100) #define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) +static inline unsigned int filemap_get_order(size_t size) +{ + unsigned int shift = ilog2(size); + + if (shift <= PAGE_SHIFT) + return 0; + + return shift - PAGE_SHIFT; +} + /** * fgf_set_order - Encode a length in the fgf_t flags. * @size: The suggested size of the folio to create. @@ -740,11 +752,11 @@ typedef unsigned int __bitwise fgf_t; */ static inline fgf_t fgf_set_order(size_t size) { - unsigned int shift = ilog2(size); + unsigned int order = filemap_get_order(size); - if (shift <= PAGE_SHIFT) + if (!order) return 0; - return (__force fgf_t)((shift - PAGE_SHIFT) << 26); + return (__force fgf_t)(order << 26); } void *filemap_get_entry(struct address_space *mapping, pgoff_t index); @@ -1270,11 +1282,6 @@ void folio_end_private_2(struct folio *folio); void folio_wait_private_2(struct folio *folio); int folio_wait_private_2_killable(struct folio *folio); -/* - * Add an arbitrary waiter to a page's wait queue - */ -void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); - /* * Fault in userspace address range. */ @@ -1353,6 +1360,7 @@ struct readahead_control { pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; + bool dropbehind; bool _workingset; unsigned long _pflags; }; diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 3a4860bd2758..3a10f8cfc3ad 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -45,6 +45,10 @@ struct pci_ecam_ops { unsigned int bus_shift; struct pci_ops pci_ops; int (*init)(struct pci_config_window *); + int (*enable_device)(struct pci_host_bridge *, + struct pci_dev *); + void (*disable_device)(struct pci_host_bridge *, + struct pci_dev *); }; /* diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 18a3aeb62ae4..ee6156bcbbd0 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -157,7 +157,7 @@ struct pci_epf { struct device dev; const char *name; struct pci_epf_header *header; - struct pci_epf_bar bar[6]; + struct pci_epf_bar bar[PCI_STD_NUM_BARS]; u8 msi_interrupts; u16 msix_interrupts; u8 func_no; @@ -174,7 +174,7 @@ struct pci_epf { /* Below members are to attach secondary EPC to an endpoint function */ struct pci_epc *sec_epc; struct list_head sec_epc_list; - struct pci_epf_bar sec_epc_bar[6]; + struct pci_epf_bar sec_epc_bar[PCI_STD_NUM_BARS]; u8 sec_epc_func_no; struct config_group *group; unsigned int is_bound; diff --git a/include/linux/pci.h b/include/linux/pci.h index db9b47ce3eef..47b31ad724fa 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -407,7 +407,7 @@ struct pci_dev { supported from root to here */ #endif unsigned int pasid_no_tlp:1; /* PASID works without TLP Prefix */ - unsigned int eetlp_prefix_path:1; /* End-to-End TLP Prefix */ + unsigned int eetlp_prefix_max:3; /* Max # of End-End TLP Prefixes, 0=not supported */ pci_channel_state_t error_state; /* Current connectivity state */ struct device dev; /* Generic device interface */ @@ -595,6 +595,8 @@ struct pci_host_bridge { u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* Platform IRQ swizzler */ int (*map_irq)(const struct pci_dev *, u8, u8); void (*release_fn)(struct pci_host_bridge *); + int (*enable_device)(struct pci_host_bridge *bridge, struct pci_dev *dev); + void (*disable_device)(struct pci_host_bridge *bridge, struct pci_dev *dev); void *release_data; unsigned int ignore_reset_delay:1; /* For entire hierarchy */ unsigned int no_ext_tags:1; /* No Extended Tags */ @@ -1046,6 +1048,20 @@ struct pci_driver { .vendor = PCI_VENDOR_ID_##vend, .device = (dev), \ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0 +/** + * PCI_VDEVICE_SUB - describe a specific PCI device/subdevice in a short form + * @vend: the vendor name + * @dev: the 16 bit PCI Device ID + * @subvend: the 16 bit PCI Subvendor ID + * @subdev: the 16 bit PCI Subdevice ID + * + * Generate the pci_device_id struct layout for the specific PCI + * device/subdevice. Private data may follow the output. + */ +#define PCI_VDEVICE_SUB(vend, dev, subvend, subdev) \ + .vendor = PCI_VENDOR_ID_##vend, .device = (dev), \ + .subvendor = (subvend), .subdevice = (subdev), 0, 0 + /** * PCI_DEVICE_DATA - macro used to describe a specific PCI device in very short form * @vend: the vendor name (without PCI_VENDOR_ID_ prefix) @@ -2297,6 +2313,7 @@ static inline void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev) { } #endif +int pcim_intx(struct pci_dev *pdev, int enabled); int pcim_request_all_regions(struct pci_dev *pdev, const char *name); void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d2402bf4aea2..de5deb1a0118 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2593,6 +2593,11 @@ #define PCI_VENDOR_ID_REDHAT 0x1b36 +#define PCI_VENDOR_ID_WCHIC 0x1c00 +#define PCI_DEVICE_ID_WCHIC_CH382_0S1P 0x3050 +#define PCI_DEVICE_ID_WCHIC_CH382_2S1P 0x3250 +#define PCI_DEVICE_ID_WCHIC_CH382_2S 0x3253 + #define PCI_VENDOR_ID_SILICOM_DENMARK 0x1c2c #define PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS 0x1c36 @@ -2647,6 +2652,12 @@ #define PCI_VENDOR_ID_AKS 0x416c #define PCI_DEVICE_ID_AKS_ALADDINCARD 0x0100 +#define PCI_VENDOR_ID_WCHCN 0x4348 +#define PCI_DEVICE_ID_WCHCN_CH353_4S 0x3453 +#define PCI_DEVICE_ID_WCHCN_CH353_2S1PF 0x5046 +#define PCI_DEVICE_ID_WCHCN_CH353_1S1P 0x5053 +#define PCI_DEVICE_ID_WCHCN_CH353_2S1P 0x7053 + #define PCI_VENDOR_ID_ACCESSIO 0x494f #define PCI_DEVICE_ID_ACCESSIO_WDG_CSM 0x22c0 diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index b5b5d17998b8..733f4ddd2ef1 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -50,7 +50,6 @@ struct dw_xpcs; struct phylink_pcs *xpcs_to_phylink_pcs(struct dw_xpcs *xpcs); int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); -void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr); diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 35842d1e3879..5b520fe86b60 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -221,10 +221,7 @@ do { \ } while (0) #define PERCPU_PTR(__p) \ -({ \ - unsigned long __pcpu_ptr = (__force unsigned long)(__p); \ - (typeof(*(__p)) __force __kernel *)(__pcpu_ptr); \ -}) + (typeof(*(__p)) __force __kernel *)((__force unsigned long)(__p)) #ifdef CONFIG_SMP diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index cb99ec8c9e96..8333f132f4a9 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1279,6 +1279,11 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data, { int size = 1; + if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) + return; + if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) + return; + data->callchain = perf_callchain(event, regs); size += data->callchain->nr; @@ -1287,12 +1292,18 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data, } static inline void perf_sample_save_raw_data(struct perf_sample_data *data, + struct perf_event *event, struct perf_raw_record *raw) { struct perf_raw_frag *frag = &raw->frag; u32 sum = 0; int size; + if (!(event->attr.sample_type & PERF_SAMPLE_RAW)) + return; + if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW)) + return; + do { sum += frag->size; if (perf_raw_frag_last(frag)) @@ -1309,6 +1320,11 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data, data->sample_flags |= PERF_SAMPLE_RAW; } +static inline bool has_branch_stack(struct perf_event *event) +{ + return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; +} + static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, struct perf_branch_stack *brs, @@ -1316,6 +1332,11 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data, { int size = sizeof(u64); /* nr */ + if (!has_branch_stack(event)) + return; + if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK)) + return; + if (branch_sample_hw_index(event)) size += sizeof(u64); size += brs->nr * sizeof(struct perf_branch_entry); @@ -1669,6 +1690,8 @@ static inline int perf_allow_tracepoint(struct perf_event_attr *attr) return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } +extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs); + extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, @@ -1705,11 +1728,6 @@ static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs) # define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs) #endif -static inline bool has_branch_stack(struct perf_event *event) -{ - return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; -} - static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; @@ -1879,6 +1897,10 @@ static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } +static inline int perf_exclude_event(struct perf_event *event, struct pt_regs *regs) +{ + return 0; +} #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index adef9d6e9b1b..94d267d02372 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -533,7 +533,14 @@ static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - ptep_get_and_clear(mm, addr, ptep); + pte_t pte = ptep_get(ptep); + + pte_clear(mm, addr, ptep); + /* + * No need for ptep_get_and_clear(): page table check doesn't care about + * any bits that could have been set by HW concurrently. + */ + page_table_check_pte_clear(mm, pte); } #ifdef CONFIG_GUP_GET_PXX_LOW_HIGH diff --git a/include/linux/phy.h b/include/linux/phy.h index 563c46205685..19f076a71f94 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -32,19 +32,6 @@ #include #include -#define PHY_DEFAULT_FEATURES (SUPPORTED_Autoneg | \ - SUPPORTED_TP | \ - SUPPORTED_MII) - -#define PHY_10BT_FEATURES (SUPPORTED_10baseT_Half | \ - SUPPORTED_10baseT_Full) - -#define PHY_100BT_FEATURES (SUPPORTED_100baseT_Half | \ - SUPPORTED_100baseT_Full) - -#define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ - SUPPORTED_1000baseT_Full) - extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; @@ -62,16 +49,11 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; #define PHY_BASIC_T1S_P2MP_FEATURES ((unsigned long *)&phy_basic_t1s_p2mp_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) -#define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) -#define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) -#define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) #define PHY_EEE_CAP1_FEATURES ((unsigned long *)&phy_eee_cap1_features) #define PHY_EEE_CAP2_FEATURES ((unsigned long *)&phy_eee_cap2_features) extern const int phy_basic_ports_array[3]; -extern const int phy_fibre_port_array[1]; -extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[3]; extern const int phy_basic_t1s_p2mp_features_array[2]; @@ -298,6 +280,29 @@ static inline const char *phy_modes(phy_interface_t interface) } } +/** + * rgmii_clock - map link speed to the clock rate + * @speed: link speed value + * + * Description: maps RGMII supported link speeds + * into the clock rates. + * + * Returns: clock rate or negative errno + */ +static inline long rgmii_clock(int speed) +{ + switch (speed) { + case SPEED_10: + return 2500000; + case SPEED_100: + return 25000000; + case SPEED_1000: + return 125000000; + default: + return -EINVAL; + } +} + #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10 @@ -817,6 +822,24 @@ struct phy_tdr_config { }; #define PHY_PAIR_ALL -1 +/** + * enum link_inband_signalling - in-band signalling modes that are supported + * + * @LINK_INBAND_DISABLE: in-band signalling can be disabled + * @LINK_INBAND_ENABLE: in-band signalling can be enabled without bypass + * @LINK_INBAND_BYPASS: in-band signalling can be enabled with bypass + * + * The possible and required bits can only be used if the valid bit is set. + * If possible is clear, that means inband signalling can not be used. + * Required is only valid when possible is set, and means that inband + * signalling must be used. + */ +enum link_inband_signalling { + LINK_INBAND_DISABLE = BIT(0), + LINK_INBAND_ENABLE = BIT(1), + LINK_INBAND_BYPASS = BIT(2), +}; + /** * struct phy_plca_cfg - Configuration of the PLCA (Physical Layer Collision * Avoidance) Reconciliation Sublayer. @@ -956,6 +979,19 @@ struct phy_driver { */ int (*get_features)(struct phy_device *phydev); + /** + * @inband_caps: query whether in-band is supported for the given PHY + * interface mode. Returns a bitmask of bits defined by enum + * link_inband_signalling. + */ + unsigned int (*inband_caps)(struct phy_device *phydev, + phy_interface_t interface); + + /** + * @config_inband: configure in-band mode for the PHY + */ + int (*config_inband)(struct phy_device *phydev, unsigned int modes); + /** * @get_rate_matching: Get the supported type of rate matching for a * particular phy interface. This is used by phy consumers to determine @@ -1090,6 +1126,53 @@ struct phy_driver { int (*cable_test_get_status)(struct phy_device *dev, bool *finished); /* Get statistics from the PHY using ethtool */ + /** + * @get_phy_stats: Retrieve PHY statistics. + * @dev: The PHY device for which the statistics are retrieved. + * @eth_stats: structure where Ethernet PHY stats will be stored. + * @stats: structure where additional PHY-specific stats will be stored. + * + * Retrieves the supported PHY statistics and populates the provided + * structures. The input structures are pre-initialized with + * `ETHTOOL_STAT_NOT_SET`, and the driver must only modify members + * corresponding to supported statistics. Unmodified members will remain + * set to `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. + */ + void (*get_phy_stats)(struct phy_device *dev, + struct ethtool_eth_phy_stats *eth_stats, + struct ethtool_phy_stats *stats); + + /** + * @get_link_stats: Retrieve link statistics. + * @dev: The PHY device for which the statistics are retrieved. + * @link_stats: structure where link-specific stats will be stored. + * + * Retrieves link-related statistics for the given PHY device. The input + * structure is pre-initialized with `ETHTOOL_STAT_NOT_SET`, and the + * driver must only modify members corresponding to supported + * statistics. Unmodified members will remain set to + * `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. + */ + void (*get_link_stats)(struct phy_device *dev, + struct ethtool_link_ext_stats *link_stats); + + /** + * @update_stats: Trigger periodic statistics updates. + * @dev: The PHY device for which statistics updates are triggered. + * + * Periodically gathers statistics from the PHY device to update locally + * maintained 64-bit counters. This is necessary for PHYs that implement + * reduced-width counters (e.g., 16-bit or 32-bit) which can overflow + * more frequently compared to 64-bit counters. By invoking this + * callback, drivers can fetch the current counter values, handle + * overflow detection, and accumulate the results into local 64-bit + * counters for accurate reporting through the `get_phy_stats` and + * `get_link_stats` interfaces. + * + * Return: 0 on success or a negative error code on failure. + */ + int (*update_stats)(struct phy_device *dev); + /** @get_sset_count: Number of statistic counters */ int (*get_sset_count)(struct phy_device *dev); /** @get_strings: Names of the statistic counters */ @@ -1580,6 +1663,9 @@ static inline bool phy_polling_mode(struct phy_device *phydev) if (phydev->drv->flags & PHY_POLL_CABLE_TEST) return true; + if (phydev->drv->update_stats) + return true; + return phydev->irq == PHY_POLL; } @@ -1818,6 +1904,9 @@ int phy_config_aneg(struct phy_device *phydev); int _phy_start_aneg(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); +unsigned int phy_inband_caps(struct phy_device *phydev, + phy_interface_t interface); +int phy_config_inband(struct phy_device *phydev, unsigned int modes); int phy_speed_down(struct phy_device *phydev, bool sync); int phy_speed_up(struct phy_device *phydev); bool phy_check_valid(int speed, int duplex, unsigned long *features); @@ -1957,7 +2046,7 @@ int genphy_c45_plca_set_cfg(struct phy_device *phydev, int genphy_c45_plca_get_status(struct phy_device *phydev, struct phy_plca_status *plca_st); int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, - unsigned long *lp, bool *is_enabled); + unsigned long *lp); int genphy_c45_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, @@ -2014,6 +2103,7 @@ void phy_advertise_eee_all(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); void phy_support_eee(struct phy_device *phydev); +void phy_disable_eee(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); @@ -2038,6 +2128,8 @@ int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask); int phy_unregister_fixup_for_id(const char *bus_id); int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); +int phy_eee_tx_clock_stop_capable(struct phy_device *phydev); +int phy_eee_rx_clock_stop(struct phy_device *phydev, bool clk_stop_enable); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); @@ -2065,6 +2157,13 @@ int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); int phy_ethtool_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data); + +void __phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats); +void __phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats); + int phy_ethtool_get_plca_cfg(struct phy_device *phydev, struct phy_plca_cfg *plca_cfg); int phy_ethtool_set_plca_cfg(struct phy_device *phydev, diff --git a/include/linux/phylib_stubs.h b/include/linux/phylib_stubs.h index 1279f48c8a70..9d2d6090c86d 100644 --- a/include/linux/phylib_stubs.h +++ b/include/linux/phylib_stubs.h @@ -5,6 +5,9 @@ #include +struct ethtool_eth_phy_stats; +struct ethtool_link_ext_stats; +struct ethtool_phy_stats; struct kernel_hwtstamp_config; struct netlink_ext_ack; struct phy_device; @@ -19,6 +22,11 @@ struct phylib_stubs { int (*hwtstamp_set)(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); + void (*get_phy_stats)(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats); + void (*get_link_ext_stats)(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats); }; static inline int phy_hwtstamp_get(struct phy_device *phydev, @@ -50,6 +58,29 @@ static inline int phy_hwtstamp_set(struct phy_device *phydev, return phylib_stubs->hwtstamp_set(phydev, config, extack); } +static inline void phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats) +{ + ASSERT_RTNL(); + + if (!phylib_stubs) + return; + + phylib_stubs->get_phy_stats(phydev, phy_stats, phydev_stats); +} + +static inline void phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ + ASSERT_RTNL(); + + if (!phylib_stubs) + return; + + phylib_stubs->get_link_ext_stats(phydev, link_stats); +} + #else static inline int phy_hwtstamp_get(struct phy_device *phydev, @@ -65,4 +96,15 @@ static inline int phy_hwtstamp_set(struct phy_device *phydev, return -EOPNOTSUPP; } +static inline void phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats) +{ +} + +static inline void phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ +} + #endif diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 5c01048860c4..898b00451bbf 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -5,6 +5,8 @@ #include #include +#include + struct device_node; struct ethtool_cmd; struct fwnode_handle; @@ -143,11 +145,17 @@ enum phylink_op_type { * possible and avoid stopping it during suspend events. * @default_an_inband: if true, defaults to MLO_AN_INBAND rather than * MLO_AN_PHY. A fixed-link specification will override. + * @eee_rx_clk_stop_enable: if true, PHY can stop the receive clock during LPI * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx * are supported by the MAC/PCS. + * @lpi_interfaces: bitmap describing which PHY interface modes can support + * LPI signalling. * @mac_capabilities: MAC pause/speed/duplex capabilities. + * @lpi_capabilities: MAC speeds which can support LPI signalling + * @lpi_timer_default: Default EEE LPI timer setting. + * @eee_enabled_default: If set, EEE will be enabled by phylink at creation time */ struct phylink_config { struct device *dev; @@ -156,10 +164,15 @@ struct phylink_config { bool mac_managed_pm; bool mac_requires_rxc; bool default_an_inband; + bool eee_rx_clk_stop_enable; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); DECLARE_PHY_INTERFACE_MASK(supported_interfaces); + DECLARE_PHY_INTERFACE_MASK(lpi_interfaces); unsigned long mac_capabilities; + unsigned long lpi_capabilities; + u32 lpi_timer_default; + bool eee_enabled_default; }; void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); @@ -173,6 +186,8 @@ void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); * @mac_finish: finish a major reconfiguration of the interface. * @mac_link_down: take the link down. * @mac_link_up: allow the link to come up. + * @mac_disable_tx_lpi: disable LPI. + * @mac_enable_tx_lpi: enable and configure LPI. * * The individual methods are described more fully below. */ @@ -193,6 +208,9 @@ struct phylink_mac_ops { struct phy_device *phy, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause); + void (*mac_disable_tx_lpi)(struct phylink_config *config); + int (*mac_enable_tx_lpi)(struct phylink_config *config, u32 timer, + bool tx_clk_stop); }; #if 0 /* For kernel-doc purposes only. */ @@ -387,12 +405,41 @@ void mac_link_down(struct phylink_config *config, unsigned int mode, void mac_link_up(struct phylink_config *config, struct phy_device *phy, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause); + +/** + * mac_disable_tx_lpi() - disable LPI generation at the MAC + * @config: a pointer to a &struct phylink_config. + * + * Disable generation of LPI at the MAC, effectively preventing the MAC + * from indicating that it is idle. + */ +void mac_disable_tx_lpi(struct phylink_config *config); + +/** + * mac_enable_tx_lpi() - configure and enable LPI generation at the MAC + * @config: a pointer to a &struct phylink_config. + * @timer: LPI timeout in microseconds. + * @tx_clk_stop: allow xMII transmit clock to be stopped during LPI + * + * Configure the LPI timeout accordingly. This will only be called when + * the link is already up, to cater for situations where the hardware + * needs to be programmed according to the link speed. + * + * Enable LPI generation at the MAC, and configure whether the xMII transmit + * clock may be stopped. + * + * Returns: 0 on success. Please consult with rmk before returning an error. + */ +int mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop); #endif struct phylink_pcs_ops; /** * struct phylink_pcs - PHYLINK PCS instance + * @supported_interfaces: describing which PHY_INTERFACE_MODE_xxx + * are supported by this PCS. * @ops: a pointer to the &struct phylink_pcs_ops structure * @phylink: pointer to &struct phylink_config * @neg_mode: provide PCS neg mode via "mode" argument @@ -409,6 +456,7 @@ struct phylink_pcs_ops; * the PCS driver. */ struct phylink_pcs { + DECLARE_PHY_INTERFACE_MASK(supported_interfaces); const struct phylink_pcs_ops *ops; struct phylink *phylink; bool neg_mode; @@ -419,6 +467,7 @@ struct phylink_pcs { /** * struct phylink_pcs_ops - MAC PCS operations structure. * @pcs_validate: validate the link configuration. + * @pcs_inband_caps: query inband support for interface mode. * @pcs_enable: enable the PCS. * @pcs_disable: disable the PCS. * @pcs_pre_config: pre-mac_config method (for errata) @@ -434,13 +483,15 @@ struct phylink_pcs { struct phylink_pcs_ops { int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state); + unsigned int (*pcs_inband_caps)(struct phylink_pcs *pcs, + phy_interface_t interface); int (*pcs_enable)(struct phylink_pcs *pcs); void (*pcs_disable)(struct phylink_pcs *pcs); void (*pcs_pre_config)(struct phylink_pcs *pcs, phy_interface_t interface); int (*pcs_post_config)(struct phylink_pcs *pcs, phy_interface_t interface); - void (*pcs_get_state)(struct phylink_pcs *pcs, + void (*pcs_get_state)(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, @@ -470,6 +521,20 @@ struct phylink_pcs_ops { int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state); +/** + * pcs_inband_caps - query PCS in-band capabilities for interface mode. + * @pcs: a pointer to a &struct phylink_pcs. + * @interface: interface mode to be queried + * + * Returns zero if it is unknown what in-band signalling is supported by the + * PHY (e.g. because the PHY driver doesn't implement the method.) Otherwise, + * returns a bit mask of the LINK_INBAND_* values from + * &enum link_inband_signalling to describe which inband modes are supported + * for this interface mode. + */ +unsigned int pcs_inband_caps(struct phylink_pcs *pcs, + phy_interface_t interface); + /** * pcs_enable() - enable the PCS. * @pcs: a pointer to a &struct phylink_pcs. @@ -485,6 +550,7 @@ void pcs_disable(struct phylink_pcs *pcs); /** * pcs_get_state() - Read the current inband link state from the hardware * @pcs: a pointer to a &struct phylink_pcs. + * @neg_mode: link negotiation mode (PHYLINK_PCS_NEG_xxx) * @state: a pointer to a &struct phylink_link_state. * * Read the current inband link state from the MAC PCS, reporting the @@ -493,8 +559,11 @@ void pcs_disable(struct phylink_pcs *pcs); * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. + * + * Note that the @neg_mode parameter is always the PHYLINK_PCS_NEG_xxx + * state, not MLO_AN_xxx. */ -void pcs_get_state(struct phylink_pcs *pcs, +void pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state); /** @@ -669,8 +738,9 @@ static inline int phylink_get_link_timer_ns(phy_interface_t interface) } void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, - u16 bmsr, u16 lpa); + unsigned int neg_mode, u16 bmsr, u16 lpa); void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, + unsigned int neg_mode, struct phylink_link_state *state); int phylink_mii_c22_pcs_encode_advertisement(phy_interface_t interface, const unsigned long *advertising); diff --git a/include/linux/pid.h b/include/linux/pid.h index a3aad9b4074c..98837a1ff0f3 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -59,6 +59,7 @@ struct pid spinlock_t lock; struct dentry *stashed; u64 ino; + struct rb_node pidfs_node; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; @@ -68,6 +69,7 @@ struct pid struct upid numbers[]; }; +extern seqcount_spinlock_t pidmap_lock_seq; extern struct pid init_struct_pid; struct file; @@ -106,9 +108,6 @@ extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); -extern int pid_max; -extern int pid_max_min, pid_max_max; - /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index f9f9931e02d6..7c67a5811199 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -30,6 +30,7 @@ struct pid_namespace { struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; + int pid_max; struct pid_namespace *parent; #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; @@ -38,9 +39,14 @@ struct pid_namespace { struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; -#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) + struct work_struct work; +#ifdef CONFIG_SYSCTL + struct ctl_table_set set; + struct ctl_table_header *sysctls; +#if defined(CONFIG_MEMFD_CREATE) int memfd_noexec_scope; #endif +#endif } __randomize_layout; extern struct pid_namespace init_pid_ns; @@ -117,6 +123,8 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); +int register_pidns_sysctls(struct pid_namespace *pidns); +void unregister_pidns_sysctls(struct pid_namespace *pidns); static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) { diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 75bdf9807802..7c830d0dec9a 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -4,5 +4,8 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); +void pidfs_add_pid(struct pid *pid); +void pidfs_remove_pid(struct pid *pid); +extern const struct dentry_operations pidfs_dentry_operations; #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/platform_data/amd_qdma.h b/include/linux/platform_data/amd_qdma.h index 576d952f97ed..967a6ef31cf9 100644 --- a/include/linux/platform_data/amd_qdma.h +++ b/include/linux/platform_data/amd_qdma.h @@ -26,11 +26,13 @@ struct dma_slave_map; * @max_mm_channels: Maximum number of MM DMA channels in each direction * @device_map: DMA slave map * @irq_index: The index of first IRQ + * @dma_dev: The device pointer for dma operations */ struct qdma_platdata { u32 max_mm_channels; u32 irq_index; struct dma_slave_map *device_map; + struct device *dma_dev; }; #endif /* _PLATDATA_AMD_QDMA_H */ diff --git a/include/linux/platform_data/clk-davinci-pll.h b/include/linux/platform_data/clk-davinci-pll.h deleted file mode 100644 index e55dab1d578b..000000000000 --- a/include/linux/platform_data/clk-davinci-pll.h +++ /dev/null @@ -1,21 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * PLL clock driver for TI Davinci SoCs - * - * Copyright (C) 2018 David Lechner - */ - -#ifndef __LINUX_PLATFORM_DATA_CLK_DAVINCI_PLL_H__ -#define __LINUX_PLATFORM_DATA_CLK_DAVINCI_PLL_H__ - -#include - -/** - * davinci_pll_platform_data - * @cfgchip: CFGCHIP syscon regmap - */ -struct davinci_pll_platform_data { - struct regmap *cfgchip; -}; - -#endif /* __LINUX_PLATFORM_DATA_CLK_DAVINCI_PLL_H__ */ diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index b3c4993e656e..ecf290a0c98f 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -5044,8 +5044,11 @@ struct ec_response_pd_status { #define PD_EVENT_POWER_CHANGE BIT(1) #define PD_EVENT_IDENTITY_RECEIVED BIT(2) #define PD_EVENT_DATA_SWAP BIT(3) +#define PD_EVENT_TYPEC BIT(4) +#define PD_EVENT_PPM BIT(5) + struct ec_response_host_event_status { - uint32_t status; /* PD MCU host event status */ + uint32_t status; /* PD MCU host event status */ } __ec_align4; /* Set USB type-C port role and muxes */ @@ -6105,6 +6108,29 @@ struct ec_response_typec_vdm_response { #undef VDO_MAX_SIZE +/* + * UCSI OPM-PPM commands + * + * These commands are used for communication between OPM and PPM. + * Only UCSI3.0 is tested. + */ + +#define EC_CMD_UCSI_PPM_SET 0x0140 + +/* The data size is stored in the host command protocol header. */ +struct ec_params_ucsi_ppm_set { + uint16_t offset; + uint8_t data[]; +} __ec_align2; + +#define EC_CMD_UCSI_PPM_GET 0x0141 + +/* For 'GET' sub-commands, data will be returned as a raw payload. */ +struct ec_params_ucsi_ppm_get { + uint16_t offset; + uint8_t size; +} __ec_align2; + /*****************************************************************************/ /* The command range 0x200-0x2FF is reserved for Rotor. */ diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index b34ed0cc1f8d..3ec24f445c29 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -41,6 +41,11 @@ #define EC_MAX_REQUEST_OVERHEAD 1 #define EC_MAX_RESPONSE_OVERHEAD 32 +/* + * ACPI notify value for MKBP host event. + */ +#define ACPI_NOTIFY_CROS_EC_MKBP 0x80 + /* * EC panic is not covered by the standard (0-F) ACPI notify values. * Arbitrarily choosing B0 to notify ec panic, which is in the 84-BF @@ -246,6 +251,8 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); +int cros_ec_rwsig_continue(struct cros_ec_device *ec_dev); + int cros_ec_query_all(struct cros_ec_device *ec_dev); int cros_ec_get_next_event(struct cros_ec_device *ec_dev, diff --git a/include/linux/platform_data/i2c-davinci.h b/include/linux/platform_data/i2c-davinci.h deleted file mode 100644 index 98967df07468..000000000000 --- a/include/linux/platform_data/i2c-davinci.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * DaVinci I2C controller platform_device info - * - * Author: Vladimir Barinov, MontaVista Software, Inc. - * - * 2007 (c) MontaVista Software, Inc. This file is licensed under - * the terms of the GNU General Public License version 2. This program - * is licensed "as is" without any warranty of any kind, whether express - * or implied. -*/ - -#ifndef __ASM_ARCH_I2C_H -#define __ASM_ARCH_I2C_H - -/* All frequencies are expressed in kHz */ -struct davinci_i2c_platform_data { - unsigned int bus_freq; /* standard bus frequency (kHz) */ - unsigned int bus_delay; /* post-transaction delay (usec) */ - bool gpio_recovery; /* Use GPIO recovery method */ - bool has_pfunc; /* Chip has a ICPFUNC register */ -}; - -/* for board setup code */ -void davinci_init_i2c(struct davinci_i2c_platform_data *); - -#endif /* __ASM_ARCH_I2C_H */ diff --git a/include/linux/platform_data/keyscan-davinci.h b/include/linux/platform_data/keyscan-davinci.h deleted file mode 100644 index 260d596ba0af..000000000000 --- a/include/linux/platform_data/keyscan-davinci.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2009 Texas Instruments, Inc - * - * Author: Miguel Aguilar - */ - -#ifndef DAVINCI_KEYSCAN_H -#define DAVINCI_KEYSCAN_H - -#include - -enum davinci_matrix_types { - DAVINCI_KEYSCAN_MATRIX_4X4, - DAVINCI_KEYSCAN_MATRIX_5X3, -}; - -struct davinci_ks_platform_data { - int (*device_enable)(struct device *dev); - unsigned short *keymap; - u32 keymapsize; - u8 rep:1; - u8 strobe; - u8 interval; - u8 matrix_type; -}; - -#endif - diff --git a/include/linux/platform_data/syscon.h b/include/linux/platform_data/syscon.h deleted file mode 100644 index 2c089dd3e2bd..000000000000 --- a/include/linux/platform_data/syscon.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PLATFORM_DATA_SYSCON_H -#define PLATFORM_DATA_SYSCON_H - -struct syscon_platform_data { - const char *label; -}; - -#endif diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 365e119bebaa..783e2a336861 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -184,6 +184,11 @@ static const struct dmi_system_id asus_use_hid_led_dmi_ids[] = { DMI_MATCH(DMI_PRODUCT_FAMILY, "ROG Flow"), }, }, + { + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "ProArt P16"), + }, + }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "GA403U"), diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index f5492ed413f3..8ab5b0e8eb2c 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -9,6 +9,7 @@ #ifndef _PLATFORM_PROFILE_H_ #define _PLATFORM_PROFILE_H_ +#include #include /* @@ -23,20 +24,34 @@ enum platform_profile_option { PLATFORM_PROFILE_BALANCED, PLATFORM_PROFILE_BALANCED_PERFORMANCE, PLATFORM_PROFILE_PERFORMANCE, + PLATFORM_PROFILE_CUSTOM, PLATFORM_PROFILE_LAST, /*must always be last */ }; -struct platform_profile_handler { - unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; - int (*profile_get)(struct platform_profile_handler *pprof, - enum platform_profile_option *profile); - int (*profile_set)(struct platform_profile_handler *pprof, - enum platform_profile_option profile); +/** + * struct platform_profile_ops - platform profile operations + * @probe: Callback to setup choices available to the new class device. These + * choices will only be enforced when setting a new profile, not when + * getting the current one. + * @profile_get: Callback that will be called when showing the current platform + * profile in sysfs. + * @profile_set: Callback that will be called when storing a new platform + * profile in sysfs. + */ +struct platform_profile_ops { + int (*probe)(void *drvdata, unsigned long *choices); + int (*profile_get)(struct device *dev, enum platform_profile_option *profile); + int (*profile_set)(struct device *dev, enum platform_profile_option profile); }; -int platform_profile_register(struct platform_profile_handler *pprof); -int platform_profile_remove(void); +struct device *platform_profile_register(struct device *dev, const char *name, + void *drvdata, + const struct platform_profile_ops *ops); +int platform_profile_remove(struct device *dev); +struct device *devm_platform_profile_register(struct device *dev, const char *name, + void *drvdata, + const struct platform_profile_ops *ops); int platform_profile_cycle(void); -void platform_profile_notify(void); +void platform_profile_notify(struct device *dev); #endif /*_PLATFORM_PROFILE_H_*/ diff --git a/include/linux/pldmfw.h b/include/linux/pldmfw.h index 0fc831338226..f5047983004f 100644 --- a/include/linux/pldmfw.h +++ b/include/linux/pldmfw.h @@ -125,9 +125,17 @@ struct pldmfw_ops; * a pointer to their own data, used to implement the device specific * operations. */ + +enum pldmfw_update_mode { + PLDMFW_UPDATE_MODE_FULL, + PLDMFW_UPDATE_MODE_SINGLE_COMPONENT, +}; + struct pldmfw { const struct pldmfw_ops *ops; struct device *dev; + u16 component_identifier; + enum pldmfw_update_mode mode; }; bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record); diff --git a/include/linux/pm.h b/include/linux/pm.h index e7f0260f15ad..78855d794342 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -384,12 +384,8 @@ const struct dev_pm_ops name = { \ #ifdef CONFIG_PM #define _EXPORT_DEV_PM_OPS(name, license, ns) _EXPORT_PM_OPS(name, license, ns) -#define EXPORT_PM_FN_GPL(name) EXPORT_SYMBOL_GPL(name) -#define EXPORT_PM_FN_NS_GPL(name, ns) EXPORT_SYMBOL_NS_GPL(name, "ns") #else #define _EXPORT_DEV_PM_OPS(name, license, ns) _DISCARD_PM_OPS(name, license, ns) -#define EXPORT_PM_FN_GPL(name) -#define EXPORT_PM_FN_NS_GPL(name, ns) #endif #ifdef CONFIG_PM_SLEEP @@ -570,7 +566,8 @@ const struct dev_pm_ops name = { \ { .event = PM_EVENT_AUTO_RESUME, }) #define PMSG_IS_AUTO(msg) (((msg).event & PM_EVENT_AUTO) != 0) - +#define PMSG_NO_WAKEUP(msg) (((msg).event & \ + (PM_EVENT_FREEZE | PM_EVENT_QUIESCE)) != 0) /* * Device run-time power management status. * @@ -683,6 +680,7 @@ struct dev_pm_info { bool no_pm_callbacks:1; /* Owned by the PM core */ bool async_in_progress:1; /* Owned by the PM core */ bool must_resume:1; /* Owned by the PM core */ + bool set_active:1; /* Owned by the PM core */ bool may_skip_resume:1; /* Set by subsystems */ #else bool should_wakeup:1; diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 45646bfcaf1a..1aab31370065 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -147,6 +147,7 @@ struct genpd_governor_data { }; struct genpd_power_state { + const char *name; s64 power_off_latency_ns; s64 power_on_latency_ns; s64 residency_ns; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 568183e3e641..c247317aae38 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -100,8 +100,11 @@ struct dev_pm_opp_data { #if defined(CONFIG_PM_OPP) struct opp_table *dev_pm_opp_get_opp_table(struct device *dev); +void dev_pm_opp_get_opp_table_ref(struct opp_table *opp_table); void dev_pm_opp_put_opp_table(struct opp_table *opp_table); +unsigned long dev_pm_opp_get_bw(struct dev_pm_opp *opp, bool peak, int index); + unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); int dev_pm_opp_get_supplies(struct dev_pm_opp *opp, struct dev_pm_opp_supply *supplies); @@ -158,6 +161,7 @@ struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, unsigned int *bw, int index); +void dev_pm_opp_get(struct dev_pm_opp *opp); void dev_pm_opp_put(struct dev_pm_opp *opp); int dev_pm_opp_add_dynamic(struct device *dev, struct dev_pm_opp_data *opp); @@ -203,8 +207,15 @@ static inline struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device * return ERR_PTR(-EOPNOTSUPP); } +static inline void dev_pm_opp_get_opp_table_ref(struct opp_table *opp_table) {} + static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {} +static inline unsigned long dev_pm_opp_get_bw(struct dev_pm_opp *opp, bool peak, int index) +{ + return 0; +} + static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { return 0; @@ -334,6 +345,8 @@ static inline struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline void dev_pm_opp_get(struct dev_pm_opp *opp) {} + static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} static inline int diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h index d9642c6cf852..25b63ed51b76 100644 --- a/include/linux/pm_wakeirq.h +++ b/include/linux/pm_wakeirq.h @@ -10,6 +10,7 @@ extern int dev_pm_set_wake_irq(struct device *dev, int irq); extern int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq); extern int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq); extern void dev_pm_clear_wake_irq(struct device *dev); +extern int devm_pm_set_wake_irq(struct device *dev, int irq); #else /* !CONFIG_PM */ @@ -32,5 +33,10 @@ static inline void dev_pm_clear_wake_irq(struct device *dev) { } +static inline int devm_pm_set_wake_irq(struct device *dev, int irq) +{ + return 0; +} + #endif /* CONFIG_PM */ #endif /* _LINUX_PM_WAKEIRQ_H */ diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 222f7530806c..d501c09c60cd 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -240,4 +240,21 @@ static inline int device_init_wakeup(struct device *dev, bool enable) return 0; } +static void device_disable_wakeup(void *dev) +{ + device_init_wakeup(dev, false); +} + +/** + * devm_device_init_wakeup - Resource managed device wakeup initialization. + * @dev: Device to handle. + * + * This function is the devm managed version of device_init_wakeup(dev, true). + */ +static inline int devm_device_init_wakeup(struct device *dev) +{ + device_init_wakeup(dev, true); + return devm_add_action_or_reset(dev, device_disable_wakeup, dev); +} + #endif /* _LINUX_PM_WAKEUP_H */ diff --git a/include/linux/pmbus.h b/include/linux/pmbus.h index fa9f08164c36..884040e1383b 100644 --- a/include/linux/pmbus.h +++ b/include/linux/pmbus.h @@ -73,6 +73,20 @@ */ #define PMBUS_USE_COEFFICIENTS_CMD BIT(5) +/* + * PMBUS_OP_PROTECTED + * Set if the chip OPERATION command is protected and protection is not + * determined by the standard WRITE_PROTECT command. + */ +#define PMBUS_OP_PROTECTED BIT(6) + +/* + * PMBUS_VOUT_PROTECTED + * Set if the chip VOUT_COMMAND command is protected and protection is not + * determined by the standard WRITE_PROTECT command. + */ +#define PMBUS_VOUT_PROTECTED BIT(7) + struct pmbus_platform_data { u32 flags; /* Device specific flags */ diff --git a/include/linux/poll.h b/include/linux/poll.h index d1ea4f3714a8..12bb18e8b978 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -25,14 +25,14 @@ struct poll_table_struct; -/* +/* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* - * Do not touch the structure directly, use the access functions - * poll_does_not_wait() and poll_requested_events() instead. + * Do not touch the structure directly, use the access function + * poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; @@ -41,18 +41,16 @@ typedef struct poll_table_struct { static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { - if (p && p->_qproc && wait_address) + if (p && p->_qproc) { p->_qproc(filp, wait_address, p); -} - -/* - * Return true if it is guaranteed that poll will not wait. This is the case - * if the poll() of another file descriptor in the set got an event, so there - * is no need for waiting. - */ -static inline bool poll_does_not_wait(const poll_table *p) -{ - return p == NULL || p->_qproc == NULL; + /* + * This memory barrier is paired in the wq_has_sleeper(). + * See the comment above prepare_to_wait(), we need to + * ensure that subsequent tests in this thread can't be + * reordered with __add_wait_queue() in _qproc() paths. + */ + smp_mb(); + } } /* diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 5180dc9f1706..6b190639b08e 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -61,6 +61,7 @@ struct bq27xxx_device_info { struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; + int voltage_min_design; bool removed; unsigned long last_update; union power_supply_propval last_status; diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index b98106e1a90f..6ed53b292162 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -15,6 +15,8 @@ #include #include #include +#include +#include #include #include @@ -40,7 +42,7 @@ enum { }; /* What algorithm is the charger using? */ -enum { +enum power_supply_charge_type { POWER_SUPPLY_CHARGE_TYPE_UNKNOWN = 0, POWER_SUPPLY_CHARGE_TYPE_NONE, POWER_SUPPLY_CHARGE_TYPE_TRICKLE, /* slow speed */ @@ -58,6 +60,7 @@ enum { POWER_SUPPLY_HEALTH_OVERHEAT, POWER_SUPPLY_HEALTH_DEAD, POWER_SUPPLY_HEALTH_OVERVOLTAGE, + POWER_SUPPLY_HEALTH_UNDERVOLTAGE, POWER_SUPPLY_HEALTH_UNSPEC_FAILURE, POWER_SUPPLY_HEALTH_COLD, POWER_SUPPLY_HEALTH_WATCHDOG_TIMER_EXPIRE, @@ -99,6 +102,7 @@ enum power_supply_property { /* Properties of type `int' */ POWER_SUPPLY_PROP_STATUS = 0, POWER_SUPPLY_PROP_CHARGE_TYPE, + POWER_SUPPLY_PROP_CHARGE_TYPES, POWER_SUPPLY_PROP_HEALTH, POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_ONLINE, @@ -245,6 +249,7 @@ struct power_supply_desc { const char *name; enum power_supply_type type; u8 charge_behaviours; + u32 charge_types; u32 usb_types; const enum power_supply_property *properties; size_t num_properties; @@ -281,6 +286,28 @@ struct power_supply_desc { int use_for_apm; }; +struct power_supply_ext { + const char *const name; + u8 charge_behaviours; + const enum power_supply_property *properties; + size_t num_properties; + + int (*get_property)(struct power_supply *psy, + const struct power_supply_ext *ext, + void *data, + enum power_supply_property psp, + union power_supply_propval *val); + int (*set_property)(struct power_supply *psy, + const struct power_supply_ext *ext, + void *data, + enum power_supply_property psp, + const union power_supply_propval *val); + int (*property_is_writeable)(struct power_supply *psy, + const struct power_supply_ext *ext, + void *data, + enum power_supply_property psp); +}; + struct power_supply { const struct power_supply_desc *desc; @@ -300,10 +327,13 @@ struct power_supply { struct delayed_work deferred_register_work; spinlock_t changed_lock; bool changed; + bool update_groups; bool initialized; bool removing; atomic_t use_cnt; struct power_supply_battery_info *battery_info; + struct rw_semaphore extensions_sem; /* protects "extensions" */ + struct list_head extensions; #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd; struct thermal_cooling_device *tcd; @@ -318,6 +348,8 @@ struct power_supply { #endif }; +#define dev_to_psy(__dev) container_of_const(__dev, struct power_supply, dev) + /* * This is recommended structure to specify static power supply parameters. * Generic one, parametrizable for different power supplies. Power supply @@ -878,10 +910,18 @@ devm_power_supply_register(struct device *parent, extern void power_supply_unregister(struct power_supply *psy); extern int power_supply_powers(struct power_supply *psy, struct device *dev); +extern int __must_check +power_supply_register_extension(struct power_supply *psy, + const struct power_supply_ext *ext, + struct device *dev, + void *data); +extern void power_supply_unregister_extension(struct power_supply *psy, + const struct power_supply_ext *ext); + #define to_power_supply(device) container_of(device, struct power_supply, dev) extern void *power_supply_get_drvdata(struct power_supply *psy); -extern int power_supply_for_each_device(void *data, int (*fn)(struct device *dev, void *data)); +extern int power_supply_for_each_psy(void *data, int (*fn)(struct power_supply *psy, void *data)); static inline bool power_supply_is_amp_property(enum power_supply_property psp) { @@ -944,6 +984,11 @@ ssize_t power_supply_charge_behaviour_show(struct device *dev, char *buf); int power_supply_charge_behaviour_parse(unsigned int available_behaviours, const char *buf); +ssize_t power_supply_charge_types_show(struct device *dev, + unsigned int available_types, + enum power_supply_charge_type current_type, + char *buf); +int power_supply_charge_types_parse(unsigned int available_types, const char *buf); #else static inline ssize_t power_supply_charge_behaviour_show(struct device *dev, @@ -959,6 +1004,20 @@ static inline int power_supply_charge_behaviour_parse(unsigned int available_beh { return -EOPNOTSUPP; } + +static inline +ssize_t power_supply_charge_types_show(struct device *dev, + unsigned int available_types, + enum power_supply_charge_type current_type, + char *buf) +{ + return -EOPNOTSUPP; +} + +static inline int power_supply_charge_types_parse(unsigned int available_types, const char *buf) +{ + return -EOPNOTSUPP; +} #endif #endif /* __LINUX_POWER_SUPPLY_H__ */ diff --git a/include/linux/pps_gen_kernel.h b/include/linux/pps_gen_kernel.h new file mode 100644 index 000000000000..022ea0ac4440 --- /dev/null +++ b/include/linux/pps_gen_kernel.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * PPS generator API kernel header + * + * Copyright (C) 2024 Rodolfo Giometti + */ + +#ifndef LINUX_PPS_GEN_KERNEL_H +#define LINUX_PPS_GEN_KERNEL_H + +#include +#include +#include + +/* + * Global defines + */ + +#define PPS_GEN_MAX_SOURCES 16 /* should be enough... */ + +struct pps_gen_device; + +/** + * struct pps_gen_source_info - the specific PPS generator info + * @use_system_clock: true, if the system clock is used to generate pulses + * @get_time: query the time stored into the generator clock + * @enable: enable/disable the PPS pulses generation + * + * This is the main generator struct where all needed information must be + * placed before calling the pps_gen_register_source(). + */ +struct pps_gen_source_info { + bool use_system_clock; + + int (*get_time)(struct pps_gen_device *pps_gen, + struct timespec64 *time); + int (*enable)(struct pps_gen_device *pps_gen, bool enable); + +/* private: internal use only */ + struct module *owner; + struct device *parent; /* for device_create */ +}; + +/* The main struct */ +struct pps_gen_device { + struct pps_gen_source_info info; /* PSS generator info */ + bool enabled; /* PSS generator status */ + + unsigned int event; + unsigned int sequence; + + unsigned int last_ev; /* last PPS event id */ + wait_queue_head_t queue; /* PPS event queue */ + + unsigned int id; /* PPS generator unique ID */ + struct cdev cdev; + struct device *dev; + struct fasync_struct *async_queue; /* fasync method */ + spinlock_t lock; +}; + +/* + * Global variables + */ + +extern const struct attribute_group *pps_gen_groups[]; + +/* + * Exported functions + */ + +extern struct pps_gen_device *pps_gen_register_source( + struct pps_gen_source_info *info); +extern void pps_gen_unregister_source(struct pps_gen_device *pps_gen); +extern void pps_gen_event(struct pps_gen_device *pps_gen, + unsigned int event, void *data); + +#endif /* LINUX_PPS_GEN_KERNEL_H */ diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 78c8ac4951b5..c7abce28ed29 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -56,8 +56,7 @@ struct pps_device { unsigned int id; /* PPS source unique ID */ void const *lookup_cookie; /* For pps_lookup_dev() only */ - struct cdev cdev; - struct device *dev; + struct device dev; struct fasync_struct *async_queue; /* fasync method */ spinlock_t lock; }; diff --git a/include/linux/prmt.h b/include/linux/prmt.h index 9c094294403f..c53ab287e932 100644 --- a/include/linux/prmt.h +++ b/include/linux/prmt.h @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ +#include + #ifdef CONFIG_ACPI_PRMT void init_prmt(void); int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer); diff --git a/include/linux/property.h b/include/linux/property.h index 61fc20e5f81f..e214ecd241eb 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -37,6 +37,7 @@ struct fwnode_handle *__dev_fwnode(struct device *dev); struct device *: __dev_fwnode)(dev) bool device_property_present(const struct device *dev, const char *propname); +bool device_property_read_bool(const struct device *dev, const char *propname); int device_property_read_u8_array(const struct device *dev, const char *propname, u8 *val, size_t nval); int device_property_read_u16_array(const struct device *dev, const char *propname, @@ -54,6 +55,8 @@ int device_property_match_string(const struct device *dev, bool fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname); +bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, + const char *propname); int fwnode_property_read_u8_array(const struct fwnode_handle *fwnode, const char *propname, u8 *val, size_t nval); @@ -207,12 +210,6 @@ int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); unsigned int device_get_child_node_count(const struct device *dev); -static inline bool device_property_read_bool(const struct device *dev, - const char *propname) -{ - return device_property_present(dev, propname); -} - static inline int device_property_read_u8(const struct device *dev, const char *propname, u8 *val) { @@ -263,12 +260,6 @@ static inline int device_property_string_array_count(const struct device *dev, return device_property_read_string_array(dev, propname, NULL, 0); } -static inline bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, - const char *propname) -{ - return fwnode_property_present(fwnode, propname); -} - static inline int fwnode_property_read_u8(const struct fwnode_handle *fwnode, const char *propname, u8 *val) { diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h index c9a31c567e85..2e18fef1a2e1 100644 --- a/include/linux/pruss_driver.h +++ b/include/linux/pruss_driver.h @@ -144,32 +144,32 @@ static inline int pruss_release_mem_region(struct pruss *pruss, static inline int pruss_cfg_get_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 *mux) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } static inline int pruss_cfg_set_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 mux) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } static inline int pruss_cfg_gpimode(struct pruss *pruss, enum pruss_pru_id pru_id, enum pruss_gpi_mode mode) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } static inline int pruss_cfg_miirt_enable(struct pruss *pruss, bool enable) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } static inline int pruss_cfg_xfr_enable(struct pruss *pruss, enum pru_type pru_type, - bool enable); + bool enable) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } #endif /* CONFIG_TI_PRUSS */ diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index 591a53e082e6..c773eeb92d04 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -5,15 +5,37 @@ #ifndef _LINUX_PSE_CONTROLLER_H #define _LINUX_PSE_CONTROLLER_H -#include #include #include /* Maximum current in uA according to IEEE 802.3-2022 Table 145-1 */ #define MAX_PI_CURRENT 1920000 +/* Maximum power in mW according to IEEE 802.3-2022 Table 145-16 */ +#define MAX_PI_PW 99900 struct phy_device; struct pse_controller_dev; +struct netlink_ext_ack; + +/* C33 PSE extended state and substate. */ +struct ethtool_c33_pse_ext_state_info { + enum ethtool_c33_pse_ext_state c33_pse_ext_state; + union { + enum ethtool_c33_pse_ext_substate_error_condition error_condition; + enum ethtool_c33_pse_ext_substate_mr_pse_enable mr_pse_enable; + enum ethtool_c33_pse_ext_substate_option_detect_ted option_detect_ted; + enum ethtool_c33_pse_ext_substate_option_vport_lim option_vport_lim; + enum ethtool_c33_pse_ext_substate_ovld_detected ovld_detected; + enum ethtool_c33_pse_ext_substate_power_not_available power_not_available; + enum ethtool_c33_pse_ext_substate_short_detected short_detected; + u32 __c33_pse_ext_substate; + }; +}; + +struct ethtool_c33_pse_pw_limit_range { + u32 min; + u32 max; +}; /** * struct pse_control_config - PSE control/channel configuration. @@ -29,7 +51,52 @@ struct pse_control_config { }; /** - * struct pse_control_status - PSE control/channel status. + * struct pse_admin_state - PSE operational state + * + * @podl_admin_state: operational state of the PoDL PSE + * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState + * @c33_admin_state: operational state of the PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + */ +struct pse_admin_state { + enum ethtool_podl_pse_admin_state podl_admin_state; + enum ethtool_c33_pse_admin_state c33_admin_state; +}; + +/** + * struct pse_pw_status - PSE power detection status + * + * @podl_pw_status: power detection status of the PoDL PSE. + * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + * @c33_pw_status: power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: + */ +struct pse_pw_status { + enum ethtool_podl_pse_pw_d_status podl_pw_status; + enum ethtool_c33_pse_pw_d_status c33_pw_status; +}; + +/** + * struct pse_ext_state_info - PSE extended state information + * + * @c33_ext_state_info: extended state information of the PSE + */ +struct pse_ext_state_info { + struct ethtool_c33_pse_ext_state_info c33_ext_state_info; +}; + +/** + * struct pse_pw_limit_ranges - PSE power limit configuration range + * + * @c33_pw_limit_ranges: supported power limit configuration range. The driver + * is in charge of the memory allocation. + */ +struct pse_pw_limit_ranges { + struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; +}; + +/** + * struct ethtool_pse_control_status - PSE control/channel status. * * @podl_admin_state: operational state of the PoDL PSE * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState @@ -47,11 +114,11 @@ struct pse_control_config { * @c33_avail_pw_limit: available power limit of the PSE in mW * IEEE 802.3-2022 145.2.5.4 pse_avail_pwr * @c33_pw_limit_ranges: supported power limit configuration range. The driver - * is in charge of the memory allocation. + * is in charge of the memory allocation * @c33_pw_limit_nb_ranges: number of supported power limit configuration * ranges */ -struct pse_control_status { +struct ethtool_pse_control_status { enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; enum ethtool_c33_pse_admin_state c33_admin_state; @@ -67,40 +134,51 @@ struct pse_control_status { /** * struct pse_controller_ops - PSE controller driver callbacks * - * @ethtool_get_status: get PSE control status for ethtool interface * @setup_pi_matrix: setup PI matrix of the PSE controller - * @pi_is_enabled: Return 1 if the PSE PI is enabled, 0 if not. - * May also return negative errno. + * @pi_get_admin_state: Get the operational state of the PSE PI. This ops + * is mandatory. + * @pi_get_pw_status: Get the power detection status of the PSE PI. This + * ops is mandatory. + * @pi_get_ext_state: Get the extended state of the PSE PI. + * @pi_get_pw_class: Get the power class of the PSE PI. + * @pi_get_actual_pw: Get actual power of the PSE PI in mW. * @pi_enable: Configure the PSE PI as enabled. * @pi_disable: Configure the PSE PI as disabled. * @pi_get_voltage: Return voltage similarly to get_voltage regulator - * callback. - * @pi_get_current_limit: Get the configured current limit similarly to - * get_current_limit regulator callback. - * @pi_set_current_limit: Configure the current limit similarly to - * set_current_limit regulator callback. - * Should not return an error in case of MAX_PI_CURRENT - * current value set. + * callback in uV. + * @pi_get_pw_limit: Get the configured power limit of the PSE PI in mW. + * @pi_set_pw_limit: Configure the power limit of the PSE PI in mW. + * @pi_get_pw_limit_ranges: Get the supported power limit configuration + * range. The driver is in charge of the memory + * allocation and should return the number of + * ranges. */ struct pse_controller_ops { - int (*ethtool_get_status)(struct pse_controller_dev *pcdev, - unsigned long id, struct netlink_ext_ack *extack, - struct pse_control_status *status); int (*setup_pi_matrix)(struct pse_controller_dev *pcdev); - int (*pi_is_enabled)(struct pse_controller_dev *pcdev, int id); + int (*pi_get_admin_state)(struct pse_controller_dev *pcdev, int id, + struct pse_admin_state *admin_state); + int (*pi_get_pw_status)(struct pse_controller_dev *pcdev, int id, + struct pse_pw_status *pw_status); + int (*pi_get_ext_state)(struct pse_controller_dev *pcdev, int id, + struct pse_ext_state_info *ext_state_info); + int (*pi_get_pw_class)(struct pse_controller_dev *pcdev, int id); + int (*pi_get_actual_pw)(struct pse_controller_dev *pcdev, int id); int (*pi_enable)(struct pse_controller_dev *pcdev, int id); int (*pi_disable)(struct pse_controller_dev *pcdev, int id); int (*pi_get_voltage)(struct pse_controller_dev *pcdev, int id); - int (*pi_get_current_limit)(struct pse_controller_dev *pcdev, - int id); - int (*pi_set_current_limit)(struct pse_controller_dev *pcdev, - int id, int max_uA); + int (*pi_get_pw_limit)(struct pse_controller_dev *pcdev, + int id); + int (*pi_set_pw_limit)(struct pse_controller_dev *pcdev, + int id, int max_mW); + int (*pi_get_pw_limit_ranges)(struct pse_controller_dev *pcdev, int id, + struct pse_pw_limit_ranges *pw_limit_ranges); }; struct module; struct device_node; struct of_phandle_args; struct pse_control; +struct ethtool_pse_control_status; /* PSE PI pairset pinout can either be Alternative A or Alternative B */ enum pse_pi_pairset_pinout { @@ -177,15 +255,13 @@ void pse_control_put(struct pse_control *psec); int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, - struct pse_control_status *status); + struct ethtool_pse_control_status *status); int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config); int pse_ethtool_set_pw_limit(struct pse_control *psec, struct netlink_ext_ack *extack, const unsigned int pw_limit); -int pse_ethtool_get_pw_limit(struct pse_control *psec, - struct netlink_ext_ack *extack); bool pse_has_podl(struct pse_control *psec); bool pse_has_c33(struct pse_control *psec); @@ -203,7 +279,7 @@ static inline void pse_control_put(struct pse_control *psec) static inline int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, - struct pse_control_status *status) + struct ethtool_pse_control_status *status) { return -EOPNOTSUPP; } @@ -222,12 +298,6 @@ static inline int pse_ethtool_set_pw_limit(struct pse_control *psec, return -EOPNOTSUPP; } -static inline int pse_ethtool_get_pw_limit(struct pse_control *psec, - struct netlink_ext_ack *extack) -{ - return -EOPNOTSUPP; -} - static inline bool pse_has_podl(struct pse_control *psec) { return false; diff --git a/include/linux/pseudo_fs.h b/include/linux/pseudo_fs.h index 730f77381d55..2503f7625d65 100644 --- a/include/linux/pseudo_fs.h +++ b/include/linux/pseudo_fs.h @@ -5,6 +5,7 @@ struct pseudo_fs_context { const struct super_operations *ops; + const struct export_operations *eops; const struct xattr_handler * const *xattr; const struct dentry_operations *dops; unsigned long magic; diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index c892d22ce0a7..0d68d09bedd1 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -307,7 +307,7 @@ static inline u64 adjust_by_scaled_ppm(u64 base, long scaled_ppm) * @info: Structure describing the new clock. * @parent: Pointer to the parent device of the new clock. * - * Returns a valid pointer on success or PTR_ERR on failure. If PHC + * Returns: a valid pointer on success or PTR_ERR on failure. If PHC * support is missing at the configuration level, this function * returns NULL, and drivers are expected to gracefully handle that * case separately. @@ -445,7 +445,7 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); * @hwtstamp: timestamp * @vclock_index: phc index of ptp vclock. * - * Returns converted timestamp, or 0 on error. + * Returns: converted timestamp, or 0 on error. */ ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index); #else diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index fd037c127bb0..551329220e4f 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -615,15 +615,14 @@ static inline int ptr_ring_resize_noprof(struct ptr_ring *r, int size, gfp_t gfp /* * Note: producer lock is nested within consumer lock, so if you * resize you must make sure all uses nest correctly. - * In particular if you consume ring in interrupt or BH context, you must - * disable interrupts/BH when doing so. + * In particular if you consume ring in BH context, you must + * disable BH when doing so. */ -static inline int ptr_ring_resize_multiple_noprof(struct ptr_ring **rings, - unsigned int nrings, - int size, - gfp_t gfp, void (*destroy)(void *)) +static inline int ptr_ring_resize_multiple_bh_noprof(struct ptr_ring **rings, + unsigned int nrings, + int size, gfp_t gfp, + void (*destroy)(void *)) { - unsigned long flags; void ***queues; int i; @@ -638,12 +637,12 @@ static inline int ptr_ring_resize_multiple_noprof(struct ptr_ring **rings, } for (i = 0; i < nrings; ++i) { - spin_lock_irqsave(&(rings[i])->consumer_lock, flags); + spin_lock_bh(&(rings[i])->consumer_lock); spin_lock(&(rings[i])->producer_lock); queues[i] = __ptr_ring_swap_queue(rings[i], queues[i], size, gfp, destroy); spin_unlock(&(rings[i])->producer_lock); - spin_unlock_irqrestore(&(rings[i])->consumer_lock, flags); + spin_unlock_bh(&(rings[i])->consumer_lock); } for (i = 0; i < nrings; ++i) @@ -662,8 +661,8 @@ nomem: noqueues: return -ENOMEM; } -#define ptr_ring_resize_multiple(...) \ - alloc_hooks(ptr_ring_resize_multiple_noprof(__VA_ARGS__)) +#define ptr_ring_resize_multiple_bh(...) \ + alloc_hooks(ptr_ring_resize_multiple_bh_noprof(__VA_ARGS__)) static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *)) { diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 6853e29d9674..a2df509056ac 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -347,6 +347,23 @@ struct pwm_chip { struct pwm_device pwms[] __counted_by(npwm); }; +/** + * pwmchip_supports_waveform() - checks if the given chip supports waveform callbacks + * @chip: The pwm_chip to test + * + * Returns true iff the pwm chip support the waveform functions like + * pwm_set_waveform_might_sleep() and pwm_round_waveform_might_sleep() + */ +static inline bool pwmchip_supports_waveform(struct pwm_chip *chip) +{ + /* + * only check for .write_waveform(). If that is available, + * .round_waveform_tohw() and .round_waveform_fromhw() asserted to be + * available, too, in pwmchip_add(). + */ + return chip->ops->write_waveform != NULL; +} + static inline struct device *pwmchip_parent(const struct pwm_chip *chip) { return chip->dev.parent; diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index 7c173aa64e1e..8d2ba3749866 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -210,6 +210,43 @@ rb_add(struct rb_node *node, struct rb_root *tree, rb_insert_color(node, tree); } +/** + * rb_find_add_cached() - find equivalent @node in @tree, or add @node + * @node: node to look-for / insert + * @tree: tree to search / modify + * @cmp: operator defining the node order + * + * Returns the rb_node matching @node, or NULL when no match is found and @node + * is inserted. + */ +static __always_inline struct rb_node * +rb_find_add_cached(struct rb_node *node, struct rb_root_cached *tree, + int (*cmp)(const struct rb_node *new, const struct rb_node *exist)) +{ + bool leftmost = true; + struct rb_node **link = &tree->rb_root.rb_node; + struct rb_node *parent = NULL; + int c; + + while (*link) { + parent = *link; + c = cmp(node, parent); + + if (c < 0) { + link = &parent->rb_left; + } else if (c > 0) { + link = &parent->rb_right; + leftmost = false; + } else { + return parent; + } + } + + rb_link_node(node, parent, link); + rb_insert_color_cached(node, tree, leftmost); + return NULL; +} + /** * rb_find_add() - find equivalent @node in @tree, or add @node * @node: node to look-for / insert diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 14dfa6008467..1b11926ddd47 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -30,6 +30,17 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) +/* + * Return the ->prev pointer of a list_head in an rcu safe way. Don't + * access it directly. + * + * Any list traversed with list_bidir_prev_rcu() must never use + * list_del_rcu(). Doing so will poison the ->prev pointer that + * list_bidir_prev_rcu() relies on, which will result in segfaults. + * To prevent these segfaults, use list_bidir_del_rcu() instead + * of list_del_rcu(). + */ +#define list_bidir_prev_rcu(list) (*((struct list_head __rcu **)(&(list)->prev))) /** * list_tail_rcu - returns the prev pointer of the head of the list @@ -158,6 +169,39 @@ static inline void list_del_rcu(struct list_head *entry) entry->prev = LIST_POISON2; } +/** + * list_bidir_del_rcu - deletes entry from list without re-initialization + * @entry: the element to delete from the list. + * + * In contrast to list_del_rcu() doesn't poison the prev pointer thus + * allowing backwards traversal via list_bidir_prev_rcu(). + * + * Note: list_empty() on entry does not return true after this because + * the entry is in a special undefined state that permits RCU-based + * lockfree reverse traversal. In particular this means that we can not + * poison the forward and backwards pointers that may still be used for + * walking the list. + * + * The caller must take whatever precautions are necessary (such as + * holding appropriate locks) to avoid racing with another list-mutation + * primitive, such as list_bidir_del_rcu() or list_add_rcu(), running on + * this same list. However, it is perfectly legal to run concurrently + * with the _rcu list-traversal primitives, such as + * list_for_each_entry_rcu(). + * + * Note that list_del_rcu() and list_bidir_del_rcu() must not be used on + * the same list. + * + * Note that the caller is not permitted to immediately free + * the newly deleted entry. Instead, either synchronize_rcu() + * or call_rcu() must be used to defer freeing until an RCU + * grace period has elapsed. + */ +static inline void list_bidir_del_rcu(struct list_head *entry) +{ + __list_del_entry(entry); +} + /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index 303ab9bee155..f9bed3d3f78d 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -65,4 +65,15 @@ static inline void cond_resched_rcu(void) #endif } +// Has the current task blocked within its current RCU read-side +// critical section? +static inline bool has_rcu_reader_blocked(void) +{ +#ifdef CONFIG_PREEMPT_RCU + return !list_empty(¤t->rcu_node_entry); +#else + return false; +#endif +} + #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ diff --git a/include/linux/regmap.h b/include/linux/regmap.h index fd41baccbf3e..3a96d068915f 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -506,6 +506,32 @@ struct regmap_range_cfg { unsigned int window_len; }; +/** + * struct regmap_sdw_mbq_cfg - Configuration for Multi-Byte Quantities + * + * @mbq_size: Callback returning the actual size of the given register. + * @deferrable: Callback returning true if the hardware can defer + * transactions to the given register. Deferral should + * only be used by SDCA parts and typically which controls + * are deferrable will be specified in either as a hard + * coded list or from the DisCo tables in the platform + * firmware. + * + * @timeout_us: The time in microseconds after which waiting for a deferred + * transaction should time out. + * @retry_us: The time in microseconds between polls of the function busy + * status whilst waiting for an opportunity to retry a deferred + * transaction. + * + * Provides additional configuration required for SoundWire MBQ register maps. + */ +struct regmap_sdw_mbq_cfg { + int (*mbq_size)(struct device *dev, unsigned int reg); + bool (*deferrable)(struct device *dev, unsigned int reg); + unsigned long timeout_us; + unsigned long retry_us; +}; + struct regmap_async; typedef int (*regmap_hw_write)(void *context, const void *data, @@ -652,6 +678,7 @@ struct regmap *__regmap_init_sdw(struct sdw_slave *sdw, const char *lock_name); struct regmap *__regmap_init_sdw_mbq(struct sdw_slave *sdw, const struct regmap_config *config, + const struct regmap_sdw_mbq_cfg *mbq_config, struct lock_class_key *lock_key, const char *lock_name); struct regmap *__regmap_init_spi_avmm(struct spi_device *spi, @@ -713,6 +740,7 @@ struct regmap *__devm_regmap_init_sdw(struct sdw_slave *sdw, const char *lock_name); struct regmap *__devm_regmap_init_sdw_mbq(struct sdw_slave *sdw, const struct regmap_config *config, + const struct regmap_sdw_mbq_cfg *mbq_config, struct lock_class_key *lock_key, const char *lock_name); struct regmap *__devm_regmap_init_slimbus(struct slim_device *slimbus, @@ -942,7 +970,22 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); */ #define regmap_init_sdw_mbq(sdw, config) \ __regmap_lockdep_wrapper(__regmap_init_sdw_mbq, #config, \ - sdw, config) + sdw, config, NULL) + +/** + * regmap_init_sdw_mbq_cfg() - Initialise MBQ SDW register map with config + * + * @sdw: Device that will be interacted with + * @config: Configuration for register map + * @mbq_config: Properties for the MBQ registers + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define regmap_init_sdw_mbq_cfg(sdw, config, mbq_config) \ + __regmap_lockdep_wrapper(__regmap_init_sdw_mbq, #config, \ + sdw, config, mbq_config) /** * regmap_init_spi_avmm() - Initialize register map for Intel SPI Slave @@ -1155,7 +1198,22 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); */ #define devm_regmap_init_sdw_mbq(sdw, config) \ __regmap_lockdep_wrapper(__devm_regmap_init_sdw_mbq, #config, \ - sdw, config) + sdw, config, NULL) + +/** + * devm_regmap_init_sdw_mbq_cfg() - Initialise managed MBQ SDW register map with config + * + * @sdw: Device that will be interacted with + * @config: Configuration for register map + * @mbq_config: Properties for the MBQ registers + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_sdw_mbq_cfg(sdw, config, mbq_config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_sdw_mbq, \ + #config, sdw, config, mbq_config) /** * devm_regmap_init_slimbus() - Initialise managed register map @@ -1244,7 +1302,7 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count); -int regmap_multi_reg_read(struct regmap *map, unsigned int *reg, void *val, +int regmap_multi_reg_read(struct regmap *map, const unsigned int *reg, void *val, size_t val_count); int regmap_update_bits_base(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 8c3c372ad735..ffe912f345ae 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -168,29 +168,6 @@ int devm_regulator_get_enable_read_voltage(struct device *dev, const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); -#if IS_ENABLED(CONFIG_OF) -struct regulator *__must_check of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id); -struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id); -#else -static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} - -static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} -#endif - int regulator_register_supply_alias(struct device *dev, const char *id, struct device *alias_dev, const char *alias_id); @@ -223,8 +200,6 @@ int regulator_disable_deferred(struct regulator *regulator, int ms); int __must_check regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); -int __must_check of_regulator_bulk_get_all(struct device *dev, struct device_node *np, - struct regulator_bulk_data **consumers); int __must_check devm_regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); void devm_regulator_bulk_put(struct regulator_bulk_data *consumers); @@ -258,6 +233,11 @@ int regulator_sync_voltage(struct regulator *regulator); int regulator_set_current_limit(struct regulator *regulator, int min_uA, int max_uA); int regulator_get_current_limit(struct regulator *regulator); +int regulator_get_unclaimed_power_budget(struct regulator *regulator); +int regulator_request_power_budget(struct regulator *regulator, + unsigned int pw_req); +void regulator_free_power_budget(struct regulator *regulator, + unsigned int pw); int regulator_set_mode(struct regulator *regulator, unsigned int mode); unsigned int regulator_get_mode(struct regulator *regulator); @@ -373,20 +353,6 @@ devm_regulator_get_optional(struct device *dev, const char *id) return ERR_PTR(-ENODEV); } -static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} - -static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} - static inline void regulator_put(struct regulator *regulator) { } @@ -483,12 +449,6 @@ static inline int devm_regulator_bulk_get(struct device *dev, int num_consumers, return 0; } -static inline int of_regulator_bulk_get_all(struct device *dev, struct device_node *np, - struct regulator_bulk_data **consumers) -{ - return 0; -} - static inline int devm_regulator_bulk_get_const( struct device *dev, int num_consumers, const struct regulator_bulk_data *in_consumers, @@ -571,6 +531,22 @@ static inline int regulator_get_current_limit(struct regulator *regulator) return 0; } +static inline int regulator_get_unclaimed_power_budget(struct regulator *regulator) +{ + return INT_MAX; +} + +static inline int regulator_request_power_budget(struct regulator *regulator, + unsigned int pw_req) +{ + return -EOPNOTSUPP; +} + +static inline void regulator_free_power_budget(struct regulator *regulator, + unsigned int pw) +{ +} + static inline int regulator_set_mode(struct regulator *regulator, unsigned int mode) { @@ -700,6 +676,38 @@ regulator_is_equal(struct regulator *reg1, struct regulator *reg2) } #endif +#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_REGULATOR) +struct regulator *__must_check of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id); +struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id); +int __must_check of_regulator_bulk_get_all(struct device *dev, struct device_node *np, + struct regulator_bulk_data **consumers); +#else +static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id) +{ + return ERR_PTR(-ENODEV); +} + +static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id) +{ + return ERR_PTR(-ENODEV); +} + +static inline int of_regulator_bulk_get_all(struct device *dev, struct device_node *np, + struct regulator_bulk_data **consumers) +{ + return 0; +} + +#endif + static inline int regulator_set_voltage_triplet(struct regulator *regulator, int min_uV, int target_uV, int max_uV) diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 5b66caf1695d..4a216fdba354 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -656,6 +656,8 @@ struct regulator_dev { int cached_err; bool use_cached_err; spinlock_t err_lock; + + int pw_requested_mW; }; /* diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index b3db09a7429b..1fc440c5c4c7 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -113,6 +113,7 @@ struct notification_limit { * @min_uA: Smallest current consumers may set. * @max_uA: Largest current consumers may set. * @ilim_uA: Maximum input current. + * @pw_budget_mW: Power budget for the regulator in mW. * @system_load: Load that isn't captured by any consumer requests. * * @over_curr_limits: Limits for acting on over current. @@ -185,6 +186,7 @@ struct regulation_constraints { int max_uA; int ilim_uA; + int pw_budget_mW; int system_load; /* used for coupled regulators */ diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 243633c8dceb..b427b5873de1 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -10,6 +10,7 @@ enum pca9450_chip_type { PCA9450_TYPE_PCA9450A = 0, PCA9450_TYPE_PCA9450BC, PCA9450_TYPE_PCA9451A, + PCA9450_TYPE_PCA9452, PCA9450_TYPE_AMOUNT, }; diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 997b34197385..6816e4c5f3f0 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -241,7 +241,7 @@ bool rfkill_soft_blocked(struct rfkill *rfkill); * rfkill_find_type - Helper for finding rfkill type by name * @name: the name of the type * - * Returns enum rfkill_type that corresponds to the name. + * Returns: enum rfkill_type that corresponds to the name. */ enum rfkill_type rfkill_find_type(const char *name); diff --git a/include/linux/rolling_buffer.h b/include/linux/rolling_buffer.h new file mode 100644 index 000000000000..ac15b1ffdd83 --- /dev/null +++ b/include/linux/rolling_buffer.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Rolling buffer of folios + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#ifndef _ROLLING_BUFFER_H +#define _ROLLING_BUFFER_H + +#include +#include + +/* + * Rolling buffer. Whilst the buffer is live and in use, folios and folio + * queue segments can be added to one end by one thread and removed from the + * other end by another thread. The buffer isn't allowed to be empty; it must + * always have at least one folio_queue in it so that neither side has to + * modify both queue pointers. + * + * The iterator in the buffer is extended as buffers are inserted. It can be + * snapshotted to use a segment of the buffer. + */ +struct rolling_buffer { + struct folio_queue *head; /* Producer's insertion point */ + struct folio_queue *tail; /* Consumer's removal point */ + struct iov_iter iter; /* Iterator tracking what's left in the buffer */ + u8 next_head_slot; /* Next slot in ->head */ + u8 first_tail_slot; /* First slot in ->tail */ +}; + +/* + * Snapshot of a rolling buffer. + */ +struct rolling_buffer_snapshot { + struct folio_queue *curr_folioq; /* Queue segment in which current folio resides */ + unsigned char curr_slot; /* Folio currently being read */ + unsigned char curr_order; /* Order of folio */ +}; + +/* Marks to store per-folio in the internal folio_queue structs. */ +#define ROLLBUF_MARK_1 BIT(0) +#define ROLLBUF_MARK_2 BIT(1) + +int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, + unsigned int direction); +int rolling_buffer_make_space(struct rolling_buffer *roll); +ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, + struct readahead_control *ractl, + struct folio_batch *put_batch); +ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio, + unsigned int flags); +struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll); +void rolling_buffer_clear(struct rolling_buffer *roll); + +static inline void rolling_buffer_advance(struct rolling_buffer *roll, size_t amount) +{ + iov_iter_advance(&roll->iter, amount); +} + +#endif /* _ROLLING_BUFFER_H */ diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 14b88f551920..4bc2ee0b10b0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -78,7 +78,7 @@ static inline bool lockdep_rtnl_is_held(void) * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL * @p: The pointer to read, prior to dereferencing * - * Return the value of the specified RCU-protected pointer, but omit + * Return: the value of the specified RCU-protected pointer, but omit * the READ_ONCE(), because caller holds RTNL. */ #define rtnl_dereference(p) \ @@ -102,6 +102,7 @@ void __rtnl_net_unlock(struct net *net); void rtnl_net_lock(struct net *net); void rtnl_net_unlock(struct net *net); int rtnl_net_trylock(struct net *net); +int rtnl_net_lock_killable(struct net *net); int rtnl_net_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b); bool rtnl_net_is_locked(struct net *net); @@ -138,6 +139,11 @@ static inline int rtnl_net_trylock(struct net *net) return rtnl_trylock(); } +static inline int rtnl_net_lock_killable(struct net *net) +{ + return rtnl_lock_killable(); +} + static inline void ASSERT_RTNL_NET(struct net *net) { ASSERT_RTNL(); @@ -178,6 +184,12 @@ void rtnetlink_init(void); void __rtnl_unlock(void); void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail); +/* Shared by rtnl_fdb_dump() and various ndo_fdb_dump() helpers. */ +struct ndo_fdb_dump_context { + unsigned long ifindex; + unsigned long fdb_idx; +}; + extern int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, diff --git a/include/linux/sched.h b/include/linux/sched.h index 66b311fbd5d6..9632e3318e0d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -398,6 +398,12 @@ struct sched_info { /* Time spent waiting on a runqueue: */ unsigned long long run_delay; + /* Max time spent waiting on a runqueue: */ + unsigned long long max_run_delay; + + /* Min time spent waiting on a runqueue: */ + unsigned long long min_run_delay; + /* Timestamps: */ /* When did we last run on a CPU? */ @@ -944,6 +950,7 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; @@ -1374,6 +1381,15 @@ struct task_struct { * with respect to preemption. */ unsigned long rseq_event_mask; +# ifdef CONFIG_DEBUG_RSEQ + /* + * This is a place holder to save a copy of the rseq fields for + * validation of read-only fields. The struct rseq has a + * variable-length array at the end, so it cannot be used + * directly. Reserve a size large enough for the known fields. + */ + char rseq_fields[sizeof(struct rseq)]; +# endif #endif #ifdef CONFIG_SCHED_MM_CID @@ -1637,8 +1653,9 @@ static inline unsigned int __task_state_index(unsigned int tsk_state, * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. + * Report frozen tasks as uninterruptible. */ - if (tsk_state & TASK_RTLOCK_WAIT) + if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN)) state = TASK_UNINTERRUPTIBLE; return fls(state); @@ -1943,11 +1960,10 @@ static inline void kick_process(struct task_struct *tsk) { } #endif extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); - -static inline void set_task_comm(struct task_struct *tsk, const char *from) -{ - __set_task_comm(tsk, from, false); -} +#define set_task_comm(tsk, from) ({ \ + BUILD_BUG_ON(sizeof(from) != TASK_COMM_LEN); \ + __set_task_comm(tsk, from, false); \ +}) /* * - Why not use task_lock()? diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h index 412cdaba33eb..17e04859b9a4 100644 --- a/include/linux/sched/hotplug.h +++ b/include/linux/sched/hotplug.h @@ -18,10 +18,6 @@ extern int sched_cpu_dying(unsigned int cpu); # define sched_cpu_dying NULL #endif -#ifdef CONFIG_HOTPLUG_CPU -extern void idle_task_exit(void); -#else static inline void idle_task_exit(void) {} -#endif #endif /* _LINUX_SCHED_HOTPLUG_H */ diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 2b461129d1fa..d8501f4709b5 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -7,16 +7,21 @@ #include enum hk_type { - HK_TYPE_TIMER, - HK_TYPE_RCU, - HK_TYPE_MISC, - HK_TYPE_SCHED, - HK_TYPE_TICK, HK_TYPE_DOMAIN, - HK_TYPE_WQ, HK_TYPE_MANAGED_IRQ, - HK_TYPE_KTHREAD, - HK_TYPE_MAX + HK_TYPE_KERNEL_NOISE, + HK_TYPE_MAX, + + /* + * The following housekeeping types are only set by the nohz_full + * boot commandline option. So they can share the same value. + */ + HK_TYPE_TICK = HK_TYPE_KERNEL_NOISE, + HK_TYPE_TIMER = HK_TYPE_KERNEL_NOISE, + HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, + HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, + HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, + HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 4237daa5ac7a..7f3dbafe1817 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -114,7 +114,10 @@ struct sched_domain { unsigned int lb_count[CPU_MAX_IDLE_TYPES]; unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; - unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_load[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_util[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_task[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_misfit[CPU_MAX_IDLE_TYPES]; unsigned int lb_gained[CPU_MAX_IDLE_TYPES]; unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES]; unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES]; @@ -140,9 +143,7 @@ struct sched_domain { unsigned int ttwu_move_affine; unsigned int ttwu_move_balance; #endif -#ifdef CONFIG_SCHED_DEBUG char *name; -#endif union { void *private; /* used during construction */ struct rcu_head rcu; /* used during destruction */ @@ -198,18 +199,12 @@ struct sched_domain_topology_level { int flags; int numa_level; struct sd_data data; -#ifdef CONFIG_SCHED_DEBUG char *name; -#endif }; extern void __init set_sched_topology(struct sched_domain_topology_level *tl); -#ifdef CONFIG_SCHED_DEBUG # define SD_INIT_NAME(type) .name = #type -#else -# define SD_INIT_NAME(type) -#endif #else /* CONFIG_SMP */ diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 06cd8fb2f409..0f28b4623ad4 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -63,4 +63,38 @@ extern void wake_q_add(struct wake_q_head *head, struct task_struct *task); extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task); extern void wake_up_q(struct wake_q_head *head); +/* Spin unlock helpers to unlock and call wake_up_q with preempt disabled */ +static inline +void raw_spin_unlock_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q) +{ + guard(preempt)(); + raw_spin_unlock(lock); + if (wake_q) { + wake_up_q(wake_q); + wake_q_init(wake_q); + } +} + +static inline +void raw_spin_unlock_irq_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q) +{ + guard(preempt)(); + raw_spin_unlock_irq(lock); + if (wake_q) { + wake_up_q(wake_q); + wake_q_init(wake_q); + } +} + +static inline +void raw_spin_unlock_irqrestore_wake(raw_spinlock_t *lock, unsigned long flags, + struct wake_q_head *wake_q) +{ + guard(preempt)(); + raw_spin_unlock_irqrestore(lock, flags); + if (wake_q) { + wake_up_q(wake_q); + wake_q_init(wake_q); + } +} #endif /* _LINUX_SCHED_WAKE_Q_H */ diff --git a/include/linux/scmi_imx_protocol.h b/include/linux/scmi_imx_protocol.h index 066216f1357a..53b356a26414 100644 --- a/include/linux/scmi_imx_protocol.h +++ b/include/linux/scmi_imx_protocol.h @@ -13,10 +13,11 @@ #include #include -enum scmi_nxp_protocol { - SCMI_PROTOCOL_IMX_BBM = 0x81, - SCMI_PROTOCOL_IMX_MISC = 0x84, -}; +#define SCMI_PROTOCOL_IMX_BBM 0x81 +#define SCMI_PROTOCOL_IMX_MISC 0x84 + +#define SCMI_IMX_VENDOR "NXP" +#define SCMI_IMX_SUBVENDOR "IMX" struct scmi_imx_bbm_proto_ops { int (*rtc_time_set)(const struct scmi_protocol_handle *ph, u32 id, diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 341980599c71..e45531455d3b 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -55,10 +55,10 @@ struct seccomp_data; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER static inline int secure_computing(void) { return 0; } -static inline int __secure_computing(const struct seccomp_data *sd) { return 0; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif +static inline int __secure_computing(const struct seccomp_data *sd) { return 0; } static inline long prctl_get_seccomp(void) { diff --git a/include/linux/security.h b/include/linux/security.h index cbdba435b798..980b6c207cad 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -225,6 +225,18 @@ extern unsigned long dac_mmap_min_addr; #define dac_mmap_min_addr 0UL #endif +/* + * A "security context" is the text representation of + * the information used by LSMs. + * This structure contains the string, its length, and which LSM + * it is useful for. + */ +struct lsm_context { + char *context; /* Provided by the module */ + u32 len; + int id; /* Identifies the module */ +}; + /* * Values used in the task_security_ops calls */ @@ -378,8 +390,8 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb, int security_move_mount(const struct path *from_path, const struct path *to_path); int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, - const char **xattr_name, void **ctx, - u32 *ctxlen); + const char **xattr_name, + struct lsm_context *lsmcxt); int security_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, @@ -553,14 +565,14 @@ int security_getprocattr(struct task_struct *p, int lsmid, const char *name, int security_setprocattr(int lsmid, const char *name, void *value, size_t size); int security_netlink_send(struct sock *sk, struct sk_buff *skb); int security_ismaclabel(const char *name); -int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); -int security_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, u32 *seclen); +int security_secid_to_secctx(u32 secid, struct lsm_context *cp); +int security_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp); int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid); -void security_release_secctx(char *secdata, u32 seclen); +void security_release_secctx(struct lsm_context *cp); void security_inode_invalidate_secctx(struct inode *inode); int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen); int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen); -int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen); +int security_inode_getsecctx(struct inode *inode, struct lsm_context *cp); int security_locked_down(enum lockdown_reason what); int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags); @@ -852,8 +864,7 @@ static inline int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, - void **ctx, - u32 *ctxlen) + struct lsm_context *lsmcxt) { return -EOPNOTSUPP; } @@ -1526,14 +1537,13 @@ static inline int security_ismaclabel(const char *name) return 0; } -static inline int security_secid_to_secctx(u32 secid, char **secdata, - u32 *seclen) +static inline int security_secid_to_secctx(u32 secid, struct lsm_context *cp) { return -EOPNOTSUPP; } static inline int security_lsmprop_to_secctx(struct lsm_prop *prop, - char **secdata, u32 *seclen) + struct lsm_context *cp) { return -EOPNOTSUPP; } @@ -1545,7 +1555,7 @@ static inline int security_secctx_to_secid(const char *secdata, return -EOPNOTSUPP; } -static inline void security_release_secctx(char *secdata, u32 seclen) +static inline void security_release_secctx(struct lsm_context *cp) { } @@ -1561,7 +1571,8 @@ static inline int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 { return -EOPNOTSUPP; } -static inline int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) +static inline int security_inode_getsecctx(struct inode *inode, + struct lsm_context *cp) { return -EOPNOTSUPP; } diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 5298765d6ca4..5ce48eab7a2a 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -272,7 +272,7 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) ({ \ unsigned __seq; \ \ - while ((__seq = seqprop_sequence(s)) & 1) \ + while (unlikely((__seq = seqprop_sequence(s)) & 1)) \ cpu_relax(); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ @@ -318,6 +318,29 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) __seq; \ }) +/** + * raw_seqcount_try_begin() - begin a seqcount_t read critical section + * w/o lockdep and w/o counter stabilization + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants + * @start: count to be passed to read_seqcount_retry() + * + * Similar to raw_seqcount_begin(), except it enables eliding the critical + * section entirely if odd, instead of doing the speculation knowing it will + * fail. + * + * Useful when counter stabilization is more or less equivalent to taking + * the lock and there is a slowpath that does that. + * + * If true, start will be set to the (even) sequence count read. + * + * Return: true when a read critical section is started. + */ +#define raw_seqcount_try_begin(s, start) \ +({ \ + start = raw_read_seqcount(s); \ + !(start & 1); \ +}) + /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index e0717c8393d7..144de7a7948d 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -161,8 +161,8 @@ struct uart_8250_port { void (*dl_write)(struct uart_8250_port *up, u32 value); struct uart_8250_em485 *em485; - void (*rs485_start_tx)(struct uart_8250_port *); - void (*rs485_stop_tx)(struct uart_8250_port *); + void (*rs485_start_tx)(struct uart_8250_port *up, bool toggle_ier); + void (*rs485_stop_tx)(struct uart_8250_port *up, bool toggle_ier); /* Serial port overrun backoff */ struct delayed_work overrun_backoff; diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index 926496c9cc9c..bf178238a308 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -199,17 +199,18 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } -static inline int skb_array_resize_multiple_noprof(struct skb_array **rings, - int nrings, unsigned int size, - gfp_t gfp) +static inline int skb_array_resize_multiple_bh_noprof(struct skb_array **rings, + int nrings, + unsigned int size, + gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); - return ptr_ring_resize_multiple_noprof((struct ptr_ring **)rings, - nrings, size, gfp, - __skb_array_destroy_skb); + return ptr_ring_resize_multiple_bh_noprof((struct ptr_ring **)rings, + nrings, size, gfp, + __skb_array_destroy_skb); } -#define skb_array_resize_multiple(...) \ - alloc_hooks(skb_array_resize_multiple_noprof(__VA_ARGS__)) +#define skb_array_resize_multiple_bh(...) \ + alloc_hooks(skb_array_resize_multiple_bh_noprof(__VA_ARGS__)) static inline void skb_array_cleanup(struct skb_array *a) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 58009fa66102..bb2b751d274a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -608,11 +608,19 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; - unsigned int xdp_frags_size; - /* Intermediate layers must ensure that destructor_arg - * remains valid until skb destructor */ - void * destructor_arg; + union { + struct { + u32 xdp_frags_size; + u32 xdp_frags_truesize; + }; + + /* + * Intermediate layers must ensure that destructor_arg + * remains valid until skb destructor. + */ + void *destructor_arg; + }; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; @@ -1134,7 +1142,7 @@ static inline bool skb_pfmemalloc(const struct sk_buff *skb) * skb_dst - returns skb dst_entry * @skb: buffer * - * Returns skb dst_entry, regardless of reference taken or not. + * Returns: skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { @@ -1222,7 +1230,7 @@ static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) * skb_unref - decrement the skb's reference count * @skb: buffer * - * Returns true if we can free the skb. + * Returns: true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { @@ -1344,7 +1352,7 @@ struct sk_buff_fclones { * @sk: socket * @skb: buffer * - * Returns true if skb is a fast clone, and its clone is not freed. + * Returns: true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ @@ -3516,7 +3524,7 @@ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * - * Returns false if this page should be returned to page allocator, true + * Returns: false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) @@ -3627,13 +3635,13 @@ static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, - struct bpf_prog *prog); + const struct bpf_prog *prog); /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * - * Returns the address of the data within @frag. The page must already + * Returns: the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) @@ -3648,7 +3656,7 @@ static inline void *skb_frag_address(const skb_frag_t *frag) * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * - * Returns the address of the data within @frag. Checks that the page + * Returns: the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) @@ -3674,7 +3682,7 @@ static inline void skb_frag_page_copy(skb_frag_t *fragto, bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** - * skb_frag_dma_map - maps a paged fragment via the DMA API + * __skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the @@ -3684,15 +3692,36 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); * * Maps the page associated with @frag to @device. */ -static inline dma_addr_t skb_frag_dma_map(struct device *dev, - const skb_frag_t *frag, - size_t offset, size_t size, - enum dma_data_direction dir) +static inline dma_addr_t __skb_frag_dma_map(struct device *dev, + const skb_frag_t *frag, + size_t offset, size_t size, + enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } +#define skb_frag_dma_map(dev, frag, ...) \ + CONCATENATE(_skb_frag_dma_map, \ + COUNT_ARGS(__VA_ARGS__))(dev, frag, ##__VA_ARGS__) + +#define __skb_frag_dma_map1(dev, frag, offset, uf, uo) ({ \ + const skb_frag_t *uf = (frag); \ + size_t uo = (offset); \ + \ + __skb_frag_dma_map(dev, uf, uo, skb_frag_size(uf) - uo, \ + DMA_TO_DEVICE); \ +}) +#define _skb_frag_dma_map1(dev, frag, offset) \ + __skb_frag_dma_map1(dev, frag, offset, __UNIQUE_ID(frag_), \ + __UNIQUE_ID(offset_)) +#define _skb_frag_dma_map0(dev, frag) \ + _skb_frag_dma_map1(dev, frag, 0) +#define _skb_frag_dma_map2(dev, frag, offset, size) \ + __skb_frag_dma_map(dev, frag, offset, size, DMA_TO_DEVICE) +#define _skb_frag_dma_map3(dev, frag, offset, size, dir) \ + __skb_frag_dma_map(dev, frag, offset, size, dir) + static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { @@ -3890,7 +3919,7 @@ static inline int skb_linearize(struct sk_buff *skb) * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * - * Return true if the skb has at least one frag that might be modified + * Return: true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) @@ -4612,7 +4641,7 @@ static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) /* Check if we need to perform checksum complete validation. * - * Returns true if checksum complete is needed, false otherwise + * Returns: true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index d9b03e0746e7..2cbe0c22a32f 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -317,17 +317,22 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void sk_psock_queue_msg(struct sk_psock *psock, +static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { + bool ret; + spin_lock_bh(&psock->ingress_lock); - if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); - else { + ret = true; + } else { sk_msg_free(psock->sk, msg); kfree(msg); + ret = false; } spin_unlock_bh(&psock->ingress_lock); + return ret; } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) diff --git a/include/linux/slab.h b/include/linux/slab.h index 10a971c2bde3..09eedaecf120 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -1099,5 +1099,6 @@ unsigned int kmem_cache_size(struct kmem_cache *s); size_t kmalloc_size_roundup(size_t size); void __init kmem_cache_init_late(void); +void __init kvfree_rcu_init(void); #endif /* _LINUX_SLAB_H */ diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 5bee6f7fc400..0c3906e8ad19 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -391,14 +391,6 @@ int cmdq_pkt_jump_rel(struct cmdq_pkt *pkt, s32 offset, u8 shift_pa); */ int cmdq_pkt_eoc(struct cmdq_pkt *pkt); -/** - * cmdq_pkt_finalize() - Append EOC and jump command to pkt. - * @pkt: the CMDQ packet - * - * Return: 0 for success; else the error code is returned - */ -int cmdq_pkt_finalize(struct cmdq_pkt *pkt); - #else /* IS_ENABLED(CONFIG_MTK_CMDQ) */ static inline int cmdq_dev_get_client_reg(struct device *dev, @@ -519,11 +511,6 @@ static inline int cmdq_pkt_eoc(struct cmdq_pkt *pkt) return -EINVAL; } -static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) -{ - return -EINVAL; -} - #endif /* IS_ENABLED(CONFIG_MTK_CMDQ) */ #endif /* __MTK_CMDQ_H__ */ diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index bd9836690da6..2d6c30317792 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -54,6 +54,8 @@ struct sdw_slave; #define SDW_MAX_PORTS 15 #define SDW_VALID_PORT_RANGE(n) ((n) < SDW_MAX_PORTS && (n) >= 1) +#define SDW_MAX_LANES 8 + enum { SDW_PORT_DIRN_SINK = 0, SDW_PORT_DIRN_SOURCE, @@ -356,6 +358,7 @@ struct sdw_dpn_prop { * and masks are supported * @commit_register_supported: is PCP_Commit register supported * @scp_int1_mask: SCP_INT1_MASK desired settings + * @lane_maps: Lane mapping for the slave, only valid if lane_control_support is set * @clock_reg_supported: the Peripheral implements the clock base and scale * registers introduced with the SoundWire 1.2 specification. SDCA devices * do not need to set this boolean property as the registers are required. @@ -385,6 +388,7 @@ struct sdw_slave_prop { u32 sdca_interrupt_register_list; u8 commit_register_supported; u8 scp_int1_mask; + u8 lane_maps[SDW_MAX_LANES]; bool clock_reg_supported; bool use_domain_irq; }; @@ -450,6 +454,7 @@ struct sdw_master_prop { int sdw_master_read_prop(struct sdw_bus *bus); int sdw_slave_read_prop(struct sdw_slave *slave); +int sdw_slave_read_lane_mapping(struct sdw_slave *slave); /* * SDW Slave Structures and APIs @@ -850,77 +855,6 @@ struct sdw_master_ops { int dev_num); }; -/** - * struct sdw_bus - SoundWire bus - * @dev: Shortcut to &bus->md->dev to avoid changing the entire code. - * @md: Master device - * @bus_lock_key: bus lock key associated to @bus_lock - * @bus_lock: bus lock - * @slaves: list of Slaves on this bus - * @msg_lock_key: message lock key associated to @msg_lock - * @msg_lock: message lock - * @m_rt_list: List of Master instance of all stream(s) running on Bus. This - * is used to compute and program bus bandwidth, clock, frame shape, - * transport and port parameters - * @defer_msg: Defer message - * @params: Current bus parameters - * @stream_refcount: number of streams currently using this bus - * @ops: Master callback ops - * @port_ops: Master port callback ops - * @prop: Master properties - * @vendor_specific_prop: pointer to non-standard properties - * @hw_sync_min_links: Number of links used by a stream above which - * hardware-based synchronization is required. This value is only - * meaningful if multi_link is set. If set to 1, hardware-based - * synchronization will be used even if a stream only uses a single - * SoundWire segment. - * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used. - * @link_id: Link id number, can be 0 to N, unique for each Controller - * @id: bus system-wide unique id - * @compute_params: points to Bus resource management implementation - * @assigned: Bitmap for Slave device numbers. - * Bit set implies used number, bit clear implies unused number. - * @clk_stop_timeout: Clock stop timeout computed - * @bank_switch_timeout: Bank switch timeout computed - * @domain: IRQ domain - * @irq_chip: IRQ chip - * @debugfs: Bus debugfs (optional) - * @multi_link: Store bus property that indicates if multi links - * are supported. This flag is populated by drivers after reading - * appropriate firmware (ACPI/DT). - */ -struct sdw_bus { - struct device *dev; - struct sdw_master_device *md; - struct lock_class_key bus_lock_key; - struct mutex bus_lock; - struct list_head slaves; - struct lock_class_key msg_lock_key; - struct mutex msg_lock; - struct list_head m_rt_list; - struct sdw_defer defer_msg; - struct sdw_bus_params params; - int stream_refcount; - const struct sdw_master_ops *ops; - const struct sdw_master_port_ops *port_ops; - struct sdw_master_prop prop; - void *vendor_specific_prop; - int hw_sync_min_links; - int controller_id; - unsigned int link_id; - int id; - int (*compute_params)(struct sdw_bus *bus); - DECLARE_BITMAP(assigned, SDW_MAX_DEVICES); - unsigned int clk_stop_timeout; - u32 bank_switch_timeout; - struct irq_chip irq_chip; - struct irq_domain *domain; -#ifdef CONFIG_DEBUG_FS - struct dentry *debugfs; -#endif - bool multi_link; -}; - int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, struct fwnode_handle *fwnode); void sdw_bus_master_delete(struct sdw_bus *bus); @@ -1010,10 +944,83 @@ struct sdw_stream_runtime { struct list_head master_list; }; +/** + * struct sdw_bus - SoundWire bus + * @dev: Shortcut to &bus->md->dev to avoid changing the entire code. + * @md: Master device + * @bus_lock_key: bus lock key associated to @bus_lock + * @bus_lock: bus lock + * @slaves: list of Slaves on this bus + * @msg_lock_key: message lock key associated to @msg_lock + * @msg_lock: message lock + * @m_rt_list: List of Master instance of all stream(s) running on Bus. This + * is used to compute and program bus bandwidth, clock, frame shape, + * transport and port parameters + * @defer_msg: Defer message + * @params: Current bus parameters + * @stream_refcount: number of streams currently using this bus + * @ops: Master callback ops + * @port_ops: Master port callback ops + * @prop: Master properties + * @vendor_specific_prop: pointer to non-standard properties + * @hw_sync_min_links: Number of links used by a stream above which + * hardware-based synchronization is required. This value is only + * meaningful if multi_link is set. If set to 1, hardware-based + * synchronization will be used even if a stream only uses a single + * SoundWire segment. + * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used. + * @link_id: Link id number, can be 0 to N, unique for each Controller + * @id: bus system-wide unique id + * @compute_params: points to Bus resource management implementation + * @assigned: Bitmap for Slave device numbers. + * Bit set implies used number, bit clear implies unused number. + * @clk_stop_timeout: Clock stop timeout computed + * @bank_switch_timeout: Bank switch timeout computed + * @domain: IRQ domain + * @irq_chip: IRQ chip + * @debugfs: Bus debugfs (optional) + * @multi_link: Store bus property that indicates if multi links + * are supported. This flag is populated by drivers after reading + * appropriate firmware (ACPI/DT). + * @lane_used_bandwidth: how much bandwidth in bits per second is used by each lane + */ +struct sdw_bus { + struct device *dev; + struct sdw_master_device *md; + struct lock_class_key bus_lock_key; + struct mutex bus_lock; + struct list_head slaves; + struct lock_class_key msg_lock_key; + struct mutex msg_lock; + struct list_head m_rt_list; + struct sdw_defer defer_msg; + struct sdw_bus_params params; + int stream_refcount; + const struct sdw_master_ops *ops; + const struct sdw_master_port_ops *port_ops; + struct sdw_master_prop prop; + void *vendor_specific_prop; + int hw_sync_min_links; + int controller_id; + unsigned int link_id; + int id; + int (*compute_params)(struct sdw_bus *bus, struct sdw_stream_runtime *stream); + DECLARE_BITMAP(assigned, SDW_MAX_DEVICES); + unsigned int clk_stop_timeout; + u32 bank_switch_timeout; + struct irq_chip irq_chip; + struct irq_domain *domain; +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs; +#endif + bool multi_link; + unsigned int lane_used_bandwidth[SDW_MAX_LANES]; +}; + struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name); void sdw_release_stream(struct sdw_stream_runtime *stream); -int sdw_compute_params(struct sdw_bus *bus); +int sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream); int sdw_stream_add_master(struct sdw_bus *bus, struct sdw_stream_config *stream_config, @@ -1034,6 +1041,7 @@ int sdw_bus_exit_clk_stop(struct sdw_bus *bus); int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id); void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id); +bool is_clock_scaling_supported_by_slave(struct sdw_slave *slave); #if IS_ENABLED(CONFIG_SOUNDWIRE) @@ -1045,6 +1053,8 @@ int sdw_stream_add_slave(struct sdw_slave *slave, int sdw_stream_remove_slave(struct sdw_slave *slave, struct sdw_stream_runtime *stream); +int sdw_slave_get_scale_index(struct sdw_slave *slave, u8 *base); + /* messaging and data APIs */ int sdw_read(struct sdw_slave *slave, u32 addr); int sdw_write(struct sdw_slave *slave, u32 addr, u8 value); diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h index 658b10fa5b20..0a5939285583 100644 --- a/include/linux/soundwire/sdw_registers.h +++ b/include/linux/soundwire/sdw_registers.h @@ -4,6 +4,9 @@ #ifndef __SDW_REGISTERS_H #define __SDW_REGISTERS_H +#include +#include + /* * SDW registers as defined by MIPI 1.2 Spec */ @@ -329,16 +332,27 @@ * 2:0 Control Number[2:0] */ -#define SDW_SDCA_CTL(fun, ent, ctl, ch) (BIT(30) | \ - (((fun) & 0x7) << 22) | \ - (((ent) & 0x40) << 15) | \ - (((ent) & 0x3f) << 7) | \ - (((ctl) & 0x30) << 15) | \ - (((ctl) & 0x0f) << 3) | \ - (((ch) & 0x38) << 12) | \ - ((ch) & 0x07)) +#define SDW_SDCA_CTL(fun, ent, ctl, ch) (BIT(30) | \ + (((fun) & GENMASK(2, 0)) << 22) | \ + (((ent) & BIT(6)) << 15) | \ + (((ent) & GENMASK(5, 0)) << 7) | \ + (((ctl) & GENMASK(5, 4)) << 15) | \ + (((ctl) & GENMASK(3, 0)) << 3) | \ + (((ch) & GENMASK(5, 3)) << 12) | \ + ((ch) & GENMASK(2, 0))) + +#define SDW_SDCA_CTL_FUNC(reg) FIELD_GET(GENMASK(24, 22), (reg)) +#define SDW_SDCA_CTL_ENT(reg) ((FIELD_GET(BIT(21), (reg)) << 6) | \ + FIELD_GET(GENMASK(12, 7), (reg))) +#define SDW_SDCA_CTL_CSEL(reg) ((FIELD_GET(GENMASK(20, 19), (reg)) << 4) | \ + FIELD_GET(GENMASK(6, 3), (reg))) +#define SDW_SDCA_CTL_CNUM(reg) ((FIELD_GET(GENMASK(17, 15), (reg)) << 3) | \ + FIELD_GET(GENMASK(2, 0), (reg))) #define SDW_SDCA_MBQ_CTL(reg) ((reg) | BIT(13)) #define SDW_SDCA_NEXT_CTL(reg) ((reg) | BIT(14)) +/* Check the reserved and fixed bits in address */ +#define SDW_SDCA_VALID_CTL(reg) (((reg) & (GENMASK(31, 25) | BIT(18) | BIT(13))) == BIT(30)) + #endif /* __SDW_REGISTERS_H */ diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index c46d2b8029be..c4830dfaff3d 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -15,16 +15,32 @@ #define SPI_MEM_OP_CMD(__opcode, __buswidth) \ { \ + .nbytes = 1, \ .buswidth = __buswidth, \ .opcode = __opcode, \ + } + +#define SPI_MEM_DTR_OP_CMD(__opcode, __buswidth) \ + { \ .nbytes = 1, \ + .opcode = __opcode, \ + .buswidth = __buswidth, \ + .dtr = true, \ } #define SPI_MEM_OP_ADDR(__nbytes, __val, __buswidth) \ + { \ + .nbytes = __nbytes, \ + .buswidth = __buswidth, \ + .val = __val, \ + } + +#define SPI_MEM_DTR_OP_ADDR(__nbytes, __val, __buswidth) \ { \ .nbytes = __nbytes, \ .val = __val, \ .buswidth = __buswidth, \ + .dtr = true, \ } #define SPI_MEM_OP_NO_ADDR { } @@ -35,22 +51,47 @@ .buswidth = __buswidth, \ } +#define SPI_MEM_DTR_OP_DUMMY(__nbytes, __buswidth) \ + { \ + .nbytes = __nbytes, \ + .buswidth = __buswidth, \ + .dtr = true, \ + } + #define SPI_MEM_OP_NO_DUMMY { } #define SPI_MEM_OP_DATA_IN(__nbytes, __buf, __buswidth) \ + { \ + .buswidth = __buswidth, \ + .dir = SPI_MEM_DATA_IN, \ + .nbytes = __nbytes, \ + .buf.in = __buf, \ + } + +#define SPI_MEM_DTR_OP_DATA_IN(__nbytes, __buf, __buswidth) \ { \ .dir = SPI_MEM_DATA_IN, \ .nbytes = __nbytes, \ .buf.in = __buf, \ .buswidth = __buswidth, \ + .dtr = true, \ } #define SPI_MEM_OP_DATA_OUT(__nbytes, __buf, __buswidth) \ + { \ + .buswidth = __buswidth, \ + .dir = SPI_MEM_DATA_OUT, \ + .nbytes = __nbytes, \ + .buf.out = __buf, \ + } + +#define SPI_MEM_DTR_OP_DATA_OUT(__nbytes, __buf, __buswidth) \ { \ .dir = SPI_MEM_DATA_OUT, \ .nbytes = __nbytes, \ .buf.out = __buf, \ .buswidth = __buswidth, \ + .dtr = true, \ } #define SPI_MEM_OP_NO_DATA { } @@ -68,6 +109,9 @@ enum spi_mem_data_dir { SPI_MEM_DATA_OUT, }; +#define SPI_MEM_OP_MAX_FREQ(__freq) \ + .max_freq = __freq + /** * struct spi_mem_op - describes a SPI memory operation * @cmd.nbytes: number of opcode bytes (only 1 or 2 are valid). The opcode is @@ -97,6 +141,9 @@ enum spi_mem_data_dir { * operation does not involve transferring data * @data.buf.in: input buffer (must be DMA-able) * @data.buf.out: output buffer (must be DMA-able) + * @max_freq: frequency limitation wrt this operation. 0 means there is no + * specific constraint and the highest achievable frequency can be + * attempted. */ struct spi_mem_op { struct { @@ -135,14 +182,17 @@ struct spi_mem_op { const void *out; } buf; } data; + + unsigned int max_freq; }; -#define SPI_MEM_OP(__cmd, __addr, __dummy, __data) \ +#define SPI_MEM_OP(__cmd, __addr, __dummy, __data, ...) \ { \ .cmd = __cmd, \ .addr = __addr, \ .dummy = __dummy, \ .data = __data, \ + __VA_ARGS__ \ } /** @@ -302,11 +352,13 @@ struct spi_controller_mem_ops { * @ecc: Supports operations with error correction * @swap16: Supports swapping bytes on a 16 bit boundary when configured in * Octal DTR + * @per_op_freq: Supports per operation frequency switching */ struct spi_controller_mem_caps { bool dtr; bool ecc; bool swap16; + bool per_op_freq; }; #define spi_mem_controller_is_capable(ctlr, cap) \ @@ -371,6 +423,8 @@ bool spi_mem_default_supports_op(struct spi_mem *mem, #endif /* CONFIG_SPI_MEM */ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op); +void spi_mem_adjust_op_freq(struct spi_mem *mem, struct spi_mem_op *op); +u64 spi_mem_calc_op_duration(struct spi_mem_op *op); bool spi_mem_supports_op(struct spi_mem *mem, const struct spi_mem_op *op); diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 08339eb8a01c..d7ba46e74f58 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -43,6 +43,12 @@ int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +/* Values for SRCU Tree srcu_data ->srcu_reader_flavor, but also used by rcutorture. */ +#define SRCU_READ_FLAVOR_NORMAL 0x1 // srcu_read_lock(). +#define SRCU_READ_FLAVOR_NMI 0x2 // srcu_read_lock_nmisafe(). +#define SRCU_READ_FLAVOR_LITE 0x4 // srcu_read_lock_lite(). +#define SRCU_READ_FLAVOR_ALL 0x7 // All of the above. + #ifdef CONFIG_TINY_SRCU #include #elif defined(CONFIG_TREE_SRCU) @@ -232,13 +238,14 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * - * The return value from srcu_read_lock() must be passed unaltered - * to the matching srcu_read_unlock(). Note that srcu_read_lock() and - * the matching srcu_read_unlock() must occur in the same context, for - * example, it is illegal to invoke srcu_read_unlock() in an irq handler - * if the matching srcu_read_lock() was invoked in process context. Or, - * for that matter to invoke srcu_read_unlock() from one task and the - * matching srcu_read_lock() from another. + * The return value from srcu_read_lock() is guaranteed to be + * non-negative. This value must be passed unaltered to the matching + * srcu_read_unlock(). Note that srcu_read_lock() and the matching + * srcu_read_unlock() must occur in the same context, for example, it is + * illegal to invoke srcu_read_unlock() in an irq handler if the matching + * srcu_read_lock() was invoked in process context. Or, for that matter to + * invoke srcu_read_unlock() from one task and the matching srcu_read_lock() + * from another. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 490aeecc6bb4..b17814c9d1c7 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -26,6 +26,7 @@ struct srcu_data { atomic_long_t srcu_lock_count[2]; /* Locks per CPU. */ atomic_long_t srcu_unlock_count[2]; /* Unlocks per CPU. */ int srcu_reader_flavor; /* Reader flavor for srcu_struct structure? */ + /* Values: SRCU_READ_FLAVOR_.* */ /* Update-side state. */ spinlock_t __private lock ____cacheline_internodealigned_in_smp; @@ -43,11 +44,6 @@ struct srcu_data { struct srcu_struct *ssp; }; -/* Values for ->srcu_reader_flavor. */ -#define SRCU_READ_FLAVOR_NORMAL 0x1 // srcu_read_lock(). -#define SRCU_READ_FLAVOR_NMI 0x2 // srcu_read_lock_nmisafe(). -#define SRCU_READ_FLAVOR_LITE 0x4 // srcu_read_lock_lite(). - /* * Node in SRCU combining tree, similar in function to rcu_data. */ @@ -258,7 +254,7 @@ static inline void srcu_check_read_flavor_lite(struct srcu_struct *ssp) if (likely(READ_ONCE(sdp->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE)) return; - // Note that the cmpxchg() in srcu_check_read_flavor() is fully ordered. + // Note that the cmpxchg() in __srcu_check_read_flavor() is fully ordered. __srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE); } diff --git a/include/linux/stat.h b/include/linux/stat.h index 3d900c86981c..be7496a6a0dd 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -50,10 +50,11 @@ struct kstat { struct timespec64 btime; /* File creation time */ u64 blocks; u64 mnt_id; - u32 dio_mem_align; - u32 dio_offset_align; u64 change_cookie; u64 subvol; + u32 dio_mem_align; + u32 dio_offset_align; + u32 dio_read_offset_align; u32 atomic_write_unit_min; u32 atomic_write_unit_max; u32 atomic_write_segments_max; diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 141e6b176a1b..78a77a4ae0ea 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -160,6 +160,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #ifdef CONFIG_HAVE_STATIC_CALL_INLINE +extern int static_call_initialized; + extern int __init static_call_init(void); extern void static_call_force_reinit(void); @@ -225,6 +227,8 @@ extern long __static_call_return0(void); #elif defined(CONFIG_HAVE_STATIC_CALL) +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } #define DEFINE_STATIC_CALL(name, _func) \ @@ -281,6 +285,8 @@ extern long __static_call_return0(void); #else /* Generic implementation */ +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } static inline long __static_call_return0(void) diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index d79ff252cfdc..c9878a612e53 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -33,7 +33,9 @@ #define STMMAC_CSR_20_35M 0x2 /* MDC = clk_scr_i/16 */ #define STMMAC_CSR_35_60M 0x3 /* MDC = clk_scr_i/26 */ #define STMMAC_CSR_150_250M 0x4 /* MDC = clk_scr_i/102 */ -#define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/122 */ +#define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/124 */ +#define STMMAC_CSR_300_500M 0x6 /* MDC = clk_scr_i/204 */ +#define STMMAC_CSR_500_800M 0x7 /* MDC = clk_scr_i/324 */ /* MTL algorithms identifiers */ #define MTL_TX_ALGORITHM_WRR 0x0 @@ -250,8 +252,8 @@ struct plat_stmmacenet_data { struct clk *stmmac_clk; struct clk *pclk; struct clk *clk_ptp_ref; - unsigned int clk_ptp_rate; - unsigned int clk_ref_rate; + unsigned long clk_ptp_rate; + unsigned long clk_ref_rate; unsigned int mult_fact_100ns; s32 ptp_max_adj; u32 cdc_error_adj; @@ -263,7 +265,7 @@ struct plat_stmmacenet_data { int mac_port_sel_speed; int has_xgmac; u8 vlan_fail_q; - unsigned int eee_usecs_rate; + unsigned long eee_usecs_rate; struct pci_dev *pdev; int int_snapshot_num; int msi_mac_vec; diff --git a/include/linux/string.h b/include/linux/string.h index 493ac4862c77..86d5d352068b 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -4,6 +4,7 @@ #include #include +#include /* for DEFINE_FREE() */ #include /* for inline */ #include /* for size_t */ #include /* for NULL */ @@ -312,6 +313,8 @@ extern void *kmemdup_array(const void *src, size_t count, size_t element_size, g extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); +DEFINE_FREE(argv_free, char **, if (!IS_ERR_OR_NULL(_T)) argv_free(_T)) + /* lib/cmdline.c */ extern int get_option(char **str, int *pint); extern char *get_options(const char *str, int nints, int *ints); diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 35766963dd14..e783132e481f 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -222,6 +222,8 @@ static inline bool cache_is_expired(struct cache_detail *detail, struct cache_he return detail->flush_time >= h->last_refresh; } +extern int cache_check_rcu(struct cache_detail *detail, + struct cache_head *h, struct cache_req *rqstp); extern int cache_check(struct cache_detail *detail, struct cache_head *h, struct cache_req *rqstp); extern void cache_flush(void); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 5321585c778f..fec976e58174 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -93,6 +93,7 @@ struct rpc_clnt { const struct cred *cl_cred; unsigned int cl_max_connect; /* max number of transports not to the same IP */ struct super_block *pipefs_sb; + atomic_t cl_task_count; }; /* diff --git a/include/linux/sunrpc/gss_asn1.h b/include/linux/sunrpc/gss_asn1.h deleted file mode 100644 index 3ccecd0ad229..000000000000 --- a/include/linux/sunrpc/gss_asn1.h +++ /dev/null @@ -1,81 +0,0 @@ -/* - * linux/include/linux/sunrpc/gss_asn1.h - * - * minimal asn1 for generic encoding/decoding of gss tokens - * - * Adapted from MIT Kerberos 5-1.2.1 lib/include/krb5.h, - * lib/gssapi/krb5/gssapiP_krb5.h, and others - * - * Copyright (c) 2000 The Regents of the University of Michigan. - * All rights reserved. - * - * Andy Adamson - */ - -/* - * Copyright 1995 by the Massachusetts Institute of Technology. - * All Rights Reserved. - * - * Export of this software from the United States of America may - * require a specific license from the United States Government. - * It is the responsibility of any person or organization contemplating - * export to obtain such a license before exporting. - * - * WITHIN THAT CONSTRAINT, permission to use, copy, modify, and - * distribute this software and its documentation for any purpose and - * without fee is hereby granted, provided that the above copyright - * notice appear in all copies and that both that copyright notice and - * this permission notice appear in supporting documentation, and that - * the name of M.I.T. not be used in advertising or publicity pertaining - * to distribution of the software without specific, written prior - * permission. Furthermore if you modify this software you must label - * your software as modified software and not distribute it in such a - * fashion that it might be confused with the original M.I.T. software. - * M.I.T. makes no representations about the suitability of - * this software for any purpose. It is provided "as is" without express - * or implied warranty. - * - */ - - -#include - -#define SIZEOF_INT 4 - -/* from gssapi_err_generic.h */ -#define G_BAD_SERVICE_NAME (-2045022976L) -#define G_BAD_STRING_UID (-2045022975L) -#define G_NOUSER (-2045022974L) -#define G_VALIDATE_FAILED (-2045022973L) -#define G_BUFFER_ALLOC (-2045022972L) -#define G_BAD_MSG_CTX (-2045022971L) -#define G_WRONG_SIZE (-2045022970L) -#define G_BAD_USAGE (-2045022969L) -#define G_UNKNOWN_QOP (-2045022968L) -#define G_NO_HOSTNAME (-2045022967L) -#define G_BAD_HOSTNAME (-2045022966L) -#define G_WRONG_MECH (-2045022965L) -#define G_BAD_TOK_HEADER (-2045022964L) -#define G_BAD_DIRECTION (-2045022963L) -#define G_TOK_TRUNC (-2045022962L) -#define G_REFLECT (-2045022961L) -#define G_WRONG_TOKID (-2045022960L) - -#define g_OID_equal(o1,o2) \ - (((o1)->len == (o2)->len) && \ - (memcmp((o1)->data,(o2)->data,(int) (o1)->len) == 0)) - -u32 g_verify_token_header( - struct xdr_netobj *mech, - int *body_size, - unsigned char **buf_in, - int toksize); - -int g_token_size( - struct xdr_netobj *mech, - unsigned int body_size); - -void g_make_token_header( - struct xdr_netobj *mech, - int body_size, - unsigned char **buf); diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 78a80bf3fdcb..43950b5237c8 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -40,7 +40,6 @@ #include #include #include -#include /* Length of constant used in key derivation */ #define GSS_KRB5_K5CLENGTH (5) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index e68fecf6eab5..74658cca0f38 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -72,16 +72,12 @@ struct svc_serv { spinlock_t sv_lock; unsigned int sv_nprogs; /* Number of sv_programs */ unsigned int sv_nrthreads; /* # of server threads */ - unsigned int sv_maxconn; /* max connections allowed or - * '0' causing max to be based - * on number of threads. */ - unsigned int sv_max_payload; /* datagram payload size */ unsigned int sv_max_mesg; /* max_payload + 1 page for overheads */ unsigned int sv_xdrsize; /* XDR buffer size */ struct list_head sv_permsocks; /* all permanent sockets */ struct list_head sv_tempsocks; /* all temporary sockets */ - int sv_tmpcnt; /* count of temporary sockets */ + int sv_tmpcnt; /* count of temporary "valid" sockets */ struct timer_list sv_temptimer; /* timer for aging temporary sockets */ char * sv_name; /* service name */ @@ -327,12 +323,7 @@ static inline bool svc_thread_should_stop(struct svc_rqst *rqstp) */ static inline void svc_thread_init_status(struct svc_rqst *rqstp, int err) { - rqstp->rq_err = err; - /* memory barrier ensures assignment to error above is visible before - * waitqueue_active() test below completes. - */ - smp_mb(); - wake_up_var(&rqstp->rq_err); + store_release_wake_up(&rqstp->rq_err, err); if (err) kthread_exit(1); } diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 0981e35a9fed..72be60952579 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -99,8 +99,30 @@ enum { XPT_HANDSHAKE, /* xprt requests a handshake */ XPT_TLS_SESSION, /* transport-layer security established */ XPT_PEER_AUTH, /* peer has been authenticated */ + XPT_PEER_VALID, /* peer has presented a filehandle that + * it has access to. It is NOT counted + * in ->sv_tmpcnt. + */ }; +/* + * Maximum number of "tmp" connections - those without XPT_PEER_VALID - + * permitted on any service. + */ +#define XPT_MAX_TMP_CONN 64 + +static inline void svc_xprt_set_valid(struct svc_xprt *xpt) +{ + if (test_bit(XPT_TEMP, &xpt->xpt_flags) && + !test_and_set_bit(XPT_PEER_VALID, &xpt->xpt_flags)) { + struct svc_serv *serv = xpt->xpt_server; + + spin_lock(&serv->sv_lock); + serv->sv_tmpcnt -= 1; + spin_unlock(&serv->sv_lock); + } +} + static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u) { spin_lock(&xpt->xpt_lock); diff --git a/include/linux/sunrpc/xdrgen/nfs4_1.h b/include/linux/sunrpc/xdrgen/nfs4_1.h new file mode 100644 index 000000000000..cf21a14aa885 --- /dev/null +++ b/include/linux/sunrpc/xdrgen/nfs4_1.h @@ -0,0 +1,153 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Generated by xdrgen. Manual edits will be lost. */ +/* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */ +/* XDR specification modification time: Mon Oct 14 09:10:13 2024 */ + +#ifndef _LINUX_XDRGEN_NFS4_1_DEF_H +#define _LINUX_XDRGEN_NFS4_1_DEF_H + +#include +#include + +typedef s64 int64_t; + +typedef u32 uint32_t; + +typedef struct { + u32 count; + uint32_t *element; +} bitmap4; + +struct nfstime4 { + int64_t seconds; + uint32_t nseconds; +}; + +typedef bool fattr4_offline; + +enum { FATTR4_OFFLINE = 83 }; + +struct open_arguments4 { + bitmap4 oa_share_access; + bitmap4 oa_share_deny; + bitmap4 oa_share_access_want; + bitmap4 oa_open_claim; + bitmap4 oa_create_mode; +}; + +enum open_args_share_access4 { + OPEN_ARGS_SHARE_ACCESS_READ = 1, + OPEN_ARGS_SHARE_ACCESS_WRITE = 2, + OPEN_ARGS_SHARE_ACCESS_BOTH = 3, +}; +typedef enum open_args_share_access4 open_args_share_access4; + +enum open_args_share_deny4 { + OPEN_ARGS_SHARE_DENY_NONE = 0, + OPEN_ARGS_SHARE_DENY_READ = 1, + OPEN_ARGS_SHARE_DENY_WRITE = 2, + OPEN_ARGS_SHARE_DENY_BOTH = 3, +}; +typedef enum open_args_share_deny4 open_args_share_deny4; + +enum open_args_share_access_want4 { + OPEN_ARGS_SHARE_ACCESS_WANT_ANY_DELEG = 3, + OPEN_ARGS_SHARE_ACCESS_WANT_NO_DELEG = 4, + OPEN_ARGS_SHARE_ACCESS_WANT_CANCEL = 5, + OPEN_ARGS_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL = 17, + OPEN_ARGS_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED = 18, + OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 20, + OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 21, +}; +typedef enum open_args_share_access_want4 open_args_share_access_want4; + +enum open_args_open_claim4 { + OPEN_ARGS_OPEN_CLAIM_NULL = 0, + OPEN_ARGS_OPEN_CLAIM_PREVIOUS = 1, + OPEN_ARGS_OPEN_CLAIM_DELEGATE_CUR = 2, + OPEN_ARGS_OPEN_CLAIM_DELEGATE_PREV = 3, + OPEN_ARGS_OPEN_CLAIM_FH = 4, + OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH = 5, + OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH = 6, +}; +typedef enum open_args_open_claim4 open_args_open_claim4; + +enum open_args_createmode4 { + OPEN_ARGS_CREATEMODE_UNCHECKED4 = 0, + OPEN_ARGS_CREATE_MODE_GUARDED = 1, + OPEN_ARGS_CREATEMODE_EXCLUSIVE4 = 2, + OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1 = 3, +}; +typedef enum open_args_createmode4 open_args_createmode4; + +typedef struct open_arguments4 fattr4_open_arguments; + +enum { FATTR4_OPEN_ARGUMENTS = 86 }; + +enum { OPEN4_RESULT_NO_OPEN_STATEID = 0x00000010 }; + +typedef struct nfstime4 fattr4_time_deleg_access; + +typedef struct nfstime4 fattr4_time_deleg_modify; + +enum { FATTR4_TIME_DELEG_ACCESS = 84 }; + +enum { FATTR4_TIME_DELEG_MODIFY = 85 }; + +enum { OPEN4_SHARE_ACCESS_WANT_DELEG_MASK = 0xFF00 }; + +enum { OPEN4_SHARE_ACCESS_WANT_NO_PREFERENCE = 0x0000 }; + +enum { OPEN4_SHARE_ACCESS_WANT_READ_DELEG = 0x0100 }; + +enum { OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG = 0x0200 }; + +enum { OPEN4_SHARE_ACCESS_WANT_ANY_DELEG = 0x0300 }; + +enum { OPEN4_SHARE_ACCESS_WANT_NO_DELEG = 0x0400 }; + +enum { OPEN4_SHARE_ACCESS_WANT_CANCEL = 0x0500 }; + +enum { OPEN4_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL = 0x10000 }; + +enum { OPEN4_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED = 0x20000 }; + +enum { OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 0x100000 }; + +enum { OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 0x200000 }; + +enum open_delegation_type4 { + OPEN_DELEGATE_NONE = 0, + OPEN_DELEGATE_READ = 1, + OPEN_DELEGATE_WRITE = 2, + OPEN_DELEGATE_NONE_EXT = 3, + OPEN_DELEGATE_READ_ATTRS_DELEG = 4, + OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5, +}; +typedef enum open_delegation_type4 open_delegation_type4; + +#define NFS4_int64_t_sz \ + (XDR_hyper) +#define NFS4_uint32_t_sz \ + (XDR_unsigned_int) +#define NFS4_bitmap4_sz (XDR_unsigned_int) +#define NFS4_nfstime4_sz \ + (NFS4_int64_t_sz + NFS4_uint32_t_sz) +#define NFS4_fattr4_offline_sz \ + (XDR_bool) +#define NFS4_open_arguments4_sz \ + (NFS4_bitmap4_sz + NFS4_bitmap4_sz + NFS4_bitmap4_sz + NFS4_bitmap4_sz + NFS4_bitmap4_sz) +#define NFS4_open_args_share_access4_sz (XDR_int) +#define NFS4_open_args_share_deny4_sz (XDR_int) +#define NFS4_open_args_share_access_want4_sz (XDR_int) +#define NFS4_open_args_open_claim4_sz (XDR_int) +#define NFS4_open_args_createmode4_sz (XDR_int) +#define NFS4_fattr4_open_arguments_sz \ + (NFS4_open_arguments4_sz) +#define NFS4_fattr4_time_deleg_access_sz \ + (NFS4_nfstime4_sz) +#define NFS4_fattr4_time_deleg_modify_sz \ + (NFS4_nfstime4_sz) +#define NFS4_open_delegation_type4_sz (XDR_int) + +#endif /* _LINUX_XDRGEN_NFS4_1_DEF_H */ diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h index c0514c684b2c..e411368cdacf 100644 --- a/include/linux/sunrpc/xprtmultipath.h +++ b/include/linux/sunrpc/xprtmultipath.h @@ -75,7 +75,6 @@ extern struct rpc_xprt_switch *xprt_iter_xchg_switch( struct rpc_xprt_switch *newswitch); extern struct rpc_xprt *xprt_iter_xprt(struct rpc_xprt_iter *xpi); -extern struct rpc_xprt *xprt_iter_get_xprt(struct rpc_xprt_iter *xpi); extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi); extern bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, diff --git a/include/linux/swap.h b/include/linux/swap.h index f3e0ac20c2e8..b13b72645db3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -219,10 +219,10 @@ enum { SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL +#define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10) #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ @@ -257,18 +257,27 @@ struct swap_cluster_info { u8 order; struct list_head list; }; -#define CLUSTER_FLAG_FREE 1 /* This cluster is free */ -#define CLUSTER_FLAG_NONFULL 2 /* This cluster is on nonfull list */ -#define CLUSTER_FLAG_FRAG 4 /* This cluster is on nonfull list */ -#define CLUSTER_FLAG_FULL 8 /* This cluster is on full list */ + +/* All on-list cluster must have a non-zero flag. */ +enum swap_cluster_flags { + CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */ + CLUSTER_FLAG_FREE, + CLUSTER_FLAG_NONFULL, + CLUSTER_FLAG_FRAG, + /* Clusters with flags above are allocatable */ + CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG, + CLUSTER_FLAG_FULL, + CLUSTER_FLAG_DISCARD, + CLUSTER_FLAG_MAX, +}; /* * The first page in the swap file is the swap header, which is always marked * bad to prevent it from being allocated as an entry. This also prevents the * cluster to which it belongs being marked free. Therefore 0 is safe to use as - * a sentinel to indicate next is not valid in percpu_cluster. + * a sentinel to indicate an entry is not valid. */ -#define SWAP_NEXT_INVALID 0 +#define SWAP_ENTRY_INVALID 0 #ifdef CONFIG_THP_SWAP #define SWAP_NR_ORDERS (PMD_ORDER + 1) @@ -282,6 +291,7 @@ struct swap_cluster_info { * throughput. */ struct percpu_cluster { + local_lock_t lock; /* Protect the percpu_cluster above */ unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; @@ -304,15 +314,12 @@ struct swap_info_struct { /* list of cluster that contains at least one free slot */ struct list_head frag_clusters[SWAP_NR_ORDERS]; /* list of cluster that are fragmented or contented */ - unsigned int frag_cluster_nr[SWAP_NR_ORDERS]; - unsigned int lowest_bit; /* index of first free in swap_map */ - unsigned int highest_bit; /* index of last free in swap_map */ + atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS]; unsigned int pages; /* total of usable pages of swap */ - unsigned int inuse_pages; /* number of those currently in use */ - unsigned int cluster_next; /* likely index for next allocation */ - unsigned int cluster_nr; /* countdown to next cluster search */ - unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ + atomic_long_t inuse_pages; /* number of those currently in use */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ + struct percpu_cluster *global_cluster; /* Use one global cluster for rotating device */ + spinlock_t global_cluster_lock; /* Serialize usage of global cluster */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h index ae73a87775b3..b5ec038069da 100644 --- a/include/linux/swap_cgroup.h +++ b/include/linux/swap_cgroup.h @@ -6,10 +6,8 @@ #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) -extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, - unsigned short old, unsigned short new); -extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, - unsigned int nr_ents); +extern void swap_cgroup_record(struct folio *folio, swp_entry_t ent); +extern unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents); extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent); extern int swap_cgroup_swapon(int type, unsigned long max_pages); extern void swap_cgroup_swapoff(int type); @@ -17,8 +15,12 @@ extern void swap_cgroup_swapoff(int type); #else static inline -unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, - unsigned int nr_ents) +void swap_cgroup_record(struct folio *folio, swp_entry_t ent) +{ +} + +static inline +unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents) { return 0; } diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h index 15adfb8c813a..840aec3523b2 100644 --- a/include/linux/swap_slots.h +++ b/include/linux/swap_slots.h @@ -16,15 +16,12 @@ struct swap_slots_cache { swp_entry_t *slots; int nr; int cur; - spinlock_t free_lock; /* protects slots_ret, n_ret */ - swp_entry_t *slots_ret; int n_ret; }; void disable_swap_slots_cache_lock(void); void reenable_swap_slots_cache_unlock(void); void enable_swap_slots_cache(void); -void free_swap_slot(swp_entry_t entry); extern bool swap_slot_cache_enabled; diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 0f2fcd244523..18f7e1fd093c 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -293,7 +293,7 @@ __ATTRIBUTE_GROUPS(_name) #define BIN_ATTRIBUTE_GROUPS(_name) \ static const struct attribute_group _name##_group = { \ - .bin_attrs = _name##_attrs, \ + .bin_attrs_new = _name##_attrs, \ }; \ __ATTRIBUTE_GROUPS(_name) @@ -511,7 +511,7 @@ __printf(3, 4) int sysfs_emit_at(char *buf, int at, const char *fmt, ...); ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count); #else /* CONFIG_SYSFS */ @@ -774,7 +774,7 @@ static inline int sysfs_emit_at(char *buf, int at, const char *fmt, ...) static inline ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 2964171856e0..0646804860ff 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -19,9 +19,6 @@ enum task_work_notify_mode { TWA_SIGNAL, TWA_SIGNAL_NO_IPI, TWA_NMI_CURRENT, - - TWA_FLAGS = 0xff00, - TWAF_NO_ALLOC = 0x0100, }; static inline bool task_work_pending(struct task_struct *task) diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 754802478b96..69f9bedd0ee8 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -295,6 +295,10 @@ static inline struct thermal_zone_device *thermal_tripless_zone_device_register( static inline void thermal_zone_device_unregister(struct thermal_zone_device *tz) { } +static inline void thermal_zone_device_update(struct thermal_zone_device *tz, + enum thermal_notify_event event) +{ } + static inline struct thermal_cooling_device * thermal_cooling_device_register(const char *type, void *devdata, const struct thermal_cooling_device_ops *ops) diff --git a/include/linux/time64.h b/include/linux/time64.h index f1bcea8c124a..9934331c7b86 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -49,6 +49,11 @@ static inline int timespec64_equal(const struct timespec64 *a, return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } +static inline bool timespec64_is_epoch(const struct timespec64 *ts) +{ + return ts->tv_sec == 0 && ts->tv_nsec == 0; +} + /* * lhs < rhs: return <0 * lhs == rhs: return 0 diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 0e035f675efe..542773650200 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -263,18 +263,6 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); -/** - * struct ktime_timestamps - Simultaneous mono/boot/real timestamps - * @mono: Monotonic timestamp - * @boot: Boottime timestamp - * @real: Realtime timestamp - */ -struct ktime_timestamps { - u64 mono; - u64 boot; - u64 real; -}; - /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value @@ -345,9 +333,6 @@ extern int get_device_system_crosststamp( */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); -/* NMI safe mono/boot/realtime timestamps */ -extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); - /* * Persistent clock related interfaces */ diff --git a/include/linux/torture.h b/include/linux/torture.h index c2e979f82f8d..0134e7221cae 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -130,7 +130,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); #endif #if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST) -long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask); +long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask, bool dowarn); #endif #endif /* __LINUX_TORTURE_H */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2a5df5b62cfc..5caea596fef0 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -273,7 +273,8 @@ struct trace_event_fields { const char *name; const int size; const int align; - const int is_signed; + const unsigned int is_signed:1; + unsigned int needs_test:1; const int filter_type; const int len; }; @@ -324,6 +325,7 @@ enum { TRACE_EVENT_FL_EPROBE_BIT, TRACE_EVENT_FL_FPROBE_BIT, TRACE_EVENT_FL_CUSTOM_BIT, + TRACE_EVENT_FL_TEST_STR_BIT, }; /* @@ -340,6 +342,7 @@ enum { * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) * This is set when the custom event has not been attached * to a tracepoint yet, then it is cleared when it is. + * TEST_STR - The event has a "%s" that points to a string outside the event */ enum { TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), @@ -352,6 +355,7 @@ enum { TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT), TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), + TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) @@ -360,7 +364,7 @@ struct trace_event_call { struct list_head list; struct trace_event_class *class; union { - char *name; + const char *name; /* Set TRACE_EVENT_FL_TRACEPOINT flag when using "tp" */ struct tracepoint *tp; }; @@ -669,6 +673,20 @@ struct trace_event_file { atomic_t tm_ref; /* trigger-mode reference counter */ }; +#ifdef CONFIG_HIST_TRIGGERS +extern struct irq_work hist_poll_work; +extern wait_queue_head_t hist_poll_wq; + +static inline void hist_poll_wakeup(void) +{ + if (wq_has_sleeper(&hist_poll_wq)) + irq_work_queue(&hist_poll_work); +} + +#define hist_poll_wait(file, wait) \ + poll_wait(file, &hist_poll_wq, wait) +#endif + #define __TRACE_EVENT_FLAGS(name, value) \ static int __init trace_init_flags_##name(void) \ { \ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 76d9055b2cff..a351763e6965 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -218,7 +218,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #define __DEFINE_RUST_DO_TRACE(name, proto, args) \ notrace void rust_do_trace_##name(proto) \ { \ - __rust_do_trace_##name(args); \ + __do_trace_##name(args); \ } /* @@ -268,7 +268,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) \ - static inline void __rust_do_trace_##name(proto) \ + static inline void __do_trace_##name(proto) \ { \ if (cond) { \ guard(preempt_notrace)(); \ @@ -277,12 +277,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) } \ static inline void trace_##name(proto) \ { \ - if (static_branch_unlikely(&__tracepoint_##name.key)) { \ - if (cond) { \ - guard(preempt_notrace)(); \ - __DO_TRACE_CALL(name, TP_ARGS(args)); \ - } \ - } \ + if (static_branch_unlikely(&__tracepoint_##name.key)) \ + __do_trace_##name(args); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ WARN_ONCE(!rcu_is_watching(), \ "RCU not watching for tracepoint"); \ @@ -291,7 +287,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #define __DECLARE_TRACE_SYSCALL(name, proto, args, data_proto) \ __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) \ - static inline void __rust_do_trace_##name(proto) \ + static inline void __do_trace_##name(proto) \ { \ guard(rcu_tasks_trace)(); \ __DO_TRACE_CALL(name, TP_ARGS(args)); \ @@ -299,10 +295,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) static inline void trace_##name(proto) \ { \ might_fault(); \ - if (static_branch_unlikely(&__tracepoint_##name.key)) { \ - guard(rcu_tasks_trace)(); \ - __DO_TRACE_CALL(name, TP_ARGS(args)); \ - } \ + if (static_branch_unlikely(&__tracepoint_##name.key)) \ + __do_trace_##name(args); \ if (IS_ENABLED(CONFIG_LOCKDEP)) { \ WARN_ONCE(!rcu_is_watching(), \ "RCU not watching for tracepoint"); \ diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index dd4b31ce6d5d..d4cdc089f6c3 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -320,7 +320,7 @@ struct serial_struct; * * @poll_init: ``int ()(struct tty_driver *driver, int line, char *options)`` * - * kgdboc support (Documentation/dev-tools/kgdb.rst). This routine is + * kgdboc support (Documentation/process/debugging/kgdb.rst). This routine is * called to initialize the HW for later use by calling @poll_get_char or * @poll_put_char. * diff --git a/include/linux/turris-omnia-mcu-interface.h b/include/linux/turris-omnia-mcu-interface.h index 2da8cbeb158a..38b45ab00053 100644 --- a/include/linux/turris-omnia-mcu-interface.h +++ b/include/linux/turris-omnia-mcu-interface.h @@ -9,7 +9,10 @@ #define __TURRIS_OMNIA_MCU_INTERFACE_H #include -#include +#include +#include +#include +#include enum omnia_commands_e { OMNIA_CMD_GET_STATUS_WORD = 0x01, /* slave sends status word back */ @@ -236,6 +239,20 @@ enum omnia_int_e { OMNIA_INT_LAN5_LED1 = BIT(31), }; +enum omnia_cmd_led_mode_e { + OMNIA_CMD_LED_MODE_LED_MASK = GENMASK(3, 0), + OMNIA_CMD_LED_MODE_USER = BIT(4), +}; + +#define OMNIA_CMD_LED_MODE_LED(_l) FIELD_PREP(OMNIA_CMD_LED_MODE_LED_MASK, _l) + +enum omnia_cmd_led_state_e { + OMNIA_CMD_LED_STATE_LED_MASK = GENMASK(3, 0), + OMNIA_CMD_LED_STATE_ON = BIT(4), +}; + +#define OMNIA_CMD_LED_STATE_LED(_l) FIELD_PREP(OMNIA_CMD_LED_STATE_LED_MASK, _l) + enum omnia_cmd_poweroff_e { OMNIA_CMD_POWER_OFF_POWERON_BUTTON = BIT(0), OMNIA_CMD_POWER_OFF_MAGIC = 0xdead, @@ -246,4 +263,135 @@ enum omnia_cmd_usb_ovc_prot_e { OMNIA_CMD_xET_USB_OVC_PROT_ENABLE = BIT(4), }; +/* Command execution functions */ + +struct i2c_client; + +int omnia_cmd_write_read(const struct i2c_client *client, + void *cmd, unsigned int cmd_len, + void *reply, unsigned int reply_len); + +static inline int omnia_cmd_write(const struct i2c_client *client, void *cmd, + unsigned int len) +{ + return omnia_cmd_write_read(client, cmd, len, NULL, 0); +} + +static inline int omnia_cmd_write_u8(const struct i2c_client *client, u8 cmd, + u8 val) +{ + u8 buf[2] = { cmd, val }; + + return omnia_cmd_write(client, buf, sizeof(buf)); +} + +static inline int omnia_cmd_write_u16(const struct i2c_client *client, u8 cmd, + u16 val) +{ + u8 buf[3]; + + buf[0] = cmd; + put_unaligned_le16(val, &buf[1]); + + return omnia_cmd_write(client, buf, sizeof(buf)); +} + +static inline int omnia_cmd_write_u32(const struct i2c_client *client, u8 cmd, + u32 val) +{ + u8 buf[5]; + + buf[0] = cmd; + put_unaligned_le32(val, &buf[1]); + + return omnia_cmd_write(client, buf, sizeof(buf)); +} + +static inline int omnia_cmd_read(const struct i2c_client *client, u8 cmd, + void *reply, unsigned int len) +{ + return omnia_cmd_write_read(client, &cmd, 1, reply, len); +} + +static inline unsigned int +omnia_compute_reply_length(unsigned long mask, bool interleaved, + unsigned int offset) +{ + if (!mask) + return 0; + + return ((__fls(mask) >> 3) << interleaved) + 1 + offset; +} + +/* Returns 0 on success */ +static inline int omnia_cmd_read_bits(const struct i2c_client *client, u8 cmd, + unsigned long bits, unsigned long *dst) +{ + __le32 reply; + int err; + + if (!bits) { + *dst = 0; + return 0; + } + + err = omnia_cmd_read(client, cmd, &reply, + omnia_compute_reply_length(bits, false, 0)); + if (err) + return err; + + *dst = le32_to_cpu(reply) & bits; + + return 0; +} + +static inline int omnia_cmd_read_bit(const struct i2c_client *client, u8 cmd, + unsigned long bit) +{ + unsigned long reply; + int err; + + err = omnia_cmd_read_bits(client, cmd, bit, &reply); + if (err) + return err; + + return !!reply; +} + +static inline int omnia_cmd_read_u32(const struct i2c_client *client, u8 cmd, + u32 *dst) +{ + __le32 reply; + int err; + + err = omnia_cmd_read(client, cmd, &reply, sizeof(reply)); + if (err) + return err; + + *dst = le32_to_cpu(reply); + + return 0; +} + +static inline int omnia_cmd_read_u16(const struct i2c_client *client, u8 cmd, + u16 *dst) +{ + __le16 reply; + int err; + + err = omnia_cmd_read(client, cmd, &reply, sizeof(reply)); + if (err) + return err; + + *dst = le16_to_cpu(reply); + + return 0; +} + +static inline int omnia_cmd_read_u8(const struct i2c_client *client, u8 cmd, + u8 *reply) +{ + return omnia_cmd_read(client, cmd, reply, sizeof(*reply)); +} + #endif /* __TURRIS_OMNIA_MCU_INTERFACE_H */ diff --git a/include/linux/types.h b/include/linux/types.h index 2d7b9ae8714c..1c509ce8f7f6 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -43,7 +43,7 @@ typedef unsigned long uintptr_t; typedef long intptr_t; #ifdef CONFIG_HAVE_UID16 -/* This is defined by include/asm-{arch}/posix_types.h */ +/* This is defined by arch/{arch}/include/asm/posix_types.h */ typedef __kernel_old_uid_t old_uid_t; typedef __kernel_old_gid_t old_gid_t; #endif /* CONFIG_UID16 */ diff --git a/include/linux/uio.h b/include/linux/uio.h index 853f9de5aa05..8ada84e85447 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -82,6 +82,15 @@ struct iov_iter { }; }; +typedef __u16 uio_meta_flags_t; + +struct uio_meta { + uio_meta_flags_t flags; + u16 app_tag; + u64 seed; + struct iov_iter iter; +}; + static inline const struct iovec *iter_iov(const struct iov_iter *iter) { if (iter->iter_type == ITER_UBUF) diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index e0a4c2082245..b1df7d792fa1 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -16,6 +16,7 @@ #include #include #include +#include struct uprobe; struct vm_area_struct; @@ -124,6 +125,10 @@ struct uprobe_task { unsigned int depth; struct return_instance *return_instances; + struct return_instance *ri_pool; + struct timer_list ri_timer; + seqcount_t ri_seqcount; + union { struct { struct arch_uprobe_task autask; @@ -137,7 +142,6 @@ struct uprobe_task { }; struct uprobe *active_uprobe; - struct timer_list ri_timer; unsigned long xol_vaddr; struct arch_uprobe *auprobe; @@ -154,12 +158,18 @@ struct return_instance { unsigned long stack; /* stack pointer */ unsigned long orig_ret_vaddr; /* original return address */ bool chained; /* true, if instance is nested */ - int consumers_cnt; + int cons_cnt; /* total number of session consumers */ struct return_instance *next; /* keep as stack */ struct rcu_head rcu; - struct return_consumer consumers[] __counted_by(consumers_cnt); + /* singular pre-allocated return_consumer instance for common case */ + struct return_consumer consumer; + /* + * extra return_consumer instances for rare cases of multiple session consumers, + * contains (cons_cnt - 1) elements + */ + struct return_consumer *extra_consumers; } ____cacheline_aligned; enum rp_check { diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index d50098fb16b5..3068c3084eb6 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -33,7 +33,9 @@ enum pd_ctrl_msg_type { PD_CTRL_FR_SWAP = 19, PD_CTRL_GET_PPS_STATUS = 20, PD_CTRL_GET_COUNTRY_CODES = 21, - /* 22-31 Reserved */ + /* 22-23 Reserved */ + PD_CTRL_GET_REVISION = 24, + /* 25-31 Reserved */ }; enum pd_data_msg_type { @@ -46,7 +48,9 @@ enum pd_data_msg_type { PD_DATA_ALERT = 6, PD_DATA_GET_COUNTRY_INFO = 7, PD_DATA_ENTER_USB = 8, - /* 9-14 Reserved */ + /* 9-11 Reserved */ + PD_DATA_REVISION = 12, + /* 13-14 Reserved */ PD_DATA_VENDOR_DEF = 15, /* 16-31 Reserved */ }; @@ -453,6 +457,20 @@ static inline unsigned int rdo_max_power(u32 rdo) #define EUDO_TBT_SUPPORT BIT(14) #define EUDO_HOST_PRESENT BIT(13) +/* + * Request Message Data Object (PD Revision 3.1+ only) + * -------- + * <31:28> :: Revision Major + * <27:24> :: Revision Minor + * <23:20> :: Version Major + * <19:16> :: Version Minor + * <15:0> :: Reserved, Shall be set to zero + */ + +#define RMDO(rev_maj, rev_min, ver_maj, ver_min) \ + (((rev_maj) & 0xf) << 28 | ((rev_min) & 0xf) << 24 | \ + ((ver_maj) & 0xf) << 20 | ((ver_min) & 0xf) << 16) + /* USB PD timers and counters */ #define PD_T_NO_RESPONSE 5000 /* 4.5 - 5.5 seconds */ #define PD_T_DB_DETECT 10000 /* 10 - 15 seconds */ diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index e4de6bc1f69b..0fa9885a1038 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -223,7 +223,6 @@ extern struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, extern struct usb_phy *devm_usb_get_phy_by_node(struct device *dev, struct device_node *node, struct notifier_block *nb); extern void usb_put_phy(struct usb_phy *); -extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x); extern void usb_phy_set_event(struct usb_phy *x, unsigned long event); extern void usb_phy_set_charger_current(struct usb_phy *usb_phy, unsigned int mA); @@ -259,10 +258,6 @@ static inline void usb_put_phy(struct usb_phy *x) { } -static inline void devm_usb_put_phy(struct device *dev, struct usb_phy *x) -{ -} - static inline void usb_phy_set_event(struct usb_phy *x, unsigned long event) { } diff --git a/include/linux/usb/storage.h b/include/linux/usb/storage.h index 8539956bc2be..51be3bb8fccb 100644 --- a/include/linux/usb/storage.h +++ b/include/linux/usb/storage.h @@ -82,4 +82,12 @@ struct bulk_cs_wrap { #define US_BULK_RESET_REQUEST 0xff #define US_BULK_GET_MAX_LUN 0xfe +/* + * If 4 LUNs are supported then the LUNs would be + * numbered from 0 to 3, and the return value for + * US_BULK_GET_MAX_LUN request would be 3. The valid + * LUN field is 4 bits wide, the upper limit is 0x0f. + */ +#define US_BULK_MAX_LUN_LIMIT 0x0f + #endif diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index 061da9546a81..b22e659f81ba 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -163,7 +163,8 @@ struct tcpc_dev { void (*frs_sourcing_vbus)(struct tcpc_dev *dev); int (*enable_auto_vbus_discharge)(struct tcpc_dev *dev, bool enable); int (*set_auto_vbus_discharge_threshold)(struct tcpc_dev *dev, enum typec_pwr_opmode mode, - bool pps_active, u32 requested_vbus_voltage); + bool pps_active, u32 requested_vbus_voltage, + u32 pps_apdo_min_voltage); bool (*is_vbus_vsafe0v)(struct tcpc_dev *dev); void (*set_partner_usb_comm_capable)(struct tcpc_dev *dev, bool enable); void (*check_contaminant)(struct tcpc_dev *dev); diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index d616b8807000..252af3f77039 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -140,6 +140,7 @@ int typec_cable_set_identity(struct typec_cable *cable); * @mode: Index of the Mode * @vdo: VDO returned by Discover Modes USB PD command * @roles: Only for ports. DRP if the mode is available in both roles + * @inactive: Only for ports. Make this port inactive (default is active). * * Description of an Alternate Mode which a connector, cable plug or partner * supports. @@ -150,6 +151,7 @@ struct typec_altmode_desc { u32 vdo; /* Only used with ports */ enum typec_port_data roles; + bool inactive; }; void typec_partner_set_pd_revision(struct typec_partner *partner, u16 pd_revision); diff --git a/include/linux/usb/typec_tbt.h b/include/linux/usb/typec_tbt.h index fa97d7e00f5c..55dcea12082c 100644 --- a/include/linux/usb/typec_tbt.h +++ b/include/linux/usb/typec_tbt.h @@ -44,6 +44,7 @@ struct typec_thunderbolt_data { #define TBT_GEN3_NON_ROUNDED 0 #define TBT_GEN3_GEN4_ROUNDED_NON_ROUNDED 1 +#define TBT_CABLE_ROUNDED BIT(19) #define TBT_CABLE_OPTICAL BIT(21) #define TBT_CABLE_RETIMER BIT(22) #define TBT_CABLE_LINK_TRAINING BIT(23) diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index cb40f1a1d081..75342022d144 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -247,6 +247,13 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, vma_is_shmem(vma); } +static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) +{ + struct userfaultfd_ctx *uffd_ctx = vma->vm_userfaultfd_ctx.ctx; + + return uffd_ctx && (uffd_ctx->features & UFFD_FEATURE_EVENT_REMAP) == 0; +} + extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); void dup_userfaultfd_fail(struct list_head *); @@ -402,6 +409,11 @@ static inline bool userfaultfd_wp_async(struct vm_area_struct *vma) return false; } +static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) diff --git a/include/linux/verification.h b/include/linux/verification.h index cb2d47f28091..4f3022d081c3 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -38,8 +38,6 @@ enum key_being_used_for { VERIFYING_UNSPECIFIED_SIGNATURE, NR__KEY_BEING_USED_FOR }; -extern const char *const key_being_used_for[NR__KEY_BEING_USED_FOR]; - #ifdef CONFIG_SYSTEM_DATA_VERIFICATION struct key; diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index a54046bf37e5..939ceabcaf06 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -15,10 +15,10 @@ #else #define MODULE_VERMAGIC_SMP "" #endif -#ifdef CONFIG_PREEMPT_BUILD -#define MODULE_VERMAGIC_PREEMPT "preempt " -#elif defined(CONFIG_PREEMPT_RT) +#ifdef CONFIG_PREEMPT_RT #define MODULE_VERMAGIC_PREEMPT "preempt_rt " +#elif defined(CONFIG_PREEMPT_BUILD) +#define MODULE_VERMAGIC_PREEMPT "preempt " #else #define MODULE_VERMAGIC_PREEMPT "" #endif diff --git a/include/linux/virtio.h b/include/linux/virtio.h index dd88682e27e3..4d16c13d0df5 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -190,6 +190,8 @@ int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); #endif void virtio_reset_device(struct virtio_device *dev); +int virtio_device_reset_prepare(struct virtio_device *dev); +int virtio_device_reset_done(struct virtio_device *dev); size_t virtio_max_dma_size(const struct virtio_device *vdev); @@ -214,6 +216,10 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev); * changes; may be called in interrupt context. * @freeze: optional function to call during suspend/hibernation. * @restore: optional function to call on resume. + * @reset_prepare: optional function to call when a transport specific reset + * occurs. + * @reset_done: optional function to call after transport specific reset + * operation has finished. */ struct virtio_driver { struct device_driver driver; @@ -229,6 +235,8 @@ struct virtio_driver { void (*config_changed)(struct virtio_device *dev); int (*freeze)(struct virtio_device *dev); int (*restore)(struct virtio_device *dev); + int (*reset_prepare)(struct virtio_device *dev); + int (*reset_done)(struct virtio_device *dev); }; #define drv_to_virtio(__drv) container_of_const(__drv, struct virtio_driver, driver) diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d2761bf8ff32..9f3a04345b86 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -515,7 +515,7 @@ static inline const char *node_stat_name(enum node_stat_item item) static inline const char *lru_list_name(enum lru_list lru) { - return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" + return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_" } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 6fb663b36f72..60c9eacd2cf3 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -431,11 +431,11 @@ enum { ((((_p)[0] & 0xFF) << 24) | (((_p)[1] & 0xFF) << 16) | ((_p)[2])) /* - * The VMCI IOCTLs. We use identity code 7, as noted in ioctl-number.h, and - * we start at sequence 9f. This gives us the same values that our shipping - * products use, starting at 1951, provided we leave out the direction and - * structure size. Note that VMMon occupies the block following us, starting - * at 2001. + * The VMCI IOCTLs. We use identity code 7, as noted in ioctl-number.rst, + * and we start at sequence 9f. This gives us the same values that our + * shipping products use, starting at 1951, provided we leave out the + * direction and structure size. Note that VMMon occupies the block + * following us, starting at 2001. */ #define IOCTL_VMCI_VERSION _IO(7, 0x9f) /* 1951 */ #define IOCTL_VMCI_INIT_CONTEXT _IO(7, 0xa0) @@ -453,9 +453,7 @@ enum { #define IOCTL_VMCI_CTX_GET_CPT_STATE _IO(7, 0xb1) #define IOCTL_VMCI_CTX_SET_CPT_STATE _IO(7, 0xb2) #define IOCTL_VMCI_GET_CONTEXT_ID _IO(7, 0xb3) -#define IOCTL_VMCI_SOCKETS_VERSION _IO(7, 0xb4) -#define IOCTL_VMCI_SOCKETS_GET_AF_VALUE _IO(7, 0xb8) -#define IOCTL_VMCI_SOCKETS_GET_LOCAL_CID _IO(7, 0xb9) +/*IOCTL_VM_SOCKETS_GET_LOCAL_CID _IO(7, 0xb9)*/ #define IOCTL_VMCI_SET_NOTIFY _IO(7, 0xcb) /* 1995 */ /*IOCTL_VMMON_START _IO(7, 0xd1)*/ /* 2001 */ diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 79c781875c09..a4d6cc0c9f68 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -97,7 +97,7 @@ struct wwan_port_caps { * * This function must be balanced with a call to wwan_remove_port(). * - * Returns a valid pointer to wwan_port on success or PTR_ERR on failure + * Returns: a valid pointer to wwan_port on success or PTR_ERR on failure */ struct wwan_port *wwan_create_port(struct device *parent, enum wwan_port_type type, diff --git a/include/media/cec.h b/include/media/cec.h index 16b412b3131b..0c8e86115b6f 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -10,7 +10,6 @@ #include #include -#include #include #include #include diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index 5bce6e423e94..e7f019f68c8d 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -73,6 +73,24 @@ #define V4L2_MBUS_CSI2_MAX_DATA_LANES 8 +/** + * enum v4l2_mbus_csi2_cphy_line_orders_type - CSI-2 C-PHY line order + * @V4L2_MBUS_CSI2_CPHY_LINE_ORDER_ABC: C-PHY line order ABC (default) + * @V4L2_MBUS_CSI2_CPHY_LINE_ORDER_ACB: C-PHY line order ACB + * @V4L2_MBUS_CSI2_CPHY_LINE_ORDER_BAC: C-PHY line order BAC + * @V4L2_MBUS_CSI2_CPHY_LINE_ORDER_BCA: C-PHY line order BCA + * @V4L2_MBUS_CSI2_CPHY_LINE_ORDER_CAB: C-PHY line order CAB + * @V4L2_MBUS_CSI2_CPHY_LINE_ORDER_CBA: C-PHY line order CBA + */ +enum v4l2_mbus_csi2_cphy_line_orders_type { + V4L2_MBUS_CSI2_CPHY_LINE_ORDER_ABC, + V4L2_MBUS_CSI2_CPHY_LINE_ORDER_ACB, + V4L2_MBUS_CSI2_CPHY_LINE_ORDER_BAC, + V4L2_MBUS_CSI2_CPHY_LINE_ORDER_BCA, + V4L2_MBUS_CSI2_CPHY_LINE_ORDER_CAB, + V4L2_MBUS_CSI2_CPHY_LINE_ORDER_CBA, +}; + /** * struct v4l2_mbus_config_mipi_csi2 - MIPI CSI-2 data bus configuration * @flags: media bus (V4L2_MBUS_*) flags @@ -81,6 +99,8 @@ * @num_data_lanes: number of data lanes * @lane_polarities: polarity of the lanes. The order is the same of * the physical lanes. + * @line_orders: line order of the data lanes. The order is the same of the + * physical lanes. */ struct v4l2_mbus_config_mipi_csi2 { unsigned int flags; @@ -88,6 +108,7 @@ struct v4l2_mbus_config_mipi_csi2 { unsigned char clock_lane; unsigned char num_data_lanes; bool lane_polarities[1 + V4L2_MBUS_CSI2_MAX_DATA_LANES]; + enum v4l2_mbus_csi2_cphy_line_orders_type line_orders[V4L2_MBUS_CSI2_MAX_DATA_LANES]; }; /** diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 363dd63babe7..9e5e95988b9e 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -88,6 +88,23 @@ struct ifa6_config { u16 scope; }; +enum addr_type_t { + UNICAST_ADDR, + MULTICAST_ADDR, + ANYCAST_ADDR, +}; + +struct inet6_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; + int ifindex; + enum addr_type_t type; + bool force_rt_scope_universe; +}; + int addrconf_init(void); void addrconf_cleanup(void); @@ -330,6 +347,11 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) return rcu_dereference_rtnl(dev->ip6_ptr); } +static inline struct inet6_dev *__in6_dev_get_rtnl_net(const struct net_device *dev) +{ + return rtnl_net_dereference(dev_net(dev), dev->ip6_ptr); +} + /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device @@ -525,4 +547,11 @@ int if6_proc_init(void); void if6_proc_exit(void); #endif +int inet6_fill_ifmcaddr(struct sk_buff *skb, + const struct ifmcaddr6 *ifmca, + struct inet6_fill_args *args); + +int inet6_fill_ifacaddr(struct sk_buff *skb, + const struct ifacaddr6 *ifaca, + struct inet6_fill_args *args); #endif diff --git a/include/net/ax25.h b/include/net/ax25.h index cb622d84cd0c..4ee141aae0a2 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -231,6 +231,7 @@ typedef struct ax25_dev { #endif refcount_t refcount; bool device_up; + struct rcu_head rcu; } ax25_dev; typedef struct ax25_cb { @@ -290,9 +291,8 @@ static inline void ax25_dev_hold(ax25_dev *ax25_dev) static inline void ax25_dev_put(ax25_dev *ax25_dev) { - if (refcount_dec_and_test(&ax25_dev->refcount)) { - kfree(ax25_dev); - } + if (refcount_dec_and_test(&ax25_dev->refcount)) + kfree_rcu(ax25_dev, rcu); } static inline __be16 ax25_type_trans(struct sk_buff *skb, struct net_device *dev) { @@ -335,9 +335,9 @@ void ax25_digi_invert(const ax25_digi *, ax25_digi *); extern spinlock_t ax25_dev_lock; #if IS_ENABLED(CONFIG_AX25) -static inline ax25_dev *ax25_dev_ax25dev(struct net_device *dev) +static inline ax25_dev *ax25_dev_ax25dev(const struct net_device *dev) { - return dev->ax25_ptr; + return rcu_dereference_rtnl(dev->ax25_ptr); } #endif diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 6203bd8663b7..0d51970d809f 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -438,7 +438,6 @@ enum { HCI_FORCE_BREDR_SMP, HCI_FORCE_STATIC_ADDR, HCI_LL_RPA_RESOLUTION, - HCI_ENABLE_LL_PRIVACY, HCI_CMD_PENDING, HCI_FORCE_NO_MITM, HCI_QUALITY_REPORT, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index ca22ead85dbe..f756fac95488 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -157,8 +157,9 @@ struct bdaddr_list_with_irk { /* Bitmask of connection flags */ enum hci_conn_flags { - HCI_CONN_FLAG_REMOTE_WAKEUP = 1, - HCI_CONN_FLAG_DEVICE_PRIVACY = 2, + HCI_CONN_FLAG_REMOTE_WAKEUP = BIT(0), + HCI_CONN_FLAG_DEVICE_PRIVACY = BIT(1), + HCI_CONN_FLAG_ADDRESS_RESOLUTION = BIT(2), }; typedef u8 hci_conn_flags_t; @@ -632,7 +633,6 @@ struct hci_dev { int (*post_init)(struct hci_dev *hdev); int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); - void (*cmd_timeout)(struct hci_dev *hdev); void (*reset)(struct hci_dev *hdev); bool (*wakeup)(struct hci_dev *hdev); int (*set_quality_report)(struct hci_dev *hdev, bool enable); @@ -1759,8 +1759,6 @@ int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type); -int hci_bdaddr_list_del_with_flags(struct list_head *list, bdaddr_t *bdaddr, - u8 type); void hci_bdaddr_list_clear(struct list_head *list); struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, @@ -1919,11 +1917,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) -/* Use LL Privacy based address resolution if supported */ -#define use_ll_privacy(dev) (ll_privacy_capable(dev) && \ - hci_dev_test_flag(dev, HCI_ENABLE_LL_PRIVACY)) - -#define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ +#define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \ (hdev->commands[39] & 0x04)) #define read_key_size_capable(dev) \ diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index f3052cb252ef..7e2cf0cca939 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -140,7 +140,6 @@ int hci_update_scan(struct hci_dev *hdev); int hci_write_le_host_supported_sync(struct hci_dev *hdev, u8 le, u8 simul); int hci_remove_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance, struct sock *sk); -int hci_remove_ext_adv_instance(struct hci_dev *hdev, u8 instance); struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, bool ext, struct sock *sk); diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index c858270141bc..c39a426ebf52 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -174,12 +174,4 @@ static inline void sk_mark_napi_id_once(struct sock *sk, #endif } -static inline void sk_mark_napi_id_once_xdp(struct sock *sk, - const struct xdp_buff *xdp) -{ -#ifdef CONFIG_NET_RX_BUSY_POLL - __sk_mark_napi_id_once(sk, xdp->rxq->napi_id); -#endif -} - #endif /* _LINUX_NET_BUSY_POLL_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 27acf1292a5c..363d7dd2255a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3023,6 +3023,10 @@ static inline const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 id) * * @bss: The BSS to authenticate with, the callee must obtain a reference * to it if it needs to keep it. + * @supported_selectors: List of selectors that should be assumed to be + * supported by the station. + * SAE_H2E must be assumed supported if set to %NULL. + * @supported_selectors_len: Length of supported_selectors in octets. * @auth_type: Authentication type (algorithm) * @ie: Extra IEs to add to Authentication frame or %NULL * @ie_len: Length of ie buffer in octets @@ -3045,6 +3049,8 @@ struct cfg80211_auth_request { struct cfg80211_bss *bss; const u8 *ie; size_t ie_len; + const u8 *supported_selectors; + u8 supported_selectors_len; enum nl80211_auth_type auth_type; const u8 *key; u8 key_len; @@ -3124,6 +3130,10 @@ enum cfg80211_assoc_req_flags { * included in the Current AP address field of the Reassociation Request * frame. * @flags: See &enum cfg80211_assoc_req_flags + * @supported_selectors: supported selectors in IEEE 802.11 format + * (or %NULL for no change). + * If %NULL, then support for SAE_H2E should be assumed. + * @supported_selectors_len: Length of supported_selectors in octets. * @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. @@ -3150,6 +3160,8 @@ struct cfg80211_assoc_request { struct cfg80211_crypto_settings crypto; bool use_mfp; u32 flags; + const u8 *supported_selectors; + u8 supported_selectors_len; struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; struct ieee80211_vht_cap vht_capa, vht_capa_mask; @@ -4582,8 +4594,18 @@ struct mgmt_frame_regs { * * @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames. * @set_ttlm: set the TID to link mapping. + * @set_epcs: Enable/Disable EPCS for station mode. * @get_radio_mask: get bitmask of radios in use. * (invoked with the wiphy mutex held) + * @assoc_ml_reconf: Request a non-AP MLO connection to perform ML + * reconfiguration, i.e., add and/or remove links to/from the + * association using ML reconfiguration action frames. Successfully added + * links will be added to the set of valid links. Successfully removed + * links will be removed from the set of valid links. The driver must + * indicate removed links by calling cfg80211_links_removed() and added + * links by calling cfg80211_mlo_reconf_add_done(). When calling + * cfg80211_mlo_reconf_add_done() the bss pointer must be given for each + * link for which MLO reconfiguration 'add' operation was requested. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4733,7 +4755,7 @@ struct cfg80211_ops { int (*set_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev, enum nl80211_tx_power_setting type, int mbm); int (*get_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev, - int *dbm); + unsigned int link_id, int *dbm); void (*rfkill_poll)(struct wiphy *wiphy); @@ -4947,6 +4969,11 @@ struct cfg80211_ops { int (*set_ttlm)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ttlm_params *params); u32 (*get_radio_mask)(struct wiphy *wiphy, struct net_device *dev); + int (*assoc_ml_reconf)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_assoc_link *add_links, + u16 rem_links); + int (*set_epcs)(struct wiphy *wiphy, struct net_device *dev, + bool val); }; /* @@ -5957,7 +5984,7 @@ int wiphy_register(struct wiphy *wiphy); * @wiphy: the wiphy to check the locking on * @p: The pointer to read, prior to dereferencing * - * Return the value of the specified RCU-protected pointer, but omit the + * Return: the value of the specified RCU-protected pointer, but omit the * READ_ONCE(), because caller holds the wiphy mutex used for updates. */ #define wiphy_dereference(wiphy, p) \ @@ -6031,6 +6058,10 @@ static inline void wiphy_unlock(struct wiphy *wiphy) mutex_unlock(&wiphy->mtx); } +DEFINE_GUARD(wiphy, struct wiphy *, + mutex_lock(&_T->mtx), + mutex_unlock(&_T->mtx)) + struct wiphy_work; typedef void (*wiphy_work_func_t)(struct wiphy *, struct wiphy_work *); @@ -9700,6 +9731,39 @@ static inline int cfg80211_color_change_notify(struct net_device *dev, */ void cfg80211_links_removed(struct net_device *dev, u16 link_mask); +/** + * struct cfg80211_mlo_reconf_done_data - MLO reconfiguration data + * @buf: MLO Reconfiguration Response frame (header + body) + * @len: length of the frame data + * @added_links: BIT mask of links successfully added to the association + * @links: per-link information indexed by link ID + * @links.bss: the BSS that MLO reconfiguration was requested for, ownership of + * the pointer moves to cfg80211 in the call to + * cfg80211_mlo_reconf_add_done(). + * + * The BSS pointer must be set for each link for which 'add' operation was + * requested in the assoc_ml_reconf callback. + */ +struct cfg80211_mlo_reconf_done_data { + const u8 *buf; + size_t len; + u16 added_links; + struct { + struct cfg80211_bss *bss; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; +}; + +/** + * cfg80211_mlo_reconf_add_done - Notify about MLO reconfiguration result + * @dev: network device. + * @data: MLO reconfiguration done data, &struct cfg80211_mlo_reconf_done_data + * + * Inform cfg80211 and the userspace that processing of ML reconfiguration + * request to add links to the association is done. + */ +void cfg80211_mlo_reconf_add_done(struct net_device *dev, + struct cfg80211_mlo_reconf_done_data *data); + /** * cfg80211_schedule_channels_check - schedule regulatory check if needed * @wdev: the wireless device to check @@ -9710,6 +9774,13 @@ void cfg80211_links_removed(struct net_device *dev, u16 link_mask); */ void cfg80211_schedule_channels_check(struct wireless_dev *wdev); +/** + * cfg80211_epcs_changed - Notify about a change in EPCS state + * @netdev: the wireless device whose EPCS state changed + * @enabled: set to true if EPCS was enabled, otherwise set to false. + */ +void cfg80211_epcs_changed(struct net_device *netdev, bool enabled); + #ifdef CONFIG_CFG80211_DEBUGFS /** * wiphy_locked_debugfs_read - do a locked read in debugfs diff --git a/include/net/devlink.h b/include/net/devlink.h index fbb9a2668e24..b8783126c1ed 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -35,7 +35,7 @@ struct devlink_port_phys_attrs { /** * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes * @controller: Associated controller number - * @pf: Associated PCI PF number for this port. + * @pf: associated PCI function number for the devlink port instance * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_pf_attrs { @@ -47,8 +47,9 @@ struct devlink_port_pci_pf_attrs { /** * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes * @controller: Associated controller number - * @pf: Associated PCI PF number for this port. - * @vf: Associated PCI VF for of the PCI PF for this port. + * @pf: associated PCI function number for the devlink port instance + * @vf: associated PCI VF number of a PF for the devlink port instance; + * VF number starts from 0 for the first PCI virtual function * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_vf_attrs { @@ -61,8 +62,8 @@ struct devlink_port_pci_vf_attrs { /** * struct devlink_port_pci_sf_attrs - devlink port's PCI SF attributes * @controller: Associated controller number - * @sf: Associated PCI SF for of the PCI PF for this port. - * @pf: Associated PCI PF number for this port. + * @sf: associated SF number of a PF for the devlink port instance + * @pf: associated PCI function number for the devlink port instance * @external: when set, indicates if a port is for an external controller */ struct devlink_port_pci_sf_attrs { @@ -1261,6 +1262,18 @@ enum devlink_trap_group_generic_id { .min_burst = _min_burst, \ } +#define devlink_fmsg_put(fmsg, name, value) ( \ + _Generic((value), \ + bool : devlink_fmsg_bool_pair_put, \ + u8 : devlink_fmsg_u8_pair_put, \ + u16 : devlink_fmsg_u32_pair_put, \ + u32 : devlink_fmsg_u32_pair_put, \ + u64 : devlink_fmsg_u64_pair_put, \ + int : devlink_fmsg_u32_pair_put, \ + char * : devlink_fmsg_string_pair_put, \ + const char * : devlink_fmsg_string_pair_put) \ + (fmsg, name, (value))) + enum { /* device supports reload operations */ DEVLINK_F_RELOAD = 1UL << 0, @@ -1522,6 +1535,7 @@ int devl_trylock(struct devlink *devlink); void devl_unlock(struct devlink *devlink); void devl_assert_locked(struct devlink *devlink); bool devl_lock_is_held(struct devlink *devlink); +DEFINE_GUARD(devl, struct devlink *, devl_lock(_T), devl_unlock(_T)); struct ib_device; @@ -1994,6 +2008,7 @@ int devlink_compat_switch_id_get(struct net_device *dev, int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port); size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port); +void devlink_fmsg_dump_skb(struct devlink_fmsg *fmsg, const struct sk_buff *skb); #else diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 6c5a1ea209a2..32a34dfe8cc5 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -6,9 +6,13 @@ #define DEFINE_DROP_REASON(FN, FNe) \ FN(NOT_SPECIFIED) \ FN(NO_SOCKET) \ + FN(SOCKET_CLOSE) \ + FN(SOCKET_FILTER) \ + FN(SOCKET_RCVBUFF) \ + FN(UNIX_DISCONNECT) \ + FN(UNIX_SKIP_OOB) \ FN(PKT_TOO_SMALL) \ FN(TCP_CSUM) \ - FN(SOCKET_FILTER) \ FN(UDP_CSUM) \ FN(NETFILTER_DROP) \ FN(OTHERHOST) \ @@ -18,7 +22,6 @@ FN(UNICAST_IN_L2_MULTICAST) \ FN(XFRM_POLICY) \ FN(IP_NOPROTO) \ - FN(SOCKET_RCVBUFF) \ FN(PROTO_MEM) \ FN(TCP_AUTH_HDR) \ FN(TCP_MD5NOTFOUND) \ @@ -36,6 +39,7 @@ FN(TCP_OVERWINDOW) \ FN(TCP_OFOMERGE) \ FN(TCP_RFC7323_PAWS) \ + FN(TCP_RFC7323_PAWS_ACK) \ FN(TCP_OLD_SEQUENCE) \ FN(TCP_INVALID_SEQUENCE) \ FN(TCP_INVALID_ACK_SEQUENCE) \ @@ -58,6 +62,12 @@ FN(TC_EGRESS) \ FN(SECURITY_HOOK) \ FN(QDISC_DROP) \ + FN(QDISC_OVERLIMIT) \ + FN(QDISC_CONGESTED) \ + FN(CAKE_FLOOD) \ + FN(FQ_BAND_LIMIT) \ + FN(FQ_HORIZON_LIMIT) \ + FN(FQ_FLOW_LIMIT) \ FN(CPU_BACKLOG) \ FN(XDP) \ FN(TC_INGRESS) \ @@ -100,11 +110,13 @@ FN(VXLAN_VNI_NOT_FOUND) \ FN(MAC_INVALID_SOURCE) \ FN(VXLAN_ENTRY_EXISTS) \ - FN(VXLAN_NO_REMOTE) \ + FN(NO_TX_TARGET) \ FN(IP_TUNNEL_ECN) \ FN(TUNNEL_TXINFO) \ FN(LOCAL_MAC) \ FN(ARP_PVLAN_DISABLE) \ + FN(MAC_IEEE_MAC_CONTROL) \ + FN(BRIDGE_INGRESS_STP_STATE) \ FNe(MAX) /** @@ -129,12 +141,27 @@ enum skb_drop_reason { * 3) no valid child socket during 3WHS process */ SKB_DROP_REASON_NO_SOCKET, + /** @SKB_DROP_REASON_SOCKET_CLOSE: socket is close()d */ + SKB_DROP_REASON_SOCKET_CLOSE, + /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */ + SKB_DROP_REASON_SOCKET_FILTER, + /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ + SKB_DROP_REASON_SOCKET_RCVBUFF, + /** + * @SKB_DROP_REASON_UNIX_DISCONNECT: recv queue is purged when SOCK_DGRAM + * or SOCK_SEQPACKET socket re-connect()s to another socket or notices + * during send() that the peer has been close()d. + */ + SKB_DROP_REASON_UNIX_DISCONNECT, + /** + * @SKB_DROP_REASON_UNIX_SKIP_OOB: Out-Of-Band data is skipped by + * recv() without MSG_OOB so dropped. + */ + SKB_DROP_REASON_UNIX_SKIP_OOB, /** @SKB_DROP_REASON_PKT_TOO_SMALL: packet size is too small */ SKB_DROP_REASON_PKT_TOO_SMALL, /** @SKB_DROP_REASON_TCP_CSUM: TCP checksum error */ SKB_DROP_REASON_TCP_CSUM, - /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */ - SKB_DROP_REASON_SOCKET_FILTER, /** @SKB_DROP_REASON_UDP_CSUM: UDP checksum error */ SKB_DROP_REASON_UDP_CSUM, /** @SKB_DROP_REASON_NETFILTER_DROP: dropped by netfilter */ @@ -165,8 +192,6 @@ enum skb_drop_reason { SKB_DROP_REASON_XFRM_POLICY, /** @SKB_DROP_REASON_IP_NOPROTO: no support for IP protocol */ SKB_DROP_REASON_IP_NOPROTO, - /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ - SKB_DROP_REASON_SOCKET_RCVBUFF, /** * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as * udp packet drop out of udp_memory_allocated. @@ -251,6 +276,11 @@ enum skb_drop_reason { * LINUX_MIB_PAWSESTABREJECTED, LINUX_MIB_PAWSACTIVEREJECTED */ SKB_DROP_REASON_TCP_RFC7323_PAWS, + /** + * @SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK: PAWS check, old ACK packet. + * Corresponds to LINUX_MIB_PAWS_OLD_ACK. + */ + SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK, /** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */ SKB_DROP_REASON_TCP_OLD_SEQUENCE, /** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */ @@ -311,6 +341,36 @@ enum skb_drop_reason { * failed to enqueue to current qdisc) */ SKB_DROP_REASON_QDISC_DROP, + /** + * @SKB_DROP_REASON_QDISC_OVERLIMIT: dropped by qdisc when a qdisc + * instance exceeds its total buffer size limit. + */ + SKB_DROP_REASON_QDISC_OVERLIMIT, + /** + * @SKB_DROP_REASON_QDISC_CONGESTED: dropped by a qdisc AQM algorithm + * due to congestion. + */ + SKB_DROP_REASON_QDISC_CONGESTED, + /** + * @SKB_DROP_REASON_CAKE_FLOOD: dropped by the flood protection part of + * CAKE qdisc AQM algorithm (BLUE). + */ + SKB_DROP_REASON_CAKE_FLOOD, + /** + * @SKB_DROP_REASON_FQ_BAND_LIMIT: dropped by fq qdisc when per band + * limit is reached. + */ + SKB_DROP_REASON_FQ_BAND_LIMIT, + /** + * @SKB_DROP_REASON_FQ_HORIZON_LIMIT: dropped by fq qdisc when packet + * timestamp is too far in the future. + */ + SKB_DROP_REASON_FQ_HORIZON_LIMIT, + /** + * @SKB_DROP_REASON_FQ_FLOW_LIMIT: dropped by fq qdisc when a flow + * exceeds its limits. + */ + SKB_DROP_REASON_FQ_FLOW_LIMIT, /** * @SKB_DROP_REASON_CPU_BACKLOG: failed to enqueue the skb to the per CPU * backlog queue. This can be caused by backlog queue full (see @@ -461,8 +521,8 @@ enum skb_drop_reason { * entry or an entry pointing to a nexthop. */ SKB_DROP_REASON_VXLAN_ENTRY_EXISTS, - /** @SKB_DROP_REASON_VXLAN_NO_REMOTE: no remote found for xmit */ - SKB_DROP_REASON_VXLAN_NO_REMOTE, + /** @SKB_DROP_REASON_NO_TX_TARGET: no target found for xmit */ + SKB_DROP_REASON_NO_TX_TARGET, /** * @SKB_DROP_REASON_IP_TUNNEL_ECN: skb is dropped according to * RFC 6040 4.2, see __INET_ECN_decapsulate() for detail. @@ -484,6 +544,16 @@ enum skb_drop_reason { * enabled. */ SKB_DROP_REASON_ARP_PVLAN_DISABLE, + /** + * @SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL: the destination MAC address + * is an IEEE MAC Control address. + */ + SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL, + /** + * @SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE: the STP state of the + * ingress bridge port does not allow frames to be forwarded. + */ + SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE, /** * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which * shouldn't be used as a real 'reason' - only for tracing code gen diff --git a/include/net/dsa.h b/include/net/dsa.h index 72ae65e7246a..a0a9481c52c2 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -906,6 +906,8 @@ struct dsa_switch_ops { void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); + void (*get_ts_stats)(struct dsa_switch *ds, int port, + struct ethtool_ts_stats *ts_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, @@ -988,10 +990,9 @@ struct dsa_switch_ops { /* * Port's MAC EEE settings */ + bool (*support_eee)(struct dsa_switch *ds, int port); int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); - int (*get_mac_eee)(struct dsa_switch *ds, int port, - struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); @@ -1383,5 +1384,6 @@ static inline bool dsa_user_dev_check(const struct net_device *dev) netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); +bool dsa_supports_eee(struct dsa_switch *ds, int port); #endif diff --git a/include/net/dst.h b/include/net/dst.h index 0f303cc60252..78c78cdce0e9 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -307,7 +307,7 @@ static inline bool dst_hold_safe(struct dst_entry *dst) * @skb: buffer * * If dst is not yet refcounted and not destroyed, grab a ref on it. - * Returns true if dst is refcounted. + * Returns: true if dst is refcounted. */ static inline bool skb_dst_force(struct sk_buff *skb) { @@ -440,6 +440,15 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) dst->expires = expires; } +static inline unsigned int dst_dev_overhead(struct dst_entry *dst, + struct sk_buff *skb) +{ + if (likely(dst)) + return LL_RESERVED_SPACE(dst->dev); + + return skb->mac_len; +} + INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, diff --git a/include/net/genetlink.h b/include/net/genetlink.h index d096cc6352de..a03d56765832 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -354,7 +354,7 @@ __genlmsg_iput(struct sk_buff *skb, const struct genl_info *info, int flags) * such requests) or a struct initialized by genl_info_init_ntf() * when constructing notifications. * - * Returns pointer to new genetlink header. + * Returns: pointer to new genetlink header. */ static inline void * genlmsg_iput(struct sk_buff *skb, const struct genl_info *info) @@ -366,7 +366,7 @@ genlmsg_iput(struct sk_buff *skb, const struct genl_info *info) * genlmsg_nlhdr - Obtain netlink header from user specified header * @user_hdr: user header as returned from genlmsg_put() * - * Returns pointer to netlink header. + * Returns: pointer to netlink header. */ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr) { @@ -435,7 +435,7 @@ static inline void genl_dump_check_consistent(struct netlink_callback *cb, * @flags: netlink message flags * @cmd: generic netlink command * - * Returns pointer to user specific header + * Returns: pointer to user specific header */ static inline void *genlmsg_put_reply(struct sk_buff *skb, struct genl_info *info, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3c82fad904d4..c7f42844c79a 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk) static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { - return inet_csk_reqsk_queue_len(sk) >= READ_ONCE(sk->sk_max_ack_backlog); + return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 56d8bc5593d3..1086256549fa 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -19,6 +19,7 @@ #include #include +#include #include #include #include @@ -172,7 +173,7 @@ struct inet_cork { u8 tx_flags; __u8 ttl; __s16 tos; - char priority; + u32 priority; __u16 gso_size; u32 ts_opt_id; u64 transmit_time; @@ -302,6 +303,11 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet) return READ_ONCE(inet->inet_flags) & IP_CMSG_ALL; } +static inline dscp_t inet_sk_dscp(const struct inet_sock *inet) +{ + return inet_dsfield_to_dscp(READ_ONCE(inet->tos)); +} + #define inet_test_bit(nr, sk) \ test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet_set_bit(nr, sk) \ diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 62c0a7e65d6b..67a313575780 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -74,6 +74,10 @@ struct inet_timewait_sock { tw_tos : 8; u32 tw_txhash; u32 tw_priority; + /** + * @tw_reuse_stamp: Time of entry into %TCP_TIME_WAIT state in msec. + */ + u32 tw_entry_stamp; struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; struct inet_bind2_bucket *tw_tb2; diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 74ff688568a0..f475757daafb 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -96,30 +96,28 @@ static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr) /* can be called with or without local BH being disabled */ struct inet_peer *inet_getpeer(struct inet_peer_base *base, - const struct inetpeer_addr *daddr, - int create); + const struct inetpeer_addr *daddr); static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base, __be32 v4daddr, - int vif, int create) + int vif) { struct inetpeer_addr daddr; daddr.a4.addr = v4daddr; daddr.a4.vif = vif; daddr.family = AF_INET; - return inet_getpeer(base, &daddr, create); + return inet_getpeer(base, &daddr); } static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base, - const struct in6_addr *v6daddr, - int create) + const struct in6_addr *v6daddr) { struct inetpeer_addr daddr; daddr.a6 = *v6daddr; daddr.family = AF_INET6; - return inet_getpeer(base, &daddr, create); + return inet_getpeer(base, &daddr); } static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a, diff --git a/include/net/ip.h b/include/net/ip.h index 0e548c1f2a0e..9f5e33e371fc 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -81,7 +81,6 @@ struct ipcm_cookie { __u8 protocol; __u8 ttl; __s16 tos; - char priority; __u16 gso_size; }; @@ -96,6 +95,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm_init(ipcm); ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark); + ipcm->sockc.priority = READ_ONCE(inet->sk.sk_priority); ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags); ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 248bfb26e2af..f5c43ad1565e 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -471,7 +471,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, /* This helper is specialized for BIG TCP needs. * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. * It assumes headers are already in skb->head. - * Returns 0, or IPPROTO_TCP if a BIG TCP packet is there. + * Returns: 0, or IPPROTO_TCP if a BIG TCP packet is there. */ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) { diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index dd9e93c12260..9804fa5d9c67 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -202,7 +202,7 @@ struct iucv_handler { * * Registers a driver with IUCV. * - * Returns 0 on success, -ENOMEM if the memory allocation for the pathid + * Returns: 0 on success, -ENOMEM if the memory allocation for the pathid * table failed, or -EIO if IUCV_DECLARE_BUFFER failed on all cpus. */ int iucv_register(struct iucv_handler *handler, int smp); @@ -224,7 +224,7 @@ void iucv_unregister(struct iucv_handler *handle, int smp); * * Allocate a new path structure for use with iucv_connect. * - * Returns NULL if the memory allocation failed or a pointer to the + * Returns: NULL if the memory allocation failed or a pointer to the * path structure. */ static inline struct iucv_path *iucv_path_alloc(u16 msglim, u8 flags, gfp_t gfp) @@ -260,7 +260,7 @@ static inline void iucv_path_free(struct iucv_path *path) * This function is issued after the user received a connection pending * external interrupt and now wishes to complete the IUCV communication path. * - * Returns the result of the CP IUCV call. + * Returns: the result of the CP IUCV call. */ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, u8 *userdata, void *private); @@ -278,7 +278,7 @@ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, * successfully, you are not able to use the path until you receive an IUCV * Connection Complete external interrupt. * - * Returns the result of the CP IUCV call. + * Returns: the result of the CP IUCV call. */ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, u8 *userid, u8 *system, u8 *userdata, @@ -292,7 +292,7 @@ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, * This function temporarily suspends incoming messages on an IUCV path. * You can later reactivate the path by invoking the iucv_resume function. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_path_quiesce(struct iucv_path *path, u8 *userdata); @@ -304,7 +304,7 @@ int iucv_path_quiesce(struct iucv_path *path, u8 *userdata); * This function resumes incoming messages on an IUCV path that has * been stopped with iucv_path_quiesce. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_path_resume(struct iucv_path *path, u8 *userdata); @@ -315,7 +315,7 @@ int iucv_path_resume(struct iucv_path *path, u8 *userdata); * * This function terminates an IUCV path. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_path_sever(struct iucv_path *path, u8 *userdata); @@ -327,7 +327,7 @@ int iucv_path_sever(struct iucv_path *path, u8 *userdata); * * Cancels a message you have sent. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg, u32 srccls); @@ -347,7 +347,7 @@ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg, * * Locking: local_bh_enable/local_bh_disable * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, u8 flags, void *buffer, size_t size, size_t *residual); @@ -367,7 +367,7 @@ int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, * * Locking: no locking. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, u8 flags, void *buffer, size_t size, @@ -382,7 +382,7 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, * are notified of a message and the time that you complete the message, * the message may be rejected. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg); @@ -399,7 +399,7 @@ int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg); * pathid, msgid, and trgcls. Prmmsg signifies the data is moved into * the parameter list. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, u8 flags, void *reply, size_t size); @@ -419,7 +419,7 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, * * Locking: local_bh_enable/local_bh_disable * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_send(struct iucv_path *path, struct iucv_message *msg, u8 flags, u32 srccls, void *buffer, size_t size); @@ -439,7 +439,7 @@ int iucv_message_send(struct iucv_path *path, struct iucv_message *msg, * * Locking: no locking. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, u8 flags, u32 srccls, void *buffer, size_t size); @@ -461,7 +461,7 @@ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, * reply to the message and a buffer is provided into which IUCV moves * the reply to this message. * - * Returns the result from the CP IUCV call. + * Returns: the result from the CP IUCV call. */ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, u8 flags, u32 srccls, void *buffer, size_t size, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ab8dce1f2c27..c3ed2fcff8b7 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1855,6 +1855,9 @@ struct ieee80211_channel_switch { * operation on this interface and request a channel context without * the AP definition. Use this e.g. because the device is able to * handle OFDMA (downlink and trigger for uplink) on a per-AP basis. + * @IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC: indicates that the AP sta should + * be removed only after setting the vif as unassociated, and not the + * opposite. Only relevant for STA vifs. */ enum ieee80211_vif_flags { IEEE80211_VIF_BEACON_FILTER = BIT(0), @@ -1863,6 +1866,7 @@ enum ieee80211_vif_flags { IEEE80211_VIF_GET_NOA_UPDATE = BIT(3), IEEE80211_VIF_EML_ACTIVE = BIT(4), IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW = BIT(5), + IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC = BIT(6), }; @@ -2216,7 +2220,7 @@ enum ieee80211_key_flags { * @tx_pn: PN used for TX keys, may be used by the driver as well if it * needs to do software PN assignment by itself (e.g. due to TSO) * @flags: key flags, see &enum ieee80211_key_flags. - * @keyidx: the key index (0-3) + * @keyidx: the key index (0-7) * @keylen: key material length * @key: key material. For ALG_TKIP the key is encoded as a 256-bit (32 byte) * data block: @@ -2225,7 +2229,7 @@ enum ieee80211_key_flags { * - Temporal Authenticator Rx MIC Key (64 bits) * @icv_len: The ICV length for this key type * @iv_len: The IV length for this key type - * @link_id: the link ID for MLO, or -1 for non-MLO or pairwise keys + * @link_id: the link ID, 0 for non-MLO, or -1 for pairwise keys */ struct ieee80211_key_conf { atomic64_t tx_pn; @@ -2336,6 +2340,8 @@ enum ieee80211_sta_rx_bandwidth { IEEE80211_STA_RX_BW_320, }; +#define IEEE80211_STA_RX_BW_MAX IEEE80211_STA_RX_BW_320 + /** * struct ieee80211_sta_rates - station rate selection table * @@ -4762,7 +4768,7 @@ struct ieee80211_ops { u32 (*get_expected_throughput)(struct ieee80211_hw *hw, struct ieee80211_sta *sta); int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - int *dbm); + unsigned int link_id, int *dbm); int (*tdls_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -7734,6 +7740,50 @@ ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width) } } +/** + * ieee80211_prepare_rx_omi_bw - prepare for sending BW RX OMI + * @link_sta: the link STA the OMI is going to be sent to + * @bw: the bandwidth requested + * + * When the driver decides to do RX OMI to change bandwidth with a STA + * it calls this function to prepare, then sends the OMI, and finally + * calls ieee80211_finalize_rx_omi_bw(). + * + * Note that the (link) STA rate control is updated accordingly as well, + * but the chanctx might not be updated if there are other users. + * If the intention is to reduce the listen bandwidth, the driver must + * ensure there are no TDLS stations nor other uses of the chanctx. + * + * Also note that in order to sequence correctly, narrowing bandwidth + * will only happen in ieee80211_finalize_rx_omi_bw(), whereas widening + * again (e.g. going back to normal) will happen here. + * + * Note that we treat this symmetrically, so if the driver calls this + * and tells the peer to only send with a lower bandwidth, we assume + * that the driver also wants to only send at that lower bandwidth, to + * allow narrowing of the chanctx request for this station/interface. + * + * Finally, the driver must ensure that if the function returned %true, + * ieee80211_finalize_rx_omi_bw() is also called, even for example in + * case of HW restart. + * + * Context: Must be called with wiphy mutex held, and will call back + * into the driver, so ensure no driver locks are held. + * + * Return: %true if changes are going to be made, %false otherwise + */ +bool ieee80211_prepare_rx_omi_bw(struct ieee80211_link_sta *link_sta, + enum ieee80211_sta_rx_bandwidth bw); + +/** + * ieee80211_finalize_rx_omi_bw - finalize BW RX OMI update + * @link_sta: the link STA the OMI was sent to + * + * See ieee80211_client_prepare_rx_omi_bw(). Context is the same here + * as well. + */ +void ieee80211_finalize_rx_omi_bw(struct ieee80211_link_sta *link_sta); + /* for older drivers - let's not document these ... */ int ieee80211_emulate_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); diff --git a/include/net/macsec.h b/include/net/macsec.h index de216cbc6b05..bc7de5b53e54 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -38,8 +38,8 @@ struct metadata_dst; typedef union salt { struct { - u32 ssci; - u64 pn; + ssci_t ssci; + __be64 pn; } __packed; u8 bytes[MACSEC_SALT_LEN]; } __packed salt_t; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 5a2a0df8ad91..0f5eb9db0c62 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -210,6 +210,8 @@ void net_ns_barrier(void); struct ns_common *get_net_ns(struct ns_common *ns); struct net *get_net_ns_by_fd(int fd); +extern struct task_struct *cleanup_net_task; + #else /* CONFIG_NET_NS */ #include #include diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 5ca019d294ca..b02bb9f109d5 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -4,6 +4,16 @@ #include +/** + * struct netdev_config - queue-related configuration for a netdev + * @hds_thresh: HDS Threshold value. + * @hds_config: HDS value from userspace. + */ +struct netdev_config { + u32 hds_thresh; + u8 hds_config; +}; + /* See the netdev.yaml spec for definition of each statistic */ struct netdev_queue_stats_rx { u64 bytes; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index cba3ccf03fcc..3f02a45773e8 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -204,8 +204,7 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, struct nf_conntrack_tuple *tuple); void __nf_ct_refresh_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - const struct sk_buff *skb, - u32 extra_jiffies, bool do_acct); + u32 extra_jiffies, unsigned int bytes); /* Refresh conntrack for this many jiffies and do accounting */ static inline void nf_ct_refresh_acct(struct nf_conn *ct, @@ -213,15 +212,14 @@ static inline void nf_ct_refresh_acct(struct nf_conn *ct, const struct sk_buff *skb, u32 extra_jiffies) { - __nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies, true); + __nf_ct_refresh_acct(ct, ctinfo, extra_jiffies, skb->len); } /* Refresh conntrack for this many jiffies */ static inline void nf_ct_refresh(struct nf_conn *ct, - const struct sk_buff *skb, u32 extra_jiffies) { - __nf_ct_refresh_acct(ct, 0, skb, extra_jiffies, false); + __nf_ct_refresh_acct(ct, 0, extra_jiffies, 0); } /* kill conntrack and do accounting */ @@ -314,16 +312,6 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct) #define NF_CT_DAY (86400 * HZ) -/* Set an arbitrary timeout large enough not to ever expire, this save - * us a check for the IPS_OFFLOAD_BIT from the packet path via - * nf_ct_is_expired(). - */ -static inline void nf_ct_offload_timeout(struct nf_conn *ct) -{ - if (nf_ct_expires(ct) < NF_CT_DAY / 2) - WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY); -} - struct kernel_param; int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp); diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 0c1dac318e02..8dcf7c371ee9 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -12,6 +12,7 @@ #include #include #include +#include enum nf_ct_ecache_state { NFCT_ECACHE_DESTROY_FAIL, /* tried but failed to send destroy event */ @@ -20,6 +21,9 @@ enum nf_ct_ecache_state { struct nf_conntrack_ecache { unsigned long cache; /* bitops want long */ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + local64_t timestamp; /* event timestamp, in nanoseconds */ +#endif u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ u32 missed; /* missed events */ @@ -108,6 +112,14 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) if (e == NULL) return; +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + /* renew only if this is the first cached event, so that the + * timestamp reflects the first, not the last, generated event. + */ + if (local64_read(&e->timestamp) && READ_ONCE(e->cache) == 0) + local64_set(&e->timestamp, ktime_get_real_ns()); +#endif + set_bit(event, &e->cache); #endif } diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index b63d53bb9dd6..d711642e78b5 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -163,6 +163,7 @@ struct flow_offload_tuple_rhash { enum nf_flow_flags { NF_FLOW_SNAT, NF_FLOW_DNAT, + NF_FLOW_CLOSING, NF_FLOW_TEARDOWN, NF_FLOW_HW, NF_FLOW_HW_DYING, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 4afa64c81304..60d5dcdb289c 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -442,6 +442,9 @@ struct nft_set_ext; * @remove: remove element from set * @walk: iterate over all set elements * @get: get set elements + * @ksize: kernel set size + * @usize: userspace set size + * @adjust_maxsize: delta to adjust maximum set size * @commit: commit set elements * @abort: abort set elements * @privsize: function to return size of set private data @@ -495,6 +498,9 @@ struct nft_set_ops { const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags); + u32 (*ksize)(u32 size); + u32 (*usize)(u32 size); + u32 (*adjust_maxsize)(const struct nft_set *set); void (*commit)(struct nft_set *set); void (*abort)(const struct nft_set *set); u64 (*privsize)(const struct nlattr * const nla[], @@ -733,15 +739,18 @@ struct nft_set_ext_tmpl { /** * struct nft_set_ext - set extensions * - * @genmask: generation mask + * @genmask: generation mask, but also flags (see NFT_SET_ELEM_DEAD_BIT) * @offset: offsets of individual extension types * @data: beginning of extension data + * + * This structure must be aligned to word size, otherwise atomic bitops + * on genmask field can cause alignment failure on some archs. */ struct nft_set_ext { u8 genmask; u8 offset[NFT_SET_EXT_NUM]; char data[]; -}; +} __aligned(BITS_PER_LONG / 8); static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) { @@ -1192,6 +1201,8 @@ struct nft_hook { struct list_head list; struct nf_hook_ops ops; struct rcu_head rcu; + char ifname[IFNAMSIZ]; + u8 ifnamelen; }; /** @@ -1227,8 +1238,6 @@ static inline bool nft_is_base_chain(const struct nft_chain *chain) return chain->flags & NFT_CHAIN_BASE; } -int __nft_release_basechain(struct nft_ctx *ctx); - unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); static inline bool nft_use_inc(u32 *use) diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h index 5adf6fda11e8..06985530517b 100644 --- a/include/net/netfilter/nf_tproxy.h +++ b/include/net/netfilter/nf_tproxy.h @@ -49,7 +49,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr); * * nf_tproxy_handle_time_wait4() consumes the socket reference passed in. * - * Returns the listener socket if there's one, the TIME_WAIT socket if + * Returns: the listener socket if there's one, the TIME_WAIT socket if * no such listener is found, or NULL if the TCP header is incomplete. */ struct sock * @@ -108,7 +108,7 @@ nf_tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, * * nf_tproxy_handle_time_wait6() consumes the socket reference passed in. * - * Returns the listener socket if there's one, the TIME_WAIT socket if + * Returns: the listener socket if there's one, the TIME_WAIT socket if * no such listener is found, or NULL if the TCP header is incomplete. */ struct sock * diff --git a/include/net/netlink.h b/include/net/netlink.h index 39eaa6be6ca8..e015ffbed819 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -649,7 +649,7 @@ static inline int nlmsg_ok(const struct nlmsghdr *nlh, int remaining) * @nlh: netlink message header * @remaining: number of bytes remaining in message stream * - * Returns the next netlink message in the message stream and + * Returns: the next netlink message in the message stream and * decrements remaining by the size of the current message. */ static inline struct nlmsghdr * @@ -676,7 +676,7 @@ nlmsg_next(const struct nlmsghdr *nlh, int *remaining) * exceeding maxtype will be rejected, policy must be specified, attributes * will be validated in the strictest way possible. * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, @@ -701,7 +701,7 @@ static inline int nla_parse(struct nlattr **tb, int maxtype, * exceeding maxtype will be ignored and attributes from the policy are not * always strictly validated (only for new attributes). * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, @@ -726,7 +726,7 @@ static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype, * exceeding maxtype will be rejected as well as trailing data, but the * policy is not completely strictly validated (only for new attributes). * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype, const struct nlattr *head, @@ -833,7 +833,7 @@ nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, * @hdrlen: length of family specific header * @attrtype: type of attribute to look for * - * Returns the first attribute which matches the specified type. + * Returns: the first attribute which matches the specified type. */ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, int hdrlen, int attrtype) @@ -854,7 +854,7 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, * specified policy. Validation is done in liberal mode. * See documentation of struct nla_policy for more details. * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_validate_deprecated(const struct nlattr *head, int len, int maxtype, @@ -877,7 +877,7 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * specified policy. Validation is done in strict mode. * See documentation of struct nla_policy for more details. * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, @@ -914,7 +914,7 @@ static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh, * nlmsg_report - need to report back to application? * @nlh: netlink message header * - * Returns 1 if a report back to the application is requested. + * Returns: 1 if a report back to the application is requested. */ static inline int nlmsg_report(const struct nlmsghdr *nlh) { @@ -925,7 +925,7 @@ static inline int nlmsg_report(const struct nlmsghdr *nlh) * nlmsg_seq - return the seq number of netlink message * @nlh: netlink message header * - * Returns 0 if netlink message is NULL + * Returns: 0 if netlink message is NULL */ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) { @@ -952,7 +952,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) * @payload: length of message payload * @flags: message flags * - * Returns NULL if the tailroom of the skb is insufficient to store + * Returns: NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, @@ -971,7 +971,7 @@ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 se * * Append data to an existing nlmsg, used when constructing a message * with multiple fixed-format headers (which is rare). - * Returns NULL if the tailroom of the skb is insufficient to store + * Returns: NULL if the tailroom of the skb is insufficient to store * the extra payload. */ static inline void *nlmsg_append(struct sk_buff *skb, u32 size) @@ -993,7 +993,7 @@ static inline void *nlmsg_append(struct sk_buff *skb, u32 size) * @payload: length of message payload * @flags: message flags * - * Returns NULL if the tailroom of the skb is insufficient to store + * Returns: NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put_answer(struct sk_buff *skb, @@ -1050,7 +1050,7 @@ static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) * nlmsg_get_pos - return current position in netlink message * @skb: socket buffer the message is stored in * - * Returns a pointer to the current tail of the message. + * Returns: a pointer to the current tail of the message. */ static inline void *nlmsg_get_pos(struct sk_buff *skb) { @@ -1276,7 +1276,7 @@ static inline int nla_ok(const struct nlattr *nla, int remaining) * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream * - * Returns the next netlink attribute in the attribute stream and + * Returns: the next netlink attribute in the attribute stream and * decrements remaining by the size of the current attribute. */ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) @@ -1292,7 +1292,7 @@ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) * @nla: attribute containing the nested attributes * @attrtype: type of attribute to look for * - * Returns the first attribute which matches the specified type. + * Returns: the first attribute which matches the specified type. */ static inline struct nlattr * nla_find_nested(const struct nlattr *nla, int attrtype) @@ -2091,7 +2091,7 @@ static inline int nla_get_flag(const struct nlattr *nla) * nla_get_msecs - return payload of msecs attribute * @nla: msecs netlink attribute * - * Returns the number of milliseconds in jiffies. + * Returns: the number of milliseconds in jiffies. */ static inline unsigned long nla_get_msecs(const struct nlattr *nla) { @@ -2183,7 +2183,7 @@ static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp) * marked their nest attributes with NLA_F_NESTED flag. New APIs should use * nla_nest_start() which sets the flag. * - * Returns the container attribute or NULL on error + * Returns: the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, int attrtype) @@ -2204,7 +2204,7 @@ static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, * Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED * flag. This is the preferred function to use in new code. * - * Returns the container attribute or NULL on error + * Returns: the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) { @@ -2219,7 +2219,7 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) * Corrects the container attribute header to include the all * appended attributes. * - * Returns the total data length of the skb. + * Returns: the total data length of the skb. */ static inline int nla_nest_end(struct sk_buff *skb, struct nlattr *start) { @@ -2252,7 +2252,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * specified policy. Attributes with a type exceeding maxtype will be * ignored. See documentation of struct nla_policy for more details. * - * Returns 0 on success or a negative error code. + * Returns: 0 on success or a negative error code. */ static inline int __nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, @@ -2285,7 +2285,7 @@ nla_validate_nested_deprecated(const struct nlattr *start, int maxtype, * nla_need_padding_for_64bit - test 64-bit alignment of the next attribute * @skb: socket buffer the message is stored in * - * Return true if padding is needed to align the next attribute (nla_data()) to + * Return: true if padding is needed to align the next attribute (nla_data()) to * a 64-bit aligned area. */ static inline bool nla_need_padding_for_64bit(struct sk_buff *skb) @@ -2312,7 +2312,7 @@ static inline bool nla_need_padding_for_64bit(struct sk_buff *skb) * This will only be done in architectures which do not have * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS defined. * - * Returns zero on success or a negative error code. + * Returns: zero on success or a negative error code. */ static inline int nla_align_64bit(struct sk_buff *skb, int padattr) { diff --git a/include/net/netmem.h b/include/net/netmem.h index 8a6e20be4b9d..1b58faa4f20f 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -72,6 +72,22 @@ static inline bool netmem_is_net_iov(const netmem_ref netmem) return (__force unsigned long)netmem & NET_IOV; } +/** + * __netmem_to_page - unsafely get pointer to the &page backing @netmem + * @netmem: netmem reference to convert + * + * Unsafe version of netmem_to_page(). When @netmem is always page-backed, + * e.g. when it's a header buffer, performs faster and generates smaller + * object code (no check for the LSB, no WARN). When @netmem points to IOV, + * provokes undefined behaviour. + * + * Return: pointer to the &page (garbage if @netmem is not page-backed). + */ +static inline struct page *__netmem_to_page(netmem_ref netmem) +{ + return (__force struct page *)netmem; +} + /* This conversion fails (returns NULL) if the netmem_ref is not struct page * backed. */ @@ -80,7 +96,7 @@ static inline struct page *netmem_to_page(netmem_ref netmem) if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) return NULL; - return (__force struct page *)netmem; + return __netmem_to_page(netmem); } static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem) @@ -103,6 +119,17 @@ static inline netmem_ref page_to_netmem(struct page *page) return (__force netmem_ref)page; } +/** + * virt_to_netmem - convert virtual memory pointer to a netmem reference + * @data: host memory pointer to convert + * + * Return: netmem reference to the &page backing this virtual address. + */ +static inline netmem_ref virt_to_netmem(const void *data) +{ + return page_to_netmem(virt_to_page(data)); +} + static inline int netmem_ref_count(netmem_ref netmem) { /* The non-pp refcount of net_iov is always 1. On net_iov, we only @@ -127,6 +154,22 @@ static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); } +/** + * __netmem_get_pp - unsafely get pointer to the &page_pool backing @netmem + * @netmem: netmem reference to get the pointer from + * + * Unsafe version of netmem_get_pp(). When @netmem is always page-backed, + * e.g. when it's a header buffer, performs faster and generates smaller + * object code (avoids clearing the LSB). When @netmem points to IOV, + * provokes invalid memory access. + * + * Return: pointer to the &page_pool (garbage if @netmem is not page-backed). + */ +static inline struct page_pool *__netmem_get_pp(netmem_ref netmem) +{ + return __netmem_to_page(netmem)->pp; +} + static inline struct page_pool *netmem_get_pp(netmem_ref netmem) { return __netmem_clear_lsb(netmem)->pp; @@ -158,12 +201,43 @@ static inline netmem_ref netmem_compound_head(netmem_ref netmem) return page_to_netmem(compound_head(netmem_to_page(netmem))); } +/** + * __netmem_address - unsafely get pointer to the memory backing @netmem + * @netmem: netmem reference to get the pointer for + * + * Unsafe version of netmem_address(). When @netmem is always page-backed, + * e.g. when it's a header buffer, performs faster and generates smaller + * object code (no check for the LSB). When @netmem points to IOV, provokes + * undefined behaviour. + * + * Return: pointer to the memory (garbage if @netmem is not page-backed). + */ +static inline void *__netmem_address(netmem_ref netmem) +{ + return page_address(__netmem_to_page(netmem)); +} + static inline void *netmem_address(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) return NULL; - return page_address(netmem_to_page(netmem)); + return __netmem_address(netmem); +} + +/** + * netmem_is_pfmemalloc - check if @netmem was allocated under memory pressure + * @netmem: netmem reference to check + * + * Return: true if @netmem is page-backed and the page was allocated under + * memory pressure, false otherwise. + */ +static inline bool netmem_is_pfmemalloc(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return false; + + return page_is_pfmemalloc(netmem_to_page(netmem)); } static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 3c014170e001..46452da35206 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -175,6 +175,7 @@ struct netns_ipv4 { u8 sysctl_tcp_retries2; u8 sysctl_tcp_orphan_retries; u8 sysctl_tcp_tw_reuse; + unsigned int sysctl_tcp_tw_reuse_delay; int sysctl_tcp_fin_timeout; u8 sysctl_tcp_sack; u8 sysctl_tcp_window_scaling; diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 793e6fd78bc5..582a3d00cbe2 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -104,8 +104,7 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) * * Get a page fragment from the page allocator or page_pool caches. * - * Return: - * Return allocated page fragment, otherwise return NULL. + * Return: allocated page fragment, otherwise return NULL. */ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, unsigned int *offset, @@ -116,22 +115,22 @@ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, return page_pool_alloc_frag(pool, offset, size, gfp); } -static inline struct page *page_pool_alloc(struct page_pool *pool, - unsigned int *offset, - unsigned int *size, gfp_t gfp) +static inline netmem_ref page_pool_alloc_netmem(struct page_pool *pool, + unsigned int *offset, + unsigned int *size, gfp_t gfp) { unsigned int max_size = PAGE_SIZE << pool->p.order; - struct page *page; + netmem_ref netmem; if ((*size << 1) > max_size) { *size = max_size; *offset = 0; - return page_pool_alloc_pages(pool, gfp); + return page_pool_alloc_netmems(pool, gfp); } - page = page_pool_alloc_frag(pool, offset, *size, gfp); - if (unlikely(!page)) - return NULL; + netmem = page_pool_alloc_frag_netmem(pool, offset, *size, gfp); + if (unlikely(!netmem)) + return 0; /* There is very likely not enough space for another fragment, so append * the remaining size to the current fragment to avoid truesize @@ -142,7 +141,23 @@ static inline struct page *page_pool_alloc(struct page_pool *pool, pool->frag_offset = max_size; } - return page; + return netmem; +} + +static inline netmem_ref page_pool_dev_alloc_netmem(struct page_pool *pool, + unsigned int *offset, + unsigned int *size) +{ + gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; + + return page_pool_alloc_netmem(pool, offset, size, gfp); +} + +static inline struct page *page_pool_alloc(struct page_pool *pool, + unsigned int *offset, + unsigned int *size, gfp_t gfp) +{ + return netmem_to_page(page_pool_alloc_netmem(pool, offset, size, gfp)); } /** @@ -155,8 +170,7 @@ static inline struct page *page_pool_alloc(struct page_pool *pool, * depending on the requested size in order to allocate memory with least memory * utilization and performance penalty. * - * Return: - * Return allocated page or page fragment, otherwise return NULL. + * Return: allocated page or page fragment, otherwise return NULL. */ static inline struct page *page_pool_dev_alloc(struct page_pool *pool, unsigned int *offset, @@ -190,8 +204,7 @@ static inline void *page_pool_alloc_va(struct page_pool *pool, * This is just a thin wrapper around the page_pool_alloc() API, and * it returns va of the allocated page or page fragment. * - * Return: - * Return the va for the allocated page or page fragment, otherwise return NULL. + * Return: the va for the allocated page or page fragment, otherwise return NULL. */ static inline void *page_pool_dev_alloc_va(struct page_pool *pool, unsigned int *size) @@ -294,7 +307,7 @@ static inline long page_pool_unref_page(struct page *page, long nr) static inline void page_pool_ref_netmem(netmem_ref netmem) { - atomic_long_inc(&netmem_to_page(netmem)->pp_ref_count); + atomic_long_inc(netmem_get_pp_ref_count_ref(netmem)); } static inline void page_pool_ref_page(struct page *page) @@ -302,7 +315,7 @@ static inline void page_pool_ref_page(struct page *page) page_pool_ref_netmem(page_to_netmem(page)); } -static inline bool page_pool_is_last_ref(netmem_ref netmem) +static inline bool page_pool_unref_and_test(netmem_ref netmem) { /* If page_pool_unref_page() returns 0, we were the last user */ return page_pool_unref_netmem(netmem, 1) == 0; @@ -317,7 +330,7 @@ static inline void page_pool_put_netmem(struct page_pool *pool, * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - if (!page_pool_is_last_ref(netmem)) + if (!page_pool_unref_and_test(netmem)) return; page_pool_put_unrefed_netmem(pool, netmem, dma_sync_size, allow_direct); @@ -418,7 +431,21 @@ static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem) */ static inline dma_addr_t page_pool_get_dma_addr(const struct page *page) { - return page_pool_get_dma_addr_netmem(page_to_netmem((struct page *)page)); + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) + ret <<= PAGE_SHIFT; + + return ret; +} + +static inline void __page_pool_dma_sync_for_cpu(const struct page_pool *pool, + const dma_addr_t dma_addr, + u32 offset, u32 dma_sync_size) +{ + dma_sync_single_range_for_cpu(pool->p.dev, dma_addr, + offset + pool->p.offset, dma_sync_size, + page_pool_get_dma_dir(pool)); } /** @@ -437,10 +464,21 @@ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool, const struct page *page, u32 offset, u32 dma_sync_size) { - dma_sync_single_range_for_cpu(pool->p.dev, - page_pool_get_dma_addr(page), - offset + pool->p.offset, dma_sync_size, - page_pool_get_dma_dir(pool)); + __page_pool_dma_sync_for_cpu(pool, page_pool_get_dma_addr(page), offset, + dma_sync_size); +} + +static inline void +page_pool_dma_sync_netmem_for_cpu(const struct page_pool *pool, + const netmem_ref netmem, u32 offset, + u32 dma_sync_size) +{ + if (!pool->dma_sync_for_cpu) + return; + + __page_pool_dma_sync_for_cpu(pool, + page_pool_get_dma_addr_netmem(netmem), + offset, dma_sync_size); } static inline bool page_pool_put(struct page_pool *pool) diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index c022c410abe3..7f405672b089 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -164,7 +164,8 @@ struct page_pool { bool has_init_callback:1; /* slow::init_callback is set */ bool dma_map:1; /* Perform DMA mapping */ - bool dma_sync:1; /* Perform DMA sync */ + bool dma_sync:1; /* Perform DMA sync for device */ + bool dma_sync_for_cpu:1; /* Perform DMA sync for cpu */ #ifdef CONFIG_PAGE_POOL_STATS bool system:1; /* This is a global percpu pool */ #endif @@ -236,13 +237,12 @@ struct page_pool { struct { struct hlist_node list; u64 detach_time; - u32 napi_id; u32 id; } user; }; struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); -netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp); +netmem_ref page_pool_alloc_netmems(struct page_pool *pool, gfp_t gfp); struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, unsigned int size, gfp_t gfp); netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, @@ -259,8 +259,7 @@ void page_pool_disable_direct_recycling(struct page_pool *pool); void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), const struct xdp_mem_info *mem); -void page_pool_put_page_bulk(struct page_pool *pool, void **data, - int count); +void page_pool_put_netmem_bulk(netmem_ref *data, u32 count); #else static inline void page_pool_destroy(struct page_pool *pool) { @@ -272,8 +271,7 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool, { } -static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, - int count) +static inline void page_pool_put_netmem_bulk(netmem_ref *data, u32 count) { } #endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index cf199af85c52..c64fd896b1f9 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -75,11 +75,11 @@ static inline bool tcf_block_non_null_shared(struct tcf_block *block) } #ifdef CONFIG_NET_CLS_ACT -DECLARE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key); +DECLARE_STATIC_KEY_FALSE(tcf_sw_enabled_key); static inline bool tcf_block_bypass_sw(struct tcf_block *block) { - return block && block->bypass_wanted; + return block && !atomic_read(&block->useswcnt); } #endif @@ -319,7 +319,7 @@ tcf_exts_hw_stats_update(const struct tcf_exts *exts, * tcf_exts_has_actions - check if at least one action is present * @exts: tc filter extensions handle * - * Returns true if at least one action is present. + * Returns: true if at least one action is present. */ static inline bool tcf_exts_has_actions(struct tcf_exts *exts) { @@ -501,7 +501,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, * through all ematches respecting their logic relations returning * as soon as the result is obvious. * - * Returns 1 if the ematch tree as-one matches, no ematches are configured + * Returns: 1 if the ematch tree as-one matches, no ematches are configured * or ematch is not enabled in the kernel, otherwise 0 is returned. */ static inline int tcf_em_tree_match(struct sk_buff *skb, @@ -760,6 +760,15 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, cls_common->extack = extack; } +static inline void tcf_proto_update_usesw(struct tcf_proto *tp, u32 flags) +{ + if (tp->usesw) + return; + if (tc_skip_sw(flags) && tc_in_hw(flags)) + return; + tp->usesw = true; +} + #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb) { diff --git a/include/net/route.h b/include/net/route.h index 84cb1e04f5cd..f86775be3e29 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -129,6 +130,33 @@ struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); + +static inline void inet_sk_init_flowi4(const struct inet_sock *inet, + struct flowi4 *fl4) +{ + const struct ip_options_rcu *ip4_opt; + const struct sock *sk; + __be32 daddr; + + rcu_read_lock(); + ip4_opt = rcu_dereference(inet->inet_opt); + + /* Source routing option overrides the socket destination address */ + if (ip4_opt && ip4_opt->opt.srr) + daddr = ip4_opt->opt.faddr; + else + daddr = inet->inet_daddr; + rcu_read_unlock(); + + sk = &inet->sk; + flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), + ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), + sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, + inet->inet_saddr, inet->inet_dport, + inet->inet_sport, sk->sk_uid); + security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); +} + struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp, const struct sk_buff *skb); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp, @@ -185,20 +213,6 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi return ip_route_output_flow(net, fl4, sk); } -static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 *fl4, - __be32 daddr, __be32 saddr, - __be32 gre_key, __u8 tos, int oif) -{ - memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; - fl4->daddr = daddr; - fl4->saddr = saddr; - fl4->flowi4_tos = tos; - fl4->flowi4_proto = IPPROTO_GRE; - fl4->fl4_gre_key = gre_key; - return ip_route_output_key(net, fl4); -} - enum skb_drop_reason ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 5d74fa7e694c..d635c5b47eba 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -425,6 +425,7 @@ struct tcf_proto { spinlock_t lock; bool deleting; bool counted; + bool usesw; refcount_t refcnt; struct rcu_head rcu; struct hlist_node destroy_ht_node; @@ -474,9 +475,7 @@ struct tcf_block { struct flow_block flow_block; struct list_head owner_list; bool keep_dst; - bool bypass_wanted; - atomic_t filtercnt; /* Number of filters */ - atomic_t skipswcnt; /* Number of skip_sw filters */ + atomic_t useswcnt; atomic_t offloadcnt; /* Number of oddloaded filters */ unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */ @@ -1245,6 +1244,14 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_DROP; } +static inline int qdisc_drop_reason(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free, + enum skb_drop_reason reason) +{ + tcf_set_drop_reason(skb, reason); + return qdisc_drop(skb, sch, to_free); +} + static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { diff --git a/include/net/scm.h b/include/net/scm.h index 0d35c7c77a74..22bb49589fde 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -105,16 +105,16 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg, #ifdef CONFIG_SECURITY_NETWORK static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm) { - char *secdata; - u32 seclen; + struct lsm_context ctx; int err; if (test_bit(SOCK_PASSSEC, &sock->flags)) { - err = security_secid_to_secctx(scm->secid, &secdata, &seclen); + err = security_secid_to_secctx(scm->secid, &ctx); - if (!err) { - put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, seclen, secdata); - security_release_secctx(secdata, seclen); + if (err >= 0) { + put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, ctx.len, + ctx.context); + security_release_secctx(&ctx); } } } diff --git a/include/net/sock.h b/include/net/sock.h index 7464e9f9f47c..8036b3b79cd8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -953,6 +953,7 @@ enum sock_flags { SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ + SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) @@ -1527,7 +1528,7 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size) } static inline bool -sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +__sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc) { int delta; @@ -1535,7 +1536,13 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || - skb_pfmemalloc(skb); + pfmemalloc; +} + +static inline bool +sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +{ + return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb)); } static inline int sk_unused_reserved_mem(const struct sock *sk) @@ -1814,13 +1821,15 @@ struct sockcm_cookie { u32 mark; u32 tsflags; u32 ts_opt_id; + u32 priority; }; static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { *sockc = (struct sockcm_cookie) { - .tsflags = READ_ONCE(sk->sk_tsflags) + .tsflags = READ_ONCE(sk->sk_tsflags), + .priority = READ_ONCE(sk->sk_priority), }; } @@ -2291,7 +2300,7 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) } /** - * sock_poll_wait - place memory barrier behind the poll_wait call. + * sock_poll_wait - wrapper for the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table @@ -2301,15 +2310,12 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { - if (!poll_does_not_wait(p)) { - poll_wait(filp, &sock->wq.wait, p); - /* We need to be sure we are in sync with the - * socket flags modification. - * - * This memory barrier is paired in the wq_has_sleeper. - */ - smp_mb(); - } + /* Provides a barrier we need to be sure we are in sync + * with the socket flags modification. + * + * This memory barrier is paired in the wq_has_sleeper. + */ + poll_wait(filp, &sock->wq.wait, p); } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) @@ -2658,7 +2664,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, { #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP) | \ - (1UL << SOCK_RCVMARK)) + (1UL << SOCK_RCVMARK) |\ + (1UL << SOCK_RCVPRIORITY)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) diff --git a/include/net/tcp.h b/include/net/tcp.h index e9b37b76e894..5b2b04835688 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1817,7 +1817,7 @@ int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() * @c: returned tcp_sigpool for usage (uninitialized on failure) * - * Returns 0 on success, error otherwise. + * Returns: 0 on success, error otherwise. */ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c); /** diff --git a/include/net/tls.h b/include/net/tls.h index 61fef2880114..857340338b69 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -59,6 +59,8 @@ struct tls_rec; #define TLS_CRYPTO_INFO_READY(info) ((info)->cipher_type) +#define TLS_HANDSHAKE_KEYUPDATE 24 /* rfc8446 B.3: Key update */ + #define TLS_AAD_SPACE_SIZE 13 #define TLS_MAX_IV_SIZE 16 @@ -130,6 +132,7 @@ struct tls_sw_context_rx { u8 async_capable:1; u8 zc_capable:1; u8 reader_contended:1; + bool key_update_pending; struct tls_strparser strp; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 33ba6fc151cf..2dd23ee2bacd 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -227,6 +227,7 @@ struct vxlan_config { unsigned int addrmax; bool no_share; enum ifla_vxlan_df df; + struct vxlanhdr reserved_bits; }; enum { diff --git a/include/net/xdp.h b/include/net/xdp.h index e6770dd40c91..4dafc5e021f1 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -11,6 +11,8 @@ #include #include /* skb_shared_info */ +#include + /** * DOC: XDP RX-queue information * @@ -62,7 +64,6 @@ struct xdp_rxq_info { u32 queue_index; u32 reg_state; struct xdp_mem_info mem; - unsigned int napi_id; u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ @@ -88,7 +89,7 @@ struct xdp_buff { u32 flags; /* supported values defined in xdp_buff_flags */ }; -static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) +static __always_inline bool xdp_buff_has_frags(const struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); } @@ -103,7 +104,8 @@ static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } -static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) +static __always_inline bool +xdp_buff_is_frag_pfmemalloc(const struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } @@ -144,15 +146,16 @@ xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) static inline struct skb_shared_info * -xdp_get_shared_info_from_buff(struct xdp_buff *xdp) +xdp_get_shared_info_from_buff(const struct xdp_buff *xdp) { return (struct skb_shared_info *)xdp_data_hard_end(xdp); } -static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) +static __always_inline unsigned int +xdp_get_buff_len(const struct xdp_buff *xdp) { unsigned int len = xdp->data_end - xdp->data; - struct skb_shared_info *sinfo; + const struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; @@ -163,26 +166,114 @@ out: return len; } +void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp); + +/** + * __xdp_buff_add_frag - attach frag to &xdp_buff + * @xdp: XDP buffer to attach the frag to + * @netmem: network memory containing the frag + * @offset: offset at which the frag starts + * @size: size of the frag + * @truesize: total memory size occupied by the frag + * @try_coalesce: whether to try coalescing the frags (not valid for XSk) + * + * Attach frag to the XDP buffer. If it currently has no frags attached, + * initialize the related fields, otherwise check that the frag number + * didn't reach the limit of ``MAX_SKB_FRAGS``. If possible, try coalescing + * the frag with the previous one. + * The function doesn't check/update the pfmemalloc bit. Please use the + * non-underscored wrapper in drivers. + * + * Return: true on success, false if there's no space for the frag in + * the shared info struct. + */ +static inline bool __xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem, + u32 offset, u32 size, u32 truesize, + bool try_coalesce) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + skb_frag_t *prev; + u32 nr_frags; + + if (!xdp_buff_has_frags(xdp)) { + xdp_buff_set_frags_flag(xdp); + + nr_frags = 0; + sinfo->xdp_frags_size = 0; + sinfo->xdp_frags_truesize = 0; + + goto fill; + } + + nr_frags = sinfo->nr_frags; + prev = &sinfo->frags[nr_frags - 1]; + + if (try_coalesce && netmem == skb_frag_netmem(prev) && + offset == skb_frag_off(prev) + skb_frag_size(prev)) { + skb_frag_size_add(prev, size); + /* Guaranteed to only decrement the refcount */ + xdp_return_frag(netmem, xdp); + } else if (unlikely(nr_frags == MAX_SKB_FRAGS)) { + return false; + } else { +fill: + __skb_fill_netmem_desc_noacc(sinfo, nr_frags++, netmem, + offset, size); + } + + sinfo->nr_frags = nr_frags; + sinfo->xdp_frags_size += size; + sinfo->xdp_frags_truesize += truesize; + + return true; +} + +/** + * xdp_buff_add_frag - attach frag to &xdp_buff + * @xdp: XDP buffer to attach the frag to + * @netmem: network memory containing the frag + * @offset: offset at which the frag starts + * @size: size of the frag + * @truesize: total memory size occupied by the frag + * + * Version of __xdp_buff_add_frag() which takes care of the pfmemalloc bit. + * + * Return: true on success, false if there's no space for the frag in + * the shared info struct. + */ +static inline bool xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem, + u32 offset, u32 size, u32 truesize) +{ + if (!__xdp_buff_add_frag(xdp, netmem, offset, size, truesize, true)) + return false; + + if (unlikely(netmem_is_pfmemalloc(netmem))) + xdp_buff_set_frag_pfmemalloc(xdp); + + return true; +} + struct xdp_frame { void *data; - u16 len; - u16 headroom; + u32 len; + u32 headroom; u32 metasize; /* uses lower 8-bits */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, - * while mem info is valid on remote CPU. + * while mem_type is valid on remote CPU. */ - struct xdp_mem_info mem; + enum xdp_mem_type mem_type:32; struct net_device *dev_rx; /* used by cpumap */ u32 frame_sz; u32 flags; /* supported values defined in xdp_buff_flags */ }; -static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) +static __always_inline bool xdp_frame_has_frags(const struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } -static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) +static __always_inline bool +xdp_frame_is_frag_pfmemalloc(const struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } @@ -190,18 +281,16 @@ static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; - void *xa; - void *q[XDP_BULK_QUEUE_SIZE]; + netmem_ref q[XDP_BULK_QUEUE_SIZE]; }; static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) { - /* bq->count will be zero'ed when bq->xa gets updated */ - bq->xa = NULL; + bq->count = 0; } static inline struct skb_shared_info * -xdp_get_shared_info_from_frame(struct xdp_frame *frame) +xdp_get_shared_info_from_frame(const struct xdp_frame *frame) { void *data_hard_start = frame->data - frame->headroom - sizeof(*frame); @@ -227,7 +316,14 @@ xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, unsigned int size, unsigned int truesize, bool pfmemalloc) { - skb_shinfo(skb)->nr_frags = nr_frags; + struct skb_shared_info *sinfo = skb_shinfo(skb); + + sinfo->nr_frags = nr_frags; + /* + * ``destructor_arg`` is unionized with ``xdp_frags_{,true}size``, + * reset it after that these fields aren't used anymore. + */ + sinfo->destructor_arg = NULL; skb->len += size; skb->data_len += size; @@ -239,6 +335,8 @@ xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) +struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp); +struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, @@ -249,7 +347,8 @@ int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline -void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) +void xdp_convert_frame_to_buff(const struct xdp_frame *frame, + struct xdp_buff *xdp) { xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame); xdp->data = frame->data; @@ -260,7 +359,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) } static inline -int xdp_update_frame_from_buff(struct xdp_buff *xdp, +int xdp_update_frame_from_buff(const struct xdp_buff *xdp, struct xdp_frame *xdp_frame) { int metasize, headroom; @@ -302,24 +401,33 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0)) return NULL; - /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */ - xdp_frame->mem = xdp->rxq->mem; + /* rxq only valid until napi_schedule ends, convert to xdp_mem_type */ + xdp_frame->mem_type = xdp->rxq->mem.type; return xdp_frame; } -void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, - struct xdp_buff *xdp); +void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type, + bool napi_direct, struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); -void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); -static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf) +static inline void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq) { - struct skb_shared_info *sinfo; + if (unlikely(!bq->count)) + return; + + page_pool_put_netmem_bulk(bq->q, bq->count); + bq->count = 0; +} + +static __always_inline unsigned int +xdp_get_frame_len(const struct xdp_frame *xdpf) +{ + const struct skb_shared_info *sinfo; unsigned int len = xdpf->len; if (likely(!xdp_frame_has_frags(xdpf))) @@ -351,6 +459,38 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator); void xdp_unreg_mem_model(struct xdp_mem_info *mem); +int xdp_reg_page_pool(struct page_pool *pool); +void xdp_unreg_page_pool(const struct page_pool *pool); +void xdp_rxq_info_attach_page_pool(struct xdp_rxq_info *xdp_rxq, + const struct page_pool *pool); + +/** + * xdp_rxq_info_attach_mem_model - attach registered mem info to RxQ info + * @xdp_rxq: XDP RxQ info to attach the memory info to + * @mem: already registered memory info + * + * If the driver registers its memory providers manually, it must use this + * function instead of xdp_rxq_info_reg_mem_model(). + */ +static inline void +xdp_rxq_info_attach_mem_model(struct xdp_rxq_info *xdp_rxq, + const struct xdp_mem_info *mem) +{ + xdp_rxq->mem = *mem; +} + +/** + * xdp_rxq_info_detach_mem_model - detach registered mem info from RxQ info + * @xdp_rxq: XDP RxQ info to detach the memory info from + * + * If the driver registers its memory providers manually and then attaches it + * via xdp_rxq_info_attach_mem_model(), it must call this function before + * xdp_rxq_info_unreg(). + */ +static inline void xdp_rxq_info_detach_mem_model(struct xdp_rxq_info *xdp_rxq) +{ + xdp_rxq->mem = (struct xdp_mem_info){ }; +} /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 40085afd9160..784cd34f5bba 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -59,15 +59,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, xp_fill_cb(pool, desc); } -static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) -{ -#ifdef CONFIG_NET_RX_BUSY_POLL - return pool->heads[0].xdp.rxq->napi_id; -#else - return 0; -#endif -} - static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { @@ -101,7 +92,7 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return xp_alloc(pool); } -static inline bool xsk_is_eop_desc(struct xdp_desc *desc) +static inline bool xsk_is_eop_desc(const struct xdp_desc *desc) { return !xp_mb_desc(desc); } @@ -136,14 +127,24 @@ out: xp_free(xskb); } -static inline void xsk_buff_add_frag(struct xdp_buff *xdp) +static inline bool xsk_buff_add_frag(struct xdp_buff *head, + struct xdp_buff *xdp) { - struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp); + const void *data = xdp->data; + struct xdp_buff_xsk *frag; + if (!__xdp_buff_add_frag(head, virt_to_netmem(data), + offset_in_page(data), xdp->data_end - data, + xdp->frame_sz, false)) + return false; + + frag = container_of(xdp, struct xdp_buff_xsk, xdp); list_add_tail(&frag->list_node, &frag->pool->xskb_list); + + return true; } -static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) +static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first) { struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp); struct xdp_buff *ret = NULL; @@ -200,7 +201,8 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) XDP_TXMD_FLAGS_CHECKSUM | \ 0) -static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta) +static inline bool +xsk_buff_valid_tx_metadata(const struct xsk_tx_metadata *meta) { return !(meta->flags & ~XDP_TXMD_FLAGS_VALID); } @@ -306,11 +308,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, { } -static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) -{ - return 0; -} - static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { @@ -337,7 +334,7 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return NULL; } -static inline bool xsk_is_eop_desc(struct xdp_desc *desc) +static inline bool xsk_is_eop_desc(const struct xdp_desc *desc) { return false; } @@ -356,11 +353,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } -static inline void xsk_buff_add_frag(struct xdp_buff *xdp) +static inline bool xsk_buff_add_frag(struct xdp_buff *head, + struct xdp_buff *xdp) { + return false; } -static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) +static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first) { return NULL; } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 32c09e85a64c..ed4b83696c77 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -38,6 +38,7 @@ #define XFRM_PROTO_COMP 108 #define XFRM_PROTO_IPIP 4 #define XFRM_PROTO_IPV6 41 +#define XFRM_PROTO_IPTFS IPPROTO_AGGFRAG #define XFRM_PROTO_ROUTING IPPROTO_ROUTING #define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS @@ -213,6 +214,7 @@ struct xfrm_state { u16 family; xfrm_address_t saddr; int header_len; + int enc_hdr_len; int trailer_len; u32 extra_flags; struct xfrm_mark smark; @@ -303,6 +305,9 @@ struct xfrm_state { * interpreted by xfrm_type methods. */ void *data; u8 dir; + + const struct xfrm_mode_cbs *mode_cbs; + void *mode_data; }; static inline struct net *xs_net(struct xfrm_state *x) @@ -460,6 +465,45 @@ struct xfrm_type_offload { int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); +/** + * struct xfrm_mode_cbs - XFRM mode callbacks + * @owner: module owner or NULL + * @init_state: Add/init mode specific state in `xfrm_state *x` + * @clone_state: Copy mode specific values from `orig` to new state `x` + * @destroy_state: Cleanup mode specific state from `xfrm_state *x` + * @user_init: Process mode specific netlink attributes from user + * @copy_to_user: Add netlink attributes to `attrs` based on state in `x` + * @sa_len: Return space required to store mode specific netlink attributes + * @get_inner_mtu: Return avail payload space after removing encap overhead + * @input: Process received packet from SA using mode + * @output: Output given packet using mode + * @prepare_output: Add mode specific encapsulation to packet in skb. On return + * `transport_header` should point at ESP header, `network_header` should + * point at outer IP header and `mac_header` should opint at the + * protocol/nexthdr field of the outer IP. + * + * One should examine and understand the specific uses of these callbacks in + * xfrm for further detail on how and when these functions are called. RTSL. + */ +struct xfrm_mode_cbs { + struct module *owner; + int (*init_state)(struct xfrm_state *x); + int (*clone_state)(struct xfrm_state *x, struct xfrm_state *orig); + void (*destroy_state)(struct xfrm_state *x); + int (*user_init)(struct net *net, struct xfrm_state *x, + struct nlattr **attrs, + struct netlink_ext_ack *extack); + int (*copy_to_user)(struct xfrm_state *x, struct sk_buff *skb); + unsigned int (*sa_len)(const struct xfrm_state *x); + u32 (*get_inner_mtu)(struct xfrm_state *x, int outer_mtu); + int (*input)(struct xfrm_state *x, struct sk_buff *skb); + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); + int (*prepare_output)(struct xfrm_state *x, struct sk_buff *skb); +}; + +int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs); +void xfrm_unregister_mode_cbs(u8 mode); + static inline int xfrm_af2proto(unsigned int family) { switch(family) { @@ -1224,9 +1268,19 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, if (xo) { x = xfrm_input_state(skb); - if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) - return (xo->flags & CRYPTO_DONE) && - (xo->status & CRYPTO_SUCCESS); + if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) { + bool check = (xo->flags & CRYPTO_DONE) && + (xo->status & CRYPTO_SUCCESS); + + /* The packets here are plain ones and secpath was + * needed to indicate that hardware already handled + * them and there is no need to do nothing in addition. + * + * Consume secpath which was set by drivers. + */ + secpath_reset(skb); + return check; + } } return __xfrm_check_nopolicy(net, skb, dir) || diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index bb03cee716b3..50779406bc2d 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -29,7 +29,7 @@ struct xdp_buff_xsk { dma_addr_t frame_dma; struct xsk_buff_pool *pool; struct list_head list_node; -}; +} __aligned_largest; #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb)) #define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t)) @@ -183,7 +183,7 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } -static inline bool xp_mb_desc(struct xdp_desc *desc) +static inline bool xp_mb_desc(const struct xdp_desc *desc) { return desc->options & XDP_PKT_CONTD; } diff --git a/include/rdma/ib_cache.h b/include/rdma/ib_cache.h index 226ae3702d8a..2bf09b594d10 100644 --- a/include/rdma/ib_cache.h +++ b/include/rdma/ib_cache.h @@ -63,22 +63,6 @@ int ib_find_cached_pkey(struct ib_device *device, u16 pkey, u16 *index); -/** - * ib_find_exact_cached_pkey - Returns the PKey table index where a specified - * PKey value occurs. Comparison uses the FULL 16 bits (incl membership bit) - * @device: The device to query. - * @port_num: The port number of the device to search for the PKey. - * @pkey: The PKey value to search for. - * @index: The index into the cached PKey table where the PKey was found. - * - * ib_find_exact_cached_pkey() searches the specified PKey table in - * the local software cache. - */ -int ib_find_exact_cached_pkey(struct ib_device *device, - u32 port_num, - u16 pkey, - u16 *index); - /** * ib_get_cached_lmc - Returns a cached lmc table entry * @device: The device to query. diff --git a/include/rdma/ib_marshall.h b/include/rdma/ib_marshall.h index 1838869aad28..b179e464e3d1 100644 --- a/include/rdma/ib_marshall.h +++ b/include/rdma/ib_marshall.h @@ -22,7 +22,4 @@ void ib_copy_ah_attr_to_user(struct ib_device *device, void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst, struct sa_path_rec *src); -void ib_copy_path_rec_from_user(struct sa_path_rec *dst, - struct ib_user_path_rec *src); - #endif /* IB_USER_MARSHALL_H */ diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h index b8c56d7dc35d..8266fab826a7 100644 --- a/include/rdma/ib_pack.h +++ b/include/rdma/ib_pack.h @@ -283,7 +283,4 @@ int ib_ud_header_init(int payload_bytes, int ib_ud_header_pack(struct ib_ud_header *header, void *buf); -int ib_ud_header_unpack(void *buf, - struct ib_ud_header *header); - #endif /* IB_PACK_H */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 3417636da960..0ad104dae253 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -59,9 +59,6 @@ extern struct workqueue_struct *ib_comp_unbound_wq; struct ib_ucq_object; -__printf(3, 4) __cold -void ibdev_printk(const char *level, const struct ib_device *ibdev, - const char *format, ...); __printf(2, 3) __cold void ibdev_emerg(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold @@ -2177,6 +2174,7 @@ struct ib_port_cache { struct ib_gid_table *gid; u8 lmc; enum ib_port_state port_state; + enum ib_port_state last_port_state; }; struct ib_port_immutable { @@ -2256,7 +2254,9 @@ struct rdma_netdev_alloc_params { struct ib_odp_counters { atomic64_t faults; + atomic64_t faults_handled; atomic64_t invalidations; + atomic64_t invalidations_handled; atomic64_t prefetch; }; @@ -2681,6 +2681,13 @@ struct ib_device_ops { */ void (*ufile_hw_cleanup)(struct ib_uverbs_file *ufile); + /** + * report_port_event - Drivers need to implement this if they have + * some private stuff to handle when link status changes. + */ + void (*report_port_event)(struct ib_device *ibdev, + struct net_device *ndev, unsigned long event); + DECLARE_RDMA_OBJ_SIZE(ib_ah); DECLARE_RDMA_OBJ_SIZE(ib_counters); DECLARE_RDMA_OBJ_SIZE(ib_cq); @@ -4469,6 +4476,17 @@ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, unsigned int port); struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port); +int ib_query_netdev_port(struct ib_device *ibdev, struct net_device *ndev, + u32 *port); + +static inline enum ib_port_state ib_get_curr_port_state(struct net_device *net_dev) +{ + return (netif_running(net_dev) && netif_carrier_ok(net_dev)) ? + IB_PORT_ACTIVE : IB_PORT_DOWN; +} + +void ib_dispatch_port_state_event(struct ib_device *ibdev, + struct net_device *ndev); struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr); int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata); diff --git a/include/rv/da_monitor.h b/include/rv/da_monitor.h index 9705b2a98e49..510c88bfabd4 100644 --- a/include/rv/da_monitor.h +++ b/include/rv/da_monitor.h @@ -14,6 +14,7 @@ #include #include #include +#include #ifdef CONFIG_RV_REACTORS @@ -324,10 +325,13 @@ static inline struct da_monitor *da_get_monitor_##name(struct task_struct *tsk) static void da_monitor_reset_all_##name(void) \ { \ struct task_struct *g, *p; \ + int cpu; \ \ read_lock(&tasklist_lock); \ for_each_process_thread(g, p) \ da_monitor_reset_##name(da_get_monitor_##name(p)); \ + for_each_present_cpu(cpu) \ + da_monitor_reset_##name(da_get_monitor_##name(idle_task(cpu))); \ read_unlock(&tasklist_lock); \ } \ \ diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h index 4a9b4169e081..183d9fd50d2d 100644 --- a/include/scsi/libfc.h +++ b/include/scsi/libfc.h @@ -963,7 +963,7 @@ int fc_queuecommand(struct Scsi_Host *, struct scsi_cmnd *); int fc_eh_abort(struct scsi_cmnd *); int fc_eh_device_reset(struct scsi_cmnd *); int fc_eh_host_reset(struct scsi_cmnd *); -int fc_slave_alloc(struct scsi_device *); +int fc_sdev_init(struct scsi_device *); /* * ELS/CT interface diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 1324068dd950..ba460b6c0374 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -683,8 +683,7 @@ int sas_phy_reset(struct sas_phy *phy, int hard_reset); int sas_phy_enable(struct sas_phy *phy, int enable); extern int sas_queuecommand(struct Scsi_Host *, struct scsi_cmnd *); extern int sas_target_alloc(struct scsi_target *); -int sas_device_configure(struct scsi_device *dev, - struct queue_limits *lim); +int sas_sdev_configure(struct scsi_device *dev, struct queue_limits *lim); extern int sas_change_queue_depth(struct scsi_device *, int new_depth); extern int sas_bios_param(struct scsi_device *, struct block_device *, sector_t capacity, int *hsc); @@ -703,7 +702,7 @@ int sas_eh_device_reset_handler(struct scsi_cmnd *cmd); int sas_eh_target_reset_handler(struct scsi_cmnd *cmd); extern void sas_target_destroy(struct scsi_target *); -extern int sas_slave_alloc(struct scsi_device *); +extern int sas_sdev_init(struct scsi_device *); extern int sas_ioctl(struct scsi_device *sdev, unsigned int cmd, void __user *arg); extern int sas_drain_work(struct sas_ha_struct *ha); @@ -750,8 +749,8 @@ void sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, #endif #define LIBSAS_SHT_BASE _LIBSAS_SHT_BASE \ - .device_configure = sas_device_configure, \ - .slave_alloc = sas_slave_alloc, \ + .sdev_configure = sas_sdev_configure, \ + .sdev_init = sas_sdev_init, \ #define LIBSAS_SHT_BASE_NO_SLAVE_INIT _LIBSAS_SHT_BASE diff --git a/include/scsi/scsi_bsg_iscsi.h b/include/scsi/scsi_bsg_iscsi.h index 9b1f0f424a79..a569c35b258d 100644 --- a/include/scsi/scsi_bsg_iscsi.h +++ b/include/scsi/scsi_bsg_iscsi.h @@ -59,7 +59,7 @@ struct iscsi_bsg_host_vendor { */ struct iscsi_bsg_host_vendor_reply { /* start of vendor response area */ - uint32_t vendor_rsp[0]; + DECLARE_FLEX_ARRAY(uint32_t, vendor_rsp); }; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 9c540f5468eb..7acd0ec82bb0 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -155,7 +155,7 @@ struct scsi_device { blist_flags_t sdev_bflags; /* black/white flags as also found in * scsi_devinfo.[hc]. For now used only to - * pass settings from slave_alloc to scsi + * pass settings from sdev_init to scsi * core. */ unsigned int eh_timeout; /* Error handling timeout */ @@ -357,7 +357,7 @@ struct scsi_target { atomic_t target_blocked; /* - * LLDs should set this in the slave_alloc host template callout. + * LLDs should set this in the sdev_init host template callout. * If set to zero then there is not limit. */ unsigned int can_queue; diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 2b4ab0369ffb..26bc23419cfd 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -168,20 +168,20 @@ struct scsi_host_template { * Return values: 0 on success, non-0 on failure * * Deallocation: If we didn't find any devices at this ID, you will - * get an immediate call to slave_destroy(). If we find something - * here then you will get a call to slave_configure(), then the + * get an immediate call to sdev_destroy(). If we find something + * here then you will get a call to sdev_configure(), then the * device will be used for however long it is kept around, then when * the device is removed from the system (or * possibly at reboot - * time), you will then get a call to slave_destroy(). This is - * assuming you implement slave_configure and slave_destroy. + * time), you will then get a call to sdev_destroy(). This is + * assuming you implement sdev_configure and sdev_destroy. * However, if you allocate memory and hang it off the device struct, - * then you must implement the slave_destroy() routine at a minimum + * then you must implement the sdev_destroy() routine at a minimum * in order to avoid leaking memory * each time a device is tore down. * * Status: OPTIONAL */ - int (* slave_alloc)(struct scsi_device *); + int (* sdev_init)(struct scsi_device *); /* * Once the device has responded to an INQUIRY and we know the @@ -206,28 +206,24 @@ struct scsi_host_template { * specific setup basis... * 6. Return 0 on success, non-0 on error. The device will be marked * as offline on error so that no access will occur. If you return - * non-0, your slave_destroy routine will never get called for this + * non-0, your sdev_destroy routine will never get called for this * device, so don't leave any loose memory hanging around, clean * up after yourself before returning non-0 * * Status: OPTIONAL - * - * Note: slave_configure is the legacy version, use device_configure for - * all new code. A driver must never define both. */ - int (* device_configure)(struct scsi_device *, struct queue_limits *lim); - int (* slave_configure)(struct scsi_device *); + int (* sdev_configure)(struct scsi_device *, struct queue_limits *lim); /* * Immediately prior to deallocating the device and after all activity * has ceased the mid layer calls this point so that the low level * driver may completely detach itself from the scsi device and vice * versa. The low level driver is responsible for freeing any memory - * it allocated in the slave_alloc or slave_configure calls. + * it allocated in the sdev_init or sdev_configure calls. * * Status: OPTIONAL */ - void (* slave_destroy)(struct scsi_device *); + void (* sdev_destroy)(struct scsi_device *); /* * Before the mid layer attempts to scan for a new device attached @@ -438,8 +434,10 @@ struct scsi_host_template { */ short cmd_per_lun; - /* If use block layer to manage tags, this is tag allocation policy */ - int tag_alloc_policy; + /* + * Allocate tags starting from last allocated tag. + */ + bool tag_alloc_policy_rr : 1; /* * Track QUEUE_FULL events and reduce queue depth on demand. @@ -599,7 +597,7 @@ struct Scsi_Host { * have some way of identifying each detected host adapter properly * and uniquely. For hosts that do not support more than one card * in the system at one time, this does not need to be set. It is - * initialized to 0 in scsi_register. + * initialized to 0 in scsi_host_alloc. */ unsigned int unique_id; diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index bd1243657c01..76de2b662f4f 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -447,10 +447,6 @@ extern int iscsi_add_session(struct iscsi_cls_session *session, unsigned int target_id); extern int iscsi_session_event(struct iscsi_cls_session *session, enum iscsi_uevent_e event); -extern struct iscsi_cls_session *iscsi_create_session(struct Scsi_Host *shost, - struct iscsi_transport *t, - int dd_size, - unsigned int target_id); extern void iscsi_force_destroy_session(struct iscsi_cls_session *session); extern void iscsi_remove_session(struct iscsi_cls_session *session); extern void iscsi_free_session(struct iscsi_cls_session *session); @@ -497,8 +493,8 @@ extern void iscsi_destroy_all_flashnode(struct Scsi_Host *shost); extern int iscsi_flashnode_bus_match(struct device *dev, const struct device_driver *drv); extern struct device * -iscsi_find_flashnode_sess(struct Scsi_Host *shost, void *data, - int (*fn)(struct device *dev, void *data)); +iscsi_find_flashnode_sess(struct Scsi_Host *shost, const void *data, + device_match_t fn); extern struct device * iscsi_find_flashnode_conn(struct iscsi_bus_flash_session *fnode_sess); diff --git a/include/soc/amlogic/reset-meson-aux.h b/include/soc/amlogic/reset-meson-aux.h deleted file mode 100644 index d8a15d48c984..000000000000 --- a/include/soc/amlogic/reset-meson-aux.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __SOC_RESET_MESON_AUX_H -#define __SOC_RESET_MESON_AUX_H - -#include - -struct device; -struct regmap; - -#if IS_ENABLED(CONFIG_RESET_MESON_AUX) -int devm_meson_rst_aux_register(struct device *dev, - struct regmap *map, - const char *adev_name); -#else -static inline int devm_meson_rst_aux_register(struct device *dev, - struct regmap *map, - const char *adev_name) -{ - return 0; -} -#endif - -#endif /* __SOC_RESET_MESON_AUX_H */ diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h index 73cac8d0287e..e1f87fbfe554 100644 --- a/include/soc/bcm2835/raspberrypi-firmware.h +++ b/include/soc/bcm2835/raspberrypi-firmware.h @@ -152,6 +152,7 @@ enum rpi_firmware_clk_id { RPI_FIRMWARE_M2MC_CLK_ID, RPI_FIRMWARE_PIXEL_BVB_CLK_ID, RPI_FIRMWARE_VEC_CLK_ID, + RPI_FIRMWARE_DISP_CLK_ID, RPI_FIRMWARE_NUM_CLK_ID, }; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 2db9ae0575b6..6db7fc9dbaa4 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -759,6 +759,14 @@ struct ocelot_mm_state { u8 active_preemptible_tcs; }; +struct ocelot_ts_stats { + u64 pkts; + u64 onestep_pkts_unconfirmed; + u64 lost; + u64 err; + struct u64_stats_sync syncp; +}; + struct ocelot_port; struct ocelot_port { @@ -778,6 +786,7 @@ struct ocelot_port { phy_interface_t phy_mode; + struct ocelot_ts_stats *ts_stats; struct sk_buff_head tx_skbs; unsigned int trap_proto; @@ -1023,6 +1032,8 @@ void ocelot_port_get_eth_mac_stats(struct ocelot *ocelot, int port, struct ethtool_eth_mac_stats *mac_stats); void ocelot_port_get_eth_phy_stats(struct ocelot *ocelot, int port, struct ethtool_eth_phy_stats *phy_stats); +void ocelot_port_get_ts_stats(struct ocelot *ocelot, int port, + struct ethtool_ts_stats *ts_stats); int ocelot_get_ts_info(struct ocelot *ocelot, int port, struct kernel_ethtool_ts_info *info); void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs); diff --git a/include/soc/qcom/tcs.h b/include/soc/qcom/tcs.h index 3acca067c72b..cff67ce25488 100644 --- a/include/soc/qcom/tcs.h +++ b/include/soc/qcom/tcs.h @@ -6,6 +6,9 @@ #ifndef __SOC_QCOM_TCS_H__ #define __SOC_QCOM_TCS_H__ +#include +#include + #define MAX_RPMH_PAYLOAD 16 /** @@ -60,22 +63,17 @@ struct tcs_request { struct tcs_cmd *cmds; }; -#define BCM_TCS_CMD_COMMIT_SHFT 30 -#define BCM_TCS_CMD_COMMIT_MASK 0x40000000 -#define BCM_TCS_CMD_VALID_SHFT 29 -#define BCM_TCS_CMD_VALID_MASK 0x20000000 -#define BCM_TCS_CMD_VOTE_X_SHFT 14 -#define BCM_TCS_CMD_VOTE_MASK 0x3fff -#define BCM_TCS_CMD_VOTE_Y_SHFT 0 -#define BCM_TCS_CMD_VOTE_Y_MASK 0xfffc000 +#define BCM_TCS_CMD_COMMIT_MASK BIT(30) +#define BCM_TCS_CMD_VALID_MASK BIT(29) +#define BCM_TCS_CMD_VOTE_MASK GENMASK(13, 0) +#define BCM_TCS_CMD_VOTE_Y_MASK GENMASK(13, 0) +#define BCM_TCS_CMD_VOTE_X_MASK GENMASK(27, 14) /* Construct a Bus Clock Manager (BCM) specific TCS command */ #define BCM_TCS_CMD(commit, valid, vote_x, vote_y) \ - (((commit) << BCM_TCS_CMD_COMMIT_SHFT) | \ - ((valid) << BCM_TCS_CMD_VALID_SHFT) | \ - ((cpu_to_le32(vote_x) & \ - BCM_TCS_CMD_VOTE_MASK) << BCM_TCS_CMD_VOTE_X_SHFT) | \ - ((cpu_to_le32(vote_y) & \ - BCM_TCS_CMD_VOTE_MASK) << BCM_TCS_CMD_VOTE_Y_SHFT)) + (u32_encode_bits(commit, BCM_TCS_CMD_COMMIT_MASK) | \ + u32_encode_bits(valid, BCM_TCS_CMD_VALID_MASK) | \ + u32_encode_bits(vote_x, BCM_TCS_CMD_VOTE_X_MASK) | \ + u32_encode_bits(vote_y, BCM_TCS_CMD_VOTE_Y_MASK)) #endif /* __SOC_QCOM_TCS_H__ */ diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index 957295364a5e..4c7a40e149a5 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -2,8 +2,6 @@ #ifndef __SOUND_HDAUDIO_EXT_H #define __SOUND_HDAUDIO_EXT_H -#include -#include #include int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, @@ -119,49 +117,6 @@ int snd_hdac_ext_bus_link_put(struct hdac_bus *bus, struct hdac_ext_link *hlink) void snd_hdac_ext_bus_link_power(struct hdac_device *codec, bool enable); -#define snd_hdac_adsp_writeb(chip, reg, value) \ - snd_hdac_reg_writeb(chip, (chip)->dsp_ba + (reg), value) -#define snd_hdac_adsp_readb(chip, reg) \ - snd_hdac_reg_readb(chip, (chip)->dsp_ba + (reg)) -#define snd_hdac_adsp_writew(chip, reg, value) \ - snd_hdac_reg_writew(chip, (chip)->dsp_ba + (reg), value) -#define snd_hdac_adsp_readw(chip, reg) \ - snd_hdac_reg_readw(chip, (chip)->dsp_ba + (reg)) -#define snd_hdac_adsp_writel(chip, reg, value) \ - snd_hdac_reg_writel(chip, (chip)->dsp_ba + (reg), value) -#define snd_hdac_adsp_readl(chip, reg) \ - snd_hdac_reg_readl(chip, (chip)->dsp_ba + (reg)) -#define snd_hdac_adsp_writeq(chip, reg, value) \ - snd_hdac_reg_writeq(chip, (chip)->dsp_ba + (reg), value) -#define snd_hdac_adsp_readq(chip, reg) \ - snd_hdac_reg_readq(chip, (chip)->dsp_ba + (reg)) - -#define snd_hdac_adsp_updateb(chip, reg, mask, val) \ - snd_hdac_adsp_writeb(chip, reg, \ - (snd_hdac_adsp_readb(chip, reg) & ~(mask)) | (val)) -#define snd_hdac_adsp_updatew(chip, reg, mask, val) \ - snd_hdac_adsp_writew(chip, reg, \ - (snd_hdac_adsp_readw(chip, reg) & ~(mask)) | (val)) -#define snd_hdac_adsp_updatel(chip, reg, mask, val) \ - snd_hdac_adsp_writel(chip, reg, \ - (snd_hdac_adsp_readl(chip, reg) & ~(mask)) | (val)) -#define snd_hdac_adsp_updateq(chip, reg, mask, val) \ - snd_hdac_adsp_writeq(chip, reg, \ - (snd_hdac_adsp_readq(chip, reg) & ~(mask)) | (val)) - -#define snd_hdac_adsp_readb_poll(chip, reg, val, cond, delay_us, timeout_us) \ - readb_poll_timeout((chip)->dsp_ba + (reg), val, cond, \ - delay_us, timeout_us) -#define snd_hdac_adsp_readw_poll(chip, reg, val, cond, delay_us, timeout_us) \ - readw_poll_timeout((chip)->dsp_ba + (reg), val, cond, \ - delay_us, timeout_us) -#define snd_hdac_adsp_readl_poll(chip, reg, val, cond, delay_us, timeout_us) \ - readl_poll_timeout((chip)->dsp_ba + (reg), val, cond, \ - delay_us, timeout_us) -#define snd_hdac_adsp_readq_poll(chip, reg, val, cond, delay_us, timeout_us) \ - readq_poll_timeout((chip)->dsp_ba + (reg), val, cond, \ - delay_us, timeout_us) - struct hdac_ext_device; /* ops common to all codec drivers */ diff --git a/include/sound/hdmi-codec.h b/include/sound/hdmi-codec.h index 5e1a9eafd10f..b220072cfa1b 100644 --- a/include/sound/hdmi-codec.h +++ b/include/sound/hdmi-codec.h @@ -105,7 +105,8 @@ struct hdmi_codec_ops { * Optional */ int (*get_dai_id)(struct snd_soc_component *comment, - struct device_node *endpoint); + struct device_node *endpoint, + void *data); /* * Hook callback function to handle connector plug event. @@ -114,9 +115,6 @@ struct hdmi_codec_ops { int (*hook_plugged_cb)(struct device *dev, void *data, hdmi_codec_plugged_cb fn, struct device *codec_dev); - - /* bit field */ - unsigned int no_capture_mute:1; }; /* HDMI codec initalization data */ @@ -128,6 +126,7 @@ struct hdmi_codec_pdata { uint spdif:1; uint no_spdif_playback:1; uint no_spdif_capture:1; + uint no_capture_mute:1; int max_i2s_channels; void *data; }; diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 67c99ffbf51b..8becb4504887 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1532,9 +1532,10 @@ static inline u64 pcm_format_to_bits(snd_pcm_format_t pcm_format) dev_dbg((pcm)->card->dev, fmt, ##args) /* helpers for copying between iov_iter and iomem */ -int copy_to_iter_fromio(struct iov_iter *itert, const void __iomem *src, - size_t count); -int copy_from_iter_toio(void __iomem *dst, struct iov_iter *iter, size_t count); +size_t copy_to_iter_fromio(const void __iomem *src, size_t bytes, + struct iov_iter *iter) __must_check; +size_t copy_from_iter_toio(void __iomem *dst, size_t bytes, + struct iov_iter *iter) __must_check; struct snd_pcm_status64 { snd_pcm_state_t state; /* stream state */ diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index f31cabf0158c..6916f7133597 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -89,6 +89,7 @@ struct snd_rawmidi_substream { unsigned int framing; /* whether to frame input data */ unsigned int clock_type; /* clock source to use for input framing */ int use_count; /* use counter (for output) */ + bool inactive; /* inactive substream (for UMP legacy) */ size_t bytes; spinlock_t lock; struct snd_rawmidi *rmidi; @@ -118,6 +119,7 @@ struct snd_rawmidi { struct list_head list; unsigned int device; /* device number */ unsigned int info_flags; /* SNDRV_RAWMIDI_INFO_XXXX */ + unsigned int tied_device; char id[64]; char name[80]; @@ -189,4 +191,13 @@ long snd_rawmidi_kernel_read(struct snd_rawmidi_substream *substream, long snd_rawmidi_kernel_write(struct snd_rawmidi_substream *substream, const unsigned char *buf, long count); +/* set up the tied devices */ +static inline void snd_rawmidi_tie_devices(struct snd_rawmidi *r1, + struct snd_rawmidi *r2) +{ + /* tied_device field keeps the device+1 (so that 0 being unknown) */ + r1->tied_device = r2->device + 1; + r2->tied_device = r1->device + 1; +} + #endif /* __SOUND_RAWMIDI_H */ diff --git a/include/sound/sdca.h b/include/sound/sdca.h index 7e138229e8f3..973252d0adac 100644 --- a/include/sound/sdca.h +++ b/include/sound/sdca.h @@ -9,6 +9,9 @@ #ifndef __SDCA_H__ #define __SDCA_H__ +#include +#include + struct sdw_slave; #define SDCA_MAX_FUNCTION_COUNT 8 @@ -20,9 +23,9 @@ struct sdw_slave; * @name: human-readable string */ struct sdca_function_desc { - u64 adr; - u32 type; const char *name; + u32 type; + u8 adr; }; /** diff --git a/include/sound/sdca_function.h b/include/sound/sdca_function.h index a01eec86b9a6..c051c17903e8 100644 --- a/include/sound/sdca_function.h +++ b/include/sound/sdca_function.h @@ -9,6 +9,8 @@ #ifndef __SDCA_FUNCTION_H__ #define __SDCA_FUNCTION_H__ +#include + /* * SDCA Function Types from SDCA specification v1.0a Section 5.1.2 * all Function types not described are reserved @@ -40,16 +42,34 @@ enum sdca_function_type { #define SDCA_FUNCTION_TYPE_RJ_NAME "RJ" #define SDCA_FUNCTION_TYPE_SIMPLE_NAME "SimpleJack" #define SDCA_FUNCTION_TYPE_HID_NAME "HID" +#define SDCA_FUNCTION_TYPE_IMP_DEF_NAME "ImplementationDefined" enum sdca_entity0_controls { - SDCA_CONTROL_ENTITY_0_COMMIT_GROUP_MASK = 0x01, - SDCA_CONTROL_ENTITY_0_INTSTAT_CLEAR = 0x02, - SDCA_CONTROL_ENTITY_0_INT_ENABLE = 0x03, - SDCA_CONTROL_ENTITY_0_FUNCTION_SDCA_VERSION = 0x04, - SDCA_CONTROL_ENTITY_0_FUNCTION_TOPOLOGY = 0x05, - SDCA_CONTROL_ENTITY_0_FUNCTION_MANUFACTURER_ID = 0x06, - SDCA_CONTROL_ENTITY_0_FUNCTION_ID = 0x07, - SDCA_CONTROL_ENTITY_0_FUNCTION_VERSION = 0x08 + SDCA_CTL_ENTITY_0_COMMIT_GROUP_MASK = 0x01, + SDCA_CTL_ENTITY_0_FUNCTION_SDCA_VERSION = 0x04, + SDCA_CTL_ENTITY_0_FUNCTION_TYPE = 0x05, + SDCA_CTL_ENTITY_0_FUNCTION_MANUFACTURER_ID = 0x06, + SDCA_CTL_ENTITY_0_FUNCTION_ID = 0x07, + SDCA_CTL_ENTITY_0_FUNCTION_VERSION = 0x08, + SDCA_CTL_ENTITY_0_FUNCTION_EXTENSION_ID = 0x09, + SDCA_CTL_ENTITY_0_FUNCTION_EXTENSION_VERSION = 0x0A, + SDCA_CTL_ENTITY_0_FUNCTION_STATUS = 0x10, + SDCA_CTL_ENTITY_0_FUNCTION_ACTION = 0x11, + SDCA_CTL_ENTITY_0_MATCHING_GUID = 0x12, + SDCA_CTL_ENTITY_0_DEVICE_MANUFACTURER_ID = 0x2C, + SDCA_CTL_ENTITY_0_DEVICE_PART_ID = 0x2D, + SDCA_CTL_ENTITY_0_DEVICE_VERSION = 0x2E, + SDCA_CTL_ENTITY_0_DEVICE_SDCA_VERSION = 0x2F, + + /* Function Status Bits */ + SDCA_CTL_ENTITY_0_DEVICE_NEWLY_ATTACHED = BIT(0), + SDCA_CTL_ENTITY_0_INTS_DISABLED_ABNORMALLY = BIT(1), + SDCA_CTL_ENTITY_0_STREAMING_STOPPED_ABNORMALLY = BIT(2), + SDCA_CTL_ENTITY_0_FUNCTION_FAULT = BIT(3), + SDCA_CTL_ENTITY_0_UMP_SEQUENCE_FAULT = BIT(4), + SDCA_CTL_ENTITY_0_FUNCTION_NEEDS_INITIALIZATION = BIT(5), + SDCA_CTL_ENTITY_0_FUNCTION_HAS_BEEN_RESET = BIT(6), + SDCA_CTL_ENTITY_0_FUNCTION_BUSY = BIT(7), }; #endif diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index 3360d9eab068..892f70532363 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -89,6 +89,13 @@ struct simple_util_priv { #define simple_props_to_dai_codec(props, i) ((props)->codec_dai + i) #define simple_props_to_codec_conf(props, i) ((props)->codec_conf + i) +/* has the same effect as simple_priv_to_props(). Preferred over + * simple_priv_to_props() when dealing with PCM runtime data as + * the ID stored in rtd->id may not be a valid array index. + */ +#define runtime_simple_priv_to_props(priv, rtd) \ + ((priv)->dai_props + ((rtd)->dai_link - (priv)->dai_link)) + #define for_each_prop_dlc_cpus(props, i, cpu) \ for ((i) = 0; \ ((i) < (props)->num.cpus) && \ @@ -264,9 +271,13 @@ static inline void simple_util_debug_info(struct simple_util_priv *priv) simple_util_debug_dai(priv, "codec", dai); if (link->name) - dev_dbg(dev, "dai name = %s\n", link->name); + dev_dbg(dev, "link name = %s\n", link->name); if (link->dai_fmt) - dev_dbg(dev, "dai format = %04x\n", link->dai_fmt); + dev_dbg(dev, "link format = %04x\n", link->dai_fmt); + if (link->playback_only) + dev_dbg(dev, "link has playback_only"); + if (link->capture_only) + dev_dbg(dev, "link has capture_only"); if (props->adata.convert_rate) dev_dbg(dev, "convert_rate = %d\n", props->adata.convert_rate); if (props->adata.convert_channels) diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index aab57c19f62b..a11501752637 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -193,6 +193,9 @@ int snd_soc_dai_set_channel_map(struct snd_soc_dai *dai, int snd_soc_dai_set_tristate(struct snd_soc_dai *dai, int tristate); +int snd_soc_dai_prepare(struct snd_soc_dai *dai, + struct snd_pcm_substream *substream); + /* Digital Audio Interface mute */ int snd_soc_dai_digital_mute(struct snd_soc_dai *dai, int mute, int direction); diff --git a/include/sound/soc.h b/include/sound/soc.h index 4f5d411e3823..fcdb5adfcd5e 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -681,6 +681,17 @@ struct snd_soc_dai_link_component { struct device_node *of_node; const char *dai_name; const struct of_phandle_args *dai_args; + + /* + * Extra format = SND_SOC_DAIFMT_Bx_Fx + * + * [Note] it is Bx_Fx base, not CBx_CFx + * + * It will be used with dai_link->dai_fmt + * see + * snd_soc_runtime_set_dai_fmt() + */ + unsigned int ext_fmt; }; /* @@ -1118,7 +1129,6 @@ struct snd_soc_card { unsigned int instantiated:1; unsigned int topology_shortname_created:1; unsigned int fully_routed:1; - unsigned int disable_route_checks:1; unsigned int probed:1; unsigned int component_chaining:1; diff --git a/include/sound/soc_sdw_utils.h b/include/sound/soc_sdw_utils.h index 0e82598e10af..36a4a1e1d8ca 100644 --- a/include/sound/soc_sdw_utils.h +++ b/include/sound/soc_sdw_utils.h @@ -224,6 +224,8 @@ int asoc_sdw_cs_amp_init(struct snd_soc_card *card, struct snd_soc_dai_link *dai_links, struct asoc_sdw_codec_info *info, bool playback); +int asoc_sdw_cs_spk_feedback_rtd_init(struct snd_soc_pcm_runtime *rtd, + struct snd_soc_dai *dai); /* MAXIM codec support */ int asoc_sdw_maxim_init(struct snd_soc_card *card, diff --git a/include/sound/ump.h b/include/sound/ump.h index 532c2c3ea28e..73f97f88e2ed 100644 --- a/include/sound/ump.h +++ b/include/sound/ump.h @@ -83,6 +83,7 @@ struct snd_ump_ops { struct snd_seq_ump_ops { void (*input_receive)(struct snd_ump_endpoint *ump, const u32 *data, int words); + int (*notify_ep_change)(struct snd_ump_endpoint *ump); int (*notify_fb_change)(struct snd_ump_endpoint *ump, struct snd_ump_block *fb); int (*switch_protocol)(struct snd_ump_endpoint *ump); diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 60af7c63b34e..51ca80abacf7 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -576,9 +576,6 @@ struct iscsit_conn { spinlock_t state_lock; spinlock_t login_timer_lock; spinlock_t login_worker_lock; - /* libcrypto RX and TX contexts for crc32c */ - struct ahash_request *conn_rx_hash; - struct ahash_request *conn_tx_hash; /* Used for scheduling TX and RX connection kthreads */ cpumask_var_t conn_cpumask; cpumask_var_t allowed_cpumask; diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index a0aed1a428a1..b0db89058c91 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -118,6 +118,8 @@ enum yfs_cm_operation { */ #define afs_call_traces \ EM(afs_call_trace_alloc, "ALLOC") \ + EM(afs_call_trace_async_abort, "ASYAB") \ + EM(afs_call_trace_async_kill, "ASYKL") \ EM(afs_call_trace_free, "FREE ") \ EM(afs_call_trace_get, "GET ") \ EM(afs_call_trace_put, "PUT ") \ @@ -168,12 +170,14 @@ enum yfs_cm_operation { #define afs_cell_traces \ EM(afs_cell_trace_alloc, "ALLOC ") \ EM(afs_cell_trace_free, "FREE ") \ + EM(afs_cell_trace_get_atcell, "GET atcell") \ EM(afs_cell_trace_get_queue_dns, "GET q-dns ") \ EM(afs_cell_trace_get_queue_manage, "GET q-mng ") \ EM(afs_cell_trace_get_queue_new, "GET q-new ") \ EM(afs_cell_trace_get_vol, "GET vol ") \ EM(afs_cell_trace_insert, "INSERT ") \ EM(afs_cell_trace_manage, "MANAGE ") \ + EM(afs_cell_trace_put_atcell, "PUT atcell") \ EM(afs_cell_trace_put_candidate, "PUT candid") \ EM(afs_cell_trace_put_destroy, "PUT destry") \ EM(afs_cell_trace_put_queue_work, "PUT q-work") \ @@ -323,6 +327,44 @@ enum yfs_cm_operation { EM(yfs_CB_TellMeAboutYourself, "YFSCB.TellMeAboutYourself") \ E_(yfs_CB_CallBack, "YFSCB.CallBack") +#define afs_cb_promise_traces \ + EM(afs_cb_promise_clear_cb_break, "CLEAR cb-break") \ + EM(afs_cb_promise_clear_rmdir, "CLEAR rmdir") \ + EM(afs_cb_promise_clear_rotate_server, "CLEAR rot-srv") \ + EM(afs_cb_promise_clear_server_change, "CLEAR srv-chg") \ + EM(afs_cb_promise_clear_vol_init_cb, "CLEAR vol-init-cb") \ + EM(afs_cb_promise_set_apply_cb, "SET apply-cb") \ + EM(afs_cb_promise_set_new_inode, "SET new-inode") \ + E_(afs_cb_promise_set_new_symlink, "SET new-symlink") + +#define afs_vnode_invalid_traces \ + EM(afs_vnode_invalid_trace_cb_ro_snapshot, "cb-ro-snapshot") \ + EM(afs_vnode_invalid_trace_cb_scrub, "cb-scrub") \ + EM(afs_vnode_invalid_trace_cb_v_break, "cb-v-break") \ + EM(afs_vnode_invalid_trace_expired, "expired") \ + EM(afs_vnode_invalid_trace_no_cb_promise, "no-cb-promise") \ + EM(afs_vnode_invalid_trace_vol_expired, "vol-expired") \ + EM(afs_vnode_invalid_trace_zap_data, "zap-data") \ + E_(afs_vnode_valid_trace, "valid") + +#define afs_dir_invalid_traces \ + EM(afs_dir_invalid_edit_add_bad_size, "edit-add-bad-size") \ + EM(afs_dir_invalid_edit_add_no_slots, "edit-add-no-slots") \ + EM(afs_dir_invalid_edit_add_too_many_blocks, "edit-add-too-many-blocks") \ + EM(afs_dir_invalid_edit_get_block, "edit-get-block") \ + EM(afs_dir_invalid_edit_mkdir, "edit-mkdir") \ + EM(afs_dir_invalid_edit_rem_bad_size, "edit-rem-bad-size") \ + EM(afs_dir_invalid_edit_rem_wrong_name, "edit-rem-wrong_name") \ + EM(afs_dir_invalid_edit_upd_bad_size, "edit-upd-bad-size") \ + EM(afs_dir_invalid_edit_upd_no_dd, "edit-upd-no-dotdot") \ + EM(afs_dir_invalid_dv_mismatch, "dv-mismatch") \ + EM(afs_dir_invalid_inval_folio, "inv-folio") \ + EM(afs_dir_invalid_iter_stale, "iter-stale") \ + EM(afs_dir_invalid_reclaimed_folio, "reclaimed-folio") \ + EM(afs_dir_invalid_release_folio, "rel-folio") \ + EM(afs_dir_invalid_remote, "remote") \ + E_(afs_dir_invalid_subdir_removed, "subdir-removed") + #define afs_edit_dir_ops \ EM(afs_edit_dir_create, "create") \ EM(afs_edit_dir_create_error, "c_fail") \ @@ -332,6 +374,7 @@ enum yfs_cm_operation { EM(afs_edit_dir_delete_error, "d_err ") \ EM(afs_edit_dir_delete_inval, "d_invl") \ EM(afs_edit_dir_delete_noent, "d_nent") \ + EM(afs_edit_dir_mkdir, "mk_ent") \ EM(afs_edit_dir_update_dd, "u_ddot") \ EM(afs_edit_dir_update_error, "u_fail") \ EM(afs_edit_dir_update_inval, "u_invl") \ @@ -385,6 +428,7 @@ enum yfs_cm_operation { EM(afs_file_error_dir_over_end, "DIR_ENT_OVER_END") \ EM(afs_file_error_dir_small, "DIR_SMALL") \ EM(afs_file_error_dir_unmarked_ext, "DIR_UNMARKED_EXT") \ + EM(afs_file_error_symlink_big, "SYM_BIG") \ EM(afs_file_error_mntpt, "MNTPT_READ_FAILED") \ E_(afs_file_error_writeback_fail, "WRITEBACK_FAILED") @@ -487,7 +531,9 @@ enum yfs_cm_operation { enum afs_alist_trace { afs_alist_traces } __mode(byte); enum afs_call_trace { afs_call_traces } __mode(byte); enum afs_cb_break_reason { afs_cb_break_reasons } __mode(byte); +enum afs_cb_promise_trace { afs_cb_promise_traces } __mode(byte); enum afs_cell_trace { afs_cell_traces } __mode(byte); +enum afs_dir_invalid_trace { afs_dir_invalid_traces} __mode(byte); enum afs_edit_dir_op { afs_edit_dir_ops } __mode(byte); enum afs_edit_dir_reason { afs_edit_dir_reasons } __mode(byte); enum afs_eproto_cause { afs_eproto_causes } __mode(byte); @@ -498,6 +544,7 @@ enum afs_flock_operation { afs_flock_operations } __mode(byte); enum afs_io_error { afs_io_errors } __mode(byte); enum afs_rotate_trace { afs_rotate_traces } __mode(byte); enum afs_server_trace { afs_server_traces } __mode(byte); +enum afs_vnode_invalid_trace { afs_vnode_invalid_traces} __mode(byte); enum afs_volume_trace { afs_volume_traces } __mode(byte); #endif /* end __AFS_GENERATE_TRACE_ENUMS_ONCE_ONLY */ @@ -513,8 +560,10 @@ enum afs_volume_trace { afs_volume_traces } __mode(byte); afs_alist_traces; afs_call_traces; afs_cb_break_reasons; +afs_cb_promise_traces; afs_cell_traces; afs_cm_operations; +afs_dir_invalid_traces; afs_edit_dir_ops; afs_edit_dir_reasons; afs_eproto_causes; @@ -526,6 +575,7 @@ afs_fs_operations; afs_io_errors; afs_rotate_traces; afs_server_traces; +afs_vnode_invalid_traces; afs_vl_operations; yfs_cm_operations; @@ -670,7 +720,7 @@ TRACE_EVENT(afs_make_fs_call, } ), - TP_printk("c=%08x %06llx:%06llx:%06x %s", + TP_printk("c=%08x V=%llx i=%llx:%x %s", __entry->call, __entry->fid.vid, __entry->fid.vnode, @@ -704,7 +754,7 @@ TRACE_EVENT(afs_make_fs_calli, } ), - TP_printk("c=%08x %06llx:%06llx:%06x %s i=%u", + TP_printk("c=%08x V=%llx i=%llx:%x %s i=%u", __entry->call, __entry->fid.vid, __entry->fid.vnode, @@ -741,7 +791,7 @@ TRACE_EVENT(afs_make_fs_call1, __entry->name[__len] = 0; ), - TP_printk("c=%08x %06llx:%06llx:%06x %s \"%s\"", + TP_printk("c=%08x V=%llx i=%llx:%x %s \"%s\"", __entry->call, __entry->fid.vid, __entry->fid.vnode, @@ -782,7 +832,7 @@ TRACE_EVENT(afs_make_fs_call2, __entry->name2[__len2] = 0; ), - TP_printk("c=%08x %06llx:%06llx:%06x %s \"%s\" \"%s\"", + TP_printk("c=%08x V=%llx i=%llx:%x %s \"%s\" \"%s\"", __entry->call, __entry->fid.vid, __entry->fid.vnode, @@ -887,9 +937,9 @@ TRACE_EVENT(afs_sent_data, ); TRACE_EVENT(afs_dir_check_failed, - TP_PROTO(struct afs_vnode *vnode, loff_t off, loff_t i_size), + TP_PROTO(struct afs_vnode *vnode, loff_t off), - TP_ARGS(vnode, off, i_size), + TP_ARGS(vnode, off), TP_STRUCT__entry( __field(struct afs_vnode *, vnode) @@ -900,7 +950,7 @@ TRACE_EVENT(afs_dir_check_failed, TP_fast_assign( __entry->vnode = vnode; __entry->off = off; - __entry->i_size = i_size; + __entry->i_size = i_size_read(&vnode->netfs.inode); ), TP_printk("vn=%p %llx/%llx", @@ -1002,7 +1052,7 @@ TRACE_EVENT(afs_edit_dir, __entry->name[__len] = 0; ), - TP_printk("d=%x:%x %s %s %u[%u] f=%x:%x \"%s\"", + TP_printk("di=%x:%x %s %s %u[%u] fi=%x:%x \"%s\"", __entry->vnode, __entry->unique, __print_symbolic(__entry->why, afs_edit_dir_reasons), __print_symbolic(__entry->op, afs_edit_dir_ops), @@ -1011,6 +1061,122 @@ TRACE_EVENT(afs_edit_dir, __entry->name) ); +TRACE_EVENT(afs_dir_invalid, + TP_PROTO(const struct afs_vnode *dvnode, enum afs_dir_invalid_trace trace), + + TP_ARGS(dvnode, trace), + + TP_STRUCT__entry( + __field(unsigned int, vnode) + __field(unsigned int, unique) + __field(enum afs_dir_invalid_trace, trace) + ), + + TP_fast_assign( + __entry->vnode = dvnode->fid.vnode; + __entry->unique = dvnode->fid.unique; + __entry->trace = trace; + ), + + TP_printk("di=%x:%x %s", + __entry->vnode, __entry->unique, + __print_symbolic(__entry->trace, afs_dir_invalid_traces)) + ); + +TRACE_EVENT(afs_cb_promise, + TP_PROTO(const struct afs_vnode *vnode, enum afs_cb_promise_trace trace), + + TP_ARGS(vnode, trace), + + TP_STRUCT__entry( + __field(unsigned int, vnode) + __field(unsigned int, unique) + __field(enum afs_cb_promise_trace, trace) + ), + + TP_fast_assign( + __entry->vnode = vnode->fid.vnode; + __entry->unique = vnode->fid.unique; + __entry->trace = trace; + ), + + TP_printk("di=%x:%x %s", + __entry->vnode, __entry->unique, + __print_symbolic(__entry->trace, afs_cb_promise_traces)) + ); + +TRACE_EVENT(afs_vnode_invalid, + TP_PROTO(const struct afs_vnode *vnode, enum afs_vnode_invalid_trace trace), + + TP_ARGS(vnode, trace), + + TP_STRUCT__entry( + __field(unsigned int, vnode) + __field(unsigned int, unique) + __field(enum afs_vnode_invalid_trace, trace) + ), + + TP_fast_assign( + __entry->vnode = vnode->fid.vnode; + __entry->unique = vnode->fid.unique; + __entry->trace = trace; + ), + + TP_printk("di=%x:%x %s", + __entry->vnode, __entry->unique, + __print_symbolic(__entry->trace, afs_vnode_invalid_traces)) + ); + +TRACE_EVENT(afs_set_dv, + TP_PROTO(const struct afs_vnode *dvnode, u64 new_dv), + + TP_ARGS(dvnode, new_dv), + + TP_STRUCT__entry( + __field(unsigned int, vnode) + __field(unsigned int, unique) + __field(u64, old_dv) + __field(u64, new_dv) + ), + + TP_fast_assign( + __entry->vnode = dvnode->fid.vnode; + __entry->unique = dvnode->fid.unique; + __entry->old_dv = dvnode->status.data_version; + __entry->new_dv = new_dv; + ), + + TP_printk("di=%x:%x dv=%llx -> dv=%llx", + __entry->vnode, __entry->unique, + __entry->old_dv, __entry->new_dv) + ); + +TRACE_EVENT(afs_dv_mismatch, + TP_PROTO(const struct afs_vnode *dvnode, u64 before_dv, int delta, u64 new_dv), + + TP_ARGS(dvnode, before_dv, delta, new_dv), + + TP_STRUCT__entry( + __field(unsigned int, vnode) + __field(unsigned int, unique) + __field(int, delta) + __field(u64, before_dv) + __field(u64, new_dv) + ), + + TP_fast_assign( + __entry->vnode = dvnode->fid.vnode; + __entry->unique = dvnode->fid.unique; + __entry->delta = delta; + __entry->before_dv = before_dv; + __entry->new_dv = new_dv; + ), + + TP_printk("di=%x:%x xdv=%llx+%d dv=%llx", + __entry->vnode, __entry->unique, + __entry->before_dv, __entry->delta, __entry->new_dv) + ); + TRACE_EVENT(afs_protocol_error, TP_PROTO(struct afs_call *call, enum afs_eproto_cause cause), @@ -1611,6 +1777,36 @@ TRACE_EVENT(afs_make_call, __entry->fid.unique) ); +TRACE_EVENT(afs_read_recv, + TP_PROTO(const struct afs_operation *op, const struct afs_call *call), + + TP_ARGS(op, call), + + TP_STRUCT__entry( + __field(unsigned int, rreq) + __field(unsigned int, sreq) + __field(unsigned int, op) + __field(unsigned int, op_flags) + __field(unsigned int, call) + __field(enum afs_call_state, call_state) + ), + + TP_fast_assign( + __entry->op = op->debug_id; + __entry->sreq = op->fetch.subreq->debug_index; + __entry->rreq = op->fetch.subreq->rreq->debug_id; + __entry->op_flags = op->flags; + __entry->call = call->debug_id; + __entry->call_state = call->state; + ), + + TP_printk("R=%08x[%x] OP=%08x c=%08x cs=%x of=%x", + __entry->rreq, __entry->sreq, + __entry->op, + __entry->call, __entry->call_state, + __entry->op_flags) + ); + #endif /* _TRACE_AFS_H */ /* This part must be outside protection */ diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 4df93ca9b7a8..549ab3b41961 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -100,7 +100,8 @@ struct find_free_extent_ctl; EM( ALLOC_CHUNK, "ALLOC_CHUNK") \ EM( ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE") \ EM( RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS") \ - EMe(COMMIT_TRANS, "COMMIT_TRANS") + EM( COMMIT_TRANS, "COMMIT_TRANS") \ + EMe(RESET_ZONES, "RESET_ZONES") /* * First define the enums in the above macros to be exported to userspace via diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 7d931db02b93..a743b2a35ea7 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -223,10 +223,10 @@ TRACE_EVENT(cachefiles_ref, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, cookie ) - __field(enum cachefiles_obj_ref_trace, why ) - __field(int, usage ) + __field(unsigned int, obj) + __field(unsigned int, cookie) + __field(enum cachefiles_obj_ref_trace, why) + __field(int, usage) ), TP_fast_assign( @@ -249,10 +249,10 @@ TRACE_EVENT(cachefiles_lookup, TP_ARGS(obj, dir, de), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(short, error ) - __field(unsigned long, dino ) - __field(unsigned long, ino ) + __field(unsigned int, obj) + __field(short, error) + __field(unsigned long, dino) + __field(unsigned long, ino) ), TP_fast_assign( @@ -273,8 +273,8 @@ TRACE_EVENT(cachefiles_mkdir, TP_ARGS(dir, subdir), TP_STRUCT__entry( - __field(unsigned int, dir ) - __field(unsigned int, subdir ) + __field(unsigned int, dir) + __field(unsigned int, subdir) ), TP_fast_assign( @@ -293,8 +293,8 @@ TRACE_EVENT(cachefiles_tmpfile, TP_ARGS(obj, backer), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, backer ) + __field(unsigned int, obj) + __field(unsigned int, backer) ), TP_fast_assign( @@ -313,8 +313,8 @@ TRACE_EVENT(cachefiles_link, TP_ARGS(obj, backer), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, backer ) + __field(unsigned int, obj) + __field(unsigned int, backer) ), TP_fast_assign( @@ -336,9 +336,9 @@ TRACE_EVENT(cachefiles_unlink, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, ino ) - __field(enum fscache_why_object_killed, why ) + __field(unsigned int, obj) + __field(unsigned int, ino) + __field(enum fscache_why_object_killed, why) ), TP_fast_assign( @@ -361,9 +361,9 @@ TRACE_EVENT(cachefiles_rename, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, ino ) - __field(enum fscache_why_object_killed, why ) + __field(unsigned int, obj) + __field(unsigned int, ino) + __field(enum fscache_why_object_killed, why) ), TP_fast_assign( @@ -380,17 +380,20 @@ TRACE_EVENT(cachefiles_rename, TRACE_EVENT(cachefiles_coherency, TP_PROTO(struct cachefiles_object *obj, ino_t ino, + u64 disk_aux, enum cachefiles_content content, enum cachefiles_coherency_trace why), - TP_ARGS(obj, ino, content, why), + TP_ARGS(obj, ino, disk_aux, content, why), /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(enum cachefiles_coherency_trace, why ) - __field(enum cachefiles_content, content ) - __field(u64, ino ) + __field(unsigned int, obj) + __field(enum cachefiles_coherency_trace, why) + __field(enum cachefiles_content, content) + __field(u64, ino) + __field(u64, aux) + __field(u64, disk_aux) ), TP_fast_assign( @@ -398,13 +401,17 @@ TRACE_EVENT(cachefiles_coherency, __entry->why = why; __entry->content = content; __entry->ino = ino; + __entry->aux = be64_to_cpup((__be64 *)obj->cookie->inline_aux); + __entry->disk_aux = disk_aux; ), - TP_printk("o=%08x %s B=%llx c=%u", + TP_printk("o=%08x %s B=%llx c=%u aux=%llx dsk=%llx", __entry->obj, __print_symbolic(__entry->why, cachefiles_coherency_traces), __entry->ino, - __entry->content) + __entry->content, + __entry->aux, + __entry->disk_aux) ); TRACE_EVENT(cachefiles_vol_coherency, @@ -416,9 +423,9 @@ TRACE_EVENT(cachefiles_vol_coherency, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(unsigned int, vol ) - __field(enum cachefiles_coherency_trace, why ) - __field(u64, ino ) + __field(unsigned int, vol) + __field(enum cachefiles_coherency_trace, why) + __field(u64, ino) ), TP_fast_assign( @@ -445,14 +452,14 @@ TRACE_EVENT(cachefiles_prep_read, TP_ARGS(obj, start, len, flags, source, why, cache_inode, netfs_inode), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned short, flags ) - __field(enum netfs_io_source, source ) - __field(enum cachefiles_prepare_read_trace, why ) - __field(size_t, len ) - __field(loff_t, start ) - __field(unsigned int, netfs_inode ) - __field(unsigned int, cache_inode ) + __field(unsigned int, obj) + __field(unsigned short, flags) + __field(enum netfs_io_source, source) + __field(enum cachefiles_prepare_read_trace, why) + __field(size_t, len) + __field(loff_t, start) + __field(unsigned int, netfs_inode) + __field(unsigned int, cache_inode) ), TP_fast_assign( @@ -484,10 +491,10 @@ TRACE_EVENT(cachefiles_read, TP_ARGS(obj, backer, start, len), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, backer ) - __field(size_t, len ) - __field(loff_t, start ) + __field(unsigned int, obj) + __field(unsigned int, backer) + __field(size_t, len) + __field(loff_t, start) ), TP_fast_assign( @@ -513,10 +520,10 @@ TRACE_EVENT(cachefiles_write, TP_ARGS(obj, backer, start, len), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, backer ) - __field(size_t, len ) - __field(loff_t, start ) + __field(unsigned int, obj) + __field(unsigned int, backer) + __field(size_t, len) + __field(loff_t, start) ), TP_fast_assign( @@ -540,11 +547,11 @@ TRACE_EVENT(cachefiles_trunc, TP_ARGS(obj, backer, from, to, why), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, backer ) - __field(enum cachefiles_trunc_trace, why ) - __field(loff_t, from ) - __field(loff_t, to ) + __field(unsigned int, obj) + __field(unsigned int, backer) + __field(enum cachefiles_trunc_trace, why) + __field(loff_t, from) + __field(loff_t, to) ), TP_fast_assign( @@ -571,8 +578,8 @@ TRACE_EVENT(cachefiles_mark_active, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(ino_t, inode ) + __field(unsigned int, obj) + __field(ino_t, inode) ), TP_fast_assign( @@ -592,8 +599,8 @@ TRACE_EVENT(cachefiles_mark_failed, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(ino_t, inode ) + __field(unsigned int, obj) + __field(ino_t, inode) ), TP_fast_assign( @@ -613,8 +620,8 @@ TRACE_EVENT(cachefiles_mark_inactive, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(ino_t, inode ) + __field(unsigned int, obj) + __field(ino_t, inode) ), TP_fast_assign( @@ -633,10 +640,10 @@ TRACE_EVENT(cachefiles_vfs_error, TP_ARGS(obj, backer, error, where), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, backer ) - __field(enum cachefiles_error_trace, where ) - __field(short, error ) + __field(unsigned int, obj) + __field(unsigned int, backer) + __field(enum cachefiles_error_trace, where) + __field(short, error) ), TP_fast_assign( @@ -660,10 +667,10 @@ TRACE_EVENT(cachefiles_io_error, TP_ARGS(obj, backer, error, where), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, backer ) - __field(enum cachefiles_error_trace, where ) - __field(short, error ) + __field(unsigned int, obj) + __field(unsigned int, backer) + __field(enum cachefiles_error_trace, where) + __field(short, error) ), TP_fast_assign( @@ -687,11 +694,11 @@ TRACE_EVENT(cachefiles_ondemand_open, TP_ARGS(obj, msg, load), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, msg_id ) - __field(unsigned int, object_id ) - __field(unsigned int, fd ) - __field(unsigned int, flags ) + __field(unsigned int, obj) + __field(unsigned int, msg_id) + __field(unsigned int, object_id) + __field(unsigned int, fd) + __field(unsigned int, flags) ), TP_fast_assign( @@ -717,9 +724,9 @@ TRACE_EVENT(cachefiles_ondemand_copen, TP_ARGS(obj, msg_id, len), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, msg_id ) - __field(long, len ) + __field(unsigned int, obj) + __field(unsigned int, msg_id) + __field(long, len) ), TP_fast_assign( @@ -740,9 +747,9 @@ TRACE_EVENT(cachefiles_ondemand_close, TP_ARGS(obj, msg), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, msg_id ) - __field(unsigned int, object_id ) + __field(unsigned int, obj) + __field(unsigned int, msg_id) + __field(unsigned int, object_id) ), TP_fast_assign( @@ -764,11 +771,11 @@ TRACE_EVENT(cachefiles_ondemand_read, TP_ARGS(obj, msg, load), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, msg_id ) - __field(unsigned int, object_id ) - __field(loff_t, start ) - __field(size_t, len ) + __field(unsigned int, obj) + __field(unsigned int, msg_id) + __field(unsigned int, object_id) + __field(loff_t, start) + __field(size_t, len) ), TP_fast_assign( @@ -793,8 +800,8 @@ TRACE_EVENT(cachefiles_ondemand_cread, TP_ARGS(obj, msg_id), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, msg_id ) + __field(unsigned int, obj) + __field(unsigned int, msg_id) ), TP_fast_assign( @@ -814,10 +821,10 @@ TRACE_EVENT(cachefiles_ondemand_fd_write, TP_ARGS(obj, backer, start, len), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, backer ) - __field(loff_t, start ) - __field(size_t, len ) + __field(unsigned int, obj) + __field(unsigned int, backer) + __field(loff_t, start) + __field(size_t, len) ), TP_fast_assign( @@ -840,8 +847,8 @@ TRACE_EVENT(cachefiles_ondemand_fd_release, TP_ARGS(obj, object_id), TP_STRUCT__entry( - __field(unsigned int, obj ) - __field(unsigned int, object_id ) + __field(unsigned int, obj) + __field(unsigned int, object_id) ), TP_fast_assign( diff --git a/include/trace/events/capability.h b/include/trace/events/capability.h new file mode 100644 index 000000000000..17340257946c --- /dev/null +++ b/include/trace/events/capability.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM capability + +#if !defined(_TRACE_CAPABILITY_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_CAPABILITY_H + +#include +#include +#include + +/** + * cap_capable - called after it's determined if a task has a particular + * effective capability + * + * @cred: The credentials used + * @target_ns: The user namespace of the resource being accessed + * @capable_ns: The user namespace in which the credential provides the + * capability to access the targeted resource. + * This will be NULL if ret is not 0. + * @cap: The capability to check for + * @ret: The return value of the check: 0 if it does, -ve if it does not + * + * Allows to trace calls to cap_capable in commoncap.c + */ +TRACE_EVENT(cap_capable, + + TP_PROTO(const struct cred *cred, struct user_namespace *target_ns, + const struct user_namespace *capable_ns, int cap, int ret), + + TP_ARGS(cred, target_ns, capable_ns, cap, ret), + + TP_STRUCT__entry( + __field(const struct cred *, cred) + __field(struct user_namespace *, target_ns) + __field(const struct user_namespace *, capable_ns) + __field(int, cap) + __field(int, ret) + ), + + TP_fast_assign( + __entry->cred = cred; + __entry->target_ns = target_ns; + __entry->capable_ns = ret == 0 ? capable_ns : NULL; + __entry->cap = cap; + __entry->ret = ret; + ), + + TP_printk("cred %p, target_ns %p, capable_ns %p, cap %d, ret %d", + __entry->cred, __entry->target_ns, __entry->capable_ns, __entry->cap, + __entry->ret) +); + +#endif /* _TRACE_CAPABILITY_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 2851c823095b..eb3b2f1326b1 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -1119,11 +1119,11 @@ TRACE_EVENT(f2fs_reserve_new_blocks, (unsigned long long)__entry->count) ); -DECLARE_EVENT_CLASS(f2fs__submit_page_bio, +DECLARE_EVENT_CLASS(f2fs__submit_folio_bio, - TP_PROTO(struct page *page, struct f2fs_io_info *fio), + TP_PROTO(struct folio *folio, struct f2fs_io_info *fio), - TP_ARGS(page, fio), + TP_ARGS(folio, fio), TP_STRUCT__entry( __field(dev_t, dev) @@ -1138,9 +1138,9 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio, ), TP_fast_assign( - __entry->dev = page_file_mapping(page)->host->i_sb->s_dev; - __entry->ino = page_file_mapping(page)->host->i_ino; - __entry->index = page->index; + __entry->dev = folio->mapping->host->i_sb->s_dev; + __entry->ino = folio->mapping->host->i_ino; + __entry->index = folio->index; __entry->old_blkaddr = fio->old_blkaddr; __entry->new_blkaddr = fio->new_blkaddr; __entry->op = fio->op; @@ -1149,7 +1149,7 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio, __entry->type = fio->type; ), - TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, " + TP_printk("dev = (%d,%d), ino = %lu, folio_index = 0x%lx, " "oldaddr = 0x%llx, newaddr = 0x%llx, rw = %s(%s), type = %s_%s", show_dev_ino(__entry), (unsigned long)__entry->index, @@ -1160,22 +1160,22 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio, show_block_type(__entry->type)) ); -DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio, +DEFINE_EVENT_CONDITION(f2fs__submit_folio_bio, f2fs_submit_folio_bio, - TP_PROTO(struct page *page, struct f2fs_io_info *fio), + TP_PROTO(struct folio *folio, struct f2fs_io_info *fio), - TP_ARGS(page, fio), + TP_ARGS(folio, fio), - TP_CONDITION(page->mapping) + TP_CONDITION(folio->mapping) ); -DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_write, +DEFINE_EVENT_CONDITION(f2fs__submit_folio_bio, f2fs_submit_folio_write, - TP_PROTO(struct page *page, struct f2fs_io_info *fio), + TP_PROTO(struct folio *folio, struct f2fs_io_info *fio), - TP_ARGS(page, fio), + TP_ARGS(folio, fio), - TP_CONDITION(page->mapping) + TP_CONDITION(folio->mapping) ); DECLARE_EVENT_CLASS(f2fs__bio, @@ -1322,12 +1322,11 @@ DECLARE_EVENT_CLASS(f2fs__folio, ), TP_fast_assign( - __entry->dev = folio_file_mapping(folio)->host->i_sb->s_dev; - __entry->ino = folio_file_mapping(folio)->host->i_ino; + __entry->dev = folio->mapping->host->i_sb->s_dev; + __entry->ino = folio->mapping->host->i_ino; __entry->type = type; - __entry->dir = - S_ISDIR(folio_file_mapping(folio)->host->i_mode); - __entry->index = folio_index(folio); + __entry->dir = S_ISDIR(folio->mapping->host->i_mode); + __entry->index = folio->index; __entry->dirty = folio_test_dirty(folio); __entry->uptodate = folio_test_uptodate(folio); ), diff --git a/include/trace/events/fib6.h b/include/trace/events/fib6.h index 5d7ee2610728..8d22b2e98d48 100644 --- a/include/trace/events/fib6.h +++ b/include/trace/events/fib6.h @@ -22,6 +22,7 @@ TRACE_EVENT(fib6_table_lookup, __field( int, err ) __field( int, oif ) __field( int, iif ) + __field( u32, flowlabel ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) @@ -42,6 +43,7 @@ TRACE_EVENT(fib6_table_lookup, __entry->err = ip6_rt_type_to_error(res->fib6_type); __entry->oif = flp->flowi6_oif; __entry->iif = flp->flowi6_iif; + __entry->flowlabel = ntohl(flowi6_get_flowlabel(flp)); __entry->tos = ip6_tclass(flp->flowlabel); __entry->scope = flp->flowi6_scope; __entry->flags = flp->flowi6_flags; @@ -76,11 +78,11 @@ TRACE_EVENT(fib6_table_lookup, } ), - TP_printk("table %3u oif %d iif %d proto %u %pI6c/%u -> %pI6c/%u tos %d scope %d flags %x ==> dev %s gw %pI6c err %d", + TP_printk("table %3u oif %d iif %d proto %u %pI6c/%u -> %pI6c/%u flowlabel %#x tos %d scope %d flags %x ==> dev %s gw %pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, - __entry->tos, __entry->scope, __entry->flags, - __entry->name, __entry->gw, __entry->err) + __entry->flowlabel, __entry->tos, __entry->scope, + __entry->flags, __entry->name, __entry->gw, __entry->err) ); #endif /* _TRACE_FIB6_H */ diff --git a/include/trace/events/hugetlbfs.h b/include/trace/events/hugetlbfs.h index 8331c904a9ba..59605dfaeeb4 100644 --- a/include/trace/events/hugetlbfs.h +++ b/include/trace/events/hugetlbfs.h @@ -23,7 +23,7 @@ TRACE_EVENT(hugetlbfs_alloc_inode, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->dir = dir->i_ino; + __entry->dir = dir ? dir->i_ino : 0; __entry->mode = mode; ), diff --git a/include/trace/events/mmap_lock.h b/include/trace/events/mmap_lock.h index bc2e3ad787b3..cf9f9faf8914 100644 --- a/include/trace/events/mmap_lock.h +++ b/include/trace/events/mmap_lock.h @@ -5,6 +5,7 @@ #if !defined(_TRACE_MMAP_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MMAP_LOCK_H +#include #include #include @@ -12,64 +13,61 @@ struct mm_struct; DECLARE_EVENT_CLASS(mmap_lock, - TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write), + TP_PROTO(struct mm_struct *mm, bool write), - TP_ARGS(mm, memcg_path, write), + TP_ARGS(mm, write), TP_STRUCT__entry( __field(struct mm_struct *, mm) - __string(memcg_path, memcg_path) + __field(u64, memcg_id) __field(bool, write) ), TP_fast_assign( __entry->mm = mm; - __assign_str(memcg_path); + __entry->memcg_id = cgroup_id_from_mm(mm); __entry->write = write; ), TP_printk( - "mm=%p memcg_path=%s write=%s", - __entry->mm, - __get_str(memcg_path), + "mm=%p memcg_id=%llu write=%s", + __entry->mm, __entry->memcg_id, __entry->write ? "true" : "false" ) ); #define DEFINE_MMAP_LOCK_EVENT(name) \ DEFINE_EVENT(mmap_lock, name, \ - TP_PROTO(struct mm_struct *mm, const char *memcg_path, \ - bool write), \ - TP_ARGS(mm, memcg_path, write)) + TP_PROTO(struct mm_struct *mm, bool write), \ + TP_ARGS(mm, write)) DEFINE_MMAP_LOCK_EVENT(mmap_lock_start_locking); DEFINE_MMAP_LOCK_EVENT(mmap_lock_released); TRACE_EVENT(mmap_lock_acquire_returned, - TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write, - bool success), + TP_PROTO(struct mm_struct *mm, bool write, bool success), - TP_ARGS(mm, memcg_path, write, success), + TP_ARGS(mm, write, success), TP_STRUCT__entry( __field(struct mm_struct *, mm) - __string(memcg_path, memcg_path) + __field(u64, memcg_id) __field(bool, write) __field(bool, success) ), TP_fast_assign( __entry->mm = mm; - __assign_str(memcg_path); + __entry->memcg_id = cgroup_id_from_mm(mm); __entry->write = write; __entry->success = success; ), TP_printk( - "mm=%p memcg_path=%s write=%s success=%s", + "mm=%p memcg_id=%llu write=%s success=%s", __entry->mm, - __get_str(memcg_path), + __entry->memcg_id, __entry->write ? "true" : "false", __entry->success ? "true" : "false" ) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index bb8a59c6caa2..72fbfe3caeaf 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -13,6 +13,69 @@ * Thus most bits set go first. */ +/* These define the values that are enums (the bits) */ +#define TRACE_GFP_FLAGS_GENERAL \ + TRACE_GFP_EM(DMA) \ + TRACE_GFP_EM(HIGHMEM) \ + TRACE_GFP_EM(DMA32) \ + TRACE_GFP_EM(MOVABLE) \ + TRACE_GFP_EM(RECLAIMABLE) \ + TRACE_GFP_EM(HIGH) \ + TRACE_GFP_EM(IO) \ + TRACE_GFP_EM(FS) \ + TRACE_GFP_EM(ZERO) \ + TRACE_GFP_EM(DIRECT_RECLAIM) \ + TRACE_GFP_EM(KSWAPD_RECLAIM) \ + TRACE_GFP_EM(WRITE) \ + TRACE_GFP_EM(NOWARN) \ + TRACE_GFP_EM(RETRY_MAYFAIL) \ + TRACE_GFP_EM(NOFAIL) \ + TRACE_GFP_EM(NORETRY) \ + TRACE_GFP_EM(MEMALLOC) \ + TRACE_GFP_EM(COMP) \ + TRACE_GFP_EM(NOMEMALLOC) \ + TRACE_GFP_EM(HARDWALL) \ + TRACE_GFP_EM(THISNODE) \ + TRACE_GFP_EM(ACCOUNT) \ + TRACE_GFP_EM(ZEROTAGS) + +#ifdef CONFIG_KASAN_HW_TAGS +# define TRACE_GFP_FLAGS_KASAN \ + TRACE_GFP_EM(SKIP_ZERO) \ + TRACE_GFP_EM(SKIP_KASAN) +#else +# define TRACE_GFP_FLAGS_KASAN +#endif + +#ifdef CONFIG_LOCKDEP +# define TRACE_GFP_FLAGS_LOCKDEP \ + TRACE_GFP_EM(NOLOCKDEP) +#else +# define TRACE_GFP_FLAGS_LOCKDEP +#endif + +#ifdef CONFIG_SLAB_OBJ_EXT +# define TRACE_GFP_FLAGS_SLAB \ + TRACE_GFP_EM(NO_OBJ_EXT) +#else +# define TRACE_GFP_FLAGS_SLAB +#endif + +#define TRACE_GFP_FLAGS \ + TRACE_GFP_FLAGS_GENERAL \ + TRACE_GFP_FLAGS_KASAN \ + TRACE_GFP_FLAGS_LOCKDEP \ + TRACE_GFP_FLAGS_SLAB + +#undef TRACE_GFP_EM +#define TRACE_GFP_EM(a) TRACE_DEFINE_ENUM(___GFP_##a##_BIT); + +TRACE_GFP_FLAGS + +/* Just in case these are ever used */ +TRACE_DEFINE_ENUM(___GFP_UNUSED_BIT); +TRACE_DEFINE_ENUM(___GFP_LAST_BIT); + #define gfpflag_string(flag) {(__force unsigned long)flag, #flag} #define __def_gfpflag_names \ @@ -116,7 +179,8 @@ DEF_PAGEFLAG_NAME(head), \ DEF_PAGEFLAG_NAME(reclaim), \ DEF_PAGEFLAG_NAME(swapbacked), \ - DEF_PAGEFLAG_NAME(unevictable) \ + DEF_PAGEFLAG_NAME(unevictable), \ + DEF_PAGEFLAG_NAME(dropbehind) \ IF_HAVE_PG_MLOCK(mlocked) \ IF_HAVE_PG_HWPOISON(hwpoison) \ IF_HAVE_PG_IDLE(idle) \ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index bf511bca896e..6e699cadcb29 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -21,6 +21,7 @@ EM(netfs_read_trace_readahead, "READAHEAD") \ EM(netfs_read_trace_readpage, "READPAGE ") \ EM(netfs_read_trace_read_gaps, "READ-GAPS") \ + EM(netfs_read_trace_read_single, "READ-SNGL") \ EM(netfs_read_trace_prefetch_for_write, "PREFETCHW") \ E_(netfs_read_trace_write_begin, "WRITEBEGN") @@ -35,9 +36,11 @@ EM(NETFS_READAHEAD, "RA") \ EM(NETFS_READPAGE, "RP") \ EM(NETFS_READ_GAPS, "RG") \ + EM(NETFS_READ_SINGLE, "R1") \ EM(NETFS_READ_FOR_WRITE, "RW") \ EM(NETFS_DIO_READ, "DR") \ EM(NETFS_WRITEBACK, "WB") \ + EM(NETFS_WRITEBACK_SINGLE, "W1") \ EM(NETFS_WRITETHROUGH, "WT") \ EM(NETFS_UNBUFFERED_WRITE, "UW") \ EM(NETFS_DIO_WRITE, "DW") \ @@ -47,17 +50,23 @@ EM(netfs_rreq_trace_assess, "ASSESS ") \ EM(netfs_rreq_trace_copy, "COPY ") \ EM(netfs_rreq_trace_collect, "COLLECT") \ + EM(netfs_rreq_trace_complete, "COMPLET") \ + EM(netfs_rreq_trace_dirty, "DIRTY ") \ EM(netfs_rreq_trace_done, "DONE ") \ EM(netfs_rreq_trace_free, "FREE ") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ + EM(netfs_rreq_trace_set_abandon, "S-ABNDN") \ EM(netfs_rreq_trace_set_pause, "PAUSE ") \ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \ EM(netfs_rreq_trace_unmark, "UNMARK ") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \ + EM(netfs_rreq_trace_wait_queue, "WAIT-Q ") \ EM(netfs_rreq_trace_wake_ip, "WAKE-IP") \ + EM(netfs_rreq_trace_wake_queue, "WAKE-Q ") \ + EM(netfs_rreq_trace_woke_queue, "WOKE-Q ") \ EM(netfs_rreq_trace_unpause, "UNPAUSE") \ E_(netfs_rreq_trace_write_done, "WR-DONE") @@ -74,6 +83,10 @@ #define netfs_sreq_traces \ EM(netfs_sreq_trace_add_donations, "+DON ") \ EM(netfs_sreq_trace_added, "ADD ") \ + EM(netfs_sreq_trace_cache_nowrite, "CA-NW") \ + EM(netfs_sreq_trace_cache_prepare, "CA-PR") \ + EM(netfs_sreq_trace_cache_write, "CA-WR") \ + EM(netfs_sreq_trace_cancel, "CANCL") \ EM(netfs_sreq_trace_clear, "CLEAR") \ EM(netfs_sreq_trace_discard, "DSCRD") \ EM(netfs_sreq_trace_donate_to_prev, "DON-P") \ @@ -84,6 +97,9 @@ EM(netfs_sreq_trace_hit_eof, "EOF ") \ EM(netfs_sreq_trace_io_progress, "IO ") \ EM(netfs_sreq_trace_limited, "LIMIT") \ + EM(netfs_sreq_trace_need_clear, "N-CLR") \ + EM(netfs_sreq_trace_partial_read, "PARTR") \ + EM(netfs_sreq_trace_need_retry, "NRTRY") \ EM(netfs_sreq_trace_prepare, "PREP ") \ EM(netfs_sreq_trace_prep_failed, "PRPFL") \ EM(netfs_sreq_trace_progress, "PRGRS") \ @@ -129,6 +145,7 @@ EM(netfs_sreq_trace_get_submit, "GET SUBMIT") \ EM(netfs_sreq_trace_get_short_read, "GET SHORTRD") \ EM(netfs_sreq_trace_new, "NEW ") \ + EM(netfs_sreq_trace_put_abandon, "PUT ABANDON") \ EM(netfs_sreq_trace_put_cancel, "PUT CANCEL ") \ EM(netfs_sreq_trace_put_clear, "PUT CLEAR ") \ EM(netfs_sreq_trace_put_consumed, "PUT CONSUME") \ @@ -152,6 +169,7 @@ EM(netfs_streaming_filled_page, "mod-streamw-f") \ EM(netfs_streaming_cont_filled_page, "mod-streamw-f+") \ EM(netfs_folio_trace_abandon, "abandon") \ + EM(netfs_folio_trace_alloc_buffer, "alloc-buf") \ EM(netfs_folio_trace_cancel_copy, "cancel-copy") \ EM(netfs_folio_trace_cancel_store, "cancel-store") \ EM(netfs_folio_trace_clear, "clear") \ @@ -168,6 +186,7 @@ EM(netfs_folio_trace_mkwrite, "mkwrite") \ EM(netfs_folio_trace_mkwrite_plus, "mkwrite+") \ EM(netfs_folio_trace_not_under_wback, "!wback") \ + EM(netfs_folio_trace_not_locked, "!locked") \ EM(netfs_folio_trace_put, "put") \ EM(netfs_folio_trace_read, "read") \ EM(netfs_folio_trace_read_done, "read-done") \ @@ -191,6 +210,14 @@ EM(netfs_trace_donate_to_next, "to-next") \ E_(netfs_trace_donate_to_deferred_next, "defer-next") +#define netfs_folioq_traces \ + EM(netfs_trace_folioq_alloc_buffer, "alloc-buf") \ + EM(netfs_trace_folioq_clear, "clear") \ + EM(netfs_trace_folioq_delete, "delete") \ + EM(netfs_trace_folioq_make_space, "make-space") \ + EM(netfs_trace_folioq_rollbuf_init, "roll-init") \ + E_(netfs_trace_folioq_read_progress, "r-progress") + #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY @@ -209,6 +236,7 @@ enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte); enum netfs_folio_trace { netfs_folio_traces } __mode(byte); enum netfs_collect_contig_trace { netfs_collect_contig_traces } __mode(byte); enum netfs_donate_trace { netfs_donate_traces } __mode(byte); +enum netfs_folioq_trace { netfs_folioq_traces } __mode(byte); #endif @@ -232,6 +260,7 @@ netfs_sreq_ref_traces; netfs_folio_traces; netfs_collect_contig_traces; netfs_donate_traces; +netfs_folioq_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -250,13 +279,13 @@ TRACE_EVENT(netfs_read, TP_ARGS(rreq, start, len, what), TP_STRUCT__entry( - __field(unsigned int, rreq ) - __field(unsigned int, cookie ) - __field(loff_t, i_size ) - __field(loff_t, start ) - __field(size_t, len ) - __field(enum netfs_read_trace, what ) - __field(unsigned int, netfs_inode ) + __field(unsigned int, rreq) + __field(unsigned int, cookie) + __field(loff_t, i_size) + __field(loff_t, start) + __field(size_t, len) + __field(enum netfs_read_trace, what) + __field(unsigned int, netfs_inode) ), TP_fast_assign( @@ -284,10 +313,10 @@ TRACE_EVENT(netfs_rreq, TP_ARGS(rreq, what), TP_STRUCT__entry( - __field(unsigned int, rreq ) - __field(unsigned int, flags ) - __field(enum netfs_io_origin, origin ) - __field(enum netfs_rreq_trace, what ) + __field(unsigned int, rreq) + __field(unsigned int, flags) + __field(enum netfs_io_origin, origin) + __field(enum netfs_rreq_trace, what) ), TP_fast_assign( @@ -311,15 +340,16 @@ TRACE_EVENT(netfs_sreq, TP_ARGS(sreq, what), TP_STRUCT__entry( - __field(unsigned int, rreq ) - __field(unsigned short, index ) - __field(short, error ) - __field(unsigned short, flags ) - __field(enum netfs_io_source, source ) - __field(enum netfs_sreq_trace, what ) - __field(size_t, len ) - __field(size_t, transferred ) - __field(loff_t, start ) + __field(unsigned int, rreq) + __field(unsigned short, index) + __field(short, error) + __field(unsigned short, flags) + __field(enum netfs_io_source, source) + __field(enum netfs_sreq_trace, what) + __field(u8, slot) + __field(size_t, len) + __field(size_t, transferred) + __field(loff_t, start) ), TP_fast_assign( @@ -332,15 +362,16 @@ TRACE_EVENT(netfs_sreq, __entry->len = sreq->len; __entry->transferred = sreq->transferred; __entry->start = sreq->start; + __entry->slot = sreq->io_iter.folioq_slot; ), - TP_printk("R=%08x[%x] %s %s f=%02x s=%llx %zx/%zx e=%d", + TP_printk("R=%08x[%x] %s %s f=%02x s=%llx %zx/%zx s=%u e=%d", __entry->rreq, __entry->index, __print_symbolic(__entry->source, netfs_sreq_sources), __print_symbolic(__entry->what, netfs_sreq_traces), __entry->flags, __entry->start, __entry->transferred, __entry->len, - __entry->error) + __entry->slot, __entry->error) ); TRACE_EVENT(netfs_failure, @@ -351,15 +382,15 @@ TRACE_EVENT(netfs_failure, TP_ARGS(rreq, sreq, error, what), TP_STRUCT__entry( - __field(unsigned int, rreq ) - __field(short, index ) - __field(short, error ) - __field(unsigned short, flags ) - __field(enum netfs_io_source, source ) - __field(enum netfs_failure, what ) - __field(size_t, len ) - __field(size_t, transferred ) - __field(loff_t, start ) + __field(unsigned int, rreq) + __field(short, index) + __field(short, error) + __field(unsigned short, flags) + __field(enum netfs_io_source, source) + __field(enum netfs_failure, what) + __field(size_t, len) + __field(size_t, transferred) + __field(loff_t, start) ), TP_fast_assign( @@ -390,9 +421,9 @@ TRACE_EVENT(netfs_rreq_ref, TP_ARGS(rreq_debug_id, ref, what), TP_STRUCT__entry( - __field(unsigned int, rreq ) - __field(int, ref ) - __field(enum netfs_rreq_ref_trace, what ) + __field(unsigned int, rreq) + __field(int, ref) + __field(enum netfs_rreq_ref_trace, what) ), TP_fast_assign( @@ -414,10 +445,10 @@ TRACE_EVENT(netfs_sreq_ref, TP_ARGS(rreq_debug_id, subreq_debug_index, ref, what), TP_STRUCT__entry( - __field(unsigned int, rreq ) - __field(unsigned int, subreq ) - __field(int, ref ) - __field(enum netfs_sreq_ref_trace, what ) + __field(unsigned int, rreq) + __field(unsigned int, subreq) + __field(int, ref) + __field(enum netfs_sreq_ref_trace, what) ), TP_fast_assign( @@ -465,10 +496,10 @@ TRACE_EVENT(netfs_write_iter, TP_ARGS(iocb, from), TP_STRUCT__entry( - __field(unsigned long long, start ) - __field(size_t, len ) - __field(unsigned int, flags ) - __field(unsigned int, ino ) + __field(unsigned long long, start) + __field(size_t, len) + __field(unsigned int, flags) + __field(unsigned int, ino) ), TP_fast_assign( @@ -489,12 +520,12 @@ TRACE_EVENT(netfs_write, TP_ARGS(wreq, what), TP_STRUCT__entry( - __field(unsigned int, wreq ) - __field(unsigned int, cookie ) - __field(unsigned int, ino ) - __field(enum netfs_write_trace, what ) - __field(unsigned long long, start ) - __field(unsigned long long, len ) + __field(unsigned int, wreq) + __field(unsigned int, cookie) + __field(unsigned int, ino) + __field(enum netfs_write_trace, what) + __field(unsigned long long, start) + __field(unsigned long long, len) ), TP_fast_assign( @@ -522,10 +553,10 @@ TRACE_EVENT(netfs_collect, TP_ARGS(wreq), TP_STRUCT__entry( - __field(unsigned int, wreq ) - __field(unsigned int, len ) - __field(unsigned long long, transferred ) - __field(unsigned long long, start ) + __field(unsigned int, wreq) + __field(unsigned int, len) + __field(unsigned long long, transferred) + __field(unsigned long long, start) ), TP_fast_assign( @@ -548,12 +579,12 @@ TRACE_EVENT(netfs_collect_sreq, TP_ARGS(wreq, subreq), TP_STRUCT__entry( - __field(unsigned int, wreq ) - __field(unsigned int, subreq ) - __field(unsigned int, stream ) - __field(unsigned int, len ) - __field(unsigned int, transferred ) - __field(unsigned long long, start ) + __field(unsigned int, wreq) + __field(unsigned int, subreq) + __field(unsigned int, stream) + __field(unsigned int, len) + __field(unsigned int, transferred) + __field(unsigned long long, start) ), TP_fast_assign( @@ -579,11 +610,11 @@ TRACE_EVENT(netfs_collect_folio, TP_ARGS(wreq, folio, fend, collected_to), TP_STRUCT__entry( - __field(unsigned int, wreq ) - __field(unsigned long, index ) - __field(unsigned long long, fend ) - __field(unsigned long long, cleaned_to ) - __field(unsigned long long, collected_to ) + __field(unsigned int, wreq) + __field(unsigned long, index) + __field(unsigned long long, fend) + __field(unsigned long long, cleaned_to) + __field(unsigned long long, collected_to) ), TP_fast_assign( @@ -608,10 +639,10 @@ TRACE_EVENT(netfs_collect_state, TP_ARGS(wreq, collected_to, notes), TP_STRUCT__entry( - __field(unsigned int, wreq ) - __field(unsigned int, notes ) - __field(unsigned long long, collected_to ) - __field(unsigned long long, cleaned_to ) + __field(unsigned int, wreq) + __field(unsigned int, notes) + __field(unsigned long long, collected_to) + __field(unsigned long long, cleaned_to) ), TP_fast_assign( @@ -680,69 +711,27 @@ TRACE_EVENT(netfs_collect_stream, __entry->collected_to, __entry->front) ); -TRACE_EVENT(netfs_progress, - TP_PROTO(const struct netfs_io_subrequest *subreq, - unsigned long long start, size_t avail, size_t part), +TRACE_EVENT(netfs_folioq, + TP_PROTO(const struct folio_queue *fq, + enum netfs_folioq_trace trace), - TP_ARGS(subreq, start, avail, part), + TP_ARGS(fq, trace), TP_STRUCT__entry( __field(unsigned int, rreq) - __field(unsigned int, subreq) - __field(unsigned int, consumed) - __field(unsigned int, transferred) - __field(unsigned long long, f_start) - __field(unsigned int, f_avail) - __field(unsigned int, f_part) - __field(unsigned char, slot) + __field(unsigned int, id) + __field(enum netfs_folioq_trace, trace) ), TP_fast_assign( - __entry->rreq = subreq->rreq->debug_id; - __entry->subreq = subreq->debug_index; - __entry->consumed = subreq->consumed; - __entry->transferred = subreq->transferred; - __entry->f_start = start; - __entry->f_avail = avail; - __entry->f_part = part; - __entry->slot = subreq->curr_folioq_slot; - ), - - TP_printk("R=%08x[%02x] s=%llx ct=%x/%x pa=%x/%x sl=%x", - __entry->rreq, __entry->subreq, __entry->f_start, - __entry->consumed, __entry->transferred, - __entry->f_part, __entry->f_avail, __entry->slot) - ); - -TRACE_EVENT(netfs_donate, - TP_PROTO(const struct netfs_io_request *rreq, - const struct netfs_io_subrequest *from, - const struct netfs_io_subrequest *to, - size_t amount, - enum netfs_donate_trace trace), - - TP_ARGS(rreq, from, to, amount, trace), - - TP_STRUCT__entry( - __field(unsigned int, rreq) - __field(unsigned int, from) - __field(unsigned int, to) - __field(unsigned int, amount) - __field(enum netfs_donate_trace, trace) - ), - - TP_fast_assign( - __entry->rreq = rreq->debug_id; - __entry->from = from->debug_index; - __entry->to = to ? to->debug_index : -1; - __entry->amount = amount; + __entry->rreq = fq ? fq->rreq_id : 0; + __entry->id = fq ? fq->debug_id : 0; __entry->trace = trace; ), - TP_printk("R=%08x[%02x] -> [%02x] %s am=%x", - __entry->rreq, __entry->from, __entry->to, - __print_symbolic(__entry->trace, netfs_donate_traces), - __entry->amount) + TP_printk("R=%08x fq=%x %s", + __entry->rreq, __entry->id, + __print_symbolic(__entry->trace, netfs_folioq_traces)) ); #undef EM diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d03e0bd8c028..2f119d18a061 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -117,8 +117,10 @@ #define rxrpc_call_poke_traces \ EM(rxrpc_call_poke_abort, "Abort") \ EM(rxrpc_call_poke_complete, "Compl") \ + EM(rxrpc_call_poke_conn_abort, "Conn-abort") \ EM(rxrpc_call_poke_error, "Error") \ EM(rxrpc_call_poke_idle, "Idle") \ + EM(rxrpc_call_poke_rx_packet, "Rx-packet") \ EM(rxrpc_call_poke_set_timeout, "Set-timo") \ EM(rxrpc_call_poke_start, "Start") \ EM(rxrpc_call_poke_timer, "Timer") \ @@ -127,9 +129,9 @@ #define rxrpc_skb_traces \ EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \ EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ + EM(rxrpc_skb_get_call_rx, "GET call-rx ") \ EM(rxrpc_skb_get_conn_secured, "GET conn-secd") \ EM(rxrpc_skb_get_conn_work, "GET conn-work") \ - EM(rxrpc_skb_get_last_nack, "GET last-nack") \ EM(rxrpc_skb_get_local_work, "GET locl-work") \ EM(rxrpc_skb_get_reject_work, "GET rej-work ") \ EM(rxrpc_skb_get_to_recvmsg, "GET to-recv ") \ @@ -138,12 +140,12 @@ EM(rxrpc_skb_new_error_report, "NEW error-rpt") \ EM(rxrpc_skb_new_jumbo_subpacket, "NEW jumbo-sub") \ EM(rxrpc_skb_new_unshared, "NEW unshared ") \ + EM(rxrpc_skb_put_call_rx, "PUT call-rx ") \ EM(rxrpc_skb_put_conn_secured, "PUT conn-secd") \ EM(rxrpc_skb_put_conn_work, "PUT conn-work") \ EM(rxrpc_skb_put_error_report, "PUT error-rep") \ EM(rxrpc_skb_put_input, "PUT input ") \ EM(rxrpc_skb_put_jumbo_subpacket, "PUT jumbo-sub") \ - EM(rxrpc_skb_put_last_nack, "PUT last-nack") \ EM(rxrpc_skb_put_purge, "PUT purge ") \ EM(rxrpc_skb_put_rotate, "PUT rotate ") \ EM(rxrpc_skb_put_unknown, "PUT unknown ") \ @@ -282,6 +284,7 @@ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ EM(rxrpc_call_see_connected, "SEE connect ") \ + EM(rxrpc_call_see_conn_abort, "SEE conn-abt") \ EM(rxrpc_call_see_disconnected, "SEE disconn ") \ EM(rxrpc_call_see_distribute_error, "SEE dist-err") \ EM(rxrpc_call_see_input, "SEE input ") \ @@ -292,7 +295,6 @@ #define rxrpc_txqueue_traces \ EM(rxrpc_txqueue_await_reply, "AWR") \ - EM(rxrpc_txqueue_dequeue, "DEQ") \ EM(rxrpc_txqueue_end, "END") \ EM(rxrpc_txqueue_queue, "QUE") \ EM(rxrpc_txqueue_queue_last, "QLS") \ @@ -300,6 +302,13 @@ EM(rxrpc_txqueue_rotate_last, "RLS") \ E_(rxrpc_txqueue_wait, "WAI") +#define rxrpc_txdata_traces \ + EM(rxrpc_txdata_inject_loss, " *INJ-LOSS*") \ + EM(rxrpc_txdata_new_data, " ") \ + EM(rxrpc_txdata_retransmit, " *RETRANS*") \ + EM(rxrpc_txdata_tlp_new_data, " *TLP-NEW*") \ + E_(rxrpc_txdata_tlp_retransmit, " *TLP-RETRANS*") + #define rxrpc_receive_traces \ EM(rxrpc_receive_end, "END") \ EM(rxrpc_receive_front, "FRN") \ @@ -335,11 +344,10 @@ E_(rxrpc_rtt_tx_ping, "PING") #define rxrpc_rtt_rx_traces \ - EM(rxrpc_rtt_rx_other_ack, "OACK") \ + EM(rxrpc_rtt_rx_data_ack, "DACK") \ EM(rxrpc_rtt_rx_obsolete, "OBSL") \ EM(rxrpc_rtt_rx_lost, "LOST") \ - EM(rxrpc_rtt_rx_ping_response, "PONG") \ - E_(rxrpc_rtt_rx_requested_ack, "RACK") + E_(rxrpc_rtt_rx_ping_response, "PONG") #define rxrpc_timer_traces \ EM(rxrpc_timer_trace_delayed_ack, "DelayAck ") \ @@ -347,11 +355,12 @@ EM(rxrpc_timer_trace_hard, "HardLimit") \ EM(rxrpc_timer_trace_idle, "IdleLimit") \ EM(rxrpc_timer_trace_keepalive, "KeepAlive") \ - EM(rxrpc_timer_trace_lost_ack, "LostAck ") \ EM(rxrpc_timer_trace_ping, "DelayPing") \ - EM(rxrpc_timer_trace_resend, "Resend ") \ - EM(rxrpc_timer_trace_resend_reset, "ResendRst") \ - E_(rxrpc_timer_trace_resend_tx, "ResendTx ") + EM(rxrpc_timer_trace_rack_off, "RACK-OFF ") \ + EM(rxrpc_timer_trace_rack_zwp, "RACK-ZWP ") \ + EM(rxrpc_timer_trace_rack_reo, "RACK-Reo ") \ + EM(rxrpc_timer_trace_rack_tlp_pto, "TLP-PTO ") \ + E_(rxrpc_timer_trace_rack_rto, "RTO ") #define rxrpc_propose_ack_traces \ EM(rxrpc_propose_ack_client_tx_end, "ClTxEnd") \ @@ -362,22 +371,24 @@ EM(rxrpc_propose_ack_ping_for_lost_ack, "LostAck") \ EM(rxrpc_propose_ack_ping_for_lost_reply, "LostRpl") \ EM(rxrpc_propose_ack_ping_for_0_retrans, "0-Retrn") \ + EM(rxrpc_propose_ack_ping_for_mtu_probe, "MTUProb") \ EM(rxrpc_propose_ack_ping_for_old_rtt, "OldRtt ") \ EM(rxrpc_propose_ack_ping_for_params, "Params ") \ EM(rxrpc_propose_ack_ping_for_rtt, "Rtt ") \ EM(rxrpc_propose_ack_processing_op, "ProcOp ") \ EM(rxrpc_propose_ack_respond_to_ack, "Rsp2Ack") \ EM(rxrpc_propose_ack_respond_to_ping, "Rsp2Png") \ + EM(rxrpc_propose_ack_retransmit, "Retrans") \ EM(rxrpc_propose_ack_retry_tx, "RetryTx") \ EM(rxrpc_propose_ack_rotate_rx, "RxAck ") \ EM(rxrpc_propose_ack_rx_idle, "RxIdle ") \ E_(rxrpc_propose_ack_terminal_ack, "ClTerm ") -#define rxrpc_congest_modes \ - EM(RXRPC_CALL_CONGEST_AVOIDANCE, "CongAvoid") \ - EM(RXRPC_CALL_FAST_RETRANSMIT, "FastReTx ") \ - EM(RXRPC_CALL_PACKET_LOSS, "PktLoss ") \ - E_(RXRPC_CALL_SLOW_START, "SlowStart") +#define rxrpc_ca_states \ + EM(RXRPC_CA_CONGEST_AVOIDANCE, "CongAvoid") \ + EM(RXRPC_CA_FAST_RETRANSMIT, "FastReTx ") \ + EM(RXRPC_CA_PACKET_LOSS, "PktLoss ") \ + E_(RXRPC_CA_SLOW_START, "SlowStart") #define rxrpc_congest_changes \ EM(rxrpc_cong_begin_retransmission, " Retrans") \ @@ -450,7 +461,7 @@ #define rxrpc_req_ack_traces \ EM(rxrpc_reqack_ack_lost, "ACK-LOST ") \ - EM(rxrpc_reqack_already_on, "ALREADY-ON") \ + EM(rxrpc_reqack_app_stall, "APP-STALL ") \ EM(rxrpc_reqack_more_rtt, "MORE-RTT ") \ EM(rxrpc_reqack_no_srv_last, "NO-SRVLAST") \ EM(rxrpc_reqack_old_rtt, "OLD-RTT ") \ @@ -460,21 +471,60 @@ /* ---- Must update size of stat_why_req_ack[] if more are added! */ #define rxrpc_txbuf_traces \ - EM(rxrpc_txbuf_alloc_ack, "ALLOC ACK ") \ EM(rxrpc_txbuf_alloc_data, "ALLOC DATA ") \ EM(rxrpc_txbuf_free, "FREE ") \ EM(rxrpc_txbuf_get_buffer, "GET BUFFER ") \ EM(rxrpc_txbuf_get_trans, "GET TRANS ") \ EM(rxrpc_txbuf_get_retrans, "GET RETRANS") \ - EM(rxrpc_txbuf_put_ack_tx, "PUT ACK TX ") \ EM(rxrpc_txbuf_put_cleaned, "PUT CLEANED") \ EM(rxrpc_txbuf_put_nomem, "PUT NOMEM ") \ EM(rxrpc_txbuf_put_rotated, "PUT ROTATED") \ EM(rxrpc_txbuf_put_send_aborted, "PUT SEND-X ") \ EM(rxrpc_txbuf_put_trans, "PUT TRANS ") \ + EM(rxrpc_txbuf_see_lost, "SEE LOST ") \ EM(rxrpc_txbuf_see_out_of_step, "OUT-OF-STEP") \ - EM(rxrpc_txbuf_see_send_more, "SEE SEND+ ") \ - E_(rxrpc_txbuf_see_unacked, "SEE UNACKED") + E_(rxrpc_txbuf_see_send_more, "SEE SEND+ ") + +#define rxrpc_tq_traces \ + EM(rxrpc_tq_alloc, "ALLOC") \ + EM(rxrpc_tq_cleaned, "CLEAN") \ + EM(rxrpc_tq_decant, "DCNT ") \ + EM(rxrpc_tq_decant_advance, "DCNT>") \ + EM(rxrpc_tq_queue, "QUEUE") \ + EM(rxrpc_tq_queue_dup, "QUE!!") \ + EM(rxrpc_tq_rotate, "ROT ") \ + EM(rxrpc_tq_rotate_and_free, "ROT-F") \ + EM(rxrpc_tq_rotate_and_keep, "ROT-K") \ + EM(rxrpc_tq_transmit, "XMIT ") \ + E_(rxrpc_tq_transmit_advance, "XMIT>") + +#define rxrpc_pmtud_reduce_traces \ + EM(rxrpc_pmtud_reduce_ack, "Ack ") \ + EM(rxrpc_pmtud_reduce_icmp, "Icmp ") \ + E_(rxrpc_pmtud_reduce_route, "Route") + +#define rxrpc_rotate_traces \ + EM(rxrpc_rotate_trace_hack, "hard-ack") \ + EM(rxrpc_rotate_trace_sack, "soft-ack") \ + E_(rxrpc_rotate_trace_snak, "soft-nack") + +#define rxrpc_rack_timer_modes \ + EM(RXRPC_CALL_RACKTIMER_OFF, "---") \ + EM(RXRPC_CALL_RACKTIMER_RACK_REORDER, "REO") \ + EM(RXRPC_CALL_RACKTIMER_TLP_PTO, "TLP") \ + E_(RXRPC_CALL_RACKTIMER_RTO, "RTO") + +#define rxrpc_tlp_probe_traces \ + EM(rxrpc_tlp_probe_trace_busy, "busy") \ + EM(rxrpc_tlp_probe_trace_transmit_new, "transmit-new") \ + E_(rxrpc_tlp_probe_trace_retransmit, "retransmit") + +#define rxrpc_tlp_ack_traces \ + EM(rxrpc_tlp_ack_trace_acked, "acked") \ + EM(rxrpc_tlp_ack_trace_dup_acked, "dup-acked") \ + EM(rxrpc_tlp_ack_trace_hard_beyond, "hard-beyond") \ + EM(rxrpc_tlp_ack_trace_incomplete, "incomplete") \ + E_(rxrpc_tlp_ack_trace_new_data, "new-data") /* * Generate enums for tracing information. @@ -496,18 +546,24 @@ enum rxrpc_congest_change { rxrpc_congest_changes } __mode(byte); enum rxrpc_conn_trace { rxrpc_conn_traces } __mode(byte); enum rxrpc_local_trace { rxrpc_local_traces } __mode(byte); enum rxrpc_peer_trace { rxrpc_peer_traces } __mode(byte); +enum rxrpc_pmtud_reduce_trace { rxrpc_pmtud_reduce_traces } __mode(byte); enum rxrpc_propose_ack_outcome { rxrpc_propose_ack_outcomes } __mode(byte); enum rxrpc_propose_ack_trace { rxrpc_propose_ack_traces } __mode(byte); enum rxrpc_receive_trace { rxrpc_receive_traces } __mode(byte); enum rxrpc_recvmsg_trace { rxrpc_recvmsg_traces } __mode(byte); enum rxrpc_req_ack_trace { rxrpc_req_ack_traces } __mode(byte); +enum rxrpc_rotate_trace { rxrpc_rotate_traces } __mode(byte); enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); enum rxrpc_sack_trace { rxrpc_sack_traces } __mode(byte); enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); +enum rxrpc_tlp_ack_trace { rxrpc_tlp_ack_traces } __mode(byte); +enum rxrpc_tlp_probe_trace { rxrpc_tlp_probe_traces } __mode(byte); +enum rxrpc_tq_trace { rxrpc_tq_traces } __mode(byte); enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); enum rxrpc_txbuf_trace { rxrpc_txbuf_traces } __mode(byte); +enum rxrpc_txdata_trace { rxrpc_txdata_traces } __mode(byte); enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ @@ -525,24 +581,31 @@ enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); rxrpc_abort_reasons; rxrpc_bundle_traces; +rxrpc_ca_states; rxrpc_call_poke_traces; rxrpc_call_traces; rxrpc_client_traces; rxrpc_congest_changes; -rxrpc_congest_modes; rxrpc_conn_traces; rxrpc_local_traces; +rxrpc_pmtud_reduce_traces; rxrpc_propose_ack_traces; +rxrpc_rack_timer_modes; rxrpc_receive_traces; rxrpc_recvmsg_traces; rxrpc_req_ack_traces; +rxrpc_rotate_traces; rxrpc_rtt_rx_traces; rxrpc_rtt_tx_traces; rxrpc_sack_traces; rxrpc_skb_traces; rxrpc_timer_traces; +rxrpc_tlp_ack_traces; +rxrpc_tlp_probe_traces; +rxrpc_tq_traces; rxrpc_tx_points; rxrpc_txbuf_traces; +rxrpc_txdata_traces; rxrpc_txqueue_traces; /* @@ -581,6 +644,20 @@ TRACE_EVENT(rxrpc_local, __entry->usage) ); +TRACE_EVENT(rxrpc_iothread_rx, + TP_PROTO(struct rxrpc_local *local, unsigned int nr_rx), + TP_ARGS(local, nr_rx), + TP_STRUCT__entry( + __field(unsigned int, local) + __field(unsigned int, nr_rx) + ), + TP_fast_assign( + __entry->local = local->debug_id; + __entry->nr_rx = nr_rx; + ), + TP_printk("L=%08x nrx=%u", __entry->local, __entry->nr_rx) + ); + TRACE_EVENT(rxrpc_peer, TP_PROTO(unsigned int peer_debug_id, int ref, enum rxrpc_peer_trace why), @@ -865,34 +942,101 @@ TRACE_EVENT(rxrpc_txqueue, TP_STRUCT__entry( __field(unsigned int, call) __field(enum rxrpc_txqueue_trace, why) - __field(rxrpc_seq_t, acks_hard_ack) __field(rxrpc_seq_t, tx_bottom) + __field(rxrpc_seq_t, acks_hard_ack) __field(rxrpc_seq_t, tx_top) - __field(rxrpc_seq_t, tx_prepared) + __field(rxrpc_seq_t, send_top) __field(int, tx_winsize) ), TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; - __entry->acks_hard_ack = call->acks_hard_ack; __entry->tx_bottom = call->tx_bottom; + __entry->acks_hard_ack = call->acks_hard_ack; __entry->tx_top = call->tx_top; - __entry->tx_prepared = call->tx_prepared; + __entry->send_top = call->send_top; __entry->tx_winsize = call->tx_winsize; ), - TP_printk("c=%08x %s f=%08x h=%08x n=%u/%u/%u/%u", + TP_printk("c=%08x %s b=%08x h=%08x n=%u/%u/%u/%u", __entry->call, __print_symbolic(__entry->why, rxrpc_txqueue_traces), __entry->tx_bottom, __entry->acks_hard_ack, - __entry->tx_top - __entry->tx_bottom, + __entry->acks_hard_ack - __entry->tx_bottom, __entry->tx_top - __entry->acks_hard_ack, - __entry->tx_prepared - __entry->tx_bottom, + __entry->send_top - __entry->tx_top, __entry->tx_winsize) ); +TRACE_EVENT(rxrpc_transmit, + TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t send_top, int space), + + TP_ARGS(call, send_top, space), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_seq_t, seq) + __field(u16, space) + __field(u16, tx_winsize) + __field(u16, cong_cwnd) + __field(u16, cong_extra) + __field(u16, in_flight) + __field(u16, prepared) + __field(u16, pmtud_jumbo) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->seq = call->tx_top + 1; + __entry->space = space; + __entry->tx_winsize = call->tx_winsize; + __entry->cong_cwnd = call->cong_cwnd; + __entry->cong_extra = call->cong_extra; + __entry->prepared = send_top - call->tx_bottom; + __entry->in_flight = call->tx_top - call->tx_bottom; + __entry->pmtud_jumbo = call->peer->pmtud_jumbo; + ), + + TP_printk("c=%08x q=%08x sp=%u tw=%u cw=%u+%u pr=%u if=%u pj=%u", + __entry->call, + __entry->seq, + __entry->space, + __entry->tx_winsize, + __entry->cong_cwnd, + __entry->cong_extra, + __entry->prepared, + __entry->in_flight, + __entry->pmtud_jumbo) + ); + +TRACE_EVENT(rxrpc_tx_rotate, + TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, rxrpc_seq_t to), + + TP_ARGS(call, seq, to), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_seq_t, seq) + __field(rxrpc_seq_t, to) + __field(rxrpc_seq_t, top) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->seq = seq; + __entry->to = to; + __entry->top = call->tx_top; + ), + + TP_printk("c=%08x q=%08x-%08x-%08x", + __entry->call, + __entry->seq, + __entry->to, + __entry->top) + ); + TRACE_EVENT(rxrpc_rx_data, TP_PROTO(unsigned int call, rxrpc_seq_t seq, rxrpc_serial_t serial, u8 flags), @@ -921,11 +1065,9 @@ TRACE_EVENT(rxrpc_rx_data, ); TRACE_EVENT(rxrpc_rx_ack, - TP_PROTO(struct rxrpc_call *call, - rxrpc_serial_t serial, rxrpc_serial_t ack_serial, - rxrpc_seq_t first, rxrpc_seq_t prev, u8 reason, u8 n_acks), + TP_PROTO(struct rxrpc_call *call, struct rxrpc_skb_priv *sp), - TP_ARGS(call, serial, ack_serial, first, prev, reason, n_acks), + TP_ARGS(call, sp), TP_STRUCT__entry( __field(unsigned int, call) @@ -935,23 +1077,26 @@ TRACE_EVENT(rxrpc_rx_ack, __field(rxrpc_seq_t, prev) __field(u8, reason) __field(u8, n_acks) + __field(u8, user_status) ), TP_fast_assign( - __entry->call = call->debug_id; - __entry->serial = serial; - __entry->ack_serial = ack_serial; - __entry->first = first; - __entry->prev = prev; - __entry->reason = reason; - __entry->n_acks = n_acks; + __entry->call = call->debug_id; + __entry->serial = sp->hdr.serial; + __entry->user_status = sp->hdr.userStatus; + __entry->ack_serial = sp->ack.acked_serial; + __entry->first = sp->ack.first_ack; + __entry->prev = sp->ack.prev_ack; + __entry->reason = sp->ack.reason; + __entry->n_acks = sp->ack.nr_acks; ), - TP_printk("c=%08x %08x %s r=%08x f=%08x p=%08x n=%u", + TP_printk("c=%08x %08x %s r=%08x us=%02x f=%08x p=%08x n=%u", __entry->call, __entry->serial, __print_symbolic(__entry->reason, rxrpc_ack_names), __entry->ack_serial, + __entry->user_status, __entry->first, __entry->prev, __entry->n_acks) @@ -981,6 +1126,29 @@ TRACE_EVENT(rxrpc_rx_abort, __entry->abort_code) ); +TRACE_EVENT(rxrpc_rx_conn_abort, + TP_PROTO(const struct rxrpc_connection *conn, const struct sk_buff *skb), + + TP_ARGS(conn, skb), + + TP_STRUCT__entry( + __field(unsigned int, conn) + __field(rxrpc_serial_t, serial) + __field(u32, abort_code) + ), + + TP_fast_assign( + __entry->conn = conn->debug_id; + __entry->serial = rxrpc_skb(skb)->hdr.serial; + __entry->abort_code = skb->priority; + ), + + TP_printk("C=%08x ABORT %08x ac=%d", + __entry->conn, + __entry->serial, + __entry->abort_code) + ); + TRACE_EVENT(rxrpc_rx_challenge, TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t serial, u32 version, u32 nonce, u32 min_level), @@ -1102,9 +1270,10 @@ TRACE_EVENT(rxrpc_tx_packet, TRACE_EVENT(rxrpc_tx_data, TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, - rxrpc_serial_t serial, unsigned int flags, bool lose), + rxrpc_serial_t serial, unsigned int flags, + enum rxrpc_txdata_trace trace), - TP_ARGS(call, seq, serial, flags, lose), + TP_ARGS(call, seq, serial, flags, trace), TP_STRUCT__entry( __field(unsigned int, call) @@ -1113,7 +1282,7 @@ TRACE_EVENT(rxrpc_tx_data, __field(u32, cid) __field(u32, call_id) __field(u16, flags) - __field(bool, lose) + __field(enum rxrpc_txdata_trace, trace) ), TP_fast_assign( @@ -1123,26 +1292,26 @@ TRACE_EVENT(rxrpc_tx_data, __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; - __entry->lose = lose; + __entry->trace = trace; ), - TP_printk("c=%08x DATA %08x:%08x %08x q=%08x fl=%02x%s%s", + TP_printk("c=%08x DATA %08x:%08x %08x q=%08x fl=%02x%s", __entry->call, __entry->cid, __entry->call_id, __entry->serial, __entry->seq, __entry->flags & RXRPC_TXBUF_WIRE_FLAGS, - __entry->flags & RXRPC_TXBUF_RESENT ? " *RETRANS*" : "", - __entry->lose ? " *LOSE*" : "") + __print_symbolic(__entry->trace, rxrpc_txdata_traces)) ); TRACE_EVENT(rxrpc_tx_ack, TP_PROTO(unsigned int call, rxrpc_serial_t serial, rxrpc_seq_t ack_first, rxrpc_serial_t ack_serial, - u8 reason, u8 n_acks, u16 rwind), + u8 reason, u8 n_acks, u16 rwind, + enum rxrpc_propose_ack_trace trace), - TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks, rwind), + TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks, rwind, trace), TP_STRUCT__entry( __field(unsigned int, call) @@ -1152,6 +1321,7 @@ TRACE_EVENT(rxrpc_tx_ack, __field(u8, reason) __field(u8, n_acks) __field(u16, rwind) + __field(enum rxrpc_propose_ack_trace, trace) ), TP_fast_assign( @@ -1162,16 +1332,18 @@ TRACE_EVENT(rxrpc_tx_ack, __entry->reason = reason; __entry->n_acks = n_acks; __entry->rwind = rwind; + __entry->trace = trace; ), - TP_printk(" c=%08x ACK %08x %s f=%08x r=%08x n=%u rw=%u", + TP_printk(" c=%08x ACK %08x %s f=%08x r=%08x n=%u rw=%u %s", __entry->call, __entry->serial, __print_symbolic(__entry->reason, rxrpc_ack_names), __entry->ack_first, __entry->ack_serial, __entry->n_acks, - __entry->rwind) + __entry->rwind, + __print_symbolic(__entry->trace, rxrpc_propose_ack_traces)) ); TRACE_EVENT(rxrpc_receive, @@ -1296,9 +1468,9 @@ TRACE_EVENT(rxrpc_rtt_rx, TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, int slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, - u32 rtt, u32 rto), + u32 rtt, u32 srtt, u32 rto), - TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, rto), + TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, srtt, rto), TP_STRUCT__entry( __field(unsigned int, call) @@ -1307,7 +1479,9 @@ TRACE_EVENT(rxrpc_rtt_rx, __field(rxrpc_serial_t, send_serial) __field(rxrpc_serial_t, resp_serial) __field(u32, rtt) + __field(u32, srtt) __field(u32, rto) + __field(u32, min_rtt) ), TP_fast_assign( @@ -1317,17 +1491,21 @@ TRACE_EVENT(rxrpc_rtt_rx, __entry->send_serial = send_serial; __entry->resp_serial = resp_serial; __entry->rtt = rtt; + __entry->srtt = srtt; __entry->rto = rto; + __entry->min_rtt = minmax_get(&call->min_rtt) ), - TP_printk("c=%08x [%d] %s sr=%08x rr=%08x rtt=%u rto=%u", + TP_printk("c=%08x [%d] %s sr=%08x rr=%08x rtt=%u srtt=%u rto=%u min=%u", __entry->call, __entry->slot, __print_symbolic(__entry->why, rxrpc_rtt_rx_traces), __entry->send_serial, __entry->resp_serial, __entry->rtt, - __entry->rto) + __entry->srtt / 8, + __entry->rto, + __entry->min_rtt) ); TRACE_EVENT(rxrpc_timer_set, @@ -1544,112 +1722,125 @@ TRACE_EVENT(rxrpc_drop_ack, ); TRACE_EVENT(rxrpc_retransmit, - TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, - rxrpc_serial_t serial, ktime_t expiry), + TP_PROTO(struct rxrpc_call *call, + struct rxrpc_send_data_req *req, + struct rxrpc_txbuf *txb), - TP_ARGS(call, seq, serial, expiry), + TP_ARGS(call, req, txb), TP_STRUCT__entry( __field(unsigned int, call) + __field(unsigned int, qbase) __field(rxrpc_seq_t, seq) __field(rxrpc_serial_t, serial) - __field(ktime_t, expiry) ), TP_fast_assign( __entry->call = call->debug_id; - __entry->seq = seq; - __entry->serial = serial; - __entry->expiry = expiry; + __entry->qbase = req->tq->qbase; + __entry->seq = req->seq; + __entry->serial = txb->serial; ), - TP_printk("c=%08x q=%x r=%x xp=%lld", + TP_printk("c=%08x tq=%x q=%x r=%x", __entry->call, + __entry->qbase, __entry->seq, - __entry->serial, - ktime_to_us(__entry->expiry)) + __entry->serial) ); TRACE_EVENT(rxrpc_congest, - TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary, - rxrpc_serial_t ack_serial, enum rxrpc_congest_change change), + TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary), - TP_ARGS(call, summary, ack_serial, change), + TP_ARGS(call, summary), TP_STRUCT__entry( __field(unsigned int, call) - __field(enum rxrpc_congest_change, change) + __field(enum rxrpc_ca_state, ca_state) __field(rxrpc_seq_t, hard_ack) __field(rxrpc_seq_t, top) __field(rxrpc_seq_t, lowest_nak) - __field(rxrpc_serial_t, ack_serial) + __field(u16, nr_sacks) + __field(u16, nr_snacks) + __field(u16, cwnd) + __field(u16, ssthresh) + __field(u16, cumul_acks) + __field(u16, dup_acks) __field_struct(struct rxrpc_ack_summary, sum) ), TP_fast_assign( __entry->call = call->debug_id; - __entry->change = change; + __entry->ca_state = call->cong_ca_state; __entry->hard_ack = call->acks_hard_ack; __entry->top = call->tx_top; __entry->lowest_nak = call->acks_lowest_nak; - __entry->ack_serial = ack_serial; + __entry->nr_sacks = call->acks_nr_sacks; + __entry->nr_snacks = call->acks_nr_snacks; + __entry->cwnd = call->cong_cwnd; + __entry->ssthresh = call->cong_ssthresh; + __entry->cumul_acks = call->cong_cumul_acks; + __entry->dup_acks = call->cong_dup_acks; memcpy(&__entry->sum, summary, sizeof(__entry->sum)); ), - TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u,%u b=%u u=%u d=%u l=%x%s%s%s", + TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u A=%u+%u/%u+%u r=%u b=%u u=%u d=%u l=%x%s%s%s", __entry->call, - __entry->ack_serial, + __entry->sum.acked_serial, __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names), __entry->hard_ack, - __print_symbolic(__entry->sum.mode, rxrpc_congest_modes), - __entry->sum.cwnd, - __entry->sum.ssthresh, - __entry->sum.nr_acks, __entry->sum.nr_retained_nacks, - __entry->sum.nr_new_acks, - __entry->sum.nr_new_nacks, + __print_symbolic(__entry->ca_state, rxrpc_ca_states), + __entry->cwnd, + __entry->ssthresh, + __entry->nr_sacks, __entry->sum.nr_new_sacks, + __entry->nr_snacks, __entry->sum.nr_new_snacks, + __entry->sum.nr_new_hacks, __entry->top - __entry->hard_ack, - __entry->sum.cumulative_acks, - __entry->sum.dup_acks, - __entry->lowest_nak, __entry->sum.new_low_nack ? "!" : "", - __print_symbolic(__entry->change, rxrpc_congest_changes), + __entry->cumul_acks, + __entry->dup_acks, + __entry->lowest_nak, __entry->sum.new_low_snack ? "!" : "", + __print_symbolic(__entry->sum.change, rxrpc_congest_changes), __entry->sum.retrans_timeo ? " rTxTo" : "") ); TRACE_EVENT(rxrpc_reset_cwnd, - TP_PROTO(struct rxrpc_call *call, ktime_t now), + TP_PROTO(struct rxrpc_call *call, ktime_t since_last_tx, ktime_t rtt), - TP_ARGS(call, now), + TP_ARGS(call, since_last_tx, rtt), TP_STRUCT__entry( __field(unsigned int, call) - __field(enum rxrpc_congest_mode, mode) + __field(enum rxrpc_ca_state, ca_state) __field(unsigned short, cwnd) __field(unsigned short, extra) __field(rxrpc_seq_t, hard_ack) __field(rxrpc_seq_t, prepared) __field(ktime_t, since_last_tx) + __field(ktime_t, rtt) __field(bool, has_data) ), TP_fast_assign( __entry->call = call->debug_id; - __entry->mode = call->cong_mode; + __entry->ca_state = call->cong_ca_state; __entry->cwnd = call->cong_cwnd; __entry->extra = call->cong_extra; __entry->hard_ack = call->acks_hard_ack; - __entry->prepared = call->tx_prepared - call->tx_bottom; - __entry->since_last_tx = ktime_sub(now, call->tx_last_sent); - __entry->has_data = !list_empty(&call->tx_sendmsg); + __entry->prepared = call->send_top - call->tx_bottom; + __entry->since_last_tx = since_last_tx; + __entry->rtt = rtt; + __entry->has_data = call->tx_bottom != call->tx_top; ), - TP_printk("c=%08x q=%08x %s cw=%u+%u pr=%u tm=%llu d=%u", + TP_printk("c=%08x q=%08x %s cw=%u+%u pr=%u tm=%llu/%llu d=%u", __entry->call, __entry->hard_ack, - __print_symbolic(__entry->mode, rxrpc_congest_modes), + __print_symbolic(__entry->ca_state, rxrpc_ca_states), __entry->cwnd, __entry->extra, __entry->prepared, - ktime_to_ns(__entry->since_last_tx), + ktime_to_us(__entry->since_last_tx), + ktime_to_us(__entry->rtt), __entry->has_data) ); @@ -1722,10 +1913,36 @@ TRACE_EVENT(rxrpc_connect_call, &__entry->srx.transport) ); -TRACE_EVENT(rxrpc_resend, - TP_PROTO(struct rxrpc_call *call, struct sk_buff *ack), +TRACE_EVENT(rxrpc_apply_acks, + TP_PROTO(struct rxrpc_call *call, struct rxrpc_txqueue *tq), - TP_ARGS(call, ack), + TP_ARGS(call, tq), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(unsigned int, nr_rep) + __field(rxrpc_seq_t, qbase) + __field(unsigned long, acks) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->qbase = tq->qbase; + __entry->acks = tq->segment_acked; + __entry->nr_rep = tq->nr_reported_acks; + ), + + TP_printk("c=%08x tq=%x acks=%016lx rep=%u", + __entry->call, + __entry->qbase, + __entry->acks, + __entry->nr_rep) + ); + +TRACE_EVENT(rxrpc_resend, + TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t ack_serial), + + TP_ARGS(call, ack_serial), TP_STRUCT__entry( __field(unsigned int, call) @@ -1735,11 +1952,10 @@ TRACE_EVENT(rxrpc_resend, ), TP_fast_assign( - struct rxrpc_skb_priv *sp = ack ? rxrpc_skb(ack) : NULL; __entry->call = call->debug_id; __entry->seq = call->acks_hard_ack; __entry->transmitted = call->tx_transmitted; - __entry->ack_serial = sp ? sp->hdr.serial : 0; + __entry->ack_serial = ack_serial; ), TP_printk("c=%08x r=%x q=%x tq=%x", @@ -1749,6 +1965,63 @@ TRACE_EVENT(rxrpc_resend, __entry->transmitted) ); +TRACE_EVENT(rxrpc_resend_lost, + TP_PROTO(struct rxrpc_call *call, struct rxrpc_txqueue *tq, unsigned long lost), + + TP_ARGS(call, tq, lost), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_seq_t, qbase) + __field(u8, nr_rep) + __field(unsigned long, lost) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->qbase = tq->qbase; + __entry->nr_rep = tq->nr_reported_acks; + __entry->lost = lost; + ), + + TP_printk("c=%08x tq=%x lost=%016lx nr=%u", + __entry->call, + __entry->qbase, + __entry->lost, + __entry->nr_rep) + ); + +TRACE_EVENT(rxrpc_rotate, + TP_PROTO(struct rxrpc_call *call, struct rxrpc_txqueue *tq, + struct rxrpc_ack_summary *summary, rxrpc_seq_t seq, + enum rxrpc_rotate_trace trace), + + TP_ARGS(call, tq, summary, seq, trace), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_seq_t, qbase) + __field(rxrpc_seq_t, seq) + __field(unsigned int, nr_rep) + __field(enum rxrpc_rotate_trace, trace) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->qbase = tq->qbase; + __entry->seq = seq; + __entry->nr_rep = tq->nr_reported_acks; + __entry->trace = trace; + ), + + TP_printk("c=%08x tq=%x q=%x nr=%x %s", + __entry->call, + __entry->qbase, + __entry->seq, + __entry->nr_rep, + __print_symbolic(__entry->trace, rxrpc_rotate_traces)) + ); + TRACE_EVENT(rxrpc_rx_icmp, TP_PROTO(struct rxrpc_peer *peer, struct sock_extended_err *ee, struct sockaddr_rxrpc *srx), @@ -1858,38 +2131,36 @@ TRACE_EVENT(rxrpc_notify_socket, ); TRACE_EVENT(rxrpc_rx_discard_ack, - TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial, - rxrpc_seq_t first_soft_ack, rxrpc_seq_t call_ackr_first, - rxrpc_seq_t prev_pkt, rxrpc_seq_t call_ackr_prev), + TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial, + rxrpc_seq_t hard_ack, rxrpc_seq_t prev_pkt), - TP_ARGS(debug_id, serial, first_soft_ack, call_ackr_first, - prev_pkt, call_ackr_prev), + TP_ARGS(call, serial, hard_ack, prev_pkt), TP_STRUCT__entry( __field(unsigned int, debug_id) __field(rxrpc_serial_t, serial) - __field(rxrpc_seq_t, first_soft_ack) - __field(rxrpc_seq_t, call_ackr_first) + __field(rxrpc_seq_t, hard_ack) __field(rxrpc_seq_t, prev_pkt) - __field(rxrpc_seq_t, call_ackr_prev) + __field(rxrpc_seq_t, acks_hard_ack) + __field(rxrpc_seq_t, acks_prev_seq) ), TP_fast_assign( - __entry->debug_id = debug_id; + __entry->debug_id = call->debug_id; __entry->serial = serial; - __entry->first_soft_ack = first_soft_ack; - __entry->call_ackr_first = call_ackr_first; + __entry->hard_ack = hard_ack; __entry->prev_pkt = prev_pkt; - __entry->call_ackr_prev = call_ackr_prev; + __entry->acks_hard_ack = call->acks_hard_ack; + __entry->acks_prev_seq = call->acks_prev_seq; ), TP_printk("c=%08x r=%08x %08x<%08x %08x<%08x", __entry->debug_id, __entry->serial, - __entry->first_soft_ack, - __entry->call_ackr_first, + __entry->hard_ack, + __entry->acks_hard_ack, __entry->prev_pkt, - __entry->call_ackr_prev) + __entry->acks_prev_seq) ); TRACE_EVENT(rxrpc_req_ack, @@ -1947,6 +2218,33 @@ TRACE_EVENT(rxrpc_txbuf, __entry->ref) ); +TRACE_EVENT(rxrpc_tq, + TP_PROTO(struct rxrpc_call *call, struct rxrpc_txqueue *tq, + rxrpc_seq_t seq, enum rxrpc_tq_trace trace), + + TP_ARGS(call, tq, seq, trace), + + TP_STRUCT__entry( + __field(unsigned int, call_debug_id) + __field(rxrpc_seq_t, qbase) + __field(rxrpc_seq_t, seq) + __field(enum rxrpc_tq_trace, trace) + ), + + TP_fast_assign( + __entry->call_debug_id = call->debug_id; + __entry->qbase = tq ? tq->qbase : call->tx_qbase; + __entry->seq = seq; + __entry->trace = trace; + ), + + TP_printk("c=%08x bq=%08x q=%08x %s", + __entry->call_debug_id, + __entry->qbase, + __entry->seq, + __print_symbolic(__entry->trace, rxrpc_tq_traces)) + ); + TRACE_EVENT(rxrpc_poke_call, TP_PROTO(struct rxrpc_call *call, bool busy, enum rxrpc_call_poke_trace what), @@ -2015,6 +2313,360 @@ TRACE_EVENT(rxrpc_sack, __entry->sack) ); +TRACE_EVENT(rxrpc_pmtud_tx, + TP_PROTO(struct rxrpc_call *call), + + TP_ARGS(call), + + TP_STRUCT__entry( + __field(unsigned int, peer_debug_id) + __field(unsigned int, call_debug_id) + __field(rxrpc_serial_t, ping_serial) + __field(unsigned short, pmtud_trial) + __field(unsigned short, pmtud_good) + __field(unsigned short, pmtud_bad) + ), + + TP_fast_assign( + __entry->peer_debug_id = call->peer->debug_id; + __entry->call_debug_id = call->debug_id; + __entry->ping_serial = call->conn->pmtud_probe; + __entry->pmtud_trial = call->peer->pmtud_trial; + __entry->pmtud_good = call->peer->pmtud_good; + __entry->pmtud_bad = call->peer->pmtud_bad; + ), + + TP_printk("P=%08x c=%08x pr=%08x %u-%u-%u", + __entry->peer_debug_id, + __entry->call_debug_id, + __entry->ping_serial, + __entry->pmtud_good, + __entry->pmtud_trial, + __entry->pmtud_bad) + ); + +TRACE_EVENT(rxrpc_pmtud_rx, + TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t resp_serial), + + TP_ARGS(conn, resp_serial), + + TP_STRUCT__entry( + __field(unsigned int, peer_debug_id) + __field(unsigned int, call_debug_id) + __field(rxrpc_serial_t, ping_serial) + __field(rxrpc_serial_t, resp_serial) + __field(unsigned short, max_data) + __field(u8, jumbo_max) + ), + + TP_fast_assign( + __entry->peer_debug_id = conn->peer->debug_id; + __entry->call_debug_id = conn->pmtud_call; + __entry->ping_serial = conn->pmtud_probe; + __entry->resp_serial = resp_serial; + __entry->max_data = conn->peer->max_data; + __entry->jumbo_max = conn->peer->pmtud_jumbo; + ), + + TP_printk("P=%08x c=%08x pr=%08x rr=%08x max=%u jm=%u", + __entry->peer_debug_id, + __entry->call_debug_id, + __entry->ping_serial, + __entry->resp_serial, + __entry->max_data, + __entry->jumbo_max) + ); + +TRACE_EVENT(rxrpc_pmtud_lost, + TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t resp_serial), + + TP_ARGS(conn, resp_serial), + + TP_STRUCT__entry( + __field(unsigned int, peer_debug_id) + __field(unsigned int, call_debug_id) + __field(rxrpc_serial_t, ping_serial) + __field(rxrpc_serial_t, resp_serial) + ), + + TP_fast_assign( + __entry->peer_debug_id = conn->peer->debug_id; + __entry->call_debug_id = conn->pmtud_call; + __entry->ping_serial = conn->pmtud_probe; + __entry->resp_serial = resp_serial; + ), + + TP_printk("P=%08x c=%08x pr=%08x rr=%08x", + __entry->peer_debug_id, + __entry->call_debug_id, + __entry->ping_serial, + __entry->resp_serial) + ); + +TRACE_EVENT(rxrpc_pmtud_reduce, + TP_PROTO(struct rxrpc_peer *peer, rxrpc_serial_t serial, + unsigned int max_data, enum rxrpc_pmtud_reduce_trace reason), + + TP_ARGS(peer, serial, max_data, reason), + + TP_STRUCT__entry( + __field(unsigned int, peer_debug_id) + __field(rxrpc_serial_t, serial) + __field(unsigned int, max_data) + __field(enum rxrpc_pmtud_reduce_trace, reason) + ), + + TP_fast_assign( + __entry->peer_debug_id = peer->debug_id; + __entry->serial = serial; + __entry->max_data = max_data; + __entry->reason = reason; + ), + + TP_printk("P=%08x %s r=%08x m=%u", + __entry->peer_debug_id, + __print_symbolic(__entry->reason, rxrpc_pmtud_reduce_traces), + __entry->serial, __entry->max_data) + ); + +TRACE_EVENT(rxrpc_rack, + TP_PROTO(struct rxrpc_call *call, ktime_t timo), + + TP_ARGS(call, timo), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_serial_t, ack_serial) + __field(rxrpc_seq_t, seq) + __field(enum rxrpc_rack_timer_mode, mode) + __field(unsigned short, nr_sent) + __field(unsigned short, nr_lost) + __field(unsigned short, nr_resent) + __field(unsigned short, nr_sacked) + __field(ktime_t, timo) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->ack_serial = call->rx_serial; + __entry->seq = call->rack_end_seq; + __entry->mode = call->rack_timer_mode; + __entry->nr_sent = call->tx_nr_sent; + __entry->nr_lost = call->tx_nr_lost; + __entry->nr_resent = call->tx_nr_resent; + __entry->nr_sacked = call->acks_nr_sacks; + __entry->timo = timo; + ), + + TP_printk("c=%08x r=%08x q=%08x %s slrs=%u,%u,%u,%u t=%lld", + __entry->call, __entry->ack_serial, __entry->seq, + __print_symbolic(__entry->mode, rxrpc_rack_timer_modes), + __entry->nr_sent, __entry->nr_lost, + __entry->nr_resent, __entry->nr_sacked, + ktime_to_us(__entry->timo)) + ); + +TRACE_EVENT(rxrpc_rack_update, + TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary), + + TP_ARGS(call, summary), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_serial_t, ack_serial) + __field(rxrpc_seq_t, seq) + __field(int, xmit_ts) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->ack_serial = call->rx_serial; + __entry->seq = call->rack_end_seq; + __entry->xmit_ts = ktime_sub(call->acks_latest_ts, call->rack_xmit_ts); + ), + + TP_printk("c=%08x r=%08x q=%08x xt=%lld", + __entry->call, __entry->ack_serial, __entry->seq, + ktime_to_us(__entry->xmit_ts)) + ); + +TRACE_EVENT(rxrpc_rack_scan_loss, + TP_PROTO(struct rxrpc_call *call), + + TP_ARGS(call), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(ktime_t, rack_rtt) + __field(ktime_t, rack_reo_wnd) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->rack_rtt = call->rack_rtt; + __entry->rack_reo_wnd = call->rack_reo_wnd; + ), + + TP_printk("c=%08x rtt=%lld reow=%lld", + __entry->call, ktime_to_us(__entry->rack_rtt), + ktime_to_us(__entry->rack_reo_wnd)) + ); + +TRACE_EVENT(rxrpc_rack_scan_loss_tq, + TP_PROTO(struct rxrpc_call *call, const struct rxrpc_txqueue *tq, + unsigned long nacks), + + TP_ARGS(call, tq, nacks), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_seq_t, qbase) + __field(unsigned long, nacks) + __field(unsigned long, lost) + __field(unsigned long, retrans) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->qbase = tq->qbase; + __entry->nacks = nacks; + __entry->lost = tq->segment_lost; + __entry->retrans = tq->segment_retransmitted; + ), + + TP_printk("c=%08x q=%08x n=%lx l=%lx r=%lx", + __entry->call, __entry->qbase, + __entry->nacks, __entry->lost, __entry->retrans) + ); + +TRACE_EVENT(rxrpc_rack_detect_loss, + TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary, + rxrpc_seq_t seq), + + TP_ARGS(call, summary, seq), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_serial_t, ack_serial) + __field(rxrpc_seq_t, seq) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->ack_serial = call->rx_serial; + __entry->seq = seq; + ), + + TP_printk("c=%08x r=%08x q=%08x", + __entry->call, __entry->ack_serial, __entry->seq) + ); + +TRACE_EVENT(rxrpc_rack_mark_loss_tq, + TP_PROTO(struct rxrpc_call *call, const struct rxrpc_txqueue *tq), + + TP_ARGS(call, tq), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_seq_t, qbase) + __field(rxrpc_seq_t, trans) + __field(unsigned long, acked) + __field(unsigned long, lost) + __field(unsigned long, retrans) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->qbase = tq->qbase; + __entry->trans = call->tx_transmitted; + __entry->acked = tq->segment_acked; + __entry->lost = tq->segment_lost; + __entry->retrans = tq->segment_retransmitted; + ), + + TP_printk("c=%08x tq=%08x txq=%08x a=%lx l=%lx r=%lx", + __entry->call, __entry->qbase, __entry->trans, + __entry->acked, __entry->lost, __entry->retrans) + ); + +TRACE_EVENT(rxrpc_tlp_probe, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_tlp_probe_trace trace), + + TP_ARGS(call, trace), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_serial_t, serial) + __field(rxrpc_seq_t, seq) + __field(enum rxrpc_tlp_probe_trace, trace) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->serial = call->tlp_serial; + __entry->seq = call->tlp_seq; + __entry->trace = trace; + ), + + TP_printk("c=%08x r=%08x pq=%08x %s", + __entry->call, __entry->serial, __entry->seq, + __print_symbolic(__entry->trace, rxrpc_tlp_probe_traces)) + ); + +TRACE_EVENT(rxrpc_tlp_ack, + TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary, + enum rxrpc_tlp_ack_trace trace), + + TP_ARGS(call, summary, trace), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(rxrpc_serial_t, serial) + __field(rxrpc_seq_t, tlp_seq) + __field(rxrpc_seq_t, hard_ack) + __field(enum rxrpc_tlp_ack_trace, trace) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->serial = call->tlp_serial; + __entry->tlp_seq = call->tlp_seq; + __entry->hard_ack = call->acks_hard_ack; + __entry->trace = trace; + ), + + TP_printk("c=%08x r=%08x pq=%08x hq=%08x %s", + __entry->call, __entry->serial, + __entry->tlp_seq, __entry->hard_ack, + __print_symbolic(__entry->trace, rxrpc_tlp_ack_traces)) + ); + +TRACE_EVENT(rxrpc_rack_timer, + TP_PROTO(struct rxrpc_call *call, ktime_t delay, bool exp), + + TP_ARGS(call, delay, exp), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(bool, exp) + __field(enum rxrpc_rack_timer_mode, mode) + __field(ktime_t, delay) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->exp = exp; + __entry->mode = call->rack_timer_mode; + __entry->delay = delay; + ), + + TP_printk("c=%08x %s %s to=%lld", + __entry->call, + __entry->exp ? "Exp" : "Set", + __print_symbolic(__entry->mode, rxrpc_rack_timer_modes), + ktime_to_us(__entry->delay)) + ); + #undef EM #undef E_ diff --git a/include/trace/events/task.h b/include/trace/events/task.h index 47b527464d1a..af535b053033 100644 --- a/include/trace/events/task.h +++ b/include/trace/events/task.h @@ -38,22 +38,56 @@ TRACE_EVENT(task_rename, TP_ARGS(task, comm), TP_STRUCT__entry( - __field( pid_t, pid) __array( char, oldcomm, TASK_COMM_LEN) __array( char, newcomm, TASK_COMM_LEN) __field( short, oom_score_adj) ), TP_fast_assign( - __entry->pid = task->pid; memcpy(entry->oldcomm, task->comm, TASK_COMM_LEN); strscpy(entry->newcomm, comm, TASK_COMM_LEN); __entry->oom_score_adj = task->signal->oom_score_adj; ), - TP_printk("pid=%d oldcomm=%s newcomm=%s oom_score_adj=%hd", - __entry->pid, __entry->oldcomm, - __entry->newcomm, __entry->oom_score_adj) + TP_printk("oldcomm=%s newcomm=%s oom_score_adj=%hd", + __entry->oldcomm, __entry->newcomm, __entry->oom_score_adj) +); + +/** + * task_prctl_unknown - called on unknown prctl() option + * @option: option passed + * @arg2: arg2 passed + * @arg3: arg3 passed + * @arg4: arg4 passed + * @arg5: arg5 passed + * + * Called on an unknown prctl() option. + */ +TRACE_EVENT(task_prctl_unknown, + + TP_PROTO(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5), + + TP_ARGS(option, arg2, arg3, arg4, arg5), + + TP_STRUCT__entry( + __field( int, option) + __field( unsigned long, arg2) + __field( unsigned long, arg3) + __field( unsigned long, arg4) + __field( unsigned long, arg5) + ), + + TP_fast_assign( + __entry->option = option; + __entry->arg2 = arg2; + __entry->arg3 = arg3; + __entry->arg4 = arg4; + __entry->arg5 = arg5; + ), + + TP_printk("option=%d arg2=%ld arg3=%ld arg4=%ld arg5=%ld", + __entry->option, __entry->arg2, __entry->arg3, __entry->arg4, __entry->arg5) ); #endif diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 80f37a0d40d7..613475285643 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -6,7 +6,6 @@ /* * FMODE_EXEC is 0x20 - * FMODE_NONOTIFY is 0x4000000 * These cannot be used by userspace O_* until internal and external open * flags are split. * -Eric Paris diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index deacfd6dd197..aa5016ff3d91 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -143,6 +143,8 @@ #define SCM_TS_OPT_ID 81 +#define SO_RCVPRIORITY 82 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index b916aab80dde..2342cb90857e 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -90,6 +90,7 @@ struct drm_msm_timespec { #define MSM_PARAM_RAYTRACING 0x11 /* RO */ #define MSM_PARAM_UBWC_SWIZZLE 0x12 /* RO */ #define MSM_PARAM_MACROTILE_MODE 0x13 /* RO */ +#define MSM_PARAM_UCHE_TRAP_BASE 0x14 /* RO */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 0383b52cbd86..f62689ca861a 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -1487,6 +1487,7 @@ struct drm_xe_oa_unit { #define DRM_XE_OA_CAPS_BASE (1 << 0) #define DRM_XE_OA_CAPS_SYNCS (1 << 1) #define DRM_XE_OA_CAPS_OA_BUFFER_SIZE (1 << 2) +#define DRM_XE_OA_CAPS_WAIT_NUM_REPORTS (1 << 3) /** @oa_timestamp_freq: OA timestamp freq */ __u64 oa_timestamp_freq; @@ -1660,6 +1661,12 @@ enum drm_xe_oa_property_id { * buffer is allocated by default. */ DRM_XE_OA_PROPERTY_OA_BUFFER_SIZE, + + /** + * @DRM_XE_OA_PROPERTY_WAIT_NUM_REPORTS: Number of reports to wait + * for before unblocking poll or read + */ + DRM_XE_OA_PROPERTY_WAIT_NUM_REPORTS, }; /** diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 75e21a135483..d9a069b4a775 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -161,6 +161,7 @@ #define AUDIT_INTEGRITY_RULE 1805 /* policy rule */ #define AUDIT_INTEGRITY_EVM_XATTR 1806 /* New EVM-covered xattr */ #define AUDIT_INTEGRITY_POLICY_RULE 1807 /* IMA policy rules */ +#define AUDIT_INTEGRITY_USERSPACE 1808 /* Userspace enforced data integrity */ #define AUDIT_KERNEL 2000 /* Asynchronous audit record. NOT A REQUEST. */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4162afc6b5d0..2acf9b336371 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1573,6 +1573,16 @@ union bpf_attr { * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. */ __s32 prog_token_fd; + /* The fd_array_cnt can be used to pass the length of the + * fd_array array. In this case all the [map] file descriptors + * passed in this array will be bound to the program, even if + * the maps are not referenced directly. The functionality is + * similar to the BPF_PROG_BIND_MAP syscall, but maps can be + * used by the verifier during the program load. If provided, + * then the fd_array[0,...,fd_array_cnt-1] is expected to be + * continuous. + */ + __u32 fd_array_cnt; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 1990b5700f69..b08c7378164d 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -286,9 +286,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 48 +#define DM_VERSION_MINOR 49 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2023-03-01)" +#define DM_VERSION_EXTRA "-ioctl (2025-01-17)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 7e1b3820f91f..d1089b88efc7 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -681,6 +681,7 @@ enum ethtool_link_ext_substate_module { * @ETH_SS_STATS_ETH_MAC: names of IEEE 802.3 MAC statistics * @ETH_SS_STATS_ETH_CTRL: names of IEEE 802.3 MAC Control statistics * @ETH_SS_STATS_RMON: names of RMON statistics + * @ETH_SS_STATS_PHY: names of PHY(dev) statistics * * @ETH_SS_COUNT: number of defined string sets */ @@ -706,6 +707,7 @@ enum ethtool_stringset { ETH_SS_STATS_ETH_MAC, ETH_SS_STATS_ETH_CTRL, ETH_SS_STATS_RMON, + ETH_SS_STATS_PHY, /* add new constants above here */ ETH_SS_COUNT diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 283305f6b063..9ff72cfb2e98 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -10,545 +10,12 @@ #define _UAPI_LINUX_ETHTOOL_NETLINK_H_ #include - -/* message types - userspace to kernel */ -enum { - ETHTOOL_MSG_USER_NONE, - ETHTOOL_MSG_STRSET_GET, - ETHTOOL_MSG_LINKINFO_GET, - ETHTOOL_MSG_LINKINFO_SET, - ETHTOOL_MSG_LINKMODES_GET, - ETHTOOL_MSG_LINKMODES_SET, - ETHTOOL_MSG_LINKSTATE_GET, - ETHTOOL_MSG_DEBUG_GET, - ETHTOOL_MSG_DEBUG_SET, - ETHTOOL_MSG_WOL_GET, - ETHTOOL_MSG_WOL_SET, - ETHTOOL_MSG_FEATURES_GET, - ETHTOOL_MSG_FEATURES_SET, - ETHTOOL_MSG_PRIVFLAGS_GET, - ETHTOOL_MSG_PRIVFLAGS_SET, - ETHTOOL_MSG_RINGS_GET, - ETHTOOL_MSG_RINGS_SET, - ETHTOOL_MSG_CHANNELS_GET, - ETHTOOL_MSG_CHANNELS_SET, - ETHTOOL_MSG_COALESCE_GET, - ETHTOOL_MSG_COALESCE_SET, - ETHTOOL_MSG_PAUSE_GET, - ETHTOOL_MSG_PAUSE_SET, - ETHTOOL_MSG_EEE_GET, - ETHTOOL_MSG_EEE_SET, - ETHTOOL_MSG_TSINFO_GET, - ETHTOOL_MSG_CABLE_TEST_ACT, - ETHTOOL_MSG_CABLE_TEST_TDR_ACT, - ETHTOOL_MSG_TUNNEL_INFO_GET, - ETHTOOL_MSG_FEC_GET, - ETHTOOL_MSG_FEC_SET, - ETHTOOL_MSG_MODULE_EEPROM_GET, - ETHTOOL_MSG_STATS_GET, - ETHTOOL_MSG_PHC_VCLOCKS_GET, - ETHTOOL_MSG_MODULE_GET, - ETHTOOL_MSG_MODULE_SET, - ETHTOOL_MSG_PSE_GET, - ETHTOOL_MSG_PSE_SET, - ETHTOOL_MSG_RSS_GET, - ETHTOOL_MSG_PLCA_GET_CFG, - ETHTOOL_MSG_PLCA_SET_CFG, - ETHTOOL_MSG_PLCA_GET_STATUS, - ETHTOOL_MSG_MM_GET, - ETHTOOL_MSG_MM_SET, - ETHTOOL_MSG_MODULE_FW_FLASH_ACT, - ETHTOOL_MSG_PHY_GET, - - /* add new constants above here */ - __ETHTOOL_MSG_USER_CNT, - ETHTOOL_MSG_USER_MAX = __ETHTOOL_MSG_USER_CNT - 1 -}; - -/* message types - kernel to userspace */ -enum { - ETHTOOL_MSG_KERNEL_NONE, - ETHTOOL_MSG_STRSET_GET_REPLY, - ETHTOOL_MSG_LINKINFO_GET_REPLY, - ETHTOOL_MSG_LINKINFO_NTF, - ETHTOOL_MSG_LINKMODES_GET_REPLY, - ETHTOOL_MSG_LINKMODES_NTF, - ETHTOOL_MSG_LINKSTATE_GET_REPLY, - ETHTOOL_MSG_DEBUG_GET_REPLY, - ETHTOOL_MSG_DEBUG_NTF, - ETHTOOL_MSG_WOL_GET_REPLY, - ETHTOOL_MSG_WOL_NTF, - ETHTOOL_MSG_FEATURES_GET_REPLY, - ETHTOOL_MSG_FEATURES_SET_REPLY, - ETHTOOL_MSG_FEATURES_NTF, - ETHTOOL_MSG_PRIVFLAGS_GET_REPLY, - ETHTOOL_MSG_PRIVFLAGS_NTF, - ETHTOOL_MSG_RINGS_GET_REPLY, - ETHTOOL_MSG_RINGS_NTF, - ETHTOOL_MSG_CHANNELS_GET_REPLY, - ETHTOOL_MSG_CHANNELS_NTF, - ETHTOOL_MSG_COALESCE_GET_REPLY, - ETHTOOL_MSG_COALESCE_NTF, - ETHTOOL_MSG_PAUSE_GET_REPLY, - ETHTOOL_MSG_PAUSE_NTF, - ETHTOOL_MSG_EEE_GET_REPLY, - ETHTOOL_MSG_EEE_NTF, - ETHTOOL_MSG_TSINFO_GET_REPLY, - ETHTOOL_MSG_CABLE_TEST_NTF, - ETHTOOL_MSG_CABLE_TEST_TDR_NTF, - ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY, - ETHTOOL_MSG_FEC_GET_REPLY, - ETHTOOL_MSG_FEC_NTF, - ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY, - ETHTOOL_MSG_STATS_GET_REPLY, - ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, - ETHTOOL_MSG_MODULE_GET_REPLY, - ETHTOOL_MSG_MODULE_NTF, - ETHTOOL_MSG_PSE_GET_REPLY, - ETHTOOL_MSG_RSS_GET_REPLY, - ETHTOOL_MSG_PLCA_GET_CFG_REPLY, - ETHTOOL_MSG_PLCA_GET_STATUS_REPLY, - ETHTOOL_MSG_PLCA_NTF, - ETHTOOL_MSG_MM_GET_REPLY, - ETHTOOL_MSG_MM_NTF, - ETHTOOL_MSG_MODULE_FW_FLASH_NTF, - ETHTOOL_MSG_PHY_GET_REPLY, - ETHTOOL_MSG_PHY_NTF, - - /* add new constants above here */ - __ETHTOOL_MSG_KERNEL_CNT, - ETHTOOL_MSG_KERNEL_MAX = __ETHTOOL_MSG_KERNEL_CNT - 1 -}; - -/* request header */ - -enum ethtool_header_flags { - ETHTOOL_FLAG_COMPACT_BITSETS = 1 << 0, /* use compact bitsets in reply */ - ETHTOOL_FLAG_OMIT_REPLY = 1 << 1, /* provide optional reply for SET or ACT requests */ - ETHTOOL_FLAG_STATS = 1 << 2, /* request statistics, if supported by the driver */ -}; +#include #define ETHTOOL_FLAG_ALL (ETHTOOL_FLAG_COMPACT_BITSETS | \ ETHTOOL_FLAG_OMIT_REPLY | \ ETHTOOL_FLAG_STATS) -enum { - ETHTOOL_A_HEADER_UNSPEC, - ETHTOOL_A_HEADER_DEV_INDEX, /* u32 */ - ETHTOOL_A_HEADER_DEV_NAME, /* string */ - ETHTOOL_A_HEADER_FLAGS, /* u32 - ETHTOOL_FLAG_* */ - ETHTOOL_A_HEADER_PHY_INDEX, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_HEADER_CNT, - ETHTOOL_A_HEADER_MAX = __ETHTOOL_A_HEADER_CNT - 1 -}; - -/* bit sets */ - -enum { - ETHTOOL_A_BITSET_BIT_UNSPEC, - ETHTOOL_A_BITSET_BIT_INDEX, /* u32 */ - ETHTOOL_A_BITSET_BIT_NAME, /* string */ - ETHTOOL_A_BITSET_BIT_VALUE, /* flag */ - - /* add new constants above here */ - __ETHTOOL_A_BITSET_BIT_CNT, - ETHTOOL_A_BITSET_BIT_MAX = __ETHTOOL_A_BITSET_BIT_CNT - 1 -}; - -enum { - ETHTOOL_A_BITSET_BITS_UNSPEC, - ETHTOOL_A_BITSET_BITS_BIT, /* nest - _A_BITSET_BIT_* */ - - /* add new constants above here */ - __ETHTOOL_A_BITSET_BITS_CNT, - ETHTOOL_A_BITSET_BITS_MAX = __ETHTOOL_A_BITSET_BITS_CNT - 1 -}; - -enum { - ETHTOOL_A_BITSET_UNSPEC, - ETHTOOL_A_BITSET_NOMASK, /* flag */ - ETHTOOL_A_BITSET_SIZE, /* u32 */ - ETHTOOL_A_BITSET_BITS, /* nest - _A_BITSET_BITS_* */ - ETHTOOL_A_BITSET_VALUE, /* binary */ - ETHTOOL_A_BITSET_MASK, /* binary */ - - /* add new constants above here */ - __ETHTOOL_A_BITSET_CNT, - ETHTOOL_A_BITSET_MAX = __ETHTOOL_A_BITSET_CNT - 1 -}; - -/* string sets */ - -enum { - ETHTOOL_A_STRING_UNSPEC, - ETHTOOL_A_STRING_INDEX, /* u32 */ - ETHTOOL_A_STRING_VALUE, /* string */ - - /* add new constants above here */ - __ETHTOOL_A_STRING_CNT, - ETHTOOL_A_STRING_MAX = __ETHTOOL_A_STRING_CNT - 1 -}; - -enum { - ETHTOOL_A_STRINGS_UNSPEC, - ETHTOOL_A_STRINGS_STRING, /* nest - _A_STRINGS_* */ - - /* add new constants above here */ - __ETHTOOL_A_STRINGS_CNT, - ETHTOOL_A_STRINGS_MAX = __ETHTOOL_A_STRINGS_CNT - 1 -}; - -enum { - ETHTOOL_A_STRINGSET_UNSPEC, - ETHTOOL_A_STRINGSET_ID, /* u32 */ - ETHTOOL_A_STRINGSET_COUNT, /* u32 */ - ETHTOOL_A_STRINGSET_STRINGS, /* nest - _A_STRINGS_* */ - - /* add new constants above here */ - __ETHTOOL_A_STRINGSET_CNT, - ETHTOOL_A_STRINGSET_MAX = __ETHTOOL_A_STRINGSET_CNT - 1 -}; - -enum { - ETHTOOL_A_STRINGSETS_UNSPEC, - ETHTOOL_A_STRINGSETS_STRINGSET, /* nest - _A_STRINGSET_* */ - - /* add new constants above here */ - __ETHTOOL_A_STRINGSETS_CNT, - ETHTOOL_A_STRINGSETS_MAX = __ETHTOOL_A_STRINGSETS_CNT - 1 -}; - -/* STRSET */ - -enum { - ETHTOOL_A_STRSET_UNSPEC, - ETHTOOL_A_STRSET_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_STRSET_STRINGSETS, /* nest - _A_STRINGSETS_* */ - ETHTOOL_A_STRSET_COUNTS_ONLY, /* flag */ - - /* add new constants above here */ - __ETHTOOL_A_STRSET_CNT, - ETHTOOL_A_STRSET_MAX = __ETHTOOL_A_STRSET_CNT - 1 -}; - -/* LINKINFO */ - -enum { - ETHTOOL_A_LINKINFO_UNSPEC, - ETHTOOL_A_LINKINFO_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_LINKINFO_PORT, /* u8 */ - ETHTOOL_A_LINKINFO_PHYADDR, /* u8 */ - ETHTOOL_A_LINKINFO_TP_MDIX, /* u8 */ - ETHTOOL_A_LINKINFO_TP_MDIX_CTRL, /* u8 */ - ETHTOOL_A_LINKINFO_TRANSCEIVER, /* u8 */ - - /* add new constants above here */ - __ETHTOOL_A_LINKINFO_CNT, - ETHTOOL_A_LINKINFO_MAX = __ETHTOOL_A_LINKINFO_CNT - 1 -}; - -/* LINKMODES */ - -enum { - ETHTOOL_A_LINKMODES_UNSPEC, - ETHTOOL_A_LINKMODES_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_LINKMODES_AUTONEG, /* u8 */ - ETHTOOL_A_LINKMODES_OURS, /* bitset */ - ETHTOOL_A_LINKMODES_PEER, /* bitset */ - ETHTOOL_A_LINKMODES_SPEED, /* u32 */ - ETHTOOL_A_LINKMODES_DUPLEX, /* u8 */ - ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, /* u8 */ - ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, /* u8 */ - ETHTOOL_A_LINKMODES_LANES, /* u32 */ - ETHTOOL_A_LINKMODES_RATE_MATCHING, /* u8 */ - - /* add new constants above here */ - __ETHTOOL_A_LINKMODES_CNT, - ETHTOOL_A_LINKMODES_MAX = __ETHTOOL_A_LINKMODES_CNT - 1 -}; - -/* LINKSTATE */ - -enum { - ETHTOOL_A_LINKSTATE_UNSPEC, - ETHTOOL_A_LINKSTATE_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_LINKSTATE_LINK, /* u8 */ - ETHTOOL_A_LINKSTATE_SQI, /* u32 */ - ETHTOOL_A_LINKSTATE_SQI_MAX, /* u32 */ - ETHTOOL_A_LINKSTATE_EXT_STATE, /* u8 */ - ETHTOOL_A_LINKSTATE_EXT_SUBSTATE, /* u8 */ - ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_LINKSTATE_CNT, - ETHTOOL_A_LINKSTATE_MAX = __ETHTOOL_A_LINKSTATE_CNT - 1 -}; - -/* DEBUG */ - -enum { - ETHTOOL_A_DEBUG_UNSPEC, - ETHTOOL_A_DEBUG_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_DEBUG_MSGMASK, /* bitset */ - - /* add new constants above here */ - __ETHTOOL_A_DEBUG_CNT, - ETHTOOL_A_DEBUG_MAX = __ETHTOOL_A_DEBUG_CNT - 1 -}; - -/* WOL */ - -enum { - ETHTOOL_A_WOL_UNSPEC, - ETHTOOL_A_WOL_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_WOL_MODES, /* bitset */ - ETHTOOL_A_WOL_SOPASS, /* binary */ - - /* add new constants above here */ - __ETHTOOL_A_WOL_CNT, - ETHTOOL_A_WOL_MAX = __ETHTOOL_A_WOL_CNT - 1 -}; - -/* FEATURES */ - -enum { - ETHTOOL_A_FEATURES_UNSPEC, - ETHTOOL_A_FEATURES_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_FEATURES_HW, /* bitset */ - ETHTOOL_A_FEATURES_WANTED, /* bitset */ - ETHTOOL_A_FEATURES_ACTIVE, /* bitset */ - ETHTOOL_A_FEATURES_NOCHANGE, /* bitset */ - - /* add new constants above here */ - __ETHTOOL_A_FEATURES_CNT, - ETHTOOL_A_FEATURES_MAX = __ETHTOOL_A_FEATURES_CNT - 1 -}; - -/* PRIVFLAGS */ - -enum { - ETHTOOL_A_PRIVFLAGS_UNSPEC, - ETHTOOL_A_PRIVFLAGS_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_PRIVFLAGS_FLAGS, /* bitset */ - - /* add new constants above here */ - __ETHTOOL_A_PRIVFLAGS_CNT, - ETHTOOL_A_PRIVFLAGS_MAX = __ETHTOOL_A_PRIVFLAGS_CNT - 1 -}; - -/* RINGS */ - -enum { - ETHTOOL_TCP_DATA_SPLIT_UNKNOWN = 0, - ETHTOOL_TCP_DATA_SPLIT_DISABLED, - ETHTOOL_TCP_DATA_SPLIT_ENABLED, -}; - -enum { - ETHTOOL_A_RINGS_UNSPEC, - ETHTOOL_A_RINGS_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_RINGS_RX_MAX, /* u32 */ - ETHTOOL_A_RINGS_RX_MINI_MAX, /* u32 */ - ETHTOOL_A_RINGS_RX_JUMBO_MAX, /* u32 */ - ETHTOOL_A_RINGS_TX_MAX, /* u32 */ - ETHTOOL_A_RINGS_RX, /* u32 */ - ETHTOOL_A_RINGS_RX_MINI, /* u32 */ - ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */ - ETHTOOL_A_RINGS_TX, /* u32 */ - ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ - ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ - ETHTOOL_A_RINGS_CQE_SIZE, /* u32 */ - ETHTOOL_A_RINGS_TX_PUSH, /* u8 */ - ETHTOOL_A_RINGS_RX_PUSH, /* u8 */ - ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN, /* u32 */ - ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_RINGS_CNT, - ETHTOOL_A_RINGS_MAX = (__ETHTOOL_A_RINGS_CNT - 1) -}; - -/* CHANNELS */ - -enum { - ETHTOOL_A_CHANNELS_UNSPEC, - ETHTOOL_A_CHANNELS_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_CHANNELS_RX_MAX, /* u32 */ - ETHTOOL_A_CHANNELS_TX_MAX, /* u32 */ - ETHTOOL_A_CHANNELS_OTHER_MAX, /* u32 */ - ETHTOOL_A_CHANNELS_COMBINED_MAX, /* u32 */ - ETHTOOL_A_CHANNELS_RX_COUNT, /* u32 */ - ETHTOOL_A_CHANNELS_TX_COUNT, /* u32 */ - ETHTOOL_A_CHANNELS_OTHER_COUNT, /* u32 */ - ETHTOOL_A_CHANNELS_COMBINED_COUNT, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_CHANNELS_CNT, - ETHTOOL_A_CHANNELS_MAX = (__ETHTOOL_A_CHANNELS_CNT - 1) -}; - -/* COALESCE */ - -enum { - ETHTOOL_A_COALESCE_UNSPEC, - ETHTOOL_A_COALESCE_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_COALESCE_RX_USECS, /* u32 */ - ETHTOOL_A_COALESCE_RX_MAX_FRAMES, /* u32 */ - ETHTOOL_A_COALESCE_RX_USECS_IRQ, /* u32 */ - ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ, /* u32 */ - ETHTOOL_A_COALESCE_TX_USECS, /* u32 */ - ETHTOOL_A_COALESCE_TX_MAX_FRAMES, /* u32 */ - ETHTOOL_A_COALESCE_TX_USECS_IRQ, /* u32 */ - ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ, /* u32 */ - ETHTOOL_A_COALESCE_STATS_BLOCK_USECS, /* u32 */ - ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX, /* u8 */ - ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX, /* u8 */ - ETHTOOL_A_COALESCE_PKT_RATE_LOW, /* u32 */ - ETHTOOL_A_COALESCE_RX_USECS_LOW, /* u32 */ - ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW, /* u32 */ - ETHTOOL_A_COALESCE_TX_USECS_LOW, /* u32 */ - ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW, /* u32 */ - ETHTOOL_A_COALESCE_PKT_RATE_HIGH, /* u32 */ - ETHTOOL_A_COALESCE_RX_USECS_HIGH, /* u32 */ - ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH, /* u32 */ - ETHTOOL_A_COALESCE_TX_USECS_HIGH, /* u32 */ - ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, /* u32 */ - ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, /* u32 */ - ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, /* u8 */ - ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, /* u8 */ - ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, /* u32 */ - ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, /* u32 */ - ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, /* u32 */ - /* nest - _A_PROFILE_IRQ_MODERATION */ - ETHTOOL_A_COALESCE_RX_PROFILE, - /* nest - _A_PROFILE_IRQ_MODERATION */ - ETHTOOL_A_COALESCE_TX_PROFILE, - - /* add new constants above here */ - __ETHTOOL_A_COALESCE_CNT, - ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1) -}; - -enum { - ETHTOOL_A_PROFILE_UNSPEC, - /* nest, _A_IRQ_MODERATION_* */ - ETHTOOL_A_PROFILE_IRQ_MODERATION, - __ETHTOOL_A_PROFILE_CNT, - ETHTOOL_A_PROFILE_MAX = (__ETHTOOL_A_PROFILE_CNT - 1) -}; - -enum { - ETHTOOL_A_IRQ_MODERATION_UNSPEC, - ETHTOOL_A_IRQ_MODERATION_USEC, /* u32 */ - ETHTOOL_A_IRQ_MODERATION_PKTS, /* u32 */ - ETHTOOL_A_IRQ_MODERATION_COMPS, /* u32 */ - - __ETHTOOL_A_IRQ_MODERATION_CNT, - ETHTOOL_A_IRQ_MODERATION_MAX = (__ETHTOOL_A_IRQ_MODERATION_CNT - 1) -}; - -/* PAUSE */ - -enum { - ETHTOOL_A_PAUSE_UNSPEC, - ETHTOOL_A_PAUSE_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_PAUSE_AUTONEG, /* u8 */ - ETHTOOL_A_PAUSE_RX, /* u8 */ - ETHTOOL_A_PAUSE_TX, /* u8 */ - ETHTOOL_A_PAUSE_STATS, /* nest - _PAUSE_STAT_* */ - ETHTOOL_A_PAUSE_STATS_SRC, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_PAUSE_CNT, - ETHTOOL_A_PAUSE_MAX = (__ETHTOOL_A_PAUSE_CNT - 1) -}; - -enum { - ETHTOOL_A_PAUSE_STAT_UNSPEC, - ETHTOOL_A_PAUSE_STAT_PAD, - - ETHTOOL_A_PAUSE_STAT_TX_FRAMES, - ETHTOOL_A_PAUSE_STAT_RX_FRAMES, - - /* add new constants above here - * adjust ETHTOOL_PAUSE_STAT_CNT if adding non-stats! - */ - __ETHTOOL_A_PAUSE_STAT_CNT, - ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1) -}; - -/* EEE */ - -enum { - ETHTOOL_A_EEE_UNSPEC, - ETHTOOL_A_EEE_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_EEE_MODES_OURS, /* bitset */ - ETHTOOL_A_EEE_MODES_PEER, /* bitset */ - ETHTOOL_A_EEE_ACTIVE, /* u8 */ - ETHTOOL_A_EEE_ENABLED, /* u8 */ - ETHTOOL_A_EEE_TX_LPI_ENABLED, /* u8 */ - ETHTOOL_A_EEE_TX_LPI_TIMER, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_EEE_CNT, - ETHTOOL_A_EEE_MAX = (__ETHTOOL_A_EEE_CNT - 1) -}; - -/* TSINFO */ - -enum { - ETHTOOL_A_TSINFO_UNSPEC, - ETHTOOL_A_TSINFO_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_TSINFO_TIMESTAMPING, /* bitset */ - ETHTOOL_A_TSINFO_TX_TYPES, /* bitset */ - ETHTOOL_A_TSINFO_RX_FILTERS, /* bitset */ - ETHTOOL_A_TSINFO_PHC_INDEX, /* u32 */ - ETHTOOL_A_TSINFO_STATS, /* nest - _A_TSINFO_STAT */ - - /* add new constants above here */ - __ETHTOOL_A_TSINFO_CNT, - ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) -}; - -enum { - ETHTOOL_A_TS_STAT_UNSPEC, - - ETHTOOL_A_TS_STAT_TX_PKTS, /* uint */ - ETHTOOL_A_TS_STAT_TX_LOST, /* uint */ - ETHTOOL_A_TS_STAT_TX_ERR, /* uint */ - - /* add new constants above here */ - __ETHTOOL_A_TS_STAT_CNT, - ETHTOOL_A_TS_STAT_MAX = (__ETHTOOL_A_TS_STAT_CNT - 1) - -}; - -/* PHC VCLOCKS */ - -enum { - ETHTOOL_A_PHC_VCLOCKS_UNSPEC, - ETHTOOL_A_PHC_VCLOCKS_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_PHC_VCLOCKS_NUM, /* u32 */ - ETHTOOL_A_PHC_VCLOCKS_INDEX, /* array, s32 */ - - /* add new constants above here */ - __ETHTOOL_A_PHC_VCLOCKS_CNT, - ETHTOOL_A_PHC_VCLOCKS_MAX = (__ETHTOOL_A_PHC_VCLOCKS_CNT - 1) -}; - -/* CABLE TEST */ - -enum { - ETHTOOL_A_CABLE_TEST_UNSPEC, - ETHTOOL_A_CABLE_TEST_HEADER, /* nest - _A_HEADER_* */ - - /* add new constants above here */ - __ETHTOOL_A_CABLE_TEST_CNT, - ETHTOOL_A_CABLE_TEST_MAX = __ETHTOOL_A_CABLE_TEST_CNT - 1 -}; - /* CABLE TEST NOTIFY */ enum { ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC, @@ -582,74 +49,12 @@ enum { ETHTOOL_A_CABLE_INF_SRC_ALCD, }; -enum { - ETHTOOL_A_CABLE_RESULT_UNSPEC, - ETHTOOL_A_CABLE_RESULT_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */ - ETHTOOL_A_CABLE_RESULT_CODE, /* u8 ETHTOOL_A_CABLE_RESULT_CODE_ */ - ETHTOOL_A_CABLE_RESULT_SRC, /* u32 ETHTOOL_A_CABLE_INF_SRC_ */ - - __ETHTOOL_A_CABLE_RESULT_CNT, - ETHTOOL_A_CABLE_RESULT_MAX = (__ETHTOOL_A_CABLE_RESULT_CNT - 1) -}; - -enum { - ETHTOOL_A_CABLE_FAULT_LENGTH_UNSPEC, - ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */ - ETHTOOL_A_CABLE_FAULT_LENGTH_CM, /* u32 */ - ETHTOOL_A_CABLE_FAULT_LENGTH_SRC, /* u32 ETHTOOL_A_CABLE_INF_SRC_ */ - - __ETHTOOL_A_CABLE_FAULT_LENGTH_CNT, - ETHTOOL_A_CABLE_FAULT_LENGTH_MAX = (__ETHTOOL_A_CABLE_FAULT_LENGTH_CNT - 1) -}; - enum { ETHTOOL_A_CABLE_TEST_NTF_STATUS_UNSPEC, ETHTOOL_A_CABLE_TEST_NTF_STATUS_STARTED, ETHTOOL_A_CABLE_TEST_NTF_STATUS_COMPLETED }; -enum { - ETHTOOL_A_CABLE_NEST_UNSPEC, - ETHTOOL_A_CABLE_NEST_RESULT, /* nest - ETHTOOL_A_CABLE_RESULT_ */ - ETHTOOL_A_CABLE_NEST_FAULT_LENGTH, /* nest - ETHTOOL_A_CABLE_FAULT_LENGTH_ */ - __ETHTOOL_A_CABLE_NEST_CNT, - ETHTOOL_A_CABLE_NEST_MAX = (__ETHTOOL_A_CABLE_NEST_CNT - 1) -}; - -enum { - ETHTOOL_A_CABLE_TEST_NTF_UNSPEC, - ETHTOOL_A_CABLE_TEST_NTF_HEADER, /* nest - ETHTOOL_A_HEADER_* */ - ETHTOOL_A_CABLE_TEST_NTF_STATUS, /* u8 - _STARTED/_COMPLETE */ - ETHTOOL_A_CABLE_TEST_NTF_NEST, /* nest - of results: */ - - __ETHTOOL_A_CABLE_TEST_NTF_CNT, - ETHTOOL_A_CABLE_TEST_NTF_MAX = (__ETHTOOL_A_CABLE_TEST_NTF_CNT - 1) -}; - -/* CABLE TEST TDR */ - -enum { - ETHTOOL_A_CABLE_TEST_TDR_CFG_UNSPEC, - ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST, /* u32 */ - ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST, /* u32 */ - ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP, /* u32 */ - ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR, /* u8 */ - - /* add new constants above here */ - __ETHTOOL_A_CABLE_TEST_TDR_CFG_CNT, - ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX = __ETHTOOL_A_CABLE_TEST_TDR_CFG_CNT - 1 -}; - -enum { - ETHTOOL_A_CABLE_TEST_TDR_UNSPEC, - ETHTOOL_A_CABLE_TEST_TDR_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_CABLE_TEST_TDR_CFG, /* nest - *_TDR_CFG_* */ - - /* add new constants above here */ - __ETHTOOL_A_CABLE_TEST_TDR_CNT, - ETHTOOL_A_CABLE_TEST_TDR_MAX = __ETHTOOL_A_CABLE_TEST_TDR_CNT - 1 -}; - /* CABLE TEST TDR NOTIFY */ enum { @@ -689,163 +94,17 @@ enum { ETHTOOL_A_CABLE_TDR_NEST_MAX = (__ETHTOOL_A_CABLE_TDR_NEST_CNT - 1) }; -enum { - ETHTOOL_A_CABLE_TEST_TDR_NTF_UNSPEC, - ETHTOOL_A_CABLE_TEST_TDR_NTF_HEADER, /* nest - ETHTOOL_A_HEADER_* */ - ETHTOOL_A_CABLE_TEST_TDR_NTF_STATUS, /* u8 - _STARTED/_COMPLETE */ - ETHTOOL_A_CABLE_TEST_TDR_NTF_NEST, /* nest - of results: */ - - /* add new constants above here */ - __ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT, - ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX = __ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT - 1 -}; - -/* TUNNEL INFO */ - -enum { - ETHTOOL_UDP_TUNNEL_TYPE_VXLAN, - ETHTOOL_UDP_TUNNEL_TYPE_GENEVE, - ETHTOOL_UDP_TUNNEL_TYPE_VXLAN_GPE, - - __ETHTOOL_UDP_TUNNEL_TYPE_CNT -}; - -enum { - ETHTOOL_A_TUNNEL_UDP_ENTRY_UNSPEC, - - ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, /* be16 */ - ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_TUNNEL_UDP_ENTRY_CNT, - ETHTOOL_A_TUNNEL_UDP_ENTRY_MAX = (__ETHTOOL_A_TUNNEL_UDP_ENTRY_CNT - 1) -}; - -enum { - ETHTOOL_A_TUNNEL_UDP_TABLE_UNSPEC, - - ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE, /* u32 */ - ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES, /* bitset */ - ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY, /* nest - _UDP_ENTRY_* */ - - /* add new constants above here */ - __ETHTOOL_A_TUNNEL_UDP_TABLE_CNT, - ETHTOOL_A_TUNNEL_UDP_TABLE_MAX = (__ETHTOOL_A_TUNNEL_UDP_TABLE_CNT - 1) -}; - -enum { - ETHTOOL_A_TUNNEL_UDP_UNSPEC, - - ETHTOOL_A_TUNNEL_UDP_TABLE, /* nest - _UDP_TABLE_* */ - - /* add new constants above here */ - __ETHTOOL_A_TUNNEL_UDP_CNT, - ETHTOOL_A_TUNNEL_UDP_MAX = (__ETHTOOL_A_TUNNEL_UDP_CNT - 1) -}; - -enum { - ETHTOOL_A_TUNNEL_INFO_UNSPEC, - ETHTOOL_A_TUNNEL_INFO_HEADER, /* nest - _A_HEADER_* */ - - ETHTOOL_A_TUNNEL_INFO_UDP_PORTS, /* nest - _UDP_TABLE */ - - /* add new constants above here */ - __ETHTOOL_A_TUNNEL_INFO_CNT, - ETHTOOL_A_TUNNEL_INFO_MAX = (__ETHTOOL_A_TUNNEL_INFO_CNT - 1) -}; - -/* FEC */ - -enum { - ETHTOOL_A_FEC_UNSPEC, - ETHTOOL_A_FEC_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_FEC_MODES, /* bitset */ - ETHTOOL_A_FEC_AUTO, /* u8 */ - ETHTOOL_A_FEC_ACTIVE, /* u32 */ - ETHTOOL_A_FEC_STATS, /* nest - _A_FEC_STAT */ - - __ETHTOOL_A_FEC_CNT, - ETHTOOL_A_FEC_MAX = (__ETHTOOL_A_FEC_CNT - 1) -}; - -enum { - ETHTOOL_A_FEC_STAT_UNSPEC, - ETHTOOL_A_FEC_STAT_PAD, - - ETHTOOL_A_FEC_STAT_CORRECTED, /* array, u64 */ - ETHTOOL_A_FEC_STAT_UNCORR, /* array, u64 */ - ETHTOOL_A_FEC_STAT_CORR_BITS, /* array, u64 */ - - /* add new constants above here */ - __ETHTOOL_A_FEC_STAT_CNT, - ETHTOOL_A_FEC_STAT_MAX = (__ETHTOOL_A_FEC_STAT_CNT - 1) -}; - -/* MODULE EEPROM */ - -enum { - ETHTOOL_A_MODULE_EEPROM_UNSPEC, - ETHTOOL_A_MODULE_EEPROM_HEADER, /* nest - _A_HEADER_* */ - - ETHTOOL_A_MODULE_EEPROM_OFFSET, /* u32 */ - ETHTOOL_A_MODULE_EEPROM_LENGTH, /* u32 */ - ETHTOOL_A_MODULE_EEPROM_PAGE, /* u8 */ - ETHTOOL_A_MODULE_EEPROM_BANK, /* u8 */ - ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS, /* u8 */ - ETHTOOL_A_MODULE_EEPROM_DATA, /* binary */ - - __ETHTOOL_A_MODULE_EEPROM_CNT, - ETHTOOL_A_MODULE_EEPROM_MAX = (__ETHTOOL_A_MODULE_EEPROM_CNT - 1) -}; - -/* STATS */ - -enum { - ETHTOOL_A_STATS_UNSPEC, - ETHTOOL_A_STATS_PAD, - ETHTOOL_A_STATS_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_STATS_GROUPS, /* bitset */ - - ETHTOOL_A_STATS_GRP, /* nest - _A_STATS_GRP_* */ - - ETHTOOL_A_STATS_SRC, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_STATS_CNT, - ETHTOOL_A_STATS_MAX = (__ETHTOOL_A_STATS_CNT - 1) -}; - enum { ETHTOOL_STATS_ETH_PHY, ETHTOOL_STATS_ETH_MAC, ETHTOOL_STATS_ETH_CTRL, ETHTOOL_STATS_RMON, + ETHTOOL_STATS_PHY, /* add new constants above here */ __ETHTOOL_STATS_CNT }; -enum { - ETHTOOL_A_STATS_GRP_UNSPEC, - ETHTOOL_A_STATS_GRP_PAD, - - ETHTOOL_A_STATS_GRP_ID, /* u32 */ - ETHTOOL_A_STATS_GRP_SS_ID, /* u32 */ - - ETHTOOL_A_STATS_GRP_STAT, /* nest */ - - ETHTOOL_A_STATS_GRP_HIST_RX, /* nest */ - ETHTOOL_A_STATS_GRP_HIST_TX, /* nest */ - - ETHTOOL_A_STATS_GRP_HIST_BKT_LOW, /* u32 */ - ETHTOOL_A_STATS_GRP_HIST_BKT_HI, /* u32 */ - ETHTOOL_A_STATS_GRP_HIST_VAL, /* u64 */ - - /* add new constants above here */ - __ETHTOOL_A_STATS_GRP_CNT, - ETHTOOL_A_STATS_GRP_MAX = (__ETHTOOL_A_STATS_GRP_CNT - 1) -}; - enum { /* 30.3.2.1.5 aSymbolErrorDuringCarrier */ ETHTOOL_A_STATS_ETH_PHY_5_SYM_ERR, @@ -935,154 +194,18 @@ enum { ETHTOOL_A_STATS_RMON_MAX = (__ETHTOOL_A_STATS_RMON_CNT - 1) }; -/* MODULE */ - enum { - ETHTOOL_A_MODULE_UNSPEC, - ETHTOOL_A_MODULE_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_MODULE_POWER_MODE_POLICY, /* u8 */ - ETHTOOL_A_MODULE_POWER_MODE, /* u8 */ + /* Basic packet counters if PHY has separate counters from the MAC */ + ETHTOOL_A_STATS_PHY_RX_PKTS, + ETHTOOL_A_STATS_PHY_RX_BYTES, + ETHTOOL_A_STATS_PHY_RX_ERRORS, + ETHTOOL_A_STATS_PHY_TX_PKTS, + ETHTOOL_A_STATS_PHY_TX_BYTES, + ETHTOOL_A_STATS_PHY_TX_ERRORS, /* add new constants above here */ - __ETHTOOL_A_MODULE_CNT, - ETHTOOL_A_MODULE_MAX = (__ETHTOOL_A_MODULE_CNT - 1) -}; - -/* Power Sourcing Equipment */ -enum { - ETHTOOL_A_C33_PSE_PW_LIMIT_UNSPEC, - ETHTOOL_A_C33_PSE_PW_LIMIT_MIN, /* u32 */ - ETHTOOL_A_C33_PSE_PW_LIMIT_MAX, /* u32 */ -}; - -enum { - ETHTOOL_A_PSE_UNSPEC, - ETHTOOL_A_PSE_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_PODL_PSE_ADMIN_STATE, /* u32 */ - ETHTOOL_A_PODL_PSE_ADMIN_CONTROL, /* u32 */ - ETHTOOL_A_PODL_PSE_PW_D_STATUS, /* u32 */ - ETHTOOL_A_C33_PSE_ADMIN_STATE, /* u32 */ - ETHTOOL_A_C33_PSE_ADMIN_CONTROL, /* u32 */ - ETHTOOL_A_C33_PSE_PW_D_STATUS, /* u32 */ - ETHTOOL_A_C33_PSE_PW_CLASS, /* u32 */ - ETHTOOL_A_C33_PSE_ACTUAL_PW, /* u32 */ - ETHTOOL_A_C33_PSE_EXT_STATE, /* u32 */ - ETHTOOL_A_C33_PSE_EXT_SUBSTATE, /* u32 */ - ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, /* u32 */ - ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES, /* nest - _C33_PSE_PW_LIMIT_* */ - - /* add new constants above here */ - __ETHTOOL_A_PSE_CNT, - ETHTOOL_A_PSE_MAX = (__ETHTOOL_A_PSE_CNT - 1) -}; - -enum { - ETHTOOL_A_RSS_UNSPEC, - ETHTOOL_A_RSS_HEADER, - ETHTOOL_A_RSS_CONTEXT, /* u32 */ - ETHTOOL_A_RSS_HFUNC, /* u32 */ - ETHTOOL_A_RSS_INDIR, /* binary */ - ETHTOOL_A_RSS_HKEY, /* binary */ - ETHTOOL_A_RSS_INPUT_XFRM, /* u32 */ - ETHTOOL_A_RSS_START_CONTEXT, /* u32 */ - - __ETHTOOL_A_RSS_CNT, - ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1), -}; - -/* PLCA */ - -enum { - ETHTOOL_A_PLCA_UNSPEC, - ETHTOOL_A_PLCA_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_PLCA_VERSION, /* u16 */ - ETHTOOL_A_PLCA_ENABLED, /* u8 */ - ETHTOOL_A_PLCA_STATUS, /* u8 */ - ETHTOOL_A_PLCA_NODE_CNT, /* u32 */ - ETHTOOL_A_PLCA_NODE_ID, /* u32 */ - ETHTOOL_A_PLCA_TO_TMR, /* u32 */ - ETHTOOL_A_PLCA_BURST_CNT, /* u32 */ - ETHTOOL_A_PLCA_BURST_TMR, /* u32 */ - - /* add new constants above here */ - __ETHTOOL_A_PLCA_CNT, - ETHTOOL_A_PLCA_MAX = (__ETHTOOL_A_PLCA_CNT - 1) -}; - -/* MAC Merge (802.3) */ - -enum { - ETHTOOL_A_MM_STAT_UNSPEC, - ETHTOOL_A_MM_STAT_PAD, - - /* aMACMergeFrameAssErrorCount */ - ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS, /* u64 */ - /* aMACMergeFrameSmdErrorCount */ - ETHTOOL_A_MM_STAT_SMD_ERRORS, /* u64 */ - /* aMACMergeFrameAssOkCount */ - ETHTOOL_A_MM_STAT_REASSEMBLY_OK, /* u64 */ - /* aMACMergeFragCountRx */ - ETHTOOL_A_MM_STAT_RX_FRAG_COUNT, /* u64 */ - /* aMACMergeFragCountTx */ - ETHTOOL_A_MM_STAT_TX_FRAG_COUNT, /* u64 */ - /* aMACMergeHoldCount */ - ETHTOOL_A_MM_STAT_HOLD_COUNT, /* u64 */ - - /* add new constants above here */ - __ETHTOOL_A_MM_STAT_CNT, - ETHTOOL_A_MM_STAT_MAX = (__ETHTOOL_A_MM_STAT_CNT - 1) -}; - -enum { - ETHTOOL_A_MM_UNSPEC, - ETHTOOL_A_MM_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_MM_PMAC_ENABLED, /* u8 */ - ETHTOOL_A_MM_TX_ENABLED, /* u8 */ - ETHTOOL_A_MM_TX_ACTIVE, /* u8 */ - ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, /* u32 */ - ETHTOOL_A_MM_RX_MIN_FRAG_SIZE, /* u32 */ - ETHTOOL_A_MM_VERIFY_ENABLED, /* u8 */ - ETHTOOL_A_MM_VERIFY_STATUS, /* u8 */ - ETHTOOL_A_MM_VERIFY_TIME, /* u32 */ - ETHTOOL_A_MM_MAX_VERIFY_TIME, /* u32 */ - ETHTOOL_A_MM_STATS, /* nest - _A_MM_STAT_* */ - - /* add new constants above here */ - __ETHTOOL_A_MM_CNT, - ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1) -}; - -/* MODULE_FW_FLASH */ - -enum { - ETHTOOL_A_MODULE_FW_FLASH_UNSPEC, - ETHTOOL_A_MODULE_FW_FLASH_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME, /* string */ - ETHTOOL_A_MODULE_FW_FLASH_PASSWORD, /* u32 */ - ETHTOOL_A_MODULE_FW_FLASH_STATUS, /* u32 */ - ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG, /* string */ - ETHTOOL_A_MODULE_FW_FLASH_DONE, /* uint */ - ETHTOOL_A_MODULE_FW_FLASH_TOTAL, /* uint */ - - /* add new constants above here */ - __ETHTOOL_A_MODULE_FW_FLASH_CNT, - ETHTOOL_A_MODULE_FW_FLASH_MAX = (__ETHTOOL_A_MODULE_FW_FLASH_CNT - 1) -}; - -enum { - ETHTOOL_A_PHY_UNSPEC, - ETHTOOL_A_PHY_HEADER, /* nest - _A_HEADER_* */ - ETHTOOL_A_PHY_INDEX, /* u32 */ - ETHTOOL_A_PHY_DRVNAME, /* string */ - ETHTOOL_A_PHY_NAME, /* string */ - ETHTOOL_A_PHY_UPSTREAM_TYPE, /* u32 */ - ETHTOOL_A_PHY_UPSTREAM_INDEX, /* u32 */ - ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, /* string */ - ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, /* string */ - - /* add new constants above here */ - __ETHTOOL_A_PHY_CNT, - ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1) + __ETHTOOL_A_STATS_PHY_CNT, + ETHTOOL_A_STATS_PHY_MAX = (__ETHTOOL_A_STATS_PHY_CNT - 1) }; /* generic netlink info */ diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h new file mode 100644 index 000000000000..fe24c3459ac0 --- /dev/null +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -0,0 +1,821 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/ethtool.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H +#define _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H + +#define ETHTOOL_FAMILY_NAME "ethtool" +#define ETHTOOL_FAMILY_VERSION 1 + +enum { + ETHTOOL_UDP_TUNNEL_TYPE_VXLAN, + ETHTOOL_UDP_TUNNEL_TYPE_GENEVE, + ETHTOOL_UDP_TUNNEL_TYPE_VXLAN_GPE, + + /* private: */ + __ETHTOOL_UDP_TUNNEL_TYPE_CNT, + ETHTOOL_UDP_TUNNEL_TYPE_MAX = (__ETHTOOL_UDP_TUNNEL_TYPE_CNT - 1) +}; + +/** + * enum ethtool_header_flags - common ethtool header flags + * @ETHTOOL_FLAG_COMPACT_BITSETS: use compact bitsets in reply + * @ETHTOOL_FLAG_OMIT_REPLY: provide optional reply for SET or ACT requests + * @ETHTOOL_FLAG_STATS: request statistics, if supported by the driver + */ +enum ethtool_header_flags { + ETHTOOL_FLAG_COMPACT_BITSETS = 1, + ETHTOOL_FLAG_OMIT_REPLY = 2, + ETHTOOL_FLAG_STATS = 4, +}; + +enum { + ETHTOOL_PHY_UPSTREAM_TYPE_MAC, + ETHTOOL_PHY_UPSTREAM_TYPE_PHY, +}; + +enum ethtool_tcp_data_split { + ETHTOOL_TCP_DATA_SPLIT_UNKNOWN, + ETHTOOL_TCP_DATA_SPLIT_DISABLED, + ETHTOOL_TCP_DATA_SPLIT_ENABLED, +}; + +enum { + ETHTOOL_A_HEADER_UNSPEC, + ETHTOOL_A_HEADER_DEV_INDEX, + ETHTOOL_A_HEADER_DEV_NAME, + ETHTOOL_A_HEADER_FLAGS, + ETHTOOL_A_HEADER_PHY_INDEX, + + __ETHTOOL_A_HEADER_CNT, + ETHTOOL_A_HEADER_MAX = (__ETHTOOL_A_HEADER_CNT - 1) +}; + +enum { + ETHTOOL_A_BITSET_BIT_UNSPEC, + ETHTOOL_A_BITSET_BIT_INDEX, + ETHTOOL_A_BITSET_BIT_NAME, + ETHTOOL_A_BITSET_BIT_VALUE, + + __ETHTOOL_A_BITSET_BIT_CNT, + ETHTOOL_A_BITSET_BIT_MAX = (__ETHTOOL_A_BITSET_BIT_CNT - 1) +}; + +enum { + ETHTOOL_A_BITSET_BITS_UNSPEC, + ETHTOOL_A_BITSET_BITS_BIT, + + __ETHTOOL_A_BITSET_BITS_CNT, + ETHTOOL_A_BITSET_BITS_MAX = (__ETHTOOL_A_BITSET_BITS_CNT - 1) +}; + +enum { + ETHTOOL_A_BITSET_UNSPEC, + ETHTOOL_A_BITSET_NOMASK, + ETHTOOL_A_BITSET_SIZE, + ETHTOOL_A_BITSET_BITS, + ETHTOOL_A_BITSET_VALUE, + ETHTOOL_A_BITSET_MASK, + + __ETHTOOL_A_BITSET_CNT, + ETHTOOL_A_BITSET_MAX = (__ETHTOOL_A_BITSET_CNT - 1) +}; + +enum { + ETHTOOL_A_STRING_UNSPEC, + ETHTOOL_A_STRING_INDEX, + ETHTOOL_A_STRING_VALUE, + + __ETHTOOL_A_STRING_CNT, + ETHTOOL_A_STRING_MAX = (__ETHTOOL_A_STRING_CNT - 1) +}; + +enum { + ETHTOOL_A_STRINGS_UNSPEC, + ETHTOOL_A_STRINGS_STRING, + + __ETHTOOL_A_STRINGS_CNT, + ETHTOOL_A_STRINGS_MAX = (__ETHTOOL_A_STRINGS_CNT - 1) +}; + +enum { + ETHTOOL_A_STRINGSET_UNSPEC, + ETHTOOL_A_STRINGSET_ID, + ETHTOOL_A_STRINGSET_COUNT, + ETHTOOL_A_STRINGSET_STRINGS, + + __ETHTOOL_A_STRINGSET_CNT, + ETHTOOL_A_STRINGSET_MAX = (__ETHTOOL_A_STRINGSET_CNT - 1) +}; + +enum { + ETHTOOL_A_STRINGSETS_UNSPEC, + ETHTOOL_A_STRINGSETS_STRINGSET, + + __ETHTOOL_A_STRINGSETS_CNT, + ETHTOOL_A_STRINGSETS_MAX = (__ETHTOOL_A_STRINGSETS_CNT - 1) +}; + +enum { + ETHTOOL_A_STRSET_UNSPEC, + ETHTOOL_A_STRSET_HEADER, + ETHTOOL_A_STRSET_STRINGSETS, + ETHTOOL_A_STRSET_COUNTS_ONLY, + + __ETHTOOL_A_STRSET_CNT, + ETHTOOL_A_STRSET_MAX = (__ETHTOOL_A_STRSET_CNT - 1) +}; + +enum { + ETHTOOL_A_PRIVFLAGS_UNSPEC, + ETHTOOL_A_PRIVFLAGS_HEADER, + ETHTOOL_A_PRIVFLAGS_FLAGS, + + __ETHTOOL_A_PRIVFLAGS_CNT, + ETHTOOL_A_PRIVFLAGS_MAX = (__ETHTOOL_A_PRIVFLAGS_CNT - 1) +}; + +enum { + ETHTOOL_A_RINGS_UNSPEC, + ETHTOOL_A_RINGS_HEADER, + ETHTOOL_A_RINGS_RX_MAX, + ETHTOOL_A_RINGS_RX_MINI_MAX, + ETHTOOL_A_RINGS_RX_JUMBO_MAX, + ETHTOOL_A_RINGS_TX_MAX, + ETHTOOL_A_RINGS_RX, + ETHTOOL_A_RINGS_RX_MINI, + ETHTOOL_A_RINGS_RX_JUMBO, + ETHTOOL_A_RINGS_TX, + ETHTOOL_A_RINGS_RX_BUF_LEN, + ETHTOOL_A_RINGS_TCP_DATA_SPLIT, + ETHTOOL_A_RINGS_CQE_SIZE, + ETHTOOL_A_RINGS_TX_PUSH, + ETHTOOL_A_RINGS_RX_PUSH, + ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN, + ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX, + ETHTOOL_A_RINGS_HDS_THRESH, + ETHTOOL_A_RINGS_HDS_THRESH_MAX, + + __ETHTOOL_A_RINGS_CNT, + ETHTOOL_A_RINGS_MAX = (__ETHTOOL_A_RINGS_CNT - 1) +}; + +enum { + ETHTOOL_A_MM_STAT_UNSPEC, + ETHTOOL_A_MM_STAT_PAD, + ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS, + ETHTOOL_A_MM_STAT_SMD_ERRORS, + ETHTOOL_A_MM_STAT_REASSEMBLY_OK, + ETHTOOL_A_MM_STAT_RX_FRAG_COUNT, + ETHTOOL_A_MM_STAT_TX_FRAG_COUNT, + ETHTOOL_A_MM_STAT_HOLD_COUNT, + + __ETHTOOL_A_MM_STAT_CNT, + ETHTOOL_A_MM_STAT_MAX = (__ETHTOOL_A_MM_STAT_CNT - 1) +}; + +enum { + ETHTOOL_A_MM_UNSPEC, + ETHTOOL_A_MM_HEADER, + ETHTOOL_A_MM_PMAC_ENABLED, + ETHTOOL_A_MM_TX_ENABLED, + ETHTOOL_A_MM_TX_ACTIVE, + ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, + ETHTOOL_A_MM_RX_MIN_FRAG_SIZE, + ETHTOOL_A_MM_VERIFY_ENABLED, + ETHTOOL_A_MM_VERIFY_STATUS, + ETHTOOL_A_MM_VERIFY_TIME, + ETHTOOL_A_MM_MAX_VERIFY_TIME, + ETHTOOL_A_MM_STATS, + + __ETHTOOL_A_MM_CNT, + ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1) +}; + +enum { + ETHTOOL_A_LINKINFO_UNSPEC, + ETHTOOL_A_LINKINFO_HEADER, + ETHTOOL_A_LINKINFO_PORT, + ETHTOOL_A_LINKINFO_PHYADDR, + ETHTOOL_A_LINKINFO_TP_MDIX, + ETHTOOL_A_LINKINFO_TP_MDIX_CTRL, + ETHTOOL_A_LINKINFO_TRANSCEIVER, + + __ETHTOOL_A_LINKINFO_CNT, + ETHTOOL_A_LINKINFO_MAX = (__ETHTOOL_A_LINKINFO_CNT - 1) +}; + +enum { + ETHTOOL_A_LINKMODES_UNSPEC, + ETHTOOL_A_LINKMODES_HEADER, + ETHTOOL_A_LINKMODES_AUTONEG, + ETHTOOL_A_LINKMODES_OURS, + ETHTOOL_A_LINKMODES_PEER, + ETHTOOL_A_LINKMODES_SPEED, + ETHTOOL_A_LINKMODES_DUPLEX, + ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, + ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, + ETHTOOL_A_LINKMODES_LANES, + ETHTOOL_A_LINKMODES_RATE_MATCHING, + + __ETHTOOL_A_LINKMODES_CNT, + ETHTOOL_A_LINKMODES_MAX = (__ETHTOOL_A_LINKMODES_CNT - 1) +}; + +enum { + ETHTOOL_A_LINKSTATE_UNSPEC, + ETHTOOL_A_LINKSTATE_HEADER, + ETHTOOL_A_LINKSTATE_LINK, + ETHTOOL_A_LINKSTATE_SQI, + ETHTOOL_A_LINKSTATE_SQI_MAX, + ETHTOOL_A_LINKSTATE_EXT_STATE, + ETHTOOL_A_LINKSTATE_EXT_SUBSTATE, + ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, + + __ETHTOOL_A_LINKSTATE_CNT, + ETHTOOL_A_LINKSTATE_MAX = (__ETHTOOL_A_LINKSTATE_CNT - 1) +}; + +enum { + ETHTOOL_A_DEBUG_UNSPEC, + ETHTOOL_A_DEBUG_HEADER, + ETHTOOL_A_DEBUG_MSGMASK, + + __ETHTOOL_A_DEBUG_CNT, + ETHTOOL_A_DEBUG_MAX = (__ETHTOOL_A_DEBUG_CNT - 1) +}; + +enum { + ETHTOOL_A_WOL_UNSPEC, + ETHTOOL_A_WOL_HEADER, + ETHTOOL_A_WOL_MODES, + ETHTOOL_A_WOL_SOPASS, + + __ETHTOOL_A_WOL_CNT, + ETHTOOL_A_WOL_MAX = (__ETHTOOL_A_WOL_CNT - 1) +}; + +enum { + ETHTOOL_A_FEATURES_UNSPEC, + ETHTOOL_A_FEATURES_HEADER, + ETHTOOL_A_FEATURES_HW, + ETHTOOL_A_FEATURES_WANTED, + ETHTOOL_A_FEATURES_ACTIVE, + ETHTOOL_A_FEATURES_NOCHANGE, + + __ETHTOOL_A_FEATURES_CNT, + ETHTOOL_A_FEATURES_MAX = (__ETHTOOL_A_FEATURES_CNT - 1) +}; + +enum { + ETHTOOL_A_CHANNELS_UNSPEC, + ETHTOOL_A_CHANNELS_HEADER, + ETHTOOL_A_CHANNELS_RX_MAX, + ETHTOOL_A_CHANNELS_TX_MAX, + ETHTOOL_A_CHANNELS_OTHER_MAX, + ETHTOOL_A_CHANNELS_COMBINED_MAX, + ETHTOOL_A_CHANNELS_RX_COUNT, + ETHTOOL_A_CHANNELS_TX_COUNT, + ETHTOOL_A_CHANNELS_OTHER_COUNT, + ETHTOOL_A_CHANNELS_COMBINED_COUNT, + + __ETHTOOL_A_CHANNELS_CNT, + ETHTOOL_A_CHANNELS_MAX = (__ETHTOOL_A_CHANNELS_CNT - 1) +}; + +enum { + ETHTOOL_A_IRQ_MODERATION_UNSPEC, + ETHTOOL_A_IRQ_MODERATION_USEC, + ETHTOOL_A_IRQ_MODERATION_PKTS, + ETHTOOL_A_IRQ_MODERATION_COMPS, + + __ETHTOOL_A_IRQ_MODERATION_CNT, + ETHTOOL_A_IRQ_MODERATION_MAX = (__ETHTOOL_A_IRQ_MODERATION_CNT - 1) +}; + +enum { + ETHTOOL_A_PROFILE_UNSPEC, + ETHTOOL_A_PROFILE_IRQ_MODERATION, + + __ETHTOOL_A_PROFILE_CNT, + ETHTOOL_A_PROFILE_MAX = (__ETHTOOL_A_PROFILE_CNT - 1) +}; + +enum { + ETHTOOL_A_COALESCE_UNSPEC, + ETHTOOL_A_COALESCE_HEADER, + ETHTOOL_A_COALESCE_RX_USECS, + ETHTOOL_A_COALESCE_RX_MAX_FRAMES, + ETHTOOL_A_COALESCE_RX_USECS_IRQ, + ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ, + ETHTOOL_A_COALESCE_TX_USECS, + ETHTOOL_A_COALESCE_TX_MAX_FRAMES, + ETHTOOL_A_COALESCE_TX_USECS_IRQ, + ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ, + ETHTOOL_A_COALESCE_STATS_BLOCK_USECS, + ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX, + ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX, + ETHTOOL_A_COALESCE_PKT_RATE_LOW, + ETHTOOL_A_COALESCE_RX_USECS_LOW, + ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW, + ETHTOOL_A_COALESCE_TX_USECS_LOW, + ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW, + ETHTOOL_A_COALESCE_PKT_RATE_HIGH, + ETHTOOL_A_COALESCE_RX_USECS_HIGH, + ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH, + ETHTOOL_A_COALESCE_TX_USECS_HIGH, + ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, + ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, + ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, + ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, + ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, + ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, + ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, + ETHTOOL_A_COALESCE_RX_PROFILE, + ETHTOOL_A_COALESCE_TX_PROFILE, + + __ETHTOOL_A_COALESCE_CNT, + ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1) +}; + +enum { + ETHTOOL_A_PAUSE_STAT_UNSPEC, + ETHTOOL_A_PAUSE_STAT_PAD, + ETHTOOL_A_PAUSE_STAT_TX_FRAMES, + ETHTOOL_A_PAUSE_STAT_RX_FRAMES, + + __ETHTOOL_A_PAUSE_STAT_CNT, + ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1) +}; + +enum { + ETHTOOL_A_PAUSE_UNSPEC, + ETHTOOL_A_PAUSE_HEADER, + ETHTOOL_A_PAUSE_AUTONEG, + ETHTOOL_A_PAUSE_RX, + ETHTOOL_A_PAUSE_TX, + ETHTOOL_A_PAUSE_STATS, + ETHTOOL_A_PAUSE_STATS_SRC, + + __ETHTOOL_A_PAUSE_CNT, + ETHTOOL_A_PAUSE_MAX = (__ETHTOOL_A_PAUSE_CNT - 1) +}; + +enum { + ETHTOOL_A_EEE_UNSPEC, + ETHTOOL_A_EEE_HEADER, + ETHTOOL_A_EEE_MODES_OURS, + ETHTOOL_A_EEE_MODES_PEER, + ETHTOOL_A_EEE_ACTIVE, + ETHTOOL_A_EEE_ENABLED, + ETHTOOL_A_EEE_TX_LPI_ENABLED, + ETHTOOL_A_EEE_TX_LPI_TIMER, + + __ETHTOOL_A_EEE_CNT, + ETHTOOL_A_EEE_MAX = (__ETHTOOL_A_EEE_CNT - 1) +}; + +enum { + ETHTOOL_A_TS_STAT_UNSPEC, + ETHTOOL_A_TS_STAT_TX_PKTS, + ETHTOOL_A_TS_STAT_TX_LOST, + ETHTOOL_A_TS_STAT_TX_ERR, + ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED, + + __ETHTOOL_A_TS_STAT_CNT, + ETHTOOL_A_TS_STAT_MAX = (__ETHTOOL_A_TS_STAT_CNT - 1) +}; + +enum { + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_UNSPEC, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER, + + __ETHTOOL_A_TS_HWTSTAMP_PROVIDER_CNT, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_MAX = (__ETHTOOL_A_TS_HWTSTAMP_PROVIDER_CNT - 1) +}; + +enum { + ETHTOOL_A_TSINFO_UNSPEC, + ETHTOOL_A_TSINFO_HEADER, + ETHTOOL_A_TSINFO_TIMESTAMPING, + ETHTOOL_A_TSINFO_TX_TYPES, + ETHTOOL_A_TSINFO_RX_FILTERS, + ETHTOOL_A_TSINFO_PHC_INDEX, + ETHTOOL_A_TSINFO_STATS, + ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER, + + __ETHTOOL_A_TSINFO_CNT, + ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_RESULT_UNSPEC, + ETHTOOL_A_CABLE_RESULT_PAIR, + ETHTOOL_A_CABLE_RESULT_CODE, + ETHTOOL_A_CABLE_RESULT_SRC, + + __ETHTOOL_A_CABLE_RESULT_CNT, + ETHTOOL_A_CABLE_RESULT_MAX = (__ETHTOOL_A_CABLE_RESULT_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_FAULT_LENGTH_UNSPEC, + ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR, + ETHTOOL_A_CABLE_FAULT_LENGTH_CM, + ETHTOOL_A_CABLE_FAULT_LENGTH_SRC, + + __ETHTOOL_A_CABLE_FAULT_LENGTH_CNT, + ETHTOOL_A_CABLE_FAULT_LENGTH_MAX = (__ETHTOOL_A_CABLE_FAULT_LENGTH_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_NEST_UNSPEC, + ETHTOOL_A_CABLE_NEST_RESULT, + ETHTOOL_A_CABLE_NEST_FAULT_LENGTH, + + __ETHTOOL_A_CABLE_NEST_CNT, + ETHTOOL_A_CABLE_NEST_MAX = (__ETHTOOL_A_CABLE_NEST_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_TEST_UNSPEC, + ETHTOOL_A_CABLE_TEST_HEADER, + + __ETHTOOL_A_CABLE_TEST_CNT, + ETHTOOL_A_CABLE_TEST_MAX = (__ETHTOOL_A_CABLE_TEST_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_TEST_NTF_UNSPEC, + ETHTOOL_A_CABLE_TEST_NTF_HEADER, + ETHTOOL_A_CABLE_TEST_NTF_STATUS, + ETHTOOL_A_CABLE_TEST_NTF_NEST, + + __ETHTOOL_A_CABLE_TEST_NTF_CNT, + ETHTOOL_A_CABLE_TEST_NTF_MAX = (__ETHTOOL_A_CABLE_TEST_NTF_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_TEST_TDR_CFG_UNSPEC, + ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST, + ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST, + ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP, + ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR, + + __ETHTOOL_A_CABLE_TEST_TDR_CFG_CNT, + ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX = (__ETHTOOL_A_CABLE_TEST_TDR_CFG_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_TEST_TDR_NTF_UNSPEC, + ETHTOOL_A_CABLE_TEST_TDR_NTF_HEADER, + ETHTOOL_A_CABLE_TEST_TDR_NTF_STATUS, + ETHTOOL_A_CABLE_TEST_TDR_NTF_NEST, + + __ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT, + ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX = (__ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT - 1) +}; + +enum { + ETHTOOL_A_CABLE_TEST_TDR_UNSPEC, + ETHTOOL_A_CABLE_TEST_TDR_HEADER, + ETHTOOL_A_CABLE_TEST_TDR_CFG, + + __ETHTOOL_A_CABLE_TEST_TDR_CNT, + ETHTOOL_A_CABLE_TEST_TDR_MAX = (__ETHTOOL_A_CABLE_TEST_TDR_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_UDP_ENTRY_UNSPEC, + ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, + ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, + + __ETHTOOL_A_TUNNEL_UDP_ENTRY_CNT, + ETHTOOL_A_TUNNEL_UDP_ENTRY_MAX = (__ETHTOOL_A_TUNNEL_UDP_ENTRY_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_UDP_TABLE_UNSPEC, + ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE, + ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES, + ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY, + + __ETHTOOL_A_TUNNEL_UDP_TABLE_CNT, + ETHTOOL_A_TUNNEL_UDP_TABLE_MAX = (__ETHTOOL_A_TUNNEL_UDP_TABLE_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_UDP_UNSPEC, + ETHTOOL_A_TUNNEL_UDP_TABLE, + + __ETHTOOL_A_TUNNEL_UDP_CNT, + ETHTOOL_A_TUNNEL_UDP_MAX = (__ETHTOOL_A_TUNNEL_UDP_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_INFO_UNSPEC, + ETHTOOL_A_TUNNEL_INFO_HEADER, + ETHTOOL_A_TUNNEL_INFO_UDP_PORTS, + + __ETHTOOL_A_TUNNEL_INFO_CNT, + ETHTOOL_A_TUNNEL_INFO_MAX = (__ETHTOOL_A_TUNNEL_INFO_CNT - 1) +}; + +enum { + ETHTOOL_A_FEC_STAT_UNSPEC, + ETHTOOL_A_FEC_STAT_PAD, + ETHTOOL_A_FEC_STAT_CORRECTED, + ETHTOOL_A_FEC_STAT_UNCORR, + ETHTOOL_A_FEC_STAT_CORR_BITS, + + __ETHTOOL_A_FEC_STAT_CNT, + ETHTOOL_A_FEC_STAT_MAX = (__ETHTOOL_A_FEC_STAT_CNT - 1) +}; + +enum { + ETHTOOL_A_FEC_UNSPEC, + ETHTOOL_A_FEC_HEADER, + ETHTOOL_A_FEC_MODES, + ETHTOOL_A_FEC_AUTO, + ETHTOOL_A_FEC_ACTIVE, + ETHTOOL_A_FEC_STATS, + + __ETHTOOL_A_FEC_CNT, + ETHTOOL_A_FEC_MAX = (__ETHTOOL_A_FEC_CNT - 1) +}; + +enum { + ETHTOOL_A_MODULE_EEPROM_UNSPEC, + ETHTOOL_A_MODULE_EEPROM_HEADER, + ETHTOOL_A_MODULE_EEPROM_OFFSET, + ETHTOOL_A_MODULE_EEPROM_LENGTH, + ETHTOOL_A_MODULE_EEPROM_PAGE, + ETHTOOL_A_MODULE_EEPROM_BANK, + ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS, + ETHTOOL_A_MODULE_EEPROM_DATA, + + __ETHTOOL_A_MODULE_EEPROM_CNT, + ETHTOOL_A_MODULE_EEPROM_MAX = (__ETHTOOL_A_MODULE_EEPROM_CNT - 1) +}; + +enum { + ETHTOOL_A_STATS_GRP_UNSPEC, + ETHTOOL_A_STATS_GRP_PAD, + ETHTOOL_A_STATS_GRP_ID, + ETHTOOL_A_STATS_GRP_SS_ID, + ETHTOOL_A_STATS_GRP_STAT, + ETHTOOL_A_STATS_GRP_HIST_RX, + ETHTOOL_A_STATS_GRP_HIST_TX, + ETHTOOL_A_STATS_GRP_HIST_BKT_LOW, + ETHTOOL_A_STATS_GRP_HIST_BKT_HI, + ETHTOOL_A_STATS_GRP_HIST_VAL, + + __ETHTOOL_A_STATS_GRP_CNT, + ETHTOOL_A_STATS_GRP_MAX = (__ETHTOOL_A_STATS_GRP_CNT - 1) +}; + +enum { + ETHTOOL_A_STATS_UNSPEC, + ETHTOOL_A_STATS_PAD, + ETHTOOL_A_STATS_HEADER, + ETHTOOL_A_STATS_GROUPS, + ETHTOOL_A_STATS_GRP, + ETHTOOL_A_STATS_SRC, + + __ETHTOOL_A_STATS_CNT, + ETHTOOL_A_STATS_MAX = (__ETHTOOL_A_STATS_CNT - 1) +}; + +enum { + ETHTOOL_A_PHC_VCLOCKS_UNSPEC, + ETHTOOL_A_PHC_VCLOCKS_HEADER, + ETHTOOL_A_PHC_VCLOCKS_NUM, + ETHTOOL_A_PHC_VCLOCKS_INDEX, + + __ETHTOOL_A_PHC_VCLOCKS_CNT, + ETHTOOL_A_PHC_VCLOCKS_MAX = (__ETHTOOL_A_PHC_VCLOCKS_CNT - 1) +}; + +enum { + ETHTOOL_A_MODULE_UNSPEC, + ETHTOOL_A_MODULE_HEADER, + ETHTOOL_A_MODULE_POWER_MODE_POLICY, + ETHTOOL_A_MODULE_POWER_MODE, + + __ETHTOOL_A_MODULE_CNT, + ETHTOOL_A_MODULE_MAX = (__ETHTOOL_A_MODULE_CNT - 1) +}; + +enum { + ETHTOOL_A_C33_PSE_PW_LIMIT_UNSPEC, + ETHTOOL_A_C33_PSE_PW_LIMIT_MIN, + ETHTOOL_A_C33_PSE_PW_LIMIT_MAX, + + __ETHTOOL_A_C33_PSE_PW_LIMIT_CNT, + __ETHTOOL_A_C33_PSE_PW_LIMIT_MAX = (__ETHTOOL_A_C33_PSE_PW_LIMIT_CNT - 1) +}; + +enum { + ETHTOOL_A_PSE_UNSPEC, + ETHTOOL_A_PSE_HEADER, + ETHTOOL_A_PODL_PSE_ADMIN_STATE, + ETHTOOL_A_PODL_PSE_ADMIN_CONTROL, + ETHTOOL_A_PODL_PSE_PW_D_STATUS, + ETHTOOL_A_C33_PSE_ADMIN_STATE, + ETHTOOL_A_C33_PSE_ADMIN_CONTROL, + ETHTOOL_A_C33_PSE_PW_D_STATUS, + ETHTOOL_A_C33_PSE_PW_CLASS, + ETHTOOL_A_C33_PSE_ACTUAL_PW, + ETHTOOL_A_C33_PSE_EXT_STATE, + ETHTOOL_A_C33_PSE_EXT_SUBSTATE, + ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, + ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES, + + __ETHTOOL_A_PSE_CNT, + ETHTOOL_A_PSE_MAX = (__ETHTOOL_A_PSE_CNT - 1) +}; + +enum { + ETHTOOL_A_RSS_UNSPEC, + ETHTOOL_A_RSS_HEADER, + ETHTOOL_A_RSS_CONTEXT, + ETHTOOL_A_RSS_HFUNC, + ETHTOOL_A_RSS_INDIR, + ETHTOOL_A_RSS_HKEY, + ETHTOOL_A_RSS_INPUT_XFRM, + ETHTOOL_A_RSS_START_CONTEXT, + + __ETHTOOL_A_RSS_CNT, + ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1) +}; + +enum { + ETHTOOL_A_PLCA_UNSPEC, + ETHTOOL_A_PLCA_HEADER, + ETHTOOL_A_PLCA_VERSION, + ETHTOOL_A_PLCA_ENABLED, + ETHTOOL_A_PLCA_STATUS, + ETHTOOL_A_PLCA_NODE_CNT, + ETHTOOL_A_PLCA_NODE_ID, + ETHTOOL_A_PLCA_TO_TMR, + ETHTOOL_A_PLCA_BURST_CNT, + ETHTOOL_A_PLCA_BURST_TMR, + + __ETHTOOL_A_PLCA_CNT, + ETHTOOL_A_PLCA_MAX = (__ETHTOOL_A_PLCA_CNT - 1) +}; + +enum { + ETHTOOL_A_MODULE_FW_FLASH_UNSPEC, + ETHTOOL_A_MODULE_FW_FLASH_HEADER, + ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME, + ETHTOOL_A_MODULE_FW_FLASH_PASSWORD, + ETHTOOL_A_MODULE_FW_FLASH_STATUS, + ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG, + ETHTOOL_A_MODULE_FW_FLASH_DONE, + ETHTOOL_A_MODULE_FW_FLASH_TOTAL, + + __ETHTOOL_A_MODULE_FW_FLASH_CNT, + ETHTOOL_A_MODULE_FW_FLASH_MAX = (__ETHTOOL_A_MODULE_FW_FLASH_CNT - 1) +}; + +enum { + ETHTOOL_A_PHY_UNSPEC, + ETHTOOL_A_PHY_HEADER, + ETHTOOL_A_PHY_INDEX, + ETHTOOL_A_PHY_DRVNAME, + ETHTOOL_A_PHY_NAME, + ETHTOOL_A_PHY_UPSTREAM_TYPE, + ETHTOOL_A_PHY_UPSTREAM_INDEX, + ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, + ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, + + __ETHTOOL_A_PHY_CNT, + ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1) +}; + +enum { + ETHTOOL_A_TSCONFIG_UNSPEC, + ETHTOOL_A_TSCONFIG_HEADER, + ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER, + ETHTOOL_A_TSCONFIG_TX_TYPES, + ETHTOOL_A_TSCONFIG_RX_FILTERS, + ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS, + + __ETHTOOL_A_TSCONFIG_CNT, + ETHTOOL_A_TSCONFIG_MAX = (__ETHTOOL_A_TSCONFIG_CNT - 1) +}; + +enum { + ETHTOOL_MSG_USER_NONE = 0, + ETHTOOL_MSG_STRSET_GET = 1, + ETHTOOL_MSG_LINKINFO_GET, + ETHTOOL_MSG_LINKINFO_SET, + ETHTOOL_MSG_LINKMODES_GET, + ETHTOOL_MSG_LINKMODES_SET, + ETHTOOL_MSG_LINKSTATE_GET, + ETHTOOL_MSG_DEBUG_GET, + ETHTOOL_MSG_DEBUG_SET, + ETHTOOL_MSG_WOL_GET, + ETHTOOL_MSG_WOL_SET, + ETHTOOL_MSG_FEATURES_GET, + ETHTOOL_MSG_FEATURES_SET, + ETHTOOL_MSG_PRIVFLAGS_GET, + ETHTOOL_MSG_PRIVFLAGS_SET, + ETHTOOL_MSG_RINGS_GET, + ETHTOOL_MSG_RINGS_SET, + ETHTOOL_MSG_CHANNELS_GET, + ETHTOOL_MSG_CHANNELS_SET, + ETHTOOL_MSG_COALESCE_GET, + ETHTOOL_MSG_COALESCE_SET, + ETHTOOL_MSG_PAUSE_GET, + ETHTOOL_MSG_PAUSE_SET, + ETHTOOL_MSG_EEE_GET, + ETHTOOL_MSG_EEE_SET, + ETHTOOL_MSG_TSINFO_GET, + ETHTOOL_MSG_CABLE_TEST_ACT, + ETHTOOL_MSG_CABLE_TEST_TDR_ACT, + ETHTOOL_MSG_TUNNEL_INFO_GET, + ETHTOOL_MSG_FEC_GET, + ETHTOOL_MSG_FEC_SET, + ETHTOOL_MSG_MODULE_EEPROM_GET, + ETHTOOL_MSG_STATS_GET, + ETHTOOL_MSG_PHC_VCLOCKS_GET, + ETHTOOL_MSG_MODULE_GET, + ETHTOOL_MSG_MODULE_SET, + ETHTOOL_MSG_PSE_GET, + ETHTOOL_MSG_PSE_SET, + ETHTOOL_MSG_RSS_GET, + ETHTOOL_MSG_PLCA_GET_CFG, + ETHTOOL_MSG_PLCA_SET_CFG, + ETHTOOL_MSG_PLCA_GET_STATUS, + ETHTOOL_MSG_MM_GET, + ETHTOOL_MSG_MM_SET, + ETHTOOL_MSG_MODULE_FW_FLASH_ACT, + ETHTOOL_MSG_PHY_GET, + ETHTOOL_MSG_TSCONFIG_GET, + ETHTOOL_MSG_TSCONFIG_SET, + + __ETHTOOL_MSG_USER_CNT, + ETHTOOL_MSG_USER_MAX = (__ETHTOOL_MSG_USER_CNT - 1) +}; + +enum { + ETHTOOL_MSG_KERNEL_NONE = 0, + ETHTOOL_MSG_STRSET_GET_REPLY = 1, + ETHTOOL_MSG_LINKINFO_GET_REPLY, + ETHTOOL_MSG_LINKINFO_NTF, + ETHTOOL_MSG_LINKMODES_GET_REPLY, + ETHTOOL_MSG_LINKMODES_NTF, + ETHTOOL_MSG_LINKSTATE_GET_REPLY, + ETHTOOL_MSG_DEBUG_GET_REPLY, + ETHTOOL_MSG_DEBUG_NTF, + ETHTOOL_MSG_WOL_GET_REPLY, + ETHTOOL_MSG_WOL_NTF, + ETHTOOL_MSG_FEATURES_GET_REPLY, + ETHTOOL_MSG_FEATURES_SET_REPLY, + ETHTOOL_MSG_FEATURES_NTF, + ETHTOOL_MSG_PRIVFLAGS_GET_REPLY, + ETHTOOL_MSG_PRIVFLAGS_NTF, + ETHTOOL_MSG_RINGS_GET_REPLY, + ETHTOOL_MSG_RINGS_NTF, + ETHTOOL_MSG_CHANNELS_GET_REPLY, + ETHTOOL_MSG_CHANNELS_NTF, + ETHTOOL_MSG_COALESCE_GET_REPLY, + ETHTOOL_MSG_COALESCE_NTF, + ETHTOOL_MSG_PAUSE_GET_REPLY, + ETHTOOL_MSG_PAUSE_NTF, + ETHTOOL_MSG_EEE_GET_REPLY, + ETHTOOL_MSG_EEE_NTF, + ETHTOOL_MSG_TSINFO_GET_REPLY, + ETHTOOL_MSG_CABLE_TEST_NTF, + ETHTOOL_MSG_CABLE_TEST_TDR_NTF, + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY, + ETHTOOL_MSG_FEC_GET_REPLY, + ETHTOOL_MSG_FEC_NTF, + ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY, + ETHTOOL_MSG_STATS_GET_REPLY, + ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, + ETHTOOL_MSG_MODULE_GET_REPLY, + ETHTOOL_MSG_MODULE_NTF, + ETHTOOL_MSG_PSE_GET_REPLY, + ETHTOOL_MSG_RSS_GET_REPLY, + ETHTOOL_MSG_PLCA_GET_CFG_REPLY, + ETHTOOL_MSG_PLCA_GET_STATUS_REPLY, + ETHTOOL_MSG_PLCA_NTF, + ETHTOOL_MSG_MM_GET_REPLY, + ETHTOOL_MSG_MM_NTF, + ETHTOOL_MSG_MODULE_FW_FLASH_NTF, + ETHTOOL_MSG_PHY_GET_REPLY, + ETHTOOL_MSG_PHY_NTF, + ETHTOOL_MSG_TSCONFIG_GET_REPLY, + ETHTOOL_MSG_TSCONFIG_SET_REPLY, + + __ETHTOOL_MSG_KERNEL_CNT, + ETHTOOL_MSG_KERNEL_MAX = (__ETHTOOL_MSG_KERNEL_CNT - 1) +}; + +#endif /* _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H */ diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 34f221d3a1b9..bd8167979707 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -25,6 +25,9 @@ #define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ #define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ #define FAN_OPEN_EXEC_PERM 0x00040000 /* File open/exec in perm check */ +/* #define FAN_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */ + +#define FAN_PRE_ACCESS 0x00100000 /* Pre-content access hook */ #define FAN_EVENT_ON_CHILD 0x08000000 /* Interested in child events */ @@ -143,6 +146,7 @@ struct fanotify_event_metadata { #define FAN_EVENT_INFO_TYPE_DFID 3 #define FAN_EVENT_INFO_TYPE_PIDFD 4 #define FAN_EVENT_INFO_TYPE_ERROR 5 +#define FAN_EVENT_INFO_TYPE_RANGE 6 /* Special info types for FAN_RENAME */ #define FAN_EVENT_INFO_TYPE_OLD_DFID_NAME 10 @@ -189,6 +193,13 @@ struct fanotify_event_info_error { __u32 error_count; }; +struct fanotify_event_info_range { + struct fanotify_event_info_header hdr; + __u32 pad; + __u64 offset; + __u64 count; +}; + /* * User space may need to record additional information about its decision. * The extra information type records what kind of information is included. @@ -224,6 +235,13 @@ struct fanotify_response_info_audit_rule { /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 +/* errno other than EPERM can specified in upper byte of deny response */ +#define FAN_ERRNO_BITS 8 +#define FAN_ERRNO_SHIFT (32 - FAN_ERRNO_BITS) +#define FAN_ERRNO_MASK ((1 << FAN_ERRNO_BITS) - 1) +#define FAN_DENY_ERRNO(err) \ + (FAN_DENY | ((((__u32)(err)) & FAN_ERRNO_MASK) << FAN_ERRNO_SHIFT)) + #define FAN_AUDIT 0x10 /* Bitmask to create audit record for result */ #define FAN_INFO 0x20 /* Bitmask to indicate additional information */ diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 6e6907e63bfc..a15ac2fa4b20 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -155,4 +155,8 @@ #define AT_HANDLE_MNT_ID_UNIQUE 0x001 /* Return the u64 unique mount ID. */ #define AT_HANDLE_CONNECTABLE 0x002 /* Request a connectable file handle */ +/* Flags for execveat2(2). */ +#define AT_EXECVE_CHECK 0x10000 /* Only perform a check if execution + would be allowed. */ + #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index a6924dd3aff1..00e9890ca3c0 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -68,6 +68,8 @@ enum { FRA_SPORT_RANGE, /* sport */ FRA_DPORT_RANGE, /* dport */ FRA_DSCP, /* dscp */ + FRA_FLOWLABEL, /* flowlabel */ + FRA_FLOWLABEL_MASK, /* flowlabel mask */ __FRA_MAX }; diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h index 24ca0c00cae3..9d9e8ae32b41 100644 --- a/include/uapi/linux/fiemap.h +++ b/include/uapi/linux/fiemap.h @@ -14,37 +14,56 @@ #include +/** + * struct fiemap_extent - description of one fiemap extent + * @fe_logical: byte offset of the extent in the file + * @fe_physical: byte offset of extent on disk + * @fe_length: length in bytes for this extent + * @fe_flags: FIEMAP_EXTENT_* flags for this extent + */ struct fiemap_extent { - __u64 fe_logical; /* logical offset in bytes for the start of - * the extent from the beginning of the file */ - __u64 fe_physical; /* physical offset in bytes for the start - * of the extent from the beginning of the disk */ - __u64 fe_length; /* length in bytes for this extent */ + __u64 fe_logical; + __u64 fe_physical; + __u64 fe_length; + /* private: */ __u64 fe_reserved64[2]; - __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */ + /* public: */ + __u32 fe_flags; + /* private: */ __u32 fe_reserved[3]; }; +/** + * struct fiemap - file extent mappings + * @fm_start: byte offset (inclusive) at which to start mapping (in) + * @fm_length: logical length of mapping which userspace wants (in) + * @fm_flags: FIEMAP_FLAG_* flags for request (in/out) + * @fm_mapped_extents: number of extents that were mapped (out) + * @fm_extent_count: size of fm_extents array (in) + * @fm_extents: array of mapped extents (out) + */ struct fiemap { - __u64 fm_start; /* logical offset (inclusive) at - * which to start mapping (in) */ - __u64 fm_length; /* logical length of mapping which - * userspace wants (in) */ - __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */ - __u32 fm_mapped_extents;/* number of extents that were mapped (out) */ - __u32 fm_extent_count; /* size of fm_extents array (in) */ + __u64 fm_start; + __u64 fm_length; + __u32 fm_flags; + __u32 fm_mapped_extents; + __u32 fm_extent_count; + /* private: */ __u32 fm_reserved; - struct fiemap_extent fm_extents[]; /* array of mapped extents (out) */ + /* public: */ + struct fiemap_extent fm_extents[]; }; #define FIEMAP_MAX_OFFSET (~0ULL) +/* flags used in fm_flags: */ #define FIEMAP_FLAG_SYNC 0x00000001 /* sync file data before map */ #define FIEMAP_FLAG_XATTR 0x00000002 /* map extended attribute tree */ #define FIEMAP_FLAG_CACHE 0x00000004 /* request caching of the extents */ #define FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR) +/* flags used in fe_flags: */ #define FIEMAP_EXTENT_LAST 0x00000001 /* Last extent in file. */ #define FIEMAP_EXTENT_UNKNOWN 0x00000002 /* Data location unknown. */ #define FIEMAP_EXTENT_DELALLOC 0x00000004 /* Location still pending. diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 753971770733..2bbe00cf1248 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -40,6 +40,15 @@ #define BLOCK_SIZE_BITS 10 #define BLOCK_SIZE (1<attr_type_mask flags */ +#define IORING_RW_ATTR_FLAG_PI (1U << 0) +/* PI attribute information */ +struct io_uring_attr_pi { + __u16 flags; + __u16 app_tag; + __u32 len; + __u64 addr; + __u64 seed; + __u64 rsvd; +}; + /* * If sqe->file_index is set to this for opcodes that instantiate a new * direct descriptor (like openat/openat2/accept), then io_uring will allocate @@ -561,6 +577,7 @@ struct io_uring_params { #define IORING_FEAT_REG_REG_RING (1U << 13) #define IORING_FEAT_RECVSEND_BUNDLE (1U << 14) #define IORING_FEAT_MIN_TIMEOUT (1U << 15) +#define IORING_FEAT_RW_ATTR (1U << 16) /* * io_uring_register(2) opcodes and arguments diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 34810f6ae2b5..78747b24bd0f 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -868,6 +868,7 @@ enum iommu_hwpt_pgfault_perm { * @pasid: Process Address Space ID * @grpid: Page Request Group Index * @perm: Combination of enum iommu_hwpt_pgfault_perm + * @__reserved: Must be 0. * @addr: Fault address * @length: a hint of how much data the requestor is expecting to fetch. For * example, if the PRI initiator knows it is going to do a 10MB @@ -883,7 +884,8 @@ struct iommu_hwpt_pgfault { __u32 pasid; __u32 grpid; __u32 perm; - __u64 addr; + __u32 __reserved; + __aligned_u64 addr; __u32 length; __u32 cookie; }; diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 283dec7e3645..5bd7ce934d74 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -137,6 +137,22 @@ struct ip_beet_phdr { __u8 reserved; }; +struct ip_iptfs_hdr { + __u8 subtype; /* 0*: basic, 1: CC */ + __u8 flags; + __be16 block_offset; +}; + +struct ip_iptfs_cc_hdr { + __u8 subtype; /* 0: basic, 1*: CC */ + __u8 flags; + __be16 block_offset; + __be32 loss_rate; + __be64 rtt_adelay_xdelay; + __be32 tval; + __be32 techo; +}; + /* index values for the variables in ipv4_devconf */ enum { diff --git a/include/uapi/linux/ipsec.h b/include/uapi/linux/ipsec.h index 50d8ee1791e2..696b790f4346 100644 --- a/include/uapi/linux/ipsec.h +++ b/include/uapi/linux/ipsec.h @@ -14,7 +14,8 @@ enum { IPSEC_MODE_ANY = 0, /* We do not support this for SA */ IPSEC_MODE_TRANSPORT = 1, IPSEC_MODE_TUNNEL = 2, - IPSEC_MODE_BEET = 3 + IPSEC_MODE_BEET = 3, + IPSEC_MODE_IPTFS = 4 }; enum { diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 502ea63b5d2e..45e6d8fca9b9 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -617,10 +617,6 @@ struct kvm_ioeventfd { #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) -#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \ - KVM_X86_DISABLE_EXITS_HLT | \ - KVM_X86_DISABLE_EXITS_PAUSE | \ - KVM_X86_DISABLE_EXITS_CSTATE) /* for KVM_ENABLE_CAP */ struct kvm_enable_cap { @@ -1070,6 +1066,10 @@ struct kvm_dirty_tlb { #define KVM_REG_SIZE_SHIFT 52 #define KVM_REG_SIZE_MASK 0x00f0000000000000ULL + +#define KVM_REG_SIZE(id) \ + (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) + #define KVM_REG_SIZE_U8 0x0000000000000000ULL #define KVM_REG_SIZE_U16 0x0010000000000000ULL #define KVM_REG_SIZE_U32 0x0020000000000000ULL diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index f0d3f268240d..6975f182b22c 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -125,6 +125,7 @@ #define MDIO_STAT1_LPOWERABLE 0x0002 /* Low-power ability */ #define MDIO_STAT1_LSTATUS BMSR_LSTATUS #define MDIO_STAT1_FAULT 0x0080 /* Fault */ +#define MDIO_PCS_STAT1_CLKSTOP_CAP 0x0040 #define MDIO_AN_STAT1_LPABLE 0x0001 /* Link partner AN ability */ #define MDIO_AN_STAT1_ABLE BMSR_ANEGCAPABLE #define MDIO_AN_STAT1_RFAULT BMSR_RFAULT diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index 50589e5dd6a3..84fa8a21dfd0 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -12,31 +12,33 @@ /** * enum mptcp_event_type * @MPTCP_EVENT_UNSPEC: unused event - * @MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport A new MPTCP connection has been created. It is the good time - * to allocate memory and send ADD_ADDR if needed. Depending on the + * @MPTCP_EVENT_CREATED: A new MPTCP connection has been created. It is the + * good time to allocate memory and send ADD_ADDR if needed. Depending on the * traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED - * is sent. - * @MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport A MPTCP connection is established (can start new subflows). - * @MPTCP_EVENT_CLOSED: token A MPTCP connection has stopped. - * @MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] A - * new address has been announced by the peer. - * @MPTCP_EVENT_REMOVED: token, rem_id An address has been lost by the peer. - * @MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, saddr4 | - * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error] A new - * subflow has been established. 'error' should not be set. - * @MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, if_idx [, error] A subflow has been - * closed. An error (copy of sk_err) could be set if an error has been - * detected for this subflow. - * @MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, if_idx [, error] The priority of a - * subflow has changed. 'error' should not be set. - * @MPTCP_EVENT_LISTENER_CREATED: family, sport, saddr4 | saddr6 A new PM - * listener is created. - * @MPTCP_EVENT_LISTENER_CLOSED: family, sport, saddr4 | saddr6 A PM listener - * is closed. + * is sent. Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport, server-side. + * @MPTCP_EVENT_ESTABLISHED: A MPTCP connection is established (can start new + * subflows). Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport, server-side. + * @MPTCP_EVENT_CLOSED: A MPTCP connection has stopped. Attribute: token. + * @MPTCP_EVENT_ANNOUNCED: A new address has been announced by the peer. + * Attributes: token, rem_id, family, daddr4 | daddr6 [, dport]. + * @MPTCP_EVENT_REMOVED: An address has been lost by the peer. Attributes: + * token, rem_id. + * @MPTCP_EVENT_SUB_ESTABLISHED: A new subflow has been established. 'error' + * should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | + * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error]. + * @MPTCP_EVENT_SUB_CLOSED: A subflow has been closed. An error (copy of + * sk_err) could be set if an error has been detected for this subflow. + * Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | + * daddr6, sport, dport, backup, if_idx [, error]. + * @MPTCP_EVENT_SUB_PRIORITY: The priority of a subflow has changed. 'error' + * should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | + * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error]. + * @MPTCP_EVENT_LISTENER_CREATED: A new PM listener is created. Attributes: + * family, sport, saddr4 | saddr6. + * @MPTCP_EVENT_LISTENER_CLOSED: A PM listener is closed. Attributes: family, + * sport, saddr4 | saddr6. */ enum mptcp_event_type { MPTCP_EVENT_UNSPEC, diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 858339d1c1c4..55b0ab51096c 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -13,6 +13,17 @@ #include #include /* for SO_TIMESTAMPING */ +/* + * Possible type of hwtstamp provider. Mainly "precise" the default one + * is for IEEE 1588 quality and "approx" is for NICs DMA point. + */ +enum hwtstamp_provider_qualifier { + HWTSTAMP_PROVIDER_QUALIFIER_PRECISE, + HWTSTAMP_PROVIDER_QUALIFIER_APPROX, + + HWTSTAMP_PROVIDER_QUALIFIER_CNT, +}; + /* SO_TIMESTAMPING flags */ enum { SOF_TIMESTAMPING_TX_HARDWARE = (1<<0), diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index c2ac7269acf7..43233af75b9d 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -57,6 +57,7 @@ enum ctattr_type { CTA_SYNPROXY, CTA_FILTER, CTA_STATUS_MASK, + CTA_TIMESTAMP_EVENT, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index caf4db2fcbb9..4273e0249fcb 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -58,7 +58,7 @@ #define NFS4_SHARE_DENY_BOTH 0x0003 /* nfs41 */ -#define NFS4_SHARE_WANT_MASK 0xFF00 +#define NFS4_SHARE_WANT_TYPE_MASK 0xFF00 #define NFS4_SHARE_WANT_NO_PREFERENCE 0x0000 #define NFS4_SHARE_WANT_READ_DELEG 0x0100 #define NFS4_SHARE_WANT_WRITE_DELEG 0x0200 @@ -66,13 +66,16 @@ #define NFS4_SHARE_WANT_NO_DELEG 0x0400 #define NFS4_SHARE_WANT_CANCEL 0x0500 -#define NFS4_SHARE_WHEN_MASK 0xF0000 +#define NFS4_SHARE_WHEN_MASK 0xF0000 #define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL 0x10000 #define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED 0x20000 +#define NFS4_SHARE_WANT_MOD_MASK 0xF00000 #define NFS4_SHARE_WANT_DELEG_TIMESTAMPS 0x100000 #define NFS4_SHARE_WANT_OPEN_XOR_DELEGATION 0x200000 +#define NFS4_SHARE_WANT_MASK (NFS4_SHARE_WANT_TYPE_MASK | NFS4_SHARE_WANT_MOD_MASK) + #define NFS4_CDFC4_FORE 0x1 #define NFS4_CDFC4_BACK 0x2 #define NFS4_CDFC4_BOTH 0x3 diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6d11437596b9..f6c1b181c886 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1329,6 +1329,13 @@ * %NL80211_ATTR_MLO_TTLM_ULINK attributes are used to specify the * TID to Link mapping for downlink/uplink traffic. * + * @NL80211_CMD_ASSOC_MLO_RECONF: For a non-AP MLD station, request to + * add/remove links to/from the association. + * + * @NL80211_CMD_EPCS_CFG: EPCS configuration for a station. Used by userland to + * control EPCS configuration. Used to notify userland on the current state + * of EPCS. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1586,6 +1593,9 @@ enum nl80211_commands { NL80211_CMD_SET_TID_TO_LINK_MAPPING, + NL80211_CMD_ASSOC_MLO_RECONF, + NL80211_CMD_EPCS_CFG, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2871,6 +2881,18 @@ enum nl80211_commands { * @NL80211_ATTR_VIF_RADIO_MASK: Bitmask of allowed radios (u32). * A value of 0 means all radios. * + * @NL80211_ATTR_SUPPORTED_SELECTORS: supported selectors, array of + * supported selectors as defined by IEEE 802.11 7.3.2.2 but without the + * length restriction (at most %NL80211_MAX_SUPP_SELECTORS). + * This can be used to provide a list of selectors that are implemented + * by the supplicant. If not given, support for SAE_H2E is assumed. + * + * @NL80211_ATTR_MLO_RECONF_REM_LINKS: (u16) A bitmask of the links requested + * to be removed from the MLO association. + * + * @NL80211_ATTR_EPCS: Flag attribute indicating that EPCS is enabled for a + * station interface. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3421,6 +3443,11 @@ enum nl80211_attrs { NL80211_ATTR_VIF_RADIO_MASK, + NL80211_ATTR_SUPPORTED_SELECTORS, + + NL80211_ATTR_MLO_RECONF_REM_LINKS, + NL80211_ATTR_EPCS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3465,6 +3492,7 @@ enum nl80211_attrs { #define NL80211_WIPHY_NAME_MAXLEN 64 #define NL80211_MAX_SUPP_RATES 32 +#define NL80211_MAX_SUPP_SELECTORS 128 #define NL80211_MAX_SUPP_HT_RATES 77 #define NL80211_MAX_SUPP_REG_RULES 128 #define NL80211_TKIP_DATA_OFFSET_ENCR_KEY 0 diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h index dcfa38fdc93c..6d06793512b1 100644 --- a/include/uapi/linux/ntsync.h +++ b/include/uapi/linux/ntsync.h @@ -11,13 +11,49 @@ #include struct ntsync_sem_args { - __u32 sem; __u32 count; __u32 max; }; -#define NTSYNC_IOC_CREATE_SEM _IOWR('N', 0x80, struct ntsync_sem_args) +struct ntsync_mutex_args { + __u32 owner; + __u32 count; +}; -#define NTSYNC_IOC_SEM_POST _IOWR('N', 0x81, __u32) +struct ntsync_event_args { + __u32 manual; + __u32 signaled; +}; + +#define NTSYNC_WAIT_REALTIME 0x1 + +struct ntsync_wait_args { + __u64 timeout; + __u64 objs; + __u32 count; + __u32 index; + __u32 flags; + __u32 owner; + __u32 alert; + __u32 pad; +}; + +#define NTSYNC_MAX_WAIT_COUNT 64 + +#define NTSYNC_IOC_CREATE_SEM _IOW ('N', 0x80, struct ntsync_sem_args) +#define NTSYNC_IOC_WAIT_ANY _IOWR('N', 0x82, struct ntsync_wait_args) +#define NTSYNC_IOC_WAIT_ALL _IOWR('N', 0x83, struct ntsync_wait_args) +#define NTSYNC_IOC_CREATE_MUTEX _IOW ('N', 0x84, struct ntsync_mutex_args) +#define NTSYNC_IOC_CREATE_EVENT _IOW ('N', 0x87, struct ntsync_event_args) + +#define NTSYNC_IOC_SEM_RELEASE _IOWR('N', 0x81, __u32) +#define NTSYNC_IOC_MUTEX_UNLOCK _IOWR('N', 0x85, struct ntsync_mutex_args) +#define NTSYNC_IOC_MUTEX_KILL _IOW ('N', 0x86, __u32) +#define NTSYNC_IOC_EVENT_SET _IOR ('N', 0x88, __u32) +#define NTSYNC_IOC_EVENT_RESET _IOR ('N', 0x89, __u32) +#define NTSYNC_IOC_EVENT_PULSE _IOR ('N', 0x8a, __u32) +#define NTSYNC_IOC_SEM_READ _IOR ('N', 0x8b, struct ntsync_sem_args) +#define NTSYNC_IOC_MUTEX_READ _IOR ('N', 0x8c, struct ntsync_mutex_args) +#define NTSYNC_IOC_EVENT_READ _IOR ('N', 0x8d, struct ntsync_event_args) #endif diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 1601c7ed5fab..3445c4970e4d 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -533,7 +533,7 @@ #define PCI_EXP_DEVSTA_TRPND 0x0020 /* Transactions Pending */ #define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V1 12 /* v1 endpoints without link end here */ #define PCI_EXP_LNKCAP 0x0c /* Link Capabilities */ -#define PCI_EXP_LNKCAP_SLS 0x0000000f /* Supported Link Speeds */ +#define PCI_EXP_LNKCAP_SLS 0x0000000f /* Max Link Speed (prior to PCIe r3.0: Supported Link Speeds) */ #define PCI_EXP_LNKCAP_SLS_2_5GB 0x00000001 /* LNKCAP2 SLS Vector bit 0 */ #define PCI_EXP_LNKCAP_SLS_5_0GB 0x00000002 /* LNKCAP2 SLS Vector bit 1 */ #define PCI_EXP_LNKCAP_SLS_8_0GB 0x00000003 /* LNKCAP2 SLS Vector bit 2 */ @@ -665,6 +665,7 @@ #define PCI_EXP_DEVCAP2_OBFF_MSG 0x00040000 /* New message signaling */ #define PCI_EXP_DEVCAP2_OBFF_WAKE 0x00080000 /* Re-use WAKE# for OBFF */ #define PCI_EXP_DEVCAP2_EE_PREFIX 0x00200000 /* End-End TLP Prefix */ +#define PCI_EXP_DEVCAP2_EE_PREFIX_MAX 0x00c00000 /* Max End-End TLP Prefixes */ #define PCI_EXP_DEVCTL2 0x28 /* Device Control 2 */ #define PCI_EXP_DEVCTL2_COMP_TIMEOUT 0x000f /* Completion Timeout Value */ #define PCI_EXP_DEVCTL2_COMP_TMOUT_DIS 0x0010 /* Completion Timeout Disable */ @@ -789,10 +790,11 @@ /* Same bits as above */ #define PCI_ERR_CAP 0x18 /* Advanced Error Capabilities & Ctrl*/ #define PCI_ERR_CAP_FEP(x) ((x) & 0x1f) /* First Error Pointer */ -#define PCI_ERR_CAP_ECRC_GENC 0x00000020 /* ECRC Generation Capable */ -#define PCI_ERR_CAP_ECRC_GENE 0x00000040 /* ECRC Generation Enable */ -#define PCI_ERR_CAP_ECRC_CHKC 0x00000080 /* ECRC Check Capable */ -#define PCI_ERR_CAP_ECRC_CHKE 0x00000100 /* ECRC Check Enable */ +#define PCI_ERR_CAP_ECRC_GENC 0x00000020 /* ECRC Generation Capable */ +#define PCI_ERR_CAP_ECRC_GENE 0x00000040 /* ECRC Generation Enable */ +#define PCI_ERR_CAP_ECRC_CHKC 0x00000080 /* ECRC Check Capable */ +#define PCI_ERR_CAP_ECRC_CHKE 0x00000100 /* ECRC Check Enable */ +#define PCI_ERR_CAP_PREFIX_LOG_PRESENT 0x00000800 /* TLP Prefix Log Present */ #define PCI_ERR_HEADER_LOG 0x1c /* Header Log Register (16 bytes) */ #define PCI_ERR_ROOT_COMMAND 0x2c /* Root Error Command */ #define PCI_ERR_ROOT_CMD_COR_EN 0x00000001 /* Correctable Err Reporting Enable */ @@ -808,6 +810,7 @@ #define PCI_ERR_ROOT_FATAL_RCV 0x00000040 /* Fatal Received */ #define PCI_ERR_ROOT_AER_IRQ 0xf8000000 /* Advanced Error Interrupt Message Number */ #define PCI_ERR_ROOT_ERR_SRC 0x34 /* Error Source Identification */ +#define PCI_ERR_PREFIX_LOG 0x38 /* TLP Prefix LOG Register (up to 16 bytes) */ /* Virtual Channel */ #define PCI_VC_PORT_CAP1 0x04 @@ -1001,9 +1004,6 @@ #define PCI_ACS_CTRL 0x06 /* ACS Control Register */ #define PCI_ACS_EGRESS_CTL_V 0x08 /* ACS Egress Control Vector */ -#define PCI_VSEC_HDR 4 /* extended cap - vendor-specific */ -#define PCI_VSEC_HDR_LEN_SHIFT 20 /* shift for length field */ - /* SATA capability */ #define PCI_SATA_REGS 4 /* SATA REGs specifier */ #define PCI_SATA_REGS_MASK 0xF /* location - BAR#/inline */ diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h index 94b46b043b53..acd261f49866 100644 --- a/include/uapi/linux/pcitest.h +++ b/include/uapi/linux/pcitest.h @@ -20,6 +20,7 @@ #define PCITEST_MSIX _IOW('P', 0x7, int) #define PCITEST_SET_IRQTYPE _IOW('P', 0x8, int) #define PCITEST_GET_IRQTYPE _IO('P', 0x9) +#define PCITEST_BARS _IO('P', 0xa) #define PCITEST_CLEAR_IRQ _IO('P', 0x10) #define PCITEST_FLAGS_USE_DMA 0x00000001 diff --git a/include/uapi/linux/pps_gen.h b/include/uapi/linux/pps_gen.h new file mode 100644 index 000000000000..60a5d0fcfa68 --- /dev/null +++ b/include/uapi/linux/pps_gen.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * PPS generator API header + * + * Copyright (C) 2024 Rodolfo Giometti + */ + +#ifndef _PPS_GEN_H_ +#define _PPS_GEN_H_ + +#include +#include + +/** + * struct pps_gen_event - the PPS generator events + * @event: the event type + * @sequence: the event sequence number + * + * Userspace can get the last PPS generator event by using the + * ioctl(pps_gen, PPS_GEN_FETCHEVENT, ...) syscall. + * The sequence field can be used to save the last event ID, while in the + * event field is stored the last event type. Currently known event is: + * + * PPS_GEN_EVENT_MISSEDPULSE : last pulse was not generated + */ +struct pps_gen_event { + unsigned int event; + unsigned int sequence; +}; + +#define PPS_GEN_EVENT_MISSEDPULSE 1 + +#define PPS_GEN_SETENABLE _IOW('p', 0xb1, unsigned int *) +#define PPS_GEN_USESYSTEMCLOCK _IOR('p', 0xb2, unsigned int *) +#define PPS_GEN_FETCHEVENT _IOR('p', 0xb3, struct pps_gen_event *) + +#endif /* _PPS_GEN_H_ */ diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index 5a43c23f53bf..ff47b6f0ba0f 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -233,7 +233,7 @@ struct mdp_superblock_1 { char set_name[32]; /* set and interpreted by user-space */ __le64 ctime; /* lo 40 bits are seconds, top 24 are microseconds or 0*/ - __le32 level; /* 0,1,4,5 */ + __le32 level; /* 0,1,4,5, -1 (linear) */ __le32 layout; /* only for raid5 and raid10 currently */ __le64 size; /* used size of component devices, in 512byte sectors */ diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h index 7be89a4906e7..a893010735fb 100644 --- a/include/uapi/linux/raid/md_u.h +++ b/include/uapi/linux/raid/md_u.h @@ -103,6 +103,8 @@ typedef struct mdu_array_info_s { } mdu_array_info_t; +#define LEVEL_LINEAR (-1) + /* we need a value for 'no level specified' and 0 * means 'raid0', so we need something else. This is * for internal use only diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index db7254d52d93..66c3903d29cf 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -93,10 +93,18 @@ enum { RTM_NEWPREFIX = 52, #define RTM_NEWPREFIX RTM_NEWPREFIX - RTM_GETMULTICAST = 58, + RTM_NEWMULTICAST = 56, +#define RTM_NEWMULTICAST RTM_NEWMULTICAST + RTM_DELMULTICAST, +#define RTM_DELMULTICAST RTM_DELMULTICAST + RTM_GETMULTICAST, #define RTM_GETMULTICAST RTM_GETMULTICAST - RTM_GETANYCAST = 62, + RTM_NEWANYCAST = 60, +#define RTM_NEWANYCAST RTM_NEWANYCAST + RTM_DELANYCAST, +#define RTM_DELANYCAST RTM_DELANYCAST + RTM_GETANYCAST, #define RTM_GETANYCAST RTM_GETANYCAST RTM_NEWNEIGHTBL = 64, @@ -389,6 +397,7 @@ enum rtattr_type_t { RTA_SPORT, RTA_DPORT, RTA_NH_ID, + RTA_FLOWLABEL, __RTA_MAX }; @@ -774,6 +783,12 @@ enum rtnetlink_groups { #define RTNLGRP_TUNNEL RTNLGRP_TUNNEL RTNLGRP_STATS, #define RTNLGRP_STATS RTNLGRP_STATS + RTNLGRP_IPV4_MCADDR, +#define RTNLGRP_IPV4_MCADDR RTNLGRP_IPV4_MCADDR + RTNLGRP_IPV6_MCADDR, +#define RTNLGRP_IPV6_MCADDR RTNLGRP_IPV6_MCADDR + RTNLGRP_IPV6_ACADDR, +#define RTNLGRP_IPV6_ACADDR RTNLGRP_IPV6_ACADDR __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) diff --git a/include/uapi/linux/securebits.h b/include/uapi/linux/securebits.h index d6d98877ff1a..3fba30dbd68b 100644 --- a/include/uapi/linux/securebits.h +++ b/include/uapi/linux/securebits.h @@ -52,10 +52,32 @@ #define SECBIT_NO_CAP_AMBIENT_RAISE_LOCKED \ (issecure_mask(SECURE_NO_CAP_AMBIENT_RAISE_LOCKED)) +/* See Documentation/userspace-api/check_exec.rst */ +#define SECURE_EXEC_RESTRICT_FILE 8 +#define SECURE_EXEC_RESTRICT_FILE_LOCKED 9 /* make bit-8 immutable */ + +#define SECBIT_EXEC_RESTRICT_FILE (issecure_mask(SECURE_EXEC_RESTRICT_FILE)) +#define SECBIT_EXEC_RESTRICT_FILE_LOCKED \ + (issecure_mask(SECURE_EXEC_RESTRICT_FILE_LOCKED)) + +/* See Documentation/userspace-api/check_exec.rst */ +#define SECURE_EXEC_DENY_INTERACTIVE 10 +#define SECURE_EXEC_DENY_INTERACTIVE_LOCKED 11 /* make bit-10 immutable */ + +#define SECBIT_EXEC_DENY_INTERACTIVE \ + (issecure_mask(SECURE_EXEC_DENY_INTERACTIVE)) +#define SECBIT_EXEC_DENY_INTERACTIVE_LOCKED \ + (issecure_mask(SECURE_EXEC_DENY_INTERACTIVE_LOCKED)) + #define SECURE_ALL_BITS (issecure_mask(SECURE_NOROOT) | \ issecure_mask(SECURE_NO_SETUID_FIXUP) | \ issecure_mask(SECURE_KEEP_CAPS) | \ - issecure_mask(SECURE_NO_CAP_AMBIENT_RAISE)) + issecure_mask(SECURE_NO_CAP_AMBIENT_RAISE) | \ + issecure_mask(SECURE_EXEC_RESTRICT_FILE) | \ + issecure_mask(SECURE_EXEC_DENY_INTERACTIVE)) #define SECURE_ALL_LOCKS (SECURE_ALL_BITS << 1) +#define SECURE_ALL_UNPRIVILEGED (issecure_mask(SECURE_EXEC_RESTRICT_FILE) | \ + issecure_mask(SECURE_EXEC_DENY_INTERACTIVE)) + #endif /* _UAPI_LINUX_SECUREBITS_H */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index adf5fd78dd50..848c7784e684 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -186,6 +186,7 @@ enum LINUX_MIB_TIMEWAITKILLED, /* TimeWaitKilled */ LINUX_MIB_PAWSACTIVEREJECTED, /* PAWSActiveRejected */ LINUX_MIB_PAWSESTABREJECTED, /* PAWSEstabRejected */ + LINUX_MIB_PAWS_OLD_ACK, /* PAWSOldAck */ LINUX_MIB_DELAYEDACKS, /* DelayedACKs */ LINUX_MIB_DELAYEDACKLOCKED, /* DelayedACKLocked */ LINUX_MIB_DELAYEDACKLOST, /* DelayedACKLost */ @@ -339,6 +340,8 @@ enum LINUX_MIB_XFRMACQUIREERROR, /* XfrmAcquireError */ LINUX_MIB_XFRMOUTSTATEDIRERROR, /* XfrmOutStateDirError */ LINUX_MIB_XFRMINSTATEDIRERROR, /* XfrmInStateDirError */ + LINUX_MIB_XFRMINIPTFSERROR, /* XfrmInIptfsError */ + LINUX_MIB_XFRMOUTNOQSPACE, /* XfrmOutNoQueueSpace */ __LINUX_MIB_XFRMMAX }; @@ -358,6 +361,11 @@ enum LINUX_MIB_TLSRXDEVICERESYNC, /* TlsRxDeviceResync */ LINUX_MIB_TLSDECRYPTRETRY, /* TlsDecryptRetry */ LINUX_MIB_TLSRXNOPADVIOL, /* TlsRxNoPadViolation */ + LINUX_MIB_TLSRXREKEYOK, /* TlsRxRekeyOk */ + LINUX_MIB_TLSRXREKEYERROR, /* TlsRxRekeyError */ + LINUX_MIB_TLSTXREKEYOK, /* TlsTxRekeyOk */ + LINUX_MIB_TLSTXREKEYERROR, /* TlsTxRekeyError */ + LINUX_MIB_TLSRXREKEYRECEIVED, /* TlsRxRekeyReceived */ __LINUX_MIB_TLSMAX }; diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 887a25286441..f78ee3670dd5 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -98,43 +98,93 @@ struct statx_timestamp { */ struct statx { /* 0x00 */ - __u32 stx_mask; /* What results were written [uncond] */ - __u32 stx_blksize; /* Preferred general I/O size [uncond] */ - __u64 stx_attributes; /* Flags conveying information about the file [uncond] */ + /* What results were written [uncond] */ + __u32 stx_mask; + + /* Preferred general I/O size [uncond] */ + __u32 stx_blksize; + + /* Flags conveying information about the file [uncond] */ + __u64 stx_attributes; + /* 0x10 */ - __u32 stx_nlink; /* Number of hard links */ - __u32 stx_uid; /* User ID of owner */ - __u32 stx_gid; /* Group ID of owner */ - __u16 stx_mode; /* File mode */ + /* Number of hard links */ + __u32 stx_nlink; + + /* User ID of owner */ + __u32 stx_uid; + + /* Group ID of owner */ + __u32 stx_gid; + + /* File mode */ + __u16 stx_mode; __u16 __spare0[1]; + /* 0x20 */ - __u64 stx_ino; /* Inode number */ - __u64 stx_size; /* File size */ - __u64 stx_blocks; /* Number of 512-byte blocks allocated */ - __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */ + /* Inode number */ + __u64 stx_ino; + + /* File size */ + __u64 stx_size; + + /* Number of 512-byte blocks allocated */ + __u64 stx_blocks; + + /* Mask to show what's supported in stx_attributes */ + __u64 stx_attributes_mask; + /* 0x40 */ - struct statx_timestamp stx_atime; /* Last access time */ - struct statx_timestamp stx_btime; /* File creation time */ - struct statx_timestamp stx_ctime; /* Last attribute change time */ - struct statx_timestamp stx_mtime; /* Last data modification time */ + /* Last access time */ + struct statx_timestamp stx_atime; + + /* File creation time */ + struct statx_timestamp stx_btime; + + /* Last attribute change time */ + struct statx_timestamp stx_ctime; + + /* Last data modification time */ + struct statx_timestamp stx_mtime; + /* 0x80 */ - __u32 stx_rdev_major; /* Device ID of special file [if bdev/cdev] */ + /* Device ID of special file [if bdev/cdev] */ + __u32 stx_rdev_major; __u32 stx_rdev_minor; - __u32 stx_dev_major; /* ID of device containing file [uncond] */ + + /* ID of device containing file [uncond] */ + __u32 stx_dev_major; __u32 stx_dev_minor; + /* 0x90 */ __u64 stx_mnt_id; - __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ - __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ + + /* Memory buffer alignment for direct I/O */ + __u32 stx_dio_mem_align; + + /* File offset alignment for direct I/O */ + __u32 stx_dio_offset_align; + /* 0xa0 */ - __u64 stx_subvol; /* Subvolume identifier */ - __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ - __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* Subvolume identifier */ + __u64 stx_subvol; + + /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_min; + + /* Max atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; + /* 0xb0 */ - __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ - __u32 __spare1[1]; + /* Max atomic write segment count */ + __u32 stx_atomic_write_segments_max; + + /* File offset alignment for direct I/O reads */ + __u32 stx_dio_read_offset_align; + /* 0xb8 */ __u64 __spare3[9]; /* Spare space for future expansion */ + /* 0x100 */ }; @@ -164,6 +214,7 @@ struct statx { #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ #define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ +#define STATX_DIO_READ_ALIGN 0x00020000U /* Want/got dio read alignment info */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 58154117d9b0..a6fce46aeb37 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -8,6 +8,13 @@ #define __always_inline inline #endif +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + /** * __struct_group() - Create a mirrored named and anonyomous struct * @@ -20,13 +27,13 @@ * and size: one anonymous and one named. The former's members can be used * normally without sub-struct naming, and the latter can be used to * reason about the start, end, and size of the group of struct members. - * The named struct can also be explicitly tagged for layer reuse, as well - * as both having struct attributes appended. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. */ #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ union { \ struct { MEMBERS } ATTRS; \ - struct TAG { MEMBERS } ATTRS NAME; \ + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ } ATTRS #ifdef __cplusplus diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index b50b2eb257a0..934e20ef7f79 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -72,6 +72,8 @@ struct taskstats { */ __u64 cpu_count __attribute__((aligned(8))); __u64 cpu_delay_total; + __u64 cpu_delay_max; + __u64 cpu_delay_min; /* Following four fields atomically updated using task->delays->lock */ @@ -80,10 +82,14 @@ struct taskstats { */ __u64 blkio_count; __u64 blkio_delay_total; + __u64 blkio_delay_max; + __u64 blkio_delay_min; /* Delay waiting for page fault I/O (swap in only) */ __u64 swapin_count; __u64 swapin_delay_total; + __u64 swapin_delay_max; + __u64 swapin_delay_min; /* cpu "wall-clock" running time * On some architectures, value will adjust for cpu time stolen @@ -166,10 +172,14 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; + __u64 freepages_delay_max; + __u64 freepages_delay_min; /* Delay waiting for thrashing page */ __u64 thrashing_count; __u64 thrashing_delay_total; + __u64 thrashing_delay_max; + __u64 thrashing_delay_min; /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ @@ -177,6 +187,8 @@ struct taskstats { /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; + __u64 compact_delay_max; + __u64 compact_delay_min; /* v12 begin */ __u32 ac_tgid; /* thread group ID */ @@ -198,10 +210,15 @@ struct taskstats { /* v13: Delay waiting for write-protect copy */ __u64 wpcopy_count; __u64 wpcopy_delay_total; + __u64 wpcopy_delay_max; + __u64 wpcopy_delay_min; /* v14: Delay waiting for IRQ/SOFTIRQ */ __u64 irq_count; __u64 irq_delay_total; + __u64 irq_delay_max; + __u64 irq_delay_min; + /* v15: add Delay max */ }; diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h index ba8604bdf206..349718c271eb 100644 --- a/include/uapi/linux/thermal.h +++ b/include/uapi/linux/thermal.h @@ -3,8 +3,8 @@ #define _UAPI_LINUX_THERMAL_H #define THERMAL_NAME_LENGTH 20 -#define THERMAL_THRESHOLD_WAY_UP BIT(0) -#define THERMAL_THRESHOLD_WAY_DOWN BIT(1) +#define THERMAL_THRESHOLD_WAY_UP 0x1 +#define THERMAL_THRESHOLD_WAY_DOWN 0x2 enum thermal_device_mode { THERMAL_DEVICE_DISABLED = 0, diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index 2ebdba111a8f..beef1752e36e 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -206,7 +206,7 @@ struct usb_ffs_dmabuf_transfer_req { * +-----+-----------------+------+--------------------------+ * | off | name | type | description | * +-----+-----------------+------+--------------------------+ - * | 0 | inteface | U8 | related interface number | + * | 0 | interface | U8 | related interface number | * +-----+-----------------+------+--------------------------+ * | 1 | dwLength | U32 | length of the descriptor | * +-----+-----------------+------+--------------------------+ @@ -224,7 +224,7 @@ struct usb_ffs_dmabuf_transfer_req { * +-----+-----------------+------+--------------------------+ * | off | name | type | description | * +-----+-----------------+------+--------------------------+ - * | 0 | inteface | U8 | related interface number | + * | 0 | interface | U8 | related interface number | * +-----+-----------------+------+--------------------------+ * | 1 | dwLength | U32 | length of the descriptor | * +-----+-----------------+------+--------------------------+ @@ -237,7 +237,7 @@ struct usb_ffs_dmabuf_transfer_req { * | 11 | ExtProp[] | | list of ext. prop. d. | * +-----+-----------------+------+--------------------------+ * - * ExtCompat[] is an array of valid Extended Compatiblity descriptors + * ExtCompat[] is an array of valid Extended Compatibility descriptors * which have the following format: * * +-----+-----------------------+------+-------------------------------------+ @@ -295,7 +295,7 @@ struct usb_functionfs_strings_head { * | 16 | stringtab | StringTab[lang_count] | table of strings per lang | * * For each language there is one stringtab entry (ie. there are lang_count - * stringtab entires). Each StringTab has following format: + * stringtab entries). Each StringTab has following format: * * | off | name | type | description | * |-----+---------+-------------------+------------------------------------| diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h index 11bd48c72c6c..68a627d04afa 100644 --- a/include/uapi/linux/vduse.h +++ b/include/uapi/linux/vduse.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ #ifndef _UAPI_VDUSE_H_ #define _UAPI_VDUSE_H_ diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 1beb317df1b9..8549d4571257 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -116,6 +116,8 @@ #define VIRTIO_PCI_CAP_PCI_CFG 5 /* Additional shared memory capability */ #define VIRTIO_PCI_CAP_SHARED_MEMORY_CFG 8 +/* PCI vendor data configuration */ +#define VIRTIO_PCI_CAP_VENDOR_CFG 9 /* This is the PCI capability header: */ struct virtio_pci_cap { @@ -130,6 +132,18 @@ struct virtio_pci_cap { __le32 length; /* Length of the structure, in bytes. */ }; +/* This is the PCI vendor data capability header: */ +struct virtio_pci_vndr_data { + __u8 cap_vndr; /* Generic PCI field: PCI_CAP_ID_VNDR */ + __u8 cap_next; /* Generic PCI field: next ptr. */ + __u8 cap_len; /* Generic PCI field: capability length */ + __u8 cfg_type; /* Identifies the structure. */ + __u16 vendor_id; /* Identifies the vendor-specific format. */ + /* For Vendor Definition */ + /* Pads structure to a multiple of 4 bytes */ + /* Reads must not have side effects */ +}; + struct virtio_pci_cap64 { struct virtio_pci_cap cap; __le32 offset_hi; /* Most sig 32 bits of offset */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index d73a97e3030a..a23495c0e0a1 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -158,7 +158,8 @@ enum { #define XFRM_MODE_ROUTEOPTIMIZATION 2 #define XFRM_MODE_IN_TRIGGER 3 #define XFRM_MODE_BEET 4 -#define XFRM_MODE_MAX 5 +#define XFRM_MODE_IPTFS 5 +#define XFRM_MODE_MAX 6 /* Netlink configuration messages. */ enum { @@ -323,6 +324,12 @@ enum xfrm_attr_type_t { XFRMA_SA_DIR, /* __u8 */ XFRMA_NAT_KEEPALIVE_INTERVAL, /* __u32 in seconds for NAT keepalive */ XFRMA_SA_PCPU, /* __u32 */ + XFRMA_IPTFS_DROP_TIME, /* __u32 in: usec to wait for next seq */ + XFRMA_IPTFS_REORDER_WINDOW, /* __u16 in: reorder window size (pkts) */ + XFRMA_IPTFS_DONT_FRAG, /* out: don't use fragmentation */ + XFRMA_IPTFS_INIT_DELAY, /* __u32 out: initial packet wait delay (usec) */ + XFRMA_IPTFS_MAX_QSIZE, /* __u32 out: max ingress queue size (octets) */ + XFRMA_IPTFS_PKT_SIZE, /* __u32 out: size of outer packet, 0 for PMTU */ __XFRMA_MAX #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ diff --git a/include/uapi/mtd/ubi-user.h b/include/uapi/mtd/ubi-user.h index e1571603175e..aa872a41ffb9 100644 --- a/include/uapi/mtd/ubi-user.h +++ b/include/uapi/mtd/ubi-user.h @@ -175,6 +175,8 @@ #define UBI_IOCRPEB _IOW(UBI_IOC_MAGIC, 4, __s32) /* Force scrubbing on the specified PEB */ #define UBI_IOCSPEB _IOW(UBI_IOC_MAGIC, 5, __s32) +/* Read detailed device erase counter information */ +#define UBI_IOCECNFO _IOWR(UBI_IOC_MAGIC, 6, struct ubi_ecinfo_req) /* ioctl commands of the UBI control character device */ @@ -412,6 +414,37 @@ struct ubi_rnvol_req { } ents[UBI_MAX_RNVOL]; } __packed; +/** + * struct ubi_ecinfo_req - a data structure used for requesting and receiving + * erase block counter information from a UBI device. + * + * @start: index of first physical erase block to read (in) + * @length: number of erase counters to read (in) + * @read_length: number of erase counters that was actually read (out) + * @padding: reserved for future, not used, has to be zeroed + * @erase_counters: array of erase counter values (out) + * + * This structure is used to retrieve erase counter information for a specified + * range of PEBs on a UBI device. + * Erase counters are read from @start and attempts to read @length number of + * erase counters. + * The retrieved values are stored in the @erase_counters array. It is the + * responsibility of the caller to allocate enough memory for storing @length + * elements in the @erase_counters array. + * If a block is bad or if the erase counter is unknown the corresponding value + * in the array will be set to -1. + * The @read_length field will indicate the number of erase counters actually + * read. Typically @read_length will be limited due to memory or the number of + * PEBs on the UBI device. + */ +struct ubi_ecinfo_req { + __s32 start; + __s32 length; + __s32 read_length; + __s8 padding[16]; + __s32 erase_counters[]; +} __packed; + /** * struct ubi_leb_change_req - a data structure used in atomic LEB change * requests. diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index bc30c1f2a109..a5c41f771e05 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -10,7 +10,7 @@ #include /** version of the sequencer */ -#define SNDRV_SEQ_VERSION SNDRV_PROTOCOL_VERSION(1, 0, 4) +#define SNDRV_SEQ_VERSION SNDRV_PROTOCOL_VERSION(1, 0, 5) /** * definition of sequencer event types @@ -92,6 +92,9 @@ #define SNDRV_SEQ_EVENT_PORT_SUBSCRIBED 66 /* ports connected */ #define SNDRV_SEQ_EVENT_PORT_UNSUBSCRIBED 67 /* ports disconnected */ +#define SNDRV_SEQ_EVENT_UMP_EP_CHANGE 68 /* UMP EP info has changed */ +#define SNDRV_SEQ_EVENT_UMP_BLOCK_CHANGE 69 /* UMP block info has changed */ + /* 70-89: synthesizer events - obsoleted */ /** user-defined events with fixed length @@ -253,6 +256,12 @@ struct snd_seq_ev_quote { struct snd_seq_event *event; /* quoted event */ } __packed; + /* UMP info change notify */ +struct snd_seq_ev_ump_notify { + unsigned char client; /**< Client number */ + unsigned char block; /**< Block number (optional) */ +}; + union snd_seq_event_data { /* event data... */ struct snd_seq_ev_note note; struct snd_seq_ev_ctrl control; @@ -265,6 +274,7 @@ union snd_seq_event_data { /* event data... */ struct snd_seq_connect connect; struct snd_seq_result result; struct snd_seq_ev_quote quote; + struct snd_seq_ev_ump_notify ump_notify; }; /* sequencer event */ diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 4cd513215bcd..5a049eeaecce 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -716,7 +716,7 @@ enum { * Raw MIDI section - /dev/snd/midi?? */ -#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 4) +#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 5) enum { SNDRV_RAWMIDI_STREAM_OUTPUT = 0, @@ -728,6 +728,9 @@ enum { #define SNDRV_RAWMIDI_INFO_INPUT 0x00000002 #define SNDRV_RAWMIDI_INFO_DUPLEX 0x00000004 #define SNDRV_RAWMIDI_INFO_UMP 0x00000008 +#define SNDRV_RAWMIDI_INFO_STREAM_INACTIVE 0x00000010 + +#define SNDRV_RAWMIDI_DEVICE_UNKNOWN 0 struct snd_rawmidi_info { unsigned int device; /* RO/WR (control): device number */ @@ -740,7 +743,8 @@ struct snd_rawmidi_info { unsigned char subname[32]; /* name of active or selected subdevice */ unsigned int subdevices_count; unsigned int subdevices_avail; - unsigned char reserved[64]; /* reserved for future use */ + int tied_device; /* R: tied rawmidi device (UMP/legacy) */ + unsigned char reserved[60]; /* reserved for future use */ }; #define SNDRV_RAWMIDI_MODE_FRAMING_MASK (7<<0) diff --git a/include/uapi/sound/compress_params.h b/include/uapi/sound/compress_params.h index ddc77322d571..bc7648a30746 100644 --- a/include/uapi/sound/compress_params.h +++ b/include/uapi/sound/compress_params.h @@ -334,6 +334,14 @@ union snd_codec_options { struct snd_dec_wma wma_d; struct snd_dec_alac alac_d; struct snd_dec_ape ape_d; + struct { + __u32 out_sample_rate; + } src_d; +} __attribute__((packed, aligned(4))); + +struct snd_codec_desc_src { + __u32 out_sample_rate_min; + __u32 out_sample_rate_max; } __attribute__((packed, aligned(4))); /** struct snd_codec_desc - description of codec capabilities @@ -347,6 +355,9 @@ union snd_codec_options { * @modes: Supported modes. See SND_AUDIOMODE defines * @formats: Supported formats. See SND_AUDIOSTREAMFORMAT defines * @min_buffer: Minimum buffer size handled by codec implementation + * @pcm_formats: Output (for decoders) or input (for encoders) + * PCM formats (required to accel mode, 0 for other modes) + * @u_space: union space (for codec dependent data) * @reserved: reserved for future use * * This structure provides a scalar value for profiles, modes and stream @@ -370,7 +381,12 @@ struct snd_codec_desc { __u32 modes; __u32 formats; __u32 min_buffer; - __u32 reserved[15]; + __u32 pcm_formats; + union { + __u32 u_space[6]; + struct snd_codec_desc_src src; + } __attribute__((packed, aligned(4))); + __u32 reserved[8]; } __attribute__((packed, aligned(4))); /** struct snd_codec @@ -395,6 +411,8 @@ struct snd_codec_desc { * @align: Block alignment in bytes of an audio sample. * Only required for PCM or IEC formats. * @options: encoder-specific settings + * @pcm_format: Output (for decoders) or input (for encoders) + * PCM formats (required to accel mode, 0 for other modes) * @reserved: reserved for future use */ @@ -411,7 +429,8 @@ struct snd_codec { __u32 format; __u32 align; union snd_codec_options options; - __u32 reserved[3]; + __u32 pcm_format; + __u32 reserved[2]; } __attribute__((packed, aligned(4))); #endif diff --git a/include/uapi/sound/fcp.h b/include/uapi/sound/fcp.h new file mode 100644 index 000000000000..aea428956d8f --- /dev/null +++ b/include/uapi/sound/fcp.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Focusrite Control Protocol Driver for ALSA + * + * Copyright (c) 2024-2025 by Geoffrey D. Bennett + */ +/* + * DOC: FCP (Focusrite Control Protocol) User-Space API + * + * This header defines the interface between the FCP kernel driver and + * user-space programs to enable the use of the proprietary features + * available in Focusrite USB audio interfaces. This includes Scarlett + * 2nd Gen, 3rd Gen, 4th Gen, Clarett USB, Clarett+, and Vocaster + * series devices. + * + * The interface is provided via ALSA's hwdep interface. Opening the + * hwdep device requires CAP_SYS_RAWIO privileges as this interface + * provides near-direct access. + * + * For details on the FCP protocol, refer to the kernel scarlett2 + * driver in sound/usb/mixer_scarlett2.c and the fcp-support project + * at https://github.com/geoffreybennett/fcp-support + * + * For examples of using these IOCTLs, see the fcp-server source in + * the fcp-support project. + * + * IOCTL Interface + * -------------- + * FCP_IOCTL_PVERSION: + * Returns the protocol version supported by the driver. + * + * FCP_IOCTL_INIT: + * Initialises the protocol and synchronises sequence numbers + * between the driver and device. Must be called at least once + * before sending commands. Can be safely called again at any time. + * + * FCP_IOCTL_CMD: + * Sends an FCP command to the device and returns the response. + * Requires prior initialisation via FCP_IOCTL_INIT. + * + * FCP_IOCTL_SET_METER_MAP: + * Configures the Level Meter control's mapping between device + * meters and control channels. Requires FCP_IOCTL_INIT to have been + * called first. The map size and number of slots cannot be changed + * after initial configuration, although the map itself can be + * updated. Once configured, the Level Meter remains functional even + * after the hwdep device is closed. + * + * FCP_IOCTL_SET_METER_LABELS: + * Set the labels for the Level Meter control. Requires + * FCP_IOCTL_SET_METER_MAP to have been called first. labels[] + * should contain a sequence of null-terminated labels corresponding + * to the control's channels. + */ +#ifndef __UAPI_SOUND_FCP_H +#define __UAPI_SOUND_FCP_H + +#include +#include + +#define FCP_HWDEP_MAJOR 2 +#define FCP_HWDEP_MINOR 0 +#define FCP_HWDEP_SUBMINOR 0 + +#define FCP_HWDEP_VERSION \ + ((FCP_HWDEP_MAJOR << 16) | \ + (FCP_HWDEP_MINOR << 8) | \ + FCP_HWDEP_SUBMINOR) + +#define FCP_HWDEP_VERSION_MAJOR(v) (((v) >> 16) & 0xFF) +#define FCP_HWDEP_VERSION_MINOR(v) (((v) >> 8) & 0xFF) +#define FCP_HWDEP_VERSION_SUBMINOR(v) ((v) & 0xFF) + +/* Get protocol version */ +#define FCP_IOCTL_PVERSION _IOR('S', 0x60, int) + +/* Start the protocol */ + +/* Step 0 and step 2 responses are variable length and placed in + * resp[] one after the other. + */ +struct fcp_init { + __u16 step0_resp_size; + __u16 step2_resp_size; + __u32 init1_opcode; + __u32 init2_opcode; + __u8 resp[]; +} __attribute__((packed)); + +#define FCP_IOCTL_INIT _IOWR('S', 0x64, struct fcp_init) + +/* Perform a command */ + +/* The request data is placed in data[] and the response data will + * overwrite it. + */ +struct fcp_cmd { + __u32 opcode; + __u16 req_size; + __u16 resp_size; + __u8 data[]; +} __attribute__((packed)); +#define FCP_IOCTL_CMD _IOWR('S', 0x65, struct fcp_cmd) + +/* Set the meter map */ +struct fcp_meter_map { + __u16 map_size; + __u16 meter_slots; + __s16 map[]; +} __attribute__((packed)); +#define FCP_IOCTL_SET_METER_MAP _IOW('S', 0x66, struct fcp_meter_map) + +/* Set the meter labels */ +struct fcp_meter_labels { + __u16 labels_size; + char labels[]; +} __attribute__((packed)); +#define FCP_IOCTL_SET_METER_LABELS _IOW('S', 0x67, struct fcp_meter_labels) + +#endif /* __UAPI_SOUND_FCP_H */ diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index 0a246bc218d3..c28c766270de 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -153,6 +153,8 @@ /* Stream */ #define SOF_TKN_STREAM_PLAYBACK_COMPATIBLE_D0I3 1200 #define SOF_TKN_STREAM_CAPTURE_COMPATIBLE_D0I3 1201 +#define SOF_TKN_STREAM_PLAYBACK_PAUSE_SUPPORTED 1202 +#define SOF_TKN_STREAM_CAPTURE_PAUSE_SUPPORTED 1203 /* Led control for mute switches */ #define SOF_TKN_MUTE_LED_USE 1300 diff --git a/include/uapi/sound/tlv.h b/include/uapi/sound/tlv.h index b99a2414b53d..5bb55c80e095 100644 --- a/include/uapi/sound/tlv.h +++ b/include/uapi/sound/tlv.h @@ -18,6 +18,8 @@ #define SNDRV_CTL_TLVT_CHMAP_VAR 0x102 /* channels freely swappable */ #define SNDRV_CTL_TLVT_CHMAP_PAIRED 0x103 /* pair-wise swappable */ +#define SNDRV_CTL_TLVT_FCP_CHANNEL_LABELS 0x110 /* channel labels */ + /* * TLV structure is right behind the struct snd_ctl_tlv: * unsigned int type - see SNDRV_CTL_TLVT_* diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h index e594abe5d05f..89672ad8c3bb 100644 --- a/include/ufs/ufs.h +++ b/include/ufs/ufs.h @@ -180,7 +180,6 @@ enum attr_idn { QUERY_ATTR_IDN_AVAIL_WB_BUFF_SIZE = 0x1D, QUERY_ATTR_IDN_WB_BUFF_LIFE_TIME_EST = 0x1E, QUERY_ATTR_IDN_CURR_WB_BUFF_SIZE = 0x1F, - QUERY_ATTR_IDN_EXT_IID_EN = 0x2A, QUERY_ATTR_IDN_TIMESTAMP = 0x30 }; @@ -391,7 +390,6 @@ enum { UFS_DEV_EXT_TEMP_NOTIF = BIT(6), UFS_DEV_HPB_SUPPORT = BIT(7), UFS_DEV_WRITE_BOOSTER_SUP = BIT(8), - UFS_DEV_EXT_IID_SUP = BIT(16), }; #define UFS_DEV_HPB_SUPPORT_VERSION 0x310 @@ -585,9 +583,6 @@ struct ufs_dev_info { bool b_advanced_rpmb_en; - /* UFS EXT_IID Enable */ - bool b_ext_iid_en; - /* UFS RTC */ enum ufs_rtc_time rtc_type; time64_t rtc_time_baseline; diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index d650ae6b58d3..650ff238cd74 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -326,10 +326,8 @@ struct ufs_pwr_mode_info { * @phy_initialization: used to initialize phys * @device_reset: called to issue a reset pulse on the UFS device * @config_scaling_param: called to configure clock scaling parameters - * @program_key: program or evict an inline encryption key * @fill_crypto_prdt: initialize crypto-related fields in the PRDT * @event_notify: called to notify important events - * @reinit_notify: called to notify reinit of UFSHCD during max gear switch * @mcq_config_resource: called to configure MCQ platform resources * @get_hba_mac: reports maximum number of outstanding commands supported by * the controller. Should be implemented for UFSHCI 4.0 or later @@ -374,14 +372,11 @@ struct ufs_hba_variant_ops { void (*config_scaling_param)(struct ufs_hba *hba, struct devfreq_dev_profile *profile, struct devfreq_simple_ondemand_data *data); - int (*program_key)(struct ufs_hba *hba, - const union ufs_crypto_cfg_entry *cfg, int slot); int (*fill_crypto_prdt)(struct ufs_hba *hba, const struct bio_crypt_ctx *crypt_ctx, void *prdt, unsigned int num_segments); void (*event_notify)(struct ufs_hba *hba, enum ufs_event_type evt, void *data); - void (*reinit_notify)(struct ufs_hba *); int (*mcq_config_resource)(struct ufs_hba *hba); int (*get_hba_mac)(struct ufs_hba *hba); int (*op_runtime_config)(struct ufs_hba *hba); @@ -405,6 +400,9 @@ enum clk_gating_state { * delay_ms * @ungate_work: worker to turn on clocks that will be used in case of * interrupt context + * @clk_gating_workq: workqueue for clock gating work. + * @lock: serialize access to some struct ufs_clk_gating members. An outer lock + * relative to the host lock * @state: the current clocks state * @delay_ms: gating delay in ms * @is_suspended: clk gating is suspended when set to 1 which can be used @@ -415,11 +413,14 @@ enum clk_gating_state { * @is_initialized: Indicates whether clock gating is initialized or not * @active_reqs: number of requests that are pending and should be waited for * completion before gating clocks. - * @clk_gating_workq: workqueue for clock gating work. */ struct ufs_clk_gating { struct delayed_work gate_work; struct work_struct ungate_work; + struct workqueue_struct *clk_gating_workq; + + spinlock_t lock; + enum clk_gating_state state; unsigned long delay_ms; bool is_suspended; @@ -428,11 +429,14 @@ struct ufs_clk_gating { bool is_enabled; bool is_initialized; int active_reqs; - struct workqueue_struct *clk_gating_workq; }; /** * struct ufs_clk_scaling - UFS clock scaling related data + * @workq: workqueue to schedule devfreq suspend/resume work + * @suspend_work: worker to suspend devfreq + * @resume_work: worker to resume devfreq + * @lock: serialize access to some struct ufs_clk_scaling members * @active_reqs: number of requests that are pending. If this is zero when * devfreq ->target() function is called then schedule "suspend_work" to * suspend devfreq. @@ -442,9 +446,6 @@ struct ufs_clk_gating { * @enable_attr: sysfs attribute to enable/disable clock scaling * @saved_pwr_info: UFS power mode may also be changed during scaling and this * one keeps track of previous power mode. - * @workq: workqueue to schedule devfreq suspend/resume work - * @suspend_work: worker to suspend devfreq - * @resume_work: worker to resume devfreq * @target_freq: frequency requested by devfreq framework * @min_gear: lowest HS gear to scale down to * @is_enabled: tracks if scaling is currently enabled or not, controlled by @@ -456,15 +457,18 @@ struct ufs_clk_gating { * @is_suspended: tracks if devfreq is suspended or not */ struct ufs_clk_scaling { + struct workqueue_struct *workq; + struct work_struct suspend_work; + struct work_struct resume_work; + + spinlock_t lock; + int active_reqs; unsigned long tot_busy_t; ktime_t window_start_t; ktime_t busy_start_t; struct device_attribute enable_attr; struct ufs_pa_layer_attr saved_pwr_info; - struct workqueue_struct *workq; - struct work_struct suspend_work; - struct work_struct resume_work; unsigned long target_freq; u32 min_gear; bool is_enabled; @@ -948,7 +952,6 @@ enum ufshcd_mcq_opr { * @nr_queues: number of Queues of different queue types * @complete_put: whether or not to call ufshcd_rpm_put() from inside * ufshcd_resume_complete() - * @ext_iid_sup: is EXT_IID is supported by UFSHC * @mcq_sup: is mcq supported by UFSHC * @mcq_enabled: is mcq ready to accept requests * @res: array of resource info of MCQ registers @@ -1114,7 +1117,6 @@ struct ufs_hba { unsigned int nr_hw_queues; unsigned int nr_queues[HCTX_MAX_TYPES]; bool complete_put; - bool ext_iid_sup; bool scsi_host_added; bool mcq_sup; bool lsdb_sup; @@ -1204,6 +1206,14 @@ static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba) ({ (void)(hba); BUILD_BUG_ON(sg_entry_size != sizeof(struct ufshcd_sg_entry)); }) #endif +#ifdef CONFIG_SCSI_UFS_CRYPTO +static inline struct ufs_hba * +ufs_hba_from_crypto_profile(struct blk_crypto_profile *profile) +{ + return container_of(profile, struct ufs_hba, crypto_profile); +} +#endif + static inline size_t ufshcd_get_ucd_size(const struct ufs_hba *hba) { return sizeof(struct utp_transfer_cmd_desc) + SG_ALL * ufshcd_sg_entry_size(hba); diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h index 27364c4a6ef9..612500a7088f 100644 --- a/include/ufs/ufshci.h +++ b/include/ufs/ufshci.h @@ -82,11 +82,6 @@ enum { MASK_MCQ_SUPPORT = 0x40000000, }; -/* MCQ capability mask */ -enum { - MASK_EXT_IID_SUPPORT = 0x00000400, -}; - enum { REG_SQATTR = 0x0, REG_SQLBA = 0x4, diff --git a/include/vdso/page.h b/include/vdso/page.h index 710ae2414e68..bc47186c07fc 100644 --- a/include/vdso/page.h +++ b/include/vdso/page.h @@ -8,7 +8,7 @@ * PAGE_SHIFT determines the page size. * * Note: This definition is required because PAGE_SHIFT is used - * in several places throuout the codebase. + * in several places throughout the codebase. */ #define PAGE_SHIFT CONFIG_PAGE_SHIFT diff --git a/init/Kconfig b/init/Kconfig index a20e6efd3f0f..d0d021b3fa3b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -129,6 +129,9 @@ config CC_HAS_COUNTED_BY # https://github.com/llvm/llvm-project/pull/112636 depends on !(CC_IS_CLANG && CLANG_VERSION < 190103) +config RUSTC_HAS_COERCE_POINTEE + def_bool RUSTC_VERSION >= 108400 + config PAHOLE_VERSION int default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE)) @@ -1136,6 +1139,16 @@ config CGROUP_RDMA Attaching processes with active RDMA resources to the cgroup hierarchy is allowed even if can cross the hierarchy's limit. +config CGROUP_DMEM + bool "Device memory controller (DMEM)" + select PAGE_COUNTER + help + The DMEM controller allows compatible devices to restrict device + memory usage based on the cgroup hierarchy. + + As an example, it allows you to restrict VRAM usage for applications + in the DRM subsystem. + config CGROUP_FREEZER bool "Freezer controller" help @@ -1956,7 +1969,8 @@ config RUST bool "Rust support" depends on HAVE_RUST depends on RUST_IS_AVAILABLE - depends on !MODVERSIONS + select EXTENDED_MODVERSIONS if MODVERSIONS + depends on !MODVERSIONS || GENDWARFKSYMS depends on !GCC_PLUGIN_RANDSTRUCT depends on !RANDSTRUCT depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE @@ -1989,8 +2003,10 @@ config BINDGEN_VERSION_TEXT string depends on RUST # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 - # (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when - # the minimum version is upgraded past that (0.69.1 already fixed the issue). + # (https://github.com/rust-lang/rust-bindgen/pull/2678) and 0.71.0 + # (https://github.com/rust-lang/rust-bindgen/pull/3040). It can be removed + # when the minimum version is upgraded past the latter (0.69.1 and 0.71.1 + # both fixed the issue). default "$(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null)" # diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 22c7f41ff642..f6867bad0d78 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -21,7 +21,7 @@ phys_addr_t phys_initrd_start __initdata; unsigned long phys_initrd_size __initdata; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_do_mounts_initrd_table[] = { +static const struct ctl_table kern_do_mounts_initrd_table[] = { { .procname = "real-root-dev", .data = &real_root_dev, @@ -89,7 +89,7 @@ static void __init handle_initrd(char *root_device_name) extern char *envp_init[]; int error; - pr_warn("using deprecated initrd support, will be removed in 2021.\n"); + pr_warn("using deprecated initrd support, will be removed soon.\n"); real_root_dev = new_encode_dev(ROOT_DEV); create_dev("/dev/root.old", Root_RAM0); diff --git a/init/main.c b/init/main.c index 00fac1170294..2a1757826397 100644 --- a/init/main.c +++ b/init/main.c @@ -640,15 +640,11 @@ static void __init setup_command_line(char *command_line) len = xlen + strlen(boot_command_line) + ilen + 1; - saved_command_line = memblock_alloc(len, SMP_CACHE_BYTES); - if (!saved_command_line) - panic("%s: Failed to allocate %zu bytes\n", __func__, len); + saved_command_line = memblock_alloc_or_panic(len, SMP_CACHE_BYTES); len = xlen + strlen(command_line) + 1; - static_command_line = memblock_alloc(len, SMP_CACHE_BYTES); - if (!static_command_line) - panic("%s: Failed to allocate %zu bytes\n", __func__, len); + static_command_line = memblock_alloc_or_panic(len, SMP_CACHE_BYTES); if (xlen) { /* @@ -992,6 +988,7 @@ void start_kernel(void) workqueue_init_early(); rcu_init(); + kvfree_rcu_init(); /* Trace events are available after this */ trace_init(); @@ -1145,16 +1142,10 @@ static int __init initcall_blacklist(char *str) str_entry = strsep(&str, ","); if (str_entry) { pr_debug("blacklisting initcall %s\n", str_entry); - entry = memblock_alloc(sizeof(*entry), + entry = memblock_alloc_or_panic(sizeof(*entry), SMP_CACHE_BYTES); - if (!entry) - panic("%s: Failed to allocate %zu bytes\n", - __func__, sizeof(*entry)); - entry->buf = memblock_alloc(strlen(str_entry) + 1, + entry->buf = memblock_alloc_or_panic(strlen(str_entry) + 1, SMP_CACHE_BYTES); - if (!entry->buf) - panic("%s: Failed to allocate %zu bytes\n", - __func__, strlen(str_entry) + 1); strcpy(entry->buf, str_entry); list_add(&entry->next, &blacklisted_initcalls); } diff --git a/io_uring/Makefile b/io_uring/Makefile index 53167bef37d7..d695b60dba4f 100644 --- a/io_uring/Makefile +++ b/io_uring/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_IO_URING) += io_uring.o opdef.o kbuf.o rsrc.o notif.o \ sync.o msg_ring.o advise.o openclose.o \ epoll.o statx.o timeout.o fdinfo.o \ cancel.o waitid.o register.o \ - truncate.o memmap.o + truncate.o memmap.o alloc_cache.o obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FUTEX) += futex.o obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o diff --git a/io_uring/alloc_cache.c b/io_uring/alloc_cache.c new file mode 100644 index 000000000000..58423888b736 --- /dev/null +++ b/io_uring/alloc_cache.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "alloc_cache.h" + +void io_alloc_cache_free(struct io_alloc_cache *cache, + void (*free)(const void *)) +{ + void *entry; + + if (!cache->entries) + return; + + while ((entry = io_alloc_cache_get(cache)) != NULL) + free(entry); + + kvfree(cache->entries); + cache->entries = NULL; +} + +/* returns false if the cache was initialized properly */ +bool io_alloc_cache_init(struct io_alloc_cache *cache, + unsigned max_nr, unsigned int size, + unsigned int init_bytes) +{ + cache->entries = kvmalloc_array(max_nr, sizeof(void *), GFP_KERNEL); + if (!cache->entries) + return true; + + cache->nr_cached = 0; + cache->max_cached = max_nr; + cache->elem_size = size; + cache->init_clear = init_bytes; + return false; +} + +void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp) +{ + void *obj; + + obj = kmalloc(cache->elem_size, gfp); + if (obj && cache->init_clear) + memset(obj, 0, cache->init_clear); + return obj; +} diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h index b7a38a2069cf..0dd17d8ba93a 100644 --- a/io_uring/alloc_cache.h +++ b/io_uring/alloc_cache.h @@ -1,11 +1,30 @@ #ifndef IOU_ALLOC_CACHE_H #define IOU_ALLOC_CACHE_H +#include + /* * Don't allow the cache to grow beyond this size. */ #define IO_ALLOC_CACHE_MAX 128 +void io_alloc_cache_free(struct io_alloc_cache *cache, + void (*free)(const void *)); +bool io_alloc_cache_init(struct io_alloc_cache *cache, + unsigned max_nr, unsigned int size, + unsigned int init_bytes); + +void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp); + +static inline void io_alloc_cache_kasan(struct iovec **iov, int *nr) +{ + if (IS_ENABLED(CONFIG_KASAN)) { + kfree(*iov); + *iov = NULL; + *nr = 0; + } +} + static inline bool io_alloc_cache_put(struct io_alloc_cache *cache, void *entry) { @@ -23,39 +42,30 @@ static inline void *io_alloc_cache_get(struct io_alloc_cache *cache) if (cache->nr_cached) { void *entry = cache->entries[--cache->nr_cached]; + /* + * If KASAN is enabled, always clear the initial bytes that + * must be zeroed post alloc, in case any of them overlap + * with KASAN storage. + */ +#if defined(CONFIG_KASAN) kasan_mempool_unpoison_object(entry, cache->elem_size); + if (cache->init_clear) + memset(entry, 0, cache->init_clear); +#endif return entry; } return NULL; } -/* returns false if the cache was initialized properly */ -static inline bool io_alloc_cache_init(struct io_alloc_cache *cache, - unsigned max_nr, size_t size) +static inline void *io_cache_alloc(struct io_alloc_cache *cache, gfp_t gfp) { - cache->entries = kvmalloc_array(max_nr, sizeof(void *), GFP_KERNEL); - if (cache->entries) { - cache->nr_cached = 0; - cache->max_cached = max_nr; - cache->elem_size = size; - return false; - } - return true; + void *obj; + + obj = io_alloc_cache_get(cache); + if (obj) + return obj; + return io_cache_alloc_new(cache, gfp); } -static inline void io_alloc_cache_free(struct io_alloc_cache *cache, - void (*free)(const void *)) -{ - void *entry; - - if (!cache->entries) - return; - - while ((entry = io_alloc_cache_get(cache)) != NULL) - free(entry); - - kvfree(cache->entries); - cache->entries = NULL; -} #endif diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index fab936d31ba8..100d5da94cb9 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -33,20 +33,18 @@ static void io_eventfd_free(struct rcu_head *rcu) kfree(ev_fd); } +static void io_eventfd_put(struct io_ev_fd *ev_fd) +{ + if (refcount_dec_and_test(&ev_fd->refs)) + call_rcu(&ev_fd->rcu, io_eventfd_free); +} + static void io_eventfd_do_signal(struct rcu_head *rcu) { struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); - - if (refcount_dec_and_test(&ev_fd->refs)) - io_eventfd_free(rcu); -} - -static void io_eventfd_put(struct io_ev_fd *ev_fd) -{ - if (refcount_dec_and_test(&ev_fd->refs)) - call_rcu(&ev_fd->rcu, io_eventfd_free); + io_eventfd_put(ev_fd); } static void io_eventfd_release(struct io_ev_fd *ev_fd, bool put_ref) diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index b214e5a407b5..f60d0a9d505e 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -211,10 +211,11 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) if (ctx->file_table.data.nodes[i]) f = io_slot_file(ctx->file_table.data.nodes[i]); - if (f) - seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); - else - seq_printf(m, "%5u: \n", i); + if (f) { + seq_printf(m, "%5u: ", i); + seq_file_path(m, f, " \t\n\\"); + seq_puts(m, "\n"); + } } seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr); for (i = 0; has_lock && i < ctx->buf_table.nr; i++) { diff --git a/io_uring/filetable.c b/io_uring/filetable.c index a21660e3145a..dd8eeec97acf 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -68,7 +68,7 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, if (slot_index >= ctx->file_table.data.nr) return -EINVAL; - node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE); + node = io_rsrc_node_alloc(IORING_RSRC_FILE); if (!node) return -ENOMEM; diff --git a/io_uring/futex.c b/io_uring/futex.c index e29662f039e1..3159a2b7eeca 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -36,7 +36,7 @@ struct io_futex_data { bool io_futex_cache_init(struct io_ring_ctx *ctx) { return io_alloc_cache_init(&ctx->futex_cache, IO_FUTEX_ALLOC_CACHE_MAX, - sizeof(struct io_futex_data)); + sizeof(struct io_futex_data), 0); } void io_futex_cache_free(struct io_ring_ctx *ctx) @@ -251,17 +251,6 @@ static void io_futex_wake_fn(struct wake_q_head *wake_q, struct futex_q *q) io_req_task_work_add(req); } -static struct io_futex_data *io_alloc_ifd(struct io_ring_ctx *ctx) -{ - struct io_futex_data *ifd; - - ifd = io_alloc_cache_get(&ctx->futex_cache); - if (ifd) - return ifd; - - return kmalloc(sizeof(struct io_futex_data), GFP_NOWAIT); -} - int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags) { struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); @@ -331,7 +320,7 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags) } io_ring_submit_lock(ctx, issue_flags); - ifd = io_alloc_ifd(ctx); + ifd = io_cache_alloc(&ctx->futex_cache, GFP_NOWAIT); if (!ifd) { ret = -ENOMEM; goto done_unlock; diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index a38f36b68060..5d0928f37471 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -634,7 +634,7 @@ static int io_wq_worker(void *data) struct io_wq_acct *acct = io_wq_get_acct(worker); struct io_wq *wq = worker->wq; bool exit_mask = false, last_timeout = false; - char buf[TASK_COMM_LEN]; + char buf[TASK_COMM_LEN] = {}; set_mask_bits(&worker->flags, 0, BIT(IO_WORKER_F_UP) | BIT(IO_WORKER_F_RUNNING)); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 06ff41484e29..ceacf6230e34 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -115,7 +115,7 @@ REQ_F_ASYNC_DATA) #define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\ - IO_REQ_CLEAN_FLAGS) + REQ_F_REISSUE | IO_REQ_CLEAN_FLAGS) #define IO_TCTX_REFS_CACHE_NR (1U << 10) @@ -143,7 +143,8 @@ struct io_defer_entry { static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct io_uring_task *tctx, - bool cancel_all); + bool cancel_all, + bool is_sqpoll_thread); static void io_queue_sqe(struct io_kiocb *req); @@ -156,7 +157,7 @@ static int __read_mostly sysctl_io_uring_disabled; static int __read_mostly sysctl_io_uring_group = -1; #ifdef CONFIG_SYSCTL -static struct ctl_table kernel_io_uring_disabled_table[] = { +static const struct ctl_table kernel_io_uring_disabled_table[] = { { .procname = "io_uring_disabled", .data = &sysctl_io_uring_disabled, @@ -215,9 +216,9 @@ bool io_match_task_safe(struct io_kiocb *head, struct io_uring_task *tctx, struct io_ring_ctx *ctx = head->ctx; /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); } else { matched = io_match_linked(head); } @@ -314,16 +315,18 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->cq_overflow_list); INIT_LIST_HEAD(&ctx->io_buffers_cache); ret = io_alloc_cache_init(&ctx->apoll_cache, IO_POLL_ALLOC_CACHE_MAX, - sizeof(struct async_poll)); + sizeof(struct async_poll), 0); ret |= io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct io_async_msghdr)); + sizeof(struct io_async_msghdr), + offsetof(struct io_async_msghdr, clear)); ret |= io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct io_async_rw)); + sizeof(struct io_async_rw), + offsetof(struct io_async_rw, clear)); ret |= io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct uring_cache)); + sizeof(struct io_uring_cmd_data), 0); spin_lock_init(&ctx->msg_lock); ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct io_kiocb)); + sizeof(struct io_kiocb), 0); ret |= io_futex_cache_init(ctx); if (ret) goto free_ref; @@ -333,7 +336,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) init_waitqueue_head(&ctx->cq_wait); init_waitqueue_head(&ctx->poll_wq); spin_lock_init(&ctx->completion_lock); - spin_lock_init(&ctx->timeout_lock); + raw_spin_lock_init(&ctx->timeout_lock); INIT_WQ_LIST(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->io_buffers_comp); INIT_LIST_HEAD(&ctx->defer_list); @@ -350,7 +353,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_WQ_LIST(&ctx->submit_state.compl_reqs); INIT_HLIST_HEAD(&ctx->cancelable_uring_cmd); io_napi_init(ctx); - mutex_init(&ctx->resize_lock); + mutex_init(&ctx->mmap_lock); return ctx; @@ -361,7 +364,7 @@ err: io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free); io_alloc_cache_free(&ctx->uring_cache, kfree); - io_alloc_cache_free(&ctx->msg_cache, io_msg_cache_free); + io_alloc_cache_free(&ctx->msg_cache, kfree); io_futex_cache_free(ctx); kvfree(ctx->cancel_table.hbs); xa_destroy(&ctx->io_bl_xa); @@ -498,10 +501,10 @@ static void io_prep_async_link(struct io_kiocb *req) if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); io_for_each_link(cur, req) io_prep_async_work(cur); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); } else { io_for_each_link(cur, req) io_prep_async_work(cur); @@ -514,7 +517,11 @@ static void io_queue_iowq(struct io_kiocb *req) struct io_uring_task *tctx = req->tctx; BUG_ON(!tctx); - BUG_ON(!tctx->io_wq); + + if ((current->flags & PF_KTHREAD) || !tctx->io_wq) { + io_req_task_queue_fail(req, -ECANCELED); + return; + } /* init ->work of the whole link before punting */ io_prep_async_link(req); @@ -546,8 +553,9 @@ void io_req_queue_iowq(struct io_kiocb *req) io_req_task_work_add(req); } -static __cold void io_queue_deferred(struct io_ring_ctx *ctx) +static __cold noinline void io_queue_deferred(struct io_ring_ctx *ctx) { + spin_lock(&ctx->completion_lock); while (!list_empty(&ctx->defer_list)) { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); @@ -558,6 +566,7 @@ static __cold void io_queue_deferred(struct io_ring_ctx *ctx) io_req_task_queue(de->req); kfree(de); } + spin_unlock(&ctx->completion_lock); } void __io_commit_cqring_flush(struct io_ring_ctx *ctx) @@ -566,11 +575,8 @@ void __io_commit_cqring_flush(struct io_ring_ctx *ctx) io_poll_wq_wake(ctx); if (ctx->off_timeout_used) io_flush_timeouts(ctx); - if (ctx->drain_active) { - spin_lock(&ctx->completion_lock); + if (ctx->drain_active) io_queue_deferred(ctx); - spin_unlock(&ctx->completion_lock); - } if (ctx->has_evfd) io_eventfd_flush_signal(ctx); } @@ -1222,10 +1228,7 @@ static void io_req_normal_work_add(struct io_kiocb *req) /* SQPOLL doesn't need the task_work added, it'll run it itself */ if (ctx->flags & IORING_SETUP_SQPOLL) { - struct io_sq_data *sqd = ctx->sq_data; - - if (sqd->thread) - __set_notify_signal(sqd->thread); + __set_notify_signal(tctx->task); return; } @@ -1400,6 +1403,12 @@ static void io_free_batch_list(struct io_ring_ctx *ctx, comp_list); if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) { + if (req->flags & REQ_F_REISSUE) { + node = req->comp_list.next; + req->flags &= ~REQ_F_REISSUE; + io_queue_iowq(req); + continue; + } if (req->flags & REQ_F_REFCOUNT) { node = req->comp_list.next; if (!req_ref_put_and_test(req)) @@ -1439,7 +1448,12 @@ void __io_submit_flush_completions(struct io_ring_ctx *ctx) struct io_kiocb *req = container_of(node, struct io_kiocb, comp_list); - if (!(req->flags & REQ_F_CQE_SKIP) && + /* + * Requests marked with REQUEUE should not post a CQE, they + * will go through the io-wq retry machinery and post one + * later. + */ + if (!(req->flags & (REQ_F_CQE_SKIP | REQ_F_REISSUE)) && unlikely(!io_fill_cqe_req(ctx, req))) { if (ctx->lockless_cq) { spin_lock(&ctx->completion_lock); @@ -1639,19 +1653,6 @@ io_req_flags_t io_file_get_flags(struct file *file) return res; } -bool io_alloc_async_data(struct io_kiocb *req) -{ - const struct io_issue_def *def = &io_issue_defs[req->opcode]; - - WARN_ON_ONCE(!def->async_size); - req->async_data = kmalloc(def->async_size, GFP_KERNEL); - if (req->async_data) { - req->flags |= REQ_F_ASYNC_DATA; - return false; - } - return true; -} - static u32 io_get_sequence(struct io_kiocb *req) { u32 seq = req->ctx->cached_sq_head; @@ -2630,36 +2631,10 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags, return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; } -static void *io_rings_map(struct io_ring_ctx *ctx, unsigned long uaddr, - size_t size) -{ - return __io_uaddr_map(&ctx->ring_pages, &ctx->n_ring_pages, uaddr, - size); -} - -static void *io_sqes_map(struct io_ring_ctx *ctx, unsigned long uaddr, - size_t size) -{ - return __io_uaddr_map(&ctx->sqe_pages, &ctx->n_sqe_pages, uaddr, - size); -} - static void io_rings_free(struct io_ring_ctx *ctx) { - if (!(ctx->flags & IORING_SETUP_NO_MMAP)) { - io_pages_unmap(ctx->rings, &ctx->ring_pages, &ctx->n_ring_pages, - true); - io_pages_unmap(ctx->sq_sqes, &ctx->sqe_pages, &ctx->n_sqe_pages, - true); - } else { - io_pages_free(&ctx->ring_pages, ctx->n_ring_pages); - ctx->n_ring_pages = 0; - io_pages_free(&ctx->sqe_pages, ctx->n_sqe_pages); - ctx->n_sqe_pages = 0; - vunmap(ctx->rings); - vunmap(ctx->sq_sqes); - } - + io_free_region(ctx, &ctx->sq_region); + io_free_region(ctx, &ctx->ring_region); ctx->rings = NULL; ctx->sq_sqes = NULL; } @@ -2731,7 +2706,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free); io_alloc_cache_free(&ctx->uring_cache, kfree); - io_alloc_cache_free(&ctx->msg_cache, io_msg_cache_free); + io_alloc_cache_free(&ctx->msg_cache, kfree); io_futex_cache_free(ctx); io_destroy_buffers(ctx); io_free_region(ctx, &ctx->param_region); @@ -2809,13 +2784,12 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) if (unlikely(!ctx->poll_activated)) io_activate_pollwq(ctx); - - poll_wait(file, &ctx->poll_wq, wait); /* - * synchronizes with barrier from wq_has_sleeper call in - * io_commit_cqring + * provides mb() which pairs with barrier from wq_has_sleeper + * call in io_commit_cqring */ - smp_rmb(); + poll_wait(file, &ctx->poll_wq, wait); + if (!io_sqring_full(ctx)) mask |= EPOLLOUT | EPOLLWRNORM; @@ -2894,7 +2868,8 @@ static __cold void io_ring_exit_work(struct work_struct *work) if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) io_move_task_work_from_local(ctx); - while (io_uring_try_cancel_requests(ctx, NULL, true)) + /* The SQPOLL thread never reaches this path */ + while (io_uring_try_cancel_requests(ctx, NULL, true, false)) cond_resched(); if (ctx->sq_data) { @@ -3062,7 +3037,8 @@ static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct io_uring_task *tctx, - bool cancel_all) + bool cancel_all, + bool is_sqpoll_thread) { struct io_task_cancel cancel = { .tctx = tctx, .all = cancel_all, }; enum io_wq_cancel cret; @@ -3092,7 +3068,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, /* SQPOLL thread does its own polling */ if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || - (ctx->sq_data && ctx->sq_data->thread == current)) { + is_sqpoll_thread) { while (!wq_list_empty(&ctx->iopoll_list)) { io_iopoll_try_reap_events(ctx); ret = true; @@ -3165,13 +3141,15 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) continue; loop |= io_uring_try_cancel_requests(node->ctx, current->io_uring, - cancel_all); + cancel_all, + false); } } else { list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) loop |= io_uring_try_cancel_requests(ctx, current->io_uring, - cancel_all); + cancel_all, + true); } if (loop) { @@ -3214,6 +3192,7 @@ end_wait: void __io_uring_cancel(bool cancel_all) { + io_uring_unreg_ringfd(); io_uring_cancel_generic(cancel_all, NULL); } @@ -3232,6 +3211,7 @@ static struct io_uring_reg_wait *io_get_ext_arg_reg(struct io_ring_ctx *ctx, end > ctx->cq_wait_size)) return ERR_PTR(-EFAULT); + offset = array_index_nospec(offset, ctx->cq_wait_size - size); return ctx->cq_wait_arg + offset; } @@ -3476,9 +3456,10 @@ bool io_is_uring_fops(struct file *file) static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, struct io_uring_params *p) { + struct io_uring_region_desc rd; struct io_rings *rings; size_t size, sq_array_offset; - void *ptr; + int ret; /* make sure these are sane, as we already accounted them */ ctx->sq_entries = p->sq_entries; @@ -3489,15 +3470,17 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, if (size == SIZE_MAX) return -EOVERFLOW; - if (!(ctx->flags & IORING_SETUP_NO_MMAP)) - rings = io_pages_map(&ctx->ring_pages, &ctx->n_ring_pages, size); - else - rings = io_rings_map(ctx, p->cq_off.user_addr, size); + memset(&rd, 0, sizeof(rd)); + rd.size = PAGE_ALIGN(size); + if (ctx->flags & IORING_SETUP_NO_MMAP) { + rd.user_addr = p->cq_off.user_addr; + rd.flags |= IORING_MEM_REGION_TYPE_USER; + } + ret = io_create_region(ctx, &ctx->ring_region, &rd, IORING_OFF_CQ_RING); + if (ret) + return ret; + ctx->rings = rings = io_region_get_ptr(&ctx->ring_region); - if (IS_ERR(rings)) - return PTR_ERR(rings); - - ctx->rings = rings; if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) ctx->sq_array = (u32 *)((char *)rings + sq_array_offset); rings->sq_ring_mask = p->sq_entries - 1; @@ -3514,17 +3497,18 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, return -EOVERFLOW; } - if (!(ctx->flags & IORING_SETUP_NO_MMAP)) - ptr = io_pages_map(&ctx->sqe_pages, &ctx->n_sqe_pages, size); - else - ptr = io_sqes_map(ctx, p->sq_off.user_addr, size); - - if (IS_ERR(ptr)) { - io_rings_free(ctx); - return PTR_ERR(ptr); + memset(&rd, 0, sizeof(rd)); + rd.size = PAGE_ALIGN(size); + if (ctx->flags & IORING_SETUP_NO_MMAP) { + rd.user_addr = p->sq_off.user_addr; + rd.flags |= IORING_MEM_REGION_TYPE_USER; } - - ctx->sq_sqes = ptr; + ret = io_create_region(ctx, &ctx->sq_region, &rd, IORING_OFF_SQES); + if (ret) { + io_rings_free(ctx); + return ret; + } + ctx->sq_sqes = io_region_get_ptr(&ctx->sq_region); return 0; } @@ -3732,7 +3716,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP | IORING_FEAT_LINKED_FILE | IORING_FEAT_REG_REG_RING | - IORING_FEAT_RECVSEND_BUNDLE | IORING_FEAT_MIN_TIMEOUT; + IORING_FEAT_RECVSEND_BUNDLE | IORING_FEAT_MIN_TIMEOUT | + IORING_FEAT_RW_ATTR; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; @@ -3893,6 +3878,8 @@ static int __init io_uring_init(void) BUILD_BUG_SQE_ELEM(46, __u16, __pad3[0]); BUILD_BUG_SQE_ELEM(48, __u64, addr3); BUILD_BUG_SQE_ELEM_SIZE(48, 0, cmd); + BUILD_BUG_SQE_ELEM(48, __u64, attr_ptr); + BUILD_BUG_SQE_ELEM(56, __u64, attr_type_mask); BUILD_BUG_SQE_ELEM(56, __u64, __pad2); BUILD_BUG_ON(sizeof(struct io_uring_files_update) != diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 12abee607e4a..ab619e63ef39 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -8,9 +8,11 @@ #include #include #include +#include "alloc_cache.h" #include "io-wq.h" #include "slist.h" #include "filetable.h" +#include "opdef.h" #ifndef CREATE_TRACE_POINTS #include @@ -125,6 +127,9 @@ static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) #if defined(CONFIG_PROVE_LOCKING) lockdep_assert(in_task()); + if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) + lockdep_assert_held(&ctx->uring_lock); + if (ctx->flags & IORING_SETUP_IOPOLL) { lockdep_assert_held(&ctx->uring_lock); } else if (!ctx->task_complete) { @@ -136,9 +141,7 @@ static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) * Not from an SQE, as those cannot be submitted, but via * updating tagged resources. */ - if (percpu_ref_is_dying(&ctx->refs)) - lockdep_assert(current_work()); - else + if (!percpu_ref_is_dying(&ctx->refs)) lockdep_assert(current == ctx->submitter_task); } #endif @@ -222,6 +225,22 @@ static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags) req->cqe.flags = cflags; } +static inline void *io_uring_alloc_async_data(struct io_alloc_cache *cache, + struct io_kiocb *req) +{ + if (cache) { + req->async_data = io_cache_alloc(cache, GFP_KERNEL); + } else { + const struct io_issue_def *def = &io_issue_defs[req->opcode]; + + WARN_ON_ONCE(!def->async_size); + req->async_data = kmalloc(def->async_size, GFP_KERNEL); + } + if (req->async_data) + req->flags |= REQ_F_ASYNC_DATA; + return req->async_data; +} + static inline bool req_has_async_data(struct io_kiocb *req) { return req->flags & REQ_F_ASYNC_DATA; diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index d407576ddfb7..04bf493eecae 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -45,10 +45,10 @@ static int io_buffer_add_list(struct io_ring_ctx *ctx, /* * Store buffer group ID and finally mark the list as visible. * The normal lookup doesn't care about the visibility as we're - * always under the ->uring_lock, but the RCU lookup from mmap does. + * always under the ->uring_lock, but lookups from mmap do. */ bl->bgid = bgid; - atomic_set(&bl->refs, 1); + guard(mutex)(&ctx->mmap_lock); return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); } @@ -139,6 +139,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, struct io_uring_buf_ring *br = bl->buf_ring; __u16 tail, head = bl->head; struct io_uring_buf *buf; + void __user *ret; tail = smp_load_acquire(&br->tail); if (unlikely(tail == head)) @@ -153,6 +154,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT; req->buf_list = bl; req->buf_index = buf->bid; + ret = u64_to_user_ptr(buf->addr); if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) { /* @@ -168,7 +170,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, io_kbuf_commit(req, bl, *len, 1); req->buf_list = NULL; } - return u64_to_user_ptr(buf->addr); + return ret; } void __user *io_buffer_select(struct io_kiocb *req, size_t *len, @@ -351,17 +353,7 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, if (bl->flags & IOBL_BUF_RING) { i = bl->buf_ring->tail - bl->head; - if (bl->buf_nr_pages) { - int j; - - if (!(bl->flags & IOBL_MMAP)) { - for (j = 0; j < bl->buf_nr_pages; j++) - unpin_user_page(bl->buf_pages[j]); - } - io_pages_unmap(bl->buf_ring, &bl->buf_pages, - &bl->buf_nr_pages, bl->flags & IOBL_MMAP); - bl->flags &= ~IOBL_MMAP; - } + io_free_region(ctx, &bl->region); /* make sure it's seen as empty */ INIT_LIST_HEAD(&bl->buf_list); bl->flags &= ~IOBL_BUF_RING; @@ -384,12 +376,10 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, return i; } -void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) +static void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) { - if (atomic_dec_and_test(&bl->refs)) { - __io_remove_buffers(ctx, bl, -1U); - kfree_rcu(bl, rcu); - } + __io_remove_buffers(ctx, bl, -1U); + kfree(bl); } void io_destroy_buffers(struct io_ring_ctx *ctx) @@ -397,10 +387,17 @@ void io_destroy_buffers(struct io_ring_ctx *ctx) struct io_buffer_list *bl; struct list_head *item, *tmp; struct io_buffer *buf; - unsigned long index; - xa_for_each(&ctx->io_bl_xa, index, bl) { - xa_erase(&ctx->io_bl_xa, bl->bgid); + while (1) { + unsigned long index = 0; + + scoped_guard(mutex, &ctx->mmap_lock) { + bl = xa_find(&ctx->io_bl_xa, &index, ULONG_MAX, XA_PRESENT); + if (bl) + xa_erase(&ctx->io_bl_xa, bl->bgid); + } + if (!bl) + break; io_put_bl(ctx, bl); } @@ -589,11 +586,7 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) INIT_LIST_HEAD(&bl->buf_list); ret = io_buffer_add_list(ctx, bl, p->bgid); if (ret) { - /* - * Doesn't need rcu free as it was never visible, but - * let's keep it consistent throughout. - */ - kfree_rcu(bl, rcu); + kfree(bl); goto err; } } @@ -613,75 +606,14 @@ err: return IOU_OK; } -static int io_pin_pbuf_ring(struct io_uring_buf_reg *reg, - struct io_buffer_list *bl) -{ - struct io_uring_buf_ring *br = NULL; - struct page **pages; - int nr_pages, ret; - - pages = io_pin_pages(reg->ring_addr, - flex_array_size(br, bufs, reg->ring_entries), - &nr_pages); - if (IS_ERR(pages)) - return PTR_ERR(pages); - - br = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - if (!br) { - ret = -ENOMEM; - goto error_unpin; - } - -#ifdef SHM_COLOUR - /* - * On platforms that have specific aliasing requirements, SHM_COLOUR - * is set and we must guarantee that the kernel and user side align - * nicely. We cannot do that if IOU_PBUF_RING_MMAP isn't set and - * the application mmap's the provided ring buffer. Fail the request - * if we, by chance, don't end up with aligned addresses. The app - * should use IOU_PBUF_RING_MMAP instead, and liburing will handle - * this transparently. - */ - if ((reg->ring_addr | (unsigned long) br) & (SHM_COLOUR - 1)) { - ret = -EINVAL; - goto error_unpin; - } -#endif - bl->buf_pages = pages; - bl->buf_nr_pages = nr_pages; - bl->buf_ring = br; - bl->flags |= IOBL_BUF_RING; - bl->flags &= ~IOBL_MMAP; - return 0; -error_unpin: - unpin_user_pages(pages, nr_pages); - kvfree(pages); - vunmap(br); - return ret; -} - -static int io_alloc_pbuf_ring(struct io_ring_ctx *ctx, - struct io_uring_buf_reg *reg, - struct io_buffer_list *bl) -{ - size_t ring_size; - - ring_size = reg->ring_entries * sizeof(struct io_uring_buf_ring); - - bl->buf_ring = io_pages_map(&bl->buf_pages, &bl->buf_nr_pages, ring_size); - if (IS_ERR(bl->buf_ring)) { - bl->buf_ring = NULL; - return -ENOMEM; - } - - bl->flags |= (IOBL_BUF_RING | IOBL_MMAP); - return 0; -} - int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) { struct io_uring_buf_reg reg; struct io_buffer_list *bl, *free_bl = NULL; + struct io_uring_region_desc rd; + struct io_uring_buf_ring *br; + unsigned long mmap_offset; + unsigned long ring_size; int ret; lockdep_assert_held(&ctx->uring_lock); @@ -693,19 +625,8 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) return -EINVAL; if (reg.flags & ~(IOU_PBUF_RING_MMAP | IOU_PBUF_RING_INC)) return -EINVAL; - if (!(reg.flags & IOU_PBUF_RING_MMAP)) { - if (!reg.ring_addr) - return -EFAULT; - if (reg.ring_addr & ~PAGE_MASK) - return -EINVAL; - } else { - if (reg.ring_addr) - return -EINVAL; - } - if (!is_power_of_2(reg.ring_entries)) return -EINVAL; - /* cannot disambiguate full vs empty due to head/tail size */ if (reg.ring_entries >= 65536) return -EINVAL; @@ -721,22 +642,48 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) return -ENOMEM; } - if (!(reg.flags & IOU_PBUF_RING_MMAP)) - ret = io_pin_pbuf_ring(®, bl); - else - ret = io_alloc_pbuf_ring(ctx, ®, bl); + mmap_offset = (unsigned long)reg.bgid << IORING_OFF_PBUF_SHIFT; + ring_size = flex_array_size(br, bufs, reg.ring_entries); - if (!ret) { - bl->nr_entries = reg.ring_entries; - bl->mask = reg.ring_entries - 1; - if (reg.flags & IOU_PBUF_RING_INC) - bl->flags |= IOBL_INC; - - io_buffer_add_list(ctx, bl, reg.bgid); - return 0; + memset(&rd, 0, sizeof(rd)); + rd.size = PAGE_ALIGN(ring_size); + if (!(reg.flags & IOU_PBUF_RING_MMAP)) { + rd.user_addr = reg.ring_addr; + rd.flags |= IORING_MEM_REGION_TYPE_USER; } + ret = io_create_region_mmap_safe(ctx, &bl->region, &rd, mmap_offset); + if (ret) + goto fail; + br = io_region_get_ptr(&bl->region); - kfree_rcu(free_bl, rcu); +#ifdef SHM_COLOUR + /* + * On platforms that have specific aliasing requirements, SHM_COLOUR + * is set and we must guarantee that the kernel and user side align + * nicely. We cannot do that if IOU_PBUF_RING_MMAP isn't set and + * the application mmap's the provided ring buffer. Fail the request + * if we, by chance, don't end up with aligned addresses. The app + * should use IOU_PBUF_RING_MMAP instead, and liburing will handle + * this transparently. + */ + if (!(reg.flags & IOU_PBUF_RING_MMAP) && + ((reg.ring_addr | (unsigned long)br) & (SHM_COLOUR - 1))) { + ret = -EINVAL; + goto fail; + } +#endif + + bl->nr_entries = reg.ring_entries; + bl->mask = reg.ring_entries - 1; + bl->flags |= IOBL_BUF_RING; + bl->buf_ring = br; + if (reg.flags & IOU_PBUF_RING_INC) + bl->flags |= IOBL_INC; + io_buffer_add_list(ctx, bl, reg.bgid); + return 0; +fail: + io_free_region(ctx, &bl->region); + kfree(free_bl); return ret; } @@ -760,7 +707,9 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) if (!(bl->flags & IOBL_BUF_RING)) return -EINVAL; - xa_erase(&ctx->io_bl_xa, bl->bgid); + scoped_guard(mutex, &ctx->mmap_lock) + xa_erase(&ctx->io_bl_xa, bl->bgid); + io_put_bl(ctx, bl); return 0; } @@ -791,50 +740,15 @@ int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg) return 0; } -struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx, - unsigned long bgid) +struct io_mapped_region *io_pbuf_get_region(struct io_ring_ctx *ctx, + unsigned int bgid) { struct io_buffer_list *bl; - bool ret; - /* - * We have to be a bit careful here - we're inside mmap and cannot grab - * the uring_lock. This means the buffer_list could be simultaneously - * going away, if someone is trying to be sneaky. Look it up under rcu - * so we know it's not going away, and attempt to grab a reference to - * it. If the ref is already zero, then fail the mapping. If successful, - * the caller will call io_put_bl() to drop the the reference at at the - * end. This may then safely free the buffer_list (and drop the pages) - * at that point, vm_insert_pages() would've already grabbed the - * necessary vma references. - */ - rcu_read_lock(); + lockdep_assert_held(&ctx->mmap_lock); + bl = xa_load(&ctx->io_bl_xa, bgid); - /* must be a mmap'able buffer ring and have pages */ - ret = false; - if (bl && bl->flags & IOBL_MMAP) - ret = atomic_inc_not_zero(&bl->refs); - rcu_read_unlock(); - - if (ret) - return bl; - - return ERR_PTR(-EINVAL); -} - -int io_pbuf_mmap(struct file *file, struct vm_area_struct *vma) -{ - struct io_ring_ctx *ctx = file->private_data; - loff_t pgoff = vma->vm_pgoff << PAGE_SHIFT; - struct io_buffer_list *bl; - int bgid, ret; - - bgid = (pgoff & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT; - bl = io_pbuf_get_bl(ctx, bgid); - if (IS_ERR(bl)) - return PTR_ERR(bl); - - ret = io_uring_mmap_pages(ctx, vma, bl->buf_pages, bl->buf_nr_pages); - io_put_bl(ctx, bl); - return ret; + if (!bl || !(bl->flags & IOBL_BUF_RING)) + return NULL; + return &bl->region; } diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h index 36aadfe5ac00..bd80c44c5af1 100644 --- a/io_uring/kbuf.h +++ b/io_uring/kbuf.h @@ -3,15 +3,13 @@ #define IOU_KBUF_H #include +#include enum { /* ring mapped provided buffers */ IOBL_BUF_RING = 1, - /* ring mapped provided buffers, but mmap'ed by application */ - IOBL_MMAP = 2, /* buffers are consumed incrementally rather than always fully */ - IOBL_INC = 4, - + IOBL_INC = 2, }; struct io_buffer_list { @@ -21,11 +19,7 @@ struct io_buffer_list { */ union { struct list_head buf_list; - struct { - struct page **buf_pages; - struct io_uring_buf_ring *buf_ring; - }; - struct rcu_head rcu; + struct io_uring_buf_ring *buf_ring; }; __u16 bgid; @@ -37,7 +31,7 @@ struct io_buffer_list { __u16 flags; - atomic_t refs; + struct io_mapped_region region; }; struct io_buffer { @@ -84,10 +78,8 @@ void __io_put_kbuf(struct io_kiocb *req, int len, unsigned issue_flags); bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags); -void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl); -struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx, - unsigned long bgid); -int io_pbuf_mmap(struct file *file, struct vm_area_struct *vma); +struct io_mapped_region *io_pbuf_get_region(struct io_ring_ctx *ctx, + unsigned int bgid); static inline bool io_kbuf_recycle_ring(struct io_kiocb *req) { diff --git a/io_uring/memmap.c b/io_uring/memmap.c index 57de9bccbf50..361134544427 100644 --- a/io_uring/memmap.c +++ b/io_uring/memmap.c @@ -36,102 +36,6 @@ static void *io_mem_alloc_compound(struct page **pages, int nr_pages, return page_address(page); } -static void *io_mem_alloc_single(struct page **pages, int nr_pages, size_t size, - gfp_t gfp) -{ - void *ret; - int i; - - for (i = 0; i < nr_pages; i++) { - pages[i] = alloc_page(gfp); - if (!pages[i]) - goto err; - } - - ret = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - if (ret) - return ret; -err: - while (i--) - put_page(pages[i]); - return ERR_PTR(-ENOMEM); -} - -void *io_pages_map(struct page ***out_pages, unsigned short *npages, - size_t size) -{ - gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN; - struct page **pages; - int nr_pages; - void *ret; - - nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; - pages = kvmalloc_array(nr_pages, sizeof(struct page *), gfp); - if (!pages) - return ERR_PTR(-ENOMEM); - - ret = io_mem_alloc_compound(pages, nr_pages, size, gfp); - if (!IS_ERR(ret)) - goto done; - if (nr_pages == 1) - goto fail; - - ret = io_mem_alloc_single(pages, nr_pages, size, gfp); - if (!IS_ERR(ret)) { -done: - *out_pages = pages; - *npages = nr_pages; - return ret; - } -fail: - kvfree(pages); - *out_pages = NULL; - *npages = 0; - return ret; -} - -void io_pages_unmap(void *ptr, struct page ***pages, unsigned short *npages, - bool put_pages) -{ - bool do_vunmap = false; - - if (!ptr) - return; - - if (put_pages && *npages) { - struct page **to_free = *pages; - int i; - - /* - * Only did vmap for the non-compound multiple page case. - * For the compound page, we just need to put the head. - */ - if (PageCompound(to_free[0])) - *npages = 1; - else if (*npages > 1) - do_vunmap = true; - for (i = 0; i < *npages; i++) - put_page(to_free[i]); - } - if (do_vunmap) - vunmap(ptr); - kvfree(*pages); - *pages = NULL; - *npages = 0; -} - -void io_pages_free(struct page ***pages, int npages) -{ - struct page **page_array = *pages; - - if (!page_array) - return; - - unpin_user_pages(page_array, npages); - kvfree(page_array); - *pages = NULL; -} - struct page **io_pin_pages(unsigned long uaddr, unsigned long len, int *npages) { unsigned long start, end, nr_pages; @@ -174,64 +78,127 @@ struct page **io_pin_pages(unsigned long uaddr, unsigned long len, int *npages) return ERR_PTR(ret); } -void *__io_uaddr_map(struct page ***pages, unsigned short *npages, - unsigned long uaddr, size_t size) -{ - struct page **page_array; - unsigned int nr_pages; - void *page_addr; - - *npages = 0; - - if (uaddr & (PAGE_SIZE - 1) || !size) - return ERR_PTR(-EINVAL); - - nr_pages = 0; - page_array = io_pin_pages(uaddr, size, &nr_pages); - if (IS_ERR(page_array)) - return page_array; - - page_addr = vmap(page_array, nr_pages, VM_MAP, PAGE_KERNEL); - if (page_addr) { - *pages = page_array; - *npages = nr_pages; - return page_addr; - } - - io_pages_free(&page_array, nr_pages); - return ERR_PTR(-ENOMEM); -} +enum { + /* memory was vmap'ed for the kernel, freeing the region vunmap's it */ + IO_REGION_F_VMAP = 1, + /* memory is provided by user and pinned by the kernel */ + IO_REGION_F_USER_PROVIDED = 2, + /* only the first page in the array is ref'ed */ + IO_REGION_F_SINGLE_REF = 4, +}; void io_free_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr) { if (mr->pages) { - unpin_user_pages(mr->pages, mr->nr_pages); + long nr_refs = mr->nr_pages; + + if (mr->flags & IO_REGION_F_SINGLE_REF) + nr_refs = 1; + + if (mr->flags & IO_REGION_F_USER_PROVIDED) + unpin_user_pages(mr->pages, nr_refs); + else + release_pages(mr->pages, nr_refs); + kvfree(mr->pages); } - if (mr->vmap_ptr) - vunmap(mr->vmap_ptr); + if ((mr->flags & IO_REGION_F_VMAP) && mr->ptr) + vunmap(mr->ptr); if (mr->nr_pages && ctx->user) __io_unaccount_mem(ctx->user, mr->nr_pages); memset(mr, 0, sizeof(*mr)); } -int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr, - struct io_uring_region_desc *reg) +static int io_region_init_ptr(struct io_mapped_region *mr) { - int pages_accounted = 0; + struct io_imu_folio_data ifd; + void *ptr; + + if (io_check_coalesce_buffer(mr->pages, mr->nr_pages, &ifd)) { + if (ifd.nr_folios == 1) { + mr->ptr = page_address(mr->pages[0]); + return 0; + } + } + ptr = vmap(mr->pages, mr->nr_pages, VM_MAP, PAGE_KERNEL); + if (!ptr) + return -ENOMEM; + + mr->ptr = ptr; + mr->flags |= IO_REGION_F_VMAP; + return 0; +} + +static int io_region_pin_pages(struct io_ring_ctx *ctx, + struct io_mapped_region *mr, + struct io_uring_region_desc *reg) +{ + unsigned long size = mr->nr_pages << PAGE_SHIFT; struct page **pages; + int nr_pages; + + pages = io_pin_pages(reg->user_addr, size, &nr_pages); + if (IS_ERR(pages)) + return PTR_ERR(pages); + if (WARN_ON_ONCE(nr_pages != mr->nr_pages)) + return -EFAULT; + + mr->pages = pages; + mr->flags |= IO_REGION_F_USER_PROVIDED; + return 0; +} + +static int io_region_allocate_pages(struct io_ring_ctx *ctx, + struct io_mapped_region *mr, + struct io_uring_region_desc *reg, + unsigned long mmap_offset) +{ + gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN; + unsigned long size = mr->nr_pages << PAGE_SHIFT; + unsigned long nr_allocated; + struct page **pages; + void *p; + + pages = kvmalloc_array(mr->nr_pages, sizeof(*pages), gfp); + if (!pages) + return -ENOMEM; + + p = io_mem_alloc_compound(pages, mr->nr_pages, size, gfp); + if (!IS_ERR(p)) { + mr->flags |= IO_REGION_F_SINGLE_REF; + goto done; + } + + nr_allocated = alloc_pages_bulk_node(gfp, NUMA_NO_NODE, + mr->nr_pages, pages); + if (nr_allocated != mr->nr_pages) { + if (nr_allocated) + release_pages(pages, nr_allocated); + kvfree(pages); + return -ENOMEM; + } +done: + reg->mmap_offset = mmap_offset; + mr->pages = pages; + return 0; +} + +int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr, + struct io_uring_region_desc *reg, + unsigned long mmap_offset) +{ int nr_pages, ret; - void *vptr; u64 end; - if (WARN_ON_ONCE(mr->pages || mr->vmap_ptr || mr->nr_pages)) + if (WARN_ON_ONCE(mr->pages || mr->ptr || mr->nr_pages)) return -EFAULT; if (memchr_inv(®->__resv, 0, sizeof(reg->__resv))) return -EINVAL; - if (reg->flags != IORING_MEM_REGION_TYPE_USER) + if (reg->flags & ~IORING_MEM_REGION_TYPE_USER) return -EINVAL; - if (!reg->user_addr) + /* user_addr should be set IFF it's a user memory backed region */ + if ((reg->flags & IORING_MEM_REGION_TYPE_USER) != !!reg->user_addr) return -EFAULT; if (!reg->size || reg->mmap_offset || reg->id) return -EINVAL; @@ -242,94 +209,120 @@ int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr, if (check_add_overflow(reg->user_addr, reg->size, &end)) return -EOVERFLOW; - pages = io_pin_pages(reg->user_addr, reg->size, &nr_pages); - if (IS_ERR(pages)) - return PTR_ERR(pages); - + nr_pages = reg->size >> PAGE_SHIFT; if (ctx->user) { ret = __io_account_mem(ctx->user, nr_pages); if (ret) - goto out_free; - pages_accounted = nr_pages; + return ret; } - - vptr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - if (!vptr) { - ret = -ENOMEM; - goto out_free; - } - - mr->pages = pages; - mr->vmap_ptr = vptr; mr->nr_pages = nr_pages; + + if (reg->flags & IORING_MEM_REGION_TYPE_USER) + ret = io_region_pin_pages(ctx, mr, reg); + else + ret = io_region_allocate_pages(ctx, mr, reg, mmap_offset); + if (ret) + goto out_free; + + ret = io_region_init_ptr(mr); + if (ret) + goto out_free; return 0; out_free: - if (pages_accounted) - __io_unaccount_mem(ctx->user, pages_accounted); - io_pages_free(&pages, nr_pages); + io_free_region(ctx, mr); return ret; } +int io_create_region_mmap_safe(struct io_ring_ctx *ctx, struct io_mapped_region *mr, + struct io_uring_region_desc *reg, + unsigned long mmap_offset) +{ + struct io_mapped_region tmp_mr; + int ret; + + memcpy(&tmp_mr, mr, sizeof(tmp_mr)); + ret = io_create_region(ctx, &tmp_mr, reg, mmap_offset); + if (ret) + return ret; + + /* + * Once published mmap can find it without holding only the ->mmap_lock + * and not ->uring_lock. + */ + guard(mutex)(&ctx->mmap_lock); + memcpy(mr, &tmp_mr, sizeof(tmp_mr)); + return 0; +} + +static struct io_mapped_region *io_mmap_get_region(struct io_ring_ctx *ctx, + loff_t pgoff) +{ + loff_t offset = pgoff << PAGE_SHIFT; + unsigned int bgid; + + switch (offset & IORING_OFF_MMAP_MASK) { + case IORING_OFF_SQ_RING: + case IORING_OFF_CQ_RING: + return &ctx->ring_region; + case IORING_OFF_SQES: + return &ctx->sq_region; + case IORING_OFF_PBUF_RING: + bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT; + return io_pbuf_get_region(ctx, bgid); + case IORING_MAP_OFF_PARAM_REGION: + return &ctx->param_region; + } + return NULL; +} + +static void *io_region_validate_mmap(struct io_ring_ctx *ctx, + struct io_mapped_region *mr) +{ + lockdep_assert_held(&ctx->mmap_lock); + + if (!io_region_is_set(mr)) + return ERR_PTR(-EINVAL); + if (mr->flags & IO_REGION_F_USER_PROVIDED) + return ERR_PTR(-EINVAL); + + return io_region_get_ptr(mr); +} + static void *io_uring_validate_mmap_request(struct file *file, loff_t pgoff, size_t sz) { struct io_ring_ctx *ctx = file->private_data; - loff_t offset = pgoff << PAGE_SHIFT; + struct io_mapped_region *region; - switch ((pgoff << PAGE_SHIFT) & IORING_OFF_MMAP_MASK) { - case IORING_OFF_SQ_RING: - case IORING_OFF_CQ_RING: - /* Don't allow mmap if the ring was setup without it */ - if (ctx->flags & IORING_SETUP_NO_MMAP) - return ERR_PTR(-EINVAL); - if (!ctx->rings) - return ERR_PTR(-EFAULT); - return ctx->rings; - case IORING_OFF_SQES: - /* Don't allow mmap if the ring was setup without it */ - if (ctx->flags & IORING_SETUP_NO_MMAP) - return ERR_PTR(-EINVAL); - if (!ctx->sq_sqes) - return ERR_PTR(-EFAULT); - return ctx->sq_sqes; - case IORING_OFF_PBUF_RING: { - struct io_buffer_list *bl; - unsigned int bgid; - void *ptr; - - bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT; - bl = io_pbuf_get_bl(ctx, bgid); - if (IS_ERR(bl)) - return bl; - ptr = bl->buf_ring; - io_put_bl(ctx, bl); - return ptr; - } - } - - return ERR_PTR(-EINVAL); -} - -int io_uring_mmap_pages(struct io_ring_ctx *ctx, struct vm_area_struct *vma, - struct page **pages, int npages) -{ - unsigned long nr_pages = npages; - - vm_flags_set(vma, VM_DONTEXPAND); - return vm_insert_pages(vma, vma->vm_start, pages, &nr_pages); + region = io_mmap_get_region(ctx, pgoff); + if (!region) + return ERR_PTR(-EINVAL); + return io_region_validate_mmap(ctx, region); } #ifdef CONFIG_MMU +static int io_region_mmap(struct io_ring_ctx *ctx, + struct io_mapped_region *mr, + struct vm_area_struct *vma, + unsigned max_pages) +{ + unsigned long nr_pages = min(mr->nr_pages, max_pages); + + vm_flags_set(vma, VM_DONTEXPAND); + return vm_insert_pages(vma, vma->vm_start, mr->pages, &nr_pages); +} + __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma) { struct io_ring_ctx *ctx = file->private_data; size_t sz = vma->vm_end - vma->vm_start; long offset = vma->vm_pgoff << PAGE_SHIFT; - unsigned int npages; + unsigned int page_limit = UINT_MAX; + struct io_mapped_region *region; void *ptr; - guard(mutex)(&ctx->resize_lock); + guard(mutex)(&ctx->mmap_lock); ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz); if (IS_ERR(ptr)) @@ -338,16 +331,12 @@ __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma) switch (offset & IORING_OFF_MMAP_MASK) { case IORING_OFF_SQ_RING: case IORING_OFF_CQ_RING: - npages = min(ctx->n_ring_pages, (sz + PAGE_SIZE - 1) >> PAGE_SHIFT); - return io_uring_mmap_pages(ctx, vma, ctx->ring_pages, npages); - case IORING_OFF_SQES: - return io_uring_mmap_pages(ctx, vma, ctx->sqe_pages, - ctx->n_sqe_pages); - case IORING_OFF_PBUF_RING: - return io_pbuf_mmap(file, vma); + page_limit = (sz + PAGE_SIZE - 1) >> PAGE_SHIFT; + break; } - return -EINVAL; + region = io_mmap_get_region(ctx, vma->vm_pgoff); + return io_region_mmap(ctx, region, vma, page_limit); } unsigned long io_uring_get_unmapped_area(struct file *filp, unsigned long addr, @@ -365,7 +354,7 @@ unsigned long io_uring_get_unmapped_area(struct file *filp, unsigned long addr, if (addr) return -EINVAL; - guard(mutex)(&ctx->resize_lock); + guard(mutex)(&ctx->mmap_lock); ptr = io_uring_validate_mmap_request(filp, pgoff, len); if (IS_ERR(ptr)) @@ -415,7 +404,7 @@ unsigned long io_uring_get_unmapped_area(struct file *file, unsigned long addr, struct io_ring_ctx *ctx = file->private_data; void *ptr; - guard(mutex)(&ctx->resize_lock); + guard(mutex)(&ctx->mmap_lock); ptr = io_uring_validate_mmap_request(file, pgoff, len); if (IS_ERR(ptr)) diff --git a/io_uring/memmap.h b/io_uring/memmap.h index f361a635b6c7..c898dcba2b4e 100644 --- a/io_uring/memmap.h +++ b/io_uring/memmap.h @@ -1,18 +1,9 @@ #ifndef IO_URING_MEMMAP_H #define IO_URING_MEMMAP_H +#define IORING_MAP_OFF_PARAM_REGION 0x20000000ULL + struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages); -void io_pages_free(struct page ***pages, int npages); -int io_uring_mmap_pages(struct io_ring_ctx *ctx, struct vm_area_struct *vma, - struct page **pages, int npages); - -void *io_pages_map(struct page ***out_pages, unsigned short *npages, - size_t size); -void io_pages_unmap(void *ptr, struct page ***pages, unsigned short *npages, - bool put_pages); - -void *__io_uaddr_map(struct page ***pages, unsigned short *npages, - unsigned long uaddr, size_t size); #ifndef CONFIG_MMU unsigned int io_uring_nommu_mmap_capabilities(struct file *file); @@ -24,11 +15,17 @@ int io_uring_mmap(struct file *file, struct vm_area_struct *vma); void io_free_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr); int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr, - struct io_uring_region_desc *reg); + struct io_uring_region_desc *reg, + unsigned long mmap_offset); + +int io_create_region_mmap_safe(struct io_ring_ctx *ctx, + struct io_mapped_region *mr, + struct io_uring_region_desc *reg, + unsigned long mmap_offset); static inline void *io_region_get_ptr(struct io_mapped_region *mr) { - return mr->vmap_ptr; + return mr->ptr; } static inline bool io_region_is_set(struct io_mapped_region *mr) diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 333c220d322a..7e6f68e911f1 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -89,8 +89,7 @@ static void io_msg_tw_complete(struct io_kiocb *req, struct io_tw_state *ts) static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req, int res, u32 cflags, u64 user_data) { - req->tctx = READ_ONCE(ctx->submitter_task->io_uring); - if (!req->tctx) { + if (!READ_ONCE(ctx->submitter_task)) { kmem_cache_free(req_cachep, req); return -EOWNERDEAD; } @@ -98,6 +97,7 @@ static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req, io_req_set_res(req, res, cflags); percpu_ref_get(&ctx->refs); req->ctx = ctx; + req->tctx = NULL; req->io_task_work.func = io_msg_tw_complete; io_req_task_work_add_remote(req, ctx, IOU_F_TWQ_LAZY_WAKE); return 0; @@ -354,10 +354,3 @@ int io_uring_sync_msg_ring(struct io_uring_sqe *sqe) return __io_msg_ring_data(fd_file(f)->private_data, &io_msg, IO_URING_F_UNLOCKED); } - -void io_msg_cache_free(const void *entry) -{ - struct io_kiocb *req = (struct io_kiocb *) entry; - - kmem_cache_free(req_cachep, req); -} diff --git a/io_uring/msg_ring.h b/io_uring/msg_ring.h index 38e7f8f0c944..32236d2fb778 100644 --- a/io_uring/msg_ring.h +++ b/io_uring/msg_ring.h @@ -4,4 +4,3 @@ int io_uring_sync_msg_ring(struct io_uring_sqe *sqe); int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags); void io_msg_ring_cleanup(struct io_kiocb *req); -void io_msg_cache_free(const void *entry); diff --git a/io_uring/net.c b/io_uring/net.c index df1f7dc6f1c8..17852a6616ff 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -137,7 +137,6 @@ static void io_netmsg_iovec_free(struct io_async_msghdr *kmsg) static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr *hdr = req->async_data; - struct iovec *iov; /* can't recycle, ensure we free the iovec if we have one */ if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) { @@ -146,10 +145,8 @@ static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags) } /* Let normal cleanup path reap it if we fail adding to the cache */ - iov = hdr->free_iov; + io_alloc_cache_kasan(&hdr->free_iov, &hdr->free_iov_nr); if (io_alloc_cache_put(&req->ctx->netmsg_cache, hdr)) { - if (iov) - kasan_mempool_poison_object(iov); req->async_data = NULL; req->flags &= ~REQ_F_ASYNC_DATA; } @@ -160,29 +157,18 @@ static struct io_async_msghdr *io_msg_alloc_async(struct io_kiocb *req) struct io_ring_ctx *ctx = req->ctx; struct io_async_msghdr *hdr; - hdr = io_alloc_cache_get(&ctx->netmsg_cache); - if (hdr) { - if (hdr->free_iov) { - kasan_mempool_unpoison_object(hdr->free_iov, - hdr->free_iov_nr * sizeof(struct iovec)); - req->flags |= REQ_F_NEED_CLEANUP; - } - req->flags |= REQ_F_ASYNC_DATA; - req->async_data = hdr; - return hdr; - } + hdr = io_uring_alloc_async_data(&ctx->netmsg_cache, req); + if (!hdr) + return NULL; - if (!io_alloc_async_data(req)) { - hdr = req->async_data; - hdr->free_iov_nr = 0; - hdr->free_iov = NULL; - return hdr; - } - return NULL; + /* If the async data was cached, we might have an iov cached inside. */ + if (hdr->free_iov) + req->flags |= REQ_F_NEED_CLEANUP; + return hdr; } /* assign new iovec to kmsg, if we need to */ -static int io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg, +static void io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg, struct iovec *iov) { if (iov) { @@ -192,7 +178,6 @@ static int io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg, kfree(kmsg->free_iov); kmsg->free_iov = iov; } - return 0; } static inline void io_mshot_prep_retry(struct io_kiocb *req, @@ -254,7 +239,8 @@ static int io_compat_msg_copy_hdr(struct io_kiocb *req, if (unlikely(ret < 0)) return ret; - return io_net_vec_assign(req, iomsg, iov); + io_net_vec_assign(req, iomsg, iov); + return 0; } #endif @@ -294,11 +280,12 @@ static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg, ret = -EINVAL; goto ua_end; } else { + struct iovec __user *uiov = msg->msg_iov; + /* we only need the length for provided buffers */ - if (!access_ok(&msg->msg_iov[0].iov_len, sizeof(__kernel_size_t))) + if (!access_ok(&uiov->iov_len, sizeof(uiov->iov_len))) goto ua_end; - unsafe_get_user(iov->iov_len, &msg->msg_iov[0].iov_len, - ua_end); + unsafe_get_user(iov->iov_len, &uiov->iov_len, ua_end); sr->len = iov->iov_len; } ret = 0; @@ -313,7 +300,8 @@ ua_end: if (unlikely(ret < 0)) return ret; - return io_net_vec_assign(req, iomsg, iov); + io_net_vec_assign(req, iomsg, iov); + return 0; } static int io_sendmsg_copy_hdr(struct io_kiocb *req, @@ -578,6 +566,54 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +static int io_send_select_buffer(struct io_kiocb *req, unsigned int issue_flags, + struct io_async_msghdr *kmsg) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + + int ret; + struct buf_sel_arg arg = { + .iovs = &kmsg->fast_iov, + .max_len = min_not_zero(sr->len, INT_MAX), + .nr_iovs = 1, + }; + + if (kmsg->free_iov) { + arg.nr_iovs = kmsg->free_iov_nr; + arg.iovs = kmsg->free_iov; + arg.mode = KBUF_MODE_FREE; + } + + if (!(sr->flags & IORING_RECVSEND_BUNDLE)) + arg.nr_iovs = 1; + else + arg.mode |= KBUF_MODE_EXPAND; + + ret = io_buffers_select(req, &arg, issue_flags); + if (unlikely(ret < 0)) + return ret; + + if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) { + kmsg->free_iov_nr = ret; + kmsg->free_iov = arg.iovs; + req->flags |= REQ_F_NEED_CLEANUP; + } + sr->len = arg.out_len; + + if (ret == 1) { + sr->buf = arg.iovs[0].iov_base; + ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len, + &kmsg->msg.msg_iter); + if (unlikely(ret)) + return ret; + } else { + iov_iter_init(&kmsg->msg.msg_iter, ITER_SOURCE, + arg.iovs, ret, arg.out_len); + } + + return 0; +} + int io_send(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); @@ -601,44 +637,9 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) retry_bundle: if (io_do_buffer_select(req)) { - struct buf_sel_arg arg = { - .iovs = &kmsg->fast_iov, - .max_len = min_not_zero(sr->len, INT_MAX), - .nr_iovs = 1, - }; - - if (kmsg->free_iov) { - arg.nr_iovs = kmsg->free_iov_nr; - arg.iovs = kmsg->free_iov; - arg.mode = KBUF_MODE_FREE; - } - - if (!(sr->flags & IORING_RECVSEND_BUNDLE)) - arg.nr_iovs = 1; - else - arg.mode |= KBUF_MODE_EXPAND; - - ret = io_buffers_select(req, &arg, issue_flags); - if (unlikely(ret < 0)) + ret = io_send_select_buffer(req, issue_flags, kmsg); + if (ret) return ret; - - if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) { - kmsg->free_iov_nr = ret; - kmsg->free_iov = arg.iovs; - req->flags |= REQ_F_NEED_CLEANUP; - } - sr->len = arg.out_len; - - if (ret == 1) { - sr->buf = arg.iovs[0].iov_base; - ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len, - &kmsg->msg.msg_iter); - if (unlikely(ret)) - return ret; - } else { - iov_iter_init(&kmsg->msg.msg_iter, ITER_SOURCE, - arg.iovs, ret, arg.out_len); - } } /* @@ -754,6 +755,7 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req) if (req->opcode == IORING_OP_RECV) { kmsg->msg.msg_name = NULL; kmsg->msg.msg_namelen = 0; + kmsg->msg.msg_inq = 0; kmsg->msg.msg_control = NULL; kmsg->msg.msg_get_inq = 1; kmsg->msg.msg_controllen = 0; @@ -1708,6 +1710,11 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) int ret; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + if (unlikely(req->flags & REQ_F_FAIL)) { + ret = -ECONNRESET; + goto out; + } + file_flags = force_nonblock ? O_NONBLOCK : 0; ret = __sys_connect_file(req->file, &io->addr, connect->addr_len, @@ -1811,11 +1818,8 @@ void io_netmsg_cache_free(const void *entry) { struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry; - if (kmsg->free_iov) { - kasan_mempool_unpoison_object(kmsg->free_iov, - kmsg->free_iov_nr * sizeof(struct iovec)); + if (kmsg->free_iov) io_netmsg_iovec_free(kmsg); - } kfree(kmsg); } #endif diff --git a/io_uring/net.h b/io_uring/net.h index 52bfee05f06a..b804c2b36e60 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -5,16 +5,20 @@ struct io_async_msghdr { #if defined(CONFIG_NET) - struct iovec fast_iov; - /* points to an allocated iov, if NULL we use fast_iov instead */ struct iovec *free_iov; + /* points to an allocated iov, if NULL we use fast_iov instead */ int free_iov_nr; - int namelen; - __kernel_size_t controllen; - __kernel_size_t payloadlen; - struct sockaddr __user *uaddr; - struct msghdr msg; - struct sockaddr_storage addr; + struct_group(clear, + int namelen; + struct iovec fast_iov; + __kernel_size_t controllen; + __kernel_size_t payloadlen; + struct sockaddr __user *uaddr; + struct msghdr msg; + struct sockaddr_storage addr; + ); +#else + struct_group(clear); #endif }; diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 3de75eca1c92..e8baef4e5146 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "io_uring.h" #include "opdef.h" @@ -414,7 +415,7 @@ const struct io_issue_def io_issue_defs[] = { .plug = 1, .iopoll = 1, .iopoll_queue = 1, - .async_size = 2 * sizeof(struct io_uring_sqe), + .async_size = sizeof(struct io_uring_cmd_data), .prep = io_uring_cmd_prep, .issue = io_uring_cmd, }, diff --git a/io_uring/poll.c b/io_uring/poll.c index bced9edd5233..bb1c0cd4f809 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -273,6 +273,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts) return IOU_POLL_REISSUE; } } + if (unlikely(req->cqe.res & EPOLLERR)) + req_set_fail(req); if (req->apoll_events & EPOLLONESHOT) return IOU_POLL_DONE; @@ -315,8 +317,10 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts) ret = io_poll_check_events(req, ts); if (ret == IOU_POLL_NO_ACTION) { + io_kbuf_recycle(req, 0); return; } else if (ret == IOU_POLL_REQUEUE) { + io_kbuf_recycle(req, 0); __io_poll_execute(req, 0); return; } @@ -648,15 +652,12 @@ static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req, if (req->flags & REQ_F_POLLED) { apoll = req->apoll; kfree(apoll->double_poll); - } else if (!(issue_flags & IO_URING_F_UNLOCKED)) { - apoll = io_alloc_cache_get(&ctx->apoll_cache); - if (!apoll) - goto alloc_apoll; - apoll->poll.retries = APOLL_MAX_RETRY; } else { -alloc_apoll: - apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); - if (unlikely(!apoll)) + if (!(issue_flags & IO_URING_F_UNLOCKED)) + apoll = io_cache_alloc(&ctx->apoll_cache, GFP_ATOMIC); + else + apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); + if (!apoll) return NULL; apoll->poll.retries = APOLL_MAX_RETRY; } diff --git a/io_uring/register.c b/io_uring/register.c index 1e99c783abdf..9a4d2fbce4ae 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -104,21 +104,13 @@ static int io_register_personality(struct io_ring_ctx *ctx) return id; } -static __cold int io_register_restrictions(struct io_ring_ctx *ctx, - void __user *arg, unsigned int nr_args) +static __cold int io_parse_restrictions(void __user *arg, unsigned int nr_args, + struct io_restriction *restrictions) { struct io_uring_restriction *res; size_t size; int i, ret; - /* Restrictions allowed only if rings started disabled */ - if (!(ctx->flags & IORING_SETUP_R_DISABLED)) - return -EBADFD; - - /* We allow only a single restrictions registration */ - if (ctx->restrictions.registered) - return -EBUSY; - if (!arg || nr_args > IORING_MAX_RESTRICTIONS) return -EINVAL; @@ -130,47 +122,57 @@ static __cold int io_register_restrictions(struct io_ring_ctx *ctx, if (IS_ERR(res)) return PTR_ERR(res); - ret = 0; + ret = -EINVAL; for (i = 0; i < nr_args; i++) { switch (res[i].opcode) { case IORING_RESTRICTION_REGISTER_OP: - if (res[i].register_op >= IORING_REGISTER_LAST) { - ret = -EINVAL; - goto out; - } - - __set_bit(res[i].register_op, - ctx->restrictions.register_op); + if (res[i].register_op >= IORING_REGISTER_LAST) + goto err; + __set_bit(res[i].register_op, restrictions->register_op); break; case IORING_RESTRICTION_SQE_OP: - if (res[i].sqe_op >= IORING_OP_LAST) { - ret = -EINVAL; - goto out; - } - - __set_bit(res[i].sqe_op, ctx->restrictions.sqe_op); + if (res[i].sqe_op >= IORING_OP_LAST) + goto err; + __set_bit(res[i].sqe_op, restrictions->sqe_op); break; case IORING_RESTRICTION_SQE_FLAGS_ALLOWED: - ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags; + restrictions->sqe_flags_allowed = res[i].sqe_flags; break; case IORING_RESTRICTION_SQE_FLAGS_REQUIRED: - ctx->restrictions.sqe_flags_required = res[i].sqe_flags; + restrictions->sqe_flags_required = res[i].sqe_flags; break; default: - ret = -EINVAL; - goto out; + goto err; } } -out: + ret = 0; + +err: + kfree(res); + return ret; +} + +static __cold int io_register_restrictions(struct io_ring_ctx *ctx, + void __user *arg, unsigned int nr_args) +{ + int ret; + + /* Restrictions allowed only if rings started disabled */ + if (!(ctx->flags & IORING_SETUP_R_DISABLED)) + return -EBADFD; + + /* We allow only a single restrictions registration */ + if (ctx->restrictions.registered) + return -EBUSY; + + ret = io_parse_restrictions(arg, nr_args, &ctx->restrictions); /* Reset all restrictions if an error happened */ if (ret != 0) memset(&ctx->restrictions, 0, sizeof(ctx->restrictions)); else ctx->restrictions.registered = true; - - kfree(res); return ret; } @@ -367,28 +369,19 @@ static int io_register_clock(struct io_ring_ctx *ctx, * either mapping or freeing. */ struct io_ring_ctx_rings { - unsigned short n_ring_pages; - unsigned short n_sqe_pages; - struct page **ring_pages; - struct page **sqe_pages; - struct io_uring_sqe *sq_sqes; struct io_rings *rings; + struct io_uring_sqe *sq_sqes; + + struct io_mapped_region sq_region; + struct io_mapped_region ring_region; }; -static void io_register_free_rings(struct io_uring_params *p, +static void io_register_free_rings(struct io_ring_ctx *ctx, + struct io_uring_params *p, struct io_ring_ctx_rings *r) { - if (!(p->flags & IORING_SETUP_NO_MMAP)) { - io_pages_unmap(r->rings, &r->ring_pages, &r->n_ring_pages, - true); - io_pages_unmap(r->sq_sqes, &r->sqe_pages, &r->n_sqe_pages, - true); - } else { - io_pages_free(&r->ring_pages, r->n_ring_pages); - io_pages_free(&r->sqe_pages, r->n_sqe_pages); - vunmap(r->rings); - vunmap(r->sq_sqes); - } + io_free_region(ctx, &r->sq_region); + io_free_region(ctx, &r->ring_region); } #define swap_old(ctx, o, n, field) \ @@ -403,17 +396,20 @@ static void io_register_free_rings(struct io_uring_params *p, static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) { + struct io_uring_region_desc rd; struct io_ring_ctx_rings o = { }, n = { }, *to_free = NULL; size_t size, sq_array_offset; + unsigned i, tail, old_head; struct io_uring_params p; - unsigned i, tail; - void *ptr; int ret; /* for single issuer, must be owner resizing */ if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && current != ctx->submitter_task) return -EEXIST; + /* limited to DEFER_TASKRUN for now */ + if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)) + return -EINVAL; if (copy_from_user(&p, arg, sizeof(p))) return -EFAULT; if (p.flags & ~RESIZE_FLAGS) @@ -438,21 +434,34 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) if (size == SIZE_MAX) return -EOVERFLOW; - if (!(p.flags & IORING_SETUP_NO_MMAP)) - n.rings = io_pages_map(&n.ring_pages, &n.n_ring_pages, size); - else - n.rings = __io_uaddr_map(&n.ring_pages, &n.n_ring_pages, - p.cq_off.user_addr, size); - if (IS_ERR(n.rings)) - return PTR_ERR(n.rings); + memset(&rd, 0, sizeof(rd)); + rd.size = PAGE_ALIGN(size); + if (p.flags & IORING_SETUP_NO_MMAP) { + rd.user_addr = p.cq_off.user_addr; + rd.flags |= IORING_MEM_REGION_TYPE_USER; + } + ret = io_create_region_mmap_safe(ctx, &n.ring_region, &rd, IORING_OFF_CQ_RING); + if (ret) { + io_register_free_rings(ctx, &p, &n); + return ret; + } + n.rings = io_region_get_ptr(&n.ring_region); - n.rings->sq_ring_mask = p.sq_entries - 1; - n.rings->cq_ring_mask = p.cq_entries - 1; - n.rings->sq_ring_entries = p.sq_entries; - n.rings->cq_ring_entries = p.cq_entries; + /* + * At this point n.rings is shared with userspace, just like o.rings + * is as well. While we don't expect userspace to modify it while + * a resize is in progress, and it's most likely that userspace will + * shoot itself in the foot if it does, we can't always assume good + * intent... Use read/write once helpers from here on to indicate the + * shared nature of it. + */ + WRITE_ONCE(n.rings->sq_ring_mask, p.sq_entries - 1); + WRITE_ONCE(n.rings->cq_ring_mask, p.cq_entries - 1); + WRITE_ONCE(n.rings->sq_ring_entries, p.sq_entries); + WRITE_ONCE(n.rings->cq_ring_entries, p.cq_entries); if (copy_to_user(arg, &p, sizeof(p))) { - io_register_free_rings(&p, &n); + io_register_free_rings(ctx, &p, &n); return -EFAULT; } @@ -461,20 +470,22 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) else size = array_size(sizeof(struct io_uring_sqe), p.sq_entries); if (size == SIZE_MAX) { - io_register_free_rings(&p, &n); + io_register_free_rings(ctx, &p, &n); return -EOVERFLOW; } - if (!(p.flags & IORING_SETUP_NO_MMAP)) - ptr = io_pages_map(&n.sqe_pages, &n.n_sqe_pages, size); - else - ptr = __io_uaddr_map(&n.sqe_pages, &n.n_sqe_pages, - p.sq_off.user_addr, - size); - if (IS_ERR(ptr)) { - io_register_free_rings(&p, &n); - return PTR_ERR(ptr); + memset(&rd, 0, sizeof(rd)); + rd.size = PAGE_ALIGN(size); + if (p.flags & IORING_SETUP_NO_MMAP) { + rd.user_addr = p.sq_off.user_addr; + rd.flags |= IORING_MEM_REGION_TYPE_USER; } + ret = io_create_region_mmap_safe(ctx, &n.sq_region, &rd, IORING_OFF_SQES); + if (ret) { + io_register_free_rings(ctx, &p, &n); + return ret; + } + n.sq_sqes = io_region_get_ptr(&n.sq_region); /* * If using SQPOLL, park the thread @@ -486,15 +497,15 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) } /* - * We'll do the swap. Grab the ctx->resize_lock, which will exclude + * We'll do the swap. Grab the ctx->mmap_lock, which will exclude * any new mmap's on the ring fd. Clear out existing mappings to prevent * mmap from seeing them, as we'll unmap them. Any attempt to mmap * existing rings beyond this point will fail. Not that it could proceed * at this point anyway, as the io_uring mmap side needs go grab the - * ctx->resize_lock as well. Likewise, hold the completion lock over the + * ctx->mmap_lock as well. Likewise, hold the completion lock over the * duration of the actual swap. */ - mutex_lock(&ctx->resize_lock); + mutex_lock(&ctx->mmap_lock); spin_lock(&ctx->completion_lock); o.rings = ctx->rings; ctx->rings = NULL; @@ -505,21 +516,22 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) * Now copy SQ and CQ entries, if any. If either of the destination * rings can't hold what is already there, then fail the operation. */ - n.sq_sqes = ptr; - tail = o.rings->sq.tail; - if (tail - o.rings->sq.head > p.sq_entries) + tail = READ_ONCE(o.rings->sq.tail); + old_head = READ_ONCE(o.rings->sq.head); + if (tail - old_head > p.sq_entries) goto overflow; - for (i = o.rings->sq.head; i < tail; i++) { + for (i = old_head; i < tail; i++) { unsigned src_head = i & (ctx->sq_entries - 1); - unsigned dst_head = i & n.rings->sq_ring_mask; + unsigned dst_head = i & (p.sq_entries - 1); n.sq_sqes[dst_head] = o.sq_sqes[src_head]; } - n.rings->sq.head = o.rings->sq.head; - n.rings->sq.tail = o.rings->sq.tail; + WRITE_ONCE(n.rings->sq.head, old_head); + WRITE_ONCE(n.rings->sq.tail, tail); - tail = o.rings->cq.tail; - if (tail - o.rings->cq.head > p.cq_entries) { + tail = READ_ONCE(o.rings->cq.tail); + old_head = READ_ONCE(o.rings->cq.head); + if (tail - old_head > p.cq_entries) { overflow: /* restore old rings, and return -EOVERFLOW via cleanup path */ ctx->rings = o.rings; @@ -528,21 +540,21 @@ overflow: ret = -EOVERFLOW; goto out; } - for (i = o.rings->cq.head; i < tail; i++) { + for (i = old_head; i < tail; i++) { unsigned src_head = i & (ctx->cq_entries - 1); - unsigned dst_head = i & n.rings->cq_ring_mask; + unsigned dst_head = i & (p.cq_entries - 1); n.rings->cqes[dst_head] = o.rings->cqes[src_head]; } - n.rings->cq.head = o.rings->cq.head; - n.rings->cq.tail = o.rings->cq.tail; + WRITE_ONCE(n.rings->cq.head, old_head); + WRITE_ONCE(n.rings->cq.tail, tail); /* invalidate cached cqe refill */ ctx->cqe_cached = ctx->cqe_sentinel = NULL; - n.rings->sq_dropped = o.rings->sq_dropped; - n.rings->sq_flags = o.rings->sq_flags; - n.rings->cq_flags = o.rings->cq_flags; - n.rings->cq_overflow = o.rings->cq_overflow; + WRITE_ONCE(n.rings->sq_dropped, READ_ONCE(o.rings->sq_dropped)); + atomic_set(&n.rings->sq_flags, atomic_read(&o.rings->sq_flags)); + WRITE_ONCE(n.rings->cq_flags, READ_ONCE(o.rings->cq_flags)); + WRITE_ONCE(n.rings->cq_overflow, READ_ONCE(o.rings->cq_overflow)); /* all done, store old pointers and assign new ones */ if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) @@ -553,16 +565,14 @@ overflow: ctx->rings = n.rings; ctx->sq_sqes = n.sq_sqes; - swap_old(ctx, o, n, n_ring_pages); - swap_old(ctx, o, n, n_sqe_pages); - swap_old(ctx, o, n, ring_pages); - swap_old(ctx, o, n, sqe_pages); + swap_old(ctx, o, n, ring_region); + swap_old(ctx, o, n, sq_region); to_free = &o; ret = 0; out: spin_unlock(&ctx->completion_lock); - mutex_unlock(&ctx->resize_lock); - io_register_free_rings(&p, to_free); + mutex_unlock(&ctx->mmap_lock); + io_register_free_rings(ctx, &p, to_free); if (ctx->sq_data) io_sq_thread_unpark(ctx->sq_data); @@ -585,7 +595,6 @@ static int io_register_mem_region(struct io_ring_ctx *ctx, void __user *uarg) rd_uptr = u64_to_user_ptr(reg.region_uptr); if (copy_from_user(&rd, rd_uptr, sizeof(rd))) return -EFAULT; - if (memchr_inv(®.__resv, 0, sizeof(reg.__resv))) return -EINVAL; if (reg.flags & ~IORING_MEM_REGION_REG_WAIT_ARG) @@ -600,7 +609,8 @@ static int io_register_mem_region(struct io_ring_ctx *ctx, void __user *uarg) !(ctx->flags & IORING_SETUP_R_DISABLED)) return -EINVAL; - ret = io_create_region(ctx, &ctx->param_region, &rd); + ret = io_create_region_mmap_safe(ctx, &ctx->param_region, &rd, + IORING_MAP_OFF_PARAM_REGION); if (ret) return ret; if (copy_to_user(rd_uptr, &rd, sizeof(rd))) { @@ -843,6 +853,8 @@ struct file *io_uring_register_get_file(unsigned int fd, bool registered) return ERR_PTR(-EINVAL); fd = array_index_nospec(fd, IO_RINGFD_REG_MAX); file = tctx->registered_rings[fd]; + if (file) + get_file(file); } else { file = fget(fd); } @@ -909,7 +921,7 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, trace_io_uring_register(ctx, opcode, ctx->file_table.data.nr, ctx->buf_table.nr, ret); mutex_unlock(&ctx->uring_lock); - if (!use_registered_ring) - fput(file); + + fput(file); return ret; } diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 077f84684c18..af39b69eb4fd 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -118,7 +118,7 @@ static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_rsrc_node *node) } } -struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type) +struct io_rsrc_node *io_rsrc_node_alloc(int type) { struct io_rsrc_node *node; @@ -203,7 +203,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE); + node = io_rsrc_node_alloc(IORING_RSRC_FILE); if (!node) { err = -ENOMEM; fput(file); @@ -444,8 +444,6 @@ int io_files_update(struct io_kiocb *req, unsigned int issue_flags) void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node) { - lockdep_assert_held(&ctx->uring_lock); - if (node->tag) io_post_aux_cqe(ctx, node->tag, 0, 0); @@ -525,7 +523,7 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, goto fail; } ret = -ENOMEM; - node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE); + node = io_rsrc_node_alloc(IORING_RSRC_FILE); if (!node) { fput(file); goto fail; @@ -626,11 +624,12 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, return ret; } -static bool io_do_coalesce_buffer(struct page ***pages, int *nr_pages, - struct io_imu_folio_data *data, int nr_folios) +static bool io_coalesce_buffer(struct page ***pages, int *nr_pages, + struct io_imu_folio_data *data) { struct page **page_array = *pages, **new_array = NULL; int nr_pages_left = *nr_pages, i, j; + int nr_folios = data->nr_folios; /* Store head pages only*/ new_array = kvmalloc_array(nr_folios, sizeof(struct page *), @@ -667,27 +666,21 @@ static bool io_do_coalesce_buffer(struct page ***pages, int *nr_pages, return true; } -static bool io_try_coalesce_buffer(struct page ***pages, int *nr_pages, - struct io_imu_folio_data *data) +bool io_check_coalesce_buffer(struct page **page_array, int nr_pages, + struct io_imu_folio_data *data) { - struct page **page_array = *pages; struct folio *folio = page_folio(page_array[0]); unsigned int count = 1, nr_folios = 1; int i; - if (*nr_pages <= 1) - return false; - data->nr_pages_mid = folio_nr_pages(folio); - if (data->nr_pages_mid == 1) - return false; - data->folio_shift = folio_shift(folio); + /* * Check if pages are contiguous inside a folio, and all folios have * the same page count except for the head and tail. */ - for (i = 1; i < *nr_pages; i++) { + for (i = 1; i < nr_pages; i++) { if (page_folio(page_array[i]) == folio && page_array[i] == page_array[i-1] + 1) { count++; @@ -715,7 +708,8 @@ static bool io_try_coalesce_buffer(struct page ***pages, int *nr_pages, if (nr_folios == 1) data->nr_pages_head = count; - return io_do_coalesce_buffer(pages, nr_pages, data, nr_folios); + data->nr_folios = nr_folios; + return true; } static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, @@ -729,12 +723,12 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, size_t size; int ret, nr_pages, i; struct io_imu_folio_data data; - bool coalesced; + bool coalesced = false; if (!iov->iov_base) return NULL; - node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER); + node = io_rsrc_node_alloc(IORING_RSRC_BUFFER); if (!node) return ERR_PTR(-ENOMEM); node->buf = NULL; @@ -749,7 +743,10 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, } /* If it's huge page(s), try to coalesce them into fewer bvec entries */ - coalesced = io_try_coalesce_buffer(&pages, &nr_pages, &data); + if (nr_pages > 1 && io_check_coalesce_buffer(pages, nr_pages, &data)) { + if (data.nr_pages_mid != 1) + coalesced = io_coalesce_buffer(&pages, &nr_pages, &data); + } imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); if (!imu) @@ -883,7 +880,7 @@ int io_import_fixed(int ddir, struct iov_iter *iter, * and advance us to the beginning. */ offset = buf_addr - imu->ubuf; - iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, offset + len); + iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, len); if (offset) { /* @@ -905,7 +902,6 @@ int io_import_fixed(int ddir, struct iov_iter *iter, const struct bio_vec *bvec = imu->bvec; if (offset < bvec->bv_len) { - iter->count -= offset; iter->iov_offset = offset; } else { unsigned long seg_skip; @@ -916,7 +912,6 @@ int io_import_fixed(int ddir, struct iov_iter *iter, iter->bvec += seg_skip; iter->nr_segs -= seg_skip; - iter->count -= bvec->bv_len + offset; iter->iov_offset = offset & ((1UL << imu->folio_shift) - 1); } } @@ -924,6 +919,16 @@ int io_import_fixed(int ddir, struct iov_iter *iter, return 0; } +/* Lock two rings at once. The rings must be different! */ +static void lock_two_rings(struct io_ring_ctx *ctx1, struct io_ring_ctx *ctx2) +{ + if (ctx1 > ctx2) + swap(ctx1, ctx2); + mutex_lock(&ctx1->uring_lock); + mutex_lock_nested(&ctx2->uring_lock, SINGLE_DEPTH_NESTING); +} + +/* Both rings are locked by the caller. */ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx, struct io_uring_clone_buffers *arg) { @@ -931,6 +936,16 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx int i, ret, off, nr; unsigned int nbufs; + lockdep_assert_held(&ctx->uring_lock); + lockdep_assert_held(&src_ctx->uring_lock); + + /* + * Accounting state is shared between the two rings; that only works if + * both rings are accounted towards the same counters. + */ + if (ctx->user != src_ctx->user || ctx->mm_account != src_ctx->mm_account) + return -EINVAL; + /* if offsets are given, must have nr specified too */ if (!arg->nr && (arg->dst_off || arg->src_off)) return -EINVAL; @@ -938,7 +953,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx if (ctx->buf_table.nr && !(arg->flags & IORING_REGISTER_DST_REPLACE)) return -EBUSY; - nbufs = READ_ONCE(src_ctx->buf_table.nr); + nbufs = src_ctx->buf_table.nr; if (!arg->nr) arg->nr = nbufs; else if (arg->nr > nbufs) @@ -962,27 +977,20 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx } } - /* - * Drop our own lock here. We'll setup the data we need and reference - * the source buffers, then re-grab, check, and assign at the end. - */ - mutex_unlock(&ctx->uring_lock); - - mutex_lock(&src_ctx->uring_lock); ret = -ENXIO; nbufs = src_ctx->buf_table.nr; if (!nbufs) - goto out_unlock; + goto out_free; ret = -EINVAL; if (!arg->nr) arg->nr = nbufs; else if (arg->nr > nbufs) - goto out_unlock; + goto out_free; ret = -EOVERFLOW; if (check_add_overflow(arg->nr, arg->src_off, &off)) - goto out_unlock; + goto out_free; if (off > nbufs) - goto out_unlock; + goto out_free; off = arg->dst_off; i = arg->src_off; @@ -994,10 +1002,10 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx if (!src_node) { dst_node = NULL; } else { - dst_node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER); + dst_node = io_rsrc_node_alloc(IORING_RSRC_BUFFER); if (!dst_node) { ret = -ENOMEM; - goto out_put_free; + goto out_free; } refcount_inc(&src_node->buf->refs); @@ -1007,10 +1015,6 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx i++; } - /* Have a ref on the bufs now, drop src lock and re-grab our own lock */ - mutex_unlock(&src_ctx->uring_lock); - mutex_lock(&ctx->uring_lock); - /* * If asked for replace, put the old table. data->nodes[] holds both * old and new nodes at this point. @@ -1019,32 +1023,17 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx io_rsrc_data_free(ctx, &ctx->buf_table); /* - * ctx->buf_table should be empty now - either the contents are being - * replaced and we just freed the table, or someone raced setting up - * a buffer table while the clone was happening. If not empty, fall - * through to failure handling. + * ctx->buf_table must be empty now - either the contents are being + * replaced and we just freed the table, or the contents are being + * copied to a ring that does not have buffers yet (checked at function + * entry). */ - if (!ctx->buf_table.nr) { - ctx->buf_table = data; - return 0; - } + WARN_ON_ONCE(ctx->buf_table.nr); + ctx->buf_table = data; + return 0; - mutex_unlock(&ctx->uring_lock); - mutex_lock(&src_ctx->uring_lock); - /* someone raced setting up buffers, dump ours */ - ret = -EBUSY; -out_put_free: - i = data.nr; - while (i--) { - if (data.nodes[i]) { - io_buffer_unmap(src_ctx, data.nodes[i]); - kfree(data.nodes[i]); - } - } -out_unlock: +out_free: io_rsrc_data_free(ctx, &data); - mutex_unlock(&src_ctx->uring_lock); - mutex_lock(&ctx->uring_lock); return ret; } @@ -1058,6 +1047,7 @@ out_unlock: int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg) { struct io_uring_clone_buffers buf; + struct io_ring_ctx *src_ctx; bool registered_src; struct file *file; int ret; @@ -1075,8 +1065,18 @@ int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg) file = io_uring_register_get_file(buf.src_fd, registered_src); if (IS_ERR(file)) return PTR_ERR(file); - ret = io_clone_buffers(ctx, file->private_data, &buf); - if (!registered_src) - fput(file); + + src_ctx = file->private_data; + if (src_ctx != ctx) { + mutex_unlock(&ctx->uring_lock); + lock_two_rings(ctx, src_ctx); + } + + ret = io_clone_buffers(ctx, src_ctx, &buf); + + if (src_ctx != ctx) + mutex_unlock(&src_ctx->uring_lock); + + fput(file); return ret; } diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 7a4668deaa1a..190f7ee45de9 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -2,6 +2,8 @@ #ifndef IOU_RSRC_H #define IOU_RSRC_H +#include + #define IO_NODE_ALLOC_CACHE_MAX 32 #define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) @@ -40,9 +42,10 @@ struct io_imu_folio_data { /* For non-head/tail folios, has to be fully included */ unsigned int nr_pages_mid; unsigned int folio_shift; + unsigned int nr_folios; }; -struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type); +struct io_rsrc_node *io_rsrc_node_alloc(int type); void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node); void io_rsrc_data_free(struct io_ring_ctx *ctx, struct io_rsrc_data *data); int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr); @@ -66,6 +69,9 @@ int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, unsigned int size, unsigned int type); +bool io_check_coalesce_buffer(struct page **page_array, int nr_pages, + struct io_imu_folio_data *data); + static inline struct io_rsrc_node *io_rsrc_node_lookup(struct io_rsrc_data *data, int index) { @@ -76,6 +82,7 @@ static inline struct io_rsrc_node *io_rsrc_node_lookup(struct io_rsrc_data *data static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node) { + lockdep_assert_held(&ctx->uring_lock); if (node && !--node->refs) io_free_rsrc_node(ctx, node); } diff --git a/io_uring/rw.c b/io_uring/rw.c index 0bcb83e4ce3c..7aa1e4c9f64a 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -146,28 +146,15 @@ static inline int io_import_iovec(int rw, struct io_kiocb *req, return 0; } -static void io_rw_iovec_free(struct io_async_rw *rw) -{ - if (rw->free_iovec) { - kfree(rw->free_iovec); - rw->free_iov_nr = 0; - rw->free_iovec = NULL; - } -} - static void io_rw_recycle(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_rw *rw = req->async_data; - struct iovec *iov; - if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) { - io_rw_iovec_free(rw); + if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) return; - } - iov = rw->free_iovec; + + io_alloc_cache_kasan(&rw->free_iovec, &rw->free_iov_nr); if (io_alloc_cache_put(&req->ctx->rw_cache, rw)) { - if (iov) - kasan_mempool_poison_object(iov); req->async_data = NULL; req->flags &= ~REQ_F_ASYNC_DATA; } @@ -202,7 +189,7 @@ static void io_req_rw_cleanup(struct io_kiocb *req, unsigned int issue_flags) * mean that the underlying data can be gone at any time. But that * should be fixed seperately, and then this check could be killed. */ - if (!(req->flags & REQ_F_REFCOUNT)) { + if (!(req->flags & (REQ_F_REISSUE | REQ_F_REFCOUNT))) { req->flags &= ~REQ_F_NEED_CLEANUP; io_rw_recycle(req, issue_flags); } @@ -213,34 +200,18 @@ static int io_rw_alloc_async(struct io_kiocb *req) struct io_ring_ctx *ctx = req->ctx; struct io_async_rw *rw; - rw = io_alloc_cache_get(&ctx->rw_cache); - if (rw) { - if (rw->free_iovec) { - kasan_mempool_unpoison_object(rw->free_iovec, - rw->free_iov_nr * sizeof(struct iovec)); - req->flags |= REQ_F_NEED_CLEANUP; - } - req->flags |= REQ_F_ASYNC_DATA; - req->async_data = rw; - goto done; - } - - if (!io_alloc_async_data(req)) { - rw = req->async_data; - rw->free_iovec = NULL; - rw->free_iov_nr = 0; -done: - rw->bytes_done = 0; - return 0; - } - - return -ENOMEM; + rw = io_uring_alloc_async_data(&ctx->rw_cache, req); + if (!rw) + return -ENOMEM; + if (rw->free_iovec) + req->flags |= REQ_F_NEED_CLEANUP; + rw->bytes_done = 0; + return 0; } static int io_prep_rw_setup(struct io_kiocb *req, int ddir, bool do_import) { struct io_async_rw *rw; - int ret; if (io_rw_alloc_async(req)) return -ENOMEM; @@ -249,12 +220,48 @@ static int io_prep_rw_setup(struct io_kiocb *req, int ddir, bool do_import) return 0; rw = req->async_data; - ret = io_import_iovec(ddir, req, rw, 0); + return io_import_iovec(ddir, req, rw, 0); +} + +static inline void io_meta_save_state(struct io_async_rw *io) +{ + io->meta_state.seed = io->meta.seed; + iov_iter_save_state(&io->meta.iter, &io->meta_state.iter_meta); +} + +static inline void io_meta_restore(struct io_async_rw *io, struct kiocb *kiocb) +{ + if (kiocb->ki_flags & IOCB_HAS_METADATA) { + io->meta.seed = io->meta_state.seed; + iov_iter_restore(&io->meta.iter, &io->meta_state.iter_meta); + } +} + +static int io_prep_rw_pi(struct io_kiocb *req, struct io_rw *rw, int ddir, + u64 attr_ptr, u64 attr_type_mask) +{ + struct io_uring_attr_pi pi_attr; + struct io_async_rw *io; + int ret; + + if (copy_from_user(&pi_attr, u64_to_user_ptr(attr_ptr), + sizeof(pi_attr))) + return -EFAULT; + + if (pi_attr.rsvd) + return -EINVAL; + + io = req->async_data; + io->meta.flags = pi_attr.flags; + io->meta.app_tag = pi_attr.app_tag; + io->meta.seed = pi_attr.seed; + ret = import_ubuf(ddir, u64_to_user_ptr(pi_attr.addr), + pi_attr.len, &io->meta.iter); if (unlikely(ret < 0)) return ret; - - iov_iter_save_state(&rw->iter, &rw->iter_state); - return 0; + req->flags |= REQ_F_HAS_METADATA; + io_meta_save_state(io); + return ret; } static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, @@ -262,6 +269,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); unsigned ioprio; + u64 attr_type_mask; int ret; rw->kiocb.ki_pos = READ_ONCE(sqe->off); @@ -279,11 +287,28 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, rw->kiocb.ki_ioprio = get_current_ioprio(); } rw->kiocb.dio_complete = NULL; + rw->kiocb.ki_flags = 0; rw->addr = READ_ONCE(sqe->addr); rw->len = READ_ONCE(sqe->len); rw->flags = READ_ONCE(sqe->rw_flags); - return io_prep_rw_setup(req, ddir, do_import); + ret = io_prep_rw_setup(req, ddir, do_import); + + if (unlikely(ret)) + return ret; + + attr_type_mask = READ_ONCE(sqe->attr_type_mask); + if (attr_type_mask) { + u64 attr_ptr; + + /* only PI attribute is supported currently */ + if (attr_type_mask != IORING_RW_ATTR_FLAG_PI) + return -EINVAL; + + attr_ptr = READ_ONCE(sqe->attr_ptr); + ret = io_prep_rw_pi(req, rw, ddir, attr_ptr, attr_type_mask); + } + return ret; } int io_prep_read(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -385,7 +410,8 @@ int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) void io_readv_writev_cleanup(struct io_kiocb *req) { - io_rw_iovec_free(req->async_data); + lockdep_assert_held(&req->ctx->uring_lock); + io_rw_recycle(req, 0); } static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) @@ -405,17 +431,12 @@ static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) return NULL; } -#ifdef CONFIG_BLOCK -static void io_resubmit_prep(struct io_kiocb *req) -{ - struct io_async_rw *io = req->async_data; - - iov_iter_restore(&io->iter, &io->iter_state); -} - static bool io_rw_should_reissue(struct io_kiocb *req) { +#ifdef CONFIG_BLOCK + struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); umode_t mode = file_inode(req->file)->i_mode; + struct io_async_rw *io = req->async_data; struct io_ring_ctx *ctx = req->ctx; if (!S_ISBLK(mode) && !S_ISREG(mode)) @@ -430,23 +451,14 @@ static bool io_rw_should_reissue(struct io_kiocb *req) */ if (percpu_ref_is_dying(&ctx->refs)) return false; - /* - * Play it safe and assume not safe to re-import and reissue if we're - * not in the original thread group (or in task context). - */ - if (!same_thread_group(req->tctx->task, current) || !in_task()) - return false; + + io_meta_restore(io, &rw->kiocb); + iov_iter_restore(&io->iter, &io->iter_state); return true; -} #else -static void io_resubmit_prep(struct io_kiocb *req) -{ -} -static bool io_rw_should_reissue(struct io_kiocb *req) -{ return false; -} #endif +} static void io_req_end_write(struct io_kiocb *req) { @@ -473,22 +485,16 @@ static void io_req_io_end(struct io_kiocb *req) } } -static bool __io_complete_rw_common(struct io_kiocb *req, long res) +static void __io_complete_rw_common(struct io_kiocb *req, long res) { - if (unlikely(res != req->cqe.res)) { - if (res == -EAGAIN && io_rw_should_reissue(req)) { - /* - * Reissue will start accounting again, finish the - * current cycle. - */ - io_req_io_end(req); - req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE; - return true; - } + if (res == req->cqe.res) + return; + if (res == -EAGAIN && io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE; + } else { req_set_fail(req); req->cqe.res = res; } - return false; } static inline int io_fixup_rw_res(struct io_kiocb *req, long res) @@ -531,8 +537,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res) struct io_kiocb *req = cmd_to_io_kiocb(rw); if (!kiocb->dio_complete || !(kiocb->ki_flags & IOCB_DIO_CALLER_COMP)) { - if (__io_complete_rw_common(req, res)) - return; + __io_complete_rw_common(req, res); io_req_set_res(req, io_fixup_rw_res(req, res), 0); } req->io_task_work.func = io_req_rw_complete; @@ -594,26 +599,19 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret, if (ret >= 0 && req->flags & REQ_F_CUR_POS) req->file->f_pos = rw->kiocb.ki_pos; if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) { - if (!__io_complete_rw_common(req, ret)) { - /* - * Safe to call io_end from here as we're inline - * from the submission path. - */ - io_req_io_end(req); - io_req_set_res(req, final_ret, - io_put_kbuf(req, ret, issue_flags)); - io_req_rw_cleanup(req, issue_flags); - return IOU_OK; - } + __io_complete_rw_common(req, ret); + /* + * Safe to call io_end from here as we're inline + * from the submission path. + */ + io_req_io_end(req); + io_req_set_res(req, final_ret, io_put_kbuf(req, ret, issue_flags)); + io_req_rw_cleanup(req, issue_flags); + return IOU_OK; } else { io_rw_done(&rw->kiocb, ret); } - if (req->flags & REQ_F_REISSUE) { - req->flags &= ~REQ_F_REISSUE; - io_resubmit_prep(req); - return -EAGAIN; - } return IOU_ISSUE_SKIP_COMPLETE; } @@ -736,8 +734,11 @@ static bool io_rw_should_retry(struct io_kiocb *req) struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); struct kiocb *kiocb = &rw->kiocb; - /* never retry for NOWAIT, we just complete with -EAGAIN */ - if (req->flags & REQ_F_NOWAIT) + /* + * Never retry for NOWAIT or a request with metadata, we just complete + * with -EAGAIN. + */ + if (req->flags & (REQ_F_NOWAIT | REQ_F_HAS_METADATA)) return false; /* Only for buffered IO */ @@ -828,6 +829,19 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) kiocb->ki_complete = io_complete_rw; } + if (req->flags & REQ_F_HAS_METADATA) { + struct io_async_rw *io = req->async_data; + + /* + * We have a union of meta fields with wpq used for buffered-io + * in io_async_rw, so fail it here. + */ + if (!(req->file->f_flags & O_DIRECT)) + return -EOPNOTSUPP; + kiocb->ki_flags |= IOCB_HAS_METADATA; + kiocb->private = &io->meta; + } + return 0; } @@ -876,8 +890,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags) if (ret == -EOPNOTSUPP && force_nonblock) ret = -EAGAIN; - if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { - req->flags &= ~REQ_F_REISSUE; + if (ret == -EAGAIN) { /* If we can poll, just do that. */ if (io_file_can_poll(req)) return -EAGAIN; @@ -902,6 +915,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags) * manually if we need to. */ iov_iter_restore(&io->iter, &io->iter_state); + io_meta_restore(io, kiocb); do { /* @@ -983,6 +997,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) io_kbuf_recycle(req, issue_flags); if (ret < 0) req_set_fail(req); + } else if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + cflags = io_put_kbuf(req, ret, issue_flags); } else { /* * Any successful return value will keep the multishot read @@ -1085,11 +1101,6 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) else ret2 = -EINVAL; - if (req->flags & REQ_F_REISSUE) { - req->flags &= ~REQ_F_REISSUE; - ret2 = -EAGAIN; - } - /* * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just * retry them without IOCB_NOWAIT. @@ -1125,6 +1136,7 @@ done: } else { ret_eagain: iov_iter_restore(&io->iter, &io->iter_state); + io_meta_restore(io, kiocb); if (kiocb->ki_flags & IOCB_WRITE) io_req_end_write(req); return -EAGAIN; @@ -1287,10 +1299,7 @@ void io_rw_cache_free(const void *entry) { struct io_async_rw *rw = (struct io_async_rw *) entry; - if (rw->free_iovec) { - kasan_mempool_unpoison_object(rw->free_iovec, - rw->free_iov_nr * sizeof(struct iovec)); - io_rw_iovec_free(rw); - } + if (rw->free_iovec) + kfree(rw->free_iovec); kfree(rw); } diff --git a/io_uring/rw.h b/io_uring/rw.h index 3f432dc75441..eaa59bd64870 100644 --- a/io_uring/rw.h +++ b/io_uring/rw.h @@ -2,14 +2,31 @@ #include +struct io_meta_state { + u32 seed; + struct iov_iter_state iter_meta; +}; + struct io_async_rw { size_t bytes_done; - struct iov_iter iter; - struct iov_iter_state iter_state; - struct iovec fast_iov; struct iovec *free_iovec; - int free_iov_nr; - struct wait_page_queue wpq; + struct_group(clear, + struct iov_iter iter; + struct iov_iter_state iter_state; + struct iovec fast_iov; + int free_iov_nr; + /* + * wpq is for buffered io, while meta fields are used with + * direct io + */ + union { + struct wait_page_queue wpq; + struct { + struct uio_meta meta; + struct io_meta_state meta_state; + }; + }; + ); }; int io_prep_read_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe); diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 6df5e649c413..d037cc68e9d3 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -264,12 +264,16 @@ static int io_sq_thread(void *data) struct io_ring_ctx *ctx; struct rusage start; unsigned long timeout = 0; - char buf[TASK_COMM_LEN]; + char buf[TASK_COMM_LEN] = {}; DEFINE_WAIT(wait); /* offload context creation failed, just exit */ - if (!current->io_uring) + if (!current->io_uring) { + mutex_lock(&sqd->lock); + sqd->thread = NULL; + mutex_unlock(&sqd->lock); goto err_out; + } snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); set_task_comm(current, buf); @@ -405,6 +409,7 @@ void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) __cold int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_uring_params *p) { + struct task_struct *task_to_put = NULL; int ret; /* Retain compatibility with failing for an invalid attach attempt */ @@ -480,6 +485,7 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx, } sqd->thread = tsk; + task_to_put = get_task_struct(tsk); ret = io_uring_alloc_task_context(tsk, ctx); wake_up_new_task(tsk); if (ret) @@ -490,11 +496,15 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx, goto err; } + if (task_to_put) + put_task_struct(task_to_put); return 0; err_sqpoll: complete(&ctx->sq_data->exited); err: io_sq_thread_finish(ctx); + if (task_to_put) + put_task_struct(task_to_put); return ret; } diff --git a/io_uring/timeout.c b/io_uring/timeout.c index f3d502717aeb..48fc8cf70784 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -74,10 +74,10 @@ static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts) if (!io_timeout_finish(timeout, data)) { if (io_req_post_cqe(req, -ETIME, IORING_CQE_F_MORE)) { /* re-arm timer */ - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); list_add(&timeout->list, ctx->timeout_list.prev); hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); return; } } @@ -85,7 +85,27 @@ static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts) io_req_task_complete(req, ts); } -static bool io_kill_timeout(struct io_kiocb *req, int status) +static __cold bool io_flush_killed_timeouts(struct list_head *list, int err) +{ + if (list_empty(list)) + return false; + + while (!list_empty(list)) { + struct io_timeout *timeout; + struct io_kiocb *req; + + timeout = list_first_entry(list, struct io_timeout, list); + list_del_init(&timeout->list); + req = cmd_to_io_kiocb(timeout); + if (err) + req_set_fail(req); + io_req_queue_tw_complete(req, err); + } + + return true; +} + +static void io_kill_timeout(struct io_kiocb *req, struct list_head *list) __must_hold(&req->ctx->timeout_lock) { struct io_timeout_data *io = req->async_data; @@ -93,23 +113,19 @@ static bool io_kill_timeout(struct io_kiocb *req, int status) if (hrtimer_try_to_cancel(&io->timer) != -1) { struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout); - if (status) - req_set_fail(req); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); - list_del_init(&timeout->list); - io_req_queue_tw_complete(req, status); - return true; + list_move_tail(&timeout->list, list); } - return false; } __cold void io_flush_timeouts(struct io_ring_ctx *ctx) { - u32 seq; struct io_timeout *timeout, *tmp; + LIST_HEAD(list); + u32 seq; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); list_for_each_entry_safe(timeout, tmp, &ctx->timeout_list, list) { @@ -131,10 +147,11 @@ __cold void io_flush_timeouts(struct io_ring_ctx *ctx) if (events_got < events_needed) break; - io_kill_timeout(req, 0); + io_kill_timeout(req, &list); } ctx->cq_last_tm_flush = seq; - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); + io_flush_killed_timeouts(&list, 0); } static void io_req_tw_fail_links(struct io_kiocb *link, struct io_tw_state *ts) @@ -200,9 +217,9 @@ void io_disarm_next(struct io_kiocb *req) } else if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); link = io_disarm_linked_timeout(req); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); if (link) io_req_queue_tw_complete(link, -ECANCELED); } @@ -238,11 +255,11 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) struct io_ring_ctx *ctx = req->ctx; unsigned long flags; - spin_lock_irqsave(&ctx->timeout_lock, flags); + raw_spin_lock_irqsave(&ctx->timeout_lock, flags); list_del_init(&timeout->list); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); - spin_unlock_irqrestore(&ctx->timeout_lock, flags); + raw_spin_unlock_irqrestore(&ctx->timeout_lock, flags); if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) req_set_fail(req); @@ -285,9 +302,9 @@ int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) { struct io_kiocb *req; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); req = io_timeout_extract(ctx, cd); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); if (IS_ERR(req)) return PTR_ERR(req); @@ -330,7 +347,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) struct io_ring_ctx *ctx = req->ctx; unsigned long flags; - spin_lock_irqsave(&ctx->timeout_lock, flags); + raw_spin_lock_irqsave(&ctx->timeout_lock, flags); prev = timeout->head; timeout->head = NULL; @@ -345,7 +362,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) } list_del(&timeout->list); timeout->prev = prev; - spin_unlock_irqrestore(&ctx->timeout_lock, flags); + raw_spin_unlock_irqrestore(&ctx->timeout_lock, flags); req->io_task_work.func = io_req_task_link_timeout; io_req_task_work_add(req); @@ -410,10 +427,12 @@ static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, timeout->off = 0; /* noseq */ data = req->async_data; + data->ts = *ts; + list_add_tail(&timeout->list, &ctx->timeout_list); hrtimer_init(&data->timer, io_timeout_get_clock(data), mode); data->timer.function = io_timeout_fn; - hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode); + hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), mode); return 0; } @@ -472,12 +491,12 @@ int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) } else { enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); if (tr->ltimeout) ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode); else ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); } if (ret < 0) @@ -525,10 +544,9 @@ static int __io_timeout_prep(struct io_kiocb *req, if (WARN_ON_ONCE(req_has_async_data(req))) return -EFAULT; - if (io_alloc_async_data(req)) + data = io_uring_alloc_async_data(NULL, req); + if (!data) return -ENOMEM; - - data = req->async_data; data->req = req; data->flags = flags; @@ -572,7 +590,7 @@ int io_timeout(struct io_kiocb *req, unsigned int issue_flags) struct list_head *entry; u32 tail, off = timeout->off; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); /* * sqe->off holds how many events that need to occur for this @@ -611,7 +629,7 @@ add: list_add(&timeout->list, entry); data->timer.function = io_timeout_fn; hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); return IOU_ISSUE_SKIP_COMPLETE; } @@ -620,7 +638,7 @@ void io_queue_linked_timeout(struct io_kiocb *req) struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout); struct io_ring_ctx *ctx = req->ctx; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); /* * If the back reference is NULL, then our linked request finished * before we got a chance to setup the timer @@ -633,7 +651,7 @@ void io_queue_linked_timeout(struct io_kiocb *req) data->mode); list_add_tail(&timeout->list, &ctx->ltimeout_list); } - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); /* drop submission reference */ io_put_req(req); } @@ -661,22 +679,22 @@ __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct io_uring_task *tctx bool cancel_all) { struct io_timeout *timeout, *tmp; - int canceled = 0; + LIST_HEAD(list); /* * completion_lock is needed for io_match_task(). Take it before * timeout_lockfirst to keep locking ordering. */ spin_lock(&ctx->completion_lock); - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); list_for_each_entry_safe(timeout, tmp, &ctx->timeout_list, list) { struct io_kiocb *req = cmd_to_io_kiocb(timeout); - if (io_match_task(req, tctx, cancel_all) && - io_kill_timeout(req, -ECANCELED)) - canceled++; + if (io_match_task(req, tctx, cancel_all)) + io_kill_timeout(req, &list); } - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); spin_unlock(&ctx->completion_lock); - return canceled != 0; + + return io_flush_killed_timeouts(&list, -ECANCELED); } diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index af842e9b4eb9..1f6a82128b47 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -16,26 +16,15 @@ #include "rsrc.h" #include "uring_cmd.h" -static struct uring_cache *io_uring_async_get(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - struct uring_cache *cache; - - cache = io_alloc_cache_get(&ctx->uring_cache); - if (cache) { - req->flags |= REQ_F_ASYNC_DATA; - req->async_data = cache; - return cache; - } - if (!io_alloc_async_data(req)) - return req->async_data; - return NULL; -} - static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - struct uring_cache *cache = req->async_data; + struct io_uring_cmd_data *cache = req->async_data; + + if (cache->op_data) { + kfree(cache->op_data); + cache->op_data = NULL; + } if (issue_flags & IO_URING_F_UNLOCKED) return; @@ -121,7 +110,7 @@ static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts) struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); unsigned int flags = IO_URING_F_COMPLETE_DEFER; - if (current->flags & (PF_EXITING | PF_KTHREAD)) + if (io_should_terminate_tw()) flags |= IO_URING_F_TASK_DEAD; /* task_work executor checks the deffered list completion */ @@ -183,11 +172,12 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - struct uring_cache *cache; + struct io_uring_cmd_data *cache; - cache = io_uring_async_get(req); - if (unlikely(!cache)) + cache = io_uring_alloc_async_data(&req->ctx->uring_cache, req); + if (!cache) return -ENOMEM; + cache->op_data = NULL; if (!(req->flags & REQ_F_FORCE_ASYNC)) { /* defer memcpy until we need it */ @@ -195,8 +185,8 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req, return 0; } - memcpy(req->async_data, sqe, uring_sqe_size(req->ctx)); - ioucmd->sqe = req->async_data; + memcpy(cache->sqes, sqe, uring_sqe_size(req->ctx)); + ioucmd->sqe = cache->sqes; return 0; } @@ -260,10 +250,10 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) ret = file->f_op->uring_cmd(ioucmd, issue_flags); if (ret == -EAGAIN) { - struct uring_cache *cache = req->async_data; + struct io_uring_cmd_data *cache = req->async_data; if (ioucmd->sqe != (void *) cache) - memcpy(cache, ioucmd->sqe, uring_sqe_size(req->ctx)); + memcpy(cache->sqes, ioucmd->sqe, uring_sqe_size(req->ctx)); return -EAGAIN; } else if (ret == -EIOCBQUEUED) { return -EIOCBQUEUED; @@ -353,7 +343,7 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) if (!prot || !prot->ioctl) return -EOPNOTSUPP; - switch (cmd->sqe->cmd_op) { + switch (cmd->cmd_op) { case SOCKET_URING_OP_SIOCINQ: ret = prot->ioctl(sk, SIOCINQ, &arg); if (ret) diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h index 7dba0f1efc58..f6837ee0955b 100644 --- a/io_uring/uring_cmd.h +++ b/io_uring/uring_cmd.h @@ -1,9 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -struct uring_cache { - struct io_uring_sqe sqes[2]; -}; - int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags); int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); diff --git a/io_uring/waitid.c b/io_uring/waitid.c index daef5dd644f0..853e97a7b0ec 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -303,10 +303,10 @@ int io_waitid(struct io_kiocb *req, unsigned int issue_flags) struct io_waitid_async *iwa; int ret; - if (io_alloc_async_data(req)) + iwa = io_uring_alloc_async_data(NULL, req); + if (!iwa) return -ENOMEM; - iwa = req->async_data; iwa->req = req; ret = kernel_waitid_prepare(&iwa->wo, iw->which, iw->upid, &iw->info, diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 54318e0b4557..15b17e86e198 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -73,7 +73,7 @@ int ipc_mni = IPCMNI; int ipc_mni_shift = IPCMNI_SHIFT; int ipc_min_cycle = RADIX_TREE_MAP_SIZE; -static struct ctl_table ipc_sysctls[] = { +static const struct ctl_table ipc_sysctls[] = { { .procname = "shmmax", .data = &init_ipc_ns.shm_ctlmax, diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index b70dc2ff22d8..0dd12e1c9f53 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -20,7 +20,7 @@ static int msg_max_limit_max = HARD_MSGMAX; static int msg_maxsize_limit_min = MIN_MSGSIZEMAX; static int msg_maxsize_limit_max = HARD_MSGSIZEMAX; -static struct ctl_table mq_sysctls[] = { +static const struct ctl_table mq_sysctls[] = { { .procname = "queues_max", .data = &init_ipc_ns.mq_queues_max, diff --git a/ipc/util.c b/ipc/util.c index 05cb9de66735..cae60f11d9c2 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -615,12 +615,11 @@ void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out) } /** - * ipc_obtain_object_idr + * ipc_obtain_object_idr - Look for an id in the ipc ids idr and + * return associated ipc object. * @ids: ipc identifier set * @id: ipc id to look for * - * Look for an id in the ipc ids idr and return associated ipc object. - * * Call inside the RCU critical section. * The ipc object is *not* locked on exit. */ @@ -637,13 +636,11 @@ struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id) } /** - * ipc_obtain_object_check + * ipc_obtain_object_check - Similar to ipc_obtain_object_idr() but + * also checks the ipc object sequence number. * @ids: ipc identifier set * @id: ipc id to look for * - * Similar to ipc_obtain_object_idr() but also checks the ipc object - * sequence number. - * * Call inside the RCU critical section. * The ipc object is *not* locked on exit. */ diff --git a/kernel/acct.c b/kernel/acct.c index 179848ad33e9..31222e8cd534 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -76,7 +76,7 @@ static int acct_parm[3] = {4, 2, 30}; #define ACCT_TIMEOUT (acct_parm[2]) /* foo second timeout between checks */ #ifdef CONFIG_SYSCTL -static struct ctl_table kern_acct_table[] = { +static const struct ctl_table kern_acct_table[] = { { .procname = "acct", .data = &acct_parm, diff --git a/kernel/audit.c b/kernel/audit.c index 6a95a6077953..5f5bf85bcc90 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1221,8 +1221,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; struct audit_sig_info *sig_data; - char *ctx = NULL; - u32 len; + struct lsm_context lsmctx = { NULL, 0, 0 }; err = audit_netlink_ok(skb, msg_type); if (err) @@ -1472,27 +1471,28 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, break; } case AUDIT_SIGNAL_INFO: - len = 0; if (lsmprop_is_set(&audit_sig_lsm)) { - err = security_lsmprop_to_secctx(&audit_sig_lsm, &ctx, - &len); - if (err) + err = security_lsmprop_to_secctx(&audit_sig_lsm, + &lsmctx); + if (err < 0) return err; } - sig_data = kmalloc(struct_size(sig_data, ctx, len), GFP_KERNEL); + sig_data = kmalloc(struct_size(sig_data, ctx, lsmctx.len), + GFP_KERNEL); if (!sig_data) { if (lsmprop_is_set(&audit_sig_lsm)) - security_release_secctx(ctx, len); + security_release_secctx(&lsmctx); return -ENOMEM; } sig_data->uid = from_kuid(&init_user_ns, audit_sig_uid); sig_data->pid = audit_sig_pid; if (lsmprop_is_set(&audit_sig_lsm)) { - memcpy(sig_data->ctx, ctx, len); - security_release_secctx(ctx, len); + memcpy(sig_data->ctx, lsmctx.context, lsmctx.len); + security_release_secctx(&lsmctx); } audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, - sig_data, struct_size(sig_data, ctx, len)); + sig_data, struct_size(sig_data, ctx, + lsmctx.len)); kfree(sig_data); break; case AUDIT_TTY_GET: { @@ -2180,23 +2180,22 @@ void audit_log_key(struct audit_buffer *ab, char *key) int audit_log_task_context(struct audit_buffer *ab) { struct lsm_prop prop; - char *ctx = NULL; - unsigned len; + struct lsm_context ctx; int error; security_current_getlsmprop_subj(&prop); if (!lsmprop_is_set(&prop)) return 0; - error = security_lsmprop_to_secctx(&prop, &ctx, &len); - if (error) { + error = security_lsmprop_to_secctx(&prop, &ctx); + if (error < 0) { if (error != -EINVAL) goto error_path; return 0; } - audit_log_format(ab, " subj=%s", ctx); - security_release_secctx(ctx, len); + audit_log_format(ab, " subj=%s", ctx.context); + security_release_secctx(&ctx); return 0; error_path: diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index bceb9f58a09e..e3f42018ed46 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1319,13 +1319,20 @@ int audit_compare_dname_path(const struct qstr *dname, const char *path, int par if (pathlen < dlen) return 1; - parentlen = parentlen == AUDIT_NAME_FULL ? parent_len(path) : parentlen; - if (pathlen - parentlen != dlen) - return 1; + if (parentlen == AUDIT_NAME_FULL) + parentlen = parent_len(path); p = path + parentlen; - return strncmp(p, dname->name, dlen); + /* handle trailing slashes */ + pathlen -= parentlen; + while (p[pathlen - 1] == '/') + pathlen--; + + if (pathlen != dlen) + return 1; + + return memcmp(p, dname->name, dlen); } int audit_filter(int msgtype, unsigned int listtype) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 561d96affe9f..9c853cde9abe 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1098,8 +1098,7 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid, char *comm) { struct audit_buffer *ab; - char *ctx = NULL; - u32 len; + struct lsm_context ctx; int rc = 0; ab = audit_log_start(context, GFP_KERNEL, AUDIT_OBJ_PID); @@ -1110,12 +1109,12 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid, from_kuid(&init_user_ns, auid), from_kuid(&init_user_ns, uid), sessionid); if (lsmprop_is_set(prop)) { - if (security_lsmprop_to_secctx(prop, &ctx, &len)) { + if (security_lsmprop_to_secctx(prop, &ctx) < 0) { audit_log_format(ab, " obj=(none)"); rc = 1; } else { - audit_log_format(ab, " obj=%s", ctx); - security_release_secctx(ctx, len); + audit_log_format(ab, " obj=%s", ctx.context); + security_release_secctx(&ctx); } } audit_log_format(ab, " ocomm="); @@ -1393,15 +1392,14 @@ static void show_special(struct audit_context *context, int *call_panic) from_kgid(&init_user_ns, context->ipc.gid), context->ipc.mode); if (lsmprop_is_set(&context->ipc.oprop)) { - char *ctx = NULL; - u32 len; + struct lsm_context lsmctx; if (security_lsmprop_to_secctx(&context->ipc.oprop, - &ctx, &len)) { + &lsmctx) < 0) { *call_panic = 1; } else { - audit_log_format(ab, " obj=%s", ctx); - security_release_secctx(ctx, len); + audit_log_format(ab, " obj=%s", lsmctx.context); + security_release_secctx(&lsmctx); } } if (context->ipc.has_perm) { @@ -1560,15 +1558,14 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, MAJOR(n->rdev), MINOR(n->rdev)); if (lsmprop_is_set(&n->oprop)) { - char *ctx = NULL; - u32 len; + struct lsm_context ctx; - if (security_lsmprop_to_secctx(&n->oprop, &ctx, &len)) { + if (security_lsmprop_to_secctx(&n->oprop, &ctx) < 0) { if (call_panic) *call_panic = 2; } else { - audit_log_format(ab, " obj=%s", ctx); - security_release_secctx(ctx, len); + audit_log_format(ab, " obj=%s", ctx.context); + security_release_secctx(&ctx); } } diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 945a5680f6a5..870aeb51d70a 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -138,7 +138,11 @@ static struct bpf_map *arena_map_alloc(union bpf_attr *attr) INIT_LIST_HEAD(&arena->vma_list); bpf_map_init_from_attr(&arena->map, attr); range_tree_init(&arena->rt); - range_tree_set(&arena->rt, 0, attr->max_entries); + err = range_tree_set(&arena->rt, 0, attr->max_entries); + if (err) { + bpf_map_area_free(arena); + goto err; + } mutex_init(&arena->lock); return &arena->map; @@ -218,7 +222,7 @@ static u64 arena_map_mem_usage(const struct bpf_map *map) struct vma_list { struct vm_area_struct *vma; struct list_head head; - atomic_t mmap_count; + refcount_t mmap_count; }; static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) @@ -228,7 +232,7 @@ static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) vml = kmalloc(sizeof(*vml), GFP_KERNEL); if (!vml) return -ENOMEM; - atomic_set(&vml->mmap_count, 1); + refcount_set(&vml->mmap_count, 1); vma->vm_private_data = vml; vml->vma = vma; list_add(&vml->head, &arena->vma_list); @@ -239,7 +243,7 @@ static void arena_vm_open(struct vm_area_struct *vma) { struct vma_list *vml = vma->vm_private_data; - atomic_inc(&vml->mmap_count); + refcount_inc(&vml->mmap_count); } static void arena_vm_close(struct vm_area_struct *vma) @@ -248,7 +252,7 @@ static void arena_vm_close(struct vm_area_struct *vma) struct bpf_arena *arena = container_of(map, struct bpf_arena, map); struct vma_list *vml = vma->vm_private_data; - if (!atomic_dec_and_test(&vml->mmap_count)) + if (!refcount_dec_and_test(&vml->mmap_count)) return; guard(mutex)(&arena->lock); /* update link list under lock */ @@ -257,8 +261,6 @@ static void arena_vm_close(struct vm_area_struct *vma) kfree(vml); } -#define MT_ENTRY ((void *)&arena_map_ops) /* unused. has to be valid pointer */ - static vm_fault_t arena_vm_fault(struct vm_fault *vmf) { struct bpf_map *map = vmf->vma->vm_file->private_data; @@ -443,7 +445,7 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt return 0; } - /* zeroing is needed, since alloc_pages_bulk_array() only fills in non-zero entries */ + /* zeroing is needed, since alloc_pages_bulk() only fills in non-zero entries */ pages = kvcalloc(page_cnt, sizeof(struct page *), GFP_KERNEL); if (!pages) return 0; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 6cdbb4c33d31..eb28c0f219ee 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -735,13 +735,13 @@ static long bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback u64 ret = 0; void *val; + cant_migrate(); + if (flags != 0) return -EINVAL; is_percpu = map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; array = container_of(map, struct bpf_array, map); - if (is_percpu) - migrate_disable(); for (i = 0; i < map->max_entries; i++) { if (is_percpu) val = this_cpu_ptr(array->pptrs[i]); @@ -756,8 +756,6 @@ static long bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback break; } - if (is_percpu) - migrate_enable(); return num_elems; } diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index 20f05de92e9c..d5dc65bb1755 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -15,22 +15,20 @@ static DEFINE_PER_CPU(int, bpf_cgrp_storage_busy); static void bpf_cgrp_storage_lock(void) { - migrate_disable(); + cant_migrate(); this_cpu_inc(bpf_cgrp_storage_busy); } static void bpf_cgrp_storage_unlock(void) { this_cpu_dec(bpf_cgrp_storage_busy); - migrate_enable(); } static bool bpf_cgrp_storage_trylock(void) { - migrate_disable(); + cant_migrate(); if (unlikely(this_cpu_inc_return(bpf_cgrp_storage_busy) != 1)) { this_cpu_dec(bpf_cgrp_storage_busy); - migrate_enable(); return false; } return true; @@ -47,17 +45,18 @@ void bpf_cgrp_storage_free(struct cgroup *cgroup) { struct bpf_local_storage *local_storage; + migrate_disable(); rcu_read_lock(); local_storage = rcu_dereference(cgroup->bpf_cgrp_storage); - if (!local_storage) { - rcu_read_unlock(); - return; - } + if (!local_storage) + goto out; bpf_cgrp_storage_lock(); bpf_local_storage_destroy(local_storage); bpf_cgrp_storage_unlock(); +out: rcu_read_unlock(); + migrate_enable(); } static struct bpf_local_storage_data * diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index a51c82dee1bd..15a3eb9b02d9 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -62,16 +62,17 @@ void bpf_inode_storage_free(struct inode *inode) if (!bsb) return; + migrate_disable(); rcu_read_lock(); local_storage = rcu_dereference(bsb->storage); - if (!local_storage) { - rcu_read_unlock(); - return; - } + if (!local_storage) + goto out; bpf_local_storage_destroy(local_storage); +out: rcu_read_unlock(); + migrate_enable(); } static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 7e6a0af0afc1..fa56c30833ff 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -81,9 +81,7 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, return NULL; if (smap->bpf_ma) { - migrate_disable(); selem = bpf_mem_cache_alloc_flags(&smap->selem_ma, gfp_flags); - migrate_enable(); if (selem) /* Keep the original bpf_map_kzalloc behavior * before started using the bpf_mem_cache_alloc. @@ -174,17 +172,14 @@ static void bpf_local_storage_free(struct bpf_local_storage *local_storage, return; } - if (smap) { - migrate_disable(); + if (smap) bpf_mem_cache_free(&smap->storage_ma, local_storage); - migrate_enable(); - } else { + else /* smap could be NULL if the selem that triggered * this 'local_storage' creation had been long gone. * In this case, directly do call_rcu(). */ call_rcu(&local_storage->rcu, bpf_local_storage_free_rcu); - } } /* rcu tasks trace callback for bpf_ma == false */ @@ -217,7 +212,10 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu) selem = container_of(rcu, struct bpf_local_storage_elem, rcu); /* The bpf_local_storage_map_free will wait for rcu_barrier */ smap = rcu_dereference_check(SDATA(selem)->smap, 1); + + migrate_disable(); bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); + migrate_enable(); bpf_mem_cache_raw_free(selem); } @@ -256,9 +254,7 @@ void bpf_selem_free(struct bpf_local_storage_elem *selem, * bpf_mem_cache_free will be able to reuse selem * immediately. */ - migrate_disable(); bpf_mem_cache_free(&smap->selem_ma, selem); - migrate_enable(); return; } @@ -497,15 +493,11 @@ int bpf_local_storage_alloc(void *owner, if (err) return err; - if (smap->bpf_ma) { - migrate_disable(); + if (smap->bpf_ma) storage = bpf_mem_cache_alloc_flags(&smap->storage_ma, gfp_flags); - migrate_enable(); - } else { + else storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), gfp_flags | __GFP_NOWARN); - } - if (!storage) { err = -ENOMEM; goto uncharge; @@ -841,8 +833,12 @@ bpf_local_storage_map_alloc(union bpf_attr *attr, smap->elem_size = offsetof(struct bpf_local_storage_elem, sdata.data[attr->value_size]); - smap->bpf_ma = bpf_ma; - if (bpf_ma) { + /* In PREEMPT_RT, kmalloc(GFP_ATOMIC) is still not safe in non + * preemptible context. Thus, enforce all storages to use + * bpf_mem_alloc when CONFIG_PREEMPT_RT is enabled. + */ + smap->bpf_ma = IS_ENABLED(CONFIG_PREEMPT_RT) ? true : bpf_ma; + if (smap->bpf_ma) { err = bpf_mem_alloc_init(&smap->selem_ma, smap->elem_size, false); if (err) goto free_smap; @@ -898,15 +894,11 @@ void bpf_local_storage_map_free(struct bpf_map *map, while ((selem = hlist_entry_safe( rcu_dereference_raw(hlist_first_rcu(&b->list)), struct bpf_local_storage_elem, map_node))) { - if (busy_counter) { - migrate_disable(); + if (busy_counter) this_cpu_inc(*busy_counter); - } bpf_selem_unlink(selem, true); - if (busy_counter) { + if (busy_counter) this_cpu_dec(*busy_counter); - migrate_enable(); - } cond_resched_rcu(); } rcu_read_unlock(); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 606efe32485a..040fb1cd840b 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -310,6 +310,20 @@ void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) kfree(arg_info); } +static bool is_module_member(const struct btf *btf, u32 id) +{ + const struct btf_type *t; + + t = btf_type_resolve_ptr(btf, id, NULL); + if (!t) + return false; + + if (!__btf_type_is_struct(t) && !btf_type_is_fwd(t)) + return false; + + return !strcmp(btf_name_by_offset(btf, t->name_off), "module"); +} + int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log) @@ -389,6 +403,13 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, goto errout; } + if (!st_ops_ids[IDX_MODULE_ID] && is_module_member(btf, member->type)) { + pr_warn("'struct module' btf id not found. Is CONFIG_MODULES enabled? bpf_struct_ops '%s' needs module support.\n", + st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index bf7fa15fdcc6..1109475953c0 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -24,22 +24,20 @@ static DEFINE_PER_CPU(int, bpf_task_storage_busy); static void bpf_task_storage_lock(void) { - migrate_disable(); + cant_migrate(); this_cpu_inc(bpf_task_storage_busy); } static void bpf_task_storage_unlock(void) { this_cpu_dec(bpf_task_storage_busy); - migrate_enable(); } static bool bpf_task_storage_trylock(void) { - migrate_disable(); + cant_migrate(); if (unlikely(this_cpu_inc_return(bpf_task_storage_busy) != 1)) { this_cpu_dec(bpf_task_storage_busy); - migrate_enable(); return false; } return true; @@ -72,18 +70,19 @@ void bpf_task_storage_free(struct task_struct *task) { struct bpf_local_storage *local_storage; + migrate_disable(); rcu_read_lock(); local_storage = rcu_dereference(task->bpf_storage); - if (!local_storage) { - rcu_read_unlock(); - return; - } + if (!local_storage) + goto out; bpf_task_storage_lock(); bpf_local_storage_destroy(local_storage); bpf_task_storage_unlock(); +out: rcu_read_unlock(); + migrate_enable(); } static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index e5a5f023cedd..9de6acddd479 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -498,11 +498,6 @@ bool btf_type_is_void(const struct btf_type *t) return t == &btf_void; } -static bool btf_type_is_fwd(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; -} - static bool btf_type_is_datasec(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; @@ -7887,14 +7882,9 @@ struct btf *btf_get_by_fd(int fd) struct btf *btf; CLASS(fd, f)(fd); - if (fd_empty(f)) - return ERR_PTR(-EBADF); - - if (fd_file(f)->f_op != &btf_fops) - return ERR_PTR(-EINVAL); - - btf = fd_file(f)->private_data; - refcount_inc(&btf->refcnt); + btf = __btf_get_by_fd(f); + if (!IS_ERR(btf)) + refcount_inc(&btf->refcnt); return btf; } @@ -8011,17 +8001,6 @@ struct btf_module { static LIST_HEAD(btf_modules); static DEFINE_MUTEX(btf_module_mutex); -static ssize_t -btf_module_read(struct file *file, struct kobject *kobj, - struct bin_attribute *bin_attr, - char *buf, loff_t off, size_t len) -{ - const struct btf *btf = bin_attr->private; - - memcpy(buf, btf->data + off, len); - return len; -} - static void purge_cand_cache(struct btf *btf); static int btf_module_notify(struct notifier_block *nb, unsigned long op, @@ -8082,8 +8061,8 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, attr->attr.name = btf->name; attr->attr.mode = 0444; attr->size = btf->data_size; - attr->private = btf; - attr->read = btf_module_read; + attr->private = btf->data; + attr->read_new = sysfs_bin_attr_simple_read; err = sysfs_create_bin_file(btf_kobj, attr); if (err) { diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index a2f46785ac3b..774accbd4a22 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -190,7 +190,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, int err; rxq.dev = xdpf->dev_rx; - rxq.mem = xdpf->mem; + rxq.mem.type = xdpf->mem_type; /* TODO: report queue_index to xdp_rxq_info */ xdp_convert_frame_to_buff(xdpf, &xdp); diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index 33c473d676a5..cfa1c18e3a48 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -91,9 +91,7 @@ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask) if (!refcount_dec_and_test(&cpumask->usage)) return; - migrate_disable(); bpf_mem_cache_free_rcu(&bpf_cpumask_ma, cpumask); - migrate_enable(); } __bpf_kfunc void bpf_cpumask_release_dtor(void *cpumask) diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 3aa002a47a96..482d284a1553 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -678,7 +678,7 @@ int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { int err; @@ -701,7 +701,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { struct sk_buff *nskb; int err; @@ -720,8 +720,8 @@ static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, } int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog, struct bpf_map *map, - bool exclude_ingress) + const struct bpf_prog *xdp_prog, + struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3ec941a0ea41..4a9eeb7aef85 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -824,13 +824,14 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { hlist_nulls_del_rcu(&l->hash_node); - check_and_free_fields(htab, l); bpf_map_dec_elem_count(&htab->map); break; } htab_unlock_bucket(htab, b, tgt_l->hash, flags); + if (l == tgt_l) + check_and_free_fields(htab, l); return l == tgt_l; } @@ -897,11 +898,9 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { check_and_free_fields(htab, l); - migrate_disable(); if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr); bpf_mem_cache_free(&htab->ma, l); - migrate_enable(); } static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) @@ -1502,10 +1501,9 @@ static void delete_all_elements(struct bpf_htab *htab) { int i; - /* It's called from a worker thread, so disable migration here, - * since bpf_mem_cache_free() relies on that. + /* It's called from a worker thread and migration has been disabled, + * therefore, it is OK to invoke bpf_mem_cache_free() directly. */ - migrate_disable(); for (i = 0; i < htab->n_buckets; i++) { struct hlist_nulls_head *head = select_bucket(htab, i); struct hlist_nulls_node *n; @@ -1517,7 +1515,6 @@ static void delete_all_elements(struct bpf_htab *htab) } cond_resched(); } - migrate_enable(); } static void htab_free_malloced_timers_and_wq(struct bpf_htab *htab) @@ -1638,41 +1635,44 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, l = lookup_elem_raw(head, hash, key, key_size); if (!l) { ret = -ENOENT; - } else { - if (is_percpu) { - u32 roundup_value_size = round_up(map->value_size, 8); - void __percpu *pptr; - int off = 0, cpu; - - pptr = htab_elem_get_ptr(l, key_size); - for_each_possible_cpu(cpu) { - copy_map_value_long(&htab->map, value + off, per_cpu_ptr(pptr, cpu)); - check_and_init_map_value(&htab->map, value + off); - off += roundup_value_size; - } - } else { - u32 roundup_key_size = round_up(map->key_size, 8); - - if (flags & BPF_F_LOCK) - copy_map_value_locked(map, value, l->key + - roundup_key_size, - true); - else - copy_map_value(map, value, l->key + - roundup_key_size); - /* Zeroing special fields in the temp buffer */ - check_and_init_map_value(map, value); - } - - hlist_nulls_del_rcu(&l->hash_node); - if (!is_lru_map) - free_htab_elem(htab, l); + goto out_unlock; } + if (is_percpu) { + u32 roundup_value_size = round_up(map->value_size, 8); + void __percpu *pptr; + int off = 0, cpu; + + pptr = htab_elem_get_ptr(l, key_size); + for_each_possible_cpu(cpu) { + copy_map_value_long(&htab->map, value + off, per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(&htab->map, value + off); + off += roundup_value_size; + } + } else { + u32 roundup_key_size = round_up(map->key_size, 8); + + if (flags & BPF_F_LOCK) + copy_map_value_locked(map, value, l->key + + roundup_key_size, + true); + else + copy_map_value(map, value, l->key + + roundup_key_size); + /* Zeroing special fields in the temp buffer */ + check_and_init_map_value(map, value); + } + hlist_nulls_del_rcu(&l->hash_node); + +out_unlock: htab_unlock_bucket(htab, b, hash, bflags); - if (is_lru_map && l) - htab_lru_push_free(htab, l); + if (l) { + if (is_lru_map) + htab_lru_push_free(htab, l); + else + free_htab_elem(htab, l); + } return ret; } @@ -2208,17 +2208,18 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_ bool is_percpu; u64 ret = 0; + cant_migrate(); + if (flags != 0) return -EINVAL; is_percpu = htab_is_percpu(htab); roundup_key_size = round_up(map->key_size, 8); - /* disable migration so percpu value prepared here will be the - * same as the one seen by the bpf program with bpf_map_lookup_elem(). + /* migration has been disabled, so percpu value prepared here will be + * the same as the one seen by the bpf program with + * bpf_map_lookup_elem(). */ - if (is_percpu) - migrate_disable(); for (i = 0; i < htab->n_buckets; i++) { b = &htab->buckets[i]; rcu_read_lock(); @@ -2244,8 +2245,6 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_ rcu_read_unlock(); } out: - if (is_percpu) - migrate_enable(); return num_elems; } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 751c150f9e1c..f27ce162427a 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1593,10 +1593,24 @@ void bpf_timer_cancel_and_free(void *val) * To avoid these issues, punt to workqueue context when we are in a * timer callback. */ - if (this_cpu_read(hrtimer_running)) + if (this_cpu_read(hrtimer_running)) { queue_work(system_unbound_wq, &t->cb.delete_work); - else + return; + } + + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + /* If the timer is running on other CPU, also use a kworker to + * wait for the completion of the timer instead of trying to + * acquire a sleepable lock in hrtimer_cancel() to wait for its + * completion. + */ + if (hrtimer_try_to_cancel(&t->timer) >= 0) + kfree_rcu(t, cb.rcu); + else + queue_work(system_unbound_wq, &t->cb.delete_work); + } else { bpf_timer_delete_work(&t->cb.delete_work); + } } /* This function is called by map_delete/update_elem for individual element and @@ -2066,9 +2080,7 @@ unlock: /* The contained type can also have resources, including a * bpf_list_head which needs to be freed. */ - migrate_disable(); __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false); - migrate_enable(); } } @@ -2105,9 +2117,7 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root, obj -= field->graph_root.node_offset; - migrate_disable(); __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false); - migrate_enable(); } } @@ -3057,6 +3067,21 @@ __bpf_kfunc int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void __user return ret + 1; } +/* Keep unsinged long in prototype so that kfunc is usable when emitted to + * vmlinux.h in BPF programs directly, but note that while in BPF prog, the + * unsigned long always points to 8-byte region on stack, the kernel may only + * read and write the 4-bytes on 32-bit. + */ +__bpf_kfunc void bpf_local_irq_save(unsigned long *flags__irq_flag) +{ + local_irq_save(*flags__irq_flag); +} + +__bpf_kfunc void bpf_local_irq_restore(unsigned long *flags__irq_flag) +{ + local_irq_restore(*flags__irq_flag); +} + __bpf_kfunc_end_defs(); BTF_KFUNCS_START(generic_btf_ids) @@ -3089,7 +3114,9 @@ BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_from_vpid, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_throw) +#ifdef CONFIG_BPF_EVENTS BTF_ID_FLAGS(func, bpf_send_signal_task, KF_TRUSTED_ARGS) +#endif BTF_KFUNCS_END(generic_btf_ids) static const struct btf_kfunc_id_set generic_kfunc_set = { @@ -3135,7 +3162,9 @@ BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) BTF_ID_FLAGS(func, bpf_dynptr_size) BTF_ID_FLAGS(func, bpf_dynptr_clone) +#ifdef CONFIG_NET BTF_ID_FLAGS(func, bpf_modify_return_test_tp) +#endif BTF_ID_FLAGS(func, bpf_wq_init) BTF_ID_FLAGS(func, bpf_wq_set_callback_impl) BTF_ID_FLAGS(func, bpf_wq_start) @@ -3149,6 +3178,8 @@ BTF_ID_FLAGS(func, bpf_get_kmem_cache) BTF_ID_FLAGS(func, bpf_iter_kmem_cache_new, KF_ITER_NEW | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_iter_kmem_cache_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_iter_kmem_cache_destroy, KF_ITER_DESTROY | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_local_irq_save) +BTF_ID_FLAGS(func, bpf_local_irq_restore) BTF_KFUNCS_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 4a858fdb6476..38050f4ee400 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -537,6 +537,7 @@ static char slot_type_char[] = { [STACK_ZERO] = '0', [STACK_DYNPTR] = 'd', [STACK_ITER] = 'i', + [STACK_IRQ_FLAG] = 'f' }; static void print_liveness(struct bpf_verifier_env *env, @@ -753,9 +754,10 @@ static void print_reg_state(struct bpf_verifier_env *env, verbose(env, ")"); } -void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, - bool print_all) +void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, + u32 frameno, bool print_all) { + const struct bpf_func_state *state = vstate->frame[frameno]; const struct bpf_reg_state *reg; int i; @@ -843,11 +845,11 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_st break; } } - if (state->acquired_refs && state->refs[0].id) { - verbose(env, " refs=%d", state->refs[0].id); - for (i = 1; i < state->acquired_refs; i++) - if (state->refs[i].id) - verbose(env, ",%d", state->refs[i].id); + if (vstate->acquired_refs && vstate->refs[0].id) { + verbose(env, " refs=%d", vstate->refs[0].id); + for (i = 1; i < vstate->acquired_refs; i++) + if (vstate->refs[i].id) + verbose(env, ",%d", vstate->refs[i].id); } if (state->in_callback_fn) verbose(env, " cb"); @@ -864,7 +866,8 @@ static inline u32 vlog_alignment(u32 pos) BPF_LOG_MIN_ALIGNMENT) - pos - 1; } -void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) +void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, + u32 frameno) { if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) { /* remove new line character */ @@ -873,5 +876,5 @@ void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state } else { verbose(env, "%d:", env->insn_idx); } - print_verifier_state(env, state, false); + print_verifier_state(env, vstate, frameno, false); } diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index f8bc1e096182..e8a772e64324 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -289,16 +289,11 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) } static struct lpm_trie_node *lpm_trie_node_alloc(struct lpm_trie *trie, - const void *value, - bool disable_migration) + const void *value) { struct lpm_trie_node *node; - if (disable_migration) - migrate_disable(); node = bpf_mem_cache_alloc(&trie->ma); - if (disable_migration) - migrate_enable(); if (!node) return NULL; @@ -342,10 +337,8 @@ static long trie_update_elem(struct bpf_map *map, if (key->prefixlen > trie->max_prefixlen) return -EINVAL; - /* Allocate and fill a new node. Need to disable migration before - * invoking bpf_mem_cache_alloc(). - */ - new_node = lpm_trie_node_alloc(trie, value, true); + /* Allocate and fill a new node */ + new_node = lpm_trie_node_alloc(trie, value); if (!new_node) return -ENOMEM; @@ -425,8 +418,7 @@ static long trie_update_elem(struct bpf_map *map, goto out; } - /* migration is disabled within the locked scope */ - im_node = lpm_trie_node_alloc(trie, NULL, false); + im_node = lpm_trie_node_alloc(trie, NULL); if (!im_node) { trie->n_entries--; ret = -ENOMEM; @@ -452,11 +444,9 @@ static long trie_update_elem(struct bpf_map *map, out: raw_spin_unlock_irqrestore(&trie->lock, irq_flags); - migrate_disable(); if (ret) bpf_mem_cache_free(&trie->ma, new_node); bpf_mem_cache_free_rcu(&trie->ma, free_node); - migrate_enable(); return ret; } @@ -555,10 +545,8 @@ static long trie_delete_elem(struct bpf_map *map, void *_key) out: raw_spin_unlock_irqrestore(&trie->lock, irq_flags); - migrate_disable(); bpf_mem_cache_free_rcu(&trie->ma, free_parent); bpf_mem_cache_free_rcu(&trie->ma, free_node); - migrate_enable(); return ret; } diff --git a/kernel/bpf/range_tree.c b/kernel/bpf/range_tree.c index 5bdf9aadca3a..37b80a23ae1a 100644 --- a/kernel/bpf/range_tree.c +++ b/kernel/bpf/range_tree.c @@ -259,9 +259,7 @@ void range_tree_destroy(struct range_tree *rt) while ((rn = range_it_iter_first(rt, 0, -1U))) { range_it_remove(rn, rt); - migrate_disable(); bpf_mem_free(&bpf_global_ma, rn); - migrate_enable(); } } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5684e8ce132d..c420edbfb7c8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -796,11 +796,9 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) if (!btf_is_kernel(field->kptr.btf)) { pointee_struct_meta = btf_find_struct_meta(field->kptr.btf, field->kptr.btf_id); - migrate_disable(); __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? pointee_struct_meta->record : NULL, fields[i].type == BPF_KPTR_PERCPU); - migrate_enable(); } else { field->kptr.dtor(xchgd_field); } @@ -835,8 +833,14 @@ static void bpf_map_free(struct bpf_map *map) struct btf_record *rec = map->record; struct btf *btf = map->btf; - /* implementation dependent freeing */ + /* implementation dependent freeing. Disabling migration to simplify + * the free of values or special fields allocated from bpf memory + * allocator. + */ + migrate_disable(); map->ops->map_free(map); + migrate_enable(); + /* Delay freeing of btf_record for maps, as map_free * callback usually needs access to them. It is better to do it here * than require each callback to do the free itself manually. @@ -2730,7 +2734,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd +#define BPF_PROG_LOAD_LAST_FIELD fd_array_cnt static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { @@ -6124,7 +6128,7 @@ static int bpf_unpriv_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table bpf_syscall_table[] = { +static const struct ctl_table bpf_syscall_table[] = { { .procname = "unprivileged_bpf_disabled", .data = &sysctl_unprivileged_bpf_disabled, diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c index fedb54c94cdb..81d6cf90584a 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -12,24 +12,16 @@ extern char __start_BTF[]; extern char __stop_BTF[]; -static ssize_t -btf_vmlinux_read(struct file *file, struct kobject *kobj, - struct bin_attribute *bin_attr, - char *buf, loff_t off, size_t len) -{ - memcpy(buf, __start_BTF + off, len); - return len; -} - static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = { .attr = { .name = "vmlinux", .mode = 0444, }, - .read = btf_vmlinux_read, + .read_new = sysfs_bin_attr_simple_read, }; struct kobject *btf_kobj; static int __init btf_vmlinux_init(void) { + bin_attr_btf_vmlinux.private = __start_BTF; bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; if (bin_attr_btf_vmlinux.size == 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f7f892a52a37..9971c03adfd5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -196,7 +196,8 @@ struct bpf_verifier_stack_elem { #define BPF_PRIV_STACK_MIN_SIZE 64 -static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx); +static int acquire_reference(struct bpf_verifier_env *env, int insn_idx); +static int release_reference_nomark(struct bpf_verifier_state *state, int ref_obj_id); static int release_reference(struct bpf_verifier_env *env, int ref_obj_id); static void invalidate_non_owning_refs(struct bpf_verifier_env *env); static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env); @@ -286,6 +287,7 @@ struct bpf_call_arg_meta { u32 ret_btf_id; u32 subprogno; struct btf_field *kptr_field; + s64 const_map_key; }; struct bpf_kfunc_call_arg_meta { @@ -641,6 +643,11 @@ static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, return stack_slot_obj_get_spi(env, reg, "iter", nr_slots); } +static int irq_flag_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + return stack_slot_obj_get_spi(env, reg, "irq_flag", 1); +} + static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) { switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { @@ -752,7 +759,7 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ if (clone_ref_obj_id) id = clone_ref_obj_id; else - id = acquire_reference_state(env, insn_idx); + id = acquire_reference(env, insn_idx); if (id < 0) return id; @@ -1014,7 +1021,7 @@ static int mark_stack_slots_iter(struct bpf_verifier_env *env, if (spi < 0) return spi; - id = acquire_reference_state(env, insn_idx); + id = acquire_reference(env, insn_idx); if (id < 0) return id; @@ -1136,10 +1143,136 @@ static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_s return 0; } +static int acquire_irq_state(struct bpf_verifier_env *env, int insn_idx); +static int release_irq_state(struct bpf_verifier_state *state, int id); + +static int mark_stack_slot_irq_flag(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, + struct bpf_reg_state *reg, int insn_idx) +{ + struct bpf_func_state *state = func(env, reg); + struct bpf_stack_state *slot; + struct bpf_reg_state *st; + int spi, i, id; + + spi = irq_flag_get_spi(env, reg); + if (spi < 0) + return spi; + + id = acquire_irq_state(env, insn_idx); + if (id < 0) + return id; + + slot = &state->stack[spi]; + st = &slot->spilled_ptr; + + __mark_reg_known_zero(st); + st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ + st->live |= REG_LIVE_WRITTEN; + st->ref_obj_id = id; + + for (i = 0; i < BPF_REG_SIZE; i++) + slot->slot_type[i] = STACK_IRQ_FLAG; + + mark_stack_slot_scratched(env, spi); + return 0; +} + +static int unmark_stack_slot_irq_flag(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + struct bpf_stack_state *slot; + struct bpf_reg_state *st; + int spi, i, err; + + spi = irq_flag_get_spi(env, reg); + if (spi < 0) + return spi; + + slot = &state->stack[spi]; + st = &slot->spilled_ptr; + + err = release_irq_state(env->cur_state, st->ref_obj_id); + WARN_ON_ONCE(err && err != -EACCES); + if (err) { + int insn_idx = 0; + + for (int i = 0; i < env->cur_state->acquired_refs; i++) { + if (env->cur_state->refs[i].id == env->cur_state->active_irq_id) { + insn_idx = env->cur_state->refs[i].insn_idx; + break; + } + } + + verbose(env, "cannot restore irq state out of order, expected id=%d acquired at insn_idx=%d\n", + env->cur_state->active_irq_id, insn_idx); + return err; + } + + __mark_reg_not_init(env, st); + + /* see unmark_stack_slots_dynptr() for why we need to set REG_LIVE_WRITTEN */ + st->live |= REG_LIVE_WRITTEN; + + for (i = 0; i < BPF_REG_SIZE; i++) + slot->slot_type[i] = STACK_INVALID; + + mark_stack_slot_scratched(env, spi); + return 0; +} + +static bool is_irq_flag_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + struct bpf_stack_state *slot; + int spi, i; + + /* For -ERANGE (i.e. spi not falling into allocated stack slots), we + * will do check_mem_access to check and update stack bounds later, so + * return true for that case. + */ + spi = irq_flag_get_spi(env, reg); + if (spi == -ERANGE) + return true; + if (spi < 0) + return false; + + slot = &state->stack[spi]; + + for (i = 0; i < BPF_REG_SIZE; i++) + if (slot->slot_type[i] == STACK_IRQ_FLAG) + return false; + return true; +} + +static int is_irq_flag_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + struct bpf_stack_state *slot; + struct bpf_reg_state *st; + int spi, i; + + spi = irq_flag_get_spi(env, reg); + if (spi < 0) + return -EINVAL; + + slot = &state->stack[spi]; + st = &slot->spilled_ptr; + + if (!st->ref_obj_id) + return -EINVAL; + + for (i = 0; i < BPF_REG_SIZE; i++) + if (slot->slot_type[i] != STACK_IRQ_FLAG) + return -EINVAL; + return 0; +} + /* Check if given stack slot is "special": * - spilled register state (STACK_SPILL); * - dynptr state (STACK_DYNPTR); * - iter state (STACK_ITER). + * - irq flag state (STACK_IRQ_FLAG) */ static bool is_stack_slot_special(const struct bpf_stack_state *stack) { @@ -1149,6 +1282,7 @@ static bool is_stack_slot_special(const struct bpf_stack_state *stack) case STACK_SPILL: case STACK_DYNPTR: case STACK_ITER: + case STACK_IRQ_FLAG: return true; case STACK_INVALID: case STACK_MISC: @@ -1263,15 +1397,18 @@ out: return arr ? arr : ZERO_SIZE_PTR; } -static int copy_reference_state(struct bpf_func_state *dst, const struct bpf_func_state *src) +static int copy_reference_state(struct bpf_verifier_state *dst, const struct bpf_verifier_state *src) { dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs, sizeof(struct bpf_reference_state), GFP_KERNEL); if (!dst->refs) return -ENOMEM; - dst->active_locks = src->active_locks; dst->acquired_refs = src->acquired_refs; + dst->active_locks = src->active_locks; + dst->active_preempt_locks = src->active_preempt_locks; + dst->active_rcu_lock = src->active_rcu_lock; + dst->active_irq_id = src->active_irq_id; return 0; } @@ -1288,7 +1425,7 @@ static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_st return 0; } -static int resize_reference_state(struct bpf_func_state *state, size_t n) +static int resize_reference_state(struct bpf_verifier_state *state, size_t n) { state->refs = realloc_array(state->refs, state->acquired_refs, n, sizeof(struct bpf_reference_state)); @@ -1331,77 +1468,90 @@ static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state * On success, returns a valid pointer id to associate with the register * On failure, returns a negative errno. */ -static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) +static struct bpf_reference_state *acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) { - struct bpf_func_state *state = cur_func(env); - int new_ofs = state->acquired_refs; - int id, err; - - err = resize_reference_state(state, state->acquired_refs + 1); - if (err) - return err; - id = ++env->id_gen; - state->refs[new_ofs].type = REF_TYPE_PTR; - state->refs[new_ofs].id = id; - state->refs[new_ofs].insn_idx = insn_idx; - - return id; -} - -static int acquire_lock_state(struct bpf_verifier_env *env, int insn_idx, enum ref_state_type type, - int id, void *ptr) -{ - struct bpf_func_state *state = cur_func(env); + struct bpf_verifier_state *state = env->cur_state; int new_ofs = state->acquired_refs; int err; err = resize_reference_state(state, state->acquired_refs + 1); if (err) - return err; - state->refs[new_ofs].type = type; - state->refs[new_ofs].id = id; + return NULL; state->refs[new_ofs].insn_idx = insn_idx; - state->refs[new_ofs].ptr = ptr; + + return &state->refs[new_ofs]; +} + +static int acquire_reference(struct bpf_verifier_env *env, int insn_idx) +{ + struct bpf_reference_state *s; + + s = acquire_reference_state(env, insn_idx); + if (!s) + return -ENOMEM; + s->type = REF_TYPE_PTR; + s->id = ++env->id_gen; + return s->id; +} + +static int acquire_lock_state(struct bpf_verifier_env *env, int insn_idx, enum ref_state_type type, + int id, void *ptr) +{ + struct bpf_verifier_state *state = env->cur_state; + struct bpf_reference_state *s; + + s = acquire_reference_state(env, insn_idx); + s->type = type; + s->id = id; + s->ptr = ptr; state->active_locks++; return 0; } -/* release function corresponding to acquire_reference_state(). Idempotent. */ -static int release_reference_state(struct bpf_func_state *state, int ptr_id) +static int acquire_irq_state(struct bpf_verifier_env *env, int insn_idx) { - int i, last_idx; + struct bpf_verifier_state *state = env->cur_state; + struct bpf_reference_state *s; - last_idx = state->acquired_refs - 1; - for (i = 0; i < state->acquired_refs; i++) { - if (state->refs[i].type != REF_TYPE_PTR) - continue; - if (state->refs[i].id == ptr_id) { - if (last_idx && i != last_idx) - memcpy(&state->refs[i], &state->refs[last_idx], - sizeof(*state->refs)); - memset(&state->refs[last_idx], 0, sizeof(*state->refs)); - state->acquired_refs--; - return 0; - } - } - return -EINVAL; + s = acquire_reference_state(env, insn_idx); + if (!s) + return -ENOMEM; + s->type = REF_TYPE_IRQ; + s->id = ++env->id_gen; + + state->active_irq_id = s->id; + return s->id; } -static int release_lock_state(struct bpf_func_state *state, int type, int id, void *ptr) +static void release_reference_state(struct bpf_verifier_state *state, int idx) { - int i, last_idx; + int last_idx; + size_t rem; + /* IRQ state requires the relative ordering of elements remaining the + * same, since it relies on the refs array to behave as a stack, so that + * it can detect out-of-order IRQ restore. Hence use memmove to shift + * the array instead of swapping the final element into the deleted idx. + */ last_idx = state->acquired_refs - 1; + rem = state->acquired_refs - idx - 1; + if (last_idx && idx != last_idx) + memmove(&state->refs[idx], &state->refs[idx + 1], sizeof(*state->refs) * rem); + memset(&state->refs[last_idx], 0, sizeof(*state->refs)); + state->acquired_refs--; + return; +} + +static int release_lock_state(struct bpf_verifier_state *state, int type, int id, void *ptr) +{ + int i; + for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].type != type) continue; if (state->refs[i].id == id && state->refs[i].ptr == ptr) { - if (last_idx && i != last_idx) - memcpy(&state->refs[i], &state->refs[last_idx], - sizeof(*state->refs)); - memset(&state->refs[last_idx], 0, sizeof(*state->refs)); - state->acquired_refs--; + release_reference_state(state, i); state->active_locks--; return 0; } @@ -1409,16 +1559,37 @@ static int release_lock_state(struct bpf_func_state *state, int type, int id, vo return -EINVAL; } -static struct bpf_reference_state *find_lock_state(struct bpf_verifier_env *env, enum ref_state_type type, +static int release_irq_state(struct bpf_verifier_state *state, int id) +{ + u32 prev_id = 0; + int i; + + if (id != state->active_irq_id) + return -EACCES; + + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].type != REF_TYPE_IRQ) + continue; + if (state->refs[i].id == id) { + release_reference_state(state, i); + state->active_irq_id = prev_id; + return 0; + } else { + prev_id = state->refs[i].id; + } + } + return -EINVAL; +} + +static struct bpf_reference_state *find_lock_state(struct bpf_verifier_state *state, enum ref_state_type type, int id, void *ptr) { - struct bpf_func_state *state = cur_func(env); int i; for (i = 0; i < state->acquired_refs; i++) { struct bpf_reference_state *s = &state->refs[i]; - if (s->type == REF_TYPE_PTR || s->type != type) + if (s->type != type) continue; if (s->id == id && s->ptr == ptr) @@ -1431,7 +1602,6 @@ static void free_func_state(struct bpf_func_state *state) { if (!state) return; - kfree(state->refs); kfree(state->stack); kfree(state); } @@ -1445,6 +1615,7 @@ static void free_verifier_state(struct bpf_verifier_state *state, free_func_state(state->frame[i]); state->frame[i] = NULL; } + kfree(state->refs); if (free_self) kfree(state); } @@ -1455,12 +1626,7 @@ static void free_verifier_state(struct bpf_verifier_state *state, static int copy_func_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { - int err; - - memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); - err = copy_reference_state(dst, src); - if (err) - return err; + memcpy(dst, src, offsetof(struct bpf_func_state, stack)); return copy_stack_state(dst, src); } @@ -1477,9 +1643,10 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, free_func_state(dst_state->frame[i]); dst_state->frame[i] = NULL; } + err = copy_reference_state(dst_state, src); + if (err) + return err; dst_state->speculative = src->speculative; - dst_state->active_rcu_lock = src->active_rcu_lock; - dst_state->active_preempt_lock = src->active_preempt_lock; dst_state->in_sleepable = src->in_sleepable; dst_state->curframe = src->curframe; dst_state->branches = src->branches; @@ -3206,10 +3373,27 @@ static int mark_reg_read(struct bpf_verifier_env *env, return 0; } -static int mark_dynptr_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +static int mark_stack_slot_obj_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + int spi, int nr_slots) { struct bpf_func_state *state = func(env, reg); - int spi, ret; + int err, i; + + for (i = 0; i < nr_slots; i++) { + struct bpf_reg_state *st = &state->stack[spi - i].spilled_ptr; + + err = mark_reg_read(env, st, st->parent, REG_LIVE_READ64); + if (err) + return err; + + mark_stack_slot_scratched(env, spi - i); + } + return 0; +} + +static int mark_dynptr_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + int spi; /* For CONST_PTR_TO_DYNPTR, it must have already been done by * check_reg_arg in check_helper_call and mark_btf_func_reg_size in @@ -3224,31 +3408,23 @@ static int mark_dynptr_read(struct bpf_verifier_env *env, struct bpf_reg_state * * bounds and spi is the first dynptr slot. Simply mark stack slot as * read. */ - ret = mark_reg_read(env, &state->stack[spi].spilled_ptr, - state->stack[spi].spilled_ptr.parent, REG_LIVE_READ64); - if (ret) - return ret; - return mark_reg_read(env, &state->stack[spi - 1].spilled_ptr, - state->stack[spi - 1].spilled_ptr.parent, REG_LIVE_READ64); + return mark_stack_slot_obj_read(env, reg, spi, BPF_DYNPTR_NR_SLOTS); } static int mark_iter_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int spi, int nr_slots) { - struct bpf_func_state *state = func(env, reg); - int err, i; + return mark_stack_slot_obj_read(env, reg, spi, nr_slots); +} - for (i = 0; i < nr_slots; i++) { - struct bpf_reg_state *st = &state->stack[spi - i].spilled_ptr; +static int mark_irq_flag_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + int spi; - err = mark_reg_read(env, st, st->parent, REG_LIVE_READ64); - if (err) - return err; - - mark_stack_slot_scratched(env, spi - i); - } - - return 0; + spi = irq_flag_get_spi(env, reg); + if (spi < 0) + return spi; + return mark_stack_slot_obj_read(env, reg, spi, 1); } /* This function is supposed to be used by the following 32-bit optimization @@ -4503,7 +4679,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_frame_stack_mask(bt, fr)); verbose(env, "stack=%s: ", env->tmp_str_buf); - print_verifier_state(env, func, true); + print_verifier_state(env, st, fr, true); } } @@ -5128,7 +5304,7 @@ enum bpf_access_src { static int check_stack_range_initialized(struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, - enum bpf_access_src type, + enum bpf_access_type type, struct bpf_call_arg_meta *meta); static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) @@ -5161,7 +5337,7 @@ static int check_stack_read_var_off(struct bpf_verifier_env *env, /* Note that we pass a NULL meta, so raw access will not be permitted. */ err = check_stack_range_initialized(env, ptr_regno, off, size, - false, ACCESS_DIRECT, NULL); + false, BPF_READ, NULL); if (err) return err; @@ -5501,13 +5677,15 @@ static bool in_sleepable(struct bpf_verifier_env *env) static bool in_rcu_cs(struct bpf_verifier_env *env) { return env->cur_state->active_rcu_lock || - cur_func(env)->active_locks || + env->cur_state->active_locks || !in_sleepable(env); } /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */ BTF_SET_START(rcu_protected_types) +#ifdef CONFIG_NET BTF_ID(struct, prog_test_ref_kfunc) +#endif #ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) #endif @@ -5515,7 +5693,9 @@ BTF_ID(struct, cgroup) BTF_ID(struct, bpf_cpumask) #endif BTF_ID(struct, task_struct) +#ifdef CONFIG_CRYPTO BTF_ID(struct, bpf_crypto_ctx) +#endif BTF_SET_END(rcu_protected_types) static bool rcu_protected_object(const struct btf *btf, u32 btf_id) @@ -7011,7 +7191,7 @@ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env, static int check_stack_access_within_bounds( struct bpf_verifier_env *env, int regno, int off, int access_size, - enum bpf_access_src src, enum bpf_access_type type) + enum bpf_access_type type) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; @@ -7020,10 +7200,7 @@ static int check_stack_access_within_bounds( int err; char *err_extra; - if (src == ACCESS_HELPER) - /* We don't know if helpers are reading or writing (or both). */ - err_extra = " indirect access to"; - else if (type == BPF_READ) + if (type == BPF_READ) err_extra = " read from"; else err_extra = " write to"; @@ -7241,7 +7418,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else if (reg->type == PTR_TO_STACK) { /* Basic bounds checks. */ - err = check_stack_access_within_bounds(env, regno, off, size, ACCESS_DIRECT, t); + err = check_stack_access_within_bounds(env, regno, off, size, t); if (err) return err; @@ -7461,13 +7638,11 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i static int check_stack_range_initialized( struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, - enum bpf_access_src type, struct bpf_call_arg_meta *meta) + enum bpf_access_type type, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = func(env, reg); int err, min_off, max_off, i, j, slot, spi; - char *err_extra = type == ACCESS_HELPER ? " indirect" : ""; - enum bpf_access_type bounds_check_type; /* Some accesses can write anything into the stack, others are * read-only. */ @@ -7478,18 +7653,10 @@ static int check_stack_range_initialized( return -EACCES; } - if (type == ACCESS_HELPER) { - /* The bounds checks for writes are more permissive than for - * reads. However, if raw_mode is not set, we'll do extra - * checks below. - */ - bounds_check_type = BPF_WRITE; + if (type == BPF_WRITE) clobber = true; - } else { - bounds_check_type = BPF_READ; - } - err = check_stack_access_within_bounds(env, regno, off, access_size, - type, bounds_check_type); + + err = check_stack_access_within_bounds(env, regno, off, access_size, type); if (err) return err; @@ -7506,8 +7673,8 @@ static int check_stack_range_initialized( char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "R%d%s variable offset stack access prohibited for !root, var_off=%s\n", - regno, err_extra, tn_buf); + verbose(env, "R%d variable offset stack access prohibited for !root, var_off=%s\n", + regno, tn_buf); return -EACCES; } /* Only initialized buffer on stack is allowed to be accessed @@ -7560,7 +7727,7 @@ static int check_stack_range_initialized( slot = -i - 1; spi = slot / BPF_REG_SIZE; if (state->allocated_stack <= slot) { - verbose(env, "verifier bug: allocated_stack too small"); + verbose(env, "verifier bug: allocated_stack too small\n"); return -EFAULT; } @@ -7588,14 +7755,14 @@ static int check_stack_range_initialized( } if (tnum_is_const(reg->var_off)) { - verbose(env, "invalid%s read from stack R%d off %d+%d size %d\n", - err_extra, regno, min_off, i - min_off, access_size); + verbose(env, "invalid read from stack R%d off %d+%d size %d\n", + regno, min_off, i - min_off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "invalid%s read from stack R%d var_off %s+%d size %d\n", - err_extra, regno, tn_buf, i - min_off, access_size); + verbose(env, "invalid read from stack R%d var_off %s+%d size %d\n", + regno, tn_buf, i - min_off, access_size); } return -EACCES; mark: @@ -7670,7 +7837,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_stack_range_initialized( env, regno, reg->off, access_size, - zero_size_allowed, ACCESS_HELPER, meta); + zero_size_allowed, access_type, meta); case PTR_TO_BTF_ID: return check_ptr_to_btf_access(env, regs, regno, reg->off, access_size, BPF_READ, -1); @@ -7835,15 +8002,15 @@ static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg * Since only one bpf_spin_lock is allowed the checks are simpler than * reg_is_refcounted() logic. The verifier needs to remember only * one spin_lock instead of array of acquired_refs. - * cur_func(env)->active_locks remembers which map value element or allocated + * env->cur_state->active_locks remembers which map value element or allocated * object got locked and clears it after bpf_spin_unlock. */ static int process_spin_lock(struct bpf_verifier_env *env, int regno, bool is_lock) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + struct bpf_verifier_state *cur = env->cur_state; bool is_const = tnum_is_const(reg->var_off); - struct bpf_func_state *cur = cur_func(env); u64 val = reg->var_off.value; struct bpf_map *map = NULL; struct btf *btf = NULL; @@ -7910,7 +8077,7 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, return -EINVAL; } - if (release_lock_state(cur_func(env), REF_TYPE_LOCK, reg->id, ptr)) { + if (release_lock_state(env->cur_state, REF_TYPE_LOCK, reg->id, ptr)) { verbose(env, "bpf_spin_unlock of different lock\n"); return -EINVAL; } @@ -8982,6 +9149,63 @@ static int check_reg_const_str(struct bpf_verifier_env *env, return 0; } +/* Returns constant key value if possible, else negative error */ +static s64 get_constant_map_key(struct bpf_verifier_env *env, + struct bpf_reg_state *key, + u32 key_size) +{ + struct bpf_func_state *state = func(env, key); + struct bpf_reg_state *reg; + int slot, spi, off; + int spill_size = 0; + int zero_size = 0; + int stack_off; + int i, err; + u8 *stype; + + if (!env->bpf_capable) + return -EOPNOTSUPP; + if (key->type != PTR_TO_STACK) + return -EOPNOTSUPP; + if (!tnum_is_const(key->var_off)) + return -EOPNOTSUPP; + + stack_off = key->off + key->var_off.value; + slot = -stack_off - 1; + spi = slot / BPF_REG_SIZE; + off = slot % BPF_REG_SIZE; + stype = state->stack[spi].slot_type; + + /* First handle precisely tracked STACK_ZERO */ + for (i = off; i >= 0 && stype[i] == STACK_ZERO; i--) + zero_size++; + if (zero_size >= key_size) + return 0; + + /* Check that stack contains a scalar spill of expected size */ + if (!is_spilled_scalar_reg(&state->stack[spi])) + return -EOPNOTSUPP; + for (i = off; i >= 0 && stype[i] == STACK_SPILL; i--) + spill_size++; + if (spill_size != key_size) + return -EOPNOTSUPP; + + reg = &state->stack[spi].spilled_ptr; + if (!tnum_is_const(reg->var_off)) + /* Stack value not statically known */ + return -EOPNOTSUPP; + + /* We are relying on a constant value. So mark as precise + * to prevent pruning on it. + */ + bt_set_frame_slot(&env->bt, key->frameno, spi); + err = mark_chain_precision_batch(env); + if (err < 0) + return err; + + return reg->var_off.value; +} + static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn, @@ -8992,6 +9216,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, enum bpf_arg_type arg_type = fn->arg_type[arg]; enum bpf_reg_type type = reg->type; u32 *arg_btf_id = NULL; + u32 key_size; int err = 0; if (arg_type == ARG_DONTCARE) @@ -9125,8 +9350,13 @@ skip_type_check: verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } - err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, - BPF_READ, false, NULL); + key_size = meta->map_ptr->key_size; + err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL); + if (err) + return err; + meta->const_map_key = get_constant_map_key(env, reg, key_size); + if (meta->const_map_key < 0 && meta->const_map_key != -EOPNOTSUPP) + return meta->const_map_key; break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && register_is_null(reg)) @@ -9658,21 +9888,38 @@ static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range reg->range = AT_PKT_END; } +static int release_reference_nomark(struct bpf_verifier_state *state, int ref_obj_id) +{ + int i; + + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].type != REF_TYPE_PTR) + continue; + if (state->refs[i].id == ref_obj_id) { + release_reference_state(state, i); + return 0; + } + } + return -EINVAL; +} + /* The pointer with the specified id has released its reference to kernel * resources. Identify all copies of the same pointer and clear the reference. + * + * This is the release function corresponding to acquire_reference(). Idempotent. */ -static int release_reference(struct bpf_verifier_env *env, - int ref_obj_id) +static int release_reference(struct bpf_verifier_env *env, int ref_obj_id) { + struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state; struct bpf_reg_state *reg; int err; - err = release_reference_state(cur_func(env), ref_obj_id); + err = release_reference_nomark(vstate, ref_obj_id); if (err) return err; - bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->ref_obj_id == ref_obj_id) mark_reg_invalid(env, reg); })); @@ -9746,9 +9993,7 @@ static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int calls callsite, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); - /* Transfer references to the callee */ - err = copy_reference_state(callee, caller); - err = err ?: set_callee_state_cb(env, caller, callee, callsite); + err = set_callee_state_cb(env, caller, callee, callsite); if (err) goto err_out; @@ -9978,19 +10223,25 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, const char *sub_name = subprog_name(env, subprog); /* Only global subprogs cannot be called with a lock held. */ - if (cur_func(env)->active_locks) { + if (env->cur_state->active_locks) { verbose(env, "global function calls are not allowed while holding a lock,\n" "use static function instead\n"); return -EINVAL; } /* Only global subprogs cannot be called with preemption disabled. */ - if (env->cur_state->active_preempt_lock) { + if (env->cur_state->active_preempt_locks) { verbose(env, "global function calls are not allowed with preemption disabled,\n" "use static function instead\n"); return -EINVAL; } + if (env->cur_state->active_irq_id) { + verbose(env, "global function calls are not allowed with IRQs disabled,\n" + "use static function instead\n"); + return -EINVAL; + } + if (err) { verbose(env, "Caller passes invalid args into func#%d ('%s')\n", subprog, sub_name); @@ -10027,9 +10278,9 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); - print_verifier_state(env, caller, true); + print_verifier_state(env, state, caller->frameno, true); verbose(env, "callee:\n"); - print_verifier_state(env, state->frame[state->curframe], true); + print_verifier_state(env, state, state->curframe, true); } return 0; @@ -10321,11 +10572,6 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) caller->regs[BPF_REG_0] = *r0; } - /* Transfer references to the caller */ - err = copy_reference_state(caller, callee); - if (err) - return err; - /* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite, * there function call logic would reschedule callback visit. If iteration * converges is_state_visited() would prune that visit eventually. @@ -10338,9 +10584,9 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); - print_verifier_state(env, callee, true); + print_verifier_state(env, state, callee->frameno, true); verbose(env, "to caller at %d:\n", *insn_idx); - print_verifier_state(env, caller, true); + print_verifier_state(env, state, caller->frameno, true); } /* clear everything in the callee. In case of exceptional exits using * bpf_throw, this will be done by copy_verifier_state for extra frames. */ @@ -10490,11 +10736,11 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit) { - struct bpf_func_state *state = cur_func(env); + struct bpf_verifier_state *state = env->cur_state; bool refs_lingering = false; int i; - if (!exception_exit && state->frameno) + if (!exception_exit && cur_func(env)->frameno) return 0; for (i = 0; i < state->acquired_refs; i++) { @@ -10511,7 +10757,7 @@ static int check_resource_leak(struct bpf_verifier_env *env, bool exception_exit { int err; - if (check_lock && cur_func(env)->active_locks) { + if (check_lock && env->cur_state->active_locks) { verbose(env, "%s cannot be used inside bpf_spin_lock-ed region\n", prefix); return -EINVAL; } @@ -10522,12 +10768,17 @@ static int check_resource_leak(struct bpf_verifier_env *env, bool exception_exit return err; } + if (check_lock && env->cur_state->active_irq_id) { + verbose(env, "%s cannot be used inside bpf_local_irq_save-ed region\n", prefix); + return -EINVAL; + } + if (check_lock && env->cur_state->active_rcu_lock) { verbose(env, "%s cannot be used inside bpf_rcu_read_lock-ed region\n", prefix); return -EINVAL; } - if (check_lock && env->cur_state->active_preempt_lock) { + if (check_lock && env->cur_state->active_preempt_locks) { verbose(env, "%s cannot be used inside bpf_preempt_disable-ed region\n", prefix); return -EINVAL; } @@ -10629,6 +10880,21 @@ static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno state->callback_subprogno == subprogno); } +/* Returns whether or not the given map type can potentially elide + * lookup return value nullness check. This is possible if the key + * is statically known. + */ +static bool can_elide_value_nullness(enum bpf_map_type type) +{ + switch (type) { + case BPF_MAP_TYPE_ARRAY: + case BPF_MAP_TYPE_PERCPU_ARRAY: + return true; + default: + return false; + } +} + static int get_helper_proto(struct bpf_verifier_env *env, int func_id, const struct bpf_func_proto **ptr) { @@ -10715,7 +10981,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } - if (env->cur_state->active_preempt_lock) { + if (env->cur_state->active_preempt_locks) { if (fn->might_sleep) { verbose(env, "sleepable helper %s#%d in non-preemptible region\n", func_id_name(func_id), func_id); @@ -10726,6 +10992,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } + if (env->cur_state->active_irq_id) { + if (fn->might_sleep) { + verbose(env, "sleepable helper %s#%d in IRQ-disabled region\n", + func_id_name(func_id), func_id); + return -EINVAL; + } + + if (in_sleepable(env) && is_storage_get_function(func_id)) + env->insn_aux_data[insn_idx].storage_get_func_atomic = true; + } + meta.func_id = func_id; /* check args */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { @@ -10772,7 +11049,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn struct bpf_func_state *state; struct bpf_reg_state *reg; - err = release_reference_state(cur_func(env), ref_obj_id); + err = release_reference_nomark(env->cur_state, ref_obj_id); if (!err) { bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg->ref_obj_id == ref_obj_id) { @@ -10984,10 +11261,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn "kernel subsystem misconfigured verifier\n"); return -EINVAL; } + + if (func_id == BPF_FUNC_map_lookup_elem && + can_elide_value_nullness(meta.map_ptr->map_type) && + meta.const_map_key >= 0 && + meta.const_map_key < meta.map_ptr->max_entries) + ret_flag &= ~PTR_MAYBE_NULL; + regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].map_uid = meta.map_uid; regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; - if (!type_may_be_null(ret_type) && + if (!type_may_be_null(ret_flag) && btf_record_has_field(meta.map_ptr->record, BPF_SPIN_LOCK)) { regs[BPF_REG_0].id = ++env->id_gen; } @@ -11105,7 +11389,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; } else if (is_acquire_function(func_id, meta.map_ptr)) { - int id = acquire_reference_state(env, insn_idx); + int id = acquire_reference(env, insn_idx); if (id < 0) return id; @@ -11287,6 +11571,11 @@ static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param return btf_param_match_suffix(btf, arg, "__str"); } +static bool is_kfunc_arg_irq_flag(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__irq_flag"); +} + static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) @@ -11440,6 +11729,7 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_CONST_STR, KF_ARG_PTR_TO_MAP, KF_ARG_PTR_TO_WORKQUEUE, + KF_ARG_PTR_TO_IRQ_FLAG, }; enum special_kfunc_type { @@ -11471,6 +11761,11 @@ enum special_kfunc_type { KF_bpf_iter_css_task_new, KF_bpf_session_cookie, KF_bpf_get_kmem_cache, + KF_bpf_local_irq_save, + KF_bpf_local_irq_restore, + KF_bpf_iter_num_new, + KF_bpf_iter_num_next, + KF_bpf_iter_num_destroy, }; BTF_SET_START(special_kfunc_set) @@ -11486,8 +11781,10 @@ BTF_ID(func, bpf_rdonly_cast) BTF_ID(func, bpf_rbtree_remove) BTF_ID(func, bpf_rbtree_add_impl) BTF_ID(func, bpf_rbtree_first) +#ifdef CONFIG_NET BTF_ID(func, bpf_dynptr_from_skb) BTF_ID(func, bpf_dynptr_from_xdp) +#endif BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_ID(func, bpf_dynptr_clone) @@ -11515,8 +11812,13 @@ BTF_ID(func, bpf_rcu_read_unlock) BTF_ID(func, bpf_rbtree_remove) BTF_ID(func, bpf_rbtree_add_impl) BTF_ID(func, bpf_rbtree_first) +#ifdef CONFIG_NET BTF_ID(func, bpf_dynptr_from_skb) BTF_ID(func, bpf_dynptr_from_xdp) +#else +BTF_ID_UNUSED +BTF_ID_UNUSED +#endif BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_ID(func, bpf_dynptr_clone) @@ -11537,6 +11839,11 @@ BTF_ID(func, bpf_session_cookie) BTF_ID_UNUSED #endif BTF_ID(func, bpf_get_kmem_cache) +BTF_ID(func, bpf_local_irq_save) +BTF_ID(func, bpf_local_irq_restore) +BTF_ID(func, bpf_iter_num_new) +BTF_ID(func, bpf_iter_num_next) +BTF_ID(func, bpf_iter_num_destroy) static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { @@ -11627,6 +11934,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_wq(meta->btf, &args[argno])) return KF_ARG_PTR_TO_WORKQUEUE; + if (is_kfunc_arg_irq_flag(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_IRQ_FLAG; + if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) { if (!btf_type_is_struct(ref_t)) { verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n", @@ -11730,11 +12040,59 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, return 0; } +static int process_irq_flag(struct bpf_verifier_env *env, int regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + bool irq_save; + int err; + + if (meta->func_id == special_kfunc_list[KF_bpf_local_irq_save]) { + irq_save = true; + } else if (meta->func_id == special_kfunc_list[KF_bpf_local_irq_restore]) { + irq_save = false; + } else { + verbose(env, "verifier internal error: unknown irq flags kfunc\n"); + return -EFAULT; + } + + if (irq_save) { + if (!is_irq_flag_reg_valid_uninit(env, reg)) { + verbose(env, "expected uninitialized irq flag as arg#%d\n", regno - 1); + return -EINVAL; + } + + err = check_mem_access(env, env->insn_idx, regno, 0, BPF_DW, BPF_WRITE, -1, false, false); + if (err) + return err; + + err = mark_stack_slot_irq_flag(env, meta, reg, env->insn_idx); + if (err) + return err; + } else { + err = is_irq_flag_reg_valid_init(env, reg); + if (err) { + verbose(env, "expected an initialized irq flag as arg#%d\n", regno - 1); + return err; + } + + err = mark_irq_flag_read(env, reg); + if (err) + return err; + + err = unmark_stack_slot_irq_flag(env, reg); + if (err) + return err; + } + return 0; +} + + static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct btf_record *rec = reg_btf_record(reg); - if (!cur_func(env)->active_locks) { + if (!env->cur_state->active_locks) { verbose(env, "verifier internal error: ref_set_non_owning w/o active lock\n"); return -EFAULT; } @@ -11753,12 +12111,11 @@ static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state static int ref_convert_owning_non_owning(struct bpf_verifier_env *env, u32 ref_obj_id) { - struct bpf_func_state *state, *unused; + struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_state *unused; struct bpf_reg_state *reg; int i; - state = cur_func(env); - if (!ref_obj_id) { verbose(env, "verifier internal error: ref_obj_id is zero for " "owning -> non-owning conversion\n"); @@ -11848,9 +12205,9 @@ static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_ } id = reg->id; - if (!cur_func(env)->active_locks) + if (!env->cur_state->active_locks) return -EINVAL; - s = find_lock_state(env, REF_TYPE_LOCK, id, ptr); + s = find_lock_state(env->cur_state, REF_TYPE_LOCK, id, ptr); if (!s) { verbose(env, "held lock and object are not in the same allocation\n"); return -EINVAL; @@ -11873,12 +12230,24 @@ static bool is_bpf_rbtree_api_kfunc(u32 btf_id) btf_id == special_kfunc_list[KF_bpf_rbtree_first]; } +static bool is_bpf_iter_num_api_kfunc(u32 btf_id) +{ + return btf_id == special_kfunc_list[KF_bpf_iter_num_new] || + btf_id == special_kfunc_list[KF_bpf_iter_num_next] || + btf_id == special_kfunc_list[KF_bpf_iter_num_destroy]; +} + static bool is_bpf_graph_api_kfunc(u32 btf_id) { return is_bpf_list_api_kfunc(btf_id) || is_bpf_rbtree_api_kfunc(btf_id) || btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]; } +static bool kfunc_spin_allowed(u32 btf_id) +{ + return is_bpf_graph_api_kfunc(btf_id) || is_bpf_iter_num_api_kfunc(btf_id); +} + static bool is_sync_callback_calling_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl]; @@ -12307,6 +12676,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ case KF_ARG_PTR_TO_REFCOUNTED_KPTR: case KF_ARG_PTR_TO_CONST_STR: case KF_ARG_PTR_TO_WORKQUEUE: + case KF_ARG_PTR_TO_IRQ_FLAG: break; default: WARN_ON_ONCE(1); @@ -12596,6 +12966,15 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (ret < 0) return ret; break; + case KF_ARG_PTR_TO_IRQ_FLAG: + if (reg->type != PTR_TO_STACK) { + verbose(env, "arg#%d doesn't point to an irq flag on stack\n", i); + return -EINVAL; + } + ret = process_irq_flag(env, regno, meta); + if (ret < 0) + return ret; + break; } } @@ -12760,22 +13139,27 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EINVAL; } - if (env->cur_state->active_preempt_lock) { + if (env->cur_state->active_preempt_locks) { if (preempt_disable) { - env->cur_state->active_preempt_lock++; + env->cur_state->active_preempt_locks++; } else if (preempt_enable) { - env->cur_state->active_preempt_lock--; + env->cur_state->active_preempt_locks--; } else if (sleepable) { verbose(env, "kernel func %s is sleepable within non-preemptible region\n", func_name); return -EACCES; } } else if (preempt_disable) { - env->cur_state->active_preempt_lock++; + env->cur_state->active_preempt_locks++; } else if (preempt_enable) { verbose(env, "unmatched attempt to enable preemption (kernel function %s)\n", func_name); return -EINVAL; } + if (env->cur_state->active_irq_id && sleepable) { + verbose(env, "kernel func %s is sleepable within IRQ-disabled region\n", func_name); + return -EACCES; + } + /* In case of release function, we get register number of refcounted * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ @@ -13069,7 +13453,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); if (is_kfunc_acquire(&meta)) { - int id = acquire_reference_state(env, insn_idx); + int id = acquire_reference(env, insn_idx); if (id < 0) return id; @@ -13794,64 +14178,56 @@ static void scalar_min_max_sub(struct bpf_reg_state *dst_reg, static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { - s32 smin_val = src_reg->s32_min_value; - u32 umin_val = src_reg->u32_min_value; - u32 umax_val = src_reg->u32_max_value; + s32 *dst_smin = &dst_reg->s32_min_value; + s32 *dst_smax = &dst_reg->s32_max_value; + u32 *dst_umin = &dst_reg->u32_min_value; + u32 *dst_umax = &dst_reg->u32_max_value; + s32 tmp_prod[4]; - if (smin_val < 0 || dst_reg->s32_min_value < 0) { - /* Ain't nobody got time to multiply that sign */ - __mark_reg32_unbounded(dst_reg); - return; - } - /* Both values are positive, so we can work with unsigned and - * copy the result to signed (unless it exceeds S32_MAX). - */ - if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) { - /* Potential overflow, we know nothing */ - __mark_reg32_unbounded(dst_reg); - return; - } - dst_reg->u32_min_value *= umin_val; - dst_reg->u32_max_value *= umax_val; - if (dst_reg->u32_max_value > S32_MAX) { + if (check_mul_overflow(*dst_umax, src_reg->u32_max_value, dst_umax) || + check_mul_overflow(*dst_umin, src_reg->u32_min_value, dst_umin)) { /* Overflow possible, we know nothing */ - dst_reg->s32_min_value = S32_MIN; - dst_reg->s32_max_value = S32_MAX; + *dst_umin = 0; + *dst_umax = U32_MAX; + } + if (check_mul_overflow(*dst_smin, src_reg->s32_min_value, &tmp_prod[0]) || + check_mul_overflow(*dst_smin, src_reg->s32_max_value, &tmp_prod[1]) || + check_mul_overflow(*dst_smax, src_reg->s32_min_value, &tmp_prod[2]) || + check_mul_overflow(*dst_smax, src_reg->s32_max_value, &tmp_prod[3])) { + /* Overflow possible, we know nothing */ + *dst_smin = S32_MIN; + *dst_smax = S32_MAX; } else { - dst_reg->s32_min_value = dst_reg->u32_min_value; - dst_reg->s32_max_value = dst_reg->u32_max_value; + *dst_smin = min_array(tmp_prod, 4); + *dst_smax = max_array(tmp_prod, 4); } } static void scalar_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { - s64 smin_val = src_reg->smin_value; - u64 umin_val = src_reg->umin_value; - u64 umax_val = src_reg->umax_value; + s64 *dst_smin = &dst_reg->smin_value; + s64 *dst_smax = &dst_reg->smax_value; + u64 *dst_umin = &dst_reg->umin_value; + u64 *dst_umax = &dst_reg->umax_value; + s64 tmp_prod[4]; - if (smin_val < 0 || dst_reg->smin_value < 0) { - /* Ain't nobody got time to multiply that sign */ - __mark_reg64_unbounded(dst_reg); - return; - } - /* Both values are positive, so we can work with unsigned and - * copy the result to signed (unless it exceeds S64_MAX). - */ - if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { - /* Potential overflow, we know nothing */ - __mark_reg64_unbounded(dst_reg); - return; - } - dst_reg->umin_value *= umin_val; - dst_reg->umax_value *= umax_val; - if (dst_reg->umax_value > S64_MAX) { + if (check_mul_overflow(*dst_umax, src_reg->umax_value, dst_umax) || + check_mul_overflow(*dst_umin, src_reg->umin_value, dst_umin)) { /* Overflow possible, we know nothing */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; + *dst_umin = 0; + *dst_umax = U64_MAX; + } + if (check_mul_overflow(*dst_smin, src_reg->smin_value, &tmp_prod[0]) || + check_mul_overflow(*dst_smin, src_reg->smax_value, &tmp_prod[1]) || + check_mul_overflow(*dst_smax, src_reg->smin_value, &tmp_prod[2]) || + check_mul_overflow(*dst_smax, src_reg->smax_value, &tmp_prod[3])) { + /* Overflow possible, we know nothing */ + *dst_smin = S64_MIN; + *dst_smax = S64_MAX; } else { - dst_reg->smin_value = dst_reg->umin_value; - dst_reg->smax_value = dst_reg->umax_value; + *dst_smin = min_array(tmp_prod, 4); + *dst_smax = max_array(tmp_prod, 4); } } @@ -14462,12 +14838,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { - print_verifier_state(env, state, true); + print_verifier_state(env, vstate, vstate->curframe, true); verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { - print_verifier_state(env, state, true); + print_verifier_state(env, vstate, vstate->curframe, true); verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } @@ -15365,7 +15741,7 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, * No one could have freed the reference state before * doing the NULL check. */ - WARN_ON_ONCE(release_reference_state(state, id)); + WARN_ON_ONCE(release_reference_nomark(vstate, id)); bpf_for_each_reg_in_vstate(vstate, state, reg, ({ mark_ptr_or_null_reg(state, reg, id, is_null); @@ -15596,9 +15972,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, if (insn->code != (BPF_JMP | BPF_JCOND) || insn->src_reg != BPF_MAY_GOTO || - insn->dst_reg || insn->imm || insn->off == 0) { - verbose(env, "invalid may_goto off %d imm %d\n", - insn->off, insn->imm); + insn->dst_reg || insn->imm) { + verbose(env, "invalid may_goto imm %d\n", insn->imm); return -EINVAL; } prev_st = find_prev_entry(env, cur_st->parent, idx); @@ -15675,7 +16050,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, *insn_idx)) return -EFAULT; if (env->log.level & BPF_LOG_LEVEL) - print_insn_state(env, this_branch->frame[this_branch->curframe]); + print_insn_state(env, this_branch, this_branch->curframe); *insn_idx += insn->off; return 0; } else if (pred == 0) { @@ -15689,7 +16064,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, *insn_idx)) return -EFAULT; if (env->log.level & BPF_LOG_LEVEL) - print_insn_state(env, this_branch->frame[this_branch->curframe]); + print_insn_state(env, this_branch, this_branch->curframe); return 0; } @@ -15806,7 +16181,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) - print_insn_state(env, this_branch->frame[this_branch->curframe]); + print_insn_state(env, this_branch, this_branch->curframe); return 0; } @@ -17734,6 +18109,12 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) return false; break; + case STACK_IRQ_FLAG: + old_reg = &old->stack[spi].spilled_ptr; + cur_reg = &cur->stack[spi].spilled_ptr; + if (!check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) + return false; + break; case STACK_MISC: case STACK_ZERO: case STACK_INVALID: @@ -17746,7 +18127,7 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, return true; } -static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur, +static bool refsafe(struct bpf_verifier_state *old, struct bpf_verifier_state *cur, struct bpf_idmap *idmap) { int i; @@ -17754,12 +18135,25 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur, if (old->acquired_refs != cur->acquired_refs) return false; + if (old->active_locks != cur->active_locks) + return false; + + if (old->active_preempt_locks != cur->active_preempt_locks) + return false; + + if (old->active_rcu_lock != cur->active_rcu_lock) + return false; + + if (!check_ids(old->active_irq_id, cur->active_irq_id, idmap)) + return false; + for (i = 0; i < old->acquired_refs; i++) { if (!check_ids(old->refs[i].id, cur->refs[i].id, idmap) || old->refs[i].type != cur->refs[i].type) return false; switch (old->refs[i].type) { case REF_TYPE_PTR: + case REF_TYPE_IRQ: break; case REF_TYPE_LOCK: if (old->refs[i].ptr != cur->refs[i].ptr) @@ -17816,9 +18210,6 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat if (!stacksafe(env, old, cur, &env->idmap_scratch, exact)) return false; - if (!refsafe(old, cur, &env->idmap_scratch)) - return false; - return true; } @@ -17846,15 +18237,12 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->speculative && !cur->speculative) return false; - if (old->active_rcu_lock != cur->active_rcu_lock) - return false; - - if (old->active_preempt_lock != cur->active_preempt_lock) - return false; - if (old->in_sleepable != cur->in_sleepable) return false; + if (!refsafe(old, cur, &env->idmap_scratch)) + return false; + /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ @@ -18245,9 +18633,9 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); verbose(env, "cur state:"); - print_verifier_state(env, cur->frame[cur->curframe], true); + print_verifier_state(env, cur, cur->curframe, true); verbose(env, "old state:"); - print_verifier_state(env, sl->state.frame[cur->curframe], true); + print_verifier_state(env, &sl->state, cur->curframe, true); return -EINVAL; } /* if the verifier is processing a loop, avoid adding new state @@ -18603,7 +18991,7 @@ static int do_check(struct bpf_verifier_env *env) env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); - print_verifier_state(env, state->frame[state->curframe], true); + print_verifier_state(env, state, state->curframe, true); do_print_state = false; } @@ -18615,7 +19003,7 @@ static int do_check(struct bpf_verifier_env *env) }; if (verifier_state_scratched(env)) - print_insn_state(env, state->frame[state->curframe]); + print_insn_state(env, state, state->curframe); verbose_linfo(env, env->insn_idx, "; "); env->prev_log_pos = env->log.end_pos; @@ -18747,10 +19135,10 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - if (cur_func(env)->active_locks) { + if (env->cur_state->active_locks) { if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock) || (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && - (insn->off != 0 || !is_bpf_graph_api_kfunc(insn->imm)))) { + (insn->off != 0 || !kfunc_spin_allowed(insn->imm)))) { verbose(env, "function calls are not allowed while holding a lock\n"); return -EINVAL; } @@ -18803,7 +19191,7 @@ process_bpf_exit_full: * match caller reference state when it exits. */ err = check_resource_leak(env, exception_exit, !env->cur_state->curframe, - "BPF_EXIT instruction"); + "BPF_EXIT instruction in main prog"); if (err) return err; @@ -18910,50 +19298,68 @@ static int find_btf_percpu_datasec(struct btf *btf) return -ENOENT; } +/* + * Add btf to the used_btfs array and return the index. (If the btf was + * already added, then just return the index.) Upon successful insertion + * increase btf refcnt, and, if present, also refcount the corresponding + * kernel module. + */ +static int __add_used_btf(struct bpf_verifier_env *env, struct btf *btf) +{ + struct btf_mod_pair *btf_mod; + int i; + + /* check whether we recorded this BTF (and maybe module) already */ + for (i = 0; i < env->used_btf_cnt; i++) + if (env->used_btfs[i].btf == btf) + return i; + + if (env->used_btf_cnt >= MAX_USED_BTFS) + return -E2BIG; + + btf_get(btf); + + btf_mod = &env->used_btfs[env->used_btf_cnt]; + btf_mod->btf = btf; + btf_mod->module = NULL; + + /* if we reference variables from kernel module, bump its refcount */ + if (btf_is_module(btf)) { + btf_mod->module = btf_try_get_module(btf); + if (!btf_mod->module) { + btf_put(btf); + return -ENXIO; + } + } + + return env->used_btf_cnt++; +} + /* replace pseudo btf_id with kernel symbol address */ -static int check_pseudo_btf_id(struct bpf_verifier_env *env, - struct bpf_insn *insn, - struct bpf_insn_aux_data *aux) +static int __check_pseudo_btf_id(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct bpf_insn_aux_data *aux, + struct btf *btf) { const struct btf_var_secinfo *vsi; const struct btf_type *datasec; - struct btf_mod_pair *btf_mod; const struct btf_type *t; const char *sym_name; bool percpu = false; u32 type, id = insn->imm; - struct btf *btf; s32 datasec_id; u64 addr; - int i, btf_fd, err; - - btf_fd = insn[1].imm; - if (btf_fd) { - btf = btf_get_by_fd(btf_fd); - if (IS_ERR(btf)) { - verbose(env, "invalid module BTF object FD specified.\n"); - return -EINVAL; - } - } else { - if (!btf_vmlinux) { - verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n"); - return -EINVAL; - } - btf = btf_vmlinux; - btf_get(btf); - } + int i; t = btf_type_by_id(btf, id); if (!t) { verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id); - err = -ENOENT; - goto err_put; + return -ENOENT; } if (!btf_type_is_var(t) && !btf_type_is_func(t)) { verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR or KIND_FUNC\n", id); - err = -EINVAL; - goto err_put; + return -EINVAL; } sym_name = btf_name_by_offset(btf, t->name_off); @@ -18961,8 +19367,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, if (!addr) { verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n", sym_name); - err = -ENOENT; - goto err_put; + return -ENOENT; } insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; @@ -18970,7 +19375,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, if (btf_type_is_func(t)) { aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; aux->btf_var.mem_size = 0; - goto check_btf; + return 0; } datasec_id = find_btf_percpu_datasec(btf); @@ -19001,8 +19406,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, tname = btf_name_by_offset(btf, t->name_off); verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); - err = -EINVAL; - goto err_put; + return -EINVAL; } aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; aux->btf_var.mem_size = tsize; @@ -19011,39 +19415,43 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, aux->btf_var.btf = btf; aux->btf_var.btf_id = type; } -check_btf: - /* check whether we recorded this BTF (and maybe module) already */ - for (i = 0; i < env->used_btf_cnt; i++) { - if (env->used_btfs[i].btf == btf) { - btf_put(btf); - return 0; - } - } - - if (env->used_btf_cnt >= MAX_USED_BTFS) { - err = -E2BIG; - goto err_put; - } - - btf_mod = &env->used_btfs[env->used_btf_cnt]; - btf_mod->btf = btf; - btf_mod->module = NULL; - - /* if we reference variables from kernel module, bump its refcount */ - if (btf_is_module(btf)) { - btf_mod->module = btf_try_get_module(btf); - if (!btf_mod->module) { - err = -ENXIO; - goto err_put; - } - } - - env->used_btf_cnt++; return 0; -err_put: - btf_put(btf); - return err; +} + +static int check_pseudo_btf_id(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct bpf_insn_aux_data *aux) +{ + struct btf *btf; + int btf_fd; + int err; + + btf_fd = insn[1].imm; + if (btf_fd) { + CLASS(fd, f)(btf_fd); + + btf = __btf_get_by_fd(f); + if (IS_ERR(btf)) { + verbose(env, "invalid module BTF object FD specified.\n"); + return -EINVAL; + } + } else { + if (!btf_vmlinux) { + verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n"); + return -EINVAL; + } + btf = btf_vmlinux; + } + + err = __check_pseudo_btf_id(env, insn, aux, btf); + if (err) + return err; + + err = __add_used_btf(env, btf); + if (err < 0) + return err; + return 0; } static bool is_tracing_prog_type(enum bpf_prog_type type) @@ -19060,6 +19468,12 @@ static bool is_tracing_prog_type(enum bpf_prog_type type) } } +static bool bpf_map_is_cgroup_storage(struct bpf_map *map) +{ + return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); +} + static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) @@ -19138,39 +19552,47 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } + if (bpf_map_is_cgroup_storage(map) && + bpf_cgroup_storage_assign(env->prog->aux, map)) { + verbose(env, "only one cgroup storage of each type is allowed\n"); + return -EBUSY; + } + + if (map->map_type == BPF_MAP_TYPE_ARENA) { + if (env->prog->aux->arena) { + verbose(env, "Only one arena per program\n"); + return -EBUSY; + } + if (!env->allow_ptr_leaks || !env->bpf_capable) { + verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n"); + return -EPERM; + } + if (!env->prog->jit_requested) { + verbose(env, "JIT is required to use arena\n"); + return -EOPNOTSUPP; + } + if (!bpf_jit_supports_arena()) { + verbose(env, "JIT doesn't support arena\n"); + return -EOPNOTSUPP; + } + env->prog->aux->arena = (void *)map; + if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) { + verbose(env, "arena's user address must be set via map_extra or mmap()\n"); + return -EINVAL; + } + } + return 0; } -static bool bpf_map_is_cgroup_storage(struct bpf_map *map) +static int __add_used_map(struct bpf_verifier_env *env, struct bpf_map *map) { - return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || - map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); -} - -/* Add map behind fd to used maps list, if it's not already there, and return - * its index. Also set *reused to true if this map was already in the list of - * used maps. - * Returns <0 on error, or >= 0 index, on success. - */ -static int add_used_map_from_fd(struct bpf_verifier_env *env, int fd, bool *reused) -{ - CLASS(fd, f)(fd); - struct bpf_map *map; - int i; - - map = __bpf_map_get(f); - if (IS_ERR(map)) { - verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); - return PTR_ERR(map); - } + int i, err; /* check whether we recorded this map already */ - for (i = 0; i < env->used_map_cnt; i++) { - if (env->used_maps[i] == map) { - *reused = true; + for (i = 0; i < env->used_map_cnt; i++) + if (env->used_maps[i] == map) return i; - } - } if (env->used_map_cnt >= MAX_USED_MAPS) { verbose(env, "The total number of maps per program has reached the limit of %u\n", @@ -19178,6 +19600,10 @@ static int add_used_map_from_fd(struct bpf_verifier_env *env, int fd, bool *reus return -E2BIG; } + err = check_map_prog_compatibility(env, map, env->prog); + if (err) + return err; + if (env->prog->sleepable) atomic64_inc(&map->sleepable_refcnt); @@ -19188,12 +19614,29 @@ static int add_used_map_from_fd(struct bpf_verifier_env *env, int fd, bool *reus */ bpf_map_inc(map); - *reused = false; env->used_maps[env->used_map_cnt++] = map; return env->used_map_cnt - 1; } +/* Add map behind fd to used maps list, if it's not already there, and return + * its index. + * Returns <0 on error, or >= 0 index, on success. + */ +static int add_used_map(struct bpf_verifier_env *env, int fd) +{ + struct bpf_map *map; + CLASS(fd, f)(fd); + + map = __bpf_map_get(f); + if (IS_ERR(map)) { + verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); + return PTR_ERR(map); + } + + return __add_used_map(env, map); +} + /* find and rewrite pseudo imm in ld_imm64 instructions: * * 1. if it accesses map FD, replace it with actual map pointer. @@ -19225,7 +19668,6 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) int map_idx; u64 addr; u32 fd; - bool reused; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || @@ -19286,7 +19728,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) break; } - map_idx = add_used_map_from_fd(env, fd, &reused); + map_idx = add_used_map(env, fd); if (map_idx < 0) return map_idx; map = env->used_maps[map_idx]; @@ -19294,10 +19736,6 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) aux = &env->insn_aux_data[i]; aux->map_index = map_idx; - err = check_map_prog_compatibility(env, map, env->prog); - if (err) - return err; - if (insn[0].src_reg == BPF_PSEUDO_MAP_FD || insn[0].src_reg == BPF_PSEUDO_MAP_IDX) { addr = (unsigned long)map; @@ -19328,39 +19766,6 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; - /* proceed with extra checks only if its newly added used map */ - if (reused) - goto next_insn; - - if (bpf_map_is_cgroup_storage(map) && - bpf_cgroup_storage_assign(env->prog->aux, map)) { - verbose(env, "only one cgroup storage of each type is allowed\n"); - return -EBUSY; - } - if (map->map_type == BPF_MAP_TYPE_ARENA) { - if (env->prog->aux->arena) { - verbose(env, "Only one arena per program\n"); - return -EBUSY; - } - if (!env->allow_ptr_leaks || !env->bpf_capable) { - verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n"); - return -EPERM; - } - if (!env->prog->jit_requested) { - verbose(env, "JIT is required to use arena\n"); - return -EOPNOTSUPP; - } - if (!bpf_jit_supports_arena()) { - verbose(env, "JIT doesn't support arena\n"); - return -EOPNOTSUPP; - } - env->prog->aux->arena = (void *)map; - if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) { - verbose(env, "arena's user address must be set via map_extra or mmap()\n"); - return -EINVAL; - } - } - next_insn: insn++; i++; @@ -19779,23 +20184,28 @@ static int opt_remove_dead_code(struct bpf_verifier_env *env) } static const struct bpf_insn NOP = BPF_JMP_IMM(BPF_JA, 0, 0, 0); +static const struct bpf_insn MAY_GOTO_0 = BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0, 0); static int opt_remove_nops(struct bpf_verifier_env *env) { - const struct bpf_insn ja = NOP; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; + bool is_may_goto_0, is_ja; int i, err; for (i = 0; i < insn_cnt; i++) { - if (memcmp(&insn[i], &ja, sizeof(ja))) + is_may_goto_0 = !memcmp(&insn[i], &MAY_GOTO_0, sizeof(MAY_GOTO_0)); + is_ja = !memcmp(&insn[i], &NOP, sizeof(NOP)); + + if (!is_may_goto_0 && !is_ja) continue; err = verifier_remove_insns(env, i, 1); if (err) return err; insn_cnt--; - i--; + /* Go back one insn to catch may_goto +1; may_goto +0 sequence */ + i -= (is_may_goto_0 && i > 0) ? 2 : 1; } return 0; @@ -21281,11 +21691,15 @@ patch_map_ops_generic: * changed in some incompatible and hard to support * way, it's fine to back out this inlining logic */ +#ifdef CONFIG_SMP insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number); insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0); cnt = 3; - +#else + insn_buf[0] = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); + cnt = 1; +#endif new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; @@ -22540,6 +22954,73 @@ struct btf *bpf_get_btf_vmlinux(void) return btf_vmlinux; } +/* + * The add_fd_from_fd_array() is executed only if fd_array_cnt is non-zero. In + * this case expect that every file descriptor in the array is either a map or + * a BTF. Everything else is considered to be trash. + */ +static int add_fd_from_fd_array(struct bpf_verifier_env *env, int fd) +{ + struct bpf_map *map; + struct btf *btf; + CLASS(fd, f)(fd); + int err; + + map = __bpf_map_get(f); + if (!IS_ERR(map)) { + err = __add_used_map(env, map); + if (err < 0) + return err; + return 0; + } + + btf = __btf_get_by_fd(f); + if (!IS_ERR(btf)) { + err = __add_used_btf(env, btf); + if (err < 0) + return err; + return 0; + } + + verbose(env, "fd %d is not pointing to valid bpf_map or btf\n", fd); + return PTR_ERR(map); +} + +static int process_fd_array(struct bpf_verifier_env *env, union bpf_attr *attr, bpfptr_t uattr) +{ + size_t size = sizeof(int); + int ret; + int fd; + u32 i; + + env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); + + /* + * The only difference between old (no fd_array_cnt is given) and new + * APIs is that in the latter case the fd_array is expected to be + * continuous and is scanned for map fds right away + */ + if (!attr->fd_array_cnt) + return 0; + + /* Check for integer overflow */ + if (attr->fd_array_cnt >= (U32_MAX / size)) { + verbose(env, "fd_array_cnt is too big (%u)\n", attr->fd_array_cnt); + return -EINVAL; + } + + for (i = 0; i < attr->fd_array_cnt; i++) { + if (copy_from_bpfptr_offset(&fd, env->fd_array, i * size, size)) + return -EFAULT; + + ret = add_fd_from_fd_array(env, fd); + if (ret) + return ret; + } + + return 0; +} + int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { u64 start_time = ktime_get_ns(); @@ -22571,7 +23052,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; - env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); @@ -22594,6 +23074,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (ret) goto err_unlock; + ret = process_fd_array(env, attr, uattr); + if (ret) + goto skip_full_check; + mark_verifier_state_clean(env); if (IS_ERR(btf_vmlinux)) { diff --git a/kernel/capability.c b/kernel/capability.c index dac4df77e376..e089d2628c29 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -38,10 +38,8 @@ __setup("no_file_caps", file_caps_disable); static void warn_legacy_capability_use(void) { - char name[sizeof(current->comm)]; - pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", - get_task_comm(name, current)); + current->comm); } /* @@ -62,10 +60,8 @@ static void warn_legacy_capability_use(void) static void warn_deprecated_v2(void) { - char name[sizeof(current->comm)]; - pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", - get_task_comm(name, current)); + current->comm); } /* diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile index a5c9359d516f..ede31601a363 100644 --- a/kernel/cgroup/Makefile +++ b/kernel/cgroup/Makefile @@ -7,4 +7,5 @@ obj-$(CONFIG_CGROUP_RDMA) += rdma.o obj-$(CONFIG_CPUSETS) += cpuset.o obj-$(CONFIG_CPUSETS_V1) += cpuset-v1.o obj-$(CONFIG_CGROUP_MISC) += misc.o +obj-$(CONFIG_CGROUP_DMEM) += dmem.o obj-$(CONFIG_CGROUP_DEBUG) += debug.o diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index f321ed515f3a..0f910c828973 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -197,10 +197,8 @@ static struct cpuset top_cpuset = { /* * There are two global locks guarding cpuset structures - cpuset_mutex and - * callback_lock. We also require taking task_lock() when dereferencing a - * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems - * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset + * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel + * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset * structures. Note that cpuset_mutex needs to be a mutex as it is used in * paths that rely on priority inheritance (e.g. scheduler - on RT) for * correctness. @@ -229,9 +227,6 @@ static struct cpuset top_cpuset = { * The cpuset_common_seq_show() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. - * - * Accessing a task's cpuset should be done in accordance with the - * guidelines for accessing subsystem state in kernel/cgroup.c */ static DEFINE_MUTEX(cpuset_mutex); @@ -890,7 +885,15 @@ v2: */ if (cgrpv2) { for (i = 0; i < ndoms; i++) { - cpumask_copy(doms[i], csa[i]->effective_cpus); + /* + * The top cpuset may contain some boot time isolated + * CPUs that need to be excluded from the sched domain. + */ + if (csa[i] == &top_cpuset) + cpumask_and(doms[i], csa[i]->effective_cpus, + housekeeping_cpumask(HK_TYPE_DOMAIN)); + else + cpumask_copy(doms[i], csa[i]->effective_cpus); if (dattr) dattr[i] = SD_ATTR_INIT; } @@ -3121,29 +3124,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, int retval = -ENODEV; buf = strstrip(buf); - - /* - * CPU or memory hotunplug may leave @cs w/o any execution - * resources, in which case the hotplug code asynchronously updates - * configuration and transfers all tasks to the nearest ancestor - * which can execute. - * - * As writes to "cpus" or "mems" may restore @cs's execution - * resources, wait for the previously scheduled operations before - * proceeding, so that we don't end up keep removing tasks added - * after execution capability is restored. - * - * cpuset_handle_hotplug may call back into cgroup core asynchronously - * via cgroup_transfer_tasks() and waiting for it from a cgroupfs - * operation like this one can lead to a deadlock through kernfs - * active_ref protection. Let's break the protection. Losing the - * protection is okay as we check whether @cs is online after - * grabbing cpuset_mutex anyway. This only happens on the legacy - * hierarchies. - */ - css_get(&cs->css); - kernfs_break_active_protection(of->kn); - cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) @@ -3176,8 +3156,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); - kernfs_unbreak_active_protection(of->kn); - css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c new file mode 100644 index 000000000000..fbe34299673d --- /dev/null +++ b/kernel/cgroup/dmem.c @@ -0,0 +1,857 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2023-2024 Intel Corporation (Maarten Lankhorst ) + * Copyright 2024 Red Hat (Maxime Ripard ) + * Partially based on the rdma and misc controllers, which bear the following copyrights: + * + * Copyright 2020 Google LLC + * Copyright (C) 2016 Parav Pandit + */ + +#include +#include +#include +#include +#include +#include +#include + +struct dmem_cgroup_region { + /** + * @ref: References keeping the region alive. + * Keeps the region reference alive after a succesful RCU lookup. + */ + struct kref ref; + + /** @rcu: RCU head for freeing */ + struct rcu_head rcu; + + /** + * @region_node: Linked into &dmem_cgroup_regions list. + * Protected by RCU and global spinlock. + */ + struct list_head region_node; + + /** + * @pools: List of pools linked to this region. + * Protected by global spinlock only + */ + struct list_head pools; + + /** @size: Size of region, in bytes */ + u64 size; + + /** @name: Name describing the node, set by dmem_cgroup_register_region */ + char *name; + + /** + * @unregistered: Whether the region is unregistered by its caller. + * No new pools should be added to the region afterwards. + */ + bool unregistered; +}; + +struct dmemcg_state { + struct cgroup_subsys_state css; + + struct list_head pools; +}; + +struct dmem_cgroup_pool_state { + struct dmem_cgroup_region *region; + struct dmemcg_state *cs; + + /* css node, RCU protected against region teardown */ + struct list_head css_node; + + /* dev node, no RCU protection required */ + struct list_head region_node; + + struct rcu_head rcu; + + struct page_counter cnt; + + bool inited; +}; + +/* + * 3 operations require locking protection: + * - Registering and unregistering region to/from list, requires global lock. + * - Adding a dmem_cgroup_pool_state to a CSS, removing when CSS is freed. + * - Adding a dmem_cgroup_pool_state to a region list. + * + * Since for the most common operations RCU provides enough protection, I + * do not think more granular locking makes sense. Most protection is offered + * by RCU and the lockless operating page_counter. + */ +static DEFINE_SPINLOCK(dmemcg_lock); +static LIST_HEAD(dmem_cgroup_regions); + +static inline struct dmemcg_state * +css_to_dmemcs(struct cgroup_subsys_state *css) +{ + return container_of(css, struct dmemcg_state, css); +} + +static inline struct dmemcg_state *get_current_dmemcs(void) +{ + return css_to_dmemcs(task_get_css(current, dmem_cgrp_id)); +} + +static struct dmemcg_state *parent_dmemcs(struct dmemcg_state *cg) +{ + return cg->css.parent ? css_to_dmemcs(cg->css.parent) : NULL; +} + +static void free_cg_pool(struct dmem_cgroup_pool_state *pool) +{ + list_del(&pool->region_node); + kfree(pool); +} + +static void +set_resource_min(struct dmem_cgroup_pool_state *pool, u64 val) +{ + page_counter_set_min(&pool->cnt, val); +} + +static void +set_resource_low(struct dmem_cgroup_pool_state *pool, u64 val) +{ + page_counter_set_low(&pool->cnt, val); +} + +static void +set_resource_max(struct dmem_cgroup_pool_state *pool, u64 val) +{ + page_counter_set_max(&pool->cnt, val); +} + +static u64 get_resource_low(struct dmem_cgroup_pool_state *pool) +{ + return pool ? READ_ONCE(pool->cnt.low) : 0; +} + +static u64 get_resource_min(struct dmem_cgroup_pool_state *pool) +{ + return pool ? READ_ONCE(pool->cnt.min) : 0; +} + +static u64 get_resource_max(struct dmem_cgroup_pool_state *pool) +{ + return pool ? READ_ONCE(pool->cnt.max) : PAGE_COUNTER_MAX; +} + +static u64 get_resource_current(struct dmem_cgroup_pool_state *pool) +{ + return pool ? page_counter_read(&pool->cnt) : 0; +} + +static void reset_all_resource_limits(struct dmem_cgroup_pool_state *rpool) +{ + set_resource_min(rpool, 0); + set_resource_low(rpool, 0); + set_resource_max(rpool, PAGE_COUNTER_MAX); +} + +static void dmemcs_offline(struct cgroup_subsys_state *css) +{ + struct dmemcg_state *dmemcs = css_to_dmemcs(css); + struct dmem_cgroup_pool_state *pool; + + rcu_read_lock(); + list_for_each_entry_rcu(pool, &dmemcs->pools, css_node) + reset_all_resource_limits(pool); + rcu_read_unlock(); +} + +static void dmemcs_free(struct cgroup_subsys_state *css) +{ + struct dmemcg_state *dmemcs = css_to_dmemcs(css); + struct dmem_cgroup_pool_state *pool, *next; + + spin_lock(&dmemcg_lock); + list_for_each_entry_safe(pool, next, &dmemcs->pools, css_node) { + /* + *The pool is dead and all references are 0, + * no need for RCU protection with list_del_rcu or freeing. + */ + list_del(&pool->css_node); + free_cg_pool(pool); + } + spin_unlock(&dmemcg_lock); + + kfree(dmemcs); +} + +static struct cgroup_subsys_state * +dmemcs_alloc(struct cgroup_subsys_state *parent_css) +{ + struct dmemcg_state *dmemcs = kzalloc(sizeof(*dmemcs), GFP_KERNEL); + if (!dmemcs) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&dmemcs->pools); + return &dmemcs->css; +} + +static struct dmem_cgroup_pool_state * +find_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region) +{ + struct dmem_cgroup_pool_state *pool; + + list_for_each_entry_rcu(pool, &dmemcs->pools, css_node, spin_is_locked(&dmemcg_lock)) + if (pool->region == region) + return pool; + + return NULL; +} + +static struct dmem_cgroup_pool_state *pool_parent(struct dmem_cgroup_pool_state *pool) +{ + if (!pool->cnt.parent) + return NULL; + + return container_of(pool->cnt.parent, typeof(*pool), cnt); +} + +static void +dmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool, + struct dmem_cgroup_pool_state *test_pool) +{ + struct page_counter *climit; + struct cgroup_subsys_state *css, *next_css; + struct dmemcg_state *dmemcg_iter; + struct dmem_cgroup_pool_state *pool, *parent_pool; + bool found_descendant; + + climit = &limit_pool->cnt; + + rcu_read_lock(); + parent_pool = pool = limit_pool; + css = &limit_pool->cs->css; + + /* + * This logic is roughly equivalent to css_foreach_descendant_pre, + * except we also track the parent pool to find out which pool we need + * to calculate protection values for. + * + * We can stop the traversal once we find test_pool among the + * descendants since we don't really care about any others. + */ + while (pool != test_pool) { + next_css = css_next_child(NULL, css); + if (next_css) { + parent_pool = pool; + } else { + while (css != &limit_pool->cs->css) { + next_css = css_next_child(css, css->parent); + if (next_css) + break; + css = css->parent; + parent_pool = pool_parent(parent_pool); + } + /* + * We can only hit this when test_pool is not a + * descendant of limit_pool. + */ + if (WARN_ON_ONCE(css == &limit_pool->cs->css)) + break; + } + css = next_css; + + found_descendant = false; + dmemcg_iter = container_of(css, struct dmemcg_state, css); + + list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) { + if (pool_parent(pool) == parent_pool) { + found_descendant = true; + break; + } + } + if (!found_descendant) + continue; + + page_counter_calculate_protection( + climit, &pool->cnt, true); + } + rcu_read_unlock(); +} + +/** + * dmem_cgroup_state_evict_valuable() - Check if we should evict from test_pool + * @limit_pool: The pool for which we hit limits + * @test_pool: The pool for which to test + * @ignore_low: Whether we have to respect low watermarks. + * @ret_hit_low: Pointer to whether it makes sense to consider low watermark. + * + * This function returns true if we can evict from @test_pool, false if not. + * When returning false and @ignore_low is false, @ret_hit_low may + * be set to true to indicate this function can be retried with @ignore_low + * set to true. + * + * Return: bool + */ +bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool, + struct dmem_cgroup_pool_state *test_pool, + bool ignore_low, bool *ret_hit_low) +{ + struct dmem_cgroup_pool_state *pool = test_pool; + struct page_counter *ctest; + u64 used, min, low; + + /* Can always evict from current pool, despite limits */ + if (limit_pool == test_pool) + return true; + + if (limit_pool) { + if (!parent_dmemcs(limit_pool->cs)) + return true; + + for (pool = test_pool; pool && limit_pool != pool; pool = pool_parent(pool)) + {} + + if (!pool) + return false; + } else { + /* + * If there is no cgroup limiting memory usage, use the root + * cgroup instead for limit calculations. + */ + for (limit_pool = test_pool; pool_parent(limit_pool); limit_pool = pool_parent(limit_pool)) + {} + } + + ctest = &test_pool->cnt; + + dmem_cgroup_calculate_protection(limit_pool, test_pool); + + used = page_counter_read(ctest); + min = READ_ONCE(ctest->emin); + + if (used <= min) + return false; + + if (!ignore_low) { + low = READ_ONCE(ctest->elow); + if (used > low) + return true; + + *ret_hit_low = true; + return false; + } + return true; +} +EXPORT_SYMBOL_GPL(dmem_cgroup_state_evict_valuable); + +static struct dmem_cgroup_pool_state * +alloc_pool_single(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region, + struct dmem_cgroup_pool_state **allocpool) +{ + struct dmemcg_state *parent = parent_dmemcs(dmemcs); + struct dmem_cgroup_pool_state *pool, *ppool = NULL; + + if (!*allocpool) { + pool = kzalloc(sizeof(*pool), GFP_NOWAIT); + if (!pool) + return ERR_PTR(-ENOMEM); + } else { + pool = *allocpool; + *allocpool = NULL; + } + + pool->region = region; + pool->cs = dmemcs; + + if (parent) + ppool = find_cg_pool_locked(parent, region); + + page_counter_init(&pool->cnt, + ppool ? &ppool->cnt : NULL, true); + reset_all_resource_limits(pool); + + list_add_tail_rcu(&pool->css_node, &dmemcs->pools); + list_add_tail(&pool->region_node, ®ion->pools); + + if (!parent) + pool->inited = true; + else + pool->inited = ppool ? ppool->inited : false; + return pool; +} + +static struct dmem_cgroup_pool_state * +get_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region, + struct dmem_cgroup_pool_state **allocpool) +{ + struct dmem_cgroup_pool_state *pool, *ppool, *retpool; + struct dmemcg_state *p, *pp; + + /* + * Recursively create pool, we may not initialize yet on + * recursion, this is done as a separate step. + */ + for (p = dmemcs; p; p = parent_dmemcs(p)) { + pool = find_cg_pool_locked(p, region); + if (!pool) + pool = alloc_pool_single(p, region, allocpool); + + if (IS_ERR(pool)) + return pool; + + if (p == dmemcs && pool->inited) + return pool; + + if (pool->inited) + break; + } + + retpool = pool = find_cg_pool_locked(dmemcs, region); + for (p = dmemcs, pp = parent_dmemcs(dmemcs); pp; p = pp, pp = parent_dmemcs(p)) { + if (pool->inited) + break; + + /* ppool was created if it didn't exist by above loop. */ + ppool = find_cg_pool_locked(pp, region); + + /* Fix up parent links, mark as inited. */ + pool->cnt.parent = &ppool->cnt; + pool->inited = true; + + pool = ppool; + } + + return retpool; +} + +static void dmemcg_free_rcu(struct rcu_head *rcu) +{ + struct dmem_cgroup_region *region = container_of(rcu, typeof(*region), rcu); + struct dmem_cgroup_pool_state *pool, *next; + + list_for_each_entry_safe(pool, next, ®ion->pools, region_node) + free_cg_pool(pool); + kfree(region->name); + kfree(region); +} + +static void dmemcg_free_region(struct kref *ref) +{ + struct dmem_cgroup_region *cgregion = container_of(ref, typeof(*cgregion), ref); + + call_rcu(&cgregion->rcu, dmemcg_free_rcu); +} + +/** + * dmem_cgroup_unregister_region() - Unregister a previously registered region. + * @region: The region to unregister. + * + * This function undoes dmem_cgroup_register_region. + */ +void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) +{ + struct list_head *entry; + + if (!region) + return; + + spin_lock(&dmemcg_lock); + + /* Remove from global region list */ + list_del_rcu(®ion->region_node); + + list_for_each_rcu(entry, ®ion->pools) { + struct dmem_cgroup_pool_state *pool = + container_of(entry, typeof(*pool), region_node); + + list_del_rcu(&pool->css_node); + } + + /* + * Ensure any RCU based lookups fail. Additionally, + * no new pools should be added to the dead region + * by get_cg_pool_unlocked. + */ + region->unregistered = true; + spin_unlock(&dmemcg_lock); + + kref_put(®ion->ref, dmemcg_free_region); +} +EXPORT_SYMBOL_GPL(dmem_cgroup_unregister_region); + +/** + * dmem_cgroup_register_region() - Register a regions for dev cgroup. + * @size: Size of region to register, in bytes. + * @fmt: Region parameters to register + * + * This function registers a node in the dmem cgroup with the + * name given. After calling this function, the region can be + * used for allocations. + * + * Return: NULL or a struct on success, PTR_ERR on failure. + */ +struct dmem_cgroup_region *dmem_cgroup_register_region(u64 size, const char *fmt, ...) +{ + struct dmem_cgroup_region *ret; + char *region_name; + va_list ap; + + if (!size) + return NULL; + + va_start(ap, fmt); + region_name = kvasprintf(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!region_name) + return ERR_PTR(-ENOMEM); + + ret = kzalloc(sizeof(*ret), GFP_KERNEL); + if (!ret) { + kfree(region_name); + return ERR_PTR(-ENOMEM); + } + + INIT_LIST_HEAD(&ret->pools); + ret->name = region_name; + ret->size = size; + kref_init(&ret->ref); + + spin_lock(&dmemcg_lock); + list_add_tail_rcu(&ret->region_node, &dmem_cgroup_regions); + spin_unlock(&dmemcg_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(dmem_cgroup_register_region); + +static struct dmem_cgroup_region *dmemcg_get_region_by_name(const char *name) +{ + struct dmem_cgroup_region *region; + + list_for_each_entry_rcu(region, &dmem_cgroup_regions, region_node, spin_is_locked(&dmemcg_lock)) + if (!strcmp(name, region->name) && + kref_get_unless_zero(®ion->ref)) + return region; + + return NULL; +} + +/** + * dmem_cgroup_pool_state_put() - Drop a reference to a dmem_cgroup_pool_state + * @pool: &dmem_cgroup_pool_state + * + * Called to drop a reference to the limiting pool returned by + * dmem_cgroup_try_charge(). + */ +void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool) +{ + if (pool) + css_put(&pool->cs->css); +} +EXPORT_SYMBOL_GPL(dmem_cgroup_pool_state_put); + +static struct dmem_cgroup_pool_state * +get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region) +{ + struct dmem_cgroup_pool_state *pool, *allocpool = NULL; + + /* fastpath lookup? */ + rcu_read_lock(); + pool = find_cg_pool_locked(cg, region); + if (pool && !READ_ONCE(pool->inited)) + pool = NULL; + rcu_read_unlock(); + + while (!pool) { + spin_lock(&dmemcg_lock); + if (!region->unregistered) + pool = get_cg_pool_locked(cg, region, &allocpool); + else + pool = ERR_PTR(-ENODEV); + spin_unlock(&dmemcg_lock); + + if (pool == ERR_PTR(-ENOMEM)) { + pool = NULL; + if (WARN_ON(allocpool)) + continue; + + allocpool = kzalloc(sizeof(*allocpool), GFP_KERNEL); + if (allocpool) { + pool = NULL; + continue; + } + } + } + + kfree(allocpool); + return pool; +} + +/** + * dmem_cgroup_uncharge() - Uncharge a pool. + * @pool: Pool to uncharge. + * @size: Size to uncharge. + * + * Undoes the effects of dmem_cgroup_try_charge. + * Must be called with the returned pool as argument, + * and same @index and @size. + */ +void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size) +{ + if (!pool) + return; + + page_counter_uncharge(&pool->cnt, size); + css_put(&pool->cs->css); +} +EXPORT_SYMBOL_GPL(dmem_cgroup_uncharge); + +/** + * dmem_cgroup_try_charge() - Try charging a new allocation to a region. + * @region: dmem region to charge + * @size: Size (in bytes) to charge. + * @ret_pool: On succesfull allocation, the pool that is charged. + * @ret_limit_pool: On a failed allocation, the limiting pool. + * + * This function charges the @region region for a size of @size bytes. + * + * If the function succeeds, @ret_pool is set, which must be passed to + * dmem_cgroup_uncharge() when undoing the allocation. + * + * When this function fails with -EAGAIN and @ret_limit_pool is non-null, it + * will be set to the pool for which the limit is hit. This can be used for + * eviction as argument to dmem_cgroup_evict_valuable(). This reference must be freed + * with @dmem_cgroup_pool_state_put(). + * + * Return: 0 on success, -EAGAIN on hitting a limit, or a negative errno on failure. + */ +int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size, + struct dmem_cgroup_pool_state **ret_pool, + struct dmem_cgroup_pool_state **ret_limit_pool) +{ + struct dmemcg_state *cg; + struct dmem_cgroup_pool_state *pool; + struct page_counter *fail; + int ret; + + *ret_pool = NULL; + if (ret_limit_pool) + *ret_limit_pool = NULL; + + /* + * hold on to css, as cgroup can be removed but resource + * accounting happens on css. + */ + cg = get_current_dmemcs(); + + pool = get_cg_pool_unlocked(cg, region); + if (IS_ERR(pool)) { + ret = PTR_ERR(pool); + goto err; + } + + if (!page_counter_try_charge(&pool->cnt, size, &fail)) { + if (ret_limit_pool) { + *ret_limit_pool = container_of(fail, struct dmem_cgroup_pool_state, cnt); + css_get(&(*ret_limit_pool)->cs->css); + } + ret = -EAGAIN; + goto err; + } + + /* On success, reference from get_current_dmemcs is transferred to *ret_pool */ + *ret_pool = pool; + return 0; + +err: + css_put(&cg->css); + return ret; +} +EXPORT_SYMBOL_GPL(dmem_cgroup_try_charge); + +static int dmem_cgroup_region_capacity_show(struct seq_file *sf, void *v) +{ + struct dmem_cgroup_region *region; + + rcu_read_lock(); + list_for_each_entry_rcu(region, &dmem_cgroup_regions, region_node) { + seq_puts(sf, region->name); + seq_printf(sf, " %llu\n", region->size); + } + rcu_read_unlock(); + return 0; +} + +static int dmemcg_parse_limit(char *options, struct dmem_cgroup_region *region, + u64 *new_limit) +{ + char *end; + + if (!strcmp(options, "max")) { + *new_limit = PAGE_COUNTER_MAX; + return 0; + } + + *new_limit = memparse(options, &end); + if (*end != '\0') + return -EINVAL; + + return 0; +} + +static ssize_t dmemcg_limit_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off, + void (*apply)(struct dmem_cgroup_pool_state *, u64)) +{ + struct dmemcg_state *dmemcs = css_to_dmemcs(of_css(of)); + int err = 0; + + while (buf && !err) { + struct dmem_cgroup_pool_state *pool = NULL; + char *options, *region_name; + struct dmem_cgroup_region *region; + u64 new_limit; + + options = buf; + buf = strchr(buf, '\n'); + if (buf) + *buf++ = '\0'; + + options = strstrip(options); + + /* eat empty lines */ + if (!options[0]) + continue; + + region_name = strsep(&options, " \t"); + if (!region_name[0]) + continue; + + rcu_read_lock(); + region = dmemcg_get_region_by_name(region_name); + rcu_read_unlock(); + + if (!region) + return -EINVAL; + + err = dmemcg_parse_limit(options, region, &new_limit); + if (err < 0) + goto out_put; + + pool = get_cg_pool_unlocked(dmemcs, region); + if (IS_ERR(pool)) { + err = PTR_ERR(pool); + goto out_put; + } + + /* And commit */ + apply(pool, new_limit); + +out_put: + kref_put(®ion->ref, dmemcg_free_region); + } + + + return err ?: nbytes; +} + +static int dmemcg_limit_show(struct seq_file *sf, void *v, + u64 (*fn)(struct dmem_cgroup_pool_state *)) +{ + struct dmemcg_state *dmemcs = css_to_dmemcs(seq_css(sf)); + struct dmem_cgroup_region *region; + + rcu_read_lock(); + list_for_each_entry_rcu(region, &dmem_cgroup_regions, region_node) { + struct dmem_cgroup_pool_state *pool = find_cg_pool_locked(dmemcs, region); + u64 val; + + seq_puts(sf, region->name); + + val = fn(pool); + if (val < PAGE_COUNTER_MAX) + seq_printf(sf, " %lld\n", val); + else + seq_puts(sf, " max\n"); + } + rcu_read_unlock(); + + return 0; +} + +static int dmem_cgroup_region_current_show(struct seq_file *sf, void *v) +{ + return dmemcg_limit_show(sf, v, get_resource_current); +} + +static int dmem_cgroup_region_min_show(struct seq_file *sf, void *v) +{ + return dmemcg_limit_show(sf, v, get_resource_min); +} + +static ssize_t dmem_cgroup_region_min_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return dmemcg_limit_write(of, buf, nbytes, off, set_resource_min); +} + +static int dmem_cgroup_region_low_show(struct seq_file *sf, void *v) +{ + return dmemcg_limit_show(sf, v, get_resource_low); +} + +static ssize_t dmem_cgroup_region_low_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return dmemcg_limit_write(of, buf, nbytes, off, set_resource_low); +} + +static int dmem_cgroup_region_max_show(struct seq_file *sf, void *v) +{ + return dmemcg_limit_show(sf, v, get_resource_max); +} + +static ssize_t dmem_cgroup_region_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return dmemcg_limit_write(of, buf, nbytes, off, set_resource_max); +} + +static struct cftype files[] = { + { + .name = "capacity", + .seq_show = dmem_cgroup_region_capacity_show, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + { + .name = "current", + .seq_show = dmem_cgroup_region_current_show, + }, + { + .name = "min", + .write = dmem_cgroup_region_min_write, + .seq_show = dmem_cgroup_region_min_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "low", + .write = dmem_cgroup_region_low_write, + .seq_show = dmem_cgroup_region_low_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "max", + .write = dmem_cgroup_region_max_write, + .seq_show = dmem_cgroup_region_max_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { } /* Zero entry terminates. */ +}; + +struct cgroup_subsys dmem_cgrp_subsys = { + .css_alloc = dmemcs_alloc, + .css_free = dmemcs_free, + .css_offline = dmemcs_offline, + .legacy_cftypes = files, + .dfl_cftypes = files, +}; diff --git a/kernel/cpu.c b/kernel/cpu.c index b605334f8ee6..07455d25329c 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -905,12 +905,13 @@ static int finish_cpu(unsigned int cpu) struct mm_struct *mm = idle->active_mm; /* - * idle_task_exit() will have switched to &init_mm, now - * clean up any remaining active_mm state. + * sched_force_init_mm() ensured the use of &init_mm, + * drop that refcount now that the CPU has stopped. */ - if (mm != &init_mm) - idle->active_mm = &init_mm; + WARN_ON(mm != &init_mm); + idle->active_mm = NULL; mmdrop_lazy_tlb(mm); + return 0; } @@ -2179,7 +2180,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { }, [CPUHP_AP_HRTIMERS_DYING] = { .name = "hrtimers:dying", - .startup.single = NULL, + .startup.single = hrtimers_cpu_starting, .teardown.single = hrtimers_cpu_dying, }, [CPUHP_AP_TICK_DYING] = { @@ -3128,11 +3129,6 @@ void init_cpu_possible(const struct cpumask *src) cpumask_copy(&__cpu_possible_mask, src); } -void init_cpu_online(const struct cpumask *src) -{ - cpumask_copy(&__cpu_online_mask, src); -} - void set_cpu_online(unsigned int cpu, bool online) { /* diff --git a/kernel/cred.c b/kernel/cred.c index da7da250f7c8..9676965c0981 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -476,56 +476,6 @@ void abort_creds(struct cred *new) } EXPORT_SYMBOL(abort_creds); -/** - * override_creds - Override the current process's subjective credentials - * @new: The credentials to be assigned - * - * Install a set of temporary override subjective credentials on the current - * process, returning the old set for later reversion. - */ -const struct cred *override_creds(const struct cred *new) -{ - const struct cred *old; - - kdebug("override_creds(%p{%ld})", new, - atomic_long_read(&new->usage)); - - /* - * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'. - * - * That means that we do not clear the 'non_rcu' flag, since - * we are only installing the cred into the thread-synchronous - * '->cred' pointer, not the '->real_cred' pointer that is - * visible to other threads under RCU. - */ - get_new_cred((struct cred *)new); - old = override_creds_light(new); - - kdebug("override_creds() = %p{%ld}", old, - atomic_long_read(&old->usage)); - return old; -} -EXPORT_SYMBOL(override_creds); - -/** - * revert_creds - Revert a temporary subjective credentials override - * @old: The credentials to be restored - * - * Revert a temporary set of override subjective credentials to an old set, - * discarding the override set. - */ -void revert_creds(const struct cred *old) -{ - const struct cred *override = current->cred; - - kdebug("revert_creds(%p{%ld})", old, - atomic_long_read(&old->usage)); - - revert_creds_light(old); - put_cred(override); -} -EXPORT_SYMBOL(revert_creds); - /** * cred_fscmp - Compare two credentials with respect to filesystem access. * @a: The first credential diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 0a39497140bf..05b137e7dcb9 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -305,7 +305,7 @@ int kdb_putarea_size(unsigned long addr, void *res, size_t size) /* * kdb_getphys - Read data from a physical address. Validate the - * address is in range, use kmap_atomic() to get data + * address is in range, use kmap_local_page() to get data * similar to kdb_getarea() - but for phys addresses * Inputs: * res Pointer to the word to receive the result @@ -324,9 +324,9 @@ static int kdb_getphys(void *res, unsigned long addr, size_t size) if (!pfn_valid(pfn)) return 1; page = pfn_to_page(pfn); - vaddr = kmap_atomic(page); + vaddr = kmap_local_page(page); memcpy(res, vaddr + (addr & (PAGE_SIZE - 1)), size); - kunmap_atomic(vaddr); + kunmap_local(vaddr); return 0; } @@ -536,21 +536,3 @@ bool kdb_task_state(const struct task_struct *p, const char *mask) return strchr(mask, state); } - -/* Maintain a small stack of kdb_flags to allow recursion without disturbing - * the global kdb state. - */ - -static int kdb_flags_stack[4], kdb_flags_index; - -void kdb_save_flags(void) -{ - BUG_ON(kdb_flags_index >= ARRAY_SIZE(kdb_flags_stack)); - kdb_flags_stack[kdb_flags_index++] = kdb_flags; -} - -void kdb_restore_flags(void) -{ - BUG_ON(kdb_flags_index <= 0); - kdb_flags = kdb_flags_stack[--kdb_flags_index]; -} diff --git a/kernel/delayacct.c b/kernel/delayacct.c index dead51de8eb5..eb63a021ac04 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -64,7 +64,7 @@ static int sysctl_delayacct(const struct ctl_table *table, int write, void *buff return err; } -static struct ctl_table kern_delayacct_table[] = { +static const struct ctl_table kern_delayacct_table[] = { { .procname = "task_delayacct", .data = NULL, @@ -93,9 +93,9 @@ void __delayacct_tsk_init(struct task_struct *tsk) /* * Finish delay accounting for a statistic using its timestamps (@start), - * accumalator (@total) and @count + * accumulator (@total) and @count */ -static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, u32 *count) +static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, u32 *count, u64 *max, u64 *min) { s64 ns = local_clock() - *start; unsigned long flags; @@ -104,6 +104,10 @@ static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, u32 *cou raw_spin_lock_irqsave(lock, flags); *total += ns; (*count)++; + if (ns > *max) + *max = ns; + if (*min == 0 || ns < *min) + *min = ns; raw_spin_unlock_irqrestore(lock, flags); } } @@ -122,7 +126,9 @@ void __delayacct_blkio_end(struct task_struct *p) delayacct_end(&p->delays->lock, &p->delays->blkio_start, &p->delays->blkio_delay, - &p->delays->blkio_count); + &p->delays->blkio_count, + &p->delays->blkio_delay_max, + &p->delays->blkio_delay_min); } int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) @@ -153,10 +159,12 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->cpu_count += t1; + d->cpu_delay_max = tsk->sched_info.max_run_delay; + d->cpu_delay_min = tsk->sched_info.min_run_delay; tmp = (s64)d->cpu_delay_total + t2; d->cpu_delay_total = (tmp < (s64)d->cpu_delay_total) ? 0 : tmp; - tmp = (s64)d->cpu_run_virtual_total + t3; + d->cpu_run_virtual_total = (tmp < (s64)d->cpu_run_virtual_total) ? 0 : tmp; @@ -164,20 +172,33 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) return 0; /* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */ - raw_spin_lock_irqsave(&tsk->delays->lock, flags); + d->blkio_delay_max = tsk->delays->blkio_delay_max; + d->blkio_delay_min = tsk->delays->blkio_delay_min; tmp = d->blkio_delay_total + tsk->delays->blkio_delay; d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp; + d->swapin_delay_max = tsk->delays->swapin_delay_max; + d->swapin_delay_min = tsk->delays->swapin_delay_min; tmp = d->swapin_delay_total + tsk->delays->swapin_delay; d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; + d->freepages_delay_max = tsk->delays->freepages_delay_max; + d->freepages_delay_min = tsk->delays->freepages_delay_min; tmp = d->freepages_delay_total + tsk->delays->freepages_delay; d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; + d->thrashing_delay_max = tsk->delays->thrashing_delay_max; + d->thrashing_delay_min = tsk->delays->thrashing_delay_min; tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; + d->compact_delay_max = tsk->delays->compact_delay_max; + d->compact_delay_min = tsk->delays->compact_delay_min; tmp = d->compact_delay_total + tsk->delays->compact_delay; d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp; + d->wpcopy_delay_max = tsk->delays->wpcopy_delay_max; + d->wpcopy_delay_min = tsk->delays->wpcopy_delay_min; tmp = d->wpcopy_delay_total + tsk->delays->wpcopy_delay; d->wpcopy_delay_total = (tmp < d->wpcopy_delay_total) ? 0 : tmp; + d->irq_delay_max = tsk->delays->irq_delay_max; + d->irq_delay_min = tsk->delays->irq_delay_min; tmp = d->irq_delay_total + tsk->delays->irq_delay; d->irq_delay_total = (tmp < d->irq_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; @@ -213,7 +234,9 @@ void __delayacct_freepages_end(void) delayacct_end(¤t->delays->lock, ¤t->delays->freepages_start, ¤t->delays->freepages_delay, - ¤t->delays->freepages_count); + ¤t->delays->freepages_count, + ¤t->delays->freepages_delay_max, + ¤t->delays->freepages_delay_min); } void __delayacct_thrashing_start(bool *in_thrashing) @@ -235,7 +258,9 @@ void __delayacct_thrashing_end(bool *in_thrashing) delayacct_end(¤t->delays->lock, ¤t->delays->thrashing_start, ¤t->delays->thrashing_delay, - ¤t->delays->thrashing_count); + ¤t->delays->thrashing_count, + ¤t->delays->thrashing_delay_max, + ¤t->delays->thrashing_delay_min); } void __delayacct_swapin_start(void) @@ -248,7 +273,9 @@ void __delayacct_swapin_end(void) delayacct_end(¤t->delays->lock, ¤t->delays->swapin_start, ¤t->delays->swapin_delay, - ¤t->delays->swapin_count); + ¤t->delays->swapin_count, + ¤t->delays->swapin_delay_max, + ¤t->delays->swapin_delay_min); } void __delayacct_compact_start(void) @@ -261,7 +288,9 @@ void __delayacct_compact_end(void) delayacct_end(¤t->delays->lock, ¤t->delays->compact_start, ¤t->delays->compact_delay, - ¤t->delays->compact_count); + ¤t->delays->compact_count, + ¤t->delays->compact_delay_max, + ¤t->delays->compact_delay_min); } void __delayacct_wpcopy_start(void) @@ -274,7 +303,9 @@ void __delayacct_wpcopy_end(void) delayacct_end(¤t->delays->lock, ¤t->delays->wpcopy_start, ¤t->delays->wpcopy_delay, - ¤t->delays->wpcopy_count); + ¤t->delays->wpcopy_count, + ¤t->delays->wpcopy_delay_max, + ¤t->delays->wpcopy_delay_min); } void __delayacct_irq(struct task_struct *task, u32 delta) @@ -284,6 +315,10 @@ void __delayacct_irq(struct task_struct *task, u32 delta) raw_spin_lock_irqsave(&task->delays->lock, flags); task->delays->irq_delay += delta; task->delays->irq_count++; + if (delta > task->delays->irq_delay_max) + task->delays->irq_delay_max = delta; + if (delta && (!task->delays->irq_delay_min || delta < task->delays->irq_delay_min)) + task->delays->irq_delay_min = delta; raw_spin_unlock_irqrestore(&task->delays->lock, flags); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 065f9188b44a..bcb09e011e9e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6277,41 +6277,6 @@ unlock: } EXPORT_SYMBOL_GPL(perf_event_update_userpage); -static vm_fault_t perf_mmap_fault(struct vm_fault *vmf) -{ - struct perf_event *event = vmf->vma->vm_file->private_data; - struct perf_buffer *rb; - vm_fault_t ret = VM_FAULT_SIGBUS; - - if (vmf->flags & FAULT_FLAG_MKWRITE) { - if (vmf->pgoff == 0) - ret = 0; - return ret; - } - - rcu_read_lock(); - rb = rcu_dereference(event->rb); - if (!rb) - goto unlock; - - if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE)) - goto unlock; - - vmf->page = perf_mmap_to_page(rb, vmf->pgoff); - if (!vmf->page) - goto unlock; - - get_page(vmf->page); - vmf->page->mapping = vmf->vma->vm_file->f_mapping; - vmf->page->index = vmf->pgoff; - - ret = 0; -unlock: - rcu_read_unlock(); - - return ret; -} - static void ring_buffer_attach(struct perf_event *event, struct perf_buffer *rb) { @@ -6551,13 +6516,87 @@ out_put: ring_buffer_put(rb); /* could be last */ } +static vm_fault_t perf_mmap_pfn_mkwrite(struct vm_fault *vmf) +{ + /* The first page is the user control page, others are read-only. */ + return vmf->pgoff == 0 ? 0 : VM_FAULT_SIGBUS; +} + static const struct vm_operations_struct perf_mmap_vmops = { .open = perf_mmap_open, .close = perf_mmap_close, /* non mergeable */ - .fault = perf_mmap_fault, - .page_mkwrite = perf_mmap_fault, + .pfn_mkwrite = perf_mmap_pfn_mkwrite, }; +static int map_range(struct perf_buffer *rb, struct vm_area_struct *vma) +{ + unsigned long nr_pages = vma_pages(vma); + int err = 0; + unsigned long pagenum; + + /* + * We map this as a VM_PFNMAP VMA. + * + * This is not ideal as this is designed broadly for mappings of PFNs + * referencing memory-mapped I/O ranges or non-system RAM i.e. for which + * !pfn_valid(pfn). + * + * We are mapping kernel-allocated memory (memory we manage ourselves) + * which would more ideally be mapped using vm_insert_page() or a + * similar mechanism, that is as a VM_MIXEDMAP mapping. + * + * However this won't work here, because: + * + * 1. It uses vma->vm_page_prot, but this field has not been completely + * setup at the point of the f_op->mmp() hook, so we are unable to + * indicate that this should be mapped CoW in order that the + * mkwrite() hook can be invoked to make the first page R/W and the + * rest R/O as desired. + * + * 2. Anything other than a VM_PFNMAP of valid PFNs will result in + * vm_normal_page() returning a struct page * pointer, which means + * vm_ops->page_mkwrite() will be invoked rather than + * vm_ops->pfn_mkwrite(), and this means we have to set page->mapping + * to work around retry logic in the fault handler, however this + * field is no longer allowed to be used within struct page. + * + * 3. Having a struct page * made available in the fault logic also + * means that the page gets put on the rmap and becomes + * inappropriately accessible and subject to map and ref counting. + * + * Ideally we would have a mechanism that could explicitly express our + * desires, but this is not currently the case, so we instead use + * VM_PFNMAP. + * + * We manage the lifetime of these mappings with internal refcounts (see + * perf_mmap_open() and perf_mmap_close()) so we ensure the lifetime of + * this mapping is maintained correctly. + */ + for (pagenum = 0; pagenum < nr_pages; pagenum++) { + unsigned long va = vma->vm_start + PAGE_SIZE * pagenum; + struct page *page = perf_mmap_to_page(rb, vma->vm_pgoff + pagenum); + + if (page == NULL) { + err = -EINVAL; + break; + } + + /* Map readonly, perf_mmap_pfn_mkwrite() called on write fault. */ + err = remap_pfn_range(vma, va, page_to_pfn(page), PAGE_SIZE, + vm_get_page_prot(vma->vm_flags & ~VM_SHARED)); + if (err) + break; + } + +#ifdef CONFIG_MMU + /* Clear any partial mappings on error. */ + if (err) + zap_page_range_single(vma, vma->vm_start, nr_pages * PAGE_SIZE, NULL); +#endif + + return err; +} + static int perf_mmap(struct file *file, struct vm_area_struct *vma) { struct perf_event *event = file->private_data; @@ -6682,6 +6721,8 @@ again: goto again; } + /* We need the rb to map pages. */ + rb = event->rb; goto unlock; } @@ -6776,6 +6817,9 @@ aux_unlock: vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &perf_mmap_vmops; + if (!ret) + ret = map_range(rb, vma); + if (event->pmu->event_mapped) event->pmu->event_mapped(event, vma->vm_mm); @@ -10039,8 +10083,7 @@ static void perf_swevent_event(struct perf_event *event, u64 nr, perf_swevent_overflow(event, 0, data, regs); } -static int perf_exclude_event(struct perf_event *event, - struct pt_regs *regs) +int perf_exclude_event(struct perf_event *event, struct pt_regs *regs) { if (event->hw.state & PERF_HES_STOPPED) return 1; @@ -10425,9 +10468,9 @@ static struct pmu perf_tracepoint = { }; static int perf_tp_filter_match(struct perf_event *event, - struct perf_sample_data *data) + struct perf_raw_record *raw) { - void *record = data->raw->frag.data; + void *record = raw->frag.data; /* only top level events have filters set */ if (event->parent) @@ -10439,7 +10482,7 @@ static int perf_tp_filter_match(struct perf_event *event, } static int perf_tp_event_match(struct perf_event *event, - struct perf_sample_data *data, + struct perf_raw_record *raw, struct pt_regs *regs) { if (event->hw.state & PERF_HES_STOPPED) @@ -10450,7 +10493,7 @@ static int perf_tp_event_match(struct perf_event *event, if (event->attr.exclude_kernel && !user_mode(regs)) return 0; - if (!perf_tp_filter_match(event, data)) + if (!perf_tp_filter_match(event, raw)) return 0; return 1; @@ -10476,6 +10519,7 @@ EXPORT_SYMBOL_GPL(perf_trace_run_bpf_submit); static void __perf_tp_event_target_task(u64 count, void *record, struct pt_regs *regs, struct perf_sample_data *data, + struct perf_raw_record *raw, struct perf_event *event) { struct trace_entry *entry = record; @@ -10485,13 +10529,17 @@ static void __perf_tp_event_target_task(u64 count, void *record, /* Cannot deliver synchronous signal to other task. */ if (event->attr.sigtrap) return; - if (perf_tp_event_match(event, data, regs)) + if (perf_tp_event_match(event, raw, regs)) { + perf_sample_data_init(data, 0, 0); + perf_sample_save_raw_data(data, event, raw); perf_swevent_event(event, count, data, regs); + } } static void perf_tp_event_target_task(u64 count, void *record, struct pt_regs *regs, struct perf_sample_data *data, + struct perf_raw_record *raw, struct perf_event_context *ctx) { unsigned int cpu = smp_processor_id(); @@ -10499,15 +10547,15 @@ static void perf_tp_event_target_task(u64 count, void *record, struct perf_event *event, *sibling; perf_event_groups_for_cpu_pmu(event, &ctx->pinned_groups, cpu, pmu) { - __perf_tp_event_target_task(count, record, regs, data, event); + __perf_tp_event_target_task(count, record, regs, data, raw, event); for_each_sibling_event(sibling, event) - __perf_tp_event_target_task(count, record, regs, data, sibling); + __perf_tp_event_target_task(count, record, regs, data, raw, sibling); } perf_event_groups_for_cpu_pmu(event, &ctx->flexible_groups, cpu, pmu) { - __perf_tp_event_target_task(count, record, regs, data, event); + __perf_tp_event_target_task(count, record, regs, data, raw, event); for_each_sibling_event(sibling, event) - __perf_tp_event_target_task(count, record, regs, data, sibling); + __perf_tp_event_target_task(count, record, regs, data, raw, sibling); } } @@ -10525,15 +10573,10 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, }, }; - perf_sample_data_init(&data, 0, 0); - perf_sample_save_raw_data(&data, &raw); - perf_trace_buf_update(record, event_type); hlist_for_each_entry_rcu(event, head, hlist_entry) { - if (perf_tp_event_match(event, &data, regs)) { - perf_swevent_event(event, count, &data, regs); - + if (perf_tp_event_match(event, &raw, regs)) { /* * Here use the same on-stack perf_sample_data, * some members in data are event-specific and @@ -10543,7 +10586,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, * because data->sample_flags is set. */ perf_sample_data_init(&data, 0, 0); - perf_sample_save_raw_data(&data, &raw); + perf_sample_save_raw_data(&data, event, &raw); + perf_swevent_event(event, count, &data, regs); } } @@ -10560,7 +10604,7 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, goto unlock; raw_spin_lock(&ctx->lock); - perf_tp_event_target_task(count, record, regs, &data, ctx); + perf_tp_event_target_task(count, record, regs, &data, &raw, ctx); raw_spin_unlock(&ctx->lock); unlock: rcu_read_unlock(); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 4f46f688d0d4..180509132d4b 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -643,7 +643,6 @@ static void rb_free_aux_page(struct perf_buffer *rb, int idx) struct page *page = virt_to_page(rb->aux_pages[idx]); ClearPagePrivate(page); - page->mapping = NULL; __free_page(page); } @@ -819,7 +818,6 @@ static void perf_mmap_free_page(void *addr) { struct page *page = virt_to_page(addr); - page->mapping = NULL; __free_page(page); } @@ -890,28 +888,13 @@ __perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff) return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE); } -static void perf_mmap_unmark_page(void *addr) -{ - struct page *page = vmalloc_to_page(addr); - - page->mapping = NULL; -} - static void rb_free_work(struct work_struct *work) { struct perf_buffer *rb; - void *base; - int i, nr; rb = container_of(work, struct perf_buffer, work); - nr = data_page_nr(rb); - base = rb->user_page; - /* The '<=' counts in the user page. */ - for (i = 0; i <= nr; i++) - perf_mmap_unmark_page(base + (i * PAGE_SIZE)); - - vfree(base); + vfree(rb->user_page); kfree(rb); } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index fa04b14a7d72..2ca797cbe465 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -28,6 +28,7 @@ #include #include #include +#include /* check_stable_address_space */ #include @@ -1260,6 +1261,9 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) * returns NULL in find_active_uprobe_rcu(). */ mmap_write_lock(mm); + if (check_stable_address_space(mm)) + goto unlock; + vma = find_vma(mm, info->vaddr); if (!vma || !valid_vma(vma, is_register) || file_inode(vma->vm_file) != uprobe->inode) @@ -1888,9 +1892,33 @@ unsigned long uprobe_get_trap_addr(struct pt_regs *regs) return instruction_pointer(regs); } -static struct return_instance *free_ret_instance(struct return_instance *ri, bool cleanup_hprobe) +static void ri_pool_push(struct uprobe_task *utask, struct return_instance *ri) { - struct return_instance *next = ri->next; + ri->cons_cnt = 0; + ri->next = utask->ri_pool; + utask->ri_pool = ri; +} + +static struct return_instance *ri_pool_pop(struct uprobe_task *utask) +{ + struct return_instance *ri = utask->ri_pool; + + if (likely(ri)) + utask->ri_pool = ri->next; + + return ri; +} + +static void ri_free(struct return_instance *ri) +{ + kfree(ri->extra_consumers); + kfree_rcu(ri, rcu); +} + +static void free_ret_instance(struct uprobe_task *utask, + struct return_instance *ri, bool cleanup_hprobe) +{ + unsigned seq; if (cleanup_hprobe) { enum hprobe_state hstate; @@ -1899,8 +1927,22 @@ static struct return_instance *free_ret_instance(struct return_instance *ri, boo hprobe_finalize(&ri->hprobe, hstate); } - kfree_rcu(ri, rcu); - return next; + /* + * At this point return_instance is unlinked from utask's + * return_instances list and this has become visible to ri_timer(). + * If seqcount now indicates that ri_timer's return instance + * processing loop isn't active, we can return ri into the pool of + * to-be-reused return instances for future uretprobes. If ri_timer() + * happens to be running right now, though, we fallback to safety and + * just perform RCU-delated freeing of ri. + */ + if (raw_seqcount_try_begin(&utask->ri_seqcount, seq)) { + /* immediate reuse of ri without RCU GP is OK */ + ri_pool_push(utask, ri); + } else { + /* we might be racing with ri_timer(), so play it safe */ + ri_free(ri); + } } /* @@ -1910,21 +1952,32 @@ static struct return_instance *free_ret_instance(struct return_instance *ri, boo void uprobe_free_utask(struct task_struct *t) { struct uprobe_task *utask = t->utask; - struct return_instance *ri; + struct return_instance *ri, *ri_next; if (!utask) return; + t->utask = NULL; WARN_ON_ONCE(utask->active_uprobe || utask->xol_vaddr); timer_delete_sync(&utask->ri_timer); ri = utask->return_instances; - while (ri) - ri = free_ret_instance(ri, true /* cleanup_hprobe */); + while (ri) { + ri_next = ri->next; + free_ret_instance(utask, ri, true /* cleanup_hprobe */); + ri = ri_next; + } + + /* free_ret_instance() above might add to ri_pool, so this loop should come last */ + ri = utask->ri_pool; + while (ri) { + ri_next = ri->next; + ri_free(ri); + ri = ri_next; + } kfree(utask); - t->utask = NULL; } #define RI_TIMER_PERIOD (HZ / 10) /* 100 ms */ @@ -1942,8 +1995,12 @@ static void ri_timer(struct timer_list *timer) /* RCU protects return_instance from freeing. */ guard(rcu)(); + write_seqcount_begin(&utask->ri_seqcount); + for_each_ret_instance_rcu(ri, utask->return_instances) hprobe_expire(&ri->hprobe, false); + + write_seqcount_end(&utask->ri_seqcount); } static struct uprobe_task *alloc_utask(void) @@ -1955,6 +2012,7 @@ static struct uprobe_task *alloc_utask(void) return NULL; timer_setup(&utask->ri_timer, ri_timer, 0); + seqcount_init(&utask->ri_seqcount); return utask; } @@ -1974,32 +2032,40 @@ static struct uprobe_task *get_utask(void) return current->utask; } -static size_t ri_size(int consumers_cnt) +static struct return_instance *alloc_return_instance(struct uprobe_task *utask) { struct return_instance *ri; - return sizeof(*ri) + sizeof(ri->consumers[0]) * consumers_cnt; -} + ri = ri_pool_pop(utask); + if (ri) + return ri; -#define DEF_CNT 4 - -static struct return_instance *alloc_return_instance(void) -{ - struct return_instance *ri; - - ri = kzalloc(ri_size(DEF_CNT), GFP_KERNEL); + ri = kzalloc(sizeof(*ri), GFP_KERNEL); if (!ri) return ZERO_SIZE_PTR; - ri->consumers_cnt = DEF_CNT; return ri; } static struct return_instance *dup_return_instance(struct return_instance *old) { - size_t size = ri_size(old->consumers_cnt); + struct return_instance *ri; - return kmemdup(old, size, GFP_KERNEL); + ri = kmemdup(old, sizeof(*ri), GFP_KERNEL); + if (!ri) + return NULL; + + if (unlikely(old->cons_cnt > 1)) { + ri->extra_consumers = kmemdup(old->extra_consumers, + sizeof(ri->extra_consumers[0]) * (old->cons_cnt - 1), + GFP_KERNEL); + if (!ri->extra_consumers) { + kfree(ri); + return NULL; + } + } + + return ri; } static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask) @@ -2108,14 +2174,17 @@ unsigned long uprobe_get_trampoline_vaddr(void) static void cleanup_return_instances(struct uprobe_task *utask, bool chained, struct pt_regs *regs) { - struct return_instance *ri = utask->return_instances; + struct return_instance *ri = utask->return_instances, *ri_next; enum rp_check ctx = chained ? RP_CHECK_CHAIN_CALL : RP_CHECK_CALL; while (ri && !arch_uretprobe_is_alive(ri, ctx, regs)) { - ri = free_ret_instance(ri, true /* cleanup_hprobe */); + ri_next = ri->next; + rcu_assign_pointer(utask->return_instances, ri_next); utask->depth--; + + free_ret_instance(utask, ri, true /* cleanup_hprobe */); + ri = ri_next; } - rcu_assign_pointer(utask->return_instances, ri); } static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs, @@ -2180,7 +2249,7 @@ static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs, return; free: - kfree(ri); + ri_free(ri); } /* Prepare to single-step probed instruction out of line. */ @@ -2294,6 +2363,47 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) return is_trap_insn(&opcode); } +static struct uprobe *find_active_uprobe_speculative(unsigned long bp_vaddr) +{ + struct mm_struct *mm = current->mm; + struct uprobe *uprobe = NULL; + struct vm_area_struct *vma; + struct file *vm_file; + loff_t offset; + unsigned int seq; + + guard(rcu)(); + + if (!mmap_lock_speculate_try_begin(mm, &seq)) + return NULL; + + vma = vma_lookup(mm, bp_vaddr); + if (!vma) + return NULL; + + /* + * vm_file memory can be reused for another instance of struct file, + * but can't be freed from under us, so it's safe to read fields from + * it, even if the values are some garbage values; ultimately + * find_uprobe_rcu() + mmap_lock_speculation_end() check will ensure + * that whatever we speculatively found is correct + */ + vm_file = READ_ONCE(vma->vm_file); + if (!vm_file) + return NULL; + + offset = (loff_t)(vma->vm_pgoff << PAGE_SHIFT) + (bp_vaddr - vma->vm_start); + uprobe = find_uprobe_rcu(vm_file->f_inode, offset); + if (!uprobe) + return NULL; + + /* now double check that nothing about MM changed */ + if (mmap_lock_speculate_retry(mm, seq)) + return NULL; + + return uprobe; +} + /* assumes being inside RCU protected region */ static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swbp) { @@ -2301,10 +2411,14 @@ static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swb struct uprobe *uprobe = NULL; struct vm_area_struct *vma; + uprobe = find_active_uprobe_speculative(bp_vaddr); + if (uprobe) + return uprobe; + mmap_read_lock(mm); vma = vma_lookup(mm, bp_vaddr); if (vma) { - if (valid_vma(vma, false)) { + if (vma->vm_file) { struct inode *inode = file_inode(vma->vm_file); loff_t offset = vaddr_to_offset(vma, bp_vaddr); @@ -2324,25 +2438,27 @@ static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swb return uprobe; } -static struct return_instance* -push_consumer(struct return_instance *ri, int idx, __u64 id, __u64 cookie) +static struct return_instance *push_consumer(struct return_instance *ri, __u64 id, __u64 cookie) { + struct return_consumer *ric; + if (unlikely(ri == ZERO_SIZE_PTR)) return ri; - if (unlikely(idx >= ri->consumers_cnt)) { - struct return_instance *old_ri = ri; - - ri->consumers_cnt += DEF_CNT; - ri = krealloc(old_ri, ri_size(old_ri->consumers_cnt), GFP_KERNEL); - if (!ri) { - kfree(old_ri); + if (unlikely(ri->cons_cnt > 0)) { + ric = krealloc(ri->extra_consumers, sizeof(*ric) * ri->cons_cnt, GFP_KERNEL); + if (!ric) { + ri_free(ri); return ZERO_SIZE_PTR; } + ri->extra_consumers = ric; } - ri->consumers[idx].id = id; - ri->consumers[idx].cookie = cookie; + ric = likely(ri->cons_cnt == 0) ? &ri->consumer : &ri->extra_consumers[ri->cons_cnt - 1]; + ric->id = id; + ric->cookie = cookie; + + ri->cons_cnt++; return ri; } @@ -2350,14 +2466,17 @@ static struct return_consumer * return_consumer_find(struct return_instance *ri, int *iter, int id) { struct return_consumer *ric; - int idx = *iter; + int idx; - for (ric = &ri->consumers[idx]; idx < ri->consumers_cnt; idx++, ric++) { + for (idx = *iter; idx < ri->cons_cnt; idx++) + { + ric = likely(idx == 0) ? &ri->consumer : &ri->extra_consumers[idx - 1]; if (ric->id == id) { *iter = idx + 1; return ric; } } + return NULL; } @@ -2371,9 +2490,9 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) struct uprobe_consumer *uc; bool has_consumers = false, remove = true; struct return_instance *ri = NULL; - int push_idx = 0; + struct uprobe_task *utask = current->utask; - current->utask->auprobe = &uprobe->arch; + utask->auprobe = &uprobe->arch; list_for_each_entry_rcu(uc, &uprobe->consumers, cons_node, rcu_read_lock_trace_held()) { bool session = uc->handler && uc->ret_handler; @@ -2393,21 +2512,15 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) continue; if (!ri) - ri = alloc_return_instance(); + ri = alloc_return_instance(utask); if (session) - ri = push_consumer(ri, push_idx++, uc->id, cookie); + ri = push_consumer(ri, uc->id, cookie); } - current->utask->auprobe = NULL; + utask->auprobe = NULL; - if (!ZERO_OR_NULL_PTR(ri)) { - /* - * The push_idx value has the final number of return consumers, - * and ri->consumers_cnt has number of allocated consumers. - */ - ri->consumers_cnt = push_idx; + if (!ZERO_OR_NULL_PTR(ri)) prepare_uretprobe(uprobe, regs, ri); - } if (remove && has_consumers) { down_read(&uprobe->register_rwsem); @@ -2461,7 +2574,7 @@ static struct return_instance *find_next_ret_chain(struct return_instance *ri) void uprobe_handle_trampoline(struct pt_regs *regs) { struct uprobe_task *utask; - struct return_instance *ri, *next; + struct return_instance *ri, *ri_next, *next_chain; struct uprobe *uprobe; enum hprobe_state hstate; bool valid; @@ -2481,8 +2594,8 @@ void uprobe_handle_trampoline(struct pt_regs *regs) * or NULL; the latter case means that nobody but ri->func * could hit this trampoline on return. TODO: sigaltstack(). */ - next = find_next_ret_chain(ri); - valid = !next || arch_uretprobe_is_alive(next, RP_CHECK_RET, regs); + next_chain = find_next_ret_chain(ri); + valid = !next_chain || arch_uretprobe_is_alive(next_chain, RP_CHECK_RET, regs); instruction_pointer_set(regs, ri->orig_ret_vaddr); do { @@ -2494,7 +2607,9 @@ void uprobe_handle_trampoline(struct pt_regs *regs) * trampoline addresses on the stack are replaced with correct * original return addresses */ - rcu_assign_pointer(utask->return_instances, ri->next); + ri_next = ri->next; + rcu_assign_pointer(utask->return_instances, ri_next); + utask->depth--; uprobe = hprobe_consume(&ri->hprobe, &hstate); if (valid) @@ -2502,9 +2617,9 @@ void uprobe_handle_trampoline(struct pt_regs *regs) hprobe_finalize(&ri->hprobe, hstate); /* We already took care of hprobe, no need to waste more time on that. */ - ri = free_ret_instance(ri, false /* !cleanup_hprobe */); - utask->depth--; - } while (ri != next); + free_ret_instance(utask, ri, false /* !cleanup_hprobe */); + ri = ri_next; + } while (ri != next_chain); } while (!valid); return; diff --git a/kernel/exit.c b/kernel/exit.c index 1dcddfe537ee..3485e5fc499e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -85,7 +85,7 @@ static unsigned int oops_limit = 10000; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_exit_table[] = { +static const struct ctl_table kern_exit_table[] = { { .procname = "oops_limit", .data = &oops_limit, diff --git a/kernel/fork.c b/kernel/fork.c index 1450b461d196..735405a9c5f3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -448,7 +448,7 @@ static bool vma_lock_alloc(struct vm_area_struct *vma) return false; init_rwsem(&vma->vm_lock->lock); - vma->vm_lock_seq = -1; + vma->vm_lock_seq = UINT_MAX; return true; } @@ -625,8 +625,8 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) * We depend on the oldmm having properly denied write access to the * exe_file already. */ - if (exe_file && deny_write_access(exe_file)) - pr_warn_once("deny_write_access() failed in %s\n", __func__); + if (exe_file && exe_file_deny_write_access(exe_file)) + pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU @@ -639,11 +639,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, 0); - uprobe_start_dup_mmap(); - if (mmap_write_lock_killable(oldmm)) { - retval = -EINTR; - goto fail_uprobe_end; - } + if (mmap_write_lock_killable(oldmm)) + return -EINTR; flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* @@ -763,7 +760,8 @@ loop_out: mt_set_in_rcu(vmi.mas.tree); ksm_fork(mm, oldmm); khugepaged_fork(mm, oldmm); - } else if (mpnt) { + } else { + /* * The entire maple tree has already been duplicated. If the * mmap duplication fails, mark the failure point with @@ -771,8 +769,18 @@ loop_out: * stop releasing VMAs that have not been duplicated after this * point. */ - mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); - mas_store(&vmi.mas, XA_ZERO_ENTRY); + if (mpnt) { + mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); + mas_store(&vmi.mas, XA_ZERO_ENTRY); + /* Avoid OOM iterating a broken tree */ + set_bit(MMF_OOM_SKIP, &mm->flags); + } + /* + * The mm_struct is going to exit, but the locks will be dropped + * first. Set the mm_struct as unstable is advisable as it is + * not fully initialised. + */ + set_bit(MMF_UNSTABLE, &mm->flags); } out: mmap_write_unlock(mm); @@ -782,8 +790,6 @@ out: dup_userfaultfd_complete(&uf); else dup_userfaultfd_fail(&uf); -fail_uprobe_end: - uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: @@ -1267,9 +1273,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); -#ifdef CONFIG_PER_VMA_LOCK - mm->mm_lock_seq = 0; -#endif mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; @@ -1424,13 +1427,13 @@ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ - if (unlikely(deny_write_access(new_exe_file))) + if (unlikely(exe_file_deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { - allow_write_access(old_exe_file); + exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; @@ -1471,7 +1474,7 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) return ret; } - ret = deny_write_access(new_exe_file); + ret = exe_file_deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); @@ -1483,7 +1486,7 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) mmap_write_unlock(mm); if (old_exe_file) { - allow_write_access(old_exe_file); + exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; @@ -1519,12 +1522,13 @@ struct file *get_task_exe_file(struct task_struct *task) struct file *exe_file = NULL; struct mm_struct *mm; + if (task->flags & PF_KTHREAD) + return NULL; + task_lock(task); mm = task->mm; - if (mm) { - if (!(task->flags & PF_KTHREAD)) - exe_file = get_mm_exe_file(mm); - } + if (mm) + exe_file = get_mm_exe_file(mm); task_unlock(task); return exe_file; } @@ -1692,9 +1696,11 @@ static struct mm_struct *dup_mm(struct task_struct *tsk, if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; + uprobe_start_dup_mmap(); err = dup_mmap(mm, oldmm); if (err) goto free_pt; + uprobe_end_dup_mmap(); mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; @@ -1709,6 +1715,8 @@ free_pt: mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); + if (err) + uprobe_end_dup_mmap(); fail_nomem: return NULL; diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index d62cca5ed8f4..daea650b16f5 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -1020,10 +1020,7 @@ retry_private: * it sees the futex_q::pi_state. */ ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current, &wake_q); - preempt_disable(); - raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); - wake_up_q(&wake_q); - preempt_enable(); + raw_spin_unlock_irq_wake(&q.pi_state->pi_mutex.wait_lock, &wake_q); if (ret) { if (ret == 1) diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index 3a10375d9521..eb86a7ade06a 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -210,13 +210,12 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { if (oparg < 0 || oparg > 31) { - char comm[sizeof(current->comm)]; /* * kill this print and return -EINVAL when userspace * is sane again */ pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n", - get_task_comm(comm, current), oparg); + current->comm, oparg); oparg &= 31; } oparg = 1 << oparg; diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c index 7670a811a565..8b888a6193cc 100644 --- a/kernel/gcov/clang.c +++ b/kernel/gcov/clang.c @@ -264,10 +264,10 @@ int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2) /** * gcov_info_add - add up profiling data - * @dest: profiling data set to which data is added - * @source: profiling data set which is added + * @dst: profiling data set to which data is added + * @src: profiling data set which is added * - * Adds profiling counts of @source to @dest. + * Adds profiling counts of @src to @dst. */ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src) { diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 383fd43ac612..00529c81cc40 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -7,20 +7,13 @@ set -e sfile="$(readlink -f "$0")" outdir="$(pwd)" tarfile=$1 -cpio_dir=$outdir/${tarfile%/*}/.tmp_cpio_dir +tmpdir=$outdir/${tarfile%/*}/.tmp_dir dir_list=" include/ arch/$SRCARCH/include/ " -if ! command -v cpio >/dev/null; then - echo >&2 "***" - echo >&2 "*** 'cpio' could not be found." - echo >&2 "***" - exit 1 -fi - # Support incremental builds by skipping archive generation # if timestamps of files being archived are not changed. @@ -48,9 +41,9 @@ all_dirs="$all_dirs $dir_list" # check include/generated/autoconf.h explicitly. # # Ignore them for md5 calculation to avoid pointless regeneration. -headers_md5="$(find $all_dirs -name "*.h" | - grep -v "include/generated/utsversion.h" | - grep -v "include/generated/autoconf.h" | +headers_md5="$(find $all_dirs -name "*.h" -a \ + ! -path include/generated/utsversion.h -a \ + ! -path include/generated/autoconf.h | xargs ls -l | md5sum | cut -d ' ' -f1)" # Any changes to this script will also cause a rebuild of the archive. @@ -65,35 +58,43 @@ fi echo " GEN $tarfile" -rm -rf $cpio_dir -mkdir $cpio_dir +rm -rf "${tmpdir}" +mkdir "${tmpdir}" if [ "$building_out_of_srctree" ]; then ( cd $srctree for f in $dir_list do find "$f" -name "*.h"; - done | cpio --quiet -pd $cpio_dir + done | tar -c -f - -T - | tar -xf - -C "${tmpdir}" ) fi -# The second CPIO can complain if files already exist which can happen with out -# of tree builds having stale headers in srctree. Just silence CPIO for now. for f in $dir_list; do find "$f" -name "*.h"; -done | cpio --quiet -pdu $cpio_dir >/dev/null 2>&1 +done | tar -c -f - -T - | tar -xf - -C "${tmpdir}" + +# Always exclude include/generated/utsversion.h +# Otherwise, the contents of the tarball may vary depending on the build steps. +rm -f "${tmpdir}/include/generated/utsversion.h" # Remove comments except SDPX lines -find $cpio_dir -type f -print0 | - xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' +# Use a temporary file to store directory contents to prevent find/xargs from +# seeing temporary files created by perl. +find "${tmpdir}" -type f -print0 > "${tmpdir}.contents.txt" +xargs -0 -P8 -n1 \ + perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' \ + < "${tmpdir}.contents.txt" +rm -f "${tmpdir}.contents.txt" # Create archive and try to normalize metadata for reproducibility. tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ + --exclude=".__afs*" --exclude=".nfs*" \ --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \ - -I $XZ -cf $tarfile -C $cpio_dir/ . > /dev/null + -I $XZ -cf $tarfile -C "${tmpdir}/" . > /dev/null echo $headers_md5 > kernel/kheaders.md5 echo "$this_file_md5" >> kernel/kheaders.md5 echo "$(md5sum $tarfile | cut -d ' ' -f1)" >> kernel/kheaders.md5 -rm -rf $cpio_dir +rm -rf "${tmpdir}" diff --git a/kernel/hung_task.c b/kernel/hung_task.c index c18717189f32..04efa7a6e69b 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -147,6 +147,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); + if (t->flags & PF_POSTCOREDUMP) + pr_err(" Blocked by coredump.\n"); pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" " disables this message.\n"); sched_show_task(t); @@ -272,7 +274,7 @@ static int proc_dohung_task_timeout_secs(const struct ctl_table *table, int writ * and hung_task_check_interval_secs */ static const unsigned long hung_task_timeout_max = (LONG_MAX / HZ); -static struct ctl_table hung_task_sysctls[] = { +static const struct ctl_table hung_task_sysctls[] = { #ifdef CONFIG_SMP { .procname = "hung_task_all_cpu_backtrace", diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 529adb1f5859..5432418c0fea 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -31,6 +31,10 @@ config GENERIC_IRQ_EFFECTIVE_AFF_MASK config GENERIC_PENDING_IRQ bool +# Deduce delayed migration from top-level interrupt chip flags +config GENERIC_PENDING_IRQ_CHIPFLAGS + bool + # Support for generic irq migrating off cpu before the cpu is offline. config GENERIC_IRQ_MIGRATION bool @@ -141,6 +145,12 @@ config GENERIC_IRQ_DEBUGFS If you don't know what to do here, say N. +# Clear forwarded VM interrupts during kexec. +# This option ensures the kernel clears active states for interrupts +# forwarded to virtual machines (VMs) during a machine kexec. +config GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD + bool + endmenu config GENERIC_IRQ_MULTI_HANDLER diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index f19d3080bf11..c0f44c06d69d 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o +obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o kexec.o obj-$(CONFIG_IRQ_TIMINGS) += timings.o ifeq ($(CONFIG_TEST_IRQ_TIMINGS),y) CFLAGS_timings.o += -DDEBUG diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 271e9139de77..c901436ebd9f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1114,13 +1114,11 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) trigger = irqd_get_trigger_type(&desc->irq_data); irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU | - IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT); + IRQD_TRIGGER_MASK | IRQD_LEVEL); if (irq_settings_has_no_balance_set(desc)) irqd_set(&desc->irq_data, IRQD_NO_BALANCING); if (irq_settings_is_per_cpu(desc)) irqd_set(&desc->irq_data, IRQD_PER_CPU); - if (irq_settings_can_move_pcntxt(desc)) - irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT); if (irq_settings_is_level(desc)) irqd_set(&desc->irq_data, IRQD_LEVEL); diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index c6ffb97966be..ca142b9a4db3 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -53,6 +53,7 @@ static const struct irq_bit_descr irqchip_flags[] = { BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI), BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND), BIT_MASK_DESCR(IRQCHIP_IMMUTABLE), + BIT_MASK_DESCR(IRQCHIP_MOVE_DEFERRED), }; static void @@ -108,7 +109,6 @@ static const struct irq_bit_descr irqdata_states[] = { BIT_MASK_DESCR(IRQD_NO_BALANCING), BIT_MASK_DESCR(IRQD_SINGLE_TARGET), - BIT_MASK_DESCR(IRQD_MOVE_PCNTXT), BIT_MASK_DESCR(IRQD_AFFINITY_SET), BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING), BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED), diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 32ffcbb87fa1..c4a8bca5f2b0 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -162,6 +162,7 @@ void irq_gc_mask_disable_and_ack_set(struct irq_data *d) irq_reg_writel(gc, mask, ct->regs.ack); irq_gc_unlock(gc); } +EXPORT_SYMBOL_GPL(irq_gc_mask_disable_and_ack_set); /** * irq_gc_eoi - EOI interrupt diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index fe0272cd84a5..a979523640d0 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -421,7 +421,7 @@ irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, #ifdef CONFIG_GENERIC_PENDING_IRQ static inline bool irq_can_move_pcntxt(struct irq_data *data) { - return irqd_can_move_in_process_context(data); + return !(data->chip->flags & IRQCHIP_MOVE_DEFERRED); } static inline bool irq_move_pending(struct irq_data *data) { @@ -441,10 +441,6 @@ static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) { return desc->pending_mask; } -static inline bool handle_enforce_irqctx(struct irq_data *data) -{ - return irqd_is_handle_enforce_irqctx(data); -} bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear); #else /* CONFIG_GENERIC_PENDING_IRQ */ static inline bool irq_can_move_pcntxt(struct irq_data *data) @@ -471,10 +467,6 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) { return false; } -static inline bool handle_enforce_irqctx(struct irq_data *data) -{ - return false; -} #endif /* !CONFIG_GENERIC_PENDING_IRQ */ #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 0253e77fcd9a..287830739783 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -708,7 +708,7 @@ int handle_irq_desc(struct irq_desc *desc) return -EINVAL; data = irq_desc_get_irq_data(desc); - if (WARN_ON_ONCE(!in_hardirq() && handle_enforce_irqctx(data))) + if (WARN_ON_ONCE(!in_hardirq() && irqd_is_handle_enforce_irqctx(data))) return -EPERM; generic_handle_irq_desc(desc); diff --git a/kernel/irq/kexec.c b/kernel/irq/kexec.c new file mode 100644 index 000000000000..1a3deffe6b5b --- /dev/null +++ b/kernel/irq/kexec.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include + +#include "internals.h" + +void machine_kexec_mask_interrupts(void) +{ + struct irq_desc *desc; + unsigned int i; + + for_each_irq_desc(i, desc) { + struct irq_chip *chip; + int check_eoi = 1; + + chip = irq_desc_get_chip(desc); + if (!chip || !irqd_is_started(&desc->irq_data)) + continue; + + if (IS_ENABLED(CONFIG_GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD)) { + /* + * First try to remove the active state from an interrupt which is forwarded + * to a VM. If the interrupt is not forwarded, try to EOI the interrupt. + */ + check_eoi = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); + } + + if (check_eoi && chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) + chip->irq_eoi(&desc->irq_data); + + irq_shutdown(desc); + } +} diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f0803d6bd296..f300bb6be3bd 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1181,49 +1181,42 @@ out_unlock: chip_bus_sync_unlock(desc); } +/* + * Interrupts explicitly requested as threaded interrupts want to be + * preemptible - many of them need to sleep and wait for slow busses to + * complete. + */ +static irqreturn_t irq_thread_fn(struct irq_desc *desc, struct irqaction *action) +{ + irqreturn_t ret = action->thread_fn(action->irq, action->dev_id); + + if (ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); + + irq_finalize_oneshot(desc, action); + return ret; +} + /* * Interrupts which are not explicitly requested as threaded * interrupts rely on the implicit bh/preempt disable of the hard irq * context. So we need to disable bh here to avoid deadlocks and other * side effects. */ -static irqreturn_t -irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) +static irqreturn_t irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) { irqreturn_t ret; local_bh_disable(); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_disable(); - ret = action->thread_fn(action->irq, action->dev_id); - if (ret == IRQ_HANDLED) - atomic_inc(&desc->threads_handled); - - irq_finalize_oneshot(desc, action); + ret = irq_thread_fn(desc, action); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_enable(); local_bh_enable(); return ret; } -/* - * Interrupts explicitly requested as threaded interrupts want to be - * preemptible - many of them need to sleep and wait for slow busses to - * complete. - */ -static irqreturn_t irq_thread_fn(struct irq_desc *desc, - struct irqaction *action) -{ - irqreturn_t ret; - - ret = action->thread_fn(action->irq, action->dev_id); - if (ret == IRQ_HANDLED) - atomic_inc(&desc->threads_handled); - - irq_finalize_oneshot(desc, action); - return ret; -} - void wake_threads_waitq(struct irq_desc *desc) { if (atomic_dec_and_test(&desc->threads_active)) diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index b07a2d732ffb..1b7fa72968bd 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -53,7 +53,7 @@ static int irq_sw_resend(struct irq_desc *desc) * Validate whether this interrupt can be safely injected from * non interrupt context */ - if (handle_enforce_irqctx(&desc->irq_data)) + if (irqd_is_handle_enforce_irqctx(&desc->irq_data)) return -EINVAL; /* diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 7b7efb1a114b..00b3bd127692 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -11,7 +11,6 @@ enum { _IRQ_NOREQUEST = IRQ_NOREQUEST, _IRQ_NOTHREAD = IRQ_NOTHREAD, _IRQ_NOAUTOEN = IRQ_NOAUTOEN, - _IRQ_MOVE_PCNTXT = IRQ_MOVE_PCNTXT, _IRQ_NO_BALANCING = IRQ_NO_BALANCING, _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, @@ -142,11 +141,6 @@ static inline void irq_settings_set_noprobe(struct irq_desc *desc) desc->status_use_accessors |= _IRQ_NOPROBE; } -static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc) -{ - return desc->status_use_accessors & _IRQ_MOVE_PCNTXT; -} - static inline bool irq_settings_can_autoenable(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOAUTOEN); diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index c43e2ac2f8de..4b7315e99bd6 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -509,6 +509,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts) /** * irq_timings_next_event - Return when the next event is supposed to arrive + * @now: current time * * During the last busy cycle, the number of interrupts is incremented * and stored in the irq_timings structure. This information is diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 2f4fb336dda1..73f7e1fd4ab4 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -147,7 +147,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) if (!irq_work_claim(work)) return false; - kasan_record_aux_stack_noalloc(work); + kasan_record_aux_stack(work); preempt_disable(); if (cpu != smp_processor_id()) { diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index 873f7c445488..cf4af5728307 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -435,13 +435,11 @@ static int __init kallsyms_test_init(void) { struct task_struct *t; - t = kthread_create(test_entry, NULL, "kallsyms_test"); + t = kthread_run_on_cpu(test_entry, NULL, 0, "kallsyms_test"); if (IS_ERR(t)) { pr_info("Create kallsyms selftest task failed\n"); return PTR_ERR(t); } - kthread_bind(t, 0); - wake_up_process(t); return 0; } diff --git a/kernel/kcov.c b/kernel/kcov.c index 28a6be6e64fd..187ba1b80bda 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -166,7 +166,7 @@ static void kcov_remote_area_put(struct kcov_remote_area *area, * Unlike in_serving_softirq(), this function returns false when called during * a hardirq or an NMI that happened in the softirq context. */ -static inline bool in_softirq_really(void) +static __always_inline bool in_softirq_really(void) { return in_serving_softirq() && !in_hardirq() && !in_nmi(); } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index c0caa14880c3..c0bdc1686154 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -925,7 +925,7 @@ static int kexec_limit_handler(const struct ctl_table *table, int write, return proc_dointvec(&tmp, write, buffer, lenp, ppos); } -static struct ctl_table kexec_core_sysctls[] = { +static const struct ctl_table kexec_core_sysctls[] = { { .procname = "kexec_load_disabled", .data = &kexec_load_disabled, @@ -1001,6 +1001,12 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { + /* + * This flow is analogous to hibernation flows that occur + * before creating an image and before jumping from the + * restore kernel to the image one, so it uses the same + * device callbacks as those two flows. + */ pm_prepare_console(); error = freeze_processes(); if (error) { @@ -1011,12 +1017,10 @@ int kernel_kexec(void) error = dpm_suspend_start(PMSG_FREEZE); if (error) goto Resume_console; - /* At this point, dpm_suspend_start() has been called, - * but *not* dpm_suspend_end(). We *must* call - * dpm_suspend_end() now. Otherwise, drivers for - * some devices (e.g. interrupt controllers) become - * desynchronized with the actual state of the - * hardware at resume time, and evil weirdness ensues. + /* + * dpm_suspend_end() must be called after dpm_suspend_start() + * to complete the transition, like in the hibernation flows + * mentioned above. */ error = dpm_suspend_end(PMSG_FREEZE); if (error) @@ -1052,6 +1056,13 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { + /* + * This flow is analogous to hibernation flows that occur after + * creating an image and after the image kernel has got control + * back, and in case the devices have been reset or otherwise + * manipulated in the meantime, it uses the device callbacks + * used by the latter. + */ syscore_resume(); Enable_irqs: local_irq_enable(); diff --git a/kernel/kheaders.c b/kernel/kheaders.c index 42163c9e94e5..378088b07f46 100644 --- a/kernel/kheaders.c +++ b/kernel/kheaders.c @@ -29,25 +29,12 @@ asm ( extern char kernel_headers_data[]; extern char kernel_headers_data_end[]; -static ssize_t -ikheaders_read(struct file *file, struct kobject *kobj, - struct bin_attribute *bin_attr, - char *buf, loff_t off, size_t len) -{ - memcpy(buf, &kernel_headers_data[off], len); - return len; -} - -static struct bin_attribute kheaders_attr __ro_after_init = { - .attr = { - .name = "kheaders.tar.xz", - .mode = 0444, - }, - .read = &ikheaders_read, -}; +static struct bin_attribute kheaders_attr __ro_after_init = + __BIN_ATTR_SIMPLE_RO(kheaders.tar.xz, 0444); static int __init ikheaders_init(void) { + kheaders_attr.private = kernel_headers_data; kheaders_attr.size = (kernel_headers_data_end - kernel_headers_data); return sysfs_create_bin_file(kernel_kobj, &kheaders_attr); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index b027a4030976..88aeac84e4c0 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -140,45 +141,39 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c); kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip; - kprobe_opcode_t *slot = NULL; /* Since the slot array is not protected by rcu, we need a mutex */ - mutex_lock(&c->mutex); - retry: - rcu_read_lock(); - list_for_each_entry_rcu(kip, &c->pages, list) { - if (kip->nused < slots_per_page(c)) { - int i; + guard(mutex)(&c->mutex); + do { + guard(rcu)(); + list_for_each_entry_rcu(kip, &c->pages, list) { + if (kip->nused < slots_per_page(c)) { + int i; - for (i = 0; i < slots_per_page(c); i++) { - if (kip->slot_used[i] == SLOT_CLEAN) { - kip->slot_used[i] = SLOT_USED; - kip->nused++; - slot = kip->insns + (i * c->insn_size); - rcu_read_unlock(); - goto out; + for (i = 0; i < slots_per_page(c); i++) { + if (kip->slot_used[i] == SLOT_CLEAN) { + kip->slot_used[i] = SLOT_USED; + kip->nused++; + return kip->insns + (i * c->insn_size); + } } + /* kip->nused is broken. Fix it. */ + kip->nused = slots_per_page(c); + WARN_ON(1); } - /* kip->nused is broken. Fix it. */ - kip->nused = slots_per_page(c); - WARN_ON(1); } - } - rcu_read_unlock(); - /* If there are any garbage slots, collect it and try again. */ - if (c->nr_garbage && collect_garbage_slots(c) == 0) - goto retry; + } while (c->nr_garbage && collect_garbage_slots(c) == 0); /* All out of space. Need to allocate a new page. */ kip = kmalloc(struct_size(kip, slot_used, slots_per_page(c)), GFP_KERNEL); if (!kip) - goto out; + return NULL; kip->insns = c->alloc(); if (!kip->insns) { kfree(kip); - goto out; + return NULL; } INIT_LIST_HEAD(&kip->list); memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c)); @@ -187,14 +182,12 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) kip->ngarbage = 0; kip->cache = c; list_add_rcu(&kip->list, &c->pages); - slot = kip->insns; /* Record the perf ksymbol register event after adding the page */ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns, PAGE_SIZE, false, c->sym); -out: - mutex_unlock(&c->mutex); - return slot; + + return kip->insns; } /* Return true if all garbages are collected, otherwise false. */ @@ -249,25 +242,35 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c) return 0; } -void __free_insn_slot(struct kprobe_insn_cache *c, - kprobe_opcode_t *slot, int dirty) +static long __find_insn_page(struct kprobe_insn_cache *c, + kprobe_opcode_t *slot, struct kprobe_insn_page **pkip) { - struct kprobe_insn_page *kip; + struct kprobe_insn_page *kip = NULL; long idx; - mutex_lock(&c->mutex); - rcu_read_lock(); + guard(rcu)(); list_for_each_entry_rcu(kip, &c->pages, list) { idx = ((long)slot - (long)kip->insns) / (c->insn_size * sizeof(kprobe_opcode_t)); - if (idx >= 0 && idx < slots_per_page(c)) - goto out; + if (idx >= 0 && idx < slots_per_page(c)) { + *pkip = kip; + return idx; + } } /* Could not find this slot. */ WARN_ON(1); - kip = NULL; -out: - rcu_read_unlock(); + *pkip = NULL; + return -1; +} + +void __free_insn_slot(struct kprobe_insn_cache *c, + kprobe_opcode_t *slot, int dirty) +{ + struct kprobe_insn_page *kip = NULL; + long idx; + + guard(mutex)(&c->mutex); + idx = __find_insn_page(c, slot, &kip); /* Mark and sweep: this may sleep */ if (kip) { /* Check double free */ @@ -281,7 +284,6 @@ out: collect_one_slot(kip, idx); } } - mutex_unlock(&c->mutex); } /* @@ -600,47 +602,43 @@ static void kick_kprobe_optimizer(void) /* Kprobe jump optimizer */ static void kprobe_optimizer(struct work_struct *work) { - mutex_lock(&kprobe_mutex); - cpus_read_lock(); - mutex_lock(&text_mutex); + guard(mutex)(&kprobe_mutex); - /* - * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) - * kprobes before waiting for quiesence period. - */ - do_unoptimize_kprobes(); + scoped_guard(cpus_read_lock) { + guard(mutex)(&text_mutex); - /* - * Step 2: Wait for quiesence period to ensure all potentially - * preempted tasks to have normally scheduled. Because optprobe - * may modify multiple instructions, there is a chance that Nth - * instruction is preempted. In that case, such tasks can return - * to 2nd-Nth byte of jump instruction. This wait is for avoiding it. - * Note that on non-preemptive kernel, this is transparently converted - * to synchronoze_sched() to wait for all interrupts to have completed. - */ - synchronize_rcu_tasks(); + /* + * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) + * kprobes before waiting for quiesence period. + */ + do_unoptimize_kprobes(); - /* Step 3: Optimize kprobes after quiesence period */ - do_optimize_kprobes(); + /* + * Step 2: Wait for quiesence period to ensure all potentially + * preempted tasks to have normally scheduled. Because optprobe + * may modify multiple instructions, there is a chance that Nth + * instruction is preempted. In that case, such tasks can return + * to 2nd-Nth byte of jump instruction. This wait is for avoiding it. + * Note that on non-preemptive kernel, this is transparently converted + * to synchronoze_sched() to wait for all interrupts to have completed. + */ + synchronize_rcu_tasks(); - /* Step 4: Free cleaned kprobes after quiesence period */ - do_free_cleaned_kprobes(); + /* Step 3: Optimize kprobes after quiesence period */ + do_optimize_kprobes(); - mutex_unlock(&text_mutex); - cpus_read_unlock(); + /* Step 4: Free cleaned kprobes after quiesence period */ + do_free_cleaned_kprobes(); + } /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); - - mutex_unlock(&kprobe_mutex); } -/* Wait for completing optimization and unoptimization */ -void wait_for_kprobe_optimizer(void) +static void wait_for_kprobe_optimizer_locked(void) { - mutex_lock(&kprobe_mutex); + lockdep_assert_held(&kprobe_mutex); while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) { mutex_unlock(&kprobe_mutex); @@ -652,8 +650,14 @@ void wait_for_kprobe_optimizer(void) mutex_lock(&kprobe_mutex); } +} - mutex_unlock(&kprobe_mutex); +/* Wait for completing optimization and unoptimization */ +void wait_for_kprobe_optimizer(void) +{ + guard(mutex)(&kprobe_mutex); + + wait_for_kprobe_optimizer_locked(); } bool optprobe_queued_unopt(struct optimized_kprobe *op) @@ -852,29 +856,24 @@ static void try_to_optimize_kprobe(struct kprobe *p) return; /* For preparing optimization, jump_label_text_reserved() is called. */ - cpus_read_lock(); - jump_label_lock(); - mutex_lock(&text_mutex); + guard(cpus_read_lock)(); + guard(jump_label_lock)(); + guard(mutex)(&text_mutex); ap = alloc_aggr_kprobe(p); if (!ap) - goto out; + return; op = container_of(ap, struct optimized_kprobe, kp); if (!arch_prepared_optinsn(&op->optinsn)) { /* If failed to setup optimizing, fallback to kprobe. */ arch_remove_optimized_kprobe(op); kfree(op); - goto out; + return; } init_aggr_kprobe(ap, p); optimize_kprobe(ap); /* This just kicks optimizer thread. */ - -out: - mutex_unlock(&text_mutex); - jump_label_unlock(); - cpus_read_unlock(); } static void optimize_all_kprobes(void) @@ -883,10 +882,10 @@ static void optimize_all_kprobes(void) struct kprobe *p; unsigned int i; - mutex_lock(&kprobe_mutex); + guard(mutex)(&kprobe_mutex); /* If optimization is already allowed, just return. */ if (kprobes_allow_optimization) - goto out; + return; cpus_read_lock(); kprobes_allow_optimization = true; @@ -898,8 +897,6 @@ static void optimize_all_kprobes(void) } cpus_read_unlock(); pr_info("kprobe jump-optimization is enabled. All kprobes are optimized if possible.\n"); -out: - mutex_unlock(&kprobe_mutex); } #ifdef CONFIG_SYSCTL @@ -909,12 +906,10 @@ static void unoptimize_all_kprobes(void) struct kprobe *p; unsigned int i; - mutex_lock(&kprobe_mutex); + guard(mutex)(&kprobe_mutex); /* If optimization is already prohibited, just return. */ - if (!kprobes_allow_optimization) { - mutex_unlock(&kprobe_mutex); + if (!kprobes_allow_optimization) return; - } cpus_read_lock(); kprobes_allow_optimization = false; @@ -926,10 +921,8 @@ static void unoptimize_all_kprobes(void) } } cpus_read_unlock(); - mutex_unlock(&kprobe_mutex); - /* Wait for unoptimizing completion. */ - wait_for_kprobe_optimizer(); + wait_for_kprobe_optimizer_locked(); pr_info("kprobe jump-optimization is disabled. All kprobes are based on software breakpoint.\n"); } @@ -941,7 +934,7 @@ static int proc_kprobes_optimization_handler(const struct ctl_table *table, { int ret; - mutex_lock(&kprobe_sysctl_mutex); + guard(mutex)(&kprobe_sysctl_mutex); sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); @@ -949,12 +942,11 @@ static int proc_kprobes_optimization_handler(const struct ctl_table *table, optimize_all_kprobes(); else unoptimize_all_kprobes(); - mutex_unlock(&kprobe_sysctl_mutex); return ret; } -static struct ctl_table kprobe_sysctls[] = { +static const struct ctl_table kprobe_sysctls[] = { { .procname = "kprobes-optimization", .data = &sysctl_kprobes_optimization, @@ -1024,7 +1016,8 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt) #define __arm_kprobe(p) arch_arm_kprobe(p) #define __disarm_kprobe(p, o) arch_disarm_kprobe(p) #define kprobe_disarmed(p) kprobe_disabled(p) -#define wait_for_kprobe_optimizer() do {} while (0) +#define wait_for_kprobe_optimizer_locked() \ + lockdep_assert_held(&kprobe_mutex) static int reuse_unused_kprobe(struct kprobe *ap) { @@ -1078,20 +1071,18 @@ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, if (*cnt == 0) { ret = register_ftrace_function(ops); - if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) - goto err_ftrace; + if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) { + /* + * At this point, sinec ops is not registered, we should be sefe from + * registering empty filter. + */ + ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0); + return ret; + } } (*cnt)++; return ret; - -err_ftrace: - /* - * At this point, sinec ops is not registered, we should be sefe from - * registering empty filter. - */ - ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0); - return ret; } static int arm_kprobe_ftrace(struct kprobe *p) @@ -1163,12 +1154,9 @@ static int arm_kprobe(struct kprobe *kp) if (unlikely(kprobe_ftrace(kp))) return arm_kprobe_ftrace(kp); - cpus_read_lock(); - mutex_lock(&text_mutex); + guard(cpus_read_lock)(); + guard(mutex)(&text_mutex); __arm_kprobe(kp); - mutex_unlock(&text_mutex); - cpus_read_unlock(); - return 0; } @@ -1177,12 +1165,9 @@ static int disarm_kprobe(struct kprobe *kp, bool reopt) if (unlikely(kprobe_ftrace(kp))) return disarm_kprobe_ftrace(kp); - cpus_read_lock(); - mutex_lock(&text_mutex); + guard(cpus_read_lock)(); + guard(mutex)(&text_mutex); __disarm_kprobe(kp, reopt); - mutex_unlock(&text_mutex); - cpus_read_unlock(); - return 0; } @@ -1299,63 +1284,56 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) int ret = 0; struct kprobe *ap = orig_p; - cpus_read_lock(); + scoped_guard(cpus_read_lock) { + /* For preparing optimization, jump_label_text_reserved() is called */ + guard(jump_label_lock)(); + guard(mutex)(&text_mutex); - /* For preparing optimization, jump_label_text_reserved() is called */ - jump_label_lock(); - mutex_lock(&text_mutex); - - if (!kprobe_aggrprobe(orig_p)) { - /* If 'orig_p' is not an 'aggr_kprobe', create new one. */ - ap = alloc_aggr_kprobe(orig_p); - if (!ap) { - ret = -ENOMEM; - goto out; + if (!kprobe_aggrprobe(orig_p)) { + /* If 'orig_p' is not an 'aggr_kprobe', create new one. */ + ap = alloc_aggr_kprobe(orig_p); + if (!ap) + return -ENOMEM; + init_aggr_kprobe(ap, orig_p); + } else if (kprobe_unused(ap)) { + /* This probe is going to die. Rescue it */ + ret = reuse_unused_kprobe(ap); + if (ret) + return ret; } - init_aggr_kprobe(ap, orig_p); - } else if (kprobe_unused(ap)) { - /* This probe is going to die. Rescue it */ - ret = reuse_unused_kprobe(ap); - if (ret) - goto out; - } - if (kprobe_gone(ap)) { - /* - * Attempting to insert new probe at the same location that - * had a probe in the module vaddr area which already - * freed. So, the instruction slot has already been - * released. We need a new slot for the new probe. - */ - ret = arch_prepare_kprobe(ap); - if (ret) + if (kprobe_gone(ap)) { /* - * Even if fail to allocate new slot, don't need to - * free the 'ap'. It will be used next time, or - * freed by unregister_kprobe(). + * Attempting to insert new probe at the same location that + * had a probe in the module vaddr area which already + * freed. So, the instruction slot has already been + * released. We need a new slot for the new probe. */ - goto out; + ret = arch_prepare_kprobe(ap); + if (ret) + /* + * Even if fail to allocate new slot, don't need to + * free the 'ap'. It will be used next time, or + * freed by unregister_kprobe(). + */ + return ret; - /* Prepare optimized instructions if possible. */ - prepare_optimized_kprobe(ap); + /* Prepare optimized instructions if possible. */ + prepare_optimized_kprobe(ap); - /* - * Clear gone flag to prevent allocating new slot again, and - * set disabled flag because it is not armed yet. - */ - ap->flags = (ap->flags & ~KPROBE_FLAG_GONE) - | KPROBE_FLAG_DISABLED; + /* + * Clear gone flag to prevent allocating new slot again, and + * set disabled flag because it is not armed yet. + */ + ap->flags = (ap->flags & ~KPROBE_FLAG_GONE) + | KPROBE_FLAG_DISABLED; + } + + /* Copy the insn slot of 'p' to 'ap'. */ + copy_kprobe(ap, p); + ret = add_new_kprobe(ap, p); } - /* Copy the insn slot of 'p' to 'ap'. */ - copy_kprobe(ap, p); - ret = add_new_kprobe(ap, p); - -out: - mutex_unlock(&text_mutex); - jump_label_unlock(); - cpus_read_unlock(); - if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { ap->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed) { @@ -1448,7 +1426,7 @@ _kprobe_addr(kprobe_opcode_t *addr, const char *symbol_name, unsigned long offset, bool *on_func_entry) { if ((symbol_name && addr) || (!symbol_name && !addr)) - goto invalid; + return ERR_PTR(-EINVAL); if (symbol_name) { /* @@ -1478,16 +1456,16 @@ _kprobe_addr(kprobe_opcode_t *addr, const char *symbol_name, * at the start of the function. */ addr = arch_adjust_kprobe_addr((unsigned long)addr, offset, on_func_entry); - if (addr) - return addr; + if (!addr) + return ERR_PTR(-EINVAL); -invalid: - return ERR_PTR(-EINVAL); + return addr; } static kprobe_opcode_t *kprobe_addr(struct kprobe *p) { bool on_func_entry; + return _kprobe_addr(p->addr, p->symbol_name, p->offset, &on_func_entry); } @@ -1505,15 +1483,15 @@ static struct kprobe *__get_valid_kprobe(struct kprobe *p) if (unlikely(!ap)) return NULL; - if (p != ap) { - list_for_each_entry(list_p, &ap->list, list) - if (list_p == p) - /* kprobe p is a valid probe */ - goto valid; - return NULL; - } -valid: - return ap; + if (p == ap) + return ap; + + list_for_each_entry(list_p, &ap->list, list) + if (list_p == p) + /* kprobe p is a valid probe */ + return ap; + + return NULL; } /* @@ -1522,14 +1500,12 @@ valid: */ static inline int warn_kprobe_rereg(struct kprobe *p) { - int ret = 0; + guard(mutex)(&kprobe_mutex); - mutex_lock(&kprobe_mutex); if (WARN_ON_ONCE(__get_valid_kprobe(p))) - ret = -EINVAL; - mutex_unlock(&kprobe_mutex); + return -EINVAL; - return ret; + return 0; } static int check_ftrace_location(struct kprobe *p) @@ -1565,17 +1541,23 @@ static int check_kprobe_address_safe(struct kprobe *p, ret = check_ftrace_location(p); if (ret) return ret; - jump_label_lock(); - preempt_disable(); + + guard(jump_label_lock)(); /* Ensure the address is in a text area, and find a module if exists. */ *probed_mod = NULL; if (!core_kernel_text((unsigned long) p->addr)) { + guard(preempt)(); *probed_mod = __module_text_address((unsigned long) p->addr); - if (!(*probed_mod)) { - ret = -EINVAL; - goto out; - } + if (!(*probed_mod)) + return -EINVAL; + + /* + * We must hold a refcount of the probed module while updating + * its code to prohibit unexpected unloading. + */ + if (unlikely(!try_module_get(*probed_mod))) + return -ENOENT; } /* Ensure it is not in reserved area. */ if (in_gate_area_no_mm((unsigned long) p->addr) || @@ -1584,21 +1566,12 @@ static int check_kprobe_address_safe(struct kprobe *p, static_call_text_reserved(p->addr, p->addr) || find_bug((unsigned long)p->addr) || is_cfi_preamble_symbol((unsigned long)p->addr)) { - ret = -EINVAL; - goto out; + module_put(*probed_mod); + return -EINVAL; } /* Get module refcount and reject __init functions for loaded modules. */ if (IS_ENABLED(CONFIG_MODULES) && *probed_mod) { - /* - * We must hold a refcount of the probed module while updating - * its code to prohibit unexpected unloading. - */ - if (unlikely(!try_module_get(*probed_mod))) { - ret = -ENOENT; - goto out; - } - /* * If the module freed '.init.text', we couldn't insert * kprobes in there. @@ -1606,27 +1579,58 @@ static int check_kprobe_address_safe(struct kprobe *p, if (within_module_init((unsigned long)p->addr, *probed_mod) && !module_is_coming(*probed_mod)) { module_put(*probed_mod); - *probed_mod = NULL; - ret = -ENOENT; + return -ENOENT; } } -out: - preempt_enable(); - jump_label_unlock(); + return 0; +} - return ret; +static int __register_kprobe(struct kprobe *p) +{ + int ret; + struct kprobe *old_p; + + guard(mutex)(&kprobe_mutex); + + old_p = get_kprobe(p->addr); + if (old_p) + /* Since this may unoptimize 'old_p', locking 'text_mutex'. */ + return register_aggr_kprobe(old_p, p); + + scoped_guard(cpus_read_lock) { + /* Prevent text modification */ + guard(mutex)(&text_mutex); + ret = prepare_kprobe(p); + if (ret) + return ret; + } + + INIT_HLIST_NODE(&p->hlist); + hlist_add_head_rcu(&p->hlist, + &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); + + if (!kprobes_all_disarmed && !kprobe_disabled(p)) { + ret = arm_kprobe(p); + if (ret) { + hlist_del_rcu(&p->hlist); + synchronize_rcu(); + } + } + + /* Try to optimize kprobe */ + try_to_optimize_kprobe(p); + return 0; } int register_kprobe(struct kprobe *p) { int ret; - struct kprobe *old_p; struct module *probed_mod; kprobe_opcode_t *addr; bool on_func_entry; - /* Adjust probe address from symbol */ + /* Canonicalize probe address from symbol */ addr = _kprobe_addr(p->addr, p->symbol_name, p->offset, &on_func_entry); if (IS_ERR(addr)) return PTR_ERR(addr); @@ -1638,6 +1642,8 @@ int register_kprobe(struct kprobe *p) /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ p->flags &= KPROBE_FLAG_DISABLED; + if (on_func_entry) + p->flags |= KPROBE_FLAG_ON_FUNC_ENTRY; p->nmissed = 0; INIT_LIST_HEAD(&p->list); @@ -1645,44 +1651,7 @@ int register_kprobe(struct kprobe *p) if (ret) return ret; - mutex_lock(&kprobe_mutex); - - if (on_func_entry) - p->flags |= KPROBE_FLAG_ON_FUNC_ENTRY; - - old_p = get_kprobe(p->addr); - if (old_p) { - /* Since this may unoptimize 'old_p', locking 'text_mutex'. */ - ret = register_aggr_kprobe(old_p, p); - goto out; - } - - cpus_read_lock(); - /* Prevent text modification */ - mutex_lock(&text_mutex); - ret = prepare_kprobe(p); - mutex_unlock(&text_mutex); - cpus_read_unlock(); - if (ret) - goto out; - - INIT_HLIST_NODE(&p->hlist); - hlist_add_head_rcu(&p->hlist, - &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); - - if (!kprobes_all_disarmed && !kprobe_disabled(p)) { - ret = arm_kprobe(p); - if (ret) { - hlist_del_rcu(&p->hlist); - synchronize_rcu(); - goto out; - } - } - - /* Try to optimize kprobe */ - try_to_optimize_kprobe(p); -out: - mutex_unlock(&kprobe_mutex); + ret = __register_kprobe(p); if (probed_mod) module_put(probed_mod); @@ -1761,29 +1730,31 @@ static int __unregister_kprobe_top(struct kprobe *p) if (IS_ERR(ap)) return PTR_ERR(ap); - if (ap == p) - /* - * This probe is an independent(and non-optimized) kprobe - * (not an aggrprobe). Remove from the hash list. - */ - goto disarmed; + WARN_ON(ap != p && !kprobe_aggrprobe(ap)); - /* Following process expects this probe is an aggrprobe */ - WARN_ON(!kprobe_aggrprobe(ap)); - - if (list_is_singular(&ap->list) && kprobe_disarmed(ap)) + /* + * If the probe is an independent(and non-optimized) kprobe + * (not an aggrprobe), the last kprobe on the aggrprobe, or + * kprobe is already disarmed, just remove from the hash list. + */ + if (ap == p || + (list_is_singular(&ap->list) && kprobe_disarmed(ap))) { /* * !disarmed could be happen if the probe is under delayed * unoptimizing. */ - goto disarmed; - else { - /* If disabling probe has special handlers, update aggrprobe */ - if (p->post_handler && !kprobe_gone(p)) { - list_for_each_entry(list_p, &ap->list, list) { - if ((list_p != p) && (list_p->post_handler)) - goto noclean; - } + hlist_del_rcu(&ap->hlist); + return 0; + } + + /* If disabling probe has special handlers, update aggrprobe */ + if (p->post_handler && !kprobe_gone(p)) { + list_for_each_entry(list_p, &ap->list, list) { + if ((list_p != p) && (list_p->post_handler)) + break; + } + /* No other probe has post_handler */ + if (list_entry_is_head(list_p, &ap->list, list)) { /* * For the kprobe-on-ftrace case, we keep the * post_handler setting to identify this aggrprobe @@ -1792,24 +1763,21 @@ static int __unregister_kprobe_top(struct kprobe *p) if (!kprobe_ftrace(ap)) ap->post_handler = NULL; } -noclean: - /* - * Remove from the aggrprobe: this path will do nothing in - * __unregister_kprobe_bottom(). - */ - list_del_rcu(&p->list); - if (!kprobe_disabled(ap) && !kprobes_all_disarmed) - /* - * Try to optimize this probe again, because post - * handler may have been changed. - */ - optimize_kprobe(ap); } + + /* + * Remove from the aggrprobe: this path will do nothing in + * __unregister_kprobe_bottom(). + */ + list_del_rcu(&p->list); + if (!kprobe_disabled(ap) && !kprobes_all_disarmed) + /* + * Try to optimize this probe again, because post + * handler may have been changed. + */ + optimize_kprobe(ap); return 0; -disarmed: - hlist_del_rcu(&ap->hlist); - return 0; } static void __unregister_kprobe_bottom(struct kprobe *p) @@ -1858,12 +1826,11 @@ void unregister_kprobes(struct kprobe **kps, int num) if (num <= 0) return; - mutex_lock(&kprobe_mutex); - for (i = 0; i < num; i++) - if (__unregister_kprobe_top(kps[i]) < 0) - kps[i]->addr = NULL; - mutex_unlock(&kprobe_mutex); - + scoped_guard(mutex, &kprobe_mutex) { + for (i = 0; i < num; i++) + if (__unregister_kprobe_top(kps[i]) < 0) + kps[i]->addr = NULL; + } synchronize_rcu(); for (i = 0; i < num; i++) if (kps[i]->addr) @@ -2302,8 +2269,9 @@ void unregister_kretprobes(struct kretprobe **rps, int num) if (num <= 0) return; - mutex_lock(&kprobe_mutex); for (i = 0; i < num; i++) { + guard(mutex)(&kprobe_mutex); + if (__unregister_kprobe_top(&rps[i]->kp) < 0) rps[i]->kp.addr = NULL; #ifdef CONFIG_KRETPROBE_ON_RETHOOK @@ -2312,7 +2280,6 @@ void unregister_kretprobes(struct kretprobe **rps, int num) rcu_assign_pointer(rps[i]->rph->rp, NULL); #endif } - mutex_unlock(&kprobe_mutex); synchronize_rcu(); for (i = 0; i < num; i++) { @@ -2393,18 +2360,14 @@ static void kill_kprobe(struct kprobe *p) /* Disable one kprobe */ int disable_kprobe(struct kprobe *kp) { - int ret = 0; struct kprobe *p; - mutex_lock(&kprobe_mutex); + guard(mutex)(&kprobe_mutex); /* Disable this kprobe */ p = __disable_kprobe(kp); - if (IS_ERR(p)) - ret = PTR_ERR(p); - mutex_unlock(&kprobe_mutex); - return ret; + return IS_ERR(p) ? PTR_ERR(p) : 0; } EXPORT_SYMBOL_GPL(disable_kprobe); @@ -2414,20 +2377,16 @@ int enable_kprobe(struct kprobe *kp) int ret = 0; struct kprobe *p; - mutex_lock(&kprobe_mutex); + guard(mutex)(&kprobe_mutex); /* Check whether specified probe is valid. */ p = __get_valid_kprobe(kp); - if (unlikely(p == NULL)) { - ret = -EINVAL; - goto out; - } + if (unlikely(p == NULL)) + return -EINVAL; - if (kprobe_gone(kp)) { + if (kprobe_gone(kp)) /* This kprobe has gone, we couldn't enable it. */ - ret = -EINVAL; - goto out; - } + return -EINVAL; if (p != kp) kp->flags &= ~KPROBE_FLAG_DISABLED; @@ -2441,8 +2400,6 @@ int enable_kprobe(struct kprobe *kp) kp->flags |= KPROBE_FLAG_DISABLED; } } -out: - mutex_unlock(&kprobe_mutex); return ret; } EXPORT_SYMBOL_GPL(enable_kprobe); @@ -2630,11 +2587,11 @@ static int kprobes_module_callback(struct notifier_block *nb, unsigned int i; int checkcore = (val == MODULE_STATE_GOING); - if (val == MODULE_STATE_COMING) { - mutex_lock(&kprobe_mutex); + guard(mutex)(&kprobe_mutex); + + if (val == MODULE_STATE_COMING) add_module_kprobe_blacklist(mod); - mutex_unlock(&kprobe_mutex); - } + if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE) return NOTIFY_DONE; @@ -2644,7 +2601,6 @@ static int kprobes_module_callback(struct notifier_block *nb, * notified, only '.init.text' section would be freed. We need to * disable kprobes which have been inserted in the sections. */ - mutex_lock(&kprobe_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) @@ -2667,7 +2623,6 @@ static int kprobes_module_callback(struct notifier_block *nb, } if (val == MODULE_STATE_GOING) remove_module_kprobe_blacklist(mod); - mutex_unlock(&kprobe_mutex); return NOTIFY_DONE; } @@ -2695,7 +2650,7 @@ void kprobe_free_init_mem(void) struct kprobe *p; int i; - mutex_lock(&kprobe_mutex); + guard(mutex)(&kprobe_mutex); /* Kill all kprobes on initmem because the target code has been freed. */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { @@ -2705,8 +2660,6 @@ void kprobe_free_init_mem(void) kill_kprobe(p); } } - - mutex_unlock(&kprobe_mutex); } static int __init init_kprobes(void) @@ -2902,11 +2855,11 @@ static int arm_all_kprobes(void) unsigned int i, total = 0, errors = 0; int err, ret = 0; - mutex_lock(&kprobe_mutex); + guard(mutex)(&kprobe_mutex); /* If kprobes are armed, just return */ if (!kprobes_all_disarmed) - goto already_enabled; + return 0; /* * optimize_kprobe() called by arm_kprobe() checks @@ -2936,8 +2889,6 @@ static int arm_all_kprobes(void) else pr_info("Kprobes globally enabled\n"); -already_enabled: - mutex_unlock(&kprobe_mutex); return ret; } @@ -2948,13 +2899,11 @@ static int disarm_all_kprobes(void) unsigned int i, total = 0, errors = 0; int err, ret = 0; - mutex_lock(&kprobe_mutex); + guard(mutex)(&kprobe_mutex); /* If kprobes are already disarmed, just return */ - if (kprobes_all_disarmed) { - mutex_unlock(&kprobe_mutex); + if (kprobes_all_disarmed) return 0; - } kprobes_all_disarmed = true; @@ -2979,11 +2928,8 @@ static int disarm_all_kprobes(void) else pr_info("Kprobes globally disabled\n"); - mutex_unlock(&kprobe_mutex); - /* Wait for disarming all kprobes by optimizer */ - wait_for_kprobe_optimizer(); - + wait_for_kprobe_optimizer_locked(); return ret; } diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 1bab21b4718f..eefb67d9883c 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -239,21 +239,7 @@ extern const void __start_notes; extern const void __stop_notes; #define notes_size (&__stop_notes - &__start_notes) -static ssize_t notes_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, - char *buf, loff_t off, size_t count) -{ - memcpy(buf, &__start_notes + off, count); - return count; -} - -static struct bin_attribute notes_attr __ro_after_init = { - .attr = { - .name = "notes", - .mode = S_IRUGO, - }, - .read = ¬es_read, -}; +static __ro_after_init BIN_ATTR_SIMPLE_RO(notes); struct kobject *kernel_kobj; EXPORT_SYMBOL_GPL(kernel_kobj); @@ -307,8 +293,9 @@ static int __init ksysfs_init(void) goto kset_exit; if (notes_size > 0) { - notes_attr.size = notes_size; - error = sysfs_create_bin_file(kernel_kobj, ¬es_attr); + bin_attr_notes.private = (void *)&__start_notes; + bin_attr_notes.size = notes_size; + error = sysfs_create_bin_file(kernel_kobj, &bin_attr_notes); if (error) goto group_exit; } diff --git a/kernel/kthread.c b/kernel/kthread.c index a5ac612b1609..4005b13ebd7f 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -35,6 +35,9 @@ static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; +static LIST_HEAD(kthreads_hotplug); +static DEFINE_MUTEX(kthreads_hotplug_lock); + struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ @@ -53,6 +56,8 @@ struct kthread_create_info struct kthread { unsigned long flags; unsigned int cpu; + unsigned int node; + int started; int result; int (*threadfn)(void *); void *data; @@ -63,6 +68,9 @@ struct kthread { #endif /* To store the full name if task comm is truncated. */ char *full_name; + struct task_struct *task; + struct list_head hotplug_node; + struct cpumask *preferred_affinity; }; enum KTHREAD_BITS { @@ -121,8 +129,11 @@ bool set_kthread_struct(struct task_struct *p) init_completion(&kthread->exited); init_completion(&kthread->parked); + INIT_LIST_HEAD(&kthread->hotplug_node); p->vfork_done = &kthread->exited; + kthread->task = p; + kthread->node = tsk_fork_get_node(current); p->worker_private = kthread; return true; } @@ -313,6 +324,16 @@ void __noreturn kthread_exit(long result) { struct kthread *kthread = to_kthread(current); kthread->result = result; + if (!list_empty(&kthread->hotplug_node)) { + mutex_lock(&kthreads_hotplug_lock); + list_del(&kthread->hotplug_node); + mutex_unlock(&kthreads_hotplug_lock); + + if (kthread->preferred_affinity) { + kfree(kthread->preferred_affinity); + kthread->preferred_affinity = NULL; + } + } do_exit(0); } EXPORT_SYMBOL(kthread_exit); @@ -338,6 +359,56 @@ void __noreturn kthread_complete_and_exit(struct completion *comp, long code) } EXPORT_SYMBOL(kthread_complete_and_exit); +static void kthread_fetch_affinity(struct kthread *kthread, struct cpumask *cpumask) +{ + const struct cpumask *pref; + + if (kthread->preferred_affinity) { + pref = kthread->preferred_affinity; + } else { + if (WARN_ON_ONCE(kthread->node == NUMA_NO_NODE)) + return; + pref = cpumask_of_node(kthread->node); + } + + cpumask_and(cpumask, pref, housekeeping_cpumask(HK_TYPE_KTHREAD)); + if (cpumask_empty(cpumask)) + cpumask_copy(cpumask, housekeeping_cpumask(HK_TYPE_KTHREAD)); +} + +static void kthread_affine_node(void) +{ + struct kthread *kthread = to_kthread(current); + cpumask_var_t affinity; + + WARN_ON_ONCE(kthread_is_per_cpu(current)); + + if (kthread->node == NUMA_NO_NODE) { + housekeeping_affine(current, HK_TYPE_KTHREAD); + } else { + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) { + WARN_ON_ONCE(1); + return; + } + + mutex_lock(&kthreads_hotplug_lock); + WARN_ON_ONCE(!list_empty(&kthread->hotplug_node)); + list_add_tail(&kthread->hotplug_node, &kthreads_hotplug); + /* + * The node cpumask is racy when read from kthread() but: + * - a racing CPU going down will either fail on the subsequent + * call to set_cpus_allowed_ptr() or be migrated to housekeepers + * afterwards by the scheduler. + * - a racing CPU going up will be handled by kthreads_online_cpu() + */ + kthread_fetch_affinity(kthread, affinity); + set_cpus_allowed_ptr(current, affinity); + mutex_unlock(&kthreads_hotplug_lock); + + free_cpumask_var(affinity); + } +} + static int kthread(void *_create) { static const struct sched_param param = { .sched_priority = 0 }; @@ -368,7 +439,6 @@ static int kthread(void *_create) * back to default in case they have been changed. */ sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m); - set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_KTHREAD)); /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); @@ -382,6 +452,11 @@ static int kthread(void *_create) schedule_preempt_disabled(); preempt_enable(); + self->started = 1; + + if (!(current->flags & PF_NO_SETAFFINITY) && !self->preferred_affinity) + kthread_affine_node(); + ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) { cgroup_kthread_ready(); @@ -540,7 +615,9 @@ static void __kthread_bind(struct task_struct *p, unsigned int cpu, unsigned int void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask) { + struct kthread *kthread = to_kthread(p); __kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE); + WARN_ON_ONCE(kthread->started); } /** @@ -554,7 +631,9 @@ void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask) */ void kthread_bind(struct task_struct *p, unsigned int cpu) { + struct kthread *kthread = to_kthread(p); __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE); + WARN_ON_ONCE(kthread->started); } EXPORT_SYMBOL(kthread_bind); @@ -738,10 +817,11 @@ EXPORT_SYMBOL(kthread_stop_put); int kthreadd(void *unused) { + static const char comm[TASK_COMM_LEN] = "kthreadd"; struct task_struct *tsk = current; /* Setup a clean context for our children to inherit. */ - set_task_comm(tsk, "kthreadd"); + set_task_comm(tsk, comm); ignore_signals(tsk); set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_TYPE_KTHREAD)); set_mems_allowed(node_states[N_MEMORY]); @@ -774,6 +854,92 @@ int kthreadd(void *unused) return 0; } +int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) +{ + struct kthread *kthread = to_kthread(p); + cpumask_var_t affinity; + unsigned long flags; + int ret; + + if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) { + WARN_ON(1); + return -EINVAL; + } + + WARN_ON_ONCE(kthread->preferred_affinity); + + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) + return -ENOMEM; + + kthread->preferred_affinity = kzalloc(sizeof(struct cpumask), GFP_KERNEL); + if (!kthread->preferred_affinity) { + ret = -ENOMEM; + goto out; + } + + mutex_lock(&kthreads_hotplug_lock); + cpumask_copy(kthread->preferred_affinity, mask); + WARN_ON_ONCE(!list_empty(&kthread->hotplug_node)); + list_add_tail(&kthread->hotplug_node, &kthreads_hotplug); + kthread_fetch_affinity(kthread, affinity); + + /* It's safe because the task is inactive. */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + do_set_cpus_allowed(p, affinity); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + mutex_unlock(&kthreads_hotplug_lock); +out: + free_cpumask_var(affinity); + + return 0; +} + +/* + * Re-affine kthreads according to their preferences + * and the newly online CPU. The CPU down part is handled + * by select_fallback_rq() which default re-affines to + * housekeepers from other nodes in case the preferred + * affinity doesn't apply anymore. + */ +static int kthreads_online_cpu(unsigned int cpu) +{ + cpumask_var_t affinity; + struct kthread *k; + int ret; + + guard(mutex)(&kthreads_hotplug_lock); + + if (list_empty(&kthreads_hotplug)) + return 0; + + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) + return -ENOMEM; + + ret = 0; + + list_for_each_entry(k, &kthreads_hotplug, hotplug_node) { + if (WARN_ON_ONCE((k->task->flags & PF_NO_SETAFFINITY) || + kthread_is_per_cpu(k->task))) { + ret = -EINVAL; + continue; + } + kthread_fetch_affinity(k, affinity); + set_cpus_allowed_ptr(k->task, affinity); + } + + free_cpumask_var(affinity); + + return ret; +} + +static int kthreads_init(void) +{ + return cpuhp_setup_state(CPUHP_AP_KTHREADS_ONLINE, "kthreads:online", + kthreads_online_cpu, NULL); +} +early_initcall(kthreads_init); + void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key) @@ -865,12 +1031,11 @@ repeat: EXPORT_SYMBOL_GPL(kthread_worker_fn); static __printf(3, 0) struct kthread_worker * -__kthread_create_worker(int cpu, unsigned int flags, - const char namefmt[], va_list args) +__kthread_create_worker_on_node(unsigned int flags, int node, + const char namefmt[], va_list args) { struct kthread_worker *worker; struct task_struct *task; - int node = NUMA_NO_NODE; worker = kzalloc(sizeof(*worker), GFP_KERNEL); if (!worker) @@ -878,20 +1043,14 @@ __kthread_create_worker(int cpu, unsigned int flags, kthread_init_worker(worker); - if (cpu >= 0) - node = cpu_to_node(cpu); - task = __kthread_create_on_node(kthread_worker_fn, worker, - node, namefmt, args); + node, namefmt, args); if (IS_ERR(task)) goto fail_task; - if (cpu >= 0) - kthread_bind(task, cpu); - worker->flags = flags; worker->task = task; - wake_up_process(task); + return worker; fail_task: @@ -900,8 +1059,9 @@ fail_task: } /** - * kthread_create_worker - create a kthread worker + * kthread_create_worker_on_node - create a kthread worker * @flags: flags modifying the default behavior of the worker + * @node: task structure for the thread is allocated on this node * @namefmt: printf-style name for the kthread worker (task). * * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) @@ -909,25 +1069,26 @@ fail_task: * when the caller was killed by a fatal signal. */ struct kthread_worker * -kthread_create_worker(unsigned int flags, const char namefmt[], ...) +kthread_create_worker_on_node(unsigned int flags, int node, const char namefmt[], ...) { struct kthread_worker *worker; va_list args; va_start(args, namefmt); - worker = __kthread_create_worker(-1, flags, namefmt, args); + worker = __kthread_create_worker_on_node(flags, node, namefmt, args); va_end(args); return worker; } -EXPORT_SYMBOL(kthread_create_worker); +EXPORT_SYMBOL(kthread_create_worker_on_node); /** * kthread_create_worker_on_cpu - create a kthread worker and bind it * to a given CPU and the associated NUMA node. * @cpu: CPU number * @flags: flags modifying the default behavior of the worker - * @namefmt: printf-style name for the kthread worker (task). + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. * * Use a valid CPU number if you want to bind the kthread worker * to the given CPU and the associated NUMA node. @@ -959,14 +1120,13 @@ EXPORT_SYMBOL(kthread_create_worker); */ struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, - const char namefmt[], ...) + const char namefmt[]) { struct kthread_worker *worker; - va_list args; - va_start(args, namefmt); - worker = __kthread_create_worker(cpu, flags, namefmt, args); - va_end(args); + worker = kthread_create_worker_on_node(flags, cpu_to_node(cpu), namefmt, cpu); + if (!IS_ERR(worker)) + kthread_bind(worker->task, cpu); return worker; } @@ -1015,7 +1175,7 @@ static void kthread_insert_work(struct kthread_worker *worker, * @work: kthread_work to queue * * Queue @work to work processor @task for async execution. @task - * must have been created with kthread_worker_create(). Returns %true + * must have been created with kthread_create_worker(). Returns %true * if @work was successfully queued, %false if it was already pending. * * Reinitialize the work if it needs to be used by another worker. diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 7a75eab9c179..d4281d1e13a6 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -77,7 +77,7 @@ static int sysctl_latencytop(const struct ctl_table *table, int write, void *buf return err; } -static struct ctl_table latencytop_sysctl[] = { +static const struct ctl_table latencytop_sysctl[] = { { .procname = "latencytop", .data = &latencytop_enabled, @@ -158,9 +158,9 @@ account_global_scheduler_latency(struct task_struct *tsk, /** * __account_scheduler_latency - record an occurred latency - * @tsk - the task struct of the task hitting the latency - * @usecs - the duration of the latency in microseconds - * @inter - 1 if the sleep was interruptible, 0 if uninterruptible + * @tsk: the task struct of the task hitting the latency + * @usecs: the duration of the latency in microseconds + * @inter: 1 if the sleep was interruptible, 0 if uninterruptible * * This function is the main entry point for recording latency entries * as called by the scheduler. diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 3c21c31796db..0cd39954d5a1 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -347,6 +347,7 @@ int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, * /sys/kernel/livepatch//transition * /sys/kernel/livepatch//force * /sys/kernel/livepatch//replace + * /sys/kernel/livepatch//stack_order * /sys/kernel/livepatch// * /sys/kernel/livepatch///patched * /sys/kernel/livepatch/// @@ -452,15 +453,38 @@ static ssize_t replace_show(struct kobject *kobj, return sysfs_emit(buf, "%d\n", patch->replace); } +static ssize_t stack_order_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct klp_patch *patch, *this_patch; + int stack_order = 0; + + this_patch = container_of(kobj, struct klp_patch, kobj); + + mutex_lock(&klp_mutex); + + klp_for_each_patch(patch) { + stack_order++; + if (patch == this_patch) + break; + } + + mutex_unlock(&klp_mutex); + + return sysfs_emit(buf, "%d\n", stack_order); +} + static struct kobj_attribute enabled_kobj_attr = __ATTR_RW(enabled); static struct kobj_attribute transition_kobj_attr = __ATTR_RO(transition); static struct kobj_attribute force_kobj_attr = __ATTR_WO(force); static struct kobj_attribute replace_kobj_attr = __ATTR_RO(replace); +static struct kobj_attribute stack_order_kobj_attr = __ATTR_RO(stack_order); static struct attribute *klp_patch_attrs[] = { &enabled_kobj_attr.attr, &transition_kobj_attr.attr, &force_kobj_attr.attr, &replace_kobj_attr.attr, + &stack_order_kobj_attr.attr, NULL }; ATTRIBUTE_GROUPS(klp_patch); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 2d8ec0351ef9..4470680f0226 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -79,7 +79,7 @@ module_param(lock_stat, int, 0644); #endif #ifdef CONFIG_SYSCTL -static struct ctl_table kern_lockdep_table[] = { +static const struct ctl_table kern_lockdep_table[] = { #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", @@ -157,10 +157,12 @@ static inline void lockdep_unlock(void) __this_cpu_dec(lockdep_recursion); } +#ifdef CONFIG_PROVE_LOCKING static inline bool lockdep_assert_locked(void) { return DEBUG_LOCKS_WARN_ON(__owner != current); } +#endif static struct task_struct *lockdep_selftest_task_struct; @@ -430,7 +432,7 @@ static inline u16 hlock_id(struct held_lock *hlock) return (hlock->class_idx | (hlock->read << MAX_LOCKDEP_KEYS_BITS)); } -static inline unsigned int chain_hlock_class_idx(u16 hlock_id) +static inline __maybe_unused unsigned int chain_hlock_class_idx(u16 hlock_id) { return hlock_id & (MAX_LOCKDEP_KEYS - 1); } diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index bbe9000260d0..20f9ef58d3d0 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -119,7 +119,8 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = #define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) -#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) +#define AVG_LOCKDEP_CHAIN_DEPTH 5 +#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS * AVG_LOCKDEP_CHAIN_DEPTH) extern struct lock_chain lock_chains[]; diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index de95ec07e477..cc33470f4de9 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -106,7 +106,7 @@ static const struct kernel_param_ops lt_bind_ops = { module_param_cb(bind_readers, <_bind_ops, &bind_readers, 0644); module_param_cb(bind_writers, <_bind_ops, &bind_writers, 0644); -long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask); +long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask, bool dowarn); static struct task_struct *stats_task; static struct task_struct **writer_tasks; @@ -1358,7 +1358,7 @@ static int __init lock_torture_init(void) if (torture_init_error(firsterr)) goto unwind; if (cpumask_nonempty(bind_writers)) - torture_sched_setaffinity(writer_tasks[i]->pid, bind_writers); + torture_sched_setaffinity(writer_tasks[i]->pid, bind_writers, true); create_reader: if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress)) @@ -1369,7 +1369,7 @@ static int __init lock_torture_init(void) if (torture_init_error(firsterr)) goto unwind; if (cpumask_nonempty(bind_readers)) - torture_sched_setaffinity(reader_tasks[j]->pid, bind_readers); + torture_sched_setaffinity(reader_tasks[j]->pid, bind_readers, true); } if (stat_interval > 0) { firsterr = torture_create_kthread(lock_torture_stats, NULL, diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 3302e52f0c96..b36f23de48f1 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -657,10 +657,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas goto err; } - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - /* Make sure we do wakeups before calling schedule */ - wake_up_q(&wake_q); - wake_q_init(&wake_q); + raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q); schedule_preempt_disabled(); @@ -710,8 +707,7 @@ skip_wait: if (ww_ctx) ww_mutex_lock_acquired(ww, ww_ctx); - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - wake_up_q(&wake_q); + raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q); preempt_enable(); return 0; @@ -720,10 +716,9 @@ err: __mutex_remove_waiter(lock, &waiter); err_early_kill: trace_contention_end(lock, ret); - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, ip); - wake_up_q(&wake_q); preempt_enable(); return ret; } @@ -935,10 +930,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne if (owner & MUTEX_FLAG_HANDOFF) __mutex_handoff(lock, next); - preempt_disable(); - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - wake_up_q(&wake_q); - preempt_enable(); + raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q); } #ifndef CONFIG_DEBUG_LOCK_ALLOC diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index e858de203eb6..4a8df1800cbb 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1292,7 +1292,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock, */ get_task_struct(owner); - raw_spin_unlock_irq(&lock->wait_lock); + raw_spin_unlock_irq_wake(&lock->wait_lock, wake_q); res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, next_lock, waiter, task); @@ -1596,6 +1596,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock, * or TASK_UNINTERRUPTIBLE) * @timeout: the pre-initialized and started timer, or NULL for none * @waiter: the pre-initialized rt_mutex_waiter + * @wake_q: wake_q of tasks to wake when we drop the lock->wait_lock * * Must be called with lock->wait_lock held and interrupts disabled */ @@ -1603,7 +1604,8 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock, struct ww_acquire_ctx *ww_ctx, unsigned int state, struct hrtimer_sleeper *timeout, - struct rt_mutex_waiter *waiter) + struct rt_mutex_waiter *waiter, + struct wake_q_head *wake_q) __releases(&lock->wait_lock) __acquires(&lock->wait_lock) { struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex); @@ -1634,7 +1636,7 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock, owner = rt_mutex_owner(lock); else owner = NULL; - raw_spin_unlock_irq(&lock->wait_lock); + raw_spin_unlock_irq_wake(&lock->wait_lock, wake_q); if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner)) rt_mutex_schedule(); @@ -1708,7 +1710,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock, ret = task_blocks_on_rt_mutex(lock, waiter, current, ww_ctx, chwalk, wake_q); if (likely(!ret)) - ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter); + ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter, wake_q); if (likely(!ret)) { /* acquired the lock */ @@ -1785,10 +1787,7 @@ static int __sched rt_mutex_slowlock(struct rt_mutex_base *lock, */ raw_spin_lock_irqsave(&lock->wait_lock, flags); ret = __rt_mutex_slowlock_locked(lock, ww_ctx, state, &wake_q); - preempt_disable(); - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - wake_up_q(&wake_q); - preempt_enable(); + raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q); rt_mutex_post_schedule(); return ret; @@ -1846,11 +1845,7 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock, owner = rt_mutex_owner(lock); else owner = NULL; - preempt_disable(); - raw_spin_unlock_irq(&lock->wait_lock); - wake_up_q(wake_q); - wake_q_init(wake_q); - preempt_enable(); + raw_spin_unlock_irq_wake(&lock->wait_lock, wake_q); if (!owner || !rtmutex_spin_on_owner(lock, &waiter, owner)) schedule_rtlock(); @@ -1879,10 +1874,7 @@ static __always_inline void __sched rtlock_slowlock(struct rt_mutex_base *lock) raw_spin_lock_irqsave(&lock->wait_lock, flags); rtlock_slowlock_locked(lock, &wake_q); - preempt_disable(); - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - wake_up_q(&wake_q); - preempt_enable(); + raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q); } #endif /* RT_MUTEX_BUILD_SPINLOCKS */ diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 33ea31d6a7b3..191e4720e546 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -383,7 +383,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, raw_spin_lock_irq(&lock->wait_lock); /* sleep on the mutex */ set_current_state(TASK_INTERRUPTIBLE); - ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter); + ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter, NULL); /* * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 5d58b2c0ef98..bcb1b9fea588 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -404,7 +404,7 @@ static inline u32 prandom_u32_below(u32 ceil) static int *get_random_order(int count) { int *order; - int n, r, tmp; + int n, r; order = kmalloc_array(count, sizeof(*order), GFP_KERNEL); if (!order) @@ -415,11 +415,8 @@ static int *get_random_order(int count) for (n = count - 1; n > 1; n--) { r = prandom_u32_below(n + 1); - if (r != n) { - tmp = order[n]; - order[n] = order[r]; - order[r] = tmp; - } + if (r != n) + swap(order[n], order[r]); } return order; diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 7b329057997a..d7762ef5949a 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -169,6 +169,36 @@ config MODVERSIONS make them incompatible with the kernel you are running. If unsure, say N. +choice + prompt "Module versioning implementation" + depends on MODVERSIONS + help + Select the tool used to calculate symbol versions for modules. + + If unsure, select GENKSYMS. + +config GENKSYMS + bool "genksyms (from source code)" + help + Calculate symbol versions from pre-processed source code using + genksyms. + + If unsure, say Y. + +config GENDWARFKSYMS + bool "gendwarfksyms (from debugging information)" + depends on DEBUG_INFO + # Requires full debugging information, split DWARF not supported. + depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT + # Requires ELF object files. + depends on !LTO + help + Calculate symbol versions from DWARF debugging information using + gendwarfksyms. Requires DEBUG_INFO to be enabled. + + If unsure, say N. +endchoice + config ASM_MODVERSIONS bool default HAVE_ASM_MODVERSIONS && MODVERSIONS @@ -177,6 +207,31 @@ config ASM_MODVERSIONS assembly. This can be enabled only when the target architecture supports it. +config EXTENDED_MODVERSIONS + bool "Extended Module Versioning Support" + depends on MODVERSIONS + help + This enables extended MODVERSIONs support, allowing long symbol + names to be versioned. + + The most likely reason you would enable this is to enable Rust + support. If unsure, say N. + +config BASIC_MODVERSIONS + bool "Basic Module Versioning Support" + depends on MODVERSIONS + default y + help + This enables basic MODVERSIONS support, allowing older tools or + kernels to potentially load modules. + + Disabling this may cause older `modprobe` or `kmod` to be unable + to read MODVERSIONS information from built modules. With this + disabled, older kernels may treat this module as unversioned. + + This is enabled by default when MODVERSIONS are enabled. + If unsure, say Y. + config MODULE_SRCVERSION_ALL bool "Source checksum for all modules" help @@ -231,6 +286,7 @@ comment "Do not forget to sign required modules with scripts/sign-file" choice prompt "Hash algorithm to sign modules" depends on MODULE_SIG || IMA_APPRAISE_MODSIG + default MODULE_SIG_SHA512 help This determines which sort of hashing algorithm will be used during signature generation. This algorithm _must_ be built into the kernel diff --git a/kernel/module/internal.h b/kernel/module/internal.h index daef2be83902..d09b46ef032f 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -47,16 +47,16 @@ struct kernel_symbol { extern struct mutex module_mutex; extern struct list_head modules; -extern struct module_attribute *modinfo_attrs[]; -extern size_t modinfo_attrs_count; +extern const struct module_attribute *const modinfo_attrs[]; +extern const size_t modinfo_attrs_count; /* Provided by the linker */ extern const struct kernel_symbol __start___ksymtab[]; extern const struct kernel_symbol __stop___ksymtab[]; extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; -extern const s32 __start___kcrctab[]; -extern const s32 __start___kcrctab_gpl[]; +extern const u32 __start___kcrctab[]; +extern const u32 __start___kcrctab_gpl[]; struct load_info { const char *name; @@ -86,6 +86,8 @@ struct load_info { unsigned int vers; unsigned int info; unsigned int pcpu; + unsigned int vers_ext_crc; + unsigned int vers_ext_name; } index; }; @@ -102,7 +104,7 @@ struct find_symbol_arg { /* Output */ struct module *owner; - const s32 *crc; + const u32 *crc; const struct kernel_symbol *sym; enum mod_license license; }; @@ -327,7 +329,8 @@ static inline struct module *mod_find(unsigned long addr, struct mod_tree_root * } #endif /* CONFIG_MODULES_TREE_LOOKUP */ -int module_enable_rodata_ro(const struct module *mod, bool after_init); +int module_enable_rodata_ro(const struct module *mod); +int module_enable_rodata_ro_after_init(const struct module *mod); int module_enable_data_nx(const struct module *mod); int module_enable_text_rox(const struct module *mod); int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, @@ -384,16 +387,25 @@ static inline void init_param_lock(struct module *mod) { } #ifdef CONFIG_MODVERSIONS int check_version(const struct load_info *info, - const char *symname, struct module *mod, const s32 *crc); + const char *symname, struct module *mod, const u32 *crc); void module_layout(struct module *mod, struct modversion_info *ver, struct kernel_param *kp, struct kernel_symbol *ks, struct tracepoint * const *tp); int check_modstruct_version(const struct load_info *info, struct module *mod); int same_magic(const char *amagic, const char *bmagic, bool has_crcs); +struct modversion_info_ext { + size_t remaining; + const u32 *crc; + const char *name; +}; +void modversion_ext_start(const struct load_info *info, struct modversion_info_ext *ver); +void modversion_ext_advance(struct modversion_info_ext *ver); +#define for_each_modversion_info_ext(ver, info) \ + for (modversion_ext_start(info, &ver); ver.remaining > 0; modversion_ext_advance(&ver)) #else /* !CONFIG_MODVERSIONS */ static inline int check_version(const struct load_info *info, const char *symname, struct module *mod, - const s32 *crc) + const u32 *crc) { return 1; } diff --git a/kernel/module/main.c b/kernel/module/main.c index 5399c182b3cb..1fb9ad289a6f 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -86,7 +86,7 @@ struct mod_tree_root mod_tree __cacheline_aligned = { struct symsearch { const struct kernel_symbol *start, *stop; - const s32 *crcs; + const u32 *crcs; enum mod_license license; }; @@ -538,7 +538,7 @@ static void setup_modinfo_##field(struct module *mod, const char *s) \ { \ mod->field = kstrdup(s, GFP_KERNEL); \ } \ -static ssize_t show_modinfo_##field(struct module_attribute *mattr, \ +static ssize_t show_modinfo_##field(const struct module_attribute *mattr, \ struct module_kobject *mk, char *buffer) \ { \ return scnprintf(buffer, PAGE_SIZE, "%s\n", mk->mod->field); \ @@ -552,7 +552,7 @@ static void free_modinfo_##field(struct module *mod) \ kfree(mod->field); \ mod->field = NULL; \ } \ -static struct module_attribute modinfo_##field = { \ +static const struct module_attribute modinfo_##field = { \ .attr = { .name = __stringify(field), .mode = 0444 }, \ .show = show_modinfo_##field, \ .setup = setup_modinfo_##field, \ @@ -842,13 +842,13 @@ void symbol_put_addr(void *addr) } EXPORT_SYMBOL_GPL(symbol_put_addr); -static ssize_t show_refcnt(struct module_attribute *mattr, +static ssize_t show_refcnt(const struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { return sprintf(buffer, "%i\n", module_refcount(mk->mod)); } -static struct module_attribute modinfo_refcnt = +static const struct module_attribute modinfo_refcnt = __ATTR(refcnt, 0444, show_refcnt, NULL); void __module_get(struct module *module) @@ -917,7 +917,7 @@ size_t module_flags_taint(unsigned long taints, char *buf) return l; } -static ssize_t show_initstate(struct module_attribute *mattr, +static ssize_t show_initstate(const struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { const char *state = "unknown"; @@ -938,10 +938,10 @@ static ssize_t show_initstate(struct module_attribute *mattr, return sprintf(buffer, "%s\n", state); } -static struct module_attribute modinfo_initstate = +static const struct module_attribute modinfo_initstate = __ATTR(initstate, 0444, show_initstate, NULL); -static ssize_t store_uevent(struct module_attribute *mattr, +static ssize_t store_uevent(const struct module_attribute *mattr, struct module_kobject *mk, const char *buffer, size_t count) { @@ -951,10 +951,10 @@ static ssize_t store_uevent(struct module_attribute *mattr, return rc ? rc : count; } -struct module_attribute module_uevent = +const struct module_attribute module_uevent = __ATTR(uevent, 0200, NULL, store_uevent); -static ssize_t show_coresize(struct module_attribute *mattr, +static ssize_t show_coresize(const struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { unsigned int size = mk->mod->mem[MOD_TEXT].size; @@ -966,11 +966,11 @@ static ssize_t show_coresize(struct module_attribute *mattr, return sprintf(buffer, "%u\n", size); } -static struct module_attribute modinfo_coresize = +static const struct module_attribute modinfo_coresize = __ATTR(coresize, 0444, show_coresize, NULL); #ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC -static ssize_t show_datasize(struct module_attribute *mattr, +static ssize_t show_datasize(const struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { unsigned int size = 0; @@ -980,11 +980,11 @@ static ssize_t show_datasize(struct module_attribute *mattr, return sprintf(buffer, "%u\n", size); } -static struct module_attribute modinfo_datasize = +static const struct module_attribute modinfo_datasize = __ATTR(datasize, 0444, show_datasize, NULL); #endif -static ssize_t show_initsize(struct module_attribute *mattr, +static ssize_t show_initsize(const struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { unsigned int size = 0; @@ -994,10 +994,10 @@ static ssize_t show_initsize(struct module_attribute *mattr, return sprintf(buffer, "%u\n", size); } -static struct module_attribute modinfo_initsize = +static const struct module_attribute modinfo_initsize = __ATTR(initsize, 0444, show_initsize, NULL); -static ssize_t show_taint(struct module_attribute *mattr, +static ssize_t show_taint(const struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { size_t l; @@ -1007,10 +1007,10 @@ static ssize_t show_taint(struct module_attribute *mattr, return l; } -static struct module_attribute modinfo_taint = +static const struct module_attribute modinfo_taint = __ATTR(taint, 0444, show_taint, NULL); -struct module_attribute *modinfo_attrs[] = { +const struct module_attribute *const modinfo_attrs[] = { &module_uevent, &modinfo_version, &modinfo_srcversion, @@ -1027,7 +1027,7 @@ struct module_attribute *modinfo_attrs[] = { NULL, }; -size_t modinfo_attrs_count = ARRAY_SIZE(modinfo_attrs); +const size_t modinfo_attrs_count = ARRAY_SIZE(modinfo_attrs); static const char vermagic[] = VERMAGIC_STRING; @@ -1681,7 +1681,7 @@ static void module_license_taint_check(struct module *mod, const char *license) static void setup_modinfo(struct module *mod, struct load_info *info) { - struct module_attribute *attr; + const struct module_attribute *attr; int i; for (i = 0; (attr = modinfo_attrs[i]); i++) { @@ -1692,7 +1692,7 @@ static void setup_modinfo(struct module *mod, struct load_info *info) static void free_modinfo(struct module *mod) { - struct module_attribute *attr; + const struct module_attribute *attr; int i; for (i = 0; (attr = modinfo_attrs[i]); i++) { @@ -2073,6 +2073,82 @@ static int elf_validity_cache_index_str(struct load_info *info) return 0; } +/** + * elf_validity_cache_index_versions() - Validate and cache version indices + * @info: Load info to cache version indices in. + * Must have &load_info->sechdrs and &load_info->secstrings populated. + * @flags: Load flags, relevant to suppress version loading, see + * uapi/linux/module.h + * + * If we're ignoring modversions based on @flags, zero all version indices + * and return validity. Othewrise check: + * + * * If "__version_ext_crcs" is present, "__version_ext_names" is present + * * There is a name present for every crc + * + * Then populate: + * + * * &load_info->index.vers + * * &load_info->index.vers_ext_crc + * * &load_info->index.vers_ext_names + * + * if present. + * + * Return: %0 if valid, %-ENOEXEC on failure. + */ +static int elf_validity_cache_index_versions(struct load_info *info, int flags) +{ + unsigned int vers_ext_crc; + unsigned int vers_ext_name; + size_t crc_count; + size_t remaining_len; + size_t name_size; + char *name; + + /* If modversions were suppressed, pretend we didn't find any */ + if (flags & MODULE_INIT_IGNORE_MODVERSIONS) { + info->index.vers = 0; + info->index.vers_ext_crc = 0; + info->index.vers_ext_name = 0; + return 0; + } + + vers_ext_crc = find_sec(info, "__version_ext_crcs"); + vers_ext_name = find_sec(info, "__version_ext_names"); + + /* If we have one field, we must have the other */ + if (!!vers_ext_crc != !!vers_ext_name) { + pr_err("extended version crc+name presence does not match"); + return -ENOEXEC; + } + + /* + * If we have extended version information, we should have the same + * number of entries in every section. + */ + if (vers_ext_crc) { + crc_count = info->sechdrs[vers_ext_crc].sh_size / sizeof(u32); + name = (void *)info->hdr + + info->sechdrs[vers_ext_name].sh_offset; + remaining_len = info->sechdrs[vers_ext_name].sh_size; + + while (crc_count--) { + name_size = strnlen(name, remaining_len) + 1; + if (name_size > remaining_len) { + pr_err("more extended version crcs than names"); + return -ENOEXEC; + } + remaining_len -= name_size; + name += name_size; + } + } + + info->index.vers = find_sec(info, "__versions"); + info->index.vers_ext_crc = vers_ext_crc; + info->index.vers_ext_name = vers_ext_name; + return 0; +} + /** * elf_validity_cache_index() - Resolve, validate, cache section indices * @info: Load info to read from and update. @@ -2087,9 +2163,7 @@ static int elf_validity_cache_index_str(struct load_info *info) * * elf_validity_cache_index_mod() * * elf_validity_cache_index_sym() * * elf_validity_cache_index_str() - * - * If versioning is not suppressed via flags, load the version index from - * a section called "__versions" with no validation. + * * elf_validity_cache_index_versions() * * If CONFIG_SMP is enabled, load the percpu section by name with no * validation. @@ -2112,11 +2186,9 @@ static int elf_validity_cache_index(struct load_info *info, int flags) err = elf_validity_cache_index_str(info); if (err < 0) return err; - - if (flags & MODULE_INIT_IGNORE_MODVERSIONS) - info->index.vers = 0; /* Pretend no __versions section! */ - else - info->index.vers = find_sec(info, "__versions"); + err = elf_validity_cache_index_versions(info, flags); + if (err < 0) + return err; info->index.pcpu = find_pcpusec(info); @@ -2327,16 +2399,29 @@ static int rewrite_section_headers(struct load_info *info, int flags) /* Track but don't keep modinfo and version sections. */ info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC; + info->sechdrs[info->index.vers_ext_crc].sh_flags &= + ~(unsigned long)SHF_ALLOC; + info->sechdrs[info->index.vers_ext_name].sh_flags &= + ~(unsigned long)SHF_ALLOC; info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC; return 0; } +static const char *const module_license_offenders[] = { + /* driverloader was caught wrongly pretending to be under GPL */ + "driverloader", + + /* lve claims to be GPL but upstream won't provide source */ + "lve", +}; + /* * These calls taint the kernel depending certain module circumstances */ static void module_augment_kernel_taints(struct module *mod, struct load_info *info) { int prev_taint = test_taint(TAINT_PROPRIETARY_MODULE); + size_t i; if (!get_modinfo(info, "intree")) { if (!test_taint(TAINT_OOT_MODULE)) @@ -2385,15 +2470,11 @@ static void module_augment_kernel_taints(struct module *mod, struct load_info *i if (strcmp(mod->name, "ndiswrapper") == 0) add_taint(TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); - /* driverloader was caught wrongly pretending to be under GPL */ - if (strcmp(mod->name, "driverloader") == 0) - add_taint_module(mod, TAINT_PROPRIETARY_MODULE, - LOCKDEP_NOW_UNRELIABLE); - - /* lve claims to be GPL but upstream won't provide source */ - if (strcmp(mod->name, "lve") == 0) - add_taint_module(mod, TAINT_PROPRIETARY_MODULE, - LOCKDEP_NOW_UNRELIABLE); + for (i = 0; i < ARRAY_SIZE(module_license_offenders); ++i) { + if (strcmp(mod->name, module_license_offenders[i]) == 0) + add_taint_module(mod, TAINT_PROPRIETARY_MODULE, + LOCKDEP_NOW_UNRELIABLE); + } if (!prev_taint && test_taint(TAINT_PROPRIETARY_MODULE)) pr_warn("%s: module license taints kernel.\n", mod->name); @@ -2948,9 +3029,12 @@ static noinline int do_init_module(struct module *mod) /* Switch to core kallsyms now init is done: kallsyms may be walking! */ rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms); #endif - ret = module_enable_rodata_ro(mod, true); + ret = module_enable_rodata_ro_after_init(mod); if (ret) - goto fail_mutex_unlock; + pr_warn("%s: module_enable_rodata_ro_after_init() returned %d, " + "ro_after_init data might still be writable\n", + mod->name, ret); + mod_tree_remove_init(mod); module_arch_freeing_init(mod); for_class_mod_mem_type(type, init) { @@ -2989,8 +3073,6 @@ static noinline int do_init_module(struct module *mod) return 0; -fail_mutex_unlock: - mutex_unlock(&module_mutex); fail_free_freeinit: kfree(freeinit); fail: @@ -3118,7 +3200,7 @@ static int complete_formation(struct module *mod, struct load_info *info) module_bug_finalize(info->hdr, info->sechdrs, mod); module_cfi_finalize(info->hdr, info->sechdrs, mod); - err = module_enable_rodata_ro(mod, false); + err = module_enable_rodata_ro(mod); if (err) goto out_strict_rwx; err = module_enable_data_nx(mod); diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c index 239e5013359d..74834ba15615 100644 --- a/kernel/module/strict_rwx.c +++ b/kernel/module/strict_rwx.c @@ -47,7 +47,7 @@ int module_enable_text_rox(const struct module *mod) return 0; } -int module_enable_rodata_ro(const struct module *mod, bool after_init) +int module_enable_rodata_ro(const struct module *mod) { int ret; @@ -61,12 +61,17 @@ int module_enable_rodata_ro(const struct module *mod, bool after_init) if (ret) return ret; - if (after_init) - return module_set_memory(mod, MOD_RO_AFTER_INIT, set_memory_ro); - return 0; } +int module_enable_rodata_ro_after_init(const struct module *mod) +{ + if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX) || !rodata_enabled) + return 0; + + return module_set_memory(mod, MOD_RO_AFTER_INIT, set_memory_ro); +} + int module_enable_data_nx(const struct module *mod) { if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) diff --git a/kernel/module/sysfs.c b/kernel/module/sysfs.c index 456358e1fdc4..b401ff4b02d2 100644 --- a/kernel/module/sysfs.c +++ b/kernel/module/sysfs.c @@ -19,24 +19,16 @@ * J. Corbet */ #ifdef CONFIG_KALLSYMS -struct module_sect_attr { - struct bin_attribute battr; - unsigned long address; -}; - struct module_sect_attrs { struct attribute_group grp; - unsigned int nsections; - struct module_sect_attr attrs[]; + struct bin_attribute attrs[]; }; #define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4)) static ssize_t module_sect_read(struct file *file, struct kobject *kobj, - struct bin_attribute *battr, + const struct bin_attribute *battr, char *buf, loff_t pos, size_t count) { - struct module_sect_attr *sattr = - container_of(battr, struct module_sect_attr, battr); char bounce[MODULE_SECT_READ_SIZE + 1]; size_t wrote; @@ -53,7 +45,7 @@ static ssize_t module_sect_read(struct file *file, struct kobject *kobj, */ wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n", kallsyms_show_value(file->f_cred) - ? (void *)sattr->address : NULL); + ? battr->private : NULL); count = min(count, wrote); memcpy(buf, bounce, count); @@ -62,59 +54,59 @@ static ssize_t module_sect_read(struct file *file, struct kobject *kobj, static void free_sect_attrs(struct module_sect_attrs *sect_attrs) { - unsigned int section; + const struct bin_attribute *const *bin_attr; - for (section = 0; section < sect_attrs->nsections; section++) - kfree(sect_attrs->attrs[section].battr.attr.name); + for (bin_attr = sect_attrs->grp.bin_attrs_new; *bin_attr; bin_attr++) + kfree((*bin_attr)->attr.name); + kfree(sect_attrs->grp.bin_attrs_new); kfree(sect_attrs); } static int add_sect_attrs(struct module *mod, const struct load_info *info) { - unsigned int nloaded = 0, i, size[2]; struct module_sect_attrs *sect_attrs; - struct module_sect_attr *sattr; - struct bin_attribute **gattr; + const struct bin_attribute **gattr; + struct bin_attribute *sattr; + unsigned int nloaded = 0, i; int ret; /* Count loaded sections and allocate structures */ for (i = 0; i < info->hdr->e_shnum; i++) if (!sect_empty(&info->sechdrs[i])) nloaded++; - size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded), - sizeof(sect_attrs->grp.bin_attrs[0])); - size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]); - sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL); + sect_attrs = kzalloc(struct_size(sect_attrs, attrs, nloaded), GFP_KERNEL); if (!sect_attrs) return -ENOMEM; + gattr = kcalloc(nloaded + 1, sizeof(*gattr), GFP_KERNEL); + if (!gattr) { + kfree(sect_attrs); + return -ENOMEM; + } + /* Setup section attributes. */ sect_attrs->grp.name = "sections"; - sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0]; + sect_attrs->grp.bin_attrs_new = gattr; - sect_attrs->nsections = 0; sattr = §_attrs->attrs[0]; - gattr = §_attrs->grp.bin_attrs[0]; for (i = 0; i < info->hdr->e_shnum; i++) { Elf_Shdr *sec = &info->sechdrs[i]; if (sect_empty(sec)) continue; - sysfs_bin_attr_init(&sattr->battr); - sattr->address = sec->sh_addr; - sattr->battr.attr.name = + sysfs_bin_attr_init(sattr); + sattr->attr.name = kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL); - if (!sattr->battr.attr.name) { + if (!sattr->attr.name) { ret = -ENOMEM; goto out; } - sect_attrs->nsections++; - sattr->battr.read = module_sect_read; - sattr->battr.size = MODULE_SECT_READ_SIZE; - sattr->battr.attr.mode = 0400; - *(gattr++) = &(sattr++)->battr; + sattr->read_new = module_sect_read; + sattr->private = (void *)sec->sh_addr; + sattr->size = MODULE_SECT_READ_SIZE; + sattr->attr.mode = 0400; + *(gattr++) = sattr++; } - *gattr = NULL; ret = sysfs_create_group(&mod->mkobj.kobj, §_attrs->grp); if (ret) @@ -146,20 +138,13 @@ static void remove_sect_attrs(struct module *mod) */ struct module_notes_attrs { - struct kobject *dir; - unsigned int notes; - struct bin_attribute attrs[] __counted_by(notes); + struct attribute_group grp; + struct bin_attribute attrs[]; }; -static void free_notes_attrs(struct module_notes_attrs *notes_attrs, - unsigned int i) +static void free_notes_attrs(struct module_notes_attrs *notes_attrs) { - if (notes_attrs->dir) { - while (i-- > 0) - sysfs_remove_bin_file(notes_attrs->dir, - ¬es_attrs->attrs[i]); - kobject_put(notes_attrs->dir); - } + kfree(notes_attrs->grp.bin_attrs_new); kfree(notes_attrs); } @@ -167,6 +152,7 @@ static int add_notes_attrs(struct module *mod, const struct load_info *info) { unsigned int notes, loaded, i; struct module_notes_attrs *notes_attrs; + const struct bin_attribute **gattr; struct bin_attribute *nattr; int ret; @@ -185,47 +171,55 @@ static int add_notes_attrs(struct module *mod, const struct load_info *info) if (!notes_attrs) return -ENOMEM; - notes_attrs->notes = notes; + gattr = kcalloc(notes + 1, sizeof(*gattr), GFP_KERNEL); + if (!gattr) { + kfree(notes_attrs); + return -ENOMEM; + } + + notes_attrs->grp.name = "notes"; + notes_attrs->grp.bin_attrs_new = gattr; + nattr = ¬es_attrs->attrs[0]; for (loaded = i = 0; i < info->hdr->e_shnum; ++i) { if (sect_empty(&info->sechdrs[i])) continue; if (info->sechdrs[i].sh_type == SHT_NOTE) { sysfs_bin_attr_init(nattr); - nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name; + nattr->attr.name = mod->sect_attrs->attrs[loaded].attr.name; nattr->attr.mode = 0444; nattr->size = info->sechdrs[i].sh_size; nattr->private = (void *)info->sechdrs[i].sh_addr; - nattr->read = sysfs_bin_attr_simple_read; - ++nattr; + nattr->read_new = sysfs_bin_attr_simple_read; + *(gattr++) = nattr++; } ++loaded; } - notes_attrs->dir = kobject_create_and_add("notes", &mod->mkobj.kobj); - if (!notes_attrs->dir) { - ret = -ENOMEM; + ret = sysfs_create_group(&mod->mkobj.kobj, ¬es_attrs->grp); + if (ret) goto out; - } - - for (i = 0; i < notes; ++i) { - ret = sysfs_create_bin_file(notes_attrs->dir, ¬es_attrs->attrs[i]); - if (ret) - goto out; - } mod->notes_attrs = notes_attrs; return 0; out: - free_notes_attrs(notes_attrs, i); + free_notes_attrs(notes_attrs); return ret; } static void remove_notes_attrs(struct module *mod) { - if (mod->notes_attrs) - free_notes_attrs(mod->notes_attrs, mod->notes_attrs->notes); + if (mod->notes_attrs) { + sysfs_remove_group(&mod->mkobj.kobj, + &mod->notes_attrs->grp); + /* + * We are positive that no one is using any notes attrs + * at this point. Deallocate immediately. + */ + free_notes_attrs(mod->notes_attrs); + mod->notes_attrs = NULL; + } } #else /* !CONFIG_KALLSYMS */ @@ -275,7 +269,7 @@ static int add_usage_links(struct module *mod) static void module_remove_modinfo_attrs(struct module *mod, int end) { - struct module_attribute *attr; + const struct module_attribute *attr; int i; for (i = 0; (attr = &mod->modinfo_attrs[i]); i++) { @@ -293,7 +287,7 @@ static void module_remove_modinfo_attrs(struct module *mod, int end) static int module_add_modinfo_attrs(struct module *mod) { - struct module_attribute *attr; + const struct module_attribute *attr; struct module_attribute *temp_attr; int error = 0; int i; diff --git a/kernel/module/version.c b/kernel/module/version.c index 53f43ac5a73e..3718a8868321 100644 --- a/kernel/module/version.c +++ b/kernel/module/version.c @@ -13,17 +13,34 @@ int check_version(const struct load_info *info, const char *symname, struct module *mod, - const s32 *crc) + const u32 *crc) { Elf_Shdr *sechdrs = info->sechdrs; unsigned int versindex = info->index.vers; unsigned int i, num_versions; struct modversion_info *versions; + struct modversion_info_ext version_ext; /* Exporting module didn't supply crcs? OK, we're already tainted. */ if (!crc) return 1; + /* If we have extended version info, rely on it */ + if (info->index.vers_ext_crc) { + for_each_modversion_info_ext(version_ext, info) { + if (strcmp(version_ext.name, symname) != 0) + continue; + if (*version_ext.crc == *crc) + return 1; + pr_debug("Found checksum %X vs module %X\n", + *crc, *version_ext.crc); + goto bad_version; + } + pr_warn_once("%s: no extended symbol version for %s\n", + info->name, symname); + return 1; + } + /* No versions at all? modprobe --force does this. */ if (versindex == 0) return try_to_force_load(mod, symname) == 0; @@ -87,6 +104,34 @@ int same_magic(const char *amagic, const char *bmagic, return strcmp(amagic, bmagic) == 0; } +void modversion_ext_start(const struct load_info *info, + struct modversion_info_ext *start) +{ + unsigned int crc_idx = info->index.vers_ext_crc; + unsigned int name_idx = info->index.vers_ext_name; + Elf_Shdr *sechdrs = info->sechdrs; + + /* + * Both of these fields are needed for this to be useful + * Any future fields should be initialized to NULL if absent. + */ + if (crc_idx == 0 || name_idx == 0) { + start->remaining = 0; + return; + } + + start->crc = (const u32 *)sechdrs[crc_idx].sh_addr; + start->name = (const char *)sechdrs[name_idx].sh_addr; + start->remaining = sechdrs[crc_idx].sh_size / sizeof(*start->crc); +} + +void modversion_ext_advance(struct modversion_info_ext *vers) +{ + vers->remaining--; + vers->crc++; + vers->name += strlen(vers->name) + 1; +} + /* * Generate the signature for all relevant module structures here. * If these change, we don't want to try to parse the module. diff --git a/kernel/padata.c b/kernel/padata.c index d51bbc76b227..418987056340 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -47,6 +47,22 @@ struct padata_mt_job_state { static void padata_free_pd(struct parallel_data *pd); static void __init padata_mt_helper(struct work_struct *work); +static inline void padata_get_pd(struct parallel_data *pd) +{ + refcount_inc(&pd->refcnt); +} + +static inline void padata_put_pd_cnt(struct parallel_data *pd, int cnt) +{ + if (refcount_sub_and_test(cnt, &pd->refcnt)) + padata_free_pd(pd); +} + +static inline void padata_put_pd(struct parallel_data *pd) +{ + padata_put_pd_cnt(pd, 1); +} + static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) { int cpu, target_cpu; @@ -206,7 +222,7 @@ int padata_do_parallel(struct padata_shell *ps, if ((pinst->flags & PADATA_RESET)) goto out; - refcount_inc(&pd->refcnt); + padata_get_pd(pd); padata->pd = pd; padata->cb_cpu = *cb_cpu; @@ -336,8 +352,14 @@ static void padata_reorder(struct parallel_data *pd) smp_mb(); reorder = per_cpu_ptr(pd->reorder_list, pd->cpu); - if (!list_empty(&reorder->list) && padata_find_next(pd, false)) + if (!list_empty(&reorder->list) && padata_find_next(pd, false)) { + /* + * Other context(eg. the padata_serial_worker) can finish the request. + * To avoid UAF issue, add pd ref here, and put pd ref after reorder_work finish. + */ + padata_get_pd(pd); queue_work(pinst->serial_wq, &pd->reorder_work); + } } static void invoke_padata_reorder(struct work_struct *work) @@ -348,6 +370,8 @@ static void invoke_padata_reorder(struct work_struct *work) pd = container_of(work, struct parallel_data, reorder_work); padata_reorder(pd); local_bh_enable(); + /* Pairs with putting the reorder_work in the serial_wq */ + padata_put_pd(pd); } static void padata_serial_worker(struct work_struct *serial_work) @@ -380,8 +404,7 @@ static void padata_serial_worker(struct work_struct *serial_work) } local_bh_enable(); - if (refcount_sub_and_test(cnt, &pd->refcnt)) - padata_free_pd(pd); + padata_put_pd_cnt(pd, cnt); } /** @@ -681,8 +704,7 @@ static int padata_replace(struct padata_instance *pinst) synchronize_rcu(); list_for_each_entry_continue_reverse(ps, &pinst->pslist, list) - if (refcount_dec_and_test(&ps->opd->refcnt)) - padata_free_pd(ps->opd); + padata_put_pd(ps->opd); pinst->flags &= ~PADATA_RESET; @@ -970,7 +992,7 @@ static ssize_t padata_sysfs_store(struct kobject *kobj, struct attribute *attr, pinst = kobj2pinst(kobj); pentry = attr2pentry(attr); - if (pentry->show) + if (pentry->store) ret = pentry->store(pinst, attr, buf, count); return ret; @@ -1121,11 +1143,16 @@ void padata_free_shell(struct padata_shell *ps) if (!ps) return; + /* + * Wait for all _do_serial calls to finish to avoid touching + * freed pd's and ps's. + */ + synchronize_rcu(); + mutex_lock(&ps->pinst->lock); list_del(&ps->list); pd = rcu_dereference_protected(ps->pd, 1); - if (refcount_dec_and_test(&pd->refcnt)) - padata_free_pd(pd); + padata_put_pd(pd); mutex_unlock(&ps->pinst->lock); kfree(ps); diff --git a/kernel/panic.c b/kernel/panic.c index fbc59b3b64d0..d8635d5cecb2 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -84,7 +84,7 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); #ifdef CONFIG_SYSCTL -static struct ctl_table kern_panic_table[] = { +static const struct ctl_table kern_panic_table[] = { #ifdef CONFIG_SMP { .procname = "oops_all_cpu_backtrace", diff --git a/kernel/params.c b/kernel/params.c index 2e447f8ae183..0074d29c9b80 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -538,7 +538,7 @@ const struct kernel_param_ops param_ops_string = { EXPORT_SYMBOL(param_ops_string); /* sysfs output in /sys/modules/XYZ/parameters/ */ -#define to_module_attr(n) container_of(n, struct module_attribute, attr) +#define to_module_attr(n) container_of_const(n, struct module_attribute, attr) #define to_module_kobject(n) container_of(n, struct module_kobject, kobj) struct param_attribute @@ -555,13 +555,13 @@ struct module_param_attrs }; #ifdef CONFIG_SYSFS -#define to_param_attr(n) container_of(n, struct param_attribute, mattr) +#define to_param_attr(n) container_of_const(n, struct param_attribute, mattr) -static ssize_t param_attr_show(struct module_attribute *mattr, +static ssize_t param_attr_show(const struct module_attribute *mattr, struct module_kobject *mk, char *buf) { int count; - struct param_attribute *attribute = to_param_attr(mattr); + const struct param_attribute *attribute = to_param_attr(mattr); if (!attribute->param->ops->get) return -EPERM; @@ -573,12 +573,12 @@ static ssize_t param_attr_show(struct module_attribute *mattr, } /* sysfs always hands a nul-terminated string in buf. We rely on that. */ -static ssize_t param_attr_store(struct module_attribute *mattr, +static ssize_t param_attr_store(const struct module_attribute *mattr, struct module_kobject *mk, const char *buf, size_t len) { int err; - struct param_attribute *attribute = to_param_attr(mattr); + const struct param_attribute *attribute = to_param_attr(mattr); if (!attribute->param->ops->set) return -EPERM; @@ -857,11 +857,11 @@ static void __init param_sysfs_builtin(void) } } -ssize_t __modver_version_show(struct module_attribute *mattr, +ssize_t __modver_version_show(const struct module_attribute *mattr, struct module_kobject *mk, char *buf) { - struct module_version_attribute *vattr = - container_of(mattr, struct module_version_attribute, mattr); + const struct module_version_attribute *vattr = + container_of_const(mattr, struct module_version_attribute, mattr); return scnprintf(buf, PAGE_SIZE, "%s\n", vattr->version); } @@ -892,7 +892,7 @@ static ssize_t module_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { - struct module_attribute *attribute; + const struct module_attribute *attribute; struct module_kobject *mk; int ret; @@ -911,7 +911,7 @@ static ssize_t module_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t len) { - struct module_attribute *attribute; + const struct module_attribute *attribute; struct module_kobject *mk; int ret; diff --git a/kernel/pid.c b/kernel/pid.c index 115448e89c3e..924084713be8 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -60,15 +61,8 @@ struct pid init_struct_pid = { }, } }; -int pid_max = PID_MAX_DEFAULT; - -int pid_max_min = RESERVED_PIDS + 1; -int pid_max_max = PID_MAX_LIMIT; -/* - * Pseudo filesystems start inode numbering after one. We use Reserved - * PIDs as a natural offset. - */ -static u64 pidfs_ino = RESERVED_PIDS; +static int pid_max_min = RESERVED_PIDS + 1; +static int pid_max_max = PID_MAX_LIMIT; /* * PID-map pages start out as NULL, they get allocated upon @@ -87,6 +81,7 @@ struct pid_namespace init_pid_ns = { #ifdef CONFIG_PID_NS .ns.ops = &pidns_operations, #endif + .pid_max = PID_MAX_DEFAULT, #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) .memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC, #endif @@ -108,6 +103,7 @@ EXPORT_SYMBOL_GPL(init_pid_ns); */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); +seqcount_spinlock_t pidmap_lock_seq = SEQCNT_SPINLOCK_ZERO(pidmap_lock_seq, &pidmap_lock); void put_pid(struct pid *pid) { @@ -158,6 +154,7 @@ void free_pid(struct pid *pid) idr_remove(&ns->idr, upid->nr); } + pidfs_remove_pid(pid); spin_unlock_irqrestore(&pidmap_lock, flags); call_rcu(&pid->rcu, delayed_put_pid); @@ -193,6 +190,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, for (i = ns->level; i >= 0; i--) { int tid = 0; + int pid_max = READ_ONCE(tmp->pid_max); if (set_tid_size) { tid = set_tid[ns->level - i]; @@ -273,22 +271,24 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, INIT_HLIST_HEAD(&pid->inodes); upid = pid->numbers + ns->level; + idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; - pid->stashed = NULL; - pid->ino = ++pidfs_ino; + pidfs_add_pid(pid); for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock_irq(&pidmap_lock); + idr_preload_end(); return pid; out_unlock: spin_unlock_irq(&pidmap_lock); + idr_preload_end(); put_pid_ns(ns); out_free: @@ -644,17 +644,118 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) return fd; } +#ifdef CONFIG_SYSCTL +static struct ctl_table_set *pid_table_root_lookup(struct ctl_table_root *root) +{ + return &task_active_pid_ns(current)->set; +} + +static int set_is_seen(struct ctl_table_set *set) +{ + return &task_active_pid_ns(current)->set == set; +} + +static int pid_table_root_permissions(struct ctl_table_header *head, + const struct ctl_table *table) +{ + struct pid_namespace *pidns = + container_of(head->set, struct pid_namespace, set); + int mode = table->mode; + + if (ns_capable(pidns->user_ns, CAP_SYS_ADMIN) || + uid_eq(current_euid(), make_kuid(pidns->user_ns, 0))) + mode = (mode & S_IRWXU) >> 6; + else if (in_egroup_p(make_kgid(pidns->user_ns, 0))) + mode = (mode & S_IRWXG) >> 3; + else + mode = mode & S_IROTH; + return (mode << 6) | (mode << 3) | mode; +} + +static void pid_table_root_set_ownership(struct ctl_table_header *head, + kuid_t *uid, kgid_t *gid) +{ + struct pid_namespace *pidns = + container_of(head->set, struct pid_namespace, set); + kuid_t ns_root_uid; + kgid_t ns_root_gid; + + ns_root_uid = make_kuid(pidns->user_ns, 0); + if (uid_valid(ns_root_uid)) + *uid = ns_root_uid; + + ns_root_gid = make_kgid(pidns->user_ns, 0); + if (gid_valid(ns_root_gid)) + *gid = ns_root_gid; +} + +static struct ctl_table_root pid_table_root = { + .lookup = pid_table_root_lookup, + .permissions = pid_table_root_permissions, + .set_ownership = pid_table_root_set_ownership, +}; + +static const struct ctl_table pid_table[] = { + { + .procname = "pid_max", + .data = &init_pid_ns.pid_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &pid_max_min, + .extra2 = &pid_max_max, + }, +}; +#endif + +int register_pidns_sysctls(struct pid_namespace *pidns) +{ +#ifdef CONFIG_SYSCTL + struct ctl_table *tbl; + + setup_sysctl_set(&pidns->set, &pid_table_root, set_is_seen); + + tbl = kmemdup(pid_table, sizeof(pid_table), GFP_KERNEL); + if (!tbl) + return -ENOMEM; + tbl->data = &pidns->pid_max; + pidns->pid_max = min(pid_max_max, max_t(int, pidns->pid_max, + PIDS_PER_CPU_DEFAULT * num_possible_cpus())); + + pidns->sysctls = __register_sysctl_table(&pidns->set, "kernel", tbl, + ARRAY_SIZE(pid_table)); + if (!pidns->sysctls) { + kfree(tbl); + retire_sysctl_set(&pidns->set); + return -ENOMEM; + } +#endif + return 0; +} + +void unregister_pidns_sysctls(struct pid_namespace *pidns) +{ +#ifdef CONFIG_SYSCTL + const struct ctl_table *tbl; + + tbl = pidns->sysctls->ctl_table_arg; + unregister_sysctl_table(pidns->sysctls); + retire_sysctl_set(&pidns->set); + kfree(tbl); +#endif +} + void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ - pid_max = min(pid_max_max, max_t(int, pid_max, - PIDS_PER_CPU_DEFAULT * num_possible_cpus())); + init_pid_ns.pid_max = min(pid_max_max, max_t(int, init_pid_ns.pid_max, + PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); - pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); + pr_info("pid_max: default: %u minimum: %u\n", init_pid_ns.pid_max, pid_max_min); idr_init(&init_pid_ns.idr); @@ -665,6 +766,16 @@ void __init pid_idr_init(void) NULL); } +static __init int pid_namespace_sysctl_init(void) +{ +#ifdef CONFIG_SYSCTL + /* "kernel" directory will have already been initialized. */ + BUG_ON(register_pidns_sysctls(&init_pid_ns)); +#endif + return 0; +} +subsys_initcall(pid_namespace_sysctl_init); + static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index d70ab49d5b4a..8f6cfec87555 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -70,6 +70,8 @@ static void dec_pid_namespaces(struct ucounts *ucounts) dec_ucount(ucounts, UCOUNT_PID_NAMESPACES); } +static void destroy_pid_namespace_work(struct work_struct *work); + static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns, struct pid_namespace *parent_pid_ns) { @@ -105,17 +107,27 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns goto out_free_idr; ns->ns.ops = &pidns_operations; + ns->pid_max = parent_pid_ns->pid_max; + err = register_pidns_sysctls(ns); + if (err) + goto out_free_inum; + refcount_set(&ns->ns.count, 1); ns->level = level; ns->parent = get_pid_ns(parent_pid_ns); ns->user_ns = get_user_ns(user_ns); ns->ucounts = ucounts; ns->pid_allocated = PIDNS_ADDING; + INIT_WORK(&ns->work, destroy_pid_namespace_work); + #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) ns->memfd_noexec_scope = pidns_memfd_noexec_scope(parent_pid_ns); #endif + return ns; +out_free_inum: + ns_free_inum(&ns->ns); out_free_idr: idr_destroy(&ns->idr); kmem_cache_free(pid_ns_cachep, ns); @@ -137,12 +149,28 @@ static void delayed_free_pidns(struct rcu_head *p) static void destroy_pid_namespace(struct pid_namespace *ns) { + unregister_pidns_sysctls(ns); + ns_free_inum(&ns->ns); idr_destroy(&ns->idr); call_rcu(&ns->rcu, delayed_free_pidns); } +static void destroy_pid_namespace_work(struct work_struct *work) +{ + struct pid_namespace *ns = + container_of(work, struct pid_namespace, work); + + do { + struct pid_namespace *parent; + + parent = ns->parent; + destroy_pid_namespace(ns); + ns = parent; + } while (ns != &init_pid_ns && refcount_dec_and_test(&ns->ns.count)); +} + struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *old_ns) { @@ -155,15 +183,8 @@ struct pid_namespace *copy_pid_ns(unsigned long flags, void put_pid_ns(struct pid_namespace *ns) { - struct pid_namespace *parent; - - while (ns != &init_pid_ns) { - parent = ns->parent; - if (!refcount_dec_and_test(&ns->ns.count)) - break; - destroy_pid_namespace(ns); - ns = parent; - } + if (ns && ns != &init_pid_ns && refcount_dec_and_test(&ns->ns.count)) + schedule_work(&ns->work); } EXPORT_SYMBOL_GPL(put_pid_ns); @@ -274,6 +295,7 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write, next = idr_get_cursor(&pid_ns->idr) - 1; tmp.data = &next; + tmp.extra2 = &pid_ns->pid_max; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (!ret && write) idr_set_cursor(&pid_ns->idr, next + 1); @@ -281,15 +303,14 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write, return ret; } -extern int pid_max; -static struct ctl_table pid_ns_ctl_table[] = { +static const struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", .maxlen = sizeof(int), .mode = 0666, /* permissions are checked in the handler */ .proc_handler = pid_ns_ctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &pid_max, + .extra2 = &init_pid_ns.pid_max, }, }; #endif /* CONFIG_CHECKPOINT_RESTORE */ diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h index 18ecaef6be41..5d8f981de7c5 100644 --- a/kernel/pid_sysctl.h +++ b/kernel/pid_sysctl.h @@ -31,7 +31,7 @@ static int pid_mfd_noexec_dointvec_minmax(const struct ctl_table *table, return err; } -static struct ctl_table pid_ns_ctl_table_vm[] = { +static const struct ctl_table pid_ns_ctl_table_vm[] = { { .procname = "memfd_noexec", .data = &init_pid_ns.memfd_noexec_scope, diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index afce8130d8b9..ca947ed32e3d 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -257,11 +257,30 @@ config DPM_WATCHDOG boot session. config DPM_WATCHDOG_TIMEOUT - int "Watchdog timeout in seconds" + int "Watchdog timeout to panic in seconds" range 1 120 default 120 depends on DPM_WATCHDOG +config DPM_WATCHDOG_WARNING_TIMEOUT + int "Watchdog timeout to warn in seconds" + range 1 DPM_WATCHDOG_TIMEOUT + default DPM_WATCHDOG_TIMEOUT + depends on DPM_WATCHDOG + help + If the DPM watchdog warning timeout and main timeout are + different then a non-fatal warning (with a stack trace of + the stuck suspend routine) will be printed when the warning + timeout expires. If the suspend routine gets un-stuck + before the main timeout expires then no other action is + taken. If the routine continues to be stuck and the main + timeout expires then an emergency-level message and stack + trace will be printed and the system will panic. + + If the warning timeout is equal to the main timeout (the + default) then the warning will never happen and the system + will jump straight to panic when the main timeout expires. + config PM_TRACE bool help diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c index b29c8aca7486..865df641b97c 100644 --- a/kernel/power/autosleep.c +++ b/kernel/power/autosleep.c @@ -9,7 +9,6 @@ #include #include -#include #include "power.h" diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index d07faf42eace..3874f0e97651 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -908,3 +908,20 @@ int em_update_performance_limits(struct em_perf_domain *pd, return 0; } EXPORT_SYMBOL_GPL(em_update_performance_limits); + +static void rebuild_sd_workfn(struct work_struct *work) +{ + rebuild_sched_domains_energy(); +} + +void em_rebuild_sched_domains(void) +{ + static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn); + + /* + * When called from the cpufreq_register_driver() path, the + * cpu_hotplug_lock is already held, so use a work item to + * avoid nested locking in rebuild_sched_domains(). + */ + schedule_work(&rebuild_sd_work); +} diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 1f87aa01ba44..10a01af63a80 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -608,7 +608,11 @@ int hibernation_platform_enter(void) local_irq_disable(); system_state = SYSTEM_SUSPEND; - syscore_suspend(); + + error = syscore_suspend(); + if (error) + goto Enable_irqs; + if (pm_wakeup_pending()) { error = -EAGAIN; goto Power_up; @@ -620,6 +624,7 @@ int hibernation_platform_enter(void) Power_up: syscore_resume(); + Enable_irqs: system_state = SYSTEM_RUNNING; local_irq_enable(); diff --git a/kernel/power/power.h b/kernel/power/power.h index de0e6b1077f2..c352dea2f67b 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -110,7 +110,7 @@ extern int hibernate_preallocate_memory(void); extern void clear_or_poison_free_pages(void); -/** +/* * Auxiliary structure used for reading the snapshot image data and * metadata from and writing them to the list of page backup entries * (PBEs) which is the main data structure of swsusp. diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 30894d8f0a78..c9fb559a6399 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1011,11 +1011,8 @@ void __init register_nosave_region(unsigned long start_pfn, unsigned long end_pf } } /* This allocation cannot fail */ - region = memblock_alloc(sizeof(struct nosave_region), + region = memblock_alloc_or_panic(sizeof(struct nosave_region), SMP_CACHE_BYTES); - if (!region) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct nosave_region)); region->start_pfn = start_pfn; region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index c6bb47666aef..a91bdf802967 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -338,3 +338,9 @@ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped); void console_prepend_replay(struct printk_message *pmsg); #endif + +#ifdef CONFIG_SMP +bool is_printk_cpu_sync_owner(void); +#else +static inline bool is_printk_cpu_sync_owner(void) { return false; } +#endif diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 80910bc3470c..07668433644b 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -523,7 +523,7 @@ static struct latched_seq clear_seq = { /* record buffer */ #define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) -#define LOG_BUF_LEN_MAX (u32)(1 << 31) +#define LOG_BUF_LEN_MAX ((u32)1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; @@ -4922,6 +4922,11 @@ void console_try_replay_all(void) static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1); static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0); +bool is_printk_cpu_sync_owner(void) +{ + return (atomic_read(&printk_cpu_sync_owner) == raw_smp_processor_id()); +} + /** * __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant * spinning lock is not owned by any CPU. diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 6f94418d53ff..32a28f563b13 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -61,10 +61,15 @@ bool is_printk_legacy_deferred(void) /* * The per-CPU variable @printk_context can be read safely in any * context. CPU migration is always disabled when set. + * + * A context holding the printk_cpu_sync must not spin waiting for + * another CPU. For legacy printing, it could be the console_lock + * or the port lock. */ return (force_legacy_kthread() || this_cpu_read(printk_context) || - in_nmi()); + in_nmi() || + is_printk_cpu_sync_owner()); } asmlinkage int vprintk(const char *fmt, va_list args) @@ -74,15 +79,6 @@ asmlinkage int vprintk(const char *fmt, va_list args) if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif - - /* - * Use the main logbuf even in NMI. But avoid calling console - * drivers that might have their own locks. - */ - if (is_printk_legacy_deferred()) - return vprintk_deferred(fmt, args); - - /* No obstacles. */ return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c index f5072dc85f7a..da77f3f5c1fe 100644 --- a/kernel/printk/sysctl.c +++ b/kernel/printk/sysctl.c @@ -20,7 +20,7 @@ static int proc_dointvec_minmax_sysadmin(const struct ctl_table *table, int writ return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table printk_sysctls[] = { +static const struct ctl_table printk_sysctls[] = { { .procname = "printk", .data = &console_loglevel, diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 9b0b52e1836f..6af90510a1ca 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -53,6 +53,37 @@ config RCU_TORTURE_TEST Say M if you want the RCU torture tests to build as a module. Say N if you are unsure. +config RCU_TORTURE_TEST_CHK_RDR_STATE + tristate "Check rcutorture reader state" + depends on RCU_TORTURE_TEST + default n + help + This option causes rcutorture to check the desired rcutorture + reader state for each segment against the actual context. + Note that PREEMPT_COUNT must be enabled if the preempt-disabled + and bh-disabled checks are to take effect, and that PREEMPT_RCU + must be enabled for the RCU-nesting checks to take effect. + These checks add overhead, and this Kconfig options is therefore + disabled by default. + + Say Y here if you want rcutorture reader contexts checked. + Say N if you are unsure. + +config RCU_TORTURE_TEST_LOG_CPU + tristate "Log CPU for rcutorture failures" + depends on RCU_TORTURE_TEST + default n + help + This option causes rcutorture to decorate each entry of its + log of failure/close-call rcutorture reader segments with the + number of the CPU that the reader was running on at the time. + This information can be useful, but it does incur additional + overhead, overhead that can make both failures and close calls + less probable. + + Say Y here if you want CPU IDs logged. + Say N if you are unsure. + config RCU_REF_SCALE_TEST tristate "Scalability tests for read-side synchronization (RCU and others)" depends on DEBUG_KERNEL diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 612d27690335..d26fb1d33ed9 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -92,12 +92,20 @@ torture_param(bool, gp_cond_exp, false, "Use conditional/async expedited GP wait torture_param(bool, gp_cond_full, false, "Use conditional/async full-state GP wait primitives"); torture_param(bool, gp_cond_exp_full, false, "Use conditional/async full-stateexpedited GP wait primitives"); +torture_param(int, gp_cond_wi, 16 * USEC_PER_SEC / HZ, + "Wait interval for normal conditional grace periods, us (default 16 jiffies)"); +torture_param(int, gp_cond_wi_exp, 128, + "Wait interval for expedited conditional grace periods, us (default 128 us)"); torture_param(bool, gp_exp, false, "Use expedited GP wait primitives"); torture_param(bool, gp_normal, false, "Use normal (non-expedited) GP wait primitives"); torture_param(bool, gp_poll, false, "Use polling GP wait primitives"); torture_param(bool, gp_poll_exp, false, "Use polling expedited GP wait primitives"); torture_param(bool, gp_poll_full, false, "Use polling full-state GP wait primitives"); torture_param(bool, gp_poll_exp_full, false, "Use polling full-state expedited GP wait primitives"); +torture_param(int, gp_poll_wi, 16 * USEC_PER_SEC / HZ, + "Wait interval for normal polled grace periods, us (default 16 jiffies)"); +torture_param(int, gp_poll_wi_exp, 128, + "Wait interval for expedited polled grace periods, us (default 128 us)"); torture_param(bool, gp_sync, false, "Use synchronous GP wait primitives"); torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers"); torture_param(int, leakpointer, 0, "Leak pointer dereferences from readers"); @@ -109,9 +117,11 @@ torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (jiffies), 0=disable"); torture_param(int, nocbs_nthreads, 0, "Number of NOCB toggle threads, 0 to disable"); torture_param(int, nocbs_toggle, 1000, "Time between toggling nocb state (ms)"); +torture_param(int, preempt_duration, 0, "Preemption duration (ms), zero to disable"); +torture_param(int, preempt_interval, MSEC_PER_SEC, "Interval between preemptions (ms)"); torture_param(int, read_exit_delay, 13, "Delay between read-then-exit episodes (s)"); torture_param(int, read_exit_burst, 16, "# of read-then-exit bursts per episode, zero to disable"); -torture_param(int, reader_flavor, 0x1, "Reader flavors to use, one per bit."); +torture_param(int, reader_flavor, SRCU_READ_FLAVOR_NORMAL, "Reader flavors to use, one per bit."); torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles"); torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); @@ -149,6 +159,7 @@ static struct task_struct **fwd_prog_tasks; static struct task_struct **barrier_cbs_tasks; static struct task_struct *barrier_task; static struct task_struct *read_exit_task; +static struct task_struct *preempt_task; #define RCU_TORTURE_PIPE_LEN 10 @@ -259,10 +270,13 @@ struct rt_read_seg { unsigned long rt_delay_ms; unsigned long rt_delay_us; bool rt_preempted; + int rt_cpu; + int rt_end_cpu; }; static int err_segs_recorded; static struct rt_read_seg err_segs[RCUTORTURE_RDR_MAX_SEGS]; static int rt_read_nsegs; +static int rt_read_preempted; static const char *rcu_torture_writer_state_getname(void) { @@ -353,7 +367,8 @@ struct rcu_torture_ops { void (*read_delay)(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp); void (*readunlock)(int idx); - int (*readlock_held)(void); + int (*readlock_held)(void); // lockdep. + int (*readlock_nesting)(void); // actual nesting, if available, -1 if not. unsigned long (*get_gp_seq)(void); unsigned long (*gp_diff)(unsigned long new, unsigned long old); void (*deferred_free)(struct rcu_torture *p); @@ -390,6 +405,7 @@ struct rcu_torture_ops { void (*get_gp_data)(int *flags, unsigned long *gp_seq); void (*gp_slow_register)(atomic_t *rgssp); void (*gp_slow_unregister)(atomic_t *rgssp); + bool (*reader_blocked)(void); long cbflood_max; int irq_capable; int can_boost; @@ -448,10 +464,8 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) rtrsp->rt_delay_us = shortdelay_us; } if (!preempt_count() && - !(torture_random(rrsp) % (nrealreaders * 500))) { + !(torture_random(rrsp) % (nrealreaders * 500))) torture_preempt_schedule(); /* QS only if preemptible. */ - rtrsp->rt_preempted = true; - } } static void rcu_torture_read_unlock(int idx) @@ -459,6 +473,15 @@ static void rcu_torture_read_unlock(int idx) rcu_read_unlock(); } +static int rcu_torture_readlock_nesting(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) + return rcu_preempt_depth(); + if (IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return (preempt_count() & PREEMPT_MASK); + return -1; +} + /* * Update callback in the pipe. This should be invoked after a grace period. */ @@ -548,6 +571,7 @@ static struct rcu_torture_ops rcu_ops = { .read_delay = rcu_read_delay, .readunlock = rcu_torture_read_unlock, .readlock_held = torture_readlock_not_held, + .readlock_nesting = rcu_torture_readlock_nesting, .get_gp_seq = rcu_get_gp_seq, .gp_diff = rcu_seq_diff, .deferred_free = rcu_torture_deferred_free, @@ -573,6 +597,7 @@ static struct rcu_torture_ops rcu_ops = { .start_gp_poll_exp_full = start_poll_synchronize_rcu_expedited_full, .poll_gp_state_exp = poll_state_synchronize_rcu, .cond_sync_exp = cond_synchronize_rcu_expedited, + .cond_sync_exp_full = cond_synchronize_rcu_expedited_full, .call = call_rcu_hurry, .cb_barrier = rcu_barrier, .fqs = rcu_force_quiescent_state, @@ -582,6 +607,9 @@ static struct rcu_torture_ops rcu_ops = { .get_gp_data = rcutorture_get_gp_data, .gp_slow_register = rcu_gp_slow_register, .gp_slow_unregister = rcu_gp_slow_unregister, + .reader_blocked = IS_ENABLED(CONFIG_RCU_TORTURE_TEST_LOG_CPU) + ? has_rcu_reader_blocked + : NULL, .irq_capable = 1, .can_boost = IS_ENABLED(CONFIG_RCU_BOOST), .extendables = RCUTORTURE_MAX_EXTEND, @@ -628,6 +656,7 @@ static struct rcu_torture_ops rcu_busted_ops = { .exp_sync = synchronize_rcu_busted, .call = call_rcu_busted, .irq_capable = 1, + .extendables = RCUTORTURE_MAX_EXTEND, .name = "busted" }; @@ -650,17 +679,17 @@ static int srcu_torture_read_lock(void) int idx; int ret = 0; - if ((reader_flavor & 0x1) || !(reader_flavor & 0x7)) { + if ((reader_flavor & SRCU_READ_FLAVOR_NORMAL) || !(reader_flavor & SRCU_READ_FLAVOR_ALL)) { idx = srcu_read_lock(srcu_ctlp); WARN_ON_ONCE(idx & ~0x1); ret += idx; } - if (reader_flavor & 0x2) { + if (reader_flavor & SRCU_READ_FLAVOR_NMI) { idx = srcu_read_lock_nmisafe(srcu_ctlp); WARN_ON_ONCE(idx & ~0x1); ret += idx << 1; } - if (reader_flavor & 0x4) { + if (reader_flavor & SRCU_READ_FLAVOR_LITE) { idx = srcu_read_lock_lite(srcu_ctlp); WARN_ON_ONCE(idx & ~0x1); ret += idx << 2; @@ -690,11 +719,11 @@ srcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) static void srcu_torture_read_unlock(int idx) { WARN_ON_ONCE((reader_flavor && (idx & ~reader_flavor)) || (!reader_flavor && (idx & ~0x1))); - if (reader_flavor & 0x4) + if (reader_flavor & SRCU_READ_FLAVOR_LITE) srcu_read_unlock_lite(srcu_ctlp, (idx & 0x4) >> 2); - if (reader_flavor & 0x2) + if (reader_flavor & SRCU_READ_FLAVOR_NMI) srcu_read_unlock_nmisafe(srcu_ctlp, (idx & 0x2) >> 1); - if ((reader_flavor & 0x1) || !(reader_flavor & 0x7)) + if ((reader_flavor & SRCU_READ_FLAVOR_NORMAL) || !(reader_flavor & SRCU_READ_FLAVOR_ALL)) srcu_read_unlock(srcu_ctlp, idx & 0x1); } @@ -857,7 +886,7 @@ static void synchronize_rcu_trivial(void) int cpu; for_each_online_cpu(cpu) { - torture_sched_setaffinity(current->pid, cpumask_of(cpu)); + torture_sched_setaffinity(current->pid, cpumask_of(cpu), true); WARN_ON_ONCE(raw_smp_processor_id() != cpu); } } @@ -1347,6 +1376,7 @@ static void rcu_torture_write_types(void) pr_alert("%s: gp_sync without primitives.\n", __func__); } pr_alert("%s: Testing %d update types.\n", __func__, nsynctypes); + pr_info("%s: gp_cond_wi %d gp_cond_wi_exp %d gp_poll_wi %d gp_poll_wi_exp %d\n", __func__, gp_cond_wi, gp_cond_wi_exp, gp_poll_wi, gp_poll_wi_exp); } /* @@ -1513,7 +1543,8 @@ rcu_torture_writer(void *arg) case RTWS_COND_GET: rcu_torture_writer_state = RTWS_COND_GET; gp_snap = cur_ops->get_gp_state(); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_cond_wi, + 1000, &rand); rcu_torture_writer_state = RTWS_COND_SYNC; cur_ops->cond_sync(gp_snap); rcu_torture_pipe_update(old_rp); @@ -1521,7 +1552,8 @@ rcu_torture_writer(void *arg) case RTWS_COND_GET_EXP: rcu_torture_writer_state = RTWS_COND_GET_EXP; gp_snap = cur_ops->get_gp_state_exp(); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_cond_wi_exp, + 1000, &rand); rcu_torture_writer_state = RTWS_COND_SYNC_EXP; cur_ops->cond_sync_exp(gp_snap); rcu_torture_pipe_update(old_rp); @@ -1529,7 +1561,8 @@ rcu_torture_writer(void *arg) case RTWS_COND_GET_FULL: rcu_torture_writer_state = RTWS_COND_GET_FULL; cur_ops->get_gp_state_full(&gp_snap_full); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_cond_wi, + 1000, &rand); rcu_torture_writer_state = RTWS_COND_SYNC_FULL; cur_ops->cond_sync_full(&gp_snap_full); rcu_torture_pipe_update(old_rp); @@ -1537,7 +1570,8 @@ rcu_torture_writer(void *arg) case RTWS_COND_GET_EXP_FULL: rcu_torture_writer_state = RTWS_COND_GET_EXP_FULL; cur_ops->get_gp_state_full(&gp_snap_full); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_cond_wi_exp, + 1000, &rand); rcu_torture_writer_state = RTWS_COND_SYNC_EXP_FULL; cur_ops->cond_sync_exp_full(&gp_snap_full); rcu_torture_pipe_update(old_rp); @@ -1557,8 +1591,8 @@ rcu_torture_writer(void *arg) break; } WARN_ON_ONCE(ulo_size > 0 && i >= ulo_size); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, - &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_poll_wi, + 1000, &rand); } rcu_torture_pipe_update(old_rp); break; @@ -1578,8 +1612,8 @@ rcu_torture_writer(void *arg) break; } WARN_ON_ONCE(rgo_size > 0 && i >= rgo_size); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, - &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_poll_wi, + 1000, &rand); } rcu_torture_pipe_update(old_rp); break; @@ -1588,8 +1622,8 @@ rcu_torture_writer(void *arg) gp_snap = cur_ops->start_gp_poll_exp(); rcu_torture_writer_state = RTWS_POLL_WAIT_EXP; while (!cur_ops->poll_gp_state_exp(gp_snap)) - torture_hrtimeout_jiffies(torture_random(&rand) % 16, - &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_poll_wi_exp, + 1000, &rand); rcu_torture_pipe_update(old_rp); break; case RTWS_POLL_GET_EXP_FULL: @@ -1597,8 +1631,8 @@ rcu_torture_writer(void *arg) cur_ops->start_gp_poll_exp_full(&gp_snap_full); rcu_torture_writer_state = RTWS_POLL_WAIT_EXP_FULL; while (!cur_ops->poll_gp_state_full(&gp_snap_full)) - torture_hrtimeout_jiffies(torture_random(&rand) % 16, - &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_poll_wi_exp, + 1000, &rand); rcu_torture_pipe_update(old_rp); break; case RTWS_SYNC: @@ -1835,6 +1869,44 @@ static void rcu_torture_reader_do_mbchk(long myid, struct rcu_torture *rtp, smp_store_release(&rtrcp_assigner->rtc_chkrdr, -1); // Assigner can again assign. } +// Verify the specified RCUTORTURE_RDR* state. +#define ROEC_ARGS "%s %s: Current %#x To add %#x To remove %#x preempt_count() %#x\n", __func__, s, curstate, new, old, preempt_count() +static void rcutorture_one_extend_check(char *s, int curstate, int new, int old, bool insoftirq) +{ + if (!IS_ENABLED(CONFIG_RCU_TORTURE_TEST_CHK_RDR_STATE)) + return; + + WARN_ONCE(!(curstate & RCUTORTURE_RDR_IRQ) && irqs_disabled(), ROEC_ARGS); + WARN_ONCE((curstate & RCUTORTURE_RDR_IRQ) && !irqs_disabled(), ROEC_ARGS); + + // If CONFIG_PREEMPT_COUNT=n, further checks are unreliable. + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return; + + WARN_ONCE((curstate & (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH)) && + !(preempt_count() & SOFTIRQ_MASK), ROEC_ARGS); + WARN_ONCE((curstate & (RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED)) && + !(preempt_count() & PREEMPT_MASK), ROEC_ARGS); + WARN_ONCE(cur_ops->readlock_nesting && + (curstate & (RCUTORTURE_RDR_RCU_1 | RCUTORTURE_RDR_RCU_2)) && + cur_ops->readlock_nesting() == 0, ROEC_ARGS); + + // Timer handlers have all sorts of stuff disabled, so ignore + // unintended disabling. + if (insoftirq) + return; + + WARN_ONCE(cur_ops->extendables && + !(curstate & (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH)) && + (preempt_count() & SOFTIRQ_MASK), ROEC_ARGS); + WARN_ONCE(cur_ops->extendables && + !(curstate & (RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED)) && + (preempt_count() & PREEMPT_MASK), ROEC_ARGS); + WARN_ONCE(cur_ops->readlock_nesting && + !(curstate & (RCUTORTURE_RDR_RCU_1 | RCUTORTURE_RDR_RCU_2)) && + cur_ops->readlock_nesting() > 0, ROEC_ARGS); +} + /* * Do one extension of an RCU read-side critical section using the * current reader state in readstate (set to zero for initial entry @@ -1844,10 +1916,11 @@ static void rcu_torture_reader_do_mbchk(long myid, struct rcu_torture *rtp, * beginning or end of the critical section and if there was actually a * change, do a ->read_delay(). */ -static void rcutorture_one_extend(int *readstate, int newstate, +static void rcutorture_one_extend(int *readstate, int newstate, bool insoftirq, struct torture_random_state *trsp, struct rt_read_seg *rtrsp) { + bool first; unsigned long flags; int idxnew1 = -1; int idxnew2 = -1; @@ -1856,8 +1929,10 @@ static void rcutorture_one_extend(int *readstate, int newstate, int statesnew = ~*readstate & newstate; int statesold = *readstate & ~newstate; + first = idxold1 == 0; WARN_ON_ONCE(idxold2 < 0); WARN_ON_ONCE(idxold2 & ~RCUTORTURE_RDR_ALLBITS); + rcutorture_one_extend_check("before change", idxold1, statesnew, statesold, insoftirq); rtrsp->rt_readstate = newstate; /* First, put new protection in place to avoid critical-section gap. */ @@ -1876,6 +1951,21 @@ static void rcutorture_one_extend(int *readstate, int newstate, if (statesnew & RCUTORTURE_RDR_RCU_2) idxnew2 = (cur_ops->readlock() << RCUTORTURE_RDR_SHIFT_2) & RCUTORTURE_RDR_MASK_2; + // Complain unless both the old and the new protection is in place. + rcutorture_one_extend_check("during change", + idxold1 | statesnew, statesnew, statesold, insoftirq); + + // Sample CPU under both sets of protections to reduce confusion. + if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_LOG_CPU)) { + int cpu = raw_smp_processor_id(); + rtrsp->rt_cpu = cpu; + if (!first) { + rtrsp[-1].rt_end_cpu = cpu; + if (cur_ops->reader_blocked) + rtrsp[-1].rt_preempted = cur_ops->reader_blocked(); + } + } + /* * Next, remove old protection, in decreasing order of strength * to avoid unlock paths that aren't safe in the stronger @@ -1926,6 +2016,7 @@ static void rcutorture_one_extend(int *readstate, int newstate, WARN_ON_ONCE(*readstate < 0); if (WARN_ON_ONCE(*readstate & ~RCUTORTURE_RDR_ALLBITS)) pr_info("Unexpected readstate value of %#x\n", *readstate); + rcutorture_one_extend_check("after change", *readstate, statesnew, statesold, insoftirq); } /* Return the biggest extendables mask given current RCU and boot parameters. */ @@ -1992,7 +2083,7 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) * critical section. */ static struct rt_read_seg * -rcutorture_loop_extend(int *readstate, struct torture_random_state *trsp, +rcutorture_loop_extend(int *readstate, bool insoftirq, struct torture_random_state *trsp, struct rt_read_seg *rtrsp) { int i; @@ -2007,7 +2098,7 @@ rcutorture_loop_extend(int *readstate, struct torture_random_state *trsp, i = ((i | (i >> 3)) & RCUTORTURE_RDR_MAX_LOOPS) + 1; for (j = 0; j < i; j++) { mask = rcutorture_extend_mask(*readstate, trsp); - rcutorture_one_extend(readstate, mask, trsp, &rtrsp[j]); + rcutorture_one_extend(readstate, mask, insoftirq, trsp, &rtrsp[j]); } return &rtrsp[j]; } @@ -2028,6 +2119,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) int newstate; struct rcu_torture *p; int pipe_count; + bool preempted = false; int readstate = 0; struct rt_read_seg rtseg[RCUTORTURE_RDR_MAX_SEGS] = { { 0 } }; struct rt_read_seg *rtrsp = &rtseg[0]; @@ -2036,7 +2128,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) WARN_ON_ONCE(!rcu_is_watching()); newstate = rcutorture_extend_mask(readstate, trsp); - rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++); + rcutorture_one_extend(&readstate, newstate, myid < 0, trsp, rtrsp++); if (checkpolling) { if (cur_ops->get_gp_state && cur_ops->poll_gp_state) cookie = cur_ops->get_gp_state(); @@ -2049,13 +2141,13 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) !cur_ops->readlock_held || cur_ops->readlock_held()); if (p == NULL) { /* Wait for rcu_torture_writer to get underway */ - rcutorture_one_extend(&readstate, 0, trsp, rtrsp); + rcutorture_one_extend(&readstate, 0, myid < 0, trsp, rtrsp); return false; } if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); rcu_torture_reader_do_mbchk(myid, p, trsp); - rtrsp = rcutorture_loop_extend(&readstate, trsp, rtrsp); + rtrsp = rcutorture_loop_extend(&readstate, myid < 0, trsp, rtrsp); preempt_disable(); pipe_count = READ_ONCE(p->rtort_pipe_count); if (pipe_count > RCU_TORTURE_PIPE_LEN) { @@ -2093,7 +2185,9 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) rcu_torture_writer_state, cpumask_pr_args(cpu_online_mask)); } - rcutorture_one_extend(&readstate, 0, trsp, rtrsp); + if (cur_ops->reader_blocked) + preempted = cur_ops->reader_blocked(); + rcutorture_one_extend(&readstate, 0, myid < 0, trsp, rtrsp); WARN_ON_ONCE(readstate); // This next splat is expected behavior if leakpointer, especially // for CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels. @@ -2105,6 +2199,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) for (rtrsp1 = &rtseg[0]; rtrsp1 < rtrsp; rtrsp1++) err_segs[i++] = *rtrsp1; rt_read_nsegs = i; + rt_read_preempted = preempted; } return true; @@ -2425,7 +2520,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) "read_exit_delay=%d read_exit_burst=%d " "reader_flavor=%x " "nocbs_nthreads=%d nocbs_toggle=%d " - "test_nmis=%d\n", + "test_nmis=%d " + "preempt_duration=%d preempt_interval=%d\n", torture_type, tag, nrealreaders, nfakewriters, stat_interval, verbose, test_no_idle_hz, shuffle_interval, stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, @@ -2438,7 +2534,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) read_exit_delay, read_exit_burst, reader_flavor, nocbs_nthreads, nocbs_toggle, - test_nmis); + test_nmis, + preempt_duration, preempt_interval); } static int rcutorture_booster_cleanup(unsigned int cpu) @@ -3068,12 +3165,12 @@ static int __init rcu_torture_fwd_prog_init(void) fwd_progress = 0; return 0; } - if (stall_cpu > 0) { - VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, conflicts with CPU-stall testing"); + if (stall_cpu > 0 || (preempt_duration > 0 && IS_ENABLED(CONFIG_RCU_NOCB_CPU))) { + VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, conflicts with CPU-stall and/or preemption testing"); fwd_progress = 0; if (IS_MODULE(CONFIG_RCU_TORTURE_TEST)) return -EINVAL; /* In module, can fail back to user. */ - WARN_ON(1); /* Make sure rcutorture notices conflict. */ + WARN_ON(1); /* Make sure rcutorture scripting notices conflict. */ return 0; } if (fwd_progress_holdoff <= 0) @@ -3418,6 +3515,35 @@ static void rcutorture_test_nmis(int n) #endif // #else // #if IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) } +// Randomly preempt online CPUs. +static int rcu_torture_preempt(void *unused) +{ + int cpu = -1; + DEFINE_TORTURE_RANDOM(rand); + + schedule_timeout_idle(stall_cpu_holdoff); + do { + // Wait for preempt_interval ms with up to 100us fuzz. + torture_hrtimeout_ms(preempt_interval, 100, &rand); + // Select online CPU. + cpu = cpumask_next(cpu, cpu_online_mask); + if (cpu >= nr_cpu_ids) + cpu = cpumask_next(-1, cpu_online_mask); + WARN_ON_ONCE(cpu >= nr_cpu_ids); + // Move to that CPU, if can't do so, retry later. + if (torture_sched_setaffinity(current->pid, cpumask_of(cpu), false)) + continue; + // Preempt at high-ish priority, then reset to normal. + sched_set_fifo(current); + torture_sched_setaffinity(current->pid, cpu_present_mask, true); + mdelay(preempt_duration); + sched_set_normal(current, 0); + stutter_wait("rcu_torture_preempt"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_preempt"); + return 0; +} + static enum cpuhp_state rcutor_hp; static void @@ -3446,6 +3572,7 @@ rcu_torture_cleanup(void) if (cur_ops->gp_kthread_dbg) cur_ops->gp_kthread_dbg(); + torture_stop_kthread(rcu_torture_preempt, preempt_task); rcu_torture_read_exit_cleanup(); rcu_torture_barrier_cleanup(); rcu_torture_fwd_prog_cleanup(); @@ -3508,26 +3635,49 @@ rcu_torture_cleanup(void) pr_alert("\t: No segments recorded!!!\n"); firsttime = 1; for (i = 0; i < rt_read_nsegs; i++) { - pr_alert("\t%d: %#x ", i, err_segs[i].rt_readstate); + pr_alert("\t%d: %#4x", i, err_segs[i].rt_readstate); if (err_segs[i].rt_delay_jiffies != 0) { pr_cont("%s%ldjiffies", firsttime ? "" : "+", err_segs[i].rt_delay_jiffies); firsttime = 0; } + if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_LOG_CPU)) { + pr_cont(" CPU %2d", err_segs[i].rt_cpu); + if (err_segs[i].rt_cpu != err_segs[i].rt_end_cpu) + pr_cont("->%-2d", err_segs[i].rt_end_cpu); + else + pr_cont(" ..."); + } if (err_segs[i].rt_delay_ms != 0) { - pr_cont("%s%ldms", firsttime ? "" : "+", + pr_cont(" %s%ldms", firsttime ? "" : "+", err_segs[i].rt_delay_ms); firsttime = 0; } if (err_segs[i].rt_delay_us != 0) { - pr_cont("%s%ldus", firsttime ? "" : "+", + pr_cont(" %s%ldus", firsttime ? "" : "+", err_segs[i].rt_delay_us); firsttime = 0; } - pr_cont("%s\n", - err_segs[i].rt_preempted ? "preempted" : ""); + pr_cont("%s", err_segs[i].rt_preempted ? " preempted" : ""); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_BH) + pr_cont(" BH"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_IRQ) + pr_cont(" IRQ"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_PREEMPT) + pr_cont(" PREEMPT"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_RBH) + pr_cont(" RBH"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_SCHED) + pr_cont(" SCHED"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_RCU_1) + pr_cont(" RCU_1"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_RCU_2) + pr_cont(" RCU_2"); + pr_cont("\n"); } + if (rt_read_preempted) + pr_alert("\tReader was preempted.\n"); } if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error) rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE"); @@ -4019,6 +4169,11 @@ rcu_torture_init(void) firsterr = rcu_torture_read_exit_init(); if (torture_init_error(firsterr)) goto unwind; + if (preempt_duration > 0) { + firsterr = torture_create_kthread(rcu_torture_preempt, NULL, preempt_task); + if (torture_init_error(firsterr)) + goto unwind; + } if (object_debug) rcu_test_debug_objects(); torture_init_end(); diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c index aacfcc9838b3..1b47376acdc4 100644 --- a/kernel/rcu/refscale.c +++ b/kernel/rcu/refscale.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "rcu.h" @@ -531,6 +532,39 @@ static const struct ref_scale_ops acqrel_ops = { static volatile u64 stopopts; +static void ref_sched_clock_section(const int nloops) +{ + u64 x = 0; + int i; + + preempt_disable(); + for (i = nloops; i >= 0; i--) + x += sched_clock(); + preempt_enable(); + stopopts = x; +} + +static void ref_sched_clock_delay_section(const int nloops, const int udl, const int ndl) +{ + u64 x = 0; + int i; + + preempt_disable(); + for (i = nloops; i >= 0; i--) { + x += sched_clock(); + un_delay(udl, ndl); + } + preempt_enable(); + stopopts = x; +} + +static const struct ref_scale_ops sched_clock_ops = { + .readsection = ref_sched_clock_section, + .delaysection = ref_sched_clock_delay_section, + .name = "sched-clock" +}; + + static void ref_clock_section(const int nloops) { u64 x = 0; @@ -1130,9 +1164,9 @@ ref_scale_init(void) int firsterr = 0; static const struct ref_scale_ops *scale_ops[] = { &rcu_ops, &srcu_ops, &srcu_lite_ops, RCU_TRACE_OPS RCU_TASKS_OPS - &refcnt_ops, &rwlock_ops, &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, - &clock_ops, &jiffies_ops, &typesafe_ref_ops, &typesafe_lock_ops, - &typesafe_seqlock_ops, + &refcnt_ops, &rwlock_ops, &rwsem_ops, &lock_ops, &lock_irq_ops, + &acqrel_ops, &sched_clock_ops, &clock_ops, &jiffies_ops, + &typesafe_ref_ops, &typesafe_lock_ops, &typesafe_seqlock_ops, }; if (!torture_init_begin(scale_type, verbose)) diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 5e2e53464794..b83c74c4dcc0 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -738,7 +738,8 @@ EXPORT_SYMBOL_GPL(__srcu_check_read_flavor); /* * Counts the new reader in the appropriate per-CPU element of the * srcu_struct. - * Returns an index that must be passed to the matching srcu_read_unlock(). + * Returns a guaranteed non-negative index that must be passed to the + * matching __srcu_read_unlock(). */ int __srcu_read_lock(struct srcu_struct *ssp) { @@ -1076,7 +1077,6 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, /* If grace period not already in progress, start it. */ if (!WARN_ON_ONCE(rcu_seq_done(&sup->srcu_gp_seq, s)) && rcu_seq_state(sup->srcu_gp_seq) == SRCU_STATE_IDLE) { - WARN_ON_ONCE(ULONG_CMP_GE(sup->srcu_gp_seq, sup->srcu_gp_seq_needed)); srcu_gp_start(ssp); // And how can that list_add() in the "else" clause diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index b3b3ce34df63..4b3f31911465 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -250,7 +250,7 @@ EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu); void kvfree_call_rcu(struct rcu_head *head, void *ptr) { if (head) - kasan_record_aux_stack_noalloc(ptr); + kasan_record_aux_stack(ptr); __kvfree_call_rcu(head, ptr); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index ff98233d4aa5..475f31deed14 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -149,7 +149,6 @@ static int rcu_scheduler_fully_active __read_mostly; static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, unsigned long gps, unsigned long flags); -static struct task_struct *rcu_boost_task(struct rcu_node *rnp); static void invoke_rcu_core(void); static void rcu_report_exp_rdp(struct rcu_data *rdp); static void sync_sched_exp_online_cleanup(int cpu); @@ -186,26 +185,6 @@ static int rcu_unlock_delay; module_param(rcu_unlock_delay, int, 0444); #endif -/* - * This rcu parameter is runtime-read-only. It reflects - * a minimum allowed number of objects which can be cached - * per-CPU. Object size is equal to one page. This value - * can be changed at boot time. - */ -static int rcu_min_cached_objs = 5; -module_param(rcu_min_cached_objs, int, 0444); - -// A page shrinker can ask for pages to be freed to make them -// available for other parts of the system. This usually happens -// under low memory conditions, and in that case we should also -// defer page-cache filling for a short time period. -// -// The default value is 5 seconds, which is long enough to reduce -// interference with the shrinker while it asks other systems to -// drain their caches. -static int rcu_delay_page_cache_fill_msec = 5000; -module_param(rcu_delay_page_cache_fill_msec, int, 0444); - /* Retrieve RCU kthreads priority for rcutorture */ int rcu_get_gp_kthreads_prio(void) { @@ -3083,9 +3062,12 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in) } head->func = func; head->next = NULL; - kasan_record_aux_stack_noalloc(head); + kasan_record_aux_stack(head); + local_irq_save(flags); rdp = this_cpu_ptr(&rcu_data); + RCU_LOCKDEP_WARN(!rcu_rdp_cpu_online(rdp), "Callback enqueued on offline CPU!"); + lazy = lazy_in && !rcu_async_should_hurry(); /* Add the callback to our list. */ @@ -3191,812 +3173,6 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func) } EXPORT_SYMBOL_GPL(call_rcu); -/* Maximum number of jiffies to wait before draining a batch. */ -#define KFREE_DRAIN_JIFFIES (5 * HZ) -#define KFREE_N_BATCHES 2 -#define FREE_N_CHANNELS 2 - -/** - * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers - * @list: List node. All blocks are linked between each other - * @gp_snap: Snapshot of RCU state for objects placed to this bulk - * @nr_records: Number of active pointers in the array - * @records: Array of the kvfree_rcu() pointers - */ -struct kvfree_rcu_bulk_data { - struct list_head list; - struct rcu_gp_oldstate gp_snap; - unsigned long nr_records; - void *records[] __counted_by(nr_records); -}; - -/* - * This macro defines how many entries the "records" array - * will contain. It is based on the fact that the size of - * kvfree_rcu_bulk_data structure becomes exactly one page. - */ -#define KVFREE_BULK_MAX_ENTR \ - ((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *)) - -/** - * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests - * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period - * @head_free: List of kfree_rcu() objects waiting for a grace period - * @head_free_gp_snap: Grace-period snapshot to check for attempted premature frees. - * @bulk_head_free: Bulk-List of kvfree_rcu() objects waiting for a grace period - * @krcp: Pointer to @kfree_rcu_cpu structure - */ - -struct kfree_rcu_cpu_work { - struct rcu_work rcu_work; - struct rcu_head *head_free; - struct rcu_gp_oldstate head_free_gp_snap; - struct list_head bulk_head_free[FREE_N_CHANNELS]; - struct kfree_rcu_cpu *krcp; -}; - -/** - * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period - * @head: List of kfree_rcu() objects not yet waiting for a grace period - * @head_gp_snap: Snapshot of RCU state for objects placed to "@head" - * @bulk_head: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period - * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period - * @lock: Synchronize access to this structure - * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES - * @initialized: The @rcu_work fields have been initialized - * @head_count: Number of objects in rcu_head singular list - * @bulk_count: Number of objects in bulk-list - * @bkvcache: - * A simple cache list that contains objects for reuse purpose. - * In order to save some per-cpu space the list is singular. - * Even though it is lockless an access has to be protected by the - * per-cpu lock. - * @page_cache_work: A work to refill the cache when it is empty - * @backoff_page_cache_fill: Delay cache refills - * @work_in_progress: Indicates that page_cache_work is running - * @hrtimer: A hrtimer for scheduling a page_cache_work - * @nr_bkv_objs: number of allocated objects at @bkvcache. - * - * This is a per-CPU structure. The reason that it is not included in - * the rcu_data structure is to permit this code to be extracted from - * the RCU files. Such extraction could allow further optimization of - * the interactions with the slab allocators. - */ -struct kfree_rcu_cpu { - // Objects queued on a linked list - // through their rcu_head structures. - struct rcu_head *head; - unsigned long head_gp_snap; - atomic_t head_count; - - // Objects queued on a bulk-list. - struct list_head bulk_head[FREE_N_CHANNELS]; - atomic_t bulk_count[FREE_N_CHANNELS]; - - struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; - raw_spinlock_t lock; - struct delayed_work monitor_work; - bool initialized; - - struct delayed_work page_cache_work; - atomic_t backoff_page_cache_fill; - atomic_t work_in_progress; - struct hrtimer hrtimer; - - struct llist_head bkvcache; - int nr_bkv_objs; -}; - -static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = { - .lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock), -}; - -static __always_inline void -debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead) -{ -#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD - int i; - - for (i = 0; i < bhead->nr_records; i++) - debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i])); -#endif -} - -static inline struct kfree_rcu_cpu * -krc_this_cpu_lock(unsigned long *flags) -{ - struct kfree_rcu_cpu *krcp; - - local_irq_save(*flags); // For safely calling this_cpu_ptr(). - krcp = this_cpu_ptr(&krc); - raw_spin_lock(&krcp->lock); - - return krcp; -} - -static inline void -krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags) -{ - raw_spin_unlock_irqrestore(&krcp->lock, flags); -} - -static inline struct kvfree_rcu_bulk_data * -get_cached_bnode(struct kfree_rcu_cpu *krcp) -{ - if (!krcp->nr_bkv_objs) - return NULL; - - WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs - 1); - return (struct kvfree_rcu_bulk_data *) - llist_del_first(&krcp->bkvcache); -} - -static inline bool -put_cached_bnode(struct kfree_rcu_cpu *krcp, - struct kvfree_rcu_bulk_data *bnode) -{ - // Check the limit. - if (krcp->nr_bkv_objs >= rcu_min_cached_objs) - return false; - - llist_add((struct llist_node *) bnode, &krcp->bkvcache); - WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs + 1); - return true; -} - -static int -drain_page_cache(struct kfree_rcu_cpu *krcp) -{ - unsigned long flags; - struct llist_node *page_list, *pos, *n; - int freed = 0; - - if (!rcu_min_cached_objs) - return 0; - - raw_spin_lock_irqsave(&krcp->lock, flags); - page_list = llist_del_all(&krcp->bkvcache); - WRITE_ONCE(krcp->nr_bkv_objs, 0); - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - llist_for_each_safe(pos, n, page_list) { - free_page((unsigned long)pos); - freed++; - } - - return freed; -} - -static void -kvfree_rcu_bulk(struct kfree_rcu_cpu *krcp, - struct kvfree_rcu_bulk_data *bnode, int idx) -{ - unsigned long flags; - int i; - - if (!WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&bnode->gp_snap))) { - debug_rcu_bhead_unqueue(bnode); - rcu_lock_acquire(&rcu_callback_map); - if (idx == 0) { // kmalloc() / kfree(). - trace_rcu_invoke_kfree_bulk_callback( - rcu_state.name, bnode->nr_records, - bnode->records); - - kfree_bulk(bnode->nr_records, bnode->records); - } else { // vmalloc() / vfree(). - for (i = 0; i < bnode->nr_records; i++) { - trace_rcu_invoke_kvfree_callback( - rcu_state.name, bnode->records[i], 0); - - vfree(bnode->records[i]); - } - } - rcu_lock_release(&rcu_callback_map); - } - - raw_spin_lock_irqsave(&krcp->lock, flags); - if (put_cached_bnode(krcp, bnode)) - bnode = NULL; - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - if (bnode) - free_page((unsigned long) bnode); - - cond_resched_tasks_rcu_qs(); -} - -static void -kvfree_rcu_list(struct rcu_head *head) -{ - struct rcu_head *next; - - for (; head; head = next) { - void *ptr = (void *) head->func; - unsigned long offset = (void *) head - ptr; - - next = head->next; - debug_rcu_head_unqueue((struct rcu_head *)ptr); - rcu_lock_acquire(&rcu_callback_map); - trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset); - - if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset))) - kvfree(ptr); - - rcu_lock_release(&rcu_callback_map); - cond_resched_tasks_rcu_qs(); - } -} - -/* - * This function is invoked in workqueue context after a grace period. - * It frees all the objects queued on ->bulk_head_free or ->head_free. - */ -static void kfree_rcu_work(struct work_struct *work) -{ - unsigned long flags; - struct kvfree_rcu_bulk_data *bnode, *n; - struct list_head bulk_head[FREE_N_CHANNELS]; - struct rcu_head *head; - struct kfree_rcu_cpu *krcp; - struct kfree_rcu_cpu_work *krwp; - struct rcu_gp_oldstate head_gp_snap; - int i; - - krwp = container_of(to_rcu_work(work), - struct kfree_rcu_cpu_work, rcu_work); - krcp = krwp->krcp; - - raw_spin_lock_irqsave(&krcp->lock, flags); - // Channels 1 and 2. - for (i = 0; i < FREE_N_CHANNELS; i++) - list_replace_init(&krwp->bulk_head_free[i], &bulk_head[i]); - - // Channel 3. - head = krwp->head_free; - krwp->head_free = NULL; - head_gp_snap = krwp->head_free_gp_snap; - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - // Handle the first two channels. - for (i = 0; i < FREE_N_CHANNELS; i++) { - // Start from the tail page, so a GP is likely passed for it. - list_for_each_entry_safe(bnode, n, &bulk_head[i], list) - kvfree_rcu_bulk(krcp, bnode, i); - } - - /* - * This is used when the "bulk" path can not be used for the - * double-argument of kvfree_rcu(). This happens when the - * page-cache is empty, which means that objects are instead - * queued on a linked list through their rcu_head structures. - * This list is named "Channel 3". - */ - if (head && !WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&head_gp_snap))) - kvfree_rcu_list(head); -} - -static bool -need_offload_krc(struct kfree_rcu_cpu *krcp) -{ - int i; - - for (i = 0; i < FREE_N_CHANNELS; i++) - if (!list_empty(&krcp->bulk_head[i])) - return true; - - return !!READ_ONCE(krcp->head); -} - -static bool -need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp) -{ - int i; - - for (i = 0; i < FREE_N_CHANNELS; i++) - if (!list_empty(&krwp->bulk_head_free[i])) - return true; - - return !!krwp->head_free; -} - -static int krc_count(struct kfree_rcu_cpu *krcp) -{ - int sum = atomic_read(&krcp->head_count); - int i; - - for (i = 0; i < FREE_N_CHANNELS; i++) - sum += atomic_read(&krcp->bulk_count[i]); - - return sum; -} - -static void -__schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) -{ - long delay, delay_left; - - delay = krc_count(krcp) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES; - if (delayed_work_pending(&krcp->monitor_work)) { - delay_left = krcp->monitor_work.timer.expires - jiffies; - if (delay < delay_left) - mod_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); - return; - } - queue_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); -} - -static void -schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&krcp->lock, flags); - __schedule_delayed_monitor_work(krcp); - raw_spin_unlock_irqrestore(&krcp->lock, flags); -} - -static void -kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp) -{ - struct list_head bulk_ready[FREE_N_CHANNELS]; - struct kvfree_rcu_bulk_data *bnode, *n; - struct rcu_head *head_ready = NULL; - unsigned long flags; - int i; - - raw_spin_lock_irqsave(&krcp->lock, flags); - for (i = 0; i < FREE_N_CHANNELS; i++) { - INIT_LIST_HEAD(&bulk_ready[i]); - - list_for_each_entry_safe_reverse(bnode, n, &krcp->bulk_head[i], list) { - if (!poll_state_synchronize_rcu_full(&bnode->gp_snap)) - break; - - atomic_sub(bnode->nr_records, &krcp->bulk_count[i]); - list_move(&bnode->list, &bulk_ready[i]); - } - } - - if (krcp->head && poll_state_synchronize_rcu(krcp->head_gp_snap)) { - head_ready = krcp->head; - atomic_set(&krcp->head_count, 0); - WRITE_ONCE(krcp->head, NULL); - } - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - for (i = 0; i < FREE_N_CHANNELS; i++) { - list_for_each_entry_safe(bnode, n, &bulk_ready[i], list) - kvfree_rcu_bulk(krcp, bnode, i); - } - - if (head_ready) - kvfree_rcu_list(head_ready); -} - -/* - * Return: %true if a work is queued, %false otherwise. - */ -static bool -kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp) -{ - unsigned long flags; - bool queued = false; - int i, j; - - raw_spin_lock_irqsave(&krcp->lock, flags); - - // Attempt to start a new batch. - for (i = 0; i < KFREE_N_BATCHES; i++) { - struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]); - - // Try to detach bulk_head or head and attach it, only when - // all channels are free. Any channel is not free means at krwp - // there is on-going rcu work to handle krwp's free business. - if (need_wait_for_krwp_work(krwp)) - continue; - - // kvfree_rcu_drain_ready() might handle this krcp, if so give up. - if (need_offload_krc(krcp)) { - // Channel 1 corresponds to the SLAB-pointer bulk path. - // Channel 2 corresponds to vmalloc-pointer bulk path. - for (j = 0; j < FREE_N_CHANNELS; j++) { - if (list_empty(&krwp->bulk_head_free[j])) { - atomic_set(&krcp->bulk_count[j], 0); - list_replace_init(&krcp->bulk_head[j], - &krwp->bulk_head_free[j]); - } - } - - // Channel 3 corresponds to both SLAB and vmalloc - // objects queued on the linked list. - if (!krwp->head_free) { - krwp->head_free = krcp->head; - get_state_synchronize_rcu_full(&krwp->head_free_gp_snap); - atomic_set(&krcp->head_count, 0); - WRITE_ONCE(krcp->head, NULL); - } - - // One work is per one batch, so there are three - // "free channels", the batch can handle. Break - // the loop since it is done with this CPU thus - // queuing an RCU work is _always_ success here. - queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work); - WARN_ON_ONCE(!queued); - break; - } - } - - raw_spin_unlock_irqrestore(&krcp->lock, flags); - return queued; -} - -/* - * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. - */ -static void kfree_rcu_monitor(struct work_struct *work) -{ - struct kfree_rcu_cpu *krcp = container_of(work, - struct kfree_rcu_cpu, monitor_work.work); - - // Drain ready for reclaim. - kvfree_rcu_drain_ready(krcp); - - // Queue a batch for a rest. - kvfree_rcu_queue_batch(krcp); - - // If there is nothing to detach, it means that our job is - // successfully done here. In case of having at least one - // of the channels that is still busy we should rearm the - // work to repeat an attempt. Because previous batches are - // still in progress. - if (need_offload_krc(krcp)) - schedule_delayed_monitor_work(krcp); -} - -static enum hrtimer_restart -schedule_page_work_fn(struct hrtimer *t) -{ - struct kfree_rcu_cpu *krcp = - container_of(t, struct kfree_rcu_cpu, hrtimer); - - queue_delayed_work(system_highpri_wq, &krcp->page_cache_work, 0); - return HRTIMER_NORESTART; -} - -static void fill_page_cache_func(struct work_struct *work) -{ - struct kvfree_rcu_bulk_data *bnode; - struct kfree_rcu_cpu *krcp = - container_of(work, struct kfree_rcu_cpu, - page_cache_work.work); - unsigned long flags; - int nr_pages; - bool pushed; - int i; - - nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ? - 1 : rcu_min_cached_objs; - - for (i = READ_ONCE(krcp->nr_bkv_objs); i < nr_pages; i++) { - bnode = (struct kvfree_rcu_bulk_data *) - __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); - - if (!bnode) - break; - - raw_spin_lock_irqsave(&krcp->lock, flags); - pushed = put_cached_bnode(krcp, bnode); - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - if (!pushed) { - free_page((unsigned long) bnode); - break; - } - } - - atomic_set(&krcp->work_in_progress, 0); - atomic_set(&krcp->backoff_page_cache_fill, 0); -} - -static void -run_page_cache_worker(struct kfree_rcu_cpu *krcp) -{ - // If cache disabled, bail out. - if (!rcu_min_cached_objs) - return; - - if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING && - !atomic_xchg(&krcp->work_in_progress, 1)) { - if (atomic_read(&krcp->backoff_page_cache_fill)) { - queue_delayed_work(system_unbound_wq, - &krcp->page_cache_work, - msecs_to_jiffies(rcu_delay_page_cache_fill_msec)); - } else { - hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - krcp->hrtimer.function = schedule_page_work_fn; - hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL); - } - } -} - -// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock() -// state specified by flags. If can_alloc is true, the caller must -// be schedulable and not be holding any locks or mutexes that might be -// acquired by the memory allocator or anything that it might invoke. -// Returns true if ptr was successfully recorded, else the caller must -// use a fallback. -static inline bool -add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp, - unsigned long *flags, void *ptr, bool can_alloc) -{ - struct kvfree_rcu_bulk_data *bnode; - int idx; - - *krcp = krc_this_cpu_lock(flags); - if (unlikely(!(*krcp)->initialized)) - return false; - - idx = !!is_vmalloc_addr(ptr); - bnode = list_first_entry_or_null(&(*krcp)->bulk_head[idx], - struct kvfree_rcu_bulk_data, list); - - /* Check if a new block is required. */ - if (!bnode || bnode->nr_records == KVFREE_BULK_MAX_ENTR) { - bnode = get_cached_bnode(*krcp); - if (!bnode && can_alloc) { - krc_this_cpu_unlock(*krcp, *flags); - - // __GFP_NORETRY - allows a light-weight direct reclaim - // what is OK from minimizing of fallback hitting point of - // view. Apart of that it forbids any OOM invoking what is - // also beneficial since we are about to release memory soon. - // - // __GFP_NOMEMALLOC - prevents from consuming of all the - // memory reserves. Please note we have a fallback path. - // - // __GFP_NOWARN - it is supposed that an allocation can - // be failed under low memory or high memory pressure - // scenarios. - bnode = (struct kvfree_rcu_bulk_data *) - __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); - raw_spin_lock_irqsave(&(*krcp)->lock, *flags); - } - - if (!bnode) - return false; - - // Initialize the new block and attach it. - bnode->nr_records = 0; - list_add(&bnode->list, &(*krcp)->bulk_head[idx]); - } - - // Finally insert and update the GP for this page. - bnode->nr_records++; - bnode->records[bnode->nr_records - 1] = ptr; - get_state_synchronize_rcu_full(&bnode->gp_snap); - atomic_inc(&(*krcp)->bulk_count[idx]); - - return true; -} - -/* - * Queue a request for lazy invocation of the appropriate free routine - * after a grace period. Please note that three paths are maintained, - * two for the common case using arrays of pointers and a third one that - * is used only when the main paths cannot be used, for example, due to - * memory pressure. - * - * Each kvfree_call_rcu() request is added to a batch. The batch will be drained - * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will - * be free'd in workqueue context. This allows us to: batch requests together to - * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load. - */ -void kvfree_call_rcu(struct rcu_head *head, void *ptr) -{ - unsigned long flags; - struct kfree_rcu_cpu *krcp; - bool success; - - /* - * Please note there is a limitation for the head-less - * variant, that is why there is a clear rule for such - * objects: it can be used from might_sleep() context - * only. For other places please embed an rcu_head to - * your data. - */ - if (!head) - might_sleep(); - - // Queue the object but don't yet schedule the batch. - if (debug_rcu_head_queue(ptr)) { - // Probable double kfree_rcu(), just leak. - WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n", - __func__, head); - - // Mark as success and leave. - return; - } - - kasan_record_aux_stack_noalloc(ptr); - success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head); - if (!success) { - run_page_cache_worker(krcp); - - if (head == NULL) - // Inline if kvfree_rcu(one_arg) call. - goto unlock_return; - - head->func = ptr; - head->next = krcp->head; - WRITE_ONCE(krcp->head, head); - atomic_inc(&krcp->head_count); - - // Take a snapshot for this krcp. - krcp->head_gp_snap = get_state_synchronize_rcu(); - success = true; - } - - /* - * The kvfree_rcu() caller considers the pointer freed at this point - * and likely removes any references to it. Since the actual slab - * freeing (and kmemleak_free()) is deferred, tell kmemleak to ignore - * this object (no scanning or false positives reporting). - */ - kmemleak_ignore(ptr); - - // Set timer to drain after KFREE_DRAIN_JIFFIES. - if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING) - __schedule_delayed_monitor_work(krcp); - -unlock_return: - krc_this_cpu_unlock(krcp, flags); - - /* - * Inline kvfree() after synchronize_rcu(). We can do - * it from might_sleep() context only, so the current - * CPU can pass the QS state. - */ - if (!success) { - debug_rcu_head_unqueue((struct rcu_head *) ptr); - synchronize_rcu(); - kvfree(ptr); - } -} -EXPORT_SYMBOL_GPL(kvfree_call_rcu); - -/** - * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete. - * - * Note that a single argument of kvfree_rcu() call has a slow path that - * triggers synchronize_rcu() following by freeing a pointer. It is done - * before the return from the function. Therefore for any single-argument - * call that will result in a kfree() to a cache that is to be destroyed - * during module exit, it is developer's responsibility to ensure that all - * such calls have returned before the call to kmem_cache_destroy(). - */ -void kvfree_rcu_barrier(void) -{ - struct kfree_rcu_cpu_work *krwp; - struct kfree_rcu_cpu *krcp; - bool queued; - int i, cpu; - - /* - * Firstly we detach objects and queue them over an RCU-batch - * for all CPUs. Finally queued works are flushed for each CPU. - * - * Please note. If there are outstanding batches for a particular - * CPU, those have to be finished first following by queuing a new. - */ - for_each_possible_cpu(cpu) { - krcp = per_cpu_ptr(&krc, cpu); - - /* - * Check if this CPU has any objects which have been queued for a - * new GP completion. If not(means nothing to detach), we are done - * with it. If any batch is pending/running for this "krcp", below - * per-cpu flush_rcu_work() waits its completion(see last step). - */ - if (!need_offload_krc(krcp)) - continue; - - while (1) { - /* - * If we are not able to queue a new RCU work it means: - * - batches for this CPU are still in flight which should - * be flushed first and then repeat; - * - no objects to detach, because of concurrency. - */ - queued = kvfree_rcu_queue_batch(krcp); - - /* - * Bail out, if there is no need to offload this "krcp" - * anymore. As noted earlier it can run concurrently. - */ - if (queued || !need_offload_krc(krcp)) - break; - - /* There are ongoing batches. */ - for (i = 0; i < KFREE_N_BATCHES; i++) { - krwp = &(krcp->krw_arr[i]); - flush_rcu_work(&krwp->rcu_work); - } - } - } - - /* - * Now we guarantee that all objects are flushed. - */ - for_each_possible_cpu(cpu) { - krcp = per_cpu_ptr(&krc, cpu); - - /* - * A monitor work can drain ready to reclaim objects - * directly. Wait its completion if running or pending. - */ - cancel_delayed_work_sync(&krcp->monitor_work); - - for (i = 0; i < KFREE_N_BATCHES; i++) { - krwp = &(krcp->krw_arr[i]); - flush_rcu_work(&krwp->rcu_work); - } - } -} -EXPORT_SYMBOL_GPL(kvfree_rcu_barrier); - -static unsigned long -kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) -{ - int cpu; - unsigned long count = 0; - - /* Snapshot count of all CPUs */ - for_each_possible_cpu(cpu) { - struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - - count += krc_count(krcp); - count += READ_ONCE(krcp->nr_bkv_objs); - atomic_set(&krcp->backoff_page_cache_fill, 1); - } - - return count == 0 ? SHRINK_EMPTY : count; -} - -static unsigned long -kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) -{ - int cpu, freed = 0; - - for_each_possible_cpu(cpu) { - int count; - struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - - count = krc_count(krcp); - count += drain_page_cache(krcp); - kfree_rcu_monitor(&krcp->monitor_work.work); - - sc->nr_to_scan -= count; - freed += count; - - if (sc->nr_to_scan <= 0) - break; - } - - return freed == 0 ? SHRINK_STOP : freed; -} - -void __init kfree_rcu_scheduler_running(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - - if (need_offload_krc(krcp)) - schedule_delayed_monitor_work(krcp); - } -} - /* * During early boot, any blocking grace-period wait automatically * implies a grace period. @@ -4895,6 +4071,22 @@ rcu_boot_init_percpu_data(int cpu) rcu_boot_init_nocb_percpu_data(rdp); } +static void rcu_thread_affine_rnp(struct task_struct *t, struct rcu_node *rnp) +{ + cpumask_var_t affinity; + int cpu; + + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) + return; + + for_each_leaf_node_possible_cpu(rnp, cpu) + cpumask_set_cpu(cpu, affinity); + + kthread_affine_preferred(t, affinity); + + free_cpumask_var(affinity); +} + struct kthread_worker *rcu_exp_gp_kworker; static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp) @@ -4917,16 +4109,9 @@ static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp) if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD)) sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, ¶m); -} -static struct task_struct *rcu_exp_par_gp_task(struct rcu_node *rnp) -{ - struct kthread_worker *kworker = READ_ONCE(rnp->exp_kworker); - - if (!kworker) - return NULL; - - return kworker->task; + rcu_thread_affine_rnp(kworker->task, rnp); + wake_up_process(kworker->task); } static void __init rcu_start_exp_gp_kworker(void) @@ -4934,7 +4119,7 @@ static void __init rcu_start_exp_gp_kworker(void) const char *name = "rcu_exp_gp_kthread_worker"; struct sched_param param = { .sched_priority = kthread_prio }; - rcu_exp_gp_kworker = kthread_create_worker(0, name); + rcu_exp_gp_kworker = kthread_run_worker(0, name); if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { pr_err("Failed to create %s!\n", name); rcu_exp_gp_kworker = NULL; @@ -5011,67 +4196,6 @@ int rcutree_prepare_cpu(unsigned int cpu) return 0; } -/* - * Update kthreads affinity during CPU-hotplug changes. - * - * Set the per-rcu_node kthread's affinity to cover all CPUs that are - * served by the rcu_node in question. The CPU hotplug lock is still - * held, so the value of rnp->qsmaskinit will be stable. - * - * We don't include outgoingcpu in the affinity set, use -1 if there is - * no outgoing CPU. If there are no CPUs left in the affinity set, - * this function allows the kthread to execute on any CPU. - * - * Any future concurrent calls are serialized via ->kthread_mutex. - */ -static void rcutree_affinity_setting(unsigned int cpu, int outgoingcpu) -{ - cpumask_var_t cm; - unsigned long mask; - struct rcu_data *rdp; - struct rcu_node *rnp; - struct task_struct *task_boost, *task_exp; - - rdp = per_cpu_ptr(&rcu_data, cpu); - rnp = rdp->mynode; - - task_boost = rcu_boost_task(rnp); - task_exp = rcu_exp_par_gp_task(rnp); - - /* - * If CPU is the boot one, those tasks are created later from early - * initcall since kthreadd must be created first. - */ - if (!task_boost && !task_exp) - return; - - if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) - return; - - mutex_lock(&rnp->kthread_mutex); - mask = rcu_rnp_online_cpus(rnp); - for_each_leaf_node_possible_cpu(rnp, cpu) - if ((mask & leaf_node_cpu_bit(rnp, cpu)) && - cpu != outgoingcpu) - cpumask_set_cpu(cpu, cm); - cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU)); - if (cpumask_empty(cm)) { - cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU)); - if (outgoingcpu >= 0) - cpumask_clear_cpu(outgoingcpu, cm); - } - - if (task_exp) - set_cpus_allowed_ptr(task_exp, cm); - - if (task_boost) - set_cpus_allowed_ptr(task_boost, cm); - - mutex_unlock(&rnp->kthread_mutex); - - free_cpumask_var(cm); -} - /* * Has the specified (known valid) CPU ever been fully online? */ @@ -5100,7 +4224,6 @@ int rcutree_online_cpu(unsigned int cpu) if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) return 0; /* Too early in boot for scheduler work. */ sync_sched_exp_online_cleanup(cpu); - rcutree_affinity_setting(cpu, -1); // Stop-machine done, so allow nohz_full to disable tick. tick_dep_clear(TICK_DEP_BIT_RCU); @@ -5317,8 +4440,6 @@ int rcutree_offline_cpu(unsigned int cpu) rnp->ffmask &= ~rdp->grpmask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - rcutree_affinity_setting(cpu, cpu); - // nohz_full CPUs need the tick for stop-machine to work quickly tick_dep_set(TICK_DEP_BIT_RCU); return 0; @@ -5648,62 +4769,12 @@ static void __init rcu_dump_rcu_node_tree(void) struct workqueue_struct *rcu_gp_wq; -static void __init kfree_rcu_batch_init(void) -{ - int cpu; - int i, j; - struct shrinker *kfree_rcu_shrinker; - - /* Clamp it to [0:100] seconds interval. */ - if (rcu_delay_page_cache_fill_msec < 0 || - rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) { - - rcu_delay_page_cache_fill_msec = - clamp(rcu_delay_page_cache_fill_msec, 0, - (int) (100 * MSEC_PER_SEC)); - - pr_info("Adjusting rcutree.rcu_delay_page_cache_fill_msec to %d ms.\n", - rcu_delay_page_cache_fill_msec); - } - - for_each_possible_cpu(cpu) { - struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - - for (i = 0; i < KFREE_N_BATCHES; i++) { - INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work); - krcp->krw_arr[i].krcp = krcp; - - for (j = 0; j < FREE_N_CHANNELS; j++) - INIT_LIST_HEAD(&krcp->krw_arr[i].bulk_head_free[j]); - } - - for (i = 0; i < FREE_N_CHANNELS; i++) - INIT_LIST_HEAD(&krcp->bulk_head[i]); - - INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor); - INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func); - krcp->initialized = true; - } - - kfree_rcu_shrinker = shrinker_alloc(0, "rcu-kfree"); - if (!kfree_rcu_shrinker) { - pr_err("Failed to allocate kfree_rcu() shrinker!\n"); - return; - } - - kfree_rcu_shrinker->count_objects = kfree_rcu_shrink_count; - kfree_rcu_shrinker->scan_objects = kfree_rcu_shrink_scan; - - shrinker_register(kfree_rcu_shrinker); -} - void __init rcu_init(void) { int cpu = smp_processor_id(); rcu_early_boot_tests(); - kfree_rcu_batch_init(); rcu_bootup_announce(); sanitize_kthread_prio(); rcu_init_geometry(); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index fb664d3a01c9..77efed89c79e 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -227,16 +227,16 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_node *rnp, bool wake) /* * Report expedited quiescent state for multiple CPUs, all covered by the - * specified leaf rcu_node structure. + * specified leaf rcu_node structure, which is acquired by the caller. */ -static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, +static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, unsigned long flags, unsigned long mask, bool wake) + __releases(rnp->lock) { int cpu; - unsigned long flags; struct rcu_data *rdp; - raw_spin_lock_irqsave_rcu_node(rnp, flags); + raw_lockdep_assert_held_rcu_node(rnp); if (!(rnp->expmask & mask)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; @@ -257,8 +257,13 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, */ static void rcu_report_exp_rdp(struct rcu_data *rdp) { + unsigned long flags; + struct rcu_node *rnp = rdp->mynode; + + raw_spin_lock_irqsave_rcu_node(rnp, flags); WRITE_ONCE(rdp->cpu_no_qs.b.exp, false); - rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true); + ASSERT_EXCLUSIVE_WRITER(rdp->cpu_no_qs.b.exp); + rcu_report_exp_cpu_mult(rnp, flags, rdp->grpmask, true); } /* Common code for work-done checking. */ @@ -432,8 +437,10 @@ retry_ipi: raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* Report quiescent states for those that went offline. */ - if (mask_ofl_test) - rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false); + if (mask_ofl_test) { + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rcu_report_exp_cpu_mult(rnp, flags, mask_ofl_test, false); + } } static void rcu_exp_sel_wait_wake(unsigned long s); @@ -712,6 +719,18 @@ static void rcu_exp_sel_wait_wake(unsigned long s) rcu_exp_wait_wake(s); } +/* Request an expedited quiescent state. */ +static void rcu_exp_need_qs(void) +{ + lockdep_assert_irqs_disabled(); + ASSERT_EXCLUSIVE_WRITER_SCOPED(*this_cpu_ptr(&rcu_data.cpu_no_qs.b.exp)); + __this_cpu_write(rcu_data.cpu_no_qs.b.exp, true); + /* Store .exp before .rcu_urgent_qs. */ + smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true); + set_tsk_need_resched(current); + set_preempt_need_resched(); +} + #ifdef CONFIG_PREEMPT_RCU /* @@ -730,24 +749,34 @@ static void rcu_exp_handler(void *unused) struct task_struct *t = current; /* - * First, the common case of not being in an RCU read-side + * First, is there no need for a quiescent state from this CPU, + * or is this CPU already looking for a quiescent state for the + * current grace period? If either is the case, just leave. + * However, this should not happen due to the preemptible + * sync_sched_exp_online_cleanup() implementation being a no-op, + * so warn if this does happen. + */ + ASSERT_EXCLUSIVE_WRITER_SCOPED(rdp->cpu_no_qs.b.exp); + if (WARN_ON_ONCE(!(READ_ONCE(rnp->expmask) & rdp->grpmask) || + READ_ONCE(rdp->cpu_no_qs.b.exp))) + return; + + /* + * Second, the common case of not being in an RCU read-side * critical section. If also enabled or idle, immediately * report the quiescent state, otherwise defer. */ if (!depth) { if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) || - rcu_is_cpu_rrupt_from_idle()) { + rcu_is_cpu_rrupt_from_idle()) rcu_report_exp_rdp(rdp); - } else { - WRITE_ONCE(rdp->cpu_no_qs.b.exp, true); - set_tsk_need_resched(t); - set_preempt_need_resched(); - } + else + rcu_exp_need_qs(); return; } /* - * Second, the less-common case of being in an RCU read-side + * Third, the less-common case of being in an RCU read-side * critical section. In this case we can count on a future * rcu_read_unlock(). However, this rcu_read_unlock() might * execute on some other CPU, but in that case there will be @@ -768,7 +797,7 @@ static void rcu_exp_handler(void *unused) return; } - // Finally, negative nesting depth should not happen. + // Fourth and finally, negative nesting depth should not happen. WARN_ON_ONCE(1); } @@ -835,16 +864,6 @@ static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp) #else /* #ifdef CONFIG_PREEMPT_RCU */ -/* Request an expedited quiescent state. */ -static void rcu_exp_need_qs(void) -{ - __this_cpu_write(rcu_data.cpu_no_qs.b.exp, true); - /* Store .exp before .rcu_urgent_qs. */ - smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true); - set_tsk_need_resched(current); - set_preempt_need_resched(); -} - /* Invoked on each online non-idle CPU for expedited quiescent state. */ static void rcu_exp_handler(void *unused) { @@ -852,6 +871,7 @@ static void rcu_exp_handler(void *unused) struct rcu_node *rnp = rdp->mynode; bool preempt_bh_enabled = !(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)); + ASSERT_EXCLUSIVE_WRITER_SCOPED(rdp->cpu_no_qs.b.exp); if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) || __this_cpu_read(rcu_data.cpu_no_qs.b.exp)) return; diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 3927ea5f7955..3600152b858e 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -275,6 +275,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) rcu_report_exp_rdp(rdp); else WARN_ON_ONCE(rdp->cpu_no_qs.b.exp); + ASSERT_EXCLUSIVE_WRITER_SCOPED(rdp->cpu_no_qs.b.exp); } /* @@ -1217,16 +1218,13 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->boost_kthread_task = t; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + rcu_thread_affine_rnp(t, rnp); wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ } -static struct task_struct *rcu_boost_task(struct rcu_node *rnp) -{ - return READ_ONCE(rnp->boost_kthread_task); -} - #else /* #ifdef CONFIG_RCU_BOOST */ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) @@ -1243,10 +1241,6 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) { } -static struct task_struct *rcu_boost_task(struct rcu_node *rnp) -{ - return NULL; -} #endif /* #else #ifdef CONFIG_RCU_BOOST */ /* diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index f8436969e0c8..c912b594ba98 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -527,12 +527,12 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read); #if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST) /* Get rcutorture access to sched_setaffinity(). */ -long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask, bool dowarn) { int ret; ret = sched_setaffinity(pid, in_mask); - WARN_ONCE(ret, "%s: sched_setaffinity(%d) returned %d\n", __func__, pid, ret); + WARN_ONCE(dowarn && ret, "%s: sched_setaffinity(%d) returned %d\n", __func__, pid, ret); return ret; } EXPORT_SYMBOL_GPL(torture_sched_setaffinity); diff --git a/kernel/reboot.c b/kernel/reboot.c index a701000bab34..b5a8569e5d81 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -1287,7 +1287,7 @@ static struct attribute *reboot_attrs[] = { }; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_reboot_table[] = { +static const struct ctl_table kern_reboot_table[] = { { .procname = "poweroff_cmd", .data = &poweroff_cmd, diff --git a/kernel/resource.c b/kernel/resource.c index b7c0e24d9398..12004452d999 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1683,8 +1683,7 @@ void __devm_release_region(struct device *dev, struct resource *parent, { struct region_devres match_data = { parent, start, n }; - __release_region(parent, start, n); - WARN_ON(devres_destroy(dev, devm_region_release, devm_region_match, + WARN_ON(devres_release(dev, devm_region_release, devm_region_match, &match_data)); } EXPORT_SYMBOL(__devm_release_region); diff --git a/kernel/rseq.c b/kernel/rseq.c index 9de6e35fe679..442aba29bc4c 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #define CREATE_TRACE_POINTS @@ -25,6 +26,78 @@ RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL | \ RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE) +#ifdef CONFIG_DEBUG_RSEQ +static struct rseq *rseq_kernel_fields(struct task_struct *t) +{ + return (struct rseq *) t->rseq_fields; +} + +static int rseq_validate_ro_fields(struct task_struct *t) +{ + static DEFINE_RATELIMIT_STATE(_rs, + DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + u32 cpu_id_start, cpu_id, node_id, mm_cid; + struct rseq __user *rseq = t->rseq; + + /* + * Validate fields which are required to be read-only by + * user-space. + */ + if (!user_read_access_begin(rseq, t->rseq_len)) + goto efault; + unsafe_get_user(cpu_id_start, &rseq->cpu_id_start, efault_end); + unsafe_get_user(cpu_id, &rseq->cpu_id, efault_end); + unsafe_get_user(node_id, &rseq->node_id, efault_end); + unsafe_get_user(mm_cid, &rseq->mm_cid, efault_end); + user_read_access_end(); + + if ((cpu_id_start != rseq_kernel_fields(t)->cpu_id_start || + cpu_id != rseq_kernel_fields(t)->cpu_id || + node_id != rseq_kernel_fields(t)->node_id || + mm_cid != rseq_kernel_fields(t)->mm_cid) && __ratelimit(&_rs)) { + + pr_warn("Detected rseq corruption for pid: %d, name: %s\n" + "\tcpu_id_start: %u ?= %u\n" + "\tcpu_id: %u ?= %u\n" + "\tnode_id: %u ?= %u\n" + "\tmm_cid: %u ?= %u\n", + t->pid, t->comm, + cpu_id_start, rseq_kernel_fields(t)->cpu_id_start, + cpu_id, rseq_kernel_fields(t)->cpu_id, + node_id, rseq_kernel_fields(t)->node_id, + mm_cid, rseq_kernel_fields(t)->mm_cid); + } + + /* For now, only print a console warning on mismatch. */ + return 0; + +efault_end: + user_read_access_end(); +efault: + return -EFAULT; +} + +static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id, + u32 node_id, u32 mm_cid) +{ + rseq_kernel_fields(t)->cpu_id_start = cpu_id; + rseq_kernel_fields(t)->cpu_id = cpu_id; + rseq_kernel_fields(t)->node_id = node_id; + rseq_kernel_fields(t)->mm_cid = mm_cid; +} +#else +static int rseq_validate_ro_fields(struct task_struct *t) +{ + return 0; +} + +static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id, + u32 node_id, u32 mm_cid) +{ +} +#endif + /* * * Restartable sequences are a lightweight interface that allows @@ -92,6 +165,11 @@ static int rseq_update_cpu_node_id(struct task_struct *t) u32 node_id = cpu_to_node(cpu_id); u32 mm_cid = task_mm_cid(t); + /* + * Validate read-only rseq fields. + */ + if (rseq_validate_ro_fields(t)) + goto efault; WARN_ON_ONCE((int) mm_cid < 0); if (!user_write_access_begin(rseq, t->rseq_len)) goto efault; @@ -105,6 +183,7 @@ static int rseq_update_cpu_node_id(struct task_struct *t) * t->rseq_len != ORIG_RSEQ_SIZE. */ user_write_access_end(); + rseq_set_ro_fields(t, cpu_id, cpu_id, node_id, mm_cid); trace_rseq_update(t); return 0; @@ -119,6 +198,11 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0, mm_cid = 0; + /* + * Validate read-only rseq fields. + */ + if (rseq_validate_ro_fields(t)) + return -EFAULT; /* * Reset cpu_id_start to its initial state (0). */ @@ -141,6 +225,9 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) */ if (put_user(mm_cid, &t->rseq->mm_cid)) return -EFAULT; + + rseq_set_ro_fields(t, cpu_id_start, cpu_id, node_id, mm_cid); + /* * Additional feature fields added after ORIG_RSEQ_SIZE * need to be conditionally reset only if @@ -423,6 +510,17 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, current->rseq = rseq; current->rseq_len = rseq_len; current->rseq_sig = sig; +#ifdef CONFIG_DEBUG_RSEQ + /* + * Initialize the in-kernel rseq fields copy for validation of + * read-only fields. + */ + if (get_user(rseq_kernel_fields(current)->cpu_id_start, &rseq->cpu_id_start) || + get_user(rseq_kernel_fields(current)->cpu_id, &rseq->cpu_id) || + get_user(rseq_kernel_fields(current)->node_id, &rseq->node_id) || + get_user(rseq_kernel_fields(current)->mm_cid, &rseq->mm_cid)) + return -EFAULT; +#endif /* * If rseq was previously inactive, and has just been * registered, ensure the cpu_id_start and cpu_id fields diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index db68a964e34e..83d46b9b8ec8 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -9,7 +9,7 @@ static struct autogroup autogroup_default; static atomic_t autogroup_seq_nr; #ifdef CONFIG_SYSCTL -static struct ctl_table sched_autogroup_sysctls[] = { +static const struct ctl_table sched_autogroup_sysctls[] = { { .procname = "sched_autogroup_enabled", .data = &sysctl_sched_autogroup_enabled, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3e5a6bf587f9..165c90ba64ea 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -740,39 +740,43 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) s64 __maybe_unused steal = 0, irq_delta = 0; #ifdef CONFIG_IRQ_TIME_ACCOUNTING - irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + if (irqtime_enabled()) { + irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; - /* - * Since irq_time is only updated on {soft,}irq_exit, we might run into - * this case when a previous update_rq_clock() happened inside a - * {soft,}IRQ region. - * - * When this happens, we stop ->clock_task and only update the - * prev_irq_time stamp to account for the part that fit, so that a next - * update will consume the rest. This ensures ->clock_task is - * monotonic. - * - * It does however cause some slight miss-attribution of {soft,}IRQ - * time, a more accurate solution would be to update the irq_time using - * the current rq->clock timestamp, except that would require using - * atomic ops. - */ - if (irq_delta > delta) - irq_delta = delta; + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}IRQ region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}IRQ + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; - rq->prev_irq_time += irq_delta; - delta -= irq_delta; - delayacct_irq(rq->curr, irq_delta); + rq->prev_irq_time += irq_delta; + delta -= irq_delta; + delayacct_irq(rq->curr, irq_delta); + } #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((¶virt_steal_rq_enabled))) { - steal = paravirt_steal_clock(cpu_of(rq)); + u64 prev_steal; + + steal = prev_steal = paravirt_steal_clock(cpu_of(rq)); steal -= rq->prev_steal_time_rq; if (unlikely(steal > delta)) steal = delta; - rq->prev_steal_time_rq += steal; + rq->prev_steal_time_rq = prev_steal; delta -= steal; } #endif @@ -789,6 +793,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) void update_rq_clock(struct rq *rq) { s64 delta; + u64 clock; lockdep_assert_rq_held(rq); @@ -800,11 +805,14 @@ void update_rq_clock(struct rq *rq) SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED); rq->clock_update_flags |= RQCF_UPDATED; #endif + clock = sched_clock_cpu(cpu_of(rq)); + scx_rq_clock_update(rq, clock); - delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + delta = clock - rq->clock; if (delta < 0) return; rq->clock += delta; + update_rq_clock_task(rq, delta); } @@ -1168,13 +1176,13 @@ int get_nohz_timer_target(void) struct sched_domain *sd; const struct cpumask *hk_mask; - if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) { + if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) { if (!idle_cpu(cpu)) return cpu; default_cpu = cpu; } - hk_mask = housekeeping_cpumask(HK_TYPE_TIMER); + hk_mask = housekeeping_cpumask(HK_TYPE_KERNEL_NOISE); guard(rcu)(); @@ -1189,7 +1197,7 @@ int get_nohz_timer_target(void) } if (default_cpu == -1) - default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER); + default_cpu = housekeeping_any_cpu(HK_TYPE_KERNEL_NOISE); return default_cpu; } @@ -1341,7 +1349,7 @@ bool sched_can_stop_tick(struct rq *rq) if (scx_enabled() && !scx_can_stop_tick(rq)) return false; - if (rq->cfs.h_nr_running > 1) + if (rq->cfs.h_nr_queued > 1) return false; /* @@ -3534,7 +3542,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * * More yuck to audit. */ - do_set_cpus_allowed(p, task_cpu_possible_mask(p)); + do_set_cpus_allowed(p, task_cpu_fallback_mask(p)); state = fail; break; case fail: @@ -4646,7 +4654,7 @@ static int sysctl_schedstats(const struct ctl_table *table, int write, void *buf #endif /* CONFIG_SCHEDSTATS */ #ifdef CONFIG_SYSCTL -static struct ctl_table sched_core_sysctls[] = { +static const struct ctl_table sched_core_sysctls[] = { #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", @@ -5632,7 +5640,7 @@ void sched_tick(void) unsigned long hw_pressure; u64 resched_latency; - if (housekeeping_cpu(cpu, HK_TYPE_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) arch_scale_freq_tick(); sched_clock_tick(); @@ -5771,7 +5779,7 @@ static void sched_tick_start(int cpu) int os; struct tick_work *twork; - if (housekeeping_cpu(cpu, HK_TYPE_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -5792,7 +5800,7 @@ static void sched_tick_stop(int cpu) struct tick_work *twork; int os; - if (housekeeping_cpu(cpu, HK_TYPE_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -6018,7 +6026,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * opportunity to pull in more work from other CPUs. */ if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) && - rq->nr_running == rq->cfs.h_nr_running)) { + rq->nr_running == rq->cfs.h_nr_queued)) { p = pick_next_task_fair(rq, prev, rf); if (unlikely(p == RETRY_TASK)) @@ -6641,7 +6649,6 @@ static void __sched notrace __schedule(int sched_mode) * as a preemption by schedule_debug() and RCU. */ bool preempt = sched_mode > SM_NONE; - bool block = false; unsigned long *switch_count; unsigned long prev_state; struct rq_flags rf; @@ -6702,7 +6709,7 @@ static void __sched notrace __schedule(int sched_mode) goto picked; } } else if (!preempt && prev_state) { - block = try_to_block_task(rq, prev, prev_state); + try_to_block_task(rq, prev, prev_state); switch_count = &prev->nvcsw; } @@ -6748,7 +6755,8 @@ picked: migrate_disable_switch(rq, prev); psi_account_irqtime(rq, prev, next); - psi_sched_switch(prev, next, block); + psi_sched_switch(prev, next, !task_on_rq_queued(prev) || + prev->se.sched_delayed); trace_sched_switch(preempt, prev, next, prev_state); @@ -7701,9 +7709,9 @@ void sched_show_task(struct task_struct *p) if (pid_alive(p)) ppid = task_pid_nr(rcu_dereference(p->real_parent)); rcu_read_unlock(); - pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n", + pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d task_flags:0x%04x flags:0x%08lx\n", free, task_pid_nr(p), task_tgid_nr(p), - ppid, read_task_thread_flags(p)); + ppid, p->flags, read_task_thread_flags(p)); print_worker_info(KERN_INFO, p); print_stop_info(KERN_INFO, p); @@ -7930,19 +7938,26 @@ void sched_setnuma(struct task_struct *p, int nid) #ifdef CONFIG_HOTPLUG_CPU /* - * Ensure that the idle task is using init_mm right before its CPU goes - * offline. + * Invoked on the outgoing CPU in context of the CPU hotplug thread + * after ensuring that there are no user space tasks left on the CPU. + * + * If there is a lazy mm in use on the hotplug thread, drop it and + * switch to init_mm. + * + * The reference count on init_mm is dropped in finish_cpu(). */ -void idle_task_exit(void) +static void sched_force_init_mm(void) { struct mm_struct *mm = current->active_mm; - BUG_ON(cpu_online(smp_processor_id())); - BUG_ON(current != this_rq()->idle); - if (mm != &init_mm) { - switch_mm(mm, &init_mm, current); + mmgrab_lazy_tlb(&init_mm); + local_irq_disable(); + current->active_mm = &init_mm; + switch_mm_irqs_off(mm, &init_mm, current); + local_irq_enable(); finish_arch_post_lock_switch(); + mmdrop_lazy_tlb(mm); } /* finish_cpu(), as ran on the BP, will clean up the active_mm state */ @@ -8180,19 +8195,14 @@ static void cpuset_cpu_active(void) cpuset_update_active_cpus(); } -static int cpuset_cpu_inactive(unsigned int cpu) +static void cpuset_cpu_inactive(unsigned int cpu) { if (!cpuhp_tasks_frozen) { - int ret = dl_bw_check_overflow(cpu); - - if (ret) - return ret; cpuset_update_active_cpus(); } else { num_cpus_frozen++; partition_sched_domains(1, NULL, NULL); } - return 0; } static inline void sched_smt_present_inc(int cpu) @@ -8254,6 +8264,11 @@ int sched_cpu_deactivate(unsigned int cpu) struct rq *rq = cpu_rq(cpu); int ret; + ret = dl_bw_deactivate(cpu); + + if (ret) + return ret; + /* * Remove CPU from nohz.idle_cpus_mask to prevent participating in * load balancing when not active @@ -8299,15 +8314,7 @@ int sched_cpu_deactivate(unsigned int cpu) return 0; sched_update_numa(cpu, false); - ret = cpuset_cpu_inactive(cpu); - if (ret) { - sched_smt_present_inc(cpu); - sched_set_rq_online(rq, cpu); - balance_push_set(cpu, false); - set_cpu_active(cpu, true); - sched_update_numa(cpu, true); - return ret; - } + cpuset_cpu_inactive(cpu); sched_domains_numa_masks_clear(cpu); return 0; } @@ -8344,6 +8351,7 @@ int sched_cpu_starting(unsigned int cpu) int sched_cpu_wait_empty(unsigned int cpu) { balance_hotplug_wait(); + sched_force_init_mm(); return 0; } @@ -10590,7 +10598,7 @@ void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) return; /* No page allocation under rq lock */ - task_work_add(curr, work, TWA_RESUME | TWAF_NO_ALLOC); + task_work_add(curr, work, TWA_RESUME); } void sched_mm_cid_exit_signals(struct task_struct *t) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 28c77904ea74..1a19d69b91ed 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -83,7 +83,7 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) if (unlikely(sg_policy->limits_changed)) { sg_policy->limits_changed = false; - sg_policy->need_freq_update = true; + sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); return true; } @@ -96,7 +96,7 @@ static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time, unsigned int next_freq) { if (sg_policy->need_freq_update) - sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); + sg_policy->need_freq_update = false; else if (sg_policy->next_freq == next_freq) return false; @@ -604,31 +604,6 @@ static const struct kobj_type sugov_tunables_ktype = { /********************** cpufreq governor interface *********************/ -#ifdef CONFIG_ENERGY_MODEL -static void rebuild_sd_workfn(struct work_struct *work) -{ - rebuild_sched_domains_energy(); -} - -static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn); - -/* - * EAS shouldn't be attempted without sugov, so rebuild the sched_domains - * on governor changes to make sure the scheduler knows about it. - */ -static void sugov_eas_rebuild_sd(void) -{ - /* - * When called from the cpufreq_register_driver() path, the - * cpu_hotplug_lock is already held, so use a work item to - * avoid nested locking in rebuild_sched_domains(). - */ - schedule_work(&rebuild_sd_work); -} -#else -static inline void sugov_eas_rebuild_sd(void) { }; -#endif - struct cpufreq_governor schedutil_gov; static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy) @@ -691,7 +666,11 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy) } sg_policy->thread = thread; - kthread_bind_mask(thread, policy->related_cpus); + if (policy->dvfs_possible_from_any_cpu) + set_cpus_allowed_ptr(thread, policy->related_cpus); + else + kthread_bind_mask(thread, policy->related_cpus); + init_irq_work(&sg_policy->irq_work, sugov_irq_work); mutex_init(&sg_policy->work_lock); @@ -784,7 +763,11 @@ static int sugov_init(struct cpufreq_policy *policy) goto fail; out: - sugov_eas_rebuild_sd(); + /* + * Schedutil is the preferred governor for EAS, so rebuild sched domains + * on governor changes to make sure the scheduler knows about them. + */ + em_rebuild_sched_domains(); mutex_unlock(&global_tunables_lock); return 0; @@ -826,7 +809,7 @@ static void sugov_exit(struct cpufreq_policy *policy) sugov_policy_free(sg_policy); cpufreq_disable_fast_switch(policy); - sugov_eas_rebuild_sd(); + em_rebuild_sched_domains(); } static int sugov_start(struct cpufreq_policy *policy) diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 0bed0fa1acd9..5d9143dd0879 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -9,6 +9,8 @@ #ifdef CONFIG_IRQ_TIME_ACCOUNTING +DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime); + /* * There are no locks covering percpu hardirq/softirq time. * They are only modified in vtime_account, on corresponding CPU @@ -22,16 +24,14 @@ */ DEFINE_PER_CPU(struct irqtime, cpu_irqtime); -static int sched_clock_irqtime; - void enable_sched_clock_irqtime(void) { - sched_clock_irqtime = 1; + static_branch_enable(&sched_clock_irqtime); } void disable_sched_clock_irqtime(void) { - sched_clock_irqtime = 0; + static_branch_disable(&sched_clock_irqtime); } static void irqtime_account_delta(struct irqtime *irqtime, u64 delta, @@ -57,7 +57,7 @@ void irqtime_account_irq(struct task_struct *curr, unsigned int offset) s64 delta; int cpu; - if (!sched_clock_irqtime) + if (!irqtime_enabled()) return; cpu = smp_processor_id(); @@ -90,8 +90,6 @@ static u64 irqtime_tick_accounted(u64 maxtime) #else /* CONFIG_IRQ_TIME_ACCOUNTING */ -#define sched_clock_irqtime (0) - static u64 irqtime_tick_accounted(u64 dummy) { return 0; @@ -478,7 +476,7 @@ void account_process_tick(struct task_struct *p, int user_tick) if (vtime_accounting_enabled_this_cpu()) return; - if (sched_clock_irqtime) { + if (irqtime_enabled()) { irqtime_account_process_tick(p, user_tick, 1); return; } @@ -507,7 +505,7 @@ void account_idle_ticks(unsigned long ticks) { u64 cputime, steal; - if (sched_clock_irqtime) { + if (irqtime_enabled()) { irqtime_account_idle_ticks(ticks); return; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index d94f2ed6d1f4..38e4537790af 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -26,7 +26,7 @@ static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */ static unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */ #ifdef CONFIG_SYSCTL -static struct ctl_table sched_dl_sysctls[] = { +static const struct ctl_table sched_dl_sysctls[] = { { .procname = "sched_deadline_period_max_us", .data = &sysctl_sched_dl_period_max, @@ -342,6 +342,29 @@ static void dl_rq_change_utilization(struct rq *rq, struct sched_dl_entity *dl_s __add_rq_bw(new_bw, &rq->dl); } +static __always_inline +void cancel_dl_timer(struct sched_dl_entity *dl_se, struct hrtimer *timer) +{ + /* + * If the timer callback was running (hrtimer_try_to_cancel == -1), + * it will eventually call put_task_struct(). + */ + if (hrtimer_try_to_cancel(timer) == 1 && !dl_server(dl_se)) + put_task_struct(dl_task_of(dl_se)); +} + +static __always_inline +void cancel_replenish_timer(struct sched_dl_entity *dl_se) +{ + cancel_dl_timer(dl_se, &dl_se->dl_timer); +} + +static __always_inline +void cancel_inactive_timer(struct sched_dl_entity *dl_se) +{ + cancel_dl_timer(dl_se, &dl_se->inactive_timer); +} + static void dl_change_utilization(struct task_struct *p, u64 new_bw) { WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV); @@ -495,10 +518,7 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags) * will not touch the rq's active utilization, * so we are still safe. */ - if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) { - if (!dl_server(dl_se)) - put_task_struct(dl_task_of(dl_se)); - } + cancel_inactive_timer(dl_se); } else { /* * Since "dl_non_contending" is not set, the @@ -2115,13 +2135,8 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * The replenish timer needs to be canceled. No * problem if it fires concurrently: boosted threads * are ignored in dl_task_timer(). - * - * If the timer callback was running (hrtimer_try_to_cancel == -1), - * it will eventually call put_task_struct(). */ - if (hrtimer_try_to_cancel(&p->dl.dl_timer) == 1 && - !dl_server(&p->dl)) - put_task_struct(p); + cancel_replenish_timer(&p->dl); p->dl.dl_throttled = 0; } } else if (!dl_prio(p->normal_prio)) { @@ -2289,8 +2304,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused * will not touch the rq's active utilization, * so we are still safe. */ - if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) - put_task_struct(p); + cancel_inactive_timer(&p->dl); } sub_rq_bw(&p->dl, &rq->dl); rq_unlock(rq, &rf); @@ -2506,16 +2520,13 @@ static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu return NULL; next_node = rb_first_cached(&rq->dl.pushable_dl_tasks_root); - -next_node: - if (next_node) { + while (next_node) { p = __node_2_pdl(next_node); if (task_is_pushable(rq, p, cpu)) return p; next_node = rb_next(next_node); - goto next_node; } return NULL; @@ -2964,11 +2975,22 @@ void dl_add_task_root_domain(struct task_struct *p) void dl_clear_root_domain(struct root_domain *rd) { - unsigned long flags; + int i; - raw_spin_lock_irqsave(&rd->dl_bw.lock, flags); + guard(raw_spinlock_irqsave)(&rd->dl_bw.lock); rd->dl_bw.total_bw = 0; - raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags); + + /* + * dl_server bandwidth is only restored when CPUs are attached to root + * domains (after domains are created or CPUs moved back to the + * default root doamin). + */ + for_each_cpu(i, rd->span) { + struct sched_dl_entity *dl_se = &cpu_rq(i)->fair_server; + + if (dl_server(dl_se) && cpu_active(i)) + rd->dl_bw.total_bw += dl_se->dl_bw; + } } #endif /* CONFIG_SMP */ @@ -3029,8 +3051,7 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) */ static void switched_to_dl(struct rq *rq, struct task_struct *p) { - if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) - put_task_struct(p); + cancel_inactive_timer(&p->dl); /* * In case a task is setscheduled to SCHED_DEADLINE we need to keep @@ -3453,29 +3474,31 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, } enum dl_bw_request { - dl_bw_req_check_overflow = 0, + dl_bw_req_deactivate = 0, dl_bw_req_alloc, dl_bw_req_free }; static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw) { - unsigned long flags; + unsigned long flags, cap; struct dl_bw *dl_b; bool overflow = 0; + u64 fair_server_bw = 0; rcu_read_lock_sched(); dl_b = dl_bw_of(cpu); raw_spin_lock_irqsave(&dl_b->lock, flags); - if (req == dl_bw_req_free) { + cap = dl_bw_capacity(cpu); + switch (req) { + case dl_bw_req_free: __dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu)); - } else { - unsigned long cap = dl_bw_capacity(cpu); - + break; + case dl_bw_req_alloc: overflow = __dl_overflow(dl_b, cap, 0, dl_bw); - if (req == dl_bw_req_alloc && !overflow) { + if (!overflow) { /* * We reserve space in the destination * root_domain, as we can't fail after this point. @@ -3484,6 +3507,42 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw) */ __dl_add(dl_b, dl_bw, dl_bw_cpus(cpu)); } + break; + case dl_bw_req_deactivate: + /* + * cpu is not off yet, but we need to do the math by + * considering it off already (i.e., what would happen if we + * turn cpu off?). + */ + cap -= arch_scale_cpu_capacity(cpu); + + /* + * cpu is going offline and NORMAL tasks will be moved away + * from it. We can thus discount dl_server bandwidth + * contribution as it won't need to be servicing tasks after + * the cpu is off. + */ + if (cpu_rq(cpu)->fair_server.dl_server) + fair_server_bw = cpu_rq(cpu)->fair_server.dl_bw; + + /* + * Not much to check if no DEADLINE bandwidth is present. + * dl_servers we can discount, as tasks will be moved out the + * offlined CPUs anyway. + */ + if (dl_b->total_bw - fair_server_bw > 0) { + /* + * Leaving at least one CPU for DEADLINE tasks seems a + * wise thing to do. As said above, cpu is not offline + * yet, so account for that. + */ + if (dl_bw_cpus(cpu) - 1) + overflow = __dl_overflow(dl_b, cap, fair_server_bw, 0); + else + overflow = 1; + } + + break; } raw_spin_unlock_irqrestore(&dl_b->lock, flags); @@ -3492,9 +3551,9 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw) return overflow ? -EBUSY : 0; } -int dl_bw_check_overflow(int cpu) +int dl_bw_deactivate(int cpu) { - return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0); + return dl_bw_manage(dl_bw_req_deactivate, cpu, 0); } int dl_bw_alloc(int cpu, u64 dl_bw) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index a1be00a988bf..fd7e85220715 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -379,7 +379,7 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu return -EINVAL; } - if (rq->cfs.h_nr_running) { + if (rq->cfs.h_nr_queued) { update_rq_clock(rq); dl_server_stop(&rq->fair_server); } @@ -392,7 +392,7 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n", cpu_of(rq)); - if (rq->cfs.h_nr_running) + if (rq->cfs.h_nr_queued) dl_server_start(&rq->fair_server); } @@ -843,13 +843,10 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SPLIT_NS(right_vruntime)); spread = right_vruntime - left_vruntime; SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread)); - SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); - SEQ_printf(m, " .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running); - SEQ_printf(m, " .%-30s: %d\n", "h_nr_delayed", cfs_rq->h_nr_delayed); - SEQ_printf(m, " .%-30s: %d\n", "idle_nr_running", - cfs_rq->idle_nr_running); - SEQ_printf(m, " .%-30s: %d\n", "idle_h_nr_running", - cfs_rq->idle_h_nr_running); + SEQ_printf(m, " .%-30s: %d\n", "nr_queued", cfs_rq->nr_queued); + SEQ_printf(m, " .%-30s: %d\n", "h_nr_runnable", cfs_rq->h_nr_runnable); + SEQ_printf(m, " .%-30s: %d\n", "h_nr_queued", cfs_rq->h_nr_queued); + SEQ_printf(m, " .%-30s: %d\n", "h_nr_idle", cfs_rq->h_nr_idle); SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); #ifdef CONFIG_SMP SEQ_printf(m, " .%-30s: %lu\n", "load_avg", @@ -1295,8 +1292,10 @@ void resched_latency_warn(int cpu, u64 latency) { static DEFINE_RATELIMIT_STATE(latency_check_ratelimit, 60 * 60 * HZ, 1); - WARN(__ratelimit(&latency_check_ratelimit), - "sched: CPU %d need_resched set for > %llu ns (%d ticks) " - "without schedule\n", - cpu, latency, cpu_rq(cpu)->ticks_without_resched); + if (likely(!__ratelimit(&latency_check_ratelimit))) + return; + + pr_err("sched: CPU %d need_resched set for > %llu ns (%d ticks) without schedule\n", + cpu, latency, cpu_rq(cpu)->ticks_without_resched); + dump_stack(); } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 7fff1d045477..8857c0709bdd 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -206,7 +206,7 @@ struct scx_dump_ctx { */ struct sched_ext_ops { /** - * select_cpu - Pick the target CPU for a task which is being woken up + * @select_cpu: Pick the target CPU for a task which is being woken up * @p: task being woken up * @prev_cpu: the cpu @p was on before sleeping * @wake_flags: SCX_WAKE_* @@ -233,7 +233,7 @@ struct sched_ext_ops { s32 (*select_cpu)(struct task_struct *p, s32 prev_cpu, u64 wake_flags); /** - * enqueue - Enqueue a task on the BPF scheduler + * @enqueue: Enqueue a task on the BPF scheduler * @p: task being enqueued * @enq_flags: %SCX_ENQ_* * @@ -248,7 +248,7 @@ struct sched_ext_ops { void (*enqueue)(struct task_struct *p, u64 enq_flags); /** - * dequeue - Remove a task from the BPF scheduler + * @dequeue: Remove a task from the BPF scheduler * @p: task being dequeued * @deq_flags: %SCX_DEQ_* * @@ -264,7 +264,7 @@ struct sched_ext_ops { void (*dequeue)(struct task_struct *p, u64 deq_flags); /** - * dispatch - Dispatch tasks from the BPF scheduler and/or user DSQs + * @dispatch: Dispatch tasks from the BPF scheduler and/or user DSQs * @cpu: CPU to dispatch tasks for * @prev: previous task being switched out * @@ -287,7 +287,7 @@ struct sched_ext_ops { void (*dispatch)(s32 cpu, struct task_struct *prev); /** - * tick - Periodic tick + * @tick: Periodic tick * @p: task running currently * * This operation is called every 1/HZ seconds on CPUs which are @@ -297,7 +297,7 @@ struct sched_ext_ops { void (*tick)(struct task_struct *p); /** - * runnable - A task is becoming runnable on its associated CPU + * @runnable: A task is becoming runnable on its associated CPU * @p: task becoming runnable * @enq_flags: %SCX_ENQ_* * @@ -324,7 +324,7 @@ struct sched_ext_ops { void (*runnable)(struct task_struct *p, u64 enq_flags); /** - * running - A task is starting to run on its associated CPU + * @running: A task is starting to run on its associated CPU * @p: task starting to run * * See ->runnable() for explanation on the task state notifiers. @@ -332,7 +332,7 @@ struct sched_ext_ops { void (*running)(struct task_struct *p); /** - * stopping - A task is stopping execution + * @stopping: A task is stopping execution * @p: task stopping to run * @runnable: is task @p still runnable? * @@ -343,7 +343,7 @@ struct sched_ext_ops { void (*stopping)(struct task_struct *p, bool runnable); /** - * quiescent - A task is becoming not runnable on its associated CPU + * @quiescent: A task is becoming not runnable on its associated CPU * @p: task becoming not runnable * @deq_flags: %SCX_DEQ_* * @@ -363,7 +363,7 @@ struct sched_ext_ops { void (*quiescent)(struct task_struct *p, u64 deq_flags); /** - * yield - Yield CPU + * @yield: Yield CPU * @from: yielding task * @to: optional yield target task * @@ -378,7 +378,7 @@ struct sched_ext_ops { bool (*yield)(struct task_struct *from, struct task_struct *to); /** - * core_sched_before - Task ordering for core-sched + * @core_sched_before: Task ordering for core-sched * @a: task A * @b: task B * @@ -396,7 +396,7 @@ struct sched_ext_ops { bool (*core_sched_before)(struct task_struct *a, struct task_struct *b); /** - * set_weight - Set task weight + * @set_weight: Set task weight * @p: task to set weight for * @weight: new weight [1..10000] * @@ -405,7 +405,7 @@ struct sched_ext_ops { void (*set_weight)(struct task_struct *p, u32 weight); /** - * set_cpumask - Set CPU affinity + * @set_cpumask: Set CPU affinity * @p: task to set CPU affinity for * @cpumask: cpumask of cpus that @p can run on * @@ -415,7 +415,7 @@ struct sched_ext_ops { const struct cpumask *cpumask); /** - * update_idle - Update the idle state of a CPU + * @update_idle: Update the idle state of a CPU * @cpu: CPU to udpate the idle state for * @idle: whether entering or exiting the idle state * @@ -436,7 +436,7 @@ struct sched_ext_ops { void (*update_idle)(s32 cpu, bool idle); /** - * cpu_acquire - A CPU is becoming available to the BPF scheduler + * @cpu_acquire: A CPU is becoming available to the BPF scheduler * @cpu: The CPU being acquired by the BPF scheduler. * @args: Acquire arguments, see the struct definition. * @@ -446,7 +446,7 @@ struct sched_ext_ops { void (*cpu_acquire)(s32 cpu, struct scx_cpu_acquire_args *args); /** - * cpu_release - A CPU is taken away from the BPF scheduler + * @cpu_release: A CPU is taken away from the BPF scheduler * @cpu: The CPU being released by the BPF scheduler. * @args: Release arguments, see the struct definition. * @@ -458,7 +458,7 @@ struct sched_ext_ops { void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args); /** - * init_task - Initialize a task to run in a BPF scheduler + * @init_task: Initialize a task to run in a BPF scheduler * @p: task to initialize for BPF scheduling * @args: init arguments, see the struct definition * @@ -473,8 +473,9 @@ struct sched_ext_ops { s32 (*init_task)(struct task_struct *p, struct scx_init_task_args *args); /** - * exit_task - Exit a previously-running task from the system + * @exit_task: Exit a previously-running task from the system * @p: task to exit + * @args: exit arguments, see the struct definition * * @p is exiting or the BPF scheduler is being unloaded. Perform any * necessary cleanup for @p. @@ -482,7 +483,7 @@ struct sched_ext_ops { void (*exit_task)(struct task_struct *p, struct scx_exit_task_args *args); /** - * enable - Enable BPF scheduling for a task + * @enable: Enable BPF scheduling for a task * @p: task to enable BPF scheduling for * * Enable @p for BPF scheduling. enable() is called on @p any time it @@ -491,7 +492,7 @@ struct sched_ext_ops { void (*enable)(struct task_struct *p); /** - * disable - Disable BPF scheduling for a task + * @disable: Disable BPF scheduling for a task * @p: task to disable BPF scheduling for * * @p is exiting, leaving SCX or the BPF scheduler is being unloaded. @@ -501,7 +502,7 @@ struct sched_ext_ops { void (*disable)(struct task_struct *p); /** - * dump - Dump BPF scheduler state on error + * @dump: Dump BPF scheduler state on error * @ctx: debug dump context * * Use scx_bpf_dump() to generate BPF scheduler specific debug dump. @@ -509,7 +510,7 @@ struct sched_ext_ops { void (*dump)(struct scx_dump_ctx *ctx); /** - * dump_cpu - Dump BPF scheduler state for a CPU on error + * @dump_cpu: Dump BPF scheduler state for a CPU on error * @ctx: debug dump context * @cpu: CPU to generate debug dump for * @idle: @cpu is currently idle without any runnable tasks @@ -521,7 +522,7 @@ struct sched_ext_ops { void (*dump_cpu)(struct scx_dump_ctx *ctx, s32 cpu, bool idle); /** - * dump_task - Dump BPF scheduler state for a runnable task on error + * @dump_task: Dump BPF scheduler state for a runnable task on error * @ctx: debug dump context * @p: runnable task to generate debug dump for * @@ -532,7 +533,7 @@ struct sched_ext_ops { #ifdef CONFIG_EXT_GROUP_SCHED /** - * cgroup_init - Initialize a cgroup + * @cgroup_init: Initialize a cgroup * @cgrp: cgroup being initialized * @args: init arguments, see the struct definition * @@ -547,7 +548,7 @@ struct sched_ext_ops { struct scx_cgroup_init_args *args); /** - * cgroup_exit - Exit a cgroup + * @cgroup_exit: Exit a cgroup * @cgrp: cgroup being exited * * Either the BPF scheduler is being unloaded or @cgrp destroyed, exit @@ -556,7 +557,7 @@ struct sched_ext_ops { void (*cgroup_exit)(struct cgroup *cgrp); /** - * cgroup_prep_move - Prepare a task to be moved to a different cgroup + * @cgroup_prep_move: Prepare a task to be moved to a different cgroup * @p: task being moved * @from: cgroup @p is being moved from * @to: cgroup @p is being moved to @@ -571,7 +572,7 @@ struct sched_ext_ops { struct cgroup *from, struct cgroup *to); /** - * cgroup_move - Commit cgroup move + * @cgroup_move: Commit cgroup move * @p: task being moved * @from: cgroup @p is being moved from * @to: cgroup @p is being moved to @@ -582,7 +583,7 @@ struct sched_ext_ops { struct cgroup *from, struct cgroup *to); /** - * cgroup_cancel_move - Cancel cgroup move + * @cgroup_cancel_move: Cancel cgroup move * @p: task whose cgroup move is being canceled * @from: cgroup @p was being moved from * @to: cgroup @p was being moved to @@ -594,7 +595,7 @@ struct sched_ext_ops { struct cgroup *from, struct cgroup *to); /** - * cgroup_set_weight - A cgroup's weight is being changed + * @cgroup_set_weight: A cgroup's weight is being changed * @cgrp: cgroup whose weight is being updated * @weight: new weight [1..10000] * @@ -608,7 +609,7 @@ struct sched_ext_ops { */ /** - * cpu_online - A CPU became online + * @cpu_online: A CPU became online * @cpu: CPU which just came up * * @cpu just came online. @cpu will not call ops.enqueue() or @@ -617,7 +618,7 @@ struct sched_ext_ops { void (*cpu_online)(s32 cpu); /** - * cpu_offline - A CPU is going offline + * @cpu_offline: A CPU is going offline * @cpu: CPU which is going offline * * @cpu is going offline. @cpu will not call ops.enqueue() or @@ -630,12 +631,12 @@ struct sched_ext_ops { */ /** - * init - Initialize the BPF scheduler + * @init: Initialize the BPF scheduler */ s32 (*init)(void); /** - * exit - Clean up after the BPF scheduler + * @exit: Clean up after the BPF scheduler * @info: Exit info * * ops.exit() is also called on ops.init() failure, which is a bit @@ -645,17 +646,17 @@ struct sched_ext_ops { void (*exit)(struct scx_exit_info *info); /** - * dispatch_max_batch - Max nr of tasks that dispatch() can dispatch + * @dispatch_max_batch: Max nr of tasks that dispatch() can dispatch */ u32 dispatch_max_batch; /** - * flags - %SCX_OPS_* flags + * @flags: %SCX_OPS_* flags */ u64 flags; /** - * timeout_ms - The maximum amount of time, in milliseconds, that a + * @timeout_ms: The maximum amount of time, in milliseconds, that a * runnable task should be able to wait before being scheduled. The * maximum timeout may not exceed the default timeout of 30 seconds. * @@ -664,13 +665,13 @@ struct sched_ext_ops { u32 timeout_ms; /** - * exit_dump_len - scx_exit_info.dump buffer length. If 0, the default + * @exit_dump_len: scx_exit_info.dump buffer length. If 0, the default * value of 32768 is used. */ u32 exit_dump_len; /** - * hotplug_seq - A sequence number that may be set by the scheduler to + * @hotplug_seq: A sequence number that may be set by the scheduler to * detect when a hotplug event has occurred during the loading process. * If 0, no detection occurs. Otherwise, the scheduler will fail to * load if the sequence number does not match @scx_hotplug_seq on the @@ -679,7 +680,7 @@ struct sched_ext_ops { u64 hotplug_seq; /** - * name - BPF scheduler's name + * @name: BPF scheduler's name * * Must be a non-zero valid BPF object name including only isalnum(), * '_' and '.' chars. Shows up in kernel.sched_ext_ops sysctl while the @@ -960,7 +961,7 @@ static DEFINE_PER_CPU(struct task_struct *, direct_dispatch_task); static struct scx_dispatch_q **global_dsqs; static const struct rhashtable_params dsq_hash_params = { - .key_len = 8, + .key_len = sizeof_field(struct scx_dispatch_q, id), .key_offset = offsetof(struct scx_dispatch_q, id), .head_offset = offsetof(struct scx_dispatch_q, hash_node), }; @@ -1408,7 +1409,6 @@ static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter) /** * scx_task_iter_next_locked - Next non-idle task with its rq locked * @iter: iterator to walk - * @include_dead: Whether we should include dead tasks in the iteration * * Visit the non-idle task with its rq lock held. Allows callers to specify * whether they would like to filter out dead tasks. See scx_task_iter_start() @@ -2747,6 +2747,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) { struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); bool prev_on_scx = prev->sched_class == &ext_sched_class; + bool prev_on_rq = prev->scx.flags & SCX_TASK_QUEUED; int nr_loops = SCX_DSP_MAX_LOOPS; lockdep_assert_rq_held(rq); @@ -2779,8 +2780,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) * See scx_ops_disable_workfn() for the explanation on the * bypassing test. */ - if ((prev->scx.flags & SCX_TASK_QUEUED) && - prev->scx.slice && !scx_rq_bypassing(rq)) { + if (prev_on_rq && prev->scx.slice && !scx_rq_bypassing(rq)) { rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; } @@ -2813,6 +2813,10 @@ static int balance_one(struct rq *rq, struct task_struct *prev) flush_dispatch_buf(rq); + if (prev_on_rq && prev->scx.slice) { + rq->scx.flags |= SCX_RQ_BAL_KEEP; + goto has_tasks; + } if (rq->scx.local_dsq.nr) goto has_tasks; if (consume_global_dsq(rq)) @@ -2838,8 +2842,7 @@ no_tasks: * Didn't find another task to run. Keep running @prev unless * %SCX_OPS_ENQ_LAST is in effect. */ - if ((prev->scx.flags & SCX_TASK_QUEUED) && - (!static_branch_unlikely(&scx_ops_enq_last) || + if (prev_on_rq && (!static_branch_unlikely(&scx_ops_enq_last) || scx_rq_bypassing(rq))) { rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; @@ -3034,7 +3037,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, */ if (p->scx.slice && !scx_rq_bypassing(rq)) { dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD); - return; + goto switch_class; } /* @@ -3051,6 +3054,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, } } +switch_class: if (next && next->sched_class != &ext_sched_class) switch_class(rq, next); } @@ -3132,6 +3136,7 @@ static struct task_struct *pick_task_scx(struct rq *rq) * scx_prio_less - Task ordering for core-sched * @a: task A * @b: task B + * @in_fi: in forced idle state * * Core-sched is implemented as an additional scheduling layer on top of the * usual sched_class'es and needs to find out the expected task ordering. For @@ -3180,6 +3185,10 @@ static bool test_and_clear_cpu_idle(int cpu) * scx_pick_idle_cpu() can get caught in an infinite loop as * @cpu is never cleared from idle_masks.smt. Ensure that @cpu * is eventually cleared. + * + * NOTE: Use cpumask_intersects() and cpumask_test_cpu() to + * reduce memory writes, which may help alleviate cache + * coherence pressure. */ if (cpumask_intersects(smt, idle_masks.smt)) cpumask_andnot(idle_masks.smt, idle_masks.smt, smt); @@ -3215,6 +3224,74 @@ found: goto retry; } +/* + * Return the amount of CPUs in the same LLC domain of @cpu (or zero if the LLC + * domain is not defined). + */ +static unsigned int llc_weight(s32 cpu) +{ + struct sched_domain *sd; + + sd = rcu_dereference(per_cpu(sd_llc, cpu)); + if (!sd) + return 0; + + return sd->span_weight; +} + +/* + * Return the cpumask representing the LLC domain of @cpu (or NULL if the LLC + * domain is not defined). + */ +static struct cpumask *llc_span(s32 cpu) +{ + struct sched_domain *sd; + + sd = rcu_dereference(per_cpu(sd_llc, cpu)); + if (!sd) + return 0; + + return sched_domain_span(sd); +} + +/* + * Return the amount of CPUs in the same NUMA domain of @cpu (or zero if the + * NUMA domain is not defined). + */ +static unsigned int numa_weight(s32 cpu) +{ + struct sched_domain *sd; + struct sched_group *sg; + + sd = rcu_dereference(per_cpu(sd_numa, cpu)); + if (!sd) + return 0; + sg = sd->groups; + if (!sg) + return 0; + + return sg->group_weight; +} + +/* + * Return the cpumask representing the NUMA domain of @cpu (or NULL if the NUMA + * domain is not defined). + */ +static struct cpumask *numa_span(s32 cpu) +{ + struct sched_domain *sd; + struct sched_group *sg; + + sd = rcu_dereference(per_cpu(sd_numa, cpu)); + if (!sd) + return NULL; + sg = sd->groups; + if (!sg) + return NULL; + + return sched_group_span(sg); +} + /* * Return true if the LLC domains do not perfectly overlap with the NUMA * domains, false otherwise. @@ -3246,19 +3323,10 @@ static bool llc_numa_mismatch(void) * overlapping, which is incorrect (as NUMA 1 has two distinct LLC * domains). */ - for_each_online_cpu(cpu) { - const struct cpumask *numa_cpus; - struct sched_domain *sd; - - sd = rcu_dereference(per_cpu(sd_llc, cpu)); - if (!sd) + for_each_online_cpu(cpu) + if (llc_weight(cpu) != numa_weight(cpu)) return true; - numa_cpus = cpumask_of_node(cpu_to_node(cpu)); - if (sd->span_weight != cpumask_weight(numa_cpus)) - return true; - } - return false; } @@ -3276,8 +3344,7 @@ static bool llc_numa_mismatch(void) static void update_selcpu_topology(void) { bool enable_llc = false, enable_numa = false; - struct sched_domain *sd; - const struct cpumask *cpus; + unsigned int nr_cpus; s32 cpu = cpumask_first(cpu_online_mask); /* @@ -3291,10 +3358,12 @@ static void update_selcpu_topology(void) * CPUs. */ rcu_read_lock(); - sd = rcu_dereference(per_cpu(sd_llc, cpu)); - if (sd) { - if (sd->span_weight < num_online_cpus()) + nr_cpus = llc_weight(cpu); + if (nr_cpus > 0) { + if (nr_cpus < num_online_cpus()) enable_llc = true; + pr_debug("sched_ext: LLC=%*pb weight=%u\n", + cpumask_pr_args(llc_span(cpu)), llc_weight(cpu)); } /* @@ -3306,15 +3375,19 @@ static void update_selcpu_topology(void) * enabling both NUMA and LLC optimizations is unnecessary, as checking * for an idle CPU in the same domain twice is redundant. */ - cpus = cpumask_of_node(cpu_to_node(cpu)); - if ((cpumask_weight(cpus) < num_online_cpus()) && llc_numa_mismatch()) - enable_numa = true; + nr_cpus = numa_weight(cpu); + if (nr_cpus > 0) { + if (nr_cpus < num_online_cpus() && llc_numa_mismatch()) + enable_numa = true; + pr_debug("sched_ext: NUMA=%*pb weight=%u\n", + cpumask_pr_args(numa_span(cpu)), numa_weight(cpu)); + } rcu_read_unlock(); pr_debug("sched_ext: LLC idle selection %s\n", - enable_llc ? "enabled" : "disabled"); + str_enabled_disabled(enable_llc)); pr_debug("sched_ext: NUMA idle selection %s\n", - enable_numa ? "enabled" : "disabled"); + str_enabled_disabled(enable_numa)); if (enable_llc) static_branch_enable_cpuslocked(&scx_selcpu_topo_llc); @@ -3344,6 +3417,8 @@ static void update_selcpu_topology(void) * 4. Pick a CPU within the same NUMA node, if enabled: * - choose a CPU from the same NUMA node to reduce memory access latency. * + * 5. Pick any idle CPU usable by the task. + * * Step 3 and 4 are performed only if the system has, respectively, multiple * LLC domains / multiple NUMA nodes (see scx_selcpu_topo_llc and * scx_selcpu_topo_numa). @@ -3360,7 +3435,6 @@ static s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, *found = false; - /* * This is necessary to protect llc_cpus. */ @@ -3379,15 +3453,10 @@ static s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, */ if (p->nr_cpus_allowed >= num_possible_cpus()) { if (static_branch_maybe(CONFIG_NUMA, &scx_selcpu_topo_numa)) - numa_cpus = cpumask_of_node(cpu_to_node(prev_cpu)); + numa_cpus = numa_span(prev_cpu); - if (static_branch_maybe(CONFIG_SCHED_MC, &scx_selcpu_topo_llc)) { - struct sched_domain *sd; - - sd = rcu_dereference(per_cpu(sd_llc, prev_cpu)); - if (sd) - llc_cpus = sched_domain_span(sd); - } + if (static_branch_maybe(CONFIG_SCHED_MC, &scx_selcpu_topo_llc)) + llc_cpus = llc_span(prev_cpu); } /* @@ -3586,20 +3655,9 @@ static void reset_idle_masks(void) cpumask_copy(idle_masks.smt, cpu_online_mask); } -void __scx_update_idle(struct rq *rq, bool idle) +static void update_builtin_idle(int cpu, bool idle) { - int cpu = cpu_of(rq); - - if (SCX_HAS_OP(update_idle) && !scx_rq_bypassing(rq)) { - SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); - if (!static_branch_unlikely(&scx_builtin_idle_enabled)) - return; - } - - if (idle) - cpumask_set_cpu(cpu, idle_masks.cpu); - else - cpumask_clear_cpu(cpu, idle_masks.cpu); + assign_cpu(cpu, idle_masks.cpu, idle); #ifdef CONFIG_SCHED_SMT if (sched_smt_active()) { @@ -3610,10 +3668,8 @@ void __scx_update_idle(struct rq *rq, bool idle) * idle_masks.smt handling is racy but that's fine as * it's only for optimization and self-correcting. */ - for_each_cpu(cpu, smt) { - if (!cpumask_test_cpu(cpu, idle_masks.cpu)) - return; - } + if (!cpumask_subset(smt, idle_masks.cpu)) + return; cpumask_or(idle_masks.smt, idle_masks.smt, smt); } else { cpumask_andnot(idle_masks.smt, idle_masks.smt, smt); @@ -3622,6 +3678,57 @@ void __scx_update_idle(struct rq *rq, bool idle) #endif } +/* + * Update the idle state of a CPU to @idle. + * + * If @do_notify is true, ops.update_idle() is invoked to notify the scx + * scheduler of an actual idle state transition (idle to busy or vice + * versa). If @do_notify is false, only the idle state in the idle masks is + * refreshed without invoking ops.update_idle(). + * + * This distinction is necessary, because an idle CPU can be "reserved" and + * awakened via scx_bpf_pick_idle_cpu() + scx_bpf_kick_cpu(), marking it as + * busy even if no tasks are dispatched. In this case, the CPU may return + * to idle without a true state transition. Refreshing the idle masks + * without invoking ops.update_idle() ensures accurate idle state tracking + * while avoiding unnecessary updates and maintaining balanced state + * transitions. + */ +void __scx_update_idle(struct rq *rq, bool idle, bool do_notify) +{ + int cpu = cpu_of(rq); + + lockdep_assert_rq_held(rq); + + /* + * Trigger ops.update_idle() only when transitioning from a task to + * the idle thread and vice versa. + * + * Idle transitions are indicated by do_notify being set to true, + * managed by put_prev_task_idle()/set_next_task_idle(). + */ + if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq)) + SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); + + /* + * Update the idle masks: + * - for real idle transitions (do_notify == true) + * - for idle-to-idle transitions (indicated by the previous task + * being the idle thread, managed by pick_task_idle()) + * + * Skip updating idle masks if the previous task is not the idle + * thread, since set_next_task_idle() has already handled it when + * transitioning from a task to the idle thread (calling this + * function with do_notify == true). + * + * In this way we can avoid updating the idle masks twice, + * unnecessarily. + */ + if (static_branch_likely(&scx_builtin_idle_enabled)) + if (do_notify || is_idle_task(rq->curr)) + update_builtin_idle(cpu, idle); +} + static void handle_hotplug(struct rq *rq, bool online) { int cpu = cpu_of(rq); @@ -4641,6 +4748,7 @@ bool task_should_scx(int policy) /** * scx_softlockup - sched_ext softlockup handler + * @dur_s: number of seconds of CPU stuck due to soft lockup * * On some multi-socket setups (e.g. 2x Intel 8480c), the BPF scheduler can * live-lock the system by making many CPUs target the same DSQ to the point @@ -4684,6 +4792,7 @@ static void scx_clear_softlockup(void) /** * scx_ops_bypass - [Un]bypass scx_ops and guarantee forward progress + * @bypass: true for bypass, false for unbypass * * Bypassing guarantees that all runnable tasks make forward progress without * trusting the BPF scheduler. We can't grab any mutexes or rwsems as they might @@ -4744,10 +4853,9 @@ static void scx_ops_bypass(bool bypass) */ for_each_possible_cpu(cpu) { struct rq *rq = cpu_rq(cpu); - struct rq_flags rf; struct task_struct *p, *n; - rq_lock(rq, &rf); + raw_spin_rq_lock(rq); if (bypass) { WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING); @@ -4763,7 +4871,7 @@ static void scx_ops_bypass(bool bypass) * sees scx_rq_bypassing() before moving tasks to SCX. */ if (!scx_enabled()) { - rq_unlock_irqrestore(rq, &rf); + raw_spin_rq_unlock(rq); continue; } @@ -4783,10 +4891,11 @@ static void scx_ops_bypass(bool bypass) sched_enq_and_set_task(&ctx); } - rq_unlock(rq, &rf); - /* resched to restore ticks and idle state */ - resched_cpu(cpu); + if (cpu_online(cpu) || cpu == smp_processor_id()) + resched_curr(rq); + + raw_spin_rq_unlock(rq); } atomic_dec(&scx_ops_breather_depth); @@ -4852,7 +4961,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work) struct task_struct *p; struct rhashtable_iter rht_iter; struct scx_dispatch_q *dsq; - int i, kind; + int i, kind, cpu; kind = atomic_read(&scx_exit_kind); while (true) { @@ -4935,6 +5044,15 @@ static void scx_ops_disable_workfn(struct kthread_work *work) scx_task_iter_stop(&sti); percpu_up_write(&scx_fork_rwsem); + /* + * Invalidate all the rq clocks to prevent getting outdated + * rq clocks from a previous scx scheduler. + */ + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + scx_rq_clock_invalidate(rq); + } + /* no task is on scx, turn off all the switches and flush in-progress calls */ static_branch_disable(&__scx_ops_enabled); for (i = SCX_OPI_BEGIN; i < SCX_OPI_END; i++) @@ -5159,9 +5277,9 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK, p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK, ops_state >> SCX_OPSS_QSEQ_SHIFT); - dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu", + dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu slice=%llu", p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf, - p->scx.dsq_vtime); + p->scx.dsq_vtime, p->scx.slice); dump_line(s, " cpus=%*pb", cpumask_pr_args(p->cpus_ptr)); if (SCX_HAS_OP(dump_task)) { @@ -5352,7 +5470,7 @@ static struct kthread_worker *scx_create_rt_helper(const char *name) { struct kthread_worker *helper; - helper = kthread_create_worker(0, name); + helper = kthread_run_worker(0, name); if (helper) sched_set_fifo(helper->task); return helper; @@ -6236,6 +6354,15 @@ void __init init_sched_ext_class(void) __bpf_kfunc_start_defs(); +static bool check_builtin_idle_enabled(void) +{ + if (static_branch_likely(&scx_builtin_idle_enabled)) + return true; + + scx_ops_error("built-in idle tracking is disabled"); + return false; +} + /** * scx_bpf_select_cpu_dfl - The default implementation of ops.select_cpu() * @p: task_struct to select a CPU for @@ -6253,10 +6380,8 @@ __bpf_kfunc_start_defs(); __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) { - if (!static_branch_likely(&scx_builtin_idle_enabled)) { - scx_ops_error("built-in idle tracking is disabled"); + if (!check_builtin_idle_enabled()) goto prev_cpu; - } if (!scx_kf_allowed(SCX_KF_SELECT_CPU)) goto prev_cpu; @@ -6340,9 +6465,7 @@ __bpf_kfunc_start_defs(); * ops.select_cpu(), and ops.dispatch(). * * When called from ops.select_cpu() or ops.enqueue(), it's for direct dispatch - * and @p must match the task being enqueued. Also, %SCX_DSQ_LOCAL_ON can't be - * used to target the local DSQ of a CPU other than the enqueueing one. Use - * ops.select_cpu() to be on the target CPU in the first place. + * and @p must match the task being enqueued. * * When called from ops.select_cpu(), @enq_flags and @dsp_id are stored, and @p * will be directly inserted into the corresponding dispatch queue after @@ -7013,7 +7136,7 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, return -ENOENT; INIT_LIST_HEAD(&kit->cursor.node); - kit->cursor.flags |= SCX_DSQ_LNODE_ITER_CURSOR | flags; + kit->cursor.flags = SCX_DSQ_LNODE_ITER_CURSOR | flags; kit->cursor.priv = READ_ONCE(kit->dsq->seq); return 0; @@ -7181,7 +7304,7 @@ __bpf_kfunc void scx_bpf_error_bstr(char *fmt, unsigned long long *data, } /** - * scx_bpf_dump - Generate extra debug dump specific to the BPF scheduler + * scx_bpf_dump_bstr - Generate extra debug dump specific to the BPF scheduler * @fmt: format string * @data: format string parameters packaged using ___bpf_fill() macro * @data__sz: @data len, must end in '__sz' for the verifier @@ -7273,7 +7396,6 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu) * scx_bpf_cpuperf_set - Set the relative performance target of a CPU * @cpu: CPU of interest * @perf: target performance level [0, %SCX_CPUPERF_ONE] - * @flags: %SCX_CPUPERF_* flags * * Set the target performance level of @cpu to @perf. @perf is in linear * relative scale between 0 and %SCX_CPUPERF_ONE. This determines how the @@ -7350,10 +7472,8 @@ __bpf_kfunc void scx_bpf_put_cpumask(const struct cpumask *cpumask) */ __bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask(void) { - if (!static_branch_likely(&scx_builtin_idle_enabled)) { - scx_ops_error("built-in idle tracking is disabled"); + if (!check_builtin_idle_enabled()) return cpu_none_mask; - } #ifdef CONFIG_SMP return idle_masks.cpu; @@ -7371,10 +7491,8 @@ __bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask(void) */ __bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask(void) { - if (!static_branch_likely(&scx_builtin_idle_enabled)) { - scx_ops_error("built-in idle tracking is disabled"); + if (!check_builtin_idle_enabled()) return cpu_none_mask; - } #ifdef CONFIG_SMP if (sched_smt_active()) @@ -7389,6 +7507,7 @@ __bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask(void) /** * scx_bpf_put_idle_cpumask - Release a previously acquired referenced kptr to * either the percpu, or SMT idle-tracking cpumask. + * @idle_mask: &cpumask to use */ __bpf_kfunc void scx_bpf_put_idle_cpumask(const struct cpumask *idle_mask) { @@ -7412,10 +7531,8 @@ __bpf_kfunc void scx_bpf_put_idle_cpumask(const struct cpumask *idle_mask) */ __bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) { - if (!static_branch_likely(&scx_builtin_idle_enabled)) { - scx_ops_error("built-in idle tracking is disabled"); + if (!check_builtin_idle_enabled()) return false; - } if (ops_cpu_valid(cpu, NULL)) return test_and_clear_cpu_idle(cpu); @@ -7445,10 +7562,8 @@ __bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) __bpf_kfunc s32 scx_bpf_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags) { - if (!static_branch_likely(&scx_builtin_idle_enabled)) { - scx_ops_error("built-in idle tracking is disabled"); + if (!check_builtin_idle_enabled()) return -EBUSY; - } return scx_pick_idle_cpu(cpus_allowed, flags); } @@ -7543,6 +7658,68 @@ out: } #endif +/** + * scx_bpf_now - Returns a high-performance monotonically non-decreasing + * clock for the current CPU. The clock returned is in nanoseconds. + * + * It provides the following properties: + * + * 1) High performance: Many BPF schedulers call bpf_ktime_get_ns() frequently + * to account for execution time and track tasks' runtime properties. + * Unfortunately, in some hardware platforms, bpf_ktime_get_ns() -- which + * eventually reads a hardware timestamp counter -- is neither performant nor + * scalable. scx_bpf_now() aims to provide a high-performance clock by + * using the rq clock in the scheduler core whenever possible. + * + * 2) High enough resolution for the BPF scheduler use cases: In most BPF + * scheduler use cases, the required clock resolution is lower than the most + * accurate hardware clock (e.g., rdtsc in x86). scx_bpf_now() basically + * uses the rq clock in the scheduler core whenever it is valid. It considers + * that the rq clock is valid from the time the rq clock is updated + * (update_rq_clock) until the rq is unlocked (rq_unpin_lock). + * + * 3) Monotonically non-decreasing clock for the same CPU: scx_bpf_now() + * guarantees the clock never goes backward when comparing them in the same + * CPU. On the other hand, when comparing clocks in different CPUs, there + * is no such guarantee -- the clock can go backward. It provides a + * monotonically *non-decreasing* clock so that it would provide the same + * clock values in two different scx_bpf_now() calls in the same CPU + * during the same period of when the rq clock is valid. + */ +__bpf_kfunc u64 scx_bpf_now(void) +{ + struct rq *rq; + u64 clock; + + preempt_disable(); + + rq = this_rq(); + if (smp_load_acquire(&rq->scx.flags) & SCX_RQ_CLK_VALID) { + /* + * If the rq clock is valid, use the cached rq clock. + * + * Note that scx_bpf_now() is re-entrant between a process + * context and an interrupt context (e.g., timer interrupt). + * However, we don't need to consider the race between them + * because such race is not observable from a caller. + */ + clock = READ_ONCE(rq->scx.clock); + } else { + /* + * Otherwise, return a fresh rq clock. + * + * The rq clock is updated outside of the rq lock. + * In this case, keep the updated rq clock invalid so the next + * kfunc call outside the rq lock gets a fresh rq clock. + */ + clock = sched_clock_cpu(cpu_of(rq)); + } + + preempt_enable(); + + return clock; +} + __bpf_kfunc_end_defs(); BTF_KFUNCS_START(scx_kfunc_ids_any) @@ -7574,6 +7751,7 @@ BTF_ID_FLAGS(func, scx_bpf_cpu_rq) #ifdef CONFIG_CGROUP_SCHED BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE) #endif +BTF_ID_FLAGS(func, scx_bpf_now) BTF_KFUNCS_END(scx_kfunc_ids_any) static const struct btf_kfunc_id_set scx_kfunc_set_any = { diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index b1675bb59fc4..4d022d17ac7d 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -57,15 +57,15 @@ static inline void init_sched_ext_class(void) {} #endif /* CONFIG_SCHED_CLASS_EXT */ #if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP) -void __scx_update_idle(struct rq *rq, bool idle); +void __scx_update_idle(struct rq *rq, bool idle, bool do_notify); -static inline void scx_update_idle(struct rq *rq, bool idle) +static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) { if (scx_enabled()) - __scx_update_idle(rq, idle); + __scx_update_idle(rq, idle, do_notify); } #else -static inline void scx_update_idle(struct rq *rq, bool idle) {} +static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {} #endif #ifdef CONFIG_CGROUP_SCHED diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3e9ca38512de..ce2e94ccad0c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -51,6 +52,8 @@ #include +#include + #include "sched.h" #include "stats.h" #include "autogroup.h" @@ -130,7 +133,7 @@ static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536; #endif #ifdef CONFIG_SYSCTL -static struct ctl_table sched_fair_sysctls[] = { +static const struct ctl_table sched_fair_sysctls[] = { #ifdef CONFIG_CFS_BANDWIDTH { .procname = "sched_cfs_bandwidth_slice_us", @@ -523,7 +526,7 @@ void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec); * Scheduling class tree data structure manipulation methods: */ -static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime) +static inline __maybe_unused u64 max_vruntime(u64 max_vruntime, u64 vruntime) { s64 delta = (s64)(vruntime - max_vruntime); if (delta > 0) @@ -532,7 +535,7 @@ static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime) return max_vruntime; } -static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) +static inline __maybe_unused u64 min_vruntime(u64 min_vruntime, u64 vruntime) { s64 delta = (s64)(vruntime - min_vruntime); if (delta < 0) @@ -689,21 +692,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) * * XXX could add max_slice to the augmented data to track this. */ -static s64 entity_lag(u64 avruntime, struct sched_entity *se) +static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) { s64 vlag, limit; - vlag = avruntime - se->vruntime; - limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); - - return clamp(vlag, -limit, limit); -} - -static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ SCHED_WARN_ON(!se->on_rq); - se->vlag = entity_lag(avg_vruntime(cfs_rq), se); + vlag = avg_vruntime(cfs_rq) - se->vruntime; + limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); + + se->vlag = clamp(vlag, -limit, limit); } /* @@ -915,7 +913,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) * We can safely skip eligibility check if there is only one entity * in this cfs_rq, saving some cycles. */ - if (cfs_rq->nr_running == 1) + if (cfs_rq->nr_queued == 1) return curr && curr->on_rq ? curr : se; if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr))) @@ -1250,7 +1248,7 @@ static void update_curr(struct cfs_rq *cfs_rq) account_cfs_rq_runtime(cfs_rq, delta_exec); - if (cfs_rq->nr_running == 1) + if (cfs_rq->nr_queued == 1) return; if (resched || did_preempt_short(cfs_rq, curr)) { @@ -2131,7 +2129,7 @@ static void update_numa_stats(struct task_numa_env *env, ns->load += cpu_load(rq); ns->runnable += cpu_runnable(rq); ns->util += cpu_util_cfs(cpu); - ns->nr_running += rq->cfs.h_nr_running; + ns->nr_running += rq->cfs.h_nr_runnable; ns->compute_capacity += capacity_of(cpu); if (find_idle && idle_core < 0 && !rq->nr_running && idle_cpu(cpu)) { @@ -3682,9 +3680,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) list_add(&se->group_node, &rq->cfs_tasks); } #endif - cfs_rq->nr_running++; - if (se_is_idle(se)) - cfs_rq->idle_nr_running++; + cfs_rq->nr_queued++; } static void @@ -3697,9 +3693,7 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) list_del_init(&se->group_node); } #endif - cfs_rq->nr_running--; - if (se_is_idle(se)) - cfs_rq->idle_nr_running--; + cfs_rq->nr_queued--; } /* @@ -3774,137 +3768,32 @@ static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } #endif -static void reweight_eevdf(struct sched_entity *se, u64 avruntime, - unsigned long weight) -{ - unsigned long old_weight = se->load.weight; - s64 vlag, vslice; - - /* - * VRUNTIME - * -------- - * - * COROLLARY #1: The virtual runtime of the entity needs to be - * adjusted if re-weight at !0-lag point. - * - * Proof: For contradiction assume this is not true, so we can - * re-weight without changing vruntime at !0-lag point. - * - * Weight VRuntime Avg-VRuntime - * before w v V - * after w' v' V' - * - * Since lag needs to be preserved through re-weight: - * - * lag = (V - v)*w = (V'- v')*w', where v = v' - * ==> V' = (V - v)*w/w' + v (1) - * - * Let W be the total weight of the entities before reweight, - * since V' is the new weighted average of entities: - * - * V' = (WV + w'v - wv) / (W + w' - w) (2) - * - * by using (1) & (2) we obtain: - * - * (WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v - * ==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v - * ==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v - * ==> (V - v)*W/(W + w' - w) = (V - v)*w/w' (3) - * - * Since we are doing at !0-lag point which means V != v, we - * can simplify (3): - * - * ==> W / (W + w' - w) = w / w' - * ==> Ww' = Ww + ww' - ww - * ==> W * (w' - w) = w * (w' - w) - * ==> W = w (re-weight indicates w' != w) - * - * So the cfs_rq contains only one entity, hence vruntime of - * the entity @v should always equal to the cfs_rq's weighted - * average vruntime @V, which means we will always re-weight - * at 0-lag point, thus breach assumption. Proof completed. - * - * - * COROLLARY #2: Re-weight does NOT affect weighted average - * vruntime of all the entities. - * - * Proof: According to corollary #1, Eq. (1) should be: - * - * (V - v)*w = (V' - v')*w' - * ==> v' = V' - (V - v)*w/w' (4) - * - * According to the weighted average formula, we have: - * - * V' = (WV - wv + w'v') / (W - w + w') - * = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w') - * = (WV - wv + w'V' - Vw + wv) / (W - w + w') - * = (WV + w'V' - Vw) / (W - w + w') - * - * ==> V'*(W - w + w') = WV + w'V' - Vw - * ==> V' * (W - w) = (W - w) * V (5) - * - * If the entity is the only one in the cfs_rq, then reweight - * always occurs at 0-lag point, so V won't change. Or else - * there are other entities, hence W != w, then Eq. (5) turns - * into V' = V. So V won't change in either case, proof done. - * - * - * So according to corollary #1 & #2, the effect of re-weight - * on vruntime should be: - * - * v' = V' - (V - v) * w / w' (4) - * = V - (V - v) * w / w' - * = V - vl * w / w' - * = V - vl' - */ - if (avruntime != se->vruntime) { - vlag = entity_lag(avruntime, se); - vlag = div_s64(vlag * old_weight, weight); - se->vruntime = avruntime - vlag; - } - - /* - * DEADLINE - * -------- - * - * When the weight changes, the virtual time slope changes and - * we should adjust the relative virtual deadline accordingly. - * - * d' = v' + (d - v)*w/w' - * = V' - (V - v)*w/w' + (d - v)*w/w' - * = V - (V - v)*w/w' + (d - v)*w/w' - * = V + (d - V)*w/w' - */ - vslice = (s64)(se->deadline - avruntime); - vslice = div_s64(vslice * old_weight, weight); - se->deadline = avruntime + vslice; -} +static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags); static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { bool curr = cfs_rq->curr == se; - u64 avruntime; if (se->on_rq) { /* commit outstanding execution time */ update_curr(cfs_rq); - avruntime = avg_vruntime(cfs_rq); + update_entity_lag(cfs_rq, se); + se->deadline -= se->vruntime; + se->rel_deadline = 1; if (!curr) __dequeue_entity(cfs_rq, se); update_load_sub(&cfs_rq->load, se->load.weight); } dequeue_load_avg(cfs_rq, se); - if (se->on_rq) { - reweight_eevdf(se, avruntime, weight); - } else { - /* - * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i), - * we need to scale se->vlag when w_i changes. - */ - se->vlag = div_s64(se->vlag * se->load.weight, weight); - } + /* + * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i), + * we need to scale se->vlag when w_i changes. + */ + se->vlag = div_s64(se->vlag * se->load.weight, weight); + if (se->rel_deadline) + se->deadline = div_s64(se->deadline * se->load.weight, weight); update_load_set(&se->load, weight); @@ -3919,6 +3808,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, enqueue_load_avg(cfs_rq, se); if (se->on_rq) { update_load_add(&cfs_rq->load, se->load.weight); + place_entity(cfs_rq, se, 0); if (!curr) __enqueue_entity(cfs_rq, se); @@ -4065,7 +3955,11 @@ static void update_cfs_group(struct sched_entity *se) struct cfs_rq *gcfs_rq = group_cfs_rq(se); long shares; - if (!gcfs_rq) + /* + * When a group becomes empty, preserve its weight. This matters for + * DELAY_DEQUEUE. + */ + if (!gcfs_rq || !gcfs_rq->load.weight) return; if (throttled_hierarchy(gcfs_rq)) @@ -5233,7 +5127,7 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) { - return !cfs_rq->nr_running; + return !cfs_rq->nr_queued; } #define UPDATE_TG 0x0 @@ -5271,6 +5165,22 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {} #endif /* CONFIG_SMP */ +void __setparam_fair(struct task_struct *p, const struct sched_attr *attr) +{ + struct sched_entity *se = &p->se; + + p->static_prio = NICE_TO_PRIO(attr->sched_nice); + if (attr->sched_runtime) { + se->custom_slice = 1; + se->slice = clamp_t(u64, attr->sched_runtime, + NSEC_PER_MSEC/10, /* HZ=1000 * 10 */ + NSEC_PER_MSEC*100); /* HZ=100 / 10 */ + } else { + se->custom_slice = 0; + se->slice = sysctl_sched_base_slice; + } +} + static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { @@ -5289,7 +5199,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * * EEVDF: placement strategy #1 / #2 */ - if (sched_feat(PLACE_LAG) && cfs_rq->nr_running && se->vlag) { + if (sched_feat(PLACE_LAG) && cfs_rq->nr_queued && se->vlag) { struct sched_entity *curr = cfs_rq->curr; unsigned long load; @@ -5359,7 +5269,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) se->vruntime = vruntime - lag; - if (sched_feat(PLACE_REL_DEADLINE) && se->rel_deadline) { + if (se->rel_deadline) { se->deadline += se->vruntime; se->rel_deadline = 0; return; @@ -5382,8 +5292,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) static void check_enqueue_throttle(struct cfs_rq *cfs_rq); static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq); -static inline bool cfs_bandwidth_used(void); - static void requeue_delayed_entity(struct sched_entity *se); @@ -5405,7 +5313,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * When enqueuing a sched_entity, we must: * - Update loads to have both entity and cfs_rq synced with now. * - For group_entity, update its runnable_weight to reflect the new - * h_nr_running of its group cfs_rq. + * h_nr_runnable of its group cfs_rq. * - For group_entity, update its weight to reflect the new share of * its group cfs_rq * - Add its new weight to cfs_rq->load.weight @@ -5438,7 +5346,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) __enqueue_entity(cfs_rq, se); se->on_rq = 1; - if (cfs_rq->nr_running == 1) { + if (cfs_rq->nr_queued == 1) { check_enqueue_throttle(cfs_rq); if (!throttled_hierarchy(cfs_rq)) { list_add_leaf_cfs_rq(cfs_rq); @@ -5480,7 +5388,7 @@ static void set_delayed(struct sched_entity *se) for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - cfs_rq->h_nr_delayed++; + cfs_rq->h_nr_runnable--; if (cfs_rq_throttled(cfs_rq)) break; } @@ -5492,7 +5400,7 @@ static void clear_delayed(struct sched_entity *se) for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - cfs_rq->h_nr_delayed--; + cfs_rq->h_nr_runnable++; if (cfs_rq_throttled(cfs_rq)) break; } @@ -5509,6 +5417,7 @@ static bool dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { bool sleep = flags & DEQUEUE_SLEEP; + int action = UPDATE_TG; update_curr(cfs_rq); clear_buddies(cfs_rq, se); @@ -5534,7 +5443,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) } } - int action = UPDATE_TG; if (entity_is_task(se) && task_on_rq_migrating(task_of(se))) action |= DO_DETACH; @@ -5542,7 +5450,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * When dequeuing a sched_entity, we must: * - Update loads to have both entity and cfs_rq synced with now. * - For group_entity, update its runnable_weight to reflect the new - * h_nr_running of its group cfs_rq. + * h_nr_runnable of its group cfs_rq. * - Subtract its previous weight from cfs_rq->load.weight. * - For group entity, update its weight to reflect the new share * of its group cfs_rq. @@ -5580,7 +5488,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (flags & DEQUEUE_DELAYED) finish_delayed_dequeue_entity(se); - if (cfs_rq->nr_running == 0) + if (cfs_rq->nr_queued == 0) update_idle_cfs_rq_clock_pelt(cfs_rq); return true; @@ -5642,17 +5550,19 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags); static struct sched_entity * pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq) { + struct sched_entity *se; + /* - * Enabling NEXT_BUDDY will affect latency but not fairness. + * Picking the ->next buddy will affect latency but not fairness. */ - if (sched_feat(NEXT_BUDDY) && + if (sched_feat(PICK_BUDDY) && cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next)) { /* ->next will never be delayed */ SCHED_WARN_ON(cfs_rq->next->sched_delayed); return cfs_rq->next; } - struct sched_entity *se = pick_eevdf(cfs_rq); + se = pick_eevdf(cfs_rq); if (se->sched_delayed) { dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED); /* @@ -5928,7 +5838,7 @@ static int tg_throttle_down(struct task_group *tg, void *data) list_del_leaf_cfs_rq(cfs_rq); SCHED_WARN_ON(cfs_rq->throttled_clock_self); - if (cfs_rq->nr_running) + if (cfs_rq->nr_queued) cfs_rq->throttled_clock_self = rq_clock(rq); } cfs_rq->throttle_count++; @@ -5941,8 +5851,8 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, idle_task_delta, delayed_delta, dequeue = 1; - long rq_h_nr_running = rq->cfs.h_nr_running; + long queued_delta, runnable_delta, idle_delta, dequeue = 1; + long rq_h_nr_queued = rq->cfs.h_nr_queued; raw_spin_lock(&cfs_b->lock); /* This will start the period timer if necessary */ @@ -5972,9 +5882,9 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq); rcu_read_unlock(); - task_delta = cfs_rq->h_nr_running; - idle_task_delta = cfs_rq->idle_h_nr_running; - delayed_delta = cfs_rq->h_nr_delayed; + queued_delta = cfs_rq->h_nr_queued; + runnable_delta = cfs_rq->h_nr_runnable; + idle_delta = cfs_rq->h_nr_idle; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); int flags; @@ -5994,11 +5904,11 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) dequeue_entity(qcfs_rq, se, flags); if (cfs_rq_is_idle(group_cfs_rq(se))) - idle_task_delta = cfs_rq->h_nr_running; + idle_delta = cfs_rq->h_nr_queued; - qcfs_rq->h_nr_running -= task_delta; - qcfs_rq->idle_h_nr_running -= idle_task_delta; - qcfs_rq->h_nr_delayed -= delayed_delta; + qcfs_rq->h_nr_queued -= queued_delta; + qcfs_rq->h_nr_runnable -= runnable_delta; + qcfs_rq->h_nr_idle -= idle_delta; if (qcfs_rq->load.weight) { /* Avoid re-evaluating load for this entity: */ @@ -6017,18 +5927,18 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) se_update_runnable(se); if (cfs_rq_is_idle(group_cfs_rq(se))) - idle_task_delta = cfs_rq->h_nr_running; + idle_delta = cfs_rq->h_nr_queued; - qcfs_rq->h_nr_running -= task_delta; - qcfs_rq->idle_h_nr_running -= idle_task_delta; - qcfs_rq->h_nr_delayed -= delayed_delta; + qcfs_rq->h_nr_queued -= queued_delta; + qcfs_rq->h_nr_runnable -= runnable_delta; + qcfs_rq->h_nr_idle -= idle_delta; } /* At this point se is NULL and we are at root level*/ - sub_nr_running(rq, task_delta); + sub_nr_running(rq, queued_delta); /* Stop the fair server if throttling resulted in no runnable tasks */ - if (rq_h_nr_running && !rq->cfs.h_nr_running) + if (rq_h_nr_queued && !rq->cfs.h_nr_queued) dl_server_stop(&rq->fair_server); done: /* @@ -6037,7 +5947,7 @@ done: */ cfs_rq->throttled = 1; SCHED_WARN_ON(cfs_rq->throttled_clock); - if (cfs_rq->nr_running) + if (cfs_rq->nr_queued) cfs_rq->throttled_clock = rq_clock(rq); return true; } @@ -6047,8 +5957,8 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, idle_task_delta, delayed_delta; - long rq_h_nr_running = rq->cfs.h_nr_running; + long queued_delta, runnable_delta, idle_delta; + long rq_h_nr_queued = rq->cfs.h_nr_queued; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -6081,9 +5991,9 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) goto unthrottle_throttle; } - task_delta = cfs_rq->h_nr_running; - idle_task_delta = cfs_rq->idle_h_nr_running; - delayed_delta = cfs_rq->h_nr_delayed; + queued_delta = cfs_rq->h_nr_queued; + runnable_delta = cfs_rq->h_nr_runnable; + idle_delta = cfs_rq->h_nr_idle; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); @@ -6097,11 +6007,11 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) enqueue_entity(qcfs_rq, se, ENQUEUE_WAKEUP); if (cfs_rq_is_idle(group_cfs_rq(se))) - idle_task_delta = cfs_rq->h_nr_running; + idle_delta = cfs_rq->h_nr_queued; - qcfs_rq->h_nr_running += task_delta; - qcfs_rq->idle_h_nr_running += idle_task_delta; - qcfs_rq->h_nr_delayed += delayed_delta; + qcfs_rq->h_nr_queued += queued_delta; + qcfs_rq->h_nr_runnable += runnable_delta; + qcfs_rq->h_nr_idle += idle_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6115,11 +6025,11 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) se_update_runnable(se); if (cfs_rq_is_idle(group_cfs_rq(se))) - idle_task_delta = cfs_rq->h_nr_running; + idle_delta = cfs_rq->h_nr_queued; - qcfs_rq->h_nr_running += task_delta; - qcfs_rq->idle_h_nr_running += idle_task_delta; - qcfs_rq->h_nr_delayed += delayed_delta; + qcfs_rq->h_nr_queued += queued_delta; + qcfs_rq->h_nr_runnable += runnable_delta; + qcfs_rq->h_nr_idle += idle_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6127,17 +6037,17 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) } /* Start the fair server if un-throttling resulted in new runnable tasks */ - if (!rq_h_nr_running && rq->cfs.h_nr_running) + if (!rq_h_nr_queued && rq->cfs.h_nr_queued) dl_server_start(&rq->fair_server); /* At this point se is NULL and we are at root level*/ - add_nr_running(rq, task_delta); + add_nr_running(rq, queued_delta); unthrottle_throttle: assert_list_leaf_cfs_rq(rq); /* Determine whether we need to wake up potentially idle CPU: */ - if (rq->curr == rq->idle && rq->cfs.nr_running) + if (rq->curr == rq->idle && rq->cfs.nr_queued) resched_curr(rq); } @@ -6438,7 +6348,7 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) if (!cfs_bandwidth_used()) return; - if (!cfs_rq->runtime_enabled || cfs_rq->nr_running) + if (!cfs_rq->runtime_enabled || cfs_rq->nr_queued) return; __return_cfs_rq_runtime(cfs_rq); @@ -6709,6 +6619,10 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) lockdep_assert_rq_held(rq); + // Do not unthrottle for an active CPU + if (cpumask_test_cpu(cpu_of(rq), cpu_active_mask)) + return; + /* * The rq clock has already been updated in the * set_rq_offline(), so we should skip updating @@ -6723,19 +6637,21 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) if (!cfs_rq->runtime_enabled) continue; - /* - * clock_task is not advancing so we just need to make sure - * there's some valid quota amount - */ - cfs_rq->runtime_remaining = 1; /* * Offline rq is schedulable till CPU is completely disabled * in take_cpu_down(), so we prevent new cfs throttling here. */ cfs_rq->runtime_enabled = 0; - if (cfs_rq_throttled(cfs_rq)) - unthrottle_cfs_rq(cfs_rq); + if (!cfs_rq_throttled(cfs_rq)) + continue; + + /* + * clock_task is not advancing so we just need to make sure + * there's some valid quota amount + */ + cfs_rq->runtime_remaining = 1; + unthrottle_cfs_rq(cfs_rq); } rcu_read_unlock(); @@ -6784,11 +6700,6 @@ static void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p) #else /* CONFIG_CFS_BANDWIDTH */ -static inline bool cfs_bandwidth_used(void) -{ - return false; -} - static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; } static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} @@ -6846,7 +6757,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) SCHED_WARN_ON(task_rq(p) != rq); - if (rq->cfs.h_nr_running > 1) { + if (rq->cfs.h_nr_queued > 1) { u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime; u64 slice = se->slice; s64 delta = slice - ran; @@ -6934,7 +6845,7 @@ static inline void check_update_overutilized_status(struct rq *rq) { } /* Runqueue only has SCHED_IDLE tasks enqueued */ static int sched_idle_rq(struct rq *rq) { - return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running && + return unlikely(rq->nr_running == rq->cfs.h_nr_idle && rq->nr_running); } @@ -6961,14 +6872,14 @@ requeue_delayed_entity(struct sched_entity *se) if (sched_feat(DELAY_ZERO)) { update_entity_lag(cfs_rq, se); if (se->vlag > 0) { - cfs_rq->nr_running--; + cfs_rq->nr_queued--; if (se != cfs_rq->curr) __dequeue_entity(cfs_rq, se); se->vlag = 0; place_entity(cfs_rq, se, 0); if (se != cfs_rq->curr) __enqueue_entity(cfs_rq, se); - cfs_rq->nr_running++; + cfs_rq->nr_queued++; } } @@ -6986,10 +6897,10 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; - int idle_h_nr_running = task_has_idle_policy(p); - int h_nr_delayed = 0; + int h_nr_idle = task_has_idle_policy(p); + int h_nr_runnable = 1; int task_new = !(flags & ENQUEUE_WAKEUP); - int rq_h_nr_running = rq->cfs.h_nr_running; + int rq_h_nr_queued = rq->cfs.h_nr_queued; u64 slice = 0; /* @@ -7014,8 +6925,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (p->in_iowait) cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT); - if (task_new) - h_nr_delayed = !!se->sched_delayed; + if (task_new && se->sched_delayed) + h_nr_runnable = 0; for_each_sched_entity(se) { if (se->on_rq) { @@ -7037,12 +6948,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) enqueue_entity(cfs_rq, se, flags); slice = cfs_rq_min_slice(cfs_rq); - cfs_rq->h_nr_running++; - cfs_rq->idle_h_nr_running += idle_h_nr_running; - cfs_rq->h_nr_delayed += h_nr_delayed; + cfs_rq->h_nr_runnable += h_nr_runnable; + cfs_rq->h_nr_queued++; + cfs_rq->h_nr_idle += h_nr_idle; if (cfs_rq_is_idle(cfs_rq)) - idle_h_nr_running = 1; + h_nr_idle = 1; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) @@ -7061,19 +6972,19 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) se->slice = slice; slice = cfs_rq_min_slice(cfs_rq); - cfs_rq->h_nr_running++; - cfs_rq->idle_h_nr_running += idle_h_nr_running; - cfs_rq->h_nr_delayed += h_nr_delayed; + cfs_rq->h_nr_runnable += h_nr_runnable; + cfs_rq->h_nr_queued++; + cfs_rq->h_nr_idle += h_nr_idle; if (cfs_rq_is_idle(cfs_rq)) - idle_h_nr_running = 1; + h_nr_idle = 1; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) goto enqueue_throttle; } - if (!rq_h_nr_running && rq->cfs.h_nr_running) { + if (!rq_h_nr_queued && rq->cfs.h_nr_queued) { /* Account for idle runtime */ if (!rq->nr_running) dl_server_update_idle_time(rq, rq->curr); @@ -7120,22 +7031,22 @@ static void set_next_buddy(struct sched_entity *se); static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) { bool was_sched_idle = sched_idle_rq(rq); - int rq_h_nr_running = rq->cfs.h_nr_running; + int rq_h_nr_queued = rq->cfs.h_nr_queued; bool task_sleep = flags & DEQUEUE_SLEEP; bool task_delayed = flags & DEQUEUE_DELAYED; struct task_struct *p = NULL; - int idle_h_nr_running = 0; - int h_nr_running = 0; - int h_nr_delayed = 0; + int h_nr_idle = 0; + int h_nr_queued = 0; + int h_nr_runnable = 0; struct cfs_rq *cfs_rq; u64 slice = 0; if (entity_is_task(se)) { p = task_of(se); - h_nr_running = 1; - idle_h_nr_running = task_has_idle_policy(p); - if (!task_sleep && !task_delayed) - h_nr_delayed = !!se->sched_delayed; + h_nr_queued = 1; + h_nr_idle = task_has_idle_policy(p); + if (task_sleep || task_delayed || !se->sched_delayed) + h_nr_runnable = 1; } else { cfs_rq = group_cfs_rq(se); slice = cfs_rq_min_slice(cfs_rq); @@ -7151,12 +7062,12 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) break; } - cfs_rq->h_nr_running -= h_nr_running; - cfs_rq->idle_h_nr_running -= idle_h_nr_running; - cfs_rq->h_nr_delayed -= h_nr_delayed; + cfs_rq->h_nr_runnable -= h_nr_runnable; + cfs_rq->h_nr_queued -= h_nr_queued; + cfs_rq->h_nr_idle -= h_nr_idle; if (cfs_rq_is_idle(cfs_rq)) - idle_h_nr_running = h_nr_running; + h_nr_idle = h_nr_queued; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) @@ -7190,21 +7101,21 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) se->slice = slice; slice = cfs_rq_min_slice(cfs_rq); - cfs_rq->h_nr_running -= h_nr_running; - cfs_rq->idle_h_nr_running -= idle_h_nr_running; - cfs_rq->h_nr_delayed -= h_nr_delayed; + cfs_rq->h_nr_runnable -= h_nr_runnable; + cfs_rq->h_nr_queued -= h_nr_queued; + cfs_rq->h_nr_idle -= h_nr_idle; if (cfs_rq_is_idle(cfs_rq)) - idle_h_nr_running = h_nr_running; + h_nr_idle = h_nr_queued; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) return 0; } - sub_nr_running(rq, h_nr_running); + sub_nr_running(rq, h_nr_queued); - if (rq_h_nr_running && !rq->cfs.h_nr_running) + if (rq_h_nr_queued && !rq->cfs.h_nr_queued) dl_server_stop(&rq->fair_server); /* balance early to pull high priority tasks */ @@ -8893,7 +8804,7 @@ static struct task_struct *pick_task_fair(struct rq *rq) again: cfs_rq = &rq->cfs; - if (!cfs_rq->nr_running) + if (!cfs_rq->nr_queued) return NULL; do { @@ -9010,7 +8921,7 @@ static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_stru static bool fair_server_has_tasks(struct sched_dl_entity *dl_se) { - return !!dl_se->rq->cfs.nr_running; + return !!dl_se->rq->cfs.nr_queued; } static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se) @@ -9341,43 +9252,43 @@ static int task_hot(struct task_struct *p, struct lb_env *env) #ifdef CONFIG_NUMA_BALANCING /* - * Returns 1, if task migration degrades locality - * Returns 0, if task migration improves locality i.e migration preferred. - * Returns -1, if task migration is not affected by locality. + * Returns a positive value, if task migration degrades locality. + * Returns 0, if task migration is not affected by locality. + * Returns a negative value, if task migration improves locality i.e migration preferred. */ -static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) +static long migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { struct numa_group *numa_group = rcu_dereference(p->numa_group); unsigned long src_weight, dst_weight; int src_nid, dst_nid, dist; if (!static_branch_likely(&sched_numa_balancing)) - return -1; + return 0; if (!p->numa_faults || !(env->sd->flags & SD_NUMA)) - return -1; + return 0; src_nid = cpu_to_node(env->src_cpu); dst_nid = cpu_to_node(env->dst_cpu); if (src_nid == dst_nid) - return -1; + return 0; /* Migrating away from the preferred node is always bad. */ if (src_nid == p->numa_preferred_nid) { if (env->src_rq->nr_running > env->src_rq->nr_preferred_running) return 1; else - return -1; + return 0; } /* Encourage migration to the preferred node. */ if (dst_nid == p->numa_preferred_nid) - return 0; + return -1; /* Leaving a core idle is often worse than degrading locality. */ if (env->idle == CPU_IDLE) - return -1; + return 0; dist = node_distance(src_nid, dst_nid); if (numa_group) { @@ -9388,37 +9299,77 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) dst_weight = task_weight(p, dst_nid, dist); } - return dst_weight < src_weight; + return src_weight - dst_weight; } #else -static inline int migrate_degrades_locality(struct task_struct *p, +static inline long migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { - return -1; + return 0; } #endif +/* + * Check whether the task is ineligible on the destination cpu + * + * When the PLACE_LAG scheduling feature is enabled and + * dst_cfs_rq->nr_queued is greater than 1, if the task + * is ineligible, it will also be ineligible when + * it is migrated to the destination cpu. + */ +static inline int task_is_ineligible_on_dst_cpu(struct task_struct *p, int dest_cpu) +{ + struct cfs_rq *dst_cfs_rq; + +#ifdef CONFIG_FAIR_GROUP_SCHED + dst_cfs_rq = task_group(p)->cfs_rq[dest_cpu]; +#else + dst_cfs_rq = &cpu_rq(dest_cpu)->cfs; +#endif + if (sched_feat(PLACE_LAG) && dst_cfs_rq->nr_queued && + !entity_eligible(task_cfs_rq(p), &p->se)) + return 1; + + return 0; +} + /* * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? */ static int can_migrate_task(struct task_struct *p, struct lb_env *env) { - int tsk_cache_hot; + long degrades, hot; lockdep_assert_rq_held(env->src_rq); + if (p->sched_task_hot) + p->sched_task_hot = 0; /* * We do not migrate tasks that are: - * 1) throttled_lb_pair, or - * 2) cannot be migrated to this CPU due to cpus_ptr, or - * 3) running (obviously), or - * 4) are cache-hot on their current CPU. + * 1) delayed dequeued unless we migrate load, or + * 2) throttled_lb_pair, or + * 3) cannot be migrated to this CPU due to cpus_ptr, or + * 4) running (obviously), or + * 5) are cache-hot on their current CPU. */ + if ((p->se.sched_delayed) && (env->migration_type != migrate_load)) + return 0; + if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) return 0; + /* + * We want to prioritize the migration of eligible tasks. + * For ineligible tasks we soft-limit them and only allow + * them to migrate when nr_balance_failed is non-zero to + * avoid load-balancing trying very hard to balance the load. + */ + if (!env->sd->nr_balance_failed && + task_is_ineligible_on_dst_cpu(p, env->dst_cpu)) + return 0; + /* Disregard percpu kthreads; they are where they need to be. */ if (kthread_is_per_cpu(p)) return 0; @@ -9474,16 +9425,15 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (env->flags & LBF_ACTIVE_LB) return 1; - tsk_cache_hot = migrate_degrades_locality(p, env); - if (tsk_cache_hot == -1) - tsk_cache_hot = task_hot(p, env); + degrades = migrate_degrades_locality(p, env); + if (!degrades) + hot = task_hot(p, env); + else + hot = degrades > 0; - if (tsk_cache_hot <= 0 || - env->sd->nr_balance_failed > env->sd->cache_nice_tries) { - if (tsk_cache_hot == 1) { - schedstat_inc(env->sd->lb_hot_gained[env->idle]); - schedstat_inc(p->stats.nr_forced_migrations); - } + if (!hot || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { + if (hot) + p->sched_task_hot = 1; return 1; } @@ -9498,6 +9448,12 @@ static void detach_task(struct task_struct *p, struct lb_env *env) { lockdep_assert_rq_held(env->src_rq); + if (p->sched_task_hot) { + p->sched_task_hot = 0; + schedstat_inc(env->sd->lb_hot_gained[env->idle]); + schedstat_inc(p->stats.nr_forced_migrations); + } + deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK); set_task_cpu(p, env->dst_cpu); } @@ -9658,6 +9614,9 @@ static int detach_tasks(struct lb_env *env) continue; next: + if (p->sched_task_hot) + schedstat_inc(p->stats.nr_failed_migrations_hot); + list_move(&p->se.group_node, tasks); } @@ -9800,7 +9759,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) { update_tg_load_avg(cfs_rq); - if (cfs_rq->nr_running == 0) + if (cfs_rq->nr_queued == 0) update_idle_cfs_rq_clock_pelt(cfs_rq); if (cfs_rq == &rq->cfs) @@ -10332,7 +10291,7 @@ sched_reduced_capacity(struct rq *rq, struct sched_domain *sd) * When there is more than 1 task, the group_overloaded case already * takes care of cpu with reduced capacity */ - if (rq->cfs.h_nr_running != 1) + if (rq->cfs.h_nr_runnable != 1) return false; return check_cpu_capacity(rq, sd); @@ -10354,7 +10313,8 @@ static inline void update_sg_lb_stats(struct lb_env *env, bool *sg_overloaded, bool *sg_overutilized) { - int i, nr_running, local_group; + int i, nr_running, local_group, sd_flags = env->sd->flags; + bool balancing_at_rd = !env->sd->parent; memset(sgs, 0, sizeof(*sgs)); @@ -10367,21 +10327,14 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_load += load; sgs->group_util += cpu_util_cfs(i); sgs->group_runnable += cpu_runnable(rq); - sgs->sum_h_nr_running += rq->cfs.h_nr_running; + sgs->sum_h_nr_running += rq->cfs.h_nr_runnable; nr_running = rq->nr_running; sgs->sum_nr_running += nr_running; - if (nr_running > 1) - *sg_overloaded = 1; - if (cpu_overutilized(i)) *sg_overutilized = 1; -#ifdef CONFIG_NUMA_BALANCING - sgs->nr_numa_running += rq->nr_numa_running; - sgs->nr_preferred_running += rq->nr_preferred_running; -#endif /* * No need to call idle_cpu() if nr_running is not 0 */ @@ -10391,10 +10344,21 @@ static inline void update_sg_lb_stats(struct lb_env *env, continue; } + /* Overload indicator is only updated at root domain */ + if (balancing_at_rd && nr_running > 1) + *sg_overloaded = 1; + +#ifdef CONFIG_NUMA_BALANCING + /* Only fbq_classify_group() uses this to classify NUMA groups */ + if (sd_flags & SD_NUMA) { + sgs->nr_numa_running += rq->nr_numa_running; + sgs->nr_preferred_running += rq->nr_preferred_running; + } +#endif if (local_group) continue; - if (env->sd->flags & SD_ASYM_CPUCAPACITY) { + if (sd_flags & SD_ASYM_CPUCAPACITY) { /* Check for a misfit task on the cpu */ if (sgs->group_misfit_task_load < rq->misfit_task_load) { sgs->group_misfit_task_load = rq->misfit_task_load; @@ -10682,7 +10646,7 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd, sgs->group_util += cpu_util_without(i, p); sgs->group_runnable += cpu_runnable_without(rq, p); local = task_running_on_cpu(i, p); - sgs->sum_h_nr_running += rq->cfs.h_nr_running - local; + sgs->sum_h_nr_running += rq->cfs.h_nr_runnable - local; nr_running = rq->nr_running - local; sgs->sum_nr_running += nr_running; @@ -11464,7 +11428,7 @@ static struct rq *sched_balance_find_src_rq(struct lb_env *env, if (rt > env->fbq_type) continue; - nr_running = rq->cfs.h_nr_running; + nr_running = rq->cfs.h_nr_runnable; if (!nr_running) continue; @@ -11623,7 +11587,7 @@ static int need_active_balance(struct lb_env *env) * available on dst_cpu. */ if (env->idle && - (env->src_rq->cfs.h_nr_running == 1)) { + (env->src_rq->cfs.h_nr_runnable == 1)) { if ((check_cpu_capacity(env->src_rq, sd)) && (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100)) return 1; @@ -11703,6 +11667,28 @@ static int should_we_balance(struct lb_env *env) return group_balance_cpu(sg) == env->dst_cpu; } +static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd, + enum cpu_idle_type idle) +{ + if (!schedstat_enabled()) + return; + + switch (env->migration_type) { + case migrate_load: + __schedstat_add(sd->lb_imbalance_load[idle], env->imbalance); + break; + case migrate_util: + __schedstat_add(sd->lb_imbalance_util[idle], env->imbalance); + break; + case migrate_task: + __schedstat_add(sd->lb_imbalance_task[idle], env->imbalance); + break; + case migrate_misfit: + __schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance); + break; + } +} + /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. @@ -11753,7 +11739,7 @@ redo: WARN_ON_ONCE(busiest == env.dst_rq); - schedstat_add(sd->lb_imbalance[idle], env.imbalance); + update_lb_imbalance_stat(&env, sd, idle); env.src_cpu = busiest->cpu; env.src_rq = busiest; @@ -12251,16 +12237,13 @@ static inline int on_null_domain(struct rq *rq) * - When one of the busy CPUs notices that there may be an idle rebalancing * needed, they will kick the idle load balancer, which then does idle * load balancing for all the idle CPUs. - * - * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED is not set - * anywhere yet. */ static inline int find_new_ilb(void) { const struct cpumask *hk_mask; int ilb_cpu; - hk_mask = housekeeping_cpumask(HK_TYPE_MISC); + hk_mask = housekeeping_cpumask(HK_TYPE_KERNEL_NOISE); for_each_cpu_and(ilb_cpu, nohz.idle_cpus_mask, hk_mask) { @@ -12278,7 +12261,8 @@ static inline int find_new_ilb(void) * Kick a CPU to do the NOHZ balancing, if it is time for it, via a cross-CPU * SMP function call (IPI). * - * We pick the first idle CPU in the HK_TYPE_MISC housekeeping set (if there is one). + * We pick the first idle CPU in the HK_TYPE_KERNEL_NOISE housekeeping set + * (if there is one). */ static void kick_ilb(unsigned int flags) { @@ -12366,7 +12350,7 @@ static void nohz_balancer_kick(struct rq *rq) * If there's a runnable CFS task and the current CPU has reduced * capacity, kick the ILB to see if there's a better CPU to run on: */ - if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) { + if (rq->cfs.h_nr_runnable >= 1 && check_cpu_capacity(rq, sd)) { flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; goto unlock; } @@ -12498,10 +12482,6 @@ void nohz_balance_enter_idle(int cpu) if (!cpu_active(cpu)) return; - /* Spare idle load balancing on CPUs that don't want to be disturbed: */ - if (!housekeeping_cpu(cpu, HK_TYPE_SCHED)) - return; - /* * Can be set safely without rq->lock held * If a clear happens, it will have evaluated last additions because @@ -12721,13 +12701,6 @@ static void nohz_newidle_balance(struct rq *this_rq) { int this_cpu = this_rq->cpu; - /* - * This CPU doesn't want to be disturbed by scheduler - * housekeeping - */ - if (!housekeeping_cpu(this_cpu, HK_TYPE_SCHED)) - return; - /* Will wake up very soon. No time for doing anything else*/ if (this_rq->avg_idle < sysctl_sched_migration_cost) return; @@ -12864,11 +12837,11 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) * have been enqueued in the meantime. Since we're not going idle, * pretend we pulled a task. */ - if (this_rq->cfs.h_nr_running && !pulled_task) + if (this_rq->cfs.h_nr_queued && !pulled_task) pulled_task = 1; /* Is there a task of a high priority class? */ - if (this_rq->nr_running != this_rq->cfs.h_nr_running) + if (this_rq->nr_running != this_rq->cfs.h_nr_queued) pulled_task = -1; out: @@ -12889,9 +12862,9 @@ out: /* * This softirq handler is triggered via SCHED_SOFTIRQ from two places: * - * - directly from the local scheduler_tick() for periodic load balancing + * - directly from the local sched_tick() for periodic load balancing * - * - indirectly from a remote scheduler_tick() for NOHZ idle balancing + * - indirectly from a remote sched_tick() for NOHZ idle balancing * through the SMP cross-call nohz_csd_func() */ static __latent_entropy void sched_balance_softirq(void) @@ -12982,7 +12955,7 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) * MIN_NR_TASKS_DURING_FORCEIDLE - 1 tasks and use that to check * if we need to give up the CPU. */ - if (rq->core->core_forceidle_count && rq->cfs.nr_running == 1 && + if (rq->core->core_forceidle_count && rq->cfs.nr_queued == 1 && __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE)) resched_curr(rq); } @@ -13126,7 +13099,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) if (!task_on_rq_queued(p)) return; - if (rq->cfs.nr_running == 1) + if (rq->cfs.nr_queued == 1) return; /* @@ -13536,7 +13509,7 @@ int sched_group_set_idle(struct task_group *tg, long idle) for_each_possible_cpu(i) { struct rq *rq = cpu_rq(i); struct sched_entity *se = tg->se[i]; - struct cfs_rq *parent_cfs_rq, *grp_cfs_rq = tg->cfs_rq[i]; + struct cfs_rq *grp_cfs_rq = tg->cfs_rq[i]; bool was_idle = cfs_rq_is_idle(grp_cfs_rq); long idle_task_delta; struct rq_flags rf; @@ -13547,16 +13520,8 @@ int sched_group_set_idle(struct task_group *tg, long idle) if (WARN_ON_ONCE(was_idle == cfs_rq_is_idle(grp_cfs_rq))) goto next_cpu; - if (se->on_rq) { - parent_cfs_rq = cfs_rq_of(se); - if (cfs_rq_is_idle(grp_cfs_rq)) - parent_cfs_rq->idle_nr_running++; - else - parent_cfs_rq->idle_nr_running--; - } - - idle_task_delta = grp_cfs_rq->h_nr_running - - grp_cfs_rq->idle_h_nr_running; + idle_task_delta = grp_cfs_rq->h_nr_queued - + grp_cfs_rq->h_nr_idle; if (!cfs_rq_is_idle(grp_cfs_rq)) idle_task_delta *= -1; @@ -13566,7 +13531,7 @@ int sched_group_set_idle(struct task_group *tg, long idle) if (!se->on_rq) break; - cfs_rq->idle_h_nr_running += idle_task_delta; + cfs_rq->h_nr_idle += idle_task_delta; /* Already accounted at parent level and above. */ if (cfs_rq_is_idle(cfs_rq)) diff --git a/kernel/sched/features.h b/kernel/sched/features.h index a3d331dd2d8f..3c12d9f93331 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -31,6 +31,15 @@ SCHED_FEAT(PREEMPT_SHORT, true) */ SCHED_FEAT(NEXT_BUDDY, false) +/* + * Allow completely ignoring cfs_rq->next; which can be set from various + * places: + * - NEXT_BUDDY (wakeup preemption) + * - yield_to_task() + * - cgroup dequeue / pick + */ +SCHED_FEAT(PICK_BUDDY, true) + /* * Consider buddies to be cache hot, decreases the likeliness of a * cache buddy being migrated away, increases cache locality. diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 621696269584..2c85c86b455f 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -452,19 +452,20 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags) static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next) { dl_server_update_idle_time(rq, prev); - scx_update_idle(rq, false); + scx_update_idle(rq, false, true); } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) { update_idle_core(rq); - scx_update_idle(rq, true); + scx_update_idle(rq, true, true); schedstat_inc(rq->sched_goidle); next->se.exec_start = rq_clock_task(rq); } struct task_struct *pick_task_idle(struct rq *rq) { + scx_update_idle(rq, true, false); return rq->idle; } diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 5891e715f00d..81bc8b329ef1 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -9,15 +9,9 @@ */ enum hk_flags { - HK_FLAG_TIMER = BIT(HK_TYPE_TIMER), - HK_FLAG_RCU = BIT(HK_TYPE_RCU), - HK_FLAG_MISC = BIT(HK_TYPE_MISC), - HK_FLAG_SCHED = BIT(HK_TYPE_SCHED), - HK_FLAG_TICK = BIT(HK_TYPE_TICK), HK_FLAG_DOMAIN = BIT(HK_TYPE_DOMAIN), - HK_FLAG_WQ = BIT(HK_TYPE_WQ), HK_FLAG_MANAGED_IRQ = BIT(HK_TYPE_MANAGED_IRQ), - HK_FLAG_KTHREAD = BIT(HK_TYPE_KTHREAD), + HK_FLAG_KERNEL_NOISE = BIT(HK_TYPE_KERNEL_NOISE), }; DEFINE_STATIC_KEY_FALSE(housekeeping_overridden); @@ -97,7 +91,7 @@ void __init housekeeping_init(void) static_branch_enable(&housekeeping_overridden); - if (housekeeping.flags & HK_FLAG_TICK) + if (housekeeping.flags & HK_FLAG_KERNEL_NOISE) sched_tick_offload_init(); for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) { @@ -121,7 +115,7 @@ static int __init housekeeping_setup(char *str, unsigned long flags) unsigned int first_cpu; int err = 0; - if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) { + if ((flags & HK_FLAG_KERNEL_NOISE) && !(housekeeping.flags & HK_FLAG_KERNEL_NOISE)) { if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) { pr_warn("Housekeeping: nohz unsupported." " Build with CONFIG_NO_HZ_FULL\n"); @@ -177,7 +171,7 @@ static int __init housekeeping_setup(char *str, unsigned long flags) housekeeping_setup_type(type, housekeeping_staging); } - if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) + if ((flags & HK_FLAG_KERNEL_NOISE) && !(housekeeping.flags & HK_FLAG_KERNEL_NOISE)) tick_nohz_full_setup(non_housekeeping_mask); housekeeping.flags |= flags; @@ -195,8 +189,7 @@ static int __init housekeeping_nohz_full_setup(char *str) { unsigned long flags; - flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | - HK_FLAG_MISC | HK_FLAG_KTHREAD; + flags = HK_FLAG_KERNEL_NOISE; return housekeeping_setup(str, flags); } @@ -210,9 +203,12 @@ static int __init housekeeping_isolcpus_setup(char *str) int len; while (isalpha(*str)) { + /* + * isolcpus=nohz is equivalent to nohz_full. + */ if (!strncmp(str, "nohz,", 5)) { str += 5; - flags |= HK_FLAG_TICK; + flags |= HK_FLAG_KERNEL_NOISE; continue; } diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index fee75cc2c47b..7a8534a2deff 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -275,7 +275,7 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load) * * group: [ see update_cfs_group() ] * se_weight() = tg->weight * grq->load_avg / tg->load_avg - * se_runnable() = grq->h_nr_running + * se_runnable() = grq->h_nr_runnable * * runnable_sum = se_runnable() * runnable = grq->runnable_sum * runnable_avg = runnable_sum @@ -321,7 +321,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq) { if (___update_load_sum(now, &cfs_rq->avg, scale_load_down(cfs_rq->load.weight), - cfs_rq->h_nr_running - cfs_rq->h_nr_delayed, + cfs_rq->h_nr_runnable, cfs_rq->curr != NULL)) { ___update_load_avg(&cfs_rq->avg, 1); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 84dad1511d1e..bb56805e3d47 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -998,7 +998,7 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st s64 delta; u64 irq; - if (static_branch_likely(&psi_disabled)) + if (static_branch_likely(&psi_disabled) || !irqtime_enabled()) return; if (!curr->pid) @@ -1240,6 +1240,11 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + if (!irqtime_enabled() && res == PSI_IRQ) + return -EOPNOTSUPP; +#endif + /* Update averages before reporting them */ mutex_lock(&group->avgs_lock); now = sched_clock(); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index bd66a46b06ac..4b8e33c615b1 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -26,7 +26,7 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff size_t *lenp, loff_t *ppos); static int sched_rr_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -static struct ctl_table sched_rt_sysctls[] = { +static const struct ctl_table sched_rt_sysctls[] = { { .procname = "sched_rt_period_us", .data = &sysctl_sched_rt_period, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c5d67a43fe52..38e0e323dda2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -362,7 +362,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr); extern bool __checkparam_dl(const struct sched_attr *attr); extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int dl_bw_check_overflow(int cpu); +extern int dl_bw_deactivate(int cpu); extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec); /* * SCHED_DEADLINE supports servers (nested scheduling) with the following @@ -650,11 +650,10 @@ struct balance_callback { /* CFS-related fields in a runqueue */ struct cfs_rq { struct load_weight load; - unsigned int nr_running; - unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */ - unsigned int idle_nr_running; /* SCHED_IDLE */ - unsigned int idle_h_nr_running; /* SCHED_IDLE */ - unsigned int h_nr_delayed; + unsigned int nr_queued; + unsigned int h_nr_queued; /* SCHED_{NORMAL,BATCH,IDLE} */ + unsigned int h_nr_runnable; /* SCHED_{NORMAL,BATCH,IDLE} */ + unsigned int h_nr_idle; /* SCHED_IDLE */ s64 avg_vruntime; u64 avg_load; @@ -760,6 +759,7 @@ enum scx_rq_flags { SCX_RQ_BAL_PENDING = 1 << 2, /* balance hasn't run yet */ SCX_RQ_BAL_KEEP = 1 << 3, /* balance decided to keep current */ SCX_RQ_BYPASSING = 1 << 4, + SCX_RQ_CLK_VALID = 1 << 5, /* RQ clock is fresh and valid */ SCX_RQ_IN_WAKEUP = 1 << 16, SCX_RQ_IN_BALANCE = 1 << 17, @@ -772,9 +772,10 @@ struct scx_rq { unsigned long ops_qseq; u64 extra_enq_flags; /* see move_task_to_local_dsq() */ u32 nr_running; - u32 flags; u32 cpuperf_target; /* [0, SCHED_CAPACITY_SCALE] */ bool cpu_released; + u32 flags; + u64 clock; /* current per-rq clock -- see scx_bpf_now() */ cpumask_var_t cpus_to_kick; cpumask_var_t cpus_to_kick_if_idle; cpumask_var_t cpus_to_preempt; @@ -904,11 +905,8 @@ struct dl_rq { static inline void se_update_runnable(struct sched_entity *se) { - if (!entity_is_task(se)) { - struct cfs_rq *cfs_rq = se->my_q; - - se->runnable_weight = cfs_rq->h_nr_running - cfs_rq->h_nr_delayed; - } + if (!entity_is_task(se)) + se->runnable_weight = se->my_q->h_nr_runnable; } static inline long se_runnable(struct sched_entity *se) @@ -1726,6 +1724,38 @@ struct rq_flags { extern struct balance_callback balance_push_callback; +#ifdef CONFIG_SCHED_CLASS_EXT +extern const struct sched_class ext_sched_class; + +DECLARE_STATIC_KEY_FALSE(__scx_ops_enabled); /* SCX BPF scheduler loaded */ +DECLARE_STATIC_KEY_FALSE(__scx_switched_all); /* all fair class tasks on SCX */ + +#define scx_enabled() static_branch_unlikely(&__scx_ops_enabled) +#define scx_switched_all() static_branch_unlikely(&__scx_switched_all) + +static inline void scx_rq_clock_update(struct rq *rq, u64 clock) +{ + if (!scx_enabled()) + return; + WRITE_ONCE(rq->scx.clock, clock); + smp_store_release(&rq->scx.flags, rq->scx.flags | SCX_RQ_CLK_VALID); +} + +static inline void scx_rq_clock_invalidate(struct rq *rq) +{ + if (!scx_enabled()) + return; + WRITE_ONCE(rq->scx.flags, rq->scx.flags & ~SCX_RQ_CLK_VALID); +} + +#else /* !CONFIG_SCHED_CLASS_EXT */ +#define scx_enabled() false +#define scx_switched_all() false + +static inline void scx_rq_clock_update(struct rq *rq, u64 clock) {} +static inline void scx_rq_clock_invalidate(struct rq *rq) {} +#endif /* !CONFIG_SCHED_CLASS_EXT */ + /* * Lockdep annotation that avoids accidental unlocks; it's like a * sticky/continuous lockdep_assert_held(). @@ -1755,7 +1785,7 @@ static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf) if (rq->clock_update_flags > RQCF_ACT_SKIP) rf->clock_update_flags = RQCF_UPDATED; #endif - + scx_rq_clock_invalidate(rq); lockdep_unpin_lock(__rq_lockp(rq), rf->cookie); } @@ -2280,7 +2310,7 @@ static inline int task_on_cpu(struct rq *rq, struct task_struct *p) static inline int task_on_rq_queued(struct task_struct *p) { - return p->on_rq == TASK_ON_RQ_QUEUED; + return READ_ONCE(p->on_rq) == TASK_ON_RQ_QUEUED; } static inline int task_on_rq_migrating(struct task_struct *p) @@ -2514,19 +2544,6 @@ extern const struct sched_class rt_sched_class; extern const struct sched_class fair_sched_class; extern const struct sched_class idle_sched_class; -#ifdef CONFIG_SCHED_CLASS_EXT -extern const struct sched_class ext_sched_class; - -DECLARE_STATIC_KEY_FALSE(__scx_ops_enabled); /* SCX BPF scheduler loaded */ -DECLARE_STATIC_KEY_FALSE(__scx_switched_all); /* all fair class tasks on SCX */ - -#define scx_enabled() static_branch_unlikely(&__scx_ops_enabled) -#define scx_switched_all() static_branch_unlikely(&__scx_switched_all) -#else /* !CONFIG_SCHED_CLASS_EXT */ -#define scx_enabled() false -#define scx_switched_all() false -#endif /* !CONFIG_SCHED_CLASS_EXT */ - /* * Iterate only active classes. SCX can take over all fair tasks or be * completely disabled. If the former, skip fair. If the latter, skip SCX. @@ -2574,7 +2591,7 @@ static inline bool sched_rt_runnable(struct rq *rq) static inline bool sched_fair_runnable(struct rq *rq) { - return rq->cfs.nr_running > 0; + return rq->cfs.nr_queued > 0; } extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); @@ -3242,6 +3259,12 @@ struct irqtime { }; DECLARE_PER_CPU(struct irqtime, cpu_irqtime); +DECLARE_STATIC_KEY_FALSE(sched_clock_irqtime); + +static inline int irqtime_enabled(void) +{ + return static_branch_likely(&sched_clock_irqtime); +} /* * Returns the irqtime minus the softirq time computed by ksoftirqd. @@ -3262,6 +3285,13 @@ static inline u64 irq_time_read(int cpu) return total; } +#else + +static inline int irqtime_enabled(void) +{ + return 0; +} + #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ #ifdef CONFIG_CPU_FREQ @@ -3509,6 +3539,8 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned #endif /* !CONFIG_HAVE_SCHED_AVG_IRQ */ +extern void __setparam_fair(struct task_struct *p, const struct sched_attr *attr); + #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) #define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus))) diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index eb0cdcd4d921..4346fd81c31f 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -103,7 +103,7 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p, * Bump this up when changing the output format or the meaning of an existing * format, so that tools can adapt (or abort) */ -#define SCHEDSTAT_VERSION 16 +#define SCHEDSTAT_VERSION 17 static int show_schedstat(struct seq_file *seq, void *v) { @@ -138,14 +138,17 @@ static int show_schedstat(struct seq_file *seq, void *v) for_each_domain(cpu, sd) { enum cpu_idle_type itype; - seq_printf(seq, "domain%d %*pb", dcount++, + seq_printf(seq, "domain%d %s %*pb", dcount++, sd->name, cpumask_pr_args(sched_domain_span(sd))); for (itype = 0; itype < CPU_MAX_IDLE_TYPES; itype++) { - seq_printf(seq, " %u %u %u %u %u %u %u %u", + seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u", sd->lb_count[itype], sd->lb_balanced[itype], sd->lb_failed[itype], - sd->lb_imbalance[itype], + sd->lb_imbalance_load[itype], + sd->lb_imbalance_util[itype], + sd->lb_imbalance_task[itype], + sd->lb_imbalance_misfit[itype], sd->lb_gained[itype], sd->lb_hot_gained[itype], sd->lb_nobusyq[itype], diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 8ee0add5a48a..19cdbe96f93d 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -138,6 +138,10 @@ static inline void psi_enqueue(struct task_struct *p, int flags) if (flags & ENQUEUE_RESTORE) return; + /* psi_sched_switch() will handle the flags */ + if (task_on_cpu(task_rq(p), p)) + return; + if (p->se.sched_delayed) { /* CPU migration of "sleeping" task */ SCHED_WARN_ON(!(flags & ENQUEUE_MIGRATED)); @@ -244,7 +248,10 @@ static inline void sched_info_dequeue(struct rq *rq, struct task_struct *t) delta = rq_clock(rq) - t->sched_info.last_queued; t->sched_info.last_queued = 0; t->sched_info.run_delay += delta; - + if (delta > t->sched_info.max_run_delay) + t->sched_info.max_run_delay = delta; + if (delta && (!t->sched_info.min_run_delay || delta < t->sched_info.min_run_delay)) + t->sched_info.min_run_delay = delta; rq_sched_info_dequeue(rq, delta); } @@ -266,6 +273,10 @@ static void sched_info_arrive(struct rq *rq, struct task_struct *t) t->sched_info.run_delay += delta; t->sched_info.last_arrival = now; t->sched_info.pcount++; + if (delta > t->sched_info.max_run_delay) + t->sched_info.max_run_delay = delta; + if (delta && (!t->sched_info.min_run_delay || delta < t->sched_info.min_run_delay)) + t->sched_info.min_run_delay = delta; rq_sched_info_arrive(rq, delta); } diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index ff0e5ab4e37c..456d339be98f 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -300,20 +300,10 @@ static void __setscheduler_params(struct task_struct *p, p->policy = policy; - if (dl_policy(policy)) { + if (dl_policy(policy)) __setparam_dl(p, attr); - } else if (fair_policy(policy)) { - p->static_prio = NICE_TO_PRIO(attr->sched_nice); - if (attr->sched_runtime) { - p->se.custom_slice = 1; - p->se.slice = clamp_t(u64, attr->sched_runtime, - NSEC_PER_MSEC/10, /* HZ=1000 * 10 */ - NSEC_PER_MSEC*100); /* HZ=100 / 10 */ - } else { - p->se.custom_slice = 0; - p->se.slice = sysctl_sched_base_slice; - } - } + else if (fair_policy(policy)) + __setparam_fair(p, attr); /* rt-policy tasks do not have a timerslack */ if (rt_or_dl_task_policy(p)) { @@ -1139,6 +1129,13 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) if (!task_has_dl_policy(p) || !dl_bandwidth_enabled()) return 0; + /* + * The special/sugov task isn't part of regular bandwidth/admission + * control so let userspace change affinities. + */ + if (dl_entity_is_special(&p->dl)) + return 0; + /* * Since bandwidth control happens on root_domain basis, * if admission test is enabled, we only admit -deadline @@ -1433,7 +1430,7 @@ int __sched yield_to(struct task_struct *p, bool preempt) struct rq *rq, *p_rq; int yielded = 0; - scoped_guard (irqsave) { + scoped_guard (raw_spinlock_irqsave, &p->pi_lock) { rq = this_rq(); again: diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 9748a4c8d668..c49aea8c1025 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -312,7 +312,7 @@ static int sched_energy_aware_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table sched_energy_aware_sysctls[] = { +static const struct ctl_table sched_energy_aware_sysctls[] = { { .procname = "sched_energy_aware", .data = &sysctl_sched_energy_aware, @@ -1635,9 +1635,7 @@ sd_init(struct sched_domain_topology_level *tl, .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, .child = child, -#ifdef CONFIG_SCHED_DEBUG .name = tl->name, -#endif }; sd_span = sched_domain_span(sd); @@ -2338,10 +2336,8 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve if (!cpumask_subset(sched_domain_span(child), sched_domain_span(sd))) { pr_err("BUG: arch topology borken\n"); -#ifdef CONFIG_SCHED_DEBUG pr_err(" the %s domain not a subset of the %s domain\n", child->name, sd->name); -#endif /* Fixup, ensure @sd has at least @child CPUs. */ cpumask_or(sched_domain_span(sd), sched_domain_span(sd), @@ -2721,9 +2717,11 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], /* * This domain won't be destroyed and as such - * its dl_bw->total_bw needs to be cleared. It - * will be recomputed in function - * update_tasks_root_domain(). + * its dl_bw->total_bw needs to be cleared. + * Tasks contribution will be then recomputed + * in function dl_update_tasks_root_domain(), + * dl_servers contribution in function + * dl_restore_server_root_domain(). */ rd = cpu_rq(cpumask_any(doms_cur[i]))->rd; dl_clear_root_domain(rd); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 385d48293a5f..f59381c4a2ff 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -2450,7 +2450,7 @@ static int seccomp_actions_logged_handler(const struct ctl_table *ro_table, int return ret; } -static struct ctl_table seccomp_sysctl_table[] = { +static const struct ctl_table seccomp_sysctl_table[] = { { .procname = "actions_avail", .data = (void *) &seccomp_actions_avail, diff --git a/kernel/signal.c b/kernel/signal.c index 989b1cc9116a..875e97f6205a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2007,11 +2007,22 @@ void posixtimer_send_sigqueue(struct k_itimer *tmr) if (!list_empty(&q->list)) { /* - * If task group is exiting with the signal already pending, - * wait for __exit_signal() to do its job. Otherwise if - * ignored, it's not supposed to be queued. Try to survive. + * The signal was ignored and blocked. The timer + * expiry queued it because blocked signals are + * queued independent of the ignored state. + * + * The unblocking set SIGPENDING, but the signal + * was not yet dequeued from the pending list. + * So prepare_signal() sees unblocked and ignored, + * which ends up here. Leave it queued like a + * regular signal. + * + * The same happens when the task group is exiting + * and the signal is already queued. + * prepare_signal() treats SIGNAL_GROUP_EXIT as + * ignored independent of its queued state. This + * gets cleaned up in __exit_signal(). */ - WARN_ON_ONCE(!(t->signal->flags & SIGNAL_GROUP_EXIT)); goto out; } @@ -2046,17 +2057,25 @@ void posixtimer_send_sigqueue(struct k_itimer *tmr) goto out; } - /* This should never happen and leaks a reference count */ - if (WARN_ON_ONCE(!hlist_unhashed(&tmr->ignored_list))) - hlist_del_init(&tmr->ignored_list); - if (unlikely(!list_empty(&q->list))) { /* This holds a reference count already */ result = TRACE_SIGNAL_ALREADY_PENDING; goto out; } - posixtimer_sigqueue_getref(q); + /* + * If the signal is on the ignore list, it got blocked after it was + * ignored earlier. But nothing lifted the ignore. Move it back to + * the pending list to be consistent with the regular signal + * handling. This already holds a reference count. + * + * If it's not on the ignore list acquire a reference count. + */ + if (likely(hlist_unhashed(&tmr->ignored_list))) + posixtimer_sigqueue_getref(q); + else + hlist_del_init(&tmr->ignored_list); + posixtimer_queue_sigqueue(q, t, tmr->it_pid_type); result = TRACE_SIGNAL_DELIVERED; out: @@ -4931,7 +4950,7 @@ static inline void siginfo_buildtime_checks(void) } #if defined(CONFIG_SYSCTL) -static struct ctl_table signal_debug_table[] = { +static const struct ctl_table signal_debug_table[] = { #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { .procname = "exception-trace", diff --git a/kernel/smp.c b/kernel/smp.c index 27dc31a146a3..974f3a3962e8 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -170,9 +170,9 @@ static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ -module_param(csd_lock_timeout, ulong, 0444); +module_param(csd_lock_timeout, ulong, 0644); static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */ -module_param(panic_on_ipistall, int, 0444); +module_param(panic_on_ipistall, int, 0644); static atomic_t csd_bug_count = ATOMIC_INIT(0); @@ -815,7 +815,8 @@ static void smp_call_function_many_cond(const struct cpumask *mask, WARN_ON_ONCE(!in_task()); /* Check if we need local execution. */ - if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask)) + if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask) && + (!cond_func || cond_func(this_cpu, info))) run_local = true; /* Check if we need remote execution, i.e., any CPU excluding this one. */ @@ -868,7 +869,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask, send_call_function_ipi_mask(cfd->cpumask_ipi); } - if (run_local && (!cond_func || cond_func(this_cpu, info))) { + if (run_local) { unsigned long flags; local_irq_save(flags); diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 39fd620a7db6..bb65321761b4 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -15,6 +15,7 @@ #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE #include +#include #include #include @@ -41,10 +42,10 @@ static int stack_erasing_sysctl(const struct ctl_table *table, int write, static_branch_enable(&stack_erasing_bypass); pr_warn("stackleak: kernel stack erasing is %s\n", - state ? "enabled" : "disabled"); + str_enabled_disabled(state)); return ret; } -static struct ctl_table stackleak_sysctls[] = { +static const struct ctl_table stackleak_sysctls[] = { { .procname = "stack_erasing", .data = NULL, diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c index 5259cda486d0..bb7d066a7c39 100644 --- a/kernel/static_call_inline.c +++ b/kernel/static_call_inline.c @@ -15,7 +15,7 @@ extern struct static_call_site __start_static_call_sites[], extern struct static_call_tramp_key __start_static_call_tramp_key[], __stop_static_call_tramp_key[]; -static int static_call_initialized; +int static_call_initialized; /* * Must be called before early_initcall() to be effective. diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index da821ce258ea..8896d844d738 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -250,8 +250,8 @@ static int multi_cpu_stop(void *data) * be detected and reported on their side. */ touch_nmi_watchdog(); + rcu_momentary_eqs(); } - rcu_momentary_eqs(); } while (curstate != MULTI_STOP_EXIT); local_irq_restore(flags); diff --git a/kernel/sys.c b/kernel/sys.c index c4c701c6f0b4..cb366ff8703a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -75,6 +75,8 @@ #include #include +#include + #include "uid16.h" #ifndef SET_UNALIGN_CTL @@ -2810,6 +2812,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = arch_lock_shadow_stack_status(me, arg2); break; default: + trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5); error = -EINVAL; break; } diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c index 3ac98bb7fb82..eb2842bd0557 100644 --- a/kernel/sysctl-test.c +++ b/kernel/sysctl-test.c @@ -374,7 +374,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value( struct kunit *test) { unsigned char data = 0; - struct ctl_table table_foo[] = { + const struct ctl_table table_foo[] = { { .procname = "foo", .data = &data, @@ -386,7 +386,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value( }, }; - struct ctl_table table_bar[] = { + const struct ctl_table table_bar[] = { { .procname = "bar", .data = &data, @@ -398,7 +398,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value( }, }; - struct ctl_table table_qux[] = { + const struct ctl_table table_qux[] = { { .procname = "qux", .data = &data, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5c9202cb8f59..cb57da499ebb 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1609,7 +1609,7 @@ int proc_do_static_key(const struct ctl_table *table, int write, return ret; } -static struct ctl_table kern_table[] = { +static const struct ctl_table kern_table[] = { { .procname = "panic", .data = &panic_timeout, @@ -1803,15 +1803,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif - { - .procname = "pid_max", - .data = &pid_max, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &pid_max_min, - .extra2 = &pid_max_max, - }, { .procname = "panic_on_oops", .data = &panic_on_oops, @@ -2030,7 +2021,7 @@ static struct ctl_table kern_table[] = { #endif }; -static struct ctl_table vm_table[] = { +static const struct ctl_table vm_table[] = { { .procname = "overcommit_memory", .data = &sysctl_overcommit_memory, diff --git a/kernel/task_work.c b/kernel/task_work.c index c969f1f26be5..d1efec571a4a 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -55,26 +55,14 @@ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; - int flags = notify & TWA_FLAGS; - notify &= ~TWA_FLAGS; if (notify == TWA_NMI_CURRENT) { if (WARN_ON_ONCE(task != current)) return -EINVAL; if (!IS_ENABLED(CONFIG_IRQ_WORK)) return -EINVAL; } else { - /* - * Record the work call stack in order to print it in KASAN - * reports. - * - * Note that stack allocation can fail if TWAF_NO_ALLOC flag - * is set and new page is needed to expand the stack buffer. - */ - if (flags & TWAF_NO_ALLOC) - kasan_record_aux_stack_noalloc(work); - else - kasan_record_aux_stack(work); + kasan_record_aux_stack(work); } head = READ_ONCE(task->task_works); diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c index 62e73444ffe4..38dae590b29f 100644 --- a/kernel/time/clocksource-wdtest.c +++ b/kernel/time/clocksource-wdtest.c @@ -137,7 +137,8 @@ static int wdtest_func(void *arg) udelay(1); j2 = clocksource_wdtest_ktime.read(&clocksource_wdtest_ktime); pr_info("--- tsc-like times: %lu - %lu = %lu.\n", j2, j1, j2 - j1); - WARN_ON_ONCE(time_before(j2, j1 + NSEC_PER_USEC)); + WARN_ONCE(time_before(j2, j1 + NSEC_PER_USEC), + "Expected at least 1000ns, got %lu.\n", j2 - j1); /* Verify tsc-like stability with various numbers of errors injected. */ max_retries = clocksource_get_max_watchdog_retry(); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 80fe3749d2db..f6d8df94045c 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1067,11 +1067,10 @@ EXPORT_SYMBOL_GPL(hrtimer_forward); * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. * - * Returns 1 when the new timer is the leftmost timer in the tree. + * Returns true when the new timer is the leftmost timer in the tree. */ -static int enqueue_hrtimer(struct hrtimer *timer, - struct hrtimer_clock_base *base, - enum hrtimer_mode mode) +static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, + enum hrtimer_mode mode) { debug_activate(timer, mode); WARN_ON_ONCE(!base->cpu_base->online); @@ -2202,6 +2201,15 @@ int hrtimers_prepare_cpu(unsigned int cpu) } cpu_base->cpu = cpu; + hrtimer_cpu_base_init_expiry_lock(cpu_base); + return 0; +} + +int hrtimers_cpu_starting(unsigned int cpu) +{ + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + + /* Clear out any left over state from a CPU down operation */ cpu_base->active_bases = 0; cpu_base->hres_active = 0; cpu_base->hang_detected = 0; @@ -2210,7 +2218,6 @@ int hrtimers_prepare_cpu(unsigned int cpu) cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->online = 1; - hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } @@ -2286,5 +2293,6 @@ int hrtimers_cpu_dying(unsigned int dying_cpu) void __init hrtimers_init(void) { hrtimers_prepare_cpu(smp_processor_id()); + hrtimers_cpu_starting(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 881a9ce96af7..1b675aee99a9 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -538,7 +538,7 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) * When the reference count reaches zero, the timer is scheduled * for RCU removal after the grace period. * - * Holding rcu_read_lock() accross the lookup ensures that + * Holding rcu_read_lock() across the lookup ensures that * the timer cannot be freed. * * The lookup validates locklessly that timr::it_signal == diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index ed58eebb4e8f..0207868c8b4d 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -1020,6 +1020,8 @@ static inline ktime_t tick_get_next_period(void) /** * tick_broadcast_setup_oneshot - setup the broadcast device + * @bc: the broadcast device + * @from_periodic: true if called from periodic mode */ static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3d128825d343..1e67d076f195 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -485,25 +485,6 @@ u64 notrace ktime_get_tai_fast_ns(void) } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); -static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) -{ - struct tk_read_base *tkr; - u64 basem, baser, delta; - unsigned int seq; - - do { - seq = raw_read_seqcount_latch(&tkf->seq); - tkr = tkf->base + (seq & 0x01); - basem = ktime_to_ns(tkr->base); - baser = ktime_to_ns(tkr->base_real); - delta = timekeeping_get_ns(tkr); - } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); - - if (mono) - *mono = basem + delta; - return baser + delta; -} - /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * @@ -511,64 +492,22 @@ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) */ u64 ktime_get_real_fast_ns(void) { - return __ktime_get_real_fast(&tk_fast_mono, NULL); + struct tk_fast *tkf = &tk_fast_mono; + struct tk_read_base *tkr; + u64 baser, delta; + unsigned int seq; + + do { + seq = raw_read_seqcount_latch(&tkf->seq); + tkr = tkf->base + (seq & 0x01); + baser = ktime_to_ns(tkr->base_real); + delta = timekeeping_get_ns(tkr); + } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); + + return baser + delta; } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); -/** - * ktime_get_fast_timestamps: - NMI safe timestamps - * @snapshot: Pointer to timestamp storage - * - * Stores clock monotonic, boottime and realtime timestamps. - * - * Boot time is a racy access on 32bit systems if the sleep time injection - * happens late during resume and not in timekeeping_resume(). That could - * be avoided by expanding struct tk_read_base with boot offset for 32bit - * and adding more overhead to the update. As this is a hard to observe - * once per resume event which can be filtered with reasonable effort using - * the accurate mono/real timestamps, it's probably not worth the trouble. - * - * Aside of that it might be possible on 32 and 64 bit to observe the - * following when the sleep time injection happens late: - * - * CPU 0 CPU 1 - * timekeeping_resume() - * ktime_get_fast_timestamps() - * mono, real = __ktime_get_real_fast() - * inject_sleep_time() - * update boot offset - * boot = mono + bootoffset; - * - * That means that boot time already has the sleep time adjustment, but - * real time does not. On the next readout both are in sync again. - * - * Preventing this for 64bit is not really feasible without destroying the - * careful cache layout of the timekeeper because the sequence count and - * struct tk_read_base would then need two cache lines instead of one. - * - * Access to the time keeper clock source is disabled across the innermost - * steps of suspend/resume. The accessors still work, but the timestamps - * are frozen until time keeping is resumed which happens very early. - * - * For regular suspend/resume there is no observable difference vs. sched - * clock, but it might affect some of the nasty low level debug printks. - * - * OTOH, access to sched clock is not guaranteed across suspend/resume on - * all systems either so it depends on the hardware in use. - * - * If that turns out to be a real problem then this could be mitigated by - * using sched clock in a similar way as during early boot. But it's not as - * trivial as on early boot because it needs some careful protection - * against the clock monotonic timestamp jumping backwards on resume. - */ -void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot) -{ - struct timekeeper *tk = &tk_core.timekeeper; - - snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono); - snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot)); -} - /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. diff --git a/kernel/time/timer.c b/kernel/time/timer.c index a5860bf6d16f..c8f776dc6ee0 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -301,7 +301,7 @@ static int timer_migration_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table timer_sysctl[] = { +static const struct ctl_table timer_sysctl[] = { { .procname = "timer_migration", .data = &sysctl_timer_migration, @@ -956,33 +956,29 @@ static int detach_if_pending(struct timer_list *timer, struct timer_base *base, static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; - struct timer_base *base; - - base = per_cpu_ptr(&timer_bases[index], cpu); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) - base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu); - return base; + index = BASE_DEF; + + return per_cpu_ptr(&timer_bases[index], cpu); } static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; - struct timer_base *base; - - base = this_cpu_ptr(&timer_bases[index]); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) - base = this_cpu_ptr(&timer_bases[BASE_DEF]); - return base; + index = BASE_DEF; + + return this_cpu_ptr(&timer_bases[index]); } static inline struct timer_base *get_timer_base(u32 tflags) diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 8d57f7686bb0..9cb9b6584ea1 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -534,8 +534,13 @@ static void __walk_groups(up_f up, struct tmigr_walk *data, break; child = group; - group = group->parent; + /* + * Pairs with the store release on group connection + * to make sure group initialization is visible. + */ + group = READ_ONCE(group->parent); data->childmask = child->groupmask; + WARN_ON_ONCE(!data->childmask); } while (group); } @@ -564,7 +569,7 @@ static struct tmigr_event *tmigr_next_groupevt(struct tmigr_group *group) while ((node = timerqueue_getnext(&group->events))) { evt = container_of(node, struct tmigr_event, nextevt); - if (!evt->ignore) { + if (!READ_ONCE(evt->ignore)) { WRITE_ONCE(group->next_expiry, evt->nextevt.expires); return evt; } @@ -660,7 +665,7 @@ static bool tmigr_active_up(struct tmigr_group *group, * lock is held while updating the ignore flag in idle path. So this * state change will not be lost. */ - group->groupevt.ignore = true; + WRITE_ONCE(group->groupevt.ignore, true); return walk_done; } @@ -721,6 +726,7 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, union tmigr_state childstate, groupstate; bool remote = data->remote; bool walk_done = false; + bool ignore; u64 nextexp; if (child) { @@ -739,11 +745,19 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, nextexp = child->next_expiry; evt = &child->groupevt; - evt->ignore = (nextexp == KTIME_MAX) ? true : false; + /* + * This can race with concurrent idle exit (activate). + * If the current writer wins, a useless remote expiration may + * be scheduled. If the activate wins, the event is properly + * ignored. + */ + ignore = (nextexp == KTIME_MAX) ? true : false; + WRITE_ONCE(evt->ignore, ignore); } else { nextexp = data->nextexp; first_childevt = evt = data->evt; + ignore = evt->ignore; /* * Walking the hierarchy is required in any case when a @@ -769,7 +783,7 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, * first event information of the group is updated properly and * also handled properly, so skip this fast return path. */ - if (evt->ignore && !remote && group->parent) + if (ignore && !remote && group->parent) return true; raw_spin_lock(&group->lock); @@ -783,7 +797,7 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, * queue when the expiry time changed only or when it could be ignored. */ if (timerqueue_node_queued(&evt->nextevt)) { - if ((evt->nextevt.expires == nextexp) && !evt->ignore) { + if ((evt->nextevt.expires == nextexp) && !ignore) { /* Make sure not to miss a new CPU event with the same expiry */ evt->cpu = first_childevt->cpu; goto check_toplvl; @@ -793,7 +807,7 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, WRITE_ONCE(group->next_expiry, KTIME_MAX); } - if (evt->ignore) { + if (ignore) { /* * When the next child event could be ignored (nextexp is * KTIME_MAX) and there was no remote timer handling before or @@ -1487,6 +1501,21 @@ static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, s.seq = 0; atomic_set(&group->migr_state, s.state); + /* + * If this is a new top-level, prepare its groupmask in advance. + * This avoids accidents where yet another new top-level is + * created in the future and made visible before the current groupmask. + */ + if (list_empty(&tmigr_level_list[lvl])) { + group->groupmask = BIT(0); + /* + * The previous top level has prepared its groupmask already, + * simply account it as the first child. + */ + if (lvl > 0) + group->num_children = 1; + } + timerqueue_init_head(&group->events); timerqueue_init(&group->groupevt.nextevt); group->groupevt.nextevt.expires = KTIME_MAX; @@ -1550,8 +1579,25 @@ static void tmigr_connect_child_parent(struct tmigr_group *child, raw_spin_lock_irq(&child->lock); raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING); - child->parent = parent; - child->groupmask = BIT(parent->num_children++); + if (activate) { + /* + * @child is the old top and @parent the new one. In this + * case groupmask is pre-initialized and @child already + * accounted, along with its new sibling corresponding to the + * CPU going up. + */ + WARN_ON_ONCE(child->groupmask != BIT(0) || parent->num_children != 2); + } else { + /* Adding @child for the CPU going up to @parent. */ + child->groupmask = BIT(parent->num_children++); + } + + /* + * Make sure parent initialization is visible before publishing it to a + * racing CPU entering/exiting idle. This RELEASE barrier enforces an + * address dependency that pairs with the READ_ONCE() in __walk_groups(). + */ + smp_store_release(&child->parent, parent); raw_spin_unlock(&parent->lock); raw_spin_unlock_irq(&child->lock); @@ -1624,9 +1670,7 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) * be different from tmigr_hierarchy_levels, contains only a * single group. */ - if (group->parent || i == tmigr_hierarchy_levels || - (list_empty(&tmigr_level_list[i]) && - list_is_singular(&tmigr_level_list[i - 1]))) + if (group->parent || list_is_singular(&tmigr_level_list[i - 1])) break; } while (i < tmigr_hierarchy_levels); diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h index 154accc7a543..ae19f70f8170 100644 --- a/kernel/time/timer_migration.h +++ b/kernel/time/timer_migration.h @@ -110,22 +110,19 @@ struct tmigr_cpu { * union tmigr_state - state of tmigr_group * @state: Combined version of the state - only used for atomic * read/cmpxchg function - * @struct: Split version of the state - only use the struct members to + * &anon struct: Split version of the state - only use the struct members to * update information to stay independent of endianness + * @active: Contains each mask bit of the active children + * @migrator: Contains mask of the child which is migrator + * @seq: Sequence counter needs to be increased when an update + * to the tmigr_state is done. It prevents a race when + * updates in the child groups are propagated in changed + * order. Detailed information about the scenario is + * given in the documentation at the begin of + * timer_migration.c. */ union tmigr_state { u32 state; - /** - * struct - split state of tmigr_group - * @active: Contains each mask bit of the active children - * @migrator: Contains mask of the child which is migrator - * @seq: Sequence counter needs to be increased when an update - * to the tmigr_state is done. It prevents a race when - * updates in the child groups are propagated in changed - * order. Detailed information about the scenario is - * given in the documentation at the begin of - * timer_migration.c. - */ struct { u8 active; u8 migrator; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 74c2b1d43bb9..d570b8b9c0a9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -31,9 +31,14 @@ config HAVE_FUNCTION_GRAPH_TRACER help See Documentation/trace/ftrace-design.rst -config HAVE_FUNCTION_GRAPH_RETVAL +config HAVE_FUNCTION_GRAPH_FREGS bool +config HAVE_FTRACE_GRAPH_FUNC + bool + help + True if ftrace_graph_func() is defined. + config HAVE_DYNAMIC_FTRACE bool help @@ -57,6 +62,12 @@ config HAVE_DYNAMIC_FTRACE_WITH_ARGS This allows for use of ftrace_regs_get_argument() and ftrace_regs_get_stack_pointer(). +config HAVE_FTRACE_REGS_HAVING_PT_REGS + bool + help + If this is set, ftrace_regs has pt_regs, thus it can convert to + pt_regs without allocating memory. + config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE bool help @@ -232,7 +243,7 @@ config FUNCTION_GRAPH_TRACER config FUNCTION_GRAPH_RETVAL bool "Kernel Function Graph Return Value" - depends on HAVE_FUNCTION_GRAPH_RETVAL + depends on HAVE_FUNCTION_GRAPH_FREGS depends on FUNCTION_GRAPH_TRACER default n help @@ -296,10 +307,9 @@ config DYNAMIC_FTRACE_WITH_ARGS config FPROBE bool "Kernel Function Probe (fprobe)" - depends on FUNCTION_TRACER - depends on DYNAMIC_FTRACE_WITH_REGS - depends on HAVE_RETHOOK - select RETHOOK + depends on HAVE_FUNCTION_GRAPH_FREGS && HAVE_FTRACE_GRAPH_FUNC + depends on DYNAMIC_FTRACE_WITH_ARGS + select FUNCTION_GRAPH_TRACER default n help This option enables kernel function probe (fprobe) based on ftrace. diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 8fd292d34d89..3679a6d18934 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -617,8 +617,9 @@ err: return ret; } -static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev, - struct block_device *bdev, char __user *arg) +int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, + struct block_device *bdev, + char __user *arg) { struct blk_user_trace_setup buts; int ret; @@ -627,29 +628,18 @@ static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (ret) return -EFAULT; + mutex_lock(&q->debugfs_mutex); ret = do_blk_trace_setup(q, name, dev, bdev, &buts); + mutex_unlock(&q->debugfs_mutex); if (ret) return ret; if (copy_to_user(arg, &buts, sizeof(buts))) { - __blk_trace_remove(q); + blk_trace_remove(q); return -EFAULT; } return 0; } - -int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, - struct block_device *bdev, - char __user *arg) -{ - int ret; - - mutex_lock(&q->debugfs_mutex); - ret = __blk_trace_setup(q, name, dev, bdev, arg); - mutex_unlock(&q->debugfs_mutex); - - return ret; -} EXPORT_SYMBOL_GPL(blk_trace_setup); #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) @@ -673,12 +663,14 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, .pid = cbuts.pid, }; + mutex_lock(&q->debugfs_mutex); ret = do_blk_trace_setup(q, name, dev, bdev, &buts); + mutex_unlock(&q->debugfs_mutex); if (ret) return ret; if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) { - __blk_trace_remove(q); + blk_trace_remove(q); return -EFAULT; } @@ -732,12 +724,10 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) int ret, start = 0; char b[BDEVNAME_SIZE]; - mutex_lock(&q->debugfs_mutex); - switch (cmd) { case BLKTRACESETUP: snprintf(b, sizeof(b), "%pg", bdev); - ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); + ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) case BLKTRACESETUP32: @@ -749,17 +739,15 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) start = 1; fallthrough; case BLKTRACESTOP: - ret = __blk_trace_startstop(q, start); + ret = blk_trace_startstop(q, start); break; case BLKTRACETEARDOWN: - ret = __blk_trace_remove(q); + ret = blk_trace_remove(q); break; default: ret = -ENOTTY; break; } - - mutex_unlock(&q->debugfs_mutex); return ret; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1b8db5aee9d3..adc947587eb8 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -357,17 +357,6 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = { .arg3_type = ARG_CONST_SIZE, }; -static const struct bpf_func_proto *bpf_get_probe_write_proto(void) -{ - if (!capable(CAP_SYS_ADMIN)) - return NULL; - - pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!", - current->comm, task_pid_nr(current)); - - return &bpf_probe_write_user_proto; -} - #define MAX_TRACE_PRINTK_VARARGS 3 #define BPF_TRACE_PRINTK_SIZE 1024 @@ -619,7 +608,8 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = { static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, - u64 flags, struct perf_sample_data *sd) + u64 flags, struct perf_raw_record *raw, + struct perf_sample_data *sd) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); @@ -644,6 +634,8 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; + perf_sample_save_raw_data(sd, event, raw); + return perf_event_output(event, sd, regs); } @@ -687,9 +679,8 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, } perf_sample_data_init(sd, 0, 0); - perf_sample_save_raw_data(sd, &raw); - err = __bpf_perf_event_output(regs, map, flags, sd); + err = __bpf_perf_event_output(regs, map, flags, &raw, sd); out: this_cpu_dec(bpf_trace_nest_level); preempt_enable(); @@ -748,9 +739,8 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); - perf_sample_save_raw_data(sd, &raw); - ret = __bpf_perf_event_output(regs, map, flags, sd); + ret = __bpf_perf_event_output(regs, map, flags, &raw, sd); out: this_cpu_dec(bpf_event_output_nest_level); preempt_enable(); @@ -853,7 +843,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type, struct task_struc if (unlikely(is_global_init(task))) return -EPERM; - if (irqs_disabled()) { + if (!preemptible()) { /* Do an early check on signal validity. Otherwise, * the error is lost in deferred irq_work. */ @@ -1444,6 +1434,8 @@ late_initcall(bpf_key_sig_kfuncs_init); static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *func_proto; + switch (func_id) { case BPF_FUNC_map_lookup_elem: return &bpf_map_lookup_elem_proto; @@ -1485,9 +1477,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_read_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; - case BPF_FUNC_probe_write_user: - return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? - NULL : bpf_get_probe_write_proto(); case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: @@ -1566,7 +1555,22 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: - return bpf_base_func_proto(func_id, prog); + break; + } + + func_proto = bpf_base_func_proto(func_id, prog); + if (func_proto) + return func_proto; + + if (!bpf_token_capable(prog->aux->token, CAP_SYS_ADMIN)) + return NULL; + + switch (func_id) { + case BPF_FUNC_probe_write_user: + return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? + NULL : &bpf_probe_write_user_proto; + default: + return NULL; } } @@ -2242,6 +2246,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; + struct bpf_prog *prog = NULL; int ret; mutex_lock(&bpf_event_mutex); @@ -2262,18 +2267,22 @@ void perf_event_detach_bpf_prog(struct perf_event *event) } put: - /* - * It could be that the bpf_prog is not sleepable (and will be freed - * via normal RCU), but is called from a point that supports sleepable - * programs and uses tasks-trace-RCU. - */ - synchronize_rcu_tasks_trace(); - - bpf_prog_put(event->prog); + prog = event->prog; event->prog = NULL; unlock: mutex_unlock(&bpf_event_mutex); + + if (prog) { + /* + * It could be that the bpf_prog is not sleepable (and will be freed + * via normal RCU), but is called from a point that supports sleepable + * programs and uses tasks-trace-RCU. + */ + synchronize_rcu_tasks_trace(); + + bpf_prog_put(prog); + } } int perf_event_query_prog_array(struct perf_event *event, void __user *info) @@ -2584,6 +2593,20 @@ struct user_syms { char *buf; }; +#ifndef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS +static DEFINE_PER_CPU(struct pt_regs, bpf_kprobe_multi_pt_regs); +#define bpf_kprobe_multi_pt_regs_ptr() this_cpu_ptr(&bpf_kprobe_multi_pt_regs) +#else +#define bpf_kprobe_multi_pt_regs_ptr() (NULL) +#endif + +static unsigned long ftrace_get_entry_ip(unsigned long fentry_ip) +{ + unsigned long ip = ftrace_get_symaddr(fentry_ip); + + return ip ? : fentry_ip; +} + static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt) { unsigned long __user usymbol; @@ -2778,7 +2801,7 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) static int kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, - unsigned long entry_ip, struct pt_regs *regs, + unsigned long entry_ip, struct ftrace_regs *fregs, bool is_return, void *data) { struct bpf_kprobe_multi_run_ctx run_ctx = { @@ -2790,16 +2813,18 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, .entry_ip = entry_ip, }; struct bpf_run_ctx *old_run_ctx; + struct pt_regs *regs; int err; if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { bpf_prog_inc_misses_counter(link->link.prog); - err = 0; + err = 1; goto out; } migrate_disable(); rcu_read_lock(); + regs = ftrace_partial_regs(fregs, bpf_kprobe_multi_pt_regs_ptr()); old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); @@ -2813,26 +2838,28 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, static int kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { struct bpf_kprobe_multi_link *link; int err; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data); + err = kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), + fregs, false, data); return is_kprobe_session(link->link.prog) ? err : 0; } static void kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { struct bpf_kprobe_multi_link *link; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data); + kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), + fregs, true, data); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 0bf78517b5d4..5dddfc2149f6 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -292,13 +292,15 @@ static inline unsigned long make_data_type_val(int idx, int size, int offset) } /* ftrace_graph_entry set to this to tell some archs to run function graph */ -static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops) +static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops, + struct ftrace_regs *fregs) { return 0; } /* ftrace_graph_return set to this to tell some archs to run function graph */ -static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops) +static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops, + struct ftrace_regs *fregs) { } @@ -520,13 +522,15 @@ int __weak ftrace_disable_ftrace_graph_caller(void) #endif int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { return 0; } static void ftrace_graph_ret_stub(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { } @@ -644,14 +648,20 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, #endif /* If the caller does not use ftrace, call this function. */ -int function_graph_enter(unsigned long ret, unsigned long func, - unsigned long frame_pointer, unsigned long *retp) +int function_graph_enter_regs(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp, + struct ftrace_regs *fregs) { struct ftrace_graph_ent trace; unsigned long bitmap = 0; int offset; + int bit; int i; + bit = ftrace_test_recursion_trylock(func, ret); + if (bit < 0) + return -EBUSY; + trace.func = func; trace.depth = ++current->curr_ret_depth; @@ -663,7 +673,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, if (static_branch_likely(&fgraph_do_direct)) { int save_curr_ret_stack = current->curr_ret_stack; - if (static_call(fgraph_func)(&trace, fgraph_direct_gops)) + if (static_call(fgraph_func)(&trace, fgraph_direct_gops, fregs)) bitmap |= BIT(fgraph_direct_gops->idx); else /* Clear out any saved storage */ @@ -681,7 +691,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, save_curr_ret_stack = current->curr_ret_stack; if (ftrace_ops_test(&gops->ops, func, NULL) && - gops->entryfunc(&trace, gops)) + gops->entryfunc(&trace, gops, fregs)) bitmap |= BIT(i); else /* Clear out any saved storage */ @@ -697,12 +707,13 @@ int function_graph_enter(unsigned long ret, unsigned long func, * flag, set that bit always. */ set_bitmap(current, offset, bitmap | BIT(0)); - + ftrace_test_recursion_unlock(bit); return 0; out_ret: current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1; out: current->curr_ret_depth--; + ftrace_test_recursion_unlock(bit); return -EBUSY; } @@ -792,15 +803,12 @@ static struct notifier_block ftrace_suspend_notifier = { .notifier_call = ftrace_suspend_notifier_call, }; -/* fgraph_ret_regs is not defined without CONFIG_FUNCTION_GRAPH_RETVAL */ -struct fgraph_ret_regs; - /* * Send the trace to the ring-buffer. * @return the original return address. */ -static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs, - unsigned long frame_pointer) +static inline unsigned long +__ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointer) { struct ftrace_ret_stack *ret_stack; struct ftrace_graph_ret trace; @@ -818,9 +826,11 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs return (unsigned long)panic; } - trace.rettime = trace_clock_local(); + if (fregs) + ftrace_regs_set_instruction_pointer(fregs, ret); + #ifdef CONFIG_FUNCTION_GRAPH_RETVAL - trace.retval = fgraph_ret_regs_return_value(ret_regs); + trace.retval = ftrace_regs_get_return_value(fregs); #endif bitmap = get_bitmap_bits(current, offset); @@ -828,17 +838,17 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs #ifdef CONFIG_HAVE_STATIC_CALL if (static_branch_likely(&fgraph_do_direct)) { if (test_bit(fgraph_direct_gops->idx, &bitmap)) - static_call(fgraph_retfunc)(&trace, fgraph_direct_gops); + static_call(fgraph_retfunc)(&trace, fgraph_direct_gops, fregs); } else #endif { for_each_set_bit(i, &bitmap, sizeof(bitmap) * BITS_PER_BYTE) { - struct fgraph_ops *gops = fgraph_array[i]; + struct fgraph_ops *gops = READ_ONCE(fgraph_array[i]); if (gops == &fgraph_stub) continue; - gops->retfunc(&trace, gops); + gops->retfunc(&trace, gops, fregs); } } @@ -855,14 +865,14 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs } /* - * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can - * leave only ftrace_return_to_handler(ret_regs). + * After all architecures have selected HAVE_FUNCTION_GRAPH_FREGS, we can + * leave only ftrace_return_to_handler(fregs). */ -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL -unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs) +#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS +unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs) { - return __ftrace_return_to_handler(ret_regs, - fgraph_ret_regs_frame_pointer(ret_regs)); + return __ftrace_return_to_handler(fregs, + ftrace_regs_get_frame_pointer(fregs)); } #else unsigned long ftrace_return_to_handler(unsigned long frame_pointer) @@ -1010,7 +1020,8 @@ void ftrace_graph_sleep_time_control(bool enable) * Simply points to ftrace_stub, but with the proper protocol. * Defined by the linker script in linux/vmlinux.lds.h */ -void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); +void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); /* The callbacks that hook a function */ trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph; @@ -1174,7 +1185,8 @@ void ftrace_graph_exit_task(struct task_struct *t) #ifdef CONFIG_DYNAMIC_FTRACE static int fgraph_pid_func(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = gops->ops.private; int pid; @@ -1188,7 +1200,7 @@ static int fgraph_pid_func(struct ftrace_graph_ent *trace, return 0; } - return gops->saved_func(trace, gops); + return gops->saved_func(trace, gops, fregs); } void fgraph_update_pid_func(void) @@ -1215,7 +1227,7 @@ void fgraph_update_pid_func(void) static int start_graph_tracing(void) { unsigned long **ret_stack_list; - int ret; + int ret, cpu; ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE, sizeof(*ret_stack_list), GFP_KERNEL); @@ -1223,6 +1235,12 @@ static int start_graph_tracing(void) if (!ret_stack_list) return -ENOMEM; + /* The cpu_boot init_task->ret_stack will never be freed */ + for_each_online_cpu(cpu) { + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + } + do { ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9ff018245840..2560b312ad57 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -8,98 +8,224 @@ #include #include #include -#include +#include +#include #include #include +#include + #include "trace.h" -struct fprobe_rethook_node { - struct rethook_node node; - unsigned long entry_ip; - unsigned long entry_parent_ip; - char data[]; -}; +#define FPROBE_IP_HASH_BITS 8 +#define FPROBE_IP_TABLE_SIZE (1 << FPROBE_IP_HASH_BITS) -static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +#define FPROBE_HASH_BITS 6 +#define FPROBE_TABLE_SIZE (1 << FPROBE_HASH_BITS) + +#define SIZE_IN_LONG(x) ((x + sizeof(long) - 1) >> (sizeof(long) == 8 ? 3 : 2)) + +/* + * fprobe_table: hold 'fprobe_hlist::hlist' for checking the fprobe still + * exists. The key is the address of fprobe instance. + * fprobe_ip_table: hold 'fprobe_hlist::array[*]' for searching the fprobe + * instance related to the funciton address. The key is the ftrace IP + * address. + * + * When unregistering the fprobe, fprobe_hlist::fp and fprobe_hlist::array[*].fp + * are set NULL and delete those from both hash tables (by hlist_del_rcu). + * After an RCU grace period, the fprobe_hlist itself will be released. + * + * fprobe_table and fprobe_ip_table can be accessed from either + * - Normal hlist traversal and RCU add/del under 'fprobe_mutex' is held. + * - RCU hlist traversal under disabling preempt + */ +static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE]; +static struct hlist_head fprobe_ip_table[FPROBE_IP_TABLE_SIZE]; +static DEFINE_MUTEX(fprobe_mutex); + +/* + * Find first fprobe in the hlist. It will be iterated twice in the entry + * probe, once for correcting the total required size, the second time is + * calling back the user handlers. + * Thus the hlist in the fprobe_table must be sorted and new probe needs to + * be added *before* the first fprobe. + */ +static struct fprobe_hlist_node *find_first_fprobe_node(unsigned long ip) { - struct fprobe_rethook_node *fpr; - struct rethook_node *rh = NULL; - struct fprobe *fp; - void *entry_data = NULL; - int ret = 0; + struct fprobe_hlist_node *node; + struct hlist_head *head; - fp = container_of(ops, struct fprobe, ops); - - if (fp->exit_handler) { - rh = rethook_try_get(fp->rethook); - if (!rh) { - fp->nmissed++; - return; - } - fpr = container_of(rh, struct fprobe_rethook_node, node); - fpr->entry_ip = ip; - fpr->entry_parent_ip = parent_ip; - if (fp->entry_data_size) - entry_data = fpr->data; + head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; + hlist_for_each_entry_rcu(node, head, hlist, + lockdep_is_held(&fprobe_mutex)) { + if (node->addr == ip) + return node; } + return NULL; +} +NOKPROBE_SYMBOL(find_first_fprobe_node); - if (fp->entry_handler) - ret = fp->entry_handler(fp, ip, parent_ip, ftrace_get_regs(fregs), entry_data); +/* Node insertion and deletion requires the fprobe_mutex */ +static void insert_fprobe_node(struct fprobe_hlist_node *node) +{ + unsigned long ip = node->addr; + struct fprobe_hlist_node *next; + struct hlist_head *head; - /* If entry_handler returns !0, nmissed is not counted. */ - if (rh) { - if (ret) - rethook_recycle(rh); - else - rethook_hook(rh, ftrace_get_regs(fregs), true); + lockdep_assert_held(&fprobe_mutex); + + next = find_first_fprobe_node(ip); + if (next) { + hlist_add_before_rcu(&node->hlist, &next->hlist); + return; } + head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; + hlist_add_head_rcu(&node->hlist, head); } -static void fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +/* Return true if there are synonims */ +static bool delete_fprobe_node(struct fprobe_hlist_node *node) { - struct fprobe *fp; - int bit; - - fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; - - /* recursion detection has to go before any traceable function and - * all functions before this point should be marked as notrace - */ - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; - } - __fprobe_handler(ip, parent_ip, ops, fregs); - ftrace_test_recursion_unlock(bit); + lockdep_assert_held(&fprobe_mutex); + WRITE_ONCE(node->fp, NULL); + hlist_del_rcu(&node->hlist); + return !!find_first_fprobe_node(node->addr); } -NOKPROBE_SYMBOL(fprobe_handler); -static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +/* Check existence of the fprobe */ +static bool is_fprobe_still_exist(struct fprobe *fp) { - struct fprobe *fp; - int bit; + struct hlist_head *head; + struct fprobe_hlist *fph; - fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; - - /* recursion detection has to go before any traceable function and - * all functions called before this point should be marked as notrace - */ - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; + head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)]; + hlist_for_each_entry_rcu(fph, head, hlist, + lockdep_is_held(&fprobe_mutex)) { + if (fph->fp == fp) + return true; } + return false; +} +NOKPROBE_SYMBOL(is_fprobe_still_exist); +static int add_fprobe_hash(struct fprobe *fp) +{ + struct fprobe_hlist *fph = fp->hlist_array; + struct hlist_head *head; + + lockdep_assert_held(&fprobe_mutex); + + if (WARN_ON_ONCE(!fph)) + return -EINVAL; + + if (is_fprobe_still_exist(fp)) + return -EEXIST; + + head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)]; + hlist_add_head_rcu(&fp->hlist_array->hlist, head); + return 0; +} + +static int del_fprobe_hash(struct fprobe *fp) +{ + struct fprobe_hlist *fph = fp->hlist_array; + + lockdep_assert_held(&fprobe_mutex); + + if (WARN_ON_ONCE(!fph)) + return -EINVAL; + + if (!is_fprobe_still_exist(fp)) + return -ENOENT; + + fph->fp = NULL; + hlist_del_rcu(&fph->hlist); + return 0; +} + +#ifdef ARCH_DEFINE_ENCODE_FPROBE_HEADER + +/* The arch should encode fprobe_header info into one unsigned long */ +#define FPROBE_HEADER_SIZE_IN_LONG 1 + +static inline bool write_fprobe_header(unsigned long *stack, + struct fprobe *fp, unsigned int size_words) +{ + if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD || + !arch_fprobe_header_encodable(fp))) + return false; + + *stack = arch_encode_fprobe_header(fp, size_words); + return true; +} + +static inline void read_fprobe_header(unsigned long *stack, + struct fprobe **fp, unsigned int *size_words) +{ + *fp = arch_decode_fprobe_header_fp(*stack); + *size_words = arch_decode_fprobe_header_size(*stack); +} + +#else + +/* Generic fprobe_header */ +struct __fprobe_header { + struct fprobe *fp; + unsigned long size_words; +} __packed; + +#define FPROBE_HEADER_SIZE_IN_LONG SIZE_IN_LONG(sizeof(struct __fprobe_header)) + +static inline bool write_fprobe_header(unsigned long *stack, + struct fprobe *fp, unsigned int size_words) +{ + struct __fprobe_header *fph = (struct __fprobe_header *)stack; + + if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD)) + return false; + + fph->fp = fp; + fph->size_words = size_words; + return true; +} + +static inline void read_fprobe_header(unsigned long *stack, + struct fprobe **fp, unsigned int *size_words) +{ + struct __fprobe_header *fph = (struct __fprobe_header *)stack; + + *fp = fph->fp; + *size_words = fph->size_words; +} + +#endif + +/* + * fprobe shadow stack management: + * Since fprobe shares a single fgraph_ops, it needs to share the stack entry + * among the probes on the same function exit. Note that a new probe can be + * registered before a target function is returning, we can not use the hash + * table to find the corresponding probes. Thus the probe address is stored on + * the shadow stack with its entry data size. + * + */ +static inline int __fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct fprobe *fp, struct ftrace_regs *fregs, + void *data) +{ + if (!fp->entry_handler) + return 0; + + return fp->entry_handler(fp, ip, parent_ip, fregs, data); +} + +static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, + struct fprobe *fp, struct ftrace_regs *fregs, + void *data) +{ + int ret; /* * This user handler is shared with other kprobes and is not expected to be * called recursively. So if any other kprobe handler is running, this will @@ -108,44 +234,183 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, */ if (unlikely(kprobe_running())) { fp->nmissed++; - goto recursion_unlock; + return 0; } kprobe_busy_begin(); - __fprobe_handler(ip, parent_ip, ops, fregs); + ret = __fprobe_handler(ip, parent_ip, fp, fregs, data); kprobe_busy_end(); - -recursion_unlock: - ftrace_test_recursion_unlock(bit); + return ret; } -static void fprobe_exit_handler(struct rethook_node *rh, void *data, - unsigned long ret_ip, struct pt_regs *regs) +static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs) { - struct fprobe *fp = (struct fprobe *)data; - struct fprobe_rethook_node *fpr; - int bit; + struct fprobe_hlist_node *node, *first; + unsigned long *fgraph_data = NULL; + unsigned long func = trace->func; + unsigned long ret_ip; + int reserved_words; + struct fprobe *fp; + int used, ret; - if (!fp || fprobe_disabled(fp)) - return; + if (WARN_ON_ONCE(!fregs)) + return 0; - fpr = container_of(rh, struct fprobe_rethook_node, node); + first = node = find_first_fprobe_node(func); + if (unlikely(!first)) + return 0; + + reserved_words = 0; + hlist_for_each_entry_from_rcu(node, hlist) { + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (!fp || !fp->exit_handler) + continue; + /* + * Since fprobe can be enabled until the next loop, we ignore the + * fprobe's disabled flag in this loop. + */ + reserved_words += + FPROBE_HEADER_SIZE_IN_LONG + SIZE_IN_LONG(fp->entry_data_size); + } + node = first; + if (reserved_words) { + fgraph_data = fgraph_reserve_data(gops->idx, reserved_words * sizeof(long)); + if (unlikely(!fgraph_data)) { + hlist_for_each_entry_from_rcu(node, hlist) { + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (fp && !fprobe_disabled(fp)) + fp->nmissed++; + } + return 0; + } + } /* - * we need to assure no calls to traceable functions in-between the - * end of fprobe_handler and the beginning of fprobe_exit_handler. + * TODO: recursion detection has been done in the fgraph. Thus we need + * to add a callback to increment missed counter. */ - bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip); - if (bit < 0) { - fp->nmissed++; + ret_ip = ftrace_regs_get_return_address(fregs); + used = 0; + hlist_for_each_entry_from_rcu(node, hlist) { + int data_size; + void *data; + + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (!fp || fprobe_disabled(fp)) + continue; + + data_size = fp->entry_data_size; + if (data_size && fp->exit_handler) + data = fgraph_data + used + FPROBE_HEADER_SIZE_IN_LONG; + else + data = NULL; + + if (fprobe_shared_with_kprobes(fp)) + ret = __fprobe_kprobe_handler(func, ret_ip, fp, fregs, data); + else + ret = __fprobe_handler(func, ret_ip, fp, fregs, data); + + /* If entry_handler returns !0, nmissed is not counted but skips exit_handler. */ + if (!ret && fp->exit_handler) { + int size_words = SIZE_IN_LONG(data_size); + + if (write_fprobe_header(&fgraph_data[used], fp, size_words)) + used += FPROBE_HEADER_SIZE_IN_LONG + size_words; + } + } + if (used < reserved_words) + memset(fgraph_data + used, 0, reserved_words - used); + + /* If any exit_handler is set, data must be used. */ + return used != 0; +} +NOKPROBE_SYMBOL(fprobe_entry); + +static void fprobe_return(struct ftrace_graph_ret *trace, + struct fgraph_ops *gops, + struct ftrace_regs *fregs) +{ + unsigned long *fgraph_data = NULL; + unsigned long ret_ip; + struct fprobe *fp; + int size, curr; + int size_words; + + fgraph_data = (unsigned long *)fgraph_retrieve_data(gops->idx, &size); + if (WARN_ON_ONCE(!fgraph_data)) + return; + size_words = SIZE_IN_LONG(size); + ret_ip = ftrace_regs_get_instruction_pointer(fregs); + + preempt_disable(); + + curr = 0; + while (size_words > curr) { + read_fprobe_header(&fgraph_data[curr], &fp, &size); + if (!fp) + break; + curr += FPROBE_HEADER_SIZE_IN_LONG; + if (is_fprobe_still_exist(fp) && !fprobe_disabled(fp)) { + if (WARN_ON_ONCE(curr + size > size_words)) + break; + fp->exit_handler(fp, trace->func, ret_ip, fregs, + size ? fgraph_data + curr : NULL); + } + curr += size; + } + preempt_enable(); +} +NOKPROBE_SYMBOL(fprobe_return); + +static struct fgraph_ops fprobe_graph_ops = { + .entryfunc = fprobe_entry, + .retfunc = fprobe_return, +}; +static int fprobe_graph_active; + +/* Add @addrs to the ftrace filter and register fgraph if needed. */ +static int fprobe_graph_add_ips(unsigned long *addrs, int num) +{ + int ret; + + lockdep_assert_held(&fprobe_mutex); + + ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0); + if (ret) + return ret; + + if (!fprobe_graph_active) { + ret = register_ftrace_graph(&fprobe_graph_ops); + if (WARN_ON_ONCE(ret)) { + ftrace_free_filter(&fprobe_graph_ops.ops); + return ret; + } + } + fprobe_graph_active++; + return 0; +} + +/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */ +static void fprobe_graph_remove_ips(unsigned long *addrs, int num) +{ + lockdep_assert_held(&fprobe_mutex); + + fprobe_graph_active--; + if (!fprobe_graph_active) { + /* Q: should we unregister it ? */ + unregister_ftrace_graph(&fprobe_graph_ops); return; } - fp->exit_handler(fp, fpr->entry_ip, ret_ip, regs, - fp->entry_data_size ? (void *)fpr->data : NULL); - ftrace_test_recursion_unlock(bit); + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } -NOKPROBE_SYMBOL(fprobe_exit_handler); static int symbols_cmp(const void *a, const void *b) { @@ -175,53 +440,97 @@ static unsigned long *get_ftrace_locations(const char **syms, int num) return ERR_PTR(-ENOENT); } -static void fprobe_init(struct fprobe *fp) +struct filter_match_data { + const char *filter; + const char *notfilter; + size_t index; + size_t size; + unsigned long *addrs; +}; + +static int filter_match_callback(void *data, const char *name, unsigned long addr) { - fp->nmissed = 0; - if (fprobe_shared_with_kprobes(fp)) - fp->ops.func = fprobe_kprobe_handler; - else - fp->ops.func = fprobe_handler; - fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS; + struct filter_match_data *match = data; + + if (!glob_match(match->filter, name) || + (match->notfilter && glob_match(match->notfilter, name))) + return 0; + + if (!ftrace_location(addr)) + return 0; + + if (match->addrs) + match->addrs[match->index] = addr; + + match->index++; + return match->index == match->size; } -static int fprobe_init_rethook(struct fprobe *fp, int num) +/* + * Make IP list from the filter/no-filter glob patterns. + * Return the number of matched symbols, or -ENOENT. + */ +static int ip_list_from_filter(const char *filter, const char *notfilter, + unsigned long *addrs, size_t size) { - int size; + struct filter_match_data match = { .filter = filter, .notfilter = notfilter, + .index = 0, .size = size, .addrs = addrs}; + int ret; - if (!fp->exit_handler) { - fp->rethook = NULL; - return 0; - } + ret = kallsyms_on_each_symbol(filter_match_callback, &match); + if (ret < 0) + return ret; + ret = module_kallsyms_on_each_symbol(NULL, filter_match_callback, &match); + if (ret < 0) + return ret; - /* Initialize rethook if needed */ - if (fp->nr_maxactive) - num = fp->nr_maxactive; - else - num *= num_possible_cpus() * 2; - if (num <= 0) - return -EINVAL; - - size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size; - - /* Initialize rethook */ - fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num); - if (IS_ERR(fp->rethook)) - return PTR_ERR(fp->rethook); - - return 0; + return match.index ?: -ENOENT; } static void fprobe_fail_cleanup(struct fprobe *fp) { - if (!IS_ERR_OR_NULL(fp->rethook)) { - /* Don't need to cleanup rethook->handler because this is not used. */ - rethook_free(fp->rethook); - fp->rethook = NULL; - } - ftrace_free_filter(&fp->ops); + kfree(fp->hlist_array); + fp->hlist_array = NULL; } +/* Initialize the fprobe data structure. */ +static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num) +{ + struct fprobe_hlist *hlist_array; + unsigned long addr; + int size, i; + + if (!fp || !addrs || num <= 0) + return -EINVAL; + + size = ALIGN(fp->entry_data_size, sizeof(long)); + if (size > MAX_FPROBE_DATA_SIZE) + return -E2BIG; + fp->entry_data_size = size; + + hlist_array = kzalloc(struct_size(hlist_array, array, num), GFP_KERNEL); + if (!hlist_array) + return -ENOMEM; + + fp->nmissed = 0; + + hlist_array->size = num; + fp->hlist_array = hlist_array; + hlist_array->fp = fp; + for (i = 0; i < num; i++) { + hlist_array->array[i].fp = fp; + addr = ftrace_location(addrs[i]); + if (!addr) { + fprobe_fail_cleanup(fp); + return -ENOENT; + } + hlist_array->array[i].addr = addr; + } + return 0; +} + +#define FPROBE_IPS_MAX INT_MAX + /** * register_fprobe() - Register fprobe to ftrace by pattern. * @fp: A fprobe data structure to be registered. @@ -235,46 +544,24 @@ static void fprobe_fail_cleanup(struct fprobe *fp) */ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter) { - struct ftrace_hash *hash; - unsigned char *str; - int ret, len; + unsigned long *addrs; + int ret; if (!fp || !filter) return -EINVAL; - fprobe_init(fp); - - len = strlen(filter); - str = kstrdup(filter, GFP_KERNEL); - ret = ftrace_set_filter(&fp->ops, str, len, 0); - kfree(str); - if (ret) + ret = ip_list_from_filter(filter, notfilter, NULL, FPROBE_IPS_MAX); + if (ret < 0) return ret; - if (notfilter) { - len = strlen(notfilter); - str = kstrdup(notfilter, GFP_KERNEL); - ret = ftrace_set_notrace(&fp->ops, str, len, 0); - kfree(str); - if (ret) - goto out; - } + addrs = kcalloc(ret, sizeof(unsigned long), GFP_KERNEL); + if (!addrs) + return -ENOMEM; + ret = ip_list_from_filter(filter, notfilter, addrs, ret); + if (ret > 0) + ret = register_fprobe_ips(fp, addrs, ret); - /* TODO: - * correctly calculate the total number of filtered symbols - * from both filter and notfilter. - */ - hash = rcu_access_pointer(fp->ops.local_hash.filter_hash); - if (WARN_ON_ONCE(!hash)) - goto out; - - ret = fprobe_init_rethook(fp, (int)hash->count); - if (!ret) - ret = register_ftrace_function(&fp->ops); - -out: - if (ret) - fprobe_fail_cleanup(fp); + kfree(addrs); return ret; } EXPORT_SYMBOL_GPL(register_fprobe); @@ -282,7 +569,7 @@ EXPORT_SYMBOL_GPL(register_fprobe); /** * register_fprobe_ips() - Register fprobe to ftrace by address. * @fp: A fprobe data structure to be registered. - * @addrs: An array of target ftrace location addresses. + * @addrs: An array of target function address. * @num: The number of entries of @addrs. * * Register @fp to ftrace for enabling the probe on the address given by @addrs. @@ -294,23 +581,27 @@ EXPORT_SYMBOL_GPL(register_fprobe); */ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) { - int ret; + struct fprobe_hlist *hlist_array; + int ret, i; - if (!fp || !addrs || num <= 0) - return -EINVAL; - - fprobe_init(fp); - - ret = ftrace_set_filter_ips(&fp->ops, addrs, num, 0, 0); + ret = fprobe_init(fp, addrs, num); if (ret) return ret; - ret = fprobe_init_rethook(fp, num); - if (!ret) - ret = register_ftrace_function(&fp->ops); + mutex_lock(&fprobe_mutex); + + hlist_array = fp->hlist_array; + ret = fprobe_graph_add_ips(addrs, num); + if (!ret) { + add_fprobe_hash(fp); + for (i = 0; i < hlist_array->size; i++) + insert_fprobe_node(&hlist_array->array[i]); + } + mutex_unlock(&fprobe_mutex); if (ret) fprobe_fail_cleanup(fp); + return ret; } EXPORT_SYMBOL_GPL(register_fprobe_ips); @@ -348,14 +639,13 @@ EXPORT_SYMBOL_GPL(register_fprobe_syms); bool fprobe_is_registered(struct fprobe *fp) { - if (!fp || (fp->ops.saved_func != fprobe_handler && - fp->ops.saved_func != fprobe_kprobe_handler)) + if (!fp || !fp->hlist_array) return false; return true; } /** - * unregister_fprobe() - Unregister fprobe from ftrace + * unregister_fprobe() - Unregister fprobe. * @fp: A fprobe data structure to be unregistered. * * Unregister fprobe (and remove ftrace hooks from the function entries). @@ -364,23 +654,41 @@ bool fprobe_is_registered(struct fprobe *fp) */ int unregister_fprobe(struct fprobe *fp) { - int ret; + struct fprobe_hlist *hlist_array; + unsigned long *addrs = NULL; + int ret = 0, i, count; - if (!fprobe_is_registered(fp)) - return -EINVAL; + mutex_lock(&fprobe_mutex); + if (!fp || !is_fprobe_still_exist(fp)) { + ret = -EINVAL; + goto out; + } - if (!IS_ERR_OR_NULL(fp->rethook)) - rethook_stop(fp->rethook); + hlist_array = fp->hlist_array; + addrs = kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL); + if (!addrs) { + ret = -ENOMEM; /* TODO: Fallback to one-by-one loop */ + goto out; + } - ret = unregister_ftrace_function(&fp->ops); - if (ret < 0) - return ret; + /* Remove non-synonim ips from table and hash */ + count = 0; + for (i = 0; i < hlist_array->size; i++) { + if (!delete_fprobe_node(&hlist_array->array[i])) + addrs[count++] = hlist_array->array[i].addr; + } + del_fprobe_hash(fp); - if (!IS_ERR_OR_NULL(fp->rethook)) - rethook_free(fp->rethook); + if (count) + fprobe_graph_remove_ips(addrs, count); - ftrace_free_filter(&fp->ops); + kfree_rcu(hlist_array, rcu); + fp->hlist_array = NULL; +out: + mutex_unlock(&fprobe_mutex); + + kfree(addrs); return ret; } EXPORT_SYMBOL_GPL(unregister_fprobe); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9b17efb1a87d..728ecda6e8d4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -536,24 +536,21 @@ static int function_stat_show(struct seq_file *m, void *v) { struct ftrace_profile *rec = v; char str[KSYM_SYMBOL_LEN]; - int ret = 0; #ifdef CONFIG_FUNCTION_GRAPH_TRACER static struct trace_seq s; unsigned long long avg; unsigned long long stddev; #endif - mutex_lock(&ftrace_profile_lock); + guard(mutex)(&ftrace_profile_lock); /* we raced with function_profile_reset() */ - if (unlikely(rec->counter == 0)) { - ret = -EBUSY; - goto out; - } + if (unlikely(rec->counter == 0)) + return -EBUSY; #ifdef CONFIG_FUNCTION_GRAPH_TRACER avg = div64_ul(rec->time, rec->counter); if (tracing_thresh && (avg < tracing_thresh)) - goto out; + return 0; #endif kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); @@ -590,10 +587,8 @@ static int function_stat_show(struct seq_file *m, void *v) trace_print_seq(m, &s); #endif seq_putc(m, '\n'); -out: - mutex_unlock(&ftrace_profile_lock); - return ret; + return 0; } static void ftrace_profile_reset(struct ftrace_profile_stat *stat) @@ -789,27 +784,24 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; - unsigned long flags; if (!ftrace_profile_enabled) return; - local_irq_save(flags); + guard(preempt_notrace)(); stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) - goto out; + return; rec = ftrace_find_profiled_func(stat, ip); if (!rec) { rec = ftrace_profile_alloc(stat, ip); if (!rec) - goto out; + return; } rec->counter++; - out: - local_irq_restore(flags); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -827,7 +819,8 @@ struct profile_fgraph_data { }; static int profile_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct profile_fgraph_data *profile_data; @@ -849,26 +842,27 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace, } static void profile_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct profile_fgraph_data *profile_data; struct ftrace_profile_stat *stat; unsigned long long calltime; unsigned long long rettime = trace_clock_local(); struct ftrace_profile *rec; - unsigned long flags; int size; - local_irq_save(flags); + guard(preempt_notrace)(); + stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) - goto out; + return; profile_data = fgraph_retrieve_data(gops->idx, &size); /* If the calltime was zero'd ignore it */ if (!profile_data || !profile_data->calltime) - goto out; + return; calltime = rettime - profile_data->calltime; @@ -896,22 +890,16 @@ static void profile_graph_return(struct ftrace_graph_ret *trace, rec->time += calltime; rec->time_squared += calltime * calltime; } - - out: - local_irq_restore(flags); } static struct fgraph_ops fprofiler_ops = { - .ops = { - .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_OPS_HASH(fprofiler_ops.ops) - }, .entryfunc = &profile_graph_entry, .retfunc = &profile_graph_return, }; static int register_ftrace_profiler(void) { + ftrace_ops_set_global_filter(&fprofiler_ops.ops); return register_ftrace_graph(&fprofiler_ops); } @@ -922,12 +910,11 @@ static void unregister_ftrace_profiler(void) #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, - .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_OPS_HASH(ftrace_profile_ops) }; static int register_ftrace_profiler(void) { + ftrace_ops_set_global_filter(&ftrace_profile_ops); return register_ftrace_function(&ftrace_profile_ops); } @@ -950,20 +937,16 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, val = !!val; - mutex_lock(&ftrace_profile_lock); + guard(mutex)(&ftrace_profile_lock); if (ftrace_profile_enabled ^ val) { if (val) { ret = ftrace_profile_init(); - if (ret < 0) { - cnt = ret; - goto out; - } + if (ret < 0) + return ret; ret = register_ftrace_profiler(); - if (ret < 0) { - cnt = ret; - goto out; - } + if (ret < 0) + return ret; ftrace_profile_enabled = 1; } else { ftrace_profile_enabled = 0; @@ -974,8 +957,6 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, unregister_ftrace_profiler(); } } - out: - mutex_unlock(&ftrace_profile_lock); *ppos += cnt; @@ -1675,14 +1656,12 @@ unsigned long ftrace_location(unsigned long ip) loc = ftrace_location_range(ip, ip); if (!loc) { if (!kallsyms_lookup_size_offset(ip, &size, &offset)) - goto out; + return 0; /* map sym+0 to __fentry__ */ if (!offset) loc = ftrace_location_range(ip, ip + size - 1); } - -out: return loc; } @@ -2077,7 +2056,7 @@ rollback: continue; if (rec == end) - goto err_out; + return -EBUSY; in_old = !!ftrace_lookup_ip(old_hash, rec->ip); in_new = !!ftrace_lookup_ip(new_hash, rec->ip); @@ -2090,7 +2069,6 @@ rollback: rec->flags |= FTRACE_FL_IPMODIFY; } while_for_each_ftrace_rec(); -err_out: return -EBUSY; } @@ -4930,23 +4908,6 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops, return __ftrace_hash_move_and_update_ops(ops, orig_hash, hash, enable); } -static bool module_exists(const char *module) -{ - /* All modules have the symbol __this_module */ - static const char this_mod[] = "__this_module"; - char modname[MAX_PARAM_PREFIX_LEN + sizeof(this_mod) + 2]; - unsigned long val; - int n; - - n = snprintf(modname, sizeof(modname), "%s:%s", module, this_mod); - - if (n > sizeof(modname) - 1) - return false; - - val = module_kallsyms_lookup_name(modname); - return val != 0; -} - static int cache_mod(struct trace_array *tr, const char *func, char *module, int enable) { @@ -4986,10 +4947,6 @@ static int cache_mod(struct trace_array *tr, return ftrace_add_mod(tr, func, module, enable); } -static int -ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, - int reset, int enable); - #ifdef CONFIG_MODULES static void process_mod_list(struct list_head *head, struct ftrace_ops *ops, char *mod, bool enable) @@ -5619,20 +5576,15 @@ static DEFINE_MUTEX(ftrace_cmd_mutex); __init int register_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p; - int ret = 0; - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); list_for_each_entry(p, &ftrace_commands, list) { - if (strcmp(cmd->name, p->name) == 0) { - ret = -EBUSY; - goto out_unlock; - } + if (strcmp(cmd->name, p->name) == 0) + return -EBUSY; } list_add(&cmd->list, &ftrace_commands); - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return 0; } /* @@ -5642,20 +5594,17 @@ __init int register_ftrace_command(struct ftrace_func_command *cmd) __init int unregister_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p, *n; - int ret = -ENODEV; - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); + list_for_each_entry_safe(p, n, &ftrace_commands, list) { if (strcmp(cmd->name, p->name) == 0) { - ret = 0; list_del_init(&p->list); - goto out_unlock; + return 0; } } - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return -ENODEV; } static int ftrace_process_regex(struct ftrace_iterator *iter, @@ -5665,7 +5614,7 @@ static int ftrace_process_regex(struct ftrace_iterator *iter, struct trace_array *tr = iter->ops->private; char *func, *command, *next = buff; struct ftrace_func_command *p; - int ret = -EINVAL; + int ret; func = strsep(&next, ":"); @@ -5682,17 +5631,14 @@ static int ftrace_process_regex(struct ftrace_iterator *iter, command = strsep(&next, ":"); - mutex_lock(&ftrace_cmd_mutex); - list_for_each_entry(p, &ftrace_commands, list) { - if (strcmp(p->name, command) == 0) { - ret = p->func(tr, hash, func, command, next, enable); - goto out_unlock; - } - } - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); - return ret; + list_for_each_entry(p, &ftrace_commands, list) { + if (strcmp(p->name, command) == 0) + return p->func(tr, hash, func, command, next, enable); + } + + return -EINVAL; } static ssize_t @@ -5726,12 +5672,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, parser->idx, enable); trace_parser_clear(parser); if (ret < 0) - goto out; + return ret; } - ret = read; - out: - return ret; + return read; } ssize_t @@ -5792,7 +5736,7 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long *ips, static int ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, unsigned long *ips, unsigned int cnt, - int remove, int reset, int enable) + int remove, int reset, int enable, char *mod) { struct ftrace_hash **orig_hash; struct ftrace_hash *hash; @@ -5818,7 +5762,15 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, goto out_regex_unlock; } - if (buf && !ftrace_match_records(hash, buf, len)) { + if (buf && !match_records(hash, buf, len, mod)) { + /* If this was for a module and nothing was enabled, flag it */ + if (mod) + (*orig_hash)->flags |= FTRACE_HASH_FL_MOD; + + /* + * Even if it is a mod, return error to let caller know + * nothing was added + */ ret = -EINVAL; goto out_regex_unlock; } @@ -5843,7 +5795,7 @@ static int ftrace_set_addr(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt, int remove, int reset, int enable) { - return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable); + return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable, NULL); } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS @@ -6221,7 +6173,38 @@ static int ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, int reset, int enable) { - return ftrace_set_hash(ops, buf, len, NULL, 0, 0, reset, enable); + char *mod = NULL, *func, *command, *next = buf; + char *tmp __free(kfree) = NULL; + struct trace_array *tr = ops->private; + int ret; + + func = strsep(&next, ":"); + + /* This can also handle :mod: parsing */ + if (next) { + if (!tr) + return -EINVAL; + + command = strsep(&next, ":"); + if (strcmp(command, "mod") != 0) + return -EINVAL; + + mod = next; + len = command - func; + /* Save the original func as ftrace_set_hash() can modify it */ + tmp = kstrdup(func, GFP_KERNEL); + } + + ret = ftrace_set_hash(ops, func, len, NULL, 0, 0, reset, enable, mod); + + if (tr && mod && ret < 0) { + /* Did tmp fail to allocate? */ + if (!tmp) + return -ENOMEM; + ret = cache_mod(tr, tmp, mod, enable); + } + + return ret; } /** @@ -6385,6 +6368,14 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable) ftrace_ops_init(ops); + /* The trace_array is needed for caching module function filters */ + if (!ops->private) { + struct trace_array *tr = trace_get_global_array(); + + ops->private = tr; + ftrace_init_trace_array(tr); + } + while (buf) { func = strsep(&buf, ","); ftrace_set_regex(ops, func, strlen(func), 0, enable); @@ -7818,9 +7809,14 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) void ftrace_init_trace_array(struct trace_array *tr) { + if (tr->flags & TRACE_ARRAY_FL_MOD_INIT) + return; + INIT_LIST_HEAD(&tr->func_probes); INIT_LIST_HEAD(&tr->mod_trace); INIT_LIST_HEAD(&tr->mod_notrace); + + tr->flags |= TRACE_ARRAY_FL_MOD_INIT; } #else @@ -7849,7 +7845,8 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) __init void ftrace_init_global_array_ops(struct trace_array *tr) { tr->ops = &global_ops; - tr->ops->private = tr; + if (!global_ops.private) + global_ops.private = tr; ftrace_init_trace_array(tr); init_array_fgraph_ops(tr, tr->ops); } @@ -8291,7 +8288,7 @@ pid_write(struct file *filp, const char __user *ubuf, if (!cnt) return 0; - mutex_lock(&ftrace_lock); + guard(mutex)(&ftrace_lock); switch (type) { case TRACE_PIDS: @@ -8307,14 +8304,13 @@ pid_write(struct file *filp, const char __user *ubuf, lockdep_is_held(&ftrace_lock)); break; default: - ret = -EINVAL; WARN_ON_ONCE(1); - goto out; + return -EINVAL; } ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); if (ret < 0) - goto out; + return ret; switch (type) { case TRACE_PIDS: @@ -8343,11 +8339,8 @@ pid_write(struct file *filp, const char __user *ubuf, ftrace_update_pid_func(); ftrace_startup_all(0); - out: - mutex_unlock(&ftrace_lock); - if (ret > 0) - *ppos += ret; + *ppos += ret; return ret; } @@ -8750,17 +8743,17 @@ static int ftrace_enable_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - int ret = -ENODEV; + int ret; - mutex_lock(&ftrace_lock); + guard(mutex)(&ftrace_lock); if (unlikely(ftrace_disabled)) - goto out; + return -ENODEV; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) - goto out; + return ret; if (ftrace_enabled) { @@ -8774,8 +8767,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, } else { if (is_permanent_ops_registered()) { ftrace_enabled = true; - ret = -EBUSY; - goto out; + return -EBUSY; } /* stopping ftrace calls (just send to ftrace_stub) */ @@ -8785,12 +8777,10 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, } last_ftrace_enabled = !!ftrace_enabled; - out: - mutex_unlock(&ftrace_lock); - return ret; + return 0; } -static struct ctl_table ftrace_sysctls[] = { +static const struct ctl_table ftrace_sysctls[] = { { .procname = "ftrace_enabled", .data = &ftrace_enabled, diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c index 4966e6bbdf6f..c62b9b3cfb3d 100644 --- a/kernel/trace/pid_list.c +++ b/kernel/trace/pid_list.c @@ -414,7 +414,7 @@ struct trace_pid_list *trace_pid_list_alloc(void) int i; /* According to linux/thread.h, pids can be no bigger that 30 bits */ - WARN_ON_ONCE(pid_max > (1 << 30)); + WARN_ON_ONCE(init_pid_ns.pid_max > (1 << 30)); pid_list = kzalloc(sizeof(*pid_list), GFP_KERNEL); if (!pid_list) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7e257e855dd1..b8e0ae15ca5b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4398,8 +4398,13 @@ rb_reserve_next_event(struct trace_buffer *buffer, int nr_loops = 0; int add_ts_default; - /* ring buffer does cmpxchg, make sure it is safe in NMI context */ - if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && + /* + * ring buffer does cmpxchg as well as atomic64 operations + * (which some archs use locking for atomic64), make sure this + * is safe in NMI context + */ + if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) || + IS_ENABLED(CONFIG_GENERIC_ATOMIC64)) && (unlikely(in_nmi()))) { return NULL; } @@ -4682,40 +4687,22 @@ int ring_buffer_write(struct trace_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_write); +/* + * The total entries in the ring buffer is the running counter + * of entries entered into the ring buffer, minus the sum of + * the entries read from the ring buffer and the number of + * entries that were overwritten. + */ +static inline unsigned long +rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) +{ + return local_read(&cpu_buffer->entries) - + (local_read(&cpu_buffer->overrun) + cpu_buffer->read); +} + static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) { - struct buffer_page *reader = cpu_buffer->reader_page; - struct buffer_page *head = rb_set_head_page(cpu_buffer); - struct buffer_page *commit = cpu_buffer->commit_page; - - /* In case of error, head will be NULL */ - if (unlikely(!head)) - return true; - - /* Reader should exhaust content in reader page */ - if (reader->read != rb_page_size(reader)) - return false; - - /* - * If writers are committing on the reader page, knowing all - * committed content has been read, the ring buffer is empty. - */ - if (commit == reader) - return true; - - /* - * If writers are committing on a page other than reader page - * and head page, there should always be content to read. - */ - if (commit != head) - return false; - - /* - * Writers are committing on the head page, we just need - * to care about there're committed data, and the reader will - * swap reader page with head page when it is to read data. - */ - return rb_page_commit(commit) == 0; + return !rb_num_of_entries(cpu_buffer); } /** @@ -4861,19 +4848,6 @@ void ring_buffer_record_enable_cpu(struct trace_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu); -/* - * The total entries in the ring buffer is the running counter - * of entries entered into the ring buffer, minus the sum of - * the entries read from the ring buffer and the number of - * entries that were overwritten. - */ -static inline unsigned long -rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) -{ - return local_read(&cpu_buffer->entries) - - (local_read(&cpu_buffer->overrun) + cpu_buffer->read); -} - /** * ring_buffer_oldest_event_ts - get the oldest event timestamp from the buffer * @buffer: The ring buffer @@ -7019,7 +6993,11 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, lockdep_assert_held(&cpu_buffer->mapping_lock); nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */ - nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; /* + meta-page */ + nr_pages = ((nr_subbufs + 1) << subbuf_order); /* + meta-page */ + if (nr_pages <= pgoff) + return -EINVAL; + + nr_pages -= pgoff; nr_vma_pages = vma_pages(vma); if (!nr_vma_pages || nr_vma_pages > nr_pages) @@ -7055,7 +7033,7 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, } while (p < nr_pages) { - struct page *page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]); + struct page *page; int off = 0; if (WARN_ON_ONCE(s >= nr_subbufs)) { @@ -7063,6 +7041,8 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, goto out; } + page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]); + for (; off < (1 << (subbuf_order)); off++, page++) { if (p >= nr_pages) break; diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 831779607e84..8226352a0062 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -25,30 +25,9 @@ menuconfig RV For further information, see: Documentation/trace/rv/runtime-verification.rst -config RV_MON_WIP - depends on RV - depends on PREEMPT_TRACER - select DA_MON_EVENTS_IMPLICIT - bool "wip monitor" - help - Enable wip (wakeup in preemptive) sample monitor that illustrates - the usage of per-cpu monitors, and one limitation of the - preempt_disable/enable events. - - For further information, see: - Documentation/trace/rv/monitor_wip.rst - -config RV_MON_WWNR - depends on RV - select DA_MON_EVENTS_ID - bool "wwnr monitor" - help - Enable wwnr (wakeup while not running) sample monitor, this is a - sample monitor that illustrates the usage of per-task monitor. - The model is borken on purpose: it serves to test reactors. - - For further information, see: - Documentation/trace/rv/monitor_wwnr.rst +source "kernel/trace/rv/monitors/wip/Kconfig" +source "kernel/trace/rv/monitors/wwnr/Kconfig" +# Add new monitors here config RV_REACTORS bool "Runtime verification reactors" diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index 963d14875b45..188b64668e1f 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -1,8 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 +ccflags-y += -I $(src) # needed for trace events + obj-$(CONFIG_RV) += rv.o obj-$(CONFIG_RV_MON_WIP) += monitors/wip/wip.o obj-$(CONFIG_RV_MON_WWNR) += monitors/wwnr/wwnr.o +# Add new monitors here obj-$(CONFIG_RV_REACTORS) += rv_reactors.o obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o obj-$(CONFIG_RV_REACT_PANIC) += reactor_panic.o diff --git a/kernel/trace/rv/monitors/wip/Kconfig b/kernel/trace/rv/monitors/wip/Kconfig new file mode 100644 index 000000000000..3ef664b5cd90 --- /dev/null +++ b/kernel/trace/rv/monitors/wip/Kconfig @@ -0,0 +1,12 @@ +config RV_MON_WIP + depends on RV + depends on PREEMPT_TRACER + select DA_MON_EVENTS_IMPLICIT + bool "wip monitor" + help + Enable wip (wakeup in preemptive) sample monitor that illustrates + the usage of per-cpu monitors, and one limitation of the + preempt_disable/enable events. + + For further information, see: + Documentation/trace/rv/monitor_wip.rst diff --git a/kernel/trace/rv/monitors/wip/wip.c b/kernel/trace/rv/monitors/wip/wip.c index b2b49a27e886..db7389157c87 100644 --- a/kernel/trace/rv/monitors/wip/wip.c +++ b/kernel/trace/rv/monitors/wip/wip.c @@ -10,7 +10,7 @@ #define MODULE_NAME "wip" -#include +#include #include #include diff --git a/kernel/trace/rv/monitors/wip/wip_trace.h b/kernel/trace/rv/monitors/wip/wip_trace.h new file mode 100644 index 000000000000..aa2162f47a4c --- /dev/null +++ b/kernel/trace/rv/monitors/wip/wip_trace.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_WIP +DEFINE_EVENT(event_da_monitor, event_wip, + TP_PROTO(char *state, char *event, char *next_state, bool final_state), + TP_ARGS(state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor, error_wip, + TP_PROTO(char *state, char *event), + TP_ARGS(state, event)); +#endif /* CONFIG_RV_MON_WIP */ diff --git a/kernel/trace/rv/monitors/wwnr/Kconfig b/kernel/trace/rv/monitors/wwnr/Kconfig new file mode 100644 index 000000000000..ee741aa6d6b8 --- /dev/null +++ b/kernel/trace/rv/monitors/wwnr/Kconfig @@ -0,0 +1,11 @@ +config RV_MON_WWNR + depends on RV + select DA_MON_EVENTS_ID + bool "wwnr monitor" + help + Enable wwnr (wakeup while not running) sample monitor, this is a + sample monitor that illustrates the usage of per-task monitor. + The model is borken on purpose: it serves to test reactors. + + For further information, see: + Documentation/trace/rv/monitor_wwnr.rst diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.c b/kernel/trace/rv/monitors/wwnr/wwnr.c index 0e43dd2db685..3b16994a9984 100644 --- a/kernel/trace/rv/monitors/wwnr/wwnr.c +++ b/kernel/trace/rv/monitors/wwnr/wwnr.c @@ -10,7 +10,7 @@ #define MODULE_NAME "wwnr" -#include +#include #include #include "wwnr.h" diff --git a/kernel/trace/rv/monitors/wwnr/wwnr_trace.h b/kernel/trace/rv/monitors/wwnr/wwnr_trace.h new file mode 100644 index 000000000000..fc97ec7476ad --- /dev/null +++ b/kernel/trace/rv/monitors/wwnr/wwnr_trace.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_WWNR +/* id is the pid of the task */ +DEFINE_EVENT(event_da_monitor_id, event_wwnr, + TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), + TP_ARGS(id, state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor_id, error_wwnr, + TP_PROTO(int id, char *state, char *event), + TP_ARGS(id, state, event)); +#endif /* CONFIG_RV_MON_WWNR */ diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 279c70e1bd74..8657fc8806e7 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -145,7 +145,7 @@ #ifdef CONFIG_DA_MON_EVENTS #define CREATE_TRACE_POINTS -#include +#include #endif #include "rv.h" diff --git a/include/trace/events/rv.h b/kernel/trace/rv/rv_trace.h similarity index 79% rename from include/trace/events/rv.h rename to kernel/trace/rv/rv_trace.h index 56592da9301c..5e65097423ba 100644 --- a/include/trace/events/rv.h +++ b/kernel/trace/rv/rv_trace.h @@ -57,15 +57,9 @@ DECLARE_EVENT_CLASS(error_da_monitor, __entry->state) ); -#ifdef CONFIG_RV_MON_WIP -DEFINE_EVENT(event_da_monitor, event_wip, - TP_PROTO(char *state, char *event, char *next_state, bool final_state), - TP_ARGS(state, event, next_state, final_state)); +#include +// Add new monitors based on CONFIG_DA_MON_EVENTS_IMPLICIT here -DEFINE_EVENT(error_da_monitor, error_wip, - TP_PROTO(char *state, char *event), - TP_ARGS(state, event)); -#endif /* CONFIG_RV_MON_WIP */ #endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */ #ifdef CONFIG_DA_MON_EVENTS_ID @@ -123,20 +117,14 @@ DECLARE_EVENT_CLASS(error_da_monitor_id, __entry->state) ); -#ifdef CONFIG_RV_MON_WWNR -/* id is the pid of the task */ -DEFINE_EVENT(event_da_monitor_id, event_wwnr, - TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), - TP_ARGS(id, state, event, next_state, final_state)); - -DEFINE_EVENT(error_da_monitor_id, error_wwnr, - TP_PROTO(int id, char *state, char *event), - TP_ARGS(id, state, event)); -#endif /* CONFIG_RV_MON_WWNR */ +#include +// Add new monitors based on CONFIG_DA_MON_EVENTS_ID here #endif /* CONFIG_DA_MON_EVENTS_ID */ #endif /* _TRACE_RV_H */ /* This part ust be outside protection */ #undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE rv_trace #include diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index be62f0ea1814..1496a5ac33ae 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -535,19 +536,16 @@ LIST_HEAD(ftrace_trace_arrays); int trace_array_get(struct trace_array *this_tr) { struct trace_array *tr; - int ret = -ENODEV; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr == this_tr) { tr->ref++; - ret = 0; - break; + return 0; } } - mutex_unlock(&trace_types_lock); - return ret; + return -ENODEV; } static void __trace_array_put(struct trace_array *this_tr) @@ -1443,22 +1441,20 @@ EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update) { - struct cond_snapshot *cond_snapshot; - int ret = 0; + struct cond_snapshot *cond_snapshot __free(kfree) = + kzalloc(sizeof(*cond_snapshot), GFP_KERNEL); + int ret; - cond_snapshot = kzalloc(sizeof(*cond_snapshot), GFP_KERNEL); if (!cond_snapshot) return -ENOMEM; cond_snapshot->cond_data = cond_data; cond_snapshot->update = update; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); - if (tr->current_trace->use_max_tr) { - ret = -EBUSY; - goto fail_unlock; - } + if (tr->current_trace->use_max_tr) + return -EBUSY; /* * The cond_snapshot can only change to NULL without the @@ -1468,29 +1464,20 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, * do safely with only holding the trace_types_lock and not * having to take the max_lock. */ - if (tr->cond_snapshot) { - ret = -EBUSY; - goto fail_unlock; - } + if (tr->cond_snapshot) + return -EBUSY; ret = tracing_arm_snapshot_locked(tr); if (ret) - goto fail_unlock; + return ret; local_irq_disable(); arch_spin_lock(&tr->max_lock); - tr->cond_snapshot = cond_snapshot; + tr->cond_snapshot = no_free_ptr(cond_snapshot); arch_spin_unlock(&tr->max_lock); local_irq_enable(); - mutex_unlock(&trace_types_lock); - - return ret; - - fail_unlock: - mutex_unlock(&trace_types_lock); - kfree(cond_snapshot); - return ret; + return 0; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable); @@ -2203,10 +2190,10 @@ static __init int init_trace_selftests(void) selftests_can_run = true; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (list_empty(&postponed_selftests)) - goto out; + return 0; pr_info("Running postponed tracer tests:\n"); @@ -2235,9 +2222,6 @@ static __init int init_trace_selftests(void) } tracing_selftest_running = false; - out: - mutex_unlock(&trace_types_lock); - return 0; } core_initcall(init_trace_selftests); @@ -2807,7 +2791,7 @@ int tracepoint_printk_sysctl(const struct ctl_table *table, int write, int save_tracepoint_printk; int ret; - mutex_lock(&tracepoint_printk_mutex); + guard(mutex)(&tracepoint_printk_mutex); save_tracepoint_printk = tracepoint_printk; ret = proc_dointvec(table, write, buffer, lenp, ppos); @@ -2820,16 +2804,13 @@ int tracepoint_printk_sysctl(const struct ctl_table *table, int write, tracepoint_printk = 0; if (save_tracepoint_printk == tracepoint_printk) - goto out; + return ret; if (tracepoint_printk) static_key_enable(&tracepoint_printk_key.key); else static_key_disable(&tracepoint_printk_key.key); - out: - mutex_unlock(&tracepoint_printk_mutex); - return ret; } @@ -3611,17 +3592,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter) } /* Returns true if the string is safe to dereference from an event */ -static bool trace_safe_str(struct trace_iterator *iter, const char *str, - bool star, int len) +static bool trace_safe_str(struct trace_iterator *iter, const char *str) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; - /* Ignore strings with no length */ - if (star && !len) - return true; - /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) @@ -3661,181 +3637,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, return false; } -static DEFINE_STATIC_KEY_FALSE(trace_no_verify); - -static int test_can_verify_check(const char *fmt, ...) -{ - char buf[16]; - va_list ap; - int ret; - - /* - * The verifier is dependent on vsnprintf() modifies the va_list - * passed to it, where it is sent as a reference. Some architectures - * (like x86_32) passes it by value, which means that vsnprintf() - * does not modify the va_list passed to it, and the verifier - * would then need to be able to understand all the values that - * vsnprintf can use. If it is passed by value, then the verifier - * is disabled. - */ - va_start(ap, fmt); - vsnprintf(buf, 16, "%d", ap); - ret = va_arg(ap, int); - va_end(ap); - - return ret; -} - -static void test_can_verify(void) -{ - if (!test_can_verify_check("%d %d", 0, 1)) { - pr_info("trace event string verifier disabled\n"); - static_branch_inc(&trace_no_verify); - } -} - /** - * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer + * ignore_event - Check dereferenced fields while writing to the seq buffer * @iter: The iterator that holds the seq buffer and the event being printed - * @fmt: The format used to print the event - * @ap: The va_list holding the data to print from @fmt. * - * This writes the data into the @iter->seq buffer using the data from - * @fmt and @ap. If the format has a %s, then the source of the string - * is examined to make sure it is safe to print, otherwise it will - * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string - * pointer. + * At boot up, test_event_printk() will flag any event that dereferences + * a string with "%s" that does exist in the ring buffer. It may still + * be valid, as the string may point to a static string in the kernel + * rodata that never gets freed. But if the string pointer is pointing + * to something that was allocated, there's a chance that it can be freed + * by the time the user reads the trace. This would cause a bad memory + * access by the kernel and possibly crash the system. + * + * This function will check if the event has any fields flagged as needing + * to be checked at runtime and perform those checks. + * + * If it is found that a field is unsafe, it will write into the @iter->seq + * a message stating what was found to be unsafe. + * + * @return: true if the event is unsafe and should be ignored, + * false otherwise. */ -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) +bool ignore_event(struct trace_iterator *iter) { - long text_delta = 0; - long data_delta = 0; - const char *p = fmt; - const char *str; - bool good; - int i, j; + struct ftrace_event_field *field; + struct trace_event *trace_event; + struct trace_event_call *event; + struct list_head *head; + struct trace_seq *seq; + const void *ptr; - if (WARN_ON_ONCE(!fmt)) - return; + trace_event = ftrace_find_event(iter->ent->type); - if (static_branch_unlikely(&trace_no_verify)) - goto print; + seq = &iter->seq; - /* - * When the kernel is booted with the tp_printk command line - * parameter, trace events go directly through to printk(). - * It also is checked by this function, but it does not - * have an associated trace_array (tr) for it. - */ - if (iter->tr) { - text_delta = iter->tr->text_delta; - data_delta = iter->tr->data_delta; + if (!trace_event) { + trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); + return true; } - /* Don't bother checking when doing a ftrace_dump() */ - if (iter->fmt == static_fmt_buf) - goto print; + event = container_of(trace_event, struct trace_event_call, event); + if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) + return false; - while (*p) { - bool star = false; - int len = 0; + head = trace_get_fields(event); + if (!head) { + trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", + trace_event_name(event)); + return true; + } - j = 0; + /* Offsets are from the iter->ent that points to the raw event */ + ptr = iter->ent; - /* - * We only care about %s and variants - * as well as %p[sS] if delta is non-zero - */ - for (i = 0; p[i]; i++) { - if (i + 1 >= iter->fmt_size) { - /* - * If we can't expand the copy buffer, - * just print it. - */ - if (!trace_iter_expand_format(iter)) - goto print; - } + list_for_each_entry(field, head, link) { + const char *str; + bool good; - if (p[i] == '\\' && p[i+1]) { - i++; - continue; - } - if (p[i] == '%') { - /* Need to test cases like %08.*s */ - for (j = 1; p[i+j]; j++) { - if (isdigit(p[i+j]) || - p[i+j] == '.') - continue; - if (p[i+j] == '*') { - star = true; - continue; - } - break; - } - if (p[i+j] == 's') - break; - - if (text_delta && p[i+1] == 'p' && - ((p[i+2] == 's' || p[i+2] == 'S'))) - break; - - star = false; - } - j = 0; - } - /* If no %s found then just print normally */ - if (!p[i]) - break; - - /* Copy up to the %s, and print that */ - strncpy(iter->fmt, p, i); - iter->fmt[i] = '\0'; - trace_seq_vprintf(&iter->seq, iter->fmt, ap); - - /* Add delta to %pS pointers */ - if (p[i+1] == 'p') { - unsigned long addr; - char fmt[4]; - - fmt[0] = '%'; - fmt[1] = 'p'; - fmt[2] = p[i+2]; /* Either %ps or %pS */ - fmt[3] = '\0'; - - addr = va_arg(ap, unsigned long); - addr += text_delta; - trace_seq_printf(&iter->seq, fmt, (void *)addr); - - p += i + 3; + if (!field->needs_test) continue; - } - /* - * If iter->seq is full, the above call no longer guarantees - * that ap is in sync with fmt processing, and further calls - * to va_arg() can return wrong positional arguments. - * - * Ensure that ap is no longer used in this case. - */ - if (iter->seq.full) { - p = ""; - break; - } + str = *(const char **)(ptr + field->offset); - if (star) - len = va_arg(ap, int); - - /* The ap now points to the string data of the %s */ - str = va_arg(ap, const char *); - - good = trace_safe_str(iter, str, star, len); - - /* Could be from the last boot */ - if (data_delta && !good) { - str += data_delta; - good = trace_safe_str(iter, str, star, len); - } + good = trace_safe_str(iter, str); /* * If you hit this warning, it is likely that the @@ -3846,44 +3710,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, * instead. See samples/trace_events/trace-events-sample.h * for reference. */ - if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'", - fmt, seq_buf_str(&iter->seq.seq))) { - int ret; - - /* Try to safely read the string */ - if (star) { - if (len + 1 > iter->fmt_size) - len = iter->fmt_size - 1; - if (len < 0) - len = 0; - ret = copy_from_kernel_nofault(iter->fmt, str, len); - iter->fmt[len] = 0; - star = false; - } else { - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); - } - if (ret < 0) - trace_seq_printf(&iter->seq, "(0x%px)", str); - else - trace_seq_printf(&iter->seq, "(0x%px:%s)", - str, iter->fmt); - str = "[UNSAFE-MEMORY]"; - strcpy(iter->fmt, "%s"); - } else { - strncpy(iter->fmt, p + i, j + 1); - iter->fmt[j+1] = '\0'; + if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", + trace_event_name(event), field->name)) { + trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", + trace_event_name(event), field->name); + return true; } - if (star) - trace_seq_printf(&iter->seq, iter->fmt, len, str); - else - trace_seq_printf(&iter->seq, iter->fmt, str); - - p += i + j + 1; } - print: - if (*p) - trace_seq_vprintf(&iter->seq, p, ap); + return false; } const char *trace_event_format(struct trace_iterator *iter, const char *fmt) @@ -4269,6 +4103,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) preempt_model_none() ? "server" : preempt_model_voluntary() ? "desktop" : preempt_model_full() ? "preempt" : + preempt_model_lazy() ? "lazy" : preempt_model_rt() ? "preempt_rt" : "unknown", /* These are reserved for later use */ @@ -4353,6 +4188,15 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) if (event) { if (tr->trace_flags & TRACE_ITER_FIELDS) return print_event_fields(iter, event); + /* + * For TRACE_EVENT() events, the print_fmt is not + * safe to use if the array has delta offsets + * Force printing via the fields. + */ + if ((tr->text_delta || tr->data_delta) && + event->type > __TRACE_LAST_TYPE) + return print_event_fields(iter, event); + return event->funcs->trace(iter, sym_flags, event); } @@ -5225,6 +5069,9 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, cpumask_var_t tracing_cpumask_new; int err; + if (count == 0 || count > KMALLOC_MAX_SIZE) + return -EINVAL; + if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) return -ENOMEM; @@ -5261,7 +5108,8 @@ static int tracing_trace_options_show(struct seq_file *m, void *v) u32 tracer_flags; int i; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); + tracer_flags = tr->current_trace->flags->val; trace_opts = tr->current_trace->flags->opts; @@ -5278,7 +5126,6 @@ static int tracing_trace_options_show(struct seq_file *m, void *v) else seq_printf(m, "no%s\n", trace_opts[i].name); } - mutex_unlock(&trace_types_lock); return 0; } @@ -5671,6 +5518,8 @@ static const char readme_msg[] = "\t efield: For event probes ('e' types), the field is on of the fields\n" "\t of the /.\n" #endif + " set_event\t\t- Enables events by name written into it\n" + "\t\t\t Can enable module events via: :mod:\n" " events/\t\t- Directory containing all trace event subsystems:\n" " enable\t\t- Write 0/1 to enable/disable tracing of all events\n" " events//\t- Directory containing all trace events for :\n" @@ -5943,7 +5792,7 @@ trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, return; } - mutex_lock(&trace_eval_mutex); + guard(mutex)(&trace_eval_mutex); if (!trace_eval_maps) trace_eval_maps = map_array; @@ -5967,8 +5816,6 @@ trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, map_array++; } memset(map_array, 0, sizeof(*map_array)); - - mutex_unlock(&trace_eval_mutex); } static void trace_create_eval_file(struct dentry *d_tracer) @@ -6132,23 +5979,18 @@ ssize_t tracing_resize_ring_buffer(struct trace_array *tr, { int ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (cpu_id != RING_BUFFER_ALL_CPUS) { /* make sure, this cpu is enabled in the mask */ - if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) { - ret = -EINVAL; - goto out; - } + if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) + return -EINVAL; } ret = __tracing_resize_ring_buffer(tr, size, cpu_id); if (ret < 0) ret = -ENOMEM; -out: - mutex_unlock(&trace_types_lock); - return ret; } @@ -6240,9 +6082,9 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) #ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; #endif - int ret = 0; + int ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); update_last_data(tr); @@ -6250,7 +6092,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); if (ret < 0) - goto out; + return ret; ret = 0; } @@ -6258,43 +6100,37 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (strcmp(t->name, buf) == 0) break; } - if (!t) { - ret = -EINVAL; - goto out; - } + if (!t) + return -EINVAL; + if (t == tr->current_trace) - goto out; + return 0; #ifdef CONFIG_TRACER_SNAPSHOT if (t->use_max_tr) { local_irq_disable(); arch_spin_lock(&tr->max_lock); - if (tr->cond_snapshot) - ret = -EBUSY; + ret = tr->cond_snapshot ? -EBUSY : 0; arch_spin_unlock(&tr->max_lock); local_irq_enable(); if (ret) - goto out; + return ret; } #endif /* Some tracers won't work on kernel command line */ if (system_state < SYSTEM_RUNNING && t->noboot) { pr_warn("Tracer '%s' is not allowed on command line, ignored\n", t->name); - goto out; + return -EINVAL; } /* Some tracers are only allowed for the top level buffer */ - if (!trace_ok_for_array(t, tr)) { - ret = -EINVAL; - goto out; - } + if (!trace_ok_for_array(t, tr)) + return -EINVAL; /* If trace pipe files are being read, we can't change the tracer */ - if (tr->trace_ref) { - ret = -EBUSY; - goto out; - } + if (tr->trace_ref) + return -EBUSY; trace_branch_disable(); @@ -6325,7 +6161,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (!had_max_tr && t->use_max_tr) { ret = tracing_arm_snapshot_locked(tr); if (ret) - goto out; + return ret; } #else tr->current_trace = &nop_trace; @@ -6338,17 +6174,15 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (t->use_max_tr) tracing_disarm_snapshot(tr); #endif - goto out; + return ret; } } tr->current_trace = t; tr->current_trace->enabled++; trace_branch_enable(tr); - out: - mutex_unlock(&trace_types_lock); - return ret; + return 0; } static ssize_t @@ -6426,22 +6260,18 @@ tracing_thresh_write(struct file *filp, const char __user *ubuf, struct trace_array *tr = filp->private_data; int ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); ret = tracing_nsecs_write(&tracing_thresh, ubuf, cnt, ppos); if (ret < 0) - goto out; + return ret; if (tr->current_trace->update_thresh) { ret = tr->current_trace->update_thresh(tr); if (ret < 0) - goto out; + return ret; } - ret = cnt; -out: - mutex_unlock(&trace_types_lock); - - return ret; + return cnt; } #ifdef CONFIG_TRACER_MAX_TRACE @@ -6660,31 +6490,29 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, * This is just a matter of traces coherency, the ring buffer itself * is protected. */ - mutex_lock(&iter->mutex); + guard(mutex)(&iter->mutex); /* return any leftover data */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (sret != -EBUSY) - goto out; + return sret; trace_seq_init(&iter->seq); if (iter->trace->read) { sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); if (sret) - goto out; + return sret; } waitagain: sret = tracing_wait_pipe(filp); if (sret <= 0) - goto out; + return sret; /* stop when tracing is finished */ - if (trace_empty(iter)) { - sret = 0; - goto out; - } + if (trace_empty(iter)) + return 0; if (cnt >= TRACE_SEQ_BUFFER_SIZE) cnt = TRACE_SEQ_BUFFER_SIZE - 1; @@ -6748,9 +6576,6 @@ waitagain: if (sret == -EBUSY) goto waitagain; -out: - mutex_unlock(&iter->mutex); - return sret; } @@ -7342,25 +7167,19 @@ u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_eve */ int tracing_set_filter_buffering(struct trace_array *tr, bool set) { - int ret = 0; - - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (set && tr->no_filter_buffering_ref++) - goto out; + return 0; if (!set) { - if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) { - ret = -EINVAL; - goto out; - } + if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) + return -EINVAL; --tr->no_filter_buffering_ref; } - out: - mutex_unlock(&trace_types_lock); - return ret; + return 0; } struct ftrace_buffer_info { @@ -7436,12 +7255,10 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, if (ret) return ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); - if (tr->current_trace->use_max_tr) { - ret = -EBUSY; - goto out; - } + if (tr->current_trace->use_max_tr) + return -EBUSY; local_irq_disable(); arch_spin_lock(&tr->max_lock); @@ -7450,24 +7267,20 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, arch_spin_unlock(&tr->max_lock); local_irq_enable(); if (ret) - goto out; + return ret; switch (val) { case 0: - if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { - ret = -EINVAL; - break; - } + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) + return -EINVAL; if (tr->allocated_snapshot) free_snapshot(tr); break; case 1: /* Only allow per-cpu swap if the ring buffer supports it */ #ifndef CONFIG_RING_BUFFER_ALLOW_SWAP - if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { - ret = -EINVAL; - break; - } + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) + return -EINVAL; #endif if (tr->allocated_snapshot) ret = resize_buffer_duplicate_size(&tr->max_buffer, @@ -7475,7 +7288,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, ret = tracing_arm_snapshot_locked(tr); if (ret) - break; + return ret; /* Now, we're going to swap */ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { @@ -7502,8 +7315,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, *ppos += cnt; ret = cnt; } -out: - mutex_unlock(&trace_types_lock); + return ret; } @@ -7889,12 +7701,11 @@ void tracing_log_err(struct trace_array *tr, len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1; - mutex_lock(&tracing_err_log_lock); + guard(mutex)(&tracing_err_log_lock); + err = get_tracing_log_err(tr, len); - if (PTR_ERR(err) == -ENOMEM) { - mutex_unlock(&tracing_err_log_lock); + if (PTR_ERR(err) == -ENOMEM) return; - } snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc); snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd); @@ -7905,7 +7716,6 @@ void tracing_log_err(struct trace_array *tr, err->info.ts = local_clock(); list_add_tail(&err->list, &tr->err_log); - mutex_unlock(&tracing_err_log_lock); } static void clear_tracing_err_log(struct trace_array *tr) @@ -9601,6 +9411,10 @@ trace_array_create_systems(const char *name, const char *systems, INIT_LIST_HEAD(&tr->hist_vars); INIT_LIST_HEAD(&tr->err_log); +#ifdef CONFIG_MODULES + INIT_LIST_HEAD(&tr->mod_events); +#endif + if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; @@ -9649,20 +9463,17 @@ static int instance_mkdir(const char *name) struct trace_array *tr; int ret; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); ret = -EEXIST; if (trace_array_find(name)) - goto out_unlock; + return -EEXIST; tr = trace_array_create(name); ret = PTR_ERR_OR_ZERO(tr); -out_unlock: - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); return ret; } @@ -9712,24 +9523,23 @@ struct trace_array *trace_array_get_by_name(const char *name, const char *system { struct trace_array *tr; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (tr->name && strcmp(tr->name, name) == 0) - goto out_unlock; + if (tr->name && strcmp(tr->name, name) == 0) { + tr->ref++; + return tr; + } } tr = trace_array_create_systems(name, systems, 0, 0); if (IS_ERR(tr)) tr = NULL; -out_unlock: - if (tr) + else tr->ref++; - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); return tr; } EXPORT_SYMBOL_GPL(trace_array_get_by_name); @@ -9780,48 +9590,36 @@ static int __remove_instance(struct trace_array *tr) int trace_array_destroy(struct trace_array *this_tr) { struct trace_array *tr; - int ret; if (!this_tr) return -EINVAL; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); - ret = -ENODEV; /* Making sure trace array exists before destroying it. */ list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (tr == this_tr) { - ret = __remove_instance(tr); - break; - } + if (tr == this_tr) + return __remove_instance(tr); } - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); - - return ret; + return -ENODEV; } EXPORT_SYMBOL_GPL(trace_array_destroy); static int instance_rmdir(const char *name) { struct trace_array *tr; - int ret; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); - ret = -ENODEV; tr = trace_array_find(name); - if (tr) - ret = __remove_instance(tr); + if (!tr) + return -ENODEV; - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); - - return ret; + return __remove_instance(tr); } static __init void create_trace_instances(struct dentry *d_tracer) @@ -9834,19 +9632,16 @@ static __init void create_trace_instances(struct dentry *d_tracer) if (MEM_FAIL(!trace_instance_dir, "Failed to create instances directory\n")) return; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (!tr->name) continue; if (MEM_FAIL(trace_array_create_dir(tr) < 0, "Failed to create instance directory\n")) - break; + return; } - - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); } static void @@ -10036,6 +9831,24 @@ late_initcall_sync(trace_eval_sync); #ifdef CONFIG_MODULES + +bool module_exists(const char *module) +{ + /* All modules have the symbol __this_module */ + static const char this_mod[] = "__this_module"; + char modname[MAX_PARAM_PREFIX_LEN + sizeof(this_mod) + 2]; + unsigned long val; + int n; + + n = snprintf(modname, sizeof(modname), "%s:%s", module, this_mod); + + if (n > sizeof(modname) - 1) + return false; + + val = module_kallsyms_lookup_name(modname); + return val != 0; +} + static void trace_module_add_evals(struct module *mod) { if (!mod->num_trace_evals) @@ -10060,7 +9873,7 @@ static void trace_module_remove_evals(struct module *mod) if (!mod->num_trace_evals) return; - mutex_lock(&trace_eval_mutex); + guard(mutex)(&trace_eval_mutex); map = trace_eval_maps; @@ -10072,12 +9885,10 @@ static void trace_module_remove_evals(struct module *mod) map = map->tail.next; } if (!map) - goto out; + return; *last = trace_eval_jmp_to_tail(map)->tail.next; kfree(map); - out: - mutex_unlock(&trace_eval_mutex); } #else static inline void trace_module_remove_evals(struct module *mod) { } @@ -10750,6 +10561,10 @@ __init static int tracer_alloc_buffers(void) #endif ftrace_init_global_array_ops(&global_trace); +#ifdef CONFIG_MODULES + INIT_LIST_HEAD(&global_trace.mod_events); +#endif + init_trace_flags_index(&global_trace); register_tracer(&nop_trace); @@ -10777,8 +10592,6 @@ __init static int tracer_alloc_buffers(void) register_snapshot_cmd(); - test_can_verify(); - return 0; out_free_pipe_cpumask: @@ -10797,6 +10610,14 @@ out: return ret; } +#ifdef CONFIG_FUNCTION_TRACER +/* Used to set module cached ftrace filtering at boot up */ +__init struct trace_array *trace_get_global_array(void) +{ + return &global_trace; +} +#endif + void __init ftrace_boot_snapshot(void) { #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 266740b4e121..9c21ba45b7af 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -400,6 +400,9 @@ struct trace_array { cpumask_var_t pipe_cpumask; int ref; int trace_ref; +#ifdef CONFIG_MODULES + struct list_head mod_events; +#endif #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops *ops; struct trace_pid_list __rcu *function_pids; @@ -432,8 +435,18 @@ struct trace_array { enum { TRACE_ARRAY_FL_GLOBAL = BIT(0), TRACE_ARRAY_FL_BOOT = BIT(1), + TRACE_ARRAY_FL_MOD_INIT = BIT(2), }; +#ifdef CONFIG_MODULES +bool module_exists(const char *module); +#else +static inline bool module_exists(const char *module) +{ + return false; +} +#endif + extern struct list_head ftrace_trace_arrays; extern struct mutex trace_types_lock; @@ -667,9 +680,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, bool trace_is_tracepoint_string(const char *str); const char *trace_event_format(struct trace_iterator *iter, const char *fmt); -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) __printf(2, 0); char *trace_iter_expand_format(struct trace_iterator *iter); +bool ignore_event(struct trace_iterator *iter); int trace_empty(struct trace_iterator *iter); @@ -694,8 +706,10 @@ void trace_latency_header(struct seq_file *m); void trace_default_header(struct seq_file *m); void print_trace_header(struct seq_file *m, struct trace_iterator *iter); -void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); -int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops); +void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); +int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); @@ -718,8 +732,6 @@ extern unsigned long tracing_thresh; /* PID filtering */ -extern int pid_max; - bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid); bool trace_ignore_this_task(struct trace_pid_list *filtered_pids, @@ -912,7 +924,9 @@ extern int __trace_graph_retaddr_entry(struct trace_array *tr, unsigned long retaddr); extern void __trace_graph_return(struct trace_array *tr, struct ftrace_graph_ret *trace, - unsigned int trace_ctx); + unsigned int trace_ctx, + u64 calltime, u64 rettime); + extern void init_array_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops); extern int allocate_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops); extern void free_fgraph_ops(struct trace_array *tr); @@ -1115,6 +1129,7 @@ void ftrace_destroy_function_files(struct trace_array *tr); int ftrace_allocate_ftrace_ops(struct trace_array *tr); void ftrace_free_ftrace_ops(struct trace_array *tr); void ftrace_init_global_array_ops(struct trace_array *tr); +struct trace_array *trace_get_global_array(void); void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func); void ftrace_reset_array_ops(struct trace_array *tr); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); @@ -1413,7 +1428,8 @@ struct ftrace_event_field { int filter_type; int offset; int size; - int is_signed; + unsigned int is_signed:1; + unsigned int needs_test:1; int len; }; diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index 4376887e0d8a..a322e4f249a5 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -74,24 +74,19 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type struct dyn_event *pos, *n; char *system = NULL, *event, *p; int argc, ret = -ENOENT; - char **argv; + char **argv __free(argv_free) = argv_split(GFP_KERNEL, raw_command, &argc); - argv = argv_split(GFP_KERNEL, raw_command, &argc); if (!argv) return -ENOMEM; if (argv[0][0] == '-') { - if (argv[0][1] != ':') { - ret = -EINVAL; - goto out; - } + if (argv[0][1] != ':') + return -EINVAL; event = &argv[0][2]; } else { event = strchr(argv[0], ':'); - if (!event) { - ret = -EINVAL; - goto out; - } + if (!event) + return -EINVAL; event++; } @@ -101,10 +96,8 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type event = p + 1; *p = '\0'; } - if (!system && event[0] == '\0') { - ret = -EINVAL; - goto out; - } + if (!system && event[0] == '\0') + return -EINVAL; mutex_lock(&event_mutex); for_each_dyn_event_safe(pos, n) { @@ -120,8 +113,6 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type } tracing_reset_all_online_cpus(); mutex_unlock(&event_mutex); -out: - argv_free(argv); return ret; } diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 82fd174ebbe0..fbfb396905a6 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -124,8 +124,8 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, __field_packed( unsigned long, ret, retval ) __field_packed( int, ret, depth ) __field_packed( unsigned int, ret, overrun ) - __field_packed( unsigned long long, ret, calltime) - __field_packed( unsigned long long, ret, rettime ) + __field(unsigned long long, calltime ) + __field(unsigned long long, rettime ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d retval: %lx", @@ -146,8 +146,8 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, __field_packed( unsigned long, ret, func ) __field_packed( int, ret, depth ) __field_packed( unsigned int, ret, overrun ) - __field_packed( unsigned long long, ret, calltime) - __field_packed( unsigned long long, ret, rettime ) + __field(unsigned long long, calltime ) + __field(unsigned long long, rettime ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d", diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index be8be0c1aaf0..82fd637cfc19 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -917,10 +917,10 @@ static int __trace_eprobe_create(int argc, const char *argv[]) goto error; } - mutex_lock(&event_mutex); - event_call = find_and_get_event(sys_name, sys_event); - ep = alloc_event_probe(group, event, event_call, argc - 2); - mutex_unlock(&event_mutex); + scoped_guard(mutex, &event_mutex) { + event_call = find_and_get_event(sys_name, sys_event); + ep = alloc_event_probe(group, event, event_call, argc - 2); + } if (IS_ERR(ep)) { ret = PTR_ERR(ep); @@ -952,23 +952,21 @@ static int __trace_eprobe_create(int argc, const char *argv[]) if (ret < 0) goto error; init_trace_eprobe_call(ep); - mutex_lock(&event_mutex); - ret = trace_probe_register_event_call(&ep->tp); - if (ret) { - if (ret == -EEXIST) { - trace_probe_log_set_index(0); - trace_probe_log_err(0, EVENT_EXIST); + scoped_guard(mutex, &event_mutex) { + ret = trace_probe_register_event_call(&ep->tp); + if (ret) { + if (ret == -EEXIST) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, EVENT_EXIST); + } + goto error; + } + ret = dyn_event_add(&ep->devent, &ep->tp.event->call); + if (ret < 0) { + trace_probe_unregister_event_call(&ep->tp); + goto error; } - mutex_unlock(&event_mutex); - goto error; } - ret = dyn_event_add(&ep->devent, &ep->tp.event->call); - if (ret < 0) { - trace_probe_unregister_event_call(&ep->tp); - mutex_unlock(&event_mutex); - goto error; - } - mutex_unlock(&event_mutex); return ret; parse_error: ret = -EINVAL; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 77e68efbd43e..4cb275316e51 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system) } static struct ftrace_event_field * -__find_event_field(struct list_head *head, char *name) +__find_event_field(struct list_head *head, const char *name) { struct ftrace_event_field *field; @@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name) static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, - int is_signed, int filter_type, int len) + int is_signed, int filter_type, int len, + int need_test) { struct ftrace_event_field *field; @@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type, field->offset = offset; field->size = size; field->is_signed = is_signed; + field->needs_test = need_test; field->len = len; list_add(&field->link, head); @@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type, head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, 0); + is_signed, filter_type, 0, 0); } EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, - int filter_type, int len) + int filter_type, int len, int need_test) { struct list_head *head; @@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, len); + is_signed, filter_type, len, need_test); } #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ - filter_type, 0); \ + filter_type, 0, 0); \ if (ret) \ return ret; @@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ - is_signed_type(type), FILTER_OTHER, 0); \ + is_signed_type(type), FILTER_OTHER, \ + 0, 0); \ if (ret) \ return ret; @@ -244,19 +247,16 @@ int trace_event_get_offsets(struct trace_event_call *call) return tail->offset + tail->size; } -/* - * Check if the referenced field is an array and return true, - * as arrays are OK to dereference. - */ -static bool test_field(const char *fmt, struct trace_event_call *call) + +static struct trace_event_fields *find_event_field(const char *fmt, + struct trace_event_call *call) { struct trace_event_fields *field = call->class->fields_array; - const char *array_descriptor; const char *p = fmt; int len; if (!(len = str_has_prefix(fmt, "REC->"))) - return false; + return NULL; fmt += len; for (p = fmt; *p; p++) { if (!isalnum(*p) && *p != '_') @@ -265,16 +265,141 @@ static bool test_field(const char *fmt, struct trace_event_call *call) len = p - fmt; for (; field->type; field++) { - if (strncmp(field->name, fmt, len) || - field->name[len]) + if (strncmp(field->name, fmt, len) || field->name[len]) continue; - array_descriptor = strchr(field->type, '['); - /* This is an array and is OK to dereference. */ - return array_descriptor != NULL; + + return field; + } + return NULL; +} + +/* + * Check if the referenced field is an array and return true, + * as arrays are OK to dereference. + */ +static bool test_field(const char *fmt, struct trace_event_call *call) +{ + struct trace_event_fields *field; + + field = find_event_field(fmt, call); + if (!field) + return false; + + /* This is an array and is OK to dereference. */ + return strchr(field->type, '[') != NULL; +} + +/* Look for a string within an argument */ +static bool find_print_string(const char *arg, const char *str, const char *end) +{ + const char *r; + + r = strstr(arg, str); + return r && r < end; +} + +/* Return true if the argument pointer is safe */ +static bool process_pointer(const char *fmt, int len, struct trace_event_call *call) +{ + const char *r, *e, *a; + + e = fmt + len; + + /* Find the REC-> in the argument */ + r = strstr(fmt, "REC->"); + if (r && r < e) { + /* + * Addresses of events on the buffer, or an array on the buffer is + * OK to dereference. There's ways to fool this, but + * this is to catch common mistakes, not malicious code. + */ + a = strchr(fmt, '&'); + if ((a && (a < r)) || test_field(r, call)) + return true; + } else if (find_print_string(fmt, "__get_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_sockaddr(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) { + return true; } return false; } +/* Return true if the string is safe */ +static bool process_string(const char *fmt, int len, struct trace_event_call *call) +{ + struct trace_event_fields *field; + const char *r, *e, *s; + + e = fmt + len; + + /* + * There are several helper functions that return strings. + * If the argument contains a function, then assume its field is valid. + * It is considered that the argument has a function if it has: + * alphanumeric or '_' before a parenthesis. + */ + s = fmt; + do { + r = strstr(s, "("); + if (!r || r >= e) + break; + for (int i = 1; r - i >= s; i++) { + char ch = *(r - i); + if (isspace(ch)) + continue; + if (isalnum(ch) || ch == '_') + return true; + /* Anything else, this isn't a function */ + break; + } + /* A function could be wrapped in parethesis, try the next one */ + s = r + 1; + } while (s < e); + + /* + * Check for arrays. If the argument has: foo[REC->val] + * then it is very likely that foo is an array of strings + * that are safe to use. + */ + r = strstr(s, "["); + if (r && r < e) { + r = strstr(r, "REC->"); + if (r && r < e) + return true; + } + + /* + * If there's any strings in the argument consider this arg OK as it + * could be: REC->field ? "foo" : "bar" and we don't want to get into + * verifying that logic here. + */ + if (find_print_string(fmt, "\"", e)) + return true; + + /* Dereferenced strings are also valid like any other pointer */ + if (process_pointer(fmt, len, call)) + return true; + + /* Make sure the field is found */ + field = find_event_field(fmt, call); + if (!field) + return false; + + /* Test this field's string before printing the event */ + call->flags |= TRACE_EVENT_FL_TEST_STR; + field->needs_test = 1; + + return true; +} + /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and @@ -284,13 +409,14 @@ static bool test_field(const char *fmt, struct trace_event_call *call) static void test_event_printk(struct trace_event_call *call) { u64 dereference_flags = 0; + u64 string_flags = 0; bool first = true; - const char *fmt, *c, *r, *a; + const char *fmt; int parens = 0; char in_quote = 0; int start_arg = 0; int arg = 0; - int i; + int i, e; fmt = call->print_fmt; @@ -374,8 +500,16 @@ static void test_event_printk(struct trace_event_call *call) star = true; continue; } - if ((fmt[i + j] == 's') && star) - arg++; + if ((fmt[i + j] == 's')) { + if (star) + arg++; + if (WARN_ONCE(arg == 63, + "Too many args for event: %s", + trace_event_name(call))) + return; + dereference_flags |= 1ULL << arg; + string_flags |= 1ULL << arg; + } break; } break; @@ -403,42 +537,47 @@ static void test_event_printk(struct trace_event_call *call) case ',': if (in_quote || parens) continue; + e = i; i++; while (isspace(fmt[i])) i++; - start_arg = i; - if (!(dereference_flags & (1ULL << arg))) - goto next_arg; - /* Find the REC-> in the argument */ - c = strchr(fmt + i, ','); - r = strstr(fmt + i, "REC->"); - if (r && (!c || r < c)) { - /* - * Addresses of events on the buffer, - * or an array on the buffer is - * OK to dereference. - * There's ways to fool this, but - * this is to catch common mistakes, - * not malicious code. - */ - a = strchr(fmt + i, '&'); - if ((a && (a < r)) || test_field(r, call)) - dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_sockaddr(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); + /* + * If start_arg is zero, then this is the start of the + * first argument. The processing of the argument happens + * when the end of the argument is found, as it needs to + * handle paranthesis and such. + */ + if (!start_arg) { + start_arg = i; + /* Balance out the i++ in the for loop */ + i--; + continue; } - next_arg: - i--; + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, e - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, e - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } + + start_arg = i; arg++; + /* Balance out the i++ in the for loop */ + i--; } } + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } + /* * If you triggered the below warning, the trace event reported * uses an unsafe dereference pointer %p*. As the data stored @@ -730,6 +869,120 @@ static int ftrace_event_enable_disable(struct trace_event_file *file, return __ftrace_event_enable_disable(file, enable, 0); } +#ifdef CONFIG_MODULES +struct event_mod_load { + struct list_head list; + char *module; + char *match; + char *system; + char *event; +}; + +static void free_event_mod(struct event_mod_load *event_mod) +{ + list_del(&event_mod->list); + kfree(event_mod->module); + kfree(event_mod->match); + kfree(event_mod->system); + kfree(event_mod->event); + kfree(event_mod); +} + +static void clear_mod_events(struct trace_array *tr) +{ + struct event_mod_load *event_mod, *n; + + list_for_each_entry_safe(event_mod, n, &tr->mod_events, list) { + free_event_mod(event_mod); + } +} + +static int remove_cache_mod(struct trace_array *tr, const char *mod, + const char *match, const char *system, const char *event) +{ + struct event_mod_load *event_mod, *n; + int ret = -EINVAL; + + list_for_each_entry_safe(event_mod, n, &tr->mod_events, list) { + if (strcmp(event_mod->module, mod) != 0) + continue; + + if (match && strcmp(event_mod->match, match) != 0) + continue; + + if (system && + (!event_mod->system || strcmp(event_mod->system, system) != 0)) + continue; + + if (event && + (!event_mod->event || strcmp(event_mod->event, event) != 0)) + continue; + + free_event_mod(event_mod); + ret = 0; + } + + return ret; +} + +static int cache_mod(struct trace_array *tr, const char *mod, int set, + const char *match, const char *system, const char *event) +{ + struct event_mod_load *event_mod; + + /* If the module exists, then this just failed to find an event */ + if (module_exists(mod)) + return -EINVAL; + + /* See if this is to remove a cached filter */ + if (!set) + return remove_cache_mod(tr, mod, match, system, event); + + event_mod = kzalloc(sizeof(*event_mod), GFP_KERNEL); + if (!event_mod) + return -ENOMEM; + + INIT_LIST_HEAD(&event_mod->list); + event_mod->module = kstrdup(mod, GFP_KERNEL); + if (!event_mod->module) + goto out_free; + + if (match) { + event_mod->match = kstrdup(match, GFP_KERNEL); + if (!event_mod->match) + goto out_free; + } + + if (system) { + event_mod->system = kstrdup(system, GFP_KERNEL); + if (!event_mod->system) + goto out_free; + } + + if (event) { + event_mod->event = kstrdup(event, GFP_KERNEL); + if (!event_mod->event) + goto out_free; + } + + list_add(&event_mod->list, &tr->mod_events); + + return 0; + + out_free: + free_event_mod(event_mod); + + return -ENOMEM; +} +#else /* CONFIG_MODULES */ +static inline void clear_mod_events(struct trace_array *tr) { } +static int cache_mod(struct trace_array *tr, const char *mod, int set, + const char *match, const char *system, const char *event) +{ + return -EINVAL; +} +#endif + static void ftrace_clear_events(struct trace_array *tr) { struct trace_event_file *file; @@ -738,6 +991,7 @@ static void ftrace_clear_events(struct trace_array *tr) list_for_each_entry(file, &tr->events, list) { ftrace_event_enable_disable(file, 0); } + clear_mod_events(tr); mutex_unlock(&event_mutex); } @@ -1026,17 +1280,36 @@ static void remove_event_file_dir(struct trace_event_file *file) */ static int __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, - const char *sub, const char *event, int set) + const char *sub, const char *event, int set, + const char *mod) { struct trace_event_file *file; struct trace_event_call *call; + char *module __free(kfree) = NULL; const char *name; int ret = -EINVAL; int eret = 0; + if (mod) { + char *p; + + module = kstrdup(mod, GFP_KERNEL); + if (!module) + return -ENOMEM; + + /* Replace all '-' with '_' as that's what modules do */ + for (p = strchr(module, '-'); p; p = strchr(p + 1, '-')) + *p = '_'; + } + list_for_each_entry(file, &tr->events, list) { call = file->event_call; + + /* If a module is specified, skip events that are not that module */ + if (module && (!call->module || strcmp(module_name(call->module), module))) + continue; + name = trace_event_name(call); if (!name || !call->class || !call->class->reg) @@ -1069,16 +1342,24 @@ __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, ret = eret; } + /* + * If this is a module setting and nothing was found, + * check if the module was loaded. If it wasn't cache it. + */ + if (module && ret == -EINVAL && !eret) + ret = cache_mod(tr, module, set, match, sub, event); + return ret; } static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, - const char *sub, const char *event, int set) + const char *sub, const char *event, int set, + const char *mod) { int ret; mutex_lock(&event_mutex); - ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set); + ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set, mod); mutex_unlock(&event_mutex); return ret; @@ -1086,11 +1367,20 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) { - char *event = NULL, *sub = NULL, *match; + char *event = NULL, *sub = NULL, *match, *mod; int ret; if (!tr) return -ENOENT; + + /* Modules events can be appened with :mod: */ + mod = strstr(buf, ":mod:"); + if (mod) { + *mod = '\0'; + /* move to the module name */ + mod += 5; + } + /* * The buf format can be : * *: means any event by that name. @@ -1113,9 +1403,13 @@ int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) sub = NULL; if (!strlen(event) || strcmp(event, "*") == 0) event = NULL; + } else if (mod) { + /* Allow wildcard for no length or star */ + if (!strlen(match) || strcmp(match, "*") == 0) + match = NULL; } - ret = __ftrace_set_clr_event(tr, match, sub, event, set); + ret = __ftrace_set_clr_event(tr, match, sub, event, set, mod); /* Put back the colon to allow this to be called again */ if (buf) @@ -1143,7 +1437,7 @@ int trace_set_clr_event(const char *system, const char *event, int set) if (!tr) return -ENODEV; - return __ftrace_set_clr_event(tr, NULL, system, event, set); + return __ftrace_set_clr_event(tr, NULL, system, event, set, NULL); } EXPORT_SYMBOL_GPL(trace_set_clr_event); @@ -1169,7 +1463,7 @@ int trace_array_set_clr_event(struct trace_array *tr, const char *system, return -ENOENT; set = (enable == true) ? 1 : 0; - return __ftrace_set_clr_event(tr, NULL, system, event, set); + return __ftrace_set_clr_event(tr, NULL, system, event, set, NULL); } EXPORT_SYMBOL_GPL(trace_array_set_clr_event); @@ -1256,37 +1550,71 @@ static void *t_start(struct seq_file *m, loff_t *pos) return file; } +enum set_event_iter_type { + SET_EVENT_FILE, + SET_EVENT_MOD, +}; + +struct set_event_iter { + enum set_event_iter_type type; + union { + struct trace_event_file *file; + struct event_mod_load *event_mod; + }; +}; + static void * s_next(struct seq_file *m, void *v, loff_t *pos) { - struct trace_event_file *file = v; + struct set_event_iter *iter = v; + struct trace_event_file *file; struct trace_array *tr = m->private; (*pos)++; - list_for_each_entry_continue(file, &tr->events, list) { - if (file->flags & EVENT_FILE_FL_ENABLED) - return file; + if (iter->type == SET_EVENT_FILE) { + file = iter->file; + list_for_each_entry_continue(file, &tr->events, list) { + if (file->flags & EVENT_FILE_FL_ENABLED) { + iter->file = file; + return iter; + } + } +#ifdef CONFIG_MODULES + iter->type = SET_EVENT_MOD; + iter->event_mod = list_entry(&tr->mod_events, struct event_mod_load, list); +#endif } +#ifdef CONFIG_MODULES + list_for_each_entry_continue(iter->event_mod, &tr->mod_events, list) + return iter; +#endif + return NULL; } static void *s_start(struct seq_file *m, loff_t *pos) { - struct trace_event_file *file; struct trace_array *tr = m->private; + struct set_event_iter *iter; loff_t l; + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return NULL; + mutex_lock(&event_mutex); - file = list_entry(&tr->events, struct trace_event_file, list); + iter->type = SET_EVENT_FILE; + iter->file = list_entry(&tr->events, struct trace_event_file, list); + for (l = 0; l <= *pos; ) { - file = s_next(m, file, &l); - if (!file) + iter = s_next(m, iter, &l); + if (!iter) break; } - return file; + return iter; } static int t_show(struct seq_file *m, void *v) @@ -1306,6 +1634,45 @@ static void t_stop(struct seq_file *m, void *p) mutex_unlock(&event_mutex); } +#ifdef CONFIG_MODULES +static int s_show(struct seq_file *m, void *v) +{ + struct set_event_iter *iter = v; + const char *system; + const char *event; + + if (iter->type == SET_EVENT_FILE) + return t_show(m, iter->file); + + /* When match is set, system and event are not */ + if (iter->event_mod->match) { + seq_printf(m, "%s:mod:%s\n", iter->event_mod->match, + iter->event_mod->module); + return 0; + } + + system = iter->event_mod->system ? : "*"; + event = iter->event_mod->event ? : "*"; + + seq_printf(m, "%s:%s:mod:%s\n", system, event, iter->event_mod->module); + + return 0; +} +#else /* CONFIG_MODULES */ +static int s_show(struct seq_file *m, void *v) +{ + struct set_event_iter *iter = v; + + return t_show(m, iter->file); +} +#endif + +static void s_stop(struct seq_file *m, void *p) +{ + kfree(p); + t_stop(m, NULL); +} + static void * __next(struct seq_file *m, void *v, loff_t *pos, int type) { @@ -1419,21 +1786,20 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, if (ret) return ret; + guard(mutex)(&event_mutex); + switch (val) { case 0: case 1: - ret = -ENODEV; - mutex_lock(&event_mutex); file = event_file_file(filp); - if (likely(file)) { - ret = tracing_update_buffers(file->tr); - if (ret < 0) { - mutex_unlock(&event_mutex); - return ret; - } - ret = ftrace_event_enable_disable(file, val); - } - mutex_unlock(&event_mutex); + if (!file) + return -ENODEV; + ret = tracing_update_buffers(file->tr); + if (ret < 0) + return ret; + ret = ftrace_event_enable_disable(file, val); + if (ret < 0) + return ret; break; default: @@ -1442,7 +1808,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, *ppos += cnt; - return ret ? ret : cnt; + return cnt; } static ssize_t @@ -1520,7 +1886,7 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, if (system) name = system->name; - ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val); + ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val, NULL); if (ret) goto out; @@ -2018,7 +2384,7 @@ event_pid_write(struct file *filp, const char __user *ubuf, if (ret < 0) return ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); if (type == TRACE_PIDS) { filtered_pids = rcu_dereference_protected(tr->filtered_pids, @@ -2034,7 +2400,7 @@ event_pid_write(struct file *filp, const char __user *ubuf, ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); if (ret < 0) - goto out; + return ret; if (type == TRACE_PIDS) rcu_assign_pointer(tr->filtered_pids, pid_list); @@ -2059,11 +2425,7 @@ event_pid_write(struct file *filp, const char __user *ubuf, */ on_each_cpu(ignore_task_cpu, tr, 1); - out: - mutex_unlock(&event_mutex); - - if (ret > 0) - *ppos += ret; + *ppos += ret; return ret; } @@ -2098,8 +2460,8 @@ static const struct seq_operations show_event_seq_ops = { static const struct seq_operations show_set_event_seq_ops = { .start = s_start, .next = s_next, - .show = t_show, - .stop = t_stop, + .show = s_show, + .stop = s_stop, }; static const struct seq_operations show_set_pid_seq_ops = { @@ -2471,7 +2833,7 @@ event_define_fields(struct trace_event_call *call) ret = trace_define_field_ext(call, field->type, field->name, offset, field->size, field->is_signed, field->filter_type, - field->len); + field->len, field->needs_test); if (WARN_ON_ONCE(ret)) { pr_err("error code is %d\n", ret); break; @@ -2972,6 +3334,20 @@ static bool event_in_systems(struct trace_event_call *call, return !*p || isspace(*p) || *p == ','; } +#ifdef CONFIG_HIST_TRIGGERS +/* + * Wake up waiter on the hist_poll_wq from irq_work because the hist trigger + * may happen in any context. + */ +static void hist_poll_event_irq_work(struct irq_work *work) +{ + wake_up_all(&hist_poll_wq); +} + +DEFINE_IRQ_WORK(hist_poll_work, hist_poll_event_irq_work); +DECLARE_WAIT_QUEUE_HEAD(hist_poll_wq); +#endif + static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) @@ -3130,13 +3506,13 @@ int trace_add_event_call(struct trace_event_call *call) int ret; lockdep_assert_held(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); ret = __register_event(call, NULL); - if (ret >= 0) - __add_event_to_tracers(call); + if (ret < 0) + return ret; - mutex_unlock(&trace_types_lock); + __add_event_to_tracers(call); return ret; } EXPORT_SYMBOL_GPL(trace_add_event_call); @@ -3216,6 +3592,28 @@ EXPORT_SYMBOL_GPL(trace_remove_event_call); event++) #ifdef CONFIG_MODULES +static void update_mod_cache(struct trace_array *tr, struct module *mod) +{ + struct event_mod_load *event_mod, *n; + + list_for_each_entry_safe(event_mod, n, &tr->mod_events, list) { + if (strcmp(event_mod->module, mod->name) != 0) + continue; + + __ftrace_set_clr_event_nolock(tr, event_mod->match, + event_mod->system, + event_mod->event, 1, mod->name); + free_event_mod(event_mod); + } +} + +static void update_cache_events(struct module *mod) +{ + struct trace_array *tr; + + list_for_each_entry(tr, &ftrace_trace_arrays, list) + update_mod_cache(tr, mod); +} static void trace_module_add_events(struct module *mod) { @@ -3238,6 +3636,8 @@ static void trace_module_add_events(struct module *mod) __register_event(*call, mod); __add_event_to_tracers(*call); } + + update_cache_events(mod); } static void trace_module_remove_events(struct module *mod) @@ -3390,30 +3790,21 @@ struct trace_event_file *trace_get_event_file(const char *instance, return ERR_PTR(ret); } - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); file = find_event_file(tr, system, event); if (!file) { trace_array_put(tr); - ret = -EINVAL; - goto out; + return ERR_PTR(-EINVAL); } /* Don't let event modules unload while in use */ ret = trace_event_try_get_ref(file->event_call); if (!ret) { trace_array_put(tr); - ret = -EBUSY; - goto out; + return ERR_PTR(-EBUSY); } - ret = 0; - out: - mutex_unlock(&event_mutex); - - if (ret) - file = ERR_PTR(ret); - return file; } EXPORT_SYMBOL_GPL(trace_get_event_file); @@ -3631,6 +4022,7 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, struct trace_event_file *file; struct ftrace_probe_ops *ops; struct event_probe_data *data; + unsigned long count = -1; const char *system; const char *event; char *number; @@ -3650,12 +4042,11 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, event = strsep(¶m, ":"); - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); - ret = -EINVAL; file = find_event_file(tr, system, event); if (!file) - goto out; + return -EINVAL; enable = strcmp(cmd, ENABLE_EVENT_STR) == 0; @@ -3664,74 +4055,62 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, else ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops; - if (glob[0] == '!') { - ret = unregister_ftrace_function_probe_func(glob+1, tr, ops); - goto out; + if (glob[0] == '!') + return unregister_ftrace_function_probe_func(glob+1, tr, ops); + + if (param) { + number = strsep(¶m, ":"); + + if (!strlen(number)) + return -EINVAL; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, &count); + if (ret) + return ret; } - ret = -ENOMEM; - - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - goto out; - - data->enable = enable; - data->count = -1; - data->file = file; - - if (!param) - goto out_reg; - - number = strsep(¶m, ":"); - - ret = -EINVAL; - if (!strlen(number)) - goto out_free; - - /* - * We use the callback data field (which is a pointer) - * as our counter. - */ - ret = kstrtoul(number, 0, &data->count); - if (ret) - goto out_free; - - out_reg: /* Don't let event modules unload while probe registered */ ret = trace_event_try_get_ref(file->event_call); - if (!ret) { - ret = -EBUSY; - goto out_free; - } + if (!ret) + return -EBUSY; ret = __ftrace_event_enable_disable(file, 1, 1); if (ret < 0) goto out_put; + ret = -ENOMEM; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out_put; + + data->enable = enable; + data->count = count; + data->file = file; + ret = register_ftrace_function_probe(glob, tr, ops, data); /* * The above returns on success the # of functions enabled, * but if it didn't find any functions it returns zero. * Consider no functions a failure too. */ - if (!ret) { - ret = -ENOENT; - goto out_disable; - } else if (ret < 0) - goto out_disable; - /* Just return zero, not the number of enabled functions */ - ret = 0; - out: - mutex_unlock(&event_mutex); - return ret; - out_disable: + /* Just return zero, not the number of enabled functions */ + if (ret > 0) + return 0; + + kfree(data); + + if (!ret) + ret = -ENOENT; + __ftrace_event_enable_disable(file, 0, 1); out_put: trace_event_put_ref(file->event_call); - out_free: - kfree(data); - goto out; + return ret; } static struct ftrace_func_command event_enable_cmd = { @@ -3954,20 +4333,17 @@ early_event_add_tracer(struct dentry *parent, struct trace_array *tr) { int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); ret = create_event_toplevel_files(parent, tr); if (ret) - goto out_unlock; + return ret; down_write(&trace_event_sem); __trace_early_add_event_dirs(tr); up_write(&trace_event_sem); - out_unlock: - mutex_unlock(&event_mutex); - - return ret; + return 0; } /* Must be called with event_mutex held */ @@ -3982,7 +4358,7 @@ int event_trace_del_tracer(struct trace_array *tr) __ftrace_clear_event_pids(tr, TRACE_PIDS | TRACE_NO_PIDS); /* Disable any running events */ - __ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0); + __ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0, NULL); /* Make sure no more events are being executed */ tracepoint_synchronize_unregister(); @@ -4266,7 +4642,7 @@ static __init void event_trace_self_tests(void) pr_info("Testing event system %s: ", system->name); - ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1); + ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1, NULL); if (WARN_ON_ONCE(ret)) { pr_warn("error enabling system %s\n", system->name); @@ -4275,7 +4651,7 @@ static __init void event_trace_self_tests(void) event_test_stuff(); - ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0); + ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0, NULL); if (WARN_ON_ONCE(ret)) { pr_warn("error disabling system %s\n", system->name); @@ -4290,7 +4666,7 @@ static __init void event_trace_self_tests(void) pr_info("Running tests on all trace events:\n"); pr_info("Testing all events: "); - ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1); + ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1, NULL); if (WARN_ON_ONCE(ret)) { pr_warn("error enabling all events\n"); return; @@ -4299,7 +4675,7 @@ static __init void event_trace_self_tests(void) event_test_stuff(); /* reset sysname */ - ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0); + ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0, NULL); if (WARN_ON_ONCE(ret)) { pr_warn("error disabling all events\n"); return; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 78051de581e7..0993dfc1c5c1 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2405,13 +2405,11 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, struct event_filter *filter = NULL; int err = 0; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); /* Make sure the system still has events */ - if (!dir->nr_events) { - err = -ENODEV; - goto out_unlock; - } + if (!dir->nr_events) + return -ENODEV; if (!strcmp(strstrip(filter_string), "0")) { filter_free_subsystem_preds(dir, tr); @@ -2422,7 +2420,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, tracepoint_synchronize_unregister(); filter_free_subsystem_filters(dir, tr); __free_filter(filter); - goto out_unlock; + return 0; } err = create_system_filter(dir, filter_string, &filter); @@ -2434,8 +2432,6 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, __free_filter(system->filter); system->filter = filter; } -out_unlock: - mutex_unlock(&event_mutex); return err; } @@ -2612,17 +2608,15 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, struct event_filter *filter = NULL; struct trace_event_call *call; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); call = event->tp_event; - err = -EINVAL; if (!call) - goto out_unlock; + return -EINVAL; - err = -EEXIST; if (event->filter) - goto out_unlock; + return -EEXIST; err = create_filter(NULL, call, filter_str, false, &filter); if (err) @@ -2637,9 +2631,6 @@ free_filter: if (err || ftrace_event_is_function(call)) __free_filter(filter); -out_unlock: - mutex_unlock(&event_mutex); - return err; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9c058aa8baf3..261163b00137 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5311,6 +5311,8 @@ static void event_hist_trigger(struct event_trigger_data *data, if (resolve_var_refs(hist_data, key, var_ref_vals, true)) hist_trigger_actions(hist_data, elt, buffer, rec, rbe, key, var_ref_vals); + + hist_poll_wakeup(); } static void hist_trigger_stacktrace_print(struct seq_file *m, @@ -5590,49 +5592,128 @@ static void hist_trigger_show(struct seq_file *m, n_entries, (u64)atomic64_read(&hist_data->map->drops)); } +struct hist_file_data { + struct file *file; + u64 last_read; + u64 last_act; +}; + +static u64 get_hist_hit_count(struct trace_event_file *event_file) +{ + struct hist_trigger_data *hist_data; + struct event_trigger_data *data; + u64 ret = 0; + + list_for_each_entry(data, &event_file->triggers, list) { + if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) { + hist_data = data->private_data; + ret += atomic64_read(&hist_data->map->hits); + } + } + return ret; +} + static int hist_show(struct seq_file *m, void *v) { + struct hist_file_data *hist_file = m->private; struct event_trigger_data *data; struct trace_event_file *event_file; - int n = 0, ret = 0; + int n = 0; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); - event_file = event_file_file(m->private); - if (unlikely(!event_file)) { - ret = -ENODEV; - goto out_unlock; - } + event_file = event_file_file(hist_file->file); + if (unlikely(!event_file)) + return -ENODEV; list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } + hist_file->last_read = get_hist_hit_count(event_file); + /* + * Update last_act too so that poll()/POLLPRI can wait for the next + * event after any syscall on hist file. + */ + hist_file->last_act = hist_file->last_read; - out_unlock: - mutex_unlock(&event_mutex); + return 0; +} + +static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wait) +{ + struct trace_event_file *event_file; + struct seq_file *m = file->private_data; + struct hist_file_data *hist_file = m->private; + __poll_t ret = 0; + u64 cnt; + + guard(mutex)(&event_mutex); + + event_file = event_file_data(file); + if (!event_file) + return EPOLLERR; + + hist_poll_wait(file, wait); + + cnt = get_hist_hit_count(event_file); + if (hist_file->last_read != cnt) + ret |= EPOLLIN | EPOLLRDNORM; + if (hist_file->last_act != cnt) { + hist_file->last_act = cnt; + ret |= EPOLLPRI; + } return ret; } +static int event_hist_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + struct hist_file_data *hist_file = m->private; + + kfree(hist_file); + return tracing_single_release_file_tr(inode, file); +} + static int event_hist_open(struct inode *inode, struct file *file) { + struct trace_event_file *event_file; + struct hist_file_data *hist_file; int ret; ret = tracing_open_file_tr(inode, file); if (ret) return ret; + guard(mutex)(&event_mutex); + + event_file = event_file_data(file); + if (!event_file) + return -ENODEV; + + hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL); + if (!hist_file) + return -ENOMEM; + + hist_file->file = file; + hist_file->last_act = get_hist_hit_count(event_file); + /* Clear private_data to avoid warning in single_open() */ file->private_data = NULL; - return single_open(file, hist_show, file); + ret = single_open(file, hist_show, hist_file); + if (ret) + kfree(hist_file); + + return ret; } const struct file_operations event_hist_fops = { .open = event_hist_open, .read = seq_read, .llseek = seq_lseek, - .release = tracing_single_release_file_tr, + .release = event_hist_release, + .poll = event_hist_poll, }; #ifdef CONFIG_HIST_TRIGGERS_DEBUG @@ -5873,25 +5954,19 @@ static int hist_debug_show(struct seq_file *m, void *v) { struct event_trigger_data *data; struct trace_event_file *event_file; - int n = 0, ret = 0; + int n = 0; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); event_file = event_file_file(m->private); - if (unlikely(!event_file)) { - ret = -ENODEV; - goto out_unlock; - } + if (unlikely(!event_file)) + return -ENODEV; list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_debug_show(m, data, n++); } - - out_unlock: - mutex_unlock(&event_mutex); - - return ret; + return 0; } static int event_hist_debug_open(struct inode *inode, struct file *file) diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index c82b401a294d..e3f7d09e5512 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -49,16 +49,11 @@ static char *last_cmd; static int errpos(const char *str) { - int ret = 0; - - mutex_lock(&lastcmd_mutex); + guard(mutex)(&lastcmd_mutex); if (!str || !last_cmd) - goto out; + return 0; - ret = err_pos(last_cmd, str); - out: - mutex_unlock(&lastcmd_mutex); - return ret; + return err_pos(last_cmd, str); } static void last_cmd_set(const char *str) @@ -74,14 +69,12 @@ static void last_cmd_set(const char *str) static void synth_err(u8 err_type, u16 err_pos) { - mutex_lock(&lastcmd_mutex); + guard(mutex)(&lastcmd_mutex); if (!last_cmd) - goto out; + return; tracing_log_err(NULL, "synthetic_events", last_cmd, err_text, err_type, err_pos); - out: - mutex_unlock(&lastcmd_mutex); } static int create_synth_event(const char *raw_command); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index a5e3d6acf1e1..d45448947094 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -211,12 +211,10 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) if (ret) return ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); - if (unlikely(!event_file_file(file))) { - mutex_unlock(&event_mutex); + if (unlikely(!event_file_file(file))) return -ENODEV; - } if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { @@ -239,8 +237,6 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) } } - mutex_unlock(&event_mutex); - return ret; } @@ -248,7 +244,6 @@ int trigger_process_regex(struct trace_event_file *file, char *buff) { char *command, *next; struct event_command *p; - int ret = -EINVAL; next = buff = skip_spaces(buff); command = strsep(&next, ": \t"); @@ -259,17 +254,14 @@ int trigger_process_regex(struct trace_event_file *file, char *buff) } command = (command[0] != '!') ? command : command + 1; - mutex_lock(&trigger_cmd_mutex); - list_for_each_entry(p, &trigger_commands, list) { - if (strcmp(p->name, command) == 0) { - ret = p->parse(p, file, buff, command, next); - goto out_unlock; - } - } - out_unlock: - mutex_unlock(&trigger_cmd_mutex); + guard(mutex)(&trigger_cmd_mutex); - return ret; + list_for_each_entry(p, &trigger_commands, list) { + if (strcmp(p->name, command) == 0) + return p->parse(p, file, buff, command, next); + } + + return -EINVAL; } static ssize_t event_trigger_regex_write(struct file *file, @@ -278,7 +270,7 @@ static ssize_t event_trigger_regex_write(struct file *file, { struct trace_event_file *event_file; ssize_t ret; - char *buf; + char *buf __free(kfree) = NULL; if (!cnt) return 0; @@ -292,24 +284,18 @@ static ssize_t event_trigger_regex_write(struct file *file, strim(buf); - mutex_lock(&event_mutex); - event_file = event_file_file(file); - if (unlikely(!event_file)) { - mutex_unlock(&event_mutex); - kfree(buf); - return -ENODEV; - } - ret = trigger_process_regex(event_file, buf); - mutex_unlock(&event_mutex); + guard(mutex)(&event_mutex); - kfree(buf); + event_file = event_file_file(file); + if (unlikely(!event_file)) + return -ENODEV; + + ret = trigger_process_regex(event_file, buf); if (ret < 0) - goto out; + return ret; *ppos += cnt; - ret = cnt; - out: - return ret; + return cnt; } static int event_trigger_regex_release(struct inode *inode, struct file *file) @@ -359,20 +345,16 @@ const struct file_operations event_trigger_fops = { __init int register_event_command(struct event_command *cmd) { struct event_command *p; - int ret = 0; - mutex_lock(&trigger_cmd_mutex); + guard(mutex)(&trigger_cmd_mutex); + list_for_each_entry(p, &trigger_commands, list) { - if (strcmp(cmd->name, p->name) == 0) { - ret = -EBUSY; - goto out_unlock; - } + if (strcmp(cmd->name, p->name) == 0) + return -EBUSY; } list_add(&cmd->list, &trigger_commands); - out_unlock: - mutex_unlock(&trigger_cmd_mutex); - return ret; + return 0; } /* @@ -382,20 +364,17 @@ __init int register_event_command(struct event_command *cmd) __init int unregister_event_command(struct event_command *cmd) { struct event_command *p, *n; - int ret = -ENODEV; - mutex_lock(&trigger_cmd_mutex); + guard(mutex)(&trigger_cmd_mutex); + list_for_each_entry_safe(p, n, &trigger_commands, list) { if (strcmp(cmd->name, p->name) == 0) { - ret = 0; list_del_init(&p->list); - goto out_unlock; + return 0; } } - out_unlock: - mutex_unlock(&trigger_cmd_mutex); - return ret; + return -ENODEV; } /** diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 17bcad8f79de..97325fbd6283 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -2899,7 +2899,7 @@ static int set_max_user_events_sysctl(const struct ctl_table *table, int write, return ret; } -static struct ctl_table user_event_sysctls[] = { +static const struct ctl_table user_event_sysctls[] = { { .procname = "user_events_max", .data = &max_user_events, diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index c62d1629cffe..b8f3c4ba309b 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -134,7 +134,7 @@ static int process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, void *dest, void *base) { - struct pt_regs *regs = rec; + struct ftrace_regs *fregs = rec; unsigned long val; int ret; @@ -142,17 +142,17 @@ retry: /* 1st stage: get value from context */ switch (code->op) { case FETCH_OP_STACK: - val = regs_get_kernel_stack_nth(regs, code->param); + val = ftrace_regs_get_kernel_stack_nth(fregs, code->param); break; case FETCH_OP_STACKP: - val = kernel_stack_pointer(regs); + val = ftrace_regs_get_stack_pointer(fregs); break; case FETCH_OP_RETVAL: - val = regs_return_value(regs); + val = ftrace_regs_get_return_value(fregs); break; #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API case FETCH_OP_ARG: - val = regs_get_kernel_argument(regs, code->param); + val = ftrace_regs_get_argument(fregs, code->param); break; case FETCH_OP_EDATA: val = *(unsigned long *)((unsigned long)edata + code->offset); @@ -175,7 +175,7 @@ NOKPROBE_SYMBOL(process_fetch_insn) /* function entry handler */ static nokprobe_inline void __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs, + struct ftrace_regs *fregs, struct trace_event_file *trace_file) { struct fentry_trace_entry_head *entry; @@ -189,41 +189,71 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs, NULL); + dsize = __get_data_size(&tf->tp, fregs, NULL); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); if (!entry) return; - fbuffer.regs = regs; + fbuffer.regs = ftrace_get_regs(fregs); entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->ip = entry_ip; - store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs) + struct ftrace_regs *fregs) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fentry_trace_func(tf, entry_ip, regs, link->file); + __fentry_trace_func(tf, entry_ip, fregs, link->file); } NOKPROBE_SYMBOL(fentry_trace_func); +static nokprobe_inline +void store_fprobe_entry_data(void *edata, struct trace_probe *tp, struct ftrace_regs *fregs) +{ + struct probe_entry_arg *earg = tp->entry_arg; + unsigned long val = 0; + int i; + + if (!earg) + return; + + for (i = 0; i < earg->size; i++) { + struct fetch_insn *code = &earg->code[i]; + + switch (code->op) { + case FETCH_OP_ARG: + val = ftrace_regs_get_argument(fregs, code->param); + break; + case FETCH_OP_ST_EDATA: + *(unsigned long *)((unsigned long)edata + code->offset) = val; + break; + case FETCH_OP_END: + goto end; + default: + break; + } + } +end: + return; +} + /* function exit handler */ static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); if (tf->tp.entry_arg) - store_trace_entry_data(entry_data, &tf->tp, regs); + store_fprobe_entry_data(entry_data, &tf->tp, fregs); return 0; } @@ -231,7 +261,7 @@ NOKPROBE_SYMBOL(trace_fprobe_entry_handler) static nokprobe_inline void __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data, struct trace_event_file *trace_file) { struct fexit_trace_entry_head *entry; @@ -245,60 +275,63 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs, entry_data); + dsize = __get_data_size(&tf->tp, fregs, entry_data); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); if (!entry) return; - fbuffer.regs = regs; + fbuffer.regs = ftrace_get_regs(fregs); entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, void *entry_data) + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data, link->file); + __fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data, link->file); } NOKPROBE_SYMBOL(fexit_trace_func); #ifdef CONFIG_PERF_EVENTS static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs) + struct ftrace_regs *fregs) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fentry_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; + struct pt_regs *regs; int rctx; head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return 0; - dsize = __get_data_size(&tf->tp, regs, NULL); + dsize = __get_data_size(&tf->tp, fregs, NULL); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_alloc(size, NULL, &rctx); + entry = perf_trace_buf_alloc(size, ®s, &rctx); if (!entry) return 0; + regs = ftrace_fill_perf_regs(fregs, regs); + entry->ip = entry_ip; memset(&entry[1], 0, dsize); - store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); return 0; @@ -307,31 +340,34 @@ NOKPROBE_SYMBOL(fentry_perf_func); static void fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fexit_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; + struct pt_regs *regs; int rctx; head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return; - dsize = __get_data_size(&tf->tp, regs, entry_data); + dsize = __get_data_size(&tf->tp, fregs, entry_data); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_alloc(size, NULL, &rctx); + entry = perf_trace_buf_alloc(size, ®s, &rctx); if (!entry) return; + regs = ftrace_fill_perf_regs(fregs, regs); + entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); } @@ -339,33 +375,34 @@ NOKPROBE_SYMBOL(fexit_perf_func); #endif /* CONFIG_PERF_EVENTS */ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); int ret = 0; if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fentry_trace_func(tf, entry_ip, regs); + fentry_trace_func(tf, entry_ip, fregs); + #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - ret = fentry_perf_func(tf, entry_ip, regs); + ret = fentry_perf_func(tf, entry_ip, fregs); #endif return ret; } NOKPROBE_SYMBOL(fentry_dispatcher); static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data); + fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - fexit_perf_func(tf, entry_ip, ret_ip, regs, entry_data); + fexit_perf_func(tf, entry_ip, ret_ip, fregs, entry_data); #endif } NOKPROBE_SYMBOL(fexit_dispatcher); @@ -379,6 +416,9 @@ static void free_trace_fprobe(struct trace_fprobe *tf) } } +/* Since alloc_trace_fprobe() can return error, check the pointer is ERR too. */ +DEFINE_FREE(free_trace_fprobe, struct trace_fprobe *, if (!IS_ERR_OR_NULL(_T)) free_trace_fprobe(_T)) + /* * Allocate new trace_probe and initialize it (including fprobe). */ @@ -387,10 +427,9 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, const char *symbol, struct tracepoint *tpoint, struct module *mod, - int maxactive, int nargs, bool is_return) { - struct trace_fprobe *tf; + struct trace_fprobe *tf __free(free_trace_fprobe) = NULL; int ret = -ENOMEM; tf = kzalloc(struct_size(tf, tp.args, nargs), GFP_KERNEL); @@ -399,7 +438,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->symbol = kstrdup(symbol, GFP_KERNEL); if (!tf->symbol) - goto error; + return ERR_PTR(-ENOMEM); if (is_return) tf->fp.exit_handler = fexit_dispatcher; @@ -408,17 +447,13 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->tpoint = tpoint; tf->mod = mod; - tf->fp.nr_maxactive = maxactive; ret = trace_probe_init(&tf->tp, event, group, false, nargs); if (ret < 0) - goto error; + return ERR_PTR(ret); dyn_event_init(&tf->devent, &trace_fprobe_ops); - return tf; -error: - free_trace_fprobe(tf); - return ERR_PTR(ret); + return_ptr(tf); } static struct trace_fprobe *find_trace_fprobe(const char *event, @@ -845,14 +880,12 @@ static int register_trace_fprobe(struct trace_fprobe *tf) struct trace_fprobe *old_tf; int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); old_tf = find_trace_fprobe(trace_probe_name(&tf->tp), trace_probe_group_name(&tf->tp)); - if (old_tf) { - ret = append_trace_fprobe(tf, old_tf); - goto end; - } + if (old_tf) + return append_trace_fprobe(tf, old_tf); /* Register new event */ ret = register_fprobe_event(tf); @@ -862,7 +895,7 @@ static int register_trace_fprobe(struct trace_fprobe *tf) trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); - goto end; + return ret; } /* Register fprobe */ @@ -872,8 +905,6 @@ static int register_trace_fprobe(struct trace_fprobe *tf) else dyn_event_add(&tf->devent, trace_probe_event_call(&tf->tp)); -end: - mutex_unlock(&event_mutex); return ret; } @@ -1034,7 +1065,10 @@ static int parse_symbol_and_return(int argc, const char *argv[], return 0; } -static int __trace_fprobe_create(int argc, const char *argv[]) +DEFINE_FREE(module_put, struct module *, if (_T) module_put(_T)) + +static int trace_fprobe_create_internal(int argc, const char *argv[], + struct traceprobe_parse_context *ctx) { /* * Argument syntax: @@ -1060,24 +1094,20 @@ static int __trace_fprobe_create(int argc, const char *argv[]) * Type of args: * FETCHARG:TYPE : use TYPE instead of unsigned long. */ - struct trace_fprobe *tf = NULL; - int i, len, new_argc = 0, ret = 0; + struct trace_fprobe *tf __free(free_trace_fprobe) = NULL; + int i, new_argc = 0, ret = 0; bool is_return = false; - char *symbol = NULL; + char *symbol __free(kfree) = NULL; const char *event = NULL, *group = FPROBE_EVENT_SYSTEM; - const char **new_argv = NULL; - int maxactive = 0; + const char **new_argv __free(kfree) = NULL; char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; char sbuf[KSYM_NAME_LEN]; char abuf[MAX_BTF_ARGS_LEN]; - char *dbuf = NULL; + char *dbuf __free(kfree) = NULL; bool is_tracepoint = false; - struct module *tp_mod = NULL; + struct module *tp_mod __free(module_put) = NULL; struct tracepoint *tpoint = NULL; - struct traceprobe_parse_context ctx = { - .flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE, - }; if ((argv[0][0] != 'f' && argv[0][0] != 't') || argc < 2) return -ECANCELED; @@ -1087,35 +1117,13 @@ static int __trace_fprobe_create(int argc, const char *argv[]) group = TRACEPOINT_EVENT_SYSTEM; } - trace_probe_log_init("trace_fprobe", argc, argv); - - event = strchr(&argv[0][1], ':'); - if (event) - event++; - - if (isdigit(argv[0][1])) { - if (event) - len = event - &argv[0][1] - 1; - else - len = strlen(&argv[0][1]); - if (len > MAX_EVENT_NAME_LEN - 1) { + if (argv[0][1] != '\0') { + if (argv[0][1] != ':') { + trace_probe_log_set_index(0); trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; - } - memcpy(buf, &argv[0][1], len); - buf[len] = '\0'; - ret = kstrtouint(buf, 0, &maxactive); - if (ret || !maxactive) { - trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; - } - /* fprobe rethook instances are iterated over via a list. The - * maximum should stay reasonable. - */ - if (maxactive > RETHOOK_MAXACTIVE_MAX) { - trace_probe_log_err(1, MAXACT_TOO_BIG); - goto parse_error; + return -EINVAL; } + event = &argv[0][2]; } trace_probe_log_set_index(1); @@ -1123,20 +1131,14 @@ static int __trace_fprobe_create(int argc, const char *argv[]) /* a symbol(or tracepoint) must be specified */ ret = parse_symbol_and_return(argc, argv, &symbol, &is_return, is_tracepoint); if (ret < 0) - goto parse_error; - - if (!is_return && maxactive) { - trace_probe_log_set_index(0); - trace_probe_log_err(1, BAD_MAXACT_TYPE); - goto parse_error; - } + return -EINVAL; trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, gbuf, event - argv[0]); if (ret) - goto parse_error; + return -EINVAL; } if (!event) { @@ -1152,67 +1154,62 @@ static int __trace_fprobe_create(int argc, const char *argv[]) } if (is_return) - ctx.flags |= TPARG_FL_RETURN; + ctx->flags |= TPARG_FL_RETURN; else - ctx.flags |= TPARG_FL_FENTRY; + ctx->flags |= TPARG_FL_FENTRY; if (is_tracepoint) { - ctx.flags |= TPARG_FL_TPOINT; + ctx->flags |= TPARG_FL_TPOINT; tpoint = find_tracepoint(symbol, &tp_mod); if (tpoint) { - ctx.funcname = kallsyms_lookup( + ctx->funcname = kallsyms_lookup( (unsigned long)tpoint->probestub, NULL, NULL, NULL, sbuf); } else if (IS_ENABLED(CONFIG_MODULES)) { /* This *may* be loaded afterwards */ tpoint = TRACEPOINT_STUB; - ctx.funcname = symbol; + ctx->funcname = symbol; } else { trace_probe_log_set_index(1); trace_probe_log_err(0, NO_TRACEPOINT); - goto parse_error; + return -EINVAL; } } else - ctx.funcname = symbol; + ctx->funcname = symbol; argc -= 2; argv += 2; new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc, - abuf, MAX_BTF_ARGS_LEN, &ctx); - if (IS_ERR(new_argv)) { - ret = PTR_ERR(new_argv); - new_argv = NULL; - goto out; - } + abuf, MAX_BTF_ARGS_LEN, ctx); + if (IS_ERR(new_argv)) + return PTR_ERR(new_argv); if (new_argv) { argc = new_argc; argv = new_argv; } - if (argc > MAX_TRACE_ARGS) { - ret = -E2BIG; - goto out; - } + if (argc > MAX_TRACE_ARGS) + return -E2BIG; ret = traceprobe_expand_dentry_args(argc, argv, &dbuf); if (ret) - goto out; + return ret; /* setup a probe */ tf = alloc_trace_fprobe(group, event, symbol, tpoint, tp_mod, - maxactive, argc, is_return); + argc, is_return); if (IS_ERR(tf)) { ret = PTR_ERR(tf); /* This must return -ENOMEM, else there is a bug */ WARN_ON_ONCE(ret != -ENOMEM); - goto out; /* We know tf is not allocated */ + return ret; } /* parse arguments */ for (i = 0; i < argc; i++) { trace_probe_log_set_index(i + 2); - ctx.offset = 0; - ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx); + ctx->offset = 0; + ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], ctx); if (ret) - goto error; /* This can be -ENOMEM */ + return ret; /* This can be -ENOMEM */ } if (is_return && tf->tp.entry_arg) { @@ -1223,7 +1220,7 @@ static int __trace_fprobe_create(int argc, const char *argv[]) ret = traceprobe_set_print_fmt(&tf->tp, is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL); if (ret < 0) - goto error; + return ret; ret = register_trace_fprobe(tf); if (ret) { @@ -1234,29 +1231,32 @@ static int __trace_fprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, BAD_PROBE_ADDR); else if (ret != -ENOMEM && ret != -EEXIST) trace_probe_log_err(0, FAIL_REG_PROBE); - goto error; + return -EINVAL; } -out: - if (tp_mod) - module_put(tp_mod); + /* 'tf' is successfully registered. To avoid freeing, assign NULL. */ + tf = NULL; + + return 0; +} + +static int trace_fprobe_create_cb(int argc, const char *argv[]) +{ + struct traceprobe_parse_context ctx = { + .flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE, + }; + int ret; + + trace_probe_log_init("trace_fprobe", argc, argv); + ret = trace_fprobe_create_internal(argc, argv, &ctx); traceprobe_finish_parse(&ctx); trace_probe_log_clear(); - kfree(new_argv); - kfree(symbol); - kfree(dbuf); return ret; - -parse_error: - ret = -EINVAL; -error: - free_trace_fprobe(tf); - goto out; } static int trace_fprobe_create(const char *raw_command) { - return trace_probe_create(raw_command, __trace_fprobe_create); + return trace_probe_create(raw_command, trace_fprobe_create_cb); } static int trace_fprobe_release(struct dyn_event *ev) @@ -1278,8 +1278,6 @@ static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev) seq_putc(m, 't'); else seq_putc(m, 'f'); - if (trace_fprobe_is_return(tf) && tf->fp.nr_maxactive) - seq_printf(m, "%d", tf->fp.nr_maxactive); seq_printf(m, ":%s/%s", trace_probe_group_name(&tf->tp), trace_probe_name(&tf->tp)); diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 74c353164ca1..d358c9935164 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -176,7 +176,8 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(&tr->array_buffer); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* fregs are guaranteed not to be NULL if HAVE_DYNAMIC_FTRACE_WITH_ARGS is set */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) static __always_inline unsigned long function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs) { diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 5504b5e4e7b4..54d850997c0a 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -175,16 +175,16 @@ struct fgraph_times { }; int trace_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; struct trace_array_cpu *data; struct fgraph_times *ftimes; - unsigned long flags; unsigned int trace_ctx; long disabled; - int ret; + int ret = 0; int cpu; if (*task_var & TRACE_GRAPH_NOTRACE) @@ -235,25 +235,21 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, if (tracing_thresh) return 1; - local_irq_save(flags); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - trace_ctx = tracing_gen_ctx_flags(flags); - if (unlikely(IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && - tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR))) { + disabled = atomic_read(&data->disabled); + if (likely(!disabled)) { + trace_ctx = tracing_gen_ctx(); + if (IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && + tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR)) { unsigned long retaddr = ftrace_graph_top_ret_addr(current); - ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx, retaddr); - } else + } else { ret = __trace_graph_entry(tr, trace, trace_ctx); - } else { - ret = 0; + } } - - atomic_dec(&data->disabled); - local_irq_restore(flags); + preempt_enable_notrace(); return ret; } @@ -270,12 +266,10 @@ __trace_graph_function(struct trace_array *tr, struct ftrace_graph_ret ret = { .func = ip, .depth = 0, - .calltime = time, - .rettime = time, }; __trace_graph_entry(tr, &ent, trace_ctx); - __trace_graph_return(tr, &ret, trace_ctx); + __trace_graph_return(tr, &ret, trace_ctx, time, time); } void @@ -287,8 +281,9 @@ trace_graph_function(struct trace_array *tr, } void __trace_graph_return(struct trace_array *tr, - struct ftrace_graph_ret *trace, - unsigned int trace_ctx) + struct ftrace_graph_ret *trace, + unsigned int trace_ctx, + u64 calltime, u64 rettime) { struct ring_buffer_event *event; struct trace_buffer *buffer = tr->array_buffer.buffer; @@ -300,6 +295,8 @@ void __trace_graph_return(struct trace_array *tr, return; entry = ring_buffer_event_data(event); entry->ret = *trace; + entry->calltime = calltime; + entry->rettime = rettime; trace_buffer_unlock_commit_nostack(buffer, event); } @@ -314,18 +311,20 @@ static void handle_nosleeptime(struct ftrace_graph_ret *trace, } void trace_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, struct ftrace_regs *fregs) { unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; struct trace_array_cpu *data; struct fgraph_times *ftimes; - unsigned long flags; unsigned int trace_ctx; + u64 calltime, rettime; long disabled; int size; int cpu; + rettime = trace_clock_local(); + ftrace_graph_addr_finish(gops, trace); if (*task_var & TRACE_GRAPH_NOTRACE) { @@ -339,22 +338,22 @@ void trace_graph_return(struct ftrace_graph_ret *trace, handle_nosleeptime(trace, ftimes, size); - trace->calltime = ftimes->calltime; + calltime = ftimes->calltime; - local_irq_save(flags); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - trace_ctx = tracing_gen_ctx_flags(flags); - __trace_graph_return(tr, trace, trace_ctx); + disabled = atomic_read(&data->disabled); + if (likely(!disabled)) { + trace_ctx = tracing_gen_ctx(); + __trace_graph_return(tr, trace, trace_ctx, calltime, rettime); } - atomic_dec(&data->disabled); - local_irq_restore(flags); + preempt_enable_notrace(); } static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_times *ftimes; int size; @@ -372,13 +371,11 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, handle_nosleeptime(trace, ftimes, size); - trace->calltime = ftimes->calltime; - if (tracing_thresh && - (trace->rettime - ftimes->calltime < tracing_thresh)) + (trace_clock_local() - ftimes->calltime < tracing_thresh)) return; else - trace_graph_return(trace, gops); + trace_graph_return(trace, gops, fregs); } static struct fgraph_ops funcgraph_ops = { @@ -861,7 +858,7 @@ print_graph_entry_leaf(struct trace_iterator *iter, graph_ret = &ret_entry->ret; call = &entry->graph_ent; - duration = graph_ret->rettime - graph_ret->calltime; + duration = ret_entry->rettime - ret_entry->calltime; func = call->func + iter->tr->text_delta; @@ -1142,11 +1139,14 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, } static enum print_line_t -print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, +print_graph_return(struct ftrace_graph_ret_entry *retentry, struct trace_seq *s, struct trace_entry *ent, struct trace_iterator *iter, u32 flags) { - unsigned long long duration = trace->rettime - trace->calltime; + struct ftrace_graph_ret *trace = &retentry->ret; + u64 calltime = retentry->calltime; + u64 rettime = retentry->rettime; + unsigned long long duration = rettime - calltime; struct fgraph_data *data = iter->private; struct trace_array *tr = iter->tr; unsigned long func; @@ -1347,7 +1347,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags) case TRACE_GRAPH_RET: { struct ftrace_graph_ret_entry *field; trace_assign_type(field, entry); - return print_graph_return(&field->ret, s, entry, iter, flags); + return print_graph_return(field, s, entry, iter, flags); } case TRACE_STACK: case TRACE_FN: diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index fce064e20570..7294ad676379 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -176,12 +176,14 @@ static int irqsoff_display_graph(struct trace_array *tr, int set) } static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; unsigned long flags; unsigned int trace_ctx; + u64 *calltime; int ret; if (ftrace_graph_ignore_func(gops, trace)) @@ -199,6 +201,12 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, if (!func_prolog_dec(tr, &data, &flags)) return 0; + calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime)); + if (!calltime) + return 0; + + *calltime = trace_clock_local(); + trace_ctx = tracing_gen_ctx_flags(flags); ret = __trace_graph_entry(tr, trace, trace_ctx); atomic_dec(&data->disabled); @@ -207,20 +215,29 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, } static void irqsoff_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; unsigned long flags; unsigned int trace_ctx; + u64 *calltime; + u64 rettime; + int size; ftrace_graph_addr_finish(gops, trace); if (!func_prolog_dec(tr, &data, &flags)) return; + rettime = trace_clock_local(); + calltime = fgraph_retrieve_data(gops->idx, &size); + if (!calltime) + return; + trace_ctx = tracing_gen_ctx_flags(flags); - __trace_graph_return(tr, trace, trace_ctx); + __trace_graph_return(tr, trace, trace_ctx, *calltime, rettime); atomic_dec(&data->disabled); } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 263fac44d3ca..d8d5f18a141a 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) "trace_kprobe: " fmt #include +#include #include #include #include @@ -257,6 +258,9 @@ static void free_trace_kprobe(struct trace_kprobe *tk) } } +DEFINE_FREE(free_trace_kprobe, struct trace_kprobe *, + if (!IS_ERR_OR_NULL(_T)) free_trace_kprobe(_T)) + /* * Allocate new trace_probe and initialize it (including kprobes). */ @@ -268,7 +272,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, int maxactive, int nargs, bool is_return) { - struct trace_kprobe *tk; + struct trace_kprobe *tk __free(free_trace_kprobe) = NULL; int ret = -ENOMEM; tk = kzalloc(struct_size(tk, tp.args, nargs), GFP_KERNEL); @@ -277,12 +281,12 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, tk->nhit = alloc_percpu(unsigned long); if (!tk->nhit) - goto error; + return ERR_PTR(ret); if (symbol) { tk->symbol = kstrdup(symbol, GFP_KERNEL); if (!tk->symbol) - goto error; + return ERR_PTR(ret); tk->rp.kp.symbol_name = tk->symbol; tk->rp.kp.offset = offs; } else @@ -299,13 +303,10 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, ret = trace_probe_init(&tk->tp, event, group, false, nargs); if (ret < 0) - goto error; + return ERR_PTR(ret); dyn_event_init(&tk->devent, &trace_kprobe_ops); - return tk; -error: - free_trace_kprobe(tk); - return ERR_PTR(ret); + return_ptr(tk); } static struct trace_kprobe *find_trace_kprobe(const char *event, @@ -634,7 +635,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk) struct trace_kprobe *old_tk; int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); old_tk = find_trace_kprobe(trace_probe_name(&tk->tp), trace_probe_group_name(&tk->tp)); @@ -642,11 +643,9 @@ static int register_trace_kprobe(struct trace_kprobe *tk) if (trace_kprobe_is_return(tk) != trace_kprobe_is_return(old_tk)) { trace_probe_log_set_index(0); trace_probe_log_err(0, DIFF_PROBE_TYPE); - ret = -EEXIST; - } else { - ret = append_trace_kprobe(tk, old_tk); + return -EEXIST; } - goto end; + return append_trace_kprobe(tk, old_tk); } /* Register new event */ @@ -657,7 +656,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk) trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); - goto end; + return ret; } /* Register k*probe */ @@ -672,8 +671,6 @@ static int register_trace_kprobe(struct trace_kprobe *tk) else dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp)); -end: - mutex_unlock(&event_mutex); return ret; } @@ -706,7 +703,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, return NOTIFY_DONE; /* Update probes on coming module */ - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); for_each_trace_kprobe(tk, pos) { if (trace_kprobe_within_module(tk, mod)) { /* Don't need to check busy - this should have gone. */ @@ -718,14 +715,13 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, module_name(mod), ret); } } - mutex_unlock(&event_mutex); return NOTIFY_DONE; } static struct notifier_block trace_kprobe_module_nb = { .notifier_call = trace_kprobe_module_callback, - .priority = 1 /* Invoked after kprobe module callback */ + .priority = 2 /* Invoked after kprobe and jump_label module callback */ }; static int trace_kprobe_register_module_notifier(void) { @@ -840,7 +836,8 @@ out: static int trace_kprobe_entry_handler(struct kretprobe_instance *ri, struct pt_regs *regs); -static int __trace_kprobe_create(int argc, const char *argv[]) +static int trace_kprobe_create_internal(int argc, const char *argv[], + struct traceprobe_parse_context *ctx) { /* * Argument syntax: @@ -866,11 +863,12 @@ static int __trace_kprobe_create(int argc, const char *argv[]) * Type of args: * FETCHARG:TYPE : use TYPE instead of unsigned long. */ - struct trace_kprobe *tk = NULL; + struct trace_kprobe *tk __free(free_trace_kprobe) = NULL; int i, len, new_argc = 0, ret = 0; bool is_return = false; - char *symbol = NULL, *tmp = NULL; - const char **new_argv = NULL; + char *symbol __free(kfree) = NULL; + char *tmp = NULL; + const char **new_argv __free(kfree) = NULL; const char *event = NULL, *group = KPROBE_EVENT_SYSTEM; enum probe_print_type ptype; int maxactive = 0; @@ -879,8 +877,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; char abuf[MAX_BTF_ARGS_LEN]; - char *dbuf = NULL; - struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL }; + char *dbuf __free(kfree) = NULL; switch (argv[0][0]) { case 'r': @@ -894,8 +891,6 @@ static int __trace_kprobe_create(int argc, const char *argv[]) if (argc < 2) return -ECANCELED; - trace_probe_log_init("trace_kprobe", argc, argv); - event = strchr(&argv[0][1], ':'); if (event) event++; @@ -903,7 +898,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) if (isdigit(argv[0][1])) { if (!is_return) { trace_probe_log_err(1, BAD_MAXACT_TYPE); - goto parse_error; + return -EINVAL; } if (event) len = event - &argv[0][1] - 1; @@ -911,21 +906,21 @@ static int __trace_kprobe_create(int argc, const char *argv[]) len = strlen(&argv[0][1]); if (len > MAX_EVENT_NAME_LEN - 1) { trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; + return -EINVAL; } memcpy(buf, &argv[0][1], len); buf[len] = '\0'; ret = kstrtouint(buf, 0, &maxactive); if (ret || !maxactive) { trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; + return -EINVAL; } /* kretprobes instances are iterated over via a list. The * maximum should stay reasonable. */ if (maxactive > KRETPROBE_MAXACTIVE_MAX) { trace_probe_log_err(1, MAXACT_TOO_BIG); - goto parse_error; + return -EINVAL; } } @@ -934,10 +929,9 @@ static int __trace_kprobe_create(int argc, const char *argv[]) if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) { trace_probe_log_set_index(1); /* Check whether uprobe event specified */ - if (strchr(argv[1], '/') && strchr(argv[1], ':')) { - ret = -ECANCELED; - goto error; - } + if (strchr(argv[1], '/') && strchr(argv[1], ':')) + return -ECANCELED; + /* a symbol specified */ symbol = kstrdup(argv[1], GFP_KERNEL); if (!symbol) @@ -950,7 +944,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) is_return = true; } else { trace_probe_log_err(tmp - symbol, BAD_ADDR_SUFFIX); - goto parse_error; + return -EINVAL; } } @@ -958,7 +952,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret || offset < 0 || offset > UINT_MAX) { trace_probe_log_err(0, BAD_PROBE_ADDR); - goto parse_error; + return -EINVAL; } ret = validate_probe_symbol(symbol); if (ret) { @@ -966,17 +960,17 @@ static int __trace_kprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, NON_UNIQ_SYMBOL); else trace_probe_log_err(0, BAD_PROBE_ADDR); - goto parse_error; + return -EINVAL; } if (is_return) - ctx.flags |= TPARG_FL_RETURN; + ctx->flags |= TPARG_FL_RETURN; ret = kprobe_on_func_entry(NULL, symbol, offset); if (ret == 0 && !is_return) - ctx.flags |= TPARG_FL_FENTRY; + ctx->flags |= TPARG_FL_FENTRY; /* Defer the ENOENT case until register kprobe */ if (ret == -EINVAL && is_return) { trace_probe_log_err(0, BAD_RETPROBE); - goto parse_error; + return -EINVAL; } } @@ -985,7 +979,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ret = traceprobe_parse_event_name(&event, &group, gbuf, event - argv[0]); if (ret) - goto parse_error; + return ret; } if (!event) { @@ -1001,26 +995,24 @@ static int __trace_kprobe_create(int argc, const char *argv[]) } argc -= 2; argv += 2; - ctx.funcname = symbol; + ctx->funcname = symbol; new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc, - abuf, MAX_BTF_ARGS_LEN, &ctx); + abuf, MAX_BTF_ARGS_LEN, ctx); if (IS_ERR(new_argv)) { ret = PTR_ERR(new_argv); new_argv = NULL; - goto out; + return ret; } if (new_argv) { argc = new_argc; argv = new_argv; } - if (argc > MAX_TRACE_ARGS) { - ret = -E2BIG; - goto out; - } + if (argc > MAX_TRACE_ARGS) + return -E2BIG; ret = traceprobe_expand_dentry_args(argc, argv, &dbuf); if (ret) - goto out; + return ret; /* setup a probe */ tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive, @@ -1029,16 +1021,16 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ret = PTR_ERR(tk); /* This must return -ENOMEM, else there is a bug */ WARN_ON_ONCE(ret != -ENOMEM); - goto out; /* We know tk is not allocated */ + return ret; /* We know tk is not allocated */ } /* parse arguments */ for (i = 0; i < argc; i++) { trace_probe_log_set_index(i + 2); - ctx.offset = 0; - ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], &ctx); + ctx->offset = 0; + ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], ctx); if (ret) - goto error; /* This can be -ENOMEM */ + return ret; /* This can be -ENOMEM */ } /* entry handler for kretprobe */ if (is_return && tk->tp.entry_arg) { @@ -1049,7 +1041,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ptype = is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; ret = traceprobe_set_print_fmt(&tk->tp, ptype); if (ret < 0) - goto error; + return ret; ret = register_trace_kprobe(tk); if (ret) { @@ -1060,27 +1052,34 @@ static int __trace_kprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, BAD_PROBE_ADDR); else if (ret != -ENOMEM && ret != -EEXIST) trace_probe_log_err(0, FAIL_REG_PROBE); - goto error; + return ret; } + /* + * Here, 'tk' has been registered to the list successfully, + * so we don't need to free it. + */ + tk = NULL; + + return 0; +} + +static int trace_kprobe_create_cb(int argc, const char *argv[]) +{ + struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL }; + int ret; + + trace_probe_log_init("trace_kprobe", argc, argv); + + ret = trace_kprobe_create_internal(argc, argv, &ctx); -out: traceprobe_finish_parse(&ctx); trace_probe_log_clear(); - kfree(new_argv); - kfree(symbol); - kfree(dbuf); return ret; - -parse_error: - ret = -EINVAL; -error: - free_trace_kprobe(tk); - goto out; } static int trace_kprobe_create(const char *raw_command) { - return trace_probe_create(raw_command, __trace_kprobe_create); + return trace_probe_create(raw_command, trace_kprobe_create_cb); } static int create_or_delete_trace_kprobe(const char *raw_command) @@ -1896,7 +1895,7 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, bool is_return) { enum probe_print_type ptype; - struct trace_kprobe *tk; + struct trace_kprobe *tk __free(free_trace_kprobe) = NULL; int ret; char *event; @@ -1927,19 +1926,14 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, ptype = trace_kprobe_is_return(tk) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; - if (traceprobe_set_print_fmt(&tk->tp, ptype) < 0) { - ret = -ENOMEM; - goto error; - } + if (traceprobe_set_print_fmt(&tk->tp, ptype) < 0) + return ERR_PTR(-ENOMEM); ret = __register_trace_kprobe(tk); if (ret < 0) - goto error; + return ERR_PTR(ret); - return trace_probe_event_call(&tk->tp); -error: - free_trace_kprobe(tk); - return ERR_PTR(ret); + return trace_probe_event_call(&(no_free_ptr(tk)->tp)); } void destroy_local_trace_kprobe(struct trace_event_call *event_call) @@ -1968,13 +1962,12 @@ static __init void enable_boot_kprobe_events(void) struct trace_kprobe *tk; struct dyn_event *pos; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); for_each_trace_kprobe(tk, pos) { list_for_each_entry(file, &tr->events, list) if (file->event_call == trace_probe_event_call(&tk->tp)) trace_event_enable_disable(file, 1, 0); } - mutex_unlock(&event_mutex); } static __init void setup_boot_kprobe_events(void) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index b9f96c77527d..f3a2722ee4c0 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1229,6 +1229,8 @@ static void trace_sched_migrate_callback(void *data, struct task_struct *p, int } } +static bool monitor_enabled; + static int register_migration_monitor(void) { int ret = 0; @@ -1237,16 +1239,25 @@ static int register_migration_monitor(void) * Timerlat thread migration check is only required when running timerlat in user-space. * Thus, enable callback only if timerlat is set with no workload. */ - if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options)) + if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options)) { + if (WARN_ON_ONCE(monitor_enabled)) + return 0; + ret = register_trace_sched_migrate_task(trace_sched_migrate_callback, NULL); + if (!ret) + monitor_enabled = true; + } return ret; } static void unregister_migration_monitor(void) { - if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options)) - unregister_trace_sched_migrate_task(trace_sched_migrate_callback, NULL); + if (!monitor_enabled) + return; + + unregister_trace_sched_migrate_task(trace_sched_migrate_callback, NULL); + monitor_enabled = false; } #else static int register_migration_monitor(void) @@ -2083,26 +2094,21 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy) { unsigned int cpu = smp_processor_id(); - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (!osnoise_has_registered_instances()) - goto out_unlock_trace; + return; - mutex_lock(&interface_lock); - cpus_read_lock(); + guard(mutex)(&interface_lock); + guard(cpus_read_lock)(); if (!cpu_online(cpu)) - goto out_unlock; + return; + if (!cpumask_test_cpu(cpu, &osnoise_cpumask)) - goto out_unlock; + return; start_kthread(cpu); - -out_unlock: - cpus_read_unlock(); - mutex_unlock(&interface_lock); -out_unlock_trace: - mutex_unlock(&trace_types_lock); } static DECLARE_WORK(osnoise_hotplug_work, osnoise_hotplug_workfn); @@ -2300,31 +2306,22 @@ static ssize_t osnoise_cpus_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - char *mask_str; + char *mask_str __free(kfree) = NULL; int len; - mutex_lock(&interface_lock); + guard(mutex)(&interface_lock); len = snprintf(NULL, 0, "%*pbl\n", cpumask_pr_args(&osnoise_cpumask)) + 1; mask_str = kmalloc(len, GFP_KERNEL); - if (!mask_str) { - count = -ENOMEM; - goto out_unlock; - } + if (!mask_str) + return -ENOMEM; len = snprintf(mask_str, len, "%*pbl\n", cpumask_pr_args(&osnoise_cpumask)); - if (len >= count) { - count = -EINVAL; - goto out_free; - } + if (len >= count) + return -EINVAL; count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len); -out_free: - kfree(mask_str); -out_unlock: - mutex_unlock(&interface_lock); - return count; } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index da748b7cbc4d..03d56f711ad1 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep); void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...) { + struct trace_seq *s = &iter->seq; va_list ap; + if (ignore_event(iter)) + return; + va_start(ap, fmt); - trace_check_vprintf(iter, trace_event_format(iter, fmt), ap); + trace_seq_vprintf(s, trace_event_format(iter, fmt), ap); va_end(ap); } EXPORT_SYMBOL(trace_event_printf); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 16a5e368e7b7..8f58ee1e8858 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1409,7 +1409,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, struct traceprobe_parse_context *ctx) { struct fetch_insn *code, *tmp = NULL; - char *type, *arg; + char *type, *arg __free(kfree) = NULL; int ret, len; len = strlen(argv); @@ -1426,22 +1426,16 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, return -ENOMEM; parg->comm = kstrdup(arg, GFP_KERNEL); - if (!parg->comm) { - ret = -ENOMEM; - goto out; - } + if (!parg->comm) + return -ENOMEM; type = parse_probe_arg_type(arg, parg, ctx); - if (IS_ERR(type)) { - ret = PTR_ERR(type); - goto out; - } + if (IS_ERR(type)) + return PTR_ERR(type); code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL); - if (!code) { - ret = -ENOMEM; - goto out; - } + if (!code) + return -ENOMEM; code[FETCH_INSN_MAX - 1].op = FETCH_OP_END; ctx->last_type = NULL; @@ -1497,8 +1491,6 @@ fail: kfree(code->data); } kfree(tmp); -out: - kfree(arg); return ret; } @@ -1668,7 +1660,7 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[], { const struct btf_param *params = NULL; int i, j, n, used, ret, args_idx = -1; - const char **new_argv = NULL; + const char **new_argv __free(kfree) = NULL; ret = argv_has_var_arg(argc, argv, &args_idx, ctx); if (ret < 0) @@ -1707,7 +1699,7 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[], ret = sprint_nth_btf_arg(n, "", buf + used, bufsize - used, ctx); if (ret < 0) - goto error; + return ERR_PTR(ret); new_argv[j++] = buf + used; used += ret + 1; @@ -1721,25 +1713,20 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[], n = simple_strtoul(argv[i] + 4, &type, 10); if (type && !(*type == ':' || *type == '\0')) { trace_probe_log_err(0, BAD_VAR); - ret = -ENOENT; - goto error; + return ERR_PTR(-ENOENT); } /* Note: $argN starts from $arg1 */ ret = sprint_nth_btf_arg(n - 1, type, buf + used, bufsize - used, ctx); if (ret < 0) - goto error; + return ERR_PTR(ret); new_argv[j++] = buf + used; used += ret + 1; } else new_argv[j++] = argv[i]; } - return new_argv; - -error: - kfree(new_argv); - return ERR_PTR(ret); + return_ptr(new_argv); } /* @buf: *buf must be equal to NULL. Caller must to free *buf */ @@ -1747,14 +1734,14 @@ int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf) { int i, used, ret; const int bufsize = MAX_DENTRY_ARGS_LEN; - char *tmpbuf = NULL; + char *tmpbuf __free(kfree) = NULL; if (*buf) return -EINVAL; used = 0; for (i = 0; i < argc; i++) { - char *tmp; + char *tmp __free(kfree) = NULL; char *equal; size_t arg_len; @@ -1769,7 +1756,7 @@ int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf) tmp = kstrdup(argv[i], GFP_KERNEL); if (!tmp) - goto nomem; + return -ENOMEM; equal = strchr(tmp, '='); if (equal) @@ -1790,18 +1777,14 @@ int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf) offsetof(struct file, f_path.dentry), equal ? equal + 1 : tmp); - kfree(tmp); if (ret >= bufsize - used) - goto nomem; + return -ENOMEM; argv[i] = tmpbuf + used; used += ret + 1; } - *buf = tmpbuf; + *buf = no_free_ptr(tmpbuf); return 0; -nomem: - kfree(tmpbuf); - return -ENOMEM; } void traceprobe_finish_parse(struct traceprobe_parse_context *ctx) diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 2caf0d2afb32..f39b37fcdb3b 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -232,7 +232,7 @@ array: /* Sum up total data length for dynamic arrays (strings) */ static nokprobe_inline int -__get_data_size(struct trace_probe *tp, struct pt_regs *regs, void *edata) +__get_data_size(struct trace_probe *tp, void *regs, void *edata) { struct probe_arg *arg; int i, len, ret = 0; diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 573b5d8e8a28..cb49f7279dc8 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -442,7 +442,7 @@ int trace_alloc_tgid_map(void) if (tgid_map) return 0; - tgid_map_max = pid_max; + tgid_map_max = init_pid_ns.pid_max; map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map), GFP_KERNEL); if (!map) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index d6c7f18daa15..af30586f1aea 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -113,11 +113,13 @@ static int wakeup_display_graph(struct trace_array *tr, int set) } static int wakeup_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; unsigned int trace_ctx; + u64 *calltime; int ret = 0; if (ftrace_graph_ignore_func(gops, trace)) @@ -135,6 +137,12 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace, if (!func_prolog_preempt_disable(tr, &data, &trace_ctx)) return 0; + calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime)); + if (!calltime) + return 0; + + *calltime = trace_clock_local(); + ret = __trace_graph_entry(tr, trace, trace_ctx); atomic_dec(&data->disabled); preempt_enable_notrace(); @@ -143,18 +151,28 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace, } static void wakeup_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; unsigned int trace_ctx; + u64 *calltime; + u64 rettime; + int size; ftrace_graph_addr_finish(gops, trace); if (!func_prolog_preempt_disable(tr, &data, &trace_ctx)) return; - __trace_graph_return(tr, trace, trace_ctx); + rettime = trace_clock_local(); + + calltime = fgraph_retrieve_data(gops->idx, &size); + if (!calltime) + return; + + __trace_graph_return(tr, trace, trace_ctx, *calltime, rettime); atomic_dec(&data->disabled); preempt_enable_notrace(); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 38b5754790c9..d88c44f1dfa5 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -774,7 +774,8 @@ struct fgraph_fixture { }; static __init int store_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops); const char *type = fixture->store_type_name; @@ -807,7 +808,8 @@ static __init int store_entry(struct ftrace_graph_ent *trace, } static __init void store_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops); const char *type = fixture->store_type_name; @@ -1025,7 +1027,8 @@ static unsigned int graph_hang_thresh; /* Wrap the real function entry probe to avoid possible hanging */ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { /* This is harmlessly racy, we want to approximately detect a hang */ if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { @@ -1039,7 +1042,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace, return 0; } - return trace_graph_entry(trace, gops); + return trace_graph_entry(trace, gops, fregs); } static struct fgraph_ops fgraph_ops __initdata = { diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 7f9572a37333..14c6f272c4d8 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -520,20 +520,18 @@ stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer, int was_enabled; int ret; - mutex_lock(&stack_sysctl_mutex); + guard(mutex)(&stack_sysctl_mutex); was_enabled = !!stack_tracer_enabled; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (was_enabled == !!stack_tracer_enabled)) - goto out; + return ret; if (stack_tracer_enabled) register_ftrace_function(&trace_ops); else unregister_ftrace_function(&trace_ops); - out: - mutex_unlock(&stack_sysctl_mutex); return ret; } diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index bb247beec447..b3b5586f104d 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -128,7 +128,7 @@ static int stat_seq_init(struct stat_session *session) int ret = 0; int i; - mutex_lock(&session->stat_mutex); + guard(mutex)(&session->stat_mutex); __reset_stat_session(session); if (!ts->stat_cmp) @@ -136,11 +136,11 @@ static int stat_seq_init(struct stat_session *session) stat = ts->stat_start(ts); if (!stat) - goto exit; + return 0; ret = insert_stat(root, stat, ts->stat_cmp); if (ret) - goto exit; + return ret; /* * Iterate over the tracer stat entries and store them in an rbtree. @@ -157,13 +157,10 @@ static int stat_seq_init(struct stat_session *session) goto exit_free_rbtree; } -exit: - mutex_unlock(&session->stat_mutex); return ret; exit_free_rbtree: __reset_stat_session(session); - mutex_unlock(&session->stat_mutex); return ret; } @@ -308,7 +305,7 @@ static int init_stat_file(struct stat_session *session) int register_stat_tracer(struct tracer_stat *trace) { struct stat_session *session, *node; - int ret = -EINVAL; + int ret; if (!trace) return -EINVAL; @@ -316,18 +313,18 @@ int register_stat_tracer(struct tracer_stat *trace) if (!trace->stat_start || !trace->stat_next || !trace->stat_show) return -EINVAL; + guard(mutex)(&all_stat_sessions_mutex); + /* Already registered? */ - mutex_lock(&all_stat_sessions_mutex); list_for_each_entry(node, &all_stat_sessions, session_list) { if (node->ts == trace) - goto out; + return -EINVAL; } - ret = -ENOMEM; /* Init the session */ session = kzalloc(sizeof(*session), GFP_KERNEL); if (!session) - goto out; + return -ENOMEM; session->ts = trace; INIT_LIST_HEAD(&session->session_list); @@ -336,16 +333,13 @@ int register_stat_tracer(struct tracer_stat *trace) ret = init_stat_file(session); if (ret) { destroy_session(session); - goto out; + return ret; } - ret = 0; /* Register */ list_add_tail(&session->session_list, &all_stat_sessions); - out: - mutex_unlock(&all_stat_sessions_mutex); - return ret; + return 0; } void unregister_stat_tracer(struct tracer_stat *trace) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 4875e7f5de3d..ccc762fbb69c 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -498,11 +498,11 @@ static int register_trace_uprobe(struct trace_uprobe *tu) struct trace_uprobe *old_tu; int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); ret = validate_ref_ctr_offset(tu); if (ret) - goto end; + return ret; /* register as an event */ old_tu = find_probe_event(trace_probe_name(&tu->tp), @@ -511,11 +511,9 @@ static int register_trace_uprobe(struct trace_uprobe *tu) if (is_ret_probe(tu) != is_ret_probe(old_tu)) { trace_probe_log_set_index(0); trace_probe_log_err(0, DIFF_PROBE_TYPE); - ret = -EEXIST; - } else { - ret = append_trace_uprobe(tu, old_tu); + return -EEXIST; } - goto end; + return append_trace_uprobe(tu, old_tu); } ret = register_uprobe_event(tu); @@ -525,14 +523,11 @@ static int register_trace_uprobe(struct trace_uprobe *tu) trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); - goto end; + return ret; } dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); -end: - mutex_unlock(&event_mutex); - return ret; } diff --git a/kernel/ucount.c b/kernel/ucount.c index f950b5e59d63..86c5f1c0bad9 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -164,8 +164,8 @@ struct ucounts *get_ucounts(struct ucounts *ucounts) struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) { struct hlist_head *hashent = ucounts_hashentry(ns, uid); - struct ucounts *ucounts, *new; bool wrapped; + struct ucounts *ucounts, *new = NULL; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); @@ -182,17 +182,17 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); - if (ucounts) { - kfree(new); - } else { + if (!ucounts) { hlist_add_head(&new->node, hashent); get_user_ns(new->ns); spin_unlock_irq(&ucounts_lock); return new; } } + wrapped = !get_ucounts_or_wrap(ucounts); spin_unlock_irq(&ucounts_lock); + kfree(new); if (wrapped) { put_ucounts(ucounts); return NULL; diff --git a/kernel/umh.c b/kernel/umh.c index be9234270777..b4da45a3a7cf 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -544,7 +544,7 @@ static int proc_cap_handler(const struct ctl_table *table, int write, return 0; } -static struct ctl_table usermodehelper_table[] = { +static const struct ctl_table usermodehelper_table[] = { { .procname = "bset", .data = &usermodehelper_bset, diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 7282f61a8650..bfbaaecb1dd4 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -75,7 +75,7 @@ static DEFINE_CTL_TABLE_POLL(hostname_poll); static DEFINE_CTL_TABLE_POLL(domainname_poll); // Note: update 'enum uts_proc' to match any changes to this table -static struct ctl_table uts_kern_table[] = { +static const struct ctl_table uts_kern_table[] = { { .procname = "arch", .data = init_uts_ns.name.machine, @@ -129,7 +129,7 @@ static struct ctl_table uts_kern_table[] = { */ void uts_proc_notify(enum uts_proc proc) { - struct ctl_table *table = &uts_kern_table[proc]; + const struct ctl_table *table = &uts_kern_table[proc]; proc_sys_poll_notify(table->poll); } diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 1895fbc32bcb..5267adeaa403 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -71,7 +71,7 @@ static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, bit /= WATCH_QUEUE_NOTE_SIZE; page = buf->page; - bit += page->index; + bit += page->private; set_bit(bit, wqueue->notes_bitmap); generic_pipe_buf_release(pipe, buf); @@ -278,7 +278,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) pages[i] = alloc_page(GFP_KERNEL); if (!pages[i]) goto error_p; - pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE; + pages[i]->private = i * WATCH_QUEUE_NOTES_PER_PAGE; } bitmap = bitmap_alloc(nr_notes, GFP_KERNEL); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 41e0f7e9fa35..b2da7de39d06 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -190,7 +190,7 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) * with printk_cpu_sync_get_irqsave() that we can still at least * get the message about the lockup out. */ - pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", cpu); + pr_emerg("CPU%u: Watchdog detected hard LOCKUP on cpu %u\n", this_cpu, cpu); printk_cpu_sync_get_irqsave(flags); print_modules(); @@ -1094,7 +1094,7 @@ static int proc_watchdog_cpumask(const struct ctl_table *table, int write, static const int sixty = 60; -static struct ctl_table watchdog_sysctls[] = { +static const struct ctl_table watchdog_sysctls[] = { { .procname = "watchdog", .data = &watchdog_user_enabled, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8b07576814a5..3c2c45313c88 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2180,7 +2180,7 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, debug_work_activate(work); /* record the work call stack in order to print it in KASAN reports */ - kasan_record_aux_stack_noalloc(work); + kasan_record_aux_stack(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); @@ -2508,6 +2508,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, return; } + WARN_ON_ONCE(cpu != WORK_CPU_UNBOUND && !cpu_online(cpu)); dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; @@ -2533,6 +2534,12 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, * @dwork: work to queue * @delay: number of jiffies to wait before queueing * + * We queue the delayed_work to a specific CPU, for non-zero delays the + * caller must ensure it is online and can't go away. Callers that fail + * to ensure this, may get @dwork->timer queued to an offlined CPU and + * this will prevent queueing of @dwork->work unless the offlined CPU + * becomes online again. + * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. @@ -3680,23 +3687,27 @@ void workqueue_softirq_dead(unsigned int cpu) * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) + * @from_cancel: are we called from the work cancel path * * %current is trying to flush the whole @target_wq or @target_work on it. - * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not - * reclaiming memory or running on a workqueue which doesn't have - * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to - * a deadlock. + * If this is not the cancel path (which implies work being flushed is either + * already running, or will not be at all), check if @target_wq doesn't have + * %WQ_MEM_RECLAIM and verify that %current is not reclaiming memory or running + * on a workqueue which doesn't have %WQ_MEM_RECLAIM as that can break forward- + * progress guarantee leading to a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, - struct work_struct *target_work) + struct work_struct *target_work, + bool from_cancel) { - work_func_t target_func = target_work ? target_work->func : NULL; + work_func_t target_func; struct worker *worker; - if (target_wq->flags & WQ_MEM_RECLAIM) + if (from_cancel || target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); + target_func = target_work ? target_work->func : NULL; WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", @@ -3980,7 +3991,7 @@ void __flush_workqueue(struct workqueue_struct *wq) list_add_tail(&this_flusher.list, &wq->flusher_overflow); } - check_flush_dependency(wq, NULL); + check_flush_dependency(wq, NULL, false); mutex_unlock(&wq->mutex); @@ -4155,7 +4166,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, } wq = pwq->wq; - check_flush_dependency(wq, work); + check_flush_dependency(wq, work, from_cancel); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); @@ -5641,6 +5652,7 @@ static void wq_adjust_max_active(struct workqueue_struct *wq) } while (activated); } +__printf(1, 0) static struct workqueue_struct *__alloc_workqueue(const char *fmt, unsigned int flags, int max_active, va_list args) @@ -7828,7 +7840,7 @@ static void __init wq_cpu_intensive_thresh_init(void) unsigned long thresh; unsigned long bogo; - pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release"); + pwq_release_worker = kthread_run_worker(0, "pool_workqueue_release"); BUG_ON(IS_ERR(pwq_release_worker)); /* if the user set it to a specific value, keep it */ diff --git a/lib/Kconfig b/lib/Kconfig index 5a318f753b2f..dccb61b7d698 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -156,13 +156,18 @@ config CRC16 config CRC_T10DIF tristate "CRC calculation for the T10 Data Integrity Field" - select CRYPTO - select CRYPTO_CRCT10DIF help This option is only needed if a module that's not in the kernel tree needs to calculate CRC checks for use with the SCSI data integrity subsystem. +config ARCH_HAS_CRC_T10DIF + bool + +config CRC_T10DIF_ARCH + tristate + default CRC_T10DIF if ARCH_HAS_CRC_T10DIF && CRC_OPTIMIZATIONS + config CRC64_ROCKSOFT tristate "CRC calculation for the Rocksoft model CRC64" select CRC64 @@ -190,61 +195,12 @@ config CRC32 the kernel tree does. Such modules that use library CRC32/CRC32c functions require M here. -config CRC32_SELFTEST - tristate "CRC32 perform self test on init" - depends on CRC32 - help - This option enables the CRC32 library functions to perform a - self test on initialization. The self test computes crc32_le - and crc32_be over byte strings with random alignment and length - and computes the total elapsed time and number of bytes processed. +config ARCH_HAS_CRC32 + bool -choice - prompt "CRC32 implementation" - depends on CRC32 - default CRC32_SLICEBY8 - help - This option allows a kernel builder to override the default choice - of CRC32 algorithm. Choose the default ("slice by 8") unless you - know that you need one of the others. - -config CRC32_SLICEBY8 - bool "Slice by 8 bytes" - help - Calculate checksum 8 bytes at a time with a clever slicing algorithm. - This is the fastest algorithm, but comes with a 8KiB lookup table. - Most modern processors have enough cache to hold this table without - thrashing the cache. - - This is the default implementation choice. Choose this one unless - you have a good reason not to. - -config CRC32_SLICEBY4 - bool "Slice by 4 bytes" - help - Calculate checksum 4 bytes at a time with a clever slicing algorithm. - This is a bit slower than slice by 8, but has a smaller 4KiB lookup - table. - - Only choose this option if you know what you are doing. - -config CRC32_SARWATE - bool "Sarwate's Algorithm (one byte at a time)" - help - Calculate checksum a byte at a time using Sarwate's algorithm. This - is not particularly fast, but has a small 256 byte lookup table. - - Only choose this option if you know what you are doing. - -config CRC32_BIT - bool "Classic Algorithm (one bit at a time)" - help - Calculate checksum one bit at a time. This is VERY slow, but has - no lookup table. This is provided as a debugging option. - - Only choose this option if you are debugging crc32. - -endchoice +config CRC32_ARCH + tristate + default CRC32 if ARCH_HAS_CRC32 && CRC_OPTIMIZATIONS config CRC64 tristate "CRC64 functions" @@ -272,14 +228,10 @@ config CRC7 config LIBCRC32C tristate "CRC32c (Castagnoli, et al) Cyclic Redundancy-Check" - select CRYPTO - select CRYPTO_CRC32C + select CRC32 help - This option is provided for the case where no in-kernel-tree - modules require CRC32c functions, but a module built outside the - kernel tree does. Such modules that use library CRC32c functions - require M here. See Castagnoli93. - Module will be libcrc32c. + This option just selects CRC32 and is provided for compatibility + purposes until the users are updated to select CRC32 directly. config CRC8 tristate "CRC8 function" @@ -288,6 +240,17 @@ config CRC8 when they need to do cyclic redundancy check according CRC8 algorithm. Module will be called crc8. +config CRC_OPTIMIZATIONS + bool "Enable optimized CRC implementations" if EXPERT + default y + help + Disabling this option reduces code size slightly by disabling the + architecture-optimized implementations of any CRC variants that are + enabled. CRC checksumming performance may get much slower. + + Keep this enabled unless you're really trying to minimize the size of + the kernel. + config XXHASH tristate diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index f3d723705879..1af972a92d06 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -433,7 +433,7 @@ config GDB_SCRIPTS build directory. If you load vmlinux into gdb, the helper scripts will be automatically imported by gdb as well, and additional functions are available to analyze a Linux kernel - instance. See Documentation/dev-tools/gdb-kernel-debugging.rst + instance. See Documentation/process/debugging/gdb-kernel-debugging.rst for further details. endif # DEBUG_INFO @@ -1397,9 +1397,9 @@ config PROVE_LOCKING For more details, see Documentation/locking/lockdep-design.rst. config PROVE_RAW_LOCK_NESTING - bool + bool "Enable raw_spinlock - spinlock nesting checks" if !ARCH_SUPPORTS_RT depends on PROVE_LOCKING - default y + default y if ARCH_SUPPORTS_RT help Enable the raw_spinlock vs. spinlock nesting checks which ensure that the lock nesting rules for PREEMPT_RT enabled kernels are @@ -1502,15 +1502,15 @@ config LOCKDEP_SMALL bool config LOCKDEP_BITS - int "Bitsize for MAX_LOCKDEP_ENTRIES" + int "Size for MAX_LOCKDEP_ENTRIES (as Nth power of 2)" depends on LOCKDEP && !LOCKDEP_SMALL - range 10 30 + range 10 24 default 15 help Try increasing this value if you hit "BUG: MAX_LOCKDEP_ENTRIES too low!" message. config LOCKDEP_CHAINS_BITS - int "Bitsize for MAX_LOCKDEP_CHAINS" + int "Size for MAX_LOCKDEP_CHAINS (as Nth power of 2)" depends on LOCKDEP && !LOCKDEP_SMALL range 10 21 default 16 @@ -1518,25 +1518,25 @@ config LOCKDEP_CHAINS_BITS Try increasing this value if you hit "BUG: MAX_LOCKDEP_CHAINS too low!" message. config LOCKDEP_STACK_TRACE_BITS - int "Bitsize for MAX_STACK_TRACE_ENTRIES" + int "Size for MAX_STACK_TRACE_ENTRIES (as Nth power of 2)" depends on LOCKDEP && !LOCKDEP_SMALL - range 10 30 + range 10 26 default 19 help Try increasing this value if you hit "BUG: MAX_STACK_TRACE_ENTRIES too low!" message. config LOCKDEP_STACK_TRACE_HASH_BITS - int "Bitsize for STACK_TRACE_HASH_SIZE" + int "Size for STACK_TRACE_HASH_SIZE (as Nth power of 2)" depends on LOCKDEP && !LOCKDEP_SMALL - range 10 30 + range 10 26 default 14 help Try increasing this value if you need large STACK_TRACE_HASH_SIZE. config LOCKDEP_CIRCULAR_QUEUE_BITS - int "Bitsize for elements in circular_queue struct" + int "Size for elements in circular_queue struct (as Nth power of 2)" depends on LOCKDEP - range 10 30 + range 10 26 default 12 help Try increasing this value if you hit "lockdep bfs error:-1" warning due to __cq_enqueue() failure. @@ -2269,7 +2269,6 @@ config TEST_LIST_SORT config TEST_MIN_HEAP tristate "Min heap test" depends on DEBUG_KERNEL || m - select MIN_HEAP help Enable this to turn on min heap function tests. This test is executed only once during system boot (so affects only boot time), @@ -2479,6 +2478,17 @@ config TEST_RHASHTABLE config TEST_IDA tristate "Perform selftest on IDA functions" +config TEST_MISC_MINOR + tristate "Basic misc minor Kunit test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + Kunit test for the misc minor. + It tests misc minor functions for dynamic and misc dynamic minor. + This include misc_xxx functions + + If unsure, say N. + config TEST_PARMAN tristate "Perform selftest on priority array manager" depends on PARMAN @@ -2838,6 +2848,26 @@ config HW_BREAKPOINT_KUNIT_TEST If unsure, say N. +config CRC_KUNIT_TEST + tristate "KUnit tests for CRC functions" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + select CRC16 + select CRC_T10DIF + select CRC32 + select CRC64 + help + Unit tests for the CRC library functions. + + This is intended to help people writing architecture-specific + optimized versions. If unsure, say N. + +config CRC_BENCHMARK + bool "Benchmark for the CRC functions" + depends on CRC_KUNIT_TEST + help + Include benchmarks in the KUnit test suite for the CRC functions. + config SIPHASH_KUNIT_TEST tristate "Perform selftest on siphash functions" if !KUNIT_ALL_TESTS depends on KUNIT @@ -2858,15 +2888,6 @@ config USERCOPY_KUNIT_TEST on the copy_to/from_user infrastructure, making sure basic user/kernel boundary testing is working. -config CRC16_KUNIT_TEST - tristate "KUnit tests for CRC16" - depends on KUNIT - default KUNIT_ALL_TESTS - select CRC16 - help - Enable this option to run unit tests for the kernel's CRC16 - implementation (). - config TEST_UDELAY tristate "udelay test driver" help @@ -3161,6 +3182,21 @@ config INT_POW_TEST If unsure, say N +config INT_SQRT_KUNIT_TEST + tristate "Integer square root test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This option enables the KUnit test suite for the int_sqrt() function, + which performs square root calculation. The test suite checks + various scenarios, including edge cases, to ensure correctness. + + Enabling this option will include tests that check various scenarios + and edge cases to ensure the accuracy and reliability of the square root + function. + + If unsure, say N + endif # RUNTIME_TESTING_MENU config ARCH_USE_MEMTEST diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index 537e1b3f5734..8336b1a489a3 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -19,7 +19,7 @@ menuconfig KGDB CONFIG_FRAME_POINTER to aid in producing more reliable stack backtraces in the external debugger. Documentation of kernel debugger is available at http://kgdb.sourceforge.net - as well as in Documentation/dev-tools/kgdb.rst. If + as well as in Documentation/process/debugging/kgdb.rst. If unsure, say N. if KGDB diff --git a/lib/Makefile b/lib/Makefile index a8155c972f02..d5cfc7afbbb8 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -164,10 +164,8 @@ obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o obj-$(CONFIG_CRC_ITU_T) += crc-itu-t.o obj-$(CONFIG_CRC32) += crc32.o obj-$(CONFIG_CRC64) += crc64.o -obj-$(CONFIG_CRC32_SELFTEST) += crc32test.o obj-$(CONFIG_CRC4) += crc4.o obj-$(CONFIG_CRC7) += crc7.o -obj-$(CONFIG_LIBCRC32C) += libcrc32c.o obj-$(CONFIG_CRC8) += crc8.o obj-$(CONFIG_CRC64_ROCKSOFT) += crc64-rocksoft.o obj-$(CONFIG_XXHASH) += xxhash.o @@ -392,9 +390,9 @@ CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-overread) CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-truncation) CFLAGS_fortify_kunit.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o +obj-$(CONFIG_CRC_KUNIT_TEST) += crc_kunit.o obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o obj-$(CONFIG_USERCOPY_KUNIT_TEST) += usercopy_kunit.o -obj-$(CONFIG_CRC16_KUNIT_TEST) += crc16_kunit.o obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 35f7560a309a..19b45617bdcf 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -29,6 +29,8 @@ EXPORT_SYMBOL(_shared_alloc_tag); DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, mem_alloc_profiling_key); +EXPORT_SYMBOL(mem_alloc_profiling_key); + DEFINE_STATIC_KEY_FALSE(mem_profiling_compressed); struct alloc_tag_kernel_section kernel_tags = { NULL, 0 }; @@ -195,6 +197,9 @@ void pgalloc_tag_swap(struct folio *new, struct folio *old) union codetag_ref ref_old, ref_new; struct alloc_tag *tag_old, *tag_new; + if (!mem_alloc_profiling_enabled()) + return; + tag_old = pgalloc_tag_get(&old->page); if (!tag_old) return; @@ -209,6 +214,13 @@ void pgalloc_tag_swap(struct folio *new, struct folio *old) return; } + /* + * Clear tag references to avoid debug warning when using + * __alloc_tag_ref_set() with non-empty reference. + */ + set_codetag_empty(&ref_old); + set_codetag_empty(&ref_new); + /* swap tags */ __alloc_tag_ref_set(&ref_old, tag_new); update_page_tag_ref(handle_old, &ref_old); @@ -401,28 +413,52 @@ repeat: static int vm_module_tags_populate(void) { - unsigned long phys_size = vm_module_tags->nr_pages << PAGE_SHIFT; + unsigned long phys_end = ALIGN_DOWN(module_tags.start_addr, PAGE_SIZE) + + (vm_module_tags->nr_pages << PAGE_SHIFT); + unsigned long new_end = module_tags.start_addr + module_tags.size; - if (phys_size < module_tags.size) { + if (phys_end < new_end) { struct page **next_page = vm_module_tags->pages + vm_module_tags->nr_pages; - unsigned long addr = module_tags.start_addr + phys_size; + unsigned long old_shadow_end = ALIGN(phys_end, MODULE_ALIGN); + unsigned long new_shadow_end = ALIGN(new_end, MODULE_ALIGN); unsigned long more_pages; unsigned long nr; - more_pages = ALIGN(module_tags.size - phys_size, PAGE_SIZE) >> PAGE_SHIFT; - nr = alloc_pages_bulk_array_node(GFP_KERNEL | __GFP_NOWARN, - NUMA_NO_NODE, more_pages, next_page); + more_pages = ALIGN(new_end - phys_end, PAGE_SIZE) >> PAGE_SHIFT; + nr = alloc_pages_bulk_node(GFP_KERNEL | __GFP_NOWARN, + NUMA_NO_NODE, more_pages, next_page); if (nr < more_pages || - vmap_pages_range(addr, addr + (nr << PAGE_SHIFT), PAGE_KERNEL, + vmap_pages_range(phys_end, phys_end + (nr << PAGE_SHIFT), PAGE_KERNEL, next_page, PAGE_SHIFT) < 0) { /* Clean up and error out */ for (int i = 0; i < nr; i++) __free_page(next_page[i]); return -ENOMEM; } + vm_module_tags->nr_pages += nr; + + /* + * Kasan allocates 1 byte of shadow for every 8 bytes of data. + * When kasan_alloc_module_shadow allocates shadow memory, + * its unit of allocation is a page. + * Therefore, here we need to align to MODULE_ALIGN. + */ + if (old_shadow_end < new_shadow_end) + kasan_alloc_module_shadow((void *)old_shadow_end, + new_shadow_end - old_shadow_end, + GFP_KERNEL); } + /* + * Mark the pages as accessible, now that they are mapped. + * With hardware tag-based KASAN, marking is skipped for + * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). + */ + kasan_unpoison_vmalloc((void *)module_tags.start_addr, + new_end - module_tags.start_addr, + KASAN_VMALLOC_PROT_NORMAL); + return 0; } diff --git a/lib/atomic64.c b/lib/atomic64.c index caf895789a1e..1a72bba36d24 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -25,15 +25,15 @@ * Ensure each lock is in a separate cacheline. */ static union { - raw_spinlock_t lock; + arch_spinlock_t lock; char pad[L1_CACHE_BYTES]; } atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp = { [0 ... (NR_LOCKS - 1)] = { - .lock = __RAW_SPIN_LOCK_UNLOCKED(atomic64_lock.lock), + .lock = __ARCH_SPIN_LOCK_UNLOCKED, }, }; -static inline raw_spinlock_t *lock_addr(const atomic64_t *v) +static inline arch_spinlock_t *lock_addr(const atomic64_t *v) { unsigned long addr = (unsigned long) v; @@ -45,12 +45,14 @@ static inline raw_spinlock_t *lock_addr(const atomic64_t *v) s64 generic_atomic64_read(const atomic64_t *v) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_read); @@ -58,11 +60,13 @@ EXPORT_SYMBOL(generic_atomic64_read); void generic_atomic64_set(atomic64_t *v, s64 i) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); v->counter = i; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); } EXPORT_SYMBOL(generic_atomic64_set); @@ -70,11 +74,13 @@ EXPORT_SYMBOL(generic_atomic64_set); void generic_atomic64_##op(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ - raw_spinlock_t *lock = lock_addr(v); \ + arch_spinlock_t *lock = lock_addr(v); \ \ - raw_spin_lock_irqsave(lock, flags); \ + local_irq_save(flags); \ + arch_spin_lock(lock); \ v->counter c_op a; \ - raw_spin_unlock_irqrestore(lock, flags); \ + arch_spin_unlock(lock); \ + local_irq_restore(flags); \ } \ EXPORT_SYMBOL(generic_atomic64_##op); @@ -82,12 +88,14 @@ EXPORT_SYMBOL(generic_atomic64_##op); s64 generic_atomic64_##op##_return(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ - raw_spinlock_t *lock = lock_addr(v); \ + arch_spinlock_t *lock = lock_addr(v); \ s64 val; \ \ - raw_spin_lock_irqsave(lock, flags); \ + local_irq_save(flags); \ + arch_spin_lock(lock); \ val = (v->counter c_op a); \ - raw_spin_unlock_irqrestore(lock, flags); \ + arch_spin_unlock(lock); \ + local_irq_restore(flags); \ return val; \ } \ EXPORT_SYMBOL(generic_atomic64_##op##_return); @@ -96,13 +104,15 @@ EXPORT_SYMBOL(generic_atomic64_##op##_return); s64 generic_atomic64_fetch_##op(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ - raw_spinlock_t *lock = lock_addr(v); \ + arch_spinlock_t *lock = lock_addr(v); \ s64 val; \ \ - raw_spin_lock_irqsave(lock, flags); \ + local_irq_save(flags); \ + arch_spin_lock(lock); \ val = v->counter; \ v->counter c_op a; \ - raw_spin_unlock_irqrestore(lock, flags); \ + arch_spin_unlock(lock); \ + local_irq_restore(flags); \ return val; \ } \ EXPORT_SYMBOL(generic_atomic64_fetch_##op); @@ -131,14 +141,16 @@ ATOMIC64_OPS(xor, ^=) s64 generic_atomic64_dec_if_positive(atomic64_t *v) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter - 1; if (val >= 0) v->counter = val; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_dec_if_positive); @@ -146,14 +158,16 @@ EXPORT_SYMBOL(generic_atomic64_dec_if_positive); s64 generic_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; if (val == o) v->counter = n; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_cmpxchg); @@ -161,13 +175,15 @@ EXPORT_SYMBOL(generic_atomic64_cmpxchg); s64 generic_atomic64_xchg(atomic64_t *v, s64 new) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; v->counter = new; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_xchg); @@ -175,14 +191,16 @@ EXPORT_SYMBOL(generic_atomic64_xchg); s64 generic_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; if (val != u) v->counter += a; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } diff --git a/lib/cpumask.c b/lib/cpumask.c index e77ee9d46f71..57274ba8b6d9 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -83,10 +83,7 @@ EXPORT_SYMBOL(alloc_cpumask_var_node); */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { - *mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES); - if (!*mask) - panic("%s: Failed to allocate %u bytes\n", __func__, - cpumask_size()); + *mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES); } /** diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c index 1ed2ed487097..311c2ab829f1 100644 --- a/lib/crc-t10dif.c +++ b/lib/crc-t10dif.c @@ -9,123 +9,57 @@ #include #include #include -#include -#include -#include -#include -#include -#include -static struct crypto_shash __rcu *crct10dif_tfm; -static DEFINE_STATIC_KEY_TRUE(crct10dif_fallback); -static DEFINE_MUTEX(crc_t10dif_mutex); -static struct work_struct crct10dif_rehash_work; - -static int crc_t10dif_notify(struct notifier_block *self, unsigned long val, void *data) -{ - struct crypto_alg *alg = data; - - if (val != CRYPTO_MSG_ALG_LOADED || - strcmp(alg->cra_name, CRC_T10DIF_STRING)) - return NOTIFY_DONE; - - schedule_work(&crct10dif_rehash_work); - return NOTIFY_OK; -} - -static void crc_t10dif_rehash(struct work_struct *work) -{ - struct crypto_shash *new, *old; - - mutex_lock(&crc_t10dif_mutex); - old = rcu_dereference_protected(crct10dif_tfm, - lockdep_is_held(&crc_t10dif_mutex)); - new = crypto_alloc_shash(CRC_T10DIF_STRING, 0, 0); - if (IS_ERR(new)) { - mutex_unlock(&crc_t10dif_mutex); - return; - } - rcu_assign_pointer(crct10dif_tfm, new); - mutex_unlock(&crc_t10dif_mutex); - - if (old) { - synchronize_rcu(); - crypto_free_shash(old); - } else { - static_branch_disable(&crct10dif_fallback); - } -} - -static struct notifier_block crc_t10dif_nb = { - .notifier_call = crc_t10dif_notify, +/* + * Table generated using the following polynomial: + * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1 + * gt: 0x8bb7 + */ +static const u16 t10_dif_crc_table[256] = { + 0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B, + 0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6, + 0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6, + 0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B, + 0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1, + 0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C, + 0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C, + 0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781, + 0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8, + 0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255, + 0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925, + 0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698, + 0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472, + 0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF, + 0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF, + 0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02, + 0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA, + 0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067, + 0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17, + 0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA, + 0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640, + 0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD, + 0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D, + 0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30, + 0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759, + 0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4, + 0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394, + 0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29, + 0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3, + 0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E, + 0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E, + 0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3 }; -__u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len) +u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len) { - struct { - struct shash_desc shash; - __u16 crc; - } desc; - int err; + size_t i; - if (static_branch_unlikely(&crct10dif_fallback)) - return crc_t10dif_generic(crc, buffer, len); + for (i = 0; i < len; i++) + crc = (crc << 8) ^ t10_dif_crc_table[(crc >> 8) ^ p[i]]; - rcu_read_lock(); - desc.shash.tfm = rcu_dereference(crct10dif_tfm); - desc.crc = crc; - err = crypto_shash_update(&desc.shash, buffer, len); - rcu_read_unlock(); - - BUG_ON(err); - - return desc.crc; + return crc; } -EXPORT_SYMBOL(crc_t10dif_update); +EXPORT_SYMBOL(crc_t10dif_generic); -__u16 crc_t10dif(const unsigned char *buffer, size_t len) -{ - return crc_t10dif_update(0, buffer, len); -} -EXPORT_SYMBOL(crc_t10dif); - -static int __init crc_t10dif_mod_init(void) -{ - INIT_WORK(&crct10dif_rehash_work, crc_t10dif_rehash); - crypto_register_notifier(&crc_t10dif_nb); - crc_t10dif_rehash(&crct10dif_rehash_work); - return 0; -} - -static void __exit crc_t10dif_mod_fini(void) -{ - crypto_unregister_notifier(&crc_t10dif_nb); - cancel_work_sync(&crct10dif_rehash_work); - crypto_free_shash(rcu_dereference_protected(crct10dif_tfm, 1)); -} - -module_init(crc_t10dif_mod_init); -module_exit(crc_t10dif_mod_fini); - -static int crc_t10dif_transform_show(char *buffer, const struct kernel_param *kp) -{ - struct crypto_shash *tfm; - int len; - - if (static_branch_unlikely(&crct10dif_fallback)) - return sprintf(buffer, "fallback\n"); - - rcu_read_lock(); - tfm = rcu_dereference(crct10dif_tfm); - len = snprintf(buffer, PAGE_SIZE, "%s\n", - crypto_shash_driver_name(tfm)); - rcu_read_unlock(); - - return len; -} - -module_param_call(transform, NULL, crc_t10dif_transform_show, NULL, 0444); - -MODULE_DESCRIPTION("T10 DIF CRC calculation (library API)"); +MODULE_DESCRIPTION("T10 DIF CRC calculation"); MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: crct10dif"); diff --git a/lib/crc16_kunit.c b/lib/crc16_kunit.c deleted file mode 100644 index 0918c98a96d2..000000000000 --- a/lib/crc16_kunit.c +++ /dev/null @@ -1,155 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * KUnits tests for CRC16. - * - * Copyright (C) 2024, LKCAMP - * Author: Vinicius Peixoto - * Author: Fabricio Gasperin - * Author: Enzo Bertoloti - */ -#include -#include -#include - -#define CRC16_KUNIT_DATA_SIZE 4096 -#define CRC16_KUNIT_TEST_SIZE 100 -#define CRC16_KUNIT_SEED 0x12345678 - -/** - * struct crc16_test - CRC16 test data - * @crc: initial input value to CRC16 - * @start: Start index within the data buffer - * @length: Length of the data - */ -static struct crc16_test { - u16 crc; - u16 start; - u16 length; -} tests[CRC16_KUNIT_TEST_SIZE]; - -u8 data[CRC16_KUNIT_DATA_SIZE]; - - -/* Naive implementation of CRC16 for validation purposes */ -static inline u16 _crc16_naive_byte(u16 crc, u8 data) -{ - u8 i = 0; - - crc ^= (u16) data; - for (i = 0; i < 8; i++) { - if (crc & 0x01) - crc = (crc >> 1) ^ 0xa001; - else - crc = crc >> 1; - } - - return crc; -} - - -static inline u16 _crc16_naive(u16 crc, u8 *buffer, size_t len) -{ - while (len--) - crc = _crc16_naive_byte(crc, *buffer++); - return crc; -} - - -/* Small helper for generating pseudorandom 16-bit data */ -static inline u16 _rand16(void) -{ - static u32 rand = CRC16_KUNIT_SEED; - - rand = next_pseudo_random32(rand); - return rand & 0xFFFF; -} - - -static int crc16_init_test_data(struct kunit_suite *suite) -{ - size_t i; - - /* Fill the data buffer with random bytes */ - for (i = 0; i < CRC16_KUNIT_DATA_SIZE; i++) - data[i] = _rand16() & 0xFF; - - /* Generate random test data while ensuring the random - * start + length values won't overflow the 4096-byte - * buffer (0x7FF * 2 = 0xFFE < 0x1000) - */ - for (size_t i = 0; i < CRC16_KUNIT_TEST_SIZE; i++) { - tests[i].crc = _rand16(); - tests[i].start = _rand16() & 0x7FF; - tests[i].length = _rand16() & 0x7FF; - } - - return 0; -} - -static void crc16_test_empty(struct kunit *test) -{ - u16 crc; - - /* The result for empty data should be the same as the - * initial crc - */ - crc = crc16(0x00, data, 0); - KUNIT_EXPECT_EQ(test, crc, 0); - crc = crc16(0xFF, data, 0); - KUNIT_EXPECT_EQ(test, crc, 0xFF); -} - -static void crc16_test_correctness(struct kunit *test) -{ - size_t i; - u16 crc, crc_naive; - - for (i = 0; i < CRC16_KUNIT_TEST_SIZE; i++) { - /* Compare results with the naive crc16 implementation */ - crc = crc16(tests[i].crc, data + tests[i].start, - tests[i].length); - crc_naive = _crc16_naive(tests[i].crc, data + tests[i].start, - tests[i].length); - KUNIT_EXPECT_EQ(test, crc, crc_naive); - } -} - - -static void crc16_test_combine(struct kunit *test) -{ - size_t i, j; - u16 crc, crc_naive; - - /* Make sure that combining two consecutive crc16 calculations - * yields the same result as calculating the crc16 for the whole thing - */ - for (i = 0; i < CRC16_KUNIT_TEST_SIZE; i++) { - crc_naive = crc16(tests[i].crc, data + tests[i].start, tests[i].length); - for (j = 0; j < tests[i].length; j++) { - crc = crc16(tests[i].crc, data + tests[i].start, j); - crc = crc16(crc, data + tests[i].start + j, tests[i].length - j); - KUNIT_EXPECT_EQ(test, crc, crc_naive); - } - } -} - - -static struct kunit_case crc16_test_cases[] = { - KUNIT_CASE(crc16_test_empty), - KUNIT_CASE(crc16_test_combine), - KUNIT_CASE(crc16_test_correctness), - {}, -}; - -static struct kunit_suite crc16_test_suite = { - .name = "crc16", - .test_cases = crc16_test_cases, - .suite_init = crc16_init_test_data, -}; -kunit_test_suite(crc16_test_suite); - -MODULE_AUTHOR("Fabricio Gasperin "); -MODULE_AUTHOR("Vinicius Peixoto "); -MODULE_AUTHOR("Enzo Bertoloti "); -MODULE_DESCRIPTION("Unit tests for crc16"); -MODULE_LICENSE("GPL"); diff --git a/lib/crc32.c b/lib/crc32.c index ff587fee3893..ede6131f66fc 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -30,20 +30,6 @@ #include #include #include -#include -#include "crc32defs.h" - -#if CRC_LE_BITS > 8 -# define tole(x) ((__force u32) cpu_to_le32(x)) -#else -# define tole(x) (x) -#endif - -#if CRC_BE_BITS > 8 -# define tobe(x) ((__force u32) cpu_to_be32(x)) -#else -# define tobe(x) (x) -#endif #include "crc32table.h" @@ -51,166 +37,21 @@ MODULE_AUTHOR("Matt Domsch "); MODULE_DESCRIPTION("Various CRC32 calculations"); MODULE_LICENSE("GPL"); -#if CRC_LE_BITS > 8 || CRC_BE_BITS > 8 - -/* implements slicing-by-4 or slicing-by-8 algorithm */ -static inline u32 __pure -crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256]) +u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len) { -# ifdef __LITTLE_ENDIAN -# define DO_CRC(x) crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8) -# define DO_CRC4 (t3[(q) & 255] ^ t2[(q >> 8) & 255] ^ \ - t1[(q >> 16) & 255] ^ t0[(q >> 24) & 255]) -# define DO_CRC8 (t7[(q) & 255] ^ t6[(q >> 8) & 255] ^ \ - t5[(q >> 16) & 255] ^ t4[(q >> 24) & 255]) -# else -# define DO_CRC(x) crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8) -# define DO_CRC4 (t0[(q) & 255] ^ t1[(q >> 8) & 255] ^ \ - t2[(q >> 16) & 255] ^ t3[(q >> 24) & 255]) -# define DO_CRC8 (t4[(q) & 255] ^ t5[(q >> 8) & 255] ^ \ - t6[(q >> 16) & 255] ^ t7[(q >> 24) & 255]) -# endif - const u32 *b; - size_t rem_len; -# ifdef CONFIG_X86 - size_t i; -# endif - const u32 *t0=tab[0], *t1=tab[1], *t2=tab[2], *t3=tab[3]; -# if CRC_LE_BITS != 32 - const u32 *t4 = tab[4], *t5 = tab[5], *t6 = tab[6], *t7 = tab[7]; -# endif - u32 q; - - /* Align it */ - if (unlikely((long)buf & 3 && len)) { - do { - DO_CRC(*buf++); - } while ((--len) && ((long)buf)&3); - } - -# if CRC_LE_BITS == 32 - rem_len = len & 3; - len = len >> 2; -# else - rem_len = len & 7; - len = len >> 3; -# endif - - b = (const u32 *)buf; -# ifdef CONFIG_X86 - --b; - for (i = 0; i < len; i++) { -# else - for (--b; len; --len) { -# endif - q = crc ^ *++b; /* use pre increment for speed */ -# if CRC_LE_BITS == 32 - crc = DO_CRC4; -# else - crc = DO_CRC8; - q = *++b; - crc ^= DO_CRC4; -# endif - } - len = rem_len; - /* And the last few bytes */ - if (len) { - u8 *p = (u8 *)(b + 1) - 1; -# ifdef CONFIG_X86 - for (i = 0; i < len; i++) - DO_CRC(*++p); /* use pre increment for speed */ -# else - do { - DO_CRC(*++p); /* use pre increment for speed */ - } while (--len); -# endif - } - return crc; -#undef DO_CRC -#undef DO_CRC4 -#undef DO_CRC8 -} -#endif - - -/** - * crc32_le_generic() - Calculate bitwise little-endian Ethernet AUTODIN II - * CRC32/CRC32C - * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for other - * uses, or the previous crc32/crc32c value if computing incrementally. - * @p: pointer to buffer over which CRC32/CRC32C is run - * @len: length of buffer @p - * @tab: little-endian Ethernet table - * @polynomial: CRC32/CRC32c LE polynomial - */ -static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p, - size_t len, const u32 (*tab)[256], - u32 polynomial) -{ -#if CRC_LE_BITS == 1 - int i; - while (len--) { - crc ^= *p++; - for (i = 0; i < 8; i++) - crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0); - } -# elif CRC_LE_BITS == 2 - while (len--) { - crc ^= *p++; - crc = (crc >> 2) ^ tab[0][crc & 3]; - crc = (crc >> 2) ^ tab[0][crc & 3]; - crc = (crc >> 2) ^ tab[0][crc & 3]; - crc = (crc >> 2) ^ tab[0][crc & 3]; - } -# elif CRC_LE_BITS == 4 - while (len--) { - crc ^= *p++; - crc = (crc >> 4) ^ tab[0][crc & 15]; - crc = (crc >> 4) ^ tab[0][crc & 15]; - } -# elif CRC_LE_BITS == 8 - /* aka Sarwate algorithm */ - while (len--) { - crc ^= *p++; - crc = (crc >> 8) ^ tab[0][crc & 255]; - } -# else - crc = (__force u32) __cpu_to_le32(crc); - crc = crc32_body(crc, p, len, tab); - crc = __le32_to_cpu((__force __le32)crc); -#endif + while (len--) + crc = (crc >> 8) ^ crc32table_le[(crc & 255) ^ *p++]; return crc; } - -#if CRC_LE_BITS == 1 -u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_le_generic(crc, p, len, NULL, CRC32_POLY_LE); -} -u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE); -} -#else -u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_le_generic(crc, p, len, crc32table_le, CRC32_POLY_LE); -} -u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE); -} -#endif -EXPORT_SYMBOL(crc32_le); -EXPORT_SYMBOL(__crc32c_le); - -u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); EXPORT_SYMBOL(crc32_le_base); -u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); -EXPORT_SYMBOL(__crc32c_le_base); - -u32 __pure crc32_be_base(u32, unsigned char const *, size_t) __alias(crc32_be); +u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len) +{ + while (len--) + crc = (crc >> 8) ^ crc32ctable_le[(crc & 255) ^ *p++]; + return crc; +} +EXPORT_SYMBOL(crc32c_le_base); /* * This multiplies the polynomials x and y modulo the given modulus. @@ -285,64 +126,10 @@ u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len) EXPORT_SYMBOL(crc32_le_shift); EXPORT_SYMBOL(__crc32c_le_shift); -/** - * crc32_be_generic() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32 - * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for - * other uses, or the previous crc32 value if computing incrementally. - * @p: pointer to buffer over which CRC32 is run - * @len: length of buffer @p - * @tab: big-endian Ethernet table - * @polynomial: CRC32 BE polynomial - */ -static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p, - size_t len, const u32 (*tab)[256], - u32 polynomial) +u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len) { -#if CRC_BE_BITS == 1 - int i; - while (len--) { - crc ^= *p++ << 24; - for (i = 0; i < 8; i++) - crc = - (crc << 1) ^ ((crc & 0x80000000) ? polynomial : - 0); - } -# elif CRC_BE_BITS == 2 - while (len--) { - crc ^= *p++ << 24; - crc = (crc << 2) ^ tab[0][crc >> 30]; - crc = (crc << 2) ^ tab[0][crc >> 30]; - crc = (crc << 2) ^ tab[0][crc >> 30]; - crc = (crc << 2) ^ tab[0][crc >> 30]; - } -# elif CRC_BE_BITS == 4 - while (len--) { - crc ^= *p++ << 24; - crc = (crc << 4) ^ tab[0][crc >> 28]; - crc = (crc << 4) ^ tab[0][crc >> 28]; - } -# elif CRC_BE_BITS == 8 - while (len--) { - crc ^= *p++ << 24; - crc = (crc << 8) ^ tab[0][crc >> 24]; - } -# else - crc = (__force u32) __cpu_to_be32(crc); - crc = crc32_body(crc, p, len, tab); - crc = __be32_to_cpu((__force __be32)crc); -# endif + while (len--) + crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++]; return crc; } - -#if CRC_BE_BITS == 1 -u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE); -} -#else -u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE); -} -#endif -EXPORT_SYMBOL(crc32_be); +EXPORT_SYMBOL(crc32_be_base); diff --git a/lib/crc32defs.h b/lib/crc32defs.h deleted file mode 100644 index 0c8fb5923e7e..000000000000 --- a/lib/crc32defs.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Try to choose an implementation variant via Kconfig */ -#ifdef CONFIG_CRC32_SLICEBY8 -# define CRC_LE_BITS 64 -# define CRC_BE_BITS 64 -#endif -#ifdef CONFIG_CRC32_SLICEBY4 -# define CRC_LE_BITS 32 -# define CRC_BE_BITS 32 -#endif -#ifdef CONFIG_CRC32_SARWATE -# define CRC_LE_BITS 8 -# define CRC_BE_BITS 8 -#endif -#ifdef CONFIG_CRC32_BIT -# define CRC_LE_BITS 1 -# define CRC_BE_BITS 1 -#endif - -/* - * How many bits at a time to use. Valid values are 1, 2, 4, 8, 32 and 64. - * For less performance-sensitive, use 4 or 8 to save table size. - * For larger systems choose same as CPU architecture as default. - * This works well on X86_64, SPARC64 systems. This may require some - * elaboration after experiments with other architectures. - */ -#ifndef CRC_LE_BITS -# ifdef CONFIG_64BIT -# define CRC_LE_BITS 64 -# else -# define CRC_LE_BITS 32 -# endif -#endif -#ifndef CRC_BE_BITS -# ifdef CONFIG_64BIT -# define CRC_BE_BITS 64 -# else -# define CRC_BE_BITS 32 -# endif -#endif - -/* - * Little-endian CRC computation. Used with serial bit streams sent - * lsbit-first. Be sure to use cpu_to_le32() to append the computed CRC. - */ -#if CRC_LE_BITS > 64 || CRC_LE_BITS < 1 || CRC_LE_BITS == 16 || \ - CRC_LE_BITS & CRC_LE_BITS-1 -# error "CRC_LE_BITS must be one of {1, 2, 4, 8, 32, 64}" -#endif - -/* - * Big-endian CRC computation. Used with serial bit streams sent - * msbit-first. Be sure to use cpu_to_be32() to append the computed CRC. - */ -#if CRC_BE_BITS > 64 || CRC_BE_BITS < 1 || CRC_BE_BITS == 16 || \ - CRC_BE_BITS & CRC_BE_BITS-1 -# error "CRC_BE_BITS must be one of {1, 2, 4, 8, 32, 64}" -#endif diff --git a/lib/crc32test.c b/lib/crc32test.c deleted file mode 100644 index 9b4af79412c4..000000000000 --- a/lib/crc32test.c +++ /dev/null @@ -1,852 +0,0 @@ -/* - * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin - * cleaned up code to current version of sparse and added the slicing-by-8 - * algorithm to the closely similar existing slicing-by-4 algorithm. - * - * Oct 15, 2000 Matt Domsch - * Nicer crc32 functions/docs submitted by linux@horizon.com. Thanks! - * Code was from the public domain, copyright abandoned. Code was - * subsequently included in the kernel, thus was re-licensed under the - * GNU GPL v2. - * - * Oct 12, 2000 Matt Domsch - * Same crc32 function was used in 5 other places in the kernel. - * I made one version, and deleted the others. - * There are various incantations of crc32(). Some use a seed of 0 or ~0. - * Some xor at the end with ~0. The generic crc32() function takes - * seed as an argument, and doesn't xor at the end. Then individual - * users can do whatever they need. - * drivers/net/smc9194.c uses seed ~0, doesn't xor with ~0. - * fs/jffs2 uses seed 0, doesn't xor with ~0. - * fs/partitions/efi.c uses seed ~0, xor's with ~0. - * - * This source code is licensed under the GNU General Public License, - * Version 2. See the file COPYING for more details. - */ - -#include -#include -#include - -#include "crc32defs.h" - -/* 4096 random bytes */ -static u8 const __aligned(8) test_buf[] __initconst = -{ - 0x5b, 0x85, 0x21, 0xcb, 0x09, 0x68, 0x7d, 0x30, - 0xc7, 0x69, 0xd7, 0x30, 0x92, 0xde, 0x59, 0xe4, - 0xc9, 0x6e, 0x8b, 0xdb, 0x98, 0x6b, 0xaa, 0x60, - 0xa8, 0xb5, 0xbc, 0x6c, 0xa9, 0xb1, 0x5b, 0x2c, - 0xea, 0xb4, 0x92, 0x6a, 0x3f, 0x79, 0x91, 0xe4, - 0xe9, 0x70, 0x51, 0x8c, 0x7f, 0x95, 0x6f, 0x1a, - 0x56, 0xa1, 0x5c, 0x27, 0x03, 0x67, 0x9f, 0x3a, - 0xe2, 0x31, 0x11, 0x29, 0x6b, 0x98, 0xfc, 0xc4, - 0x53, 0x24, 0xc5, 0x8b, 0xce, 0x47, 0xb2, 0xb9, - 0x32, 0xcb, 0xc1, 0xd0, 0x03, 0x57, 0x4e, 0xd4, - 0xe9, 0x3c, 0xa1, 0x63, 0xcf, 0x12, 0x0e, 0xca, - 0xe1, 0x13, 0xd1, 0x93, 0xa6, 0x88, 0x5c, 0x61, - 0x5b, 0xbb, 0xf0, 0x19, 0x46, 0xb4, 0xcf, 0x9e, - 0xb6, 0x6b, 0x4c, 0x3a, 0xcf, 0x60, 0xf9, 0x7a, - 0x8d, 0x07, 0x63, 0xdb, 0x40, 0xe9, 0x0b, 0x6f, - 0xad, 0x97, 0xf1, 0xed, 0xd0, 0x1e, 0x26, 0xfd, - 0xbf, 0xb7, 0xc8, 0x04, 0x94, 0xf8, 0x8b, 0x8c, - 0xf1, 0xab, 0x7a, 0xd4, 0xdd, 0xf3, 0xe8, 0x88, - 0xc3, 0xed, 0x17, 0x8a, 0x9b, 0x40, 0x0d, 0x53, - 0x62, 0x12, 0x03, 0x5f, 0x1b, 0x35, 0x32, 0x1f, - 0xb4, 0x7b, 0x93, 0x78, 0x0d, 0xdb, 0xce, 0xa4, - 0xc0, 0x47, 0xd5, 0xbf, 0x68, 0xe8, 0x5d, 0x74, - 0x8f, 0x8e, 0x75, 0x1c, 0xb2, 0x4f, 0x9a, 0x60, - 0xd1, 0xbe, 0x10, 0xf4, 0x5c, 0xa1, 0x53, 0x09, - 0xa5, 0xe0, 0x09, 0x54, 0x85, 0x5c, 0xdc, 0x07, - 0xe7, 0x21, 0x69, 0x7b, 0x8a, 0xfd, 0x90, 0xf1, - 0x22, 0xd0, 0xb4, 0x36, 0x28, 0xe6, 0xb8, 0x0f, - 0x39, 0xde, 0xc8, 0xf3, 0x86, 0x60, 0x34, 0xd2, - 0x5e, 0xdf, 0xfd, 0xcf, 0x0f, 0xa9, 0x65, 0xf0, - 0xd5, 0x4d, 0x96, 0x40, 0xe3, 0xdf, 0x3f, 0x95, - 0x5a, 0x39, 0x19, 0x93, 0xf4, 0x75, 0xce, 0x22, - 0x00, 0x1c, 0x93, 0xe2, 0x03, 0x66, 0xf4, 0x93, - 0x73, 0x86, 0x81, 0x8e, 0x29, 0x44, 0x48, 0x86, - 0x61, 0x7c, 0x48, 0xa3, 0x43, 0xd2, 0x9c, 0x8d, - 0xd4, 0x95, 0xdd, 0xe1, 0x22, 0x89, 0x3a, 0x40, - 0x4c, 0x1b, 0x8a, 0x04, 0xa8, 0x09, 0x69, 0x8b, - 0xea, 0xc6, 0x55, 0x8e, 0x57, 0xe6, 0x64, 0x35, - 0xf0, 0xc7, 0x16, 0x9f, 0x5d, 0x5e, 0x86, 0x40, - 0x46, 0xbb, 0xe5, 0x45, 0x88, 0xfe, 0xc9, 0x63, - 0x15, 0xfb, 0xf5, 0xbd, 0x71, 0x61, 0xeb, 0x7b, - 0x78, 0x70, 0x07, 0x31, 0x03, 0x9f, 0xb2, 0xc8, - 0xa7, 0xab, 0x47, 0xfd, 0xdf, 0xa0, 0x78, 0x72, - 0xa4, 0x2a, 0xe4, 0xb6, 0xba, 0xc0, 0x1e, 0x86, - 0x71, 0xe6, 0x3d, 0x18, 0x37, 0x70, 0xe6, 0xff, - 0xe0, 0xbc, 0x0b, 0x22, 0xa0, 0x1f, 0xd3, 0xed, - 0xa2, 0x55, 0x39, 0xab, 0xa8, 0x13, 0x73, 0x7c, - 0x3f, 0xb2, 0xd6, 0x19, 0xac, 0xff, 0x99, 0xed, - 0xe8, 0xe6, 0xa6, 0x22, 0xe3, 0x9c, 0xf1, 0x30, - 0xdc, 0x01, 0x0a, 0x56, 0xfa, 0xe4, 0xc9, 0x99, - 0xdd, 0xa8, 0xd8, 0xda, 0x35, 0x51, 0x73, 0xb4, - 0x40, 0x86, 0x85, 0xdb, 0x5c, 0xd5, 0x85, 0x80, - 0x14, 0x9c, 0xfd, 0x98, 0xa9, 0x82, 0xc5, 0x37, - 0xff, 0x32, 0x5d, 0xd0, 0x0b, 0xfa, 0xdc, 0x04, - 0x5e, 0x09, 0xd2, 0xca, 0x17, 0x4b, 0x1a, 0x8e, - 0x15, 0xe1, 0xcc, 0x4e, 0x52, 0x88, 0x35, 0xbd, - 0x48, 0xfe, 0x15, 0xa0, 0x91, 0xfd, 0x7e, 0x6c, - 0x0e, 0x5d, 0x79, 0x1b, 0x81, 0x79, 0xd2, 0x09, - 0x34, 0x70, 0x3d, 0x81, 0xec, 0xf6, 0x24, 0xbb, - 0xfb, 0xf1, 0x7b, 0xdf, 0x54, 0xea, 0x80, 0x9b, - 0xc7, 0x99, 0x9e, 0xbd, 0x16, 0x78, 0x12, 0x53, - 0x5e, 0x01, 0xa7, 0x4e, 0xbd, 0x67, 0xe1, 0x9b, - 0x4c, 0x0e, 0x61, 0x45, 0x97, 0xd2, 0xf0, 0x0f, - 0xfe, 0x15, 0x08, 0xb7, 0x11, 0x4c, 0xe7, 0xff, - 0x81, 0x53, 0xff, 0x91, 0x25, 0x38, 0x7e, 0x40, - 0x94, 0xe5, 0xe0, 0xad, 0xe6, 0xd9, 0x79, 0xb6, - 0x92, 0xc9, 0xfc, 0xde, 0xc3, 0x1a, 0x23, 0xbb, - 0xdd, 0xc8, 0x51, 0x0c, 0x3a, 0x72, 0xfa, 0x73, - 0x6f, 0xb7, 0xee, 0x61, 0x39, 0x03, 0x01, 0x3f, - 0x7f, 0x94, 0x2e, 0x2e, 0xba, 0x3a, 0xbb, 0xb4, - 0xfa, 0x6a, 0x17, 0xfe, 0xea, 0xef, 0x5e, 0x66, - 0x97, 0x3f, 0x32, 0x3d, 0xd7, 0x3e, 0xb1, 0xf1, - 0x6c, 0x14, 0x4c, 0xfd, 0x37, 0xd3, 0x38, 0x80, - 0xfb, 0xde, 0xa6, 0x24, 0x1e, 0xc8, 0xca, 0x7f, - 0x3a, 0x93, 0xd8, 0x8b, 0x18, 0x13, 0xb2, 0xe5, - 0xe4, 0x93, 0x05, 0x53, 0x4f, 0x84, 0x66, 0xa7, - 0x58, 0x5c, 0x7b, 0x86, 0x52, 0x6d, 0x0d, 0xce, - 0xa4, 0x30, 0x7d, 0xb6, 0x18, 0x9f, 0xeb, 0xff, - 0x22, 0xbb, 0x72, 0x29, 0xb9, 0x44, 0x0b, 0x48, - 0x1e, 0x84, 0x71, 0x81, 0xe3, 0x6d, 0x73, 0x26, - 0x92, 0xb4, 0x4d, 0x2a, 0x29, 0xb8, 0x1f, 0x72, - 0xed, 0xd0, 0xe1, 0x64, 0x77, 0xea, 0x8e, 0x88, - 0x0f, 0xef, 0x3f, 0xb1, 0x3b, 0xad, 0xf9, 0xc9, - 0x8b, 0xd0, 0xac, 0xc6, 0xcc, 0xa9, 0x40, 0xcc, - 0x76, 0xf6, 0x3b, 0x53, 0xb5, 0x88, 0xcb, 0xc8, - 0x37, 0xf1, 0xa2, 0xba, 0x23, 0x15, 0x99, 0x09, - 0xcc, 0xe7, 0x7a, 0x3b, 0x37, 0xf7, 0x58, 0xc8, - 0x46, 0x8c, 0x2b, 0x2f, 0x4e, 0x0e, 0xa6, 0x5c, - 0xea, 0x85, 0x55, 0xba, 0x02, 0x0e, 0x0e, 0x48, - 0xbc, 0xe1, 0xb1, 0x01, 0x35, 0x79, 0x13, 0x3d, - 0x1b, 0xc0, 0x53, 0x68, 0x11, 0xe7, 0x95, 0x0f, - 0x9d, 0x3f, 0x4c, 0x47, 0x7b, 0x4d, 0x1c, 0xae, - 0x50, 0x9b, 0xcb, 0xdd, 0x05, 0x8d, 0x9a, 0x97, - 0xfd, 0x8c, 0xef, 0x0c, 0x1d, 0x67, 0x73, 0xa8, - 0x28, 0x36, 0xd5, 0xb6, 0x92, 0x33, 0x40, 0x75, - 0x0b, 0x51, 0xc3, 0x64, 0xba, 0x1d, 0xc2, 0xcc, - 0xee, 0x7d, 0x54, 0x0f, 0x27, 0x69, 0xa7, 0x27, - 0x63, 0x30, 0x29, 0xd9, 0xc8, 0x84, 0xd8, 0xdf, - 0x9f, 0x68, 0x8d, 0x04, 0xca, 0xa6, 0xc5, 0xc7, - 0x7a, 0x5c, 0xc8, 0xd1, 0xcb, 0x4a, 0xec, 0xd0, - 0xd8, 0x20, 0x69, 0xc5, 0x17, 0xcd, 0x78, 0xc8, - 0x75, 0x23, 0x30, 0x69, 0xc9, 0xd4, 0xea, 0x5c, - 0x4f, 0x6b, 0x86, 0x3f, 0x8b, 0xfe, 0xee, 0x44, - 0xc9, 0x7c, 0xb7, 0xdd, 0x3e, 0xe5, 0xec, 0x54, - 0x03, 0x3e, 0xaa, 0x82, 0xc6, 0xdf, 0xb2, 0x38, - 0x0e, 0x5d, 0xb3, 0x88, 0xd9, 0xd3, 0x69, 0x5f, - 0x8f, 0x70, 0x8a, 0x7e, 0x11, 0xd9, 0x1e, 0x7b, - 0x38, 0xf1, 0x42, 0x1a, 0xc0, 0x35, 0xf5, 0xc7, - 0x36, 0x85, 0xf5, 0xf7, 0xb8, 0x7e, 0xc7, 0xef, - 0x18, 0xf1, 0x63, 0xd6, 0x7a, 0xc6, 0xc9, 0x0e, - 0x4d, 0x69, 0x4f, 0x84, 0xef, 0x26, 0x41, 0x0c, - 0xec, 0xc7, 0xe0, 0x7e, 0x3c, 0x67, 0x01, 0x4c, - 0x62, 0x1a, 0x20, 0x6f, 0xee, 0x47, 0x4d, 0xc0, - 0x99, 0x13, 0x8d, 0x91, 0x4a, 0x26, 0xd4, 0x37, - 0x28, 0x90, 0x58, 0x75, 0x66, 0x2b, 0x0a, 0xdf, - 0xda, 0xee, 0x92, 0x25, 0x90, 0x62, 0x39, 0x9e, - 0x44, 0x98, 0xad, 0xc1, 0x88, 0xed, 0xe4, 0xb4, - 0xaf, 0xf5, 0x8c, 0x9b, 0x48, 0x4d, 0x56, 0x60, - 0x97, 0x0f, 0x61, 0x59, 0x9e, 0xa6, 0x27, 0xfe, - 0xc1, 0x91, 0x15, 0x38, 0xb8, 0x0f, 0xae, 0x61, - 0x7d, 0x26, 0x13, 0x5a, 0x73, 0xff, 0x1c, 0xa3, - 0x61, 0x04, 0x58, 0x48, 0x55, 0x44, 0x11, 0xfe, - 0x15, 0xca, 0xc3, 0xbd, 0xca, 0xc5, 0xb4, 0x40, - 0x5d, 0x1b, 0x7f, 0x39, 0xb5, 0x9c, 0x35, 0xec, - 0x61, 0x15, 0x32, 0x32, 0xb8, 0x4e, 0x40, 0x9f, - 0x17, 0x1f, 0x0a, 0x4d, 0xa9, 0x91, 0xef, 0xb7, - 0xb0, 0xeb, 0xc2, 0x83, 0x9a, 0x6c, 0xd2, 0x79, - 0x43, 0x78, 0x5e, 0x2f, 0xe5, 0xdd, 0x1a, 0x3c, - 0x45, 0xab, 0x29, 0x40, 0x3a, 0x37, 0x5b, 0x6f, - 0xd7, 0xfc, 0x48, 0x64, 0x3c, 0x49, 0xfb, 0x21, - 0xbe, 0xc3, 0xff, 0x07, 0xfb, 0x17, 0xe9, 0xc9, - 0x0c, 0x4c, 0x5c, 0x15, 0x9e, 0x8e, 0x22, 0x30, - 0x0a, 0xde, 0x48, 0x7f, 0xdb, 0x0d, 0xd1, 0x2b, - 0x87, 0x38, 0x9e, 0xcc, 0x5a, 0x01, 0x16, 0xee, - 0x75, 0x49, 0x0d, 0x30, 0x01, 0x34, 0x6a, 0xb6, - 0x9a, 0x5a, 0x2a, 0xec, 0xbb, 0x48, 0xac, 0xd3, - 0x77, 0x83, 0xd8, 0x08, 0x86, 0x4f, 0x48, 0x09, - 0x29, 0x41, 0x79, 0xa1, 0x03, 0x12, 0xc4, 0xcd, - 0x90, 0x55, 0x47, 0x66, 0x74, 0x9a, 0xcc, 0x4f, - 0x35, 0x8c, 0xd6, 0x98, 0xef, 0xeb, 0x45, 0xb9, - 0x9a, 0x26, 0x2f, 0x39, 0xa5, 0x70, 0x6d, 0xfc, - 0xb4, 0x51, 0xee, 0xf4, 0x9c, 0xe7, 0x38, 0x59, - 0xad, 0xf4, 0xbc, 0x46, 0xff, 0x46, 0x8e, 0x60, - 0x9c, 0xa3, 0x60, 0x1d, 0xf8, 0x26, 0x72, 0xf5, - 0x72, 0x9d, 0x68, 0x80, 0x04, 0xf6, 0x0b, 0xa1, - 0x0a, 0xd5, 0xa7, 0x82, 0x3a, 0x3e, 0x47, 0xa8, - 0x5a, 0xde, 0x59, 0x4f, 0x7b, 0x07, 0xb3, 0xe9, - 0x24, 0x19, 0x3d, 0x34, 0x05, 0xec, 0xf1, 0xab, - 0x6e, 0x64, 0x8f, 0xd3, 0xe6, 0x41, 0x86, 0x80, - 0x70, 0xe3, 0x8d, 0x60, 0x9c, 0x34, 0x25, 0x01, - 0x07, 0x4d, 0x19, 0x41, 0x4e, 0x3d, 0x5c, 0x7e, - 0xa8, 0xf5, 0xcc, 0xd5, 0x7b, 0xe2, 0x7d, 0x3d, - 0x49, 0x86, 0x7d, 0x07, 0xb7, 0x10, 0xe3, 0x35, - 0xb8, 0x84, 0x6d, 0x76, 0xab, 0x17, 0xc6, 0x38, - 0xb4, 0xd3, 0x28, 0x57, 0xad, 0xd3, 0x88, 0x5a, - 0xda, 0xea, 0xc8, 0x94, 0xcc, 0x37, 0x19, 0xac, - 0x9c, 0x9f, 0x4b, 0x00, 0x15, 0xc0, 0xc8, 0xca, - 0x1f, 0x15, 0xaa, 0xe0, 0xdb, 0xf9, 0x2f, 0x57, - 0x1b, 0x24, 0xc7, 0x6f, 0x76, 0x29, 0xfb, 0xed, - 0x25, 0x0d, 0xc0, 0xfe, 0xbd, 0x5a, 0xbf, 0x20, - 0x08, 0x51, 0x05, 0xec, 0x71, 0xa3, 0xbf, 0xef, - 0x5e, 0x99, 0x75, 0xdb, 0x3c, 0x5f, 0x9a, 0x8c, - 0xbb, 0x19, 0x5c, 0x0e, 0x93, 0x19, 0xf8, 0x6a, - 0xbc, 0xf2, 0x12, 0x54, 0x2f, 0xcb, 0x28, 0x64, - 0x88, 0xb3, 0x92, 0x0d, 0x96, 0xd1, 0xa6, 0xe4, - 0x1f, 0xf1, 0x4d, 0xa4, 0xab, 0x1c, 0xee, 0x54, - 0xf2, 0xad, 0x29, 0x6d, 0x32, 0x37, 0xb2, 0x16, - 0x77, 0x5c, 0xdc, 0x2e, 0x54, 0xec, 0x75, 0x26, - 0xc6, 0x36, 0xd9, 0x17, 0x2c, 0xf1, 0x7a, 0xdc, - 0x4b, 0xf1, 0xe2, 0xd9, 0x95, 0xba, 0xac, 0x87, - 0xc1, 0xf3, 0x8e, 0x58, 0x08, 0xd8, 0x87, 0x60, - 0xc9, 0xee, 0x6a, 0xde, 0xa4, 0xd2, 0xfc, 0x0d, - 0xe5, 0x36, 0xc4, 0x5c, 0x52, 0xb3, 0x07, 0x54, - 0x65, 0x24, 0xc1, 0xb1, 0xd1, 0xb1, 0x53, 0x13, - 0x31, 0x79, 0x7f, 0x05, 0x76, 0xeb, 0x37, 0x59, - 0x15, 0x2b, 0xd1, 0x3f, 0xac, 0x08, 0x97, 0xeb, - 0x91, 0x98, 0xdf, 0x6c, 0x09, 0x0d, 0x04, 0x9f, - 0xdc, 0x3b, 0x0e, 0x60, 0x68, 0x47, 0x23, 0x15, - 0x16, 0xc6, 0x0b, 0x35, 0xf8, 0x77, 0xa2, 0x78, - 0x50, 0xd4, 0x64, 0x22, 0x33, 0xff, 0xfb, 0x93, - 0x71, 0x46, 0x50, 0x39, 0x1b, 0x9c, 0xea, 0x4e, - 0x8d, 0x0c, 0x37, 0xe5, 0x5c, 0x51, 0x3a, 0x31, - 0xb2, 0x85, 0x84, 0x3f, 0x41, 0xee, 0xa2, 0xc1, - 0xc6, 0x13, 0x3b, 0x54, 0x28, 0xd2, 0x18, 0x37, - 0xcc, 0x46, 0x9f, 0x6a, 0x91, 0x3d, 0x5a, 0x15, - 0x3c, 0x89, 0xa3, 0x61, 0x06, 0x7d, 0x2e, 0x78, - 0xbe, 0x7d, 0x40, 0xba, 0x2f, 0x95, 0xb1, 0x2f, - 0x87, 0x3b, 0x8a, 0xbe, 0x6a, 0xf4, 0xc2, 0x31, - 0x74, 0xee, 0x91, 0xe0, 0x23, 0xaa, 0x5d, 0x7f, - 0xdd, 0xf0, 0x44, 0x8c, 0x0b, 0x59, 0x2b, 0xfc, - 0x48, 0x3a, 0xdf, 0x07, 0x05, 0x38, 0x6c, 0xc9, - 0xeb, 0x18, 0x24, 0x68, 0x8d, 0x58, 0x98, 0xd3, - 0x31, 0xa3, 0xe4, 0x70, 0x59, 0xb1, 0x21, 0xbe, - 0x7e, 0x65, 0x7d, 0xb8, 0x04, 0xab, 0xf6, 0xe4, - 0xd7, 0xda, 0xec, 0x09, 0x8f, 0xda, 0x6d, 0x24, - 0x07, 0xcc, 0x29, 0x17, 0x05, 0x78, 0x1a, 0xc1, - 0xb1, 0xce, 0xfc, 0xaa, 0x2d, 0xe7, 0xcc, 0x85, - 0x84, 0x84, 0x03, 0x2a, 0x0c, 0x3f, 0xa9, 0xf8, - 0xfd, 0x84, 0x53, 0x59, 0x5c, 0xf0, 0xd4, 0x09, - 0xf0, 0xd2, 0x6c, 0x32, 0x03, 0xb0, 0xa0, 0x8c, - 0x52, 0xeb, 0x23, 0x91, 0x88, 0x43, 0x13, 0x46, - 0xf6, 0x1e, 0xb4, 0x1b, 0xf5, 0x8e, 0x3a, 0xb5, - 0x3d, 0x00, 0xf6, 0xe5, 0x08, 0x3d, 0x5f, 0x39, - 0xd3, 0x21, 0x69, 0xbc, 0x03, 0x22, 0x3a, 0xd2, - 0x5c, 0x84, 0xf8, 0x15, 0xc4, 0x80, 0x0b, 0xbc, - 0x29, 0x3c, 0xf3, 0x95, 0x98, 0xcd, 0x8f, 0x35, - 0xbc, 0xa5, 0x3e, 0xfc, 0xd4, 0x13, 0x9e, 0xde, - 0x4f, 0xce, 0x71, 0x9d, 0x09, 0xad, 0xf2, 0x80, - 0x6b, 0x65, 0x7f, 0x03, 0x00, 0x14, 0x7c, 0x15, - 0x85, 0x40, 0x6d, 0x70, 0xea, 0xdc, 0xb3, 0x63, - 0x35, 0x4f, 0x4d, 0xe0, 0xd9, 0xd5, 0x3c, 0x58, - 0x56, 0x23, 0x80, 0xe2, 0x36, 0xdd, 0x75, 0x1d, - 0x94, 0x11, 0x41, 0x8e, 0xe0, 0x81, 0x8e, 0xcf, - 0xe0, 0xe5, 0xf6, 0xde, 0xd1, 0xe7, 0x04, 0x12, - 0x79, 0x92, 0x2b, 0x71, 0x2a, 0x79, 0x8b, 0x7c, - 0x44, 0x79, 0x16, 0x30, 0x4e, 0xf4, 0xf6, 0x9b, - 0xb7, 0x40, 0xa3, 0x5a, 0xa7, 0x69, 0x3e, 0xc1, - 0x3a, 0x04, 0xd0, 0x88, 0xa0, 0x3b, 0xdd, 0xc6, - 0x9e, 0x7e, 0x1e, 0x1e, 0x8f, 0x44, 0xf7, 0x73, - 0x67, 0x1e, 0x1a, 0x78, 0xfa, 0x62, 0xf4, 0xa9, - 0xa8, 0xc6, 0x5b, 0xb8, 0xfa, 0x06, 0x7d, 0x5e, - 0x38, 0x1c, 0x9a, 0x39, 0xe9, 0x39, 0x98, 0x22, - 0x0b, 0xa7, 0xac, 0x0b, 0xf3, 0xbc, 0xf1, 0xeb, - 0x8c, 0x81, 0xe3, 0x48, 0x8a, 0xed, 0x42, 0xc2, - 0x38, 0xcf, 0x3e, 0xda, 0xd2, 0x89, 0x8d, 0x9c, - 0x53, 0xb5, 0x2f, 0x41, 0x01, 0x26, 0x84, 0x9c, - 0xa3, 0x56, 0xf6, 0x49, 0xc7, 0xd4, 0x9f, 0x93, - 0x1b, 0x96, 0x49, 0x5e, 0xad, 0xb3, 0x84, 0x1f, - 0x3c, 0xa4, 0xe0, 0x9b, 0xd1, 0x90, 0xbc, 0x38, - 0x6c, 0xdd, 0x95, 0x4d, 0x9d, 0xb1, 0x71, 0x57, - 0x2d, 0x34, 0xe8, 0xb8, 0x42, 0xc7, 0x99, 0x03, - 0xc7, 0x07, 0x30, 0x65, 0x91, 0x55, 0xd5, 0x90, - 0x70, 0x97, 0x37, 0x68, 0xd4, 0x11, 0xf9, 0xe8, - 0xce, 0xec, 0xdc, 0x34, 0xd5, 0xd3, 0xb7, 0xc4, - 0xb8, 0x97, 0x05, 0x92, 0xad, 0xf8, 0xe2, 0x36, - 0x64, 0x41, 0xc9, 0xc5, 0x41, 0x77, 0x52, 0xd7, - 0x2c, 0xa5, 0x24, 0x2f, 0xd9, 0x34, 0x0b, 0x47, - 0x35, 0xa7, 0x28, 0x8b, 0xc5, 0xcd, 0xe9, 0x46, - 0xac, 0x39, 0x94, 0x3c, 0x10, 0xc6, 0x29, 0x73, - 0x0e, 0x0e, 0x5d, 0xe0, 0x71, 0x03, 0x8a, 0x72, - 0x0e, 0x26, 0xb0, 0x7d, 0x84, 0xed, 0x95, 0x23, - 0x49, 0x5a, 0x45, 0x83, 0x45, 0x60, 0x11, 0x4a, - 0x46, 0x31, 0xd4, 0xd8, 0x16, 0x54, 0x98, 0x58, - 0xed, 0x6d, 0xcc, 0x5d, 0xd6, 0x50, 0x61, 0x9f, - 0x9d, 0xc5, 0x3e, 0x9d, 0x32, 0x47, 0xde, 0x96, - 0xe1, 0x5d, 0xd8, 0xf8, 0xb4, 0x69, 0x6f, 0xb9, - 0x15, 0x90, 0x57, 0x7a, 0xf6, 0xad, 0xb0, 0x5b, - 0xf5, 0xa6, 0x36, 0x94, 0xfd, 0x84, 0xce, 0x1c, - 0x0f, 0x4b, 0xd0, 0xc2, 0x5b, 0x6b, 0x56, 0xef, - 0x73, 0x93, 0x0b, 0xc3, 0xee, 0xd9, 0xcf, 0xd3, - 0xa4, 0x22, 0x58, 0xcd, 0x50, 0x6e, 0x65, 0xf4, - 0xe9, 0xb7, 0x71, 0xaf, 0x4b, 0xb3, 0xb6, 0x2f, - 0x0f, 0x0e, 0x3b, 0xc9, 0x85, 0x14, 0xf5, 0x17, - 0xe8, 0x7a, 0x3a, 0xbf, 0x5f, 0x5e, 0xf8, 0x18, - 0x48, 0xa6, 0x72, 0xab, 0x06, 0x95, 0xe9, 0xc8, - 0xa7, 0xf4, 0x32, 0x44, 0x04, 0x0c, 0x84, 0x98, - 0x73, 0xe3, 0x89, 0x8d, 0x5f, 0x7e, 0x4a, 0x42, - 0x8f, 0xc5, 0x28, 0xb1, 0x82, 0xef, 0x1c, 0x97, - 0x31, 0x3b, 0x4d, 0xe0, 0x0e, 0x10, 0x10, 0x97, - 0x93, 0x49, 0x78, 0x2f, 0x0d, 0x86, 0x8b, 0xa1, - 0x53, 0xa9, 0x81, 0x20, 0x79, 0xe7, 0x07, 0x77, - 0xb6, 0xac, 0x5e, 0xd2, 0x05, 0xcd, 0xe9, 0xdb, - 0x8a, 0x94, 0x82, 0x8a, 0x23, 0xb9, 0x3d, 0x1c, - 0xa9, 0x7d, 0x72, 0x4a, 0xed, 0x33, 0xa3, 0xdb, - 0x21, 0xa7, 0x86, 0x33, 0x45, 0xa5, 0xaa, 0x56, - 0x45, 0xb5, 0x83, 0x29, 0x40, 0x47, 0x79, 0x04, - 0x6e, 0xb9, 0x95, 0xd0, 0x81, 0x77, 0x2d, 0x48, - 0x1e, 0xfe, 0xc3, 0xc2, 0x1e, 0xe5, 0xf2, 0xbe, - 0xfd, 0x3b, 0x94, 0x9f, 0xc4, 0xc4, 0x26, 0x9d, - 0xe4, 0x66, 0x1e, 0x19, 0xee, 0x6c, 0x79, 0x97, - 0x11, 0x31, 0x4b, 0x0d, 0x01, 0xcb, 0xde, 0xa8, - 0xf6, 0x6d, 0x7c, 0x39, 0x46, 0x4e, 0x7e, 0x3f, - 0x94, 0x17, 0xdf, 0xa1, 0x7d, 0xd9, 0x1c, 0x8e, - 0xbc, 0x7d, 0x33, 0x7d, 0xe3, 0x12, 0x40, 0xca, - 0xab, 0x37, 0x11, 0x46, 0xd4, 0xae, 0xef, 0x44, - 0xa2, 0xb3, 0x6a, 0x66, 0x0e, 0x0c, 0x90, 0x7f, - 0xdf, 0x5c, 0x66, 0x5f, 0xf2, 0x94, 0x9f, 0xa6, - 0x73, 0x4f, 0xeb, 0x0d, 0xad, 0xbf, 0xc0, 0x63, - 0x5c, 0xdc, 0x46, 0x51, 0xe8, 0x8e, 0x90, 0x19, - 0xa8, 0xa4, 0x3c, 0x91, 0x79, 0xfa, 0x7e, 0x58, - 0x85, 0x13, 0x55, 0xc5, 0x19, 0x82, 0x37, 0x1b, - 0x0a, 0x02, 0x1f, 0x99, 0x6b, 0x18, 0xf1, 0x28, - 0x08, 0xa2, 0x73, 0xb8, 0x0f, 0x2e, 0xcd, 0xbf, - 0xf3, 0x86, 0x7f, 0xea, 0xef, 0xd0, 0xbb, 0xa6, - 0x21, 0xdf, 0x49, 0x73, 0x51, 0xcc, 0x36, 0xd3, - 0x3e, 0xa0, 0xf8, 0x44, 0xdf, 0xd3, 0xa6, 0xbe, - 0x8a, 0xd4, 0x57, 0xdd, 0x72, 0x94, 0x61, 0x0f, - 0x82, 0xd1, 0x07, 0xb8, 0x7c, 0x18, 0x83, 0xdf, - 0x3a, 0xe5, 0x50, 0x6a, 0x82, 0x20, 0xac, 0xa9, - 0xa8, 0xff, 0xd9, 0xf3, 0x77, 0x33, 0x5a, 0x9e, - 0x7f, 0x6d, 0xfe, 0x5d, 0x33, 0x41, 0x42, 0xe7, - 0x6c, 0x19, 0xe0, 0x44, 0x8a, 0x15, 0xf6, 0x70, - 0x98, 0xb7, 0x68, 0x4d, 0xfa, 0x97, 0x39, 0xb0, - 0x8e, 0xe8, 0x84, 0x8b, 0x75, 0x30, 0xb7, 0x7d, - 0x92, 0x69, 0x20, 0x9c, 0x81, 0xfb, 0x4b, 0xf4, - 0x01, 0x50, 0xeb, 0xce, 0x0c, 0x1c, 0x6c, 0xb5, - 0x4a, 0xd7, 0x27, 0x0c, 0xce, 0xbb, 0xe5, 0x85, - 0xf0, 0xb6, 0xee, 0xd5, 0x70, 0xdd, 0x3b, 0xfc, - 0xd4, 0x99, 0xf1, 0x33, 0xdd, 0x8b, 0xc4, 0x2f, - 0xae, 0xab, 0x74, 0x96, 0x32, 0xc7, 0x4c, 0x56, - 0x3c, 0x89, 0x0f, 0x96, 0x0b, 0x42, 0xc0, 0xcb, - 0xee, 0x0f, 0x0b, 0x8c, 0xfb, 0x7e, 0x47, 0x7b, - 0x64, 0x48, 0xfd, 0xb2, 0x00, 0x80, 0x89, 0xa5, - 0x13, 0x55, 0x62, 0xfc, 0x8f, 0xe2, 0x42, 0x03, - 0xb7, 0x4e, 0x2a, 0x79, 0xb4, 0x82, 0xea, 0x23, - 0x49, 0xda, 0xaf, 0x52, 0x63, 0x1e, 0x60, 0x03, - 0x89, 0x06, 0x44, 0x46, 0x08, 0xc3, 0xc4, 0x87, - 0x70, 0x2e, 0xda, 0x94, 0xad, 0x6b, 0xe0, 0xe4, - 0xd1, 0x8a, 0x06, 0xc2, 0xa8, 0xc0, 0xa7, 0x43, - 0x3c, 0x47, 0x52, 0x0e, 0xc3, 0x77, 0x81, 0x11, - 0x67, 0x0e, 0xa0, 0x70, 0x04, 0x47, 0x29, 0x40, - 0x86, 0x0d, 0x34, 0x56, 0xa7, 0xc9, 0x35, 0x59, - 0x68, 0xdc, 0x93, 0x81, 0x70, 0xee, 0x86, 0xd9, - 0x80, 0x06, 0x40, 0x4f, 0x1a, 0x0d, 0x40, 0x30, - 0x0b, 0xcb, 0x96, 0x47, 0xc1, 0xb7, 0x52, 0xfd, - 0x56, 0xe0, 0x72, 0x4b, 0xfb, 0xbd, 0x92, 0x45, - 0x61, 0x71, 0xc2, 0x33, 0x11, 0xbf, 0x52, 0x83, - 0x79, 0x26, 0xe0, 0x49, 0x6b, 0xb7, 0x05, 0x8b, - 0xe8, 0x0e, 0x87, 0x31, 0xd7, 0x9d, 0x8a, 0xf5, - 0xc0, 0x5f, 0x2e, 0x58, 0x4a, 0xdb, 0x11, 0xb3, - 0x6c, 0x30, 0x2a, 0x46, 0x19, 0xe3, 0x27, 0x84, - 0x1f, 0x63, 0x6e, 0xf6, 0x57, 0xc7, 0xc9, 0xd8, - 0x5e, 0xba, 0xb3, 0x87, 0xd5, 0x83, 0x26, 0x34, - 0x21, 0x9e, 0x65, 0xde, 0x42, 0xd3, 0xbe, 0x7b, - 0xbc, 0x91, 0x71, 0x44, 0x4d, 0x99, 0x3b, 0x31, - 0xe5, 0x3f, 0x11, 0x4e, 0x7f, 0x13, 0x51, 0x3b, - 0xae, 0x79, 0xc9, 0xd3, 0x81, 0x8e, 0x25, 0x40, - 0x10, 0xfc, 0x07, 0x1e, 0xf9, 0x7b, 0x9a, 0x4b, - 0x6c, 0xe3, 0xb3, 0xad, 0x1a, 0x0a, 0xdd, 0x9e, - 0x59, 0x0c, 0xa2, 0xcd, 0xae, 0x48, 0x4a, 0x38, - 0x5b, 0x47, 0x41, 0x94, 0x65, 0x6b, 0xbb, 0xeb, - 0x5b, 0xe3, 0xaf, 0x07, 0x5b, 0xd4, 0x4a, 0xa2, - 0xc9, 0x5d, 0x2f, 0x64, 0x03, 0xd7, 0x3a, 0x2c, - 0x6e, 0xce, 0x76, 0x95, 0xb4, 0xb3, 0xc0, 0xf1, - 0xe2, 0x45, 0x73, 0x7a, 0x5c, 0xab, 0xc1, 0xfc, - 0x02, 0x8d, 0x81, 0x29, 0xb3, 0xac, 0x07, 0xec, - 0x40, 0x7d, 0x45, 0xd9, 0x7a, 0x59, 0xee, 0x34, - 0xf0, 0xe9, 0xd5, 0x7b, 0x96, 0xb1, 0x3d, 0x95, - 0xcc, 0x86, 0xb5, 0xb6, 0x04, 0x2d, 0xb5, 0x92, - 0x7e, 0x76, 0xf4, 0x06, 0xa9, 0xa3, 0x12, 0x0f, - 0xb1, 0xaf, 0x26, 0xba, 0x7c, 0xfc, 0x7e, 0x1c, - 0xbc, 0x2c, 0x49, 0x97, 0x53, 0x60, 0x13, 0x0b, - 0xa6, 0x61, 0x83, 0x89, 0x42, 0xd4, 0x17, 0x0c, - 0x6c, 0x26, 0x52, 0xc3, 0xb3, 0xd4, 0x67, 0xf5, - 0xe3, 0x04, 0xb7, 0xf4, 0xcb, 0x80, 0xb8, 0xcb, - 0x77, 0x56, 0x3e, 0xaa, 0x57, 0x54, 0xee, 0xb4, - 0x2c, 0x67, 0xcf, 0xf2, 0xdc, 0xbe, 0x55, 0xf9, - 0x43, 0x1f, 0x6e, 0x22, 0x97, 0x67, 0x7f, 0xc4, - 0xef, 0xb1, 0x26, 0x31, 0x1e, 0x27, 0xdf, 0x41, - 0x80, 0x47, 0x6c, 0xe2, 0xfa, 0xa9, 0x8c, 0x2a, - 0xf6, 0xf2, 0xab, 0xf0, 0x15, 0xda, 0x6c, 0xc8, - 0xfe, 0xb5, 0x23, 0xde, 0xa9, 0x05, 0x3f, 0x06, - 0x54, 0x4c, 0xcd, 0xe1, 0xab, 0xfc, 0x0e, 0x62, - 0x33, 0x31, 0x73, 0x2c, 0x76, 0xcb, 0xb4, 0x47, - 0x1e, 0x20, 0xad, 0xd8, 0xf2, 0x31, 0xdd, 0xc4, - 0x8b, 0x0c, 0x77, 0xbe, 0xe1, 0x8b, 0x26, 0x00, - 0x02, 0x58, 0xd6, 0x8d, 0xef, 0xad, 0x74, 0x67, - 0xab, 0x3f, 0xef, 0xcb, 0x6f, 0xb0, 0xcc, 0x81, - 0x44, 0x4c, 0xaf, 0xe9, 0x49, 0x4f, 0xdb, 0xa0, - 0x25, 0xa4, 0xf0, 0x89, 0xf1, 0xbe, 0xd8, 0x10, - 0xff, 0xb1, 0x3b, 0x4b, 0xfa, 0x98, 0xf5, 0x79, - 0x6d, 0x1e, 0x69, 0x4d, 0x57, 0xb1, 0xc8, 0x19, - 0x1b, 0xbd, 0x1e, 0x8c, 0x84, 0xb7, 0x7b, 0xe8, - 0xd2, 0x2d, 0x09, 0x41, 0x41, 0x37, 0x3d, 0xb1, - 0x6f, 0x26, 0x5d, 0x71, 0x16, 0x3d, 0xb7, 0x83, - 0x27, 0x2c, 0xa7, 0xb6, 0x50, 0xbd, 0x91, 0x86, - 0xab, 0x24, 0xa1, 0x38, 0xfd, 0xea, 0x71, 0x55, - 0x7e, 0x9a, 0x07, 0x77, 0x4b, 0xfa, 0x61, 0x66, - 0x20, 0x1e, 0x28, 0x95, 0x18, 0x1b, 0xa4, 0xa0, - 0xfd, 0xc0, 0x89, 0x72, 0x43, 0xd9, 0x3b, 0x49, - 0x5a, 0x3f, 0x9d, 0xbf, 0xdb, 0xb4, 0x46, 0xea, - 0x42, 0x01, 0x77, 0x23, 0x68, 0x95, 0xb6, 0x24, - 0xb3, 0xa8, 0x6c, 0x28, 0x3b, 0x11, 0x40, 0x7e, - 0x18, 0x65, 0x6d, 0xd8, 0x24, 0x42, 0x7d, 0x88, - 0xc0, 0x52, 0xd9, 0x05, 0xe4, 0x95, 0x90, 0x87, - 0x8c, 0xf4, 0xd0, 0x6b, 0xb9, 0x83, 0x99, 0x34, - 0x6d, 0xfe, 0x54, 0x40, 0x94, 0x52, 0x21, 0x4f, - 0x14, 0x25, 0xc5, 0xd6, 0x5e, 0x95, 0xdc, 0x0a, - 0x2b, 0x89, 0x20, 0x11, 0x84, 0x48, 0xd6, 0x3a, - 0xcd, 0x5c, 0x24, 0xad, 0x62, 0xe3, 0xb1, 0x93, - 0x25, 0x8d, 0xcd, 0x7e, 0xfc, 0x27, 0xa3, 0x37, - 0xfd, 0x84, 0xfc, 0x1b, 0xb2, 0xf1, 0x27, 0x38, - 0x5a, 0xb7, 0xfc, 0xf2, 0xfa, 0x95, 0x66, 0xd4, - 0xfb, 0xba, 0xa7, 0xd7, 0xa3, 0x72, 0x69, 0x48, - 0x48, 0x8c, 0xeb, 0x28, 0x89, 0xfe, 0x33, 0x65, - 0x5a, 0x36, 0x01, 0x7e, 0x06, 0x79, 0x0a, 0x09, - 0x3b, 0x74, 0x11, 0x9a, 0x6e, 0xbf, 0xd4, 0x9e, - 0x58, 0x90, 0x49, 0x4f, 0x4d, 0x08, 0xd4, 0xe5, - 0x4a, 0x09, 0x21, 0xef, 0x8b, 0xb8, 0x74, 0x3b, - 0x91, 0xdd, 0x36, 0x85, 0x60, 0x2d, 0xfa, 0xd4, - 0x45, 0x7b, 0x45, 0x53, 0xf5, 0x47, 0x87, 0x7e, - 0xa6, 0x37, 0xc8, 0x78, 0x7a, 0x68, 0x9d, 0x8d, - 0x65, 0x2c, 0x0e, 0x91, 0x5c, 0xa2, 0x60, 0xf0, - 0x8e, 0x3f, 0xe9, 0x1a, 0xcd, 0xaa, 0xe7, 0xd5, - 0x77, 0x18, 0xaf, 0xc9, 0xbc, 0x18, 0xea, 0x48, - 0x1b, 0xfb, 0x22, 0x48, 0x70, 0x16, 0x29, 0x9e, - 0x5b, 0xc1, 0x2c, 0x66, 0x23, 0xbc, 0xf0, 0x1f, - 0xef, 0xaf, 0xe4, 0xd6, 0x04, 0x19, 0x82, 0x7a, - 0x0b, 0xba, 0x4b, 0x46, 0xb1, 0x6a, 0x85, 0x5d, - 0xb4, 0x73, 0xd6, 0x21, 0xa1, 0x71, 0x60, 0x14, - 0xee, 0x0a, 0x77, 0xc4, 0x66, 0x2e, 0xf9, 0x69, - 0x30, 0xaf, 0x41, 0x0b, 0xc8, 0x83, 0x3c, 0x53, - 0x99, 0x19, 0x27, 0x46, 0xf7, 0x41, 0x6e, 0x56, - 0xdc, 0x94, 0x28, 0x67, 0x4e, 0xb7, 0x25, 0x48, - 0x8a, 0xc2, 0xe0, 0x60, 0x96, 0xcc, 0x18, 0xf4, - 0x84, 0xdd, 0xa7, 0x5e, 0x3e, 0x05, 0x0b, 0x26, - 0x26, 0xb2, 0x5c, 0x1f, 0x57, 0x1a, 0x04, 0x7e, - 0x6a, 0xe3, 0x2f, 0xb4, 0x35, 0xb6, 0x38, 0x40, - 0x40, 0xcd, 0x6f, 0x87, 0x2e, 0xef, 0xa3, 0xd7, - 0xa9, 0xc2, 0xe8, 0x0d, 0x27, 0xdf, 0x44, 0x62, - 0x99, 0xa0, 0xfc, 0xcf, 0x81, 0x78, 0xcb, 0xfe, - 0xe5, 0xa0, 0x03, 0x4e, 0x6c, 0xd7, 0xf4, 0xaf, - 0x7a, 0xbb, 0x61, 0x82, 0xfe, 0x71, 0x89, 0xb2, - 0x22, 0x7c, 0x8e, 0x83, 0x04, 0xce, 0xf6, 0x5d, - 0x84, 0x8f, 0x95, 0x6a, 0x7f, 0xad, 0xfd, 0x32, - 0x9c, 0x5e, 0xe4, 0x9c, 0x89, 0x60, 0x54, 0xaa, - 0x96, 0x72, 0xd2, 0xd7, 0x36, 0x85, 0xa9, 0x45, - 0xd2, 0x2a, 0xa1, 0x81, 0x49, 0x6f, 0x7e, 0x04, - 0xfa, 0xe2, 0xfe, 0x90, 0x26, 0x77, 0x5a, 0x33, - 0xb8, 0x04, 0x9a, 0x7a, 0xe6, 0x4c, 0x4f, 0xad, - 0x72, 0x96, 0x08, 0x28, 0x58, 0x13, 0xf8, 0xc4, - 0x1c, 0xf0, 0xc3, 0x45, 0x95, 0x49, 0x20, 0x8c, - 0x9f, 0x39, 0x70, 0xe1, 0x77, 0xfe, 0xd5, 0x4b, - 0xaf, 0x86, 0xda, 0xef, 0x22, 0x06, 0x83, 0x36, - 0x29, 0x12, 0x11, 0x40, 0xbc, 0x3b, 0x86, 0xaa, - 0xaa, 0x65, 0x60, 0xc3, 0x80, 0xca, 0xed, 0xa9, - 0xf3, 0xb0, 0x79, 0x96, 0xa2, 0x55, 0x27, 0x28, - 0x55, 0x73, 0x26, 0xa5, 0x50, 0xea, 0x92, 0x4b, - 0x3c, 0x5c, 0x82, 0x33, 0xf0, 0x01, 0x3f, 0x03, - 0xc1, 0x08, 0x05, 0xbf, 0x98, 0xf4, 0x9b, 0x6d, - 0xa5, 0xa8, 0xb4, 0x82, 0x0c, 0x06, 0xfa, 0xff, - 0x2d, 0x08, 0xf3, 0x05, 0x4f, 0x57, 0x2a, 0x39, - 0xd4, 0x83, 0x0d, 0x75, 0x51, 0xd8, 0x5b, 0x1b, - 0xd3, 0x51, 0x5a, 0x32, 0x2a, 0x9b, 0x32, 0xb2, - 0xf2, 0xa4, 0x96, 0x12, 0xf2, 0xae, 0x40, 0x34, - 0x67, 0xa8, 0xf5, 0x44, 0xd5, 0x35, 0x53, 0xfe, - 0xa3, 0x60, 0x96, 0x63, 0x0f, 0x1f, 0x6e, 0xb0, - 0x5a, 0x42, 0xa6, 0xfc, 0x51, 0x0b, 0x60, 0x27, - 0xbc, 0x06, 0x71, 0xed, 0x65, 0x5b, 0x23, 0x86, - 0x4a, 0x07, 0x3b, 0x22, 0x07, 0x46, 0xe6, 0x90, - 0x3e, 0xf3, 0x25, 0x50, 0x1b, 0x4c, 0x7f, 0x03, - 0x08, 0xa8, 0x36, 0x6b, 0x87, 0xe5, 0xe3, 0xdb, - 0x9a, 0x38, 0x83, 0xff, 0x9f, 0x1a, 0x9f, 0x57, - 0xa4, 0x2a, 0xf6, 0x37, 0xbc, 0x1a, 0xff, 0xc9, - 0x1e, 0x35, 0x0c, 0xc3, 0x7c, 0xa3, 0xb2, 0xe5, - 0xd2, 0xc6, 0xb4, 0x57, 0x47, 0xe4, 0x32, 0x16, - 0x6d, 0xa9, 0xae, 0x64, 0xe6, 0x2d, 0x8d, 0xc5, - 0x8d, 0x50, 0x8e, 0xe8, 0x1a, 0x22, 0x34, 0x2a, - 0xd9, 0xeb, 0x51, 0x90, 0x4a, 0xb1, 0x41, 0x7d, - 0x64, 0xf9, 0xb9, 0x0d, 0xf6, 0x23, 0x33, 0xb0, - 0x33, 0xf4, 0xf7, 0x3f, 0x27, 0x84, 0xc6, 0x0f, - 0x54, 0xa5, 0xc0, 0x2e, 0xec, 0x0b, 0x3a, 0x48, - 0x6e, 0x80, 0x35, 0x81, 0x43, 0x9b, 0x90, 0xb1, - 0xd0, 0x2b, 0xea, 0x21, 0xdc, 0xda, 0x5b, 0x09, - 0xf4, 0xcc, 0x10, 0xb4, 0xc7, 0xfe, 0x79, 0x51, - 0xc3, 0xc5, 0xac, 0x88, 0x74, 0x84, 0x0b, 0x4b, - 0xca, 0x79, 0x16, 0x29, 0xfb, 0x69, 0x54, 0xdf, - 0x41, 0x7e, 0xe9, 0xc7, 0x8e, 0xea, 0xa5, 0xfe, - 0xfc, 0x76, 0x0e, 0x90, 0xc4, 0x92, 0x38, 0xad, - 0x7b, 0x48, 0xe6, 0x6e, 0xf7, 0x21, 0xfd, 0x4e, - 0x93, 0x0a, 0x7b, 0x41, 0x83, 0x68, 0xfb, 0x57, - 0x51, 0x76, 0x34, 0xa9, 0x6c, 0x00, 0xaa, 0x4f, - 0x66, 0x65, 0x98, 0x4a, 0x4f, 0xa3, 0xa0, 0xef, - 0x69, 0x3f, 0xe3, 0x1c, 0x92, 0x8c, 0xfd, 0xd8, - 0xe8, 0xde, 0x7c, 0x7f, 0x3e, 0x84, 0x8e, 0x69, - 0x3c, 0xf1, 0xf2, 0x05, 0x46, 0xdc, 0x2f, 0x9d, - 0x5e, 0x6e, 0x4c, 0xfb, 0xb5, 0x99, 0x2a, 0x59, - 0x63, 0xc1, 0x34, 0xbc, 0x57, 0xc0, 0x0d, 0xb9, - 0x61, 0x25, 0xf3, 0x33, 0x23, 0x51, 0xb6, 0x0d, - 0x07, 0xa6, 0xab, 0x94, 0x4a, 0xb7, 0x2a, 0xea, - 0xee, 0xac, 0xa3, 0xc3, 0x04, 0x8b, 0x0e, 0x56, - 0xfe, 0x44, 0xa7, 0x39, 0xe2, 0xed, 0xed, 0xb4, - 0x22, 0x2b, 0xac, 0x12, 0x32, 0x28, 0x91, 0xd8, - 0xa5, 0xab, 0xff, 0x5f, 0xe0, 0x4b, 0xda, 0x78, - 0x17, 0xda, 0xf1, 0x01, 0x5b, 0xcd, 0xe2, 0x5f, - 0x50, 0x45, 0x73, 0x2b, 0xe4, 0x76, 0x77, 0xf4, - 0x64, 0x1d, 0x43, 0xfb, 0x84, 0x7a, 0xea, 0x91, - 0xae, 0xf9, 0x9e, 0xb7, 0xb4, 0xb0, 0x91, 0x5f, - 0x16, 0x35, 0x9a, 0x11, 0xb8, 0xc7, 0xc1, 0x8c, - 0xc6, 0x10, 0x8d, 0x2f, 0x63, 0x4a, 0xa7, 0x57, - 0x3a, 0x51, 0xd6, 0x32, 0x2d, 0x64, 0x72, 0xd4, - 0x66, 0xdc, 0x10, 0xa6, 0x67, 0xd6, 0x04, 0x23, - 0x9d, 0x0a, 0x11, 0x77, 0xdd, 0x37, 0x94, 0x17, - 0x3c, 0xbf, 0x8b, 0x65, 0xb0, 0x2e, 0x5e, 0x66, - 0x47, 0x64, 0xac, 0xdd, 0xf0, 0x84, 0xfd, 0x39, - 0xfa, 0x15, 0x5d, 0xef, 0xae, 0xca, 0xc1, 0x36, - 0xa7, 0x5c, 0xbf, 0xc7, 0x08, 0xc2, 0x66, 0x00, - 0x74, 0x74, 0x4e, 0x27, 0x3f, 0x55, 0x8a, 0xb7, - 0x38, 0x66, 0x83, 0x6d, 0xcf, 0x99, 0x9e, 0x60, - 0x8f, 0xdd, 0x2e, 0x62, 0x22, 0x0e, 0xef, 0x0c, - 0x98, 0xa7, 0x85, 0x74, 0x3b, 0x9d, 0xec, 0x9e, - 0xa9, 0x19, 0x72, 0xa5, 0x7f, 0x2c, 0x39, 0xb7, - 0x7d, 0xb7, 0xf1, 0x12, 0x65, 0x27, 0x4b, 0x5a, - 0xde, 0x17, 0xfe, 0xad, 0x44, 0xf3, 0x20, 0x4d, - 0xfd, 0xe4, 0x1f, 0xb5, 0x81, 0xb0, 0x36, 0x37, - 0x08, 0x6f, 0xc3, 0x0c, 0xe9, 0x85, 0x98, 0x82, - 0xa9, 0x62, 0x0c, 0xc4, 0x97, 0xc0, 0x50, 0xc8, - 0xa7, 0x3c, 0x50, 0x9f, 0x43, 0xb9, 0xcd, 0x5e, - 0x4d, 0xfa, 0x1c, 0x4b, 0x0b, 0xa9, 0x98, 0x85, - 0x38, 0x92, 0xac, 0x8d, 0xe4, 0xad, 0x9b, 0x98, - 0xab, 0xd9, 0x38, 0xac, 0x62, 0x52, 0xa3, 0x22, - 0x63, 0x0f, 0xbf, 0x95, 0x48, 0xdf, 0x69, 0xe7, - 0x8b, 0x33, 0xd5, 0xb2, 0xbd, 0x05, 0x49, 0x49, - 0x9d, 0x57, 0x73, 0x19, 0x33, 0xae, 0xfa, 0x33, - 0xf1, 0x19, 0xa8, 0x80, 0xce, 0x04, 0x9f, 0xbc, - 0x1d, 0x65, 0x82, 0x1b, 0xe5, 0x3a, 0x51, 0xc8, - 0x1c, 0x21, 0xe3, 0x5d, 0xf3, 0x7d, 0x9b, 0x2f, - 0x2c, 0x1d, 0x4a, 0x7f, 0x9b, 0x68, 0x35, 0xa3, - 0xb2, 0x50, 0xf7, 0x62, 0x79, 0xcd, 0xf4, 0x98, - 0x4f, 0xe5, 0x63, 0x7c, 0x3e, 0x45, 0x31, 0x8c, - 0x16, 0xa0, 0x12, 0xc8, 0x58, 0xce, 0x39, 0xa6, - 0xbc, 0x54, 0xdb, 0xc5, 0xe0, 0xd5, 0xba, 0xbc, - 0xb9, 0x04, 0xf4, 0x8d, 0xe8, 0x2f, 0x15, 0x9d, -}; - -/* 100 test cases */ -static struct crc_test { - u32 crc; /* random starting crc */ - u32 start; /* random 6 bit offset in buf */ - u32 length; /* random 11 bit length of test */ - u32 crc_le; /* expected crc32_le result */ - u32 crc_be; /* expected crc32_be result */ - u32 crc32c_le; /* expected crc32c_le result */ -} const test[] __initconst = -{ - {0x674bf11d, 0x00000038, 0x00000542, 0x0af6d466, 0xd8b6e4c1, 0xf6e93d6c}, - {0x35c672c6, 0x0000003a, 0x000001aa, 0xc6d3dfba, 0x28aaf3ad, 0x0fe92aca}, - {0x496da28e, 0x00000039, 0x000005af, 0xd933660f, 0x5d57e81f, 0x52e1ebb8}, - {0x09a9b90e, 0x00000027, 0x000001f8, 0xb45fe007, 0xf45fca9a, 0x0798af9a}, - {0xdc97e5a9, 0x00000025, 0x000003b6, 0xf81a3562, 0xe0126ba2, 0x18eb3152}, - {0x47c58900, 0x0000000a, 0x000000b9, 0x8e58eccf, 0xf3afc793, 0xd00d08c7}, - {0x292561e8, 0x0000000c, 0x00000403, 0xa2ba8aaf, 0x0b797aed, 0x8ba966bc}, - {0x415037f6, 0x00000003, 0x00000676, 0xa17d52e8, 0x7f0fdf35, 0x11d694a2}, - {0x3466e707, 0x00000026, 0x00000042, 0x258319be, 0x75c484a2, 0x6ab3208d}, - {0xafd1281b, 0x00000023, 0x000002ee, 0x4428eaf8, 0x06c7ad10, 0xba4603c5}, - {0xd3857b18, 0x00000028, 0x000004a2, 0x5c430821, 0xb062b7cb, 0xe6071c6f}, - {0x1d825a8f, 0x0000002b, 0x0000050b, 0xd2c45f0c, 0xd68634e0, 0x179ec30a}, - {0x5033e3bc, 0x0000000b, 0x00000078, 0xa3ea4113, 0xac6d31fb, 0x0903beb8}, - {0x94f1fb5e, 0x0000000f, 0x000003a2, 0xfbfc50b1, 0x3cfe50ed, 0x6a7cb4fa}, - {0xc9a0fe14, 0x00000009, 0x00000473, 0x5fb61894, 0x87070591, 0xdb535801}, - {0x88a034b1, 0x0000001c, 0x000005ad, 0xc1b16053, 0x46f95c67, 0x92bed597}, - {0xf0f72239, 0x00000020, 0x0000026d, 0xa6fa58f3, 0xf8c2c1dd, 0x192a3f1b}, - {0xcc20a5e3, 0x0000003b, 0x0000067a, 0x7740185a, 0x308b979a, 0xccbaec1a}, - {0xce589c95, 0x0000002b, 0x00000641, 0xd055e987, 0x40aae25b, 0x7eabae4d}, - {0x78edc885, 0x00000035, 0x000005be, 0xa39cb14b, 0x035b0d1f, 0x28c72982}, - {0x9d40a377, 0x0000003b, 0x00000038, 0x1f47ccd2, 0x197fbc9d, 0xc3cd4d18}, - {0x703d0e01, 0x0000003c, 0x000006f1, 0x88735e7c, 0xfed57c5a, 0xbca8f0e7}, - {0x776bf505, 0x0000000f, 0x000005b2, 0x5cc4fc01, 0xf32efb97, 0x713f60b3}, - {0x4a3e7854, 0x00000027, 0x000004b8, 0x8d923c82, 0x0cbfb4a2, 0xebd08fd5}, - {0x209172dd, 0x0000003b, 0x00000356, 0xb89e9c2b, 0xd7868138, 0x64406c59}, - {0x3ba4cc5b, 0x0000002f, 0x00000203, 0xe51601a9, 0x5b2a1032, 0x7421890e}, - {0xfc62f297, 0x00000000, 0x00000079, 0x71a8e1a2, 0x5d88685f, 0xe9347603}, - {0x64280b8b, 0x00000016, 0x000007ab, 0x0fa7a30c, 0xda3a455f, 0x1bef9060}, - {0x97dd724b, 0x00000033, 0x000007ad, 0x5788b2f4, 0xd7326d32, 0x34720072}, - {0x61394b52, 0x00000035, 0x00000571, 0xc66525f1, 0xcabe7fef, 0x48310f59}, - {0x29b4faff, 0x00000024, 0x0000006e, 0xca13751e, 0x993648e0, 0x783a4213}, - {0x29bfb1dc, 0x0000000b, 0x00000244, 0x436c43f7, 0x429f7a59, 0x9e8efd41}, - {0x86ae934b, 0x00000035, 0x00000104, 0x0760ec93, 0x9cf7d0f4, 0xfc3d34a5}, - {0xc4c1024e, 0x0000002e, 0x000006b1, 0x6516a3ec, 0x19321f9c, 0x17a52ae2}, - {0x3287a80a, 0x00000026, 0x00000496, 0x0b257eb1, 0x754ebd51, 0x886d935a}, - {0xa4db423e, 0x00000023, 0x0000045d, 0x9b3a66dc, 0x873e9f11, 0xeaaeaeb2}, - {0x7a1078df, 0x00000015, 0x0000014a, 0x8c2484c5, 0x6a628659, 0x8e900a4b}, - {0x6048bd5b, 0x00000006, 0x0000006a, 0x897e3559, 0xac9961af, 0xd74662b1}, - {0xd8f9ea20, 0x0000003d, 0x00000277, 0x60eb905b, 0xed2aaf99, 0xd26752ba}, - {0xea5ec3b4, 0x0000002a, 0x000004fe, 0x869965dc, 0x6c1f833b, 0x8b1fcd62}, - {0x2dfb005d, 0x00000016, 0x00000345, 0x6a3b117e, 0xf05e8521, 0xf54342fe}, - {0x5a214ade, 0x00000020, 0x000005b6, 0x467f70be, 0xcb22ccd3, 0x5b95b988}, - {0xf0ab9cca, 0x00000032, 0x00000515, 0xed223df3, 0x7f3ef01d, 0x2e1176be}, - {0x91b444f9, 0x0000002e, 0x000007f8, 0x84e9a983, 0x5676756f, 0x66120546}, - {0x1b5d2ddb, 0x0000002e, 0x0000012c, 0xba638c4c, 0x3f42047b, 0xf256a5cc}, - {0xd824d1bb, 0x0000003a, 0x000007b5, 0x6288653b, 0x3a3ebea0, 0x4af1dd69}, - {0x0470180c, 0x00000034, 0x000001f0, 0x9d5b80d6, 0x3de08195, 0x56f0a04a}, - {0xffaa3a3f, 0x00000036, 0x00000299, 0xf3a82ab8, 0x53e0c13d, 0x74f6b6b2}, - {0x6406cfeb, 0x00000023, 0x00000600, 0xa920b8e8, 0xe4e2acf4, 0x085951fd}, - {0xb24aaa38, 0x0000003e, 0x000004a1, 0x657cc328, 0x5077b2c3, 0xc65387eb}, - {0x58b2ab7c, 0x00000039, 0x000002b4, 0x3a17ee7e, 0x9dcb3643, 0x1ca9257b}, - {0x3db85970, 0x00000006, 0x000002b6, 0x95268b59, 0xb9812c10, 0xfd196d76}, - {0x857830c5, 0x00000003, 0x00000590, 0x4ef439d5, 0xf042161d, 0x5ef88339}, - {0xe1fcd978, 0x0000003e, 0x000007d8, 0xae8d8699, 0xce0a1ef5, 0x2c3714d9}, - {0xb982a768, 0x00000016, 0x000006e0, 0x62fad3df, 0x5f8a067b, 0x58576548}, - {0x1d581ce8, 0x0000001e, 0x0000058b, 0xf0f5da53, 0x26e39eee, 0xfd7c57de}, - {0x2456719b, 0x00000025, 0x00000503, 0x4296ac64, 0xd50e4c14, 0xd5fedd59}, - {0xfae6d8f2, 0x00000000, 0x0000055d, 0x057fdf2e, 0x2a31391a, 0x1cc3b17b}, - {0xcba828e3, 0x00000039, 0x000002ce, 0xe3f22351, 0x8f00877b, 0x270eed73}, - {0x13d25952, 0x0000000a, 0x0000072d, 0x76d4b4cc, 0x5eb67ec3, 0x91ecbb11}, - {0x0342be3f, 0x00000015, 0x00000599, 0xec75d9f1, 0x9d4d2826, 0x05ed8d0c}, - {0xeaa344e0, 0x00000014, 0x000004d8, 0x72a4c981, 0x2064ea06, 0x0b09ad5b}, - {0xbbb52021, 0x0000003b, 0x00000272, 0x04af99fc, 0xaf042d35, 0xf8d511fb}, - {0xb66384dc, 0x0000001d, 0x000007fc, 0xd7629116, 0x782bd801, 0x5ad832cc}, - {0x616c01b6, 0x00000022, 0x000002c8, 0x5b1dab30, 0x783ce7d2, 0x1214d196}, - {0xce2bdaad, 0x00000016, 0x0000062a, 0x932535c8, 0x3f02926d, 0x5747218a}, - {0x00fe84d7, 0x00000005, 0x00000205, 0x850e50aa, 0x753d649c, 0xde8f14de}, - {0xbebdcb4c, 0x00000006, 0x0000055d, 0xbeaa37a2, 0x2d8c9eba, 0x3563b7b9}, - {0xd8b1a02a, 0x00000010, 0x00000387, 0x5017d2fc, 0x503541a5, 0x071475d0}, - {0x3b96cad2, 0x00000036, 0x00000347, 0x1d2372ae, 0x926cd90b, 0x54c79d60}, - {0xc94c1ed7, 0x00000005, 0x0000038b, 0x9e9fdb22, 0x144a9178, 0x4c53eee6}, - {0x1aad454e, 0x00000025, 0x000002b2, 0xc3f6315c, 0x5c7a35b3, 0x10137a3c}, - {0xa4fec9a6, 0x00000000, 0x000006d6, 0x90be5080, 0xa4107605, 0xaa9d6c73}, - {0x1bbe71e2, 0x0000001f, 0x000002fd, 0x4e504c3b, 0x284ccaf1, 0xb63d23e7}, - {0x4201c7e4, 0x00000002, 0x000002b7, 0x7822e3f9, 0x0cc912a9, 0x7f53e9cf}, - {0x23fddc96, 0x00000003, 0x00000627, 0x8a385125, 0x07767e78, 0x13c1cd83}, - {0xd82ba25c, 0x00000016, 0x0000063e, 0x98e4148a, 0x283330c9, 0x49ff5867}, - {0x786f2032, 0x0000002d, 0x0000060f, 0xf201600a, 0xf561bfcd, 0x8467f211}, - {0xfebe4e1f, 0x0000002a, 0x000004f2, 0x95e51961, 0xfd80dcab, 0x3f9683b2}, - {0x1a6e0a39, 0x00000008, 0x00000672, 0x8af6c2a5, 0x78dd84cb, 0x76a3f874}, - {0x56000ab8, 0x0000000e, 0x000000e5, 0x36bacb8f, 0x22ee1f77, 0x863b702f}, - {0x4717fe0c, 0x00000000, 0x000006ec, 0x8439f342, 0x5c8e03da, 0xdc6c58ff}, - {0xd5d5d68e, 0x0000003c, 0x000003a3, 0x46fff083, 0x177d1b39, 0x0622cc95}, - {0xc25dd6c6, 0x00000024, 0x000006c0, 0x5ceb8eb4, 0x892b0d16, 0xe85605cd}, - {0xe9b11300, 0x00000023, 0x00000683, 0x07a5d59a, 0x6c6a3208, 0x31da5f06}, - {0x95cd285e, 0x00000001, 0x00000047, 0x7b3a4368, 0x0202c07e, 0xa1f2e784}, - {0xd9245a25, 0x0000001e, 0x000003a6, 0xd33c1841, 0x1936c0d5, 0xb07cc616}, - {0x103279db, 0x00000006, 0x0000039b, 0xca09b8a0, 0x77d62892, 0xbf943b6c}, - {0x1cba3172, 0x00000027, 0x000001c8, 0xcb377194, 0xebe682db, 0x2c01af1c}, - {0x8f613739, 0x0000000c, 0x000001df, 0xb4b0bc87, 0x7710bd43, 0x0fe5f56d}, - {0x1c6aa90d, 0x0000001b, 0x0000053c, 0x70559245, 0xda7894ac, 0xf8943b2d}, - {0xaabe5b93, 0x0000003d, 0x00000715, 0xcdbf42fa, 0x0c3b99e7, 0xe4d89272}, - {0xf15dd038, 0x00000006, 0x000006db, 0x6e104aea, 0x8d5967f2, 0x7c2f6bbb}, - {0x584dd49c, 0x00000020, 0x000007bc, 0x36b6cfd6, 0xad4e23b2, 0xabbf388b}, - {0x5d8c9506, 0x00000020, 0x00000470, 0x4c62378e, 0x31d92640, 0x1dca1f4e}, - {0xb80d17b0, 0x00000032, 0x00000346, 0x22a5bb88, 0x9a7ec89f, 0x5c170e23}, - {0xdaf0592e, 0x00000023, 0x000007b0, 0x3cab3f99, 0x9b1fdd99, 0xc0e9d672}, - {0x4793cc85, 0x0000000d, 0x00000706, 0xe82e04f6, 0xed3db6b7, 0xc18bdc86}, - {0x82ebf64e, 0x00000009, 0x000007c3, 0x69d590a9, 0x9efa8499, 0xa874fcdd}, - {0xb18a0319, 0x00000026, 0x000007db, 0x1cf98dcc, 0x8fa9ad6a, 0x9dc0bb48}, -}; - -#include - -static int __init crc32c_test(void) -{ - int i; - int errors = 0; - int bytes = 0; - u64 nsec; - unsigned long flags; - - /* keep static to prevent cache warming code from - * getting eliminated by the compiler */ - static u32 crc; - - /* pre-warm the cache */ - for (i = 0; i < 100; i++) { - bytes += test[i].length; - - crc ^= __crc32c_le(test[i].crc, test_buf + - test[i].start, test[i].length); - } - - /* reduce OS noise */ - local_irq_save(flags); - - nsec = ktime_get_ns(); - for (i = 0; i < 100; i++) { - if (test[i].crc32c_le != __crc32c_le(test[i].crc, test_buf + - test[i].start, test[i].length)) - errors++; - } - nsec = ktime_get_ns() - nsec; - - local_irq_restore(flags); - - pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS); - - if (errors) - pr_warn("crc32c: %d self tests failed\n", errors); - else { - pr_info("crc32c: self tests passed, processed %d bytes in %lld nsec\n", - bytes, nsec); - } - - return 0; -} - -static int __init crc32c_combine_test(void) -{ - int i, j; - int errors = 0, runs = 0; - - for (i = 0; i < 10; i++) { - u32 crc_full; - - crc_full = __crc32c_le(test[i].crc, test_buf + test[i].start, - test[i].length); - for (j = 0; j <= test[i].length; ++j) { - u32 crc1, crc2; - u32 len1 = j, len2 = test[i].length - j; - - crc1 = __crc32c_le(test[i].crc, test_buf + - test[i].start, len1); - crc2 = __crc32c_le(0, test_buf + test[i].start + - len1, len2); - - if (!(crc_full == __crc32c_le_combine(crc1, crc2, len2) && - crc_full == test[i].crc32c_le)) - errors++; - runs++; - cond_resched(); - } - } - - if (errors) - pr_warn("crc32c_combine: %d/%d self tests failed\n", errors, runs); - else - pr_info("crc32c_combine: %d self tests passed\n", runs); - - return 0; -} - -static int __init crc32_test(void) -{ - int i; - int errors = 0; - int bytes = 0; - u64 nsec; - unsigned long flags; - - /* keep static to prevent cache warming code from - * getting eliminated by the compiler */ - static u32 crc; - - /* pre-warm the cache */ - for (i = 0; i < 100; i++) { - bytes += 2*test[i].length; - - crc ^= crc32_le(test[i].crc, test_buf + - test[i].start, test[i].length); - - crc ^= crc32_be(test[i].crc, test_buf + - test[i].start, test[i].length); - } - - /* reduce OS noise */ - local_irq_save(flags); - - nsec = ktime_get_ns(); - for (i = 0; i < 100; i++) { - if (test[i].crc_le != crc32_le(test[i].crc, test_buf + - test[i].start, test[i].length)) - errors++; - - if (test[i].crc_be != crc32_be(test[i].crc, test_buf + - test[i].start, test[i].length)) - errors++; - } - nsec = ktime_get_ns() - nsec; - - local_irq_restore(flags); - - pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n", - CRC_LE_BITS, CRC_BE_BITS); - - if (errors) - pr_warn("crc32: %d self tests failed\n", errors); - else { - pr_info("crc32: self tests passed, processed %d bytes in %lld nsec\n", - bytes, nsec); - } - - return 0; -} - -static int __init crc32_combine_test(void) -{ - int i, j; - int errors = 0, runs = 0; - - for (i = 0; i < 10; i++) { - u32 crc_full; - - crc_full = crc32_le(test[i].crc, test_buf + test[i].start, - test[i].length); - for (j = 0; j <= test[i].length; ++j) { - u32 crc1, crc2; - u32 len1 = j, len2 = test[i].length - j; - - crc1 = crc32_le(test[i].crc, test_buf + - test[i].start, len1); - crc2 = crc32_le(0, test_buf + test[i].start + - len1, len2); - - if (!(crc_full == crc32_le_combine(crc1, crc2, len2) && - crc_full == test[i].crc_le)) - errors++; - runs++; - cond_resched(); - } - } - - if (errors) - pr_warn("crc32_combine: %d/%d self tests failed\n", errors, runs); - else - pr_info("crc32_combine: %d self tests passed\n", runs); - - return 0; -} - -static int __init crc32test_init(void) -{ - crc32_test(); - crc32c_test(); - - crc32_combine_test(); - crc32c_combine_test(); - - return 0; -} - -static void __exit crc32_exit(void) -{ -} - -module_init(crc32test_init); -module_exit(crc32_exit); - -MODULE_AUTHOR("Matt Domsch "); -MODULE_DESCRIPTION("CRC32 selftest"); -MODULE_LICENSE("GPL"); diff --git a/lib/crc_kunit.c b/lib/crc_kunit.c new file mode 100644 index 000000000000..6a61d4b5fd45 --- /dev/null +++ b/lib/crc_kunit.c @@ -0,0 +1,435 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Unit tests and benchmarks for the CRC library functions + * + * Copyright 2024 Google LLC + * + * Author: Eric Biggers + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#define CRC_KUNIT_SEED 42 +#define CRC_KUNIT_MAX_LEN 16384 +#define CRC_KUNIT_NUM_TEST_ITERS 1000 + +static struct rnd_state rng; +static u8 *test_buffer; +static size_t test_buflen; + +/** + * struct crc_variant - describes a CRC variant + * @bits: Number of bits in the CRC, 1 <= @bits <= 64. + * @le: true if it's a "little endian" CRC (reversed mapping between bits and + * polynomial coefficients in each byte), false if it's a "big endian" CRC + * (natural mapping between bits and polynomial coefficients in each byte) + * @poly: The generator polynomial with the highest-order term omitted. + * Bit-reversed if @le is true. + * @func: The function to compute a CRC. The type signature uses u64 so that it + * can fit any CRC up to CRC-64. + * @combine_func: Optional function to combine two CRCs. + */ +struct crc_variant { + int bits; + bool le; + u64 poly; + u64 (*func)(u64 crc, const u8 *p, size_t len); + u64 (*combine_func)(u64 crc1, u64 crc2, size_t len2); +}; + +static u32 rand32(void) +{ + return prandom_u32_state(&rng); +} + +static u64 rand64(void) +{ + u32 n = rand32(); + + return ((u64)n << 32) | rand32(); +} + +static u64 crc_mask(const struct crc_variant *v) +{ + return (u64)-1 >> (64 - v->bits); +} + +/* Reference implementation of any CRC variant */ +static u64 crc_ref(const struct crc_variant *v, + u64 crc, const u8 *p, size_t len) +{ + size_t i, j; + + for (i = 0; i < len; i++) { + for (j = 0; j < 8; j++) { + if (v->le) { + crc ^= (p[i] >> j) & 1; + crc = (crc >> 1) ^ ((crc & 1) ? v->poly : 0); + } else { + crc ^= (u64)((p[i] >> (7 - j)) & 1) << + (v->bits - 1); + if (crc & (1ULL << (v->bits - 1))) + crc = ((crc << 1) ^ v->poly) & + crc_mask(v); + else + crc <<= 1; + } + } + } + return crc; +} + +static int crc_suite_init(struct kunit_suite *suite) +{ + /* + * Allocate the test buffer using vmalloc() with a page-aligned length + * so that it is immediately followed by a guard page. This allows + * buffer overreads to be detected, even in assembly code. + */ + test_buflen = round_up(CRC_KUNIT_MAX_LEN, PAGE_SIZE); + test_buffer = vmalloc(test_buflen); + if (!test_buffer) + return -ENOMEM; + + prandom_seed_state(&rng, CRC_KUNIT_SEED); + prandom_bytes_state(&rng, test_buffer, test_buflen); + return 0; +} + +static void crc_suite_exit(struct kunit_suite *suite) +{ + vfree(test_buffer); + test_buffer = NULL; +} + +/* Generate a random initial CRC. */ +static u64 generate_random_initial_crc(const struct crc_variant *v) +{ + switch (rand32() % 4) { + case 0: + return 0; + case 1: + return crc_mask(v); /* All 1 bits */ + default: + return rand64() & crc_mask(v); + } +} + +/* Generate a random length, preferring small lengths. */ +static size_t generate_random_length(size_t max_length) +{ + size_t len; + + switch (rand32() % 3) { + case 0: + len = rand32() % 128; + break; + case 1: + len = rand32() % 3072; + break; + default: + len = rand32(); + break; + } + return len % (max_length + 1); +} + +/* Test that v->func gives the same CRCs as a reference implementation. */ +static void crc_main_test(struct kunit *test, const struct crc_variant *v) +{ + size_t i; + + for (i = 0; i < CRC_KUNIT_NUM_TEST_ITERS; i++) { + u64 init_crc, expected_crc, actual_crc; + size_t len, offset; + bool nosimd; + + init_crc = generate_random_initial_crc(v); + len = generate_random_length(CRC_KUNIT_MAX_LEN); + + /* Generate a random offset. */ + if (rand32() % 2 == 0) { + /* Use a random alignment mod 64 */ + offset = rand32() % 64; + offset = min(offset, CRC_KUNIT_MAX_LEN - len); + } else { + /* Go up to the guard page, to catch buffer overreads */ + offset = test_buflen - len; + } + + if (rand32() % 8 == 0) + /* Refresh the data occasionally. */ + prandom_bytes_state(&rng, &test_buffer[offset], len); + + nosimd = rand32() % 8 == 0; + + /* + * Compute the CRC, and verify that it equals the CRC computed + * by a simple bit-at-a-time reference implementation. + */ + expected_crc = crc_ref(v, init_crc, &test_buffer[offset], len); + if (nosimd) + local_irq_disable(); + actual_crc = v->func(init_crc, &test_buffer[offset], len); + if (nosimd) + local_irq_enable(); + KUNIT_EXPECT_EQ_MSG(test, expected_crc, actual_crc, + "Wrong result with len=%zu offset=%zu nosimd=%d", + len, offset, nosimd); + } +} + +/* Test that CRC(concat(A, B)) == combine_CRCs(CRC(A), CRC(B), len(B)). */ +static void crc_combine_test(struct kunit *test, const struct crc_variant *v) +{ + int i; + + for (i = 0; i < 100; i++) { + u64 init_crc = generate_random_initial_crc(v); + size_t len1 = generate_random_length(CRC_KUNIT_MAX_LEN); + size_t len2 = generate_random_length(CRC_KUNIT_MAX_LEN - len1); + u64 crc1, crc2, expected_crc, actual_crc; + + prandom_bytes_state(&rng, test_buffer, len1 + len2); + crc1 = v->func(init_crc, test_buffer, len1); + crc2 = v->func(0, &test_buffer[len1], len2); + expected_crc = v->func(init_crc, test_buffer, len1 + len2); + actual_crc = v->combine_func(crc1, crc2, len2); + KUNIT_EXPECT_EQ_MSG(test, expected_crc, actual_crc, + "CRC combination gave wrong result with len1=%zu len2=%zu\n", + len1, len2); + } +} + +static void crc_test(struct kunit *test, const struct crc_variant *v) +{ + crc_main_test(test, v); + if (v->combine_func) + crc_combine_test(test, v); +} + +static __always_inline void +crc_benchmark(struct kunit *test, + u64 (*crc_func)(u64 crc, const u8 *p, size_t len)) +{ + static const size_t lens_to_test[] = { + 1, 16, 64, 127, 128, 200, 256, 511, 512, 1024, 3173, 4096, 16384, + }; + size_t len, i, j, num_iters; + /* + * Some of the CRC library functions are marked as __pure, so use + * volatile to ensure that all calls are really made as intended. + */ + volatile u64 crc = 0; + u64 t; + + if (!IS_ENABLED(CONFIG_CRC_BENCHMARK)) + kunit_skip(test, "not enabled"); + + /* warm-up */ + for (i = 0; i < 10000000; i += CRC_KUNIT_MAX_LEN) + crc = crc_func(crc, test_buffer, CRC_KUNIT_MAX_LEN); + + for (i = 0; i < ARRAY_SIZE(lens_to_test); i++) { + len = lens_to_test[i]; + KUNIT_ASSERT_LE(test, len, CRC_KUNIT_MAX_LEN); + num_iters = 10000000 / (len + 128); + preempt_disable(); + t = ktime_get_ns(); + for (j = 0; j < num_iters; j++) + crc = crc_func(crc, test_buffer, len); + t = ktime_get_ns() - t; + preempt_enable(); + kunit_info(test, "len=%zu: %llu MB/s\n", + len, div64_u64((u64)len * num_iters * 1000, t)); + } +} + +/* crc16 */ + +static u64 crc16_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc16(crc, p, len); +} + +static const struct crc_variant crc_variant_crc16 = { + .bits = 16, + .le = true, + .poly = 0xa001, + .func = crc16_wrapper, +}; + +static void crc16_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc16); +} + +static void crc16_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc16_wrapper); +} + +/* crc_t10dif */ + +static u64 crc_t10dif_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc_t10dif_update(crc, p, len); +} + +static const struct crc_variant crc_variant_crc_t10dif = { + .bits = 16, + .le = false, + .poly = 0x8bb7, + .func = crc_t10dif_wrapper, +}; + +static void crc_t10dif_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc_t10dif); +} + +static void crc_t10dif_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc_t10dif_wrapper); +} + +/* crc32_le */ + +static u64 crc32_le_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc32_le(crc, p, len); +} + +static u64 crc32_le_combine_wrapper(u64 crc1, u64 crc2, size_t len2) +{ + return crc32_le_combine(crc1, crc2, len2); +} + +static const struct crc_variant crc_variant_crc32_le = { + .bits = 32, + .le = true, + .poly = 0xedb88320, + .func = crc32_le_wrapper, + .combine_func = crc32_le_combine_wrapper, +}; + +static void crc32_le_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc32_le); +} + +static void crc32_le_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc32_le_wrapper); +} + +/* crc32_be */ + +static u64 crc32_be_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc32_be(crc, p, len); +} + +static const struct crc_variant crc_variant_crc32_be = { + .bits = 32, + .le = false, + .poly = 0x04c11db7, + .func = crc32_be_wrapper, +}; + +static void crc32_be_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc32_be); +} + +static void crc32_be_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc32_be_wrapper); +} + +/* crc32c */ + +static u64 crc32c_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc32c(crc, p, len); +} + +static u64 crc32c_combine_wrapper(u64 crc1, u64 crc2, size_t len2) +{ + return __crc32c_le_combine(crc1, crc2, len2); +} + +static const struct crc_variant crc_variant_crc32c = { + .bits = 32, + .le = true, + .poly = 0x82f63b78, + .func = crc32c_wrapper, + .combine_func = crc32c_combine_wrapper, +}; + +static void crc32c_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc32c); +} + +static void crc32c_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc32c_wrapper); +} + +/* crc64_be */ + +static u64 crc64_be_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc64_be(crc, p, len); +} + +static const struct crc_variant crc_variant_crc64_be = { + .bits = 64, + .le = false, + .poly = 0x42f0e1eba9ea3693, + .func = crc64_be_wrapper, +}; + +static void crc64_be_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc64_be); +} + +static void crc64_be_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc64_be_wrapper); +} + +static struct kunit_case crc_test_cases[] = { + KUNIT_CASE(crc16_test), + KUNIT_CASE(crc16_benchmark), + KUNIT_CASE(crc_t10dif_test), + KUNIT_CASE(crc_t10dif_benchmark), + KUNIT_CASE(crc32_le_test), + KUNIT_CASE(crc32_le_benchmark), + KUNIT_CASE(crc32_be_test), + KUNIT_CASE(crc32_be_benchmark), + KUNIT_CASE(crc32c_test), + KUNIT_CASE(crc32c_benchmark), + KUNIT_CASE(crc64_be_test), + KUNIT_CASE(crc64_be_benchmark), + {}, +}; + +static struct kunit_suite crc_test_suite = { + .name = "crc", + .test_cases = crc_test_cases, + .suite_init = crc_suite_init, + .suite_exit = crc_suite_exit, +}; +kunit_test_suite(crc_test_suite); + +MODULE_DESCRIPTION("Unit tests and benchmarks for the CRC library functions"); +MODULE_LICENSE("GPL"); diff --git a/lib/crypto/aesgcm.c b/lib/crypto/aesgcm.c index 6bba6473fdf3..902e49410aaf 100644 --- a/lib/crypto/aesgcm.c +++ b/lib/crypto/aesgcm.c @@ -697,7 +697,7 @@ static int __init libaesgcm_init(void) u8 tagbuf[AES_BLOCK_SIZE]; int plen = aesgcm_tv[i].plen; struct aesgcm_ctx ctx; - u8 buf[sizeof(ptext12)]; + static u8 buf[sizeof(ptext12)]; if (aesgcm_expandkey(&ctx, aesgcm_tv[i].key, aesgcm_tv[i].klen, aesgcm_tv[i].clen - plen)) { diff --git a/lib/crypto/gf128mul.c b/lib/crypto/gf128mul.c index 8f8c45e0cdcf..fbe72cb3453a 100644 --- a/lib/crypto/gf128mul.c +++ b/lib/crypto/gf128mul.c @@ -225,44 +225,6 @@ void gf128mul_lle(be128 *r, const be128 *b) } EXPORT_SYMBOL(gf128mul_lle); -void gf128mul_bbe(be128 *r, const be128 *b) -{ - be128 p[8]; - int i; - - p[0] = *r; - for (i = 0; i < 7; ++i) - gf128mul_x_bbe(&p[i + 1], &p[i]); - - memset(r, 0, sizeof(*r)); - for (i = 0;;) { - u8 ch = ((u8 *)b)[i]; - - if (ch & 0x80) - be128_xor(r, r, &p[7]); - if (ch & 0x40) - be128_xor(r, r, &p[6]); - if (ch & 0x20) - be128_xor(r, r, &p[5]); - if (ch & 0x10) - be128_xor(r, r, &p[4]); - if (ch & 0x08) - be128_xor(r, r, &p[3]); - if (ch & 0x04) - be128_xor(r, r, &p[2]); - if (ch & 0x02) - be128_xor(r, r, &p[1]); - if (ch & 0x01) - be128_xor(r, r, &p[0]); - - if (++i >= 16) - break; - - gf128mul_x8_bbe(r); - } -} -EXPORT_SYMBOL(gf128mul_bbe); - /* This version uses 64k bytes of table space. A 16 byte buffer has to be multiplied by a 16 byte key value in GF(2^128). If we consider a GF(2^128) value in @@ -380,28 +342,6 @@ out: } EXPORT_SYMBOL(gf128mul_init_4k_lle); -struct gf128mul_4k *gf128mul_init_4k_bbe(const be128 *g) -{ - struct gf128mul_4k *t; - int j, k; - - t = kzalloc(sizeof(*t), GFP_KERNEL); - if (!t) - goto out; - - t->t[1] = *g; - for (j = 1; j <= 64; j <<= 1) - gf128mul_x_bbe(&t->t[j + j], &t->t[j]); - - for (j = 2; j < 256; j += j) - for (k = 1; k < j; ++k) - be128_xor(&t->t[j + k], &t->t[j], &t->t[k]); - -out: - return t; -} -EXPORT_SYMBOL(gf128mul_init_4k_bbe); - void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t) { u8 *ap = (u8 *)a; @@ -417,20 +357,5 @@ void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t) } EXPORT_SYMBOL(gf128mul_4k_lle); -void gf128mul_4k_bbe(be128 *a, const struct gf128mul_4k *t) -{ - u8 *ap = (u8 *)a; - be128 r[1]; - int i = 0; - - *r = t->t[ap[0]]; - while (++i < 16) { - gf128mul_x8_bbe(r); - be128_xor(r, r, &t->t[ap[i]]); - } - *a = *r; -} -EXPORT_SYMBOL(gf128mul_4k_bbe); - MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Functions for multiplying elements of GF(2^128)"); diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 52eb6ba29698..999053fa133e 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only #include #include -#include +#include #include #include #include @@ -12,6 +12,24 @@ #include #include +/* + * The should_fail() functions use prandom instead of the normal Linux RNG + * since they don't need cryptographically secure random numbers. + */ +static DEFINE_PER_CPU(struct rnd_state, fault_rnd_state); + +static u32 fault_prandom_u32_below_100(void) +{ + struct rnd_state *state; + u32 res; + + state = &get_cpu_var(fault_rnd_state); + res = prandom_u32_state(state); + put_cpu_var(fault_rnd_state); + + return res % 100; +} + /* * setup_fault_attr() is a helper function for various __setup handlers, so it * returns 0 on error, because that is what __setup handlers do. @@ -31,6 +49,8 @@ int setup_fault_attr(struct fault_attr *attr, char *str) return 0; } + prandom_init_once(&fault_rnd_state); + attr->probability = probability; attr->interval = interval; atomic_set(&attr->times, times); @@ -146,7 +166,7 @@ bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags) return false; } - if (attr->probability <= get_random_u32_below(100)) + if (attr->probability <= fault_prandom_u32_below_100()) return false; fail: @@ -219,6 +239,8 @@ struct dentry *fault_create_debugfs_attr(const char *name, if (IS_ERR(dir)) return dir; + prandom_init_once(&fault_rnd_state); + debugfs_create_ul("probability", mode, dir, &attr->probability); debugfs_create_ul("interval", mode, dir, &attr->interval); debugfs_create_atomic_t("times", mode, dir, &attr->times); @@ -431,6 +453,8 @@ static const struct config_item_type fault_config_type = { void fault_config_init(struct fault_config *config, const char *name) { + prandom_init_once(&fault_rnd_state); + config_group_init_type_name(&config->group, name, &fault_config_type); } EXPORT_SYMBOL_GPL(fault_config_init); diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c index f755b997b967..6d03425b849e 100644 --- a/lib/gen_crc32table.c +++ b/lib/gen_crc32table.c @@ -2,30 +2,11 @@ #include #include "../include/linux/crc32poly.h" #include "../include/generated/autoconf.h" -#include "crc32defs.h" #include -#define ENTRIES_PER_LINE 4 - -#if CRC_LE_BITS > 8 -# define LE_TABLE_ROWS (CRC_LE_BITS/8) -# define LE_TABLE_SIZE 256 -#else -# define LE_TABLE_ROWS 1 -# define LE_TABLE_SIZE (1 << CRC_LE_BITS) -#endif - -#if CRC_BE_BITS > 8 -# define BE_TABLE_ROWS (CRC_BE_BITS/8) -# define BE_TABLE_SIZE 256 -#else -# define BE_TABLE_ROWS 1 -# define BE_TABLE_SIZE (1 << CRC_BE_BITS) -#endif - -static uint32_t crc32table_le[LE_TABLE_ROWS][256]; -static uint32_t crc32table_be[BE_TABLE_ROWS][256]; -static uint32_t crc32ctable_le[LE_TABLE_ROWS][256]; +static uint32_t crc32table_le[256]; +static uint32_t crc32table_be[256]; +static uint32_t crc32ctable_le[256]; /** * crc32init_le() - allocate and initialize LE table data @@ -34,25 +15,17 @@ static uint32_t crc32ctable_le[LE_TABLE_ROWS][256]; * fact that crctable[i^j] = crctable[i] ^ crctable[j]. * */ -static void crc32init_le_generic(const uint32_t polynomial, - uint32_t (*tab)[256]) +static void crc32init_le_generic(const uint32_t polynomial, uint32_t tab[256]) { unsigned i, j; uint32_t crc = 1; - tab[0][0] = 0; + tab[0] = 0; - for (i = LE_TABLE_SIZE >> 1; i; i >>= 1) { + for (i = 128; i; i >>= 1) { crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0); - for (j = 0; j < LE_TABLE_SIZE; j += 2 * i) - tab[0][i + j] = crc ^ tab[0][j]; - } - for (i = 0; i < LE_TABLE_SIZE; i++) { - crc = tab[0][i]; - for (j = 1; j < LE_TABLE_ROWS; j++) { - crc = tab[0][crc & 0xff] ^ (crc >> 8); - tab[j][i] = crc; - } + for (j = 0; j < 256; j += 2 * i) + tab[i + j] = crc ^ tab[j]; } } @@ -74,34 +47,22 @@ static void crc32init_be(void) unsigned i, j; uint32_t crc = 0x80000000; - crc32table_be[0][0] = 0; + crc32table_be[0] = 0; - for (i = 1; i < BE_TABLE_SIZE; i <<= 1) { + for (i = 1; i < 256; i <<= 1) { crc = (crc << 1) ^ ((crc & 0x80000000) ? CRC32_POLY_BE : 0); for (j = 0; j < i; j++) - crc32table_be[0][i + j] = crc ^ crc32table_be[0][j]; - } - for (i = 0; i < BE_TABLE_SIZE; i++) { - crc = crc32table_be[0][i]; - for (j = 1; j < BE_TABLE_ROWS; j++) { - crc = crc32table_be[0][(crc >> 24) & 0xff] ^ (crc << 8); - crc32table_be[j][i] = crc; - } + crc32table_be[i + j] = crc ^ crc32table_be[j]; } } -static void output_table(uint32_t (*table)[256], int rows, int len, char *trans) +static void output_table(const uint32_t table[256]) { - int i, j; + int i; - for (j = 0 ; j < rows; j++) { - printf("{"); - for (i = 0; i < len - 1; i++) { - if (i % ENTRIES_PER_LINE == 0) - printf("\n"); - printf("%s(0x%8.8xL), ", trans, table[j][i]); - } - printf("%s(0x%8.8xL)},\n", trans, table[j][len - 1]); + for (i = 0; i < 256; i += 4) { + printf("\t0x%08x, 0x%08x, 0x%08x, 0x%08x,\n", + table[i], table[i + 1], table[i + 2], table[i + 3]); } } @@ -109,34 +70,20 @@ int main(int argc, char** argv) { printf("/* this file is generated - do not edit */\n\n"); - if (CRC_LE_BITS > 1) { - crc32init_le(); - printf("static const u32 ____cacheline_aligned " - "crc32table_le[%d][%d] = {", - LE_TABLE_ROWS, LE_TABLE_SIZE); - output_table(crc32table_le, LE_TABLE_ROWS, - LE_TABLE_SIZE, "tole"); - printf("};\n"); - } + crc32init_le(); + printf("static const u32 ____cacheline_aligned crc32table_le[256] = {\n"); + output_table(crc32table_le); + printf("};\n"); - if (CRC_BE_BITS > 1) { - crc32init_be(); - printf("static const u32 ____cacheline_aligned " - "crc32table_be[%d][%d] = {", - BE_TABLE_ROWS, BE_TABLE_SIZE); - output_table(crc32table_be, LE_TABLE_ROWS, - BE_TABLE_SIZE, "tobe"); - printf("};\n"); - } - if (CRC_LE_BITS > 1) { - crc32cinit_le(); - printf("static const u32 ____cacheline_aligned " - "crc32ctable_le[%d][%d] = {", - LE_TABLE_ROWS, LE_TABLE_SIZE); - output_table(crc32ctable_le, LE_TABLE_ROWS, - LE_TABLE_SIZE, "tole"); - printf("};\n"); - } + crc32init_be(); + printf("static const u32 ____cacheline_aligned crc32table_be[256] = {\n"); + output_table(crc32table_be); + printf("};\n"); + + crc32cinit_le(); + printf("static const u32 ____cacheline_aligned crc32ctable_le[256] = {\n"); + output_table(crc32ctable_le); + printf("};\n"); return 0; } diff --git a/lib/inflate.c b/lib/inflate.c index fbaf03c1748d..eab886baa1b4 100644 --- a/lib/inflate.c +++ b/lib/inflate.c @@ -1257,8 +1257,6 @@ static int INIT gunzip(void) /* Decompress */ if ((res = inflate())) { switch (res) { - case 0: - break; case 1: error("invalid compressed format (err=1)"); break; diff --git a/lib/kobject.c b/lib/kobject.c index 72fa20f405f1..abe5f5b856ce 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -1096,30 +1096,6 @@ void *kobj_ns_grab_current(enum kobj_ns_type type) } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); -const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk) -{ - const void *ns = NULL; - - spin_lock(&kobj_ns_type_lock); - if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) - ns = kobj_ns_ops_tbl[type]->netlink_ns(sk); - spin_unlock(&kobj_ns_type_lock); - - return ns; -} - -const void *kobj_ns_initial(enum kobj_ns_type type) -{ - const void *ns = NULL; - - spin_lock(&kobj_ns_type_lock); - if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) - ns = kobj_ns_ops_tbl[type]->initial_ns(); - spin_unlock(&kobj_ns_type_lock); - - return ns; -} - void kobj_ns_drop(enum kobj_ns_type type, void *ns) { spin_lock(&kobj_ns_type_lock); diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig index 34d7242d526d..a97897edd964 100644 --- a/lib/kunit/Kconfig +++ b/lib/kunit/Kconfig @@ -81,4 +81,16 @@ config KUNIT_DEFAULT_ENABLED In most cases this should be left as Y. Only if additional opt-in behavior is needed should this be set to N. +config KUNIT_AUTORUN_ENABLED + bool "Default value of kunit.autorun" + default y + help + Sets the default value of kunit.autorun. If set to N then KUnit + tests will not run after initialization unless kunit.autorun=1 is + passed to the kernel command line. The test can still be run manually + via debugfs interface. + + In most cases this should be left as Y. Only if additional opt-in + behavior is needed should this be set to N. + endif # KUNIT diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index af71911f4a07..9c326f1837bd 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -145,7 +145,7 @@ static ssize_t debugfs_run(struct file *file, struct inode *f_inode = file->f_inode; struct kunit_suite *suite = (struct kunit_suite *) f_inode->i_private; - __kunit_test_suites_init(&suite, 1); + __kunit_test_suites_init(&suite, 1, true); return count; } diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c index 34b7b6833df3..3f39955cb0f1 100644 --- a/lib/kunit/executor.c +++ b/lib/kunit/executor.c @@ -29,6 +29,22 @@ const char *kunit_action(void) return action_param; } +/* + * Run KUnit tests after initialization + */ +#ifdef CONFIG_KUNIT_AUTORUN_ENABLED +static bool autorun_param = true; +#else +static bool autorun_param; +#endif +module_param_named(autorun, autorun_param, bool, 0); +MODULE_PARM_DESC(autorun, "Run KUnit tests after initialization"); + +bool kunit_autorun(void) +{ + return autorun_param; +} + static char *filter_glob_param; static char *filter_param; static char *filter_action_param; @@ -260,13 +276,14 @@ free_copy: void kunit_exec_run_tests(struct kunit_suite_set *suite_set, bool builtin) { size_t num_suites = suite_set->end - suite_set->start; + bool autorun = kunit_autorun(); - if (builtin || num_suites) { + if (autorun && (builtin || num_suites)) { pr_info("KTAP version 1\n"); pr_info("1..%zu\n", num_suites); } - __kunit_test_suites_init(suite_set->start, num_suites); + __kunit_test_suites_init(suite_set->start, num_suites, autorun); } void kunit_exec_list_tests(struct kunit_suite_set *suite_set, bool include_attr) diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 089c832e3cdb..146d1b48a096 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -708,7 +708,8 @@ bool kunit_enabled(void) return enable_param; } -int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites) +int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites, + bool run_tests) { unsigned int i; @@ -731,7 +732,8 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_ for (i = 0; i < num_suites; i++) { kunit_init_suite(suites[i]); - kunit_run_tests(suites[i]); + if (run_tests) + kunit_run_tests(suites[i]); } static_branch_dec(&kunit_running); diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c index 13e15687675a..48342736d016 100644 --- a/lib/kunit_iov_iter.c +++ b/lib/kunit_iov_iter.c @@ -57,15 +57,12 @@ static void *__init iov_kunit_create_buffer(struct kunit *test, KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pages); *ppages = pages; - got = alloc_pages_bulk_array(GFP_KERNEL, npages, pages); + got = alloc_pages_bulk(GFP_KERNEL, npages, pages); if (got != npages) { release_pages(pages, got); KUNIT_ASSERT_EQ(test, got, npages); } - for (int i = 0; i < npages; i++) - pages[i]->index = i; - buffer = vmap(pages, npages, VM_MAP | VM_MAP_PUT_PAGES, PAGE_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buffer); @@ -392,7 +389,7 @@ static void __init iov_kunit_load_folioq(struct kunit *test, if (folioq_full(p)) { p->next = kzalloc(sizeof(struct folio_queue), GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, p->next); - folioq_init(p->next); + folioq_init(p->next, 0); p->next->prev = p; p = p->next; } @@ -409,7 +406,7 @@ static struct folio_queue *iov_kunit_create_folioq(struct kunit *test) folioq = kzalloc(sizeof(struct folio_queue), GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, folioq); kunit_add_action_or_reset(test, iov_kunit_destroy_folioq, folioq); - folioq_init(folioq); + folioq_init(folioq, 0); return folioq; } diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c deleted file mode 100644 index 649e687413a0..000000000000 --- a/lib/libcrc32c.c +++ /dev/null @@ -1,74 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * CRC32C - *@Article{castagnoli-crc, - * author = { Guy Castagnoli and Stefan Braeuer and Martin Herrman}, - * title = {{Optimization of Cyclic Redundancy-Check Codes with 24 - * and 32 Parity Bits}}, - * journal = IEEE Transactions on Communication, - * year = {1993}, - * volume = {41}, - * number = {6}, - * pages = {}, - * month = {June}, - *} - * Used by the iSCSI driver, possibly others, and derived from - * the iscsi-crc.c module of the linux-iscsi driver at - * http://linux-iscsi.sourceforge.net. - * - * Following the example of lib/crc32, this function is intended to be - * flexible and useful for all users. Modules that currently have their - * own crc32c, but hopefully may be able to use this one are: - * net/sctp (please add all your doco to here if you change to - * use this one!) - * - * - * Copyright (c) 2004 Cisco Systems, Inc. - */ - -#include -#include -#include -#include -#include -#include - -static struct crypto_shash *tfm; - -u32 crc32c(u32 crc, const void *address, unsigned int length) -{ - SHASH_DESC_ON_STACK(shash, tfm); - u32 ret, *ctx = (u32 *)shash_desc_ctx(shash); - int err; - - shash->tfm = tfm; - *ctx = crc; - - err = crypto_shash_update(shash, address, length); - BUG_ON(err); - - ret = *ctx; - barrier_data(ctx); - return ret; -} - -EXPORT_SYMBOL(crc32c); - -static int __init libcrc32c_mod_init(void) -{ - tfm = crypto_alloc_shash("crc32c", 0, 0); - return PTR_ERR_OR_ZERO(tfm); -} - -static void __exit libcrc32c_mod_fini(void) -{ - crypto_free_shash(tfm); -} - -module_init(libcrc32c_mod_init); -module_exit(libcrc32c_mod_fini); - -MODULE_AUTHOR("Clay Haapala "); -MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations"); -MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: crc32c"); diff --git a/lib/list_debug.c b/lib/list_debug.c index db602417febf..ee7eeeb8f92c 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -22,17 +22,17 @@ __list_valid_slowpath bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev, struct list_head *next) { - if (CHECK_DATA_CORRUPTION(prev == NULL, + if (CHECK_DATA_CORRUPTION(prev == NULL, NULL, "list_add corruption. prev is NULL.\n") || - CHECK_DATA_CORRUPTION(next == NULL, + CHECK_DATA_CORRUPTION(next == NULL, NULL, "list_add corruption. next is NULL.\n") || - CHECK_DATA_CORRUPTION(next->prev != prev, + CHECK_DATA_CORRUPTION(next->prev != prev, next, "list_add corruption. next->prev should be prev (%px), but was %px. (next=%px).\n", prev, next->prev, next) || - CHECK_DATA_CORRUPTION(prev->next != next, + CHECK_DATA_CORRUPTION(prev->next != next, prev, "list_add corruption. prev->next should be next (%px), but was %px. (prev=%px).\n", next, prev->next, prev) || - CHECK_DATA_CORRUPTION(new == prev || new == next, + CHECK_DATA_CORRUPTION(new == prev || new == next, NULL, "list_add double add: new=%px, prev=%px, next=%px.\n", new, prev, next)) return false; @@ -49,20 +49,20 @@ bool __list_del_entry_valid_or_report(struct list_head *entry) prev = entry->prev; next = entry->next; - if (CHECK_DATA_CORRUPTION(next == NULL, + if (CHECK_DATA_CORRUPTION(next == NULL, NULL, "list_del corruption, %px->next is NULL\n", entry) || - CHECK_DATA_CORRUPTION(prev == NULL, + CHECK_DATA_CORRUPTION(prev == NULL, NULL, "list_del corruption, %px->prev is NULL\n", entry) || - CHECK_DATA_CORRUPTION(next == LIST_POISON1, + CHECK_DATA_CORRUPTION(next == LIST_POISON1, next, "list_del corruption, %px->next is LIST_POISON1 (%px)\n", entry, LIST_POISON1) || - CHECK_DATA_CORRUPTION(prev == LIST_POISON2, + CHECK_DATA_CORRUPTION(prev == LIST_POISON2, prev, "list_del corruption, %px->prev is LIST_POISON2 (%px)\n", entry, LIST_POISON2) || - CHECK_DATA_CORRUPTION(prev->next != entry, + CHECK_DATA_CORRUPTION(prev->next != entry, prev, "list_del corruption. prev->next should be %px, but was %px. (prev=%px)\n", entry, prev->next, prev) || - CHECK_DATA_CORRUPTION(next->prev != entry, + CHECK_DATA_CORRUPTION(next->prev != entry, next, "list_del corruption. next->prev should be %px, but was %px. (next=%px)\n", entry, next->prev, next)) return false; diff --git a/lib/list_sort.c b/lib/list_sort.c index 8d3f623536fe..a310ecb7ccc0 100644 --- a/lib/list_sort.c +++ b/lib/list_sort.c @@ -108,6 +108,13 @@ static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head, * and list_sort is a stable sort, so it is not necessary to distinguish * the @a < @b and @a == @b cases. * + * The comparison function must adhere to specific mathematical properties + * to ensure correct and stable sorting: + * - Antisymmetry: cmp(@a, @b) must return the opposite sign of + * cmp(@b, @a). + * - Transitivity: if cmp(@a, @b) <= 0 and cmp(@b, @c) <= 0, then + * cmp(@a, @c) <= 0. + * * This is compatible with two styles of @cmp function: * - The traditional style which returns <0 / =0 / >0, or * - Returning a boolean 0/1. diff --git a/lib/lockref.c b/lib/lockref.c index 2afe4c5d8919..5d8e3ef3860e 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -58,63 +58,34 @@ EXPORT_SYMBOL(lockref_get); * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ -int lockref_get_not_zero(struct lockref *lockref) +bool lockref_get_not_zero(struct lockref *lockref) { - int retval; + bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count <= 0) - return 0; + return false; , - return 1; + return true; ); spin_lock(&lockref->lock); - retval = 0; if (lockref->count > 0) { lockref->count++; - retval = 1; + retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); -/** - * lockref_put_not_zero - Decrements count unless count <= 1 before decrement - * @lockref: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count would become zero - */ -int lockref_put_not_zero(struct lockref *lockref) -{ - int retval; - - CMPXCHG_LOOP( - new.count--; - if (old.count <= 1) - return 0; - , - return 1; - ); - - spin_lock(&lockref->lock); - retval = 0; - if (lockref->count > 1) { - lockref->count--; - retval = 1; - } - spin_unlock(&lockref->lock); - return retval; -} -EXPORT_SYMBOL(lockref_put_not_zero); - /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. - * If the lockref was dead or locked, return an error. + * If the lockref was dead or locked, return -1. */ int lockref_put_return(struct lockref *lockref) { @@ -134,22 +105,22 @@ EXPORT_SYMBOL(lockref_put_return); * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ -int lockref_put_or_lock(struct lockref *lockref) +bool lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , - return 1; + return true; ); spin_lock(&lockref->lock); if (lockref->count <= 1) - return 0; + return false; lockref->count--; spin_unlock(&lockref->lock); - return 1; + return true; } EXPORT_SYMBOL(lockref_put_or_lock); @@ -169,23 +140,22 @@ EXPORT_SYMBOL(lockref_mark_dead); * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ -int lockref_get_not_dead(struct lockref *lockref) +bool lockref_get_not_dead(struct lockref *lockref) { - int retval; + bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count < 0) - return 0; + return false; , - return 1; + return true; ); spin_lock(&lockref->lock); - retval = 0; if (lockref->count >= 0) { lockref->count++; - retval = 1; + retval = true; } spin_unlock(&lockref->lock); return retval; diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c index b0bbeeb74b9e..2a397bb2c661 100644 --- a/lib/lz4/lz4_compress.c +++ b/lib/lz4/lz4_compress.c @@ -33,7 +33,6 @@ /*-************************************ * Dependencies **************************************/ -#include #include "lz4defs.h" #include #include diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 0e31e6da5ce7..3a2cd9acada4 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -33,7 +33,6 @@ /*-************************************ * Dependencies **************************************/ -#include #include "lz4defs.h" #include #include diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h index cb358d6bde5a..17277ec16919 100644 --- a/lib/lz4/lz4defs.h +++ b/lib/lz4/lz4defs.h @@ -39,6 +39,7 @@ #include #include /* memset, memcpy */ +#include #define FORCE_INLINE __always_inline @@ -92,8 +93,7 @@ typedef uintptr_t uptrval; #define MB (1 << 20) #define GB (1U << 30) -#define MAXD_LOG 16 -#define MAX_DISTANCE ((1 << MAXD_LOG) - 1) +#define MAX_DISTANCE LZ4_DISTANCE_MAX #define STEPSIZE sizeof(size_t) #define ML_BITS 4 diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c index bc45594ad2a8..91936dc3d14b 100644 --- a/lib/lz4/lz4hc_compress.c +++ b/lib/lz4/lz4hc_compress.c @@ -34,7 +34,6 @@ /*-************************************ * Dependencies **************************************/ -#include #include "lz4defs.h" #include #include diff --git a/lib/maple_tree.c b/lib/maple_tree.c index d0ae808f3a14..f7153ade1be5 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -1863,11 +1863,11 @@ static inline int mab_no_null_split(struct maple_big_node *b_node, * Return: The first split location. The middle split is set in @mid_split. */ static inline int mab_calc_split(struct ma_state *mas, - struct maple_big_node *bn, unsigned char *mid_split, unsigned long min) + struct maple_big_node *bn, unsigned char *mid_split) { unsigned char b_end = bn->b_end; int split = b_end / 2; /* Assume equal split. */ - unsigned char slot_min, slot_count = mt_slots[bn->type]; + unsigned char slot_count = mt_slots[bn->type]; /* * To support gap tracking, all NULL entries are kept together and a node cannot @@ -1900,18 +1900,7 @@ static inline int mab_calc_split(struct ma_state *mas, split = b_end / 3; *mid_split = split * 2; } else { - slot_min = mt_min_slots[bn->type]; - *mid_split = 0; - /* - * Avoid having a range less than the slot count unless it - * causes one node to be deficient. - * NOTE: mt_min_slots is 1 based, b_end and split are zero. - */ - while ((split < slot_count - 1) && - ((bn->pivot[split] - min) < slot_count - 1) && - (b_end - split > slot_min)) - split++; } /* Avoid ending a node on a NULL entry */ @@ -2377,7 +2366,7 @@ static inline struct maple_enode static inline unsigned char mas_mab_to_node(struct ma_state *mas, struct maple_big_node *b_node, struct maple_enode **left, struct maple_enode **right, struct maple_enode **middle, - unsigned char *mid_split, unsigned long min) + unsigned char *mid_split) { unsigned char split = 0; unsigned char slot_count = mt_slots[b_node->type]; @@ -2390,7 +2379,7 @@ static inline unsigned char mas_mab_to_node(struct ma_state *mas, if (b_node->b_end < slot_count) { split = b_node->b_end; } else { - split = mab_calc_split(mas, b_node, mid_split, min); + split = mab_calc_split(mas, b_node, mid_split); *right = mas_new_ma_node(mas, b_node); } @@ -2877,7 +2866,7 @@ static void mas_spanning_rebalance(struct ma_state *mas, mast->bn->b_end--; mast->bn->type = mte_node_type(mast->orig_l->node); split = mas_mab_to_node(mas, mast->bn, &left, &right, &middle, - &mid_split, mast->orig_l->min); + &mid_split); mast_set_split_parents(mast, left, middle, right, split, mid_split); mast_cp_to_nodes(mast, left, middle, right, split, mid_split); @@ -3365,7 +3354,7 @@ static void mas_split(struct ma_state *mas, struct maple_big_node *b_node) if (mas_push_data(mas, height, &mast, false)) break; - split = mab_calc_split(mas, b_node, &mid_split, prev_l_mas.min); + split = mab_calc_split(mas, b_node, &mid_split); mast_split_data(&mast, mas, split); /* * Usually correct, mab_mas_cp in the above call overwrites @@ -4354,6 +4343,7 @@ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, ret = 1; } if (ret < 0 && range_lo > min) { + mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; @@ -4744,29 +4734,6 @@ again: return entry; } -/* - * mas_next_entry() - Internal function to get the next entry. - * @mas: The maple state - * @limit: The maximum range start. - * - * Set the @mas->node to the next entry and the range_start to - * the beginning value for the entry. Does not check beyond @limit. - * Sets @mas->index and @mas->last to the range, Does not update @mas->index and - * @mas->last on overflow. - * Restarts on dead nodes. - * - * Return: the next entry or %NULL. - */ -static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) -{ - if (mas->last >= limit) { - mas->status = ma_overflow; - return NULL; - } - - return mas_next_slot(mas, limit, false); -} - /* * mas_rev_awalk() - Internal function. Reverse allocation walk. Find the * highest gap address of a given size in a given node and descend. @@ -4902,15 +4869,14 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) if (gap >= size) { if (ma_is_leaf(type)) { found = true; - goto done; - } - if (mas->index <= pivot) { - mas->node = mas_slot(mas, slots, offset); - mas->min = min; - mas->max = pivot; - offset = 0; break; } + + mas->node = mas_slot(mas, slots, offset); + mas->min = min; + mas->max = pivot; + offset = 0; + break; } next_slot: min = pivot + 1; @@ -4920,9 +4886,6 @@ next_slot: } } - if (mte_is_root(mas->node)) - found = true; -done: mas->offset = offset; return found; } @@ -5026,8 +4989,8 @@ static inline void mas_awalk(struct ma_state *mas, unsigned long size) * There are 4 options: * go to child (descend) * go back to parent (ascend) - * no gap found. (return, slot == MAPLE_NODE_SLOTS) - * found the gap. (return, slot != MAPLE_NODE_SLOTS) + * no gap found. (return, error == -EBUSY) + * found the gap. (return) */ while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) @@ -5112,9 +5075,6 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, return xa_err(mas->node); offset = mas->offset; - if (unlikely(offset == MAPLE_NODE_SLOTS)) - return -EBUSY; - node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); @@ -6937,7 +6897,7 @@ retry: goto unlock; while (mas_is_active(&mas) && (mas.last < max)) { - entry = mas_next_entry(&mas, max); + entry = mas_next_slot(&mas, max, false); if (likely(entry && !xa_is_zero(entry))) break; } @@ -7596,7 +7556,7 @@ void mt_validate(struct maple_tree *mt) MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && - (mas.max != ULONG_MAX))) { + (!mte_is_root(mas.node)))) { pr_err("Invalid size %u of " PTR_FMT "\n", end, mas_mn(&mas)); } diff --git a/lib/math/Makefile b/lib/math/Makefile index 3ef11305f8d2..853f023ae537 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -9,3 +9,4 @@ obj-$(CONFIG_INT_POW_TEST) += tests/int_pow_kunit.o obj-$(CONFIG_TEST_DIV64) += test_div64.o obj-$(CONFIG_TEST_MULDIV64) += test_mul_u64_u64_div_u64.o obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o +obj-$(CONFIG_INT_SQRT_KUNIT_TEST) += tests/int_sqrt_kunit.o \ No newline at end of file diff --git a/lib/math/tests/Makefile b/lib/math/tests/Makefile index 6a169123320a..e1a79f093b2d 100644 --- a/lib/math/tests/Makefile +++ b/lib/math/tests/Makefile @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_INT_POW_TEST) += int_pow_kunit.o +obj-$(CONFIG_INT_SQRT_KUNIT_TEST) += int_sqrt_kunit.o diff --git a/lib/math/tests/int_sqrt_kunit.c b/lib/math/tests/int_sqrt_kunit.c new file mode 100644 index 000000000000..1798e1312eb7 --- /dev/null +++ b/lib/math/tests/int_sqrt_kunit.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include + +struct test_case_params { + unsigned long x; + unsigned long expected_result; + const char *name; +}; + +static const struct test_case_params params[] = { + { 0, 0, "edge case: square root of 0" }, + { 1, 1, "perfect square: square root of 1" }, + { 2, 1, "non-perfect square: square root of 2" }, + { 3, 1, "non-perfect square: square root of 3" }, + { 4, 2, "perfect square: square root of 4" }, + { 5, 2, "non-perfect square: square root of 5" }, + { 6, 2, "non-perfect square: square root of 6" }, + { 7, 2, "non-perfect square: square root of 7" }, + { 8, 2, "non-perfect square: square root of 8" }, + { 9, 3, "perfect square: square root of 9" }, + { 15, 3, "non-perfect square: square root of 15 (N-1 from 16)" }, + { 16, 4, "perfect square: square root of 16" }, + { 17, 4, "non-perfect square: square root of 17 (N+1 from 16)" }, + { 80, 8, "non-perfect square: square root of 80 (N-1 from 81)" }, + { 81, 9, "perfect square: square root of 81" }, + { 82, 9, "non-perfect square: square root of 82 (N+1 from 81)" }, + { 255, 15, "non-perfect square: square root of 255 (N-1 from 256)" }, + { 256, 16, "perfect square: square root of 256" }, + { 257, 16, "non-perfect square: square root of 257 (N+1 from 256)" }, + { 2147483648, 46340, "large input: square root of 2147483648" }, + { 4294967295, 65535, "edge case: ULONG_MAX for 32-bit" }, +}; + +static void get_desc(const struct test_case_params *tc, char *desc) +{ + strscpy(desc, tc->name, KUNIT_PARAM_DESC_SIZE); +} + +KUNIT_ARRAY_PARAM(int_sqrt, params, get_desc); + +static void int_sqrt_test(struct kunit *test) +{ + const struct test_case_params *tc = (const struct test_case_params *)test->param_value; + + KUNIT_EXPECT_EQ(test, tc->expected_result, int_sqrt(tc->x)); +} + +static struct kunit_case math_int_sqrt_test_cases[] = { + KUNIT_CASE_PARAM(int_sqrt_test, int_sqrt_gen_params), + {} +}; + +static struct kunit_suite int_sqrt_test_suite = { + .name = "math-int_sqrt", + .test_cases = math_int_sqrt_test_cases, +}; + +kunit_test_suites(&int_sqrt_test_suite); + +MODULE_DESCRIPTION("math.int_sqrt KUnit test suite"); +MODULE_LICENSE("GPL"); diff --git a/lib/packing.c b/lib/packing.c index 793942745e34..bb1643d9e64d 100644 --- a/lib/packing.c +++ b/lib/packing.c @@ -5,10 +5,37 @@ #include #include #include +#include #include #include #include +#define __pack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks) \ + ({ \ + for (size_t i = 0; i < (num_fields); i++) { \ + typeof(&(fields)[0]) field = &(fields)[i]; \ + u64 uval; \ + \ + uval = ustruct_field_to_u64(ustruct, field->offset, field->size); \ + \ + __pack(pbuf, uval, field->startbit, field->endbit, \ + pbuflen, quirks); \ + } \ + }) + +#define __unpack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks) \ + ({ \ + for (size_t i = 0; i < (num_fields); i++) { \ + typeof(&(fields)[0]) field = &fields[i]; \ + u64 uval; \ + \ + __unpack(pbuf, &uval, field->startbit, field->endbit, \ + pbuflen, quirks); \ + \ + u64_to_ustruct_field(ustruct, field->offset, field->size, uval); \ + } \ + }) + /** * calculate_box_addr - Determine physical location of byte in buffer * @box: Index of byte within buffer seen as a logical big-endian big number @@ -51,64 +78,29 @@ static size_t calculate_box_addr(size_t box, size_t len, u8 quirks) return offset_of_group + offset_in_group; } -/** - * pack - Pack u64 number into bitfield of buffer. - * - * @pbuf: Pointer to a buffer holding the packed value. - * @uval: CPU-readable unpacked value to pack. - * @startbit: The index (in logical notation, compensated for quirks) where - * the packed value starts within pbuf. Must be larger than, or - * equal to, endbit. - * @endbit: The index (in logical notation, compensated for quirks) where - * the packed value ends within pbuf. Must be smaller than, or equal - * to, startbit. - * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. - * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and - * QUIRK_MSB_ON_THE_RIGHT. - * - * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming - * correct usage, return code may be discarded. The @pbuf memory will - * be modified on success. - */ -int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen, - u8 quirks) +static void __pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, + size_t pbuflen, u8 quirks) { /* Logical byte indices corresponding to the * start and end of the field. */ - int plogical_first_u8, plogical_last_u8, box; - /* width of the field to access in the pbuf */ - u64 value_width; - - /* startbit is expected to be larger than endbit, and both are - * expected to be within the logically addressable range of the buffer. - */ - if (unlikely(startbit < endbit || startbit >= BITS_PER_BYTE * pbuflen)) - /* Invalid function call */ - return -EINVAL; - - value_width = startbit - endbit + 1; - if (unlikely(value_width > 64)) - return -ERANGE; + int plogical_first_u8 = startbit / BITS_PER_BYTE; + int plogical_last_u8 = endbit / BITS_PER_BYTE; + int value_width = startbit - endbit + 1; + int box; /* Check if "uval" fits in "value_width" bits. - * If value_width is 64, the check will fail, but any - * 64-bit uval will surely fit. + * The test only works for value_width < 64, but in the latter case, + * any 64-bit uval will surely fit. */ - if (unlikely(value_width < 64 && uval >= (1ull << value_width))) - /* Cannot store "uval" inside "value_width" bits. - * Truncating "uval" is most certainly not desirable, - * so simply erroring out is appropriate. - */ - return -ERANGE; + WARN(value_width < 64 && uval >= (1ull << value_width), + "Cannot store 0x%llx inside bits %zu-%zu - will truncate\n", + uval, startbit, endbit); /* Iterate through an idealistic view of the pbuf as an u64 with * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low * logical bit significance. "box" denotes the current logical u8. */ - plogical_first_u8 = startbit / BITS_PER_BYTE; - plogical_last_u8 = endbit / BITS_PER_BYTE; - for (box = plogical_first_u8; box >= plogical_last_u8; box--) { /* Bit indices into the currently accessed 8-bit box */ size_t box_start_bit, box_end_bit, box_addr; @@ -163,15 +155,13 @@ int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen, ((u8 *)pbuf)[box_addr] &= ~box_mask; ((u8 *)pbuf)[box_addr] |= pval; } - return 0; } -EXPORT_SYMBOL(pack); /** - * unpack - Unpack u64 number from packed buffer. + * pack - Pack u64 number into bitfield of buffer. * * @pbuf: Pointer to a buffer holding the packed value. - * @uval: Pointer to an u64 holding the unpacked value. + * @uval: CPU-readable unpacked value to pack. * @startbit: The index (in logical notation, compensated for quirks) where * the packed value starts within pbuf. Must be larger than, or * equal to, endbit. @@ -183,19 +173,12 @@ EXPORT_SYMBOL(pack); * QUIRK_MSB_ON_THE_RIGHT. * * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming - * correct usage, return code may be discarded. The @uval will be - * modified on success. + * correct usage, return code may be discarded. The @pbuf memory will + * be modified on success. */ -int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, - size_t pbuflen, u8 quirks) +int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen, + u8 quirks) { - /* Logical byte indices corresponding to the - * start and end of the field. - */ - int plogical_first_u8, plogical_last_u8, box; - /* width of the field to access in the pbuf */ - u64 value_width; - /* startbit is expected to be larger than endbit, and both are * expected to be within the logically addressable range of the buffer. */ @@ -203,10 +186,25 @@ int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, /* Invalid function call */ return -EINVAL; - value_width = startbit - endbit + 1; - if (unlikely(value_width > 64)) + if (unlikely(startbit - endbit >= 64)) return -ERANGE; + __pack(pbuf, uval, startbit, endbit, pbuflen, quirks); + + return 0; +} +EXPORT_SYMBOL(pack); + +static void __unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, + size_t pbuflen, u8 quirks) +{ + /* Logical byte indices corresponding to the + * start and end of the field. + */ + int plogical_first_u8 = startbit / BITS_PER_BYTE; + int plogical_last_u8 = endbit / BITS_PER_BYTE; + int box; + /* Initialize parameter */ *uval = 0; @@ -214,9 +212,6 @@ int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low * logical bit significance. "box" denotes the current logical u8. */ - plogical_first_u8 = startbit / BITS_PER_BYTE; - plogical_last_u8 = endbit / BITS_PER_BYTE; - for (box = plogical_first_u8; box >= plogical_last_u8; box--) { /* Bit indices into the currently accessed 8-bit box */ size_t box_start_bit, box_end_bit, box_addr; @@ -271,6 +266,46 @@ int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, *uval &= ~proj_mask; *uval |= pval; } +} + +/** + * unpack - Unpack u64 number from packed buffer. + * + * @pbuf: Pointer to a buffer holding the packed value. + * @uval: Pointer to an u64 holding the unpacked value. + * @startbit: The index (in logical notation, compensated for quirks) where + * the packed value starts within pbuf. Must be larger than, or + * equal to, endbit. + * @endbit: The index (in logical notation, compensated for quirks) where + * the packed value ends within pbuf. Must be smaller than, or equal + * to, startbit. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming + * correct usage, return code may be discarded. The @uval will be + * modified on success. + */ +int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, + size_t pbuflen, u8 quirks) +{ + /* width of the field to access in the pbuf */ + u64 value_width; + + /* startbit is expected to be larger than endbit, and both are + * expected to be within the logically addressable range of the buffer. + */ + if (startbit < endbit || startbit >= BITS_PER_BYTE * pbuflen) + /* Invalid function call */ + return -EINVAL; + + value_width = startbit - endbit + 1; + if (value_width > 64) + return -ERANGE; + + __unpack(pbuf, uval, startbit, endbit, pbuflen, quirks); + return 0; } EXPORT_SYMBOL(unpack); @@ -314,4 +349,130 @@ int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, } EXPORT_SYMBOL(packing); +static u64 ustruct_field_to_u64(const void *ustruct, size_t field_offset, + size_t field_size) +{ + switch (field_size) { + case 1: + return *((u8 *)(ustruct + field_offset)); + case 2: + return *((u16 *)(ustruct + field_offset)); + case 4: + return *((u32 *)(ustruct + field_offset)); + default: + return *((u64 *)(ustruct + field_offset)); + } +} + +static void u64_to_ustruct_field(void *ustruct, size_t field_offset, + size_t field_size, u64 uval) +{ + switch (field_size) { + case 1: + *((u8 *)(ustruct + field_offset)) = uval; + break; + case 2: + *((u16 *)(ustruct + field_offset)) = uval; + break; + case 4: + *((u32 *)(ustruct + field_offset)) = uval; + break; + default: + *((u64 *)(ustruct + field_offset)) = uval; + break; + } +} + +/** + * pack_fields_u8 - Pack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u8 definitions. + * @fields: Array of packed_field_u8 field definition. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the pack_fields() macro instead of calling this directly. + */ +void pack_fields_u8(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks) +{ + __pack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(pack_fields_u8); + +/** + * pack_fields_u16 - Pack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u16 definitions. + * @fields: Array of packed_field_u16 field definitions. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the pack_fields() macro instead of calling this directly. + */ +void pack_fields_u16(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks) +{ + __pack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(pack_fields_u16); + +/** + * unpack_fields_u8 - Unpack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u8 definitions. + * @fields: Array of packed_field_u8 field definitions. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the unpack_fields() macro instead of calling this directly. + */ +void unpack_fields_u8(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks) +{ + __unpack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(unpack_fields_u8); + +/** + * unpack_fields_u16 - Unpack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u16 definitions. + * @fields: Array of packed_field_u16 field definitions. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the unpack_fields() macro instead of calling this directly. + */ +void unpack_fields_u16(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks) +{ + __unpack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(unpack_fields_u16); + MODULE_DESCRIPTION("Generic bitfield packing and unpacking"); diff --git a/lib/packing_test.c b/lib/packing_test.c index b38ea43c03fd..ce3b83d33b04 100644 --- a/lib/packing_test.c +++ b/lib/packing_test.c @@ -396,9 +396,70 @@ static void packing_test_unpack(struct kunit *test) KUNIT_EXPECT_EQ(test, uval, params->uval); } +#define PACKED_BUF_SIZE 8 + +typedef struct __packed { u8 buf[PACKED_BUF_SIZE]; } packed_buf_t; + +struct test_data { + u32 field3; + u16 field2; + u16 field4; + u16 field6; + u8 field1; + u8 field5; +}; + +static const struct packed_field_u8 test_fields[] = { + PACKED_FIELD(63, 61, struct test_data, field1), + PACKED_FIELD(60, 52, struct test_data, field2), + PACKED_FIELD(51, 28, struct test_data, field3), + PACKED_FIELD(27, 14, struct test_data, field4), + PACKED_FIELD(13, 9, struct test_data, field5), + PACKED_FIELD(8, 0, struct test_data, field6), +}; + +static void packing_test_pack_fields(struct kunit *test) +{ + const struct test_data data = { + .field1 = 0x2, + .field2 = 0x100, + .field3 = 0xF00050, + .field4 = 0x7D3, + .field5 = 0x9, + .field6 = 0x10B, + }; + packed_buf_t expect = { + .buf = { 0x50, 0x0F, 0x00, 0x05, 0x01, 0xF4, 0xD3, 0x0B }, + }; + packed_buf_t buf = {}; + + pack_fields(&buf, sizeof(buf), &data, test_fields, 0); + + KUNIT_EXPECT_MEMEQ(test, &expect, &buf, sizeof(buf)); +} + +static void packing_test_unpack_fields(struct kunit *test) +{ + const packed_buf_t buf = { + .buf = { 0x17, 0x28, 0x10, 0x19, 0x3D, 0xA9, 0x07, 0x9C }, + }; + struct test_data data = {}; + + unpack_fields(&buf, sizeof(buf), &data, test_fields, 0); + + KUNIT_EXPECT_EQ(test, 0, data.field1); + KUNIT_EXPECT_EQ(test, 0x172, data.field2); + KUNIT_EXPECT_EQ(test, 0x810193, data.field3); + KUNIT_EXPECT_EQ(test, 0x36A4, data.field4); + KUNIT_EXPECT_EQ(test, 0x3, data.field5); + KUNIT_EXPECT_EQ(test, 0x19C, data.field6); +} + static struct kunit_case packing_test_cases[] = { KUNIT_CASE_PARAM(packing_test_pack, packing_gen_params), KUNIT_CASE_PARAM(packing_test_unpack, packing_gen_params), + KUNIT_CASE(packing_test_pack_fields), + KUNIT_CASE(packing_test_unpack_fields), {}, }; diff --git a/lib/parser.c b/lib/parser.c index f4eafb9d74e6..73e8f8e5be73 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -275,8 +275,9 @@ EXPORT_SYMBOL(match_hex); * * Description: Parse the string @str to check if matches wildcard * pattern @pattern. The pattern may contain two types of wildcards: - * '*' - matches zero or more characters - * '?' - matches one character + * + * * '*' - matches zero or more characters + * * '?' - matches one character * * Return: If the @str matches the @pattern, return true, else return false. */ diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c index 6e1581b9a616..6264e2013f25 100644 --- a/lib/pldmfw/pldmfw.c +++ b/lib/pldmfw/pldmfw.c @@ -481,9 +481,17 @@ static int pldm_parse_components(struct pldmfw_priv *data) component->component_data = data->fw->data + offset; component->component_size = size; + if (data->context->mode == PLDMFW_UPDATE_MODE_SINGLE_COMPONENT && + data->context->component_identifier != component->identifier) + continue; + list_add_tail(&component->entry, &data->components); } + if (data->context->mode == PLDMFW_UPDATE_MODE_SINGLE_COMPONENT && + list_empty(&data->components)) + return -ENOENT; + header_crc_ptr = data->fw->data + data->offset; err = pldm_move_fw_offset(data, sizeof(data->header_crc)); diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 6c902639728b..3e555d012ed6 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -584,10 +584,6 @@ static struct bucket_table *rhashtable_insert_one( */ rht_assign_locked(bkt, obj); - atomic_inc(&ht->nelems); - if (rht_grow_above_75(ht, tbl)) - schedule_work(&ht->run_work); - return NULL; } @@ -615,15 +611,23 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); data = ERR_PTR(-EAGAIN); } else { + bool inserted; + flags = rht_lock(tbl, bkt); data = rhashtable_lookup_one(ht, bkt, tbl, hash, key, obj); new_tbl = rhashtable_insert_one(ht, bkt, tbl, hash, obj, data); + inserted = data && !new_tbl; + if (inserted) + atomic_inc(&ht->nelems); if (PTR_ERR(new_tbl) != -EEXIST) data = ERR_CAST(new_tbl); rht_unlock(tbl, bkt, flags); + + if (inserted && rht_grow_above_75(ht, tbl)) + schedule_work(&ht->run_work); } } while (!IS_ERR_OR_NULL(new_tbl)); @@ -665,7 +669,7 @@ EXPORT_SYMBOL_GPL(rhashtable_insert_slow); * structure outside the hash table. * * This function may be called from any process context, including - * non-preemptable context, but cannot be called from softirq or + * non-preemptible context, but cannot be called from softirq or * hardirq context. * * You must call rhashtable_walk_exit after this function returns. diff --git a/lib/sort.c b/lib/sort.c index 048b7a6ef967..8e73dc55476b 100644 --- a/lib/sort.c +++ b/lib/sort.c @@ -200,6 +200,13 @@ static size_t parent(size_t i, unsigned int lsbit, size_t size) * copy (e.g. fix up pointers or auxiliary data), but the built-in swap * avoids a slow retpoline and so is significantly faster. * + * The comparison function must adhere to specific mathematical + * properties to ensure correct and stable sorting: + * - Antisymmetry: cmp_func(a, b) must return the opposite sign of + * cmp_func(b, a). + * - Transitivity: if cmp_func(a, b) <= 0 and cmp_func(b, c) <= 0, then + * cmp_func(a, c) <= 0. + * * Sorting time is O(n log n) both on average and worst-case. While * quicksort is slightly faster on average, it suffers from exploitable * O(n*n) worst-case behavior and extra memory requirements that make diff --git a/lib/stackinit_kunit.c b/lib/stackinit_kunit.c index c40818ec9c18..fbe910c9c825 100644 --- a/lib/stackinit_kunit.c +++ b/lib/stackinit_kunit.c @@ -47,10 +47,12 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define DO_NOTHING_TYPE_SCALAR(var_type) var_type #define DO_NOTHING_TYPE_STRING(var_type) void #define DO_NOTHING_TYPE_STRUCT(var_type) void +#define DO_NOTHING_TYPE_UNION(var_type) void #define DO_NOTHING_RETURN_SCALAR(ptr) *(ptr) #define DO_NOTHING_RETURN_STRING(ptr) /**/ #define DO_NOTHING_RETURN_STRUCT(ptr) /**/ +#define DO_NOTHING_RETURN_UNION(ptr) /**/ #define DO_NOTHING_CALL_SCALAR(var, name) \ (var) = do_nothing_ ## name(&(var)) @@ -58,10 +60,13 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, do_nothing_ ## name(var) #define DO_NOTHING_CALL_STRUCT(var, name) \ do_nothing_ ## name(&(var)) +#define DO_NOTHING_CALL_UNION(var, name) \ + do_nothing_ ## name(&(var)) #define FETCH_ARG_SCALAR(var) &var #define FETCH_ARG_STRING(var) var #define FETCH_ARG_STRUCT(var) &var +#define FETCH_ARG_UNION(var) &var /* * On m68k, if the leaf function test variable is longer than 8 bytes, @@ -77,6 +82,7 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define INIT_CLONE_SCALAR /**/ #define INIT_CLONE_STRING [FILL_SIZE_STRING] #define INIT_CLONE_STRUCT /**/ +#define INIT_CLONE_UNION /**/ #define ZERO_CLONE_SCALAR(zero) memset(&(zero), 0x00, sizeof(zero)) #define ZERO_CLONE_STRING(zero) memset(&(zero), 0x00, sizeof(zero)) @@ -92,6 +98,7 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, zero.three = 0; \ zero.four = 0; \ } while (0) +#define ZERO_CLONE_UNION(zero) ZERO_CLONE_STRUCT(zero) #define INIT_SCALAR_none(var_type) /**/ #define INIT_SCALAR_zero(var_type) = 0 @@ -101,6 +108,7 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define INIT_STRUCT_none(var_type) /**/ #define INIT_STRUCT_zero(var_type) = { } +#define INIT_STRUCT_old_zero(var_type) = { 0 } #define __static_partial { .two = 0, } @@ -146,6 +154,34 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define INIT_STRUCT_assigned_copy(var_type) \ ; var = *(arg) +/* Union initialization is the same as structs. */ +#define INIT_UNION_none(var_type) INIT_STRUCT_none(var_type) +#define INIT_UNION_zero(var_type) INIT_STRUCT_zero(var_type) +#define INIT_UNION_old_zero(var_type) INIT_STRUCT_old_zero(var_type) + +#define INIT_UNION_static_partial(var_type) \ + INIT_STRUCT_static_partial(var_type) +#define INIT_UNION_static_all(var_type) \ + INIT_STRUCT_static_all(var_type) +#define INIT_UNION_dynamic_partial(var_type) \ + INIT_STRUCT_dynamic_partial(var_type) +#define INIT_UNION_dynamic_all(var_type) \ + INIT_STRUCT_dynamic_all(var_type) +#define INIT_UNION_runtime_partial(var_type) \ + INIT_STRUCT_runtime_partial(var_type) +#define INIT_UNION_runtime_all(var_type) \ + INIT_STRUCT_runtime_all(var_type) +#define INIT_UNION_assigned_static_partial(var_type) \ + INIT_STRUCT_assigned_static_partial(var_type) +#define INIT_UNION_assigned_static_all(var_type) \ + INIT_STRUCT_assigned_static_all(var_type) +#define INIT_UNION_assigned_dynamic_partial(var_type) \ + INIT_STRUCT_assigned_dynamic_partial(var_type) +#define INIT_UNION_assigned_dynamic_all(var_type) \ + INIT_STRUCT_assigned_dynamic_all(var_type) +#define INIT_UNION_assigned_copy(var_type) \ + INIT_STRUCT_assigned_copy(var_type) + /* * @name: unique string name for the test * @var_type: type to be tested for zeroing initialization @@ -294,6 +330,33 @@ struct test_user { unsigned long four; }; +/* No padding: all members are the same size. */ +union test_same_sizes { + unsigned long one; + unsigned long two; + unsigned long three; + unsigned long four; +}; + +/* Mismatched sizes, with one and two being small */ +union test_small_start { + char one:1; + char two; + short three; + unsigned long four; + struct big_struct { + unsigned long array[8]; + } big; +}; + +/* Mismatched sizes, with one and two being small */ +union test_small_end { + short one; + unsigned long two; + char three:1; + char four; +}; + #define ALWAYS_PASS WANT_SUCCESS #define ALWAYS_FAIL XFAIL @@ -332,6 +395,11 @@ struct test_user { struct test_ ## name, STRUCT, init, \ xfail) +#define DEFINE_UNION_TEST(name, init, xfail) \ + DEFINE_TEST(name ## _ ## init, \ + union test_ ## name, STRUCT, init, \ + xfail) + #define DEFINE_STRUCT_TESTS(init, xfail) \ DEFINE_STRUCT_TEST(small_hole, init, xfail); \ DEFINE_STRUCT_TEST(big_hole, init, xfail); \ @@ -343,9 +411,22 @@ struct test_user { xfail); \ DEFINE_STRUCT_TESTS(base ## _ ## all, xfail) +#define DEFINE_UNION_INITIALIZER_TESTS(base, xfail) \ + DEFINE_UNION_TESTS(base ## _ ## partial, \ + xfail); \ + DEFINE_UNION_TESTS(base ## _ ## all, xfail) + +#define DEFINE_UNION_TESTS(init, xfail) \ + DEFINE_UNION_TEST(same_sizes, init, xfail); \ + DEFINE_UNION_TEST(small_start, init, xfail); \ + DEFINE_UNION_TEST(small_end, init, xfail); + /* These should be fully initialized all the time! */ DEFINE_SCALAR_TESTS(zero, ALWAYS_PASS); DEFINE_STRUCT_TESTS(zero, ALWAYS_PASS); +DEFINE_STRUCT_TESTS(old_zero, ALWAYS_PASS); +DEFINE_UNION_TESTS(zero, ALWAYS_PASS); +DEFINE_UNION_TESTS(old_zero, ALWAYS_PASS); /* Struct initializers: padding may be left uninitialized. */ DEFINE_STRUCT_INITIALIZER_TESTS(static, STRONG_PASS); DEFINE_STRUCT_INITIALIZER_TESTS(dynamic, STRONG_PASS); @@ -353,6 +434,12 @@ DEFINE_STRUCT_INITIALIZER_TESTS(runtime, STRONG_PASS); DEFINE_STRUCT_INITIALIZER_TESTS(assigned_static, STRONG_PASS); DEFINE_STRUCT_INITIALIZER_TESTS(assigned_dynamic, STRONG_PASS); DEFINE_STRUCT_TESTS(assigned_copy, ALWAYS_FAIL); +DEFINE_UNION_INITIALIZER_TESTS(static, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(dynamic, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(runtime, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(assigned_static, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(assigned_dynamic, STRONG_PASS); +DEFINE_UNION_TESTS(assigned_copy, ALWAYS_FAIL); /* No initialization without compiler instrumentation. */ DEFINE_SCALAR_TESTS(none, STRONG_PASS); DEFINE_STRUCT_TESTS(none, BYREF_PASS); @@ -436,13 +523,23 @@ DEFINE_TEST_DRIVER(switch_2_none, uint64_t, SCALAR, ALWAYS_FAIL); KUNIT_CASE(test_trailing_hole_ ## init),\ KUNIT_CASE(test_packed_ ## init) \ +#define KUNIT_test_unions(init) \ + KUNIT_CASE(test_same_sizes_ ## init), \ + KUNIT_CASE(test_small_start_ ## init), \ + KUNIT_CASE(test_small_end_ ## init) \ + static struct kunit_case stackinit_test_cases[] = { /* These are explicitly initialized and should always pass. */ KUNIT_test_scalars(zero), KUNIT_test_structs(zero), + KUNIT_test_structs(old_zero), + KUNIT_test_unions(zero), + KUNIT_test_unions(old_zero), /* Padding here appears to be accidentally always initialized? */ KUNIT_test_structs(dynamic_partial), KUNIT_test_structs(assigned_dynamic_partial), + KUNIT_test_unions(dynamic_partial), + KUNIT_test_unions(assigned_dynamic_partial), /* Padding initialization depends on compiler behaviors. */ KUNIT_test_structs(static_partial), KUNIT_test_structs(static_all), @@ -452,8 +549,17 @@ static struct kunit_case stackinit_test_cases[] = { KUNIT_test_structs(assigned_static_partial), KUNIT_test_structs(assigned_static_all), KUNIT_test_structs(assigned_dynamic_all), + KUNIT_test_unions(static_partial), + KUNIT_test_unions(static_all), + KUNIT_test_unions(dynamic_all), + KUNIT_test_unions(runtime_partial), + KUNIT_test_unions(runtime_all), + KUNIT_test_unions(assigned_static_partial), + KUNIT_test_unions(assigned_static_all), + KUNIT_test_unions(assigned_dynamic_all), /* Everything fails this since it effectively performs a memcpy(). */ KUNIT_test_structs(assigned_copy), + KUNIT_test_unions(assigned_copy), /* STRUCTLEAK_BYREF_ALL should cover everything from here down. */ KUNIT_test_scalars(none), KUNIT_CASE(test_switch_1_none), diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 2eed1ad958e9..af0041df2b72 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -478,7 +478,7 @@ static int __bpf_ld_imm64(struct bpf_insn insns[2], u8 reg, s64 imm64) * to overflow the field size of the native instruction, triggering * a branch conversion mechanism in some JITs. */ -static int __bpf_fill_max_jmp(struct bpf_test *self, int jmp, int imm) +static int __bpf_fill_max_jmp(struct bpf_test *self, int jmp, int imm, bool alu32) { struct bpf_insn *insns; int len = S16_MAX + 5; @@ -501,7 +501,7 @@ static int __bpf_fill_max_jmp(struct bpf_test *self, int jmp, int imm) }; int op = ops[(i >> 1) % ARRAY_SIZE(ops)]; - if (i & 1) + if ((i & 1) || alu32) insns[i++] = BPF_ALU32_REG(op, R0, R1); else insns[i++] = BPF_ALU64_REG(op, R0, R1); @@ -516,27 +516,47 @@ static int __bpf_fill_max_jmp(struct bpf_test *self, int jmp, int imm) } /* Branch taken by runtime decision */ +static int bpf_fill_max_jmp_taken_32(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JEQ, 1, true); +} + static int bpf_fill_max_jmp_taken(struct bpf_test *self) { - return __bpf_fill_max_jmp(self, BPF_JEQ, 1); + return __bpf_fill_max_jmp(self, BPF_JEQ, 1, false); } /* Branch not taken by runtime decision */ +static int bpf_fill_max_jmp_not_taken_32(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JEQ, 0, true); +} + static int bpf_fill_max_jmp_not_taken(struct bpf_test *self) { - return __bpf_fill_max_jmp(self, BPF_JEQ, 0); + return __bpf_fill_max_jmp(self, BPF_JEQ, 0, false); } /* Branch always taken, known at JIT time */ +static int bpf_fill_max_jmp_always_taken_32(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JGE, 0, true); +} + static int bpf_fill_max_jmp_always_taken(struct bpf_test *self) { - return __bpf_fill_max_jmp(self, BPF_JGE, 0); + return __bpf_fill_max_jmp(self, BPF_JGE, 0, false); } /* Branch never taken, known at JIT time */ +static int bpf_fill_max_jmp_never_taken_32(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JLT, 0, true); +} + static int bpf_fill_max_jmp_never_taken(struct bpf_test *self) { - return __bpf_fill_max_jmp(self, BPF_JLT, 0); + return __bpf_fill_max_jmp(self, BPF_JLT, 0, false); } /* ALU result computation used in tests */ @@ -14233,6 +14253,38 @@ static struct bpf_test tests[] = { { { 0, 0 } }, }, /* Conditional branch conversions */ + { + "Long conditional jump: taken at runtime (32 bits)", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_max_jmp_taken_32, + }, + { + "Long conditional jump: not taken at runtime (32 bits)", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 2 } }, + .fill_helper = bpf_fill_max_jmp_not_taken_32, + }, + { + "Long conditional jump: always taken, known at JIT time (32 bits)", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_max_jmp_always_taken_32, + }, + { + "Long conditional jump: never taken, known at JIT time (32 bits)", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 2 } }, + .fill_helper = bpf_fill_max_jmp_never_taken_32, + }, { "Long conditional jump: taken at runtime", { }, diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index 24de0e5ff859..cf92111b5c79 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -17,10 +17,8 @@ static u32 rand1, entry_val, exit_val; /* Use indirect calls to avoid inlining the target functions */ static u32 (*target)(u32 value); static u32 (*target2)(u32 value); -static u32 (*target_nest)(u32 value, u32 (*nest)(u32)); static unsigned long target_ip; static unsigned long target2_ip; -static unsigned long target_nest_ip; static int entry_return_value; static noinline u32 fprobe_selftest_target(u32 value) @@ -33,14 +31,9 @@ static noinline u32 fprobe_selftest_target2(u32 value) return (value / div_factor) + 1; } -static noinline u32 fprobe_selftest_nest_target(u32 value, u32 (*nest)(u32)) -{ - return nest(value + 2); -} - static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { KUNIT_EXPECT_FALSE(current_test, preemptible()); /* This can be called on the fprobe_selftest_target and the fprobe_selftest_target2 */ @@ -59,9 +52,9 @@ static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip, static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { - unsigned long ret = regs_return_value(regs); + unsigned long ret = ftrace_regs_get_return_value(fregs); KUNIT_EXPECT_FALSE(current_test, preemptible()); if (ip != target_ip) { @@ -79,22 +72,6 @@ static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, KUNIT_EXPECT_NULL(current_test, data); } -static notrace int nest_entry_handler(struct fprobe *fp, unsigned long ip, - unsigned long ret_ip, - struct pt_regs *regs, void *data) -{ - KUNIT_EXPECT_FALSE(current_test, preemptible()); - return 0; -} - -static notrace void nest_exit_handler(struct fprobe *fp, unsigned long ip, - unsigned long ret_ip, - struct pt_regs *regs, void *data) -{ - KUNIT_EXPECT_FALSE(current_test, preemptible()); - KUNIT_EXPECT_EQ(current_test, ip, target_nest_ip); -} - /* Test entry only (no rethook) */ static void test_fprobe_entry(struct kunit *test) { @@ -191,25 +168,6 @@ static void test_fprobe_data(struct kunit *test) KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); } -/* Test nr_maxactive */ -static void test_fprobe_nest(struct kunit *test) -{ - static const char *syms[] = {"fprobe_selftest_target", "fprobe_selftest_nest_target"}; - struct fprobe fp = { - .entry_handler = nest_entry_handler, - .exit_handler = nest_exit_handler, - .nr_maxactive = 1, - }; - - current_test = test; - KUNIT_EXPECT_EQ(test, 0, register_fprobe_syms(&fp, syms, 2)); - - target_nest(rand1, target); - KUNIT_EXPECT_EQ(test, 1, fp.nmissed); - - KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); -} - static void test_fprobe_skip(struct kunit *test) { struct fprobe fp = { @@ -247,10 +205,8 @@ static int fprobe_test_init(struct kunit *test) rand1 = get_random_u32_above(div_factor); target = fprobe_selftest_target; target2 = fprobe_selftest_target2; - target_nest = fprobe_selftest_nest_target; target_ip = get_ftrace_location(target); target2_ip = get_ftrace_location(target2); - target_nest_ip = get_ftrace_location(target_nest); return 0; } @@ -260,7 +216,6 @@ static struct kunit_case fprobe_testcases[] = { KUNIT_CASE(test_fprobe), KUNIT_CASE(test_fprobe_syms), KUNIT_CASE(test_fprobe_data), - KUNIT_CASE(test_fprobe_nest), KUNIT_CASE(test_fprobe_skip), {} }; diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 704cb1093ae8..13e2a10d7554 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -1563,6 +1563,30 @@ static noinline void __init check_root_expand(struct maple_tree *mt) mas_unlock(&mas); } +static noinline void __init check_deficient_node(struct maple_tree *mt) +{ + MA_STATE(mas, mt, 0, 0); + int count; + + mas_lock(&mas); + for (count = 0; count < 10; count++) { + mas_set(&mas, count); + mas_store_gfp(&mas, xa_mk_value(count), GFP_KERNEL); + } + + for (count = 20; count < 39; count++) { + mas_set(&mas, count); + mas_store_gfp(&mas, xa_mk_value(count), GFP_KERNEL); + } + + for (count = 10; count < 12; count++) { + mas_set(&mas, count); + mas_store_gfp(&mas, xa_mk_value(count), GFP_KERNEL); + } + mas_unlock(&mas); + mt_validate(mt); +} + static noinline void __init check_gap_combining(struct maple_tree *mt) { struct maple_enode *mn1, *mn2; @@ -3714,6 +3738,34 @@ static noinline void __init alloc_cyclic_testing(struct maple_tree *mt) } mtree_destroy(mt); + + /* + * Issue with reverse search was discovered + * https://lore.kernel.org/all/20241216060600.287B4C4CED0@smtp.kernel.org/ + * Exhausting the allocation area and forcing the search to wrap needs a + * mas_reset() in mas_alloc_cyclic(). + */ + next = 0; + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + for (int i = 0; i < 1023; i++) { + mtree_alloc_cyclic(mt, &location, mt, 2, 1024, &next, GFP_KERNEL); + MT_BUG_ON(mt, i != location - 2); + MT_BUG_ON(mt, i != next - 3); + MT_BUG_ON(mt, mtree_load(mt, location) != mt); + } + mtree_erase(mt, 123); + MT_BUG_ON(mt, mtree_load(mt, 123) != NULL); + mtree_alloc_cyclic(mt, &location, mt, 2, 1024, &next, GFP_KERNEL); + MT_BUG_ON(mt, 123 != location); + MT_BUG_ON(mt, 124 != next); + MT_BUG_ON(mt, mtree_load(mt, location) != mt); + mtree_erase(mt, 100); + mtree_alloc_cyclic(mt, &location, mt, 2, 1024, &next, GFP_KERNEL); + MT_BUG_ON(mt, 100 != location); + MT_BUG_ON(mt, 101 != next); + MT_BUG_ON(mt, mtree_load(mt, location) != mt); + mtree_destroy(mt); + /* Overflow test */ next = ULONG_MAX - 1; ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL); @@ -3796,6 +3848,10 @@ static int __init maple_tree_seed(void) goto skip; #endif + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); + check_deficient_node(&tree); + mtree_destroy(&tree); + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); check_store_null(&tree); mtree_destroy(&tree); diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c index e6fbb798558b..a9c4a74d3898 100644 --- a/lib/test_min_heap.c +++ b/lib/test_min_heap.c @@ -32,7 +32,7 @@ static __init int pop_verify_heap(bool min_heap, int last; last = values[0]; - min_heap_pop(heap, funcs, NULL); + min_heap_pop_inline(heap, funcs, NULL); while (heap->nr > 0) { if (min_heap) { if (last > values[0]) { @@ -48,7 +48,7 @@ static __init int pop_verify_heap(bool min_heap, } } last = values[0]; - min_heap_pop(heap, funcs, NULL); + min_heap_pop_inline(heap, funcs, NULL); } return err; } @@ -69,7 +69,7 @@ static __init int test_heapify_all(bool min_heap) int i, err; /* Test with known set of values. */ - min_heapify_all(&heap, &funcs, NULL); + min_heapify_all_inline(&heap, &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); @@ -78,7 +78,7 @@ static __init int test_heapify_all(bool min_heap) for (i = 0; i < heap.nr; i++) values[i] = get_random_u32(); - min_heapify_all(&heap, &funcs, NULL); + min_heapify_all_inline(&heap, &funcs, NULL); err += pop_verify_heap(min_heap, &heap, &funcs); return err; @@ -102,14 +102,14 @@ static __init int test_heap_push(bool min_heap) /* Test with known set of values copied from data. */ for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_push(&heap, &data[i], &funcs, NULL); + min_heap_push_inline(&heap, &data[i], &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); /* Test with randomly generated values. */ while (heap.nr < heap.size) { temp = get_random_u32(); - min_heap_push(&heap, &temp, &funcs, NULL); + min_heap_push_inline(&heap, &temp, &funcs, NULL); } err += pop_verify_heap(min_heap, &heap, &funcs); @@ -135,22 +135,22 @@ static __init int test_heap_pop_push(bool min_heap) /* Fill values with data to pop and replace. */ temp = min_heap ? 0x80000000 : 0x7FFFFFFF; for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_push(&heap, &temp, &funcs, NULL); + min_heap_push_inline(&heap, &temp, &funcs, NULL); /* Test with known set of values copied from data. */ for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_pop_push(&heap, &data[i], &funcs, NULL); + min_heap_pop_push_inline(&heap, &data[i], &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); heap.nr = 0; for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_push(&heap, &temp, &funcs, NULL); + min_heap_push_inline(&heap, &temp, &funcs, NULL); /* Test with randomly generated values. */ for (i = 0; i < ARRAY_SIZE(data); i++) { temp = get_random_u32(); - min_heap_pop_push(&heap, &temp, &funcs, NULL); + min_heap_pop_push_inline(&heap, &temp, &funcs, NULL); } err += pop_verify_heap(min_heap, &heap, &funcs); @@ -163,7 +163,7 @@ static __init int test_heap_del(bool min_heap) -3, -1, -2, -4, 0x8000000, 0x7FFFFFF }; struct min_heap_test heap; - min_heap_init(&heap, values, ARRAY_SIZE(values)); + min_heap_init_inline(&heap, values, ARRAY_SIZE(values)); heap.nr = ARRAY_SIZE(values); struct min_heap_callbacks funcs = { .less = min_heap ? less_than : greater_than, @@ -172,9 +172,9 @@ static __init int test_heap_del(bool min_heap) int i, err; /* Test with known set of values. */ - min_heapify_all(&heap, &funcs, NULL); + min_heapify_all_inline(&heap, &funcs, NULL); for (i = 0; i < ARRAY_SIZE(values) / 2; i++) - min_heap_del(&heap, get_random_u32() % heap.nr, &funcs, NULL); + min_heap_del_inline(&heap, get_random_u32() % heap.nr, &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); @@ -182,10 +182,10 @@ static __init int test_heap_del(bool min_heap) heap.nr = ARRAY_SIZE(values); for (i = 0; i < heap.nr; i++) values[i] = get_random_u32(); - min_heapify_all(&heap, &funcs, NULL); + min_heapify_all_inline(&heap, &funcs, NULL); for (i = 0; i < ARRAY_SIZE(values) / 2; i++) - min_heap_del(&heap, get_random_u32() % heap.nr, &funcs, NULL); + min_heap_del_inline(&heap, get_random_u32() % heap.nr, &funcs, NULL); err += pop_verify_heap(min_heap, &heap, &funcs); return err; diff --git a/lib/test_objpool.c b/lib/test_objpool.c index 5a3f6961a70f..896c0131c9a8 100644 --- a/lib/test_objpool.c +++ b/lib/test_objpool.c @@ -371,14 +371,10 @@ static int ot_start_sync(struct ot_test *test) if (!cpu_online(cpu)) continue; - work = kthread_create_on_node(ot_thread_worker, item, - cpu_to_node(cpu), "ot_worker_%d", cpu); - if (IS_ERR(work)) { + work = kthread_run_on_cpu(ot_thread_worker, item, + cpu, "ot_worker_%d"); + if (IS_ERR(work)) pr_err("failed to create thread for cpu %d\n", cpu); - } else { - kthread_bind(work, cpu); - wake_up_process(work); - } } /* wait a while to make sure all threads waiting at start line */ @@ -562,14 +558,9 @@ static int ot_start_async(struct ot_test *test) if (!cpu_online(cpu)) continue; - work = kthread_create_on_node(ot_thread_worker, item, - cpu_to_node(cpu), "ot_worker_%d", cpu); - if (IS_ERR(work)) { + work = kthread_run_on_cpu(ot_thread_worker, item, cpu, "ot_worker_%d"); + if (IS_ERR(work)) pr_err("failed to create thread for cpu %d\n", cpu); - } else { - kthread_bind(work, cpu); - wake_up_process(work); - } } /* wait a while to make sure all threads waiting at start line */ diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c index b6696fa1d426..4249e0cc8aaf 100644 --- a/lib/test_sysctl.c +++ b/lib/test_sysctl.c @@ -71,7 +71,7 @@ static struct test_sysctl_data test_data = { }; /* These are all under /proc/sys/debug/test_sysctl/ */ -static struct ctl_table test_table[] = { +static const struct ctl_table test_table[] = { { .procname = "int_0001", .data = &test_data.int_0001, @@ -177,7 +177,7 @@ static int test_sysctl_setup_node_tests(void) } /* Used to test that unregister actually removes the directory */ -static struct ctl_table test_table_unregister[] = { +static const struct ctl_table test_table_unregister[] = { { .procname = "unregister_error", .data = &test_data.int_0001, @@ -220,7 +220,7 @@ static int test_sysctl_run_register_mount_point(void) return 0; } -static struct ctl_table test_table_empty[] = { }; +static const struct ctl_table test_table_empty[] = { }; static int test_sysctl_run_register_empty(void) { diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index 4ddf769861ff..f585949ff696 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -373,7 +373,7 @@ vm_map_ram_test(void) if (!pages) return -1; - nr_allocated = alloc_pages_bulk_array(GFP_KERNEL, map_nr_pages, pages); + nr_allocated = alloc_pages_bulk(GFP_KERNEL, map_nr_pages, pages); if (nr_allocated != map_nr_pages) goto cleanup; diff --git a/lib/test_xarray.c b/lib/test_xarray.c index d5c5cbba33ed..6932a26f4927 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1448,6 +1448,41 @@ static noinline void check_pause(struct xarray *xa) XA_BUG_ON(xa, count != order_limit); xa_destroy(xa); + + index = 0; + for (order = XA_CHUNK_SHIFT; order > 0; order--) { + XA_BUG_ON(xa, xa_store_order(xa, index, order, + xa_mk_index(index), GFP_KERNEL)); + index += 1UL << order; + } + + index = 0; + count = 0; + xas_set(&xas, 0); + rcu_read_lock(); + xas_for_each(&xas, entry, ULONG_MAX) { + XA_BUG_ON(xa, entry != xa_mk_index(index)); + index += 1UL << (XA_CHUNK_SHIFT - count); + count++; + } + rcu_read_unlock(); + XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + + index = 0; + count = 0; + xas_set(&xas, XA_CHUNK_SIZE / 2 + 1); + rcu_read_lock(); + xas_for_each(&xas, entry, ULONG_MAX) { + XA_BUG_ON(xa, entry != xa_mk_index(index)); + index += 1UL << (XA_CHUNK_SHIFT - count); + count++; + xas_pause(&xas); + } + rcu_read_unlock(); + XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + + xa_destroy(xa); + } static noinline void check_move_tiny(struct xarray *xa) diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 9d3dac38a3f4..56fe96319292 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -160,8 +160,7 @@ long long simple_strtoll(const char *cp, char **endp, unsigned int base) } EXPORT_SYMBOL(simple_strtoll); -static noinline_for_stack -int skip_atoi(const char **s) +static inline int skip_atoi(const char **s) { int i = 0; @@ -407,7 +406,7 @@ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) return len + width; } -#define SIGN 1 /* unsigned/signed, must be 1 */ +#define SIGN 1 /* unsigned/signed */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ @@ -415,38 +414,26 @@ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ -static_assert(SIGN == 1); static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ('a' ^ 'A')); -enum format_type { - FORMAT_TYPE_NONE, /* Just a string part */ - FORMAT_TYPE_WIDTH, - FORMAT_TYPE_PRECISION, - FORMAT_TYPE_CHAR, - FORMAT_TYPE_STR, - FORMAT_TYPE_PTR, - FORMAT_TYPE_PERCENT_CHAR, - FORMAT_TYPE_INVALID, - FORMAT_TYPE_LONG_LONG, - FORMAT_TYPE_ULONG, - FORMAT_TYPE_LONG, - FORMAT_TYPE_UBYTE, - FORMAT_TYPE_BYTE, - FORMAT_TYPE_USHORT, - FORMAT_TYPE_SHORT, - FORMAT_TYPE_UINT, - FORMAT_TYPE_INT, - FORMAT_TYPE_SIZE_T, - FORMAT_TYPE_PTRDIFF +enum format_state { + FORMAT_STATE_NONE, /* Just a string part */ + FORMAT_STATE_NUM, + FORMAT_STATE_WIDTH, + FORMAT_STATE_PRECISION, + FORMAT_STATE_CHAR, + FORMAT_STATE_STR, + FORMAT_STATE_PTR, + FORMAT_STATE_PERCENT_CHAR, + FORMAT_STATE_INVALID, }; struct printf_spec { - unsigned int type:8; /* format_type enum */ - signed int field_width:24; /* width of output field */ - unsigned int flags:8; /* flags to number() */ - unsigned int base:8; /* number base, 8, 10 or 16 only */ - signed int precision:16; /* # of digits/chars */ + unsigned char flags; /* flags to number() */ + unsigned char base; /* number base, 8, 10 or 16 only */ + short precision; /* # of digits/chars */ + int field_width; /* width of output field */ } __packed; static_assert(sizeof(struct printf_spec) == 8); @@ -579,7 +566,6 @@ char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; - spec.type = FORMAT_TYPE_PTR; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; @@ -2530,6 +2516,26 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, } } +struct fmt { + const char *str; + unsigned char state; // enum format_state + unsigned char size; // size of numbers +}; + +#define SPEC_CHAR(x, flag) [(x)-32] = flag +static unsigned char spec_flag(unsigned char c) +{ + static const unsigned char spec_flag_array[] = { + SPEC_CHAR(' ', SPACE), + SPEC_CHAR('#', SPECIAL), + SPEC_CHAR('+', PLUS), + SPEC_CHAR('-', LEFT), + SPEC_CHAR('0', ZEROPAD), + }; + c -= 32; + return (c < sizeof(spec_flag_array)) ? spec_flag_array[c] : 0; +} + /* * Helper function to decode printf style format. * Each call decode a token from the format and return the @@ -2552,181 +2558,141 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack -int format_decode(const char *fmt, struct printf_spec *spec) +struct fmt format_decode(struct fmt fmt, struct printf_spec *spec) { - const char *start = fmt; - char qualifier; + const char *start = fmt.str; + char flag; /* we finished early by reading the field width */ - if (spec->type == FORMAT_TYPE_WIDTH) { + if (unlikely(fmt.state == FORMAT_STATE_WIDTH)) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } - spec->type = FORMAT_TYPE_NONE; + fmt.state = FORMAT_STATE_NONE; goto precision; } /* we finished early by reading the precision */ - if (spec->type == FORMAT_TYPE_PRECISION) { + if (unlikely(fmt.state == FORMAT_STATE_PRECISION)) { if (spec->precision < 0) spec->precision = 0; - spec->type = FORMAT_TYPE_NONE; + fmt.state = FORMAT_STATE_NONE; goto qualifier; } /* By default */ - spec->type = FORMAT_TYPE_NONE; + fmt.state = FORMAT_STATE_NONE; - for (; *fmt ; ++fmt) { - if (*fmt == '%') + for (; *fmt.str ; fmt.str++) { + if (*fmt.str == '%') break; } /* Return the current non-format string */ - if (fmt != start || !*fmt) - return fmt - start; + if (fmt.str != start || !*fmt.str) + return fmt; - /* Process flags */ + /* Process flags. This also skips the first '%' */ spec->flags = 0; - - while (1) { /* this also skips first '%' */ - bool found = true; - - ++fmt; - - switch (*fmt) { - case '-': spec->flags |= LEFT; break; - case '+': spec->flags |= PLUS; break; - case ' ': spec->flags |= SPACE; break; - case '#': spec->flags |= SPECIAL; break; - case '0': spec->flags |= ZEROPAD; break; - default: found = false; - } - - if (!found) - break; - } + do { + /* this also skips first '%' */ + flag = spec_flag(*++fmt.str); + spec->flags |= flag; + } while (flag); /* get field width */ spec->field_width = -1; - if (isdigit(*fmt)) - spec->field_width = skip_atoi(&fmt); - else if (*fmt == '*') { + if (isdigit(*fmt.str)) + spec->field_width = skip_atoi(&fmt.str); + else if (unlikely(*fmt.str == '*')) { /* it's the next argument */ - spec->type = FORMAT_TYPE_WIDTH; - return ++fmt - start; + fmt.state = FORMAT_STATE_WIDTH; + fmt.str++; + return fmt; } precision: /* get the precision */ spec->precision = -1; - if (*fmt == '.') { - ++fmt; - if (isdigit(*fmt)) { - spec->precision = skip_atoi(&fmt); + if (unlikely(*fmt.str == '.')) { + fmt.str++; + if (isdigit(*fmt.str)) { + spec->precision = skip_atoi(&fmt.str); if (spec->precision < 0) spec->precision = 0; - } else if (*fmt == '*') { + } else if (*fmt.str == '*') { /* it's the next argument */ - spec->type = FORMAT_TYPE_PRECISION; - return ++fmt - start; + fmt.state = FORMAT_STATE_PRECISION; + fmt.str++; + return fmt; } } qualifier: - /* get the conversion qualifier */ - qualifier = 0; - if (*fmt == 'h' || _tolower(*fmt) == 'l' || - *fmt == 'z' || *fmt == 't') { - qualifier = *fmt++; - if (unlikely(qualifier == *fmt)) { - if (qualifier == 'l') { - qualifier = 'L'; - ++fmt; - } else if (qualifier == 'h') { - qualifier = 'H'; - ++fmt; - } - } - } - - /* default base */ + /* Set up default numeric format */ spec->base = 10; - switch (*fmt) { - case 'c': - spec->type = FORMAT_TYPE_CHAR; - return ++fmt - start; + fmt.state = FORMAT_STATE_NUM; + fmt.size = sizeof(int); + static const struct format_state { + unsigned char state; + unsigned char size; + unsigned char flags_or_double_size; + unsigned char base; + } lookup_state[256] = { + // Length + ['l'] = { 0, sizeof(long), sizeof(long long) }, + ['L'] = { 0, sizeof(long long) }, + ['h'] = { 0, sizeof(short), sizeof(char) }, + ['H'] = { 0, sizeof(char) }, // Questionable historical + ['z'] = { 0, sizeof(size_t) }, + ['t'] = { 0, sizeof(ptrdiff_t) }, - case 's': - spec->type = FORMAT_TYPE_STR; - return ++fmt - start; + // Non-numeric formats + ['c'] = { FORMAT_STATE_CHAR }, + ['s'] = { FORMAT_STATE_STR }, + ['p'] = { FORMAT_STATE_PTR }, + ['%'] = { FORMAT_STATE_PERCENT_CHAR }, - case 'p': - spec->type = FORMAT_TYPE_PTR; - return ++fmt - start; + // Numerics + ['o'] = { FORMAT_STATE_NUM, 0, 0, 8 }, + ['x'] = { FORMAT_STATE_NUM, 0, SMALL, 16 }, + ['X'] = { FORMAT_STATE_NUM, 0, 0, 16 }, + ['d'] = { FORMAT_STATE_NUM, 0, SIGN, 10 }, + ['i'] = { FORMAT_STATE_NUM, 0, SIGN, 10 }, + ['u'] = { FORMAT_STATE_NUM, 0, 0, 10, }, - case '%': - spec->type = FORMAT_TYPE_PERCENT_CHAR; - return ++fmt - start; - - /* integer number formats - set up the flags and "break" */ - case 'o': - spec->base = 8; - break; - - case 'x': - spec->flags |= SMALL; - fallthrough; - - case 'X': - spec->base = 16; - break; - - case 'd': - case 'i': - spec->flags |= SIGN; - break; - case 'u': - break; - - case 'n': /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ - fallthrough; + }; - default: - WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); - spec->type = FORMAT_TYPE_INVALID; - return fmt - start; + const struct format_state *p = lookup_state + (u8)*fmt.str; + if (p->size) { + fmt.size = p->size; + if (p->flags_or_double_size && fmt.str[0] == fmt.str[1]) { + fmt.size = p->flags_or_double_size; + fmt.str++; + } + fmt.str++; + p = lookup_state + *fmt.str; + } + if (p->state) { + if (p->base) + spec->base = p->base; + spec->flags |= p->flags_or_double_size; + fmt.state = p->state; + fmt.str++; + return fmt; } - if (qualifier == 'L') - spec->type = FORMAT_TYPE_LONG_LONG; - else if (qualifier == 'l') { - BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); - spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); - } else if (qualifier == 'z') { - spec->type = FORMAT_TYPE_SIZE_T; - } else if (qualifier == 't') { - spec->type = FORMAT_TYPE_PTRDIFF; - } else if (qualifier == 'H') { - BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); - spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); - } else if (qualifier == 'h') { - BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); - spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); - } else { - BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT); - spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN); - } - - return ++fmt - start; + WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt.str); + fmt.state = FORMAT_STATE_INVALID; + return fmt; } static void @@ -2747,11 +2713,27 @@ set_precision(struct printf_spec *spec, int prec) } } +/* + * Turn a 1/2/4-byte value into a 64-bit one for printing: truncate + * as necessary and deal with signedness. + * + * 'size' is the size of the value in bytes. + */ +static unsigned long long convert_num_spec(unsigned int val, int size, struct printf_spec spec) +{ + unsigned int shift = 32 - size*8; + + val <<= shift; + if (!(spec.flags & SIGN)) + return val >> shift; + return (int)val >> shift; +} + /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space - * @fmt: The format string to use + * @fmt_str: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some @@ -2775,11 +2757,14 @@ set_precision(struct printf_spec *spec, int prec) * * If you're not already dealing with a va_list consider using snprintf(). */ -int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) +int vsnprintf(char *buf, size_t size, const char *fmt_str, va_list args) { - unsigned long long num; char *str, *end; struct printf_spec spec = {0}; + struct fmt fmt = { + .str = fmt_str, + .state = FORMAT_STATE_NONE, + }; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ @@ -2795,33 +2780,43 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) size = end - buf; } - while (*fmt) { - const char *old_fmt = fmt; - int read = format_decode(fmt, &spec); + while (*fmt.str) { + const char *old_fmt = fmt.str; - fmt += read; + fmt = format_decode(fmt, &spec); - switch (spec.type) { - case FORMAT_TYPE_NONE: { - int copy = read; + switch (fmt.state) { + case FORMAT_STATE_NONE: { + int read = fmt.str - old_fmt; if (str < end) { + int copy = read; if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; - break; + continue; } - case FORMAT_TYPE_WIDTH: + case FORMAT_STATE_NUM: { + unsigned long long num; + if (fmt.size <= sizeof(int)) + num = convert_num_spec(va_arg(args, int), fmt.size, spec); + else + num = va_arg(args, long long); + str = number(str, end, num, spec); + continue; + } + + case FORMAT_STATE_WIDTH: set_field_width(&spec, va_arg(args, int)); - break; + continue; - case FORMAT_TYPE_PRECISION: + case FORMAT_STATE_PRECISION: set_precision(&spec, va_arg(args, int)); - break; + continue; - case FORMAT_TYPE_CHAR: { + case FORMAT_STATE_CHAR: { char c; if (!(spec.flags & LEFT)) { @@ -2841,27 +2836,27 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) *str = ' '; ++str; } - break; + continue; } - case FORMAT_TYPE_STR: + case FORMAT_STATE_STR: str = string(str, end, va_arg(args, char *), spec); - break; + continue; - case FORMAT_TYPE_PTR: - str = pointer(fmt, str, end, va_arg(args, void *), + case FORMAT_STATE_PTR: + str = pointer(fmt.str, str, end, va_arg(args, void *), spec); - while (isalnum(*fmt)) - fmt++; - break; + while (isalnum(*fmt.str)) + fmt.str++; + continue; - case FORMAT_TYPE_PERCENT_CHAR: + case FORMAT_STATE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; - break; + continue; - case FORMAT_TYPE_INVALID: + default: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way @@ -2871,47 +2866,6 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) * sync. */ goto out; - - default: - switch (spec.type) { - case FORMAT_TYPE_LONG_LONG: - num = va_arg(args, long long); - break; - case FORMAT_TYPE_ULONG: - num = va_arg(args, unsigned long); - break; - case FORMAT_TYPE_LONG: - num = va_arg(args, long); - break; - case FORMAT_TYPE_SIZE_T: - if (spec.flags & SIGN) - num = va_arg(args, ssize_t); - else - num = va_arg(args, size_t); - break; - case FORMAT_TYPE_PTRDIFF: - num = va_arg(args, ptrdiff_t); - break; - case FORMAT_TYPE_UBYTE: - num = (unsigned char) va_arg(args, int); - break; - case FORMAT_TYPE_BYTE: - num = (signed char) va_arg(args, int); - break; - case FORMAT_TYPE_USHORT: - num = (unsigned short) va_arg(args, int); - break; - case FORMAT_TYPE_SHORT: - num = (short) va_arg(args, int); - break; - case FORMAT_TYPE_INT: - num = (int) va_arg(args, int); - break; - default: - num = va_arg(args, unsigned int); - } - - str = number(str, end, num, spec); } } @@ -3067,7 +3021,7 @@ EXPORT_SYMBOL(sprintf); * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) - * @fmt: The format string to use + * @fmt_str: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument @@ -3080,8 +3034,12 @@ EXPORT_SYMBOL(sprintf); * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ -int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) +int vbin_printf(u32 *bin_buf, size_t size, const char *fmt_str, va_list args) { + struct fmt fmt = { + .str = fmt_str, + .state = FORMAT_STATE_NONE, + }; struct printf_spec spec = {0}; char *str, *end; int width; @@ -3113,31 +3071,29 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) value; \ }) - while (*fmt) { - int read = format_decode(fmt, &spec); + while (*fmt.str) { + fmt = format_decode(fmt, &spec); - fmt += read; - - switch (spec.type) { - case FORMAT_TYPE_NONE: - case FORMAT_TYPE_PERCENT_CHAR: + switch (fmt.state) { + case FORMAT_STATE_NONE: + case FORMAT_STATE_PERCENT_CHAR: break; - case FORMAT_TYPE_INVALID: + case FORMAT_STATE_INVALID: goto out; - case FORMAT_TYPE_WIDTH: - case FORMAT_TYPE_PRECISION: + case FORMAT_STATE_WIDTH: + case FORMAT_STATE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ - if (*fmt == 'p') + if (*fmt.str == 'p') set_field_width(&spec, width); break; - case FORMAT_TYPE_CHAR: + case FORMAT_STATE_CHAR: save_arg(char); break; - case FORMAT_TYPE_STR: { + case FORMAT_STATE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; @@ -3153,9 +3109,9 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) break; } - case FORMAT_TYPE_PTR: + case FORMAT_STATE_PTR: /* Dereferenced pointers must be done now */ - switch (*fmt) { + switch (*fmt.str) { /* Dereference of functions is still OK */ case 'S': case 's': @@ -3165,11 +3121,11 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) save_arg(void *); break; default: - if (!isalnum(*fmt)) { + if (!isalnum(*fmt.str)) { save_arg(void *); break; } - str = pointer(fmt, str, end, va_arg(args, void *), + str = pointer(fmt.str, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; @@ -3177,35 +3133,14 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ - while (isalnum(*fmt)) - fmt++; + while (isalnum(*fmt.str)) + fmt.str++; break; - default: - switch (spec.type) { - - case FORMAT_TYPE_LONG_LONG: + case FORMAT_STATE_NUM: + if (fmt.size > sizeof(int)) { save_arg(long long); - break; - case FORMAT_TYPE_ULONG: - case FORMAT_TYPE_LONG: - save_arg(unsigned long); - break; - case FORMAT_TYPE_SIZE_T: - save_arg(size_t); - break; - case FORMAT_TYPE_PTRDIFF: - save_arg(ptrdiff_t); - break; - case FORMAT_TYPE_UBYTE: - case FORMAT_TYPE_BYTE: - save_arg(char); - break; - case FORMAT_TYPE_USHORT: - case FORMAT_TYPE_SHORT: - save_arg(short); - break; - default: + } else { save_arg(int); } } @@ -3221,7 +3156,7 @@ EXPORT_SYMBOL_GPL(vbin_printf); * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space - * @fmt: The format string to use + * @fmt_str: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets @@ -3239,8 +3174,12 @@ EXPORT_SYMBOL_GPL(vbin_printf); * return is greater than or equal to @size, the resulting * string is truncated. */ -int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) +int bstr_printf(char *buf, size_t size, const char *fmt_str, const u32 *bin_buf) { + struct fmt fmt = { + .str = fmt_str, + .state = FORMAT_STATE_NONE, + }; struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; @@ -3272,33 +3211,33 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) size = end - buf; } - while (*fmt) { - const char *old_fmt = fmt; - int read = format_decode(fmt, &spec); + while (*fmt.str) { + const char *old_fmt = fmt.str; + unsigned long long num; - fmt += read; - - switch (spec.type) { - case FORMAT_TYPE_NONE: { - int copy = read; + fmt = format_decode(fmt, &spec); + switch (fmt.state) { + case FORMAT_STATE_NONE: { + int read = fmt.str - old_fmt; if (str < end) { + int copy = read; if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; - break; + continue; } - case FORMAT_TYPE_WIDTH: + case FORMAT_STATE_WIDTH: set_field_width(&spec, get_arg(int)); - break; + continue; - case FORMAT_TYPE_PRECISION: + case FORMAT_STATE_PRECISION: set_precision(&spec, get_arg(int)); - break; + continue; - case FORMAT_TYPE_CHAR: { + case FORMAT_STATE_CHAR: { char c; if (!(spec.flags & LEFT)) { @@ -3317,21 +3256,21 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) *str = ' '; ++str; } - break; + continue; } - case FORMAT_TYPE_STR: { + case FORMAT_STATE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); - break; + continue; } - case FORMAT_TYPE_PTR: { + case FORMAT_STATE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ - switch (*fmt) { + switch (*fmt.str) { case 'S': case 's': case 'x': @@ -3340,7 +3279,7 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) process = true; break; default: - if (!isalnum(*fmt)) { + if (!isalnum(*fmt.str)) { process = true; break; } @@ -3355,63 +3294,32 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) } } if (process) - str = pointer(fmt, str, end, get_arg(void *), spec); + str = pointer(fmt.str, str, end, get_arg(void *), spec); - while (isalnum(*fmt)) - fmt++; - break; + while (isalnum(*fmt.str)) + fmt.str++; + continue; } - case FORMAT_TYPE_PERCENT_CHAR: + case FORMAT_STATE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; - break; + continue; - case FORMAT_TYPE_INVALID: + case FORMAT_STATE_INVALID: goto out; - default: { - unsigned long long num; - - switch (spec.type) { - - case FORMAT_TYPE_LONG_LONG: + case FORMAT_STATE_NUM: + if (fmt.size > sizeof(int)) { num = get_arg(long long); - break; - case FORMAT_TYPE_ULONG: - case FORMAT_TYPE_LONG: - num = get_arg(unsigned long); - break; - case FORMAT_TYPE_SIZE_T: - num = get_arg(size_t); - break; - case FORMAT_TYPE_PTRDIFF: - num = get_arg(ptrdiff_t); - break; - case FORMAT_TYPE_UBYTE: - num = get_arg(unsigned char); - break; - case FORMAT_TYPE_BYTE: - num = get_arg(signed char); - break; - case FORMAT_TYPE_USHORT: - num = get_arg(unsigned short); - break; - case FORMAT_TYPE_SHORT: - num = get_arg(short); - break; - case FORMAT_TYPE_UINT: - num = get_arg(unsigned int); - break; - default: - num = get_arg(int); + } else { + num = convert_num_spec(get_arg(int), fmt.size, spec); } - str = number(str, end, num, spec); - } /* default: */ - } /* switch(spec.type) */ - } /* while(*fmt) */ + continue; + } + } /* while(*fmt.str) */ out: if (size > 0) { diff --git a/lib/win_minmax.c b/lib/win_minmax.c index ec10506834b6..1682e614309c 100644 --- a/lib/win_minmax.c +++ b/lib/win_minmax.c @@ -97,3 +97,4 @@ u32 minmax_running_min(struct minmax *m, u32 win, u32 t, u32 meas) return minmax_subwin_update(m, win, &val); } +EXPORT_SYMBOL(minmax_running_min); diff --git a/lib/xarray.c b/lib/xarray.c index 32d4bac8c94c..116e9286c64e 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -125,19 +125,20 @@ static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) */ static void xas_squash_marks(const struct xa_state *xas) { - unsigned int mark = 0; + xa_mark_t mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; - if (!xas->xa_sibs) - return; + for (;;) { + unsigned long *marks = node_marks(xas->xa_node, mark); - do { - unsigned long *marks = xas->xa_node->marks[mark]; - if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) - continue; - __set_bit(xas->xa_offset, marks); - bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); - } while (mark++ != (__force unsigned)XA_MARK_MAX); + if (find_next_bit(marks, limit, xas->xa_offset + 1) != limit) { + __set_bit(xas->xa_offset, marks); + bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); + } + if (mark == XA_MARK_MAX) + break; + mark_inc(mark); + } } /* extracts the offset within this node from the index */ @@ -435,6 +436,11 @@ static unsigned long max_index(void *entry) return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } +static inline void *xa_zero_to_null(void *entry) +{ + return xa_is_zero(entry) ? NULL : entry; +} + static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; @@ -451,8 +457,8 @@ static void xas_shrink(struct xa_state *xas) break; if (!xa_is_node(entry) && node->shift) break; - if (xa_is_zero(entry) && xa_zero_busy(xa)) - entry = NULL; + if (xa_zero_busy(xa)) + entry = xa_zero_to_null(entry); xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); @@ -1022,7 +1028,7 @@ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, unsigned int mask = xas->xa_sibs; /* XXX: no support for splitting really large entries yet */ - if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order)) + if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT <= order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; @@ -1147,6 +1153,7 @@ void xas_pause(struct xa_state *xas) if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } + xas->xa_index &= ~0UL << node->shift; xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; @@ -1382,6 +1389,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; + if (xa_is_sibling(entry)) + continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); @@ -1474,9 +1483,7 @@ void *xa_load(struct xarray *xa, unsigned long index) rcu_read_lock(); do { - entry = xas_load(&xas); - if (xa_is_zero(entry)) - entry = NULL; + entry = xa_zero_to_null(xas_load(&xas)); } while (xas_retry(&xas, entry)); rcu_read_unlock(); @@ -1486,8 +1493,6 @@ EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { - if (xa_is_zero(curr)) - return NULL; if (xas_error(xas)) curr = xas->xa_node; return curr; @@ -1508,7 +1513,7 @@ static void *xas_result(struct xa_state *xas, void *curr) void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); - return xas_result(&xas, xas_store(&xas, NULL)); + return xas_result(&xas, xa_zero_to_null(xas_store(&xas, NULL))); } EXPORT_SYMBOL(__xa_erase); @@ -1567,7 +1572,7 @@ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); - return xas_result(&xas, curr); + return xas_result(&xas, xa_zero_to_null(curr)); } EXPORT_SYMBOL(__xa_store); @@ -1600,6 +1605,9 @@ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) } EXPORT_SYMBOL(xa_store); +static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp); + /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. @@ -1618,6 +1626,13 @@ EXPORT_SYMBOL(xa_store); */ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) +{ + return xa_zero_to_null(__xa_cmpxchg_raw(xa, index, old, entry, gfp)); +} +EXPORT_SYMBOL(__xa_cmpxchg); + +static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; @@ -1636,7 +1651,6 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, return xas_result(&xas, curr); } -EXPORT_SYMBOL(__xa_cmpxchg); /** * __xa_insert() - Store this entry in the XArray if no entry is present. @@ -1656,26 +1670,16 @@ EXPORT_SYMBOL(__xa_cmpxchg); */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { - XA_STATE(xas, xa, index); void *curr; + int errno; - if (WARN_ON_ONCE(xa_is_advanced(entry))) - return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; - - do { - curr = xas_load(&xas); - if (!curr) { - xas_store(&xas, entry); - if (xa_track_free(xa)) - xas_clear_mark(&xas, XA_FREE_MARK); - } else { - xas_set_err(&xas, -EBUSY); - } - } while (__xas_nomem(&xas, gfp)); - - return xas_error(&xas); + curr = __xa_cmpxchg_raw(xa, index, NULL, entry, gfp); + errno = xa_err(curr); + if (errno) + return errno; + return (curr != NULL) ? -EBUSY : 0; } EXPORT_SYMBOL(__xa_insert); diff --git a/mm/Kconfig b/mm/Kconfig index 84000b016808..1b501db06417 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -550,20 +550,63 @@ menuconfig MEMORY_HOTPLUG if MEMORY_HOTPLUG -config MEMORY_HOTPLUG_DEFAULT_ONLINE - bool "Online the newly added memory blocks by default" - depends on MEMORY_HOTPLUG +choice + prompt "Memory Hotplug Default Online Type" + default MHP_DEFAULT_ONLINE_TYPE_OFFLINE help + Default memory type for hotplugged memory. + This option sets the default policy setting for memory hotplug onlining policy (/sys/devices/system/memory/auto_online_blocks) which determines what happens to newly added memory regions. Policy setting can always be changed at runtime. + + The default is 'offline'. + + Select offline to defer onlining to drivers and user policy. + Select auto to let the kernel choose what zones to utilize. + Select online_kernel to generally allow kernel usage of this memory. + Select online_movable to generally disallow kernel usage of this memory. + + Example kernel usage would be page structs and page tables. + See Documentation/admin-guide/mm/memory-hotplug.rst for more information. - Say Y here if you want all hot-plugged memory blocks to appear in - 'online' state by default. - Say N here if you want the default policy to keep all hot-plugged - memory blocks in 'offline' state. +config MHP_DEFAULT_ONLINE_TYPE_OFFLINE + bool "offline" + help + Hotplugged memory will not be onlined by default. + Choose this for systems with drivers and user policy that + handle onlining of hotplug memory policy. + +config MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO + bool "auto" + help + Select this if you want the kernel to automatically online + hotplugged memory into the zone it thinks is reasonable. + This memory may be utilized for kernel data. + +config MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL + bool "kernel" + help + Select this if you want the kernel to automatically online + hotplugged memory into a zone capable of being used for kernel + data. This typically means ZONE_NORMAL. + +config MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE + bool "movable" + help + Select this if you want the kernel to automatically online + hotplug memory into ZONE_MOVABLE. This memory will generally + not be utilized for kernel data. + + This should only be used when the admin knows sufficient + ZONE_NORMAL memory is available to describe hotplug memory, + otherwise hotplug memory may fail to online. For example, + sufficient kernel-capable memory (ZONE_NORMAL) must be + available to allocate page structs to describe ZONE_MOVABLE. + +endchoice config MEMORY_HOTREMOVE bool "Allow for memory hot remove" @@ -1301,6 +1344,21 @@ config ARCH_HAS_USER_SHADOW_STACK The architecture has hardware support for userspace shadow call stacks (eg, x86 CET, arm64 GCS or RISC-V Zicfiss). +config ARCH_SUPPORTS_PT_RECLAIM + def_bool n + +config PT_RECLAIM + bool "reclaim empty user page table pages" + default y + depends on ARCH_SUPPORTS_PT_RECLAIM && MMU && SMP + select MMU_GATHER_RCU_TABLE_FREE + help + Try to reclaim empty user page table pages in paths other than munmap + and exit_mmap path. + + Note: now only empty user PTE page table pages will be reclaimed. + + source "mm/damon/Kconfig" endmenu diff --git a/mm/Makefile b/mm/Makefile index dba52bb0da8a..850386a67b3e 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -146,3 +146,4 @@ obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o obj-$(CONFIG_EXECMEM) += execmem.o obj-$(CONFIG_TMPFS_QUOTA) += shmem_quota.o +obj-$(CONFIG_PT_RECLAIM) += pt_reclaim.o diff --git a/mm/cma.h b/mm/cma.h index ad61cc6dd439..8485ef893e99 100644 --- a/mm/cma.h +++ b/mm/cma.h @@ -36,7 +36,7 @@ struct cma { }; extern struct cma cma_areas[MAX_CMA_AREAS]; -extern unsigned cma_area_count; +extern unsigned int cma_area_count; static inline unsigned long cma_bitmap_maxno(struct cma *cma) { diff --git a/mm/compaction.c b/mm/compaction.c index a2b16b08cbbf..12ed8425fa17 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -83,6 +83,7 @@ static inline bool is_via_compact_memory(int order) { return false; } static struct page *mark_allocated_noprof(struct page *page, unsigned int order, gfp_t gfp_flags) { post_alloc_hook(page, order, __GFP_MOVABLE); + set_page_refcounted(page); return page; } #define mark_allocated(...) alloc_hooks(mark_allocated_noprof(__VA_ARGS__)) @@ -630,7 +631,8 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (PageCompound(page)) { const unsigned int order = compound_order(page); - if (blockpfn + (1UL << order) <= end_pfn) { + if ((order <= MAX_PAGE_ORDER) && + (blockpfn + (1UL << order) <= end_pfn)) { blockpfn += (1UL << order) - 1; page += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; @@ -1868,6 +1870,7 @@ again: dst = (struct folio *)freepage; post_alloc_hook(&dst->page, order, __GFP_MOVABLE); + set_page_refcounted(&dst->page); if (order) prep_compound_page(&dst->page, order); cc->nr_freepages -= 1 << order; @@ -2488,7 +2491,8 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, */ static enum compact_result compaction_suit_allocation_order(struct zone *zone, unsigned int order, - int highest_zoneidx, unsigned int alloc_flags) + int highest_zoneidx, unsigned int alloc_flags, + bool async) { unsigned long watermark; @@ -2497,6 +2501,23 @@ compaction_suit_allocation_order(struct zone *zone, unsigned int order, alloc_flags)) return COMPACT_SUCCESS; + /* + * For unmovable allocations (without ALLOC_CMA), check if there is enough + * free memory in the non-CMA pageblocks. Otherwise compaction could form + * the high-order page in CMA pageblocks, which would not help the + * allocation to succeed. However, limit the check to costly order async + * compaction (such as opportunistic THP attempts) because there is the + * possibility that compaction would migrate pages from non-CMA to CMA + * pageblock. + */ + if (order > PAGE_ALLOC_COSTLY_ORDER && async && + !(alloc_flags & ALLOC_CMA)) { + watermark = low_wmark_pages(zone) + compact_gap(order); + if (!__zone_watermark_ok(zone, 0, watermark, highest_zoneidx, + 0, zone_page_state(zone, NR_FREE_PAGES))) + return COMPACT_SKIPPED; + } + if (!compaction_suitable(zone, order, highest_zoneidx)) return COMPACT_SKIPPED; @@ -2532,7 +2553,8 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) if (!is_via_compact_memory(cc->order)) { ret = compaction_suit_allocation_order(cc->zone, cc->order, cc->highest_zoneidx, - cc->alloc_flags); + cc->alloc_flags, + cc->mode == MIGRATE_ASYNC); if (ret != COMPACT_CONTINUE) return ret; } @@ -3035,7 +3057,8 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) ret = compaction_suit_allocation_order(zone, pgdat->kcompactd_max_order, - highest_zoneidx, ALLOC_WMARK_MIN); + highest_zoneidx, ALLOC_WMARK_MIN, + false); if (ret == COMPACT_CONTINUE) return true; } @@ -3076,7 +3099,8 @@ static void kcompactd_do_work(pg_data_t *pgdat) continue; ret = compaction_suit_allocation_order(zone, - cc.order, zoneid, ALLOC_WMARK_MIN); + cc.order, zoneid, ALLOC_WMARK_MIN, + false); if (ret != COMPACT_CONTINUE) continue; @@ -3154,15 +3178,9 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx) static int kcompactd(void *p) { pg_data_t *pgdat = (pg_data_t *)p; - struct task_struct *tsk = current; long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC); long timeout = default_timeout; - const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); - - if (!cpumask_empty(cpumask)) - set_cpus_allowed_ptr(tsk, cpumask); - set_freezable(); pgdat->kcompactd_max_order = 0; @@ -3233,10 +3251,12 @@ void __meminit kcompactd_run(int nid) if (pgdat->kcompactd) return; - pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid); + pgdat->kcompactd = kthread_create_on_node(kcompactd, pgdat, nid, "kcompactd%d", nid); if (IS_ERR(pgdat->kcompactd)) { pr_err("Failed to start kcompactd on node %d\n", nid); pgdat->kcompactd = NULL; + } else { + wake_up_process(pgdat->kcompactd); } } @@ -3254,30 +3274,6 @@ void __meminit kcompactd_stop(int nid) } } -/* - * It's optimal to keep kcompactd on the same CPUs as their memory, but - * not required for correctness. So if the last cpu in a node goes - * away, we get changed to run anywhere: as the first one comes back, - * restore their cpu bindings. - */ -static int kcompactd_cpu_online(unsigned int cpu) -{ - int nid; - - for_each_node_state(nid, N_MEMORY) { - pg_data_t *pgdat = NODE_DATA(nid); - const struct cpumask *mask; - - mask = cpumask_of_node(pgdat->node_id); - - if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) - /* One of our CPUs online: restore mask */ - if (pgdat->kcompactd) - set_cpus_allowed_ptr(pgdat->kcompactd, mask); - } - return 0; -} - static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -3297,7 +3293,7 @@ static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table, return ret; } -static struct ctl_table vm_compaction[] = { +static const struct ctl_table vm_compaction[] = { { .procname = "compact_memory", .data = &sysctl_compact_memory, @@ -3337,15 +3333,6 @@ static struct ctl_table vm_compaction[] = { static int __init kcompactd_init(void) { int nid; - int ret; - - ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "mm/compaction:online", - kcompactd_cpu_online, NULL); - if (ret < 0) { - pr_err("kcompactd: failed to register hotplug callbacks.\n"); - return ret; - } for_each_node_state(nid, N_MEMORY) kcompactd_run(nid); diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index d0357f3e9372..c213cf8b5638 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -71,36 +71,6 @@ config DAMON_SYSFS_KUNIT_TEST If unsure, say N. -config DAMON_DBGFS_DEPRECATED - bool "DAMON debugfs interface (DEPRECATED!)" - depends on DAMON_VADDR && DAMON_PADDR && DEBUG_FS - help - This builds the debugfs interface for DAMON. The user space admins - can use the interface for arbitrary data access monitoring. - - If unsure, say N. - - This is deprecated, so users should move to the sysfs interface - (DAMON_SYSFS). If you depend on this and cannot move, please report - your usecase to damon@lists.linux.dev and linux-mm@kvack.org. - -config DAMON_DBGFS - bool - default y - depends on DAMON_DBGFS_DEPRECATED - -config DAMON_DBGFS_KUNIT_TEST - bool "Test for damon debugfs interface" if !KUNIT_ALL_TESTS - depends on DAMON_DBGFS && KUNIT=y - default KUNIT_ALL_TESTS - help - This builds the DAMON debugfs interface Kunit test suite. - - For more information on KUnit and unit tests in general, please refer - to the KUnit documentation. - - If unsure, say N. - config DAMON_RECLAIM bool "Build DAMON-based reclaim (DAMON_RECLAIM)" depends on DAMON_PADDR diff --git a/mm/damon/Makefile b/mm/damon/Makefile index f7add3f4aa79..8b49012ba8c3 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -4,6 +4,5 @@ obj-y := core.o obj-$(CONFIG_DAMON_VADDR) += ops-common.o vaddr.o obj-$(CONFIG_DAMON_PADDR) += ops-common.o paddr.o obj-$(CONFIG_DAMON_SYSFS) += sysfs-common.o sysfs-schemes.o sysfs.o -obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o obj-$(CONFIG_DAMON_RECLAIM) += modules-common.o reclaim.o obj-$(CONFIG_DAMON_LRU_SORT) += modules-common.o lru_sort.o diff --git a/mm/damon/core.c b/mm/damon/core.c index 8b8e2933dcd4..c7b981308862 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -14,6 +14,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -266,7 +267,7 @@ int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, } struct damos_filter *damos_new_filter(enum damos_filter_type type, - bool matching) + bool matching, bool allow) { struct damos_filter *filter; @@ -275,6 +276,7 @@ struct damos_filter *damos_new_filter(enum damos_filter_type type, return NULL; filter->type = type; filter->matching = matching; + filter->allow = allow; INIT_LIST_HEAD(&filter->list); return filter; } @@ -504,6 +506,8 @@ struct damon_ctx *damon_new_ctx(void) ctx->next_ops_update_sis = 0; mutex_init(&ctx->kdamond_lock); + mutex_init(&ctx->call_control_lock); + mutex_init(&ctx->walk_control_lock); ctx->attrs.min_nr_regions = 10; ctx->attrs.max_nr_regions = 1000; @@ -803,7 +807,8 @@ static int damos_commit_filters(struct damos *dst, struct damos *src) continue; new_filter = damos_new_filter( - src_filter->type, src_filter->matching); + src_filter->type, src_filter->matching, + src_filter->allow); if (!new_filter) return -ENOMEM; damos_commit_filter_arg(new_filter, src_filter); @@ -868,6 +873,11 @@ static int damon_commit_schemes(struct damon_ctx *dst, struct damon_ctx *src) NUMA_NO_NODE); if (!new_scheme) return -ENOMEM; + err = damos_commit(new_scheme, src_scheme); + if (err) { + damon_destroy_scheme(new_scheme); + return err; + } damon_add_scheme(dst, new_scheme); } return 0; @@ -961,8 +971,11 @@ static int damon_commit_targets( return -ENOMEM; err = damon_commit_target(new_target, false, src_target, damon_target_has_pid(src)); - if (err) + if (err) { + damon_destroy_target(new_target); return err; + } + damon_add_target(dst, new_target); } return 0; } @@ -1154,6 +1167,94 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs) return err; } +static bool damon_is_running(struct damon_ctx *ctx) +{ + bool running; + + mutex_lock(&ctx->kdamond_lock); + running = ctx->kdamond != NULL; + mutex_unlock(&ctx->kdamond_lock); + return running; +} + +/** + * damon_call() - Invoke a given function on DAMON worker thread (kdamond). + * @ctx: DAMON context to call the function for. + * @control: Control variable of the call request. + * + * Ask DAMON worker thread (kdamond) of @ctx to call a function with an + * argument data that respectively passed via &damon_call_control->fn and + * &damon_call_control->data of @control, and wait until the kdamond finishes + * handling of the request. + * + * The kdamond executes the function with the argument in the main loop, just + * after a sampling of the iteration is finished. The function can hence + * safely access the internal data of the &struct damon_ctx without additional + * synchronization. The return value of the function will be saved in + * &damon_call_control->return_code. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_call(struct damon_ctx *ctx, struct damon_call_control *control) +{ + init_completion(&control->completion); + control->canceled = false; + + mutex_lock(&ctx->call_control_lock); + if (ctx->call_control) { + mutex_unlock(&ctx->call_control_lock); + return -EBUSY; + } + ctx->call_control = control; + mutex_unlock(&ctx->call_control_lock); + if (!damon_is_running(ctx)) + return -EINVAL; + wait_for_completion(&control->completion); + if (control->canceled) + return -ECANCELED; + return 0; +} + +/** + * damos_walk() - Invoke a given functions while DAMOS walk regions. + * @ctx: DAMON context to call the functions for. + * @control: Control variable of the walk request. + * + * Ask DAMON worker thread (kdamond) of @ctx to call a function for each region + * that the kdamond will apply DAMOS action to, and wait until the kdamond + * finishes handling of the request. + * + * The kdamond executes the given function in the main loop, for each region + * just after it applied any DAMOS actions of @ctx to it. The invocation is + * made only within one &damos->apply_interval_us since damos_walk() + * invocation, for each scheme. The given callback function can hence safely + * access the internal data of &struct damon_ctx and &struct damon_region that + * each of the scheme will apply the action for next interval, without + * additional synchronizations against the kdamond. If every scheme of @ctx + * passed at least one &damos->apply_interval_us, kdamond marks the request as + * completed so that damos_walk() can wakeup and return. + * + * Return: 0 on success, negative error code otherwise. + */ +int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control) +{ + init_completion(&control->completion); + control->canceled = false; + mutex_lock(&ctx->walk_control_lock); + if (ctx->walk_control) { + mutex_unlock(&ctx->walk_control_lock); + return -EBUSY; + } + ctx->walk_control = control; + mutex_unlock(&ctx->walk_control_lock); + if (!damon_is_running(ctx)) + return -EINVAL; + wait_for_completion(&control->completion); + if (control->canceled) + return -ECANCELED; + return 0; +} + /* * Reset the aggregated monitoring results ('nr_accesses' of each region). */ @@ -1264,16 +1365,18 @@ static bool damos_skip_charged_region(struct damon_target *t, } static void damos_update_stat(struct damos *s, - unsigned long sz_tried, unsigned long sz_applied) + unsigned long sz_tried, unsigned long sz_applied, + unsigned long sz_ops_filter_passed) { s->stat.nr_tried++; s->stat.sz_tried += sz_tried; if (sz_applied) s->stat.nr_applied++; s->stat.sz_applied += sz_applied; + s->stat.sz_ops_filter_passed += sz_ops_filter_passed; } -static bool __damos_filter_out(struct damon_ctx *ctx, struct damon_target *t, +static bool damos_filter_match(struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, struct damos_filter *filter) { bool matched = false; @@ -1327,12 +1430,98 @@ static bool damos_filter_out(struct damon_ctx *ctx, struct damon_target *t, struct damos_filter *filter; damos_for_each_filter(filter, s) { - if (__damos_filter_out(ctx, t, r, filter)) - return true; + if (damos_filter_match(ctx, t, r, filter)) + return !filter->allow; } return false; } +/* + * damos_walk_call_walk() - Call &damos_walk_control->walk_fn. + * @ctx: The context of &damon_ctx->walk_control. + * @t: The monitoring target of @r that @s will be applied. + * @r: The region of @t that @s will be applied. + * @s: The scheme of @ctx that will be applied to @r. + * + * This function is called from kdamond whenever it asked the operation set to + * apply a DAMOS scheme action to a region. If a DAMOS walk request is + * installed by damos_walk() and not yet uninstalled, invoke it. + */ +static void damos_walk_call_walk(struct damon_ctx *ctx, struct damon_target *t, + struct damon_region *r, struct damos *s, + unsigned long sz_filter_passed) +{ + struct damos_walk_control *control; + + mutex_lock(&ctx->walk_control_lock); + control = ctx->walk_control; + mutex_unlock(&ctx->walk_control_lock); + if (!control) + return; + control->walk_fn(control->data, ctx, t, r, s, sz_filter_passed); +} + +/* + * damos_walk_complete() - Complete DAMOS walk request if all walks are done. + * @ctx: The context of &damon_ctx->walk_control. + * @s: A scheme of @ctx that all walks are now done. + * + * This function is called when kdamond finished applying the action of a DAMOS + * scheme to all regions that eligible for the given &damos->apply_interval_us. + * If every scheme of @ctx including @s now finished walking for at least one + * &damos->apply_interval_us, this function makrs the handling of the given + * DAMOS walk request is done, so that damos_walk() can wake up and return. + */ +static void damos_walk_complete(struct damon_ctx *ctx, struct damos *s) +{ + struct damos *siter; + struct damos_walk_control *control; + + mutex_lock(&ctx->walk_control_lock); + control = ctx->walk_control; + mutex_unlock(&ctx->walk_control_lock); + if (!control) + return; + + s->walk_completed = true; + /* if all schemes completed, signal completion to walker */ + damon_for_each_scheme(siter, ctx) { + if (!siter->walk_completed) + return; + } + complete(&control->completion); + mutex_lock(&ctx->walk_control_lock); + ctx->walk_control = NULL; + mutex_unlock(&ctx->walk_control_lock); +} + +/* + * damos_walk_cancel() - Cancel the current DAMOS walk request. + * @ctx: The context of &damon_ctx->walk_control. + * + * This function is called when @ctx is deactivated by DAMOS watermarks, DAMOS + * walk is requested but there is no DAMOS scheme to walk for, or the kdamond + * is already out of the main loop and therefore gonna be terminated, and hence + * cannot continue the walks. This function therefore marks the walk request + * as canceled, so that damos_walk() can wake up and return. + */ +static void damos_walk_cancel(struct damon_ctx *ctx) +{ + struct damos_walk_control *control; + + mutex_lock(&ctx->walk_control_lock); + control = ctx->walk_control; + mutex_unlock(&ctx->walk_control_lock); + + if (!control) + return; + control->canceled = true; + complete(&control->completion); + mutex_lock(&ctx->walk_control_lock); + ctx->walk_control = NULL; + mutex_unlock(&ctx->walk_control_lock); +} + static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t, struct damon_region *r, struct damos *s) { @@ -1340,6 +1529,7 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t, unsigned long sz = damon_sz_region(r); struct timespec64 begin, end; unsigned long sz_applied = 0; + unsigned long sz_ops_filter_passed = 0; int err = 0; /* * We plan to support multiple context per kdamond, as DAMON sysfs @@ -1385,8 +1575,10 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t, if (!err) { trace_damos_before_apply(cidx, sidx, tidx, r, damon_nr_regions(t), do_trace); - sz_applied = c->ops.apply_scheme(c, t, r, s); + sz_applied = c->ops.apply_scheme(c, t, r, s, + &sz_ops_filter_passed); } + damos_walk_call_walk(c, t, r, s, sz_ops_filter_passed); ktime_get_coarse_ts64(&end); quota->total_charged_ns += timespec64_to_ns(&end) - timespec64_to_ns(&begin); @@ -1400,7 +1592,7 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t, r->age = 0; update_stat: - damos_update_stat(s, sz, sz_applied); + damos_update_stat(s, sz, sz_applied, sz_ops_filter_passed); } static void damon_do_apply_schemes(struct damon_ctx *c, @@ -1542,7 +1734,7 @@ static unsigned long damos_quota_score(struct damos_quota *quota) static void damos_set_effective_quota(struct damos_quota *quota) { unsigned long throughput; - unsigned long esz; + unsigned long esz = ULONG_MAX; if (!quota->ms && list_empty("a->goals)) { quota->esz = quota->sz; @@ -1564,10 +1756,7 @@ static void damos_set_effective_quota(struct damos_quota *quota) quota->total_charged_ns; else throughput = PAGE_SIZE * 1024; - if (!list_empty("a->goals)) - esz = min(throughput * quota->ms, esz); - else - esz = throughput * quota->ms; + esz = min(throughput * quota->ms, esz); } if (quota->sz && quota->sz < esz) @@ -1658,6 +1847,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c) damon_for_each_scheme(s, c) { if (c->passed_sample_intervals < s->next_apply_sis) continue; + damos_walk_complete(c, s); s->next_apply_sis = c->passed_sample_intervals + (s->apply_interval_us ? s->apply_interval_us : c->attrs.aggr_interval) / sample_interval; @@ -1886,9 +2076,8 @@ static unsigned long damos_wmark_wait_us(struct damos *scheme) if (metric > scheme->wmarks.high || scheme->wmarks.low > metric) { if (scheme->wmarks.activated) pr_debug("deactivate a scheme (%d) for %s wmark\n", - scheme->action, - metric > scheme->wmarks.high ? - "high" : "low"); + scheme->action, + str_high_low(metric > scheme->wmarks.high)); scheme->wmarks.activated = false; return scheme->wmarks.interval; } @@ -1912,6 +2101,39 @@ static void kdamond_usleep(unsigned long usecs) usleep_range_idle(usecs, usecs + 1); } +/* + * kdamond_call() - handle damon_call_control. + * @ctx: The &struct damon_ctx of the kdamond. + * @cancel: Whether to cancel the invocation of the function. + * + * If there is a &struct damon_call_control request that registered via + * &damon_call() on @ctx, do or cancel the invocation of the function depending + * on @cancel. @cancel is set when the kdamond is deactivated by DAMOS + * watermarks, or the kdamond is already out of the main loop and therefore + * will be terminated. + */ +static void kdamond_call(struct damon_ctx *ctx, bool cancel) +{ + struct damon_call_control *control; + int ret = 0; + + mutex_lock(&ctx->call_control_lock); + control = ctx->call_control; + mutex_unlock(&ctx->call_control_lock); + if (!control) + return; + if (cancel) { + control->canceled = true; + } else { + ret = control->fn(control->data); + control->return_code = ret; + } + complete(&control->completion); + mutex_lock(&ctx->call_control_lock); + ctx->call_control = NULL; + mutex_unlock(&ctx->call_control_lock); +} + /* Returns negative error code if it's not activated but should return */ static int kdamond_wait_activation(struct damon_ctx *ctx) { @@ -1936,6 +2158,8 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) if (ctx->callback.after_wmarks_check && ctx->callback.after_wmarks_check(ctx)) break; + kdamond_call(ctx, true); + damos_walk_cancel(ctx); } return -EBUSY; } @@ -2006,6 +2230,7 @@ static int kdamond_fn(void *data) if (ctx->callback.after_sampling && ctx->callback.after_sampling(ctx)) break; + kdamond_call(ctx, false); kdamond_usleep(sample_interval); ctx->passed_sample_intervals++; @@ -2028,6 +2253,8 @@ static int kdamond_fn(void *data) */ if (!list_empty(&ctx->schemes)) kdamond_apply_schemes(ctx); + else + damos_walk_cancel(ctx); sample_interval = ctx->attrs.sample_interval ? ctx->attrs.sample_interval : 1; @@ -2067,6 +2294,9 @@ done: ctx->kdamond = NULL; mutex_unlock(&ctx->kdamond_lock); + kdamond_call(ctx, true); + damos_walk_cancel(ctx); + mutex_lock(&damon_lock); nr_running_ctxs--; if (!nr_running_ctxs && running_exclusive_ctxs) diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c deleted file mode 100644 index b4213bc47e44..000000000000 --- a/mm/damon/dbgfs.c +++ /dev/null @@ -1,1148 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DAMON Debugfs Interface - * - * Author: SeongJae Park - */ - -#define pr_fmt(fmt) "damon-dbgfs: " fmt - -#include -#include -#include -#include -#include -#include -#include - -#define DAMON_DBGFS_DEPRECATION_NOTICE \ - "DAMON debugfs interface is deprecated, so users should move " \ - "to DAMON_SYSFS. If you cannot, please report your usecase to " \ - "damon@lists.linux.dev and linux-mm@kvack.org.\n" - -static struct damon_ctx **dbgfs_ctxs; -static int dbgfs_nr_ctxs; -static struct dentry **dbgfs_dirs; -static DEFINE_MUTEX(damon_dbgfs_lock); - -static void damon_dbgfs_warn_deprecation(void) -{ - pr_warn_once(DAMON_DBGFS_DEPRECATION_NOTICE); -} - -/* - * Returns non-empty string on success, negative error code otherwise. - */ -static char *user_input_str(const char __user *buf, size_t count, loff_t *ppos) -{ - char *kbuf; - ssize_t ret; - - /* We do not accept continuous write */ - if (*ppos) - return ERR_PTR(-EINVAL); - - kbuf = kmalloc(count + 1, GFP_KERNEL | __GFP_NOWARN); - if (!kbuf) - return ERR_PTR(-ENOMEM); - - ret = simple_write_to_buffer(kbuf, count + 1, ppos, buf, count); - if (ret != count) { - kfree(kbuf); - return ERR_PTR(-EIO); - } - kbuf[ret] = '\0'; - - return kbuf; -} - -static ssize_t dbgfs_attrs_read(struct file *file, - char __user *buf, size_t count, loff_t *ppos) -{ - struct damon_ctx *ctx = file->private_data; - char kbuf[128]; - int ret; - - mutex_lock(&ctx->kdamond_lock); - ret = scnprintf(kbuf, ARRAY_SIZE(kbuf), "%lu %lu %lu %lu %lu\n", - ctx->attrs.sample_interval, ctx->attrs.aggr_interval, - ctx->attrs.ops_update_interval, - ctx->attrs.min_nr_regions, ctx->attrs.max_nr_regions); - mutex_unlock(&ctx->kdamond_lock); - - return simple_read_from_buffer(buf, count, ppos, kbuf, ret); -} - -static ssize_t dbgfs_attrs_write(struct file *file, - const char __user *buf, size_t count, loff_t *ppos) -{ - struct damon_ctx *ctx = file->private_data; - struct damon_attrs attrs; - char *kbuf; - ssize_t ret; - - kbuf = user_input_str(buf, count, ppos); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - - if (sscanf(kbuf, "%lu %lu %lu %lu %lu", - &attrs.sample_interval, &attrs.aggr_interval, - &attrs.ops_update_interval, - &attrs.min_nr_regions, - &attrs.max_nr_regions) != 5) { - ret = -EINVAL; - goto out; - } - - mutex_lock(&ctx->kdamond_lock); - if (ctx->kdamond) { - ret = -EBUSY; - goto unlock_out; - } - - ret = damon_set_attrs(ctx, &attrs); - if (!ret) - ret = count; -unlock_out: - mutex_unlock(&ctx->kdamond_lock); -out: - kfree(kbuf); - return ret; -} - -/* - * Return corresponding dbgfs' scheme action value (int) for the given - * damos_action if the given damos_action value is valid and supported by - * dbgfs, negative error code otherwise. - */ -static int damos_action_to_dbgfs_scheme_action(enum damos_action action) -{ - switch (action) { - case DAMOS_WILLNEED: - return 0; - case DAMOS_COLD: - return 1; - case DAMOS_PAGEOUT: - return 2; - case DAMOS_HUGEPAGE: - return 3; - case DAMOS_NOHUGEPAGE: - return 4; - case DAMOS_STAT: - return 5; - default: - return -EINVAL; - } -} - -static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) -{ - struct damos *s; - int written = 0; - int rc; - - damon_for_each_scheme(s, c) { - rc = scnprintf(&buf[written], len - written, - "%lu %lu %u %u %u %u %d %lu %lu %lu %u %u %u %d %lu %lu %lu %lu %lu %lu %lu %lu %lu\n", - s->pattern.min_sz_region, - s->pattern.max_sz_region, - s->pattern.min_nr_accesses, - s->pattern.max_nr_accesses, - s->pattern.min_age_region, - s->pattern.max_age_region, - damos_action_to_dbgfs_scheme_action(s->action), - s->quota.ms, s->quota.sz, - s->quota.reset_interval, - s->quota.weight_sz, - s->quota.weight_nr_accesses, - s->quota.weight_age, - s->wmarks.metric, s->wmarks.interval, - s->wmarks.high, s->wmarks.mid, s->wmarks.low, - s->stat.nr_tried, s->stat.sz_tried, - s->stat.nr_applied, s->stat.sz_applied, - s->stat.qt_exceeds); - if (!rc) - return -ENOMEM; - - written += rc; - } - return written; -} - -static ssize_t dbgfs_schemes_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - struct damon_ctx *ctx = file->private_data; - char *kbuf; - ssize_t len; - - kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN); - if (!kbuf) - return -ENOMEM; - - mutex_lock(&ctx->kdamond_lock); - len = sprint_schemes(ctx, kbuf, count); - mutex_unlock(&ctx->kdamond_lock); - if (len < 0) - goto out; - len = simple_read_from_buffer(buf, count, ppos, kbuf, len); - -out: - kfree(kbuf); - return len; -} - -static void free_schemes_arr(struct damos **schemes, ssize_t nr_schemes) -{ - ssize_t i; - - for (i = 0; i < nr_schemes; i++) - kfree(schemes[i]); - kfree(schemes); -} - -/* - * Return corresponding damos_action for the given dbgfs input for a scheme - * action if the input is valid, negative error code otherwise. - */ -static enum damos_action dbgfs_scheme_action_to_damos_action(int dbgfs_action) -{ - switch (dbgfs_action) { - case 0: - return DAMOS_WILLNEED; - case 1: - return DAMOS_COLD; - case 2: - return DAMOS_PAGEOUT; - case 3: - return DAMOS_HUGEPAGE; - case 4: - return DAMOS_NOHUGEPAGE; - case 5: - return DAMOS_STAT; - default: - return -EINVAL; - } -} - -/* - * Converts a string into an array of struct damos pointers - * - * Returns an array of struct damos pointers that converted if the conversion - * success, or NULL otherwise. - */ -static struct damos **str_to_schemes(const char *str, ssize_t len, - ssize_t *nr_schemes) -{ - struct damos *scheme, **schemes; - const int max_nr_schemes = 256; - int pos = 0, parsed, ret; - unsigned int action_input; - enum damos_action action; - - schemes = kmalloc_array(max_nr_schemes, sizeof(scheme), - GFP_KERNEL); - if (!schemes) - return NULL; - - *nr_schemes = 0; - while (pos < len && *nr_schemes < max_nr_schemes) { - struct damos_access_pattern pattern = {}; - struct damos_quota quota = {}; - struct damos_watermarks wmarks; - - ret = sscanf(&str[pos], - "%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u %u %lu %lu %lu %lu%n", - &pattern.min_sz_region, &pattern.max_sz_region, - &pattern.min_nr_accesses, - &pattern.max_nr_accesses, - &pattern.min_age_region, - &pattern.max_age_region, - &action_input, "a.ms, - "a.sz, "a.reset_interval, - "a.weight_sz, "a.weight_nr_accesses, - "a.weight_age, &wmarks.metric, - &wmarks.interval, &wmarks.high, &wmarks.mid, - &wmarks.low, &parsed); - if (ret != 18) - break; - action = dbgfs_scheme_action_to_damos_action(action_input); - if ((int)action < 0) - goto fail; - - if (pattern.min_sz_region > pattern.max_sz_region || - pattern.min_nr_accesses > pattern.max_nr_accesses || - pattern.min_age_region > pattern.max_age_region) - goto fail; - - if (wmarks.high < wmarks.mid || wmarks.high < wmarks.low || - wmarks.mid < wmarks.low) - goto fail; - - pos += parsed; - scheme = damon_new_scheme(&pattern, action, 0, "a, - &wmarks, NUMA_NO_NODE); - if (!scheme) - goto fail; - - schemes[*nr_schemes] = scheme; - *nr_schemes += 1; - } - return schemes; -fail: - free_schemes_arr(schemes, *nr_schemes); - return NULL; -} - -static ssize_t dbgfs_schemes_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct damon_ctx *ctx = file->private_data; - char *kbuf; - struct damos **schemes; - ssize_t nr_schemes = 0, ret; - - kbuf = user_input_str(buf, count, ppos); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - - schemes = str_to_schemes(kbuf, count, &nr_schemes); - if (!schemes) { - ret = -EINVAL; - goto out; - } - - mutex_lock(&ctx->kdamond_lock); - if (ctx->kdamond) { - ret = -EBUSY; - goto unlock_out; - } - - damon_set_schemes(ctx, schemes, nr_schemes); - ret = count; - nr_schemes = 0; - -unlock_out: - mutex_unlock(&ctx->kdamond_lock); - free_schemes_arr(schemes, nr_schemes); -out: - kfree(kbuf); - return ret; -} - -static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len) -{ - struct damon_target *t; - int id; - int written = 0; - int rc; - - damon_for_each_target(t, ctx) { - if (damon_target_has_pid(ctx)) - /* Show pid numbers to debugfs users */ - id = pid_vnr(t->pid); - else - /* Show 42 for physical address space, just for fun */ - id = 42; - - rc = scnprintf(&buf[written], len - written, "%d ", id); - if (!rc) - return -ENOMEM; - written += rc; - } - if (written) - written -= 1; - written += scnprintf(&buf[written], len - written, "\n"); - return written; -} - -static ssize_t dbgfs_target_ids_read(struct file *file, - char __user *buf, size_t count, loff_t *ppos) -{ - struct damon_ctx *ctx = file->private_data; - ssize_t len; - char ids_buf[320]; - - mutex_lock(&ctx->kdamond_lock); - len = sprint_target_ids(ctx, ids_buf, 320); - mutex_unlock(&ctx->kdamond_lock); - if (len < 0) - return len; - - return simple_read_from_buffer(buf, count, ppos, ids_buf, len); -} - -/* - * Converts a string into an integers array - * - * Returns an array of integers array if the conversion success, or NULL - * otherwise. - */ -static int *str_to_ints(const char *str, ssize_t len, ssize_t *nr_ints) -{ - int *array; - const int max_nr_ints = 32; - int nr; - int pos = 0, parsed, ret; - - *nr_ints = 0; - array = kmalloc_array(max_nr_ints, sizeof(*array), GFP_KERNEL); - if (!array) - return NULL; - while (*nr_ints < max_nr_ints && pos < len) { - ret = sscanf(&str[pos], "%d%n", &nr, &parsed); - pos += parsed; - if (ret != 1) - break; - array[*nr_ints] = nr; - *nr_ints += 1; - } - - return array; -} - -static void dbgfs_put_pids(struct pid **pids, int nr_pids) -{ - int i; - - for (i = 0; i < nr_pids; i++) - put_pid(pids[i]); -} - -/* - * Converts a string into an struct pid pointers array - * - * Returns an array of struct pid pointers if the conversion success, or NULL - * otherwise. - */ -static struct pid **str_to_pids(const char *str, ssize_t len, ssize_t *nr_pids) -{ - int *ints; - ssize_t nr_ints; - struct pid **pids; - - *nr_pids = 0; - - ints = str_to_ints(str, len, &nr_ints); - if (!ints) - return NULL; - - pids = kmalloc_array(nr_ints, sizeof(*pids), GFP_KERNEL); - if (!pids) - goto out; - - for (; *nr_pids < nr_ints; (*nr_pids)++) { - pids[*nr_pids] = find_get_pid(ints[*nr_pids]); - if (!pids[*nr_pids]) { - dbgfs_put_pids(pids, *nr_pids); - kfree(ints); - kfree(pids); - return NULL; - } - } - -out: - kfree(ints); - return pids; -} - -/* - * dbgfs_set_targets() - Set monitoring targets. - * @ctx: monitoring context - * @nr_targets: number of targets - * @pids: array of target pids (size is same to @nr_targets) - * - * This function should not be called while the kdamond is running. @pids is - * ignored if the context is not configured to have pid in each target. On - * failure, reference counts of all pids in @pids are decremented. - * - * Return: 0 on success, negative error code otherwise. - */ -static int dbgfs_set_targets(struct damon_ctx *ctx, ssize_t nr_targets, - struct pid **pids) -{ - ssize_t i; - struct damon_target *t, *next; - - damon_for_each_target_safe(t, next, ctx) { - if (damon_target_has_pid(ctx)) - put_pid(t->pid); - damon_destroy_target(t); - } - - for (i = 0; i < nr_targets; i++) { - t = damon_new_target(); - if (!t) { - damon_for_each_target_safe(t, next, ctx) - damon_destroy_target(t); - if (damon_target_has_pid(ctx)) - dbgfs_put_pids(pids, nr_targets); - return -ENOMEM; - } - if (damon_target_has_pid(ctx)) - t->pid = pids[i]; - damon_add_target(ctx, t); - } - - return 0; -} - -static ssize_t dbgfs_target_ids_write(struct file *file, - const char __user *buf, size_t count, loff_t *ppos) -{ - struct damon_ctx *ctx = file->private_data; - bool id_is_pid = true; - char *kbuf; - struct pid **target_pids = NULL; - ssize_t nr_targets; - ssize_t ret; - - kbuf = user_input_str(buf, count, ppos); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - - if (!strncmp(kbuf, "paddr\n", count)) { - id_is_pid = false; - nr_targets = 1; - } - - if (id_is_pid) { - target_pids = str_to_pids(kbuf, count, &nr_targets); - if (!target_pids) { - ret = -ENOMEM; - goto out; - } - } - - mutex_lock(&ctx->kdamond_lock); - if (ctx->kdamond) { - if (id_is_pid) - dbgfs_put_pids(target_pids, nr_targets); - ret = -EBUSY; - goto unlock_out; - } - - /* remove previously set targets */ - dbgfs_set_targets(ctx, 0, NULL); - if (!nr_targets) { - ret = count; - goto unlock_out; - } - - /* Configure the context for the address space type */ - if (id_is_pid) - ret = damon_select_ops(ctx, DAMON_OPS_VADDR); - else - ret = damon_select_ops(ctx, DAMON_OPS_PADDR); - if (ret) - goto unlock_out; - - ret = dbgfs_set_targets(ctx, nr_targets, target_pids); - if (!ret) - ret = count; - -unlock_out: - mutex_unlock(&ctx->kdamond_lock); - kfree(target_pids); -out: - kfree(kbuf); - return ret; -} - -static ssize_t sprint_init_regions(struct damon_ctx *c, char *buf, ssize_t len) -{ - struct damon_target *t; - struct damon_region *r; - int target_idx = 0; - int written = 0; - int rc; - - damon_for_each_target(t, c) { - damon_for_each_region(r, t) { - rc = scnprintf(&buf[written], len - written, - "%d %lu %lu\n", - target_idx, r->ar.start, r->ar.end); - if (!rc) - return -ENOMEM; - written += rc; - } - target_idx++; - } - return written; -} - -static ssize_t dbgfs_init_regions_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - struct damon_ctx *ctx = file->private_data; - char *kbuf; - ssize_t len; - - kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN); - if (!kbuf) - return -ENOMEM; - - mutex_lock(&ctx->kdamond_lock); - if (ctx->kdamond) { - mutex_unlock(&ctx->kdamond_lock); - len = -EBUSY; - goto out; - } - - len = sprint_init_regions(ctx, kbuf, count); - mutex_unlock(&ctx->kdamond_lock); - if (len < 0) - goto out; - len = simple_read_from_buffer(buf, count, ppos, kbuf, len); - -out: - kfree(kbuf); - return len; -} - -static int add_init_region(struct damon_ctx *c, int target_idx, - struct damon_addr_range *ar) -{ - struct damon_target *t; - struct damon_region *r, *prev; - unsigned long idx = 0; - int rc = -EINVAL; - - if (ar->start >= ar->end) - return -EINVAL; - - damon_for_each_target(t, c) { - if (idx++ == target_idx) { - r = damon_new_region(ar->start, ar->end); - if (!r) - return -ENOMEM; - damon_add_region(r, t); - if (damon_nr_regions(t) > 1) { - prev = damon_prev_region(r); - if (prev->ar.end > r->ar.start) { - damon_destroy_region(r, t); - return -EINVAL; - } - } - rc = 0; - } - } - return rc; -} - -static int set_init_regions(struct damon_ctx *c, const char *str, ssize_t len) -{ - struct damon_target *t; - struct damon_region *r, *next; - int pos = 0, parsed, ret; - int target_idx; - struct damon_addr_range ar; - int err; - - damon_for_each_target(t, c) { - damon_for_each_region_safe(r, next, t) - damon_destroy_region(r, t); - } - - while (pos < len) { - ret = sscanf(&str[pos], "%d %lu %lu%n", - &target_idx, &ar.start, &ar.end, &parsed); - if (ret != 3) - break; - err = add_init_region(c, target_idx, &ar); - if (err) - goto fail; - pos += parsed; - } - - return 0; - -fail: - damon_for_each_target(t, c) { - damon_for_each_region_safe(r, next, t) - damon_destroy_region(r, t); - } - return err; -} - -static ssize_t dbgfs_init_regions_write(struct file *file, - const char __user *buf, size_t count, - loff_t *ppos) -{ - struct damon_ctx *ctx = file->private_data; - char *kbuf; - ssize_t ret = count; - int err; - - kbuf = user_input_str(buf, count, ppos); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - - mutex_lock(&ctx->kdamond_lock); - if (ctx->kdamond) { - ret = -EBUSY; - goto unlock_out; - } - - err = set_init_regions(ctx, kbuf, ret); - if (err) - ret = err; - -unlock_out: - mutex_unlock(&ctx->kdamond_lock); - kfree(kbuf); - return ret; -} - -static ssize_t dbgfs_kdamond_pid_read(struct file *file, - char __user *buf, size_t count, loff_t *ppos) -{ - struct damon_ctx *ctx = file->private_data; - char *kbuf; - ssize_t len; - - kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN); - if (!kbuf) - return -ENOMEM; - - mutex_lock(&ctx->kdamond_lock); - if (ctx->kdamond) - len = scnprintf(kbuf, count, "%d\n", ctx->kdamond->pid); - else - len = scnprintf(kbuf, count, "none\n"); - mutex_unlock(&ctx->kdamond_lock); - if (!len) - goto out; - len = simple_read_from_buffer(buf, count, ppos, kbuf, len); - -out: - kfree(kbuf); - return len; -} - -static int damon_dbgfs_open(struct inode *inode, struct file *file) -{ - damon_dbgfs_warn_deprecation(); - - file->private_data = inode->i_private; - - return nonseekable_open(inode, file); -} - -static const struct file_operations attrs_fops = { - .open = damon_dbgfs_open, - .read = dbgfs_attrs_read, - .write = dbgfs_attrs_write, -}; - -static const struct file_operations schemes_fops = { - .open = damon_dbgfs_open, - .read = dbgfs_schemes_read, - .write = dbgfs_schemes_write, -}; - -static const struct file_operations target_ids_fops = { - .open = damon_dbgfs_open, - .read = dbgfs_target_ids_read, - .write = dbgfs_target_ids_write, -}; - -static const struct file_operations init_regions_fops = { - .open = damon_dbgfs_open, - .read = dbgfs_init_regions_read, - .write = dbgfs_init_regions_write, -}; - -static const struct file_operations kdamond_pid_fops = { - .open = damon_dbgfs_open, - .read = dbgfs_kdamond_pid_read, -}; - -static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx) -{ - const char * const file_names[] = {"attrs", "schemes", "target_ids", - "init_regions", "kdamond_pid"}; - const struct file_operations *fops[] = {&attrs_fops, &schemes_fops, - &target_ids_fops, &init_regions_fops, &kdamond_pid_fops}; - int i; - - for (i = 0; i < ARRAY_SIZE(file_names); i++) - debugfs_create_file(file_names[i], 0600, dir, ctx, fops[i]); -} - -static void dbgfs_before_terminate(struct damon_ctx *ctx) -{ - struct damon_target *t, *next; - - if (!damon_target_has_pid(ctx)) - return; - - mutex_lock(&ctx->kdamond_lock); - damon_for_each_target_safe(t, next, ctx) { - put_pid(t->pid); - damon_destroy_target(t); - } - mutex_unlock(&ctx->kdamond_lock); -} - -static struct damon_ctx *dbgfs_new_ctx(void) -{ - struct damon_ctx *ctx; - - ctx = damon_new_ctx(); - if (!ctx) - return NULL; - - if (damon_select_ops(ctx, DAMON_OPS_VADDR) && - damon_select_ops(ctx, DAMON_OPS_PADDR)) { - damon_destroy_ctx(ctx); - return NULL; - } - ctx->callback.before_terminate = dbgfs_before_terminate; - return ctx; -} - -static void dbgfs_destroy_ctx(struct damon_ctx *ctx) -{ - damon_destroy_ctx(ctx); -} - -static ssize_t damon_dbgfs_deprecated_read(struct file *file, - char __user *buf, size_t count, loff_t *ppos) -{ - static const char kbuf[512] = DAMON_DBGFS_DEPRECATION_NOTICE; - - return simple_read_from_buffer(buf, count, ppos, kbuf, strlen(kbuf)); -} - -/* - * Make a context of @name and create a debugfs directory for it. - * - * This function should be called while holding damon_dbgfs_lock. - * - * Returns 0 on success, negative error code otherwise. - */ -static int dbgfs_mk_context(char *name) -{ - struct dentry *root, **new_dirs, *new_dir; - struct damon_ctx **new_ctxs, *new_ctx; - - if (damon_nr_running_ctxs()) - return -EBUSY; - - new_ctxs = krealloc(dbgfs_ctxs, sizeof(*dbgfs_ctxs) * - (dbgfs_nr_ctxs + 1), GFP_KERNEL); - if (!new_ctxs) - return -ENOMEM; - dbgfs_ctxs = new_ctxs; - - new_dirs = krealloc(dbgfs_dirs, sizeof(*dbgfs_dirs) * - (dbgfs_nr_ctxs + 1), GFP_KERNEL); - if (!new_dirs) - return -ENOMEM; - dbgfs_dirs = new_dirs; - - root = dbgfs_dirs[0]; - if (!root) - return -ENOENT; - - new_dir = debugfs_create_dir(name, root); - /* Below check is required for a potential duplicated name case */ - if (IS_ERR(new_dir)) - return PTR_ERR(new_dir); - dbgfs_dirs[dbgfs_nr_ctxs] = new_dir; - - new_ctx = dbgfs_new_ctx(); - if (!new_ctx) { - debugfs_remove(new_dir); - dbgfs_dirs[dbgfs_nr_ctxs] = NULL; - return -ENOMEM; - } - - dbgfs_ctxs[dbgfs_nr_ctxs] = new_ctx; - dbgfs_fill_ctx_dir(dbgfs_dirs[dbgfs_nr_ctxs], - dbgfs_ctxs[dbgfs_nr_ctxs]); - dbgfs_nr_ctxs++; - - return 0; -} - -static ssize_t dbgfs_mk_context_write(struct file *file, - const char __user *buf, size_t count, loff_t *ppos) -{ - char *kbuf; - char *ctx_name; - ssize_t ret; - - kbuf = user_input_str(buf, count, ppos); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - ctx_name = kmalloc(count + 1, GFP_KERNEL); - if (!ctx_name) { - kfree(kbuf); - return -ENOMEM; - } - - /* Trim white space */ - if (sscanf(kbuf, "%s", ctx_name) != 1) { - ret = -EINVAL; - goto out; - } - - mutex_lock(&damon_dbgfs_lock); - ret = dbgfs_mk_context(ctx_name); - if (!ret) - ret = count; - mutex_unlock(&damon_dbgfs_lock); - -out: - kfree(kbuf); - kfree(ctx_name); - return ret; -} - -/* - * Remove a context of @name and its debugfs directory. - * - * This function should be called while holding damon_dbgfs_lock. - * - * Return 0 on success, negative error code otherwise. - */ -static int dbgfs_rm_context(char *name) -{ - struct dentry *root, *dir, **new_dirs; - struct inode *inode; - struct damon_ctx **new_ctxs; - int i, j; - int ret = 0; - - if (damon_nr_running_ctxs()) - return -EBUSY; - - root = dbgfs_dirs[0]; - if (!root) - return -ENOENT; - - dir = debugfs_lookup(name, root); - if (!dir) - return -ENOENT; - - inode = d_inode(dir); - if (!S_ISDIR(inode->i_mode)) { - ret = -EINVAL; - goto out_dput; - } - - new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs), - GFP_KERNEL); - if (!new_dirs) { - ret = -ENOMEM; - goto out_dput; - } - - new_ctxs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_ctxs), - GFP_KERNEL); - if (!new_ctxs) { - ret = -ENOMEM; - goto out_new_dirs; - } - - for (i = 0, j = 0; i < dbgfs_nr_ctxs; i++) { - if (dbgfs_dirs[i] == dir) { - debugfs_remove(dbgfs_dirs[i]); - dbgfs_destroy_ctx(dbgfs_ctxs[i]); - continue; - } - new_dirs[j] = dbgfs_dirs[i]; - new_ctxs[j++] = dbgfs_ctxs[i]; - } - - kfree(dbgfs_dirs); - kfree(dbgfs_ctxs); - - dbgfs_dirs = new_dirs; - dbgfs_ctxs = new_ctxs; - dbgfs_nr_ctxs--; - - goto out_dput; - -out_new_dirs: - kfree(new_dirs); -out_dput: - dput(dir); - return ret; -} - -static ssize_t dbgfs_rm_context_write(struct file *file, - const char __user *buf, size_t count, loff_t *ppos) -{ - char *kbuf; - ssize_t ret; - char *ctx_name; - - kbuf = user_input_str(buf, count, ppos); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - ctx_name = kmalloc(count + 1, GFP_KERNEL); - if (!ctx_name) { - kfree(kbuf); - return -ENOMEM; - } - - /* Trim white space */ - if (sscanf(kbuf, "%s", ctx_name) != 1) { - ret = -EINVAL; - goto out; - } - - mutex_lock(&damon_dbgfs_lock); - ret = dbgfs_rm_context(ctx_name); - if (!ret) - ret = count; - mutex_unlock(&damon_dbgfs_lock); - -out: - kfree(kbuf); - kfree(ctx_name); - return ret; -} - -static ssize_t dbgfs_monitor_on_read(struct file *file, - char __user *buf, size_t count, loff_t *ppos) -{ - char monitor_on_buf[5]; - bool monitor_on = damon_nr_running_ctxs() != 0; - int len; - - len = scnprintf(monitor_on_buf, 5, monitor_on ? "on\n" : "off\n"); - - return simple_read_from_buffer(buf, count, ppos, monitor_on_buf, len); -} - -static ssize_t dbgfs_monitor_on_write(struct file *file, - const char __user *buf, size_t count, loff_t *ppos) -{ - ssize_t ret; - char *kbuf; - - kbuf = user_input_str(buf, count, ppos); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - - /* Remove white space */ - if (sscanf(kbuf, "%s", kbuf) != 1) { - kfree(kbuf); - return -EINVAL; - } - - mutex_lock(&damon_dbgfs_lock); - if (!strncmp(kbuf, "on", count)) { - int i; - - for (i = 0; i < dbgfs_nr_ctxs; i++) { - if (damon_targets_empty(dbgfs_ctxs[i])) { - kfree(kbuf); - mutex_unlock(&damon_dbgfs_lock); - return -EINVAL; - } - } - ret = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs, true); - } else if (!strncmp(kbuf, "off", count)) { - ret = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); - } else { - ret = -EINVAL; - } - mutex_unlock(&damon_dbgfs_lock); - - if (!ret) - ret = count; - kfree(kbuf); - return ret; -} - -static int damon_dbgfs_static_file_open(struct inode *inode, struct file *file) -{ - damon_dbgfs_warn_deprecation(); - return nonseekable_open(inode, file); -} - -static const struct file_operations deprecated_fops = { - .read = damon_dbgfs_deprecated_read, -}; - -static const struct file_operations mk_contexts_fops = { - .open = damon_dbgfs_static_file_open, - .write = dbgfs_mk_context_write, -}; - -static const struct file_operations rm_contexts_fops = { - .open = damon_dbgfs_static_file_open, - .write = dbgfs_rm_context_write, -}; - -static const struct file_operations monitor_on_fops = { - .open = damon_dbgfs_static_file_open, - .read = dbgfs_monitor_on_read, - .write = dbgfs_monitor_on_write, -}; - -static int __init __damon_dbgfs_init(void) -{ - struct dentry *dbgfs_root; - const char * const file_names[] = {"mk_contexts", "rm_contexts", - "monitor_on_DEPRECATED", "DEPRECATED"}; - const struct file_operations *fops[] = {&mk_contexts_fops, - &rm_contexts_fops, &monitor_on_fops, &deprecated_fops}; - int i; - - dbgfs_root = debugfs_create_dir("damon", NULL); - - for (i = 0; i < ARRAY_SIZE(file_names); i++) - debugfs_create_file(file_names[i], 0600, dbgfs_root, NULL, - fops[i]); - dbgfs_fill_ctx_dir(dbgfs_root, dbgfs_ctxs[0]); - - dbgfs_dirs = kmalloc(sizeof(dbgfs_root), GFP_KERNEL); - if (!dbgfs_dirs) { - debugfs_remove(dbgfs_root); - return -ENOMEM; - } - dbgfs_dirs[0] = dbgfs_root; - - return 0; -} - -/* - * Functions for the initialization - */ - -static int __init damon_dbgfs_init(void) -{ - int rc = -ENOMEM; - - mutex_lock(&damon_dbgfs_lock); - dbgfs_ctxs = kmalloc(sizeof(*dbgfs_ctxs), GFP_KERNEL); - if (!dbgfs_ctxs) - goto out; - dbgfs_ctxs[0] = dbgfs_new_ctx(); - if (!dbgfs_ctxs[0]) { - kfree(dbgfs_ctxs); - goto out; - } - dbgfs_nr_ctxs = 1; - - rc = __damon_dbgfs_init(); - if (rc) { - kfree(dbgfs_ctxs[0]); - kfree(dbgfs_ctxs); - pr_err("%s: dbgfs init failed\n", __func__); - } - -out: - mutex_unlock(&damon_dbgfs_lock); - return rc; -} - -module_init(damon_dbgfs_init); - -#include "tests/dbgfs-kunit.h" diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index a9ff35341d65..0f9ae14f884d 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -198,7 +198,7 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) return max_nr_accesses; } -static bool __damos_pa_filter_out(struct damos_filter *filter, +static bool damos_pa_filter_match(struct damos_filter *filter, struct folio *folio) { bool matched = false; @@ -237,13 +237,14 @@ static bool damos_pa_filter_out(struct damos *scheme, struct folio *folio) struct damos_filter *filter; damos_for_each_filter(filter, scheme) { - if (__damos_pa_filter_out(filter, folio)) - return true; + if (damos_pa_filter_match(filter, folio)) + return !filter->allow; } return false; } -static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s) +static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s, + unsigned long *sz_filter_passed) { unsigned long addr, applied; LIST_HEAD(folio_list); @@ -258,7 +259,8 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s) } } if (install_young_filter) { - filter = damos_new_filter(DAMOS_FILTER_TYPE_YOUNG, true); + filter = damos_new_filter( + DAMOS_FILTER_TYPE_YOUNG, true, false); if (!filter) return 0; damos_add_filter(s, filter); @@ -272,6 +274,8 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s) if (damos_pa_filter_out(s, folio)) goto put_folio; + else + *sz_filter_passed += folio_size(folio); folio_clear_referenced(folio); folio_test_clear_young(folio); @@ -292,7 +296,8 @@ put_folio: } static inline unsigned long damon_pa_mark_accessed_or_deactivate( - struct damon_region *r, struct damos *s, bool mark_accessed) + struct damon_region *r, struct damos *s, bool mark_accessed, + unsigned long *sz_filter_passed) { unsigned long addr, applied = 0; @@ -304,6 +309,8 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate( if (damos_pa_filter_out(s, folio)) goto put_folio; + else + *sz_filter_passed += folio_size(folio); if (mark_accessed) folio_mark_accessed(folio); @@ -317,15 +324,17 @@ put_folio: } static unsigned long damon_pa_mark_accessed(struct damon_region *r, - struct damos *s) + struct damos *s, unsigned long *sz_filter_passed) { - return damon_pa_mark_accessed_or_deactivate(r, s, true); + return damon_pa_mark_accessed_or_deactivate(r, s, true, + sz_filter_passed); } static unsigned long damon_pa_deactivate_pages(struct damon_region *r, - struct damos *s) + struct damos *s, unsigned long *sz_filter_passed) { - return damon_pa_mark_accessed_or_deactivate(r, s, false); + return damon_pa_mark_accessed_or_deactivate(r, s, false, + sz_filter_passed); } static unsigned int __damon_pa_migrate_folio_list( @@ -449,7 +458,8 @@ static unsigned long damon_pa_migrate_pages(struct list_head *folio_list, return nr_migrated; } -static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s) +static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s, + unsigned long *sz_filter_passed) { unsigned long addr, applied; LIST_HEAD(folio_list); @@ -462,6 +472,8 @@ static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s) if (damos_pa_filter_out(s, folio)) goto put_folio; + else + *sz_filter_passed += folio_size(folio); if (!folio_isolate_lru(folio)) goto put_folio; @@ -474,23 +486,57 @@ put_folio: return applied * PAGE_SIZE; } +static bool damon_pa_scheme_has_filter(struct damos *s) +{ + struct damos_filter *f; + + damos_for_each_filter(f, s) + return true; + return false; +} + +static unsigned long damon_pa_stat(struct damon_region *r, struct damos *s, + unsigned long *sz_filter_passed) +{ + unsigned long addr; + LIST_HEAD(folio_list); + + if (!damon_pa_scheme_has_filter(s)) + return 0; + + addr = r->ar.start; + while (addr < r->ar.end) { + struct folio *folio = damon_get_folio(PHYS_PFN(addr)); + + if (!folio) { + addr += PAGE_SIZE; + continue; + } + + if (!damos_pa_filter_out(s, folio)) + *sz_filter_passed += folio_size(folio); + addr += folio_size(folio); + folio_put(folio); + } + return 0; +} static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, - struct damos *scheme) + struct damos *scheme, unsigned long *sz_filter_passed) { switch (scheme->action) { case DAMOS_PAGEOUT: - return damon_pa_pageout(r, scheme); + return damon_pa_pageout(r, scheme, sz_filter_passed); case DAMOS_LRU_PRIO: - return damon_pa_mark_accessed(r, scheme); + return damon_pa_mark_accessed(r, scheme, sz_filter_passed); case DAMOS_LRU_DEPRIO: - return damon_pa_deactivate_pages(r, scheme); + return damon_pa_deactivate_pages(r, scheme, sz_filter_passed); case DAMOS_MIGRATE_HOT: case DAMOS_MIGRATE_COLD: - return damon_pa_migrate(r, scheme); + return damon_pa_migrate(r, scheme, sz_filter_passed); case DAMOS_STAT: - break; + return damon_pa_stat(r, scheme, sz_filter_passed); default: /* DAMOS actions that not yet supported by 'paddr'. */ break; diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 9e0077a9404e..a675150965e0 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -221,7 +221,7 @@ static int damon_reclaim_apply_parameters(void) } if (skip_anon) { - filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true); + filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true, false); if (!filter) goto out; damos_add_filter(scheme, filter); diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h index 9a18f3c535d3..70d84bdc9f5f 100644 --- a/mm/damon/sysfs-common.h +++ b/mm/damon/sysfs-common.h @@ -45,19 +45,13 @@ void damon_sysfs_schemes_update_stats( struct damon_sysfs_schemes *sysfs_schemes, struct damon_ctx *ctx); -int damon_sysfs_schemes_update_regions_start( - struct damon_sysfs_schemes *sysfs_schemes, - struct damon_ctx *ctx, bool total_bytes_only); - -void damos_sysfs_mark_finished_regions_updates(struct damon_ctx *ctx); - -bool damos_sysfs_regions_upd_done(void); - -int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx); +void damos_sysfs_populate_region_dir(struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx, struct damon_target *t, + struct damon_region *r, struct damos *s, + bool total_bytes_only, unsigned long sz_filter_passed); int damon_sysfs_schemes_clear_regions( - struct damon_sysfs_schemes *sysfs_schemes, - struct damon_ctx *ctx); + struct damon_sysfs_schemes *sysfs_schemes); int damos_sysfs_set_quota_scores(struct damon_sysfs_schemes *sysfs_schemes, struct damon_ctx *ctx); diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index b095457380b5..98f93ae9f59e 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -19,6 +19,7 @@ struct damon_sysfs_scheme_region { struct damon_addr_range ar; unsigned int nr_accesses; unsigned int age; + unsigned long sz_filter_passed; struct list_head list; }; @@ -74,6 +75,15 @@ static ssize_t age_show(struct kobject *kobj, struct kobj_attribute *attr, return sysfs_emit(buf, "%u\n", region->age); } +static ssize_t sz_filter_passed_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_scheme_region *region = container_of(kobj, + struct damon_sysfs_scheme_region, kobj); + + return sysfs_emit(buf, "%lu\n", region->sz_filter_passed); +} + static void damon_sysfs_scheme_region_release(struct kobject *kobj) { struct damon_sysfs_scheme_region *region = container_of(kobj, @@ -95,11 +105,15 @@ static struct kobj_attribute damon_sysfs_scheme_region_nr_accesses_attr = static struct kobj_attribute damon_sysfs_scheme_region_age_attr = __ATTR_RO_MODE(age, 0400); +static struct kobj_attribute damon_sysfs_scheme_region_sz_filter_passed_attr = + __ATTR_RO_MODE(sz_filter_passed, 0400); + static struct attribute *damon_sysfs_scheme_region_attrs[] = { &damon_sysfs_scheme_region_start_attr.attr, &damon_sysfs_scheme_region_end_attr.attr, &damon_sysfs_scheme_region_nr_accesses_attr.attr, &damon_sysfs_scheme_region_age_attr.attr, + &damon_sysfs_scheme_region_sz_filter_passed_attr.attr, NULL, }; ATTRIBUTE_GROUPS(damon_sysfs_scheme_region); @@ -114,55 +128,11 @@ static const struct kobj_type damon_sysfs_scheme_region_ktype = { * scheme regions directory */ -/* - * enum damos_sysfs_regions_upd_status - Represent DAMOS tried regions update - * status - * @DAMOS_TRIED_REGIONS_UPD_IDLE: Waiting for next request. - * @DAMOS_TRIED_REGIONS_UPD_STARTED: Update started. - * @DAMOS_TRIED_REGIONS_UPD_FINISHED: Update finished. - * - * Each DAMON-based operation scheme (&struct damos) has its own apply - * interval, and we need to expose the scheme tried regions based on only - * single snapshot. For this, we keep the tried regions update status for each - * scheme. The status becomes 'idle' at the beginning. - * - * Once the tried regions update request is received, the request handling - * start function (damon_sysfs_scheme_update_regions_start()) sets the status - * of all schemes as 'idle' again, and register ->before_damos_apply() - * callback. - * - * Then, the first followup ->before_damos_apply() callback - * (damon_sysfs_before_damos_apply()) sets the status 'started'. The first - * ->after_sampling() or ->after_aggregation() callback - * (damon_sysfs_cmd_request_callback()) after the call is called only after - * the scheme is completely applied to the given snapshot. Hence the callback - * knows the situation by showing 'started' status, and sets the status as - * 'finished'. Then, damon_sysfs_before_damos_apply() understands the - * situation by showing the 'finished' status and do nothing. - * - * If DAMOS is not applied to any region due to any reasons including the - * access pattern, the watermarks, the quotas, and the filters, - * ->before_damos_apply() will not be called back. Until the situation is - * changed, the update will not be finished. To avoid this, - * damon_sysfs_after_sampling() set the status as 'finished' if more than two - * apply intervals of the scheme is passed while the state is 'idle'. - * - * Finally, the tried regions request handling finisher function - * (damon_sysfs_schemes_update_regions_stop()) unregisters the callbacks. - */ -enum damos_sysfs_regions_upd_status { - DAMOS_TRIED_REGIONS_UPD_IDLE, - DAMOS_TRIED_REGIONS_UPD_STARTED, - DAMOS_TRIED_REGIONS_UPD_FINISHED, -}; - struct damon_sysfs_scheme_regions { struct kobject kobj; struct list_head regions_list; int nr_regions; unsigned long total_bytes; - enum damos_sysfs_regions_upd_status upd_status; - unsigned long upd_timeout_jiffies; }; static struct damon_sysfs_scheme_regions * @@ -178,7 +148,6 @@ damon_sysfs_scheme_regions_alloc(void) INIT_LIST_HEAD(®ions->regions_list); regions->nr_regions = 0; regions->total_bytes = 0; - regions->upd_status = DAMOS_TRIED_REGIONS_UPD_IDLE; return regions; } @@ -233,6 +202,7 @@ struct damon_sysfs_stats { unsigned long sz_tried; unsigned long nr_applied; unsigned long sz_applied; + unsigned long sz_ops_filter_passed; unsigned long qt_exceeds; }; @@ -277,6 +247,15 @@ static ssize_t sz_applied_show(struct kobject *kobj, return sysfs_emit(buf, "%lu\n", stats->sz_applied); } +static ssize_t sz_ops_filter_passed_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_stats *stats = container_of(kobj, + struct damon_sysfs_stats, kobj); + + return sysfs_emit(buf, "%lu\n", stats->sz_ops_filter_passed); +} + static ssize_t qt_exceeds_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -303,6 +282,9 @@ static struct kobj_attribute damon_sysfs_stats_nr_applied_attr = static struct kobj_attribute damon_sysfs_stats_sz_applied_attr = __ATTR_RO_MODE(sz_applied, 0400); +static struct kobj_attribute damon_sysfs_stats_sz_ops_filter_passed_attr = + __ATTR_RO_MODE(sz_ops_filter_passed, 0400); + static struct kobj_attribute damon_sysfs_stats_qt_exceeds_attr = __ATTR_RO_MODE(qt_exceeds, 0400); @@ -311,6 +293,7 @@ static struct attribute *damon_sysfs_stats_attrs[] = { &damon_sysfs_stats_sz_tried_attr.attr, &damon_sysfs_stats_nr_applied_attr.attr, &damon_sysfs_stats_sz_applied_attr.attr, + &damon_sysfs_stats_sz_ops_filter_passed_attr.attr, &damon_sysfs_stats_qt_exceeds_attr.attr, NULL, }; @@ -330,6 +313,7 @@ struct damon_sysfs_scheme_filter { struct kobject kobj; enum damos_filter_type type; bool matching; + bool allow; char *memcg_path; struct damon_addr_range addr_range; int target_idx; @@ -402,6 +386,30 @@ static ssize_t matching_store(struct kobject *kobj, return count; } +static ssize_t allow_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_scheme_filter *filter = container_of(kobj, + struct damon_sysfs_scheme_filter, kobj); + + return sysfs_emit(buf, "%c\n", filter->allow ? 'Y' : 'N'); +} + +static ssize_t allow_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_scheme_filter *filter = container_of(kobj, + struct damon_sysfs_scheme_filter, kobj); + bool allow; + int err = kstrtobool(buf, &allow); + + if (err) + return err; + + filter->allow = allow; + return count; +} + static ssize_t memcg_path_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -499,6 +507,9 @@ static struct kobj_attribute damon_sysfs_scheme_filter_type_attr = static struct kobj_attribute damon_sysfs_scheme_filter_matching_attr = __ATTR_RW_MODE(matching, 0600); +static struct kobj_attribute damon_sysfs_scheme_filter_allow_attr = + __ATTR_RW_MODE(allow, 0600); + static struct kobj_attribute damon_sysfs_scheme_filter_memcg_path_attr = __ATTR_RW_MODE(memcg_path, 0600); @@ -514,6 +525,7 @@ static struct kobj_attribute damon_sysfs_scheme_filter_damon_target_idx_attr = static struct attribute *damon_sysfs_scheme_filter_attrs[] = { &damon_sysfs_scheme_filter_type_attr.attr, &damon_sysfs_scheme_filter_matching_attr.attr, + &damon_sysfs_scheme_filter_allow_attr.attr, &damon_sysfs_scheme_filter_memcg_path_attr.attr, &damon_sysfs_scheme_filter_addr_start_attr.attr, &damon_sysfs_scheme_filter_addr_end_attr.attr, @@ -1918,7 +1930,8 @@ static int damon_sysfs_add_scheme_filters(struct damos *scheme, sysfs_filters->filters_arr[i]; struct damos_filter *filter = damos_new_filter(sysfs_filter->type, - sysfs_filter->matching); + sysfs_filter->matching, + sysfs_filter->allow); int err; if (!filter) @@ -2122,32 +2135,32 @@ void damon_sysfs_schemes_update_stats( sysfs_stats->sz_tried = scheme->stat.sz_tried; sysfs_stats->nr_applied = scheme->stat.nr_applied; sysfs_stats->sz_applied = scheme->stat.sz_applied; + sysfs_stats->sz_ops_filter_passed = + scheme->stat.sz_ops_filter_passed; sysfs_stats->qt_exceeds = scheme->stat.qt_exceeds; } } -/* - * damon_sysfs_schemes that need to update its schemes regions dir. Protected - * by damon_sysfs_lock +/** + * damos_sysfs_populate_region_dir() - Populate a schemes tried region dir. + * @sysfs_schemes: Schemes directory to populate regions directory. + * @ctx: Corresponding DAMON context. + * @t: DAMON target of @r. + * @r: DAMON region to populate the directory for. + * @s: Corresponding scheme. + * @total_bytes_only: Whether the request is for bytes update only. + * @sz_filter_passed: Bytes of @r that passed filters of @s. + * + * Called from DAMOS walk callback while holding damon_sysfs_lock. */ -static struct damon_sysfs_schemes *damon_sysfs_schemes_for_damos_callback; -static int damon_sysfs_schemes_region_idx; -static bool damos_regions_upd_total_bytes_only; - -/* - * DAMON callback that called before damos apply. While this callback is - * registered, damon_sysfs_lock should be held to ensure the regions - * directories exist. - */ -static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx, - struct damon_target *t, struct damon_region *r, - struct damos *s) +void damos_sysfs_populate_region_dir(struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx, struct damon_target *t, + struct damon_region *r, struct damos *s, bool total_bytes_only, + unsigned long sz_filter_passed) { struct damos *scheme; struct damon_sysfs_scheme_regions *sysfs_regions; struct damon_sysfs_scheme_region *region; - struct damon_sysfs_schemes *sysfs_schemes = - damon_sysfs_schemes_for_damos_callback; int schemes_idx = 0; damon_for_each_scheme(scheme, ctx) { @@ -2158,152 +2171,40 @@ static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx, /* user could have removed the scheme sysfs dir */ if (schemes_idx >= sysfs_schemes->nr) - return 0; + return; sysfs_regions = sysfs_schemes->schemes_arr[schemes_idx]->tried_regions; - if (sysfs_regions->upd_status == DAMOS_TRIED_REGIONS_UPD_FINISHED) - return 0; - if (sysfs_regions->upd_status == DAMOS_TRIED_REGIONS_UPD_IDLE) - sysfs_regions->upd_status = DAMOS_TRIED_REGIONS_UPD_STARTED; sysfs_regions->total_bytes += r->ar.end - r->ar.start; - if (damos_regions_upd_total_bytes_only) - return 0; + if (total_bytes_only) + return; region = damon_sysfs_scheme_region_alloc(r); if (!region) - return 0; + return; + region->sz_filter_passed = sz_filter_passed; list_add_tail(®ion->list, &sysfs_regions->regions_list); sysfs_regions->nr_regions++; if (kobject_init_and_add(®ion->kobj, &damon_sysfs_scheme_region_ktype, &sysfs_regions->kobj, "%d", - damon_sysfs_schemes_region_idx++)) { + sysfs_regions->nr_regions++)) { kobject_put(®ion->kobj); } - return 0; -} - -/* - * DAMON callback that called after each accesses sampling. While this - * callback is registered, damon_sysfs_lock should be held to ensure the - * regions directories exist. - */ -void damos_sysfs_mark_finished_regions_updates(struct damon_ctx *ctx) -{ - struct damon_sysfs_schemes *sysfs_schemes = - damon_sysfs_schemes_for_damos_callback; - struct damon_sysfs_scheme_regions *sysfs_regions; - int i; - - for (i = 0; i < sysfs_schemes->nr; i++) { - sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions; - if (sysfs_regions->upd_status == - DAMOS_TRIED_REGIONS_UPD_STARTED || - time_after(jiffies, - sysfs_regions->upd_timeout_jiffies)) - sysfs_regions->upd_status = - DAMOS_TRIED_REGIONS_UPD_FINISHED; - } } /* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */ int damon_sysfs_schemes_clear_regions( - struct damon_sysfs_schemes *sysfs_schemes, - struct damon_ctx *ctx) + struct damon_sysfs_schemes *sysfs_schemes) { - struct damos *scheme; - int schemes_idx = 0; + int i; - damon_for_each_scheme(scheme, ctx) { + for (i = 0; i < sysfs_schemes->nr; i++) { struct damon_sysfs_scheme *sysfs_scheme; - /* user could have removed the scheme sysfs dir */ - if (schemes_idx >= sysfs_schemes->nr) - break; - - sysfs_scheme = sysfs_schemes->schemes_arr[schemes_idx++]; + sysfs_scheme = sysfs_schemes->schemes_arr[i]; damon_sysfs_scheme_regions_rm_dirs( sysfs_scheme->tried_regions); sysfs_scheme->tried_regions->total_bytes = 0; } return 0; } - -static struct damos *damos_sysfs_nth_scheme(int n, struct damon_ctx *ctx) -{ - struct damos *scheme; - int i = 0; - - damon_for_each_scheme(scheme, ctx) { - if (i == n) - return scheme; - i++; - } - return NULL; -} - -static void damos_tried_regions_init_upd_status( - struct damon_sysfs_schemes *sysfs_schemes, - struct damon_ctx *ctx) -{ - int i; - struct damos *scheme; - struct damon_sysfs_scheme_regions *sysfs_regions; - - for (i = 0; i < sysfs_schemes->nr; i++) { - sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions; - scheme = damos_sysfs_nth_scheme(i, ctx); - if (!scheme) { - sysfs_regions->upd_status = - DAMOS_TRIED_REGIONS_UPD_FINISHED; - continue; - } - sysfs_regions->upd_status = DAMOS_TRIED_REGIONS_UPD_IDLE; - sysfs_regions->upd_timeout_jiffies = jiffies + - 2 * usecs_to_jiffies(scheme->apply_interval_us ? - scheme->apply_interval_us : - ctx->attrs.aggr_interval); - } -} - -/* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */ -int damon_sysfs_schemes_update_regions_start( - struct damon_sysfs_schemes *sysfs_schemes, - struct damon_ctx *ctx, bool total_bytes_only) -{ - damon_sysfs_schemes_clear_regions(sysfs_schemes, ctx); - damon_sysfs_schemes_for_damos_callback = sysfs_schemes; - damos_tried_regions_init_upd_status(sysfs_schemes, ctx); - damos_regions_upd_total_bytes_only = total_bytes_only; - ctx->callback.before_damos_apply = damon_sysfs_before_damos_apply; - return 0; -} - -bool damos_sysfs_regions_upd_done(void) -{ - struct damon_sysfs_schemes *sysfs_schemes = - damon_sysfs_schemes_for_damos_callback; - struct damon_sysfs_scheme_regions *sysfs_regions; - int i; - - for (i = 0; i < sysfs_schemes->nr; i++) { - sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions; - if (sysfs_regions->upd_status != - DAMOS_TRIED_REGIONS_UPD_FINISHED) - return false; - } - return true; -} - -/* - * Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock. Caller - * should unlock damon_sysfs_lock which held before - * damon_sysfs_schemes_update_regions_start() - */ -int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx) -{ - damon_sysfs_schemes_for_damos_callback = NULL; - ctx->callback.before_damos_apply = NULL; - damon_sysfs_schemes_region_idx = 0; - return 0; -} diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 58145d59881d..deeab04d3b46 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1181,25 +1181,9 @@ static int damon_sysfs_add_targets(struct damon_ctx *ctx, return 0; } -static bool damon_sysfs_schemes_regions_updating; - static void damon_sysfs_before_terminate(struct damon_ctx *ctx) { struct damon_target *t, *next; - struct damon_sysfs_kdamond *kdamond; - enum damon_sysfs_cmd cmd; - - /* damon_sysfs_schemes_update_regions_stop() might not yet called */ - kdamond = damon_sysfs_cmd_request.kdamond; - cmd = damon_sysfs_cmd_request.cmd; - if (kdamond && ctx == kdamond->damon_ctx && - (cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS || - cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES) && - damon_sysfs_schemes_regions_updating) { - damon_sysfs_schemes_update_regions_stop(ctx); - damon_sysfs_schemes_regions_updating = false; - mutex_unlock(&damon_sysfs_lock); - } if (!damon_target_has_pid(ctx)) return; @@ -1214,57 +1198,24 @@ static void damon_sysfs_before_terminate(struct damon_ctx *ctx) /* * damon_sysfs_upd_schemes_stats() - Update schemes stats sysfs files. - * @kdamond: The kobject wrapper that associated to the kdamond thread. + * @data: The kobject wrapper that associated to the kdamond thread. * * This function reads the schemes stats of specific kdamond and update the * related values for sysfs files. This function should be called from DAMON - * callbacks while holding ``damon_syfs_lock``, to safely access the DAMON - * contexts-internal data and DAMON sysfs variables. + * worker thread,to safely access the DAMON contexts-internal data. Caller + * should also ensure holding ``damon_syfs_lock``, and ->damon_ctx of @data is + * not NULL but a valid pointer, to safely access DAMON sysfs variables. */ -static int damon_sysfs_upd_schemes_stats(struct damon_sysfs_kdamond *kdamond) +static int damon_sysfs_upd_schemes_stats(void *data) { + struct damon_sysfs_kdamond *kdamond = data; struct damon_ctx *ctx = kdamond->damon_ctx; - if (!ctx) - return -EINVAL; damon_sysfs_schemes_update_stats( kdamond->contexts->contexts_arr[0]->schemes, ctx); return 0; } -static int damon_sysfs_upd_schemes_regions_start( - struct damon_sysfs_kdamond *kdamond, bool total_bytes_only) -{ - struct damon_ctx *ctx = kdamond->damon_ctx; - - if (!ctx) - return -EINVAL; - return damon_sysfs_schemes_update_regions_start( - kdamond->contexts->contexts_arr[0]->schemes, ctx, - total_bytes_only); -} - -static int damon_sysfs_upd_schemes_regions_stop( - struct damon_sysfs_kdamond *kdamond) -{ - struct damon_ctx *ctx = kdamond->damon_ctx; - - if (!ctx) - return -EINVAL; - return damon_sysfs_schemes_update_regions_stop(ctx); -} - -static int damon_sysfs_clear_schemes_regions( - struct damon_sysfs_kdamond *kdamond) -{ - struct damon_ctx *ctx = kdamond->damon_ctx; - - if (!ctx) - return -EINVAL; - return damon_sysfs_schemes_clear_regions( - kdamond->contexts->contexts_arr[0]->schemes, ctx); -} - static inline bool damon_sysfs_kdamond_running( struct damon_sysfs_kdamond *kdamond) { @@ -1318,9 +1269,9 @@ static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond) return err; } -static int damon_sysfs_commit_schemes_quota_goals( - struct damon_sysfs_kdamond *sysfs_kdamond) +static int damon_sysfs_commit_schemes_quota_goals(void *data) { + struct damon_sysfs_kdamond *sysfs_kdamond = data; struct damon_ctx *ctx; struct damon_sysfs_context *sysfs_ctx; @@ -1338,20 +1289,18 @@ static int damon_sysfs_commit_schemes_quota_goals( /* * damon_sysfs_upd_schemes_effective_quotas() - Update schemes effective quotas * sysfs files. - * @kdamond: The kobject wrapper that associated to the kdamond thread. + * @data: The kobject wrapper that associated to the kdamond thread. * * This function reads the schemes' effective quotas of specific kdamond and * update the related values for sysfs files. This function should be called * from DAMON callbacks while holding ``damon_syfs_lock``, to safely access the * DAMON contexts-internal data and DAMON sysfs variables. */ -static int damon_sysfs_upd_schemes_effective_quotas( - struct damon_sysfs_kdamond *kdamond) +static int damon_sysfs_upd_schemes_effective_quotas(void *data) { + struct damon_sysfs_kdamond *kdamond = data; struct damon_ctx *ctx = kdamond->damon_ctx; - if (!ctx) - return -EINVAL; damos_sysfs_update_effective_quotas( kdamond->contexts->contexts_arr[0]->schemes, ctx); return 0; @@ -1371,67 +1320,27 @@ static int damon_sysfs_cmd_request_callback(struct damon_ctx *c, bool active, bool after_aggregation) { struct damon_sysfs_kdamond *kdamond; - bool total_bytes_only = false; int err = 0; /* avoid deadlock due to concurrent state_store('off') */ - if (!damon_sysfs_schemes_regions_updating && - !mutex_trylock(&damon_sysfs_lock)) + if (!mutex_trylock(&damon_sysfs_lock)) return 0; kdamond = damon_sysfs_cmd_request.kdamond; if (!kdamond || kdamond->damon_ctx != c) goto out; switch (damon_sysfs_cmd_request.cmd) { - case DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS: - err = damon_sysfs_upd_schemes_stats(kdamond); - break; case DAMON_SYSFS_CMD_COMMIT: if (!after_aggregation) goto out; err = damon_sysfs_commit_input(kdamond); break; - case DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS: - err = damon_sysfs_commit_schemes_quota_goals(kdamond); - break; - case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES: - total_bytes_only = true; - fallthrough; - case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS: - if (!damon_sysfs_schemes_regions_updating) { - err = damon_sysfs_upd_schemes_regions_start(kdamond, - total_bytes_only); - if (!err) { - damon_sysfs_schemes_regions_updating = true; - goto keep_lock_out; - } - } else { - damos_sysfs_mark_finished_regions_updates(c); - /* - * Continue regions updating if DAMON is till - * active and the update for all schemes is not - * finished. - */ - if (active && !damos_sysfs_regions_upd_done()) - goto keep_lock_out; - err = damon_sysfs_upd_schemes_regions_stop(kdamond); - damon_sysfs_schemes_regions_updating = false; - } - break; - case DAMON_SYSFS_CMD_CLEAR_SCHEMES_TRIED_REGIONS: - err = damon_sysfs_clear_schemes_regions(kdamond); - break; - case DAMON_SYSFS_CMD_UPDATE_SCHEMES_EFFECTIVE_QUOTAS: - err = damon_sysfs_upd_schemes_effective_quotas(kdamond); - break; default: break; } /* Mark the request as invalid now. */ damon_sysfs_cmd_request.kdamond = NULL; out: - if (!damon_sysfs_schemes_regions_updating) - mutex_unlock(&damon_sysfs_lock); -keep_lock_out: + mutex_unlock(&damon_sysfs_lock); return err; } @@ -1525,6 +1434,58 @@ static int damon_sysfs_turn_damon_off(struct damon_sysfs_kdamond *kdamond) */ } +static int damon_sysfs_damon_call(int (*fn)(void *data), + struct damon_sysfs_kdamond *kdamond) +{ + struct damon_call_control call_control = {}; + + if (!kdamond->damon_ctx) + return -EINVAL; + call_control.fn = fn; + call_control.data = kdamond; + return damon_call(kdamond->damon_ctx, &call_control); +} + +struct damon_sysfs_schemes_walk_data { + struct damon_sysfs_kdamond *sysfs_kdamond; + bool total_bytes_only; +}; + +/* populate the region directory */ +static void damon_sysfs_schemes_tried_regions_upd_one(void *data, struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + struct damos *s, unsigned long sz_filter_passed) +{ + struct damon_sysfs_schemes_walk_data *walk_data = data; + struct damon_sysfs_kdamond *sysfs_kdamond = walk_data->sysfs_kdamond; + + damos_sysfs_populate_region_dir( + sysfs_kdamond->contexts->contexts_arr[0]->schemes, + ctx, t, r, s, walk_data->total_bytes_only, + sz_filter_passed); +} + +static int damon_sysfs_update_schemes_tried_regions( + struct damon_sysfs_kdamond *sysfs_kdamond, bool total_bytes_only) +{ + struct damon_sysfs_schemes_walk_data walk_data = { + .sysfs_kdamond = sysfs_kdamond, + .total_bytes_only = total_bytes_only, + }; + struct damos_walk_control control = { + .walk_fn = damon_sysfs_schemes_tried_regions_upd_one, + .data = &walk_data, + }; + struct damon_ctx *ctx = sysfs_kdamond->damon_ctx; + + if (!ctx) + return -EINVAL; + + damon_sysfs_schemes_clear_regions( + sysfs_kdamond->contexts->contexts_arr[0]->schemes); + return damos_walk(ctx, &control); +} + /* * damon_sysfs_handle_cmd() - Handle a command for a specific kdamond. * @cmd: The command to handle. @@ -1543,12 +1504,29 @@ static int damon_sysfs_handle_cmd(enum damon_sysfs_cmd cmd, { bool need_wait = true; - /* Handle commands that doesn't access DAMON context-internal data */ switch (cmd) { case DAMON_SYSFS_CMD_ON: return damon_sysfs_turn_damon_on(kdamond); case DAMON_SYSFS_CMD_OFF: return damon_sysfs_turn_damon_off(kdamond); + case DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS: + return damon_sysfs_damon_call( + damon_sysfs_commit_schemes_quota_goals, + kdamond); + case DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS: + return damon_sysfs_damon_call( + damon_sysfs_upd_schemes_stats, kdamond); + case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES: + return damon_sysfs_update_schemes_tried_regions(kdamond, true); + case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS: + return damon_sysfs_update_schemes_tried_regions(kdamond, false); + case DAMON_SYSFS_CMD_CLEAR_SCHEMES_TRIED_REGIONS: + return damon_sysfs_schemes_clear_regions( + kdamond->contexts->contexts_arr[0]->schemes); + case DAMON_SYSFS_CMD_UPDATE_SCHEMES_EFFECTIVE_QUOTAS: + return damon_sysfs_damon_call( + damon_sysfs_upd_schemes_effective_quotas, + kdamond); default: break; } diff --git a/mm/damon/tests/.kunitconfig b/mm/damon/tests/.kunitconfig index a73be044fc9b..36a450f57b58 100644 --- a/mm/damon/tests/.kunitconfig +++ b/mm/damon/tests/.kunitconfig @@ -13,10 +13,3 @@ CONFIG_DAMON_VADDR_KUNIT_TEST=y CONFIG_SYSFS=y CONFIG_DAMON_SYSFS=y CONFIG_DAMON_SYSFS_KUNIT_TEST=y - -# for DAMON debugfs interface -CONFIG_DEBUG_FS=y -CONFIG_DAMON_PADDR=y -CONFIG_DAMON_DBGFS_DEPRECATED=y -CONFIG_DAMON_DBGFS=y -CONFIG_DAMON_DBGFS_KUNIT_TEST=y diff --git a/mm/damon/tests/core-kunit.h b/mm/damon/tests/core-kunit.h index cf22e09a3507..532c6a6f21f9 100644 --- a/mm/damon/tests/core-kunit.h +++ b/mm/damon/tests/core-kunit.h @@ -411,7 +411,7 @@ static void damos_test_new_filter(struct kunit *test) { struct damos_filter *filter; - filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true); + filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true, false); KUNIT_EXPECT_EQ(test, filter->type, DAMOS_FILTER_TYPE_ANON); KUNIT_EXPECT_EQ(test, filter->matching, true); KUNIT_EXPECT_PTR_EQ(test, filter->list.prev, &filter->list); @@ -425,7 +425,7 @@ static void damos_test_filter_out(struct kunit *test) struct damon_region *r, *r2; struct damos_filter *f; - f = damos_new_filter(DAMOS_FILTER_TYPE_ADDR, true); + f = damos_new_filter(DAMOS_FILTER_TYPE_ADDR, true, false); f->addr_range = (struct damon_addr_range){ .start = DAMON_MIN_REGION * 2, .end = DAMON_MIN_REGION * 6}; @@ -434,25 +434,25 @@ static void damos_test_filter_out(struct kunit *test) damon_add_region(r, t); /* region in the range */ - KUNIT_EXPECT_TRUE(test, __damos_filter_out(NULL, t, r, f)); + KUNIT_EXPECT_TRUE(test, damos_filter_match(NULL, t, r, f)); KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1); /* region before the range */ r->ar.start = DAMON_MIN_REGION * 1; r->ar.end = DAMON_MIN_REGION * 2; - KUNIT_EXPECT_FALSE(test, __damos_filter_out(NULL, t, r, f)); + KUNIT_EXPECT_FALSE(test, damos_filter_match(NULL, t, r, f)); KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1); /* region after the range */ r->ar.start = DAMON_MIN_REGION * 6; r->ar.end = DAMON_MIN_REGION * 8; - KUNIT_EXPECT_FALSE(test, __damos_filter_out(NULL, t, r, f)); + KUNIT_EXPECT_FALSE(test, damos_filter_match(NULL, t, r, f)); KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1); /* region started before the range */ r->ar.start = DAMON_MIN_REGION * 1; r->ar.end = DAMON_MIN_REGION * 4; - KUNIT_EXPECT_FALSE(test, __damos_filter_out(NULL, t, r, f)); + KUNIT_EXPECT_FALSE(test, damos_filter_match(NULL, t, r, f)); /* filter should have split the region */ KUNIT_EXPECT_EQ(test, r->ar.start, DAMON_MIN_REGION * 1); KUNIT_EXPECT_EQ(test, r->ar.end, DAMON_MIN_REGION * 2); @@ -465,7 +465,7 @@ static void damos_test_filter_out(struct kunit *test) /* region started in the range */ r->ar.start = DAMON_MIN_REGION * 2; r->ar.end = DAMON_MIN_REGION * 8; - KUNIT_EXPECT_TRUE(test, __damos_filter_out(NULL, t, r, f)); + KUNIT_EXPECT_TRUE(test, damos_filter_match(NULL, t, r, f)); /* filter should have split the region */ KUNIT_EXPECT_EQ(test, r->ar.start, DAMON_MIN_REGION * 2); KUNIT_EXPECT_EQ(test, r->ar.end, DAMON_MIN_REGION * 6); diff --git a/mm/damon/tests/dbgfs-kunit.h b/mm/damon/tests/dbgfs-kunit.h deleted file mode 100644 index 087e53f641a8..000000000000 --- a/mm/damon/tests/dbgfs-kunit.h +++ /dev/null @@ -1,173 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * DAMON Debugfs Interface Unit Tests - * - * Author: SeongJae Park - */ - -#ifdef CONFIG_DAMON_DBGFS_KUNIT_TEST - -#ifndef _DAMON_DBGFS_TEST_H -#define _DAMON_DBGFS_TEST_H - -#include - -static void damon_dbgfs_test_str_to_ints(struct kunit *test) -{ - char *question; - int *answers; - int expected[] = {12, 35, 46}; - ssize_t nr_integers = 0, i; - - question = "123"; - answers = str_to_ints(question, strlen(question), &nr_integers); - KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers); - KUNIT_EXPECT_EQ(test, 123, answers[0]); - kfree(answers); - - question = "123abc"; - answers = str_to_ints(question, strlen(question), &nr_integers); - KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers); - KUNIT_EXPECT_EQ(test, 123, answers[0]); - kfree(answers); - - question = "a123"; - answers = str_to_ints(question, strlen(question), &nr_integers); - KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); - kfree(answers); - - question = "12 35"; - answers = str_to_ints(question, strlen(question), &nr_integers); - KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers); - for (i = 0; i < nr_integers; i++) - KUNIT_EXPECT_EQ(test, expected[i], answers[i]); - kfree(answers); - - question = "12 35 46"; - answers = str_to_ints(question, strlen(question), &nr_integers); - KUNIT_EXPECT_EQ(test, (ssize_t)3, nr_integers); - for (i = 0; i < nr_integers; i++) - KUNIT_EXPECT_EQ(test, expected[i], answers[i]); - kfree(answers); - - question = "12 35 abc 46"; - answers = str_to_ints(question, strlen(question), &nr_integers); - KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers); - for (i = 0; i < 2; i++) - KUNIT_EXPECT_EQ(test, expected[i], answers[i]); - kfree(answers); - - question = ""; - answers = str_to_ints(question, strlen(question), &nr_integers); - KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); - kfree(answers); - - question = "\n"; - answers = str_to_ints(question, strlen(question), &nr_integers); - KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); - kfree(answers); -} - -static void damon_dbgfs_test_set_targets(struct kunit *test) -{ - struct damon_ctx *ctx = dbgfs_new_ctx(); - char buf[64]; - - if (!damon_is_registered_ops(DAMON_OPS_PADDR)) { - dbgfs_destroy_ctx(ctx); - kunit_skip(test, "PADDR not registered"); - } - - /* Make DAMON consider target has no pid */ - damon_select_ops(ctx, DAMON_OPS_PADDR); - - dbgfs_set_targets(ctx, 0, NULL); - sprint_target_ids(ctx, buf, 64); - KUNIT_EXPECT_STREQ(test, (char *)buf, "\n"); - - dbgfs_set_targets(ctx, 1, NULL); - sprint_target_ids(ctx, buf, 64); - KUNIT_EXPECT_STREQ(test, (char *)buf, "42\n"); - - dbgfs_set_targets(ctx, 0, NULL); - sprint_target_ids(ctx, buf, 64); - KUNIT_EXPECT_STREQ(test, (char *)buf, "\n"); - - dbgfs_destroy_ctx(ctx); -} - -static void damon_dbgfs_test_set_init_regions(struct kunit *test) -{ - struct damon_ctx *ctx = damon_new_ctx(); - /* Each line represents one region in `` `` */ - char * const valid_inputs[] = {"1 10 20\n 1 20 30\n1 35 45", - "1 10 20\n", - "1 10 20\n0 39 59\n0 70 134\n 1 20 25\n", - ""}; - /* Reading the file again will show sorted, clean output */ - char * const valid_expects[] = {"1 10 20\n1 20 30\n1 35 45\n", - "1 10 20\n", - "0 39 59\n0 70 134\n1 10 20\n1 20 25\n", - ""}; - char * const invalid_inputs[] = {"3 10 20\n", /* target not exists */ - "1 10 20\n 1 14 26\n", /* regions overlap */ - "0 10 20\n1 30 40\n 0 5 8"}; /* not sorted by address */ - char *input, *expect; - int i, rc; - char buf[256]; - - if (!damon_is_registered_ops(DAMON_OPS_PADDR)) { - damon_destroy_ctx(ctx); - kunit_skip(test, "PADDR not registered"); - } - - damon_select_ops(ctx, DAMON_OPS_PADDR); - - dbgfs_set_targets(ctx, 3, NULL); - - /* Put valid inputs and check the results */ - for (i = 0; i < ARRAY_SIZE(valid_inputs); i++) { - input = valid_inputs[i]; - expect = valid_expects[i]; - - rc = set_init_regions(ctx, input, strnlen(input, 256)); - KUNIT_EXPECT_EQ(test, rc, 0); - - memset(buf, 0, 256); - sprint_init_regions(ctx, buf, 256); - - KUNIT_EXPECT_STREQ(test, (char *)buf, expect); - } - /* Put invalid inputs and check the return error code */ - for (i = 0; i < ARRAY_SIZE(invalid_inputs); i++) { - input = invalid_inputs[i]; - pr_info("input: %s\n", input); - rc = set_init_regions(ctx, input, strnlen(input, 256)); - KUNIT_EXPECT_EQ(test, rc, -EINVAL); - - memset(buf, 0, 256); - sprint_init_regions(ctx, buf, 256); - - KUNIT_EXPECT_STREQ(test, (char *)buf, ""); - } - - dbgfs_set_targets(ctx, 0, NULL); - damon_destroy_ctx(ctx); -} - -static struct kunit_case damon_test_cases[] = { - KUNIT_CASE(damon_dbgfs_test_str_to_ints), - KUNIT_CASE(damon_dbgfs_test_set_targets), - KUNIT_CASE(damon_dbgfs_test_set_init_regions), - {}, -}; - -static struct kunit_suite damon_test_suite = { - .name = "damon-dbgfs", - .test_cases = damon_test_cases, -}; -kunit_test_suite(damon_test_suite); - -#endif /* _DAMON_DBGFS_TEST_H */ - -#endif /* CONFIG_DAMON_KUNIT_TEST */ diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h index b9fe3bc8472b..7cd944266a92 100644 --- a/mm/damon/tests/vaddr-kunit.h +++ b/mm/damon/tests/vaddr-kunit.h @@ -68,7 +68,7 @@ static void damon_test_three_regions_in_vmas(struct kunit *test) static struct mm_struct mm; struct damon_addr_range regions[3] = {0}; /* 10-20-25, 200-210-220, 300-305, 307-330 */ - struct vm_area_struct vmas[] = { + static struct vm_area_struct vmas[] = { (struct vm_area_struct) {.vm_start = 10, .vm_end = 20}, (struct vm_area_struct) {.vm_start = 20, .vm_end = 25}, (struct vm_area_struct) {.vm_start = 200, .vm_end = 210}, diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index b9eaa20b73b9..a6174f725bd7 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -655,7 +655,7 @@ static unsigned long damos_madvise(struct damon_target *target, static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, - struct damos *scheme) + struct damos *scheme, unsigned long *sz_filter_passed) { int madv_action; diff --git a/mm/debug.c b/mm/debug.c index 95b6ab809c0e..8d2acf432385 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -249,6 +249,77 @@ void dump_mm(const struct mm_struct *mm) } EXPORT_SYMBOL(dump_mm); +void dump_vmg(const struct vma_merge_struct *vmg, const char *reason) +{ + if (reason) + pr_warn("vmg %px dumped because: %s\n", vmg, reason); + + if (!vmg) { + pr_warn("vmg %px state: (NULL)\n", vmg); + return; + } + + pr_warn("vmg %px state: mm %px pgoff %lx\n" + "vmi %px [%lx,%lx)\n" + "prev %px next %px vma %px\n" + "start %lx end %lx flags %lx\n" + "file %px anon_vma %px policy %px\n" + "uffd_ctx %px\n" + "anon_name %px\n" + "merge_flags %x state %x\n", + vmg, vmg->mm, vmg->pgoff, + vmg->vmi, vmg->vmi ? vma_iter_addr(vmg->vmi) : 0, + vmg->vmi ? vma_iter_end(vmg->vmi) : 0, + vmg->prev, vmg->next, vmg->vma, + vmg->start, vmg->end, vmg->flags, + vmg->file, vmg->anon_vma, vmg->policy, +#ifdef CONFIG_USERFAULTFD + vmg->uffd_ctx.ctx, +#else + (void *)0, +#endif + vmg->anon_name, + (int)vmg->merge_flags, (int)vmg->state); + + if (vmg->mm) { + pr_warn("vmg %px mm:\n", vmg); + dump_mm(vmg->mm); + } else { + pr_warn("vmg %px mm: (NULL)\n", vmg); + } + + if (vmg->vma) { + pr_warn("vmg %px vma:\n", vmg); + dump_vma(vmg->vma); + } else { + pr_warn("vmg %px vma: (NULL)\n", vmg); + } + + if (vmg->prev) { + pr_warn("vmg %px prev:\n", vmg); + dump_vma(vmg->prev); + } else { + pr_warn("vmg %px prev: (NULL)\n", vmg); + } + + if (vmg->next) { + pr_warn("vmg %px next:\n", vmg); + dump_vma(vmg->next); + } else { + pr_warn("vmg %px next: (NULL)\n", vmg); + } + +#ifdef CONFIG_DEBUG_VM_MAPLE_TREE + if (vmg->vmi) { + pr_warn("vmg %px vmi:\n", vmg); + vma_iter_dump_tree(vmg->vmi); + } else { + pr_warn("vmg %px vmi: (NULL)\n", vmg); + } +#endif +} +EXPORT_SYMBOL(dump_vmg); + static bool page_init_poisoning __read_mostly = true; static int __init setup_vm_debug(char *str) diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c index ce06b2884789..ff35b84a7b50 100644 --- a/mm/early_ioremap.c +++ b/mm/early_ioremap.c @@ -245,7 +245,10 @@ early_memremap_prot(resource_size_t phys_addr, unsigned long size, #define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT) -void __init copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size) +/* + * If no empty slot, handle that and return -ENOMEM. + */ +int __init copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size) { unsigned long slop, clen; char *p; @@ -256,12 +259,15 @@ void __init copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size) if (clen > MAX_MAP_CHUNK - slop) clen = MAX_MAP_CHUNK - slop; p = early_memremap(src & PAGE_MASK, clen + slop); + if (!p) + return -ENOMEM; memcpy(dest, p + slop, clen); early_memunmap(p, clen + slop); dest += clen; src += clen; size -= clen; } + return 0; } #else /* CONFIG_MMU */ diff --git a/mm/filemap.c b/mm/filemap.c index f61cf51c2238..804d7365680c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include #include "internal.h" @@ -124,15 +125,6 @@ * ->private_lock (zap_pte_range->block_dirty_folio) */ -static void mapping_set_update(struct xa_state *xas, - struct address_space *mapping) -{ - if (dax_mapping(mapping) || shmem_mapping(mapping)) - return; - xas_set_update(xas, workingset_update_node); - xas_set_lru(xas, &shadow_nodes); -} - static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { @@ -449,6 +441,24 @@ int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, } EXPORT_SYMBOL(filemap_fdatawrite_range); +/** + * filemap_fdatawrite_range_kick - start writeback on a range + * @mapping: target address_space + * @start: index to start writeback on + * @end: last (non-inclusive) index for writeback + * + * This is a non-integrity writeback helper, to start writing back folios + * for the indicated range. + * + * Return: %0 on success, negative error code otherwise. + */ +int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, + loff_t end) +{ + return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE); +} +EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick); + /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space @@ -1472,25 +1482,6 @@ static int folio_put_wait_locked(struct folio *folio, int state) return folio_wait_bit_common(folio, PG_locked, state, DROP); } -/** - * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue - * @folio: Folio defining the wait queue of interest - * @waiter: Waiter to add to the queue - * - * Add an arbitrary @waiter to the wait queue for the nominated @folio. - */ -void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) -{ - wait_queue_head_t *q = folio_waitqueue(folio); - unsigned long flags; - - spin_lock_irqsave(&q->lock, flags); - __add_wait_queue_entry_tail(q, waiter); - folio_set_waiters(folio); - spin_unlock_irqrestore(&q->lock, flags); -} -EXPORT_SYMBOL_GPL(folio_add_wait_queue); - /** * folio_unlock - Unlock a locked folio. * @folio: The folio. @@ -1532,7 +1523,7 @@ void folio_end_read(struct folio *folio, bool success) /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); + VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; @@ -1599,6 +1590,27 @@ int folio_wait_private_2_killable(struct folio *folio) } EXPORT_SYMBOL(folio_wait_private_2_killable); +/* + * If folio was marked as dropbehind, then pages should be dropped when writeback + * completes. Do that now. If we fail, it's likely because of a big folio - + * just reset dropbehind for that case and latter completions should invalidate. + */ +static void folio_end_dropbehind_write(struct folio *folio) +{ + /* + * Hitting !in_task() should not happen off RWF_DONTCACHE writeback, + * but can happen if normal writeback just happens to find dirty folios + * that were created as part of uncached writeback, and that writeback + * would otherwise not need non-IRQ handling. Just skip the + * invalidation in that case. + */ + if (in_task() && folio_trylock(folio)) { + if (folio->mapping) + folio_unmap_invalidate(folio->mapping, folio, 0); + folio_unlock(folio); + } +} + /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. @@ -1609,6 +1621,8 @@ EXPORT_SYMBOL(folio_wait_private_2_killable); */ void folio_end_writeback(struct folio *folio) { + bool folio_dropbehind = false; + VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* @@ -1630,9 +1644,14 @@ void folio_end_writeback(struct folio *folio) * reused before the folio_wake_bit(). */ folio_get(folio); + if (!folio_test_dirty(folio)) + folio_dropbehind = folio_test_clear_dropbehind(folio); if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); + + if (folio_dropbehind) + folio_end_dropbehind_write(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); @@ -1955,6 +1974,8 @@ no_page: /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); + if (fgp_flags & FGP_DONTCACHE) + __folio_set_dropbehind(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) @@ -1977,6 +1998,9 @@ no_page: if (!folio) return ERR_PTR(-ENOENT); + /* not an uncached lookup, clear uncached if set */ + if (folio_test_dropbehind(folio) && !(fgp_flags & FGP_DONTCACHE)) + folio_clear_dropbehind(folio); return folio; } EXPORT_SYMBOL(__filemap_get_folio); @@ -2459,18 +2483,22 @@ unlock_mapping: return error; } -static int filemap_create_folio(struct file *file, - struct address_space *mapping, loff_t pos, - struct folio_batch *fbatch) +static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch) { + struct address_space *mapping = iocb->ki_filp->f_mapping; struct folio *folio; int error; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t index; + if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) + return -EAGAIN; + folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order); if (!folio) return -ENOMEM; + if (iocb->ki_flags & IOCB_DONTCACHE) + __folio_set_dropbehind(folio); /* * Protect against truncate / hole punch. Grabbing invalidate_lock @@ -2486,7 +2514,7 @@ static int filemap_create_folio(struct file *file, * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); - index = (pos >> (PAGE_SHIFT + min_order)) << min_order; + index = (iocb->ki_pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) @@ -2494,7 +2522,8 @@ static int filemap_create_folio(struct file *file, if (error) goto error; - error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); + error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, + folio); if (error) goto error; @@ -2515,6 +2544,8 @@ static int filemap_readahead(struct kiocb *iocb, struct file *file, if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; + if (iocb->ki_flags & IOCB_DONTCACHE) + ractl.dropbehind = 1; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } @@ -2524,7 +2555,6 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count, { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; - struct file_ra_state *ra = &filp->f_ra; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; @@ -2539,20 +2569,21 @@ retry: filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { + DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index); + if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_NOWAIT) flags = memalloc_noio_save(); - page_cache_sync_readahead(mapping, ra, filp, index, - last_index - index); + if (iocb->ki_flags & IOCB_DONTCACHE) + ractl.dropbehind = 1; + page_cache_sync_ra(&ractl, last_index - index); if (iocb->ki_flags & IOCB_NOWAIT) memalloc_noio_restore(flags); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { - if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) - return -EAGAIN; - err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch); + err = filemap_create_folio(iocb, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; @@ -2593,6 +2624,20 @@ static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) return (pos1 >> shift == pos2 >> shift); } +static void filemap_end_dropbehind_read(struct address_space *mapping, + struct folio *folio) +{ + if (!folio_test_dropbehind(folio)) + return; + if (folio_test_writeback(folio) || folio_test_dirty(folio)) + return; + if (folio_trylock(folio)) { + if (folio_test_clear_dropbehind(folio)) + folio_unmap_invalidate(mapping, folio, 0); + folio_unlock(folio); + } +} + /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. @@ -2706,8 +2751,12 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, } } put_folios: - for (i = 0; i < folio_batch_count(&fbatch); i++) - folio_put(fbatch.folios[i]); + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; + + filemap_end_dropbehind_read(mapping, folio); + folio_put(folio); + } folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); @@ -3005,7 +3054,7 @@ static inline loff_t folio_seek_hole_data(struct xa_state *xas, if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; - start = (start + bsz) & ~(bsz - 1); + start = (start + bsz) & ~((u64)bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: @@ -3150,6 +3199,14 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) unsigned long vm_flags = vmf->vma->vm_flags; unsigned int mmap_miss; + /* + * If we have pre-content watches we need to disable readahead to make + * sure that we don't populate our mapping with 0 filled pages that we + * never emitted an event for. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) + return fpin; + #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { @@ -3218,6 +3275,10 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct file *fpin = NULL; unsigned int mmap_miss; + /* See comment in do_sync_mmap_readahead. */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) + return fpin; + /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; @@ -3276,6 +3337,48 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) return ret; } +/** + * filemap_fsnotify_fault - maybe emit a pre-content event. + * @vmf: struct vm_fault containing details of the fault. + * + * If we have a pre-content watch on this file we will emit an event for this + * range. If we return anything the fault caller should return immediately, we + * will return VM_FAULT_RETRY if we had to emit an event, which will trigger the + * fault again and then the fault handler will run the second time through. + * + * Return: a bitwise-OR of %VM_FAULT_ codes, 0 if nothing happened. + */ +vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf) +{ + struct file *fpin = NULL; + int mask = (vmf->flags & FAULT_FLAG_WRITE) ? MAY_WRITE : MAY_ACCESS; + loff_t pos = vmf->pgoff >> PAGE_SHIFT; + size_t count = PAGE_SIZE; + int err; + + /* + * We already did this and now we're retrying with everything locked, + * don't emit the event and continue. + */ + if (vmf->flags & FAULT_FLAG_TRIED) + return 0; + + /* No watches, we're done. */ + if (likely(!FMODE_FSNOTIFY_HSM(vmf->vma->vm_file->f_mode))) + return 0; + + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + if (!fpin) + return VM_FAULT_SIGBUS; + + err = fsnotify_file_area_perm(fpin, mask, &pos, count); + fput(fpin); + if (err) + return VM_FAULT_SIGBUS; + return VM_FAULT_RETRY; +} +EXPORT_SYMBOL_GPL(filemap_fsnotify_fault); + /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault @@ -3379,6 +3482,37 @@ retry_find: * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { + /* + * If this is a precontent file we have can now emit an event to + * try and populate the folio. + */ + if (!(vmf->flags & FAULT_FLAG_TRIED) && + unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + loff_t pos = folio_pos(folio); + size_t count = folio_size(folio); + + /* We're NOWAIT, we have to retry. */ + if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) { + folio_unlock(folio); + goto out_retry; + } + + if (mapping_locked) + filemap_invalidate_unlock_shared(mapping); + mapping_locked = false; + + folio_unlock(folio); + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + if (!fpin) + goto out_retry; + + error = fsnotify_file_area_perm(fpin, MAY_ACCESS, &pos, + count); + if (error) + ret = VM_FAULT_SIGBUS; + goto out_retry; + } + /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we @@ -4384,6 +4518,20 @@ resched: rcu_read_unlock(); } +/* + * See mincore: reveal pagecache information only for files + * that the calling process has write access to, or could (if + * tried) open for writing. + */ +static inline bool can_do_cachestat(struct file *f) +{ + if (f->f_mode & FMODE_WRITE) + return true; + if (inode_owner_or_capable(file_mnt_idmap(f), file_inode(f))) + return true; + return file_permission(f, MAY_WRITE) == 0; +} + /* * The cachestat(2) system call. * @@ -4439,6 +4587,9 @@ SYSCALL_DEFINE4(cachestat, unsigned int, fd, if (is_file_hugepages(fd_file(f))) return -EOPNOTSUPP; + if (!can_do_cachestat(fd_file(f))) + return -EPERM; + if (flags != 0) return -EINVAL; diff --git a/mm/gup.c b/mm/gup.c index 3b75e631f369..3883b307780e 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -596,6 +596,33 @@ static struct folio *try_grab_folio_fast(struct page *page, int refs, } #endif /* CONFIG_HAVE_GUP_FAST */ +/* Common code for can_follow_write_* */ +static inline bool can_follow_write_common(struct page *page, + struct vm_area_struct *vma, unsigned int flags) +{ + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + return page && PageAnon(page) && PageAnonExclusive(page); +} + static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags, unsigned long address) { @@ -622,6 +649,18 @@ static struct page *no_page_table(struct vm_area_struct *vma, } #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES +/* FOLL_FORCE can write to even unwritable PUDs in COW mappings. */ +static inline bool can_follow_write_pud(pud_t pud, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) +{ + /* If the pud is writable, we can write to the page. */ + if (pud_write(pud)) + return true; + + return can_follow_write_common(page, vma, flags); +} + static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) @@ -634,10 +673,11 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma, assert_spin_locked(pud_lockptr(mm, pudp)); - if ((flags & FOLL_WRITE) && !pud_write(pud)) + if (!pud_present(pud)) return NULL; - if (!pud_present(pud)) + if ((flags & FOLL_WRITE) && + !can_follow_write_pud(pud, pfn_to_page(pfn), vma, flags)) return NULL; pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; @@ -686,27 +726,7 @@ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, if (pmd_write(pmd)) return true; - /* Maybe FOLL_FORCE is set to override it? */ - if (!(flags & FOLL_FORCE)) - return false; - - /* But FOLL_FORCE has no effect on shared mappings */ - if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) - return false; - - /* ... or read-only private ones */ - if (!(vma->vm_flags & VM_MAYWRITE)) - return false; - - /* ... or already writable ones that just need to take a write fault */ - if (vma->vm_flags & VM_WRITE) - return false; - - /* - * See can_change_pte_writable(): we broke COW and could map the page - * writable if we have an exclusive anonymous page ... - */ - if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + if (!can_follow_write_common(page, vma, flags)) return false; /* ... and a write-fault isn't required for other reasons. */ @@ -807,27 +827,7 @@ static inline bool can_follow_write_pte(pte_t pte, struct page *page, if (pte_write(pte)) return true; - /* Maybe FOLL_FORCE is set to override it? */ - if (!(flags & FOLL_FORCE)) - return false; - - /* But FOLL_FORCE has no effect on shared mappings */ - if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) - return false; - - /* ... or read-only private ones */ - if (!(vma->vm_flags & VM_MAYWRITE)) - return false; - - /* ... or already writable ones that just need to take a write fault */ - if (vma->vm_flags & VM_WRITE) - return false; - - /* - * See can_change_pte_writable(): we broke COW and could map the page - * writable if we have an exclusive anonymous page ... - */ - if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + if (!can_follow_write_common(page, vma, flags)) return false; /* ... and a write-fault isn't required for other reasons. */ @@ -1294,9 +1294,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; - /* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */ - if (is_vm_hugetlb_page(vma)) - return -EFAULT; /* * We used to let the write,force case do COW in a * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could @@ -2323,13 +2320,13 @@ static void pofs_unpin(struct pages_or_folios *pofs) /* * Returns the number of collected folios. Return value is always >= 0. */ -static unsigned long collect_longterm_unpinnable_folios( +static void collect_longterm_unpinnable_folios( struct list_head *movable_folio_list, struct pages_or_folios *pofs) { - unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; + unsigned long i; for (i = 0; i < pofs->nr_entries; i++) { struct folio *folio = pofs_get_folio(pofs, i); @@ -2341,13 +2338,11 @@ static unsigned long collect_longterm_unpinnable_folios( if (folio_is_longterm_pinnable(folio)) continue; - collected++; - if (folio_is_device_coherent(folio)) continue; if (folio_test_hugetlb(folio)) { - isolate_hugetlb(folio, movable_folio_list); + folio_isolate_hugetlb(folio, movable_folio_list); continue; } @@ -2364,8 +2359,6 @@ static unsigned long collect_longterm_unpinnable_folios( NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } - - return collected; } /* @@ -2442,11 +2435,9 @@ static long check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs) { LIST_HEAD(movable_folio_list); - unsigned long collected; - collected = collect_longterm_unpinnable_folios(&movable_folio_list, - pofs); - if (!collected) + collect_longterm_unpinnable_folios(&movable_folio_list, pofs); + if (list_empty(&movable_folio_list)) return 0; return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs); @@ -3360,8 +3351,7 @@ static unsigned long gup_fast(unsigned long start, unsigned long end, return 0; if (gup_flags & FOLL_PIN) { - seq = raw_read_seqcount(¤t->mm->write_protect_seq); - if (seq & 1) + if (!raw_seqcount_try_begin(¤t->mm->write_protect_seq, seq)) return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ee335d96fc39..3d3ebdc002d5 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -617,6 +617,8 @@ DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT); DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN); +DEFINE_MTHP_STAT_ATTR(swpin_fallback, MTHP_STAT_SWPIN_FALLBACK); +DEFINE_MTHP_STAT_ATTR(swpin_fallback_charge, MTHP_STAT_SWPIN_FALLBACK_CHARGE); DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); #ifdef CONFIG_SHMEM @@ -637,6 +639,8 @@ static struct attribute *anon_stats_attrs[] = { #ifndef CONFIG_SHMEM &zswpout_attr.attr, &swpin_attr.attr, + &swpin_fallback_attr.attr, + &swpin_fallback_charge_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif @@ -669,6 +673,8 @@ static struct attribute *any_stats_attrs[] = { #ifdef CONFIG_SHMEM &zswpout_attr.attr, &swpin_attr.attr, + &swpin_fallback_attr.attr, + &swpin_fallback_charge_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif @@ -1176,11 +1182,12 @@ static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, folio_throttle_swaprate(folio, gfp); /* - * When a folio is not zeroed during allocation (__GFP_ZERO not used), - * folio_zero_user() is used to make sure that the page corresponding - * to the faulting address will be hot in the cache after zeroing. + * When a folio is not zeroed during allocation (__GFP_ZERO not used) + * or user folios require special handling, folio_zero_user() is used to + * make sure that the page corresponding to the faulting address will be + * hot in the cache after zeroing. */ - if (!alloc_zeroed()) + if (user_alloc_needs_zeroing()) folio_zero_user(folio, addr); /* * The memory barrier inside __folio_mark_uptodate makes sure that @@ -2002,7 +2009,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) spin_unlock(vmf->ptl); writable = false; - if (!migrate_misplaced_folio(folio, vma, target_nid)) { + if (!migrate_misplaced_folio(folio, target_nid)) { flags |= TNF_MIGRATED; nid = target_nid; task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); @@ -2205,6 +2212,16 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd) return pmd; } +static pmd_t clear_uffd_wp_pmd(pmd_t pmd) +{ + if (pmd_present(pmd)) + pmd = pmd_clear_uffd_wp(pmd); + else if (is_swap_pmd(pmd)) + pmd = pmd_swp_clear_uffd_wp(pmd); + + return pmd; +} + bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) { @@ -2243,6 +2260,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, pgtable_trans_huge_deposit(mm, new_pmd, pgtable); } pmd = move_soft_dirty_pmd(pmd); + if (vma_has_uffd_without_event_remap(vma)) + pmd = clear_uffd_wp_pmd(pmd); set_pmd_at(mm, new_addr, new_pmd, pmd); if (force_flush) flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE); @@ -3271,7 +3290,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ lruvec = folio_lruvec_lock(folio); - ClearPageHasHWPoisoned(head); + folio_clear_has_hwpoisoned(folio); for (i = nr - new_nr; i >= new_nr; i -= new_nr) { struct folio *tail; @@ -3576,7 +3595,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -3688,7 +3707,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio) if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -3732,7 +3751,7 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (partially_mapped) { if (!folio_test_partially_mapped(folio)) { - __folio_set_partially_mapped(folio); + folio_set_partially_mapped(folio); if (folio_test_pmd_mappable(folio)) count_vm_event(THP_DEFERRED_SPLIT_PAGE); count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); @@ -3825,7 +3844,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, } else { /* We lost race with folio_put() */ if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -4162,20 +4181,21 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, if (input_buf[0] == '/') { char *tok; - char *buf = input_buf; + char *tok_buf = input_buf; char file_path[MAX_INPUT_BUF_SZ]; pgoff_t off_start = 0, off_end = 0; size_t input_len = strlen(input_buf); - tok = strsep(&buf, ","); - if (tok) { + tok = strsep(&tok_buf, ","); + if (tok && tok_buf) { strscpy(file_path, tok); } else { ret = -EINVAL; goto out; } - ret = sscanf(buf, "0x%lx,0x%lx,%d", &off_start, &off_end, &new_order); + ret = sscanf(tok_buf, "0x%lx,0x%lx,%d", &off_start, + &off_end, &new_order); if (ret != 2 && ret != 3) { ret = -EINVAL; goto out; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ea2ed8e301ef..65068671e460 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -48,6 +48,7 @@ #include #include "internal.h" #include "hugetlb_vmemmap.h" +#include int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; @@ -1246,69 +1247,6 @@ void clear_vma_resv_huge_pages(struct vm_area_struct *vma) hugetlb_dup_vma_private(vma); } -/* Returns true if the VMA has associated reserve pages */ -static bool vma_has_reserves(struct vm_area_struct *vma, long chg) -{ - if (vma->vm_flags & VM_NORESERVE) { - /* - * This address is already reserved by other process(chg == 0), - * so, we should decrement reserved count. Without decrementing, - * reserve count remains after releasing inode, because this - * allocated page will go into page cache and is regarded as - * coming from reserved pool in releasing step. Currently, we - * don't have any other solution to deal with this situation - * properly, so add work-around here. - */ - if (vma->vm_flags & VM_MAYSHARE && chg == 0) - return true; - else - return false; - } - - /* Shared mappings always use reserves */ - if (vma->vm_flags & VM_MAYSHARE) { - /* - * We know VM_NORESERVE is not set. Therefore, there SHOULD - * be a region map for all pages. The only situation where - * there is no region map is if a hole was punched via - * fallocate. In this case, there really are no reserves to - * use. This situation is indicated if chg != 0. - */ - if (chg) - return false; - else - return true; - } - - /* - * Only the process that called mmap() has reserves for - * private mappings. - */ - if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { - /* - * Like the shared case above, a hole punch or truncate - * could have been performed on the private mapping. - * Examine the value of chg to determine if reserves - * actually exist or were previously consumed. - * Very Subtle - The value of chg comes from a previous - * call to vma_needs_reserves(). The reserve map for - * private mappings has different (opposite) semantics - * than that of shared mappings. vma_needs_reserves() - * has already taken this difference in semantics into - * account. Therefore, the meaning of chg is the same - * as in the shared case above. Code could easily be - * combined, but keeping it separate draws attention to - * subtle differences. - */ - if (chg) - return false; - else - return true; - } - - return false; -} - static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio) { int nid = folio_nid(folio); @@ -1336,6 +1274,9 @@ static struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h, if (folio_test_hwpoison(folio)) continue; + if (is_migrate_isolate_page(&folio->page)) + continue; + list_move(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); folio_clear_hugetlb_freed(folio); @@ -1394,8 +1335,7 @@ static unsigned long available_huge_pages(struct hstate *h) static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address, int avoid_reserve, - long chg) + unsigned long address, long gbl_chg) { struct folio *folio = NULL; struct mempolicy *mpol; @@ -1404,15 +1344,10 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, int nid; /* - * A child process with MAP_PRIVATE mappings created by their parent - * have no page reserves. This check ensures that reservations are - * not "stolen". The child may still get SIGKILLed + * gbl_chg==1 means the allocation requires a new page that was not + * reserved before. Making sure there's at least one free page. */ - if (!vma_has_reserves(vma, chg) && !available_huge_pages(h)) - goto err; - - /* If reserves cannot be used, ensure enough pages are in the pool */ - if (avoid_reserve && !available_huge_pages(h)) + if (gbl_chg && !available_huge_pages(h)) goto err; gfp_mask = htlb_alloc_mask(h); @@ -1430,11 +1365,6 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); - if (folio && !avoid_reserve && vma_has_reserves(vma, chg)) { - folio_set_hugetlb_restore_reserve(folio); - h->resv_huge_pages--; - } - mpol_cond_put(mpol); return folio; @@ -2463,7 +2393,13 @@ static int gather_surplus_pages(struct hstate *h, long delta) long needed, allocated; bool alloc_ok = true; int node; - nodemask_t *mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h)); + nodemask_t *mbind_nodemask, alloc_nodemask; + + mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h)); + if (mbind_nodemask) + nodes_and(alloc_nodemask, *mbind_nodemask, cpuset_current_mems_allowed); + else + alloc_nodemask = cpuset_current_mems_allowed; lockdep_assert_held(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - h->free_huge_pages; @@ -2479,8 +2415,16 @@ retry: spin_unlock_irq(&hugetlb_lock); for (i = 0; i < needed; i++) { folio = NULL; - for_each_node_mask(node, cpuset_current_mems_allowed) { - if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) { + + /* Prioritize current node */ + if (node_isset(numa_mem_id(), alloc_nodemask)) + folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), + numa_mem_id(), NULL); + + if (!folio) { + for_each_node_mask(node, alloc_nodemask) { + if (node == numa_mem_id()) + continue; folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), node, NULL); if (folio) @@ -2868,7 +2812,7 @@ retry: * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); - isolated = isolate_hugetlb(old_folio, list); + isolated = folio_isolate_hugetlb(old_folio, list); ret = isolated ? 0 : -EBUSY; spin_lock_irq(&hugetlb_lock); goto free_new; @@ -2953,7 +2897,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) if (hstate_is_gigantic(h)) return -ENOMEM; - if (folio_ref_count(folio) && isolate_hugetlb(folio, list)) + if (folio_ref_count(folio) && folio_isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); @@ -2961,69 +2905,129 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) return ret; } +/* + * replace_free_hugepage_folios - Replace free hugepage folios in a given pfn + * range with new folios. + * @start_pfn: start pfn of the given pfn range + * @end_pfn: end pfn of the given pfn range + * Returns 0 on success, otherwise negated error. + */ +int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) +{ + struct hstate *h; + struct folio *folio; + int ret = 0; + + LIST_HEAD(isolate_list); + + while (start_pfn < end_pfn) { + folio = pfn_folio(start_pfn); + if (folio_test_hugetlb(folio)) { + h = folio_hstate(folio); + } else { + start_pfn++; + continue; + } + + if (!folio_ref_count(folio)) { + ret = alloc_and_dissolve_hugetlb_folio(h, folio, + &isolate_list); + if (ret) + break; + + putback_movable_pages(&isolate_list); + } + start_pfn++; + } + + return ret; +} + +typedef enum { + /* + * For either 0/1: we checked the per-vma resv map, and one resv + * count either can be reused (0), or an extra needed (1). + */ + MAP_CHG_REUSE = 0, + MAP_CHG_NEEDED = 1, + /* + * Cannot use per-vma resv count can be used, hence a new resv + * count is enforced. + * + * NOTE: This is mostly identical to MAP_CHG_NEEDED, except + * that currently vma_needs_reservation() has an unwanted side + * effect to either use end() or commit() to complete the + * transaction. Hence it needs to differenciate from NEEDED. + */ + MAP_CHG_ENFORCED = 2, +} map_chg_state; + +/* + * NOTE! "cow_from_owner" represents a very hacky usage only used in CoW + * faults of hugetlb private mappings on top of a non-page-cache folio (in + * which case even if there's a private vma resv map it won't cover such + * allocation). New call sites should (probably) never set it to true!! + * When it's set, the allocation will bypass all vma level reservations. + */ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, - unsigned long addr, int avoid_reserve) + unsigned long addr, bool cow_from_owner) { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; - long map_chg, map_commit, nr_pages = pages_per_huge_page(h); - long gbl_chg; - int memcg_charge_ret, ret, idx; + long retval, gbl_chg; + map_chg_state map_chg; + int ret, idx; struct hugetlb_cgroup *h_cg = NULL; - struct mem_cgroup *memcg; - bool deferred_reserve; gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL; - memcg = get_mem_cgroup_from_current(); - memcg_charge_ret = mem_cgroup_hugetlb_try_charge(memcg, gfp, nr_pages); - if (memcg_charge_ret == -ENOMEM) { - mem_cgroup_put(memcg); - return ERR_PTR(-ENOMEM); - } - idx = hstate_index(h); - /* - * Examine the region/reserve map to determine if the process - * has a reservation for the page to be allocated. A return - * code of zero indicates a reservation exists (no change). - */ - map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); - if (map_chg < 0) { - if (!memcg_charge_ret) - mem_cgroup_cancel_charge(memcg, nr_pages); - mem_cgroup_put(memcg); - return ERR_PTR(-ENOMEM); + + /* Whether we need a separate per-vma reservation? */ + if (cow_from_owner) { + /* + * Special case! Since it's a CoW on top of a reserved + * page, the private resv map doesn't count. So it cannot + * consume the per-vma resv map even if it's reserved. + */ + map_chg = MAP_CHG_ENFORCED; + } else { + /* + * Examine the region/reserve map to determine if the process + * has a reservation for the page to be allocated. A return + * code of zero indicates a reservation exists (no change). + */ + retval = vma_needs_reservation(h, vma, addr); + if (retval < 0) + return ERR_PTR(-ENOMEM); + map_chg = retval ? MAP_CHG_NEEDED : MAP_CHG_REUSE; } /* + * Whether we need a separate global reservation? + * * Processes that did not create the mapping will have no * reserves as indicated by the region/reserve map. Check * that the allocation will not exceed the subpool limit. - * Allocations for MAP_NORESERVE mappings also need to be - * checked against any subpool limit. + * Or if it can get one from the pool reservation directly. */ - if (map_chg || avoid_reserve) { + if (map_chg) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; - + } else { /* - * Even though there was no reservation in the region/reserve - * map, there could be reservations associated with the - * subpool that can be used. This would be indicated if the - * return value of hugepage_subpool_get_pages() is zero. - * However, if avoid_reserve is specified we still avoid even - * the subpool reservations. + * If we have the vma reservation ready, no need for extra + * global reservation. */ - if (avoid_reserve) - gbl_chg = 1; + gbl_chg = 0; } - /* If this allocation is not consuming a reservation, charge it now. + /* + * If this allocation is not consuming a per-vma reservation, + * charge the hugetlb cgroup now. */ - deferred_reserve = map_chg || avoid_reserve; - if (deferred_reserve) { + if (map_chg) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); if (ret) @@ -3040,27 +3044,32 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ - folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg); + folio = dequeue_hugetlb_folio_vma(h, vma, addr, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); if (!folio) goto out_uncharge_cgroup; spin_lock_irq(&hugetlb_lock); - if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { - folio_set_hugetlb_restore_reserve(folio); - h->resv_huge_pages--; - } list_add(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); /* Fall through */ } + /* + * Either dequeued or buddy-allocated folio needs to add special + * mark to the folio when it consumes a global reservation. + */ + if (!gbl_chg) { + folio_set_hugetlb_restore_reserve(folio); + h->resv_huge_pages--; + } + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ - if (deferred_reserve) { + if (map_chg) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), h_cg, folio); } @@ -3069,50 +3078,61 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, hugetlb_set_folio_subpool(folio, spool); - map_commit = vma_commit_reservation(h, vma, addr); - if (unlikely(map_chg > map_commit)) { + if (map_chg != MAP_CHG_ENFORCED) { + /* commit() is only needed if the map_chg is not enforced */ + retval = vma_commit_reservation(h, vma, addr); /* + * Check for possible race conditions. When it happens.. * The page was added to the reservation map between * vma_needs_reservation and vma_commit_reservation. * This indicates a race with hugetlb_reserve_pages. * Adjust for the subpool count incremented above AND - * in hugetlb_reserve_pages for the same page. Also, + * in hugetlb_reserve_pages for the same page. Also, * the reservation count added in hugetlb_reserve_pages * no longer applies. */ - long rsv_adjust; + if (unlikely(map_chg == MAP_CHG_NEEDED && retval == 0)) { + long rsv_adjust; - rsv_adjust = hugepage_subpool_put_pages(spool, 1); - hugetlb_acct_memory(h, -rsv_adjust); - if (deferred_reserve) { - spin_lock_irq(&hugetlb_lock); - hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), - pages_per_huge_page(h), folio); - spin_unlock_irq(&hugetlb_lock); + rsv_adjust = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -rsv_adjust); + if (map_chg) { + spin_lock_irq(&hugetlb_lock); + hugetlb_cgroup_uncharge_folio_rsvd( + hstate_index(h), pages_per_huge_page(h), + folio); + spin_unlock_irq(&hugetlb_lock); + } } } - if (!memcg_charge_ret) - mem_cgroup_commit_charge(folio, memcg); + ret = mem_cgroup_charge_hugetlb(folio, gfp); + /* + * Unconditionally increment NR_HUGETLB here. If it turns out that + * mem_cgroup_charge_hugetlb failed, then immediately free the page and + * decrement NR_HUGETLB. + */ lruvec_stat_mod_folio(folio, NR_HUGETLB, pages_per_huge_page(h)); - mem_cgroup_put(memcg); + + if (ret == -ENOMEM) { + free_huge_folio(folio); + return ERR_PTR(-ENOMEM); + } return folio; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); out_uncharge_cgroup_reservation: - if (deferred_reserve) + if (map_chg) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: - if (map_chg || avoid_reserve) + if (map_chg) hugepage_subpool_put_pages(spool, 1); out_end_reservation: - vma_end_reservation(h, vma, addr); - if (!memcg_charge_ret) - mem_cgroup_cancel_charge(memcg, nr_pages); - mem_cgroup_put(memcg); + if (map_chg != MAP_CHG_ENFORCED) + vma_end_reservation(h, vma, addr); return ERR_PTR(-ENOSPC); } @@ -3289,7 +3309,7 @@ static void __init gather_bootmem_prealloc(void) .thread_fn = gather_bootmem_prealloc_parallel, .fn_arg = NULL, .start = 0, - .size = num_node_state(N_MEMORY), + .size = nr_node_ids, .align = 1, .min_chunk = 1, .max_threads = num_node_state(N_MEMORY), @@ -3806,13 +3826,15 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { struct page *page = folio_page(folio, i); + /* Careful: see __split_huge_page_tail() */ + struct folio *new_folio = (struct folio *)page; - page->mapping = NULL; clear_compound_head(page); prep_compound_page(page, dst->order); - init_new_hugetlb_folio(dst, page_folio(page)); - list_add(&page->lru, &dst_list); + new_folio->mapping = NULL; + init_new_hugetlb_folio(dst, new_folio); + list_add(&new_folio->lru, &dst_list); } } @@ -4845,7 +4867,7 @@ out: return ret; } -static struct ctl_table hugetlb_table[] = { +static const struct ctl_table hugetlb_table[] = { { .procname = "nr_hugepages", .data = NULL, @@ -5141,12 +5163,12 @@ const struct vm_operations_struct hugetlb_vm_ops = { }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, - int writable) + bool try_mkwrite) { pte_t entry; unsigned int shift = huge_page_shift(hstate_vma(vma)); - if (writable) { + if (try_mkwrite && (vma->vm_flags & VM_WRITE)) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, vma->vm_page_prot))); } else { @@ -5169,6 +5191,13 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma, update_mmu_cache(vma, address, ptep); } +static void set_huge_ptep_maybe_writable(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + if (vma->vm_flags & VM_WRITE) + set_huge_ptep_writable(vma, address, ptep); +} + bool is_hugetlb_entry_migration(pte_t pte) { swp_entry_t swp; @@ -5199,7 +5228,7 @@ static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, struct folio *new_folio, pte_t old, unsigned long sz) { - pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); + pte_t newpte = make_huge_pte(vma, &new_folio->page, true); __folio_mark_uptodate(new_folio); hugetlb_add_new_anon_rmap(new_folio, vma, addr); @@ -5333,14 +5362,14 @@ again: spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ - new_folio = alloc_hugetlb_folio(dst_vma, addr, 1); + new_folio = alloc_hugetlb_folio(dst_vma, addr, false); if (IS_ERR(new_folio)) { folio_put(pte_folio); ret = PTR_ERR(new_folio); break; } ret = copy_user_large_folio(new_folio, pte_folio, - ALIGN_DOWN(addr, sz), dst_vma); + addr, dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); @@ -5402,6 +5431,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { + bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; @@ -5418,7 +5448,18 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); - set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); + + if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) + huge_pte_clear(mm, new_addr, dst_pte, sz); + else { + if (need_clear_uffd_wp) { + if (pte_present(pte)) + pte = huge_pte_clear_uffd_wp(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_clear_uffd_wp(pte); + } + set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); + } if (src_ptl != dst_ptl) spin_unlock(src_ptl); @@ -5787,7 +5828,7 @@ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio, struct hstate *h = hstate_vma(vma); struct folio *old_folio; struct folio *new_folio; - int outside_reserve = 0; + bool cow_from_owner = 0; vm_fault_t ret = 0; struct mmu_notifier_range range; @@ -5802,13 +5843,6 @@ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio, if (!unshare && huge_pte_uffd_wp(pte)) return 0; - /* - * hugetlb does not support FOLL_FORCE-style write faults that keep the - * PTE mapped R/O such as maybe_mkwrite() would do. - */ - if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE))) - return VM_FAULT_SIGSEGV; - /* Let's take out MAP_SHARED mappings first. */ if (vma->vm_flags & VM_MAYSHARE) { set_huge_ptep_writable(vma, vmf->address, vmf->pte); @@ -5837,7 +5871,8 @@ retry_avoidcopy: SetPageAnonExclusive(&old_folio->page); } if (likely(!unshare)) - set_huge_ptep_writable(vma, vmf->address, vmf->pte); + set_huge_ptep_maybe_writable(vma, vmf->address, + vmf->pte); delayacct_wpcopy_end(); return 0; @@ -5856,7 +5891,7 @@ retry_avoidcopy: */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_folio != pagecache_folio) - outside_reserve = 1; + cow_from_owner = true; folio_get(old_folio); @@ -5865,7 +5900,7 @@ retry_avoidcopy: * be acquired again before returning to the caller, as expected. */ spin_unlock(vmf->ptl); - new_folio = alloc_hugetlb_folio(vma, vmf->address, outside_reserve); + new_folio = alloc_hugetlb_folio(vma, vmf->address, cow_from_owner); if (IS_ERR(new_folio)) { /* @@ -5875,7 +5910,7 @@ retry_avoidcopy: * reliability, unmap the page from child processes. The child * may get SIGKILLed if it later faults. */ - if (outside_reserve) { + if (cow_from_owner) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx; u32 hash; @@ -6126,7 +6161,7 @@ static vm_fault_t hugetlb_no_page(struct address_space *mapping, goto out; } - folio = alloc_hugetlb_folio(vma, vmf->address, 0); + folio = alloc_hugetlb_folio(vma, vmf->address, false); if (IS_ERR(folio)) { /* * Returning error will result in faulting task being @@ -6223,8 +6258,7 @@ static vm_fault_t hugetlb_no_page(struct address_space *mapping, hugetlb_add_new_anon_rmap(folio, vma, vmf->address); else hugetlb_add_file_rmap(folio); - new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE) - && (vma->vm_flags & VM_SHARED))); + new_pte = make_huge_pte(vma, &folio->page, vma->vm_flags & VM_SHARED); /* * If this pte was previously wr-protected, keep it wr-protected even * if populated. @@ -6556,7 +6590,6 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, spinlock_t *ptl; int ret = -ENOMEM; struct folio *folio; - int writable; bool folio_in_pagecache = false; if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) { @@ -6594,7 +6627,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, goto out; } - folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); + folio = alloc_hugetlb_folio(dst_vma, dst_addr, false); if (IS_ERR(folio)) { ret = -ENOMEM; goto out; @@ -6636,15 +6669,14 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, goto out; } - folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); + folio = alloc_hugetlb_folio(dst_vma, dst_addr, false); if (IS_ERR(folio)) { folio_put(*foliop); ret = -ENOMEM; *foliop = NULL; goto out; } - ret = copy_user_large_folio(folio, *foliop, - ALIGN_DOWN(dst_addr, size), dst_vma); + ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { @@ -6711,12 +6743,8 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY * with wp flag set, don't set pte write bit. */ - if (wp_enabled || (is_continue && !vm_shared)) - writable = 0; - else - writable = dst_vma->vm_flags & VM_WRITE; - - _dst_pte = make_huge_pte(dst_vma, &folio->page, writable); + _dst_pte = make_huge_pte(dst_vma, &folio->page, + !wp_enabled && !(is_continue && !vm_shared)); /* * Always mark UFFDIO_COPY page dirty; note that this may not be * extremely important for hugetlbfs for now since swapping is not @@ -7212,7 +7240,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7227,7 +7255,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7239,10 +7267,6 @@ out: /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7251,18 +7275,20 @@ out: int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; } @@ -7397,7 +7423,24 @@ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ -bool isolate_hugetlb(struct folio *folio, struct list_head *list) +/** + * folio_isolate_hugetlb - try to isolate an allocated hugetlb folio + * @folio: the folio to isolate + * @list: the list to add the folio to on success + * + * Isolate an allocated (refcount > 0) hugetlb folio, marking it as + * isolated/non-migratable, and moving it from the active list to the + * given list. + * + * Isolation will fail if @folio is not an allocated hugetlb folio, or if + * it is already isolated/non-migratable. + * + * On success, an additional folio reference is taken that must be dropped + * using folio_putback_hugetlb() to undo the isolation. + * + * Return: True if isolation worked, otherwise False. + */ +bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list) { bool ret = true; @@ -7445,7 +7488,18 @@ int get_huge_page_for_hwpoison(unsigned long pfn, int flags, return ret; } -void folio_putback_active_hugetlb(struct folio *folio) +/** + * folio_putback_hugetlb - unisolate a hugetlb folio + * @folio: the isolated hugetlb folio + * + * Putback/un-isolate the hugetlb folio that was previous isolated using + * folio_isolate_hugetlb(): marking it non-isolated/migratable and putting it + * back onto the active list. + * + * Will drop the additional folio reference obtained through + * folio_isolate_hugetlb(). + */ +void folio_putback_hugetlb(struct folio *folio) { spin_lock_irq(&hugetlb_lock); folio_set_hugetlb_migratable(folio); @@ -7492,6 +7546,16 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re } spin_unlock_irq(&hugetlb_lock); } + + /* + * Our old folio is isolated and has "migratable" cleared until it + * is putback. As migration succeeded, set the new folio "migratable" + * and add it to the active list. + */ + spin_lock_irq(&hugetlb_lock); + folio_set_hugetlb_migratable(new_folio); + list_move_tail(&new_folio->lru, &(folio_hstate(new_folio))->hugepage_activelist); + spin_unlock_irq(&hugetlb_lock); } static void hugetlb_unshare_pmds(struct vm_area_struct *vma, diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index e716c4671a15..bb9578bd99f9 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -195,24 +195,23 @@ static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) * cannot fail. */ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, - struct page *page) + struct folio *folio) { unsigned int nr_pages; struct page_counter *counter; - struct hugetlb_cgroup *page_hcg; + struct hugetlb_cgroup *hcg; struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); - struct folio *folio = page_folio(page); - page_hcg = hugetlb_cgroup_from_folio(folio); + hcg = hugetlb_cgroup_from_folio(folio); /* * We can have pages in active list without any cgroup * ie, hugepage with less than 3 pages. We can safely * ignore those pages. */ - if (!page_hcg || page_hcg != h_cg) + if (!hcg || hcg != h_cg) goto out; - nr_pages = compound_nr(page); + nr_pages = folio_nr_pages(folio); if (!parent) { parent = root_h_cgroup; /* root has no limit */ @@ -235,13 +234,13 @@ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) { struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; - struct page *page; + struct folio *folio; do { for_each_hstate(h) { spin_lock_irq(&hugetlb_lock); - list_for_each_entry(page, &h->hugepage_activelist, lru) - hugetlb_cgroup_move_parent(hstate_index(h), h_cg, page); + list_for_each_entry(folio, &h->hugepage_activelist, lru) + hugetlb_cgroup_move_parent(hstate_index(h), h_cg, folio); spin_unlock_irq(&hugetlb_lock); } @@ -917,7 +916,6 @@ void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio) set_hugetlb_cgroup_rsvd(new_folio, h_cg_rsvd); list_move(&new_folio->lru, &h->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); - return; } static struct cftype hugetlb_files[] = { diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 57b7f591eee8..7735972add01 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -693,7 +693,7 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l free_vmemmap_page_list(&vmemmap_pages); } -static struct ctl_table hugetlb_vmemmap_sysctls[] = { +static const struct ctl_table hugetlb_vmemmap_sysctls[] = { { .procname = "hugetlb_optimize_vmemmap", .data = &vmemmap_optimize_enabled, diff --git a/mm/init-mm.c b/mm/init-mm.c index 24c809379274..6af3ad675930 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -40,7 +40,7 @@ struct mm_struct init_mm = { .arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), #ifdef CONFIG_PER_VMA_LOCK - .mm_lock_seq = 0, + .mm_lock_seq = SEQCNT_ZERO(init_mm.mm_lock_seq), #endif .user_ns = &init_user_ns, .cpu_bitmap = CPU_BITS_NONE, diff --git a/mm/internal.h b/mm/internal.h index cb8d8e8e3ffa..109ef30fee11 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -392,6 +392,8 @@ void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); +int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, + gfp_t gfp); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *, unsigned int order); @@ -735,15 +737,30 @@ static inline void prep_compound_tail(struct page *head, int tail_idx) extern void prep_compound_page(struct page *page, unsigned int order); -extern void post_alloc_hook(struct page *page, unsigned int order, - gfp_t gfp_flags); +void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; -void free_unref_page(struct page *page, unsigned int order); +struct page *__alloc_frozen_pages_noprof(gfp_t, unsigned int order, int nid, + nodemask_t *); +#define __alloc_frozen_pages(...) \ + alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__)) +void free_frozen_pages(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); +#ifdef CONFIG_NUMA +struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order); +#else +static inline struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order) +{ + return __alloc_frozen_pages_noprof(gfp, order, numa_node_id(), NULL); +} +#endif + +#define alloc_frozen_pages(...) \ + alloc_hooks(alloc_frozen_pages_noprof(__VA_ARGS__)) + extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); @@ -824,10 +841,6 @@ int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); -int __alloc_contig_migrate_range(struct compact_control *cc, - unsigned long start, unsigned long end, - int migratetype); - /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); @@ -1285,12 +1298,6 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr, void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); -static inline bool alloc_zeroed(void) -{ - return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, - &init_on_alloc); -} - /* * Parses a string with mem suffixes into its order. Useful to parse kernel * parameters. @@ -1446,22 +1453,6 @@ void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); -#ifdef CONFIG_64BIT -static inline int can_do_mseal(unsigned long flags) -{ - if (flags) - return -EINVAL; - - return 0; -} - -#else -static inline int can_do_mseal(unsigned long flags) -{ - return -EPERM; -} -#endif - #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) @@ -1510,6 +1501,12 @@ static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; +#define mapping_set_update(xas, mapping) do { \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ + xas_set_update(xas, workingset_update_node); \ + xas_set_lru(xas, &shadow_nodes); \ + } \ +} while (0) /* mremap.c */ unsigned long move_page_tables(struct vm_area_struct *vma, @@ -1530,4 +1527,23 @@ int walk_page_range_mm(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); +/* pt_reclaim.c */ +bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval); +void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb, + pmd_t pmdval); +void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, + struct mmu_gather *tlb); + +#ifdef CONFIG_PT_RECLAIM +bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, + struct zap_details *details); +#else +static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, + struct zap_details *details) +{ + return false; +} +#endif /* CONFIG_PT_RECLAIM */ + + #endif /* __MM_INTERNAL_H */ diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 8b9e348113b1..d54e89f8c3e7 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -524,7 +524,11 @@ size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object) sizeof(struct kasan_free_meta) : 0); } -static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags) +/* + * This function avoids dynamic memory allocations and thus can be called from + * contexts that do not allow allocating memory. + */ +void kasan_record_aux_stack(void *addr) { struct slab *slab = kasan_addr_to_slab(addr); struct kmem_cache *cache; @@ -541,17 +545,7 @@ static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags) return; alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0]; - alloc_meta->aux_stack[0] = kasan_save_stack(0, depot_flags); -} - -void kasan_record_aux_stack(void *addr) -{ - return __kasan_record_aux_stack(addr, STACK_DEPOT_FLAG_CAN_ALLOC); -} - -void kasan_record_aux_stack_noalloc(void *addr) -{ - return __kasan_record_aux_stack(addr, 0); + alloc_meta->aux_stack[0] = kasan_save_stack(0, 0); } void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags) diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index ccd66c7a4081..9a6927394b54 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -263,8 +264,8 @@ void __init kasan_init_hw_tags(void) pr_info("KernelAddressSanitizer initialized (hw-tags, mode=%s, vmalloc=%s, stacktrace=%s)\n", kasan_mode_info(), - kasan_vmalloc_enabled() ? "on" : "off", - kasan_stack_collection_enabled() ? "on" : "off"); + str_on_off(kasan_vmalloc_enabled()), + str_on_off(kasan_stack_collection_enabled())); } #ifdef CONFIG_KASAN_VMALLOC diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index b7e4b81421b3..129178be5e64 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -501,18 +501,18 @@ static inline bool kasan_byte_accessible(const void *addr) /** * kasan_poison - mark the memory range as inaccessible - * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE - * @size - range size, must be aligned to KASAN_GRANULE_SIZE - * @value - value that's written to metadata for the range - * @init - whether to initialize the memory range (only for hardware tag-based) + * @addr: range start address, must be aligned to KASAN_GRANULE_SIZE + * @size: range size, must be aligned to KASAN_GRANULE_SIZE + * @value: value that's written to metadata for the range + * @init: whether to initialize the memory range (only for hardware tag-based) */ void kasan_poison(const void *addr, size_t size, u8 value, bool init); /** * kasan_unpoison - mark the memory range as accessible - * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE - * @size - range size, can be unaligned - * @init - whether to initialize the memory range (only for hardware tag-based) + * @addr: range start address, must be aligned to KASAN_GRANULE_SIZE + * @size: range size, can be unaligned + * @init: whether to initialize the memory range (only for hardware tag-based) * * For the tag-based modes, the @size gets aligned to KASAN_GRANULE_SIZE before * marking the range. @@ -530,8 +530,8 @@ bool kasan_byte_accessible(const void *addr); /** * kasan_poison_last_granule - mark the last granule of the memory range as * inaccessible - * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE - * @size - range size + * @address: range start address, must be aligned to KASAN_GRANULE_SIZE + * @size: range size * * This function is only available for the generic mode, as it's the only mode * that has partially poisoned memory granules. diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index 99d4ff0ed57a..59d673400085 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -47,8 +47,8 @@ static struct { * Some tests use these global variables to store return values from function * calls that could otherwise be eliminated by the compiler as dead code. */ -void *kasan_ptr_result; -int kasan_int_result; +static volatile void *kasan_ptr_result; +static volatile int kasan_int_result; /* Probe for console output: obtains test_status lines of interest. */ static void probe_console(void *ignore, const char *buf, size_t len) diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c index 220b5d4c6876..b9382b5b6a37 100644 --- a/mm/kasan/sw_tags.c +++ b/mm/kasan/sw_tags.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -45,7 +46,7 @@ void __init kasan_init_sw_tags(void) kasan_init_tags(); pr_info("KernelAddressSanitizer initialized (sw-tags, stacktrace=%s)\n", - kasan_stack_collection_enabled() ? "on" : "off"); + str_on_off(kasan_stack_collection_enabled())); } /* diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 67fc321db79b..102048821c22 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -1084,6 +1085,7 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) * properties (e.g. reside in DMAable memory). */ if ((flags & GFP_ZONEMASK) || + ((flags & __GFP_THISNODE) && num_online_nodes() > 1) || (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) { atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index f65fb182466d..00034e37bc9f 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -88,7 +89,7 @@ struct expect_report { static const char *get_access_type(const struct expect_report *r) { - return r->is_write ? "write" : "read"; + return str_write_read(r->is_write); } /* Check observed report matches information in @r. */ diff --git a/mm/kfence/report.c b/mm/kfence/report.c index 6370c5207d1a..10e6802a2edf 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -184,7 +185,7 @@ static void print_diff_canary(unsigned long address, size_t bytes_to_show, static const char *get_access_type(bool is_write) { - return is_write ? "write" : "read"; + return str_write_read(is_write); } void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *regs, diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6f8d46d107b4..5f0be134141e 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -947,17 +948,10 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, return SCAN_SUCCEED; } -static int find_pmd_or_thp_or_none(struct mm_struct *mm, - unsigned long address, - pmd_t **pmd) +static inline int check_pmd_state(pmd_t *pmd) { - pmd_t pmde; + pmd_t pmde = pmdp_get_lockless(pmd); - *pmd = mm_find_pmd(mm, address); - if (!*pmd) - return SCAN_PMD_NULL; - - pmde = pmdp_get_lockless(*pmd); if (pmd_none(pmde)) return SCAN_PMD_NONE; if (!pmd_present(pmde)) @@ -971,6 +965,17 @@ static int find_pmd_or_thp_or_none(struct mm_struct *mm, return SCAN_SUCCEED; } +static int find_pmd_or_thp_or_none(struct mm_struct *mm, + unsigned long address, + pmd_t **pmd) +{ + *pmd = mm_find_pmd(mm, address); + if (!*pmd) + return SCAN_PMD_NULL; + + return check_pmd_state(*pmd); +} + static int check_pmd_still_valid(struct mm_struct *mm, unsigned long address, pmd_t *pmd) @@ -1720,7 +1725,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) pmd_t *pmd, pgt_pmd; spinlock_t *pml; spinlock_t *ptl; - bool skipped_uffd = false; + bool success = false; /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that @@ -1757,6 +1762,19 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) mmu_notifier_invalidate_range_start(&range); pml = pmd_lock(mm, pmd); + /* + * The lock of new_folio is still held, we will be blocked in + * the page fault path, which prevents the pte entries from + * being set again. So even though the old empty PTE page may be + * concurrently freed and a new PTE page is filled into the pmd + * entry, it is still empty and can be removed. + * + * So here we only need to recheck if the state of pmd entry + * still meets our requirements, rather than checking pmd_same() + * like elsewhere. + */ + if (check_pmd_state(pmd) != SCAN_SUCCEED) + goto drop_pml; ptl = pte_lockptr(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); @@ -1770,20 +1788,20 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) * repeating the anon_vma check protects from one category, * and repeating the userfaultfd_wp() check from another. */ - if (unlikely(vma->anon_vma || userfaultfd_wp(vma))) { - skipped_uffd = true; - } else { + if (likely(!vma->anon_vma && !userfaultfd_wp(vma))) { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); + success = true; } if (ptl != pml) spin_unlock(ptl); +drop_pml: spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); - if (!skipped_uffd) { + if (success) { mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); @@ -1837,6 +1855,8 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, if (result != SCAN_SUCCEED) goto out; + mapping_set_update(&xas, mapping); + __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); @@ -2419,7 +2439,7 @@ skip: VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); - if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { + if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); @@ -2765,7 +2785,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); - if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { + if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 2a945c07ae99..c6ed68604136 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -373,7 +373,7 @@ static void print_unreferenced(struct seq_file *seq, for (i = 0; i < nr_entries; i++) { void *ptr = (void *)entries[i]; - warn_or_seq_printf(seq, " [<%pK>] %pS\n", ptr, ptr); + warn_or_seq_printf(seq, " %pS\n", ptr); } } @@ -1093,7 +1093,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, pr_debug("%s(0x%px, %zu)\n", __func__, ptr, size); if (kmemleak_enabled && ptr && !IS_ERR_PCPU(ptr)) - create_object_percpu((__force unsigned long)ptr, size, 0, gfp); + create_object_percpu((__force unsigned long)ptr, size, 1, gfp); } EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); @@ -1689,7 +1689,7 @@ static void kmemleak_scan(void) unsigned long phys = object->pointer; if (PHYS_PFN(phys) < min_low_pfn || - PHYS_PFN(phys + object->size) >= max_low_pfn) + PHYS_PFN(phys + object->size) > max_low_pfn) __paint_it(object, KMEMLEAK_BLACK); } @@ -1855,7 +1855,7 @@ static int kmemleak_scan_thread(void *arg) * Wait before the first scan to allow the system to fully initialize. */ if (first_run) { - signed long timeout = msecs_to_jiffies(SECS_FIRST_SCAN * 1000); + signed long timeout = secs_to_jiffies(SECS_FIRST_SCAN); first_run = 0; while (timeout && !kthread_should_stop()) timeout = schedule_timeout_interruptible(timeout); @@ -2241,7 +2241,7 @@ void __init kmemleak_init(void) return; jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE); - jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000); + jiffies_scan_wait = secs_to_jiffies(SECS_SCAN_WAIT); object_cache = KMEM_CACHE(kmemleak_object, SLAB_NOLEAKTRACE); scan_area_cache = KMEM_CACHE(kmemleak_scan_area, SLAB_NOLEAKTRACE); diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c index 9c58f081d84f..1bb505a08415 100644 --- a/mm/kmsan/shadow.c +++ b/mm/kmsan/shadow.c @@ -280,12 +280,8 @@ void __init kmsan_init_alloc_meta_for_range(void *start, void *end) start = (void *)PAGE_ALIGN_DOWN((u64)start); size = PAGE_ALIGN((u64)end - (u64)start); - shadow = memblock_alloc(size, PAGE_SIZE); - origin = memblock_alloc(size, PAGE_SIZE); - - if (!shadow || !origin) - panic("%s: Failed to allocate metadata memory for early boot range of size %llu", - __func__, size); + shadow = memblock_alloc_or_panic(size, PAGE_SIZE); + origin = memblock_alloc_or_panic(size, PAGE_SIZE); for (u64 addr = 0; addr < size; addr += PAGE_SIZE) { page = virt_to_page_or_null((char *)start + addr); diff --git a/mm/ksm.c b/mm/ksm.c index 31a9bc365437..8be2b144fefd 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -3262,6 +3262,25 @@ static void wait_while_offlining(void) #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_PROC_FS +/* + * The process is mergeable only if any VMA is currently + * applicable to KSM. + * + * The mmap lock must be held in read mode. + */ +bool ksm_process_mergeable(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + mmap_assert_locked(mm); + VMA_ITERATOR(vmi, mm, 0); + for_each_vma(vmi, vma) + if (vma->vm_flags & VM_MERGEABLE) + return true; + + return false; +} + long ksm_process_profit(struct mm_struct *mm) { return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE - diff --git a/mm/list_lru.c b/mm/list_lru.c index f93ada6a207b..7d69434c70e0 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -77,7 +77,6 @@ again: spin_lock(&l->lock); nr_items = READ_ONCE(l->nr_items); if (likely(nr_items != LONG_MIN)) { - WARN_ON(nr_items < 0); rcu_read_unlock(); return l; } @@ -450,6 +449,7 @@ static void memcg_reparent_list_lru_one(struct list_lru *lru, int nid, list_splice_init(&src->list, &dst->list); if (src->nr_items) { + WARN_ON(src->nr_items < 0); dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); } diff --git a/mm/madvise.c b/mm/madvise.c index 0ceae57da7da..49f3a75046f6 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -851,7 +851,12 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, static long madvise_dontneed_single_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - zap_page_range_single(vma, start, end - start, NULL); + struct zap_details details = { + .reclaim_pt = true, + .even_cows = true, + }; + + zap_page_range_single(vma, start, end - start, &details); return 0; } diff --git a/mm/memblock.c b/mm/memblock.c index 095c18b5c430..95af35fd1389 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1691,6 +1691,26 @@ void * __init memblock_alloc_try_nid( return ptr; } +/** + * __memblock_alloc_or_panic - Try to allocate memory and panic on failure + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @func: caller func name + * + * This function attempts to allocate memory using memblock_alloc, + * and in case of failure, it calls panic with the formatted message. + * This function should not be used directly, please use the macro memblock_alloc_or_panic. + */ +void *__init __memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align, + const char *func) +{ + void *addr = memblock_alloc(size, align); + + if (unlikely(!addr)) + panic("%s: Failed to allocate %pap bytes\n", func, &size); + return addr; +} + /** * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index a071fa43d479..2be6b9112808 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -899,7 +899,7 @@ static void memcg_event_remove(struct work_struct *work) * * Called with wqh->lock held and interrupts disabled. */ -static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode, +static int memcg_event_wake(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { struct mem_cgroup_event *event = @@ -1040,13 +1040,13 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, } else if (!strcmp(name, "memory.oom_control")) { pr_warn_once("oom_control is deprecated and will be removed. " "Please report your usecase to linux-mm-@kvack.org" - " if you depend on this functionality. \n"); + " if you depend on this functionality.\n"); event->register_event = mem_cgroup_oom_register_event; event->unregister_event = mem_cgroup_oom_unregister_event; } else if (!strcmp(name, "memory.pressure_level")) { pr_warn_once("pressure_level is deprecated and will be removed. " "Please report your usecase to linux-mm-@kvack.org " - "if you depend on this functionality. \n"); + "if you depend on this functionality.\n"); event->register_event = vmpressure_register_event; event->unregister_event = vmpressure_unregister_event; } else if (!strcmp(name, "memory.memsw.usage_in_bytes")) { @@ -1134,8 +1134,8 @@ static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg) failed = iter; mem_cgroup_iter_break(memcg, iter); break; - } else - iter->oom_lock = true; + } + iter->oom_lock = true; } if (failed) { @@ -1202,7 +1202,7 @@ struct oom_wait_info { }; static int memcg_oom_wake_function(wait_queue_entry_t *wait, - unsigned mode, int sync, void *arg) + unsigned int mode, int sync, void *arg) { struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg; struct mem_cgroup *oom_wait_memcg; @@ -1644,7 +1644,7 @@ static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, unsigned long nr = 0; enum lru_list lru; - VM_BUG_ON((unsigned)nid >= nr_node_ids); + VM_BUG_ON((unsigned int)nid >= nr_node_ids); for_each_lru(lru) { if (!(BIT(lru) & lru_mask)) @@ -1881,7 +1881,7 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, pr_warn_once("oom_control is deprecated and will be removed. " "Please report your usecase to linux-mm-@kvack.org if you " - "depend on this functionality. \n"); + "depend on this functionality.\n"); /* cannot set to root cgroup and only 0 and 1 are allowed */ if (mem_cgroup_is_root(memcg) || !((val == 0) || (val == 1))) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7b3503d12aaf..46f8b372d212 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1161,6 +1161,7 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, { struct mem_cgroup *iter; int ret = 0; + int i = 0; BUG_ON(mem_cgroup_is_root(memcg)); @@ -1169,8 +1170,12 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, struct task_struct *task; css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); - while (!ret && (task = css_task_iter_next(&it))) + while (!ret && (task = css_task_iter_next(&it))) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + cond_resched(); ret = fn(task, arg); + } css_task_iter_end(&it); if (ret) { mem_cgroup_iter_break(memcg, iter); @@ -1448,6 +1453,18 @@ unsigned long memcg_page_state_local_output(struct mem_cgroup *memcg, int item) memcg_page_state_output_unit(item); } +#ifdef CONFIG_HUGETLB_PAGE +static bool memcg_accounts_hugetlb(void) +{ + return cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; +} +#else /* CONFIG_HUGETLB_PAGE */ +static bool memcg_accounts_hugetlb(void) +{ + return false; +} +#endif /* CONFIG_HUGETLB_PAGE */ + static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) { int i; @@ -1469,7 +1486,7 @@ static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) #ifdef CONFIG_HUGETLB_PAGE if (unlikely(memory_stats[i].idx == NR_HUGETLB) && - !(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)) + !memcg_accounts_hugetlb()) continue; #endif size = memcg_page_state_output(memcg, memory_stats[i].idx); @@ -2371,21 +2388,6 @@ done_restock: return 0; } -/** - * mem_cgroup_cancel_charge() - cancel an uncommitted try_charge() call. - * @memcg: memcg previously charged. - * @nr_pages: number of pages previously charged. - */ -void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) -{ - if (mem_cgroup_is_root(memcg)) - return; - - page_counter_uncharge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_uncharge(&memcg->memsw, nr_pages); -} - static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) { VM_BUG_ON_FOLIO(folio_memcg_charged(folio), folio); @@ -2399,18 +2401,6 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) folio->memcg_data = (unsigned long)memcg; } -/** - * mem_cgroup_commit_charge - commit a previously successful try_charge(). - * @folio: folio to commit the charge to. - * @memcg: memcg previously charged. - */ -void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg) -{ - css_get(&memcg->css); - commit_charge(folio, memcg); - memcg1_commit_charge(folio, memcg); -} - static inline void __mod_objcg_mlstate(struct obj_cgroup *objcg, struct pglist_data *pgdat, enum node_stat_item idx, int nr) @@ -4498,7 +4488,9 @@ static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg, if (ret) goto out; - mem_cgroup_commit_charge(folio, memcg); + css_get(&memcg->css); + commit_charge(folio, memcg); + memcg1_commit_charge(folio, memcg); out: return ret; } @@ -4516,38 +4508,37 @@ int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) } /** - * mem_cgroup_hugetlb_try_charge - try to charge the memcg for a hugetlb folio - * @memcg: memcg to charge. - * @gfp: reclaim mode. - * @nr_pages: number of pages to charge. + * mem_cgroup_charge_hugetlb - charge the memcg for a hugetlb folio + * @folio: folio being charged + * @gfp: reclaim mode * - * This function is called when allocating a huge page folio to determine if - * the memcg has the capacity for it. It does not commit the charge yet, - * as the hugetlb folio itself has not been obtained from the hugetlb pool. + * This function is called when allocating a huge page folio, after the page has + * already been obtained and charged to the appropriate hugetlb cgroup + * controller (if it is enabled). * - * Once we have obtained the hugetlb folio, we can call - * mem_cgroup_commit_charge() to commit the charge. If we fail to obtain the - * folio, we should instead call mem_cgroup_cancel_charge() to undo the effect - * of try_charge(). - * - * Returns 0 on success. Otherwise, an error code is returned. + * Returns ENOMEM if the memcg is already full. + * Returns 0 if either the charge was successful, or if we skip the charging. */ -int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp, - long nr_pages) +int mem_cgroup_charge_hugetlb(struct folio *folio, gfp_t gfp) { + struct mem_cgroup *memcg = get_mem_cgroup_from_current(); + int ret = 0; + /* - * If hugetlb memcg charging is not enabled, do not fail hugetlb allocation, - * but do not attempt to commit charge later (or cancel on error) either. + * Even memcg does not account for hugetlb, we still want to update + * system-level stats via lruvec_stat_mod_folio. Return 0, and skip + * charging the memcg. */ - if (mem_cgroup_disabled() || !memcg || - !cgroup_subsys_on_dfl(memory_cgrp_subsys) || - !(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)) - return -EOPNOTSUPP; + if (mem_cgroup_disabled() || !memcg_accounts_hugetlb() || + !memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + goto out; - if (try_charge(memcg, gfp, nr_pages)) - return -ENOMEM; + if (charge_memcg(folio, memcg, gfp)) + ret = -ENOMEM; - return 0; +out: + mem_cgroup_put(memcg); + return ret; } /** @@ -4609,7 +4600,7 @@ void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) * correspond 1:1 to page and swap slot lifetimes: we charge the * page to memory here, and uncharge swap when the slot is freed. */ - if (!mem_cgroup_disabled() && do_memsw_account()) { + if (do_memsw_account()) { /* * The swap entry might not get freed for a long time, * let's not wait for it. The page already received a @@ -4973,7 +4964,6 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { struct mem_cgroup *memcg, *swap_memcg; unsigned int nr_entries; - unsigned short oldid; VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); @@ -5000,11 +4990,10 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) /* Get references for the tail pages, too */ if (nr_entries > 1) mem_cgroup_id_get_many(swap_memcg, nr_entries - 1); - oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg), - nr_entries); - VM_BUG_ON_FOLIO(oldid, folio); mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); + swap_cgroup_record(folio, entry); + folio_unqueue_deferred_split(folio); folio->memcg_data = 0; @@ -5035,7 +5024,6 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) unsigned int nr_pages = folio_nr_pages(folio); struct page_counter *counter; struct mem_cgroup *memcg; - unsigned short oldid; if (do_memsw_account()) return 0; @@ -5064,10 +5052,10 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) /* Get references for the tail pages, too */ if (nr_pages > 1) mem_cgroup_id_get_many(memcg, nr_pages - 1); - oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages); - VM_BUG_ON_FOLIO(oldid, folio); mod_memcg_state(memcg, MEMCG_SWAP, nr_pages); + swap_cgroup_record(folio, entry); + return 0; } @@ -5081,7 +5069,7 @@ void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) struct mem_cgroup *memcg; unsigned short id; - id = swap_cgroup_record(entry, 0, nr_pages); + id = swap_cgroup_clear(entry, nr_pages); rcu_read_lock(); memcg = mem_cgroup_from_id(id); if (memcg) { diff --git a/mm/memfd.c b/mm/memfd.c index c17c3ea701a1..37f7be57c2f5 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -327,15 +327,51 @@ static int check_sysctl_memfd_noexec(unsigned int *flags) return 0; } -SYSCALL_DEFINE2(memfd_create, - const char __user *, uname, - unsigned int, flags) +static inline bool is_write_sealed(unsigned int seals) { - unsigned int *file_seals; - struct file *file; - int fd, error; - char *name; - long len; + return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); +} + +static int check_write_seal(unsigned long *vm_flags_ptr) +{ + unsigned long vm_flags = *vm_flags_ptr; + unsigned long mask = vm_flags & (VM_SHARED | VM_WRITE); + + /* If a private matting then writability is irrelevant. */ + if (!(mask & VM_SHARED)) + return 0; + + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * write seals are active. + */ + if (mask & VM_WRITE) + return -EPERM; + + /* + * This is a read-only mapping, disallow mprotect() from making a + * write-sealed mapping writable in future. + */ + *vm_flags_ptr &= ~VM_MAYWRITE; + + return 0; +} + +int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr) +{ + int err = 0; + unsigned int *seals_ptr = memfd_file_seals_ptr(file); + unsigned int seals = seals_ptr ? *seals_ptr : 0; + + if (is_write_sealed(seals)) + err = check_write_seal(vm_flags_ptr); + + return err; +} + +static int sanitize_flags(unsigned int *flags_ptr) +{ + unsigned int flags = *flags_ptr; if (!(flags & MFD_HUGETLB)) { if (flags & ~(unsigned int)MFD_ALL_FLAGS) @@ -351,50 +387,52 @@ SYSCALL_DEFINE2(memfd_create, if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL)) return -EINVAL; - error = check_sysctl_memfd_noexec(&flags); - if (error < 0) - return error; + return check_sysctl_memfd_noexec(flags_ptr); +} - /* length includes terminating zero */ - len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); - if (len <= 0) - return -EFAULT; - if (len > MFD_NAME_MAX_LEN + 1) - return -EINVAL; +static char *alloc_name(const char __user *uname) +{ + int error; + char *name; + long len; - name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_KERNEL); + name = kmalloc(NAME_MAX + 1, GFP_KERNEL); if (!name) - return -ENOMEM; + return ERR_PTR(-ENOMEM); strcpy(name, MFD_NAME_PREFIX); - if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) { + /* returned length does not include terminating zero */ + len = strncpy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, MFD_NAME_MAX_LEN + 1); + if (len < 0) { error = -EFAULT; goto err_name; + } else if (len > MFD_NAME_MAX_LEN) { + error = -EINVAL; + goto err_name; } - /* terminating-zero may have changed after strnlen_user() returned */ - if (name[len + MFD_NAME_PREFIX_LEN - 1]) { - error = -EFAULT; - goto err_name; - } + return name; - fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0); - if (fd < 0) { - error = fd; - goto err_name; - } +err_name: + kfree(name); + return ERR_PTR(error); +} + +static struct file *alloc_file(const char *name, unsigned int flags) +{ + unsigned int *file_seals; + struct file *file; if (flags & MFD_HUGETLB) { file = hugetlb_file_setup(name, 0, VM_NORESERVE, HUGETLB_ANONHUGE_INODE, (flags >> MFD_HUGE_SHIFT) & MFD_HUGE_MASK); - } else + } else { file = shmem_file_setup(name, 0, VM_NORESERVE); - if (IS_ERR(file)) { - error = PTR_ERR(file); - goto err_fd; } + if (IS_ERR(file)) + return file; file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_LARGEFILE; @@ -414,6 +452,37 @@ SYSCALL_DEFINE2(memfd_create, *file_seals &= ~F_SEAL_SEAL; } + return file; +} + +SYSCALL_DEFINE2(memfd_create, + const char __user *, uname, + unsigned int, flags) +{ + struct file *file; + int fd, error; + char *name; + + error = sanitize_flags(&flags); + if (error < 0) + return error; + + name = alloc_name(uname); + if (IS_ERR(name)) + return PTR_ERR(name); + + fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0); + if (fd < 0) { + error = fd; + goto err_name; + } + + file = alloc_file(name, flags); + if (IS_ERR(file)) { + error = PTR_ERR(file); + goto err_fd; + } + fd_install(fd, file); kfree(name); return fd; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index a7b8ccd29b6f..995a15eb67e2 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -124,7 +124,7 @@ const struct attribute_group memory_failure_attr_group = { .attrs = memory_failure_attr, }; -static struct ctl_table memory_failure_table[] = { +static const struct ctl_table memory_failure_table[] = { { .procname = "memory_failure_early_kill", .data = &sysctl_memory_failure_early_kill, diff --git a/mm/memory.c b/mm/memory.c index 75c2dfd04f72..539c0f7c6d54 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -76,6 +76,7 @@ #include #include #include +#include #include @@ -1436,7 +1437,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) static inline bool should_zap_cows(struct zap_details *details) { /* By default, zap all pages */ - if (!details) + if (!details || details->reclaim_pt) return true; /* Or, we zap COWed pages only if the caller wants to */ @@ -1466,34 +1467,42 @@ static inline bool zap_drop_markers(struct zap_details *details) /* * This function makes sure that we'll replace the none pte with an uffd-wp * swap special pte marker when necessary. Must be with the pgtable lock held. + * + * Returns true if uffd-wp ptes was installed, false otherwise. */ -static inline void +static inline bool zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, int nr, struct zap_details *details, pte_t pteval) { + bool was_installed = false; + +#ifdef CONFIG_PTE_MARKER_UFFD_WP /* Zap on anonymous always means dropping everything */ if (vma_is_anonymous(vma)) - return; + return false; if (zap_drop_markers(details)) - return; + return false; for (;;) { /* the PFN in the PTE is irrelevant. */ - pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); + if (pte_install_uffd_wp_if_needed(vma, addr, pte, pteval)) + was_installed = true; if (--nr == 0) break; pte++; addr += PAGE_SIZE; } +#endif + return was_installed; } static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, struct folio *folio, struct page *page, pte_t *pte, pte_t ptent, unsigned int nr, unsigned long addr, struct zap_details *details, int *rss, - bool *force_flush, bool *force_break) + bool *force_flush, bool *force_break, bool *any_skipped) { struct mm_struct *mm = tlb->mm; bool delay_rmap = false; @@ -1519,8 +1528,8 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entries(tlb, pte, nr, addr); if (unlikely(userfaultfd_pte_wp(vma, ptent))) - zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, - ptent); + *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, + nr, details, ptent); if (!delay_rmap) { folio_remove_rmap_ptes(folio, page, nr, vma); @@ -1544,7 +1553,7 @@ static inline int zap_present_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, pte_t *pte, pte_t ptent, unsigned int max_nr, unsigned long addr, struct zap_details *details, int *rss, bool *force_flush, - bool *force_break) + bool *force_break, bool *any_skipped) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; struct mm_struct *mm = tlb->mm; @@ -1559,15 +1568,17 @@ static inline int zap_present_ptes(struct mmu_gather *tlb, arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entry(tlb, pte, addr); if (userfaultfd_pte_wp(vma, ptent)) - zap_install_uffd_wp_if_needed(vma, addr, pte, 1, - details, ptent); + *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, + pte, 1, details, ptent); ksm_might_unmap_zero_page(mm, ptent); return 1; } folio = page_folio(page); - if (unlikely(!should_zap_folio(details, folio))) + if (unlikely(!should_zap_folio(details, folio))) { + *any_skipped = true; return 1; + } /* * Make sure that the common "small folio" case is as fast as possible @@ -1579,14 +1590,121 @@ static inline int zap_present_ptes(struct mmu_gather *tlb, zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, addr, details, rss, force_flush, - force_break); + force_break, any_skipped); return nr; } zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr, - details, rss, force_flush, force_break); + details, rss, force_flush, force_break, any_skipped); return 1; } +static inline int zap_nonpresent_ptes(struct mmu_gather *tlb, + struct vm_area_struct *vma, pte_t *pte, pte_t ptent, + unsigned int max_nr, unsigned long addr, + struct zap_details *details, int *rss, bool *any_skipped) +{ + swp_entry_t entry; + int nr = 1; + + *any_skipped = true; + entry = pte_to_swp_entry(ptent); + if (is_device_private_entry(entry) || + is_device_exclusive_entry(entry)) { + struct page *page = pfn_swap_entry_to_page(entry); + struct folio *folio = page_folio(page); + + if (unlikely(!should_zap_folio(details, folio))) + return 1; + /* + * Both device private/exclusive mappings should only + * work with anonymous page so far, so we don't need to + * consider uffd-wp bit when zap. For more information, + * see zap_install_uffd_wp_if_needed(). + */ + WARN_ON_ONCE(!vma_is_anonymous(vma)); + rss[mm_counter(folio)]--; + if (is_device_private_entry(entry)) + folio_remove_rmap_pte(folio, page, vma); + folio_put(folio); + } else if (!non_swap_entry(entry)) { + /* Genuine swap entries, hence a private anon pages */ + if (!should_zap_cows(details)) + return 1; + + nr = swap_pte_batch(pte, max_nr, ptent); + rss[MM_SWAPENTS] -= nr; + free_swap_and_cache_nr(entry, nr); + } else if (is_migration_entry(entry)) { + struct folio *folio = pfn_swap_entry_folio(entry); + + if (!should_zap_folio(details, folio)) + return 1; + rss[mm_counter(folio)]--; + } else if (pte_marker_entry_uffd_wp(entry)) { + /* + * For anon: always drop the marker; for file: only + * drop the marker if explicitly requested. + */ + if (!vma_is_anonymous(vma) && !zap_drop_markers(details)) + return 1; + } else if (is_guard_swp_entry(entry)) { + /* + * Ordinary zapping should not remove guard PTE + * markers. Only do so if we should remove PTE markers + * in general. + */ + if (!zap_drop_markers(details)) + return 1; + } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { + if (!should_zap_cows(details)) + return 1; + } else { + /* We should have covered all the swap entry types */ + pr_alert("unrecognized swap entry 0x%lx\n", entry.val); + WARN_ON_ONCE(1); + } + clear_not_present_full_ptes(vma->vm_mm, addr, pte, nr, tlb->fullmm); + *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); + + return nr; +} + +static inline int do_zap_pte_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pte_t *pte, + unsigned long addr, unsigned long end, + struct zap_details *details, int *rss, + bool *force_flush, bool *force_break, + bool *any_skipped) +{ + pte_t ptent = ptep_get(pte); + int max_nr = (end - addr) / PAGE_SIZE; + int nr = 0; + + /* Skip all consecutive none ptes */ + if (pte_none(ptent)) { + for (nr = 1; nr < max_nr; nr++) { + ptent = ptep_get(pte + nr); + if (!pte_none(ptent)) + break; + } + max_nr -= nr; + if (!max_nr) + return nr; + pte += nr; + addr += nr * PAGE_SIZE; + } + + if (pte_present(ptent)) + nr += zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr, + details, rss, force_flush, force_break, + any_skipped); + else + nr += zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr, + details, rss, any_skipped); + + return nr; +} + static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, @@ -1598,9 +1716,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, spinlock_t *ptl; pte_t *start_pte; pte_t *pte; - swp_entry_t entry; + pmd_t pmdval; + unsigned long start = addr; + bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details); + bool direct_reclaim = false; int nr; +retry: tlb_change_page_size(tlb, PAGE_SIZE); init_rss_vec(rss); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); @@ -1610,90 +1732,24 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { - pte_t ptent = ptep_get(pte); - struct folio *folio; - struct page *page; - int max_nr; - - nr = 1; - if (pte_none(ptent)) - continue; + bool any_skipped = false; if (need_resched()) break; - if (pte_present(ptent)) { - max_nr = (end - addr) / PAGE_SIZE; - nr = zap_present_ptes(tlb, vma, pte, ptent, max_nr, - addr, details, rss, &force_flush, - &force_break); - if (unlikely(force_break)) { - addr += nr * PAGE_SIZE; - break; - } - continue; + nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss, + &force_flush, &force_break, &any_skipped); + if (any_skipped) + can_reclaim_pt = false; + if (unlikely(force_break)) { + addr += nr * PAGE_SIZE; + break; } - - entry = pte_to_swp_entry(ptent); - if (is_device_private_entry(entry) || - is_device_exclusive_entry(entry)) { - page = pfn_swap_entry_to_page(entry); - folio = page_folio(page); - if (unlikely(!should_zap_folio(details, folio))) - continue; - /* - * Both device private/exclusive mappings should only - * work with anonymous page so far, so we don't need to - * consider uffd-wp bit when zap. For more information, - * see zap_install_uffd_wp_if_needed(). - */ - WARN_ON_ONCE(!vma_is_anonymous(vma)); - rss[mm_counter(folio)]--; - if (is_device_private_entry(entry)) - folio_remove_rmap_pte(folio, page, vma); - folio_put(folio); - } else if (!non_swap_entry(entry)) { - max_nr = (end - addr) / PAGE_SIZE; - nr = swap_pte_batch(pte, max_nr, ptent); - /* Genuine swap entries, hence a private anon pages */ - if (!should_zap_cows(details)) - continue; - rss[MM_SWAPENTS] -= nr; - free_swap_and_cache_nr(entry, nr); - } else if (is_migration_entry(entry)) { - folio = pfn_swap_entry_folio(entry); - if (!should_zap_folio(details, folio)) - continue; - rss[mm_counter(folio)]--; - } else if (pte_marker_entry_uffd_wp(entry)) { - /* - * For anon: always drop the marker; for file: only - * drop the marker if explicitly requested. - */ - if (!vma_is_anonymous(vma) && - !zap_drop_markers(details)) - continue; - } else if (is_guard_swp_entry(entry)) { - /* - * Ordinary zapping should not remove guard PTE - * markers. Only do so if we should remove PTE markers - * in general. - */ - if (!zap_drop_markers(details)) - continue; - } else if (is_hwpoison_entry(entry) || - is_poisoned_swp_entry(entry)) { - if (!should_zap_cows(details)) - continue; - } else { - /* We should have covered all the swap entry types */ - pr_alert("unrecognized swap entry 0x%lx\n", entry.val); - WARN_ON_ONCE(1); - } - clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); - zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); + if (can_reclaim_pt && addr == end) + direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval); + add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); @@ -1713,6 +1769,20 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, if (force_flush) tlb_flush_mmu(tlb); + if (addr != end) { + cond_resched(); + force_flush = false; + force_break = false; + goto retry; + } + + if (can_reclaim_pt) { + if (direct_reclaim) + free_pte(mm, start, tlb, pmdval); + else + try_to_free_pte(mm, pmd, start, tlb); + } + return addr; } @@ -1935,7 +2005,6 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, struct mmu_notifier_range range; struct mmu_gather tlb; - lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, end); hugetlb_zap_begin(vma, &range.start, &range.end); @@ -3013,7 +3082,6 @@ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, { return __apply_to_page_range(mm, addr, size, fn, data, false); } -EXPORT_SYMBOL_GPL(apply_to_existing_page_range); /* * handle_pte_fault chooses page fault handler according to an entry which was @@ -4189,8 +4257,10 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf) if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, gfp, entry)) return folio; + count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK_CHARGE); folio_put(folio); } + count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK); order = next_order(&orders, order); } @@ -4733,12 +4803,12 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) folio_throttle_swaprate(folio, gfp); /* * When a folio is not zeroed during allocation - * (__GFP_ZERO not used), folio_zero_user() is used - * to make sure that the page corresponding to the - * faulting address will be hot in the cache after - * zeroing. + * (__GFP_ZERO not used) or user folios require special + * handling, folio_zero_user() is used to make sure + * that the page corresponding to the faulting address + * will be hot in the cache after zeroing. */ - if (!alloc_zeroed()) + if (user_alloc_needs_zeroing()) folio_zero_user(folio, vmf->address); return folio; } @@ -5625,7 +5695,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) ignore_writable = true; /* Migrate to the requested node */ - if (!migrate_misplaced_folio(folio, vma, target_nid)) { + if (!migrate_misplaced_folio(folio, target_nid)) { nid = target_nid; flags |= TNF_MIGRATED; task_numa_fault(last_cpupid, nid, nr_pages, flags); @@ -5662,8 +5732,17 @@ out_map: static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; + if (vma_is_anonymous(vma)) return do_huge_pmd_anonymous_page(vmf); + /* + * Currently we just emit PAGE_SIZE for our fault events, so don't allow + * a huge fault if we have a pre content watch on this file. This would + * be trivial to support, but there would need to be tests to ensure + * this works properly and those don't exist currently. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) + return VM_FAULT_FALLBACK; if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PMD_ORDER); return VM_FAULT_FALLBACK; @@ -5687,6 +5766,9 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) } if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { + /* See comment in create_huge_pmd. */ + if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) + goto split; if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) @@ -5709,6 +5791,9 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vma)) return VM_FAULT_FALLBACK; + /* See comment in create_huge_pmd. */ + if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) + return VM_FAULT_FALLBACK; if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PUD_ORDER); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -5726,6 +5811,9 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) if (vma_is_anonymous(vma)) goto split; if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { + /* See comment in create_huge_pmd. */ + if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) + goto split; if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) @@ -6069,7 +6157,8 @@ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma, } /* - * By the time we get here, we already hold the mm semaphore + * By the time we get here, we already hold either the VMA lock or the + * mmap_lock (FAULT_FLAG_VMA_LOCK tells you which). * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __folio_lock_or_retry(). @@ -6185,7 +6274,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r /* * Helper for page fault handling. * - * This is kind of equivalend to "mmap_read_lock()" followed + * This is kind of equivalent to "mmap_read_lock()" followed * by "find_extend_vma()", except it's a lot more careful about * the locking (and will drop the lock on failure). * @@ -6815,9 +6904,10 @@ static inline int process_huge_page( return 0; } -static void clear_gigantic_page(struct folio *folio, unsigned long addr, +static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint, unsigned int nr_pages) { + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio)); int i; might_sleep(); @@ -6851,13 +6941,14 @@ void folio_zero_user(struct folio *folio, unsigned long addr_hint) } static int copy_user_gigantic_page(struct folio *dst, struct folio *src, - unsigned long addr, + unsigned long addr_hint, struct vm_area_struct *vma, unsigned int nr_pages) { - int i; + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst)); struct page *dst_page; struct page *src_page; + int i; for (i = 0; i < nr_pages; i++) { dst_page = folio_page(dst, i); @@ -6959,7 +7050,8 @@ bool ptlock_alloc(struct ptdesc *ptdesc) void ptlock_free(struct ptdesc *ptdesc) { - kmem_cache_free(page_ptl_cachep, ptdesc->ptl); + if (ptdesc->ptl) + kmem_cache_free(page_ptl_cachep, ptdesc->ptl); } #endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c43b4e7fb298..e3655f07dd6e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -219,11 +219,30 @@ void put_online_mems(void) bool movable_node_enabled = false; -#ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE -int mhp_default_online_type = MMOP_OFFLINE; -#else -int mhp_default_online_type = MMOP_ONLINE; -#endif +static int mhp_default_online_type = -1; +int mhp_get_default_online_type(void) +{ + if (mhp_default_online_type >= 0) + return mhp_default_online_type; + + if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE)) + mhp_default_online_type = MMOP_OFFLINE; + else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO)) + mhp_default_online_type = MMOP_ONLINE; + else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL)) + mhp_default_online_type = MMOP_ONLINE_KERNEL; + else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE)) + mhp_default_online_type = MMOP_ONLINE_MOVABLE; + else + mhp_default_online_type = MMOP_OFFLINE; + + return mhp_default_online_type; +} + +void mhp_set_default_online_type(int online_type) +{ + mhp_default_online_type = online_type; +} static int __init setup_memhp_default_state(char *str) { @@ -650,6 +669,7 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) * this and the first chunk to online will be pageblock_nr_pages. */ for (pfn = start_pfn; pfn < end_pfn;) { + struct page *page = pfn_to_page(pfn); int order; /* @@ -664,7 +684,14 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) else order = MAX_PAGE_ORDER; - (*online_page_callback)(pfn_to_page(pfn), order); + /* + * Exposing the page to the buddy by freeing can cause + * issues with debug_pagealloc enabled: some archs don't + * like double-unmappings. So treat them like any pages that + * were allocated from the buddy. + */ + debug_pagealloc_map_pages(page, 1 << order); + (*online_page_callback)(page, order); pfn += (1UL << order); } @@ -1320,7 +1347,7 @@ static int check_hotplug_memory_range(u64 start, u64 size) static int online_memory_block(struct memory_block *mem, void *arg) { - mem->online_type = mhp_default_online_type; + mem->online_type = mhp_get_default_online_type(); return device_online(&mem->dev); } @@ -1567,7 +1594,7 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) merge_system_ram_resource(res); /* online pages if requested */ - if (mhp_default_online_type != MMOP_OFFLINE) + if (mhp_get_default_online_type() != MMOP_OFFLINE) walk_memory_blocks(start, size, NULL, online_memory_block); return ret; @@ -1830,7 +1857,7 @@ put_folio: nodemask_t nmask = node_states[N_MEMORY]; struct migration_target_control mtc = { .nmask = &nmask, - .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + .gfp_mask = GFP_KERNEL | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, .reason = MR_MEMORY_HOTPLUG, }; int ret; @@ -1992,8 +2019,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages, /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - MEMORY_OFFLINE | REPORT_FAILURE, - GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL); + MEMORY_OFFLINE | REPORT_FAILURE); if (ret) { reason = "failure to isolate range"; goto failed_removal_pcplists_disabled; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 04f35659717a..bbaadbeeb291 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -647,7 +647,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) - if (!isolate_hugetlb(folio, qp->pagelist)) + if (!folio_isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); @@ -2205,9 +2205,9 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); - page = __alloc_pages_noprof(preferred_gfp, order, nid, nodemask); + page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) - page = __alloc_pages_noprof(gfp, order, nid, NULL); + page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL); return page; } @@ -2222,7 +2222,7 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, * * Return: The page on success or NULL if allocation fails. */ -struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, +static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; @@ -2253,8 +2253,9 @@ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ - page = __alloc_pages_node_noprof(nid, - gfp | __GFP_THISNODE | __GFP_NORETRY, order); + page = __alloc_frozen_pages_noprof( + gfp | __GFP_THISNODE | __GFP_NORETRY, order, + nid, NULL); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* @@ -2266,9 +2267,10 @@ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, } } - page = __alloc_pages_noprof(gfp, order, nid, nodemask); + page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask); - if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) { + if (unlikely(pol->mode == MPOL_INTERLEAVE || + pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { @@ -2284,8 +2286,13 @@ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { - return page_rmappable_folio(alloc_pages_mpol_noprof(gfp | __GFP_COMP, - order, pol, ilx, nid)); + struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol, + ilx, nid); + if (!page) + return NULL; + + set_page_refcounted(page); + return page_rmappable_folio(page); } /** @@ -2299,7 +2306,7 @@ struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and - * excepting where direct use of alloc_pages_mpol() is more appropriate. + * excepting where direct use of folio_alloc_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ @@ -2320,6 +2327,21 @@ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct } EXPORT_SYMBOL(vma_alloc_folio_noprof); +struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order) +{ + struct mempolicy *pol = &default_policy; + + /* + * No reference counting needed for current->mempolicy + * nor system default_policy + */ + if (!in_interrupt() && !(gfp & __GFP_THISNODE)) + pol = get_task_policy(current); + + return alloc_pages_mpol(gfp, order, pol, NO_INTERLEAVE_INDEX, + numa_node_id()); +} + /** * alloc_pages - Allocate pages. * @gfp: GFP flags. @@ -2336,17 +2358,11 @@ EXPORT_SYMBOL(vma_alloc_folio_noprof); */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { - struct mempolicy *pol = &default_policy; + struct page *page = alloc_frozen_pages_noprof(gfp, order); - /* - * No reference counting needed for current->mempolicy - * nor system default_policy - */ - if (!in_interrupt() && !(gfp & __GFP_THISNODE)) - pol = get_task_policy(current); - - return alloc_pages_mpol_noprof(gfp, order, pol, NO_INTERLEAVE_INDEX, - numa_node_id()); + if (page) + set_page_refcounted(page); + return page; } EXPORT_SYMBOL(alloc_pages_noprof); @@ -2356,7 +2372,7 @@ struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) } EXPORT_SYMBOL(folio_alloc_noprof); -static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, +static unsigned long alloc_pages_bulk_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { @@ -2375,13 +2391,13 @@ static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, - nr_pages_per_node + 1, NULL, + nr_pages_per_node + 1, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, - nr_pages_per_node, NULL, page_array); + nr_pages_per_node, page_array); } page_array += nr_allocated; @@ -2391,7 +2407,7 @@ static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, return total_allocated; } -static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, +static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { @@ -2430,7 +2446,7 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, - NULL, page_array); + page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ @@ -2493,7 +2509,7 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, - NULL, page_array); + page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) @@ -2506,7 +2522,7 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, return total_allocated; } -static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, +static unsigned long alloc_pages_bulk_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { @@ -2517,11 +2533,11 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, - nr_pages, NULL, page_array); + nr_pages, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, - nr_pages - nr_allocated, NULL, + nr_pages - nr_allocated, page_array + nr_allocated); return nr_allocated; } @@ -2532,7 +2548,7 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, * It can accelerate memory allocation especially interleaving * allocate memory. */ -unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, +unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; @@ -2543,21 +2559,21 @@ unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) - return alloc_pages_bulk_array_interleave(gfp, pol, + return alloc_pages_bulk_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) - return alloc_pages_bulk_array_weighted_interleave( + return alloc_pages_bulk_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) - return alloc_pages_bulk_array_preferred_many(gfp, + return alloc_pages_bulk_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, - nr_pages, NULL, page_array); + nr_pages, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) diff --git a/mm/migrate.c b/mm/migrate.c index cc68583c86f9..fb19a18892c8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -68,10 +68,6 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode) if (!folio) goto out; - if (unlikely(folio_test_slab(folio))) - goto out_putfolio; - /* Pairs with smp_wmb() in slab freeing, e.g. SLUB's __free_slab() */ - smp_rmb(); /* * Check movable flag before taking the page lock because * we use non-atomic bitops on newly allocated page flags so @@ -79,10 +75,6 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode) */ if (unlikely(!__folio_test_movable(folio))) goto out_putfolio; - /* Pairs with smp_wmb() in slab allocation, e.g. SLUB's alloc_slab_page() */ - smp_rmb(); - if (unlikely(folio_test_slab(folio))) - goto out_putfolio; /* * As movable pages are not isolated from LRU lists, concurrent @@ -136,7 +128,7 @@ static void putback_movable_folio(struct folio *folio) * * This function shall be used whenever the isolated pageset has been * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() - * and isolate_hugetlb(). + * and folio_isolate_hugetlb(). */ void putback_movable_pages(struct list_head *l) { @@ -145,7 +137,7 @@ void putback_movable_pages(struct list_head *l) list_for_each_entry_safe(folio, folio2, l, lru) { if (unlikely(folio_test_hugetlb(folio))) { - folio_putback_active_hugetlb(folio); + folio_putback_hugetlb(folio); continue; } list_del(&folio->lru); @@ -177,7 +169,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list) bool isolated, lru; if (folio_test_hugetlb(folio)) - return isolate_hugetlb(folio, list); + return folio_isolate_hugetlb(folio, list); lru = !__folio_test_movable(folio); if (lru) @@ -1459,7 +1451,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, if (folio_ref_count(src) == 1) { /* page was freed from under us. So we are done. */ - folio_putback_active_hugetlb(src); + folio_putback_hugetlb(src); return MIGRATEPAGE_SUCCESS; } @@ -1542,19 +1534,19 @@ out_unlock: folio_unlock(src); out: if (rc == MIGRATEPAGE_SUCCESS) - folio_putback_active_hugetlb(src); + folio_putback_hugetlb(src); else if (rc != -EAGAIN) list_move_tail(&src->lru, ret); /* - * If migration was not successful and there's a freeing callback, use - * it. Otherwise, put_page() will drop the reference grabbed during - * isolation. + * If migration was not successful and there's a freeing callback, + * return the folio to that special allocator. Otherwise, simply drop + * our additional reference. */ if (put_new_folio) put_new_folio(dst, private); else - folio_putback_active_hugetlb(dst); + folio_put(dst); return rc; } @@ -1695,6 +1687,81 @@ static int migrate_hugetlbs(struct list_head *from, new_folio_t get_new_folio, return nr_failed; } +static void migrate_folios_move(struct list_head *src_folios, + struct list_head *dst_folios, + free_folio_t put_new_folio, unsigned long private, + enum migrate_mode mode, int reason, + struct list_head *ret_folios, + struct migrate_pages_stats *stats, + int *retry, int *thp_retry, int *nr_failed, + int *nr_retry_pages) +{ + struct folio *folio, *folio2, *dst, *dst2; + bool is_thp; + int nr_pages; + int rc; + + dst = list_first_entry(dst_folios, struct folio, lru); + dst2 = list_next_entry(dst, lru); + list_for_each_entry_safe(folio, folio2, src_folios, lru) { + is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio); + nr_pages = folio_nr_pages(folio); + + cond_resched(); + + rc = migrate_folio_move(put_new_folio, private, + folio, dst, mode, + reason, ret_folios); + /* + * The rules are: + * Success: folio will be freed + * -EAGAIN: stay on the unmap_folios list + * Other errno: put on ret_folios list + */ + switch (rc) { + case -EAGAIN: + *retry += 1; + *thp_retry += is_thp; + *nr_retry_pages += nr_pages; + break; + case MIGRATEPAGE_SUCCESS: + stats->nr_succeeded += nr_pages; + stats->nr_thp_succeeded += is_thp; + break; + default: + *nr_failed += 1; + stats->nr_thp_failed += is_thp; + stats->nr_failed_pages += nr_pages; + break; + } + dst = dst2; + dst2 = list_next_entry(dst, lru); + } +} + +static void migrate_folios_undo(struct list_head *src_folios, + struct list_head *dst_folios, + free_folio_t put_new_folio, unsigned long private, + struct list_head *ret_folios) +{ + struct folio *folio, *folio2, *dst, *dst2; + + dst = list_first_entry(dst_folios, struct folio, lru); + dst2 = list_next_entry(dst, lru); + list_for_each_entry_safe(folio, folio2, src_folios, lru) { + int old_page_state = 0; + struct anon_vma *anon_vma = NULL; + + __migrate_folio_extract(dst, &old_page_state, &anon_vma); + migrate_folio_undo_src(folio, old_page_state & PAGE_WAS_MAPPED, + anon_vma, true, ret_folios); + list_del(&dst->lru); + migrate_folio_undo_dst(dst, true, put_new_folio, private); + dst = dst2; + dst2 = list_next_entry(dst, lru); + } +} + /* * migrate_pages_batch() first unmaps folios in the from list as many as * possible, then move the unmapped folios. @@ -1717,7 +1784,7 @@ static int migrate_pages_batch(struct list_head *from, int pass = 0; bool is_thp = false; bool is_large = false; - struct folio *folio, *folio2, *dst = NULL, *dst2; + struct folio *folio, *folio2, *dst = NULL; int rc, rc_saved = 0, nr_pages; LIST_HEAD(unmap_folios); LIST_HEAD(dst_folios); @@ -1888,42 +1955,11 @@ move: thp_retry = 0; nr_retry_pages = 0; - dst = list_first_entry(&dst_folios, struct folio, lru); - dst2 = list_next_entry(dst, lru); - list_for_each_entry_safe(folio, folio2, &unmap_folios, lru) { - is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio); - nr_pages = folio_nr_pages(folio); - - cond_resched(); - - rc = migrate_folio_move(put_new_folio, private, - folio, dst, mode, - reason, ret_folios); - /* - * The rules are: - * Success: folio will be freed - * -EAGAIN: stay on the unmap_folios list - * Other errno: put on ret_folios list - */ - switch(rc) { - case -EAGAIN: - retry++; - thp_retry += is_thp; - nr_retry_pages += nr_pages; - break; - case MIGRATEPAGE_SUCCESS: - stats->nr_succeeded += nr_pages; - stats->nr_thp_succeeded += is_thp; - break; - default: - nr_failed++; - stats->nr_thp_failed += is_thp; - stats->nr_failed_pages += nr_pages; - break; - } - dst = dst2; - dst2 = list_next_entry(dst, lru); - } + /* Move the unmapped folios */ + migrate_folios_move(&unmap_folios, &dst_folios, + put_new_folio, private, mode, reason, + ret_folios, stats, &retry, &thp_retry, + &nr_failed, &nr_retry_pages); } nr_failed += retry; stats->nr_thp_failed += thp_retry; @@ -1932,20 +1968,8 @@ move: rc = rc_saved ? : nr_failed; out: /* Cleanup remaining folios */ - dst = list_first_entry(&dst_folios, struct folio, lru); - dst2 = list_next_entry(dst, lru); - list_for_each_entry_safe(folio, folio2, &unmap_folios, lru) { - int old_page_state = 0; - struct anon_vma *anon_vma = NULL; - - __migrate_folio_extract(dst, &old_page_state, &anon_vma); - migrate_folio_undo_src(folio, old_page_state & PAGE_WAS_MAPPED, - anon_vma, true, ret_folios); - list_del(&dst->lru); - migrate_folio_undo_dst(dst, true, put_new_folio, private); - dst = dst2; - dst2 = list_next_entry(dst, lru); - } + migrate_folios_undo(&unmap_folios, &dst_folios, + put_new_folio, private, ret_folios); return rc; } @@ -2208,7 +2232,7 @@ static int __add_folio_for_migration(struct folio *folio, int node, return -EACCES; if (folio_test_hugetlb(folio)) { - if (isolate_hugetlb(folio, pagelist)) + if (folio_isolate_hugetlb(folio, pagelist)) return 1; } else if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, pagelist); @@ -2683,8 +2707,7 @@ int migrate_misplaced_folio_prepare(struct folio *folio, * elevated reference count on the folio. This function will un-isolate the * folio, dereferencing the folio before returning. */ -int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, - int node) +int migrate_misplaced_folio(struct folio *folio, int node) { pg_data_t *pgdat = NODE_DATA(node); int nr_remaining; diff --git a/mm/mm_init.c b/mm/mm_init.c index 24b68b425afb..2630cc30147e 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1585,13 +1585,17 @@ void __init *memmap_alloc(phys_addr_t size, phys_addr_t align, { void *ptr; + /* + * Kmemleak will explicitly scan mem_map by traversing all valid + * `struct *page`,so memblock does not need to be added to the scan list. + */ if (exact_nid) ptr = memblock_alloc_exact_nid_raw(size, align, min_addr, - MEMBLOCK_ALLOC_ACCESSIBLE, + MEMBLOCK_ALLOC_NOLEAKTRACE, nid); else ptr = memblock_alloc_try_nid_raw(size, align, min_addr, - MEMBLOCK_ALLOC_ACCESSIBLE, + MEMBLOCK_ALLOC_NOLEAKTRACE, nid); if (ptr && size > 0) diff --git a/mm/mmap.c b/mm/mmap.c index d32b7e701058..cda01071c7b1 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -110,8 +111,7 @@ static int check_brk_limits(unsigned long addr, unsigned long len) return mlock_future_ok(current->mm, current->mm->def_flags, len) ? 0 : -EAGAIN; } -static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma, - unsigned long addr, unsigned long request, unsigned long flags); + SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long newbrk, oldbrk, origbrk; @@ -277,8 +277,62 @@ static inline bool file_mmap_ok(struct file *file, struct inode *inode, return true; } -/* +/** + * do_mmap() - Perform a userland memory mapping into the current process + * address space of length @len with protection bits @prot, mmap flags @flags + * (from which VMA flags will be inferred), and any additional VMA flags to + * apply @vm_flags. If this is a file-backed mapping then the file is specified + * in @file and page offset into the file via @pgoff. + * + * This function does not perform security checks on the file and assumes, if + * @uf is non-NULL, the caller has provided a list head to track unmap events + * for userfaultfd @uf. + * + * It also simply indicates whether memory population is required by setting + * @populate, which must be non-NULL, expecting the caller to actually perform + * this task itself if appropriate. + * + * This function will invoke architecture-specific (and if provided and + * relevant, file system-specific) logic to determine the most appropriate + * unmapped area in which to place the mapping if not MAP_FIXED. + * + * Callers which require userland mmap() behaviour should invoke vm_mmap(), + * which is also exported for module use. + * + * Those which require this behaviour less security checks, userfaultfd and + * populate behaviour, and who handle the mmap write lock themselves, should + * call this function. + * + * Note that the returned address may reside within a merged VMA if an + * appropriate merge were to take place, so it doesn't necessarily specify the + * start of a VMA, rather only the start of a valid mapped range of length + * @len bytes, rounded down to the nearest page size. + * * The caller must write-lock current->mm->mmap_lock. + * + * @file: An optional struct file pointer describing the file which is to be + * mapped, if a file-backed mapping. + * @addr: If non-zero, hints at (or if @flags has MAP_FIXED set, specifies) the + * address at which to perform this mapping. See mmap (2) for details. Must be + * page-aligned. + * @len: The length of the mapping. Will be page-aligned and must be at least 1 + * page in size. + * @prot: Protection bits describing access required to the mapping. See mmap + * (2) for details. + * @flags: Flags specifying how the mapping should be performed, see mmap (2) + * for details. + * @vm_flags: VMA flags which should be set by default, or 0 otherwise. + * @pgoff: Page offset into the @file if file-backed, should be 0 otherwise. + * @populate: A pointer to a value which will be set to 0 if no population of + * the range is required, or the number of bytes to populate if it is. Must be + * non-NULL. See mmap (2) for details as to under what circumstances population + * of the range occurs. + * @uf: An optional pointer to a list head to track userfaultfd unmap events + * should unmapping events arise. If provided, it is up to the caller to manage + * this. + * + * Returns: Either an error, or the address at which the requested mapping has + * been performed. */ unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, @@ -291,6 +345,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr, *populate = 0; + mmap_assert_write_locked(mm); + if (!len) return -EINVAL; @@ -369,6 +425,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (file) { struct inode *inode = file_inode(file); unsigned long flags_mask; + int err; if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; @@ -427,6 +484,14 @@ unsigned long do_mmap(struct file *file, unsigned long addr, default: return -EINVAL; } + + /* + * Check to see if we are violating any seals and update VMA + * flags if necessary to avoid future seal violations. + */ + err = memfd_check_seals_mmap(file, &vm_flags); + if (err) + return (unsigned long)err; } else { switch (flags & MAP_TYPE) { case MAP_SHARED: @@ -577,115 +642,6 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ -/** - * unmapped_area() - Find an area between the low_limit and the high_limit with - * the correct alignment and offset, all from @info. Note: current->mm is used - * for the search. - * - * @info: The unmapped area information including the range [low_limit - - * high_limit), the alignment offset and mask. - * - * Return: A memory address or -ENOMEM. - */ -static unsigned long unmapped_area(struct vm_unmapped_area_info *info) -{ - unsigned long length, gap; - unsigned long low_limit, high_limit; - struct vm_area_struct *tmp; - VMA_ITERATOR(vmi, current->mm, 0); - - /* Adjust search length to account for worst case alignment overhead */ - length = info->length + info->align_mask + info->start_gap; - if (length < info->length) - return -ENOMEM; - - low_limit = info->low_limit; - if (low_limit < mmap_min_addr) - low_limit = mmap_min_addr; - high_limit = info->high_limit; -retry: - if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length)) - return -ENOMEM; - - /* - * Adjust for the gap first so it doesn't interfere with the - * later alignment. The first step is the minimum needed to - * fulill the start gap, the next steps is the minimum to align - * that. It is the minimum needed to fulill both. - */ - gap = vma_iter_addr(&vmi) + info->start_gap; - gap += (info->align_offset - gap) & info->align_mask; - tmp = vma_next(&vmi); - if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ - if (vm_start_gap(tmp) < gap + length - 1) { - low_limit = tmp->vm_end; - vma_iter_reset(&vmi); - goto retry; - } - } else { - tmp = vma_prev(&vmi); - if (tmp && vm_end_gap(tmp) > gap) { - low_limit = vm_end_gap(tmp); - vma_iter_reset(&vmi); - goto retry; - } - } - - return gap; -} - -/** - * unmapped_area_topdown() - Find an area between the low_limit and the - * high_limit with the correct alignment and offset at the highest available - * address, all from @info. Note: current->mm is used for the search. - * - * @info: The unmapped area information including the range [low_limit - - * high_limit), the alignment offset and mask. - * - * Return: A memory address or -ENOMEM. - */ -static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) -{ - unsigned long length, gap, gap_end; - unsigned long low_limit, high_limit; - struct vm_area_struct *tmp; - VMA_ITERATOR(vmi, current->mm, 0); - - /* Adjust search length to account for worst case alignment overhead */ - length = info->length + info->align_mask + info->start_gap; - if (length < info->length) - return -ENOMEM; - - low_limit = info->low_limit; - if (low_limit < mmap_min_addr) - low_limit = mmap_min_addr; - high_limit = info->high_limit; -retry: - if (vma_iter_area_highest(&vmi, low_limit, high_limit, length)) - return -ENOMEM; - - gap = vma_iter_end(&vmi) - info->length; - gap -= (gap - info->align_offset) & info->align_mask; - gap_end = vma_iter_end(&vmi); - tmp = vma_next(&vmi); - if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ - if (vm_start_gap(tmp) < gap_end) { - high_limit = vm_start_gap(tmp); - vma_iter_reset(&vmi); - goto retry; - } - } else { - tmp = vma_prev(&vmi); - if (tmp && vm_end_gap(tmp) > gap) { - high_limit = tmp->vm_start; - vma_iter_reset(&vmi); - goto retry; - } - } - - return gap; -} - /* * Determine if the allocation needs to ensure that there is no * existing mapping within it's guard gaps, for use as start_gap. @@ -888,7 +844,7 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (get_area) { addr = get_area(file, addr, len, pgoff, flags); - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && !file && !addr /* no hint */ && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ @@ -985,211 +941,6 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr, return vma; } -/* - * Verify that the stack growth is acceptable and - * update accounting. This is shared with both the - * grow-up and grow-down cases. - */ -static int acct_stack_growth(struct vm_area_struct *vma, - unsigned long size, unsigned long grow) -{ - struct mm_struct *mm = vma->vm_mm; - unsigned long new_start; - - /* address space limit tests */ - if (!may_expand_vm(mm, vma->vm_flags, grow)) - return -ENOMEM; - - /* Stack limit test */ - if (size > rlimit(RLIMIT_STACK)) - return -ENOMEM; - - /* mlock limit tests */ - if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT)) - return -ENOMEM; - - /* Check to ensure the stack will not grow into a hugetlb-only region */ - new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : - vma->vm_end - size; - if (is_hugepage_only_range(vma->vm_mm, new_start, size)) - return -EFAULT; - - /* - * Overcommit.. This must be the final test, as it will - * update security statistics. - */ - if (security_vm_enough_memory_mm(mm, grow)) - return -ENOMEM; - - return 0; -} - -#if defined(CONFIG_STACK_GROWSUP) -/* - * PA-RISC uses this for its stack. - * vma is the last one with address > vma->vm_end. Have to extend vma. - */ -static int expand_upwards(struct vm_area_struct *vma, unsigned long address) -{ - struct mm_struct *mm = vma->vm_mm; - struct vm_area_struct *next; - unsigned long gap_addr; - int error = 0; - VMA_ITERATOR(vmi, mm, vma->vm_start); - - if (!(vma->vm_flags & VM_GROWSUP)) - return -EFAULT; - - mmap_assert_write_locked(mm); - - /* Guard against exceeding limits of the address space. */ - address &= PAGE_MASK; - if (address >= (TASK_SIZE & PAGE_MASK)) - return -ENOMEM; - address += PAGE_SIZE; - - /* Enforce stack_guard_gap */ - gap_addr = address + stack_guard_gap; - - /* Guard against overflow */ - if (gap_addr < address || gap_addr > TASK_SIZE) - gap_addr = TASK_SIZE; - - next = find_vma_intersection(mm, vma->vm_end, gap_addr); - if (next && vma_is_accessible(next)) { - if (!(next->vm_flags & VM_GROWSUP)) - return -ENOMEM; - /* Check that both stack segments have the same anon_vma? */ - } - - if (next) - vma_iter_prev_range_limit(&vmi, address); - - vma_iter_config(&vmi, vma->vm_start, address); - if (vma_iter_prealloc(&vmi, vma)) - return -ENOMEM; - - /* We must make sure the anon_vma is allocated. */ - if (unlikely(anon_vma_prepare(vma))) { - vma_iter_free(&vmi); - return -ENOMEM; - } - - /* Lock the VMA before expanding to prevent concurrent page faults */ - vma_start_write(vma); - /* We update the anon VMA tree. */ - anon_vma_lock_write(vma->anon_vma); - - /* Somebody else might have raced and expanded it already */ - if (address > vma->vm_end) { - unsigned long size, grow; - - size = address - vma->vm_start; - grow = (address - vma->vm_end) >> PAGE_SHIFT; - - error = -ENOMEM; - if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { - error = acct_stack_growth(vma, size, grow); - if (!error) { - if (vma->vm_flags & VM_LOCKED) - mm->locked_vm += grow; - vm_stat_account(mm, vma->vm_flags, grow); - anon_vma_interval_tree_pre_update_vma(vma); - vma->vm_end = address; - /* Overwrite old entry in mtree. */ - vma_iter_store(&vmi, vma); - anon_vma_interval_tree_post_update_vma(vma); - - perf_event_mmap(vma); - } - } - } - anon_vma_unlock_write(vma->anon_vma); - vma_iter_free(&vmi); - validate_mm(mm); - return error; -} -#endif /* CONFIG_STACK_GROWSUP */ - -/* - * vma is the first one with address < vma->vm_start. Have to extend vma. - * mmap_lock held for writing. - */ -int expand_downwards(struct vm_area_struct *vma, unsigned long address) -{ - struct mm_struct *mm = vma->vm_mm; - struct vm_area_struct *prev; - int error = 0; - VMA_ITERATOR(vmi, mm, vma->vm_start); - - if (!(vma->vm_flags & VM_GROWSDOWN)) - return -EFAULT; - - mmap_assert_write_locked(mm); - - address &= PAGE_MASK; - if (address < mmap_min_addr || address < FIRST_USER_ADDRESS) - return -EPERM; - - /* Enforce stack_guard_gap */ - prev = vma_prev(&vmi); - /* Check that both stack segments have the same anon_vma? */ - if (prev) { - if (!(prev->vm_flags & VM_GROWSDOWN) && - vma_is_accessible(prev) && - (address - prev->vm_end < stack_guard_gap)) - return -ENOMEM; - } - - if (prev) - vma_iter_next_range_limit(&vmi, vma->vm_start); - - vma_iter_config(&vmi, address, vma->vm_end); - if (vma_iter_prealloc(&vmi, vma)) - return -ENOMEM; - - /* We must make sure the anon_vma is allocated. */ - if (unlikely(anon_vma_prepare(vma))) { - vma_iter_free(&vmi); - return -ENOMEM; - } - - /* Lock the VMA before expanding to prevent concurrent page faults */ - vma_start_write(vma); - /* We update the anon VMA tree. */ - anon_vma_lock_write(vma->anon_vma); - - /* Somebody else might have raced and expanded it already */ - if (address < vma->vm_start) { - unsigned long size, grow; - - size = vma->vm_end - address; - grow = (vma->vm_start - address) >> PAGE_SHIFT; - - error = -ENOMEM; - if (grow <= vma->vm_pgoff) { - error = acct_stack_growth(vma, size, grow); - if (!error) { - if (vma->vm_flags & VM_LOCKED) - mm->locked_vm += grow; - vm_stat_account(mm, vma->vm_flags, grow); - anon_vma_interval_tree_pre_update_vma(vma); - vma->vm_start = address; - vma->vm_pgoff -= grow; - /* Overwrite old entry in mtree. */ - vma_iter_store(&vmi, vma); - anon_vma_interval_tree_post_update_vma(vma); - - perf_event_mmap(vma); - } - } - } - anon_vma_unlock_write(vma->anon_vma); - vma_iter_free(&vmi); - validate_mm(mm); - return error; -} - /* enforced gap between the expanding stack and other mappings. */ unsigned long stack_guard_gap = 256UL<f_mapping); - - if (error) - return error; - writable_file_mapping = true; - } - - ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf); - - /* Clear our write mapping regardless of error. */ - if (writable_file_mapping) - mapping_unmap_writable(file->f_mapping); - - validate_mm(current->mm); - return ret; -} - -static int __vm_munmap(unsigned long start, size_t len, bool unlock) -{ - int ret; - struct mm_struct *mm = current->mm; - LIST_HEAD(uf); - VMA_ITERATOR(vmi, mm, start); - - if (mmap_write_lock_killable(mm)) - return -EINTR; - - ret = do_vmi_munmap(&vmi, mm, start, len, &uf, unlock); - if (ret || !unlock) - mmap_write_unlock(mm); - - userfaultfd_unmap_complete(mm, &uf); - return ret; -} - int vm_munmap(unsigned long start, size_t len) { return __vm_munmap(start, len, false); @@ -1508,88 +1207,6 @@ out: return ret; } -/* - * do_brk_flags() - Increase the brk vma if the flags match. - * @vmi: The vma iterator - * @addr: The start address - * @len: The length of the increase - * @vma: The vma, - * @flags: The VMA Flags - * - * Extend the brk VMA from addr to addr + len. If the VMA is NULL or the flags - * do not match then create a new anonymous VMA. Eventually we may be able to - * do some brk-specific accounting here. - */ -static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long addr, unsigned long len, unsigned long flags) -{ - struct mm_struct *mm = current->mm; - - /* - * Check against address space limits by the changed size - * Note: This happens *after* clearing old mappings in some code paths. - */ - flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; - if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) - return -ENOMEM; - - if (mm->map_count > sysctl_max_map_count) - return -ENOMEM; - - if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) - return -ENOMEM; - - /* - * Expand the existing vma if possible; Note that singular lists do not - * occur after forking, so the expand will only happen on new VMAs. - */ - if (vma && vma->vm_end == addr) { - VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr)); - - vmg.prev = vma; - /* vmi is positioned at prev, which this mode expects. */ - vmg.merge_flags = VMG_FLAG_JUST_EXPAND; - - if (vma_merge_new_range(&vmg)) - goto out; - else if (vmg_nomem(&vmg)) - goto unacct_fail; - } - - if (vma) - vma_iter_next_range(vmi); - /* create a vma struct for an anonymous mapping */ - vma = vm_area_alloc(mm); - if (!vma) - goto unacct_fail; - - vma_set_anonymous(vma); - vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT); - vm_flags_init(vma, flags); - vma->vm_page_prot = vm_get_page_prot(flags); - vma_start_write(vma); - if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL)) - goto mas_store_fail; - - mm->map_count++; - validate_mm(mm); - ksm_add_vma(vma); -out: - perf_event_mmap(vma); - mm->total_vm += len >> PAGE_SHIFT; - mm->data_vm += len >> PAGE_SHIFT; - if (flags & VM_LOCKED) - mm->locked_vm += (len >> PAGE_SHIFT); - vm_flags_set(vma, VM_SOFTDIRTY); - return 0; - -mas_store_fail: - vm_area_free(vma); -unacct_fail: - vm_unacct_memory(len >> PAGE_SHIFT); - return -ENOMEM; -} - int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) { struct mm_struct *mm = current->mm; @@ -1660,7 +1277,6 @@ void exit_mmap(struct mm_struct *mm) goto destroy; } - lru_add_drain(); flush_cache_mm(mm); tlb_gather_mmu_fullmm(&tlb, mm); /* update_hiwater_rss(mm) here? but nobody should be looking */ @@ -2103,7 +1719,6 @@ int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift) vma, new_start, length, false, true)) return -ENOMEM; - lru_add_drain(); tlb_gather_mmu(&tlb, mm); next = vma_next(&vmi); if (new_end > old_start) { @@ -2128,3 +1743,55 @@ int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift) /* Shrink the vma to just the new range */ return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff); } + +#ifdef CONFIG_MMU +/* + * Obtain a read lock on mm->mmap_lock, if the specified address is below the + * start of the VMA, the intent is to perform a write, and it is a + * downward-growing stack, then attempt to expand the stack to contain it. + * + * This function is intended only for obtaining an argument page from an ELF + * image, and is almost certainly NOT what you want to use for any other + * purpose. + * + * IMPORTANT - VMA fields are accessed without an mmap lock being held, so the + * VMA referenced must not be linked in any user-visible tree, i.e. it must be a + * new VMA being mapped. + * + * The function assumes that addr is either contained within the VMA or below + * it, and makes no attempt to validate this value beyond that. + * + * Returns true if the read lock was obtained and a stack was perhaps expanded, + * false if the stack expansion failed. + * + * On stack expansion the function temporarily acquires an mmap write lock + * before downgrading it. + */ +bool mmap_read_lock_maybe_expand(struct mm_struct *mm, + struct vm_area_struct *new_vma, + unsigned long addr, bool write) +{ + if (!write || addr >= new_vma->vm_start) { + mmap_read_lock(mm); + return true; + } + + if (!(new_vma->vm_flags & VM_GROWSDOWN)) + return false; + + mmap_write_lock(mm); + if (expand_downwards(new_vma, addr)) { + mmap_write_unlock(mm); + return false; + } + + mmap_write_downgrade(mm); + return true; +} +#else +bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, bool write) +{ + return false; +} +#endif diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index f186d57df2c6..e7dbaf96aa17 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -17,51 +17,7 @@ EXPORT_TRACEPOINT_SYMBOL(mmap_lock_start_locking); EXPORT_TRACEPOINT_SYMBOL(mmap_lock_acquire_returned); EXPORT_TRACEPOINT_SYMBOL(mmap_lock_released); -#ifdef CONFIG_MEMCG - -/* - * Size of the buffer for memcg path names. Ignoring stack trace support, - * trace_events_hist.c uses MAX_FILTER_STR_VAL for this, so we also use it. - */ -#define MEMCG_PATH_BUF_SIZE MAX_FILTER_STR_VAL - -#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ - do { \ - if (trace_mmap_lock_##type##_enabled()) { \ - char buf[MEMCG_PATH_BUF_SIZE]; \ - get_mm_memcg_path(mm, buf, sizeof(buf)); \ - trace_mmap_lock_##type(mm, buf, ##__VA_ARGS__); \ - } \ - } while (0) - -#else /* !CONFIG_MEMCG */ - -#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ - trace_mmap_lock_##type(mm, "", ##__VA_ARGS__) - -#endif /* CONFIG_MEMCG */ - #ifdef CONFIG_TRACING -#ifdef CONFIG_MEMCG -/* - * Write the given mm_struct's memcg path to a buffer. If the path cannot be - * determined, empty string is written. - */ -static void get_mm_memcg_path(struct mm_struct *mm, char *buf, size_t buflen) -{ - struct mem_cgroup *memcg; - - buf[0] = '\0'; - memcg = get_mem_cgroup_from_mm(mm); - if (memcg == NULL) - return; - if (memcg->css.cgroup) - cgroup_path(memcg->css.cgroup, buf, buflen); - css_put(&memcg->css); -} - -#endif /* CONFIG_MEMCG */ - /* * Trace calls must be in a separate file, as otherwise there's a circular * dependency between linux/mmap_lock.h and trace/events/mmap_lock.h. @@ -69,20 +25,20 @@ static void get_mm_memcg_path(struct mm_struct *mm, char *buf, size_t buflen) void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write) { - TRACE_MMAP_LOCK_EVENT(start_locking, mm, write); + trace_mmap_lock_start_locking(mm, write); } EXPORT_SYMBOL(__mmap_lock_do_trace_start_locking); void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { - TRACE_MMAP_LOCK_EVENT(acquire_returned, mm, write, success); + trace_mmap_lock_acquire_returned(mm, write, success); } EXPORT_SYMBOL(__mmap_lock_do_trace_acquire_returned); void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write) { - TRACE_MMAP_LOCK_EVENT(released, mm, write); + trace_mmap_lock_released(mm, write); } EXPORT_SYMBOL(__mmap_lock_do_trace_released); #endif /* CONFIG_TRACING */ diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 99b3e9408aa0..7aa6f18c500b 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -311,11 +311,34 @@ static inline void tlb_table_invalidate(struct mmu_gather *tlb) } } -static void tlb_remove_table_one(void *table) +#ifdef CONFIG_PT_RECLAIM +static inline void __tlb_remove_table_one_rcu(struct rcu_head *head) +{ + struct ptdesc *ptdesc; + + ptdesc = container_of(head, struct ptdesc, pt_rcu_head); + __tlb_remove_table(ptdesc); +} + +static inline void __tlb_remove_table_one(void *table) +{ + struct ptdesc *ptdesc; + + ptdesc = table; + call_rcu(&ptdesc->pt_rcu_head, __tlb_remove_table_one_rcu); +} +#else +static inline void __tlb_remove_table_one(void *table) { tlb_remove_table_sync_one(); __tlb_remove_table(table); } +#endif /* CONFIG_PT_RECLAIM */ + +static void tlb_remove_table_one(void *table) +{ + __tlb_remove_table_one(table); +} static void tlb_table_flush(struct mmu_gather *tlb) { diff --git a/mm/mremap.c b/mm/mremap.c index 60473413836b..cff7f552f909 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -138,6 +138,7 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct vm_area_struct *new_vma, pmd_t *new_pmd, unsigned long new_addr, bool need_rmap_locks) { + bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; pmd_t dummy_pmdval; @@ -216,7 +217,18 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, force_flush = true; pte = move_pte(pte, old_addr, new_addr); pte = move_soft_dirty_pte(pte); - set_pte_at(mm, new_addr, new_pte, pte); + + if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) + pte_clear(mm, new_addr, new_pte); + else { + if (need_clear_uffd_wp) { + if (pte_present(pte)) + pte = pte_clear_uffd_wp(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_clear_uffd_wp(pte); + } + set_pte_at(mm, new_addr, new_pte, pte); + } } arch_leave_lazy_mmu_mode(); @@ -278,6 +290,15 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, if (WARN_ON_ONCE(!pmd_none(*new_pmd))) return false; + /* If this pmd belongs to a uffd vma with remap events disabled, we need + * to ensure that the uffd-wp state is cleared from all pgtables. This + * means recursing into lower page tables in move_page_tables(), and we + * can reuse the existing code if we simply treat the entry as "not + * moved". + */ + if (vma_has_uffd_without_event_remap(vma)) + return false; + /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. @@ -333,6 +354,15 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr, if (WARN_ON_ONCE(!pud_none(*new_pud))) return false; + /* If this pud belongs to a uffd vma with remap events disabled, we need + * to ensure that the uffd-wp state is cleared from all pgtables. This + * means recursing into lower page tables in move_page_tables(), and we + * can reuse the existing code if we simply treat the entry as "not + * moved". + */ + if (vma_has_uffd_without_event_remap(vma)) + return false; + /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. diff --git a/mm/mseal.c b/mm/mseal.c index 81d6e980e8a9..c27197ac04e8 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -217,9 +217,9 @@ int do_mseal(unsigned long start, size_t len_in, unsigned long flags) unsigned long end; struct mm_struct *mm = current->mm; - ret = can_do_mseal(flags); - if (ret) - return ret; + /* Verify flags not set. */ + if (flags) + return -EINVAL; start = untagged_addr(start); if (!PAGE_ALIGNED(start)) diff --git a/mm/nommu.c b/mm/nommu.c index 9cb6e99215e2..baa79abdaf03 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1613,6 +1613,13 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, } EXPORT_SYMBOL(remap_vmalloc_range); +vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf) +{ + BUG(); + return 0; +} +EXPORT_SYMBOL_GPL(filemap_fsnotify_fault); + vm_fault_t filemap_fault(struct vm_fault *vmf) { BUG(); diff --git a/mm/numa.c b/mm/numa.c index e2eec07707d1..f1787d7713a6 100644 --- a/mm/numa.c +++ b/mm/numa.c @@ -37,13 +37,7 @@ void __init alloc_node_data(int nid) void __init alloc_offline_node_data(int nid) { pg_data_t *pgdat; - - pgdat = memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); - if (!pgdat) - panic("Cannot allocate %zuB for node %d.\n", - sizeof(*pgdat), nid); - - node_data[nid] = pgdat; + node_data[nid] = memblock_alloc_or_panic(sizeof(*pgdat), SMP_CACHE_BYTES); } /* Stub functions: */ diff --git a/mm/numa_emulation.c b/mm/numa_emulation.c index 031fb9961bf7..9d55679d99ce 100644 --- a/mm/numa_emulation.c +++ b/mm/numa_emulation.c @@ -8,11 +8,12 @@ #include #include #include +#include #define FAKE_NODE_MIN_SIZE ((u64)32 << 20) #define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) -static int emu_nid_to_phys[MAX_NUMNODES]; +int emu_nid_to_phys[MAX_NUMNODES]; static char *emu_cmdline __initdata; int __init numa_emu_cmdline(char *str) @@ -379,6 +380,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]); int max_emu_nid, dfl_phys_nid; int i, j, ret; + nodemask_t physnode_mask = numa_nodes_parsed; if (!emu_cmdline) goto no_emu; @@ -395,7 +397,6 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) * split the system RAM into N fake nodes. */ if (strchr(emu_cmdline, 'U')) { - nodemask_t physnode_mask = numa_nodes_parsed; unsigned long n; int nid = 0; @@ -465,9 +466,6 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) */ max_emu_nid = setup_emu2phys_nid(&dfl_phys_nid); - /* commit */ - *numa_meminfo = ei; - /* Make sure numa_nodes_parsed only contains emulated nodes */ nodes_clear(numa_nodes_parsed); for (i = 0; i < ARRAY_SIZE(ei.blk); i++) @@ -475,10 +473,21 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) ei.blk[i].nid != NUMA_NO_NODE) node_set(ei.blk[i].nid, numa_nodes_parsed); - numa_emu_update_cpu_to_node(emu_nid_to_phys, ARRAY_SIZE(emu_nid_to_phys)); + /* fix pxm_to_node_map[] and node_to_pxm_map[] to avoid collision + * with faked numa nodes, particularly during later memory hotplug + * handling, and also update numa_nodes_parsed accordingly. + */ + ret = fix_pxm_node_maps(max_emu_nid); + if (ret < 0) + goto no_emu; + + /* commit */ + *numa_meminfo = ei; + + numa_emu_update_cpu_to_node(emu_nid_to_phys, max_emu_nid + 1); /* make sure all emulated nodes are mapped to a physical node */ - for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) + for (i = 0; i < max_emu_nid + 1; i++) if (emu_nid_to_phys[i] == NUMA_NO_NODE) emu_nid_to_phys[i] = dfl_phys_nid; @@ -501,12 +510,34 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) numa_set_distance(i, j, dist); } } + for (i = 0; i < numa_distance_cnt; i++) { + for (j = 0; j < numa_distance_cnt; j++) { + int physi, physj; + u8 dist; + + /* distance between fake nodes is already ok */ + if (emu_nid_to_phys[i] != NUMA_NO_NODE && + emu_nid_to_phys[j] != NUMA_NO_NODE) + continue; + if (emu_nid_to_phys[i] != NUMA_NO_NODE) + physi = emu_nid_to_phys[i]; + else + physi = i - max_emu_nid; + if (emu_nid_to_phys[j] != NUMA_NO_NODE) + physj = emu_nid_to_phys[j]; + else + physj = j - max_emu_nid; + dist = phys_dist[physi * numa_dist_cnt + physj]; + numa_set_distance(i, j, dist); + } + } /* free the copied physical distance table */ memblock_free(phys_dist, phys_size); return; no_emu: + numa_nodes_parsed = physnode_mask; /* No emulation. Build identity emu_nid_to_phys[] for numa_add_cpu() */ for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) emu_nid_to_phys[i] = i; diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index a3877e9bc878..ff4054f4334d 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -7,7 +7,7 @@ #include #include -static int numa_distance_cnt; +int numa_distance_cnt; static u8 *numa_distance; nodemask_t numa_nodes_parsed __initdata; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 1c485beb0b93..1cf121ad7085 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include "internal.h" @@ -430,10 +431,15 @@ static void dump_tasks(struct oom_control *oc) mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); else { struct task_struct *p; + int i = 0; rcu_read_lock(); - for_each_process(p) + for_each_process(p) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + touch_softlockup_watchdog(); dump_task(p, oc); + } rcu_read_unlock(); } } @@ -699,7 +705,7 @@ static void queue_oom_reaper(struct task_struct *tsk) } #ifdef CONFIG_SYSCTL -static struct ctl_table vm_oom_kill_table[] = { +static const struct ctl_table vm_oom_kill_table[] = { { .procname = "panic_on_oom", .data = &sysctl_panic_on_oom, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d213ead95675..eb55ece39c56 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -692,6 +692,8 @@ static unsigned long bdi_ratio_from_pages(unsigned long pages) unsigned long ratio; global_dirty_limits(&background_thresh, &dirty_thresh); + if (!dirty_thresh) + return -EINVAL; ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh); return ratio; @@ -790,13 +792,15 @@ int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes) { int ret; unsigned long pages = min_bytes >> PAGE_SHIFT; - unsigned long min_ratio; + long min_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; min_ratio = bdi_ratio_from_pages(pages); + if (min_ratio < 0) + return min_ratio; return __bdi_set_min_ratio(bdi, min_ratio); } @@ -809,13 +813,15 @@ int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes) { int ret; unsigned long pages = max_bytes >> PAGE_SHIFT; - unsigned long max_ratio; + long max_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; max_ratio = bdi_ratio_from_pages(pages); + if (max_ratio < 0) + return max_ratio; return __bdi_set_max_ratio(bdi, max_ratio); } @@ -936,26 +942,25 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE); + + /* + * It's very possible that wb_thresh is close to 0 not because the + * device is slow, but that it has remained inactive for long time. + * Honour such devices a reasonable good (hopefully IO efficient) + * threshold, so that the occasional writes won't be blocked and active + * writes can rampup the threshold quickly. + */ + if (thresh > dtc->dirty) { + if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) + wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 100); + else + wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 8); + } + wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); if (wb_thresh > wb_max_thresh) wb_thresh = wb_max_thresh; - /* - * With strictlimit flag, the wb_thresh is treated as - * a hard limit in balance_dirty_pages() and wb_position_ratio(). - * It's possible that wb_thresh is close to zero, not because - * the device is slow, but because it has been inactive. - * To prevent occasional writes from being blocked, we raise wb_thresh. - */ - if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { - unsigned long limit = hard_dirty_limit(dom, dtc->thresh); - u64 wb_scale_thresh = 0; - - if (limit > dtc->dirty) - wb_scale_thresh = (limit - dtc->dirty) / 100; - wb_thresh = max(wb_thresh, min(wb_scale_thresh, wb_max_thresh / 4)); - } - return wb_thresh; } @@ -963,6 +968,7 @@ unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; + domain_dirty_avail(&gdtc, true); return __wb_calc_thresh(&gdtc, thresh); } @@ -1139,12 +1145,6 @@ static void wb_position_ratio(struct dirty_throttle_control *dtc) if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; - if (dtc->wb_dirty < 8) { - dtc->pos_ratio = min_t(long long, pos_ratio * 2, - 2 << RATELIMIT_CALC_SHIFT); - return; - } - if (dtc->wb_dirty >= wb_thresh) return; @@ -1215,14 +1215,6 @@ static void wb_position_ratio(struct dirty_throttle_control *dtc) */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; - /* - * It's very possible that wb_thresh is close to 0 not because the - * device is slow, but that it has remained inactive for long time. - * Honour such devices a reasonable good (hopefully IO efficient) - * threshold, so that the occasional writes won't be blocked and active - * writes can rampup the threshold quickly. - */ - wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh @@ -1478,17 +1470,10 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". - * - * We rampup dirty_ratelimit forcibly if wb_dirty is low because - * it's possible that wb_thresh is close to zero due to inactivity - * of backing device. */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; - if (dtc->wb_dirty < 8) - setpoint = dtc->wb_dirty + 1; - else - setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; + setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { @@ -2313,7 +2298,7 @@ static int page_writeback_cpu_online(unsigned int cpu) /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; -static struct ctl_table vm_page_writeback_sysctls[] = { +static const struct ctl_table vm_page_writeback_sysctls[] = { { .procname = "dirty_background_ratio", .data = &dirty_background_ratio, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1cb4b8c8886d..579789600a3c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1238,13 +1238,15 @@ static void split_large_buddy(struct zone *zone, struct page *page, if (order > pageblock_order) order = pageblock_order; - while (pfn != end) { + do { int mt = get_pfnblock_migratetype(page, pfn); __free_one_page(page, pfn, zone, order, mt, fpi); pfn += 1 << order; + if (pfn == end) + break; page = pfn_to_page(pfn); - } + } while (1); } static void free_one_page(struct zone *zone, struct page *page, @@ -1293,12 +1295,6 @@ void __meminit __free_pages_core(struct page *page, unsigned int order, set_page_count(p, 0); } - /* - * Freeing the page with debug_pagealloc enabled will try to - * unmap it; some archs don't like double-unmappings, so - * map it first. - */ - debug_pagealloc_map_pages(page, nr_pages); adjust_managed_page_count(page, nr_pages); } else { for (loop = 0; loop < nr_pages; loop++, p++) { @@ -1506,7 +1502,6 @@ inline void post_alloc_hook(struct page *page, unsigned int order, int i; set_page_private(page, 0); - set_page_refcounted(page); arch_alloc_page(page, order); debug_pagealloc_map_pages(page, 1 << order); @@ -1854,6 +1849,14 @@ static bool can_steal_fallback(unsigned int order, int start_mt) if (order >= pageblock_order) return true; + /* + * Movable pages won't cause permanent fragmentation, so when you alloc + * small pages, you just need to temporarily steal unmovable or + * reclaimable pages that are closest to the request size. After a + * while, memory compaction may occur to form large contiguous pages, + * and the next movable allocation may not need to steal. Unmovable and + * reclaimable allocations need to actually steal pages. + */ if (order >= pageblock_order / 2 || start_mt == MIGRATE_RECLAIMABLE || start_mt == MIGRATE_UNMOVABLE || @@ -2590,9 +2593,9 @@ static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone, return high; } -static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, - struct page *page, int migratetype, - unsigned int order) +static void free_frozen_page_commit(struct zone *zone, + struct per_cpu_pages *pcp, struct page *page, int migratetype, + unsigned int order) { int high, batch; int pindex; @@ -2641,7 +2644,7 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, /* * Free a pcp page */ -void free_unref_page(struct page *page, unsigned int order) +void free_frozen_pages(struct page *page, unsigned int order) { unsigned long __maybe_unused UP_flags; struct per_cpu_pages *pcp; @@ -2664,20 +2667,20 @@ void free_unref_page(struct page *page, unsigned int order) * get those areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ + zone = page_zone(page); migratetype = get_pfnblock_migratetype(page, pfn); if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(page_zone(page), page, pfn, order, FPI_NONE); + free_one_page(zone, page, pfn, order, FPI_NONE); return; } migratetype = MIGRATE_MOVABLE; } - zone = page_zone(page); pcp_trylock_prepare(UP_flags); pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (pcp) { - free_unref_page_commit(zone, pcp, page, migratetype, order); + free_frozen_page_commit(zone, pcp, page, migratetype, order); pcp_spin_unlock(pcp); } else { free_one_page(zone, page, pfn, order, FPI_NONE); @@ -2741,7 +2744,7 @@ void free_unref_folios(struct folio_batch *folios) /* * Free isolated pages directly to the - * allocator, see comment in free_unref_page. + * allocator, see comment in free_frozen_pages. */ if (is_migrate_isolate(migratetype)) { free_one_page(zone, &folio->page, pfn, @@ -2772,7 +2775,7 @@ void free_unref_folios(struct folio_batch *folios) migratetype = MIGRATE_MOVABLE; trace_mm_page_free_batched(&folio->page); - free_unref_page_commit(zone, pcp, &folio->page, migratetype, + free_frozen_page_commit(zone, pcp, &folio->page, migratetype, order); } @@ -3565,7 +3568,6 @@ __alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order, if (!page) page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); - return page; } @@ -4529,28 +4531,23 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, } /* - * __alloc_pages_bulk - Allocate a number of order-0 pages to a list or array + * __alloc_pages_bulk - Allocate a number of order-0 pages to an array * @gfp: GFP flags for the allocation * @preferred_nid: The preferred NUMA node ID to allocate from * @nodemask: Set of nodes to allocate from, may be NULL - * @nr_pages: The number of pages desired on the list or array - * @page_list: Optional list to store the allocated pages - * @page_array: Optional array to store the pages + * @nr_pages: The number of pages desired in the array + * @page_array: Array to store the pages * * This is a batched version of the page allocator that attempts to - * allocate nr_pages quickly. Pages are added to page_list if page_list - * is not NULL, otherwise it is assumed that the page_array is valid. + * allocate nr_pages quickly. Pages are added to the page_array. * - * For lists, nr_pages is the number of pages that should be allocated. - * - * For arrays, only NULL elements are populated with pages and nr_pages + * Note that only NULL elements are populated with pages and nr_pages * is the maximum number of pages that will be stored in the array. * - * Returns the number of pages on the list or array. + * Returns the number of pages in the array. */ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, - struct list_head *page_list, struct page **page_array) { struct page *page; @@ -4568,7 +4565,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, * Skip populated array elements to determine if any pages need * to be allocated before disabling IRQs. */ - while (page_array && nr_populated < nr_pages && page_array[nr_populated]) + while (nr_populated < nr_pages && page_array[nr_populated]) nr_populated++; /* No pages requested? */ @@ -4576,7 +4573,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, goto out; /* Already populated array? */ - if (unlikely(page_array && nr_pages - nr_populated == 0)) + if (unlikely(nr_pages - nr_populated == 0)) goto out; /* Bulk allocator does not support memcg accounting. */ @@ -4658,7 +4655,7 @@ retry_this_zone: while (nr_populated < nr_pages) { /* Skip existing pages */ - if (page_array && page_array[nr_populated]) { + if (page_array[nr_populated]) { nr_populated++; continue; } @@ -4676,11 +4673,8 @@ retry_this_zone: nr_account++; prep_new_page(page, 0, gfp, 0); - if (page_list) - list_add(&page->lru, page_list); - else - page_array[nr_populated] = page; - nr_populated++; + set_page_refcounted(page); + page_array[nr_populated++] = page; } pcp_spin_unlock(pcp); @@ -4697,14 +4691,8 @@ failed_irq: failed: page = __alloc_pages_noprof(gfp, 0, preferred_nid, nodemask); - if (page) { - if (page_list) - list_add(&page->lru, page_list); - else - page_array[nr_populated] = page; - nr_populated++; - } - + if (page) + page_array[nr_populated++] = page; goto out; } EXPORT_SYMBOL_GPL(alloc_pages_bulk_noprof); @@ -4712,8 +4700,8 @@ EXPORT_SYMBOL_GPL(alloc_pages_bulk_noprof); /* * This is the 'heart' of the zoned buddy allocator. */ -struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, - int preferred_nid, nodemask_t *nodemask) +struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, + int preferred_nid, nodemask_t *nodemask) { struct page *page; unsigned int alloc_flags = ALLOC_WMARK_LOW; @@ -4766,7 +4754,7 @@ struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, out: if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT) && page && unlikely(__memcg_kmem_charge_page(page, gfp, order) != 0)) { - __free_pages(page, order); + free_frozen_pages(page, order); page = NULL; } @@ -4775,6 +4763,18 @@ out: return page; } +EXPORT_SYMBOL(__alloc_frozen_pages_noprof); + +struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, + int preferred_nid, nodemask_t *nodemask) +{ + struct page *page; + + page = __alloc_frozen_pages_noprof(gfp, order, preferred_nid, nodemask); + if (page) + set_page_refcounted(page); + return page; +} EXPORT_SYMBOL(__alloc_pages_noprof); struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, @@ -4835,11 +4835,11 @@ void __free_pages(struct page *page, unsigned int order) struct alloc_tag *tag = pgalloc_tag_get(page); if (put_page_testzero(page)) - free_unref_page(page, order); + free_frozen_pages(page, order); else if (!head) { pgalloc_tag_sub_pages(tag, (1 << order) - 1); while (order-- > 0) - free_unref_page(page + (1 << order), order); + free_frozen_pages(page + (1 << order), order); } } EXPORT_SYMBOL(__free_pages); @@ -5159,13 +5159,6 @@ static void build_thisnode_zonelists(pg_data_t *pgdat) zonerefs->zone_idx = 0; } -/* - * Build zonelists ordered by zone and nodes within zones. - * This results in conserving DMA zone[s] until all Normal memory is - * exhausted, but results in overflowing to remote node while memory - * may still exist in local DMA zone. - */ - static void build_zonelists(pg_data_t *pgdat) { static int node_order[MAX_NUMNODES]; @@ -5690,10 +5683,13 @@ __meminit void zone_pcp_init(struct zone *zone) zone->present_pages, zone_batchsize(zone)); } +static void setup_per_zone_lowmem_reserve(void); + void adjust_managed_page_count(struct page *page, long count) { atomic_long_add(count, &page_zone(page)->managed_pages); totalram_pages_add(count); + setup_per_zone_lowmem_reserve(); } EXPORT_SYMBOL(adjust_managed_page_count); @@ -6170,7 +6166,7 @@ out: return ret; } -static struct ctl_table page_alloc_sysctl_table[] = { +static const struct ctl_table page_alloc_sysctl_table[] = { { .procname = "min_free_kbytes", .data = &min_free_kbytes, @@ -6265,9 +6261,8 @@ static void alloc_contig_dump_pages(struct list_head *page_list) * @migratetype: using migratetype to filter the type of migration in * trace_mm_alloc_contig_migrate_range_info. */ -int __alloc_contig_migrate_range(struct compact_control *cc, - unsigned long start, unsigned long end, - int migratetype) +static int __alloc_contig_migrate_range(struct compact_control *cc, + unsigned long start, unsigned long end, int migratetype) { /* This function is based on compact_zone() from compaction.c. */ unsigned int nr_reclaimed; @@ -6276,7 +6271,7 @@ int __alloc_contig_migrate_range(struct compact_control *cc, int ret = 0; struct migration_target_control mtc = { .nid = zone_to_nid(cc->zone), - .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + .gfp_mask = cc->gfp_mask, .reason = MR_CONTIG_RANGE, }; struct page *page; @@ -6346,7 +6341,7 @@ int __alloc_contig_migrate_range(struct compact_control *cc, return (ret < 0) ? ret : 0; } -static void split_free_pages(struct list_head *list) +static void split_free_pages(struct list_head *list, gfp_t gfp_mask) { int order; @@ -6357,7 +6352,8 @@ static void split_free_pages(struct list_head *list) list_for_each_entry_safe(page, next, &list[order], lru) { int i; - post_alloc_hook(page, order, __GFP_MOVABLE); + post_alloc_hook(page, order, gfp_mask); + set_page_refcounted(page); if (!order) continue; @@ -6371,6 +6367,40 @@ static void split_free_pages(struct list_head *list) } } +static int __alloc_contig_verify_gfp_mask(gfp_t gfp_mask, gfp_t *gfp_cc_mask) +{ + const gfp_t reclaim_mask = __GFP_IO | __GFP_FS | __GFP_RECLAIM; + const gfp_t action_mask = __GFP_COMP | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | + __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO; + const gfp_t cc_action_mask = __GFP_RETRY_MAYFAIL | __GFP_NOWARN; + + /* + * We are given the range to allocate; node, mobility and placement + * hints are irrelevant at this point. We'll simply ignore them. + */ + gfp_mask &= ~(GFP_ZONEMASK | __GFP_RECLAIMABLE | __GFP_WRITE | + __GFP_HARDWALL | __GFP_THISNODE | __GFP_MOVABLE); + + /* + * We only support most reclaim flags (but not NOFAIL/NORETRY), and + * selected action flags. + */ + if (gfp_mask & ~(reclaim_mask | action_mask)) + return -EINVAL; + + /* + * Flags to control page compaction/migration/reclaim, to free up our + * page range. Migratable pages are movable, __GFP_MOVABLE is implied + * for them. + * + * Traditionally we always had __GFP_RETRY_MAYFAIL set, keep doing that + * to not degrade callers. + */ + *gfp_cc_mask = (gfp_mask & (reclaim_mask | cc_action_mask)) | + __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; + return 0; +} + /** * alloc_contig_range() -- tries to allocate given range of pages * @start: start PFN to allocate @@ -6379,7 +6409,9 @@ static void split_free_pages(struct list_head *list) * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks * in range must have the same migratetype and it must * be either of the two. - * @gfp_mask: GFP mask to use during compaction + * @gfp_mask: GFP mask. Node/zone/placement hints are ignored; only some + * action and reclaim modifiers are supported. Reclaim modifiers + * control allocation behavior during compaction/migration/reclaim. * * The PFN range does not have to be pageblock aligned. The PFN range must * belong to a single zone. @@ -6405,11 +6437,14 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end, .mode = MIGRATE_SYNC, .ignore_skip_hint = true, .no_set_skip_hint = true, - .gfp_mask = current_gfp_context(gfp_mask), .alloc_contig = true, }; INIT_LIST_HEAD(&cc.migratepages); + gfp_mask = current_gfp_context(gfp_mask); + if (__alloc_contig_verify_gfp_mask(gfp_mask, (gfp_t *)&cc.gfp_mask)) + return -EINVAL; + /* * What we do here is we mark all pageblocks in range as * MIGRATE_ISOLATE. Because pageblock and max order pages may @@ -6431,7 +6466,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end, * put back to page allocator so that buddy can use them. */ - ret = start_isolate_page_range(start, end, migratetype, 0, gfp_mask); + ret = start_isolate_page_range(start, end, migratetype, 0); if (ret) goto done; @@ -6450,7 +6485,17 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end, ret = __alloc_contig_migrate_range(&cc, start, end, migratetype); if (ret && ret != -EBUSY) goto done; - ret = 0; + + /* + * When in-use hugetlb pages are migrated, they may simply be released + * back into the free hugepage pool instead of being returned to the + * buddy system. After the migration of in-use huge pages is completed, + * we will invoke replace_free_hugepage_folios() to ensure that these + * hugepages are properly released to the buddy system. + */ + ret = replace_free_hugepage_folios(start, end); + if (ret) + goto done; /* * Pages from [start, end) are within a pageblock_nr_pages @@ -6484,7 +6529,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end, } if (!(gfp_mask & __GFP_COMP)) { - split_free_pages(cc.freepages); + split_free_pages(cc.freepages, gfp_mask); /* Free head and tail (if any) */ if (start != outer_start) @@ -6497,6 +6542,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end, check_new_pages(head, order); prep_new_page(head, order, gfp_mask, 0); + set_page_refcounted(head); } else { ret = -EINVAL; WARN(true, "PFN range: requested [%lu, %lu), allocated [%lu, %lu)\n", @@ -6551,7 +6597,9 @@ static bool zone_spans_last_pfn(const struct zone *zone, /** * alloc_contig_pages() -- tries to find and allocate contiguous range of pages * @nr_pages: Number of contiguous pages to allocate - * @gfp_mask: GFP mask to limit search and used during compaction + * @gfp_mask: GFP mask. Node/zone/placement hints limit the search; only some + * action and reclaim modifiers are supported. Reclaim modifiers + * control allocation behavior during compaction/migration/reclaim. * @nid: Target node * @nodemask: Mask for other possible nodes * diff --git a/mm/page_counter.c b/mm/page_counter.c index b249d15af9dd..af23f927611b 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -288,7 +288,7 @@ int page_counter_memparse(const char *buf, const char *max, } -#ifdef CONFIG_MEMCG +#if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM) /* * This function calculates an individual page counter's effective * protection which is derived from its own memory.min/low, its @@ -460,4 +460,4 @@ void page_counter_calculate_protection(struct page_counter *root, atomic_long_read(&parent->children_low_usage), recursive_protection)); } -#endif /* CONFIG_MEMCG */ +#endif /* CONFIG_MEMCG || CONFIG_CGROUP_DMEM */ diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c index 3f7a203d35c6..d2423f30577e 100644 --- a/mm/page_frag_cache.c +++ b/mm/page_frag_cache.c @@ -86,7 +86,7 @@ void __page_frag_cache_drain(struct page *page, unsigned int count) VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); if (page_ref_sub_and_test(page, count)) - free_unref_page(page, compound_order(page)); + free_frozen_pages(page, compound_order(page)); } EXPORT_SYMBOL(__page_frag_cache_drain); @@ -138,7 +138,7 @@ refill: goto refill; if (unlikely(encoded_page_decode_pfmemalloc(encoded_page))) { - free_unref_page(page, + free_frozen_pages(page, encoded_page_decode_order(encoded_page)); goto refill; } @@ -166,6 +166,6 @@ void page_frag_free(void *addr) struct page *page = virt_to_head_page(addr); if (unlikely(put_page_testzero(page))) - free_unref_page(page, compound_order(page)); + free_frozen_pages(page, compound_order(page)); } EXPORT_SYMBOL(page_frag_free); diff --git a/mm/page_idle.c b/mm/page_idle.c index 41ea77f22011..947c7c7a3728 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -112,7 +112,7 @@ static void page_idle_clear_pte_refs(struct folio *folio) } static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { u64 *out = (u64 *)buf; @@ -157,7 +157,7 @@ static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj, } static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { const u64 *in = (u64 *)buf; @@ -193,17 +193,17 @@ static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj, return (char *)in - buf; } -static struct bin_attribute page_idle_bitmap_attr = +static const struct bin_attribute page_idle_bitmap_attr = __BIN_ATTR(bitmap, 0600, page_idle_bitmap_read, page_idle_bitmap_write, 0); -static struct bin_attribute *page_idle_bin_attrs[] = { +static const struct bin_attribute *const page_idle_bin_attrs[] = { &page_idle_bitmap_attr, NULL, }; static const struct attribute_group page_idle_attr_group = { - .bin_attrs = page_idle_bin_attrs, + .bin_attrs_new = page_idle_bin_attrs, .name = "page_idle", }; diff --git a/mm/page_io.c b/mm/page_io.c index 4b4ea8e49cf6..9b983de351f9 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -163,7 +163,6 @@ reprobe: page_no = 1; /* force Empty message */ sis->max = page_no; sis->pages = page_no - 1; - sis->highest_bit = page_no - 1; out: return ret; bad_bmap: diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 7e04047977cf..c608e9d72865 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -286,7 +286,6 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * within a free or in-use page. * @boundary_pfn: pageblock-aligned pfn that a page might cross * @flags: isolation flags - * @gfp_flags: GFP flags used for migrating pages * @isolate_before: isolate the pageblock before the boundary_pfn * @skip_isolation: the flag to skip the pageblock isolation in second * isolate_single_pageblock() @@ -306,8 +305,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * the in-use page then splitting the free page. */ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, - gfp_t gfp_flags, bool isolate_before, bool skip_isolation, - int migratetype) + bool isolate_before, bool skip_isolation, int migratetype) { unsigned long start_pfn; unsigned long isolate_pageblock; @@ -444,8 +442,6 @@ failed: * and PageOffline() pages. * REPORT_FAILURE - report details about the failure to * isolate the range - * @gfp_flags: GFP flags used for migrating pages that sit across the - * range boundaries. * * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in * the range will never be allocated. Any free pages and pages freed in the @@ -478,7 +474,7 @@ failed: * Return: 0 on success and -EBUSY if any part of range cannot be isolated. */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - int migratetype, int flags, gfp_t gfp_flags) + int migratetype, int flags) { unsigned long pfn; struct page *page; @@ -489,7 +485,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, bool skip_isolation = false; /* isolate [isolate_start, isolate_start + pageblock_nr_pages) pageblock */ - ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false, + ret = isolate_single_pageblock(isolate_start, flags, false, skip_isolation, migratetype); if (ret) return ret; @@ -498,7 +494,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, skip_isolation = true; /* isolate [isolate_end - pageblock_nr_pages, isolate_end) pageblock */ - ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true, + ret = isolate_single_pageblock(isolate_end, flags, true, skip_isolation, migratetype); if (ret) { unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype); diff --git a/mm/percpu.c b/mm/percpu.c index d8dd31a2e407..ac61e3fc5f15 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1359,10 +1359,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, /* allocate chunk */ alloc_size = struct_size(chunk, populated, BITS_TO_LONGS(region_size >> PAGE_SHIFT)); - chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); - if (!chunk) - panic("%s: Failed to allocate %zu bytes\n", __func__, - alloc_size); + chunk = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); INIT_LIST_HEAD(&chunk->list); @@ -1374,24 +1371,14 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, region_bits = pcpu_chunk_map_bits(chunk); alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]); - chunk->alloc_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); - if (!chunk->alloc_map) - panic("%s: Failed to allocate %zu bytes\n", __func__, - alloc_size); + chunk->alloc_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]); - chunk->bound_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); - if (!chunk->bound_map) - panic("%s: Failed to allocate %zu bytes\n", __func__, - alloc_size); + chunk->bound_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]); - chunk->md_blocks = memblock_alloc(alloc_size, SMP_CACHE_BYTES); - if (!chunk->md_blocks) - panic("%s: Failed to allocate %zu bytes\n", __func__, - alloc_size); - + chunk->md_blocks = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); #ifdef NEED_PCPUOBJ_EXT /* first chunk is free to use */ chunk->obj_exts = NULL; @@ -2595,28 +2582,16 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, /* process group information and build config tables accordingly */ alloc_size = ai->nr_groups * sizeof(group_offsets[0]); - group_offsets = memblock_alloc(alloc_size, SMP_CACHE_BYTES); - if (!group_offsets) - panic("%s: Failed to allocate %zu bytes\n", __func__, - alloc_size); + group_offsets = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = ai->nr_groups * sizeof(group_sizes[0]); - group_sizes = memblock_alloc(alloc_size, SMP_CACHE_BYTES); - if (!group_sizes) - panic("%s: Failed to allocate %zu bytes\n", __func__, - alloc_size); + group_sizes = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = nr_cpu_ids * sizeof(unit_map[0]); - unit_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); - if (!unit_map) - panic("%s: Failed to allocate %zu bytes\n", __func__, - alloc_size); + unit_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = nr_cpu_ids * sizeof(unit_off[0]); - unit_off = memblock_alloc(alloc_size, SMP_CACHE_BYTES); - if (!unit_off) - panic("%s: Failed to allocate %zu bytes\n", __func__, - alloc_size); + unit_off = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; @@ -2685,12 +2660,9 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, pcpu_free_slot = pcpu_sidelined_slot + 1; pcpu_to_depopulate_slot = pcpu_free_slot + 1; pcpu_nr_slots = pcpu_to_depopulate_slot + 1; - pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * + pcpu_chunk_lists = memblock_alloc_or_panic(pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]), SMP_CACHE_BYTES); - if (!pcpu_chunk_lists) - panic("%s: Failed to allocate %zu bytes\n", __func__, - pcpu_nr_slots * sizeof(pcpu_chunk_lists[0])); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_chunk_lists[i]); @@ -3155,25 +3127,19 @@ void __init __weak pcpu_populate_pte(unsigned long addr) pmd_t *pmd; if (pgd_none(*pgd)) { - p4d = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE); - if (!p4d) - goto err_alloc; + p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE); pgd_populate(&init_mm, pgd, p4d); } p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { - pud = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); - if (!pud) - goto err_alloc; + pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE); p4d_populate(&init_mm, p4d, pud); } pud = pud_offset(p4d, addr); if (pud_none(*pud)) { - pmd = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); - if (!pmd) - goto err_alloc; + pmd = memblock_alloc_or_panic(PMD_TABLE_SIZE, PMD_TABLE_SIZE); pud_populate(&init_mm, pud, pmd); } @@ -3181,16 +3147,11 @@ void __init __weak pcpu_populate_pte(unsigned long addr) if (!pmd_present(*pmd)) { pte_t *new; - new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); - if (!new) - goto err_alloc; + new = memblock_alloc_or_panic(PTE_TABLE_SIZE, PTE_TABLE_SIZE); pmd_populate_kernel(&init_mm, pmd, new); } return; - -err_alloc: - panic("%s: Failed to allocate memory\n", __func__); } /** @@ -3237,10 +3198,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); - pages = memblock_alloc(pages_size, SMP_CACHE_BYTES); - if (!pages) - panic("%s: Failed to allocate %zu bytes\n", __func__, - pages_size); + pages = memblock_alloc_or_panic(pages_size, SMP_CACHE_BYTES); /* allocate pages */ j = 0; diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 5297dcc38c37..5a882f2b10f9 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -279,7 +279,7 @@ static unsigned long pmdp_get_lockless_start(void) { return 0; } static void pmdp_get_lockless_end(unsigned long irqflags) { } #endif -pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) +pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) { unsigned long irqflags; pmd_t pmdval; diff --git a/mm/pt_reclaim.c b/mm/pt_reclaim.c new file mode 100644 index 000000000000..7e9455a18aae --- /dev/null +++ b/mm/pt_reclaim.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include + +#include "internal.h" + +bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, + struct zap_details *details) +{ + return details && details->reclaim_pt && (end - start >= PMD_SIZE); +} + +bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval) +{ + spinlock_t *pml = pmd_lockptr(mm, pmd); + + if (!spin_trylock(pml)) + return false; + + *pmdval = pmdp_get_lockless(pmd); + pmd_clear(pmd); + spin_unlock(pml); + + return true; +} + +void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb, + pmd_t pmdval) +{ + pte_free_tlb(tlb, pmd_pgtable(pmdval), addr); + mm_dec_nr_ptes(mm); +} + +void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, + struct mmu_gather *tlb) +{ + pmd_t pmdval; + spinlock_t *pml, *ptl = NULL; + pte_t *start_pte, *pte; + int i; + + pml = pmd_lock(mm, pmd); + start_pte = pte_offset_map_rw_nolock(mm, pmd, addr, &pmdval, &ptl); + if (!start_pte) + goto out_ptl; + if (ptl != pml) + spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); + + /* Check if it is empty PTE page */ + for (i = 0, pte = start_pte; i < PTRS_PER_PTE; i++, pte++) { + if (!pte_none(ptep_get(pte))) + goto out_ptl; + } + pte_unmap(start_pte); + + pmd_clear(pmd); + + if (ptl != pml) + spin_unlock(ptl); + spin_unlock(pml); + + free_pte(mm, addr, tlb, pmdval); + + return; +out_ptl: + if (start_pte) + pte_unmap_unlock(start_pte, ptl); + if (ptl != pml) + spin_unlock(pml); +} diff --git a/mm/readahead.c b/mm/readahead.c index ea650b8b02fb..220155a5c964 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -128,6 +128,7 @@ #include #include #include +#include #include "internal.h" @@ -158,20 +159,10 @@ static void read_pages(struct readahead_control *rac) if (aops->readahead) { aops->readahead(rac); - /* - * Clean up the remaining folios. The sizes in ->ra - * may be used to size the next readahead, so make sure - * they accurately reflect what happened. - */ + /* Clean up the remaining folios. */ while ((folio = readahead_folio(rac)) != NULL) { - unsigned long nr = folio_nr_pages(folio); - folio_get(folio); - rac->ra->size -= nr; - if (rac->ra->async_size >= nr) { - rac->ra->async_size -= nr; - filemap_remove_folio(folio); - } + filemap_remove_folio(folio); folio_unlock(folio); folio_put(folio); } @@ -188,6 +179,18 @@ static void read_pages(struct readahead_control *rac) BUG_ON(readahead_count(rac)); } +static struct folio *ractl_alloc_folio(struct readahead_control *ractl, + gfp_t gfp_mask, unsigned int order) +{ + struct folio *folio; + + folio = filemap_alloc_folio(gfp_mask, order); + if (folio && ractl->dropbehind) + __folio_set_dropbehind(folio); + + return folio; +} + /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. @@ -265,8 +268,8 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, continue; } - folio = filemap_alloc_folio(gfp_mask, - mapping_min_folio_order(mapping)); + folio = ractl_alloc_folio(ractl, gfp_mask, + mapping_min_folio_order(mapping)); if (!folio) break; @@ -436,7 +439,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; - struct folio *folio = filemap_alloc_folio(gfp, order); + struct folio *folio = ractl_alloc_folio(ractl, gfp, order); if (!folio) return -ENOMEM; @@ -458,7 +461,8 @@ void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra, unsigned int new_order) { struct address_space *mapping = ractl->mapping; - pgoff_t index = readahead_index(ractl); + pgoff_t start = readahead_index(ractl); + pgoff_t index = start; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; @@ -516,12 +520,18 @@ void page_cache_ra_order(struct readahead_control *ractl, /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this - * situation. + * situation below. */ if (!err) return; fallback: - do_page_cache_ra(ractl, ra->size, ra->async_size); + /* + * ->readahead() may have updated readahead window size so we have to + * check there's still something to read. + */ + if (ra->size > index - start) + do_page_cache_ra(ractl, ra->size - (index - start), + ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, @@ -548,6 +558,15 @@ void page_cache_sync_ra(struct readahead_control *ractl, unsigned long max_pages, contig_count; pgoff_t prev_index, miss; + /* + * If we have pre-content watches we need to disable readahead to make + * sure that we don't find 0 filled pages in cache that we never emitted + * events for. Filesystems supporting HSM must make sure to not call + * this function with ractl->file unset for files handled by HSM. + */ + if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) + return; + /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced @@ -626,6 +645,10 @@ void page_cache_async_ra(struct readahead_control *ractl, if (!ra->ra_pages) return; + /* See the comment in page_cache_sync_ra. */ + if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) + return; + /* * Same bit is used for PG_readahead and PG_reclaim. */ @@ -646,7 +669,11 @@ void page_cache_async_ra(struct readahead_control *ractl, 1UL << order); if (index == expected) { ra->start += ra->size; - ra->size = get_next_ra_size(ra, max_pages); + /* + * In the case of MADV_HUGEPAGE, the actual size might exceed + * the readahead window. + */ + ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); ra->async_size = ra->size; goto readit; } @@ -750,7 +777,7 @@ void readahead_expand(struct readahead_control *ractl, if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ - folio = filemap_alloc_folio(gfp_mask, min_order); + folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; @@ -779,7 +806,7 @@ void readahead_expand(struct readahead_control *ractl, if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ - folio = filemap_alloc_folio(gfp_mask, min_order); + folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; diff --git a/mm/rodata_test.c b/mm/rodata_test.c index 6d783436951f..e7173fcd210c 100644 --- a/mm/rodata_test.c +++ b/mm/rodata_test.c @@ -12,7 +12,8 @@ #include #include -static const int rodata_test_data = 0xC3; +#define TEST_VALUE 0xC3 +static const int rodata_test_data = TEST_VALUE; void rodata_test(void) { @@ -20,7 +21,7 @@ void rodata_test(void) /* test 1: read the value */ /* If this test fails, some previous testrun has clobbered the state */ - if (!rodata_test_data) { + if (unlikely(READ_ONCE(rodata_test_data) != TEST_VALUE)) { pr_err("test 1 fails (start data)\n"); return; } @@ -33,7 +34,7 @@ void rodata_test(void) } /* test 3: check the value hasn't changed */ - if (rodata_test_data == zero) { + if (unlikely(READ_ONCE(rodata_test_data) != TEST_VALUE)) { pr_err("test data was changed\n"); return; } diff --git a/mm/secretmem.c b/mm/secretmem.c index 399552814fd0..1b0a214ee558 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -195,14 +195,13 @@ static struct file *secretmem_file_create(unsigned long flags) struct file *file; struct inode *inode; const char *anon_name = "[secretmem]"; - const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name)); int err; inode = alloc_anon_inode(secretmem_mnt->mnt_sb); if (IS_ERR(inode)) return ERR_CAST(inode); - err = security_inode_init_security_anon(inode, &qname, NULL); + err = security_inode_init_security_anon(inode, &QSTR(anon_name), NULL); if (err) { file = ERR_PTR(err); goto err_free_inode; diff --git a/mm/shmem.c b/mm/shmem.c index ccb9629a0f70..4ea6109a8043 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -553,38 +553,105 @@ static bool shmem_confirm_swap(struct address_space *mapping, /* ifdef here to avoid bloating shmem.o when not necessary */ static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; +static int tmpfs_huge __read_mostly = SHMEM_HUGE_NEVER; -static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - loff_t write_end, bool shmem_huge_force, - unsigned long vm_flags) +/** + * shmem_mapping_size_orders - Get allowable folio orders for the given file size. + * @mapping: Target address_space. + * @index: The page index. + * @write_end: end of a write, could extend inode size. + * + * This returns huge orders for folios (when supported) based on the file size + * which the mapping currently allows at the given index. The index is relevant + * due to alignment considerations the mapping might have. The returned order + * may be less than the size passed. + * + * Return: The orders. + */ +static inline unsigned int +shmem_mapping_size_orders(struct address_space *mapping, pgoff_t index, loff_t write_end) { + unsigned int order; + size_t size; + + if (!mapping_large_folio_support(mapping) || !write_end) + return 0; + + /* Calculate the write size based on the write_end */ + size = write_end - (index << PAGE_SHIFT); + order = filemap_get_order(size); + if (!order) + return 0; + + /* If we're not aligned, allocate a smaller folio */ + if (index & ((1UL << order) - 1)) + order = __ffs(index); + + order = min_t(size_t, order, MAX_PAGECACHE_ORDER); + return order > 0 ? BIT(order + 1) - 1 : 0; +} + +static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t index, + loff_t write_end, bool shmem_huge_force, + struct vm_area_struct *vma, + unsigned long vm_flags) +{ + unsigned int maybe_pmd_order = HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER ? + 0 : BIT(HPAGE_PMD_ORDER); + unsigned long within_size_orders; + unsigned int order; + pgoff_t aligned_index; loff_t i_size; - if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER) - return false; if (!S_ISREG(inode->i_mode)) - return false; + return 0; if (shmem_huge == SHMEM_HUGE_DENY) - return false; + return 0; if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE) - return true; + return maybe_pmd_order; + /* + * The huge order allocation for anon shmem is controlled through + * the mTHP interface, so we still use PMD-sized huge order to + * check whether global control is enabled. + * + * For tmpfs mmap()'s huge order, we still use PMD-sized order to + * allocate huge pages due to lack of a write size hint. + * + * Otherwise, tmpfs will allow getting a highest order hint based on + * the size of write and fallocate paths, then will try each allowable + * huge orders. + */ switch (SHMEM_SB(inode->i_sb)->huge) { case SHMEM_HUGE_ALWAYS: - return true; + if (vma) + return maybe_pmd_order; + + return shmem_mapping_size_orders(inode->i_mapping, index, write_end); case SHMEM_HUGE_WITHIN_SIZE: - index = round_up(index + 1, HPAGE_PMD_NR); - i_size = max(write_end, i_size_read(inode)); - i_size = round_up(i_size, PAGE_SIZE); - if (i_size >> PAGE_SHIFT >= index) - return true; + if (vma) + within_size_orders = maybe_pmd_order; + else + within_size_orders = shmem_mapping_size_orders(inode->i_mapping, + index, write_end); + + order = highest_order(within_size_orders); + while (within_size_orders) { + aligned_index = round_up(index + 1, 1 << order); + i_size = max(write_end, i_size_read(inode)); + i_size = round_up(i_size, PAGE_SIZE); + if (i_size >> PAGE_SHIFT >= aligned_index) + return within_size_orders; + + order = next_order(&within_size_orders, order); + } fallthrough; case SHMEM_HUGE_ADVISE: if (vm_flags & VM_HUGEPAGE) - return true; + return maybe_pmd_order; fallthrough; default: - return false; + return 0; } } @@ -779,14 +846,23 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, return 0; } -static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - loff_t write_end, bool shmem_huge_force, - unsigned long vm_flags) +static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t index, + loff_t write_end, bool shmem_huge_force, + struct vm_area_struct *vma, + unsigned long vm_flags) { - return false; + return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static void shmem_update_stats(struct folio *folio, int nr_pages) +{ + if (folio_test_pmd_mappable(folio)) + __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr_pages); + __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr_pages); + __lruvec_stat_mod_folio(folio, NR_SHMEM, nr_pages); +} + /* * Somewhat like filemap_add_folio, but error if expected item has gone. */ @@ -821,10 +897,7 @@ static int shmem_add_to_page_cache(struct folio *folio, xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; - if (folio_test_pmd_mappable(folio)) - __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr); - __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); - __lruvec_stat_mod_folio(folio, NR_SHMEM, nr); + shmem_update_stats(folio, nr); mapping->nrpages += nr; unlock: xas_unlock_irq(&xas); @@ -852,8 +925,7 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) error = shmem_replace_entry(mapping, folio->index, folio, radswap); folio->mapping = NULL; mapping->nrpages -= nr; - __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); - __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); + shmem_update_stats(folio, -nr); xa_unlock_irq(&mapping->i_pages); folio_put_refs(folio, nr); BUG_ON(error); @@ -1176,7 +1248,7 @@ static int shmem_getattr(struct mnt_idmap *idmap, STATX_ATTR_NODUMP); generic_fillattr(idmap, request_mask, inode, stat); - if (shmem_huge_global_enabled(inode, 0, 0, false, 0)) + if (shmem_huge_global_enabled(inode, 0, 0, false, NULL, 0)) stat->blksize = HPAGE_PMD_SIZE; if (request_mask & STATX_BTIME) { @@ -1531,7 +1603,7 @@ try_split: !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) - shmem_falloc->nr_unswapped++; + shmem_falloc->nr_unswapped += nr_pages; else shmem_falloc = NULL; spin_unlock(&inode->i_lock); @@ -1685,22 +1757,19 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, unsigned long mask = READ_ONCE(huge_shmem_orders_always); unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size); unsigned long vm_flags = vma ? vma->vm_flags : 0; - bool global_huge; + pgoff_t aligned_index; + unsigned int global_orders; loff_t i_size; int order; if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags))) return 0; - global_huge = shmem_huge_global_enabled(inode, index, write_end, - shmem_huge_force, vm_flags); - if (!vma || !vma_is_anon_shmem(vma)) { - /* - * For tmpfs, we now only support PMD sized THP if huge page - * is enabled, otherwise fallback to order 0. - */ - return global_huge ? BIT(HPAGE_PMD_ORDER) : 0; - } + global_orders = shmem_huge_global_enabled(inode, index, write_end, + shmem_huge_force, vma, vm_flags); + /* Tmpfs huge pages allocation */ + if (!vma || !vma_is_anon_shmem(vma)) + return global_orders; /* * Following the 'deny' semantics of the top level, force the huge @@ -1719,9 +1788,9 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, /* Allow mTHP that will be fully within i_size. */ order = highest_order(within_size_orders); while (within_size_orders) { - index = round_up(index + 1, order); + aligned_index = round_up(index + 1, 1 << order); i_size = round_up(i_size_read(inode), PAGE_SIZE); - if (i_size >> PAGE_SHIFT >= index) { + if (i_size >> PAGE_SHIFT >= aligned_index) { mask |= within_size_orders; break; } @@ -1732,7 +1801,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, if (vm_flags & VM_HUGEPAGE) mask |= READ_ONCE(huge_shmem_orders_madvise); - if (global_huge) + if (global_orders > 0) mask |= READ_ONCE(huge_shmem_orders_inherit); return THP_ORDERS_ALL_FILE_DEFAULT & mask; @@ -1898,6 +1967,65 @@ unlock: return ERR_PTR(error); } +static struct folio *shmem_swap_alloc_folio(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + swp_entry_t entry, int order, gfp_t gfp) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct folio *new; + void *shadow; + int nr_pages; + + /* + * We have arrived here because our zones are constrained, so don't + * limit chance of success with further cpuset and node constraints. + */ + gfp &= ~GFP_CONSTRAINT_MASK; + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && order > 0) { + gfp_t huge_gfp = vma_thp_gfp_mask(vma); + + gfp = limit_gfp_mask(huge_gfp, gfp); + } + + new = shmem_alloc_folio(gfp, order, info, index); + if (!new) + return ERR_PTR(-ENOMEM); + + nr_pages = folio_nr_pages(new); + if (mem_cgroup_swapin_charge_folio(new, vma ? vma->vm_mm : NULL, + gfp, entry)) { + folio_put(new); + return ERR_PTR(-ENOMEM); + } + + /* + * Prevent parallel swapin from proceeding with the swap cache flag. + * + * Of course there is another possible concurrent scenario as well, + * that is to say, the swap cache flag of a large folio has already + * been set by swapcache_prepare(), while another thread may have + * already split the large swap entry stored in the shmem mapping. + * In this case, shmem_add_to_page_cache() will help identify the + * concurrent swapin and return -EEXIST. + */ + if (swapcache_prepare(entry, nr_pages)) { + folio_put(new); + return ERR_PTR(-EEXIST); + } + + __folio_set_locked(new); + __folio_set_swapbacked(new); + new->swap = entry; + + mem_cgroup_swapin_uncharge_swap(entry, nr_pages); + shadow = get_shadow_from_swap_cache(entry); + if (shadow) + workingset_refault(new, shadow); + folio_add_lru(new); + swap_read_folio(new, NULL); + return new; +} + /* * When a page is moved from swapcache to shmem filecache (either by the * usual swapin of shmem_get_folio_gfp(), or by the less common swapoff of @@ -1969,10 +2097,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, } if (!error) { mem_cgroup_replace_folio(old, new); - __lruvec_stat_mod_folio(new, NR_FILE_PAGES, nr_pages); - __lruvec_stat_mod_folio(new, NR_SHMEM, nr_pages); - __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -nr_pages); - __lruvec_stat_mod_folio(old, NR_SHMEM, -nr_pages); + shmem_update_stats(new, nr_pages); + shmem_update_stats(old, -nr_pages); } xa_unlock_irq(&swap_mapping->i_pages); @@ -2003,7 +2129,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, } static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index, - struct folio *folio, swp_entry_t swap) + struct folio *folio, swp_entry_t swap, + bool skip_swapcache) { struct address_space *mapping = inode->i_mapping; swp_entry_t swapin_error; @@ -2019,7 +2146,8 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index, nr_pages = folio_nr_pages(folio); folio_wait_writeback(folio); - delete_from_swap_cache(folio); + if (!skip_swapcache) + delete_from_swap_cache(folio); /* * Don't treat swapin error folio as alloced. Otherwise inode->i_blocks * won't be 0 when inode is released and thus trigger WARN_ON(i_blocks) @@ -2123,6 +2251,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, struct shmem_inode_info *info = SHMEM_I(inode); struct swap_info_struct *si; struct folio *folio = NULL; + bool skip_swapcache = false; swp_entry_t swap; int error, nr_pages; @@ -2144,6 +2273,8 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, /* Look it up and read it in.. */ folio = swap_cache_get_folio(swap, NULL, 0); if (!folio) { + int order = xa_get_order(&mapping->i_pages, index); + bool fallback_order0 = false; int split_order; /* Or update major stats only when swapin succeeds?? */ @@ -2153,6 +2284,33 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, count_memcg_event_mm(fault_mm, PGMAJFAULT); } + /* + * If uffd is active for the vma, we need per-page fault + * fidelity to maintain the uffd semantics, then fallback + * to swapin order-0 folio, as well as for zswap case. + */ + if (order > 0 && ((vma && unlikely(userfaultfd_armed(vma))) || + !zswap_never_enabled())) + fallback_order0 = true; + + /* Skip swapcache for synchronous device. */ + if (!fallback_order0 && data_race(si->flags & SWP_SYNCHRONOUS_IO)) { + folio = shmem_swap_alloc_folio(inode, vma, index, swap, order, gfp); + if (!IS_ERR(folio)) { + skip_swapcache = true; + goto alloced; + } + + /* + * Fallback to swapin order-0 folio unless the swap entry + * already exists. + */ + error = PTR_ERR(folio); + folio = NULL; + if (error == -EEXIST) + goto failed; + } + /* * Now swap device can only swap in order 0 folio, then we * should split the large swap entry stored in the pagecache @@ -2183,9 +2341,10 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, } } +alloced: /* We have to do this with folio locked to prevent races */ folio_lock(folio); - if (!folio_test_swapcache(folio) || + if ((!skip_swapcache && !folio_test_swapcache(folio)) || folio->swap.val != swap.val || !shmem_confirm_swap(mapping, index, swap)) { error = -EEXIST; @@ -2221,7 +2380,12 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, if (sgp == SGP_WRITE) folio_mark_accessed(folio); - delete_from_swap_cache(folio); + if (skip_swapcache) { + folio->swap.val = 0; + swapcache_clear(si, swap, nr_pages); + } else { + delete_from_swap_cache(folio); + } folio_mark_dirty(folio); swap_free_nr(swap, nr_pages); put_swap_device(si); @@ -2232,8 +2396,11 @@ failed: if (!shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; if (error == -EIO) - shmem_set_folio_swapin_error(inode, index, folio, swap); + shmem_set_folio_swapin_error(inode, index, folio, swap, + skip_swapcache); unlock: + if (skip_swapcache) + swapcache_clear(si, swap, folio_nr_pages(folio)); if (folio) { folio_unlock(folio); folio_put(folio); @@ -2749,12 +2916,6 @@ out_nomem: static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); - struct shmem_inode_info *info = SHMEM_I(inode); - int ret; - - ret = seal_check_write(info->seals, vma); - if (ret) - return ret; file_accessed(file); /* This is anonymous shared memory if it is unlinked at the time of mmap */ @@ -3818,7 +3979,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry) static int shmem_rmdir(struct inode *dir, struct dentry *dentry) { - if (!simple_offset_empty(dentry)) + if (!simple_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); @@ -3875,7 +4036,7 @@ static int shmem_rename2(struct mnt_idmap *idmap, return simple_offset_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); - if (!simple_offset_empty(new_dentry)) + if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (flags & RENAME_WHITEOUT) { @@ -3914,6 +4075,7 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir, int len; struct inode *inode; struct folio *folio; + char *link; len = strlen(symname) + 1; if (len > PAGE_SIZE) @@ -3935,12 +4097,13 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir, inode->i_size = len-1; if (len <= SHORT_SYMLINK_LEN) { - inode->i_link = kmemdup(symname, len, GFP_KERNEL); - if (!inode->i_link) { + link = kmemdup(symname, len, GFP_KERNEL); + if (!link) { error = -ENOMEM; goto out_remove_offset; } inode->i_op = &shmem_short_symlink_operations; + inode_set_cached_link(inode, link, len - 1); } else { inode_nohighmem(inode); inode->i_mapping->a_ops = &shmem_aops; @@ -4365,7 +4528,7 @@ static int shmem_parse_opt_casefold(struct fs_context *fc, struct fs_parameter * bool latest_version) { struct shmem_options *ctx = fc->fs_private; - unsigned int version = UTF8_LATEST; + int version = UTF8_LATEST; struct unicode_map *encoding; char *version_str = param->string + 5; @@ -4580,48 +4743,37 @@ bad_value: return invalfc(fc, "Bad value for '%s'", param->key); } -static int shmem_parse_options(struct fs_context *fc, void *data) +static char *shmem_next_opt(char **s) { - char *options = data; + char *sbegin = *s; + char *p; - if (options) { - int err = security_sb_eat_lsm_opts(options, &fc->security); - if (err) - return err; - } + if (sbegin == NULL) + return NULL; - while (options != NULL) { - char *this_char = options; - for (;;) { - /* - * NUL-terminate this option: unfortunately, - * mount options form a comma-separated list, - * but mpol's nodelist may also contain commas. - */ - options = strchr(options, ','); - if (options == NULL) - break; - options++; - if (!isdigit(*options)) { - options[-1] = '\0'; - break; - } - } - if (*this_char) { - char *value = strchr(this_char, '='); - size_t len = 0; - int err; - - if (value) { - *value++ = '\0'; - len = strlen(value); - } - err = vfs_parse_fs_string(fc, this_char, value, len); - if (err < 0) - return err; + /* + * NUL-terminate this option: unfortunately, + * mount options form a comma-separated list, + * but mpol's nodelist may also contain commas. + */ + for (;;) { + p = strchr(*s, ','); + if (p == NULL) + break; + *s = p + 1; + if (!isdigit(*(p+1))) { + *p = '\0'; + return sbegin; } } - return 0; + + *s = NULL; + return sbegin; +} + +static int shmem_parse_monolithic(struct fs_context *fc, void *data) +{ + return vfs_parse_monolithic_sep(fc, data, shmem_next_opt); } /* @@ -4888,7 +5040,12 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) sbinfo->gid = ctx->gid; sbinfo->full_inums = ctx->full_inums; sbinfo->mode = ctx->mode; - sbinfo->huge = ctx->huge; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (ctx->seen & SHMEM_SEEN_HUGE) + sbinfo->huge = ctx->huge; + else + sbinfo->huge = tmpfs_huge; +#endif sbinfo->mpol = ctx->mpol; ctx->mpol = NULL; @@ -4966,7 +5123,7 @@ static const struct fs_context_operations shmem_fs_context_ops = { .free = shmem_free_fc, .get_tree = shmem_get_tree, #ifdef CONFIG_TMPFS - .parse_monolithic = shmem_parse_options, + .parse_monolithic = shmem_parse_monolithic, .parse_param = shmem_parse_one, .reconfigure = shmem_reconfigure, #endif @@ -5439,6 +5596,21 @@ static int __init setup_transparent_hugepage_shmem(char *str) } __setup("transparent_hugepage_shmem=", setup_transparent_hugepage_shmem); +static int __init setup_transparent_hugepage_tmpfs(char *str) +{ + int huge; + + huge = shmem_parse_huge(str); + if (huge < 0) { + pr_warn("transparent_hugepage_tmpfs= cannot parse, ignored\n"); + return huge; + } + + tmpfs_huge = huge; + return 1; +} +__setup("transparent_hugepage_tmpfs=", setup_transparent_hugepage_tmpfs); + static char str_dup[PAGE_SIZE] __initdata; static int __init setup_thp_shmem(char *str) { diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 4a85b94d12ce..794bd433cce0 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -195,8 +195,6 @@ int shrinker_debugfs_add(struct shrinker *shrinker) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { - struct dentry *entry; - char buf[128]; const char *new, *old; va_list ap; int ret = 0; @@ -213,18 +211,8 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) old = shrinker->name; shrinker->name = new; - if (shrinker->debugfs_entry) { - snprintf(buf, sizeof(buf), "%s-%d", shrinker->name, - shrinker->debugfs_id); - - entry = debugfs_rename(shrinker_debugfs_root, - shrinker->debugfs_entry, - shrinker_debugfs_root, buf); - if (IS_ERR(entry)) - ret = PTR_ERR(entry); - else - shrinker->debugfs_entry = entry; - } + ret = debugfs_change_name(shrinker->debugfs_entry, "%s-%d", + shrinker->name, shrinker->debugfs_id); mutex_unlock(&shrinker_mutex); diff --git a/mm/slab.h b/mm/slab.h index 632fedd71fea..e9fd9bf0bfa6 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -128,7 +128,7 @@ static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t) /** * slab_folio - The folio allocated for a slab - * @slab: The slab. + * @s: The slab. * * Slabs are allocated as folios that contain the individual objects and are * using some fields in the first struct page of the folio - those fields are @@ -159,7 +159,7 @@ static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t) /** * slab_page - The first struct page allocated for a slab - * @slab: The slab. + * @s: The slab. * * A convenience wrapper for converting slab to the first struct page of the * underlying folio, to communicate with code not yet converted to folio or diff --git a/mm/slab_common.c b/mm/slab_common.c index a29457bef626..4030907b6b7d 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -28,7 +28,9 @@ #include #include #include +#include +#include "../kernel/rcu/rcu.h" #include "internal.h" #include "slab.h" @@ -1282,3 +1284,881 @@ EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); EXPORT_TRACEPOINT_SYMBOL(kfree); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free); +/* + * This rcu parameter is runtime-read-only. It reflects + * a minimum allowed number of objects which can be cached + * per-CPU. Object size is equal to one page. This value + * can be changed at boot time. + */ +static int rcu_min_cached_objs = 5; +module_param(rcu_min_cached_objs, int, 0444); + +// A page shrinker can ask for pages to be freed to make them +// available for other parts of the system. This usually happens +// under low memory conditions, and in that case we should also +// defer page-cache filling for a short time period. +// +// The default value is 5 seconds, which is long enough to reduce +// interference with the shrinker while it asks other systems to +// drain their caches. +static int rcu_delay_page_cache_fill_msec = 5000; +module_param(rcu_delay_page_cache_fill_msec, int, 0444); + +/* Maximum number of jiffies to wait before draining a batch. */ +#define KFREE_DRAIN_JIFFIES (5 * HZ) +#define KFREE_N_BATCHES 2 +#define FREE_N_CHANNELS 2 + +/** + * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers + * @list: List node. All blocks are linked between each other + * @gp_snap: Snapshot of RCU state for objects placed to this bulk + * @nr_records: Number of active pointers in the array + * @records: Array of the kvfree_rcu() pointers + */ +struct kvfree_rcu_bulk_data { + struct list_head list; + struct rcu_gp_oldstate gp_snap; + unsigned long nr_records; + void *records[] __counted_by(nr_records); +}; + +/* + * This macro defines how many entries the "records" array + * will contain. It is based on the fact that the size of + * kvfree_rcu_bulk_data structure becomes exactly one page. + */ +#define KVFREE_BULK_MAX_ENTR \ + ((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *)) + +/** + * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests + * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period + * @head_free: List of kfree_rcu() objects waiting for a grace period + * @head_free_gp_snap: Grace-period snapshot to check for attempted premature frees. + * @bulk_head_free: Bulk-List of kvfree_rcu() objects waiting for a grace period + * @krcp: Pointer to @kfree_rcu_cpu structure + */ + +struct kfree_rcu_cpu_work { + struct rcu_work rcu_work; + struct rcu_head *head_free; + struct rcu_gp_oldstate head_free_gp_snap; + struct list_head bulk_head_free[FREE_N_CHANNELS]; + struct kfree_rcu_cpu *krcp; +}; + +/** + * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period + * @head: List of kfree_rcu() objects not yet waiting for a grace period + * @head_gp_snap: Snapshot of RCU state for objects placed to "@head" + * @bulk_head: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period + * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period + * @lock: Synchronize access to this structure + * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES + * @initialized: The @rcu_work fields have been initialized + * @head_count: Number of objects in rcu_head singular list + * @bulk_count: Number of objects in bulk-list + * @bkvcache: + * A simple cache list that contains objects for reuse purpose. + * In order to save some per-cpu space the list is singular. + * Even though it is lockless an access has to be protected by the + * per-cpu lock. + * @page_cache_work: A work to refill the cache when it is empty + * @backoff_page_cache_fill: Delay cache refills + * @work_in_progress: Indicates that page_cache_work is running + * @hrtimer: A hrtimer for scheduling a page_cache_work + * @nr_bkv_objs: number of allocated objects at @bkvcache. + * + * This is a per-CPU structure. The reason that it is not included in + * the rcu_data structure is to permit this code to be extracted from + * the RCU files. Such extraction could allow further optimization of + * the interactions with the slab allocators. + */ +struct kfree_rcu_cpu { + // Objects queued on a linked list + // through their rcu_head structures. + struct rcu_head *head; + unsigned long head_gp_snap; + atomic_t head_count; + + // Objects queued on a bulk-list. + struct list_head bulk_head[FREE_N_CHANNELS]; + atomic_t bulk_count[FREE_N_CHANNELS]; + + struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; + raw_spinlock_t lock; + struct delayed_work monitor_work; + bool initialized; + + struct delayed_work page_cache_work; + atomic_t backoff_page_cache_fill; + atomic_t work_in_progress; + struct hrtimer hrtimer; + + struct llist_head bkvcache; + int nr_bkv_objs; +}; + +static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = { + .lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock), +}; + +static __always_inline void +debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead) +{ +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD + int i; + + for (i = 0; i < bhead->nr_records; i++) + debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i])); +#endif +} + +static inline struct kfree_rcu_cpu * +krc_this_cpu_lock(unsigned long *flags) +{ + struct kfree_rcu_cpu *krcp; + + local_irq_save(*flags); // For safely calling this_cpu_ptr(). + krcp = this_cpu_ptr(&krc); + raw_spin_lock(&krcp->lock); + + return krcp; +} + +static inline void +krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags) +{ + raw_spin_unlock_irqrestore(&krcp->lock, flags); +} + +static inline struct kvfree_rcu_bulk_data * +get_cached_bnode(struct kfree_rcu_cpu *krcp) +{ + if (!krcp->nr_bkv_objs) + return NULL; + + WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs - 1); + return (struct kvfree_rcu_bulk_data *) + llist_del_first(&krcp->bkvcache); +} + +static inline bool +put_cached_bnode(struct kfree_rcu_cpu *krcp, + struct kvfree_rcu_bulk_data *bnode) +{ + // Check the limit. + if (krcp->nr_bkv_objs >= rcu_min_cached_objs) + return false; + + llist_add((struct llist_node *) bnode, &krcp->bkvcache); + WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs + 1); + return true; +} + +static int +drain_page_cache(struct kfree_rcu_cpu *krcp) +{ + unsigned long flags; + struct llist_node *page_list, *pos, *n; + int freed = 0; + + if (!rcu_min_cached_objs) + return 0; + + raw_spin_lock_irqsave(&krcp->lock, flags); + page_list = llist_del_all(&krcp->bkvcache); + WRITE_ONCE(krcp->nr_bkv_objs, 0); + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + llist_for_each_safe(pos, n, page_list) { + free_page((unsigned long)pos); + freed++; + } + + return freed; +} + +static void +kvfree_rcu_bulk(struct kfree_rcu_cpu *krcp, + struct kvfree_rcu_bulk_data *bnode, int idx) +{ + unsigned long flags; + int i; + + if (!WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&bnode->gp_snap))) { + debug_rcu_bhead_unqueue(bnode); + rcu_lock_acquire(&rcu_callback_map); + if (idx == 0) { // kmalloc() / kfree(). + trace_rcu_invoke_kfree_bulk_callback( + "slab", bnode->nr_records, + bnode->records); + + kfree_bulk(bnode->nr_records, bnode->records); + } else { // vmalloc() / vfree(). + for (i = 0; i < bnode->nr_records; i++) { + trace_rcu_invoke_kvfree_callback( + "slab", bnode->records[i], 0); + + vfree(bnode->records[i]); + } + } + rcu_lock_release(&rcu_callback_map); + } + + raw_spin_lock_irqsave(&krcp->lock, flags); + if (put_cached_bnode(krcp, bnode)) + bnode = NULL; + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + if (bnode) + free_page((unsigned long) bnode); + + cond_resched_tasks_rcu_qs(); +} + +static void +kvfree_rcu_list(struct rcu_head *head) +{ + struct rcu_head *next; + + for (; head; head = next) { + void *ptr = (void *) head->func; + unsigned long offset = (void *) head - ptr; + + next = head->next; + debug_rcu_head_unqueue((struct rcu_head *)ptr); + rcu_lock_acquire(&rcu_callback_map); + trace_rcu_invoke_kvfree_callback("slab", head, offset); + + if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset))) + kvfree(ptr); + + rcu_lock_release(&rcu_callback_map); + cond_resched_tasks_rcu_qs(); + } +} + +/* + * This function is invoked in workqueue context after a grace period. + * It frees all the objects queued on ->bulk_head_free or ->head_free. + */ +static void kfree_rcu_work(struct work_struct *work) +{ + unsigned long flags; + struct kvfree_rcu_bulk_data *bnode, *n; + struct list_head bulk_head[FREE_N_CHANNELS]; + struct rcu_head *head; + struct kfree_rcu_cpu *krcp; + struct kfree_rcu_cpu_work *krwp; + struct rcu_gp_oldstate head_gp_snap; + int i; + + krwp = container_of(to_rcu_work(work), + struct kfree_rcu_cpu_work, rcu_work); + krcp = krwp->krcp; + + raw_spin_lock_irqsave(&krcp->lock, flags); + // Channels 1 and 2. + for (i = 0; i < FREE_N_CHANNELS; i++) + list_replace_init(&krwp->bulk_head_free[i], &bulk_head[i]); + + // Channel 3. + head = krwp->head_free; + krwp->head_free = NULL; + head_gp_snap = krwp->head_free_gp_snap; + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + // Handle the first two channels. + for (i = 0; i < FREE_N_CHANNELS; i++) { + // Start from the tail page, so a GP is likely passed for it. + list_for_each_entry_safe(bnode, n, &bulk_head[i], list) + kvfree_rcu_bulk(krcp, bnode, i); + } + + /* + * This is used when the "bulk" path can not be used for the + * double-argument of kvfree_rcu(). This happens when the + * page-cache is empty, which means that objects are instead + * queued on a linked list through their rcu_head structures. + * This list is named "Channel 3". + */ + if (head && !WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&head_gp_snap))) + kvfree_rcu_list(head); +} + +static bool +need_offload_krc(struct kfree_rcu_cpu *krcp) +{ + int i; + + for (i = 0; i < FREE_N_CHANNELS; i++) + if (!list_empty(&krcp->bulk_head[i])) + return true; + + return !!READ_ONCE(krcp->head); +} + +static bool +need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp) +{ + int i; + + for (i = 0; i < FREE_N_CHANNELS; i++) + if (!list_empty(&krwp->bulk_head_free[i])) + return true; + + return !!krwp->head_free; +} + +static int krc_count(struct kfree_rcu_cpu *krcp) +{ + int sum = atomic_read(&krcp->head_count); + int i; + + for (i = 0; i < FREE_N_CHANNELS; i++) + sum += atomic_read(&krcp->bulk_count[i]); + + return sum; +} + +static void +__schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) +{ + long delay, delay_left; + + delay = krc_count(krcp) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES; + if (delayed_work_pending(&krcp->monitor_work)) { + delay_left = krcp->monitor_work.timer.expires - jiffies; + if (delay < delay_left) + mod_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); + return; + } + queue_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); +} + +static void +schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&krcp->lock, flags); + __schedule_delayed_monitor_work(krcp); + raw_spin_unlock_irqrestore(&krcp->lock, flags); +} + +static void +kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp) +{ + struct list_head bulk_ready[FREE_N_CHANNELS]; + struct kvfree_rcu_bulk_data *bnode, *n; + struct rcu_head *head_ready = NULL; + unsigned long flags; + int i; + + raw_spin_lock_irqsave(&krcp->lock, flags); + for (i = 0; i < FREE_N_CHANNELS; i++) { + INIT_LIST_HEAD(&bulk_ready[i]); + + list_for_each_entry_safe_reverse(bnode, n, &krcp->bulk_head[i], list) { + if (!poll_state_synchronize_rcu_full(&bnode->gp_snap)) + break; + + atomic_sub(bnode->nr_records, &krcp->bulk_count[i]); + list_move(&bnode->list, &bulk_ready[i]); + } + } + + if (krcp->head && poll_state_synchronize_rcu(krcp->head_gp_snap)) { + head_ready = krcp->head; + atomic_set(&krcp->head_count, 0); + WRITE_ONCE(krcp->head, NULL); + } + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + for (i = 0; i < FREE_N_CHANNELS; i++) { + list_for_each_entry_safe(bnode, n, &bulk_ready[i], list) + kvfree_rcu_bulk(krcp, bnode, i); + } + + if (head_ready) + kvfree_rcu_list(head_ready); +} + +/* + * Return: %true if a work is queued, %false otherwise. + */ +static bool +kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp) +{ + unsigned long flags; + bool queued = false; + int i, j; + + raw_spin_lock_irqsave(&krcp->lock, flags); + + // Attempt to start a new batch. + for (i = 0; i < KFREE_N_BATCHES; i++) { + struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]); + + // Try to detach bulk_head or head and attach it, only when + // all channels are free. Any channel is not free means at krwp + // there is on-going rcu work to handle krwp's free business. + if (need_wait_for_krwp_work(krwp)) + continue; + + // kvfree_rcu_drain_ready() might handle this krcp, if so give up. + if (need_offload_krc(krcp)) { + // Channel 1 corresponds to the SLAB-pointer bulk path. + // Channel 2 corresponds to vmalloc-pointer bulk path. + for (j = 0; j < FREE_N_CHANNELS; j++) { + if (list_empty(&krwp->bulk_head_free[j])) { + atomic_set(&krcp->bulk_count[j], 0); + list_replace_init(&krcp->bulk_head[j], + &krwp->bulk_head_free[j]); + } + } + + // Channel 3 corresponds to both SLAB and vmalloc + // objects queued on the linked list. + if (!krwp->head_free) { + krwp->head_free = krcp->head; + get_state_synchronize_rcu_full(&krwp->head_free_gp_snap); + atomic_set(&krcp->head_count, 0); + WRITE_ONCE(krcp->head, NULL); + } + + // One work is per one batch, so there are three + // "free channels", the batch can handle. Break + // the loop since it is done with this CPU thus + // queuing an RCU work is _always_ success here. + queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work); + WARN_ON_ONCE(!queued); + break; + } + } + + raw_spin_unlock_irqrestore(&krcp->lock, flags); + return queued; +} + +/* + * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. + */ +static void kfree_rcu_monitor(struct work_struct *work) +{ + struct kfree_rcu_cpu *krcp = container_of(work, + struct kfree_rcu_cpu, monitor_work.work); + + // Drain ready for reclaim. + kvfree_rcu_drain_ready(krcp); + + // Queue a batch for a rest. + kvfree_rcu_queue_batch(krcp); + + // If there is nothing to detach, it means that our job is + // successfully done here. In case of having at least one + // of the channels that is still busy we should rearm the + // work to repeat an attempt. Because previous batches are + // still in progress. + if (need_offload_krc(krcp)) + schedule_delayed_monitor_work(krcp); +} + +static void fill_page_cache_func(struct work_struct *work) +{ + struct kvfree_rcu_bulk_data *bnode; + struct kfree_rcu_cpu *krcp = + container_of(work, struct kfree_rcu_cpu, + page_cache_work.work); + unsigned long flags; + int nr_pages; + bool pushed; + int i; + + nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ? + 1 : rcu_min_cached_objs; + + for (i = READ_ONCE(krcp->nr_bkv_objs); i < nr_pages; i++) { + bnode = (struct kvfree_rcu_bulk_data *) + __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + + if (!bnode) + break; + + raw_spin_lock_irqsave(&krcp->lock, flags); + pushed = put_cached_bnode(krcp, bnode); + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + if (!pushed) { + free_page((unsigned long) bnode); + break; + } + } + + atomic_set(&krcp->work_in_progress, 0); + atomic_set(&krcp->backoff_page_cache_fill, 0); +} + +// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock() +// state specified by flags. If can_alloc is true, the caller must +// be schedulable and not be holding any locks or mutexes that might be +// acquired by the memory allocator or anything that it might invoke. +// Returns true if ptr was successfully recorded, else the caller must +// use a fallback. +static inline bool +add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp, + unsigned long *flags, void *ptr, bool can_alloc) +{ + struct kvfree_rcu_bulk_data *bnode; + int idx; + + *krcp = krc_this_cpu_lock(flags); + if (unlikely(!(*krcp)->initialized)) + return false; + + idx = !!is_vmalloc_addr(ptr); + bnode = list_first_entry_or_null(&(*krcp)->bulk_head[idx], + struct kvfree_rcu_bulk_data, list); + + /* Check if a new block is required. */ + if (!bnode || bnode->nr_records == KVFREE_BULK_MAX_ENTR) { + bnode = get_cached_bnode(*krcp); + if (!bnode && can_alloc) { + krc_this_cpu_unlock(*krcp, *flags); + + // __GFP_NORETRY - allows a light-weight direct reclaim + // what is OK from minimizing of fallback hitting point of + // view. Apart of that it forbids any OOM invoking what is + // also beneficial since we are about to release memory soon. + // + // __GFP_NOMEMALLOC - prevents from consuming of all the + // memory reserves. Please note we have a fallback path. + // + // __GFP_NOWARN - it is supposed that an allocation can + // be failed under low memory or high memory pressure + // scenarios. + bnode = (struct kvfree_rcu_bulk_data *) + __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + raw_spin_lock_irqsave(&(*krcp)->lock, *flags); + } + + if (!bnode) + return false; + + // Initialize the new block and attach it. + bnode->nr_records = 0; + list_add(&bnode->list, &(*krcp)->bulk_head[idx]); + } + + // Finally insert and update the GP for this page. + bnode->nr_records++; + bnode->records[bnode->nr_records - 1] = ptr; + get_state_synchronize_rcu_full(&bnode->gp_snap); + atomic_inc(&(*krcp)->bulk_count[idx]); + + return true; +} + +#if !defined(CONFIG_TINY_RCU) + +static enum hrtimer_restart +schedule_page_work_fn(struct hrtimer *t) +{ + struct kfree_rcu_cpu *krcp = + container_of(t, struct kfree_rcu_cpu, hrtimer); + + queue_delayed_work(system_highpri_wq, &krcp->page_cache_work, 0); + return HRTIMER_NORESTART; +} + +static void +run_page_cache_worker(struct kfree_rcu_cpu *krcp) +{ + // If cache disabled, bail out. + if (!rcu_min_cached_objs) + return; + + if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING && + !atomic_xchg(&krcp->work_in_progress, 1)) { + if (atomic_read(&krcp->backoff_page_cache_fill)) { + queue_delayed_work(system_unbound_wq, + &krcp->page_cache_work, + msecs_to_jiffies(rcu_delay_page_cache_fill_msec)); + } else { + hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + krcp->hrtimer.function = schedule_page_work_fn; + hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL); + } + } +} + +void __init kfree_rcu_scheduler_running(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + if (need_offload_krc(krcp)) + schedule_delayed_monitor_work(krcp); + } +} + +/* + * Queue a request for lazy invocation of the appropriate free routine + * after a grace period. Please note that three paths are maintained, + * two for the common case using arrays of pointers and a third one that + * is used only when the main paths cannot be used, for example, due to + * memory pressure. + * + * Each kvfree_call_rcu() request is added to a batch. The batch will be drained + * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will + * be free'd in workqueue context. This allows us to: batch requests together to + * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load. + */ +void kvfree_call_rcu(struct rcu_head *head, void *ptr) +{ + unsigned long flags; + struct kfree_rcu_cpu *krcp; + bool success; + + /* + * Please note there is a limitation for the head-less + * variant, that is why there is a clear rule for such + * objects: it can be used from might_sleep() context + * only. For other places please embed an rcu_head to + * your data. + */ + if (!head) + might_sleep(); + + // Queue the object but don't yet schedule the batch. + if (debug_rcu_head_queue(ptr)) { + // Probable double kfree_rcu(), just leak. + WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n", + __func__, head); + + // Mark as success and leave. + return; + } + + kasan_record_aux_stack(ptr); + success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head); + if (!success) { + run_page_cache_worker(krcp); + + if (head == NULL) + // Inline if kvfree_rcu(one_arg) call. + goto unlock_return; + + head->func = ptr; + head->next = krcp->head; + WRITE_ONCE(krcp->head, head); + atomic_inc(&krcp->head_count); + + // Take a snapshot for this krcp. + krcp->head_gp_snap = get_state_synchronize_rcu(); + success = true; + } + + /* + * The kvfree_rcu() caller considers the pointer freed at this point + * and likely removes any references to it. Since the actual slab + * freeing (and kmemleak_free()) is deferred, tell kmemleak to ignore + * this object (no scanning or false positives reporting). + */ + kmemleak_ignore(ptr); + + // Set timer to drain after KFREE_DRAIN_JIFFIES. + if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING) + __schedule_delayed_monitor_work(krcp); + +unlock_return: + krc_this_cpu_unlock(krcp, flags); + + /* + * Inline kvfree() after synchronize_rcu(). We can do + * it from might_sleep() context only, so the current + * CPU can pass the QS state. + */ + if (!success) { + debug_rcu_head_unqueue((struct rcu_head *) ptr); + synchronize_rcu(); + kvfree(ptr); + } +} +EXPORT_SYMBOL_GPL(kvfree_call_rcu); + +/** + * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete. + * + * Note that a single argument of kvfree_rcu() call has a slow path that + * triggers synchronize_rcu() following by freeing a pointer. It is done + * before the return from the function. Therefore for any single-argument + * call that will result in a kfree() to a cache that is to be destroyed + * during module exit, it is developer's responsibility to ensure that all + * such calls have returned before the call to kmem_cache_destroy(). + */ +void kvfree_rcu_barrier(void) +{ + struct kfree_rcu_cpu_work *krwp; + struct kfree_rcu_cpu *krcp; + bool queued; + int i, cpu; + + /* + * Firstly we detach objects and queue them over an RCU-batch + * for all CPUs. Finally queued works are flushed for each CPU. + * + * Please note. If there are outstanding batches for a particular + * CPU, those have to be finished first following by queuing a new. + */ + for_each_possible_cpu(cpu) { + krcp = per_cpu_ptr(&krc, cpu); + + /* + * Check if this CPU has any objects which have been queued for a + * new GP completion. If not(means nothing to detach), we are done + * with it. If any batch is pending/running for this "krcp", below + * per-cpu flush_rcu_work() waits its completion(see last step). + */ + if (!need_offload_krc(krcp)) + continue; + + while (1) { + /* + * If we are not able to queue a new RCU work it means: + * - batches for this CPU are still in flight which should + * be flushed first and then repeat; + * - no objects to detach, because of concurrency. + */ + queued = kvfree_rcu_queue_batch(krcp); + + /* + * Bail out, if there is no need to offload this "krcp" + * anymore. As noted earlier it can run concurrently. + */ + if (queued || !need_offload_krc(krcp)) + break; + + /* There are ongoing batches. */ + for (i = 0; i < KFREE_N_BATCHES; i++) { + krwp = &(krcp->krw_arr[i]); + flush_rcu_work(&krwp->rcu_work); + } + } + } + + /* + * Now we guarantee that all objects are flushed. + */ + for_each_possible_cpu(cpu) { + krcp = per_cpu_ptr(&krc, cpu); + + /* + * A monitor work can drain ready to reclaim objects + * directly. Wait its completion if running or pending. + */ + cancel_delayed_work_sync(&krcp->monitor_work); + + for (i = 0; i < KFREE_N_BATCHES; i++) { + krwp = &(krcp->krw_arr[i]); + flush_rcu_work(&krwp->rcu_work); + } + } +} +EXPORT_SYMBOL_GPL(kvfree_rcu_barrier); + +#endif /* #if !defined(CONFIG_TINY_RCU) */ + +static unsigned long +kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + int cpu; + unsigned long count = 0; + + /* Snapshot count of all CPUs */ + for_each_possible_cpu(cpu) { + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + count += krc_count(krcp); + count += READ_ONCE(krcp->nr_bkv_objs); + atomic_set(&krcp->backoff_page_cache_fill, 1); + } + + return count == 0 ? SHRINK_EMPTY : count; +} + +static unsigned long +kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + int cpu, freed = 0; + + for_each_possible_cpu(cpu) { + int count; + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + count = krc_count(krcp); + count += drain_page_cache(krcp); + kfree_rcu_monitor(&krcp->monitor_work.work); + + sc->nr_to_scan -= count; + freed += count; + + if (sc->nr_to_scan <= 0) + break; + } + + return freed == 0 ? SHRINK_STOP : freed; +} + +void __init kvfree_rcu_init(void) +{ + int cpu; + int i, j; + struct shrinker *kfree_rcu_shrinker; + + /* Clamp it to [0:100] seconds interval. */ + if (rcu_delay_page_cache_fill_msec < 0 || + rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) { + + rcu_delay_page_cache_fill_msec = + clamp(rcu_delay_page_cache_fill_msec, 0, + (int) (100 * MSEC_PER_SEC)); + + pr_info("Adjusting rcutree.rcu_delay_page_cache_fill_msec to %d ms.\n", + rcu_delay_page_cache_fill_msec); + } + + for_each_possible_cpu(cpu) { + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + for (i = 0; i < KFREE_N_BATCHES; i++) { + INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work); + krcp->krw_arr[i].krcp = krcp; + + for (j = 0; j < FREE_N_CHANNELS; j++) + INIT_LIST_HEAD(&krcp->krw_arr[i].bulk_head_free[j]); + } + + for (i = 0; i < FREE_N_CHANNELS; i++) + INIT_LIST_HEAD(&krcp->bulk_head[i]); + + INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor); + INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func); + krcp->initialized = true; + } + + kfree_rcu_shrinker = shrinker_alloc(0, "slab-kvfree-rcu"); + if (!kfree_rcu_shrinker) { + pr_err("Failed to allocate kfree_rcu() shrinker!\n"); + return; + } + + kfree_rcu_shrinker->count_objects = kfree_rcu_shrink_count; + kfree_rcu_shrinker->scan_objects = kfree_rcu_shrink_scan; + + shrinker_register(kfree_rcu_shrinker); +} diff --git a/mm/slub.c b/mm/slub.c index c2151c9fee22..1f50129dcfb3 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2311,7 +2311,7 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init, * We have to do this manually because the rcu_head is * not located inside the object. */ - kasan_record_aux_stack_noalloc(x); + kasan_record_aux_stack(x); delayed_free->object = x; call_rcu(&delayed_free->head, slab_free_after_rcu_debug); @@ -2420,17 +2420,15 @@ static inline struct slab *alloc_slab_page(gfp_t flags, int node, unsigned int order = oo_order(oo); if (node == NUMA_NO_NODE) - folio = (struct folio *)alloc_pages(flags, order); + folio = (struct folio *)alloc_frozen_pages(flags, order); else - folio = (struct folio *)__alloc_pages_node(node, flags, order); + folio = (struct folio *)__alloc_frozen_pages(flags, order, node, NULL); if (!folio) return NULL; slab = folio_slab(folio); __folio_set_slab(folio); - /* Make the flag visible before any changes to folio->mapping */ - smp_wmb(); if (folio_is_pfmemalloc(folio)) slab_set_pfmemalloc(slab); @@ -2651,12 +2649,10 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab) __slab_clear_pfmemalloc(slab); folio->mapping = NULL; - /* Make the mapping reset visible before clearing the flag */ - smp_wmb(); __folio_clear_slab(folio); mm_account_reclaimed_pages(pages); unaccount_slab(slab, order, s); - __free_pages(&folio->page, order); + free_frozen_pages(&folio->page, order); } static void rcu_free_slab(struct rcu_head *h) @@ -7513,10 +7509,7 @@ static int slab_debug_trace_open(struct inode *inode, struct file *filep) return -ENOMEM; } - if (strcmp(filep->f_path.dentry->d_name.name, "alloc_traces") == 0) - alloc = TRACK_ALLOC; - else - alloc = TRACK_FREE; + alloc = debugfs_get_aux_num(filep); if (!alloc_loc_track(t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL)) { bitmap_free(obj_map); @@ -7572,11 +7565,11 @@ static void debugfs_slab_add(struct kmem_cache *s) slab_cache_dir = debugfs_create_dir(s->name, slab_debugfs_root); - debugfs_create_file("alloc_traces", 0400, - slab_cache_dir, s, &slab_debugfs_fops); + debugfs_create_file_aux_num("alloc_traces", 0400, slab_cache_dir, s, + TRACK_ALLOC, &slab_debugfs_fops); - debugfs_create_file("free_traces", 0400, - slab_cache_dir, s, &slab_debugfs_fops); + debugfs_create_file_aux_num("free_traces", 0400, slab_cache_dir, s, + TRACK_FREE, &slab_debugfs_fops); } void debugfs_slab_release(struct kmem_cache *s) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index cec67c5f37d8..3287ebadd167 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -31,6 +31,8 @@ #include #include +#include "internal.h" + /* * Allocate a block of memory to be used to back the virtual memory map * or to back the page tables that are used to create the mapping. @@ -42,8 +44,7 @@ static void * __ref __earlyonly_bootmem_alloc(int node, unsigned long align, unsigned long goal) { - return memblock_alloc_try_nid_raw(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, node); + return memmap_alloc(size, align, goal, node, false); } void * __meminit vmemmap_alloc_block(unsigned long size, int node) diff --git a/mm/sparse.c b/mm/sparse.c index 13b6624d3562..133b033d0cba 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -257,10 +257,7 @@ static void __init memblocks_present(void) size = sizeof(struct mem_section *) * NR_SECTION_ROOTS; align = 1 << (INTERNODE_CACHE_SHIFT); - mem_section = memblock_alloc(size, align); - if (!mem_section) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, size, align); + mem_section = memblock_alloc_or_panic(size, align); } #endif diff --git a/mm/swap.c b/mm/swap.c index 10decd9dffa1..fc8281ef4241 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -109,7 +109,7 @@ void __folio_put(struct folio *folio) page_cache_release(folio); folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); - free_unref_page(&folio->page, folio_order(folio)); + free_frozen_pages(&folio->page, folio_order(folio)); } EXPORT_SYMBOL(__folio_put); @@ -379,37 +379,58 @@ static void __lru_cache_activate_folio(struct folio *folio) } #ifdef CONFIG_LRU_GEN -static void folio_inc_refs(struct folio *folio) + +static void lru_gen_inc_refs(struct folio *folio) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); if (folio_test_unevictable(folio)) return; + /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) { - folio_set_referenced(folio); + set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced)); return; } - if (!folio_test_workingset(folio)) { - folio_set_workingset(folio); - return; - } - - /* see the comment on MAX_NR_TIERS */ do { - new_flags = old_flags & LRU_REFS_MASK; - if (new_flags == LRU_REFS_MASK) - break; + if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) { + if (!folio_test_workingset(folio)) + folio_set_workingset(folio); + return; + } - new_flags += BIT(LRU_REFS_PGOFF); - new_flags |= old_flags & ~LRU_REFS_MASK; + new_flags = old_flags + BIT(LRU_REFS_PGOFF); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); } -#else -static void folio_inc_refs(struct folio *folio) + +static bool lru_gen_clear_refs(struct folio *folio) +{ + struct lru_gen_folio *lrugen; + int gen = folio_lru_gen(folio); + int type = folio_is_file_lru(folio); + + if (gen < 0) + return true; + + set_mask_bits(&folio->flags, LRU_REFS_FLAGS | BIT(PG_workingset), 0); + + lrugen = &folio_lruvec(folio)->lrugen; + /* whether can do without shuffling under the LRU lock */ + return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type])); +} + +#else /* !CONFIG_LRU_GEN */ + +static void lru_gen_inc_refs(struct folio *folio) { } + +static bool lru_gen_clear_refs(struct folio *folio) +{ + return false; +} + #endif /* CONFIG_LRU_GEN */ /** @@ -427,8 +448,10 @@ static void folio_inc_refs(struct folio *folio) */ void folio_mark_accessed(struct folio *folio) { + if (folio_test_dropbehind(folio)) + return; if (lru_gen_enabled()) { - folio_inc_refs(folio); + lru_gen_inc_refs(folio); return; } @@ -474,7 +497,7 @@ void folio_add_lru(struct folio *folio) folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - /* see the comment in lru_gen_add_folio() */ + /* see the comment in lru_gen_folio_seq() */ if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); @@ -524,7 +547,7 @@ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) */ static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio) { - bool active = folio_test_active(folio); + bool active = folio_test_active(folio) || lru_gen_enabled(); long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio)) @@ -589,7 +612,10 @@ static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio) lruvec_del_folio(lruvec, folio); folio_clear_active(folio); - folio_clear_referenced(folio); + if (lru_gen_enabled()) + lru_gen_clear_refs(folio); + else + folio_clear_referenced(folio); /* * Lazyfree folios are clean anonymous folios. They have * the swapbacked flag cleared, to distinguish them from normal @@ -657,6 +683,9 @@ void deactivate_file_folio(struct folio *folio) if (folio_test_unevictable(folio)) return; + if (lru_gen_enabled() && lru_gen_clear_refs(folio)) + return; + folio_batch_add_and_move(folio, lru_deactivate_file, true); } @@ -670,7 +699,10 @@ void deactivate_file_folio(struct folio *folio) */ void folio_deactivate(struct folio *folio) { - if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) + if (folio_test_unevictable(folio)) + return; + + if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; folio_batch_add_and_move(folio, lru_deactivate, true); diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c index da1278f0563b..be39078f255b 100644 --- a/mm/swap_cgroup.c +++ b/mm/swap_cgroup.c @@ -6,149 +6,106 @@ #include /* depends on mm.h include */ static DEFINE_MUTEX(swap_cgroup_mutex); + +/* Pack two cgroup id (short) of two entries in one swap_cgroup (atomic_t) */ +#define ID_PER_SC (sizeof(struct swap_cgroup) / sizeof(unsigned short)) +#define ID_SHIFT (BITS_PER_TYPE(unsigned short)) +#define ID_MASK (BIT(ID_SHIFT) - 1) +struct swap_cgroup { + atomic_t ids; +}; + struct swap_cgroup_ctrl { - struct page **map; - unsigned long length; - spinlock_t lock; + struct swap_cgroup *map; }; static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES]; -struct swap_cgroup { - unsigned short id; -}; -#define SC_PER_PAGE (PAGE_SIZE/sizeof(struct swap_cgroup)) - -/* - * SwapCgroup implements "lookup" and "exchange" operations. - * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge - * against SwapCache. At swap_free(), this is accessed directly from swap. - * - * This means, - * - we have no race in "exchange" when we're accessed via SwapCache because - * SwapCache(and its swp_entry) is under lock. - * - When called via swap_free(), there is no user of this entry and no race. - * Then, we don't need lock around "exchange". - * - * TODO: we can push these buffers out to HIGHMEM. - */ - -/* - * allocate buffer for swap_cgroup. - */ -static int swap_cgroup_prepare(int type) +static unsigned short __swap_cgroup_id_lookup(struct swap_cgroup *map, + pgoff_t offset) { - struct page *page; - struct swap_cgroup_ctrl *ctrl; - unsigned long idx, max; + unsigned int shift = (offset % ID_PER_SC) * ID_SHIFT; + unsigned int old_ids = atomic_read(&map[offset / ID_PER_SC].ids); - ctrl = &swap_cgroup_ctrl[type]; + BUILD_BUG_ON(!is_power_of_2(ID_PER_SC)); + BUILD_BUG_ON(sizeof(struct swap_cgroup) != sizeof(atomic_t)); - for (idx = 0; idx < ctrl->length; idx++) { - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) - goto not_enough_page; - ctrl->map[idx] = page; - - if (!(idx % SWAP_CLUSTER_MAX)) - cond_resched(); - } - return 0; -not_enough_page: - max = idx; - for (idx = 0; idx < max; idx++) - __free_page(ctrl->map[idx]); - - return -ENOMEM; + return (old_ids >> shift) & ID_MASK; } -static struct swap_cgroup *__lookup_swap_cgroup(struct swap_cgroup_ctrl *ctrl, - pgoff_t offset) +static unsigned short __swap_cgroup_id_xchg(struct swap_cgroup *map, + pgoff_t offset, + unsigned short new_id) { - struct page *mappage; - struct swap_cgroup *sc; + unsigned short old_id; + struct swap_cgroup *sc = &map[offset / ID_PER_SC]; + unsigned int shift = (offset % ID_PER_SC) * ID_SHIFT; + unsigned int new_ids, old_ids = atomic_read(&sc->ids); - mappage = ctrl->map[offset / SC_PER_PAGE]; - sc = page_address(mappage); - return sc + offset % SC_PER_PAGE; -} + do { + old_id = (old_ids >> shift) & ID_MASK; + new_ids = (old_ids & ~(ID_MASK << shift)); + new_ids |= ((unsigned int)new_id) << shift; + } while (!atomic_try_cmpxchg(&sc->ids, &old_ids, new_ids)); -static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent, - struct swap_cgroup_ctrl **ctrlp) -{ - pgoff_t offset = swp_offset(ent); - struct swap_cgroup_ctrl *ctrl; - - ctrl = &swap_cgroup_ctrl[swp_type(ent)]; - if (ctrlp) - *ctrlp = ctrl; - return __lookup_swap_cgroup(ctrl, offset); + return old_id; } /** - * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry. - * @ent: swap entry to be cmpxchged - * @old: old id - * @new: new id + * swap_cgroup_record - record mem_cgroup for a set of swap entries. + * These entries must belong to one single folio, and that folio + * must be being charged for swap space (swap out), and these + * entries must not have been charged * - * Returns old id at success, 0 at failure. - * (There is no mem_cgroup using 0 as its id) + * @folio: the folio that the swap entry belongs to + * @ent: the first swap entry to be recorded */ -unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, - unsigned short old, unsigned short new) +void swap_cgroup_record(struct folio *folio, swp_entry_t ent) { - struct swap_cgroup_ctrl *ctrl; - struct swap_cgroup *sc; - unsigned long flags; - unsigned short retval; + unsigned int nr_ents = folio_nr_pages(folio); + struct swap_cgroup *map; + pgoff_t offset, end; + unsigned short old; - sc = lookup_swap_cgroup(ent, &ctrl); + offset = swp_offset(ent); + end = offset + nr_ents; + map = swap_cgroup_ctrl[swp_type(ent)].map; - spin_lock_irqsave(&ctrl->lock, flags); - retval = sc->id; - if (retval == old) - sc->id = new; - else - retval = 0; - spin_unlock_irqrestore(&ctrl->lock, flags); - return retval; + do { + old = __swap_cgroup_id_xchg(map, offset, + mem_cgroup_id(folio_memcg(folio))); + VM_BUG_ON(old); + } while (++offset != end); } /** - * swap_cgroup_record - record mem_cgroup for a set of swap entries + * swap_cgroup_clear - clear mem_cgroup for a set of swap entries. + * These entries must be being uncharged from swap. They either + * belongs to one single folio in the swap cache (swap in for + * cgroup v1), or no longer have any users (slot freeing). + * * @ent: the first swap entry to be recorded into - * @id: mem_cgroup to be recorded * @nr_ents: number of swap entries to be recorded * - * Returns old value at success, 0 at failure. - * (Of course, old value can be 0.) + * Returns the existing old value. */ -unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, - unsigned int nr_ents) +unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents) { - struct swap_cgroup_ctrl *ctrl; - struct swap_cgroup *sc; - unsigned short old; - unsigned long flags; pgoff_t offset = swp_offset(ent); pgoff_t end = offset + nr_ents; + struct swap_cgroup *map; + unsigned short old, iter = 0; - sc = lookup_swap_cgroup(ent, &ctrl); + offset = swp_offset(ent); + end = offset + nr_ents; + map = swap_cgroup_ctrl[swp_type(ent)].map; - spin_lock_irqsave(&ctrl->lock, flags); - old = sc->id; - for (;;) { - VM_BUG_ON(sc->id != old); - sc->id = id; - offset++; - if (offset == end) - break; - if (offset % SC_PER_PAGE) - sc++; - else - sc = __lookup_swap_cgroup(ctrl, offset); - } - spin_unlock_irqrestore(&ctrl->lock, flags); + do { + old = __swap_cgroup_id_xchg(map, offset, 0); + if (!iter) + iter = old; + VM_BUG_ON(iter != old); + } while (++offset != end); return old; } @@ -161,39 +118,33 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, */ unsigned short lookup_swap_cgroup_id(swp_entry_t ent) { - if (mem_cgroup_disabled()) - return 0; - return lookup_swap_cgroup(ent, NULL)->id; -} - -int swap_cgroup_swapon(int type, unsigned long max_pages) -{ - void *array; - unsigned long length; struct swap_cgroup_ctrl *ctrl; if (mem_cgroup_disabled()) return 0; - length = DIV_ROUND_UP(max_pages, SC_PER_PAGE); + ctrl = &swap_cgroup_ctrl[swp_type(ent)]; + return __swap_cgroup_id_lookup(ctrl->map, swp_offset(ent)); +} - array = vcalloc(length, sizeof(void *)); - if (!array) +int swap_cgroup_swapon(int type, unsigned long max_pages) +{ + struct swap_cgroup *map; + struct swap_cgroup_ctrl *ctrl; + + if (mem_cgroup_disabled()) + return 0; + + BUILD_BUG_ON(sizeof(unsigned short) * ID_PER_SC != + sizeof(struct swap_cgroup)); + map = vzalloc(DIV_ROUND_UP(max_pages, ID_PER_SC) * + sizeof(struct swap_cgroup)); + if (!map) goto nomem; ctrl = &swap_cgroup_ctrl[type]; mutex_lock(&swap_cgroup_mutex); - ctrl->length = length; - ctrl->map = array; - spin_lock_init(&ctrl->lock); - if (swap_cgroup_prepare(type)) { - /* memory shortage */ - ctrl->map = NULL; - ctrl->length = 0; - mutex_unlock(&swap_cgroup_mutex); - vfree(array); - goto nomem; - } + ctrl->map = map; mutex_unlock(&swap_cgroup_mutex); return 0; @@ -205,8 +156,7 @@ nomem: void swap_cgroup_swapoff(int type) { - struct page **map; - unsigned long i, length; + struct swap_cgroup *map; struct swap_cgroup_ctrl *ctrl; if (mem_cgroup_disabled()) @@ -215,19 +165,8 @@ void swap_cgroup_swapoff(int type) mutex_lock(&swap_cgroup_mutex); ctrl = &swap_cgroup_ctrl[type]; map = ctrl->map; - length = ctrl->length; ctrl->map = NULL; - ctrl->length = 0; mutex_unlock(&swap_cgroup_mutex); - if (map) { - for (i = 0; i < length; i++) { - struct page *page = map[i]; - if (page) - __free_page(page); - if (!(i % SWAP_CLUSTER_MAX)) - cond_resched(); - } - vfree(map); - } + vfree(map); } diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 13ab3b771409..9c7c171df7ba 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -43,17 +43,15 @@ static DEFINE_MUTEX(swap_slots_cache_mutex); /* Serialize swap slots cache enable/disable operations */ static DEFINE_MUTEX(swap_slots_cache_enable_mutex); -static void __drain_swap_slots_cache(unsigned int type); +static void __drain_swap_slots_cache(void); #define use_swap_slot_cache (swap_slot_cache_active && swap_slot_cache_enabled) -#define SLOTS_CACHE 0x1 -#define SLOTS_CACHE_RET 0x2 static void deactivate_swap_slots_cache(void) { mutex_lock(&swap_slots_cache_mutex); swap_slot_cache_active = false; - __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET); + __drain_swap_slots_cache(); mutex_unlock(&swap_slots_cache_mutex); } @@ -72,7 +70,7 @@ void disable_swap_slots_cache_lock(void) if (swap_slot_cache_initialized) { /* serialize with cpu hotplug operations */ cpus_read_lock(); - __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET); + __drain_swap_slots_cache(); cpus_read_unlock(); } } @@ -113,7 +111,7 @@ out: static int alloc_swap_slot_cache(unsigned int cpu) { struct swap_slots_cache *cache; - swp_entry_t *slots, *slots_ret; + swp_entry_t *slots; /* * Do allocation outside swap_slots_cache_mutex @@ -125,28 +123,19 @@ static int alloc_swap_slot_cache(unsigned int cpu) if (!slots) return -ENOMEM; - slots_ret = kvcalloc(SWAP_SLOTS_CACHE_SIZE, sizeof(swp_entry_t), - GFP_KERNEL); - if (!slots_ret) { - kvfree(slots); - return -ENOMEM; - } - mutex_lock(&swap_slots_cache_mutex); cache = &per_cpu(swp_slots, cpu); - if (cache->slots || cache->slots_ret) { + if (cache->slots) { /* cache already allocated */ mutex_unlock(&swap_slots_cache_mutex); kvfree(slots); - kvfree(slots_ret); return 0; } if (!cache->lock_initialized) { mutex_init(&cache->alloc_lock); - spin_lock_init(&cache->free_lock); cache->lock_initialized = true; } cache->nr = 0; @@ -160,19 +149,16 @@ static int alloc_swap_slot_cache(unsigned int cpu) */ mb(); cache->slots = slots; - cache->slots_ret = slots_ret; mutex_unlock(&swap_slots_cache_mutex); return 0; } -static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type, - bool free_slots) +static void drain_slots_cache_cpu(unsigned int cpu, bool free_slots) { struct swap_slots_cache *cache; - swp_entry_t *slots = NULL; cache = &per_cpu(swp_slots, cpu); - if ((type & SLOTS_CACHE) && cache->slots) { + if (cache->slots) { mutex_lock(&cache->alloc_lock); swapcache_free_entries(cache->slots + cache->cur, cache->nr); cache->cur = 0; @@ -183,20 +169,9 @@ static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type, } mutex_unlock(&cache->alloc_lock); } - if ((type & SLOTS_CACHE_RET) && cache->slots_ret) { - spin_lock_irq(&cache->free_lock); - swapcache_free_entries(cache->slots_ret, cache->n_ret); - cache->n_ret = 0; - if (free_slots && cache->slots_ret) { - slots = cache->slots_ret; - cache->slots_ret = NULL; - } - spin_unlock_irq(&cache->free_lock); - kvfree(slots); - } } -static void __drain_swap_slots_cache(unsigned int type) +static void __drain_swap_slots_cache(void) { unsigned int cpu; @@ -224,13 +199,13 @@ static void __drain_swap_slots_cache(unsigned int type) * There are no slots on such cpu that need to be drained. */ for_each_online_cpu(cpu) - drain_slots_cache_cpu(cpu, type, false); + drain_slots_cache_cpu(cpu, false); } static int free_slot_cache(unsigned int cpu) { mutex_lock(&swap_slots_cache_mutex); - drain_slots_cache_cpu(cpu, SLOTS_CACHE | SLOTS_CACHE_RET, true); + drain_slots_cache_cpu(cpu, true); mutex_unlock(&swap_slots_cache_mutex); return 0; } @@ -269,39 +244,6 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache) return cache->nr; } -void free_swap_slot(swp_entry_t entry) -{ - struct swap_slots_cache *cache; - - /* Large folio swap slot is not covered. */ - zswap_invalidate(entry); - - cache = raw_cpu_ptr(&swp_slots); - if (likely(use_swap_slot_cache && cache->slots_ret)) { - spin_lock_irq(&cache->free_lock); - /* Swap slots cache may be deactivated before acquiring lock */ - if (!use_swap_slot_cache || !cache->slots_ret) { - spin_unlock_irq(&cache->free_lock); - goto direct_free; - } - if (cache->n_ret >= SWAP_SLOTS_CACHE_SIZE) { - /* - * Return slots to global pool. - * The current swap_map value is SWAP_HAS_CACHE. - * Set it to 0 to indicate it is available for - * allocation in global pool - */ - swapcache_free_entries(cache->slots_ret, cache->n_ret); - cache->n_ret = 0; - } - cache->slots_ret[cache->n_ret++] = entry; - spin_unlock_irq(&cache->free_lock); - } else { -direct_free: - swapcache_free_entries(&entry, 1); - } -} - swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; diff --git a/mm/swap_state.c b/mm/swap_state.c index e0c0321b8ff7..ca42b2be64d9 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -317,7 +317,6 @@ void free_pages_and_swap_cache(struct encoded_page **pages, int nr) struct folio_batch folios; unsigned int refs[PAGEVEC_SIZE]; - lru_add_drain(); folio_batch_init(&folios); for (int i = 0; i < nr; i++) { struct folio *folio = page_folio(encoded_page_ptr(pages[i])); diff --git a/mm/swapfile.c b/mm/swapfile.c index b0a9071cfe1d..ba19430dd4ea 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -53,15 +53,15 @@ static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); -static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry, - unsigned int nr_pages); -static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, +static void swap_entry_range_free(struct swap_info_struct *si, + struct swap_cluster_info *ci, + swp_entry_t entry, unsigned int nr_pages); +static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries); static bool folio_swapcache_freeable(struct folio *folio); -static struct swap_cluster_info *lock_cluster_or_swap_info( - struct swap_info_struct *si, unsigned long offset); -static void unlock_cluster_or_swap_info(struct swap_info_struct *si, - struct swap_cluster_info *ci); +static struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, + unsigned long offset); +static inline void unlock_cluster(struct swap_cluster_info *ci); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; @@ -129,6 +129,26 @@ static inline unsigned char swap_count(unsigned char ent) return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } +/* + * Use the second highest bit of inuse_pages counter as the indicator + * if one swap device is on the available plist, so the atomic can + * still be updated arithmetically while having special data embedded. + * + * inuse_pages counter is the only thing indicating if a device should + * be on avail_lists or not (except swapon / swapoff). By embedding the + * off-list bit in the atomic counter, updates no longer need any lock + * to check the list status. + * + * This bit will be set if the device is not on the plist and not + * usable, will be cleared if the device is on the plist. + */ +#define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2)) +#define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT) +static long swap_usage_in_pages(struct swap_info_struct *si) +{ + return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK; +} + /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* @@ -222,9 +242,9 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si, * swap_map is HAS_CACHE only, which means the slots have no page table * reference or pending writeback, and can't be allocated to others. */ - ci = lock_cluster_or_swap_info(si, offset); + ci = lock_cluster(si, offset); need_reclaim = swap_is_has_cache(si, offset, nr_pages); - unlock_cluster_or_swap_info(si, ci); + unlock_cluster(ci); if (!need_reclaim) goto out_unlock; @@ -242,12 +262,9 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si, folio_ref_sub(folio, nr_pages); folio_set_dirty(folio); - spin_lock(&si->lock); - /* Only sinple page folio can be backed by zswap */ - if (nr_pages == 1) - zswap_invalidate(entry); - swap_entry_range_free(si, entry, nr_pages); - spin_unlock(&si->lock); + ci = lock_cluster(si, offset); + swap_entry_range_free(si, ci, entry, nr_pages); + unlock_cluster(ci); ret = nr_pages; out_unlock: folio_unlock(folio); @@ -382,9 +399,23 @@ static void discard_swap_cluster(struct swap_info_struct *si, #endif #define LATENCY_LIMIT 256 -static inline bool cluster_is_free(struct swap_cluster_info *info) +static inline bool cluster_is_empty(struct swap_cluster_info *info) { - return info->flags & CLUSTER_FLAG_FREE; + return info->count == 0; +} + +static inline bool cluster_is_discard(struct swap_cluster_info *info) +{ + return info->flags == CLUSTER_FLAG_DISCARD; +} + +static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order) +{ + if (unlikely(ci->flags > CLUSTER_FLAG_USABLE)) + return false; + if (!order) + return true; + return cluster_is_empty(ci) || order == ci->order; } static inline unsigned int cluster_index(struct swap_info_struct *si, @@ -393,6 +424,12 @@ static inline unsigned int cluster_index(struct swap_info_struct *si, return ci - si->cluster_info; } +static inline struct swap_cluster_info *offset_to_cluster(struct swap_info_struct *si, + unsigned long offset) +{ + return &si->cluster_info[offset / SWAPFILE_CLUSTER]; +} + static inline unsigned int cluster_offset(struct swap_info_struct *si, struct swap_cluster_info *ci) { @@ -404,45 +441,38 @@ static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si { struct swap_cluster_info *ci; - ci = si->cluster_info; - if (ci) { - ci += offset / SWAPFILE_CLUSTER; - spin_lock(&ci->lock); - } + ci = offset_to_cluster(si, offset); + spin_lock(&ci->lock); + return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { - if (ci) - spin_unlock(&ci->lock); + spin_unlock(&ci->lock); } -/* - * Determine the locking method in use for this device. Return - * swap_cluster_info if SSD-style cluster-based locking is in place. - */ -static inline struct swap_cluster_info *lock_cluster_or_swap_info( - struct swap_info_struct *si, unsigned long offset) +static void move_cluster(struct swap_info_struct *si, + struct swap_cluster_info *ci, struct list_head *list, + enum swap_cluster_flags new_flags) { - struct swap_cluster_info *ci; + VM_WARN_ON(ci->flags == new_flags); - /* Try to use fine-grained SSD-style locking if available: */ - ci = lock_cluster(si, offset); - /* Otherwise, fall back to traditional, coarse locking: */ - if (!ci) - spin_lock(&si->lock); + BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX); + lockdep_assert_held(&ci->lock); - return ci; -} - -static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, - struct swap_cluster_info *ci) -{ - if (ci) - unlock_cluster(ci); + spin_lock(&si->lock); + if (ci->flags == CLUSTER_FLAG_NONE) + list_add_tail(&ci->list, list); else - spin_unlock(&si->lock); + list_move_tail(&ci->list, list); + spin_unlock(&si->lock); + + if (ci->flags == CLUSTER_FLAG_FRAG) + atomic_long_dec(&si->frag_cluster_nr[ci->order]); + else if (new_flags == CLUSTER_FLAG_FRAG) + atomic_long_inc(&si->frag_cluster_nr[ci->order]); + ci->flags = new_flags; } /* Add a cluster to discard list and schedule it to do discard */ @@ -458,51 +488,98 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si, */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); - - VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); - list_move_tail(&ci->list, &si->discard_clusters); - ci->flags = 0; + VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); + move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { - lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); - - if (ci->flags) - list_move_tail(&ci->list, &si->free_clusters); - else - list_add_tail(&ci->list, &si->free_clusters); - ci->flags = CLUSTER_FLAG_FREE; + move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); ci->order = 0; } +/* + * Isolate and lock the first cluster that is not contented on a list, + * clean its flag before taken off-list. Cluster flag must be in sync + * with list status, so cluster updaters can always know the cluster + * list status without touching si lock. + * + * Note it's possible that all clusters on a list are contented so + * this returns NULL for an non-empty list. + */ +static struct swap_cluster_info *isolate_lock_cluster( + struct swap_info_struct *si, struct list_head *list) +{ + struct swap_cluster_info *ci, *ret = NULL; + + spin_lock(&si->lock); + + if (unlikely(!(si->flags & SWP_WRITEOK))) + goto out; + + list_for_each_entry(ci, list, list) { + if (!spin_trylock(&ci->lock)) + continue; + + /* We may only isolate and clear flags of following lists */ + VM_BUG_ON(!ci->flags); + VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE && + ci->flags != CLUSTER_FLAG_FULL); + + list_del(&ci->list); + ci->flags = CLUSTER_FLAG_NONE; + ret = ci; + break; + } +out: + spin_unlock(&si->lock); + + return ret; +} + /* * Doing discard actually. After a cluster discard is finished, the cluster - * will be added to free cluster list. caller should hold si->lock. -*/ -static void swap_do_scheduled_discard(struct swap_info_struct *si) + * will be added to free cluster list. Discard cluster is a bit special as + * they don't participate in allocation or reclaim, so clusters marked as + * CLUSTER_FLAG_DISCARD must remain off-list or on discard list. + */ +static bool swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *ci; + bool ret = false; unsigned int idx; + spin_lock(&si->lock); while (!list_empty(&si->discard_clusters)) { ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); + /* + * Delete the cluster from list to prepare for discard, but keep + * the CLUSTER_FLAG_DISCARD flag, there could be percpu_cluster + * pointing to it, or ran into by relocate_cluster. + */ list_del(&ci->list); idx = cluster_index(si, ci); spin_unlock(&si->lock); - discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); - spin_lock(&si->lock); spin_lock(&ci->lock); - __free_cluster(si, ci); + /* + * Discard is done, clear its flags as it's off-list, then + * return the cluster to allocation list. + */ + ci->flags = CLUSTER_FLAG_NONE; memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); + __free_cluster(si, ci); spin_unlock(&ci->lock); + ret = true; + spin_lock(&si->lock); } + spin_unlock(&si->lock); + return ret; } static void swap_discard_work(struct work_struct *work) @@ -511,9 +588,7 @@ static void swap_discard_work(struct work_struct *work) si = container_of(work, struct swap_info_struct, discard_work); - spin_lock(&si->lock); swap_do_scheduled_discard(si); - spin_unlock(&si->lock); } static void swap_users_ref_free(struct percpu_ref *ref) @@ -524,15 +599,16 @@ static void swap_users_ref_free(struct percpu_ref *ref) complete(&si->comp); } +/* + * Must be called after freeing if ci->count == 0, moves the cluster to free + * or discard list. + */ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->count != 0); - lockdep_assert_held(&si->lock); + VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); lockdep_assert_held(&ci->lock); - if (ci->flags & CLUSTER_FLAG_FRAG) - si->frag_cluster_nr[ci->order]--; - /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed @@ -547,6 +623,48 @@ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info * __free_cluster(si, ci); } +/* + * Must be called after freeing if ci->count != 0, moves the cluster to + * nonfull list. + */ +static void partial_free_cluster(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER); + lockdep_assert_held(&ci->lock); + + if (ci->flags != CLUSTER_FLAG_NONFULL) + move_cluster(si, ci, &si->nonfull_clusters[ci->order], + CLUSTER_FLAG_NONFULL); +} + +/* + * Must be called after allocation, moves the cluster to full or frag list. + * Note: allocation doesn't acquire si lock, and may drop the ci lock for + * reclaim, so the cluster could be any where when called. + */ +static void relocate_cluster(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + lockdep_assert_held(&ci->lock); + + /* Discard cluster must remain off-list or on discard list */ + if (cluster_is_discard(ci)) + return; + + if (!ci->count) { + free_cluster(si, ci); + } else if (ci->count != SWAPFILE_CLUSTER) { + if (ci->flags != CLUSTER_FLAG_FRAG) + move_cluster(si, ci, &si->frag_clusters[ci->order], + CLUSTER_FLAG_FRAG); + } else { + if (ci->flags != CLUSTER_FLAG_FULL) + move_cluster(si, ci, &si->full_clusters, + CLUSTER_FLAG_FULL); + } +} + /* * The cluster corresponding to page_nr will be used. The cluster will not be * added to free cluster list and its usage counter will be increased by 1. @@ -558,9 +676,6 @@ static void inc_cluster_info_page(struct swap_info_struct *si, unsigned long idx = page_nr / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; - if (!cluster_info) - return; - ci = cluster_info + idx; ci->count++; @@ -568,63 +683,33 @@ static void inc_cluster_info_page(struct swap_info_struct *si, VM_BUG_ON(ci->flags); } -/* - * The cluster ci decreases @nr_pages usage. If the usage counter becomes 0, - * which means no page in the cluster is in use, we can optionally discard - * the cluster and add it to free cluster list. - */ -static void dec_cluster_info_page(struct swap_info_struct *si, - struct swap_cluster_info *ci, int nr_pages) -{ - if (!si->cluster_info) - return; - - VM_BUG_ON(ci->count < nr_pages); - VM_BUG_ON(cluster_is_free(ci)); - lockdep_assert_held(&si->lock); - lockdep_assert_held(&ci->lock); - ci->count -= nr_pages; - - if (!ci->count) { - free_cluster(si, ci); - return; - } - - if (!(ci->flags & CLUSTER_FLAG_NONFULL)) { - VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); - if (ci->flags & CLUSTER_FLAG_FRAG) - si->frag_cluster_nr[ci->order]--; - list_move_tail(&ci->list, &si->nonfull_clusters[ci->order]); - ci->flags = CLUSTER_FLAG_NONFULL; - } -} - static bool cluster_reclaim_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned long end) { unsigned char *map = si->swap_map; - unsigned long offset; + unsigned long offset = start; + int nr_reclaim; spin_unlock(&ci->lock); - spin_unlock(&si->lock); - - for (offset = start; offset < end; offset++) { + do { switch (READ_ONCE(map[offset])) { case 0: - continue; + offset++; + break; case SWAP_HAS_CACHE: - if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT) > 0) - continue; - goto out; + nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); + if (nr_reclaim > 0) + offset += nr_reclaim; + else + goto out; + break; default: goto out; } - } + } while (offset < end); out: - spin_lock(&si->lock); spin_lock(&ci->lock); - /* * Recheck the range no matter reclaim succeeded or not, the slot * could have been be freed while we are not holding the lock. @@ -638,11 +723,11 @@ out: static bool cluster_scan_range(struct swap_info_struct *si, struct swap_cluster_info *ci, - unsigned long start, unsigned int nr_pages) + unsigned long start, unsigned int nr_pages, + bool *need_reclaim) { unsigned long offset, end = start + nr_pages; unsigned char *map = si->swap_map; - bool need_reclaim = false; for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { @@ -651,16 +736,13 @@ static bool cluster_scan_range(struct swap_info_struct *si, case SWAP_HAS_CACHE: if (!vm_swap_full()) return false; - need_reclaim = true; + *need_reclaim = true; continue; default: return false; } } - if (need_reclaim) - return cluster_reclaim_range(si, ci, start, end); - return true; } @@ -670,73 +752,79 @@ static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster { unsigned int nr_pages = 1 << order; + lockdep_assert_held(&ci->lock); + if (!(si->flags & SWP_WRITEOK)) return false; - if (cluster_is_free(ci)) { - if (nr_pages < SWAPFILE_CLUSTER) { - list_move_tail(&ci->list, &si->nonfull_clusters[order]); - ci->flags = CLUSTER_FLAG_NONFULL; - } + /* + * The first allocation in a cluster makes the + * cluster exclusive to this order + */ + if (cluster_is_empty(ci)) ci->order = order; - } memset(si->swap_map + start, usage, nr_pages); - swap_range_alloc(si, start, nr_pages); + swap_range_alloc(si, nr_pages); ci->count += nr_pages; - if (ci->count == SWAPFILE_CLUSTER) { - VM_BUG_ON(!(ci->flags & - (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG))); - if (ci->flags & CLUSTER_FLAG_FRAG) - si->frag_cluster_nr[ci->order]--; - list_move_tail(&ci->list, &si->full_clusters); - ci->flags = CLUSTER_FLAG_FULL; - } - return true; } -static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigned long offset, - unsigned int *foundp, unsigned int order, +/* Try use a new cluster for current CPU and allocate from it. */ +static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, + struct swap_cluster_info *ci, + unsigned long offset, + unsigned int order, unsigned char usage) { - unsigned long start = offset & ~(SWAPFILE_CLUSTER - 1); + unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; + unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER); unsigned long end = min(start + SWAPFILE_CLUSTER, si->max); unsigned int nr_pages = 1 << order; - struct swap_cluster_info *ci; + bool need_reclaim, ret; - if (end < nr_pages) - return SWAP_NEXT_INVALID; - end -= nr_pages; + lockdep_assert_held(&ci->lock); - ci = lock_cluster(si, offset); - if (ci->count + nr_pages > SWAPFILE_CLUSTER) { - offset = SWAP_NEXT_INVALID; - goto done; - } + if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER) + goto out; - while (offset <= end) { - if (cluster_scan_range(si, ci, offset, nr_pages)) { - if (!cluster_alloc_range(si, ci, offset, usage, order)) { - offset = SWAP_NEXT_INVALID; - goto done; - } - *foundp = offset; - if (ci->count == SWAPFILE_CLUSTER) { - offset = SWAP_NEXT_INVALID; - goto done; - } - offset += nr_pages; - break; + for (end -= nr_pages; offset <= end; offset += nr_pages) { + need_reclaim = false; + if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim)) + continue; + if (need_reclaim) { + ret = cluster_reclaim_range(si, ci, offset, offset + nr_pages); + /* + * Reclaim drops ci->lock and cluster could be used + * by another order. Not checking flag as off-list + * cluster has no flag set, and change of list + * won't cause fragmentation. + */ + if (!cluster_is_usable(ci, order)) + goto out; + if (cluster_is_empty(ci)) + offset = start; + /* Reclaim failed but cluster is usable, try next */ + if (!ret) + continue; } + if (!cluster_alloc_range(si, ci, offset, usage, order)) + break; + found = offset; offset += nr_pages; + if (ci->count < SWAPFILE_CLUSTER && offset <= end) + next = offset; + break; } - if (offset > end) - offset = SWAP_NEXT_INVALID; -done: +out: + relocate_cluster(si, ci); unlock_cluster(ci); - return offset; + if (si->flags & SWP_SOLIDSTATE) + __this_cpu_write(si->percpu_cluster->next[order], next); + else + si->global_cluster->next[order] = next; + return found; } /* Return true if reclaimed a whole cluster */ @@ -749,20 +837,19 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) int nr_reclaim; if (force) - to_scan = si->inuse_pages / SWAPFILE_CLUSTER; + to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER; - while (!list_empty(&si->full_clusters)) { - ci = list_first_entry(&si->full_clusters, struct swap_cluster_info, list); - list_move_tail(&ci->list, &si->full_clusters); + while ((ci = isolate_lock_cluster(si, &si->full_clusters))) { offset = cluster_offset(si, ci); end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; - spin_unlock(&si->lock); while (offset < end) { if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { + spin_unlock(&ci->lock); nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); + spin_lock(&ci->lock); if (nr_reclaim) { offset += abs(nr_reclaim); continue; @@ -770,8 +857,8 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) } offset++; } - spin_lock(&si->lock); + unlock_cluster(ci); if (to_scan <= 0) break; } @@ -783,9 +870,7 @@ static void swap_reclaim_work(struct work_struct *work) si = container_of(work, struct swap_info_struct, reclaim_work); - spin_lock(&si->lock); swap_reclaim_full_clusters(si, true); - spin_unlock(&si->lock); } /* @@ -796,29 +881,41 @@ static void swap_reclaim_work(struct work_struct *work) static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order, unsigned char usage) { - struct percpu_cluster *cluster; struct swap_cluster_info *ci; unsigned int offset, found = 0; -new_cluster: - lockdep_assert_held(&si->lock); - cluster = this_cpu_ptr(si->percpu_cluster); - offset = cluster->next[order]; + if (si->flags & SWP_SOLIDSTATE) { + /* Fast path using per CPU cluster */ + local_lock(&si->percpu_cluster->lock); + offset = __this_cpu_read(si->percpu_cluster->next[order]); + } else { + /* Serialize HDD SWAP allocation for each device. */ + spin_lock(&si->global_cluster_lock); + offset = si->global_cluster->next[order]; + } + if (offset) { - offset = alloc_swap_scan_cluster(si, offset, &found, order, usage); + ci = lock_cluster(si, offset); + /* Cluster could have been used by another order */ + if (cluster_is_usable(ci, order)) { + if (cluster_is_empty(ci)) + offset = cluster_offset(si, ci); + found = alloc_swap_scan_cluster(si, ci, offset, + order, usage); + } else { + unlock_cluster(ci); + } if (found) goto done; } - if (!list_empty(&si->free_clusters)) { - ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list); - offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); - /* - * Either we didn't touch the cluster due to swapoff, - * or the allocation must success. - */ - VM_BUG_ON((si->flags & SWP_WRITEOK) && !found); - goto done; +new_cluster: + ci = isolate_lock_cluster(si, &si->free_clusters); + if (ci) { + found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), + order, usage); + if (found) + goto done; } /* Try reclaim from full clusters if free clusters list is drained */ @@ -826,56 +923,42 @@ new_cluster: swap_reclaim_full_clusters(si, false); if (order < PMD_ORDER) { - unsigned int frags = 0; + unsigned int frags = 0, frags_existing; - while (!list_empty(&si->nonfull_clusters[order])) { - ci = list_first_entry(&si->nonfull_clusters[order], - struct swap_cluster_info, list); - list_move_tail(&ci->list, &si->frag_clusters[order]); - ci->flags = CLUSTER_FLAG_FRAG; - si->frag_cluster_nr[order]++; - offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), - &found, order, usage); - frags++; + while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[order]))) { + found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), + order, usage); if (found) - break; + goto done; + /* Clusters failed to allocate are moved to frag_clusters */ + frags++; } - if (!found) { + frags_existing = atomic_long_read(&si->frag_cluster_nr[order]); + while (frags < frags_existing && + (ci = isolate_lock_cluster(si, &si->frag_clusters[order]))) { + atomic_long_dec(&si->frag_cluster_nr[order]); /* - * Nonfull clusters are moved to frag tail if we reached - * here, count them too, don't over scan the frag list. + * Rotate the frag list to iterate, they were all + * failing high order allocation or moved here due to + * per-CPU usage, but they could contain newly released + * reclaimable (eg. lazy-freed swap cache) slots. */ - while (frags < si->frag_cluster_nr[order]) { - ci = list_first_entry(&si->frag_clusters[order], - struct swap_cluster_info, list); - /* - * Rotate the frag list to iterate, they were all failing - * high order allocation or moved here due to per-CPU usage, - * this help keeping usable cluster ahead. - */ - list_move_tail(&ci->list, &si->frag_clusters[order]); - offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), - &found, order, usage); - frags++; - if (found) - break; - } + found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), + order, usage); + if (found) + goto done; + frags++; } } - if (found) - goto done; - - if (!list_empty(&si->discard_clusters)) { - /* - * we don't have free cluster but have some clusters in - * discarding, do discard now and reclaim them, then - * reread cluster_next_cpu since we dropped si->lock - */ - swap_do_scheduled_discard(si); + /* + * We don't have free cluster but have some clusters in + * discarding, do discard now and reclaim them, then + * reread cluster_next_cpu since we dropped si->lock + */ + if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si)) goto new_cluster; - } if (order) goto done; @@ -886,76 +969,153 @@ new_cluster: * Clusters here have at least one usable slots and can't fail order 0 * allocation, but reclaim may drop si->lock and race with another user. */ - while (!list_empty(&si->frag_clusters[o])) { - ci = list_first_entry(&si->frag_clusters[o], - struct swap_cluster_info, list); - offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), - &found, 0, usage); + while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) { + atomic_long_dec(&si->frag_cluster_nr[o]); + found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), + 0, usage); if (found) goto done; } - while (!list_empty(&si->nonfull_clusters[o])) { - ci = list_first_entry(&si->nonfull_clusters[o], - struct swap_cluster_info, list); - offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), - &found, 0, usage); + while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[o]))) { + found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), + 0, usage); if (found) goto done; } } - done: - cluster->next[order] = offset; + if (si->flags & SWP_SOLIDSTATE) + local_unlock(&si->percpu_cluster->lock); + else + spin_unlock(&si->global_cluster_lock); return found; } -static void __del_from_avail_list(struct swap_info_struct *si) +/* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */ +static void del_from_avail_list(struct swap_info_struct *si, bool swapoff) { int nid; + unsigned long pages; + + spin_lock(&swap_avail_lock); + + if (swapoff) { + /* + * Forcefully remove it. Clear the SWP_WRITEOK flags for + * swapoff here so it's synchronized by both si->lock and + * swap_avail_lock, to ensure the result can be seen by + * add_to_avail_list. + */ + lockdep_assert_held(&si->lock); + si->flags &= ~SWP_WRITEOK; + atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); + } else { + /* + * If not called by swapoff, take it off-list only if it's + * full and SWAP_USAGE_OFFLIST_BIT is not set (strictly + * si->inuse_pages == pages), any concurrent slot freeing, + * or device already removed from plist by someone else + * will make this return false. + */ + pages = si->pages; + if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages, + pages | SWAP_USAGE_OFFLIST_BIT)) + goto skip; + } - assert_spin_locked(&si->lock); for_each_node(nid) plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]); -} -static void del_from_avail_list(struct swap_info_struct *si) -{ - spin_lock(&swap_avail_lock); - __del_from_avail_list(si); +skip: spin_unlock(&swap_avail_lock); } -static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, - unsigned int nr_entries) -{ - unsigned int end = offset + nr_entries - 1; - - if (offset == si->lowest_bit) - si->lowest_bit += nr_entries; - if (end == si->highest_bit) - WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); - WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries); - if (si->inuse_pages == si->pages) { - si->lowest_bit = si->max; - si->highest_bit = 0; - del_from_avail_list(si); - - if (si->cluster_info && vm_swap_full()) - schedule_work(&si->reclaim_work); - } -} - -static void add_to_avail_list(struct swap_info_struct *si) +/* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */ +static void add_to_avail_list(struct swap_info_struct *si, bool swapon) { int nid; + long val; + unsigned long pages; spin_lock(&swap_avail_lock); + + /* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */ + if (swapon) { + lockdep_assert_held(&si->lock); + si->flags |= SWP_WRITEOK; + } else { + if (!(READ_ONCE(si->flags) & SWP_WRITEOK)) + goto skip; + } + + if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT)) + goto skip; + + val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); + + /* + * When device is full and device is on the plist, only one updater will + * see (inuse_pages == si->pages) and will call del_from_avail_list. If + * that updater happen to be here, just skip adding. + */ + pages = si->pages; + if (val == pages) { + /* Just like the cmpxchg in del_from_avail_list */ + if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages, + pages | SWAP_USAGE_OFFLIST_BIT)) + goto skip; + } + for_each_node(nid) plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]); + +skip: spin_unlock(&swap_avail_lock); } +/* + * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock + * within each cluster, so the total contribution to the global counter should + * always be positive and cannot exceed the total number of usable slots. + */ +static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries) +{ + long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages); + + /* + * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set, + * remove it from the plist. + */ + if (unlikely(val == si->pages)) { + del_from_avail_list(si, false); + return true; + } + + return false; +} + +static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries) +{ + long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages); + + /* + * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set, + * remove it from the plist. + */ + if (unlikely(val & SWAP_USAGE_OFFLIST_BIT)) + add_to_avail_list(si, false); +} + +static void swap_range_alloc(struct swap_info_struct *si, + unsigned int nr_entries) +{ + if (swap_usage_add(si, nr_entries)) { + if (vm_swap_full()) + schedule_work(&si->reclaim_work); + } +} + static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { @@ -968,18 +1128,11 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset, * Use atomic clear_bit operations only on zeromap instead of non-atomic * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. */ - for (i = 0; i < nr_entries; i++) + for (i = 0; i < nr_entries; i++) { clear_bit(offset + i, si->zeromap); - - if (offset < si->lowest_bit) - si->lowest_bit = offset; - if (end > si->highest_bit) { - bool was_full = !si->highest_bit; - - WRITE_ONCE(si->highest_bit, end); - if (was_full && (si->flags & SWP_WRITEOK)) - add_to_avail_list(si); + zswap_invalidate(swp_entry(si->type, offset + i)); } + if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; @@ -999,50 +1152,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset, */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); - WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); -} - -static void set_cluster_next(struct swap_info_struct *si, unsigned long next) -{ - unsigned long prev; - - if (!(si->flags & SWP_SOLIDSTATE)) { - si->cluster_next = next; - return; - } - - prev = this_cpu_read(*si->cluster_next_cpu); - /* - * Cross the swap address space size aligned trunk, choose - * another trunk randomly to avoid lock contention on swap - * address space if possible. - */ - if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != - (next >> SWAP_ADDRESS_SPACE_SHIFT)) { - /* No free swap slots available */ - if (si->highest_bit <= si->lowest_bit) - return; - next = get_random_u32_inclusive(si->lowest_bit, si->highest_bit); - next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); - next = max_t(unsigned int, next, si->lowest_bit); - } - this_cpu_write(*si->cluster_next_cpu, next); -} - -static bool swap_offset_available_and_locked(struct swap_info_struct *si, - unsigned long offset) -{ - if (data_race(!si->swap_map[offset])) { - spin_lock(&si->lock); - return true; - } - - if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { - spin_lock(&si->lock); - return true; - } - - return false; + swap_usage_sub(si, nr_entries); } static int cluster_alloc_swap(struct swap_info_struct *si, @@ -1051,10 +1161,6 @@ static int cluster_alloc_swap(struct swap_info_struct *si, { int n_ret = 0; - VM_BUG_ON(!si->cluster_info); - - si->flags += SWP_SCANNING; - while (n_ret < nr) { unsigned long offset = cluster_alloc_swap_entry(si, order, usage); @@ -1063,8 +1169,6 @@ static int cluster_alloc_swap(struct swap_info_struct *si, slots[n_ret++] = swp_entry(si->type, offset); } - si->flags -= SWP_SCANNING; - return n_ret; } @@ -1072,13 +1176,7 @@ static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { - unsigned long offset; - unsigned long scan_base; - unsigned long last_in_cluster = 0; - int latency_ration = LATENCY_LIMIT; unsigned int nr_pages = 1 << order; - int n_ret = 0; - bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially @@ -1090,7 +1188,6 @@ static int scan_swap_map_slots(struct swap_info_struct *si, * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ - if (order > 0) { /* * Should not even be attempting large allocations when huge @@ -1103,165 +1200,30 @@ static int scan_swap_map_slots(struct swap_info_struct *si, } /* - * Swapfile is not block device or not using clusters so unable + * Swapfile is not block device so unable * to allocate large entries. */ - if (!(si->flags & SWP_BLKDEV) || !si->cluster_info) + if (!(si->flags & SWP_BLKDEV)) return 0; } - if (si->cluster_info) - return cluster_alloc_swap(si, usage, nr, slots, order); - - si->flags += SWP_SCANNING; - - /* For HDD, sequential access is more important. */ - scan_base = si->cluster_next; - offset = scan_base; - - if (unlikely(!si->cluster_nr--)) { - if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { - si->cluster_nr = SWAPFILE_CLUSTER - 1; - goto checks; - } - - spin_unlock(&si->lock); - - /* - * If seek is expensive, start searching for new cluster from - * start of partition, to minimize the span of allocated swap. - */ - scan_base = offset = si->lowest_bit; - last_in_cluster = offset + SWAPFILE_CLUSTER - 1; - - /* Locate the first empty (unaligned) cluster */ - for (; last_in_cluster <= READ_ONCE(si->highest_bit); offset++) { - if (si->swap_map[offset]) - last_in_cluster = offset + SWAPFILE_CLUSTER; - else if (offset == last_in_cluster) { - spin_lock(&si->lock); - offset -= SWAPFILE_CLUSTER - 1; - si->cluster_next = offset; - si->cluster_nr = SWAPFILE_CLUSTER - 1; - goto checks; - } - if (unlikely(--latency_ration < 0)) { - cond_resched(); - latency_ration = LATENCY_LIMIT; - } - } - - offset = scan_base; - spin_lock(&si->lock); - si->cluster_nr = SWAPFILE_CLUSTER - 1; - } - -checks: - if (!(si->flags & SWP_WRITEOK)) - goto no_page; - if (!si->highest_bit) - goto no_page; - if (offset > si->highest_bit) - scan_base = offset = si->lowest_bit; - - /* reuse swap entry of cache-only swap if not busy. */ - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { - int swap_was_freed; - spin_unlock(&si->lock); - swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); - spin_lock(&si->lock); - /* entry was freed successfully, try to use this again */ - if (swap_was_freed > 0) - goto checks; - goto scan; /* check next one */ - } - - if (si->swap_map[offset]) { - if (!n_ret) - goto scan; - else - goto done; - } - memset(si->swap_map + offset, usage, nr_pages); - - swap_range_alloc(si, offset, nr_pages); - slots[n_ret++] = swp_entry(si->type, offset); - - /* got enough slots or reach max slots? */ - if ((n_ret == nr) || (offset >= si->highest_bit)) - goto done; - - /* search for next available slot */ - - /* time to take a break? */ - if (unlikely(--latency_ration < 0)) { - if (n_ret) - goto done; - spin_unlock(&si->lock); - cond_resched(); - spin_lock(&si->lock); - latency_ration = LATENCY_LIMIT; - } - - if (si->cluster_nr && !si->swap_map[++offset]) { - /* non-ssd case, still more slots in cluster? */ - --si->cluster_nr; - goto checks; - } + return cluster_alloc_swap(si, usage, nr, slots, order); +} +static bool get_swap_device_info(struct swap_info_struct *si) +{ + if (!percpu_ref_tryget_live(&si->users)) + return false; /* - * Even if there's no free clusters available (fragmented), - * try to scan a little more quickly with lock held unless we - * have scanned too many slots already. + * Guarantee the si->users are checked before accessing other + * fields of swap_info_struct, and si->flags (SWP_WRITEOK) is + * up to dated. + * + * Paired with the spin_unlock() after setup_swap_info() in + * enable_swap_info(), and smp_wmb() in swapoff. */ - if (!scanned_many) { - unsigned long scan_limit; - - if (offset < scan_base) - scan_limit = scan_base; - else - scan_limit = si->highest_bit; - for (; offset <= scan_limit && --latency_ration > 0; - offset++) { - if (!si->swap_map[offset]) - goto checks; - } - } - -done: - if (order == 0) - set_cluster_next(si, offset + 1); - si->flags -= SWP_SCANNING; - return n_ret; - -scan: - VM_WARN_ON(order > 0); - spin_unlock(&si->lock); - while (++offset <= READ_ONCE(si->highest_bit)) { - if (unlikely(--latency_ration < 0)) { - cond_resched(); - latency_ration = LATENCY_LIMIT; - scanned_many = true; - } - if (swap_offset_available_and_locked(si, offset)) - goto checks; - } - offset = si->lowest_bit; - while (offset < scan_base) { - if (unlikely(--latency_ration < 0)) { - cond_resched(); - latency_ration = LATENCY_LIMIT; - scanned_many = true; - } - if (swap_offset_available_and_locked(si, offset)) - goto checks; - offset++; - } - spin_lock(&si->lock); - -no_page: - si->flags -= SWP_SCANNING; - return n_ret; + smp_rmb(); + return true; } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order) @@ -1291,32 +1253,15 @@ start_over: /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); - spin_lock(&si->lock); - if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { - spin_lock(&swap_avail_lock); - if (plist_node_empty(&si->avail_lists[node])) { - spin_unlock(&si->lock); - goto nextsi; - } - WARN(!si->highest_bit, - "swap_info %d in list but !highest_bit\n", - si->type); - WARN(!(si->flags & SWP_WRITEOK), - "swap_info %d in list but !SWP_WRITEOK\n", - si->type); - __del_from_avail_list(si); - spin_unlock(&si->lock); - goto nextsi; + if (get_swap_device_info(si)) { + n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, + n_goal, swp_entries, order); + put_swap_device(si); + if (n_ret || size > 1) + goto check_out; } - n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, - n_goal, swp_entries, order); - spin_unlock(&si->lock); - if (n_ret || size > 1) - goto check_out; - cond_resched(); spin_lock(&swap_avail_lock); -nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, @@ -1376,22 +1321,6 @@ out: return NULL; } -static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, - struct swap_info_struct *q) -{ - struct swap_info_struct *p; - - p = _swap_info_get(entry); - - if (p != q) { - if (q != NULL) - spin_unlock(&q->lock); - if (p != NULL) - spin_lock(&p->lock); - } - return p; -} - static unsigned char __swap_entry_free_locked(struct swap_info_struct *si, unsigned long offset, unsigned char usage) @@ -1481,16 +1410,8 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry) si = swp_swap_info(entry); if (!si) goto bad_nofile; - if (!percpu_ref_tryget_live(&si->users)) + if (!get_swap_device_info(si)) goto out; - /* - * Guarantee the si->users are checked before accessing other - * fields of swap_info_struct. - * - * Paired with the spin_unlock() after setup_swap_info() in - * enable_swap_info(). - */ - smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) goto put_out; @@ -1513,11 +1434,11 @@ static unsigned char __swap_entry_free(struct swap_info_struct *si, unsigned long offset = swp_offset(entry); unsigned char usage; - ci = lock_cluster_or_swap_info(si, offset); + ci = lock_cluster(si, offset); usage = __swap_entry_free_locked(si, offset, 1); - unlock_cluster_or_swap_info(si, ci); if (!usage) - free_swap_slot(entry); + swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1); + unlock_cluster(ci); return usage; } @@ -1538,22 +1459,17 @@ static bool __swap_entries_free(struct swap_info_struct *si, if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER) goto fallback; - ci = lock_cluster_or_swap_info(si, offset); + ci = lock_cluster(si, offset); if (!swap_is_last_map(si, offset, nr, &has_cache)) { - unlock_cluster_or_swap_info(si, ci); + unlock_cluster(ci); goto fallback; } for (i = 0; i < nr; i++) WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE); - unlock_cluster_or_swap_info(si, ci); + if (!has_cache) + swap_entry_range_free(si, ci, entry, nr); + unlock_cluster(ci); - if (!has_cache) { - for (i = 0; i < nr; i++) - zswap_invalidate(swp_entry(si->type, offset + i)); - spin_lock(&si->lock); - swap_entry_range_free(si, entry, nr); - spin_unlock(&si->lock); - } return has_cache; fallback: @@ -1573,24 +1489,32 @@ fallback: * Drop the last HAS_CACHE flag of swap entries, caller have to * ensure all entries belong to the same cgroup. */ -static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry, - unsigned int nr_pages) +static void swap_entry_range_free(struct swap_info_struct *si, + struct swap_cluster_info *ci, + swp_entry_t entry, unsigned int nr_pages) { unsigned long offset = swp_offset(entry); unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; - struct swap_cluster_info *ci; - ci = lock_cluster(si, offset); + /* It should never free entries across different clusters */ + VM_BUG_ON(ci != offset_to_cluster(si, offset + nr_pages - 1)); + VM_BUG_ON(cluster_is_empty(ci)); + VM_BUG_ON(ci->count < nr_pages); + + ci->count -= nr_pages; do { VM_BUG_ON(*map != SWAP_HAS_CACHE); *map = 0; } while (++map < map_end); - dec_cluster_info_page(si, ci, nr_pages); - unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, nr_pages); swap_range_free(si, offset, nr_pages); + + if (!ci->count) + free_cluster(si, ci); + else + partial_free_cluster(si, ci); } static void cluster_swap_free_nr(struct swap_info_struct *si, @@ -1598,29 +1522,14 @@ static void cluster_swap_free_nr(struct swap_info_struct *si, unsigned char usage) { struct swap_cluster_info *ci; - DECLARE_BITMAP(to_free, BITS_PER_LONG) = { 0 }; - int i, nr; + unsigned long end = offset + nr_pages; - ci = lock_cluster_or_swap_info(si, offset); - while (nr_pages) { - nr = min(BITS_PER_LONG, nr_pages); - for (i = 0; i < nr; i++) { - if (!__swap_entry_free_locked(si, offset + i, usage)) - bitmap_set(to_free, i, 1); - } - if (!bitmap_empty(to_free, BITS_PER_LONG)) { - unlock_cluster_or_swap_info(si, ci); - for_each_set_bit(i, to_free, BITS_PER_LONG) - free_swap_slot(swp_entry(si->type, offset + i)); - if (nr == nr_pages) - return; - bitmap_clear(to_free, 0, BITS_PER_LONG); - ci = lock_cluster_or_swap_info(si, offset); - } - offset += nr; - nr_pages -= nr; - } - unlock_cluster_or_swap_info(si, ci); + ci = lock_cluster(si, offset); + do { + if (!__swap_entry_free_locked(si, offset, usage)) + swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1); + } while (++offset < end); + unlock_cluster(ci); } /* @@ -1659,59 +1568,35 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry) if (!si) return; - ci = lock_cluster_or_swap_info(si, offset); - if (size > 1 && swap_is_has_cache(si, offset, size)) { - unlock_cluster_or_swap_info(si, ci); - spin_lock(&si->lock); - swap_entry_range_free(si, entry, size); - spin_unlock(&si->lock); - return; - } - for (int i = 0; i < size; i++, entry.val++) { - if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { - unlock_cluster_or_swap_info(si, ci); - free_swap_slot(entry); - if (i == size - 1) - return; - lock_cluster_or_swap_info(si, offset); + ci = lock_cluster(si, offset); + if (swap_is_has_cache(si, offset, size)) + swap_entry_range_free(si, ci, entry, size); + else { + for (int i = 0; i < size; i++, entry.val++) { + if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) + swap_entry_range_free(si, ci, entry, 1); } } - unlock_cluster_or_swap_info(si, ci); -} - -static int swp_entry_cmp(const void *ent1, const void *ent2) -{ - const swp_entry_t *e1 = ent1, *e2 = ent2; - - return (int)swp_type(*e1) - (int)swp_type(*e2); + unlock_cluster(ci); } void swapcache_free_entries(swp_entry_t *entries, int n) { - struct swap_info_struct *p, *prev; int i; + struct swap_cluster_info *ci; + struct swap_info_struct *si = NULL; if (n <= 0) return; - prev = NULL; - p = NULL; - - /* - * Sort swap entries by swap device, so each lock is only taken once. - * nr_swapfiles isn't absolutely correct, but the overhead of sort() is - * so low that it isn't necessary to optimize further. - */ - if (nr_swapfiles > 1) - sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { - p = swap_info_get_cont(entries[i], prev); - if (p) - swap_entry_range_free(p, entries[i], 1); - prev = p; + si = _swap_info_get(entries[i]); + if (si) { + ci = lock_cluster(si, swp_offset(entries[i])); + swap_entry_range_free(si, ci, entries[i], 1); + unlock_cluster(ci); + } } - if (p) - spin_unlock(&p->lock); } int __swap_count(swp_entry_t entry) @@ -1733,9 +1618,9 @@ int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) struct swap_cluster_info *ci; int count; - ci = lock_cluster_or_swap_info(si, offset); + ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); - unlock_cluster_or_swap_info(si, ci); + unlock_cluster(ci); return count; } @@ -1758,7 +1643,7 @@ int swp_swapcount(swp_entry_t entry) offset = swp_offset(entry); - ci = lock_cluster_or_swap_info(si, offset); + ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if (!(count & COUNT_CONTINUED)) @@ -1781,7 +1666,7 @@ int swp_swapcount(swp_entry_t entry) n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: - unlock_cluster_or_swap_info(si, ci); + unlock_cluster(ci); return count; } @@ -1796,8 +1681,8 @@ static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, int i; bool ret = false; - ci = lock_cluster_or_swap_info(si, offset); - if (!ci || nr_pages == 1) { + ci = lock_cluster(si, offset); + if (nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; @@ -1809,7 +1694,7 @@ static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, } } unlock_out: - unlock_cluster_or_swap_info(si, ci); + unlock_cluster(ci); return ret; } @@ -1963,10 +1848,11 @@ swp_entry_t get_swap_page_of_type(int type) goto fail; /* This is called for allocating swap entry, not cache */ - spin_lock(&si->lock); - if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0)) - atomic_long_dec(&nr_swap_pages); - spin_unlock(&si->lock); + if (get_swap_device_info(si)) { + if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0)) + atomic_long_dec(&nr_swap_pages); + put_swap_device(si); + } fail: return entry; } @@ -2057,7 +1943,7 @@ unsigned int count_swap_pages(int type, int free) if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) - n -= sis->inuse_pages; + n -= swap_usage_in_pages(sis); } spin_unlock(&sis->lock); } @@ -2392,7 +2278,7 @@ static int try_to_unuse(unsigned int type) swp_entry_t entry; unsigned int i; - if (!READ_ONCE(si->inuse_pages)) + if (!swap_usage_in_pages(si)) goto success; retry: @@ -2405,7 +2291,7 @@ retry: spin_lock(&mmlist_lock); p = &init_mm.mmlist; - while (READ_ONCE(si->inuse_pages) && + while (swap_usage_in_pages(si) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { @@ -2433,7 +2319,7 @@ retry: mmput(prev_mm); i = 0; - while (READ_ONCE(si->inuse_pages) && + while (swap_usage_in_pages(si) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { @@ -2468,7 +2354,7 @@ retry: * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ - if (READ_ONCE(si->inuse_pages)) { + if (swap_usage_in_pages(si)) { if (!signal_pending(current)) goto retry; return -EINTR; @@ -2495,7 +2381,7 @@ static void drain_mmlist(void) unsigned int type; for (type = 0; type < nr_swapfiles; type++) - if (swap_info[type]->inuse_pages) + if (swap_usage_in_pages(swap_info[type])) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) @@ -2674,7 +2560,6 @@ static void setup_swap_info(struct swap_info_struct *si, int prio, static void _enable_swap_info(struct swap_info_struct *si) { - si->flags |= SWP_WRITEOK; atomic_long_add(si->pages, &nr_swap_pages); total_swap_pages += si->pages; @@ -2691,9 +2576,8 @@ static void _enable_swap_info(struct swap_info_struct *si) */ plist_add(&si->list, &swap_active_head); - /* add to available list iff swap device is not full */ - if (si->highest_bit) - add_to_avail_list(si); + /* Add back to available list */ + add_to_avail_list(si, true); } static void enable_swap_info(struct swap_info_struct *si, int prio, @@ -2742,6 +2626,25 @@ bool has_usable_swap(void) return ret; } +/* + * Called after clearing SWP_WRITEOK, ensures cluster_alloc_range + * see the updated flags, so there will be no more allocations. + */ +static void wait_for_allocation(struct swap_info_struct *si) +{ + unsigned long offset; + unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER); + struct swap_cluster_info *ci; + + BUG_ON(si->flags & SWP_WRITEOK); + + for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) { + ci = lock_cluster(si, offset); + unlock_cluster(ci); + offset += SWAPFILE_CLUSTER; + } +} + SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; @@ -2791,7 +2694,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out_dput; } spin_lock(&p->lock); - del_from_avail_list(p); + del_from_avail_list(p, true); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; @@ -2809,10 +2712,11 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; - p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); + wait_for_allocation(p); + disable_swap_slots_cache_lock(); set_current_oom_origin(); @@ -2855,16 +2759,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_lock(&p->lock); drain_mmlist(); - /* wait for anyone still in scan_swap_map_slots */ - p->highest_bit = 0; /* cuts scans short */ - while (p->flags >= SWP_SCANNING) { - spin_unlock(&p->lock); - spin_unlock(&swap_lock); - schedule_timeout_uninterruptible(1); - spin_lock(&swap_lock); - spin_lock(&p->lock); - } - swap_file = p->swap_file; p->swap_file = NULL; p->max = 0; @@ -2881,8 +2775,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; - free_percpu(p->cluster_next_cpu); - p->cluster_next_cpu = NULL; + kfree(p->global_cluster); + p->global_cluster = NULL; vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); @@ -2992,7 +2886,7 @@ static int swap_show(struct seq_file *swap, void *v) } bytes = K(si->pages); - inuse = K(READ_ONCE(si->inuse_pages)); + inuse = K(swap_usage_in_pages(si)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); @@ -3109,6 +3003,7 @@ static struct swap_info_struct *alloc_swap_info(void) } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); + atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT); init_completion(&p->comp); return p; @@ -3193,10 +3088,6 @@ static unsigned long read_swap_header(struct swap_info_struct *si, return 0; } - si->lowest_bit = 1; - si->cluster_next = 1; - si->cluster_nr = 0; - maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { @@ -3213,7 +3104,6 @@ static unsigned long read_swap_header(struct swap_info_struct *si, if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } - si->highest_bit = maxpages - 1; if (!maxpages) return 0; @@ -3281,7 +3171,6 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, unsigned long maxpages) { unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); - unsigned long col = si->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; struct swap_cluster_info *cluster_info; unsigned long i, j, k, idx; int cpu, err = -ENOMEM; @@ -3293,25 +3182,27 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, for (i = 0; i < nr_clusters; i++) spin_lock_init(&cluster_info[i].lock); - si->cluster_next_cpu = alloc_percpu(unsigned int); - if (!si->cluster_next_cpu) - goto err_free; + if (si->flags & SWP_SOLIDSTATE) { + si->percpu_cluster = alloc_percpu(struct percpu_cluster); + if (!si->percpu_cluster) + goto err_free; - /* Random start position to help with wear leveling */ - for_each_possible_cpu(cpu) - per_cpu(*si->cluster_next_cpu, cpu) = - get_random_u32_inclusive(1, si->highest_bit); + for_each_possible_cpu(cpu) { + struct percpu_cluster *cluster; - si->percpu_cluster = alloc_percpu(struct percpu_cluster); - if (!si->percpu_cluster) - goto err_free; - - for_each_possible_cpu(cpu) { - struct percpu_cluster *cluster; - - cluster = per_cpu_ptr(si->percpu_cluster, cpu); + cluster = per_cpu_ptr(si->percpu_cluster, cpu); + for (i = 0; i < SWAP_NR_ORDERS; i++) + cluster->next[i] = SWAP_ENTRY_INVALID; + local_lock_init(&cluster->lock); + } + } else { + si->global_cluster = kmalloc(sizeof(*si->global_cluster), + GFP_KERNEL); + if (!si->global_cluster) + goto err_free; for (i = 0; i < SWAP_NR_ORDERS; i++) - cluster->next[i] = SWAP_NEXT_INVALID; + si->global_cluster->next[i] = SWAP_ENTRY_INVALID; + spin_lock_init(&si->global_cluster_lock); } /* @@ -3335,7 +3226,7 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&si->nonfull_clusters[i]); INIT_LIST_HEAD(&si->frag_clusters[i]); - si->frag_cluster_nr[i] = 0; + atomic_long_set(&si->frag_cluster_nr[i], 0); } /* @@ -3343,7 +3234,7 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { - j = (k + col) % SWAP_CLUSTER_COLS; + j = k % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { struct swap_cluster_info *ci; idx = i * SWAP_CLUSTER_COLS + j; @@ -3493,18 +3384,18 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (si->bdev && bdev_nonrot(si->bdev)) { si->flags |= SWP_SOLIDSTATE; - - cluster_info = setup_clusters(si, swap_header, maxpages); - if (IS_ERR(cluster_info)) { - error = PTR_ERR(cluster_info); - cluster_info = NULL; - goto bad_swap_unlock_inode; - } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } + cluster_info = setup_clusters(si, swap_header, maxpages); + if (IS_ERR(cluster_info)) { + error = PTR_ERR(cluster_info); + cluster_info = NULL; + goto bad_swap_unlock_inode; + } + if ((swap_flags & SWAP_FLAG_DISCARD) && si->bdev && bdev_max_discard_sectors(si->bdev)) { /* @@ -3585,8 +3476,8 @@ bad_swap_unlock_inode: bad_swap: free_percpu(si->percpu_cluster); si->percpu_cluster = NULL; - free_percpu(si->cluster_next_cpu); - si->cluster_next_cpu = NULL; + kfree(si->global_cluster); + si->global_cluster = NULL; inode = NULL; destroy_swap_extents(si); swap_cgroup_swapoff(si->type); @@ -3623,7 +3514,7 @@ void si_swapinfo(struct sysinfo *val) struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) - nr_to_be_unused += READ_ONCE(si->inuse_pages); + nr_to_be_unused += swap_usage_in_pages(si); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; @@ -3655,7 +3546,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); VM_WARN_ON(usage == 1 && nr > 1); - ci = lock_cluster_or_swap_info(si, offset); + ci = lock_cluster(si, offset); err = 0; for (i = 0; i < nr; i++) { @@ -3710,7 +3601,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) } unlock_out: - unlock_cluster_or_swap_info(si, ci); + unlock_cluster(ci); return err; } @@ -3819,7 +3710,6 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) */ goto outer; } - spin_lock(&si->lock); offset = swp_offset(entry); @@ -3884,7 +3774,6 @@ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); - spin_unlock(&si->lock); put_swap_device(si); outer: if (page) diff --git a/mm/truncate.c b/mm/truncate.c index 7c304d2f0052..e2e115adfbc5 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -525,6 +525,15 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, } EXPORT_SYMBOL(invalidate_mapping_pages); +static int folio_launder(struct address_space *mapping, struct folio *folio) +{ + if (!folio_test_dirty(folio)) + return 0; + if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL) + return 0; + return mapping->a_ops->launder_folio(folio); +} + /* * This is like mapping_evict_folio(), except it ignores the folio's * refcount. We do this because invalidate_inode_pages2() needs stronger @@ -532,14 +541,26 @@ EXPORT_SYMBOL(invalidate_mapping_pages); * shrink_folio_list() has a temp ref on them, or because they're transiently * sitting in the folio_add_lru() caches. */ -static int invalidate_complete_folio2(struct address_space *mapping, - struct folio *folio) +int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, + gfp_t gfp) { - if (folio->mapping != mapping) - return 0; + int ret; - if (!filemap_release_folio(folio, GFP_KERNEL)) + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + + if (folio_test_dirty(folio)) return 0; + if (folio_mapped(folio)) + unmap_mapping_folio(folio); + BUG_ON(folio_mapped(folio)); + + ret = folio_launder(mapping, folio); + if (ret) + return ret; + if (folio->mapping != mapping) + return -EBUSY; + if (!filemap_release_folio(folio, gfp)) + return -EBUSY; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); @@ -558,16 +579,7 @@ static int invalidate_complete_folio2(struct address_space *mapping, failed: xa_unlock_irq(&mapping->i_pages); spin_unlock(&mapping->host->i_lock); - return 0; -} - -static int folio_launder(struct address_space *mapping, struct folio *folio) -{ - if (!folio_test_dirty(folio)) - return 0; - if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL) - return 0; - return mapping->a_ops->launder_folio(folio); + return -EBUSY; } /** @@ -631,16 +643,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, } VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio); folio_wait_writeback(folio); - - if (folio_mapped(folio)) - unmap_mapping_folio(folio); - BUG_ON(folio_mapped(folio)); - - ret2 = folio_launder(mapping, folio); - if (ret2 == 0) { - if (!invalidate_complete_folio2(mapping, folio)) - ret2 = -EBUSY; - } + ret2 = folio_unmap_invalidate(mapping, folio, GFP_KERNEL); if (ret2 < 0) ret = ret2; folio_unlock(folio); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 60a0be33766f..af3dfc3633db 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1020,6 +1020,14 @@ void double_pt_unlock(spinlock_t *ptl1, __release(ptl2); } +static inline bool is_pte_pages_stable(pte_t *dst_pte, pte_t *src_pte, + pte_t orig_dst_pte, pte_t orig_src_pte, + pmd_t *dst_pmd, pmd_t dst_pmdval) +{ + return pte_same(ptep_get(src_pte), orig_src_pte) && + pte_same(ptep_get(dst_pte), orig_dst_pte) && + pmd_same(dst_pmdval, pmdp_get_lockless(dst_pmd)); +} static int move_present_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, @@ -1027,6 +1035,7 @@ static int move_present_pte(struct mm_struct *mm, unsigned long dst_addr, unsigned long src_addr, pte_t *dst_pte, pte_t *src_pte, pte_t orig_dst_pte, pte_t orig_src_pte, + pmd_t *dst_pmd, pmd_t dst_pmdval, spinlock_t *dst_ptl, spinlock_t *src_ptl, struct folio *src_folio) { @@ -1034,8 +1043,8 @@ static int move_present_pte(struct mm_struct *mm, double_pt_lock(dst_ptl, src_ptl); - if (!pte_same(ptep_get(src_pte), orig_src_pte) || - !pte_same(ptep_get(dst_pte), orig_dst_pte)) { + if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte, + dst_pmd, dst_pmdval)) { err = -EAGAIN; goto out; } @@ -1071,6 +1080,7 @@ static int move_swap_pte(struct mm_struct *mm, unsigned long dst_addr, unsigned long src_addr, pte_t *dst_pte, pte_t *src_pte, pte_t orig_dst_pte, pte_t orig_src_pte, + pmd_t *dst_pmd, pmd_t dst_pmdval, spinlock_t *dst_ptl, spinlock_t *src_ptl) { if (!pte_swp_exclusive(orig_src_pte)) @@ -1078,8 +1088,8 @@ static int move_swap_pte(struct mm_struct *mm, double_pt_lock(dst_ptl, src_ptl); - if (!pte_same(ptep_get(src_pte), orig_src_pte) || - !pte_same(ptep_get(dst_pte), orig_dst_pte)) { + if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte, + dst_pmd, dst_pmdval)) { double_pt_unlock(dst_ptl, src_ptl); return -EAGAIN; } @@ -1097,13 +1107,14 @@ static int move_zeropage_pte(struct mm_struct *mm, unsigned long dst_addr, unsigned long src_addr, pte_t *dst_pte, pte_t *src_pte, pte_t orig_dst_pte, pte_t orig_src_pte, + pmd_t *dst_pmd, pmd_t dst_pmdval, spinlock_t *dst_ptl, spinlock_t *src_ptl) { pte_t zero_pte; double_pt_lock(dst_ptl, src_ptl); - if (!pte_same(ptep_get(src_pte), orig_src_pte) || - !pte_same(ptep_get(dst_pte), orig_dst_pte)) { + if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte, + dst_pmd, dst_pmdval)) { double_pt_unlock(dst_ptl, src_ptl); return -EAGAIN; } @@ -1136,6 +1147,7 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pte_t *src_pte = NULL; pte_t *dst_pte = NULL; pmd_t dummy_pmdval; + pmd_t dst_pmdval; struct folio *src_folio = NULL; struct anon_vma *src_anon_vma = NULL; struct mmu_notifier_range range; @@ -1148,11 +1160,11 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, retry: /* * Use the maywrite version to indicate that dst_pte will be modified, - * but since we will use pte_same() to detect the change of the pte - * entry, there is no need to get pmdval, so just pass a dummy variable - * to it. + * since dst_pte needs to be none, the subsequent pte_same() check + * cannot prevent the dst_pte page from being freed concurrently, so we + * also need to abtain dst_pmdval and recheck pmd_same() later. */ - dst_pte = pte_offset_map_rw_nolock(mm, dst_pmd, dst_addr, &dummy_pmdval, + dst_pte = pte_offset_map_rw_nolock(mm, dst_pmd, dst_addr, &dst_pmdval, &dst_ptl); /* Retry if a huge pmd materialized from under us */ @@ -1161,7 +1173,11 @@ retry: goto out; } - /* same as dst_pte */ + /* + * Unlike dst_pte, the subsequent pte_same() check can ensure the + * stability of the src_pte page, so there is no need to get pmdval, + * just pass a dummy variable to it. + */ src_pte = pte_offset_map_rw_nolock(mm, src_pmd, src_addr, &dummy_pmdval, &src_ptl); @@ -1177,8 +1193,8 @@ retry: } /* Sanity checks before the operation */ - if (WARN_ON_ONCE(pmd_none(*dst_pmd)) || WARN_ON_ONCE(pmd_none(*src_pmd)) || - WARN_ON_ONCE(pmd_trans_huge(*dst_pmd)) || WARN_ON_ONCE(pmd_trans_huge(*src_pmd))) { + if (pmd_none(*dst_pmd) || pmd_none(*src_pmd) || + pmd_trans_huge(*dst_pmd) || pmd_trans_huge(*src_pmd)) { err = -EINVAL; goto out; } @@ -1213,7 +1229,7 @@ retry: err = move_zeropage_pte(mm, dst_vma, src_vma, dst_addr, src_addr, dst_pte, src_pte, orig_dst_pte, orig_src_pte, - dst_ptl, src_ptl); + dst_pmd, dst_pmdval, dst_ptl, src_ptl); goto out; } @@ -1303,8 +1319,8 @@ retry: err = move_present_pte(mm, dst_vma, src_vma, dst_addr, src_addr, dst_pte, src_pte, - orig_dst_pte, orig_src_pte, - dst_ptl, src_ptl, src_folio); + orig_dst_pte, orig_src_pte, dst_pmd, + dst_pmdval, dst_ptl, src_ptl, src_folio); } else { entry = pte_to_swp_entry(orig_src_pte); if (non_swap_entry(entry)) { @@ -1319,10 +1335,9 @@ retry: goto out; } - err = move_swap_pte(mm, dst_addr, src_addr, - dst_pte, src_pte, - orig_dst_pte, orig_src_pte, - dst_ptl, src_ptl); + err = move_swap_pte(mm, dst_addr, src_addr, dst_pte, src_pte, + orig_dst_pte, orig_src_pte, dst_pmd, + dst_pmdval, dst_ptl, src_ptl); } out: diff --git a/mm/util.c b/mm/util.c index c1c3b06ab4f9..b6b9684a1438 100644 --- a/mm/util.c +++ b/mm/util.c @@ -297,12 +297,7 @@ void *memdup_user_nul(const void __user *src, size_t len) { char *p; - /* - * Always use GFP_KERNEL, since copy_from_user() can sleep and - * cause pagefault, which makes it pointless to use GFP_NOFS - * or GFP_ATOMIC. - */ - p = kmalloc_track_caller(len + 1, GFP_KERNEL); + p = kmem_buckets_alloc_track_caller(user_buckets, len + 1, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -587,6 +582,23 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, return ret; } +/* + * Perform a userland memory mapping into the current process address space. See + * the comment for do_mmap() for more details on this operation in general. + * + * This differs from do_mmap() in that: + * + * a. An offset parameter is provided rather than pgoff, which is both checked + * for overflow and page alignment. + * b. mmap locking is performed on the caller's behalf. + * c. Userfaultfd unmap events and memory population are handled. + * + * This means that this function performs essentially the same work as if + * userland were invoking mmap (2). + * + * Returns either an error, or the address at which the requested mapping has + * been performed. + */ unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long offset) diff --git a/mm/vma.c b/mm/vma.c index 8e31b7e25aeb..af1d549b179c 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -202,6 +202,38 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma, flush_dcache_mmap_unlock(mapping); } +/* + * vma has some anon_vma assigned, and is already inserted on that + * anon_vma's interval trees. + * + * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the + * vma must be removed from the anon_vma's interval trees using + * anon_vma_interval_tree_pre_update_vma(). + * + * After the update, the vma will be reinserted using + * anon_vma_interval_tree_post_update_vma(). + * + * The entire update must be protected by exclusive mmap_lock and by + * the root anon_vma's mutex. + */ +static void +anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc; + + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); +} + +static void +anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc; + + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); +} + /* * vma_prepare() - Helper function for handling locking VMAs prior to altering * @vp: The initialized vma_prepare struct @@ -398,7 +430,6 @@ void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; - lru_add_drain(); tlb_gather_mmu(&tlb, mm); update_hiwater_rss(mm); unmap_vmas(&tlb, mas, vma, vma->vm_start, vma->vm_end, vma->vm_end, @@ -415,8 +446,9 @@ void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, * has already been checked or doesn't make sense to fail. * VMA Iterator will point to the original VMA. */ -static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long addr, int new_below) +static __must_check int +__split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, int new_below) { struct vma_prepare vp; struct vm_area_struct *new; @@ -510,38 +542,6 @@ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, return __split_vma(vmi, vma, addr, new_below); } -/* - * vma has some anon_vma assigned, and is already inserted on that - * anon_vma's interval trees. - * - * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the - * vma must be removed from the anon_vma's interval trees using - * anon_vma_interval_tree_pre_update_vma(). - * - * After the update, the vma will be reinserted using - * anon_vma_interval_tree_post_update_vma(). - * - * The entire update must be protected by exclusive mmap_lock and by - * the root anon_vma's mutex. - */ -void -anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) -{ - struct anon_vma_chain *avc; - - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); -} - -void -anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) -{ - struct anon_vma_chain *avc; - - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); -} - /* * dup_anon_vma() - Helper function to duplicate anon_vma * @dst: The destination VMA @@ -710,7 +710,8 @@ static bool can_merge_remove_vma(struct vm_area_struct *vma) * - The caller must hold a WRITE lock on the mm_struct->mmap_lock. * - vmi must be positioned within [@vmg->vma->vm_start, @vmg->vma->vm_end). */ -static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct *vmg) +static __must_check struct vm_area_struct *vma_merge_existing_range( + struct vma_merge_struct *vmg) { struct vm_area_struct *vma = vmg->vma; struct vm_area_struct *prev = vmg->prev; @@ -728,19 +729,20 @@ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct * bool expanded; mmap_assert_write_locked(vmg->mm); - VM_WARN_ON(!vma); /* We are modifying a VMA, so caller must specify. */ - VM_WARN_ON(vmg->next); /* We set this. */ - VM_WARN_ON(prev && start <= prev->vm_start); - VM_WARN_ON(start >= end); + VM_WARN_ON_VMG(!vma, vmg); /* We are modifying a VMA, so caller must specify. */ + VM_WARN_ON_VMG(vmg->next, vmg); /* We set this. */ + VM_WARN_ON_VMG(prev && start <= prev->vm_start, vmg); + VM_WARN_ON_VMG(start >= end, vmg); + /* * If vma == prev, then we are offset into a VMA. Otherwise, if we are * not, we must span a portion of the VMA. */ - VM_WARN_ON(vma && ((vma != prev && vmg->start != vma->vm_start) || - vmg->end > vma->vm_end)); + VM_WARN_ON_VMG(vma && ((vma != prev && vmg->start != vma->vm_start) || + vmg->end > vma->vm_end), vmg); /* The vmi must be positioned within vmg->vma. */ - VM_WARN_ON(vma && !(vma_iter_addr(vmg->vmi) >= vma->vm_start && - vma_iter_addr(vmg->vmi) < vma->vm_end)); + VM_WARN_ON_VMG(vma && !(vma_iter_addr(vmg->vmi) >= vma->vm_start && + vma_iter_addr(vmg->vmi) < vma->vm_end), vmg); vmg->state = VMA_MERGE_NOMERGE; @@ -857,9 +859,9 @@ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct * pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start); - VM_WARN_ON(!merge_right); + VM_WARN_ON_VMG(!merge_right, vmg); /* If we are offset into a VMA, then prev must be vma. */ - VM_WARN_ON(vmg->start > vma->vm_start && prev && vma != prev); + VM_WARN_ON_VMG(vmg->start > vma->vm_start && prev && vma != prev, vmg); if (merge_will_delete_vma) { vmg->vma = next; @@ -971,9 +973,9 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) bool just_expand = vmg->merge_flags & VMG_FLAG_JUST_EXPAND; mmap_assert_write_locked(vmg->mm); - VM_WARN_ON(vmg->vma); + VM_WARN_ON_VMG(vmg->vma, vmg); /* vmi must point at or before the gap. */ - VM_WARN_ON(vma_iter_addr(vmg->vmi) > end); + VM_WARN_ON_VMG(vma_iter_addr(vmg->vmi) > end, vmg); vmg->state = VMA_MERGE_NOMERGE; @@ -1055,7 +1057,7 @@ int vma_expand(struct vma_merge_struct *vmg) remove_next = true; /* This should already have been checked by this point. */ - VM_WARN_ON(!can_merge_remove_vma(next)); + VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg); vma_start_write(next); ret = dup_anon_vma(vma, next, &anon_dup); if (ret) @@ -1063,10 +1065,10 @@ int vma_expand(struct vma_merge_struct *vmg) } /* Not merging but overwriting any part of next is not handled. */ - VM_WARN_ON(next && !remove_next && - next != vma && vmg->end > next->vm_start); + VM_WARN_ON_VMG(next && !remove_next && + next != vma && vmg->end > next->vm_start, vmg); /* Only handles expanding */ - VM_WARN_ON(vma->vm_start < vmg->start || vma->vm_end > vmg->end); + VM_WARN_ON_VMG(vma->vm_start < vmg->start || vma->vm_end > vmg->end, vmg); if (commit_merge(vmg, NULL, remove_next ? next : NULL, NULL, 0, true)) goto nomem; @@ -1130,7 +1132,6 @@ static inline void vms_clear_ptes(struct vma_munmap_struct *vms, * were isolated before we downgraded mmap_lock. */ mas_set(mas_detach, 1); - lru_add_drain(); tlb_gather_mmu(&tlb, vms->vma->vm_mm); update_hiwater_rss(vms->vma->vm_mm); unmap_vmas(&tlb, mas_detach, vms->vma, vms->start, vms->end, @@ -2430,7 +2431,7 @@ static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma) vma_set_page_prot(vma); } -unsigned long __mmap_region(struct file *file, unsigned long addr, +static unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { @@ -2460,10 +2461,13 @@ unsigned long __mmap_region(struct file *file, unsigned long addr, /* If flags changed, we might be able to merge, so try again. */ if (map.retry_merge) { + struct vm_area_struct *merged; VMG_MMAP_STATE(vmg, &map, vma); vma_iter_config(map.vmi, map.addr, map.end); - vma_merge_existing_range(&vmg); + merged = vma_merge_existing_range(&vmg); + if (merged) + vma = merged; } __mmap_complete(&map, vma); @@ -2478,3 +2482,476 @@ abort_munmap: vms_abort_munmap_vmas(&map.vms, &map.mas_detach); return error; } + +/** + * mmap_region() - Actually perform the userland mapping of a VMA into + * current->mm with known, aligned and overflow-checked @addr and @len, and + * correctly determined VMA flags @vm_flags and page offset @pgoff. + * + * This is an internal memory management function, and should not be used + * directly. + * + * The caller must write-lock current->mm->mmap_lock. + * + * @file: If a file-backed mapping, a pointer to the struct file describing the + * file to be mapped, otherwise NULL. + * @addr: The page-aligned address at which to perform the mapping. + * @len: The page-aligned, non-zero, length of the mapping. + * @vm_flags: The VMA flags which should be applied to the mapping. + * @pgoff: If @file is specified, the page offset into the file, if not then + * the virtual page offset in memory of the anonymous mapping. + * @uf: Optionally, a pointer to a list head used for tracking userfaultfd unmap + * events. + * + * Returns: Either an error, or the address at which the requested mapping has + * been performed. + */ +unsigned long mmap_region(struct file *file, unsigned long addr, + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) +{ + unsigned long ret; + bool writable_file_mapping = false; + + mmap_assert_write_locked(current->mm); + + /* Check to see if MDWE is applicable. */ + if (map_deny_write_exec(vm_flags, vm_flags)) + return -EACCES; + + /* Allow architectures to sanity-check the vm_flags. */ + if (!arch_validate_flags(vm_flags)) + return -EINVAL; + + /* Map writable and ensure this isn't a sealed memfd. */ + if (file && is_shared_maywrite(vm_flags)) { + int error = mapping_map_writable(file->f_mapping); + + if (error) + return error; + writable_file_mapping = true; + } + + ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf); + + /* Clear our write mapping regardless of error. */ + if (writable_file_mapping) + mapping_unmap_writable(file->f_mapping); + + validate_mm(current->mm); + return ret; +} + +/* + * do_brk_flags() - Increase the brk vma if the flags match. + * @vmi: The vma iterator + * @addr: The start address + * @len: The length of the increase + * @vma: The vma, + * @flags: The VMA Flags + * + * Extend the brk VMA from addr to addr + len. If the VMA is NULL or the flags + * do not match then create a new anonymous VMA. Eventually we may be able to + * do some brk-specific accounting here. + */ +int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, unsigned long len, unsigned long flags) +{ + struct mm_struct *mm = current->mm; + + /* + * Check against address space limits by the changed size + * Note: This happens *after* clearing old mappings in some code paths. + */ + flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; + if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) + return -ENOMEM; + + if (mm->map_count > sysctl_max_map_count) + return -ENOMEM; + + if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) + return -ENOMEM; + + /* + * Expand the existing vma if possible; Note that singular lists do not + * occur after forking, so the expand will only happen on new VMAs. + */ + if (vma && vma->vm_end == addr) { + VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr)); + + vmg.prev = vma; + /* vmi is positioned at prev, which this mode expects. */ + vmg.merge_flags = VMG_FLAG_JUST_EXPAND; + + if (vma_merge_new_range(&vmg)) + goto out; + else if (vmg_nomem(&vmg)) + goto unacct_fail; + } + + if (vma) + vma_iter_next_range(vmi); + /* create a vma struct for an anonymous mapping */ + vma = vm_area_alloc(mm); + if (!vma) + goto unacct_fail; + + vma_set_anonymous(vma); + vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT); + vm_flags_init(vma, flags); + vma->vm_page_prot = vm_get_page_prot(flags); + vma_start_write(vma); + if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL)) + goto mas_store_fail; + + mm->map_count++; + validate_mm(mm); + ksm_add_vma(vma); +out: + perf_event_mmap(vma); + mm->total_vm += len >> PAGE_SHIFT; + mm->data_vm += len >> PAGE_SHIFT; + if (flags & VM_LOCKED) + mm->locked_vm += (len >> PAGE_SHIFT); + vm_flags_set(vma, VM_SOFTDIRTY); + return 0; + +mas_store_fail: + vm_area_free(vma); +unacct_fail: + vm_unacct_memory(len >> PAGE_SHIFT); + return -ENOMEM; +} + +/** + * unmapped_area() - Find an area between the low_limit and the high_limit with + * the correct alignment and offset, all from @info. Note: current->mm is used + * for the search. + * + * @info: The unmapped area information including the range [low_limit - + * high_limit), the alignment offset and mask. + * + * Return: A memory address or -ENOMEM. + */ +unsigned long unmapped_area(struct vm_unmapped_area_info *info) +{ + unsigned long length, gap; + unsigned long low_limit, high_limit; + struct vm_area_struct *tmp; + VMA_ITERATOR(vmi, current->mm, 0); + + /* Adjust search length to account for worst case alignment overhead */ + length = info->length + info->align_mask + info->start_gap; + if (length < info->length) + return -ENOMEM; + + low_limit = info->low_limit; + if (low_limit < mmap_min_addr) + low_limit = mmap_min_addr; + high_limit = info->high_limit; +retry: + if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length)) + return -ENOMEM; + + /* + * Adjust for the gap first so it doesn't interfere with the + * later alignment. The first step is the minimum needed to + * fulill the start gap, the next steps is the minimum to align + * that. It is the minimum needed to fulill both. + */ + gap = vma_iter_addr(&vmi) + info->start_gap; + gap += (info->align_offset - gap) & info->align_mask; + tmp = vma_next(&vmi); + if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ + if (vm_start_gap(tmp) < gap + length - 1) { + low_limit = tmp->vm_end; + vma_iter_reset(&vmi); + goto retry; + } + } else { + tmp = vma_prev(&vmi); + if (tmp && vm_end_gap(tmp) > gap) { + low_limit = vm_end_gap(tmp); + vma_iter_reset(&vmi); + goto retry; + } + } + + return gap; +} + +/** + * unmapped_area_topdown() - Find an area between the low_limit and the + * high_limit with the correct alignment and offset at the highest available + * address, all from @info. Note: current->mm is used for the search. + * + * @info: The unmapped area information including the range [low_limit - + * high_limit), the alignment offset and mask. + * + * Return: A memory address or -ENOMEM. + */ +unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) +{ + unsigned long length, gap, gap_end; + unsigned long low_limit, high_limit; + struct vm_area_struct *tmp; + VMA_ITERATOR(vmi, current->mm, 0); + + /* Adjust search length to account for worst case alignment overhead */ + length = info->length + info->align_mask + info->start_gap; + if (length < info->length) + return -ENOMEM; + + low_limit = info->low_limit; + if (low_limit < mmap_min_addr) + low_limit = mmap_min_addr; + high_limit = info->high_limit; +retry: + if (vma_iter_area_highest(&vmi, low_limit, high_limit, length)) + return -ENOMEM; + + gap = vma_iter_end(&vmi) - info->length; + gap -= (gap - info->align_offset) & info->align_mask; + gap_end = vma_iter_end(&vmi); + tmp = vma_next(&vmi); + if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ + if (vm_start_gap(tmp) < gap_end) { + high_limit = vm_start_gap(tmp); + vma_iter_reset(&vmi); + goto retry; + } + } else { + tmp = vma_prev(&vmi); + if (tmp && vm_end_gap(tmp) > gap) { + high_limit = tmp->vm_start; + vma_iter_reset(&vmi); + goto retry; + } + } + + return gap; +} + +/* + * Verify that the stack growth is acceptable and + * update accounting. This is shared with both the + * grow-up and grow-down cases. + */ +static int acct_stack_growth(struct vm_area_struct *vma, + unsigned long size, unsigned long grow) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long new_start; + + /* address space limit tests */ + if (!may_expand_vm(mm, vma->vm_flags, grow)) + return -ENOMEM; + + /* Stack limit test */ + if (size > rlimit(RLIMIT_STACK)) + return -ENOMEM; + + /* mlock limit tests */ + if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT)) + return -ENOMEM; + + /* Check to ensure the stack will not grow into a hugetlb-only region */ + new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : + vma->vm_end - size; + if (is_hugepage_only_range(vma->vm_mm, new_start, size)) + return -EFAULT; + + /* + * Overcommit.. This must be the final test, as it will + * update security statistics. + */ + if (security_vm_enough_memory_mm(mm, grow)) + return -ENOMEM; + + return 0; +} + +#if defined(CONFIG_STACK_GROWSUP) +/* + * PA-RISC uses this for its stack. + * vma is the last one with address > vma->vm_end. Have to extend vma. + */ +int expand_upwards(struct vm_area_struct *vma, unsigned long address) +{ + struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *next; + unsigned long gap_addr; + int error = 0; + VMA_ITERATOR(vmi, mm, vma->vm_start); + + if (!(vma->vm_flags & VM_GROWSUP)) + return -EFAULT; + + mmap_assert_write_locked(mm); + + /* Guard against exceeding limits of the address space. */ + address &= PAGE_MASK; + if (address >= (TASK_SIZE & PAGE_MASK)) + return -ENOMEM; + address += PAGE_SIZE; + + /* Enforce stack_guard_gap */ + gap_addr = address + stack_guard_gap; + + /* Guard against overflow */ + if (gap_addr < address || gap_addr > TASK_SIZE) + gap_addr = TASK_SIZE; + + next = find_vma_intersection(mm, vma->vm_end, gap_addr); + if (next && vma_is_accessible(next)) { + if (!(next->vm_flags & VM_GROWSUP)) + return -ENOMEM; + /* Check that both stack segments have the same anon_vma? */ + } + + if (next) + vma_iter_prev_range_limit(&vmi, address); + + vma_iter_config(&vmi, vma->vm_start, address); + if (vma_iter_prealloc(&vmi, vma)) + return -ENOMEM; + + /* We must make sure the anon_vma is allocated. */ + if (unlikely(anon_vma_prepare(vma))) { + vma_iter_free(&vmi); + return -ENOMEM; + } + + /* Lock the VMA before expanding to prevent concurrent page faults */ + vma_start_write(vma); + /* We update the anon VMA tree. */ + anon_vma_lock_write(vma->anon_vma); + + /* Somebody else might have raced and expanded it already */ + if (address > vma->vm_end) { + unsigned long size, grow; + + size = address - vma->vm_start; + grow = (address - vma->vm_end) >> PAGE_SHIFT; + + error = -ENOMEM; + if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { + error = acct_stack_growth(vma, size, grow); + if (!error) { + if (vma->vm_flags & VM_LOCKED) + mm->locked_vm += grow; + vm_stat_account(mm, vma->vm_flags, grow); + anon_vma_interval_tree_pre_update_vma(vma); + vma->vm_end = address; + /* Overwrite old entry in mtree. */ + vma_iter_store(&vmi, vma); + anon_vma_interval_tree_post_update_vma(vma); + + perf_event_mmap(vma); + } + } + } + anon_vma_unlock_write(vma->anon_vma); + vma_iter_free(&vmi); + validate_mm(mm); + return error; +} +#endif /* CONFIG_STACK_GROWSUP */ + +/* + * vma is the first one with address < vma->vm_start. Have to extend vma. + * mmap_lock held for writing. + */ +int expand_downwards(struct vm_area_struct *vma, unsigned long address) +{ + struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *prev; + int error = 0; + VMA_ITERATOR(vmi, mm, vma->vm_start); + + if (!(vma->vm_flags & VM_GROWSDOWN)) + return -EFAULT; + + mmap_assert_write_locked(mm); + + address &= PAGE_MASK; + if (address < mmap_min_addr || address < FIRST_USER_ADDRESS) + return -EPERM; + + /* Enforce stack_guard_gap */ + prev = vma_prev(&vmi); + /* Check that both stack segments have the same anon_vma? */ + if (prev) { + if (!(prev->vm_flags & VM_GROWSDOWN) && + vma_is_accessible(prev) && + (address - prev->vm_end < stack_guard_gap)) + return -ENOMEM; + } + + if (prev) + vma_iter_next_range_limit(&vmi, vma->vm_start); + + vma_iter_config(&vmi, address, vma->vm_end); + if (vma_iter_prealloc(&vmi, vma)) + return -ENOMEM; + + /* We must make sure the anon_vma is allocated. */ + if (unlikely(anon_vma_prepare(vma))) { + vma_iter_free(&vmi); + return -ENOMEM; + } + + /* Lock the VMA before expanding to prevent concurrent page faults */ + vma_start_write(vma); + /* We update the anon VMA tree. */ + anon_vma_lock_write(vma->anon_vma); + + /* Somebody else might have raced and expanded it already */ + if (address < vma->vm_start) { + unsigned long size, grow; + + size = vma->vm_end - address; + grow = (vma->vm_start - address) >> PAGE_SHIFT; + + error = -ENOMEM; + if (grow <= vma->vm_pgoff) { + error = acct_stack_growth(vma, size, grow); + if (!error) { + if (vma->vm_flags & VM_LOCKED) + mm->locked_vm += grow; + vm_stat_account(mm, vma->vm_flags, grow); + anon_vma_interval_tree_pre_update_vma(vma); + vma->vm_start = address; + vma->vm_pgoff -= grow; + /* Overwrite old entry in mtree. */ + vma_iter_store(&vmi, vma); + anon_vma_interval_tree_post_update_vma(vma); + + perf_event_mmap(vma); + } + } + } + anon_vma_unlock_write(vma->anon_vma); + vma_iter_free(&vmi); + validate_mm(mm); + return error; +} + +int __vm_munmap(unsigned long start, size_t len, bool unlock) +{ + int ret; + struct mm_struct *mm = current->mm; + LIST_HEAD(uf); + VMA_ITERATOR(vmi, mm, start); + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = do_vmi_munmap(&vmi, mm, start, len, &uf, unlock); + if (ret || !unlock) + mmap_write_unlock(mm); + + userfaultfd_unmap_complete(mm, &uf); + return ret; +} diff --git a/mm/vma.h b/mm/vma.h index 388d34748674..a2e8710b8c47 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -139,15 +139,10 @@ void validate_mm(struct mm_struct *mm); #define validate_mm(mm) do { } while (0) #endif -/* Required for expand_downwards(). */ -void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma); - -/* Required for expand_downwards(). */ -void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma); - -int vma_expand(struct vma_merge_struct *vmg); -int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, pgoff_t pgoff); +__must_check int vma_expand(struct vma_merge_struct *vmg); +__must_check int vma_shrink(struct vma_iterator *vmi, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff); static inline int vma_iter_store_gfp(struct vma_iterator *vmi, struct vm_area_struct *vma, gfp_t gfp) @@ -180,13 +175,14 @@ void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next); /* We are about to modify the VMA's flags. */ -struct vm_area_struct *vma_modify_flags(struct vma_iterator *vmi, +__must_check struct vm_area_struct +*vma_modify_flags(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags); /* We are about to modify the VMA's flags and/or anon_name. */ -struct vm_area_struct +__must_check struct vm_area_struct *vma_modify_flags_name(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, @@ -196,7 +192,7 @@ struct vm_area_struct struct anon_vma_name *new_name); /* We are about to modify the VMA's memory policy. */ -struct vm_area_struct +__must_check struct vm_area_struct *vma_modify_policy(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, @@ -204,7 +200,7 @@ struct vm_area_struct struct mempolicy *new_pol); /* We are about to modify the VMA's flags and/or uffd context. */ -struct vm_area_struct +__must_check struct vm_area_struct *vma_modify_flags_uffd(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, @@ -212,11 +208,13 @@ struct vm_area_struct unsigned long new_flags, struct vm_userfaultfd_ctx new_ctx); -struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg); +__must_check struct vm_area_struct +*vma_merge_new_range(struct vma_merge_struct *vmg); -struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, - struct vm_area_struct *vma, - unsigned long delta); +__must_check struct vm_area_struct +*vma_merge_extend(struct vma_iterator *vmi, + struct vm_area_struct *vma, + unsigned long delta); void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb); @@ -243,10 +241,16 @@ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); int mm_take_all_locks(struct mm_struct *mm); void mm_drop_all_locks(struct mm_struct *mm); -unsigned long __mmap_region(struct file *file, unsigned long addr, +unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf); +int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma, + unsigned long addr, unsigned long request, unsigned long flags); + +unsigned long unmapped_area(struct vm_unmapped_area_info *info); +unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info); + static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) { /* @@ -472,4 +476,12 @@ static inline bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior) #endif +#if defined(CONFIG_STACK_GROWSUP) +int expand_upwards(struct vm_area_struct *vma, unsigned long address); +#endif + +int expand_downwards(struct vm_area_struct *vma, unsigned long address); + +int __vm_munmap(unsigned long start, size_t len, bool unlock); + #endif /* __MM_VMA_H */ diff --git a/mm/vma_internal.h b/mm/vma_internal.h index fc5f172a36bd..2f05735ff190 100644 --- a/mm/vma_internal.h +++ b/mm/vma_internal.h @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f009b21705c1..a6e7acebe9ad 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3374,7 +3374,8 @@ void vfree(const void *addr) struct page *page = vm->pages[i]; BUG_ON(!page); - mod_memcg_page_state(page, MEMCG_VMALLOC, -1); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + mod_memcg_page_state(page, MEMCG_VMALLOC, -1); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations @@ -3382,7 +3383,8 @@ void vfree(const void *addr) __free_page(page); cond_resched(); } - atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); kvfree(vm->pages); kfree(vm); } @@ -3560,11 +3562,11 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * but mempolicy wants to alloc memory by interleaving. */ if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) - nr = alloc_pages_bulk_array_mempolicy_noprof(gfp, + nr = alloc_pages_bulk_mempolicy_noprof(gfp, nr_pages_request, pages + nr_allocated); else - nr = alloc_pages_bulk_array_node_noprof(gfp, nid, + nr = alloc_pages_bulk_node_noprof(gfp, nid, nr_pages_request, pages + nr_allocated); diff --git a/mm/vmscan.c b/mm/vmscan.c index 76378bc257e3..c767d71c43d7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -374,7 +374,14 @@ unsigned long zone_reclaimable_pages(struct zone *zone) if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); - + /* + * If there are no reclaimable file-backed or anonymous pages, + * ensure zones with sufficient free pages are not skipped. + * This prevents zones like DMA32 from being ignored in reclaim + * scenarios where they can still help alleviate memory pressure. + */ + if (nr == 0) + nr = zone_page_state_snapshot(zone, NR_FREE_PAGES); return nr; } @@ -855,6 +862,31 @@ enum folio_references { FOLIOREF_ACTIVATE, }; +#ifdef CONFIG_LRU_GEN +/* + * Only used on a mapped folio in the eviction (rmap walk) path, where promotion + * needs to be done by taking the folio off the LRU list and then adding it back + * with PG_active set. In contrast, the aging (page table walk) path uses + * folio_update_gen(). + */ +static bool lru_gen_set_refs(struct folio *folio) +{ + /* see the comment on LRU_REFS_FLAGS */ + if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) { + set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced)); + return false; + } + + set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_workingset)); + return true; +} +#else +static bool lru_gen_set_refs(struct folio *folio) +{ + return false; +} +#endif /* CONFIG_LRU_GEN */ + static enum folio_references folio_check_references(struct folio *folio, struct scan_control *sc) { @@ -863,7 +895,6 @@ static enum folio_references folio_check_references(struct folio *folio, referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, &vm_flags); - referenced_folio = folio_test_clear_referenced(folio); /* * The supposedly reclaimable folio was found to be in a VM_LOCKED vma. @@ -881,6 +912,15 @@ static enum folio_references folio_check_references(struct folio *folio, if (referenced_ptes == -1) return FOLIOREF_KEEP; + if (lru_gen_enabled()) { + if (!referenced_ptes) + return FOLIOREF_RECLAIM; + + return lru_gen_set_refs(folio) ? FOLIOREF_ACTIVATE : FOLIOREF_KEEP; + } + + referenced_folio = folio_test_clear_referenced(folio); + if (referenced_ptes) { /* * All mapped folios start out with page table @@ -1046,7 +1086,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, struct folio_batch free_folios; LIST_HEAD(ret_folios); LIST_HEAD(demote_folios); - unsigned int nr_reclaimed = 0; + unsigned int nr_reclaimed = 0, nr_demoted = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; @@ -1085,11 +1125,6 @@ retry: if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; - /* folio_update_gen() tried to promote this page? */ - if (lru_gen_enabled() && !ignore_references && - folio_mapped(folio) && folio_test_referenced(folio)) - goto keep_locked; - /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing @@ -1515,8 +1550,9 @@ keep: /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ - stat->nr_demoted = demote_folio_list(&demote_folios, pgdat); - nr_reclaimed += stat->nr_demoted; + nr_demoted = demote_folio_list(&demote_folios, pgdat); + nr_reclaimed += nr_demoted; + stat->nr_demoted += nr_demoted; /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ @@ -1657,6 +1693,7 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; + unsigned long max_nr_skipped = 0; LIST_HEAD(folios_skipped); total_scan = 0; @@ -1671,9 +1708,12 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, nr_pages = folio_nr_pages(folio); total_scan += nr_pages; - if (folio_zonenum(folio) > sc->reclaim_idx) { + /* Using max_nr_skipped to prevent hard LOCKUP*/ + if (max_nr_skipped < SWAP_CLUSTER_MAX_SKIPPED && + (folio_zonenum(folio) > sc->reclaim_idx)) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; + max_nr_skipped++; goto move; } @@ -2612,11 +2652,17 @@ static bool should_clear_pmd_young(void) READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \ } +#define evictable_min_seq(min_seq, swappiness) \ + min((min_seq)[!(swappiness)], (min_seq)[(swappiness) <= MAX_SWAPPINESS]) + #define for_each_gen_type_zone(gen, type, zone) \ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++) +#define for_each_evictable_type(type, swappiness) \ + for ((type) = !(swappiness); (type) <= ((swappiness) <= MAX_SWAPPINESS); (type)++) + #define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS) #define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS) @@ -2662,10 +2708,16 @@ static int get_nr_gens(struct lruvec *lruvec, int type) static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { - /* see the comment on lru_gen_folio */ - return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS && - get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) && - get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS; + int type; + + for (type = 0; type < ANON_AND_FILE; type++) { + int n = get_nr_gens(lruvec, type); + + if (n < MIN_NR_GENS || n > MAX_NR_GENS) + return false; + } + + return true; } /****************************************************************************** @@ -3066,16 +3118,20 @@ struct ctrl_pos { static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { + int i; struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); - pos->refaulted = lrugen->avg_refaulted[type][tier] + - atomic_long_read(&lrugen->refaulted[hist][type][tier]); - pos->total = lrugen->avg_total[type][tier] + - atomic_long_read(&lrugen->evicted[hist][type][tier]); - if (tier) - pos->total += lrugen->protected[hist][type][tier - 1]; pos->gain = gain; + pos->refaulted = pos->total = 0; + + for (i = tier % MAX_NR_TIERS; i <= min(tier, MAX_NR_TIERS - 1); i++) { + pos->refaulted += lrugen->avg_refaulted[type][i] + + atomic_long_read(&lrugen->refaulted[hist][type][i]); + pos->total += lrugen->avg_total[type][i] + + lrugen->protected[hist][type][i] + + atomic_long_read(&lrugen->evicted[hist][type][i]); + } } static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) @@ -3101,17 +3157,15 @@ static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2); sum = lrugen->avg_total[type][tier] + + lrugen->protected[hist][type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); - if (tier) - sum += lrugen->protected[hist][type][tier - 1]; WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2); } if (clear) { atomic_long_set(&lrugen->refaulted[hist][type][tier], 0); atomic_long_set(&lrugen->evicted[hist][type][tier], 0); - if (tier) - WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0); + WRITE_ONCE(lrugen->protected[hist][type][tier], 0); } } } @@ -3138,16 +3192,19 @@ static int folio_update_gen(struct folio *folio, int gen) VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); + /* see the comment on LRU_REFS_FLAGS */ + if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) { + set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced)); + return -1; + } + do { /* lru_gen_del_folio() has isolated this page? */ - if (!(old_flags & LRU_GEN_MASK)) { - /* for shrink_folio_list() */ - new_flags = old_flags | BIT(PG_referenced); - continue; - } + if (!(old_flags & LRU_GEN_MASK)) + return -1; - new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); - new_flags |= (gen + 1UL) << LRU_GEN_PGOFF; + new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS); + new_flags |= ((gen + 1UL) << LRU_GEN_PGOFF) | BIT(PG_workingset); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; @@ -3171,7 +3228,7 @@ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclai new_gen = (old_gen + 1) % MAX_NR_GENS; - new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); + new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS); new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF; /* for folio_end_writeback() */ if (reclaiming) @@ -3246,7 +3303,7 @@ static int should_skip_vma(unsigned long start, unsigned long end, struct mm_wal return true; if (vma_is_anonymous(vma)) - return !walk->can_swap; + return !walk->swappiness; if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping)) return true; @@ -3256,7 +3313,10 @@ static int should_skip_vma(unsigned long start, unsigned long end, struct mm_wal return true; if (shmem_mapping(mapping)) - return !walk->can_swap; + return !walk->swappiness; + + if (walk->swappiness > MAX_SWAPPINESS) + return true; /* to exclude special mappings like dax, etc. */ return !mapping->a_ops->read_folio; @@ -3344,21 +3404,19 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned } static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, - struct pglist_data *pgdat, bool can_swap) + struct pglist_data *pgdat) { - struct folio *folio; + struct folio *folio = pfn_folio(pfn); + + if (folio_lru_gen(folio) < 0) + return NULL; - folio = pfn_folio(pfn); if (folio_nid(folio) != pgdat->node_id) return NULL; if (folio_memcg(folio) != memcg) return NULL; - /* file VMAs can contain anon pages from COW */ - if (!folio_is_file_lru(folio) && !can_swap) - return NULL; - return folio; } @@ -3370,29 +3428,55 @@ static bool suitable_to_scan(int total, int young) return young * n >= total; } +static void walk_update_folio(struct lru_gen_mm_walk *walk, struct folio *folio, + int new_gen, bool dirty) +{ + int old_gen; + + if (!folio) + return; + + if (dirty && !folio_test_dirty(folio) && + !(folio_test_anon(folio) && folio_test_swapbacked(folio) && + !folio_test_swapcache(folio))) + folio_mark_dirty(folio); + + if (walk) { + old_gen = folio_update_gen(folio, new_gen); + if (old_gen >= 0 && old_gen != new_gen) + update_batch_size(walk, folio, old_gen, new_gen); + } else if (lru_gen_set_refs(folio)) { + old_gen = folio_lru_gen(folio); + if (old_gen >= 0 && old_gen != new_gen) + folio_activate(folio); + } +} + static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *args) { int i; + bool dirty; pte_t *pte; spinlock_t *ptl; unsigned long addr; int total = 0; int young = 0; + struct folio *last = NULL; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); - int old_gen, new_gen = lru_gen_from_seq(max_seq); + int gen = lru_gen_from_seq(max_seq); pmd_t pmdval; - pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, - &ptl); + pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, &ptl); if (!pte) return false; + if (!spin_trylock(ptl)) { pte_unmap(pte); - return false; + return true; } if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) { @@ -3414,26 +3498,30 @@ restart: if (pfn == -1) continue; - folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); + folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) continue; if (!ptep_clear_young_notify(args->vma, addr, pte + i)) continue; + if (last != folio) { + walk_update_folio(walk, last, gen, dirty); + + last = folio; + dirty = false; + } + + if (pte_dirty(ptent)) + dirty = true; + young++; walk->mm_stats[MM_LEAF_YOUNG]++; - - if (pte_dirty(ptent) && !folio_test_dirty(folio) && - !(folio_test_anon(folio) && folio_test_swapbacked(folio) && - !folio_test_swapcache(folio))) - folio_mark_dirty(folio); - - old_gen = folio_update_gen(folio, new_gen); - if (old_gen >= 0 && old_gen != new_gen) - update_batch_size(walk, folio, old_gen, new_gen); } + walk_update_folio(walk, last, gen, dirty); + last = NULL; + if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end)) goto restart; @@ -3447,13 +3535,15 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area struct mm_walk *args, unsigned long *bitmap, unsigned long *first) { int i; + bool dirty; pmd_t *pmd; spinlock_t *ptl; + struct folio *last = NULL; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); - int old_gen, new_gen = lru_gen_from_seq(max_seq); + int gen = lru_gen_from_seq(max_seq); VM_WARN_ON_ONCE(pud_leaf(*pud)); @@ -3499,27 +3589,30 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area if (pfn == -1) goto next; - folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); + folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) goto next; if (!pmdp_clear_young_notify(vma, addr, pmd + i)) goto next; + if (last != folio) { + walk_update_folio(walk, last, gen, dirty); + + last = folio; + dirty = false; + } + + if (pmd_dirty(pmd[i])) + dirty = true; + walk->mm_stats[MM_LEAF_YOUNG]++; - - if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) && - !(folio_test_anon(folio) && folio_test_swapbacked(folio) && - !folio_test_swapcache(folio))) - folio_mark_dirty(folio); - - old_gen = folio_update_gen(folio, new_gen); - if (old_gen >= 0 && old_gen != new_gen) - update_batch_size(walk, folio, old_gen, new_gen); next: i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1; } while (i <= MIN_LRU_BATCH); + walk_update_folio(walk, last, gen, dirty); + arch_leave_lazy_mmu_mode(); spin_unlock(ptl); done: @@ -3711,22 +3804,25 @@ static void clear_mm_walk(void) kfree(walk); } -static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) +static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness) { int zone; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; + int hist = lru_hist_from_seq(lrugen->min_seq[type]); int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); - if (type == LRU_GEN_ANON && !can_swap) + if (type ? swappiness > MAX_SWAPPINESS : !swappiness) goto done; - /* prevent cold/hot inversion if force_scan is true */ + /* prevent cold/hot inversion if the type is evictable */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { struct list_head *head = &lrugen->folios[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); + int refs = folio_lru_refs(folio); + bool workingset = folio_test_workingset(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); @@ -3736,6 +3832,15 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) new_gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]); + /* don't count the workingset being lazily promoted */ + if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) { + int tier = lru_tier_from_refs(refs, workingset); + int delta = folio_nr_pages(folio); + + WRITE_ONCE(lrugen->protected[hist][type][tier], + lrugen->protected[hist][type][tier] + delta); + } + if (!--remaining) return false; } @@ -3747,7 +3852,7 @@ done: return true; } -static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) +static bool try_to_inc_min_seq(struct lruvec *lruvec, int swappiness) { int gen, type, zone; bool success = false; @@ -3757,7 +3862,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); /* find the oldest populated generation */ - for (type = !can_swap; type < ANON_AND_FILE; type++) { + for_each_evictable_type(type, swappiness) { while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) { gen = lru_gen_from_seq(min_seq[type]); @@ -3773,13 +3878,17 @@ next: } /* see the comment on lru_gen_folio */ - if (can_swap) { - min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]); - min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]); + if (swappiness && swappiness <= MAX_SWAPPINESS) { + unsigned long seq = lrugen->max_seq - MIN_NR_GENS; + + if (min_seq[LRU_GEN_ANON] > seq && min_seq[LRU_GEN_FILE] < seq) + min_seq[LRU_GEN_ANON] = seq; + else if (min_seq[LRU_GEN_FILE] > seq && min_seq[LRU_GEN_ANON] < seq) + min_seq[LRU_GEN_FILE] = seq; } - for (type = !can_swap; type < ANON_AND_FILE; type++) { - if (min_seq[type] == lrugen->min_seq[type]) + for_each_evictable_type(type, swappiness) { + if (min_seq[type] <= lrugen->min_seq[type]) continue; reset_ctrl_pos(lruvec, type, true); @@ -3790,8 +3899,7 @@ next: return success; } -static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, - bool can_swap, bool force_scan) +static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness) { bool success; int prev, next; @@ -3809,13 +3917,11 @@ restart: if (!success) goto unlock; - for (type = ANON_AND_FILE - 1; type >= 0; type--) { + for (type = 0; type < ANON_AND_FILE; type++) { if (get_nr_gens(lruvec, type) != MAX_NR_GENS) continue; - VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap)); - - if (inc_min_seq(lruvec, type, can_swap)) + if (inc_min_seq(lruvec, type, swappiness)) continue; spin_unlock_irq(&lruvec->lru_lock); @@ -3859,7 +3965,7 @@ unlock: } static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, - bool can_swap, bool force_scan) + int swappiness, bool force_scan) { bool success; struct lru_gen_mm_walk *walk; @@ -3870,7 +3976,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, VM_WARN_ON_ONCE(seq > READ_ONCE(lrugen->max_seq)); if (!mm_state) - return inc_max_seq(lruvec, seq, can_swap, force_scan); + return inc_max_seq(lruvec, seq, swappiness); /* see the comment in iterate_mm_list() */ if (seq <= READ_ONCE(mm_state->seq)) @@ -3895,7 +4001,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, walk->lruvec = lruvec; walk->seq = seq; - walk->can_swap = can_swap; + walk->swappiness = swappiness; walk->force_scan = force_scan; do { @@ -3905,7 +4011,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, } while (mm); done: if (success) { - success = inc_max_seq(lruvec, seq, can_swap, force_scan); + success = inc_max_seq(lruvec, seq, swappiness); WARN_ON_ONCE(!success); } @@ -3946,13 +4052,13 @@ static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc) { int gen, type, zone; unsigned long total = 0; - bool can_swap = get_swappiness(lruvec, sc); + int swappiness = get_swappiness(lruvec, sc); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); - for (type = !can_swap; type < ANON_AND_FILE; type++) { + for_each_evictable_type(type, swappiness) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { @@ -3972,6 +4078,7 @@ static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc { int gen; unsigned long birth; + int swappiness = get_swappiness(lruvec, sc); struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); @@ -3981,8 +4088,7 @@ static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc if (!lruvec_is_sizable(lruvec, sc)) return false; - /* see the comment on lru_gen_folio */ - gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); + gen = lru_gen_from_seq(evictable_min_seq(min_seq, swappiness)); birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); return time_is_before_jiffies(birth + min_ttl); @@ -4041,21 +4147,22 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; + bool dirty; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; + struct folio *last = NULL; int young = 1; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; struct folio *folio = pfn_folio(pvmw->pfn); - bool can_swap = !folio_is_file_lru(folio); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); DEFINE_MAX_SEQ(lruvec); - int old_gen, new_gen = lru_gen_from_seq(max_seq); + int gen = lru_gen_from_seq(max_seq); lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); @@ -4102,37 +4209,28 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) if (pfn == -1) continue; - folio = get_pfn_folio(pfn, memcg, pgdat, can_swap); + folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) continue; if (!ptep_clear_young_notify(vma, addr, pte + i)) continue; + if (last != folio) { + walk_update_folio(walk, last, gen, dirty); + + last = folio; + dirty = false; + } + + if (pte_dirty(ptent)) + dirty = true; + young++; - - if (pte_dirty(ptent) && !folio_test_dirty(folio) && - !(folio_test_anon(folio) && folio_test_swapbacked(folio) && - !folio_test_swapcache(folio))) - folio_mark_dirty(folio); - - if (walk) { - old_gen = folio_update_gen(folio, new_gen); - if (old_gen >= 0 && old_gen != new_gen) - update_batch_size(walk, folio, old_gen, new_gen); - - continue; - } - - old_gen = folio_lru_gen(folio); - if (old_gen < 0) - folio_set_referenced(folio); - else if (old_gen != new_gen) { - folio_clear_lru_refs(folio); - folio_activate(folio); - } } + walk_update_folio(walk, last, gen, dirty); + arch_leave_lazy_mmu_mode(); /* feedback from rmap walkers to page table walkers */ @@ -4290,7 +4388,8 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); - int tier = lru_tier_from_refs(refs); + bool workingset = folio_test_workingset(folio); + int tier = lru_tier_from_refs(refs, workingset); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); @@ -4312,14 +4411,17 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c } /* protected */ - if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) { - int hist = lru_hist_from_seq(lrugen->min_seq[type]); - + if (tier > tier_idx || refs + workingset == BIT(LRU_REFS_WIDTH) + 1) { gen = folio_inc_gen(lruvec, folio, false); - list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); + list_move(&folio->lru, &lrugen->folios[gen][type][zone]); - WRITE_ONCE(lrugen->protected[hist][type][tier - 1], - lrugen->protected[hist][type][tier - 1] + delta); + /* don't count the workingset being lazily promoted */ + if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) { + int hist = lru_hist_from_seq(lrugen->min_seq[type]); + + WRITE_ONCE(lrugen->protected[hist][type][tier], + lrugen->protected[hist][type][tier] + delta); + } return true; } @@ -4339,8 +4441,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c } /* waiting for writeback */ - if (folio_test_locked(folio) || writeback || - (type == LRU_GEN_FILE && dirty)) { + if (writeback || (type == LRU_GEN_FILE && dirty)) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; @@ -4369,13 +4470,12 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca return false; } - /* see the comment on MAX_NR_TIERS */ + /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) - folio_clear_lru_refs(folio); + set_mask_bits(&folio->flags, LRU_REFS_MASK, 0); /* for shrink_folio_list() */ folio_clear_reclaim(folio); - folio_clear_referenced(folio); success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); @@ -4471,13 +4571,13 @@ static int get_tier_idx(struct lruvec *lruvec, int type) struct ctrl_pos sp, pv; /* - * To leave a margin for fluctuations, use a larger gain factor (1:2). + * To leave a margin for fluctuations, use a larger gain factor (2:3). * This value is chosen because any other tier would have at least twice * as many refaults as the first tier. */ - read_ctrl_pos(lruvec, type, 0, 1, &sp); + read_ctrl_pos(lruvec, type, 0, 2, &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { - read_ctrl_pos(lruvec, type, tier, 2, &pv); + read_ctrl_pos(lruvec, type, tier, 3, &pv); if (!positive_ctrl_err(&sp, &pv)) break; } @@ -4485,79 +4585,45 @@ static int get_tier_idx(struct lruvec *lruvec, int type) return tier - 1; } -static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx) +static int get_type_to_scan(struct lruvec *lruvec, int swappiness) { - int type, tier; struct ctrl_pos sp, pv; - int gain[ANON_AND_FILE] = { swappiness, MAX_SWAPPINESS - swappiness }; + if (swappiness <= MIN_SWAPPINESS + 1) + return LRU_GEN_FILE; + + if (swappiness >= MAX_SWAPPINESS) + return LRU_GEN_ANON; /* - * Compare the first tier of anon with that of file to determine which - * type to scan. Also need to compare other tiers of the selected type - * with the first tier of the other type to determine the last tier (of - * the selected type) to evict. + * Compare the sum of all tiers of anon with that of file to determine + * which type to scan. */ - read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp); - read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv); - type = positive_ctrl_err(&sp, &pv); + read_ctrl_pos(lruvec, LRU_GEN_ANON, MAX_NR_TIERS, swappiness, &sp); + read_ctrl_pos(lruvec, LRU_GEN_FILE, MAX_NR_TIERS, MAX_SWAPPINESS - swappiness, &pv); - read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp); - for (tier = 1; tier < MAX_NR_TIERS; tier++) { - read_ctrl_pos(lruvec, type, tier, gain[type], &pv); - if (!positive_ctrl_err(&sp, &pv)) - break; - } - - *tier_idx = tier - 1; - - return type; + return positive_ctrl_err(&sp, &pv); } static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness, int *type_scanned, struct list_head *list) { int i; - int type; - int scanned; - int tier = -1; - DEFINE_MIN_SEQ(lruvec); + int type = get_type_to_scan(lruvec, swappiness); - /* - * Try to make the obvious choice first, and if anon and file are both - * available from the same generation, - * 1. Interpret swappiness 1 as file first and MAX_SWAPPINESS as anon - * first. - * 2. If !__GFP_IO, file first since clean pagecache is more likely to - * exist than clean swapcache. - */ - if (!swappiness) - type = LRU_GEN_FILE; - else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE]) - type = LRU_GEN_ANON; - else if (swappiness == 1) - type = LRU_GEN_FILE; - else if (swappiness == MAX_SWAPPINESS) - type = LRU_GEN_ANON; - else if (!(sc->gfp_mask & __GFP_IO)) - type = LRU_GEN_FILE; - else - type = get_type_to_scan(lruvec, swappiness, &tier); + for_each_evictable_type(i, swappiness) { + int scanned; + int tier = get_tier_idx(lruvec, type); - for (i = !swappiness; i < ANON_AND_FILE; i++) { - if (tier < 0) - tier = get_tier_idx(lruvec, type); + *type_scanned = type; scanned = scan_folios(lruvec, sc, type, tier, list); if (scanned) - break; + return scanned; type = !type; - tier = -1; } - *type_scanned = type; - - return scanned; + return 0; } static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness) @@ -4573,6 +4639,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap struct reclaim_stat stat; struct lru_gen_mm_walk *walk; bool skip_retry = false; + struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); @@ -4582,7 +4649,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap scanned += try_to_inc_min_seq(lruvec, swappiness); - if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS) + if (evictable_min_seq(lrugen->min_seq, swappiness) + MIN_NR_GENS > lrugen->max_seq) scanned = 0; spin_unlock_irq(&lruvec->lru_lock); @@ -4598,31 +4665,24 @@ retry: type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); list_for_each_entry_safe_reverse(folio, next, &list, lru) { + DEFINE_MIN_SEQ(lruvec); + if (!folio_evictable(folio)) { list_del(&folio->lru); folio_putback_lru(folio); continue; } - if (folio_test_reclaim(folio) && - (folio_test_dirty(folio) || folio_test_writeback(folio))) { - /* restore LRU_REFS_FLAGS cleared by isolate_folio() */ - if (folio_test_workingset(folio)) - folio_set_referenced(folio); - continue; - } - - if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) || - folio_mapped(folio) || folio_test_locked(folio) || - folio_test_dirty(folio) || folio_test_writeback(folio)) { - /* don't add rejected folios to the oldest generation */ - set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, - BIT(PG_active)); - continue; - } - /* retry folios that may have missed folio_rotate_reclaimable() */ - list_move(&folio->lru, &clean); + if (!skip_retry && !folio_test_active(folio) && !folio_mapped(folio) && + !folio_test_dirty(folio) && !folio_test_writeback(folio)) { + list_move(&folio->lru, &clean); + continue; + } + + /* don't add rejected folios to the oldest generation */ + if (lru_gen_folio_seq(lruvec, folio, false) == min_seq[type]) + set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_active)); } spin_lock_irq(&lruvec->lru_lock); @@ -4635,6 +4695,9 @@ retry: reset_batch_size(walk); } + __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(), + stat.nr_demoted); + item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); @@ -4654,63 +4717,32 @@ retry: } static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, - bool can_swap, unsigned long *nr_to_scan) + int swappiness, unsigned long *nr_to_scan) { int gen, type, zone; - unsigned long old = 0; - unsigned long young = 0; - unsigned long total = 0; + unsigned long size = 0; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); - /* whether this lruvec is completely out of cold folios */ - if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) { - *nr_to_scan = 0; + *nr_to_scan = 0; + /* have to run aging, since eviction is not possible anymore */ + if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS > max_seq) return true; - } - for (type = !can_swap; type < ANON_AND_FILE; type++) { + for_each_evictable_type(type, swappiness) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { - unsigned long size = 0; - gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); - - total += size; - if (seq == max_seq) - young += size; - else if (seq + MIN_NR_GENS == max_seq) - old += size; } } - *nr_to_scan = total; - - /* - * The aging tries to be lazy to reduce the overhead, while the eviction - * stalls when the number of generations reaches MIN_NR_GENS. Hence, the - * ideal number of generations is MIN_NR_GENS+1. - */ - if (min_seq[!can_swap] + MIN_NR_GENS < max_seq) - return false; - - /* - * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1) - * of the total number of pages for each generation. A reasonable range - * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The - * aging cares about the upper bound of hot pages, while the eviction - * cares about the lower bound of cold pages. - */ - if (young * MIN_NR_GENS > total) - return true; - if (old * (MIN_NR_GENS + 2) < total) - return true; - - return false; + *nr_to_scan = size; + /* better to run aging even though eviction is still possible */ + return evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq; } /* @@ -4718,7 +4750,7 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg * reclaim. */ -static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap) +static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, int swappiness) { bool success; unsigned long nr_to_scan; @@ -4728,7 +4760,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) return -1; - success = should_run_aging(lruvec, max_seq, can_swap, &nr_to_scan); + success = should_run_aging(lruvec, max_seq, swappiness, &nr_to_scan); /* try to scrape all its memory if this memcg was deleted */ if (nr_to_scan && !mem_cgroup_online(memcg)) @@ -4739,7 +4771,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool return nr_to_scan >> sc->priority; /* stop scanning this lruvec as it's low on cold folios */ - return try_to_inc_max_seq(lruvec, max_seq, can_swap, false) ? -1 : 0; + return try_to_inc_max_seq(lruvec, max_seq, swappiness, false) ? -1 : 0; } static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) @@ -5283,8 +5315,7 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, s = "rep"; n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]); n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]); - if (tier) - n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]); + n[2] = READ_ONCE(lrugen->protected[hist][type][tier]); } for (i = 0; i < 3; i++) @@ -5339,7 +5370,7 @@ static int lru_gen_seq_show(struct seq_file *m, void *v) seq_printf(m, " node %5d\n", nid); if (!full) - seq = min_seq[LRU_GEN_ANON]; + seq = evictable_min_seq(min_seq, MAX_SWAPPINESS / 2); else if (max_seq >= MAX_NR_GENS) seq = max_seq - MAX_NR_GENS + 1; else @@ -5379,23 +5410,14 @@ static const struct seq_operations lru_gen_seq_ops = { }; static int run_aging(struct lruvec *lruvec, unsigned long seq, - bool can_swap, bool force_scan) + int swappiness, bool force_scan) { DEFINE_MAX_SEQ(lruvec); - DEFINE_MIN_SEQ(lruvec); - - if (seq < max_seq) - return 0; if (seq > max_seq) return -EINVAL; - if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq) - return -ERANGE; - - try_to_inc_max_seq(lruvec, max_seq, can_swap, force_scan); - - return 0; + return try_to_inc_max_seq(lruvec, max_seq, swappiness, force_scan) ? 0 : -EEXIST; } static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, @@ -5411,7 +5433,7 @@ static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_co while (!signal_pending(current)) { DEFINE_MIN_SEQ(lruvec); - if (seq < min_seq[!swappiness]) + if (seq < evictable_min_seq(min_seq, swappiness)) return 0; if (sc->nr_reclaimed >= nr_to_reclaim) @@ -5456,7 +5478,7 @@ static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, if (swappiness < MIN_SWAPPINESS) swappiness = get_swappiness(lruvec, sc); - else if (swappiness > MAX_SWAPPINESS) + else if (swappiness > MAX_SWAPPINESS + 1) goto done; switch (cmd) { @@ -7182,10 +7204,6 @@ static int kswapd(void *p) unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; - const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); - - if (!cpumask_empty(cpumask)) - set_cpus_allowed_ptr(tsk, cpumask); /* * Tell the memory management that we're a "memory allocator", @@ -7354,13 +7372,15 @@ void __meminit kswapd_run(int nid) pgdat_kswapd_lock(pgdat); if (!pgdat->kswapd) { - pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); + pgdat->kswapd = kthread_create_on_node(kswapd, pgdat, nid, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ pr_err("Failed to start kswapd on node %d，ret=%ld\n", nid, PTR_ERR(pgdat->kswapd)); BUG_ON(system_state < SYSTEM_RUNNING); pgdat->kswapd = NULL; + } else { + wake_up_process(pgdat->kswapd); } } pgdat_kswapd_unlock(pgdat); diff --git a/mm/vmstat.c b/mm/vmstat.c index 4d016314a56c..16bfe1c694dd 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -2122,10 +2122,20 @@ static void __init start_shepherd_timer(void) { int cpu; - for_each_possible_cpu(cpu) + for_each_possible_cpu(cpu) { INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), vmstat_update); + /* + * For secondary CPUs during CPU hotplug scenarios, + * vmstat_cpu_online() will enable the work. + * mm/vmstat:online enables and disables vmstat_work + * symmetrically during CPU hotplug events. + */ + if (!cpu_online(cpu)) + disable_delayed_work_sync(&per_cpu(vmstat_work, cpu)); + } + schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); } @@ -2148,13 +2158,14 @@ static int vmstat_cpu_online(unsigned int cpu) if (!node_state(cpu_to_node(cpu), N_CPU)) { node_set_state(cpu_to_node(cpu), N_CPU); } + enable_delayed_work(&per_cpu(vmstat_work, cpu)); return 0; } static int vmstat_cpu_down_prep(unsigned int cpu) { - cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu)); + disable_delayed_work_sync(&per_cpu(vmstat_work, cpu)); return 0; } diff --git a/mm/workingset.c b/mm/workingset.c index a4705e196545..4841ae8af411 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -239,7 +239,8 @@ static void *lru_gen_eviction(struct folio *folio) int type = folio_is_file_lru(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); - int tier = lru_tier_from_refs(refs); + bool workingset = folio_test_workingset(folio); + int tier = lru_tier_from_refs(refs, workingset); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); @@ -253,18 +254,18 @@ static void *lru_gen_eviction(struct folio *folio) hist = lru_hist_from_seq(min_seq); atomic_long_add(delta, &lrugen->evicted[hist][type][tier]); - return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs); + return pack_shadow(mem_cgroup_id(memcg), pgdat, token, workingset); } /* * Tests if the shadow entry is for a folio that was recently evicted. * Fills in @lruvec, @token, @workingset with the values unpacked from shadow. */ -static bool lru_gen_test_recent(void *shadow, bool file, struct lruvec **lruvec, +static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec, unsigned long *token, bool *workingset) { int memcg_id; - unsigned long min_seq; + unsigned long max_seq; struct mem_cgroup *memcg; struct pglist_data *pgdat; @@ -273,8 +274,10 @@ static bool lru_gen_test_recent(void *shadow, bool file, struct lruvec **lruvec, memcg = mem_cgroup_from_id(memcg_id); *lruvec = mem_cgroup_lruvec(memcg, pgdat); - min_seq = READ_ONCE((*lruvec)->lrugen.min_seq[file]); - return (*token >> LRU_REFS_WIDTH) == (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH)); + max_seq = READ_ONCE((*lruvec)->lrugen.max_seq); + max_seq &= EVICTION_MASK >> LRU_REFS_WIDTH; + + return abs_diff(max_seq, *token >> LRU_REFS_WIDTH) < MAX_NR_GENS; } static void lru_gen_refault(struct folio *folio, void *shadow) @@ -290,7 +293,7 @@ static void lru_gen_refault(struct folio *folio, void *shadow) rcu_read_lock(); - recent = lru_gen_test_recent(shadow, type, &lruvec, &token, &workingset); + recent = lru_gen_test_recent(shadow, &lruvec, &token, &workingset); if (lruvec != folio_lruvec(folio)) goto unlock; @@ -302,24 +305,20 @@ static void lru_gen_refault(struct folio *folio, void *shadow) lrugen = &lruvec->lrugen; hist = lru_hist_from_seq(READ_ONCE(lrugen->min_seq[type])); - /* see the comment in folio_lru_refs() */ - refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + workingset; - tier = lru_tier_from_refs(refs); + refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + 1; + tier = lru_tier_from_refs(refs, workingset); atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]); - mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta); - /* - * Count the following two cases as stalls: - * 1. For pages accessed through page tables, hotter pages pushed out - * hot pages which refaulted immediately. - * 2. For pages accessed multiple times through file descriptors, - * they would have been protected by sort_folio(). - */ - if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) { - set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset)); + /* see folio_add_lru() where folio_set_active() will be called */ + if (lru_gen_in_fault()) + mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta); + + if (workingset) { + folio_set_workingset(folio); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); - } + } else + set_mask_bits(&folio->flags, LRU_REFS_MASK, (refs - 1UL) << LRU_REFS_PGOFF); unlock: rcu_read_unlock(); } @@ -331,7 +330,7 @@ static void *lru_gen_eviction(struct folio *folio) return NULL; } -static bool lru_gen_test_recent(void *shadow, bool file, struct lruvec **lruvec, +static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec, unsigned long *token, bool *workingset) { return false; @@ -428,17 +427,16 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset, struct pglist_data *pgdat; unsigned long eviction; - rcu_read_lock(); - if (lru_gen_enabled()) { - bool recent = lru_gen_test_recent(shadow, file, - &eviction_lruvec, &eviction, workingset); + bool recent; + rcu_read_lock(); + recent = lru_gen_test_recent(shadow, &eviction_lruvec, &eviction, workingset); rcu_read_unlock(); return recent; } - + rcu_read_lock(); unpack_shadow(shadow, &memcgid, &pgdat, &eviction, workingset); eviction <<= bucket_order; @@ -459,14 +457,12 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset, * configurations instead. */ eviction_memcg = mem_cgroup_from_id(memcgid); - if (!mem_cgroup_disabled() && - (!eviction_memcg || !mem_cgroup_tryget(eviction_memcg))) { - rcu_read_unlock(); - return false; - } - + if (!mem_cgroup_tryget(eviction_memcg)) + eviction_memcg = NULL; rcu_read_unlock(); + if (!mem_cgroup_disabled() && !eviction_memcg) + return false; /* * Flush stats (and potentially sleep) outside the RCU read section. * @@ -544,6 +540,8 @@ void workingset_refault(struct folio *folio, void *shadow) bool workingset; long nr; + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + if (lru_gen_enabled()) { lru_gen_refault(folio, shadow); return; @@ -558,7 +556,6 @@ void workingset_refault(struct folio *folio, void *shadow) * is actually experiencing the refault event. Make sure the folio is * locked to guarantee folio_memcg() stability throughout. */ - VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); nr = folio_nr_pages(folio); memcg = folio_memcg(folio); pgdat = folio_pgdat(folio); diff --git a/mm/zpdesc.h b/mm/zpdesc.h new file mode 100644 index 000000000000..fa47fece2237 --- /dev/null +++ b/mm/zpdesc.h @@ -0,0 +1,182 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* zpdesc.h: zswap.zpool memory descriptor + * + * Written by Alex Shi + * Hyeonggon Yoo <42.hyeyoo@gmail.com> + */ +#ifndef __MM_ZPDESC_H__ +#define __MM_ZPDESC_H__ + +/* + * struct zpdesc - Memory descriptor for zpool memory. + * @flags: Page flags, mostly unused by zsmalloc. + * @lru: Indirectly used by page migration. + * @movable_ops: Used by page migration. + * @next: Next zpdesc in a zspage in zsmalloc zpool. + * @handle: For huge zspage in zsmalloc zpool. + * @zspage: Points to the zspage this zpdesc is a part of. + * @first_obj_offset: First object offset in zsmalloc zpool. + * @_refcount: The number of references to this zpdesc. + * + * This struct overlays struct page for now. Do not modify without a good + * understanding of the issues. In particular, do not expand into the overlap + * with memcg_data. + * + * Page flags used: + * * PG_private identifies the first component page. + * * PG_locked is used by page migration code. + */ +struct zpdesc { + unsigned long flags; + struct list_head lru; + unsigned long movable_ops; + union { + struct zpdesc *next; + unsigned long handle; + }; + struct zspage *zspage; + /* + * Only the lower 24 bits are available for offset, limiting a page + * to 16 MiB. The upper 8 bits are reserved for PGTY_zsmalloc. + * + * Do not access this field directly. + * Instead, use {get,set}_first_obj_offset() helpers. + */ + unsigned int first_obj_offset; + atomic_t _refcount; +}; +#define ZPDESC_MATCH(pg, zp) \ + static_assert(offsetof(struct page, pg) == offsetof(struct zpdesc, zp)) + +ZPDESC_MATCH(flags, flags); +ZPDESC_MATCH(lru, lru); +ZPDESC_MATCH(mapping, movable_ops); +ZPDESC_MATCH(index, next); +ZPDESC_MATCH(index, handle); +ZPDESC_MATCH(private, zspage); +ZPDESC_MATCH(page_type, first_obj_offset); +ZPDESC_MATCH(_refcount, _refcount); +#undef ZPDESC_MATCH +static_assert(sizeof(struct zpdesc) <= sizeof(struct page)); + +/* + * zpdesc_page - The first struct page allocated for a zpdesc + * @zp: The zpdesc. + * + * A convenience wrapper for converting zpdesc to the first struct page of the + * underlying folio, to communicate with code not yet converted to folio or + * struct zpdesc. + * + */ +#define zpdesc_page(zp) (_Generic((zp), \ + const struct zpdesc *: (const struct page *)(zp), \ + struct zpdesc *: (struct page *)(zp))) + +/** + * zpdesc_folio - The folio allocated for a zpdesc + * @zp: The zpdesc. + * + * Zpdescs are descriptors for zpool memory. The zpool memory itself is + * allocated as folios that contain the zpool objects, and zpdesc uses specific + * fields in the first struct page of the folio - those fields are now accessed + * by struct zpdesc. + * + * It is occasionally necessary convert to back to a folio in order to + * communicate with the rest of the mm. Please use this helper function + * instead of casting yourself, as the implementation may change in the future. + */ +#define zpdesc_folio(zp) (_Generic((zp), \ + const struct zpdesc *: (const struct folio *)(zp), \ + struct zpdesc *: (struct folio *)(zp))) +/** + * page_zpdesc - Converts from first struct page to zpdesc. + * @p: The first (either head of compound or single) page of zpdesc. + * + * A temporary wrapper to convert struct page to struct zpdesc in situations + * where we know the page is the compound head, or single order-0 page. + * + * Long-term ideally everything would work with struct zpdesc directly or go + * through folio to struct zpdesc. + * + * Return: The zpdesc which contains this page + */ +#define page_zpdesc(p) (_Generic((p), \ + const struct page *: (const struct zpdesc *)(p), \ + struct page *: (struct zpdesc *)(p))) + +static inline void zpdesc_lock(struct zpdesc *zpdesc) +{ + folio_lock(zpdesc_folio(zpdesc)); +} + +static inline bool zpdesc_trylock(struct zpdesc *zpdesc) +{ + return folio_trylock(zpdesc_folio(zpdesc)); +} + +static inline void zpdesc_unlock(struct zpdesc *zpdesc) +{ + folio_unlock(zpdesc_folio(zpdesc)); +} + +static inline void zpdesc_wait_locked(struct zpdesc *zpdesc) +{ + folio_wait_locked(zpdesc_folio(zpdesc)); +} + +static inline void zpdesc_get(struct zpdesc *zpdesc) +{ + folio_get(zpdesc_folio(zpdesc)); +} + +static inline void zpdesc_put(struct zpdesc *zpdesc) +{ + folio_put(zpdesc_folio(zpdesc)); +} + +static inline void *kmap_local_zpdesc(struct zpdesc *zpdesc) +{ + return kmap_local_page(zpdesc_page(zpdesc)); +} + +static inline unsigned long zpdesc_pfn(struct zpdesc *zpdesc) +{ + return page_to_pfn(zpdesc_page(zpdesc)); +} + +static inline struct zpdesc *pfn_zpdesc(unsigned long pfn) +{ + return page_zpdesc(pfn_to_page(pfn)); +} + +static inline void __zpdesc_set_movable(struct zpdesc *zpdesc, + const struct movable_operations *mops) +{ + __SetPageMovable(zpdesc_page(zpdesc), mops); +} + +static inline void __zpdesc_set_zsmalloc(struct zpdesc *zpdesc) +{ + __SetPageZsmalloc(zpdesc_page(zpdesc)); +} + +static inline void __zpdesc_clear_zsmalloc(struct zpdesc *zpdesc) +{ + __ClearPageZsmalloc(zpdesc_page(zpdesc)); +} + +static inline bool zpdesc_is_isolated(struct zpdesc *zpdesc) +{ + return PageIsolated(zpdesc_page(zpdesc)); +} + +static inline struct zone *zpdesc_zone(struct zpdesc *zpdesc) +{ + return page_zone(zpdesc_page(zpdesc)); +} + +static inline bool zpdesc_is_locked(struct zpdesc *zpdesc) +{ + return folio_test_locked(zpdesc_folio(zpdesc)); +} +#endif diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 64b66a4d3e6e..6d0e47f7ae33 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -13,24 +13,6 @@ * Released under the terms of GNU General Public License Version 2.0 */ -/* - * Following is how we use various fields and flags of underlying - * struct page(s) to form a zspage. - * - * Usage of struct page fields: - * page->private: points to zspage - * page->index: links together all component pages of a zspage - * For the huge page, this is always 0, so we use this field - * to store handle. - * page->page_type: PGTY_zsmalloc, lower 24 bits locate the first object - * offset in a subpage of a zspage - * - * Usage of struct page flags: - * PG_private: identifies the first component page - * PG_owner_priv_1: identifies the huge component page - * - */ - #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* @@ -67,6 +49,7 @@ #include #include #include +#include "zpdesc.h" #define ZSPAGE_MAGIC 0x58 @@ -245,6 +228,35 @@ struct zs_pool { atomic_t compaction_in_progress; }; +static inline void zpdesc_set_first(struct zpdesc *zpdesc) +{ + SetPagePrivate(zpdesc_page(zpdesc)); +} + +static inline void zpdesc_inc_zone_page_state(struct zpdesc *zpdesc) +{ + inc_zone_page_state(zpdesc_page(zpdesc), NR_ZSPAGES); +} + +static inline void zpdesc_dec_zone_page_state(struct zpdesc *zpdesc) +{ + dec_zone_page_state(zpdesc_page(zpdesc), NR_ZSPAGES); +} + +static inline struct zpdesc *alloc_zpdesc(gfp_t gfp) +{ + struct page *page = alloc_page(gfp); + + return page_zpdesc(page); +} + +static inline void free_zpdesc(struct zpdesc *zpdesc) +{ + struct page *page = zpdesc_page(zpdesc); + + __free_page(page); +} + struct zspage { struct { unsigned int huge:HUGE_BITS; @@ -254,7 +266,7 @@ struct zspage { }; unsigned int inuse; unsigned int freeobj; - struct page *first_page; + struct zpdesc *first_zpdesc; struct list_head list; /* fullness list */ struct zs_pool *pool; rwlock_t lock; @@ -440,9 +452,9 @@ static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = { .lock = INIT_LOCAL_LOCK(lock), }; -static __maybe_unused int is_first_page(struct page *page) +static inline bool __maybe_unused is_first_zpdesc(struct zpdesc *zpdesc) { - return PagePrivate(page); + return PagePrivate(zpdesc_page(zpdesc)); } /* Protected by class->lock */ @@ -451,36 +463,35 @@ static inline int get_zspage_inuse(struct zspage *zspage) return zspage->inuse; } - static inline void mod_zspage_inuse(struct zspage *zspage, int val) { zspage->inuse += val; } -static inline struct page *get_first_page(struct zspage *zspage) +static struct zpdesc *get_first_zpdesc(struct zspage *zspage) { - struct page *first_page = zspage->first_page; + struct zpdesc *first_zpdesc = zspage->first_zpdesc; - VM_BUG_ON_PAGE(!is_first_page(first_page), first_page); - return first_page; + VM_BUG_ON_PAGE(!is_first_zpdesc(first_zpdesc), zpdesc_page(first_zpdesc)); + return first_zpdesc; } #define FIRST_OBJ_PAGE_TYPE_MASK 0xffffff -static inline unsigned int get_first_obj_offset(struct page *page) +static inline unsigned int get_first_obj_offset(struct zpdesc *zpdesc) { - VM_WARN_ON_ONCE(!PageZsmalloc(page)); - return page->page_type & FIRST_OBJ_PAGE_TYPE_MASK; + VM_WARN_ON_ONCE(!PageZsmalloc(zpdesc_page(zpdesc))); + return zpdesc->first_obj_offset & FIRST_OBJ_PAGE_TYPE_MASK; } -static inline void set_first_obj_offset(struct page *page, unsigned int offset) +static inline void set_first_obj_offset(struct zpdesc *zpdesc, unsigned int offset) { /* With 24 bits available, we can support offsets into 16 MiB pages. */ BUILD_BUG_ON(PAGE_SIZE > SZ_16M); - VM_WARN_ON_ONCE(!PageZsmalloc(page)); + VM_WARN_ON_ONCE(!PageZsmalloc(zpdesc_page(zpdesc))); VM_WARN_ON_ONCE(offset & ~FIRST_OBJ_PAGE_TYPE_MASK); - page->page_type &= ~FIRST_OBJ_PAGE_TYPE_MASK; - page->page_type |= offset & FIRST_OBJ_PAGE_TYPE_MASK; + zpdesc->first_obj_offset &= ~FIRST_OBJ_PAGE_TYPE_MASK; + zpdesc->first_obj_offset |= offset & FIRST_OBJ_PAGE_TYPE_MASK; } static inline unsigned int get_freeobj(struct zspage *zspage) @@ -733,52 +744,52 @@ out: return newfg; } -static struct zspage *get_zspage(struct page *page) +static struct zspage *get_zspage(struct zpdesc *zpdesc) { - struct zspage *zspage = (struct zspage *)page_private(page); + struct zspage *zspage = zpdesc->zspage; BUG_ON(zspage->magic != ZSPAGE_MAGIC); return zspage; } -static struct page *get_next_page(struct page *page) +static struct zpdesc *get_next_zpdesc(struct zpdesc *zpdesc) { - struct zspage *zspage = get_zspage(page); + struct zspage *zspage = get_zspage(zpdesc); if (unlikely(ZsHugePage(zspage))) return NULL; - return (struct page *)page->index; + return zpdesc->next; } /** - * obj_to_location - get (, ) from encoded object value + * obj_to_location - get (, ) from encoded object value * @obj: the encoded object value - * @page: page object resides in zspage + * @zpdesc: zpdesc object resides in zspage * @obj_idx: object index */ -static void obj_to_location(unsigned long obj, struct page **page, +static void obj_to_location(unsigned long obj, struct zpdesc **zpdesc, unsigned int *obj_idx) { - *page = pfn_to_page(obj >> OBJ_INDEX_BITS); + *zpdesc = pfn_zpdesc(obj >> OBJ_INDEX_BITS); *obj_idx = (obj & OBJ_INDEX_MASK); } -static void obj_to_page(unsigned long obj, struct page **page) +static void obj_to_zpdesc(unsigned long obj, struct zpdesc **zpdesc) { - *page = pfn_to_page(obj >> OBJ_INDEX_BITS); + *zpdesc = pfn_zpdesc(obj >> OBJ_INDEX_BITS); } /** - * location_to_obj - get obj value encoded from (, ) - * @page: page object resides in zspage + * location_to_obj - get obj value encoded from (, ) + * @zpdesc: zpdesc object resides in zspage * @obj_idx: object index */ -static unsigned long location_to_obj(struct page *page, unsigned int obj_idx) +static unsigned long location_to_obj(struct zpdesc *zpdesc, unsigned int obj_idx) { unsigned long obj; - obj = page_to_pfn(page) << OBJ_INDEX_BITS; + obj = zpdesc_pfn(zpdesc) << OBJ_INDEX_BITS; obj |= obj_idx & OBJ_INDEX_MASK; return obj; @@ -789,15 +800,15 @@ static unsigned long handle_to_obj(unsigned long handle) return *(unsigned long *)handle; } -static inline bool obj_allocated(struct page *page, void *obj, +static inline bool obj_allocated(struct zpdesc *zpdesc, void *obj, unsigned long *phandle) { unsigned long handle; - struct zspage *zspage = get_zspage(page); + struct zspage *zspage = get_zspage(zpdesc); if (unlikely(ZsHugePage(zspage))) { - VM_BUG_ON_PAGE(!is_first_page(page), page); - handle = page->index; + VM_BUG_ON_PAGE(!is_first_zpdesc(zpdesc), zpdesc_page(zpdesc)); + handle = zpdesc->handle; } else handle = *(unsigned long *)obj; @@ -809,22 +820,24 @@ static inline bool obj_allocated(struct page *page, void *obj, return true; } -static void reset_page(struct page *page) +static void reset_zpdesc(struct zpdesc *zpdesc) { + struct page *page = zpdesc_page(zpdesc); + __ClearPageMovable(page); ClearPagePrivate(page); - set_page_private(page, 0); - page->index = 0; + zpdesc->zspage = NULL; + zpdesc->next = NULL; __ClearPageZsmalloc(page); } static int trylock_zspage(struct zspage *zspage) { - struct page *cursor, *fail; + struct zpdesc *cursor, *fail; - for (cursor = get_first_page(zspage); cursor != NULL; cursor = - get_next_page(cursor)) { - if (!trylock_page(cursor)) { + for (cursor = get_first_zpdesc(zspage); cursor != NULL; cursor = + get_next_zpdesc(cursor)) { + if (!zpdesc_trylock(cursor)) { fail = cursor; goto unlock; } @@ -832,9 +845,9 @@ static int trylock_zspage(struct zspage *zspage) return 1; unlock: - for (cursor = get_first_page(zspage); cursor != fail; cursor = - get_next_page(cursor)) - unlock_page(cursor); + for (cursor = get_first_zpdesc(zspage); cursor != fail; cursor = + get_next_zpdesc(cursor)) + zpdesc_unlock(cursor); return 0; } @@ -842,23 +855,23 @@ unlock: static void __free_zspage(struct zs_pool *pool, struct size_class *class, struct zspage *zspage) { - struct page *page, *next; + struct zpdesc *zpdesc, *next; assert_spin_locked(&class->lock); VM_BUG_ON(get_zspage_inuse(zspage)); VM_BUG_ON(zspage->fullness != ZS_INUSE_RATIO_0); - next = page = get_first_page(zspage); + next = zpdesc = get_first_zpdesc(zspage); do { - VM_BUG_ON_PAGE(!PageLocked(page), page); - next = get_next_page(page); - reset_page(page); - unlock_page(page); - dec_zone_page_state(page, NR_ZSPAGES); - put_page(page); - page = next; - } while (page != NULL); + VM_BUG_ON_PAGE(!zpdesc_is_locked(zpdesc), zpdesc_page(zpdesc)); + next = get_next_zpdesc(zpdesc); + reset_zpdesc(zpdesc); + zpdesc_unlock(zpdesc); + zpdesc_dec_zone_page_state(zpdesc); + zpdesc_put(zpdesc); + zpdesc = next; + } while (zpdesc != NULL); cache_free_zspage(pool, zspage); @@ -891,16 +904,16 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) { unsigned int freeobj = 1; unsigned long off = 0; - struct page *page = get_first_page(zspage); + struct zpdesc *zpdesc = get_first_zpdesc(zspage); - while (page) { - struct page *next_page; + while (zpdesc) { + struct zpdesc *next_zpdesc; struct link_free *link; void *vaddr; - set_first_obj_offset(page, off); + set_first_obj_offset(zpdesc, off); - vaddr = kmap_local_page(page); + vaddr = kmap_local_zpdesc(zpdesc); link = (struct link_free *)vaddr + off / sizeof(*link); while ((off += class->size) < PAGE_SIZE) { @@ -913,8 +926,8 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) * page, which must point to the first object on the next * page (if present) */ - next_page = get_next_page(page); - if (next_page) { + next_zpdesc = get_next_zpdesc(zpdesc); + if (next_zpdesc) { link->next = freeobj++ << OBJ_TAG_BITS; } else { /* @@ -924,7 +937,7 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) link->next = -1UL << OBJ_TAG_BITS; } kunmap_local(vaddr); - page = next_page; + zpdesc = next_zpdesc; off %= PAGE_SIZE; } @@ -932,35 +945,35 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) } static void create_page_chain(struct size_class *class, struct zspage *zspage, - struct page *pages[]) + struct zpdesc *zpdescs[]) { int i; - struct page *page; - struct page *prev_page = NULL; - int nr_pages = class->pages_per_zspage; + struct zpdesc *zpdesc; + struct zpdesc *prev_zpdesc = NULL; + int nr_zpdescs = class->pages_per_zspage; /* * Allocate individual pages and link them together as: - * 1. all pages are linked together using page->index - * 2. each sub-page point to zspage using page->private + * 1. all pages are linked together using zpdesc->next + * 2. each sub-page point to zspage using zpdesc->zspage * - * we set PG_private to identify the first page (i.e. no other sub-page + * we set PG_private to identify the first zpdesc (i.e. no other zpdesc * has this flag set). */ - for (i = 0; i < nr_pages; i++) { - page = pages[i]; - set_page_private(page, (unsigned long)zspage); - page->index = 0; + for (i = 0; i < nr_zpdescs; i++) { + zpdesc = zpdescs[i]; + zpdesc->zspage = zspage; + zpdesc->next = NULL; if (i == 0) { - zspage->first_page = page; - SetPagePrivate(page); + zspage->first_zpdesc = zpdesc; + zpdesc_set_first(zpdesc); if (unlikely(class->objs_per_zspage == 1 && class->pages_per_zspage == 1)) SetZsHugePage(zspage); } else { - prev_page->index = (unsigned long)page; + prev_zpdesc->next = zpdesc; } - prev_page = page; + prev_zpdesc = zpdesc; } } @@ -972,7 +985,7 @@ static struct zspage *alloc_zspage(struct zs_pool *pool, gfp_t gfp) { int i; - struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE]; + struct zpdesc *zpdescs[ZS_MAX_PAGES_PER_ZSPAGE]; struct zspage *zspage = cache_alloc_zspage(pool, gfp); if (!zspage) @@ -982,25 +995,25 @@ static struct zspage *alloc_zspage(struct zs_pool *pool, migrate_lock_init(zspage); for (i = 0; i < class->pages_per_zspage; i++) { - struct page *page; + struct zpdesc *zpdesc; - page = alloc_page(gfp); - if (!page) { + zpdesc = alloc_zpdesc(gfp); + if (!zpdesc) { while (--i >= 0) { - dec_zone_page_state(pages[i], NR_ZSPAGES); - __ClearPageZsmalloc(pages[i]); - __free_page(pages[i]); + zpdesc_dec_zone_page_state(zpdescs[i]); + __zpdesc_clear_zsmalloc(zpdescs[i]); + free_zpdesc(zpdescs[i]); } cache_free_zspage(pool, zspage); return NULL; } - __SetPageZsmalloc(page); + __zpdesc_set_zsmalloc(zpdesc); - inc_zone_page_state(page, NR_ZSPAGES); - pages[i] = page; + zpdesc_inc_zone_page_state(zpdesc); + zpdescs[i] = zpdesc; } - create_page_chain(class, zspage, pages); + create_page_chain(class, zspage, zpdescs); init_zspage(class, zspage); zspage->pool = pool; zspage->class = class->index; @@ -1044,7 +1057,7 @@ static inline void __zs_cpu_down(struct mapping_area *area) } static void *__zs_map_object(struct mapping_area *area, - struct page *pages[2], int off, int size) + struct zpdesc *zpdescs[2], int off, int size) { size_t sizes[2]; char *buf = area->vm_buf; @@ -1060,14 +1073,14 @@ static void *__zs_map_object(struct mapping_area *area, sizes[1] = size - sizes[0]; /* copy object to per-cpu buffer */ - memcpy_from_page(buf, pages[0], off, sizes[0]); - memcpy_from_page(buf + sizes[0], pages[1], 0, sizes[1]); + memcpy_from_page(buf, zpdesc_page(zpdescs[0]), off, sizes[0]); + memcpy_from_page(buf + sizes[0], zpdesc_page(zpdescs[1]), 0, sizes[1]); out: return area->vm_buf; } static void __zs_unmap_object(struct mapping_area *area, - struct page *pages[2], int off, int size) + struct zpdesc *zpdescs[2], int off, int size) { size_t sizes[2]; char *buf; @@ -1085,8 +1098,8 @@ static void __zs_unmap_object(struct mapping_area *area, sizes[1] = size - sizes[0]; /* copy per-cpu buffer to object */ - memcpy_to_page(pages[0], off, buf, sizes[0]); - memcpy_to_page(pages[1], 0, buf + sizes[0], sizes[1]); + memcpy_to_page(zpdesc_page(zpdescs[0]), off, buf, sizes[0]); + memcpy_to_page(zpdesc_page(zpdescs[1]), 0, buf + sizes[0], sizes[1]); out: /* enable page faults to match kunmap_local() return conditions */ @@ -1176,13 +1189,13 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, enum zs_mapmode mm) { struct zspage *zspage; - struct page *page; + struct zpdesc *zpdesc; unsigned long obj, off; unsigned int obj_idx; struct size_class *class; struct mapping_area *area; - struct page *pages[2]; + struct zpdesc *zpdescs[2]; void *ret; /* @@ -1195,8 +1208,8 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, /* It guarantees it can get zspage from handle safely */ read_lock(&pool->migrate_lock); obj = handle_to_obj(handle); - obj_to_location(obj, &page, &obj_idx); - zspage = get_zspage(page); + obj_to_location(obj, &zpdesc, &obj_idx); + zspage = get_zspage(zpdesc); /* * migration cannot move any zpages in this zspage. Here, class->lock @@ -1215,17 +1228,17 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, area->vm_mm = mm; if (off + class->size <= PAGE_SIZE) { /* this object is contained entirely within a page */ - area->vm_addr = kmap_local_page(page); + area->vm_addr = kmap_local_zpdesc(zpdesc); ret = area->vm_addr + off; goto out; } /* this object spans two pages */ - pages[0] = page; - pages[1] = get_next_page(page); - BUG_ON(!pages[1]); + zpdescs[0] = zpdesc; + zpdescs[1] = get_next_zpdesc(zpdesc); + BUG_ON(!zpdescs[1]); - ret = __zs_map_object(area, pages, off, class->size); + ret = __zs_map_object(area, zpdescs, off, class->size); out: if (likely(!ZsHugePage(zspage))) ret += ZS_HANDLE_SIZE; @@ -1237,7 +1250,7 @@ EXPORT_SYMBOL_GPL(zs_map_object); void zs_unmap_object(struct zs_pool *pool, unsigned long handle) { struct zspage *zspage; - struct page *page; + struct zpdesc *zpdesc; unsigned long obj, off; unsigned int obj_idx; @@ -1245,8 +1258,8 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) struct mapping_area *area; obj = handle_to_obj(handle); - obj_to_location(obj, &page, &obj_idx); - zspage = get_zspage(page); + obj_to_location(obj, &zpdesc, &obj_idx); + zspage = get_zspage(zpdesc); class = zspage_class(pool, zspage); off = offset_in_page(class->size * obj_idx); @@ -1254,13 +1267,13 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) if (off + class->size <= PAGE_SIZE) kunmap_local(area->vm_addr); else { - struct page *pages[2]; + struct zpdesc *zpdescs[2]; - pages[0] = page; - pages[1] = get_next_page(page); - BUG_ON(!pages[1]); + zpdescs[0] = zpdesc; + zpdescs[1] = get_next_zpdesc(zpdesc); + BUG_ON(!zpdescs[1]); - __zs_unmap_object(area, pages, off, class->size); + __zs_unmap_object(area, zpdescs, off, class->size); } local_unlock(&zs_map_area.lock); @@ -1290,12 +1303,12 @@ EXPORT_SYMBOL_GPL(zs_huge_class_size); static unsigned long obj_malloc(struct zs_pool *pool, struct zspage *zspage, unsigned long handle) { - int i, nr_page, offset; + int i, nr_zpdesc, offset; unsigned long obj; struct link_free *link; struct size_class *class; - struct page *m_page; + struct zpdesc *m_zpdesc; unsigned long m_offset; void *vaddr; @@ -1303,27 +1316,26 @@ static unsigned long obj_malloc(struct zs_pool *pool, obj = get_freeobj(zspage); offset = obj * class->size; - nr_page = offset >> PAGE_SHIFT; + nr_zpdesc = offset >> PAGE_SHIFT; m_offset = offset_in_page(offset); - m_page = get_first_page(zspage); + m_zpdesc = get_first_zpdesc(zspage); - for (i = 0; i < nr_page; i++) - m_page = get_next_page(m_page); + for (i = 0; i < nr_zpdesc; i++) + m_zpdesc = get_next_zpdesc(m_zpdesc); - vaddr = kmap_local_page(m_page); + vaddr = kmap_local_zpdesc(m_zpdesc); link = (struct link_free *)vaddr + m_offset / sizeof(*link); set_freeobj(zspage, link->next >> OBJ_TAG_BITS); if (likely(!ZsHugePage(zspage))) /* record handle in the header of allocated chunk */ link->handle = handle | OBJ_ALLOCATED_TAG; else - /* record handle to page->index */ - zspage->first_page->index = handle | OBJ_ALLOCATED_TAG; + zspage->first_zpdesc->handle = handle | OBJ_ALLOCATED_TAG; kunmap_local(vaddr); mod_zspage_inuse(zspage, 1); - obj = location_to_obj(m_page, obj); + obj = location_to_obj(m_zpdesc, obj); record_obj(handle, obj); return obj; @@ -1402,23 +1414,24 @@ static void obj_free(int class_size, unsigned long obj) { struct link_free *link; struct zspage *zspage; - struct page *f_page; + struct zpdesc *f_zpdesc; unsigned long f_offset; unsigned int f_objidx; void *vaddr; - obj_to_location(obj, &f_page, &f_objidx); - f_offset = offset_in_page(class_size * f_objidx); - zspage = get_zspage(f_page); - vaddr = kmap_local_page(f_page); + obj_to_location(obj, &f_zpdesc, &f_objidx); + f_offset = offset_in_page(class_size * f_objidx); + zspage = get_zspage(f_zpdesc); + + vaddr = kmap_local_zpdesc(f_zpdesc); link = (struct link_free *)(vaddr + f_offset); /* Insert this object in containing zspage's freelist */ if (likely(!ZsHugePage(zspage))) link->next = get_freeobj(zspage) << OBJ_TAG_BITS; else - f_page->index = 0; + f_zpdesc->handle = 0; set_freeobj(zspage, f_objidx); kunmap_local(vaddr); @@ -1428,7 +1441,7 @@ static void obj_free(int class_size, unsigned long obj) void zs_free(struct zs_pool *pool, unsigned long handle) { struct zspage *zspage; - struct page *f_page; + struct zpdesc *f_zpdesc; unsigned long obj; struct size_class *class; int fullness; @@ -1442,8 +1455,8 @@ void zs_free(struct zs_pool *pool, unsigned long handle) */ read_lock(&pool->migrate_lock); obj = handle_to_obj(handle); - obj_to_page(obj, &f_page); - zspage = get_zspage(f_page); + obj_to_zpdesc(obj, &f_zpdesc); + zspage = get_zspage(f_zpdesc); class = zspage_class(pool, zspage); spin_lock(&class->lock); read_unlock(&pool->migrate_lock); @@ -1463,7 +1476,7 @@ EXPORT_SYMBOL_GPL(zs_free); static void zs_object_copy(struct size_class *class, unsigned long dst, unsigned long src) { - struct page *s_page, *d_page; + struct zpdesc *s_zpdesc, *d_zpdesc; unsigned int s_objidx, d_objidx; unsigned long s_off, d_off; void *s_addr, *d_addr; @@ -1472,8 +1485,8 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, s_size = d_size = class->size; - obj_to_location(src, &s_page, &s_objidx); - obj_to_location(dst, &d_page, &d_objidx); + obj_to_location(src, &s_zpdesc, &s_objidx); + obj_to_location(dst, &d_zpdesc, &d_objidx); s_off = offset_in_page(class->size * s_objidx); d_off = offset_in_page(class->size * d_objidx); @@ -1484,8 +1497,8 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, if (d_off + class->size > PAGE_SIZE) d_size = PAGE_SIZE - d_off; - s_addr = kmap_local_page(s_page); - d_addr = kmap_local_page(d_page); + s_addr = kmap_local_zpdesc(s_zpdesc); + d_addr = kmap_local_zpdesc(d_zpdesc); while (1) { size = min(s_size, d_size); @@ -1510,17 +1523,17 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, if (s_off >= PAGE_SIZE) { kunmap_local(d_addr); kunmap_local(s_addr); - s_page = get_next_page(s_page); - s_addr = kmap_local_page(s_page); - d_addr = kmap_local_page(d_page); + s_zpdesc = get_next_zpdesc(s_zpdesc); + s_addr = kmap_local_zpdesc(s_zpdesc); + d_addr = kmap_local_zpdesc(d_zpdesc); s_size = class->size - written; s_off = 0; } if (d_off >= PAGE_SIZE) { kunmap_local(d_addr); - d_page = get_next_page(d_page); - d_addr = kmap_local_page(d_page); + d_zpdesc = get_next_zpdesc(d_zpdesc); + d_addr = kmap_local_zpdesc(d_zpdesc); d_size = class->size - written; d_off = 0; } @@ -1535,18 +1548,18 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, * return handle. */ static unsigned long find_alloced_obj(struct size_class *class, - struct page *page, int *obj_idx) + struct zpdesc *zpdesc, int *obj_idx) { unsigned int offset; int index = *obj_idx; unsigned long handle = 0; - void *addr = kmap_local_page(page); + void *addr = kmap_local_zpdesc(zpdesc); - offset = get_first_obj_offset(page); + offset = get_first_obj_offset(zpdesc); offset += class->size * index; while (offset < PAGE_SIZE) { - if (obj_allocated(page, addr + offset, &handle)) + if (obj_allocated(zpdesc, addr + offset, &handle)) break; offset += class->size; @@ -1566,14 +1579,14 @@ static void migrate_zspage(struct zs_pool *pool, struct zspage *src_zspage, unsigned long used_obj, free_obj; unsigned long handle; int obj_idx = 0; - struct page *s_page = get_first_page(src_zspage); + struct zpdesc *s_zpdesc = get_first_zpdesc(src_zspage); struct size_class *class = pool->size_class[src_zspage->class]; while (1) { - handle = find_alloced_obj(class, s_page, &obj_idx); + handle = find_alloced_obj(class, s_zpdesc, &obj_idx); if (!handle) { - s_page = get_next_page(s_page); - if (!s_page) + s_zpdesc = get_next_zpdesc(s_zpdesc); + if (!s_zpdesc) break; obj_idx = 0; continue; @@ -1653,7 +1666,7 @@ static int putback_zspage(struct size_class *class, struct zspage *zspage) */ static void lock_zspage(struct zspage *zspage) { - struct page *curr_page, *page; + struct zpdesc *curr_zpdesc, *zpdesc; /* * Pages we haven't locked yet can be migrated off the list while we're @@ -1665,24 +1678,24 @@ static void lock_zspage(struct zspage *zspage) */ while (1) { migrate_read_lock(zspage); - page = get_first_page(zspage); - if (trylock_page(page)) + zpdesc = get_first_zpdesc(zspage); + if (zpdesc_trylock(zpdesc)) break; - get_page(page); + zpdesc_get(zpdesc); migrate_read_unlock(zspage); - wait_on_page_locked(page); - put_page(page); + zpdesc_wait_locked(zpdesc); + zpdesc_put(zpdesc); } - curr_page = page; - while ((page = get_next_page(curr_page))) { - if (trylock_page(page)) { - curr_page = page; + curr_zpdesc = zpdesc; + while ((zpdesc = get_next_zpdesc(curr_zpdesc))) { + if (zpdesc_trylock(zpdesc)) { + curr_zpdesc = zpdesc; } else { - get_page(page); + zpdesc_get(zpdesc); migrate_read_unlock(zspage); - wait_on_page_locked(page); - put_page(page); + zpdesc_wait_locked(zpdesc); + zpdesc_put(zpdesc); migrate_read_lock(zspage); } } @@ -1720,26 +1733,28 @@ static void migrate_write_unlock(struct zspage *zspage) static const struct movable_operations zsmalloc_mops; static void replace_sub_page(struct size_class *class, struct zspage *zspage, - struct page *newpage, struct page *oldpage) + struct zpdesc *newzpdesc, struct zpdesc *oldzpdesc) { - struct page *page; - struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, }; + struct zpdesc *zpdesc; + struct zpdesc *zpdescs[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, }; + unsigned int first_obj_offset; int idx = 0; - page = get_first_page(zspage); + zpdesc = get_first_zpdesc(zspage); do { - if (page == oldpage) - pages[idx] = newpage; + if (zpdesc == oldzpdesc) + zpdescs[idx] = newzpdesc; else - pages[idx] = page; + zpdescs[idx] = zpdesc; idx++; - } while ((page = get_next_page(page)) != NULL); + } while ((zpdesc = get_next_zpdesc(zpdesc)) != NULL); - create_page_chain(class, zspage, pages); - set_first_obj_offset(newpage, get_first_obj_offset(oldpage)); + create_page_chain(class, zspage, zpdescs); + first_obj_offset = get_first_obj_offset(oldzpdesc); + set_first_obj_offset(newzpdesc, first_obj_offset); if (unlikely(ZsHugePage(zspage))) - newpage->index = oldpage->index; - __SetPageMovable(newpage, &zsmalloc_mops); + newzpdesc->handle = oldzpdesc->handle; + __zpdesc_set_movable(newzpdesc, &zsmalloc_mops); } static bool zs_page_isolate(struct page *page, isolate_mode_t mode) @@ -1759,20 +1774,22 @@ static int zs_page_migrate(struct page *newpage, struct page *page, struct zs_pool *pool; struct size_class *class; struct zspage *zspage; - struct page *dummy; + struct zpdesc *dummy; + struct zpdesc *newzpdesc = page_zpdesc(newpage); + struct zpdesc *zpdesc = page_zpdesc(page); void *s_addr, *d_addr, *addr; unsigned int offset; unsigned long handle; unsigned long old_obj, new_obj; unsigned int obj_idx; - VM_BUG_ON_PAGE(!PageIsolated(page), page); + VM_BUG_ON_PAGE(!zpdesc_is_isolated(zpdesc), zpdesc_page(zpdesc)); /* We're committed, tell the world that this is a Zsmalloc page. */ - __SetPageZsmalloc(newpage); + __zpdesc_set_zsmalloc(newzpdesc); /* The page is locked, so this pointer must remain valid */ - zspage = get_zspage(page); + zspage = get_zspage(zpdesc); pool = zspage->pool; /* @@ -1789,30 +1806,29 @@ static int zs_page_migrate(struct page *newpage, struct page *page, /* the migrate_write_lock protects zpage access via zs_map_object */ migrate_write_lock(zspage); - offset = get_first_obj_offset(page); - s_addr = kmap_local_page(page); + offset = get_first_obj_offset(zpdesc); + s_addr = kmap_local_zpdesc(zpdesc); /* * Here, any user cannot access all objects in the zspage so let's move. */ - d_addr = kmap_local_page(newpage); + d_addr = kmap_local_zpdesc(newzpdesc); copy_page(d_addr, s_addr); kunmap_local(d_addr); for (addr = s_addr + offset; addr < s_addr + PAGE_SIZE; addr += class->size) { - if (obj_allocated(page, addr, &handle)) { + if (obj_allocated(zpdesc, addr, &handle)) { old_obj = handle_to_obj(handle); obj_to_location(old_obj, &dummy, &obj_idx); - new_obj = (unsigned long)location_to_obj(newpage, - obj_idx); + new_obj = (unsigned long)location_to_obj(newzpdesc, obj_idx); record_obj(handle, new_obj); } } kunmap_local(s_addr); - replace_sub_page(class, zspage, newpage, page); + replace_sub_page(class, zspage, newzpdesc, zpdesc); /* * Since we complete the data copy and set up new zspage structure, * it's okay to release migration_lock. @@ -1821,14 +1837,14 @@ static int zs_page_migrate(struct page *newpage, struct page *page, spin_unlock(&class->lock); migrate_write_unlock(zspage); - get_page(newpage); - if (page_zone(newpage) != page_zone(page)) { - dec_zone_page_state(page, NR_ZSPAGES); - inc_zone_page_state(newpage, NR_ZSPAGES); + zpdesc_get(newzpdesc); + if (zpdesc_zone(newzpdesc) != zpdesc_zone(zpdesc)) { + zpdesc_dec_zone_page_state(zpdesc); + zpdesc_inc_zone_page_state(newzpdesc); } - reset_page(page); - put_page(page); + reset_zpdesc(zpdesc); + zpdesc_put(zpdesc); return MIGRATEPAGE_SUCCESS; } @@ -1897,13 +1913,13 @@ static void init_deferred_free(struct zs_pool *pool) static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) { - struct page *page = get_first_page(zspage); + struct zpdesc *zpdesc = get_first_zpdesc(zspage); do { - WARN_ON(!trylock_page(page)); - __SetPageMovable(page, &zsmalloc_mops); - unlock_page(page); - } while ((page = get_next_page(page)) != NULL); + WARN_ON(!zpdesc_trylock(zpdesc)); + __zpdesc_set_movable(zpdesc, &zsmalloc_mops); + zpdesc_unlock(zpdesc); + } while ((zpdesc = get_next_zpdesc(zpdesc)) != NULL); } #else static inline void zs_flush_migration(struct zs_pool *pool) { } diff --git a/mm/zswap.c b/mm/zswap.c index f6316b66fb23..6504174fbc6a 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -251,7 +251,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) struct zswap_pool *pool; char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; - int ret; + int ret, cpu; if (!zswap_has_pool) { /* if either are unset, pool initialization failed, and we @@ -285,6 +285,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) goto error; } + for_each_possible_cpu(cpu) + mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex); + ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); if (ret) @@ -817,36 +820,41 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); - struct crypto_acomp *acomp; - struct acomp_req *req; + struct crypto_acomp *acomp = NULL; + struct acomp_req *req = NULL; + u8 *buffer = NULL; int ret; - mutex_init(&acomp_ctx->mutex); - - acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) - return -ENOMEM; + buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); + if (!buffer) { + ret = -ENOMEM; + goto fail; + } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); if (IS_ERR(acomp)) { pr_err("could not alloc crypto acomp %s : %ld\n", pool->tfm_name, PTR_ERR(acomp)); ret = PTR_ERR(acomp); - goto acomp_fail; + goto fail; } - acomp_ctx->acomp = acomp; - acomp_ctx->is_sleepable = acomp_is_async(acomp); - req = acomp_request_alloc(acomp_ctx->acomp); + req = acomp_request_alloc(acomp); if (!req) { pr_err("could not alloc crypto acomp_request %s\n", pool->tfm_name); ret = -ENOMEM; - goto req_fail; + goto fail; } - acomp_ctx->req = req; + /* + * Only hold the mutex after completing allocations, otherwise we may + * recurse into zswap through reclaim and attempt to hold the mutex + * again resulting in a deadlock. + */ + mutex_lock(&acomp_ctx->mutex); crypto_init_wait(&acomp_ctx->wait); + /* * if the backend of acomp is async zip, crypto_req_done() will wakeup * crypto_wait_req(); if the backend of acomp is scomp, the callback @@ -855,12 +863,17 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + acomp_ctx->buffer = buffer; + acomp_ctx->acomp = acomp; + acomp_ctx->is_sleepable = acomp_is_async(acomp); + acomp_ctx->req = req; + mutex_unlock(&acomp_ctx->mutex); return 0; -req_fail: - crypto_free_acomp(acomp_ctx->acomp); -acomp_fail: - kfree(acomp_ctx->buffer); +fail: + if (acomp) + crypto_free_acomp(acomp); + kfree(buffer); return ret; } @@ -869,17 +882,45 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); + mutex_lock(&acomp_ctx->mutex); if (!IS_ERR_OR_NULL(acomp_ctx)) { if (!IS_ERR_OR_NULL(acomp_ctx->req)) acomp_request_free(acomp_ctx->req); + acomp_ctx->req = NULL; if (!IS_ERR_OR_NULL(acomp_ctx->acomp)) crypto_free_acomp(acomp_ctx->acomp); kfree(acomp_ctx->buffer); } + mutex_unlock(&acomp_ctx->mutex); return 0; } +static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool) +{ + struct crypto_acomp_ctx *acomp_ctx; + + for (;;) { + acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); + mutex_lock(&acomp_ctx->mutex); + if (likely(acomp_ctx->req)) + return acomp_ctx; + /* + * It is possible that we were migrated to a different CPU after + * getting the per-CPU ctx but before the mutex was acquired. If + * the old CPU got offlined, zswap_cpu_comp_dead() could have + * already freed ctx->req (among other things) and set it to + * NULL. Just try again on the new CPU that we ended up on. + */ + mutex_unlock(&acomp_ctx->mutex); + } +} + +static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx) +{ + mutex_unlock(&acomp_ctx->mutex); +} + static bool zswap_compress(struct page *page, struct zswap_entry *entry, struct zswap_pool *pool) { @@ -893,10 +934,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry, gfp_t gfp; u8 *dst; - acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); - - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(pool); dst = acomp_ctx->buffer; sg_init_table(&input, 1); sg_set_page(&input, page, PAGE_SIZE, 0); @@ -949,7 +987,7 @@ unlock: else if (alloc_ret) zswap_reject_alloc_fail++; - mutex_unlock(&acomp_ctx->mutex); + acomp_ctx_put_unlock(acomp_ctx); return comp_ret == 0 && alloc_ret == 0; } @@ -960,9 +998,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) struct crypto_acomp_ctx *acomp_ctx; u8 *src; - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool); src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); /* * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer @@ -986,10 +1022,10 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait)); BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE); - mutex_unlock(&acomp_ctx->mutex); if (src != acomp_ctx->buffer) zpool_unmap_handle(zpool, entry->handle); + acomp_ctx_put_unlock(acomp_ctx); } /********************************* @@ -1156,7 +1192,7 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o /* * It's safe to drop the lock here because we return either - * LRU_REMOVED_RETRY or LRU_RETRY. + * LRU_REMOVED_RETRY, LRU_RETRY or LRU_STOP. */ spin_unlock(&l->lock); diff --git a/net/802/psnap.c b/net/802/psnap.c index fca9d454905f..389df460c8c4 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -55,11 +55,11 @@ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, goto drop; rcu_read_lock(); - proto = find_snap_client(skb_transport_header(skb)); + proto = find_snap_client(skb->data); if (proto) { /* Pass the frame on. */ - skb->transport_header += 5; skb_pull_rcsum(skb, 5); + skb_reset_transport_header(skb); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } rcu_read_unlock(); diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 9fa0b246902b..05cbb3c227c5 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -432,49 +432,18 @@ static struct atalk_addr *__aarp_proxy_find(struct net_device *dev, return a ? sa : NULL; } -/* - * Probe a Phase 1 device or a device that requires its Net:Node to - * be set via an ioctl. - */ -static void aarp_send_probe_phase1(struct atalk_iface *iface) -{ - struct ifreq atreq; - struct sockaddr_at *sa = (struct sockaddr_at *)&atreq.ifr_addr; - const struct net_device_ops *ops = iface->dev->netdev_ops; - - sa->sat_addr.s_node = iface->address.s_node; - sa->sat_addr.s_net = ntohs(iface->address.s_net); - - /* We pass the Net:Node to the drivers/cards by a Device ioctl. */ - if (!(ops->ndo_do_ioctl(iface->dev, &atreq, SIOCSIFADDR))) { - ops->ndo_do_ioctl(iface->dev, &atreq, SIOCGIFADDR); - if (iface->address.s_net != htons(sa->sat_addr.s_net) || - iface->address.s_node != sa->sat_addr.s_node) - iface->status |= ATIF_PROBE_FAIL; - - iface->address.s_net = htons(sa->sat_addr.s_net); - iface->address.s_node = sa->sat_addr.s_node; - } -} - - void aarp_probe_network(struct atalk_iface *atif) { - if (atif->dev->type == ARPHRD_LOCALTLK || - atif->dev->type == ARPHRD_PPP) - aarp_send_probe_phase1(atif); - else { - unsigned int count; + unsigned int count; - for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) { - aarp_send_probe(atif->dev, &atif->address); + for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) { + aarp_send_probe(atif->dev, &atif->address); - /* Defer 1/10th */ - msleep(100); + /* Defer 1/10th */ + msleep(100); - if (atif->status & ATIF_PROBE_FAIL) - break; - } + if (atif->status & ATIF_PROBE_FAIL) + break; } } diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index d6f9fae06a9d..aa6c714892ec 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -467,7 +467,7 @@ einval_put: goto out_put; } -static void ax25_fillin_cb_from_dev(ax25_cb *ax25, ax25_dev *ax25_dev) +static void ax25_fillin_cb_from_dev(ax25_cb *ax25, const ax25_dev *ax25_dev) { ax25->rtt = msecs_to_jiffies(ax25_dev->values[AX25_VALUES_T1]) / 2; ax25->t1 = msecs_to_jiffies(ax25_dev->values[AX25_VALUES_T1]); @@ -677,22 +677,22 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname, break; } - rtnl_lock(); - dev = __dev_get_by_name(&init_net, devname); + rcu_read_lock(); + dev = dev_get_by_name_rcu(&init_net, devname); if (!dev) { - rtnl_unlock(); + rcu_read_unlock(); res = -ENODEV; break; } ax25->ax25_dev = ax25_dev_ax25dev(dev); if (!ax25->ax25_dev) { - rtnl_unlock(); + rcu_read_unlock(); res = -ENODEV; break; } ax25_fillin_cb(ax25, ax25->ax25_dev); - rtnl_unlock(); + rcu_read_unlock(); break; default: diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 9efd6690b344..3733c0254a50 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -90,7 +90,7 @@ void ax25_dev_device_up(struct net_device *dev) spin_lock_bh(&ax25_dev_lock); list_add(&ax25_dev->list, &ax25_dev_list); - dev->ax25_ptr = ax25_dev; + rcu_assign_pointer(dev->ax25_ptr, ax25_dev); spin_unlock_bh(&ax25_dev_lock); ax25_register_dev_sysctl(ax25_dev); @@ -125,7 +125,7 @@ void ax25_dev_device_down(struct net_device *dev) } } - dev->ax25_ptr = NULL; + RCU_INIT_POINTER(dev->ax25_ptr, NULL); spin_unlock_bh(&ax25_dev_lock); netdev_put(dev, &ax25_dev->dev_tracker); ax25_dev_put(ax25_dev); diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c index 36249776c021..215d4ccf12b9 100644 --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -122,6 +122,7 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) if (dev == NULL) dev = skb->dev; + rcu_read_lock(); if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) { kfree_skb(skb); goto put; @@ -202,7 +203,7 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) ax25_queue_xmit(skb, dev); put: - + rcu_read_unlock(); ax25_route_lock_unuse(); return NETDEV_TX_OK; } diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c index 3db76d2470e9..8bca2ace98e5 100644 --- a/net/ax25/ax25_out.c +++ b/net/ax25/ax25_out.c @@ -39,10 +39,14 @@ ax25_cb *ax25_send_frame(struct sk_buff *skb, int paclen, const ax25_address *sr * specified. */ if (paclen == 0) { - if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) + rcu_read_lock(); + ax25_dev = ax25_dev_ax25dev(dev); + if (!ax25_dev) { + rcu_read_unlock(); return NULL; - + } paclen = ax25_dev->values[AX25_VALUES_PACLEN]; + rcu_read_unlock(); } /* @@ -53,13 +57,19 @@ ax25_cb *ax25_send_frame(struct sk_buff *skb, int paclen, const ax25_address *sr return ax25; /* It already existed */ } - if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) + rcu_read_lock(); + ax25_dev = ax25_dev_ax25dev(dev); + if (!ax25_dev) { + rcu_read_unlock(); return NULL; + } - if ((ax25 = ax25_create_cb()) == NULL) + if ((ax25 = ax25_create_cb()) == NULL) { + rcu_read_unlock(); return NULL; - + } ax25_fillin_cb(ax25, ax25_dev); + rcu_read_unlock(); ax25->source_addr = *src; ax25->dest_addr = *dest; @@ -358,7 +368,9 @@ void ax25_queue_xmit(struct sk_buff *skb, struct net_device *dev) { unsigned char *ptr; + rcu_read_lock(); skb->protocol = ax25_type_trans(skb, ax25_fwd_dev(dev)); + rcu_read_unlock(); ptr = skb_push(skb, 1); *ptr = 0x00; /* KISS */ diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index b7c4d656a94b..69de75db0c9c 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -406,6 +406,7 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr) ax25_route_lock_unuse(); return -EHOSTUNREACH; } + rcu_read_lock(); if ((ax25->ax25_dev = ax25_dev_ax25dev(ax25_rt->dev)) == NULL) { err = -EHOSTUNREACH; goto put; @@ -442,6 +443,7 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr) } put: + rcu_read_unlock(); ax25_route_lock_unuse(); return err; } diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 449faf5a5487..8c814f790d17 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -38,7 +39,6 @@ #include #include #include -#include #include #include @@ -47,7 +47,6 @@ #include "log.h" #include "netlink.h" #include "originator.h" -#include "soft-interface.h" #include "translation-table.h" static const u8 batadv_announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; @@ -2233,25 +2232,16 @@ int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; - struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hashtable *hash; struct batadv_priv *bat_priv; int bucket = cb->args[0]; int idx = cb->args[1]; - int ifindex; int ret = 0; - ifindex = batadv_netlink_get_ifindex(cb->nlh, - BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); hash = bat_priv->bla.claim_hash; @@ -2403,25 +2393,16 @@ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; - struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hashtable *hash; struct batadv_priv *bat_priv; int bucket = cb->args[0]; int idx = cb->args[1]; - int ifindex; int ret = 0; - ifindex = batadv_netlink_get_ifindex(cb->nlh, - BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); hash = bat_priv->bla.backbone_hash; diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 801eff8a40e5..e5a07152d4ec 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -7,11 +7,11 @@ #include "distributed-arp-table.h" #include "main.h" -#include #include #include #include #include +#include #include #include #include @@ -32,11 +32,11 @@ #include #include #include +#include #include #include #include #include -#include #include #include "bridge_loop_avoidance.h" @@ -46,7 +46,6 @@ #include "netlink.h" #include "originator.h" #include "send.h" -#include "soft-interface.h" #include "translation-table.h" #include "tvlv.h" @@ -937,25 +936,16 @@ int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; - struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hashtable *hash; struct batadv_priv *bat_priv; int bucket = cb->args[0]; int idx = cb->args[1]; - int ifindex; int ret = 0; - ifindex = batadv_netlink_get_ifindex(cb->nlh, - BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); hash = bat_priv->dat.hash; diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 0ddd8b4b3f4c..f68e34ed1f62 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -31,7 +32,6 @@ #include #include #include -#include #include #include @@ -40,7 +40,6 @@ #include "netlink.h" #include "originator.h" #include "routing.h" -#include "soft-interface.h" #include "translation-table.h" /* These are the offsets of the "hw type" and "hw address length" in the dhcp @@ -502,22 +501,13 @@ void batadv_gw_node_free(struct batadv_priv *bat_priv) int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; - struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_priv *bat_priv; - int ifindex; int ret; - ifindex = batadv_netlink_get_ifindex(cb->nlh, - BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 8e0f44c71696..333e947afcce 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -637,6 +637,13 @@ unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len) vhdr = (struct vlan_ethhdr *)(skb->data + header_len); vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; + + /* VID 0 is only used to indicate "priority tag" frames which only + * contain priority information and no VID. + */ + if (vid == 0) + return BATADV_NO_FLAGS; + vid |= BATADV_VLAN_HAS_TAG; return vid; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 97ea71a052f8..964f3088af5b 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -7,13 +7,13 @@ #ifndef _NET_BATMAN_ADV_MAIN_H_ #define _NET_BATMAN_ADV_MAIN_H_ -#define BATADV_DRIVER_AUTHOR "Marek Lindner , " \ +#define BATADV_DRIVER_AUTHOR "Marek Lindner , " \ "Simon Wunderlich " #define BATADV_DRIVER_DESC "B.A.T.M.A.N. advanced" #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2024.3" +#define BATADV_SOURCE_VERSION "2025.0" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 14088c4ff2f6..d95c418484fa 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -46,7 +47,6 @@ #include #include #include -#include #include #include @@ -56,7 +56,6 @@ #include "log.h" #include "netlink.h" #include "send.h" -#include "soft-interface.h" #include "translation-table.h" #include "tvlv.h" @@ -2104,21 +2103,13 @@ batadv_mcast_netlink_get_primary(struct netlink_callback *cb, struct batadv_hard_iface **primary_if) { struct batadv_hard_iface *hard_iface = NULL; - struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_priv *bat_priv; - int ifindex; int ret = 0; - ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 9362cd9d6f3d..eefba5600ded 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -158,8 +158,7 @@ static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { * * Return: interface index, or 0. */ -int -batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) +static int batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) { struct nlattr *attr = nlmsg_find_attr(nlh, GENL_HDRLEN, attrtype); @@ -881,14 +880,14 @@ static int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv, } /** - * batadv_netlink_get_hardif() - Get hardif attributes + * batadv_netlink_cmd_get_hardif() - Get hardif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ -static int batadv_netlink_get_hardif(struct sk_buff *skb, - struct genl_info *info) +static int batadv_netlink_cmd_get_hardif(struct sk_buff *skb, + struct genl_info *info) { struct batadv_hard_iface *hard_iface = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; @@ -964,28 +963,16 @@ static int batadv_netlink_set_hardif(struct sk_buff *skb, static int batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb) { - struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hard_iface *hard_iface; struct batadv_priv *bat_priv; - int ifindex; int portid = NETLINK_CB(cb->skb).portid; int skip = cb->args[0]; int i = 0; - ifindex = batadv_netlink_get_ifindex(cb->nlh, - BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface) - return -ENODEV; - - if (!batadv_softif_is_valid(soft_iface)) { - dev_put(soft_iface); - return -ENODEV; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); @@ -1150,23 +1137,17 @@ static int batadv_netlink_set_vlan(struct sk_buff *skb, struct genl_info *info) } /** - * batadv_get_softif_from_info() - Retrieve soft interface from genl attributes + * batadv_netlink_get_softif_from_ifindex() - Get soft-iface from ifindex * @net: the applicable net namespace - * @info: receiver information + * @ifindex: index of the soft interface * * Return: Pointer to soft interface (with increased refcnt) on success, error * pointer on error */ static struct net_device * -batadv_get_softif_from_info(struct net *net, struct genl_info *info) +batadv_netlink_get_softif_from_ifindex(struct net *net, int ifindex) { struct net_device *soft_iface; - int ifindex; - - if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) - return ERR_PTR(-EINVAL); - - ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface) @@ -1184,28 +1165,61 @@ err_put_softif: } /** - * batadv_get_hardif_from_info() - Retrieve hardif from genl attributes - * @bat_priv: the bat priv with all the soft interface information + * batadv_netlink_get_softif_from_info() - Get soft-iface from genl attributes * @net: the applicable net namespace * @info: receiver information * + * Return: Pointer to soft interface (with increased refcnt) on success, error + * pointer on error + */ +static struct net_device * +batadv_netlink_get_softif_from_info(struct net *net, struct genl_info *info) +{ + int ifindex; + + if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) + return ERR_PTR(-EINVAL); + + ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); + + return batadv_netlink_get_softif_from_ifindex(net, ifindex); +} + +/** + * batadv_netlink_get_softif() - Retrieve soft interface from netlink callback + * @cb: callback structure containing arguments + * + * Return: Pointer to soft interface (with increased refcnt) on success, error + * pointer on error + */ +struct net_device *batadv_netlink_get_softif(struct netlink_callback *cb) +{ + int ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return ERR_PTR(-ENONET); + + return batadv_netlink_get_softif_from_ifindex(sock_net(cb->skb->sk), + ifindex); +} + +/** + * batadv_netlink_get_hardif_from_ifindex() - Get hard-iface from ifindex + * @bat_priv: the bat priv with all the soft interface information + * @net: the applicable net namespace + * @ifindex: index of the hard interface + * * Return: Pointer to hard interface (with increased refcnt) on success, error * pointer on error */ static struct batadv_hard_iface * -batadv_get_hardif_from_info(struct batadv_priv *bat_priv, struct net *net, - struct genl_info *info) +batadv_netlink_get_hardif_from_ifindex(struct batadv_priv *bat_priv, + struct net *net, int ifindex) { struct batadv_hard_iface *hard_iface; struct net_device *hard_dev; - unsigned int hardif_index; - if (!info->attrs[BATADV_ATTR_HARD_IFINDEX]) - return ERR_PTR(-EINVAL); - - hardif_index = nla_get_u32(info->attrs[BATADV_ATTR_HARD_IFINDEX]); - - hard_dev = dev_get_by_index(net, hardif_index); + hard_dev = dev_get_by_index(net, ifindex); if (!hard_dev) return ERR_PTR(-ENODEV); @@ -1229,6 +1243,51 @@ err_put_harddev: return ERR_PTR(-EINVAL); } +/** + * batadv_netlink_get_hardif_from_info() - Get hard-iface from genl attributes + * @bat_priv: the bat priv with all the soft interface information + * @net: the applicable net namespace + * @info: receiver information + * + * Return: Pointer to hard interface (with increased refcnt) on success, error + * pointer on error + */ +static struct batadv_hard_iface * +batadv_netlink_get_hardif_from_info(struct batadv_priv *bat_priv, + struct net *net, struct genl_info *info) +{ + int ifindex; + + if (!info->attrs[BATADV_ATTR_HARD_IFINDEX]) + return ERR_PTR(-EINVAL); + + ifindex = nla_get_u32(info->attrs[BATADV_ATTR_HARD_IFINDEX]); + + return batadv_netlink_get_hardif_from_ifindex(bat_priv, net, ifindex); +} + +/** + * batadv_netlink_get_hardif() - Retrieve hard interface from netlink callback + * @bat_priv: the bat priv with all the soft interface information + * @cb: callback structure containing arguments + * + * Return: Pointer to hard interface (with increased refcnt) on success, error + * pointer on error + */ +struct batadv_hard_iface * +batadv_netlink_get_hardif(struct batadv_priv *bat_priv, + struct netlink_callback *cb) +{ + int ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_HARD_IFINDEX); + if (!ifindex) + return ERR_PTR(-ENONET); + + return batadv_netlink_get_hardif_from_ifindex(bat_priv, + sock_net(cb->skb->sk), + ifindex); +} + /** * batadv_get_vlan_from_info() - Retrieve vlan from genl attributes * @bat_priv: the bat priv with all the soft interface information @@ -1288,7 +1347,7 @@ static int batadv_pre_doit(const struct genl_split_ops *ops, return -EINVAL; if (ops->internal_flags & BATADV_FLAG_NEED_MESH) { - soft_iface = batadv_get_softif_from_info(net, info); + soft_iface = batadv_netlink_get_softif_from_info(net, info); if (IS_ERR(soft_iface)) return PTR_ERR(soft_iface); @@ -1297,7 +1356,8 @@ static int batadv_pre_doit(const struct genl_split_ops *ops, } if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF) { - hard_iface = batadv_get_hardif_from_info(bat_priv, net, info); + hard_iface = batadv_netlink_get_hardif_from_info(bat_priv, net, + info); if (IS_ERR(hard_iface)) { ret = PTR_ERR(hard_iface); goto err_put_softif; @@ -1390,7 +1450,7 @@ static const struct genl_small_ops batadv_netlink_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .dumpit = batadv_netlink_dump_hardif, - .doit = batadv_netlink_get_hardif, + .doit = batadv_netlink_cmd_get_hardif, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_HARDIF, }, diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index 876d2806a67d..2097c2ae98f1 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -15,7 +15,10 @@ void batadv_netlink_register(void); void batadv_netlink_unregister(void); -int batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype); +struct net_device *batadv_netlink_get_softif(struct netlink_callback *cb); +struct batadv_hard_iface * +batadv_netlink_get_hardif(struct batadv_priv *bat_priv, + struct netlink_callback *cb); int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst, u8 result, u32 test_time, u64 total_bytes, diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 8f6dd2c6ee41..bcc2e20e0cd6 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -26,9 +27,7 @@ #include #include #include -#include #include -#include #include "bat_algo.h" #include "distributed-arp-table.h" @@ -41,7 +40,6 @@ #include "netlink.h" #include "network-coding.h" #include "routing.h" -#include "soft-interface.h" #include "translation-table.h" /* hash class keys */ @@ -755,64 +753,48 @@ batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node, */ int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb) { - struct net *net = sock_net(cb->skb->sk); + struct batadv_hard_iface *primary_if, *hard_iface; struct net_device *soft_iface; - struct net_device *hard_iface = NULL; - struct batadv_hard_iface *hardif = BATADV_IF_DEFAULT; struct batadv_priv *bat_priv; - struct batadv_hard_iface *primary_if = NULL; int ret; - int ifindex, hard_ifindex; - ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; - goto out; + goto out_put_soft_iface; } - hard_ifindex = batadv_netlink_get_ifindex(cb->nlh, - BATADV_ATTR_HARD_IFINDEX); - if (hard_ifindex) { - hard_iface = dev_get_by_index(net, hard_ifindex); - if (hard_iface) - hardif = batadv_hardif_get_by_netdev(hard_iface); - - if (!hardif) { - ret = -ENODEV; - goto out; - } - - if (hardif->soft_iface != soft_iface) { - ret = -ENOENT; - goto out; - } + hard_iface = batadv_netlink_get_hardif(bat_priv, cb); + if (IS_ERR(hard_iface) && PTR_ERR(hard_iface) != -ENONET) { + ret = PTR_ERR(hard_iface); + goto out_put_primary_if; + } else if (IS_ERR(hard_iface)) { + /* => PTR_ERR(hard_iface) == -ENONET + * => no hard-iface given, ok + */ + hard_iface = BATADV_IF_DEFAULT; } if (!bat_priv->algo_ops->neigh.dump) { ret = -EOPNOTSUPP; - goto out; + goto out_put_hard_iface; } - bat_priv->algo_ops->neigh.dump(msg, cb, bat_priv, hardif); + bat_priv->algo_ops->neigh.dump(msg, cb, bat_priv, hard_iface); ret = msg->len; - out: - batadv_hardif_put(hardif); - dev_put(hard_iface); +out_put_hard_iface: + batadv_hardif_put(hard_iface); +out_put_primary_if: batadv_hardif_put(primary_if); +out_put_soft_iface: dev_put(soft_iface); return ret; @@ -1342,64 +1324,48 @@ static void batadv_purge_orig(struct work_struct *work) */ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) { - struct net *net = sock_net(cb->skb->sk); + struct batadv_hard_iface *primary_if, *hard_iface; struct net_device *soft_iface; - struct net_device *hard_iface = NULL; - struct batadv_hard_iface *hardif = BATADV_IF_DEFAULT; struct batadv_priv *bat_priv; - struct batadv_hard_iface *primary_if = NULL; int ret; - int ifindex, hard_ifindex; - ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; - goto out; + goto out_put_soft_iface; } - hard_ifindex = batadv_netlink_get_ifindex(cb->nlh, - BATADV_ATTR_HARD_IFINDEX); - if (hard_ifindex) { - hard_iface = dev_get_by_index(net, hard_ifindex); - if (hard_iface) - hardif = batadv_hardif_get_by_netdev(hard_iface); - - if (!hardif) { - ret = -ENODEV; - goto out; - } - - if (hardif->soft_iface != soft_iface) { - ret = -ENOENT; - goto out; - } + hard_iface = batadv_netlink_get_hardif(bat_priv, cb); + if (IS_ERR(hard_iface) && PTR_ERR(hard_iface) != -ENONET) { + ret = PTR_ERR(hard_iface); + goto out_put_primary_if; + } else if (IS_ERR(hard_iface)) { + /* => PTR_ERR(hard_iface) == -ENONET + * => no hard-iface given, ok + */ + hard_iface = BATADV_IF_DEFAULT; } if (!bat_priv->algo_ops->orig.dump) { ret = -EOPNOTSUPP; - goto out; + goto out_put_hard_iface; } - bat_priv->algo_ops->orig.dump(msg, cb, bat_priv, hardif); + bat_priv->algo_ops->orig.dump(msg, cb, bat_priv, hard_iface); ret = msg->len; - out: - batadv_hardif_put(hardif); - dev_put(hard_iface); +out_put_hard_iface: + batadv_hardif_put(hard_iface); +out_put_primary_if: batadv_hardif_put(primary_if); +out_put_soft_iface: dev_put(soft_iface); return ret; diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 2758aba47a2f..822d788a5f86 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -637,6 +637,14 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto, if (proto != htons(ETH_P_8021Q)) return -EINVAL; + /* VID 0 is only used to indicate "priority tag" frames which only + * contain priority information and no VID. No management structures + * should be created for this VID and it should be handled like an + * untagged frame. + */ + if (vid == 0) + return 0; + vid |= BATADV_VLAN_HAS_TAG; /* if a new vlan is getting created and it already exists, it means that @@ -684,6 +692,12 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto, if (proto != htons(ETH_P_8021Q)) return -EINVAL; + /* "priority tag" frames are handled like "untagged" frames + * and no softif_vlan needs to be destroyed + */ + if (vid == 0) + return 0; + vlan = batadv_softif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG); if (!vlan) return -ENOENT; @@ -783,13 +797,13 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); atomic_set(&bat_priv->bcast_seqno, 1); atomic_set(&bat_priv->tt.vn, 0); - atomic_set(&bat_priv->tt.local_changes, 0); atomic_set(&bat_priv->tt.ogm_append_cnt, 0); #ifdef CONFIG_BATMAN_ADV_BLA atomic_set(&bat_priv->bla.num_requests, 0); #endif atomic_set(&bat_priv->tp_num, 0); + WRITE_ONCE(bat_priv->tt.local_changes, 0); bat_priv->tt.last_changeset = NULL; bat_priv->tt.last_changeset_len = 0; bat_priv->isolation_mark = 0; diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 760d51fdbdf6..3c0a14a582e4 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -39,7 +40,6 @@ #include #include #include -#include #include #include @@ -423,8 +423,8 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv, struct batadv_tt_change_node *tt_change_node, *entry, *safe; struct batadv_tt_common_entry *common = &tt_local_entry->common; u8 flags = common->flags | event_flags; - bool event_removed = false; bool del_op_requested, del_op_entry; + size_t changes; tt_change_node = kmem_cache_alloc(batadv_tt_change_cache, GFP_ATOMIC); if (!tt_change_node) @@ -438,51 +438,45 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv, del_op_requested = flags & BATADV_TT_CLIENT_DEL; - /* check for ADD+DEL or DEL+ADD events */ + /* check for ADD+DEL, DEL+ADD, ADD+ADD or DEL+DEL events */ spin_lock_bh(&bat_priv->tt.changes_list_lock); + changes = READ_ONCE(bat_priv->tt.local_changes); list_for_each_entry_safe(entry, safe, &bat_priv->tt.changes_list, list) { if (!batadv_compare_eth(entry->change.addr, common->addr)) continue; - /* DEL+ADD in the same orig interval have no effect and can be - * removed to avoid silly behaviour on the receiver side. The - * other way around (ADD+DEL) can happen in case of roaming of - * a client still in the NEW state. Roaming of NEW clients is - * now possible due to automatically recognition of "temporary" - * clients - */ del_op_entry = entry->change.flags & BATADV_TT_CLIENT_DEL; - if (!del_op_requested && del_op_entry) - goto del; - if (del_op_requested && !del_op_entry) - goto del; - - /* this is a second add in the same originator interval. It - * means that flags have been changed: update them! - */ - if (!del_op_requested && !del_op_entry) + if (del_op_requested != del_op_entry) { + /* DEL+ADD in the same orig interval have no effect and + * can be removed to avoid silly behaviour on the + * receiver side. The other way around (ADD+DEL) can + * happen in case of roaming of a client still in the + * NEW state. Roaming of NEW clients is now possible due + * to automatically recognition of "temporary" clients + */ + list_del(&entry->list); + kmem_cache_free(batadv_tt_change_cache, entry); + changes--; + } else { + /* this is a second add or del in the same originator + * interval. It could mean that flags have been changed + * (e.g. double add): update them + */ entry->change.flags = flags; + } - continue; -del: - list_del(&entry->list); - kmem_cache_free(batadv_tt_change_cache, entry); kmem_cache_free(batadv_tt_change_cache, tt_change_node); - event_removed = true; - goto unlock; + goto update_changes; } /* track the change in the OGMinterval list */ list_add_tail(&tt_change_node->list, &bat_priv->tt.changes_list); + changes++; -unlock: +update_changes: + WRITE_ONCE(bat_priv->tt.local_changes, changes); spin_unlock_bh(&bat_priv->tt.changes_list_lock); - - if (event_removed) - atomic_dec(&bat_priv->tt.local_changes); - else - atomic_inc(&bat_priv->tt.local_changes); } /** @@ -952,7 +946,7 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) size_t tt_extra_len = 0; u16 tvlv_len; - tt_diff_entries_num = atomic_read(&bat_priv->tt.local_changes); + tt_diff_entries_num = READ_ONCE(bat_priv->tt.local_changes); tt_diff_len = batadv_tt_len(tt_diff_entries_num); /* if we have too many changes for one packet don't send any @@ -979,7 +973,7 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) goto container_register; spin_lock_bh(&bat_priv->tt.changes_list_lock); - atomic_set(&bat_priv->tt.local_changes, 0); + WRITE_ONCE(bat_priv->tt.local_changes, 0); list_for_each_entry_safe(entry, safe, &bat_priv->tt.changes_list, list) { @@ -1136,26 +1130,18 @@ batadv_tt_local_dump_bucket(struct sk_buff *msg, u32 portid, */ int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb) { - struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; struct batadv_hashtable *hash; int ret; - int ifindex; int bucket = cb->args[0]; int idx = cb->args[1]; int portid = NETLINK_CB(cb->skb).portid; - ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); @@ -1395,7 +1381,7 @@ static void batadv_tt_changes_list_free(struct batadv_priv *bat_priv) kmem_cache_free(batadv_tt_change_cache, entry); } - atomic_set(&bat_priv->tt.local_changes, 0); + WRITE_ONCE(bat_priv->tt.local_changes, 0); spin_unlock_bh(&bat_priv->tt.changes_list_lock); } @@ -1911,28 +1897,20 @@ batadv_tt_global_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, */ int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb) { - struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; struct batadv_hashtable *hash; struct hlist_head *head; int ret; - int ifindex; int bucket = cb->args[0]; int idx = cb->args[1]; int sub = cb->args[2]; int portid = NETLINK_CB(cb->skb).portid; - ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); - if (!ifindex) - return -EINVAL; - - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } + soft_iface = batadv_netlink_get_softif(cb); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); @@ -3656,7 +3634,7 @@ static void batadv_tt_local_commit_changes_nolock(struct batadv_priv *bat_priv) { lockdep_assert_held(&bat_priv->tt.commit_lock); - if (atomic_read(&bat_priv->tt.local_changes) < 1) { + if (READ_ONCE(bat_priv->tt.local_changes) == 0) { if (!batadv_atomic_dec_not_zero(&bat_priv->tt.ogm_append_cnt)) batadv_tt_tvlv_container_update(bat_priv); return; diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 04f6398b3a40..f491bff8c51b 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1022,7 +1022,7 @@ struct batadv_priv_tt { atomic_t ogm_append_cnt; /** @local_changes: changes registered in an originator interval */ - atomic_t local_changes; + size_t local_changes; /** * @changes_list: tracks tt local changes within an originator interval @@ -1044,7 +1044,7 @@ struct batadv_priv_tt { */ struct list_head roam_list; - /** @changes_list_lock: lock protecting changes_list */ + /** @changes_list_lock: lock protecting changes_list & local_changes */ spinlock_t changes_list_lock; /** @req_list_lock: lock protecting req_list */ diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 18ab5628f85a..e7ec12437c8b 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1456,8 +1456,8 @@ static void hci_cmd_timeout(struct work_struct *work) bt_dev_err(hdev, "command tx timeout"); } - if (hdev->cmd_timeout) - hdev->cmd_timeout(hdev); + if (hdev->reset) + hdev->reset(hdev); atomic_set(&hdev->cmd_cnt, 1); queue_work(hdev->workqueue, &hdev->cmd_work); @@ -2181,26 +2181,6 @@ int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, return 0; } -int hci_bdaddr_list_del_with_flags(struct list_head *list, bdaddr_t *bdaddr, - u8 type) -{ - struct bdaddr_list_with_flags *entry; - - if (!bacmp(bdaddr, BDADDR_ANY)) { - hci_bdaddr_list_clear(list); - return 0; - } - - entry = hci_bdaddr_list_lookup_with_flags(list, bdaddr, type); - if (!entry) - return -ENOENT; - - list_del(&entry->list); - kfree(entry); - - return 0; -} - /* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index c86f4e42e69c..dd770ef5ec36 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1031,9 +1031,9 @@ static bool adv_use_rpa(struct hci_dev *hdev, uint32_t flags) static int hci_set_random_addr_sync(struct hci_dev *hdev, bdaddr_t *rpa) { - /* If we're advertising or initiating an LE connection we can't - * go ahead and change the random address at this time. This is - * because the eventual initiator address used for the + /* If a random_addr has been set we're advertising or initiating an LE + * connection we can't go ahead and change the random address at this + * time. This is because the eventual initiator address used for the * subsequently created connection will be undefined (some * controllers use the new address and others the one we had * when the operation started). @@ -1041,8 +1041,9 @@ static int hci_set_random_addr_sync(struct hci_dev *hdev, bdaddr_t *rpa) * In this kind of scenario skip the update and let the random * address be updated at the next cycle. */ - if (hci_dev_test_flag(hdev, HCI_LE_ADV) || - hci_lookup_le_connect(hdev)) { + if (bacmp(&hdev->random_addr, BDADDR_ANY) && + (hci_dev_test_flag(hdev, HCI_LE_ADV) || + hci_lookup_le_connect(hdev))) { bt_dev_dbg(hdev, "Deferring random address update"); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); return 0; @@ -1065,7 +1066,7 @@ int hci_update_random_address_sync(struct hci_dev *hdev, bool require_privacy, /* If Controller supports LL Privacy use own address type is * 0x03 */ - if (use_ll_privacy(hdev)) + if (ll_privacy_capable(hdev)) *own_addr_type = ADDR_LE_DEV_RANDOM_RESOLVED; else *own_addr_type = ADDR_LE_DEV_RANDOM; @@ -1785,30 +1786,6 @@ int hci_remove_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance, HCI_CMD_TIMEOUT, sk); } -static int remove_ext_adv_sync(struct hci_dev *hdev, void *data) -{ - struct adv_info *adv = data; - u8 instance = 0; - - if (adv) - instance = adv->instance; - - return hci_remove_ext_adv_instance_sync(hdev, instance, NULL); -} - -int hci_remove_ext_adv_instance(struct hci_dev *hdev, u8 instance) -{ - struct adv_info *adv = NULL; - - if (instance) { - adv = hci_find_adv_instance(hdev, instance); - if (!adv) - return -EINVAL; - } - - return hci_cmd_sync_queue(hdev, remove_ext_adv_sync, adv, NULL); -} - int hci_le_terminate_big_sync(struct hci_dev *hdev, u8 handle, u8 reason) { struct hci_cp_le_term_big cp; @@ -2161,7 +2138,7 @@ static int hci_le_set_scan_enable_sync(struct hci_dev *hdev, u8 val, static int hci_le_set_addr_resolution_enable_sync(struct hci_dev *hdev, u8 val) { - if (!use_ll_privacy(hdev)) + if (!ll_privacy_capable(hdev)) return 0; /* If controller is not/already resolving we are done. */ @@ -2253,7 +2230,7 @@ static int hci_le_del_resolve_list_sync(struct hci_dev *hdev, struct hci_cp_le_del_from_resolv_list cp; struct bdaddr_list_with_irk *entry; - if (!use_ll_privacy(hdev)) + if (!ll_privacy_capable(hdev)) return 0; /* Check if the IRK has been programmed */ @@ -2318,7 +2295,7 @@ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, struct bdaddr_list_with_irk *entry; struct hci_conn_params *p; - if (!use_ll_privacy(hdev)) + if (!ll_privacy_capable(hdev)) return 0; /* Attempt to program local identity address, type and irk if params is @@ -2331,7 +2308,8 @@ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, hci_copy_identity_address(hdev, &cp.bdaddr, &cp.bdaddr_type); memcpy(cp.peer_irk, hdev->irk, 16); goto done; - } + } else if (!(params->flags & HCI_CONN_FLAG_ADDRESS_RESOLUTION)) + return 0; irk = hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type); if (!irk) @@ -2378,6 +2356,10 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, struct hci_cp_le_set_privacy_mode cp; struct smp_irk *irk; + if (!ll_privacy_capable(hdev) || + !(params->flags & HCI_CONN_FLAG_ADDRESS_RESOLUTION)) + return 0; + /* If device privacy mode has already been set there is nothing to do */ if (params->privacy_mode == HCI_DEVICE_PRIVACY) return 0; @@ -2427,11 +2409,6 @@ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, if (*num_entries >= hdev->le_accept_list_size) return -ENOSPC; - /* Accept list can not be used with RPAs */ - if (!use_ll_privacy(hdev) && - hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type)) - return -EINVAL; - /* Attempt to program the device in the resolving list first to avoid * having to rollback in case it fails since the resolving list is * dynamic it can probably be smaller than the accept list. @@ -2566,7 +2543,7 @@ static int hci_pause_addr_resolution(struct hci_dev *hdev) { int err; - if (!use_ll_privacy(hdev)) + if (!ll_privacy_capable(hdev)) return 0; if (!hci_dev_test_flag(hdev, HCI_LL_RPA_RESOLUTION)) @@ -2670,12 +2647,12 @@ static int hci_le_clear_accept_list_sync(struct hci_dev *hdev) * * Update is done using the following sequence: * - * use_ll_privacy((Disable Advertising) -> Disable Resolving List) -> + * ll_privacy_capable((Disable Advertising) -> Disable Resolving List) -> * Remove Devices From Accept List -> - * (has IRK && use_ll_privacy(Remove Devices From Resolving List))-> + * (has IRK && ll_privacy_capable(Remove Devices From Resolving List))-> * Add Devices to Accept List -> - * (has IRK && use_ll_privacy(Remove Devices From Resolving List)) -> - * use_ll_privacy(Enable Resolving List -> (Enable Advertising)) -> + * (has IRK && ll_privacy_capable(Remove Devices From Resolving List)) -> + * ll_privacy_capable(Enable Resolving List -> (Enable Advertising)) -> * Enable Scanning * * In case of failure advertising shall be restored to its original state and @@ -2696,7 +2673,7 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) /* Pause advertising if resolving list can be used as controllers * cannot accept resolving list modifications while advertising. */ - if (use_ll_privacy(hdev)) { + if (ll_privacy_capable(hdev)) { err = hci_pause_advertising_sync(hdev); if (err) { bt_dev_err(hdev, "pause advertising failed: %d", err); @@ -2841,7 +2818,7 @@ done: bt_dev_err(hdev, "Unable to enable LL privacy: %d", err); /* Resume advertising if it was paused */ - if (use_ll_privacy(hdev)) + if (ll_privacy_capable(hdev)) hci_resume_advertising_sync(hdev); /* Select filter policy to use accept list */ @@ -3099,7 +3076,7 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) * If there are devices to scan: * * Disable Scanning -> Update Accept List -> - * use_ll_privacy((Disable Advertising) -> Disable Resolving List -> + * ll_privacy_capable((Disable Advertising) -> Disable Resolving List -> * Update Resolving List -> Enable Resolving List -> (Enable Advertising)) -> * Enable Scanning * @@ -3453,7 +3430,7 @@ int hci_update_name_sync(struct hci_dev *hdev) * * HCI_SSP_ENABLED(Enable SSP) * HCI_LE_ENABLED(Enable LE) - * HCI_LE_ENABLED(use_ll_privacy(Add local IRK to Resolving List) -> + * HCI_LE_ENABLED(ll_privacy_capable(Add local IRK to Resolving List) -> * Update adv data) * Enable Authentication * lmp_bredr_capable(Set Fast Connectable -> Set Scan Type -> Set Class -> @@ -4228,6 +4205,14 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev) if (use_enhanced_conn_complete(hdev)) events[1] |= 0x02; /* LE Enhanced Connection Complete */ + /* Mark Device Privacy if Privacy Mode is supported */ + if (privacy_mode_capable(hdev)) + hdev->conn_flags |= HCI_CONN_FLAG_DEVICE_PRIVACY; + + /* Mark Address Resolution if LL Privacy is supported */ + if (ll_privacy_capable(hdev)) + hdev->conn_flags |= HCI_CONN_FLAG_ADDRESS_RESOLUTION; + /* If the controller supports Extended Scanner Filter * Policies, enable the corresponding event. */ @@ -5384,7 +5369,7 @@ int hci_stop_discovery_sync(struct hci_dev *hdev) } /* Resume advertising if it was paused */ - if (use_ll_privacy(hdev)) + if (ll_privacy_capable(hdev)) hci_resume_advertising_sync(hdev); /* No further actions needed for LE-only discovery */ @@ -5896,7 +5881,7 @@ static int hci_active_scan_sync(struct hci_dev *hdev, uint16_t interval) failed: /* Resume advertising if it was paused */ - if (use_ll_privacy(hdev)) + if (ll_privacy_capable(hdev)) hci_resume_advertising_sync(hdev); /* Resume passive scanning */ @@ -6672,7 +6657,7 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, /* If Controller supports LL Privacy use own address type is * 0x03 */ - if (use_ll_privacy(hdev)) + if (ll_privacy_capable(hdev)) *own_addr_type = ADDR_LE_DEV_RANDOM_RESOLVED; else *own_addr_type = ADDR_LE_DEV_RANDOM; diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 4b54dbbf0729..041ce9adc378 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -90,9 +90,28 @@ static void bt_host_release(struct device *dev) module_put(THIS_MODULE); } +static ssize_t reset_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct hci_dev *hdev = to_hci_dev(dev); + + if (hdev->reset) + hdev->reset(hdev); + + return count; +} +static DEVICE_ATTR_WO(reset); + +static struct attribute *bt_host_attrs[] = { + &dev_attr_reset.attr, + NULL, +}; +ATTRIBUTE_GROUPS(bt_host); + static const struct device_type bt_host = { .name = "host", .release = bt_host_release, + .groups = bt_host_groups, }; void hci_init_sysfs(struct hci_dev *hdev) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 43d0ebe11100..44acddf58a0c 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1281,6 +1281,42 @@ static int iso_sock_accept(struct socket *sock, struct socket *newsock, BT_DBG("new socket %p", ch); + /* A Broadcast Sink might require BIG sync to be terminated + * and re-established multiple times, while keeping the same + * PA sync handle active. To allow this, once all BIS + * connections have been accepted on a PA sync parent socket, + * "reset" socket state, to allow future BIG re-sync procedures. + */ + if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { + /* Iterate through the list of bound BIS indices + * and clear each BIS as they are accepted by the + * user space, one by one. + */ + for (int i = 0; i < iso_pi(sk)->bc_num_bis; i++) { + if (iso_pi(sk)->bc_bis[i] > 0) { + iso_pi(sk)->bc_bis[i] = 0; + iso_pi(sk)->bc_num_bis--; + break; + } + } + + if (iso_pi(sk)->bc_num_bis == 0) { + /* Once the last BIS was accepted, reset parent + * socket parameters to mark that the listening + * process for BIS connections has been completed: + * + * 1. Reset the DEFER setup flag on the parent sk. + * 2. Clear the flag marking that the BIG create + * sync command is pending. + * 3. Transition socket state from BT_LISTEN to + * BT_CONNECTED. + */ + set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); + clear_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags); + sk->sk_state = BT_CONNECTED; + } + } + done: release_sock(sk); return err; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 3d2553dcdb1b..46ea0bee2259 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -710,12 +710,12 @@ static bool l2cap_valid_mtu(struct l2cap_chan *chan, u16 mtu) { switch (chan->scid) { case L2CAP_CID_ATT: - if (mtu < L2CAP_LE_MIN_MTU) + if (mtu && mtu < L2CAP_LE_MIN_MTU) return false; break; default: - if (mtu < L2CAP_DEFAULT_MIN_MTU) + if (mtu && mtu < L2CAP_DEFAULT_MIN_MTU) return false; } @@ -1888,7 +1888,8 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, chan = l2cap_chan_create(); if (!chan) { sk_free(sk); - sock->sk = NULL; + if (sock) + sock->sk = NULL; return NULL; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index b31192d473d0..f53304cb09db 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -210,7 +210,7 @@ static const u16 mgmt_untrusted_events[] = { MGMT_EV_EXP_FEATURE_CHANGED, }; -#define CACHE_TIMEOUT msecs_to_jiffies(2 * 1000) +#define CACHE_TIMEOUT secs_to_jiffies(2) #define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \ "\x00\x00\x00\x00\x00\x00\x00\x00" @@ -4417,12 +4417,6 @@ static const u8 le_simultaneous_roles_uuid[16] = { 0x96, 0x46, 0xc0, 0x42, 0xb5, 0x10, 0x1b, 0x67, }; -/* 15c0a148-c273-11ea-b3de-0242ac130004 */ -static const u8 rpa_resolution_uuid[16] = { - 0x04, 0x00, 0x13, 0xac, 0x42, 0x02, 0xde, 0xb3, - 0xea, 0x11, 0x73, 0xc2, 0x48, 0xa1, 0xc0, 0x15, -}; - /* 6fbaf188-05e0-496a-9885-d6ddfdb4e03e */ static const u8 iso_socket_uuid[16] = { 0x3e, 0xe0, 0xb4, 0xfd, 0xdd, 0xd6, 0x85, 0x98, @@ -4473,17 +4467,6 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, idx++; } - if (hdev && ll_privacy_capable(hdev)) { - if (hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) - flags = BIT(0) | BIT(1); - else - flags = BIT(1); - - memcpy(rp->features[idx].uuid, rpa_resolution_uuid, 16); - rp->features[idx].flags = cpu_to_le32(flags); - idx++; - } - if (hdev && (aosp_has_quality_report(hdev) || hdev->set_quality_report)) { if (hci_dev_test_flag(hdev, HCI_QUALITY_REPORT)) @@ -4540,27 +4523,6 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, return status; } -static int exp_ll_privacy_feature_changed(bool enabled, struct hci_dev *hdev, - struct sock *skip) -{ - struct mgmt_ev_exp_feature_changed ev; - - memset(&ev, 0, sizeof(ev)); - memcpy(ev.uuid, rpa_resolution_uuid, 16); - ev.flags = cpu_to_le32((enabled ? BIT(0) : 0) | BIT(1)); - - // Do we need to be atomic with the conn_flags? - if (enabled && privacy_mode_capable(hdev)) - hdev->conn_flags |= HCI_CONN_FLAG_DEVICE_PRIVACY; - else - hdev->conn_flags &= ~HCI_CONN_FLAG_DEVICE_PRIVACY; - - return mgmt_limited_event(MGMT_EV_EXP_FEATURE_CHANGED, hdev, - &ev, sizeof(ev), - HCI_MGMT_EXP_FEATURE_EVENTS, skip); - -} - static int exp_feature_changed(struct hci_dev *hdev, const u8 *uuid, bool enabled, struct sock *skip) { @@ -4601,16 +4563,6 @@ static int set_zero_key_func(struct sock *sk, struct hci_dev *hdev, } #endif - if (hdev && use_ll_privacy(hdev) && !hdev_is_powered(hdev)) { - bool changed; - - changed = hci_dev_test_and_clear_flag(hdev, - HCI_ENABLE_LL_PRIVACY); - if (changed) - exp_feature_changed(hdev, rpa_resolution_uuid, false, - sk); - } - hci_sock_set_flag(sk, HCI_MGMT_EXP_FEATURE_EVENTS); return mgmt_cmd_complete(sk, hdev ? hdev->id : MGMT_INDEX_NONE, @@ -4716,71 +4668,6 @@ static int set_mgmt_mesh_func(struct sock *sk, struct hci_dev *hdev, return err; } -static int set_rpa_resolution_func(struct sock *sk, struct hci_dev *hdev, - struct mgmt_cp_set_exp_feature *cp, - u16 data_len) -{ - struct mgmt_rp_set_exp_feature rp; - bool val, changed; - int err; - u32 flags; - - /* Command requires to use the controller index */ - if (!hdev) - return mgmt_cmd_status(sk, MGMT_INDEX_NONE, - MGMT_OP_SET_EXP_FEATURE, - MGMT_STATUS_INVALID_INDEX); - - /* Changes can only be made when controller is powered down */ - if (hdev_is_powered(hdev)) - return mgmt_cmd_status(sk, hdev->id, - MGMT_OP_SET_EXP_FEATURE, - MGMT_STATUS_REJECTED); - - /* Parameters are limited to a single octet */ - if (data_len != MGMT_SET_EXP_FEATURE_SIZE + 1) - return mgmt_cmd_status(sk, hdev->id, - MGMT_OP_SET_EXP_FEATURE, - MGMT_STATUS_INVALID_PARAMS); - - /* Only boolean on/off is supported */ - if (cp->param[0] != 0x00 && cp->param[0] != 0x01) - return mgmt_cmd_status(sk, hdev->id, - MGMT_OP_SET_EXP_FEATURE, - MGMT_STATUS_INVALID_PARAMS); - - val = !!cp->param[0]; - - if (val) { - changed = !hci_dev_test_and_set_flag(hdev, - HCI_ENABLE_LL_PRIVACY); - hci_dev_clear_flag(hdev, HCI_ADVERTISING); - - /* Enable LL privacy + supported settings changed */ - flags = BIT(0) | BIT(1); - } else { - changed = hci_dev_test_and_clear_flag(hdev, - HCI_ENABLE_LL_PRIVACY); - - /* Disable LL privacy + supported settings changed */ - flags = BIT(1); - } - - memcpy(rp.uuid, rpa_resolution_uuid, 16); - rp.flags = cpu_to_le32(flags); - - hci_sock_set_flag(sk, HCI_MGMT_EXP_FEATURE_EVENTS); - - err = mgmt_cmd_complete(sk, hdev->id, - MGMT_OP_SET_EXP_FEATURE, 0, - &rp, sizeof(rp)); - - if (changed) - exp_ll_privacy_feature_changed(val, hdev, sk); - - return err; -} - static int set_quality_report_func(struct sock *sk, struct hci_dev *hdev, struct mgmt_cp_set_exp_feature *cp, u16 data_len) @@ -5032,7 +4919,6 @@ static const struct mgmt_exp_feature { EXP_FEAT(debug_uuid, set_debug_func), #endif EXP_FEAT(mgmt_mesh_uuid, set_mgmt_mesh_func), - EXP_FEAT(rpa_resolution_uuid, set_rpa_resolution_func), EXP_FEAT(quality_report_uuid, set_quality_report_func), EXP_FEAT(offload_codecs_uuid, set_offload_codec_func), EXP_FEAT(le_simultaneous_roles_uuid, set_le_simultaneous_roles_func), @@ -5062,22 +4948,6 @@ static int set_exp_feature(struct sock *sk, struct hci_dev *hdev, MGMT_STATUS_NOT_SUPPORTED); } -static u32 get_params_flags(struct hci_dev *hdev, - struct hci_conn_params *params) -{ - u32 flags = hdev->conn_flags; - - /* Devices using RPAs can only be programmed in the acceptlist if - * LL Privacy has been enable otherwise they cannot mark - * HCI_CONN_FLAG_REMOTE_WAKEUP. - */ - if ((flags & HCI_CONN_FLAG_REMOTE_WAKEUP) && !use_ll_privacy(hdev) && - hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type)) - flags &= ~HCI_CONN_FLAG_REMOTE_WAKEUP; - - return flags; -} - static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len) { @@ -5112,7 +4982,6 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, if (!params) goto done; - supported_flags = get_params_flags(hdev, params); current_flags = params->flags; } @@ -5192,7 +5061,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - supported_flags = get_params_flags(hdev, params); + supported_flags = hdev->conn_flags; if ((supported_flags | current_flags) != supported_flags) { bt_dev_warn(hdev, "Bad flag given (0x%x) vs supported (0x%0x)", @@ -5519,10 +5388,16 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, { struct mgmt_rp_remove_adv_monitor rp; struct mgmt_pending_cmd *cmd = data; - struct mgmt_cp_remove_adv_monitor *cp = cmd->param; + struct mgmt_cp_remove_adv_monitor *cp; + + if (status == -ECANCELED || + cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) + return; hci_dev_lock(hdev); + cp = cmd->param; + rp.monitor_handle = cp->monitor_handle; if (!status) @@ -5540,6 +5415,10 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, static int mgmt_remove_adv_monitor_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; + + if (cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) + return -ECANCELED; + struct mgmt_cp_remove_adv_monitor *cp = cmd->param; u16 handle = __le16_to_cpu(cp->monitor_handle); @@ -7655,6 +7534,24 @@ static void device_added(struct sock *sk, struct hci_dev *hdev, mgmt_event(MGMT_EV_DEVICE_ADDED, hdev, &ev, sizeof(ev), sk); } +static void add_device_complete(struct hci_dev *hdev, void *data, int err) +{ + struct mgmt_pending_cmd *cmd = data; + struct mgmt_cp_add_device *cp = cmd->param; + + if (!err) { + device_added(cmd->sk, hdev, &cp->addr.bdaddr, cp->addr.type, + cp->action); + device_flags_changed(NULL, hdev, &cp->addr.bdaddr, + cp->addr.type, hdev->conn_flags, + PTR_UINT(cmd->user_data)); + } + + mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_ADD_DEVICE, + mgmt_status(err), &cp->addr, sizeof(cp->addr)); + mgmt_pending_free(cmd); +} + static int add_device_sync(struct hci_dev *hdev, void *data) { return hci_update_passive_scan_sync(hdev); @@ -7663,6 +7560,7 @@ static int add_device_sync(struct hci_dev *hdev, void *data) static int add_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { + struct mgmt_pending_cmd *cmd; struct mgmt_cp_add_device *cp = data; u8 auto_conn, addr_type; struct hci_conn_params *params; @@ -7743,9 +7641,24 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, current_flags = params->flags; } - err = hci_cmd_sync_queue(hdev, add_device_sync, NULL, NULL); - if (err < 0) + cmd = mgmt_pending_new(sk, MGMT_OP_ADD_DEVICE, hdev, data, len); + if (!cmd) { + err = -ENOMEM; goto unlock; + } + + cmd->user_data = UINT_PTR(current_flags); + + err = hci_cmd_sync_queue(hdev, add_device_sync, cmd, + add_device_complete); + if (err < 0) { + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, + MGMT_STATUS_FAILED, &cp->addr, + sizeof(cp->addr)); + mgmt_pending_free(cmd); + } + + goto unlock; added: device_added(sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index af80d599c337..21a5b5535ebc 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -201,14 +201,14 @@ static ssize_t address_show(struct device *tty_dev, struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); - return sprintf(buf, "%pMR\n", &dev->dst); + return sysfs_emit(buf, "%pMR\n", &dev->dst); } static ssize_t channel_show(struct device *tty_dev, struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); - return sprintf(buf, "%d\n", dev->channel); + return sysfs_emit(buf, "%d\n", dev->channel); } static DEVICE_ATTR_RO(address); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 501ec4249fed..8f6f7db48d4e 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -153,7 +153,7 @@ static void xdp_test_run_init_page(netmem_ref netmem, void *arg) new_ctx->data = new_ctx->data_meta + meta_len; xdp_update_frame_from_buff(new_ctx, frm); - frm->mem = new_ctx->rxq->mem; + frm->mem_type = new_ctx->rxq->mem.type; memcpy(&head->orig_ctx, new_ctx, sizeof(head->orig_ctx)); } @@ -246,7 +246,7 @@ static void reset_ctx(struct xdp_page_head *head) head->ctx.data_meta = head->orig_ctx.data_meta; head->ctx.data_end = head->orig_ctx.data_end; xdp_update_frame_from_buff(&head->ctx, head->frame); - head->frame->mem = head->orig_ctx.rxq->mem; + head->frame->mem_type = head->orig_ctx.rxq->mem.type; } static int xdp_recv_frames(struct xdp_frame **frames, int nframes, @@ -1018,6 +1018,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_CGROUP_SKB: is_direct_pkt_access = true; break; default: diff --git a/net/bridge/br.c b/net/bridge/br.c index 2cab878e0a39..183fcb362f9e 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -51,6 +51,13 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v } } + if (is_vlan_dev(dev)) { + struct net_device *real_dev = vlan_dev_real_dev(dev); + + if (netif_is_bridge_master(real_dev)) + br_vlan_vlan_upper_event(real_dev, dev, event); + } + /* not a port of a bridge */ p = br_port_get_rtnl(dev); if (!p) diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index c7869a286df4..115a23054a58 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -229,7 +229,7 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, #endif #if IS_ENABLED(CONFIG_IPV6) -struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *msg) +struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb, struct nd_msg *msg) { struct nd_msg *m; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 82bac2426631..902694c0ce64 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -955,6 +955,7 @@ int br_fdb_dump(struct sk_buff *skb, struct net_device *filter_dev, int *idx) { + struct ndo_fdb_dump_context *ctx = (void *)cb->ctx; struct net_bridge *br = netdev_priv(dev); struct net_bridge_fdb_entry *f; int err = 0; @@ -970,7 +971,7 @@ int br_fdb_dump(struct sk_buff *skb, rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { - if (*idx < cb->args[2]) + if (*idx < ctx->fdb_idx) goto skip; if (filter_dev && (!f->dst || f->dst->dev != filter_dev)) { if (filter_dev != dev) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index e19b583ff2c6..29097e984b4f 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -201,6 +201,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, enum br_pkt_type pkt_type, bool local_rcv, bool local_orig, u16 vid) { + enum skb_drop_reason reason = SKB_DROP_REASON_NO_TX_TARGET; struct net_bridge_port *prev = NULL; struct net_bridge_port *p; @@ -234,8 +235,11 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, continue; prev = maybe_deliver(prev, p, skb, local_orig); - if (IS_ERR(prev)) + if (IS_ERR(prev)) { + reason = PTR_ERR(prev) == -ENOMEM ? SKB_DROP_REASON_NOMEM : + SKB_DROP_REASON_NOT_SPECIFIED; goto out; + } } if (!prev) @@ -249,7 +253,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, out: if (!local_rcv) - kfree_skb(skb); + kfree_skb_reason(skb, reason); } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING @@ -289,6 +293,7 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, struct net_bridge_mcast *brmctx, bool local_rcv, bool local_orig) { + enum skb_drop_reason reason = SKB_DROP_REASON_NO_TX_TARGET; struct net_bridge_port *prev = NULL; struct net_bridge_port_group *p; bool allow_mode_include = true; @@ -329,8 +334,11 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, } prev = maybe_deliver(prev, port, skb, local_orig); - if (IS_ERR(prev)) + if (IS_ERR(prev)) { + reason = PTR_ERR(prev) == -ENOMEM ? SKB_DROP_REASON_NOMEM : + SKB_DROP_REASON_NOT_SPECIFIED; goto out; + } delivered: if ((unsigned long)lport >= (unsigned long)port) p = rcu_dereference(p->next); @@ -349,6 +357,6 @@ delivered: out: if (!local_rcv) - kfree_skb(skb); + kfree_skb_reason(skb, reason); } #endif diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index ceaa5a89b947..232133a0fd21 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -75,6 +75,7 @@ static int br_pass_frame_up(struct sk_buff *skb, bool promisc) /* note: already called with rcu_read_lock */ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct net_bridge_port *p = br_port_get_rcu(skb->dev); enum br_pkt_type pkt_type = BR_PKT_UNICAST; struct net_bridge_fdb_entry *dst = NULL; @@ -96,8 +97,10 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (br_mst_is_enabled(br)) { state = BR_STATE_FORWARDING; } else { - if (p->state == BR_STATE_DISABLED) + if (p->state == BR_STATE_DISABLED) { + reason = SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE; goto drop; + } state = p->state; } @@ -155,8 +158,10 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb } } - if (state == BR_STATE_LEARNING) + if (state == BR_STATE_LEARNING) { + reason = SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE; goto drop; + } BR_INPUT_SKB_CB(skb)->brdev = br->dev; BR_INPUT_SKB_CB(skb)->src_port_isolated = !!(p->flags & BR_ISOLATED); @@ -223,7 +228,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb out: return 0; drop: - kfree_skb(skb); + kfree_skb_reason(skb, reason); goto out; } EXPORT_SYMBOL_GPL(br_handle_frame_finish); @@ -324,6 +329,7 @@ static int br_process_frame_type(struct net_bridge_port *p, */ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct net_bridge_port *p; struct sk_buff *skb = *pskb; const unsigned char *dest = eth_hdr(skb)->h_dest; @@ -331,8 +337,10 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; - if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) + if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) { + reason = SKB_DROP_REASON_MAC_INVALID_SOURCE; goto drop; + } skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) @@ -374,6 +382,7 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) return RX_HANDLER_PASS; case 0x01: /* IEEE MAC (Pause) */ + reason = SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL; goto drop; case 0x0E: /* 802.1AB LLDP */ @@ -423,8 +432,9 @@ defer_stp_filtering: return nf_hook_bridge_pre(skb, pskb); default: + reason = SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE; drop: - kfree_skb(skb); + kfree_skb_reason(skb, reason); } return RX_HANDLER_CONSUMED; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 451e45b9a6a5..94cbe967d1c1 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -393,38 +393,10 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_ reason = ip_route_input(skb, iph->daddr, iph->saddr, ip4h_dscp(iph), dev); if (reason) { - struct in_device *in_dev = __in_dev_get_rcu(dev); - - /* If err equals -EHOSTUNREACH the error is due to a - * martian destination or due to the fact that - * forwarding is disabled. For most martian packets, - * ip_route_output_key() will fail. It won't fail for 2 types of - * martian destinations: loopback destinations and destination - * 0.0.0.0. In both cases the packet will be dropped because the - * destination is the loopback device and not the bridge. */ - if (reason != SKB_DROP_REASON_IP_INADDRERRORS || !in_dev || - IN_DEV_FORWARD(in_dev)) - goto free_skb; - - rt = ip_route_output(net, iph->daddr, 0, - ip4h_dscp(iph), 0, - RT_SCOPE_UNIVERSE); - if (!IS_ERR(rt)) { - /* - Bridged-and-DNAT'ed traffic doesn't - * require ip_forwarding. */ - if (rt->dst.dev == dev) { - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - goto bridged_dnat; - } - ip_rt_put(rt); - } -free_skb: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return 0; } else { if (skb_dst(skb)->dev == dev) { -bridged_dnat: skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 9853cfbb9d14..1054b8a88edc 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1571,6 +1571,9 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, void br_vlan_port_event(struct net_bridge_port *p, unsigned long event); int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr); +void br_vlan_vlan_upper_event(struct net_device *br_dev, + struct net_device *vlan_dev, + unsigned long event); int br_vlan_rtnl_init(void); void br_vlan_rtnl_uninit(void); void br_vlan_notify(const struct net_bridge *br, @@ -1802,6 +1805,12 @@ static inline int br_vlan_bridge_event(struct net_device *dev, return 0; } +static inline void br_vlan_vlan_upper_event(struct net_device *br_dev, + struct net_device *vlan_dev, + unsigned long event) +{ +} + static inline int br_vlan_rtnl_init(void) { return 0; @@ -2290,6 +2299,6 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, u16 vid, struct net_bridge_port *p); void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, u16 vid, struct net_bridge_port *p, struct nd_msg *msg); -struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *m); +struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb, struct nd_msg *m); bool br_is_neigh_suppress_enabled(const struct net_bridge_port *p, u16 vid); #endif diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index ea733542244c..c1176a5e02c4 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -1002,7 +1002,7 @@ static const struct attribute_group bridge_group = { * Returns the number of bytes read. */ static ssize_t brforward_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -1023,10 +1023,10 @@ static ssize_t brforward_read(struct file *filp, struct kobject *kobj, return n; } -static struct bin_attribute bridge_forward = { +static const struct bin_attribute bridge_forward = { .attr = { .name = SYSFS_BRIDGE_FDB, .mode = 0444, }, - .read = brforward_read, + .read_new = brforward_read, }; /* diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 89f51ea4cabe..d9a69ec9affe 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1664,6 +1664,18 @@ static void br_vlan_set_all_vlan_dev_state(struct net_bridge_port *p) } } +static void br_vlan_toggle_bridge_binding(struct net_device *br_dev, + bool enable) +{ + struct net_bridge *br = netdev_priv(br_dev); + + if (enable) + br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, true); + else + br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, + br_vlan_has_upper_bind_vlan_dev(br_dev)); +} + static void br_vlan_upper_change(struct net_device *dev, struct net_device *upper_dev, bool linking) @@ -1673,13 +1685,9 @@ static void br_vlan_upper_change(struct net_device *dev, if (!br_vlan_is_bind_vlan_dev(upper_dev)) return; - if (linking) { + br_vlan_toggle_bridge_binding(dev, linking); + if (linking) br_vlan_set_vlan_dev_state(br, upper_dev); - br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, true); - } else { - br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, - br_vlan_has_upper_bind_vlan_dev(dev)); - } } struct br_vlan_link_state_walk_data { @@ -1764,6 +1772,30 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) return ret; } +void br_vlan_vlan_upper_event(struct net_device *br_dev, + struct net_device *vlan_dev, + unsigned long event) +{ + struct vlan_dev_priv *vlan = vlan_dev_priv(vlan_dev); + struct net_bridge *br = netdev_priv(br_dev); + bool bridge_binding; + + switch (event) { + case NETDEV_CHANGE: + case NETDEV_UP: + break; + default: + return; + } + + bridge_binding = vlan->flags & VLAN_FLAG_BRIDGE_BINDING; + br_vlan_toggle_bridge_binding(br_dev, bridge_binding); + if (bridge_binding) + br_vlan_set_vlan_dev_state(br, vlan_dev); + else if (!bridge_binding && netif_carrier_ok(br_dev)) + netif_carrier_on(vlan_dev); +} + /* Must be protected by RTNL. */ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event) { diff --git a/net/can/raw.c b/net/can/raw.c index 255c0a8f39d6..46e8ed9d64da 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -962,7 +962,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } skb->dev = dev; - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = sockc.priority; skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 9b1168eb77ab..b24afec24138 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1173,6 +1173,8 @@ EXPORT_SYMBOL(ceph_osdc_new_request); int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt) { + WARN_ON(op->op != CEPH_OSD_OP_SPARSE_READ); + op->extent.sparse_ext_cnt = cnt; op->extent.sparse_ext = kmalloc_array(cnt, sizeof(*op->extent.sparse_ext), diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 2f4ed83a75ae..7d41cde1bcca 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -50,15 +50,16 @@ void bpf_sk_storage_free(struct sock *sk) { struct bpf_local_storage *sk_storage; + migrate_disable(); rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); - if (!sk_storage) { - rcu_read_unlock(); - return; - } + if (!sk_storage) + goto out; bpf_local_storage_destroy(sk_storage); +out: rcu_read_unlock(); + migrate_enable(); } static void bpf_sk_storage_map_free(struct bpf_map *map) @@ -160,6 +161,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); + migrate_disable(); rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); @@ -212,6 +214,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) out: rcu_read_unlock(); + migrate_enable(); /* In case of an error, don't free anything explicitly here, the * caller is responsible to call bpf_sk_storage_free. diff --git a/net/core/dev.c b/net/core/dev.c index 45a8c3dd4a64..c0021cbd28fc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -92,6 +92,7 @@ #include #include #include +#include #include #include #include @@ -105,6 +106,7 @@ #include #include #include +#include #include #include #include @@ -180,8 +182,6 @@ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); -static DECLARE_RWSEM(devnet_rename_sem); - static inline void dev_base_seq_inc(struct net *net) { unsigned int val = net->dev_base_seq + 1; @@ -460,7 +460,7 @@ EXPORT_PER_CPU_SYMBOL(softnet_data); * PP consumers must pay attention to run APIs in the appropriate context * (e.g. NAPI context). */ -static DEFINE_PER_CPU(struct page_pool *, system_page_pool); +DEFINE_PER_CPU(struct page_pool *, system_page_pool); #ifdef CONFIG_LOCKDEP /* @@ -753,6 +753,80 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, } EXPORT_SYMBOL_GPL(dev_fill_forward_path); +/* must be called under rcu_read_lock(), as we dont take a reference */ +static struct napi_struct *napi_by_id(unsigned int napi_id) +{ + unsigned int hash = napi_id % HASH_SIZE(napi_hash); + struct napi_struct *napi; + + hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) + if (napi->napi_id == napi_id) + return napi; + + return NULL; +} + +/* must be called under rcu_read_lock(), as we dont take a reference */ +static struct napi_struct * +netdev_napi_by_id(struct net *net, unsigned int napi_id) +{ + struct napi_struct *napi; + + napi = napi_by_id(napi_id); + if (!napi) + return NULL; + + if (WARN_ON_ONCE(!napi->dev)) + return NULL; + if (!net_eq(net, dev_net(napi->dev))) + return NULL; + + return napi; +} + +/** + * netdev_napi_by_id_lock() - find a device by NAPI ID and lock it + * @net: the applicable net namespace + * @napi_id: ID of a NAPI of a target device + * + * Find a NAPI instance with @napi_id. Lock its device. + * The device must be in %NETREG_REGISTERED state for lookup to succeed. + * netdev_unlock() must be called to release it. + * + * Return: pointer to NAPI, its device with lock held, NULL if not found. + */ +struct napi_struct * +netdev_napi_by_id_lock(struct net *net, unsigned int napi_id) +{ + struct napi_struct *napi; + struct net_device *dev; + + rcu_read_lock(); + napi = netdev_napi_by_id(net, napi_id); + if (!napi || READ_ONCE(napi->dev->reg_state) != NETREG_REGISTERED) { + rcu_read_unlock(); + return NULL; + } + + dev = napi->dev; + dev_hold(dev); + rcu_read_unlock(); + + dev = __netdev_put_lock(dev); + if (!dev) + return NULL; + + rcu_read_lock(); + napi = netdev_napi_by_id(net, napi_id); + if (napi && napi->dev != dev) + napi = NULL; + rcu_read_unlock(); + + if (!napi) + netdev_unlock(dev); + return napi; +} + /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace @@ -927,7 +1001,6 @@ EXPORT_SYMBOL(netdev_get_by_index); * its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ - struct net_device *dev_get_by_napi_id(unsigned int napi_id) { struct napi_struct *napi; @@ -941,7 +1014,73 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id) return napi ? napi->dev : NULL; } -EXPORT_SYMBOL(dev_get_by_napi_id); + +/* Release the held reference on the net_device, and if the net_device + * is still registered try to lock the instance lock. If device is being + * unregistered NULL will be returned (but the reference has been released, + * either way!) + * + * This helper is intended for locking net_device after it has been looked up + * using a lockless lookup helper. Lock prevents the instance from going away. + */ +struct net_device *__netdev_put_lock(struct net_device *dev) +{ + netdev_lock(dev); + if (dev->reg_state > NETREG_REGISTERED) { + netdev_unlock(dev); + dev_put(dev); + return NULL; + } + dev_put(dev); + return dev; +} + +/** + * netdev_get_by_index_lock() - find a device by its ifindex + * @net: the applicable net namespace + * @ifindex: index of device + * + * Search for an interface by index. If a valid device + * with @ifindex is found it will be returned with netdev->lock held. + * netdev_unlock() must be called to release it. + * + * Return: pointer to a device with lock held, NULL if not found. + */ +struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex) +{ + struct net_device *dev; + + dev = dev_get_by_index(net, ifindex); + if (!dev) + return NULL; + + return __netdev_put_lock(dev); +} + +struct net_device * +netdev_xa_find_lock(struct net *net, struct net_device *dev, + unsigned long *index) +{ + if (dev) + netdev_unlock(dev); + + do { + rcu_read_lock(); + dev = xa_find(&net->dev_by_index, index, ULONG_MAX, XA_PRESENT); + if (!dev) { + rcu_read_unlock(); + return NULL; + } + dev_hold(dev); + rcu_read_unlock(); + + dev = __netdev_put_lock(dev); + if (dev) + return dev; + + (*index)++; + } while (true); +} static DEFINE_SEQLOCK(netdev_rename_lock); @@ -1210,23 +1349,16 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev, */ int dev_change_name(struct net_device *dev, const char *newname) { + struct net *net = dev_net(dev); unsigned char old_assign_type; char oldname[IFNAMSIZ]; int err = 0; int ret; - struct net *net; - ASSERT_RTNL(); - BUG_ON(!dev_net(dev)); + ASSERT_RTNL_NET(net); - net = dev_net(dev); - - down_write(&devnet_rename_sem); - - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - up_write(&devnet_rename_sem); + if (!strncmp(newname, dev->name, IFNAMSIZ)) return 0; - } memcpy(oldname, dev->name, IFNAMSIZ); @@ -1234,10 +1366,8 @@ int dev_change_name(struct net_device *dev, const char *newname) err = dev_get_valid_name(net, dev, newname); write_sequnlock_bh(&netdev_rename_lock); - if (err < 0) { - up_write(&devnet_rename_sem); + if (err < 0) return err; - } if (oldname[0] && !strchr(oldname, '%')) netdev_info(dev, "renamed from %s%s\n", oldname, @@ -1249,14 +1379,13 @@ int dev_change_name(struct net_device *dev, const char *newname) rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { + write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); + write_sequnlock_bh(&netdev_rename_lock); WRITE_ONCE(dev->name_assign_type, old_assign_type); - up_write(&devnet_rename_sem); return ret; } - up_write(&devnet_rename_sem); - netdev_adjacent_rename_links(dev, oldname); netdev_name_node_del(dev->name_node); @@ -1272,7 +1401,6 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - down_write(&devnet_rename_sem); write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); @@ -1480,7 +1608,7 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { - dev->flags |= IFF_UP; + netif_set_up(dev, true); dev_set_rx_mode(dev); dev_activate(dev); add_device_randomness(dev->dev_addr, dev->addr_len); @@ -1559,7 +1687,7 @@ static void __dev_close_many(struct list_head *head) if (ops->ndo_stop) ops->ndo_stop(dev); - dev->flags &= ~IFF_UP; + netif_set_up(dev, false); netpoll_poll_enable(dev); } } @@ -1769,14 +1897,19 @@ int register_netdevice_notifier(struct notifier_block *nb) /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); + + /* When RTNL is removed, we need protection for netdev_chain. */ rtnl_lock(); + err = raw_notifier_chain_register(&netdev_chain, nb); if (err) goto unlock; if (dev_boot_phase) goto unlock; for_each_net(net) { + __rtnl_net_lock(net); err = call_netdevice_register_net_notifiers(nb, net); + __rtnl_net_unlock(net); if (err) goto rollback; } @@ -1787,8 +1920,11 @@ unlock: return err; rollback: - for_each_net_continue_reverse(net) + for_each_net_continue_reverse(net) { + __rtnl_net_lock(net); call_netdevice_unregister_net_notifiers(nb, net); + __rtnl_net_unlock(net); + } raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; @@ -1821,8 +1957,11 @@ int unregister_netdevice_notifier(struct notifier_block *nb) if (err) goto unlock; - for_each_net(net) + for_each_net(net) { + __rtnl_net_lock(net); call_netdevice_unregister_net_notifiers(nb, net); + __rtnl_net_unlock(net); + } unlock: rtnl_unlock(); @@ -1886,9 +2025,10 @@ int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; - rtnl_lock(); + rtnl_net_lock(net); err = __register_netdevice_notifier_net(net, nb, false); - rtnl_unlock(); + rtnl_net_unlock(net); + return err; } EXPORT_SYMBOL(register_netdevice_notifier_net); @@ -1914,9 +2054,10 @@ int unregister_netdevice_notifier_net(struct net *net, { int err; - rtnl_lock(); + rtnl_net_lock(net); err = __unregister_netdevice_notifier_net(net, nb); - rtnl_unlock(); + rtnl_net_unlock(net); + return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_net); @@ -1933,15 +2074,17 @@ int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { + struct net *net = dev_net(dev); int err; - rtnl_lock(); - err = __register_netdevice_notifier_net(dev_net(dev), nb, false); + rtnl_net_lock(net); + err = __register_netdevice_notifier_net(net, nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } - rtnl_unlock(); + rtnl_net_unlock(net); + return err; } EXPORT_SYMBOL(register_netdevice_notifier_dev_net); @@ -1950,12 +2093,14 @@ int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { + struct net *net = dev_net(dev); int err; - rtnl_lock(); + rtnl_net_lock(net); list_del(&nn->list); - err = __unregister_netdevice_notifier_net(dev_net(dev), nb); - rtnl_unlock(); + err = __unregister_netdevice_notifier_net(net, nb); + rtnl_net_unlock(net); + return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net); @@ -2104,8 +2249,8 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif #ifdef CONFIG_NET_CLS_ACT -DEFINE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key); -EXPORT_SYMBOL(tcf_bypass_check_needed_key); +DEFINE_STATIC_KEY_FALSE(tcf_sw_enabled_key); +EXPORT_SYMBOL(tcf_sw_enabled_key); #endif DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); @@ -3233,7 +3378,7 @@ void netif_device_attach(struct net_device *dev) if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_wake_all_queues(dev); - __netdev_watchdog_up(dev); + netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_device_attach); @@ -3642,8 +3787,10 @@ int skb_csum_hwoffload_help(struct sk_buff *skb, if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) && - skb_network_header_len(skb) != sizeof(struct ipv6hdr)) + skb_network_header_len(skb) != sizeof(struct ipv6hdr) && + !ipv6_has_hopopt_jumbo(skb)) goto sw_checksum; + switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): @@ -3998,10 +4145,13 @@ static int tc_run(struct tcx_entry *entry, struct sk_buff *skb, if (!miniq) return ret; - if (static_branch_unlikely(&tcf_bypass_check_needed_key)) { - if (tcf_block_bypass_sw(miniq->block)) - return ret; - } + /* Global bypass */ + if (!static_branch_likely(&tcf_sw_enabled_key)) + return ret; + + /* Block-wise bypass */ + if (tcf_block_bypass_sw(miniq->block)) + return ret; tc_skb_cb(skb)->mru = 0; tc_skb_cb(skb)->post_ct = false; @@ -4931,7 +5081,7 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; @@ -5033,7 +5183,7 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, } static int -netif_skb_check_for_xdp(struct sk_buff **pskb, struct bpf_prog *prog) +netif_skb_check_for_xdp(struct sk_buff **pskb, const struct bpf_prog *prog) { struct sk_buff *skb = *pskb; int err, hroom, troom; @@ -5057,7 +5207,7 @@ netif_skb_check_for_xdp(struct sk_buff **pskb, struct bpf_prog *prog) static u32 netif_receive_generic_xdp(struct sk_buff **pskb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { struct sk_buff *skb = *pskb; u32 mac_len, act = XDP_DROP; @@ -5110,7 +5260,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff **pskb, * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX * queues, so they do not have this starvation issue. */ -void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) +void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog) { struct net_device *dev = skb->dev; struct netdev_queue *txq; @@ -5135,7 +5285,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); -int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb) +int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; @@ -5474,8 +5624,14 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, orig_dev = skb->dev; skb_reset_network_header(skb); +#if !defined(CONFIG_DEBUG_NET) + /* We plan to no longer reset the transport header here. + * Give some time to fuzzers and dev build to catch bugs + * in network stacks. + */ if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); +#endif skb_reset_mac_len(skb); pt_prev = NULL; @@ -5959,8 +6115,6 @@ void netif_receive_skb_list(struct list_head *head) } EXPORT_SYMBOL(netif_receive_skb_list); -static DEFINE_PER_CPU(struct work_struct, flush_works); - /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) { @@ -6017,36 +6171,54 @@ static bool flush_required(int cpu) return true; } +struct flush_backlogs { + cpumask_t flush_cpus; + struct work_struct w[]; +}; + +static struct flush_backlogs *flush_backlogs_alloc(void) +{ + return kmalloc(struct_size_t(struct flush_backlogs, w, nr_cpu_ids), + GFP_KERNEL); +} + +static struct flush_backlogs *flush_backlogs_fallback; +static DEFINE_MUTEX(flush_backlogs_mutex); + static void flush_all_backlogs(void) { - static cpumask_t flush_cpus; + struct flush_backlogs *ptr = flush_backlogs_alloc(); unsigned int cpu; - /* since we are under rtnl lock protection we can use static data - * for the cpumask and avoid allocating on stack the possibly - * large mask - */ - ASSERT_RTNL(); + if (!ptr) { + mutex_lock(&flush_backlogs_mutex); + ptr = flush_backlogs_fallback; + } + cpumask_clear(&ptr->flush_cpus); cpus_read_lock(); - cpumask_clear(&flush_cpus); for_each_online_cpu(cpu) { if (flush_required(cpu)) { - queue_work_on(cpu, system_highpri_wq, - per_cpu_ptr(&flush_works, cpu)); - cpumask_set_cpu(cpu, &flush_cpus); + INIT_WORK(&ptr->w[cpu], flush_backlog); + queue_work_on(cpu, system_highpri_wq, &ptr->w[cpu]); + __cpumask_set_cpu(cpu, &ptr->flush_cpus); } } /* we can have in flight packet[s] on the cpus we are not flushing, * synchronize_net() in unregister_netdevice_many() will take care of - * them + * them. */ - for_each_cpu(cpu, &flush_cpus) - flush_work(per_cpu_ptr(&flush_works, cpu)); + for_each_cpu(cpu, &ptr->flush_cpus) + flush_work(&ptr->w[cpu]); cpus_read_unlock(); + + if (ptr != flush_backlogs_fallback) + kfree(ptr); + else + mutex_unlock(&flush_backlogs_mutex); } static void net_rps_send_ipi(struct softnet_data *remsd) @@ -6291,19 +6463,6 @@ bool napi_complete_done(struct napi_struct *n, int work_done) } EXPORT_SYMBOL(napi_complete_done); -/* must be called under rcu_read_lock(), as we dont take a reference */ -struct napi_struct *napi_by_id(unsigned int napi_id) -{ - unsigned int hash = napi_id % HASH_SIZE(napi_hash); - struct napi_struct *napi; - - hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) - if (napi->napi_id == napi_id) - return napi; - - return NULL; -} - static void skb_defer_free_flush(struct softnet_data *sd) { struct sk_buff *skb, *next; @@ -6549,7 +6708,7 @@ void napi_resume_irqs(unsigned int napi_id) static void __napi_hash_add_with_id(struct napi_struct *napi, unsigned int napi_id) { - napi->napi_id = napi_id; + WRITE_ONCE(napi->napi_id, napi_id); hlist_add_head_rcu(&napi->napi_hash_node, &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); } @@ -6633,6 +6792,8 @@ int dev_set_threaded(struct net_device *dev, bool threaded) struct napi_struct *napi; int err = 0; + netdev_assert_locked_or_invisible(dev); + if (dev->threaded == threaded) return 0; @@ -6711,13 +6872,14 @@ static void napi_restore_config(struct napi_struct *n) n->gro_flush_timeout = n->config->gro_flush_timeout; n->irq_suspend_timeout = n->config->irq_suspend_timeout; /* a NAPI ID might be stored in the config, if so use it. if not, use - * napi_hash_add to generate one for us. It will be saved to the config - * in napi_disable. + * napi_hash_add to generate one for us. */ - if (n->config->napi_id) + if (n->config->napi_id) { napi_hash_add_with_id(n, n->config->napi_id); - else + } else { napi_hash_add(n); + n->config->napi_id = n->napi_id; + } } static void napi_save_config(struct napi_struct *n) @@ -6725,13 +6887,45 @@ static void napi_save_config(struct napi_struct *n) n->config->defer_hard_irqs = n->defer_hard_irqs; n->config->gro_flush_timeout = n->gro_flush_timeout; n->config->irq_suspend_timeout = n->irq_suspend_timeout; - n->config->napi_id = n->napi_id; napi_hash_del(n); } -void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight) +/* Netlink wants the NAPI list to be sorted by ID, if adding a NAPI which will + * inherit an existing ID try to insert it at the right position. + */ +static void +netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) { + unsigned int new_id, pos_id; + struct list_head *higher; + struct napi_struct *pos; + + new_id = UINT_MAX; + if (napi->config && napi->config->napi_id) + new_id = napi->config->napi_id; + + higher = &dev->napi_list; + list_for_each_entry(pos, &dev->napi_list, dev_list) { + if (pos->napi_id >= MIN_NAPI_ID) + pos_id = pos->napi_id; + else if (pos->config) + pos_id = pos->config->napi_id; + else + pos_id = UINT_MAX; + + if (pos_id <= new_id) + break; + higher = &pos->dev_list; + } + list_add_rcu(&napi->dev_list, higher); /* adds after higher */ +} + +void netif_napi_add_weight_locked(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight) +{ + netdev_assert_locked(dev); if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) return; @@ -6755,7 +6949,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, napi->list_owner = -1; set_bit(NAPI_STATE_SCHED, &napi->state); set_bit(NAPI_STATE_NPSVC, &napi->state); - list_add_rcu(&napi->dev_list, &dev->napi_list); + netif_napi_dev_list_add(dev, napi); /* default settings from sysfs are applied to all NAPIs. any per-NAPI * configuration will be loaded in napi_enable @@ -6770,15 +6964,17 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, */ if (dev->threaded && napi_kthread_create(napi)) dev->threaded = false; - netif_napi_set_irq(napi, -1); + netif_napi_set_irq_locked(napi, -1); } -EXPORT_SYMBOL(netif_napi_add_weight); +EXPORT_SYMBOL(netif_napi_add_weight_locked); -void napi_disable(struct napi_struct *n) +void napi_disable_locked(struct napi_struct *n) { unsigned long val, new; might_sleep(); + netdev_assert_locked(n->dev); + set_bit(NAPI_STATE_DISABLE, &n->state); val = READ_ONCE(n->state); @@ -6801,16 +6997,25 @@ void napi_disable(struct napi_struct *n) clear_bit(NAPI_STATE_DISABLE, &n->state); } -EXPORT_SYMBOL(napi_disable); +EXPORT_SYMBOL(napi_disable_locked); /** - * napi_enable - enable NAPI scheduling - * @n: NAPI context + * napi_disable() - prevent NAPI from scheduling + * @n: NAPI context * - * Resume NAPI from being scheduled on this context. - * Must be paired with napi_disable. + * Stop NAPI from being scheduled on this context. + * Waits till any outstanding processing completes. + * Takes netdev_lock() for associated net_device. */ -void napi_enable(struct napi_struct *n) +void napi_disable(struct napi_struct *n) +{ + netdev_lock(n->dev); + napi_disable_locked(n); + netdev_unlock(n->dev); +} +EXPORT_SYMBOL(napi_disable); + +void napi_enable_locked(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); @@ -6827,6 +7032,22 @@ void napi_enable(struct napi_struct *n) new |= NAPIF_STATE_THREADED; } while (!try_cmpxchg(&n->state, &val, new)); } +EXPORT_SYMBOL(napi_enable_locked); + +/** + * napi_enable() - enable NAPI scheduling + * @n: NAPI context + * + * Enable scheduling of a NAPI instance. + * Must be paired with napi_disable(). + * Takes netdev_lock() for associated net_device. + */ +void napi_enable(struct napi_struct *n) +{ + netdev_lock(n->dev); + napi_enable_locked(n); + netdev_unlock(n->dev); +} EXPORT_SYMBOL(napi_enable); static void flush_gro_hash(struct napi_struct *napi) @@ -6843,8 +7064,10 @@ static void flush_gro_hash(struct napi_struct *napi) } /* Must be called in process context */ -void __netif_napi_del(struct napi_struct *napi) +void __netif_napi_del_locked(struct napi_struct *napi) { + netdev_assert_locked(napi->dev); + if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) return; @@ -6864,7 +7087,7 @@ void __netif_napi_del(struct napi_struct *napi) napi->thread = NULL; } } -EXPORT_SYMBOL(__netif_napi_del); +EXPORT_SYMBOL(__netif_napi_del_locked); static int __napi_poll(struct napi_struct *n, bool *repoll) { @@ -9480,11 +9703,31 @@ u8 dev_xdp_prog_count(struct net_device *dev) } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); +u8 dev_xdp_sb_prog_count(struct net_device *dev) +{ + u8 count = 0; + int i; + + for (i = 0; i < __MAX_XDP_MODE; i++) + if (dev->xdp_state[i].prog && + !dev->xdp_state[i].prog->aux->xdp_has_frags) + count++; + return count; +} + int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) { if (!dev->netdev_ops->ndo_bpf) return -EOPNOTSUPP; + if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + bpf->command == XDP_SETUP_PROG && + bpf->prog && !bpf->prog->aux->xdp_has_frags) { + NL_SET_ERR_MSG(bpf->extack, + "unable to propagate XDP to device using tcp-data-split"); + return -EBUSY; + } + if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider"); return -EBUSY; @@ -9522,6 +9765,12 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, struct netdev_bpf xdp; int err; + if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + prog && !prog->aux->xdp_has_frags) { + NL_SET_ERR_MSG(extack, "unable to install XDP to device using tcp-data-split"); + return -EBUSY; + } + if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider"); return -EBUSY; @@ -9675,6 +9924,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Program bound to different device"); return -EINVAL; } + if (bpf_prog_is_dev_bound(new_prog->aux) && mode == XDP_MODE_SKB) { + NL_SET_ERR_MSG(extack, "Can't attach device-bound programs in generic mode"); + return -EINVAL; + } if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); return -EINVAL; @@ -10002,6 +10255,15 @@ static void dev_index_release(struct net *net, int ifindex) WARN_ON(xa_erase(&net->dev_by_index, ifindex)); } +static bool from_cleanup_net(void) +{ +#ifdef CONFIG_NET_NS + return current == cleanup_net_task; +#else + return false; +#endif +} + /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); @@ -10598,7 +10860,9 @@ int register_netdevice(struct net_device *dev) ret = netdev_register_kobject(dev); + netdev_lock(dev); WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED); + netdev_unlock(dev); if (ret) goto err_uninit_notify; @@ -10666,54 +10930,26 @@ err_free_name: EXPORT_SYMBOL(register_netdevice); /* Initialize the core of a dummy net device. - * This is useful if you are calling this function after alloc_netdev(), - * since it does not memset the net_device fields. + * The setup steps dummy netdevs need which normal netdevs get by going + * through register_netdevice(). */ -static void init_dummy_netdev_core(struct net_device *dev) +static void init_dummy_netdev(struct net_device *dev) { /* make sure we BUG if trying to hit standard * register/unregister code path */ dev->reg_state = NETREG_DUMMY; - /* NAPI wants this */ - INIT_LIST_HEAD(&dev->napi_list); - /* a dummy interface is started by default */ set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); - /* napi_busy_loop stats accounting wants this */ - dev_net_set(dev, &init_net); - /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. */ } -/** - * init_dummy_netdev - init a dummy network device for NAPI - * @dev: device to init - * - * This takes a network device structure and initializes the minimum - * amount of fields so it can be used to schedule NAPI polls without - * registering a full blown interface. This is to be used by drivers - * that need to tie several hardware interfaces to a single NAPI - * poll scheduler due to HW limitations. - */ -void init_dummy_netdev(struct net_device *dev) -{ - /* Clear everything. Note we don't initialize spinlocks - * as they aren't supposed to be taken by any of the - * NAPI code and this dummy netdev is supposed to be - * only ever used for NAPI polls - */ - memset(dev, 0, sizeof(struct net_device)); - init_dummy_netdev_core(dev); -} -EXPORT_SYMBOL_GPL(init_dummy_netdev); - /** * register_netdev - register a network device * @dev: device to register @@ -10729,12 +10965,16 @@ EXPORT_SYMBOL_GPL(init_dummy_netdev); */ int register_netdev(struct net_device *dev) { + struct net *net = dev_net(dev); int err; - if (rtnl_lock_killable()) + if (rtnl_net_lock_killable(net)) return -EINTR; + err = register_netdevice(dev); - rtnl_unlock(); + + rtnl_net_unlock(net); + return err; } EXPORT_SYMBOL(register_netdev); @@ -10896,7 +11136,9 @@ void netdev_run_todo(void) continue; } + netdev_lock(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED); + netdev_unlock(dev); linkwatch_sync_dev(dev); } @@ -11282,6 +11524,11 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, if (!dev->ethtool) goto free_all; + dev->cfg = kzalloc(sizeof(*dev->cfg), GFP_KERNEL_ACCOUNT); + if (!dev->cfg) + goto free_all; + dev->cfg_pending = dev->cfg; + napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) @@ -11311,6 +11558,22 @@ free_dev: } EXPORT_SYMBOL(alloc_netdev_mqs); +static void netdev_napi_exit(struct net_device *dev) +{ + if (!list_empty(&dev->napi_list)) { + struct napi_struct *p, *n; + + netdev_lock(dev); + list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) + __netif_napi_del_locked(p); + netdev_unlock(dev); + + synchronize_net(); + } + + kvfree(dev->napi_config); +} + /** * free_netdev - free network device * @dev: device @@ -11322,8 +11585,6 @@ EXPORT_SYMBOL(alloc_netdev_mqs); */ void free_netdev(struct net_device *dev) { - struct napi_struct *p, *n; - might_sleep(); /* When called immediately after register_netdevice() failed the unwind @@ -11336,8 +11597,8 @@ void free_netdev(struct net_device *dev) return; } - mutex_destroy(&dev->lock); - + WARN_ON(dev->cfg != dev->cfg_pending); + kfree(dev->cfg); kfree(dev->ethtool); netif_free_tx_queues(dev); netif_free_rx_queues(dev); @@ -11347,10 +11608,7 @@ void free_netdev(struct net_device *dev) /* Flush device addresses */ dev_addr_flush(dev); - list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) - netif_napi_del(p); - - kvfree(dev->napi_config); + netdev_napi_exit(dev); ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT @@ -11364,6 +11622,8 @@ void free_netdev(struct net_device *dev) netdev_free_phy_link_topology(dev); + mutex_destroy(&dev->lock); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { @@ -11388,7 +11648,7 @@ EXPORT_SYMBOL(free_netdev); struct net_device *alloc_netdev_dummy(int sizeof_priv) { return alloc_netdev(sizeof_priv, "dummy#", NET_NAME_UNKNOWN, - init_dummy_netdev_core); + init_dummy_netdev); } EXPORT_SYMBOL_GPL(alloc_netdev_dummy); @@ -11401,7 +11661,7 @@ EXPORT_SYMBOL_GPL(alloc_netdev_dummy); void synchronize_net(void) { might_sleep(); - if (rtnl_is_locked()) + if (from_cleanup_net() || rtnl_is_locked()) synchronize_rcu_expedited(); else synchronize_rcu(); @@ -11502,7 +11762,9 @@ void unregister_netdevice_many_notify(struct list_head *head, list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); + netdev_lock(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); + netdev_unlock(dev); } flush_all_backlogs(); @@ -11604,9 +11866,11 @@ EXPORT_SYMBOL(unregister_netdevice_many); */ void unregister_netdev(struct net_device *dev) { - rtnl_lock(); + struct net *net = dev_net(dev); + + rtnl_net_lock(net); unregister_netdevice(dev); - rtnl_unlock(); + rtnl_net_unlock(net); } EXPORT_SYMBOL(unregister_netdev); @@ -12152,11 +12416,18 @@ static int net_page_pool_create(int cpuid) .nid = cpu_to_mem(cpuid), }; struct page_pool *pp_ptr; + int err; pp_ptr = page_pool_create_percpu(&page_pool_params, cpuid); if (IS_ERR(pp_ptr)) return -ENOMEM; + err = xdp_reg_page_pool(pp_ptr); + if (err) { + page_pool_destroy(pp_ptr); + return err; + } + per_cpu(system_page_pool, cpuid) = pp_ptr; #endif return 0; @@ -12222,11 +12493,12 @@ static int __init net_dev_init(void) * Initialise the packet receive queues. */ - for_each_possible_cpu(i) { - struct work_struct *flush = per_cpu_ptr(&flush_works, i); - struct softnet_data *sd = &per_cpu(softnet_data, i); + flush_backlogs_fallback = flush_backlogs_alloc(); + if (!flush_backlogs_fallback) + goto out; - INIT_WORK(flush, flush_backlog); + for_each_possible_cpu(i) { + struct softnet_data *sd = &per_cpu(softnet_data, i); skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); @@ -12290,6 +12562,7 @@ out: if (!pp_ptr) continue; + xdp_unreg_page_pool(pp_ptr); page_pool_destroy(pp_ptr); per_cpu(system_page_pool, i) = NULL; } diff --git a/net/core/dev.h b/net/core/dev.h index d043dee25a68..a5b166bbd169 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -2,6 +2,7 @@ #ifndef _NET_CORE_DEV_H #define _NET_CORE_DEV_H +#include #include #include #include @@ -22,6 +23,23 @@ struct sd_flow_limit { extern int netdev_flow_limit_table_len; +struct napi_struct * +netdev_napi_by_id_lock(struct net *net, unsigned int napi_id); +struct net_device *dev_get_by_napi_id(unsigned int napi_id); + +struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex); +struct net_device *__netdev_put_lock(struct net_device *dev); +struct net_device * +netdev_xa_find_lock(struct net *net, struct net_device *dev, + unsigned long *index); + +DEFINE_FREE(netdev_unlock, struct net_device *, if (_T) netdev_unlock(_T)); + +#define for_each_netdev_lock_scoped(net, var_name, ifindex) \ + for (struct net_device *var_name __free(netdev_unlock) = NULL; \ + (var_name = netdev_xa_find_lock(net, var_name, &ifindex)); \ + ifindex++) + #ifdef CONFIG_PROC_FS int __init dev_proc_init(void); #else @@ -109,6 +127,18 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, void unregister_netdevice_many_notify(struct list_head *head, u32 portid, const struct nlmsghdr *nlh); +static inline void netif_set_up(struct net_device *dev, bool value) +{ + if (value) + dev->flags |= IFF_UP; + else + dev->flags &= ~IFF_UP; + + netdev_lock(dev); + dev->up = value; + netdev_unlock(dev); +} + static inline void netif_set_gso_max_size(struct net_device *dev, unsigned int size) { @@ -269,7 +299,6 @@ void xdp_do_check_flushed(struct napi_struct *napi); static inline void xdp_do_check_flushed(struct napi_struct *napi) { } #endif -struct napi_struct *napi_by_id(unsigned int napi_id); void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); #define XMIT_RECURSION_LIMIT 8 @@ -310,5 +339,8 @@ static inline void dev_xmit_recursion_dec(void) int dev_set_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack); +int dev_get_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg); +int net_hwtstamp_validate(const struct kernel_hwtstamp_config *cfg); #endif diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 166e404f7c03..90716bd736f3 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -242,9 +242,9 @@ static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list, __hw_addr_del_entry(from_list, ha, false, false); } -static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len) +int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; @@ -260,6 +260,7 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, } return err; } +EXPORT_SYMBOL(__hw_addr_sync_multiple); /* This function only works where there is a strict 1-1 relationship * between source and destination of they synch. If you ever need to diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 46d43b950471..4c2098ac9d72 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -184,7 +185,7 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm return err; } -static int net_hwtstamp_validate(const struct kernel_hwtstamp_config *cfg) +int net_hwtstamp_validate(const struct kernel_hwtstamp_config *cfg) { enum hwtstamp_tx_types tx_type; enum hwtstamp_rx_filters rx_filter; @@ -266,9 +267,24 @@ static int dev_eth_ioctl(struct net_device *dev, * -EOPNOTSUPP for phylib for now, which is still more accurate than letting * the netdev handle the GET request. */ -static int dev_get_hwtstamp_phylib(struct net_device *dev, - struct kernel_hwtstamp_config *cfg) +int dev_get_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg) { + struct hwtstamp_provider *hwprov; + + hwprov = rtnl_dereference(dev->hwprov); + if (hwprov) { + cfg->qualifier = hwprov->desc.qualifier; + if (hwprov->source == HWTSTAMP_SOURCE_PHYLIB && + hwprov->phydev) + return phy_hwtstamp_get(hwprov->phydev, cfg); + + if (hwprov->source == HWTSTAMP_SOURCE_NETDEV) + return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg); + + return -EOPNOTSUPP; + } + if (phy_is_default_hwtstamp(dev->phydev)) return phy_hwtstamp_get(dev->phydev, cfg); @@ -324,11 +340,32 @@ int dev_set_hwtstamp_phylib(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; - bool phy_ts = phy_is_default_hwtstamp(dev->phydev); struct kernel_hwtstamp_config old_cfg = {}; + struct hwtstamp_provider *hwprov; + struct phy_device *phydev; bool changed = false; + bool phy_ts; int err; + hwprov = rtnl_dereference(dev->hwprov); + if (hwprov) { + if (hwprov->source == HWTSTAMP_SOURCE_PHYLIB && + hwprov->phydev) { + phy_ts = true; + phydev = hwprov->phydev; + } else if (hwprov->source == HWTSTAMP_SOURCE_NETDEV) { + phy_ts = false; + } else { + return -EOPNOTSUPP; + } + + cfg->qualifier = hwprov->desc.qualifier; + } else { + phy_ts = phy_is_default_hwtstamp(dev->phydev); + if (phy_ts) + phydev = dev->phydev; + } + cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV; if (phy_ts && dev->see_all_hwtstamp_requests) { @@ -350,7 +387,7 @@ int dev_set_hwtstamp_phylib(struct net_device *dev, changed = kernel_hwtstamp_config_changed(&old_cfg, cfg); if (phy_ts) { - err = phy_hwtstamp_set(dev->phydev, cfg, extack); + err = phy_hwtstamp_set(phydev, cfg, extack); if (err) { if (changed) ops->ndo_hwtstamp_set(dev, &old_cfg, NULL); @@ -506,7 +543,7 @@ static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs) } /* - * Perform the SIOCxIFxxx calls, inside rtnl_lock() + * Perform the SIOCxIFxxx calls, inside rtnl_net_lock() */ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, unsigned int cmd) @@ -583,11 +620,14 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, return -ENODEV; if (!netif_is_bridge_master(dev)) return -EOPNOTSUPP; + netdev_hold(dev, &dev_tracker, GFP_KERNEL); - rtnl_unlock(); + rtnl_net_unlock(net); + err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL); + netdev_put(dev, &dev_tracker); - rtnl_lock(); + rtnl_net_lock(net); return err; case SIOCDEVPRIVATE ... SIOCDEVPRIVATE + 15: @@ -733,9 +773,11 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, dev_load(net, ifr->ifr_name); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - rtnl_lock(); + + rtnl_net_lock(net); ret = dev_ifsioc(net, ifr, data, cmd); - rtnl_unlock(); + rtnl_net_unlock(net); + if (colon) *colon = ':'; return ret; @@ -779,9 +821,11 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: dev_load(net, ifr->ifr_name); - rtnl_lock(); + + rtnl_net_lock(net); ret = dev_ifsioc(net, ifr, data, cmd); - rtnl_unlock(); + rtnl_net_unlock(net); + if (need_copyout) *need_copyout = false; return ret; @@ -804,9 +848,10 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15)) { dev_load(net, ifr->ifr_name); - rtnl_lock(); + + rtnl_net_lock(net); ret = dev_ifsioc(net, ifr, data, cmd); - rtnl_unlock(); + rtnl_net_unlock(net); return ret; } return -ENOTTY; diff --git a/net/core/devmem.c b/net/core/devmem.c index 11b91c12ee11..3bba3f018df0 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -140,6 +141,16 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, return -ERANGE; } + if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) { + NL_SET_ERR_MSG(extack, "tcp-data-split is disabled"); + return -EINVAL; + } + + if (dev->cfg->hds_thresh) { + NL_SET_ERR_MSG(extack, "hds-thresh is not zero"); + return -EINVAL; + } + rxq = __netif_get_rx_queue(dev, rxq_idx); if (rxq->mp_params.mp_priv) { NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); @@ -331,11 +342,11 @@ int mp_dmabuf_devmem_init(struct page_pool *pool) if (!binding) return -EINVAL; - if (!pool->dma_map) - return -EOPNOTSUPP; - - if (pool->dma_sync) - return -EOPNOTSUPP; + /* dma-buf dma addresses do not need and should not be used with + * dma_sync_for_cpu/device. Force disable dma_sync. + */ + pool->dma_sync = false; + pool->dma_sync_for_cpu = false; if (pool->p.order != 0) return -E2BIG; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 34185d138c95..e684ba3ebb38 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -770,6 +770,8 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = { [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, [FRA_DSCP] = NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2), + [FRA_FLOWLABEL] = { .type = NLA_BE32 }, + [FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 }, }; int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/core/filter.c b/net/core/filter.c index 21131ec25f24..2ec162dd83c4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3734,13 +3734,22 @@ static const struct bpf_func_proto bpf_skb_adjust_room_proto = { static u32 __bpf_skb_min_len(const struct sk_buff *skb) { - u32 min_len = skb_network_offset(skb); + int offset = skb_network_offset(skb); + u32 min_len = 0; - if (skb_transport_header_was_set(skb)) - min_len = skb_transport_offset(skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) - min_len = skb_checksum_start_offset(skb) + - skb->csum_offset + sizeof(__sum16); + if (offset > 0) + min_len = offset; + if (skb_transport_header_was_set(skb)) { + offset = skb_transport_offset(skb); + if (offset > 0) + min_len = offset; + } + if (skb->ip_summed == CHECKSUM_PARTIAL) { + offset = skb_checksum_start_offset(skb) + + skb->csum_offset + sizeof(__sum16); + if (offset > 0) + min_len = offset; + } return min_len; } @@ -4119,13 +4128,13 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) } static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink, - struct xdp_mem_info *mem_info, bool release) + enum xdp_mem_type mem_type, bool release) { struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp); if (release) { xsk_buff_del_tail(zc_frag); - __xdp_return(NULL, mem_info, false, zc_frag); + __xdp_return(0, mem_type, false, zc_frag); } else { zc_frag->data_end -= shrink; } @@ -4134,19 +4143,16 @@ static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink, static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag, int shrink) { - struct xdp_mem_info *mem_info = &xdp->rxq->mem; + enum xdp_mem_type mem_type = xdp->rxq->mem.type; bool release = skb_frag_size(frag) == shrink; - if (mem_info->type == MEM_TYPE_XSK_BUFF_POOL) { - bpf_xdp_shrink_data_zc(xdp, shrink, mem_info, release); + if (mem_type == MEM_TYPE_XSK_BUFF_POOL) { + bpf_xdp_shrink_data_zc(xdp, shrink, mem_type, release); goto out; } - if (release) { - struct page *page = skb_frag_page(frag); - - __xdp_return(page_address(page), mem_info, false, NULL); - } + if (release) + __xdp_return(skb_frag_netmem(frag), mem_type, false, NULL); out: return release; @@ -4348,9 +4354,9 @@ u32 xdp_master_redirect(struct xdp_buff *xdp) EXPORT_SYMBOL_GPL(xdp_master_redirect); static inline int __xdp_do_redirect_xsk(struct bpf_redirect_info *ri, - struct net_device *dev, + const struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; @@ -4371,10 +4377,10 @@ err: return err; } -static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, - struct net_device *dev, - struct xdp_frame *xdpf, - struct bpf_prog *xdp_prog) +static __always_inline int +__xdp_do_redirect_frame(struct bpf_redirect_info *ri, struct net_device *dev, + struct xdp_frame *xdpf, + const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; @@ -4443,7 +4449,7 @@ err: } int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; @@ -4457,7 +4463,8 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, EXPORT_SYMBOL_GPL(xdp_do_redirect); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, - struct xdp_frame *xdpf, struct bpf_prog *xdp_prog) + struct xdp_frame *xdpf, + const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; @@ -4472,9 +4479,9 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, void *fwd, - enum bpf_map_type map_type, u32 map_id, - u32 flags) + const struct bpf_prog *xdp_prog, + void *fwd, enum bpf_map_type map_type, + u32 map_id, u32 flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct bpf_map *map; @@ -4528,7 +4535,8 @@ err: } int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct xdp_buff *xdp, struct bpf_prog *xdp_prog) + struct xdp_buff *xdp, + const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; @@ -7643,7 +7651,7 @@ static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; @@ -9070,7 +9078,8 @@ static bool xdp_is_valid_access(int off, int size, return __is_valid_xdp_access(off, size); } -void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act) +void bpf_warn_invalid_xdp_action(const struct net_device *dev, + const struct bpf_prog *prog, u32 act) { const u32 act_max = XDP_REDIRECT; @@ -11242,6 +11251,7 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; + int err; selected_sk = map->ops->map_lookup_elem(map, key); if (!selected_sk) @@ -11249,10 +11259,6 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, reuse = rcu_dereference(selected_sk->sk_reuseport_cb); if (!reuse) { - /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ - if (sk_is_refcounted(selected_sk)) - sock_put(selected_sk); - /* reuseport_array has only sk with non NULL sk_reuseport_cb. * The only (!reuse) case here is - the sk has already been * unhashed (e.g. by close()), so treat it as -ENOENT. @@ -11260,24 +11266,33 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, * Other maps (e.g. sock_map) do not provide this guarantee and * the sk may never be in the reuseport group to begin with. */ - return is_sockarray ? -ENOENT : -EINVAL; + err = is_sockarray ? -ENOENT : -EINVAL; + goto error; } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { struct sock *sk = reuse_kern->sk; - if (sk->sk_protocol != selected_sk->sk_protocol) - return -EPROTOTYPE; - else if (sk->sk_family != selected_sk->sk_family) - return -EAFNOSUPPORT; - - /* Catch all. Likely bound to a different sockaddr. */ - return -EBADFD; + if (sk->sk_protocol != selected_sk->sk_protocol) { + err = -EPROTOTYPE; + } else if (sk->sk_family != selected_sk->sk_family) { + err = -EAFNOSUPPORT; + } else { + /* Catch all. Likely bound to a different sockaddr. */ + err = -EBADFD; + } + goto error; } reuse_kern->selected_sk = selected_sk; return 0; +error: + /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ + if (sk_is_refcounted(selected_sk)) + sock_put(selected_sk); + + return err; } static const struct bpf_func_proto sk_select_reuseport_proto = { diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 1b4d39e38084..cb04ef2b9807 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -42,14 +42,18 @@ static unsigned int default_operstate(const struct net_device *dev) * first check whether lower is indeed the source of its down state. */ if (!netif_carrier_ok(dev)) { - int iflink = dev_get_iflink(dev); struct net_device *peer; + int iflink; /* If called from netdev_run_todo()/linkwatch_sync_dev(), * dev_net(dev) can be already freed, and RTNL is not held. */ - if (dev->reg_state == NETREG_UNREGISTERED || - iflink == dev->ifindex) + if (dev->reg_state <= NETREG_REGISTERED) + iflink = dev_get_iflink(dev); + else + iflink = dev->ifindex; + + if (iflink == dev->ifindex) return IF_OPER_DOWN; ASSERT_RTNL(); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 2d9afc6e2161..07cb99b114bd 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -36,7 +36,7 @@ static const char fmt_uint[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; -/* Caller holds RTNL or RCU */ +/* Caller holds RTNL, netdev->lock or RCU */ static inline int dev_isalive(const struct net_device *dev) { return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED; @@ -108,6 +108,36 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, return ret; } +/* Same as netdev_store() but takes netdev_lock() instead of rtnl_lock() */ +static ssize_t +netdev_lock_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len, + int (*set)(struct net_device *, unsigned long)) +{ + struct net_device *netdev = to_net_dev(dev); + struct net *net = dev_net(netdev); + unsigned long new; + int ret; + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + ret = kstrtoul(buf, 0, &new); + if (ret) + return ret; + + netdev_lock(netdev); + + if (dev_isalive(netdev)) { + ret = (*set)(netdev, new); + if (ret == 0) + ret = len; + } + netdev_unlock(netdev); + + return ret; +} + NETDEVICE_SHOW_RO(dev_id, fmt_hex); NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); @@ -420,7 +450,7 @@ static ssize_t gro_flush_timeout_store(struct device *dev, if (!capable(CAP_NET_ADMIN)) return -EPERM; - return netdev_store(dev, attr, buf, len, change_gro_flush_timeout); + return netdev_lock_store(dev, attr, buf, len, change_gro_flush_timeout); } NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); @@ -440,7 +470,8 @@ static ssize_t napi_defer_hard_irqs_store(struct device *dev, if (!capable(CAP_NET_ADMIN)) return -EPERM; - return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs); + return netdev_lock_store(dev, attr, buf, len, + change_napi_defer_hard_irqs); } NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint); @@ -638,7 +669,7 @@ static ssize_t threaded_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { - return netdev_store(dev, attr, buf, len, modify_napi_threaded); + return netdev_lock_store(dev, attr, buf, len, modify_napi_threaded); } static DEVICE_ATTR_RW(threaded); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b5cd3ae4f04c..cb39a12b2f82 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -588,6 +588,8 @@ static void unhash_nsid(struct net *net, struct net *last) static LLIST_HEAD(cleanup_list); +struct task_struct *cleanup_net_task; + static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; @@ -596,6 +598,8 @@ static void cleanup_net(struct work_struct *work) LIST_HEAD(net_exit_list); LIST_HEAD(dev_kill_list); + cleanup_net_task = current; + /* Atomically snapshot the list of namespaces to cleanup */ net_kill_list = llist_del_all(&cleanup_list); @@ -670,6 +674,7 @@ static void cleanup_net(struct work_struct *work) put_user_ns(net->user_ns); net_free(net); } + cleanup_net_task = NULL; } /** diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index a89cbd8d87c3..996ac6a449eb 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -197,6 +197,16 @@ static const struct genl_multicast_group netdev_nl_mcgrps[] = { [NETDEV_NLGRP_PAGE_POOL] = { "page-pool", }, }; +static void __netdev_nl_sock_priv_init(void *priv) +{ + netdev_nl_sock_priv_init(priv); +} + +static void __netdev_nl_sock_priv_destroy(void *priv) +{ + netdev_nl_sock_priv_destroy(priv); +} + struct genl_family netdev_nl_family __ro_after_init = { .name = NETDEV_FAMILY_NAME, .version = NETDEV_FAMILY_VERSION, @@ -208,6 +218,6 @@ struct genl_family netdev_nl_family __ro_after_init = { .mcgrps = netdev_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), .sock_priv_size = sizeof(struct list_head), - .sock_priv_init = (void *)netdev_nl_sock_priv_init, - .sock_priv_destroy = (void *)netdev_nl_sock_priv_destroy, + .sock_priv_init = __netdev_nl_sock_priv_init, + .sock_priv_destroy = __netdev_nl_sock_priv_destroy, }; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 9527dd46e4dc..715f85c6b62e 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -167,17 +167,14 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, void *hdr; pid_t pid; - if (WARN_ON_ONCE(!napi->dev)) - return -EINVAL; - if (!(napi->dev->flags & IFF_UP)) + if (!napi->dev->up) return 0; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; - if (napi->napi_id >= MIN_NAPI_ID && - nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) + if (nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) goto nla_put_failure; if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex)) @@ -232,22 +229,21 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) if (!rsp) return -ENOMEM; - rtnl_lock(); - rcu_read_lock(); - - napi = napi_by_id(napi_id); + napi = netdev_napi_by_id_lock(genl_info_net(info), napi_id); if (napi) { err = netdev_nl_napi_fill_one(rsp, napi, info); + netdev_unlock(napi->dev); } else { NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]); err = -ENOENT; } - rcu_read_unlock(); - rtnl_unlock(); - - if (err) + if (err) { goto err_free_msg; + } else if (!rsp->len) { + err = -ENOENT; + goto err_free_msg; + } return genlmsg_reply(rsp, info); @@ -262,12 +258,21 @@ netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, struct netdev_nl_dump_ctx *ctx) { struct napi_struct *napi; + unsigned int prev_id; int err = 0; - if (!(netdev->flags & IFF_UP)) + if (!netdev->up) return err; + prev_id = UINT_MAX; list_for_each_entry(napi, &netdev->napi_list, dev_list) { + if (napi->napi_id < MIN_NAPI_ID) + continue; + + /* Dump continuation below depends on the list being sorted */ + WARN_ON_ONCE(napi->napi_id >= prev_id); + prev_id = napi->napi_id; + if (ctx->napi_id && napi->napi_id >= ctx->napi_id) continue; @@ -291,22 +296,22 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) if (info->attrs[NETDEV_A_NAPI_IFINDEX]) ifindex = nla_get_u32(info->attrs[NETDEV_A_NAPI_IFINDEX]); - rtnl_lock(); if (ifindex) { - netdev = __dev_get_by_index(net, ifindex); - if (netdev) + netdev = netdev_get_by_index_lock(net, ifindex); + if (netdev) { err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); - else + netdev_unlock(netdev); + } else { err = -ENODEV; + } } else { - for_each_netdev_dump(net, netdev, ctx->ifindex) { + for_each_netdev_lock_scoped(net, netdev, ctx->ifindex) { err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); if (err < 0) break; ctx->napi_id = 0; } } - rtnl_unlock(); return err; } @@ -347,20 +352,15 @@ int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info) napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]); - rtnl_lock(); - rcu_read_lock(); - - napi = napi_by_id(napi_id); + napi = netdev_napi_by_id_lock(genl_info_net(info), napi_id); if (napi) { err = netdev_nl_napi_set_config(napi, info); + netdev_unlock(napi->dev); } else { NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]); err = -ENOENT; } - rcu_read_unlock(); - rtnl_unlock(); - return err; } @@ -430,10 +430,10 @@ static int netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { - int err = 0; + int err; - if (!(netdev->flags & IFF_UP)) - return err; + if (!netdev->up) + return -ENOENT; err = netdev_nl_queue_validate(netdev, q_idx, q_type); if (err) @@ -464,11 +464,13 @@ int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - netdev = __dev_get_by_index(genl_info_net(info), ifindex); - if (netdev) + netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex); + if (netdev) { err = netdev_nl_queue_fill(rsp, netdev, q_id, q_type, info); - else + netdev_unlock(netdev); + } else { err = -ENODEV; + } rtnl_unlock(); @@ -488,24 +490,21 @@ netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, struct netdev_nl_dump_ctx *ctx) { int err = 0; - int i; - if (!(netdev->flags & IFF_UP)) + if (!netdev->up) return err; - for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->rxq_idx < netdev->real_num_rx_queues; ctx->rxq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->rxq_idx, NETDEV_QUEUE_TYPE_RX, info); if (err) return err; - ctx->rxq_idx = i++; } - for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->txq_idx < netdev->real_num_tx_queues; ctx->txq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->txq_idx, NETDEV_QUEUE_TYPE_TX, info); if (err) return err; - ctx->txq_idx = i++; } return err; @@ -525,13 +524,15 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); if (ifindex) { - netdev = __dev_get_by_index(net, ifindex); - if (netdev) + netdev = netdev_get_by_index_lock(net, ifindex); + if (netdev) { err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); - else + netdev_unlock(netdev); + } else { err = -ENODEV; + } } else { - for_each_netdev_dump(net, netdev, ctx->ifindex) { + for_each_netdev_lock_scoped(net, netdev, ctx->ifindex) { err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); if (err < 0) break; @@ -671,7 +672,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->rxq_idx = i++; + ctx->rxq_idx = ++i; } i = ctx->txq_idx; while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { @@ -679,7 +680,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->txq_idx = i++; + ctx->txq_idx = ++i; } ctx->rxq_idx = 0; diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c index e217a5838c87..db82786fa0c4 100644 --- a/net/core/netdev_rx_queue.c +++ b/net/core/netdev_rx_queue.c @@ -79,3 +79,4 @@ err_free_new_mem: return err; } +EXPORT_SYMBOL_NS_GPL(netdev_rx_queue_restart, "NETDEV_INTERNAL"); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2e459b9d88eb..62b4041aae1a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -390,7 +390,7 @@ netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) } EXPORT_SYMBOL(netpoll_send_skb); -void netpoll_send_udp(struct netpoll *np, const char *msg, int len) +int netpoll_send_udp(struct netpoll *np, const char *msg, int len) { int total_len, ip_len, udp_len; struct sk_buff *skb; @@ -414,7 +414,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) skb = find_skb(np, total_len + np->dev->needed_tailroom, total_len - len); if (!skb) - return; + return -ENOMEM; skb_copy_to_linear_data(skb, msg, len); skb_put(skb, len); @@ -490,7 +490,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) skb->dev = np->dev; - netpoll_send_skb(np, skb); + return (int)netpoll_send_skb(np, skb); } EXPORT_SYMBOL(netpoll_send_udp); @@ -627,6 +627,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) const struct net_device_ops *ops; int err; + skb_queue_head_init(&np->skb_pool); + if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", ndev->name); @@ -634,7 +636,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) goto out; } - if (!rcu_access_pointer(ndev->npinfo)) { + npinfo = rtnl_dereference(ndev->npinfo); + if (!npinfo) { npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); if (!npinfo) { err = -ENOMEM; @@ -654,7 +657,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) goto free_npinfo; } } else { - npinfo = rtnl_dereference(ndev->npinfo); refcount_inc(&npinfo->refcnt); } @@ -662,6 +664,9 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) strscpy(np->dev_name, ndev->name, IFNAMSIZ); npinfo->netpoll = np; + /* fill up the skb queue */ + refill_skbs(np); + /* last thing to do is link it to the net device structure */ rcu_assign_pointer(ndev->npinfo, npinfo); @@ -681,8 +686,6 @@ int netpoll_setup(struct netpoll *np) struct in_device *in_dev; int err; - skb_queue_head_init(&np->skb_pool); - rtnl_lock(); if (np->dev_name[0]) { struct net *net = current->nsproxy->net_ns; @@ -782,9 +785,6 @@ put_noaddr: } } - /* fill up the skb queue */ - refill_skbs(np); - err = __netpoll_setup(np, ndev); if (err) goto flush; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index f89cf93f6eb4..f5e908c9e7ad 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -201,6 +201,7 @@ static int page_pool_init(struct page_pool *pool, memcpy(&pool->slow, ¶ms->slow, sizeof(pool->slow)); pool->cpuid = cpuid; + pool->dma_sync_for_cpu = true; /* Validate only known flags were used */ if (pool->slow.flags & ~PP_FLAG_ALL) @@ -287,6 +288,9 @@ static int page_pool_init(struct page_pool *pool, } if (pool->mp_priv) { + if (!pool->dma_map || !pool->dma_sync) + return -EOPNOTSUPP; + err = mp_dmabuf_devmem_init(pool); if (err) { pr_warn("%s() mem-provider init failed %d\n", __func__, @@ -532,12 +536,11 @@ static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool, if (unlikely(pool->alloc.count > 0)) return pool->alloc.cache[--pool->alloc.count]; - /* Mark empty alloc.cache slots "empty" for alloc_pages_bulk_array */ + /* Mark empty alloc.cache slots "empty" for alloc_pages_bulk */ memset(&pool->alloc.cache, 0, sizeof(void *) * bulk); - nr_pages = alloc_pages_bulk_array_node(gfp, - pool->p.nid, bulk, - (struct page **)pool->alloc.cache); + nr_pages = alloc_pages_bulk_node(gfp, pool->p.nid, bulk, + (struct page **)pool->alloc.cache); if (unlikely(!nr_pages)) return 0; @@ -574,7 +577,7 @@ static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool, /* For using page_pool replace: alloc_pages() API calls, but provide * synchronization guarantee for allocation side. */ -netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp) +netmem_ref page_pool_alloc_netmems(struct page_pool *pool, gfp_t gfp) { netmem_ref netmem; @@ -590,14 +593,14 @@ netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp) netmem = __page_pool_alloc_pages_slow(pool, gfp); return netmem; } -EXPORT_SYMBOL(page_pool_alloc_netmem); +EXPORT_SYMBOL(page_pool_alloc_netmems); +ALLOW_ERROR_INJECTION(page_pool_alloc_netmems, NULL); struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) { - return netmem_to_page(page_pool_alloc_netmem(pool, gfp)); + return netmem_to_page(page_pool_alloc_netmems(pool, gfp)); } EXPORT_SYMBOL(page_pool_alloc_pages); -ALLOW_ERROR_INJECTION(page_pool_alloc_pages, NULL); /* Calculate distance between two u32 values, valid if distance is below 2^(31) * https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution @@ -839,69 +842,104 @@ void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, } EXPORT_SYMBOL(page_pool_put_unrefed_page); -/** - * page_pool_put_page_bulk() - release references on multiple pages - * @pool: pool from which pages were allocated - * @data: array holding page pointers - * @count: number of pages in @data - * - * Tries to refill a number of pages into the ptr_ring cache holding ptr_ring - * producer lock. If the ptr_ring is full, page_pool_put_page_bulk() - * will release leftover pages to the page allocator. - * page_pool_put_page_bulk() is suitable to be run inside the driver NAPI tx - * completion loop for the XDP_REDIRECT use case. - * - * Please note the caller must not use data area after running - * page_pool_put_page_bulk(), as this function overwrites it. - */ -void page_pool_put_page_bulk(struct page_pool *pool, void **data, - int count) +static void page_pool_recycle_ring_bulk(struct page_pool *pool, + netmem_ref *bulk, + u32 bulk_len) { - int i, bulk_len = 0; - bool allow_direct; bool in_softirq; + u32 i; - allow_direct = page_pool_napi_local(pool); - - for (i = 0; i < count; i++) { - netmem_ref netmem = page_to_netmem(virt_to_head_page(data[i])); - - /* It is not the last user for the page frag case */ - if (!page_pool_is_last_ref(netmem)) - continue; - - netmem = __page_pool_put_page(pool, netmem, -1, allow_direct); - /* Approved for bulk recycling in ptr_ring cache */ - if (netmem) - data[bulk_len++] = (__force void *)netmem; - } - - if (!bulk_len) - return; - - /* Bulk producer into ptr_ring page_pool cache */ + /* Bulk produce into ptr_ring page_pool cache */ in_softirq = page_pool_producer_lock(pool); + for (i = 0; i < bulk_len; i++) { - if (__ptr_ring_produce(&pool->ring, data[i])) { + if (__ptr_ring_produce(&pool->ring, (__force void *)bulk[i])) { /* ring full */ recycle_stat_inc(pool, ring_full); break; } } - recycle_stat_add(pool, ring, i); - page_pool_producer_unlock(pool, in_softirq); - /* Hopefully all pages was return into ptr_ring */ + page_pool_producer_unlock(pool, in_softirq); + recycle_stat_add(pool, ring, i); + + /* Hopefully all pages were returned into ptr_ring */ if (likely(i == bulk_len)) return; - /* ptr_ring cache full, free remaining pages outside producer lock - * since put_page() with refcnt == 1 can be an expensive operation + /* + * ptr_ring cache is full, free remaining pages outside producer lock + * since put_page() with refcnt == 1 can be an expensive operation. */ for (; i < bulk_len; i++) - page_pool_return_page(pool, (__force netmem_ref)data[i]); + page_pool_return_page(pool, bulk[i]); } -EXPORT_SYMBOL(page_pool_put_page_bulk); + +/** + * page_pool_put_netmem_bulk() - release references on multiple netmems + * @data: array holding netmem references + * @count: number of entries in @data + * + * Tries to refill a number of netmems into the ptr_ring cache holding ptr_ring + * producer lock. If the ptr_ring is full, page_pool_put_netmem_bulk() + * will release leftover netmems to the memory provider. + * page_pool_put_netmem_bulk() is suitable to be run inside the driver NAPI tx + * completion loop for the XDP_REDIRECT use case. + * + * Please note the caller must not use data area after running + * page_pool_put_netmem_bulk(), as this function overwrites it. + */ +void page_pool_put_netmem_bulk(netmem_ref *data, u32 count) +{ + u32 bulk_len = 0; + + for (u32 i = 0; i < count; i++) { + netmem_ref netmem = netmem_compound_head(data[i]); + + if (page_pool_unref_and_test(netmem)) + data[bulk_len++] = netmem; + } + + count = bulk_len; + while (count) { + netmem_ref bulk[XDP_BULK_QUEUE_SIZE]; + struct page_pool *pool = NULL; + bool allow_direct; + u32 foreign = 0; + + bulk_len = 0; + + for (u32 i = 0; i < count; i++) { + struct page_pool *netmem_pp; + netmem_ref netmem = data[i]; + + netmem_pp = netmem_get_pp(netmem); + if (unlikely(!pool)) { + pool = netmem_pp; + allow_direct = page_pool_napi_local(pool); + } else if (netmem_pp != pool) { + /* + * If the netmem belongs to a different + * page_pool, save it for another round. + */ + data[foreign++] = netmem; + continue; + } + + netmem = __page_pool_put_page(pool, netmem, -1, + allow_direct); + /* Approved for bulk recycling in ptr_ring cache */ + if (netmem) + bulk[bulk_len++] = netmem; + } + + if (bulk_len) + page_pool_recycle_ring_bulk(pool, bulk, bulk_len); + + count = foreign; + } +} +EXPORT_SYMBOL(page_pool_put_netmem_bulk); static netmem_ref page_pool_drain_frag(struct page_pool *pool, netmem_ref netmem) @@ -957,7 +995,7 @@ netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, } if (!netmem) { - netmem = page_pool_alloc_netmem(pool, gfp); + netmem = page_pool_alloc_netmems(pool, gfp); if (unlikely(!netmem)) { pool->frag_page = 0; return 0; @@ -1108,7 +1146,9 @@ void page_pool_disable_direct_recycling(struct page_pool *pool) WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state)); WARN_ON(READ_ONCE(pool->p.napi->list_owner) != -1); + mutex_lock(&page_pools_lock); WRITE_ONCE(pool->p.napi, NULL); + mutex_unlock(&page_pools_lock); } EXPORT_SYMBOL(page_pool_disable_direct_recycling); diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h index 57439787b9c2..2fb06d5f6d55 100644 --- a/net/core/page_pool_priv.h +++ b/net/core/page_pool_priv.h @@ -7,6 +7,8 @@ #include "netmem_priv.h" +extern struct mutex page_pools_lock; + s32 page_pool_inflight(const struct page_pool *pool, bool strict); int page_pool_list(struct page_pool *pool); diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 48335766c1bf..6677e0c2e256 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include @@ -14,10 +15,11 @@ #include "netdev-genl-gen.h" static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1); -/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user. +/* Protects: page_pools, netdevice->page_pools, pool->p.napi, pool->slow.netdev, + * pool->user. * Ordering: inside rtnl_lock */ -static DEFINE_MUTEX(page_pools_lock); +DEFINE_MUTEX(page_pools_lock); /* Page pools are only reachable from user space (via netlink) if they are * linked to a netdev at creation time. Following page pool "visibility" @@ -216,6 +218,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, { struct net_devmem_dmabuf_binding *binding = pool->mp_priv; size_t inflight, refsz; + unsigned int napi_id; void *hdr; hdr = genlmsg_iput(rsp, info); @@ -229,8 +232,10 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, pool->slow.netdev->ifindex)) goto err_cancel; - if (pool->user.napi_id && - nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id)) + + napi_id = pool->p.napi ? READ_ONCE(pool->p.napi->napi_id) : 0; + if (napi_id >= MIN_NAPI_ID && + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, napi_id)) goto err_cancel; inflight = page_pool_inflight(pool, false); @@ -319,8 +324,6 @@ int page_pool_list(struct page_pool *pool) if (pool->slow.netdev) { hlist_add_head(&pool->user.list, &pool->slow.netdev->page_pools); - pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0; - netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF); } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 7e23cacbe66e..82b6a2c3c141 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -851,6 +851,9 @@ static ssize_t get_imix_entries(const char __user *buffer, unsigned long weight; unsigned long size; + if (pkt_dev->n_imix_entries >= MAX_IMIX_ENTRIES) + return -E2BIG; + len = num_arg(&buffer[i], max_digits, &size); if (len < 0) return len; @@ -880,9 +883,6 @@ static ssize_t get_imix_entries(const char __user *buffer, i++; pkt_dev->n_imix_entries++; - - if (pkt_dev->n_imix_entries > MAX_IMIX_ENTRIES) - return -E2BIG; } while (c == ' '); return i; @@ -3883,17 +3883,14 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) list_add_tail(&t->th_list, &pn->pktgen_threads); init_completion(&t->start_done); - p = kthread_create_on_node(pktgen_thread_worker, - t, - cpu_to_node(cpu), - "kpktgend_%d", cpu); + p = kthread_create_on_cpu(pktgen_thread_worker, t, cpu, "kpktgend_%d"); if (IS_ERR(p)) { pr_err("kthread_create_on_node() failed for cpu %d\n", t->cpu); list_del(&t->th_list); kfree(t); return PTR_ERR(p); } - kthread_bind(p, cpu); + t->tsk = p; pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ebcfc2debf1a..1f4d4b5570ab 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -84,7 +84,6 @@ int rtnl_lock_killable(void) { return mutex_lock_killable(&rtnl_mutex); } -EXPORT_SYMBOL(rtnl_lock_killable); static struct sk_buff *defer_kfree_skb_list; void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail) @@ -221,6 +220,16 @@ int rtnl_net_trylock(struct net *net) } EXPORT_SYMBOL(rtnl_net_trylock); +int rtnl_net_lock_killable(struct net *net) +{ + int ret = rtnl_lock_killable(); + + if (!ret) + __rtnl_net_lock(net); + + return ret; +} + static int rtnl_net_cmp_locks(const struct net *net_a, const struct net *net_b) { if (net_eq(net_a, net_b)) @@ -3819,6 +3828,7 @@ out_unregister: } static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops, + struct nlattr *tbp[], struct nlattr *data[], struct netlink_ext_ack *extack) { @@ -3826,7 +3836,7 @@ static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops, int err; if (!data || !data[ops->peer_type]) - return NULL; + return rtnl_link_get_net_ifla(tbp); err = rtnl_nla_parse_ifinfomsg(tb, data[ops->peer_type], extack); if (err < 0) @@ -3971,7 +3981,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, } if (ops->peer_type) { - peer_net = rtnl_get_peer_net(ops, data, extack); + peer_net = rtnl_get_peer_net(ops, tb, data, extack); if (IS_ERR(peer_net)) { ret = PTR_ERR(peer_net); goto put_ops; @@ -4764,15 +4774,16 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, int *idx, struct netdev_hw_addr_list *list) { + struct ndo_fdb_dump_context *ctx = (void *)cb->ctx; struct netdev_hw_addr *ha; - int err; u32 portid, seq; + int err; portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; list_for_each_entry(ha, &list->list, list) { - if (*idx < cb->args[2]) + if (*idx < ctx->fdb_idx) goto skip; err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0, @@ -4911,18 +4922,16 @@ static int valid_fdb_dump_legacy(const struct nlmsghdr *nlh, static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) { - struct net_device *dev; - struct net_device *br_dev = NULL; - const struct net_device_ops *ops = NULL; - const struct net_device_ops *cops = NULL; + const struct net_device_ops *ops = NULL, *cops = NULL; + struct ndo_fdb_dump_context *ctx = (void *)cb->ctx; + struct net_device *dev, *br_dev = NULL; struct net *net = sock_net(skb->sk); - struct hlist_head *head; int brport_idx = 0; int br_idx = 0; - int h, s_h; - int idx = 0, s_idx; - int err = 0; int fidx = 0; + int err; + + NL_ASSERT_CTX_FITS(struct ndo_fdb_dump_context); if (cb->strict_check) err = valid_fdb_dump_strict(cb->nlh, &br_idx, &brport_idx, @@ -4941,70 +4950,51 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) ops = br_dev->netdev_ops; } - s_h = cb->args[0]; - s_idx = cb->args[1]; + for_each_netdev_dump(net, dev, ctx->ifindex) { + if (brport_idx && (dev->ifindex != brport_idx)) + continue; - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - hlist_for_each_entry(dev, head, index_hlist) { - - if (brport_idx && (dev->ifindex != brport_idx)) + if (!br_idx) { /* user did not specify a specific bridge */ + if (netif_is_bridge_port(dev)) { + br_dev = netdev_master_upper_dev_get(dev); + cops = br_dev->netdev_ops; + } + } else { + if (dev != br_dev && + !netif_is_bridge_port(dev)) continue; - if (!br_idx) { /* user did not specify a specific bridge */ - if (netif_is_bridge_port(dev)) { - br_dev = netdev_master_upper_dev_get(dev); - cops = br_dev->netdev_ops; - } - } else { - if (dev != br_dev && - !netif_is_bridge_port(dev)) - continue; - - if (br_dev != netdev_master_upper_dev_get(dev) && - !netif_is_bridge_master(dev)) - continue; - cops = ops; - } - - if (idx < s_idx) - goto cont; - - if (netif_is_bridge_port(dev)) { - if (cops && cops->ndo_fdb_dump) { - err = cops->ndo_fdb_dump(skb, cb, - br_dev, dev, - &fidx); - if (err == -EMSGSIZE) - goto out; - } - } - - if (dev->netdev_ops->ndo_fdb_dump) - err = dev->netdev_ops->ndo_fdb_dump(skb, cb, - dev, NULL, - &fidx); - else - err = ndo_dflt_fdb_dump(skb, cb, dev, NULL, - &fidx); - if (err == -EMSGSIZE) - goto out; - - cops = NULL; - - /* reset fdb offset to 0 for rest of the interfaces */ - cb->args[2] = 0; - fidx = 0; -cont: - idx++; + if (br_dev != netdev_master_upper_dev_get(dev) && + !netif_is_bridge_master(dev)) + continue; + cops = ops; } + + if (netif_is_bridge_port(dev)) { + if (cops && cops->ndo_fdb_dump) { + err = cops->ndo_fdb_dump(skb, cb, br_dev, dev, + &fidx); + if (err == -EMSGSIZE) + break; + } + } + + if (dev->netdev_ops->ndo_fdb_dump) + err = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, + &fidx); + else + err = ndo_dflt_fdb_dump(skb, cb, dev, NULL, &fidx); + if (err == -EMSGSIZE) + break; + + cops = NULL; + + /* reset fdb offset to 0 for rest of the interfaces */ + ctx->fdb_idx = 0; + fidx = 0; } -out: - cb->args[0] = h; - cb->args[1] = idx; - cb->args[2] = fidx; + ctx->fdb_idx = fidx; return skb->len; } diff --git a/net/core/rtnl_net_debug.c b/net/core/rtnl_net_debug.c index f406045cbd0e..7ecd28cc1c22 100644 --- a/net/core/rtnl_net_debug.c +++ b/net/core/rtnl_net_debug.c @@ -27,7 +27,6 @@ static int rtnl_net_debug_event(struct notifier_block *nb, case NETDEV_CHANGEADDR: case NETDEV_PRE_CHANGEADDR: case NETDEV_GOING_DOWN: - case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: case NETDEV_BONDING_FAILOVER: case NETDEV_PRE_UP: @@ -60,18 +59,10 @@ static int rtnl_net_debug_event(struct notifier_block *nb, ASSERT_RTNL(); break; - /* Once an event fully supports RTNL_NET, move it here - * and remove "if (0)" below. - * - * case NETDEV_XXX: - * ASSERT_RTNL_NET(net); - * break; - */ - } - - /* Just to avoid unused-variable error for dev and net. */ - if (0) + case NETDEV_CHANGENAME: ASSERT_RTNL_NET(net); + break; + } return NOTIFY_DONE; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6841e61a6bd0..a441613a1e6c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1009,7 +1009,7 @@ int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, EXPORT_SYMBOL(skb_pp_cow_data); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, - struct bpf_prog *prog) + const struct bpf_prog *prog) { if (!prog->aux->xdp_has_frags) return -EINVAL; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index e90fbab703b2..61f3f3d4e528 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -369,8 +369,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes) { int ret = -ENOSPC, i = msg->sg.curr; + u32 copy, buf_size, copied = 0; struct scatterlist *sge; - u32 copy, buf_size; void *to; do { @@ -397,6 +397,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, goto out; } bytes -= copy; + copied += copy; if (!bytes) break; msg->sg.copybreak = 0; @@ -404,7 +405,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, } while (i != msg->sg.end); out: msg->sg.curr = i; - return ret; + return (ret < 0) ? ret : copied; } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); @@ -445,8 +446,10 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - if (!msg_rx->skb) + if (!msg_rx->skb) { sk_mem_uncharge(sk, copy); + atomic_sub(copy, &sk->sk_rmem_alloc); + } msg_rx->sg.size -= copy; if (!sge->length) { @@ -772,6 +775,8 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock) list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) { list_del(&msg->list); + if (!msg->skb) + atomic_sub(msg->sg.size, &psock->sk->sk_rmem_alloc); sk_msg_free(psock->sk, msg); kfree(msg); } diff --git a/net/core/sock.c b/net/core/sock.c index 74729d20cd00..eae2ae70a2e0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -454,6 +454,13 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return 0; } +static bool sk_set_prio_allowed(const struct sock *sk, int val) +{ + return ((val >= TC_PRIO_BESTEFFORT && val <= TC_PRIO_INTERACTIVE) || + sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || + sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); +} + static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { @@ -1193,9 +1200,7 @@ int sk_setsockopt(struct sock *sk, int level, int optname, /* handle options which do not require locking the socket. */ switch (optname) { case SO_PRIORITY: - if ((val >= 0 && val <= 6) || - sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || - sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + if (sk_set_prio_allowed(sk, val)) { sock_set_priority(sk, val); return 0; } @@ -1295,7 +1300,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname, sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; case SO_REUSEPORT: - sk->sk_reuseport = valbool; + if (valbool && !sk_is_inet(sk)) + ret = -EOPNOTSUPP; + else + sk->sk_reuseport = valbool; break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); @@ -1514,6 +1522,10 @@ set_sndbuf: sock_valbool_flag(sk, SOCK_RCVMARK, valbool); break; + case SO_RCVPRIORITY: + sock_valbool_flag(sk, SOCK_RCVPRIORITY, valbool); + break; + case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; @@ -1942,6 +1954,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname, v.val = sock_flag(sk, SOCK_RCVMARK); break; + case SO_RCVPRIORITY: + v.val = sock_flag(sk, SOCK_RCVPRIORITY); + break; + case SO_RXQ_OVFL: v.val = sock_flag(sk, SOCK_RXQ_OVFL); break; @@ -2942,6 +2958,13 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, case SCM_RIGHTS: case SCM_CREDENTIALS: break; + case SO_PRIORITY: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + if (!sk_set_prio_allowed(sk, *(u32 *)CMSG_DATA(cmsg))) + return -EPERM; + sockc->priority = *(u32 *)CMSG_DATA(cmsg); + break; default: return -EINVAL; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index cb8d32e5c14e..ad2741f1346a 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -319,7 +319,7 @@ static int proc_do_dev_weight(const struct ctl_table *table, int write, int ret, weight; mutex_lock(&dev_weight_mutex); - ret = proc_dointvec(table, write, buffer, lenp, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) { weight = READ_ONCE(weight_p); WRITE_ONCE(net_hotdata.dev_rx_weight, weight * dev_weight_rx_bias); @@ -412,6 +412,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_dev_weight, + .extra1 = SYSCTL_ONE, }, { .procname = "dev_weight_rx_bias", @@ -419,6 +420,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_dev_weight, + .extra1 = SYSCTL_ONE, }, { .procname = "dev_weight_tx_bias", @@ -426,6 +428,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_dev_weight, + .extra1 = SYSCTL_ONE, }, { .procname = "netdev_max_backlog", diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 3717fb152ecc..a50a7ef49ae8 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -9,6 +9,7 @@ #include #include #include +#include static unsigned int classify(const struct sk_buff *skb) { @@ -21,19 +22,39 @@ static unsigned int classify(const struct sk_buff *skb) void skb_clone_tx_timestamp(struct sk_buff *skb) { + struct hwtstamp_provider *hwprov; struct mii_timestamper *mii_ts; + struct phy_device *phydev; struct sk_buff *clone; unsigned int type; - if (!skb->sk || !skb->dev || - !phy_is_default_hwtstamp(skb->dev->phydev)) + if (!skb->sk || !skb->dev) return; + rcu_read_lock(); + hwprov = rcu_dereference(skb->dev->hwprov); + if (hwprov) { + if (hwprov->source != HWTSTAMP_SOURCE_PHYLIB || + !hwprov->phydev) { + rcu_read_unlock(); + return; + } + + phydev = hwprov->phydev; + } else { + phydev = skb->dev->phydev; + if (!phy_is_default_hwtstamp(phydev)) { + rcu_read_unlock(); + return; + } + } + rcu_read_unlock(); + type = classify(skb); if (type == PTP_CLASS_NONE) return; - mii_ts = skb->dev->phydev->mii_ts; + mii_ts = phydev->mii_ts; if (likely(mii_ts->txtstamp)) { clone = skb_clone_sk(skb); if (!clone) @@ -45,12 +66,33 @@ EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp); bool skb_defer_rx_timestamp(struct sk_buff *skb) { + struct hwtstamp_provider *hwprov; struct mii_timestamper *mii_ts; + struct phy_device *phydev; unsigned int type; - if (!skb->dev || !phy_is_default_hwtstamp(skb->dev->phydev)) + if (!skb->dev) return false; + rcu_read_lock(); + hwprov = rcu_dereference(skb->dev->hwprov); + if (hwprov) { + if (hwprov->source != HWTSTAMP_SOURCE_PHYLIB || + !hwprov->phydev) { + rcu_read_unlock(); + return false; + } + + phydev = hwprov->phydev; + } else { + phydev = skb->dev->phydev; + if (!phy_is_default_hwtstamp(phydev)) { + rcu_read_unlock(); + return false; + } + } + rcu_read_unlock(); + if (skb_headroom(skb) < ETH_HLEN) return false; @@ -63,7 +105,7 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) if (type == PTP_CLASS_NONE) return false; - mii_ts = skb->dev->phydev->mii_ts; + mii_ts = phydev->mii_ts; if (likely(mii_ts->rxtstamp)) return mii_ts->rxtstamp(mii_ts, skb, type); diff --git a/net/core/xdp.c b/net/core/xdp.c index bcc5551c6424..2c6ab6fb452f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -186,7 +186,6 @@ int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, xdp_rxq_info_init(xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; - xdp_rxq->napi_id = napi_id; xdp_rxq->frag_size = frag_size; xdp_rxq->reg_state = REG_STATE_REGISTERED; @@ -358,6 +357,9 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); + if (type == MEM_TYPE_XSK_BUFF_POOL && allocator) + xsk_pool_set_rxq_info(allocator, xdp_rxq); + if (trace_mem_connect_enabled() && xdp_alloc) trace_mem_connect(xdp_alloc, xdp_rxq); return 0; @@ -365,33 +367,87 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); +/** + * xdp_reg_page_pool - register &page_pool as a memory provider for XDP + * @pool: &page_pool to register + * + * Can be used to register pools manually without connecting to any XDP RxQ + * info, so that the XDP layer will be aware of them. Then, they can be + * attached to an RxQ info manually via xdp_rxq_info_attach_page_pool(). + * + * Return: %0 on success, -errno on error. + */ +int xdp_reg_page_pool(struct page_pool *pool) +{ + struct xdp_mem_info mem; + + return xdp_reg_mem_model(&mem, MEM_TYPE_PAGE_POOL, pool); +} +EXPORT_SYMBOL_GPL(xdp_reg_page_pool); + +/** + * xdp_unreg_page_pool - unregister &page_pool from the memory providers list + * @pool: &page_pool to unregister + * + * A shorthand for manual unregistering page pools. If the pool was previously + * attached to an RxQ info, it must be detached first. + */ +void xdp_unreg_page_pool(const struct page_pool *pool) +{ + struct xdp_mem_info mem = { + .type = MEM_TYPE_PAGE_POOL, + .id = pool->xdp_mem_id, + }; + + xdp_unreg_mem_model(&mem); +} +EXPORT_SYMBOL_GPL(xdp_unreg_page_pool); + +/** + * xdp_rxq_info_attach_page_pool - attach registered pool to RxQ info + * @xdp_rxq: XDP RxQ info to attach the pool to + * @pool: pool to attach + * + * If the pool was registered manually, this function must be called instead + * of xdp_rxq_info_reg_mem_model() to connect it to the RxQ info. + */ +void xdp_rxq_info_attach_page_pool(struct xdp_rxq_info *xdp_rxq, + const struct page_pool *pool) +{ + struct xdp_mem_info mem = { + .type = MEM_TYPE_PAGE_POOL, + .id = pool->xdp_mem_id, + }; + + xdp_rxq_info_attach_mem_model(xdp_rxq, &mem); +} +EXPORT_SYMBOL_GPL(xdp_rxq_info_attach_page_pool); + /* XDP RX runs under NAPI protection, and in different delivery error * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ -void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, - struct xdp_buff *xdp) +void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type, + bool napi_direct, struct xdp_buff *xdp) { - struct page *page; - - switch (mem->type) { + switch (mem_type) { case MEM_TYPE_PAGE_POOL: - page = virt_to_head_page(data); + netmem = netmem_compound_head(netmem); if (napi_direct && xdp_return_frame_no_direct()) napi_direct = false; /* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE) * as mem->type knows this a page_pool page */ - page_pool_put_full_page(page->pp, page, napi_direct); + page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, + napi_direct); break; case MEM_TYPE_PAGE_SHARED: - page_frag_free(data); + page_frag_free(__netmem_address(netmem)); break; case MEM_TYPE_PAGE_ORDER0: - page = virt_to_page(data); /* Assumes order0 page*/ - put_page(page); + put_page(__netmem_to_page(netmem)); break; case MEM_TYPE_XSK_BUFF_POOL: /* NB! Only valid from an xdp_buff! */ @@ -399,7 +455,7 @@ void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ - WARN(1, "Incorrect XDP memory type (%d) usage", mem->type); + WARN(1, "Incorrect XDP memory type (%d) usage", mem_type); break; } } @@ -407,38 +463,34 @@ void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, void xdp_return_frame(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; - int i; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); - for (i = 0; i < sinfo->nr_frags; i++) { - struct page *page = skb_frag_page(&sinfo->frags[i]); + for (u32 i = 0; i < sinfo->nr_frags; i++) + __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdpf->mem_type, + false, NULL); - __xdp_return(page_address(page), &xdpf->mem, false, NULL); - } out: - __xdp_return(xdpf->data, &xdpf->mem, false, NULL); + __xdp_return(virt_to_netmem(xdpf->data), xdpf->mem_type, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; - int i; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); - for (i = 0; i < sinfo->nr_frags; i++) { - struct page *page = skb_frag_page(&sinfo->frags[i]); + for (u32 i = 0; i < sinfo->nr_frags; i++) + __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdpf->mem_type, + true, NULL); - __xdp_return(page_address(page), &xdpf->mem, true, NULL); - } out: - __xdp_return(xdpf->data, &xdpf->mem, true, NULL); + __xdp_return(virt_to_netmem(xdpf->data), xdpf->mem_type, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); @@ -452,46 +504,19 @@ EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); * xdp_frame_bulk is usually stored/allocated on the function * call-stack to avoid locking penalties. */ -void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq) -{ - struct xdp_mem_allocator *xa = bq->xa; - - if (unlikely(!xa || !bq->count)) - return; - - page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count); - /* bq->xa is not cleared to save lookup, if mem.id same in next bulk */ - bq->count = 0; -} -EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk); /* Must be called with rcu_read_lock held */ void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq) { - struct xdp_mem_info *mem = &xdpf->mem; - struct xdp_mem_allocator *xa; - - if (mem->type != MEM_TYPE_PAGE_POOL) { + if (xdpf->mem_type != MEM_TYPE_PAGE_POOL) { xdp_return_frame(xdpf); return; } - xa = bq->xa; - if (unlikely(!xa)) { - xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); - bq->count = 0; - bq->xa = xa; - } - if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); - if (unlikely(mem->id != xa->mem.id)) { - xdp_flush_frame_bulk(bq); - bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); - } - if (unlikely(xdp_frame_has_frags(xdpf))) { struct skb_shared_info *sinfo; int i; @@ -500,31 +525,40 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf, for (i = 0; i < sinfo->nr_frags; i++) { skb_frag_t *frag = &sinfo->frags[i]; - bq->q[bq->count++] = skb_frag_address(frag); + bq->q[bq->count++] = skb_frag_netmem(frag); if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); } } - bq->q[bq->count++] = xdpf->data; + bq->q[bq->count++] = virt_to_netmem(xdpf->data); } EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); +/** + * xdp_return_frag -- free one XDP frag or decrement its refcount + * @netmem: network memory reference to release + * @xdp: &xdp_buff to release the frag for + */ +void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp) +{ + __xdp_return(netmem, xdp->rxq->mem.type, true, NULL); +} +EXPORT_SYMBOL_GPL(xdp_return_frag); + void xdp_return_buff(struct xdp_buff *xdp) { struct skb_shared_info *sinfo; - int i; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); - for (i = 0; i < sinfo->nr_frags; i++) { - struct page *page = skb_frag_page(&sinfo->frags[i]); + for (u32 i = 0; i < sinfo->nr_frags; i++) + __xdp_return(skb_frag_netmem(&sinfo->frags[i]), + xdp->rxq->mem.type, true, xdp); - __xdp_return(page_address(page), &xdp->rxq->mem, true, xdp); - } out: - __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp); + __xdp_return(virt_to_netmem(xdp->data), xdp->rxq->mem.type, true, xdp); } EXPORT_SYMBOL_GPL(xdp_return_buff); @@ -570,7 +604,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) xdpf->headroom = 0; xdpf->metasize = metasize; xdpf->frame_sz = PAGE_SIZE; - xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + xdpf->mem_type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); return xdpf; @@ -594,6 +628,173 @@ int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) } EXPORT_SYMBOL_GPL(xdp_alloc_skb_bulk); +/** + * xdp_build_skb_from_buff - create an skb from &xdp_buff + * @xdp: &xdp_buff to convert to an skb + * + * Perform common operations to create a new skb to pass up the stack from + * &xdp_buff: allocate an skb head from the NAPI percpu cache, initialize + * skb data pointers and offsets, set the recycle bit if the buff is + * PP-backed, Rx queue index, protocol and update frags info. + * + * Return: new &sk_buff on success, %NULL on error. + */ +struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp) +{ + const struct xdp_rxq_info *rxq = xdp->rxq; + const struct skb_shared_info *sinfo; + struct sk_buff *skb; + u32 nr_frags = 0; + int metalen; + + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } + + skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, xdp->data - xdp->data_hard_start); + __skb_put(skb, xdp->data_end - xdp->data); + + metalen = xdp->data - xdp->data_meta; + if (metalen > 0) + skb_metadata_set(skb, metalen); + + if (rxq->mem.type == MEM_TYPE_PAGE_POOL) + skb_mark_for_recycle(skb); + + skb_record_rx_queue(skb, rxq->queue_index); + + if (unlikely(nr_frags)) { + u32 tsize; + + tsize = sinfo->xdp_frags_truesize ? : nr_frags * xdp->frame_sz; + xdp_update_skb_shared_info(skb, nr_frags, + sinfo->xdp_frags_size, tsize, + xdp_buff_is_frag_pfmemalloc(xdp)); + } + + skb->protocol = eth_type_trans(skb, rxq->dev); + + return skb; +} +EXPORT_SYMBOL_GPL(xdp_build_skb_from_buff); + +/** + * xdp_copy_frags_from_zc - copy frags from XSk buff to skb + * @skb: skb to copy frags to + * @xdp: XSk &xdp_buff from which the frags will be copied + * @pp: &page_pool backing page allocation, if available + * + * Copy all frags from XSk &xdp_buff to the skb to pass it up the stack. + * Allocate a new buffer for each frag, copy it and attach to the skb. + * + * Return: true on success, false on netmem allocation fail. + */ +static noinline bool xdp_copy_frags_from_zc(struct sk_buff *skb, + const struct xdp_buff *xdp, + struct page_pool *pp) +{ + struct skb_shared_info *sinfo = skb_shinfo(skb); + const struct skb_shared_info *xinfo; + u32 nr_frags, tsize = 0; + bool pfmemalloc = false; + + xinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = xinfo->nr_frags; + + for (u32 i = 0; i < nr_frags; i++) { + u32 len = skb_frag_size(&xinfo->frags[i]); + u32 offset, truesize = len; + netmem_ref netmem; + + netmem = page_pool_dev_alloc_netmem(pp, &offset, &truesize); + if (unlikely(!netmem)) { + sinfo->nr_frags = i; + return false; + } + + memcpy(__netmem_address(netmem), + __netmem_address(xinfo->frags[i].netmem), + LARGEST_ALIGN(len)); + __skb_fill_netmem_desc_noacc(sinfo, i, netmem, offset, len); + + tsize += truesize; + pfmemalloc |= netmem_is_pfmemalloc(netmem); + } + + xdp_update_skb_shared_info(skb, nr_frags, xinfo->xdp_frags_size, + tsize, pfmemalloc); + + return true; +} + +/** + * xdp_build_skb_from_zc - create an skb from XSk &xdp_buff + * @xdp: source XSk buff + * + * Similar to xdp_build_skb_from_buff(), but for XSk frames. Allocate an skb + * head, new buffer for the head, copy the data and initialize the skb fields. + * If there are frags, allocate new buffers for them and copy. + * Buffers are allocated from the system percpu pools to try recycling them. + * If new skb was built successfully, @xdp is returned to XSk pool's freelist. + * On error, it remains untouched and the caller must take care of this. + * + * Return: new &sk_buff on success, %NULL on error. + */ +struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp) +{ + struct page_pool *pp = this_cpu_read(system_page_pool); + const struct xdp_rxq_info *rxq = xdp->rxq; + u32 len = xdp->data_end - xdp->data_meta; + u32 truesize = xdp->frame_sz; + struct sk_buff *skb; + int metalen; + void *data; + + if (!IS_ENABLED(CONFIG_PAGE_POOL)) + return NULL; + + data = page_pool_dev_alloc_va(pp, &truesize); + if (unlikely(!data)) + return NULL; + + skb = napi_build_skb(data, truesize); + if (unlikely(!skb)) { + page_pool_free_va(pp, data, true); + return NULL; + } + + skb_mark_for_recycle(skb); + skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); + + memcpy(__skb_put(skb, len), xdp->data_meta, LARGEST_ALIGN(len)); + + metalen = xdp->data - xdp->data_meta; + if (metalen > 0) { + skb_metadata_set(skb, metalen); + __skb_pull(skb, metalen); + } + + skb_record_rx_queue(skb, rxq->queue_index); + + if (unlikely(xdp_buff_has_frags(xdp)) && + unlikely(!xdp_copy_frags_from_zc(skb, xdp, pp))) { + napi_consume_skb(skb, true); + return NULL; + } + + xsk_buff_free(xdp); + + skb->protocol = eth_type_trans(skb, rxq->dev); + + return skb; +} +EXPORT_SYMBOL_GPL(xdp_build_skb_from_zc); + struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev) @@ -640,7 +841,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, * - RX ring dev queue index (skb_record_rx_queue) */ - if (xdpf->mem.type == MEM_TYPE_PAGE_POOL) + if (xdpf->mem_type == MEM_TYPE_PAGE_POOL) skb_mark_for_recycle(skb); /* Allow SKB to reuse area used by xdp_frame */ @@ -687,8 +888,7 @@ struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) nxdpf = addr; nxdpf->data = addr + headroom; nxdpf->frame_sz = PAGE_SIZE; - nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0; - nxdpf->mem.id = 0; + nxdpf->mem_type = MEM_TYPE_PAGE_ORDER0; return nxdpf; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5926159a6f20..be515ba821e2 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -15,6 +15,7 @@ #include #include +#include #include #include #include @@ -473,7 +474,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, .flowi4_oif = inet_iif(skb), .daddr = iph->saddr, .saddr = iph->daddr, - .flowi4_tos = ip_sock_rt_tos(sk), + .flowi4_tos = inet_dscp_to_dsfield(inet_sk_dscp(inet_sk(sk))), .flowi4_scope = ip_sock_rt_scope(sk), .flowi4_proto = sk->sk_protocol, .fl4_sport = dccp_hdr(skb)->dccph_dport, diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index 3fc474d6e57d..b15845fd6300 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -11,10 +11,6 @@ #include "dccp.h" #include "feat.h" -#ifndef CONFIG_SYSCTL -#error This file should not be compiled without CONFIG_SYSCTL defined -#endif - /* Boundary values */ static int u8_max = 0xFF; static unsigned long seqw_min = DCCPF_SEQ_WMIN, diff --git a/net/devlink/health.c b/net/devlink/health.c index b8d3084e6fe0..57db6799722a 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -1238,3 +1238,70 @@ int devlink_nl_health_reporter_test_doit(struct sk_buff *skb, return reporter->ops->test(reporter, info->extack); } + +/** + * devlink_fmsg_dump_skb - Dump sk_buffer structure + * @fmsg: devlink formatted message pointer + * @skb: pointer to skb + * + * Dump diagnostic information about sk_buff structure, like headroom, length, + * tailroom, MAC, etc. + */ +void devlink_fmsg_dump_skb(struct devlink_fmsg *fmsg, const struct sk_buff *skb) +{ + struct skb_shared_info *sh = skb_shinfo(skb); + struct sock *sk = skb->sk; + bool has_mac, has_trans; + + has_mac = skb_mac_header_was_set(skb); + has_trans = skb_transport_header_was_set(skb); + + devlink_fmsg_pair_nest_start(fmsg, "skb"); + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_put(fmsg, "actual len", skb->len); + devlink_fmsg_put(fmsg, "head len", skb_headlen(skb)); + devlink_fmsg_put(fmsg, "data len", skb->data_len); + devlink_fmsg_put(fmsg, "tail len", skb_tailroom(skb)); + devlink_fmsg_put(fmsg, "MAC", has_mac ? skb->mac_header : -1); + devlink_fmsg_put(fmsg, "MAC len", + has_mac ? skb_mac_header_len(skb) : -1); + devlink_fmsg_put(fmsg, "network hdr", skb->network_header); + devlink_fmsg_put(fmsg, "network hdr len", + has_trans ? skb_network_header_len(skb) : -1); + devlink_fmsg_put(fmsg, "transport hdr", + has_trans ? skb->transport_header : -1); + devlink_fmsg_put(fmsg, "csum", (__force u32)skb->csum); + devlink_fmsg_put(fmsg, "csum_ip_summed", (u8)skb->ip_summed); + devlink_fmsg_put(fmsg, "csum_complete_sw", !!skb->csum_complete_sw); + devlink_fmsg_put(fmsg, "csum_valid", !!skb->csum_valid); + devlink_fmsg_put(fmsg, "csum_level", (u8)skb->csum_level); + devlink_fmsg_put(fmsg, "sw_hash", !!skb->sw_hash); + devlink_fmsg_put(fmsg, "l4_hash", !!skb->l4_hash); + devlink_fmsg_put(fmsg, "proto", ntohs(skb->protocol)); + devlink_fmsg_put(fmsg, "pkt_type", (u8)skb->pkt_type); + devlink_fmsg_put(fmsg, "iif", skb->skb_iif); + + if (sk) { + devlink_fmsg_pair_nest_start(fmsg, "sk"); + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_put(fmsg, "family", sk->sk_type); + devlink_fmsg_put(fmsg, "type", sk->sk_type); + devlink_fmsg_put(fmsg, "proto", sk->sk_protocol); + devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_pair_nest_end(fmsg); + } + + devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_pair_nest_end(fmsg); + + devlink_fmsg_pair_nest_start(fmsg, "shinfo"); + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_put(fmsg, "tx_flags", sh->tx_flags); + devlink_fmsg_put(fmsg, "nr_frags", sh->nr_frags); + devlink_fmsg_put(fmsg, "gso_size", sh->gso_size); + devlink_fmsg_put(fmsg, "gso_type", sh->gso_type); + devlink_fmsg_put(fmsg, "gso_segs", sh->gso_segs); + devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_pair_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_dump_skb); diff --git a/net/devlink/port.c b/net/devlink/port.c index be9158b4453c..939081a0e615 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -1376,7 +1376,7 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set); * * @devlink_port: devlink port * @controller: associated controller number for the devlink port instance - * @pf: associated PF for the devlink port instance + * @pf: associated PCI function number for the devlink port instance * @external: indicates if the port is for an external controller */ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, @@ -1402,8 +1402,9 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); * * @devlink_port: devlink port * @controller: associated controller number for the devlink port instance - * @pf: associated PF for the devlink port instance - * @vf: associated VF of a PF for the devlink port instance + * @pf: associated PCI function number for the devlink port instance + * @vf: associated PCI VF number of a PF for the devlink port instance; + * VF number starts from 0 for the first PCI virtual function * @external: indicates if the port is for an external controller */ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, @@ -1430,8 +1431,8 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); * * @devlink_port: devlink port * @controller: associated controller number for the devlink port instance - * @pf: associated PF for the devlink port instance - * @sf: associated SF of a PF for the devlink port instance + * @pf: associated PCI function number for the devlink port instance + * @sf: associated SF number of a PF for the devlink port instance * @external: indicates if the port is for an external controller */ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 5a7c0e565a89..e827775baf2e 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1367,7 +1367,7 @@ static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn) return dsa_switch_parse_ports_of(ds, dn); } -static int dev_is_class(struct device *dev, void *class) +static int dev_is_class(struct device *dev, const void *class) { if (dev->class != NULL && !strcmp(dev->class->name, class)) return 1; diff --git a/net/dsa/port.c b/net/dsa/port.c index ee0aaec4c8e0..5c9d1798e830 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1575,6 +1575,22 @@ void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, cpu_dp->tag_ops = tag_ops; } +/* dsa_supports_eee - indicate that EEE is supported + * @ds: pointer to &struct dsa_switch + * @port: port index + * + * A default implementation for the .support_eee() DSA operations member, + * which drivers can use to indicate that they support EEE on all of their + * user ports. + * + * Returns: true + */ +bool dsa_supports_eee(struct dsa_switch *ds, int port) +{ + return true; +} +EXPORT_SYMBOL_GPL(dsa_supports_eee); + static void dsa_port_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) diff --git a/net/dsa/tag.h b/net/dsa/tag.h index d5707870906b..5d80ddad4ff6 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -138,9 +138,10 @@ static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path * @skb: Pointer to socket buffer (packet) * - * Receive path method for switches which cannot avoid tagging all packets - * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or - * ds->untag_vlan_aware_bridge_pvid is set to true. + * Receive path method for switches which send some packets as VLAN-tagged + * towards the CPU port (generally from VLAN-aware bridge ports) even when the + * packet was not tagged on the wire. Called when ds->untag_bridge_pvid + * (legacy) or ds->untag_vlan_aware_bridge_pvid is set to true. * * As a side effect of this method, any VLAN tag from the skb head is moved * to hwaccel. @@ -149,14 +150,19 @@ static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) { struct dsa_port *dp = dsa_user_to_port(skb->dev); struct net_device *br = dsa_port_bridge_dev_get(dp); - u16 vid; + u16 vid, proto; + int err; /* software untagging for standalone ports not yet necessary */ if (!br) return skb; + err = br_vlan_get_proto(br, &proto); + if (err) + return skb; + /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb)) { + if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { skb = skb_vlan_untag(skb); if (!skb) return NULL; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 281bbac5539d..c33d4bf17929 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -66,7 +66,7 @@ static int ksz_connect(struct dsa_switch *ds) if (!priv) return -ENOMEM; - xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit", + xmit_worker = kthread_run_worker(0, "dsa%d:%d_xmit", ds->dst->index, ds->index); if (IS_ERR(xmit_worker)) { ret = PTR_ERR(xmit_worker); diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 11ea8cfd6266..3929584791e4 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -110,7 +110,7 @@ static int ocelot_connect(struct dsa_switch *ds) if (!priv) return -ENOMEM; - priv->xmit_worker = kthread_create_worker(0, "felix_xmit"); + priv->xmit_worker = kthread_run_worker(0, "felix_xmit"); if (IS_ERR(priv->xmit_worker)) { err = PTR_ERR(priv->xmit_worker); kfree(priv); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 3e902af7eea6..02adec693811 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -707,7 +707,7 @@ static int sja1105_connect(struct dsa_switch *ds) spin_lock_init(&priv->meta_lock); - xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit", + xmit_worker = kthread_run_worker(0, "dsa%d:%d_xmit", ds->dst->index, ds->index); if (IS_ERR(xmit_worker)) { err = PTR_ERR(xmit_worker); diff --git a/net/dsa/user.c b/net/dsa/user.c index 06c30a9e29ff..291ab1b4acc4 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -515,12 +515,13 @@ dsa_user_port_fdb_do_dump(const unsigned char *addr, u16 vid, bool is_static, void *data) { struct dsa_user_dump_ctx *dump = data; + struct ndo_fdb_dump_context *ctx = (void *)dump->cb->ctx; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; struct ndmsg *ndm; - if (dump->idx < dump->cb->args[2]) + if (dump->idx < ctx->fdb_idx) goto skip; nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, @@ -1149,6 +1150,16 @@ dsa_user_get_rmon_stats(struct net_device *dev, ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); } +static void dsa_user_get_ts_stats(struct net_device *dev, + struct ethtool_ts_stats *ts_stats) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_ts_stats) + ds->ops->get_ts_stats(ds, dp->index, ts_stats); +} + static void dsa_user_net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { @@ -1228,8 +1239,12 @@ static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e) struct dsa_switch *ds = dp->ds; int ret; + /* Check whether the switch supports EEE */ + if (!ds->ops->support_eee || !ds->ops->support_eee(ds, dp->index)) + return -EOPNOTSUPP; + /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev || !dp->pl) + if (!dev->phydev) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -1246,18 +1261,14 @@ static int dsa_user_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; - int ret; - /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev || !dp->pl) - return -ENODEV; - - if (!ds->ops->get_mac_eee) + /* Check whether the switch supports EEE */ + if (!ds->ops->support_eee || !ds->ops->support_eee(ds, dp->index)) return -EOPNOTSUPP; - ret = ds->ops->get_mac_eee(ds, dp->index, e); - if (ret) - return ret; + /* Port's PHY and MAC both need to be EEE capable */ + if (!dev->phydev) + return -ENODEV; return phylink_ethtool_get_eee(dp->pl, e); } @@ -2500,6 +2511,7 @@ static const struct ethtool_ops dsa_user_ethtool_ops = { .get_eth_mac_stats = dsa_user_get_eth_mac_stats, .get_eth_ctrl_stats = dsa_user_get_eth_ctrl_stats, .get_rmon_stats = dsa_user_get_rmon_stats, + .get_ts_stats = dsa_user_get_ts_stats, .set_wol = dsa_user_set_wol, .get_wol = dsa_user_get_wol, .set_eee = dsa_user_set_eee, diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 9b540644ba31..a1490c4afe6b 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -9,4 +9,4 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ module.o cmis_fw_update.o cmis_cdb.o pse-pd.o plca.o mm.o \ - phy.o + phy.o tsconfig.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 05ce4f8080b3..2bd77c94f9f1 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -5,9 +5,12 @@ #include #include #include +#include #include "netlink.h" #include "common.h" +#include "../core/dev.h" + const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_SG_BIT] = "tx-scatter-gather", @@ -763,20 +766,98 @@ int ethtool_check_ops(const struct ethtool_ops *ops) return 0; } -int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) +static void ethtool_init_tsinfo(struct kernel_ethtool_ts_info *info) { - const struct ethtool_ops *ops = dev->ethtool_ops; - struct phy_device *phydev = dev->phydev; - int err = 0; - memset(info, 0, sizeof(*info)); info->cmd = ETHTOOL_GET_TS_INFO; info->phc_index = -1; +} - if (phy_is_default_hwtstamp(phydev) && phy_has_tsinfo(phydev)) - err = phy_ts_info(phydev, info); - else if (ops->get_ts_info) - err = ops->get_ts_info(dev, info); +int ethtool_net_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + int err; + + if (!ops->get_ts_info) + return -ENODEV; + + /* Does ptp comes from netdev */ + ethtool_init_tsinfo(info); + info->phc_qualifier = hwprov_desc->qualifier; + err = ops->get_ts_info(dev, info); + if (err) + return err; + + if (info->phc_index == hwprov_desc->index && + net_support_hwtstamp_qualifier(dev, hwprov_desc->qualifier)) + return 0; + + return -ENODEV; +} + +struct phy_device * +ethtool_phy_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc) +{ + int err; + + /* Only precise qualifier is supported in phydev */ + if (hwprov_desc->qualifier != HWTSTAMP_PROVIDER_QUALIFIER_PRECISE) + return ERR_PTR(-ENODEV); + + /* Look in the phy topology */ + if (dev->link_topo) { + struct phy_device_node *pdn; + unsigned long phy_index; + + xa_for_each(&dev->link_topo->phys, phy_index, pdn) { + if (!phy_has_tsinfo(pdn->phy)) + continue; + + ethtool_init_tsinfo(info); + err = phy_ts_info(pdn->phy, info); + if (err) + return ERR_PTR(err); + + if (info->phc_index == hwprov_desc->index) + return pdn->phy; + } + return ERR_PTR(-ENODEV); + } + + /* Look on the dev->phydev */ + if (phy_has_tsinfo(dev->phydev)) { + ethtool_init_tsinfo(info); + err = phy_ts_info(dev->phydev, info); + if (err) + return ERR_PTR(err); + + if (info->phc_index == hwprov_desc->index) + return dev->phydev; + } + + return ERR_PTR(-ENODEV); +} + +int ethtool_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc) +{ + int err; + + err = ethtool_net_get_ts_info_by_phc(dev, info, hwprov_desc); + if (err == -ENODEV) { + struct phy_device *phy; + + phy = ethtool_phy_get_ts_info_by_phc(dev, info, hwprov_desc); + if (IS_ERR(phy)) + err = PTR_ERR(phy); + else + err = 0; + } info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE; @@ -784,6 +865,59 @@ int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info return err; } +int __ethtool_get_ts_info(struct net_device *dev, + struct kernel_ethtool_ts_info *info) +{ + struct hwtstamp_provider *hwprov; + int err = 0; + + rcu_read_lock(); + hwprov = rcu_dereference(dev->hwprov); + /* No provider specified, use default behavior */ + if (!hwprov) { + const struct ethtool_ops *ops = dev->ethtool_ops; + struct phy_device *phydev = dev->phydev; + + ethtool_init_tsinfo(info); + if (phy_is_default_hwtstamp(phydev) && + phy_has_tsinfo(phydev)) + err = phy_ts_info(phydev, info); + else if (ops->get_ts_info) + err = ops->get_ts_info(dev, info); + + info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + + rcu_read_unlock(); + return err; + } + + err = ethtool_get_ts_info_by_phc(dev, info, &hwprov->desc); + rcu_read_unlock(); + return err; +} + +bool net_support_hwtstamp_qualifier(struct net_device *dev, + enum hwtstamp_provider_qualifier qualifier) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops) + return false; + + /* Return true with precise qualifier and with NIC without + * qualifier description to not break the old behavior. + */ + if (!ops->supported_hwtstamp_qualifiers && + qualifier == HWTSTAMP_PROVIDER_QUALIFIER_PRECISE) + return true; + + if (ops->supported_hwtstamp_qualifiers & BIT(qualifier)) + return true; + + return false; +} + int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index) { struct kernel_ethtool_ts_info info = { }; diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 4a2de3ce7354..850eadde4bfc 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -21,6 +21,7 @@ struct link_mode_info { }; struct genl_info; +struct hwtstamp_provider_desc; extern const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]; @@ -49,6 +50,18 @@ int ethtool_check_max_channel(struct net_device *dev, struct genl_info *info); int ethtool_check_rss_ctx_busy(struct net_device *dev, u32 rss_context); int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info); +int ethtool_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc); +int ethtool_net_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc); +struct phy_device * +ethtool_phy_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc); +bool net_support_hwtstamp_qualifier(struct net_device *dev, + enum hwtstamp_provider_qualifier qualifier); extern const struct ethtool_phy_ops *ethtool_phy_ops; extern const struct ethtool_pse_ops *ethtool_pse_ops; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7bb94875a7ec..34bee42e1247 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -998,7 +998,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, ethtool_get_flow_spec_ring(info.fs.ring_cookie)) return -EINVAL; - if (ops->get_rxfh) { + if (cmd == ETHTOOL_SRXFH && ops->get_rxfh) { struct ethtool_rxfh_param rxfh = {}; rc = ops->get_rxfh(dev, &rxfh); diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index 34d76e87847d..af19e1bed303 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -3,6 +3,7 @@ #include "netlink.h" #include "common.h" #include +#include struct linkstate_req_info { struct ethnl_req_info base; @@ -26,9 +27,8 @@ const struct nla_policy ethnl_linkstate_get_policy[] = { NLA_POLICY_NESTED(ethnl_header_policy_stats), }; -static int linkstate_get_sqi(struct net_device *dev) +static int linkstate_get_sqi(struct phy_device *phydev) { - struct phy_device *phydev = dev->phydev; int ret; if (!phydev) @@ -46,9 +46,8 @@ static int linkstate_get_sqi(struct net_device *dev) return ret; } -static int linkstate_get_sqi_max(struct net_device *dev) +static int linkstate_get_sqi_max(struct phy_device *phydev) { - struct phy_device *phydev = dev->phydev; int ret; if (!phydev) @@ -100,19 +99,28 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, { struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_LINKSTATE_HEADER], + info->extack); + if (IS_ERR(phydev)) { + ret = PTR_ERR(phydev); + goto out; + } + ret = ethnl_ops_begin(dev); if (ret < 0) return ret; data->link = __ethtool_get_link(dev); - ret = linkstate_get_sqi(dev); + ret = linkstate_get_sqi(phydev); if (linkstate_sqi_critical_error(ret)) goto out; data->sqi = ret; - ret = linkstate_get_sqi_max(dev); + ret = linkstate_get_sqi_max(phydev); if (linkstate_sqi_critical_error(ret)) goto out; data->sqi_max = ret; @@ -127,9 +135,9 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, sizeof(data->link_stats) / 8); if (req_base->flags & ETHTOOL_FLAG_STATS) { - if (dev->phydev) - data->link_stats.link_down_events = - READ_ONCE(dev->phydev->link_down_events); + if (phydev) + phy_ethtool_get_link_ext_stats(phydev, + &data->link_stats); if (dev->ethtool_ops->get_link_ext_stats) dev->ethtool_ops->get_link_ext_stats(dev, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index e3f0ef6b851b..b4c45207fa32 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include #include #include @@ -90,7 +91,7 @@ int ethnl_ops_begin(struct net_device *dev) pm_runtime_get_sync(dev->dev.parent); if (!netif_device_present(dev) || - dev->reg_state == NETREG_UNREGISTERING) { + dev->reg_state >= NETREG_UNREGISTERING) { ret = -ENODEV; goto err; } @@ -394,6 +395,8 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, [ETHTOOL_MSG_MM_GET] = ðnl_mm_request_ops, [ETHTOOL_MSG_MM_SET] = ðnl_mm_request_ops, + [ETHTOOL_MSG_TSCONFIG_GET] = ðnl_tsconfig_request_ops, + [ETHTOOL_MSG_TSCONFIG_SET] = ðnl_tsconfig_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -665,6 +668,7 @@ static int ethnl_default_set_doit(struct sk_buff *skb, struct genl_info *info) const struct ethnl_request_ops *ops; struct ethnl_req_info req_info = {}; const u8 cmd = info->genlhdr->cmd; + struct net_device *dev; int ret; ops = ethnl_default_requests[cmd]; @@ -686,20 +690,36 @@ static int ethnl_default_set_doit(struct sk_buff *skb, struct genl_info *info) goto out_dev; } + dev = req_info.dev; + rtnl_lock(); - ret = ethnl_ops_begin(req_info.dev); + dev->cfg_pending = kmemdup(dev->cfg, sizeof(*dev->cfg), + GFP_KERNEL_ACCOUNT); + if (!dev->cfg_pending) { + ret = -ENOMEM; + goto out_tie_cfg; + } + + ret = ethnl_ops_begin(dev); if (ret < 0) - goto out_rtnl; + goto out_free_cfg; ret = ops->set(&req_info, info); - if (ret <= 0) + if (ret < 0) goto out_ops; - ethtool_notify(req_info.dev, ops->set_ntf_cmd, NULL); + + swap(dev->cfg, dev->cfg_pending); + if (!ret) + goto out_ops; + ethtool_notify(dev, ops->set_ntf_cmd, NULL); ret = 0; out_ops: - ethnl_ops_complete(req_info.dev); -out_rtnl: + ethnl_ops_complete(dev); +out_free_cfg: + kfree(dev->cfg_pending); +out_tie_cfg: + dev->cfg_pending = dev->cfg; rtnl_unlock(); out_dev: ethnl_parse_header_dev_put(&req_info); @@ -1074,9 +1094,9 @@ static const struct genl_ops ethtool_genl_ops[] = { { .cmd = ETHTOOL_MSG_TSINFO_GET, .doit = ethnl_default_doit, - .start = ethnl_default_start, - .dumpit = ethnl_default_dumpit, - .done = ethnl_default_done, + .start = ethnl_tsinfo_start, + .dumpit = ethnl_tsinfo_dumpit, + .done = ethnl_tsinfo_done, .policy = ethnl_tsinfo_get_policy, .maxattr = ARRAY_SIZE(ethnl_tsinfo_get_policy) - 1, }, @@ -1243,6 +1263,22 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_phy_get_policy, .maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_TSCONFIG_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_tsconfig_get_policy, + .maxattr = ARRAY_SIZE(ethnl_tsconfig_get_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_TSCONFIG_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_default_set_doit, + .policy = ethnl_tsconfig_set_policy, + .maxattr = ARRAY_SIZE(ethnl_tsconfig_set_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 203b08eb6c6f..ff69ca0715de 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -435,6 +435,7 @@ extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; extern const struct ethnl_request_ops ethnl_phy_request_ops; +extern const struct ethnl_request_ops ethnl_tsconfig_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -455,7 +456,7 @@ extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANT extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1]; extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1]; extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1]; -extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX + 1]; +extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_HDS_THRESH_MAX + 1]; extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1]; extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; @@ -464,7 +465,7 @@ extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_STATS_SRC extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_TX + 1]; extern const struct nla_policy ethnl_eee_get_policy[ETHTOOL_A_EEE_HEADER + 1]; extern const struct nla_policy ethnl_eee_set_policy[ETHTOOL_A_EEE_TX_LPI_TIMER + 1]; -extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_HEADER + 1]; +extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1]; extern const struct nla_policy ethnl_cable_test_act_policy[ETHTOOL_A_CABLE_TEST_HEADER + 1]; extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG + 1]; extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1]; @@ -485,6 +486,8 @@ extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; extern const struct nla_policy ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD + 1]; extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1]; +extern const struct nla_policy ethnl_tsconfig_get_policy[ETHTOOL_A_TSCONFIG_HEADER + 1]; +extern const struct nla_policy ethnl_tsconfig_set_policy[ETHTOOL_A_TSCONFIG_MAX + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); @@ -499,11 +502,15 @@ int ethnl_phy_start(struct netlink_callback *cb); int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_phy_done(struct netlink_callback *cb); +int ethnl_tsinfo_start(struct netlink_callback *cb); +int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_tsinfo_done(struct netlink_callback *cb); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_mac_names[__ETHTOOL_A_STATS_ETH_MAC_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_ctrl_names[__ETHTOOL_A_STATS_ETH_CTRL_CNT][ETH_GSTRING_LEN]; extern const char stats_rmon_names[__ETHTOOL_A_STATS_RMON_CNT][ETH_GSTRING_LEN]; +extern const char stats_phy_names[__ETHTOOL_A_STATS_PHY_CNT][ETH_GSTRING_LEN]; #endif /* _NET_ETHTOOL_NETLINK_H */ diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index a0705edca22a..2819e2ba6be2 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -19,7 +19,7 @@ struct pse_req_info { struct pse_reply_data { struct ethnl_reply_data base; - struct pse_control_status status; + struct ethtool_pse_control_status status; }; #define PSE_REPDATA(__reply_base) \ @@ -80,7 +80,7 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); - const struct pse_control_status *st = &data->status; + const struct ethtool_pse_control_status *st = &data->status; int len = 0; if (st->podl_admin_state > 0) @@ -114,7 +114,7 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, } static int pse_put_pw_limit_ranges(struct sk_buff *skb, - const struct pse_control_status *st) + const struct ethtool_pse_control_status *st) { const struct ethtool_c33_pse_pw_limit_range *pw_limit_ranges; int i; @@ -146,7 +146,7 @@ static int pse_fill_reply(struct sk_buff *skb, const struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); - const struct pse_control_status *st = &data->status; + const struct ethtool_pse_control_status *st = &data->status; if (st->podl_admin_state > 0 && nla_put_u32(skb, ETHTOOL_A_PODL_PSE_ADMIN_STATE, diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index b7865a14fdf8..7839bfd1ac6a 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only +#include + #include "netlink.h" #include "common.h" @@ -37,6 +39,10 @@ static int rings_prepare_data(const struct ethnl_req_info *req_base, ret = ethnl_ops_begin(dev); if (ret < 0) return ret; + + data->kernel_ringparam.tcp_data_split = dev->cfg->hds_config; + data->kernel_ringparam.hds_thresh = dev->cfg->hds_thresh; + dev->ethtool_ops->get_ringparam(dev, &data->ringparam, &data->kernel_ringparam, info->extack); ethnl_ops_complete(dev); @@ -61,7 +67,9 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u8)) + /* _RINGS_TX_PUSH */ nla_total_size(sizeof(u8))) + /* _RINGS_RX_PUSH */ nla_total_size(sizeof(u32)) + /* _RINGS_TX_PUSH_BUF_LEN */ - nla_total_size(sizeof(u32)); /* _RINGS_TX_PUSH_BUF_LEN_MAX */ + nla_total_size(sizeof(u32)) + /* _RINGS_TX_PUSH_BUF_LEN_MAX */ + nla_total_size(sizeof(u32)) + /* _RINGS_HDS_THRESH */ + nla_total_size(sizeof(u32)); /* _RINGS_HDS_THRESH_MAX*/ } static int rings_fill_reply(struct sk_buff *skb, @@ -108,7 +116,12 @@ static int rings_fill_reply(struct sk_buff *skb, (nla_put_u32(skb, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX, kr->tx_push_buf_max_len) || nla_put_u32(skb, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN, - kr->tx_push_buf_len)))) + kr->tx_push_buf_len))) || + ((supported_ring_params & ETHTOOL_RING_USE_HDS_THRS) && + (nla_put_u32(skb, ETHTOOL_A_RINGS_HDS_THRESH, + kr->hds_thresh) || + nla_put_u32(skb, ETHTOOL_A_RINGS_HDS_THRESH_MAX, + kr->hds_thresh_max)))) return -EMSGSIZE; return 0; @@ -130,6 +143,7 @@ const struct nla_policy ethnl_rings_set_policy[] = { [ETHTOOL_A_RINGS_TX_PUSH] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_RINGS_RX_PUSH] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN] = { .type = NLA_U32 }, + [ETHTOOL_A_RINGS_HDS_THRESH] = { .type = NLA_U32 }, }; static int @@ -155,6 +169,14 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info, return -EOPNOTSUPP; } + if (tb[ETHTOOL_A_RINGS_HDS_THRESH] && + !(ops->supported_ring_params & ETHTOOL_RING_USE_HDS_THRS)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_HDS_THRESH], + "setting hds-thresh is not supported"); + return -EOPNOTSUPP; + } + if (tb[ETHTOOL_A_RINGS_CQE_SIZE] && !(ops->supported_ring_params & ETHTOOL_RING_USE_CQE_SIZE)) { NL_SET_ERR_MSG_ATTR(info->extack, @@ -203,6 +225,7 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) dev->ethtool_ops->get_ringparam(dev, &ringparam, &kernel_ringparam, info->extack); + kernel_ringparam.tcp_data_split = dev->cfg->hds_config; ethnl_update_u32(&ringparam.rx_pending, tb[ETHTOOL_A_RINGS_RX], &mod); ethnl_update_u32(&ringparam.rx_mini_pending, @@ -222,9 +245,32 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) tb[ETHTOOL_A_RINGS_RX_PUSH], &mod); ethnl_update_u32(&kernel_ringparam.tx_push_buf_len, tb[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN], &mod); + ethnl_update_u32(&kernel_ringparam.hds_thresh, + tb[ETHTOOL_A_RINGS_HDS_THRESH], &mod); if (!mod) return 0; + if (kernel_ringparam.tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + dev_xdp_sb_prog_count(dev)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT], + "tcp-data-split can not be enabled with single buffer XDP"); + return -EINVAL; + } + + if (dev_get_min_mp_channel_count(dev)) { + if (kernel_ringparam.tcp_data_split != + ETHTOOL_TCP_DATA_SPLIT_ENABLED) { + NL_SET_ERR_MSG(info->extack, + "can't disable tcp-data-split while device has memory provider enabled"); + return -EINVAL; + } else if (kernel_ringparam.hds_thresh) { + NL_SET_ERR_MSG(info->extack, + "can't set non-zero hds_thresh while device is memory provider enabled"); + return -EINVAL; + } + } + /* ensure new ring parameters are within limits */ if (ringparam.rx_pending > ringparam.rx_max_pending) err_attr = tb[ETHTOOL_A_RINGS_RX]; @@ -234,6 +280,8 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) err_attr = tb[ETHTOOL_A_RINGS_RX_JUMBO]; else if (ringparam.tx_pending > ringparam.tx_max_pending) err_attr = tb[ETHTOOL_A_RINGS_TX]; + else if (kernel_ringparam.hds_thresh > kernel_ringparam.hds_thresh_max) + err_attr = tb[ETHTOOL_A_RINGS_HDS_THRESH]; else err_attr = NULL; if (err_attr) { @@ -250,6 +298,9 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) return -EINVAL; } + dev->cfg_pending->hds_config = kernel_ringparam.tcp_data_split; + dev->cfg_pending->hds_thresh = kernel_ringparam.hds_thresh; + ret = dev->ethtool_ops->set_ringparam(dev, &ringparam, &kernel_ringparam, info->extack); return ret < 0 ? ret : 1; diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c index 912f0c4fff2f..038a2558f052 100644 --- a/net/ethtool/stats.c +++ b/net/ethtool/stats.c @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only +#include +#include + #include "netlink.h" #include "common.h" #include "bitset.h" @@ -20,6 +23,7 @@ struct stats_reply_data { struct ethtool_eth_mac_stats mac_stats; struct ethtool_eth_ctrl_stats ctrl_stats; struct ethtool_rmon_stats rmon_stats; + struct ethtool_phy_stats phydev_stats; ); const struct ethtool_rmon_hist_range *rmon_ranges; }; @@ -32,6 +36,7 @@ const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_STATS_ETH_MAC] = "eth-mac", [ETHTOOL_STATS_ETH_CTRL] = "eth-ctrl", [ETHTOOL_STATS_RMON] = "rmon", + [ETHTOOL_STATS_PHY] = "phydev", }; const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN] = { @@ -76,6 +81,15 @@ const char stats_rmon_names[__ETHTOOL_A_STATS_RMON_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_RMON_JABBER] = "etherStatsJabbers", }; +const char stats_phy_names[__ETHTOOL_A_STATS_PHY_CNT][ETH_GSTRING_LEN] = { + [ETHTOOL_A_STATS_PHY_RX_PKTS] = "RxFrames", + [ETHTOOL_A_STATS_PHY_RX_BYTES] = "RxOctets", + [ETHTOOL_A_STATS_PHY_RX_ERRORS] = "RxErrors", + [ETHTOOL_A_STATS_PHY_TX_PKTS] = "TxFrames", + [ETHTOOL_A_STATS_PHY_TX_BYTES] = "TxOctets", + [ETHTOOL_A_STATS_PHY_TX_ERRORS] = "TxErrors", +}; + const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_SRC + 1] = { [ETHTOOL_A_STATS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), @@ -120,8 +134,15 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, struct stats_reply_data *data = STATS_REPDATA(reply_base); enum ethtool_mac_stats_src src = req_info->src; struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_STATS_HEADER], + info->extack); + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + ret = ethnl_ops_begin(dev); if (ret < 0) return ret; @@ -145,6 +166,14 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, data->ctrl_stats.src = src; data->rmon_stats.src = src; + if ((test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask) || + test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) && + src == ETHTOOL_MAC_STATS_SRC_AGGREGATE) { + if (phydev) + phy_ethtool_get_phy_stats(phydev, &data->phy_stats, + &data->phydev_stats); + } + if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask) && dev->ethtool_ops->get_eth_phy_stats) dev->ethtool_ops->get_eth_phy_stats(dev, &data->phy_stats); @@ -194,6 +223,10 @@ static int stats_reply_size(const struct ethnl_req_info *req_base, nla_total_size(4)) * /* _A_STATS_GRP_HIST_BKT_HI */ ETHTOOL_RMON_HIST_MAX * 2; } + if (test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask)) { + n_stats += sizeof(struct ethtool_phy_stats) / sizeof(u64); + n_grps++; + } len += n_grps * (nla_total_size(0) + /* _A_STATS_GRP */ nla_total_size(4) + /* _A_STATS_GRP_ID */ @@ -247,6 +280,25 @@ static int stats_put_phy_stats(struct sk_buff *skb, return 0; } +static int stats_put_phydev_stats(struct sk_buff *skb, + const struct stats_reply_data *data) +{ + if (stat_put(skb, ETHTOOL_A_STATS_PHY_RX_PKTS, + data->phydev_stats.rx_packets) || + stat_put(skb, ETHTOOL_A_STATS_PHY_RX_BYTES, + data->phydev_stats.rx_bytes) || + stat_put(skb, ETHTOOL_A_STATS_PHY_RX_ERRORS, + data->phydev_stats.rx_errors) || + stat_put(skb, ETHTOOL_A_STATS_PHY_TX_PKTS, + data->phydev_stats.tx_packets) || + stat_put(skb, ETHTOOL_A_STATS_PHY_TX_BYTES, + data->phydev_stats.tx_bytes) || + stat_put(skb, ETHTOOL_A_STATS_PHY_TX_ERRORS, + data->phydev_stats.tx_errors)) + return -EMSGSIZE; + return 0; +} + static int stats_put_mac_stats(struct sk_buff *skb, const struct stats_reply_data *data) { @@ -423,6 +475,9 @@ static int stats_fill_reply(struct sk_buff *skb, if (!ret && test_bit(ETHTOOL_STATS_RMON, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_RMON, ETH_SS_STATS_RMON, stats_put_rmon_stats); + if (!ret && test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask)) + ret = stats_put_stats(skb, data, ETHTOOL_STATS_PHY, + ETH_SS_STATS_PHY, stats_put_phydev_stats); return ret; } diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index b3382b3cf325..818cf01f0911 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -105,6 +105,11 @@ static const struct strset_info info_template[] = { .count = __ETHTOOL_A_STATS_RMON_CNT, .strings = stats_rmon_names, }, + [ETH_SS_STATS_PHY] = { + .per_dev = false, + .count = __ETHTOOL_A_STATS_PHY_CNT, + .strings = stats_phy_names, + }, }; struct strset_req_info { diff --git a/net/ethtool/ts.h b/net/ethtool/ts.h new file mode 100644 index 000000000000..d901a879a671 --- /dev/null +++ b/net/ethtool/ts.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _NET_ETHTOOL_TS_H +#define _NET_ETHTOOL_TS_H + +#include "netlink.h" + +static const struct nla_policy +ethnl_ts_hwtst_prov_policy[ETHTOOL_A_TS_HWTSTAMP_PROVIDER_MAX + 1] = { + [ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER] = + NLA_POLICY_MAX(NLA_U32, HWTSTAMP_PROVIDER_QUALIFIER_CNT - 1) +}; + +int ts_parse_hwtst_provider(const struct nlattr *nest, + struct hwtstamp_provider_desc *hwprov_desc, + struct netlink_ext_ack *extack, + bool *mod); + +#endif /* _NET_ETHTOOL_TS_H */ diff --git a/net/ethtool/tsconfig.c b/net/ethtool/tsconfig.c new file mode 100644 index 000000000000..9188e088fb2f --- /dev/null +++ b/net/ethtool/tsconfig.c @@ -0,0 +1,444 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +#include "netlink.h" +#include "common.h" +#include "bitset.h" +#include "../core/dev.h" +#include "ts.h" + +struct tsconfig_req_info { + struct ethnl_req_info base; +}; + +struct tsconfig_reply_data { + struct ethnl_reply_data base; + struct hwtstamp_provider_desc hwprov_desc; + struct { + u32 tx_type; + u32 rx_filter; + u32 flags; + } hwtst_config; +}; + +#define TSCONFIG_REPDATA(__reply_base) \ + container_of(__reply_base, struct tsconfig_reply_data, base) + +const struct nla_policy ethnl_tsconfig_get_policy[ETHTOOL_A_TSCONFIG_HEADER + 1] = { + [ETHTOOL_A_TSCONFIG_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int tsconfig_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + const struct genl_info *info) +{ + struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); + struct hwtstamp_provider *hwprov = NULL; + struct net_device *dev = reply_base->dev; + struct kernel_hwtstamp_config cfg = {}; + int ret; + + if (!dev->netdev_ops->ndo_hwtstamp_get) + return -EOPNOTSUPP; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + ret = dev_get_hwtstamp_phylib(dev, &cfg); + if (ret) + goto out; + + data->hwtst_config.tx_type = BIT(cfg.tx_type); + data->hwtst_config.rx_filter = BIT(cfg.rx_filter); + data->hwtst_config.flags = BIT(cfg.flags); + + data->hwprov_desc.index = -1; + hwprov = rtnl_dereference(dev->hwprov); + if (hwprov) { + data->hwprov_desc.index = hwprov->desc.index; + data->hwprov_desc.qualifier = hwprov->desc.qualifier; + } else { + struct kernel_ethtool_ts_info ts_info = {}; + + ts_info.phc_index = -1; + ret = __ethtool_get_ts_info(dev, &ts_info); + if (ret) + goto out; + + if (ts_info.phc_index == -1) + return -ENODEV; + + data->hwprov_desc.index = ts_info.phc_index; + data->hwprov_desc.qualifier = ts_info.phc_qualifier; + } + +out: + ethnl_ops_complete(dev); + return ret; +} + +static int tsconfig_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + int len = 0; + int ret; + + BUILD_BUG_ON(__HWTSTAMP_TX_CNT > 32); + BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT > 32); + + if (data->hwtst_config.flags) + /* _TSCONFIG_HWTSTAMP_FLAGS */ + len += nla_total_size(sizeof(u32)); + + if (data->hwtst_config.tx_type) { + ret = ethnl_bitset32_size(&data->hwtst_config.tx_type, + NULL, __HWTSTAMP_TX_CNT, + ts_tx_type_names, compact); + if (ret < 0) + return ret; + len += ret; /* _TSCONFIG_TX_TYPES */ + } + if (data->hwtst_config.rx_filter) { + ret = ethnl_bitset32_size(&data->hwtst_config.rx_filter, + NULL, __HWTSTAMP_FILTER_CNT, + ts_rx_filter_names, compact); + if (ret < 0) + return ret; + len += ret; /* _TSCONFIG_RX_FILTERS */ + } + + if (data->hwprov_desc.index >= 0) + /* _TSCONFIG_HWTSTAMP_PROVIDER */ + len += nla_total_size(0) + + 2 * nla_total_size(sizeof(u32)); + + return len; +} + +static int tsconfig_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + int ret; + + if (data->hwtst_config.flags) { + ret = nla_put_u32(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS, + data->hwtst_config.flags); + if (ret < 0) + return ret; + } + + if (data->hwtst_config.tx_type) { + ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_TX_TYPES, + &data->hwtst_config.tx_type, NULL, + __HWTSTAMP_TX_CNT, + ts_tx_type_names, compact); + if (ret < 0) + return ret; + } + + if (data->hwtst_config.rx_filter) { + ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_RX_FILTERS, + &data->hwtst_config.rx_filter, + NULL, __HWTSTAMP_FILTER_CNT, + ts_rx_filter_names, compact); + if (ret < 0) + return ret; + } + + if (data->hwprov_desc.index >= 0) { + struct nlattr *nest; + + nest = nla_nest_start(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX, + data->hwprov_desc.index) || + nla_put_u32(skb, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER, + data->hwprov_desc.qualifier)) { + nla_nest_cancel(skb, nest); + return -EMSGSIZE; + } + + nla_nest_end(skb, nest); + } + return 0; +} + +/* TSCONFIG_SET */ +const struct nla_policy ethnl_tsconfig_set_policy[ETHTOOL_A_TSCONFIG_MAX + 1] = { + [ETHTOOL_A_TSCONFIG_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER] = + NLA_POLICY_NESTED(ethnl_ts_hwtst_prov_policy), + [ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS] = { .type = NLA_U32 }, + [ETHTOOL_A_TSCONFIG_RX_FILTERS] = { .type = NLA_NESTED }, + [ETHTOOL_A_TSCONFIG_TX_TYPES] = { .type = NLA_NESTED }, +}; + +static int tsconfig_send_reply(struct net_device *dev, struct genl_info *info) +{ + struct tsconfig_reply_data *reply_data; + struct tsconfig_req_info *req_info; + struct sk_buff *rskb; + void *reply_payload; + int reply_len = 0; + int ret; + + req_info = kzalloc(sizeof(*req_info), GFP_KERNEL); + if (!req_info) + return -ENOMEM; + reply_data = kmalloc(sizeof(*reply_data), GFP_KERNEL); + if (!reply_data) { + kfree(req_info); + return -ENOMEM; + } + + ASSERT_RTNL(); + reply_data->base.dev = dev; + ret = tsconfig_prepare_data(&req_info->base, &reply_data->base, info); + if (ret < 0) + goto err_cleanup; + + ret = tsconfig_reply_size(&req_info->base, &reply_data->base); + if (ret < 0) + goto err_cleanup; + + reply_len = ret + ethnl_reply_header_size(); + rskb = ethnl_reply_init(reply_len, dev, ETHTOOL_MSG_TSCONFIG_SET_REPLY, + ETHTOOL_A_TSCONFIG_HEADER, info, &reply_payload); + if (!rskb) + goto err_cleanup; + + ret = tsconfig_fill_reply(rskb, &req_info->base, &reply_data->base); + if (ret < 0) + goto err_cleanup; + + genlmsg_end(rskb, reply_payload); + ret = genlmsg_reply(rskb, info); + +err_cleanup: + kfree(reply_data); + kfree(req_info); + return ret; +} + +static int ethnl_set_tsconfig_validate(struct ethnl_req_info *req_base, + struct genl_info *info) +{ + const struct net_device_ops *ops = req_base->dev->netdev_ops; + + if (!ops->ndo_hwtstamp_set || !ops->ndo_hwtstamp_get) + return -EOPNOTSUPP; + + return 1; +} + +static struct hwtstamp_provider * +tsconfig_set_hwprov_from_desc(struct net_device *dev, + struct genl_info *info, + struct hwtstamp_provider_desc *hwprov_desc) +{ + struct kernel_ethtool_ts_info ts_info; + struct hwtstamp_provider *hwprov; + struct nlattr **tb = info->attrs; + struct phy_device *phy = NULL; + enum hwtstamp_source source; + int ret; + + ret = ethtool_net_get_ts_info_by_phc(dev, &ts_info, hwprov_desc); + if (!ret) { + /* Found */ + source = HWTSTAMP_SOURCE_NETDEV; + } else { + phy = ethtool_phy_get_ts_info_by_phc(dev, &ts_info, hwprov_desc); + if (IS_ERR(phy)) { + if (PTR_ERR(phy) == -ENODEV) + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER], + "phc not in this net device topology"); + return ERR_CAST(phy); + } + + source = HWTSTAMP_SOURCE_PHYLIB; + } + + hwprov = kzalloc(sizeof(*hwprov), GFP_KERNEL); + if (!hwprov) + return ERR_PTR(-ENOMEM); + + hwprov->desc.index = hwprov_desc->index; + hwprov->desc.qualifier = hwprov_desc->qualifier; + hwprov->source = source; + hwprov->phydev = phy; + + return hwprov; +} + +static int ethnl_set_tsconfig(struct ethnl_req_info *req_base, + struct genl_info *info) +{ + struct kernel_hwtstamp_config hwtst_config = {0}; + bool hwprov_mod = false, config_mod = false; + struct hwtstamp_provider *hwprov = NULL; + struct net_device *dev = req_base->dev; + struct nlattr **tb = info->attrs; + int ret; + + BUILD_BUG_ON(__HWTSTAMP_TX_CNT >= 32); + BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT >= 32); + + if (!netif_device_present(dev)) + return -ENODEV; + + if (tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER]) { + struct hwtstamp_provider_desc __hwprov_desc = {.index = -1}; + struct hwtstamp_provider *__hwprov; + + __hwprov = rtnl_dereference(dev->hwprov); + if (__hwprov) { + __hwprov_desc.index = __hwprov->desc.index; + __hwprov_desc.qualifier = __hwprov->desc.qualifier; + } + + ret = ts_parse_hwtst_provider(tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER], + &__hwprov_desc, info->extack, + &hwprov_mod); + if (ret < 0) + return ret; + + if (hwprov_mod) { + hwprov = tsconfig_set_hwprov_from_desc(dev, info, + &__hwprov_desc); + if (IS_ERR(hwprov)) + return PTR_ERR(hwprov); + } + } + + /* Get current hwtstamp config if we are not changing the + * hwtstamp source. It will be zeroed in the other case. + */ + if (!hwprov_mod) { + ret = dev_get_hwtstamp_phylib(dev, &hwtst_config); + if (ret < 0 && ret != -EOPNOTSUPP) + goto err_free_hwprov; + } + + /* Get the hwtstamp config from netlink */ + if (tb[ETHTOOL_A_TSCONFIG_TX_TYPES]) { + u32 req_tx_type; + + req_tx_type = BIT(hwtst_config.tx_type); + ret = ethnl_update_bitset32(&req_tx_type, + __HWTSTAMP_TX_CNT, + tb[ETHTOOL_A_TSCONFIG_TX_TYPES], + ts_tx_type_names, info->extack, + &config_mod); + if (ret < 0) + goto err_free_hwprov; + + /* Select only one tx type at a time */ + if (ffs(req_tx_type) != fls(req_tx_type)) { + ret = -EINVAL; + goto err_free_hwprov; + } + + hwtst_config.tx_type = ffs(req_tx_type) - 1; + } + + if (tb[ETHTOOL_A_TSCONFIG_RX_FILTERS]) { + u32 req_rx_filter; + + req_rx_filter = BIT(hwtst_config.rx_filter); + ret = ethnl_update_bitset32(&req_rx_filter, + __HWTSTAMP_FILTER_CNT, + tb[ETHTOOL_A_TSCONFIG_RX_FILTERS], + ts_rx_filter_names, info->extack, + &config_mod); + if (ret < 0) + goto err_free_hwprov; + + /* Select only one rx filter at a time */ + if (ffs(req_rx_filter) != fls(req_rx_filter)) { + ret = -EINVAL; + goto err_free_hwprov; + } + + hwtst_config.rx_filter = ffs(req_rx_filter) - 1; + } + + if (tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS]) { + ethnl_update_u32(&hwtst_config.flags, + tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS], + &config_mod); + } + + ret = net_hwtstamp_validate(&hwtst_config); + if (ret) + goto err_free_hwprov; + + if (hwprov_mod) { + struct kernel_hwtstamp_config zero_config = {0}; + struct hwtstamp_provider *__hwprov; + + /* Disable current time stamping if we try to enable + * another one + */ + ret = dev_set_hwtstamp_phylib(dev, &zero_config, info->extack); + if (ret < 0) + goto err_free_hwprov; + + /* Change the selected hwtstamp source */ + __hwprov = rcu_replace_pointer_rtnl(dev->hwprov, hwprov); + if (__hwprov) + kfree_rcu(__hwprov, rcu_head); + } + + if (config_mod) { + ret = dev_set_hwtstamp_phylib(dev, &hwtst_config, + info->extack); + if (ret < 0) + return ret; + } + + if (hwprov_mod || config_mod) { + ret = tsconfig_send_reply(dev, info); + if (ret && ret != -EOPNOTSUPP) { + NL_SET_ERR_MSG(info->extack, + "error while reading the new configuration set"); + return ret; + } + } + + /* tsconfig has no notification */ + return 0; + +err_free_hwprov: + kfree(hwprov); + + return ret; +} + +const struct ethnl_request_ops ethnl_tsconfig_request_ops = { + .request_cmd = ETHTOOL_MSG_TSCONFIG_GET, + .reply_cmd = ETHTOOL_MSG_TSCONFIG_GET_REPLY, + .hdr_attr = ETHTOOL_A_TSCONFIG_HEADER, + .req_info_size = sizeof(struct tsconfig_req_info), + .reply_data_size = sizeof(struct tsconfig_reply_data), + + .prepare_data = tsconfig_prepare_data, + .reply_size = tsconfig_reply_size, + .fill_reply = tsconfig_fill_reply, + + .set_validate = ethnl_set_tsconfig_validate, + .set = ethnl_set_tsconfig, +}; diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c index 03d12d6f79ca..691be6c445b3 100644 --- a/net/ethtool/tsinfo.c +++ b/net/ethtool/tsinfo.c @@ -1,13 +1,18 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include +#include +#include #include "netlink.h" #include "common.h" #include "bitset.h" +#include "ts.h" struct tsinfo_req_info { struct ethnl_req_info base; + struct hwtstamp_provider_desc hwprov_desc; }; struct tsinfo_reply_data { @@ -16,34 +21,96 @@ struct tsinfo_reply_data { struct ethtool_ts_stats stats; }; +#define TSINFO_REQINFO(__req_base) \ + container_of(__req_base, struct tsinfo_req_info, base) + #define TSINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct tsinfo_reply_data, base) #define ETHTOOL_TS_STAT_CNT \ (__ETHTOOL_A_TS_STAT_CNT - (ETHTOOL_A_TS_STAT_UNSPEC + 1)) -const struct nla_policy ethnl_tsinfo_get_policy[] = { +const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1] = { [ETHTOOL_A_TSINFO_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), + [ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER] = + NLA_POLICY_NESTED(ethnl_ts_hwtst_prov_policy), }; +int ts_parse_hwtst_provider(const struct nlattr *nest, + struct hwtstamp_provider_desc *hwprov_desc, + struct netlink_ext_ack *extack, + bool *mod) +{ + struct nlattr *tb[ARRAY_SIZE(ethnl_ts_hwtst_prov_policy)]; + int ret; + + ret = nla_parse_nested(tb, + ARRAY_SIZE(ethnl_ts_hwtst_prov_policy) - 1, + nest, + ethnl_ts_hwtst_prov_policy, extack); + if (ret < 0) + return ret; + + if (NL_REQ_ATTR_CHECK(extack, nest, tb, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX) || + NL_REQ_ATTR_CHECK(extack, nest, tb, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER)) + return -EINVAL; + + ethnl_update_u32(&hwprov_desc->index, + tb[ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX], + mod); + ethnl_update_u32(&hwprov_desc->qualifier, + tb[ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER], + mod); + + return 0; +} + +static int +tsinfo_parse_request(struct ethnl_req_info *req_base, struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct tsinfo_req_info *req = TSINFO_REQINFO(req_base); + bool mod = false; + + req->hwprov_desc.index = -1; + + if (!tb[ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER]) + return 0; + + return ts_parse_hwtst_provider(tb[ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER], + &req->hwprov_desc, extack, &mod); +} + static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); + struct tsinfo_req_info *req = TSINFO_REQINFO(req_base); struct net_device *dev = reply_base->dev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; + + if (req->hwprov_desc.index != -1) { + ret = ethtool_get_ts_info_by_phc(dev, &data->ts_info, + &req->hwprov_desc); + ethnl_ops_complete(dev); + return ret; + } + if (req_base->flags & ETHTOOL_FLAG_STATS) { ethtool_stats_init((u64 *)&data->stats, sizeof(data->stats) / sizeof(u64)); if (dev->ethtool_ops->get_ts_stats) dev->ethtool_ops->get_ts_stats(dev, &data->stats); } + ret = __ethtool_get_ts_info(dev, &data->ts_info); ethnl_ops_complete(dev); @@ -87,8 +154,11 @@ static int tsinfo_reply_size(const struct ethnl_req_info *req_base, return ret; len += ret; /* _TSINFO_RX_FILTERS */ } - if (ts_info->phc_index >= 0) + if (ts_info->phc_index >= 0) { len += nla_total_size(sizeof(u32)); /* _TSINFO_PHC_INDEX */ + /* _TSINFO_HWTSTAMP_PROVIDER */ + len += nla_total_size(0) + 2 * nla_total_size(sizeof(u32)); + } if (req_base->flags & ETHTOOL_FLAG_STATS) len += nla_total_size(0) + /* _TSINFO_STATS */ nla_total_size_64bit(sizeof(u64)) * ETHTOOL_TS_STAT_CNT; @@ -116,6 +186,8 @@ static int tsinfo_put_stats(struct sk_buff *skb, if (tsinfo_put_stat(skb, stats->tx_stats.pkts, ETHTOOL_A_TS_STAT_TX_PKTS) || + tsinfo_put_stat(skb, stats->tx_stats.onestep_pkts_unconfirmed, + ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED) || tsinfo_put_stat(skb, stats->tx_stats.lost, ETHTOOL_A_TS_STAT_TX_LOST) || tsinfo_put_stat(skb, stats->tx_stats.err, @@ -163,9 +235,29 @@ static int tsinfo_fill_reply(struct sk_buff *skb, if (ret < 0) return ret; } - if (ts_info->phc_index >= 0 && - nla_put_u32(skb, ETHTOOL_A_TSINFO_PHC_INDEX, ts_info->phc_index)) - return -EMSGSIZE; + if (ts_info->phc_index >= 0) { + struct nlattr *nest; + + ret = nla_put_u32(skb, ETHTOOL_A_TSINFO_PHC_INDEX, + ts_info->phc_index); + if (ret) + return -EMSGSIZE; + + nest = nla_nest_start(skb, ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX, + ts_info->phc_index) || + nla_put_u32(skb, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER, + ts_info->phc_qualifier)) { + nla_nest_cancel(skb, nest); + return -EMSGSIZE; + } + + nla_nest_end(skb, nest); + } if (req_base->flags & ETHTOOL_FLAG_STATS && tsinfo_put_stats(skb, &data->stats)) return -EMSGSIZE; @@ -173,6 +265,263 @@ static int tsinfo_fill_reply(struct sk_buff *skb, return 0; } +struct ethnl_tsinfo_dump_ctx { + struct tsinfo_req_info *req_info; + struct tsinfo_reply_data *reply_data; + unsigned long pos_ifindex; + bool netdev_dump_done; + unsigned long pos_phyindex; + enum hwtstamp_provider_qualifier pos_phcqualifier; +}; + +static void *ethnl_tsinfo_prepare_dump(struct sk_buff *skb, + struct net_device *dev, + struct tsinfo_reply_data *reply_data, + struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + void *ehdr = NULL; + + ehdr = ethnl_dump_put(skb, cb, + ETHTOOL_MSG_TSINFO_GET_REPLY); + if (!ehdr) + return ERR_PTR(-EMSGSIZE); + + reply_data = ctx->reply_data; + memset(reply_data, 0, sizeof(*reply_data)); + reply_data->base.dev = dev; + memset(&reply_data->ts_info, 0, sizeof(reply_data->ts_info)); + + return ehdr; +} + +static int ethnl_tsinfo_end_dump(struct sk_buff *skb, + struct net_device *dev, + struct tsinfo_req_info *req_info, + struct tsinfo_reply_data *reply_data, + void *ehdr) +{ + int ret; + + reply_data->ts_info.so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + + ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_TSINFO_HEADER); + if (ret < 0) + return ret; + + ret = tsinfo_fill_reply(skb, &req_info->base, &reply_data->base); + if (ret < 0) + return ret; + + reply_data->base.dev = NULL; + genlmsg_end(skb, ehdr); + + return ret; +} + +static int ethnl_tsinfo_dump_one_phydev(struct sk_buff *skb, + struct net_device *dev, + struct phy_device *phydev, + struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct tsinfo_reply_data *reply_data; + struct tsinfo_req_info *req_info; + void *ehdr = NULL; + int ret = 0; + + if (!phy_has_tsinfo(phydev)) + return -EOPNOTSUPP; + + reply_data = ctx->reply_data; + req_info = ctx->req_info; + ehdr = ethnl_tsinfo_prepare_dump(skb, dev, reply_data, cb); + if (IS_ERR(ehdr)) + return PTR_ERR(ehdr); + + ret = phy_ts_info(phydev, &reply_data->ts_info); + if (ret < 0) + goto err; + + ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data, ehdr); + if (ret < 0) + goto err; + + return ret; +err: + genlmsg_cancel(skb, ehdr); + return ret; +} + +static int ethnl_tsinfo_dump_one_netdev(struct sk_buff *skb, + struct net_device *dev, + struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct tsinfo_reply_data *reply_data; + struct tsinfo_req_info *req_info; + void *ehdr = NULL; + int ret = 0; + + if (!ops->get_ts_info) + return -EOPNOTSUPP; + + reply_data = ctx->reply_data; + req_info = ctx->req_info; + for (; ctx->pos_phcqualifier < HWTSTAMP_PROVIDER_QUALIFIER_CNT; + ctx->pos_phcqualifier++) { + if (!net_support_hwtstamp_qualifier(dev, + ctx->pos_phcqualifier)) + continue; + + ehdr = ethnl_tsinfo_prepare_dump(skb, dev, reply_data, cb); + if (IS_ERR(ehdr)) { + ret = PTR_ERR(ehdr); + goto err; + } + + reply_data->ts_info.phc_qualifier = ctx->pos_phcqualifier; + ret = ops->get_ts_info(dev, &reply_data->ts_info); + if (ret < 0) + goto err; + + ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data, + ehdr); + if (ret < 0) + goto err; + } + + return ret; + +err: + genlmsg_cancel(skb, ehdr); + return ret; +} + +static int ethnl_tsinfo_dump_one_net_topo(struct sk_buff *skb, + struct net_device *dev, + struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct phy_device_node *pdn; + int ret = 0; + + if (!ctx->netdev_dump_done) { + ret = ethnl_tsinfo_dump_one_netdev(skb, dev, cb); + if (ret < 0 && ret != -EOPNOTSUPP) + return ret; + ctx->netdev_dump_done = true; + } + + if (!dev->link_topo) { + if (phy_has_tsinfo(dev->phydev)) { + ret = ethnl_tsinfo_dump_one_phydev(skb, dev, + dev->phydev, cb); + if (ret < 0 && ret != -EOPNOTSUPP) + return ret; + } + + return 0; + } + + xa_for_each_start(&dev->link_topo->phys, ctx->pos_phyindex, pdn, + ctx->pos_phyindex) { + if (phy_has_tsinfo(pdn->phy)) { + ret = ethnl_tsinfo_dump_one_phydev(skb, dev, + pdn->phy, cb); + if (ret < 0 && ret != -EOPNOTSUPP) + return ret; + } + } + + return ret; +} + +int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + if (ctx->req_info->base.dev) { + ret = ethnl_tsinfo_dump_one_net_topo(skb, + ctx->req_info->base.dev, + cb); + } else { + for_each_netdev_dump(net, dev, ctx->pos_ifindex) { + ret = ethnl_tsinfo_dump_one_net_topo(skb, dev, cb); + if (ret < 0 && ret != -EOPNOTSUPP) + break; + ctx->pos_phyindex = 0; + ctx->netdev_dump_done = false; + ctx->pos_phcqualifier = HWTSTAMP_PROVIDER_QUALIFIER_PRECISE; + } + } + rtnl_unlock(); + + return ret; +} + +int ethnl_tsinfo_start(struct netlink_callback *cb) +{ + const struct genl_dumpit_info *info = genl_dumpit_info(cb); + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct nlattr **tb = info->info.attrs; + struct tsinfo_reply_data *reply_data; + struct tsinfo_req_info *req_info; + int ret; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + req_info = kzalloc(sizeof(*req_info), GFP_KERNEL); + if (!req_info) + return -ENOMEM; + reply_data = kzalloc(sizeof(*reply_data), GFP_KERNEL); + if (!reply_data) { + ret = -ENOMEM; + goto free_req_info; + } + + ret = ethnl_parse_header_dev_get(&req_info->base, + tb[ETHTOOL_A_TSINFO_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); + if (ret < 0) + goto free_reply_data; + + ctx->req_info = req_info; + ctx->reply_data = reply_data; + ctx->pos_ifindex = 0; + ctx->pos_phyindex = 0; + ctx->netdev_dump_done = false; + ctx->pos_phcqualifier = HWTSTAMP_PROVIDER_QUALIFIER_PRECISE; + + return 0; + +free_reply_data: + kfree(reply_data); +free_req_info: + kfree(req_info); + + return ret; +} + +int ethnl_tsinfo_done(struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct tsinfo_req_info *req_info = ctx->req_info; + + ethnl_parse_header_dev_put(&req_info->base); + kfree(ctx->reply_data); + kfree(ctx->req_info); + + return 0; +} + const struct ethnl_request_ops ethnl_tsinfo_request_ops = { .request_cmd = ETHTOOL_MSG_TSINFO_GET, .reply_cmd = ETHTOOL_MSG_TSINFO_GET_REPLY, @@ -180,6 +529,7 @@ const struct ethnl_request_ops ethnl_tsinfo_request_ops = { .req_info_size = sizeof(struct tsinfo_req_info), .reply_data_size = sizeof(struct tsinfo_reply_data), + .parse_request = tsinfo_parse_request, .prepare_data = tsinfo_prepare_data, .reply_size = tsinfo_reply_size, .fill_reply = tsinfo_fill_reply, diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 1a195efc79cd..5b2cfac3b2ba 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -57,14 +57,11 @@ DEFINE_SHOW_ATTRIBUTE(hsr_node_table); void hsr_debugfs_rename(struct net_device *dev) { struct hsr_priv *priv = netdev_priv(dev); - struct dentry *d; + int err; - d = debugfs_rename(hsr_debugfs_root_dir, priv->node_tbl_root, - hsr_debugfs_root_dir, dev->name); - if (IS_ERR(d)) + err = debugfs_change_name(priv->node_tbl_root, "%s", dev->name); + if (err) netdev_warn(dev, "failed to rename\n"); - else - priv->node_tbl_root = d; } /* hsr_debugfs_init - create hsr node_table file for dumping diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 03eadd6c51fd..b6fb18469439 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -663,6 +663,19 @@ bool is_hsr_master(struct net_device *dev) } EXPORT_SYMBOL(is_hsr_master); +struct net_device *hsr_get_port_ndev(struct net_device *ndev, + enum hsr_port_type pt) +{ + struct hsr_priv *hsr = netdev_priv(ndev); + struct hsr_port *port; + + hsr_for_each_port(hsr, port) + if (port->type == pt) + return port->dev; + return NULL; +} +EXPORT_SYMBOL(hsr_get_port_ndev); + /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 87bb3a91598e..a4bacf198555 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -700,9 +700,12 @@ static int fill_frame_info(struct hsr_frame_info *frame, frame->is_vlan = true; if (frame->is_vlan) { - if (skb->mac_len < offsetofend(struct hsr_vlan_ethhdr, vlanhdr)) + /* Note: skb->mac_len might be wrong here. */ + if (!pskb_may_pull(skb, + skb_mac_offset(skb) + + offsetofend(struct hsr_vlan_ethhdr, vlanhdr))) return -EINVAL; - vlan_hdr = (struct hsr_vlan_ethhdr *)ethhdr; + vlan_hdr = (struct hsr_vlan_ethhdr *)skb_mac_header(skb); proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto; } diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index fcfeb79bb040..7561845b8bf6 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -121,15 +121,6 @@ struct hsrv1_ethhdr_sp { struct hsr_sup_tag hsr_sup; } __packed; -enum hsr_port_type { - HSR_PT_NONE = 0, /* Must be 0, used by framereg */ - HSR_PT_SLAVE_A, - HSR_PT_SLAVE_B, - HSR_PT_INTERLINK, - HSR_PT_MASTER, - HSR_PT_PORTS, /* This must be the last item in the enum */ -}; - /* PRP Redunancy Control Trailor (RCT). * As defined in IEC-62439-4:2012, the PRP RCT is really { sequence Nr, * Lan indentifier (LanId), LSDU_size and PRP_suffix = 0x88FB }. @@ -163,6 +154,7 @@ struct hsr_port { struct net_device *dev; struct hsr_priv *hsr; enum hsr_port_type type; + struct rcu_head rcu; }; struct hsr_frame_info; diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index 464f683e016d..2a802a5de2ac 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -204,7 +204,6 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, } list_add_tail_rcu(&port->port_list, &hsr->ports); - synchronize_rcu(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); netdev_update_features(master->dev); @@ -235,7 +234,5 @@ void hsr_del_port(struct hsr_port *port) netdev_upper_dev_unlink(port->dev, master->dev); } - synchronize_rcu(); - - kfree(port); + kfree_rcu(port, rcu); } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8095e82de808..21f46ee7b6e9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1309,8 +1309,6 @@ int inet_sk_rebuild_header(struct sock *sk) { struct rtable *rt = dst_rtable(__sk_dst_check(sk, 0)); struct inet_sock *inet = inet_sk(sk); - __be32 daddr; - struct ip_options_rcu *inet_opt; struct flowi4 *fl4; int err; @@ -1319,17 +1317,9 @@ int inet_sk_rebuild_header(struct sock *sk) return 0; /* Reroute. */ - rcu_read_lock(); - inet_opt = rcu_dereference(inet->inet_opt); - daddr = inet->inet_daddr; - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; - rcu_read_unlock(); fl4 = &inet->cork.fl.u.ip4; - rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, - inet->inet_dport, inet->inet_sport, - sk->sk_protocol, ip_sock_rt_tos(sk), - sk->sk_bound_dev_if); + inet_sk_init_flowi4(inet, fl4); + rt = ip_route_output_flow(sock_net(sk), fl4, sk); if (!IS_ERR(rt)) { err = 0; sk_setup_caps(sk, &rt->dst); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 4aca1f05edd3..4b5bc6eb52e7 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -102,8 +102,6 @@ EXPORT_SYMBOL(ip4_datagram_connect); void ip4_datagram_release_cb(struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); - const struct ip_options_rcu *inet_opt; - __be32 daddr = inet->inet_daddr; struct dst_entry *dst; struct flowi4 fl4; struct rtable *rt; @@ -115,14 +113,9 @@ void ip4_datagram_release_cb(struct sock *sk) rcu_read_unlock(); return; } - inet_opt = rcu_dereference(inet->inet_opt); - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; - rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, - inet->inet_saddr, inet->inet_dport, - inet->inet_sport, sk->sk_protocol, - ip_sock_rt_tos(sk), sk->sk_bound_dev_if); + inet_sk_init_flowi4(inet, &fl4); + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); dst = !IS_ERR(rt) ? &rt->dst : NULL; sk_dst_set(sk, dst); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index f3281312eb5e..0e4076866c0a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -279,7 +279,7 @@ static void esp_output_done(void *data, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb->sk, skb, err); + xfrm_output_resume(skb_to_full_sk(skb), skb, err); } } @@ -816,7 +816,8 @@ int esp_input_done2(struct sk_buff *skb, int err) } skb_pull_rcsum(skb, hlen); - if (x->props.mode == XFRM_MODE_TUNNEL) + if (x->props.mode == XFRM_MODE_TUNNEL || + x->props.mode == XFRM_MODE_IPTFS) skb_reset_transport_header(skb); else skb_set_transport_header(skb, -ihl); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 8325224ef072..9517b8667e00 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -249,6 +249,12 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, int err = -EINVAL; struct fib4_rule *rule4 = (struct fib4_rule *) rule; + if (tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) { + NL_SET_ERR_MSG(extack, + "Flow label cannot be specified for IPv4 FIB rules"); + goto errout; + } + if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): ECN bits must be 0"); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 161f5526b86c..d6411ac81096 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2999,7 +2999,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%s\t%08X\t%08X\t%04X\t%d\t%u\t" - "%d\t%08X\t%d\t%u\t%u", + "%u\t%08X\t%d\t%u\t%u", nhc->nhc_dev ? nhc->nhc_dev->name : "*", prefix, gw, flags, 0, 0, fi->fib_priority, @@ -3011,7 +3011,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) } else { seq_printf(seq, "*\t%08X\t%08X\t%04X\t%d\t%u\t" - "%d\t%08X\t%d\t%u\t%u", + "%u\t%08X\t%d\t%u\t%u", prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 963a89ae9c26..094084b61bff 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -312,7 +312,6 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, struct dst_entry *dst = &rt->dst; struct inet_peer *peer; bool rc = true; - int vif; if (!apply_ratelimit) return true; @@ -321,12 +320,12 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) goto out; - vif = l3mdev_master_ifindex(dst->dev); - peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); + rcu_read_lock(); + peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, + l3mdev_master_ifindex_rcu(dst->dev)); rc = inet_peer_xrlim_allow(peer, READ_ONCE(net->ipv4.sysctl_icmp_ratelimit)); - if (peer) - inet_putpeer(peer); + rcu_read_unlock(); out: if (!rc) __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6a238398acc9..3da126cea884 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -88,6 +88,8 @@ #include #include +#include +#include #include #include #include @@ -1430,6 +1432,65 @@ static void ip_mc_hash_remove(struct in_device *in_dev, *mc_hash = im->next_hash; } +static int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, + const struct ip_mc_list *im, int event) +{ + struct ifa_cacheinfo ci; + struct ifaddrmsg *ifm; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct ifaddrmsg), 0); + if (!nlh) + return -EMSGSIZE; + + ifm = nlmsg_data(nlh); + ifm->ifa_family = AF_INET; + ifm->ifa_prefixlen = 32; + ifm->ifa_flags = IFA_F_PERMANENT; + ifm->ifa_scope = RT_SCOPE_UNIVERSE; + ifm->ifa_index = dev->ifindex; + + ci.cstamp = (READ_ONCE(im->mca_cstamp) - INITIAL_JIFFIES) * 100UL / HZ; + ci.tstamp = ci.cstamp; + ci.ifa_prefered = INFINITY_LIFE_TIME; + ci.ifa_valid = INFINITY_LIFE_TIME; + + if (nla_put_in_addr(skb, IFA_MULTICAST, im->multiaddr) < 0 || + nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci) < 0) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } + + nlmsg_end(skb, nlh); + return 0; +} + +static void inet_ifmcaddr_notify(struct net_device *dev, + const struct ip_mc_list *im, int event) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOMEM; + + skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(sizeof(__be32)) + + nla_total_size(sizeof(struct ifa_cacheinfo)), + GFP_KERNEL); + if (!skb) + goto error; + + err = inet_fill_ifmcaddr(skb, dev, im, event); + if (err < 0) { + WARN_ON_ONCE(err == -EMSGSIZE); + nlmsg_free(skb); + goto error; + } + + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MCADDR, NULL, GFP_KERNEL); + return; +error: + rtnl_set_sk_err(net, RTNLGRP_IPV4_MCADDR, err); +} /* * A socket has joined a multicast group on device dev. @@ -1473,6 +1534,8 @@ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, im->interface = in_dev; in_dev_hold(in_dev); im->multiaddr = addr; + im->mca_cstamp = jiffies; + im->mca_tstamp = im->mca_cstamp; /* initial mode is (EX, empty) */ im->sfmode = mode; im->sfcount[mode] = 1; @@ -1492,6 +1555,7 @@ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); + inet_ifmcaddr_notify(in_dev->dev, im, RTM_NEWMULTICAST); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: @@ -1705,6 +1769,8 @@ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) *ip = i->next_rcu; in_dev->mc_count--; __igmp_group_dropped(i, gfp); + inet_ifmcaddr_notify(in_dev->dev, i, + RTM_DELMULTICAST); ip_mc_clear_src(i); if (!in_dev->dead) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6872b5aff73e..e4decfb270fa 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1561,20 +1561,13 @@ EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr); static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl) { const struct inet_sock *inet = inet_sk(sk); - const struct ip_options_rcu *inet_opt; - __be32 daddr = inet->inet_daddr; struct flowi4 *fl4; struct rtable *rt; rcu_read_lock(); - inet_opt = rcu_dereference(inet->inet_opt); - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; fl4 = &fl->u.ip4; - rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, - inet->inet_saddr, inet->inet_dport, - inet->inet_sport, sk->sk_protocol, - ip_sock_rt_tos(sk), sk->sk_bound_dev_if); + inet_sk_init_flowi4(inet, fl4); + rt = ip_route_output_flow(sock_net(sk), fl4, sk); if (IS_ERR(rt)) rt = NULL; if (rt) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 5ab56f4cb529..b8b23a77ceb4 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -95,6 +95,7 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr, { struct rb_node **pp, *parent, *next; struct inet_peer *p; + u32 now; pp = &base->rb_root.rb_node; parent = NULL; @@ -108,8 +109,9 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr, p = rb_entry(parent, struct inet_peer, rb_node); cmp = inetpeer_addr_cmp(daddr, &p->daddr); if (cmp == 0) { - if (!refcount_inc_not_zero(&p->refcnt)) - break; + now = jiffies; + if (READ_ONCE(p->dtime) != now) + WRITE_ONCE(p->dtime, now); return p; } if (gc_stack) { @@ -150,9 +152,6 @@ static void inet_peer_gc(struct inet_peer_base *base, for (i = 0; i < gc_cnt; i++) { p = gc_stack[i]; - /* The READ_ONCE() pairs with the WRITE_ONCE() - * in inet_putpeer() - */ delta = (__u32)jiffies - READ_ONCE(p->dtime); if (delta < ttl || !refcount_dec_if_one(&p->refcnt)) @@ -168,31 +167,23 @@ static void inet_peer_gc(struct inet_peer_base *base, } } +/* Must be called under RCU : No refcount change is done here. */ struct inet_peer *inet_getpeer(struct inet_peer_base *base, - const struct inetpeer_addr *daddr, - int create) + const struct inetpeer_addr *daddr) { struct inet_peer *p, *gc_stack[PEER_MAX_GC]; struct rb_node **pp, *parent; unsigned int gc_cnt, seq; - int invalidated; /* Attempt a lockless lookup first. * Because of a concurrent writer, we might not find an existing entry. */ - rcu_read_lock(); seq = read_seqbegin(&base->lock); p = lookup(daddr, base, seq, NULL, &gc_cnt, &parent, &pp); - invalidated = read_seqretry(&base->lock, seq); - rcu_read_unlock(); if (p) return p; - /* If no writer did a change during our lookup, we can return early. */ - if (!create && !invalidated) - return NULL; - /* retry an exact lookup, taking the lock before. * At least, nodes should be hot in our cache. */ @@ -201,12 +192,12 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, gc_cnt = 0; p = lookup(daddr, base, seq, gc_stack, &gc_cnt, &parent, &pp); - if (!p && create) { + if (!p) { p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC); if (p) { p->daddr = *daddr; p->dtime = (__u32)jiffies; - refcount_set(&p->refcnt, 2); + refcount_set(&p->refcnt, 1); atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; @@ -231,15 +222,9 @@ EXPORT_SYMBOL_GPL(inet_getpeer); void inet_putpeer(struct inet_peer *p) { - /* The WRITE_ONCE() pairs with itself (we run lockless) - * and the READ_ONCE() in inet_peer_gc() - */ - WRITE_ONCE(p->dtime, (__u32)jiffies); - if (refcount_dec_and_test(&p->refcnt)) kfree_rcu(p, rcu); } -EXPORT_SYMBOL_GPL(inet_putpeer); /* * Check transmit rate limitation for given message. @@ -261,23 +246,27 @@ EXPORT_SYMBOL_GPL(inet_putpeer); #define XRLIM_BURST_FACTOR 6 bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) { - unsigned long now, token; + unsigned long now, token, otoken, delta; bool rc = false; if (!peer) return true; - token = peer->rate_tokens; + token = otoken = READ_ONCE(peer->rate_tokens); now = jiffies; - token += now - peer->rate_last; - peer->rate_last = now; - if (token > XRLIM_BURST_FACTOR * timeout) - token = XRLIM_BURST_FACTOR * timeout; + delta = now - READ_ONCE(peer->rate_last); + if (delta) { + WRITE_ONCE(peer->rate_last, now); + token += delta; + if (token > XRLIM_BURST_FACTOR * timeout) + token = XRLIM_BURST_FACTOR * timeout; + } if (token >= timeout) { token -= timeout; rc = true; } - peer->rate_tokens = token; + if (token != otoken) + WRITE_ONCE(peer->rate_tokens, token); return rc; } EXPORT_SYMBOL(inet_peer_xrlim_allow); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 07036a2943c1..7a435746a22d 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -82,15 +82,20 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, static void ip4_frag_init(struct inet_frag_queue *q, const void *a) { struct ipq *qp = container_of(q, struct ipq, q); - struct net *net = q->fqdir->net; - const struct frag_v4_compare_key *key = a; + struct net *net = q->fqdir->net; + struct inet_peer *p = NULL; q->key.v4 = *key; qp->ecn = 0; - qp->peer = q->fqdir->max_dist ? - inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) : - NULL; + if (q->fqdir->max_dist) { + rcu_read_lock(); + p = inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif); + if (p && !refcount_inc_not_zero(&p->refcnt)) + p = NULL; + rcu_read_unlock(); + } + qp->peer = p; } static void ip4_frag_free(struct inet_frag_queue *q) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f1f31ebfc793..ed1b6b44faf8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -924,15 +924,18 @@ static int ipgre_open(struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { - struct flowi4 fl4; + struct flowi4 fl4 = { + .flowi4_oif = t->parms.link, + .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(&t->parms.iph)), + .flowi4_scope = RT_SCOPE_UNIVERSE, + .flowi4_proto = IPPROTO_GRE, + .saddr = t->parms.iph.saddr, + .daddr = t->parms.iph.daddr, + .fl4_gre_key = t->parms.o_key, + }; struct rtable *rt; - rt = ip_route_output_gre(t->net, &fl4, - t->parms.iph.daddr, - t->parms.iph.saddr, - t->parms.o_key, - t->parms.iph.tos & INET_DSCP_MASK, - t->parms.link); + rt = ip_route_output_key(t->net, &fl4); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index f0a4dda246ab..30a5e9460d00 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -314,7 +314,7 @@ static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, int tcp_v4_early_demux(struct sk_buff *skb); int udp_v4_early_demux(struct sk_buff *skb); -static int ip_rcv_finish_core(struct net *net, struct sock *sk, +static int ip_rcv_finish_core(struct net *net, struct sk_buff *skb, struct net_device *dev, const struct sk_buff *hint) { @@ -442,7 +442,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) if (!skb) return NET_RX_SUCCESS; - ret = ip_rcv_finish_core(net, sk, skb, dev, NULL); + ret = ip_rcv_finish_core(net, skb, dev, NULL); if (ret != NET_RX_DROP) ret = dst_input(skb); return ret; @@ -589,8 +589,7 @@ static struct sk_buff *ip_extract_route_hint(const struct net *net, return skb; } -static void ip_list_rcv_finish(struct net *net, struct sock *sk, - struct list_head *head) +static void ip_list_rcv_finish(struct net *net, struct list_head *head) { struct sk_buff *skb, *next, *hint = NULL; struct dst_entry *curr_dst = NULL; @@ -607,7 +606,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, skb = l3mdev_ip_rcv(skb); if (!skb) continue; - if (ip_rcv_finish_core(net, sk, skb, dev, hint) == NET_RX_DROP) + if (ip_rcv_finish_core(net, skb, dev, hint) == NET_RX_DROP) continue; dst = skb_dst(skb); @@ -633,7 +632,7 @@ static void ip_sublist_rcv(struct list_head *head, struct net_device *dev, { NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL, head, dev, NULL, ip_rcv_finish); - ip_list_rcv_finish(net, NULL, head); + ip_list_rcv_finish(net, head); } /* Receive a list of IP packets */ diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 0065b1996c94..ea7a260bec8a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -478,24 +478,16 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, /* Make sure we can route this packet. */ rt = dst_rtable(__sk_dst_check(sk, 0)); if (!rt) { - __be32 daddr; + inet_sk_init_flowi4(inet, fl4); - /* Use correct destination address if we have options. */ - daddr = inet->inet_daddr; - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; + /* sctp_v4_xmit() uses its own DSCP value */ + fl4->flowi4_tos = tos & INET_DSCP_MASK; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ - rt = ip_route_output_ports(net, fl4, sk, - daddr, inet->inet_saddr, - inet->inet_dport, - inet->inet_sport, - sk->sk_protocol, - tos & INET_DSCP_MASK, - sk->sk_bound_dev_if); + rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; sk_setup_caps(sk, &rt->dst); @@ -1169,7 +1161,10 @@ alloc_new_skb: /* [!] NOTE: copy will be negative if pagedlen>0 * because then the equation reduces to -fraggap. */ - if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { + if (copy > 0 && + INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, data + transhdrlen, offset, + copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; @@ -1213,8 +1208,9 @@ alloc_new_skb: unsigned int off; off = skb->len; - if (getfrag(from, skb_put(skb, copy), - offset, copy, off, skb) < 0) { + if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, skb_put(skb, copy), + offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; @@ -1252,7 +1248,8 @@ alloc_new_skb: get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); - if (getfrag(from, + if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; @@ -1328,7 +1325,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->mark = ipc->sockc.mark; - cork->priority = ipc->priority; + cork->priority = ipc->sockc.priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; sock_tx_timestamp(sk, &ipc->sockc, &cork->tx_flags); @@ -1465,7 +1462,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, ip_options_build(skb, opt, cork->addr, rt); } - skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); + skb->priority = cork->priority; skb->mark = cork->mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index cf377377b52d..6d9c5c20b1c4 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -128,20 +128,20 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) { - char *secdata; - u32 seclen, secid; + struct lsm_context ctx; + u32 secid; int err; err = security_socket_getpeersec_dgram(NULL, skb, &secid); if (err) return; - err = security_secid_to_secctx(secid, &secdata, &seclen); - if (err) + err = security_secid_to_secctx(secid, &ctx); + if (err < 0) return; - put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata); - security_release_secctx(secdata, seclen); + put_cmsg(msg, SOL_IP, SCM_SECURITY, ctx.len, ctx.context); + security_release_secctx(&ctx); } static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) @@ -315,7 +315,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, if (val < 0 || val > 255) return -EINVAL; ipc->tos = val; - ipc->priority = rt_tos2priority(ipc->tos); + ipc->sockc.priority = rt_tos2priority(ipc->tos); break; case IP_PROTOCOL: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 25505f9b724c..09b73acf037a 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -294,7 +294,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, - iph->tos & INET_DSCP_MASK, dev_net(dev), + iph->tos & INET_DSCP_MASK, tunnel->net, tunnel->parms.link, tunnel->fwmark, 0, 0); rt = ip_route_output_key(tunnel->net, &fl4); @@ -611,7 +611,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), - tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark, + tos & INET_DSCP_MASK, tunnel->net, 0, skb->mark, skb_get_hash(skb), key->flow_flags); if (!tunnel_hlen) @@ -774,7 +774,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, tos & INET_DSCP_MASK, - dev_net(dev), READ_ONCE(tunnel->parms.link), + tunnel->net, READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 99d8faa508e5..21ae7594a852 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -831,7 +831,7 @@ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, cache->mfc_un.res.maxvif = vifi + 1; } } - cache->mfc_un.res.lastuse = jiffies; + WRITE_ONCE(cache->mfc_un.res.lastuse, jiffies); } static int vif_add(struct net *net, struct mr_table *mrt, @@ -1681,9 +1681,9 @@ int ipmr_ioctl(struct sock *sk, int cmd, void *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr->src.s_addr, sr->grp.s_addr); if (c) { - sr->pktcnt = c->_c.mfc_un.res.pkt; - sr->bytecnt = c->_c.mfc_un.res.bytes; - sr->wrong_if = c->_c.mfc_un.res.wrong_if; + sr->pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr->bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr->wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); return 0; } @@ -1753,9 +1753,9 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { - sr.pktcnt = c->_c.mfc_un.res.pkt; - sr.bytecnt = c->_c.mfc_un.res.bytes; - sr.wrong_if = c->_c.mfc_un.res.wrong_if; + sr.pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr.bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr.wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) @@ -1988,9 +1988,9 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, int vif, ct; vif = c->_c.mfc_parent; - c->_c.mfc_un.res.pkt++; - c->_c.mfc_un.res.bytes += skb->len; - c->_c.mfc_un.res.lastuse = jiffies; + atomic_long_inc(&c->_c.mfc_un.res.pkt); + atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); + WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; @@ -2021,7 +2021,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, goto dont_forward; } - c->_c.mfc_un.res.wrong_if++; + atomic_long_inc(&c->_c.mfc_un.res.wrong_if); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -3029,9 +3029,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", - mfc->_c.mfc_un.res.pkt, - mfc->_c.mfc_un.res.bytes, - mfc->_c.mfc_un.res.wrong_if); + atomic_long_read(&mfc->_c.mfc_un.res.pkt), + atomic_long_read(&mfc->_c.mfc_un.res.bytes), + atomic_long_read(&mfc->_c.mfc_un.res.wrong_if)); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index f0af12a2f70b..28d77d454d44 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -263,9 +263,9 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, lastuse = READ_ONCE(c->mfc_un.res.lastuse); lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; - mfcs.mfcs_packets = c->mfc_un.res.pkt; - mfcs.mfcs_bytes = c->mfc_un.res.bytes; - mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + mfcs.mfcs_packets = atomic_long_read(&c->mfc_un.res.pkt); + mfcs.mfcs_bytes = atomic_long_read(&c->mfc_un.res.bytes); + mfcs.mfcs_wrong_if = atomic_long_read(&c->mfc_un.res.wrong_if); if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), RTA_PAD)) @@ -330,9 +330,6 @@ next_entry: list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { if (e < s_e) goto next_entry2; - if (filter->dev && - !mr_mfc_uses_dev(mrt, mfc, filter->dev)) - goto next_entry2; err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 40053a02bae1..affd21a0f572 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -189,6 +189,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED), SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED), SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED), + SNMP_MIB_ITEM("PAWSOldAck", LINUX_MIB_PAWS_OLD_ACK), SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS), SNMP_MIB_ITEM("DelayedACKLocked", LINUX_MIB_DELAYEDACKLOCKED), SNMP_MIB_ITEM("DelayedACKLost", LINUX_MIB_DELAYEDACKLOST), diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 0e9e01967ec9..4304a68d1db0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -358,7 +358,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IP); - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_dst_set(skb, &rt->dst); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0fbec3509618..577b88a43293 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -870,11 +870,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) } log_martians = IN_DEV_LOG_MARTIANS(in_dev); vif = l3mdev_master_ifindex_rcu(rt->dst.dev); - rcu_read_unlock(); net = dev_net(rt->dst.dev); - peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif); if (!peer) { + rcu_read_unlock(); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); return; @@ -893,7 +893,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) */ if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; - goto out_put_peer; + goto out_unlock; } /* Check for load limit; set rate_last to the latest sent @@ -914,8 +914,8 @@ void ip_rt_send_redirect(struct sk_buff *skb) &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); } -out_put_peer: - inet_putpeer(peer); +out_unlock: + rcu_read_unlock(); } static int ip_error(struct sk_buff *skb) @@ -975,9 +975,9 @@ static int ip_error(struct sk_buff *skb) break; } + rcu_read_lock(); peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, - l3mdev_master_ifindex(skb->dev), 1); - + l3mdev_master_ifindex_rcu(skb->dev)); send = true; if (peer) { now = jiffies; @@ -989,8 +989,9 @@ static int ip_error(struct sk_buff *skb) peer->rate_tokens -= ip_rt_error_cost; else send = false; - inet_putpeer(peer); } + rcu_read_unlock(); + if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); @@ -2445,6 +2446,7 @@ martian_destination: net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n", &daddr, &saddr, dev->name); #endif + goto out; e_nobufs: reason = SKB_DROP_REASON_NOMEM; @@ -3268,6 +3270,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct flowi4 fl4 = {}; __be32 dst = 0; __be32 src = 0; + dscp_t dscp; kuid_t uid; u32 iif; int err; @@ -3282,6 +3285,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, dst = nla_get_in_addr_default(tb[RTA_DST], 0); iif = nla_get_u32_default(tb[RTA_IIF], 0); mark = nla_get_u32_default(tb[RTA_MARK], 0); + dscp = inet_dsfield_to_dscp(rtm->rtm_tos); if (tb[RTA_UID]) uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else @@ -3306,7 +3310,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos & INET_DSCP_MASK; + fl4.flowi4_tos = inet_dscp_to_dsfield(dscp); fl4.flowi4_oif = nla_get_u32_default(tb[RTA_OIF], 0); fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; @@ -3330,9 +3334,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; - err = ip_route_input_rcu(skb, dst, src, - inet_dsfield_to_dscp(rtm->rtm_tos), - dev, &res) ? -EINVAL : 0; + err = ip_route_input_rcu(skb, dst, src, dscp, dev, + &res) ? -EINVAL : 0; rt = skb_rtable(skb); if (err == 0 && rt->dst.error) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a79b2a52ce01..42cb5dc9cb24 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -45,6 +45,7 @@ static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024; static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX; static int tcp_plb_max_rounds = 31; static int tcp_plb_max_cong_thresh = 256; +static unsigned int tcp_tw_reuse_delay_max = TCP_PAWS_MSL * MSEC_PER_SEC; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -1065,6 +1066,15 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, + { + .procname = "tcp_tw_reuse_delay", + .data = &init_net.ipv4.sysctl_tcp_tw_reuse_delay, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = &tcp_tw_reuse_delay_max, + }, { .procname = "tcp_max_syn_backlog", .data = &init_net.ipv4.sysctl_max_syn_backlog, diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 99cef92e6290..47f65b1b70ca 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -49,13 +49,14 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, sge = sk_msg_elem(msg, i); size = (apply && apply_bytes < sge->length) ? apply_bytes : sge->length; - if (!sk_wmem_schedule(sk, size)) { + if (!__sk_rmem_schedule(sk, size, false)) { if (!copied) ret = -ENOMEM; break; } sk_mem_charge(sk, size); + atomic_add(size, &sk->sk_rmem_alloc); sk_msg_xfer(tmp, msg, i, size); copied += size; if (sge->length) @@ -74,7 +75,8 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - sk_psock_queue_msg(psock, tmp); + if (!sk_psock_queue_msg(psock, tmp)) + atomic_sub(copied, &sk->sk_rmem_alloc); sk_psock_data_ready(sk, psock); } else { sk_msg_free(sk, tmp); @@ -493,7 +495,7 @@ more_data: static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_msg tmp, *msg_tx = NULL; - int copied = 0, err = 0; + int copied = 0, err = 0, ret = 0; struct sk_psock *psock; long timeo; int flags; @@ -536,14 +538,14 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) copy = msg_tx->sg.size - osize; } - err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, + ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, copy); - if (err < 0) { + if (ret < 0) { sk_msg_trim(sk, msg_tx, osize); goto out_err; } - copied += copy; + copied += ret; if (psock->cork_bytes) { if (size > psock->cork_bytes) psock->cork_bytes = 0; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5dbed91c6178..76c23675ae50 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -392,6 +392,10 @@ static void hystart_update(struct sock *sk, u32 delay) if (after(tp->snd_una, ca->end_seq)) bictcp_hystart_reset(sk); + /* hystart triggers when cwnd is larger than some threshold */ + if (tcp_snd_cwnd(tp) < hystart_low_window) + return; + if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); @@ -467,9 +471,7 @@ __bpf_kfunc static void cubictcp_acked(struct sock *sk, const struct ack_sample if (ca->delay_min == 0 || ca->delay_min > delay) ca->delay_min = delay; - /* hystart triggers when cwnd is larger than some threshold */ - if (!ca->found && tcp_in_slow_start(tp) && hystart && - tcp_snd_cwnd(tp) >= hystart_low_window) + if (!ca->found && tcp_in_slow_start(tp) && hystart) hystart_update(sk, delay); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5bdf13ac26ef..eb82e01da911 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4450,34 +4450,40 @@ static u32 tcp_tsval_replay(const struct sock *sk) return inet_csk(sk)->icsk_rto * 1200 / HZ; } -static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) +static enum skb_drop_reason tcp_disordered_ack_check(const struct sock *sk, + const struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); const struct tcphdr *th = tcp_hdr(skb); - u32 seq = TCP_SKB_CB(skb)->seq; + SKB_DR_INIT(reason, TCP_RFC7323_PAWS); u32 ack = TCP_SKB_CB(skb)->ack_seq; + u32 seq = TCP_SKB_CB(skb)->seq; - return /* 1. Pure ACK with correct sequence number. */ - (th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) && + /* 1. Is this not a pure ACK ? */ + if (!th->ack || seq != TCP_SKB_CB(skb)->end_seq) + return reason; - /* 2. ... and duplicate ACK. */ - ack == tp->snd_una && + /* 2. Is its sequence not the expected one ? */ + if (seq != tp->rcv_nxt) + return before(seq, tp->rcv_nxt) ? + SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK : + reason; - /* 3. ... and does not update window. */ - !tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) && + /* 3. Is this not a duplicate ACK ? */ + if (ack != tp->snd_una) + return reason; - /* 4. ... and sits in replay window. */ - (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= - tcp_tsval_replay(sk); -} + /* 4. Is this updating the window ? */ + if (tcp_may_update_window(tp, ack, seq, ntohs(th->window) << + tp->rx_opt.snd_wscale)) + return reason; -static inline bool tcp_paws_discard(const struct sock *sk, - const struct sk_buff *skb) -{ - const struct tcp_sock *tp = tcp_sk(sk); + /* 5. Is this not in the replay window ? */ + if ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) > + tcp_tsval_replay(sk)) + return reason; - return !tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW) && - !tcp_disordered_ack(sk, skb); + return 0; } /* Check segment sequence number for validity. @@ -5949,23 +5955,35 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, SKB_DR(reason); /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) && - tp->rx_opt.saw_tstamp && - tcp_paws_discard(sk, skb)) { - if (!th->rst) { - if (unlikely(th->syn)) - goto syn_challenge; - NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); - if (!tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDPAWS, - &tp->last_oow_ack_time)) - tcp_send_dupack(sk, skb); - SKB_DR_SET(reason, TCP_RFC7323_PAWS); - goto discard; - } - /* Reset is accepted even if it did not pass PAWS. */ - } + if (!tcp_fast_parse_options(sock_net(sk), skb, th, tp) || + !tp->rx_opt.saw_tstamp || + tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW)) + goto step1; + reason = tcp_disordered_ack_check(sk, skb); + if (!reason) + goto step1; + /* Reset is accepted even if it did not pass PAWS. */ + if (th->rst) + goto step1; + if (unlikely(th->syn)) + goto syn_challenge; + + /* Old ACK are common, increment PAWS_OLD_ACK + * and do not send a dupack. + */ + if (reason == SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWS_OLD_ACK); + goto discard; + } + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); + if (!tcp_oow_rate_limited(sock_net(sk), skb, + LINUX_MIB_TCPACKSKIPPEDPAWS, + &tp->last_oow_ack_time)) + tcp_send_dupack(sk, skb); + goto discard; + +step1: /* Step 1: check sequence number */ reason = tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); if (reason) { @@ -7328,6 +7346,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, req->timeout))) { reqsk_free(req); + dst_release(dst); return 0; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a38c8b1f44db..cc2b5194a18d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -120,6 +120,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); int ts_recent_stamp; + u32 reuse_thresh; if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) reuse = 0; @@ -162,9 +163,10 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) and use initial timestamp retrieved from peer table. */ ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp); + reuse_thresh = READ_ONCE(tw->tw_entry_stamp) + + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse_delay); if (ts_recent_stamp && - (!twp || (reuse && time_after32(ktime_get_seconds(), - ts_recent_stamp)))) { + (!twp || (reuse && time_after32(tcp_clock_ms(), reuse_thresh)))) { /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk * and releasing the bucket lock. */ @@ -896,7 +898,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_mark : sk->sk_mark; + inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); @@ -3457,6 +3459,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_tcp_tw_reuse = 2; + net->ipv4.sysctl_tcp_tw_reuse_delay = 1 * MSEC_PER_SEC; net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; refcount_set(&net->ipv4.tcp_death_row.tw_refcount, 1); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7121d8573928..b089b08e9617 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -157,8 +157,11 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, rcv_nxt); if (tmp_opt.saw_tstamp) { + u64 ts = tcp_clock_ms(); + + WRITE_ONCE(tw->tw_entry_stamp, ts); WRITE_ONCE(tcptw->tw_ts_recent_stamp, - ktime_get_seconds()); + div_u64(ts, MSEC_PER_SEC)); WRITE_ONCE(tcptw->tw_ts_recent, tmp_opt.rcv_tsval); } @@ -316,6 +319,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_mark = sk->sk_mark; tw->tw_priority = READ_ONCE(sk->sk_priority); tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; + /* refreshed when we enter true TIME-WAIT state */ + tw->tw_entry_stamp = tcp_time_stamp_ms(tp); tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; tcptw->tw_rcv_wnd = tcp_receive_window(tp); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0e5b9a654254..bc95d2a5924f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -265,11 +265,14 @@ static u16 tcp_select_window(struct sock *sk) u32 cur_win, new_win; /* Make the window 0 if we failed to queue the data because we - * are out of memory. The window is temporary, so we don't store - * it on the socket. + * are out of memory. */ - if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) + if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) { + tp->pred_flags = 0; + tp->rcv_wnd = 0; + tp->rcv_wup = tp->rcv_nxt; return 0; + } cur_win = tcp_receive_window(tp); new_win = __tcp_select_window(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e8953e88efef..c472c9a57cf6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -420,6 +420,49 @@ u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, } EXPORT_SYMBOL(udp_ehashfn); +/** + * udp4_lib_lookup1() - Simplified lookup using primary hash (destination port) + * @net: Network namespace + * @saddr: Source address, network order + * @sport: Source port, network order + * @daddr: Destination address, network order + * @hnum: Destination port, host order + * @dif: Destination interface index + * @sdif: Destination bridge port index, if relevant + * @udptable: Set of UDP hash tables + * + * Simplified lookup to be used as fallback if no sockets are found due to a + * potential race between (receive) address change, and lookup happening before + * the rehash operation. This function ignores SO_REUSEPORT groups while scoring + * result sockets, because if we have one, we don't need the fallback at all. + * + * Called under rcu_read_lock(). + * + * Return: socket with highest matching score if any, NULL if none + */ +static struct sock *udp4_lib_lookup1(const struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, + int dif, int sdif, + const struct udp_table *udptable) +{ + unsigned int slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot = &udptable->hash[slot]; + struct sock *sk, *result = NULL; + int score, badness = 0; + + sk_for_each_rcu(sk, &hslot->head) { + score = compute_score(sk, net, + saddr, sport, daddr, hnum, dif, sdif); + if (score > badness) { + result = sk; + badness = score; + } + } + + return result; +} + /* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(const struct net *net, __be32 saddr, __be16 sport, @@ -533,7 +576,7 @@ begin: return NULL; } -/* In hash4, rehash can happen in connect(), where hash4_cnt keeps unchanged. */ +/* udp_rehash4() only checks hslot4, and hash4_cnt is not processed. */ static void udp_rehash4(struct udp_table *udptable, struct sock *sk, u16 newhash4) { @@ -582,15 +625,13 @@ void udp_lib_hash4(struct sock *sk, u16 hash) struct net *net = sock_net(sk); struct udp_table *udptable; - /* Connected udp socket can re-connect to another remote address, - * so rehash4 is needed. + /* Connected udp socket can re-connect to another remote address, which + * will be handled by rehash. Thus no need to redo hash4 here. */ - udptable = net->ipv4.udp_table; - if (udp_hashed4(sk)) { - udp_rehash4(udptable, sk, hash); + if (udp_hashed4(sk)) return; - } + udptable = net->ipv4.udp_table; hslot = udp_hashslot(udptable, net, udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); hslot4 = udp_hashslot4(udptable, hash); @@ -683,6 +724,19 @@ struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, result = udp4_lib_lookup2(net, saddr, sport, htonl(INADDR_ANY), hnum, dif, sdif, hslot2, skb); + if (!IS_ERR_OR_NULL(result)) + goto done; + + /* Primary hash (destination port) lookup as fallback for this race: + * 1. __ip4_datagram_connect() sets sk_rcv_saddr + * 2. lookup (this function): new sk_rcv_saddr, hashes not updated yet + * 3. rehash operation updating _secondary and four-tuple_ hashes + * The primary hash doesn't need an update after 1., so, thanks to this + * further step, 1. and 3. don't need to be atomic against the lookup. + */ + result = udp4_lib_lookup1(net, saddr, sport, daddr, hnum, dif, sdif, + udptable); + done: if (IS_ERR(result)) return NULL; @@ -2173,14 +2227,14 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2, *nhslot2; + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); udp_sk(sk)->udp_portaddr_hash = newhash; if (hslot2 != nhslot2 || rcu_access_pointer(sk->sk_reuseport_cb)) { - hslot = udp_hashslot(udptable, sock_net(sk), - udp_sk(sk)->udp_port_hash); /* we must lock primary chain too */ spin_lock_bh(&hslot->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) @@ -2199,19 +2253,29 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) spin_unlock(&nhslot2->lock); } - if (udp_hashed4(sk)) { - udp_rehash4(udptable, sk, newhash4); + spin_unlock_bh(&hslot->lock); + } - if (hslot2 != nhslot2) { - spin_lock(&hslot2->lock); - udp_hash4_dec(hslot2); - spin_unlock(&hslot2->lock); + /* Now process hash4 if necessary: + * (1) update hslot4; + * (2) update hslot2->hash4_cnt. + * Note that hslot2/hslot4 should be checked separately, as + * either of them may change with the other unchanged. + */ + if (udp_hashed4(sk)) { + spin_lock_bh(&hslot->lock); - spin_lock(&nhslot2->lock); - udp_hash4_inc(nhslot2); - spin_unlock(&nhslot2->lock); - } + udp_rehash4(udptable, sk, newhash4); + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + udp_hash4_dec(hslot2); + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + udp_hash4_inc(nhslot2); + spin_unlock(&nhslot2->lock); } + spin_unlock_bh(&hslot->lock); } } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 0e765466d7f7..ac8cc1076536 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -852,7 +852,7 @@ static void addrconf_forward_change(struct net *net, __s32 newf) struct inet6_dev *idev; for_each_netdev(net, dev) { - idev = __in6_dev_get(dev); + idev = __in6_dev_get_rtnl_net(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); @@ -865,13 +865,12 @@ static void addrconf_forward_change(struct net *net, __s32 newf) static int addrconf_fixup_forwarding(const struct ctl_table *table, int *p, int newf) { - struct net *net; + struct net *net = (struct net *)table->extra2; int old; - if (!rtnl_trylock()) + if (!rtnl_net_trylock(net)) return restart_syscall(); - net = (struct net *)table->extra2; old = *p; WRITE_ONCE(*p, newf); @@ -881,7 +880,7 @@ static int addrconf_fixup_forwarding(const struct ctl_table *table, int *p, int NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); - rtnl_unlock(); + rtnl_net_unlock(net); return 0; } @@ -903,7 +902,7 @@ static int addrconf_fixup_forwarding(const struct ctl_table *table, int *p, int net->ipv6.devconf_all); } else if ((!newf) ^ (!old)) dev_forward_change((struct inet6_dev *)table->extra1); - rtnl_unlock(); + rtnl_net_unlock(net); if (newf) rt6_purge_dflt_routers(net); @@ -916,7 +915,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf) struct inet6_dev *idev; for_each_netdev(net, dev) { - idev = __in6_dev_get(dev); + idev = __in6_dev_get_rtnl_net(dev); if (idev) { int changed = (!idev->cnf.ignore_routes_with_linkdown) ^ (!newf); @@ -933,13 +932,12 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf) static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int newf) { - struct net *net; + struct net *net = (struct net *)table->extra2; int old; - if (!rtnl_trylock()) + if (!rtnl_net_trylock(net)) return restart_syscall(); - net = (struct net *)table->extra2; old = *p; WRITE_ONCE(*p, newf); @@ -950,7 +948,7 @@ static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int ne NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); - rtnl_unlock(); + rtnl_net_unlock(net); return 0; } @@ -964,7 +962,8 @@ static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int ne NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); } - rtnl_unlock(); + + rtnl_net_unlock(net); return 1; } @@ -2980,11 +2979,11 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg) if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; - rtnl_lock(); + rtnl_net_lock(net); dev = __dev_get_by_index(net, ireq.ifr6_ifindex); if (dev && dev->type == ARPHRD_SIT) err = addrconf_set_sit_dstaddr(net, dev, &ireq); - rtnl_unlock(); + rtnl_net_unlock(net); return err; } @@ -3008,39 +3007,25 @@ static int ipv6_mc_config(struct sock *sk, bool join, /* * Manual configuration of address on an interface */ -static int inet6_addr_add(struct net *net, int ifindex, - struct ifa6_config *cfg, +static int inet6_addr_add(struct net *net, struct net_device *dev, + struct ifa6_config *cfg, clock_t expires, u32 flags, struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; - struct net_device *dev; - unsigned long timeout; - clock_t expires; - u32 flags; - ASSERT_RTNL(); + ASSERT_RTNL_NET(net); if (cfg->plen > 128) { NL_SET_ERR_MSG_MOD(extack, "Invalid prefix length"); return -EINVAL; } - /* check the lifetime */ - if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) { - NL_SET_ERR_MSG_MOD(extack, "address lifetime invalid"); - return -EINVAL; - } - if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64) { NL_SET_ERR_MSG_MOD(extack, "address with \"mngtmpaddr\" flag must have a prefix length of 64"); return -EINVAL; } - dev = __dev_get_by_index(net, ifindex); - if (!dev) - return -ENODEV; - idev = addrconf_add_dev(dev); if (IS_ERR(idev)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device"); @@ -3049,7 +3034,7 @@ static int inet6_addr_add(struct net *net, int ifindex, if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk, - true, cfg->pfx, ifindex); + true, cfg->pfx, dev->ifindex); if (ret < 0) { NL_SET_ERR_MSG_MOD(extack, "Multicast auto join failed"); @@ -3059,24 +3044,6 @@ static int inet6_addr_add(struct net *net, int ifindex, cfg->scope = ipv6_addr_scope(cfg->pfx); - timeout = addrconf_timeout_fixup(cfg->valid_lft, HZ); - if (addrconf_finite_timeout(timeout)) { - expires = jiffies_to_clock_t(timeout * HZ); - cfg->valid_lft = timeout; - flags = RTF_EXPIRES; - } else { - expires = 0; - flags = 0; - cfg->ifa_flags |= IFA_F_PERMANENT; - } - - timeout = addrconf_timeout_fixup(cfg->preferred_lft, HZ); - if (addrconf_finite_timeout(timeout)) { - if (timeout == 0) - cfg->ifa_flags |= IFA_F_DEPRECATED; - cfg->preferred_lft = timeout; - } - ifp = ipv6_add_addr(idev, cfg, true, extack); if (!IS_ERR(ifp)) { if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) { @@ -3104,7 +3071,7 @@ static int inet6_addr_add(struct net *net, int ifindex, return 0; } else if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, - cfg->pfx, ifindex); + cfg->pfx, dev->ifindex); } return PTR_ERR(ifp); @@ -3129,7 +3096,7 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, return -ENODEV; } - idev = __in6_dev_get(dev); + idev = __in6_dev_get_rtnl_net(dev); if (!idev) { NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device"); return -ENXIO; @@ -3170,6 +3137,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) .preferred_lft = INFINITY_LIFE_TIME, .valid_lft = INFINITY_LIFE_TIME, }; + struct net_device *dev; struct in6_ifreq ireq; int err; @@ -3182,9 +3150,13 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) cfg.pfx = &ireq.ifr6_addr; cfg.plen = ireq.ifr6_prefixlen; - rtnl_lock(); - err = inet6_addr_add(net, ireq.ifr6_ifindex, &cfg, NULL); - rtnl_unlock(); + rtnl_net_lock(net); + dev = __dev_get_by_index(net, ireq.ifr6_ifindex); + if (dev) + err = inet6_addr_add(net, dev, &cfg, 0, 0, NULL); + else + err = -ENODEV; + rtnl_net_unlock(net); return err; } @@ -3199,10 +3171,10 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg) if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; - rtnl_lock(); + rtnl_net_lock(net); err = inet6_addr_del(net, ireq.ifr6_ifindex, 0, &ireq.ifr6_addr, ireq.ifr6_prefixlen, NULL); - rtnl_unlock(); + rtnl_net_unlock(net); return err; } @@ -4205,6 +4177,7 @@ static void addrconf_dad_work(struct work_struct *w) struct inet6_dev *idev = ifp->idev; bool bump_id, disable_ipv6 = false; struct in6_addr mcaddr; + struct net *net; enum { DAD_PROCESS, @@ -4212,7 +4185,9 @@ static void addrconf_dad_work(struct work_struct *w) DAD_ABORT, } action = DAD_PROCESS; - rtnl_lock(); + net = dev_net(idev->dev); + + rtnl_net_lock(net); spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_PREDAD) { @@ -4222,7 +4197,7 @@ static void addrconf_dad_work(struct work_struct *w) action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; - if ((READ_ONCE(dev_net(idev->dev)->ipv6.devconf_all->accept_dad) > 1 || + if ((READ_ONCE(net->ipv6.devconf_all->accept_dad) > 1 || READ_ONCE(idev->cnf.accept_dad) > 1) && !idev->cnf.disable_ipv6 && !(ifp->flags & IFA_F_STABLE_PRIVACY)) { @@ -4304,7 +4279,7 @@ static void addrconf_dad_work(struct work_struct *w) ifp->dad_nonce); out: in6_ifa_put(ifp); - rtnl_unlock(); + rtnl_net_unlock(net); } /* ifp->idev must be at least read locked */ @@ -4752,9 +4727,9 @@ static void addrconf_verify_work(struct work_struct *w) struct net *net = container_of(to_delayed_work(w), struct net, ipv6.addr_chk_work); - rtnl_lock(); + rtnl_net_lock(net); addrconf_verify_rtnl(net); - rtnl_unlock(); + rtnl_net_unlock(net); } static void addrconf_verify(struct net *net) @@ -4817,8 +4792,12 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, /* We ignore other flags so far. */ ifa_flags &= IFA_F_MANAGETEMPADDR; - return inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx, - ifm->ifa_prefixlen, extack); + rtnl_net_lock(net); + err = inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx, + ifm->ifa_prefixlen, extack); + rtnl_net_unlock(net); + + return err; } static int modify_prefix_route(struct net *net, struct inet6_ifaddr *ifp, @@ -4867,19 +4846,14 @@ static int modify_prefix_route(struct net *net, struct inet6_ifaddr *ifp, } static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, - struct ifa6_config *cfg) + struct ifa6_config *cfg, clock_t expires, + u32 flags) { - u32 flags; - clock_t expires; - unsigned long timeout; bool was_managetempaddr; - bool had_prefixroute; bool new_peer = false; + bool had_prefixroute; - ASSERT_RTNL(); - - if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) - return -EINVAL; + ASSERT_RTNL_NET(net); if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && (ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64)) @@ -4888,24 +4862,6 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, if (!(ifp->flags & IFA_F_TENTATIVE) || ifp->flags & IFA_F_DADFAILED) cfg->ifa_flags &= ~IFA_F_OPTIMISTIC; - timeout = addrconf_timeout_fixup(cfg->valid_lft, HZ); - if (addrconf_finite_timeout(timeout)) { - expires = jiffies_to_clock_t(timeout * HZ); - cfg->valid_lft = timeout; - flags = RTF_EXPIRES; - } else { - expires = 0; - flags = 0; - cfg->ifa_flags |= IFA_F_PERMANENT; - } - - timeout = addrconf_timeout_fixup(cfg->preferred_lft, HZ); - if (addrconf_finite_timeout(timeout)) { - if (timeout == 0) - cfg->ifa_flags |= IFA_F_DEPRECATED; - cfg->preferred_lft = timeout; - } - if (cfg->peer_pfx && memcmp(&ifp->peer_addr, cfg->peer_pfx, sizeof(struct in6_addr))) { if (!ipv6_addr_any(&ifp->peer_addr)) @@ -4990,13 +4946,16 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); - struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *peer_pfx; struct inet6_ifaddr *ifa; struct net_device *dev; struct inet6_dev *idev; struct ifa6_config cfg; + struct ifaddrmsg *ifm; + unsigned long timeout; + clock_t expires; + u32 flags; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, @@ -5019,23 +4978,6 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[IFA_PROTO]) cfg.ifa_proto = nla_get_u8(tb[IFA_PROTO]); - cfg.valid_lft = INFINITY_LIFE_TIME; - cfg.preferred_lft = INFINITY_LIFE_TIME; - - if (tb[IFA_CACHEINFO]) { - struct ifa_cacheinfo *ci; - - ci = nla_data(tb[IFA_CACHEINFO]); - cfg.valid_lft = ci->ifa_valid; - cfg.preferred_lft = ci->ifa_prefered; - } - - dev = __dev_get_by_index(net, ifm->ifa_index); - if (!dev) { - NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface"); - return -ENODEV; - } - cfg.ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); /* We ignore other flags so far. */ @@ -5043,9 +4985,55 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; + cfg.ifa_flags |= IFA_F_PERMANENT; + cfg.valid_lft = INFINITY_LIFE_TIME; + cfg.preferred_lft = INFINITY_LIFE_TIME; + expires = 0; + flags = 0; + + if (tb[IFA_CACHEINFO]) { + struct ifa_cacheinfo *ci; + + ci = nla_data(tb[IFA_CACHEINFO]); + cfg.valid_lft = ci->ifa_valid; + cfg.preferred_lft = ci->ifa_prefered; + + if (!cfg.valid_lft || cfg.preferred_lft > cfg.valid_lft) { + NL_SET_ERR_MSG_MOD(extack, "address lifetime invalid"); + return -EINVAL; + } + + timeout = addrconf_timeout_fixup(cfg.valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + cfg.ifa_flags &= ~IFA_F_PERMANENT; + cfg.valid_lft = timeout; + expires = jiffies_to_clock_t(timeout * HZ); + flags = RTF_EXPIRES; + } + + timeout = addrconf_timeout_fixup(cfg.preferred_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + cfg.ifa_flags |= IFA_F_DEPRECATED; + + cfg.preferred_lft = timeout; + } + } + + rtnl_net_lock(net); + + dev = __dev_get_by_index(net, ifm->ifa_index); + if (!dev) { + NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface"); + err = -ENODEV; + goto unlock; + } + idev = ipv6_find_idev(dev); - if (IS_ERR(idev)) - return PTR_ERR(idev); + if (IS_ERR(idev)) { + err = PTR_ERR(idev); + goto unlock; + } if (!ipv6_allow_optimistic_dad(net, idev)) cfg.ifa_flags &= ~IFA_F_OPTIMISTIC; @@ -5053,7 +5041,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, if (cfg.ifa_flags & IFA_F_NODAD && cfg.ifa_flags & IFA_F_OPTIMISTIC) { NL_SET_ERR_MSG(extack, "IFA_F_NODAD and IFA_F_OPTIMISTIC are mutually exclusive"); - return -EINVAL; + err = -EINVAL; + goto unlock; } ifa = ipv6_get_ifaddr(net, cfg.pfx, dev, 1); @@ -5062,7 +5051,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, * It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. */ - return inet6_addr_add(net, ifm->ifa_index, &cfg, extack); + err = inet6_addr_add(net, dev, &cfg, expires, flags, extack); + goto unlock; } if (nlh->nlmsg_flags & NLM_F_EXCL || @@ -5070,10 +5060,12 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, NL_SET_ERR_MSG_MOD(extack, "address already assigned"); err = -EEXIST; } else { - err = inet6_addr_modify(net, ifa, &cfg); + err = inet6_addr_modify(net, ifa, &cfg, expires, flags); } in6_ifa_put(ifa); +unlock: + rtnl_net_unlock(net); return err; } @@ -5127,22 +5119,6 @@ static inline int inet6_ifaddr_msgsize(void) + nla_total_size(4) /* IFA_RT_PRIORITY */; } -enum addr_type_t { - UNICAST_ADDR, - MULTICAST_ADDR, - ANYCAST_ADDR, -}; - -struct inet6_fill_args { - u32 portid; - u32 seq; - int event; - unsigned int flags; - int netnsid; - int ifindex; - enum addr_type_t type; -}; - static int inet6_fill_ifaddr(struct sk_buff *skb, const struct inet6_ifaddr *ifa, struct inet6_fill_args *args) @@ -5221,15 +5197,16 @@ error: return -EMSGSIZE; } -static int inet6_fill_ifmcaddr(struct sk_buff *skb, - const struct ifmcaddr6 *ifmca, - struct inet6_fill_args *args) +int inet6_fill_ifmcaddr(struct sk_buff *skb, + const struct ifmcaddr6 *ifmca, + struct inet6_fill_args *args) { int ifindex = ifmca->idev->dev->ifindex; u8 scope = RT_SCOPE_UNIVERSE; struct nlmsghdr *nlh; - if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) + if (!args->force_rt_scope_universe && + ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, @@ -5255,9 +5232,9 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, return 0; } -static int inet6_fill_ifacaddr(struct sk_buff *skb, - const struct ifacaddr6 *ifaca, - struct inet6_fill_args *args) +int inet6_fill_ifacaddr(struct sk_buff *skb, + const struct ifacaddr6 *ifaca, + struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; @@ -5418,6 +5395,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, .flags = NLM_F_MULTI, .netnsid = -1, .type = type, + .force_rt_scope_universe = false, }; struct { unsigned long ifindex; @@ -5546,6 +5524,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, .event = RTM_NEWADDR, .flags = 0, .netnsid = -1, + .force_rt_scope_universe = false, }; struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; @@ -5617,6 +5596,7 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) .event = event, .flags = 0, .netnsid = -1, + .force_rt_scope_universe = false, }; int err = -ENOBUFS; @@ -6382,7 +6362,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf) struct inet6_dev *idev; for_each_netdev(net, dev) { - idev = __in6_dev_get(dev); + idev = __in6_dev_get_rtnl_net(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); @@ -6403,7 +6383,7 @@ static int addrconf_disable_ipv6(const struct ctl_table *table, int *p, int newf return 0; } - if (!rtnl_trylock()) + if (!rtnl_net_trylock(net)) return restart_syscall(); old = *p; @@ -6412,10 +6392,11 @@ static int addrconf_disable_ipv6(const struct ctl_table *table, int *p, int newf if (p == &net->ipv6.devconf_all->disable_ipv6) { WRITE_ONCE(net->ipv6.devconf_dflt->disable_ipv6, newf); addrconf_disable_change(net, newf); - } else if ((!newf) ^ (!old)) + } else if ((!newf) ^ (!old)) { dev_disable_change((struct inet6_dev *)table->extra1); + } - rtnl_unlock(); + rtnl_net_unlock(net); return 0; } @@ -6458,20 +6439,20 @@ static int addrconf_sysctl_proxy_ndp(const struct ctl_table *ctl, int write, if (write && old != new) { struct net *net = ctl->extra2; - if (!rtnl_trylock()) + if (!rtnl_net_trylock(net)) return restart_syscall(); - if (valp == &net->ipv6.devconf_dflt->proxy_ndp) + if (valp == &net->ipv6.devconf_dflt->proxy_ndp) { inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); - else if (valp == &net->ipv6.devconf_all->proxy_ndp) + } else if (valp == &net->ipv6.devconf_all->proxy_ndp) { inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); - else { + } else { struct inet6_dev *idev = ctl->extra1; inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, @@ -6479,7 +6460,7 @@ static int addrconf_sysctl_proxy_ndp(const struct ctl_table *ctl, int write, idev->dev->ifindex, &idev->cnf); } - rtnl_unlock(); + rtnl_net_unlock(net); } return ret; @@ -6499,7 +6480,7 @@ static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write, .mode = ctl->mode, }; - if (!rtnl_trylock()) + if (!rtnl_net_trylock(net)) return restart_syscall(); new_val = *((u32 *)ctl->data); @@ -6529,7 +6510,7 @@ static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write, WRITE_ONCE(net->ipv6.devconf_dflt->addr_gen_mode, new_val); for_each_netdev(net, dev) { - idev = __in6_dev_get(dev); + idev = __in6_dev_get_rtnl_net(dev); if (idev && idev->cnf.addr_gen_mode != new_val) { WRITE_ONCE(idev->cnf.addr_gen_mode, @@ -6543,7 +6524,7 @@ static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write, } out: - rtnl_unlock(); + rtnl_net_unlock(net); return ret; } @@ -6565,7 +6546,7 @@ static int addrconf_sysctl_stable_secret(const struct ctl_table *ctl, int write, lctl.maxlen = IPV6_MAX_STRLEN; lctl.data = str; - if (!rtnl_trylock()) + if (!rtnl_net_trylock(net)) return restart_syscall(); if (!write && !secret->initialized) { @@ -6595,7 +6576,7 @@ static int addrconf_sysctl_stable_secret(const struct ctl_table *ctl, int write, struct net_device *dev; for_each_netdev(net, dev) { - struct inet6_dev *idev = __in6_dev_get(dev); + struct inet6_dev *idev = __in6_dev_get_rtnl_net(dev); if (idev) { WRITE_ONCE(idev->cnf.addr_gen_mode, @@ -6610,7 +6591,7 @@ static int addrconf_sysctl_stable_secret(const struct ctl_table *ctl, int write, } out: - rtnl_unlock(); + rtnl_net_unlock(net); return err; } @@ -6694,7 +6675,7 @@ int addrconf_disable_policy(const struct ctl_table *ctl, int *valp, int val) return 0; } - if (!rtnl_trylock()) + if (!rtnl_net_trylock(net)) return restart_syscall(); WRITE_ONCE(*valp, val); @@ -6703,7 +6684,7 @@ int addrconf_disable_policy(const struct ctl_table *ctl, int *valp, int val) struct net_device *dev; for_each_netdev(net, dev) { - idev = __in6_dev_get(dev); + idev = __in6_dev_get_rtnl_net(dev); if (idev) addrconf_disable_policy_idev(idev, val); } @@ -6712,7 +6693,7 @@ int addrconf_disable_policy(const struct ctl_table *ctl, int *valp, int val) addrconf_disable_policy_idev(idev, val); } - rtnl_unlock(); + rtnl_net_unlock(net); return 0; } @@ -7425,9 +7406,9 @@ static const struct rtnl_msg_handler addrconf_rtnl_msg_handlers[] __initconst_or {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETLINK, .dumpit = inet6_dump_ifinfo, .flags = RTNL_FLAG_DUMP_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWADDR, - .doit = inet6_rtm_newaddr}, + .doit = inet6_rtm_newaddr, .flags = RTNL_FLAG_DOIT_PERNET}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELADDR, - .doit = inet6_rtm_deladdr}, + .doit = inet6_rtm_deladdr, .flags = RTNL_FLAG_DOIT_PERNET}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETADDR, .doit = inet6_rtm_getaddr, .dumpit = inet6_dump_ifaddr, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, @@ -7469,9 +7450,9 @@ int __init addrconf_init(void) goto out_nowq; } - rtnl_lock(); + rtnl_net_lock(&init_net); idev = ipv6_add_dev(blackhole_netdev); - rtnl_unlock(); + rtnl_net_unlock(&init_net); if (IS_ERR(idev)) { err = PTR_ERR(idev); goto errlo; @@ -7521,17 +7502,17 @@ void addrconf_cleanup(void) rtnl_af_unregister(&inet6_ops); - rtnl_lock(); + rtnl_net_lock(&init_net); /* clean dev list */ for_each_netdev(&init_net, dev) { - if (__in6_dev_get(dev) == NULL) + if (!__in6_dev_get_rtnl_net(dev)) continue; addrconf_ifdown(dev, true); } addrconf_ifdown(init_net.loopback_dev, true); - rtnl_unlock(); + rtnl_net_unlock(&init_net); destroy_workqueue(addrconf_wq); } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 562cace50ca9..21e01695b48c 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -278,6 +278,37 @@ static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, return aca; } +static void inet6_ifacaddr_notify(struct net_device *dev, + const struct ifacaddr6 *ifaca, int event) +{ + struct inet6_fill_args fillargs = { + .event = event, + .netnsid = -1, + }; + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOMEM; + + skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(sizeof(struct in6_addr)) + + nla_total_size(sizeof(struct ifa_cacheinfo)), + GFP_KERNEL); + if (!skb) + goto error; + + err = inet6_fill_ifacaddr(skb, ifaca, &fillargs); + if (err < 0) { + pr_err("Failed to fill in anycast addresses (err %d)\n", err); + nlmsg_free(skb); + goto error; + } + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ACADDR, NULL, GFP_KERNEL); + return; +error: + rtnl_set_sk_err(net, RTNLGRP_IPV6_ACADDR, err); +} + /* * device anycast group inc (add if not found) */ @@ -333,6 +364,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) addrconf_join_solict(idev->dev, &aca->aca_addr); + inet6_ifacaddr_notify(idev->dev, aca, RTM_NEWANYCAST); + aca_put(aca); return 0; out: @@ -375,6 +408,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) ip6_del_rt(dev_net(idev->dev), aca->aca_rt, false); + inet6_ifacaddr_notify(idev->dev, aca, RTM_DELANYCAST); + aca_put(aca); return 0; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index b2400c226a32..9e73944e3b53 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -315,7 +315,7 @@ static void esp_output_done(void *data, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb->sk, skb, err); + xfrm_output_resume(skb_to_full_sk(skb), skb, err); } } @@ -859,7 +859,8 @@ int esp6_input_done2(struct sk_buff *skb, int err) skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); skb_pull_rcsum(skb, hlen); - if (x->props.mode == XFRM_MODE_TUNNEL) + if (x->props.mode == XFRM_MODE_TUNNEL || + x->props.mode == XFRM_MODE_IPTFS) skb_reset_transport_header(skb); else skb_set_transport_header(skb, -hdr_len); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index c85c1627cb16..67d39114d9a6 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -26,6 +26,8 @@ struct fib6_rule { struct fib_rule common; struct rt6key src; struct rt6key dst; + __be32 flowlabel; + __be32 flowlabel_mask; dscp_t dscp; u8 dscp_full:1; /* DSCP or TOS selector */ }; @@ -34,7 +36,7 @@ static bool fib6_rule_matchall(const struct fib_rule *rule) { struct fib6_rule *r = container_of(rule, struct fib6_rule, common); - if (r->dst.plen || r->src.plen || r->dscp) + if (r->dst.plen || r->src.plen || r->dscp || r->flowlabel_mask) return false; return fib_rule_matchall(rule); } @@ -332,6 +334,9 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, if (r->dscp && r->dscp != ip6_dscp(fl6->flowlabel)) return 0; + if ((r->flowlabel ^ flowi6_get_flowlabel(fl6)) & r->flowlabel_mask) + return 0; + if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto)) return 0; @@ -360,6 +365,35 @@ static int fib6_nl2rule_dscp(const struct nlattr *nla, struct fib6_rule *rule6, return 0; } +static int fib6_nl2rule_flowlabel(struct nlattr **tb, struct fib6_rule *rule6, + struct netlink_ext_ack *extack) +{ + __be32 flowlabel, flowlabel_mask; + + if (NL_REQ_ATTR_CHECK(extack, NULL, tb, FRA_FLOWLABEL) || + NL_REQ_ATTR_CHECK(extack, NULL, tb, FRA_FLOWLABEL_MASK)) + return -EINVAL; + + flowlabel = nla_get_be32(tb[FRA_FLOWLABEL]); + flowlabel_mask = nla_get_be32(tb[FRA_FLOWLABEL_MASK]); + + if (flowlabel_mask & ~IPV6_FLOWLABEL_MASK) { + NL_SET_ERR_MSG_ATTR(extack, tb[FRA_FLOWLABEL_MASK], + "Invalid flow label mask"); + return -EINVAL; + } + + if (flowlabel & ~flowlabel_mask) { + NL_SET_ERR_MSG(extack, "Flow label and mask do not match"); + return -EINVAL; + } + + rule6->flowlabel = flowlabel; + rule6->flowlabel_mask = flowlabel_mask; + + return 0; +} + static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, @@ -379,6 +413,10 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, if (tb[FRA_DSCP] && fib6_nl2rule_dscp(tb[FRA_DSCP], rule6, extack) < 0) goto errout; + if ((tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) && + fib6_nl2rule_flowlabel(tb, rule6, extack) < 0) + goto errout; + if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) { if (rule->table == RT6_TABLE_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid table"); @@ -444,6 +482,14 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, return 0; } + if (tb[FRA_FLOWLABEL] && + nla_get_be32(tb[FRA_FLOWLABEL]) != rule6->flowlabel) + return 0; + + if (tb[FRA_FLOWLABEL_MASK] && + nla_get_be32(tb[FRA_FLOWLABEL_MASK]) != rule6->flowlabel_mask) + return 0; + if (frh->src_len && nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr))) return 0; @@ -472,6 +518,11 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->tos = inet_dscp_to_dsfield(rule6->dscp); } + if (rule6->flowlabel_mask && + (nla_put_be32(skb, FRA_FLOWLABEL, rule6->flowlabel) || + nla_put_be32(skb, FRA_FLOWLABEL_MASK, rule6->flowlabel_mask))) + goto nla_put_failure; + if ((rule6->dst.plen && nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) || (rule6->src.plen && @@ -487,7 +538,9 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(16) /* dst */ + nla_total_size(16) /* src */ - + nla_total_size(1); /* dscp */ + + nla_total_size(1) /* dscp */ + + nla_total_size(4) /* flowlabel */ + + nla_total_size(4); /* flowlabel mask */ } static void fib6_rule_flush_cache(struct fib_rules_ops *ops) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 071b0bc1179d..a6984a29fdb9 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -222,10 +222,10 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); - peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr, 1); + rcu_read_lock(); + peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr); res = inet_peer_xrlim_allow(peer, tmo); - if (peer) - inet_putpeer(peer); + rcu_read_unlock(); } if (!res) __ICMP6_INC_STATS(net, ip6_dst_idev(dst), diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 7646e401c630..1d41b2ab4884 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -195,6 +195,8 @@ static const struct nf_hook_ops ila_nf_hook_ops[] = { }, }; +static DEFINE_MUTEX(ila_mutex); + static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) { struct ila_net *ilan = net_generic(net, ila_net_id); @@ -202,16 +204,20 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match); int err = 0, order; - if (!ilan->xlat.hooks_registered) { + if (!READ_ONCE(ilan->xlat.hooks_registered)) { /* We defer registering net hooks in the namespace until the * first mapping is added. */ - err = nf_register_net_hooks(net, ila_nf_hook_ops, - ARRAY_SIZE(ila_nf_hook_ops)); + mutex_lock(&ila_mutex); + if (!ilan->xlat.hooks_registered) { + err = nf_register_net_hooks(net, ila_nf_hook_ops, + ARRAY_SIZE(ila_nf_hook_ops)); + if (!err) + WRITE_ONCE(ilan->xlat.hooks_registered, true); + } + mutex_unlock(&ila_mutex); if (err) return err; - - ilan->xlat.hooks_registered = true; } ila = kzalloc(sizeof(*ila), GFP_KERNEL); diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index 9d8422e350f8..28e5a89dc255 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -253,14 +253,15 @@ static int ioam6_do_fill(struct net *net, struct sk_buff *skb) } static int ioam6_do_inline(struct net *net, struct sk_buff *skb, - struct ioam6_lwt_encap *tuninfo) + struct ioam6_lwt_encap *tuninfo, + struct dst_entry *cache_dst) { struct ipv6hdr *oldhdr, *hdr; int hdrlen, err; hdrlen = (tuninfo->eh.hdrlen + 1) << 3; - err = skb_cow_head(skb, hdrlen + skb->mac_len); + err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb)); if (unlikely(err)) return err; @@ -291,7 +292,8 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo, bool has_tunsrc, struct in6_addr *tunsrc, - struct in6_addr *tundst) + struct in6_addr *tundst, + struct dst_entry *cache_dst) { struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr, *inner_hdr; @@ -300,7 +302,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb, hdrlen = (tuninfo->eh.hdrlen + 1) << 3; len = sizeof(*hdr) + hdrlen; - err = skb_cow_head(skb, len + skb->mac_len); + err = skb_cow_head(skb, len + dst_dev_overhead(cache_dst, skb)); if (unlikely(err)) return err; @@ -334,7 +336,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb, static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); + struct dst_entry *dst = skb_dst(skb), *cache_dst; struct in6_addr orig_daddr; struct ioam6_lwt *ilwt; int err = -EINVAL; @@ -352,6 +354,10 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) orig_daddr = ipv6_hdr(skb)->daddr; + local_bh_disable(); + cache_dst = dst_cache_get(&ilwt->cache); + local_bh_enable(); + switch (ilwt->mode) { case IOAM6_IPTUNNEL_MODE_INLINE: do_inline: @@ -359,7 +365,7 @@ do_inline: if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP) goto out; - err = ioam6_do_inline(net, skb, &ilwt->tuninfo); + err = ioam6_do_inline(net, skb, &ilwt->tuninfo, cache_dst); if (unlikely(err)) goto drop; @@ -369,7 +375,7 @@ do_encap: /* Encapsulation (ip6ip6) */ err = ioam6_do_encap(net, skb, &ilwt->tuninfo, ilwt->has_tunsrc, &ilwt->tunsrc, - &ilwt->tundst); + &ilwt->tundst, cache_dst); if (unlikely(err)) goto drop; @@ -387,41 +393,36 @@ do_encap: goto drop; } - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); - if (unlikely(err)) - goto drop; + if (unlikely(!cache_dst)) { + struct ipv6hdr *hdr = ipv6_hdr(skb); + struct flowi6 fl6; - if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) { - local_bh_disable(); - dst = dst_cache_get(&ilwt->cache); - local_bh_enable(); + memset(&fl6, 0, sizeof(fl6)); + fl6.daddr = hdr->daddr; + fl6.saddr = hdr->saddr; + fl6.flowlabel = ip6_flowinfo(hdr); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = hdr->nexthdr; - if (unlikely(!dst)) { - struct ipv6hdr *hdr = ipv6_hdr(skb); - struct flowi6 fl6; - - memset(&fl6, 0, sizeof(fl6)); - fl6.daddr = hdr->daddr; - fl6.saddr = hdr->saddr; - fl6.flowlabel = ip6_flowinfo(hdr); - fl6.flowi6_mark = skb->mark; - fl6.flowi6_proto = hdr->nexthdr; - - dst = ip6_route_output(net, NULL, &fl6); - if (dst->error) { - err = dst->error; - dst_release(dst); - goto drop; - } - - local_bh_disable(); - dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr); - local_bh_enable(); + cache_dst = ip6_route_output(net, NULL, &fl6); + if (cache_dst->error) { + err = cache_dst->error; + dst_release(cache_dst); + goto drop; } - skb_dst_drop(skb); - skb_dst_set(skb, dst); + local_bh_disable(); + dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr); + local_bh_enable(); + err = skb_cow_head(skb, LL_RESERVED_SPACE(cache_dst->dev)); + if (unlikely(err)) + goto drop; + } + + if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) { + skb_dst_drop(skb); + skb_dst_set(skb, cache_dst); return dst_output(net, sk, skb); } out: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index f7b4608bb316..d577bf2f3053 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -613,15 +613,15 @@ int ip6_forward(struct sk_buff *skb) else target = &hdr->daddr; - peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1); + rcu_read_lock(); + peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ if (inet_peer_xrlim_allow(peer, 1*HZ)) ndisc_send_redirect(skb, target); - if (peer) - inet_putpeer(peer); + rcu_read_unlock(); } else { int addrtype = ipv6_addr_type(&hdr->saddr); @@ -1401,6 +1401,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; cork->base.mark = ipc6->sockc.mark; + cork->base.priority = ipc6->sockc.priority; sock_tx_timestamp(sk, &ipc6->sockc, &cork->base.tx_flags); if (ipc6->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) { cork->base.flags |= IPCORK_TS_OPT_ID; @@ -1697,8 +1698,9 @@ alloc_new_skb: pskb_trim_unique(skb_prev, maxfraglen); } if (copy > 0 && - getfrag(from, data + transhdrlen, offset, - copy, fraggap, skb) < 0) { + INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, data + transhdrlen, offset, + copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; @@ -1742,8 +1744,9 @@ alloc_new_skb: unsigned int off; off = skb->len; - if (getfrag(from, skb_put(skb, copy), - offset, copy, off, skb) < 0) { + if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, skb_put(skb, copy), + offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; @@ -1781,7 +1784,8 @@ alloc_new_skb: get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); - if (getfrag(from, + if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; @@ -1939,7 +1943,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, hdr->saddr = fl6->saddr; hdr->daddr = *final_dst; - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = cork->base.priority; skb->mark = cork->base.mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 578ff1336afe..535e9f72514c 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -520,9 +520,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", - mfc->_c.mfc_un.res.pkt, - mfc->_c.mfc_un.res.bytes, - mfc->_c.mfc_un.res.wrong_if); + atomic_long_read(&mfc->_c.mfc_un.res.pkt), + atomic_long_read(&mfc->_c.mfc_un.res.bytes), + atomic_long_read(&mfc->_c.mfc_un.res.wrong_if)); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && @@ -884,7 +884,7 @@ static void ip6mr_update_thresholds(struct mr_table *mrt, cache->mfc_un.res.maxvif = vifi + 1; } } - cache->mfc_un.res.lastuse = jiffies; + WRITE_ONCE(cache->mfc_un.res.lastuse, jiffies); } static int mif6_add(struct net *net, struct mr_table *mrt, @@ -1945,9 +1945,9 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void *arg) c = ip6mr_cache_find(mrt, &sr->src.sin6_addr, &sr->grp.sin6_addr); if (c) { - sr->pktcnt = c->_c.mfc_un.res.pkt; - sr->bytecnt = c->_c.mfc_un.res.bytes; - sr->wrong_if = c->_c.mfc_un.res.wrong_if; + sr->pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr->bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr->wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); return 0; } @@ -2017,9 +2017,9 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { - sr.pktcnt = c->_c.mfc_un.res.pkt; - sr.bytecnt = c->_c.mfc_un.res.bytes; - sr.wrong_if = c->_c.mfc_un.res.wrong_if; + sr.pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr.bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr.wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) @@ -2142,9 +2142,9 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, int true_vifi = ip6mr_find_vif(mrt, dev); vif = c->_c.mfc_parent; - c->_c.mfc_un.res.pkt++; - c->_c.mfc_un.res.bytes += skb->len; - c->_c.mfc_un.res.lastuse = jiffies; + atomic_long_inc(&c->_c.mfc_un.res.pkt); + atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); + WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); if (ipv6_addr_any(&c->mf6c_origin) && true_vifi >= 0) { struct mfc6_cache *cache_proxy; @@ -2162,7 +2162,7 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, * Wrong interface: drop packet and (maybe) send PIM assert. */ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) { - c->_c.mfc_un.res.wrong_if++; + atomic_long_inc(&c->_c.mfc_un.res.wrong_if); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index b244dbf61d5f..9dfdb40988b0 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -33,8 +33,10 @@ #include #include #include +#include #include #include +#include #include #include #include @@ -47,6 +49,7 @@ #include #include +#include #include #include @@ -901,6 +904,41 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, return mc; } +static void inet6_ifmcaddr_notify(struct net_device *dev, + const struct ifmcaddr6 *ifmca, int event) +{ + struct inet6_fill_args fillargs = { + .portid = 0, + .seq = 0, + .event = event, + .flags = 0, + .netnsid = -1, + .force_rt_scope_universe = true, + }; + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOMEM; + + skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(sizeof(struct in6_addr)) + + nla_total_size(sizeof(struct ifa_cacheinfo)), + GFP_KERNEL); + if (!skb) + goto error; + + err = inet6_fill_ifmcaddr(skb, ifmca, &fillargs); + if (err < 0) { + WARN_ON_ONCE(err == -EMSGSIZE); + nlmsg_free(skb); + goto error; + } + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MCADDR, NULL, GFP_KERNEL); + return; +error: + rtnl_set_sk_err(net, RTNLGRP_IPV6_MCADDR, err); +} + /* * device multicast group inc (add if not found) */ @@ -948,6 +986,7 @@ static int __ipv6_dev_mc_inc(struct net_device *dev, mld_del_delrec(idev, mc); igmp6_group_added(mc); + inet6_ifmcaddr_notify(dev, mc, RTM_NEWMULTICAST); mutex_unlock(&idev->mc_lock); ma_put(mc); return 0; @@ -977,6 +1016,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) *map = ma->next; igmp6_group_dropped(ma); + inet6_ifmcaddr_notify(idev->dev, ma, + RTM_DELMULTICAST); ip6_mc_clear_src(ma); mutex_unlock(&idev->mc_lock); @@ -1021,29 +1062,31 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, rcu_read_lock(); idev = __in6_dev_get(dev); - if (idev) { - for_each_mc_rcu(idev, mc) { - if (ipv6_addr_equal(&mc->mca_addr, group)) + if (!idev) + goto unlock; + for_each_mc_rcu(idev, mc) { + if (ipv6_addr_equal(&mc->mca_addr, group)) + break; + } + if (!mc) + goto unlock; + if (src_addr && !ipv6_addr_any(src_addr)) { + struct ip6_sf_list *psf; + + for_each_psf_rcu(mc, psf) { + if (ipv6_addr_equal(&psf->sf_addr, src_addr)) break; } - if (mc) { - if (src_addr && !ipv6_addr_any(src_addr)) { - struct ip6_sf_list *psf; - - for_each_psf_rcu(mc, psf) { - if (ipv6_addr_equal(&psf->sf_addr, src_addr)) - break; - } - if (psf) - rv = psf->sf_count[MCAST_INCLUDE] || - psf->sf_count[MCAST_EXCLUDE] != - mc->mca_sfcount[MCAST_EXCLUDE]; - else - rv = mc->mca_sfcount[MCAST_EXCLUDE] != 0; - } else - rv = true; /* don't filter unspecified source */ - } + if (psf) + rv = READ_ONCE(psf->sf_count[MCAST_INCLUDE]) || + READ_ONCE(psf->sf_count[MCAST_EXCLUDE]) != + READ_ONCE(mc->mca_sfcount[MCAST_EXCLUDE]); + else + rv = READ_ONCE(mc->mca_sfcount[MCAST_EXCLUDE]) != 0; + } else { + rv = true; /* don't filter unspecified source */ } +unlock: rcu_read_unlock(); return rv; } @@ -2285,7 +2328,7 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, /* source filter not found, or count wrong => bug */ return -ESRCH; } - psf->sf_count[sfmode]--; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] - 1); if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { struct inet6_dev *idev = pmc->idev; @@ -2391,7 +2434,7 @@ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, rcu_assign_pointer(pmc->mca_sources, psf); } } - psf->sf_count[sfmode]++; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] + 1); return 0; } @@ -2503,7 +2546,8 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, sf_markstate(pmc); isexclude = pmc->mca_sfmode == MCAST_EXCLUDE; if (!delta) - pmc->mca_sfcount[sfmode]++; + WRITE_ONCE(pmc->mca_sfcount[sfmode], + pmc->mca_sfcount[sfmode] + 1); err = 0; for (i = 0; i < sfcount; i++) { err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]); @@ -2514,7 +2558,8 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int j; if (!delta) - pmc->mca_sfcount[sfmode]--; + WRITE_ONCE(pmc->mca_sfcount[sfmode], + pmc->mca_sfcount[sfmode] - 1); for (j = 0; j < i; j++) ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { @@ -2559,7 +2604,8 @@ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) RCU_INIT_POINTER(pmc->mca_sources, NULL); pmc->mca_sfmode = MCAST_EXCLUDE; pmc->mca_sfcount[MCAST_INCLUDE] = 0; - pmc->mca_sfcount[MCAST_EXCLUDE] = 1; + /* Paired with the READ_ONCE() from ipv6_chk_mcast_addr() */ + WRITE_ONCE(pmc->mca_sfcount[MCAST_EXCLUDE], 1); } /* called with mc_lock */ @@ -3074,8 +3120,8 @@ static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) state->dev->ifindex, state->dev->name, &state->im->mca_addr, &psf->sf_addr, - psf->sf_count[MCAST_INCLUDE], - psf->sf_count[MCAST_EXCLUDE]); + READ_ONCE(psf->sf_count[MCAST_INCLUDE]), + READ_ONCE(psf->sf_count[MCAST_EXCLUDE])); } return 0; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index aba94a348673..d044c67019de 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1731,10 +1731,12 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) "Redirect: destination is not a neighbour\n"); goto release; } - peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1); + + rcu_read_lock(); + peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr); ret = inet_peer_xrlim_allow(peer, 1*HZ); - if (peer) - inet_putpeer(peer); + rcu_read_unlock(); + if (!ret) goto release; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 88b3fcacd4f9..46b8adf6e7f8 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -119,6 +119,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return -EINVAL; ipcm6_init_sk(&ipc6, sk); + ipc6.sockc.priority = READ_ONCE(sk->sk_priority); ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = READ_ONCE(sk->sk_mark); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8476a3944a88..a45aba090aa4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -619,7 +619,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); @@ -780,6 +780,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init(&ipc6); ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = fl6.flowi6_mark; + ipc6.sockc.priority = READ_ONCE(sk->sk_priority); if (sin6) { if (addr_len < SIN6_LEN_RFC2133) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 67ff16c04718..78362822b907 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5005,6 +5005,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, + [RTA_FLOWLABEL] = { .type = NLA_BE32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -5030,6 +5031,12 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } + if (tb[RTA_FLOWLABEL]) { + NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL], + "Flow label cannot be specified for this operation"); + goto errout; + } + *cfg = (struct fib6_config){ .fc_table = rtm->rtm_table, .fc_dst_len = rtm->rtm_dst_len, @@ -6013,6 +6020,13 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb, return -EINVAL; } + if (tb[RTA_FLOWLABEL] && + (nla_get_be32(tb[RTA_FLOWLABEL]) & ~IPV6_FLOWLABEL_MASK)) { + NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL], + "Invalid flow label"); + return -EINVAL; + } + for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; @@ -6027,6 +6041,7 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb, case RTA_SPORT: case RTA_DPORT: case RTA_IP_PROTO: + case RTA_FLOWLABEL: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); @@ -6049,6 +6064,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct sk_buff *skb; struct rtmsg *rtm; struct flowi6 fl6 = {}; + __be32 flowlabel; bool fibmatch; err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack); @@ -6057,7 +6073,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = -EINVAL; rtm = nlmsg_data(nlh); - fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0); fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH); if (tb[RTA_SRC]) { @@ -6103,6 +6118,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout; } + flowlabel = nla_get_be32_default(tb[RTA_FLOWLABEL], 0); + fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, flowlabel); + if (iif) { struct net_device *dev; int flags = 0; diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index db3c19a42e1c..7ba22d2f2bfe 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -125,7 +125,8 @@ static void rpl_destroy_state(struct lwtunnel_state *lwt) } static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, - const struct ipv6_rpl_sr_hdr *srh) + const struct ipv6_rpl_sr_hdr *srh, + struct dst_entry *cache_dst) { struct ipv6_rpl_sr_hdr *isrh, *csrh; const struct ipv6hdr *oldhdr; @@ -153,7 +154,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, hdrlen = ((csrh->hdrlen + 1) << 3); - err = skb_cow_head(skb, hdrlen + skb->mac_len); + err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb)); if (unlikely(err)) { kfree(buf); return err; @@ -186,7 +187,8 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, return 0; } -static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt) +static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt, + struct dst_entry *cache_dst) { struct dst_entry *dst = skb_dst(skb); struct rpl_iptunnel_encap *tinfo; @@ -196,7 +198,7 @@ static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt) tinfo = rpl_encap_lwtunnel(dst->lwtstate); - return rpl_do_srh_inline(skb, rlwt, tinfo->srh); + return rpl_do_srh_inline(skb, rlwt, tinfo->srh, cache_dst); } static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -208,14 +210,14 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb) rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate); - err = rpl_do_srh(skb, rlwt); - if (unlikely(err)) - goto drop; - local_bh_disable(); dst = dst_cache_get(&rlwt->cache); local_bh_enable(); + err = rpl_do_srh(skb, rlwt, dst); + if (unlikely(err)) + goto drop; + if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); struct flowi6 fl6; @@ -237,15 +239,15 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb) local_bh_disable(); dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr); local_bh_enable(); + + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + if (unlikely(err)) + goto drop; } skb_dst_drop(skb); skb_dst_set(skb, dst); - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); - if (unlikely(err)) - goto drop; - return dst_output(net, sk, skb); drop: @@ -262,29 +264,31 @@ static int rpl_input(struct sk_buff *skb) rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate); - err = rpl_do_srh(skb, rlwt); - if (unlikely(err)) - goto drop; - local_bh_disable(); dst = dst_cache_get(&rlwt->cache); + local_bh_enable(); + + err = rpl_do_srh(skb, rlwt, dst); + if (unlikely(err)) + goto drop; if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); if (!dst->error) { + local_bh_disable(); dst_cache_set_ip6(&rlwt->cache, dst, &ipv6_hdr(skb)->saddr); + local_bh_enable(); } + + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + if (unlikely(err)) + goto drop; } else { skb_dst_drop(skb); skb_dst_set(skb, dst); } - local_bh_enable(); - - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); - if (unlikely(err)) - goto drop; return dst_input(skb); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 098632adc9b5..4bf937bfc263 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -124,8 +124,8 @@ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb, return flowlabel; } -/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ -int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) +static int __seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, + int proto, struct dst_entry *cache_dst) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(dst->dev); @@ -137,7 +137,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) hdrlen = (osrh->hdrlen + 1) << 3; tot_len = hdrlen + sizeof(*hdr); - err = skb_cow_head(skb, tot_len + skb->mac_len); + err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb)); if (unlikely(err)) return err; @@ -197,11 +197,18 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) return 0; } + +/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ +int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) +{ + return __seg6_do_srh_encap(skb, osrh, proto, NULL); +} EXPORT_SYMBOL_GPL(seg6_do_srh_encap); /* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */ static int seg6_do_srh_encap_red(struct sk_buff *skb, - struct ipv6_sr_hdr *osrh, int proto) + struct ipv6_sr_hdr *osrh, int proto, + struct dst_entry *cache_dst) { __u8 first_seg = osrh->first_segment; struct dst_entry *dst = skb_dst(skb); @@ -230,7 +237,7 @@ static int seg6_do_srh_encap_red(struct sk_buff *skb, tot_len = red_hdrlen + sizeof(struct ipv6hdr); - err = skb_cow_head(skb, tot_len + skb->mac_len); + err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb)); if (unlikely(err)) return err; @@ -317,8 +324,8 @@ out: return 0; } -/* insert an SRH within an IPv6 packet, just after the IPv6 header */ -int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) +static int __seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, + struct dst_entry *cache_dst) { struct ipv6hdr *hdr, *oldhdr; struct ipv6_sr_hdr *isrh; @@ -326,7 +333,7 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) hdrlen = (osrh->hdrlen + 1) << 3; - err = skb_cow_head(skb, hdrlen + skb->mac_len); + err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb)); if (unlikely(err)) return err; @@ -369,9 +376,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) return 0; } -EXPORT_SYMBOL_GPL(seg6_do_srh_inline); -static int seg6_do_srh(struct sk_buff *skb) +static int seg6_do_srh(struct sk_buff *skb, struct dst_entry *cache_dst) { struct dst_entry *dst = skb_dst(skb); struct seg6_iptunnel_encap *tinfo; @@ -384,7 +390,7 @@ static int seg6_do_srh(struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IPV6)) return -EINVAL; - err = seg6_do_srh_inline(skb, tinfo->srh); + err = __seg6_do_srh_inline(skb, tinfo->srh, cache_dst); if (err) return err; break; @@ -402,9 +408,11 @@ static int seg6_do_srh(struct sk_buff *skb) return -EINVAL; if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP) - err = seg6_do_srh_encap(skb, tinfo->srh, proto); + err = __seg6_do_srh_encap(skb, tinfo->srh, + proto, cache_dst); else - err = seg6_do_srh_encap_red(skb, tinfo->srh, proto); + err = seg6_do_srh_encap_red(skb, tinfo->srh, + proto, cache_dst); if (err) return err; @@ -425,11 +433,13 @@ static int seg6_do_srh(struct sk_buff *skb) skb_push(skb, skb->mac_len); if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP) - err = seg6_do_srh_encap(skb, tinfo->srh, - IPPROTO_ETHERNET); + err = __seg6_do_srh_encap(skb, tinfo->srh, + IPPROTO_ETHERNET, + cache_dst); else err = seg6_do_srh_encap_red(skb, tinfo->srh, - IPPROTO_ETHERNET); + IPPROTO_ETHERNET, + cache_dst); if (err) return err; @@ -444,6 +454,13 @@ static int seg6_do_srh(struct sk_buff *skb) return 0; } +/* insert an SRH within an IPv6 packet, just after the IPv6 header */ +int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) +{ + return __seg6_do_srh_inline(skb, osrh, NULL); +} +EXPORT_SYMBOL_GPL(seg6_do_srh_inline); + static int seg6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -458,31 +475,33 @@ static int seg6_input_core(struct net *net, struct sock *sk, struct seg6_lwt *slwt; int err; - err = seg6_do_srh(skb); - if (unlikely(err)) - goto drop; - slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); local_bh_disable(); dst = dst_cache_get(&slwt->cache); + local_bh_enable(); + + err = seg6_do_srh(skb, dst); + if (unlikely(err)) + goto drop; if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); if (!dst->error) { + local_bh_disable(); dst_cache_set_ip6(&slwt->cache, dst, &ipv6_hdr(skb)->saddr); + local_bh_enable(); } + + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + if (unlikely(err)) + goto drop; } else { skb_dst_drop(skb); skb_dst_set(skb, dst); } - local_bh_enable(); - - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); - if (unlikely(err)) - goto drop; if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, @@ -528,16 +547,16 @@ static int seg6_output_core(struct net *net, struct sock *sk, struct seg6_lwt *slwt; int err; - err = seg6_do_srh(skb); - if (unlikely(err)) - goto drop; - slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); local_bh_disable(); dst = dst_cache_get(&slwt->cache); local_bh_enable(); + err = seg6_do_srh(skb, dst); + if (unlikely(err)) + goto drop; + if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); struct flowi6 fl6; @@ -559,15 +578,15 @@ static int seg6_output_core(struct net *net, struct sock *sk, local_bh_disable(); dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); local_bh_enable(); + + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + if (unlikely(err)) + goto drop; } skb_dst_drop(skb); skb_dst_set(skb, dst); - err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); - if (unlikely(err)) - goto drop; - if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d766fd798ecf..6671daa67f4f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -170,6 +170,49 @@ static int compute_score(struct sock *sk, const struct net *net, return score; } +/** + * udp6_lib_lookup1() - Simplified lookup using primary hash (destination port) + * @net: Network namespace + * @saddr: Source address, network order + * @sport: Source port, network order + * @daddr: Destination address, network order + * @hnum: Destination port, host order + * @dif: Destination interface index + * @sdif: Destination bridge port index, if relevant + * @udptable: Set of UDP hash tables + * + * Simplified lookup to be used as fallback if no sockets are found due to a + * potential race between (receive) address change, and lookup happening before + * the rehash operation. This function ignores SO_REUSEPORT groups while scoring + * result sockets, because if we have one, we don't need the fallback at all. + * + * Called under rcu_read_lock(). + * + * Return: socket with highest matching score if any, NULL if none + */ +static struct sock *udp6_lib_lookup1(const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, + unsigned int hnum, int dif, int sdif, + const struct udp_table *udptable) +{ + unsigned int slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot = &udptable->hash[slot]; + struct sock *sk, *result = NULL; + int score, badness = 0; + + sk_for_each_rcu(sk, &hslot->head) { + score = compute_score(sk, net, + saddr, sport, daddr, hnum, dif, sdif); + if (score > badness) { + result = sk; + badness = score; + } + } + + return result; +} + /* called with rcu_read_lock() */ static struct sock *udp6_lib_lookup2(const struct net *net, const struct in6_addr *saddr, __be16 sport, @@ -347,6 +390,13 @@ struct sock *__udp6_lib_lookup(const struct net *net, result = udp6_lib_lookup2(net, saddr, sport, &in6addr_any, hnum, dif, sdif, hslot2, skb); + if (!IS_ERR_OR_NULL(result)) + goto done; + + /* Cover address change/lookup/rehash race: see __udp4_lib_lookup() */ + result = udp6_lib_lookup1(net, saddr, sport, daddr, hnum, dif, sdif, + udptable); + done: if (IS_ERR(result)) return NULL; @@ -1448,6 +1498,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = READ_ONCE(sk->sk_mark); + ipc6.sockc.priority = READ_ONCE(sk->sk_priority); /* destination address check */ if (sin6) { diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 5f7b1fdbffe6..b3d5d1f266ee 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -82,14 +82,14 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) toobig = skb->len > mtu && !skb_is_gso(skb); - if (toobig && xfrm6_local_dontfrag(skb->sk)) { + if (toobig && xfrm6_local_dontfrag(sk)) { xfrm6_local_rxpmtu(skb, mtu); kfree_skb(skb); return -EMSGSIZE; } else if (toobig && xfrm6_noneed_fragment(skb)) { skb->ignore_df = 1; goto skip_frag; - } else if (!skb->ignore_df && toobig && skb->sk) { + } else if (!skb->ignore_df && toobig && sk) { xfrm_local_error(skb, mtu); kfree_skb(skb); return -EMSGSIZE; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index d692b902e120..e83691073496 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -73,9 +73,9 @@ static netdev_tx_t l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev int ret = l2tp_xmit_skb(session, skb); if (likely(ret == NET_XMIT_SUCCESS)) - dev_sw_netstats_tx_add(dev, 1, len); + dev_dstats_tx_add(dev, len); else - DEV_STATS_INC(dev, tx_dropped); + dev_dstats_tx_dropped(dev); return NETDEV_TX_OK; } @@ -84,7 +84,6 @@ static const struct net_device_ops l2tp_eth_netdev_ops = { .ndo_init = l2tp_eth_dev_init, .ndo_uninit = l2tp_eth_dev_uninit, .ndo_start_xmit = l2tp_eth_dev_xmit, - .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, }; @@ -100,7 +99,7 @@ static void l2tp_eth_dev_setup(struct net_device *dev) dev->lltx = true; dev->netdev_ops = &l2tp_eth_netdev_ops; dev->needs_free_netdev = true; - dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len) @@ -128,7 +127,7 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, goto error_rcu; if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) - dev_sw_netstats_rx_add(dev, data_len); + dev_dstats_rx_add(dev, data_len); else DEV_STATS_INC(dev, rx_errors); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 4bc24fddfd52..29795d2839e8 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -425,7 +425,6 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int rc; struct inet_sock *inet = inet_sk(sk); struct rtable *rt = NULL; - struct flowi4 *fl4; int connected = 0; __be32 daddr; @@ -455,7 +454,6 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (sk->sk_state != TCP_ESTABLISHED) goto out; - daddr = inet->inet_daddr; connected = 1; } @@ -482,29 +480,24 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto error; } - fl4 = &inet->cork.fl.u.ip4; if (connected) rt = dst_rtable(__sk_dst_check(sk, 0)); rcu_read_lock(); if (!rt) { - const struct ip_options_rcu *inet_opt; + struct flowi4 *fl4 = &inet->cork.fl.u.ip4; - inet_opt = rcu_dereference(inet->inet_opt); + inet_sk_init_flowi4(inet, fl4); - /* Use correct destination address if we have options. */ - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; + /* Overwrite ->daddr if msg->msg_name was provided */ + if (!connected) + fl4->daddr = daddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ - rt = ip_route_output_ports(sock_net(sk), fl4, sk, - daddr, inet->inet_saddr, - inet->inet_dport, inet->inet_sport, - sk->sk_protocol, ip_sock_rt_tos(sk), - sk->sk_bound_dev_if); + rt = ip_route_output_flow(sock_net(sk), fl4, sk); if (IS_ERR(rt)) goto no_route; if (connected) { diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index 51bccfb00a9c..61b0159b2fbe 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -124,8 +124,8 @@ static inline int llc_fixup_skb(struct sk_buff *skb) if (unlikely(!pskb_may_pull(skb, llc_len))) return 0; - skb->transport_header += llc_len; skb_pull(skb, llc_len); + skb_reset_transport_header(skb); if (skb->protocol == htons(ETH_P_802_2)) { __be16 pdulen; s32 data_size; diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c index 72e101135f8c..c8d88e2508fc 100644 --- a/net/llc/sysctl_net_llc.c +++ b/net/llc/sysctl_net_llc.c @@ -11,10 +11,6 @@ #include #include -#ifndef CONFIG_SYSCTL -#error This file should not be compiled without CONFIG_SYSCTL defined -#endif - static struct ctl_table llc2_timeout_table[] = { { .procname = "ack", diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index d3fc158ccaf6..9351c64608a9 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -503,6 +503,9 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, if (IS_ERR(link)) return PTR_ERR(link); + if (WARN_ON(pairwise && link_id >= 0)) + return -EINVAL; + if (pairwise && params->mode == NL80211_KEY_SET_TX) return ieee80211_set_tx(sdata, mac_addr, key_idx); @@ -525,10 +528,12 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, if (IS_ERR(key)) return PTR_ERR(key); - key->conf.link_id = link_id; - - if (pairwise) + if (pairwise) { key->conf.flags |= IEEE80211_KEY_FLAG_PAIRWISE; + key->conf.link_id = -1; + } else { + key->conf.link_id = link->link_id; + } if (params->mode == NL80211_KEY_NO_TX) key->conf.flags |= IEEE80211_KEY_FLAG_NO_AUTO_TX; @@ -1671,7 +1676,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, link_conf->ema_ap = false; link_conf->bssid_indicator = 0; - __sta_info_flush(sdata, true, link_id); + __sta_info_flush(sdata, true, link_id, NULL); ieee80211_remove_link_keys(link, &keys); if (!list_empty(&keys)) { @@ -3190,19 +3195,27 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, static int ieee80211_get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id, int *dbm) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + struct ieee80211_link_data *link_data; if (local->ops->get_txpower && (sdata->flags & IEEE80211_SDATA_IN_DRIVER)) - return drv_get_txpower(local, sdata, dbm); + return drv_get_txpower(local, sdata, link_id, dbm); - if (local->emulate_chanctx) + if (local->emulate_chanctx) { *dbm = local->hw.conf.power_level; - else - *dbm = sdata->vif.bss_conf.txpower; + } else { + link_data = wiphy_dereference(wiphy, sdata->link[link_id]); + + if (link_data) + *dbm = link_data->conf->txpower; + else + return -ENOLINK; + } /* INT_MIN indicates no power level was set yet */ if (*dbm == INT_MIN) @@ -5172,6 +5185,18 @@ ieee80211_set_ttlm(struct wiphy *wiphy, struct net_device *dev, return ieee80211_req_neg_ttlm(sdata, params); } +static int +ieee80211_assoc_ml_reconf(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_assoc_link *add_links, + u16 rem_links) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + lockdep_assert_wiphy(sdata->local->hw.wiphy); + + return ieee80211_mgd_assoc_ml_reconf(sdata, add_links, rem_links); +} + const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -5286,4 +5311,5 @@ const struct cfg80211_ops mac80211_config_ops = { .set_hw_timestamp = ieee80211_set_hw_timestamp, .set_ttlm = ieee80211_set_ttlm, .get_radio_mask = ieee80211_get_radio_mask, + .assoc_ml_reconf = ieee80211_assoc_ml_reconf, }; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index a442cb667520..dc28f2b0957a 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -247,6 +247,13 @@ static enum nl80211_chan_width ieee80211_get_sta_bw(struct sta_info *sta, if (!link_sta) return NL80211_CHAN_WIDTH_20_NOHT; + /* + * We assume that TX/RX might be asymmetric (so e.g. VHT operating + * mode notification changes what a STA wants to receive, but not + * necessarily what it will transmit to us), and therefore use the + * capabilities here. Calling it RX bandwidth capability is a bit + * wrong though, since capabilities are in fact symmetric. + */ width = ieee80211_sta_cap_rx_bw(link_sta); switch (width) { diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h index 35a8ba25fa57..5b81998cb0c9 100644 --- a/net/mac80211/debug.h +++ b/net/mac80211/debug.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions - * Copyright (C) 2022 - 2023 Intel Corporation + * Copyright (C) 2022 - 2024 Intel Corporation */ #ifndef __MAC80211_DEBUG_H #define __MAC80211_DEBUG_H @@ -152,6 +152,14 @@ do { \ else \ _sdata_err((link)->sdata, fmt, ##__VA_ARGS__); \ } while (0) +#define link_id_info(sdata, link_id, fmt, ...) \ + do { \ + if (ieee80211_vif_is_mld(&sdata->vif)) \ + _sdata_info(sdata, "[link %d] " fmt, link_id, \ + ##__VA_ARGS__); \ + else \ + _sdata_info(sdata, fmt, ##__VA_ARGS__); \ + } while (0) #define _link_id_dbg(print, sdata, link_id, fmt, ...) \ do { \ if (ieee80211_vif_is_mld(&(sdata)->vif)) \ diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index be2e486907f9..bf0a2902d93c 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -284,7 +284,8 @@ static ssize_t aql_txq_limit_write(struct file *file, q_limit_low_old = local->aql_txq_limit_low[ac]; q_limit_high_old = local->aql_txq_limit_high[ac]; - wiphy_lock(local->hw.wiphy); + guard(wiphy)(local->hw.wiphy); + local->aql_txq_limit_low[ac] = q_limit_low; local->aql_txq_limit_high[ac] = q_limit_high; @@ -296,7 +297,6 @@ static ssize_t aql_txq_limit_write(struct file *file, sta->airtime[ac].aql_limit_high = q_limit_high; } } - wiphy_unlock(local->hw.wiphy); return count; } diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index b3a64edea0f2..117f58af5ff9 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -402,25 +402,6 @@ void ieee80211_debugfs_key_update_default(struct ieee80211_sub_if_data *sdata) } } -void ieee80211_debugfs_key_add_mgmt_default(struct ieee80211_sub_if_data *sdata) -{ - char buf[50]; - struct ieee80211_key *key; - - if (!sdata->vif.debugfs_dir) - return; - - key = wiphy_dereference(sdata->local->hw.wiphy, - sdata->deflink.default_mgmt_key); - if (key) { - sprintf(buf, "../keys/%d", key->debugfs.cnt); - sdata->debugfs.default_mgmt_key = - debugfs_create_symlink("default_mgmt_key", - sdata->vif.debugfs_dir, buf); - } else - ieee80211_debugfs_key_remove_mgmt_default(sdata); -} - void ieee80211_debugfs_key_remove_mgmt_default(struct ieee80211_sub_if_data *sdata) { if (!sdata) @@ -430,27 +411,6 @@ void ieee80211_debugfs_key_remove_mgmt_default(struct ieee80211_sub_if_data *sda sdata->debugfs.default_mgmt_key = NULL; } -void -ieee80211_debugfs_key_add_beacon_default(struct ieee80211_sub_if_data *sdata) -{ - char buf[50]; - struct ieee80211_key *key; - - if (!sdata->vif.debugfs_dir) - return; - - key = wiphy_dereference(sdata->local->hw.wiphy, - sdata->deflink.default_beacon_key); - if (key) { - sprintf(buf, "../keys/%d", key->debugfs.cnt); - sdata->debugfs.default_beacon_key = - debugfs_create_symlink("default_beacon_key", - sdata->vif.debugfs_dir, buf); - } else { - ieee80211_debugfs_key_remove_beacon_default(sdata); - } -} - void ieee80211_debugfs_key_remove_beacon_default(struct ieee80211_sub_if_data *sdata) { @@ -460,10 +420,3 @@ ieee80211_debugfs_key_remove_beacon_default(struct ieee80211_sub_if_data *sdata) debugfs_remove(sdata->debugfs.default_beacon_key); sdata->debugfs.default_beacon_key = NULL; } - -void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, - struct sta_info *sta) -{ - debugfs_remove(key->debugfs.stalink); - key->debugfs.stalink = NULL; -} diff --git a/net/mac80211/debugfs_key.h b/net/mac80211/debugfs_key.h index af7cf495f8d1..e17a48d5c6cc 100644 --- a/net/mac80211/debugfs_key.h +++ b/net/mac80211/debugfs_key.h @@ -6,16 +6,10 @@ void ieee80211_debugfs_key_add(struct ieee80211_key *key); void ieee80211_debugfs_key_remove(struct ieee80211_key *key); void ieee80211_debugfs_key_update_default(struct ieee80211_sub_if_data *sdata); -void ieee80211_debugfs_key_add_mgmt_default( - struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_key_remove_mgmt_default( struct ieee80211_sub_if_data *sdata); -void ieee80211_debugfs_key_add_beacon_default( - struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_key_remove_beacon_default( struct ieee80211_sub_if_data *sdata); -void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, - struct sta_info *sta); #else static inline void ieee80211_debugfs_key_add(struct ieee80211_key *key) {} @@ -24,21 +18,12 @@ static inline void ieee80211_debugfs_key_remove(struct ieee80211_key *key) static inline void ieee80211_debugfs_key_update_default( struct ieee80211_sub_if_data *sdata) {} -static inline void ieee80211_debugfs_key_add_mgmt_default( - struct ieee80211_sub_if_data *sdata) -{} static inline void ieee80211_debugfs_key_remove_mgmt_default( struct ieee80211_sub_if_data *sdata) {} -static inline void ieee80211_debugfs_key_add_beacon_default( - struct ieee80211_sub_if_data *sdata) -{} static inline void ieee80211_debugfs_key_remove_beacon_default( struct ieee80211_sub_if_data *sdata) {} -static inline void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, - struct sta_info *sta) -{} #endif #endif /* __MAC80211_DEBUGFS_KEY_H */ diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index a9bc2fd59f55..54c479910d05 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -727,7 +727,7 @@ static ssize_t ieee80211_if_parse_active_links(struct ieee80211_sub_if_data *sda { u16 active_links; - if (kstrtou16(buf, 0, &active_links)) + if (kstrtou16(buf, 0, &active_links) || !active_links) return -EINVAL; return ieee80211_set_active_links(&sdata->vif, active_links) ?: buflen; @@ -1025,16 +1025,7 @@ void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata) void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata) { - struct dentry *dir; - char buf[10 + IFNAMSIZ]; - - dir = sdata->vif.debugfs_dir; - - if (IS_ERR_OR_NULL(dir)) - return; - - sprintf(buf, "netdev:%s", sdata->name); - debugfs_rename(dir->d_parent, dir, dir->d_parent, buf); + debugfs_change_name(sdata->vif.debugfs_dir, "netdev:%s", sdata->name); } void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index edd1e4d4ad9d..5acecc7bd4a9 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -724,6 +724,9 @@ static inline void drv_flush_sta(struct ieee80211_local *local, if (sdata && !check_sdata_in_driver(sdata)) return; + if (!sta->uploaded) + return; + trace_drv_flush_sta(local, sdata, &sta->sta); if (local->ops->flush_sta) local->ops->flush_sta(&local->hw, &sdata->vif, &sta->sta); @@ -1273,7 +1276,8 @@ static inline u32 drv_get_expected_throughput(struct ieee80211_local *local, } static inline int drv_get_txpower(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, int *dbm) + struct ieee80211_sub_if_data *sdata, + unsigned int link_id, int *dbm) { int ret; @@ -1283,8 +1287,8 @@ static inline int drv_get_txpower(struct ieee80211_local *local, if (!local->ops->get_txpower) return -EOPNOTSUPP; - ret = local->ops->get_txpower(&local->hw, &sdata->vif, dbm); - trace_drv_get_txpower(local, sdata, *dbm, ret); + ret = local->ops->get_txpower(&local->hw, &sdata->vif, link_id, dbm); + trace_drv_get_txpower(local, sdata, link_id, *dbm, ret); return ret; } diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c index 99f6174a9d69..42f7ee142ce3 100644 --- a/net/mac80211/ethtool.c +++ b/net/mac80211/ethtool.c @@ -19,16 +19,13 @@ static int ieee80211_set_ringparam(struct net_device *dev, struct netlink_ext_ack *extack) { struct ieee80211_local *local = wiphy_priv(dev->ieee80211_ptr->wiphy); - int ret; if (rp->rx_mini_pending != 0 || rp->rx_jumbo_pending != 0) return -EINVAL; - wiphy_lock(local->hw.wiphy); - ret = drv_set_ringparam(local, rp->tx_pending, rp->rx_pending); - wiphy_unlock(local->hw.wiphy); + guard(wiphy)(local->hw.wiphy); - return ret; + return drv_set_ringparam(local, rp->tx_pending, rp->rx_pending); } static void ieee80211_get_ringparam(struct net_device *dev, @@ -40,10 +37,10 @@ static void ieee80211_get_ringparam(struct net_device *dev, memset(rp, 0, sizeof(*rp)); - wiphy_lock(local->hw.wiphy); + guard(wiphy)(local->hw.wiphy); + drv_get_ringparam(local, &rp->tx_pending, &rp->tx_max_pending, &rp->rx_pending, &rp->rx_max_pending); - wiphy_unlock(local->hw.wiphy); } static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = { @@ -109,7 +106,7 @@ static void ieee80211_get_stats(struct net_device *dev, * network device. */ - wiphy_lock(local->hw.wiphy); + guard(wiphy)(local->hw.wiphy); if (sdata->vif.type == NL80211_IFTYPE_STATION) { sta = sta_info_get_bss(sdata, sdata->deflink.u.mgd.bssid); @@ -160,6 +157,10 @@ do_survey: chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf); if (chanctx_conf) channel = chanctx_conf->def.chan; + else if (local->open_count > 0 && + local->open_count == local->monitors && + sdata->vif.type == NL80211_IFTYPE_MONITOR) + channel = local->monitor_chanreq.oper.chan; else channel = NULL; rcu_read_unlock(); @@ -205,13 +206,10 @@ do_survey: else data[i++] = -1LL; - if (WARN_ON(i != STA_STATS_LEN)) { - wiphy_unlock(local->hw.wiphy); + if (WARN_ON(i != STA_STATS_LEN)) return; - } drv_get_et_stats(sdata, stats, &(data[STA_STATS_LEN])); - wiphy_unlock(local->hw.wiphy); } static void ieee80211_get_strings(struct net_device *dev, u32 sset, u8 *data) diff --git a/net/mac80211/he.c b/net/mac80211/he.c index ecbb042dd043..5792ef77e986 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -3,10 +3,11 @@ * HE handling * * Copyright(c) 2017 Intel Deutschland GmbH - * Copyright(c) 2019 - 2023 Intel Corporation + * Copyright(c) 2019 - 2024 Intel Corporation */ #include "ieee80211_i.h" +#include "rate.h" static void ieee80211_update_from_he_6ghz_capa(const struct ieee80211_he_6ghz_capa *he_6ghz_capa, @@ -248,3 +249,119 @@ ieee80211_he_spr_ie_to_bss_conf(struct ieee80211_vif *vif, he_obss_pd->enable = true; } } + +static void ieee80211_link_sta_rc_update_omi(struct ieee80211_link_data *link, + struct link_sta_info *link_sta) +{ + struct ieee80211_sub_if_data *sdata = link->sdata; + struct ieee80211_supported_band *sband; + enum ieee80211_sta_rx_bandwidth new_bw; + enum nl80211_band band; + + band = link->conf->chanreq.oper.chan->band; + sband = sdata->local->hw.wiphy->bands[band]; + + new_bw = ieee80211_sta_cur_vht_bw(link_sta); + if (link_sta->pub->bandwidth == new_bw) + return; + + link_sta->pub->bandwidth = new_bw; + rate_control_rate_update(sdata->local, sband, link_sta, + IEEE80211_RC_BW_CHANGED); +} + +bool ieee80211_prepare_rx_omi_bw(struct ieee80211_link_sta *pub_link_sta, + enum ieee80211_sta_rx_bandwidth bw) +{ + struct sta_info *sta = container_of(pub_link_sta->sta, + struct sta_info, sta); + struct ieee80211_local *local = sta->sdata->local; + struct link_sta_info *link_sta = + sdata_dereference(sta->link[pub_link_sta->link_id], sta->sdata); + struct ieee80211_link_data *link = + sdata_dereference(sta->sdata->link[pub_link_sta->link_id], + sta->sdata); + struct ieee80211_chanctx_conf *conf; + struct ieee80211_chanctx *chanctx; + bool ret; + + if (WARN_ON(!link || !link_sta || link_sta->pub != pub_link_sta)) + return false; + + conf = sdata_dereference(link->conf->chanctx_conf, sta->sdata); + if (WARN_ON(!conf)) + return false; + + trace_api_prepare_rx_omi_bw(local, sta->sdata, link_sta, bw); + + chanctx = container_of(conf, typeof(*chanctx), conf); + + if (link_sta->rx_omi_bw_staging == bw) { + ret = false; + goto trace; + } + + /* must call this API in pairs */ + if (WARN_ON(link_sta->rx_omi_bw_tx != link_sta->rx_omi_bw_staging || + link_sta->rx_omi_bw_rx != link_sta->rx_omi_bw_staging)) { + ret = false; + goto trace; + } + + if (bw < link_sta->rx_omi_bw_staging) { + link_sta->rx_omi_bw_tx = bw; + ieee80211_link_sta_rc_update_omi(link, link_sta); + } else { + link_sta->rx_omi_bw_rx = bw; + ieee80211_recalc_chanctx_min_def(local, chanctx, NULL, false); + } + + link_sta->rx_omi_bw_staging = bw; + ret = true; +trace: + trace_api_return_bool(local, ret); + return ret; +} +EXPORT_SYMBOL_GPL(ieee80211_prepare_rx_omi_bw); + +void ieee80211_finalize_rx_omi_bw(struct ieee80211_link_sta *pub_link_sta) +{ + struct sta_info *sta = container_of(pub_link_sta->sta, + struct sta_info, sta); + struct ieee80211_local *local = sta->sdata->local; + struct link_sta_info *link_sta = + sdata_dereference(sta->link[pub_link_sta->link_id], sta->sdata); + struct ieee80211_link_data *link = + sdata_dereference(sta->sdata->link[pub_link_sta->link_id], + sta->sdata); + struct ieee80211_chanctx_conf *conf; + struct ieee80211_chanctx *chanctx; + + if (WARN_ON(!link || !link_sta || link_sta->pub != pub_link_sta)) + return; + + conf = sdata_dereference(link->conf->chanctx_conf, sta->sdata); + if (WARN_ON(!conf)) + return; + + trace_api_finalize_rx_omi_bw(local, sta->sdata, link_sta); + + chanctx = container_of(conf, typeof(*chanctx), conf); + + if (link_sta->rx_omi_bw_tx != link_sta->rx_omi_bw_staging) { + /* rate control in finalize only when widening bandwidth */ + WARN_ON(link_sta->rx_omi_bw_tx > link_sta->rx_omi_bw_staging); + link_sta->rx_omi_bw_tx = link_sta->rx_omi_bw_staging; + ieee80211_link_sta_rc_update_omi(link, link_sta); + } + + if (link_sta->rx_omi_bw_rx != link_sta->rx_omi_bw_staging) { + /* channel context in finalize only when narrowing bandwidth */ + WARN_ON(link_sta->rx_omi_bw_rx < link_sta->rx_omi_bw_staging); + link_sta->rx_omi_bw_rx = link_sta->rx_omi_bw_staging; + ieee80211_recalc_chanctx_min_def(local, chanctx, NULL, false); + } + + trace_api_return_void(local); +} +EXPORT_SYMBOL_GPL(ieee80211_finalize_rx_omi_bw); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index a1b4178deccf..05a945df3259 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -245,6 +245,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, sdata->vif.cfg.ibss_creator = false; sdata->vif.bss_conf.enable_beacon = false; netif_carrier_off(sdata->dev); + synchronize_net(); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IBSS | BSS_CHANGED_BEACON_ENABLED); @@ -1826,8 +1827,8 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - ieee80211_ibss_disconnect(sdata); ifibss->ssid_len = 0; + ieee80211_ibss_disconnect(sdata); eth_zero_addr(ifibss->bssid); /* remove beacon */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 9f0db39b28ff..e7dc3f0cfc9a 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -404,6 +404,8 @@ struct ieee80211_mgd_auth_data { int tries; u16 algorithm, expected_transaction; + unsigned long userspace_selectors[BITS_TO_LONGS(128)]; + u8 key[WLAN_KEY_LEN_WEP104]; u8 key_len, key_idx; bool done, waiting; @@ -444,6 +446,8 @@ struct ieee80211_mgd_assoc_data { const u8 *supp_rates; u8 supp_rates_len; + unsigned long userspace_selectors[BITS_TO_LONGS(128)]; + unsigned long timeout; int tries; @@ -602,6 +606,15 @@ struct ieee80211_if_managed { /* dialog token enumerator for neg TTLM request */ u8 dialog_token_alloc; struct wiphy_delayed_work neg_ttlm_timeout_work; + + /* Locally initiated multi-link reconfiguration */ + struct { + struct ieee80211_mgd_assoc_data *add_links_data; + struct wiphy_delayed_work wk; + u16 removed_links; + u16 added_links; + u8 dialog_token; + } reconf; }; struct ieee80211_if_ibss { @@ -1204,7 +1217,7 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p) for (int ___link_id = 0; \ ___link_id < ARRAY_SIZE(___sdata->link); \ ___link_id++) \ - if ((_link = wiphy_dereference((local)->hw.wiphy, \ + if ((_link = wiphy_dereference((_local)->hw.wiphy, \ ___sdata->link[___link_id]))) static inline int @@ -1749,6 +1762,7 @@ struct ieee802_11_elems { const struct ieee80211_eht_operation *eht_operation; const struct ieee80211_multi_link_elem *ml_basic; const struct ieee80211_multi_link_elem *ml_reconf; + const struct ieee80211_multi_link_elem *ml_epcs; const struct ieee80211_bandwidth_indication *bandwidth_indication; const struct ieee80211_ttlm_elem *ttlm[IEEE80211_TTLM_MAX_CNT]; @@ -1779,6 +1793,7 @@ struct ieee802_11_elems { /* mult-link element can be de-fragmented and thus u8 is not sufficient */ size_t ml_basic_len; size_t ml_reconf_len; + size_t ml_epcs_len; u8 ttlm_num; @@ -2109,8 +2124,6 @@ void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata, int ieee80211_send_smps_action(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps, const u8 *da, const u8 *bssid, int link_id); -bool ieee80211_smps_is_restrictive(enum ieee80211_smps_mode smps_mode_old, - enum ieee80211_smps_mode smps_mode_new); void ieee80211_add_addbaext(struct sk_buff *skb, const u8 req_addba_ext_data, u16 buf_size); @@ -2766,6 +2779,12 @@ void ieee80211_check_wbrf_support(struct ieee80211_local *local); void ieee80211_add_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef); void ieee80211_remove_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef); +int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata, + struct cfg80211_assoc_link *add_links, + u16 rem_links); + +void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len); #if IS_ENABLED(CONFIG_MAC80211_KUNIT_TEST) #define EXPORT_SYMBOL_IF_MAC80211_KUNIT(sym) EXPORT_SYMBOL_IF_KUNIT(sym) #define VISIBLE_IF_MAC80211_KUNIT diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 806dffa48ef9..0ea7e77860b7 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -295,7 +295,6 @@ static int ieee80211_change_mac(struct net_device *dev, void *addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; - int ret; /* * This happens during unregistration if there's a bond device @@ -305,11 +304,9 @@ static int ieee80211_change_mac(struct net_device *dev, void *addr) if (!dev->ieee80211_ptr->registered) return 0; - wiphy_lock(local->hw.wiphy); - ret = _ieee80211_change_mac(sdata, addr); - wiphy_unlock(local->hw.wiphy); + guard(wiphy)(local->hw.wiphy); - return ret; + return _ieee80211_change_mac(sdata, addr); } static inline int identical_mac_addr_allowed(int type1, int type2) @@ -445,16 +442,13 @@ static int ieee80211_open(struct net_device *dev) if (!is_valid_ether_addr(dev->dev_addr)) return -EADDRNOTAVAIL; - wiphy_lock(sdata->local->hw.wiphy); + guard(wiphy)(sdata->local->hw.wiphy); + err = ieee80211_check_concurrent_iface(sdata, sdata->vif.type); if (err) - goto out; + return err; - err = ieee80211_do_open(&sdata->wdev, true); -out: - wiphy_unlock(sdata->local->hw.wiphy); - - return err; + return ieee80211_do_open(&sdata->wdev, true); } static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_down) @@ -775,11 +769,11 @@ static int ieee80211_stop(struct net_device *dev) ieee80211_stop_mbssid(sdata); } - wiphy_lock(sdata->local->hw.wiphy); + guard(wiphy)(sdata->local->hw.wiphy); + wiphy_work_cancel(sdata->local->hw.wiphy, &sdata->activate_links_work); ieee80211_do_stop(sdata, true); - wiphy_unlock(sdata->local->hw.wiphy); return 0; } @@ -1566,6 +1560,10 @@ static void ieee80211_iface_process_skb(struct ieee80211_local *local, ieee80211_process_neg_ttlm_res(sdata, mgmt, skb->len); break; + case WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP: + ieee80211_process_ml_reconf_resp(sdata, mgmt, + skb->len); + break; default: break; } @@ -2279,7 +2277,7 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) */ cfg80211_shutdown_all_interfaces(local->hw.wiphy); - wiphy_lock(local->hw.wiphy); + guard(wiphy)(local->hw.wiphy); WARN(local->open_count, "%s: open count remains %d\n", wiphy_name(local->hw.wiphy), local->open_count); @@ -2309,7 +2307,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) if (!netdev) kfree(sdata); } - wiphy_unlock(local->hw.wiphy); } static int netdev_notify(struct notifier_block *nb, diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 67ecfea22982..dcf8643a0baa 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -1409,7 +1409,7 @@ ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, if (sdata->u.mgd.mfp != IEEE80211_MFP_DISABLED) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; - key->conf.link_id = link_id; + key->conf.link_id = link_data->link_id; err = ieee80211_key_link(key, link_data, NULL); if (err) diff --git a/net/mac80211/main.c b/net/mac80211/main.c index ee1211a213d7..53e5aee46885 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include @@ -726,8 +726,13 @@ ieee80211_default_mgmt_stypes[NUM_NL80211_IFTYPES] = { }, [NL80211_IFTYPE_P2P_DEVICE] = { .tx = 0xffff, + /* + * To support P2P PASN pairing let user space register to rx + * also AUTH frames on P2P device interface. + */ .rx = BIT(IEEE80211_STYPE_ACTION >> 4) | - BIT(IEEE80211_STYPE_PROBE_REQ >> 4), + BIT(IEEE80211_STYPE_PROBE_REQ >> 4) | + BIT(IEEE80211_STYPE_AUTH >> 4), }, }; @@ -1305,6 +1310,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 && !(iftd->he_cap.he_cap_elem.phy_cap_info[0] & he_40_mhz_cap)) return -EINVAL; + + /* no support for per-band vendor elems with MLO */ + if (WARN_ON(iftd->vendor_elems.len && + hw->wiphy->flags & WIPHY_FLAG_SUPPORTS_MLO)) + return -EINVAL; } /* HT, VHT, HE require QoS, thus >= 4 queues */ diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 6ea35c88dc48..5a0156e11c91 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -432,15 +432,14 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; - u32 rates, basic_rates = 0, changed = 0; + u32 rates, changed = 0; enum ieee80211_sta_rx_bandwidth bw = sta->sta.deflink.bandwidth; sband = ieee80211_get_sband(sdata); if (!sband) return; - rates = ieee80211_sta_get_rates(sdata, elems, sband->band, - &basic_rates); + rates = ieee80211_sta_get_rates(sdata, elems, sband->band, NULL); spin_lock_bh(&sta->mesh->plink_lock); sta->deflink.rx_stats.last_rx = jiffies; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 61c318f5239f..f8d52b3b0d0e 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -344,6 +344,7 @@ ieee80211_determine_ap_chan(struct ieee80211_sub_if_data *sdata, static bool ieee80211_verify_peer_he_mcs_support(struct ieee80211_sub_if_data *sdata, + int link_id, const struct ieee80211_he_cap_elem *he_cap, const struct ieee80211_he_operation *he_op) { @@ -371,9 +372,9 @@ ieee80211_verify_peer_he_mcs_support(struct ieee80211_sub_if_data *sdata, */ if ((mcs_80_map_tx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED || (mcs_80_map_rx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED) { - sdata_info(sdata, - "Missing mandatory rates for 1 Nss, rx 0x%x, tx 0x%x, disable HE\n", - mcs_80_map_tx, mcs_80_map_rx); + link_id_info(sdata, link_id, + "Missing mandatory rates for 1 Nss, rx 0x%x, tx 0x%x, disable HE\n", + mcs_80_map_tx, mcs_80_map_rx); return false; } @@ -417,9 +418,9 @@ ieee80211_verify_peer_he_mcs_support(struct ieee80211_sub_if_data *sdata, if (ap_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || ap_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || ap_rx_val < ap_op_val || ap_tx_val < ap_op_val) { - sdata_info(sdata, - "Invalid rates for %d Nss, rx %d, tx %d oper %d, disable HE\n", - nss, ap_rx_val, ap_rx_val, ap_op_val); + link_id_info(sdata, link_id, + "Invalid rates for %d Nss, rx %d, tx %d oper %d, disable HE\n", + nss, ap_rx_val, ap_tx_val, ap_op_val); return false; } } @@ -589,6 +590,68 @@ ieee80211_verify_sta_eht_mcs_support(struct ieee80211_sub_if_data *sdata, return true; } +static void ieee80211_get_rates(struct ieee80211_supported_band *sband, + const u8 *supp_rates, + unsigned int supp_rates_len, + const u8 *ext_supp_rates, + unsigned int ext_supp_rates_len, + u32 *rates, u32 *basic_rates, + unsigned long *unknown_rates_selectors, + bool *have_higher_than_11mbit, + int *min_rate, int *min_rate_index) +{ + int i, j; + + for (i = 0; i < supp_rates_len + ext_supp_rates_len; i++) { + u8 supp_rate = i < supp_rates_len ? + supp_rates[i] : + ext_supp_rates[i - supp_rates_len]; + int rate = supp_rate & 0x7f; + bool is_basic = !!(supp_rate & 0x80); + + if ((rate * 5) > 110 && have_higher_than_11mbit) + *have_higher_than_11mbit = true; + + /* + * Skip membership selectors since they're not rates. + * + * Note: Even though the membership selector and the basic + * rate flag share the same bit, they are not exactly + * the same. + */ + if (is_basic && rate >= BSS_MEMBERSHIP_SELECTOR_MIN) { + if (unknown_rates_selectors) + set_bit(rate, unknown_rates_selectors); + continue; + } + + for (j = 0; j < sband->n_bitrates; j++) { + struct ieee80211_rate *br; + int brate; + + br = &sband->bitrates[j]; + + brate = DIV_ROUND_UP(br->bitrate, 5); + if (brate == rate) { + if (rates) + *rates |= BIT(j); + if (is_basic && basic_rates) + *basic_rates |= BIT(j); + if (min_rate && (rate * 5) < *min_rate) { + *min_rate = rate * 5; + if (min_rate_index) + *min_rate_index = j; + } + break; + } + } + + /* Handle an unknown entry as if it is an unknown selector */ + if (is_basic && unknown_rates_selectors && j == sband->n_bitrates) + set_bit(rate, unknown_rates_selectors); + } +} + static bool ieee80211_chandef_usable(struct ieee80211_sub_if_data *sdata, const struct cfg80211_chan_def *chandef, u32 prohibited_flags) @@ -819,7 +882,8 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, struct ieee80211_conn_settings *conn, struct cfg80211_bss *cbss, int link_id, struct ieee80211_chan_req *chanreq, - struct cfg80211_chan_def *ap_chandef) + struct cfg80211_chan_def *ap_chandef, + unsigned long *userspace_selectors) { const struct cfg80211_bss_ies *ies = rcu_dereference(cbss->ies); struct ieee80211_bss *bss = (void *)cbss->priv; @@ -833,6 +897,8 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems; struct ieee80211_supported_band *sband; enum ieee80211_conn_mode ap_mode; + unsigned long unknown_rates_selectors[BITS_TO_LONGS(128)] = {}; + unsigned long sta_selectors[BITS_TO_LONGS(128)] = {}; int ret; again: @@ -861,6 +927,11 @@ again: sband = sdata->local->hw.wiphy->bands[channel->band]; + ieee80211_get_rates(sband, elems->supp_rates, elems->supp_rates_len, + elems->ext_supp_rates, elems->ext_supp_rates_len, + NULL, NULL, unknown_rates_selectors, NULL, NULL, + NULL); + switch (channel->band) { case NL80211_BAND_S1GHZ: if (WARN_ON(ap_mode != IEEE80211_CONN_MODE_S1G)) { @@ -870,8 +941,8 @@ again: return elems; case NL80211_BAND_6GHZ: if (ap_mode < IEEE80211_CONN_MODE_HE) { - sdata_info(sdata, - "Rejecting non-HE 6/7 GHz connection"); + link_id_info(sdata, link_id, + "Rejecting non-HE 6/7 GHz connection"); ret = -EINVAL; goto free; } @@ -911,6 +982,29 @@ again: chanreq->oper = *ap_chandef; + bitmap_copy(sta_selectors, userspace_selectors, 128); + if (conn->mode >= IEEE80211_CONN_MODE_HT) + set_bit(BSS_MEMBERSHIP_SELECTOR_HT_PHY, sta_selectors); + if (conn->mode >= IEEE80211_CONN_MODE_VHT) + set_bit(BSS_MEMBERSHIP_SELECTOR_VHT_PHY, sta_selectors); + if (conn->mode >= IEEE80211_CONN_MODE_HE) + set_bit(BSS_MEMBERSHIP_SELECTOR_HE_PHY, sta_selectors); + if (conn->mode >= IEEE80211_CONN_MODE_EHT) + set_bit(BSS_MEMBERSHIP_SELECTOR_EHT_PHY, sta_selectors); + + /* + * We do not support EPD or GLK so never add them. + * SAE_H2E is handled through userspace_selectors. + */ + + /* Check if we support all required features */ + if (!bitmap_subset(unknown_rates_selectors, sta_selectors, 128)) { + link_id_info(sdata, link_id, + "required basic rate or BSS membership selectors not supported or disabled, rejecting connection\n"); + ret = -EINVAL; + goto free; + } + ieee80211_set_chanreq_ap(sdata, chanreq, conn, ap_chandef); while (!ieee80211_chandef_usable(sdata, &chanreq->oper, @@ -942,16 +1036,18 @@ again: } if (chanreq->oper.width != ap_chandef->width || ap_mode != conn->mode) - sdata_info(sdata, - "regulatory prevented using AP config, downgraded\n"); + link_id_info(sdata, link_id, + "regulatory prevented using AP config, downgraded\n"); if (conn->mode >= IEEE80211_CONN_MODE_HE && - (!ieee80211_verify_peer_he_mcs_support(sdata, (void *)elems->he_cap, + (!ieee80211_verify_peer_he_mcs_support(sdata, link_id, + (void *)elems->he_cap, elems->he_operation) || !ieee80211_verify_sta_he_mcs_support(sdata, sband, elems->he_operation))) { conn->mode = IEEE80211_CONN_MODE_VHT; - sdata_info(sdata, "required MCSes not supported, disabling HE\n"); + link_id_info(sdata, link_id, + "required MCSes not supported, disabling HE\n"); } if (conn->mode >= IEEE80211_CONN_MODE_EHT && @@ -961,7 +1057,8 @@ again: conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, conn->bw_limit, IEEE80211_CONN_BW_LIMIT_160); - sdata_info(sdata, "required MCSes not supported, disabling EHT\n"); + link_id_info(sdata, link_id, + "required MCSes not supported, disabling EHT\n"); } /* the mode can only decrease, so this must terminate */ @@ -988,7 +1085,8 @@ free: static int ieee80211_config_bw(struct ieee80211_link_data *link, struct ieee802_11_elems *elems, - bool update, u64 *changed) + bool update, u64 *changed, + const char *frame) { struct ieee80211_channel *channel = link->conf->chanreq.oper.chan; struct ieee80211_sub_if_data *sdata = link->sdata; @@ -1013,9 +1111,10 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link, if (ap_mode != link->u.mgd.conn.mode) { link_info(link, - "AP appears to change mode (expected %s, found %s), disconnect\n", + "AP %pM appears to change mode (expected %s, found %s) in %s, disconnect\n", + link->u.mgd.bssid, ieee80211_conn_mode_str(link->u.mgd.conn.mode), - ieee80211_conn_mode_str(ap_mode)); + ieee80211_conn_mode_str(ap_mode), frame); return -EINVAL; } @@ -1060,16 +1159,16 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link, return 0; link_info(link, - "AP %pM changed bandwidth, new used config is %d.%03d MHz, width %d (%d.%03d/%d MHz)\n", - link->u.mgd.bssid, chanreq.oper.chan->center_freq, + "AP %pM changed bandwidth in %s, new used config is %d.%03d MHz, width %d (%d.%03d/%d MHz)\n", + link->u.mgd.bssid, frame, chanreq.oper.chan->center_freq, chanreq.oper.chan->freq_offset, chanreq.oper.width, chanreq.oper.center_freq1, chanreq.oper.freq1_offset, chanreq.oper.center_freq2); if (!cfg80211_chandef_valid(&chanreq.oper)) { sdata_info(sdata, - "AP %pM changed caps/bw in a way we can't support - disconnect\n", - link->u.mgd.bssid); + "AP %pM changed caps/bw in %s in a way we can't support - disconnect\n", + link->u.mgd.bssid, frame); return -EINVAL; } @@ -1098,8 +1197,8 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link, ret = ieee80211_link_change_chanreq(link, &chanreq, changed); if (ret) { sdata_info(sdata, - "AP %pM changed bandwidth to incompatible one - disconnect\n", - link->u.mgd.bssid); + "AP %pM changed bandwidth in %s to incompatible one - disconnect\n", + link->u.mgd.bssid, frame); return ret; } @@ -1412,23 +1511,25 @@ static size_t ieee80211_add_before_he_elems(struct sk_buff *skb, #define PRESENT_ELEMS_MAX 8 #define PRESENT_ELEM_EXT_OFFS 0x100 -static void ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, u16 capab, - const struct element *ext_capa, - const u16 *present_elems); +static void +ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, u16 capab, + const struct element *ext_capa, + const u16 *present_elems, + struct ieee80211_mgd_assoc_data *assoc_data); -static size_t ieee80211_assoc_link_elems(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, u16 *capab, - const struct element *ext_capa, - const u8 *extra_elems, - size_t extra_elems_len, - unsigned int link_id, - struct ieee80211_link_data *link, - u16 *present_elems) +static size_t +ieee80211_add_link_elems(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, u16 *capab, + const struct element *ext_capa, + const u8 *extra_elems, + size_t extra_elems_len, + unsigned int link_id, + struct ieee80211_link_data *link, + u16 *present_elems, + struct ieee80211_mgd_assoc_data *assoc_data) { enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data; struct cfg80211_bss *cbss = assoc_data->link[link_id].bss; struct ieee80211_channel *chan = cbss->channel; const struct ieee80211_sband_iftype_data *iftd; @@ -1577,7 +1678,7 @@ static size_t ieee80211_assoc_link_elems(struct ieee80211_sub_if_data *sdata, if (link_id == assoc_data->assoc_link_id) ieee80211_assoc_add_ml_elem(sdata, skb, orig_capab, ext_capa, - present_elems); + present_elems, assoc_data); /* crash if somebody gets it wrong */ present_elems = NULL; @@ -1656,14 +1757,14 @@ static void ieee80211_add_non_inheritance_elem(struct sk_buff *skb, *len = skb->len - skb_len - 2; } -static void ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, u16 capab, - const struct element *ext_capa, - const u16 *outer_present_elems) +static void +ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, u16 capab, + const struct element *ext_capa, + const u16 *outer_present_elems, + struct ieee80211_mgd_assoc_data *assoc_data) { struct ieee80211_local *local = sdata->local; - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data; struct ieee80211_multi_link_elem *ml_elem; struct ieee80211_mle_basic_common_info *common; const struct wiphy_iftype_ext_capab *ift_ext_capa; @@ -1736,16 +1837,17 @@ static void ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata, * (if applicable) are skipped. So we only have * the capability field (remember the position and fill * later), followed by the elements added below by - * calling ieee80211_assoc_link_elems(). + * calling ieee80211_add_link_elems(). */ capab_pos = skb_put(skb, 2); - extra_used = ieee80211_assoc_link_elems(sdata, skb, &capab, - ext_capa, - extra_elems, - extra_elems_len, - link_id, NULL, - link_present_elems); + extra_used = ieee80211_add_link_elems(sdata, skb, &capab, + ext_capa, + extra_elems, + extra_elems_len, + link_id, NULL, + link_present_elems, + assoc_data); if (extra_elems) skb_put_data(skb, extra_elems + extra_used, extra_elems_len - extra_used); @@ -1762,6 +1864,55 @@ static void ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata, ieee80211_fragment_element(skb, ml_elem_len, WLAN_EID_FRAGMENT); } +static int +ieee80211_link_common_elems_size(struct ieee80211_sub_if_data *sdata, + enum nl80211_iftype iftype, + struct cfg80211_bss *cbss, + size_t elems_len) +{ + struct ieee80211_local *local = sdata->local; + const struct ieee80211_sband_iftype_data *iftd; + struct ieee80211_supported_band *sband; + size_t size = 0; + + if (!cbss) + return size; + + sband = local->hw.wiphy->bands[cbss->channel->band]; + + /* add STA profile elements length */ + size += elems_len; + + /* and supported rates length */ + size += 4 + sband->n_bitrates; + + /* supported channels */ + size += 2 + 2 * sband->n_channels; + + iftd = ieee80211_get_sband_iftype_data(sband, iftype); + if (iftd) + size += iftd->vendor_elems.len; + + /* power capability */ + size += 4; + + /* HT, VHT, HE, EHT */ + size += 2 + sizeof(struct ieee80211_ht_cap); + size += 2 + sizeof(struct ieee80211_vht_cap); + size += 2 + 1 + sizeof(struct ieee80211_he_cap_elem) + + sizeof(struct ieee80211_he_mcs_nss_supp) + + IEEE80211_HE_PPE_THRES_MAX_LEN; + + if (sband->band == NL80211_BAND_6GHZ) + size += 2 + 1 + sizeof(struct ieee80211_he_6ghz_capa); + + size += 2 + 1 + sizeof(struct ieee80211_eht_cap_elem) + + sizeof(struct ieee80211_eht_mcs_nss_supp) + + IEEE80211_EHT_PPE_THRES_MAX_LEN; + + return size; +} + static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; @@ -1800,42 +1951,15 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { struct cfg80211_bss *cbss = assoc_data->link[link_id].bss; - const struct ieee80211_sband_iftype_data *iftd; - struct ieee80211_supported_band *sband; + size_t elems_len = assoc_data->link[link_id].elems_len; if (!cbss) continue; - sband = local->hw.wiphy->bands[cbss->channel->band]; - n_links++; - /* add STA profile elements length */ - size += assoc_data->link[link_id].elems_len; - /* and supported rates length */ - size += 4 + sband->n_bitrates; - /* supported channels */ - size += 2 + 2 * sband->n_channels; - iftd = ieee80211_get_sband_iftype_data(sband, iftype); - if (iftd) - size += iftd->vendor_elems.len; - - /* power capability */ - size += 4; - - /* HT, VHT, HE, EHT */ - size += 2 + sizeof(struct ieee80211_ht_cap); - size += 2 + sizeof(struct ieee80211_vht_cap); - size += 2 + 1 + sizeof(struct ieee80211_he_cap_elem) + - sizeof(struct ieee80211_he_mcs_nss_supp) + - IEEE80211_HE_PPE_THRES_MAX_LEN; - - if (sband->band == NL80211_BAND_6GHZ) - size += 2 + 1 + sizeof(struct ieee80211_he_6ghz_capa); - - size += 2 + 1 + sizeof(struct ieee80211_eht_cap_elem) + - sizeof(struct ieee80211_eht_mcs_nss_supp) + - IEEE80211_EHT_PPE_THRES_MAX_LEN; + size += ieee80211_link_common_elems_size(sdata, iftype, cbss, + elems_len); /* non-inheritance element */ size += 2 + 2 + PRESENT_ELEMS_MAX; @@ -1932,12 +2056,12 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) /* add the elements for the assoc (main) link */ link_capab = capab; - offset = ieee80211_assoc_link_elems(sdata, skb, &link_capab, - ext_capa, - assoc_data->ie, - assoc_data->ie_len, - assoc_data->assoc_link_id, link, - present_elems); + offset = ieee80211_add_link_elems(sdata, skb, &link_capab, + ext_capa, + assoc_data->ie, + assoc_data->ie_len, + assoc_data->assoc_link_id, link, + present_elems, assoc_data); put_unaligned_le16(link_capab, capab_pos); /* if present, add any custom non-vendor IEs */ @@ -3593,12 +3717,45 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, netif_carrier_on(sdata->dev); } +static void ieee80211_ml_reconf_reset(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_mgd_assoc_data *add_links_data = + sdata->u.mgd.reconf.add_links_data; + + if (!ieee80211_vif_is_mld(&sdata->vif) || + !(sdata->u.mgd.reconf.added_links | + sdata->u.mgd.reconf.removed_links)) + return; + + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &sdata->u.mgd.reconf.wk); + sdata->u.mgd.reconf.added_links = 0; + sdata->u.mgd.reconf.removed_links = 0; + sdata->u.mgd.reconf.dialog_token = 0; + + if (add_links_data) { + struct cfg80211_mlo_reconf_done_data done_data = {}; + u8 link_id; + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; + link_id++) + done_data.links[link_id].bss = + add_links_data->link[link_id].bss; + + cfg80211_mlo_reconf_add_done(sdata->dev, &done_data); + + kfree(sdata->u.mgd.reconf.add_links_data); + sdata->u.mgd.reconf.add_links_data = NULL; + } +} + static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, u16 stype, u16 reason, bool tx, u8 *frame_buf) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; + struct sta_info *ap_sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr); unsigned int link_id; u64 changed = 0; struct ieee80211_prep_tx_info info = { @@ -3609,6 +3766,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, lockdep_assert_wiphy(local->hw.wiphy); + if (WARN_ON(!ap_sta)) + return; + if (WARN_ON_ONCE(tx && !frame_buf)) return; @@ -3672,8 +3832,16 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->vif.cfg.ssid_len = 0; - /* remove AP and TDLS peers */ - sta_info_flush(sdata, -1); + /* Remove TDLS peers */ + __sta_info_flush(sdata, false, -1, ap_sta); + + if (sdata->vif.driver_flags & IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC) { + /* Only move the AP state */ + sta_info_move_state(ap_sta, IEEE80211_STA_NONE); + } else { + /* Remove AP peer */ + sta_info_flush(sdata, -1); + } /* finally reset all BSS / config parameters */ if (!ieee80211_vif_is_mld(&sdata->vif)) @@ -3724,6 +3892,14 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_vif_cfg_change_notify(sdata, changed); } + if (sdata->vif.driver_flags & IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC) { + /* + * After notifying the driver about the disassoc, + * remove the ap sta. + */ + sta_info_flush(sdata, -1); + } + /* disassociated - set to defaults now */ ieee80211_set_wmm_default(&sdata->deflink, false, false); @@ -3785,6 +3961,12 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_vif_set_links(sdata, 0, 0); ifmgd->mcast_seq_last = IEEE80211_SN_MODULO; + + /* if disconnection happens in the middle of the ML reconfiguration + * flow, cfg80211 must called to release the BSS references obtained + * when the flow started. + */ + ieee80211_ml_reconf_reset(sdata); } static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) @@ -4220,6 +4402,8 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata, lockdep_assert_wiphy(sdata->local->hw.wiphy); + sdata->u.mgd.auth_data = NULL; + if (!assoc) { /* * we are not authenticated yet, the only timer that could be @@ -4241,7 +4425,6 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata, cfg80211_put_bss(sdata->local->hw.wiphy, auth_data->bss); kfree(auth_data); - sdata->u.mgd.auth_data = NULL; } enum assoc_status { @@ -4258,6 +4441,8 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata, lockdep_assert_wiphy(sdata->local->hw.wiphy); + sdata->u.mgd.assoc_data = NULL; + if (status != ASSOC_SUCCESS) { /* * we are not associated yet, the only timer that could be @@ -4296,7 +4481,6 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata, } kfree(assoc_data); - sdata->u.mgd.assoc_data = NULL; } static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, @@ -4599,57 +4783,6 @@ static void ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, false); } -static void ieee80211_get_rates(struct ieee80211_supported_band *sband, - u8 *supp_rates, unsigned int supp_rates_len, - u32 *rates, u32 *basic_rates, - bool *have_higher_than_11mbit, - int *min_rate, int *min_rate_index) -{ - int i, j; - - for (i = 0; i < supp_rates_len; i++) { - int rate = supp_rates[i] & 0x7f; - bool is_basic = !!(supp_rates[i] & 0x80); - - if ((rate * 5) > 110) - *have_higher_than_11mbit = true; - - /* - * Skip HT, VHT, HE, EHT and SAE H2E only BSS membership - * selectors since they're not rates. - * - * Note: Even though the membership selector and the basic - * rate flag share the same bit, they are not exactly - * the same. - */ - if (supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_HT_PHY) || - supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_VHT_PHY) || - supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_HE_PHY) || - supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_EHT_PHY) || - supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_SAE_H2E)) - continue; - - for (j = 0; j < sband->n_bitrates; j++) { - struct ieee80211_rate *br; - int brate; - - br = &sband->bitrates[j]; - - brate = DIV_ROUND_UP(br->bitrate, 5); - if (brate == rate) { - *rates |= BIT(j); - if (is_basic) - *basic_rates |= BIT(j); - if ((rate * 5) < *min_rate) { - *min_rate = rate * 5; - *min_rate_index = j; - } - break; - } - } - } -} - static bool ieee80211_twt_req_supported(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const struct link_sta_info *link_sta, @@ -4711,7 +4844,8 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, u64 *changed) { struct ieee80211_sub_if_data *sdata = link->sdata; - struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data; + struct ieee80211_mgd_assoc_data *assoc_data = + sdata->u.mgd.assoc_data ?: sdata->u.mgd.reconf.add_links_data; struct ieee80211_bss_conf *bss_conf = link->conf; struct ieee80211_local *local = sdata->local; unsigned int link_id = link->link_id; @@ -4898,7 +5032,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, /* check/update if AP changed anything in assoc response vs. scan */ if (ieee80211_config_bw(link, elems, link_id == assoc_data->assoc_link_id, - changed)) { + changed, "assoc response")) { ret = false; goto out; } @@ -5121,7 +5255,9 @@ static int ieee80211_mgd_setup_link_sta(struct ieee80211_link_data *link, sband = local->hw.wiphy->bands[cbss->channel->band]; ieee80211_get_rates(sband, bss->supp_rates, bss->supp_rates_len, - &rates, &basic_rates, &have_higher_than_11mbit, + NULL, 0, + &rates, &basic_rates, NULL, + &have_higher_than_11mbit, &min_rate, &min_rate_index); /* @@ -5514,7 +5650,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, int link_id, struct cfg80211_bss *cbss, bool mlo, - struct ieee80211_conn_settings *conn) + struct ieee80211_conn_settings *conn, + unsigned long *userspace_selectors) { struct ieee80211_local *local = sdata->local; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; @@ -5527,7 +5664,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); elems = ieee80211_determine_chan_mode(sdata, conn, cbss, link_id, - &chanreq, &ap_chandef); + &chanreq, &ap_chandef, + userspace_selectors); if (IS_ERR(elems)) { rcu_read_unlock(); @@ -5721,7 +5859,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, link->u.mgd.conn = assoc_data->link[link_id].conn; err = ieee80211_prep_channel(sdata, link, link_id, cbss, - true, &link->u.mgd.conn); + true, &link->u.mgd.conn, + assoc_data->userspace_selectors); if (err) { link_info(link, "prep_channel failed\n"); goto out_err; @@ -5839,6 +5978,8 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, if (!assoc_data) return; + info.link_id = assoc_data->assoc_link_id; + parse_params.mode = assoc_data->link[assoc_data->assoc_link_id].conn.mode; @@ -7056,7 +7197,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, changed |= ieee80211_recalc_twt_req(sdata, sband, link, link_sta, elems); - if (ieee80211_config_bw(link, elems, true, &changed)) { + if (ieee80211_config_bw(link, elems, true, &changed, "beacon")) { ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DEAUTH_LEAVING, true, deauth_buf); @@ -8135,6 +8276,25 @@ static void ieee80211_request_smps_mgd_work(struct wiphy *wiphy, link->u.mgd.driver_smps_mode); } +static void ieee80211_ml_sta_reconf_timeout(struct wiphy *wiphy, + struct wiphy_work *work) +{ + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, + u.mgd.reconf.wk.work); + + if (!sdata->u.mgd.reconf.added_links && + !sdata->u.mgd.reconf.removed_links) + return; + + sdata_info(sdata, + "mlo: reconf: timeout: added=0x%x, removed=0x%x\n", + sdata->u.mgd.reconf.added_links, + sdata->u.mgd.reconf.removed_links); + + __ieee80211_disconnect(sdata); +} + /* interface setup */ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) { @@ -8149,6 +8309,8 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) ieee80211_tdls_peer_del_work); wiphy_delayed_work_init(&ifmgd->ml_reconf_work, ieee80211_ml_reconf_work); + wiphy_delayed_work_init(&ifmgd->reconf.wk, + ieee80211_ml_sta_reconf_timeout); timer_setup(&ifmgd->timer, ieee80211_sta_timer, 0); timer_setup(&ifmgd->bcn_mon_timer, ieee80211_sta_bcn_mon_timer, 0); timer_setup(&ifmgd->conn_mon_timer, ieee80211_sta_conn_mon_timer, 0); @@ -8209,6 +8371,9 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link) if (sdata->u.mgd.assoc_data) ether_addr_copy(link->conf->addr, sdata->u.mgd.assoc_data->link[link_id].addr); + else if (sdata->u.mgd.reconf.add_links_data) + ether_addr_copy(link->conf->addr, + sdata->u.mgd.reconf.add_links_data->link[link_id].addr); else if (!is_valid_ether_addr(link->conf->addr)) eth_random_addr(link->conf->addr); } @@ -8231,7 +8396,8 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *cbss, s8 link_id, const u8 *ap_mld_addr, bool assoc, struct ieee80211_conn_settings *conn, - bool override) + bool override, + unsigned long *userspace_selectors) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -8370,7 +8536,8 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, */ link->u.mgd.conn = *conn; err = ieee80211_prep_channel(sdata, link, link->link_id, cbss, - mlo, &link->u.mgd.conn); + mlo, &link->u.mgd.conn, + userspace_selectors); if (err) { if (new_sta) sta_info_free(local, new_sta); @@ -8486,6 +8653,22 @@ out: return ret; } +static void ieee80211_parse_cfg_selectors(unsigned long *userspace_selectors, + const u8 *supported_selectors, + u8 supported_selectors_len) +{ + if (supported_selectors) { + for (int i = 0; i < supported_selectors_len; i++) { + set_bit(supported_selectors[i], + userspace_selectors); + } + } else { + /* Assume SAE_H2E support for backward compatibility. */ + set_bit(BSS_MEMBERSHIP_SELECTOR_SAE_H2E, + userspace_selectors); + } +} + /* config hooks */ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, struct cfg80211_auth_request *req) @@ -8587,6 +8770,10 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, memcpy(auth_data->key, req->key, req->key_len); } + ieee80211_parse_cfg_selectors(auth_data->userspace_selectors, + req->supported_selectors, + req->supported_selectors_len); + auth_data->algorithm = auth_alg; /* try to authenticate/probe */ @@ -8640,7 +8827,8 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, err = ieee80211_prep_connection(sdata, req->bss, req->link_id, req->ap_mld_addr, cont_auth, - &conn, false); + &conn, false, + auth_data->userspace_selectors); if (err) goto err_clear; @@ -8927,6 +9115,10 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, false); } + ieee80211_parse_cfg_selectors(assoc_data->userspace_selectors, + req->supported_selectors, + req->supported_selectors_len); + memcpy(&ifmgd->ht_capa, &req->ht_capa, sizeof(ifmgd->ht_capa)); memcpy(&ifmgd->ht_capa_mask, &req->ht_capa_mask, sizeof(ifmgd->ht_capa_mask)); @@ -9173,7 +9365,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, /* only calculate the mode, hence link == NULL */ err = ieee80211_prep_channel(sdata, NULL, i, assoc_data->link[i].bss, true, - &assoc_data->link[i].conn); + &assoc_data->link[i].conn, + assoc_data->userspace_selectors); if (err) { req->links[i].error = err; goto err_clear; @@ -9189,7 +9382,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, err = ieee80211_prep_connection(sdata, cbss, req->link_id, req->ap_mld_addr, true, &assoc_data->link[assoc_link_id].conn, - override); + override, + assoc_data->userspace_selectors); if (err) goto err_clear; @@ -9433,3 +9627,697 @@ void ieee80211_disable_rssi_reports(struct ieee80211_vif *vif) _ieee80211_enable_rssi_reports(sdata, 0, 0); } EXPORT_SYMBOL(ieee80211_disable_rssi_reports); + +static void ieee80211_ml_reconf_selectors(unsigned long *userspace_selectors) +{ + *userspace_selectors = 0; + + /* these selectors are mandatory for ML reconfiguration */ + set_bit(BSS_MEMBERSHIP_SELECTOR_SAE_H2E, userspace_selectors); + set_bit(BSS_MEMBERSHIP_SELECTOR_HE_PHY, userspace_selectors); + set_bit(BSS_MEMBERSHIP_SELECTOR_EHT_PHY, userspace_selectors); +} + +void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_mgd_assoc_data *add_links_data = + ifmgd->reconf.add_links_data; + struct sta_info *sta; + struct cfg80211_mlo_reconf_done_data done_data = {}; + u16 sta_changed_links = sdata->u.mgd.reconf.added_links | + sdata->u.mgd.reconf.removed_links; + u16 link_mask, valid_links; + unsigned int link_id; + unsigned long userspace_selectors; + size_t orig_len = len; + u8 i, group_key_data_len; + u8 *pos; + + if (!ieee80211_vif_is_mld(&sdata->vif) || + len < offsetofend(typeof(*mgmt), u.action.u.ml_reconf_resp) || + mgmt->u.action.u.ml_reconf_resp.dialog_token != + sdata->u.mgd.reconf.dialog_token || + !sta_changed_links) + return; + + pos = mgmt->u.action.u.ml_reconf_resp.variable; + len -= offsetofend(typeof(*mgmt), u.action.u.ml_reconf_resp); + + /* each status duple is 3 octets */ + if (len < mgmt->u.action.u.ml_reconf_resp.count * 3) { + sdata_info(sdata, + "mlo: reconf: unexpected len=%zu, count=%u\n", + len, mgmt->u.action.u.ml_reconf_resp.count); + goto disconnect; + } + + link_mask = sta_changed_links; + for (i = 0; i < mgmt->u.action.u.ml_reconf_resp.count; i++) { + u16 status = get_unaligned_le16(pos + 1); + + link_id = *pos; + + if (!(link_mask & BIT(link_id))) { + sdata_info(sdata, + "mlo: reconf: unexpected link: %u, changed=0x%x\n", + link_id, sta_changed_links); + goto disconnect; + } + + /* clear the corresponding link, to detect the case that + * the same link was included more than one time + */ + link_mask &= ~BIT(link_id); + + /* Handle failure to remove links here. Failure to remove added + * links will be done later in the flow. + */ + if (status != WLAN_STATUS_SUCCESS) { + sdata_info(sdata, + "mlo: reconf: failed on link=%u, status=%u\n", + link_id, status); + + /* The AP MLD failed to remove a link that was already + * removed locally. As this is not expected behavior, + * disconnect + */ + if (sdata->u.mgd.reconf.removed_links & BIT(link_id)) + goto disconnect; + + /* The AP MLD failed to add a link. Remove it from the + * added links. + */ + sdata->u.mgd.reconf.added_links &= ~BIT(link_id); + } + + pos += 3; + len -= 3; + } + + if (link_mask) { + sdata_info(sdata, + "mlo: reconf: no response for links=0x%x\n", + link_mask); + goto disconnect; + } + + if (!sdata->u.mgd.reconf.added_links) + goto out; + + if (len < 1 || len < 1 + *pos) { + sdata_info(sdata, + "mlo: reconf: invalid group key data length"); + goto disconnect; + } + + /* The Group Key Data field must be present when links are added. This + * field should be processed by userland. + */ + group_key_data_len = *pos++; + + pos += group_key_data_len; + len -= group_key_data_len + 1; + + /* Process the information for the added links */ + sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr); + if (WARN_ON(!sta)) + goto disconnect; + + valid_links = sdata->vif.valid_links; + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + if (!add_links_data->link[link_id].bss || + !(sdata->u.mgd.reconf.added_links & BIT(link_id))) + + continue; + + valid_links |= BIT(link_id); + if (ieee80211_sta_allocate_link(sta, link_id)) + goto disconnect; + } + + ieee80211_vif_set_links(sdata, valid_links, sdata->vif.dormant_links); + ieee80211_ml_reconf_selectors(&userspace_selectors); + link_mask = 0; + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + struct cfg80211_bss *cbss = add_links_data->link[link_id].bss; + struct ieee80211_link_data *link; + struct link_sta_info *link_sta; + u64 changed = 0; + + if (!cbss) + continue; + + link = sdata_dereference(sdata->link[link_id], sdata); + if (WARN_ON(!link)) + goto disconnect; + + link_info(link, + "mlo: reconf: local address %pM, AP link address %pM\n", + add_links_data->link[link_id].addr, + add_links_data->link[link_id].bss->bssid); + + link_sta = rcu_dereference_protected(sta->link[link_id], + lockdep_is_held(&local->hw.wiphy->mtx)); + if (WARN_ON(!link_sta)) + goto disconnect; + + if (!link->u.mgd.have_beacon) { + const struct cfg80211_bss_ies *ies; + + rcu_read_lock(); + ies = rcu_dereference(cbss->beacon_ies); + if (ies) + link->u.mgd.have_beacon = true; + else + ies = rcu_dereference(cbss->ies); + ieee80211_get_dtim(ies, + &link->conf->sync_dtim_count, + &link->u.mgd.dtim_period); + link->conf->beacon_int = cbss->beacon_interval; + rcu_read_unlock(); + } + + link->conf->dtim_period = link->u.mgd.dtim_period ?: 1; + + link->u.mgd.conn = add_links_data->link[link_id].conn; + if (ieee80211_prep_channel(sdata, link, link_id, cbss, + true, &link->u.mgd.conn, + &userspace_selectors)) { + link_info(link, "mlo: reconf: prep_channel failed\n"); + goto disconnect; + } + + if (ieee80211_mgd_setup_link_sta(link, sta, link_sta, + add_links_data->link[link_id].bss)) + goto disconnect; + + if (!ieee80211_assoc_config_link(link, link_sta, + add_links_data->link[link_id].bss, + mgmt, pos, len, + &changed)) + goto disconnect; + + /* The AP MLD indicated success for this link, but the station + * profile status indicated otherwise. Since there is an + * inconsistency in the ML reconfiguration response, disconnect + */ + if (add_links_data->link[link_id].status != WLAN_STATUS_SUCCESS) + goto disconnect; + + ieee80211_sta_init_nss(link_sta); + if (ieee80211_sta_activate_link(sta, link_id)) + goto disconnect; + + changed |= ieee80211_link_set_associated(link, cbss); + ieee80211_link_info_change_notify(sdata, link, changed); + + ieee80211_recalc_smps(sdata, link); + link_mask |= BIT(link_id); + } + + sdata_info(sdata, + "mlo: reconf: current valid_links=0x%x, added=0x%x\n", + valid_links, link_mask); + + /* links might have changed due to rejected ones, set them again */ + ieee80211_vif_set_links(sdata, valid_links, sdata->vif.dormant_links); + ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_MLD_VALID_LINKS); + + ieee80211_recalc_ps(local); + ieee80211_recalc_ps_vif(sdata); + + done_data.buf = (const u8 *)mgmt; + done_data.len = orig_len; + done_data.added_links = link_mask; + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) + done_data.links[link_id].bss = add_links_data->link[link_id].bss; + + cfg80211_mlo_reconf_add_done(sdata->dev, &done_data); + kfree(sdata->u.mgd.reconf.add_links_data); + sdata->u.mgd.reconf.add_links_data = NULL; +out: + ieee80211_ml_reconf_reset(sdata); + return; + +disconnect: + __ieee80211_disconnect(sdata); +} + +static struct sk_buff * +ieee80211_build_ml_reconf_req(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_assoc_data *add_links_data, + u16 removed_links) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_mgmt *mgmt; + struct ieee80211_multi_link_elem *ml_elem; + struct ieee80211_mle_basic_common_info *common; + enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); + struct sk_buff *skb; + size_t size; + unsigned int link_id; + __le16 eml_capa = 0, mld_capa_ops = 0; + struct ieee80211_tx_info *info; + u8 common_size, var_common_size; + u8 *ml_elem_len; + u16 capab = 0; + + size = local->hw.extra_tx_headroom + sizeof(*mgmt); + + /* Consider the maximal length of the reconfiguration ML element */ + size += sizeof(struct ieee80211_multi_link_elem); + + /* The Basic ML element and the Reconfiguration ML element have the same + * fixed common information fields in the context of ML reconfiguration + * action frame. The AP MLD MAC address must always be present + */ + common_size = sizeof(*common); + + /* when adding links, the MLD capabilities must be present */ + var_common_size = 0; + if (add_links_data) { + const struct wiphy_iftype_ext_capab *ift_ext_capa = + cfg80211_get_iftype_ext_capa(local->hw.wiphy, + ieee80211_vif_type_p2p(&sdata->vif)); + + if (ift_ext_capa) { + eml_capa = cpu_to_le16(ift_ext_capa->eml_capabilities); + mld_capa_ops = + cpu_to_le16(ift_ext_capa->mld_capa_and_ops); + } + + /* MLD capabilities and operation */ + var_common_size += 2; + + /* EML capabilities */ + if (eml_capa & cpu_to_le16((IEEE80211_EML_CAP_EMLSR_SUPP | + IEEE80211_EML_CAP_EMLMR_SUPPORT))) + var_common_size += 2; + } + + /* Add the common information length */ + size += common_size + var_common_size; + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + struct cfg80211_bss *cbss; + size_t elems_len; + + if (removed_links & BIT(link_id)) { + size += sizeof(struct ieee80211_mle_per_sta_profile) + + ETH_ALEN; + continue; + } + + if (!add_links_data || !add_links_data->link[link_id].bss) + continue; + + elems_len = add_links_data->link[link_id].elems_len; + cbss = add_links_data->link[link_id].bss; + + /* should be the same across all BSSes */ + if (cbss->capability & WLAN_CAPABILITY_PRIVACY) + capab |= WLAN_CAPABILITY_PRIVACY; + + size += 2 + sizeof(struct ieee80211_mle_per_sta_profile) + + ETH_ALEN; + + /* SSID element + WMM */ + size += 2 + sdata->vif.cfg.ssid_len + 9; + size += ieee80211_link_common_elems_size(sdata, iftype, cbss, + elems_len); + } + + skb = alloc_skb(size, GFP_KERNEL); + if (!skb) + return NULL; + + skb_reserve(skb, local->hw.extra_tx_headroom); + mgmt = skb_put_zero(skb, offsetofend(struct ieee80211_mgmt, + u.action.u.ml_reconf_req)); + + /* Add the MAC header */ + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + memcpy(mgmt->da, sdata->vif.cfg.ap_addr, ETH_ALEN); + memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); + memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN); + + /* Add the action frame fixed fields */ + mgmt->u.action.category = WLAN_CATEGORY_PROTECTED_EHT; + mgmt->u.action.u.ml_reconf_req.action_code = + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_REQ; + + /* allocate a dialog token and store it */ + sdata->u.mgd.reconf.dialog_token = ++sdata->u.mgd.dialog_token_alloc; + mgmt->u.action.u.ml_reconf_req.dialog_token = + sdata->u.mgd.reconf.dialog_token; + + /* Add the ML reconfiguration element and the common information */ + skb_put_u8(skb, WLAN_EID_EXTENSION); + ml_elem_len = skb_put(skb, 1); + skb_put_u8(skb, WLAN_EID_EXT_EHT_MULTI_LINK); + ml_elem = skb_put(skb, sizeof(*ml_elem)); + ml_elem->control = + cpu_to_le16(IEEE80211_ML_CONTROL_TYPE_RECONF | + IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR); + common = skb_put(skb, common_size); + common->len = common_size + var_common_size; + memcpy(common->mld_mac_addr, sdata->vif.addr, ETH_ALEN); + + if (add_links_data) { + if (eml_capa & + cpu_to_le16((IEEE80211_EML_CAP_EMLSR_SUPP | + IEEE80211_EML_CAP_EMLMR_SUPPORT))) { + ml_elem->control |= + cpu_to_le16(IEEE80211_MLC_RECONF_PRES_EML_CAPA); + skb_put_data(skb, &eml_capa, sizeof(eml_capa)); + } + + ml_elem->control |= + cpu_to_le16(IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP); + + skb_put_data(skb, &mld_capa_ops, sizeof(mld_capa_ops)); + } + + if (sdata->u.mgd.flags & IEEE80211_STA_ENABLE_RRM) + capab |= WLAN_CAPABILITY_RADIO_MEASURE; + + /* Add the per station profile */ + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + u8 *subelem_len = NULL; + u16 ctrl; + const u8 *addr; + + /* Skip links that are not changing */ + if (!(removed_links & BIT(link_id)) && + (!add_links_data || !add_links_data->link[link_id].bss)) + continue; + + ctrl = link_id | + IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT; + + if (removed_links & BIT(link_id)) { + struct ieee80211_bss_conf *conf = + sdata_dereference(sdata->vif.link_conf[link_id], + sdata); + if (!conf) + continue; + + addr = conf->addr; + ctrl |= u16_encode_bits(IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_DEL_LINK, + IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE); + } else { + addr = add_links_data->link[link_id].addr; + ctrl |= IEEE80211_MLE_STA_RECONF_CONTROL_COMPLETE_PROFILE | + u16_encode_bits(IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_ADD_LINK, + IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE); + } + + skb_put_u8(skb, IEEE80211_MLE_SUBELEM_PER_STA_PROFILE); + subelem_len = skb_put(skb, 1); + + put_unaligned_le16(ctrl, skb_put(skb, sizeof(ctrl))); + skb_put_u8(skb, 1 + ETH_ALEN); + skb_put_data(skb, addr, ETH_ALEN); + + if (!(removed_links & BIT(link_id))) { + u16 link_present_elems[PRESENT_ELEMS_MAX] = {}; + size_t extra_used; + void *capab_pos; + u8 qos_info; + + capab_pos = skb_put(skb, 2); + + skb_put_u8(skb, WLAN_EID_SSID); + skb_put_u8(skb, sdata->vif.cfg.ssid_len); + skb_put_data(skb, sdata->vif.cfg.ssid, + sdata->vif.cfg.ssid_len); + + extra_used = + ieee80211_add_link_elems(sdata, skb, &capab, NULL, + add_links_data->link[link_id].elems, + add_links_data->link[link_id].elems_len, + link_id, NULL, + link_present_elems, + add_links_data); + + if (add_links_data->link[link_id].elems) + skb_put_data(skb, + add_links_data->link[link_id].elems + + extra_used, + add_links_data->link[link_id].elems_len - + extra_used); + if (sdata->u.mgd.flags & IEEE80211_STA_UAPSD_ENABLED) { + qos_info = sdata->u.mgd.uapsd_queues; + qos_info |= (sdata->u.mgd.uapsd_max_sp_len << + IEEE80211_WMM_IE_STA_QOSINFO_SP_SHIFT); + } else { + qos_info = 0; + } + + ieee80211_add_wmm_info_ie(skb_put(skb, 9), qos_info); + put_unaligned_le16(capab, capab_pos); + } + + ieee80211_fragment_element(skb, subelem_len, + IEEE80211_MLE_SUBELEM_FRAGMENT); + } + + ieee80211_fragment_element(skb, ml_elem_len, WLAN_EID_FRAGMENT); + + info = IEEE80211_SKB_CB(skb); + info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; + + return skb; +} + +int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata, + struct cfg80211_assoc_link *add_links, + u16 rem_links) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_mgd_assoc_data *data = NULL; + struct sta_info *sta; + struct sk_buff *skb; + u16 added_links, new_valid_links; + int link_id, err; + + if (!ieee80211_vif_is_mld(&sdata->vif) || + !(sdata->vif.cfg.mld_capa_op & + IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT)) + return -EINVAL; + + /* No support for concurrent ML reconfiguration operation */ + if (sdata->u.mgd.reconf.added_links || + sdata->u.mgd.reconf.removed_links) + return -EBUSY; + + added_links = 0; + for (link_id = 0; add_links && link_id < IEEE80211_MLD_MAX_NUM_LINKS; + link_id++) { + if (!add_links[link_id].bss) + continue; + + added_links |= BIT(link_id); + } + + sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr); + if (WARN_ON(!sta)) + return -ENOLINK; + + if (rem_links & BIT(sta->sta.deflink.link_id)) + return -EINVAL; + + /* Adding links to the set of valid link is done only after a successful + * ML reconfiguration frame exchange. Here prepare the data for the ML + * reconfiguration frame construction and allocate the required + * resources + */ + if (added_links) { + bool uapsd_supported; + unsigned long userspace_selectors; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + uapsd_supported = true; + ieee80211_ml_reconf_selectors(&userspace_selectors); + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; + link_id++) { + struct ieee80211_supported_band *sband; + struct cfg80211_bss *link_cbss = add_links[link_id].bss; + struct ieee80211_bss *bss; + + if (!link_cbss) + continue; + + bss = (void *)link_cbss->priv; + + if (!bss->wmm_used) { + err = -EINVAL; + goto err_free; + } + + if (link_cbss->channel->band == NL80211_BAND_S1GHZ) { + err = -EINVAL; + goto err_free; + } + + eth_random_addr(data->link[link_id].addr); + data->link[link_id].conn = + ieee80211_conn_settings_unlimited; + sband = + local->hw.wiphy->bands[link_cbss->channel->band]; + + ieee80211_determine_our_sta_mode(sdata, sband, + NULL, true, link_id, + &data->link[link_id].conn); + + data->link[link_id].bss = link_cbss; + data->link[link_id].disabled = + add_links[link_id].disabled; + data->link[link_id].elems = + (u8 *)add_links[link_id].elems; + data->link[link_id].elems_len = + add_links[link_id].elems_len; + + if (!bss->uapsd_supported) + uapsd_supported = false; + + if (data->link[link_id].conn.mode < + IEEE80211_CONN_MODE_EHT) { + err = -EINVAL; + goto err_free; + } + + err = ieee80211_mgd_get_ap_ht_vht_capa(sdata, data, + link_id); + if (err) { + err = -EINVAL; + goto err_free; + } + } + + /* Require U-APSD support to be similar to the current valid + * links + */ + if (uapsd_supported != + !!(sdata->u.mgd.flags & IEEE80211_STA_UAPSD_ENABLED)) { + err = -EINVAL; + goto err_free; + } + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; + link_id++) { + if (!data->link[link_id].bss) + continue; + + /* only used to verify the mode, nothing is allocated */ + err = ieee80211_prep_channel(sdata, NULL, link_id, + data->link[link_id].bss, + true, + &data->link[link_id].conn, + &userspace_selectors); + if (err) + goto err_free; + } + } + + /* link removal is done before the ML reconfiguration frame exchange so + * that these links will not be used between their removal by the AP MLD + * and before the station got the ML reconfiguration response. Based on + * Section 35.3.6.4 in Draft P802.11be_D7.0 the AP MLD should accept the + * link removal request. + */ + if (rem_links) { + u16 new_active_links = sdata->vif.active_links & ~rem_links; + + new_valid_links = sdata->vif.valid_links & ~rem_links; + + /* Should not be left with no valid links to perform the + * ML reconfiguration + */ + if (!new_valid_links || + !(new_valid_links & ~sdata->vif.dormant_links)) { + sdata_info(sdata, "mlo: reconf: no valid links\n"); + err = -EINVAL; + goto err_free; + } + + if (new_active_links != sdata->vif.active_links) { + if (!new_active_links) + new_active_links = + BIT(__ffs(new_valid_links & + ~sdata->vif.dormant_links)); + + err = ieee80211_set_active_links(&sdata->vif, + new_active_links); + if (err) { + sdata_info(sdata, + "mlo: reconf: failed set active links\n"); + goto err_free; + } + } + } + + /* Build the SKB before the link removal as the construction of the + * station info for removed links requires the local address. + * Invalidate the removed links, so that the transmission of the ML + * reconfiguration request frame would not be done using them, as the AP + * is expected to send the ML reconfiguration response frame on the link + * on which the request was received. + */ + skb = ieee80211_build_ml_reconf_req(sdata, data, rem_links); + if (!skb) { + err = -ENOMEM; + goto err_free; + } + + if (rem_links) { + u16 new_dormant_links = sdata->vif.dormant_links & ~rem_links; + + err = ieee80211_vif_set_links(sdata, new_valid_links, + new_dormant_links); + if (err) { + sdata_info(sdata, + "mlo: reconf: failed set valid links\n"); + kfree_skb(skb); + goto err_free; + } + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; + link_id++) { + if (!(rem_links & BIT(link_id))) + continue; + + ieee80211_sta_remove_link(sta, link_id); + } + + /* notify the driver and upper layers */ + ieee80211_vif_cfg_change_notify(sdata, + BSS_CHANGED_MLD_VALID_LINKS); + cfg80211_links_removed(sdata->dev, rem_links); + } + + sdata_info(sdata, "mlo: reconf: adding=0x%x, removed=0x%x\n", + added_links, rem_links); + + ieee80211_tx_skb(sdata, skb); + + sdata->u.mgd.reconf.added_links = added_links; + sdata->u.mgd.reconf.add_links_data = data; + sdata->u.mgd.reconf.removed_links = rem_links; + wiphy_delayed_work_queue(sdata->local->hw.wiphy, + &sdata->u.mgd.reconf.wk, + IEEE80211_ASSOC_TIMEOUT_SHORT); + return 0; + + err_free: + kfree(data); + return err; +} diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c index 279c5143b335..cd318c1c67be 100644 --- a/net/mac80211/parse.c +++ b/net/mac80211/parse.c @@ -44,6 +44,9 @@ struct ieee80211_elems_parse { /* The reconfiguration Multi-Link element in the original elements */ const struct element *ml_reconf_elem; + /* The EPCS Multi-Link element in the original elements */ + const struct element *ml_epcs_elem; + /* * scratch buffer that can be used for various element parsing related * tasks, e.g., element de-fragmentation etc. @@ -159,6 +162,9 @@ ieee80211_parse_extension_element(u32 *crc, case IEEE80211_ML_CONTROL_TYPE_RECONF: elems_parse->ml_reconf_elem = elem; break; + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: + elems_parse->ml_epcs_elem = elem; + break; default: break; } @@ -943,6 +949,27 @@ ieee80211_mle_defrag_reconf(struct ieee80211_elems_parse *elems_parse) elems_parse->scratch_pos += ml_len; } +static void +ieee80211_mle_defrag_epcs(struct ieee80211_elems_parse *elems_parse) +{ + struct ieee802_11_elems *elems = &elems_parse->elems; + ssize_t ml_len; + + ml_len = cfg80211_defragment_element(elems_parse->ml_epcs_elem, + elems->ie_start, + elems->total_len, + elems_parse->scratch_pos, + elems_parse->scratch + + elems_parse->scratch_len - + elems_parse->scratch_pos, + WLAN_EID_FRAGMENT); + if (ml_len < 0) + return; + elems->ml_epcs = (void *)elems_parse->scratch_pos; + elems->ml_epcs_len = ml_len; + elems_parse->scratch_pos += ml_len; +} + struct ieee802_11_elems * ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) { @@ -1001,6 +1028,8 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) ieee80211_mle_defrag_reconf(elems_parse); + ieee80211_mle_defrag_epcs(elems_parse); + if (elems->tim && !elems->parse_error) { const struct ieee80211_tim_ie *tim_ie = elems->tim; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 2bec18fc1b03..1e28efe4203c 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3001,6 +3001,7 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta } IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, fwded_frames); + ieee80211_set_qos_hdr(sdata, fwd_skb); ieee80211_add_pending_skb(local, fwd_skb); rx_accept: @@ -3034,8 +3035,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) check_da = NULL; break; case NL80211_IFTYPE_STATION: - if (!rx->sta || - !test_sta_flag(rx->sta, WLAN_STA_TDLS_PEER)) + if (!test_sta_flag(rx->sta, WLAN_STA_TDLS_PEER)) check_sa = NULL; break; case NL80211_IFTYPE_MESH_POINT: @@ -3819,6 +3819,18 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) u.action.u.ttlm_res)) goto invalid; goto queue; + case WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP: + if (sdata->vif.type != NL80211_IFTYPE_STATION) + break; + + /* The reconfiguration response action frame must + * least one 'Status Duple' entry (3 octets) + */ + if (len < + offsetofend(typeof(*mgmt), + u.action.u.ml_reconf_resp) + 3) + goto invalid; + goto queue; default: break; } @@ -4562,7 +4574,9 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) return ieee80211_is_public_action(hdr, skb->len) || ieee80211_is_probe_req(hdr->frame_control) || ieee80211_is_probe_resp(hdr->frame_control) || - ieee80211_is_beacon(hdr->frame_control); + ieee80211_is_beacon(hdr->frame_control) || + (ieee80211_is_auth(hdr->frame_control) && + ether_addr_equal(sdata->vif.addr, hdr->addr1)); case NL80211_IFTYPE_NAN: /* Currently no frames on NAN interface are allowed */ return false; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index aa22f09e6d14..f83268fa9f92 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -509,6 +509,24 @@ static int sta_info_alloc_link(struct ieee80211_local *local, for (i = 0; i < ARRAY_SIZE(link_info->rx_stats_avg.chain_signal); i++) ewma_signal_init(&link_info->rx_stats_avg.chain_signal[i]); + link_info->rx_omi_bw_rx = IEEE80211_STA_RX_BW_MAX; + link_info->rx_omi_bw_tx = IEEE80211_STA_RX_BW_MAX; + link_info->rx_omi_bw_staging = IEEE80211_STA_RX_BW_MAX; + + /* + * Cause (a) warning(s) if IEEE80211_STA_RX_BW_MAX != 320 + * or if new values are added to the enum. + */ + switch (link_info->cur_max_bandwidth) { + case IEEE80211_STA_RX_BW_20: + case IEEE80211_STA_RX_BW_40: + case IEEE80211_STA_RX_BW_80: + case IEEE80211_STA_RX_BW_160: + case IEEE80211_STA_RX_BW_MAX: + /* intentionally nothing */ + break; + } + return 0; } @@ -1567,7 +1585,7 @@ void sta_info_stop(struct ieee80211_local *local) int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans, - int link_id) + int link_id, struct sta_info *do_not_flush_sta) { struct ieee80211_local *local = sdata->local; struct sta_info *sta, *tmp; @@ -1585,6 +1603,9 @@ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans, (!vlans || sdata->bss != sta->sdata->bss)) continue; + if (sta == do_not_flush_sta) + continue; + if (link_id >= 0 && sta->sta.valid_links && !(sta->sta.valid_links & BIT(link_id))) continue; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 9f89fb5bee37..07b7ec39a52f 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -512,6 +512,10 @@ struct ieee80211_fragment_cache { * @status_stats.avg_ack_signal: average ACK signal * @cur_max_bandwidth: maximum bandwidth to use for TX to the station, * taken from HT/VHT capabilities or VHT operating mode notification + * @rx_omi_bw_rx: RX OMI bandwidth restriction to apply for RX + * @rx_omi_bw_tx: RX OMI bandwidth restriction to apply for TX + * @rx_omi_bw_staging: RX OMI bandwidth restriction to apply later + * during finalize * @debugfs_dir: debug filesystem directory dentry * @pub: public (driver visible) link STA data * TODO Move other link params from sta_info as required for MLD operation @@ -561,6 +565,9 @@ struct link_sta_info { } tx_stats; enum ieee80211_sta_rx_bandwidth cur_max_bandwidth; + enum ieee80211_sta_rx_bandwidth rx_omi_bw_rx, + rx_omi_bw_tx, + rx_omi_bw_staging; #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfs_dir; @@ -899,9 +906,10 @@ void sta_info_stop(struct ieee80211_local *local); * @link_id: if given (>=0), all those STA entries using @link_id only * will be removed. If -1 is passed, all STA entries will be * removed. + * @do_not_flush_sta: a station that shouldn't be flushed. */ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans, - int link_id); + int link_id, struct sta_info *do_not_flush_sta); /** * sta_info_flush - flush matching STA entries from the STA table @@ -916,7 +924,7 @@ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans, static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata, int link_id) { - return __sta_info_flush(sdata, false, link_id); + return __sta_info_flush(sdata, false, link_id, NULL); } void sta_set_rate_info_tx(struct sta_info *sta, diff --git a/net/mac80211/tests/Makefile b/net/mac80211/tests/Makefile index 511dfa226699..0f5336bc7314 100644 --- a/net/mac80211/tests/Makefile +++ b/net/mac80211/tests/Makefile @@ -1,3 +1,3 @@ -mac80211-tests-y += module.o elems.o mfp.o tpe.o +mac80211-tests-y += module.o util.o elems.o mfp.o tpe.o obj-$(CONFIG_MAC80211_KUNIT_TEST) += mac80211-tests.o diff --git a/net/mac80211/tests/util.c b/net/mac80211/tests/util.c new file mode 100644 index 000000000000..0936a73e3617 --- /dev/null +++ b/net/mac80211/tests/util.c @@ -0,0 +1,313 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Utilities for mac80211 unit testing + * + * Copyright (C) 2024 Intel Corporation + */ +#include +#include +#include +#include +#include "util.h" + +#define CHAN2G(_freq) { \ + .band = NL80211_BAND_2GHZ, \ + .center_freq = (_freq), \ + .hw_value = (_freq), \ +} + +static const struct ieee80211_channel channels_2ghz[] = { + CHAN2G(2412), /* Channel 1 */ + CHAN2G(2417), /* Channel 2 */ + CHAN2G(2422), /* Channel 3 */ + CHAN2G(2427), /* Channel 4 */ + CHAN2G(2432), /* Channel 5 */ + CHAN2G(2437), /* Channel 6 */ + CHAN2G(2442), /* Channel 7 */ + CHAN2G(2447), /* Channel 8 */ + CHAN2G(2452), /* Channel 9 */ + CHAN2G(2457), /* Channel 10 */ + CHAN2G(2462), /* Channel 11 */ + CHAN2G(2467), /* Channel 12 */ + CHAN2G(2472), /* Channel 13 */ + CHAN2G(2484), /* Channel 14 */ +}; + +#define CHAN5G(_freq) { \ + .band = NL80211_BAND_5GHZ, \ + .center_freq = (_freq), \ + .hw_value = (_freq), \ +} + +static const struct ieee80211_channel channels_5ghz[] = { + CHAN5G(5180), /* Channel 36 */ + CHAN5G(5200), /* Channel 40 */ + CHAN5G(5220), /* Channel 44 */ + CHAN5G(5240), /* Channel 48 */ +}; + +static const struct ieee80211_rate bitrates[] = { + { .bitrate = 10 }, + { .bitrate = 20, .flags = IEEE80211_RATE_SHORT_PREAMBLE }, + { .bitrate = 55, .flags = IEEE80211_RATE_SHORT_PREAMBLE }, + { .bitrate = 110, .flags = IEEE80211_RATE_SHORT_PREAMBLE }, + { .bitrate = 60 }, + { .bitrate = 90 }, + { .bitrate = 120 }, + { .bitrate = 180 }, + { .bitrate = 240 }, + { .bitrate = 360 }, + { .bitrate = 480 }, + { .bitrate = 540 } +}; + +/* Copied from hwsim except that it only supports 4 EHT streams and STA/P2P mode */ +static const struct ieee80211_sband_iftype_data sband_capa_5ghz[] = { + { + .types_mask = BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_P2P_CLIENT), + .he_cap = { + .has_he = true, + .he_cap_elem = { + .mac_cap_info[0] = + IEEE80211_HE_MAC_CAP0_HTC_HE, + .mac_cap_info[1] = + IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | + IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, + .mac_cap_info[2] = + IEEE80211_HE_MAC_CAP2_BSR | + IEEE80211_HE_MAC_CAP2_MU_CASCADING | + IEEE80211_HE_MAC_CAP2_ACK_EN, + .mac_cap_info[3] = + IEEE80211_HE_MAC_CAP3_OMI_CONTROL | + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, + .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, + .phy_cap_info[0] = + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, + .phy_cap_info[1] = + IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | + IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | + IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | + IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, + .phy_cap_info[2] = + IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | + IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | + IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | + IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | + IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, + + /* Leave all the other PHY capability bytes + * unset, as DCM, beam forming, RU and PPE + * threshold information are not supported + */ + }, + .he_mcs_nss_supp = { + .rx_mcs_80 = cpu_to_le16(0xfffa), + .tx_mcs_80 = cpu_to_le16(0xfffa), + .rx_mcs_160 = cpu_to_le16(0xfffa), + .tx_mcs_160 = cpu_to_le16(0xfffa), + .rx_mcs_80p80 = cpu_to_le16(0xfffa), + .tx_mcs_80p80 = cpu_to_le16(0xfffa), + }, + }, + .eht_cap = { + .has_eht = true, + .eht_cap_elem = { + .mac_cap_info[0] = + IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS | + IEEE80211_EHT_MAC_CAP0_OM_CONTROL | + IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1, + .phy_cap_info[0] = + IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ | + IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI | + IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO | + IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER | + IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE | + IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK, + .phy_cap_info[1] = + IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK | + IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK, + .phy_cap_info[2] = + IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK | + IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK, + .phy_cap_info[3] = + IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK | + IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK | + IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK | + IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK | + IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK | + IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK | + IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK, + .phy_cap_info[4] = + IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO | + IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP | + IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP | + IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI | + IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK, + .phy_cap_info[5] = + IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK | + IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP | + IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP | + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT | + IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK | + IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK, + .phy_cap_info[6] = + IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK | + IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK, + .phy_cap_info[7] = + IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW | + IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ | + IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ | + IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ | + IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ, + }, + + /* For all MCS and bandwidth, set 4 NSS for both Tx and + * Rx + */ + .eht_mcs_nss_supp = { + /* + * As B1 and B2 are set in the supported + * channel width set field in the HE PHY + * capabilities information field include all + * the following MCS/NSS. + */ + .bw._80 = { + .rx_tx_mcs9_max_nss = 0x44, + .rx_tx_mcs11_max_nss = 0x44, + .rx_tx_mcs13_max_nss = 0x44, + }, + .bw._160 = { + .rx_tx_mcs9_max_nss = 0x44, + .rx_tx_mcs11_max_nss = 0x44, + .rx_tx_mcs13_max_nss = 0x44, + }, + }, + /* PPE threshold information is not supported */ + }, + }, +}; + +int t_sdata_init(struct kunit_resource *resource, void *ctx) +{ + struct kunit *test = kunit_get_current_test(); + struct t_sdata *t_sdata; + + t_sdata = kzalloc(sizeof(*t_sdata), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, t_sdata); + + resource->data = t_sdata; + resource->name = "sdata"; + + t_sdata->sdata = kzalloc(sizeof(*t_sdata->sdata), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, t_sdata->sdata); + + t_sdata->wiphy = kzalloc(sizeof(*t_sdata->wiphy), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, t_sdata->wiphy); + + strscpy(t_sdata->sdata->name, "kunit"); + + t_sdata->sdata->local = &t_sdata->local; + t_sdata->sdata->local->hw.wiphy = t_sdata->wiphy; + t_sdata->sdata->wdev.wiphy = t_sdata->wiphy; + t_sdata->sdata->vif.type = NL80211_IFTYPE_STATION; + + t_sdata->sdata->deflink.sdata = t_sdata->sdata; + t_sdata->sdata->deflink.link_id = 0; + + t_sdata->wiphy->bands[NL80211_BAND_2GHZ] = &t_sdata->band_2ghz; + t_sdata->wiphy->bands[NL80211_BAND_5GHZ] = &t_sdata->band_5ghz; + + for (int band = NL80211_BAND_2GHZ; band <= NL80211_BAND_5GHZ; band++) { + struct ieee80211_supported_band *sband; + + sband = t_sdata->wiphy->bands[band]; + sband->band = band; + + sband->bitrates = + kmemdup(bitrates, sizeof(bitrates), GFP_KERNEL); + sband->n_bitrates = ARRAY_SIZE(bitrates); + + /* Initialize channels, feel free to add more channels/bands */ + switch (band) { + case NL80211_BAND_2GHZ: + sband->channels = kmemdup(channels_2ghz, + sizeof(channels_2ghz), + GFP_KERNEL); + sband->n_channels = ARRAY_SIZE(channels_2ghz); + sband->bitrates = kmemdup(bitrates, + sizeof(bitrates), + GFP_KERNEL); + sband->n_bitrates = ARRAY_SIZE(bitrates); + break; + case NL80211_BAND_5GHZ: + sband->channels = kmemdup(channels_5ghz, + sizeof(channels_5ghz), + GFP_KERNEL); + sband->n_channels = ARRAY_SIZE(channels_5ghz); + sband->bitrates = kmemdup(bitrates, + sizeof(bitrates), + GFP_KERNEL); + sband->n_bitrates = ARRAY_SIZE(bitrates); + + sband->vht_cap.vht_supported = true; + sband->vht_cap.cap = + IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ | + IEEE80211_VHT_CAP_RXLDPC | + IEEE80211_VHT_CAP_SHORT_GI_80 | + IEEE80211_VHT_CAP_SHORT_GI_160 | + IEEE80211_VHT_CAP_TXSTBC | + IEEE80211_VHT_CAP_RXSTBC_4 | + IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; + sband->vht_cap.vht_mcs.rx_mcs_map = + cpu_to_le16(IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 | + IEEE80211_VHT_MCS_SUPPORT_0_9 << 2 | + IEEE80211_VHT_MCS_SUPPORT_0_9 << 4 | + IEEE80211_VHT_MCS_SUPPORT_0_9 << 6 | + IEEE80211_VHT_MCS_SUPPORT_0_9 << 8 | + IEEE80211_VHT_MCS_SUPPORT_0_9 << 10 | + IEEE80211_VHT_MCS_SUPPORT_0_9 << 12 | + IEEE80211_VHT_MCS_SUPPORT_0_9 << 14); + sband->vht_cap.vht_mcs.tx_mcs_map = + sband->vht_cap.vht_mcs.rx_mcs_map; + break; + default: + continue; + } + + sband->ht_cap.ht_supported = band != NL80211_BAND_6GHZ; + sband->ht_cap.cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 | + IEEE80211_HT_CAP_GRN_FLD | + IEEE80211_HT_CAP_SGI_20 | + IEEE80211_HT_CAP_SGI_40 | + IEEE80211_HT_CAP_DSSSCCK40; + sband->ht_cap.ampdu_factor = 0x3; + sband->ht_cap.ampdu_density = 0x6; + memset(&sband->ht_cap.mcs, 0, sizeof(sband->ht_cap.mcs)); + sband->ht_cap.mcs.rx_mask[0] = 0xff; + sband->ht_cap.mcs.rx_mask[1] = 0xff; + sband->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED; + } + + ieee80211_set_sband_iftype_data(&t_sdata->band_5ghz, sband_capa_5ghz); + + return 0; +} + +void t_sdata_exit(struct kunit_resource *resource) +{ + struct t_sdata *t_sdata = resource->data; + + kfree(t_sdata->band_2ghz.channels); + kfree(t_sdata->band_2ghz.bitrates); + kfree(t_sdata->band_5ghz.channels); + kfree(t_sdata->band_5ghz.bitrates); + + kfree(t_sdata->sdata); + kfree(t_sdata->wiphy); + + kfree(t_sdata); +} diff --git a/net/mac80211/tests/util.h b/net/mac80211/tests/util.h new file mode 100644 index 000000000000..6615880c123f --- /dev/null +++ b/net/mac80211/tests/util.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Utilities for mac80211 unit testing + * + * Copyright (C) 2024 Intel Corporation + */ +#ifndef __MAC80211_UTILS_H +#define __MAC80211_UTILS_H + +#include "../ieee80211_i.h" + +struct t_sdata { + struct ieee80211_sub_if_data *sdata; + struct wiphy *wiphy; + struct ieee80211_local local; + + void *ctx; + + struct ieee80211_supported_band band_2ghz; + struct ieee80211_supported_band band_5ghz; +}; + +#define T_SDATA(test) ({ \ + struct t_sdata *__t_sdata = \ + kunit_alloc_resource(test, t_sdata_init, \ + t_sdata_exit, \ + GFP_KERNEL, NULL); \ + \ + KUNIT_ASSERT_NOT_NULL(test, __t_sdata); \ + __t_sdata; \ + }) + +int t_sdata_init(struct kunit_resource *resource, void *data); +void t_sdata_exit(struct kunit_resource *resource); + +#endif /* __MAC80211_UTILS_H */ diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 7a4985fc2b16..72fad8ea8bb9 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -2173,13 +2173,14 @@ DEFINE_EVENT(chanswitch_evt, drv_channel_switch_rx_beacon, TRACE_EVENT(drv_get_txpower, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - int dbm, int ret), + unsigned int link_id, int dbm, int ret), - TP_ARGS(local, sdata, dbm, ret), + TP_ARGS(local, sdata, link_id, dbm, ret), TP_STRUCT__entry( LOCAL_ENTRY VIF_ENTRY + __field(unsigned int, link_id) __field(int, dbm) __field(int, ret) ), @@ -2187,13 +2188,14 @@ TRACE_EVENT(drv_get_txpower, TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; + __entry->link_id = link_id; __entry->dbm = dbm; __entry->ret = ret; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " dbm:%d ret:%d", - LOCAL_PR_ARG, VIF_PR_ARG, __entry->dbm, __entry->ret + LOCAL_PR_FMT VIF_PR_FMT " link_id:%d dbm:%d ret:%d", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->link_id, __entry->dbm, __entry->ret ) ); @@ -2588,6 +2590,45 @@ TRACE_EVENT(drv_change_sta_links, * Tracing for API calls that drivers call. */ +TRACE_EVENT(api_return_bool, + TP_PROTO(struct ieee80211_local *local, bool result), + + TP_ARGS(local, result), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(bool, result) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->result = result; + ), + + TP_printk( + LOCAL_PR_FMT " result=%d", + LOCAL_PR_ARG, __entry->result + ) +); + +TRACE_EVENT(api_return_void, + TP_PROTO(struct ieee80211_local *local), + + TP_ARGS(local), + + TP_STRUCT__entry( + LOCAL_ENTRY + ), + + TP_fast_assign( + LOCAL_ASSIGN; + ), + + TP_printk( + LOCAL_PR_FMT, LOCAL_PR_ARG + ) +); + TRACE_EVENT(api_start_tx_ba_session, TP_PROTO(struct ieee80211_sta *sta, u16 tid), @@ -3052,6 +3093,65 @@ TRACE_EVENT(api_request_smps, ) ); +TRACE_EVENT(api_prepare_rx_omi_bw, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct link_sta_info *link_sta, + enum ieee80211_sta_rx_bandwidth bw), + + TP_ARGS(local, sdata, link_sta, bw), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + STA_ENTRY + __field(int, link_id) + __field(u32, bw) + __field(bool, result) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + STA_NAMED_ASSIGN(link_sta->sta); + __entry->link_id = link_sta->link_id; + __entry->bw = bw; + ), + + TP_printk( + LOCAL_PR_FMT " " VIF_PR_FMT " " STA_PR_FMT " link:%d, bw:%d", + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, + __entry->link_id, __entry->bw + ) +); + +TRACE_EVENT(api_finalize_rx_omi_bw, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct link_sta_info *link_sta), + + TP_ARGS(local, sdata, link_sta), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + STA_ENTRY + __field(int, link_id) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + STA_NAMED_ASSIGN(link_sta->sta); + __entry->link_id = link_sta->link_id; + ), + + TP_printk( + LOCAL_PR_FMT " " VIF_PR_FMT " " STA_PR_FMT " link:%d", + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->link_id + ) +); + /* * Tracing for internal functions * (which may also be called in response to driver calls) @@ -3059,49 +3159,55 @@ TRACE_EVENT(api_request_smps, TRACE_EVENT(wake_queue, TP_PROTO(struct ieee80211_local *local, u16 queue, - enum queue_stop_reason reason), + enum queue_stop_reason reason, int refcount), - TP_ARGS(local, queue, reason), + TP_ARGS(local, queue, reason, refcount), TP_STRUCT__entry( LOCAL_ENTRY __field(u16, queue) __field(u32, reason) + __field(int, refcount) ), TP_fast_assign( LOCAL_ASSIGN; __entry->queue = queue; __entry->reason = reason; + __entry->refcount = refcount; ), TP_printk( - LOCAL_PR_FMT " queue:%d, reason:%d", - LOCAL_PR_ARG, __entry->queue, __entry->reason + LOCAL_PR_FMT " queue:%d, reason:%d, refcount: %d", + LOCAL_PR_ARG, __entry->queue, __entry->reason, + __entry->refcount ) ); TRACE_EVENT(stop_queue, TP_PROTO(struct ieee80211_local *local, u16 queue, - enum queue_stop_reason reason), + enum queue_stop_reason reason, int refcount), - TP_ARGS(local, queue, reason), + TP_ARGS(local, queue, reason, refcount), TP_STRUCT__entry( LOCAL_ENTRY __field(u16, queue) __field(u32, reason) + __field(int, refcount) ), TP_fast_assign( LOCAL_ASSIGN; __entry->queue = queue; __entry->reason = reason; + __entry->refcount = refcount; ), TP_printk( - LOCAL_PR_FMT " queue:%d, reason:%d", - LOCAL_PR_ARG, __entry->queue, __entry->reason + LOCAL_PR_FMT " queue:%d, reason:%d, refcount: %d", + LOCAL_PR_ARG, __entry->queue, __entry->reason, + __entry->refcount ) ); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index dc0b74443c8d..f6b631faf4f7 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -437,8 +437,6 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, { struct ieee80211_local *local = hw_to_local(hw); - trace_wake_queue(local, queue, reason); - if (WARN_ON(queue >= hw->queues)) return; @@ -456,6 +454,9 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, if (local->q_stop_reasons[queue][reason] == 0) __clear_bit(reason, &local->queue_stop_reasons[queue]); + trace_wake_queue(local, queue, reason, + local->q_stop_reasons[queue][reason]); + if (local->queue_stop_reasons[queue] != 0) /* someone still has this queue stopped */ return; @@ -502,8 +503,6 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, { struct ieee80211_local *local = hw_to_local(hw); - trace_stop_queue(local, queue, reason); - if (WARN_ON(queue >= hw->queues)) return; @@ -512,6 +511,9 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, else local->q_stop_reasons[queue][reason]++; + trace_stop_queue(local, queue, reason, + local->q_stop_reasons[queue][reason]); + set_bit(reason, &local->queue_stop_reasons[queue]); } @@ -2748,6 +2750,7 @@ u8 *ieee80211_ie_build_he_oper(u8 *pos, const struct cfg80211_chan_def *chandef) { struct ieee80211_he_operation *he_oper; struct ieee80211_he_6ghz_oper *he_6ghz_op; + struct cfg80211_chan_def he_chandef; u32 he_oper_params; u8 ie_len = 1 + sizeof(struct ieee80211_he_operation); @@ -2779,27 +2782,33 @@ u8 *ieee80211_ie_build_he_oper(u8 *pos, const struct cfg80211_chan_def *chandef) if (chandef->chan->band != NL80211_BAND_6GHZ) goto out; + cfg80211_chandef_create(&he_chandef, chandef->chan, NL80211_CHAN_NO_HT); + he_chandef.center_freq1 = chandef->center_freq1; + he_chandef.center_freq2 = chandef->center_freq2; + he_chandef.width = chandef->width; + /* TODO add VHT operational */ he_6ghz_op = (struct ieee80211_he_6ghz_oper *)pos; he_6ghz_op->minrate = 6; /* 6 Mbps */ he_6ghz_op->primary = - ieee80211_frequency_to_channel(chandef->chan->center_freq); + ieee80211_frequency_to_channel(he_chandef.chan->center_freq); he_6ghz_op->ccfs0 = - ieee80211_frequency_to_channel(chandef->center_freq1); - if (chandef->center_freq2) + ieee80211_frequency_to_channel(he_chandef.center_freq1); + if (he_chandef.center_freq2) he_6ghz_op->ccfs1 = - ieee80211_frequency_to_channel(chandef->center_freq2); + ieee80211_frequency_to_channel(he_chandef.center_freq2); else he_6ghz_op->ccfs1 = 0; - switch (chandef->width) { + switch (he_chandef.width) { case NL80211_CHAN_WIDTH_320: - /* - * TODO: mesh operation is not defined over 6GHz 320 MHz - * channels. + /* Downgrade EHT 320 MHz BW to 160 MHz for HE and set new + * center_freq1 */ - WARN_ON(1); - break; + ieee80211_chandef_downgrade(&he_chandef, NULL); + he_6ghz_op->ccfs0 = + ieee80211_frequency_to_channel(he_chandef.center_freq1); + fallthrough; case NL80211_CHAN_WIDTH_160: /* Convert 160 MHz channel width to new style as interop * workaround. @@ -2807,7 +2816,7 @@ u8 *ieee80211_ie_build_he_oper(u8 *pos, const struct cfg80211_chan_def *chandef) he_6ghz_op->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ; he_6ghz_op->ccfs1 = he_6ghz_op->ccfs0; - if (chandef->chan->center_freq < chandef->center_freq1) + if (he_chandef.chan->center_freq < he_chandef.center_freq1) he_6ghz_op->ccfs0 -= 8; else he_6ghz_op->ccfs0 += 8; @@ -3647,31 +3656,6 @@ again: WARN_ON_ONCE(!cfg80211_chandef_valid(c)); } -/* - * Returns true if smps_mode_new is strictly more restrictive than - * smps_mode_old. - */ -bool ieee80211_smps_is_restrictive(enum ieee80211_smps_mode smps_mode_old, - enum ieee80211_smps_mode smps_mode_new) -{ - if (WARN_ON_ONCE(smps_mode_old == IEEE80211_SMPS_AUTOMATIC || - smps_mode_new == IEEE80211_SMPS_AUTOMATIC)) - return false; - - switch (smps_mode_old) { - case IEEE80211_SMPS_STATIC: - return false; - case IEEE80211_SMPS_DYNAMIC: - return smps_mode_new == IEEE80211_SMPS_STATIC; - case IEEE80211_SMPS_OFF: - return smps_mode_new != IEEE80211_SMPS_OFF; - default: - WARN_ON(1); - } - - return false; -} - int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, struct cfg80211_csa_settings *csa_settings) { diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 6a20fa099190..c5c5d16ed6c8 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -350,9 +350,9 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, } /* FIXME: move this to some better location - parses HE/EHT now */ -enum ieee80211_sta_rx_bandwidth -_ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta, - struct cfg80211_chan_def *chandef) +static enum ieee80211_sta_rx_bandwidth +__ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta, + struct cfg80211_chan_def *chandef) { unsigned int link_id = link_sta->link_id; struct ieee80211_sub_if_data *sdata = link_sta->sta->sdata; @@ -423,6 +423,28 @@ _ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta, return IEEE80211_STA_RX_BW_80; } +enum ieee80211_sta_rx_bandwidth +_ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta, + struct cfg80211_chan_def *chandef) +{ + /* + * With RX OMI, also pretend that the STA's capability changed. + * Of course this isn't really true, it didn't change, only our + * RX capability was changed by notifying RX OMI to the STA. + * The purpose, however, is to save power, and that requires + * changing also transmissions to the AP and the chanctx. The + * transmissions depend on link_sta->bandwidth which is set in + * _ieee80211_sta_cur_vht_bw() below, but the chanctx depends + * on the result of this function which is also called by + * _ieee80211_sta_cur_vht_bw(), so we need to do that here as + * well. This is sufficient for the steady state, but during + * the transition we already need to change TX/RX separately, + * so _ieee80211_sta_cur_vht_bw() below applies the _tx one. + */ + return min(__ieee80211_sta_cap_rx_bw(link_sta, chandef), + link_sta->rx_omi_bw_rx); +} + enum nl80211_chan_width ieee80211_sta_cap_chan_bw(struct link_sta_info *link_sta) { @@ -503,8 +525,11 @@ _ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta, rcu_read_unlock(); } - bw = _ieee80211_sta_cap_rx_bw(link_sta, chandef); + /* intentionally do not take rx_bw_omi_rx into account */ + bw = __ieee80211_sta_cap_rx_bw(link_sta, chandef); bw = min(bw, link_sta->cur_max_bandwidth); + /* but do apply rx_omi_bw_tx */ + bw = min(bw, link_sta->rx_omi_bw_tx); /* Don't consider AP's bandwidth for TDLS peers, section 11.23.1 of * IEEE80211-2016 specification makes higher bandwidth operation diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 08dd521a51a5..8f2bff268392 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -194,9 +194,6 @@ int ieee802154_mlme_tx_locked(struct ieee802154_local *local, struct ieee802154_sub_if_data *sdata, struct sk_buff *skb); void ieee802154_mlme_op_post(struct ieee802154_local *local); -int ieee802154_mlme_tx_one(struct ieee802154_local *local, - struct ieee802154_sub_if_data *sdata, - struct sk_buff *skb); int ieee802154_mlme_tx_one_locked(struct ieee802154_local *local, struct ieee802154_sub_if_data *sdata, struct sk_buff *skb); diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index c0e2da5072be..9e4631fade90 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -684,6 +684,10 @@ void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata) ASSERT_RTNL(); mutex_lock(&sdata->local->iflist_mtx); + if (list_empty(&sdata->local->interfaces)) { + mutex_unlock(&sdata->local->iflist_mtx); + return; + } list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 337d6faf0d2a..4d13f18f6f2c 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -178,19 +178,6 @@ void ieee802154_mlme_op_post(struct ieee802154_local *local) ieee802154_release_queue(local); } -int ieee802154_mlme_tx_one(struct ieee802154_local *local, - struct ieee802154_sub_if_data *sdata, - struct sk_buff *skb) -{ - int ret; - - ieee802154_mlme_op_pre(local); - ret = ieee802154_mlme_tx(local, sdata, skb); - ieee802154_mlme_op_post(local); - - return ret; -} - int ieee802154_mlme_tx_one_locked(struct ieee802154_local *local, struct ieee802154_sub_if_data *sdata, struct sk_buff *skb) diff --git a/net/mctp/device.c b/net/mctp/device.c index 26ce34b7e88e..8e0724c56723 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -20,8 +20,7 @@ #include struct mctp_dump_cb { - int h; - int idx; + unsigned long ifindex; size_t a_idx; }; @@ -115,43 +114,29 @@ static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct mctp_dump_cb *mcb = (void *)cb->ctx; struct net *net = sock_net(skb->sk); - struct hlist_head *head; struct net_device *dev; struct ifaddrmsg *hdr; struct mctp_dev *mdev; - int ifindex; - int idx = 0, rc; + int ifindex, rc; hdr = nlmsg_data(cb->nlh); // filter by ifindex if requested ifindex = hdr->ifa_index; rcu_read_lock(); - for (; mcb->h < NETDEV_HASHENTRIES; mcb->h++, mcb->idx = 0) { - idx = 0; - head = &net->dev_index_head[mcb->h]; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx >= mcb->idx && - (ifindex == 0 || ifindex == dev->ifindex)) { - mdev = __mctp_dev_get(dev); - if (mdev) { - rc = mctp_dump_dev_addrinfo(mdev, - skb, cb); - mctp_dev_put(mdev); - // Error indicates full buffer, this - // callback will get retried. - if (rc < 0) - goto out; - } - } - idx++; - // reset for next iteration - mcb->a_idx = 0; - } + for_each_netdev_dump(net, dev, mcb->ifindex) { + if (ifindex && ifindex != dev->ifindex) + continue; + mdev = __mctp_dev_get(dev); + if (!mdev) + continue; + rc = mctp_dump_dev_addrinfo(mdev, skb, cb); + mctp_dev_put(mdev); + if (rc < 0) + break; + mcb->a_idx = 0; } -out: rcu_read_unlock(); - mcb->idx = idx; return skb->len; } @@ -531,9 +516,12 @@ static struct notifier_block mctp_dev_nb = { }; static const struct rtnl_msg_handler mctp_device_rtnl_msg_handlers[] = { - {THIS_MODULE, PF_MCTP, RTM_NEWADDR, mctp_rtm_newaddr, NULL, 0}, - {THIS_MODULE, PF_MCTP, RTM_DELADDR, mctp_rtm_deladdr, NULL, 0}, - {THIS_MODULE, PF_MCTP, RTM_GETADDR, NULL, mctp_dump_addrinfo, 0}, + {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_NEWADDR, + .doit = mctp_rtm_newaddr}, + {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_DELADDR, + .doit = mctp_rtm_deladdr}, + {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_GETADDR, + .dumpit = mctp_dump_addrinfo}, }; int __init mctp_device_init(void) diff --git a/net/mctp/route.c b/net/mctp/route.c index 597e9cf5aa64..3f2bd65ff5e3 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -374,8 +374,13 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) msk = NULL; rc = -EINVAL; - /* we may be receiving a locally-routed packet; drop source sk - * accounting + /* We may be receiving a locally-routed packet; drop source sk + * accounting. + * + * From here, we will either queue the skb - either to a frag_queue, or + * to a receiving socket. When that succeeds, we clear the skb pointer; + * a non-NULL skb on exit will be otherwise unowned, and hence + * kfree_skb()-ed. */ skb_orphan(skb); @@ -434,7 +439,9 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * pending key. */ if (flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(&msk->sk, skb); + rc = sock_queue_rcv_skb(&msk->sk, skb); + if (!rc) + skb = NULL; if (key) { /* we've hit a pending reassembly; not much we * can do but drop it @@ -443,7 +450,6 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) MCTP_TRACE_KEY_REPLIED); key = NULL; } - rc = 0; goto out_unlock; } @@ -470,8 +476,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * this function. */ rc = mctp_key_add(key, msk); - if (!rc) + if (!rc) { trace_mctp_key_acquire(key); + skb = NULL; + } /* we don't need to release key->lock on exit, so * clean up here and suppress the unlock via @@ -489,6 +497,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) key = NULL; } else { rc = mctp_frag_queue(key, skb); + if (!rc) + skb = NULL; } } @@ -503,12 +513,19 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) else rc = mctp_frag_queue(key, skb); + if (rc) + goto out_unlock; + + /* we've queued; the queue owns the skb now */ + skb = NULL; + /* end of message? deliver to socket, and we're done with * the reassembly/response key */ - if (!rc && flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(key->sk, key->reasm_head); - key->reasm_head = NULL; + if (flags & MCTP_HDR_FLAG_EOM) { + rc = sock_queue_rcv_skb(key->sk, key->reasm_head); + if (!rc) + key->reasm_head = NULL; __mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED); key = NULL; } @@ -527,8 +544,7 @@ out_unlock: if (any_key) mctp_key_unref(any_key); out: - if (rc) - kfree_skb(skb); + kfree_skb(skb); return rc; } diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 8551dab1d1e6..17165b86ce22 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -837,6 +837,90 @@ static void mctp_test_route_input_multiple_nets_key(struct kunit *test) mctp_test_route_input_multiple_nets_key_fini(test, &t2); } +/* Input route to socket, using a single-packet message, where sock delivery + * fails. Ensure we're handling the failure appropriately. + */ +static void mctp_test_route_input_sk_fail_single(struct kunit *test) +{ + const struct mctp_hdr hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO); + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct socket *sock; + struct sk_buff *skb; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + /* No rcvbuf space, so delivery should fail. __sock_set_rcvbuf will + * clamp the minimum to SOCK_MIN_RCVBUF, so we open-code this. + */ + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + skb = mctp_test_create_skb(&hdr, 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); + skb_get(skb); + + mctp_test_skb_set_dev(skb, dev); + + /* do route input, which should fail */ + rc = mctp_route_input(&rt->rt, skb); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to skb */ + KUNIT_EXPECT_EQ(test, refcount_read(&skb->users), 1); + kfree_skb(skb); + + __mctp_route_test_fini(test, dev, rt, sock); +} + +/* Input route to socket, using a fragmented message, where sock delivery fails. + */ +static void mctp_test_route_input_sk_fail_frag(struct kunit *test) +{ + const struct mctp_hdr hdrs[2] = { RX_FRAG(FL_S, 0), RX_FRAG(FL_E, 1) }; + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct sk_buff *skbs[2]; + struct socket *sock; + unsigned int i; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + for (i = 0; i < ARRAY_SIZE(skbs); i++) { + skbs[i] = mctp_test_create_skb(&hdrs[i], 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skbs[i]); + skb_get(skbs[i]); + + mctp_test_skb_set_dev(skbs[i], dev); + } + + /* first route input should succeed, we're only queueing to the + * frag list + */ + rc = mctp_route_input(&rt->rt, skbs[0]); + KUNIT_EXPECT_EQ(test, rc, 0); + + /* final route input should fail to deliver to the socket */ + rc = mctp_route_input(&rt->rt, skbs[1]); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to both skbs */ + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[0]->users), 1); + kfree_skb(skbs[0]); + + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[1]->users), 1); + kfree_skb(skbs[1]); + + __mctp_route_test_fini(test, dev, rt, sock); +} + #if IS_ENABLED(CONFIG_MCTP_FLOWS) static void mctp_test_flow_init(struct kunit *test, @@ -1053,6 +1137,8 @@ static struct kunit_case mctp_test_cases[] = { mctp_route_input_sk_reasm_gen_params), KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys, mctp_route_input_sk_keys_gen_params), + KUNIT_CASE(mctp_test_route_input_sk_fail_single), + KUNIT_CASE(mctp_test_route_input_sk_fail_frag), KUNIT_CASE(mctp_test_route_input_multiple_nets_bind), KUNIT_CASE(mctp_test_route_input_multiple_nets_key), KUNIT_CASE(mctp_test_packet_flow), diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 38d8121331d4..2dd81e6c26bd 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -32,6 +32,7 @@ struct mptcp_pernet { unsigned int close_timeout; unsigned int stale_loss_cnt; atomic_t active_disable_times; + u8 syn_retrans_before_tcp_fallback; unsigned long active_disable_stamp; u8 mptcp_enabled; u8 checksum_enabled; @@ -92,6 +93,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; pernet->blackhole_timeout = 3600; + pernet->syn_retrans_before_tcp_fallback = 2; atomic_set(&pernet->active_disable_times, 0); pernet->close_timeout = TCP_TIMEWAIT_LEN; pernet->checksum_enabled = 0; @@ -102,16 +104,15 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) } #ifdef CONFIG_SYSCTL -static int mptcp_set_scheduler(const struct net *net, const char *name) +static int mptcp_set_scheduler(char *scheduler, const char *name) { - struct mptcp_pernet *pernet = mptcp_get_pernet(net); struct mptcp_sched_ops *sched; int ret = 0; rcu_read_lock(); sched = mptcp_sched_find(name); if (sched) - strscpy(pernet->scheduler, name, MPTCP_SCHED_NAME_MAX); + strscpy(scheduler, name, MPTCP_SCHED_NAME_MAX); else ret = -ENOENT; rcu_read_unlock(); @@ -122,7 +123,7 @@ static int mptcp_set_scheduler(const struct net *net, const char *name) static int proc_scheduler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - const struct net *net = current->nsproxy->net_ns; + char (*scheduler)[MPTCP_SCHED_NAME_MAX] = ctl->data; char val[MPTCP_SCHED_NAME_MAX]; struct ctl_table tbl = { .data = val, @@ -130,11 +131,11 @@ static int proc_scheduler(const struct ctl_table *ctl, int write, }; int ret; - strscpy(val, mptcp_get_scheduler(net), MPTCP_SCHED_NAME_MAX); + strscpy(val, *scheduler, MPTCP_SCHED_NAME_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) - ret = mptcp_set_scheduler(net, val); + ret = mptcp_set_scheduler(*scheduler, val); return ret; } @@ -161,7 +162,9 @@ static int proc_blackhole_detect_timeout(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct mptcp_pernet *pernet = mptcp_get_pernet(current->nsproxy->net_ns); + struct mptcp_pernet *pernet = container_of(table->data, + struct mptcp_pernet, + blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); @@ -228,7 +231,7 @@ static struct ctl_table mptcp_sysctl_table[] = { { .procname = "available_schedulers", .maxlen = MPTCP_SCHED_BUF_MAX, - .mode = 0644, + .mode = 0444, .proc_handler = proc_available_schedulers, }, { @@ -244,6 +247,12 @@ static struct ctl_table mptcp_sysctl_table[] = { .proc_handler = proc_blackhole_detect_timeout, .extra1 = SYSCTL_ZERO, }, + { + .procname = "syn_retrans_before_tcp_fallback", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + }, }; static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) @@ -268,6 +277,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) /* table[7] is for available_schedulers which is read-only info */ table[8].data = &pernet->close_timeout; table[9].data = &pernet->blackhole_timeout; + table[10].data = &pernet->syn_retrans_before_tcp_fallback; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); @@ -391,22 +401,26 @@ void mptcp_active_enable(struct sock *sk) void mptcp_active_detect_blackhole(struct sock *ssk, bool expired) { struct mptcp_subflow_context *subflow; - u32 timeouts; if (!sk_is_mptcp(ssk)) return; - timeouts = inet_csk(ssk)->icsk_retransmits; subflow = mptcp_subflow_ctx(ssk); if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) { - if (timeouts == 2 || (timeouts < 2 && expired)) { - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP); + struct net *net = sock_net(ssk); + u8 timeouts, to_max; + + timeouts = inet_csk(ssk)->icsk_retransmits; + to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback; + + if (timeouts == to_max || (timeouts < to_max && expired)) { + MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP); subflow->mpc_drop = 1; mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow); - } else { - subflow->mpc_drop = 0; } + } else if (ssk->sk_state == TCP_SYN_SENT) { + subflow->mpc_drop = 0; } } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 1603b3702e22..fd2de185bc93 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -108,7 +108,6 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_DSS; mp_opt->use_map = 1; mp_opt->mpc_map = 1; - mp_opt->use_ack = 0; mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; } @@ -157,11 +156,6 @@ static void mptcp_parse_option(const struct sk_buff *skb, pr_debug("DSS\n"); ptr++; - /* we must clear 'mpc_map' be able to detect MP_CAPABLE - * map vs DSS map in mptcp_incoming_options(), and reconstruct - * map info accordingly - */ - mp_opt->mpc_map = 0; flags = (*ptr++) & MPTCP_DSS_FLAG_MASK; mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0; mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0; @@ -369,8 +363,11 @@ void mptcp_get_options(const struct sk_buff *skb, const unsigned char *ptr; int length; - /* initialize option status */ - mp_opt->suboptions = 0; + /* Ensure that casting the whole status to u32 is efficient and safe */ + BUILD_BUG_ON(sizeof_field(struct mptcp_options_received, status) != sizeof(u32)); + BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct mptcp_options_received, status), + sizeof(u32))); + *(u32 *)&mp_opt->status = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); @@ -607,7 +604,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, } opts->ext_copy.use_ack = 1; opts->suboptions = OPTION_MPTCP_DSS; - WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk)); /* Add kind/length/subtype/flag overhead if mapping is not populated */ if (dss_size == 0) @@ -667,8 +663,15 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * &echo, &drop_other_suboptions)) return false; + /* + * Later on, mptcp_write_options() will enforce mutually exclusion with + * DSS, bail out if such option is set and we can't drop it. + */ if (drop_other_suboptions) remaining += opt_size; + else if (opts->suboptions & OPTION_MPTCP_DSS) + return false; + len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port); if (remaining < len) return false; @@ -1281,7 +1284,7 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) } MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT); } - return; + goto update_wspace; } if (rcv_wnd_new != rcv_wnd_old) { @@ -1306,6 +1309,9 @@ raise_win: th->window = htons(new_win); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDSHARED); } + +update_wspace: + WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); } __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 7a0f7998376a..572d160edca3 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -107,8 +107,8 @@ static void remote_address(const struct sock_common *skc, #endif } -static bool lookup_subflow_by_saddr(const struct list_head *list, - const struct mptcp_addr_info *saddr) +bool mptcp_lookup_subflow_by_saddr(const struct list_head *list, + const struct mptcp_addr_info *saddr) { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; @@ -1447,8 +1447,8 @@ out_free: return ret; } -static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, - const struct mptcp_addr_info *addr) +bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk, + const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *entry; @@ -1476,7 +1476,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); - ret = remove_anno_list_by_saddr(msk, addr); + ret = mptcp_remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); if (ret) { @@ -1520,7 +1520,7 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, } lock_sock(sk); - remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); + remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); @@ -1633,36 +1633,6 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) return ret; } -/* Called from the userspace PM only */ -void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) -{ - struct mptcp_rm_list alist = { .nr = 0 }; - struct mptcp_pm_addr_entry *entry; - int anno_nr = 0; - - list_for_each_entry(entry, rm_list, list) { - if (alist.nr >= MPTCP_RM_IDS_MAX) - break; - - /* only delete if either announced or matching a subflow */ - if (remove_anno_list_by_saddr(msk, &entry->addr)) - anno_nr++; - else if (!lookup_subflow_by_saddr(&msk->conn_list, - &entry->addr)) - continue; - - alist.ids[alist.nr++] = entry->addr.id; - } - - if (alist.nr) { - spin_lock_bh(&msk->pm.lock); - msk->pm.add_addr_signaled -= anno_nr; - mptcp_pm_remove_addr(msk, &alist); - spin_unlock_bh(&msk->pm.lock); - } -} - -/* Called from the in-kernel PM only */ static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list) { @@ -1671,11 +1641,11 @@ static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk, list_for_each_entry(entry, rm_list, list) { if (slist.nr < MPTCP_RM_IDS_MAX && - lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) + mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); if (alist.nr < MPTCP_RM_IDS_MAX && - remove_anno_list_by_saddr(msk, &entry->addr)) + mptcp_remove_anno_list_by_saddr(msk, &entry->addr)) alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); } @@ -2050,7 +2020,8 @@ int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && - (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL | + MPTCP_PM_ADDR_FLAG_IMPLICIT))) { spin_unlock_bh(&pernet->lock); GENL_SET_ERR_MSG(info, "invalid addr flags"); return -EINVAL; diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index e35178f5205f..a3d477059b11 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -8,6 +8,10 @@ #include "mib.h" #include "mptcp_pm_gen.h" +#define mptcp_for_each_userspace_pm_addr(__msk, __entry) \ + list_for_each_entry(__entry, \ + &((__msk)->pm.userspace_pm_local_addr_list), list) + void mptcp_free_local_addr_list(struct mptcp_sock *msk) { struct mptcp_pm_addr_entry *entry, *tmp; @@ -26,6 +30,19 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk) } } +static struct mptcp_pm_addr_entry * +mptcp_userspace_pm_lookup_addr(struct mptcp_sock *msk, + const struct mptcp_addr_info *addr) +{ + struct mptcp_pm_addr_entry *entry; + + mptcp_for_each_userspace_pm_addr(msk, entry) { + if (mptcp_addresses_equal(&entry->addr, addr, false)) + return entry; + } + return NULL; +} + static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *entry, bool needs_id) @@ -41,7 +58,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, bitmap_zero(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_lock_bh(&msk->pm.lock); - list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { + mptcp_for_each_userspace_pm_addr(msk, e) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); if (addr_match && entry->addr.id == 0 && needs_id) entry->addr.id = e->addr.id; @@ -90,22 +107,20 @@ append_err: static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *addr) { - struct mptcp_pm_addr_entry *entry, *tmp; struct sock *sk = (struct sock *)msk; + struct mptcp_pm_addr_entry *entry; - list_for_each_entry_safe(entry, tmp, &msk->pm.userspace_pm_local_addr_list, list) { - if (mptcp_addresses_equal(&entry->addr, &addr->addr, false)) { - /* TODO: a refcount is needed because the entry can - * be used multiple times (e.g. fullmesh mode). - */ - list_del_rcu(&entry->list); - sock_kfree_s(sk, entry, sizeof(*entry)); - msk->pm.local_addr_used--; - return 0; - } - } + entry = mptcp_userspace_pm_lookup_addr(msk, &addr->addr); + if (!entry) + return -EINVAL; - return -EINVAL; + /* TODO: a refcount is needed because the entry can + * be used multiple times (e.g. fullmesh mode). + */ + list_del_rcu(&entry->list); + sock_kfree_s(sk, entry, sizeof(*entry)); + msk->pm.local_addr_used--; + return 0; } static struct mptcp_pm_addr_entry * @@ -113,7 +128,7 @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id) { struct mptcp_pm_addr_entry *entry; - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + mptcp_for_each_userspace_pm_addr(msk, entry) { if (entry->addr.id == id) return entry; } @@ -123,17 +138,12 @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id) int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { - struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry; + struct mptcp_pm_addr_entry *entry = NULL, new_entry; __be16 msk_sport = ((struct inet_sock *) inet_sk((struct sock *)msk))->inet_sport; spin_lock_bh(&msk->pm.lock); - list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { - if (mptcp_addresses_equal(&e->addr, skc, false)) { - entry = e; - break; - } - } + entry = mptcp_userspace_pm_lookup_addr(msk, skc); spin_unlock_bh(&msk->pm.lock); if (entry) return entry->addr.id; @@ -153,50 +163,60 @@ bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { struct mptcp_pm_addr_entry *entry; - bool backup = false; + bool backup; spin_lock_bh(&msk->pm.lock); - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { - if (mptcp_addresses_equal(&entry->addr, skc, false)) { - backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); - break; - } - } + entry = mptcp_userspace_pm_lookup_addr(msk, skc); + backup = entry && !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); spin_unlock_bh(&msk->pm.lock); return backup; } -int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) +static struct mptcp_sock *mptcp_userspace_pm_get_sock(const struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; + struct mptcp_sock *msk; + + if (!token) { + GENL_SET_ERR_MSG(info, "missing required token"); + return NULL; + } + + msk = mptcp_token_get_sock(genl_info_net(info), nla_get_u32(token)); + if (!msk) { + NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + return NULL; + } + + if (!mptcp_pm_is_userspace(msk)) { + GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); + sock_put((struct sock *)msk); + return NULL; + } + + return msk; +} + +int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) +{ struct nlattr *addr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct mptcp_pm_addr_entry addr_val; struct mptcp_sock *msk; int err = -EINVAL; struct sock *sk; - u32 token_val; - if (!addr || !token) { - GENL_SET_ERR_MSG(info, "missing required inputs"); + if (!addr) { + GENL_SET_ERR_MSG(info, "missing required address"); return err; } - token_val = nla_get_u32(token); - - msk = mptcp_token_get_sock(sock_net(skb->sk), token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return err; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto announce_err; - } - err = mptcp_pm_parse_entry(addr, info, true, &addr_val); if (err < 0) { GENL_SET_ERR_MSG(info, "error parsing local address"); @@ -267,40 +287,48 @@ remove_err: return err; } +void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *entry) +{ + struct mptcp_rm_list alist = { .nr = 0 }; + int anno_nr = 0; + + /* only delete if either announced or matching a subflow */ + if (mptcp_remove_anno_list_by_saddr(msk, &entry->addr)) + anno_nr++; + else if (!mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) + return; + + alist.ids[alist.nr++] = entry->addr.id; + + spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= anno_nr; + mptcp_pm_remove_addr(msk, &alist); + spin_unlock_bh(&msk->pm.lock); +} + int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *id = info->attrs[MPTCP_PM_ATTR_LOC_ID]; struct mptcp_pm_addr_entry *match; - struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; - LIST_HEAD(free_list); int err = -EINVAL; struct sock *sk; - u32 token_val; u8 id_val; - if (!id || !token) { - GENL_SET_ERR_MSG(info, "missing required inputs"); + if (!id) { + GENL_SET_ERR_MSG(info, "missing required ID"); return err; } id_val = nla_get_u8(id); - token_val = nla_get_u32(token); - msk = mptcp_token_get_sock(sock_net(skb->sk), token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return err; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto out; - } - if (id_val == 0) { err = mptcp_userspace_pm_remove_id_zero_address(msk, info); goto out; @@ -317,16 +345,14 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) goto out; } - list_move(&match->list, &free_list); + list_del_rcu(&match->list); spin_unlock_bh(&msk->pm.lock); - mptcp_pm_remove_addrs(msk, &free_list); + mptcp_pm_remove_addr_entry(msk, match); release_sock(sk); - list_for_each_entry_safe(match, entry, &free_list, list) { - sock_kfree_s(sk, match, sizeof(*match)); - } + sock_kfree_s(sk, match, sizeof(*match)); err = 0; out: @@ -337,7 +363,6 @@ out: int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct mptcp_pm_addr_entry entry = { 0 }; struct mptcp_addr_info addr_r; @@ -345,28 +370,18 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) struct mptcp_sock *msk; int err = -EINVAL; struct sock *sk; - u32 token_val; - if (!laddr || !raddr || !token) { - GENL_SET_ERR_MSG(info, "missing required inputs"); + if (!laddr || !raddr) { + GENL_SET_ERR_MSG(info, "missing required address(es)"); return err; } - token_val = nla_get_u32(token); - - msk = mptcp_token_get_sock(genl_info_net(info), token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return err; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto create_err; - } - err = mptcp_pm_parse_entry(laddr, info, true, &entry); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr"); @@ -469,36 +484,25 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk, int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR]; - struct mptcp_addr_info addr_l; + struct mptcp_pm_addr_entry addr_l; struct mptcp_addr_info addr_r; struct mptcp_sock *msk; struct sock *sk, *ssk; int err = -EINVAL; - u32 token_val; - if (!laddr || !raddr || !token) { - GENL_SET_ERR_MSG(info, "missing required inputs"); + if (!laddr || !raddr) { + GENL_SET_ERR_MSG(info, "missing required address(es)"); return err; } - token_val = nla_get_u32(token); - - msk = mptcp_token_get_sock(genl_info_net(info), token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return err; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto destroy_err; - } - - err = mptcp_pm_parse_addr(laddr, info, &addr_l); + err = mptcp_pm_parse_entry(laddr, info, true, &addr_l); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr"); goto destroy_err; @@ -511,43 +515,41 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info } #if IS_ENABLED(CONFIG_MPTCP_IPV6) - if (addr_l.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) { - ipv6_addr_set_v4mapped(addr_l.addr.s_addr, &addr_l.addr6); - addr_l.family = AF_INET6; + if (addr_l.addr.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) { + ipv6_addr_set_v4mapped(addr_l.addr.addr.s_addr, &addr_l.addr.addr6); + addr_l.addr.family = AF_INET6; } - if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr6)) { + if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr.addr6)) { ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6); addr_r.family = AF_INET6; } #endif - if (addr_l.family != addr_r.family) { + if (addr_l.addr.family != addr_r.family) { GENL_SET_ERR_MSG(info, "address families do not match"); err = -EINVAL; goto destroy_err; } - if (!addr_l.port || !addr_r.port) { + if (!addr_l.addr.port || !addr_r.port) { GENL_SET_ERR_MSG(info, "missing local or remote port"); err = -EINVAL; goto destroy_err; } lock_sock(sk); - ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r); - if (ssk) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); - struct mptcp_pm_addr_entry entry = { .addr = addr_l }; - - spin_lock_bh(&msk->pm.lock); - mptcp_userspace_pm_delete_local_addr(msk, &entry); - spin_unlock_bh(&msk->pm.lock); - mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN); - mptcp_close_ssk(sk, ssk, subflow); - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); - err = 0; - } else { + ssk = mptcp_nl_find_ssk(msk, &addr_l.addr, &addr_r); + if (!ssk) { err = -ESRCH; + goto release_sock; } + + spin_lock_bh(&msk->pm.lock); + mptcp_userspace_pm_delete_local_addr(msk, &addr_l); + spin_unlock_bh(&msk->pm.lock); + mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN); + mptcp_close_ssk(sk, ssk, mptcp_subflow_ctx(ssk)); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); +release_sock: release_sock(sk); destroy_err: @@ -560,31 +562,19 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info) struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, }; struct mptcp_pm_addr_entry rem = { .addr = { .family = AF_UNSPEC }, }; struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; - struct net *net = sock_net(skb->sk); struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; int ret = -EINVAL; struct sock *sk; - u32 token_val; u8 bkup = 0; - token_val = nla_get_u32(token); - - msk = mptcp_token_get_sock(net, token_val); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return ret; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "userspace PM not selected"); - goto set_flags_err; - } - ret = mptcp_pm_parse_entry(attr, info, false, &loc); if (ret < 0) goto set_flags_err; @@ -606,13 +596,12 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info) bkup = 1; spin_lock_bh(&msk->pm.lock); - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { - if (mptcp_addresses_equal(&entry->addr, &loc.addr, false)) { - if (bkup) - entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; - else - entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; - } + entry = mptcp_userspace_pm_lookup_addr(msk, &loc.addr); + if (entry) { + if (bkup) + entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; + else + entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; } spin_unlock_bh(&msk->pm.lock); @@ -632,33 +621,23 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, DECLARE_BITMAP(map, MPTCP_PM_MAX_ADDR_ID + 1); } *bitmap; const struct genl_info *info = genl_info_dump(cb); - struct net *net = sock_net(msg->sk); struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; - struct nlattr *token; int ret = -EINVAL; struct sock *sk; void *hdr; bitmap = (struct id_bitmap *)cb->ctx; - token = info->attrs[MPTCP_PM_ATTR_TOKEN]; - msk = mptcp_token_get_sock(net, nla_get_u32(token)); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return ret; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto out; - } - lock_sock(sk); spin_lock_bh(&msk->pm.lock); - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + mptcp_for_each_userspace_pm_addr(msk, entry) { if (test_bit(entry->addr.id, bitmap->map)) continue; @@ -680,7 +659,6 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, release_sock(sk); ret = msg->len; -out: sock_put(sk); return ret; } @@ -689,28 +667,19 @@ int mptcp_userspace_pm_get_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct mptcp_pm_addr_entry addr, *entry; - struct net *net = sock_net(skb->sk); struct mptcp_sock *msk; struct sk_buff *msg; int ret = -EINVAL; struct sock *sk; void *reply; - msk = mptcp_token_get_sock(net, nla_get_u32(token)); - if (!msk) { - NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + msk = mptcp_userspace_pm_get_sock(info); + if (!msk) return ret; - } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) { - GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto out; - } - ret = mptcp_pm_parse_entry(attr, info, false, &addr); if (ret < 0) goto out; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 08a72242428c..6bd819047470 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -47,7 +47,7 @@ static void __mptcp_destroy_sock(struct sock *sk); static void mptcp_check_send_data_fin(struct sock *sk); DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); -static struct net_device mptcp_napi_dev; +static struct net_device *mptcp_napi_dev; /* Returns end sequence number of the receiver's advertised window */ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) @@ -136,6 +136,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, int delta; if (MPTCP_SKB_CB(from)->offset || + ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) || !skb_try_coalesce(to, from, &fragstolen, &delta)) return false; @@ -528,13 +529,13 @@ static void mptcp_send_ack(struct mptcp_sock *msk) mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } -static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied) { bool slow; slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) - tcp_cleanup_rbuf(ssk, 1); + tcp_cleanup_rbuf(ssk, copied); unlock_sock_fast(ssk, slow); } @@ -551,7 +552,7 @@ static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } -static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) +static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied) { int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; @@ -559,14 +560,14 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) int space = __mptcp_space(sk); bool cleanup, rx_empty; - cleanup = (space > 0) && (space >= (old_space << 1)); - rx_empty = !__mptcp_rmem(sk); + cleanup = (space > 0) && (space >= (old_space << 1)) && copied; + rx_empty = !__mptcp_rmem(sk) && copied; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) - mptcp_subflow_cleanup_rbuf(ssk); + mptcp_subflow_cleanup_rbuf(ssk, copied); } } @@ -1766,8 +1767,10 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, * see mptcp_disconnect(). * Attempt it again outside the problematic scope. */ - if (!mptcp_disconnect(sk, 0)) + if (!mptcp_disconnect(sk, 0)) { + sk->sk_disconnects++; sk->sk_socket->state = SS_UNCONNECTED; + } } inet_clear_bit(DEFER_CONNECT, sk); @@ -1939,6 +1942,8 @@ do_error: goto out; } +static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); + static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, struct msghdr *msg, size_t len, int flags, @@ -1992,6 +1997,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, break; } + mptcp_rcv_space_adjust(msk, copied); return copied; } @@ -2217,9 +2223,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, copied += bytes_read; - /* be sure to advertise window change */ - mptcp_cleanup_rbuf(msk); - if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) continue; @@ -2268,7 +2271,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } pr_debug("block timeout %ld\n", timeo); - mptcp_rcv_space_adjust(msk, copied); + mptcp_cleanup_rbuf(msk, copied); err = sk_wait_data(sk, &timeo, NULL); if (err < 0) { err = copied ? : err; @@ -2276,7 +2279,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } - mptcp_rcv_space_adjust(msk, copied); + mptcp_cleanup_rbuf(msk, copied); out_err: if (cmsg_flags && copied >= 0) { @@ -4146,11 +4149,13 @@ void __init mptcp_proto_init(void) if (percpu_counter_init(&mptcp_sockets_allocated, 0, GFP_KERNEL)) panic("Failed to allocate MPTCP pcpu counter\n"); - init_dummy_netdev(&mptcp_napi_dev); + mptcp_napi_dev = alloc_netdev_dummy(0); + if (!mptcp_napi_dev) + panic("Failed to allocate MPTCP dummy netdev\n"); for_each_possible_cpu(cpu) { delegated = per_cpu_ptr(&mptcp_delegated_actions, cpu); INIT_LIST_HEAD(&delegated->head); - netif_napi_add_tx(&mptcp_napi_dev, &delegated->napi, + netif_napi_add_tx(mptcp_napi_dev, &delegated->napi, mptcp_napi_poll); napi_enable(&delegated->napi); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index a93e661ef5c4..f6a207958459 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -149,22 +149,24 @@ struct mptcp_options_received { u32 subflow_seq; u16 data_len; __sum16 csum; - u16 suboptions; + struct_group(status, + u16 suboptions; + u16 use_map:1, + dsn64:1, + data_fin:1, + use_ack:1, + ack64:1, + mpc_map:1, + reset_reason:4, + reset_transient:1, + echo:1, + backup:1, + deny_join_id0:1, + __unused:2; + ); + u8 join_id; u32 token; u32 nonce; - u16 use_map:1, - dsn64:1, - data_fin:1, - use_ack:1, - ack64:1, - mpc_map:1, - reset_reason:4, - reset_transient:1, - echo:1, - backup:1, - deny_join_id0:1, - __unused:2; - u8 join_id; u64 thmac; u8 hmac[MPTCPOPT_HMAC_LEN]; struct mptcp_addr_info addr; @@ -760,10 +762,15 @@ static inline u64 mptcp_data_avail(const struct mptcp_sock *msk) static inline bool mptcp_epollin_ready(const struct sock *sk) { + u64 data_avail = mptcp_data_avail(mptcp_sk(sk)); + + if (!data_avail) + return false; + /* mptcp doesn't have to deal with small skbs in the receive queue, - * at it can always coalesce them + * as it can always coalesce them */ - return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) || + return (data_avail >= sk->sk_rcvlowat) || (mem_cgroup_sockets_enabled && sk->sk_memcg && mem_cgroup_under_socket_pressure(sk->sk_memcg)) || READ_ONCE(tcp_memory_pressure); @@ -1027,6 +1034,10 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, struct mptcp_pm_add_entry * mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, const struct mptcp_addr_info *addr); +bool mptcp_lookup_subflow_by_saddr(const struct list_head *list, + const struct mptcp_addr_info *saddr); +bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk, + const struct mptcp_addr_info *addr); int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info); int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info); int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info); @@ -1034,7 +1045,8 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); -void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); +void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *entry); void mptcp_free_local_addr_list(struct mptcp_sock *msk); diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index ef0f8f73826f..4e0842df5234 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -289,6 +289,7 @@ enum { ncsi_dev_state_config_sp = 0x0301, ncsi_dev_state_config_cis, ncsi_dev_state_config_oem_gma, + ncsi_dev_state_config_apply_mac, ncsi_dev_state_config_clear_vids, ncsi_dev_state_config_svf, ncsi_dev_state_config_ev, @@ -322,6 +323,7 @@ struct ncsi_dev_priv { #define NCSI_DEV_RESHUFFLE 4 #define NCSI_DEV_RESET 8 /* Reset state of NC */ unsigned int gma_flag; /* OEM GMA flag */ + struct sockaddr pending_mac; /* MAC address received from GMA */ spinlock_t lock; /* Protect the NCSI device */ unsigned int package_probe_id;/* Current ID during probe */ unsigned int package_num; /* Number of packages */ diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 5cf55bde366d..7891a537bddd 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1038,7 +1038,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) : ncsi_dev_state_config_clear_vids; break; case ncsi_dev_state_config_oem_gma: - nd->state = ncsi_dev_state_config_clear_vids; + nd->state = ncsi_dev_state_config_apply_mac; nca.package = np->id; nca.channel = nc->id; @@ -1050,10 +1050,22 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) nca.type = NCSI_PKT_CMD_OEM; ret = ncsi_gma_handler(&nca, nc->version.mf_id); } - if (ret < 0) + if (ret < 0) { + nd->state = ncsi_dev_state_config_clear_vids; schedule_work(&ndp->work); + } break; + case ncsi_dev_state_config_apply_mac: + rtnl_lock(); + ret = dev_set_mac_address(dev, &ndp->pending_mac, NULL); + rtnl_unlock(); + if (ret < 0) + netdev_warn(dev, "NCSI: 'Writing MAC address to device failed\n"); + + nd->state = ncsi_dev_state_config_clear_vids; + + fallthrough; case ncsi_dev_state_config_clear_vids: case ncsi_dev_state_config_svf: case ncsi_dev_state_config_ev: @@ -1373,6 +1385,12 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) nd->state = ncsi_dev_state_probe_package; break; case ncsi_dev_state_probe_package: + if (ndp->package_probe_id >= 8) { + /* Last package probed, finishing */ + ndp->flags |= NCSI_DEV_PROBED; + break; + } + ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_SP; @@ -1489,13 +1507,8 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) if (ret) goto error; - /* Probe next package */ + /* Probe next package after receiving response */ ndp->package_probe_id++; - if (ndp->package_probe_id >= 8) { - /* Probe finished */ - ndp->flags |= NCSI_DEV_PROBED; - break; - } nd->state = ncsi_dev_state_probe_package; ndp->active_package = NULL; break; diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index e28be33bdf2c..4a8ce2949fae 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -628,16 +628,14 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr) static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id) { struct ncsi_dev_priv *ndp = nr->ndp; + struct sockaddr *saddr = &ndp->pending_mac; struct net_device *ndev = ndp->ndev.dev; struct ncsi_rsp_oem_pkt *rsp; - struct sockaddr saddr; u32 mac_addr_off = 0; - int ret = 0; /* Get the response header */ rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp); - saddr.sa_family = ndev->type; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; if (mfr_id == NCSI_OEM_MFR_BCM_ID) mac_addr_off = BCM_MAC_ADDR_OFFSET; @@ -646,22 +644,17 @@ static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id) else if (mfr_id == NCSI_OEM_MFR_INTEL_ID) mac_addr_off = INTEL_MAC_ADDR_OFFSET; - memcpy(saddr.sa_data, &rsp->data[mac_addr_off], ETH_ALEN); + saddr->sa_family = ndev->type; + memcpy(saddr->sa_data, &rsp->data[mac_addr_off], ETH_ALEN); if (mfr_id == NCSI_OEM_MFR_BCM_ID || mfr_id == NCSI_OEM_MFR_INTEL_ID) - eth_addr_inc((u8 *)saddr.sa_data); - if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + eth_addr_inc((u8 *)saddr->sa_data); + if (!is_valid_ether_addr((const u8 *)saddr->sa_data)) return -ENXIO; /* Set the flag for GMA command which should only be called once */ ndp->gma_flag = 1; - rtnl_lock(); - ret = dev_set_mac_address(ndev, &saddr, NULL); - rtnl_unlock(); - if (ret < 0) - netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); - - return ret; + return 0; } /* Response handler for Mellanox card */ @@ -1096,14 +1089,12 @@ static int ncsi_rsp_handler_netlink(struct ncsi_request *nr) static int ncsi_rsp_handler_gmcma(struct ncsi_request *nr) { struct ncsi_dev_priv *ndp = nr->ndp; + struct sockaddr *saddr = &ndp->pending_mac; struct net_device *ndev = ndp->ndev.dev; struct ncsi_rsp_gmcma_pkt *rsp; - struct sockaddr saddr; - int ret = -1; int i; rsp = (struct ncsi_rsp_gmcma_pkt *)skb_network_header(nr->rsp); - saddr.sa_family = ndev->type; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netdev_info(ndev, "NCSI: Received %d provisioned MAC addresses\n", @@ -1115,20 +1106,20 @@ static int ncsi_rsp_handler_gmcma(struct ncsi_request *nr) rsp->addresses[i][4], rsp->addresses[i][5]); } + saddr->sa_family = ndev->type; for (i = 0; i < rsp->address_count; i++) { - memcpy(saddr.sa_data, &rsp->addresses[i], ETH_ALEN); - ret = ndev->netdev_ops->ndo_set_mac_address(ndev, &saddr); - if (ret < 0) { + if (!is_valid_ether_addr(rsp->addresses[i])) { netdev_warn(ndev, "NCSI: Unable to assign %pM to device\n", - saddr.sa_data); + rsp->addresses[i]); continue; } - netdev_warn(ndev, "NCSI: Set MAC address to %pM\n", saddr.sa_data); + memcpy(saddr->sa_data, rsp->addresses[i], ETH_ALEN); + netdev_warn(ndev, "NCSI: Will set MAC address to %pM\n", saddr->sa_data); break; } - ndp->gma_flag = ret == 0; - return ret; + ndp->gma_flag = 1; + return 0; } static struct ncsi_rsp_handler { diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index bfae7066936b..db794fe1300e 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -611,6 +611,8 @@ init_list_set(struct net *net, struct ip_set *set, u32 size) return true; } +static struct lock_class_key list_set_lockdep_key; + static int list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) @@ -627,6 +629,7 @@ list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (size < IP_SET_LIST_MIN_SIZE) size = IP_SET_LIST_MIN_SIZE; + lockdep_set_class(&set->lock, &list_set_lockdep_key); set->variant = &set_variant; set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem), __alignof__(struct set_elem)); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 98d7dbe3d787..20a1727e2457 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1046,28 +1046,35 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, #ifdef CONFIG_PROC_FS struct ip_vs_iter_state { struct seq_net_private p; - struct hlist_head *l; + unsigned int bucket; + unsigned int skip_elems; }; -static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) +static void *ip_vs_conn_array(struct ip_vs_iter_state *iter) { int idx; struct ip_vs_conn *cp; - struct ip_vs_iter_state *iter = seq->private; - for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { + for (idx = iter->bucket; idx < ip_vs_conn_tab_size; idx++) { + unsigned int skip = 0; + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { /* __ip_vs_conn_get() is not needed by * ip_vs_conn_seq_show and ip_vs_conn_sync_seq_show */ - if (pos-- == 0) { - iter->l = &ip_vs_conn_tab[idx]; + if (skip >= iter->skip_elems) { + iter->bucket = idx; return cp; } + + ++skip; } + + iter->skip_elems = 0; cond_resched_rcu(); } + iter->bucket = idx; return NULL; } @@ -1076,9 +1083,14 @@ static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos) { struct ip_vs_iter_state *iter = seq->private; - iter->l = NULL; rcu_read_lock(); - return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN; + if (*pos == 0) { + iter->skip_elems = 0; + iter->bucket = 0; + return SEQ_START_TOKEN; + } + + return ip_vs_conn_array(iter); } static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) @@ -1086,28 +1098,22 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct ip_vs_conn *cp = v; struct ip_vs_iter_state *iter = seq->private; struct hlist_node *e; - struct hlist_head *l = iter->l; - int idx; ++*pos; if (v == SEQ_START_TOKEN) - return ip_vs_conn_array(seq, 0); + return ip_vs_conn_array(iter); /* more on same hash chain? */ e = rcu_dereference(hlist_next_rcu(&cp->c_list)); - if (e) + if (e) { + iter->skip_elems++; return hlist_entry(e, struct ip_vs_conn, c_list); - - idx = l - ip_vs_conn_tab; - while (++idx < ip_vs_conn_tab_size) { - hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { - iter->l = &ip_vs_conn_tab[idx]; - return cp; - } - cond_resched_rcu(); } - iter->l = NULL; - return NULL; + + iter->skip_elems = 0; + iter->bucket++; + + return ip_vs_conn_array(iter); } static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v) @@ -1495,8 +1501,8 @@ int __init ip_vs_conn_init(void) max_avail -= 2; /* ~4 in hash row */ max_avail -= 1; /* IPVS up to 1/2 of mem */ max_avail -= order_base_2(sizeof(struct ip_vs_conn)); - max = clamp(max, min, max_avail); - ip_vs_conn_tab_bits = clamp_val(ip_vs_conn_tab_bits, min, max); + max = clamp(max_avail, min, max); + ip_vs_conn_tab_bits = clamp(ip_vs_conn_tab_bits, min, max); ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index d011d2eb0848..7be4c35e4795 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -106,7 +106,7 @@ static int amanda_help(struct sk_buff *skb, /* increase the UDP timeout of the master connection as replies from * Amanda clients to the server can be quite delayed */ - nf_ct_refresh(ct, skb, master_timeout * HZ); + nf_ct_refresh(ct, master_timeout * HZ); /* No data? */ dataoff = protoff + sizeof(struct udphdr); diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index cfa0fe0356de..a7552a46d6ac 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -75,7 +75,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, nf_ct_expect_related(exp, 0); nf_ct_expect_put(exp); - nf_ct_refresh(ct, skb, timeout * HZ); + nf_ct_refresh(ct, timeout * HZ); out: return NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 9db3e2b0b1c3..7f8b245e287a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1544,12 +1544,6 @@ static void gc_worker(struct work_struct *work) tmp = nf_ct_tuplehash_to_ctrack(h); - if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) { - nf_ct_offload_timeout(tmp); - if (!nf_conntrack_max95) - continue; - } - if (expired_count > GC_SCAN_EXPIRED_MAX) { rcu_read_unlock(); @@ -2089,9 +2083,8 @@ EXPORT_SYMBOL_GPL(nf_conntrack_in); /* Refresh conntrack for this many jiffies and do accounting if do_acct is 1 */ void __nf_ct_refresh_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - const struct sk_buff *skb, u32 extra_jiffies, - bool do_acct) + unsigned int bytes) { /* Only update if this is not a fixed timeout */ if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) @@ -2104,8 +2097,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, if (READ_ONCE(ct->timeout) != extra_jiffies) WRITE_ONCE(ct->timeout, extra_jiffies); acct: - if (do_acct) - nf_ct_acct_update(ct, CTINFO2DIR(ctinfo), skb->len); + if (bytes) + nf_ct_acct_update(ct, CTINFO2DIR(ctinfo), bytes); } EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct); @@ -2517,12 +2510,15 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) struct hlist_nulls_head *hash; unsigned int nr_slots, i; - if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head))) + if (*sizep > (INT_MAX / sizeof(struct hlist_nulls_head))) return NULL; BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); + if (nr_slots > (INT_MAX / sizeof(struct hlist_nulls_head))) + return NULL; + hash = kvcalloc(nr_slots, sizeof(struct hlist_nulls_head), GFP_KERNEL); if (hash && nulls) diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 69948e1d6974..af68c64acaab 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -162,6 +162,14 @@ static int __nf_conntrack_eventmask_report(struct nf_conntrack_ecache *e, return ret; } +static void nf_ct_ecache_tstamp_refresh(struct nf_conntrack_ecache *e) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + if (local64_read(&e->timestamp)) + local64_set(&e->timestamp, ktime_get_real_ns()); +#endif +} + int nf_conntrack_eventmask_report(unsigned int events, struct nf_conn *ct, u32 portid, int report) { @@ -186,6 +194,8 @@ int nf_conntrack_eventmask_report(unsigned int events, struct nf_conn *ct, /* This is a resent of a destroy event? If so, skip missed */ missed = e->portid ? 0 : e->missed; + nf_ct_ecache_tstamp_refresh(e); + ret = __nf_conntrack_eventmask_report(e, events, missed, &item); if (unlikely(ret < 0 && (events & (1 << IPCT_DESTROY)))) { /* This is a destroy event that has been triggered by a process, @@ -297,6 +307,18 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state) } } +static void nf_ct_ecache_tstamp_new(const struct nf_conn *ct, struct nf_conntrack_ecache *e) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + u64 ts = 0; + + if (nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP)) + ts = ktime_get_real_ns(); + + local64_set(&e->timestamp, ts); +#endif +} + bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) { struct net *net = nf_ct_net(ct); @@ -326,6 +348,7 @@ bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp e = nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp); if (e) { + nf_ct_ecache_tstamp_new(ct, e); e->ctmask = ctmask; e->expmask = expmask; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 5a9bce24f3c3..14f73872f647 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1385,7 +1385,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, if (info->timeout > 0) { pr_debug("nf_ct_ras: set RAS connection timeout to " "%u seconds\n", info->timeout); - nf_ct_refresh(ct, skb, info->timeout * HZ); + nf_ct_refresh(ct, info->timeout * HZ); /* Set expect timeout */ spin_lock_bh(&nf_conntrack_expect_lock); @@ -1433,7 +1433,7 @@ static int process_urq(struct sk_buff *skb, struct nf_conn *ct, info->sig_port[!dir] = 0; /* Give it 30 seconds for UCF or URJ */ - nf_ct_refresh(ct, skb, 30 * HZ); + nf_ct_refresh(ct, 30 * HZ); return 0; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 36168f8b6efa..db23876a6016 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -357,11 +357,11 @@ nla_put_failure: static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_secctx; - int len, ret; - char *secctx; + struct lsm_context ctx; + int ret; - ret = security_secid_to_secctx(ct->secmark, &secctx, &len); - if (ret) + ret = security_secid_to_secctx(ct->secmark, &ctx); + if (ret < 0) return 0; ret = -1; @@ -369,13 +369,13 @@ static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) if (!nest_secctx) goto nla_put_failure; - if (nla_put_string(skb, CTA_SECCTX_NAME, secctx)) + if (nla_put_string(skb, CTA_SECCTX_NAME, ctx.context)) goto nla_put_failure; nla_nest_end(skb, nest_secctx); ret = 0; nla_put_failure: - security_release_secctx(secctx, len); + security_release_secctx(&ctx); return ret; } #else @@ -383,6 +383,23 @@ nla_put_failure: #endif #ifdef CONFIG_NF_CONNTRACK_EVENTS +static int +ctnetlink_dump_event_timestamp(struct sk_buff *skb, const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + const struct nf_conntrack_ecache *e = nf_ct_ecache_find(ct); + + if (e) { + u64 ts = local64_read(&e->timestamp); + + if (ts) + return nla_put_be64(skb, CTA_TIMESTAMP_EVENT, + cpu_to_be64(ts), CTA_TIMESTAMP_PAD); + } +#endif + return 0; +} + static inline int ctnetlink_label_size(const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); @@ -663,14 +680,14 @@ static inline size_t ctnetlink_acct_size(const struct nf_conn *ct) static inline int ctnetlink_secctx_size(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_SECMARK - int len, ret; + int ret; - ret = security_secid_to_secctx(ct->secmark, NULL, &len); - if (ret) + ret = security_secid_to_secctx(ct->secmark, NULL); + if (ret < 0) return 0; return nla_total_size(0) /* CTA_SECCTX */ - + nla_total_size(sizeof(char) * len); /* CTA_SECCTX_NAME */ + + nla_total_size(sizeof(char) * ret); /* CTA_SECCTX_NAME */ #else return 0; #endif @@ -717,6 +734,9 @@ static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) #endif + ctnetlink_proto_size(ct) + ctnetlink_label_size(ct) +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + + nla_total_size(sizeof(u64)) /* CTA_TIMESTAMP_EVENT */ +#endif ; } @@ -838,6 +858,10 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) if (ctnetlink_dump_mark(skb, ct, events & (1 << IPCT_MARK))) goto nla_put_failure; #endif + + if (ctnetlink_dump_event_timestamp(skb, ct)) + goto nla_put_failure; + nlmsg_end(skb, nlh); err = nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); @@ -1557,6 +1581,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { .len = NF_CT_LABELS_MAX_SIZE }, [CTA_FILTER] = { .type = NLA_NESTED }, [CTA_STATUS_MASK] = { .type = NLA_U32 }, + [CTA_TIMESTAMP_EVENT] = { .type = NLA_REJECT }, }; static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 4cc97f971264..7c6f7c9f7332 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -39,20 +39,15 @@ static const char *const sctp_conntrack_names[] = { [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT", }; -#define SECS * HZ -#define MINS * 60 SECS -#define HOURS * 60 MINS -#define DAYS * 24 HOURS - static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { - [SCTP_CONNTRACK_CLOSED] = 10 SECS, - [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, - [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, - [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, - [SCTP_CONNTRACK_SHUTDOWN_SENT] = 3 SECS, - [SCTP_CONNTRACK_SHUTDOWN_RECD] = 3 SECS, - [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, - [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, + [SCTP_CONNTRACK_CLOSED] = secs_to_jiffies(10), + [SCTP_CONNTRACK_COOKIE_WAIT] = secs_to_jiffies(3), + [SCTP_CONNTRACK_COOKIE_ECHOED] = secs_to_jiffies(3), + [SCTP_CONNTRACK_ESTABLISHED] = secs_to_jiffies(210), + [SCTP_CONNTRACK_SHUTDOWN_SENT] = secs_to_jiffies(3), + [SCTP_CONNTRACK_SHUTDOWN_RECD] = secs_to_jiffies(3), + [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = secs_to_jiffies(3), + [SCTP_CONNTRACK_HEARTBEAT_SENT] = secs_to_jiffies(30), }; #define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index d0eac27f6ba0..ca748f8dbff1 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1553,7 +1553,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, if (dataoff >= skb->len) return NF_ACCEPT; - nf_ct_refresh(ct, skb, sip_timeout * HZ); + nf_ct_refresh(ct, sip_timeout * HZ); if (unlikely(skb_linearize(skb))) return NF_DROP; @@ -1624,7 +1624,7 @@ static int sip_help_udp(struct sk_buff *skb, unsigned int protoff, if (dataoff >= skb->len) return NF_ACCEPT; - nf_ct_refresh(ct, skb, sip_timeout * HZ); + nf_ct_refresh(ct, sip_timeout * HZ); if (unlikely(skb_linearize(skb))) return NF_DROP; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 7d4f0fa8b609..502cf10aab41 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -172,17 +172,16 @@ static void ct_seq_stop(struct seq_file *s, void *v) #ifdef CONFIG_NF_CONNTRACK_SECMARK static void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { + struct lsm_context ctx; int ret; - u32 len; - char *secctx; - ret = security_secid_to_secctx(ct->secmark, &secctx, &len); - if (ret) + ret = security_secid_to_secctx(ct->secmark, &ctx); + if (ret < 0) return; - seq_printf(s, "secctx=%s ", secctx); + seq_printf(s, "secctx=%s ", ctx.context); - security_release_secctx(secctx, len); + security_release_secctx(&ctx); } #else static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index df72b0376970..9d8361526f82 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -161,42 +161,86 @@ void flow_offload_route_init(struct flow_offload *flow, } EXPORT_SYMBOL_GPL(flow_offload_route_init); -static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) +static inline bool nf_flow_has_expired(const struct flow_offload *flow) { - tcp->seen[0].td_maxwin = 0; - tcp->seen[1].td_maxwin = 0; + return nf_flow_timeout_delta(flow->timeout) <= 0; } -static void flow_offload_fixup_ct(struct nf_conn *ct) +static void flow_offload_fixup_tcp(struct nf_conn *ct, u8 tcp_state) { + struct ip_ct_tcp *tcp = &ct->proto.tcp; + + spin_lock_bh(&ct->lock); + if (tcp->state != tcp_state) + tcp->state = tcp_state; + + /* syn packet triggers the TCP reopen case from conntrack. */ + if (tcp->state == TCP_CONNTRACK_CLOSE) + ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_CLOSE_INIT; + + /* Conntrack state is outdated due to offload bypass. + * Clear IP_CT_TCP_FLAG_MAXACK_SET, otherwise conntracks + * TCP reset validation will fail. + */ + tcp->seen[0].td_maxwin = 0; + tcp->seen[0].flags &= ~IP_CT_TCP_FLAG_MAXACK_SET; + tcp->seen[1].td_maxwin = 0; + tcp->seen[1].flags &= ~IP_CT_TCP_FLAG_MAXACK_SET; + spin_unlock_bh(&ct->lock); +} + +static void flow_offload_fixup_ct(struct flow_offload *flow) +{ + struct nf_conn *ct = flow->ct; struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); + bool expired, closing = false; + u32 offload_timeout = 0; s32 timeout; if (l4num == IPPROTO_TCP) { - struct nf_tcp_net *tn = nf_tcp_pernet(net); + const struct nf_tcp_net *tn = nf_tcp_pernet(net); + u8 tcp_state; - flow_offload_fixup_tcp(&ct->proto.tcp); + /* Enter CLOSE state if fin/rst packet has been seen, this + * allows TCP reopen from conntrack. Otherwise, pick up from + * the last seen TCP state. + */ + closing = test_bit(NF_FLOW_CLOSING, &flow->flags); + if (closing) { + flow_offload_fixup_tcp(ct, TCP_CONNTRACK_CLOSE); + timeout = READ_ONCE(tn->timeouts[TCP_CONNTRACK_CLOSE]); + expired = false; + } else { + tcp_state = READ_ONCE(ct->proto.tcp.state); + flow_offload_fixup_tcp(ct, tcp_state); + timeout = READ_ONCE(tn->timeouts[tcp_state]); + expired = nf_flow_has_expired(flow); + } + offload_timeout = READ_ONCE(tn->offload_timeout); - timeout = tn->timeouts[ct->proto.tcp.state]; - timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { - struct nf_udp_net *tn = nf_udp_pernet(net); + const struct nf_udp_net *tn = nf_udp_pernet(net); enum udp_conntrack state = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? UDP_CT_REPLIED : UDP_CT_UNREPLIED; - timeout = tn->timeouts[state]; - timeout -= tn->offload_timeout; + timeout = READ_ONCE(tn->timeouts[state]); + expired = nf_flow_has_expired(flow); + offload_timeout = READ_ONCE(tn->offload_timeout); } else { return; } + if (expired) + timeout -= offload_timeout; + if (timeout < 0) timeout = 0; - if (nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout) - WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout); + if (closing || + nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout) + nf_ct_refresh(ct, timeout); } static void flow_offload_route_release(struct flow_offload *flow) @@ -294,7 +338,7 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) return err; } - nf_ct_offload_timeout(flow->ct); + nf_ct_refresh(flow->ct, NF_CT_DAY); if (nf_flowtable_hw_offload(flow_table)) { __set_bit(NF_FLOW_HW, &flow->flags); @@ -316,18 +360,14 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, else return; - if (likely(!nf_flowtable_hw_offload(flow_table))) + if (likely(!nf_flowtable_hw_offload(flow_table)) || + test_bit(NF_FLOW_CLOSING, &flow->flags)) return; nf_flow_offload_add(flow_table, flow); } EXPORT_SYMBOL_GPL(flow_offload_refresh); -static inline bool nf_flow_has_expired(const struct flow_offload *flow) -{ - return nf_flow_timeout_delta(flow->timeout) <= 0; -} - static void flow_offload_del(struct nf_flowtable *flow_table, struct flow_offload *flow) { @@ -344,7 +384,7 @@ void flow_offload_teardown(struct flow_offload *flow) { clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); set_bit(NF_FLOW_TEARDOWN, &flow->flags); - flow_offload_fixup_ct(flow->ct); + flow_offload_fixup_ct(flow); } EXPORT_SYMBOL_GPL(flow_offload_teardown); @@ -414,15 +454,116 @@ static bool nf_flow_custom_gc(struct nf_flowtable *flow_table, return flow_table->type->gc && flow_table->type->gc(flow); } +/** + * nf_flow_table_tcp_timeout() - new timeout of offloaded tcp entry + * @ct: Flowtable offloaded tcp ct + * + * Return: number of seconds when ct entry should expire. + */ +static u32 nf_flow_table_tcp_timeout(const struct nf_conn *ct) +{ + u8 state = READ_ONCE(ct->proto.tcp.state); + + switch (state) { + case TCP_CONNTRACK_SYN_SENT: + case TCP_CONNTRACK_SYN_RECV: + return 0; + case TCP_CONNTRACK_ESTABLISHED: + return NF_CT_DAY; + case TCP_CONNTRACK_FIN_WAIT: + case TCP_CONNTRACK_CLOSE_WAIT: + case TCP_CONNTRACK_LAST_ACK: + case TCP_CONNTRACK_TIME_WAIT: + return 5 * 60 * HZ; + case TCP_CONNTRACK_CLOSE: + return 0; + } + + return 0; +} + +/** + * nf_flow_table_extend_ct_timeout() - Extend ct timeout of offloaded conntrack entry + * @ct: Flowtable offloaded ct + * + * Datapath lookups in the conntrack table will evict nf_conn entries + * if they have expired. + * + * Once nf_conn entries have been offloaded, nf_conntrack might not see any + * packets anymore. Thus ct->timeout is no longer refreshed and ct can + * be evicted. + * + * To avoid the need for an additional check on the offload bit for every + * packet processed via nf_conntrack_in(), set an arbitrary timeout large + * enough not to ever expire, this save us a check for the IPS_OFFLOAD_BIT + * from the packet path via nf_ct_is_expired(). + */ +static void nf_flow_table_extend_ct_timeout(struct nf_conn *ct) +{ + static const u32 min_timeout = 5 * 60 * HZ; + u32 expires = nf_ct_expires(ct); + + /* normal case: large enough timeout, nothing to do. */ + if (likely(expires >= min_timeout)) + return; + + /* must check offload bit after this, we do not hold any locks. + * flowtable and ct entries could have been removed on another CPU. + */ + if (!refcount_inc_not_zero(&ct->ct_general.use)) + return; + + /* load ct->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + + if (nf_ct_is_confirmed(ct) && + test_bit(IPS_OFFLOAD_BIT, &ct->status)) { + u8 l4proto = nf_ct_protonum(ct); + u32 new_timeout = true; + + switch (l4proto) { + case IPPROTO_UDP: + new_timeout = NF_CT_DAY; + break; + case IPPROTO_TCP: + new_timeout = nf_flow_table_tcp_timeout(ct); + break; + default: + WARN_ON_ONCE(1); + break; + } + + /* Update to ct->timeout from nf_conntrack happens + * without holding ct->lock. + * + * Use cmpxchg to ensure timeout extension doesn't + * happen when we race with conntrack datapath. + * + * The inverse -- datapath updating ->timeout right + * after this -- is fine, datapath is authoritative. + */ + if (new_timeout) { + new_timeout += nfct_time_stamp; + cmpxchg(&ct->timeout, expires, new_timeout); + } + } + + nf_ct_put(ct); +} + static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { + bool teardown = test_bit(NF_FLOW_TEARDOWN, &flow->flags); + if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || nf_flow_custom_gc(flow_table, flow)) flow_offload_teardown(flow); + else if (!teardown) + nf_flow_table_extend_ct_timeout(flow->ct); - if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { + if (teardown) { if (test_bit(NF_FLOW_HW, &flow->flags)) { if (!test_bit(NF_FLOW_HW_DYING, &flow->flags)) nf_flow_offload_del(flow_table, flow); @@ -431,6 +572,10 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, } else { flow_offload_del(flow_table, flow); } + } else if (test_bit(NF_FLOW_CLOSING, &flow->flags) && + test_bit(NF_FLOW_HW, &flow->flags) && + !test_bit(NF_FLOW_HW_DYING, &flow->flags)) { + nf_flow_offload_del(flow_table, flow); } else if (test_bit(NF_FLOW_HW, &flow->flags)) { nf_flow_offload_stats(flow_table, flow); } diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 98edcaa37b38..97c6eb8847a0 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -28,11 +28,15 @@ static int nf_flow_state_check(struct flow_offload *flow, int proto, return 0; tcph = (void *)(skb_network_header(skb) + thoff); - if (unlikely(tcph->fin || tcph->rst)) { + if (tcph->syn && test_bit(NF_FLOW_CLOSING, &flow->flags)) { flow_offload_teardown(flow); return -1; } + if ((tcph->fin || tcph->rst) && + !test_bit(NF_FLOW_CLOSING, &flow->flags)) + set_bit(NF_FLOW_CLOSING, &flow->flags); + return 0; } @@ -377,8 +381,10 @@ static int nf_flow_offload_forward(struct nf_flowtable_ctx *ctx, flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset; - if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) + if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) { + flow_offload_teardown(flow); return 0; + } iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset); thoff = (iph->ihl * 4) + ctx->offset; @@ -656,8 +662,10 @@ static int nf_flow_offload_ipv6_forward(struct nf_flowtable_ctx *ctx, flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset; - if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) + if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) { + flow_offload_teardown(flow); return 0; + } ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset); thoff = sizeof(*ip6h) + ctx->offset; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0b9f1e8dfe49..a34de9c17cf1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1956,15 +1956,16 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, if (!first) first = hook; - if (nla_put_string(skb, NFTA_DEVICE_NAME, - hook->ops.dev->name)) + if (nla_put(skb, NFTA_DEVICE_NAME, + hook->ifnamelen, hook->ifname)) goto nla_put_failure; n++; } nla_nest_end(skb, nest_devs); if (n == 1 && - nla_put_string(skb, NFTA_HOOK_DEV, first->ops.dev->name)) + nla_put(skb, NFTA_HOOK_DEV, + first->ifnamelen, first->ifname)) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -2276,7 +2277,6 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, const struct nlattr *attr) { struct net_device *dev; - char ifname[IFNAMSIZ]; struct nft_hook *hook; int err; @@ -2286,12 +2286,17 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, goto err_hook_alloc; } - nla_strscpy(ifname, attr, IFNAMSIZ); + err = nla_strscpy(hook->ifname, attr, IFNAMSIZ); + if (err < 0) + goto err_hook_dev; + + hook->ifnamelen = nla_len(attr); + /* nf_tables_netdev_event() is called under rtnl_mutex, this is * indirectly serializing all the other holders of the commit_mutex with * the rtnl_mutex. */ - dev = __dev_get_by_name(net, ifname); + dev = __dev_get_by_name(net, hook->ifname); if (!dev) { err = -ENOENT; goto err_hook_dev; @@ -2312,7 +2317,7 @@ static struct nft_hook *nft_hook_list_find(struct list_head *hook_list, struct nft_hook *hook; list_for_each_entry(hook, hook_list, list) { - if (this->ops.dev == hook->ops.dev) + if (!strcmp(hook->ifname, this->ifname)) return hook; } @@ -2598,9 +2603,8 @@ int nft_chain_add(struct nft_table *table, struct nft_chain *chain) static u64 chain_id; -static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, - u8 policy, u32 flags, - struct netlink_ext_ack *extack) +static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 policy, + u32 flags, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; @@ -3038,7 +3042,7 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, extack); } - return nf_tables_addchain(&ctx, family, genmask, policy, flags, extack); + return nf_tables_addchain(&ctx, family, policy, flags, extack); } static int nft_delchain_hook(struct nft_ctx *ctx, @@ -4753,6 +4757,14 @@ static int nf_tables_fill_set_concat(struct sk_buff *skb, return 0; } +static u32 nft_set_userspace_size(const struct nft_set_ops *ops, u32 size) +{ + if (ops->usize) + return ops->usize(size); + + return size; +} + static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { @@ -4823,7 +4835,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, if (!nest) goto nla_put_failure; if (set->size && - nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size))) + nla_put_be32(skb, NFTA_SET_DESC_SIZE, + htonl(nft_set_userspace_size(set->ops, set->size)))) goto nla_put_failure; if (set->field_count > 1 && @@ -5065,7 +5078,7 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { - u32 num_regs = 0, key_num_regs = 0; + u32 len = 0, num_regs; struct nlattr *attr; int rem, err, i; @@ -5079,12 +5092,12 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, } for (i = 0; i < desc->field_count; i++) - num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + len += round_up(desc->field_len[i], sizeof(u32)); - key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); - if (key_num_regs != num_regs) + if (len != desc->klen) return -EINVAL; + num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); if (num_regs > NFT_REG32_COUNT) return -E2BIG; @@ -5191,6 +5204,15 @@ static bool nft_set_is_same(const struct nft_set *set, return true; } +static u32 nft_set_kernel_size(const struct nft_set_ops *ops, + const struct nft_set_desc *desc) +{ + if (ops->ksize) + return ops->ksize(desc->size); + + return desc->size; +} + static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { @@ -5373,6 +5395,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (err < 0) return err; + if (desc.size) + desc.size = nft_set_kernel_size(set->ops, &desc); + err = 0; if (!nft_set_is_same(set, &desc, exprs, num_exprs, flags)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); @@ -5395,6 +5420,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (IS_ERR(ops)) return PTR_ERR(ops); + if (desc.size) + desc.size = nft_set_kernel_size(ops, &desc); + udlen = 0; if (nla[NFTA_SET_USERDATA]) udlen = nla_len(nla[NFTA_SET_USERDATA]); @@ -7051,6 +7079,27 @@ static bool nft_setelem_valid_key_end(const struct nft_set *set, return true; } +static u32 nft_set_maxsize(const struct nft_set *set) +{ + u32 maxsize, delta; + + if (!set->size) + return UINT_MAX; + + if (set->ops->adjust_maxsize) + delta = set->ops->adjust_maxsize(set); + else + delta = 0; + + if (check_add_overflow(set->size, set->ndeact, &maxsize)) + return UINT_MAX; + + if (check_add_overflow(maxsize, delta, &maxsize)) + return UINT_MAX; + + return maxsize; +} + static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr, u32 nlmsg_flags) { @@ -7423,7 +7472,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } if (!(flags & NFT_SET_ELEM_CATCHALL)) { - unsigned int max = set->size ? set->size + set->ndeact : UINT_MAX; + unsigned int max = nft_set_maxsize(set); if (!atomic_add_unless(&set->nelems, 1, max)) { err = -ENFILE; @@ -8822,6 +8871,7 @@ static void nft_unregister_flowtable_hook(struct net *net, } static void __nft_unregister_flowtable_net_hooks(struct net *net, + struct nft_flowtable *flowtable, struct list_head *hook_list, bool release_netdev) { @@ -8829,6 +8879,8 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); + flowtable->data.type->setup(&flowtable->data, hook->ops.dev, + FLOW_BLOCK_UNBIND); if (release_netdev) { list_del(&hook->list); kfree_rcu(hook, rcu); @@ -8837,9 +8889,10 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, } static void nft_unregister_flowtable_net_hooks(struct net *net, + struct nft_flowtable *flowtable, struct list_head *hook_list) { - __nft_unregister_flowtable_net_hooks(net, hook_list, false); + __nft_unregister_flowtable_net_hooks(net, flowtable, hook_list, false); } static int nft_register_flowtable_net_hooks(struct net *net, @@ -8847,7 +8900,7 @@ static int nft_register_flowtable_net_hooks(struct net *net, struct list_head *hook_list, struct nft_flowtable *flowtable) { - struct nft_hook *hook, *hook2, *next; + struct nft_hook *hook, *next; struct nft_flowtable *ft; int err, i = 0; @@ -8856,12 +8909,9 @@ static int nft_register_flowtable_net_hooks(struct net *net, if (!nft_is_active_next(net, ft)) continue; - list_for_each_entry(hook2, &ft->hook_list, list) { - if (hook->ops.dev == hook2->ops.dev && - hook->ops.pf == hook2->ops.pf) { - err = -EEXIST; - goto err_unregister_net_hooks; - } + if (nft_hook_list_find(&ft->hook_list, hook)) { + err = -EEXIST; + goto err_unregister_net_hooks; } } @@ -9275,7 +9325,8 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, list_for_each_entry_rcu(hook, hook_list, list, lockdep_commit_lock_is_held(net)) { - if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name)) + if (nla_put(skb, NFTA_DEVICE_NAME, + hook->ifnamelen, hook->ifname)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); @@ -9481,8 +9532,6 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) flowtable->data.type->free(&flowtable->data); list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - flowtable->data.type->setup(&flowtable->data, hook->ops.dev, - FLOW_BLOCK_UNBIND); list_del_rcu(&hook->list); kfree_rcu(hook, rcu); } @@ -10870,6 +10919,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) &nft_trans_flowtable_hooks(trans), trans->msg_type); nft_unregister_flowtable_net_hooks(net, + nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans)); } else { list_del_rcu(&nft_trans_flowtable(trans)->list); @@ -10878,6 +10928,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) NULL, trans->msg_type); nft_unregister_flowtable_net_hooks(net, + nft_trans_flowtable(trans), &nft_trans_flowtable(trans)->hook_list); } break; @@ -11140,11 +11191,13 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nft_unregister_flowtable_net_hooks(net, + nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans)); } else { nft_use_dec_restore(&table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, + nft_trans_flowtable(trans), &nft_trans_flowtable(trans)->hook_list); } break; @@ -11688,47 +11741,6 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, } EXPORT_SYMBOL_GPL(nft_data_dump); -static void __nft_release_basechain_now(struct nft_ctx *ctx) -{ - struct nft_rule *rule, *nr; - - list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { - list_del(&rule->list); - nf_tables_rule_release(ctx, rule); - } - nf_tables_chain_destroy(ctx->chain); -} - -int __nft_release_basechain(struct nft_ctx *ctx) -{ - struct nft_rule *rule; - - if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain))) - return 0; - - nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); - list_for_each_entry(rule, &ctx->chain->rules, list) - nft_use_dec(&ctx->chain->use); - - nft_chain_del(ctx->chain); - nft_use_dec(&ctx->table->use); - - if (!maybe_get_net(ctx->net)) { - __nft_release_basechain_now(ctx); - return 0; - } - - /* wait for ruleset dumps to complete. Owning chain is no longer in - * lists, so new dumps can't find any of these rules anymore. - */ - synchronize_rcu(); - - __nft_release_basechain_now(ctx); - put_net(ctx->net); - return 0; -} -EXPORT_SYMBOL_GPL(__nft_release_basechain); - static void __nft_release_hook(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable; @@ -11737,7 +11749,8 @@ static void __nft_release_hook(struct net *net, struct nft_table *table) list_for_each_entry(chain, &table->chains, list) __nf_tables_unregister_hook(net, table, chain, true); list_for_each_entry(flowtable, &table->flowtables, list) - __nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list, + __nft_unregister_flowtable_net_hooks(net, flowtable, + &flowtable->hook_list, true); } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index d2773ce9b585..5c913987901a 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -470,18 +470,18 @@ static int nfqnl_put_sk_classid(struct sk_buff *skb, struct sock *sk) return 0; } -static u32 nfqnl_get_sk_secctx(struct sk_buff *skb, char **secdata) +static int nfqnl_get_sk_secctx(struct sk_buff *skb, struct lsm_context *ctx) { - u32 seclen = 0; + int seclen = 0; #if IS_ENABLED(CONFIG_NETWORK_SECMARK) + if (!skb || !sk_fullsock(skb->sk)) return 0; read_lock_bh(&skb->sk->sk_callback_lock); if (skb->secmark) - security_secid_to_secctx(skb->secmark, secdata, &seclen); - + seclen = security_secid_to_secctx(skb->secmark, ctx); read_unlock_bh(&skb->sk->sk_callback_lock); #endif return seclen; @@ -567,8 +567,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, enum ip_conntrack_info ctinfo = 0; const struct nfnl_ct_hook *nfnl_ct; bool csum_verify; - char *secdata = NULL; - u32 seclen = 0; + struct lsm_context ctx; + int seclen = 0; ktime_t tstamp; size = nlmsg_total_size(sizeof(struct nfgenmsg)) @@ -642,7 +642,9 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, } if ((queue->flags & NFQA_CFG_F_SECCTX) && entskb->sk) { - seclen = nfqnl_get_sk_secctx(entskb, &secdata); + seclen = nfqnl_get_sk_secctx(entskb, &ctx); + if (seclen < 0) + return NULL; if (seclen) size += nla_total_size(seclen); } @@ -782,7 +784,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (nfqnl_put_sk_classid(skb, entskb->sk) < 0) goto nla_put_failure; - if (seclen && nla_put(skb, NFQA_SECCTX, seclen, secdata)) + if (seclen > 0 && nla_put(skb, NFQA_SECCTX, ctx.len, ctx.context)) goto nla_put_failure; if (ct && nfnl_ct->build(skb, ct, ctinfo, NFQA_CT, NFQA_CT_INFO) < 0) @@ -810,8 +812,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, } nlh->nlmsg_len = skb->len; - if (seclen) - security_release_secctx(secdata, seclen); + if (seclen >= 0) + security_release_secctx(&ctx); return skb; nla_put_failure: @@ -819,8 +821,8 @@ nla_put_failure: kfree_skb(skb); net_err_ratelimited("nf_queue: error creating packet message\n"); nlmsg_failure: - if (seclen) - security_release_secctx(secdata, seclen); + if (seclen >= 0) + security_release_secctx(&ctx); return NULL; } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 7010541fcca6..19a553550c76 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -319,37 +319,21 @@ static const struct nft_chain_type nft_chain_filter_netdev = { }; static void nft_netdev_event(unsigned long event, struct net_device *dev, - struct nft_ctx *ctx) + struct nft_base_chain *basechain) { - struct nft_base_chain *basechain = nft_base_chain(ctx->chain); - struct nft_hook *hook, *found = NULL; - int n = 0; + struct nft_hook *hook; list_for_each_entry(hook, &basechain->hook_list, list) { - if (hook->ops.dev == dev) - found = hook; + if (hook->ops.dev != dev) + continue; - n++; + if (!(basechain->chain.table->flags & NFT_TABLE_F_DORMANT)) + nf_unregister_net_hook(dev_net(dev), &hook->ops); + + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + break; } - if (!found) - return; - - if (n > 1) { - if (!(ctx->chain->table->flags & NFT_TABLE_F_DORMANT)) - nf_unregister_net_hook(ctx->net, &found->ops); - - list_del_rcu(&found->list); - kfree_rcu(found, rcu); - return; - } - - /* UNREGISTER events are also happening on netns exit. - * - * Although nf_tables core releases all tables/chains, only this event - * handler provides guarantee that hook->ops.dev is still accessible, - * so we cannot skip exiting net namespaces. - */ - __nft_release_basechain(ctx); } static int nf_tables_netdev_event(struct notifier_block *this, @@ -358,25 +342,20 @@ static int nf_tables_netdev_event(struct notifier_block *this, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nft_base_chain *basechain; struct nftables_pernet *nft_net; - struct nft_chain *chain, *nr; + struct nft_chain *chain; struct nft_table *table; - struct nft_ctx ctx = { - .net = dev_net(dev), - }; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - nft_net = nft_pernet(ctx.net); + nft_net = nft_pernet(dev_net(dev)); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV && table->family != NFPROTO_INET) continue; - ctx.family = table->family; - ctx.table = table; - list_for_each_entry_safe(chain, nr, &table->chains, list) { + list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain)) continue; @@ -385,8 +364,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, basechain->ops.hooknum != NF_INET_INGRESS) continue; - ctx.chain = chain; - nft_netdev_event(event, dev, &ctx); + nft_netdev_event(event, dev, basechain); } } mutex_unlock(&nft_net->commit_mutex); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 67a41cd2baaf..2e59aba681a1 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -929,7 +929,7 @@ static void nft_ct_timeout_obj_eval(struct nft_object *obj, */ values = nf_ct_timeout_data(timeout); if (values) - nf_ct_refresh(ct, pkt->skb, values[0]); + nf_ct_refresh(ct, values[0]); } static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 3b474d235663..221d50223018 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -289,6 +289,15 @@ static bool nft_flow_offload_skip(struct sk_buff *skb, int family) return false; } +static void flow_offload_ct_tcp(struct nf_conn *ct) +{ + /* conntrack will not see all packets, disable tcp window validation. */ + spin_lock_bh(&ct->lock); + ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; + ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; + spin_unlock_bh(&ct->lock); +} + static void nft_flow_offload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -356,11 +365,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, goto err_flow_alloc; flow_offload_route_init(flow, &route); - - if (tcph) { - ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; - ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; - } + if (tcph) + flow_offload_ct_tcp(ct); __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); ret = flow_offload_add(flowtable, flow); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index b7ea21327549..2e8ef16ff191 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -750,6 +750,46 @@ static void nft_rbtree_gc_init(const struct nft_set *set) priv->last_gc = jiffies; } +/* rbtree stores ranges as singleton elements, each range is composed of two + * elements ... + */ +static u32 nft_rbtree_ksize(u32 size) +{ + return size * 2; +} + +/* ... hide this detail to userspace. */ +static u32 nft_rbtree_usize(u32 size) +{ + if (!size) + return 0; + + return size / 2; +} + +static u32 nft_rbtree_adjust_maxsize(const struct nft_set *set) +{ + struct nft_rbtree *priv = nft_set_priv(set); + struct nft_rbtree_elem *rbe; + struct rb_node *node; + const void *key; + + node = rb_last(&priv->root); + if (!node) + return 0; + + rbe = rb_entry(node, struct nft_rbtree_elem, node); + if (!nft_rbtree_interval_end(rbe)) + return 0; + + key = nft_set_ext_key(&rbe->ext); + if (memchr(key, 1, set->klen)) + return 0; + + /* this is the all-zero no-match element. */ + return 1; +} + const struct nft_set_type nft_set_rbtree_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { @@ -768,5 +808,8 @@ const struct nft_set_type nft_set_rbtree_type = { .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .get = nft_rbtree_get, + .ksize = nft_rbtree_ksize, + .usize = nft_rbtree_usize, + .adjust_maxsize = nft_rbtree_adjust_maxsize, }, }; diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c index 8a07b46cc8fb..3210cfc966ab 100644 --- a/net/netfilter/nft_xfrm.c +++ b/net/netfilter/nft_xfrm.c @@ -112,7 +112,8 @@ static bool xfrm_state_addr_ok(enum nft_xfrm_keys k, u8 family, u8 mode) return true; } - return mode == XFRM_MODE_BEET || mode == XFRM_MODE_TUNNEL; + return mode == XFRM_MODE_BEET || mode == XFRM_MODE_TUNNEL || + mode == XFRM_MODE_IPTFS; } static void nft_xfrm_state_get_key(const struct nft_xfrm *priv, diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 0859b8f76764..fa02aab56724 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -363,11 +363,15 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, bool select unsigned int i; for (i = 0; i < ht->cfg.size; i++) { + struct hlist_head *head = &ht->hash[i]; struct dsthash_ent *dh; struct hlist_node *n; + if (hlist_empty(head)) + continue; + spin_lock_bh(&ht->lock); - hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { + hlist_for_each_entry_safe(dh, n, head, node) { if (time_after_eq(jiffies, dh->expires) || select_all) dsthash_free(ht, dh); } diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 1bc2d0890a9f..dfda9ea61971 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -374,8 +374,7 @@ int netlbl_unlhsh_add(struct net *net, struct net_device *dev; struct netlbl_unlhsh_iface *iface; struct audit_buffer *audit_buf = NULL; - char *secctx = NULL; - u32 secctx_len; + struct lsm_context ctx; if (addr_len != sizeof(struct in_addr) && addr_len != sizeof(struct in6_addr)) @@ -438,11 +437,9 @@ int netlbl_unlhsh_add(struct net *net, unlhsh_add_return: rcu_read_unlock(); if (audit_buf != NULL) { - if (security_secid_to_secctx(secid, - &secctx, - &secctx_len) == 0) { - audit_log_format(audit_buf, " sec_obj=%s", secctx); - security_release_secctx(secctx, secctx_len); + if (security_secid_to_secctx(secid, &ctx) >= 0) { + audit_log_format(audit_buf, " sec_obj=%s", ctx.context); + security_release_secctx(&ctx); } audit_log_format(audit_buf, " res=%u", ret_val == 0 ? 1 : 0); audit_log_end(audit_buf); @@ -473,8 +470,7 @@ static int netlbl_unlhsh_remove_addr4(struct net *net, struct netlbl_unlhsh_addr4 *entry; struct audit_buffer *audit_buf; struct net_device *dev; - char *secctx; - u32 secctx_len; + struct lsm_context ctx; spin_lock(&netlbl_unlhsh_lock); list_entry = netlbl_af4list_remove(addr->s_addr, mask->s_addr, @@ -494,10 +490,9 @@ static int netlbl_unlhsh_remove_addr4(struct net *net, addr->s_addr, mask->s_addr); dev_put(dev); if (entry != NULL && - security_secid_to_secctx(entry->secid, - &secctx, &secctx_len) == 0) { - audit_log_format(audit_buf, " sec_obj=%s", secctx); - security_release_secctx(secctx, secctx_len); + security_secid_to_secctx(entry->secid, &ctx) >= 0) { + audit_log_format(audit_buf, " sec_obj=%s", ctx.context); + security_release_secctx(&ctx); } audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0); audit_log_end(audit_buf); @@ -534,8 +529,7 @@ static int netlbl_unlhsh_remove_addr6(struct net *net, struct netlbl_unlhsh_addr6 *entry; struct audit_buffer *audit_buf; struct net_device *dev; - char *secctx; - u32 secctx_len; + struct lsm_context ctx; spin_lock(&netlbl_unlhsh_lock); list_entry = netlbl_af6list_remove(addr, mask, &iface->addr6_list); @@ -554,10 +548,9 @@ static int netlbl_unlhsh_remove_addr6(struct net *net, addr, mask); dev_put(dev); if (entry != NULL && - security_secid_to_secctx(entry->secid, - &secctx, &secctx_len) == 0) { - audit_log_format(audit_buf, " sec_obj=%s", secctx); - security_release_secctx(secctx, secctx_len); + security_secid_to_secctx(entry->secid, &ctx) >= 0) { + audit_log_format(audit_buf, " sec_obj=%s", ctx.context); + security_release_secctx(&ctx); } audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0); audit_log_end(audit_buf); @@ -1069,10 +1062,9 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd, int ret_val = -ENOMEM; struct netlbl_unlhsh_walk_arg *cb_arg = arg; struct net_device *dev; + struct lsm_context ctx; void *data; u32 secid; - char *secctx; - u32 secctx_len; data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_unlabel_gnl_family, @@ -1127,14 +1119,14 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd, secid = addr6->secid; } - ret_val = security_secid_to_secctx(secid, &secctx, &secctx_len); - if (ret_val != 0) + ret_val = security_secid_to_secctx(secid, &ctx); + if (ret_val < 0) goto list_cb_failure; ret_val = nla_put(cb_arg->skb, NLBL_UNLABEL_A_SECCTX, - secctx_len, - secctx); - security_release_secctx(secctx, secctx_len); + ctx.len, + ctx.context); + security_release_secctx(&ctx); if (ret_val != 0) goto list_cb_failure; diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c index 81635a13987b..0d04d23aafe7 100644 --- a/net/netlabel/netlabel_user.c +++ b/net/netlabel/netlabel_user.c @@ -84,8 +84,7 @@ struct audit_buffer *netlbl_audit_start_common(int type, struct netlbl_audit *audit_info) { struct audit_buffer *audit_buf; - char *secctx; - u32 secctx_len; + struct lsm_context ctx; if (audit_enabled == AUDIT_OFF) return NULL; @@ -99,10 +98,9 @@ struct audit_buffer *netlbl_audit_start_common(int type, audit_info->sessionid); if (lsmprop_is_set(&audit_info->prop) && - security_lsmprop_to_secctx(&audit_info->prop, &secctx, - &secctx_len) == 0) { - audit_log_format(audit_buf, " subj=%s", secctx); - security_release_secctx(secctx, secctx_len); + security_lsmprop_to_secctx(&audit_info->prop, &ctx) > 0) { + audit_log_format(audit_buf, " subj=%s", ctx.context); + security_release_secctx(&ctx); } return audit_buf; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f4e7b5e4bb59..85311226183a 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1287,6 +1287,7 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) { int delta; + skb_assert_len(skb); WARN_ON(skb->sk != NULL); delta = skb->end - skb->tail; if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 2b5e246b8d9a..b94cb2ffbaf8 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -754,6 +754,12 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) int ret; struct sk_buff *skbn; + /* + * Reject malformed packets early. Check that it contains at least 2 + * addresses and 1 byte more for Time-To-Live + */ + if (skb->len < 2 * sizeof(ax25_address) + 1) + return 0; nr_src = (ax25_address *)(skb->data + 0); nr_dest = (ax25_address *)(skb->data + 7); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index de175318a3a0..082ab66f120b 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -542,6 +542,8 @@ static u8 nci_hci_create_pipe(struct nci_dev *ndev, u8 dest_host, pr_debug("pipe created=%d\n", pipe); + if (pipe >= NCI_HCI_MAX_PIPES) + pipe = NCI_HCI_INVALID_PIPE; return pipe; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 16e260014684..704c858cf209 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -934,7 +934,9 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, { struct vport *vport = ovs_vport_rcu(dp, out_port); - if (likely(vport && netif_carrier_ok(vport->dev))) { + if (likely(vport && + netif_running(vport->dev) && + netif_carrier_ok(vport->dev))) { u16 mru = OVS_CB(skb)->mru; u32 cutlen = OVS_CB(skb)->cutlen; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 886c0dd47b66..c131e5ceea37 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -538,10 +538,8 @@ static void *packet_current_frame(struct packet_sock *po, return packet_lookup_frame(po, rb, rb->head, status); } -static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) +static u16 vlan_get_tci(const struct sk_buff *skb, struct net_device *dev) { - u8 *skb_orig_data = skb->data; - int skb_orig_len = skb->len; struct vlan_hdr vhdr, *vh; unsigned int header_len; @@ -562,33 +560,21 @@ static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) else return 0; - skb_push(skb, skb->data - skb_mac_header(skb)); - vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); - if (skb_orig_data != skb->data) { - skb->data = skb_orig_data; - skb->len = skb_orig_len; - } + vh = skb_header_pointer(skb, skb_mac_offset(skb) + header_len, + sizeof(vhdr), &vhdr); if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } -static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) +static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb) { __be16 proto = skb->protocol; - if (unlikely(eth_type_vlan(proto))) { - u8 *skb_orig_data = skb->data; - int skb_orig_len = skb->len; - - skb_push(skb, skb->data - skb_mac_header(skb)); - proto = __vlan_get_protocol(skb, proto, NULL); - if (skb_orig_data != skb->data) { - skb->data = skb_orig_data; - skb->len = skb_orig_len; - } - } + if (unlikely(eth_type_vlan(proto))) + proto = __vlan_get_protocol_offset(skb, proto, + skb_mac_offset(skb), NULL); return proto; } @@ -3126,7 +3112,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->protocol = proto; skb->dev = dev; - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = sockc.priority; skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); diff --git a/net/psample/psample.c b/net/psample/psample.c index a0ddae8a65f9..25f92ba0840c 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -393,7 +393,9 @@ void psample_sample_packet(struct psample_group *group, nla_total_size_64bit(sizeof(u64)) + /* timestamp */ nla_total_size(sizeof(u16)) + /* protocol */ (md->user_cookie_len ? - nla_total_size(md->user_cookie_len) : 0); /* user cookie */ + nla_total_size(md->user_cookie_len) : 0) + /* user cookie */ + (md->rate_as_probability ? + nla_total_size(0) : 0); /* rate as probability */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -498,8 +500,9 @@ void psample_sample_packet(struct psample_group *group, md->user_cookie)) goto error; - if (md->rate_as_probability) - nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY); + if (md->rate_as_probability && + nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY)) + goto error; genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 351ac1747224..0581c53e6517 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -61,8 +61,10 @@ static atomic_t rds_tcp_unloading = ATOMIC_INIT(0); static struct kmem_cache *rds_tcp_conn_slab; -static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, - void *buffer, size_t *lenp, loff_t *fpos); +static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos); +static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos); static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF; static int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF; @@ -74,7 +76,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = { /* data is per-net pointer */ .maxlen = sizeof(int), .mode = 0644, - .proc_handler = rds_tcp_skbuf_handler, + .proc_handler = rds_tcp_sndbuf_handler, .extra1 = &rds_tcp_min_sndbuf, }, #define RDS_TCP_RCVBUF 1 @@ -83,7 +85,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = { /* data is per-net pointer */ .maxlen = sizeof(int), .mode = 0644, - .proc_handler = rds_tcp_skbuf_handler, + .proc_handler = rds_tcp_rcvbuf_handler, .extra1 = &rds_tcp_min_rcvbuf, }, }; @@ -682,10 +684,10 @@ static void rds_tcp_sysctl_reset(struct net *net) spin_unlock_irq(&rds_tcp_conn_lock); } -static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, +static int rds_tcp_skbuf_handler(struct rds_tcp_net *rtn, + const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *fpos) { - struct net *net = current->nsproxy->net_ns; int err; err = proc_dointvec_minmax(ctl, write, buffer, lenp, fpos); @@ -694,11 +696,34 @@ static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, *(int *)(ctl->extra1)); return err; } - if (write) + + if (write && rtn->rds_tcp_listen_sock && rtn->rds_tcp_listen_sock->sk) { + struct net *net = sock_net(rtn->rds_tcp_listen_sock->sk); + rds_tcp_sysctl_reset(net); + } + return 0; } +static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos) +{ + struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net, + sndbuf_size); + + return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos); +} + +static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos) +{ + struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net, + rcvbuf_size); + + return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos); +} + static void rds_tcp_exit(void) { rds_tcp_set_unloading(); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 59050caab65c..72c65d938a15 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -397,15 +397,15 @@ static int rose_setsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); - int opt; + unsigned int opt; if (level != SOL_ROSE) return -ENOPROTOOPT; - if (optlen < sizeof(int)) + if (optlen < sizeof(unsigned int)) return -EINVAL; - if (copy_from_sockptr(&opt, optval, sizeof(int))) + if (copy_from_sockptr(&opt, optval, sizeof(unsigned int))) return -EFAULT; switch (optname) { @@ -414,31 +414,31 @@ static int rose_setsockopt(struct socket *sock, int level, int optname, return 0; case ROSE_T1: - if (opt < 1) + if (opt < 1 || opt > UINT_MAX / HZ) return -EINVAL; rose->t1 = opt * HZ; return 0; case ROSE_T2: - if (opt < 1) + if (opt < 1 || opt > UINT_MAX / HZ) return -EINVAL; rose->t2 = opt * HZ; return 0; case ROSE_T3: - if (opt < 1) + if (opt < 1 || opt > UINT_MAX / HZ) return -EINVAL; rose->t3 = opt * HZ; return 0; case ROSE_HOLDBACK: - if (opt < 1) + if (opt < 1 || opt > UINT_MAX / HZ) return -EINVAL; rose->hb = opt * HZ; return 0; case ROSE_IDLE: - if (opt < 0) + if (opt > UINT_MAX / (60 * HZ)) return -EINVAL; rose->idle = opt * 60 * HZ; return 0; diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c index f06ddbed3fed..1525773e94aa 100644 --- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -122,6 +122,10 @@ static void rose_heartbeat_expiry(struct timer_list *t) struct rose_sock *rose = rose_sk(sk); bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ/20); + goto out; + } switch (rose->state) { case ROSE_STATE_0: /* Magic here: If we listen() and a new link dies before it @@ -152,6 +156,7 @@ static void rose_heartbeat_expiry(struct timer_list *t) } rose_start_heartbeat(sk); +out: bh_unlock_sock(sk); sock_put(sk); } @@ -162,6 +167,10 @@ static void rose_timer_expiry(struct timer_list *t) struct sock *sk = &rose->sock; bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &rose->timer, jiffies + HZ/20); + goto out; + } switch (rose->state) { case ROSE_STATE_1: /* T1 */ case ROSE_STATE_4: /* T2 */ @@ -182,6 +191,7 @@ static void rose_timer_expiry(struct timer_list *t) } break; } +out: bh_unlock_sock(sk); sock_put(sk); } @@ -192,6 +202,10 @@ static void rose_idletimer_expiry(struct timer_list *t) struct sock *sk = &rose->sock; bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &rose->idletimer, jiffies + HZ/20); + goto out; + } rose_clear_queues(sk); rose_write_internal(sk, ROSE_CLEAR_REQUEST); @@ -207,6 +221,7 @@ static void rose_idletimer_expiry(struct timer_list *t) sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } +out: bh_unlock_sock(sk); sock_put(sk); } diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index ac5caf5a48e1..210b75e3179e 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -16,6 +16,7 @@ rxrpc-y := \ conn_object.o \ conn_service.o \ input.o \ + input_rack.o \ insecure.o \ io_thread.o \ key.o \ diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 9d8bd0b37e41..86873399f7d5 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -408,9 +408,9 @@ void rxrpc_kernel_shutdown_call(struct socket *sock, struct rxrpc_call *call) /* Make sure we're not going to call back into a kernel service */ if (call->notify_rx) { - spin_lock(&call->notify_lock); + spin_lock_irq(&call->notify_lock); call->notify_rx = rxrpc_dummy_notify_rx; - spin_unlock(&call->notify_lock); + spin_unlock_irq(&call->notify_lock); } } mutex_unlock(&call->user_mutex); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index d0fd37bdcfe9..718193df9d2e 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -30,6 +30,7 @@ struct rxrpc_crypt { struct key_preparsed_payload; struct rxrpc_connection; struct rxrpc_txbuf; +struct rxrpc_txqueue; /* * Mark applied to socket buffers in skb->mark. skb->priority is used @@ -98,6 +99,7 @@ struct rxrpc_net { atomic_t stat_tx_data_send; atomic_t stat_tx_data_send_frag; atomic_t stat_tx_data_send_fail; + atomic_t stat_tx_data_send_msgsize; atomic_t stat_tx_data_underflow; atomic_t stat_tx_data_cwnd_reset; atomic_t stat_rx_data; @@ -109,6 +111,8 @@ struct rxrpc_net { atomic_t stat_tx_ack_skip; atomic_t stat_tx_acks[256]; atomic_t stat_rx_acks[256]; + atomic_t stat_tx_jumbo[10]; + atomic_t stat_rx_jumbo[10]; atomic_t stat_why_req_ack[8]; @@ -210,9 +214,8 @@ struct rxrpc_skb_priv { rxrpc_seq_t first_ack; /* First packet in acks table */ rxrpc_seq_t prev_ack; /* Highest seq seen */ rxrpc_serial_t acked_serial; /* Packet in response to (or 0) */ + u16 nr_acks; /* Number of acks+nacks */ u8 reason; /* Reason for ack */ - u8 nr_acks; /* Number of acks+nacks */ - u8 nr_nacks; /* Number of nacks */ } ack; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ @@ -320,6 +323,12 @@ struct rxrpc_local { struct list_head new_client_calls; /* Newly created client calls need connection */ spinlock_t client_call_lock; /* Lock for ->new_client_calls */ struct sockaddr_rxrpc srx; /* local address */ + /* Provide a kvec table sufficiently large to manage either a DATA + * packet with a maximum set of jumbo subpackets or a PING ACK padded + * out to 64K with zeropages for PMTUD. + */ + struct kvec kvec[RXRPC_MAX_NR_JUMBO > 3 + 16 ? + RXRPC_MAX_NR_JUMBO : 3 + 16]; }; /* @@ -338,25 +347,28 @@ struct rxrpc_peer { time64_t last_tx_at; /* Last time packet sent here */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ - unsigned int if_mtu; /* interface MTU for this peer */ - unsigned int mtu; /* network MTU for this peer */ - unsigned int maxdata; /* data size (MTU - hdrsize) */ - unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ int debug_id; /* debug ID for printks */ struct sockaddr_rxrpc srx; /* remote address */ - /* calculated RTT cache */ -#define RXRPC_RTT_CACHE_SIZE 32 - spinlock_t rtt_input_lock; /* RTT lock for input routine */ - ktime_t rtt_last_req; /* Time of last RTT request */ - unsigned int rtt_count; /* Number of samples we've got */ + /* Path MTU discovery [RFC8899] */ + unsigned int pmtud_trial; /* Current MTU probe size */ + unsigned int pmtud_good; /* Largest working MTU probe we've tried */ + unsigned int pmtud_bad; /* Smallest non-working MTU probe we've tried */ + bool pmtud_lost; /* T if MTU probe was lost */ + bool pmtud_probing; /* T if we have an active probe outstanding */ + bool pmtud_pending; /* T if a call to this peer should send a probe */ + u8 pmtud_jumbo; /* Max jumbo packets for the MTU */ + bool ackr_adv_pmtud; /* T if the peer advertises path-MTU */ + unsigned int ackr_max_data; /* Maximum data advertised by peer */ + seqcount_t mtu_lock; /* Lockless MTU access management */ + unsigned int if_mtu; /* Local interface MTU (- hdrsize) for this peer */ + unsigned int max_data; /* Maximum packet data capacity for this peer */ + unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ + unsigned short tx_seg_max; /* Maximum number of transmissable segments */ - u32 srtt_us; /* smoothed round trip time << 3 in usecs */ - u32 mdev_us; /* medium deviation */ - u32 mdev_max_us; /* maximal mdev for the last rtt period */ - u32 rttvar_us; /* smoothed mdev_max */ - u32 rto_us; /* Retransmission timeout in usec */ - u8 backoff; /* Backoff timeout (as shift) */ + /* Calculated RTT cache */ + unsigned int recent_srtt_us; + unsigned int recent_rto_us; u8 cong_ssthresh; /* Congestion slow-start threshold */ }; @@ -525,6 +537,8 @@ struct rxrpc_connection { int debug_id; /* debug ID for printks */ rxrpc_serial_t tx_serial; /* Outgoing packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ + rxrpc_serial_t pmtud_probe; /* Serial of MTU probe (or 0) */ + unsigned int pmtud_call; /* ID of call used for probe */ u32 service_id; /* Service ID, possibly upgraded */ u32 security_level; /* Security level selected */ u8 security_ix; /* security type */ @@ -557,6 +571,7 @@ enum rxrpc_call_flag { RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ RXRPC_CALL_TX_ALL_ACKED, /* Last packet has been hard-acked */ + RXRPC_CALL_TX_NO_MORE, /* No more data to transmit (MSG_MORE deasserted) */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ @@ -599,13 +614,25 @@ enum rxrpc_call_state { /* * Call Tx congestion management modes. */ -enum rxrpc_congest_mode { - RXRPC_CALL_SLOW_START, - RXRPC_CALL_CONGEST_AVOIDANCE, - RXRPC_CALL_PACKET_LOSS, - RXRPC_CALL_FAST_RETRANSMIT, - NR__RXRPC_CONGEST_MODES -}; +enum rxrpc_ca_state { + RXRPC_CA_SLOW_START, + RXRPC_CA_CONGEST_AVOIDANCE, + RXRPC_CA_PACKET_LOSS, + RXRPC_CA_FAST_RETRANSMIT, + NR__RXRPC_CA_STATES +} __mode(byte); + +/* + * Current purpose of call RACK timer. According to the RACK-TLP protocol + * [RFC8985], the transmission timer (call->rack_timo_at) may only be used for + * one of these at once. + */ +enum rxrpc_rack_timer_mode { + RXRPC_CALL_RACKTIMER_OFF, /* Timer not running */ + RXRPC_CALL_RACKTIMER_RACK_REORDER, /* RACK reordering timer */ + RXRPC_CALL_RACKTIMER_TLP_PTO, /* TLP timeout */ + RXRPC_CALL_RACKTIMER_RTO, /* Retransmission timeout */ +} __mode(byte); /* * RxRPC call definition @@ -624,8 +651,7 @@ struct rxrpc_call { struct mutex user_mutex; /* User access mutex */ struct sockaddr_rxrpc dest_srx; /* Destination address */ ktime_t delay_ack_at; /* When DELAY ACK needs to happen */ - ktime_t ack_lost_at; /* When ACK is figured as lost */ - ktime_t resend_at; /* When next resend needs to happen */ + ktime_t rack_timo_at; /* When ACK is figured as lost */ ktime_t ping_at; /* When next to send a ping */ ktime_t keepalive_at; /* When next to send a keepalive ping */ ktime_t expect_rx_by; /* When we expect to get a packet by */ @@ -670,21 +696,30 @@ struct rxrpc_call { unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ + /* Sendmsg data tracking. */ + rxrpc_seq_t send_top; /* Highest Tx slot filled by sendmsg. */ + struct rxrpc_txqueue *send_queue; /* Queue that sendmsg is writing into */ + /* Transmitted data tracking. */ - spinlock_t tx_lock; /* Transmit queue lock */ - struct list_head tx_sendmsg; /* Sendmsg prepared packets */ - struct list_head tx_buffer; /* Buffer of transmissible packets */ + struct rxrpc_txqueue *tx_queue; /* Start of transmission buffers */ + struct rxrpc_txqueue *tx_qtail; /* End of transmission buffers */ + rxrpc_seq_t tx_qbase; /* First slot in tx_queue */ rxrpc_seq_t tx_bottom; /* First packet in buffer */ rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ - rxrpc_seq_t tx_prepared; /* Highest Tx slot prepared. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ + rxrpc_serial_t tx_last_serial; /* Serial of last DATA transmitted */ u16 tx_backoff; /* Delay to insert due to Tx failure (ms) */ - u8 tx_winsize; /* Maximum size of Tx window */ + u16 tx_nr_sent; /* Number of packets sent, but unacked */ + u16 tx_nr_lost; /* Number of packets marked lost */ + u16 tx_nr_resent; /* Number of packets resent, but unacked */ + u16 tx_winsize; /* Maximum size of Tx window */ #define RXRPC_TX_MAX_WINDOW 128 + u8 tx_jumbo_max; /* Maximum subpkts peer will accept */ ktime_t tx_last_sent; /* Last time a transmission occurred */ /* Received data tracking */ struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ + struct sk_buff_head rx_queue; /* Queue of packets for this call to receive */ struct sk_buff_head rx_oos_queue; /* Queue of out of sequence packets */ rxrpc_seq_t rx_highest_seq; /* Higest sequence number received */ @@ -698,14 +733,32 @@ struct rxrpc_call { */ #define RXRPC_TX_SMSS RXRPC_JUMBO_DATALEN #define RXRPC_MIN_CWND 4 - u8 cong_cwnd; /* Congestion window size */ + enum rxrpc_ca_state cong_ca_state; /* Congestion control state */ u8 cong_extra; /* Extra to send for congestion management */ - u8 cong_ssthresh; /* Slow-start threshold */ - enum rxrpc_congest_mode cong_mode:8; /* Congestion management mode */ - u8 cong_dup_acks; /* Count of ACKs showing missing packets */ - u8 cong_cumul_acks; /* Cumulative ACK count */ + u16 cong_cwnd; /* Congestion window size */ + u16 cong_ssthresh; /* Slow-start threshold */ + u16 cong_dup_acks; /* Count of ACKs showing missing packets */ + u16 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ - struct sk_buff *cong_last_nack; /* Last ACK with nacks received */ + + /* RACK-TLP [RFC8985] state. */ + ktime_t rack_xmit_ts; /* Latest transmission timestamp */ + ktime_t rack_rtt; /* RTT of most recently ACK'd segment */ + ktime_t rack_rtt_ts; /* Timestamp of rack_rtt */ + ktime_t rack_reo_wnd; /* Reordering window */ + unsigned int rack_reo_wnd_mult; /* Multiplier applied to rack_reo_wnd */ + int rack_reo_wnd_persist; /* Num loss recoveries before reset reo_wnd */ + rxrpc_seq_t rack_fack; /* Highest sequence so far ACK'd */ + rxrpc_seq_t rack_end_seq; /* Highest sequence seen */ + rxrpc_seq_t rack_dsack_round; /* DSACK opt recv'd in latest roundtrip */ + bool rack_dsack_round_none; /* T if dsack_round is "None" */ + bool rack_reordering_seen; /* T if detected reordering event */ + enum rxrpc_rack_timer_mode rack_timer_mode; /* Current mode of RACK timer */ + bool tlp_is_retrans; /* T if unacked TLP retransmission */ + rxrpc_serial_t tlp_serial; /* Serial of TLP probe (or 0 if none in progress) */ + rxrpc_seq_t tlp_seq; /* Sequence of TLP probe */ + unsigned int tlp_rtt_taken; /* Last time RTT taken */ + ktime_t tlp_max_ack_delay; /* Sender budget for max delayed ACK interval */ /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ @@ -730,32 +783,45 @@ struct rxrpc_call { /* Transmission-phase ACK management (ACKs we've received). */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ - rxrpc_seq_t acks_first_seq; /* first sequence number received */ + rxrpc_seq_t acks_hard_ack; /* Highest sequence hard acked */ rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ - rxrpc_seq_t acks_hard_ack; /* Latest hard-ack point */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_serial_t acks_highest_serial; /* Highest serial number ACK'd */ + unsigned short acks_nr_sacks; /* Number of soft acks recorded */ + unsigned short acks_nr_snacks; /* Number of soft nacks recorded */ + + /* Calculated RTT cache */ + ktime_t rtt_last_req; /* Time of last RTT request */ + unsigned int rtt_count; /* Number of samples we've got */ + unsigned int rtt_taken; /* Number of samples taken (wrapping) */ + struct minmax min_rtt; /* Estimated minimum RTT */ + u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + u32 mdev_us; /* medium deviation */ + u32 mdev_max_us; /* maximal mdev for the last rtt period */ + u32 rttvar_us; /* smoothed mdev_max */ + u32 rto_us; /* Retransmission timeout in usec */ + u8 backoff; /* Backoff timeout (as shift) */ }; /* * Summary of a new ACK and the changes it made to the Tx buffer packet states. */ struct rxrpc_ack_summary { - u16 nr_acks; /* Number of ACKs in packet */ - u16 nr_new_acks; /* Number of new ACKs in packet */ - u16 nr_new_nacks; /* Number of new nacks in packet */ - u16 nr_retained_nacks; /* Number of nacks retained between ACKs */ - u8 ack_reason; - bool saw_nacks; /* Saw NACKs in packet */ - bool new_low_nack; /* T if new low NACK found */ - bool retrans_timeo; /* T if reTx due to timeout happened */ - u8 flight_size; /* Number of unreceived transmissions */ - /* Place to stash values for tracing */ - enum rxrpc_congest_mode mode:8; - u8 cwnd; - u8 ssthresh; - u8 dup_acks; - u8 cumulative_acks; + rxrpc_serial_t ack_serial; /* Serial number of ACK */ + rxrpc_serial_t acked_serial; /* Serial number ACK'd */ + u16 in_flight; /* Number of unreceived transmissions */ + u16 nr_new_hacks; /* Number of rotated new ACKs */ + u16 nr_new_sacks; /* Number of new soft ACKs in packet */ + u16 nr_new_snacks; /* Number of new soft nacks in packet */ + u8 ack_reason; + bool new_low_snack:1; /* T if new low soft NACK found */ + bool retrans_timeo:1; /* T if reTx due to timeout happened */ + bool need_retransmit:1; /* T if we need transmission */ + bool rtt_sample_avail:1; /* T if RTT sample available */ + bool in_fast_or_rto_recovery:1; + bool exiting_fast_or_rto_recovery:1; + bool tlp_probe_acked:1; /* T if the TLP probe seq was acked */ + u8 /*enum rxrpc_congest_change*/ change; }; /* @@ -793,25 +859,23 @@ struct rxrpc_send_params { * Buffer of data to be output as a packet. */ struct rxrpc_txbuf { - struct list_head call_link; /* Link in call->tx_sendmsg/tx_buffer */ - struct list_head tx_link; /* Link in live Enc queue or Tx queue */ - ktime_t last_sent; /* Time at which last transmitted */ refcount_t ref; rxrpc_seq_t seq; /* Sequence number of this packet */ rxrpc_serial_t serial; /* Last serial number transmitted with */ unsigned int call_debug_id; unsigned int debug_id; - unsigned int len; /* Amount of data in buffer */ - unsigned int space; /* Remaining data space */ - unsigned int offset; /* Offset of fill point */ + unsigned short len; /* Amount of data in buffer */ + unsigned short space; /* Remaining data space */ + unsigned short offset; /* Offset of fill point */ + unsigned short pkt_len; /* Size of packet content */ + unsigned short alloc_size; /* Amount of bufferage allocated */ unsigned int flags; #define RXRPC_TXBUF_WIRE_FLAGS 0xff /* The wire protocol flags */ #define RXRPC_TXBUF_RESENT 0x100 /* Set if has been resent */ __be16 cksum; /* Checksum to go in header */ - unsigned short ack_rwind; /* ACK receive window */ - u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ + bool jumboable; /* Can be non-terminal jumbo subpacket */ u8 nr_kvec; /* Amount of kvec[] used */ - struct kvec kvec[3]; + struct kvec kvec[1]; }; static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) @@ -824,6 +888,46 @@ static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) return !rxrpc_sending_to_server(txb); } +/* + * Transmit queue element, including RACK [RFC8985] per-segment metadata. The + * transmission timestamp is in usec from the base. + */ +struct rxrpc_txqueue { + /* Start with the members we want to prefetch. */ + struct rxrpc_txqueue *next; + ktime_t xmit_ts_base; + rxrpc_seq_t qbase; + u8 nr_reported_acks; /* Number of segments explicitly acked/nacked */ + unsigned long segment_acked; /* Bit-per-buf: Set if ACK'd */ + unsigned long segment_lost; /* Bit-per-buf: Set if declared lost */ + unsigned long segment_retransmitted; /* Bit-per-buf: Set if retransmitted */ + unsigned long rtt_samples; /* Bit-per-buf: Set if available for RTT */ + unsigned long ever_retransmitted; /* Bit-per-buf: Set if ever retransmitted */ + + /* The arrays we want to pack into as few cache lines as possible. */ + struct { +#define RXRPC_NR_TXQUEUE BITS_PER_LONG +#define RXRPC_TXQ_MASK (RXRPC_NR_TXQUEUE - 1) + struct rxrpc_txbuf *bufs[RXRPC_NR_TXQUEUE]; + unsigned int segment_serial[RXRPC_NR_TXQUEUE]; + unsigned int segment_xmit_ts[RXRPC_NR_TXQUEUE]; + } ____cacheline_aligned; +}; + +/* + * Data transmission request. + */ +struct rxrpc_send_data_req { + ktime_t now; /* Current time */ + struct rxrpc_txqueue *tq; /* Tx queue segment holding first DATA */ + rxrpc_seq_t seq; /* Sequence of first data */ + int n; /* Number of DATA packets to glue into jumbo */ + bool retrans; /* T if this is a retransmission */ + bool did_send; /* T if did actually send */ + bool tlp_probe; /* T if this is a TLP probe */ + int /* enum rxrpc_txdata_trace */ trace; +}; + #include /* @@ -840,6 +944,21 @@ static inline rxrpc_serial_t rxrpc_get_next_serial(struct rxrpc_connection *conn return serial; } +/* + * Allocate the next serial n numbers on a connection. 0 must be skipped. + */ +static inline rxrpc_serial_t rxrpc_get_next_serials(struct rxrpc_connection *conn, + unsigned int n) +{ + rxrpc_serial_t serial; + + serial = conn->tx_serial; + if (serial + n <= n) + serial = 1; + conn->tx_serial = serial + n; + return serial; +} + /* * af_rxrpc.c */ @@ -865,10 +984,10 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why); void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); -void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); -void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb); - -bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); +void rxrpc_resend_tlp(struct rxrpc_call *call); +void rxrpc_transmit_some_data(struct rxrpc_call *call, unsigned int limit, + enum rxrpc_txdata_trace trace); +bool rxrpc_input_call_event(struct rxrpc_call *call); /* * call_object.c @@ -1046,6 +1165,32 @@ void rxrpc_congestion_degrade(struct rxrpc_call *); void rxrpc_input_call_packet(struct rxrpc_call *, struct sk_buff *); void rxrpc_implicit_end_call(struct rxrpc_call *, struct sk_buff *); +/* + * input_rack.c + */ +void rxrpc_input_rack_one(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + unsigned int ix); +void rxrpc_input_rack(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + unsigned long new_acks); +void rxrpc_rack_detect_loss_and_arm_timer(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary); +ktime_t rxrpc_tlp_calc_pto(struct rxrpc_call *call, ktime_t now); +void rxrpc_tlp_send_probe(struct rxrpc_call *call); +void rxrpc_tlp_process_ack(struct rxrpc_call *call, struct rxrpc_ack_summary *summary); +void rxrpc_rack_timer_expired(struct rxrpc_call *call, ktime_t overran_by); + +/* Initialise TLP state [RFC8958 7.1]. */ +static inline void rxrpc_tlp_init(struct rxrpc_call *call) +{ + call->tlp_serial = 0; + call->tlp_seq = call->acks_hard_ack; + call->tlp_is_retrans = false; +} + /* * io_thread.c */ @@ -1149,17 +1294,20 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) */ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why); +void rxrpc_send_probe_for_pmtud(struct rxrpc_call *call); int rxrpc_send_abort_packet(struct rxrpc_call *); +void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req *req); void rxrpc_send_conn_abort(struct rxrpc_connection *conn); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); -void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb); /* * peer_event.c */ void rxrpc_input_error(struct rxrpc_local *, struct sk_buff *); void rxrpc_peer_keepalive_worker(struct work_struct *); +void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t acked_serial, + bool sendmsg_fail); /* * peer_object.c @@ -1208,10 +1356,12 @@ static inline int rxrpc_abort_eproto(struct rxrpc_call *call, /* * rtt.c */ -void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, - rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); -ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans); -void rxrpc_peer_init_rtt(struct rxrpc_peer *); +void rxrpc_call_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + int rtt_slot, + rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, + ktime_t send_time, ktime_t resp_time); +ktime_t rxrpc_get_rto_backoff(struct rxrpc_call *call, bool retrans); +void rxrpc_call_init_rtt(struct rxrpc_call *call); /* * rxkad.c @@ -1284,7 +1434,6 @@ static inline void rxrpc_sysctl_exit(void) {} extern atomic_t rxrpc_nr_txbuf; struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, size_t data_align, gfp_t gfp); -struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_size); void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); @@ -1311,6 +1460,53 @@ static inline bool after_eq(u32 seq1, u32 seq2) return (s32)(seq1 - seq2) >= 0; } +static inline u32 earliest(u32 seq1, u32 seq2) +{ + return before(seq1, seq2) ? seq1 : seq2; +} + +static inline u32 latest(u32 seq1, u32 seq2) +{ + return after(seq1, seq2) ? seq1 : seq2; +} + +static inline bool rxrpc_seq_in_txq(const struct rxrpc_txqueue *tq, rxrpc_seq_t seq) +{ + return (seq & (RXRPC_NR_TXQUEUE - 1)) == tq->qbase; +} + +static inline void rxrpc_queue_rx_call_packet(struct rxrpc_call *call, struct sk_buff *skb) +{ + rxrpc_get_skb(skb, rxrpc_skb_get_call_rx); + __skb_queue_tail(&call->rx_queue, skb); + rxrpc_poke_call(call, rxrpc_call_poke_rx_packet); +} + +/* + * Calculate how much space there is for transmitting more DATA packets. + */ +static inline unsigned int rxrpc_tx_window_space(const struct rxrpc_call *call) +{ + int winsize = umin(call->tx_winsize, call->cong_cwnd + call->cong_extra); + int transmitted = call->tx_top - call->tx_bottom; + + return max(winsize - transmitted, 0); +} + +static inline unsigned int rxrpc_left_out(const struct rxrpc_call *call) +{ + return call->acks_nr_sacks + call->tx_nr_lost; +} + +/* + * Calculate the number of transmitted DATA packets assumed to be in flight + * [approx RFC6675]. + */ +static inline unsigned int rxrpc_tx_in_flight(const struct rxrpc_call *call) +{ + return call->tx_nr_sent - rxrpc_left_out(call) + call->tx_nr_resent; +} + /* * debug tracing */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 0f5a1d77b890..e685034ce4f7 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -188,8 +188,8 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) /* Make sure that there aren't any incoming calls in progress before we * clear the preallocation buffers. */ - spin_lock(&rx->incoming_lock); - spin_unlock(&rx->incoming_lock); + spin_lock_irq(&rx->incoming_lock); + spin_unlock_irq(&rx->incoming_lock); head = b->peer_backlog_head; tail = b->peer_backlog_tail; @@ -343,7 +343,7 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, if (sp->hdr.type != RXRPC_PACKET_TYPE_DATA) return rxrpc_protocol_error(skb, rxrpc_eproto_no_service_call); - read_lock(&local->services_lock); + read_lock_irq(&local->services_lock); /* Weed out packets to services we're not offering. Packets that would * begin a call are explicitly rejected and the rest are just @@ -399,34 +399,34 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, spin_unlock(&conn->state_lock); spin_unlock(&rx->incoming_lock); - read_unlock(&local->services_lock); + read_unlock_irq(&local->services_lock); if (hlist_unhashed(&call->error_link)) { - spin_lock(&call->peer->lock); + spin_lock_irq(&call->peer->lock); hlist_add_head(&call->error_link, &call->peer->error_targets); - spin_unlock(&call->peer->lock); + spin_unlock_irq(&call->peer->lock); } _leave(" = %p{%d}", call, call->debug_id); - rxrpc_input_call_event(call, skb); + rxrpc_queue_rx_call_packet(call, skb); rxrpc_put_call(call, rxrpc_call_put_input); return true; unsupported_service: - read_unlock(&local->services_lock); + read_unlock_irq(&local->services_lock); return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, RX_INVALID_OPERATION, -EOPNOTSUPP); unsupported_security: - read_unlock(&local->services_lock); + read_unlock_irq(&local->services_lock); return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, RX_INVALID_OPERATION, -EKEYREJECTED); no_call: spin_unlock(&rx->incoming_lock); - read_unlock(&local->services_lock); + read_unlock_irq(&local->services_lock); _leave(" = f [%u]", skb->mark); return false; discard: - read_unlock(&local->services_lock); + read_unlock_irq(&local->services_lock); return true; } diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 7bbb68504766..8e477f7f8850 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -44,8 +44,8 @@ void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial); - if (call->peer->srtt_us) - delay = (call->peer->srtt_us >> 3) * NSEC_PER_USEC; + if (call->srtt_us) + delay = (call->srtt_us >> 3) * NSEC_PER_USEC; else delay = ms_to_ktime(READ_ONCE(rxrpc_soft_ack_delay)); ktime_add_ms(delay, call->tx_backoff); @@ -55,149 +55,106 @@ void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, } /* - * Handle congestion being detected by the retransmit timeout. + * Retransmit one or more packets. */ -static void rxrpc_congestion_timeout(struct rxrpc_call *call) +static bool rxrpc_retransmit_data(struct rxrpc_call *call, + struct rxrpc_send_data_req *req) { - set_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags); + struct rxrpc_txqueue *tq = req->tq; + unsigned int ix = req->seq & RXRPC_TXQ_MASK; + struct rxrpc_txbuf *txb = tq->bufs[ix]; + + _enter("%x,%x,%x,%x", tq->qbase, req->seq, ix, txb->debug_id); + + req->retrans = true; + trace_rxrpc_retransmit(call, req, txb); + + txb->flags |= RXRPC_TXBUF_RESENT; + rxrpc_send_data_packet(call, req); + rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); + + req->tq = NULL; + req->n = 0; + req->did_send = true; + req->now = ktime_get_real(); + return true; } /* * Perform retransmission of NAK'd and unack'd packets. */ -void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) +static void rxrpc_resend(struct rxrpc_call *call) { - struct rxrpc_ackpacket *ack = NULL; - struct rxrpc_skb_priv *sp; - struct rxrpc_txbuf *txb; - rxrpc_seq_t transmitted = call->tx_transmitted; - ktime_t next_resend = KTIME_MAX, rto = ns_to_ktime(call->peer->rto_us * NSEC_PER_USEC); - ktime_t resend_at = KTIME_MAX, now, delay; - bool unacked = false, did_send = false; - unsigned int i; + struct rxrpc_send_data_req req = { + .now = ktime_get_real(), + .trace = rxrpc_txdata_retransmit, + }; + struct rxrpc_txqueue *tq; - _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); + _enter("{%d,%d}", call->tx_bottom, call->tx_top); - now = ktime_get_real(); + trace_rxrpc_resend(call, call->acks_highest_serial); - if (list_empty(&call->tx_buffer)) - goto no_resend; + /* Scan the transmission queue, looking for lost packets. */ + for (tq = call->tx_queue; tq; tq = tq->next) { + unsigned long lost = tq->segment_lost; - trace_rxrpc_resend(call, ack_skb); - txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); + if (after(tq->qbase, call->tx_transmitted)) + break; - /* Scan the soft ACK table without dropping the lock and resend any - * explicitly NAK'd packets. - */ - if (ack_skb) { - sp = rxrpc_skb(ack_skb); - ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); + _debug("retr %16lx %u c=%08x [%x]", + tq->segment_acked, tq->nr_reported_acks, call->debug_id, tq->qbase); + _debug("lost %16lx", lost); - for (i = 0; i < sp->ack.nr_acks; i++) { - rxrpc_seq_t seq; + trace_rxrpc_resend_lost(call, tq, lost); + while (lost) { + unsigned int ix = __ffs(lost); + struct rxrpc_txbuf *txb = tq->bufs[ix]; - if (ack->acks[i] & 1) - continue; - seq = sp->ack.first_ack + i; - if (after(txb->seq, transmitted)) - break; - if (after(txb->seq, seq)) - continue; /* A new hard ACK probably came in */ - list_for_each_entry_from(txb, &call->tx_buffer, call_link) { - if (txb->seq == seq) - goto found_txb; - } - goto no_further_resend; + __clear_bit(ix, &lost); + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_lost); - found_txb: - resend_at = ktime_add(txb->last_sent, rto); - if (after(txb->serial, call->acks_highest_serial)) { - if (ktime_after(resend_at, now) && - ktime_before(resend_at, next_resend)) - next_resend = resend_at; - continue; /* Ack point not yet reached */ - } - - rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); - - trace_rxrpc_retransmit(call, txb->seq, txb->serial, - ktime_sub(resend_at, now)); - - txb->flags |= RXRPC_TXBUF_RESENT; - rxrpc_transmit_one(call, txb); - did_send = true; - now = ktime_get_real(); - - if (list_is_last(&txb->call_link, &call->tx_buffer)) - goto no_further_resend; - txb = list_next_entry(txb, call_link); + req.tq = tq; + req.seq = tq->qbase + ix; + req.n = 1; + rxrpc_retransmit_data(call, &req); } } - /* Fast-forward through the Tx queue to the point the peer says it has - * seen. Anything between the soft-ACK table and that point will get - * ACK'd or NACK'd in due course, so don't worry about it here; here we - * need to consider retransmitting anything beyond that point. - */ - if (after_eq(call->acks_prev_seq, call->tx_transmitted)) - goto no_further_resend; - - list_for_each_entry_from(txb, &call->tx_buffer, call_link) { - resend_at = ktime_add(txb->last_sent, rto); - - if (before_eq(txb->seq, call->acks_prev_seq)) - continue; - if (after(txb->seq, call->tx_transmitted)) - break; /* Not transmitted yet */ - - if (ack && ack->reason == RXRPC_ACK_PING_RESPONSE && - before(txb->serial, ntohl(ack->serial))) - goto do_resend; /* Wasn't accounted for by a more recent ping. */ - - if (ktime_after(resend_at, now)) { - if (ktime_before(resend_at, next_resend)) - next_resend = resend_at; - continue; - } - - do_resend: - unacked = true; - - txb->flags |= RXRPC_TXBUF_RESENT; - rxrpc_transmit_one(call, txb); - did_send = true; - rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); - now = ktime_get_real(); - } - -no_further_resend: -no_resend: - if (resend_at < KTIME_MAX) { - delay = rxrpc_get_rto_backoff(call->peer, did_send); - resend_at = ktime_add(resend_at, delay); - trace_rxrpc_timer_set(call, resend_at - now, rxrpc_timer_trace_resend_reset); - } - call->resend_at = resend_at; - - if (unacked) - rxrpc_congestion_timeout(call); - - /* If there was nothing that needed retransmission then it's likely - * that an ACK got lost somewhere. Send a ping to find out instead of - * retransmitting data. - */ - if (!did_send) { - ktime_t next_ping = ktime_add_us(call->acks_latest_ts, - call->peer->srtt_us >> 3); - - if (ktime_sub(next_ping, now) <= 0) - rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, - rxrpc_propose_ack_ping_for_0_retrans); - } - + rxrpc_get_rto_backoff(call, req.did_send); _leave(""); } +/* + * Resend the highest-seq DATA packet so far transmitted for RACK-TLP [RFC8985 7.3]. + */ +void rxrpc_resend_tlp(struct rxrpc_call *call) +{ + struct rxrpc_send_data_req req = { + .now = ktime_get_real(), + .seq = call->tx_transmitted, + .n = 1, + .tlp_probe = true, + .trace = rxrpc_txdata_tlp_retransmit, + }; + + /* There's a chance it'll be on the tail segment of the queue. */ + req.tq = READ_ONCE(call->tx_qtail); + if (req.tq && + before(call->tx_transmitted, req.tq->qbase + RXRPC_NR_TXQUEUE)) { + rxrpc_retransmit_data(call, &req); + return; + } + + for (req.tq = call->tx_queue; req.tq; req.tq = req.tq->next) { + if (after_eq(call->tx_transmitted, req.tq->qbase) && + before(call->tx_transmitted, req.tq->qbase + RXRPC_NR_TXQUEUE)) { + rxrpc_retransmit_data(call, &req); + return; + } + } +} + /* * Start transmitting the reply to a service. This cancels the need to ACK the * request if we haven't yet done so. @@ -231,68 +188,93 @@ static void rxrpc_close_tx_phase(struct rxrpc_call *call) } } -static bool rxrpc_tx_window_has_space(struct rxrpc_call *call) -{ - unsigned int winsize = min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra); - rxrpc_seq_t window = call->acks_hard_ack, wtop = window + winsize; - rxrpc_seq_t tx_top = call->tx_top; - int space; - - space = wtop - tx_top; - return space > 0; -} - /* - * Decant some if the sendmsg prepared queue into the transmission buffer. + * Transmit some as-yet untransmitted data, to a maximum of the supplied limit. */ -static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) +static void rxrpc_transmit_fresh_data(struct rxrpc_call *call, unsigned int limit, + enum rxrpc_txdata_trace trace) { - struct rxrpc_txbuf *txb; + int space = rxrpc_tx_window_space(call); if (!test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { - if (list_empty(&call->tx_sendmsg)) + if (call->send_top == call->tx_top) return; rxrpc_expose_client_call(call); } - while ((txb = list_first_entry_or_null(&call->tx_sendmsg, - struct rxrpc_txbuf, call_link))) { - spin_lock(&call->tx_lock); - list_del(&txb->call_link); - spin_unlock(&call->tx_lock); + while (space > 0) { + struct rxrpc_send_data_req req = { + .now = ktime_get_real(), + .seq = call->tx_transmitted + 1, + .n = 0, + .trace = trace, + }; + struct rxrpc_txqueue *tq; + struct rxrpc_txbuf *txb; + rxrpc_seq_t send_top, seq; + int limit = min(space, max(call->peer->pmtud_jumbo, 1)); - call->tx_top = txb->seq; - list_add_tail(&txb->call_link, &call->tx_buffer); - - if (txb->flags & RXRPC_LAST_PACKET) - rxrpc_close_tx_phase(call); - - rxrpc_transmit_one(call, txb); - - if (!rxrpc_tx_window_has_space(call)) + /* Order send_top before the contents of the new txbufs and + * txqueue pointers + */ + send_top = smp_load_acquire(&call->send_top); + if (call->tx_top == send_top) break; + + trace_rxrpc_transmit(call, send_top, space); + + tq = call->tx_qtail; + seq = call->tx_top; + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_decant); + + do { + int ix; + + seq++; + ix = seq & RXRPC_TXQ_MASK; + if (!ix) { + tq = tq->next; + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_decant_advance); + } + if (!req.tq) + req.tq = tq; + txb = tq->bufs[ix]; + req.n++; + if (!txb->jumboable) + break; + } while (req.n < limit && before(seq, send_top)); + + if (txb->flags & RXRPC_LAST_PACKET) { + rxrpc_close_tx_phase(call); + tq = NULL; + } + call->tx_qtail = tq; + call->tx_top = seq; + + space -= req.n; + rxrpc_send_data_packet(call, &req); } } -static void rxrpc_transmit_some_data(struct rxrpc_call *call) +void rxrpc_transmit_some_data(struct rxrpc_call *call, unsigned int limit, + enum rxrpc_txdata_trace trace) { switch (__rxrpc_call_state(call)) { case RXRPC_CALL_SERVER_ACK_REQUEST: - if (list_empty(&call->tx_sendmsg)) + if (call->tx_bottom == READ_ONCE(call->send_top)) return; rxrpc_begin_service_reply(call); fallthrough; case RXRPC_CALL_SERVER_SEND_REPLY: case RXRPC_CALL_CLIENT_SEND_REQUEST: - if (!rxrpc_tx_window_has_space(call)) + if (!rxrpc_tx_window_space(call)) return; - if (list_empty(&call->tx_sendmsg)) { + if (call->tx_bottom == READ_ONCE(call->send_top)) { rxrpc_inc_stat(call->rxnet, stat_tx_data_underflow); return; } - rxrpc_decant_prepared_tx(call); + rxrpc_transmit_fresh_data(call, limit, trace); break; default: return; @@ -305,8 +287,8 @@ static void rxrpc_transmit_some_data(struct rxrpc_call *call) */ static void rxrpc_send_initial_ping(struct rxrpc_call *call) { - if (call->peer->rtt_count < 3 || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), + if (call->rtt_count < 3 || + ktime_before(ktime_add_ms(call->rtt_last_req, 1000), ktime_get_real())) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_params); @@ -315,10 +297,11 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call) /* * Handle retransmission and deferred ACK/abort generation. */ -bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) +bool rxrpc_input_call_event(struct rxrpc_call *call) { + struct sk_buff *skb; ktime_t now, t; - bool resend = false; + bool did_receive = false, saw_ack = false; s32 abort_code; rxrpc_see_call(call, rxrpc_call_see_input); @@ -328,9 +311,6 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)], call->events); - if (__rxrpc_call_is_complete(call)) - goto out; - /* Handle abort request locklessly, vs rxrpc_propose_abort(). */ abort_code = smp_load_acquire(&call->send_abort); if (abort_code) { @@ -339,11 +319,33 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) goto out; } - if (skb && skb->mark == RXRPC_SKB_MARK_ERROR) - goto out; + do { + skb = __skb_dequeue(&call->rx_queue); + if (skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - if (skb) - rxrpc_input_call_packet(call, skb); + if (__rxrpc_call_is_complete(call) || + skb->mark == RXRPC_SKB_MARK_ERROR) { + rxrpc_free_skb(skb, rxrpc_skb_put_call_rx); + goto out; + } + + saw_ack |= sp->hdr.type == RXRPC_PACKET_TYPE_ACK; + + rxrpc_input_call_packet(call, skb); + rxrpc_free_skb(skb, rxrpc_skb_put_call_rx); + did_receive = true; + } + + t = ktime_sub(call->rack_timo_at, ktime_get_real()); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, + rxrpc_timer_trace_rack_off + call->rack_timer_mode); + call->rack_timo_at = KTIME_MAX; + rxrpc_rack_timer_expired(call, t); + } + + } while (!skb_queue_empty(&call->rx_queue)); /* If we see our async-event poke, check for timeout trippage. */ now = ktime_get_real(); @@ -376,13 +378,6 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_propose_ack_delayed_ack); } - t = ktime_sub(call->ack_lost_at, now); - if (t <= 0) { - trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_lost_ack); - call->ack_lost_at = KTIME_MAX; - set_bit(RXRPC_CALL_EV_ACK_LOST, &call->events); - } - t = ktime_sub(call->ping_at, now); if (t <= 0) { trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_ping); @@ -391,15 +386,6 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_propose_ack_ping_for_keepalive); } - t = ktime_sub(call->resend_at, now); - if (t <= 0) { - trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_resend); - call->resend_at = KTIME_MAX; - resend = true; - } - - rxrpc_transmit_some_data(call); - now = ktime_get_real(); t = ktime_sub(call->keepalive_at, now); if (t <= 0) { @@ -409,35 +395,40 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_propose_ack_ping_for_keepalive); } - if (skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - if (sp->hdr.type == RXRPC_PACKET_TYPE_ACK) - rxrpc_congestion_degrade(call); - } - if (test_and_clear_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events)) rxrpc_send_initial_ping(call); + rxrpc_transmit_some_data(call, UINT_MAX, rxrpc_txdata_new_data); + + if (saw_ack) + rxrpc_congestion_degrade(call); + + if (did_receive && + (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_SEND_REQUEST || + __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SEND_REPLY)) { + t = ktime_sub(call->rack_timo_at, ktime_get_real()); + trace_rxrpc_rack(call, t); + } + /* Process events */ if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_lost_ack); - if (resend && + if (call->tx_nr_lost > 0 && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY && !test_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags)) - rxrpc_resend(call, NULL); + rxrpc_resend(call); if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) rxrpc_send_ACK(call, RXRPC_ACK_IDLE, 0, rxrpc_propose_ack_rx_idle); if (call->ackr_nr_unacked > 2) { - if (call->peer->rtt_count < 3) + if (call->rtt_count < 3) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_rtt); - else if (ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), + else if (ktime_before(ktime_add_ms(call->rtt_last_req, 1000), ktime_get_real())) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_old_rtt); @@ -455,8 +446,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) set(call->expect_req_by); set(call->expect_rx_by); set(call->delay_ack_at); - set(call->ack_lost_at); - set(call->resend_at); + set(call->rack_timo_at); set(call->keepalive_at); set(call->ping_at); @@ -467,7 +457,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) } else { unsigned long nowj = jiffies, delayj, nextj; - delayj = max(nsecs_to_jiffies(delay), 1); + delayj = umax(nsecs_to_jiffies(delay), 1); nextj = nowj + delayj; if (time_before(nextj, call->timer.expires) || !timer_pending(&call->timer)) { @@ -484,9 +474,12 @@ out: rxrpc_disconnect_call(call); if (call->security) call->security->free_call_crypto(call); + } else { + if (did_receive && + call->peer->ackr_adv_pmtud && + call->peer->pmtud_pending) + rxrpc_send_probe_for_pmtud(call); } - if (call->acks_hard_ack != call->tx_bottom) - rxrpc_shrink_call_tx_buffer(call); _leave(""); return true; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f9e983a12c14..5a543c3f6fb0 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -49,7 +49,7 @@ void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) bool busy; if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) { - spin_lock_bh(&local->lock); + spin_lock_irq(&local->lock); busy = !list_empty(&call->attend_link); trace_rxrpc_poke_call(call, busy, what); if (!busy && !rxrpc_try_get_call(call, rxrpc_call_get_poke)) @@ -57,7 +57,7 @@ void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) if (!busy) { list_add_tail(&call->attend_link, &local->call_attend_q); } - spin_unlock_bh(&local->lock); + spin_unlock_irq(&local->lock); if (!busy) rxrpc_wake_up_io_thread(local); } @@ -146,23 +146,21 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); INIT_LIST_HEAD(&call->attend_link); - INIT_LIST_HEAD(&call->tx_sendmsg); - INIT_LIST_HEAD(&call->tx_buffer); + skb_queue_head_init(&call->rx_queue); skb_queue_head_init(&call->recvmsg_queue); skb_queue_head_init(&call->rx_oos_queue); init_waitqueue_head(&call->waitq); spin_lock_init(&call->notify_lock); - spin_lock_init(&call->tx_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; call->tx_total_len = -1; + call->tx_jumbo_max = 1; call->next_rx_timo = 20 * HZ; call->next_req_timo = 1 * HZ; call->ackr_window = 1; call->ackr_wtop = 1; call->delay_ack_at = KTIME_MAX; - call->ack_lost_at = KTIME_MAX; - call->resend_at = KTIME_MAX; + call->rack_timo_at = KTIME_MAX; call->ping_at = KTIME_MAX; call->keepalive_at = KTIME_MAX; call->expect_rx_by = KTIME_MAX; @@ -177,6 +175,8 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->cong_cwnd = RXRPC_MIN_CWND; call->cong_ssthresh = RXRPC_TX_MAX_WINDOW; + rxrpc_call_init_rtt(call); + call->rxnet = rxnet; call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK; atomic_inc(&rxnet->nr_calls); @@ -220,9 +220,9 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, __set_bit(RXRPC_CALL_EXCLUSIVE, &call->flags); if (p->timeouts.normal) - call->next_rx_timo = min(p->timeouts.normal, 1); + call->next_rx_timo = umin(p->timeouts.normal, 1); if (p->timeouts.idle) - call->next_req_timo = min(p->timeouts.idle, 1); + call->next_req_timo = umin(p->timeouts.idle, 1); if (p->timeouts.hard) call->hard_timo = p->timeouts.hard; @@ -302,9 +302,9 @@ static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp) trace_rxrpc_client(NULL, -1, rxrpc_client_queue_new_call); rxrpc_get_call(call, rxrpc_call_get_io_thread); - spin_lock(&local->client_call_lock); + spin_lock_irq(&local->client_call_lock); list_add_tail(&call->wait_link, &local->new_client_calls); - spin_unlock(&local->client_call_lock); + spin_unlock_irq(&local->client_call_lock); rxrpc_wake_up_io_thread(local); return 0; @@ -434,7 +434,7 @@ error_attached_to_socket: /* * Set up an incoming call. call->conn points to the connection. - * This is called in BH context and isn't allowed to fail. + * This is called with interrupts disabled and isn't allowed to fail. */ void rxrpc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_call *call, @@ -531,11 +531,29 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace why) } /* - * Clean up the Rx skb ring. + * Clean up the transmission buffers. */ -static void rxrpc_cleanup_ring(struct rxrpc_call *call) +static void rxrpc_cleanup_tx_buffers(struct rxrpc_call *call) +{ + struct rxrpc_txqueue *tq, *next; + + for (tq = call->tx_queue; tq; tq = next) { + next = tq->next; + for (int i = 0; i < RXRPC_NR_TXQUEUE; i++) + if (tq->bufs[i]) + rxrpc_put_txbuf(tq->bufs[i], rxrpc_txbuf_put_cleaned); + trace_rxrpc_tq(call, tq, 0, rxrpc_tq_cleaned); + kfree(tq); + } +} + +/* + * Clean up the receive buffers. + */ +static void rxrpc_cleanup_rx_buffers(struct rxrpc_call *call) { rxrpc_purge_queue(&call->recvmsg_queue); + rxrpc_purge_queue(&call->rx_queue); rxrpc_purge_queue(&call->rx_oos_queue); } @@ -558,7 +576,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) rxrpc_put_call_slot(call); /* Make sure we don't get any more notifications */ - spin_lock(&rx->recvmsg_lock); + spin_lock_irq(&rx->recvmsg_lock); if (!list_empty(&call->recvmsg_link)) { _debug("unlinking once-pending call %p { e=%lx f=%lx }", @@ -571,7 +589,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) call->recvmsg_link.next = NULL; call->recvmsg_link.prev = NULL; - spin_unlock(&rx->recvmsg_lock); + spin_unlock_irq(&rx->recvmsg_lock); if (put) rxrpc_put_call(call, rxrpc_call_put_unnotify); @@ -671,23 +689,11 @@ static void rxrpc_rcu_free_call(struct rcu_head *rcu) static void rxrpc_destroy_call(struct work_struct *work) { struct rxrpc_call *call = container_of(work, struct rxrpc_call, destroyer); - struct rxrpc_txbuf *txb; del_timer_sync(&call->timer); - rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack); - rxrpc_cleanup_ring(call); - while ((txb = list_first_entry_or_null(&call->tx_sendmsg, - struct rxrpc_txbuf, call_link))) { - list_del(&txb->call_link); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); - } - while ((txb = list_first_entry_or_null(&call->tx_buffer, - struct rxrpc_txbuf, call_link))) { - list_del(&txb->call_link); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); - } - + rxrpc_cleanup_tx_buffers(call); + rxrpc_cleanup_rx_buffers(call); rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); rxrpc_put_connection(call->conn, rxrpc_conn_put_call); rxrpc_deactivate_bundle(call->bundle); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index bb11e8289d6d..db0099197890 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -231,7 +231,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) distance = id - id_cursor; if (distance < 0) distance = -distance; - limit = max_t(unsigned long, atomic_read(&rxnet->nr_conns) * 4, 1024); + limit = umax(atomic_read(&rxnet->nr_conns) * 4, 1024); if (distance > limit) goto mark_dont_reuse; @@ -437,9 +437,9 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, call->dest_srx.srx_service = conn->service_id; call->cong_ssthresh = call->peer->cong_ssthresh; if (call->cong_cwnd >= call->cong_ssthresh) - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + call->cong_ca_state = RXRPC_CA_CONGEST_AVOIDANCE; else - call->cong_mode = RXRPC_CALL_SLOW_START; + call->cong_ca_state = RXRPC_CA_SLOW_START; chan->call_id = call_id; chan->call_debug_id = call->debug_id; @@ -508,16 +508,18 @@ static void rxrpc_activate_channels(struct rxrpc_bundle *bundle) void rxrpc_connect_client_calls(struct rxrpc_local *local) { struct rxrpc_call *call; + LIST_HEAD(new_client_calls); - while ((call = list_first_entry_or_null(&local->new_client_calls, - struct rxrpc_call, wait_link)) - ) { + spin_lock_irq(&local->client_call_lock); + list_splice_tail_init(&local->new_client_calls, &new_client_calls); + spin_unlock_irq(&local->client_call_lock); + + while ((call = list_first_entry_or_null(&new_client_calls, + struct rxrpc_call, wait_link))) { struct rxrpc_bundle *bundle = call->bundle; - spin_lock(&local->client_call_lock); list_move_tail(&call->wait_link, &bundle->waiting_calls); rxrpc_see_call(call, rxrpc_call_see_waiting_call); - spin_unlock(&local->client_call_lock); if (rxrpc_bundle_has_space(bundle)) rxrpc_activate_channels(bundle); @@ -545,9 +547,9 @@ void rxrpc_expose_client_call(struct rxrpc_call *call) set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); trace_rxrpc_client(conn, channel, rxrpc_client_exposed); - spin_lock(&call->peer->lock); + spin_lock_irq(&call->peer->lock); hlist_add_head(&call->error_link, &call->peer->error_targets); - spin_unlock(&call->peer->lock); + spin_unlock_irq(&call->peer->lock); } } @@ -588,9 +590,9 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call ASSERTCMP(call->call_id, ==, 0); ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags)); /* May still be on ->new_client_calls. */ - spin_lock(&local->client_call_lock); + spin_lock_irq(&local->client_call_lock); list_del_init(&call->wait_link); - spin_unlock(&local->client_call_lock); + spin_unlock_irq(&local->client_call_lock); return; } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 598b4ee389fc..713e04394ceb 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -26,7 +26,7 @@ static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff bool aborted = false; if (conn->state != RXRPC_CONN_ABORTED) { - spin_lock(&conn->state_lock); + spin_lock_irq(&conn->state_lock); if (conn->state != RXRPC_CONN_ABORTED) { conn->abort_code = abort_code; conn->error = err; @@ -37,7 +37,7 @@ static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff set_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events); aborted = true; } - spin_unlock(&conn->state_lock); + spin_unlock_irq(&conn->state_lock); } return aborted; @@ -63,11 +63,12 @@ int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, /* * Mark a connection as being remotely aborted. */ -static bool rxrpc_input_conn_abort(struct rxrpc_connection *conn, +static void rxrpc_input_conn_abort(struct rxrpc_connection *conn, struct sk_buff *skb) { - return rxrpc_set_conn_aborted(conn, skb, skb->priority, -ECONNABORTED, - RXRPC_CALL_REMOTELY_ABORTED); + trace_rxrpc_rx_conn_abort(conn, skb); + rxrpc_set_conn_aborted(conn, skb, skb->priority, -ECONNABORTED, + RXRPC_CALL_REMOTELY_ABORTED); } /* @@ -91,7 +92,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct rxrpc_acktrailer trailer; size_t len; int ret, ioc; - u32 serial, mtu, call_id, padding; + u32 serial, max_mtu, if_mtu, call_id, padding; _enter("%d", conn->debug_id); @@ -149,8 +150,13 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, break; case RXRPC_PACKET_TYPE_ACK: - mtu = conn->peer->if_mtu; - mtu -= conn->peer->hdrsize; + if_mtu = conn->peer->if_mtu - conn->peer->hdrsize; + if (conn->peer->ackr_adv_pmtud) { + max_mtu = umax(conn->peer->max_data, rxrpc_rx_mtu); + } else { + if_mtu = umin(1444, if_mtu); + max_mtu = if_mtu; + } pkt.ack.bufferSpace = 0; pkt.ack.maxSkew = htons(skb ? skb->priority : 0); pkt.ack.firstPacket = htonl(chan->last_seq + 1); @@ -158,10 +164,10 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0); pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE; pkt.ack.nAcks = 0; - trailer.maxMTU = htonl(rxrpc_rx_mtu); - trailer.ifMTU = htonl(mtu); + trailer.maxMTU = htonl(max_mtu); + trailer.ifMTU = htonl(if_mtu); trailer.rwind = htonl(rxrpc_rx_window_size); - trailer.jumbo_max = htonl(rxrpc_rx_jumbo_max); + trailer.jumbo_max = 0; pkt.whdr.flags |= RXRPC_SLOW_START_OK; padding = 0; iov[0].iov_len += sizeof(pkt.ack); @@ -171,7 +177,8 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, trace_rxrpc_tx_ack(chan->call_debug_id, serial, ntohl(pkt.ack.firstPacket), ntohl(pkt.ack.serial), - pkt.ack.reason, 0, rxrpc_rx_window_size); + pkt.ack.reason, 0, rxrpc_rx_window_size, + rxrpc_propose_ack_retransmit); break; default: @@ -202,11 +209,14 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn) for (i = 0; i < RXRPC_MAXCALLS; i++) { call = conn->channels[i].call; - if (call) + if (call) { + rxrpc_see_call(call, rxrpc_call_see_conn_abort); rxrpc_set_call_completion(call, conn->completion, conn->abort_code, conn->error); + rxrpc_poke_call(call, rxrpc_call_poke_conn_abort); + } } _leave(""); @@ -252,10 +262,10 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, if (ret < 0) return ret; - spin_lock(&conn->state_lock); + spin_lock_irq(&conn->state_lock); if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) conn->state = RXRPC_CONN_SERVICE; - spin_unlock(&conn->state_lock); + spin_unlock_irq(&conn->state_lock); if (conn->state == RXRPC_CONN_SERVICE) { /* Offload call state flipping to the I/O thread. As diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 694c4df7a1a3..7eba4d7d9a38 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -31,13 +31,13 @@ void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) if (WARN_ON_ONCE(!local)) return; - spin_lock_bh(&local->lock); + spin_lock_irq(&local->lock); busy = !list_empty(&conn->attend_link); if (!busy) { rxrpc_get_connection(conn, why); list_add_tail(&conn->attend_link, &local->conn_attend_q); } - spin_unlock_bh(&local->lock); + spin_unlock_irq(&local->lock); rxrpc_wake_up_io_thread(local); } @@ -196,9 +196,9 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) call->peer->cong_ssthresh = call->cong_ssthresh; if (!hlist_unhashed(&call->error_link)) { - spin_lock(&call->peer->lock); + spin_lock_irq(&call->peer->lock); hlist_del_init(&call->error_link); - spin_unlock(&call->peer->lock); + spin_unlock_irq(&call->peer->lock); } if (rxrpc_is_client_call(call)) { @@ -321,6 +321,12 @@ static void rxrpc_clean_up_connection(struct work_struct *work) list_del_init(&conn->proc_link); write_unlock(&rxnet->conn_lock); + if (conn->pmtud_probe) { + trace_rxrpc_pmtud_lost(conn, 0); + conn->peer->pmtud_probing = false; + conn->peer->pmtud_pending = true; + } + rxrpc_purge_queue(&conn->rx_queue); rxrpc_kill_client_conn(conn); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 16d49a861dbb..4974b5accafa 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -27,80 +27,68 @@ static void rxrpc_proto_abort(struct rxrpc_call *call, rxrpc_seq_t seq, } /* - * Do TCP-style congestion management [RFC 5681]. + * Do TCP-style congestion management [RFC5681]. */ static void rxrpc_congestion_management(struct rxrpc_call *call, - struct sk_buff *skb, - struct rxrpc_ack_summary *summary, - rxrpc_serial_t acked_serial) + struct rxrpc_ack_summary *summary) { - enum rxrpc_congest_change change = rxrpc_cong_no_change; - unsigned int cumulative_acks = call->cong_cumul_acks; - unsigned int cwnd = call->cong_cwnd; - bool resend = false; - - summary->flight_size = - (call->tx_top - call->acks_hard_ack) - summary->nr_acks; + summary->change = rxrpc_cong_no_change; + summary->in_flight = rxrpc_tx_in_flight(call); if (test_and_clear_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags)) { summary->retrans_timeo = true; - call->cong_ssthresh = max_t(unsigned int, - summary->flight_size / 2, 2); - cwnd = 1; - if (cwnd >= call->cong_ssthresh && - call->cong_mode == RXRPC_CALL_SLOW_START) { - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; - call->cong_tstamp = skb->tstamp; - cumulative_acks = 0; + call->cong_ssthresh = umax(summary->in_flight / 2, 2); + call->cong_cwnd = 1; + if (call->cong_cwnd >= call->cong_ssthresh && + call->cong_ca_state == RXRPC_CA_SLOW_START) { + call->cong_ca_state = RXRPC_CA_CONGEST_AVOIDANCE; + call->cong_tstamp = call->acks_latest_ts; + call->cong_cumul_acks = 0; } } - cumulative_acks += summary->nr_new_acks; - if (cumulative_acks > 255) - cumulative_acks = 255; + call->cong_cumul_acks += summary->nr_new_sacks; + call->cong_cumul_acks += summary->nr_new_hacks; + if (call->cong_cumul_acks > 255) + call->cong_cumul_acks = 255; - summary->cwnd = call->cong_cwnd; - summary->ssthresh = call->cong_ssthresh; - summary->cumulative_acks = cumulative_acks; - summary->dup_acks = call->cong_dup_acks; - - switch (call->cong_mode) { - case RXRPC_CALL_SLOW_START: - if (summary->saw_nacks) + switch (call->cong_ca_state) { + case RXRPC_CA_SLOW_START: + if (call->acks_nr_snacks > 0) goto packet_loss_detected; - if (summary->cumulative_acks > 0) - cwnd += 1; - if (cwnd >= call->cong_ssthresh) { - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; - call->cong_tstamp = skb->tstamp; + if (call->cong_cumul_acks > 0) + call->cong_cwnd += 1; + if (call->cong_cwnd >= call->cong_ssthresh) { + call->cong_ca_state = RXRPC_CA_CONGEST_AVOIDANCE; + call->cong_tstamp = call->acks_latest_ts; } goto out; - case RXRPC_CALL_CONGEST_AVOIDANCE: - if (summary->saw_nacks) + case RXRPC_CA_CONGEST_AVOIDANCE: + if (call->acks_nr_snacks > 0) goto packet_loss_detected; /* We analyse the number of packets that get ACK'd per RTT * period and increase the window if we managed to fill it. */ - if (call->peer->rtt_count == 0) + if (call->rtt_count == 0) goto out; - if (ktime_before(skb->tstamp, + if (ktime_before(call->acks_latest_ts, ktime_add_us(call->cong_tstamp, - call->peer->srtt_us >> 3))) + call->srtt_us >> 3))) goto out_no_clear_ca; - change = rxrpc_cong_rtt_window_end; - call->cong_tstamp = skb->tstamp; - if (cumulative_acks >= cwnd) - cwnd++; + summary->change = rxrpc_cong_rtt_window_end; + call->cong_tstamp = call->acks_latest_ts; + if (call->cong_cumul_acks >= call->cong_cwnd) + call->cong_cwnd++; goto out; - case RXRPC_CALL_PACKET_LOSS: - if (!summary->saw_nacks) + case RXRPC_CA_PACKET_LOSS: + if (call->acks_nr_snacks == 0) goto resume_normality; - if (summary->new_low_nack) { - change = rxrpc_cong_new_low_nack; + if (summary->new_low_snack) { + summary->change = rxrpc_cong_new_low_nack; call->cong_dup_acks = 1; if (call->cong_extra > 1) call->cong_extra = 1; @@ -111,31 +99,35 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, if (call->cong_dup_acks < 3) goto send_extra_data; - change = rxrpc_cong_begin_retransmission; - call->cong_mode = RXRPC_CALL_FAST_RETRANSMIT; - call->cong_ssthresh = max_t(unsigned int, - summary->flight_size / 2, 2); - cwnd = call->cong_ssthresh + 3; + summary->change = rxrpc_cong_begin_retransmission; + call->cong_ca_state = RXRPC_CA_FAST_RETRANSMIT; + call->cong_ssthresh = umax(summary->in_flight / 2, 2); + call->cong_cwnd = call->cong_ssthresh + 3; call->cong_extra = 0; call->cong_dup_acks = 0; - resend = true; + summary->need_retransmit = true; + summary->in_fast_or_rto_recovery = true; goto out; - case RXRPC_CALL_FAST_RETRANSMIT: - if (!summary->new_low_nack) { - if (summary->nr_new_acks == 0) - cwnd += 1; + case RXRPC_CA_FAST_RETRANSMIT: + rxrpc_tlp_init(call); + summary->in_fast_or_rto_recovery = true; + if (!summary->new_low_snack) { + if (summary->nr_new_sacks == 0) + call->cong_cwnd += 1; call->cong_dup_acks++; if (call->cong_dup_acks == 2) { - change = rxrpc_cong_retransmit_again; + summary->change = rxrpc_cong_retransmit_again; call->cong_dup_acks = 0; - resend = true; + summary->need_retransmit = true; } } else { - change = rxrpc_cong_progress; - cwnd = call->cong_ssthresh; - if (!summary->saw_nacks) + summary->change = rxrpc_cong_progress; + call->cong_cwnd = call->cong_ssthresh; + if (call->acks_nr_snacks == 0) { + summary->exiting_fast_or_rto_recovery = true; goto resume_normality; + } } goto out; @@ -145,30 +137,25 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, } resume_normality: - change = rxrpc_cong_cleared_nacks; + summary->change = rxrpc_cong_cleared_nacks; call->cong_dup_acks = 0; call->cong_extra = 0; - call->cong_tstamp = skb->tstamp; - if (cwnd < call->cong_ssthresh) - call->cong_mode = RXRPC_CALL_SLOW_START; + call->cong_tstamp = call->acks_latest_ts; + if (call->cong_cwnd < call->cong_ssthresh) + call->cong_ca_state = RXRPC_CA_SLOW_START; else - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + call->cong_ca_state = RXRPC_CA_CONGEST_AVOIDANCE; out: - cumulative_acks = 0; + call->cong_cumul_acks = 0; out_no_clear_ca: - if (cwnd >= RXRPC_TX_MAX_WINDOW) - cwnd = RXRPC_TX_MAX_WINDOW; - call->cong_cwnd = cwnd; - call->cong_cumul_acks = cumulative_acks; - summary->mode = call->cong_mode; - trace_rxrpc_congest(call, summary, acked_serial, change); - if (resend) - rxrpc_resend(call, skb); + if (call->cong_cwnd >= RXRPC_TX_MAX_WINDOW) + call->cong_cwnd = RXRPC_TX_MAX_WINDOW; + trace_rxrpc_congest(call, summary); return; packet_loss_detected: - change = rxrpc_cong_saw_nack; - call->cong_mode = RXRPC_CALL_PACKET_LOSS; + summary->change = rxrpc_cong_saw_nack; + call->cong_ca_state = RXRPC_CA_PACKET_LOSS; call->cong_dup_acks = 0; goto send_extra_data; @@ -177,7 +164,7 @@ send_extra_data: * state. */ if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) || - summary->nr_acks != call->tx_top - call->acks_hard_ack) { + call->acks_nr_sacks != call->tx_top - call->tx_bottom) { call->cong_extra++; wake_up(&call->waitq); } @@ -189,26 +176,42 @@ send_extra_data: */ void rxrpc_congestion_degrade(struct rxrpc_call *call) { - ktime_t rtt, now; + ktime_t rtt, now, time_since; - if (call->cong_mode != RXRPC_CALL_SLOW_START && - call->cong_mode != RXRPC_CALL_CONGEST_AVOIDANCE) + if (call->cong_ca_state != RXRPC_CA_SLOW_START && + call->cong_ca_state != RXRPC_CA_CONGEST_AVOIDANCE) return; if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_REPLY) return; - rtt = ns_to_ktime(call->peer->srtt_us * (1000 / 8)); + rtt = ns_to_ktime(call->srtt_us * (NSEC_PER_USEC / 8)); now = ktime_get_real(); - if (!ktime_before(ktime_add(call->tx_last_sent, rtt), now)) + time_since = ktime_sub(now, call->tx_last_sent); + if (ktime_before(time_since, rtt)) return; - trace_rxrpc_reset_cwnd(call, now); + trace_rxrpc_reset_cwnd(call, time_since, rtt); rxrpc_inc_stat(call->rxnet, stat_tx_data_cwnd_reset); call->tx_last_sent = now; - call->cong_mode = RXRPC_CALL_SLOW_START; - call->cong_ssthresh = max_t(unsigned int, call->cong_ssthresh, - call->cong_cwnd * 3 / 4); - call->cong_cwnd = max_t(unsigned int, call->cong_cwnd / 2, RXRPC_MIN_CWND); + call->cong_ca_state = RXRPC_CA_SLOW_START; + call->cong_ssthresh = umax(call->cong_ssthresh, call->cong_cwnd * 3 / 4); + call->cong_cwnd = umax(call->cong_cwnd / 2, RXRPC_MIN_CWND); +} + +/* + * Add an RTT sample derived from an ACK'd DATA packet. + */ +static void rxrpc_add_data_rtt_sample(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + int ix) +{ + ktime_t xmit_ts = ktime_add_us(tq->xmit_ts_base, tq->segment_xmit_ts[ix]); + + rxrpc_call_add_rtt(call, rxrpc_rtt_rx_data_ack, -1, + summary->acked_serial, summary->ack_serial, + xmit_ts, call->acks_latest_ts); + __clear_bit(ix, &tq->rtt_samples); /* Prevent repeat RTT sample */ } /* @@ -217,37 +220,120 @@ void rxrpc_congestion_degrade(struct rxrpc_call *call) static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, struct rxrpc_ack_summary *summary) { - struct rxrpc_txbuf *txb; - bool rot_last = false; + struct rxrpc_txqueue *tq = call->tx_queue; + rxrpc_seq_t seq = call->tx_bottom + 1; + bool rot_last = false, trace = false; - list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { - if (before_eq(txb->seq, call->acks_hard_ack)) - continue; - if (txb->flags & RXRPC_LAST_PACKET) { + _enter("%x,%x", call->tx_bottom, to); + + trace_rxrpc_tx_rotate(call, seq, to); + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate); + + if (call->acks_lowest_nak == call->tx_bottom) { + call->acks_lowest_nak = to; + } else if (after(to, call->acks_lowest_nak)) { + summary->new_low_snack = true; + call->acks_lowest_nak = to; + } + + /* We may have a left over fully-consumed buffer at the front that we + * couldn't drop before (rotate_and_keep below). + */ + if (seq == call->tx_qbase + RXRPC_NR_TXQUEUE) { + call->tx_qbase += RXRPC_NR_TXQUEUE; + call->tx_queue = tq->next; + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate_and_free); + kfree(tq); + tq = call->tx_queue; + } + + do { + unsigned int ix = seq - call->tx_qbase; + + _debug("tq=%x seq=%x i=%d f=%x", tq->qbase, seq, ix, tq->bufs[ix]->flags); + if (tq->bufs[ix]->flags & RXRPC_LAST_PACKET) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; } - if (txb->seq == to) - break; - } - if (rot_last) + if (summary->acked_serial == tq->segment_serial[ix] && + test_bit(ix, &tq->rtt_samples)) + rxrpc_add_data_rtt_sample(call, summary, tq, ix); + + if (ix == tq->nr_reported_acks) { + /* Packet directly hard ACK'd. */ + tq->nr_reported_acks++; + rxrpc_input_rack_one(call, summary, tq, ix); + if (seq == call->tlp_seq) + summary->tlp_probe_acked = true; + summary->nr_new_hacks++; + __set_bit(ix, &tq->segment_acked); + trace_rxrpc_rotate(call, tq, summary, seq, rxrpc_rotate_trace_hack); + } else if (test_bit(ix, &tq->segment_acked)) { + /* Soft ACK -> hard ACK. */ + call->acks_nr_sacks--; + trace_rxrpc_rotate(call, tq, summary, seq, rxrpc_rotate_trace_sack); + } else { + /* Soft NAK -> hard ACK. */ + call->acks_nr_snacks--; + rxrpc_input_rack_one(call, summary, tq, ix); + if (seq == call->tlp_seq) + summary->tlp_probe_acked = true; + summary->nr_new_hacks++; + __set_bit(ix, &tq->segment_acked); + trace_rxrpc_rotate(call, tq, summary, seq, rxrpc_rotate_trace_snak); + } + + call->tx_nr_sent--; + if (__test_and_clear_bit(ix, &tq->segment_lost)) + call->tx_nr_lost--; + if (__test_and_clear_bit(ix, &tq->segment_retransmitted)) + call->tx_nr_resent--; + __clear_bit(ix, &tq->ever_retransmitted); + + rxrpc_put_txbuf(tq->bufs[ix], rxrpc_txbuf_put_rotated); + tq->bufs[ix] = NULL; + + WRITE_ONCE(call->tx_bottom, seq); + trace_rxrpc_txqueue(call, (rot_last ? + rxrpc_txqueue_rotate_last : + rxrpc_txqueue_rotate)); + + seq++; + trace = true; + if (!(seq & RXRPC_TXQ_MASK)) { + trace_rxrpc_rack_update(call, summary); + trace = false; + prefetch(tq->next); + if (tq != call->tx_qtail) { + call->tx_qbase += RXRPC_NR_TXQUEUE; + call->tx_queue = tq->next; + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate_and_free); + kfree(tq); + tq = call->tx_queue; + } else { + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate_and_keep); + tq = NULL; + break; + } + } + + } while (before_eq(seq, to)); + + if (trace) + trace_rxrpc_rack_update(call, summary); + + if (rot_last) { set_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags); - - _enter("%x,%x,%x,%d", to, call->acks_hard_ack, call->tx_top, rot_last); - - if (call->acks_lowest_nak == call->acks_hard_ack) { - call->acks_lowest_nak = to; - } else if (after(to, call->acks_lowest_nak)) { - summary->new_low_nack = true; - call->acks_lowest_nak = to; + if (tq) { + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate_and_free); + kfree(tq); + call->tx_queue = NULL; + } } - smp_store_release(&call->acks_hard_ack, to); + _debug("%x,%x,%x,%d", to, call->tx_bottom, call->tx_top, rot_last); - trace_rxrpc_txqueue(call, (rot_last ? - rxrpc_txqueue_rotate_last : - rxrpc_txqueue_rotate)); wake_up(&call->waitq); return rot_last; } @@ -263,13 +349,10 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, { ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); - call->resend_at = KTIME_MAX; - trace_rxrpc_timer_can(call, rxrpc_timer_trace_resend); - - if (unlikely(call->cong_last_nack)) { - rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack); - call->cong_last_nack = NULL; - } + call->rack_timer_mode = RXRPC_CALL_RACKTIMER_OFF; + call->rack_timo_at = KTIME_MAX; + trace_rxrpc_rack_timer(call, 0, false); + trace_rxrpc_timer_can(call, rxrpc_timer_trace_rack_off + call->rack_timer_mode); switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: @@ -365,7 +448,7 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); bool last = sp->hdr.flags & RXRPC_LAST_PACKET; - __skb_queue_tail(&call->recvmsg_queue, skb); + skb_queue_tail(&call->recvmsg_queue, skb); rxrpc_input_update_ack_window(call, window, wtop); trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq); if (last) @@ -442,7 +525,6 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg); - spin_lock(&call->recvmsg_queue.lock); rxrpc_input_queue_data(call, skb, window, wtop, rxrpc_receive_queue); *_notify = true; @@ -464,8 +546,6 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, rxrpc_receive_queue_oos); } - spin_unlock(&call->recvmsg_queue.lock); - call->ackr_sack_base = sack; } else { unsigned int slot; @@ -530,7 +610,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len = skb->len - offset; bool notify = false; - int ack_reason = 0; + int ack_reason = 0, count = 1, stat_ix; while (sp->hdr.flags & RXRPC_JUMBO_PACKET) { if (len < RXRPC_JUMBO_SUBPKTLEN) @@ -559,12 +639,16 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb sp->hdr.serial++; offset += RXRPC_JUMBO_SUBPKTLEN; len -= RXRPC_JUMBO_SUBPKTLEN; + count++; } sp->offset = offset; sp->len = len; rxrpc_input_data_one(call, skb, ¬ify, &ack_serial, &ack_reason); + stat_ix = umin(count, ARRAY_SIZE(call->rxnet->stat_rx_jumbo)) - 1; + atomic_inc(&call->rxnet->stat_rx_jumbo[stat_ix]); + if (ack_reason > 0) { rxrpc_send_ACK(call, ack_reason, ack_serial, rxrpc_propose_ack_input_data); @@ -667,7 +751,7 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); smp_mb(); /* Read data before setting avail bit */ set_bit(i, &call->rtt_avail); - rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial, + rxrpc_call_add_rtt(call, type, i, acked_serial, ack_serial, sent_at, resp_time); matched = true; } @@ -677,7 +761,7 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, */ if (after(acked_serial, orig_serial)) { trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_obsolete, i, - orig_serial, acked_serial, 0, 0); + orig_serial, acked_serial, 0, 0, 0); clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); smp_wmb(); set_bit(i, &call->rtt_avail); @@ -685,7 +769,7 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, } if (!matched) - trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0); + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0, 0); } /* @@ -695,10 +779,13 @@ static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb struct rxrpc_acktrailer *trailer) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_peer *peer; - unsigned int mtu; + struct rxrpc_peer *peer = call->peer; + unsigned int max_data, capacity; bool wake = false; - u32 rwind = ntohl(trailer->rwind); + u32 max_mtu = ntohl(trailer->maxMTU); + //u32 if_mtu = ntohl(trailer->ifMTU); + u32 rwind = ntohl(trailer->rwind); + u32 jumbo_max = ntohl(trailer->jumbo_max); if (rwind > RXRPC_TX_MAX_WINDOW) rwind = RXRPC_TX_MAX_WINDOW; @@ -709,54 +796,149 @@ static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb call->tx_winsize = rwind; } - mtu = min(ntohl(trailer->maxMTU), ntohl(trailer->ifMTU)); + max_mtu = clamp(max_mtu, 500, 65535); + peer->ackr_max_data = max_mtu; - peer = call->peer; - if (mtu < peer->maxdata) { - spin_lock(&peer->lock); - peer->maxdata = mtu; - peer->mtu = mtu + peer->hdrsize; - spin_unlock(&peer->lock); + if (max_mtu < peer->max_data) { + trace_rxrpc_pmtud_reduce(peer, sp->hdr.serial, max_mtu, + rxrpc_pmtud_reduce_ack); + write_seqcount_begin(&peer->mtu_lock); + peer->max_data = max_mtu; + write_seqcount_end(&peer->mtu_lock); } + max_data = umin(max_mtu, peer->max_data); + capacity = max_data; + capacity += sizeof(struct rxrpc_jumbo_header); /* First subpacket has main hdr, not jumbo */ + capacity /= sizeof(struct rxrpc_jumbo_header) + RXRPC_JUMBO_DATALEN; + + if (jumbo_max == 0) { + /* The peer says it supports pmtu discovery */ + peer->ackr_adv_pmtud = true; + } else { + peer->ackr_adv_pmtud = false; + capacity = clamp(capacity, 1, jumbo_max); + } + + call->tx_jumbo_max = capacity; + if (wake) wake_up(&call->waitq); } +#if defined(CONFIG_X86) && __GNUC__ && !defined(__clang__) +/* Clang doesn't support the %z constraint modifier */ +#define shiftr_adv_rotr(shift_from, rotate_into) ({ \ + asm(" shr%z1 %1\n" \ + " inc %0\n" \ + " rcr%z2 %2\n" \ + : "+d"(shift_from), "+m"(*(shift_from)), "+rm"(rotate_into) \ + ); \ + }) +#else +#define shiftr_adv_rotr(shift_from, rotate_into) ({ \ + typeof(rotate_into) __bit0 = *(shift_from) & 1; \ + *(shift_from) >>= 1; \ + shift_from++; \ + rotate_into >>= 1; \ + rotate_into |= __bit0 << (sizeof(rotate_into) * 8 - 1); \ + }) +#endif + /* - * Determine how many nacks from the previous ACK have now been satisfied. + * Deal with RTT samples from soft ACKs. */ -static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call, - struct rxrpc_ack_summary *summary, - rxrpc_seq_t seq) +static void rxrpc_input_soft_rtt(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq) { - struct sk_buff *skb = call->cong_last_nack; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int i, new_acks = 0, retained_nacks = 0; - rxrpc_seq_t old_seq = sp->ack.first_ack; - u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); + for (int ix = 0; ix < RXRPC_NR_TXQUEUE; ix++) + if (summary->acked_serial == tq->segment_serial[ix]) + return rxrpc_add_data_rtt_sample(call, summary, tq, ix); +} - if (after_eq(seq, old_seq + sp->ack.nr_acks)) { - summary->nr_new_acks += sp->ack.nr_nacks; - summary->nr_new_acks += seq - (old_seq + sp->ack.nr_acks); - summary->nr_retained_nacks = 0; - } else if (seq == old_seq) { - summary->nr_retained_nacks = sp->ack.nr_nacks; - } else { - for (i = 0; i < sp->ack.nr_acks; i++) { - if (acks[i] == RXRPC_ACK_TYPE_NACK) { - if (before(old_seq + i, seq)) - new_acks++; - else - retained_nacks++; - } - } +/* + * Process a batch of soft ACKs specific to a transmission queue segment. + */ +static void rxrpc_input_soft_ack_tq(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + unsigned long extracted_acks, + int nr_reported, + rxrpc_seq_t seq, + rxrpc_seq_t *lowest_nak) +{ + unsigned long old_reported = 0, flipped, new_acks = 0; + unsigned long a_to_n, n_to_a = 0; + int new, a, n; - summary->nr_new_acks += new_acks; - summary->nr_retained_nacks = retained_nacks; + if (tq->nr_reported_acks > 0) + old_reported = ~0UL >> (RXRPC_NR_TXQUEUE - tq->nr_reported_acks); + + _enter("{%x,%lx,%d},%lx,%d,%x", + tq->qbase, tq->segment_acked, tq->nr_reported_acks, + extracted_acks, nr_reported, seq); + + _debug("[%x]", tq->qbase); + _debug("tq %16lx %u", tq->segment_acked, tq->nr_reported_acks); + _debug("sack %16lx %u", extracted_acks, nr_reported); + + /* See how many previously logged ACKs/NAKs have flipped. */ + flipped = (tq->segment_acked ^ extracted_acks) & old_reported; + if (flipped) { + n_to_a = ~tq->segment_acked & flipped; /* Old NAK -> ACK */ + a_to_n = tq->segment_acked & flipped; /* Old ACK -> NAK */ + a = hweight_long(n_to_a); + n = hweight_long(a_to_n); + _debug("flip %16lx", flipped); + _debug("ntoa %16lx %d", n_to_a, a); + _debug("aton %16lx %d", a_to_n, n); + call->acks_nr_sacks += a - n; + call->acks_nr_snacks += n - a; + summary->nr_new_sacks += a; + summary->nr_new_snacks += n; } - return old_seq + sp->ack.nr_acks; + /* See how many new ACKs/NAKs have been acquired. */ + new = nr_reported - tq->nr_reported_acks; + if (new > 0) { + new_acks = extracted_acks & ~old_reported; + if (new_acks) { + a = hweight_long(new_acks); + n = new - a; + _debug("new_a %16lx new=%d a=%d n=%d", new_acks, new, a, n); + call->acks_nr_sacks += a; + call->acks_nr_snacks += n; + summary->nr_new_sacks += a; + summary->nr_new_snacks += n; + } else { + call->acks_nr_snacks += new; + summary->nr_new_snacks += new; + } + } + + tq->nr_reported_acks = nr_reported; + tq->segment_acked = extracted_acks; + trace_rxrpc_apply_acks(call, tq); + + if (extracted_acks != ~0UL) { + rxrpc_seq_t lowest = seq + ffz(extracted_acks); + + if (before(lowest, *lowest_nak)) + *lowest_nak = lowest; + } + + if (summary->acked_serial) + rxrpc_input_soft_rtt(call, summary, tq); + + new_acks |= n_to_a; + if (new_acks) + rxrpc_input_rack(call, summary, tq, new_acks); + + if (call->tlp_serial && + rxrpc_seq_in_txq(tq, call->tlp_seq) && + test_bit(call->tlp_seq - tq->qbase, &new_acks)) + summary->tlp_probe_acked = true; } /* @@ -770,39 +952,50 @@ static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call, */ static void rxrpc_input_soft_acks(struct rxrpc_call *call, struct rxrpc_ack_summary *summary, - struct sk_buff *skb, - rxrpc_seq_t seq, - rxrpc_seq_t since) + struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int i, old_nacks = 0; + struct rxrpc_txqueue *tq = call->tx_queue; + unsigned long extracted = ~0UL; + unsigned int nr = 0; + rxrpc_seq_t seq = call->acks_hard_ack + 1; rxrpc_seq_t lowest_nak = seq + sp->ack.nr_acks; u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); - for (i = 0; i < sp->ack.nr_acks; i++) { - if (acks[i] == RXRPC_ACK_TYPE_ACK) { - summary->nr_acks++; - if (after_eq(seq, since)) - summary->nr_new_acks++; - } else { - summary->saw_nacks = true; - if (before(seq, since)) { - /* Overlap with previous ACK */ - old_nacks++; - } else { - summary->nr_new_nacks++; - sp->ack.nr_nacks++; - } + _enter("%x,%x,%u", tq->qbase, seq, sp->ack.nr_acks); - if (before(seq, lowest_nak)) - lowest_nak = seq; + while (after(seq, tq->qbase + RXRPC_NR_TXQUEUE - 1)) + tq = tq->next; + + for (unsigned int i = 0; i < sp->ack.nr_acks; i++) { + /* Decant ACKs until we hit a txqueue boundary. */ + shiftr_adv_rotr(acks, extracted); + if (i == 256) { + acks -= i; + i = 0; } seq++; + nr++; + if ((seq & RXRPC_TXQ_MASK) != 0) + continue; + + _debug("bound %16lx %u", extracted, nr); + + rxrpc_input_soft_ack_tq(call, summary, tq, extracted, RXRPC_NR_TXQUEUE, + seq - RXRPC_NR_TXQUEUE, &lowest_nak); + extracted = ~0UL; + nr = 0; + tq = tq->next; + prefetch(tq); } - if (lowest_nak != call->acks_lowest_nak) { - call->acks_lowest_nak = lowest_nak; - summary->new_low_nack = true; + if (nr) { + unsigned int nr_reported = seq & RXRPC_TXQ_MASK; + + extracted >>= RXRPC_NR_TXQUEUE - nr_reported; + _debug("tail %16lx %u", extracted, nr_reported); + rxrpc_input_soft_ack_tq(call, summary, tq, extracted, nr_reported, + seq & ~RXRPC_TXQ_MASK, &lowest_nak); } /* We *can* have more nacks than we did - the peer is permitted to drop @@ -810,9 +1003,14 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, * possible for the nack distribution to change whilst the number of * nacks stays the same or goes down. */ - if (old_nacks < summary->nr_retained_nacks) - summary->nr_new_acks += summary->nr_retained_nacks - old_nacks; - summary->nr_retained_nacks = old_nacks; + if (lowest_nak != call->acks_lowest_nak) { + call->acks_lowest_nak = lowest_nak; + summary->new_low_snack = true; + } + + _debug("summary A=%d+%d N=%d+%d", + call->acks_nr_sacks, summary->nr_new_sacks, + call->acks_nr_snacks, summary->nr_new_snacks); } /* @@ -820,21 +1018,21 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, * with respect to the ack state conveyed by preceding ACKs. */ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, - rxrpc_seq_t first_pkt, rxrpc_seq_t prev_pkt) + rxrpc_seq_t hard_ack, rxrpc_seq_t prev_pkt) { - rxrpc_seq_t base = READ_ONCE(call->acks_first_seq); + rxrpc_seq_t base = READ_ONCE(call->acks_hard_ack); - if (after(first_pkt, base)) + if (after(hard_ack, base)) return true; /* The window advanced */ - if (before(first_pkt, base)) + if (before(hard_ack, base)) return false; /* firstPacket regressed */ if (after_eq(prev_pkt, call->acks_prev_seq)) return true; /* previousPacket hasn't regressed. */ /* Some rx implementations put a serial number in previousPacket. */ - if (after_eq(prev_pkt, base + call->tx_winsize)) + if (after(prev_pkt, base + call->tx_winsize)) return false; return true; } @@ -852,53 +1050,34 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_acktrailer trailer; - rxrpc_serial_t ack_serial, acked_serial; - rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; _enter(""); offset = sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); - ack_serial = sp->hdr.serial; - acked_serial = sp->ack.acked_serial; - first_soft_ack = sp->ack.first_ack; - prev_pkt = sp->ack.prev_ack; - nr_acks = sp->ack.nr_acks; - hard_ack = first_soft_ack - 1; - summary.ack_reason = (sp->ack.reason < RXRPC_ACK__INVALID ? - sp->ack.reason : RXRPC_ACK__INVALID); + summary.ack_serial = sp->hdr.serial; + first_soft_ack = sp->ack.first_ack; + prev_pkt = sp->ack.prev_ack; + nr_acks = sp->ack.nr_acks; + hard_ack = first_soft_ack - 1; + summary.acked_serial = sp->ack.acked_serial; + summary.ack_reason = (sp->ack.reason < RXRPC_ACK__INVALID ? + sp->ack.reason : RXRPC_ACK__INVALID); - trace_rxrpc_rx_ack(call, ack_serial, acked_serial, - first_soft_ack, prev_pkt, - summary.ack_reason, nr_acks); + trace_rxrpc_rx_ack(call, sp); rxrpc_inc_stat(call->rxnet, stat_rx_acks[summary.ack_reason]); - - if (acked_serial != 0) { - switch (summary.ack_reason) { - case RXRPC_ACK_PING_RESPONSE: - rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, - rxrpc_rtt_rx_ping_response); - break; - case RXRPC_ACK_REQUESTED: - rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, - rxrpc_rtt_rx_requested_ack); - break; - default: - rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, - rxrpc_rtt_rx_other_ack); - break; - } - } + prefetch(call->tx_queue); /* If we get an EXCEEDS_WINDOW ACK from the server, it probably * indicates that the client address changed due to NAT. The server * lost the call because it switched to a different peer. */ if (unlikely(summary.ack_reason == RXRPC_ACK_EXCEEDS_WINDOW) && - first_soft_ack == 1 && + hard_ack == 0 && prev_pkt == 0 && rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, @@ -911,9 +1090,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * if we still have it buffered to the beginning. */ if (unlikely(summary.ack_reason == RXRPC_ACK_OUT_OF_SEQUENCE) && - first_soft_ack == 1 && + hard_ack == 0 && prev_pkt == 0 && - call->acks_hard_ack == 0 && + call->tx_bottom == 0 && rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); @@ -921,11 +1100,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } /* Discard any out-of-order or duplicate ACKs (outside lock). */ - if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, - first_soft_ack, call->acks_first_seq, - prev_pkt, call->acks_prev_seq); - goto send_response; + if (!rxrpc_is_ack_valid(call, hard_ack, prev_pkt)) { + trace_rxrpc_rx_discard_ack(call, summary.ack_serial, hard_ack, prev_pkt); + goto send_response; /* Still respond if requested. */ } trailer.maxMTU = 0; @@ -937,34 +1114,30 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (nr_acks > 0) skb_condense(skb); - if (call->cong_last_nack) { - since = rxrpc_input_check_prev_ack(call, &summary, first_soft_ack); - rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack); - call->cong_last_nack = NULL; - } else { - summary.nr_new_acks = first_soft_ack - call->acks_first_seq; - call->acks_lowest_nak = first_soft_ack + nr_acks; - since = first_soft_ack; - } - - call->acks_latest_ts = skb->tstamp; - call->acks_first_seq = first_soft_ack; + call->acks_latest_ts = ktime_get_real(); + call->acks_hard_ack = hard_ack; call->acks_prev_seq = prev_pkt; - switch (summary.ack_reason) { - case RXRPC_ACK_PING: - break; - default: - if (acked_serial && after(acked_serial, call->acks_highest_serial)) - call->acks_highest_serial = acked_serial; - break; + if (summary.acked_serial) { + switch (summary.ack_reason) { + case RXRPC_ACK_PING_RESPONSE: + rxrpc_complete_rtt_probe(call, call->acks_latest_ts, + summary.acked_serial, summary.ack_serial, + rxrpc_rtt_rx_ping_response); + break; + default: + if (after(summary.acked_serial, call->acks_highest_serial)) + call->acks_highest_serial = summary.acked_serial; + summary.rtt_sample_avail = true; + break; + } } /* Parse rwind and mtu sizes if provided. */ if (trailer.maxMTU) rxrpc_input_ack_trailer(call, skb, &trailer); - if (first_soft_ack == 0) + if (hard_ack + 1 == 0) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero); /* Ignore ACKs unless we are or have just been transmitting. */ @@ -978,13 +1151,13 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto send_response; } - if (before(hard_ack, call->acks_hard_ack) || + if (before(hard_ack, call->tx_bottom) || after(hard_ack, call->tx_top)) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_outside_window); if (nr_acks > call->tx_top - hard_ack) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_sack_overflow); - if (after(hard_ack, call->acks_hard_ack)) { + if (after(hard_ack, call->tx_bottom)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack); goto send_response; @@ -994,25 +1167,30 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (nr_acks > 0) { if (offset > (int)skb->len - nr_acks) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack); - rxrpc_input_soft_acks(call, &summary, skb, first_soft_ack, since); - rxrpc_get_skb(skb, rxrpc_skb_get_last_nack); - call->cong_last_nack = skb; + rxrpc_input_soft_acks(call, &summary, skb); } if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && - summary.nr_acks == call->tx_top - hard_ack && + call->acks_nr_sacks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ping(call, ack_serial, + rxrpc_propose_ping(call, summary.ack_serial, rxrpc_propose_ack_ping_for_lost_reply); - rxrpc_congestion_management(call, skb, &summary, acked_serial); + /* Drive the congestion management algorithm first and then RACK-TLP as + * the latter depends on the state/change in state in the former. + */ + rxrpc_congestion_management(call, &summary); + rxrpc_rack_detect_loss_and_arm_timer(call, &summary); + rxrpc_tlp_process_ack(call, &summary); + if (call->tlp_serial && after_eq(summary.acked_serial, call->tlp_serial)) + call->tlp_serial = 0; send_response: if (summary.ack_reason == RXRPC_ACK_PING) - rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, + rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, summary.ack_serial, rxrpc_propose_ack_respond_to_ping); else if (sp->hdr.flags & RXRPC_REQUEST_ACK) - rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial, + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, summary.ack_serial, rxrpc_propose_ack_respond_to_ack); } @@ -1111,5 +1289,5 @@ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) break; } - rxrpc_input_call_event(call, skb); + rxrpc_input_call_event(call); } diff --git a/net/rxrpc/input_rack.c b/net/rxrpc/input_rack.c new file mode 100644 index 000000000000..13c371261e0a --- /dev/null +++ b/net/rxrpc/input_rack.c @@ -0,0 +1,418 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* RACK-TLP [RFC8958] Implementation + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include "ar-internal.h" + +static bool rxrpc_rack_sent_after(ktime_t t1, rxrpc_seq_t seq1, + ktime_t t2, rxrpc_seq_t seq2) +{ + if (ktime_after(t1, t2)) + return true; + return t1 == t2 && after(seq1, seq2); +} + +/* + * Mark a packet lost. + */ +static void rxrpc_rack_mark_lost(struct rxrpc_call *call, + struct rxrpc_txqueue *tq, unsigned int ix) +{ + if (__test_and_set_bit(ix, &tq->segment_lost)) { + if (__test_and_clear_bit(ix, &tq->segment_retransmitted)) + call->tx_nr_resent--; + } else { + call->tx_nr_lost++; + } + tq->segment_xmit_ts[ix] = UINT_MAX; +} + +/* + * Get the transmission time of a packet in the Tx queue. + */ +static ktime_t rxrpc_get_xmit_ts(const struct rxrpc_txqueue *tq, unsigned int ix) +{ + if (tq->segment_xmit_ts[ix] == UINT_MAX) + return KTIME_MAX; + return ktime_add_us(tq->xmit_ts_base, tq->segment_xmit_ts[ix]); +} + +/* + * Get a bitmask of nack bits for a queue segment and mask off any that aren't + * yet reported. + */ +static unsigned long rxrpc_tq_nacks(const struct rxrpc_txqueue *tq) +{ + unsigned long nacks = ~tq->segment_acked; + + if (tq->nr_reported_acks < RXRPC_NR_TXQUEUE) + nacks &= (1UL << tq->nr_reported_acks) - 1; + return nacks; +} + +/* + * Update the RACK state for the most recently sent packet that has been + * delivered [RFC8958 6.2 Step 2]. + */ +static void rxrpc_rack_update(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + unsigned int ix) +{ + rxrpc_seq_t seq = tq->qbase + ix; + ktime_t xmit_ts = rxrpc_get_xmit_ts(tq, ix); + ktime_t rtt = ktime_sub(call->acks_latest_ts, xmit_ts); + + if (__test_and_clear_bit(ix, &tq->segment_lost)) + call->tx_nr_lost--; + + if (test_bit(ix, &tq->segment_retransmitted)) { + /* Use Rx.serial instead of TCP.ACK.ts_option.echo_reply. */ + if (before(call->acks_highest_serial, tq->segment_serial[ix])) + return; + if (rtt < minmax_get(&call->min_rtt)) + return; + } + + /* The RACK algorithm requires the segment ACKs to be traversed in + * order of segment transmission - but the only thing this seems to + * matter for is that RACK.rtt is set to the rtt of the most recently + * transmitted segment. We should be able to achieve the same by only + * setting RACK.rtt if the xmit time is greater. + */ + if (ktime_after(xmit_ts, call->rack_rtt_ts)) { + call->rack_rtt = rtt; + call->rack_rtt_ts = xmit_ts; + } + + if (rxrpc_rack_sent_after(xmit_ts, seq, call->rack_xmit_ts, call->rack_end_seq)) { + call->rack_rtt = rtt; + call->rack_xmit_ts = xmit_ts; + call->rack_end_seq = seq; + } +} + +/* + * Detect data segment reordering [RFC8958 6.2 Step 3]. + */ +static void rxrpc_rack_detect_reordering(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + unsigned int ix) +{ + rxrpc_seq_t seq = tq->qbase + ix; + + /* Track the highest sequence number so far ACK'd. This is not + * necessarily the same as ack.firstPacket + ack.nAcks - 1 as the peer + * could put a NACK in the last SACK slot. + */ + if (after(seq, call->rack_fack)) + call->rack_fack = seq; + else if (before(seq, call->rack_fack) && + test_bit(ix, &tq->segment_retransmitted)) + call->rack_reordering_seen = true; +} + +void rxrpc_input_rack_one(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + unsigned int ix) +{ + rxrpc_rack_update(call, summary, tq, ix); + rxrpc_rack_detect_reordering(call, summary, tq, ix); +} + +void rxrpc_input_rack(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + unsigned long new_acks) +{ + while (new_acks) { + unsigned int ix = __ffs(new_acks); + + __clear_bit(ix, &new_acks); + rxrpc_input_rack_one(call, summary, tq, ix); + } + + trace_rxrpc_rack_update(call, summary); +} + +/* + * Update the reordering window [RFC8958 6.2 Step 4]. Returns the updated + * duration of the reordering window. + * + * Note that the Rx protocol doesn't have a 'DSACK option' per se, but ACKs can + * be given a 'DUPLICATE' reason with the serial number referring to the + * duplicated DATA packet. Rx does not inform as to whether this was a + * reception of the same packet twice or of a retransmission of a packet we + * already received (though this could be determined by the transmitter based + * on the serial number). + */ +static ktime_t rxrpc_rack_update_reo_wnd(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary) +{ + rxrpc_seq_t snd_una = call->acks_lowest_nak; /* Lowest unack'd seq */ + rxrpc_seq_t snd_nxt = call->tx_transmitted + 1; /* Next seq to be sent */ + bool have_dsack_option = summary->ack_reason == RXRPC_ACK_DUPLICATE; + int dup_thresh = 3; + + /* DSACK-based reordering window adaptation */ + if (!call->rack_dsack_round_none && + after_eq(snd_una, call->rack_dsack_round)) + call->rack_dsack_round_none = true; + + /* Grow the reordering window per round that sees DSACK. Reset the + * window after 16 DSACK-free recoveries. + */ + if (call->rack_dsack_round_none && have_dsack_option) { + call->rack_dsack_round_none = false; + call->rack_dsack_round = snd_nxt; + call->rack_reo_wnd_mult++; + call->rack_reo_wnd_persist = 16; + } else if (summary->exiting_fast_or_rto_recovery) { + call->rack_reo_wnd_persist--; + if (call->rack_reo_wnd_persist <= 0) + call->rack_reo_wnd_mult = 1; + } + + if (!call->rack_reordering_seen) { + if (summary->in_fast_or_rto_recovery) + return 0; + if (call->acks_nr_sacks >= dup_thresh) + return 0; + } + + return us_to_ktime(umin(call->rack_reo_wnd_mult * minmax_get(&call->min_rtt) / 4, + call->srtt_us >> 3)); +} + +/* + * Detect losses [RFC8958 6.2 Step 5]. + */ +static ktime_t rxrpc_rack_detect_loss(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary) +{ + struct rxrpc_txqueue *tq; + ktime_t timeout = 0, lost_after, now = ktime_get_real(); + + call->rack_reo_wnd = rxrpc_rack_update_reo_wnd(call, summary); + lost_after = ktime_add(call->rack_rtt, call->rack_reo_wnd); + trace_rxrpc_rack_scan_loss(call); + + for (tq = call->tx_queue; tq; tq = tq->next) { + unsigned long nacks = rxrpc_tq_nacks(tq); + + if (after(tq->qbase, call->tx_transmitted)) + break; + trace_rxrpc_rack_scan_loss_tq(call, tq, nacks); + + /* Skip ones marked lost but not yet retransmitted */ + nacks &= ~tq->segment_lost | tq->segment_retransmitted; + + while (nacks) { + unsigned int ix = __ffs(nacks); + rxrpc_seq_t seq = tq->qbase + ix; + ktime_t remaining; + ktime_t xmit_ts = rxrpc_get_xmit_ts(tq, ix); + + __clear_bit(ix, &nacks); + + if (rxrpc_rack_sent_after(call->rack_xmit_ts, call->rack_end_seq, + xmit_ts, seq)) { + remaining = ktime_sub(ktime_add(xmit_ts, lost_after), now); + if (remaining <= 0) { + rxrpc_rack_mark_lost(call, tq, ix); + trace_rxrpc_rack_detect_loss(call, summary, seq); + } else { + timeout = max(remaining, timeout); + } + } + } + } + + return timeout; +} + +/* + * Detect losses and set a timer to retry the detection [RFC8958 6.2 Step 5]. + */ +void rxrpc_rack_detect_loss_and_arm_timer(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary) +{ + ktime_t timeout = rxrpc_rack_detect_loss(call, summary); + + if (timeout) { + call->rack_timer_mode = RXRPC_CALL_RACKTIMER_RACK_REORDER; + call->rack_timo_at = ktime_add(ktime_get_real(), timeout); + trace_rxrpc_rack_timer(call, timeout, false); + trace_rxrpc_timer_set(call, timeout, rxrpc_timer_trace_rack_reo); + } +} + +/* + * Handle RACK-TLP RTO expiration [RFC8958 6.3]. + */ +static void rxrpc_rack_mark_losses_on_rto(struct rxrpc_call *call) +{ + struct rxrpc_txqueue *tq; + rxrpc_seq_t snd_una = call->acks_lowest_nak; /* Lowest unack'd seq */ + ktime_t lost_after = ktime_add(call->rack_rtt, call->rack_reo_wnd); + ktime_t deadline = ktime_sub(ktime_get_real(), lost_after); + + for (tq = call->tx_queue; tq; tq = tq->next) { + unsigned long unacked = ~tq->segment_acked; + + trace_rxrpc_rack_mark_loss_tq(call, tq); + while (unacked) { + unsigned int ix = __ffs(unacked); + rxrpc_seq_t seq = tq->qbase + ix; + ktime_t xmit_ts = rxrpc_get_xmit_ts(tq, ix); + + if (after(seq, call->tx_transmitted)) + return; + __clear_bit(ix, &unacked); + + if (seq == snd_una || + ktime_before(xmit_ts, deadline)) + rxrpc_rack_mark_lost(call, tq, ix); + } + } +} + +/* + * Calculate the TLP loss probe timeout (PTO) [RFC8958 7.2]. + */ +ktime_t rxrpc_tlp_calc_pto(struct rxrpc_call *call, ktime_t now) +{ + unsigned int flight_size = rxrpc_tx_in_flight(call); + ktime_t rto_at = ktime_add(call->tx_last_sent, + rxrpc_get_rto_backoff(call, false)); + ktime_t pto; + + if (call->rtt_count > 0) { + /* Use 2*SRTT as the timeout. */ + pto = ns_to_ktime(call->srtt_us * NSEC_PER_USEC / 4); + if (flight_size) + pto = ktime_add(pto, call->tlp_max_ack_delay); + } else { + pto = NSEC_PER_SEC; + } + + if (ktime_after(ktime_add(now, pto), rto_at)) + pto = ktime_sub(rto_at, now); + return pto; +} + +/* + * Send a TLP loss probe on PTO expiration [RFC8958 7.3]. + */ +void rxrpc_tlp_send_probe(struct rxrpc_call *call) +{ + unsigned int in_flight = rxrpc_tx_in_flight(call); + + if (after_eq(call->acks_hard_ack, call->tx_transmitted)) + return; /* Everything we transmitted has been acked. */ + + /* There must be no other loss probe still in flight and we need to + * have taken a new RTT sample since last probe or the start of + * connection. + */ + if (!call->tlp_serial && + call->tlp_rtt_taken != call->rtt_taken) { + call->tlp_is_retrans = false; + if (after(call->send_top, call->tx_transmitted) && + rxrpc_tx_window_space(call) > 0) { + /* Transmit the lowest-sequence unsent DATA */ + call->tx_last_serial = 0; + rxrpc_transmit_some_data(call, 1, rxrpc_txdata_tlp_new_data); + call->tlp_serial = call->tx_last_serial; + call->tlp_seq = call->tx_transmitted; + trace_rxrpc_tlp_probe(call, rxrpc_tlp_probe_trace_transmit_new); + in_flight = rxrpc_tx_in_flight(call); + } else { + /* Retransmit the highest-sequence DATA sent */ + call->tx_last_serial = 0; + rxrpc_resend_tlp(call); + call->tlp_is_retrans = true; + trace_rxrpc_tlp_probe(call, rxrpc_tlp_probe_trace_retransmit); + } + } else { + trace_rxrpc_tlp_probe(call, rxrpc_tlp_probe_trace_busy); + } + + if (in_flight != 0) { + ktime_t rto = rxrpc_get_rto_backoff(call, false); + + call->rack_timer_mode = RXRPC_CALL_RACKTIMER_RTO; + call->rack_timo_at = ktime_add(ktime_get_real(), rto); + trace_rxrpc_rack_timer(call, rto, false); + trace_rxrpc_timer_set(call, rto, rxrpc_timer_trace_rack_rto); + } +} + +/* + * Detect losses using the ACK of a TLP loss probe [RFC8958 7.4]. + */ +void rxrpc_tlp_process_ack(struct rxrpc_call *call, struct rxrpc_ack_summary *summary) +{ + if (!call->tlp_serial || after(call->tlp_seq, call->acks_hard_ack)) + return; + + if (!call->tlp_is_retrans) { + /* TLP of new data delivered */ + trace_rxrpc_tlp_ack(call, summary, rxrpc_tlp_ack_trace_new_data); + call->tlp_serial = 0; + } else if (summary->ack_reason == RXRPC_ACK_DUPLICATE && + summary->acked_serial == call->tlp_serial) { + /* General Case: Detected packet losses using RACK [7.4.1] */ + trace_rxrpc_tlp_ack(call, summary, rxrpc_tlp_ack_trace_dup_acked); + call->tlp_serial = 0; + } else if (after(call->acks_hard_ack, call->tlp_seq)) { + /* Repaired the single loss */ + trace_rxrpc_tlp_ack(call, summary, rxrpc_tlp_ack_trace_hard_beyond); + call->tlp_serial = 0; + // TODO: Invoke congestion control to react to the loss + // event the probe has repaired + } else if (summary->tlp_probe_acked) { + trace_rxrpc_tlp_ack(call, summary, rxrpc_tlp_ack_trace_acked); + /* Special Case: Detected a single loss repaired by the loss + * probe [7.4.2] + */ + call->tlp_serial = 0; + } else { + trace_rxrpc_tlp_ack(call, summary, rxrpc_tlp_ack_trace_incomplete); + } +} + +/* + * Handle RACK timer expiration; returns true to request a resend. + */ +void rxrpc_rack_timer_expired(struct rxrpc_call *call, ktime_t overran_by) +{ + struct rxrpc_ack_summary summary = {}; + enum rxrpc_rack_timer_mode mode = call->rack_timer_mode; + + trace_rxrpc_rack_timer(call, overran_by, true); + call->rack_timer_mode = RXRPC_CALL_RACKTIMER_OFF; + + switch (mode) { + case RXRPC_CALL_RACKTIMER_RACK_REORDER: + rxrpc_rack_detect_loss_and_arm_timer(call, &summary); + break; + case RXRPC_CALL_RACKTIMER_TLP_PTO: + rxrpc_tlp_send_probe(call); + break; + case RXRPC_CALL_RACKTIMER_RTO: + // Might need to poke the congestion algo in some way + rxrpc_rack_mark_losses_on_rto(call); + break; + //case RXRPC_CALL_RACKTIMER_ZEROWIN: + default: + pr_warn("Unexpected rack timer %u", call->rack_timer_mode); + } +} diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 6716c021a532..e068f9b79d02 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -19,11 +19,14 @@ static int none_init_connection_security(struct rxrpc_connection *conn, */ static struct rxrpc_txbuf *none_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { - return rxrpc_alloc_data_txbuf(call, min_t(size_t, remain, RXRPC_JUMBO_DATALEN), 1, gfp); + return rxrpc_alloc_data_txbuf(call, umin(remain, RXRPC_JUMBO_DATALEN), 1, gfp); } static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { + txb->pkt_len = txb->len; + if (txb->len == RXRPC_JUMBO_DATALEN) + txb->jumboable = true; return 0; } diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 07c74c77d802..64f8d77b8731 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -338,7 +338,6 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, struct rxrpc_channel *chan; struct rxrpc_call *call = NULL; unsigned int channel; - bool ret; if (sp->hdr.securityIndex != conn->security_ix) return rxrpc_direct_abort(skb, rxrpc_eproto_wrong_security, @@ -364,6 +363,12 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, if (sp->hdr.callNumber == 0) return rxrpc_input_conn_packet(conn, skb); + /* Deal with path MTU discovery probing. */ + if (sp->hdr.type == RXRPC_PACKET_TYPE_ACK && + conn->pmtud_probe && + after_eq(sp->ack.acked_serial, conn->pmtud_probe)) + rxrpc_input_probe_for_pmtud(conn, sp->ack.acked_serial, false); + /* Call-bound packets are routed by connection channel. */ channel = sp->hdr.cid & RXRPC_CHANNELMASK; chan = &conn->channels[channel]; @@ -419,9 +424,9 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, peer_srx, skb); } - ret = rxrpc_input_call_event(call, skb); + rxrpc_queue_rx_call_packet(call, skb); rxrpc_put_call(call, rxrpc_call_put_input); - return ret; + return true; } /* @@ -438,6 +443,8 @@ int rxrpc_io_thread(void *data) ktime_t now; #endif bool should_stop; + LIST_HEAD(conn_attend_q); + LIST_HEAD(call_attend_q); complete(&local->io_thread_ready); @@ -448,43 +455,26 @@ int rxrpc_io_thread(void *data) for (;;) { rxrpc_inc_stat(local->rxnet, stat_io_loop); - /* Deal with connections that want immediate attention. */ - conn = list_first_entry_or_null(&local->conn_attend_q, - struct rxrpc_connection, - attend_link); - if (conn) { - spin_lock_bh(&local->lock); - list_del_init(&conn->attend_link); - spin_unlock_bh(&local->lock); + /* Inject a delay into packets if requested. */ +#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY + now = ktime_get_real(); + while ((skb = skb_peek(&local->rx_delay_queue))) { + if (ktime_before(now, skb->tstamp)) + break; + skb = skb_dequeue(&local->rx_delay_queue); + skb_queue_tail(&local->rx_queue, skb); + } +#endif - rxrpc_input_conn_event(conn, NULL); - rxrpc_put_connection(conn, rxrpc_conn_put_poke); - continue; + if (!skb_queue_empty(&local->rx_queue)) { + spin_lock_irq(&local->rx_queue.lock); + skb_queue_splice_tail_init(&local->rx_queue, &rx_queue); + spin_unlock_irq(&local->rx_queue.lock); + trace_rxrpc_iothread_rx(local, skb_queue_len(&rx_queue)); } - if (test_and_clear_bit(RXRPC_CLIENT_CONN_REAP_TIMER, - &local->client_conn_flags)) - rxrpc_discard_expired_client_conns(local); - - /* Deal with calls that want immediate attention. */ - if ((call = list_first_entry_or_null(&local->call_attend_q, - struct rxrpc_call, - attend_link))) { - spin_lock_bh(&local->lock); - list_del_init(&call->attend_link); - spin_unlock_bh(&local->lock); - - trace_rxrpc_call_poked(call); - rxrpc_input_call_event(call, NULL); - rxrpc_put_call(call, rxrpc_call_put_poke); - continue; - } - - if (!list_empty(&local->new_client_calls)) - rxrpc_connect_client_calls(local); - - /* Process received packets and errors. */ - if ((skb = __skb_dequeue(&rx_queue))) { + /* Distribute packets and errors. */ + while ((skb = __skb_dequeue(&rx_queue))) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); switch (skb->mark) { case RXRPC_SKB_MARK_PACKET: @@ -508,27 +498,46 @@ int rxrpc_io_thread(void *data) rxrpc_free_skb(skb, rxrpc_skb_put_unknown); break; } - continue; } - /* Inject a delay into packets if requested. */ -#ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY - now = ktime_get_real(); - while ((skb = skb_peek(&local->rx_delay_queue))) { - if (ktime_before(now, skb->tstamp)) - break; - skb = skb_dequeue(&local->rx_delay_queue); - skb_queue_tail(&local->rx_queue, skb); - } -#endif + /* Deal with connections that want immediate attention. */ + spin_lock_irq(&local->lock); + list_splice_tail_init(&local->conn_attend_q, &conn_attend_q); + spin_unlock_irq(&local->lock); - if (!skb_queue_empty(&local->rx_queue)) { - spin_lock_irq(&local->rx_queue.lock); - skb_queue_splice_tail_init(&local->rx_queue, &rx_queue); - spin_unlock_irq(&local->rx_queue.lock); - continue; + while ((conn = list_first_entry_or_null(&conn_attend_q, + struct rxrpc_connection, + attend_link))) { + spin_lock_irq(&local->lock); + list_del_init(&conn->attend_link); + spin_unlock_irq(&local->lock); + rxrpc_input_conn_event(conn, NULL); + rxrpc_put_connection(conn, rxrpc_conn_put_poke); } + if (test_and_clear_bit(RXRPC_CLIENT_CONN_REAP_TIMER, + &local->client_conn_flags)) + rxrpc_discard_expired_client_conns(local); + + /* Deal with calls that want immediate attention. */ + spin_lock_irq(&local->lock); + list_splice_tail_init(&local->call_attend_q, &call_attend_q); + spin_unlock_irq(&local->lock); + + while ((call = list_first_entry_or_null(&call_attend_q, + struct rxrpc_call, + attend_link))) { + spin_lock_irq(&local->lock); + list_del_init(&call->attend_link); + spin_unlock_irq(&local->lock); + trace_rxrpc_call_poked(call); + rxrpc_input_call_event(call); + rxrpc_put_call(call, rxrpc_call_put_poke); + } + + if (!list_empty(&local->new_client_calls)) + rxrpc_connect_client_calls(local); + set_current_state(TASK_INTERRUPTIBLE); should_stop = kthread_should_stop(); if (!skb_queue_empty(&local->rx_queue) || @@ -558,7 +567,7 @@ int rxrpc_io_thread(void *data) } timeout = nsecs_to_jiffies(delay_ns); - timeout = max(timeout, 1UL); + timeout = umax(timeout, 1); schedule_timeout(timeout); __set_current_state(TASK_RUNNING); continue; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 2792d2304605..a74a4b43904f 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -215,9 +215,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) /* we want to set the don't fragment bit */ rxrpc_local_dont_fragment(local, true); - - /* We want receive timestamps. */ - sock_enable_timestamps(usk); break; default: diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 657cf35089a6..8fcc8139d771 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -46,13 +46,13 @@ unsigned int rxrpc_rx_window_size = 255; * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet * made by gluing normal packets together that we're willing to handle. */ -unsigned int rxrpc_rx_mtu = 5692; +unsigned int rxrpc_rx_mtu = RXRPC_JUMBO(46); /* * The maximum number of fragments in a received jumbo packet that we tell the * sender that we're willing to handle. */ -unsigned int rxrpc_rx_jumbo_max = 4; +unsigned int rxrpc_rx_jumbo_max = 46; #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY /* diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 5ea9601efd05..6f7a125d6e90 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -72,76 +72,50 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call, ktime_t now) } /* - * Fill out an ACK packet. + * Allocate transmission buffers for an ACK and attach them to local->kv[]. */ -static void rxrpc_fill_out_ack(struct rxrpc_call *call, - struct rxrpc_txbuf *txb, - u8 ack_reason, - rxrpc_serial_t serial) +static int rxrpc_alloc_ack(struct rxrpc_call *call, size_t sack_size) { - struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; - struct rxrpc_acktrailer *trailer = txb->kvec[2].iov_base + 3; - struct rxrpc_ackpacket *ack = (struct rxrpc_ackpacket *)(whdr + 1); - unsigned int qsize, sack, wrap, to; - rxrpc_seq_t window, wtop; - int rsize; - u32 mtu, jmax; - u8 *filler = txb->kvec[2].iov_base; - u8 *sackp = txb->kvec[1].iov_base; + struct rxrpc_wire_header *whdr; + struct rxrpc_acktrailer *trailer; + struct rxrpc_ackpacket *ack; + struct kvec *kv = call->local->kvec; + gfp_t gfp = rcu_read_lock_held() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS; + void *buf, *buf2 = NULL; + u8 *filler; - rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); + buf = page_frag_alloc(&call->local->tx_alloc, + sizeof(*whdr) + sizeof(*ack) + 1 + 3 + sizeof(*trailer), gfp); + if (!buf) + return -ENOMEM; - window = call->ackr_window; - wtop = call->ackr_wtop; - sack = call->ackr_sack_base % RXRPC_SACK_SIZE; - - whdr->seq = 0; - whdr->type = RXRPC_PACKET_TYPE_ACK; - txb->flags |= RXRPC_SLOW_START_OK; - ack->bufferSpace = 0; - ack->maxSkew = 0; - ack->firstPacket = htonl(window); - ack->previousPacket = htonl(call->rx_highest_seq); - ack->serial = htonl(serial); - ack->reason = ack_reason; - ack->nAcks = wtop - window; - filler[0] = 0; - filler[1] = 0; - filler[2] = 0; - - if (ack_reason == RXRPC_ACK_PING) - txb->flags |= RXRPC_REQUEST_ACK; - - if (after(wtop, window)) { - txb->len += ack->nAcks; - txb->kvec[1].iov_base = sackp; - txb->kvec[1].iov_len = ack->nAcks; - - wrap = RXRPC_SACK_SIZE - sack; - to = min_t(unsigned int, ack->nAcks, RXRPC_SACK_SIZE); - - if (sack + ack->nAcks <= RXRPC_SACK_SIZE) { - memcpy(sackp, call->ackr_sack_table + sack, ack->nAcks); - } else { - memcpy(sackp, call->ackr_sack_table + sack, wrap); - memcpy(sackp + wrap, call->ackr_sack_table, to - wrap); + if (sack_size) { + buf2 = page_frag_alloc(&call->local->tx_alloc, sack_size, gfp); + if (!buf2) { + page_frag_free(buf); + return -ENOMEM; } - } else if (before(wtop, window)) { - pr_warn("ack window backward %x %x", window, wtop); - } else if (ack->reason == RXRPC_ACK_DELAY) { - ack->reason = RXRPC_ACK_IDLE; } - mtu = call->peer->if_mtu; - mtu -= call->peer->hdrsize; - jmax = rxrpc_rx_jumbo_max; - qsize = (window - 1) - call->rx_consumed; - rsize = max_t(int, call->rx_winsize - qsize, 0); - txb->ack_rwind = rsize; - trailer->maxMTU = htonl(rxrpc_rx_mtu); - trailer->ifMTU = htonl(mtu); - trailer->rwind = htonl(rsize); - trailer->jumbo_max = htonl(jmax); + whdr = buf; + ack = buf + sizeof(*whdr); + filler = buf + sizeof(*whdr) + sizeof(*ack) + 1; + trailer = buf + sizeof(*whdr) + sizeof(*ack) + 1 + 3; + + kv[0].iov_base = whdr; + kv[0].iov_len = sizeof(*whdr) + sizeof(*ack); + kv[1].iov_base = buf2; + kv[1].iov_len = sack_size; + kv[2].iov_base = filler; + kv[2].iov_len = 3 + sizeof(*trailer); + return 3; /* Number of kvec[] used. */ +} + +static void rxrpc_free_ack(struct rxrpc_call *call) +{ + page_frag_free(call->local->kvec[0].iov_base); + if (call->local->kvec[1].iov_base) + page_frag_free(call->local->kvec[1].iov_base); } /* @@ -172,16 +146,111 @@ no_slot: trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_no_slot, rtt_slot, serial); } +/* + * Fill out an ACK packet. + */ +static int rxrpc_fill_out_ack(struct rxrpc_call *call, int nr_kv, u8 ack_reason, + rxrpc_serial_t serial_to_ack, rxrpc_serial_t *_ack_serial) +{ + struct kvec *kv = call->local->kvec; + struct rxrpc_wire_header *whdr = kv[0].iov_base; + struct rxrpc_acktrailer *trailer = kv[2].iov_base + 3; + struct rxrpc_ackpacket *ack = (struct rxrpc_ackpacket *)(whdr + 1); + unsigned int qsize, sack, wrap, to, max_mtu, if_mtu; + rxrpc_seq_t window, wtop; + ktime_t now = ktime_get_real(); + int rsize; + u8 *filler = kv[2].iov_base; + u8 *sackp = kv[1].iov_base; + + rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); + + window = call->ackr_window; + wtop = call->ackr_wtop; + sack = call->ackr_sack_base % RXRPC_SACK_SIZE; + + *_ack_serial = rxrpc_get_next_serial(call->conn); + + whdr->epoch = htonl(call->conn->proto.epoch); + whdr->cid = htonl(call->cid); + whdr->callNumber = htonl(call->call_id); + whdr->serial = htonl(*_ack_serial); + whdr->seq = 0; + whdr->type = RXRPC_PACKET_TYPE_ACK; + whdr->flags = call->conn->out_clientflag | RXRPC_SLOW_START_OK; + whdr->userStatus = 0; + whdr->securityIndex = call->security_ix; + whdr->_rsvd = 0; + whdr->serviceId = htons(call->dest_srx.srx_service); + + ack->bufferSpace = 0; + ack->maxSkew = 0; + ack->firstPacket = htonl(window); + ack->previousPacket = htonl(call->rx_highest_seq); + ack->serial = htonl(serial_to_ack); + ack->reason = ack_reason; + ack->nAcks = wtop - window; + filler[0] = 0; + filler[1] = 0; + filler[2] = 0; + + if (ack_reason == RXRPC_ACK_PING) + whdr->flags |= RXRPC_REQUEST_ACK; + + if (after(wtop, window)) { + kv[1].iov_len = ack->nAcks; + + wrap = RXRPC_SACK_SIZE - sack; + to = umin(ack->nAcks, RXRPC_SACK_SIZE); + + if (sack + ack->nAcks <= RXRPC_SACK_SIZE) { + memcpy(sackp, call->ackr_sack_table + sack, ack->nAcks); + } else { + memcpy(sackp, call->ackr_sack_table + sack, wrap); + memcpy(sackp + wrap, call->ackr_sack_table, to - wrap); + } + } else if (before(wtop, window)) { + pr_warn("ack window backward %x %x", window, wtop); + } else if (ack->reason == RXRPC_ACK_DELAY) { + ack->reason = RXRPC_ACK_IDLE; + } + + qsize = (window - 1) - call->rx_consumed; + rsize = max_t(int, call->rx_winsize - qsize, 0); + + if_mtu = call->peer->if_mtu - call->peer->hdrsize; + if (call->peer->ackr_adv_pmtud) { + max_mtu = umax(call->peer->max_data, rxrpc_rx_mtu); + } else { + if_mtu = umin(if_mtu, 1444); + max_mtu = if_mtu; + } + + trailer->maxMTU = htonl(max_mtu); + trailer->ifMTU = htonl(if_mtu); + trailer->rwind = htonl(rsize); + trailer->jumbo_max = 0; /* Advertise pmtu discovery */ + + if (ack_reason == RXRPC_ACK_PING) + rxrpc_begin_rtt_probe(call, *_ack_serial, now, rxrpc_rtt_tx_ping); + if (whdr->flags & RXRPC_REQUEST_ACK) + call->rtt_last_req = now; + rxrpc_set_keepalive(call, now); + return nr_kv; +} + /* * Transmit an ACK packet. */ -static void rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +static void rxrpc_send_ack_packet(struct rxrpc_call *call, int nr_kv, size_t len, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) { - struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct kvec *kv = call->local->kvec; + struct rxrpc_wire_header *whdr = kv[0].iov_base; + struct rxrpc_acktrailer *trailer = kv[2].iov_base + 3; struct rxrpc_connection *conn; struct rxrpc_ackpacket *ack = (struct rxrpc_ackpacket *)(whdr + 1); struct msghdr msg; - ktime_t now; int ret; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -195,33 +264,34 @@ static void rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *t msg.msg_controllen = 0; msg.msg_flags = MSG_SPLICE_PAGES; - whdr->flags = txb->flags & RXRPC_TXBUF_WIRE_FLAGS; - - txb->serial = rxrpc_get_next_serial(conn); - whdr->serial = htonl(txb->serial); - trace_rxrpc_tx_ack(call->debug_id, txb->serial, + trace_rxrpc_tx_ack(call->debug_id, serial, ntohl(ack->firstPacket), ntohl(ack->serial), ack->reason, ack->nAcks, - txb->ack_rwind); + ntohl(trailer->rwind), why); rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); - iov_iter_kvec(&msg.msg_iter, WRITE, txb->kvec, txb->nr_kvec, txb->len); - rxrpc_local_dont_fragment(conn->local, false); - ret = do_udp_sendmsg(conn->local->socket, &msg, txb->len); + iov_iter_kvec(&msg.msg_iter, WRITE, kv, nr_kv, len); + rxrpc_local_dont_fragment(conn->local, why == rxrpc_propose_ack_ping_for_mtu_probe); + + ret = do_udp_sendmsg(conn->local->socket, &msg, len); call->peer->last_tx_at = ktime_get_seconds(); if (ret < 0) { - trace_rxrpc_tx_fail(call->debug_id, txb->serial, ret, + trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_ack); + if (why == rxrpc_propose_ack_ping_for_mtu_probe && + ret == -EMSGSIZE) + rxrpc_input_probe_for_pmtud(conn, serial, true); } else { trace_rxrpc_tx_packet(call->debug_id, whdr, rxrpc_tx_point_call_ack); - now = ktime_get_real(); - if (ack->reason == RXRPC_ACK_PING) - rxrpc_begin_rtt_probe(call, txb->serial, now, rxrpc_rtt_tx_ping); - if (txb->flags & RXRPC_REQUEST_ACK) - call->peer->rtt_last_req = now; - rxrpc_set_keepalive(call, now); + if (why == rxrpc_propose_ack_ping_for_mtu_probe) { + call->peer->pmtud_pending = false; + call->peer->pmtud_probing = true; + call->conn->pmtud_probe = serial; + call->conn->pmtud_call = call->debug_id; + trace_rxrpc_pmtud_tx(call); + } } rxrpc_tx_backoff(call, ret); } @@ -230,31 +300,62 @@ static void rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *t * Queue an ACK for immediate transmission. */ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, - rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) + rxrpc_serial_t serial_to_ack, enum rxrpc_propose_ack_trace why) { - struct rxrpc_txbuf *txb; + struct kvec *kv = call->local->kvec; + rxrpc_serial_t ack_serial; + size_t len; + int nr_kv; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return; rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); - txb = rxrpc_alloc_ack_txbuf(call, call->ackr_wtop - call->ackr_window); - if (!txb) { + nr_kv = rxrpc_alloc_ack(call, call->ackr_wtop - call->ackr_window); + if (nr_kv < 0) { kleave(" = -ENOMEM"); return; } - txb->ack_why = why; + nr_kv = rxrpc_fill_out_ack(call, nr_kv, ack_reason, serial_to_ack, &ack_serial); + len = kv[0].iov_len; + len += kv[1].iov_len; + len += kv[2].iov_len; + + /* Extend a path MTU probe ACK. */ + if (why == rxrpc_propose_ack_ping_for_mtu_probe) { + size_t probe_mtu = call->peer->pmtud_trial + sizeof(struct rxrpc_wire_header); + + if (len > probe_mtu) + goto skip; + while (len < probe_mtu) { + size_t part = umin(probe_mtu - len, PAGE_SIZE); + + kv[nr_kv].iov_base = page_address(ZERO_PAGE(0)); + kv[nr_kv].iov_len = part; + len += part; + nr_kv++; + } + } - rxrpc_fill_out_ack(call, txb, ack_reason, serial); call->ackr_nr_unacked = 0; atomic_set(&call->ackr_nr_consumed, 0); clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); - trace_rxrpc_send_ack(call, why, ack_reason, serial); - rxrpc_send_ack_packet(call, txb); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); + trace_rxrpc_send_ack(call, why, ack_reason, ack_serial); + rxrpc_send_ack_packet(call, nr_kv, len, ack_serial, why); +skip: + rxrpc_free_ack(call); +} + +/* + * Send an ACK probe for path MTU discovery. + */ +void rxrpc_send_probe_for_pmtud(struct rxrpc_call *call) +{ + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_mtu_probe); } /* @@ -324,14 +425,21 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) /* * Prepare a (sub)packet for transmission. */ -static void rxrpc_prepare_data_subpacket(struct rxrpc_call *call, struct rxrpc_txbuf *txb, - rxrpc_serial_t serial) +static size_t rxrpc_prepare_data_subpacket(struct rxrpc_call *call, + struct rxrpc_send_data_req *req, + struct rxrpc_txbuf *txb, + rxrpc_serial_t serial, int subpkt) { struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxrpc_jumbo_header *jumbo = (void *)(whdr + 1) - sizeof(*jumbo); enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; + struct kvec *kv = &call->local->kvec[subpkt]; + size_t len = txb->pkt_len; + bool last; + u8 flags; - _enter("%x,{%d}", txb->seq, txb->len); + _enter("%x,%zd", txb->seq, len); txb->serial = serial; @@ -339,6 +447,15 @@ static void rxrpc_prepare_data_subpacket(struct rxrpc_call *call, struct rxrpc_t txb->seq == 1) whdr->userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; + txb->flags &= ~RXRPC_REQUEST_ACK; + flags = txb->flags & RXRPC_TXBUF_WIRE_FLAGS; + last = txb->flags & RXRPC_LAST_PACKET; + + if (subpkt < req->n - 1) { + len = RXRPC_JUMBO_DATALEN; + goto dont_set_request_ack; + } + /* If our RTT cache needs working on, request an ACK. Also request * ACKs if a DATA packet appears to have been lost. * @@ -346,113 +463,188 @@ static void rxrpc_prepare_data_subpacket(struct rxrpc_call *call, struct rxrpc_t * service call, lest OpenAFS incorrectly send us an ACK with some * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if (txb->flags & RXRPC_REQUEST_ACK) - why = rxrpc_reqack_already_on; - else if ((txb->flags & RXRPC_LAST_PACKET) && rxrpc_sending_to_client(txb)) + if (last && rxrpc_sending_to_client(txb)) why = rxrpc_reqack_no_srv_last; else if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) why = rxrpc_reqack_ack_lost; else if (txb->flags & RXRPC_TXBUF_RESENT) why = rxrpc_reqack_retrans; - else if (call->cong_mode == RXRPC_CALL_SLOW_START && call->cong_cwnd <= 2) + else if (call->cong_ca_state == RXRPC_CA_SLOW_START && call->cong_cwnd <= RXRPC_MIN_CWND) why = rxrpc_reqack_slow_start; else if (call->tx_winsize <= 2) why = rxrpc_reqack_small_txwin; - else if (call->peer->rtt_count < 3 && txb->seq & 1) + else if (call->rtt_count < 3) why = rxrpc_reqack_more_rtt; - else if (ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), ktime_get_real())) + else if (ktime_before(ktime_add_ms(call->rtt_last_req, 1000), ktime_get_real())) why = rxrpc_reqack_old_rtt; + else if (!last && !after(READ_ONCE(call->send_top), txb->seq)) + why = rxrpc_reqack_app_stall; else goto dont_set_request_ack; rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); trace_rxrpc_req_ack(call->debug_id, txb->seq, why); - if (why != rxrpc_reqack_no_srv_last) - txb->flags |= RXRPC_REQUEST_ACK; + if (why != rxrpc_reqack_no_srv_last) { + flags |= RXRPC_REQUEST_ACK; + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, -1, serial); + call->rtt_last_req = req->now; + } dont_set_request_ack: - whdr->flags = txb->flags & RXRPC_TXBUF_WIRE_FLAGS; - whdr->serial = htonl(txb->serial); - whdr->cksum = txb->cksum; + /* The jumbo header overlays the wire header in the txbuf. */ + if (subpkt < req->n - 1) + flags |= RXRPC_JUMBO_PACKET; + else + flags &= ~RXRPC_JUMBO_PACKET; + if (subpkt == 0) { + whdr->flags = flags; + whdr->serial = htonl(txb->serial); + whdr->cksum = txb->cksum; + whdr->serviceId = htons(conn->service_id); + kv->iov_base = whdr; + len += sizeof(*whdr); + } else { + jumbo->flags = flags; + jumbo->pad = 0; + jumbo->cksum = txb->cksum; + kv->iov_base = jumbo; + len += sizeof(*jumbo); + } - trace_rxrpc_tx_data(call, txb->seq, txb->serial, txb->flags, false); + trace_rxrpc_tx_data(call, txb->seq, txb->serial, flags, req->trace); + kv->iov_len = len; + return len; } /* - * Prepare a packet for transmission. + * Prepare a transmission queue object for initial transmission. Returns the + * number of microseconds since the transmission queue base timestamp. */ -static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +static unsigned int rxrpc_prepare_txqueue(struct rxrpc_txqueue *tq, + struct rxrpc_send_data_req *req) { + if (!tq) + return 0; + if (tq->xmit_ts_base == KTIME_MIN) { + tq->xmit_ts_base = req->now; + return 0; + } + return ktime_to_us(ktime_sub(req->now, tq->xmit_ts_base)); +} + +/* + * Prepare a (jumbo) packet for transmission. + */ +static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req *req) +{ + struct rxrpc_txqueue *tq = req->tq; rxrpc_serial_t serial; + unsigned int xmit_ts; + rxrpc_seq_t seq = req->seq; + size_t len = 0; + bool start_tlp = false; + + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_transmit); /* Each transmission of a Tx packet needs a new serial number */ - serial = rxrpc_get_next_serial(call->conn); + serial = rxrpc_get_next_serials(call->conn, req->n); - rxrpc_prepare_data_subpacket(call, txb, serial); + call->tx_last_serial = serial + req->n - 1; + call->tx_last_sent = req->now; + xmit_ts = rxrpc_prepare_txqueue(tq, req); + prefetch(tq->next); - return txb->len; -} + for (int i = 0;;) { + int ix = seq & RXRPC_TXQ_MASK; + struct rxrpc_txbuf *txb = tq->bufs[seq & RXRPC_TXQ_MASK]; -/* - * Set timeouts after transmitting a packet. - */ -static void rxrpc_tstamp_data_packets(struct rxrpc_call *call, struct rxrpc_txbuf *txb) -{ - ktime_t now = ktime_get_real(); - bool ack_requested = txb->flags & RXRPC_REQUEST_ACK; + _debug("prep[%u] tq=%x q=%x", i, tq->qbase, seq); - call->tx_last_sent = now; - txb->last_sent = now; - - if (ack_requested) { - rxrpc_begin_rtt_probe(call, txb->serial, now, rxrpc_rtt_tx_data); - - call->peer->rtt_last_req = now; - if (call->peer->rtt_count > 1) { - ktime_t delay = rxrpc_get_rto_backoff(call->peer, false); - - call->ack_lost_at = ktime_add(now, delay); - trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_lost_ack); + /* Record (re-)transmission for RACK [RFC8985 6.1]. */ + if (__test_and_clear_bit(ix, &tq->segment_lost)) + call->tx_nr_lost--; + if (req->retrans) { + __set_bit(ix, &tq->ever_retransmitted); + __set_bit(ix, &tq->segment_retransmitted); + call->tx_nr_resent++; + } else { + call->tx_nr_sent++; + start_tlp = true; } + tq->segment_xmit_ts[ix] = xmit_ts; + tq->segment_serial[ix] = serial; + if (i + 1 == req->n) + /* Only sample the last subpacket in a jumbo. */ + __set_bit(ix, &tq->rtt_samples); + len += rxrpc_prepare_data_subpacket(call, req, txb, serial, i); + serial++; + seq++; + i++; + if (i >= req->n) + break; + if (!(seq & RXRPC_TXQ_MASK)) { + tq = tq->next; + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_transmit_advance); + xmit_ts = rxrpc_prepare_txqueue(tq, req); + } + } + + /* Set timeouts */ + if (req->tlp_probe) { + /* Sending TLP loss probe [RFC8985 7.3]. */ + call->tlp_serial = serial - 1; + call->tlp_seq = seq - 1; + } else if (start_tlp) { + /* Schedule TLP loss probe [RFC8985 7.2]. */ + ktime_t pto; + + if (!test_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) + /* The first packet may take longer to elicit a response. */ + pto = NSEC_PER_SEC; + else + pto = rxrpc_tlp_calc_pto(call, req->now); + + call->rack_timer_mode = RXRPC_CALL_RACKTIMER_TLP_PTO; + call->rack_timo_at = ktime_add(req->now, pto); + trace_rxrpc_rack_timer(call, pto, false); + trace_rxrpc_timer_set(call, pto, rxrpc_timer_trace_rack_tlp_pto); } if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) { ktime_t delay = ms_to_ktime(READ_ONCE(call->next_rx_timo)); - call->expect_rx_by = ktime_add(now, delay); + call->expect_rx_by = ktime_add(req->now, delay); trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_expect_rx); } - rxrpc_set_keepalive(call, now); + rxrpc_set_keepalive(call, req->now); + return len; } /* - * send a packet through the transport endpoint + * Send one or more packets through the transport endpoint */ -static int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req *req) { - struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; struct rxrpc_connection *conn = call->conn; enum rxrpc_tx_point frag; + struct rxrpc_txqueue *tq = req->tq; + struct rxrpc_txbuf *txb; struct msghdr msg; + rxrpc_seq_t seq = req->seq; size_t len; - int ret; + bool new_call = test_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags); + int ret, stat_ix; - _enter("%x,{%d}", txb->seq, txb->len); + _enter("%x,%x-%x", tq->qbase, seq, seq + req->n - 1); - len = rxrpc_prepare_data_packet(call, txb); + stat_ix = umin(req->n, ARRAY_SIZE(call->rxnet->stat_tx_jumbo)) - 1; + atomic_inc(&call->rxnet->stat_tx_jumbo[stat_ix]); - if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { - static int lose; - if ((lose++ & 7) == 7) { - ret = 0; - trace_rxrpc_tx_data(call, txb->seq, txb->serial, - txb->flags, true); - goto done; - } - } + len = rxrpc_prepare_data_packet(call, req); + txb = tq->bufs[seq & RXRPC_TXQ_MASK]; - iov_iter_kvec(&msg.msg_iter, WRITE, txb->kvec, txb->nr_kvec, len); + iov_iter_kvec(&msg.msg_iter, WRITE, call->local->kvec, req->n, len); msg.msg_name = &call->peer->srx.transport; msg.msg_namelen = call->peer->srx.transport_len; @@ -460,16 +652,11 @@ static int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *t msg.msg_controllen = 0; msg.msg_flags = MSG_SPLICE_PAGES; - /* Track what we've attempted to transmit at least once so that the - * retransmission algorithm doesn't try to resend what we haven't sent - * yet. + /* Send the packet with the don't fragment bit set unless we think it's + * too big or if this is a retransmission. */ - if (txb->seq == call->tx_transmitted + 1) - call->tx_transmitted = txb->seq; - - /* send the packet with the don't fragment bit set if we currently - * think it's small enough */ - if (txb->len >= call->peer->maxdata) { + if (seq == call->tx_transmitted + 1 && + len >= sizeof(struct rxrpc_wire_header) + call->peer->max_data) { rxrpc_local_dont_fragment(conn->local, false); frag = rxrpc_tx_point_call_data_frag; } else { @@ -477,7 +664,25 @@ static int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *t frag = rxrpc_tx_point_call_data_nofrag; } -retry: + /* Track what we've attempted to transmit at least once so that the + * retransmission algorithm doesn't try to resend what we haven't sent + * yet. + */ + if (seq == call->tx_transmitted + 1) + call->tx_transmitted = seq + req->n - 1; + + if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { + static int lose; + + if ((lose++ & 7) == 7) { + ret = 0; + trace_rxrpc_tx_data(call, txb->seq, txb->serial, txb->flags, + rxrpc_txdata_inject_loss); + conn->peer->last_tx_at = ktime_get_seconds(); + goto done; + } + } + /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet * to go out of the interface @@ -488,36 +693,35 @@ retry: ret = do_udp_sendmsg(conn->local->socket, &msg, len); conn->peer->last_tx_at = ktime_get_seconds(); - if (ret < 0) { + if (ret == -EMSGSIZE) { + rxrpc_inc_stat(call->rxnet, stat_tx_data_send_msgsize); + trace_rxrpc_tx_packet(call->debug_id, call->local->kvec[0].iov_base, frag); + ret = 0; + } else if (ret < 0) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); trace_rxrpc_tx_fail(call->debug_id, txb->serial, ret, frag); } else { - trace_rxrpc_tx_packet(call->debug_id, whdr, frag); + trace_rxrpc_tx_packet(call->debug_id, call->local->kvec[0].iov_base, frag); } rxrpc_tx_backoff(call, ret); - if (ret == -EMSGSIZE && frag == rxrpc_tx_point_call_data_frag) { - rxrpc_local_dont_fragment(conn->local, false); - frag = rxrpc_tx_point_call_data_frag; - goto retry; - } -done: - if (ret >= 0) { - rxrpc_tstamp_data_packets(call, txb); - } else { - /* Cancel the call if the initial transmission fails, - * particularly if that's due to network routing issues that - * aren't going away anytime soon. The layer above can arrange - * the retransmission. + if (ret < 0) { + /* Cancel the call if the initial transmission fails or if we + * hit due to network routing issues that aren't going away + * anytime soon. The layer above can arrange the + * retransmission. */ - if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) + if (new_call || + ret == -ENETUNREACH || + ret == -EHOSTUNREACH || + ret == -ECONNREFUSED) rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_USER_ABORT, ret); } - _leave(" = %d [%u]", ret, call->peer->maxdata); - return ret; +done: + _leave(" = %d [%u]", ret, call->peer->max_data); } /* @@ -692,41 +896,3 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) peer->last_tx_at = ktime_get_seconds(); _leave(""); } - -/* - * Schedule an instant Tx resend. - */ -static inline void rxrpc_instant_resend(struct rxrpc_call *call, - struct rxrpc_txbuf *txb) -{ - if (!__rxrpc_call_is_complete(call)) - kdebug("resend"); -} - -/* - * Transmit one packet. - */ -void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb) -{ - int ret; - - ret = rxrpc_send_data_packet(call, txb); - if (ret < 0) { - switch (ret) { - case -ENETUNREACH: - case -EHOSTUNREACH: - case -ECONNREFUSED: - rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - 0, ret); - break; - default: - _debug("need instant resend %d", ret); - rxrpc_instant_resend(call, txb); - } - } else { - ktime_t delay = ns_to_ktime(call->peer->rto_us * NSEC_PER_USEC); - - call->resend_at = ktime_add(ktime_get_real(), delay); - trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_resend_tx); - } -} diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 552ba84a255c..e874c31fa901 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -102,6 +102,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local, */ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu) { + unsigned int max_data; + /* wind down the local interface MTU */ if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) peer->if_mtu = mtu; @@ -120,11 +122,17 @@ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu) } } - if (mtu < peer->mtu) { - spin_lock(&peer->lock); - peer->mtu = mtu; - peer->maxdata = peer->mtu - peer->hdrsize; - spin_unlock(&peer->lock); + max_data = max_t(int, mtu - peer->hdrsize, 500); + if (max_data < peer->max_data) { + if (peer->pmtud_good > max_data) + peer->pmtud_good = max_data; + if (peer->pmtud_bad > max_data + 1) + peer->pmtud_bad = max_data + 1; + + trace_rxrpc_pmtud_reduce(peer, 0, max_data, rxrpc_pmtud_reduce_icmp); + write_seqcount_begin(&peer->mtu_lock); + peer->max_data = max_data; + write_seqcount_end(&peer->mtu_lock); } } @@ -205,23 +213,23 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, struct sk_buff *skb, struct rxrpc_call *call; HLIST_HEAD(error_targets); - spin_lock(&peer->lock); + spin_lock_irq(&peer->lock); hlist_move_list(&peer->error_targets, &error_targets); while (!hlist_empty(&error_targets)) { call = hlist_entry(error_targets.first, struct rxrpc_call, error_link); hlist_del_init(&call->error_link); - spin_unlock(&peer->lock); + spin_unlock_irq(&peer->lock); rxrpc_see_call(call, rxrpc_call_see_distribute_error); rxrpc_set_call_completion(call, compl, 0, -err); - rxrpc_input_call_event(call, skb); + rxrpc_input_call_event(call); - spin_lock(&peer->lock); + spin_lock_irq(&peer->lock); } - spin_unlock(&peer->lock); + spin_unlock_irq(&peer->lock); } /* @@ -238,7 +246,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, bool use; int slot; - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); while (!list_empty(collector)) { peer = list_entry(collector->next, @@ -249,7 +257,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, continue; use = __rxrpc_use_local(peer->local, rxrpc_local_use_peer_keepalive); - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); if (use) { keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; @@ -269,17 +277,17 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, */ slot += cursor; slot &= mask; - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); rxrpc_unuse_local(peer->local, rxrpc_local_unuse_peer_keepalive); } rxrpc_put_peer(peer, rxrpc_peer_put_keepalive); - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); } - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); } /* @@ -309,7 +317,7 @@ void rxrpc_peer_keepalive_worker(struct work_struct *work) * second; the bucket at cursor + 1 goes at now + 1s and so * on... */ - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); list_splice_init(&rxnet->peer_keepalive_new, &collector); stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive); @@ -321,7 +329,7 @@ void rxrpc_peer_keepalive_worker(struct work_struct *work) } base = now; - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); rxnet->peer_keepalive_base = base; rxnet->peer_keepalive_cursor = cursor; @@ -347,3 +355,89 @@ void rxrpc_peer_keepalive_worker(struct work_struct *work) _leave(""); } + +/* + * Do path MTU probing. + */ +void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t acked_serial, + bool sendmsg_fail) +{ + struct rxrpc_peer *peer = conn->peer; + unsigned int max_data = peer->max_data; + int good, trial, bad, jumbo; + + good = peer->pmtud_good; + trial = peer->pmtud_trial; + bad = peer->pmtud_bad; + if (good >= bad - 1) { + conn->pmtud_probe = 0; + peer->pmtud_lost = false; + return; + } + + if (!peer->pmtud_probing) + goto send_probe; + + if (sendmsg_fail || after(acked_serial, conn->pmtud_probe)) { + /* Retry a lost probe. */ + if (!peer->pmtud_lost) { + trace_rxrpc_pmtud_lost(conn, acked_serial); + conn->pmtud_probe = 0; + peer->pmtud_lost = true; + goto send_probe; + } + + /* The probed size didn't seem to get through. */ + bad = trial; + peer->pmtud_bad = bad; + if (bad <= max_data) + max_data = bad - 1; + } else { + /* It did get through. */ + good = trial; + peer->pmtud_good = good; + if (good > max_data) + max_data = good; + } + + max_data = umin(max_data, peer->ackr_max_data); + if (max_data != peer->max_data) { + preempt_disable(); + write_seqcount_begin(&peer->mtu_lock); + peer->max_data = max_data; + write_seqcount_end(&peer->mtu_lock); + preempt_enable(); + } + + jumbo = max_data + sizeof(struct rxrpc_jumbo_header); + jumbo /= RXRPC_JUMBO_SUBPKTLEN; + peer->pmtud_jumbo = jumbo; + + trace_rxrpc_pmtud_rx(conn, acked_serial); + conn->pmtud_probe = 0; + peer->pmtud_lost = false; + + if (good < RXRPC_JUMBO(2) && bad > RXRPC_JUMBO(2)) + trial = RXRPC_JUMBO(2); + else if (good < RXRPC_JUMBO(4) && bad > RXRPC_JUMBO(4)) + trial = RXRPC_JUMBO(4); + else if (good < RXRPC_JUMBO(3) && bad > RXRPC_JUMBO(3)) + trial = RXRPC_JUMBO(3); + else if (good < RXRPC_JUMBO(6) && bad > RXRPC_JUMBO(6)) + trial = RXRPC_JUMBO(6); + else if (good < RXRPC_JUMBO(5) && bad > RXRPC_JUMBO(5)) + trial = RXRPC_JUMBO(5); + else if (good < RXRPC_JUMBO(8) && bad > RXRPC_JUMBO(8)) + trial = RXRPC_JUMBO(8); + else if (good < RXRPC_JUMBO(7) && bad > RXRPC_JUMBO(7)) + trial = RXRPC_JUMBO(7); + else + trial = (good + bad) / 2; + peer->pmtud_trial = trial; + + if (good >= bad) + return; + +send_probe: + peer->pmtud_pending = true; +} diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 49dcda67a0d5..0fcc87f0409f 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -162,6 +162,11 @@ static void rxrpc_assess_MTU_size(struct rxrpc_local *local, #endif peer->if_mtu = 1500; + if (peer->max_data < peer->if_mtu - peer->hdrsize) { + trace_rxrpc_pmtud_reduce(peer, 0, peer->if_mtu - peer->hdrsize, + rxrpc_pmtud_reduce_route); + peer->max_data = peer->if_mtu - peer->hdrsize; + } memset(&fl, 0, sizeof(fl)); switch (peer->srx.transport.family) { @@ -199,8 +204,16 @@ static void rxrpc_assess_MTU_size(struct rxrpc_local *local, } peer->if_mtu = dst_mtu(dst); + peer->hdrsize += dst->header_len + dst->trailer_len; + peer->tx_seg_max = dst->dev->gso_max_segs; dst_release(dst); + peer->max_data = umin(RXRPC_JUMBO(1), peer->if_mtu - peer->hdrsize); + peer->pmtud_good = 500; + peer->pmtud_bad = peer->if_mtu - peer->hdrsize + 1; + peer->pmtud_trial = umin(peer->max_data, peer->pmtud_bad - 1); + peer->pmtud_pending = true; + _leave(" [if_mtu %u]", peer->if_mtu); } @@ -222,11 +235,9 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp, peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); spin_lock_init(&peer->lock); - spin_lock_init(&peer->rtt_input_lock); + seqcount_init(&peer->mtu_lock); peer->debug_id = atomic_inc_return(&rxrpc_debug_id); - - rxrpc_peer_init_rtt(peer); - + peer->recent_srtt_us = UINT_MAX; peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW; trace_rxrpc_peer(peer->debug_id, 1, why); } @@ -242,9 +253,7 @@ static void rxrpc_init_peer(struct rxrpc_local *local, struct rxrpc_peer *peer, unsigned long hash_key) { peer->hash_key = hash_key; - rxrpc_assess_MTU_size(local, peer); - peer->mtu = peer->if_mtu; - peer->rtt_last_req = ktime_get_real(); + switch (peer->srx.transport.family) { case AF_INET: @@ -268,7 +277,9 @@ static void rxrpc_init_peer(struct rxrpc_local *local, struct rxrpc_peer *peer, } peer->hdrsize += sizeof(struct rxrpc_wire_header); - peer->maxdata = peer->mtu - peer->hdrsize; + peer->max_data = peer->if_mtu - peer->hdrsize; + + rxrpc_assess_MTU_size(local, peer); } /* @@ -304,6 +315,7 @@ static void rxrpc_free_peer(struct rxrpc_peer *peer) * Set up a new incoming peer. There shouldn't be any other matching peers * since we've already done a search in the list from the non-reentrant context * (the data_ready handler) that is the only place we can add new peers. + * Called with interrupts disabled. */ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) { @@ -313,10 +325,10 @@ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) hash_key = rxrpc_peer_hash_key(local, &peer->srx); rxrpc_init_peer(local, peer, hash_key); - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); } /* @@ -348,7 +360,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, return NULL; } - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); /* Need to check that we aren't racing with someone else */ peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); @@ -361,7 +373,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, &rxnet->peer_keepalive_new); } - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); if (peer) rxrpc_free_peer(candidate); @@ -411,10 +423,10 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) ASSERT(hlist_empty(&peer->error_targets)); - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); rxrpc_free_peer(peer); } @@ -479,7 +491,7 @@ EXPORT_SYMBOL(rxrpc_kernel_get_call_peer); */ unsigned int rxrpc_kernel_get_srtt(const struct rxrpc_peer *peer) { - return peer->rtt_count > 0 ? peer->srtt_us >> 3 : UINT_MAX; + return READ_ONCE(peer->recent_srtt_us); } EXPORT_SYMBOL(rxrpc_kernel_get_srtt); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 263a2251e3d2..d803562ca0ac 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -52,7 +52,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); enum rxrpc_call_state state; - rxrpc_seq_t acks_hard_ack; + rxrpc_seq_t tx_bottom; char lbuff[50], rbuff[50]; long timeout = 0; @@ -79,7 +79,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) if (state != RXRPC_CALL_SERVER_PREALLOC) timeout = ktime_ms_delta(READ_ONCE(call->expect_rx_by), ktime_get_real()); - acks_hard_ack = READ_ONCE(call->acks_hard_ack); + tx_bottom = READ_ONCE(call->tx_bottom); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" " %-8.8s %08x %08x %08x %02x %08x %02x %08x %02x %06lx\n", @@ -93,7 +93,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) rxrpc_call_states[state], call->abort_code, call->debug_id, - acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack, + tx_bottom, READ_ONCE(call->tx_top) - tx_bottom, call->ackr_window, call->ackr_wtop - call->ackr_window, call->rx_serial, call->cong_cwnd, @@ -283,9 +283,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) { seq_puts(seq, - "Proto Local " - " Remote " - " Use SST MTU LastUse RTT RTO\n" + "Proto Local Remote Use SST Maxd LastUse RTT RTO\n" ); return 0; } @@ -298,16 +296,15 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) now = ktime_get_seconds(); seq_printf(seq, - "UDP %-47.47s %-47.47s %3u" - " %3u %5u %6llus %8u %8u\n", + "UDP %-47.47s %-47.47s %3u %4u %5u %6llus %8d %8d\n", lbuff, rbuff, refcount_read(&peer->ref), peer->cong_ssthresh, - peer->mtu, + peer->max_data, now - peer->last_tx_at, - peer->srtt_us >> 3, - peer->rto_us); + READ_ONCE(peer->recent_srtt_us), + READ_ONCE(peer->recent_rto_us)); return 0; } @@ -476,10 +473,11 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) struct rxrpc_net *rxnet = rxrpc_net(seq_file_single_net(seq)); seq_printf(seq, - "Data : send=%u sendf=%u fail=%u\n", + "Data : send=%u sendf=%u fail=%u emsz=%u\n", atomic_read(&rxnet->stat_tx_data_send), atomic_read(&rxnet->stat_tx_data_send_frag), - atomic_read(&rxnet->stat_tx_data_send_fail)); + atomic_read(&rxnet->stat_tx_data_send_fail), + atomic_read(&rxnet->stat_tx_data_send_msgsize)); seq_printf(seq, "Data-Tx : nr=%u retrans=%u uf=%u cwr=%u\n", atomic_read(&rxnet->stat_tx_data), @@ -508,7 +506,7 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_DELAY]), atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_IDLE])); seq_printf(seq, - "Ack-Rx : req=%u dup=%u oos=%u exw=%u nos=%u png=%u prs=%u dly=%u idl=%u\n", + "Ack-Rx : req=%u dup=%u oos=%u exw=%u nos=%u png=%u prs=%u dly=%u idl=%u z=%u\n", atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_REQUESTED]), atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_DUPLICATE]), atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_OUT_OF_SEQUENCE]), @@ -517,19 +515,44 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_PING]), atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_PING_RESPONSE]), atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_DELAY]), - atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_IDLE])); + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_IDLE]), + atomic_read(&rxnet->stat_rx_acks[0])); seq_printf(seq, - "Why-Req-A: acklost=%u already=%u mrtt=%u ortt=%u\n", + "Why-Req-A: acklost=%u mrtt=%u ortt=%u stall=%u\n", atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_ack_lost]), - atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_already_on]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_more_rtt]), - atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_old_rtt])); + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_old_rtt]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_app_stall])); seq_printf(seq, "Why-Req-A: nolast=%u retx=%u slows=%u smtxw=%u\n", atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_no_srv_last]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_retrans]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_slow_start]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_small_txwin])); + seq_printf(seq, + "Jumbo-Tx : %u,%u,%u,%u,%u,%u,%u,%u,%u,%u\n", + atomic_read(&rxnet->stat_tx_jumbo[0]), + atomic_read(&rxnet->stat_tx_jumbo[1]), + atomic_read(&rxnet->stat_tx_jumbo[2]), + atomic_read(&rxnet->stat_tx_jumbo[3]), + atomic_read(&rxnet->stat_tx_jumbo[4]), + atomic_read(&rxnet->stat_tx_jumbo[5]), + atomic_read(&rxnet->stat_tx_jumbo[6]), + atomic_read(&rxnet->stat_tx_jumbo[7]), + atomic_read(&rxnet->stat_tx_jumbo[8]), + atomic_read(&rxnet->stat_tx_jumbo[9])); + seq_printf(seq, + "Jumbo-Rx : %u,%u,%u,%u,%u,%u,%u,%u,%u,%u\n", + atomic_read(&rxnet->stat_rx_jumbo[0]), + atomic_read(&rxnet->stat_rx_jumbo[1]), + atomic_read(&rxnet->stat_rx_jumbo[2]), + atomic_read(&rxnet->stat_rx_jumbo[3]), + atomic_read(&rxnet->stat_rx_jumbo[4]), + atomic_read(&rxnet->stat_rx_jumbo[5]), + atomic_read(&rxnet->stat_rx_jumbo[6]), + atomic_read(&rxnet->stat_rx_jumbo[7]), + atomic_read(&rxnet->stat_rx_jumbo[8]), + atomic_read(&rxnet->stat_rx_jumbo[9])); seq_printf(seq, "Buffers : txb=%u rxb=%u\n", atomic_read(&rxrpc_nr_txbuf), @@ -567,6 +590,8 @@ int rxrpc_stats_clear(struct file *file, char *buf, size_t size) atomic_set(&rxnet->stat_tx_ack_skip, 0); memset(&rxnet->stat_tx_acks, 0, sizeof(rxnet->stat_tx_acks)); memset(&rxnet->stat_rx_acks, 0, sizeof(rxnet->stat_rx_acks)); + memset(&rxnet->stat_tx_jumbo, 0, sizeof(rxnet->stat_tx_jumbo)); + memset(&rxnet->stat_rx_jumbo, 0, sizeof(rxnet->stat_rx_jumbo)); memset(&rxnet->stat_why_req_ack, 0, sizeof(rxnet->stat_why_req_ack)); diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index 4fe6b4d20ada..42f70e4636f8 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -92,11 +92,16 @@ struct rxrpc_jumbo_header { /* * The maximum number of subpackets that can possibly fit in a UDP packet is: * - * ((max_IP - IP_hdr - UDP_hdr) / RXRPC_JUMBO_SUBPKTLEN) + 1 - * = ((65535 - 28 - 28) / 1416) + 1 - * = 46 non-terminal packets and 1 terminal packet. + * (max_UDP - wirehdr + jumbohdr) / (jumbohdr + 1412) + * = ((65535 - 28 + 4) / 1416) + * = 45 non-terminal packets and 1 terminal packet. */ -#define RXRPC_MAX_NR_JUMBO 47 +#define RXRPC_MAX_NR_JUMBO 46 + +/* Size of a jumbo packet with N subpackets, excluding UDP+IP */ +#define RXRPC_JUMBO(N) ((int)sizeof(struct rxrpc_wire_header) + \ + RXRPC_JUMBO_DATALEN + \ + ((N) - 1) * RXRPC_JUMBO_SUBPKTLEN) /*****************************************************************************/ /* diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index a482f88c5fc5..32cd5f1d541d 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -36,16 +36,16 @@ void rxrpc_notify_socket(struct rxrpc_call *call) sk = &rx->sk; if (rx && sk->sk_state < RXRPC_CLOSE) { if (call->notify_rx) { - spin_lock(&call->notify_lock); + spin_lock_irq(&call->notify_lock); call->notify_rx(sk, call, call->user_call_ID); - spin_unlock(&call->notify_lock); + spin_unlock_irq(&call->notify_lock); } else { - spin_lock(&rx->recvmsg_lock); + spin_lock_irq(&rx->recvmsg_lock); if (list_empty(&call->recvmsg_link)) { rxrpc_get_call(call, rxrpc_call_get_notify_socket); list_add_tail(&call->recvmsg_link, &rx->recvmsg_q); } - spin_unlock(&rx->recvmsg_lock); + spin_unlock_irq(&rx->recvmsg_lock); if (!sock_flag(sk, SOCK_DEAD)) { _debug("call %ps", sk->sk_data_ready); @@ -337,14 +337,14 @@ try_again: * We also want to weed out calls that got requeued whilst we were * shovelling data out. */ - spin_lock(&rx->recvmsg_lock); + spin_lock_irq(&rx->recvmsg_lock); l = rx->recvmsg_q.next; call = list_entry(l, struct rxrpc_call, recvmsg_link); if (!rxrpc_call_is_complete(call) && skb_queue_empty(&call->recvmsg_queue)) { list_del_init(&call->recvmsg_link); - spin_unlock(&rx->recvmsg_lock); + spin_unlock_irq(&rx->recvmsg_lock); release_sock(&rx->sk); trace_rxrpc_recvmsg(call->debug_id, rxrpc_recvmsg_unqueue, 0); rxrpc_put_call(call, rxrpc_call_put_recvmsg); @@ -355,7 +355,7 @@ try_again: list_del_init(&call->recvmsg_link); else rxrpc_get_call(call, rxrpc_call_get_recvmsg); - spin_unlock(&rx->recvmsg_lock); + spin_unlock_irq(&rx->recvmsg_lock); call_debug_id = call->debug_id; trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_dequeue, 0); @@ -445,9 +445,9 @@ error_unlock_call: error_requeue_call: if (!(flags & MSG_PEEK)) { - spin_lock(&rx->recvmsg_lock); + spin_lock_irq(&rx->recvmsg_lock); list_add(&call->recvmsg_link, &rx->recvmsg_q); - spin_unlock(&rx->recvmsg_lock); + spin_unlock_irq(&rx->recvmsg_lock); trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0); } else { rxrpc_put_call(call, rxrpc_call_put_recvmsg); diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c index cdab7b7d08a0..7474f88d7b18 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -12,22 +12,22 @@ #include "ar-internal.h" #define RXRPC_RTO_MAX (120 * USEC_PER_SEC) -#define RXRPC_TIMEOUT_INIT ((unsigned int)(1 * MSEC_PER_SEC)) /* RFC6298 2.1 initial RTO value */ +#define RXRPC_TIMEOUT_INIT ((unsigned int)(1 * USEC_PER_SEC)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ -static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) +static u32 rxrpc_rto_min_us(struct rxrpc_call *call) { return 200; } -static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer) +static u32 __rxrpc_set_rto(const struct rxrpc_call *call) { - return (peer->srtt_us >> 3) + peer->rttvar_us; + return (call->srtt_us >> 3) + call->rttvar_us; } static u32 rxrpc_bound_rto(u32 rto) { - return min(rto, RXRPC_RTO_MAX); + return clamp(200000, rto + 100000, RXRPC_RTO_MAX); } /* @@ -40,10 +40,10 @@ static u32 rxrpc_bound_rto(u32 rto) * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ -static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us) +static void rxrpc_rtt_estimator(struct rxrpc_call *call, long sample_rtt_us) { long m = sample_rtt_us; /* RTT */ - u32 srtt = peer->srtt_us; + u32 srtt = call->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev @@ -66,7 +66,7 @@ static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us) srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ - m -= (peer->mdev_us >> 2); /* similar update on mdev */ + m -= (call->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain @@ -78,31 +78,31 @@ static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us) if (m > 0) m >>= 3; } else { - m -= (peer->mdev_us >> 2); /* similar update on mdev */ + m -= (call->mdev_us >> 2); /* similar update on mdev */ } - peer->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ - if (peer->mdev_us > peer->mdev_max_us) { - peer->mdev_max_us = peer->mdev_us; - if (peer->mdev_max_us > peer->rttvar_us) - peer->rttvar_us = peer->mdev_max_us; + call->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ + if (call->mdev_us > call->mdev_max_us) { + call->mdev_max_us = call->mdev_us; + if (call->mdev_max_us > call->rttvar_us) + call->rttvar_us = call->mdev_max_us; } } else { /* no previous measure. */ srtt = m << 3; /* take the measured time to be rtt */ - peer->mdev_us = m << 1; /* make sure rto = 3*rtt */ - peer->rttvar_us = max(peer->mdev_us, rxrpc_rto_min_us(peer)); - peer->mdev_max_us = peer->rttvar_us; + call->mdev_us = m << 1; /* make sure rto = 3*rtt */ + call->rttvar_us = umax(call->mdev_us, rxrpc_rto_min_us(call)); + call->mdev_max_us = call->rttvar_us; } - peer->srtt_us = max(1U, srtt); + call->srtt_us = umax(srtt, 1); } /* * Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ -static void rxrpc_set_rto(struct rxrpc_peer *peer) +static void rxrpc_set_rto(struct rxrpc_call *call) { u32 rto; @@ -113,7 +113,7 @@ static void rxrpc_set_rto(struct rxrpc_peer *peer) * is invisible. Actually, Linux-2.4 also generates erratic * ACKs in some circumstances. */ - rto = __rxrpc_set_rto(peer); + rto = __rxrpc_set_rto(call); /* 2. Fixups made earlier cannot be right. * If we do not estimate RTO correctly without them, @@ -124,61 +124,73 @@ static void rxrpc_set_rto(struct rxrpc_peer *peer) /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo * guarantees that rto is higher. */ - peer->rto_us = rxrpc_bound_rto(rto); + call->rto_us = rxrpc_bound_rto(rto); } -static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) +static void rxrpc_update_rtt_min(struct rxrpc_call *call, ktime_t resp_time, long rtt_us) +{ + /* Window size 5mins in approx usec (ipv4.sysctl_tcp_min_rtt_wlen) */ + u32 wlen_us = 5ULL * NSEC_PER_SEC / 1024; + + minmax_running_min(&call->min_rtt, wlen_us, resp_time / 1024, + (u32)rtt_us ? : jiffies_to_usecs(1)); +} + +static void rxrpc_ack_update_rtt(struct rxrpc_call *call, ktime_t resp_time, long rtt_us) { if (rtt_us < 0) return; - //rxrpc_update_rtt_min(peer, rtt_us); - rxrpc_rtt_estimator(peer, rtt_us); - rxrpc_set_rto(peer); + /* Update RACK min RTT [RFC8985 6.1 Step 1]. */ + rxrpc_update_rtt_min(call, resp_time, rtt_us); - /* RFC6298: only reset backoff on valid RTT measurement. */ - peer->backoff = 0; + rxrpc_rtt_estimator(call, rtt_us); + rxrpc_set_rto(call); + + /* Only reset backoff on valid RTT measurement [RFC6298]. */ + call->backoff = 0; } /* * Add RTT information to cache. This is called in softirq mode and has - * exclusive access to the peer RTT data. + * exclusive access to the call RTT data. */ -void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, +void rxrpc_call_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time) { - struct rxrpc_peer *peer = call->peer; s64 rtt_us; rtt_us = ktime_to_us(ktime_sub(resp_time, send_time)); if (rtt_us < 0) return; - spin_lock(&peer->rtt_input_lock); - rxrpc_ack_update_rtt(peer, rtt_us); - if (peer->rtt_count < 3) - peer->rtt_count++; - spin_unlock(&peer->rtt_input_lock); + rxrpc_ack_update_rtt(call, resp_time, rtt_us); + if (call->rtt_count < 3) + call->rtt_count++; + call->rtt_taken++; + + WRITE_ONCE(call->peer->recent_srtt_us, call->srtt_us / 8); + WRITE_ONCE(call->peer->recent_rto_us, call->rto_us); trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, - peer->srtt_us >> 3, peer->rto_us); + rtt_us, call->srtt_us, call->rto_us); } /* * Get the retransmission timeout to set in nanoseconds, backing it off each * time we retransmit. */ -ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) +ktime_t rxrpc_get_rto_backoff(struct rxrpc_call *call, bool retrans) { u64 timo_us; - u32 backoff = READ_ONCE(peer->backoff); + u32 backoff = READ_ONCE(call->backoff); - timo_us = peer->rto_us; + timo_us = call->rto_us; timo_us <<= backoff; if (retrans && timo_us * 2 <= RXRPC_RTO_MAX) - WRITE_ONCE(peer->backoff, backoff + 1); + WRITE_ONCE(call->backoff, backoff + 1); if (timo_us < 1) timo_us = 1; @@ -186,10 +198,11 @@ ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) return ns_to_ktime(timo_us * NSEC_PER_USEC); } -void rxrpc_peer_init_rtt(struct rxrpc_peer *peer) +void rxrpc_call_init_rtt(struct rxrpc_call *call) { - peer->rto_us = RXRPC_TIMEOUT_INIT; - peer->mdev_us = RXRPC_TIMEOUT_INIT; - peer->backoff = 0; - //minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U); + call->rtt_last_req = KTIME_MIN; + call->rto_us = RXRPC_TIMEOUT_INIT; + call->mdev_us = RXRPC_TIMEOUT_INIT; + call->backoff = 0; + //minmax_reset(&call->rtt_min, rxrpc_jiffies32, ~0U); } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 48a1475e6b06..62b09d23ec08 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -148,14 +148,14 @@ error: static struct rxrpc_txbuf *rxkad_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { struct rxrpc_txbuf *txb; - size_t shdr, space; + size_t shdr, alloc, limit, part; - remain = min(remain, 65535 - sizeof(struct rxrpc_wire_header)); + remain = umin(remain, 65535 - sizeof(struct rxrpc_wire_header)); switch (call->conn->security_level) { default: - space = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); - return rxrpc_alloc_data_txbuf(call, space, 1, gfp); + alloc = umin(remain, RXRPC_JUMBO_DATALEN); + return rxrpc_alloc_data_txbuf(call, alloc, 1, gfp); case RXRPC_SECURITY_AUTH: shdr = sizeof(struct rxkad_level1_hdr); break; @@ -164,15 +164,21 @@ static struct rxrpc_txbuf *rxkad_alloc_txbuf(struct rxrpc_call *call, size_t rem break; } - space = min_t(size_t, round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN), remain + shdr); - space = round_up(space, RXKAD_ALIGN); + limit = round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN) - shdr; + if (remain < limit) { + part = remain; + alloc = round_up(shdr + part, RXKAD_ALIGN); + } else { + part = limit; + alloc = RXRPC_JUMBO_DATALEN; + } - txb = rxrpc_alloc_data_txbuf(call, space, RXKAD_ALIGN, gfp); + txb = rxrpc_alloc_data_txbuf(call, alloc, RXKAD_ALIGN, gfp); if (!txb) return NULL; txb->offset += shdr; - txb->space -= shdr; + txb->space = part; return txb; } @@ -263,13 +269,13 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, check = txb->seq ^ call->call_id; hdr->data_size = htonl((u32)check << 16 | txb->len); - txb->len += sizeof(struct rxkad_level1_hdr); - pad = txb->len; + txb->pkt_len = sizeof(struct rxkad_level1_hdr) + txb->len; + pad = txb->pkt_len; pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; if (pad) { memset(txb->kvec[0].iov_base + txb->offset, 0, pad); - txb->len += pad; + txb->pkt_len += pad; } /* start the encryption afresh */ @@ -298,7 +304,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, struct rxkad_level2_hdr *rxkhdr = (void *)(whdr + 1); struct rxrpc_crypt iv; struct scatterlist sg; - size_t pad; + size_t content, pad; u16 check; int ret; @@ -309,23 +315,20 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, rxkhdr->data_size = htonl(txb->len | (u32)check << 16); rxkhdr->checksum = 0; - txb->len += sizeof(struct rxkad_level2_hdr); - pad = txb->len; - pad = RXKAD_ALIGN - pad; - pad &= RXKAD_ALIGN - 1; - if (pad) { + content = sizeof(struct rxkad_level2_hdr) + txb->len; + txb->pkt_len = round_up(content, RXKAD_ALIGN); + pad = txb->pkt_len - content; + if (pad) memset(txb->kvec[0].iov_base + txb->offset, 0, pad); - txb->len += pad; - } /* encrypt from the session key */ token = call->conn->key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); - sg_init_one(&sg, rxkhdr, txb->len); + sg_init_one(&sg, rxkhdr, txb->pkt_len); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg, &sg, txb->len, iv.x); + skcipher_request_set_crypt(req, &sg, &sg, txb->pkt_len, iv.x); ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); return ret; @@ -384,19 +387,33 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) switch (call->conn->security_level) { case RXRPC_SECURITY_PLAIN: + txb->pkt_len = txb->len; ret = 0; break; case RXRPC_SECURITY_AUTH: ret = rxkad_secure_packet_auth(call, txb, req); + if (txb->alloc_size == RXRPC_JUMBO_DATALEN) + txb->jumboable = true; break; case RXRPC_SECURITY_ENCRYPT: ret = rxkad_secure_packet_encrypt(call, txb, req); + if (txb->alloc_size == RXRPC_JUMBO_DATALEN) + txb->jumboable = true; break; default: ret = -EPERM; break; } + /* Clear excess space in the packet */ + if (txb->pkt_len < txb->alloc_size) { + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + size_t gap = txb->alloc_size - txb->pkt_len; + void *p = whdr + 1; + + memset(p + txb->pkt_len, 0, gap); + } + skcipher_request_free(req); _leave(" = %d [set %x]", ret, y); return ret; diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c index 085e7892d310..7ef93407be83 100644 --- a/net/rxrpc/rxperf.c +++ b/net/rxrpc/rxperf.c @@ -503,7 +503,7 @@ static int rxperf_process_call(struct rxperf_call *call) reply_len + sizeof(rxperf_magic_cookie)); while (reply_len > 0) { - len = min_t(size_t, reply_len, PAGE_SIZE); + len = umin(reply_len, PAGE_SIZE); bvec_set_page(&bv, ZERO_PAGE(0), len, 0); iov_iter_bvec(&msg.msg_iter, WRITE, &bv, 1, len); msg.msg_flags = MSG_MORE; diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index cb8dd1d3b1d4..9784adc8f275 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -114,10 +114,10 @@ found: if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) { ret = conn->security->init_connection_security(conn, token); if (ret == 0) { - spin_lock(&conn->state_lock); + spin_lock_irq(&conn->state_lock); if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) conn->state = RXRPC_CONN_CLIENT; - spin_unlock(&conn->state_lock); + spin_unlock_irq(&conn->state_lock); } } mutex_unlock(&conn->security_lock); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 6abb8eec1b2b..0e8da909d4f2 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -94,9 +94,11 @@ no_wait: */ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) { + rxrpc_seq_t tx_bottom = READ_ONCE(call->tx_bottom); + if (_tx_win) - *_tx_win = call->tx_bottom; - return call->tx_prepared - call->tx_bottom < 256; + *_tx_win = tx_bottom; + return call->send_top - tx_bottom < 256; } /* @@ -132,13 +134,13 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, rxrpc_seq_t tx_start, tx_win; signed long rtt, timeout; - rtt = READ_ONCE(call->peer->srtt_us) >> 3; + rtt = READ_ONCE(call->srtt_us) >> 3; rtt = usecs_to_jiffies(rtt) * 2; if (rtt < 2) rtt = 2; timeout = rtt; - tx_start = smp_load_acquire(&call->acks_hard_ack); + tx_start = READ_ONCE(call->tx_bottom); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); @@ -195,8 +197,8 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, DECLARE_WAITQUEUE(myself, current); int ret; - _enter(",{%u,%u,%u,%u}", - call->tx_bottom, call->acks_hard_ack, call->tx_top, call->tx_winsize); + _enter(",{%u,%u,%u}", + call->tx_bottom, call->tx_top, call->tx_winsize); add_wait_queue(&call->waitq, &myself); @@ -240,36 +242,76 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, struct rxrpc_txbuf *txb, rxrpc_notify_end_tx_t notify_end_tx) { + struct rxrpc_txqueue *sq = call->send_queue; rxrpc_seq_t seq = txb->seq; bool poke, last = txb->flags & RXRPC_LAST_PACKET; - + int ix = seq & RXRPC_TXQ_MASK; rxrpc_inc_stat(call->rxnet, stat_tx_data); - ASSERTCMP(txb->seq, ==, call->tx_prepared + 1); - - /* We have to set the timestamp before queueing as the retransmit - * algorithm can see the packet as soon as we queue it. - */ - txb->last_sent = ktime_get_real(); + ASSERTCMP(txb->seq, ==, call->send_top + 1); if (last) trace_rxrpc_txqueue(call, rxrpc_txqueue_queue_last); else trace_rxrpc_txqueue(call, rxrpc_txqueue_queue); + if (WARN_ON_ONCE(sq->bufs[ix])) + trace_rxrpc_tq(call, sq, seq, rxrpc_tq_queue_dup); + else + trace_rxrpc_tq(call, sq, seq, rxrpc_tq_queue); + /* Add the packet to the call's output buffer */ - spin_lock(&call->tx_lock); - poke = list_empty(&call->tx_sendmsg); - list_add_tail(&txb->call_link, &call->tx_sendmsg); - call->tx_prepared = seq; - if (last) + poke = (READ_ONCE(call->tx_bottom) == call->send_top); + sq->bufs[ix] = txb; + /* Order send_top after the queue->next pointer and txb content. */ + smp_store_release(&call->send_top, seq); + if (last) { + set_bit(RXRPC_CALL_TX_NO_MORE, &call->flags); rxrpc_notify_end_tx(rx, call, notify_end_tx); - spin_unlock(&call->tx_lock); + call->send_queue = NULL; + } if (poke) rxrpc_poke_call(call, rxrpc_call_poke_start); } +/* + * Allocate a new txqueue unit and add it to the transmission queue. + */ +static int rxrpc_alloc_txqueue(struct sock *sk, struct rxrpc_call *call) +{ + struct rxrpc_txqueue *tq; + + tq = kzalloc(sizeof(*tq), sk->sk_allocation); + if (!tq) + return -ENOMEM; + + tq->xmit_ts_base = KTIME_MIN; + for (int i = 0; i < RXRPC_NR_TXQUEUE; i++) + tq->segment_xmit_ts[i] = UINT_MAX; + + if (call->send_queue) { + tq->qbase = call->send_top + 1; + call->send_queue->next = tq; + call->send_queue = tq; + } else if (WARN_ON(call->tx_queue)) { + kfree(tq); + return -ENOMEM; + } else { + /* We start at seq 1, so pretend seq 0 is hard-acked. */ + tq->nr_reported_acks = 1; + tq->segment_acked = 1UL; + tq->qbase = 0; + call->tx_qbase = 0; + call->send_queue = tq; + call->tx_qtail = tq; + call->tx_queue = tq; + } + + trace_rxrpc_tq(call, tq, call->send_top, rxrpc_tq_alloc); + return 0; +} + /* * send data through a socket * - must be called in process context @@ -288,6 +330,13 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, bool more = msg->msg_flags & MSG_MORE; int ret, copied = 0; + if (test_bit(RXRPC_CALL_TX_NO_MORE, &call->flags)) { + trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send, + call->cid, call->call_id, call->rx_consumed, + 0, -EPROTO); + return -EPROTO; + } + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); ret = rxrpc_wait_to_be_connected(call, &timeo); @@ -344,6 +393,13 @@ reload: if (!rxrpc_check_tx_space(call, NULL)) goto wait_for_space; + /* See if we need to begin/extend the Tx queue. */ + if (!call->send_queue || !((call->send_top + 1) & RXRPC_TXQ_MASK)) { + ret = rxrpc_alloc_txqueue(sk, call); + if (ret < 0) + goto maybe_error; + } + /* Work out the maximum size of a packet. Assume that * the security header is going to be in the padded * region (enc blocksize), but the trailer is not. @@ -360,7 +416,7 @@ reload: /* append next segment of data to the current buffer */ if (msg_data_left(msg) > 0) { - size_t copy = min_t(size_t, txb->space, msg_data_left(msg)); + size_t copy = umin(txb->space, msg_data_left(msg)); _debug("add %zu", copy); if (!copy_from_iter_full(txb->kvec[0].iov_base + txb->offset, @@ -385,16 +441,12 @@ reload: (msg_data_left(msg) == 0 && !more)) { if (msg_data_left(msg) == 0 && !more) txb->flags |= RXRPC_LAST_PACKET; - else if (call->tx_top - call->acks_hard_ack < - call->tx_winsize) - txb->flags |= RXRPC_MORE_PACKETS; ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; txb->kvec[0].iov_len += txb->len; - txb->len = txb->kvec[0].iov_len; rxrpc_queue_packet(rx, call, txb, notify_end_tx); txb = NULL; } diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index 9bf9a1f6e4cb..46a20cf4c402 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -11,6 +11,8 @@ #include "ar-internal.h" static struct ctl_table_header *rxrpc_sysctl_reg_table; +static const unsigned int rxrpc_rx_mtu_min = 500; +static const unsigned int rxrpc_jumbo_max = RXRPC_MAX_NR_JUMBO; static const unsigned int four = 4; static const unsigned int max_backlog = RXRPC_BACKLOG_MAX - 1; static const unsigned int n_65535 = 65535; @@ -115,7 +117,7 @@ static struct ctl_table rxrpc_sysctl_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = (void *)SYSCTL_ONE, + .extra1 = (void *)&rxrpc_rx_mtu_min, .extra2 = (void *)&n_65535, }, { @@ -125,7 +127,7 @@ static struct ctl_table rxrpc_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)SYSCTL_ONE, - .extra2 = (void *)&four, + .extra2 = (void *)&rxrpc_jumbo_max, }, }; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index c3913d8a50d3..131d9e55c8e9 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -24,7 +24,7 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_ size_t total, hoff; void *buf; - txb = kmalloc(sizeof(*txb), gfp); + txb = kzalloc(sizeof(*txb), gfp); if (!txb) return NULL; @@ -43,20 +43,14 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_ whdr = buf + hoff; - INIT_LIST_HEAD(&txb->call_link); - INIT_LIST_HEAD(&txb->tx_link); refcount_set(&txb->ref, 1); - txb->last_sent = KTIME_MIN; txb->call_debug_id = call->debug_id; txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->alloc_size = data_size; txb->space = data_size; - txb->len = 0; txb->offset = sizeof(*whdr); txb->flags = call->conn->out_clientflag; - txb->ack_why = 0; - txb->seq = call->tx_prepared + 1; - txb->serial = 0; - txb->cksum = 0; + txb->seq = call->send_top + 1; txb->nr_kvec = 1; txb->kvec[0].iov_base = whdr; txb->kvec[0].iov_len = sizeof(*whdr); @@ -79,84 +73,6 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_ return txb; } -/* - * Allocate and partially initialise an ACK packet. - */ -struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_size) -{ - struct rxrpc_wire_header *whdr; - struct rxrpc_acktrailer *trailer; - struct rxrpc_ackpacket *ack; - struct rxrpc_txbuf *txb; - gfp_t gfp = rcu_read_lock_held() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS; - void *buf, *buf2 = NULL; - u8 *filler; - - txb = kmalloc(sizeof(*txb), gfp); - if (!txb) - return NULL; - - buf = page_frag_alloc(&call->local->tx_alloc, - sizeof(*whdr) + sizeof(*ack) + 1 + 3 + sizeof(*trailer), gfp); - if (!buf) { - kfree(txb); - return NULL; - } - - if (sack_size) { - buf2 = page_frag_alloc(&call->local->tx_alloc, sack_size, gfp); - if (!buf2) { - page_frag_free(buf); - kfree(txb); - return NULL; - } - } - - whdr = buf; - ack = buf + sizeof(*whdr); - filler = buf + sizeof(*whdr) + sizeof(*ack) + 1; - trailer = buf + sizeof(*whdr) + sizeof(*ack) + 1 + 3; - - INIT_LIST_HEAD(&txb->call_link); - INIT_LIST_HEAD(&txb->tx_link); - refcount_set(&txb->ref, 1); - txb->call_debug_id = call->debug_id; - txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); - txb->space = 0; - txb->len = sizeof(*whdr) + sizeof(*ack) + 3 + sizeof(*trailer); - txb->offset = 0; - txb->flags = call->conn->out_clientflag; - txb->ack_rwind = 0; - txb->seq = 0; - txb->serial = 0; - txb->cksum = 0; - txb->nr_kvec = 3; - txb->kvec[0].iov_base = whdr; - txb->kvec[0].iov_len = sizeof(*whdr) + sizeof(*ack); - txb->kvec[1].iov_base = buf2; - txb->kvec[1].iov_len = sack_size; - txb->kvec[2].iov_base = filler; - txb->kvec[2].iov_len = 3 + sizeof(*trailer); - - whdr->epoch = htonl(call->conn->proto.epoch); - whdr->cid = htonl(call->cid); - whdr->callNumber = htonl(call->call_id); - whdr->seq = 0; - whdr->type = RXRPC_PACKET_TYPE_ACK; - whdr->flags = 0; - whdr->userStatus = 0; - whdr->securityIndex = call->security_ix; - whdr->_rsvd = 0; - whdr->serviceId = htons(call->dest_srx.srx_service); - - get_page(virt_to_head_page(trailer)); - - trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, - rxrpc_txbuf_alloc_ack); - atomic_inc(&rxrpc_nr_txbuf); - return txb; -} - void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) { int r; @@ -179,7 +95,8 @@ static void rxrpc_free_txbuf(struct rxrpc_txbuf *txb) trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 0, rxrpc_txbuf_free); for (i = 0; i < txb->nr_kvec; i++) - if (txb->kvec[i].iov_base) + if (txb->kvec[i].iov_base && + !is_zero_pfn(page_to_pfn(virt_to_page(txb->kvec[i].iov_base)))) page_frag_free(txb->kvec[i].iov_base); kfree(txb); atomic_dec(&rxrpc_nr_txbuf); @@ -202,37 +119,3 @@ void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) rxrpc_free_txbuf(txb); } } - -/* - * Shrink the transmit buffer. - */ -void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) -{ - struct rxrpc_txbuf *txb; - rxrpc_seq_t hard_ack = smp_load_acquire(&call->acks_hard_ack); - bool wake = false; - - _enter("%x/%x/%x", call->tx_bottom, call->acks_hard_ack, call->tx_top); - - while ((txb = list_first_entry_or_null(&call->tx_buffer, - struct rxrpc_txbuf, call_link))) { - hard_ack = smp_load_acquire(&call->acks_hard_ack); - if (before(hard_ack, txb->seq)) - break; - - if (txb->seq != call->tx_bottom + 1) - rxrpc_see_txbuf(txb, rxrpc_txbuf_see_out_of_step); - ASSERTCMP(txb->seq, ==, call->tx_bottom + 1); - smp_store_release(&call->tx_bottom, call->tx_bottom + 1); - list_del_rcu(&txb->call_link); - - trace_rxrpc_txqueue(call, rxrpc_txqueue_dequeue); - - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_rotated); - if (after(call->acks_hard_ack, call->tx_bottom + 128)) - wake = true; - } - - if (wake) - wake_up(&call->waitq); -} diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 7578e27260c9..8e47e5355be6 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -390,6 +390,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->protocol = protocol; tp->prio = prio; tp->chain = chain; + tp->usesw = !tp->ops->reoffload; spin_lock_init(&tp->lock); refcount_set(&tp->refcnt, 1); @@ -410,39 +411,31 @@ static void tcf_proto_get(struct tcf_proto *tp) refcount_inc(&tp->refcnt); } -static void tcf_maintain_bypass(struct tcf_block *block) +static void tcf_proto_count_usesw(struct tcf_proto *tp, bool add) { - int filtercnt = atomic_read(&block->filtercnt); - int skipswcnt = atomic_read(&block->skipswcnt); - bool bypass_wanted = filtercnt > 0 && filtercnt == skipswcnt; - - if (bypass_wanted != block->bypass_wanted) { #ifdef CONFIG_NET_CLS_ACT - if (bypass_wanted) - static_branch_inc(&tcf_bypass_check_needed_key); - else - static_branch_dec(&tcf_bypass_check_needed_key); -#endif - block->bypass_wanted = bypass_wanted; - } -} + struct tcf_block *block = tp->chain->block; + bool counted = false; -static void tcf_block_filter_cnt_update(struct tcf_block *block, bool *counted, bool add) -{ - lockdep_assert_not_held(&block->cb_lock); - - down_write(&block->cb_lock); - if (*counted != add) { - if (add) { - atomic_inc(&block->filtercnt); - *counted = true; - } else { - atomic_dec(&block->filtercnt); - *counted = false; + if (!add) { + if (tp->usesw && tp->counted) { + if (!atomic_dec_return(&block->useswcnt)) + static_branch_dec(&tcf_sw_enabled_key); + tp->counted = false; } + return; } - tcf_maintain_bypass(block); - up_write(&block->cb_lock); + + spin_lock(&tp->lock); + if (tp->usesw && !tp->counted) { + counted = true; + tp->counted = true; + } + spin_unlock(&tp->lock); + + if (counted && atomic_inc_return(&block->useswcnt) == 1) + static_branch_inc(&tcf_sw_enabled_key); +#endif } static void tcf_chain_put(struct tcf_chain *chain); @@ -451,7 +444,7 @@ static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, bool sig_destroy, struct netlink_ext_ack *extack) { tp->ops->destroy(tp, rtnl_held, extack); - tcf_block_filter_cnt_update(tp->chain->block, &tp->counted, false); + tcf_proto_count_usesw(tp, false); if (sig_destroy) tcf_proto_signal_destroyed(tp->chain, tp); tcf_chain_put(tp->chain); @@ -2409,7 +2402,7 @@ replay: tfilter_notify(net, skb, n, tp, block, q, parent, fh, RTM_NEWTFILTER, false, rtnl_held, extack); tfilter_put(tp, fh); - tcf_block_filter_cnt_update(block, &tp->counted, true); + tcf_proto_count_usesw(tp, true); /* q pointer is NULL for shared blocks */ if (q) q->flags &= ~TCQ_F_CAN_BYPASS; @@ -3532,8 +3525,6 @@ static void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) if (*flags & TCA_CLS_FLAGS_IN_HW) return; *flags |= TCA_CLS_FLAGS_IN_HW; - if (tc_skip_sw(*flags)) - atomic_inc(&block->skipswcnt); atomic_inc(&block->offloadcnt); } @@ -3542,8 +3533,6 @@ static void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) if (!(*flags & TCA_CLS_FLAGS_IN_HW)) return; *flags &= ~TCA_CLS_FLAGS_IN_HW; - if (tc_skip_sw(*flags)) - atomic_dec(&block->skipswcnt); atomic_dec(&block->offloadcnt); } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 1941ebec23ff..7fbe42f0e5c2 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -509,6 +509,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, if (!tc_in_hw(prog->gen_flags)) prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW; + tcf_proto_update_usesw(tp, prog->gen_flags); + if (oldprog) { idr_replace(&head->handle_idr, prog, handle); list_replace_rcu(&oldprog->link, &prog->link); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 5502998aace7..5c2580a07530 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -356,7 +356,8 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_KEYS] = { .type = NLA_U32 }, [TCA_FLOW_MODE] = { .type = NLA_U32 }, [TCA_FLOW_BASECLASS] = { .type = NLA_U32 }, - [TCA_FLOW_RSHIFT] = { .type = NLA_U32 }, + [TCA_FLOW_RSHIFT] = NLA_POLICY_MAX(NLA_U32, + 31 /* BITS_PER_U32 - 1 */), [TCA_FLOW_ADDEND] = { .type = NLA_U32 }, [TCA_FLOW_MASK] = { .type = NLA_U32 }, [TCA_FLOW_XOR] = { .type = NLA_U32 }, diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 1008ec8a464c..03505673d523 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2503,6 +2503,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (!tc_in_hw(fnew->flags)) fnew->flags |= TCA_CLS_FLAGS_NOT_IN_HW; + tcf_proto_update_usesw(tp, fnew->flags); + spin_lock(&tp->lock); /* tp was deleted concurrently. -EAGAIN will cause caller to lookup diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 9f1e62ca508d..f03bf5da39ee 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -228,6 +228,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, if (!tc_in_hw(new->flags)) new->flags |= TCA_CLS_FLAGS_NOT_IN_HW; + tcf_proto_update_usesw(tp, new->flags); + *arg = head; rcu_assign_pointer(tp->root, new); return 0; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d3a03c57545b..2a1c00048fd6 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -951,6 +951,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (!tc_in_hw(new->flags)) new->flags |= TCA_CLS_FLAGS_NOT_IN_HW; + tcf_proto_update_usesw(tp, new->flags); + u32_replace_knode(tp, tp_c, new); tcf_unbind_filter(tp, &n->res); tcf_exts_get_net(&n->exts); @@ -1164,6 +1166,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (!tc_in_hw(n->flags)) n->flags |= TCA_CLS_FLAGS_NOT_IN_HW; + tcf_proto_update_usesw(tp, n->flags); + ins = &ht->ht[TC_U32_HASH(handle)]; for (pins = rtnl_dereference(*ins); pins; ins = &pins->next, pins = rtnl_dereference(*ins)) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 300430b8c4d2..e3e91cf867eb 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1560,7 +1560,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { - NL_SET_ERR_MSG(extack, "Invalid qdisc name"); + NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; } @@ -1664,13 +1664,17 @@ replay: q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) goto create_n_graft; + if (q->parent != tcm->tcm_parent) { + NL_SET_ERR_MSG(extack, "Cannot move an existing qdisc to a different parent"); + return -EINVAL; + } if (n->nlmsg_flags & NLM_F_EXCL) { NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot override"); return -EEXIST; } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { - NL_SET_ERR_MSG(extack, "Invalid qdisc name"); + NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; } if (q->flags & TCQ_F_INGRESS) { @@ -1746,7 +1750,7 @@ replay: return -EEXIST; } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { - NL_SET_ERR_MSG(extack, "Invalid qdisc name"); + NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; } err = qdisc_change(q, tca, extack); diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 8d8b2db4653c..48dd8c88903f 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -484,13 +484,14 @@ static bool cobalt_queue_empty(struct cobalt_vars *vars, /* Call this with a freshly dequeued packet for possible congestion marking. * Returns true as an instruction to drop the packet, false for delivery. */ -static bool cobalt_should_drop(struct cobalt_vars *vars, - struct cobalt_params *p, - ktime_t now, - struct sk_buff *skb, - u32 bulk_flows) +static enum skb_drop_reason cobalt_should_drop(struct cobalt_vars *vars, + struct cobalt_params *p, + ktime_t now, + struct sk_buff *skb, + u32 bulk_flows) { - bool next_due, over_target, drop = false; + enum skb_drop_reason reason = SKB_NOT_DROPPED_YET; + bool next_due, over_target; ktime_t schedule; u64 sojourn; @@ -533,7 +534,8 @@ static bool cobalt_should_drop(struct cobalt_vars *vars, if (next_due && vars->dropping) { /* Use ECN mark if possible, otherwise drop */ - drop = !(vars->ecn_marked = INET_ECN_set_ce(skb)); + if (!(vars->ecn_marked = INET_ECN_set_ce(skb))) + reason = SKB_DROP_REASON_QDISC_CONGESTED; vars->count++; if (!vars->count) @@ -556,16 +558,17 @@ static bool cobalt_should_drop(struct cobalt_vars *vars, } /* Simple BLUE implementation. Lack of ECN is deliberate. */ - if (vars->p_drop) - drop |= (get_random_u32() < vars->p_drop); + if (vars->p_drop && reason == SKB_NOT_DROPPED_YET && + get_random_u32() < vars->p_drop) + reason = SKB_DROP_REASON_CAKE_FLOOD; /* Overload the drop_next field as an activity timeout */ if (!vars->count) vars->drop_next = ktime_add_ns(now, p->interval); - else if (ktime_to_ns(schedule) > 0 && !drop) + else if (ktime_to_ns(schedule) > 0 && reason == SKB_NOT_DROPPED_YET) vars->drop_next = now; - return drop; + return reason; } static bool cake_update_flowkeys(struct flow_keys *keys, @@ -627,6 +630,63 @@ static bool cake_ddst(int flow_mode) return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST; } +static void cake_dec_srchost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_dsrc(flow_mode) && + q->hosts[flow->srchost].srchost_bulk_flow_count)) + q->hosts[flow->srchost].srchost_bulk_flow_count--; +} + +static void cake_inc_srchost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_dsrc(flow_mode) && + q->hosts[flow->srchost].srchost_bulk_flow_count < CAKE_QUEUES)) + q->hosts[flow->srchost].srchost_bulk_flow_count++; +} + +static void cake_dec_dsthost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_ddst(flow_mode) && + q->hosts[flow->dsthost].dsthost_bulk_flow_count)) + q->hosts[flow->dsthost].dsthost_bulk_flow_count--; +} + +static void cake_inc_dsthost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_ddst(flow_mode) && + q->hosts[flow->dsthost].dsthost_bulk_flow_count < CAKE_QUEUES)) + q->hosts[flow->dsthost].dsthost_bulk_flow_count++; +} + +static u16 cake_get_flow_quantum(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + u16 host_load = 1; + + if (cake_dsrc(flow_mode)) + host_load = max(host_load, + q->hosts[flow->srchost].srchost_bulk_flow_count); + + if (cake_ddst(flow_mode)) + host_load = max(host_load, + q->hosts[flow->dsthost].dsthost_bulk_flow_count); + + /* The get_random_u16() is a way to apply dithering to avoid + * accumulating roundoff errors + */ + return (q->flow_quantum * quantum_div[host_load] + + get_random_u16()) >> 16; +} + static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, int flow_mode, u16 flow_override, u16 host_override) { @@ -773,10 +833,8 @@ skip_hash: allocate_dst = cake_ddst(flow_mode); if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { - if (allocate_src) - q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--; - if (allocate_dst) - q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--; + cake_dec_srchost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode); + cake_dec_dsthost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode); } found: /* reserve queue for future packets in same flow */ @@ -801,9 +859,10 @@ found: q->hosts[outer_hash + k].srchost_tag = srchost_hash; found_src: srchost_idx = outer_hash + k; - if (q->flows[reduced_hash].set == CAKE_SET_BULK) - q->hosts[srchost_idx].srchost_bulk_flow_count++; q->flows[reduced_hash].srchost = srchost_idx; + + if (q->flows[reduced_hash].set == CAKE_SET_BULK) + cake_inc_srchost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode); } if (allocate_dst) { @@ -824,9 +883,10 @@ found_src: q->hosts[outer_hash + k].dsthost_tag = dsthost_hash; found_dst: dsthost_idx = outer_hash + k; - if (q->flows[reduced_hash].set == CAKE_SET_BULK) - q->hosts[dsthost_idx].dsthost_bulk_flow_count++; q->flows[reduced_hash].dsthost = dsthost_idx; + + if (q->flows[reduced_hash].set == CAKE_SET_BULK) + cake_inc_dsthost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode); } } @@ -1528,12 +1588,11 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) flow->dropped++; b->tin_dropped++; - sch->qstats.drops++; if (q->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, skb, now, true); - __qdisc_drop(skb, to_free); + qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT); sch->q.qlen--; qdisc_tree_reduce_backlog(sch, 1, len); @@ -1839,10 +1898,6 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* flowchain */ if (!flow->set || flow->set == CAKE_SET_DECAYING) { - struct cake_host *srchost = &b->hosts[flow->srchost]; - struct cake_host *dsthost = &b->hosts[flow->dsthost]; - u16 host_load = 1; - if (!flow->set) { list_add_tail(&flow->flowchain, &b->new_flows); } else { @@ -1852,18 +1907,8 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, flow->set = CAKE_SET_SPARSE; b->sparse_flow_count++; - if (cake_dsrc(q->flow_mode)) - host_load = max(host_load, srchost->srchost_bulk_flow_count); - - if (cake_ddst(q->flow_mode)) - host_load = max(host_load, dsthost->dsthost_bulk_flow_count); - - flow->deficit = (b->flow_quantum * - quantum_div[host_load]) >> 16; + flow->deficit = cake_get_flow_quantum(b, flow, q->flow_mode); } else if (flow->set == CAKE_SET_SPARSE_WAIT) { - struct cake_host *srchost = &b->hosts[flow->srchost]; - struct cake_host *dsthost = &b->hosts[flow->dsthost]; - /* this flow was empty, accounted as a sparse flow, but actually * in the bulk rotation. */ @@ -1871,12 +1916,8 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, b->sparse_flow_count--; b->bulk_flow_count++; - if (cake_dsrc(q->flow_mode)) - srchost->srchost_bulk_flow_count++; - - if (cake_ddst(q->flow_mode)) - dsthost->dsthost_bulk_flow_count++; - + cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode); } if (q->buffer_used > q->buffer_max_used) @@ -1926,20 +1967,19 @@ static void cake_clear_tin(struct Qdisc *sch, u16 tin) q->cur_tin = tin; for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++) while (!!(skb = cake_dequeue_one(sch))) - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_QUEUE_PURGE); } static struct sk_buff *cake_dequeue(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[q->cur_tin]; - struct cake_host *srchost, *dsthost; + enum skb_drop_reason reason; ktime_t now = ktime_get(); struct cake_flow *flow; struct list_head *head; bool first_flow = true; struct sk_buff *skb; - u16 host_load; u64 delay; u32 len; @@ -2039,11 +2079,6 @@ retry: q->cur_flow = flow - b->flows; first_flow = false; - /* triple isolation (modified DRR++) */ - srchost = &b->hosts[flow->srchost]; - dsthost = &b->hosts[flow->dsthost]; - host_load = 1; - /* flow isolation (DRR++) */ if (flow->deficit <= 0) { /* Keep all flows with deficits out of the sparse and decaying @@ -2055,11 +2090,8 @@ retry: b->sparse_flow_count--; b->bulk_flow_count++; - if (cake_dsrc(q->flow_mode)) - srchost->srchost_bulk_flow_count++; - - if (cake_ddst(q->flow_mode)) - dsthost->dsthost_bulk_flow_count++; + cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode); flow->set = CAKE_SET_BULK; } else { @@ -2071,19 +2103,7 @@ retry: } } - if (cake_dsrc(q->flow_mode)) - host_load = max(host_load, srchost->srchost_bulk_flow_count); - - if (cake_ddst(q->flow_mode)) - host_load = max(host_load, dsthost->dsthost_bulk_flow_count); - - WARN_ON(host_load > CAKE_QUEUES); - - /* The get_random_u16() is a way to apply dithering to avoid - * accumulating roundoff errors - */ - flow->deficit += (b->flow_quantum * quantum_div[host_load] + - get_random_u16()) >> 16; + flow->deficit += cake_get_flow_quantum(b, flow, q->flow_mode); list_move_tail(&flow->flowchain, &b->old_flows); goto retry; @@ -2107,11 +2127,8 @@ retry: if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; - if (cake_dsrc(q->flow_mode)) - srchost->srchost_bulk_flow_count--; - - if (cake_ddst(q->flow_mode)) - dsthost->dsthost_bulk_flow_count--; + cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode); b->decaying_flow_count++; } else if (flow->set == CAKE_SET_SPARSE || @@ -2129,12 +2146,8 @@ retry: else if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; - if (cake_dsrc(q->flow_mode)) - srchost->srchost_bulk_flow_count--; - - if (cake_ddst(q->flow_mode)) - dsthost->dsthost_bulk_flow_count--; - + cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode); } else b->decaying_flow_count--; @@ -2143,12 +2156,12 @@ retry: goto begin; } + reason = cobalt_should_drop(&flow->cvars, &b->cparams, now, skb, + (b->bulk_flow_count * + !!(q->rate_flags & + CAKE_FLAG_INGRESS))); /* Last packet in queue may be marked, shouldn't be dropped */ - if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb, - (b->bulk_flow_count * - !!(q->rate_flags & - CAKE_FLAG_INGRESS))) || - !flow->head) + if (reason == SKB_NOT_DROPPED_YET || !flow->head) break; /* drop this packet, get another one */ @@ -2162,7 +2175,7 @@ retry: b->tin_dropped++; qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_qstats_drop(sch); - kfree_skb(skb); + kfree_skb_reason(skb, reason); if (q->rate_flags & CAKE_FLAG_INGRESS) goto retry; } diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 3e8d4fe4d91e..81189d02fee7 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -52,7 +52,7 @@ static void drop_func(struct sk_buff *skb, void *ctx) { struct Qdisc *sch = ctx; - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_CONGESTED); qdisc_qstats_drop(sch); } @@ -89,7 +89,8 @@ static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, } q = qdisc_priv(sch); q->drop_overlimit++; - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_reason(skb, sch, to_free, + SKB_DROP_REASON_QDISC_OVERLIMIT); } static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index f80bc05d4c5a..516038a44163 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -91,6 +91,8 @@ ets_class_from_arg(struct Qdisc *sch, unsigned long arg) { struct ets_sched *q = qdisc_priv(sch); + if (arg == 0 || arg > q->nbands) + return NULL; return &q->classes[arg - 1]; } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a5e87f9ea986..2ca5332cfcc5 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -537,6 +537,8 @@ static bool fq_packet_beyond_horizon(const struct sk_buff *skb, return unlikely((s64)skb->tstamp > (s64)(now + q->horizon)); } +#define FQDR(reason) SKB_DROP_REASON_FQ_##reason + static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { @@ -548,7 +550,8 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, band = fq_prio2band(q->prio2band, skb->priority & TC_PRIO_MAX); if (unlikely(q->band_pkt_count[band] >= sch->limit)) { q->stat_band_drops[band]++; - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_reason(skb, sch, to_free, + FQDR(BAND_LIMIT)); } now = ktime_get_ns(); @@ -558,8 +561,9 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Check if packet timestamp is too far in the future. */ if (fq_packet_beyond_horizon(skb, q, now)) { if (q->horizon_drop) { - q->stat_horizon_drops++; - return qdisc_drop(skb, sch, to_free); + q->stat_horizon_drops++; + return qdisc_drop_reason(skb, sch, to_free, + FQDR(HORIZON_LIMIT)); } q->stat_horizon_caps++; skb->tstamp = now + q->horizon; @@ -572,7 +576,8 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (f != &q->internal) { if (unlikely(f->qlen >= q->flow_plimit)) { q->stat_flows_plimit++; - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_reason(skb, sch, to_free, + FQDR(FLOW_LIMIT)); } if (fq_flow_is_detached(f)) { @@ -597,6 +602,7 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_SUCCESS; } +#undef FQDR static void fq_check_throttled(struct fq_sched_data *q, u64 now) { diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 4f908c11ba95..799f5397ad4c 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -168,6 +168,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets, skb = dequeue_head(flow); len += qdisc_pkt_len(skb); mem += get_codel_cb(skb)->mem_usage; + tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_OVERLIMIT); __qdisc_drop(skb, to_free); } while (++i < max_packets && len < threshold); @@ -274,7 +275,7 @@ static void drop_func(struct sk_buff *skb, void *ctx) { struct Qdisc *sch = ctx; - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_CONGESTED); qdisc_qstats_drop(sch); } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index c38f33ff80bd..93c36afbf576 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -130,6 +130,7 @@ static inline void flow_queue_add(struct fq_pie_flow *flow, static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_OVERLIMIT; struct fq_pie_sched_data *q = qdisc_priv(sch); struct fq_pie_flow *sel_flow; int ret; @@ -161,6 +162,8 @@ static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->overmemory++; } + reason = SKB_DROP_REASON_QDISC_CONGESTED; + if (!pie_drop_early(sch, &q->p_params, &sel_flow->vars, sel_flow->backlog, skb->len)) { enqueue = true; @@ -198,8 +201,7 @@ static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, out: q->stats.dropped++; sel_flow->vars.accu_prob = 0; - __qdisc_drop(skb, to_free); - qdisc_qstats_drop(sch); + qdisc_drop_reason(skb, sch, to_free, reason); return NET_XMIT_CN; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 38ec18f73de4..14ab2f4c190a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -551,25 +551,20 @@ static void dev_watchdog(struct timer_list *t) netdev_put(dev, &dev->watchdog_dev_tracker); } -void __netdev_watchdog_up(struct net_device *dev) +void netdev_watchdog_up(struct net_device *dev) { - if (dev->netdev_ops->ndo_tx_timeout) { - if (dev->watchdog_timeo <= 0) - dev->watchdog_timeo = 5*HZ; - if (!mod_timer(&dev->watchdog_timer, - round_jiffies(jiffies + dev->watchdog_timeo))) - netdev_hold(dev, &dev->watchdog_dev_tracker, - GFP_ATOMIC); - } + if (!dev->netdev_ops->ndo_tx_timeout) + return; + if (dev->watchdog_timeo <= 0) + dev->watchdog_timeo = 5*HZ; + if (!mod_timer(&dev->watchdog_timer, + round_jiffies(jiffies + dev->watchdog_timeo))) + netdev_hold(dev, &dev->watchdog_dev_tracker, + GFP_ATOMIC); } -EXPORT_SYMBOL_GPL(__netdev_watchdog_up); +EXPORT_SYMBOL_GPL(netdev_watchdog_up); -static void dev_watchdog_up(struct net_device *dev) -{ - __netdev_watchdog_up(dev); -} - -static void dev_watchdog_down(struct net_device *dev) +static void netdev_watchdog_down(struct net_device *dev) { netif_tx_lock_bh(dev); if (del_timer(&dev->watchdog_timer)) @@ -591,7 +586,7 @@ void netif_carrier_on(struct net_device *dev) atomic_inc(&dev->carrier_up_count); linkwatch_fire_event(dev); if (netif_running(dev)) - __netdev_watchdog_up(dev); + netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_carrier_on); @@ -911,8 +906,8 @@ static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch, bands[prio] = q; } - return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len, - GFP_KERNEL); + return skb_array_resize_multiple_bh(bands, PFIFO_FAST_BANDS, new_len, + GFP_KERNEL); } struct Qdisc_ops pfifo_fast_ops __read_mostly = { @@ -1267,7 +1262,7 @@ void dev_activate(struct net_device *dev) if (need_watchdog) { netif_trans_update(dev); - dev_watchdog_up(dev); + netdev_watchdog_up(dev); } } EXPORT_SYMBOL(dev_activate); @@ -1282,15 +1277,17 @@ static void qdisc_deactivate(struct Qdisc *qdisc) static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, - void *_qdisc_default) + void *_sync_needed) { - struct Qdisc *qdisc_default = _qdisc_default; + bool *sync_needed = _sync_needed; struct Qdisc *qdisc; qdisc = rtnl_dereference(dev_queue->qdisc); if (qdisc) { + if (qdisc->enqueue) + *sync_needed = true; qdisc_deactivate(qdisc); - rcu_assign_pointer(dev_queue->qdisc, qdisc_default); + rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); } } @@ -1357,24 +1354,22 @@ static bool some_qdisc_is_busy(struct net_device *dev) */ void dev_deactivate_many(struct list_head *head) { + bool sync_needed = false; struct net_device *dev; list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, - &noop_qdisc); + &sync_needed); if (dev_ingress_queue(dev)) dev_deactivate_queue(dev, dev_ingress_queue(dev), - &noop_qdisc); + &sync_needed); - dev_watchdog_down(dev); + netdev_watchdog_down(dev); } - /* Wait for outstanding qdisc-less dev_queue_xmit calls or - * outstanding qdisc enqueuing calls. - * This is avoided if all devices are in dismantle phase : - * Caller will call synchronize_net() for us - */ - synchronize_net(); + /* Wait for outstanding qdisc enqueuing calls. */ + if (sync_needed) + synchronize_net(); list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 7d2151c62c4a..ab6234b4fcd5 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -251,10 +251,10 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->stats.pdrop++; drop: - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT); congestion_drop: - qdisc_drop(skb, sch, to_free); + qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_CONGESTED); return NET_XMIT_CN; } diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index b3dcb845b327..bb1fa9aa530b 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -85,6 +85,7 @@ EXPORT_SYMBOL_GPL(pie_drop_early); static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_OVERLIMIT; struct pie_sched_data *q = qdisc_priv(sch); bool enqueue = false; @@ -93,6 +94,8 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto out; } + reason = SKB_DROP_REASON_QDISC_CONGESTED; + if (!pie_drop_early(sch, &q->params, &q->vars, sch->qstats.backlog, skb->len)) { enqueue = true; @@ -121,7 +124,7 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, out: q->stats.dropped++; q->vars.accu_prob = 0; - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_reason(skb, sch, to_free, reason); } static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 6029bc29b51e..ef8a2afed26b 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -70,6 +70,7 @@ static int red_use_nodrop(struct red_sched_data *q) static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_CONGESTED; struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; unsigned int len; @@ -107,6 +108,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, break; case RED_HARD_MARK: + reason = SKB_DROP_REASON_QDISC_OVERLIMIT; qdisc_qstats_overlimit(sch); if (red_use_harddrop(q) || !red_use_ecn(q)) { q->stats.forced_drop++; @@ -143,7 +145,7 @@ congestion_drop: if (!skb) return NET_XMIT_CN | ret; - qdisc_drop(skb, sch, to_free); + qdisc_drop_reason(skb, sch, to_free, reason); return NET_XMIT_CN; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index b717e15a3a17..d2835f1168e1 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -280,6 +280,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_OVERLIMIT; struct sfb_sched_data *q = qdisc_priv(sch); unsigned int len = qdisc_pkt_len(skb); struct Qdisc *child = q->qdisc; @@ -380,6 +381,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, } r = get_random_u16() & SFB_MAX_PROB; + reason = SKB_DROP_REASON_QDISC_CONGESTED; if (unlikely(r < p_min)) { if (unlikely(p_min > SFB_MAX_PROB / 2)) { @@ -414,7 +416,7 @@ enqueue: return ret; drop: - qdisc_drop(skb, sch, to_free); + qdisc_drop_reason(skb, sch, to_free, reason); return NET_XMIT_CN; other_drop: if (ret & __NET_XMIT_BYPASS) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index a4b8296a2fa1..65d5b59da583 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -652,6 +652,10 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, if (!p) return -ENOMEM; } + if (ctl->limit == 1) { + NL_SET_ERR_MSG_MOD(extack, "invalid limit"); + return -EINVAL; + } sch_tree_lock(sch); if (ctl->quantum) q->quantum = ctl->quantum; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index c45c192b7878..0b0794f164cf 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -137,7 +137,8 @@ static struct sctp_association *sctp_association_init( = 5 * asoc->rto_max; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; - asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ; + asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = + (unsigned long)sp->autoclose * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 8b9a1b96695e..29727ed1008e 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -427,16 +428,19 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct dst_entry *dst = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; - u8 tos = READ_ONCE(inet_sk(sk)->tos); + dscp_t dscp; if (t->dscp & SCTP_DSCP_SET_MASK) - tos = t->dscp & SCTP_DSCP_VAL_MASK; + dscp = inet_dsfield_to_dscp(t->dscp); + else + dscp = inet_sk_dscp(inet_sk(sk)); + memset(&_fl, 0x0, sizeof(_fl)); fl4->daddr = daddr->v4.sin_addr.s_addr; fl4->fl4_dport = daddr->v4.sin_port; fl4->flowi4_proto = IPPROTO_SCTP; if (asoc) { - fl4->flowi4_tos = tos & INET_DSCP_MASK; + fl4->flowi4_tos = inet_dscp_to_dsfield(dscp); fl4->flowi4_scope = ip_sock_rt_scope(asoc->base.sk); fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if; fl4->fl4_sport = htons(asoc->base.bind_addr.port); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index e5a5af343c4c..8e1e97be4df7 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -387,7 +387,8 @@ static struct ctl_table sctp_net_table[] = { static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, + sctp.sctp_hmac_alg); struct ctl_table tbl; bool changed = false; char *none = "none"; @@ -432,7 +433,7 @@ static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.rto_min); unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; @@ -460,7 +461,7 @@ static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.rto_max); unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; @@ -498,7 +499,7 @@ static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write, static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.auth_enable); struct ctl_table tbl; int new_value, ret; @@ -527,7 +528,7 @@ static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.udp_port); unsigned int min = *(unsigned int *)ctl->extra1; unsigned int max = *(unsigned int *)ctl->extra2; struct ctl_table tbl; @@ -568,7 +569,8 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, + sctp.probe_interval); struct ctl_table tbl; int ret, new_value; diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 15463062fe7b..7101a48bce54 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -40,7 +40,7 @@ static void net_shaper_lock(struct net_shaper_binding *binding) { switch (binding->type) { case NET_SHAPER_BINDING_TYPE_NETDEV: - mutex_lock(&binding->netdev->lock); + netdev_lock(binding->netdev); break; } } @@ -49,7 +49,7 @@ static void net_shaper_unlock(struct net_shaper_binding *binding) { switch (binding->type) { case NET_SHAPER_BINDING_TYPE_NETDEV: - mutex_unlock(&binding->netdev->lock); + netdev_unlock(binding->netdev); break; } } @@ -1398,7 +1398,7 @@ void net_shaper_set_real_num_tx_queues(struct net_device *dev, /* Only drivers implementing shapers support ensure * the lock is acquired in advance. */ - lockdep_assert_held(&dev->lock); + netdev_assert_locked(dev); /* Take action only when decreasing the tx queue number. */ for (i = txq; i < dev->real_num_tx_queues; ++i) { diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 9e6c69d18581..ca6984541edb 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1117,7 +1117,10 @@ static int smc_find_proposal_devices(struct smc_sock *smc, ini->check_smcrv2 = true; ini->smcrv2.saddr = smc->clcsock->sk->sk_rcv_saddr; if (!(ini->smcr_version & SMC_V2) || - smc->clcsock->sk->sk_family != AF_INET || +#if IS_ENABLED(CONFIG_IPV6) + (smc->clcsock->sk->sk_family == AF_INET6 && + !ipv6_addr_v4mapped(&smc->clcsock->sk->sk_v6_rcv_saddr)) || +#endif !smc_clc_ueid_count() || smc_find_rdma_device(smc, ini)) ini->smcr_version &= ~SMC_V2; @@ -2032,6 +2035,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc, if (pclc->hdr.typev1 == SMC_TYPE_N) return 0; pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx) + return -EPROTO; if (smc_clc_prfx_match(newclcsock, pclc_prfx)) return SMC_CLC_DECL_DIFFPREFIX; @@ -2145,6 +2150,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); + if (!pclc_smcd || !smc_v2_ext || !smcd_v2_ext) + goto not_found; mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) { @@ -2221,7 +2228,9 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, int rc = 0; /* check if ISM V1 is available */ - if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1)) + if (!(ini->smcd_version & SMC_V1) || + !smcd_indicated(ini->smc_type_v1) || + !pclc_smcd) goto not_found; ini->is_smcd = true; /* prepare ISM check */ ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid); @@ -2272,7 +2281,8 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, goto not_found; smc_v2_ext = smc_get_clc_v2_ext(pclc); - if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) + if (!smc_v2_ext || + !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) goto not_found; /* prepare RDMA check */ @@ -2731,7 +2741,7 @@ int smc_accept(struct socket *sock, struct socket *new_sock, release_sock(clcsk); } else if (!atomic_read(&smc_sk(nsk)->conn.bytes_to_rcv)) { lock_sock(nsk); - smc_rx_wait(smc_sk(nsk), &timeo, smc_rx_data_available); + smc_rx_wait(smc_sk(nsk), &timeo, 0, smc_rx_data_available); release_sock(nsk); } } @@ -2881,6 +2891,13 @@ __poll_t smc_poll(struct file *file, struct socket *sock, } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + + if (sk->sk_state != SMC_INIT) { + /* Race breaker the same way as tcp_poll(). */ + smp_mb__after_atomic(); + if (atomic_read(&smc->conn.sndbuf_space)) + mask |= EPOLLOUT | EPOLLWRNORM; + } } if (atomic_read(&smc->conn.bytes_to_rcv)) mask |= EPOLLIN | EPOLLRDNORM; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 33fa787c28eb..521f5df80e10 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -352,8 +352,11 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) struct smc_clc_msg_hdr *hdr = &pclc->hdr; struct smc_clc_v2_extension *v2_ext; - v2_ext = smc_get_clc_v2_ext(pclc); pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx || + pclc_prfx->ipv6_prefixes_cnt > SMC_CLC_MAX_V6_PREFIX) + return false; + if (hdr->version == SMC_V1) { if (hdr->typev1 == SMC_TYPE_N) return false; @@ -365,6 +368,13 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) sizeof(struct smc_clc_msg_trail)) return false; } else { + v2_ext = smc_get_clc_v2_ext(pclc); + if ((hdr->typev2 != SMC_TYPE_N && + (!v2_ext || v2_ext->hdr.eid_cnt > SMC_CLC_MAX_UEID)) || + (smcd_indicated(hdr->typev2) && + v2_ext->hdr.ism_gid_cnt > SMCD_CLC_MAX_V2_GID_ENTRIES)) + return false; + if (ntohs(hdr->length) != sizeof(*pclc) + sizeof(struct smc_clc_msg_smcd) + @@ -764,6 +774,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, SMC_CLC_RECV_BUF_LEN : datlen; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, recvlen); len = sock_recvmsg(smc->clcsock, &msg, krflags); + if (len < recvlen) { + smc->sk.sk_err = EPROTO; + reason_code = -EPROTO; + goto out; + } datlen -= len; } if (clcm->type == SMC_CLC_DECLINE) { diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 5fd6f5b8ef03..767289925410 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -336,8 +336,12 @@ struct smc_clc_msg_decline_v2 { /* clc decline message */ static inline struct smc_clc_msg_proposal_prefix * smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) { + u16 offset = ntohs(pclc->iparea_offset); + + if (offset > sizeof(struct smc_clc_msg_smcd)) + return NULL; return (struct smc_clc_msg_proposal_prefix *) - ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset)); + ((u8 *)pclc + sizeof(*pclc) + offset); } static inline bool smcr_indicated(int smc_type) @@ -376,8 +380,14 @@ static inline struct smc_clc_v2_extension * smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) { struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop); + u16 max_offset; - if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset)) + max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_smcd) - + offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); + + if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset) || + ntohs(prop_smcd->v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_v2_extension *) @@ -390,9 +400,15 @@ smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) static inline struct smc_clc_smcd_v2_extension * smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext) { + u16 max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_smcd_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_v2_extension, hdr) - + offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset); + if (!prop_v2ext) return NULL; - if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset)) + if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) || + ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_smcd_v2_extension *) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 500952c2e67b..ac07b963aede 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -795,9 +795,14 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, if (lgr->smc_version == SMC_V2) { lnk->smcibdev = ini->smcrv2.ib_dev_v2; lnk->ibport = ini->smcrv2.ib_port_v2; + lnk->wr_rx_sge_cnt = lnk->smcibdev->ibdev->attrs.max_recv_sge < 2 ? 1 : 2; + lnk->wr_rx_buflen = smc_link_shared_v2_rxbuf(lnk) ? + SMC_WR_BUF_SIZE : SMC_WR_BUF_V2_SIZE; } else { lnk->smcibdev = ini->ib_dev; lnk->ibport = ini->ib_port; + lnk->wr_rx_sge_cnt = 1; + lnk->wr_rx_buflen = SMC_WR_BUF_SIZE; } get_device(&lnk->smcibdev->ibdev->dev); atomic_inc(&lnk->smcibdev->lnk_cnt); @@ -1818,7 +1823,9 @@ void smcr_link_down_cond_sched(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); - schedule_work(&lnk->link_down_wrk); + smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */ + if (!schedule_work(&lnk->link_down_wrk)) + smcr_link_put(lnk); } } @@ -1850,11 +1857,14 @@ static void smc_link_down_work(struct work_struct *work) struct smc_link_group *lgr = link->lgr; if (list_empty(&lgr->list)) - return; + goto out; wake_up_all(&lgr->llc_msg_waiter); down_write(&lgr->llc_conf_mutex); smcr_link_down(link); up_write(&lgr->llc_conf_mutex); + +out: + smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */ } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, @@ -2145,7 +2155,7 @@ static int smcr_buf_map_link(struct smc_buf_desc *buf_desc, bool is_rmb, for_each_sg(buf_desc->sgt[lnk->link_idx].sgl, sg, nents, i) { size = min_t(int, PAGE_SIZE - offset, buf_size); sg_set_page(sg, vmalloc_to_page(buf), size, offset); - buf += size / sizeof(*buf); + buf += size; buf_size -= size; offset = 0; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 69b54ecd6503..48a1b1dcb576 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -122,10 +122,14 @@ struct smc_link { } ____cacheline_aligned_in_smp; struct completion tx_ref_comp; - struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */ + u8 *wr_rx_bufs; /* WR recv payload buffers */ struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */ struct ib_sge *wr_rx_sges; /* WR recv scatter meta data */ /* above three vectors have wr_rx_cnt elements and use the same index */ + int wr_rx_sge_cnt; /* rx sge, V1 is 1, V2 is either 2 or 1 */ + int wr_rx_buflen; /* buffer len for the first sge, len for the + * second sge is lgr shared if rx sge is 2. + */ dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ dma_addr_t wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/ u64 wr_rx_id; /* seq # of last recv WR */ @@ -506,6 +510,11 @@ static inline bool smc_link_active(struct smc_link *lnk) return lnk->state == SMC_LNK_ACTIVE; } +static inline bool smc_link_shared_v2_rxbuf(struct smc_link *lnk) +{ + return lnk->wr_rx_sge_cnt > 1; +} + static inline void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) { sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 9c563cdbea90..53828833a3f7 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -662,7 +662,6 @@ void smc_ib_destroy_queue_pair(struct smc_link *lnk) /* create a queue pair within the protection domain for a link */ int smc_ib_create_queue_pair(struct smc_link *lnk) { - int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1; struct ib_qp_init_attr qp_attr = { .event_handler = smc_ib_qp_event_handler, .qp_context = lnk, @@ -676,7 +675,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk) .max_send_wr = SMC_WR_BUF_CNT * 3, .max_recv_wr = SMC_WR_BUF_CNT * 3, .max_send_sge = SMC_IB_MAX_SEND_SGE, - .max_recv_sge = sges_per_buf, + .max_recv_sge = lnk->wr_rx_sge_cnt, .max_inline_data = 0, }, .sq_sig_type = IB_SIGNAL_REQ_WR, diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 018ce8133b02..f865c58c3aa7 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -997,13 +997,14 @@ static int smc_llc_cli_conf_link(struct smc_link *link, } static void smc_llc_save_add_link_rkeys(struct smc_link *link, - struct smc_link *link_new) + struct smc_link *link_new, + u8 *llc_msg) { struct smc_llc_msg_add_link_v2_ext *ext; struct smc_link_group *lgr = link->lgr; int max, i; - ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 + + ext = (struct smc_llc_msg_add_link_v2_ext *)(llc_msg + SMC_WR_TX_SIZE); max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); down_write(&lgr->rmbs_lock); @@ -1098,7 +1099,9 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) if (rc) goto out_clear_lnk; if (lgr->smc_version == SMC_V2) { - smc_llc_save_add_link_rkeys(link, lnk_new); + u8 *llc_msg = smc_link_shared_v2_rxbuf(link) ? + (u8 *)lgr->wr_rx_buf_v2 : (u8 *)llc; + smc_llc_save_add_link_rkeys(link, lnk_new, llc_msg); } else { rc = smc_llc_cli_rkey_exchange(link, lnk_new); if (rc) { @@ -1498,7 +1501,9 @@ int smc_llc_srv_add_link(struct smc_link *link, if (rc) goto out_err; if (lgr->smc_version == SMC_V2) { - smc_llc_save_add_link_rkeys(link, link_new); + u8 *llc_msg = smc_link_shared_v2_rxbuf(link) ? + (u8 *)lgr->wr_rx_buf_v2 : (u8 *)add_llc; + smc_llc_save_add_link_rkeys(link, link_new, llc_msg); } else { rc = smc_llc_srv_rkey_exchange(link, link_new); if (rc) @@ -1807,8 +1812,12 @@ static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr) if (lgr->smc_version == SMC_V2) { struct smc_llc_msg_delete_rkey_v2 *llcv2; - memcpy(lgr->wr_rx_buf_v2, llc, sizeof(*llc)); - llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)lgr->wr_rx_buf_v2; + if (smc_link_shared_v2_rxbuf(link)) { + memcpy(lgr->wr_rx_buf_v2, llc, sizeof(*llc)); + llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)lgr->wr_rx_buf_v2; + } else { + llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)llc; + } llcv2->num_inval_rkeys = 0; max = min_t(u8, llcv2->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index f0cbe77a80b4..e7f1134453ef 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -197,7 +197,7 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, partial[i].offset = offset; partial[i].len = size; partial[i].private = (unsigned long)priv[i]; - buf += size / sizeof(*buf); + buf += size; left -= size; offset = 0; } @@ -238,22 +238,23 @@ out: return -ENOMEM; } -static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn) +static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn, size_t peeked) { - return atomic_read(&conn->bytes_to_rcv) && + return smc_rx_data_available(conn, peeked) && !atomic_read(&conn->splice_pending); } /* blocks rcvbuf consumer until >=len bytes available or timeout or interrupted * @smc smc socket * @timeo pointer to max seconds to wait, pointer to value 0 for no timeout + * @peeked number of bytes already peeked * @fcrit add'l criterion to evaluate as function pointer * Returns: * 1 if at least 1 byte available in rcvbuf or if socket error/shutdown. * 0 otherwise (nothing in rcvbuf nor timeout, e.g. interrupted). */ -int smc_rx_wait(struct smc_sock *smc, long *timeo, - int (*fcrit)(struct smc_connection *conn)) +int smc_rx_wait(struct smc_sock *smc, long *timeo, size_t peeked, + int (*fcrit)(struct smc_connection *conn, size_t baseline)) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct smc_connection *conn = &smc->conn; @@ -262,7 +263,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, struct sock *sk = &smc->sk; int rc; - if (fcrit(conn)) + if (fcrit(conn, peeked)) return 1; sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); add_wait_queue(sk_sleep(sk), &wait); @@ -271,7 +272,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, cflags->peer_conn_abort || READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN || conn->killed || - fcrit(conn), + fcrit(conn, peeked), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); @@ -322,11 +323,11 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len, return -EAGAIN; } -static bool smc_rx_recvmsg_data_available(struct smc_sock *smc) +static bool smc_rx_recvmsg_data_available(struct smc_sock *smc, size_t peeked) { struct smc_connection *conn = &smc->conn; - if (smc_rx_data_available(conn)) + if (smc_rx_data_available(conn, peeked)) return true; else if (conn->urg_state == SMC_URG_VALID) /* we received a single urgent Byte - skip */ @@ -344,10 +345,10 @@ static bool smc_rx_recvmsg_data_available(struct smc_sock *smc) int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, struct pipe_inode_info *pipe, size_t len, int flags) { - size_t copylen, read_done = 0, read_remaining = len; + size_t copylen, read_done = 0, read_remaining = len, peeked_bytes = 0; size_t chunk_len, chunk_off, chunk_len_sum; struct smc_connection *conn = &smc->conn; - int (*func)(struct smc_connection *conn); + int (*func)(struct smc_connection *conn, size_t baseline); union smc_host_cursor cons; int readable, chunk; char *rcvbuf_base; @@ -384,14 +385,14 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, if (conn->killed) break; - if (smc_rx_recvmsg_data_available(smc)) + if (smc_rx_recvmsg_data_available(smc, peeked_bytes)) goto copy; if (sk->sk_shutdown & RCV_SHUTDOWN) { /* smc_cdc_msg_recv_action() could have run after * above smc_rx_recvmsg_data_available() */ - if (smc_rx_recvmsg_data_available(smc)) + if (smc_rx_recvmsg_data_available(smc, peeked_bytes)) goto copy; break; } @@ -425,26 +426,28 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, } } - if (!smc_rx_data_available(conn)) { - smc_rx_wait(smc, &timeo, smc_rx_data_available); + if (!smc_rx_data_available(conn, peeked_bytes)) { + smc_rx_wait(smc, &timeo, peeked_bytes, smc_rx_data_available); continue; } copy: /* initialize variables for 1st iteration of subsequent loop */ /* could be just 1 byte, even after waiting on data above */ - readable = atomic_read(&conn->bytes_to_rcv); + readable = smc_rx_data_available(conn, peeked_bytes); splbytes = atomic_read(&conn->splice_pending); if (!readable || (msg && splbytes)) { if (splbytes) func = smc_rx_data_available_and_no_splice_pend; else func = smc_rx_data_available; - smc_rx_wait(smc, &timeo, func); + smc_rx_wait(smc, &timeo, peeked_bytes, func); continue; } smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn); + if ((flags & MSG_PEEK) && peeked_bytes) + smc_curs_add(conn->rmb_desc->len, &cons, peeked_bytes); /* subsequent splice() calls pick up where previous left */ if (splbytes) smc_curs_add(conn->rmb_desc->len, &cons, splbytes); @@ -480,6 +483,8 @@ copy: } read_remaining -= chunk_len; read_done += chunk_len; + if (flags & MSG_PEEK) + peeked_bytes += chunk_len; if (chunk_len_sum == copylen) break; /* either on 1st or 2nd iteration */ diff --git a/net/smc/smc_rx.h b/net/smc/smc_rx.h index db823c97d824..994f5e42d1ba 100644 --- a/net/smc/smc_rx.h +++ b/net/smc/smc_rx.h @@ -21,11 +21,11 @@ void smc_rx_init(struct smc_sock *smc); int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, struct pipe_inode_info *pipe, size_t len, int flags); -int smc_rx_wait(struct smc_sock *smc, long *timeo, - int (*fcrit)(struct smc_connection *conn)); -static inline int smc_rx_data_available(struct smc_connection *conn) +int smc_rx_wait(struct smc_sock *smc, long *timeo, size_t peeked, + int (*fcrit)(struct smc_connection *conn, size_t baseline)); +static inline int smc_rx_data_available(struct smc_connection *conn, size_t peeked) { - return atomic_read(&conn->bytes_to_rcv); + return atomic_read(&conn->bytes_to_rcv) - peeked; } #endif /* SMC_RX_H */ diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 994c0cd4fddb..b04a21b8c511 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -439,7 +439,7 @@ static inline void smc_wr_rx_demultiplex(struct ib_wc *wc) return; /* short message */ temp_wr_id = wc->wr_id; index = do_div(temp_wr_id, link->wr_rx_cnt); - wr_rx = (struct smc_wr_rx_hdr *)&link->wr_rx_bufs[index]; + wr_rx = (struct smc_wr_rx_hdr *)(link->wr_rx_bufs + index * link->wr_rx_buflen); hash_for_each_possible(smc_wr_rx_hash, handler, list, wr_rx->type) { if (handler->type == wr_rx->type) handler->handler(wc, wr_rx); @@ -555,7 +555,6 @@ void smc_wr_remember_qp_attr(struct smc_link *lnk) static void smc_wr_init_sge(struct smc_link *lnk) { - int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1; bool send_inline = (lnk->qp_attr.cap.max_inline_data > SMC_WR_TX_SIZE); u32 i; @@ -608,13 +607,14 @@ static void smc_wr_init_sge(struct smc_link *lnk) * the larger spillover buffer, allowing easy data mapping. */ for (i = 0; i < lnk->wr_rx_cnt; i++) { - int x = i * sges_per_buf; + int x = i * lnk->wr_rx_sge_cnt; lnk->wr_rx_sges[x].addr = - lnk->wr_rx_dma_addr + i * SMC_WR_BUF_SIZE; - lnk->wr_rx_sges[x].length = SMC_WR_TX_SIZE; + lnk->wr_rx_dma_addr + i * lnk->wr_rx_buflen; + lnk->wr_rx_sges[x].length = smc_link_shared_v2_rxbuf(lnk) ? + SMC_WR_TX_SIZE : lnk->wr_rx_buflen; lnk->wr_rx_sges[x].lkey = lnk->roce_pd->local_dma_lkey; - if (lnk->lgr->smc_version == SMC_V2) { + if (lnk->lgr->smc_version == SMC_V2 && smc_link_shared_v2_rxbuf(lnk)) { lnk->wr_rx_sges[x + 1].addr = lnk->wr_rx_v2_dma_addr + SMC_WR_TX_SIZE; lnk->wr_rx_sges[x + 1].length = @@ -624,7 +624,7 @@ static void smc_wr_init_sge(struct smc_link *lnk) } lnk->wr_rx_ibs[i].next = NULL; lnk->wr_rx_ibs[i].sg_list = &lnk->wr_rx_sges[x]; - lnk->wr_rx_ibs[i].num_sge = sges_per_buf; + lnk->wr_rx_ibs[i].num_sge = lnk->wr_rx_sge_cnt; } lnk->wr_reg.wr.next = NULL; lnk->wr_reg.wr.num_sge = 0; @@ -655,7 +655,7 @@ void smc_wr_free_link(struct smc_link *lnk) if (lnk->wr_rx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, - SMC_WR_BUF_SIZE * lnk->wr_rx_cnt, + lnk->wr_rx_buflen * lnk->wr_rx_cnt, DMA_FROM_DEVICE); lnk->wr_rx_dma_addr = 0; } @@ -740,13 +740,11 @@ int smc_wr_alloc_lgr_mem(struct smc_link_group *lgr) int smc_wr_alloc_link_mem(struct smc_link *link) { - int sges_per_buf = link->lgr->smc_version == SMC_V2 ? 2 : 1; - /* allocate link related memory */ link->wr_tx_bufs = kcalloc(SMC_WR_BUF_CNT, SMC_WR_BUF_SIZE, GFP_KERNEL); if (!link->wr_tx_bufs) goto no_mem; - link->wr_rx_bufs = kcalloc(SMC_WR_BUF_CNT * 3, SMC_WR_BUF_SIZE, + link->wr_rx_bufs = kcalloc(SMC_WR_BUF_CNT * 3, link->wr_rx_buflen, GFP_KERNEL); if (!link->wr_rx_bufs) goto no_mem_wr_tx_bufs; @@ -774,7 +772,7 @@ int smc_wr_alloc_link_mem(struct smc_link *link) if (!link->wr_tx_sges) goto no_mem_wr_tx_rdma_sges; link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3, - sizeof(link->wr_rx_sges[0]) * sges_per_buf, + sizeof(link->wr_rx_sges[0]) * link->wr_rx_sge_cnt, GFP_KERNEL); if (!link->wr_rx_sges) goto no_mem_wr_tx_sges; @@ -872,7 +870,7 @@ int smc_wr_create_link(struct smc_link *lnk) smc_wr_tx_set_wr_id(&lnk->wr_tx_id, 0); lnk->wr_rx_id = 0; lnk->wr_rx_dma_addr = ib_dma_map_single( - ibdev, lnk->wr_rx_bufs, SMC_WR_BUF_SIZE * lnk->wr_rx_cnt, + ibdev, lnk->wr_rx_bufs, lnk->wr_rx_buflen * lnk->wr_rx_cnt, DMA_FROM_DEVICE); if (ib_dma_mapping_error(ibdev, lnk->wr_rx_dma_addr)) { lnk->wr_rx_dma_addr = 0; @@ -880,13 +878,15 @@ int smc_wr_create_link(struct smc_link *lnk) goto out; } if (lnk->lgr->smc_version == SMC_V2) { - lnk->wr_rx_v2_dma_addr = ib_dma_map_single(ibdev, - lnk->lgr->wr_rx_buf_v2, SMC_WR_BUF_V2_SIZE, - DMA_FROM_DEVICE); - if (ib_dma_mapping_error(ibdev, lnk->wr_rx_v2_dma_addr)) { - lnk->wr_rx_v2_dma_addr = 0; - rc = -EIO; - goto dma_unmap; + if (smc_link_shared_v2_rxbuf(lnk)) { + lnk->wr_rx_v2_dma_addr = + ib_dma_map_single(ibdev, lnk->lgr->wr_rx_buf_v2, + SMC_WR_BUF_V2_SIZE, DMA_FROM_DEVICE); + if (ib_dma_mapping_error(ibdev, lnk->wr_rx_v2_dma_addr)) { + lnk->wr_rx_v2_dma_addr = 0; + rc = -EIO; + goto dma_unmap; + } } lnk->wr_tx_v2_dma_addr = ib_dma_map_single(ibdev, lnk->lgr->wr_tx_buf_v2, SMC_WR_BUF_V2_SIZE, @@ -935,7 +935,7 @@ dma_unmap: lnk->wr_tx_v2_dma_addr = 0; } ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, - SMC_WR_BUF_SIZE * lnk->wr_rx_cnt, + lnk->wr_rx_buflen * lnk->wr_rx_cnt, DMA_FROM_DEVICE); lnk->wr_rx_dma_addr = 0; out: diff --git a/net/socket.c b/net/socket.c index 9a117248f18f..262a28b59c7f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -110,6 +110,8 @@ #include #include +#include "core/dev.h" + #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; @@ -774,34 +776,6 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(kernel_sendmsg); -/** - * kernel_sendmsg_locked - send a message through @sock (kernel-space) - * @sk: sock - * @msg: message header - * @vec: output s/g array - * @num: output s/g array length - * @size: total message data size - * - * Builds the message data with @vec and sends it through @sock. - * Returns the number of bytes sent, or an error code. - * Caller must hold @sk. - */ - -int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, - struct kvec *vec, size_t num, size_t size) -{ - struct socket *sock = sk->sk_socket; - const struct proto_ops *ops = READ_ONCE(sock->ops); - - if (!ops->sendmsg_locked) - return sock_no_sendmsg_locked(sk, msg, size); - - iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size); - - return ops->sendmsg_locked(sk, msg, msg_data_left(msg)); -} -EXPORT_SYMBOL(kernel_sendmsg_locked); - static bool skb_is_err_queue(const struct sk_buff *skb) { /* pkt_type of skbs enqueued on the error queue are set to @@ -1008,12 +982,23 @@ static void sock_recv_mark(struct msghdr *msg, struct sock *sk, } } +static void sock_recv_priority(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + if (sock_flag(sk, SOCK_RCVPRIORITY) && skb) { + __u32 priority = skb->priority; + + put_cmsg(msg, SOL_SOCKET, SO_PRIORITY, sizeof(__u32), &priority); + } +} + void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { sock_recv_timestamp(msg, sk, skb); sock_recv_drops(msg, sk, skb); sock_recv_mark(msg, sk, skb); + sock_recv_priority(msg, sk, skb); } EXPORT_SYMBOL_GPL(__sock_recv_cmsgs); diff --git a/net/sunrpc/auth_gss/Makefile b/net/sunrpc/auth_gss/Makefile index ad1736d93b76..452f67deebc6 100644 --- a/net/sunrpc/auth_gss/Makefile +++ b/net/sunrpc/auth_gss/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_SUNRPC_GSS) += auth_rpcgss.o -auth_rpcgss-y := auth_gss.o gss_generic_token.o \ +auth_rpcgss-y := auth_gss.o \ gss_mech_switch.o svcauth_gss.o \ gss_rpc_upcall.o gss_rpc_xdr.o trace.o diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c deleted file mode 100644 index 4a4082bb22ad..000000000000 --- a/net/sunrpc/auth_gss/gss_generic_token.c +++ /dev/null @@ -1,231 +0,0 @@ -/* - * linux/net/sunrpc/gss_generic_token.c - * - * Adapted from MIT Kerberos 5-1.2.1 lib/gssapi/generic/util_token.c - * - * Copyright (c) 2000 The Regents of the University of Michigan. - * All rights reserved. - * - * Andy Adamson - */ - -/* - * Copyright 1993 by OpenVision Technologies, Inc. - * - * Permission to use, copy, modify, distribute, and sell this software - * and its documentation for any purpose is hereby granted without fee, - * provided that the above copyright notice appears in all copies and - * that both that copyright notice and this permission notice appear in - * supporting documentation, and that the name of OpenVision not be used - * in advertising or publicity pertaining to distribution of the software - * without specific, written prior permission. OpenVision makes no - * representations about the suitability of this software for any - * purpose. It is provided "as is" without express or implied warranty. - * - * OPENVISION DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, - * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO - * EVENT SHALL OPENVISION BE LIABLE FOR ANY SPECIAL, INDIRECT OR - * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF - * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR - * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR - * PERFORMANCE OF THIS SOFTWARE. - */ - -#include -#include -#include -#include -#include - - -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_AUTH -#endif - - -/* TWRITE_STR from gssapiP_generic.h */ -#define TWRITE_STR(ptr, str, len) \ - memcpy((ptr), (char *) (str), (len)); \ - (ptr) += (len); - -/* XXXX this code currently makes the assumption that a mech oid will - never be longer than 127 bytes. This assumption is not inherent in - the interfaces, so the code can be fixed if the OSI namespace - balloons unexpectedly. */ - -/* Each token looks like this: - -0x60 tag for APPLICATION 0, SEQUENCE - (constructed, definite-length) - possible multiple bytes, need to parse/generate - 0x06 tag for OBJECT IDENTIFIER - compile-time constant string (assume 1 byte) - compile-time constant string - the ANY containing the application token - bytes 0,1 are the token type - bytes 2,n are the token data - -For the purposes of this abstraction, the token "header" consists of -the sequence tag and length octets, the mech OID DER encoding, and the -first two inner bytes, which indicate the token type. The token -"body" consists of everything else. - -*/ - -static int -der_length_size( int length) -{ - if (length < (1<<7)) - return 1; - else if (length < (1<<8)) - return 2; -#if (SIZEOF_INT == 2) - else - return 3; -#else - else if (length < (1<<16)) - return 3; - else if (length < (1<<24)) - return 4; - else - return 5; -#endif -} - -static void -der_write_length(unsigned char **buf, int length) -{ - if (length < (1<<7)) { - *(*buf)++ = (unsigned char) length; - } else { - *(*buf)++ = (unsigned char) (der_length_size(length)+127); -#if (SIZEOF_INT > 2) - if (length >= (1<<24)) - *(*buf)++ = (unsigned char) (length>>24); - if (length >= (1<<16)) - *(*buf)++ = (unsigned char) ((length>>16)&0xff); -#endif - if (length >= (1<<8)) - *(*buf)++ = (unsigned char) ((length>>8)&0xff); - *(*buf)++ = (unsigned char) (length&0xff); - } -} - -/* returns decoded length, or < 0 on failure. Advances buf and - decrements bufsize */ - -static int -der_read_length(unsigned char **buf, int *bufsize) -{ - unsigned char sf; - int ret; - - if (*bufsize < 1) - return -1; - sf = *(*buf)++; - (*bufsize)--; - if (sf & 0x80) { - if ((sf &= 0x7f) > ((*bufsize)-1)) - return -1; - if (sf > SIZEOF_INT) - return -1; - ret = 0; - for (; sf; sf--) { - ret = (ret<<8) + (*(*buf)++); - (*bufsize)--; - } - } else { - ret = sf; - } - - return ret; -} - -/* returns the length of a token, given the mech oid and the body size */ - -int -g_token_size(struct xdr_netobj *mech, unsigned int body_size) -{ - /* set body_size to sequence contents size */ - body_size += 2 + (int) mech->len; /* NEED overflow check */ - return 1 + der_length_size(body_size) + body_size; -} - -EXPORT_SYMBOL_GPL(g_token_size); - -/* fills in a buffer with the token header. The buffer is assumed to - be the right size. buf is advanced past the token header */ - -void -g_make_token_header(struct xdr_netobj *mech, int body_size, unsigned char **buf) -{ - *(*buf)++ = 0x60; - der_write_length(buf, 2 + mech->len + body_size); - *(*buf)++ = 0x06; - *(*buf)++ = (unsigned char) mech->len; - TWRITE_STR(*buf, mech->data, ((int) mech->len)); -} - -EXPORT_SYMBOL_GPL(g_make_token_header); - -/* - * Given a buffer containing a token, reads and verifies the token, - * leaving buf advanced past the token header, and setting body_size - * to the number of remaining bytes. Returns 0 on success, - * G_BAD_TOK_HEADER for a variety of errors, and G_WRONG_MECH if the - * mechanism in the token does not match the mech argument. buf and - * *body_size are left unmodified on error. - */ -u32 -g_verify_token_header(struct xdr_netobj *mech, int *body_size, - unsigned char **buf_in, int toksize) -{ - unsigned char *buf = *buf_in; - int seqsize; - struct xdr_netobj toid; - int ret = 0; - - if ((toksize-=1) < 0) - return G_BAD_TOK_HEADER; - if (*buf++ != 0x60) - return G_BAD_TOK_HEADER; - - if ((seqsize = der_read_length(&buf, &toksize)) < 0) - return G_BAD_TOK_HEADER; - - if (seqsize != toksize) - return G_BAD_TOK_HEADER; - - if ((toksize-=1) < 0) - return G_BAD_TOK_HEADER; - if (*buf++ != 0x06) - return G_BAD_TOK_HEADER; - - if ((toksize-=1) < 0) - return G_BAD_TOK_HEADER; - toid.len = *buf++; - - if ((toksize-=toid.len) < 0) - return G_BAD_TOK_HEADER; - toid.data = buf; - buf+=toid.len; - - if (! g_OID_equal(&toid, mech)) - ret = G_WRONG_MECH; - - /* G_WRONG_MECH is not returned immediately because it's more important - to return G_BAD_TOK_HEADER if the token header is in fact bad */ - - if ((toksize-=2) < 0) - return G_BAD_TOK_HEADER; - - if (ret) - return ret; - - *buf_in = buf; - *body_size = toksize; - - return ret; -} - -EXPORT_SYMBOL_GPL(g_verify_token_header); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index d2b02710ab07..9a27201638e2 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -442,35 +442,6 @@ encryptor(struct scatterlist *sg, void *data) return 0; } -int -gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *buf, - int offset, struct page **pages) -{ - int ret; - struct encryptor_desc desc; - SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm); - - BUG_ON((buf->len - offset) % crypto_sync_skcipher_blocksize(tfm) != 0); - - skcipher_request_set_sync_tfm(req, tfm); - skcipher_request_set_callback(req, 0, NULL, NULL); - - memset(desc.iv, 0, sizeof(desc.iv)); - desc.req = req; - desc.pos = offset; - desc.outbuf = buf; - desc.pages = pages; - desc.fragno = 0; - desc.fraglen = 0; - - sg_init_table(desc.infrags, 4); - sg_init_table(desc.outfrags, 4); - - ret = xdr_process_buf(buf, offset, buf->len - offset, encryptor, &desc); - skcipher_request_zero(req); - return ret; -} - struct decryptor_desc { u8 iv[GSS_KRB5_MAX_BLOCKSIZE]; struct skcipher_request *req; @@ -525,32 +496,6 @@ decryptor(struct scatterlist *sg, void *data) return 0; } -int -gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *buf, - int offset) -{ - int ret; - struct decryptor_desc desc; - SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm); - - /* XXXJBF: */ - BUG_ON((buf->len - offset) % crypto_sync_skcipher_blocksize(tfm) != 0); - - skcipher_request_set_sync_tfm(req, tfm); - skcipher_request_set_callback(req, 0, NULL, NULL); - - memset(desc.iv, 0, sizeof(desc.iv)); - desc.req = req; - desc.fragno = 0; - desc.fraglen = 0; - - sg_init_table(desc.frags, 4); - - ret = xdr_process_buf(buf, offset, buf->len - offset, decryptor, &desc); - skcipher_request_zero(req); - return ret; -} - /* * This function makes the assumption that it was ultimately called * from gss_wrap(). diff --git a/net/sunrpc/auth_gss/gss_krb5_internal.h b/net/sunrpc/auth_gss/gss_krb5_internal.h index 3afd4065bf3d..a47e9ec228a5 100644 --- a/net/sunrpc/auth_gss/gss_krb5_internal.h +++ b/net/sunrpc/auth_gss/gss_krb5_internal.h @@ -172,13 +172,6 @@ u32 krb5_decrypt(struct crypto_sync_skcipher *key, void *iv, void *in, int xdr_extend_head(struct xdr_buf *buf, unsigned int base, unsigned int shiftlen); -int gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, - struct xdr_buf *outbuf, int offset, - struct page **pages); - -int gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm, - struct xdr_buf *inbuf, int offset); - u32 gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages); diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index fae632da1058..c84d0cf61980 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 059f6ef1ad18..cb279eb9ac4b 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -281,21 +281,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h return rv; } -/* - * This is the generic cache management routine for all - * the authentication caches. - * It checks the currency of a cache item and will (later) - * initiate an upcall to fill it if needed. - * - * - * Returns 0 if the cache_head can be used, or cache_puts it and returns - * -EAGAIN if upcall is pending and request has been queued - * -ETIMEDOUT if upcall failed or request could not be queue or - * upcall completed but item is still invalid (implying that - * the cache item has been replaced with a newer one). - * -ENOENT if cache entry was negative - */ -int cache_check(struct cache_detail *detail, +int cache_check_rcu(struct cache_detail *detail, struct cache_head *h, struct cache_req *rqstp) { int rv; @@ -336,6 +322,31 @@ int cache_check(struct cache_detail *detail, rv = -ETIMEDOUT; } } + + return rv; +} +EXPORT_SYMBOL_GPL(cache_check_rcu); + +/* + * This is the generic cache management routine for all + * the authentication caches. + * It checks the currency of a cache item and will (later) + * initiate an upcall to fill it if needed. + * + * + * Returns 0 if the cache_head can be used, or cache_puts it and returns + * -EAGAIN if upcall is pending and request has been queued + * -ETIMEDOUT if upcall failed or request could not be queue or + * upcall completed but item is still invalid (implying that + * the cache item has been replaced with a newer one). + * -ENOENT if cache entry was negative + */ +int cache_check(struct cache_detail *detail, + struct cache_head *h, struct cache_req *rqstp) +{ + int rv; + + rv = cache_check_rcu(detail, h, rqstp); if (rv) cache_put(h, detail); return rv; @@ -1427,17 +1438,11 @@ static int c_show(struct seq_file *m, void *p) seq_printf(m, "# expiry=%lld refcnt=%d flags=%lx\n", convert_to_wallclock(cp->expiry_time), kref_read(&cp->ref), cp->flags); - if (!cache_get_rcu(cp)) - return 0; - if (cache_check(cd, cp, NULL)) - /* cache_check does a cache_put on failure */ + if (cache_check_rcu(cd, cp, NULL)) + seq_puts(m, "# "); + else if (cache_is_expired(cd, cp)) seq_puts(m, "# "); - else { - if (cache_is_expired(cd, cp)) - seq_puts(m, "# "); - cache_put(cp, cd); - } return cd->cache_show(m, cd, cp); } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 0090162ee8c3..2fe88ea79a70 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -958,12 +958,17 @@ void rpc_shutdown_client(struct rpc_clnt *clnt) trace_rpc_clnt_shutdown(clnt); + clnt->cl_shutdown = 1; while (!list_empty(&clnt->cl_tasks)) { rpc_killall_tasks(clnt); wait_event_timeout(destroy_wait, list_empty(&clnt->cl_tasks), 1*HZ); } + /* wait for tasks still in workqueue or waitqueue */ + wait_event_timeout(destroy_wait, + atomic_read(&clnt->cl_task_count) == 0, 1 * HZ); + rpc_release_client(clnt); } EXPORT_SYMBOL_GPL(rpc_shutdown_client); @@ -1139,6 +1144,7 @@ void rpc_task_release_client(struct rpc_task *task) list_del(&task->tk_task); spin_unlock(&clnt->cl_lock); task->tk_client = NULL; + atomic_dec(&clnt->cl_task_count); rpc_release_client(clnt); } @@ -1189,10 +1195,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) task->tk_flags |= RPC_TASK_TIMEOUT; if (clnt->cl_noretranstimeo) task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT; - /* Add to the client's list of all tasks */ - spin_lock(&clnt->cl_lock); - list_add_tail(&task->tk_task, &clnt->cl_tasks); - spin_unlock(&clnt->cl_lock); + atomic_inc(&clnt->cl_task_count); } static void @@ -1787,9 +1790,14 @@ call_reserveresult(struct rpc_task *task) if (status >= 0) { if (task->tk_rqstp) { task->tk_action = call_refresh; + + /* Add to the client's list of all tasks */ + spin_lock(&task->tk_client->cl_lock); + if (list_empty(&task->tk_task)) + list_add_tail(&task->tk_task, &task->tk_client->cl_tasks); + spin_unlock(&task->tk_client->cl_lock); return; } - rpc_call_rpcerror(task, -EIO); return; } @@ -1854,13 +1862,13 @@ call_refreshresult(struct rpc_task *task) fallthrough; case -EAGAIN: status = -EACCES; - fallthrough; - case -EKEYEXPIRED: if (!task->tk_cred_retry) break; task->tk_cred_retry--; trace_rpc_retry_refresh_status(task); return; + case -EKEYEXPIRED: + break; case -ENOMEM: rpc_delay(task, HZ >> 4); return; @@ -3319,8 +3327,11 @@ bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_has_addr); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -static void rpc_show_header(void) +static void rpc_show_header(struct rpc_clnt *clnt) { + printk(KERN_INFO "clnt[%pISpc] RPC tasks[%d]\n", + (struct sockaddr *)&clnt->cl_xprt->addr, + atomic_read(&clnt->cl_task_count)); printk(KERN_INFO "-pid- flgs status -client- --rqstp- " "-timeout ---ops--\n"); } @@ -3352,7 +3363,7 @@ void rpc_show_tasks(struct net *net) spin_lock(&clnt->cl_lock); list_for_each_entry(task, &clnt->cl_tasks, tk_task) { if (!header) { - rpc_show_header(); + rpc_show_header(clnt); header++; } rpc_show_task(clnt, task); diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c index a176d5a0b0ee..32417db340de 100644 --- a/net/sunrpc/debugfs.c +++ b/net/sunrpc/debugfs.c @@ -74,6 +74,9 @@ tasks_stop(struct seq_file *f, void *v) { struct rpc_clnt *clnt = f->private; spin_unlock(&clnt->cl_lock); + seq_printf(f, "clnt[%pISpc] RPC tasks[%d]\n", + (struct sockaddr *)&clnt->cl_xprt->addr, + atomic_read(&clnt->cl_task_count)); } static const struct seq_operations tasks_seq_operations = { @@ -179,6 +182,18 @@ xprt_info_show(struct seq_file *f, void *v) seq_printf(f, "addr: %s\n", xprt->address_strings[RPC_DISPLAY_ADDR]); seq_printf(f, "port: %s\n", xprt->address_strings[RPC_DISPLAY_PORT]); seq_printf(f, "state: 0x%lx\n", xprt->state); + seq_printf(f, "netns: %u\n", xprt->xprt_net->ns.inum); + + if (xprt->ops->get_srcaddr) { + int ret, buflen; + char buf[INET6_ADDRSTRLEN]; + + buflen = ARRAY_SIZE(buf); + ret = xprt->ops->get_srcaddr(xprt, buf, buflen); + if (ret < 0) + ret = sprintf(buf, ""); + seq_printf(f, "saddr: %.*s\n", ret, buf); + } return 0; } diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 7ce3721c06ca..eadc00410ebc 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -630,7 +630,7 @@ static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry) static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, const char *name) { - struct qstr q = QSTR_INIT(name, strlen(name)); + struct qstr q = QSTR(name); struct dentry *dentry = d_hash_and_lookup(parent, &q); if (!dentry) { dentry = d_alloc(parent, &q); @@ -1190,8 +1190,7 @@ static const struct rpc_filelist files[] = { struct dentry *rpc_d_lookup_sb(const struct super_block *sb, const unsigned char *dir_name) { - struct qstr dir = QSTR_INIT(dir_name, strlen(dir_name)); - return d_hash_and_lookup(sb->s_root, &dir); + return d_hash_and_lookup(sb->s_root, &QSTR(dir_name)); } EXPORT_SYMBOL_GPL(rpc_d_lookup_sb); @@ -1300,11 +1299,9 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) struct dentry *gssd_dentry; struct dentry *clnt_dentry = NULL; struct dentry *pipe_dentry = NULL; - struct qstr q = QSTR_INIT(files[RPCAUTH_gssd].name, - strlen(files[RPCAUTH_gssd].name)); /* We should never get this far if "gssd" doesn't exist */ - gssd_dentry = d_hash_and_lookup(root, &q); + gssd_dentry = d_hash_and_lookup(root, &QSTR(files[RPCAUTH_gssd].name)); if (!gssd_dentry) return ERR_PTR(-ENOENT); @@ -1314,9 +1311,8 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) goto out; } - q.name = gssd_dummy_clnt_dir[0].name; - q.len = strlen(gssd_dummy_clnt_dir[0].name); - clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); + clnt_dentry = d_hash_and_lookup(gssd_dentry, + &QSTR(gssd_dummy_clnt_dir[0].name)); if (!clnt_dentry) { __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(-ENOENT); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 79879b7d39cb..e7f9c295d13c 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -651,8 +651,8 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node) if (pages > RPCSVC_MAXPAGES) pages = RPCSVC_MAXPAGES; - ret = alloc_pages_bulk_array_node(GFP_KERNEL, node, pages, - rqstp->rq_pages); + ret = alloc_pages_bulk_node(GFP_KERNEL, node, pages, + rqstp->rq_pages); return ret == pages; } diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 43c57124de52..ae25405d8bd2 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -606,7 +606,8 @@ int svc_port_is_privileged(struct sockaddr *sin) } /* - * Make sure that we don't have too many active connections. If we have, + * Make sure that we don't have too many connections that have not yet + * demonstrated that they have access to the NFS server. If we have, * something must be dropped. It's not clear what will happen if we allow * "too many" connections, but when dealing with network-facing software, * we have to code defensively. Here we do that by imposing hard limits. @@ -618,34 +619,26 @@ int svc_port_is_privileged(struct sockaddr *sin) * The only somewhat efficient mechanism would be if drop old * connections from the same IP first. But right now we don't even * record the client IP in svc_sock. - * - * single-threaded services that expect a lot of clients will probably - * need to set sv_maxconn to override the default value which is based - * on the number of threads */ static void svc_check_conn_limits(struct svc_serv *serv) { - unsigned int limit = serv->sv_maxconn ? serv->sv_maxconn : - (serv->sv_nrthreads+3) * 20; - - if (serv->sv_tmpcnt > limit) { - struct svc_xprt *xprt = NULL; + if (serv->sv_tmpcnt > XPT_MAX_TMP_CONN) { + struct svc_xprt *xprt = NULL, *xprti; spin_lock_bh(&serv->sv_lock); if (!list_empty(&serv->sv_tempsocks)) { - /* Try to help the admin */ - net_notice_ratelimited("%s: too many open connections, consider increasing the %s\n", - serv->sv_name, serv->sv_maxconn ? - "max number of connections" : - "number of threads"); /* * Always select the oldest connection. It's not fair, - * but so is life + * but nor is life. */ - xprt = list_entry(serv->sv_tempsocks.prev, - struct svc_xprt, - xpt_list); - set_bit(XPT_CLOSE, &xprt->xpt_flags); - svc_xprt_get(xprt); + list_for_each_entry_reverse(xprti, &serv->sv_tempsocks, + xpt_list) { + if (!test_bit(XPT_PEER_VALID, &xprti->xpt_flags)) { + xprt = xprti; + set_bit(XPT_CLOSE, &xprt->xpt_flags); + svc_xprt_get(xprt); + break; + } + } } spin_unlock_bh(&serv->sv_lock); @@ -671,8 +664,7 @@ static bool svc_alloc_arg(struct svc_rqst *rqstp) } for (filled = 0; filled < pages; filled = ret) { - ret = alloc_pages_bulk_array(GFP_KERNEL, pages, - rqstp->rq_pages); + ret = alloc_pages_bulk(GFP_KERNEL, pages, rqstp->rq_pages); if (ret > filled) /* Made progress, don't sleep yet */ continue; @@ -1039,7 +1031,8 @@ static void svc_delete_xprt(struct svc_xprt *xprt) spin_lock_bh(&serv->sv_lock); list_del_init(&xprt->xpt_list); - if (test_bit(XPT_TEMP, &xprt->xpt_flags)) + if (test_bit(XPT_TEMP, &xprt->xpt_flags) && + !test_bit(XPT_PEER_VALID, &xprt->xpt_flags)) serv->sv_tmpcnt--; spin_unlock_bh(&serv->sv_lock); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 95397677673b..cb3bd12f5818 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1083,9 +1083,6 @@ static void svc_tcp_fragment_received(struct svc_sock *svsk) /* If we have more data, signal svc_xprt_enqueue() to try again */ svsk->sk_tcplen = 0; svsk->sk_marker = xdr_zero; - - smp_wmb(); - tcp_set_rcvlowat(svsk->sk_sk, 1); } /** @@ -1175,17 +1172,10 @@ err_incomplete: goto err_delete; if (len == want) svc_tcp_fragment_received(svsk); - else { - /* Avoid more ->sk_data_ready() calls until the rest - * of the message has arrived. This reduces service - * thread wake-ups on large incoming messages. */ - tcp_set_rcvlowat(svsk->sk_sk, - svc_sock_reclen(svsk) - svsk->sk_tcplen); - + else trace_svcsock_tcp_recv_short(&svsk->sk_xprt, svc_sock_reclen(svsk), svsk->sk_tcplen - sizeof(rpc_fraghdr)); - } goto err_noclose; error: if (len != -EAGAIN) diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 62e07c330a66..4e003cb516fe 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1097,6 +1097,12 @@ out_overflow: * Checks that we have enough buffer space to encode 'nbytes' more * bytes of data. If so, update the total xdr_buf length, and * adjust the length of the current kvec. + * + * The returned pointer is valid only until the next call to + * xdr_reserve_space() or xdr_commit_encode() on @xdr. The current + * implementation of this API guarantees that space reserved for a + * four-byte data item remains valid until @xdr is destroyed, but + * that might not always be true in the future. */ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes) { diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c index 720d3ba742ec..7e98d4dd9f10 100644 --- a/net/sunrpc/xprtmultipath.c +++ b/net/sunrpc/xprtmultipath.c @@ -602,23 +602,6 @@ struct rpc_xprt *xprt_iter_get_helper(struct rpc_xprt_iter *xpi, return ret; } -/** - * xprt_iter_get_xprt - Returns the rpc_xprt pointed to by the cursor - * @xpi: pointer to rpc_xprt_iter - * - * Returns a reference to the struct rpc_xprt that is currently - * pointed to by the cursor. - */ -struct rpc_xprt *xprt_iter_get_xprt(struct rpc_xprt_iter *xpi) -{ - struct rpc_xprt *xprt; - - rcu_read_lock(); - xprt = xprt_iter_get_helper(xpi, xprt_iter_ops(xpi)->xpi_xprt); - rcu_read_unlock(); - return xprt; -} - /** * xprt_iter_get_next - Returns the next rpc_xprt following the cursor * @xpi: pointer to rpc_xprt_iter diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 43c3f1c971b8..c524421ec652 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -2293,8 +2293,8 @@ static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr) keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME))); /* Verify the supplied size values */ - if (unlikely(size != keylen + sizeof(struct tipc_aead_key) || - keylen > TIPC_AEAD_KEY_SIZE_MAX)) { + if (unlikely(keylen > TIPC_AEAD_KEY_SIZE_MAX || + size != keylen + sizeof(struct tipc_aead_key))) { pr_debug("%s: invalid MSG_CRYPTO key size\n", rx->name); goto exit; } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index d1180370fdf4..e74940eab3a4 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -949,8 +949,8 @@ void tipc_nametbl_stop(struct net *net) } spin_unlock_bh(&tn->nametbl_lock); - synchronize_net(); - kfree(nt); + /* TODO: clear tn->nametbl, implement proper RCU rules ? */ + kfree_rcu(nt, rcu); } static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 3bcd9ef8cee3..7ff6eeebaae6 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -90,6 +90,7 @@ struct publication { /** * struct name_table - table containing all existing port name publications + * @rcu: RCU callback head used for deferred freeing * @services: name sequence hash lists * @node_scope: all local publications with node scope * - used by name_distr during re-init of name table @@ -102,6 +103,7 @@ struct publication { * @snd_nxt: next sequence number to be used */ struct name_table { + struct rcu_head rcu; struct hlist_head services[TIPC_NAMETBL_SIZE]; struct list_head node_scope; struct list_head cluster_scope; diff --git a/net/tls/tls.h b/net/tls/tls.h index e5e47452308a..774859b63f0d 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -145,7 +145,8 @@ void tls_err_abort(struct sock *sk, int err); int init_prot_info(struct tls_prot_info *prot, const struct tls_crypto_info *crypto_info, const struct tls_cipher_desc *cipher_desc); -int tls_set_sw_offload(struct sock *sk, int tx); +int tls_set_sw_offload(struct sock *sk, int tx, + struct tls_crypto_info *new_crypto_info); void tls_update_rx_zc_capable(struct tls_context *tls_ctx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index dc063c2c7950..e50b6e71df13 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1227,7 +1227,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) context->resync_nh_reset = 1; ctx->priv_ctx_rx = context; - rc = tls_set_sw_offload(sk, 0); + rc = tls_set_sw_offload(sk, 0, NULL); if (rc) goto release_ctx; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 6b4b9f2749a6..99ca4465f702 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -423,9 +423,10 @@ static __poll_t tls_sk_poll(struct file *file, struct socket *sock, ctx = tls_sw_ctx_rx(tls_ctx); psock = sk_psock_get(sk); - if (skb_queue_empty_lockless(&ctx->rx_list) && - !tls_strp_msg_ready(ctx) && - sk_psock_queue_empty(psock)) + if ((skb_queue_empty_lockless(&ctx->rx_list) && + !tls_strp_msg_ready(ctx) && + sk_psock_queue_empty(psock)) || + READ_ONCE(ctx->key_update_pending)) mask &= ~(EPOLLIN | EPOLLRDNORM); if (psock) @@ -612,11 +613,13 @@ static int validate_crypto_info(const struct tls_crypto_info *crypto_info, static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, unsigned int optlen, int tx) { - struct tls_crypto_info *crypto_info; - struct tls_crypto_info *alt_crypto_info; + struct tls_crypto_info *crypto_info, *alt_crypto_info; + struct tls_crypto_info *old_crypto_info = NULL; struct tls_context *ctx = tls_get_ctx(sk); const struct tls_cipher_desc *cipher_desc; union tls_crypto_context *crypto_ctx; + union tls_crypto_context tmp = {}; + bool update = false; int rc = 0; int conf; @@ -633,9 +636,21 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, crypto_info = &crypto_ctx->info; - /* Currently we don't support set crypto info more than one time */ - if (TLS_CRYPTO_INFO_READY(crypto_info)) - return -EBUSY; + if (TLS_CRYPTO_INFO_READY(crypto_info)) { + /* Currently we only support setting crypto info more + * than one time for TLS 1.3 + */ + if (crypto_info->version != TLS_1_3_VERSION) { + TLS_INC_STATS(sock_net(sk), tx ? LINUX_MIB_TLSTXREKEYERROR + : LINUX_MIB_TLSRXREKEYERROR); + return -EBUSY; + } + + update = true; + old_crypto_info = crypto_info; + crypto_info = &tmp.info; + crypto_ctx = &tmp; + } rc = copy_from_sockptr(crypto_info, optval, sizeof(*crypto_info)); if (rc) { @@ -643,7 +658,14 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, goto err_crypto_info; } - rc = validate_crypto_info(crypto_info, alt_crypto_info); + if (update) { + /* Ensure that TLS version and ciphers are not modified */ + if (crypto_info->version != old_crypto_info->version || + crypto_info->cipher_type != old_crypto_info->cipher_type) + rc = -EINVAL; + } else { + rc = validate_crypto_info(crypto_info, alt_crypto_info); + } if (rc) goto err_crypto_info; @@ -673,11 +695,17 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXDEVICE); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXDEVICE); } else { - rc = tls_set_sw_offload(sk, 1); + rc = tls_set_sw_offload(sk, 1, + update ? crypto_info : NULL); if (rc) goto err_crypto_info; - TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXSW); - TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXSW); + + if (update) { + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXREKEYOK); + } else { + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXSW); + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXSW); + } conf = TLS_SW; } } else { @@ -687,14 +715,21 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICE); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXDEVICE); } else { - rc = tls_set_sw_offload(sk, 0); + rc = tls_set_sw_offload(sk, 0, + update ? crypto_info : NULL); if (rc) goto err_crypto_info; - TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXSW); - TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXSW); + + if (update) { + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXREKEYOK); + } else { + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXSW); + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXSW); + } conf = TLS_SW; } - tls_sw_strparser_arm(sk, ctx); + if (!update) + tls_sw_strparser_arm(sk, ctx); } if (tx) @@ -702,6 +737,10 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, else ctx->rx_conf = conf; update_sk_prot(sk, ctx); + + if (update) + return 0; + if (tx) { ctx->sk_write_space = sk->sk_write_space; sk->sk_write_space = tls_write_space; @@ -713,6 +752,10 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, return 0; err_crypto_info: + if (update) { + TLS_INC_STATS(sock_net(sk), tx ? LINUX_MIB_TLSTXREKEYERROR + : LINUX_MIB_TLSRXREKEYERROR); + } memzero_explicit(crypto_ctx, sizeof(*crypto_ctx)); return rc; } diff --git a/net/tls/tls_proc.c b/net/tls/tls_proc.c index 68982728f620..367666aa07b8 100644 --- a/net/tls/tls_proc.c +++ b/net/tls/tls_proc.c @@ -22,6 +22,11 @@ static const struct snmp_mib tls_mib_list[] = { SNMP_MIB_ITEM("TlsRxDeviceResync", LINUX_MIB_TLSRXDEVICERESYNC), SNMP_MIB_ITEM("TlsDecryptRetry", LINUX_MIB_TLSDECRYPTRETRY), SNMP_MIB_ITEM("TlsRxNoPadViolation", LINUX_MIB_TLSRXNOPADVIOL), + SNMP_MIB_ITEM("TlsRxRekeyOk", LINUX_MIB_TLSRXREKEYOK), + SNMP_MIB_ITEM("TlsRxRekeyError", LINUX_MIB_TLSRXREKEYERROR), + SNMP_MIB_ITEM("TlsTxRekeyOk", LINUX_MIB_TLSTXREKEYOK), + SNMP_MIB_ITEM("TlsTxRekeyError", LINUX_MIB_TLSTXREKEYERROR), + SNMP_MIB_ITEM("TlsRxRekeyReceived", LINUX_MIB_TLSRXREKEYRECEIVED), SNMP_MIB_SENTINEL }; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index bbf26cc4f6ee..914d4e1516a3 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -458,7 +458,7 @@ int tls_tx_records(struct sock *sk, int flags) tx_err: if (rc < 0 && rc != -EAGAIN) - tls_err_abort(sk, -EBADMSG); + tls_err_abort(sk, rc); return rc; } @@ -1314,6 +1314,10 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, int ret = 0; long timeo; + /* a rekey is pending, let userspace deal with it */ + if (unlikely(ctx->key_update_pending)) + return -EKEYEXPIRED; + timeo = sock_rcvtimeo(sk, nonblock); while (!tls_strp_msg_ready(ctx)) { @@ -1720,6 +1724,36 @@ tls_decrypt_device(struct sock *sk, struct msghdr *msg, return 1; } +static int tls_check_pending_rekey(struct sock *sk, struct tls_context *ctx, + struct sk_buff *skb) +{ + const struct strp_msg *rxm = strp_msg(skb); + const struct tls_msg *tlm = tls_msg(skb); + char hs_type; + int err; + + if (likely(tlm->control != TLS_RECORD_TYPE_HANDSHAKE)) + return 0; + + if (rxm->full_len < 1) + return 0; + + err = skb_copy_bits(skb, rxm->offset, &hs_type, 1); + if (err < 0) { + DEBUG_NET_WARN_ON_ONCE(1); + return err; + } + + if (hs_type == TLS_HANDSHAKE_KEYUPDATE) { + struct tls_sw_context_rx *rx_ctx = ctx->priv_ctx_rx; + + WRITE_ONCE(rx_ctx->key_update_pending, true); + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXREKEYRECEIVED); + } + + return 0; +} + static int tls_rx_one_record(struct sock *sk, struct msghdr *msg, struct tls_decrypt_arg *darg) { @@ -1739,7 +1773,7 @@ static int tls_rx_one_record(struct sock *sk, struct msghdr *msg, rxm->full_len -= prot->overhead_size; tls_advance_record_sn(sk, prot, &tls_ctx->rx); - return 0; + return tls_check_pending_rekey(sk, tls_ctx, darg->skb); } int decrypt_skb(struct sock *sk, struct scatterlist *sgout) @@ -2684,12 +2718,22 @@ int init_prot_info(struct tls_prot_info *prot, return 0; } -int tls_set_sw_offload(struct sock *sk, int tx) +static void tls_finish_key_update(struct sock *sk, struct tls_context *tls_ctx) { + struct tls_sw_context_rx *ctx = tls_ctx->priv_ctx_rx; + + WRITE_ONCE(ctx->key_update_pending, false); + /* wake-up pre-existing poll() */ + ctx->saved_data_ready(sk); +} + +int tls_set_sw_offload(struct sock *sk, int tx, + struct tls_crypto_info *new_crypto_info) +{ + struct tls_crypto_info *crypto_info, *src_crypto_info; struct tls_sw_context_tx *sw_ctx_tx = NULL; struct tls_sw_context_rx *sw_ctx_rx = NULL; const struct tls_cipher_desc *cipher_desc; - struct tls_crypto_info *crypto_info; char *iv, *rec_seq, *key, *salt; struct cipher_context *cctx; struct tls_prot_info *prot; @@ -2701,44 +2745,47 @@ int tls_set_sw_offload(struct sock *sk, int tx) ctx = tls_get_ctx(sk); prot = &ctx->prot_info; - if (tx) { - ctx->priv_ctx_tx = init_ctx_tx(ctx, sk); - if (!ctx->priv_ctx_tx) - return -ENOMEM; + /* new_crypto_info != NULL means rekey */ + if (!new_crypto_info) { + if (tx) { + ctx->priv_ctx_tx = init_ctx_tx(ctx, sk); + if (!ctx->priv_ctx_tx) + return -ENOMEM; + } else { + ctx->priv_ctx_rx = init_ctx_rx(ctx); + if (!ctx->priv_ctx_rx) + return -ENOMEM; + } + } + if (tx) { sw_ctx_tx = ctx->priv_ctx_tx; crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; } else { - ctx->priv_ctx_rx = init_ctx_rx(ctx); - if (!ctx->priv_ctx_rx) - return -ENOMEM; - sw_ctx_rx = ctx->priv_ctx_rx; crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; aead = &sw_ctx_rx->aead_recv; } - cipher_desc = get_cipher_desc(crypto_info->cipher_type); + src_crypto_info = new_crypto_info ?: crypto_info; + + cipher_desc = get_cipher_desc(src_crypto_info->cipher_type); if (!cipher_desc) { rc = -EINVAL; goto free_priv; } - rc = init_prot_info(prot, crypto_info, cipher_desc); + rc = init_prot_info(prot, src_crypto_info, cipher_desc); if (rc) goto free_priv; - iv = crypto_info_iv(crypto_info, cipher_desc); - key = crypto_info_key(crypto_info, cipher_desc); - salt = crypto_info_salt(crypto_info, cipher_desc); - rec_seq = crypto_info_rec_seq(crypto_info, cipher_desc); - - memcpy(cctx->iv, salt, cipher_desc->salt); - memcpy(cctx->iv + cipher_desc->salt, iv, cipher_desc->iv); - memcpy(cctx->rec_seq, rec_seq, cipher_desc->rec_seq); + iv = crypto_info_iv(src_crypto_info, cipher_desc); + key = crypto_info_key(src_crypto_info, cipher_desc); + salt = crypto_info_salt(src_crypto_info, cipher_desc); + rec_seq = crypto_info_rec_seq(src_crypto_info, cipher_desc); if (!*aead) { *aead = crypto_alloc_aead(cipher_desc->cipher_name, 0, 0); @@ -2751,20 +2798,30 @@ int tls_set_sw_offload(struct sock *sk, int tx) ctx->push_pending_record = tls_sw_push_pending_record; + /* setkey is the last operation that could fail during a + * rekey. if it succeeds, we can start modifying the + * context. + */ rc = crypto_aead_setkey(*aead, key, cipher_desc->key); - if (rc) - goto free_aead; + if (rc) { + if (new_crypto_info) + goto out; + else + goto free_aead; + } - rc = crypto_aead_setauthsize(*aead, prot->tag_size); - if (rc) - goto free_aead; + if (!new_crypto_info) { + rc = crypto_aead_setauthsize(*aead, prot->tag_size); + if (rc) + goto free_aead; + } - if (sw_ctx_rx) { + if (!tx && !new_crypto_info) { tfm = crypto_aead_tfm(sw_ctx_rx->aead_recv); tls_update_rx_zc_capable(ctx); sw_ctx_rx->async_capable = - crypto_info->version != TLS_1_3_VERSION && + src_crypto_info->version != TLS_1_3_VERSION && !!(tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC); rc = tls_strp_init(&sw_ctx_rx->strp, sk); @@ -2772,18 +2829,33 @@ int tls_set_sw_offload(struct sock *sk, int tx) goto free_aead; } + memcpy(cctx->iv, salt, cipher_desc->salt); + memcpy(cctx->iv + cipher_desc->salt, iv, cipher_desc->iv); + memcpy(cctx->rec_seq, rec_seq, cipher_desc->rec_seq); + + if (new_crypto_info) { + unsafe_memcpy(crypto_info, new_crypto_info, + cipher_desc->crypto_info, + /* size was checked in do_tls_setsockopt_conf */); + memzero_explicit(new_crypto_info, cipher_desc->crypto_info); + if (!tx) + tls_finish_key_update(sk, ctx); + } + goto out; free_aead: crypto_free_aead(*aead); *aead = NULL; free_priv: - if (tx) { - kfree(ctx->priv_ctx_tx); - ctx->priv_ctx_tx = NULL; - } else { - kfree(ctx->priv_ctx_rx); - ctx->priv_ctx_rx = NULL; + if (!new_crypto_info) { + if (tx) { + kfree(ctx->priv_ctx_tx); + ctx->priv_ctx_tx = NULL; + } else { + kfree(ctx->priv_ctx_rx); + ctx->priv_ctx_rx = NULL; + } } out: return rc; diff --git a/net/unix/Kconfig b/net/unix/Kconfig index 8b5d04210d7c..6f1783c1659b 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -17,9 +17,11 @@ config UNIX Say Y unless you know what you are doing. config AF_UNIX_OOB - bool + bool "UNIX: out-of-bound messages" depends on UNIX default y + help + Support for MSG_OOB in UNIX domain sockets. If unsure, say Y. config UNIX_DIAG tristate "UNIX: socket monitoring interface" diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6b1762300443..34945de1fb1f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -286,14 +286,9 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb) } #endif /* CONFIG_SECURITY_NETWORK */ -static inline int unix_our_peer(struct sock *sk, struct sock *osk) -{ - return unix_peer(osk) == sk; -} - static inline int unix_may_send(struct sock *sk, struct sock *osk) { - return unix_peer(osk) == NULL || unix_our_peer(sk, osk); + return !unix_peer(osk) || unix_peer(osk) == sk; } static inline int unix_recvq_full_lockless(const struct sock *sk) @@ -627,7 +622,9 @@ static void unix_write_space(struct sock *sk) static void unix_dgram_disconnected(struct sock *sk, struct sock *other) { if (!skb_queue_empty(&sk->sk_receive_queue)) { - skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge_reason(&sk->sk_receive_queue, + SKB_DROP_REASON_UNIX_DISCONNECT); + wake_up_interruptible_all(&unix_sk(sk)->peer_wait); /* If one link of bidirectional dgram pipe is disconnected, @@ -645,7 +642,7 @@ static void unix_sock_destructor(struct sock *sk) { struct unix_sock *u = unix_sk(sk); - skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge_reason(&sk->sk_receive_queue, SKB_DROP_REASON_SOCKET_CLOSE); DEBUG_NET_WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk)); @@ -720,8 +717,8 @@ static void unix_release_sock(struct sock *sk, int embrion) if (state == TCP_LISTEN) unix_release_sock(skb->sk, 1); - /* passed fds are erased in the kfree_skb hook */ - kfree_skb(skb); + /* passed fds are erased in the kfree_skb hook */ + kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE); } if (path.dentry) @@ -1563,32 +1560,30 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); /* First of all allocate resources. - If we will make it after state is locked, - we will have to recheck all again in any case. + * If we will make it after state is locked, + * we will have to recheck all again in any case. */ /* create new sock for complete connection */ newsk = unix_create1(net, NULL, 0, sock->type); if (IS_ERR(newsk)) { err = PTR_ERR(newsk); - newsk = NULL; goto out; } - err = -ENOMEM; - /* Allocate skb for sending to listening sock */ skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL); - if (skb == NULL) - goto out; + if (!skb) { + err = -ENOMEM; + goto out_free_sk; + } restart: /* Find listening sock. */ other = unix_find_other(net, sunaddr, addr_len, sk->sk_type); if (IS_ERR(other)) { err = PTR_ERR(other); - other = NULL; - goto out; + goto out_free_skb; } unix_state_lock(other); @@ -1600,23 +1595,25 @@ restart: goto restart; } - err = -ECONNREFUSED; - if (other->sk_state != TCP_LISTEN) - goto out_unlock; - if (other->sk_shutdown & RCV_SHUTDOWN) + if (other->sk_state != TCP_LISTEN || + other->sk_shutdown & RCV_SHUTDOWN) { + err = -ECONNREFUSED; goto out_unlock; + } if (unix_recvq_full_lockless(other)) { - err = -EAGAIN; - if (!timeo) + if (!timeo) { + err = -EAGAIN; goto out_unlock; + } timeo = unix_wait_for_peer(other, timeo); + sock_put(other); err = sock_intr_errno(timeo); if (signal_pending(current)) - goto out; - sock_put(other); + goto out_free_skb; + goto restart; } @@ -1701,15 +1698,13 @@ restart: return 0; out_unlock: - if (other) - unix_state_unlock(other); - + unix_state_unlock(other); + sock_put(other); +out_free_skb: + consume_skb(skb); +out_free_sk: + unix_release_sock(newsk, 0); out: - kfree_skb(skb); - if (newsk) - unix_release_sock(newsk, 0); - if (other) - sock_put(other); return err; } @@ -1964,7 +1959,6 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { - DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name); struct sock *sk = sock->sk, *other = NULL; struct unix_sock *u = unix_sk(sk); struct scm_cookie scm; @@ -1980,12 +1974,13 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, wait_for_unix_gc(scm.fp); - err = -EOPNOTSUPP; - if (msg->msg_flags&MSG_OOB) + if (msg->msg_flags & MSG_OOB) { + err = -EOPNOTSUPP; goto out; + } if (msg->msg_namelen) { - err = unix_validate_addr(sunaddr, msg->msg_namelen); + err = unix_validate_addr(msg->msg_name, msg->msg_namelen); if (err) goto out; @@ -1995,12 +1990,6 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, NULL); if (err) goto out; - } else { - sunaddr = NULL; - err = -ENOTCONN; - other = unix_peer_get(sk); - if (!other) - goto out; } if ((test_bit(SOCK_PASSCRED, &sock->flags) || @@ -2011,9 +2000,10 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, goto out; } - err = -EMSGSIZE; - if (len > READ_ONCE(sk->sk_sndbuf) - 32) + if (len > READ_ONCE(sk->sk_sndbuf) - 32) { + err = -EMSGSIZE; goto out; + } if (len > SKB_MAX_ALLOC) { data_len = min_t(size_t, @@ -2027,7 +2017,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, skb = sock_alloc_send_pskb(sk, len - data_len, data_len, msg->msg_flags & MSG_DONTWAIT, &err, PAGE_ALLOC_COSTLY_ORDER); - if (skb == NULL) + if (!skb) goto out; err = unix_scm_to_skb(&scm, skb, true); @@ -2043,17 +2033,18 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); -restart: - if (!other) { - err = -ECONNRESET; - if (sunaddr == NULL) - goto out_free; - - other = unix_find_other(sock_net(sk), sunaddr, msg->msg_namelen, - sk->sk_type); + if (msg->msg_namelen) { +lookup: + other = unix_find_other(sock_net(sk), msg->msg_name, + msg->msg_namelen, sk->sk_type); if (IS_ERR(other)) { err = PTR_ERR(other); - other = NULL; + goto out_free; + } + } else { + other = unix_peer_get(sk); + if (!other) { + err = -ENOTCONN; goto out_free; } } @@ -2061,36 +2052,37 @@ restart: if (sk_filter(other, skb) < 0) { /* Toss the packet but do not return any error to the sender */ err = len; - goto out_free; + goto out_sock_put; } +restart: sk_locked = 0; unix_state_lock(other); restart_locked: - err = -EPERM; - if (!unix_may_send(sk, other)) + + if (!unix_may_send(sk, other)) { + err = -EPERM; goto out_unlock; + } if (unlikely(sock_flag(other, SOCK_DEAD))) { - /* - * Check with 1003.1g - what should - * datagram error - */ + /* Check with 1003.1g - what should datagram error */ + unix_state_unlock(other); - sock_put(other); - if (!sk_locked) - unix_state_lock(sk); - - err = 0; if (sk->sk_type == SOCK_SEQPACKET) { /* We are here only when racing with unix_release_sock() * is clearing @other. Never change state to TCP_CLOSE * unlike SOCK_DGRAM wants. */ - unix_state_unlock(sk); err = -EPIPE; - } else if (unix_peer(sk) == other) { + goto out_sock_put; + } + + if (!sk_locked) + unix_state_lock(sk); + + if (unix_peer(sk) == other) { unix_peer(sk) = NULL; unix_dgram_peer_wake_disconnect_wakeup(sk, other); @@ -2100,19 +2092,23 @@ restart_locked: unix_dgram_disconnected(sk, other); sock_put(other); err = -ECONNREFUSED; - } else { - unix_state_unlock(sk); + goto out_sock_put; } - other = NULL; - if (err) - goto out_free; - goto restart; + unix_state_unlock(sk); + + if (!msg->msg_namelen) { + err = -ECONNRESET; + goto out_sock_put; + } + + goto lookup; } - err = -EPIPE; - if (other->sk_shutdown & RCV_SHUTDOWN) + if (other->sk_shutdown & RCV_SHUTDOWN) { + err = -EPIPE; goto out_unlock; + } if (sk->sk_type != SOCK_SEQPACKET) { err = security_unix_may_send(sk->sk_socket, other->sk_socket); @@ -2132,7 +2128,7 @@ restart_locked: err = sock_intr_errno(timeo); if (signal_pending(current)) - goto out_free; + goto out_sock_put; goto restart; } @@ -2173,11 +2169,11 @@ out_unlock: if (sk_locked) unix_state_unlock(sk); unix_state_unlock(other); +out_sock_put: + sock_put(other); out_free: - kfree_skb(skb); + consume_skb(skb); out: - if (other) - sock_put(other); scm_destroy(&scm); return err; } @@ -2193,7 +2189,7 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other { struct unix_sock *ousk = unix_sk(other); struct sk_buff *skb; - int err = 0; + int err; skb = sock_alloc_send_skb(sock->sk, 1, msg->msg_flags & MSG_DONTWAIT, &err); @@ -2201,25 +2197,22 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other return err; err = unix_scm_to_skb(scm, skb, !fds_sent); - if (err < 0) { - kfree_skb(skb); - return err; - } + if (err < 0) + goto out; + skb_put(skb, 1); err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, 1); - if (err) { - kfree_skb(skb); - return err; - } + if (err) + goto out; unix_state_lock(other); if (sock_flag(other, SOCK_DEAD) || (other->sk_shutdown & RCV_SHUTDOWN)) { unix_state_unlock(other); - kfree_skb(skb); - return -EPIPE; + err = -EPIPE; + goto out; } maybe_add_creds(skb, sock, other); @@ -2234,6 +2227,9 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other unix_state_unlock(other); other->sk_data_ready(other); + return 0; +out: + consume_skb(skb); return err; } #endif @@ -2242,13 +2238,11 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; + struct sk_buff *skb = NULL; struct sock *other = NULL; - int err, size; - struct sk_buff *skb; - int sent = 0; struct scm_cookie scm; bool fds_sent = false; - int data_len; + int err, sent = 0; err = scm_send(sock, msg, &scm, false); if (err < 0) @@ -2256,8 +2250,8 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, wait_for_unix_gc(scm.fp); - err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) { + err = -EOPNOTSUPP; #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (len) len--; @@ -2270,17 +2264,19 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, err = READ_ONCE(sk->sk_state) == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out_err; } else { - err = -ENOTCONN; other = unix_peer(sk); - if (!other) + if (!other) { + err = -ENOTCONN; goto out_err; + } } if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) - goto pipe_err; + goto out_pipe; while (sent < len) { - size = len - sent; + int size = len - sent; + int data_len; if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { skb = sock_alloc_send_pskb(sk, 0, 0, @@ -2306,20 +2302,18 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, /* Only send the fds in the first buffer */ err = unix_scm_to_skb(&scm, skb, !fds_sent); - if (err < 0) { - kfree_skb(skb); - goto out_err; - } + if (err < 0) + goto out_free; + fds_sent = true; if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { skb->ip_summed = CHECKSUM_UNNECESSARY; err = skb_splice_from_iter(skb, &msg->msg_iter, size, sk->sk_allocation); - if (err < 0) { - kfree_skb(skb); - goto out_err; - } + if (err < 0) + goto out_free; + size = err; refcount_add(size, &sk->sk_wmem_alloc); } else { @@ -2327,17 +2321,15 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, skb->data_len = data_len; skb->len = size; err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); - if (err) { - kfree_skb(skb); - goto out_err; - } + if (err) + goto out_free; } unix_state_lock(other); if (sock_flag(other, SOCK_DEAD) || (other->sk_shutdown & RCV_SHUTDOWN)) - goto pipe_err_free; + goto out_pipe_unlock; maybe_add_creds(skb, sock, other); scm_stat_add(other, skb); @@ -2360,13 +2352,14 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, return sent; -pipe_err_free: +out_pipe_unlock: unix_state_unlock(other); - kfree_skb(skb); -pipe_err: - if (sent == 0 && !(msg->msg_flags&MSG_NOSIGNAL)) +out_pipe: + if (!sent && !(msg->msg_flags & MSG_NOSIGNAL)) send_sig(SIGPIPE, current, 0); err = -EPIPE; +out_free: + consume_skb(skb); out_err: scm_destroy(&scm); return sent ? : err; @@ -2699,7 +2692,7 @@ unlock: spin_unlock(&sk->sk_receive_queue.lock); consume_skb(read_skb); - kfree_skb(unread_skb); + kfree_skb_reason(unread_skb, SKB_DROP_REASON_UNIX_SKIP_OOB); return skb; } @@ -2728,7 +2721,7 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) if (sock_flag(sk, SOCK_DEAD)) { unix_state_unlock(sk); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE); return -ECONNRESET; } @@ -2742,7 +2735,7 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) unix_state_unlock(sk); if (drop) { - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_UNIX_SKIP_OOB); return -EAGAIN; } } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 0068e758be4d..9848b7b78701 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -573,7 +573,7 @@ static void __unix_gc(struct work_struct *work) UNIXCB(skb).fp->dead = true; } - __skb_queue_purge(&hitlist); + __skb_queue_purge_reason(&hitlist, SKB_DROP_REASON_SOCKET_CLOSE); skip_gc: WRITE_ONCE(gc_in_progress, false); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 5cf8109f672a..075695173648 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -337,7 +337,10 @@ EXPORT_SYMBOL_GPL(vsock_find_connected_socket); void vsock_remove_sock(struct vsock_sock *vsk) { - vsock_remove_bound(vsk); + /* Transport reassignment must not remove the binding. */ + if (sock_flag(sk_vsock(vsk), SOCK_DEAD)) + vsock_remove_bound(vsk); + vsock_remove_connected(vsk); } EXPORT_SYMBOL_GPL(vsock_remove_sock); @@ -491,6 +494,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); + + /* transport's release() and destruct() can touch some socket + * state, since we are reassigning the socket to a new transport + * during vsock_connect(), let's reset these fields to have a + * clean state. + */ + sock_reset_flag(sk, SOCK_DONE); + sk->sk_state = TCP_CLOSE; + vsk->peer_shutdown = 0; } /* We increase the module refcnt to prevent the transport unloading @@ -812,12 +824,13 @@ static void __vsock_release(struct sock *sk, int level) */ lock_sock_nested(sk, level); + sock_orphan(sk); + if (vsk->transport) vsk->transport->release(vsk); else if (sock_type_connectible(sk->sk_type)) vsock_remove_sock(vsk); - sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; skb_queue_purge(&sk->sk_receive_queue); @@ -870,6 +883,9 @@ EXPORT_SYMBOL_GPL(vsock_create_connected); s64 vsock_stream_has_data(struct vsock_sock *vsk) { + if (WARN_ON(!vsk->transport)) + return 0; + return vsk->transport->stream_has_data(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_data); @@ -878,6 +894,9 @@ s64 vsock_connectible_has_data(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); + if (WARN_ON(!vsk->transport)) + return 0; + if (sk->sk_type == SOCK_SEQPACKET) return vsk->transport->seqpacket_has_data(vsk); else @@ -887,6 +906,9 @@ EXPORT_SYMBOL_GPL(vsock_connectible_has_data); s64 vsock_stream_has_space(struct vsock_sock *vsk) { + if (WARN_ON(!vsk->transport)) + return 0; + return vsk->transport->stream_has_space(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_space); @@ -1501,6 +1523,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, if (err < 0) goto out; + /* sk_err might have been set as a result of an earlier + * (failed) connect attempt. + */ + sk->sk_err = 0; + /* Mark sock as connecting and set the error code to in * progress in case this is a non-blocking connect. */ diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 56c232cf5b0f..31342ab502b4 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -13,12 +13,12 @@ #include #include #include -#include +#include /* Older (VMBUS version 'VERSION_WIN10' or before) Windows hosts have some * stricter requirements on the hv_sock ring buffer size of six 4K pages. - * hyperv-tlfs defines HV_HYP_PAGE_SIZE as 4K. Newer hosts don't have this - * limitation; but, keep the defaults the same for compat. + * HV_HYP_PAGE_SIZE is defined as 4K. Newer hosts don't have this limitation; + * but, keep the defaults the same for compat. */ #define RINGBUFFER_HVS_RCV_SIZE (HV_HYP_PAGE_SIZE * 6) #define RINGBUFFER_HVS_SND_SIZE (HV_HYP_PAGE_SIZE * 6) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 9acc13ab3f82..7f7de6d88096 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -26,6 +26,9 @@ /* Threshold for detecting small packets to copy */ #define GOOD_COPY_LEN 128 +static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, + bool cancel_timeout); + static const struct virtio_transport * virtio_transport_get_ops(struct vsock_sock *vsk) { @@ -1109,6 +1112,8 @@ void virtio_transport_destruct(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; + virtio_transport_cancel_close_work(vsk, true); + kfree(vvs); vsk->trans = NULL; } @@ -1204,6 +1209,22 @@ static void virtio_transport_wait_close(struct sock *sk, long timeout) } } +static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, + bool cancel_timeout) +{ + struct sock *sk = sk_vsock(vsk); + + if (vsk->close_work_scheduled && + (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) { + vsk->close_work_scheduled = false; + + virtio_transport_remove_sock(vsk); + + /* Release refcnt obtained when we scheduled the timeout */ + sock_put(sk); + } +} + static void virtio_transport_do_close(struct vsock_sock *vsk, bool cancel_timeout) { @@ -1215,15 +1236,7 @@ static void virtio_transport_do_close(struct vsock_sock *vsk, sk->sk_state = TCP_CLOSING; sk->sk_state_change(sk); - if (vsk->close_work_scheduled && - (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) { - vsk->close_work_scheduled = false; - - virtio_transport_remove_sock(vsk); - - /* Release refcnt obtained when we scheduled the timeout */ - sock_put(sk); - } + virtio_transport_cancel_close_work(vsk, cancel_timeout); } static void virtio_transport_close_timeout(struct work_struct *work) @@ -1628,8 +1641,11 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, lock_sock(sk); - /* Check if sk has been closed before lock_sock */ - if (sock_flag(sk, SOCK_DONE)) { + /* Check if sk has been closed or assigned to another transport before + * lock_sock (note: listener sockets are not assigned to any transport) + */ + if (sock_flag(sk, SOCK_DONE) || + (sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) { (void)virtio_transport_reset_no_sock(t, skb); release_sock(sk); sock_put(sk); diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index 4aa6e74ec295..f201d9eca1df 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -77,6 +77,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct sk_psock *psock; + struct vsock_sock *vsk; int copied; psock = sk_psock_get(sk); @@ -84,6 +85,13 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, return __vsock_recvmsg(sk, msg, len, flags); lock_sock(sk); + vsk = vsock_sk(sk); + + if (!vsk->transport) { + copied = -ENODEV; + goto out; + } + if (vsock_has_data(sk, psock) && sk_psock_queue_empty(psock)) { release_sock(sk); sk_psock_put(sk, psock); @@ -108,6 +116,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, copied = sk_msg_recvmsg(sk, psock, msg, len, flags); } +out: release_sock(sk); sk_psock_put(sk, psock); diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 40b6375a5de4..9f918b77b40e 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -55,6 +55,56 @@ void cfg80211_chandef_create(struct cfg80211_chan_def *chandef, } EXPORT_SYMBOL(cfg80211_chandef_create); +static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c) +{ + return nl80211_chan_width_to_mhz(c->width); +} + +static u32 cfg80211_get_start_freq(const struct cfg80211_chan_def *chandef, + u32 cf) +{ + u32 start_freq, center_freq, bandwidth; + + center_freq = MHZ_TO_KHZ((cf == 1) ? + chandef->center_freq1 : chandef->center_freq2); + bandwidth = MHZ_TO_KHZ(cfg80211_chandef_get_width(chandef)); + + if (bandwidth <= MHZ_TO_KHZ(20)) + start_freq = center_freq; + else + start_freq = center_freq - bandwidth / 2 + MHZ_TO_KHZ(10); + + return start_freq; +} + +static u32 cfg80211_get_end_freq(const struct cfg80211_chan_def *chandef, + u32 cf) +{ + u32 end_freq, center_freq, bandwidth; + + center_freq = MHZ_TO_KHZ((cf == 1) ? + chandef->center_freq1 : chandef->center_freq2); + bandwidth = MHZ_TO_KHZ(cfg80211_chandef_get_width(chandef)); + + if (bandwidth <= MHZ_TO_KHZ(20)) + end_freq = center_freq; + else + end_freq = center_freq + bandwidth / 2 - MHZ_TO_KHZ(10); + + return end_freq; +} + +#define for_each_subchan(chandef, freq, cf) \ + for (u32 punctured = chandef->punctured, \ + cf = 1, freq = cfg80211_get_start_freq(chandef, cf); \ + freq <= cfg80211_get_end_freq(chandef, cf); \ + freq += MHZ_TO_KHZ(20), \ + ((cf == 1 && chandef->center_freq2 != 0 && \ + freq > cfg80211_get_end_freq(chandef, cf)) ? \ + (cf++, freq = cfg80211_get_start_freq(chandef, cf), \ + punctured = 0) : (punctured >>= 1))) \ + if (!(punctured & 1)) + struct cfg80211_per_bw_puncturing_values { u8 len; const u16 *valid_values; @@ -258,11 +308,6 @@ int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width) } EXPORT_SYMBOL(nl80211_chan_width_to_mhz); -static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c) -{ - return nl80211_chan_width_to_mhz(c->width); -} - static bool cfg80211_valid_center_freq(u32 center, enum nl80211_chan_width width) { @@ -582,29 +627,11 @@ cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, } EXPORT_SYMBOL(cfg80211_chandef_compatible); -static void cfg80211_set_chans_dfs_state(struct wiphy *wiphy, u32 center_freq, - u32 bandwidth, - enum nl80211_dfs_state dfs_state) -{ - struct ieee80211_channel *c; - u32 freq; - - for (freq = center_freq - bandwidth/2 + 10; - freq <= center_freq + bandwidth/2 - 10; - freq += 20) { - c = ieee80211_get_channel(wiphy, freq); - if (!c || !(c->flags & IEEE80211_CHAN_RADAR)) - continue; - - c->dfs_state = dfs_state; - c->dfs_state_entered = jiffies; - } -} - void cfg80211_set_dfs_state(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, enum nl80211_dfs_state dfs_state) { + struct ieee80211_channel *c; int width; if (WARN_ON(!cfg80211_chandef_valid(chandef))) @@ -614,41 +641,14 @@ void cfg80211_set_dfs_state(struct wiphy *wiphy, if (width < 0) return; - cfg80211_set_chans_dfs_state(wiphy, chandef->center_freq1, - width, dfs_state); + for_each_subchan(chandef, freq, cf) { + c = ieee80211_get_channel_khz(wiphy, freq); + if (!c || !(c->flags & IEEE80211_CHAN_RADAR)) + continue; - if (!chandef->center_freq2) - return; - cfg80211_set_chans_dfs_state(wiphy, chandef->center_freq2, - width, dfs_state); -} - -static u32 cfg80211_get_start_freq(u32 center_freq, - u32 bandwidth) -{ - u32 start_freq; - - bandwidth = MHZ_TO_KHZ(bandwidth); - if (bandwidth <= MHZ_TO_KHZ(20)) - start_freq = center_freq; - else - start_freq = center_freq - bandwidth / 2 + MHZ_TO_KHZ(10); - - return start_freq; -} - -static u32 cfg80211_get_end_freq(u32 center_freq, - u32 bandwidth) -{ - u32 end_freq; - - bandwidth = MHZ_TO_KHZ(bandwidth); - if (bandwidth <= MHZ_TO_KHZ(20)) - end_freq = center_freq; - else - end_freq = center_freq + bandwidth / 2 - MHZ_TO_KHZ(10); - - return end_freq; + c->dfs_state = dfs_state; + c->dfs_state_entered = jiffies; + } } static bool @@ -725,17 +725,12 @@ static bool cfg80211_dfs_permissive_chan(struct wiphy *wiphy, } static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy, - u32 center_freq, - u32 bandwidth, - enum nl80211_iftype iftype) + const struct cfg80211_chan_def *chandef, + enum nl80211_iftype iftype) { struct ieee80211_channel *c; - u32 freq, start_freq, end_freq; - start_freq = cfg80211_get_start_freq(center_freq, bandwidth); - end_freq = cfg80211_get_end_freq(center_freq, bandwidth); - - for (freq = start_freq; freq <= end_freq; freq += MHZ_TO_KHZ(20)) { + for_each_subchan(chandef, freq, cf) { c = ieee80211_get_channel_khz(wiphy, freq); if (!c) return -EINVAL; @@ -768,25 +763,9 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, if (width < 0) return -EINVAL; - ret = cfg80211_get_chans_dfs_required(wiphy, - ieee80211_chandef_to_khz(chandef), - width, iftype); - if (ret < 0) - return ret; - else if (ret > 0) - return BIT(chandef->width); - - if (!chandef->center_freq2) - return 0; - - ret = cfg80211_get_chans_dfs_required(wiphy, - MHZ_TO_KHZ(chandef->center_freq2), - width, iftype); - if (ret < 0) - return ret; - else if (ret > 0) - return BIT(chandef->width); + ret = cfg80211_get_chans_dfs_required(wiphy, chandef, iftype); + return (ret > 0) ? BIT(chandef->width) : ret; break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_OCB: @@ -806,48 +785,11 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, } EXPORT_SYMBOL(cfg80211_chandef_dfs_required); -static int cfg80211_get_chans_dfs_usable(struct wiphy *wiphy, - u32 center_freq, - u32 bandwidth) -{ - struct ieee80211_channel *c; - u32 freq, start_freq, end_freq; - int count = 0; - - start_freq = cfg80211_get_start_freq(center_freq, bandwidth); - end_freq = cfg80211_get_end_freq(center_freq, bandwidth); - - /* - * Check entire range of channels for the bandwidth. - * Check all channels are DFS channels (DFS_USABLE or - * DFS_AVAILABLE). Return number of usable channels - * (require CAC). Allow DFS and non-DFS channel mix. - */ - for (freq = start_freq; freq <= end_freq; freq += MHZ_TO_KHZ(20)) { - c = ieee80211_get_channel_khz(wiphy, freq); - if (!c) - return -EINVAL; - - if (c->flags & IEEE80211_CHAN_DISABLED) - return -EINVAL; - - if (c->flags & IEEE80211_CHAN_RADAR) { - if (c->dfs_state == NL80211_DFS_UNAVAILABLE) - return -EINVAL; - - if (c->dfs_state == NL80211_DFS_USABLE) - count++; - } - } - - return count; -} - bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef) { - int width; - int r1, r2 = 0; + struct ieee80211_channel *c; + int width, count = 0; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -856,28 +798,30 @@ bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy, if (width < 0) return false; - r1 = cfg80211_get_chans_dfs_usable(wiphy, - MHZ_TO_KHZ(chandef->center_freq1), - width); - - if (r1 < 0) - return false; - - switch (chandef->width) { - case NL80211_CHAN_WIDTH_80P80: - WARN_ON(!chandef->center_freq2); - r2 = cfg80211_get_chans_dfs_usable(wiphy, - MHZ_TO_KHZ(chandef->center_freq2), - width); - if (r2 < 0) + /* + * Check entire range of channels for the bandwidth. + * Check all channels are DFS channels (DFS_USABLE or + * DFS_AVAILABLE). Return number of usable channels + * (require CAC). Allow DFS and non-DFS channel mix. + */ + for_each_subchan(chandef, freq, cf) { + c = ieee80211_get_channel_khz(wiphy, freq); + if (!c) return false; - break; - default: - WARN_ON(chandef->center_freq2); - break; + + if (c->flags & IEEE80211_CHAN_DISABLED) + return false; + + if (c->flags & IEEE80211_CHAN_RADAR) { + if (c->dfs_state == NL80211_DFS_UNAVAILABLE) + return false; + + if (c->dfs_state == NL80211_DFS_USABLE) + count++; + } } - return (r1 + r2 > 0); + return count > 0; } EXPORT_SYMBOL(cfg80211_chandef_dfs_usable); @@ -1039,10 +983,10 @@ bool cfg80211_any_wiphy_oper_chan(struct wiphy *wiphy, if (!reg_dfs_domain_same(wiphy, &rdev->wiphy)) continue; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + found = cfg80211_is_wiphy_oper_chan(&rdev->wiphy, chan) || cfg80211_offchan_chain_is_active(rdev, chan); - wiphy_unlock(&rdev->wiphy); if (found) return true; @@ -1051,26 +995,29 @@ bool cfg80211_any_wiphy_oper_chan(struct wiphy *wiphy, return false; } -static bool cfg80211_get_chans_dfs_available(struct wiphy *wiphy, - u32 center_freq, - u32 bandwidth) +static bool cfg80211_chandef_dfs_available(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef) { struct ieee80211_channel *c; - u32 freq, start_freq, end_freq; + int width; bool dfs_offload; + if (WARN_ON(!cfg80211_chandef_valid(chandef))) + return false; + + width = cfg80211_chandef_get_width(chandef); + if (width < 0) + return false; + dfs_offload = wiphy_ext_feature_isset(wiphy, NL80211_EXT_FEATURE_DFS_OFFLOAD); - start_freq = cfg80211_get_start_freq(center_freq, bandwidth); - end_freq = cfg80211_get_end_freq(center_freq, bandwidth); - /* * Check entire range of channels for the bandwidth. * If any channel in between is disabled or has not * had gone through CAC return false */ - for (freq = start_freq; freq <= end_freq; freq += MHZ_TO_KHZ(20)) { + for_each_subchan(chandef, freq, cf) { c = ieee80211_get_channel_khz(wiphy, freq); if (!c) return false; @@ -1087,75 +1034,11 @@ static bool cfg80211_get_chans_dfs_available(struct wiphy *wiphy, return true; } -static bool cfg80211_chandef_dfs_available(struct wiphy *wiphy, - const struct cfg80211_chan_def *chandef) -{ - int width; - int r; - - if (WARN_ON(!cfg80211_chandef_valid(chandef))) - return false; - - width = cfg80211_chandef_get_width(chandef); - if (width < 0) - return false; - - r = cfg80211_get_chans_dfs_available(wiphy, - MHZ_TO_KHZ(chandef->center_freq1), - width); - - /* If any of channels unavailable for cf1 just return */ - if (!r) - return r; - - switch (chandef->width) { - case NL80211_CHAN_WIDTH_80P80: - WARN_ON(!chandef->center_freq2); - r = cfg80211_get_chans_dfs_available(wiphy, - MHZ_TO_KHZ(chandef->center_freq2), - width); - break; - default: - WARN_ON(chandef->center_freq2); - break; - } - - return r; -} - -static unsigned int cfg80211_get_chans_dfs_cac_time(struct wiphy *wiphy, - u32 center_freq, - u32 bandwidth) -{ - struct ieee80211_channel *c; - u32 start_freq, end_freq, freq; - unsigned int dfs_cac_ms = 0; - - start_freq = cfg80211_get_start_freq(center_freq, bandwidth); - end_freq = cfg80211_get_end_freq(center_freq, bandwidth); - - for (freq = start_freq; freq <= end_freq; freq += MHZ_TO_KHZ(20)) { - c = ieee80211_get_channel_khz(wiphy, freq); - if (!c) - return 0; - - if (c->flags & IEEE80211_CHAN_DISABLED) - return 0; - - if (!(c->flags & IEEE80211_CHAN_RADAR)) - continue; - - if (c->dfs_cac_ms > dfs_cac_ms) - dfs_cac_ms = c->dfs_cac_ms; - } - - return dfs_cac_ms; -} - unsigned int cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef) { + struct ieee80211_channel *c; int width; unsigned int t1 = 0, t2 = 0; @@ -1166,45 +1049,39 @@ cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy, if (width < 0) return 0; - t1 = cfg80211_get_chans_dfs_cac_time(wiphy, - MHZ_TO_KHZ(chandef->center_freq1), - width); + for_each_subchan(chandef, freq, cf) { + c = ieee80211_get_channel_khz(wiphy, freq); + if (!c || (c->flags & IEEE80211_CHAN_DISABLED)) { + if (cf == 1) + t1 = INT_MAX; + else + t2 = INT_MAX; + continue; + } - if (!chandef->center_freq2) + if (!(c->flags & IEEE80211_CHAN_RADAR)) + continue; + + if (cf == 1 && c->dfs_cac_ms > t1) + t1 = c->dfs_cac_ms; + + if (cf == 2 && c->dfs_cac_ms > t2) + t2 = c->dfs_cac_ms; + } + + if (t1 == INT_MAX && t2 == INT_MAX) + return 0; + + if (t1 == INT_MAX) + return t2; + + if (t2 == INT_MAX) return t1; - t2 = cfg80211_get_chans_dfs_cac_time(wiphy, - MHZ_TO_KHZ(chandef->center_freq2), - width); - return max(t1, t2); } EXPORT_SYMBOL(cfg80211_chandef_dfs_cac_time); -static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, - u32 center_freq, u32 bandwidth, - u32 prohibited_flags, - u32 permitting_flags) -{ - struct ieee80211_channel *c; - u32 freq, start_freq, end_freq; - - start_freq = cfg80211_get_start_freq(center_freq, bandwidth); - end_freq = cfg80211_get_end_freq(center_freq, bandwidth); - - for (freq = start_freq; freq <= end_freq; freq += MHZ_TO_KHZ(20)) { - c = ieee80211_get_channel_khz(wiphy, freq); - if (!c) - return false; - if (c->flags & permitting_flags) - continue; - if (c->flags & prohibited_flags) - return false; - } - - return true; -} - /* check if the operating channels are valid and supported */ static bool cfg80211_edmg_usable(struct wiphy *wiphy, u8 edmg_channels, enum ieee80211_edmg_bw_config edmg_bw_config, @@ -1270,6 +1147,7 @@ bool _cfg80211_chandef_usable(struct wiphy *wiphy, bool ext_nss_cap, support_80_80 = false, support_320 = false; const struct ieee80211_sband_iftype_data *iftd; struct ieee80211_supported_band *sband; + struct ieee80211_channel *c; int i; if (WARN_ON(!cfg80211_chandef_valid(chandef))) @@ -1420,19 +1298,17 @@ bool _cfg80211_chandef_usable(struct wiphy *wiphy, if (width < 20) prohibited_flags |= IEEE80211_CHAN_NO_OFDM; + for_each_subchan(chandef, freq, cf) { + c = ieee80211_get_channel_khz(wiphy, freq); + if (!c) + return false; + if (c->flags & permitting_flags) + continue; + if (c->flags & prohibited_flags) + return false; + } - if (!cfg80211_secondary_chans_ok(wiphy, - ieee80211_chandef_to_khz(chandef), - width, prohibited_flags, - permitting_flags)) - return false; - - if (!chandef->center_freq2) - return true; - return cfg80211_secondary_chans_ok(wiphy, - MHZ_TO_KHZ(chandef->center_freq2), - width, prohibited_flags, - permitting_flags); + return true; } bool cfg80211_chandef_usable(struct wiphy *wiphy, diff --git a/net/wireless/core.c b/net/wireless/core.c index afbdc549fb4a..12b780de8779 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -143,10 +143,7 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, if (result) return result; - if (!IS_ERR_OR_NULL(rdev->wiphy.debugfsdir)) - debugfs_rename(rdev->wiphy.debugfsdir->d_parent, - rdev->wiphy.debugfsdir, - rdev->wiphy.debugfsdir->d_parent, newname); + debugfs_change_name(rdev->wiphy.debugfsdir, "%s", newname); nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); @@ -191,7 +188,8 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, return err; } - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->netdev) continue; @@ -212,7 +210,6 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, continue; nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); } - wiphy_unlock(&rdev->wiphy); return 0; } @@ -221,9 +218,9 @@ static void cfg80211_rfkill_poll(struct rfkill *rfkill, void *data) { struct cfg80211_registered_device *rdev = data; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + rdev_rfkill_poll(rdev); - wiphy_unlock(&rdev->wiphy); } void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, @@ -283,7 +280,7 @@ void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy) /* otherwise, check iftype */ - wiphy_lock(wiphy); + guard(wiphy)(wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_P2P_DEVICE: @@ -295,8 +292,6 @@ void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy) default: break; } - - wiphy_unlock(wiphy); } } EXPORT_SYMBOL_GPL(cfg80211_shutdown_all_interfaces); @@ -331,9 +326,9 @@ static void cfg80211_event_work(struct work_struct *work) rdev = container_of(work, struct cfg80211_registered_device, event_work); - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + cfg80211_process_rdev_events(rdev); - wiphy_unlock(&rdev->wiphy); } void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev) @@ -347,10 +342,10 @@ void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev) if (wdev->netdev) dev_close(wdev->netdev); - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + cfg80211_leave(rdev, wdev); cfg80211_remove_virtual_intf(rdev, wdev); - wiphy_unlock(&rdev->wiphy); } } } @@ -423,9 +418,9 @@ static void cfg80211_wiphy_work(struct work_struct *work) trace_wiphy_work_worker_start(&rdev->wiphy); - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); if (rdev->suspended) - goto out; + return; spin_lock_irq(&rdev->wiphy_work_lock); wk = list_first_entry_or_null(&rdev->wiphy_work_list, @@ -441,8 +436,6 @@ static void cfg80211_wiphy_work(struct work_struct *work) } else { spin_unlock_irq(&rdev->wiphy_work_lock); } -out: - wiphy_unlock(&rdev->wiphy); } /* exported functions */ @@ -1526,9 +1519,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, break; case NETDEV_REGISTER: if (!wdev->registered) { - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + cfg80211_register_wdev(rdev, wdev); - wiphy_unlock(&rdev->wiphy); } break; case NETDEV_UNREGISTER: @@ -1537,16 +1530,16 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, * so check wdev->registered. */ if (wdev->registered && !wdev->registering) { - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + _cfg80211_unregister_wdev(wdev, false); - wiphy_unlock(&rdev->wiphy); } break; case NETDEV_GOING_DOWN: - wiphy_lock(&rdev->wiphy); - cfg80211_leave(rdev, wdev); - cfg80211_remove_links(wdev); - wiphy_unlock(&rdev->wiphy); + scoped_guard(wiphy, &rdev->wiphy) { + cfg80211_leave(rdev, wdev); + cfg80211_remove_links(wdev); + } /* since we just did cfg80211_leave() nothing to do there */ cancel_work_sync(&wdev->disconnect_wk); cancel_work_sync(&wdev->pmsr_free_wk); diff --git a/net/wireless/core.h b/net/wireless/core.h index 4c45f994a8c0..826299f3d781 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -567,6 +567,10 @@ int cfg80211_remove_virtual_intf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask); +int cfg80211_assoc_ml_reconf(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_assoc_link *links, + u16 rem_links); /** * struct cfg80211_colocated_ap - colocated AP information * diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index a5eb92d93074..e10f2b3b4b7f 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -352,6 +352,13 @@ cfg80211_mlme_check_mlo_compat(const struct ieee80211_multi_link_elem *mle_a, return -EINVAL; } + if (ieee80211_mle_get_ext_mld_capa_op((const u8 *)mle_a) != + ieee80211_mle_get_ext_mld_capa_op((const u8 *)mle_b)) { + NL_SET_ERR_MSG(extack, + "extended link MLD capabilities/ops mismatch"); + return -EINVAL; + } + return 0; } @@ -627,10 +634,10 @@ void cfg80211_mgmt_registrations_update_wk(struct work_struct *wk) rdev = container_of(wk, struct cfg80211_registered_device, mgmt_registrations_update_wk); - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) cfg80211_mgmt_registrations_update(wdev); - wiphy_unlock(&rdev->wiphy); } int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, @@ -1193,10 +1200,10 @@ cfg80211_background_cac_event(struct cfg80211_registered_device *rdev, const struct cfg80211_chan_def *chandef, enum nl80211_radar_event event) { - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + __cfg80211_background_cac_event(rdev, rdev->background_radar_wdev, chandef, event); - wiphy_unlock(&rdev->wiphy); } void cfg80211_background_cac_done_wk(struct work_struct *work) @@ -1287,3 +1294,80 @@ void cfg80211_stop_background_radar_detection(struct wireless_dev *wdev) &rdev->background_radar_chandef, NL80211_RADAR_CAC_ABORTED); } + +int cfg80211_assoc_ml_reconf(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_assoc_link *links, + u16 rem_links) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + lockdep_assert_wiphy(wdev->wiphy); + + err = rdev_assoc_ml_reconf(rdev, dev, links, rem_links); + if (!err) { + int link_id; + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; + link_id++) { + if (!links[link_id].bss) + continue; + + cfg80211_ref_bss(&rdev->wiphy, links[link_id].bss); + cfg80211_hold_bss(bss_from_pub(links[link_id].bss)); + } + } + + return err; +} + +void cfg80211_mlo_reconf_add_done(struct net_device *dev, + struct cfg80211_mlo_reconf_done_data *data) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + int link_id; + + lockdep_assert_wiphy(wiphy); + + trace_cfg80211_mlo_reconf_add_done(dev, data->added_links, + data->buf, data->len); + + if (WARN_ON(!wdev->valid_links)) + return; + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) + return; + + /* validate that a BSS is given for each added link */ + for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { + struct cfg80211_bss *bss = data->links[link_id].bss; + + if (!(data->added_links & BIT(link_id))) + continue; + + if (WARN_ON(!bss)) + return; + } + + for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { + struct cfg80211_bss *bss = data->links[link_id].bss; + + if (!bss) + continue; + + if (data->added_links & BIT(link_id)) { + wdev->links[link_id].client.current_bss = + bss_from_pub(bss); + } else { + cfg80211_unhold_bss(bss_from_pub(bss)); + cfg80211_put_bss(wiphy, bss); + } + } + + wdev->valid_links |= data->added_links; + nl80211_mlo_reconf_add_done(dev, data); +} +EXPORT_SYMBOL(cfg80211_mlo_reconf_add_done); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index dd84fc54fb9b..d7d3da0f6833 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -294,6 +294,21 @@ static int validate_he_capa(const struct nlattr *attr, return 0; } +static int validate_supported_selectors(const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + const u8 *supported_selectors = nla_data(attr); + u8 supported_selectors_len = nla_len(attr); + + /* The top bit must not be set as it is not part of the selector */ + for (int i = 0; i < supported_selectors_len; i++) { + if (supported_selectors[i] & 0x80) + return -EINVAL; + } + + return 0; +} + /* policy for the attributes */ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR]; @@ -830,6 +845,11 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MLO_TTLM_ULINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8), [NL80211_ATTR_ASSOC_SPP_AMSDU] = { .type = NLA_FLAG }, [NL80211_ATTR_VIF_RADIO_MASK] = { .type = NLA_U32 }, + [NL80211_ATTR_SUPPORTED_SELECTORS] = + NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_supported_selectors, + NL80211_MAX_SUPP_SELECTORS), + [NL80211_ATTR_MLO_RECONF_REM_LINKS] = { .type = NLA_U16 }, + [NL80211_ATTR_EPCS] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -3626,7 +3646,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } else wdev = netdev->ieee80211_ptr; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); /* * end workaround code, by now the rdev is available @@ -3639,32 +3659,24 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rtnl_unlock(); if (result) - goto out; + return result; if (info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS]) { struct ieee80211_txq_params txq_params; struct nlattr *tb[NL80211_TXQ_ATTR_MAX + 1]; - if (!rdev->ops->set_txq_params) { - result = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->set_txq_params) + return -EOPNOTSUPP; - if (!netdev) { - result = -EINVAL; - goto out; - } + if (!netdev) + return -EINVAL; if (netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && - netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) { - result = -EINVAL; - goto out; - } + netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EINVAL; - if (!netif_running(netdev)) { - result = -ENETDOWN; - goto out; - } + if (!netif_running(netdev)) + return -ENETDOWN; nla_for_each_nested(nl_txq_params, info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS], @@ -3675,10 +3687,11 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) txq_params_policy, info->extack); if (result) - goto out; + return result; + result = parse_txq_params(tb, &txq_params); if (result) - goto out; + return result; txq_params.link_id = nl80211_link_id_or_invalid(info->attrs); @@ -3694,7 +3707,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) result = rdev_set_txq_params(rdev, netdev, &txq_params); if (result) - goto out; + return result; } } @@ -3711,7 +3724,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } if (result) - goto out; + return result; } if (info->attrs[NL80211_ATTR_WIPHY_TX_POWER_SETTING]) { @@ -3722,19 +3735,15 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (!(rdev->wiphy.features & NL80211_FEATURE_VIF_TXPOWER)) txp_wdev = NULL; - if (!rdev->ops->set_tx_power) { - result = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->set_tx_power) + return -EOPNOTSUPP; idx = NL80211_ATTR_WIPHY_TX_POWER_SETTING; type = nla_get_u32(info->attrs[idx]); if (!info->attrs[NL80211_ATTR_WIPHY_TX_POWER_LEVEL] && - (type != NL80211_TX_POWER_AUTOMATIC)) { - result = -EINVAL; - goto out; - } + (type != NL80211_TX_POWER_AUTOMATIC)) + return -EINVAL; if (type != NL80211_TX_POWER_AUTOMATIC) { idx = NL80211_ATTR_WIPHY_TX_POWER_LEVEL; @@ -3743,7 +3752,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) result = rdev_set_tx_power(rdev, txp_wdev, type, mbm); if (result) - goto out; + return result; } if (info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX] && @@ -3752,10 +3761,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if ((!rdev->wiphy.available_antennas_tx && !rdev->wiphy.available_antennas_rx) || - !rdev->ops->set_antenna) { - result = -EOPNOTSUPP; - goto out; - } + !rdev->ops->set_antenna) + return -EOPNOTSUPP; tx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX]); rx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_RX]); @@ -3763,17 +3770,15 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) /* reject antenna configurations which don't match the * available antenna masks, except for the "all" mask */ if ((~tx_ant && (tx_ant & ~rdev->wiphy.available_antennas_tx)) || - (~rx_ant && (rx_ant & ~rdev->wiphy.available_antennas_rx))) { - result = -EINVAL; - goto out; - } + (~rx_ant && (rx_ant & ~rdev->wiphy.available_antennas_rx))) + return -EINVAL; tx_ant = tx_ant & rdev->wiphy.available_antennas_tx; rx_ant = rx_ant & rdev->wiphy.available_antennas_rx; result = rdev_set_antenna(rdev, tx_ant, rx_ant); if (result) - goto out; + return result; } changed = 0; @@ -3795,10 +3800,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]) { frag_threshold = nla_get_u32( info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]); - if (frag_threshold < 256) { - result = -EINVAL; - goto out; - } + if (frag_threshold < 256) + return -EINVAL; if (frag_threshold != (u32) -1) { /* @@ -3819,10 +3822,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_WIPHY_COVERAGE_CLASS]) { - if (info->attrs[NL80211_ATTR_WIPHY_DYN_ACK]) { - result = -EINVAL; - goto out; - } + if (info->attrs[NL80211_ATTR_WIPHY_DYN_ACK]) + return -EINVAL; coverage_class = nla_get_u8( info->attrs[NL80211_ATTR_WIPHY_COVERAGE_CLASS]); @@ -3830,20 +3831,17 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_WIPHY_DYN_ACK]) { - if (!(rdev->wiphy.features & NL80211_FEATURE_ACKTO_ESTIMATION)) { - result = -EOPNOTSUPP; - goto out; - } + if (!(rdev->wiphy.features & NL80211_FEATURE_ACKTO_ESTIMATION)) + return -EOPNOTSUPP; changed |= WIPHY_PARAM_DYN_ACK; } if (info->attrs[NL80211_ATTR_TXQ_LIMIT]) { if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_TXQS)) { - result = -EOPNOTSUPP; - goto out; - } + NL80211_EXT_FEATURE_TXQS)) + return -EOPNOTSUPP; + txq_limit = nla_get_u32( info->attrs[NL80211_ATTR_TXQ_LIMIT]); changed |= WIPHY_PARAM_TXQ_LIMIT; @@ -3851,10 +3849,9 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TXQ_MEMORY_LIMIT]) { if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_TXQS)) { - result = -EOPNOTSUPP; - goto out; - } + NL80211_EXT_FEATURE_TXQS)) + return -EOPNOTSUPP; + txq_memory_limit = nla_get_u32( info->attrs[NL80211_ATTR_TXQ_MEMORY_LIMIT]); changed |= WIPHY_PARAM_TXQ_MEMORY_LIMIT; @@ -3862,10 +3859,9 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TXQ_QUANTUM]) { if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_TXQS)) { - result = -EOPNOTSUPP; - goto out; - } + NL80211_EXT_FEATURE_TXQS)) + return -EOPNOTSUPP; + txq_quantum = nla_get_u32( info->attrs[NL80211_ATTR_TXQ_QUANTUM]); changed |= WIPHY_PARAM_TXQ_QUANTUM; @@ -3877,10 +3873,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) u8 old_coverage_class; u32 old_txq_limit, old_txq_memory_limit, old_txq_quantum; - if (!rdev->ops->set_wiphy_params) { - result = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->set_wiphy_params) + return -EOPNOTSUPP; old_retry_short = rdev->wiphy.retry_short; old_retry_long = rdev->wiphy.retry_long; @@ -3918,15 +3912,11 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev->wiphy.txq_limit = old_txq_limit; rdev->wiphy.txq_memory_limit = old_txq_memory_limit; rdev->wiphy.txq_quantum = old_txq_quantum; - goto out; + return result; } } - result = 0; - -out: - wiphy_unlock(&rdev->wiphy); - return result; + return 0; } int nl80211_send_chandef(struct sk_buff *msg, const struct cfg80211_chan_def *chandef) @@ -4010,10 +4000,10 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag goto nla_put_failure; } - if (rdev->ops->get_tx_power) { + if (rdev->ops->get_tx_power && !wdev->valid_links) { int dbm, ret; - ret = rdev_get_tx_power(rdev, wdev, &dbm); + ret = rdev_get_tx_power(rdev, wdev, 0, &dbm); if (ret == 0 && nla_put_u32(msg, NL80211_ATTR_WIPHY_TX_POWER_LEVEL, DBM_TO_MBM(dbm))) @@ -4082,6 +4072,15 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag if (ret == 0 && nl80211_send_chandef(msg, &chandef)) goto nla_put_failure; + if (rdev->ops->get_tx_power) { + int dbm, ret; + + ret = rdev_get_tx_power(rdev, wdev, link_id, &dbm); + if (ret == 0 && + nla_put_u32(msg, NL80211_ATTR_WIPHY_TX_POWER_LEVEL, + DBM_TO_MBM(dbm))) + goto nla_put_failure; + } nla_nest_end(msg, link); } @@ -4144,22 +4143,22 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * if_idx = 0; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (if_idx < if_start) { if_idx++; continue; } + if (nl80211_send_iface(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev, - NL80211_CMD_NEW_INTERFACE) < 0) { - wiphy_unlock(&rdev->wiphy); + NL80211_CMD_NEW_INTERFACE) < 0) goto out; - } + if_idx++; } - wiphy_unlock(&rdev->wiphy); if_start = 0; wp_idx++; @@ -4517,16 +4516,13 @@ static int _nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - int ret; /* to avoid failing a new interface creation due to pending removal */ cfg80211_destroy_ifaces(rdev); - wiphy_lock(&rdev->wiphy); - ret = _nl80211_new_interface(skb, info); - wiphy_unlock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); - return ret; + return _nl80211_new_interface(skb, info); } static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) @@ -10098,7 +10094,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, struct cfg80211_chan_def chandef; enum nl80211_dfs_regions dfs_region; unsigned int cac_time_ms; - int err = -EINVAL; + int err; flush_delayed_work(&rdev->dfs_update_channels_wk); @@ -10113,35 +10109,29 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, return -EINVAL; } - wiphy_lock(wiphy); + guard(wiphy)(wiphy); dfs_region = reg_get_dfs_region(wiphy); if (dfs_region == NL80211_DFS_UNSET) - goto unlock; + return -EINVAL; err = nl80211_parse_chandef(rdev, info, &chandef); if (err) - goto unlock; + return err; err = cfg80211_chandef_dfs_required(wiphy, &chandef, wdev->iftype); if (err < 0) - goto unlock; + return err; - if (err == 0) { - err = -EINVAL; - goto unlock; - } + if (err == 0) + return -EINVAL; - if (!cfg80211_chandef_dfs_usable(wiphy, &chandef)) { - err = -EINVAL; - goto unlock; - } + if (!cfg80211_chandef_dfs_usable(wiphy, &chandef)) + return -EINVAL; - if (nla_get_flag(info->attrs[NL80211_ATTR_RADAR_BACKGROUND])) { - err = cfg80211_start_background_radar_detection(rdev, wdev, - &chandef); - goto unlock; - } + if (nla_get_flag(info->attrs[NL80211_ATTR_RADAR_BACKGROUND])) + return cfg80211_start_background_radar_detection(rdev, wdev, + &chandef); if (cfg80211_beaconing_iface_active(wdev)) { /* During MLO other link(s) can beacon, only the current link @@ -10151,26 +10141,19 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, !wdev->links[link_id].ap.beacon_interval) { /* nothing */ } else { - err = -EBUSY; - goto unlock; + return -EBUSY; } } - if (wdev->links[link_id].cac_started) { - err = -EBUSY; - goto unlock; - } + if (wdev->links[link_id].cac_started) + return -EBUSY; /* CAC start is offloaded to HW and can't be started manually */ - if (wiphy_ext_feature_isset(wiphy, NL80211_EXT_FEATURE_DFS_OFFLOAD)) { - err = -EOPNOTSUPP; - goto unlock; - } + if (wiphy_ext_feature_isset(wiphy, NL80211_EXT_FEATURE_DFS_OFFLOAD)) + return -EOPNOTSUPP; - if (!rdev->ops->start_radar_detection) { - err = -EOPNOTSUPP; - goto unlock; - } + if (!rdev->ops->start_radar_detection) + return -EOPNOTSUPP; cac_time_ms = cfg80211_chandef_dfs_cac_time(&rdev->wiphy, &chandef); if (WARN_ON(!cac_time_ms)) @@ -10178,29 +10161,28 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, err = rdev_start_radar_detection(rdev, dev, &chandef, cac_time_ms, link_id); - if (!err) { - switch (wdev->iftype) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_P2P_GO: - wdev->links[0].ap.chandef = chandef; - break; - case NL80211_IFTYPE_ADHOC: - wdev->u.ibss.chandef = chandef; - break; - case NL80211_IFTYPE_MESH_POINT: - wdev->u.mesh.chandef = chandef; - break; - default: - break; - } - wdev->links[link_id].cac_started = true; - wdev->links[link_id].cac_start_time = jiffies; - wdev->links[link_id].cac_time_ms = cac_time_ms; - } -unlock: - wiphy_unlock(wiphy); + if (err) + return err; - return err; + switch (wdev->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + wdev->links[0].ap.chandef = chandef; + break; + case NL80211_IFTYPE_ADHOC: + wdev->u.ibss.chandef = chandef; + break; + case NL80211_IFTYPE_MESH_POINT: + wdev->u.mesh.chandef = chandef; + break; + default: + break; + } + wdev->links[link_id].cac_started = true; + wdev->links[link_id].cac_start_time = jiffies; + wdev->links[link_id].cac_time_ms = cac_time_ms; + + return 0; } static int nl80211_notify_radar_detection(struct sk_buff *skb, @@ -10897,6 +10879,13 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) req.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } + if (info->attrs[NL80211_ATTR_SUPPORTED_SELECTORS]) { + req.supported_selectors = + nla_data(info->attrs[NL80211_ATTR_SUPPORTED_SELECTORS]); + req.supported_selectors_len = + nla_len(info->attrs[NL80211_ATTR_SUPPORTED_SELECTORS]); + } + auth_type = nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); if (!nl80211_valid_auth_type(rdev, auth_type, NL80211_CMD_AUTHENTICATE)) return -EINVAL; @@ -11127,12 +11116,83 @@ static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device return bss; } +static int nl80211_process_links(struct cfg80211_registered_device *rdev, + struct cfg80211_assoc_link *links, + const u8 *ssid, int ssid_len, + struct genl_info *info) +{ + unsigned int attrsize = NUM_NL80211_ATTR * sizeof(struct nlattr *); + struct nlattr **attrs __free(kfree) = kzalloc(attrsize, GFP_KERNEL); + struct nlattr *link; + unsigned int link_id; + int rem, err; + + if (!attrs) + return -ENOMEM; + + nla_for_each_nested(link, info->attrs[NL80211_ATTR_MLO_LINKS], rem) { + memset(attrs, 0, attrsize); + + nla_parse_nested(attrs, NL80211_ATTR_MAX, link, NULL, NULL); + + if (!attrs[NL80211_ATTR_MLO_LINK_ID]) { + NL_SET_BAD_ATTR(info->extack, link); + return -EINVAL; + } + + link_id = nla_get_u8(attrs[NL80211_ATTR_MLO_LINK_ID]); + /* cannot use the same link ID again */ + if (links[link_id].bss) { + NL_SET_BAD_ATTR(info->extack, link); + return -EINVAL; + } + links[link_id].bss = + nl80211_assoc_bss(rdev, ssid, ssid_len, attrs, + link_id, link_id); + if (IS_ERR(links[link_id].bss)) { + err = PTR_ERR(links[link_id].bss); + links[link_id].bss = NULL; + NL_SET_ERR_MSG_ATTR(info->extack, link, + "Error fetching BSS for link"); + return err; + } + + if (attrs[NL80211_ATTR_IE]) { + links[link_id].elems = nla_data(attrs[NL80211_ATTR_IE]); + links[link_id].elems_len = + nla_len(attrs[NL80211_ATTR_IE]); + + if (cfg80211_find_elem(WLAN_EID_FRAGMENT, + links[link_id].elems, + links[link_id].elems_len)) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[NL80211_ATTR_IE], + "cannot deal with fragmentation"); + return -EINVAL; + } + + if (cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, + links[link_id].elems, + links[link_id].elems_len)) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[NL80211_ATTR_IE], + "cannot deal with non-inheritance"); + return -EINVAL; + } + } + + links[link_id].disabled = + nla_get_flag(attrs[NL80211_ATTR_MLO_LINK_DISABLED]); + } + + return 0; +} + static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct cfg80211_assoc_request req = {}; - struct nlattr **attrs = NULL; const u8 *ap_addr, *ssid; unsigned int link_id; int err, ssid_len; @@ -11179,6 +11239,13 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_PREV_BSSID]) req.prev_bssid = nla_data(info->attrs[NL80211_ATTR_PREV_BSSID]); + if (info->attrs[NL80211_ATTR_SUPPORTED_SELECTORS]) { + req.supported_selectors = + nla_data(info->attrs[NL80211_ATTR_SUPPORTED_SELECTORS]); + req.supported_selectors_len = + nla_len(info->attrs[NL80211_ATTR_SUPPORTED_SELECTORS]); + } + if (nla_get_flag(info->attrs[NL80211_ATTR_DISABLE_HT])) req.flags |= ASSOC_REQ_DISABLE_HT; @@ -11264,10 +11331,6 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) req.link_id = nl80211_link_id_or_invalid(info->attrs); if (info->attrs[NL80211_ATTR_MLO_LINKS]) { - unsigned int attrsize = NUM_NL80211_ATTR * sizeof(*attrs); - struct nlattr *link; - int rem = 0; - if (req.link_id < 0) return -EINVAL; @@ -11282,72 +11345,10 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) req.ap_mld_addr = nla_data(info->attrs[NL80211_ATTR_MLD_ADDR]); ap_addr = req.ap_mld_addr; - attrs = kzalloc(attrsize, GFP_KERNEL); - if (!attrs) - return -ENOMEM; - - nla_for_each_nested(link, - info->attrs[NL80211_ATTR_MLO_LINKS], - rem) { - memset(attrs, 0, attrsize); - - nla_parse_nested(attrs, NL80211_ATTR_MAX, - link, NULL, NULL); - - if (!attrs[NL80211_ATTR_MLO_LINK_ID]) { - err = -EINVAL; - NL_SET_BAD_ATTR(info->extack, link); - goto free; - } - - link_id = nla_get_u8(attrs[NL80211_ATTR_MLO_LINK_ID]); - /* cannot use the same link ID again */ - if (req.links[link_id].bss) { - err = -EINVAL; - NL_SET_BAD_ATTR(info->extack, link); - goto free; - } - req.links[link_id].bss = - nl80211_assoc_bss(rdev, ssid, ssid_len, attrs, - req.link_id, link_id); - if (IS_ERR(req.links[link_id].bss)) { - err = PTR_ERR(req.links[link_id].bss); - req.links[link_id].bss = NULL; - NL_SET_ERR_MSG_ATTR(info->extack, - link, "Error fetching BSS for link"); - goto free; - } - - if (attrs[NL80211_ATTR_IE]) { - req.links[link_id].elems = - nla_data(attrs[NL80211_ATTR_IE]); - req.links[link_id].elems_len = - nla_len(attrs[NL80211_ATTR_IE]); - - if (cfg80211_find_elem(WLAN_EID_FRAGMENT, - req.links[link_id].elems, - req.links[link_id].elems_len)) { - NL_SET_ERR_MSG_ATTR(info->extack, - attrs[NL80211_ATTR_IE], - "cannot deal with fragmentation"); - err = -EINVAL; - goto free; - } - - if (cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, - req.links[link_id].elems, - req.links[link_id].elems_len)) { - NL_SET_ERR_MSG_ATTR(info->extack, - attrs[NL80211_ATTR_IE], - "cannot deal with non-inheritance"); - err = -EINVAL; - goto free; - } - } - - req.links[link_id].disabled = - nla_get_flag(attrs[NL80211_ATTR_MLO_LINK_DISABLED]); - } + err = nl80211_process_links(rdev, req.links, ssid, ssid_len, + info); + if (err) + goto free; if (!req.links[req.link_id].bss) { err = -EINVAL; @@ -11367,9 +11368,6 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) err = -EINVAL; goto free; } - - kfree(attrs); - attrs = NULL; } else { if (req.link_id >= 0) return -EINVAL; @@ -11429,7 +11427,6 @@ free: for (link_id = 0; link_id < ARRAY_SIZE(req.links); link_id++) cfg80211_put_bss(&rdev->wiphy, req.links[link_id].bss); cfg80211_put_bss(&rdev->wiphy, req.bss); - kfree(attrs); return err; } @@ -16481,6 +16478,86 @@ nl80211_set_ttlm(struct sk_buff *skb, struct genl_info *info) return rdev_set_ttlm(rdev, dev, ¶ms); } +static int nl80211_assoc_ml_reconf(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_assoc_link links[IEEE80211_MLD_MAX_NUM_LINKS] = {}; + unsigned int link_id; + u16 add_links, rem_links; + int err; + + if (!wdev->valid_links) + return -EINVAL; + + if (dev->ieee80211_ptr->conn_owner_nlportid && + dev->ieee80211_ptr->conn_owner_nlportid != info->snd_portid) + return -EPERM; + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + add_links = 0; + if (info->attrs[NL80211_ATTR_MLO_LINKS]) { + err = nl80211_process_links(rdev, links, NULL, 0, info); + if (err) + return err; + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; + link_id++) { + if (!links[link_id].bss) + continue; + add_links |= BIT(link_id); + } + } + + if (info->attrs[NL80211_ATTR_MLO_RECONF_REM_LINKS]) + rem_links = + nla_get_u16(info->attrs[NL80211_ATTR_MLO_RECONF_REM_LINKS]); + else + rem_links = 0; + + /* Validate that existing links are not added, removed links are valid + * and don't allow adding and removing the same links + */ + if ((add_links & rem_links) || !(add_links | rem_links) || + (wdev->valid_links & add_links) || + ((wdev->valid_links & rem_links) != rem_links)) { + err = -EINVAL; + goto out; + } + + err = cfg80211_assoc_ml_reconf(rdev, dev, links, rem_links); + +out: + for (link_id = 0; link_id < ARRAY_SIZE(links); link_id++) + cfg80211_put_bss(&rdev->wiphy, links[link_id].bss); + + return err; +} + +static int +nl80211_epcs_cfg(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + bool val; + + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + if (!wdev->connected) + return -ENOLINK; + + val = nla_get_flag(info->attrs[NL80211_ATTR_EPCS]); + + return rdev_set_epcs(rdev, dev, val); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -17673,6 +17750,18 @@ static const struct genl_small_ops nl80211_small_ops[] = { .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), }, + { + .cmd = NL80211_CMD_ASSOC_MLO_RECONF, + .doit = nl80211_assoc_ml_reconf, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + }, + { + .cmd = NL80211_CMD_EPCS_CFG, + .doit = nl80211_epcs_cfg, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + }, }; static struct genl_family nl80211_fam __ro_after_init = { @@ -18448,10 +18537,9 @@ void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer_addr)) goto nla_put_failure; - if ((td_bitmap_len > 0) && td_bitmap) - if (nla_put(msg, NL80211_ATTR_TD_BITMAP, - td_bitmap_len, td_bitmap)) - goto nla_put_failure; + if (td_bitmap_len > 0 && td_bitmap && + nla_put(msg, NL80211_ATTR_TD_BITMAP, td_bitmap_len, td_bitmap)) + goto nla_put_failure; genlmsg_end(msg, hdr); @@ -18569,6 +18657,23 @@ void cfg80211_links_removed(struct net_device *dev, u16 link_mask) } EXPORT_SYMBOL(cfg80211_links_removed); +void nl80211_mlo_reconf_add_done(struct net_device *dev, + struct cfg80211_mlo_reconf_done_data *data) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct nl80211_mlme_event event = { + .cmd = NL80211_CMD_ASSOC_MLO_RECONF, + .buf = data->buf, + .buf_len = data->len, + .uapsd_queues = -1, + }; + + nl80211_send_mlme_event(rdev, dev, &event, GFP_KERNEL); +} +EXPORT_SYMBOL(nl80211_mlo_reconf_add_done); + void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid, gfp_t gfp) @@ -20401,6 +20506,39 @@ void cfg80211_schedule_channels_check(struct wireless_dev *wdev) } EXPORT_SYMBOL(cfg80211_schedule_channels_check); +void cfg80211_epcs_changed(struct net_device *netdev, bool enabled) +{ + struct wireless_dev *wdev = netdev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct sk_buff *msg; + void *hdr; + + trace_cfg80211_epcs_changed(wdev, enabled); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_EPCS_CFG); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (enabled && nla_put_flag(msg, NL80211_ATTR_EPCS)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_MLME, GFP_KERNEL); + return; + + nla_put_failure: + nlmsg_free(msg); +} +EXPORT_SYMBOL(cfg80211_epcs_changed); + /* initialisation/exit functions */ int __init nl80211_init(void) diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index ffaab9a92e5b..5e25782af1e0 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -124,4 +124,7 @@ void cfg80211_free_coalesce(struct cfg80211_coalesce *coalesce); /* peer measurement */ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info); +void nl80211_mlo_reconf_add_done(struct net_device *dev, + struct cfg80211_mlo_reconf_done_data *data); + #endif /* __NET_WIRELESS_NL80211_H */ diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 0396fa19bdf1..a117f5093ca2 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -630,9 +630,9 @@ void cfg80211_pmsr_free_wk(struct work_struct *work) struct wireless_dev *wdev = container_of(work, struct wireless_dev, pmsr_free_wk); - wiphy_lock(wdev->wiphy); + guard(wiphy)(wdev->wiphy); + cfg80211_pmsr_process_abort(wdev); - wiphy_unlock(wdev->wiphy); } void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index adb6105bbb7d..759da1623342 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -600,11 +600,12 @@ static inline int rdev_set_tx_power(struct cfg80211_registered_device *rdev, } static inline int rdev_get_tx_power(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, int *dbm) + struct wireless_dev *wdev, unsigned int link_id, + int *dbm) { int ret; - trace_rdev_get_tx_power(&rdev->wiphy, wdev); - ret = rdev->ops->get_tx_power(&rdev->wiphy, wdev, dbm); + trace_rdev_get_tx_power(&rdev->wiphy, wdev, link_id); + ret = rdev->ops->get_tx_power(&rdev->wiphy, wdev, link_id, dbm); trace_rdev_return_int_int(&rdev->wiphy, ret, *dbm); return ret; } @@ -1546,4 +1547,38 @@ rdev_get_radio_mask(struct cfg80211_registered_device *rdev, return rdev->ops->get_radio_mask(wiphy, dev); } + +static inline int +rdev_assoc_ml_reconf(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_assoc_link *add_links, + u16 rem_links) +{ + struct wiphy *wiphy = &rdev->wiphy; + int ret = -EOPNOTSUPP; + + trace_rdev_assoc_ml_reconf(wiphy, dev, add_links, rem_links); + if (rdev->ops->assoc_ml_reconf) + ret = rdev->ops->assoc_ml_reconf(wiphy, dev, add_links, + rem_links); + trace_rdev_return_int(wiphy, ret); + + return ret; +} + +static inline int +rdev_set_epcs(struct cfg80211_registered_device *rdev, + struct net_device *dev, bool val) +{ + struct wiphy *wiphy = &rdev->wiphy; + int ret = -EOPNOTSUPP; + + trace_rdev_set_epcs(wiphy, dev, val); + if (rdev->ops->set_epcs) + ret = rdev->ops->set_epcs(wiphy, dev, val); + trace_rdev_return_int(wiphy, ret); + + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 1df65a5a44f7..2dd0533e7660 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2465,11 +2465,11 @@ static void reg_leave_invalid_chans(struct wiphy *wiphy) struct wireless_dev *wdev; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - wiphy_lock(wiphy); + guard(wiphy)(wiphy); + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) if (!reg_wdev_chan_valid(wiphy, wdev)) cfg80211_leave(rdev, wdev); - wiphy_unlock(wiphy); } static void reg_check_chans_work(struct work_struct *work) @@ -2649,13 +2649,11 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy, return; rtnl_lock(); - wiphy_lock(wiphy); - - tmp = get_wiphy_regdom(wiphy); - rcu_assign_pointer(wiphy->regd, new_regd); - rcu_free_regdom(tmp); - - wiphy_unlock(wiphy); + scoped_guard(wiphy, wiphy) { + tmp = get_wiphy_regdom(wiphy); + rcu_assign_pointer(wiphy->regd, new_regd); + rcu_free_regdom(tmp); + } rtnl_unlock(); } EXPORT_SYMBOL(wiphy_apply_custom_regulatory); @@ -2825,9 +2823,9 @@ reg_process_hint_driver(struct wiphy *wiphy, tmp = get_wiphy_regdom(wiphy); ASSERT_RTNL(); - wiphy_lock(wiphy); - rcu_assign_pointer(wiphy->regd, regd); - wiphy_unlock(wiphy); + scoped_guard(wiphy, wiphy) { + rcu_assign_pointer(wiphy->regd, regd); + } rcu_free_regdom(tmp); } @@ -3205,9 +3203,9 @@ static void reg_process_self_managed_hints(void) ASSERT_RTNL(); for_each_rdev(rdev) { - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + reg_process_self_managed_hint(&rdev->wiphy); - wiphy_unlock(&rdev->wiphy); } reg_check_channels(); @@ -3600,14 +3598,12 @@ static bool is_wiphy_all_set_reg_flag(enum ieee80211_regulatory_flags flag) struct wireless_dev *wdev; for_each_rdev(rdev) { - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { - if (!(wdev->wiphy->regulatory_flags & flag)) { - wiphy_unlock(&rdev->wiphy); + if (!(wdev->wiphy->regulatory_flags & flag)) return false; - } } - wiphy_unlock(&rdev->wiphy); } return true; @@ -3883,19 +3879,18 @@ static int reg_set_rd_driver(const struct ieee80211_regdomain *rd, if (!driver_request->intersect) { ASSERT_RTNL(); - wiphy_lock(request_wiphy); - if (request_wiphy->regd) - tmp = get_wiphy_regdom(request_wiphy); + scoped_guard(wiphy, request_wiphy) { + if (request_wiphy->regd) + tmp = get_wiphy_regdom(request_wiphy); - regd = reg_copy_regd(rd); - if (IS_ERR(regd)) { - wiphy_unlock(request_wiphy); - return PTR_ERR(regd); + regd = reg_copy_regd(rd); + if (IS_ERR(regd)) + return PTR_ERR(regd); + + rcu_assign_pointer(request_wiphy->regd, regd); + rcu_free_regdom(tmp); } - rcu_assign_pointer(request_wiphy->regd, regd); - rcu_free_regdom(tmp); - wiphy_unlock(request_wiphy); reset_regdomains(false, rd); return 0; } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 1c6fd45aa809..cd2124329521 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -272,12 +272,19 @@ cfg80211_gen_new_ie(const u8 *ie, size_t ielen, { const struct element *non_inherit_elem, *parent, *sub; u8 *pos = new_ie; - u8 id, ext_id; + const u8 *mbssid_index_ie; + u8 id, ext_id, bssid_index = 255; unsigned int match_len; non_inherit_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, subie, subie_len); + mbssid_index_ie = cfg80211_find_ie(WLAN_EID_MULTI_BSSID_IDX, subie, + subie_len); + if (mbssid_index_ie && mbssid_index_ie[1] > 0 && + mbssid_index_ie[2] > 0 && mbssid_index_ie[2] <= 46) + bssid_index = mbssid_index_ie[2]; + /* We copy the elements one by one from the parent to the generated * elements. * If they are not inherited (included in subie or in the non @@ -316,6 +323,24 @@ cfg80211_gen_new_ie(const u8 *ie, size_t ielen, continue; } + /* For ML probe response, match the MLE in the frame body with + * MLD id being 'bssid_index' + */ + if (parent->id == WLAN_EID_EXTENSION && parent->datalen > 1 && + parent->data[0] == WLAN_EID_EXT_EHT_MULTI_LINK && + bssid_index == ieee80211_mle_get_mld_id(parent->data + 1)) { + if (!cfg80211_copy_elem_with_frags(parent, + ie, ielen, + &pos, new_ie, + new_ie_len)) + return 0; + + /* Continue here to prevent processing the MLE in + * sub-element, which AP MLD should not carry + */ + continue; + } + /* Already copied if an earlier element had the same type */ if (cfg80211_find_elem_match(id, ie, (u8 *)parent - ie, &ext_id, match_len, 0)) @@ -704,7 +729,7 @@ cfg80211_parse_colocated_ap_iter(void *_data, u8 type, bss_params))) return RNR_ITER_CONTINUE; - entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN, GFP_ATOMIC); + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return RNR_ITER_ERROR; @@ -713,6 +738,17 @@ cfg80211_parse_colocated_ap_iter(void *_data, u8 type, if (!cfg80211_parse_ap_info(entry, tbtt_info, tbtt_info_len, data->ssid_elem, data->s_ssid_tmp)) { + struct cfg80211_colocated_ap *tmp; + + /* Don't add duplicate BSSIDs on the same channel. */ + list_for_each_entry(tmp, &data->ap_list, list) { + if (ether_addr_equal(tmp->bssid, entry->bssid) && + tmp->center_freq == entry->center_freq) { + kfree(entry); + return RNR_ITER_CONTINUE; + } + } + data->n_coloc++; list_add_tail(&entry->list, &data->ap_list); } else { @@ -763,12 +799,11 @@ static void cfg80211_scan_req_add_chan(struct cfg80211_scan_request *request, } } + request->n_channels++; request->channels[n_channels] = chan; if (add_to_6ghz) request->scan_6ghz_params[request->n_6ghz_params].channel_idx = n_channels; - - request->n_channels++; } static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap, @@ -858,9 +893,7 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) if (ret) continue; - entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN, - GFP_ATOMIC); - + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) continue; @@ -1238,7 +1271,8 @@ void cfg80211_sched_scan_results_wk(struct work_struct *work) rdev = container_of(work, struct cfg80211_registered_device, sched_scan_res_wk); - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + list_for_each_entry_safe(req, tmp, &rdev->sched_scan_req_list, list) { if (req->report_results) { req->report_results = false; @@ -1253,7 +1287,6 @@ void cfg80211_sched_scan_results_wk(struct work_struct *work) NL80211_CMD_SCHED_SCAN_RESULTS); } } - wiphy_unlock(&rdev->wiphy); } void cfg80211_sched_scan_results(struct wiphy *wiphy, u64 reqid) @@ -1288,9 +1321,9 @@ EXPORT_SYMBOL(cfg80211_sched_scan_stopped_locked); void cfg80211_sched_scan_stopped(struct wiphy *wiphy, u64 reqid) { - wiphy_lock(wiphy); + guard(wiphy)(wiphy); + cfg80211_sched_scan_stopped_locked(wiphy, reqid); - wiphy_unlock(wiphy); } EXPORT_SYMBOL(cfg80211_sched_scan_stopped); @@ -3565,10 +3598,8 @@ int cfg80211_wext_siwscan(struct net_device *dev, /* translate "Scan for SSID" request */ if (wreq) { if (wrqu->data.flags & IW_SCAN_THIS_ESSID) { - if (wreq->essid_len > IEEE80211_MAX_SSID_LEN) { - err = -EINVAL; - goto out; - } + if (wreq->essid_len > IEEE80211_MAX_SSID_LEN) + return -EINVAL; memcpy(creq->ssids[0].ssid, wreq->essid, wreq->essid_len); creq->ssids[0].ssid_len = wreq->essid_len; } @@ -3584,20 +3615,20 @@ int cfg80211_wext_siwscan(struct net_device *dev, eth_broadcast_addr(creq->bssid); - wiphy_lock(&rdev->wiphy); - - rdev->scan_req = creq; - err = rdev_scan(rdev, creq); - if (err) { - rdev->scan_req = NULL; - /* creq will be freed below */ - } else { - nl80211_send_scan_start(rdev, dev->ieee80211_ptr); - /* creq now owned by driver */ - creq = NULL; - dev_hold(dev); + scoped_guard(wiphy, &rdev->wiphy) { + rdev->scan_req = creq; + err = rdev_scan(rdev, creq); + if (err) { + rdev->scan_req = NULL; + /* creq will be freed below */ + } else { + nl80211_send_scan_start(rdev, dev->ieee80211_ptr); + /* creq now owned by driver */ + creq = NULL; + dev_hold(dev); + } } - wiphy_unlock(&rdev->wiphy); + out: kfree(creq); return err; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 268171600087..cf998500a965 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -252,7 +252,7 @@ void cfg80211_conn_work(struct work_struct *work) u8 bssid_buf[ETH_ALEN], *bssid = NULL; enum nl80211_timeout_reason treason; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->netdev) @@ -280,8 +280,6 @@ void cfg80211_conn_work(struct work_struct *work) __cfg80211_connect_result(wdev->netdev, &cr, false); } } - - wiphy_unlock(&rdev->wiphy); } static void cfg80211_step_auth_next(struct cfg80211_conn *conn, @@ -693,13 +691,13 @@ static bool cfg80211_is_all_idle(void) * as chan dfs state, etc. */ for_each_rdev(rdev) { - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (wdev->conn || wdev->connected || cfg80211_beaconing_iface_active(wdev)) is_all_idle = false; } - wiphy_unlock(&rdev->wiphy); } return is_all_idle; @@ -1583,7 +1581,7 @@ void cfg80211_autodisconnect_wk(struct work_struct *work) container_of(work, struct wireless_dev, disconnect_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - wiphy_lock(wdev->wiphy); + guard(wiphy)(wdev->wiphy); if (wdev->conn_owner_nlportid) { switch (wdev->iftype) { @@ -1619,6 +1617,4 @@ void cfg80211_autodisconnect_wk(struct work_struct *work) break; } } - - wiphy_unlock(wdev->wiphy); } diff --git a/net/wireless/tests/scan.c b/net/wireless/tests/scan.c index e12f620b5f42..b1a9c1466d6c 100644 --- a/net/wireless/tests/scan.c +++ b/net/wireless/tests/scan.c @@ -810,6 +810,8 @@ static void test_cfg80211_parse_colocated_ap(struct kunit *test) skb_put_data(input, "123", 3); ies = kunit_kzalloc(test, struct_size(ies, data, input->len), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, ies); + ies->len = input->len; memcpy(ies->data, input->data, input->len); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index d5c9bb614fa6..4f0abd5d49df 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1690,9 +1690,28 @@ TRACE_EVENT(rdev_set_wiphy_params, WIPHY_PR_ARG, __entry->changed) ); -DEFINE_EVENT(wiphy_wdev_evt, rdev_get_tx_power, - TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), - TP_ARGS(wiphy, wdev) +DECLARE_EVENT_CLASS(wiphy_wdev_link_evt, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id), + TP_ARGS(wiphy, wdev, link_id), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(unsigned int, link_id) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->link_id = link_id; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", link_id: %u", + WIPHY_PR_ARG, WDEV_PR_ARG, __entry->link_id) +); + +DEFINE_EVENT(wiphy_wdev_link_evt, rdev_get_tx_power, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id), + TP_ARGS(wiphy, wdev, link_id) ); TRACE_EVENT(rdev_set_tx_power, @@ -2192,25 +2211,6 @@ TRACE_EVENT(rdev_set_noack_map, TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", noack_map: %u", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->noack_map) ); - -DECLARE_EVENT_CLASS(wiphy_wdev_link_evt, - TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, - unsigned int link_id), - TP_ARGS(wiphy, wdev, link_id), - TP_STRUCT__entry( - WIPHY_ENTRY - WDEV_ENTRY - __field(unsigned int, link_id) - ), - TP_fast_assign( - WIPHY_ASSIGN; - WDEV_ASSIGN; - __entry->link_id = link_id; - ), - TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", link_id: %u", - WIPHY_PR_ARG, WDEV_PR_ARG, __entry->link_id) -); - DEFINE_EVENT(wiphy_wdev_link_evt, rdev_get_channel, TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id), @@ -3049,6 +3049,24 @@ TRACE_EVENT(rdev_set_ttlm, WIPHY_PR_ARG, NETDEV_PR_ARG) ); +TRACE_EVENT(rdev_set_epcs, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + bool val), + TP_ARGS(wiphy, netdev, val), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(bool, val) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->val = val; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", config=%u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->val) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ @@ -4104,6 +4122,66 @@ TRACE_EVENT(cfg80211_links_removed, __entry->link_mask) ); +TRACE_EVENT(cfg80211_mlo_reconf_add_done, + TP_PROTO(struct net_device *netdev, u16 link_mask, + const u8 *buf, size_t len), + TP_ARGS(netdev, link_mask, buf, len), + TP_STRUCT__entry( + NETDEV_ENTRY + __field(u16, link_mask) + __dynamic_array(u8, buf, len) + ), + TP_fast_assign( + NETDEV_ASSIGN; + __entry->link_mask = link_mask; + memcpy(__get_dynamic_array(buf), buf, len); + ), + TP_printk(NETDEV_PR_FMT ", link_mask:0x%x", + NETDEV_PR_ARG, __entry->link_mask) +); + +TRACE_EVENT(rdev_assoc_ml_reconf, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_assoc_link *add_links, + u16 rem_links), + TP_ARGS(wiphy, netdev, add_links, rem_links), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u16, add_links) + __field(u16, rem_links) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + u32 i; + + __entry->add_links = 0; + __entry->rem_links = rem_links; + for (i = 0; add_links && i < IEEE80211_MLD_MAX_NUM_LINKS; i++) + if (add_links[i].bss) + __entry->add_links |= BIT(i); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", add_links=0x%x, rem_links=0x%x", + WIPHY_PR_ARG, NETDEV_PR_ARG, + __entry->add_links, __entry->rem_links) +); + +TRACE_EVENT(cfg80211_epcs_changed, + TP_PROTO(struct wireless_dev *wdev, bool enabled), + TP_ARGS(wdev, enabled), + TP_STRUCT__entry( + WDEV_ENTRY + __field(u32, enabled) + ), + TP_fast_assign( + WDEV_ASSIGN; + __entry->enabled = enabled; + ), + TP_printk(WDEV_PR_FMT ", enabled=%u", + WDEV_PR_ARG, __entry->enabled) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/wireless/util.c b/net/wireless/util.c index 65c8e47246b7..60157943d351 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -2572,7 +2572,6 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; - int ret; wdev = dev->ieee80211_ptr; if (!wdev) @@ -2584,11 +2583,9 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, memset(sinfo, 0, sizeof(*sinfo)); - wiphy_lock(&rdev->wiphy); - ret = rdev_get_station(rdev, dev, mac_addr, sinfo); - wiphy_unlock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); - return ret; + return rdev_get_station(rdev, dev, mac_addr, sinfo); } EXPORT_SYMBOL(cfg80211_get_station); diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 90d5c0592667..a74b1afc594e 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -39,7 +39,6 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, struct cfg80211_registered_device *rdev; struct vif_params vifparams; enum nl80211_iftype type; - int ret; rdev = wiphy_to_rdev(wdev->wiphy); @@ -62,11 +61,9 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, memset(&vifparams, 0, sizeof(vifparams)); - wiphy_lock(wdev->wiphy); - ret = cfg80211_change_iface(rdev, dev, type, &vifparams); - wiphy_unlock(wdev->wiphy); + guard(wiphy)(wdev->wiphy); - return ret; + return cfg80211_change_iface(rdev, dev, type, &vifparams); } int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, @@ -258,23 +255,17 @@ int cfg80211_wext_siwrts(struct net_device *dev, u32 orts = wdev->wiphy->rts_threshold; int err; - wiphy_lock(&rdev->wiphy); - if (rts->disabled || !rts->fixed) { + guard(wiphy)(&rdev->wiphy); + if (rts->disabled || !rts->fixed) wdev->wiphy->rts_threshold = (u32) -1; - } else if (rts->value < 0) { - err = -EINVAL; - goto out; - } else { + else if (rts->value < 0) + return -EINVAL; + else wdev->wiphy->rts_threshold = rts->value; - } err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_RTS_THRESHOLD); - if (err) wdev->wiphy->rts_threshold = orts; - -out: - wiphy_unlock(&rdev->wiphy); return err; } @@ -302,12 +293,12 @@ int cfg80211_wext_siwfrag(struct net_device *dev, u32 ofrag = wdev->wiphy->frag_threshold; int err; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + if (frag->disabled || !frag->fixed) { wdev->wiphy->frag_threshold = (u32) -1; } else if (frag->value < 256) { - err = -EINVAL; - goto out; + return -EINVAL; } else { /* Fragment length must be even, so strip LSB. */ wdev->wiphy->frag_threshold = frag->value & ~0x1; @@ -316,9 +307,6 @@ int cfg80211_wext_siwfrag(struct net_device *dev, err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_FRAG_THRESHOLD); if (err) wdev->wiphy->frag_threshold = ofrag; -out: - wiphy_unlock(&rdev->wiphy); - return err; } @@ -352,7 +340,8 @@ static int cfg80211_wext_siwretry(struct net_device *dev, (retry->flags & IW_RETRY_TYPE) != IW_RETRY_LIMIT) return -EINVAL; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + if (retry->flags & IW_RETRY_LONG) { wdev->wiphy->retry_long = retry->value; changed |= WIPHY_PARAM_RETRY_LONG; @@ -371,7 +360,6 @@ static int cfg80211_wext_siwretry(struct net_device *dev, wdev->wiphy->retry_short = oshort; wdev->wiphy->retry_long = olong; } - wiphy_unlock(&rdev->wiphy); return err; } @@ -578,9 +566,9 @@ static int cfg80211_wext_siwencode(struct net_device *dev, struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - int idx, err; - bool remove = false; struct key_params params; + bool remove = false; + int idx; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) @@ -592,11 +580,9 @@ static int cfg80211_wext_siwencode(struct net_device *dev, !rdev->ops->set_default_key) return -EOPNOTSUPP; - wiphy_lock(&rdev->wiphy); - if (wdev->valid_links) { - err = -EOPNOTSUPP; - goto out; - } + guard(wiphy)(&rdev->wiphy); + if (wdev->valid_links) + return -EOPNOTSUPP; idx = erq->flags & IW_ENCODE_INDEX; if (idx == 0) { @@ -604,8 +590,7 @@ static int cfg80211_wext_siwencode(struct net_device *dev, if (idx < 0) idx = 0; } else if (idx < 1 || idx > 4) { - err = -EINVAL; - goto out; + return -EINVAL; } else { idx--; } @@ -614,7 +599,8 @@ static int cfg80211_wext_siwencode(struct net_device *dev, remove = true; else if (erq->length == 0) { /* No key data - just set the default TX key index */ - err = 0; + int err = 0; + if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) @@ -622,28 +608,22 @@ static int cfg80211_wext_siwencode(struct net_device *dev, true); if (!err) wdev->wext.default_key = idx; - goto out; + return err; } memset(¶ms, 0, sizeof(params)); params.key = keybuf; params.key_len = erq->length; - if (erq->length == 5) { + if (erq->length == 5) params.cipher = WLAN_CIPHER_SUITE_WEP40; - } else if (erq->length == 13) { + else if (erq->length == 13) params.cipher = WLAN_CIPHER_SUITE_WEP104; - } else if (!remove) { - err = -EINVAL; - goto out; - } + else if (!remove) + return -EINVAL; - err = cfg80211_set_encryption(rdev, dev, false, NULL, remove, - wdev->wext.default_key == -1, - idx, ¶ms); -out: - wiphy_unlock(&rdev->wiphy); - - return err; + return cfg80211_set_encryption(rdev, dev, false, NULL, remove, + wdev->wext.default_key == -1, + idx, ¶ms); } static int cfg80211_wext_siwencodeext(struct net_device *dev, @@ -659,7 +639,6 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev, bool remove = false; struct key_params params; u32 cipher; - int ret; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) @@ -734,16 +713,13 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev, params.seq_len = 6; } - wiphy_lock(wdev->wiphy); - ret = cfg80211_set_encryption( - rdev, dev, - !(ext->ext_flags & IW_ENCODE_EXT_GROUP_KEY), - addr, remove, - ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, - idx, ¶ms); - wiphy_unlock(wdev->wiphy); + guard(wiphy)(wdev->wiphy); - return ret; + return cfg80211_set_encryption(rdev, dev, + !(ext->ext_flags & IW_ENCODE_EXT_GROUP_KEY), + addr, remove, + ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, + idx, ¶ms); } static int cfg80211_wext_giwencode(struct net_device *dev, @@ -794,61 +770,41 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, struct cfg80211_chan_def chandef = { .width = NL80211_CHAN_WIDTH_20_NOHT, }; - int freq, ret; + int freq; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: - ret = cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); - break; + return cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); case NL80211_IFTYPE_ADHOC: - ret = cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); - break; + return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); case NL80211_IFTYPE_MONITOR: freq = cfg80211_wext_freq(wextfreq); - if (freq < 0) { - ret = freq; - break; - } - if (freq == 0) { - ret = -EINVAL; - break; - } + if (freq < 0) + return freq; + if (freq == 0) + return -EINVAL; + chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); - if (!chandef.chan) { - ret = -EINVAL; - break; - } - ret = cfg80211_set_monitor_channel(rdev, dev, &chandef); - break; + if (!chandef.chan) + return -EINVAL; + return cfg80211_set_monitor_channel(rdev, dev, &chandef); case NL80211_IFTYPE_MESH_POINT: freq = cfg80211_wext_freq(wextfreq); - if (freq < 0) { - ret = freq; - break; - } - if (freq == 0) { - ret = -EINVAL; - break; - } + if (freq < 0) + return freq; + if (freq == 0) + return -EINVAL; chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); - if (!chandef.chan) { - ret = -EINVAL; - break; - } - ret = cfg80211_set_mesh_channel(rdev, wdev, &chandef); - break; + if (!chandef.chan) + return -EINVAL; + return cfg80211_set_mesh_channel(rdev, wdev, &chandef); default: - ret = -EOPNOTSUPP; - break; + return -EOPNOTSUPP; } - - wiphy_unlock(&rdev->wiphy); - - return ret; } static int cfg80211_wext_giwfreq(struct net_device *dev, @@ -861,35 +817,26 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, struct cfg80211_chan_def chandef = {}; int ret; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + switch (wdev->iftype) { case NL80211_IFTYPE_STATION: - ret = cfg80211_mgd_wext_giwfreq(dev, info, freq, extra); - break; + return cfg80211_mgd_wext_giwfreq(dev, info, freq, extra); case NL80211_IFTYPE_ADHOC: - ret = cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); - break; + return cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); case NL80211_IFTYPE_MONITOR: - if (!rdev->ops->get_channel) { - ret = -EINVAL; - break; - } + if (!rdev->ops->get_channel) + return -EINVAL; ret = rdev_get_channel(rdev, wdev, 0, &chandef); if (ret) - break; + return ret; freq->m = chandef.chan->center_freq; freq->e = 6; - ret = 0; - break; + return ret; default: - ret = -EINVAL; - break; + return -EINVAL; } - - wiphy_unlock(&rdev->wiphy); - - return ret; } static int cfg80211_wext_siwtxpower(struct net_device *dev, @@ -900,7 +847,6 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); enum nl80211_tx_power_setting type; int dbm = 0; - int ret; if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) return -EINVAL; @@ -942,11 +888,9 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev, return 0; } - wiphy_lock(&rdev->wiphy); - ret = rdev_set_tx_power(rdev, wdev, type, DBM_TO_MBM(dbm)); - wiphy_unlock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); - return ret; + return rdev_set_tx_power(rdev, wdev, type, DBM_TO_MBM(dbm)); } static int cfg80211_wext_giwtxpower(struct net_device *dev, @@ -965,9 +909,9 @@ static int cfg80211_wext_giwtxpower(struct net_device *dev, if (!rdev->ops->get_tx_power) return -EOPNOTSUPP; - wiphy_lock(&rdev->wiphy); - err = rdev_get_tx_power(rdev, wdev, &val); - wiphy_unlock(&rdev->wiphy); + scoped_guard(wiphy, &rdev->wiphy) { + err = rdev_get_tx_power(rdev, wdev, 0, &val); + } if (err) return err; @@ -1209,9 +1153,9 @@ static int cfg80211_wext_siwpower(struct net_device *dev, timeout = wrq->value / 1000; } - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + err = rdev_set_power_mgmt(rdev, dev, ps, timeout); - wiphy_unlock(&rdev->wiphy); if (err) return err; @@ -1244,8 +1188,8 @@ static int cfg80211_wext_siwrate(struct net_device *dev, struct cfg80211_bitrate_mask mask; u32 fixed, maxrate; struct ieee80211_supported_band *sband; - int band, ridx, ret; bool match = false; + int band, ridx; if (!rdev->ops->set_bitrate_mask) return -EOPNOTSUPP; @@ -1283,14 +1227,12 @@ static int cfg80211_wext_siwrate(struct net_device *dev, if (!match) return -EINVAL; - wiphy_lock(&rdev->wiphy); - if (dev->ieee80211_ptr->valid_links) - ret = -EOPNOTSUPP; - else - ret = rdev_set_bitrate_mask(rdev, dev, 0, NULL, &mask); - wiphy_unlock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); - return ret; + if (dev->ieee80211_ptr->valid_links) + return -EOPNOTSUPP; + + return rdev_set_bitrate_mask(rdev, dev, 0, NULL, &mask); } static int cfg80211_wext_giwrate(struct net_device *dev, @@ -1319,9 +1261,9 @@ static int cfg80211_wext_giwrate(struct net_device *dev, if (err) return err; - wiphy_lock(&rdev->wiphy); - err = rdev_get_station(rdev, dev, addr, &sinfo); - wiphy_unlock(&rdev->wiphy); + scoped_guard(wiphy, &rdev->wiphy) { + err = rdev_get_station(rdev, dev, addr, &sinfo); + } if (err) return err; @@ -1420,23 +1362,17 @@ static int cfg80211_wext_siwap(struct net_device *dev, struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - int ret; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - ret = cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); - break; + return cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); case NL80211_IFTYPE_STATION: - ret = cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra); - break; + return cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra); default: - ret = -EOPNOTSUPP; - break; + return -EOPNOTSUPP; } - wiphy_unlock(&rdev->wiphy); - - return ret; } static int cfg80211_wext_giwap(struct net_device *dev, @@ -1446,23 +1382,17 @@ static int cfg80211_wext_giwap(struct net_device *dev, struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - int ret; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - ret = cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); - break; + return cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); case NL80211_IFTYPE_STATION: - ret = cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra); - break; + return cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra); default: - ret = -EOPNOTSUPP; - break; + return -EOPNOTSUPP; } - wiphy_unlock(&rdev->wiphy); - - return ret; } static int cfg80211_wext_siwessid(struct net_device *dev, @@ -1472,23 +1402,17 @@ static int cfg80211_wext_siwessid(struct net_device *dev, struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - int ret; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - ret = cfg80211_ibss_wext_siwessid(dev, info, data, ssid); - break; + return cfg80211_ibss_wext_siwessid(dev, info, data, ssid); case NL80211_IFTYPE_STATION: - ret = cfg80211_mgd_wext_siwessid(dev, info, data, ssid); - break; + return cfg80211_mgd_wext_siwessid(dev, info, data, ssid); default: - ret = -EOPNOTSUPP; - break; + return -EOPNOTSUPP; } - wiphy_unlock(&rdev->wiphy); - - return ret; } static int cfg80211_wext_giwessid(struct net_device *dev, @@ -1498,26 +1422,20 @@ static int cfg80211_wext_giwessid(struct net_device *dev, struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - int ret; data->flags = 0; data->length = 0; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - ret = cfg80211_ibss_wext_giwessid(dev, info, data, ssid); - break; + return cfg80211_ibss_wext_giwessid(dev, info, data, ssid); case NL80211_IFTYPE_STATION: - ret = cfg80211_mgd_wext_giwessid(dev, info, data, ssid); - break; + return cfg80211_mgd_wext_giwessid(dev, info, data, ssid); default: - ret = -EOPNOTSUPP; - break; + return -EOPNOTSUPP; } - wiphy_unlock(&rdev->wiphy); - - return ret; } static int cfg80211_wext_siwpmksa(struct net_device *dev, @@ -1528,7 +1446,6 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmksa cfg_pmksa; struct iw_pmksa *pmksa = (struct iw_pmksa *)extra; - int ret; memset(&cfg_pmksa, 0, sizeof(struct cfg80211_pmksa)); @@ -1538,39 +1455,27 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev, cfg_pmksa.bssid = pmksa->bssid.sa_data; cfg_pmksa.pmkid = pmksa->pmkid; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + switch (pmksa->cmd) { case IW_PMKSA_ADD: - if (!rdev->ops->set_pmksa) { - ret = -EOPNOTSUPP; - break; - } + if (!rdev->ops->set_pmksa) + return -EOPNOTSUPP; - ret = rdev_set_pmksa(rdev, dev, &cfg_pmksa); - break; + return rdev_set_pmksa(rdev, dev, &cfg_pmksa); case IW_PMKSA_REMOVE: - if (!rdev->ops->del_pmksa) { - ret = -EOPNOTSUPP; - break; - } + if (!rdev->ops->del_pmksa) + return -EOPNOTSUPP; - ret = rdev_del_pmksa(rdev, dev, &cfg_pmksa); - break; + return rdev_del_pmksa(rdev, dev, &cfg_pmksa); case IW_PMKSA_FLUSH: - if (!rdev->ops->flush_pmksa) { - ret = -EOPNOTSUPP; - break; - } + if (!rdev->ops->flush_pmksa) + return -EOPNOTSUPP; - ret = rdev_flush_pmksa(rdev, dev); - break; + return rdev_flush_pmksa(rdev, dev); default: - ret = -EOPNOTSUPP; - break; + return -EOPNOTSUPP; } - wiphy_unlock(&rdev->wiphy); - - return ret; } static const iw_handler cfg80211_handlers[] = { diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 3bb04b05c5ce..bea70eb6f034 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -640,10 +640,8 @@ EXPORT_SYMBOL(wireless_send_event); #ifdef CONFIG_CFG80211_WEXT static void wireless_warn_cfg80211_wext(void) { - char name[sizeof(current->comm)]; - pr_warn_once("warning: `%s' uses wireless extensions which will stop working for Wi-Fi 7 hardware; use nl80211\n", - get_task_comm(name, current)); + current->comm); } #endif diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 8edd9ada69d0..573b6b15a446 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -302,8 +302,8 @@ int cfg80211_wext_siwgenie(struct net_device *dev, struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + int ie_len = data->length; u8 *ie = extra; - int ie_len = data->length, err; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; @@ -311,39 +311,31 @@ int cfg80211_wext_siwgenie(struct net_device *dev, if (!ie_len) ie = NULL; - wiphy_lock(wdev->wiphy); + guard(wiphy)(wdev->wiphy); /* no change */ - err = 0; if (wdev->wext.ie_len == ie_len && memcmp(wdev->wext.ie, ie, ie_len) == 0) - goto out; + return 0; if (ie_len) { ie = kmemdup(extra, ie_len, GFP_KERNEL); - if (!ie) { - err = -ENOMEM; - goto out; - } - } else + if (!ie) + return -ENOMEM; + } else { ie = NULL; + } kfree(wdev->wext.ie); wdev->wext.ie = ie; wdev->wext.ie_len = ie_len; - if (wdev->conn) { - err = cfg80211_disconnect(rdev, dev, - WLAN_REASON_DEAUTH_LEAVING, false); - if (err) - goto out; - } + if (wdev->conn) + return cfg80211_disconnect(rdev, dev, + WLAN_REASON_DEAUTH_LEAVING, false); /* userspace better not think we'll reconnect */ - err = 0; - out: - wiphy_unlock(wdev->wiphy); - return err; + return 0; } int cfg80211_wext_siwmlme(struct net_device *dev, @@ -353,7 +345,6 @@ int cfg80211_wext_siwmlme(struct net_device *dev, struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_mlme *mlme = (struct iw_mlme *)extra; struct cfg80211_registered_device *rdev; - int err; if (!wdev) return -EOPNOTSUPP; @@ -366,17 +357,13 @@ int cfg80211_wext_siwmlme(struct net_device *dev, if (mlme->addr.sa_family != ARPHRD_ETHER) return -EINVAL; - wiphy_lock(&rdev->wiphy); + guard(wiphy)(&rdev->wiphy); + switch (mlme->cmd) { case IW_MLME_DEAUTH: case IW_MLME_DISASSOC: - err = cfg80211_disconnect(rdev, dev, mlme->reason_code, true); - break; + return cfg80211_disconnect(rdev, dev, mlme->reason_code, true); default: - err = -EOPNOTSUPP; - break; + return -EOPNOTSUPP; } - wiphy_unlock(&rdev->wiphy); - - return err; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 3fa70286c846..89d2bef96469 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -322,7 +322,6 @@ static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) return -ENOSPC; } - sk_mark_napi_id_once_xdp(&xs->sk, xdp); return 0; } @@ -908,11 +907,8 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len if (unlikely(!xs->tx)) return -ENOBUFS; - if (sk_can_busy_loop(sk)) { - if (xs->zc) - __sk_mark_napi_id_once(sk, xsk_pool_get_napi_id(xs->pool)); + if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ - } if (xs->zc && xsk_no_wakeup(sk)) return 0; @@ -1298,6 +1294,14 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xs->queue_id = qid; xp_add_xsk(xs->pool, xs); + if (xs->zc && qid < dev->real_num_rx_queues) { + struct netdev_rx_queue *rxq; + + rxq = __netif_get_rx_queue(dev, qid); + if (rxq->napi) + __sk_mark_napi_id_once(sk, rxq->napi->napi_id); + } + out_unlock: if (err) { dev_put(dev); diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index d7b16f2c23e9..f0157702718f 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -135,6 +135,22 @@ config NET_KEY_MIGRATE If unsure, say N. +config XFRM_IPTFS + tristate "IPsec IP-TFS/AGGFRAG (RFC 9347) encapsulation support" + depends on XFRM + help + Information on the IP-TFS/AGGFRAG encapsulation can be found + in RFC 9347. This feature supports demand driven (i.e., + non-constant send rate) IP-TFS to take advantage of the + AGGFRAG ESP payload encapsulation. This payload type + supports aggregation and fragmentation of the inner IP + packet stream which in turn yields higher small-packet + bandwidth as well as reducing MTU/PMTU issues. Congestion + control is unimplementated as the send rate is demand driven + rather than constant. + + If unsure, say N. + config XFRM_ESPINTCP bool diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 512e0b2f8514..5a1787587cb3 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -21,5 +21,6 @@ obj-$(CONFIG_XFRM_USER) += xfrm_user.o obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o +obj-$(CONFIG_XFRM_IPTFS) += xfrm_iptfs.o obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o obj-$(CONFIG_DEBUG_INFO_BTF) += xfrm_state_bpf.o diff --git a/net/xfrm/trace_iptfs.h b/net/xfrm/trace_iptfs.h new file mode 100644 index 000000000000..74391ba24445 --- /dev/null +++ b/net/xfrm/trace_iptfs.h @@ -0,0 +1,218 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* xfrm_trace_iptfs.h + * + * August 12 2023, Christian Hopps + * + * Copyright (c) 2023, LabN Consulting, L.L.C. + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM iptfs + +#if !defined(_TRACE_IPTFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IPTFS_H + +#include +#include +#include +#include + +struct xfrm_iptfs_data; + +TRACE_EVENT(iptfs_egress_recv, + TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs, u16 blkoff), + TP_ARGS(skb, xtfs, blkoff), + TP_STRUCT__entry(__field(struct sk_buff *, skb) + __field(void *, head) + __field(void *, head_pg_addr) + __field(void *, pg0addr) + __field(u32, skb_len) + __field(u32, data_len) + __field(u32, headroom) + __field(u32, tailroom) + __field(u32, tail) + __field(u32, end) + __field(u32, pg0off) + __field(u8, head_frag) + __field(u8, frag_list) + __field(u8, nr_frags) + __field(u16, blkoff)), + TP_fast_assign(__entry->skb = skb; + __entry->head = skb->head; + __entry->skb_len = skb->len; + __entry->data_len = skb->data_len; + __entry->headroom = skb_headroom(skb); + __entry->tailroom = skb_tailroom(skb); + __entry->tail = (u32)skb->tail; + __entry->end = (u32)skb->end; + __entry->head_frag = skb->head_frag; + __entry->frag_list = (bool)skb_shinfo(skb)->frag_list; + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + __entry->blkoff = blkoff; + __entry->head_pg_addr = page_address(virt_to_head_page(skb->head)); + __entry->pg0addr = (__entry->nr_frags + ? page_address(netmem_to_page(skb_shinfo(skb)->frags[0].netmem)) + : NULL); + __entry->pg0off = (__entry->nr_frags + ? skb_shinfo(skb)->frags[0].offset + : 0); + ), + TP_printk("EGRESS: skb=%p len=%u data_len=%u headroom=%u head_frag=%u frag_list=%u nr_frags=%u blkoff=%u\n\t\ttailroom=%u tail=%u end=%u head=%p hdpgaddr=%p pg0->addr=%p pg0->data=%p pg0->off=%u", + __entry->skb, __entry->skb_len, __entry->data_len, __entry->headroom, + __entry->head_frag, __entry->frag_list, __entry->nr_frags, __entry->blkoff, + __entry->tailroom, __entry->tail, __entry->end, __entry->head, + __entry->head_pg_addr, __entry->pg0addr, __entry->pg0addr + __entry->pg0off, + __entry->pg0off) + ) + +DECLARE_EVENT_CLASS(iptfs_ingress_preq_event, + TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs, + u32 pmtu, u8 was_gso), + TP_ARGS(skb, xtfs, pmtu, was_gso), + TP_STRUCT__entry(__field(struct sk_buff *, skb) + __field(u32, skb_len) + __field(u32, data_len) + __field(u32, pmtu) + __field(u32, queue_size) + __field(u32, proto_seq) + __field(u8, proto) + __field(u8, was_gso) + ), + TP_fast_assign(__entry->skb = skb; + __entry->skb_len = skb->len; + __entry->data_len = skb->data_len; + __entry->queue_size = + xtfs->cfg.max_queue_size - xtfs->queue_size; + __entry->proto = __trace_ip_proto(ip_hdr(skb)); + __entry->proto_seq = __trace_ip_proto_seq(ip_hdr(skb)); + __entry->pmtu = pmtu; + __entry->was_gso = was_gso; + ), + TP_printk("INGRPREQ: skb=%p len=%u data_len=%u qsize=%u proto=%u proto_seq=%u pmtu=%u was_gso=%u", + __entry->skb, __entry->skb_len, __entry->data_len, + __entry->queue_size, __entry->proto, __entry->proto_seq, + __entry->pmtu, __entry->was_gso)); + +DEFINE_EVENT(iptfs_ingress_preq_event, iptfs_enqueue, + TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs, u32 pmtu, u8 was_gso), + TP_ARGS(skb, xtfs, pmtu, was_gso)); + +DEFINE_EVENT(iptfs_ingress_preq_event, iptfs_no_queue_space, + TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs, u32 pmtu, u8 was_gso), + TP_ARGS(skb, xtfs, pmtu, was_gso)); + +DEFINE_EVENT(iptfs_ingress_preq_event, iptfs_too_big, + TP_PROTO(struct sk_buff *skb, struct xfrm_iptfs_data *xtfs, u32 pmtu, u8 was_gso), + TP_ARGS(skb, xtfs, pmtu, was_gso)); + +DECLARE_EVENT_CLASS(iptfs_ingress_postq_event, + TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff, struct iphdr *iph), + TP_ARGS(skb, mtu, blkoff, iph), + TP_STRUCT__entry(__field(struct sk_buff *, skb) + __field(u32, skb_len) + __field(u32, data_len) + __field(u32, mtu) + __field(u32, proto_seq) + __field(u16, blkoff) + __field(u8, proto)), + TP_fast_assign(__entry->skb = skb; + __entry->skb_len = skb->len; + __entry->data_len = skb->data_len; + __entry->mtu = mtu; + __entry->blkoff = blkoff; + __entry->proto = iph ? __trace_ip_proto(iph) : 0; + __entry->proto_seq = iph ? __trace_ip_proto_seq(iph) : 0; + ), + TP_printk("INGRPSTQ: skb=%p len=%u data_len=%u mtu=%u blkoff=%u proto=%u proto_seq=%u", + __entry->skb, __entry->skb_len, __entry->data_len, __entry->mtu, + __entry->blkoff, __entry->proto, __entry->proto_seq)); + +DEFINE_EVENT(iptfs_ingress_postq_event, iptfs_first_dequeue, + TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff, + struct iphdr *iph), + TP_ARGS(skb, mtu, blkoff, iph)); + +DEFINE_EVENT(iptfs_ingress_postq_event, iptfs_first_fragmenting, + TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff, + struct iphdr *iph), + TP_ARGS(skb, mtu, blkoff, iph)); + +DEFINE_EVENT(iptfs_ingress_postq_event, iptfs_first_final_fragment, + TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff, + struct iphdr *iph), + TP_ARGS(skb, mtu, blkoff, iph)); + +DEFINE_EVENT(iptfs_ingress_postq_event, iptfs_first_toobig, + TP_PROTO(struct sk_buff *skb, u32 mtu, u16 blkoff, + struct iphdr *iph), + TP_ARGS(skb, mtu, blkoff, iph)); + +TRACE_EVENT(iptfs_ingress_nth_peek, + TP_PROTO(struct sk_buff *skb, u32 remaining), + TP_ARGS(skb, remaining), + TP_STRUCT__entry(__field(struct sk_buff *, skb) + __field(u32, skb_len) + __field(u32, remaining)), + TP_fast_assign(__entry->skb = skb; + __entry->skb_len = skb->len; + __entry->remaining = remaining; + ), + TP_printk("INGRPSTQ: NTHPEEK: skb=%p len=%u remaining=%u", + __entry->skb, __entry->skb_len, __entry->remaining)); + +TRACE_EVENT(iptfs_ingress_nth_add, TP_PROTO(struct sk_buff *skb, u8 share_ok), + TP_ARGS(skb, share_ok), + TP_STRUCT__entry(__field(struct sk_buff *, skb) + __field(u32, skb_len) + __field(u32, data_len) + __field(u8, share_ok) + __field(u8, head_frag) + __field(u8, pp_recycle) + __field(u8, cloned) + __field(u8, shared) + __field(u8, nr_frags) + __field(u8, frag_list) + ), + TP_fast_assign(__entry->skb = skb; + __entry->skb_len = skb->len; + __entry->data_len = skb->data_len; + __entry->share_ok = share_ok; + __entry->head_frag = skb->head_frag; + __entry->pp_recycle = skb->pp_recycle; + __entry->cloned = skb_cloned(skb); + __entry->shared = skb_shared(skb); + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + __entry->frag_list = (bool)skb_shinfo(skb)->frag_list; + ), + TP_printk("INGRPSTQ: NTHADD: skb=%p len=%u data_len=%u share_ok=%u head_frag=%u pp_recycle=%u cloned=%u shared=%u nr_frags=%u frag_list=%u", + __entry->skb, __entry->skb_len, __entry->data_len, __entry->share_ok, + __entry->head_frag, __entry->pp_recycle, __entry->cloned, __entry->shared, + __entry->nr_frags, __entry->frag_list)); + +DECLARE_EVENT_CLASS(iptfs_timer_event, + TP_PROTO(struct xfrm_iptfs_data *xtfs, u64 time_val), + TP_ARGS(xtfs, time_val), + TP_STRUCT__entry(__field(u64, time_val) + __field(u64, set_time)), + TP_fast_assign(__entry->time_val = time_val; + __entry->set_time = xtfs->iptfs_settime; + ), + TP_printk("TIMER: set_time=%llu time_val=%llu", + __entry->set_time, __entry->time_val)); + +DEFINE_EVENT(iptfs_timer_event, iptfs_timer_start, + TP_PROTO(struct xfrm_iptfs_data *xtfs, u64 time_val), + TP_ARGS(xtfs, time_val)); + +DEFINE_EVENT(iptfs_timer_event, iptfs_timer_expire, + TP_PROTO(struct xfrm_iptfs_data *xtfs, u64 time_val), + TP_ARGS(xtfs, time_val)); + +#endif /* _TRACE_IPTFS_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ../../net/xfrm +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace_iptfs +#include diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 5b9ee63e30b6..b8d2e6930041 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -284,9 +284,15 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_SA_DIR: case XFRMA_NAT_KEEPALIVE_INTERVAL: case XFRMA_SA_PCPU: + case XFRMA_IPTFS_DROP_TIME: + case XFRMA_IPTFS_REORDER_WINDOW: + case XFRMA_IPTFS_DONT_FRAG: + case XFRMA_IPTFS_INIT_DELAY: + case XFRMA_IPTFS_MAX_QSIZE: + case XFRMA_IPTFS_PKT_SIZE: return xfrm_nla_cpy(dst, src, nla_len(src)); default: - BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_PCPU); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_IPTFS_PKT_SIZE); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } @@ -441,7 +447,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, int err; if (type > XFRMA_MAX) { - BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_PCPU); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_IPTFS_PKT_SIZE); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index b33c4591e09a..d1fa94e52cea 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -42,7 +42,8 @@ static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb, skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); - pskb_pull(skb, skb->mac_len + x->props.header_len); + pskb_pull(skb, + skb->mac_len + x->props.header_len - x->props.enc_hdr_len); } static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb, @@ -68,6 +69,7 @@ static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb, static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) { switch (x->outer_mode.encap) { + case XFRM_MODE_IPTFS: case XFRM_MODE_TUNNEL: if (x->outer_mode.family == AF_INET) return __xfrm_mode_tunnel_prep(x, skb, diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 841a60a6fbfe..7e6a71b9d6a3 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -48,7 +48,7 @@ static DEFINE_SPINLOCK(xfrm_input_afinfo_lock); static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[2][AF_INET6 + 1]; static struct gro_cells gro_cells; -static struct net_device xfrm_napi_dev; +static struct net_device *xfrm_napi_dev; static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet); @@ -446,6 +446,9 @@ static int xfrm_inner_mode_input(struct xfrm_state *x, WARN_ON_ONCE(1); break; default: + if (x->mode_cbs && x->mode_cbs->input) + return x->mode_cbs->input(x, skb); + WARN_ON_ONCE(1); break; } @@ -453,6 +456,10 @@ static int xfrm_inner_mode_input(struct xfrm_state *x, return -EOPNOTSUPP; } +/* NOTE: encap_type - In addition to the normal (non-negative) values for + * encap_type, a negative value of -1 or -2 can be used to resume/restart this + * function after a previous invocation early terminated for async operation. + */ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { const struct xfrm_state_afinfo *afinfo; @@ -489,6 +496,10 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) family = x->props.family; + /* An encap_type of -2 indicates reconstructed inner packet */ + if (encap_type == -2) + goto resume_decapped; + /* An encap_type of -1 indicates async resumption. */ if (encap_type == -1) { async = 1; @@ -679,11 +690,14 @@ resume: XFRM_MODE_SKB_CB(skb)->protocol = nexthdr; - if (xfrm_inner_mode_input(x, skb)) { + err = xfrm_inner_mode_input(x, skb); + if (err == -EINPROGRESS) + return 0; + else if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } - +resume_decapped: if (x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL) { decaps = 1; break; @@ -811,8 +825,11 @@ void __init xfrm_input_init(void) int err; int i; - init_dummy_netdev(&xfrm_napi_dev); - err = gro_cells_init(&gro_cells, &xfrm_napi_dev); + xfrm_napi_dev = alloc_netdev_dummy(0); + if (!xfrm_napi_dev) + panic("Failed to allocate XFRM dummy netdev\n"); + + err = gro_cells_init(&gro_cells, xfrm_napi_dev); if (err) gro_cells.cells = NULL; diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 98f1e2b67c76..c397eb99d867 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -506,7 +506,7 @@ xmit: skb_dst_set(skb, dst); skb->dev = tdev; - err = dst_output(xi->net, skb->sk, skb); + err = dst_output(xi->net, skb_to_full_sk(skb), skb); if (net_xmit_eval(err) == 0) { dev_sw_netstats_tx_add(dev, 1, length); } else { diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c new file mode 100644 index 000000000000..755f1eea8bfa --- /dev/null +++ b/net/xfrm/xfrm_iptfs.c @@ -0,0 +1,2764 @@ +// SPDX-License-Identifier: GPL-2.0 +/* xfrm_iptfs: IPTFS encapsulation support + * + * April 21 2022, Christian Hopps + * + * Copyright (c) 2022, LabN Consulting, L.L.C. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "xfrm_inout.h" +#include "trace_iptfs.h" + +/* IPTFS encap (header) values. */ +#define IPTFS_SUBTYPE_BASIC 0 +#define IPTFS_SUBTYPE_CC 1 + +/* ----------------------------------------------- */ +/* IP-TFS default SA values (tunnel egress/dir-in) */ +/* ----------------------------------------------- */ + +/** + * define IPTFS_DEFAULT_DROP_TIME_USECS - default drop time + * + * The default IPTFS drop time in microseconds. The drop time is the amount of + * time before a missing out-of-order IPTFS tunnel packet is considered lost. + * See also the reorder window. + * + * Default 1s. + */ +#define IPTFS_DEFAULT_DROP_TIME_USECS 1000000 + +/** + * define IPTFS_DEFAULT_REORDER_WINDOW - default reorder window size + * + * The default IPTFS reorder window size. The reorder window size dictates the + * maximum number of IPTFS tunnel packets in a sequence that may arrive out of + * order. + * + * Default 3. (tcp folks suggested) + */ +#define IPTFS_DEFAULT_REORDER_WINDOW 3 + +/* ------------------------------------------------ */ +/* IPTFS default SA values (tunnel ingress/dir-out) */ +/* ------------------------------------------------ */ + +/** + * define IPTFS_DEFAULT_INIT_DELAY_USECS - default initial output delay + * + * The initial output delay is the amount of time prior to servicing the output + * queue after queueing the first packet on said queue. This applies anytime the + * output queue was previously empty. + * + * Default 0. + */ +#define IPTFS_DEFAULT_INIT_DELAY_USECS 0 + +/** + * define IPTFS_DEFAULT_MAX_QUEUE_SIZE - default max output queue size. + * + * The default IPTFS max output queue size in octets. The output queue is where + * received packets destined for output over an IPTFS tunnel are stored prior to + * being output in aggregated/fragmented form over the IPTFS tunnel. + * + * Default 1M. + */ +#define IPTFS_DEFAULT_MAX_QUEUE_SIZE (1024 * 10240) + +/* Assumed: skb->head is cache aligned. + * + * L2 Header resv: Arrange for cacheline to start at skb->data - 16 to keep the + * to-be-pushed L2 header in the same cacheline as resulting `skb->data` (i.e., + * the L3 header). If cacheline size is > 64 then skb->data + pushed L2 will all + * be in a single cacheline if we simply reserve 64 bytes. + * + * L3 Header resv: For L3+L2 headers (i.e., skb->data points at the IPTFS payload) + * we want `skb->data` to be cacheline aligned and all pushed L2L3 headers will + * be in their own cacheline[s]. 128 works for cachelins up to 128 bytes, for + * any larger cacheline sizes the pushed headers will simply share the cacheline + * with the start of the IPTFS payload (skb->data). + */ +#define XFRM_IPTFS_MIN_L3HEADROOM 128 +#define XFRM_IPTFS_MIN_L2HEADROOM (L1_CACHE_BYTES > 64 ? 64 : 64 + 16) + +/* Min to try to share outer iptfs skb data vs copying into new skb */ +#define IPTFS_PKT_SHARE_MIN 129 + +#define NSECS_IN_USEC 1000 + +#define IPTFS_HRTIMER_MODE HRTIMER_MODE_REL_SOFT + +/** + * struct xfrm_iptfs_config - configuration for the IPTFS tunnel. + * @pkt_size: size of the outer IP packet. 0 to use interface and MTU discovery, + * otherwise the user specified value. + * @max_queue_size: The maximum number of octets allowed to be queued to be sent + * over the IPTFS SA. The queue size is measured as the size of all the + * packets enqueued. + * @reorder_win_size: the number slots in the reorder window, thus the number of + * packets that may arrive out of order. + * @dont_frag: true to inhibit fragmenting across IPTFS outer packets. + */ +struct xfrm_iptfs_config { + u32 pkt_size; /* outer_packet_size or 0 */ + u32 max_queue_size; /* octets */ + u16 reorder_win_size; + u8 dont_frag : 1; +}; + +struct skb_wseq { + struct sk_buff *skb; + u64 drop_time; +}; + +/** + * struct xfrm_iptfs_data - mode specific xfrm state. + * @cfg: IPTFS tunnel config. + * @x: owning SA (xfrm_state). + * @queue: queued user packets to send. + * @queue_size: number of octets on queue (sum of packet sizes). + * @ecn_queue_size: octets above with ECN mark. + * @init_delay_ns: nanoseconds to wait to send initial IPTFS packet. + * @iptfs_timer: output timer. + * @iptfs_settime: time the output timer was set. + * @payload_mtu: max payload size. + * @w_seq_set: true after first seq received. + * @w_wantseq: waiting for this seq number as next to process (in order). + * @w_saved: the saved buf array (reorder window). + * @w_savedlen: the saved len (not size). + * @drop_lock: lock to protect reorder queue. + * @drop_timer: timer for considering next packet lost. + * @drop_time_ns: timer intervan in nanoseconds. + * @ra_newskb: new pkt being reassembled. + * @ra_wantseq: expected next sequence for reassembly. + * @ra_runt: last pkt bytes from very end of last skb. + * @ra_runtlen: size of ra_runt. + */ +struct xfrm_iptfs_data { + struct xfrm_iptfs_config cfg; + + /* Ingress User Input */ + struct xfrm_state *x; /* owning state */ + struct sk_buff_head queue; /* output queue */ + + u32 queue_size; /* octets */ + u32 ecn_queue_size; /* octets above which ECN mark */ + u64 init_delay_ns; /* nanoseconds */ + struct hrtimer iptfs_timer; /* output timer */ + time64_t iptfs_settime; /* time timer was set */ + u32 payload_mtu; /* max payload size */ + + /* Tunnel input reordering */ + bool w_seq_set; /* true after first seq received */ + u64 w_wantseq; /* expected next sequence */ + struct skb_wseq *w_saved; /* the saved buf array */ + u32 w_savedlen; /* the saved len (not size) */ + spinlock_t drop_lock; + struct hrtimer drop_timer; + u64 drop_time_ns; + + /* Tunnel input reassembly */ + struct sk_buff *ra_newskb; /* new pkt being reassembled */ + u64 ra_wantseq; /* expected next sequence */ + u8 ra_runt[6]; /* last pkt bytes from last skb */ + u8 ra_runtlen; /* count of ra_runt */ +}; + +static u32 __iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu); +static enum hrtimer_restart iptfs_delay_timer(struct hrtimer *me); +static enum hrtimer_restart iptfs_drop_timer(struct hrtimer *me); + +/* ================= */ +/* Utility Functions */ +/* ================= */ + +#ifdef TRACEPOINTS_ENABLED +static u32 __trace_ip_proto(struct iphdr *iph) +{ + if (iph->version == 4) + return iph->protocol; + return ((struct ipv6hdr *)iph)->nexthdr; +} + +static u32 __trace_ip_proto_seq(struct iphdr *iph) +{ + void *nexthdr; + u32 protocol = 0; + + if (iph->version == 4) { + nexthdr = (void *)(iph + 1); + protocol = iph->protocol; + } else if (iph->version == 6) { + nexthdr = (void *)(((struct ipv6hdr *)(iph)) + 1); + protocol = ((struct ipv6hdr *)(iph))->nexthdr; + } + switch (protocol) { + case IPPROTO_ICMP: + return ntohs(((struct icmphdr *)nexthdr)->un.echo.sequence); + case IPPROTO_ICMPV6: + return ntohs(((struct icmp6hdr *)nexthdr)->icmp6_sequence); + case IPPROTO_TCP: + return ntohl(((struct tcphdr *)nexthdr)->seq); + case IPPROTO_UDP: + return ntohs(((struct udphdr *)nexthdr)->source); + default: + return 0; + } +} +#endif /*TRACEPOINTS_ENABLED*/ + +static u64 __esp_seq(struct sk_buff *skb) +{ + u64 seq = ntohl(XFRM_SKB_CB(skb)->seq.input.low); + + return seq | (u64)ntohl(XFRM_SKB_CB(skb)->seq.input.hi) << 32; +} + +/* ======================= */ +/* IPTFS SK_BUFF Functions */ +/* ======================= */ + +/** + * iptfs_alloc_skb() - Allocate a new `skb`. + * @tpl: the skb to copy required meta-data from. + * @len: the linear length of the head data, zero is fine. + * @l3resv: true if skb reserve needs to support pushing L3 headers + * + * A new `skb` is allocated and required meta-data is copied from `tpl`, the + * head data is sized to `len` + reserved space set according to the @l3resv + * boolean. + * + * When @l3resv is false, resv is XFRM_IPTFS_MIN_L2HEADROOM which arranges for + * `skb->data - 16` which is a good guess for good cache alignment (placing the + * to be pushed L2 header at the start of a cacheline. + * + * Otherwise, @l3resv is true and resv is set to the correct reserved space for + * dst->dev plus the calculated L3 overhead for the xfrm dst or + * XFRM_IPTFS_MIN_L3HEADROOM whichever is larger. This is then cache aligned so + * that all the headers will commonly fall in a cacheline when possible. + * + * l3resv=true is used on tunnel ingress (tx), because we need to reserve for + * the new IPTFS packet (i.e., L2+L3 headers). On tunnel egress (rx) the data + * being copied into the skb includes the user L3 headers already so we only + * need to reserve for L2. + * + * Return: the new skb or NULL. + */ +static struct sk_buff *iptfs_alloc_skb(struct sk_buff *tpl, u32 len, bool l3resv) +{ + struct sk_buff *skb; + u32 resv; + + if (!l3resv) { + resv = XFRM_IPTFS_MIN_L2HEADROOM; + } else { + struct dst_entry *dst = skb_dst(tpl); + + resv = LL_RESERVED_SPACE(dst->dev) + dst->header_len; + resv = max(resv, XFRM_IPTFS_MIN_L3HEADROOM); + resv = L1_CACHE_ALIGN(resv); + } + + skb = alloc_skb(len + resv, GFP_ATOMIC | __GFP_NOWARN); + if (!skb) + return NULL; + + skb_reserve(skb, resv); + + if (!l3resv) { + /* xfrm_input resume needs dev and xfrm ext from tunnel pkt */ + skb->dev = tpl->dev; + __skb_ext_copy(skb, tpl); + } + + /* dropped by xfrm_input, used by xfrm_output */ + skb_dst_copy(skb, tpl); + + return skb; +} + +/** + * iptfs_skb_head_to_frag() - initialize a skb_frag_t based on skb head data + * @skb: skb with the head data + * @frag: frag to initialize + */ +static void iptfs_skb_head_to_frag(const struct sk_buff *skb, skb_frag_t *frag) +{ + struct page *page = virt_to_head_page(skb->data); + unsigned char *addr = (unsigned char *)page_address(page); + + skb_frag_fill_page_desc(frag, page, skb->data - addr, skb_headlen(skb)); +} + +/** + * struct iptfs_skb_frag_walk - use to track a walk through fragments + * @fragi: current fragment index + * @past: length of data in fragments before @fragi + * @total: length of data in all fragments + * @nr_frags: number of fragments present in array + * @initial_offset: the value passed in to skb_prepare_frag_walk() + * @frags: the page fragments inc. room for head page + * @pp_recycle: copy of skb->pp_recycle + */ +struct iptfs_skb_frag_walk { + u32 fragi; + u32 past; + u32 total; + u32 nr_frags; + u32 initial_offset; + skb_frag_t frags[MAX_SKB_FRAGS + 1]; + bool pp_recycle; +}; + +/** + * iptfs_skb_prepare_frag_walk() - initialize a frag walk over an skb. + * @skb: the skb to walk. + * @initial_offset: start the walk @initial_offset into the skb. + * @walk: the walk to initialize + * + * Future calls to skb_add_frags() will expect the @offset value to be at + * least @initial_offset large. + */ +static void iptfs_skb_prepare_frag_walk(struct sk_buff *skb, u32 initial_offset, + struct iptfs_skb_frag_walk *walk) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + skb_frag_t *frag, *from; + u32 i; + + walk->initial_offset = initial_offset; + walk->fragi = 0; + walk->past = 0; + walk->total = 0; + walk->nr_frags = 0; + walk->pp_recycle = skb->pp_recycle; + + if (skb->head_frag) { + if (initial_offset >= skb_headlen(skb)) { + initial_offset -= skb_headlen(skb); + } else { + frag = &walk->frags[walk->nr_frags++]; + iptfs_skb_head_to_frag(skb, frag); + frag->offset += initial_offset; + frag->len -= initial_offset; + walk->total += frag->len; + initial_offset = 0; + } + } else { + initial_offset -= skb_headlen(skb); + } + + for (i = 0; i < shinfo->nr_frags; i++) { + from = &shinfo->frags[i]; + if (initial_offset >= from->len) { + initial_offset -= from->len; + continue; + } + frag = &walk->frags[walk->nr_frags++]; + *frag = *from; + if (initial_offset) { + frag->offset += initial_offset; + frag->len -= initial_offset; + initial_offset = 0; + } + walk->total += frag->len; + } +} + +static u32 iptfs_skb_reset_frag_walk(struct iptfs_skb_frag_walk *walk, + u32 offset) +{ + /* Adjust offset to refer to internal walk values */ + offset -= walk->initial_offset; + + /* Get to the correct fragment for offset */ + while (offset < walk->past) { + walk->past -= walk->frags[--walk->fragi].len; + if (offset >= walk->past) + break; + } + while (offset >= walk->past + walk->frags[walk->fragi].len) + walk->past += walk->frags[walk->fragi++].len; + + /* offset now relative to this current frag */ + offset -= walk->past; + return offset; +} + +/** + * iptfs_skb_can_add_frags() - check if ok to add frags from walk to skb + * @skb: skb to check for adding frags to + * @walk: the walk that will be used as source for frags. + * @offset: offset from beginning of original skb to start from. + * @len: amount of data to add frag references to in @skb. + * + * Return: true if ok to add frags. + */ +static bool iptfs_skb_can_add_frags(const struct sk_buff *skb, + struct iptfs_skb_frag_walk *walk, + u32 offset, u32 len) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + u32 fragi, nr_frags, fraglen; + + if (skb_has_frag_list(skb) || skb->pp_recycle != walk->pp_recycle) + return false; + + /* Make offset relative to current frag after setting that */ + offset = iptfs_skb_reset_frag_walk(walk, offset); + + /* Verify we have array space for the fragments we need to add */ + fragi = walk->fragi; + nr_frags = shinfo->nr_frags; + while (len && fragi < walk->nr_frags) { + skb_frag_t *frag = &walk->frags[fragi]; + + fraglen = frag->len; + if (offset) { + fraglen -= offset; + offset = 0; + } + if (++nr_frags > MAX_SKB_FRAGS) + return false; + if (len <= fraglen) + return true; + len -= fraglen; + fragi++; + } + /* We may not copy all @len but what we have will fit. */ + return true; +} + +/** + * iptfs_skb_add_frags() - add a range of fragment references into an skb + * @skb: skb to add references into + * @walk: the walk to add referenced fragments from. + * @offset: offset from beginning of original skb to start from. + * @len: amount of data to add frag references to in @skb. + * + * iptfs_skb_can_add_frags() should be called before this function to verify + * that the destination @skb is compatible with the walk and has space in the + * array for the to be added frag references. + * + * Return: The number of bytes not added to @skb b/c we reached the end of the + * walk before adding all of @len. + */ +static int iptfs_skb_add_frags(struct sk_buff *skb, + struct iptfs_skb_frag_walk *walk, u32 offset, + u32 len) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + u32 fraglen; + + if (!walk->nr_frags || offset >= walk->total + walk->initial_offset) + return len; + + /* make offset relative to current frag after setting that */ + offset = iptfs_skb_reset_frag_walk(walk, offset); + + while (len && walk->fragi < walk->nr_frags) { + skb_frag_t *frag = &walk->frags[walk->fragi]; + skb_frag_t *tofrag = &shinfo->frags[shinfo->nr_frags]; + + *tofrag = *frag; + if (offset) { + tofrag->offset += offset; + tofrag->len -= offset; + offset = 0; + } + __skb_frag_ref(tofrag); + shinfo->nr_frags++; + + /* see if we are done */ + fraglen = tofrag->len; + if (len < fraglen) { + tofrag->len = len; + skb->len += len; + skb->data_len += len; + return 0; + } + /* advance to next source fragment */ + len -= fraglen; /* careful, use dst bv_len */ + skb->len += fraglen; /* careful, " " " */ + skb->data_len += fraglen; /* careful, " " " */ + walk->past += frag->len; /* careful, use src bv_len */ + walk->fragi++; + } + return len; +} + +/* ================================== */ +/* IPTFS Trace Event Definitions */ +/* ================================== */ + +#define CREATE_TRACE_POINTS +#include "trace_iptfs.h" + +/* ================================== */ +/* IPTFS Receiving (egress) Functions */ +/* ================================== */ + +/** + * iptfs_pskb_add_frags() - Create and add frags into a new sk_buff. + * @tpl: template to create new skb from. + * @walk: The source for fragments to add. + * @off: The offset into @walk to add frags from, also used with @st and + * @copy_len. + * @len: The length of data to add covering frags from @walk into @skb. + * This must be <= @skblen. + * @st: The sequence state to copy from into the new head skb. + * @copy_len: Copy @copy_len bytes from @st at offset @off into the new skb + * linear space. + * + * Create a new sk_buff `skb` using the template @tpl. Copy @copy_len bytes from + * @st into the new skb linear space, and then add shared fragments from the + * frag walk for the remaining @len of data (i.e., @len - @copy_len bytes). + * + * Return: The newly allocated sk_buff `skb` or NULL if an error occurs. + */ +static struct sk_buff * +iptfs_pskb_add_frags(struct sk_buff *tpl, struct iptfs_skb_frag_walk *walk, + u32 off, u32 len, struct skb_seq_state *st, u32 copy_len) +{ + struct sk_buff *skb; + + skb = iptfs_alloc_skb(tpl, copy_len, false); + if (!skb) + return NULL; + + /* this should not normally be happening */ + if (!iptfs_skb_can_add_frags(skb, walk, off + copy_len, + len - copy_len)) { + kfree_skb(skb); + return NULL; + } + + if (copy_len && + skb_copy_seq_read(st, off, skb_put(skb, copy_len), copy_len)) { + XFRM_INC_STATS(dev_net(st->root_skb->dev), + LINUX_MIB_XFRMINERROR); + kfree_skb(skb); + return NULL; + } + + iptfs_skb_add_frags(skb, walk, off + copy_len, len - copy_len); + return skb; +} + +/** + * iptfs_pskb_extract_seq() - Create and load data into a new sk_buff. + * @skblen: the total data size for `skb`. + * @st: The source for the rest of the data to copy into `skb`. + * @off: The offset into @st to copy data from. + * @len: The length of data to copy from @st into `skb`. This must be <= + * @skblen. + * + * Create a new sk_buff `skb` with @skblen of packet data space. If non-zero, + * copy @rlen bytes of @runt into `skb`. Then using seq functions copy @len + * bytes from @st into `skb` starting from @off. + * + * It is an error for @len to be greater than the amount of data left in @st. + * + * Return: The newly allocated sk_buff `skb` or NULL if an error occurs. + */ +static struct sk_buff * +iptfs_pskb_extract_seq(u32 skblen, struct skb_seq_state *st, u32 off, int len) +{ + struct sk_buff *skb = iptfs_alloc_skb(st->root_skb, skblen, false); + + if (!skb) + return NULL; + if (skb_copy_seq_read(st, off, skb_put(skb, len), len)) { + XFRM_INC_STATS(dev_net(st->root_skb->dev), LINUX_MIB_XFRMINERROR); + kfree_skb(skb); + return NULL; + } + return skb; +} + +/** + * iptfs_input_save_runt() - save data in xtfs runt space. + * @xtfs: xtfs state + * @seq: the current sequence + * @buf: packet data + * @len: length of packet data + * + * Save the small (`len`) start of a fragmented packet in `buf` in the xtfs data + * runt space. + */ +static void iptfs_input_save_runt(struct xfrm_iptfs_data *xtfs, u64 seq, + u8 *buf, int len) +{ + memcpy(xtfs->ra_runt, buf, len); + + xtfs->ra_runtlen = len; + xtfs->ra_wantseq = seq + 1; +} + +/** + * __iptfs_iphlen() - return the v4/v6 header length using packet data. + * @data: pointer at octet with version nibble + * + * The version data has been checked to be valid (i.e., either 4 or 6). + * + * Return: the IP header size based on the IP version. + */ +static u32 __iptfs_iphlen(u8 *data) +{ + struct iphdr *iph = (struct iphdr *)data; + + if (iph->version == 0x4) + return sizeof(*iph); + return sizeof(struct ipv6hdr); +} + +/** + * __iptfs_iplen() - return the v4/v6 length using packet data. + * @data: pointer to ip (v4/v6) packet header + * + * Grab the IPv4 or IPv6 length value in the start of the inner packet header + * pointed to by `data`. Assumes data len is enough for the length field only. + * + * The version data has been checked to be valid (i.e., either 4 or 6). + * + * Return: the length value. + */ +static u32 __iptfs_iplen(u8 *data) +{ + struct iphdr *iph = (struct iphdr *)data; + + if (iph->version == 0x4) + return ntohs(iph->tot_len); + return ntohs(((struct ipv6hdr *)iph)->payload_len) + + sizeof(struct ipv6hdr); +} + +/** + * iptfs_complete_inner_skb() - finish preparing the inner packet for gro recv. + * @x: xfrm state + * @skb: the inner packet + * + * Finish the standard xfrm processing on the inner packet prior to sending back + * through gro_cells_receive. We do this separately b/c we are building a list + * of packets in the hopes that one day a list will be taken by + * xfrm_input. + */ +static void iptfs_complete_inner_skb(struct xfrm_state *x, struct sk_buff *skb) +{ + skb_reset_network_header(skb); + + /* The packet is going back through gro_cells_receive no need to + * set this. + */ + skb_reset_transport_header(skb); + + /* Packet already has checksum value set. */ + skb->ip_summed = CHECKSUM_NONE; + + /* Our skb will contain the header data copied when this outer packet + * which contained the start of this inner packet. This is true + * when we allocate a new skb as well as when we reuse the existing skb. + */ + if (ip_hdr(skb)->version == 0x4) { + struct iphdr *iph = ip_hdr(skb); + + if (x->props.flags & XFRM_STATE_DECAP_DSCP) + ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, iph); + if (!(x->props.flags & XFRM_STATE_NOECN)) + if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) + IP_ECN_set_ce(iph); + + skb->protocol = htons(ETH_P_IP); + } else { + struct ipv6hdr *iph = ipv6_hdr(skb); + + if (x->props.flags & XFRM_STATE_DECAP_DSCP) + ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, iph); + if (!(x->props.flags & XFRM_STATE_NOECN)) + if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) + IP6_ECN_set_ce(skb, iph); + + skb->protocol = htons(ETH_P_IPV6); + } +} + +static void __iptfs_reassem_done(struct xfrm_iptfs_data *xtfs, bool free) +{ + assert_spin_locked(&xtfs->drop_lock); + + /* We don't care if it works locking takes care of things */ + hrtimer_try_to_cancel(&xtfs->drop_timer); + if (free) + kfree_skb(xtfs->ra_newskb); + xtfs->ra_newskb = NULL; +} + +/** + * iptfs_reassem_abort() - In-progress packet is aborted free the state. + * @xtfs: xtfs state + */ +static void iptfs_reassem_abort(struct xfrm_iptfs_data *xtfs) +{ + __iptfs_reassem_done(xtfs, true); +} + +/** + * iptfs_reassem_done() - In-progress packet is complete, clear the state. + * @xtfs: xtfs state + */ +static void iptfs_reassem_done(struct xfrm_iptfs_data *xtfs) +{ + __iptfs_reassem_done(xtfs, false); +} + +/** + * iptfs_reassem_cont() - Continue the reassembly of an inner packets. + * @xtfs: xtfs state + * @seq: sequence of current packet + * @st: seq read stat for current packet + * @skb: current packet + * @data: offset into sequential packet data + * @blkoff: packet blkoff value + * @list: list of skbs to enqueue completed packet on + * + * Process an IPTFS payload that has a non-zero `blkoff` or when we are + * expecting the continuation b/c we have a runt or in-progress packet. + * + * Return: the new data offset to continue processing from. + */ +static u32 iptfs_reassem_cont(struct xfrm_iptfs_data *xtfs, u64 seq, + struct skb_seq_state *st, struct sk_buff *skb, + u32 data, u32 blkoff, struct list_head *list) +{ + struct iptfs_skb_frag_walk _fragwalk; + struct iptfs_skb_frag_walk *fragwalk = NULL; + struct sk_buff *newskb = xtfs->ra_newskb; + u32 remaining = skb->len - data; + u32 runtlen = xtfs->ra_runtlen; + u32 copylen, fraglen, ipremain, iphlen, iphremain, rrem; + + /* Handle packet fragment we aren't expecting */ + if (!runtlen && !xtfs->ra_newskb) + return data + min(blkoff, remaining); + + /* Important to remember that input to this function is an ordered + * packet stream (unless the user disabled the reorder window). Thus if + * we are waiting for, and expecting the next packet so we can continue + * assembly, a newer sequence number indicates older ones are not coming + * (or if they do should be ignored). Technically we can receive older + * ones when the reorder window is disabled; however, the user should + * have disabled fragmentation in this case, and regardless we don't + * deal with it. + * + * blkoff could be zero if the stream is messed up (or it's an all pad + * insertion) be careful to handle that case in each of the below + */ + + /* Too old case: This can happen when the reorder window is disabled so + * ordering isn't actually guaranteed. + */ + if (seq < xtfs->ra_wantseq) + return data + remaining; + + /* Too new case: We missed what we wanted cleanup. */ + if (seq > xtfs->ra_wantseq) { + XFRM_INC_STATS(xs_net(xtfs->x), LINUX_MIB_XFRMINIPTFSERROR); + goto abandon; + } + + if (blkoff == 0) { + if ((*skb->data & 0xF0) != 0) { + XFRM_INC_STATS(xs_net(xtfs->x), + LINUX_MIB_XFRMINIPTFSERROR); + goto abandon; + } + /* Handle all pad case, advance expected sequence number. + * (RFC 9347 S2.2.3) + */ + xtfs->ra_wantseq++; + /* will end parsing */ + return data + remaining; + } + + if (runtlen) { + /* Regardless of what happens we're done with the runt */ + xtfs->ra_runtlen = 0; + + /* The start of this inner packet was at the very end of the last + * iptfs payload which didn't include enough for the ip header + * length field. We must have *at least* that now. + */ + rrem = sizeof(xtfs->ra_runt) - runtlen; + if (remaining < rrem || blkoff < rrem) { + XFRM_INC_STATS(xs_net(xtfs->x), + LINUX_MIB_XFRMINIPTFSERROR); + goto abandon; + } + + /* fill in the runt data */ + if (skb_copy_seq_read(st, data, &xtfs->ra_runt[runtlen], + rrem)) { + XFRM_INC_STATS(xs_net(xtfs->x), + LINUX_MIB_XFRMINBUFFERERROR); + goto abandon; + } + + /* We have enough data to get the ip length value now, + * allocate an in progress skb + */ + ipremain = __iptfs_iplen(xtfs->ra_runt); + if (ipremain < sizeof(xtfs->ra_runt)) { + /* length has to be at least runtsize large */ + XFRM_INC_STATS(xs_net(xtfs->x), + LINUX_MIB_XFRMINIPTFSERROR); + goto abandon; + } + + /* For the runt case we don't attempt sharing currently. NOTE: + * Currently, this IPTFS implementation will not create runts. + */ + + newskb = iptfs_alloc_skb(skb, ipremain, false); + if (!newskb) { + XFRM_INC_STATS(xs_net(xtfs->x), LINUX_MIB_XFRMINERROR); + goto abandon; + } + xtfs->ra_newskb = newskb; + + /* Copy the runt data into the buffer, but leave data + * pointers the same as normal non-runt case. The extra `rrem` + * recopied bytes are basically cacheline free. Allows using + * same logic below to complete. + */ + memcpy(skb_put(newskb, runtlen), xtfs->ra_runt, + sizeof(xtfs->ra_runt)); + } + + /* Continue reassembling the packet */ + ipremain = __iptfs_iplen(newskb->data); + iphlen = __iptfs_iphlen(newskb->data); + + ipremain -= newskb->len; + if (blkoff < ipremain) { + /* Corrupt data, we don't have enough to complete the packet */ + XFRM_INC_STATS(xs_net(xtfs->x), LINUX_MIB_XFRMINIPTFSERROR); + goto abandon; + } + + /* We want the IP header in linear space */ + if (newskb->len < iphlen) { + iphremain = iphlen - newskb->len; + if (blkoff < iphremain) { + XFRM_INC_STATS(xs_net(xtfs->x), + LINUX_MIB_XFRMINIPTFSERROR); + goto abandon; + } + fraglen = min(blkoff, remaining); + copylen = min(fraglen, iphremain); + if (skb_copy_seq_read(st, data, skb_put(newskb, copylen), + copylen)) { + XFRM_INC_STATS(xs_net(xtfs->x), + LINUX_MIB_XFRMINBUFFERERROR); + goto abandon; + } + /* this is a silly condition that might occur anyway */ + if (copylen < iphremain) { + xtfs->ra_wantseq++; + return data + fraglen; + } + /* update data and things derived from it */ + data += copylen; + blkoff -= copylen; + remaining -= copylen; + ipremain -= copylen; + } + + fraglen = min(blkoff, remaining); + copylen = min(fraglen, ipremain); + + /* If we may have the opportunity to share prepare a fragwalk. */ + if (!skb_has_frag_list(skb) && !skb_has_frag_list(newskb) && + (skb->head_frag || skb->len == skb->data_len) && + skb->pp_recycle == newskb->pp_recycle) { + fragwalk = &_fragwalk; + iptfs_skb_prepare_frag_walk(skb, data, fragwalk); + } + + /* Try share then copy. */ + if (fragwalk && + iptfs_skb_can_add_frags(newskb, fragwalk, data, copylen)) { + iptfs_skb_add_frags(newskb, fragwalk, data, copylen); + } else { + /* copy fragment data into newskb */ + if (skb_copy_seq_read(st, data, skb_put(newskb, copylen), + copylen)) { + XFRM_INC_STATS(xs_net(xtfs->x), + LINUX_MIB_XFRMINBUFFERERROR); + goto abandon; + } + } + + if (copylen < ipremain) { + xtfs->ra_wantseq++; + } else { + /* We are done with packet reassembly! */ + iptfs_reassem_done(xtfs); + iptfs_complete_inner_skb(xtfs->x, newskb); + list_add_tail(&newskb->list, list); + } + + /* will continue on to new data block or end */ + return data + fraglen; + +abandon: + if (xtfs->ra_newskb) { + iptfs_reassem_abort(xtfs); + } else { + xtfs->ra_runtlen = 0; + xtfs->ra_wantseq = 0; + } + /* skip past fragment, maybe to end */ + return data + min(blkoff, remaining); +} + +static bool __input_process_payload(struct xfrm_state *x, u32 data, + struct skb_seq_state *skbseq, + struct list_head *sublist) +{ + u8 hbytes[sizeof(struct ipv6hdr)]; + struct iptfs_skb_frag_walk _fragwalk; + struct iptfs_skb_frag_walk *fragwalk = NULL; + struct sk_buff *defer, *first_skb, *next, *skb; + const unsigned char *old_mac; + struct xfrm_iptfs_data *xtfs; + struct iphdr *iph; + struct net *net; + u32 first_iplen, iphlen, iplen, remaining, tail; + u32 capturelen; + u64 seq; + + xtfs = x->mode_data; + net = xs_net(x); + skb = skbseq->root_skb; + first_skb = NULL; + defer = NULL; + + seq = __esp_seq(skb); + + /* Save the old mac header if set */ + old_mac = skb_mac_header_was_set(skb) ? skb_mac_header(skb) : NULL; + + /* New packets */ + + tail = skb->len; + while (data < tail) { + __be16 protocol = 0; + + /* Gather information on the next data block. + * `data` points to the start of the data block. + */ + remaining = tail - data; + + /* try and copy enough bytes to read length from ipv4/ipv6 */ + iphlen = min_t(u32, remaining, 6); + if (skb_copy_seq_read(skbseq, data, hbytes, iphlen)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); + goto done; + } + + iph = (struct iphdr *)hbytes; + if (iph->version == 0x4) { + /* must have at least tot_len field present */ + if (remaining < 4) { + /* save the bytes we have, advance data and exit */ + iptfs_input_save_runt(xtfs, seq, hbytes, + remaining); + data += remaining; + break; + } + + iplen = be16_to_cpu(iph->tot_len); + iphlen = iph->ihl << 2; + protocol = cpu_to_be16(ETH_P_IP); + XFRM_MODE_SKB_CB(skbseq->root_skb)->tos = iph->tos; + } else if (iph->version == 0x6) { + /* must have at least payload_len field present */ + if (remaining < 6) { + /* save the bytes we have, advance data and exit */ + iptfs_input_save_runt(xtfs, seq, hbytes, + remaining); + data += remaining; + break; + } + + iplen = be16_to_cpu(((struct ipv6hdr *)hbytes)->payload_len); + iplen += sizeof(struct ipv6hdr); + iphlen = sizeof(struct ipv6hdr); + protocol = cpu_to_be16(ETH_P_IPV6); + XFRM_MODE_SKB_CB(skbseq->root_skb)->tos = + ipv6_get_dsfield((struct ipv6hdr *)iph); + } else if (iph->version == 0x0) { + /* pad */ + data = tail; + break; + } else { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); + goto done; + } + + if (unlikely(skbseq->stepped_offset)) { + /* We need to reset our seq read, it can't backup at + * this point. + */ + struct sk_buff *save = skbseq->root_skb; + + skb_abort_seq_read(skbseq); + skb_prepare_seq_read(save, data, tail, skbseq); + } + + if (first_skb) { + skb = NULL; + } else { + first_skb = skb; + first_iplen = iplen; + fragwalk = NULL; + + /* We are going to skip over `data` bytes to reach the + * start of the IP header of `iphlen` len for `iplen` + * inner packet. + */ + + if (skb_has_frag_list(skb)) { + defer = skb; + skb = NULL; + } else if (data + iphlen <= skb_headlen(skb) && + /* make sure our header is 32-bit aligned? */ + /* ((uintptr_t)(skb->data + data) & 0x3) == 0 && */ + skb_tailroom(skb) + tail - data >= iplen) { + /* Reuse the received skb. + * + * We have enough headlen to pull past any + * initial fragment data, leaving at least the + * IP header in the linear buffer space. + * + * For linear buffer space we only require that + * linear buffer space is large enough to + * eventually hold the entire reassembled + * packet (by including tailroom in the check). + * + * For non-linear tailroom is 0 and so we only + * re-use if the entire packet is present + * already. + * + * NOTE: there are many more options for + * sharing, KISS for now. Also, this can produce + * skb's with the IP header unaligned to 32 + * bits. If that ends up being a problem then a + * check should be added to the conditional + * above that the header lies on a 32-bit + * boundary as well. + */ + skb_pull(skb, data); + + /* our range just changed */ + data = 0; + tail = skb->len; + remaining = skb->len; + + skb->protocol = protocol; + skb_mac_header_rebuild(skb); + if (skb->mac_len) + eth_hdr(skb)->h_proto = skb->protocol; + + /* all pointers could be changed now reset walk */ + skb_abort_seq_read(skbseq); + skb_prepare_seq_read(skb, data, tail, skbseq); + } else if (skb->head_frag && + /* We have the IP header right now */ + remaining >= iphlen) { + fragwalk = &_fragwalk; + iptfs_skb_prepare_frag_walk(skb, data, fragwalk); + defer = skb; + skb = NULL; + } else { + /* We couldn't reuse the input skb so allocate a + * new one. + */ + defer = skb; + skb = NULL; + } + + /* Don't trim `first_skb` until the end as we are + * walking that data now. + */ + } + + capturelen = min(iplen, remaining); + if (!skb) { + if (!fragwalk || + /* Large enough to be worth sharing */ + iplen < IPTFS_PKT_SHARE_MIN || + /* Have IP header + some data to share. */ + capturelen <= iphlen || + /* Try creating skb and adding frags */ + !(skb = iptfs_pskb_add_frags(first_skb, fragwalk, + data, capturelen, + skbseq, iphlen))) { + skb = iptfs_pskb_extract_seq(iplen, skbseq, data, capturelen); + } + if (!skb) { + /* skip to next packet or done */ + data += capturelen; + continue; + } + + skb->protocol = protocol; + if (old_mac) { + /* rebuild the mac header */ + skb_set_mac_header(skb, -first_skb->mac_len); + memcpy(skb_mac_header(skb), old_mac, first_skb->mac_len); + eth_hdr(skb)->h_proto = skb->protocol; + } + } + + data += capturelen; + + if (skb->len < iplen) { + /* Start reassembly */ + spin_lock(&xtfs->drop_lock); + + xtfs->ra_newskb = skb; + xtfs->ra_wantseq = seq + 1; + if (!hrtimer_is_queued(&xtfs->drop_timer)) { + /* softirq blocked lest the timer fire and interrupt us */ + hrtimer_start(&xtfs->drop_timer, + xtfs->drop_time_ns, + IPTFS_HRTIMER_MODE); + } + + spin_unlock(&xtfs->drop_lock); + + break; + } + + iptfs_complete_inner_skb(x, skb); + list_add_tail(&skb->list, sublist); + } + + if (data != tail) + /* this should not happen from the above code */ + XFRM_INC_STATS(net, LINUX_MIB_XFRMINIPTFSERROR); + + if (first_skb && first_iplen && !defer && first_skb != xtfs->ra_newskb) { + /* first_skb is queued b/c !defer and not partial */ + if (pskb_trim(first_skb, first_iplen)) { + /* error trimming */ + list_del(&first_skb->list); + defer = first_skb; + } + first_skb->ip_summed = CHECKSUM_NONE; + } + + /* Send the packets! */ + list_for_each_entry_safe(skb, next, sublist, list) { + skb_list_del_init(skb); + if (xfrm_input(skb, 0, 0, -2)) + kfree_skb(skb); + } +done: + skb = skbseq->root_skb; + skb_abort_seq_read(skbseq); + + if (defer) { + consume_skb(defer); + } else if (!first_skb) { + /* skb is the original passed in skb, but we didn't get far + * enough to process it as the first_skb, if we had it would + * either be save in ra_newskb, trimmed and sent on as an skb or + * placed in defer to be freed. + */ + kfree_skb(skb); + } + return true; +} + +/** + * iptfs_input_ordered() - handle next in order IPTFS payload. + * @x: xfrm state + * @skb: current packet + * + * Process the IPTFS payload in `skb` and consume it afterwards. + */ +static void iptfs_input_ordered(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ip_iptfs_cc_hdr iptcch; + struct skb_seq_state skbseq; + struct list_head sublist; /* rename this it's just a list */ + struct xfrm_iptfs_data *xtfs; + struct ip_iptfs_hdr *ipth; + struct net *net; + u32 blkoff, data, remaining; + bool consumed = false; + u64 seq; + + xtfs = x->mode_data; + net = xs_net(x); + + seq = __esp_seq(skb); + + /* Large enough to hold both types of header */ + ipth = (struct ip_iptfs_hdr *)&iptcch; + + skb_prepare_seq_read(skb, 0, skb->len, &skbseq); + + /* Get the IPTFS header and validate it */ + + if (skb_copy_seq_read(&skbseq, 0, ipth, sizeof(*ipth))) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); + goto done; + } + data = sizeof(*ipth); + + trace_iptfs_egress_recv(skb, xtfs, be16_to_cpu(ipth->block_offset)); + + /* Set data past the basic header */ + if (ipth->subtype == IPTFS_SUBTYPE_CC) { + /* Copy the rest of the CC header */ + remaining = sizeof(iptcch) - sizeof(*ipth); + if (skb_copy_seq_read(&skbseq, data, ipth + 1, remaining)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); + goto done; + } + data += remaining; + } else if (ipth->subtype != IPTFS_SUBTYPE_BASIC) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); + goto done; + } + + if (ipth->flags != 0) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); + goto done; + } + + INIT_LIST_HEAD(&sublist); + + /* Handle fragment at start of payload, and/or waiting reassembly. */ + + blkoff = ntohs(ipth->block_offset); + /* check before locking i.e., maybe */ + if (blkoff || xtfs->ra_runtlen || xtfs->ra_newskb) { + spin_lock(&xtfs->drop_lock); + + /* check again after lock */ + if (blkoff || xtfs->ra_runtlen || xtfs->ra_newskb) { + data = iptfs_reassem_cont(xtfs, seq, &skbseq, skb, data, + blkoff, &sublist); + } + + spin_unlock(&xtfs->drop_lock); + } + + /* New packets */ + consumed = __input_process_payload(x, data, &skbseq, &sublist); +done: + if (!consumed) { + skb = skbseq.root_skb; + skb_abort_seq_read(&skbseq); + kfree_skb(skb); + } +} + +/* ------------------------------- */ +/* Input (Egress) Re-ordering Code */ +/* ------------------------------- */ + +static void __vec_shift(struct xfrm_iptfs_data *xtfs, u32 shift) +{ + u32 savedlen = xtfs->w_savedlen; + + if (shift > savedlen) + shift = savedlen; + if (shift != savedlen) + memcpy(xtfs->w_saved, xtfs->w_saved + shift, + (savedlen - shift) * sizeof(*xtfs->w_saved)); + memset(xtfs->w_saved + savedlen - shift, 0, + shift * sizeof(*xtfs->w_saved)); + xtfs->w_savedlen -= shift; +} + +static void __reorder_past(struct xfrm_iptfs_data *xtfs, struct sk_buff *inskb, + struct list_head *freelist) +{ + list_add_tail(&inskb->list, freelist); +} + +static u32 __reorder_drop(struct xfrm_iptfs_data *xtfs, struct list_head *list) + +{ + struct skb_wseq *s, *se; + const u32 savedlen = xtfs->w_savedlen; + time64_t now = ktime_get_raw_fast_ns(); + u32 count = 0; + u32 scount = 0; + + if (xtfs->w_saved[0].drop_time > now) + goto set_timer; + + ++xtfs->w_wantseq; + + /* Keep flushing packets until we reach a drop time greater than now. */ + s = xtfs->w_saved; + se = s + savedlen; + do { + /* Walking past empty slots until we reach a packet */ + for (; s < se && !s->skb; s++) { + if (s->drop_time > now) + goto outerdone; + } + /* Sending packets until we hit another empty slot. */ + for (; s < se && s->skb; scount++, s++) + list_add_tail(&s->skb->list, list); + } while (s < se); +outerdone: + + count = s - xtfs->w_saved; + if (count) { + xtfs->w_wantseq += count; + + /* Shift handled slots plus final empty slot into slot 0. */ + __vec_shift(xtfs, count); + } + + if (xtfs->w_savedlen) { +set_timer: + /* Drifting is OK */ + hrtimer_start(&xtfs->drop_timer, + xtfs->w_saved[0].drop_time - now, + IPTFS_HRTIMER_MODE); + } + return scount; +} + +static void __reorder_this(struct xfrm_iptfs_data *xtfs, struct sk_buff *inskb, + struct list_head *list) +{ + struct skb_wseq *s, *se; + const u32 savedlen = xtfs->w_savedlen; + u32 count = 0; + + /* Got what we wanted. */ + list_add_tail(&inskb->list, list); + ++xtfs->w_wantseq; + if (!savedlen) + return; + + /* Flush remaining consecutive packets. */ + + /* Keep sending until we hit another missed pkt. */ + for (s = xtfs->w_saved, se = s + savedlen; s < se && s->skb; s++) + list_add_tail(&s->skb->list, list); + count = s - xtfs->w_saved; + if (count) + xtfs->w_wantseq += count; + + /* Shift handled slots plus final empty slot into slot 0. */ + __vec_shift(xtfs, count + 1); +} + +/* Set the slot's drop time and all the empty slots below it until reaching a + * filled slot which will already be set. + */ +static void iptfs_set_window_drop_times(struct xfrm_iptfs_data *xtfs, int index) +{ + const u32 savedlen = xtfs->w_savedlen; + struct skb_wseq *s = xtfs->w_saved; + time64_t drop_time; + + assert_spin_locked(&xtfs->drop_lock); + + if (savedlen > index + 1) { + /* we are below another, our drop time and the timer are already set */ + return; + } + /* we are the most future so get a new drop time. */ + drop_time = ktime_get_raw_fast_ns(); + drop_time += xtfs->drop_time_ns; + + /* Walk back through the array setting drop times as we go */ + s[index].drop_time = drop_time; + while (index-- > 0 && !s[index].skb) + s[index].drop_time = drop_time; + + /* If we walked all the way back, schedule the drop timer if needed */ + if (index == -1 && !hrtimer_is_queued(&xtfs->drop_timer)) + hrtimer_start(&xtfs->drop_timer, xtfs->drop_time_ns, + IPTFS_HRTIMER_MODE); +} + +static void __reorder_future_fits(struct xfrm_iptfs_data *xtfs, + struct sk_buff *inskb, + struct list_head *freelist) +{ + const u64 inseq = __esp_seq(inskb); + const u64 wantseq = xtfs->w_wantseq; + const u64 distance = inseq - wantseq; + const u32 savedlen = xtfs->w_savedlen; + const u32 index = distance - 1; + + /* Handle future sequence number received which fits in the window. + * + * We know we don't have the seq we want so we won't be able to flush + * anything. + */ + + /* slot count is 4, saved size is 3 savedlen is 2 + * + * "window boundary" is based on the fixed window size + * distance is also slot number + * index is an array index (i.e., - 1 of slot) + * : : - implicit NULL after array len + * + * +--------- used length (savedlen == 2) + * | +----- array size (nslots - 1 == 3) + * | | + window boundary (nslots == 4) + * V V | V + * | + * 0 1 2 3 | slot number + * --- 0 1 2 | array index + * [-] [b] : :| array + * + * "2" "3" "4" *5*| seq numbers + * + * We receive seq number 5 + * distance == 3 [inseq(5) - w_wantseq(2)] + * index == 2 [distance(6) - 1] + */ + + if (xtfs->w_saved[index].skb) { + /* a dup of a future */ + list_add_tail(&inskb->list, freelist); + return; + } + + xtfs->w_saved[index].skb = inskb; + xtfs->w_savedlen = max(savedlen, index + 1); + iptfs_set_window_drop_times(xtfs, index); +} + +static void __reorder_future_shifts(struct xfrm_iptfs_data *xtfs, + struct sk_buff *inskb, + struct list_head *list) +{ + const u32 nslots = xtfs->cfg.reorder_win_size + 1; + const u64 inseq = __esp_seq(inskb); + u32 savedlen = xtfs->w_savedlen; + u64 wantseq = xtfs->w_wantseq; + struct skb_wseq *wnext; + struct sk_buff *slot0; + u32 beyond, shifting, slot; + u64 distance; + + /* Handle future sequence number received. + * + * IMPORTANT: we are at least advancing w_wantseq (i.e., wantseq) by 1 + * b/c we are beyond the window boundary. + * + * We know we don't have the wantseq so that counts as a drop. + */ + + /* example: slot count is 4, array size is 3 savedlen is 2, slot 0 is + * the missing sequence number. + * + * the final slot at savedlen (index savedlen - 1) is always occupied. + * + * beyond is "beyond array size" not savedlen. + * + * +--------- array length (savedlen == 2) + * | +----- array size (nslots - 1 == 3) + * | | +- window boundary (nslots == 4) + * V V | + * | + * 0 1 2 3 | slot number + * --- 0 1 2 | array index + * [b] [c] : :| array + * | + * "2" "3" "4" "5"|*6* seq numbers + * + * We receive seq number 6 + * distance == 4 [inseq(6) - w_wantseq(2)] + * newslot == distance + * index == 3 [distance(4) - 1] + * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))] + * shifting == 1 [min(savedlen(2), beyond(1)] + * slot0_skb == [b], and should match w_wantseq + * + * +--- window boundary (nslots == 4) + * 0 1 2 3 | 4 slot number + * --- 0 1 2 | 3 array index + * [b] : : : :| array + * "2" "3" "4" "5" *6* seq numbers + * + * We receive seq number 6 + * distance == 4 [inseq(6) - w_wantseq(2)] + * newslot == distance + * index == 3 [distance(4) - 1] + * beyond == 1 [newslot(4) - lastslot((nslots(4) - 1))] + * shifting == 1 [min(savedlen(1), beyond(1)] + * slot0_skb == [b] and should match w_wantseq + * + * +-- window boundary (nslots == 4) + * 0 1 2 3 | 4 5 6 slot number + * --- 0 1 2 | 3 4 5 array index + * [-] [c] : :| array + * "2" "3" "4" "5" "6" "7" *8* seq numbers + * + * savedlen = 2, beyond = 3 + * iter 1: slot0 == NULL, missed++, lastdrop = 2 (2+1-1), slot0 = [-] + * iter 2: slot0 == NULL, missed++, lastdrop = 3 (2+2-1), slot0 = [c] + * 2 < 3, extra = 1 (3-2), missed += extra, lastdrop = 4 (2+2+1-1) + * + * We receive seq number 8 + * distance == 6 [inseq(8) - w_wantseq(2)] + * newslot == distance + * index == 5 [distance(6) - 1] + * beyond == 3 [newslot(6) - lastslot((nslots(4) - 1))] + * shifting == 2 [min(savedlen(2), beyond(3)] + * + * slot0_skb == NULL changed from [b] when "savedlen < beyond" is true. + */ + + /* Now send any packets that are being shifted out of saved, and account + * for missing packets that are exiting the window as we shift it. + */ + + distance = inseq - wantseq; + beyond = distance - (nslots - 1); + + /* If savedlen > beyond we are shifting some, else all. */ + shifting = min(savedlen, beyond); + + /* slot0 is the buf that just shifted out and into slot0 */ + slot0 = NULL; + wnext = xtfs->w_saved; + for (slot = 1; slot <= shifting; slot++, wnext++) { + /* handle what was in slot0 before we occupy it */ + if (slot0) + list_add_tail(&slot0->list, list); + slot0 = wnext->skb; + wnext->skb = NULL; + } + + /* slot0 is now either NULL (in which case it's what we now are waiting + * for, or a buf in which case we need to handle it like we received it; + * however, we may be advancing past that buffer as well.. + */ + + /* Handle case where we need to shift more than we had saved, slot0 will + * be NULL iff savedlen is 0, otherwise slot0 will always be + * non-NULL b/c we shifted the final element, which is always set if + * there is any saved, into slot0. + */ + if (savedlen < beyond) { + if (savedlen != 0) + list_add_tail(&slot0->list, list); + slot0 = NULL; + /* slot0 has had an empty slot pushed into it */ + } + + /* Remove the entries */ + __vec_shift(xtfs, beyond); + + /* Advance want seq */ + xtfs->w_wantseq += beyond; + + /* Process drops here when implementing congestion control */ + + /* We've shifted. plug the packet in at the end. */ + xtfs->w_savedlen = nslots - 1; + xtfs->w_saved[xtfs->w_savedlen - 1].skb = inskb; + iptfs_set_window_drop_times(xtfs, xtfs->w_savedlen - 1); + + /* if we don't have a slot0 then we must wait for it */ + if (!slot0) + return; + + /* If slot0, seq must match new want seq */ + + /* slot0 is valid, treat like we received expected. */ + __reorder_this(xtfs, slot0, list); +} + +/* Receive a new packet into the reorder window. Return a list of ordered + * packets from the window. + */ +static void iptfs_input_reorder(struct xfrm_iptfs_data *xtfs, + struct sk_buff *inskb, struct list_head *list, + struct list_head *freelist) +{ + const u32 nslots = xtfs->cfg.reorder_win_size + 1; + u64 inseq = __esp_seq(inskb); + u64 wantseq; + + assert_spin_locked(&xtfs->drop_lock); + + if (unlikely(!xtfs->w_seq_set)) { + xtfs->w_seq_set = true; + xtfs->w_wantseq = inseq; + } + wantseq = xtfs->w_wantseq; + + if (likely(inseq == wantseq)) + __reorder_this(xtfs, inskb, list); + else if (inseq < wantseq) + __reorder_past(xtfs, inskb, freelist); + else if ((inseq - wantseq) < nslots) + __reorder_future_fits(xtfs, inskb, freelist); + else + __reorder_future_shifts(xtfs, inskb, list); +} + +/** + * iptfs_drop_timer() - Handle drop timer expiry. + * @me: the timer + * + * This is similar to our input function. + * + * The drop timer is set when we start an in progress reassembly, and also when + * we save a future packet in the window saved array. + * + * NOTE packets in the save window are always newer WRT drop times as + * they get further in the future. i.e. for: + * + * if slots (S0, S1, ... Sn) and `Dn` is the drop time for slot `Sn`, + * then D(n-1) <= D(n). + * + * So, regardless of why the timer is firing we can always discard any inprogress + * fragment; either it's the reassembly timer, or slot 0 is going to be + * dropped as S0 must have the most recent drop time, and slot 0 holds the + * continuation fragment of the in progress packet. + * + * Returns HRTIMER_NORESTART. + */ +static enum hrtimer_restart iptfs_drop_timer(struct hrtimer *me) +{ + struct sk_buff *skb, *next; + struct list_head list; + struct xfrm_iptfs_data *xtfs; + struct xfrm_state *x; + u32 count; + + xtfs = container_of(me, typeof(*xtfs), drop_timer); + x = xtfs->x; + + INIT_LIST_HEAD(&list); + + spin_lock(&xtfs->drop_lock); + + /* Drop any in progress packet */ + skb = xtfs->ra_newskb; + xtfs->ra_newskb = NULL; + + /* Now drop as many packets as we should from the reordering window + * saved array + */ + count = xtfs->w_savedlen ? __reorder_drop(xtfs, &list) : 0; + + spin_unlock(&xtfs->drop_lock); + + if (skb) + kfree_skb_reason(skb, SKB_DROP_REASON_FRAG_REASM_TIMEOUT); + + if (count) { + list_for_each_entry_safe(skb, next, &list, list) { + skb_list_del_init(skb); + iptfs_input_ordered(x, skb); + } + } + + return HRTIMER_NORESTART; +} + +/** + * iptfs_input() - handle receipt of iptfs payload + * @x: xfrm state + * @skb: the packet + * + * We have an IPTFS payload order it if needed, then process newly in order + * packets. + * + * Return: -EINPROGRESS to inform xfrm_input to stop processing the skb. + */ +static int iptfs_input(struct xfrm_state *x, struct sk_buff *skb) +{ + struct list_head freelist, list; + struct xfrm_iptfs_data *xtfs = x->mode_data; + struct sk_buff *next; + + /* Fast path for no reorder window. */ + if (xtfs->cfg.reorder_win_size == 0) { + iptfs_input_ordered(x, skb); + goto done; + } + + /* Fetch list of in-order packets from the reordering window as well as + * a list of buffers we need to now free. + */ + INIT_LIST_HEAD(&list); + INIT_LIST_HEAD(&freelist); + + spin_lock(&xtfs->drop_lock); + iptfs_input_reorder(xtfs, skb, &list, &freelist); + spin_unlock(&xtfs->drop_lock); + + list_for_each_entry_safe(skb, next, &list, list) { + skb_list_del_init(skb); + iptfs_input_ordered(x, skb); + } + + list_for_each_entry_safe(skb, next, &freelist, list) { + skb_list_del_init(skb); + kfree_skb(skb); + } +done: + /* We always have dealt with the input SKB, either we are re-using it, + * or we have freed it. Return EINPROGRESS so that xfrm_input stops + * processing it. + */ + return -EINPROGRESS; +} + +/* ================================= */ +/* IPTFS Sending (ingress) Functions */ +/* ================================= */ + +/* ------------------------- */ +/* Enqueue to send functions */ +/* ------------------------- */ + +/** + * iptfs_enqueue() - enqueue packet if ok to send. + * @xtfs: xtfs state + * @skb: the packet + * + * Return: true if packet enqueued. + */ +static bool iptfs_enqueue(struct xfrm_iptfs_data *xtfs, struct sk_buff *skb) +{ + u64 newsz = xtfs->queue_size + skb->len; + struct iphdr *iph; + + assert_spin_locked(&xtfs->x->lock); + + if (newsz > xtfs->cfg.max_queue_size) + return false; + + /* Set ECN CE if we are above our ECN queue threshold */ + if (newsz > xtfs->ecn_queue_size) { + iph = ip_hdr(skb); + if (iph->version == 4) + IP_ECN_set_ce(iph); + else if (iph->version == 6) + IP6_ECN_set_ce(skb, ipv6_hdr(skb)); + } + + __skb_queue_tail(&xtfs->queue, skb); + xtfs->queue_size += skb->len; + return true; +} + +static int iptfs_get_cur_pmtu(struct xfrm_state *x, struct xfrm_iptfs_data *xtfs, + struct sk_buff *skb) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)skb_dst(skb); + u32 payload_mtu = xtfs->payload_mtu; + u32 pmtu = __iptfs_get_inner_mtu(x, xdst->child_mtu_cached); + + if (payload_mtu && payload_mtu < pmtu) + pmtu = payload_mtu; + + return pmtu; +} + +static int iptfs_is_too_big(struct sock *sk, struct sk_buff *skb, u32 pmtu) +{ + if (skb->len <= pmtu) + return 0; + + /* We only send ICMP too big if the user has configured us as + * dont-fragment. + */ + if (skb->dev) + XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMOUTERROR); + + if (sk) + xfrm_local_error(skb, pmtu); + else if (ip_hdr(skb)->version == 4) + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(pmtu)); + else + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, pmtu); + + return 1; +} + +/* IPv4/IPv6 packet ingress to IPTFS tunnel, arrange to send in IPTFS payload + * (i.e., aggregating or fragmenting as appropriate). + * This is set in dst->output for an SA. + */ +static int iptfs_output_collect(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + struct xfrm_iptfs_data *xtfs = x->mode_data; + struct sk_buff *segs, *nskb; + u32 pmtu = 0; + bool ok = true; + bool was_gso; + + /* We have hooked into dst_entry->output which means we have skipped the + * protocol specific netfilter (see xfrm4_output, xfrm6_output). + * when our timer runs we will end up calling xfrm_output directly on + * the encapsulated traffic. + * + * For both cases this is the NF_INET_POST_ROUTING hook which allows + * changing the skb->dst entry which then may not be xfrm based anymore + * in which case a REROUTED flag is set. and dst_output is called. + * + * For IPv6 we are also skipping fragmentation handling for local + * sockets, which may or may not be good depending on our tunnel DF + * setting. Normally with fragmentation supported we want to skip this + * fragmentation. + */ + + if (xtfs->cfg.dont_frag) + pmtu = iptfs_get_cur_pmtu(x, xtfs, skb); + + /* Break apart GSO skbs. If the queue is nearing full then we want the + * accounting and queuing to be based on the individual packets not on the + * aggregate GSO buffer. + */ + was_gso = skb_is_gso(skb); + if (!was_gso) { + segs = skb; + } else { + segs = skb_gso_segment(skb, 0); + if (IS_ERR_OR_NULL(segs)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); + kfree_skb(skb); + if (IS_ERR(segs)) + return PTR_ERR(segs); + return -EINVAL; + } + consume_skb(skb); + skb = NULL; + } + + /* We can be running on multiple cores and from the network softirq or + * from user context depending on where the packet is coming from. + */ + spin_lock_bh(&x->lock); + + skb_list_walk_safe(segs, skb, nskb) { + skb_mark_not_on_list(skb); + + /* Once we drop due to no queue space we continue to drop the + * rest of the packets from that GRO. + */ + if (!ok) { +nospace: + trace_iptfs_no_queue_space(skb, xtfs, pmtu, was_gso); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOQSPACE); + kfree_skb_reason(skb, SKB_DROP_REASON_FULL_RING); + continue; + } + + /* If the user indicated no iptfs fragmenting check before + * enqueue. + */ + if (xtfs->cfg.dont_frag && iptfs_is_too_big(sk, skb, pmtu)) { + trace_iptfs_too_big(skb, xtfs, pmtu, was_gso); + kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG); + continue; + } + + /* Enqueue to send in tunnel */ + ok = iptfs_enqueue(xtfs, skb); + if (!ok) + goto nospace; + + trace_iptfs_enqueue(skb, xtfs, pmtu, was_gso); + } + + /* Start a delay timer if we don't have one yet */ + if (!hrtimer_is_queued(&xtfs->iptfs_timer)) { + hrtimer_start(&xtfs->iptfs_timer, xtfs->init_delay_ns, IPTFS_HRTIMER_MODE); + xtfs->iptfs_settime = ktime_get_raw_fast_ns(); + trace_iptfs_timer_start(xtfs, xtfs->init_delay_ns); + } + + spin_unlock_bh(&x->lock); + return 0; +} + +/* -------------------------- */ +/* Dequeue and send functions */ +/* -------------------------- */ + +static void iptfs_output_prepare_skb(struct sk_buff *skb, u32 blkoff) +{ + struct ip_iptfs_hdr *h; + size_t hsz = sizeof(*h); + + /* now reset values to be pointing at the rest of the packets */ + h = skb_push(skb, hsz); + memset(h, 0, hsz); + if (blkoff) + h->block_offset = htons(blkoff); + + /* network_header current points at the inner IP packet + * move it to the iptfs header + */ + skb->transport_header = skb->network_header; + skb->network_header -= hsz; + + IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; +} + +/** + * iptfs_copy_create_frag() - create an inner fragment skb. + * @st: The source packet data. + * @offset: offset in @st of the new fragment data. + * @copy_len: the amount of data to copy from @st. + * + * Create a new skb holding a single IPTFS inner packet fragment. @copy_len must + * not be greater than the max fragment size. + * + * Return: the new fragment skb or an ERR_PTR(). + */ +static struct sk_buff *iptfs_copy_create_frag(struct skb_seq_state *st, u32 offset, u32 copy_len) +{ + struct sk_buff *src = st->root_skb; + struct sk_buff *skb; + int err; + + skb = iptfs_alloc_skb(src, copy_len, true); + if (!skb) + return ERR_PTR(-ENOMEM); + + /* Now copy `copy_len` data from src */ + err = skb_copy_seq_read(st, offset, skb_put(skb, copy_len), copy_len); + if (err) { + kfree_skb(skb); + return ERR_PTR(err); + } + + return skb; +} + +/** + * iptfs_copy_create_frags() - create and send N-1 fragments of a larger skb. + * @skbp: the source packet skb (IN), skb holding the last fragment in + * the fragment stream (OUT). + * @xtfs: IPTFS SA state. + * @mtu: the max IPTFS fragment size. + * + * This function is responsible for fragmenting a larger inner packet into a + * sequence of IPTFS payload packets. The last fragment is returned rather than + * being sent so that the caller can append more inner packets (aggregation) if + * there is room. + * + * Return: 0 on success or a negative error code on failure + */ +static int iptfs_copy_create_frags(struct sk_buff **skbp, struct xfrm_iptfs_data *xtfs, u32 mtu) +{ + struct skb_seq_state skbseq; + struct list_head sublist; + struct sk_buff *skb = *skbp; + struct sk_buff *nskb = *skbp; + u32 copy_len, offset; + u32 to_copy = skb->len - mtu; + u32 blkoff = 0; + int err = 0; + + INIT_LIST_HEAD(&sublist); + + skb_prepare_seq_read(skb, 0, skb->len, &skbseq); + + /* A trimmed `skb` will be sent as the first fragment, later. */ + offset = mtu; + to_copy = skb->len - offset; + while (to_copy) { + /* Send all but last fragment to allow agg. append */ + trace_iptfs_first_fragmenting(nskb, mtu, to_copy, NULL); + list_add_tail(&nskb->list, &sublist); + + /* FUTURE: if the packet has an odd/non-aligning length we could + * send less data in the penultimate fragment so that the last + * fragment then ends on an aligned boundary. + */ + copy_len = min(to_copy, mtu); + nskb = iptfs_copy_create_frag(&skbseq, offset, copy_len); + if (IS_ERR(nskb)) { + XFRM_INC_STATS(xs_net(xtfs->x), LINUX_MIB_XFRMOUTERROR); + skb_abort_seq_read(&skbseq); + err = PTR_ERR(nskb); + nskb = NULL; + break; + } + iptfs_output_prepare_skb(nskb, to_copy); + offset += copy_len; + to_copy -= copy_len; + blkoff = to_copy; + } + skb_abort_seq_read(&skbseq); + + /* return last fragment that will be unsent (or NULL) */ + *skbp = nskb; + if (nskb) + trace_iptfs_first_final_fragment(nskb, mtu, blkoff, NULL); + + /* trim the original skb to MTU */ + if (!err) + err = pskb_trim(skb, mtu); + + if (err) { + /* Free all frags. Don't bother sending a partial packet we will + * never complete. + */ + kfree_skb(nskb); + list_for_each_entry_safe(skb, nskb, &sublist, list) { + skb_list_del_init(skb); + kfree_skb(skb); + } + return err; + } + + /* prepare the initial fragment with an iptfs header */ + iptfs_output_prepare_skb(skb, 0); + + /* Send all but last fragment, if we fail to send a fragment then free + * the rest -- no point in sending a packet that can't be reassembled. + */ + list_for_each_entry_safe(skb, nskb, &sublist, list) { + skb_list_del_init(skb); + if (!err) + err = xfrm_output(NULL, skb); + else + kfree_skb(skb); + } + if (err) + kfree_skb(*skbp); + return err; +} + +/** + * iptfs_first_skb() - handle the first dequeued inner packet for output + * @skbp: the source packet skb (IN), skb holding the last fragment in + * the fragment stream (OUT). + * @xtfs: IPTFS SA state. + * @mtu: the max IPTFS fragment size. + * + * This function is responsible for fragmenting a larger inner packet into a + * sequence of IPTFS payload packets. + * + * The last fragment is returned rather than being sent so that the caller can + * append more inner packets (aggregation) if there is room. + * + * Return: 0 on success or a negative error code on failure + */ +static int iptfs_first_skb(struct sk_buff **skbp, struct xfrm_iptfs_data *xtfs, u32 mtu) +{ + struct sk_buff *skb = *skbp; + int err; + + /* Classic ESP skips the don't fragment ICMP error if DF is clear on + * the inner packet or ignore_df is set. Otherwise it will send an ICMP + * or local error if the inner packet won't fit it's MTU. + * + * With IPTFS we do not care about the inner packet DF bit. If the + * tunnel is configured to "don't fragment" we error back if things + * don't fit in our max packet size. Otherwise we iptfs-fragment as + * normal. + */ + + /* The opportunity for HW offload has ended */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); + if (err) + return err; + } + + /* We've split gso up before queuing */ + + trace_iptfs_first_dequeue(skb, mtu, 0, ip_hdr(skb)); + + /* Consider the buffer Tx'd and no longer owned */ + skb_orphan(skb); + + /* Simple case -- it fits. `mtu` accounted for all the overhead + * including the basic IPTFS header. + */ + if (skb->len <= mtu) { + iptfs_output_prepare_skb(skb, 0); + return 0; + } + + return iptfs_copy_create_frags(skbp, xtfs, mtu); +} + +static struct sk_buff **iptfs_rehome_fraglist(struct sk_buff **nextp, struct sk_buff *child) +{ + u32 fllen = 0; + + /* It might be possible to account for a frag list in addition to page + * fragment if it's a valid state to be in. The page fragments size + * should be kept as data_len so only the frag_list size is removed, + * this must be done above as well. + */ + *nextp = skb_shinfo(child)->frag_list; + while (*nextp) { + fllen += (*nextp)->len; + nextp = &(*nextp)->next; + } + skb_frag_list_init(child); + child->len -= fllen; + child->data_len -= fllen; + + return nextp; +} + +static void iptfs_consume_frags(struct sk_buff *to, struct sk_buff *from) +{ + struct skb_shared_info *fromi = skb_shinfo(from); + struct skb_shared_info *toi = skb_shinfo(to); + unsigned int new_truesize; + + /* If we have data in a head page, grab it */ + if (!skb_headlen(from)) { + new_truesize = SKB_TRUESIZE(skb_end_offset(from)); + } else { + iptfs_skb_head_to_frag(from, &toi->frags[toi->nr_frags]); + skb_frag_ref(to, toi->nr_frags++); + new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff)); + } + + /* Move any other page fragments rather than copy */ + memcpy(&toi->frags[toi->nr_frags], fromi->frags, + sizeof(fromi->frags[0]) * fromi->nr_frags); + toi->nr_frags += fromi->nr_frags; + fromi->nr_frags = 0; + from->data_len = 0; + from->len = 0; + to->truesize += from->truesize - new_truesize; + from->truesize = new_truesize; + + /* We are done with this SKB */ + consume_skb(from); +} + +static void iptfs_output_queued(struct xfrm_state *x, struct sk_buff_head *list) +{ + struct xfrm_iptfs_data *xtfs = x->mode_data; + struct sk_buff *skb, *skb2, **nextp; + struct skb_shared_info *shi, *shi2; + + /* If we are fragmenting due to a large inner packet we will output all + * the outer IPTFS packets required to contain the fragments of the + * single large inner packet. These outer packets need to be sent + * consecutively (ESP seq-wise). Since this output function is always + * running from a timer we do not need a lock to provide this guarantee. + * We will output our packets consecutively before the timer is allowed + * to run again on some other CPU. + */ + + while ((skb = __skb_dequeue(list))) { + u32 mtu = iptfs_get_cur_pmtu(x, xtfs, skb); + bool share_ok = true; + int remaining; + + /* protocol comes to us cleared sometimes */ + skb->protocol = x->outer_mode.family == AF_INET ? htons(ETH_P_IP) : + htons(ETH_P_IPV6); + + if (skb->len > mtu && xtfs->cfg.dont_frag) { + /* We handle this case before enqueueing so we are only + * here b/c MTU changed after we enqueued before we + * dequeued, just drop these. + */ + XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTERROR); + + trace_iptfs_first_toobig(skb, mtu, 0, ip_hdr(skb)); + kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG); + continue; + } + + /* Convert first inner packet into an outer IPTFS packet, + * dealing with any fragmentation into multiple outer packets + * if necessary. + */ + if (iptfs_first_skb(&skb, xtfs, mtu)) + continue; + + /* If fragmentation was required the returned skb is the last + * IPTFS fragment in the chain, and it's IPTFS header blkoff has + * been set just past the end of the fragment data. + * + * In either case the space remaining to send more inner packet + * data is `mtu` - (skb->len - sizeof iptfs header). This is b/c + * the `mtu` value has the basic IPTFS header len accounted for, + * and we added that header to the skb so it is a part of + * skb->len, thus we subtract it from the skb length. + */ + remaining = mtu - (skb->len - sizeof(struct ip_iptfs_hdr)); + + /* Re-home (un-nest) nested fragment lists. We need to do this + * b/c we will simply be appending any following aggregated + * inner packets using the frag list. + */ + shi = skb_shinfo(skb); + nextp = &shi->frag_list; + while (*nextp) { + if (skb_has_frag_list(*nextp)) + nextp = iptfs_rehome_fraglist(&(*nextp)->next, *nextp); + else + nextp = &(*nextp)->next; + } + + if (shi->frag_list || skb_cloned(skb) || skb_shared(skb)) + share_ok = false; + + /* See if we have enough space to simply append. + * + * NOTE: Maybe do not append if we will be mis-aligned, + * SW-based endpoints will probably have to copy in this + * case. + */ + while ((skb2 = skb_peek(list))) { + trace_iptfs_ingress_nth_peek(skb2, remaining); + if (skb2->len > remaining) + break; + + __skb_unlink(skb2, list); + + /* Consider the buffer Tx'd and no longer owned */ + skb_orphan(skb); + + /* If we don't have a cksum in the packet we need to add + * one before encapsulation. + */ + if (skb2->ip_summed == CHECKSUM_PARTIAL) { + if (skb_checksum_help(skb2)) { + XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTERROR); + kfree_skb(skb2); + continue; + } + } + + /* skb->pp_recycle is passed to __skb_flag_unref for all + * frag pages so we can only share pages with skb's who + * match ourselves. + */ + shi2 = skb_shinfo(skb2); + if (share_ok && + (shi2->frag_list || + (!skb2->head_frag && skb_headlen(skb)) || + skb->pp_recycle != skb2->pp_recycle || + skb_zcopy(skb2) || + (shi->nr_frags + shi2->nr_frags + 1 > MAX_SKB_FRAGS))) + share_ok = false; + + /* Do accounting */ + skb->data_len += skb2->len; + skb->len += skb2->len; + remaining -= skb2->len; + + trace_iptfs_ingress_nth_add(skb2, share_ok); + + if (share_ok) { + iptfs_consume_frags(skb, skb2); + } else { + /* Append to the frag_list */ + *nextp = skb2; + nextp = &skb2->next; + if (skb_has_frag_list(skb2)) + nextp = iptfs_rehome_fraglist(nextp, + skb2); + skb->truesize += skb2->truesize; + } + } + + xfrm_output(NULL, skb); + } +} + +static enum hrtimer_restart iptfs_delay_timer(struct hrtimer *me) +{ + struct sk_buff_head list; + struct xfrm_iptfs_data *xtfs; + struct xfrm_state *x; + time64_t settime; + + xtfs = container_of(me, typeof(*xtfs), iptfs_timer); + x = xtfs->x; + + /* Process all the queued packets + * + * softirq execution order: timer > tasklet > hrtimer + * + * Network rx will have run before us giving one last chance to queue + * ingress packets for us to process and transmit. + */ + + spin_lock(&x->lock); + __skb_queue_head_init(&list); + skb_queue_splice_init(&xtfs->queue, &list); + xtfs->queue_size = 0; + settime = xtfs->iptfs_settime; + spin_unlock(&x->lock); + + /* After the above unlock, packets can begin queuing again, and the + * timer can be set again, from another CPU either in softirq or user + * context (not from this one since we are running at softirq level + * already). + */ + + trace_iptfs_timer_expire(xtfs, (unsigned long long)(ktime_get_raw_fast_ns() - settime)); + + iptfs_output_queued(x, &list); + + return HRTIMER_NORESTART; +} + +/** + * iptfs_encap_add_ipv4() - add outer encaps + * @x: xfrm state + * @skb: the packet + * + * This was originally taken from xfrm4_tunnel_encap_add. The reason for the + * copy is that IP-TFS/AGGFRAG can have different functionality for how to set + * the TOS/DSCP bits. Sets the protocol to a different value and doesn't do + * anything with inner headers as they aren't pointing into a normal IP + * singleton inner packet. + * + * Return: 0 on success or a negative error code on failure + */ +static int iptfs_encap_add_ipv4(struct xfrm_state *x, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct iphdr *top_iph; + + skb_reset_inner_network_header(skb); + skb_reset_inner_transport_header(skb); + + skb_set_network_header(skb, -(x->props.header_len - x->props.enc_hdr_len)); + skb->mac_header = skb->network_header + offsetof(struct iphdr, protocol); + skb->transport_header = skb->network_header + sizeof(*top_iph); + + top_iph = ip_hdr(skb); + top_iph->ihl = 5; + top_iph->version = 4; + top_iph->protocol = IPPROTO_AGGFRAG; + + /* As we have 0, fractional, 1 or N inner packets there's no obviously + * correct DSCP mapping to inherit. ECN should be cleared per RFC9347 + * 3.1. + */ + top_iph->tos = 0; + + top_iph->frag_off = htons(IP_DF); + top_iph->ttl = ip4_dst_hoplimit(xfrm_dst_child(dst)); + top_iph->saddr = x->props.saddr.a4; + top_iph->daddr = x->id.daddr.a4; + ip_select_ident(dev_net(dst->dev), skb, NULL); + + return 0; +} + +#if IS_ENABLED(CONFIG_IPV6) +/** + * iptfs_encap_add_ipv6() - add outer encaps + * @x: xfrm state + * @skb: the packet + * + * This was originally taken from xfrm6_tunnel_encap_add. The reason for the + * copy is that IP-TFS/AGGFRAG can have different functionality for how to set + * the flow label and TOS/DSCP bits. It also sets the protocol to a different + * value and doesn't do anything with inner headers as they aren't pointing into + * a normal IP singleton inner packet. + * + * Return: 0 on success or a negative error code on failure + */ +static int iptfs_encap_add_ipv6(struct xfrm_state *x, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct ipv6hdr *top_iph; + int dsfield; + + skb_reset_inner_network_header(skb); + skb_reset_inner_transport_header(skb); + + skb_set_network_header(skb, -x->props.header_len + x->props.enc_hdr_len); + skb->mac_header = skb->network_header + offsetof(struct ipv6hdr, nexthdr); + skb->transport_header = skb->network_header + sizeof(*top_iph); + + top_iph = ipv6_hdr(skb); + top_iph->version = 6; + top_iph->priority = 0; + memset(top_iph->flow_lbl, 0, sizeof(top_iph->flow_lbl)); + top_iph->nexthdr = IPPROTO_AGGFRAG; + + /* As we have 0, fractional, 1 or N inner packets there's no obviously + * correct DSCP mapping to inherit. ECN should be cleared per RFC9347 + * 3.1. + */ + dsfield = 0; + ipv6_change_dsfield(top_iph, 0, dsfield); + + top_iph->hop_limit = ip6_dst_hoplimit(xfrm_dst_child(dst)); + top_iph->saddr = *(struct in6_addr *)&x->props.saddr; + top_iph->daddr = *(struct in6_addr *)&x->id.daddr; + + return 0; +} +#endif + +/** + * iptfs_prepare_output() - prepare the skb for output + * @x: xfrm state + * @skb: the packet + * + * Return: Error value, if 0 then skb values should be as follows: + * - transport_header should point at ESP header + * - network_header should point at Outer IP header + * - mac_header should point at protocol/nexthdr of the outer IP + */ +static int iptfs_prepare_output(struct xfrm_state *x, struct sk_buff *skb) +{ + if (x->outer_mode.family == AF_INET) + return iptfs_encap_add_ipv4(x, skb); + if (x->outer_mode.family == AF_INET6) { +#if IS_ENABLED(CONFIG_IPV6) + return iptfs_encap_add_ipv6(x, skb); +#else + return -EAFNOSUPPORT; +#endif + } + return -EOPNOTSUPP; +} + +/* ========================== */ +/* State Management Functions */ +/* ========================== */ + +/** + * __iptfs_get_inner_mtu() - return inner MTU with no fragmentation. + * @x: xfrm state. + * @outer_mtu: the outer mtu + * + * Return: Correct MTU taking in to account the encap overhead. + */ +static u32 __iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu) +{ + struct crypto_aead *aead; + u32 blksize; + + aead = x->data; + blksize = ALIGN(crypto_aead_blocksize(aead), 4); + return ((outer_mtu - x->props.header_len - crypto_aead_authsize(aead)) & + ~(blksize - 1)) - 2; +} + +/** + * iptfs_get_inner_mtu() - return the inner MTU for an IPTFS xfrm. + * @x: xfrm state. + * @outer_mtu: Outer MTU for the encapsulated packet. + * + * Return: Correct MTU taking in to account the encap overhead. + */ +static u32 iptfs_get_inner_mtu(struct xfrm_state *x, int outer_mtu) +{ + struct xfrm_iptfs_data *xtfs = x->mode_data; + + /* If not dont-frag we have no MTU */ + if (!xtfs->cfg.dont_frag) + return x->outer_mode.family == AF_INET ? IP_MAX_MTU : IP6_MAX_MTU; + return __iptfs_get_inner_mtu(x, outer_mtu); +} + +/** + * iptfs_user_init() - initialize the SA with IPTFS options from netlink. + * @net: the net data + * @x: xfrm state + * @attrs: netlink attributes + * @extack: extack return data + * + * Return: 0 on success or a negative error code on failure + */ +static int iptfs_user_init(struct net *net, struct xfrm_state *x, + struct nlattr **attrs, + struct netlink_ext_ack *extack) +{ + struct xfrm_iptfs_data *xtfs = x->mode_data; + struct xfrm_iptfs_config *xc; + u64 q; + + xc = &xtfs->cfg; + xc->max_queue_size = IPTFS_DEFAULT_MAX_QUEUE_SIZE; + xc->reorder_win_size = IPTFS_DEFAULT_REORDER_WINDOW; + xtfs->drop_time_ns = IPTFS_DEFAULT_DROP_TIME_USECS * NSECS_IN_USEC; + xtfs->init_delay_ns = IPTFS_DEFAULT_INIT_DELAY_USECS * NSECS_IN_USEC; + + if (attrs[XFRMA_IPTFS_DONT_FRAG]) + xc->dont_frag = true; + if (attrs[XFRMA_IPTFS_REORDER_WINDOW]) + xc->reorder_win_size = + nla_get_u16(attrs[XFRMA_IPTFS_REORDER_WINDOW]); + /* saved array is for saving 1..N seq nums from wantseq */ + if (xc->reorder_win_size) { + xtfs->w_saved = kcalloc(xc->reorder_win_size, + sizeof(*xtfs->w_saved), GFP_KERNEL); + if (!xtfs->w_saved) { + NL_SET_ERR_MSG(extack, "Cannot alloc reorder window"); + return -ENOMEM; + } + } + if (attrs[XFRMA_IPTFS_PKT_SIZE]) { + xc->pkt_size = nla_get_u32(attrs[XFRMA_IPTFS_PKT_SIZE]); + if (!xc->pkt_size) { + xtfs->payload_mtu = 0; + } else if (xc->pkt_size > x->props.header_len) { + xtfs->payload_mtu = xc->pkt_size - x->props.header_len; + } else { + NL_SET_ERR_MSG(extack, + "Packet size must be 0 or greater than IPTFS/ESP header length"); + return -EINVAL; + } + } + if (attrs[XFRMA_IPTFS_MAX_QSIZE]) + xc->max_queue_size = nla_get_u32(attrs[XFRMA_IPTFS_MAX_QSIZE]); + if (attrs[XFRMA_IPTFS_DROP_TIME]) + xtfs->drop_time_ns = + (u64)nla_get_u32(attrs[XFRMA_IPTFS_DROP_TIME]) * + NSECS_IN_USEC; + if (attrs[XFRMA_IPTFS_INIT_DELAY]) + xtfs->init_delay_ns = + (u64)nla_get_u32(attrs[XFRMA_IPTFS_INIT_DELAY]) * NSECS_IN_USEC; + + q = (u64)xc->max_queue_size * 95; + do_div(q, 100); + xtfs->ecn_queue_size = (u32)q; + + return 0; +} + +static unsigned int iptfs_sa_len(const struct xfrm_state *x) +{ + struct xfrm_iptfs_data *xtfs = x->mode_data; + struct xfrm_iptfs_config *xc = &xtfs->cfg; + unsigned int l = 0; + + if (x->dir == XFRM_SA_DIR_IN) { + l += nla_total_size(sizeof(u32)); /* drop time usec */ + l += nla_total_size(sizeof(xc->reorder_win_size)); + } else { + if (xc->dont_frag) + l += nla_total_size(0); /* dont-frag flag */ + l += nla_total_size(sizeof(u32)); /* init delay usec */ + l += nla_total_size(sizeof(xc->max_queue_size)); + l += nla_total_size(sizeof(xc->pkt_size)); + } + + return l; +} + +static int iptfs_copy_to_user(struct xfrm_state *x, struct sk_buff *skb) +{ + struct xfrm_iptfs_data *xtfs = x->mode_data; + struct xfrm_iptfs_config *xc = &xtfs->cfg; + int ret = 0; + u64 q; + + if (x->dir == XFRM_SA_DIR_IN) { + q = xtfs->drop_time_ns; + do_div(q, NSECS_IN_USEC); + ret = nla_put_u32(skb, XFRMA_IPTFS_DROP_TIME, q); + if (ret) + return ret; + + ret = nla_put_u16(skb, XFRMA_IPTFS_REORDER_WINDOW, + xc->reorder_win_size); + } else { + if (xc->dont_frag) { + ret = nla_put_flag(skb, XFRMA_IPTFS_DONT_FRAG); + if (ret) + return ret; + } + + q = xtfs->init_delay_ns; + do_div(q, NSECS_IN_USEC); + ret = nla_put_u32(skb, XFRMA_IPTFS_INIT_DELAY, q); + if (ret) + return ret; + + ret = nla_put_u32(skb, XFRMA_IPTFS_MAX_QSIZE, xc->max_queue_size); + if (ret) + return ret; + + ret = nla_put_u32(skb, XFRMA_IPTFS_PKT_SIZE, xc->pkt_size); + } + + return ret; +} + +static void __iptfs_init_state(struct xfrm_state *x, + struct xfrm_iptfs_data *xtfs) +{ + __skb_queue_head_init(&xtfs->queue); + hrtimer_init(&xtfs->iptfs_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE); + xtfs->iptfs_timer.function = iptfs_delay_timer; + + spin_lock_init(&xtfs->drop_lock); + hrtimer_init(&xtfs->drop_timer, CLOCK_MONOTONIC, IPTFS_HRTIMER_MODE); + xtfs->drop_timer.function = iptfs_drop_timer; + + /* Modify type (esp) adjustment values */ + + if (x->props.family == AF_INET) + x->props.header_len += sizeof(struct iphdr) + sizeof(struct ip_iptfs_hdr); + else if (x->props.family == AF_INET6) + x->props.header_len += sizeof(struct ipv6hdr) + sizeof(struct ip_iptfs_hdr); + x->props.enc_hdr_len = sizeof(struct ip_iptfs_hdr); + + /* Always keep a module reference when x->mode_data is set */ + __module_get(x->mode_cbs->owner); + + x->mode_data = xtfs; + xtfs->x = x; +} + +static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig) +{ + struct xfrm_iptfs_data *xtfs; + + xtfs = kmemdup(orig->mode_data, sizeof(*xtfs), GFP_KERNEL); + if (!xtfs) + return -ENOMEM; + + x->mode_data = xtfs; + xtfs->x = x; + + xtfs->ra_newskb = NULL; + if (xtfs->cfg.reorder_win_size) { + xtfs->w_saved = kcalloc(xtfs->cfg.reorder_win_size, + sizeof(*xtfs->w_saved), GFP_KERNEL); + if (!xtfs->w_saved) { + kfree_sensitive(xtfs); + return -ENOMEM; + } + } + + return 0; +} + +static int iptfs_init_state(struct xfrm_state *x) +{ + struct xfrm_iptfs_data *xtfs; + + if (x->mode_data) { + /* We have arrived here from xfrm_state_clone() */ + xtfs = x->mode_data; + } else { + xtfs = kzalloc(sizeof(*xtfs), GFP_KERNEL); + if (!xtfs) + return -ENOMEM; + } + + __iptfs_init_state(x, xtfs); + + return 0; +} + +static void iptfs_destroy_state(struct xfrm_state *x) +{ + struct xfrm_iptfs_data *xtfs = x->mode_data; + struct sk_buff_head list; + struct skb_wseq *s, *se; + struct sk_buff *skb; + + if (!xtfs) + return; + + spin_lock_bh(&xtfs->x->lock); + hrtimer_cancel(&xtfs->iptfs_timer); + __skb_queue_head_init(&list); + skb_queue_splice_init(&xtfs->queue, &list); + spin_unlock_bh(&xtfs->x->lock); + + while ((skb = __skb_dequeue(&list))) + kfree_skb(skb); + + spin_lock_bh(&xtfs->drop_lock); + hrtimer_cancel(&xtfs->drop_timer); + spin_unlock_bh(&xtfs->drop_lock); + + if (xtfs->ra_newskb) + kfree_skb(xtfs->ra_newskb); + + for (s = xtfs->w_saved, se = s + xtfs->w_savedlen; s < se; s++) { + if (s->skb) + kfree_skb(s->skb); + } + + kfree_sensitive(xtfs->w_saved); + kfree_sensitive(xtfs); + + module_put(x->mode_cbs->owner); +} + +static const struct xfrm_mode_cbs iptfs_mode_cbs = { + .owner = THIS_MODULE, + .init_state = iptfs_init_state, + .clone_state = iptfs_clone_state, + .destroy_state = iptfs_destroy_state, + .user_init = iptfs_user_init, + .copy_to_user = iptfs_copy_to_user, + .sa_len = iptfs_sa_len, + .get_inner_mtu = iptfs_get_inner_mtu, + .input = iptfs_input, + .output = iptfs_output_collect, + .prepare_output = iptfs_prepare_output, +}; + +static int __init xfrm_iptfs_init(void) +{ + int err; + + pr_info("xfrm_iptfs: IPsec IP-TFS tunnel mode module\n"); + + err = xfrm_register_mode_cbs(XFRM_MODE_IPTFS, &iptfs_mode_cbs); + if (err < 0) + pr_info("%s: can't register IP-TFS\n", __func__); + + return err; +} + +static void __exit xfrm_iptfs_fini(void) +{ + xfrm_unregister_mode_cbs(XFRM_MODE_IPTFS); +} + +module_init(xfrm_iptfs_init); +module_exit(xfrm_iptfs_fini); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("IP-TFS support for xfrm ipsec tunnels"); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index e5722c95b8bb..f7abd42c077d 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -472,6 +472,8 @@ static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb) WARN_ON_ONCE(1); break; default: + if (x->mode_cbs && x->mode_cbs->prepare_output) + return x->mode_cbs->prepare_output(x, skb); WARN_ON_ONCE(1); break; } @@ -675,6 +677,10 @@ static void xfrm_get_inner_ipproto(struct sk_buff *skb, struct xfrm_state *x) return; } + if (x->outer_mode.encap == XFRM_MODE_IPTFS) { + xo->inner_ipproto = IPPROTO_AGGFRAG; + return; + } /* non-Tunnel Mode */ if (!skb->encapsulation) @@ -796,7 +802,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) { skb->protocol = htons(ETH_P_IP); - if (skb->sk) + if (skb->sk && sk_fullsock(skb->sk)) xfrm_local_error(skb, mtu); else icmp_send(skb, ICMP_DEST_UNREACH, @@ -832,6 +838,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; struct dst_entry *dst = skb_dst(skb); + struct sock *sk = skb_to_full_sk(skb); if (skb->ignore_df) goto out; @@ -846,9 +853,9 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) skb->dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); - if (xfrm6_local_dontfrag(skb->sk)) + if (xfrm6_local_dontfrag(sk)) ipv6_stub->xfrm6_local_rxpmtu(skb, mtu); - else if (skb->sk) + else if (sk) xfrm_local_error(skb, mtu); else icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 4408c11c0835..6551e588fe52 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2497,6 +2497,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i]; if (tmpl->mode == XFRM_MODE_TUNNEL || + tmpl->mode == XFRM_MODE_IPTFS || tmpl->mode == XFRM_MODE_BEET) { remote = &tmpl->id.daddr; local = &tmpl->saddr; @@ -2748,13 +2749,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst1->input = dst_discard; - rcu_read_lock(); - afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family); - if (likely(afinfo)) - dst1->output = afinfo->output; - else - dst1->output = dst_discard_out; - rcu_read_unlock(); + if (xfrm[i]->mode_cbs && xfrm[i]->mode_cbs->output) { + dst1->output = xfrm[i]->mode_cbs->output; + } else { + rcu_read_lock(); + afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family); + if (likely(afinfo)) + dst1->output = afinfo->output; + else + dst1->output = dst_discard_out; + rcu_read_unlock(); + } xdst_prev = xdst; @@ -2959,7 +2964,7 @@ static void xfrm_policy_queue_process(struct timer_list *t) skb_dst_drop(skb); skb_dst_set(skb, dst); - dst_output(net, skb->sk, skb); + dst_output(net, skb_to_full_sk(skb), skb); } out: @@ -3290,7 +3295,8 @@ no_transform: ok: xfrm_pols_put(pols, drop_pols); if (dst && dst->xfrm && - dst->xfrm->props.mode == XFRM_MODE_TUNNEL) + (dst->xfrm->props.mode == XFRM_MODE_TUNNEL || + dst->xfrm->props.mode == XFRM_MODE_IPTFS)) dst->flags |= DST_XFRM_TUNNEL; return dst; @@ -4519,6 +4525,7 @@ static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tm switch (t->mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: + case XFRM_MODE_IPTFS: if (xfrm_addr_equal(&t->id.daddr, &m->old_daddr, m->old_family) && xfrm_addr_equal(&t->saddr, &m->old_saddr, @@ -4561,7 +4568,8 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, continue; n++; if (pol->xfrm_vec[i].mode != XFRM_MODE_TUNNEL && - pol->xfrm_vec[i].mode != XFRM_MODE_BEET) + pol->xfrm_vec[i].mode != XFRM_MODE_BEET && + pol->xfrm_vec[i].mode != XFRM_MODE_IPTFS) continue; /* update endpoints */ memcpy(&pol->xfrm_vec[i].id.daddr, &mp->new_daddr, diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index eeb984be03a7..8e07dd614b0b 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -43,6 +43,8 @@ static const struct snmp_mib xfrm_mib_list[] = { SNMP_MIB_ITEM("XfrmAcquireError", LINUX_MIB_XFRMACQUIREERROR), SNMP_MIB_ITEM("XfrmOutStateDirError", LINUX_MIB_XFRMOUTSTATEDIRERROR), SNMP_MIB_ITEM("XfrmInStateDirError", LINUX_MIB_XFRMINSTATEDIRERROR), + SNMP_MIB_ITEM("XfrmInIptfsError", LINUX_MIB_XFRMINIPTFSERROR), + SNMP_MIB_ITEM("XfrmOutNoQueueSpace", LINUX_MIB_XFRMOUTNOQSPACE), SNMP_MIB_SENTINEL }; diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index bc56c6305725..dbdf8a39dffe 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -714,10 +714,12 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff oseq += skb_shinfo(skb)->gso_segs; } - if (unlikely(xo->seq.low < replay_esn->oseq)) { - XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi; - xo->seq.hi = oseq_hi; - replay_esn->oseq_hi = oseq_hi; + if (unlikely(oseq < replay_esn->oseq)) { + replay_esn->oseq_hi = ++oseq_hi; + if (xo->seq.low < replay_esn->oseq) { + XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi; + xo->seq.hi = oseq_hi; + } if (replay_esn->oseq_hi == 0) { replay_esn->oseq--; replay_esn->oseq_hi--; @@ -729,6 +731,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff } replay_esn->oseq = oseq; + xfrm_dev_state_advance_esn(x); if (xfrm_aevent_is_on(net)) xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 67ca7ac955a3..ad2202fa82f3 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -34,6 +34,8 @@ #define xfrm_state_deref_prot(table, net) \ rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) +#define xfrm_state_deref_check(table, net) \ + rcu_dereference_check((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) static void xfrm_state_gc_task(struct work_struct *work); @@ -62,6 +64,8 @@ static inline unsigned int xfrm_dst_hash(struct net *net, u32 reqid, unsigned short family) { + lockdep_assert_held(&net->xfrm.xfrm_state_lock); + return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask); } @@ -70,6 +74,8 @@ static inline unsigned int xfrm_src_hash(struct net *net, const xfrm_address_t *saddr, unsigned short family) { + lockdep_assert_held(&net->xfrm.xfrm_state_lock); + return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask); } @@ -77,11 +83,15 @@ static inline unsigned int xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { + lockdep_assert_held(&net->xfrm.xfrm_state_lock); + return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } static unsigned int xfrm_seq_hash(struct net *net, u32 seq) { + lockdep_assert_held(&net->xfrm.xfrm_state_lock); + return __xfrm_seq_hash(seq, net->xfrm.state_hmask); } @@ -467,6 +477,11 @@ static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = { .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, + [XFRM_MODE_IPTFS] = { + .encap = XFRM_MODE_IPTFS, + .flags = XFRM_MODE_FLAG_TUNNEL, + .family = AF_INET, + }, }; static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = { @@ -488,6 +503,11 @@ static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = { .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, + [XFRM_MODE_IPTFS] = { + .encap = XFRM_MODE_IPTFS, + .flags = XFRM_MODE_FLAG_TUNNEL, + .family = AF_INET6, + }, }; static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) @@ -515,6 +535,60 @@ static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) return NULL; } +static const struct xfrm_mode_cbs __rcu *xfrm_mode_cbs_map[XFRM_MODE_MAX]; +static DEFINE_SPINLOCK(xfrm_mode_cbs_map_lock); + +int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs) +{ + if (mode >= XFRM_MODE_MAX) + return -EINVAL; + + spin_lock_bh(&xfrm_mode_cbs_map_lock); + rcu_assign_pointer(xfrm_mode_cbs_map[mode], mode_cbs); + spin_unlock_bh(&xfrm_mode_cbs_map_lock); + + return 0; +} +EXPORT_SYMBOL(xfrm_register_mode_cbs); + +void xfrm_unregister_mode_cbs(u8 mode) +{ + if (mode >= XFRM_MODE_MAX) + return; + + spin_lock_bh(&xfrm_mode_cbs_map_lock); + RCU_INIT_POINTER(xfrm_mode_cbs_map[mode], NULL); + spin_unlock_bh(&xfrm_mode_cbs_map_lock); + synchronize_rcu(); +} +EXPORT_SYMBOL(xfrm_unregister_mode_cbs); + +static const struct xfrm_mode_cbs *xfrm_get_mode_cbs(u8 mode) +{ + const struct xfrm_mode_cbs *cbs; + bool try_load = true; + + if (mode >= XFRM_MODE_MAX) + return NULL; + +retry: + rcu_read_lock(); + + cbs = rcu_dereference(xfrm_mode_cbs_map[mode]); + if (cbs && !try_module_get(cbs->owner)) + cbs = NULL; + + rcu_read_unlock(); + + if (mode == XFRM_MODE_IPTFS && !cbs && try_load) { + request_module("xfrm-iptfs"); + try_load = false; + goto retry; + } + + return cbs; +} + void xfrm_state_free(struct xfrm_state *x) { kmem_cache_free(xfrm_state_cache, x); @@ -523,6 +597,8 @@ EXPORT_SYMBOL(xfrm_state_free); static void ___xfrm_state_destroy(struct xfrm_state *x) { + if (x->mode_cbs && x->mode_cbs->destroy_state) + x->mode_cbs->destroy_state(x); hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); kfree(x->aead); @@ -682,6 +758,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) x->replay_maxdiff = 0; x->pcpu_num = UINT_MAX; spin_lock_init(&x->lock); + x->mode_data = NULL; } return x; } @@ -1041,16 +1118,38 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl, x->props.family = tmpl->encap_family; } -static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark, +struct xfrm_hash_state_ptrs { + const struct hlist_head *bydst; + const struct hlist_head *bysrc; + const struct hlist_head *byspi; + unsigned int hmask; +}; + +static void xfrm_hash_ptrs_get(const struct net *net, struct xfrm_hash_state_ptrs *ptrs) +{ + unsigned int sequence; + + do { + sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); + + ptrs->bydst = xfrm_state_deref_check(net->xfrm.state_bydst, net); + ptrs->bysrc = xfrm_state_deref_check(net->xfrm.state_bysrc, net); + ptrs->byspi = xfrm_state_deref_check(net->xfrm.state_byspi, net); + ptrs->hmask = net->xfrm.state_hmask; + } while (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)); +} + +static struct xfrm_state *__xfrm_state_lookup_all(const struct xfrm_hash_state_ptrs *state_ptrs, + u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, struct xfrm_dev_offload *xdo) { - unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); + unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask); struct xfrm_state *x; - hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) { + hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) { #ifdef CONFIG_XFRM_OFFLOAD if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) @@ -1084,15 +1183,16 @@ static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark, return NULL; } -static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, +static struct xfrm_state *__xfrm_state_lookup(const struct xfrm_hash_state_ptrs *state_ptrs, + u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { - unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); + unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask); struct xfrm_state *x; - hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) { + hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || @@ -1114,11 +1214,11 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, __be32 spi, u8 proto, unsigned short family) { + struct xfrm_hash_state_ptrs state_ptrs; struct hlist_head *state_cache_input; struct xfrm_state *x = NULL; - int cpu = get_cpu(); - state_cache_input = per_cpu_ptr(net->xfrm.state_cache_input, cpu); + state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input); rcu_read_lock(); hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) { @@ -1135,7 +1235,9 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, goto out; } - x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family); + xfrm_hash_ptrs_get(net, &state_ptrs); + + x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family); if (x && x->km.state == XFRM_STATE_VALID) { spin_lock_bh(&net->xfrm.xfrm_state_lock); @@ -1150,20 +1252,20 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, out: rcu_read_unlock(); - put_cpu(); return x; } EXPORT_SYMBOL(xfrm_input_state_lookup); -static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, +static struct xfrm_state *__xfrm_state_lookup_byaddr(const struct xfrm_hash_state_ptrs *state_ptrs, + u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { - unsigned int h = xfrm_src_hash(net, daddr, saddr, family); + unsigned int h = __xfrm_src_hash(daddr, saddr, family, state_ptrs->hmask); struct xfrm_state *x; - hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) { + hlist_for_each_entry_rcu(x, state_ptrs->bysrc + h, bysrc) { if (x->props.family != family || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family) || @@ -1183,14 +1285,17 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, static inline struct xfrm_state * __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family) { + struct xfrm_hash_state_ptrs state_ptrs; struct net *net = xs_net(x); u32 mark = x->mark.v & x->mark.m; + xfrm_hash_ptrs_get(net, &state_ptrs); + if (use_spi) - return __xfrm_state_lookup(net, mark, &x->id.daddr, + return __xfrm_state_lookup(&state_ptrs, mark, &x->id.daddr, x->id.spi, x->id.proto, family); else - return __xfrm_state_lookup_byaddr(net, mark, + return __xfrm_state_lookup_byaddr(&state_ptrs, mark, &x->id.daddr, &x->props.saddr, x->id.proto, family); @@ -1264,6 +1369,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, u32 if_id) { static xfrm_address_t saddr_wildcard = { }; + struct xfrm_hash_state_ptrs state_ptrs; struct net *net = xp_net(pol); unsigned int h, h_wildcard; struct xfrm_state *x, *x0, *to_put; @@ -1328,8 +1434,10 @@ cached: else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */ WARN_ON(1); - h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); - hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) { + xfrm_hash_ptrs_get(net, &state_ptrs); + + h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask); + hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) @@ -1362,8 +1470,9 @@ cached: if (best || acquire_in_progress) goto found; - h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); - hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) { + h_wildcard = __xfrm_dst_hash(daddr, &saddr_wildcard, tmpl->reqid, + encap_family, state_ptrs.hmask); + hlist_for_each_entry_rcu(x, state_ptrs.bydst + h_wildcard, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) @@ -1401,7 +1510,7 @@ found: if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && - (x0 = __xfrm_state_lookup_all(net, mark, daddr, + (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr, tmpl->id.spi, tmpl->id.proto, encap_family, &pol->xdo)) != NULL) { @@ -1945,6 +2054,12 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->new_mapping_sport = 0; x->dir = orig->dir; + x->mode_cbs = orig->mode_cbs; + if (x->mode_cbs && x->mode_cbs->clone_state) { + if (x->mode_cbs->clone_state(x, orig)) + goto error; + } + return x; error: @@ -2180,10 +2295,13 @@ struct xfrm_state * xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { + struct xfrm_hash_state_ptrs state_ptrs; struct xfrm_state *x; rcu_read_lock(); - x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family); + xfrm_hash_ptrs_get(net, &state_ptrs); + + x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family); rcu_read_unlock(); return x; } @@ -2194,10 +2312,14 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { + struct xfrm_hash_state_ptrs state_ptrs; struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); - x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family); + + xfrm_hash_ptrs_get(net, &state_ptrs); + + x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } @@ -2271,6 +2393,7 @@ static int __xfrm6_state_sort_cmp(const void *p) #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: + case XFRM_MODE_IPTFS: return 4; } return 5; @@ -2297,6 +2420,7 @@ static int __xfrm6_tmpl_sort_cmp(const void *p) #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: + case XFRM_MODE_IPTFS: return 3; } return 4; @@ -2986,6 +3110,9 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) case XFRM_MODE_TUNNEL: break; default: + if (x->mode_cbs && x->mode_cbs->get_inner_mtu) + return x->mode_cbs->get_inner_mtu(x, mtu); + WARN_ON_ONCE(1); break; } @@ -3086,6 +3213,12 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, } } + x->mode_cbs = xfrm_get_mode_cbs(x->props.mode); + if (x->mode_cbs) { + if (x->mode_cbs->init_state) + err = x->mode_cbs->init_state(x); + module_put(x->mode_cbs->owner); + } error: return err; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b2876e09328b..08c6d6f0179f 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -301,6 +301,16 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, NL_SET_ERR_MSG(extack, "TFC padding can only be used in tunnel mode"); goto out; } + if ((attrs[XFRMA_IPTFS_DROP_TIME] || + attrs[XFRMA_IPTFS_REORDER_WINDOW] || + attrs[XFRMA_IPTFS_DONT_FRAG] || + attrs[XFRMA_IPTFS_INIT_DELAY] || + attrs[XFRMA_IPTFS_MAX_QSIZE] || + attrs[XFRMA_IPTFS_PKT_SIZE]) && + p->mode != XFRM_MODE_IPTFS) { + NL_SET_ERR_MSG(extack, "IP-TFS options can only be used in IP-TFS mode"); + goto out; + } break; case IPPROTO_COMP: @@ -373,6 +383,16 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_BEET: break; + case XFRM_MODE_IPTFS: + if (p->id.proto != IPPROTO_ESP) { + NL_SET_ERR_MSG(extack, "IP-TFS mode only supported with ESP"); + goto out; + } + if (sa_dir == 0) { + NL_SET_ERR_MSG(extack, "IP-TFS mode requires in or out direction attribute"); + goto out; + } + break; default: NL_SET_ERR_MSG(extack, "Unsupported mode"); @@ -421,6 +441,18 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, goto out; } + if (attrs[XFRMA_IPTFS_DROP_TIME]) { + NL_SET_ERR_MSG(extack, "IP-TFS drop time should not be set for output SA"); + err = -EINVAL; + goto out; + } + + if (attrs[XFRMA_IPTFS_REORDER_WINDOW]) { + NL_SET_ERR_MSG(extack, "IP-TFS reorder window should not be set for output SA"); + err = -EINVAL; + goto out; + } + if (attrs[XFRMA_REPLAY_VAL]) { struct xfrm_replay_state *replay; @@ -458,6 +490,30 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, } } + + if (attrs[XFRMA_IPTFS_DONT_FRAG]) { + NL_SET_ERR_MSG(extack, "IP-TFS don't fragment should not be set for input SA"); + err = -EINVAL; + goto out; + } + + if (attrs[XFRMA_IPTFS_INIT_DELAY]) { + NL_SET_ERR_MSG(extack, "IP-TFS initial delay should not be set for input SA"); + err = -EINVAL; + goto out; + } + + if (attrs[XFRMA_IPTFS_MAX_QSIZE]) { + NL_SET_ERR_MSG(extack, "IP-TFS max queue size should not be set for input SA"); + err = -EINVAL; + goto out; + } + + if (attrs[XFRMA_IPTFS_PKT_SIZE]) { + NL_SET_ERR_MSG(extack, "IP-TFS packet size should not be set for input SA"); + err = -EINVAL; + goto out; + } } if (!sa_dir && attrs[XFRMA_SA_PCPU]) { @@ -886,6 +942,12 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, goto error; } + if (x->mode_cbs && x->mode_cbs->user_init) { + err = x->mode_cbs->user_init(net, x, attrs, extack); + if (err) + goto error; + } + return x; error: @@ -1301,6 +1363,10 @@ static int copy_to_user_state_extra(struct xfrm_state *x, if (ret) goto out; } + if (x->mode_cbs && x->mode_cbs->copy_to_user) + ret = x->mode_cbs->copy_to_user(x, skb); + if (ret) + goto out; if (x->mapping_maxage) { ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage); if (ret) @@ -1958,6 +2024,8 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, return -EINVAL; } break; + case XFRM_MODE_IPTFS: + break; default: if (ut[i].family != prev_family) { NL_SET_ERR_MSG(extack, "Mode in template doesn't support a family change"); @@ -3220,6 +3288,12 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, [XFRMA_SA_PCPU] = { .type = NLA_U32 }, + [XFRMA_IPTFS_DROP_TIME] = { .type = NLA_U32 }, + [XFRMA_IPTFS_REORDER_WINDOW] = { .type = NLA_U16 }, + [XFRMA_IPTFS_DONT_FRAG] = { .type = NLA_FLAG }, + [XFRMA_IPTFS_INIT_DELAY] = { .type = NLA_U32 }, + [XFRMA_IPTFS_MAX_QSIZE] = { .type = NLA_U32 }, + [XFRMA_IPTFS_PKT_SIZE] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(xfrma_policy); @@ -3554,6 +3628,9 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) if (x->nat_keepalive_interval) l += nla_total_size(sizeof(x->nat_keepalive_interval)); + if (x->mode_cbs && x->mode_cbs->sa_len) + l += x->mode_cbs->sa_len(x); + return l; } diff --git a/rust/Makefile b/rust/Makefile index a40a3936126d..8fcfd60447bc 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -11,9 +11,6 @@ always-$(CONFIG_RUST) += exports_core_generated.h obj-$(CONFIG_RUST) += helpers/helpers.o CFLAGS_REMOVE_helpers/helpers.o = -Wmissing-prototypes -Wmissing-declarations -always-$(CONFIG_RUST) += libmacros.so -no-clean-files += libmacros.so - always-$(CONFIG_RUST) += bindings/bindings_generated.rs bindings/bindings_helpers_generated.rs obj-$(CONFIG_RUST) += bindings.o kernel.o always-$(CONFIG_RUST) += exports_helpers_generated.h \ @@ -38,9 +35,14 @@ obj-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated_kunit.o always-$(subst y,$(CONFIG_RUST),$(CONFIG_JUMP_LABEL)) += kernel/generated_arch_static_branch_asm.rs -# Avoids running `$(RUSTC)` for the sysroot when it may not be available. +# Avoids running `$(RUSTC)` when it may not be available. ifdef CONFIG_RUST +libmacros_name := $(shell MAKEFLAGS= $(RUSTC) --print file-names --crate-name macros --crate-type proc-macro - $@ + $(call rust_exports,$<,"EXPORT_SYMBOL_RUST_GPL(%s);\n") > $@ $(obj)/exports_core_generated.h: $(obj)/core.o FORCE $(call if_changed,exports) @@ -359,13 +362,13 @@ quiet_cmd_rustc_procmacro = $(RUSTC_OR_CLIPPY_QUIET) P $@ cmd_rustc_procmacro = \ $(RUSTC_OR_CLIPPY) $(rust_common_flags) \ -Clinker-flavor=gcc -Clinker=$(HOSTCC) \ - -Clink-args='$(call escsq,$(KBUILD_HOSTLDFLAGS))' \ + -Clink-args='$(call escsq,$(KBUILD_PROCMACROLDFLAGS))' \ --emit=dep-info=$(depfile) --emit=link=$@ --extern proc_macro \ --crate-type proc-macro \ - --crate-name $(patsubst lib%.so,%,$(notdir $@)) $< + --crate-name $(patsubst lib%.$(libmacros_extension),%,$(notdir $@)) $< # Procedural macros can only be used with the `rustc` that compiled it. -$(obj)/libmacros.so: $(src)/macros/lib.rs FORCE +$(obj)/$(libmacros_name): $(src)/macros/lib.rs FORCE +$(call if_changed_dep,rustc_procmacro) quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L $@ @@ -382,7 +385,7 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L $(cmd_objtool) rust-analyzer: - $(Q)$(srctree)/scripts/generate_rust_analyzer.py \ + $(Q)MAKEFLAGS= $(srctree)/scripts/generate_rust_analyzer.py \ --cfgs='core=$(core-cfgs)' \ $(realpath $(srctree)) $(realpath $(objtree)) \ $(rustc_sysroot) $(RUST_LIB_SRC) $(if $(KBUILD_EXTMOD),$(srcroot)) \ @@ -401,11 +404,36 @@ ifneq ($(or $(CONFIG_ARM64),$(and $(CONFIG_RISCV),$(CONFIG_64BIT))),) __ashlti3 __lshrti3 endif +ifdef CONFIG_MODVERSIONS +cmd_gendwarfksyms = $(if $(skip_gendwarfksyms),, \ + $(call rust_exports,$@,"%s\n") | \ + scripts/gendwarfksyms/gendwarfksyms \ + $(if $(KBUILD_GENDWARFKSYMS_STABLE), --stable) \ + $(if $(KBUILD_SYMTYPES), --symtypes $(@:.o=.symtypes),) \ + $@ >> $(dot-target).cmd) +endif + define rule_rustc_library $(call cmd_and_fixdep,rustc_library) $(call cmd,gen_objtooldep) + $(call cmd,gendwarfksyms) endef +define rule_rust_cc_library + $(call if_changed_rule,cc_o_c) + $(call cmd,force_checksrc) + $(call cmd,gendwarfksyms) +endef + +# helpers.o uses the same export mechanism as Rust libraries, so ensure symbol +# versions are calculated for the helpers too. +$(obj)/helpers/helpers.o: $(src)/helpers/helpers.c $(recordmcount_source) FORCE + +$(call if_changed_rule,rust_cc_library) + +# Disable symbol versioning for exports.o to avoid conflicts with the actual +# symbol versions generated from Rust objects. +$(obj)/exports.o: private skip_gendwarfksyms = 1 + $(obj)/core.o: private skip_clippy = 1 $(obj)/core.o: private skip_flags = -Wunreachable_pub $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym)) @@ -417,13 +445,16 @@ ifneq ($(or $(CONFIG_X86_64),$(CONFIG_X86_32)),) $(obj)/core.o: scripts/target.json endif +$(obj)/compiler_builtins.o: private skip_gendwarfksyms = 1 $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*' $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE +$(call if_changed_rule,rustc_library) +$(obj)/build_error.o: private skip_gendwarfksyms = 1 $(obj)/build_error.o: $(src)/build_error.rs $(obj)/compiler_builtins.o FORCE +$(call if_changed_rule,rustc_library) +$(obj)/ffi.o: private skip_gendwarfksyms = 1 $(obj)/ffi.o: $(src)/ffi.rs $(obj)/compiler_builtins.o FORCE +$(call if_changed_rule,rustc_library) @@ -435,6 +466,7 @@ $(obj)/bindings.o: $(src)/bindings/lib.rs \ +$(call if_changed_rule,rustc_library) $(obj)/uapi.o: private rustc_target_flags = --extern ffi +$(obj)/uapi.o: private skip_gendwarfksyms = 1 $(obj)/uapi.o: $(src)/uapi/lib.rs \ $(obj)/ffi.o \ $(obj)/uapi/uapi_generated.rs FORCE @@ -443,7 +475,7 @@ $(obj)/uapi.o: $(src)/uapi/lib.rs \ $(obj)/kernel.o: private rustc_target_flags = --extern ffi \ --extern build_error --extern macros --extern bindings --extern uapi $(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/build_error.o \ - $(obj)/libmacros.so $(obj)/bindings.o $(obj)/uapi.o FORCE + $(obj)/$(libmacros_name) $(obj)/bindings.o $(obj)/uapi.o FORCE +$(call if_changed_rule,rustc_library) ifdef CONFIG_JUMP_LABEL diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 5c4dfe22f41a..55354e4dec14 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -20,9 +20,13 @@ #include #include #include +#include +#include #include #include +#include #include +#include #include #include #include diff --git a/rust/ffi.rs b/rust/ffi.rs index be153c4d551b..584f75b49862 100644 --- a/rust/ffi.rs +++ b/rust/ffi.rs @@ -10,4 +10,39 @@ #![no_std] -pub use core::ffi::*; +macro_rules! alias { + ($($name:ident = $ty:ty;)*) => {$( + #[allow(non_camel_case_types, missing_docs)] + pub type $name = $ty; + + // Check size compatibility with `core`. + const _: () = assert!( + core::mem::size_of::<$name>() == core::mem::size_of::() + ); + )*} +} + +alias! { + // `core::ffi::c_char` is either `i8` or `u8` depending on architecture. In the kernel, we use + // `-funsigned-char` so it's always mapped to `u8`. + c_char = u8; + + c_schar = i8; + c_uchar = u8; + + c_short = i16; + c_ushort = u16; + + c_int = i32; + c_uint = u32; + + // In the kernel, `intptr_t` is defined to be `long` in all platforms, so we can map the type to + // `isize`. + c_long = isize; + c_ulong = usize; + + c_longlong = i64; + c_ulonglong = u64; +} + +pub use core::ffi::c_void; diff --git a/rust/helpers/device.c b/rust/helpers/device.c new file mode 100644 index 000000000000..b2135c6686b0 --- /dev/null +++ b/rust/helpers/device.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +int rust_helper_devm_add_action(struct device *dev, + void (*action)(void *), + void *data) +{ + return devm_add_action(dev, action, data); +} diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c index dcf827a61b52..0640b7e115be 100644 --- a/rust/helpers/helpers.c +++ b/rust/helpers/helpers.c @@ -12,14 +12,19 @@ #include "build_assert.c" #include "build_bug.c" #include "cred.c" +#include "device.c" #include "err.c" #include "fs.c" +#include "io.c" #include "jump_label.c" #include "kunit.c" #include "mutex.c" #include "page.c" +#include "platform.c" +#include "pci.c" #include "pid_namespace.c" #include "rbtree.c" +#include "rcu.c" #include "refcount.c" #include "security.c" #include "signal.c" diff --git a/rust/helpers/io.c b/rust/helpers/io.c new file mode 100644 index 000000000000..4c2401ccd720 --- /dev/null +++ b/rust/helpers/io.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +void __iomem *rust_helper_ioremap(phys_addr_t offset, size_t size) +{ + return ioremap(offset, size); +} + +void rust_helper_iounmap(volatile void __iomem *addr) +{ + iounmap(addr); +} + +u8 rust_helper_readb(const volatile void __iomem *addr) +{ + return readb(addr); +} + +u16 rust_helper_readw(const volatile void __iomem *addr) +{ + return readw(addr); +} + +u32 rust_helper_readl(const volatile void __iomem *addr) +{ + return readl(addr); +} + +#ifdef CONFIG_64BIT +u64 rust_helper_readq(const volatile void __iomem *addr) +{ + return readq(addr); +} +#endif + +void rust_helper_writeb(u8 value, volatile void __iomem *addr) +{ + writeb(value, addr); +} + +void rust_helper_writew(u16 value, volatile void __iomem *addr) +{ + writew(value, addr); +} + +void rust_helper_writel(u32 value, volatile void __iomem *addr) +{ + writel(value, addr); +} + +#ifdef CONFIG_64BIT +void rust_helper_writeq(u64 value, volatile void __iomem *addr) +{ + writeq(value, addr); +} +#endif + +u8 rust_helper_readb_relaxed(const volatile void __iomem *addr) +{ + return readb_relaxed(addr); +} + +u16 rust_helper_readw_relaxed(const volatile void __iomem *addr) +{ + return readw_relaxed(addr); +} + +u32 rust_helper_readl_relaxed(const volatile void __iomem *addr) +{ + return readl_relaxed(addr); +} + +#ifdef CONFIG_64BIT +u64 rust_helper_readq_relaxed(const volatile void __iomem *addr) +{ + return readq_relaxed(addr); +} +#endif + +void rust_helper_writeb_relaxed(u8 value, volatile void __iomem *addr) +{ + writeb_relaxed(value, addr); +} + +void rust_helper_writew_relaxed(u16 value, volatile void __iomem *addr) +{ + writew_relaxed(value, addr); +} + +void rust_helper_writel_relaxed(u32 value, volatile void __iomem *addr) +{ + writel_relaxed(value, addr); +} + +#ifdef CONFIG_64BIT +void rust_helper_writeq_relaxed(u64 value, volatile void __iomem *addr) +{ + writeq_relaxed(value, addr); +} +#endif diff --git a/rust/helpers/mutex.c b/rust/helpers/mutex.c index 7e00680958ef..06575553eda5 100644 --- a/rust/helpers/mutex.c +++ b/rust/helpers/mutex.c @@ -12,3 +12,8 @@ void rust_helper___mutex_init(struct mutex *mutex, const char *name, { __mutex_init(mutex, name, key); } + +void rust_helper_mutex_assert_is_held(struct mutex *mutex) +{ + lockdep_assert_held(mutex); +} diff --git a/rust/helpers/pci.c b/rust/helpers/pci.c new file mode 100644 index 000000000000..8ba22f911459 --- /dev/null +++ b/rust/helpers/pci.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +void rust_helper_pci_set_drvdata(struct pci_dev *pdev, void *data) +{ + pci_set_drvdata(pdev, data); +} + +void *rust_helper_pci_get_drvdata(struct pci_dev *pdev) +{ + return pci_get_drvdata(pdev); +} + +resource_size_t rust_helper_pci_resource_len(struct pci_dev *pdev, int bar) +{ + return pci_resource_len(pdev, bar); +} diff --git a/rust/helpers/platform.c b/rust/helpers/platform.c new file mode 100644 index 000000000000..ab9b9f317301 --- /dev/null +++ b/rust/helpers/platform.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +void *rust_helper_platform_get_drvdata(const struct platform_device *pdev) +{ + return platform_get_drvdata(pdev); +} + +void rust_helper_platform_set_drvdata(struct platform_device *pdev, void *data) +{ + platform_set_drvdata(pdev, data); +} diff --git a/rust/helpers/rcu.c b/rust/helpers/rcu.c new file mode 100644 index 000000000000..f1cec6583513 --- /dev/null +++ b/rust/helpers/rcu.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +void rust_helper_rcu_read_lock(void) +{ + rcu_read_lock(); +} + +void rust_helper_rcu_read_unlock(void) +{ + rcu_read_unlock(); +} diff --git a/rust/helpers/security.c b/rust/helpers/security.c index 239e5b4745fe..0c4c2065df28 100644 --- a/rust/helpers/security.c +++ b/rust/helpers/security.c @@ -8,13 +8,13 @@ void rust_helper_security_cred_getsecid(const struct cred *c, u32 *secid) security_cred_getsecid(c, secid); } -int rust_helper_security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +int rust_helper_security_secid_to_secctx(u32 secid, struct lsm_context *cp) { - return security_secid_to_secctx(secid, secdata, seclen); + return security_secid_to_secctx(secid, cp); } -void rust_helper_security_release_secctx(char *secdata, u32 seclen) +void rust_helper_security_release_secctx(struct lsm_context *cp) { - security_release_secctx(secdata, seclen); + security_release_secctx(cp); } #endif diff --git a/rust/helpers/spinlock.c b/rust/helpers/spinlock.c index 5971fdf6f755..42c4bf01a23e 100644 --- a/rust/helpers/spinlock.c +++ b/rust/helpers/spinlock.c @@ -30,3 +30,8 @@ int rust_helper_spin_trylock(spinlock_t *lock) { return spin_trylock(lock); } + +void rust_helper_spin_assert_is_held(spinlock_t *lock) +{ + lockdep_assert_held(lock); +} diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs index f2f7f3a53d29..fc9c9c41cd79 100644 --- a/rust/kernel/alloc.rs +++ b/rust/kernel/alloc.rs @@ -123,7 +123,7 @@ pub mod flags { /// [`Allocator`] is designed to be implemented as a ZST; [`Allocator`] functions do not operate on /// an object instance. /// -/// In order to be able to support `#[derive(SmartPointer)]` later on, we need to avoid a design +/// In order to be able to support `#[derive(CoercePointee)]` later on, we need to avoid a design /// that requires an `Allocator` to be instantiated, hence its functions must not contain any kind /// of `self` parameter. /// diff --git a/rust/kernel/alloc/kbox.rs b/rust/kernel/alloc/kbox.rs index 9ce414361c2c..cb4ebea3b074 100644 --- a/rust/kernel/alloc/kbox.rs +++ b/rust/kernel/alloc/kbox.rs @@ -354,22 +354,30 @@ where A: Allocator, { type Borrowed<'a> = &'a T; + type BorrowedMut<'a> = &'a mut T; - fn into_foreign(self) -> *const crate::ffi::c_void { - Box::into_raw(self) as _ + fn into_foreign(self) -> *mut crate::ffi::c_void { + Box::into_raw(self).cast() } - unsafe fn from_foreign(ptr: *const crate::ffi::c_void) -> Self { + unsafe fn from_foreign(ptr: *mut crate::ffi::c_void) -> Self { // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous // call to `Self::into_foreign`. - unsafe { Box::from_raw(ptr as _) } + unsafe { Box::from_raw(ptr.cast()) } } - unsafe fn borrow<'a>(ptr: *const crate::ffi::c_void) -> &'a T { + unsafe fn borrow<'a>(ptr: *mut crate::ffi::c_void) -> &'a T { // SAFETY: The safety requirements of this method ensure that the object remains alive and // immutable for the duration of 'a. unsafe { &*ptr.cast() } } + + unsafe fn borrow_mut<'a>(ptr: *mut crate::ffi::c_void) -> &'a mut T { + let ptr = ptr.cast(); + // SAFETY: The safety requirements of this method ensure that the pointer is valid and that + // nothing else will access the value for the duration of 'a. + unsafe { &mut *ptr } + } } impl ForeignOwnable for Pin> @@ -377,19 +385,20 @@ where A: Allocator, { type Borrowed<'a> = Pin<&'a T>; + type BorrowedMut<'a> = Pin<&'a mut T>; - fn into_foreign(self) -> *const crate::ffi::c_void { + fn into_foreign(self) -> *mut crate::ffi::c_void { // SAFETY: We are still treating the box as pinned. - Box::into_raw(unsafe { Pin::into_inner_unchecked(self) }) as _ + Box::into_raw(unsafe { Pin::into_inner_unchecked(self) }).cast() } - unsafe fn from_foreign(ptr: *const crate::ffi::c_void) -> Self { + unsafe fn from_foreign(ptr: *mut crate::ffi::c_void) -> Self { // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous // call to `Self::into_foreign`. - unsafe { Pin::new_unchecked(Box::from_raw(ptr as _)) } + unsafe { Pin::new_unchecked(Box::from_raw(ptr.cast())) } } - unsafe fn borrow<'a>(ptr: *const crate::ffi::c_void) -> Pin<&'a T> { + unsafe fn borrow<'a>(ptr: *mut crate::ffi::c_void) -> Pin<&'a T> { // SAFETY: The safety requirements for this function ensure that the object is still alive, // so it is safe to dereference the raw pointer. // The safety requirements of `from_foreign` also ensure that the object remains alive for @@ -399,6 +408,18 @@ where // SAFETY: This pointer originates from a `Pin>`. unsafe { Pin::new_unchecked(r) } } + + unsafe fn borrow_mut<'a>(ptr: *mut crate::ffi::c_void) -> Pin<&'a mut T> { + let ptr = ptr.cast(); + // SAFETY: The safety requirements for this function ensure that the object is still alive, + // so it is safe to dereference the raw pointer. + // The safety requirements of `from_foreign` also ensure that the object remains alive for + // the lifetime of the returned value. + let r = unsafe { &mut *ptr }; + + // SAFETY: This pointer originates from a `Pin>`. + unsafe { Pin::new_unchecked(r) } + } } impl Deref for Box @@ -427,13 +448,23 @@ where } } +impl fmt::Display for Box +where + T: ?Sized + fmt::Display, + A: Allocator, +{ + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + ::fmt(&**self, f) + } +} + impl fmt::Debug for Box where T: ?Sized + fmt::Debug, A: Allocator, { fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { - fmt::Debug::fmt(&**self, f) + ::fmt(&**self, f) } } diff --git a/rust/kernel/alloc/layout.rs b/rust/kernel/alloc/layout.rs index 4b3cd7fdc816..93ed514f7cc7 100644 --- a/rust/kernel/alloc/layout.rs +++ b/rust/kernel/alloc/layout.rs @@ -43,6 +43,25 @@ impl ArrayLayout { /// # Errors /// /// When `len * size_of::()` overflows or when `len * size_of::() > isize::MAX`. + /// + /// # Examples + /// + /// ``` + /// # use kernel::alloc::layout::{ArrayLayout, LayoutError}; + /// let layout = ArrayLayout::::new(15)?; + /// assert_eq!(layout.len(), 15); + /// + /// // Errors because `len * size_of::()` overflows. + /// let layout = ArrayLayout::::new(isize::MAX as usize); + /// assert!(layout.is_err()); + /// + /// // Errors because `len * size_of::() > isize::MAX`, + /// // even though `len < isize::MAX`. + /// let layout = ArrayLayout::::new(isize::MAX as usize / 2); + /// assert!(layout.is_err()); + /// + /// # Ok::<(), Error>(()) + /// ``` pub const fn new(len: usize) -> Result { match len.checked_mul(core::mem::size_of::()) { Some(size) if size <= ISIZE_MAX => { diff --git a/rust/kernel/block/mq/gen_disk.rs b/rust/kernel/block/mq/gen_disk.rs index 798c4ae0bded..14806e1997fd 100644 --- a/rust/kernel/block/mq/gen_disk.rs +++ b/rust/kernel/block/mq/gen_disk.rs @@ -174,9 +174,9 @@ impl GenDiskBuilder { /// /// # Invariants /// -/// - `gendisk` must always point to an initialized and valid `struct gendisk`. -/// - `gendisk` was added to the VFS through a call to -/// `bindings::device_add_disk`. +/// - `gendisk` must always point to an initialized and valid `struct gendisk`. +/// - `gendisk` was added to the VFS through a call to +/// `bindings::device_add_disk`. pub struct GenDisk { _tagset: Arc>, gendisk: *mut bindings::gendisk, diff --git a/rust/kernel/block/mq/operations.rs b/rust/kernel/block/mq/operations.rs index c8646d0d9866..864ff379dc91 100644 --- a/rust/kernel/block/mq/operations.rs +++ b/rust/kernel/block/mq/operations.rs @@ -9,6 +9,7 @@ use crate::{ block::mq::request::RequestDataWrapper, block::mq::Request, error::{from_result, Result}, + prelude::*, types::ARef, }; use core::{marker::PhantomData, sync::atomic::AtomicU64, sync::atomic::Ordering}; @@ -35,7 +36,7 @@ pub trait Operations: Sized { /// Called by the kernel to poll the device for completed requests. Only /// used for poll queues. fn poll() -> bool { - crate::build_error(crate::error::VTABLE_DEFAULT_ERROR) + build_error!(crate::error::VTABLE_DEFAULT_ERROR) } } diff --git a/rust/kernel/block/mq/tag_set.rs b/rust/kernel/block/mq/tag_set.rs index d7f175a05d99..00ddcc71dfa2 100644 --- a/rust/kernel/block/mq/tag_set.rs +++ b/rust/kernel/block/mq/tag_set.rs @@ -52,7 +52,7 @@ impl TagSet { numa_node: bindings::NUMA_NO_NODE, queue_depth: num_tags, cmd_size, - flags: bindings::BLK_MQ_F_SHOULD_MERGE, + flags: 0, driver_data: core::ptr::null_mut::(), nr_maps: num_maps, ..tag_set diff --git a/rust/kernel/build_assert.rs b/rust/kernel/build_assert.rs index 9e37120bc69c..6331b15d7c4d 100644 --- a/rust/kernel/build_assert.rs +++ b/rust/kernel/build_assert.rs @@ -2,6 +2,9 @@ //! Build-time assert. +#[doc(hidden)] +pub use build_error::build_error; + /// Fails the build if the code path calling `build_error!` can possibly be executed. /// /// If the macro is executed in const context, `build_error!` will panic. @@ -11,7 +14,6 @@ /// # Examples /// /// ``` -/// # use kernel::build_error; /// #[inline] /// fn foo(a: usize) -> usize { /// a.checked_add(1).unwrap_or_else(|| build_error!("overflow")) @@ -23,10 +25,10 @@ #[macro_export] macro_rules! build_error { () => {{ - $crate::build_error("") + $crate::build_assert::build_error("") }}; ($msg:expr) => {{ - $crate::build_error($msg) + $crate::build_assert::build_error($msg) }}; } @@ -73,12 +75,12 @@ macro_rules! build_error { macro_rules! build_assert { ($cond:expr $(,)?) => {{ if !$cond { - $crate::build_error(concat!("assertion failed: ", stringify!($cond))); + $crate::build_assert::build_error(concat!("assertion failed: ", stringify!($cond))); } }}; ($cond:expr, $msg:expr) => {{ if !$cond { - $crate::build_error($msg); + $crate::build_assert::build_error($msg); } }}; } diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs index c926e0c2b852..db2d9658ba47 100644 --- a/rust/kernel/device.rs +++ b/rust/kernel/device.rs @@ -6,6 +6,7 @@ use crate::{ bindings, + str::CStr, types::{ARef, Opaque}, }; use core::{fmt, ptr}; @@ -173,13 +174,19 @@ impl Device { #[cfg(CONFIG_PRINTK)] unsafe { bindings::_dev_printk( - klevel as *const _ as *const core::ffi::c_char, + klevel as *const _ as *const crate::ffi::c_char, self.as_raw(), c_str!("%pA").as_char_ptr(), - &msg as *const _ as *const core::ffi::c_void, + &msg as *const _ as *const crate::ffi::c_void, ) }; } + + /// Checks if property is present or not. + pub fn property_present(&self, name: &CStr) -> bool { + // SAFETY: By the invariant of `CStr`, `name` is null-terminated. + unsafe { bindings::device_property_present(self.as_raw().cast_const(), name.as_char_ptr()) } + } } // SAFETY: Instances of `Device` are always reference-counted. diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs new file mode 100644 index 000000000000..e5859217a579 --- /dev/null +++ b/rust/kernel/device_id.rs @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Generic implementation of device IDs. +//! +//! Each bus / subsystem that matches device and driver through a bus / subsystem specific ID is +//! expected to implement [`RawDeviceId`]. + +use core::mem::MaybeUninit; + +/// Marker trait to indicate a Rust device ID type represents a corresponding C device ID type. +/// +/// This is meant to be implemented by buses/subsystems so that they can use [`IdTable`] to +/// guarantee (at compile-time) zero-termination of device id tables provided by drivers. +/// +/// # Safety +/// +/// Implementers must ensure that: +/// - `Self` is layout-compatible with [`RawDeviceId::RawType`]; i.e. it's safe to transmute to +/// `RawDeviceId`. +/// +/// This requirement is needed so `IdArray::new` can convert `Self` to `RawType` when building +/// the ID table. +/// +/// Ideally, this should be achieved using a const function that does conversion instead of +/// transmute; however, const trait functions relies on `const_trait_impl` unstable feature, +/// which is broken/gone in Rust 1.73. +/// +/// - `DRIVER_DATA_OFFSET` is the offset of context/data field of the device ID (usually named +/// `driver_data`) of the device ID, the field is suitable sized to write a `usize` value. +/// +/// Similar to the previous requirement, the data should ideally be added during `Self` to +/// `RawType` conversion, but there's currently no way to do it when using traits in const. +pub unsafe trait RawDeviceId { + /// The raw type that holds the device id. + /// + /// Id tables created from [`Self`] are going to hold this type in its zero-terminated array. + type RawType: Copy; + + /// The offset to the context/data field. + const DRIVER_DATA_OFFSET: usize; + + /// The index stored at `DRIVER_DATA_OFFSET` of the implementor of the [`RawDeviceId`] trait. + fn index(&self) -> usize; +} + +/// A zero-terminated device id array. +#[repr(C)] +pub struct RawIdArray { + ids: [T::RawType; N], + sentinel: MaybeUninit, +} + +impl RawIdArray { + #[doc(hidden)] + pub const fn size(&self) -> usize { + core::mem::size_of::() + } +} + +/// A zero-terminated device id array, followed by context data. +#[repr(C)] +pub struct IdArray { + raw_ids: RawIdArray, + id_infos: [U; N], +} + +impl IdArray { + /// Creates a new instance of the array. + /// + /// The contents are derived from the given identifiers and context information. + pub const fn new(ids: [(T, U); N]) -> Self { + let mut raw_ids = [const { MaybeUninit::::uninit() }; N]; + let mut infos = [const { MaybeUninit::uninit() }; N]; + + let mut i = 0usize; + while i < N { + // SAFETY: by the safety requirement of `RawDeviceId`, we're guaranteed that `T` is + // layout-wise compatible with `RawType`. + raw_ids[i] = unsafe { core::mem::transmute_copy(&ids[i].0) }; + // SAFETY: by the safety requirement of `RawDeviceId`, this would be effectively + // `raw_ids[i].driver_data = i;`. + unsafe { + raw_ids[i] + .as_mut_ptr() + .byte_offset(T::DRIVER_DATA_OFFSET as _) + .cast::() + .write(i); + } + + // SAFETY: this is effectively a move: `infos[i] = ids[i].1`. We make a copy here but + // later forget `ids`. + infos[i] = MaybeUninit::new(unsafe { core::ptr::read(&ids[i].1) }); + i += 1; + } + + core::mem::forget(ids); + + Self { + raw_ids: RawIdArray { + // SAFETY: this is effectively `array_assume_init`, which is unstable, so we use + // `transmute_copy` instead. We have initialized all elements of `raw_ids` so this + // `array_assume_init` is safe. + ids: unsafe { core::mem::transmute_copy(&raw_ids) }, + sentinel: MaybeUninit::zeroed(), + }, + // SAFETY: We have initialized all elements of `infos` so this `array_assume_init` is + // safe. + id_infos: unsafe { core::mem::transmute_copy(&infos) }, + } + } + + /// Reference to the contained [`RawIdArray`]. + pub const fn raw_ids(&self) -> &RawIdArray { + &self.raw_ids + } +} + +/// A device id table. +/// +/// This trait is only implemented by `IdArray`. +/// +/// The purpose of this trait is to allow `&'static dyn IdArray` to be in context when `N` in +/// `IdArray` doesn't matter. +pub trait IdTable { + /// Obtain the pointer to the ID table. + fn as_ptr(&self) -> *const T::RawType; + + /// Obtain the pointer to the bus specific device ID from an index. + fn id(&self, index: usize) -> &T::RawType; + + /// Obtain the pointer to the driver-specific information from an index. + fn info(&self, index: usize) -> &U; +} + +impl IdTable for IdArray { + fn as_ptr(&self) -> *const T::RawType { + // This cannot be `self.ids.as_ptr()`, as the return pointer must have correct provenance + // to access the sentinel. + (self as *const Self).cast() + } + + fn id(&self, index: usize) -> &T::RawType { + &self.raw_ids.ids[index] + } + + fn info(&self, index: usize) -> &U { + &self.id_infos[index] + } +} + +/// Create device table alias for modpost. +#[macro_export] +macro_rules! module_device_table { + ($table_type: literal, $module_table_name:ident, $table_name:ident) => { + #[rustfmt::skip] + #[export_name = + concat!("__mod_device_table__", $table_type, + "__", module_path!(), + "_", line!(), + "_", stringify!($table_name)) + ] + static $module_table_name: [core::mem::MaybeUninit; $table_name.raw_ids().size()] = + unsafe { core::mem::transmute_copy($table_name.raw_ids()) }; + }; +} diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs new file mode 100644 index 000000000000..942376f6f3af --- /dev/null +++ b/rust/kernel/devres.rs @@ -0,0 +1,201 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Devres abstraction +//! +//! [`Devres`] represents an abstraction for the kernel devres (device resource management) +//! implementation. + +use crate::{ + alloc::Flags, + bindings, + device::Device, + error::{Error, Result}, + ffi::c_void, + prelude::*, + revocable::Revocable, + sync::Arc, + types::ARef, +}; + +use core::ops::Deref; + +#[pin_data] +struct DevresInner { + dev: ARef, + callback: unsafe extern "C" fn(*mut c_void), + #[pin] + data: Revocable, +} + +/// This abstraction is meant to be used by subsystems to containerize [`Device`] bound resources to +/// manage their lifetime. +/// +/// [`Device`] bound resources should be freed when either the resource goes out of scope or the +/// [`Device`] is unbound respectively, depending on what happens first. +/// +/// To achieve that [`Devres`] registers a devres callback on creation, which is called once the +/// [`Device`] is unbound, revoking access to the encapsulated resource (see also [`Revocable`]). +/// +/// After the [`Devres`] has been unbound it is not possible to access the encapsulated resource +/// anymore. +/// +/// [`Devres`] users should make sure to simply free the corresponding backing resource in `T`'s +/// [`Drop`] implementation. +/// +/// # Example +/// +/// ```no_run +/// # use kernel::{bindings, c_str, device::Device, devres::Devres, io::{Io, IoRaw}}; +/// # use core::ops::Deref; +/// +/// // See also [`pci::Bar`] for a real example. +/// struct IoMem(IoRaw); +/// +/// impl IoMem { +/// /// # Safety +/// /// +/// /// [`paddr`, `paddr` + `SIZE`) must be a valid MMIO region that is mappable into the CPUs +/// /// virtual address space. +/// unsafe fn new(paddr: usize) -> Result{ +/// // SAFETY: By the safety requirements of this function [`paddr`, `paddr` + `SIZE`) is +/// // valid for `ioremap`. +/// let addr = unsafe { bindings::ioremap(paddr as _, SIZE as _) }; +/// if addr.is_null() { +/// return Err(ENOMEM); +/// } +/// +/// Ok(IoMem(IoRaw::new(addr as _, SIZE)?)) +/// } +/// } +/// +/// impl Drop for IoMem { +/// fn drop(&mut self) { +/// // SAFETY: `self.0.addr()` is guaranteed to be properly mapped by `Self::new`. +/// unsafe { bindings::iounmap(self.0.addr() as _); }; +/// } +/// } +/// +/// impl Deref for IoMem { +/// type Target = Io; +/// +/// fn deref(&self) -> &Self::Target { +/// // SAFETY: The memory range stored in `self` has been properly mapped in `Self::new`. +/// unsafe { Io::from_raw(&self.0) } +/// } +/// } +/// # fn no_run() -> Result<(), Error> { +/// # // SAFETY: Invalid usage; just for the example to get an `ARef` instance. +/// # let dev = unsafe { Device::get_device(core::ptr::null_mut()) }; +/// +/// // SAFETY: Invalid usage for example purposes. +/// let iomem = unsafe { IoMem::<{ core::mem::size_of::() }>::new(0xBAAAAAAD)? }; +/// let devres = Devres::new(&dev, iomem, GFP_KERNEL)?; +/// +/// let res = devres.try_access().ok_or(ENXIO)?; +/// res.writel(0x42, 0x0); +/// # Ok(()) +/// # } +/// ``` +pub struct Devres(Arc>); + +impl DevresInner { + fn new(dev: &Device, data: T, flags: Flags) -> Result>> { + let inner = Arc::pin_init( + pin_init!( DevresInner { + dev: dev.into(), + callback: Self::devres_callback, + data <- Revocable::new(data), + }), + flags, + )?; + + // Convert `Arc` into a raw pointer and make devres own this reference until + // `Self::devres_callback` is called. + let data = inner.clone().into_raw(); + + // SAFETY: `devm_add_action` guarantees to call `Self::devres_callback` once `dev` is + // detached. + let ret = + unsafe { bindings::devm_add_action(dev.as_raw(), Some(inner.callback), data as _) }; + + if ret != 0 { + // SAFETY: We just created another reference to `inner` in order to pass it to + // `bindings::devm_add_action`. If `bindings::devm_add_action` fails, we have to drop + // this reference accordingly. + let _ = unsafe { Arc::from_raw(data) }; + return Err(Error::from_errno(ret)); + } + + Ok(inner) + } + + fn as_ptr(&self) -> *const Self { + self as _ + } + + fn remove_action(this: &Arc) { + // SAFETY: + // - `self.inner.dev` is a valid `Device`, + // - the `action` and `data` pointers are the exact same ones as given to devm_add_action() + // previously, + // - `self` is always valid, even if the action has been released already. + let ret = unsafe { + bindings::devm_remove_action_nowarn( + this.dev.as_raw(), + Some(this.callback), + this.as_ptr() as _, + ) + }; + + if ret == 0 { + // SAFETY: We leaked an `Arc` reference to devm_add_action() in `DevresInner::new`; if + // devm_remove_action_nowarn() was successful we can (and have to) claim back ownership + // of this reference. + let _ = unsafe { Arc::from_raw(this.as_ptr()) }; + } + } + + #[allow(clippy::missing_safety_doc)] + unsafe extern "C" fn devres_callback(ptr: *mut kernel::ffi::c_void) { + let ptr = ptr as *mut DevresInner; + // Devres owned this memory; now that we received the callback, drop the `Arc` and hence the + // reference. + // SAFETY: Safe, since we leaked an `Arc` reference to devm_add_action() in + // `DevresInner::new`. + let inner = unsafe { Arc::from_raw(ptr) }; + + inner.data.revoke(); + } +} + +impl Devres { + /// Creates a new [`Devres`] instance of the given `data`. The `data` encapsulated within the + /// returned `Devres` instance' `data` will be revoked once the device is detached. + pub fn new(dev: &Device, data: T, flags: Flags) -> Result { + let inner = DevresInner::new(dev, data, flags)?; + + Ok(Devres(inner)) + } + + /// Same as [`Devres::new`], but does not return a `Devres` instance. Instead the given `data` + /// is owned by devres and will be revoked / dropped, once the device is detached. + pub fn new_foreign_owned(dev: &Device, data: T, flags: Flags) -> Result { + let _ = DevresInner::new(dev, data, flags)?; + + Ok(()) + } +} + +impl Deref for Devres { + type Target = Revocable; + + fn deref(&self) -> &Self::Target { + &self.0.data + } +} + +impl Drop for Devres { + fn drop(&mut self) { + DevresInner::remove_action(&self.0); + } +} diff --git a/rust/kernel/driver.rs b/rust/kernel/driver.rs new file mode 100644 index 000000000000..2a16d5e64e6c --- /dev/null +++ b/rust/kernel/driver.rs @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Generic support for drivers of different buses (e.g., PCI, Platform, Amba, etc.). +//! +//! Each bus / subsystem is expected to implement [`RegistrationOps`], which allows drivers to +//! register using the [`Registration`] class. + +use crate::error::{Error, Result}; +use crate::{device, init::PinInit, of, str::CStr, try_pin_init, types::Opaque, ThisModule}; +use core::pin::Pin; +use macros::{pin_data, pinned_drop}; + +/// The [`RegistrationOps`] trait serves as generic interface for subsystems (e.g., PCI, Platform, +/// Amba, etc.) to provide the corresponding subsystem specific implementation to register / +/// unregister a driver of the particular type (`RegType`). +/// +/// For instance, the PCI subsystem would set `RegType` to `bindings::pci_driver` and call +/// `bindings::__pci_register_driver` from `RegistrationOps::register` and +/// `bindings::pci_unregister_driver` from `RegistrationOps::unregister`. +/// +/// # Safety +/// +/// A call to [`RegistrationOps::unregister`] for a given instance of `RegType` is only valid if a +/// preceding call to [`RegistrationOps::register`] has been successful. +pub unsafe trait RegistrationOps { + /// The type that holds information about the registration. This is typically a struct defined + /// by the C portion of the kernel. + type RegType: Default; + + /// Registers a driver. + /// + /// # Safety + /// + /// On success, `reg` must remain pinned and valid until the matching call to + /// [`RegistrationOps::unregister`]. + unsafe fn register( + reg: &Opaque, + name: &'static CStr, + module: &'static ThisModule, + ) -> Result; + + /// Unregisters a driver previously registered with [`RegistrationOps::register`]. + /// + /// # Safety + /// + /// Must only be called after a preceding successful call to [`RegistrationOps::register`] for + /// the same `reg`. + unsafe fn unregister(reg: &Opaque); +} + +/// A [`Registration`] is a generic type that represents the registration of some driver type (e.g. +/// `bindings::pci_driver`). Therefore a [`Registration`] must be initialized with a type that +/// implements the [`RegistrationOps`] trait, such that the generic `T::register` and +/// `T::unregister` calls result in the subsystem specific registration calls. +/// +///Once the `Registration` structure is dropped, the driver is unregistered. +#[pin_data(PinnedDrop)] +pub struct Registration { + #[pin] + reg: Opaque, +} + +// SAFETY: `Registration` has no fields or methods accessible via `&Registration`, so it is safe to +// share references to it with multiple threads as nothing can be done. +unsafe impl Sync for Registration {} + +// SAFETY: Both registration and unregistration are implemented in C and safe to be performed from +// any thread, so `Registration` is `Send`. +unsafe impl Send for Registration {} + +impl Registration { + /// Creates a new instance of the registration object. + pub fn new(name: &'static CStr, module: &'static ThisModule) -> impl PinInit { + try_pin_init!(Self { + reg <- Opaque::try_ffi_init(|ptr: *mut T::RegType| { + // SAFETY: `try_ffi_init` guarantees that `ptr` is valid for write. + unsafe { ptr.write(T::RegType::default()) }; + + // SAFETY: `try_ffi_init` guarantees that `ptr` is valid for write, and it has + // just been initialised above, so it's also valid for read. + let drv = unsafe { &*(ptr as *const Opaque) }; + + // SAFETY: `drv` is guaranteed to be pinned until `T::unregister`. + unsafe { T::register(drv, name, module) } + }), + }) + } +} + +#[pinned_drop] +impl PinnedDrop for Registration { + fn drop(self: Pin<&mut Self>) { + // SAFETY: The existence of `self` guarantees that `self.reg` has previously been + // successfully registered with `T::register` + unsafe { T::unregister(&self.reg) }; + } +} + +/// Declares a kernel module that exposes a single driver. +/// +/// It is meant to be used as a helper by other subsystems so they can more easily expose their own +/// macros. +#[macro_export] +macro_rules! module_driver { + (<$gen_type:ident>, $driver_ops:ty, { type: $type:ty, $($f:tt)* }) => { + type Ops<$gen_type> = $driver_ops; + + #[$crate::prelude::pin_data] + struct DriverModule { + #[pin] + _driver: $crate::driver::Registration>, + } + + impl $crate::InPlaceModule for DriverModule { + fn init( + module: &'static $crate::ThisModule + ) -> impl $crate::init::PinInit { + $crate::try_pin_init!(Self { + _driver <- $crate::driver::Registration::new( + ::NAME, + module, + ), + }) + } + } + + $crate::prelude::module! { + type: DriverModule, + $($f)* + } + } +} + +/// The bus independent adapter to match a drivers and a devices. +/// +/// This trait should be implemented by the bus specific adapter, which represents the connection +/// of a device and a driver. +/// +/// It provides bus independent functions for device / driver interactions. +pub trait Adapter { + /// The type holding driver private data about each device id supported by the driver. + type IdInfo: 'static; + + /// The [`of::IdTable`] of the corresponding driver. + fn of_id_table() -> Option>; + + /// Returns the driver's private data from the matching entry in the [`of::IdTable`], if any. + /// + /// If this returns `None`, it means there is no match with an entry in the [`of::IdTable`]. + #[cfg(CONFIG_OF)] + fn of_id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> { + let table = Self::of_id_table()?; + + // SAFETY: + // - `table` has static lifetime, hence it's valid for read, + // - `dev` is guaranteed to be valid while it's alive, and so is `pdev.as_ref().as_raw()`. + let raw_id = unsafe { bindings::of_match_device(table.as_ptr(), dev.as_raw()) }; + + if raw_id.is_null() { + None + } else { + // SAFETY: `DeviceId` is a `#[repr(transparent)` wrapper of `struct of_device_id` and + // does not add additional invariants, so it's safe to transmute. + let id = unsafe { &*raw_id.cast::() }; + + Some(table.info(::index(id))) + } + } + + #[cfg(not(CONFIG_OF))] + #[allow(missing_docs)] + fn of_id_info(_dev: &device::Device) -> Option<&'static Self::IdInfo> { + None + } + + /// Returns the driver's private data from the matching entry of any of the ID tables, if any. + /// + /// If this returns `None`, it means that there is no match in any of the ID tables directly + /// associated with a [`device::Device`]. + fn id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> { + let id = Self::of_id_info(dev); + if id.is_some() { + return id; + } + + None + } +} diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 52c502432447..f6ecf09cb65f 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -4,9 +4,10 @@ //! //! C header: [`include/uapi/asm-generic/errno-base.h`](srctree/include/uapi/asm-generic/errno-base.h) -use crate::{alloc::AllocError, str::CStr}; - -use core::alloc::LayoutError; +use crate::{ + alloc::{layout::LayoutError, AllocError}, + str::CStr, +}; use core::fmt; use core::num::NonZeroI32; @@ -101,19 +102,16 @@ impl Error { /// It is a bug to pass an out-of-range `errno`. `EINVAL` would /// be returned in such a case. pub fn from_errno(errno: crate::ffi::c_int) -> Error { - if errno < -(bindings::MAX_ERRNO as i32) || errno >= 0 { + if let Some(error) = Self::try_from_errno(errno) { + error + } else { // TODO: Make it a `WARN_ONCE` once available. crate::pr_warn!( "attempted to create `Error` with out of range `errno`: {}", errno ); - return code::EINVAL; + code::EINVAL } - - // INVARIANT: The check above ensures the type invariant - // will hold. - // SAFETY: `errno` is checked above to be in a valid range. - unsafe { Error::from_errno_unchecked(errno) } } /// Creates an [`Error`] from a kernel error code. @@ -153,11 +151,8 @@ impl Error { /// Returns the error encoded as a pointer. pub fn to_ptr(self) -> *mut T { - #[cfg_attr(target_pointer_width = "32", allow(clippy::useless_conversion))] // SAFETY: `self.0` is a valid error due to its invariant. - unsafe { - bindings::ERR_PTR(self.0.get().into()) as *mut _ - } + unsafe { bindings::ERR_PTR(self.0.get() as _) as *mut _ } } /// Returns a string representing the error, if one exists. diff --git a/rust/kernel/firmware.rs b/rust/kernel/firmware.rs index 13a374a5cdb7..c5162fdc95ff 100644 --- a/rust/kernel/firmware.rs +++ b/rust/kernel/firmware.rs @@ -12,7 +12,7 @@ use core::ptr::NonNull; /// One of the following: `bindings::request_firmware`, `bindings::firmware_request_nowarn`, /// `bindings::firmware_request_platform`, `bindings::request_firmware_direct`. struct FwFunc( - unsafe extern "C" fn(*mut *const bindings::firmware, *const i8, *mut bindings::device) -> i32, + unsafe extern "C" fn(*mut *const bindings::firmware, *const u8, *mut bindings::device) -> i32, ); impl FwFunc { diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 347049df556b..3f9236c1c9d5 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -290,9 +290,17 @@ macro_rules! stack_pin_init { /// /// ```rust,ignore /// # #![expect(clippy::disallowed_names)] -/// # use kernel::{init, pin_init, stack_try_pin_init, init::*, sync::Mutex, new_mutex}; +/// # use kernel::{ +/// # init, +/// # pin_init, +/// # stack_try_pin_init, +/// # init::*, +/// # sync::Mutex, +/// # new_mutex, +/// # alloc::AllocError, +/// # }; /// # use macros::pin_data; -/// # use core::{alloc::AllocError, pin::Pin}; +/// # use core::pin::Pin; /// #[pin_data] /// struct Foo { /// #[pin] @@ -316,9 +324,17 @@ macro_rules! stack_pin_init { /// /// ```rust,ignore /// # #![expect(clippy::disallowed_names)] -/// # use kernel::{init, pin_init, stack_try_pin_init, init::*, sync::Mutex, new_mutex}; +/// # use kernel::{ +/// # init, +/// # pin_init, +/// # stack_try_pin_init, +/// # init::*, +/// # sync::Mutex, +/// # new_mutex, +/// # alloc::AllocError, +/// # }; /// # use macros::pin_data; -/// # use core::{alloc::AllocError, pin::Pin}; +/// # use core::pin::Pin; /// #[pin_data] /// struct Foo { /// #[pin] @@ -1076,8 +1092,9 @@ pub fn uninit() -> impl Init, E> { /// ```rust /// use kernel::{alloc::KBox, error::Error, init::init_array_from_fn}; /// let array: KBox<[usize; 1_000]> = -/// KBox::init::(init_array_from_fn(|i| i), GFP_KERNEL).unwrap(); +/// KBox::init::(init_array_from_fn(|i| i), GFP_KERNEL)?; /// assert_eq!(array.len(), 1_000); +/// # Ok::<(), Error>(()) /// ``` pub fn init_array_from_fn( mut make_init: impl FnMut(usize) -> I, @@ -1120,8 +1137,9 @@ where /// ```rust /// use kernel::{sync::{Arc, Mutex}, init::pin_init_array_from_fn, new_mutex}; /// let array: Arc<[Mutex; 1_000]> = -/// Arc::pin_init(pin_init_array_from_fn(|i| new_mutex!(i)), GFP_KERNEL).unwrap(); +/// Arc::pin_init(pin_init_array_from_fn(|i| new_mutex!(i)), GFP_KERNEL)?; /// assert_eq!(array.len(), 1_000); +/// # Ok::<(), Error>(()) /// ``` pub fn pin_init_array_from_fn( mut make_init: impl FnMut(usize) -> I, diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs new file mode 100644 index 000000000000..d4a73e52e3ee --- /dev/null +++ b/rust/kernel/io.rs @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Memory-mapped IO. +//! +//! C header: [`include/asm-generic/io.h`](srctree/include/asm-generic/io.h) + +use crate::error::{code::EINVAL, Result}; +use crate::{bindings, build_assert}; + +/// Raw representation of an MMIO region. +/// +/// By itself, the existence of an instance of this structure does not provide any guarantees that +/// the represented MMIO region does exist or is properly mapped. +/// +/// Instead, the bus specific MMIO implementation must convert this raw representation into an `Io` +/// instance providing the actual memory accessors. Only by the conversion into an `Io` structure +/// any guarantees are given. +pub struct IoRaw { + addr: usize, + maxsize: usize, +} + +impl IoRaw { + /// Returns a new `IoRaw` instance on success, an error otherwise. + pub fn new(addr: usize, maxsize: usize) -> Result { + if maxsize < SIZE { + return Err(EINVAL); + } + + Ok(Self { addr, maxsize }) + } + + /// Returns the base address of the MMIO region. + #[inline] + pub fn addr(&self) -> usize { + self.addr + } + + /// Returns the maximum size of the MMIO region. + #[inline] + pub fn maxsize(&self) -> usize { + self.maxsize + } +} + +/// IO-mapped memory, starting at the base address @addr and spanning @maxlen bytes. +/// +/// The creator (usually a subsystem / bus such as PCI) is responsible for creating the +/// mapping, performing an additional region request etc. +/// +/// # Invariant +/// +/// `addr` is the start and `maxsize` the length of valid I/O mapped memory region of size +/// `maxsize`. +/// +/// # Examples +/// +/// ```no_run +/// # use kernel::{bindings, io::{Io, IoRaw}}; +/// # use core::ops::Deref; +/// +/// // See also [`pci::Bar`] for a real example. +/// struct IoMem(IoRaw); +/// +/// impl IoMem { +/// /// # Safety +/// /// +/// /// [`paddr`, `paddr` + `SIZE`) must be a valid MMIO region that is mappable into the CPUs +/// /// virtual address space. +/// unsafe fn new(paddr: usize) -> Result{ +/// // SAFETY: By the safety requirements of this function [`paddr`, `paddr` + `SIZE`) is +/// // valid for `ioremap`. +/// let addr = unsafe { bindings::ioremap(paddr as _, SIZE as _) }; +/// if addr.is_null() { +/// return Err(ENOMEM); +/// } +/// +/// Ok(IoMem(IoRaw::new(addr as _, SIZE)?)) +/// } +/// } +/// +/// impl Drop for IoMem { +/// fn drop(&mut self) { +/// // SAFETY: `self.0.addr()` is guaranteed to be properly mapped by `Self::new`. +/// unsafe { bindings::iounmap(self.0.addr() as _); }; +/// } +/// } +/// +/// impl Deref for IoMem { +/// type Target = Io; +/// +/// fn deref(&self) -> &Self::Target { +/// // SAFETY: The memory range stored in `self` has been properly mapped in `Self::new`. +/// unsafe { Io::from_raw(&self.0) } +/// } +/// } +/// +///# fn no_run() -> Result<(), Error> { +/// // SAFETY: Invalid usage for example purposes. +/// let iomem = unsafe { IoMem::<{ core::mem::size_of::() }>::new(0xBAAAAAAD)? }; +/// iomem.writel(0x42, 0x0); +/// assert!(iomem.try_writel(0x42, 0x0).is_ok()); +/// assert!(iomem.try_writel(0x42, 0x4).is_err()); +/// # Ok(()) +/// # } +/// ``` +#[repr(transparent)] +pub struct Io(IoRaw); + +macro_rules! define_read { + ($(#[$attr:meta])* $name:ident, $try_name:ident, $type_name:ty) => { + /// Read IO data from a given offset known at compile time. + /// + /// Bound checks are performed on compile time, hence if the offset is not known at compile + /// time, the build will fail. + $(#[$attr])* + #[inline] + pub fn $name(&self, offset: usize) -> $type_name { + let addr = self.io_addr_assert::<$type_name>(offset); + + // SAFETY: By the type invariant `addr` is a valid address for MMIO operations. + unsafe { bindings::$name(addr as _) } + } + + /// Read IO data from a given offset. + /// + /// Bound checks are performed on runtime, it fails if the offset (plus the type size) is + /// out of bounds. + $(#[$attr])* + pub fn $try_name(&self, offset: usize) -> Result<$type_name> { + let addr = self.io_addr::<$type_name>(offset)?; + + // SAFETY: By the type invariant `addr` is a valid address for MMIO operations. + Ok(unsafe { bindings::$name(addr as _) }) + } + }; +} + +macro_rules! define_write { + ($(#[$attr:meta])* $name:ident, $try_name:ident, $type_name:ty) => { + /// Write IO data from a given offset known at compile time. + /// + /// Bound checks are performed on compile time, hence if the offset is not known at compile + /// time, the build will fail. + $(#[$attr])* + #[inline] + pub fn $name(&self, value: $type_name, offset: usize) { + let addr = self.io_addr_assert::<$type_name>(offset); + + // SAFETY: By the type invariant `addr` is a valid address for MMIO operations. + unsafe { bindings::$name(value, addr as _, ) } + } + + /// Write IO data from a given offset. + /// + /// Bound checks are performed on runtime, it fails if the offset (plus the type size) is + /// out of bounds. + $(#[$attr])* + pub fn $try_name(&self, value: $type_name, offset: usize) -> Result { + let addr = self.io_addr::<$type_name>(offset)?; + + // SAFETY: By the type invariant `addr` is a valid address for MMIO operations. + unsafe { bindings::$name(value, addr as _) } + Ok(()) + } + }; +} + +impl Io { + /// Converts an `IoRaw` into an `Io` instance, providing the accessors to the MMIO mapping. + /// + /// # Safety + /// + /// Callers must ensure that `addr` is the start of a valid I/O mapped memory region of size + /// `maxsize`. + pub unsafe fn from_raw(raw: &IoRaw) -> &Self { + // SAFETY: `Io` is a transparent wrapper around `IoRaw`. + unsafe { &*core::ptr::from_ref(raw).cast() } + } + + /// Returns the base address of this mapping. + #[inline] + pub fn addr(&self) -> usize { + self.0.addr() + } + + /// Returns the maximum size of this mapping. + #[inline] + pub fn maxsize(&self) -> usize { + self.0.maxsize() + } + + #[inline] + const fn offset_valid(offset: usize, size: usize) -> bool { + let type_size = core::mem::size_of::(); + if let Some(end) = offset.checked_add(type_size) { + end <= size && offset % type_size == 0 + } else { + false + } + } + + #[inline] + fn io_addr(&self, offset: usize) -> Result { + if !Self::offset_valid::(offset, self.maxsize()) { + return Err(EINVAL); + } + + // Probably no need to check, since the safety requirements of `Self::new` guarantee that + // this can't overflow. + self.addr().checked_add(offset).ok_or(EINVAL) + } + + #[inline] + fn io_addr_assert(&self, offset: usize) -> usize { + build_assert!(Self::offset_valid::(offset, SIZE)); + + self.addr() + offset + } + + define_read!(readb, try_readb, u8); + define_read!(readw, try_readw, u16); + define_read!(readl, try_readl, u32); + define_read!( + #[cfg(CONFIG_64BIT)] + readq, + try_readq, + u64 + ); + + define_read!(readb_relaxed, try_readb_relaxed, u8); + define_read!(readw_relaxed, try_readw_relaxed, u16); + define_read!(readl_relaxed, try_readl_relaxed, u32); + define_read!( + #[cfg(CONFIG_64BIT)] + readq_relaxed, + try_readq_relaxed, + u64 + ); + + define_write!(writeb, try_writeb, u8); + define_write!(writew, try_writew, u16); + define_write!(writel, try_writel, u32); + define_write!( + #[cfg(CONFIG_64BIT)] + writeq, + try_writeq, + u64 + ); + + define_write!(writeb_relaxed, try_writeb_relaxed, u8); + define_write!(writew_relaxed, try_writew_relaxed, u16); + define_write!(writel_relaxed, try_writel_relaxed, u32); + define_write!( + #[cfg(CONFIG_64BIT)] + writeq_relaxed, + try_writeq_relaxed, + u64 + ); +} diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index e1065a7551a3..496ed32b0911 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -13,11 +13,17 @@ #![no_std] #![feature(arbitrary_self_types)] -#![feature(coerce_unsized)] -#![feature(dispatch_from_dyn)] +#![cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, feature(derive_coerce_pointee))] +#![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(coerce_unsized))] +#![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(dispatch_from_dyn))] +#![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(unsize))] #![feature(inline_const)] #![feature(lint_reasons)] -#![feature(unsize)] +// Stable in Rust 1.83 +#![feature(const_maybe_uninit_as_mut_ptr)] +#![feature(const_mut_refs)] +#![feature(const_ptr_write)] +#![feature(const_refs_to_cell)] // Ensure conditional compilation based on the kernel configuration works; // otherwise we may silently break things like initcall handling. @@ -32,14 +38,19 @@ pub use ffi; pub mod alloc; #[cfg(CONFIG_BLOCK)] pub mod block; -mod build_assert; +#[doc(hidden)] +pub mod build_assert; pub mod cred; pub mod device; +pub mod device_id; +pub mod devres; +pub mod driver; pub mod error; #[cfg(CONFIG_RUST_FW_LOADER_ABSTRACTIONS)] pub mod firmware; pub mod fs; pub mod init; +pub mod io; pub mod ioctl; pub mod jump_label; #[cfg(CONFIG_KUNIT)] @@ -48,11 +59,16 @@ pub mod list; pub mod miscdevice; #[cfg(CONFIG_NET)] pub mod net; +pub mod of; pub mod page; +#[cfg(CONFIG_PCI)] +pub mod pci; pub mod pid_namespace; +pub mod platform; pub mod prelude; pub mod print; pub mod rbtree; +pub mod revocable; pub mod security; pub mod seq_file; pub mod sizes; @@ -74,9 +90,6 @@ pub use bindings; pub use macros; pub use uapi; -#[doc(hidden)] -pub use build_error::build_error; - /// Prefix to appear before log messages printed from within the `kernel` crate. const __LOG_PREFIX: &[u8] = b"rust_kernel\0"; @@ -116,6 +129,12 @@ impl InPlaceModule for T { } } +/// Metadata attached to a [`Module`] or [`InPlaceModule`]. +pub trait ModuleMetadata { + /// The name of the module as specified in the `module!` macro. + const NAME: &'static crate::str::CStr; +} + /// Equivalent to `THIS_MODULE` in the C API. /// /// C header: [`include/linux/init.h`](srctree/include/linux/init.h) diff --git a/rust/kernel/list/arc.rs b/rust/kernel/list/arc.rs index 3483d8c232c4..13c50df37b89 100644 --- a/rust/kernel/list/arc.rs +++ b/rust/kernel/list/arc.rs @@ -7,7 +7,7 @@ use crate::alloc::{AllocError, Flags}; use crate::prelude::*; use crate::sync::{Arc, ArcBorrow, UniqueArc}; -use core::marker::{PhantomPinned, Unsize}; +use core::marker::PhantomPinned; use core::ops::Deref; use core::pin::Pin; use core::sync::atomic::{AtomicBool, Ordering}; @@ -159,6 +159,7 @@ pub use impl_list_arc_safe; /// /// [`List`]: crate::list::List #[repr(transparent)] +#[cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, derive(core::marker::CoercePointee))] pub struct ListArc where T: ListArcSafe + ?Sized, @@ -443,18 +444,20 @@ where // This is to allow coercion from `ListArc` to `ListArc` if `T` can be converted to the // dynamically-sized type (DST) `U`. +#[cfg(not(CONFIG_RUSTC_HAS_COERCE_POINTEE))] impl core::ops::CoerceUnsized> for ListArc where - T: ListArcSafe + Unsize + ?Sized, + T: ListArcSafe + core::marker::Unsize + ?Sized, U: ListArcSafe + ?Sized, { } // This is to allow `ListArc` to be dispatched on when `ListArc` can be coerced into // `ListArc`. +#[cfg(not(CONFIG_RUSTC_HAS_COERCE_POINTEE))] impl core::ops::DispatchFromDyn> for ListArc where - T: ListArcSafe + Unsize + ?Sized, + T: ListArcSafe + core::marker::Unsize + ?Sized, U: ListArcSafe + ?Sized, { } diff --git a/rust/kernel/miscdevice.rs b/rust/kernel/miscdevice.rs index 7e2a79b3ae26..e14433b2ab9d 100644 --- a/rust/kernel/miscdevice.rs +++ b/rust/kernel/miscdevice.rs @@ -10,17 +10,16 @@ use crate::{ bindings, + device::Device, error::{to_result, Error, Result, VTABLE_DEFAULT_ERROR}, + ffi::{c_int, c_long, c_uint, c_ulong}, + fs::File, prelude::*, + seq_file::SeqFile, str::CStr, types::{ForeignOwnable, Opaque}, }; -use core::{ - ffi::{c_int, c_long, c_uint, c_ulong}, - marker::PhantomData, - mem::MaybeUninit, - pin::Pin, -}; +use core::{marker::PhantomData, mem::MaybeUninit, pin::Pin}; /// Options for creating a misc device. #[derive(Copy, Clone)] @@ -84,6 +83,16 @@ impl MiscDeviceRegistration { pub fn as_raw(&self) -> *mut bindings::miscdevice { self.inner.get() } + + /// Access the `this_device` field. + pub fn device(&self) -> &Device { + // SAFETY: This can only be called after a successful register(), which always + // initialises `this_device` with a valid device. Furthermore, the signature of this + // function tells the borrow-checker that the `&Device` reference must not outlive the + // `&MiscDeviceRegistration` used to obtain it, so the last use of the reference must be + // before the underlying `struct miscdevice` is destroyed. + unsafe { Device::as_ref((*self.as_raw()).this_device) } + } } #[pinned_drop] @@ -96,17 +105,17 @@ impl PinnedDrop for MiscDeviceRegistration { /// Trait implemented by the private data of an open misc device. #[vtable] -pub trait MiscDevice { +pub trait MiscDevice: Sized { /// What kind of pointer should `Self` be wrapped in. type Ptr: ForeignOwnable + Send + Sync; /// Called when the misc device is opened. /// /// The returned pointer will be stored as the private data for the file. - fn open() -> Result; + fn open(_file: &File, _misc: &MiscDeviceRegistration) -> Result; /// Called when the misc device is released. - fn release(device: Self::Ptr) { + fn release(device: Self::Ptr, _file: &File) { drop(device); } @@ -117,10 +126,11 @@ pub trait MiscDevice { /// [`kernel::ioctl`]: mod@crate::ioctl fn ioctl( _device: ::Borrowed<'_>, + _file: &File, _cmd: u32, _arg: usize, ) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Handler for ioctls. @@ -133,10 +143,20 @@ pub trait MiscDevice { #[cfg(CONFIG_COMPAT)] fn compat_ioctl( _device: ::Borrowed<'_>, + _file: &File, _cmd: u32, _arg: usize, ) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) + } + + /// Show info for this fd. + fn show_fdinfo( + _device: ::Borrowed<'_>, + _m: &SeqFile, + _file: &File, + ) { + build_error!(VTABLE_DEFAULT_ERROR) } } @@ -165,6 +185,7 @@ const fn create_vtable() -> &'static bindings::file_operations { } else { None }, + show_fdinfo: maybe_fn(T::HAS_SHOW_FDINFO, fops_show_fdinfo::), // SAFETY: All zeros is a valid value for `bindings::file_operations`. ..unsafe { MaybeUninit::zeroed().assume_init() } }; @@ -179,21 +200,38 @@ const fn create_vtable() -> &'static bindings::file_operations { /// The file must be associated with a `MiscDeviceRegistration`. unsafe extern "C" fn fops_open( inode: *mut bindings::inode, - file: *mut bindings::file, + raw_file: *mut bindings::file, ) -> c_int { // SAFETY: The pointers are valid and for a file being opened. - let ret = unsafe { bindings::generic_file_open(inode, file) }; + let ret = unsafe { bindings::generic_file_open(inode, raw_file) }; if ret != 0 { return ret; } - let ptr = match T::open() { + // SAFETY: The open call of a file can access the private data. + let misc_ptr = unsafe { (*raw_file).private_data }; + + // SAFETY: This is a miscdevice, so `misc_open()` set the private data to a pointer to the + // associated `struct miscdevice` before calling into this method. Furthermore, `misc_open()` + // ensures that the miscdevice can't be unregistered and freed during this call to `fops_open`. + let misc = unsafe { &*misc_ptr.cast::>() }; + + // SAFETY: + // * This underlying file is valid for (much longer than) the duration of `T::open`. + // * There is no active fdget_pos region on the file on this thread. + let file = unsafe { File::from_raw_file(raw_file) }; + + let ptr = match T::open(file, misc) { Ok(ptr) => ptr, Err(err) => return err.to_errno(), }; - // SAFETY: The open call of a file owns the private data. - unsafe { (*file).private_data = ptr.into_foreign().cast_mut() }; + // This overwrites the private data with the value specified by the user, changing the type of + // this file's private data. All future accesses to the private data is performed by other + // fops_* methods in this file, which all correctly cast the private data to the new type. + // + // SAFETY: The open call of a file can access the private data. + unsafe { (*raw_file).private_data = ptr.into_foreign() }; 0 } @@ -211,7 +249,10 @@ unsafe extern "C" fn fops_release( // SAFETY: The release call of a file owns the private data. let ptr = unsafe { ::from_foreign(private) }; - T::release(ptr); + // SAFETY: + // * The file is valid for the duration of this call. + // * There is no active fdget_pos region on the file on this thread. + T::release(ptr, unsafe { File::from_raw_file(file) }); 0 } @@ -229,7 +270,12 @@ unsafe extern "C" fn fops_ioctl( // SAFETY: Ioctl calls can borrow the private data of the file. let device = unsafe { ::borrow(private) }; - match T::ioctl(device, cmd, arg as usize) { + // SAFETY: + // * The file is valid for the duration of this call. + // * There is no active fdget_pos region on the file on this thread. + let file = unsafe { File::from_raw_file(file) }; + + match T::ioctl(device, file, cmd, arg) { Ok(ret) => ret as c_long, Err(err) => err.to_errno() as c_long, } @@ -249,8 +295,36 @@ unsafe extern "C" fn fops_compat_ioctl( // SAFETY: Ioctl calls can borrow the private data of the file. let device = unsafe { ::borrow(private) }; - match T::compat_ioctl(device, cmd, arg as usize) { + // SAFETY: + // * The file is valid for the duration of this call. + // * There is no active fdget_pos region on the file on this thread. + let file = unsafe { File::from_raw_file(file) }; + + match T::compat_ioctl(device, file, cmd, arg) { Ok(ret) => ret as c_long, Err(err) => err.to_errno() as c_long, } } + +/// # Safety +/// +/// - `file` must be a valid file that is associated with a `MiscDeviceRegistration`. +/// - `seq_file` must be a valid `struct seq_file` that we can write to. +unsafe extern "C" fn fops_show_fdinfo( + seq_file: *mut bindings::seq_file, + file: *mut bindings::file, +) { + // SAFETY: The release call of a file owns the private data. + let private = unsafe { (*file).private_data }; + // SAFETY: Ioctl calls can borrow the private data of the file. + let device = unsafe { ::borrow(private) }; + // SAFETY: + // * The file is valid for the duration of this call. + // * There is no active fdget_pos region on the file on this thread. + let file = unsafe { File::from_raw_file(file) }; + // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which + // this method is called. + let m = unsafe { SeqFile::from_raw(seq_file) }; + + T::show_fdinfo(device, m, file); +} diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index b89c681d97c0..bb654a28dab3 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -587,17 +587,17 @@ pub trait Driver { /// Issues a PHY software reset. fn soft_reset(_dev: &mut Device) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Sets up device-specific structures during discovery. fn probe(_dev: &mut Device) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Probes the hardware to determine what abilities it has. fn get_features(_dev: &mut Device) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Returns true if this is a suitable driver for the given phydev. @@ -609,32 +609,32 @@ pub trait Driver { /// Configures the advertisement and resets auto-negotiation /// if auto-negotiation is enabled. fn config_aneg(_dev: &mut Device) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Determines the negotiated speed and duplex. fn read_status(_dev: &mut Device) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Suspends the hardware, saving state if needed. fn suspend(_dev: &mut Device) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Resumes the hardware, restoring state if needed. fn resume(_dev: &mut Device) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Overrides the default MMD read function for reading a MMD register. fn read_mmd(_dev: &mut Device, _devnum: u8, _regnum: u16) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Overrides the default MMD write function for writing a MMD register. fn write_mmd(_dev: &mut Device, _devnum: u8, _regnum: u16, _val: u16) -> Result { - kernel::build_error(VTABLE_DEFAULT_ERROR) + build_error!(VTABLE_DEFAULT_ERROR) } /// Callback for notification of link change. @@ -837,7 +837,7 @@ impl DeviceMask { /// [::kernel::net::phy::create_phy_driver::()]; /// /// impl ::kernel::Module for Module { -/// fn init(module: &'static ThisModule) -> Result { +/// fn init(module: &'static ::kernel::ThisModule) -> Result { /// let drivers = unsafe { &mut DRIVERS }; /// let mut reg = ::kernel::net::phy::Registration::register( /// module, @@ -860,7 +860,7 @@ impl DeviceMask { /// ]; /// #[cfg(MODULE)] /// #[no_mangle] -/// static __mod_mdio__phydev_device_table: [::kernel::bindings::mdio_device_id; 2] = _DEVICE_TABLE; +/// static __mod_device_table__mdio__phydev: [::kernel::bindings::mdio_device_id; 2] = _DEVICE_TABLE; /// ``` #[macro_export] macro_rules! module_phy_driver { @@ -883,7 +883,7 @@ macro_rules! module_phy_driver { #[cfg(MODULE)] #[no_mangle] - static __mod_mdio__phydev_device_table: [$crate::bindings::mdio_device_id; + static __mod_device_table__mdio__phydev: [$crate::bindings::mdio_device_id; $crate::module_phy_driver!(@count_devices $($dev),+) + 1] = _DEVICE_TABLE; }; @@ -903,7 +903,7 @@ macro_rules! module_phy_driver { [$($crate::net::phy::create_phy_driver::<$driver>()),+]; impl $crate::Module for Module { - fn init(module: &'static ThisModule) -> Result { + fn init(module: &'static $crate::ThisModule) -> Result { // SAFETY: The anonymous constant guarantees that nobody else can access // the `DRIVERS` static. The array is used only in the C side. let drivers = unsafe { &mut DRIVERS }; diff --git a/rust/kernel/of.rs b/rust/kernel/of.rs new file mode 100644 index 000000000000..04f2d8ef29cb --- /dev/null +++ b/rust/kernel/of.rs @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Device Tree / Open Firmware abstractions. + +use crate::{bindings, device_id::RawDeviceId, prelude::*}; + +/// IdTable type for OF drivers. +pub type IdTable = &'static dyn kernel::device_id::IdTable; + +/// An open firmware device id. +#[repr(transparent)] +#[derive(Clone, Copy)] +pub struct DeviceId(bindings::of_device_id); + +// SAFETY: +// * `DeviceId` is a `#[repr(transparent)` wrapper of `struct of_device_id` and does not add +// additional invariants, so it's safe to transmute to `RawType`. +// * `DRIVER_DATA_OFFSET` is the offset to the `data` field. +unsafe impl RawDeviceId for DeviceId { + type RawType = bindings::of_device_id; + + const DRIVER_DATA_OFFSET: usize = core::mem::offset_of!(bindings::of_device_id, data); + + fn index(&self) -> usize { + self.0.data as _ + } +} + +impl DeviceId { + /// Create a new device id from an OF 'compatible' string. + pub const fn new(compatible: &'static CStr) -> Self { + let src = compatible.as_bytes_with_nul(); + // Replace with `bindings::of_device_id::default()` once stabilized for `const`. + // SAFETY: FFI type is valid to be zero-initialized. + let mut of: bindings::of_device_id = unsafe { core::mem::zeroed() }; + + // TODO: Use `clone_from_slice` once the corresponding types do match. + let mut i = 0; + while i < src.len() { + of.compatible[i] = src[i] as _; + i += 1; + } + + Self(of) + } +} + +/// Create an OF `IdTable` with an "alias" for modpost. +#[macro_export] +macro_rules! of_device_table { + ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => { + const $table_name: $crate::device_id::IdArray< + $crate::of::DeviceId, + $id_info_type, + { $table_data.len() }, + > = $crate::device_id::IdArray::new($table_data); + + $crate::module_device_table!("of", $module_table_name, $table_name); + }; +} diff --git a/rust/kernel/page.rs b/rust/kernel/page.rs index fdac6c375fe4..f6126aca33a6 100644 --- a/rust/kernel/page.rs +++ b/rust/kernel/page.rs @@ -57,9 +57,8 @@ impl Page { /// ``` /// use kernel::page::Page; /// - /// # fn dox() -> Result<(), kernel::alloc::AllocError> { /// let page = Page::alloc_page(GFP_KERNEL)?; - /// # Ok(()) } + /// # Ok::<(), kernel::alloc::AllocError>(()) /// ``` /// /// Allocate memory for a page and zero its contents. @@ -67,9 +66,8 @@ impl Page { /// ``` /// use kernel::page::Page; /// - /// # fn dox() -> Result<(), kernel::alloc::AllocError> { /// let page = Page::alloc_page(GFP_KERNEL | __GFP_ZERO)?; - /// # Ok(()) } + /// # Ok::<(), kernel::alloc::AllocError>(()) /// ``` pub fn alloc_page(flags: Flags) -> Result { // SAFETY: Depending on the value of `gfp_flags`, this call may sleep. Other than that, it diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs new file mode 100644 index 000000000000..4c98b5b9aa1e --- /dev/null +++ b/rust/kernel/pci.rs @@ -0,0 +1,434 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Abstractions for the PCI bus. +//! +//! C header: [`include/linux/pci.h`](srctree/include/linux/pci.h) + +use crate::{ + alloc::flags::*, + bindings, container_of, device, + device_id::RawDeviceId, + devres::Devres, + driver, + error::{to_result, Result}, + io::Io, + io::IoRaw, + str::CStr, + types::{ARef, ForeignOwnable, Opaque}, + ThisModule, +}; +use core::{ops::Deref, ptr::addr_of_mut}; +use kernel::prelude::*; + +/// An adapter for the registration of PCI drivers. +pub struct Adapter(T); + +// SAFETY: A call to `unregister` for a given instance of `RegType` is guaranteed to be valid if +// a preceding call to `register` has been successful. +unsafe impl driver::RegistrationOps for Adapter { + type RegType = bindings::pci_driver; + + unsafe fn register( + pdrv: &Opaque, + name: &'static CStr, + module: &'static ThisModule, + ) -> Result { + // SAFETY: It's safe to set the fields of `struct pci_driver` on initialization. + unsafe { + (*pdrv.get()).name = name.as_char_ptr(); + (*pdrv.get()).probe = Some(Self::probe_callback); + (*pdrv.get()).remove = Some(Self::remove_callback); + (*pdrv.get()).id_table = T::ID_TABLE.as_ptr(); + } + + // SAFETY: `pdrv` is guaranteed to be a valid `RegType`. + to_result(unsafe { + bindings::__pci_register_driver(pdrv.get(), module.0, name.as_char_ptr()) + }) + } + + unsafe fn unregister(pdrv: &Opaque) { + // SAFETY: `pdrv` is guaranteed to be a valid `RegType`. + unsafe { bindings::pci_unregister_driver(pdrv.get()) } + } +} + +impl Adapter { + extern "C" fn probe_callback( + pdev: *mut bindings::pci_dev, + id: *const bindings::pci_device_id, + ) -> kernel::ffi::c_int { + // SAFETY: The PCI bus only ever calls the probe callback with a valid pointer to a + // `struct pci_dev`. + let dev = unsafe { device::Device::get_device(addr_of_mut!((*pdev).dev)) }; + // SAFETY: `dev` is guaranteed to be embedded in a valid `struct pci_dev` by the call + // above. + let mut pdev = unsafe { Device::from_dev(dev) }; + + // SAFETY: `DeviceId` is a `#[repr(transparent)` wrapper of `struct pci_device_id` and + // does not add additional invariants, so it's safe to transmute. + let id = unsafe { &*id.cast::() }; + let info = T::ID_TABLE.info(id.index()); + + match T::probe(&mut pdev, info) { + Ok(data) => { + // Let the `struct pci_dev` own a reference of the driver's private data. + // SAFETY: By the type invariant `pdev.as_raw` returns a valid pointer to a + // `struct pci_dev`. + unsafe { bindings::pci_set_drvdata(pdev.as_raw(), data.into_foreign() as _) }; + } + Err(err) => return Error::to_errno(err), + } + + 0 + } + + extern "C" fn remove_callback(pdev: *mut bindings::pci_dev) { + // SAFETY: The PCI bus only ever calls the remove callback with a valid pointer to a + // `struct pci_dev`. + let ptr = unsafe { bindings::pci_get_drvdata(pdev) }; + + // SAFETY: `remove_callback` is only ever called after a successful call to + // `probe_callback`, hence it's guaranteed that `ptr` points to a valid and initialized + // `KBox` pointer created through `KBox::into_foreign`. + let _ = unsafe { KBox::::from_foreign(ptr) }; + } +} + +/// Declares a kernel module that exposes a single PCI driver. +/// +/// # Example +/// +///```ignore +/// kernel::module_pci_driver! { +/// type: MyDriver, +/// name: "Module name", +/// author: "Author name", +/// description: "Description", +/// license: "GPL v2", +/// } +///``` +#[macro_export] +macro_rules! module_pci_driver { +($($f:tt)*) => { + $crate::module_driver!(, $crate::pci::Adapter, { $($f)* }); +}; +} + +/// Abstraction for bindings::pci_device_id. +#[repr(transparent)] +#[derive(Clone, Copy)] +pub struct DeviceId(bindings::pci_device_id); + +impl DeviceId { + const PCI_ANY_ID: u32 = !0; + + /// Equivalent to C's `PCI_DEVICE` macro. + /// + /// Create a new `pci::DeviceId` from a vendor and device ID number. + pub const fn from_id(vendor: u32, device: u32) -> Self { + Self(bindings::pci_device_id { + vendor, + device, + subvendor: DeviceId::PCI_ANY_ID, + subdevice: DeviceId::PCI_ANY_ID, + class: 0, + class_mask: 0, + driver_data: 0, + override_only: 0, + }) + } + + /// Equivalent to C's `PCI_DEVICE_CLASS` macro. + /// + /// Create a new `pci::DeviceId` from a class number and mask. + pub const fn from_class(class: u32, class_mask: u32) -> Self { + Self(bindings::pci_device_id { + vendor: DeviceId::PCI_ANY_ID, + device: DeviceId::PCI_ANY_ID, + subvendor: DeviceId::PCI_ANY_ID, + subdevice: DeviceId::PCI_ANY_ID, + class, + class_mask, + driver_data: 0, + override_only: 0, + }) + } +} + +// SAFETY: +// * `DeviceId` is a `#[repr(transparent)` wrapper of `pci_device_id` and does not add +// additional invariants, so it's safe to transmute to `RawType`. +// * `DRIVER_DATA_OFFSET` is the offset to the `driver_data` field. +unsafe impl RawDeviceId for DeviceId { + type RawType = bindings::pci_device_id; + + const DRIVER_DATA_OFFSET: usize = core::mem::offset_of!(bindings::pci_device_id, driver_data); + + fn index(&self) -> usize { + self.0.driver_data as _ + } +} + +/// IdTable type for PCI +pub type IdTable = &'static dyn kernel::device_id::IdTable; + +/// Create a PCI `IdTable` with its alias for modpost. +#[macro_export] +macro_rules! pci_device_table { + ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => { + const $table_name: $crate::device_id::IdArray< + $crate::pci::DeviceId, + $id_info_type, + { $table_data.len() }, + > = $crate::device_id::IdArray::new($table_data); + + $crate::module_device_table!("pci", $module_table_name, $table_name); + }; +} + +/// The PCI driver trait. +/// +/// # Example +/// +///``` +/// # use kernel::{bindings, pci}; +/// +/// struct MyDriver; +/// +/// kernel::pci_device_table!( +/// PCI_TABLE, +/// MODULE_PCI_TABLE, +/// ::IdInfo, +/// [ +/// (pci::DeviceId::from_id(bindings::PCI_VENDOR_ID_REDHAT, bindings::PCI_ANY_ID as _), ()) +/// ] +/// ); +/// +/// impl pci::Driver for MyDriver { +/// type IdInfo = (); +/// const ID_TABLE: pci::IdTable = &PCI_TABLE; +/// +/// fn probe( +/// _pdev: &mut pci::Device, +/// _id_info: &Self::IdInfo, +/// ) -> Result>> { +/// Err(ENODEV) +/// } +/// } +///``` +/// Drivers must implement this trait in order to get a PCI driver registered. Please refer to the +/// `Adapter` documentation for an example. +pub trait Driver { + /// The type holding information about each device id supported by the driver. + /// + /// TODO: Use associated_type_defaults once stabilized: + /// + /// type IdInfo: 'static = (); + type IdInfo: 'static; + + /// The table of device ids supported by the driver. + const ID_TABLE: IdTable; + + /// PCI driver probe. + /// + /// Called when a new platform device is added or discovered. + /// Implementers should attempt to initialize the device here. + fn probe(dev: &mut Device, id_info: &Self::IdInfo) -> Result>>; +} + +/// The PCI device representation. +/// +/// A PCI device is based on an always reference counted `device:Device` instance. Cloning a PCI +/// device, hence, also increments the base device' reference count. +/// +/// # Invariants +/// +/// `Device` hold a valid reference of `ARef` whose underlying `struct device` is a +/// member of a `struct pci_dev`. +#[derive(Clone)] +pub struct Device(ARef); + +/// A PCI BAR to perform I/O-Operations on. +/// +/// # Invariants +/// +/// `Bar` always holds an `IoRaw` inststance that holds a valid pointer to the start of the I/O +/// memory mapped PCI bar and its size. +pub struct Bar { + pdev: Device, + io: IoRaw, + num: i32, +} + +impl Bar { + fn new(pdev: Device, num: u32, name: &CStr) -> Result { + let len = pdev.resource_len(num)?; + if len == 0 { + return Err(ENOMEM); + } + + // Convert to `i32`, since that's what all the C bindings use. + let num = i32::try_from(num)?; + + // SAFETY: + // `pdev` is valid by the invariants of `Device`. + // `num` is checked for validity by a previous call to `Device::resource_len`. + // `name` is always valid. + let ret = unsafe { bindings::pci_request_region(pdev.as_raw(), num, name.as_char_ptr()) }; + if ret != 0 { + return Err(EBUSY); + } + + // SAFETY: + // `pdev` is valid by the invariants of `Device`. + // `num` is checked for validity by a previous call to `Device::resource_len`. + // `name` is always valid. + let ioptr: usize = unsafe { bindings::pci_iomap(pdev.as_raw(), num, 0) } as usize; + if ioptr == 0 { + // SAFETY: + // `pdev` valid by the invariants of `Device`. + // `num` is checked for validity by a previous call to `Device::resource_len`. + unsafe { bindings::pci_release_region(pdev.as_raw(), num) }; + return Err(ENOMEM); + } + + let io = match IoRaw::new(ioptr, len as usize) { + Ok(io) => io, + Err(err) => { + // SAFETY: + // `pdev` is valid by the invariants of `Device`. + // `ioptr` is guaranteed to be the start of a valid I/O mapped memory region. + // `num` is checked for validity by a previous call to `Device::resource_len`. + unsafe { Self::do_release(&pdev, ioptr, num) }; + return Err(err); + } + }; + + Ok(Bar { pdev, io, num }) + } + + /// # Safety + /// + /// `ioptr` must be a valid pointer to the memory mapped PCI bar number `num`. + unsafe fn do_release(pdev: &Device, ioptr: usize, num: i32) { + // SAFETY: + // `pdev` is valid by the invariants of `Device`. + // `ioptr` is valid by the safety requirements. + // `num` is valid by the safety requirements. + unsafe { + bindings::pci_iounmap(pdev.as_raw(), ioptr as _); + bindings::pci_release_region(pdev.as_raw(), num); + } + } + + fn release(&self) { + // SAFETY: The safety requirements are guaranteed by the type invariant of `self.pdev`. + unsafe { Self::do_release(&self.pdev, self.io.addr(), self.num) }; + } +} + +impl Bar { + fn index_is_valid(index: u32) -> bool { + // A `struct pci_dev` owns an array of resources with at most `PCI_NUM_RESOURCES` entries. + index < bindings::PCI_NUM_RESOURCES + } +} + +impl Drop for Bar { + fn drop(&mut self) { + self.release(); + } +} + +impl Deref for Bar { + type Target = Io; + + fn deref(&self) -> &Self::Target { + // SAFETY: By the type invariant of `Self`, the MMIO range in `self.io` is properly mapped. + unsafe { Io::from_raw(&self.io) } + } +} + +impl Device { + /// Create a PCI Device instance from an existing `device::Device`. + /// + /// # Safety + /// + /// `dev` must be an `ARef` whose underlying `bindings::device` is a member of + /// a `bindings::pci_dev`. + pub unsafe fn from_dev(dev: ARef) -> Self { + Self(dev) + } + + fn as_raw(&self) -> *mut bindings::pci_dev { + // SAFETY: By the type invariant `self.0.as_raw` is a pointer to the `struct device` + // embedded in `struct pci_dev`. + unsafe { container_of!(self.0.as_raw(), bindings::pci_dev, dev) as _ } + } + + /// Returns the PCI vendor ID. + pub fn vendor_id(&self) -> u16 { + // SAFETY: `self.as_raw` is a valid pointer to a `struct pci_dev`. + unsafe { (*self.as_raw()).vendor } + } + + /// Returns the PCI device ID. + pub fn device_id(&self) -> u16 { + // SAFETY: `self.as_raw` is a valid pointer to a `struct pci_dev`. + unsafe { (*self.as_raw()).device } + } + + /// Enable memory resources for this device. + pub fn enable_device_mem(&self) -> Result { + // SAFETY: `self.as_raw` is guaranteed to be a pointer to a valid `struct pci_dev`. + let ret = unsafe { bindings::pci_enable_device_mem(self.as_raw()) }; + if ret != 0 { + Err(Error::from_errno(ret)) + } else { + Ok(()) + } + } + + /// Enable bus-mastering for this device. + pub fn set_master(&self) { + // SAFETY: `self.as_raw` is guaranteed to be a pointer to a valid `struct pci_dev`. + unsafe { bindings::pci_set_master(self.as_raw()) }; + } + + /// Returns the size of the given PCI bar resource. + pub fn resource_len(&self, bar: u32) -> Result { + if !Bar::index_is_valid(bar) { + return Err(EINVAL); + } + + // SAFETY: + // - `bar` is a valid bar number, as guaranteed by the above call to `Bar::index_is_valid`, + // - by its type invariant `self.as_raw` is always a valid pointer to a `struct pci_dev`. + Ok(unsafe { bindings::pci_resource_len(self.as_raw(), bar.try_into()?) }) + } + + /// Mapps an entire PCI-BAR after performing a region-request on it. I/O operation bound checks + /// can be performed on compile time for offsets (plus the requested type size) < SIZE. + pub fn iomap_region_sized( + &self, + bar: u32, + name: &CStr, + ) -> Result>> { + let bar = Bar::::new(self.clone(), bar, name)?; + let devres = Devres::new(self.as_ref(), bar, GFP_KERNEL)?; + + Ok(devres) + } + + /// Mapps an entire PCI-BAR after performing a region-request on it. + pub fn iomap_region(&self, bar: u32, name: &CStr) -> Result> { + self.iomap_region_sized::<0>(bar, name) + } +} + +impl AsRef for Device { + fn as_ref(&self) -> &device::Device { + &self.0 + } +} diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs new file mode 100644 index 000000000000..50e6b0421813 --- /dev/null +++ b/rust/kernel/platform.rs @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Abstractions for the platform bus. +//! +//! C header: [`include/linux/platform_device.h`](srctree/include/linux/platform_device.h) + +use crate::{ + bindings, container_of, device, driver, + error::{to_result, Result}, + of, + prelude::*, + str::CStr, + types::{ARef, ForeignOwnable, Opaque}, + ThisModule, +}; + +use core::ptr::addr_of_mut; + +/// An adapter for the registration of platform drivers. +pub struct Adapter(T); + +// SAFETY: A call to `unregister` for a given instance of `RegType` is guaranteed to be valid if +// a preceding call to `register` has been successful. +unsafe impl driver::RegistrationOps for Adapter { + type RegType = bindings::platform_driver; + + unsafe fn register( + pdrv: &Opaque, + name: &'static CStr, + module: &'static ThisModule, + ) -> Result { + let of_table = match T::OF_ID_TABLE { + Some(table) => table.as_ptr(), + None => core::ptr::null(), + }; + + // SAFETY: It's safe to set the fields of `struct platform_driver` on initialization. + unsafe { + (*pdrv.get()).driver.name = name.as_char_ptr(); + (*pdrv.get()).probe = Some(Self::probe_callback); + (*pdrv.get()).remove = Some(Self::remove_callback); + (*pdrv.get()).driver.of_match_table = of_table; + } + + // SAFETY: `pdrv` is guaranteed to be a valid `RegType`. + to_result(unsafe { bindings::__platform_driver_register(pdrv.get(), module.0) }) + } + + unsafe fn unregister(pdrv: &Opaque) { + // SAFETY: `pdrv` is guaranteed to be a valid `RegType`. + unsafe { bindings::platform_driver_unregister(pdrv.get()) }; + } +} + +impl Adapter { + extern "C" fn probe_callback(pdev: *mut bindings::platform_device) -> kernel::ffi::c_int { + // SAFETY: The platform bus only ever calls the probe callback with a valid `pdev`. + let dev = unsafe { device::Device::get_device(addr_of_mut!((*pdev).dev)) }; + // SAFETY: `dev` is guaranteed to be embedded in a valid `struct platform_device` by the + // call above. + let mut pdev = unsafe { Device::from_dev(dev) }; + + let info = ::id_info(pdev.as_ref()); + match T::probe(&mut pdev, info) { + Ok(data) => { + // Let the `struct platform_device` own a reference of the driver's private data. + // SAFETY: By the type invariant `pdev.as_raw` returns a valid pointer to a + // `struct platform_device`. + unsafe { bindings::platform_set_drvdata(pdev.as_raw(), data.into_foreign() as _) }; + } + Err(err) => return Error::to_errno(err), + } + + 0 + } + + extern "C" fn remove_callback(pdev: *mut bindings::platform_device) { + // SAFETY: `pdev` is a valid pointer to a `struct platform_device`. + let ptr = unsafe { bindings::platform_get_drvdata(pdev) }; + + // SAFETY: `remove_callback` is only ever called after a successful call to + // `probe_callback`, hence it's guaranteed that `ptr` points to a valid and initialized + // `KBox` pointer created through `KBox::into_foreign`. + let _ = unsafe { KBox::::from_foreign(ptr) }; + } +} + +impl driver::Adapter for Adapter { + type IdInfo = T::IdInfo; + + fn of_id_table() -> Option> { + T::OF_ID_TABLE + } +} + +/// Declares a kernel module that exposes a single platform driver. +/// +/// # Examples +/// +/// ```ignore +/// kernel::module_platform_driver! { +/// type: MyDriver, +/// name: "Module name", +/// author: "Author name", +/// description: "Description", +/// license: "GPL v2", +/// } +/// ``` +#[macro_export] +macro_rules! module_platform_driver { + ($($f:tt)*) => { + $crate::module_driver!(, $crate::platform::Adapter, { $($f)* }); + }; +} + +/// The platform driver trait. +/// +/// Drivers must implement this trait in order to get a platform driver registered. +/// +/// # Example +/// +///``` +/// # use kernel::{bindings, c_str, of, platform}; +/// +/// struct MyDriver; +/// +/// kernel::of_device_table!( +/// OF_TABLE, +/// MODULE_OF_TABLE, +/// ::IdInfo, +/// [ +/// (of::DeviceId::new(c_str!("test,device")), ()) +/// ] +/// ); +/// +/// impl platform::Driver for MyDriver { +/// type IdInfo = (); +/// const OF_ID_TABLE: Option> = Some(&OF_TABLE); +/// +/// fn probe( +/// _pdev: &mut platform::Device, +/// _id_info: Option<&Self::IdInfo>, +/// ) -> Result>> { +/// Err(ENODEV) +/// } +/// } +///``` +pub trait Driver { + /// The type holding driver private data about each device id supported by the driver. + /// + /// TODO: Use associated_type_defaults once stabilized: + /// + /// type IdInfo: 'static = (); + type IdInfo: 'static; + + /// The table of OF device ids supported by the driver. + const OF_ID_TABLE: Option>; + + /// Platform driver probe. + /// + /// Called when a new platform device is added or discovered. + /// Implementers should attempt to initialize the device here. + fn probe(dev: &mut Device, id_info: Option<&Self::IdInfo>) -> Result>>; +} + +/// The platform device representation. +/// +/// A platform device is based on an always reference counted `device:Device` instance. Cloning a +/// platform device, hence, also increments the base device' reference count. +/// +/// # Invariants +/// +/// `Device` holds a valid reference of `ARef` whose underlying `struct device` is a +/// member of a `struct platform_device`. +#[derive(Clone)] +pub struct Device(ARef); + +impl Device { + /// Convert a raw kernel device into a `Device` + /// + /// # Safety + /// + /// `dev` must be an `Aref` whose underlying `bindings::device` is a member of a + /// `bindings::platform_device`. + unsafe fn from_dev(dev: ARef) -> Self { + Self(dev) + } + + fn as_raw(&self) -> *mut bindings::platform_device { + // SAFETY: By the type invariant `self.0.as_raw` is a pointer to the `struct device` + // embedded in `struct platform_device`. + unsafe { container_of!(self.0.as_raw(), bindings::platform_device, dev) }.cast_mut() + } +} + +impl AsRef for Device { + fn as_ref(&self) -> &device::Device { + &self.0 + } +} diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs index 9ab4e0b6cbc9..dde2e0649790 100644 --- a/rust/kernel/prelude.rs +++ b/rust/kernel/prelude.rs @@ -19,7 +19,7 @@ pub use crate::alloc::{flags::*, Box, KBox, KVBox, KVVec, KVec, VBox, VVec, Vec} #[doc(no_inline)] pub use macros::{module, pin_data, pinned_drop, vtable, Zeroable}; -pub use super::build_assert; +pub use super::{build_assert, build_error}; // `super::std_vendor` is hidden, which makes the macro inline for some reason. #[doc(no_inline)] diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs index a28077a7cb30..b19ee490be58 100644 --- a/rust/kernel/print.rs +++ b/rust/kernel/print.rs @@ -107,7 +107,7 @@ pub unsafe fn call_printk( // SAFETY: TODO. unsafe { bindings::_printk( - format_string.as_ptr() as _, + format_string.as_ptr(), module_name.as_ptr(), &args as *const _ as *const c_void, ); @@ -128,7 +128,7 @@ pub fn call_printk_cont(args: fmt::Arguments<'_>) { #[cfg(CONFIG_PRINTK)] unsafe { bindings::_printk( - format_strings::CONT.as_ptr() as _, + format_strings::CONT.as_ptr(), &args as *const _ as *const c_void, ); } diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs index cb4415a12258..ee2731dad72d 100644 --- a/rust/kernel/rbtree.rs +++ b/rust/kernel/rbtree.rs @@ -36,17 +36,17 @@ use core::{ /// /// // Check the nodes we just inserted. /// { -/// assert_eq!(tree.get(&10).unwrap(), &100); -/// assert_eq!(tree.get(&20).unwrap(), &200); -/// assert_eq!(tree.get(&30).unwrap(), &300); +/// assert_eq!(tree.get(&10), Some(&100)); +/// assert_eq!(tree.get(&20), Some(&200)); +/// assert_eq!(tree.get(&30), Some(&300)); /// } /// /// // Iterate over the nodes we just inserted. /// { /// let mut iter = tree.iter(); -/// assert_eq!(iter.next().unwrap(), (&10, &100)); -/// assert_eq!(iter.next().unwrap(), (&20, &200)); -/// assert_eq!(iter.next().unwrap(), (&30, &300)); +/// assert_eq!(iter.next(), Some((&10, &100))); +/// assert_eq!(iter.next(), Some((&20, &200))); +/// assert_eq!(iter.next(), Some((&30, &300))); /// assert!(iter.next().is_none()); /// } /// @@ -61,9 +61,9 @@ use core::{ /// // Check that the tree reflects the replacement. /// { /// let mut iter = tree.iter(); -/// assert_eq!(iter.next().unwrap(), (&10, &1000)); -/// assert_eq!(iter.next().unwrap(), (&20, &200)); -/// assert_eq!(iter.next().unwrap(), (&30, &300)); +/// assert_eq!(iter.next(), Some((&10, &1000))); +/// assert_eq!(iter.next(), Some((&20, &200))); +/// assert_eq!(iter.next(), Some((&30, &300))); /// assert!(iter.next().is_none()); /// } /// @@ -73,9 +73,9 @@ use core::{ /// // Check that the tree reflects the update. /// { /// let mut iter = tree.iter(); -/// assert_eq!(iter.next().unwrap(), (&10, &1000)); -/// assert_eq!(iter.next().unwrap(), (&20, &200)); -/// assert_eq!(iter.next().unwrap(), (&30, &3000)); +/// assert_eq!(iter.next(), Some((&10, &1000))); +/// assert_eq!(iter.next(), Some((&20, &200))); +/// assert_eq!(iter.next(), Some((&30, &3000))); /// assert!(iter.next().is_none()); /// } /// @@ -85,8 +85,8 @@ use core::{ /// // Check that the tree reflects the removal. /// { /// let mut iter = tree.iter(); -/// assert_eq!(iter.next().unwrap(), (&20, &200)); -/// assert_eq!(iter.next().unwrap(), (&30, &3000)); +/// assert_eq!(iter.next(), Some((&20, &200))); +/// assert_eq!(iter.next(), Some((&30, &3000))); /// assert!(iter.next().is_none()); /// } /// @@ -128,20 +128,20 @@ use core::{ /// // Check the nodes we just inserted. /// { /// let mut iter = tree.iter(); -/// assert_eq!(iter.next().unwrap(), (&10, &100)); -/// assert_eq!(iter.next().unwrap(), (&20, &200)); -/// assert_eq!(iter.next().unwrap(), (&30, &300)); +/// assert_eq!(iter.next(), Some((&10, &100))); +/// assert_eq!(iter.next(), Some((&20, &200))); +/// assert_eq!(iter.next(), Some((&30, &300))); /// assert!(iter.next().is_none()); /// } /// /// // Remove a node, getting back ownership of it. -/// let existing = tree.remove(&30).unwrap(); +/// let existing = tree.remove(&30); /// /// // Check that the tree reflects the removal. /// { /// let mut iter = tree.iter(); -/// assert_eq!(iter.next().unwrap(), (&10, &100)); -/// assert_eq!(iter.next().unwrap(), (&20, &200)); +/// assert_eq!(iter.next(), Some((&10, &100))); +/// assert_eq!(iter.next(), Some((&20, &200))); /// assert!(iter.next().is_none()); /// } /// @@ -155,9 +155,9 @@ use core::{ /// // Check that the tree reflect the new insertion. /// { /// let mut iter = tree.iter(); -/// assert_eq!(iter.next().unwrap(), (&10, &100)); -/// assert_eq!(iter.next().unwrap(), (&15, &150)); -/// assert_eq!(iter.next().unwrap(), (&20, &200)); +/// assert_eq!(iter.next(), Some((&10, &100))); +/// assert_eq!(iter.next(), Some((&15, &150))); +/// assert_eq!(iter.next(), Some((&20, &200))); /// assert!(iter.next().is_none()); /// } /// diff --git a/rust/kernel/revocable.rs b/rust/kernel/revocable.rs new file mode 100644 index 000000000000..1e5a9d25c21b --- /dev/null +++ b/rust/kernel/revocable.rs @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Revocable objects. +//! +//! The [`Revocable`] type wraps other types and allows access to them to be revoked. The existence +//! of a [`RevocableGuard`] ensures that objects remain valid. + +use crate::{bindings, prelude::*, sync::rcu, types::Opaque}; +use core::{ + marker::PhantomData, + ops::Deref, + ptr::drop_in_place, + sync::atomic::{AtomicBool, Ordering}, +}; + +/// An object that can become inaccessible at runtime. +/// +/// Once access is revoked and all concurrent users complete (i.e., all existing instances of +/// [`RevocableGuard`] are dropped), the wrapped object is also dropped. +/// +/// # Examples +/// +/// ``` +/// # use kernel::revocable::Revocable; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// fn add_two(v: &Revocable) -> Option { +/// let guard = v.try_access()?; +/// Some(guard.a + guard.b) +/// } +/// +/// let v = KBox::pin_init(Revocable::new(Example { a: 10, b: 20 }), GFP_KERNEL).unwrap(); +/// assert_eq!(add_two(&v), Some(30)); +/// v.revoke(); +/// assert_eq!(add_two(&v), None); +/// ``` +/// +/// Sample example as above, but explicitly using the rcu read side lock. +/// +/// ``` +/// # use kernel::revocable::Revocable; +/// use kernel::sync::rcu; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// fn add_two(v: &Revocable) -> Option { +/// let guard = rcu::read_lock(); +/// let e = v.try_access_with_guard(&guard)?; +/// Some(e.a + e.b) +/// } +/// +/// let v = KBox::pin_init(Revocable::new(Example { a: 10, b: 20 }), GFP_KERNEL).unwrap(); +/// assert_eq!(add_two(&v), Some(30)); +/// v.revoke(); +/// assert_eq!(add_two(&v), None); +/// ``` +#[pin_data(PinnedDrop)] +pub struct Revocable { + is_available: AtomicBool, + #[pin] + data: Opaque, +} + +// SAFETY: `Revocable` is `Send` if the wrapped object is also `Send`. This is because while the +// functionality exposed by `Revocable` can be accessed from any thread/CPU, it is possible that +// this isn't supported by the wrapped object. +unsafe impl Send for Revocable {} + +// SAFETY: `Revocable` is `Sync` if the wrapped object is both `Send` and `Sync`. We require `Send` +// from the wrapped object as well because of `Revocable::revoke`, which can trigger the `Drop` +// implementation of the wrapped object from an arbitrary thread. +unsafe impl Sync for Revocable {} + +impl Revocable { + /// Creates a new revocable instance of the given data. + pub fn new(data: impl PinInit) -> impl PinInit { + pin_init!(Self { + is_available: AtomicBool::new(true), + data <- Opaque::pin_init(data), + }) + } + + /// Tries to access the revocable wrapped object. + /// + /// Returns `None` if the object has been revoked and is therefore no longer accessible. + /// + /// Returns a guard that gives access to the object otherwise; the object is guaranteed to + /// remain accessible while the guard is alive. In such cases, callers are not allowed to sleep + /// because another CPU may be waiting to complete the revocation of this object. + pub fn try_access(&self) -> Option> { + let guard = rcu::read_lock(); + if self.is_available.load(Ordering::Relaxed) { + // Since `self.is_available` is true, data is initialised and has to remain valid + // because the RCU read side lock prevents it from being dropped. + Some(RevocableGuard::new(self.data.get(), guard)) + } else { + None + } + } + + /// Tries to access the revocable wrapped object. + /// + /// Returns `None` if the object has been revoked and is therefore no longer accessible. + /// + /// Returns a shared reference to the object otherwise; the object is guaranteed to + /// remain accessible while the rcu read side guard is alive. In such cases, callers are not + /// allowed to sleep because another CPU may be waiting to complete the revocation of this + /// object. + pub fn try_access_with_guard<'a>(&'a self, _guard: &'a rcu::Guard) -> Option<&'a T> { + if self.is_available.load(Ordering::Relaxed) { + // SAFETY: Since `self.is_available` is true, data is initialised and has to remain + // valid because the RCU read side lock prevents it from being dropped. + Some(unsafe { &*self.data.get() }) + } else { + None + } + } + + /// # Safety + /// + /// Callers must ensure that there are no more concurrent users of the revocable object. + unsafe fn revoke_internal(&self) { + if self.is_available.swap(false, Ordering::Relaxed) { + if SYNC { + // SAFETY: Just an FFI call, there are no further requirements. + unsafe { bindings::synchronize_rcu() }; + } + + // SAFETY: We know `self.data` is valid because only one CPU can succeed the + // `compare_exchange` above that takes `is_available` from `true` to `false`. + unsafe { drop_in_place(self.data.get()) }; + } + } + + /// Revokes access to and drops the wrapped object. + /// + /// Access to the object is revoked immediately to new callers of [`Revocable::try_access`], + /// expecting that there are no concurrent users of the object. + /// + /// # Safety + /// + /// Callers must ensure that there are no more concurrent users of the revocable object. + pub unsafe fn revoke_nosync(&self) { + // SAFETY: By the safety requirement of this function, the caller ensures that nobody is + // accessing the data anymore and hence we don't have to wait for the grace period to + // finish. + unsafe { self.revoke_internal::() } + } + + /// Revokes access to and drops the wrapped object. + /// + /// Access to the object is revoked immediately to new callers of [`Revocable::try_access`]. + /// + /// If there are concurrent users of the object (i.e., ones that called + /// [`Revocable::try_access`] beforehand and still haven't dropped the returned guard), this + /// function waits for the concurrent access to complete before dropping the wrapped object. + pub fn revoke(&self) { + // SAFETY: By passing `true` we ask `revoke_internal` to wait for the grace period to + // finish. + unsafe { self.revoke_internal::() } + } +} + +#[pinned_drop] +impl PinnedDrop for Revocable { + fn drop(self: Pin<&mut Self>) { + // Drop only if the data hasn't been revoked yet (in which case it has already been + // dropped). + // SAFETY: We are not moving out of `p`, only dropping in place + let p = unsafe { self.get_unchecked_mut() }; + if *p.is_available.get_mut() { + // SAFETY: We know `self.data` is valid because no other CPU has changed + // `is_available` to `false` yet, and no other CPU can do it anymore because this CPU + // holds the only reference (mutable) to `self` now. + unsafe { drop_in_place(p.data.get()) }; + } + } +} + +/// A guard that allows access to a revocable object and keeps it alive. +/// +/// CPUs may not sleep while holding on to [`RevocableGuard`] because it's in atomic context +/// holding the RCU read-side lock. +/// +/// # Invariants +/// +/// The RCU read-side lock is held while the guard is alive. +pub struct RevocableGuard<'a, T> { + data_ref: *const T, + _rcu_guard: rcu::Guard, + _p: PhantomData<&'a ()>, +} + +impl RevocableGuard<'_, T> { + fn new(data_ref: *const T, rcu_guard: rcu::Guard) -> Self { + Self { + data_ref, + _rcu_guard: rcu_guard, + _p: PhantomData, + } + } +} + +impl Deref for RevocableGuard<'_, T> { + type Target = T; + + fn deref(&self) -> &Self::Target { + // SAFETY: By the type invariants, we hold the rcu read-side lock, so the object is + // guaranteed to remain valid. + unsafe { &*self.data_ref } + } +} diff --git a/rust/kernel/security.rs b/rust/kernel/security.rs index 2522868862a1..25d2b1ac3833 100644 --- a/rust/kernel/security.rs +++ b/rust/kernel/security.rs @@ -15,60 +15,56 @@ use crate::{ /// /// # Invariants /// -/// The `secdata` and `seclen` fields correspond to a valid security context as returned by a -/// successful call to `security_secid_to_secctx`, that has not yet been destroyed by calling -/// `security_release_secctx`. +/// The `ctx` field corresponds to a valid security context as returned by a successful call to +/// `security_secid_to_secctx`, that has not yet been destroyed by `security_release_secctx`. pub struct SecurityCtx { - secdata: *mut core::ffi::c_char, - seclen: usize, + ctx: bindings::lsm_context, } impl SecurityCtx { /// Get the security context given its id. pub fn from_secid(secid: u32) -> Result { - let mut secdata = core::ptr::null_mut(); - let mut seclen = 0u32; - // SAFETY: Just a C FFI call. The pointers are valid for writes. - to_result(unsafe { bindings::security_secid_to_secctx(secid, &mut secdata, &mut seclen) })?; + // SAFETY: `struct lsm_context` can be initialized to all zeros. + let mut ctx: bindings::lsm_context = unsafe { core::mem::zeroed() }; + + // SAFETY: Just a C FFI call. The pointer is valid for writes. + to_result(unsafe { bindings::security_secid_to_secctx(secid, &mut ctx) })?; // INVARIANT: If the above call did not fail, then we have a valid security context. - Ok(Self { - secdata, - seclen: seclen as usize, - }) + Ok(Self { ctx }) } /// Returns whether the security context is empty. pub fn is_empty(&self) -> bool { - self.seclen == 0 + self.ctx.len == 0 } /// Returns the length of this security context. pub fn len(&self) -> usize { - self.seclen + self.ctx.len as usize } /// Returns the bytes for this security context. pub fn as_bytes(&self) -> &[u8] { - let ptr = self.secdata; + let ptr = self.ctx.context; if ptr.is_null() { - debug_assert_eq!(self.seclen, 0); + debug_assert_eq!(self.len(), 0); // We can't pass a null pointer to `slice::from_raw_parts` even if the length is zero. return &[]; } // SAFETY: The call to `security_secid_to_secctx` guarantees that the pointer is valid for - // `seclen` bytes. Furthermore, if the length is zero, then we have ensured that the + // `self.len()` bytes. Furthermore, if the length is zero, then we have ensured that the // pointer is not null. - unsafe { core::slice::from_raw_parts(ptr.cast(), self.seclen) } + unsafe { core::slice::from_raw_parts(ptr.cast(), self.len()) } } } impl Drop for SecurityCtx { fn drop(&mut self) { - // SAFETY: By the invariant of `Self`, this frees a pointer that came from a successful + // SAFETY: By the invariant of `Self`, this frees a context that came from a successful // call to `security_secid_to_secctx` and has not yet been destroyed by // `security_release_secctx`. - unsafe { bindings::security_release_secctx(self.secdata, self.seclen as u32) }; + unsafe { bindings::security_release_secctx(&mut self.ctx) }; } } diff --git a/rust/kernel/seq_file.rs b/rust/kernel/seq_file.rs index 6ca29d576d02..04947c672979 100644 --- a/rust/kernel/seq_file.rs +++ b/rust/kernel/seq_file.rs @@ -36,7 +36,7 @@ impl SeqFile { bindings::seq_printf( self.inner.get(), c_str!("%pA").as_char_ptr(), - &args as *const _ as *const core::ffi::c_void, + &args as *const _ as *const crate::ffi::c_void, ); } } diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index d04c12a1426d..28e2201604d6 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -39,12 +39,13 @@ impl fmt::Display for BStr { /// ``` /// # use kernel::{fmt, b_str, str::{BStr, CString}}; /// let ascii = b_str!("Hello, BStr!"); - /// let s = CString::try_from_fmt(fmt!("{}", ascii)).unwrap(); + /// let s = CString::try_from_fmt(fmt!("{}", ascii))?; /// assert_eq!(s.as_bytes(), "Hello, BStr!".as_bytes()); /// /// let non_ascii = b_str!("🦀"); - /// let s = CString::try_from_fmt(fmt!("{}", non_ascii)).unwrap(); + /// let s = CString::try_from_fmt(fmt!("{}", non_ascii))?; /// assert_eq!(s.as_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes()); + /// # Ok::<(), kernel::error::Error>(()) /// ``` fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { for &b in &self.0 { @@ -70,12 +71,13 @@ impl fmt::Debug for BStr { /// # use kernel::{fmt, b_str, str::{BStr, CString}}; /// // Embedded double quotes are escaped. /// let ascii = b_str!("Hello, \"BStr\"!"); - /// let s = CString::try_from_fmt(fmt!("{:?}", ascii)).unwrap(); + /// let s = CString::try_from_fmt(fmt!("{:?}", ascii))?; /// assert_eq!(s.as_bytes(), "\"Hello, \\\"BStr\\\"!\"".as_bytes()); /// /// let non_ascii = b_str!("😺"); - /// let s = CString::try_from_fmt(fmt!("{:?}", non_ascii)).unwrap(); + /// let s = CString::try_from_fmt(fmt!("{:?}", non_ascii))?; /// assert_eq!(s.as_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes()); + /// # Ok::<(), kernel::error::Error>(()) /// ``` fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { f.write_char('"')?; @@ -189,7 +191,7 @@ impl CStr { // to a `NUL`-terminated C string. let len = unsafe { bindings::strlen(ptr) } + 1; // SAFETY: Lifetime guaranteed by the safety precondition. - let bytes = unsafe { core::slice::from_raw_parts(ptr as _, len as _) }; + let bytes = unsafe { core::slice::from_raw_parts(ptr as _, len) }; // SAFETY: As `len` is returned by `strlen`, `bytes` does not contain interior `NUL`. // As we have added 1 to `len`, the last byte is known to be `NUL`. unsafe { Self::from_bytes_with_nul_unchecked(bytes) } @@ -248,7 +250,7 @@ impl CStr { /// Returns a C pointer to the string. #[inline] pub const fn as_char_ptr(&self) -> *const crate::ffi::c_char { - self.0.as_ptr() as _ + self.0.as_ptr() } /// Convert the string to a byte slice without the trailing `NUL` byte. @@ -273,8 +275,9 @@ impl CStr { /// /// ``` /// # use kernel::str::CStr; - /// let cstr = CStr::from_bytes_with_nul(b"foo\0").unwrap(); + /// let cstr = CStr::from_bytes_with_nul(b"foo\0")?; /// assert_eq!(cstr.to_str(), Ok("foo")); + /// # Ok::<(), kernel::error::Error>(()) /// ``` #[inline] pub fn to_str(&self) -> Result<&str, core::str::Utf8Error> { @@ -384,12 +387,13 @@ impl fmt::Display for CStr { /// # use kernel::str::CStr; /// # use kernel::str::CString; /// let penguin = c_str!("🐧"); - /// let s = CString::try_from_fmt(fmt!("{}", penguin)).unwrap(); + /// let s = CString::try_from_fmt(fmt!("{}", penguin))?; /// assert_eq!(s.as_bytes_with_nul(), "\\xf0\\x9f\\x90\\xa7\0".as_bytes()); /// /// let ascii = c_str!("so \"cool\""); - /// let s = CString::try_from_fmt(fmt!("{}", ascii)).unwrap(); + /// let s = CString::try_from_fmt(fmt!("{}", ascii))?; /// assert_eq!(s.as_bytes_with_nul(), "so \"cool\"\0".as_bytes()); + /// # Ok::<(), kernel::error::Error>(()) /// ``` fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { for &c in self.as_bytes() { @@ -413,13 +417,14 @@ impl fmt::Debug for CStr { /// # use kernel::str::CStr; /// # use kernel::str::CString; /// let penguin = c_str!("🐧"); - /// let s = CString::try_from_fmt(fmt!("{:?}", penguin)).unwrap(); + /// let s = CString::try_from_fmt(fmt!("{:?}", penguin))?; /// assert_eq!(s.as_bytes_with_nul(), "\"\\xf0\\x9f\\x90\\xa7\"\0".as_bytes()); /// /// // Embedded double quotes are escaped. /// let ascii = c_str!("so \"cool\""); - /// let s = CString::try_from_fmt(fmt!("{:?}", ascii)).unwrap(); + /// let s = CString::try_from_fmt(fmt!("{:?}", ascii))?; /// assert_eq!(s.as_bytes_with_nul(), "\"so \\\"cool\\\"\"\0".as_bytes()); + /// # Ok::<(), kernel::error::Error>(()) /// ``` fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { f.write_str("\"")?; @@ -522,6 +527,7 @@ macro_rules! c_str { } #[cfg(test)] +#[expect(clippy::items_after_test_module)] mod tests { use super::*; @@ -547,7 +553,7 @@ mod tests { }) } - const ALL_ASCII_CHARS: &'static str = + const ALL_ASCII_CHARS: &str = "\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\x09\\x0a\\x0b\\x0c\\x0d\\x0e\\x0f\ \\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a\\x1b\\x1c\\x1d\\x1e\\x1f \ !\"#$%&'()*+,-./0123456789:;<=>?@\ @@ -581,6 +587,7 @@ mod tests { fn test_cstr_as_str_unchecked() { let good_bytes = b"\xf0\x9f\x90\xA7\0"; let checked_cstr = CStr::from_bytes_with_nul(good_bytes).unwrap(); + // SAFETY: The contents come from a string literal which contains valid UTF-8. let unchecked_str = unsafe { checked_cstr.as_str_unchecked() }; assert_eq!(unchecked_str, "🐧"); } @@ -799,16 +806,17 @@ impl fmt::Write for Formatter { /// ``` /// use kernel::{str::CString, fmt}; /// -/// let s = CString::try_from_fmt(fmt!("{}{}{}", "abc", 10, 20)).unwrap(); +/// let s = CString::try_from_fmt(fmt!("{}{}{}", "abc", 10, 20))?; /// assert_eq!(s.as_bytes_with_nul(), "abc1020\0".as_bytes()); /// /// let tmp = "testing"; -/// let s = CString::try_from_fmt(fmt!("{tmp}{}", 123)).unwrap(); +/// let s = CString::try_from_fmt(fmt!("{tmp}{}", 123))?; /// assert_eq!(s.as_bytes_with_nul(), "testing123\0".as_bytes()); /// /// // This fails because it has an embedded `NUL` byte. /// let s = CString::try_from_fmt(fmt!("a\0b{}", 123)); /// assert_eq!(s.is_ok(), false); +/// # Ok::<(), kernel::error::Error>(()) /// ``` pub struct CString { buf: KVec, @@ -838,7 +846,7 @@ impl CString { // SAFETY: The buffer is valid for read because `f.bytes_written()` is bounded by `size` // (which the minimum buffer size) and is non-zero (we wrote at least the `NUL` terminator) // so `f.bytes_written() - 1` doesn't underflow. - let ptr = unsafe { bindings::memchr(buf.as_ptr().cast(), 0, (f.bytes_written() - 1) as _) }; + let ptr = unsafe { bindings::memchr(buf.as_ptr().cast(), 0, f.bytes_written() - 1) }; if !ptr.is_null() { return Err(EINVAL); } diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs index 1eab7ebf25fd..3498fb344dc9 100644 --- a/rust/kernel/sync.rs +++ b/rust/kernel/sync.rs @@ -12,12 +12,13 @@ mod condvar; pub mod lock; mod locked_by; pub mod poll; +pub mod rcu; pub use arc::{Arc, ArcBorrow, UniqueArc}; pub use condvar::{new_condvar, CondVar, CondVarTimeoutResult}; pub use lock::global::{global_lock, GlobalGuard, GlobalLock, GlobalLockBackend, GlobalLockedBy}; -pub use lock::mutex::{new_mutex, Mutex}; -pub use lock::spinlock::{new_spinlock, SpinLock}; +pub use lock::mutex::{new_mutex, Mutex, MutexGuard}; +pub use lock::spinlock::{new_spinlock, SpinLock, SpinLockGuard}; pub use locked_by::LockedBy; /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`. diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index fa4509406ee9..3cefda7a4372 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -26,7 +26,7 @@ use crate::{ use core::{ alloc::Layout, fmt, - marker::{PhantomData, Unsize}, + marker::PhantomData, mem::{ManuallyDrop, MaybeUninit}, ops::{Deref, DerefMut}, pin::Pin, @@ -125,8 +125,18 @@ mod std_vendor; /// let coerced: Arc = obj; /// # Ok::<(), Error>(()) /// ``` +#[repr(transparent)] +#[cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, derive(core::marker::CoercePointee))] pub struct Arc { ptr: NonNull>, + // NB: this informs dropck that objects of type `ArcInner` may be used in ` as + // Drop>::drop`. Note that dropck already assumes that objects of type `T` may be used in + // ` as Drop>::drop` and the distinction between `T` and `ArcInner` is not presently + // meaningful with respect to dropck - but this may change in the future so this is left here + // out of an abundance of caution. + // + // See https://doc.rust-lang.org/nomicon/phantom-data.html#generic-parameters-and-drop-checking + // for more detail on the semantics of dropck in the presence of `PhantomData`. _p: PhantomData>, } @@ -172,10 +182,12 @@ impl ArcInner { // This is to allow coercion from `Arc` to `Arc` if `T` can be converted to the // dynamically-sized type (DST) `U`. -impl, U: ?Sized> core::ops::CoerceUnsized> for Arc {} +#[cfg(not(CONFIG_RUSTC_HAS_COERCE_POINTEE))] +impl, U: ?Sized> core::ops::CoerceUnsized> for Arc {} // This is to allow `Arc` to be dispatched on when `Arc` can be coerced into `Arc`. -impl, U: ?Sized> core::ops::DispatchFromDyn> for Arc {} +#[cfg(not(CONFIG_RUSTC_HAS_COERCE_POINTEE))] +impl, U: ?Sized> core::ops::DispatchFromDyn> for Arc {} // SAFETY: It is safe to send `Arc` to another thread when the underlying `T` is `Sync` because // it effectively means sharing `&T` (which is safe because `T` is `Sync`); additionally, it needs @@ -201,10 +213,11 @@ impl Arc { }; let inner = KBox::new(value, flags)?; + let inner = KBox::leak(inner).into(); // SAFETY: We just created `inner` with a reference count of 1, which is owned by the new // `Arc` object. - Ok(unsafe { Self::from_inner(KBox::leak(inner).into()) }) + Ok(unsafe { Self::from_inner(inner) }) } } @@ -331,26 +344,37 @@ impl Arc { impl ForeignOwnable for Arc { type Borrowed<'a> = ArcBorrow<'a, T>; + type BorrowedMut<'a> = Self::Borrowed<'a>; - fn into_foreign(self) -> *const crate::ffi::c_void { - ManuallyDrop::new(self).ptr.as_ptr() as _ + fn into_foreign(self) -> *mut crate::ffi::c_void { + ManuallyDrop::new(self).ptr.as_ptr().cast() } - unsafe fn borrow<'a>(ptr: *const crate::ffi::c_void) -> ArcBorrow<'a, T> { - // By the safety requirement of this function, we know that `ptr` came from - // a previous call to `Arc::into_foreign`. - let inner = NonNull::new(ptr as *mut ArcInner).unwrap(); + unsafe fn from_foreign(ptr: *mut crate::ffi::c_void) -> Self { + // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous + // call to `Self::into_foreign`. + let inner = unsafe { NonNull::new_unchecked(ptr.cast::>()) }; + + // SAFETY: By the safety requirement of this function, we know that `ptr` came from + // a previous call to `Arc::into_foreign`, which guarantees that `ptr` is valid and + // holds a reference count increment that is transferrable to us. + unsafe { Self::from_inner(inner) } + } + + unsafe fn borrow<'a>(ptr: *mut crate::ffi::c_void) -> ArcBorrow<'a, T> { + // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous + // call to `Self::into_foreign`. + let inner = unsafe { NonNull::new_unchecked(ptr.cast::>()) }; // SAFETY: The safety requirements of `from_foreign` ensure that the object remains alive // for the lifetime of the returned value. unsafe { ArcBorrow::new(inner) } } - unsafe fn from_foreign(ptr: *const crate::ffi::c_void) -> Self { - // SAFETY: By the safety requirement of this function, we know that `ptr` came from - // a previous call to `Arc::into_foreign`, which guarantees that `ptr` is valid and - // holds a reference count increment that is transferrable to us. - unsafe { Self::from_inner(NonNull::new(ptr as _).unwrap()) } + unsafe fn borrow_mut<'a>(ptr: *mut crate::ffi::c_void) -> ArcBorrow<'a, T> { + // SAFETY: The safety requirements for `borrow_mut` are a superset of the safety + // requirements for `borrow`. + unsafe { Self::borrow(ptr) } } } @@ -372,10 +396,14 @@ impl AsRef for Arc { impl Clone for Arc { fn clone(&self) -> Self { + // SAFETY: By the type invariant, there is necessarily a reference to the object, so it is + // safe to dereference it. + let refcount = unsafe { self.ptr.as_ref() }.refcount.get(); + // INVARIANT: C `refcount_inc` saturates the refcount, so it cannot overflow to zero. // SAFETY: By the type invariant, there is necessarily a reference to the object, so it is // safe to increment the refcount. - unsafe { bindings::refcount_inc(self.ptr.as_ref().refcount.get()) }; + unsafe { bindings::refcount_inc(refcount) }; // SAFETY: We just incremented the refcount. This increment is now owned by the new `Arc`. unsafe { Self::from_inner(self.ptr) } @@ -471,6 +499,8 @@ impl From>> for Arc { /// obj.as_arc_borrow().use_reference(); /// # Ok::<(), Error>(()) /// ``` +#[repr(transparent)] +#[cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, derive(core::marker::CoercePointee))] pub struct ArcBorrow<'a, T: ?Sized + 'a> { inner: NonNull>, _p: PhantomData<&'a ()>, @@ -478,7 +508,8 @@ pub struct ArcBorrow<'a, T: ?Sized + 'a> { // This is to allow `ArcBorrow` to be dispatched on when `ArcBorrow` can be coerced into // `ArcBorrow`. -impl, U: ?Sized> core::ops::DispatchFromDyn> +#[cfg(not(CONFIG_RUSTC_HAS_COERCE_POINTEE))] +impl, U: ?Sized> core::ops::DispatchFromDyn> for ArcBorrow<'_, T> { } diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs index 41dcddac69e2..eb80048e0110 100644 --- a/rust/kernel/sync/lock.rs +++ b/rust/kernel/sync/lock.rs @@ -90,12 +90,20 @@ pub unsafe trait Backend { // SAFETY: The safety requirements ensure that the lock is initialised. *guard_state = unsafe { Self::lock(ptr) }; } + + /// Asserts that the lock is held using lockdep. + /// + /// # Safety + /// + /// Callers must ensure that [`Backend::init`] has been previously called. + unsafe fn assert_is_held(ptr: *mut Self::State); } /// A mutual exclusion primitive. /// /// Exposes one of the kernel locking primitives. Which one is exposed depends on the lock /// [`Backend`] specified as the generic parameter `B`. +#[repr(C)] #[pin_data] pub struct Lock { /// The kernel lock object. @@ -134,6 +142,28 @@ impl Lock { } } +impl Lock<(), B> { + /// Constructs a [`Lock`] from a raw pointer. + /// + /// This can be useful for interacting with a lock which was initialised outside of Rust. + /// + /// # Safety + /// + /// The caller promises that `ptr` points to a valid initialised instance of [`State`] during + /// the whole lifetime of `'a`. + /// + /// [`State`]: Backend::State + pub unsafe fn from_raw<'a>(ptr: *mut B::State) -> &'a Self { + // SAFETY: + // - By the safety contract `ptr` must point to a valid initialised instance of `B::State` + // - Since the lock data type is `()` which is a ZST, `state` is the only non-ZST member of + // the struct + // - Combined with `#[repr(C)]`, this guarantees `Self` has an equivalent data layout to + // `B::State`. + unsafe { &*ptr.cast() } + } +} + impl Lock { /// Acquires the lock and gives the caller access to the data protected by it. pub fn lock(&self) -> Guard<'_, T, B> { @@ -211,7 +241,10 @@ impl<'a, T: ?Sized, B: Backend> Guard<'a, T, B> { /// # Safety /// /// The caller must ensure that it owns the lock. - pub(crate) unsafe fn new(lock: &'a Lock, state: B::GuardState) -> Self { + pub unsafe fn new(lock: &'a Lock, state: B::GuardState) -> Self { + // SAFETY: The caller can only hold the lock if `Backend::init` has already been called. + unsafe { B::assert_is_held(lock.state.get()) }; + Self { lock, state, diff --git a/rust/kernel/sync/lock/mutex.rs b/rust/kernel/sync/lock/mutex.rs index 0e946ebefce1..70cadbc2e8e2 100644 --- a/rust/kernel/sync/lock/mutex.rs +++ b/rust/kernel/sync/lock/mutex.rs @@ -86,6 +86,14 @@ pub use new_mutex; /// [`struct mutex`]: srctree/include/linux/mutex.h pub type Mutex = super::Lock; +/// A [`Guard`] acquired from locking a [`Mutex`]. +/// +/// This is simply a type alias for a [`Guard`] returned from locking a [`Mutex`]. It will unlock +/// the [`Mutex`] upon being dropped. +/// +/// [`Guard`]: super::Guard +pub type MutexGuard<'a, T> = super::Guard<'a, T, MutexBackend>; + /// A kernel `struct mutex` lock backend. pub struct MutexBackend; @@ -126,4 +134,9 @@ unsafe impl super::Backend for MutexBackend { None } } + + unsafe fn assert_is_held(ptr: *mut Self::State) { + // SAFETY: The `ptr` pointer is guaranteed to be valid and initialized before use. + unsafe { bindings::mutex_assert_is_held(ptr) } + } } diff --git a/rust/kernel/sync/lock/spinlock.rs b/rust/kernel/sync/lock/spinlock.rs index 9f4d128bed98..ab2f8d075311 100644 --- a/rust/kernel/sync/lock/spinlock.rs +++ b/rust/kernel/sync/lock/spinlock.rs @@ -87,6 +87,14 @@ pub type SpinLock = super::Lock; /// A kernel `spinlock_t` lock backend. pub struct SpinLockBackend; +/// A [`Guard`] acquired from locking a [`SpinLock`]. +/// +/// This is simply a type alias for a [`Guard`] returned from locking a [`SpinLock`]. It will unlock +/// the [`SpinLock`] upon being dropped. +/// +/// [`Guard`]: super::Guard +pub type SpinLockGuard<'a, T> = super::Guard<'a, T, SpinLockBackend>; + // SAFETY: The underlying kernel `spinlock_t` object ensures mutual exclusion. `relock` uses the // default implementation that always calls the same locking method. unsafe impl super::Backend for SpinLockBackend { @@ -125,4 +133,9 @@ unsafe impl super::Backend for SpinLockBackend { None } } + + unsafe fn assert_is_held(ptr: *mut Self::State) { + // SAFETY: The `ptr` pointer is guaranteed to be valid and initialized before use. + unsafe { bindings::spin_assert_is_held(ptr) } + } } diff --git a/rust/kernel/sync/rcu.rs b/rust/kernel/sync/rcu.rs new file mode 100644 index 000000000000..b51d9150ffe2 --- /dev/null +++ b/rust/kernel/sync/rcu.rs @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! RCU support. +//! +//! C header: [`include/linux/rcupdate.h`](srctree/include/linux/rcupdate.h) + +use crate::{bindings, types::NotThreadSafe}; + +/// Evidence that the RCU read side lock is held on the current thread/CPU. +/// +/// The type is explicitly not `Send` because this property is per-thread/CPU. +/// +/// # Invariants +/// +/// The RCU read side lock is actually held while instances of this guard exist. +pub struct Guard(NotThreadSafe); + +impl Guard { + /// Acquires the RCU read side lock and returns a guard. + pub fn new() -> Self { + // SAFETY: An FFI call with no additional requirements. + unsafe { bindings::rcu_read_lock() }; + // INVARIANT: The RCU read side lock was just acquired above. + Self(NotThreadSafe) + } + + /// Explicitly releases the RCU read side lock. + pub fn unlock(self) {} +} + +impl Default for Guard { + fn default() -> Self { + Self::new() + } +} + +impl Drop for Guard { + fn drop(&mut self) { + // SAFETY: By the type invariants, the RCU read side is locked, so it is ok to unlock it. + unsafe { bindings::rcu_read_unlock() }; + } +} + +/// Acquires the RCU read side lock. +pub fn read_lock() -> Guard { + Guard::new() +} diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs index ec6457bb3084..2bbaab83b9d6 100644 --- a/rust/kernel/types.rs +++ b/rust/kernel/types.rs @@ -19,35 +19,34 @@ use core::{ /// This trait is meant to be used in cases when Rust objects are stored in C objects and /// eventually "freed" back to Rust. pub trait ForeignOwnable: Sized { - /// Type of values borrowed between calls to [`ForeignOwnable::into_foreign`] and - /// [`ForeignOwnable::from_foreign`]. + /// Type used to immutably borrow a value that is currently foreign-owned. type Borrowed<'a>; + /// Type used to mutably borrow a value that is currently foreign-owned. + type BorrowedMut<'a>; + /// Converts a Rust-owned object to a foreign-owned one. /// /// The foreign representation is a pointer to void. There are no guarantees for this pointer. /// For example, it might be invalid, dangling or pointing to uninitialized memory. Using it in - /// any way except for [`ForeignOwnable::from_foreign`], [`ForeignOwnable::borrow`], - /// [`ForeignOwnable::try_from_foreign`] can result in undefined behavior. - fn into_foreign(self) -> *const crate::ffi::c_void; - - /// Borrows a foreign-owned object. + /// any way except for [`from_foreign`], [`try_from_foreign`], [`borrow`], or [`borrow_mut`] can + /// result in undefined behavior. /// - /// # Safety - /// - /// `ptr` must have been returned by a previous call to [`ForeignOwnable::into_foreign`] for - /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet. - unsafe fn borrow<'a>(ptr: *const crate::ffi::c_void) -> Self::Borrowed<'a>; + /// [`from_foreign`]: Self::from_foreign + /// [`try_from_foreign`]: Self::try_from_foreign + /// [`borrow`]: Self::borrow + /// [`borrow_mut`]: Self::borrow_mut + fn into_foreign(self) -> *mut crate::ffi::c_void; /// Converts a foreign-owned object back to a Rust-owned one. /// /// # Safety /// - /// `ptr` must have been returned by a previous call to [`ForeignOwnable::into_foreign`] for - /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet. - /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow`] for - /// this object must have been dropped. - unsafe fn from_foreign(ptr: *const crate::ffi::c_void) -> Self; + /// The provided pointer must have been returned by a previous call to [`into_foreign`], and it + /// must not be passed to `from_foreign` more than once. + /// + /// [`into_foreign`]: Self::into_foreign + unsafe fn from_foreign(ptr: *mut crate::ffi::c_void) -> Self; /// Tries to convert a foreign-owned object back to a Rust-owned one. /// @@ -56,9 +55,10 @@ pub trait ForeignOwnable: Sized { /// /// # Safety /// - /// `ptr` must either be null or satisfy the safety requirements for - /// [`ForeignOwnable::from_foreign`]. - unsafe fn try_from_foreign(ptr: *const crate::ffi::c_void) -> Option { + /// `ptr` must either be null or satisfy the safety requirements for [`from_foreign`]. + /// + /// [`from_foreign`]: Self::from_foreign + unsafe fn try_from_foreign(ptr: *mut crate::ffi::c_void) -> Option { if ptr.is_null() { None } else { @@ -67,18 +67,63 @@ pub trait ForeignOwnable: Sized { unsafe { Some(Self::from_foreign(ptr)) } } } + + /// Borrows a foreign-owned object immutably. + /// + /// This method provides a way to access a foreign-owned value from Rust immutably. It provides + /// you with exactly the same abilities as an `&Self` when the value is Rust-owned. + /// + /// # Safety + /// + /// The provided pointer must have been returned by a previous call to [`into_foreign`], and if + /// the pointer is ever passed to [`from_foreign`], then that call must happen after the end of + /// the lifetime 'a. + /// + /// [`into_foreign`]: Self::into_foreign + /// [`from_foreign`]: Self::from_foreign + unsafe fn borrow<'a>(ptr: *mut crate::ffi::c_void) -> Self::Borrowed<'a>; + + /// Borrows a foreign-owned object mutably. + /// + /// This method provides a way to access a foreign-owned value from Rust mutably. It provides + /// you with exactly the same abilities as an `&mut Self` when the value is Rust-owned, except + /// that the address of the object must not be changed. + /// + /// Note that for types like [`Arc`], an `&mut Arc` only gives you immutable access to the + /// inner value, so this method also only provides immutable access in that case. + /// + /// In the case of `Box`, this method gives you the ability to modify the inner `T`, but it + /// does not let you change the box itself. That is, you cannot change which allocation the box + /// points at. + /// + /// # Safety + /// + /// The provided pointer must have been returned by a previous call to [`into_foreign`], and if + /// the pointer is ever passed to [`from_foreign`], then that call must happen after the end of + /// the lifetime 'a. + /// + /// The lifetime 'a must not overlap with the lifetime of any other call to [`borrow`] or + /// `borrow_mut` on the same object. + /// + /// [`into_foreign`]: Self::into_foreign + /// [`from_foreign`]: Self::from_foreign + /// [`borrow`]: Self::borrow + /// [`Arc`]: crate::sync::Arc + unsafe fn borrow_mut<'a>(ptr: *mut crate::ffi::c_void) -> Self::BorrowedMut<'a>; } impl ForeignOwnable for () { type Borrowed<'a> = (); + type BorrowedMut<'a> = (); - fn into_foreign(self) -> *const crate::ffi::c_void { + fn into_foreign(self) -> *mut crate::ffi::c_void { core::ptr::NonNull::dangling().as_ptr() } - unsafe fn borrow<'a>(_: *const crate::ffi::c_void) -> Self::Borrowed<'a> {} + unsafe fn from_foreign(_: *mut crate::ffi::c_void) -> Self {} - unsafe fn from_foreign(_: *const crate::ffi::c_void) -> Self {} + unsafe fn borrow<'a>(_: *mut crate::ffi::c_void) -> Self::Borrowed<'a> {} + unsafe fn borrow_mut<'a>(_: *mut crate::ffi::c_void) -> Self::BorrowedMut<'a> {} } /// Runs a cleanup function/closure when dropped. @@ -281,6 +326,17 @@ impl Opaque { } } + /// Create an opaque pin-initializer from the given pin-initializer. + pub fn pin_init(slot: impl PinInit) -> impl PinInit { + Self::ffi_init(|ptr: *mut T| { + // SAFETY: + // - `ptr` is a valid pointer to uninitialized memory, + // - `slot` is not accessed on error; the call is infallible, + // - `slot` is pinned in memory. + let _ = unsafe { init::PinInit::::__pinned_init(slot, ptr) }; + }) + } + /// Creates a pin-initializer from the given initializer closure. /// /// The returned initializer calls the given closure with the pointer to the inner `T` of this @@ -434,7 +490,7 @@ impl ARef { /// } /// /// let mut data = Empty {}; - /// let ptr = NonNull::::new(&mut data as *mut _).unwrap(); + /// let ptr = NonNull::::new(&mut data).unwrap(); /// # // SAFETY: TODO. /// let data_ref: ARef = unsafe { ARef::from_raw(ptr) }; /// let raw_ptr: NonNull = ARef::into_raw(data_ref); diff --git a/rust/kernel/uaccess.rs b/rust/kernel/uaccess.rs index 05b0b8d13b10..719b0a48ff55 100644 --- a/rust/kernel/uaccess.rs +++ b/rust/kernel/uaccess.rs @@ -5,10 +5,10 @@ //! C header: [`include/linux/uaccess.h`](srctree/include/linux/uaccess.h) use crate::{ - alloc::Flags, + alloc::{Allocator, Flags}, bindings, error::Result, - ffi::{c_ulong, c_void}, + ffi::c_void, prelude::*, transmute::{AsBytes, FromBytes}, }; @@ -127,7 +127,7 @@ impl UserSlice { /// Reads the entirety of the user slice, appending it to the end of the provided buffer. /// /// Fails with [`EFAULT`] if the read happens on a bad address. - pub fn read_all(self, buf: &mut KVec, flags: Flags) -> Result { + pub fn read_all(self, buf: &mut Vec, flags: Flags) -> Result { self.reader().read_all(buf, flags) } @@ -224,13 +224,9 @@ impl UserSliceReader { if len > self.length { return Err(EFAULT); } - let Ok(len_ulong) = c_ulong::try_from(len) else { - return Err(EFAULT); - }; - // SAFETY: `out_ptr` points into a mutable slice of length `len_ulong`, so we may write + // SAFETY: `out_ptr` points into a mutable slice of length `len`, so we may write // that many bytes to it. - let res = - unsafe { bindings::copy_from_user(out_ptr, self.ptr as *const c_void, len_ulong) }; + let res = unsafe { bindings::copy_from_user(out_ptr, self.ptr as *const c_void, len) }; if res != 0 { return Err(EFAULT); } @@ -259,9 +255,6 @@ impl UserSliceReader { if len > self.length { return Err(EFAULT); } - let Ok(len_ulong) = c_ulong::try_from(len) else { - return Err(EFAULT); - }; let mut out: MaybeUninit = MaybeUninit::uninit(); // SAFETY: The local variable `out` is valid for writing `size_of::()` bytes. // @@ -272,7 +265,7 @@ impl UserSliceReader { bindings::_copy_from_user( out.as_mut_ptr().cast::(), self.ptr as *const c_void, - len_ulong, + len, ) }; if res != 0 { @@ -288,7 +281,7 @@ impl UserSliceReader { /// Reads the entirety of the user slice, appending it to the end of the provided buffer. /// /// Fails with [`EFAULT`] if the read happens on a bad address. - pub fn read_all(mut self, buf: &mut KVec, flags: Flags) -> Result { + pub fn read_all(mut self, buf: &mut Vec, flags: Flags) -> Result { let len = self.length; buf.reserve(len, flags)?; @@ -335,12 +328,9 @@ impl UserSliceWriter { if len > self.length { return Err(EFAULT); } - let Ok(len_ulong) = c_ulong::try_from(len) else { - return Err(EFAULT); - }; - // SAFETY: `data_ptr` points into an immutable slice of length `len_ulong`, so we may read + // SAFETY: `data_ptr` points into an immutable slice of length `len`, so we may read // that many bytes from it. - let res = unsafe { bindings::copy_to_user(self.ptr as *mut c_void, data_ptr, len_ulong) }; + let res = unsafe { bindings::copy_to_user(self.ptr as *mut c_void, data_ptr, len) }; if res != 0 { return Err(EFAULT); } @@ -359,9 +349,6 @@ impl UserSliceWriter { if len > self.length { return Err(EFAULT); } - let Ok(len_ulong) = c_ulong::try_from(len) else { - return Err(EFAULT); - }; // SAFETY: The reference points to a value of type `T`, so it is valid for reading // `size_of::()` bytes. // @@ -372,7 +359,7 @@ impl UserSliceWriter { bindings::_copy_to_user( self.ptr as *mut c_void, (value as *const T).cast::(), - len_ulong, + len, ) }; if res != 0 { diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs index 4d1d2062f6eb..0cd100d2aefb 100644 --- a/rust/kernel/workqueue.rs +++ b/rust/kernel/workqueue.rs @@ -69,6 +69,7 @@ //! fn print_later(val: Arc) { //! let _ = workqueue::system().enqueue(val); //! } +//! # print_later(MyStruct::new(42).unwrap()); //! ``` //! //! The following example shows how multiple `work_struct` fields can be used: @@ -126,6 +127,8 @@ //! fn print_2_later(val: Arc) { //! let _ = workqueue::system().enqueue::, 2>(val); //! } +//! # print_1_later(MyStruct::new(24, 25).unwrap()); +//! # print_2_later(MyStruct::new(41, 42).unwrap()); //! ``` //! //! C header: [`include/linux/workqueue.h`](srctree/include/linux/workqueue.h) @@ -519,7 +522,15 @@ impl_has_work! { impl{T} HasWork for ClosureWork { self.work } } -// SAFETY: TODO. +// SAFETY: The `__enqueue` implementation in RawWorkItem uses a `work_struct` initialized with the +// `run` method of this trait as the function pointer because: +// - `__enqueue` gets the `work_struct` from the `Work` field, using `T::raw_get_work`. +// - The only safe way to create a `Work` object is through `Work::new`. +// - `Work::new` makes sure that `T::Pointer::run` is passed to `init_work_with_key`. +// - Finally `Work` and `RawWorkItem` guarantee that the correct `Work` field +// will be used because of the ID const generic bound. This makes sure that `T::raw_get_work` +// uses the correct offset for the `Work` field, and `Work::new` picks the correct +// implementation of `WorkItemPointer` for `Arc`. unsafe impl WorkItemPointer for Arc where T: WorkItem, @@ -537,7 +548,13 @@ where } } -// SAFETY: TODO. +// SAFETY: The `work_struct` raw pointer is guaranteed to be valid for the duration of the call to +// the closure because we get it from an `Arc`, which means that the ref count will be at least 1, +// and we don't drop the `Arc` ourselves. If `queue_work_on` returns true, it is further guaranteed +// to be valid until a call to the function pointer in `work_struct` because we leak the memory it +// points to, and only reclaim it if the closure returns false, or in `WorkItemPointer::run`, which +// is what the function pointer in the `work_struct` must be pointing to, according to the safety +// requirements of `WorkItemPointer`. unsafe impl RawWorkItem for Arc where T: WorkItem, diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index 4ab94e44adfe..d61bc6a56425 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -123,12 +123,12 @@ pub fn module(ts: TokenStream) -> TokenStream { /// used on the Rust side, it should not be possible to call the default /// implementation. This is done to ensure that we call the vtable methods /// through the C vtable, and not through the Rust vtable. Therefore, the -/// default implementation should call `kernel::build_error`, which prevents +/// default implementation should call `build_error!`, which prevents /// calls to this function at compile time: /// /// ```compile_fail /// # // Intentionally missing `use`s to simplify `rusttest`. -/// kernel::build_error(VTABLE_DEFAULT_ERROR) +/// build_error!(VTABLE_DEFAULT_ERROR) /// ``` /// /// Note that you might need to import [`kernel::error::VTABLE_DEFAULT_ERROR`]. @@ -145,11 +145,11 @@ pub fn module(ts: TokenStream) -> TokenStream { /// #[vtable] /// pub trait Operations: Send + Sync + Sized { /// fn foo(&self) -> Result<()> { -/// kernel::build_error(VTABLE_DEFAULT_ERROR) +/// build_error!(VTABLE_DEFAULT_ERROR) /// } /// /// fn bar(&self) -> Result<()> { -/// kernel::build_error(VTABLE_DEFAULT_ERROR) +/// build_error!(VTABLE_DEFAULT_ERROR) /// } /// } /// diff --git a/rust/macros/module.rs b/rust/macros/module.rs index 2587f41b0d39..cdf94f4982df 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -228,6 +228,10 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { kernel::ThisModule::from_ptr(core::ptr::null_mut()) }}; + impl kernel::ModuleMetadata for {type_} {{ + const NAME: &'static kernel::str::CStr = kernel::c_str!(\"{name}\"); + }} + // Double nested modules, since then nobody can access the public items inside. mod __module_init {{ mod __module_init {{ diff --git a/samples/Kconfig b/samples/Kconfig index b288d9991d27..820e00b2ed68 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -291,8 +291,19 @@ config SAMPLE_CGROUP help Build samples that demonstrate the usage of the cgroup API. +config SAMPLE_CHECK_EXEC + bool "Exec secure bits examples" + depends on CC_CAN_LINK && HEADERS_INSTALL + help + Build a tool to easily configure SECBIT_EXEC_RESTRICT_FILE and + SECBIT_EXEC_DENY_INTERACTIVE, and a simple script interpreter to + demonstrate how they should be used with execveat(2) + + AT_EXECVE_CHECK. + source "samples/rust/Kconfig" +source "samples/damon/Kconfig" + endif # SAMPLES config HAVE_SAMPLE_FTRACE_DIRECT diff --git a/samples/Makefile b/samples/Makefile index b85fa64390c5..f24cd0d72dd0 100644 --- a/samples/Makefile +++ b/samples/Makefile @@ -3,6 +3,7 @@ subdir-$(CONFIG_SAMPLE_AUXDISPLAY) += auxdisplay subdir-$(CONFIG_SAMPLE_ANDROID_BINDERFS) += binderfs +subdir-$(CONFIG_SAMPLE_CHECK_EXEC) += check-exec subdir-$(CONFIG_SAMPLE_CGROUP) += cgroup obj-$(CONFIG_SAMPLE_CONFIGFS) += configfs/ obj-$(CONFIG_SAMPLE_CONNECTOR) += connector/ @@ -39,3 +40,5 @@ obj-$(CONFIG_SAMPLE_KMEMLEAK) += kmemleak/ obj-$(CONFIG_SAMPLE_CORESIGHT_SYSCFG) += coresight/ obj-$(CONFIG_SAMPLE_FPROBE) += fprobe/ obj-$(CONFIG_SAMPLES_RUST) += rust/ +obj-$(CONFIG_SAMPLE_DAMON_WSSE) += damon/ +obj-$(CONFIG_SAMPLE_DAMON_PRCL) += damon/ diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 96a05e70ace3..dd9944a97b7e 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -123,7 +123,7 @@ always-y += ibumad_kern.o always-y += hbm_out_kern.o always-y += hbm_edt_kern.o -TPROGS_CFLAGS = $(TPROGS_USER_CFLAGS) +COMMON_CFLAGS = $(TPROGS_USER_CFLAGS) TPROGS_LDFLAGS = $(TPROGS_USER_LDFLAGS) ifeq ($(ARCH), arm) diff --git a/samples/bpf/xdp2skb_meta_kern.c b/samples/bpf/xdp2skb_meta_kern.c index af29a1bde4e4..3c36c25d9902 100644 --- a/samples/bpf/xdp2skb_meta_kern.c +++ b/samples/bpf/xdp2skb_meta_kern.c @@ -63,7 +63,6 @@ SEC("tc_mark") int _tc_mark(struct __sk_buff *ctx) { void *data = (void *)(unsigned long)ctx->data; - void *data_end = (void *)(unsigned long)ctx->data_end; void *data_meta = (void *)(unsigned long)ctx->data_meta; struct meta_info *meta = data_meta; diff --git a/samples/check-exec/.gitignore b/samples/check-exec/.gitignore new file mode 100644 index 000000000000..cd759a19dacd --- /dev/null +++ b/samples/check-exec/.gitignore @@ -0,0 +1,2 @@ +/inc +/set-exec diff --git a/samples/check-exec/Makefile b/samples/check-exec/Makefile new file mode 100644 index 000000000000..c4f08ad0f8e3 --- /dev/null +++ b/samples/check-exec/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: BSD-3-Clause + +userprogs-always-y := \ + inc \ + set-exec + +userccflags += -I usr/include + +.PHONY: all clean + +all: + $(MAKE) -C ../.. samples/check-exec/ + +clean: + $(MAKE) -C ../.. M=samples/check-exec/ clean diff --git a/samples/check-exec/inc.c b/samples/check-exec/inc.c new file mode 100644 index 000000000000..7f6ef06a2f06 --- /dev/null +++ b/samples/check-exec/inc.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Very simple script interpreter that can evaluate two different commands (one + * per line): + * - "?" to initialize a counter from user's input; + * - "+" to increment the counter (which is set to 0 by default). + * + * See tools/testing/selftests/exec/check-exec-tests.sh and + * Documentation/userspace-api/check_exec.rst + * + * Copyright © 2024 Microsoft Corporation + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + +/* Returns 1 on error, 0 otherwise. */ +static int interpret_buffer(char *buffer, size_t buffer_size) +{ + char *line, *saveptr = NULL; + long long number = 0; + + /* Each command is the first character of a line. */ + saveptr = NULL; + line = strtok_r(buffer, "\n", &saveptr); + while (line) { + if (*line != '#' && strlen(line) != 1) { + fprintf(stderr, "# ERROR: Unknown string\n"); + return 1; + } + switch (*line) { + case '#': + /* Skips shebang and comments. */ + break; + case '+': + /* Increments and prints the number. */ + number++; + printf("%lld\n", number); + break; + case '?': + /* Reads integer from stdin. */ + fprintf(stderr, "> Enter new number: \n"); + if (scanf("%lld", &number) != 1) { + fprintf(stderr, + "# WARNING: Failed to read number from stdin\n"); + } + break; + default: + fprintf(stderr, "# ERROR: Unknown character '%c'\n", + *line); + return 1; + } + line = strtok_r(NULL, "\n", &saveptr); + } + return 0; +} + +/* Returns 1 on error, 0 otherwise. */ +static int interpret_stream(FILE *script, char *const script_name, + char *const *const envp, const bool restrict_stream) +{ + int err; + char *const script_argv[] = { script_name, NULL }; + char buf[128] = {}; + size_t buf_size = sizeof(buf); + + /* + * We pass a valid argv and envp to the kernel to emulate a native + * script execution. We must use the script file descriptor instead of + * the script path name to avoid race conditions. + */ + err = sys_execveat(fileno(script), "", script_argv, envp, + AT_EMPTY_PATH | AT_EXECVE_CHECK); + if (err && restrict_stream) { + perror("ERROR: Script execution check"); + return 1; + } + + /* Reads script. */ + buf_size = fread(buf, 1, buf_size - 1, script); + return interpret_buffer(buf, buf_size); +} + +static void print_usage(const char *argv0) +{ + fprintf(stderr, "usage: %s | -i | -c \n\n", + argv0); + fprintf(stderr, "Example:\n"); + fprintf(stderr, " ./set-exec -fi -- ./inc -i < script-exec.inc\n"); +} + +int main(const int argc, char *const argv[], char *const *const envp) +{ + int opt; + char *cmd = NULL; + char *script_name = NULL; + bool interpret_stdin = false; + FILE *script_file = NULL; + int secbits; + bool deny_interactive, restrict_file; + size_t arg_nb; + + secbits = prctl(PR_GET_SECUREBITS); + if (secbits == -1) { + /* + * This should never happen, except with a buggy seccomp + * filter. + */ + perror("ERROR: Failed to get securebits"); + return 1; + } + + deny_interactive = !!(secbits & SECBIT_EXEC_DENY_INTERACTIVE); + restrict_file = !!(secbits & SECBIT_EXEC_RESTRICT_FILE); + + while ((opt = getopt(argc, argv, "c:i")) != -1) { + switch (opt) { + case 'c': + if (cmd) { + fprintf(stderr, "ERROR: Command already set"); + return 1; + } + cmd = optarg; + break; + case 'i': + interpret_stdin = true; + break; + default: + print_usage(argv[0]); + return 1; + } + } + + /* Checks that only one argument is used, or read stdin. */ + arg_nb = !!cmd + !!interpret_stdin; + if (arg_nb == 0 && argc == 2) { + script_name = argv[1]; + } else if (arg_nb != 1) { + print_usage(argv[0]); + return 1; + } + + if (cmd) { + /* + * Other kind of interactive interpretations should be denied + * as well (e.g. CLI arguments passing script snippets, + * environment variables interpreted as script). However, any + * way to pass script files should only be restricted according + * to restrict_file. + */ + if (deny_interactive) { + fprintf(stderr, + "ERROR: Interactive interpretation denied.\n"); + return 1; + } + + return interpret_buffer(cmd, strlen(cmd)); + } + + if (interpret_stdin && !script_name) { + script_file = stdin; + /* + * As for any execve(2) call, this path may be logged by the + * kernel. + */ + script_name = "/proc/self/fd/0"; + /* + * When stdin is used, it can point to a regular file or a + * pipe. Restrict stdin execution according to + * SECBIT_EXEC_DENY_INTERACTIVE but always allow executable + * files (which are not considered as interactive inputs). + */ + return interpret_stream(script_file, script_name, envp, + deny_interactive); + } else if (script_name && !interpret_stdin) { + /* + * In this sample, we don't pass any argument to scripts, but + * otherwise we would have to forge an argv with such + * arguments. + */ + script_file = fopen(script_name, "r"); + if (!script_file) { + perror("ERROR: Failed to open script"); + return 1; + } + /* + * Restricts file execution according to + * SECBIT_EXEC_RESTRICT_FILE. + */ + return interpret_stream(script_file, script_name, envp, + restrict_file); + } + + print_usage(argv[0]); + return 1; +} diff --git a/samples/check-exec/run-script-ask.inc b/samples/check-exec/run-script-ask.inc new file mode 100755 index 000000000000..8ef0fdc37266 --- /dev/null +++ b/samples/check-exec/run-script-ask.inc @@ -0,0 +1,9 @@ +#!/usr/bin/env sh +# SPDX-License-Identifier: BSD-3-Clause + +DIR="$(dirname -- "$0")" + +PATH="${PATH}:${DIR}" + +set -x +"${DIR}/script-ask.inc" diff --git a/samples/check-exec/script-ask.inc b/samples/check-exec/script-ask.inc new file mode 100755 index 000000000000..720a8e649225 --- /dev/null +++ b/samples/check-exec/script-ask.inc @@ -0,0 +1,5 @@ +#!/usr/bin/env inc +# SPDX-License-Identifier: BSD-3-Clause + +? ++ diff --git a/samples/check-exec/script-exec.inc b/samples/check-exec/script-exec.inc new file mode 100755 index 000000000000..3245cb9d8dd1 --- /dev/null +++ b/samples/check-exec/script-exec.inc @@ -0,0 +1,4 @@ +#!/usr/bin/env inc +# SPDX-License-Identifier: BSD-3-Clause + ++ diff --git a/samples/check-exec/script-noexec.inc b/samples/check-exec/script-noexec.inc new file mode 100644 index 000000000000..3245cb9d8dd1 --- /dev/null +++ b/samples/check-exec/script-noexec.inc @@ -0,0 +1,4 @@ +#!/usr/bin/env inc +# SPDX-License-Identifier: BSD-3-Clause + ++ diff --git a/samples/check-exec/set-exec.c b/samples/check-exec/set-exec.c new file mode 100644 index 000000000000..ba86a60a20dd --- /dev/null +++ b/samples/check-exec/set-exec.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Simple tool to set SECBIT_EXEC_RESTRICT_FILE, SECBIT_EXEC_DENY_INTERACTIVE, + * before executing a command. + * + * Copyright © 2024 Microsoft Corporation + */ + +#define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static void print_usage(const char *argv0) +{ + fprintf(stderr, "usage: %s -f|-i -- [args]...\n\n", argv0); + fprintf(stderr, "Execute a command with\n"); + fprintf(stderr, "- SECBIT_EXEC_RESTRICT_FILE set: -f\n"); + fprintf(stderr, "- SECBIT_EXEC_DENY_INTERACTIVE set: -i\n"); +} + +int main(const int argc, char *const argv[], char *const *const envp) +{ + const char *cmd_path; + char *const *cmd_argv; + int opt, secbits_cur, secbits_new; + bool has_policy = false; + + secbits_cur = prctl(PR_GET_SECUREBITS); + if (secbits_cur == -1) { + /* + * This should never happen, except with a buggy seccomp + * filter. + */ + perror("ERROR: Failed to get securebits"); + return 1; + } + + secbits_new = secbits_cur; + while ((opt = getopt(argc, argv, "fi")) != -1) { + switch (opt) { + case 'f': + secbits_new |= SECBIT_EXEC_RESTRICT_FILE | + SECBIT_EXEC_RESTRICT_FILE_LOCKED; + has_policy = true; + break; + case 'i': + secbits_new |= SECBIT_EXEC_DENY_INTERACTIVE | + SECBIT_EXEC_DENY_INTERACTIVE_LOCKED; + has_policy = true; + break; + default: + print_usage(argv[0]); + return 1; + } + } + + if (!argv[optind] || !has_policy) { + print_usage(argv[0]); + return 1; + } + + if (secbits_cur != secbits_new && + prctl(PR_SET_SECUREBITS, secbits_new)) { + perror("Failed to set secure bit(s)."); + fprintf(stderr, + "Hint: The running kernel may not support this feature.\n"); + return 1; + } + + cmd_path = argv[optind]; + cmd_argv = argv + optind; + fprintf(stderr, "Executing command...\n"); + execvpe(cmd_path, cmd_argv, envp); + fprintf(stderr, "Failed to execute \"%s\": %s\n", cmd_path, + strerror(errno)); + return 1; +} diff --git a/samples/damon/Kconfig b/samples/damon/Kconfig new file mode 100644 index 000000000000..63f6dcd71daa --- /dev/null +++ b/samples/damon/Kconfig @@ -0,0 +1,30 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "DAMON Samples" + +config SAMPLE_DAMON_WSSE + bool "DAMON sameple module for working set size estimation" + depends on DAMON && DAMON_VADDR + help + This builds DAMON sample module for working set size estimation. + + The module receives a pid, monitor access to the virtual address + space of the process, estimate working set size of the process, and + repeatedly prints the size on the kernel log. + + If unsure, say N. + +config SAMPLE_DAMON_PRCL + bool "DAMON sameple module for access-aware proactive reclamation" + depends on DAMON && DAMON_VADDR + help + This builds DAMON sample module for access-aware proactive + reclamation. + + The module receives a pid, monitor access to the virtual address + space of the process, find memory regions that not accessed, and + proactively reclaim the regions. + + If unsure, say N. + +endmenu diff --git a/samples/damon/Makefile b/samples/damon/Makefile new file mode 100644 index 000000000000..7f155143f237 --- /dev/null +++ b/samples/damon/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_SAMPLE_DAMON_WSSE) += wsse.o +obj-$(CONFIG_SAMPLE_DAMON_PRCL) += prcl.o diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c new file mode 100644 index 000000000000..c3acbdab7a62 --- /dev/null +++ b/samples/damon/prcl.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * proactive reclamation: monitor access pattern of a given process, find + * regiosn that seems not accessed, and proactively page out the regions. + */ + +#define pr_fmt(fmt) "damon_sample_prcl: " fmt + +#include +#include +#include +#include + +static int target_pid __read_mostly; +module_param(target_pid, int, 0600); + +static int damon_sample_prcl_enable_store( + const char *val, const struct kernel_param *kp); + +static const struct kernel_param_ops enable_param_ops = { + .set = damon_sample_prcl_enable_store, + .get = param_get_bool, +}; + +static bool enable __read_mostly; +module_param_cb(enable, &enable_param_ops, &enable, 0600); +MODULE_PARM_DESC(enable, "Enable of disable DAMON_SAMPLE_WSSE"); + +static struct damon_ctx *ctx; +static struct pid *target_pidp; + +static int damon_sample_prcl_after_aggregate(struct damon_ctx *c) +{ + struct damon_target *t; + + damon_for_each_target(t, c) { + struct damon_region *r; + unsigned long wss = 0; + + damon_for_each_region(r, t) { + if (r->nr_accesses > 0) + wss += r->ar.end - r->ar.start; + } + pr_info("wss: %lu\n", wss); + } + return 0; +} + +static int damon_sample_prcl_start(void) +{ + struct damon_target *target; + struct damos *scheme; + + pr_info("start\n"); + + ctx = damon_new_ctx(); + if (!ctx) + return -ENOMEM; + if (damon_select_ops(ctx, DAMON_OPS_VADDR)) { + damon_destroy_ctx(ctx); + return -EINVAL; + } + + target = damon_new_target(); + if (!target) { + damon_destroy_ctx(ctx); + return -ENOMEM; + } + damon_add_target(ctx, target); + target_pidp = find_get_pid(target_pid); + if (!target_pidp) { + damon_destroy_ctx(ctx); + return -EINVAL; + } + target->pid = target_pidp; + + ctx->callback.after_aggregation = damon_sample_prcl_after_aggregate; + + scheme = damon_new_scheme( + &(struct damos_access_pattern) { + .min_sz_region = PAGE_SIZE, + .max_sz_region = ULONG_MAX, + .min_nr_accesses = 0, + .max_nr_accesses = 0, + .min_age_region = 50, + .max_age_region = UINT_MAX}, + DAMOS_PAGEOUT, + 0, + &(struct damos_quota){}, + &(struct damos_watermarks){}, + NUMA_NO_NODE); + if (!scheme) { + damon_destroy_ctx(ctx); + return -ENOMEM; + } + damon_set_schemes(ctx, &scheme, 1); + + return damon_start(&ctx, 1, true); +} + +static void damon_sample_prcl_stop(void) +{ + pr_info("stop\n"); + if (ctx) { + damon_stop(&ctx, 1); + damon_destroy_ctx(ctx); + } + if (target_pidp) + put_pid(target_pidp); +} + +static int damon_sample_prcl_enable_store( + const char *val, const struct kernel_param *kp) +{ + bool enabled = enable; + int err; + + err = kstrtobool(val, &enable); + if (err) + return err; + + if (enable == enabled) + return 0; + + if (enable) + return damon_sample_prcl_start(); + damon_sample_prcl_stop(); + return 0; +} + +static int __init damon_sample_prcl_init(void) +{ + return 0; +} + +module_init(damon_sample_prcl_init); diff --git a/samples/damon/wsse.c b/samples/damon/wsse.c new file mode 100644 index 000000000000..11be25803274 --- /dev/null +++ b/samples/damon/wsse.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * working set size estimation: monitor access pattern of given process and + * print estimated working set size (total size of regions that showing some + * access). + */ + +#define pr_fmt(fmt) "damon_sample_wsse: " fmt + +#include +#include +#include +#include + +static int target_pid __read_mostly; +module_param(target_pid, int, 0600); + +static int damon_sample_wsse_enable_store( + const char *val, const struct kernel_param *kp); + +static const struct kernel_param_ops enable_param_ops = { + .set = damon_sample_wsse_enable_store, + .get = param_get_bool, +}; + +static bool enable __read_mostly; +module_param_cb(enable, &enable_param_ops, &enable, 0600); +MODULE_PARM_DESC(enable, "Enable or disable DAMON_SAMPLE_WSSE"); + +static struct damon_ctx *ctx; +static struct pid *target_pidp; + +static int damon_sample_wsse_after_aggregate(struct damon_ctx *c) +{ + struct damon_target *t; + + damon_for_each_target(t, c) { + struct damon_region *r; + unsigned long wss = 0; + + damon_for_each_region(r, t) { + if (r->nr_accesses > 0) + wss += r->ar.end - r->ar.start; + } + pr_info("wss: %lu\n", wss); + } + return 0; +} + +static int damon_sample_wsse_start(void) +{ + struct damon_target *target; + + pr_info("start\n"); + + ctx = damon_new_ctx(); + if (!ctx) + return -ENOMEM; + if (damon_select_ops(ctx, DAMON_OPS_VADDR)) { + damon_destroy_ctx(ctx); + return -EINVAL; + } + + target = damon_new_target(); + if (!target) { + damon_destroy_ctx(ctx); + return -ENOMEM; + } + damon_add_target(ctx, target); + target_pidp = find_get_pid(target_pid); + if (!target_pidp) { + damon_destroy_ctx(ctx); + return -EINVAL; + } + target->pid = target_pidp; + + ctx->callback.after_aggregation = damon_sample_wsse_after_aggregate; + return damon_start(&ctx, 1, true); +} + +static void damon_sample_wsse_stop(void) +{ + pr_info("stop\n"); + if (ctx) { + damon_stop(&ctx, 1); + damon_destroy_ctx(ctx); + } + if (target_pidp) + put_pid(target_pidp); +} + +static int damon_sample_wsse_enable_store( + const char *val, const struct kernel_param *kp) +{ + bool enabled = enable; + int err; + + err = kstrtobool(val, &enable); + if (err) + return err; + + if (enable == enabled) + return 0; + + if (enable) + return damon_sample_wsse_start(); + damon_sample_wsse_stop(); + return 0; +} + +static int __init damon_sample_wsse_init(void) +{ + return 0; +} + +module_init(damon_sample_wsse_init); diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c index 0a50b05add96..bfe98ce826f3 100644 --- a/samples/fprobe/fprobe_example.c +++ b/samples/fprobe/fprobe_example.c @@ -50,7 +50,7 @@ static void show_backtrace(void) static int sample_entry_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { if (use_trace) /* @@ -67,7 +67,7 @@ static int sample_entry_handler(struct fprobe *fp, unsigned long ip, } static void sample_exit_handler(struct fprobe *fp, unsigned long ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *regs, void *data) { unsigned long rip = ret_ip; diff --git a/samples/landlock/sandboxer.c b/samples/landlock/sandboxer.c index 57565dfd74a2..07fab2ef534e 100644 --- a/samples/landlock/sandboxer.c +++ b/samples/landlock/sandboxer.c @@ -91,6 +91,9 @@ static int parse_path(char *env_path, const char ***const path_list) } } *path_list = malloc(num_paths * sizeof(**path_list)); + if (!*path_list) + return -1; + for (i = 0; i < num_paths; i++) (*path_list)[i] = strsep(&env_path, ENV_DELIMITER); @@ -127,6 +130,10 @@ static int populate_ruleset_fs(const char *const env_var, const int ruleset_fd, env_path_name = strdup(env_path_name); unsetenv(env_var); num_paths = parse_path(env_path_name, &path_list); + if (num_paths < 0) { + fprintf(stderr, "Failed to allocate memory\n"); + goto out_free_name; + } if (num_paths == 1 && path_list[0][0] == '\0') { /* * Allows to not use all possible restrictions (e.g. use diff --git a/samples/livepatch/livepatch-callbacks-busymod.c b/samples/livepatch/livepatch-callbacks-busymod.c index 378e2d40271a..69105596e72e 100644 --- a/samples/livepatch/livepatch-callbacks-busymod.c +++ b/samples/livepatch/livepatch-callbacks-busymod.c @@ -44,8 +44,7 @@ static void busymod_work_func(struct work_struct *work) static int livepatch_callbacks_mod_init(void) { pr_info("%s\n", __func__); - schedule_delayed_work(&work, - msecs_to_jiffies(1000 * 0)); + schedule_delayed_work(&work, 0); return 0; } diff --git a/samples/livepatch/livepatch-shadow-fix1.c b/samples/livepatch/livepatch-shadow-fix1.c index 6701641bf12d..f3f153895d6c 100644 --- a/samples/livepatch/livepatch-shadow-fix1.c +++ b/samples/livepatch/livepatch-shadow-fix1.c @@ -72,8 +72,7 @@ static struct dummy *livepatch_fix1_dummy_alloc(void) if (!d) return NULL; - d->jiffies_expire = jiffies + - msecs_to_jiffies(1000 * EXPIRE_PERIOD); + d->jiffies_expire = jiffies + secs_to_jiffies(EXPIRE_PERIOD); /* * Patch: save the extra memory location into a SV_LEAK shadow diff --git a/samples/livepatch/livepatch-shadow-mod.c b/samples/livepatch/livepatch-shadow-mod.c index 7e753b0d2fa6..5d83ad5a8118 100644 --- a/samples/livepatch/livepatch-shadow-mod.c +++ b/samples/livepatch/livepatch-shadow-mod.c @@ -101,8 +101,7 @@ static __used noinline struct dummy *dummy_alloc(void) if (!d) return NULL; - d->jiffies_expire = jiffies + - msecs_to_jiffies(1000 * EXPIRE_PERIOD); + d->jiffies_expire = jiffies + secs_to_jiffies(EXPIRE_PERIOD); /* Oops, forgot to save leak! */ leak = kzalloc(sizeof(*leak), GFP_KERNEL); @@ -152,8 +151,7 @@ static void alloc_work_func(struct work_struct *work) list_add(&d->list, &dummy_list); mutex_unlock(&dummy_list_mutex); - schedule_delayed_work(&alloc_dwork, - msecs_to_jiffies(1000 * ALLOC_PERIOD)); + schedule_delayed_work(&alloc_dwork, secs_to_jiffies(ALLOC_PERIOD)); } /* @@ -184,16 +182,13 @@ static void cleanup_work_func(struct work_struct *work) } mutex_unlock(&dummy_list_mutex); - schedule_delayed_work(&cleanup_dwork, - msecs_to_jiffies(1000 * CLEANUP_PERIOD)); + schedule_delayed_work(&cleanup_dwork, secs_to_jiffies(CLEANUP_PERIOD)); } static int livepatch_shadow_mod_init(void) { - schedule_delayed_work(&alloc_dwork, - msecs_to_jiffies(1000 * ALLOC_PERIOD)); - schedule_delayed_work(&cleanup_dwork, - msecs_to_jiffies(1000 * CLEANUP_PERIOD)); + schedule_delayed_work(&alloc_dwork, secs_to_jiffies(ALLOC_PERIOD)); + schedule_delayed_work(&cleanup_dwork, secs_to_jiffies(CLEANUP_PERIOD)); return 0; } diff --git a/samples/rust/Kconfig b/samples/rust/Kconfig index b0f74a81c8f9..918dbead2c0b 100644 --- a/samples/rust/Kconfig +++ b/samples/rust/Kconfig @@ -20,6 +20,16 @@ config SAMPLE_RUST_MINIMAL If unsure, say N. +config SAMPLE_RUST_MISC_DEVICE + tristate "Misc device" + help + This option builds the Rust misc device. + + To compile this as a module, choose M here: + the module will be called rust_misc_device. + + If unsure, say N. + config SAMPLE_RUST_PRINT tristate "Printing macros" help @@ -30,6 +40,27 @@ config SAMPLE_RUST_PRINT If unsure, say N. +config SAMPLE_RUST_DRIVER_PCI + tristate "PCI Driver" + depends on PCI + help + This option builds the Rust PCI driver sample. + + To compile this as a module, choose M here: + the module will be called driver_pci. + + If unsure, say N. + +config SAMPLE_RUST_DRIVER_PLATFORM + tristate "Platform Driver" + help + This option builds the Rust Platform driver sample. + + To compile this as a module, choose M here: + the module will be called rust_driver_platform. + + If unsure, say N. + config SAMPLE_RUST_HOSTPROGS bool "Host programs" help diff --git a/samples/rust/Makefile b/samples/rust/Makefile index c1a5c1655395..5a8ab0df0567 100644 --- a/samples/rust/Makefile +++ b/samples/rust/Makefile @@ -2,7 +2,10 @@ ccflags-y += -I$(src) # needed for trace events obj-$(CONFIG_SAMPLE_RUST_MINIMAL) += rust_minimal.o +obj-$(CONFIG_SAMPLE_RUST_MISC_DEVICE) += rust_misc_device.o obj-$(CONFIG_SAMPLE_RUST_PRINT) += rust_print.o +obj-$(CONFIG_SAMPLE_RUST_DRIVER_PCI) += rust_driver_pci.o +obj-$(CONFIG_SAMPLE_RUST_DRIVER_PLATFORM) += rust_driver_platform.o rust_print-y := rust_print_main.o rust_print_events.o diff --git a/samples/rust/rust_driver_pci.rs b/samples/rust/rust_driver_pci.rs new file mode 100644 index 000000000000..1fb6e44f3395 --- /dev/null +++ b/samples/rust/rust_driver_pci.rs @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Rust PCI driver sample (based on QEMU's `pci-testdev`). +//! +//! To make this driver probe, QEMU must be run with `-device pci-testdev`. + +use kernel::{bindings, c_str, devres::Devres, pci, prelude::*}; + +struct Regs; + +impl Regs { + const TEST: usize = 0x0; + const OFFSET: usize = 0x4; + const DATA: usize = 0x8; + const COUNT: usize = 0xC; + const END: usize = 0x10; +} + +type Bar0 = pci::Bar<{ Regs::END }>; + +#[derive(Debug)] +struct TestIndex(u8); + +impl TestIndex { + const NO_EVENTFD: Self = Self(0); +} + +struct SampleDriver { + pdev: pci::Device, + bar: Devres, +} + +kernel::pci_device_table!( + PCI_TABLE, + MODULE_PCI_TABLE, + ::IdInfo, + [( + pci::DeviceId::from_id(bindings::PCI_VENDOR_ID_REDHAT, 0x5), + TestIndex::NO_EVENTFD + )] +); + +impl SampleDriver { + fn testdev(index: &TestIndex, bar: &Bar0) -> Result { + // Select the test. + bar.writeb(index.0, Regs::TEST); + + let offset = u32::from_le(bar.readl(Regs::OFFSET)) as usize; + let data = bar.readb(Regs::DATA); + + // Write `data` to `offset` to increase `count` by one. + // + // Note that we need `try_writeb`, since `offset` can't be checked at compile-time. + bar.try_writeb(data, offset)?; + + Ok(bar.readl(Regs::COUNT)) + } +} + +impl pci::Driver for SampleDriver { + type IdInfo = TestIndex; + + const ID_TABLE: pci::IdTable = &PCI_TABLE; + + fn probe(pdev: &mut pci::Device, info: &Self::IdInfo) -> Result>> { + dev_dbg!( + pdev.as_ref(), + "Probe Rust PCI driver sample (PCI ID: 0x{:x}, 0x{:x}).\n", + pdev.vendor_id(), + pdev.device_id() + ); + + pdev.enable_device_mem()?; + pdev.set_master(); + + let bar = pdev.iomap_region_sized::<{ Regs::END }>(0, c_str!("rust_driver_pci"))?; + + let drvdata = KBox::new( + Self { + pdev: pdev.clone(), + bar, + }, + GFP_KERNEL, + )?; + + let bar = drvdata.bar.try_access().ok_or(ENXIO)?; + + dev_info!( + pdev.as_ref(), + "pci-testdev data-match count: {}\n", + Self::testdev(info, &bar)? + ); + + Ok(drvdata.into()) + } +} + +impl Drop for SampleDriver { + fn drop(&mut self) { + dev_dbg!(self.pdev.as_ref(), "Remove Rust PCI driver sample.\n"); + } +} + +kernel::module_pci_driver! { + type: SampleDriver, + name: "rust_driver_pci", + author: "Danilo Krummrich", + description: "Rust PCI driver", + license: "GPL v2", +} diff --git a/samples/rust/rust_driver_platform.rs b/samples/rust/rust_driver_platform.rs new file mode 100644 index 000000000000..8120609e2940 --- /dev/null +++ b/samples/rust/rust_driver_platform.rs @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Rust Platform driver sample. + +use kernel::{c_str, of, platform, prelude::*}; + +struct SampleDriver { + pdev: platform::Device, +} + +struct Info(u32); + +kernel::of_device_table!( + OF_TABLE, + MODULE_OF_TABLE, + ::IdInfo, + [(of::DeviceId::new(c_str!("test,rust-device")), Info(42))] +); + +impl platform::Driver for SampleDriver { + type IdInfo = Info; + const OF_ID_TABLE: Option> = Some(&OF_TABLE); + + fn probe(pdev: &mut platform::Device, info: Option<&Self::IdInfo>) -> Result>> { + dev_dbg!(pdev.as_ref(), "Probe Rust Platform driver sample.\n"); + + if let Some(info) = info { + dev_info!(pdev.as_ref(), "Probed with info: '{}'.\n", info.0); + } + + let drvdata = KBox::new(Self { pdev: pdev.clone() }, GFP_KERNEL)?; + + Ok(drvdata.into()) + } +} + +impl Drop for SampleDriver { + fn drop(&mut self) { + dev_dbg!(self.pdev.as_ref(), "Remove Rust Platform driver sample.\n"); + } +} + +kernel::module_platform_driver! { + type: SampleDriver, + name: "rust_driver_platform", + author: "Danilo Krummrich", + description: "Rust Platform driver", + license: "GPL v2", +} diff --git a/samples/rust/rust_misc_device.rs b/samples/rust/rust_misc_device.rs new file mode 100644 index 000000000000..40ad7266c225 --- /dev/null +++ b/samples/rust/rust_misc_device.rs @@ -0,0 +1,238 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2024 Google LLC. + +//! Rust misc device sample. + +/// Below is an example userspace C program that exercises this sample's functionality. +/// +/// ```c +/// #include +/// #include +/// #include +/// #include +/// #include +/// #include +/// +/// #define RUST_MISC_DEV_FAIL _IO('|', 0) +/// #define RUST_MISC_DEV_HELLO _IO('|', 0x80) +/// #define RUST_MISC_DEV_GET_VALUE _IOR('|', 0x81, int) +/// #define RUST_MISC_DEV_SET_VALUE _IOW('|', 0x82, int) +/// +/// int main() { +/// int value, new_value; +/// int fd, ret; +/// +/// // Open the device file +/// printf("Opening /dev/rust-misc-device for reading and writing\n"); +/// fd = open("/dev/rust-misc-device", O_RDWR); +/// if (fd < 0) { +/// perror("open"); +/// return errno; +/// } +/// +/// // Make call into driver to say "hello" +/// printf("Calling Hello\n"); +/// ret = ioctl(fd, RUST_MISC_DEV_HELLO, NULL); +/// if (ret < 0) { +/// perror("ioctl: Failed to call into Hello"); +/// close(fd); +/// return errno; +/// } +/// +/// // Get initial value +/// printf("Fetching initial value\n"); +/// ret = ioctl(fd, RUST_MISC_DEV_GET_VALUE, &value); +/// if (ret < 0) { +/// perror("ioctl: Failed to fetch the initial value"); +/// close(fd); +/// return errno; +/// } +/// +/// value++; +/// +/// // Set value to something different +/// printf("Submitting new value (%d)\n", value); +/// ret = ioctl(fd, RUST_MISC_DEV_SET_VALUE, &value); +/// if (ret < 0) { +/// perror("ioctl: Failed to submit new value"); +/// close(fd); +/// return errno; +/// } +/// +/// // Ensure new value was applied +/// printf("Fetching new value\n"); +/// ret = ioctl(fd, RUST_MISC_DEV_GET_VALUE, &new_value); +/// if (ret < 0) { +/// perror("ioctl: Failed to fetch the new value"); +/// close(fd); +/// return errno; +/// } +/// +/// if (value != new_value) { +/// printf("Failed: Committed and retrieved values are different (%d - %d)\n", value, new_value); +/// close(fd); +/// return -1; +/// } +/// +/// // Call the unsuccessful ioctl +/// printf("Attempting to call in to an non-existent IOCTL\n"); +/// ret = ioctl(fd, RUST_MISC_DEV_FAIL, NULL); +/// if (ret < 0) { +/// perror("ioctl: Succeeded to fail - this was expected"); +/// } else { +/// printf("ioctl: Failed to fail\n"); +/// close(fd); +/// return -1; +/// } +/// +/// // Close the device file +/// printf("Closing /dev/rust-misc-device\n"); +/// close(fd); +/// +/// printf("Success\n"); +/// return 0; +/// } +/// ``` +use core::pin::Pin; + +use kernel::{ + c_str, + device::Device, + fs::File, + ioctl::{_IO, _IOC_SIZE, _IOR, _IOW}, + miscdevice::{MiscDevice, MiscDeviceOptions, MiscDeviceRegistration}, + new_mutex, + prelude::*, + sync::Mutex, + types::ARef, + uaccess::{UserSlice, UserSliceReader, UserSliceWriter}, +}; + +const RUST_MISC_DEV_HELLO: u32 = _IO('|' as u32, 0x80); +const RUST_MISC_DEV_GET_VALUE: u32 = _IOR::('|' as u32, 0x81); +const RUST_MISC_DEV_SET_VALUE: u32 = _IOW::('|' as u32, 0x82); + +module! { + type: RustMiscDeviceModule, + name: "rust_misc_device", + author: "Lee Jones", + description: "Rust misc device sample", + license: "GPL", +} + +#[pin_data] +struct RustMiscDeviceModule { + #[pin] + _miscdev: MiscDeviceRegistration, +} + +impl kernel::InPlaceModule for RustMiscDeviceModule { + fn init(_module: &'static ThisModule) -> impl PinInit { + pr_info!("Initialising Rust Misc Device Sample\n"); + + let options = MiscDeviceOptions { + name: c_str!("rust-misc-device"), + }; + + try_pin_init!(Self { + _miscdev <- MiscDeviceRegistration::register(options), + }) + } +} + +struct Inner { + value: i32, +} + +#[pin_data(PinnedDrop)] +struct RustMiscDevice { + #[pin] + inner: Mutex, + dev: ARef, +} + +#[vtable] +impl MiscDevice for RustMiscDevice { + type Ptr = Pin>; + + fn open(_file: &File, misc: &MiscDeviceRegistration) -> Result>> { + let dev = ARef::from(misc.device()); + + dev_info!(dev, "Opening Rust Misc Device Sample\n"); + + KBox::try_pin_init( + try_pin_init! { + RustMiscDevice { + inner <- new_mutex!( Inner{ value: 0_i32 } ), + dev: dev, + } + }, + GFP_KERNEL, + ) + } + + fn ioctl(me: Pin<&RustMiscDevice>, _file: &File, cmd: u32, arg: usize) -> Result { + dev_info!(me.dev, "IOCTLing Rust Misc Device Sample\n"); + + let size = _IOC_SIZE(cmd); + + match cmd { + RUST_MISC_DEV_GET_VALUE => me.get_value(UserSlice::new(arg, size).writer())?, + RUST_MISC_DEV_SET_VALUE => me.set_value(UserSlice::new(arg, size).reader())?, + RUST_MISC_DEV_HELLO => me.hello()?, + _ => { + dev_err!(me.dev, "-> IOCTL not recognised: {}\n", cmd); + return Err(ENOTTY); + } + }; + + Ok(0) + } +} + +#[pinned_drop] +impl PinnedDrop for RustMiscDevice { + fn drop(self: Pin<&mut Self>) { + dev_info!(self.dev, "Exiting the Rust Misc Device Sample\n"); + } +} + +impl RustMiscDevice { + fn set_value(&self, mut reader: UserSliceReader) -> Result { + let new_value = reader.read::()?; + let mut guard = self.inner.lock(); + + dev_info!( + self.dev, + "-> Copying data from userspace (value: {})\n", + new_value + ); + + guard.value = new_value; + Ok(0) + } + + fn get_value(&self, mut writer: UserSliceWriter) -> Result { + let guard = self.inner.lock(); + let value = guard.value; + + // Free-up the lock and use our locally cached instance from here + drop(guard); + + dev_info!( + self.dev, + "-> Copying data to userspace (value: {})\n", + &value + ); + + writer.write::(&value)?; + Ok(0) + } + + fn hello(&self) -> Result { + dev_info!(self.dev, "-> Hello from the Rust Misc Device\n"); + + Ok(0) + } +} diff --git a/samples/rust/rust_print_main.rs b/samples/rust/rust_print_main.rs index aed90a6feecf..7e8af5f176a3 100644 --- a/samples/rust/rust_print_main.rs +++ b/samples/rust/rust_print_main.rs @@ -34,6 +34,24 @@ fn arc_print() -> Result { // Uses `dbg` to print, will move `c` (for temporary debugging purposes). dbg!(c); + { + // `Arc` can be used to delegate dynamic dispatch and the following is an example. + // Both `i32` and `&str` implement `Display`. This enables us to express a unified + // behaviour, contract or protocol on both `i32` and `&str` into a single `Arc` of + // type `Arc`. + + use core::fmt::Display; + fn arc_dyn_print(arc: &Arc) { + pr_info!("Arc says {arc}"); + } + + let a_i32_display: Arc = Arc::new(42i32, GFP_KERNEL)?; + let a_str_display: Arc = a.clone(); + + arc_dyn_print(&a_i32_display); + arc_dyn_print(&a_str_display); + } + // Pretty-prints the debug formatting with lower-case hexadecimal integers. pr_info!("{:#x?}", a); @@ -83,7 +101,7 @@ impl Drop for RustPrint { } mod trace { - use core::ffi::c_int; + use kernel::ffi::c_int; kernel::declare_trace! { /// # Safety diff --git a/samples/vfs/.gitignore b/samples/vfs/.gitignore index 79212d91285b..8708341bc082 100644 --- a/samples/vfs/.gitignore +++ b/samples/vfs/.gitignore @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only /test-fsmount +/test-list-all-mounts /test-statx +/mountinfo diff --git a/samples/vfs/Makefile b/samples/vfs/Makefile index 6377a678134a..6554b73a75c8 100644 --- a/samples/vfs/Makefile +++ b/samples/vfs/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -userprogs-always-y += test-fsmount test-statx +userprogs-always-y += test-fsmount test-statx mountinfo test-list-all-mounts userccflags += -I usr/include diff --git a/samples/vfs/mountinfo.c b/samples/vfs/mountinfo.c new file mode 100644 index 000000000000..bc78275cac69 --- /dev/null +++ b/samples/vfs/mountinfo.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +/* + * Use pidfds, nsfds, listmount() and statmount() mimic the + * contents of /proc/self/mountinfo. + */ +#define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "samples-vfs.h" + +/* max mounts per listmount call */ +#define MAXMOUNTS 1024 + +/* size of struct statmount (including trailing string buffer) */ +#define STATMOUNT_BUFSIZE 4096 + +static bool ext_format; + +#ifndef __NR_pidfd_open +#define __NR_pidfd_open -1 +#endif + +/* + * There are no bindings in glibc for listmount() and statmount() (yet), + * make our own here. + */ +static int statmount(__u64 mnt_id, __u64 mnt_ns_id, __u64 mask, + struct statmount *buf, size_t bufsize, + unsigned int flags) +{ + struct mnt_id_req req = { + .size = MNT_ID_REQ_SIZE_VER0, + .mnt_id = mnt_id, + .param = mask, + }; + + if (mnt_ns_id) { + req.size = MNT_ID_REQ_SIZE_VER1; + req.mnt_ns_id = mnt_ns_id; + } + + return syscall(__NR_statmount, &req, buf, bufsize, flags); +} + +static ssize_t listmount(__u64 mnt_id, __u64 mnt_ns_id, __u64 last_mnt_id, + __u64 list[], size_t num, unsigned int flags) +{ + struct mnt_id_req req = { + .size = MNT_ID_REQ_SIZE_VER0, + .mnt_id = mnt_id, + .param = last_mnt_id, + }; + + if (mnt_ns_id) { + req.size = MNT_ID_REQ_SIZE_VER1; + req.mnt_ns_id = mnt_ns_id; + } + + return syscall(__NR_listmount, &req, list, num, flags); +} + +static void show_mnt_attrs(__u64 flags) +{ + printf("%s", flags & MOUNT_ATTR_RDONLY ? "ro" : "rw"); + + if (flags & MOUNT_ATTR_NOSUID) + printf(",nosuid"); + if (flags & MOUNT_ATTR_NODEV) + printf(",nodev"); + if (flags & MOUNT_ATTR_NOEXEC) + printf(",noexec"); + + switch (flags & MOUNT_ATTR__ATIME) { + case MOUNT_ATTR_RELATIME: + printf(",relatime"); + break; + case MOUNT_ATTR_NOATIME: + printf(",noatime"); + break; + case MOUNT_ATTR_STRICTATIME: + /* print nothing */ + break; + } + + if (flags & MOUNT_ATTR_NODIRATIME) + printf(",nodiratime"); + if (flags & MOUNT_ATTR_NOSYMFOLLOW) + printf(",nosymfollow"); + if (flags & MOUNT_ATTR_IDMAP) + printf(",idmapped"); +} + +static void show_propagation(struct statmount *sm) +{ + if (sm->mnt_propagation & MS_SHARED) + printf(" shared:%llu", sm->mnt_peer_group); + if (sm->mnt_propagation & MS_SLAVE) { + printf(" master:%llu", sm->mnt_master); + if (sm->propagate_from && sm->propagate_from != sm->mnt_master) + printf(" propagate_from:%llu", sm->propagate_from); + } + if (sm->mnt_propagation & MS_UNBINDABLE) + printf(" unbindable"); +} + +static void show_sb_flags(__u64 flags) +{ + printf("%s", flags & MS_RDONLY ? "ro" : "rw"); + if (flags & MS_SYNCHRONOUS) + printf(",sync"); + if (flags & MS_DIRSYNC) + printf(",dirsync"); + if (flags & MS_MANDLOCK) + printf(",mand"); + if (flags & MS_LAZYTIME) + printf(",lazytime"); +} + +static int dump_mountinfo(__u64 mnt_id, __u64 mnt_ns_id) +{ + int ret; + struct statmount *buf = alloca(STATMOUNT_BUFSIZE); + const __u64 mask = STATMOUNT_SB_BASIC | STATMOUNT_MNT_BASIC | + STATMOUNT_PROPAGATE_FROM | STATMOUNT_FS_TYPE | + STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | + STATMOUNT_MNT_OPTS | STATMOUNT_FS_SUBTYPE | + STATMOUNT_SB_SOURCE; + + ret = statmount(mnt_id, mnt_ns_id, mask, buf, STATMOUNT_BUFSIZE, 0); + if (ret < 0) { + perror("statmount"); + return 1; + } + + if (ext_format) + printf("0x%llx 0x%llx 0x%llx ", mnt_ns_id, mnt_id, buf->mnt_parent_id); + + printf("%u %u %u:%u %s %s ", buf->mnt_id_old, buf->mnt_parent_id_old, + buf->sb_dev_major, buf->sb_dev_minor, + &buf->str[buf->mnt_root], + &buf->str[buf->mnt_point]); + show_mnt_attrs(buf->mnt_attr); + show_propagation(buf); + + printf(" - %s", &buf->str[buf->fs_type]); + if (buf->mask & STATMOUNT_FS_SUBTYPE) + printf(".%s", &buf->str[buf->fs_subtype]); + if (buf->mask & STATMOUNT_SB_SOURCE) + printf(" %s ", &buf->str[buf->sb_source]); + else + printf(" :none "); + + show_sb_flags(buf->sb_flags); + if (buf->mask & STATMOUNT_MNT_OPTS) + printf(",%s", &buf->str[buf->mnt_opts]); + printf("\n"); + return 0; +} + +static int dump_mounts(__u64 mnt_ns_id) +{ + __u64 mntid[MAXMOUNTS]; + __u64 last_mnt_id = 0; + ssize_t count; + int i; + + /* + * Get a list of all mntids in mnt_ns_id. If it returns MAXMOUNTS + * mounts, then go again until we get everything. + */ + do { + count = listmount(LSMT_ROOT, mnt_ns_id, last_mnt_id, mntid, MAXMOUNTS, 0); + if (count < 0 || count > MAXMOUNTS) { + errno = count < 0 ? errno : count; + perror("listmount"); + return 1; + } + + /* Walk the returned mntids and print info about each */ + for (i = 0; i < count; ++i) { + int ret = dump_mountinfo(mntid[i], mnt_ns_id); + + if (ret != 0) + return ret; + } + /* Set up last_mnt_id to pick up where we left off */ + last_mnt_id = mntid[count - 1]; + } while (count == MAXMOUNTS); + return 0; +} + +static void usage(const char * const prog) +{ + printf("Usage:\n"); + printf("%s [-e] [-p pid] [-r] [-h]\n", prog); + printf(" -e: extended format\n"); + printf(" -h: print usage message\n"); + printf(" -p: get mount namespace from given pid\n"); + printf(" -r: recursively print all mounts in all child namespaces\n"); +} + +int main(int argc, char * const *argv) +{ + struct mnt_ns_info mni = { .size = MNT_NS_INFO_SIZE_VER0 }; + int pidfd, mntns, ret, opt; + pid_t pid = getpid(); + bool recursive = false; + + while ((opt = getopt(argc, argv, "ehp:r")) != -1) { + switch (opt) { + case 'e': + ext_format = true; + break; + case 'h': + usage(argv[0]); + return 0; + case 'p': + pid = atoi(optarg); + break; + case 'r': + recursive = true; + break; + } + } + + /* Get a pidfd for pid */ + pidfd = syscall(__NR_pidfd_open, pid, 0); + if (pidfd < 0) { + perror("pidfd_open"); + return 1; + } + + /* Get the mnt namespace for pidfd */ + mntns = ioctl(pidfd, PIDFD_GET_MNT_NAMESPACE, NULL); + if (mntns < 0) { + perror("PIDFD_GET_MNT_NAMESPACE"); + return 1; + } + close(pidfd); + + /* get info about mntns. In particular, the mnt_ns_id */ + ret = ioctl(mntns, NS_MNT_GET_INFO, &mni); + if (ret < 0) { + perror("NS_MNT_GET_INFO"); + return 1; + } + + do { + int ret; + + ret = dump_mounts(mni.mnt_ns_id); + if (ret) + return ret; + + if (!recursive) + break; + + /* get the next mntns (and overwrite the old mount ns info) */ + ret = ioctl(mntns, NS_MNT_GET_NEXT, &mni); + close(mntns); + mntns = ret; + } while (mntns >= 0); + + return 0; +} diff --git a/samples/vfs/samples-vfs.h b/samples/vfs/samples-vfs.h new file mode 100644 index 000000000000..103e1e7c4cec --- /dev/null +++ b/samples/vfs/samples-vfs.h @@ -0,0 +1,241 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __SAMPLES_VFS_H +#define __SAMPLES_VFS_H + +#include +#include +#include +#include + +#define die_errno(format, ...) \ + do { \ + fprintf(stderr, "%m | %s: %d: %s: " format "\n", __FILE__, \ + __LINE__, __func__, ##__VA_ARGS__); \ + exit(EXIT_FAILURE); \ + } while (0) + +struct statmount { + __u32 size; /* Total size, including strings */ + __u32 mnt_opts; /* [str] Options (comma separated, escaped) */ + __u64 mask; /* What results were written */ + __u32 sb_dev_major; /* Device ID */ + __u32 sb_dev_minor; + __u64 sb_magic; /* ..._SUPER_MAGIC */ + __u32 sb_flags; /* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */ + __u32 fs_type; /* [str] Filesystem type */ + __u64 mnt_id; /* Unique ID of mount */ + __u64 mnt_parent_id; /* Unique ID of parent (for root == mnt_id) */ + __u32 mnt_id_old; /* Reused IDs used in proc/.../mountinfo */ + __u32 mnt_parent_id_old; + __u64 mnt_attr; /* MOUNT_ATTR_... */ + __u64 mnt_propagation; /* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */ + __u64 mnt_peer_group; /* ID of shared peer group */ + __u64 mnt_master; /* Mount receives propagation from this ID */ + __u64 propagate_from; /* Propagation from in current namespace */ + __u32 mnt_root; /* [str] Root of mount relative to root of fs */ + __u32 mnt_point; /* [str] Mountpoint relative to current root */ + __u64 mnt_ns_id; /* ID of the mount namespace */ + __u32 fs_subtype; /* [str] Subtype of fs_type (if any) */ + __u32 sb_source; /* [str] Source string of the mount */ + __u32 opt_num; /* Number of fs options */ + __u32 opt_array; /* [str] Array of nul terminated fs options */ + __u32 opt_sec_num; /* Number of security options */ + __u32 opt_sec_array; /* [str] Array of nul terminated security options */ + __u64 __spare2[46]; + char str[]; /* Variable size part containing strings */ +}; + +struct mnt_id_req { + __u32 size; + __u32 spare; + __u64 mnt_id; + __u64 param; + __u64 mnt_ns_id; +}; + +#ifndef MNT_ID_REQ_SIZE_VER0 +#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ +#endif + +#ifndef MNT_ID_REQ_SIZE_VER1 +#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */ +#endif + +/* Get the id for a mount namespace */ +#ifndef NS_GET_MNTNS_ID +#define NS_GET_MNTNS_ID _IO(0xb7, 0x5) +#endif + +struct mnt_ns_info { + __u32 size; + __u32 nr_mounts; + __u64 mnt_ns_id; +}; + +#ifndef MNT_NS_INFO_SIZE_VER0 +#define MNT_NS_INFO_SIZE_VER0 16 /* size of first published struct */ +#endif + +#ifndef NS_MNT_GET_INFO +#define NS_MNT_GET_INFO _IOR(0xb7, 10, struct mnt_ns_info) +#endif + +#ifndef NS_MNT_GET_NEXT +#define NS_MNT_GET_NEXT _IOR(0xb7, 11, struct mnt_ns_info) +#endif + +#ifndef NS_MNT_GET_PREV +#define NS_MNT_GET_PREV _IOR(0xb7, 12, struct mnt_ns_info) +#endif + +#ifndef PIDFD_GET_MNT_NAMESPACE +#define PIDFD_GET_MNT_NAMESPACE _IO(0xFF, 3) +#endif + +#ifndef __NR_listmount +#define __NR_listmount 458 +#endif + +#ifndef __NR_statmount +#define __NR_statmount 457 +#endif + +#ifndef LSMT_ROOT +#define LSMT_ROOT 0xffffffffffffffff /* root mount */ +#endif + +/* @mask bits for statmount(2) */ +#ifndef STATMOUNT_SB_BASIC +#define STATMOUNT_SB_BASIC 0x00000001U /* Want/got sb_... */ +#endif + +#ifndef STATMOUNT_MNT_BASIC +#define STATMOUNT_MNT_BASIC 0x00000002U /* Want/got mnt_... */ +#endif + +#ifndef STATMOUNT_PROPAGATE_FROM +#define STATMOUNT_PROPAGATE_FROM 0x00000004U /* Want/got propagate_from */ +#endif + +#ifndef STATMOUNT_MNT_ROOT +#define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ +#endif + +#ifndef STATMOUNT_MNT_POINT +#define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ +#endif + +#ifndef STATMOUNT_FS_TYPE +#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ +#endif + +#ifndef STATMOUNT_MNT_NS_ID +#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ +#endif + +#ifndef STATMOUNT_MNT_OPTS +#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ +#endif + +#ifndef STATMOUNT_FS_SUBTYPE +#define STATMOUNT_FS_SUBTYPE 0x00000100U /* Want/got fs_subtype */ +#endif + +#ifndef STATMOUNT_SB_SOURCE +#define STATMOUNT_SB_SOURCE 0x00000200U /* Want/got sb_source */ +#endif + +#ifndef STATMOUNT_OPT_ARRAY +#define STATMOUNT_OPT_ARRAY 0x00000400U /* Want/got opt_... */ +#endif + +#ifndef STATMOUNT_OPT_SEC_ARRAY +#define STATMOUNT_OPT_SEC_ARRAY 0x00000800U /* Want/got opt_sec... */ +#endif + +#ifndef STATX_MNT_ID_UNIQUE +#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ +#endif + +#ifndef MOUNT_ATTR_RDONLY +#define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */ +#endif + +#ifndef MOUNT_ATTR_NOSUID +#define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */ +#endif + +#ifndef MOUNT_ATTR_NODEV +#define MOUNT_ATTR_NODEV 0x00000004 /* Disallow access to device special files */ +#endif + +#ifndef MOUNT_ATTR_NOEXEC +#define MOUNT_ATTR_NOEXEC 0x00000008 /* Disallow program execution */ +#endif + +#ifndef MOUNT_ATTR__ATIME +#define MOUNT_ATTR__ATIME 0x00000070 /* Setting on how atime should be updated */ +#endif + +#ifndef MOUNT_ATTR_RELATIME +#define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */ +#endif + +#ifndef MOUNT_ATTR_NOATIME +#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */ +#endif + +#ifndef MOUNT_ATTR_STRICTATIME +#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ +#endif + +#ifndef MOUNT_ATTR_NODIRATIME +#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ +#endif + +#ifndef MOUNT_ATTR_IDMAP +#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */ +#endif + +#ifndef MOUNT_ATTR_NOSYMFOLLOW +#define MOUNT_ATTR_NOSYMFOLLOW 0x00200000 /* Do not follow symlinks */ +#endif + +#ifndef MS_RDONLY +#define MS_RDONLY 1 /* Mount read-only */ +#endif + +#ifndef MS_SYNCHRONOUS +#define MS_SYNCHRONOUS 16 /* Writes are synced at once */ +#endif + +#ifndef MS_MANDLOCK +#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ +#endif + +#ifndef MS_DIRSYNC +#define MS_DIRSYNC 128 /* Directory modifications are synchronous */ +#endif + +#ifndef MS_UNBINDABLE +#define MS_UNBINDABLE (1<<17) /* change to unbindable */ +#endif + +#ifndef MS_PRIVATE +#define MS_PRIVATE (1<<18) /* change to private */ +#endif + +#ifndef MS_SLAVE +#define MS_SLAVE (1<<19) /* change to slave */ +#endif + +#ifndef MS_SHARED +#define MS_SHARED (1<<20) /* change to shared */ +#endif + +#ifndef MS_LAZYTIME +#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ +#endif + +#endif /* __SAMPLES_VFS_H */ diff --git a/samples/vfs/test-list-all-mounts.c b/samples/vfs/test-list-all-mounts.c new file mode 100644 index 000000000000..1a02ea4593e3 --- /dev/null +++ b/samples/vfs/test-list-all-mounts.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Christian Brauner + +#define _GNU_SOURCE +#include +#include +#include +#include +#include + +#include "../../tools/testing/selftests/pidfd/pidfd.h" +#include "samples-vfs.h" + +static int __statmount(__u64 mnt_id, __u64 mnt_ns_id, __u64 mask, + struct statmount *stmnt, size_t bufsize, + unsigned int flags) +{ + struct mnt_id_req req = { + .size = MNT_ID_REQ_SIZE_VER1, + .mnt_id = mnt_id, + .param = mask, + .mnt_ns_id = mnt_ns_id, + }; + + return syscall(__NR_statmount, &req, stmnt, bufsize, flags); +} + +static struct statmount *sys_statmount(__u64 mnt_id, __u64 mnt_ns_id, + __u64 mask, unsigned int flags) +{ + size_t bufsize = 1 << 15; + struct statmount *stmnt = NULL, *tmp = NULL; + int ret; + + for (;;) { + tmp = realloc(stmnt, bufsize); + if (!tmp) + goto out; + + stmnt = tmp; + ret = __statmount(mnt_id, mnt_ns_id, mask, stmnt, bufsize, flags); + if (!ret) + return stmnt; + + if (errno != EOVERFLOW) + goto out; + + bufsize <<= 1; + if (bufsize >= UINT_MAX / 2) + goto out; + } + +out: + free(stmnt); + return NULL; +} + +static ssize_t sys_listmount(__u64 mnt_id, __u64 last_mnt_id, __u64 mnt_ns_id, + __u64 list[], size_t num, unsigned int flags) +{ + struct mnt_id_req req = { + .size = MNT_ID_REQ_SIZE_VER1, + .mnt_id = mnt_id, + .param = last_mnt_id, + .mnt_ns_id = mnt_ns_id, + }; + + return syscall(__NR_listmount, &req, list, num, flags); +} + +int main(int argc, char *argv[]) +{ +#define LISTMNT_BUFFER 10 + __u64 list[LISTMNT_BUFFER], last_mnt_id = 0; + int ret, pidfd, fd_mntns; + struct mnt_ns_info info = {}; + + pidfd = sys_pidfd_open(getpid(), 0); + if (pidfd < 0) + die_errno("pidfd_open failed"); + + fd_mntns = ioctl(pidfd, PIDFD_GET_MNT_NAMESPACE, 0); + if (fd_mntns < 0) + die_errno("ioctl(PIDFD_GET_MNT_NAMESPACE) failed"); + + ret = ioctl(fd_mntns, NS_MNT_GET_INFO, &info); + if (ret < 0) + die_errno("ioctl(NS_GET_MNTNS_ID) failed"); + + printf("Listing %u mounts for mount namespace %" PRIu64 "\n", + info.nr_mounts, (uint64_t)info.mnt_ns_id); + for (;;) { + ssize_t nr_mounts; +next: + nr_mounts = sys_listmount(LSMT_ROOT, last_mnt_id, + info.mnt_ns_id, list, LISTMNT_BUFFER, + 0); + if (nr_mounts <= 0) { + int fd_mntns_next; + + printf("Finished listing %u mounts for mount namespace %" PRIu64 "\n\n", + info.nr_mounts, (uint64_t)info.mnt_ns_id); + fd_mntns_next = ioctl(fd_mntns, NS_MNT_GET_NEXT, &info); + if (fd_mntns_next < 0) { + if (errno == ENOENT) { + printf("Finished listing all mount namespaces\n"); + exit(0); + } + die_errno("ioctl(NS_MNT_GET_NEXT) failed"); + } + close(fd_mntns); + fd_mntns = fd_mntns_next; + last_mnt_id = 0; + printf("Listing %u mounts for mount namespace %" PRIu64 "\n", + info.nr_mounts, (uint64_t)info.mnt_ns_id); + goto next; + } + + for (size_t cur = 0; cur < nr_mounts; cur++) { + struct statmount *stmnt; + + last_mnt_id = list[cur]; + + stmnt = sys_statmount(last_mnt_id, info.mnt_ns_id, + STATMOUNT_SB_BASIC | + STATMOUNT_MNT_BASIC | + STATMOUNT_MNT_ROOT | + STATMOUNT_MNT_POINT | + STATMOUNT_MNT_NS_ID | + STATMOUNT_MNT_OPTS | + STATMOUNT_FS_TYPE, 0); + if (!stmnt) { + printf("Failed to statmount(%" PRIu64 ") in mount namespace(%" PRIu64 ")\n", + (uint64_t)last_mnt_id, (uint64_t)info.mnt_ns_id); + continue; + } + + printf("mnt_id:\t\t%" PRIu64 "\nmnt_parent_id:\t%" PRIu64 "\nfs_type:\t%s\nmnt_root:\t%s\nmnt_point:\t%s\nmnt_opts:\t%s\n\n", + (uint64_t)stmnt->mnt_id, + (uint64_t)stmnt->mnt_parent_id, + stmnt->str + stmnt->fs_type, + stmnt->str + stmnt->mnt_root, + stmnt->str + stmnt->mnt_point, + stmnt->str + stmnt->mnt_opts); + free(stmnt); + } + } + + exit(0); +} diff --git a/scripts/.gitignore b/scripts/.gitignore index 3dbb8bb2457b..c2ef68848da5 100644 --- a/scripts/.gitignore +++ b/scripts/.gitignore @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only /asn1_compiler +/gen_packed_field_checks /generate_rust_target /insert-sys-cert /kallsyms diff --git a/scripts/Makefile b/scripts/Makefile index 6bcda4b9d054..46f860529df5 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -47,13 +47,14 @@ HOSTCFLAGS_sorttable.o += -DMCOUNT_SORT_ENABLED endif # The following programs are only built on demand -hostprogs += unifdef +hostprogs += unifdef gen_packed_field_checks # The module linker script is preprocessed on demand targets += module.lds subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins -subdir-$(CONFIG_MODVERSIONS) += genksyms +subdir-$(CONFIG_GENKSYMS) += genksyms +subdir-$(CONFIG_GENDWARFKSYMS) += gendwarfksyms subdir-$(CONFIG_SECURITY_SELINUX) += selinux subdir-$(CONFIG_SECURITY_IPE) += ipe diff --git a/scripts/Makefile.build b/scripts/Makefile.build index c16e4cf54d77..993708d11874 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -107,13 +107,24 @@ cmd_cpp_i_c = $(CPP) $(c_flags) -o $@ $< $(obj)/%.i: $(obj)/%.c FORCE $(call if_changed_dep,cpp_i_c) +getexportsymbols = $(NM) $@ | sed -n 's/.* __export_symbol_\(.*\)/$(1)/p' + +gendwarfksyms = $(objtree)/scripts/gendwarfksyms/gendwarfksyms \ + $(if $(KBUILD_SYMTYPES), --symtypes $(@:.o=.symtypes)) \ + $(if $(KBUILD_GENDWARFKSYMS_STABLE), --stable) + genksyms = $(objtree)/scripts/genksyms/genksyms \ $(if $(KBUILD_SYMTYPES), -T $(@:.o=.symtypes)) \ $(if $(KBUILD_PRESERVE), -p) \ $(addprefix -r , $(wildcard $(@:.o=.symref))) # These mirror gensymtypes_S and co below, keep them in synch. +ifdef CONFIG_GENDWARFKSYMS +cmd_gensymtypes_c = $(if $(skip_gendwarfksyms),, \ + $(call getexportsymbols,\1) | $(gendwarfksyms) $@) +else cmd_gensymtypes_c = $(CPP) -D__GENKSYMS__ $(c_flags) $< | $(genksyms) +endif # CONFIG_GENDWARFKSYMS # LLVM assembly # Generate .ll files from .c @@ -183,7 +194,9 @@ endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT is-standard-object = $(if $(filter-out y%, $(OBJECT_FILES_NON_STANDARD_$(target-stem).o)$(OBJECT_FILES_NON_STANDARD)n),$(is-kernel-object)) +ifdef CONFIG_OBJTOOL $(obj)/%.o: private objtool-enabled = $(if $(is-standard-object),$(if $(delay-objtool),$(is-single-obj-m),y)) +endif ifneq ($(findstring 1, $(KBUILD_EXTRA_WARN)),) cmd_warn_shared_object = $(if $(word 2, $(modname-multi)),$(warning $(kbuild-file): $*.o is added to multiple modules: $(modname-multi))) @@ -286,14 +299,26 @@ $(obj)/%.rs: $(obj)/%.rs.S FORCE # This is convoluted. The .S file must first be preprocessed to run guards and # expand names, then the resulting exports must be constructed into plain # EXPORT_SYMBOL(symbol); to build our dummy C file, and that gets preprocessed -# to make the genksyms input. +# to make the genksyms input or compiled into an object for gendwarfksyms. # # These mirror gensymtypes_c and co above, keep them in synch. -cmd_gensymtypes_S = \ - { echo "\#include " ; \ - echo "\#include " ; \ - $(NM) $@ | sed -n 's/.* __export_symbol_\(.*\)/EXPORT_SYMBOL(\1);/p' ; } | \ - $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | $(genksyms) +getasmexports = \ + { echo "\#include " ; \ + echo "\#include " ; \ + echo "\#include " ; \ + $(call getexportsymbols,EXPORT_SYMBOL(\1);) ; } + +ifdef CONFIG_GENDWARFKSYMS +cmd_gensymtypes_S = \ + $(getasmexports) | \ + $(CC) $(c_flags) -c -o $(@:.o=.gendwarfksyms.o) -xc -; \ + $(call getexportsymbols,\1) | \ + $(gendwarfksyms) $(@:.o=.gendwarfksyms.o) +else +cmd_gensymtypes_S = \ + $(getasmexports) | \ + $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | $(genksyms) +endif # CONFIG_GENDWARFKSYMS quiet_cmd_cpp_s_S = CPP $(quiet_modtag) $@ cmd_cpp_s_S = $(CPP) $(a_flags) -o $@ $< diff --git a/scripts/Makefile.defconf b/scripts/Makefile.defconf index 226ea3df3b4b..a44307f08e9d 100644 --- a/scripts/Makefile.defconf +++ b/scripts/Makefile.defconf @@ -1,6 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 # Configuration heplers +cmd_merge_fragments = \ + $(srctree)/scripts/kconfig/merge_config.sh \ + $4 -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$2 \ + $(foreach config,$3,$(srctree)/arch/$(SRCARCH)/configs/$(config).config) + # Creates 'merged defconfigs' # --------------------------------------------------------------------------- # Usage: @@ -8,9 +13,7 @@ # # Input config fragments without '.config' suffix define merge_into_defconfig - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \ - -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \ - $(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config) + $(call cmd,merge_fragments,$1,$2) +$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig endef @@ -22,8 +25,6 @@ endef # # Input config fragments without '.config' suffix define merge_into_defconfig_override - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \ - -Q -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \ - $(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config) + $(call cmd,merge_fragments,$1,$2,-Q) +$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig endef diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 1d13cecc7cc7..eb719f6d8d53 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -77,6 +77,9 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init) # Warn if there is an enum types mismatch KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion) +# Explicitly clear padding bits during variable initialization +KBUILD_CFLAGS += $(call cc-option,-fzero-init-padding-bits=all) + KBUILD_CFLAGS += -Wextra KBUILD_CFLAGS += -Wunused diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 7395200538da..ad55ef201aac 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -287,6 +287,8 @@ delay-objtool := $(or $(CONFIG_LTO_CLANG),$(CONFIG_X86_KERNEL_IBT)) cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool-args) $@) cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd) +objtool-enabled := y + endif # CONFIG_OBJTOOL # Useful for describing the dependency of composite objects @@ -302,11 +304,11 @@ endef # =========================================================================== # These are shared by some Makefile.* files. -objtool-enabled := y - ifdef CONFIG_LTO_CLANG -# objtool cannot process LLVM IR. Make $(LD) covert LLVM IR to ELF here. -cmd_ld_single = $(if $(objtool-enabled), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@) +# Run $(LD) here to covert LLVM IR to ELF in the following cases: +# - when this object needs objtool processing, as objtool cannot process LLVM IR +# - when this is a single-object module, as modpost cannot process LLVM IR +cmd_ld_single = $(if $(objtool-enabled)$(is-single-obj-m), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@) endif quiet_cmd_cc_o_c = CC $(quiet_modtag) $@ @@ -374,6 +376,9 @@ quiet_cmd_ar = AR $@ quiet_cmd_objcopy = OBJCOPY $@ cmd_objcopy = $(OBJCOPY) $(OBJCOPYFLAGS) $(OBJCOPYFLAGS_$(@F)) $< $@ +quiet_cmd_strip_relocs = RSTRIP $@ +cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' $@ + # Gzip # --------------------------------------------------------------------------- diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index f97c9926ed31..1628198f3e83 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -105,7 +105,7 @@ else sig-key := $(CONFIG_MODULE_SIG_KEY) endif quiet_cmd_sign = SIGN $@ - cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" certs/signing_key.x509 $@ \ + cmd_sign = $(objtree)/scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" $(objtree)/certs/signing_key.x509 $@ \ $(if $(KBUILD_EXTMOD),|| true) ifeq ($(sign-only),) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index ab0e94ea6249..d7d45067d08b 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -43,6 +43,8 @@ MODPOST = $(objtree)/scripts/mod/modpost modpost-args = \ $(if $(CONFIG_MODULES),-M) \ $(if $(CONFIG_MODVERSIONS),-m) \ + $(if $(CONFIG_BASIC_MODVERSIONS),-b) \ + $(if $(CONFIG_EXTENDED_MODVERSIONS),-x) \ $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \ $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ $(if $(KBUILD_MODPOST_WARN),-w) \ diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 9eed3683ad76..7b28ad331742 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -834,16 +834,6 @@ foreach my $entry (@mode_permission_funcs) { $mode_perms_search = "(?:${mode_perms_search})"; our %deprecated_apis = ( - "synchronize_rcu_bh" => "synchronize_rcu", - "synchronize_rcu_bh_expedited" => "synchronize_rcu_expedited", - "call_rcu_bh" => "call_rcu", - "rcu_barrier_bh" => "rcu_barrier", - "synchronize_sched" => "synchronize_rcu", - "synchronize_sched_expedited" => "synchronize_rcu_expedited", - "call_rcu_sched" => "call_rcu", - "rcu_barrier_sched" => "rcu_barrier", - "get_state_synchronize_sched" => "get_state_synchronize_rcu", - "cond_synchronize_sched" => "cond_synchronize_rcu", "kmap" => "kmap_local_page", "kunmap" => "kunmap_local", "kmap_atomic" => "kmap_local_page", @@ -2875,7 +2865,7 @@ sub process { if ($realfile =~ m@^include/asm/@) { ERROR("MODIFIED_INCLUDE_ASM", - "do not modify files in include/asm, change architecture specific files in include/asm-\n" . "$here$rawline\n"); + "do not modify files in include/asm, change architecture specific files in arch//include/asm\n" . "$here$rawline\n"); } $found_file = 1; } @@ -3230,19 +3220,19 @@ sub process { my $tag_case = not ($tag eq "Fixes:"); my $tag_space = not ($line =~ /^fixes:? [0-9a-f]{5,40} ($balanced_parens)/i); - my $id_length = not ($orig_commit =~ /^[0-9a-f]{12}$/i); + my $id_length = not ($orig_commit =~ /^[0-9a-f]{12,40}$/i); my $id_case = not ($orig_commit !~ /[A-F]/); my $id = "0123456789ab"; my ($cid, $ctitle) = git_commit_info($orig_commit, $id, $title); - if ($ctitle ne $title || $tag_case || $tag_space || - $id_length || $id_case || !$title_has_quotes) { + if (defined($cid) && ($ctitle ne $title || $tag_case || $tag_space || $id_length || $id_case || !$title_has_quotes)) { + my $fixed = "Fixes: $cid (\"$ctitle\")"; if (WARN("BAD_FIXES_TAG", - "Please use correct Fixes: style 'Fixes: <12 chars of sha1> (\"\")' - ie: 'Fixes: $cid (\"$ctitle\")'\n" . $herecurr) && + "Please use correct Fixes: style 'Fixes: <12+ chars of sha1> (\"<title line>\")' - ie: '$fixed'\n" . $herecurr) && $fix) { - $fixed[$fixlinenr] = "Fixes: $cid (\"$ctitle\")"; + $fixed[$fixlinenr] = $fixed; } } } @@ -5513,9 +5503,9 @@ sub process { } } -# check for unnecessary parentheses around comparisons in if uses -# when !drivers/staging or command-line uses --strict - if (($realfile !~ m@^(?:drivers/staging/)@ || $check_orig) && +# check for unnecessary parentheses around comparisons +# except in drivers/staging + if (($realfile !~ m@^(?:drivers/staging/)@) && $perl_version_ok && defined($stat) && $stat =~ /(^.\s*if\s*($balanced_parens))/) { my $if_stat = $1; @@ -5843,6 +5833,8 @@ sub process { #CamelCase if ($var !~ /^$Constant$/ && $var =~ /[A-Z][a-z]|[a-z][A-Z]/ && +#Ignore C keywords + $var !~ /^_Generic$/ && #Ignore some autogenerated defines and enum values $var !~ /^(?:[A-Z]+_){1,5}[A-Z]{1,3}[a-z]/ && #Ignore Page<foo> variants diff --git a/scripts/coccinelle/misc/secs_to_jiffies.cocci b/scripts/coccinelle/misc/secs_to_jiffies.cocci new file mode 100644 index 000000000000..8bbb2884ea5d --- /dev/null +++ b/scripts/coccinelle/misc/secs_to_jiffies.cocci @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only +/// +/// Find usages of: +/// - msecs_to_jiffies(value*1000) +/// - msecs_to_jiffies(value*MSEC_PER_SEC) +/// +// Confidence: High +// Copyright: (C) 2024 Easwar Hariharan, Microsoft +// Keywords: secs, seconds, jiffies +// + +virtual patch + +@depends on patch@ constant C; @@ + +- msecs_to_jiffies(C * 1000) ++ secs_to_jiffies(C) + +@depends on patch@ constant C; @@ + +- msecs_to_jiffies(C * MSEC_PER_SEC) ++ secs_to_jiffies(C) diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index 46fa18b80fc1..17abc4e7a985 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -286,6 +286,18 @@ handle_line() { last=$(( $last - 1 )) fi + # Extract info after the symbol if present. E.g.: + # func_name+0x54/0x80 (P) + # ^^^ + # The regex assumes only uppercase letters will be used. To be + # extended if needed. + local info_str="" + if [[ ${words[$last]} =~ \([A-Z]*\) ]]; then + info_str=${words[$last]} + unset words[$last] + last=$(( $last - 1 )) + fi + if [[ ${words[$last]} =~ \[([^]]+)\] ]]; then module=${words[$last]} # some traces format is "(%pS)", which like "(foo+0x0/0x1 [bar])" @@ -313,9 +325,9 @@ handle_line() { # Add up the line number to the symbol if [[ -z ${module} ]] then - echo "${words[@]}" "$symbol" + echo "${words[@]}" "$symbol ${info_str}" else - echo "${words[@]}" "$symbol $module" + echo "${words[@]}" "$symbol $module ${info_str}" fi } diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py index 2f11c4f9c345..13eb8b3901b8 100644 --- a/scripts/gdb/linux/cpus.py +++ b/scripts/gdb/linux/cpus.py @@ -167,7 +167,7 @@ def get_current_task(cpu): var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task") return per_cpu(var_ptr, cpu).dereference() elif utils.is_target_arch("aarch64"): - current_task_addr = gdb.parse_and_eval("$SP_EL0") + current_task_addr = gdb.parse_and_eval("(unsigned long)$SP_EL0") if (current_task_addr >> 63) != 0: current_task = current_task_addr.cast(task_ptr_type) return current_task.dereference() diff --git a/scripts/gen_packed_field_checks.c b/scripts/gen_packed_field_checks.c new file mode 100644 index 000000000000..60042b7616ee --- /dev/null +++ b/scripts/gen_packed_field_checks.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024, Intel Corporation +#include <stdbool.h> +#include <stdio.h> + +#define MAX_PACKED_FIELD_SIZE 50 + +int main(int argc, char **argv) +{ + /* The first macro doesn't need a 'do {} while(0)' loop */ + printf("#define CHECK_PACKED_FIELDS_1(fields) \\\n"); + printf("\tCHECK_PACKED_FIELD(fields, 0)\n\n"); + + /* Remaining macros require a do/while loop, and are implemented + * recursively by calling the previous iteration's macro. + */ + for (int i = 2; i <= MAX_PACKED_FIELD_SIZE; i++) { + printf("#define CHECK_PACKED_FIELDS_%d(fields) do { \\\n", i); + printf("\tCHECK_PACKED_FIELDS_%d(fields); \\\n", i - 1); + printf("\tCHECK_PACKED_FIELD(fields, %d); \\\n", i - 1); + printf("} while (0)\n\n"); + } + + printf("#define CHECK_PACKED_FIELDS(fields) \\\n"); + + for (int i = 1; i <= MAX_PACKED_FIELD_SIZE; i++) + printf("\t__builtin_choose_expr(ARRAY_SIZE(fields) == %d, ({ CHECK_PACKED_FIELDS_%d(fields); }), \\\n", + i, i); + + printf("\t({ BUILD_BUG_ON_MSG(1, \"CHECK_PACKED_FIELDS() must be regenerated to support array sizes larger than %d.\"); }) \\\n", + MAX_PACKED_FIELD_SIZE); + + for (int i = 1; i <= MAX_PACKED_FIELD_SIZE; i++) + printf(")"); + + printf("\n"); +} diff --git a/scripts/gendwarfksyms/.gitignore b/scripts/gendwarfksyms/.gitignore new file mode 100644 index 000000000000..0927f8d3cd96 --- /dev/null +++ b/scripts/gendwarfksyms/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +/gendwarfksyms diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile new file mode 100644 index 000000000000..6334c7d3c4d5 --- /dev/null +++ b/scripts/gendwarfksyms/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +hostprogs-always-y += gendwarfksyms + +gendwarfksyms-objs += gendwarfksyms.o +gendwarfksyms-objs += cache.o +gendwarfksyms-objs += die.o +gendwarfksyms-objs += dwarf.o +gendwarfksyms-objs += kabi.o +gendwarfksyms-objs += symbols.o +gendwarfksyms-objs += types.o + +HOSTLDLIBS_gendwarfksyms := -ldw -lelf -lz diff --git a/scripts/gendwarfksyms/cache.c b/scripts/gendwarfksyms/cache.c new file mode 100644 index 000000000000..c9c19b86a686 --- /dev/null +++ b/scripts/gendwarfksyms/cache.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include "gendwarfksyms.h" + +struct cache_item { + unsigned long key; + int value; + struct hlist_node hash; +}; + +void cache_set(struct cache *cache, unsigned long key, int value) +{ + struct cache_item *ci; + + ci = xmalloc(sizeof(struct cache_item)); + ci->key = key; + ci->value = value; + hash_add(cache->cache, &ci->hash, hash_32(key)); +} + +int cache_get(struct cache *cache, unsigned long key) +{ + struct cache_item *ci; + + hash_for_each_possible(cache->cache, ci, hash, hash_32(key)) { + if (ci->key == key) + return ci->value; + } + + return -1; +} + +void cache_init(struct cache *cache) +{ + hash_init(cache->cache); +} + +void cache_free(struct cache *cache) +{ + struct hlist_node *tmp; + struct cache_item *ci; + + hash_for_each_safe(cache->cache, ci, tmp, hash) { + free(ci); + } + + hash_init(cache->cache); +} diff --git a/scripts/gendwarfksyms/die.c b/scripts/gendwarfksyms/die.c new file mode 100644 index 000000000000..66bd4c9bc952 --- /dev/null +++ b/scripts/gendwarfksyms/die.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include <string.h> +#include "gendwarfksyms.h" + +#define DIE_HASH_BITS 15 + +/* {die->addr, state} -> struct die * */ +static HASHTABLE_DEFINE(die_map, 1 << DIE_HASH_BITS); + +static unsigned int map_hits; +static unsigned int map_misses; + +static inline unsigned int die_hash(uintptr_t addr, enum die_state state) +{ + return hash_32(addr_hash(addr) ^ (unsigned int)state); +} + +static void init_die(struct die *cd) +{ + cd->state = DIE_INCOMPLETE; + cd->mapped = false; + cd->fqn = NULL; + cd->tag = -1; + cd->addr = 0; + INIT_LIST_HEAD(&cd->fragments); +} + +static struct die *create_die(Dwarf_Die *die, enum die_state state) +{ + struct die *cd; + + cd = xmalloc(sizeof(struct die)); + init_die(cd); + cd->addr = (uintptr_t)die->addr; + + hash_add(die_map, &cd->hash, die_hash(cd->addr, state)); + return cd; +} + +int __die_map_get(uintptr_t addr, enum die_state state, struct die **res) +{ + struct die *cd; + + hash_for_each_possible(die_map, cd, hash, die_hash(addr, state)) { + if (cd->addr == addr && cd->state == state) { + *res = cd; + return 0; + } + } + + return -1; +} + +struct die *die_map_get(Dwarf_Die *die, enum die_state state) +{ + struct die *cd; + + if (__die_map_get((uintptr_t)die->addr, state, &cd) == 0) { + map_hits++; + return cd; + } + + map_misses++; + return create_die(die, state); +} + +static void reset_die(struct die *cd) +{ + struct die_fragment *tmp; + struct die_fragment *df; + + list_for_each_entry_safe(df, tmp, &cd->fragments, list) { + if (df->type == FRAGMENT_STRING) + free(df->data.str); + free(df); + } + + if (cd->fqn && *cd->fqn) + free(cd->fqn); + init_die(cd); +} + +void die_map_for_each(die_map_callback_t func, void *arg) +{ + struct hlist_node *tmp; + struct die *cd; + + hash_for_each_safe(die_map, cd, tmp, hash) { + func(cd, arg); + } +} + +void die_map_free(void) +{ + struct hlist_node *tmp; + unsigned int stats[DIE_LAST + 1]; + struct die *cd; + int i; + + memset(stats, 0, sizeof(stats)); + + hash_for_each_safe(die_map, cd, tmp, hash) { + stats[cd->state]++; + reset_die(cd); + free(cd); + } + hash_init(die_map); + + if (map_hits + map_misses > 0) + debug("hits %u, misses %u (hit rate %.02f%%)", map_hits, + map_misses, + (100.0f * map_hits) / (map_hits + map_misses)); + + for (i = 0; i <= DIE_LAST; i++) + debug("%s: %u entries", die_state_name(i), stats[i]); +} + +static struct die_fragment *append_item(struct die *cd) +{ + struct die_fragment *df; + + df = xmalloc(sizeof(struct die_fragment)); + df->type = FRAGMENT_EMPTY; + list_add_tail(&df->list, &cd->fragments); + return df; +} + +void die_map_add_string(struct die *cd, const char *str) +{ + struct die_fragment *df; + + if (!cd) + return; + + df = append_item(cd); + df->data.str = xstrdup(str); + df->type = FRAGMENT_STRING; +} + +void die_map_add_linebreak(struct die *cd, int linebreak) +{ + struct die_fragment *df; + + if (!cd) + return; + + df = append_item(cd); + df->data.linebreak = linebreak; + df->type = FRAGMENT_LINEBREAK; +} + +void die_map_add_die(struct die *cd, struct die *child) +{ + struct die_fragment *df; + + if (!cd) + return; + + df = append_item(cd); + df->data.addr = child->addr; + df->type = FRAGMENT_DIE; +} diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c new file mode 100644 index 000000000000..534d9aa7c114 --- /dev/null +++ b/scripts/gendwarfksyms/dwarf.c @@ -0,0 +1,1159 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include <assert.h> +#include <inttypes.h> +#include <stdarg.h> +#include "gendwarfksyms.h" + +/* See get_union_kabi_status */ +#define KABI_PREFIX "__kabi_" +#define KABI_PREFIX_LEN (sizeof(KABI_PREFIX) - 1) +#define KABI_RESERVED_PREFIX "reserved" +#define KABI_RESERVED_PREFIX_LEN (sizeof(KABI_RESERVED_PREFIX) - 1) +#define KABI_RENAMED_PREFIX "renamed" +#define KABI_RENAMED_PREFIX_LEN (sizeof(KABI_RENAMED_PREFIX) - 1) +#define KABI_IGNORED_PREFIX "ignored" +#define KABI_IGNORED_PREFIX_LEN (sizeof(KABI_IGNORED_PREFIX) - 1) + +static inline bool is_kabi_prefix(const char *name) +{ + return name && !strncmp(name, KABI_PREFIX, KABI_PREFIX_LEN); +} + +enum kabi_status { + /* >0 to stop DIE processing */ + KABI_NORMAL = 1, + KABI_RESERVED, + KABI_IGNORED, +}; + +static bool do_linebreak; +static int indentation_level; + +/* Line breaks and indentation for pretty-printing */ +static void process_linebreak(struct die *cache, int n) +{ + indentation_level += n; + do_linebreak = true; + die_map_add_linebreak(cache, n); +} + +#define DEFINE_GET_ATTR(attr, type) \ + static bool get_##attr##_attr(Dwarf_Die *die, unsigned int id, \ + type *value) \ + { \ + Dwarf_Attribute da; \ + return dwarf_attr(die, id, &da) && \ + !dwarf_form##attr(&da, value); \ + } + +DEFINE_GET_ATTR(flag, bool) +DEFINE_GET_ATTR(udata, Dwarf_Word) + +static bool get_ref_die_attr(Dwarf_Die *die, unsigned int id, Dwarf_Die *value) +{ + Dwarf_Attribute da; + + /* dwarf_formref_die returns a pointer instead of an error value. */ + return dwarf_attr(die, id, &da) && dwarf_formref_die(&da, value); +} + +#define DEFINE_GET_STRING_ATTR(attr) \ + static const char *get_##attr##_attr(Dwarf_Die *die) \ + { \ + Dwarf_Attribute da; \ + if (dwarf_attr(die, DW_AT_##attr, &da)) \ + return dwarf_formstring(&da); \ + return NULL; \ + } + +DEFINE_GET_STRING_ATTR(name) +DEFINE_GET_STRING_ATTR(linkage_name) + +static const char *get_symbol_name(Dwarf_Die *die) +{ + const char *name; + + /* rustc uses DW_AT_linkage_name for exported symbols */ + name = get_linkage_name_attr(die); + if (!name) + name = get_name_attr(die); + + return name; +} + +static bool match_export_symbol(struct state *state, Dwarf_Die *die) +{ + Dwarf_Die *source = die; + Dwarf_Die origin; + + /* If the DIE has an abstract origin, use it for type information. */ + if (get_ref_die_attr(die, DW_AT_abstract_origin, &origin)) + source = &origin; + + state->sym = symbol_get(get_symbol_name(die)); + + /* Look up using the origin name if there are no matches. */ + if (!state->sym && source != die) + state->sym = symbol_get(get_symbol_name(source)); + + state->die = *source; + return !!state->sym; +} + +/* DW_AT_decl_file -> struct srcfile */ +static struct cache srcfile_cache; + +static bool is_definition_private(Dwarf_Die *die) +{ + Dwarf_Word filenum; + Dwarf_Files *files; + Dwarf_Die cudie; + const char *s; + int res; + + /* + * Definitions in .c files cannot change the public ABI, + * so consider them private. + */ + if (!get_udata_attr(die, DW_AT_decl_file, &filenum)) + return false; + + res = cache_get(&srcfile_cache, filenum); + if (res >= 0) + return !!res; + + if (!dwarf_cu_die(die->cu, &cudie, NULL, NULL, NULL, NULL, NULL, NULL)) + error("dwarf_cu_die failed: '%s'", dwarf_errmsg(-1)); + + if (dwarf_getsrcfiles(&cudie, &files, NULL)) + error("dwarf_getsrcfiles failed: '%s'", dwarf_errmsg(-1)); + + s = dwarf_filesrc(files, filenum, NULL, NULL); + if (!s) + error("dwarf_filesrc failed: '%s'", dwarf_errmsg(-1)); + + s = strrchr(s, '.'); + res = s && !strcmp(s, ".c"); + cache_set(&srcfile_cache, filenum, res); + + return !!res; +} + +static bool is_kabi_definition(struct die *cache, Dwarf_Die *die) +{ + bool value; + + if (get_flag_attr(die, DW_AT_declaration, &value) && value) + return false; + + if (kabi_is_declonly(cache->fqn)) + return false; + + return !is_definition_private(die); +} + +/* + * Type string processing + */ +static void process(struct die *cache, const char *s) +{ + s = s ?: "<null>"; + + if (dump_dies && do_linebreak) { + fputs("\n", stderr); + for (int i = 0; i < indentation_level; i++) + fputs(" ", stderr); + do_linebreak = false; + } + if (dump_dies) + fputs(s, stderr); + + if (cache) + die_debug_r("cache %p string '%s'", cache, s); + die_map_add_string(cache, s); +} + +#define MAX_FMT_BUFFER_SIZE 128 + +static void process_fmt(struct die *cache, const char *fmt, ...) +{ + char buf[MAX_FMT_BUFFER_SIZE]; + va_list args; + + va_start(args, fmt); + + if (checkp(vsnprintf(buf, sizeof(buf), fmt, args)) >= sizeof(buf)) + error("vsnprintf overflow: increase MAX_FMT_BUFFER_SIZE"); + + process(cache, buf); + va_end(args); +} + +#define MAX_FQN_SIZE 64 + +/* Get a fully qualified name from DWARF scopes */ +static char *get_fqn(Dwarf_Die *die) +{ + const char *list[MAX_FQN_SIZE]; + Dwarf_Die *scopes = NULL; + bool has_name = false; + char *fqn = NULL; + char *p; + int count = 0; + int len = 0; + int res; + int i; + + res = checkp(dwarf_getscopes_die(die, &scopes)); + if (!res) { + list[count] = get_name_attr(die); + + if (!list[count]) + return NULL; + + len += strlen(list[count]); + count++; + + goto done; + } + + for (i = res - 1; i >= 0 && count < MAX_FQN_SIZE; i--) { + if (dwarf_tag(&scopes[i]) == DW_TAG_compile_unit) + continue; + + list[count] = get_name_attr(&scopes[i]); + + if (list[count]) { + has_name = true; + } else { + list[count] = "<anonymous>"; + has_name = false; + } + + len += strlen(list[count]); + count++; + + if (i > 0) { + list[count++] = "::"; + len += 2; + } + } + + free(scopes); + + if (count == MAX_FQN_SIZE) + warn("increase MAX_FQN_SIZE: reached the maximum"); + + /* Consider the DIE unnamed if the last scope doesn't have a name */ + if (!has_name) + return NULL; +done: + fqn = xmalloc(len + 1); + *fqn = '\0'; + + p = fqn; + for (i = 0; i < count; i++) + p = stpcpy(p, list[i]); + + return fqn; +} + +static void update_fqn(struct die *cache, Dwarf_Die *die) +{ + if (!cache->fqn) + cache->fqn = get_fqn(die) ?: ""; +} + +static void process_fqn(struct die *cache, Dwarf_Die *die) +{ + update_fqn(cache, die); + if (*cache->fqn) + process(cache, " "); + process(cache, cache->fqn); +} + +#define DEFINE_PROCESS_UDATA_ATTRIBUTE(attribute) \ + static void process_##attribute##_attr(struct die *cache, \ + Dwarf_Die *die) \ + { \ + Dwarf_Word value; \ + if (get_udata_attr(die, DW_AT_##attribute, &value)) \ + process_fmt(cache, " " #attribute "(%" PRIu64 ")", \ + value); \ + } + +DEFINE_PROCESS_UDATA_ATTRIBUTE(accessibility) +DEFINE_PROCESS_UDATA_ATTRIBUTE(alignment) +DEFINE_PROCESS_UDATA_ATTRIBUTE(bit_size) +DEFINE_PROCESS_UDATA_ATTRIBUTE(byte_size) +DEFINE_PROCESS_UDATA_ATTRIBUTE(encoding) +DEFINE_PROCESS_UDATA_ATTRIBUTE(data_bit_offset) +DEFINE_PROCESS_UDATA_ATTRIBUTE(data_member_location) +DEFINE_PROCESS_UDATA_ATTRIBUTE(discr_value) + +/* Match functions -- die_match_callback_t */ +#define DEFINE_MATCH(type) \ + static bool match_##type##_type(Dwarf_Die *die) \ + { \ + return dwarf_tag(die) == DW_TAG_##type##_type; \ + } + +DEFINE_MATCH(enumerator) +DEFINE_MATCH(formal_parameter) +DEFINE_MATCH(member) +DEFINE_MATCH(subrange) + +bool match_all(Dwarf_Die *die) +{ + return true; +} + +int process_die_container(struct state *state, struct die *cache, + Dwarf_Die *die, die_callback_t func, + die_match_callback_t match) +{ + Dwarf_Die current; + int res; + + /* Track the first item in lists. */ + if (state) + state->first_list_item = true; + + res = checkp(dwarf_child(die, ¤t)); + while (!res) { + if (match(¤t)) { + /* <0 = error, 0 = continue, >0 = stop */ + res = checkp(func(state, cache, ¤t)); + if (res) + goto out; + } + + res = checkp(dwarf_siblingof(¤t, ¤t)); + } + + res = 0; +out: + if (state) + state->first_list_item = false; + + return res; +} + +static int process_type(struct state *state, struct die *parent, + Dwarf_Die *die); + +static void process_type_attr(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Die type; + + if (get_ref_die_attr(die, DW_AT_type, &type)) { + check(process_type(state, cache, &type)); + return; + } + + /* Compilers can omit DW_AT_type -- print out 'void' to clarify */ + process(cache, "base_type void"); +} + +static void process_list_comma(struct state *state, struct die *cache) +{ + if (state->first_list_item) { + state->first_list_item = false; + } else { + process(cache, " ,"); + process_linebreak(cache, 0); + } +} + +/* Comma-separated with DW_AT_type */ +static void __process_list_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type) +{ + const char *name = get_name_attr(die); + + if (stable) { + if (is_kabi_prefix(name)) + name = NULL; + state->kabi.orig_name = NULL; + } + + process_list_comma(state, cache); + process(cache, type); + process_type_attr(state, cache, die); + + if (stable && state->kabi.orig_name) + name = state->kabi.orig_name; + if (name) { + process(cache, " "); + process(cache, name); + } + + process_accessibility_attr(cache, die); + process_bit_size_attr(cache, die); + process_data_bit_offset_attr(cache, die); + process_data_member_location_attr(cache, die); +} + +#define DEFINE_PROCESS_LIST_TYPE(type) \ + static void process_##type##_type(struct state *state, \ + struct die *cache, Dwarf_Die *die) \ + { \ + __process_list_type(state, cache, die, #type " "); \ + } + +DEFINE_PROCESS_LIST_TYPE(formal_parameter) +DEFINE_PROCESS_LIST_TYPE(member) + +/* Container types with DW_AT_type */ +static void __process_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type) +{ + process(cache, type); + process_fqn(cache, die); + process(cache, " {"); + process_linebreak(cache, 1); + process_type_attr(state, cache, die); + process_linebreak(cache, -1); + process(cache, "}"); + process_byte_size_attr(cache, die); + process_alignment_attr(cache, die); +} + +#define DEFINE_PROCESS_TYPE(type) \ + static void process_##type##_type(struct state *state, \ + struct die *cache, Dwarf_Die *die) \ + { \ + __process_type(state, cache, die, #type "_type"); \ + } + +DEFINE_PROCESS_TYPE(atomic) +DEFINE_PROCESS_TYPE(const) +DEFINE_PROCESS_TYPE(immutable) +DEFINE_PROCESS_TYPE(packed) +DEFINE_PROCESS_TYPE(pointer) +DEFINE_PROCESS_TYPE(reference) +DEFINE_PROCESS_TYPE(restrict) +DEFINE_PROCESS_TYPE(rvalue_reference) +DEFINE_PROCESS_TYPE(shared) +DEFINE_PROCESS_TYPE(template_type_parameter) +DEFINE_PROCESS_TYPE(volatile) +DEFINE_PROCESS_TYPE(typedef) + +static void process_subrange_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Word count = 0; + + if (get_udata_attr(die, DW_AT_count, &count)) + process_fmt(cache, "[%" PRIu64 "]", count); + else if (get_udata_attr(die, DW_AT_upper_bound, &count)) + process_fmt(cache, "[%" PRIu64 "]", count + 1); + else + process(cache, "[]"); +} + +static void process_array_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process(cache, "array_type"); + /* Array size */ + check(process_die_container(state, cache, die, process_type, + match_subrange_type)); + process(cache, " {"); + process_linebreak(cache, 1); + process_type_attr(state, cache, die); + process_linebreak(cache, -1); + process(cache, "}"); +} + +static void __process_subroutine_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type) +{ + process(cache, type); + process(cache, " ("); + process_linebreak(cache, 1); + /* Parameters */ + check(process_die_container(state, cache, die, process_type, + match_formal_parameter_type)); + process_linebreak(cache, -1); + process(cache, ")"); + process_linebreak(cache, 0); + /* Return type */ + process(cache, "-> "); + process_type_attr(state, cache, die); +} + +static void process_subroutine_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + __process_subroutine_type(state, cache, die, "subroutine_type"); +} + +static void process_variant_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process_list_comma(state, cache); + process(cache, "variant {"); + process_linebreak(cache, 1); + check(process_die_container(state, cache, die, process_type, + match_member_type)); + process_linebreak(cache, -1); + process(cache, "}"); + process_discr_value_attr(cache, die); +} + +static void process_variant_part_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process_list_comma(state, cache); + process(cache, "variant_part {"); + process_linebreak(cache, 1); + check(process_die_container(state, cache, die, process_type, + match_all)); + process_linebreak(cache, -1); + process(cache, "}"); +} + +static int get_kabi_status(Dwarf_Die *die, const char **suffix) +{ + const char *name = get_name_attr(die); + + if (suffix) + *suffix = NULL; + + if (is_kabi_prefix(name)) { + name += KABI_PREFIX_LEN; + + if (!strncmp(name, KABI_RESERVED_PREFIX, + KABI_RESERVED_PREFIX_LEN)) + return KABI_RESERVED; + if (!strncmp(name, KABI_IGNORED_PREFIX, + KABI_IGNORED_PREFIX_LEN)) + return KABI_IGNORED; + + if (!strncmp(name, KABI_RENAMED_PREFIX, + KABI_RENAMED_PREFIX_LEN)) { + if (suffix) { + name += KABI_RENAMED_PREFIX_LEN; + *suffix = name; + } + return KABI_RESERVED; + } + } + + return KABI_NORMAL; +} + +static int check_struct_member_kabi_status(struct state *state, + struct die *__unused, Dwarf_Die *die) +{ + int res; + + assert(dwarf_tag(die) == DW_TAG_member_type); + + /* + * If the union member is a struct, expect the __kabi field to + * be the first member of the structure, i.e..: + * + * union { + * type new_member; + * struct { + * type __kabi_field; + * } + * }; + */ + res = get_kabi_status(die, &state->kabi.orig_name); + + if (res == KABI_RESERVED && + !get_ref_die_attr(die, DW_AT_type, &state->kabi.placeholder)) + error("structure member missing a type?"); + + return res; +} + +static int check_union_member_kabi_status(struct state *state, + struct die *__unused, Dwarf_Die *die) +{ + Dwarf_Die type; + int res; + + assert(dwarf_tag(die) == DW_TAG_member_type); + + if (!get_ref_die_attr(die, DW_AT_type, &type)) + error("union member missing a type?"); + + /* + * We expect a union with two members. Check if either of them + * has a __kabi name prefix, i.e.: + * + * union { + * ... + * type memberN; // <- type, N = {0,1} + * ... + * }; + * + * The member can also be a structure type, in which case we'll + * check the first structure member. + * + * In any case, stop processing after we've seen two members. + */ + res = get_kabi_status(die, &state->kabi.orig_name); + + if (res == KABI_RESERVED) + state->kabi.placeholder = type; + if (res != KABI_NORMAL) + return res; + + if (dwarf_tag(&type) == DW_TAG_structure_type) + res = checkp(process_die_container( + state, NULL, &type, check_struct_member_kabi_status, + match_member_type)); + + if (res <= KABI_NORMAL && ++state->kabi.members < 2) + return 0; /* Continue */ + + return res; +} + +static int get_union_kabi_status(Dwarf_Die *die, Dwarf_Die *placeholder, + const char **orig_name) +{ + struct state state; + int res; + + if (!stable) + return KABI_NORMAL; + + /* + * To maintain a stable kABI, distributions may choose to reserve + * space in structs for later use by adding placeholder members, + * for example: + * + * struct s { + * u32 a; + * // an 8-byte placeholder for future use + * u64 __kabi_reserved_0; + * }; + * + * When the reserved member is taken into use, the type change + * would normally cause the symbol version to change as well, but + * if the replacement uses the following convention, gendwarfksyms + * continues to use the placeholder type for versioning instead, + * thus maintaining the same symbol version: + * + * struct s { + * u32 a; + * union { + * // placeholder replaced with a new member `b` + * struct t b; + * struct { + * // the placeholder type that is still + * // used for versioning + * u64 __kabi_reserved_0; + * }; + * }; + * }; + * + * I.e., as long as the replaced member is in a union, and the + * placeholder has a __kabi_reserved name prefix, we'll continue + * to use the placeholder type (here u64) for version calculation + * instead of the union type. + * + * It's also possible to ignore new members from versioning if + * they've been added to alignment holes, for example, by + * including them in a union with another member that uses the + * __kabi_ignored name prefix: + * + * struct s { + * u32 a; + * // an alignment hole is used to add `n` + * union { + * u32 n; + * // hide the entire union member from versioning + * u8 __kabi_ignored_0; + * }; + * u64 b; + * }; + * + * Note that the user of this feature is responsible for ensuring + * that the structure actually remains ABI compatible. + */ + memset(&state.kabi, 0, sizeof(struct kabi_state)); + + res = checkp(process_die_container(&state, NULL, die, + check_union_member_kabi_status, + match_member_type)); + + if (res == KABI_RESERVED) { + if (placeholder) + *placeholder = state.kabi.placeholder; + if (orig_name) + *orig_name = state.kabi.orig_name; + } + + return res; +} + +static bool is_kabi_ignored(Dwarf_Die *die) +{ + Dwarf_Die type; + + if (!stable) + return false; + + if (!get_ref_die_attr(die, DW_AT_type, &type)) + error("member missing a type?"); + + return dwarf_tag(&type) == DW_TAG_union_type && + checkp(get_union_kabi_status(&type, NULL, NULL)) == KABI_IGNORED; +} + +static int ___process_structure_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + switch (dwarf_tag(die)) { + case DW_TAG_member: + if (is_kabi_ignored(die)) + return 0; + return check(process_type(state, cache, die)); + case DW_TAG_variant_part: + return check(process_type(state, cache, die)); + case DW_TAG_class_type: + case DW_TAG_enumeration_type: + case DW_TAG_structure_type: + case DW_TAG_template_type_parameter: + case DW_TAG_union_type: + case DW_TAG_subprogram: + /* Skip non-member types, including member functions */ + return 0; + default: + error("unexpected structure_type child: %x", dwarf_tag(die)); + } +} + +static void __process_structure_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type, + die_callback_t process_func, + die_match_callback_t match_func) +{ + bool expand; + + process(cache, type); + process_fqn(cache, die); + process(cache, " {"); + process_linebreak(cache, 1); + + expand = state->expand.expand && is_kabi_definition(cache, die); + + if (expand) { + state->expand.current_fqn = cache->fqn; + check(process_die_container(state, cache, die, process_func, + match_func)); + } + + process_linebreak(cache, -1); + process(cache, "}"); + + if (expand) { + process_byte_size_attr(cache, die); + process_alignment_attr(cache, die); + } +} + +#define DEFINE_PROCESS_STRUCTURE_TYPE(structure) \ + static void process_##structure##_type( \ + struct state *state, struct die *cache, Dwarf_Die *die) \ + { \ + __process_structure_type(state, cache, die, \ + #structure "_type", \ + ___process_structure_type, \ + match_all); \ + } + +DEFINE_PROCESS_STRUCTURE_TYPE(class) +DEFINE_PROCESS_STRUCTURE_TYPE(structure) + +static void process_union_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Die placeholder; + + int res = checkp(get_union_kabi_status(die, &placeholder, + &state->kabi.orig_name)); + + if (res == KABI_RESERVED) + check(process_type(state, cache, &placeholder)); + if (res > KABI_NORMAL) + return; + + __process_structure_type(state, cache, die, "union_type", + ___process_structure_type, match_all); +} + +static void process_enumerator_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + bool overridden = false; + Dwarf_Word value; + + if (stable) { + /* Get the fqn before we process anything */ + update_fqn(cache, die); + + if (kabi_is_enumerator_ignored(state->expand.current_fqn, + cache->fqn)) + return; + + overridden = kabi_get_enumerator_value( + state->expand.current_fqn, cache->fqn, &value); + } + + process_list_comma(state, cache); + process(cache, "enumerator"); + process_fqn(cache, die); + + if (overridden || get_udata_attr(die, DW_AT_const_value, &value)) { + process(cache, " = "); + process_fmt(cache, "%" PRIu64, value); + } +} + +static void process_enumeration_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + __process_structure_type(state, cache, die, "enumeration_type", + process_type, match_enumerator_type); +} + +static void process_base_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process(cache, "base_type"); + process_fqn(cache, die); + process_byte_size_attr(cache, die); + process_encoding_attr(cache, die); + process_alignment_attr(cache, die); +} + +static void process_unspecified_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + /* + * These can be emitted for stand-alone assembly code, which means we + * might run into them in vmlinux.o. + */ + process(cache, "unspecified_type"); +} + +static void process_cached(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + struct die_fragment *df; + Dwarf_Die child; + + list_for_each_entry(df, &cache->fragments, list) { + switch (df->type) { + case FRAGMENT_STRING: + die_debug_b("cache %p STRING '%s'", cache, + df->data.str); + process(NULL, df->data.str); + break; + case FRAGMENT_LINEBREAK: + process_linebreak(NULL, df->data.linebreak); + break; + case FRAGMENT_DIE: + if (!dwarf_die_addr_die(dwarf_cu_getdwarf(die->cu), + (void *)df->data.addr, &child)) + error("dwarf_die_addr_die failed"); + die_debug_b("cache %p DIE addr %" PRIxPTR " tag %x", + cache, df->data.addr, dwarf_tag(&child)); + check(process_type(state, NULL, &child)); + break; + default: + error("empty die_fragment"); + } + } +} + +static void state_init(struct state *state) +{ + state->expand.expand = true; + state->expand.current_fqn = NULL; + cache_init(&state->expansion_cache); +} + +static void expansion_state_restore(struct expansion_state *state, + struct expansion_state *saved) +{ + state->expand = saved->expand; + state->current_fqn = saved->current_fqn; +} + +static void expansion_state_save(struct expansion_state *state, + struct expansion_state *saved) +{ + expansion_state_restore(saved, state); +} + +static bool is_expanded_type(int tag) +{ + return tag == DW_TAG_class_type || tag == DW_TAG_structure_type || + tag == DW_TAG_union_type || tag == DW_TAG_enumeration_type; +} + +#define PROCESS_TYPE(type) \ + case DW_TAG_##type##_type: \ + process_##type##_type(state, cache, die); \ + break; + +static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) +{ + enum die_state want_state = DIE_COMPLETE; + struct die *cache; + struct expansion_state saved; + int tag = dwarf_tag(die); + + expansion_state_save(&state->expand, &saved); + + /* + * Structures and enumeration types are expanded only once per + * exported symbol. This is sufficient for detecting ABI changes + * within the structure. + */ + if (is_expanded_type(tag)) { + if (cache_was_expanded(&state->expansion_cache, die->addr)) + state->expand.expand = false; + + if (state->expand.expand) + cache_mark_expanded(&state->expansion_cache, die->addr); + else + want_state = DIE_UNEXPANDED; + } + + /* + * If we have want_state already cached, use it instead of walking + * through DWARF. + */ + cache = die_map_get(die, want_state); + + if (cache->state == want_state) { + die_debug_g("cached addr %p tag %x -- %s", die->addr, tag, + die_state_name(cache->state)); + + process_cached(state, cache, die); + die_map_add_die(parent, cache); + + expansion_state_restore(&state->expand, &saved); + return 0; + } + + die_debug_g("addr %p tag %x -- %s -> %s", die->addr, tag, + die_state_name(cache->state), die_state_name(want_state)); + + switch (tag) { + /* Type modifiers */ + PROCESS_TYPE(atomic) + PROCESS_TYPE(const) + PROCESS_TYPE(immutable) + PROCESS_TYPE(packed) + PROCESS_TYPE(pointer) + PROCESS_TYPE(reference) + PROCESS_TYPE(restrict) + PROCESS_TYPE(rvalue_reference) + PROCESS_TYPE(shared) + PROCESS_TYPE(volatile) + /* Container types */ + PROCESS_TYPE(class) + PROCESS_TYPE(structure) + PROCESS_TYPE(union) + PROCESS_TYPE(enumeration) + /* Subtypes */ + PROCESS_TYPE(enumerator) + PROCESS_TYPE(formal_parameter) + PROCESS_TYPE(member) + PROCESS_TYPE(subrange) + PROCESS_TYPE(template_type_parameter) + PROCESS_TYPE(variant) + PROCESS_TYPE(variant_part) + /* Other types */ + PROCESS_TYPE(array) + PROCESS_TYPE(base) + PROCESS_TYPE(subroutine) + PROCESS_TYPE(typedef) + PROCESS_TYPE(unspecified) + default: + error("unexpected type: %x", tag); + } + + die_debug_r("parent %p cache %p die addr %p tag %x", parent, cache, + die->addr, tag); + + /* Update cache state and append to the parent (if any) */ + cache->tag = tag; + cache->state = want_state; + die_map_add_die(parent, cache); + + expansion_state_restore(&state->expand, &saved); + return 0; +} + +/* + * Exported symbol processing + */ +static struct die *get_symbol_cache(struct state *state, Dwarf_Die *die) +{ + struct die *cache; + + cache = die_map_get(die, DIE_SYMBOL); + + if (cache->state != DIE_INCOMPLETE) + return NULL; /* We already processed a symbol for this DIE */ + + cache->tag = dwarf_tag(die); + return cache; +} + +static void process_symbol(struct state *state, Dwarf_Die *die, + die_callback_t process_func) +{ + struct die *cache; + + symbol_set_die(state->sym, die); + + cache = get_symbol_cache(state, die); + if (!cache) + return; + + debug("%s", state->sym->name); + check(process_func(state, cache, die)); + cache->state = DIE_SYMBOL; + if (dump_dies) + fputs("\n", stderr); +} + +static int __process_subprogram(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + __process_subroutine_type(state, cache, die, "subprogram"); + return 0; +} + +static void process_subprogram(struct state *state, Dwarf_Die *die) +{ + process_symbol(state, die, __process_subprogram); +} + +static int __process_variable(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process(cache, "variable "); + process_type_attr(state, cache, die); + return 0; +} + +static void process_variable(struct state *state, Dwarf_Die *die) +{ + process_symbol(state, die, __process_variable); +} + +static void save_symbol_ptr(struct state *state) +{ + Dwarf_Die ptr_type; + Dwarf_Die type; + + if (!get_ref_die_attr(&state->die, DW_AT_type, &ptr_type) || + dwarf_tag(&ptr_type) != DW_TAG_pointer_type) + error("%s must be a pointer type!", + get_symbol_name(&state->die)); + + if (!get_ref_die_attr(&ptr_type, DW_AT_type, &type)) + error("%s pointer missing a type attribute?", + get_symbol_name(&state->die)); + + /* + * Save the symbol pointer DIE in case the actual symbol is + * missing from the DWARF. Clang, for example, intentionally + * omits external symbols from the debugging information. + */ + if (dwarf_tag(&type) == DW_TAG_subroutine_type) + symbol_set_ptr(state->sym, &type); + else + symbol_set_ptr(state->sym, &ptr_type); +} + +static int process_exported_symbols(struct state *unused, struct die *cache, + Dwarf_Die *die) +{ + int tag = dwarf_tag(die); + + switch (tag) { + /* Possible containers of exported symbols */ + case DW_TAG_namespace: + case DW_TAG_class_type: + case DW_TAG_structure_type: + return check(process_die_container( + NULL, cache, die, process_exported_symbols, match_all)); + + /* Possible exported symbols */ + case DW_TAG_subprogram: + case DW_TAG_variable: { + struct state state; + + if (!match_export_symbol(&state, die)) + return 0; + + state_init(&state); + + if (is_symbol_ptr(get_symbol_name(&state.die))) + save_symbol_ptr(&state); + else if (tag == DW_TAG_subprogram) + process_subprogram(&state, &state.die); + else + process_variable(&state, &state.die); + + cache_free(&state.expansion_cache); + return 0; + } + default: + return 0; + } +} + +static void process_symbol_ptr(struct symbol *sym, void *arg) +{ + struct state state; + Dwarf *dwarf = arg; + + if (sym->state != SYMBOL_UNPROCESSED || !sym->ptr_die_addr) + return; + + debug("%s", sym->name); + state_init(&state); + state.sym = sym; + + if (!dwarf_die_addr_die(dwarf, (void *)sym->ptr_die_addr, &state.die)) + error("dwarf_die_addr_die failed for symbol ptr: '%s'", + sym->name); + + if (dwarf_tag(&state.die) == DW_TAG_subroutine_type) + process_subprogram(&state, &state.die); + else + process_variable(&state, &state.die); + + cache_free(&state.expansion_cache); +} + +void process_cu(Dwarf_Die *cudie) +{ + check(process_die_container(NULL, NULL, cudie, process_exported_symbols, + match_all)); + + symbol_for_each(process_symbol_ptr, dwarf_cu_getdwarf(cudie->cu)); + + cache_free(&srcfile_cache); +} diff --git a/scripts/gendwarfksyms/examples/kabi.h b/scripts/gendwarfksyms/examples/kabi.h new file mode 100644 index 000000000000..97a5669b083d --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Google LLC + * + * Example macros for maintaining kABI stability. + * + * This file is based on android_kabi.h, which has the following notice: + * + * Heavily influenced by rh_kabi.h which came from the RHEL/CENTOS kernel + * and was: + * Copyright (c) 2014 Don Zickus + * Copyright (c) 2015-2018 Jiri Benc + * Copyright (c) 2015 Sabrina Dubroca, Hannes Frederic Sowa + * Copyright (c) 2016-2018 Prarit Bhargava + * Copyright (c) 2017 Paolo Abeni, Larry Woodman + */ + +#ifndef __KABI_H__ +#define __KABI_H__ + +/* Kernel macros for userspace testing. */ +#ifndef __aligned +#define __aligned(x) __attribute__((__aligned__(x))) +#endif +#ifndef __used +#define __used __attribute__((__used__)) +#endif +#ifndef __section +#define __section(section) __attribute__((__section__(section))) +#endif +#ifndef __PASTE +#define ___PASTE(a, b) a##b +#define __PASTE(a, b) ___PASTE(a, b) +#endif +#ifndef __stringify +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) +#endif + +#define __KABI_RULE(hint, target, value) \ + static const char __PASTE(__gendwarfksyms_rule_, \ + __COUNTER__)[] __used __aligned(1) \ + __section(".discard.gendwarfksyms.kabi_rules") = \ + "1\0" #hint "\0" #target "\0" #value + +#define __KABI_NORMAL_SIZE_ALIGN(_orig, _new) \ + union { \ + _Static_assert( \ + sizeof(struct { _new; }) <= sizeof(struct { _orig; }), \ + __FILE__ ":" __stringify(__LINE__) ": " __stringify( \ + _new) " is larger than " __stringify(_orig)); \ + _Static_assert( \ + __alignof__(struct { _new; }) <= \ + __alignof__(struct { _orig; }), \ + __FILE__ ":" __stringify(__LINE__) ": " __stringify( \ + _orig) " is not aligned the same as " __stringify(_new)); \ + } + +#define __KABI_REPLACE(_orig, _new) \ + union { \ + _new; \ + struct { \ + _orig; \ + }; \ + __KABI_NORMAL_SIZE_ALIGN(_orig, _new); \ + } + +/* + * KABI_DECLONLY(fqn) + * Treat the struct/union/enum fqn as a declaration, i.e. even if + * a definition is available, don't expand the contents. + */ +#define KABI_DECLONLY(fqn) __KABI_RULE(declonly, fqn, ) + +/* + * KABI_ENUMERATOR_IGNORE(fqn, field) + * When expanding enum fqn, skip the provided field. This makes it + * possible to hide added enum fields from versioning. + */ +#define KABI_ENUMERATOR_IGNORE(fqn, field) \ + __KABI_RULE(enumerator_ignore, fqn field, ) + +/* + * KABI_ENUMERATOR_VALUE(fqn, field, value) + * When expanding enum fqn, use the provided value for the + * specified field. This makes it possible to override enumerator + * values when calculating versions. + */ +#define KABI_ENUMERATOR_VALUE(fqn, field, value) \ + __KABI_RULE(enumerator_value, fqn field, value) + +/* + * KABI_RESERVE + * Reserve some "padding" in a structure for use by LTS backports. + * This is normally placed at the end of a structure. + * number: the "number" of the padding variable in the structure. Start with + * 1 and go up. + */ +#define KABI_RESERVE(n) unsigned long __kabi_reserved##n + +/* + * KABI_RESERVE_ARRAY + * Same as _BACKPORT_RESERVE but allocates an array with the specified + * size in bytes. + */ +#define KABI_RESERVE_ARRAY(n, s) \ + unsigned char __aligned(8) __kabi_reserved##n[s] + +/* + * KABI_IGNORE + * Add a new field that's ignored in versioning. + */ +#define KABI_IGNORE(n, _new) \ + union { \ + _new; \ + unsigned char __kabi_ignored##n; \ + } + +/* + * KABI_REPLACE + * Replace a field with a compatible new field. + */ +#define KABI_REPLACE(_oldtype, _oldname, _new) \ + __KABI_REPLACE(_oldtype __kabi_renamed##_oldname, struct { _new; }) + +/* + * KABI_USE(number, _new) + * Use a previous padding entry that was defined with KABI_RESERVE + * number: the previous "number" of the padding variable + * _new: the variable to use now instead of the padding variable + */ +#define KABI_USE(number, _new) __KABI_REPLACE(KABI_RESERVE(number), _new) + +/* + * KABI_USE2(number, _new1, _new2) + * Use a previous padding entry that was defined with KABI_RESERVE for + * two new variables that fit into 64 bits. This is good for when you do not + * want to "burn" a 64bit padding variable for a smaller variable size if not + * needed. + */ +#define KABI_USE2(number, _new1, _new2) \ + __KABI_REPLACE( \ + KABI_RESERVE(number), struct { \ + _new1; \ + _new2; \ + }) +/* + * KABI_USE_ARRAY(number, bytes, _new) + * Use a previous padding entry that was defined with KABI_RESERVE_ARRAY + * number: the previous "number" of the padding variable + * bytes: the size in bytes reserved for the array + * _new: the variable to use now instead of the padding variable + */ +#define KABI_USE_ARRAY(number, bytes, _new) \ + __KABI_REPLACE(KABI_RESERVE_ARRAY(number, bytes), _new) + +#endif /* __KABI_H__ */ diff --git a/scripts/gendwarfksyms/examples/kabi_ex.c b/scripts/gendwarfksyms/examples/kabi_ex.c new file mode 100644 index 000000000000..0b7ffd830541 --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi_ex.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * kabi_ex.c + * + * Copyright (C) 2024 Google LLC + * + * Examples for kABI stability features with --stable. See kabi_ex.h + * for details. + */ + +#include "kabi_ex.h" + +struct s e0; +enum e e1; + +struct ex0a ex0a; +struct ex0b ex0b; +struct ex0c ex0c; + +struct ex1a ex1a; +struct ex1b ex1b; +struct ex1c ex1c; + +struct ex2a ex2a; +struct ex2b ex2b; +struct ex2c ex2c; + +struct ex3a ex3a; +struct ex3b ex3b; +struct ex3c ex3c; diff --git a/scripts/gendwarfksyms/examples/kabi_ex.h b/scripts/gendwarfksyms/examples/kabi_ex.h new file mode 100644 index 000000000000..1736e0f65208 --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi_ex.h @@ -0,0 +1,263 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * kabi_ex.h + * + * Copyright (C) 2024 Google LLC + * + * Examples for kABI stability features with --stable. + */ + +/* + * The comments below each example contain the expected gendwarfksyms + * output, which can be verified using LLVM's FileCheck tool: + * + * https://llvm.org/docs/CommandGuide/FileCheck.html + * + * Usage: + * + * $ gcc -g -c examples/kabi_ex.c -o examples/kabi_ex.o + * + * $ nm examples/kabi_ex.o | awk '{ print $NF }' | \ + * ./gendwarfksyms --stable --dump-dies \ + * examples/kabi_ex.o 2>&1 >/dev/null | \ + * FileCheck examples/kabi_ex.h --check-prefix=STABLE + */ + +#ifndef __KABI_EX_H__ +#define __KABI_EX_H__ + +#include "kabi.h" + +/* + * Example: kABI rules + */ + +struct s { + int a; +}; + +KABI_DECLONLY(s); + +/* + * STABLE: variable structure_type s { + * STABLE-NEXT: } + */ + +enum e { + A, + B, + C, + D, +}; + +KABI_ENUMERATOR_IGNORE(e, B); +KABI_ENUMERATOR_IGNORE(e, C); +KABI_ENUMERATOR_VALUE(e, D, 123456789); + +/* + * STABLE: variable enumeration_type e { + * STABLE-NEXT: enumerator A = 0 , + * STABLE-NEXT: enumerator D = 123456789 + * STABLE-NEXT: } byte_size(4) +*/ + +/* + * Example: Reserved fields + */ +struct ex0a { + int a; + KABI_RESERVE(0); + KABI_RESERVE(1); +}; + +/* + * STABLE: variable structure_type ex0a { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) data_member_location(8) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16) + * STABLE-NEXT: } byte_size(24) + */ + +struct ex0b { + int a; + KABI_RESERVE(0); + KABI_USE2(1, int b, int c); +}; + +/* + * STABLE: variable structure_type ex0b { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16) + * STABLE-NEXT: } byte_size(24) + */ + +struct ex0c { + int a; + KABI_USE(0, void *p); + KABI_USE2(1, int b, int c); +}; + +/* + * STABLE: variable structure_type ex0c { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16) + * STABLE-NEXT: } byte_size(24) + */ + +/* + * Example: A reserved array + */ + +struct ex1a { + unsigned int a; + KABI_RESERVE_ARRAY(0, 64); +}; + +/* + * STABLE: variable structure_type ex1a { + * STABLE-NEXT: member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) , + * STABLE-NEXT: member array_type[64] { + * STABLE-NEXT: base_type unsigned char byte_size(1) encoding(8) + * STABLE-NEXT: } data_member_location(8) + * STABLE-NEXT: } byte_size(72) + */ + +struct ex1b { + unsigned int a; + KABI_USE_ARRAY( + 0, 64, struct { + void *p; + KABI_RESERVE_ARRAY(1, 56); + }); +}; + +/* + * STABLE: variable structure_type ex1b { + * STABLE-NEXT: member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) , + * STABLE-NEXT: member array_type[64] { + * STABLE-NEXT: base_type unsigned char byte_size(1) encoding(8) + * STABLE-NEXT: } data_member_location(8) + * STABLE-NEXT: } byte_size(72) + */ + +struct ex1c { + unsigned int a; + KABI_USE_ARRAY(0, 64, void *p[8]); +}; + +/* + * STABLE: variable structure_type ex1c { + * STABLE-NEXT: member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) , + * STABLE-NEXT: member array_type[64] { + * STABLE-NEXT: base_type unsigned char byte_size(1) encoding(8) + * STABLE-NEXT: } data_member_location(8) + * STABLE-NEXT: } byte_size(72) + */ + +/* + * Example: An ignored field added to an alignment hole + */ + +struct ex2a { + int a; + unsigned long b; + int c; + unsigned long d; +}; + +/* + * STABLE: variable structure_type ex2a { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) b data_member_location(8) + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) c data_member_location(16) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24) + * STABLE-NEXT: } byte_size(32) + */ + +struct ex2b { + int a; + KABI_IGNORE(0, unsigned int n); + unsigned long b; + int c; + unsigned long d; +}; + +_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2b), "ex2a size doesn't match ex2b"); + +/* + * STABLE: variable structure_type ex2b { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8) + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) c data_member_location(16) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24) + * STABLE-NEXT: } byte_size(32) + */ + +struct ex2c { + int a; + KABI_IGNORE(0, unsigned int n); + unsigned long b; + int c; + KABI_IGNORE(1, unsigned int m); + unsigned long d; +}; + +_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2c), "ex2a size doesn't match ex2c"); + +/* + * STABLE: variable structure_type ex2c { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8) + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) c data_member_location(16) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24) + * STABLE-NEXT: } byte_size(32) + */ + + +/* + * Example: A replaced field + */ + +struct ex3a { + unsigned long a; + unsigned long unused; +}; + +/* + * STABLE: variable structure_type ex3a { + * STABLE-NEXT: member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) a data_member_location(0) + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8) + * STABLE-NEXT: } byte_size(16) + */ + +struct ex3b { + unsigned long a; + KABI_REPLACE(unsigned long, unused, unsigned long renamed); +}; + +_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3b), "ex3a size doesn't match ex3b"); + +/* + * STABLE: variable structure_type ex3b { + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0) + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8) + * STABLE-NEXT: } byte_size(16) + */ + +struct ex3c { + unsigned long a; + KABI_REPLACE(unsigned long, unused, long replaced); +}; + +_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3c), "ex3a size doesn't match ex3c"); + +/* + * STABLE: variable structure_type ex3c { + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0) + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8) + * STABLE-NEXT: } byte_size(16) + */ + +#endif /* __KABI_EX_H__ */ diff --git a/scripts/gendwarfksyms/examples/symbolptr.c b/scripts/gendwarfksyms/examples/symbolptr.c new file mode 100644 index 000000000000..88bc1bd60da8 --- /dev/null +++ b/scripts/gendwarfksyms/examples/symbolptr.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + * + * Example for symbol pointers. When compiled with Clang, gendwarfkyms + * uses a symbol pointer for `f`. + * + * $ clang -g -c examples/symbolptr.c -o examples/symbolptr.o + * $ echo -e "f\ng\np" | ./gendwarfksyms -d examples/symbolptr.o + */ + +/* Kernel macros for userspace testing. */ +#ifndef __used +#define __used __attribute__((__used__)) +#endif +#ifndef __section +#define __section(section) __attribute__((__section__(section))) +#endif + +#define __GENDWARFKSYMS_EXPORT(sym) \ + static typeof(sym) *__gendwarfksyms_ptr_##sym __used \ + __section(".discard.gendwarfksyms") = &sym; + +extern void f(unsigned int arg); +void g(int *arg); +void g(int *arg) {} + +struct s; +extern struct s *p; + +__GENDWARFKSYMS_EXPORT(f); +__GENDWARFKSYMS_EXPORT(g); +__GENDWARFKSYMS_EXPORT(p); diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c new file mode 100644 index 000000000000..08ae61eb327e --- /dev/null +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include <fcntl.h> +#include <getopt.h> +#include <errno.h> +#include <stdarg.h> +#include <string.h> +#include <unistd.h> +#include "gendwarfksyms.h" + +/* + * Options + */ + +/* Print debugging information to stderr */ +int debug; +/* Dump DIE contents */ +int dump_dies; +/* Print debugging information about die_map changes */ +int dump_die_map; +/* Print out type strings (i.e. type_map) */ +int dump_types; +/* Print out expanded type strings used for symbol versions */ +int dump_versions; +/* Support kABI stability features */ +int stable; +/* Write a symtypes file */ +int symtypes; +static const char *symtypes_file; + +static void usage(void) +{ + fputs("Usage: gendwarfksyms [options] elf-object-file ... < symbol-list\n\n" + "Options:\n" + " -d, --debug Print debugging information\n" + " --dump-dies Dump DWARF DIE contents\n" + " --dump-die-map Print debugging information about die_map changes\n" + " --dump-types Dump type strings\n" + " --dump-versions Dump expanded type strings used for symbol versions\n" + " -s, --stable Support kABI stability features\n" + " -T, --symtypes file Write a symtypes file\n" + " -h, --help Print this message\n" + "\n", + stderr); +} + +static int process_module(Dwfl_Module *mod, void **userdata, const char *name, + Dwarf_Addr base, void *arg) +{ + Dwarf_Addr dwbias; + Dwarf_Die cudie; + Dwarf_CU *cu = NULL; + Dwarf *dbg; + FILE *symfile = arg; + int res; + + debug("%s", name); + dbg = dwfl_module_getdwarf(mod, &dwbias); + + /* + * Look for exported symbols in each CU, follow the DIE tree, and add + * the entries to die_map. + */ + do { + res = dwarf_get_units(dbg, cu, &cu, NULL, NULL, &cudie, NULL); + if (res < 0) + error("dwarf_get_units failed: no debugging information?"); + if (res == 1) + break; /* No more units */ + + process_cu(&cudie); + } while (cu); + + /* + * Use die_map to expand type strings, write them to `symfile`, and + * calculate symbol versions. + */ + generate_symtypes_and_versions(symfile); + die_map_free(); + + return DWARF_CB_OK; +} + +static const Dwfl_Callbacks callbacks = { + .section_address = dwfl_offline_section_address, + .find_debuginfo = dwfl_standard_find_debuginfo, +}; + +int main(int argc, char **argv) +{ + FILE *symfile = NULL; + unsigned int n; + int opt; + + static const struct option opts[] = { + { "debug", 0, NULL, 'd' }, + { "dump-dies", 0, &dump_dies, 1 }, + { "dump-die-map", 0, &dump_die_map, 1 }, + { "dump-types", 0, &dump_types, 1 }, + { "dump-versions", 0, &dump_versions, 1 }, + { "stable", 0, NULL, 's' }, + { "symtypes", 1, NULL, 'T' }, + { "help", 0, NULL, 'h' }, + { 0, 0, NULL, 0 } + }; + + while ((opt = getopt_long(argc, argv, "dsT:h", opts, NULL)) != EOF) { + switch (opt) { + case 0: + break; + case 'd': + debug = 1; + break; + case 's': + stable = 1; + break; + case 'T': + symtypes = 1; + symtypes_file = optarg; + break; + case 'h': + usage(); + return 0; + default: + usage(); + return 1; + } + } + + if (dump_die_map) + dump_dies = 1; + + if (optind >= argc) { + usage(); + error("no input files?"); + } + + symbol_read_exports(stdin); + + if (symtypes_file) { + symfile = fopen(symtypes_file, "w"); + if (!symfile) + error("fopen failed for '%s': %s", symtypes_file, + strerror(errno)); + } + + for (n = optind; n < argc; n++) { + Dwfl *dwfl; + int fd; + + fd = open(argv[n], O_RDONLY); + if (fd == -1) + error("open failed for '%s': %s", argv[n], + strerror(errno)); + + symbol_read_symtab(fd); + kabi_read_rules(fd); + + dwfl = dwfl_begin(&callbacks); + if (!dwfl) + error("dwfl_begin failed for '%s': %s", argv[n], + dwarf_errmsg(-1)); + + if (!dwfl_report_offline(dwfl, argv[n], argv[n], fd)) + error("dwfl_report_offline failed for '%s': %s", + argv[n], dwarf_errmsg(-1)); + + dwfl_report_end(dwfl, NULL, NULL); + + if (dwfl_getmodules(dwfl, &process_module, symfile, 0)) + error("dwfl_getmodules failed for '%s'", argv[n]); + + dwfl_end(dwfl); + kabi_free(); + } + + if (symfile) + check(fclose(symfile)); + + symbol_print_versions(); + symbol_free(); + + return 0; +} diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h new file mode 100644 index 000000000000..197a1a8123c6 --- /dev/null +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -0,0 +1,296 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Google LLC + */ + +#include <dwarf.h> +#include <elfutils/libdw.h> +#include <elfutils/libdwfl.h> +#include <stdlib.h> +#include <stdio.h> + +#include <hash.h> +#include <hashtable.h> +#include <xalloc.h> + +#ifndef __GENDWARFKSYMS_H +#define __GENDWARFKSYMS_H + +/* + * Options -- in gendwarfksyms.c + */ +extern int debug; +extern int dump_dies; +extern int dump_die_map; +extern int dump_types; +extern int dump_versions; +extern int stable; +extern int symtypes; + +/* + * Output helpers + */ +#define __PREFIX "gendwarfksyms: " +#define __println(prefix, format, ...) \ + fprintf(stderr, prefix __PREFIX "%s: " format "\n", __func__, \ + ##__VA_ARGS__) + +#define debug(format, ...) \ + do { \ + if (debug) \ + __println("", format, ##__VA_ARGS__); \ + } while (0) + +#define warn(format, ...) __println("warning: ", format, ##__VA_ARGS__) +#define error(format, ...) \ + do { \ + __println("error: ", format, ##__VA_ARGS__); \ + exit(1); \ + } while (0) + +#define __die_debug(color, format, ...) \ + do { \ + if (dump_dies && dump_die_map) \ + fprintf(stderr, \ + "\033[" #color "m<" format ">\033[39m", \ + __VA_ARGS__); \ + } while (0) + +#define die_debug_r(format, ...) __die_debug(91, format, __VA_ARGS__) +#define die_debug_g(format, ...) __die_debug(92, format, __VA_ARGS__) +#define die_debug_b(format, ...) __die_debug(94, format, __VA_ARGS__) + +/* + * Error handling helpers + */ +#define __check(expr, test) \ + ({ \ + int __res = expr; \ + if (test) \ + error("`%s` failed: %d", #expr, __res); \ + __res; \ + }) + +/* Error == non-zero values */ +#define check(expr) __check(expr, __res) +/* Error == negative values */ +#define checkp(expr) __check(expr, __res < 0) + +/* Consistent aliases (DW_TAG_<type>_type) for DWARF tags */ +#define DW_TAG_enumerator_type DW_TAG_enumerator +#define DW_TAG_formal_parameter_type DW_TAG_formal_parameter +#define DW_TAG_member_type DW_TAG_member +#define DW_TAG_template_type_parameter_type DW_TAG_template_type_parameter +#define DW_TAG_typedef_type DW_TAG_typedef +#define DW_TAG_variant_part_type DW_TAG_variant_part +#define DW_TAG_variant_type DW_TAG_variant + +/* + * symbols.c + */ + +/* See symbols.c:is_symbol_ptr */ +#define SYMBOL_PTR_PREFIX "__gendwarfksyms_ptr_" +#define SYMBOL_PTR_PREFIX_LEN (sizeof(SYMBOL_PTR_PREFIX) - 1) + +static inline unsigned int addr_hash(uintptr_t addr) +{ + return hash_ptr((const void *)addr); +} + +enum symbol_state { + SYMBOL_UNPROCESSED, + SYMBOL_MAPPED, + SYMBOL_PROCESSED +}; + +struct symbol_addr { + uint32_t section; + Elf64_Addr address; +}; + +struct symbol { + const char *name; + struct symbol_addr addr; + struct hlist_node addr_hash; + struct hlist_node name_hash; + enum symbol_state state; + uintptr_t die_addr; + uintptr_t ptr_die_addr; + unsigned long crc; +}; + +typedef void (*symbol_callback_t)(struct symbol *, void *arg); + +bool is_symbol_ptr(const char *name); +void symbol_read_exports(FILE *file); +void symbol_read_symtab(int fd); +struct symbol *symbol_get(const char *name); +void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr); +void symbol_set_die(struct symbol *sym, Dwarf_Die *die); +void symbol_set_crc(struct symbol *sym, unsigned long crc); +void symbol_for_each(symbol_callback_t func, void *arg); +void symbol_print_versions(void); +void symbol_free(void); + +/* + * die.c + */ + +enum die_state { + DIE_INCOMPLETE, + DIE_UNEXPANDED, + DIE_COMPLETE, + DIE_SYMBOL, + DIE_LAST = DIE_SYMBOL +}; + +enum die_fragment_type { + FRAGMENT_EMPTY, + FRAGMENT_STRING, + FRAGMENT_LINEBREAK, + FRAGMENT_DIE +}; + +struct die_fragment { + enum die_fragment_type type; + union { + char *str; + int linebreak; + uintptr_t addr; + } data; + struct list_head list; +}; + +#define CASE_CONST_TO_STR(name) \ + case name: \ + return #name; + +static inline const char *die_state_name(enum die_state state) +{ + switch (state) { + CASE_CONST_TO_STR(DIE_INCOMPLETE) + CASE_CONST_TO_STR(DIE_UNEXPANDED) + CASE_CONST_TO_STR(DIE_COMPLETE) + CASE_CONST_TO_STR(DIE_SYMBOL) + } + + error("unexpected die_state: %d", state); +} + +struct die { + enum die_state state; + bool mapped; + char *fqn; + int tag; + uintptr_t addr; + struct list_head fragments; + struct hlist_node hash; +}; + +typedef void (*die_map_callback_t)(struct die *, void *arg); + +int __die_map_get(uintptr_t addr, enum die_state state, struct die **res); +struct die *die_map_get(Dwarf_Die *die, enum die_state state); +void die_map_add_string(struct die *pd, const char *str); +void die_map_add_linebreak(struct die *pd, int linebreak); +void die_map_for_each(die_map_callback_t func, void *arg); +void die_map_add_die(struct die *pd, struct die *child); +void die_map_free(void); + +/* + * cache.c + */ + +#define CACHE_HASH_BITS 10 + +/* A cache for addresses we've already seen. */ +struct cache { + HASHTABLE_DECLARE(cache, 1 << CACHE_HASH_BITS); +}; + +void cache_set(struct cache *cache, unsigned long key, int value); +int cache_get(struct cache *cache, unsigned long key); +void cache_init(struct cache *cache); +void cache_free(struct cache *cache); + +static inline void __cache_mark_expanded(struct cache *cache, uintptr_t addr) +{ + cache_set(cache, addr, 1); +} + +static inline bool __cache_was_expanded(struct cache *cache, uintptr_t addr) +{ + return cache_get(cache, addr) == 1; +} + +static inline void cache_mark_expanded(struct cache *cache, void *addr) +{ + __cache_mark_expanded(cache, (uintptr_t)addr); +} + +static inline bool cache_was_expanded(struct cache *cache, void *addr) +{ + return __cache_was_expanded(cache, (uintptr_t)addr); +} + +/* + * dwarf.c + */ + +struct expansion_state { + bool expand; + const char *current_fqn; +}; + +struct kabi_state { + int members; + Dwarf_Die placeholder; + const char *orig_name; +}; + +struct state { + struct symbol *sym; + Dwarf_Die die; + + /* List expansion */ + bool first_list_item; + + /* Structure expansion */ + struct expansion_state expand; + struct cache expansion_cache; + + /* Reserved or ignored members */ + struct kabi_state kabi; +}; + +typedef int (*die_callback_t)(struct state *state, struct die *cache, + Dwarf_Die *die); +typedef bool (*die_match_callback_t)(Dwarf_Die *die); +bool match_all(Dwarf_Die *die); + +int process_die_container(struct state *state, struct die *cache, + Dwarf_Die *die, die_callback_t func, + die_match_callback_t match); + +void process_cu(Dwarf_Die *cudie); + +/* + * types.c + */ + +void generate_symtypes_and_versions(FILE *file); + +/* + * kabi.c + */ + +bool kabi_is_enumerator_ignored(const char *fqn, const char *field); +bool kabi_get_enumerator_value(const char *fqn, const char *field, + unsigned long *value); +bool kabi_is_declonly(const char *fqn); + +void kabi_read_rules(int fd); +void kabi_free(void); + +#endif /* __GENDWARFKSYMS_H */ diff --git a/scripts/gendwarfksyms/kabi.c b/scripts/gendwarfksyms/kabi.c new file mode 100644 index 000000000000..66f01fcd1607 --- /dev/null +++ b/scripts/gendwarfksyms/kabi.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> + +#include "gendwarfksyms.h" + +#define KABI_RULE_SECTION ".discard.gendwarfksyms.kabi_rules" +#define KABI_RULE_VERSION "1" + +/* + * The rule section consists of four null-terminated strings per + * entry: + * + * 1. version + * Entry format version. Must match KABI_RULE_VERSION. + * + * 2. type + * Type of the kABI rule. Must be one of the tags defined below. + * + * 3. target + * Rule-dependent target, typically the fully qualified name of + * the target DIE. + * + * 4. value + * Rule-dependent value. + */ +#define KABI_RULE_MIN_ENTRY_SIZE \ + (/* version\0 */ 2 + /* type\0 */ 2 + /* target\0" */ 1 + \ + /* value\0 */ 1) +#define KABI_RULE_EMPTY_VALUE "" + +/* + * Rule: declonly + * - For the struct/enum/union in the target field, treat it as a + * declaration only even if a definition is available. + */ +#define KABI_RULE_TAG_DECLONLY "declonly" + +/* + * Rule: enumerator_ignore + * - For the enum_field in the target field, ignore the enumerator. + */ +#define KABI_RULE_TAG_ENUMERATOR_IGNORE "enumerator_ignore" + +/* + * Rule: enumerator_value + * - For the fqn_field in the target field, set the value to the + * unsigned integer in the value field. + */ +#define KABI_RULE_TAG_ENUMERATOR_VALUE "enumerator_value" + +enum kabi_rule_type { + KABI_RULE_TYPE_UNKNOWN, + KABI_RULE_TYPE_DECLONLY, + KABI_RULE_TYPE_ENUMERATOR_IGNORE, + KABI_RULE_TYPE_ENUMERATOR_VALUE, +}; + +#define RULE_HASH_BITS 7 + +struct rule { + enum kabi_rule_type type; + const char *target; + const char *value; + struct hlist_node hash; +}; + +/* { type, target } -> struct rule */ +static HASHTABLE_DEFINE(rules, 1 << RULE_HASH_BITS); + +static inline unsigned int rule_values_hash(enum kabi_rule_type type, + const char *target) +{ + return hash_32(type) ^ hash_str(target); +} + +static inline unsigned int rule_hash(const struct rule *rule) +{ + return rule_values_hash(rule->type, rule->target); +} + +static inline const char *get_rule_field(const char **pos, ssize_t *left) +{ + const char *start = *pos; + size_t len; + + if (*left <= 0) + error("unexpected end of kABI rules"); + + len = strnlen(start, *left) + 1; + *pos += len; + *left -= len; + + return start; +} + +void kabi_read_rules(int fd) +{ + GElf_Shdr shdr_mem; + GElf_Shdr *shdr; + Elf_Data *rule_data = NULL; + Elf_Scn *scn; + Elf *elf; + size_t shstrndx; + const char *rule_str; + ssize_t left; + int i; + + const struct { + enum kabi_rule_type type; + const char *tag; + } rule_types[] = { + { + .type = KABI_RULE_TYPE_DECLONLY, + .tag = KABI_RULE_TAG_DECLONLY, + }, + { + .type = KABI_RULE_TYPE_ENUMERATOR_IGNORE, + .tag = KABI_RULE_TAG_ENUMERATOR_IGNORE, + }, + { + .type = KABI_RULE_TYPE_ENUMERATOR_VALUE, + .tag = KABI_RULE_TAG_ENUMERATOR_VALUE, + }, + }; + + if (!stable) + return; + + if (elf_version(EV_CURRENT) != EV_CURRENT) + error("elf_version failed: %s", elf_errmsg(-1)); + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) + error("elf_begin failed: %s", elf_errmsg(-1)); + + if (elf_getshdrstrndx(elf, &shstrndx) < 0) + error("elf_getshdrstrndx failed: %s", elf_errmsg(-1)); + + scn = elf_nextscn(elf, NULL); + + while (scn) { + const char *sname; + + shdr = gelf_getshdr(scn, &shdr_mem); + if (!shdr) + error("gelf_getshdr failed: %s", elf_errmsg(-1)); + + sname = elf_strptr(elf, shstrndx, shdr->sh_name); + if (!sname) + error("elf_strptr failed: %s", elf_errmsg(-1)); + + if (!strcmp(sname, KABI_RULE_SECTION)) { + rule_data = elf_getdata(scn, NULL); + if (!rule_data) + error("elf_getdata failed: %s", elf_errmsg(-1)); + break; + } + + scn = elf_nextscn(elf, scn); + } + + if (!rule_data) { + debug("kABI rules not found"); + check(elf_end(elf)); + return; + } + + rule_str = rule_data->d_buf; + left = shdr->sh_size; + + if (left < KABI_RULE_MIN_ENTRY_SIZE) + error("kABI rule section too small: %zd bytes", left); + + if (rule_str[left - 1] != '\0') + error("kABI rules are not null-terminated"); + + while (left > KABI_RULE_MIN_ENTRY_SIZE) { + enum kabi_rule_type type = KABI_RULE_TYPE_UNKNOWN; + const char *field; + struct rule *rule; + + /* version */ + field = get_rule_field(&rule_str, &left); + + if (strcmp(field, KABI_RULE_VERSION)) + error("unsupported kABI rule version: '%s'", field); + + /* type */ + field = get_rule_field(&rule_str, &left); + + for (i = 0; i < ARRAY_SIZE(rule_types); i++) { + if (!strcmp(field, rule_types[i].tag)) { + type = rule_types[i].type; + break; + } + } + + if (type == KABI_RULE_TYPE_UNKNOWN) + error("unsupported kABI rule type: '%s'", field); + + rule = xmalloc(sizeof(struct rule)); + + rule->type = type; + rule->target = xstrdup(get_rule_field(&rule_str, &left)); + rule->value = xstrdup(get_rule_field(&rule_str, &left)); + + hash_add(rules, &rule->hash, rule_hash(rule)); + + debug("kABI rule: type: '%s', target: '%s', value: '%s'", field, + rule->target, rule->value); + } + + if (left > 0) + warn("unexpected data at the end of the kABI rules section"); + + check(elf_end(elf)); +} + +bool kabi_is_declonly(const char *fqn) +{ + struct rule *rule; + + if (!stable) + return false; + if (!fqn || !*fqn) + return false; + + hash_for_each_possible(rules, rule, hash, + rule_values_hash(KABI_RULE_TYPE_DECLONLY, fqn)) { + if (rule->type == KABI_RULE_TYPE_DECLONLY && + !strcmp(fqn, rule->target)) + return true; + } + + return false; +} + +static char *get_enumerator_target(const char *fqn, const char *field) +{ + char *target = NULL; + + if (asprintf(&target, "%s %s", fqn, field) < 0) + error("asprintf failed for '%s %s'", fqn, field); + + return target; +} + +static unsigned long get_ulong_value(const char *value) +{ + unsigned long result = 0; + char *endptr = NULL; + + errno = 0; + result = strtoul(value, &endptr, 10); + + if (errno || *endptr) + error("invalid unsigned value '%s'", value); + + return result; +} + +bool kabi_is_enumerator_ignored(const char *fqn, const char *field) +{ + bool match = false; + struct rule *rule; + char *target; + + if (!stable) + return false; + if (!fqn || !*fqn || !field || !*field) + return false; + + target = get_enumerator_target(fqn, field); + + hash_for_each_possible( + rules, rule, hash, + rule_values_hash(KABI_RULE_TYPE_ENUMERATOR_IGNORE, target)) { + if (rule->type == KABI_RULE_TYPE_ENUMERATOR_IGNORE && + !strcmp(target, rule->target)) { + match = true; + break; + } + } + + free(target); + return match; +} + +bool kabi_get_enumerator_value(const char *fqn, const char *field, + unsigned long *value) +{ + bool match = false; + struct rule *rule; + char *target; + + if (!stable) + return false; + if (!fqn || !*fqn || !field || !*field) + return false; + + target = get_enumerator_target(fqn, field); + + hash_for_each_possible(rules, rule, hash, + rule_values_hash(KABI_RULE_TYPE_ENUMERATOR_VALUE, + target)) { + if (rule->type == KABI_RULE_TYPE_ENUMERATOR_VALUE && + !strcmp(target, rule->target)) { + *value = get_ulong_value(rule->value); + match = true; + break; + } + } + + free(target); + return match; +} + +void kabi_free(void) +{ + struct hlist_node *tmp; + struct rule *rule; + + hash_for_each_safe(rules, rule, tmp, hash) { + free((void *)rule->target); + free((void *)rule->value); + free(rule); + } + + hash_init(rules); +} diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c new file mode 100644 index 000000000000..327f87389c34 --- /dev/null +++ b/scripts/gendwarfksyms/symbols.c @@ -0,0 +1,341 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include "gendwarfksyms.h" + +#define SYMBOL_HASH_BITS 12 + +/* struct symbol_addr -> struct symbol */ +static HASHTABLE_DEFINE(symbol_addrs, 1 << SYMBOL_HASH_BITS); +/* name -> struct symbol */ +static HASHTABLE_DEFINE(symbol_names, 1 << SYMBOL_HASH_BITS); + +static inline unsigned int symbol_addr_hash(const struct symbol_addr *addr) +{ + return hash_32(addr->section ^ addr_hash(addr->address)); +} + +static unsigned int __for_each_addr(struct symbol *sym, symbol_callback_t func, + void *data) +{ + struct hlist_node *tmp; + struct symbol *match = NULL; + unsigned int processed = 0; + + hash_for_each_possible_safe(symbol_addrs, match, tmp, addr_hash, + symbol_addr_hash(&sym->addr)) { + if (match == sym) + continue; /* Already processed */ + + if (match->addr.section == sym->addr.section && + match->addr.address == sym->addr.address) { + func(match, data); + ++processed; + } + } + + return processed; +} + +/* + * For symbols without debugging information (e.g. symbols defined in other + * TUs), we also match __gendwarfksyms_ptr_<symbol_name> symbols, which the + * kernel uses to ensure type information is present in the TU that exports + * the symbol. A __gendwarfksyms_ptr pointer must have the same type as the + * exported symbol, e.g.: + * + * typeof(symname) *__gendwarf_ptr_symname = &symname; + */ +bool is_symbol_ptr(const char *name) +{ + return name && !strncmp(name, SYMBOL_PTR_PREFIX, SYMBOL_PTR_PREFIX_LEN); +} + +static unsigned int for_each(const char *name, symbol_callback_t func, + void *data) +{ + struct hlist_node *tmp; + struct symbol *match; + + if (!name || !*name) + return 0; + if (is_symbol_ptr(name)) + name += SYMBOL_PTR_PREFIX_LEN; + + hash_for_each_possible_safe(symbol_names, match, tmp, name_hash, + hash_str(name)) { + if (strcmp(match->name, name)) + continue; + + /* Call func for the match, and all address matches */ + if (func) + func(match, data); + + if (match->addr.section != SHN_UNDEF) + return __for_each_addr(match, func, data) + 1; + + return 1; + } + + return 0; +} + +static void set_crc(struct symbol *sym, void *data) +{ + unsigned long *crc = data; + + if (sym->state == SYMBOL_PROCESSED && sym->crc != *crc) + warn("overriding version for symbol %s (crc %lx vs. %lx)", + sym->name, sym->crc, *crc); + + sym->state = SYMBOL_PROCESSED; + sym->crc = *crc; +} + +void symbol_set_crc(struct symbol *sym, unsigned long crc) +{ + if (for_each(sym->name, set_crc, &crc) == 0) + error("no matching symbols: '%s'", sym->name); +} + +static void set_ptr(struct symbol *sym, void *data) +{ + sym->ptr_die_addr = (uintptr_t)((Dwarf_Die *)data)->addr; +} + +void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr) +{ + if (for_each(sym->name, set_ptr, ptr) == 0) + error("no matching symbols: '%s'", sym->name); +} + +static void set_die(struct symbol *sym, void *data) +{ + sym->die_addr = (uintptr_t)((Dwarf_Die *)data)->addr; + sym->state = SYMBOL_MAPPED; +} + +void symbol_set_die(struct symbol *sym, Dwarf_Die *die) +{ + if (for_each(sym->name, set_die, die) == 0) + error("no matching symbols: '%s'", sym->name); +} + +static bool is_exported(const char *name) +{ + return for_each(name, NULL, NULL) > 0; +} + +void symbol_read_exports(FILE *file) +{ + struct symbol *sym; + char *line = NULL; + char *name = NULL; + size_t size = 0; + int nsym = 0; + + while (getline(&line, &size, file) > 0) { + if (sscanf(line, "%ms\n", &name) != 1) + error("malformed input line: %s", line); + + if (is_exported(name)) { + /* Ignore duplicates */ + free(name); + continue; + } + + sym = xcalloc(1, sizeof(struct symbol)); + sym->name = name; + sym->addr.section = SHN_UNDEF; + sym->state = SYMBOL_UNPROCESSED; + + hash_add(symbol_names, &sym->name_hash, hash_str(sym->name)); + ++nsym; + + debug("%s", sym->name); + } + + free(line); + debug("%d exported symbols", nsym); +} + +static void get_symbol(struct symbol *sym, void *arg) +{ + struct symbol **res = arg; + + if (sym->state == SYMBOL_UNPROCESSED) + *res = sym; +} + +struct symbol *symbol_get(const char *name) +{ + struct symbol *sym = NULL; + + for_each(name, get_symbol, &sym); + return sym; +} + +void symbol_for_each(symbol_callback_t func, void *arg) +{ + struct hlist_node *tmp; + struct symbol *sym; + + hash_for_each_safe(symbol_names, sym, tmp, name_hash) { + func(sym, arg); + } +} + +typedef void (*elf_symbol_callback_t)(const char *name, GElf_Sym *sym, + Elf32_Word xndx, void *arg); + +static void elf_for_each_global(int fd, elf_symbol_callback_t func, void *arg) +{ + size_t sym_size; + GElf_Shdr shdr_mem; + GElf_Shdr *shdr; + Elf_Data *xndx_data = NULL; + Elf_Scn *scn; + Elf *elf; + + if (elf_version(EV_CURRENT) != EV_CURRENT) + error("elf_version failed: %s", elf_errmsg(-1)); + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) + error("elf_begin failed: %s", elf_errmsg(-1)); + + scn = elf_nextscn(elf, NULL); + + while (scn) { + shdr = gelf_getshdr(scn, &shdr_mem); + if (!shdr) + error("gelf_getshdr failed: %s", elf_errmsg(-1)); + + if (shdr->sh_type == SHT_SYMTAB_SHNDX) { + xndx_data = elf_getdata(scn, NULL); + if (!xndx_data) + error("elf_getdata failed: %s", elf_errmsg(-1)); + break; + } + + scn = elf_nextscn(elf, scn); + } + + sym_size = gelf_fsize(elf, ELF_T_SYM, 1, EV_CURRENT); + scn = elf_nextscn(elf, NULL); + + while (scn) { + shdr = gelf_getshdr(scn, &shdr_mem); + if (!shdr) + error("gelf_getshdr failed: %s", elf_errmsg(-1)); + + if (shdr->sh_type == SHT_SYMTAB) { + unsigned int nsyms; + unsigned int n; + Elf_Data *data = elf_getdata(scn, NULL); + + if (!data) + error("elf_getdata failed: %s", elf_errmsg(-1)); + + if (shdr->sh_entsize != sym_size) + error("expected sh_entsize (%lu) to be %zu", + shdr->sh_entsize, sym_size); + + nsyms = shdr->sh_size / shdr->sh_entsize; + + for (n = 1; n < nsyms; ++n) { + const char *name = NULL; + Elf32_Word xndx = 0; + GElf_Sym sym_mem; + GElf_Sym *sym; + + sym = gelf_getsymshndx(data, xndx_data, n, + &sym_mem, &xndx); + if (!sym) + error("gelf_getsymshndx failed: %s", + elf_errmsg(-1)); + + if (GELF_ST_BIND(sym->st_info) == STB_LOCAL) + continue; + + if (sym->st_shndx != SHN_XINDEX) + xndx = sym->st_shndx; + + name = elf_strptr(elf, shdr->sh_link, + sym->st_name); + if (!name) + error("elf_strptr failed: %s", + elf_errmsg(-1)); + + /* Skip empty symbol names */ + if (*name) + func(name, sym, xndx, arg); + } + } + + scn = elf_nextscn(elf, scn); + } + + check(elf_end(elf)); +} + +static void set_symbol_addr(struct symbol *sym, void *arg) +{ + struct symbol_addr *addr = arg; + + if (sym->addr.section == SHN_UNDEF) { + sym->addr = *addr; + hash_add(symbol_addrs, &sym->addr_hash, + symbol_addr_hash(&sym->addr)); + + debug("%s -> { %u, %lx }", sym->name, sym->addr.section, + sym->addr.address); + } else if (sym->addr.section != addr->section || + sym->addr.address != addr->address) { + warn("multiple addresses for symbol %s?", sym->name); + } +} + +static void elf_set_symbol_addr(const char *name, GElf_Sym *sym, + Elf32_Word xndx, void *arg) +{ + struct symbol_addr addr = { .section = xndx, .address = sym->st_value }; + + /* Set addresses for exported symbols */ + if (addr.section != SHN_UNDEF) + for_each(name, set_symbol_addr, &addr); +} + +void symbol_read_symtab(int fd) +{ + elf_for_each_global(fd, elf_set_symbol_addr, NULL); +} + +void symbol_print_versions(void) +{ + struct hlist_node *tmp; + struct symbol *sym; + + hash_for_each_safe(symbol_names, sym, tmp, name_hash) { + if (sym->state != SYMBOL_PROCESSED) + warn("no information for symbol %s", sym->name); + + printf("#SYMVER %s 0x%08lx\n", sym->name, sym->crc); + } +} + +void symbol_free(void) +{ + struct hlist_node *tmp; + struct symbol *sym; + + hash_for_each_safe(symbol_names, sym, tmp, name_hash) { + free((void *)sym->name); + free(sym); + } + + hash_init(symbol_addrs); + hash_init(symbol_names); +} diff --git a/scripts/gendwarfksyms/types.c b/scripts/gendwarfksyms/types.c new file mode 100644 index 000000000000..6c03265f4d10 --- /dev/null +++ b/scripts/gendwarfksyms/types.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#define _GNU_SOURCE +#include <inttypes.h> +#include <stdio.h> +#include <zlib.h> + +#include "gendwarfksyms.h" + +static struct cache expansion_cache; + +/* + * A simple linked list of shared or owned strings to avoid copying strings + * around when not necessary. + */ +struct type_list_entry { + const char *str; + void *owned; + struct list_head list; +}; + +static void type_list_free(struct list_head *list) +{ + struct type_list_entry *entry; + struct type_list_entry *tmp; + + list_for_each_entry_safe(entry, tmp, list, list) { + if (entry->owned) + free(entry->owned); + free(entry); + } + + INIT_LIST_HEAD(list); +} + +static int type_list_append(struct list_head *list, const char *s, void *owned) +{ + struct type_list_entry *entry; + + if (!s) + return 0; + + entry = xmalloc(sizeof(struct type_list_entry)); + entry->str = s; + entry->owned = owned; + list_add_tail(&entry->list, list); + + return strlen(entry->str); +} + +static void type_list_write(struct list_head *list, FILE *file) +{ + struct type_list_entry *entry; + + list_for_each_entry(entry, list, list) { + if (entry->str) + checkp(fputs(entry->str, file)); + } +} + +/* + * An expanded type string in symtypes format. + */ +struct type_expansion { + char *name; + size_t len; + struct list_head expanded; + struct hlist_node hash; +}; + +static void type_expansion_init(struct type_expansion *type) +{ + type->name = NULL; + type->len = 0; + INIT_LIST_HEAD(&type->expanded); +} + +static inline void type_expansion_free(struct type_expansion *type) +{ + free(type->name); + type->name = NULL; + type->len = 0; + type_list_free(&type->expanded); +} + +static void type_expansion_append(struct type_expansion *type, const char *s, + void *owned) +{ + type->len += type_list_append(&type->expanded, s, owned); +} + +/* + * type_map -- the longest expansions for each type. + * + * const char *name -> struct type_expansion * + */ +#define TYPE_HASH_BITS 12 +static HASHTABLE_DEFINE(type_map, 1 << TYPE_HASH_BITS); + +static int type_map_get(const char *name, struct type_expansion **res) +{ + struct type_expansion *e; + + hash_for_each_possible(type_map, e, hash, hash_str(name)) { + if (!strcmp(name, e->name)) { + *res = e; + return 0; + } + } + + return -1; +} + +static void type_map_add(const char *name, struct type_expansion *type) +{ + struct type_expansion *e; + + if (type_map_get(name, &e)) { + e = xmalloc(sizeof(struct type_expansion)); + type_expansion_init(e); + e->name = xstrdup(name); + + hash_add(type_map, &e->hash, hash_str(e->name)); + + if (dump_types) + debug("adding %s", e->name); + } else { + /* Use the longest available expansion */ + if (type->len <= e->len) + return; + + type_list_free(&e->expanded); + + if (dump_types) + debug("replacing %s", e->name); + } + + /* Take ownership of type->expanded */ + list_replace_init(&type->expanded, &e->expanded); + e->len = type->len; + + if (dump_types) { + checkp(fputs(e->name, stderr)); + checkp(fputs(" ", stderr)); + type_list_write(&e->expanded, stderr); + checkp(fputs("\n", stderr)); + } +} + +static void type_map_write(FILE *file) +{ + struct type_expansion *e; + struct hlist_node *tmp; + + if (!file) + return; + + hash_for_each_safe(type_map, e, tmp, hash) { + checkp(fputs(e->name, file)); + checkp(fputs(" ", file)); + type_list_write(&e->expanded, file); + checkp(fputs("\n", file)); + } +} + +static void type_map_free(void) +{ + struct type_expansion *e; + struct hlist_node *tmp; + + hash_for_each_safe(type_map, e, tmp, hash) { + type_expansion_free(e); + free(e); + } + + hash_init(type_map); +} + +/* + * CRC for a type, with an optional fully expanded type string for + * debugging. + */ +struct version { + struct type_expansion type; + unsigned long crc; +}; + +static void version_init(struct version *version) +{ + version->crc = crc32(0, NULL, 0); + type_expansion_init(&version->type); +} + +static void version_free(struct version *version) +{ + type_expansion_free(&version->type); +} + +static void version_add(struct version *version, const char *s) +{ + version->crc = crc32(version->crc, (void *)s, strlen(s)); + if (dump_versions) + type_expansion_append(&version->type, s, NULL); +} + +/* + * Type reference format: <prefix>#<name>, where prefix: + * s -> structure + * u -> union + * e -> enum + * t -> typedef + * + * Names with spaces are additionally wrapped in single quotes. + */ +static inline bool is_type_prefix(const char *s) +{ + return (s[0] == 's' || s[0] == 'u' || s[0] == 'e' || s[0] == 't') && + s[1] == '#'; +} + +static char get_type_prefix(int tag) +{ + switch (tag) { + case DW_TAG_class_type: + case DW_TAG_structure_type: + return 's'; + case DW_TAG_union_type: + return 'u'; + case DW_TAG_enumeration_type: + return 'e'; + case DW_TAG_typedef_type: + return 't'; + default: + return 0; + } +} + +static char *get_type_name(struct die *cache) +{ + const char *quote; + char prefix; + char *name; + + if (cache->state == DIE_INCOMPLETE) { + warn("found incomplete cache entry: %p", cache); + return NULL; + } + if (cache->state == DIE_SYMBOL) + return NULL; + if (!cache->fqn || !*cache->fqn) + return NULL; + + prefix = get_type_prefix(cache->tag); + if (!prefix) + return NULL; + + /* Wrap names with spaces in single quotes */ + quote = strstr(cache->fqn, " ") ? "'" : ""; + + /* <prefix>#<type_name>\0 */ + if (asprintf(&name, "%c#%s%s%s", prefix, quote, cache->fqn, quote) < 0) + error("asprintf failed for '%s'", cache->fqn); + + return name; +} + +static void __calculate_version(struct version *version, struct list_head *list) +{ + struct type_list_entry *entry; + struct type_expansion *e; + + /* Calculate a CRC over an expanded type string */ + list_for_each_entry(entry, list, list) { + if (is_type_prefix(entry->str)) { + check(type_map_get(entry->str, &e)); + + /* + * It's sufficient to expand each type reference just + * once to detect changes. + */ + if (cache_was_expanded(&expansion_cache, e)) { + version_add(version, entry->str); + } else { + cache_mark_expanded(&expansion_cache, e); + __calculate_version(version, &e->expanded); + } + } else { + version_add(version, entry->str); + } + } +} + +static void calculate_version(struct version *version, struct list_head *list) +{ + version_init(version); + __calculate_version(version, list); + cache_free(&expansion_cache); +} + +static void __type_expand(struct die *cache, struct type_expansion *type, + bool recursive); + +static void type_expand_child(struct die *cache, struct type_expansion *type, + bool recursive) +{ + struct type_expansion child; + char *name; + + name = get_type_name(cache); + if (!name) { + __type_expand(cache, type, recursive); + return; + } + + if (recursive && !__cache_was_expanded(&expansion_cache, cache->addr)) { + __cache_mark_expanded(&expansion_cache, cache->addr); + type_expansion_init(&child); + __type_expand(cache, &child, true); + type_map_add(name, &child); + type_expansion_free(&child); + } + + type_expansion_append(type, name, name); +} + +static void __type_expand(struct die *cache, struct type_expansion *type, + bool recursive) +{ + struct die_fragment *df; + struct die *child; + + list_for_each_entry(df, &cache->fragments, list) { + switch (df->type) { + case FRAGMENT_STRING: + type_expansion_append(type, df->data.str, NULL); + break; + case FRAGMENT_DIE: + /* Use a complete die_map expansion if available */ + if (__die_map_get(df->data.addr, DIE_COMPLETE, + &child) && + __die_map_get(df->data.addr, DIE_UNEXPANDED, + &child)) + error("unknown child: %" PRIxPTR, + df->data.addr); + + type_expand_child(child, type, recursive); + break; + case FRAGMENT_LINEBREAK: + /* + * Keep whitespace in the symtypes format, but avoid + * repeated spaces. + */ + if (list_is_last(&df->list, &cache->fragments) || + list_next_entry(df, list)->type != + FRAGMENT_LINEBREAK) + type_expansion_append(type, " ", NULL); + break; + default: + error("empty die_fragment in %p", cache); + } + } +} + +static void type_expand(struct die *cache, struct type_expansion *type, + bool recursive) +{ + type_expansion_init(type); + __type_expand(cache, type, recursive); + cache_free(&expansion_cache); +} + +static void expand_type(struct die *cache, void *arg) +{ + struct type_expansion type; + char *name; + + if (cache->mapped) + return; + + cache->mapped = true; + + /* + * Skip unexpanded die_map entries if there's a complete + * expansion available for this DIE. + */ + if (cache->state == DIE_UNEXPANDED && + !__die_map_get(cache->addr, DIE_COMPLETE, &cache)) { + if (cache->mapped) + return; + + cache->mapped = true; + } + + name = get_type_name(cache); + if (!name) + return; + + debug("%s", name); + type_expand(cache, &type, true); + type_map_add(name, &type); + + type_expansion_free(&type); + free(name); +} + +static void expand_symbol(struct symbol *sym, void *arg) +{ + struct type_expansion type; + struct version version; + struct die *cache; + + /* + * No need to expand again unless we want a symtypes file entry + * for the symbol. Note that this means `sym` has the same address + * as another symbol that was already processed. + */ + if (!symtypes && sym->state == SYMBOL_PROCESSED) + return; + + if (__die_map_get(sym->die_addr, DIE_SYMBOL, &cache)) + return; /* We'll warn about missing CRCs later. */ + + type_expand(cache, &type, false); + + /* If the symbol already has a version, don't calculate it again. */ + if (sym->state != SYMBOL_PROCESSED) { + calculate_version(&version, &type.expanded); + symbol_set_crc(sym, version.crc); + debug("%s = %lx", sym->name, version.crc); + + if (dump_versions) { + checkp(fputs(sym->name, stderr)); + checkp(fputs(" ", stderr)); + type_list_write(&version.type.expanded, stderr); + checkp(fputs("\n", stderr)); + } + + version_free(&version); + } + + /* These aren't needed in type_map unless we want a symtypes file. */ + if (symtypes) + type_map_add(sym->name, &type); + + type_expansion_free(&type); +} + +void generate_symtypes_and_versions(FILE *file) +{ + cache_init(&expansion_cache); + + /* + * die_map processing: + * + * 1. die_map contains all types referenced in exported symbol + * signatures, but can contain duplicates just like the original + * DWARF, and some references may not be fully expanded depending + * on how far we processed the DIE tree for that specific symbol. + * + * For each die_map entry, find the longest available expansion, + * and add it to type_map. + */ + die_map_for_each(expand_type, NULL); + + /* + * 2. For each exported symbol, expand the die_map type, and use + * type_map expansions to calculate a symbol version from the + * fully expanded type string. + */ + symbol_for_each(expand_symbol, NULL); + + /* + * 3. If a symtypes file is requested, write type_map contents to + * the file. + */ + type_map_write(file); + type_map_free(); +} diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py index 09e1d166d8d2..aa8ea1a4dbe5 100755 --- a/scripts/generate_rust_analyzer.py +++ b/scripts/generate_rust_analyzer.py @@ -8,6 +8,7 @@ import json import logging import os import pathlib +import subprocess import sys def args_crates_cfgs(cfgs): @@ -35,8 +36,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): crates_cfgs = args_crates_cfgs(cfgs) def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=True, is_proc_macro=False): - crates_indexes[display_name] = len(crates) - crates.append({ + crate = { "display_name": display_name, "root_module": str(root_module), "is_workspace_member": is_workspace_member, @@ -47,7 +47,15 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): "env": { "RUST_MODFILE": "This is only for rust-analyzer" } - }) + } + if is_proc_macro: + proc_macro_dylib_name = subprocess.check_output( + [os.environ["RUSTC"], "--print", "file-names", "--crate-name", display_name, "--crate-type", "proc-macro", "-"], + stdin=subprocess.DEVNULL, + ).decode('utf-8').strip() + crate["proc_macro_dylib_path"] = f"{objtree}/rust/{proc_macro_dylib_name}" + crates_indexes[display_name] = len(crates) + crates.append(crate) # First, the ones in `rust/` since they are a bit special. append_crate( @@ -70,7 +78,6 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): [], is_proc_macro=True, ) - crates[-1]["proc_macro_dylib_path"] = f"{objtree}/rust/libmacros.so" append_crate( "build_error", diff --git a/scripts/genksyms/Makefile b/scripts/genksyms/Makefile index 312edccda736..4350311fb7b3 100644 --- a/scripts/genksyms/Makefile +++ b/scripts/genksyms/Makefile @@ -4,24 +4,6 @@ hostprogs-always-y += genksyms genksyms-objs := genksyms.o parse.tab.o lex.lex.o -# FIXME: fix the ambiguous grammar in parse.y and delete this hack -# -# Suppress shift/reduce, reduce/reduce conflicts warnings -# unless W=1 is specified. -# -# Just in case, run "$(YACC) --version" without suppressing stderr -# so that 'bison: not found' will be displayed if it is missing. -ifeq ($(findstring 1,$(KBUILD_EXTRA_WARN)),) - -quiet_cmd_bison_no_warn = $(quiet_cmd_bison) - cmd_bison_no_warn = $(YACC) --version >/dev/null; \ - $(cmd_bison) 2>/dev/null - -$(obj)/pars%.tab.c $(obj)/pars%.tab.h: $(src)/pars%.y FORCE - $(call if_changed,bison_no_warn) - -endif - # -I needed for generated C source to include headers in source tree HOSTCFLAGS_parse.tab.o := -I $(src) HOSTCFLAGS_lex.lex.o := -I $(src) diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index 07f9b8cfb233..8b0d7ac73dbb 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -12,18 +12,19 @@ #include <stdio.h> #include <string.h> +#include <stdint.h> #include <stdlib.h> #include <unistd.h> #include <assert.h> #include <stdarg.h> #include <getopt.h> +#include <hashtable.h> + #include "genksyms.h" /*----------------------------------------------------------------------*/ -#define HASH_BUCKETS 4096 - -static struct symbol *symtab[HASH_BUCKETS]; +static HASHTABLE_DEFINE(symbol_hashtable, 1U << 12); static FILE *debugfile; int cur_line = 1; @@ -60,7 +61,7 @@ static void print_type_name(enum symbol_type type, const char *name); /*----------------------------------------------------------------------*/ -static const unsigned int crctab32[] = { +static const uint32_t crctab32[] = { 0x00000000U, 0x77073096U, 0xee0e612cU, 0x990951baU, 0x076dc419U, 0x706af48fU, 0xe963a535U, 0x9e6495a3U, 0x0edb8832U, 0x79dcb8a4U, 0xe0d5e91eU, 0x97d2d988U, 0x09b64c2bU, 0x7eb17cbdU, 0xe7b82d07U, @@ -115,19 +116,19 @@ static const unsigned int crctab32[] = { 0x2d02ef8dU }; -static unsigned long partial_crc32_one(unsigned char c, unsigned long crc) +static uint32_t partial_crc32_one(uint8_t c, uint32_t crc) { return crctab32[(crc ^ c) & 0xff] ^ (crc >> 8); } -static unsigned long partial_crc32(const char *s, unsigned long crc) +static uint32_t partial_crc32(const char *s, uint32_t crc) { while (*s) crc = partial_crc32_one(*s++, crc); return crc; } -static unsigned long crc32(const char *s) +static uint32_t crc32(const char *s) { return partial_crc32(s, 0xffffffff) ^ 0xffffffff; } @@ -151,14 +152,14 @@ static enum symbol_type map_to_ns(enum symbol_type t) struct symbol *find_symbol(const char *name, enum symbol_type ns, int exact) { - unsigned long h = crc32(name) % HASH_BUCKETS; struct symbol *sym; - for (sym = symtab[h]; sym; sym = sym->hash_next) + hash_for_each_possible(symbol_hashtable, sym, hnode, crc32(name)) { if (map_to_ns(sym->type) == map_to_ns(ns) && strcmp(name, sym->name) == 0 && sym->is_declared) break; + } if (exact && sym && sym->type != ns) return NULL; @@ -224,64 +225,56 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, return NULL; } - h = crc32(name) % HASH_BUCKETS; - for (sym = symtab[h]; sym; sym = sym->hash_next) { - if (map_to_ns(sym->type) == map_to_ns(type) && - strcmp(name, sym->name) == 0) { - if (is_reference) - /* fall through */ ; - else if (sym->type == type && - equal_list(sym->defn, defn)) { - if (!sym->is_declared && sym->is_override) { - print_location(); - print_type_name(type, name); - fprintf(stderr, " modversion is " - "unchanged\n"); - } - sym->is_declared = 1; - return sym; - } else if (!sym->is_declared) { - if (sym->is_override && flag_preserve) { - print_location(); - fprintf(stderr, "ignoring "); - print_type_name(type, name); - fprintf(stderr, " modversion change\n"); - sym->is_declared = 1; - return sym; - } else { - status = is_unknown_symbol(sym) ? - STATUS_DEFINED : STATUS_MODIFIED; - } - } else { - error_with_pos("redefinition of %s", name); - return sym; + h = crc32(name); + hash_for_each_possible(symbol_hashtable, sym, hnode, h) { + if (map_to_ns(sym->type) != map_to_ns(type) || + strcmp(name, sym->name)) + continue; + + if (is_reference) { + break; + } else if (sym->type == type && equal_list(sym->defn, defn)) { + if (!sym->is_declared && sym->is_override) { + print_location(); + print_type_name(type, name); + fprintf(stderr, " modversion is unchanged\n"); } + sym->is_declared = 1; + } else if (sym->is_declared) { + error_with_pos("redefinition of %s", name); + } else if (sym->is_override && flag_preserve) { + print_location(); + fprintf(stderr, "ignoring "); + print_type_name(type, name); + fprintf(stderr, " modversion change\n"); + sym->is_declared = 1; + } else { + status = is_unknown_symbol(sym) ? + STATUS_DEFINED : STATUS_MODIFIED; break; } + free_list(defn, NULL); + return sym; } if (sym) { - struct symbol **psym; + hash_del(&sym->hnode); - for (psym = &symtab[h]; *psym; psym = &(*psym)->hash_next) { - if (*psym == sym) { - *psym = sym->hash_next; - break; - } - } + free_list(sym->defn, NULL); + free(sym->name); + free(sym); --nsyms; } sym = xmalloc(sizeof(*sym)); - sym->name = name; + sym->name = xstrdup(name); sym->type = type; sym->defn = defn; sym->expansion_trail = NULL; sym->visited = NULL; sym->is_extern = is_extern; - sym->hash_next = symtab[h]; - symtab[h] = sym; + hash_add(symbol_hashtable, &sym->hnode, h); sym->is_declared = !is_reference; sym->status = status; @@ -480,7 +473,7 @@ static void read_reference(FILE *f) defn = def; def = read_node(f); } - subsym = add_reference_symbol(xstrdup(sym->string), sym->tag, + subsym = add_reference_symbol(sym->string, sym->tag, defn, is_extern); subsym->is_override = is_override; free_node(sym); @@ -525,7 +518,7 @@ static void print_list(FILE * f, struct string_list *list) } } -static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc) +static uint32_t expand_and_crc_sym(struct symbol *sym, uint32_t crc) { struct string_list *list = sym->defn; struct string_list **e, **b; @@ -632,7 +625,7 @@ static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc) void export_symbol(const char *name) { struct symbol *sym; - unsigned long crc; + uint32_t crc; int has_changed = 0; sym = find_symbol(name, SYM_NORMAL, 0); @@ -680,7 +673,7 @@ void export_symbol(const char *name) if (flag_dump_defs) fputs(">\n", debugfile); - printf("#SYMVER %s 0x%08lx\n", name, crc); + printf("#SYMVER %s 0x%08lx\n", name, (unsigned long)crc); } /*----------------------------------------------------------------------*/ @@ -832,9 +825,9 @@ int main(int argc, char **argv) } if (flag_debug) { - fprintf(debugfile, "Hash table occupancy %d/%d = %g\n", - nsyms, HASH_BUCKETS, - (double)nsyms / (double)HASH_BUCKETS); + fprintf(debugfile, "Hash table occupancy %d/%zd = %g\n", + nsyms, HASH_SIZE(symbol_hashtable), + (double)nsyms / HASH_SIZE(symbol_hashtable)); } if (dumpfile) diff --git a/scripts/genksyms/genksyms.h b/scripts/genksyms/genksyms.h index 21ed2ec2d98c..0c355075f0e6 100644 --- a/scripts/genksyms/genksyms.h +++ b/scripts/genksyms/genksyms.h @@ -12,8 +12,11 @@ #ifndef MODUTILS_GENKSYMS_H #define MODUTILS_GENKSYMS_H 1 +#include <stdbool.h> #include <stdio.h> +#include <list_types.h> + enum symbol_type { SYM_NORMAL, SYM_TYPEDEF, SYM_ENUM, SYM_STRUCT, SYM_UNION, SYM_ENUM_CONST @@ -31,8 +34,8 @@ struct string_list { }; struct symbol { - struct symbol *hash_next; - const char *name; + struct hlist_node hnode; + char *name; enum symbol_type type; struct string_list *defn; struct symbol *expansion_trail; @@ -64,6 +67,8 @@ struct string_list *copy_list_range(struct string_list *start, int yylex(void); int yyparse(void); +extern bool dont_want_type_specifier; + void error_with_pos(const char *, ...) __attribute__ ((format(printf, 1, 2))); /*----------------------------------------------------------------------*/ diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l index a4d7495eaf75..22aeb57649d9 100644 --- a/scripts/genksyms/lex.l +++ b/scripts/genksyms/lex.l @@ -12,6 +12,7 @@ %{ #include <limits.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <ctype.h> @@ -50,6 +51,7 @@ MC_TOKEN ([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>) %% +u?int(8|16|32|64)x(1|2|4|8|16)_t return BUILTIN_INT_KEYW; /* Keep track of our location in the original source files. */ ^#[ \t]+{INT}[ \t]+\"[^\"\n]+\".*\n return FILENAME; @@ -113,6 +115,12 @@ MC_TOKEN ([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>) /* The second stage lexer. Here we incorporate knowledge of the state of the parser to tailor the tokens that are returned. */ +/* + * The lexer cannot distinguish whether a typedef'ed string is a TYPE or an + * IDENT. We need a hint from the parser to handle this accurately. + */ +bool dont_want_type_specifier; + int yylex(void) { @@ -207,7 +215,7 @@ repeat: goto repeat; } } - if (!suppress_type_lookup) + if (!suppress_type_lookup && !dont_want_type_specifier) { if (find_symbol(yytext, SYM_TYPEDEF, 1)) token = TYPE; @@ -431,7 +439,12 @@ fini: if (suppress_type_lookup > 0) --suppress_type_lookup; - if (dont_want_brace_phrase > 0) + + /* + * __attribute__() can be placed immediately after the 'struct' keyword. + * e.g.) struct __attribute__((__packed__)) foo { ... }; + */ + if (token != ATTRIBUTE_PHRASE && dont_want_brace_phrase > 0) --dont_want_brace_phrase; yylval = &next_node->next; diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 8e9b5e69e8f0..ee600a804fa1 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -12,6 +12,7 @@ %{ #include <assert.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include "genksyms.h" @@ -148,32 +149,45 @@ simple_declaration: current_name = NULL; } $$ = $3; + dont_want_type_specifier = false; } ; init_declarator_list_opt: - /* empty */ { $$ = NULL; } - | init_declarator_list + /* empty */ { $$ = NULL; } + | init_declarator_list { free_list(decl_spec, NULL); $$ = $1; } ; init_declarator_list: init_declarator { struct string_list *decl = *$1; *$1 = NULL; + + /* avoid sharing among multiple init_declarators */ + if (decl_spec) + decl_spec = copy_list_range(decl_spec, NULL); + add_symbol(current_name, is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern); current_name = NULL; $$ = $1; + dont_want_type_specifier = true; } - | init_declarator_list ',' init_declarator - { struct string_list *decl = *$3; - *$3 = NULL; + | init_declarator_list ',' attribute_opt init_declarator + { struct string_list *decl = *$4; + *$4 = NULL; free_list(*$2, NULL); *$2 = decl_spec; + + /* avoid sharing among multiple init_declarators */ + if (decl_spec) + decl_spec = copy_list_range(decl_spec, NULL); + add_symbol(current_name, is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern); current_name = NULL; - $$ = $3; + $$ = $4; + dont_want_type_specifier = true; } ; @@ -189,8 +203,9 @@ decl_specifier_seq_opt: ; decl_specifier_seq: - decl_specifier { decl_spec = *$1; } + attribute_opt decl_specifier { decl_spec = *$2; } | decl_specifier_seq decl_specifier { decl_spec = *$2; } + | decl_specifier_seq ATTRIBUTE_PHRASE { decl_spec = *$2; } ; decl_specifier: @@ -200,7 +215,8 @@ decl_specifier: remove_node($1); $$ = $1; } - | type_specifier + | type_specifier { dont_want_type_specifier = true; $$ = $1; } + | type_qualifier ; storage_class_specifier: @@ -213,24 +229,23 @@ storage_class_specifier: type_specifier: simple_type_specifier - | cvar_qualifier | TYPEOF_KEYW '(' parameter_declaration ')' | TYPEOF_PHRASE /* References to s/u/e's defined elsewhere. Rearrange things so that it is easier to expand the definition fully later. */ - | STRUCT_KEYW IDENT - { remove_node($1); (*$2)->tag = SYM_STRUCT; $$ = $2; } - | UNION_KEYW IDENT - { remove_node($1); (*$2)->tag = SYM_UNION; $$ = $2; } + | STRUCT_KEYW attribute_opt IDENT + { remove_node($1); (*$3)->tag = SYM_STRUCT; $$ = $3; } + | UNION_KEYW attribute_opt IDENT + { remove_node($1); (*$3)->tag = SYM_UNION; $$ = $3; } | ENUM_KEYW IDENT { remove_node($1); (*$2)->tag = SYM_ENUM; $$ = $2; } /* Full definitions of an s/u/e. Record it. */ - | STRUCT_KEYW IDENT class_body - { record_compound($1, $2, $3, SYM_STRUCT); $$ = $3; } - | UNION_KEYW IDENT class_body - { record_compound($1, $2, $3, SYM_UNION); $$ = $3; } + | STRUCT_KEYW attribute_opt IDENT class_body + { record_compound($1, $3, $4, SYM_STRUCT); $$ = $4; } + | UNION_KEYW attribute_opt IDENT class_body + { record_compound($1, $3, $4, SYM_UNION); $$ = $4; } | ENUM_KEYW IDENT enum_body { record_compound($1, $2, $3, SYM_ENUM); $$ = $3; } /* @@ -239,8 +254,8 @@ type_specifier: | ENUM_KEYW enum_body { add_symbol(NULL, SYM_ENUM, NULL, 0); $$ = $2; } /* Anonymous s/u definitions. Nothing needs doing. */ - | STRUCT_KEYW class_body { $$ = $2; } - | UNION_KEYW class_body { $$ = $2; } + | STRUCT_KEYW attribute_opt class_body { $$ = $3; } + | UNION_KEYW attribute_opt class_body { $$ = $3; } ; simple_type_specifier: @@ -260,22 +275,24 @@ simple_type_specifier: ; ptr_operator: - '*' cvar_qualifier_seq_opt + '*' type_qualifier_seq_opt { $$ = $2 ? $2 : $1; } ; -cvar_qualifier_seq_opt: +type_qualifier_seq_opt: /* empty */ { $$ = NULL; } - | cvar_qualifier_seq + | type_qualifier_seq ; -cvar_qualifier_seq: - cvar_qualifier - | cvar_qualifier_seq cvar_qualifier { $$ = $2; } +type_qualifier_seq: + type_qualifier + | ATTRIBUTE_PHRASE + | type_qualifier_seq type_qualifier { $$ = $2; } + | type_qualifier_seq ATTRIBUTE_PHRASE { $$ = $2; } ; -cvar_qualifier: - CONST_KEYW | VOLATILE_KEYW | ATTRIBUTE_PHRASE +type_qualifier: + CONST_KEYW | VOLATILE_KEYW | RESTRICT_KEYW { /* restrict has no effect in prototypes so ignore it */ remove_node($1); @@ -297,15 +314,7 @@ direct_declarator: current_name = (*$1)->string; $$ = $1; } - } - | TYPE - { if (current_name != NULL) { - error_with_pos("unexpected second declaration name"); - YYERROR; - } else { - current_name = (*$1)->string; - $$ = $1; - } + dont_want_type_specifier = false; } | direct_declarator '(' parameter_declaration_clause ')' { $$ = $4; } @@ -325,16 +334,19 @@ nested_declarator: ; direct_nested_declarator: - IDENT - | TYPE - | direct_nested_declarator '(' parameter_declaration_clause ')' + direct_nested_declarator1 + | direct_nested_declarator1 '(' parameter_declaration_clause ')' { $$ = $4; } - | direct_nested_declarator '(' error ')' + ; + +direct_nested_declarator1: + IDENT { $$ = $1; dont_want_type_specifier = false; } + | direct_nested_declarator1 '(' error ')' { $$ = $4; } - | direct_nested_declarator BRACKET_PHRASE + | direct_nested_declarator1 BRACKET_PHRASE { $$ = $2; } - | '(' nested_declarator ')' - { $$ = $3; } + | '(' attribute_opt nested_declarator ')' + { $$ = $4; } | '(' error ')' { $$ = $3; } ; @@ -352,45 +364,57 @@ parameter_declaration_list_opt: parameter_declaration_list: parameter_declaration + { $$ = $1; dont_want_type_specifier = false; } | parameter_declaration_list ',' parameter_declaration - { $$ = $3; } + { $$ = $3; dont_want_type_specifier = false; } ; parameter_declaration: - decl_specifier_seq m_abstract_declarator + decl_specifier_seq abstract_declarator_opt { $$ = $2 ? $2 : $1; } ; -m_abstract_declarator: - ptr_operator m_abstract_declarator - { $$ = $2 ? $2 : $1; } - | direct_m_abstract_declarator +abstract_declarator_opt: + /* empty */ { $$ = NULL; } + | abstract_declarator ; -direct_m_abstract_declarator: - /* empty */ { $$ = NULL; } - | IDENT +abstract_declarator: + ptr_operator + | ptr_operator abstract_declarator + { $$ = $2 ? $2 : $1; } + | direct_abstract_declarator attribute_opt + { $$ = $2; dont_want_type_specifier = false; } + ; + +direct_abstract_declarator: + direct_abstract_declarator1 + | direct_abstract_declarator1 open_paren parameter_declaration_clause ')' + { $$ = $4; } + | open_paren parameter_declaration_clause ')' + { $$ = $3; } + ; + +direct_abstract_declarator1: + IDENT { /* For version 2 checksums, we don't want to remember private parameter names. */ remove_node($1); $$ = $1; } - /* This wasn't really a typedef name but an identifier that - shadows one. */ - | TYPE - { remove_node($1); - $$ = $1; - } - | direct_m_abstract_declarator '(' parameter_declaration_clause ')' + | direct_abstract_declarator1 open_paren error ')' { $$ = $4; } - | direct_m_abstract_declarator '(' error ')' - { $$ = $4; } - | direct_m_abstract_declarator BRACKET_PHRASE + | direct_abstract_declarator1 BRACKET_PHRASE { $$ = $2; } - | '(' m_abstract_declarator ')' - { $$ = $3; } - | '(' error ')' + | open_paren attribute_opt abstract_declarator ')' + { $$ = $4; } + | open_paren error ')' { $$ = $3; } + | BRACKET_PHRASE + ; + +open_paren: + '(' { $$ = $1; dont_want_type_specifier = false; } ; function_definition: @@ -430,9 +454,9 @@ member_specification: member_declaration: decl_specifier_seq_opt member_declarator_list_opt ';' - { $$ = $3; } + { $$ = $3; dont_want_type_specifier = false; } | error ';' - { $$ = $2; } + { $$ = $2; dont_want_type_specifier = false; } ; member_declarator_list_opt: @@ -442,7 +466,9 @@ member_declarator_list_opt: member_declarator_list: member_declarator - | member_declarator_list ',' member_declarator { $$ = $3; } + { $$ = $1; dont_want_type_specifier = true; } + | member_declarator_list ',' member_declarator + { $$ = $3; dont_want_type_specifier = true; } ; member_declarator: @@ -457,7 +483,7 @@ member_bitfield_declarator: attribute_opt: /* empty */ { $$ = NULL; } - | attribute_opt ATTRIBUTE_PHRASE + | attribute_opt ATTRIBUTE_PHRASE { $$ = $2; } ; enum_body: @@ -472,12 +498,12 @@ enumerator_list: enumerator: IDENT { - const char *name = strdup((*$1)->string); + const char *name = (*$1)->string; add_symbol(name, SYM_ENUM_CONST, NULL, 0); } | IDENT '=' EXPRESSION_PHRASE { - const char *name = strdup((*$1)->string); + const char *name = (*$1)->string; struct string_list *expr = copy_list_range(*$3, *$2); add_symbol(name, SYM_ENUM_CONST, expr, 0); } diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index a0a0be38cbdc..fb50bd4f4103 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -105,9 +105,11 @@ configfiles = $(wildcard $(srctree)/kernel/configs/$(1) $(srctree)/arch/$(SRCARC all-config-fragments = $(call configfiles,*.config) config-fragments = $(call configfiles,$@) +cmd_merge_fragments = $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments) + %.config: $(obj)/conf $(if $(config-fragments),, $(error $@ fragment does not exists on this architecture)) - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments) + $(call cmd,merge_fragments) $(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig PHONY += tinyconfig diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 4286d5e7f95d..3b55e7a4131d 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -360,10 +360,12 @@ int conf_read_simple(const char *name, int def) *p = '\0'; - in = zconf_fopen(env); + name = env; + + in = zconf_fopen(name); if (in) { conf_message("using defaults found in %s", - env); + name); goto load; } diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index 6c92ef1e16ef..eaa465b0ccf9 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -1464,8 +1464,8 @@ void ConfigMainWindow::loadConfig(void) { QString str; - str = QFileDialog::getOpenFileName(this, "", configname); - if (str.isNull()) + str = QFileDialog::getOpenFileName(this, QString(), configname); + if (str.isEmpty()) return; if (conf_read(str.toLocal8Bit().constData())) @@ -1491,8 +1491,8 @@ void ConfigMainWindow::saveConfigAs(void) { QString str; - str = QFileDialog::getSaveFileName(this, "", configname); - if (str.isNull()) + str = QFileDialog::getSaveFileName(this, QString(), configname); + if (str.isEmpty()) return; if (conf_write(str.toLocal8Bit().constData())) { diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 89b84bf8e21f..7beb59dec5a0 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -388,6 +388,7 @@ static void sym_warn_unmet_dep(const struct symbol *sym) " Selected by [m]:\n"); fputs(str_get(&gs), stderr); + str_free(&gs); sym_warnings++; } diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 4ee843d3600e..e57c5e989a0a 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -2085,7 +2085,7 @@ sub process_name($$) { # Look for foo() or static void foo() - description; or misspelt # identifier elsif (/^$decl_start$fn_type?(\w+)\s*$parenthesis?\s*$decl_end?$/ || - /^$decl_start$fn_type?(\w+.*)$parenthesis?\s*$decl_end$/) { + /^$decl_start$fn_type?(\w+[^-:]*)$parenthesis?\s*$decl_end$/) { $identifier = $1; $decl_type = 'function'; $identifier =~ s/^define\s+//; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index d853ddb3b28c..56a077d204cf 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -283,7 +283,11 @@ vmlinux_link vmlinux # fill in BTF IDs if is_enabled CONFIG_DEBUG_INFO_BTF; then info BTFIDS vmlinux - ${RESOLVE_BTFIDS} vmlinux + RESOLVE_BTFIDS_ARGS="" + if is_enabled CONFIG_WERROR; then + RESOLVE_BTFIDS_ARGS=" --fatal_warnings " + fi + ${RESOLVE_BTFIDS} ${RESOLVE_BTFIDS_ARGS} vmlinux fi mksysmap vmlinux System.map diff --git a/scripts/mksysmap b/scripts/mksysmap index c12723a04655..3accbdb269ac 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -26,7 +26,7 @@ # (do not forget a space before each pattern) # local symbols for ARM, MIPS, etc. -/ \\$/d +/ \$/d # local labels, .LBB, .Ltmpxxx, .L__unnamed_xx, .LASANPC, etc. / \.L/d @@ -39,7 +39,7 @@ / __pi_\.L/d # arm64 local symbols in non-VHE KVM namespace -/ __kvm_nvhe_\\$/d +/ __kvm_nvhe_\$/d / __kvm_nvhe_\.L/d # lld arm/aarch64/mips thunks diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index 9c7b404defbd..d3d00e85edf7 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -237,7 +237,6 @@ int main(void) DEVID(typec_device_id); DEVID_FIELD(typec_device_id, svid); - DEVID_FIELD(typec_device_id, mode); DEVID(tee_client_device_id); DEVID_FIELD(tee_client_device_id, uuid); diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 5b5745f00eb3..00586119a25b 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -132,7 +132,8 @@ struct devtable { * based at address m. */ #define DEF_FIELD(m, devid, f) \ - typeof(((struct devid *)0)->f) f = TO_NATIVE(*(typeof(f) *)((m) + OFF_##devid##_##f)) + typeof(((struct devid *)0)->f) f = \ + get_unaligned_native((typeof(f) *)((m) + OFF_##devid##_##f)) /* Define a variable f that holds the address of field f of struct devid * based at address m. Due to the way typeof works, for a field of type @@ -600,7 +601,7 @@ static void do_pnp_card_entry(struct module *mod, void *symval) static void do_pcmcia_entry(struct module *mod, void *symval) { char alias[256] = {}; - unsigned int i; + DEF_FIELD(symval, pcmcia_device_id, match_flags); DEF_FIELD(symval, pcmcia_device_id, manf_id); DEF_FIELD(symval, pcmcia_device_id, card_id); @@ -609,10 +610,6 @@ static void do_pcmcia_entry(struct module *mod, void *symval) DEF_FIELD(symval, pcmcia_device_id, device_no); DEF_FIELD_ADDR(symval, pcmcia_device_id, prod_id_hash); - for (i=0; i<4; i++) { - (*prod_id_hash)[i] = TO_NATIVE((*prod_id_hash)[i]); - } - ADD(alias, "m", match_flags & PCMCIA_DEV_ID_MATCH_MANF_ID, manf_id); ADD(alias, "c", match_flags & PCMCIA_DEV_ID_MATCH_CARD_ID, @@ -623,10 +620,14 @@ static void do_pcmcia_entry(struct module *mod, void *symval) function); ADD(alias, "pfn", match_flags & PCMCIA_DEV_ID_MATCH_DEVICE_NO, device_no); - ADD(alias, "pa", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID1, (*prod_id_hash)[0]); - ADD(alias, "pb", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID2, (*prod_id_hash)[1]); - ADD(alias, "pc", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID3, (*prod_id_hash)[2]); - ADD(alias, "pd", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID4, (*prod_id_hash)[3]); + ADD(alias, "pa", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID1, + get_unaligned_native(*prod_id_hash + 0)); + ADD(alias, "pb", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID2, + get_unaligned_native(*prod_id_hash + 1)); + ADD(alias, "pc", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID3, + get_unaligned_native(*prod_id_hash + 2)); + ADD(alias, "pd", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID4, + get_unaligned_native(*prod_id_hash + 3)); module_alias_printf(mod, true, "pcmcia:%s", alias); } @@ -654,10 +655,9 @@ static void do_input(char *alias, { unsigned int i; - for (i = min / BITS_PER_LONG; i < max / BITS_PER_LONG + 1; i++) - arr[i] = TO_NATIVE(arr[i]); - for (i = min; i < max; i++) - if (arr[i / BITS_PER_LONG] & (1ULL << (i%BITS_PER_LONG))) + for (i = min; i <= max; i++) + if (get_unaligned_native(arr + i / BITS_PER_LONG) & + (1ULL << (i % BITS_PER_LONG))) sprintf(alias + strlen(alias), "%X,*", i); } @@ -812,15 +812,13 @@ static void do_virtio_entry(struct module *mod, void *symval) * Each byte of the guid will be represented by two hex characters * in the name. */ - static void do_vmbus_entry(struct module *mod, void *symval) { - int i; DEF_FIELD_ADDR(symval, hv_vmbus_device_id, guid); - char guid_name[(sizeof(*guid) + 1) * 2]; + char guid_name[sizeof(*guid) * 2 + 1]; - for (i = 0; i < (sizeof(*guid) * 2); i += 2) - sprintf(&guid_name[i], "%02x", TO_NATIVE((guid->b)[i/2])); + for (int i = 0; i < sizeof(*guid); i++) + sprintf(&guid_name[i * 2], "%02x", guid->b[i]); module_alias_printf(mod, false, "vmbus:%s", guid_name); } @@ -1221,17 +1219,12 @@ static void do_tbsvc_entry(struct module *mod, void *symval) module_alias_printf(mod, true, "tbsvc:%s", alias); } -/* Looks like: typec:idNmN */ +/* Looks like: typec:idN */ static void do_typec_entry(struct module *mod, void *symval) { - char alias[256] = {}; - DEF_FIELD(symval, typec_device_id, svid); - DEF_FIELD(symval, typec_device_id, mode); - ADD(alias, "m", mode != TYPEC_ANY_MODE, mode); - - module_alias_printf(mod, false, "typec:id%04X%s", svid, alias); + module_alias_printf(mod, false, "typec:id%04X", svid); } /* Looks like: tee:uuid */ diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index fb787a5715f5..e18ae7dc8140 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -33,6 +33,10 @@ static bool module_enabled; static bool modversions; /* Is CONFIG_MODULE_SRCVERSION_ALL set? */ static bool all_versions; +/* Is CONFIG_BASIC_MODVERSIONS set? */ +static bool basic_modversions; +/* Is CONFIG_EXTENDED_MODVERSIONS set? */ +static bool extended_modversions; /* If we are modposting external module set to 1 */ static bool external_module; /* Only warn about unresolved symbols */ @@ -155,12 +159,13 @@ char *get_line(char **stringp) /* A list of all modules we processed */ LIST_HEAD(modules); -static struct module *find_module(const char *modname) +static struct module *find_module(const char *filename, const char *modname) { struct module *mod; list_for_each_entry(mod, &modules, list) { - if (strcmp(mod->name, modname) == 0) + if (!strcmp(mod->dump_file, filename) && + !strcmp(mod->name, modname)) return mod; } return NULL; @@ -1137,9 +1142,9 @@ static Elf_Addr addend_386_rel(uint32_t *location, unsigned int r_type) { switch (r_type) { case R_386_32: - return TO_NATIVE(*location); + return get_unaligned_native(location); case R_386_PC32: - return TO_NATIVE(*location) + 4; + return get_unaligned_native(location) + 4; } return (Elf_Addr)(-1); @@ -1160,24 +1165,24 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) switch (r_type) { case R_ARM_ABS32: case R_ARM_REL32: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); return inst + sym->st_value; case R_ARM_MOVW_ABS_NC: case R_ARM_MOVT_ABS: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); offset = sign_extend32(((inst & 0xf0000) >> 4) | (inst & 0xfff), 15); return offset + sym->st_value; case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); offset = sign_extend32((inst & 0x00ffffff) << 2, 25); return offset + sym->st_value + 8; case R_ARM_THM_MOVW_ABS_NC: case R_ARM_THM_MOVT_ABS: - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); offset = sign_extend32(((upper & 0x000f) << 12) | ((upper & 0x0400) << 1) | ((lower & 0x7000) >> 4) | @@ -1194,8 +1199,8 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) * imm11 = lower[10:0] * imm32 = SignExtend(S:J2:J1:imm6:imm11:'0') */ - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); sign = (upper >> 10) & 1; j1 = (lower >> 13) & 1; @@ -1218,8 +1223,8 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) * I2 = NOT(J2 XOR S) * imm32 = SignExtend(S:I1:I2:imm10:imm11:'0') */ - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); sign = (upper >> 10) & 1; j1 = (lower >> 13) & 1; @@ -1240,7 +1245,7 @@ static Elf_Addr addend_mips_rel(uint32_t *location, unsigned int r_type) { uint32_t inst; - inst = TO_NATIVE(*location); + inst = get_unaligned_native(location); switch (r_type) { case R_MIPS_LO16: return inst & 0xffff; @@ -1804,6 +1809,49 @@ static void add_exported_symbols(struct buffer *buf, struct module *mod) } } +/** + * Record CRCs for unresolved symbols, supporting long names + */ +static void add_extended_versions(struct buffer *b, struct module *mod) +{ + struct symbol *s; + + if (!extended_modversions) + return; + + buf_printf(b, "\n"); + buf_printf(b, "static const u32 ____version_ext_crcs[]\n"); + buf_printf(b, "__used __section(\"__version_ext_crcs\") = {\n"); + list_for_each_entry(s, &mod->unresolved_symbols, list) { + if (!s->module) + continue; + if (!s->crc_valid) { + warn("\"%s\" [%s.ko] has no CRC!\n", + s->name, mod->name); + continue; + } + buf_printf(b, "\t0x%08x,\n", s->crc); + } + buf_printf(b, "};\n"); + + buf_printf(b, "static const char ____version_ext_names[]\n"); + buf_printf(b, "__used __section(\"__version_ext_names\") =\n"); + list_for_each_entry(s, &mod->unresolved_symbols, list) { + if (!s->module) + continue; + if (!s->crc_valid) + /* + * We already warned on this when producing the crc + * table. + * We need to skip its name too, as the indexes in + * both tables need to align. + */ + continue; + buf_printf(b, "\t\"%s\\0\"\n", s->name); + } + buf_printf(b, ";\n"); +} + /** * Record CRCs for unresolved symbols **/ @@ -1811,7 +1859,7 @@ static void add_versions(struct buffer *b, struct module *mod) { struct symbol *s; - if (!modversions) + if (!basic_modversions) return; buf_printf(b, "\n"); @@ -1827,11 +1875,16 @@ static void add_versions(struct buffer *b, struct module *mod) continue; } if (strlen(s->name) >= MODULE_NAME_LEN) { - error("too long symbol \"%s\" [%s.ko]\n", - s->name, mod->name); - break; + if (extended_modversions) { + /* this symbol will only be in the extended info */ + continue; + } else { + error("too long symbol \"%s\" [%s.ko]\n", + s->name, mod->name); + break; + } } - buf_printf(b, "\t{ %#8x, \"%s\" },\n", + buf_printf(b, "\t{ 0x%08x, \"%s\" },\n", s->crc, s->name); } @@ -1960,6 +2013,7 @@ static void write_mod_c_file(struct module *mod) add_header(&buf, mod); add_exported_symbols(&buf, mod); add_versions(&buf, mod); + add_extended_versions(&buf, mod); add_depends(&buf, mod); buf_printf(&buf, "\n"); @@ -2030,10 +2084,10 @@ static void read_dump(const char *fname) continue; } - mod = find_module(modname); + mod = find_module(fname, modname); if (!mod) { mod = new_module(modname, strlen(modname)); - mod->from_dump = true; + mod->dump_file = fname; } s = sym_add_exported(symname, mod, gpl_only, namespace); sym_set_crc(s, crc); @@ -2052,7 +2106,7 @@ static void write_dump(const char *fname) struct symbol *sym; list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; list_for_each_entry(sym, &mod->exported_symbols, list) { if (trim_unused_exports && !sym->used) @@ -2076,7 +2130,7 @@ static void write_namespace_deps_files(const char *fname) list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || list_empty(&mod->missing_namespaces)) + if (mod->dump_file || list_empty(&mod->missing_namespaces)) continue; buf_printf(&ns_deps_buf, "%s.ko:", mod->name); @@ -2125,7 +2179,7 @@ int main(int argc, char **argv) LIST_HEAD(dump_lists); struct dump_list *dl, *dl2; - while ((opt = getopt(argc, argv, "ei:MmnT:to:au:WwENd:")) != -1) { + while ((opt = getopt(argc, argv, "ei:MmnT:to:au:WwENd:xb")) != -1) { switch (opt) { case 'e': external_module = true; @@ -2174,6 +2228,12 @@ int main(int argc, char **argv) case 'd': missing_namespace_deps = optarg; break; + case 'b': + basic_modversions = true; + break; + case 'x': + extended_modversions = true; + break; default: exit(1); } @@ -2194,7 +2254,7 @@ int main(int argc, char **argv) read_symbols_from_files(files_source); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || mod->is_vmlinux) + if (mod->dump_file || mod->is_vmlinux) continue; check_modname_len(mod); @@ -2205,7 +2265,7 @@ int main(int argc, char **argv) handle_white_list_exports(unused_exports_white_list); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; if (mod->is_vmlinux) diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 49848fcbe2a1..ffd0a52a606e 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -65,6 +65,20 @@ #define TO_NATIVE(x) \ (target_is_big_endian == host_is_big_endian ? x : bswap(x)) +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __attribute__((__packed__)) *__pptr = \ + (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) + +#define get_unaligned_native(ptr) \ +({ \ + typeof(*(ptr)) _val = get_unaligned(ptr); \ + TO_NATIVE(_val); \ +}) + #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #define strstarts(str, prefix) (strncmp(str, prefix, strlen(prefix)) == 0) @@ -95,14 +109,15 @@ struct module_alias { /** * struct module - represent a module (vmlinux or *.ko) * + * @dump_file: path to the .symvers file if loaded from a file * @aliases: list head for module_aliases */ struct module { struct list_head list; struct list_head exported_symbols; struct list_head unresolved_symbols; + const char *dump_file; bool is_gpl_compatible; - bool from_dump; /* true if module was loaded from *.symvers */ bool is_vmlinux; bool seen; bool has_init; diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index f83493838cf9..0cf3a55b05e1 100644 --- a/scripts/package/PKGBUILD +++ b/scripts/package/PKGBUILD @@ -22,7 +22,6 @@ license=(GPL-2.0-only) makedepends=( bc bison - cpio flex gettext kmod @@ -103,7 +102,7 @@ _package-headers() { _package-api-headers() { pkgdesc="Kernel headers sanitized for use in userspace" - provides=(linux-api-headers) + provides=(linux-api-headers="${pkgver}") conflicts=(linux-api-headers) _prologue diff --git a/scripts/package/builddeb b/scripts/package/builddeb index fb686fd3266f..3627ca227e5a 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -5,10 +5,12 @@ # # Simple script to generate a deb package for a Linux kernel. All the # complexity of what to do with a kernel after it is installed or removed -# is left to other scripts and packages: they can install scripts in the -# /etc/kernel/{pre,post}{inst,rm}.d/ directories (or an alternative location -# specified in KDEB_HOOKDIR) that will be called on package install and -# removal. +# is left to other scripts and packages. Scripts can be placed into the +# preinst, postinst, prerm and postrm directories in /etc/kernel or +# /usr/share/kernel. A different list of search directories can be given +# via KDEB_HOOKDIR. Scripts in directories earlier in the list will +# override scripts of the same name in later directories. The script will +# be called on package installation and removal. set -eu @@ -63,15 +65,19 @@ install_linux_image () { esac cp "$(${MAKE} -s -f ${srctree}/Makefile image_name)" "${pdir}/${installed_image_path}" + if [ "${ARCH}" != um ]; then + install_maint_scripts "${pdir}" + fi +} + +install_maint_scripts () { # Install the maintainer scripts # Note: hook scripts under /etc/kernel are also executed by official Debian # kernel packages, as well as kernel packages built using make-kpkg. # make-kpkg sets $INITRD to indicate whether an initramfs is wanted, and # so do we; recent versions of dracut and initramfs-tools will obey this. - debhookdir=${KDEB_HOOKDIR:-/etc/kernel} + debhookdir=${KDEB_HOOKDIR:-/etc/kernel /usr/share/kernel} for script in postinst postrm preinst prerm; do - mkdir -p "${pdir}${debhookdir}/${script}.d" - mkdir -p "${pdir}/DEBIAN" cat <<-EOF > "${pdir}/DEBIAN/${script}" #!/bin/sh @@ -84,7 +90,15 @@ install_linux_image () { # Tell initramfs builder whether it's wanted export INITRD=$(if_enabled_echo CONFIG_BLK_DEV_INITRD Yes No) - test -d ${debhookdir}/${script}.d && run-parts --arg="${KERNELRELEASE}" --arg="/${installed_image_path}" ${debhookdir}/${script}.d + # run-parts will error out if one of its directory arguments does not + # exist, so filter the list of hook directories accordingly. + hookdirs= + for dir in ${debhookdir}; do + test -d "\$dir/${script}.d" || continue + hookdirs="\$hookdirs \$dir/${script}.d" + done + hookdirs="\${hookdirs# }" + test -n "\$hookdirs" && run-parts --arg="${KERNELRELEASE}" --arg="/${installed_image_path}" \$hookdirs exit 0 EOF chmod 755 "${pdir}/DEBIAN/${script}" diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index d3c5b104c063..bb6e23c1174e 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -49,17 +49,10 @@ mkdir -p "${destdir}" # This caters to host programs that participate in Kbuild. objtool and # resolve_btfids are out of scope. if [ "${CC}" != "${HOSTCC}" ]; then - echo "Rebuilding host programs with ${CC}..." - - # This leverages external module building. - # - Clear sub_make_done to allow the top-level Makefile to redo sub-make. - # - Filter out --no-print-directory to print "Entering directory" logs - # when Make changes the working directory. - unset sub_make_done - MAKEFLAGS=$(echo "${MAKEFLAGS}" | sed s/--no-print-directory//) - - cat <<-'EOF' > "${destdir}/Kbuild" - subdir-y := scripts + cat "${destdir}/scripts/Makefile" - <<-'EOF' > "${destdir}/scripts/Kbuild" + subdir-y += basic + hostprogs-always-y += mod/modpost + mod/modpost-objs := $(addprefix mod/, modpost.o file2alias.o sumversion.o symsearch.o) EOF # HOSTCXX is not overridden. The C++ compiler is used to build: @@ -67,20 +60,12 @@ if [ "${CC}" != "${HOSTCC}" ]; then # - GCC plugins, which will not work on the installed system even after # being rebuilt. # - # Use the single-target build to avoid the modpost invocation, which - # would overwrite Module.symvers. - "${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/ + # Clear VPATH and srcroot because the source files reside in the output + # directory. + # shellcheck disable=SC2016 # $(MAKE), $(CC), and $(build) will be expanded by Make + "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC=$(CC) VPATH= srcroot=. $(build)='"${destdir}"/scripts - cat <<-'EOF' > "${destdir}/scripts/Kbuild" - subdir-y := basic - hostprogs-always-y := mod/modpost - mod/modpost-objs := $(addprefix mod/, modpost.o file2alias.o sumversion.o symsearch.o) - EOF - - # Run once again to rebuild scripts/basic/ and scripts/mod/modpost. - "${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/ - - rm -f "${destdir}/Kbuild" "${destdir}/scripts/Kbuild" + rm -f "${destdir}/scripts/Kbuild" fi find "${destdir}" \( -name '.*.cmd' -o -name '*.o' \) -delete diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 4ffcc70f8e31..b6dd98ca860b 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -70,6 +70,13 @@ set_debarch() { debarch=sh4$(if_enabled_echo CONFIG_CPU_BIG_ENDIAN eb) fi ;; + um) + if is_enabled CONFIG_64BIT; then + debarch=amd64 + else + debarch=i386 + fi + ;; esac if [ -z "$debarch" ]; then debarch=$(dpkg-architecture -qDEB_HOST_ARCH) @@ -198,7 +205,7 @@ Priority: optional Maintainer: $maintainer Rules-Requires-Root: no Build-Depends: debhelper-compat (= 12) -Build-Depends-Arch: bc, bison, cpio, flex, +Build-Depends-Arch: bc, bison, flex, gcc-${host_gnu} <!pkg.${sourcename}.nokernelheaders>, kmod, libelf-dev:native, libssl-dev:native, libssl-dev <!pkg.${sourcename}.nokernelheaders>, diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh index 93c0ef7fb3fb..d2323de0692c 100755 --- a/scripts/rust_is_available.sh +++ b/scripts/rust_is_available.sh @@ -123,8 +123,10 @@ fi # Non-stable and distributions' versions may have a version suffix, e.g. `-dev`. # # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 -# (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when -# the minimum version is upgraded past that (0.69.1 already fixed the issue). +# (https://github.com/rust-lang/rust-bindgen/pull/2678) and 0.71.0 +# (https://github.com/rust-lang/rust-bindgen/pull/3040). It can be removed when +# the minimum version is upgraded past the latter (0.69.1 and 0.71.1 both fixed +# the issue). rust_bindings_generator_output=$( \ LC_ALL=C "$BINDGEN" --version workaround-for-0.69.0 2>/dev/null ) || rust_bindings_generator_code=$? diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 83cdb843d92f..9f41575afd7a 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -64,14 +64,204 @@ #define EM_LOONGARCH 258 #endif +typedef union { + Elf32_Ehdr e32; + Elf64_Ehdr e64; +} Elf_Ehdr; + +typedef union { + Elf32_Shdr e32; + Elf64_Shdr e64; +} Elf_Shdr; + +typedef union { + Elf32_Sym e32; + Elf64_Sym e64; +} Elf_Sym; + static uint32_t (*r)(const uint32_t *); static uint16_t (*r2)(const uint16_t *); static uint64_t (*r8)(const uint64_t *); static void (*w)(uint32_t, uint32_t *); -static void (*w2)(uint16_t, uint16_t *); -static void (*w8)(uint64_t, uint64_t *); typedef void (*table_sort_t)(char *, int); +static struct elf_funcs { + int (*compare_extable)(const void *a, const void *b); + uint64_t (*ehdr_shoff)(Elf_Ehdr *ehdr); + uint16_t (*ehdr_shstrndx)(Elf_Ehdr *ehdr); + uint16_t (*ehdr_shentsize)(Elf_Ehdr *ehdr); + uint16_t (*ehdr_shnum)(Elf_Ehdr *ehdr); + uint64_t (*shdr_addr)(Elf_Shdr *shdr); + uint64_t (*shdr_offset)(Elf_Shdr *shdr); + uint64_t (*shdr_size)(Elf_Shdr *shdr); + uint64_t (*shdr_entsize)(Elf_Shdr *shdr); + uint32_t (*shdr_link)(Elf_Shdr *shdr); + uint32_t (*shdr_name)(Elf_Shdr *shdr); + uint32_t (*shdr_type)(Elf_Shdr *shdr); + uint8_t (*sym_type)(Elf_Sym *sym); + uint32_t (*sym_name)(Elf_Sym *sym); + uint64_t (*sym_value)(Elf_Sym *sym); + uint16_t (*sym_shndx)(Elf_Sym *sym); +} e; + +static uint64_t ehdr64_shoff(Elf_Ehdr *ehdr) +{ + return r8(&ehdr->e64.e_shoff); +} + +static uint64_t ehdr32_shoff(Elf_Ehdr *ehdr) +{ + return r(&ehdr->e32.e_shoff); +} + +static uint64_t ehdr_shoff(Elf_Ehdr *ehdr) +{ + return e.ehdr_shoff(ehdr); +} + +#define EHDR_HALF(fn_name) \ +static uint16_t ehdr64_##fn_name(Elf_Ehdr *ehdr) \ +{ \ + return r2(&ehdr->e64.e_##fn_name); \ +} \ + \ +static uint16_t ehdr32_##fn_name(Elf_Ehdr *ehdr) \ +{ \ + return r2(&ehdr->e32.e_##fn_name); \ +} \ + \ +static uint16_t ehdr_##fn_name(Elf_Ehdr *ehdr) \ +{ \ + return e.ehdr_##fn_name(ehdr); \ +} + +EHDR_HALF(shentsize) +EHDR_HALF(shstrndx) +EHDR_HALF(shnum) + +#define SHDR_WORD(fn_name) \ +static uint32_t shdr64_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e64.sh_##fn_name); \ +} \ + \ +static uint32_t shdr32_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e32.sh_##fn_name); \ +} \ + \ +static uint32_t shdr_##fn_name(Elf_Shdr *shdr) \ +{ \ + return e.shdr_##fn_name(shdr); \ +} + +#define SHDR_ADDR(fn_name) \ +static uint64_t shdr64_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r8(&shdr->e64.sh_##fn_name); \ +} \ + \ +static uint64_t shdr32_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e32.sh_##fn_name); \ +} \ + \ +static uint64_t shdr_##fn_name(Elf_Shdr *shdr) \ +{ \ + return e.shdr_##fn_name(shdr); \ +} + +#define SHDR_WORD(fn_name) \ +static uint32_t shdr64_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e64.sh_##fn_name); \ +} \ + \ +static uint32_t shdr32_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e32.sh_##fn_name); \ +} \ +static uint32_t shdr_##fn_name(Elf_Shdr *shdr) \ +{ \ + return e.shdr_##fn_name(shdr); \ +} + +SHDR_ADDR(addr) +SHDR_ADDR(offset) +SHDR_ADDR(size) +SHDR_ADDR(entsize) + +SHDR_WORD(link) +SHDR_WORD(name) +SHDR_WORD(type) + +#define SYM_ADDR(fn_name) \ +static uint64_t sym64_##fn_name(Elf_Sym *sym) \ +{ \ + return r8(&sym->e64.st_##fn_name); \ +} \ + \ +static uint64_t sym32_##fn_name(Elf_Sym *sym) \ +{ \ + return r(&sym->e32.st_##fn_name); \ +} \ + \ +static uint64_t sym_##fn_name(Elf_Sym *sym) \ +{ \ + return e.sym_##fn_name(sym); \ +} + +#define SYM_WORD(fn_name) \ +static uint32_t sym64_##fn_name(Elf_Sym *sym) \ +{ \ + return r(&sym->e64.st_##fn_name); \ +} \ + \ +static uint32_t sym32_##fn_name(Elf_Sym *sym) \ +{ \ + return r(&sym->e32.st_##fn_name); \ +} \ + \ +static uint32_t sym_##fn_name(Elf_Sym *sym) \ +{ \ + return e.sym_##fn_name(sym); \ +} + +#define SYM_HALF(fn_name) \ +static uint16_t sym64_##fn_name(Elf_Sym *sym) \ +{ \ + return r2(&sym->e64.st_##fn_name); \ +} \ + \ +static uint16_t sym32_##fn_name(Elf_Sym *sym) \ +{ \ + return r2(&sym->e32.st_##fn_name); \ +} \ + \ +static uint16_t sym_##fn_name(Elf_Sym *sym) \ +{ \ + return e.sym_##fn_name(sym); \ +} + +static uint8_t sym64_type(Elf_Sym *sym) +{ + return ELF64_ST_TYPE(sym->e64.st_info); +} + +static uint8_t sym32_type(Elf_Sym *sym) +{ + return ELF32_ST_TYPE(sym->e32.st_info); +} + +static uint8_t sym_type(Elf_Sym *sym) +{ + return e.sym_type(sym); +} + +SYM_ADDR(value) +SYM_WORD(name) +SYM_HALF(shndx) + /* * Get the whole file as a programming convenience in order to avoid * malloc+lseek+read+free of many pieces. If successful, then mmap @@ -146,31 +336,11 @@ static void wbe(uint32_t val, uint32_t *x) put_unaligned_be32(val, x); } -static void w2be(uint16_t val, uint16_t *x) -{ - put_unaligned_be16(val, x); -} - -static void w8be(uint64_t val, uint64_t *x) -{ - put_unaligned_be64(val, x); -} - static void wle(uint32_t val, uint32_t *x) { put_unaligned_le32(val, x); } -static void w2le(uint16_t val, uint16_t *x) -{ - put_unaligned_le16(val, x); -} - -static void w8le(uint64_t val, uint64_t *x) -{ - put_unaligned_le64(val, x); -} - /* * Move reserved section indices SHN_LORESERVE..SHN_HIRESERVE out of * the way to -256..-1, to avoid conflicting with real section @@ -195,10 +365,430 @@ static inline unsigned int get_secindex(unsigned int shndx, return r(&symtab_shndx_start[sym_offs]); } -/* 32 bit and 64 bit are very similar */ -#include "sorttable.h" -#define SORTTABLE_64 -#include "sorttable.h" +static int compare_extable_32(const void *a, const void *b) +{ + Elf32_Addr av = r(a); + Elf32_Addr bv = r(b); + + if (av < bv) + return -1; + return av > bv; +} + +static int compare_extable_64(const void *a, const void *b) +{ + Elf64_Addr av = r8(a); + Elf64_Addr bv = r8(b); + + if (av < bv) + return -1; + return av > bv; +} + +static int compare_extable(const void *a, const void *b) +{ + return e.compare_extable(a, b); +} + +static inline void *get_index(void *start, int entsize, int index) +{ + return start + (entsize * index); +} + +static int extable_ent_size; +static int long_size; + + +#ifdef UNWINDER_ORC_ENABLED +/* ORC unwinder only support X86_64 */ +#include <asm/orc_types.h> + +#define ERRSTR_MAXSZ 256 + +static char g_err[ERRSTR_MAXSZ]; +static int *g_orc_ip_table; +static struct orc_entry *g_orc_table; + +static pthread_t orc_sort_thread; + +static inline unsigned long orc_ip(const int *ip) +{ + return (unsigned long)ip + *ip; +} + +static int orc_sort_cmp(const void *_a, const void *_b) +{ + struct orc_entry *orc_a, *orc_b; + const int *a = g_orc_ip_table + *(int *)_a; + const int *b = g_orc_ip_table + *(int *)_b; + unsigned long a_val = orc_ip(a); + unsigned long b_val = orc_ip(b); + + if (a_val > b_val) + return 1; + if (a_val < b_val) + return -1; + + /* + * The "weak" section terminator entries need to always be on the left + * to ensure the lookup code skips them in favor of real entries. + * These terminator entries exist to handle any gaps created by + * whitelisted .o files which didn't get objtool generation. + */ + orc_a = g_orc_table + (a - g_orc_ip_table); + orc_b = g_orc_table + (b - g_orc_ip_table); + if (orc_a->type == ORC_TYPE_UNDEFINED && orc_b->type == ORC_TYPE_UNDEFINED) + return 0; + return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; +} + +static void *sort_orctable(void *arg) +{ + int i; + int *idxs = NULL; + int *tmp_orc_ip_table = NULL; + struct orc_entry *tmp_orc_table = NULL; + unsigned int *orc_ip_size = (unsigned int *)arg; + unsigned int num_entries = *orc_ip_size / sizeof(int); + unsigned int orc_size = num_entries * sizeof(struct orc_entry); + + idxs = (int *)malloc(*orc_ip_size); + if (!idxs) { + snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s", + strerror(errno)); + pthread_exit(g_err); + } + + tmp_orc_ip_table = (int *)malloc(*orc_ip_size); + if (!tmp_orc_ip_table) { + snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s", + strerror(errno)); + pthread_exit(g_err); + } + + tmp_orc_table = (struct orc_entry *)malloc(orc_size); + if (!tmp_orc_table) { + snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_table: %s", + strerror(errno)); + pthread_exit(g_err); + } + + /* initialize indices array, convert ip_table to absolute address */ + for (i = 0; i < num_entries; i++) { + idxs[i] = i; + tmp_orc_ip_table[i] = g_orc_ip_table[i] + i * sizeof(int); + } + memcpy(tmp_orc_table, g_orc_table, orc_size); + + qsort(idxs, num_entries, sizeof(int), orc_sort_cmp); + + for (i = 0; i < num_entries; i++) { + if (idxs[i] == i) + continue; + + /* convert back to relative address */ + g_orc_ip_table[i] = tmp_orc_ip_table[idxs[i]] - i * sizeof(int); + g_orc_table[i] = tmp_orc_table[idxs[i]]; + } + + free(idxs); + free(tmp_orc_ip_table); + free(tmp_orc_table); + pthread_exit(NULL); +} +#endif + +#ifdef MCOUNT_SORT_ENABLED +static pthread_t mcount_sort_thread; + +struct elf_mcount_loc { + Elf_Ehdr *ehdr; + Elf_Shdr *init_data_sec; + uint64_t start_mcount_loc; + uint64_t stop_mcount_loc; +}; + +/* Sort the addresses stored between __start_mcount_loc to __stop_mcount_loc in vmlinux */ +static void *sort_mcount_loc(void *arg) +{ + struct elf_mcount_loc *emloc = (struct elf_mcount_loc *)arg; + uint64_t offset = emloc->start_mcount_loc - shdr_addr(emloc->init_data_sec) + + shdr_offset(emloc->init_data_sec); + uint64_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc; + unsigned char *start_loc = (void *)emloc->ehdr + offset; + + qsort(start_loc, count/long_size, long_size, compare_extable); + return NULL; +} + +/* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */ +static void get_mcount_loc(struct elf_mcount_loc *emloc, Elf_Shdr *symtab_sec, + const char *strtab) +{ + Elf_Sym *sym, *end_sym; + int symentsize = shdr_entsize(symtab_sec); + int found = 0; + + sym = (void *)emloc->ehdr + shdr_offset(symtab_sec); + end_sym = (void *)sym + shdr_size(symtab_sec); + + while (sym < end_sym) { + if (!strcmp(strtab + sym_name(sym), "__start_mcount_loc")) { + emloc->start_mcount_loc = sym_value(sym); + if (++found == 2) + break; + } else if (!strcmp(strtab + sym_name(sym), "__stop_mcount_loc")) { + emloc->stop_mcount_loc = sym_value(sym); + if (++found == 2) + break; + } + sym = (void *)sym + symentsize; + } + + if (!emloc->start_mcount_loc) { + fprintf(stderr, "get start_mcount_loc error!"); + return; + } + + if (!emloc->stop_mcount_loc) { + fprintf(stderr, "get stop_mcount_loc error!"); + return; + } +} +#endif + +static int do_sort(Elf_Ehdr *ehdr, + char const *const fname, + table_sort_t custom_sort) +{ + int rc = -1; + Elf_Shdr *shdr_start; + Elf_Shdr *strtab_sec = NULL; + Elf_Shdr *symtab_sec = NULL; + Elf_Shdr *extab_sec = NULL; + Elf_Shdr *string_sec; + Elf_Sym *sym; + const Elf_Sym *symtab; + Elf32_Word *symtab_shndx = NULL; + Elf_Sym *sort_needed_sym = NULL; + Elf_Shdr *sort_needed_sec; + uint32_t *sort_needed_loc; + void *sym_start; + void *sym_end; + const char *secstrings; + const char *strtab; + char *extab_image; + int sort_need_index; + int symentsize; + int shentsize; + int idx; + int i; + unsigned int shnum; + unsigned int shstrndx; +#ifdef MCOUNT_SORT_ENABLED + struct elf_mcount_loc mstruct = {0}; +#endif +#ifdef UNWINDER_ORC_ENABLED + unsigned int orc_ip_size = 0; + unsigned int orc_size = 0; + unsigned int orc_num_entries = 0; +#endif + + shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr)); + shentsize = ehdr_shentsize(ehdr); + + shstrndx = ehdr_shstrndx(ehdr); + if (shstrndx == SHN_XINDEX) + shstrndx = shdr_link(shdr_start); + string_sec = get_index(shdr_start, shentsize, shstrndx); + secstrings = (const char *)ehdr + shdr_offset(string_sec); + + shnum = ehdr_shnum(ehdr); + if (shnum == SHN_UNDEF) + shnum = shdr_size(shdr_start); + + for (i = 0; i < shnum; i++) { + Elf_Shdr *shdr = get_index(shdr_start, shentsize, i); + + idx = shdr_name(shdr); + if (!strcmp(secstrings + idx, "__ex_table")) + extab_sec = shdr; + if (!strcmp(secstrings + idx, ".symtab")) + symtab_sec = shdr; + if (!strcmp(secstrings + idx, ".strtab")) + strtab_sec = shdr; + + if (shdr_type(shdr) == SHT_SYMTAB_SHNDX) + symtab_shndx = (Elf32_Word *)((const char *)ehdr + + shdr_offset(shdr)); + +#ifdef MCOUNT_SORT_ENABLED + /* locate the .init.data section in vmlinux */ + if (!strcmp(secstrings + idx, ".init.data")) + mstruct.init_data_sec = shdr; +#endif + +#ifdef UNWINDER_ORC_ENABLED + /* locate the ORC unwind tables */ + if (!strcmp(secstrings + idx, ".orc_unwind_ip")) { + orc_ip_size = shdr_size(shdr); + g_orc_ip_table = (int *)((void *)ehdr + + shdr_offset(shdr)); + } + if (!strcmp(secstrings + idx, ".orc_unwind")) { + orc_size = shdr_size(shdr); + g_orc_table = (struct orc_entry *)((void *)ehdr + + shdr_offset(shdr)); + } +#endif + } /* for loop */ + +#ifdef UNWINDER_ORC_ENABLED + if (!g_orc_ip_table || !g_orc_table) { + fprintf(stderr, + "incomplete ORC unwind tables in file: %s\n", fname); + goto out; + } + + orc_num_entries = orc_ip_size / sizeof(int); + if (orc_ip_size % sizeof(int) != 0 || + orc_size % sizeof(struct orc_entry) != 0 || + orc_num_entries != orc_size / sizeof(struct orc_entry)) { + fprintf(stderr, + "inconsistent ORC unwind table entries in file: %s\n", + fname); + goto out; + } + + /* create thread to sort ORC unwind tables concurrently */ + if (pthread_create(&orc_sort_thread, NULL, + sort_orctable, &orc_ip_size)) { + fprintf(stderr, + "pthread_create orc_sort_thread failed '%s': %s\n", + strerror(errno), fname); + goto out; + } +#endif + if (!extab_sec) { + fprintf(stderr, "no __ex_table in file: %s\n", fname); + goto out; + } + + if (!symtab_sec) { + fprintf(stderr, "no .symtab in file: %s\n", fname); + goto out; + } + + if (!strtab_sec) { + fprintf(stderr, "no .strtab in file: %s\n", fname); + goto out; + } + + extab_image = (void *)ehdr + shdr_offset(extab_sec); + strtab = (const char *)ehdr + shdr_offset(strtab_sec); + symtab = (const Elf_Sym *)((const char *)ehdr + shdr_offset(symtab_sec)); + +#ifdef MCOUNT_SORT_ENABLED + mstruct.ehdr = ehdr; + get_mcount_loc(&mstruct, symtab_sec, strtab); + + if (!mstruct.init_data_sec || !mstruct.start_mcount_loc || !mstruct.stop_mcount_loc) { + fprintf(stderr, + "incomplete mcount's sort in file: %s\n", + fname); + goto out; + } + + /* create thread to sort mcount_loc concurrently */ + if (pthread_create(&mcount_sort_thread, NULL, &sort_mcount_loc, &mstruct)) { + fprintf(stderr, + "pthread_create mcount_sort_thread failed '%s': %s\n", + strerror(errno), fname); + goto out; + } +#endif + + if (custom_sort) { + custom_sort(extab_image, shdr_size(extab_sec)); + } else { + int num_entries = shdr_size(extab_sec) / extable_ent_size; + qsort(extab_image, num_entries, + extable_ent_size, compare_extable); + } + + /* find the flag main_extable_sort_needed */ + sym_start = (void *)ehdr + shdr_offset(symtab_sec); + sym_end = sym_start + shdr_size(symtab_sec); + symentsize = shdr_entsize(symtab_sec); + + for (sym = sym_start; (void *)sym + symentsize < sym_end; + sym = (void *)sym + symentsize) { + if (sym_type(sym) != STT_OBJECT) + continue; + if (!strcmp(strtab + sym_name(sym), + "main_extable_sort_needed")) { + sort_needed_sym = sym; + break; + } + } + + if (!sort_needed_sym) { + fprintf(stderr, + "no main_extable_sort_needed symbol in file: %s\n", + fname); + goto out; + } + + sort_need_index = get_secindex(sym_shndx(sym), + ((void *)sort_needed_sym - (void *)symtab) / symentsize, + symtab_shndx); + sort_needed_sec = get_index(shdr_start, shentsize, sort_need_index); + sort_needed_loc = (void *)ehdr + + shdr_offset(sort_needed_sec) + + sym_value(sort_needed_sym) - shdr_addr(sort_needed_sec); + + /* extable has been sorted, clear the flag */ + w(0, sort_needed_loc); + rc = 0; + +out: +#ifdef UNWINDER_ORC_ENABLED + if (orc_sort_thread) { + void *retval = NULL; + /* wait for ORC tables sort done */ + rc = pthread_join(orc_sort_thread, &retval); + if (rc) { + fprintf(stderr, + "pthread_join failed '%s': %s\n", + strerror(errno), fname); + } else if (retval) { + rc = -1; + fprintf(stderr, + "failed to sort ORC tables '%s': %s\n", + (char *)retval, fname); + } + } +#endif + +#ifdef MCOUNT_SORT_ENABLED + if (mcount_sort_thread) { + void *retval = NULL; + /* wait for mcount sort done */ + rc = pthread_join(mcount_sort_thread, &retval); + if (rc) { + fprintf(stderr, + "pthread_join failed '%s': %s\n", + strerror(errno), fname); + } else if (retval) { + rc = -1; + fprintf(stderr, + "failed to sort mcount '%s': %s\n", + (char *)retval, fname); + } + } +#endif + return rc; +} static int compare_relative_table(const void *a, const void *b) { @@ -267,41 +857,36 @@ static void sort_relative_table_with_data(char *extab_image, int image_size) static int do_file(char const *const fname, void *addr) { - int rc = -1; - Elf32_Ehdr *ehdr = addr; + Elf_Ehdr *ehdr = addr; table_sort_t custom_sort = NULL; - switch (ehdr->e_ident[EI_DATA]) { + switch (ehdr->e32.e_ident[EI_DATA]) { case ELFDATA2LSB: r = rle; r2 = r2le; r8 = r8le; w = wle; - w2 = w2le; - w8 = w8le; break; case ELFDATA2MSB: r = rbe; r2 = r2be; r8 = r8be; w = wbe; - w2 = w2be; - w8 = w8be; break; default: fprintf(stderr, "unrecognized ELF data encoding %d: %s\n", - ehdr->e_ident[EI_DATA], fname); + ehdr->e32.e_ident[EI_DATA], fname); return -1; } - if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0 || - (r2(&ehdr->e_type) != ET_EXEC && r2(&ehdr->e_type) != ET_DYN) || - ehdr->e_ident[EI_VERSION] != EV_CURRENT) { + if (memcmp(ELFMAG, ehdr->e32.e_ident, SELFMAG) != 0 || + (r2(&ehdr->e32.e_type) != ET_EXEC && r2(&ehdr->e32.e_type) != ET_DYN) || + ehdr->e32.e_ident[EI_VERSION] != EV_CURRENT) { fprintf(stderr, "unrecognized ET_EXEC/ET_DYN file %s\n", fname); return -1; } - switch (r2(&ehdr->e_machine)) { + switch (r2(&ehdr->e32.e_machine)) { case EM_386: case EM_AARCH64: case EM_LOONGARCH: @@ -324,40 +909,85 @@ static int do_file(char const *const fname, void *addr) break; default: fprintf(stderr, "unrecognized e_machine %d %s\n", - r2(&ehdr->e_machine), fname); + r2(&ehdr->e32.e_machine), fname); return -1; } - switch (ehdr->e_ident[EI_CLASS]) { - case ELFCLASS32: - if (r2(&ehdr->e_ehsize) != sizeof(Elf32_Ehdr) || - r2(&ehdr->e_shentsize) != sizeof(Elf32_Shdr)) { + switch (ehdr->e32.e_ident[EI_CLASS]) { + case ELFCLASS32: { + struct elf_funcs efuncs = { + .compare_extable = compare_extable_32, + .ehdr_shoff = ehdr32_shoff, + .ehdr_shentsize = ehdr32_shentsize, + .ehdr_shstrndx = ehdr32_shstrndx, + .ehdr_shnum = ehdr32_shnum, + .shdr_addr = shdr32_addr, + .shdr_offset = shdr32_offset, + .shdr_link = shdr32_link, + .shdr_size = shdr32_size, + .shdr_name = shdr32_name, + .shdr_type = shdr32_type, + .shdr_entsize = shdr32_entsize, + .sym_type = sym32_type, + .sym_name = sym32_name, + .sym_value = sym32_value, + .sym_shndx = sym32_shndx, + }; + + e = efuncs; + long_size = 4; + extable_ent_size = 8; + + if (r2(&ehdr->e32.e_ehsize) != sizeof(Elf32_Ehdr) || + r2(&ehdr->e32.e_shentsize) != sizeof(Elf32_Shdr)) { fprintf(stderr, "unrecognized ET_EXEC/ET_DYN file: %s\n", fname); - break; + return -1; + } + } - rc = do_sort_32(ehdr, fname, custom_sort); break; - case ELFCLASS64: - { - Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr; - if (r2(&ghdr->e_ehsize) != sizeof(Elf64_Ehdr) || - r2(&ghdr->e_shentsize) != sizeof(Elf64_Shdr)) { + case ELFCLASS64: { + struct elf_funcs efuncs = { + .compare_extable = compare_extable_64, + .ehdr_shoff = ehdr64_shoff, + .ehdr_shentsize = ehdr64_shentsize, + .ehdr_shstrndx = ehdr64_shstrndx, + .ehdr_shnum = ehdr64_shnum, + .shdr_addr = shdr64_addr, + .shdr_offset = shdr64_offset, + .shdr_link = shdr64_link, + .shdr_size = shdr64_size, + .shdr_name = shdr64_name, + .shdr_type = shdr64_type, + .shdr_entsize = shdr64_entsize, + .sym_type = sym64_type, + .sym_name = sym64_name, + .sym_value = sym64_value, + .sym_shndx = sym64_shndx, + }; + + e = efuncs; + long_size = 8; + extable_ent_size = 16; + + if (r2(&ehdr->e64.e_ehsize) != sizeof(Elf64_Ehdr) || + r2(&ehdr->e64.e_shentsize) != sizeof(Elf64_Shdr)) { fprintf(stderr, "unrecognized ET_EXEC/ET_DYN file: %s\n", fname); - break; + return -1; } - rc = do_sort_64(ghdr, fname, custom_sort); + } break; default: fprintf(stderr, "unrecognized ELF class %d %s\n", - ehdr->e_ident[EI_CLASS], fname); - break; + ehdr->e32.e_ident[EI_CLASS], fname); + return -1; } - return rc; + return do_sort(ehdr, fname, custom_sort); } int main(int argc, char *argv[]) diff --git a/scripts/sorttable.h b/scripts/sorttable.h deleted file mode 100644 index 7bd0184380d3..000000000000 --- a/scripts/sorttable.h +++ /dev/null @@ -1,497 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * sorttable.h - * - * Added ORC unwind tables sort support and other updates: - * Copyright (C) 1999-2019 Alibaba Group Holding Limited. by: - * Shile Zhang <shile.zhang@linux.alibaba.com> - * - * Copyright 2011 - 2012 Cavium, Inc. - * - * Some of code was taken out of arch/x86/kernel/unwind_orc.c, written by: - * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> - * - * Some of this code was taken out of recordmcount.h written by: - * - * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>. All rights reserved. - * Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc. - */ - -#undef extable_ent_size -#undef compare_extable -#undef get_mcount_loc -#undef sort_mcount_loc -#undef elf_mcount_loc -#undef do_sort -#undef Elf_Addr -#undef Elf_Ehdr -#undef Elf_Shdr -#undef Elf_Rel -#undef Elf_Rela -#undef Elf_Sym -#undef ELF_R_SYM -#undef Elf_r_sym -#undef ELF_R_INFO -#undef Elf_r_info -#undef ELF_ST_BIND -#undef ELF_ST_TYPE -#undef fn_ELF_R_SYM -#undef fn_ELF_R_INFO -#undef uint_t -#undef _r -#undef _w - -#ifdef SORTTABLE_64 -# define extable_ent_size 16 -# define compare_extable compare_extable_64 -# define get_mcount_loc get_mcount_loc_64 -# define sort_mcount_loc sort_mcount_loc_64 -# define elf_mcount_loc elf_mcount_loc_64 -# define do_sort do_sort_64 -# define Elf_Addr Elf64_Addr -# define Elf_Ehdr Elf64_Ehdr -# define Elf_Shdr Elf64_Shdr -# define Elf_Rel Elf64_Rel -# define Elf_Rela Elf64_Rela -# define Elf_Sym Elf64_Sym -# define ELF_R_SYM ELF64_R_SYM -# define Elf_r_sym Elf64_r_sym -# define ELF_R_INFO ELF64_R_INFO -# define Elf_r_info Elf64_r_info -# define ELF_ST_BIND ELF64_ST_BIND -# define ELF_ST_TYPE ELF64_ST_TYPE -# define fn_ELF_R_SYM fn_ELF64_R_SYM -# define fn_ELF_R_INFO fn_ELF64_R_INFO -# define uint_t uint64_t -# define _r r8 -# define _w w8 -#else -# define extable_ent_size 8 -# define compare_extable compare_extable_32 -# define get_mcount_loc get_mcount_loc_32 -# define sort_mcount_loc sort_mcount_loc_32 -# define elf_mcount_loc elf_mcount_loc_32 -# define do_sort do_sort_32 -# define Elf_Addr Elf32_Addr -# define Elf_Ehdr Elf32_Ehdr -# define Elf_Shdr Elf32_Shdr -# define Elf_Rel Elf32_Rel -# define Elf_Rela Elf32_Rela -# define Elf_Sym Elf32_Sym -# define ELF_R_SYM ELF32_R_SYM -# define Elf_r_sym Elf32_r_sym -# define ELF_R_INFO ELF32_R_INFO -# define Elf_r_info Elf32_r_info -# define ELF_ST_BIND ELF32_ST_BIND -# define ELF_ST_TYPE ELF32_ST_TYPE -# define fn_ELF_R_SYM fn_ELF32_R_SYM -# define fn_ELF_R_INFO fn_ELF32_R_INFO -# define uint_t uint32_t -# define _r r -# define _w w -#endif - -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) -/* ORC unwinder only support X86_64 */ -#include <asm/orc_types.h> - -#define ERRSTR_MAXSZ 256 - -char g_err[ERRSTR_MAXSZ]; -int *g_orc_ip_table; -struct orc_entry *g_orc_table; - -pthread_t orc_sort_thread; - -static inline unsigned long orc_ip(const int *ip) -{ - return (unsigned long)ip + *ip; -} - -static int orc_sort_cmp(const void *_a, const void *_b) -{ - struct orc_entry *orc_a; - const int *a = g_orc_ip_table + *(int *)_a; - const int *b = g_orc_ip_table + *(int *)_b; - unsigned long a_val = orc_ip(a); - unsigned long b_val = orc_ip(b); - - if (a_val > b_val) - return 1; - if (a_val < b_val) - return -1; - - /* - * The "weak" section terminator entries need to always be on the left - * to ensure the lookup code skips them in favor of real entries. - * These terminator entries exist to handle any gaps created by - * whitelisted .o files which didn't get objtool generation. - */ - orc_a = g_orc_table + (a - g_orc_ip_table); - return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; -} - -static void *sort_orctable(void *arg) -{ - int i; - int *idxs = NULL; - int *tmp_orc_ip_table = NULL; - struct orc_entry *tmp_orc_table = NULL; - unsigned int *orc_ip_size = (unsigned int *)arg; - unsigned int num_entries = *orc_ip_size / sizeof(int); - unsigned int orc_size = num_entries * sizeof(struct orc_entry); - - idxs = (int *)malloc(*orc_ip_size); - if (!idxs) { - snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s", - strerror(errno)); - pthread_exit(g_err); - } - - tmp_orc_ip_table = (int *)malloc(*orc_ip_size); - if (!tmp_orc_ip_table) { - snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s", - strerror(errno)); - pthread_exit(g_err); - } - - tmp_orc_table = (struct orc_entry *)malloc(orc_size); - if (!tmp_orc_table) { - snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_table: %s", - strerror(errno)); - pthread_exit(g_err); - } - - /* initialize indices array, convert ip_table to absolute address */ - for (i = 0; i < num_entries; i++) { - idxs[i] = i; - tmp_orc_ip_table[i] = g_orc_ip_table[i] + i * sizeof(int); - } - memcpy(tmp_orc_table, g_orc_table, orc_size); - - qsort(idxs, num_entries, sizeof(int), orc_sort_cmp); - - for (i = 0; i < num_entries; i++) { - if (idxs[i] == i) - continue; - - /* convert back to relative address */ - g_orc_ip_table[i] = tmp_orc_ip_table[idxs[i]] - i * sizeof(int); - g_orc_table[i] = tmp_orc_table[idxs[i]]; - } - - free(idxs); - free(tmp_orc_ip_table); - free(tmp_orc_table); - pthread_exit(NULL); -} -#endif - -static int compare_extable(const void *a, const void *b) -{ - Elf_Addr av = _r(a); - Elf_Addr bv = _r(b); - - if (av < bv) - return -1; - if (av > bv) - return 1; - return 0; -} -#ifdef MCOUNT_SORT_ENABLED -pthread_t mcount_sort_thread; - -struct elf_mcount_loc { - Elf_Ehdr *ehdr; - Elf_Shdr *init_data_sec; - uint_t start_mcount_loc; - uint_t stop_mcount_loc; -}; - -/* Sort the addresses stored between __start_mcount_loc to __stop_mcount_loc in vmlinux */ -static void *sort_mcount_loc(void *arg) -{ - struct elf_mcount_loc *emloc = (struct elf_mcount_loc *)arg; - uint_t offset = emloc->start_mcount_loc - _r(&(emloc->init_data_sec)->sh_addr) - + _r(&(emloc->init_data_sec)->sh_offset); - uint_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc; - unsigned char *start_loc = (void *)emloc->ehdr + offset; - - qsort(start_loc, count/sizeof(uint_t), sizeof(uint_t), compare_extable); - return NULL; -} - -/* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */ -static void get_mcount_loc(uint_t *_start, uint_t *_stop) -{ - FILE *file_start, *file_stop; - char start_buff[20]; - char stop_buff[20]; - int len = 0; - - file_start = popen(" grep start_mcount System.map | awk '{print $1}' ", "r"); - if (!file_start) { - fprintf(stderr, "get start_mcount_loc error!"); - return; - } - - file_stop = popen(" grep stop_mcount System.map | awk '{print $1}' ", "r"); - if (!file_stop) { - fprintf(stderr, "get stop_mcount_loc error!"); - pclose(file_start); - return; - } - - while (fgets(start_buff, sizeof(start_buff), file_start) != NULL) { - len = strlen(start_buff); - start_buff[len - 1] = '\0'; - } - *_start = strtoul(start_buff, NULL, 16); - - while (fgets(stop_buff, sizeof(stop_buff), file_stop) != NULL) { - len = strlen(stop_buff); - stop_buff[len - 1] = '\0'; - } - *_stop = strtoul(stop_buff, NULL, 16); - - pclose(file_start); - pclose(file_stop); -} -#endif -static int do_sort(Elf_Ehdr *ehdr, - char const *const fname, - table_sort_t custom_sort) -{ - int rc = -1; - Elf_Shdr *s, *shdr = (Elf_Shdr *)((char *)ehdr + _r(&ehdr->e_shoff)); - Elf_Shdr *strtab_sec = NULL; - Elf_Shdr *symtab_sec = NULL; - Elf_Shdr *extab_sec = NULL; - Elf_Sym *sym; - const Elf_Sym *symtab; - Elf32_Word *symtab_shndx = NULL; - Elf_Sym *sort_needed_sym = NULL; - Elf_Shdr *sort_needed_sec; - Elf_Rel *relocs = NULL; - int relocs_size = 0; - uint32_t *sort_needed_loc; - const char *secstrings; - const char *strtab; - char *extab_image; - int extab_index = 0; - int i; - int idx; - unsigned int shnum; - unsigned int shstrndx; -#ifdef MCOUNT_SORT_ENABLED - struct elf_mcount_loc mstruct = {0}; - uint_t _start_mcount_loc = 0; - uint_t _stop_mcount_loc = 0; -#endif -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) - unsigned int orc_ip_size = 0; - unsigned int orc_size = 0; - unsigned int orc_num_entries = 0; -#endif - - shstrndx = r2(&ehdr->e_shstrndx); - if (shstrndx == SHN_XINDEX) - shstrndx = r(&shdr[0].sh_link); - secstrings = (const char *)ehdr + _r(&shdr[shstrndx].sh_offset); - - shnum = r2(&ehdr->e_shnum); - if (shnum == SHN_UNDEF) - shnum = _r(&shdr[0].sh_size); - - for (i = 0, s = shdr; s < shdr + shnum; i++, s++) { - idx = r(&s->sh_name); - if (!strcmp(secstrings + idx, "__ex_table")) { - extab_sec = s; - extab_index = i; - } - if (!strcmp(secstrings + idx, ".symtab")) - symtab_sec = s; - if (!strcmp(secstrings + idx, ".strtab")) - strtab_sec = s; - - if ((r(&s->sh_type) == SHT_REL || - r(&s->sh_type) == SHT_RELA) && - r(&s->sh_info) == extab_index) { - relocs = (void *)ehdr + _r(&s->sh_offset); - relocs_size = _r(&s->sh_size); - } - if (r(&s->sh_type) == SHT_SYMTAB_SHNDX) - symtab_shndx = (Elf32_Word *)((const char *)ehdr + - _r(&s->sh_offset)); - -#ifdef MCOUNT_SORT_ENABLED - /* locate the .init.data section in vmlinux */ - if (!strcmp(secstrings + idx, ".init.data")) { - get_mcount_loc(&_start_mcount_loc, &_stop_mcount_loc); - mstruct.ehdr = ehdr; - mstruct.init_data_sec = s; - mstruct.start_mcount_loc = _start_mcount_loc; - mstruct.stop_mcount_loc = _stop_mcount_loc; - } -#endif - -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) - /* locate the ORC unwind tables */ - if (!strcmp(secstrings + idx, ".orc_unwind_ip")) { - orc_ip_size = s->sh_size; - g_orc_ip_table = (int *)((void *)ehdr + - s->sh_offset); - } - if (!strcmp(secstrings + idx, ".orc_unwind")) { - orc_size = s->sh_size; - g_orc_table = (struct orc_entry *)((void *)ehdr + - s->sh_offset); - } -#endif - } /* for loop */ - -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) - if (!g_orc_ip_table || !g_orc_table) { - fprintf(stderr, - "incomplete ORC unwind tables in file: %s\n", fname); - goto out; - } - - orc_num_entries = orc_ip_size / sizeof(int); - if (orc_ip_size % sizeof(int) != 0 || - orc_size % sizeof(struct orc_entry) != 0 || - orc_num_entries != orc_size / sizeof(struct orc_entry)) { - fprintf(stderr, - "inconsistent ORC unwind table entries in file: %s\n", - fname); - goto out; - } - - /* create thread to sort ORC unwind tables concurrently */ - if (pthread_create(&orc_sort_thread, NULL, - sort_orctable, &orc_ip_size)) { - fprintf(stderr, - "pthread_create orc_sort_thread failed '%s': %s\n", - strerror(errno), fname); - goto out; - } -#endif - -#ifdef MCOUNT_SORT_ENABLED - if (!mstruct.init_data_sec || !_start_mcount_loc || !_stop_mcount_loc) { - fprintf(stderr, - "incomplete mcount's sort in file: %s\n", - fname); - goto out; - } - - /* create thread to sort mcount_loc concurrently */ - if (pthread_create(&mcount_sort_thread, NULL, &sort_mcount_loc, &mstruct)) { - fprintf(stderr, - "pthread_create mcount_sort_thread failed '%s': %s\n", - strerror(errno), fname); - goto out; - } -#endif - if (!extab_sec) { - fprintf(stderr, "no __ex_table in file: %s\n", fname); - goto out; - } - - if (!symtab_sec) { - fprintf(stderr, "no .symtab in file: %s\n", fname); - goto out; - } - - if (!strtab_sec) { - fprintf(stderr, "no .strtab in file: %s\n", fname); - goto out; - } - - extab_image = (void *)ehdr + _r(&extab_sec->sh_offset); - strtab = (const char *)ehdr + _r(&strtab_sec->sh_offset); - symtab = (const Elf_Sym *)((const char *)ehdr + - _r(&symtab_sec->sh_offset)); - - if (custom_sort) { - custom_sort(extab_image, _r(&extab_sec->sh_size)); - } else { - int num_entries = _r(&extab_sec->sh_size) / extable_ent_size; - qsort(extab_image, num_entries, - extable_ent_size, compare_extable); - } - - /* If there were relocations, we no longer need them. */ - if (relocs) - memset(relocs, 0, relocs_size); - - /* find the flag main_extable_sort_needed */ - for (sym = (void *)ehdr + _r(&symtab_sec->sh_offset); - sym < sym + _r(&symtab_sec->sh_size) / sizeof(Elf_Sym); - sym++) { - if (ELF_ST_TYPE(sym->st_info) != STT_OBJECT) - continue; - if (!strcmp(strtab + r(&sym->st_name), - "main_extable_sort_needed")) { - sort_needed_sym = sym; - break; - } - } - - if (!sort_needed_sym) { - fprintf(stderr, - "no main_extable_sort_needed symbol in file: %s\n", - fname); - goto out; - } - - sort_needed_sec = &shdr[get_secindex(r2(&sym->st_shndx), - sort_needed_sym - symtab, - symtab_shndx)]; - sort_needed_loc = (void *)ehdr + - _r(&sort_needed_sec->sh_offset) + - _r(&sort_needed_sym->st_value) - - _r(&sort_needed_sec->sh_addr); - - /* extable has been sorted, clear the flag */ - w(0, sort_needed_loc); - rc = 0; - -out: -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) - if (orc_sort_thread) { - void *retval = NULL; - /* wait for ORC tables sort done */ - rc = pthread_join(orc_sort_thread, &retval); - if (rc) { - fprintf(stderr, - "pthread_join failed '%s': %s\n", - strerror(errno), fname); - } else if (retval) { - rc = -1; - fprintf(stderr, - "failed to sort ORC tables '%s': %s\n", - (char *)retval, fname); - } - } -#endif - -#ifdef MCOUNT_SORT_ENABLED - if (mcount_sort_thread) { - void *retval = NULL; - /* wait for mcount sort done */ - rc = pthread_join(mcount_sort_thread, &retval); - if (rc) { - fprintf(stderr, - "pthread_join failed '%s': %s\n", - strerror(errno), fname); - } else if (retval) { - rc = -1; - fprintf(stderr, - "failed to sort mcount '%s': %s\n", - (char *)retval, fname); - } - } -#endif - return rc; -} diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index 8b8fb115fc81..8d608f61bf37 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -214,9 +214,15 @@ class id_parser(object): # Remove trailing xml comment closure if line.strip().endswith('-->'): expr = expr.rstrip('-->').strip() + # Remove trailing Jinja2 comment closure + if line.strip().endswith('#}'): + expr = expr.rstrip('#}').strip() # Special case for SH magic boot code files if line.startswith('LIST \"'): expr = expr.rstrip('\"').strip() + # Remove j2 comment closure + if line.startswith('{#'): + expr = expr.rstrip('#}').strip() self.parse(expr) self.spdx_valid += 1 # diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 05bd9ca1fbfa..a290db720b0f 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -222,6 +222,7 @@ autonymous||autonomous auxillary||auxiliary auxilliary||auxiliary avaiable||available +avaialable||available avaible||available availabe||available availabled||available @@ -267,6 +268,7 @@ broadcase||broadcast broadcat||broadcast bufer||buffer bufferred||buffered +bufferur||buffer bufufer||buffer cacluated||calculated caculate||calculate @@ -405,6 +407,7 @@ configutation||configuration congiuration||configuration conider||consider conjuction||conjunction +connction||connection connecetd||connected connectinos||connections connetor||connector @@ -413,6 +416,7 @@ connnections||connections consistancy||consistency consistant||consistent consits||consists +constructred||constructed containes||contains containts||contains contaisn||contains @@ -450,6 +454,7 @@ creationg||creating cryptocraphic||cryptographic cummulative||cumulative cunter||counter +curent||current curently||currently cylic||cyclic dafault||default @@ -461,6 +466,7 @@ decendant||descendant decendants||descendants decompres||decompress decsribed||described +decrese||decrease decription||description detault||default dectected||detected @@ -485,6 +491,7 @@ delare||declare delares||declares delaring||declaring delemiter||delimiter +deley||delay delibrately||deliberately delievered||delivered demodualtor||demodulator @@ -551,6 +558,7 @@ disgest||digest disired||desired dispalying||displaying dissable||disable +dissapeared||disappeared diplay||display directon||direction direcly||directly @@ -606,6 +614,7 @@ eigth||eight elementry||elementary eletronic||electronic embeded||embedded +emtpy||empty enabledi||enabled enbale||enable enble||enable @@ -669,6 +678,7 @@ exmaple||example expecially||especially experies||expires explicite||explicit +explicity||explicitly explicitely||explicitly explict||explicit explictely||explicitly @@ -723,10 +733,12 @@ followign||following followings||following follwing||following fonud||found +forcebly||forcibly forseeable||foreseeable forse||force fortan||fortran forwardig||forwarding +forwared||forwarded frambuffer||framebuffer framming||framing framwork||framework @@ -767,6 +779,7 @@ grahpical||graphical granularty||granularity grapic||graphic grranted||granted +grups||groups guage||gauge guarenteed||guaranteed guarentee||guarantee @@ -780,6 +793,7 @@ hardare||hardware harware||hardware hardward||hardware havind||having +heigth||height heirarchically||hierarchically heirarchy||hierarchy heirachy||hierarchy @@ -788,9 +802,11 @@ hearbeat||heartbeat heterogenous||heterogeneous hexdecimal||hexadecimal hybernate||hibernate +hiearchy||hierarchy hierachy||hierarchy hierarchie||hierarchy homogenous||homogeneous +horizental||horizontal howver||however hsould||should hypervior||hypervisor @@ -842,6 +858,7 @@ independed||independent indiate||indicate indicat||indicate inexpect||inexpected +infalte||inflate inferface||interface infinit||infinite infomation||information @@ -861,6 +878,7 @@ initators||initiators initialiazation||initialization initializationg||initialization initializiation||initialization +initializtion||initialization initialze||initialize initialzed||initialized initialzing||initializing @@ -877,6 +895,7 @@ instanciate||instantiate instanciated||instantiated instuments||instruments insufficent||insufficient +intead||instead inteface||interface integreated||integrated integrety||integrity @@ -1081,6 +1100,7 @@ notications||notifications notifcations||notifications notifed||notified notity||notify +notfify||notify nubmer||number numebr||number numer||number @@ -1122,6 +1142,7 @@ orientatied||orientated orientied||oriented orignal||original originial||original +orphanded||orphaned otherise||otherwise ouput||output oustanding||outstanding @@ -1184,9 +1205,11 @@ peroid||period persistance||persistence persistant||persistent phoneticly||phonetically +pipline||pipeline plaform||platform plalform||platform platfoem||platform +platfomr||platform platfrom||platform plattform||platform pleaes||please @@ -1211,6 +1234,7 @@ preceeding||preceding preceed||precede precendence||precedence precission||precision +predicition||prediction preemptable||preemptible prefered||preferred prefferably||preferably @@ -1289,6 +1313,7 @@ querrying||querying queus||queues randomally||randomly raoming||roaming +readyness||readiness reasearcher||researcher reasearchers||researchers reasearch||research @@ -1305,8 +1330,10 @@ recieves||receives recieving||receiving recogniced||recognised recognizeable||recognizable +recompte||recompute recommanded||recommended recyle||recycle +redect||reject redircet||redirect redirectrion||redirection redundacy||redundancy @@ -1314,6 +1341,7 @@ reename||rename refcounf||refcount refence||reference refered||referred +referencce||reference referenace||reference refererence||reference refering||referring @@ -1348,11 +1376,13 @@ replys||replies reponse||response representaion||representation repsonse||response +reqested||requested reqeust||request reqister||register requed||requeued requestied||requested requiere||require +requieres||requires requirment||requirement requred||required requried||required @@ -1440,6 +1470,7 @@ sequencial||sequential serivce||service serveral||several servive||service +sesion||session setts||sets settting||setting shapshot||snapshot @@ -1602,11 +1633,13 @@ trys||tries thses||these tiggers||triggers tiggered||triggered +tiggerring||triggering tipically||typically timeing||timing timming||timing timout||timeout tmis||this +tolarance||tolerance toogle||toggle torerable||tolerable torlence||tolerance @@ -1633,6 +1666,7 @@ trasfer||transfer trasmission||transmission trasmitter||transmitter treshold||threshold +trigged||triggered triggerd||triggered trigerred||triggered trigerring||triggering @@ -1648,6 +1682,7 @@ uknown||unknown usccess||success uncommited||uncommitted uncompatible||incompatible +uncomressed||uncompressed unconditionaly||unconditionally undeflow||underflow undelying||underlying @@ -1715,6 +1750,7 @@ utitity||utility utitlty||utility vaid||valid vaild||valid +validationg||validating valide||valid variantions||variations varible||variable @@ -1724,6 +1760,7 @@ verbse||verbose veify||verify verfication||verification veriosn||version +versoin||version verisons||versions verison||version veritical||vertical diff --git a/scripts/tags.sh b/scripts/tags.sh index b21236377998..45eaf35f5bff 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -188,6 +188,7 @@ regex_c=( '/^PCI_OP_WRITE([[:space:]]*\(\w*\).*[1-4])/pci_bus_write_config_\1/' '/\<DEFINE_\(RT_MUTEX\|MUTEX\|SEMAPHORE\|SPINLOCK\)([[:space:]]*\([[:alnum:]_]*\)/\2/v/' '/\<DEFINE_\(RAW_SPINLOCK\|RWLOCK\|SEQLOCK\)([[:space:]]*\([[:alnum:]_]*\)/\2/v/' + '/\<DEFINE_TIMER(\([^,)]*\),/\1/' '/\<DECLARE_\(RWSEM\|COMPLETION\)([[:space:]]*\([[:alnum:]_]\+\)/\2/v/' '/\<DECLARE_BITMAP([[:space:]]*\([[:alnum:]_]\+\)/\1/v/' '/\(^\|\s\)\(\|L\|H\)LIST_HEAD([[:space:]]*\([[:alnum:]_]*\)/\3/v/' @@ -212,6 +213,13 @@ regex_c=( '/^SEQCOUNT_LOCKTYPE(\([^,]*\),[[:space:]]*\([^,]*\),[^)]*)/seqcount_\2_init/' '/^\<DECLARE_IDTENTRY[[:alnum:]_]*([^,)]*,[[:space:]]*\([[:alnum:]_]\+\)/\1/' '/^\<DEFINE_IDTENTRY[[:alnum:]_]*([[:space:]]*\([[:alnum:]_]\+\)/\1/' + '/^\<DEFINE_FREE(\([[:alnum:]_]\+\)/cleanup_\1/' + '/^\<DEFINE_CLASS(\([[:alnum:]_]\+\)/class_\1/' + '/^\<EXTEND_CLASS(\([[:alnum:]_]\+\),[[:space:]]*\([[:alnum:]_]\+\)/class_\1\2/' + '/^\<DEFINE_GUARD(\([[:alnum:]_]\+\)/class_\1/' + '/^\<DEFINE_GUARD_COND(\([[:alnum:]_]\+\),[[:space:]]*\([[:alnum:]_]\+\)/class_\1\2/' + '/^\<DEFINE_LOCK_GUARD_[[:digit:]](\([[:alnum:]_]\+\)/class_\1/' + '/^\<DEFINE_LOCK_GUARD_[[:digit:]]_COND(\([[:alnum:]_]\+\),[[:space:]]*\([[:alnum:]_]\+\)/class_\1\2/' ) regex_kconfig=( '/^[[:blank:]]*\(menu\|\)config[[:blank:]]\+\([[:alnum:]_]\+\)/\2/' @@ -260,7 +268,8 @@ exuberant() # identifiers to ignore by ctags local ign=( ACPI_EXPORT_SYMBOL - DEFINE_{TRACE,MUTEX} + DECLARE_BITMAP + DEFINE_{TRACE,MUTEX,TIMER} EXPORT_SYMBOL EXPORT_SYMBOL_GPL EXPORT_TRACEPOINT_SYMBOL EXPORT_TRACEPOINT_SYMBOL_GPL ____cacheline_aligned ____cacheline_aligned_in_smp diff --git a/security/Kconfig b/security/Kconfig index 28e685f53bd1..f10dbf15c294 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -64,6 +64,11 @@ config SECURITY If you are unsure how to answer this question, answer N. +config HAS_SECURITY_AUDIT + def_bool y + depends on AUDIT + depends on SECURITY + config SECURITYFS bool "Enable the securityfs filesystem" help diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index c9d5ca3d8d08..b56e001e0c6a 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -127,6 +127,7 @@ choice repeating for all types and padding except float and double which use 0xFF repeating (-NaN). Clang on 32-bit uses 0xFF repeating for all types and padding. + GCC uses 0xFE repeating for all types, and zero for padding. config INIT_STACK_ALL_ZERO bool "zero-init everything (strongest and safest)" diff --git a/security/Makefile b/security/Makefile index cc0982214b84..22ff4c8bd8ce 100644 --- a/security/Makefile +++ b/security/Makefile @@ -15,7 +15,7 @@ obj-$(CONFIG_SECURITY) += security.o obj-$(CONFIG_SECURITYFS) += inode.o obj-$(CONFIG_SECURITY_SELINUX) += selinux/ obj-$(CONFIG_SECURITY_SMACK) += smack/ -obj-$(CONFIG_SECURITY) += lsm_audit.o +obj-$(CONFIG_HAS_SECURITY_AUDIT) += lsm_audit.o obj-$(CONFIG_SECURITY_TOMOYO) += tomoyo/ obj-$(CONFIG_SECURITY_APPARMOR) += apparmor/ obj-$(CONFIG_SECURITY_YAMA) += yama/ diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 2c0185ebc900..c07d150685d7 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -2612,7 +2612,7 @@ static int policy_readlink(struct dentry *dentry, char __user *buffer, res = snprintf(name, sizeof(name), "%s:[%lu]", AAFS_NAME, d_inode(dentry)->i_ino); if (res > 0 && res < sizeof(name)) - res = readlink_copy(buffer, buflen, name); + res = readlink_copy(buffer, buflen, name, strlen(name)); else res = -ENOENT; diff --git a/security/apparmor/include/secid.h b/security/apparmor/include/secid.h index f6a515640950..6025d3849cf8 100644 --- a/security/apparmor/include/secid.h +++ b/security/apparmor/include/secid.h @@ -25,11 +25,10 @@ struct aa_label; extern int apparmor_display_secid_mode; struct aa_label *aa_secid_to_label(u32 secid); -int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); -int apparmor_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, - u32 *seclen); +int apparmor_secid_to_secctx(u32 secid, struct lsm_context *cp); +int apparmor_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp); int apparmor_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid); -void apparmor_release_secctx(char *secdata, u32 seclen); +void apparmor_release_secctx(struct lsm_context *cp); int aa_alloc_secid(struct aa_label *label, gfp_t gfp); diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 1edc12862a7d..9b6c2f157f83 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -2038,7 +2038,7 @@ static int apparmor_dointvec(const struct ctl_table *table, int write, return proc_dointvec(table, write, buffer, lenp, ppos); } -static struct ctl_table apparmor_sysctl_table[] = { +static const struct ctl_table apparmor_sysctl_table[] = { #ifdef CONFIG_USER_NS { .procname = "unprivileged_userns_apparmor_policy", diff --git a/security/apparmor/secid.c b/security/apparmor/secid.c index 47dc08fc583e..28caf66b9033 100644 --- a/security/apparmor/secid.c +++ b/security/apparmor/secid.c @@ -47,23 +47,21 @@ struct aa_label *aa_secid_to_label(u32 secid) return xa_load(&aa_secids, secid); } -static int apparmor_label_to_secctx(struct aa_label *label, char **secdata, - u32 *seclen) +static int apparmor_label_to_secctx(struct aa_label *label, + struct lsm_context *cp) { /* TODO: cache secctx and ref count so we don't have to recreate */ int flags = FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED | FLAG_ABS_ROOT; int len; - AA_BUG(!seclen); - if (!label) return -EINVAL; if (apparmor_display_secid_mode) flags |= FLAG_SHOW_MODE; - if (secdata) - len = aa_label_asxprint(secdata, root_ns, label, + if (cp) + len = aa_label_asxprint(&cp->context, root_ns, label, flags, GFP_ATOMIC); else len = aa_label_snxprint(NULL, 0, root_ns, label, flags); @@ -71,26 +69,28 @@ static int apparmor_label_to_secctx(struct aa_label *label, char **secdata, if (len < 0) return -ENOMEM; - *seclen = len; + if (cp) { + cp->len = len; + cp->id = LSM_ID_APPARMOR; + } - return 0; + return len; } -int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +int apparmor_secid_to_secctx(u32 secid, struct lsm_context *cp) { struct aa_label *label = aa_secid_to_label(secid); - return apparmor_label_to_secctx(label, secdata, seclen); + return apparmor_label_to_secctx(label, cp); } -int apparmor_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, - u32 *seclen) +int apparmor_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp) { struct aa_label *label; label = prop->apparmor.label; - return apparmor_label_to_secctx(label, secdata, seclen); + return apparmor_label_to_secctx(label, cp); } int apparmor_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) @@ -106,9 +106,13 @@ int apparmor_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) return 0; } -void apparmor_release_secctx(char *secdata, u32 seclen) +void apparmor_release_secctx(struct lsm_context *cp) { - kfree(secdata); + if (cp->id == LSM_ID_APPARMOR) { + kfree(cp->context); + cp->context = NULL; + cp->id = LSM_ID_UNDEF; + } } /** diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c index 3663aec7bcbd..db759025abe1 100644 --- a/security/bpf/hooks.c +++ b/security/bpf/hooks.c @@ -13,7 +13,6 @@ static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = { #include <linux/lsm_hook_defs.h> #undef LSM_HOOK LSM_HOOK_INIT(inode_free_security, bpf_inode_storage_free), - LSM_HOOK_INIT(task_free, bpf_task_storage_free), }; static const struct lsm_id bpf_lsmid = { diff --git a/security/commoncap.c b/security/commoncap.c index cefad323a0b1..58a0c1c3e409 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -27,6 +27,9 @@ #include <linux/mnt_idmapping.h> #include <uapi/linux/lsm.h> +#define CREATE_TRACE_POINTS +#include <trace/events/capability.h> + /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. @@ -50,24 +53,24 @@ static void warn_setuid_and_fcaps_mixed(const char *fname) } /** - * cap_capable - Determine whether a task has a particular effective capability + * cap_capable_helper - Determine whether a task has a particular effective + * capability. * @cred: The credentials to use - * @targ_ns: The user namespace in which we need the capability + * @target_ns: The user namespace of the resource being accessed + * @cred_ns: The user namespace of the credentials * @cap: The capability to check for - * @opts: Bitmask of options defined in include/linux/security.h * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * - * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() - * and has_capability() functions. That is, it has the reverse semantics: - * cap_has_capability() returns 0 when a task has a capability, but the - * kernel's capable() and has_capability() returns 1 for this case. + * See cap_capable for more details. */ -int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, - int cap, unsigned int opts) +static inline int cap_capable_helper(const struct cred *cred, + struct user_namespace *target_ns, + const struct user_namespace *cred_ns, + int cap) { - struct user_namespace *ns = targ_ns; + struct user_namespace *ns = target_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target @@ -75,21 +78,21 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, */ for (;;) { /* Do we have the necessary capabilities? */ - if (ns == cred->user_ns) + if (likely(ns == cred_ns)) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ - if (ns->level <= cred->user_ns->level) + if (ns->level <= cred_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ - if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid)) + if ((ns->parent == cred_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* @@ -102,6 +105,31 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, /* We never get here */ } +/** + * cap_capable - Determine whether a task has a particular effective capability + * @cred: The credentials to use + * @target_ns: The user namespace of the resource being accessed + * @cap: The capability to check for + * @opts: Bitmask of options defined in include/linux/security.h (unused) + * + * Determine whether the nominated task has the specified capability amongst + * its effective set, returning 0 if it does, -ve if it does not. + * + * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() + * and has_capability() functions. That is, it has the reverse semantics: + * cap_has_capability() returns 0 when a task has a capability, but the + * kernel's capable() and has_capability() returns 1 for this case. + */ +int cap_capable(const struct cred *cred, struct user_namespace *target_ns, + int cap, unsigned int opts) +{ + const struct user_namespace *cred_ns = cred->user_ns; + int ret = cap_capable_helper(cred, target_ns, cred_ns, cap); + + trace_cap_capable(cred, target_ns, cred_ns, cap, ret); + return ret; +} + /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set @@ -1302,21 +1330,38 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ - || (cap_capable(current_cred(), - current_cred()->user_ns, - CAP_SETPCAP, - CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits - * [4] doing anything requires privilege (go read about - * the "sendmail capabilities bug") */ ) /* cannot change a locked bit */ return -EPERM; + /* + * Doing anything requires privilege (go read about the + * "sendmail capabilities bug"), except for unprivileged bits. + * Indeed, the SECURE_ALL_UNPRIVILEGED bits are not + * restrictions enforced by the kernel but by user space on + * itself. + */ + if (cap_capable(current_cred(), current_cred()->user_ns, + CAP_SETPCAP, CAP_OPT_NONE) != 0) { + const unsigned long unpriv_and_locks = + SECURE_ALL_UNPRIVILEGED | + SECURE_ALL_UNPRIVILEGED << 1; + const unsigned long changed = old->securebits ^ arg2; + + /* For legacy reason, denies non-change. */ + if (!changed) + return -EPERM; + + /* Denies privileged changes. */ + if (changed & ~unpriv_and_locks) + return -EPERM; + } + new = prepare_creds(); if (!new) return -ENOMEM; @@ -1428,12 +1473,6 @@ int cap_mmap_addr(unsigned long addr) return ret; } -int cap_mmap_file(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags) -{ - return 0; -} - #ifdef CONFIG_SECURITY static const struct lsm_id capability_lsmid = { @@ -1453,7 +1492,6 @@ static struct security_hook_list capability_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), - LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index c0d3b716d11f..24d09ea91b87 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -278,6 +278,7 @@ unsigned long ima_get_binary_runtime_size(void); int ima_init_template(void); void ima_init_template_list(void); int __init ima_init_digests(void); +void __init ima_init_reboot_notifier(void); int ima_lsm_policy_change(struct notifier_block *nb, unsigned long event, void *lsm_data); diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 884a3533f7af..f435eff4667f 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/file.h> +#include <linux/binfmts.h> #include <linux/fs.h> #include <linux/xattr.h> #include <linux/magic.h> @@ -469,6 +470,17 @@ int ima_check_blacklist(struct ima_iint_cache *iint, return rc; } +static bool is_bprm_creds_for_exec(enum ima_hooks func, struct file *file) +{ + struct linux_binprm *bprm; + + if (func == BPRM_CHECK) { + bprm = container_of(&file, struct linux_binprm, file); + return bprm->is_check; + } + return false; +} + /* * ima_appraise_measurement - appraise file measurement * @@ -483,6 +495,7 @@ int ima_appraise_measurement(enum ima_hooks func, struct ima_iint_cache *iint, int xattr_len, const struct modsig *modsig) { static const char op[] = "appraise_data"; + int audit_msgno = AUDIT_INTEGRITY_DATA; const char *cause = "unknown"; struct dentry *dentry = file_dentry(file); struct inode *inode = d_backing_inode(dentry); @@ -494,6 +507,16 @@ int ima_appraise_measurement(enum ima_hooks func, struct ima_iint_cache *iint, if (!(inode->i_opflags & IOP_XATTR) && !try_modsig) return INTEGRITY_UNKNOWN; + /* + * Unlike any of the other LSM hooks where the kernel enforces file + * integrity, enforcing file integrity for the bprm_creds_for_exec() + * LSM hook with the AT_EXECVE_CHECK flag is left up to the discretion + * of the script interpreter(userspace). Differentiate kernel and + * userspace enforced integrity audit messages. + */ + if (is_bprm_creds_for_exec(func, file)) + audit_msgno = AUDIT_INTEGRITY_USERSPACE; + /* If reading the xattr failed and there's no modsig, error out. */ if (rc <= 0 && !try_modsig) { if (rc && rc != -ENODATA) @@ -569,7 +592,7 @@ out: (iint->flags & IMA_FAIL_UNVERIFIABLE_SIGS))) { status = INTEGRITY_FAIL; cause = "unverifiable-signature"; - integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename, + integrity_audit_msg(audit_msgno, inode, filename, op, cause, rc, 0); } else if (status != INTEGRITY_PASS) { /* Fix mode, but don't replace file signatures. */ @@ -589,7 +612,7 @@ out: status = INTEGRITY_PASS; } - integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename, + integrity_audit_msg(audit_msgno, inode, filename, op, cause, rc, 0); } else { ima_cache_flags(iint, func); diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c index 4e208239a40e..a2f34f2d8ad7 100644 --- a/security/integrity/ima/ima_init.c +++ b/security/integrity/ima/ima_init.c @@ -152,6 +152,8 @@ int __init ima_init(void) ima_init_key_queue(); + ima_init_reboot_notifier(); + ima_measure_critical_data("kernel_info", "kernel_version", UTS_RELEASE, strlen(UTS_RELEASE), false, NULL, 0); diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c index 52e00332defe..9d45f4d26f73 100644 --- a/security/integrity/ima/ima_kexec.c +++ b/security/integrity/ima/ima_kexec.c @@ -37,7 +37,8 @@ static int ima_dump_measurement_list(unsigned long *buffer_size, void **buffer, memset(&khdr, 0, sizeof(khdr)); khdr.version = 1; - list_for_each_entry_rcu(qe, &ima_measurements, later) { + /* This is an append-only list, no need to hold the RCU read lock */ + list_for_each_entry_rcu(qe, &ima_measurements, later, true) { if (file.count < file.size) { khdr.count++; ima_measurements_show(&file, qe); diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 9b87556b03a7..9f9897a7c217 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -554,6 +554,34 @@ static int ima_bprm_check(struct linux_binprm *bprm) MAY_EXEC, CREDS_CHECK); } +/** + * ima_bprm_creds_for_exec - collect/store/appraise measurement. + * @bprm: contains the linux_binprm structure + * + * Based on the IMA policy and the execveat(2) AT_EXECVE_CHECK flag, measure + * and appraise the integrity of a file to be executed by script interpreters. + * Unlike any of the other LSM hooks where the kernel enforces file integrity, + * enforcing file integrity is left up to the discretion of the script + * interpreter (userspace). + * + * On success return 0. On integrity appraisal error, assuming the file + * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. + */ +static int ima_bprm_creds_for_exec(struct linux_binprm *bprm) +{ + /* + * As security_bprm_check() is called multiple times, both + * the script and the shebang interpreter are measured, appraised, + * and audited. Limit usage of this LSM hook to just measuring, + * appraising, and auditing the indirect script execution + * (e.g. ./sh example.sh). + */ + if (!bprm->is_check) + return 0; + + return ima_bprm_check(bprm); +} + /** * ima_file_check - based on policy, collect/store measurement. * @file: pointer to the file to be measured @@ -1174,6 +1202,7 @@ static int __init init_ima(void) static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), + LSM_HOOK_INIT(bprm_creds_for_exec, ima_bprm_creds_for_exec), LSM_HOOK_INIT(file_post_open, ima_file_check), LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), LSM_HOOK_INIT(file_release, ima_file_free), diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 21a8e54c383f..128fab897930 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -148,7 +148,8 @@ static struct ima_rule_entry dont_measure_rules[] __ro_after_init = { {.action = DONT_MEASURE, .fsmagic = PROC_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = SYSFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = DEBUGFS_MAGIC, .flags = IMA_FSMAGIC}, - {.action = DONT_MEASURE, .fsmagic = TMPFS_MAGIC, .flags = IMA_FSMAGIC}, + {.action = DONT_MEASURE, .fsmagic = TMPFS_MAGIC, .func = FILE_CHECK, + .flags = IMA_FSMAGIC | IMA_FUNC}, {.action = DONT_MEASURE, .fsmagic = DEVPTS_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = BINFMTFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = SECURITYFS_MAGIC, .flags = IMA_FSMAGIC}, @@ -1431,7 +1432,7 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) int token; unsigned long lnum; - if (result < 0) + if (result < 0 || *p == '#') /* ignore suffixed comment */ break; if ((*p == '\0') || (*p == ' ') || (*p == '\t')) continue; diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c index 532da87ce519..83d53824aa98 100644 --- a/security/integrity/ima/ima_queue.c +++ b/security/integrity/ima/ima_queue.c @@ -16,6 +16,7 @@ */ #include <linux/rculist.h> +#include <linux/reboot.h> #include <linux/slab.h> #include "ima.h" @@ -44,6 +45,12 @@ struct ima_h_table ima_htable = { */ static DEFINE_MUTEX(ima_extend_list_mutex); +/* + * Used internally by the kernel to suspend measurements. + * Protected by ima_extend_list_mutex. + */ +static bool ima_measurements_suspended; + /* lookup up the digest value in the hash table, and return the entry */ static struct ima_queue_entry *ima_lookup_digest_entry(u8 *digest_value, int pcr) @@ -168,6 +175,18 @@ int ima_add_template_entry(struct ima_template_entry *entry, int violation, int result = 0, tpmresult = 0; mutex_lock(&ima_extend_list_mutex); + + /* + * Avoid appending to the measurement log when the TPM subsystem has + * been shut down while preparing for system reboot. + */ + if (ima_measurements_suspended) { + audit_cause = "measurements_suspended"; + audit_info = 0; + result = -ENODEV; + goto out; + } + if (!violation && !IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE)) { if (ima_lookup_digest_entry(digest, entry->pcr)) { audit_cause = "hash_exists"; @@ -211,6 +230,31 @@ int ima_restore_measurement_entry(struct ima_template_entry *entry) return result; } +static void ima_measurements_suspend(void) +{ + mutex_lock(&ima_extend_list_mutex); + ima_measurements_suspended = true; + mutex_unlock(&ima_extend_list_mutex); +} + +static int ima_reboot_notifier(struct notifier_block *nb, + unsigned long action, + void *data) +{ + ima_measurements_suspend(); + + return NOTIFY_DONE; +} + +static struct notifier_block ima_reboot_nb = { + .notifier_call = ima_reboot_notifier, +}; + +void __init ima_init_reboot_notifier(void) +{ + register_reboot_notifier(&ima_reboot_nb); +} + int __init ima_init_digests(void) { u16 digest_size; diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c index 91f000eef3ad..cde08c478f32 100644 --- a/security/keys/sysctl.c +++ b/security/keys/sysctl.c @@ -9,7 +9,7 @@ #include <linux/sysctl.h> #include "internal.h" -static struct ctl_table key_sysctls[] = { +static const struct ctl_table key_sysctls[] = { { .procname = "maxkeys", .data = &key_quota_maxkeys, diff --git a/security/keys/trusted-keys/trusted_dcp.c b/security/keys/trusted-keys/trusted_dcp.c index e908c53a803c..7b6eb655df0c 100644 --- a/security/keys/trusted-keys/trusted_dcp.c +++ b/security/keys/trusted-keys/trusted_dcp.c @@ -201,12 +201,16 @@ static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob) { struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob; int blen, ret; - u8 plain_blob_key[AES_KEYSIZE_128]; + u8 *plain_blob_key; blen = calc_blob_len(p->key_len); if (blen > MAX_BLOB_SIZE) return -E2BIG; + plain_blob_key = kmalloc(AES_KEYSIZE_128, GFP_KERNEL); + if (!plain_blob_key) + return -ENOMEM; + b->fmt_version = DCP_BLOB_VERSION; get_random_bytes(b->nonce, AES_KEYSIZE_128); get_random_bytes(plain_blob_key, AES_KEYSIZE_128); @@ -229,7 +233,8 @@ static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob) ret = 0; out: - memzero_explicit(plain_blob_key, sizeof(plain_blob_key)); + memzero_explicit(plain_blob_key, AES_KEYSIZE_128); + kfree(plain_blob_key); return ret; } @@ -238,7 +243,7 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) { struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob; int blen, ret; - u8 plain_blob_key[AES_KEYSIZE_128]; + u8 *plain_blob_key = NULL; if (b->fmt_version != DCP_BLOB_VERSION) { pr_err("DCP blob has bad version: %i, expected %i\n", @@ -256,6 +261,12 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) goto out; } + plain_blob_key = kmalloc(AES_KEYSIZE_128, GFP_KERNEL); + if (!plain_blob_key) { + ret = -ENOMEM; + goto out; + } + ret = decrypt_blob_key(b->blob_key, plain_blob_key); if (ret) { pr_err("Unable to decrypt blob key: %i\n", ret); @@ -271,7 +282,10 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) ret = 0; out: - memzero_explicit(plain_blob_key, sizeof(plain_blob_key)); + if (plain_blob_key) { + memzero_explicit(plain_blob_key, AES_KEYSIZE_128); + kfree(plain_blob_key); + } return ret; } diff --git a/security/landlock/access.h b/security/landlock/access.h new file mode 100644 index 000000000000..74fd8f399fbd --- /dev/null +++ b/security/landlock/access.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Landlock LSM - Access types and helpers + * + * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> + * Copyright © 2018-2020 ANSSI + * Copyright © 2024-2025 Microsoft Corporation + */ + +#ifndef _SECURITY_LANDLOCK_ACCESS_H +#define _SECURITY_LANDLOCK_ACCESS_H + +#include <linux/bitops.h> +#include <linux/build_bug.h> +#include <linux/kernel.h> +#include <uapi/linux/landlock.h> + +#include "limits.h" + +/* + * All access rights that are denied by default whether they are handled or not + * by a ruleset/layer. This must be ORed with all ruleset->access_masks[] + * entries when we need to get the absolute handled access masks, see + * landlock_upgrade_handled_access_masks(). + */ +/* clang-format off */ +#define _LANDLOCK_ACCESS_FS_INITIALLY_DENIED ( \ + LANDLOCK_ACCESS_FS_REFER) +/* clang-format on */ + +typedef u16 access_mask_t; + +/* Makes sure all filesystem access rights can be stored. */ +static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_FS); +/* Makes sure all network access rights can be stored. */ +static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_NET); +/* Makes sure all scoped rights can be stored. */ +static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_SCOPE); +/* Makes sure for_each_set_bit() and for_each_clear_bit() calls are OK. */ +static_assert(sizeof(unsigned long) >= sizeof(access_mask_t)); + +/* Ruleset access masks. */ +struct access_masks { + access_mask_t fs : LANDLOCK_NUM_ACCESS_FS; + access_mask_t net : LANDLOCK_NUM_ACCESS_NET; + access_mask_t scope : LANDLOCK_NUM_SCOPE; +}; + +union access_masks_all { + struct access_masks masks; + u32 all; +}; + +/* Makes sure all fields are covered. */ +static_assert(sizeof(typeof_member(union access_masks_all, masks)) == + sizeof(typeof_member(union access_masks_all, all))); + +typedef u16 layer_mask_t; + +/* Makes sure all layers can be checked. */ +static_assert(BITS_PER_TYPE(layer_mask_t) >= LANDLOCK_MAX_NUM_LAYERS); + +/* Upgrades with all initially denied by default access rights. */ +static inline struct access_masks +landlock_upgrade_handled_access_masks(struct access_masks access_masks) +{ + /* + * All access rights that are denied by default whether they are + * explicitly handled or not. + */ + if (access_masks.fs) + access_masks.fs |= _LANDLOCK_ACCESS_FS_INITIALLY_DENIED; + + return access_masks; +} + +#endif /* _SECURITY_LANDLOCK_ACCESS_H */ diff --git a/security/landlock/fs.c b/security/landlock/fs.c index e31b97a9f175..71b9dc331aae 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -36,6 +36,7 @@ #include <uapi/linux/fiemap.h> #include <uapi/linux/landlock.h> +#include "access.h" #include "common.h" #include "cred.h" #include "fs.h" @@ -388,14 +389,6 @@ static bool is_nouser_or_private(const struct dentry *dentry) unlikely(IS_PRIVATE(d_backing_inode(dentry)))); } -static access_mask_t -get_handled_fs_accesses(const struct landlock_ruleset *const domain) -{ - /* Handles all initially denied by default access rights. */ - return landlock_union_access_masks(domain).fs | - LANDLOCK_ACCESS_FS_INITIALLY_DENIED; -} - static const struct access_masks any_fs = { .fs = ~0, }; @@ -572,6 +565,12 @@ static void test_no_more_access(struct kunit *const test) #undef NMA_TRUE #undef NMA_FALSE +static bool is_layer_masks_allowed( + layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS]) +{ + return !memchr_inv(layer_masks, 0, sizeof(*layer_masks)); +} + /* * Removes @layer_masks accesses that are not requested. * @@ -589,7 +588,8 @@ scope_to_request(const access_mask_t access_request, for_each_clear_bit(access_bit, &access_req, ARRAY_SIZE(*layer_masks)) (*layer_masks)[access_bit] = 0; - return !memchr_inv(layer_masks, 0, sizeof(*layer_masks)); + + return is_layer_masks_allowed(layer_masks); } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST @@ -778,16 +778,21 @@ static bool is_access_to_paths_allowed( if (WARN_ON_ONCE(domain->num_layers < 1 || !layer_masks_parent1)) return false; + allowed_parent1 = is_layer_masks_allowed(layer_masks_parent1); + if (unlikely(layer_masks_parent2)) { if (WARN_ON_ONCE(!dentry_child1)) return false; + + allowed_parent2 = is_layer_masks_allowed(layer_masks_parent2); + /* * For a double request, first check for potential privilege * escalation by looking at domain handled accesses (which are * a superset of the meaningful requested accesses). */ access_masked_parent1 = access_masked_parent2 = - get_handled_fs_accesses(domain); + landlock_union_access_masks(domain).fs; is_dom_check = true; } else { if (WARN_ON_ONCE(dentry_child1 || dentry_child2)) @@ -847,15 +852,6 @@ static bool is_access_to_paths_allowed( child1_is_directory, layer_masks_parent2, layer_masks_child2, child2_is_directory))) { - allowed_parent1 = scope_to_request( - access_request_parent1, layer_masks_parent1); - allowed_parent2 = scope_to_request( - access_request_parent2, layer_masks_parent2); - - /* Stops when all accesses are granted. */ - if (allowed_parent1 && allowed_parent2) - break; - /* * Now, downgrades the remaining checks from domain * handled accesses to requested accesses. @@ -863,15 +859,32 @@ static bool is_access_to_paths_allowed( is_dom_check = false; access_masked_parent1 = access_request_parent1; access_masked_parent2 = access_request_parent2; + + allowed_parent1 = + allowed_parent1 || + scope_to_request(access_masked_parent1, + layer_masks_parent1); + allowed_parent2 = + allowed_parent2 || + scope_to_request(access_masked_parent2, + layer_masks_parent2); + + /* Stops when all accesses are granted. */ + if (allowed_parent1 && allowed_parent2) + break; } rule = find_rule(domain, walker_path.dentry); - allowed_parent1 = landlock_unmask_layers( - rule, access_masked_parent1, layer_masks_parent1, - ARRAY_SIZE(*layer_masks_parent1)); - allowed_parent2 = landlock_unmask_layers( - rule, access_masked_parent2, layer_masks_parent2, - ARRAY_SIZE(*layer_masks_parent2)); + allowed_parent1 = allowed_parent1 || + landlock_unmask_layers( + rule, access_masked_parent1, + layer_masks_parent1, + ARRAY_SIZE(*layer_masks_parent1)); + allowed_parent2 = allowed_parent2 || + landlock_unmask_layers( + rule, access_masked_parent2, + layer_masks_parent2, + ARRAY_SIZE(*layer_masks_parent2)); /* Stops when a rule from each layer grants access. */ if (allowed_parent1 && allowed_parent2) @@ -895,8 +908,10 @@ jump_up: * access to internal filesystems (e.g. nsfs, which is * reachable through /proc/<pid>/ns/<namespace>). */ - allowed_parent1 = allowed_parent2 = - !!(walker_path.mnt->mnt_flags & MNT_INTERNAL); + if (walker_path.mnt->mnt_flags & MNT_INTERNAL) { + allowed_parent1 = true; + allowed_parent2 = true; + } break; } parent_dentry = dget_parent(walker_path.dentry); @@ -908,39 +923,29 @@ jump_up: return allowed_parent1 && allowed_parent2; } -static int check_access_path(const struct landlock_ruleset *const domain, - const struct path *const path, - access_mask_t access_request) -{ - layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; - - access_request = landlock_init_layer_masks( - domain, access_request, &layer_masks, LANDLOCK_KEY_INODE); - if (is_access_to_paths_allowed(domain, path, access_request, - &layer_masks, NULL, 0, NULL, NULL)) - return 0; - return -EACCES; -} - static int current_check_access_path(const struct path *const path, - const access_mask_t access_request) + access_mask_t access_request) { const struct landlock_ruleset *const dom = get_current_fs_domain(); + layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; if (!dom) return 0; - return check_access_path(dom, path, access_request); + + access_request = landlock_init_layer_masks( + dom, access_request, &layer_masks, LANDLOCK_KEY_INODE); + if (is_access_to_paths_allowed(dom, path, access_request, &layer_masks, + NULL, 0, NULL, NULL)) + return 0; + + return -EACCES; } -static access_mask_t get_mode_access(const umode_t mode) +static __attribute_const__ access_mask_t get_mode_access(const umode_t mode) { switch (mode & S_IFMT) { case S_IFLNK: return LANDLOCK_ACCESS_FS_MAKE_SYM; - case 0: - /* A zero mode translates to S_IFREG. */ - case S_IFREG: - return LANDLOCK_ACCESS_FS_MAKE_REG; case S_IFDIR: return LANDLOCK_ACCESS_FS_MAKE_DIR; case S_IFCHR: @@ -951,9 +956,12 @@ static access_mask_t get_mode_access(const umode_t mode) return LANDLOCK_ACCESS_FS_MAKE_FIFO; case S_IFSOCK: return LANDLOCK_ACCESS_FS_MAKE_SOCK; + case S_IFREG: + case 0: + /* A zero mode translates to S_IFREG. */ default: - WARN_ON_ONCE(1); - return 0; + /* Treats weird files as regular files. */ + return LANDLOCK_ACCESS_FS_MAKE_REG; } } @@ -1414,11 +1422,7 @@ static int hook_path_mknod(const struct path *const dir, struct dentry *const dentry, const umode_t mode, const unsigned int dev) { - const struct landlock_ruleset *const dom = get_current_fs_domain(); - - if (!dom) - return 0; - return check_access_path(dom, dir, get_mode_access(mode)); + return current_check_access_path(dir, get_mode_access(mode)); } static int hook_path_symlink(const struct path *const dir, diff --git a/security/landlock/fs.h b/security/landlock/fs.h index 1487e1f023a1..d445f411c26a 100644 --- a/security/landlock/fs.h +++ b/security/landlock/fs.h @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/rcupdate.h> +#include "access.h" #include "ruleset.h" #include "setup.h" diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c index a93bdbf52fff..241ce44375b6 100644 --- a/security/landlock/ruleset.c +++ b/security/landlock/ruleset.c @@ -8,11 +8,13 @@ #include <linux/bits.h> #include <linux/bug.h> +#include <linux/cleanup.h> #include <linux/compiler_types.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/lockdep.h> +#include <linux/mutex.h> #include <linux/overflow.h> #include <linux/rbtree.h> #include <linux/refcount.h> @@ -20,6 +22,7 @@ #include <linux/spinlock.h> #include <linux/workqueue.h> +#include "access.h" #include "limits.h" #include "object.h" #include "ruleset.h" @@ -384,7 +387,8 @@ static int merge_ruleset(struct landlock_ruleset *const dst, err = -EINVAL; goto out_unlock; } - dst->access_masks[dst->num_layers - 1] = src->access_masks[0]; + dst->access_masks[dst->num_layers - 1] = + landlock_upgrade_handled_access_masks(src->access_masks[0]); /* Merges the @src inode tree. */ err = merge_tree(dst, src, LANDLOCK_KEY_INODE); @@ -537,7 +541,7 @@ struct landlock_ruleset * landlock_merge_ruleset(struct landlock_ruleset *const parent, struct landlock_ruleset *const ruleset) { - struct landlock_ruleset *new_dom; + struct landlock_ruleset *new_dom __free(landlock_put_ruleset) = NULL; u32 num_layers; int err; @@ -557,29 +561,25 @@ landlock_merge_ruleset(struct landlock_ruleset *const parent, new_dom = create_ruleset(num_layers); if (IS_ERR(new_dom)) return new_dom; + new_dom->hierarchy = kzalloc(sizeof(*new_dom->hierarchy), GFP_KERNEL_ACCOUNT); - if (!new_dom->hierarchy) { - err = -ENOMEM; - goto out_put_dom; - } + if (!new_dom->hierarchy) + return ERR_PTR(-ENOMEM); + refcount_set(&new_dom->hierarchy->usage, 1); /* ...as a child of @parent... */ err = inherit_ruleset(parent, new_dom); if (err) - goto out_put_dom; + return ERR_PTR(err); /* ...and including @ruleset. */ err = merge_ruleset(new_dom, ruleset); if (err) - goto out_put_dom; + return ERR_PTR(err); - return new_dom; - -out_put_dom: - landlock_put_ruleset(new_dom); - return ERR_PTR(err); + return no_free_ptr(new_dom); } /* diff --git a/security/landlock/ruleset.h b/security/landlock/ruleset.h index 631e24d4ffe9..52f4f0af6ab0 100644 --- a/security/landlock/ruleset.h +++ b/security/landlock/ruleset.h @@ -9,58 +9,17 @@ #ifndef _SECURITY_LANDLOCK_RULESET_H #define _SECURITY_LANDLOCK_RULESET_H -#include <linux/bitops.h> -#include <linux/build_bug.h> -#include <linux/kernel.h> +#include <linux/cleanup.h> +#include <linux/err.h> #include <linux/mutex.h> #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/workqueue.h> -#include <uapi/linux/landlock.h> +#include "access.h" #include "limits.h" #include "object.h" -/* - * All access rights that are denied by default whether they are handled or not - * by a ruleset/layer. This must be ORed with all ruleset->access_masks[] - * entries when we need to get the absolute handled access masks. - */ -/* clang-format off */ -#define LANDLOCK_ACCESS_FS_INITIALLY_DENIED ( \ - LANDLOCK_ACCESS_FS_REFER) -/* clang-format on */ - -typedef u16 access_mask_t; -/* Makes sure all filesystem access rights can be stored. */ -static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_FS); -/* Makes sure all network access rights can be stored. */ -static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_NET); -/* Makes sure all scoped rights can be stored. */ -static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_SCOPE); -/* Makes sure for_each_set_bit() and for_each_clear_bit() calls are OK. */ -static_assert(sizeof(unsigned long) >= sizeof(access_mask_t)); - -/* Ruleset access masks. */ -struct access_masks { - access_mask_t fs : LANDLOCK_NUM_ACCESS_FS; - access_mask_t net : LANDLOCK_NUM_ACCESS_NET; - access_mask_t scope : LANDLOCK_NUM_SCOPE; -}; - -union access_masks_all { - struct access_masks masks; - u32 all; -}; - -/* Makes sure all fields are covered. */ -static_assert(sizeof(typeof_member(union access_masks_all, masks)) == - sizeof(typeof_member(union access_masks_all, all))); - -typedef u16 layer_mask_t; -/* Makes sure all layers can be checked. */ -static_assert(BITS_PER_TYPE(layer_mask_t) >= LANDLOCK_MAX_NUM_LAYERS); - /** * struct landlock_layer - Access rights for a given layer */ @@ -252,6 +211,9 @@ landlock_create_ruleset(const access_mask_t access_mask_fs, void landlock_put_ruleset(struct landlock_ruleset *const ruleset); void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset); +DEFINE_FREE(landlock_put_ruleset, struct landlock_ruleset *, + if (!IS_ERR_OR_NULL(_T)) landlock_put_ruleset(_T)) + int landlock_insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, const access_mask_t access); @@ -366,7 +328,7 @@ landlock_get_fs_access_mask(const struct landlock_ruleset *const ruleset, { /* Handles all initially denied by default access rights. */ return ruleset->access_masks[layer_level].fs | - LANDLOCK_ACCESS_FS_INITIALLY_DENIED; + _LANDLOCK_ACCESS_FS_INITIALLY_DENIED; } static inline access_mask_t diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 4ed8e70c25ed..a9760d252fc2 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -10,6 +10,7 @@ #include <linux/anon_inodes.h> #include <linux/build_bug.h> #include <linux/capability.h> +#include <linux/cleanup.h> #include <linux/compiler_types.h> #include <linux/dcache.h> #include <linux/err.h> @@ -398,8 +399,7 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, const enum landlock_rule_type, rule_type, const void __user *const, rule_attr, const __u32, flags) { - struct landlock_ruleset *ruleset; - int err; + struct landlock_ruleset *ruleset __free(landlock_put_ruleset) = NULL; if (!is_initialized()) return -EOPNOTSUPP; @@ -415,17 +415,12 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, switch (rule_type) { case LANDLOCK_RULE_PATH_BENEATH: - err = add_rule_path_beneath(ruleset, rule_attr); - break; + return add_rule_path_beneath(ruleset, rule_attr); case LANDLOCK_RULE_NET_PORT: - err = add_rule_net_port(ruleset, rule_attr); - break; + return add_rule_net_port(ruleset, rule_attr); default: - err = -EINVAL; - break; + return -EINVAL; } - landlock_put_ruleset(ruleset); - return err; } /* Enforcement */ @@ -456,10 +451,10 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, flags) { - struct landlock_ruleset *new_dom, *ruleset; + struct landlock_ruleset *new_dom, + *ruleset __free(landlock_put_ruleset) = NULL; struct cred *new_cred; struct landlock_cred_security *new_llcred; - int err; if (!is_initialized()) return -EOPNOTSUPP; @@ -483,10 +478,9 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, /* Prepares new credentials. */ new_cred = prepare_creds(); - if (!new_cred) { - err = -ENOMEM; - goto out_put_ruleset; - } + if (!new_cred) + return -ENOMEM; + new_llcred = landlock_cred(new_cred); /* @@ -495,21 +489,12 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, */ new_dom = landlock_merge_ruleset(new_llcred->domain, ruleset); if (IS_ERR(new_dom)) { - err = PTR_ERR(new_dom); - goto out_put_creds; + abort_creds(new_cred); + return PTR_ERR(new_dom); } /* Replaces the old (prepared) domain. */ landlock_put_ruleset(new_llcred->domain); new_llcred->domain = new_dom; - - landlock_put_ruleset(ruleset); return commit_creds(new_cred); - -out_put_creds: - abort_creds(new_cred); - -out_put_ruleset: - landlock_put_ruleset(ruleset); - return err; } diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c index f2bdbd55aa2b..cf83afa1d879 100644 --- a/security/lockdown/lockdown.c +++ b/security/lockdown/lockdown.c @@ -96,7 +96,7 @@ static int __init lockdown_lsm_init(void) static ssize_t lockdown_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { - char temp[80]; + char temp[80] = ""; int i, offset = 0; for (i = 0; i < ARRAY_SIZE(lockdown_levels); i++) { diff --git a/security/lsm_audit.c b/security/lsm_audit.c index 9a8352972086..52db886dbba8 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -171,7 +171,7 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb, static inline void print_ipv6_addr(struct audit_buffer *ab, const struct in6_addr *addr, __be16 port, - char *name1, char *name2) + const char *name1, const char *name2) { if (!ipv6_addr_any(addr)) audit_log_format(ab, " %s=%pI6c", name1, addr); @@ -180,7 +180,7 @@ static inline void print_ipv6_addr(struct audit_buffer *ab, } static inline void print_ipv4_addr(struct audit_buffer *ab, __be32 addr, - __be16 port, char *name1, char *name2) + __be16 port, const char *name1, const char *name2) { if (addr) audit_log_format(ab, " %s=%pI4", name1, &addr); @@ -299,10 +299,10 @@ static void dump_common_audit_data(struct audit_buffer *ab, if (tsk) { pid_t pid = task_tgid_nr(tsk); if (pid) { - char comm[sizeof(tsk->comm)]; + char tskcomm[sizeof(tsk->comm)]; audit_log_format(ab, " opid=%d ocomm=", pid); audit_log_untrustedstring(ab, - get_task_comm(comm, tsk)); + get_task_comm(tskcomm, tsk)); } } break; @@ -425,6 +425,9 @@ static void dump_common_audit_data(struct audit_buffer *ab, case LSM_AUDIT_DATA_ANONINODE: audit_log_format(ab, " anonclass=%s", a->u.anonclass); break; + case LSM_AUDIT_DATA_NLMSGTYPE: + audit_log_format(ab, " nl-msgtype=%hu", a->u.nlmsg_type); + break; } /* switch (a->type) */ } diff --git a/security/safesetid/securityfs.c b/security/safesetid/securityfs.c index 25310468bcdd..8e1ffd70b18a 100644 --- a/security/safesetid/securityfs.c +++ b/security/safesetid/securityfs.c @@ -143,6 +143,9 @@ static ssize_t handle_policy_update(struct file *file, char *buf, *p, *end; int err; + if (len >= KMALLOC_MAX_SIZE) + return -EINVAL; + pol = kmalloc(sizeof(struct setid_ruleset), GFP_KERNEL); if (!pol) return -ENOMEM; diff --git a/security/security.c b/security/security.c index 09664e09fec9..143561ebc3e8 100644 --- a/security/security.c +++ b/security/security.c @@ -1248,6 +1248,12 @@ int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) * to 1 if AT_SECURE should be set to request libc enable secure mode. @bprm * contains the linux_binprm structure. * + * If execveat(2) is called with the AT_EXECVE_CHECK flag, bprm->is_check is + * set. The result must be the same as without this flag even if the execution + * will never really happen and @bprm will always be dropped. + * + * This hook must not change current->cred, only @bprm->cred. + * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_creds_for_exec(struct linux_binprm *bprm) @@ -1735,8 +1741,7 @@ void security_inode_free(struct inode *inode) * @mode: mode used to determine resource type * @name: name of the last path component * @xattr_name: name of the security/LSM xattr - * @ctx: pointer to the resulting LSM context - * @ctxlen: length of @ctx + * @lsmctx: pointer to the resulting LSM context * * Compute a context for a dentry as the inode is not yet available since NFSv4 * has no label backed by an EA anyway. It is important to note that @@ -1746,11 +1751,11 @@ void security_inode_free(struct inode *inode) */ int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, - const char **xattr_name, void **ctx, - u32 *ctxlen) + const char **xattr_name, + struct lsm_context *lsmctx) { return call_int_hook(dentry_init_security, dentry, mode, name, - xattr_name, ctx, ctxlen); + xattr_name, lsmctx); } EXPORT_SYMBOL(security_dentry_init_security); @@ -3098,6 +3103,10 @@ int security_file_receive(struct file *file) * Save open-time permission checking state for later use upon file_permission, * and recheck access if anything has changed since inode_permission. * + * We can check if a file is opened for execution (e.g. execve(2) call), either + * directly or indirectly (e.g. ELF's ld.so) by checking file->f_flags & + * __FMODE_EXEC . + * * Return: Returns 0 if permission is granted. */ int security_file_open(struct file *file) @@ -4139,10 +4148,8 @@ int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, if (base) uctx = (struct lsm_ctx __user *)(base + total); rc = scall->hl->hook.getselfattr(attr, uctx, &entrysize, flags); - if (rc == -EOPNOTSUPP) { - rc = 0; + if (rc == -EOPNOTSUPP) continue; - } if (rc == -E2BIG) { rc = 0; left = 0; @@ -4304,40 +4311,36 @@ EXPORT_SYMBOL(security_ismaclabel); /** * security_secid_to_secctx() - Convert a secid to a secctx * @secid: secid - * @secdata: secctx - * @seclen: secctx length + * @cp: the LSM context * - * Convert secid to security context. If @secdata is NULL the length of the - * result will be returned in @seclen, but no @secdata will be returned. This + * Convert secid to security context. If @cp is NULL the length of the + * result will be returned, but no data will be returned. This * does mean that the length could change between calls to check the length and - * the next call which actually allocates and returns the @secdata. + * the next call which actually allocates and returns the data. * - * Return: Return 0 on success, error on failure. + * Return: Return length of data on success, error on failure. */ -int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +int security_secid_to_secctx(u32 secid, struct lsm_context *cp) { - return call_int_hook(secid_to_secctx, secid, secdata, seclen); + return call_int_hook(secid_to_secctx, secid, cp); } EXPORT_SYMBOL(security_secid_to_secctx); /** * security_lsmprop_to_secctx() - Convert a lsm_prop to a secctx * @prop: lsm specific information - * @secdata: secctx - * @seclen: secctx length + * @cp: the LSM context * - * Convert a @prop entry to security context. If @secdata is NULL the - * length of the result will be returned in @seclen, but no @secdata - * will be returned. This does mean that the length could change between - * calls to check the length and the next call which actually allocates - * and returns the @secdata. + * Convert a @prop entry to security context. If @cp is NULL the + * length of the result will be returned. This does mean that the + * length could change between calls to check the length and the + * next call which actually allocates and returns the @cp. * - * Return: Return 0 on success, error on failure. + * Return: Return length of data on success, error on failure. */ -int security_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, - u32 *seclen) +int security_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp) { - return call_int_hook(lsmprop_to_secctx, prop, secdata, seclen); + return call_int_hook(lsmprop_to_secctx, prop, cp); } EXPORT_SYMBOL(security_lsmprop_to_secctx); @@ -4360,14 +4363,14 @@ EXPORT_SYMBOL(security_secctx_to_secid); /** * security_release_secctx() - Free a secctx buffer - * @secdata: secctx - * @seclen: length of secctx + * @cp: the security context * * Release the security context. */ -void security_release_secctx(char *secdata, u32 seclen) +void security_release_secctx(struct lsm_context *cp) { - call_void_hook(release_secctx, secdata, seclen); + call_void_hook(release_secctx, cp); + memset(cp, 0, sizeof(*cp)); } EXPORT_SYMBOL(security_release_secctx); @@ -4430,17 +4433,17 @@ EXPORT_SYMBOL(security_inode_setsecctx); /** * security_inode_getsecctx() - Get the security label of an inode * @inode: inode - * @ctx: secctx - * @ctxlen: length of secctx + * @cp: security context * - * On success, returns 0 and fills out @ctx and @ctxlen with the security - * context for the given @inode. + * On success, returns 0 and fills out @cp with the security context + * for the given @inode. * * Return: Returns 0 on success, error on failure. */ -int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) +int security_inode_getsecctx(struct inode *inode, struct lsm_context *cp) { - return call_int_hook(inode_getsecctx, inode, ctx, ctxlen); + memset(cp, 0, sizeof(*cp)); + return call_int_hook(inode_getsecctx, inode, cp); } EXPORT_SYMBOL(security_inode_getsecctx); diff --git a/security/selinux/Makefile b/security/selinux/Makefile index 86f0575f670d..66e56e9011df 100644 --- a/security/selinux/Makefile +++ b/security/selinux/Makefile @@ -33,11 +33,10 @@ $(addprefix $(obj)/,$(selinux-y)): $(obj)/flask.h quiet_cmd_genhdrs = GEN $(addprefix $(obj)/,$(genhdrs)) cmd_genhdrs = $< $(addprefix $(obj)/,$(genhdrs)) -# see the note above, replace the $targets and 'flask.h' rule with the lines -# below: -# targets += $(genhdrs) +targets += $(genhdrs) + +# see the note above, replace the 'flask.h' rule with the line below: # $(addprefix $(obj)/,$(genhdrs)) &: $(obj)/genheaders FORCE -targets += flask.h $(obj)/flask.h: $(obj)/genheaders FORCE $(call if_changed,genhdrs) diff --git a/security/selinux/avc.c b/security/selinux/avc.c index cc0b0af20296..1f2680bcc43a 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -174,13 +174,15 @@ int avc_get_hash_stats(char *page) * using a linked list for extended_perms_decision lookup because the list is * always small. i.e. less than 5, typically 1 */ -static struct extended_perms_decision *avc_xperms_decision_lookup(u8 driver, - struct avc_xperms_node *xp_node) +static struct extended_perms_decision * +avc_xperms_decision_lookup(u8 driver, u8 base_perm, + struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node; list_for_each_entry(xpd_node, &xp_node->xpd_head, xpd_list) { - if (xpd_node->xpd.driver == driver) + if (xpd_node->xpd.driver == driver && + xpd_node->xpd.base_perm == base_perm) return &xpd_node->xpd; } return NULL; @@ -205,11 +207,12 @@ avc_xperms_has_perm(struct extended_perms_decision *xpd, } static void avc_xperms_allow_perm(struct avc_xperms_node *xp_node, - u8 driver, u8 perm) + u8 driver, u8 base_perm, u8 perm) { struct extended_perms_decision *xpd; security_xperm_set(xp_node->xp.drivers.p, driver); - xpd = avc_xperms_decision_lookup(driver, xp_node); + xp_node->xp.base_perms |= base_perm; + xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node); if (xpd && xpd->allowed) security_xperm_set(xpd->allowed->p, perm); } @@ -245,6 +248,7 @@ static void avc_xperms_free(struct avc_xperms_node *xp_node) static void avc_copy_xperms_decision(struct extended_perms_decision *dest, struct extended_perms_decision *src) { + dest->base_perm = src->base_perm; dest->driver = src->driver; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) @@ -272,6 +276,7 @@ static inline void avc_quick_copy_xperms_decision(u8 perm, */ u8 i = perm >> 5; + dest->base_perm = src->base_perm; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) dest->allowed->p[i] = src->allowed->p[i]; @@ -357,6 +362,7 @@ static int avc_xperms_populate(struct avc_node *node, memcpy(dest->xp.drivers.p, src->xp.drivers.p, sizeof(dest->xp.drivers.p)); dest->xp.len = src->xp.len; + dest->xp.base_perms = src->xp.base_perms; /* for each source xpd allocate a destination xpd and copy */ list_for_each_entry(src_xpd, &src->xpd_head, xpd_list) { @@ -807,6 +813,7 @@ out: * @event : Updating event * @perms : Permission mask bits * @driver: xperm driver information + * @base_perm: the base permission associated with the extended permission * @xperm: xperm permissions * @ssid: AVC entry source sid * @tsid: AVC entry target sid @@ -820,10 +827,9 @@ out: * otherwise, this function updates the AVC entry. The original AVC-entry object * will release later by RCU. */ -static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, - u32 tsid, u16 tclass, u32 seqno, - struct extended_perms_decision *xpd, - u32 flags) +static int avc_update_node(u32 event, u32 perms, u8 driver, u8 base_perm, + u8 xperm, u32 ssid, u32 tsid, u16 tclass, u32 seqno, + struct extended_perms_decision *xpd, u32 flags) { u32 hvalue; int rc = 0; @@ -880,7 +886,7 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, case AVC_CALLBACK_GRANT: node->ae.avd.allowed |= perms; if (node->ae.xp_node && (flags & AVC_EXTENDED_PERMS)) - avc_xperms_allow_perm(node->ae.xp_node, driver, xperm); + avc_xperms_allow_perm(node->ae.xp_node, driver, base_perm, xperm); break; case AVC_CALLBACK_TRY_REVOKE: case AVC_CALLBACK_REVOKE: @@ -987,10 +993,9 @@ static noinline void avc_compute_av(u32 ssid, u32 tsid, u16 tclass, avc_insert(ssid, tsid, tclass, avd, xp_node); } -static noinline int avc_denied(u32 ssid, u32 tsid, - u16 tclass, u32 requested, - u8 driver, u8 xperm, unsigned int flags, - struct av_decision *avd) +static noinline int avc_denied(u32 ssid, u32 tsid, u16 tclass, u32 requested, + u8 driver, u8 base_perm, u8 xperm, + unsigned int flags, struct av_decision *avd) { if (flags & AVC_STRICT) return -EACCES; @@ -999,7 +1004,7 @@ static noinline int avc_denied(u32 ssid, u32 tsid, !(avd->flags & AVD_FLAGS_PERMISSIVE)) return -EACCES; - avc_update_node(AVC_CALLBACK_GRANT, requested, driver, + avc_update_node(AVC_CALLBACK_GRANT, requested, driver, base_perm, xperm, ssid, tsid, tclass, avd->seqno, NULL, flags); return 0; } @@ -1012,7 +1017,8 @@ static noinline int avc_denied(u32 ssid, u32 tsid, * driver field is used to specify which set contains the permission. */ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, - u8 driver, u8 xperm, struct common_audit_data *ad) + u8 driver, u8 base_perm, u8 xperm, + struct common_audit_data *ad) { struct avc_node *node; struct av_decision avd; @@ -1047,22 +1053,23 @@ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, local_xpd.auditallow = &auditallow; local_xpd.dontaudit = &dontaudit; - xpd = avc_xperms_decision_lookup(driver, xp_node); + xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node); if (unlikely(!xpd)) { /* * Compute the extended_perms_decision only if the driver - * is flagged + * is flagged and the base permission is known. */ - if (!security_xperm_test(xp_node->xp.drivers.p, driver)) { + if (!security_xperm_test(xp_node->xp.drivers.p, driver) || + !(xp_node->xp.base_perms & base_perm)) { avd.allowed &= ~requested; goto decision; } rcu_read_unlock(); - security_compute_xperms_decision(ssid, tsid, tclass, - driver, &local_xpd); + security_compute_xperms_decision(ssid, tsid, tclass, driver, + base_perm, &local_xpd); rcu_read_lock(); - avc_update_node(AVC_CALLBACK_ADD_XPERMS, requested, - driver, xperm, ssid, tsid, tclass, avd.seqno, + avc_update_node(AVC_CALLBACK_ADD_XPERMS, requested, driver, + base_perm, xperm, ssid, tsid, tclass, avd.seqno, &local_xpd, 0); } else { avc_quick_copy_xperms_decision(xperm, &local_xpd, xpd); @@ -1075,8 +1082,8 @@ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, decision: denied = requested & ~(avd.allowed); if (unlikely(denied)) - rc = avc_denied(ssid, tsid, tclass, requested, - driver, xperm, AVC_EXTENDED_PERMS, &avd); + rc = avc_denied(ssid, tsid, tclass, requested, driver, + base_perm, xperm, AVC_EXTENDED_PERMS, &avd); rcu_read_unlock(); @@ -1110,7 +1117,7 @@ static noinline int avc_perm_nonode(u32 ssid, u32 tsid, u16 tclass, avc_compute_av(ssid, tsid, tclass, avd, &xp_node); denied = requested & ~(avd->allowed); if (unlikely(denied)) - return avc_denied(ssid, tsid, tclass, requested, 0, 0, + return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0, flags, avd); return 0; } @@ -1158,7 +1165,7 @@ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid, rcu_read_unlock(); if (unlikely(denied)) - return avc_denied(ssid, tsid, tclass, requested, 0, 0, + return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0, flags, avd); return 0; } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 366c87a40bd1..7b867dfec88b 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -407,7 +407,7 @@ static const struct { static int match_opt_prefix(char *s, int l, char **arg) { - int i; + unsigned int i; for (i = 0; i < ARRAY_SIZE(tokens); i++) { size_t len = tokens[i].len; @@ -2869,8 +2869,8 @@ static void selinux_inode_free_security(struct inode *inode) static int selinux_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, - const char **xattr_name, void **ctx, - u32 *ctxlen) + const char **xattr_name, + struct lsm_context *cp) { u32 newsid; int rc; @@ -2885,8 +2885,8 @@ static int selinux_dentry_init_security(struct dentry *dentry, int mode, if (xattr_name) *xattr_name = XATTR_NAME_SELINUX; - return security_sid_to_context(newsid, (char **)ctx, - ctxlen); + cp->id = LSM_ID_SELINUX; + return security_sid_to_context(newsid, &cp->context, &cp->len); } static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, @@ -3135,7 +3135,7 @@ static int selinux_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, const struct cred *cred = current_cred(); struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = iattr->ia_valid; - __u32 av = FILE__WRITE; + u32 av = FILE__WRITE; /* ATTR_FORCE is just used for ATTR_KILL_S[UG]ID. */ if (ia_valid & ATTR_FORCE) { @@ -3404,7 +3404,8 @@ static int selinux_path_notify(const struct path *path, u64 mask, perm |= FILE__WATCH_WITH_PERM; /* watches on read-like events need the file:watch_reads permission */ - if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_CLOSE_NOWRITE)) + if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_PRE_ACCESS | + FS_CLOSE_NOWRITE)) perm |= FILE__WATCH_READS; return path_has_perm(current_cred(), path, perm); @@ -3688,8 +3689,8 @@ static int ioctl_has_perm(const struct cred *cred, struct file *file, return 0; isec = inode_security(inode); - rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, - requested, driver, xperm, &ad); + rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, requested, + driver, AVC_EXT_IOCTL, xperm, &ad); out: return rc; } @@ -4835,7 +4836,7 @@ out: return err; err_af: /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */ - if (sksec->sclass == SECCLASS_SCTP_SOCKET) + if (sk->sk_protocol == IPPROTO_SCTP) return -EINVAL; return -EAFNOSUPPORT; } @@ -5939,20 +5940,20 @@ static int nlmsg_sock_has_extended_perms(struct sock *sk, u32 perms, u16 nlmsg_t { struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; - struct lsm_network_audit net; u8 driver; u8 xperm; if (sock_skip_has_perm(sksec->sid)) return 0; - ad_net_init_from_sk(&ad, &net, sk); + ad.type = LSM_AUDIT_DATA_NLMSGTYPE; + ad.u.nlmsg_type = nlmsg_type; driver = nlmsg_type >> 8; xperm = nlmsg_type & 0xff; return avc_has_extended_perms(current_sid(), sksec->sid, sksec->sclass, - perms, driver, xperm, &ad); + perms, driver, AVC_EXT_NLMSG, xperm, &ad); } static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) @@ -6640,15 +6641,28 @@ static int selinux_ismaclabel(const char *name) return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0); } -static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +static int selinux_secid_to_secctx(u32 secid, struct lsm_context *cp) { - return security_sid_to_context(secid, secdata, seclen); + u32 seclen; + int ret; + + if (cp) { + cp->id = LSM_ID_SELINUX; + ret = security_sid_to_context(secid, &cp->context, &cp->len); + if (ret < 0) + return ret; + return cp->len; + } + ret = security_sid_to_context(secid, NULL, &seclen); + if (ret < 0) + return ret; + return seclen; } -static int selinux_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, - u32 *seclen) +static int selinux_lsmprop_to_secctx(struct lsm_prop *prop, + struct lsm_context *cp) { - return selinux_secid_to_secctx(prop->selinux.secid, secdata, seclen); + return selinux_secid_to_secctx(prop->selinux.secid, cp); } static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) @@ -6657,9 +6671,13 @@ static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) secid, GFP_KERNEL); } -static void selinux_release_secctx(char *secdata, u32 seclen) +static void selinux_release_secctx(struct lsm_context *cp) { - kfree(secdata); + if (cp->id == LSM_ID_SELINUX) { + kfree(cp->context); + cp->context = NULL; + cp->id = LSM_ID_UNDEF; + } } static void selinux_inode_invalidate_secctx(struct inode *inode) @@ -6691,14 +6709,16 @@ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) ctx, ctxlen, 0, NULL); } -static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) +static int selinux_inode_getsecctx(struct inode *inode, struct lsm_context *cp) { - int len = 0; + int len; len = selinux_inode_getsecurity(&nop_mnt_idmap, inode, - XATTR_SELINUX_SUFFIX, ctx, true); + XATTR_SELINUX_SUFFIX, + (void **)&cp->context, true); if (len < 0) return len; - *ctxlen = len; + cp->len = len; + cp->id = LSM_ID_SELINUX; return 0; } #ifdef CONFIG_KEYS diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h index 96a614d47df8..281f40103663 100644 --- a/security/selinux/include/avc.h +++ b/security/selinux/include/avc.h @@ -136,8 +136,11 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid, u16 tclass, u32 requested, int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata); +#define AVC_EXT_IOCTL (1 << 0) /* Cache entry for an ioctl extended permission */ +#define AVC_EXT_NLMSG (1 << 1) /* Cache entry for an nlmsg extended permission */ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, - u8 driver, u8 perm, struct common_audit_data *ad); + u8 driver, u8 base_perm, u8 perm, + struct common_audit_data *ad); u32 avc_policy_seqno(void); diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 2bc20135324a..03e82477dce9 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -179,7 +179,7 @@ const struct security_class_mapping secclass_map[] = { { "anon_inode", { COMMON_FILE_PERMS, NULL } }, { "io_uring", { "override_creds", "sqpoll", "cmd", NULL } }, { "user_namespace", { "create", NULL } }, - { NULL } + /* last one */ { NULL, {} } }; #ifdef __KERNEL__ /* avoid this check when building host programs */ diff --git a/security/selinux/include/conditional.h b/security/selinux/include/conditional.h index 5910bb7c2eca..060833e2dba2 100644 --- a/security/selinux/include/conditional.h +++ b/security/selinux/include/conditional.h @@ -16,7 +16,7 @@ int security_get_bools(struct selinux_policy *policy, u32 *len, char ***names, int **values); -int security_set_bools(u32 len, int *values); +int security_set_bools(u32 len, const int *values); int security_get_bool_value(u32 index); diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index c7f2731abd03..8b4c2aa35839 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -46,10 +46,11 @@ #define POLICYDB_VERSION_INFINIBAND 31 #define POLICYDB_VERSION_GLBLUB 32 #define POLICYDB_VERSION_COMP_FTRANS 33 /* compressed filename transitions */ +#define POLICYDB_VERSION_COND_XPERMS 34 /* extended permissions in conditional policies */ /* Range of policy versions we understand*/ #define POLICYDB_VERSION_MIN POLICYDB_VERSION_BASE -#define POLICYDB_VERSION_MAX POLICYDB_VERSION_COMP_FTRANS +#define POLICYDB_VERSION_MAX POLICYDB_VERSION_COND_XPERMS /* Mask for just the mount related flags */ #define SE_MNTMASK 0x0f @@ -239,6 +240,7 @@ struct extended_perms_data { struct extended_perms_decision { u8 used; u8 driver; + u8 base_perm; struct extended_perms_data *allowed; struct extended_perms_data *auditallow; struct extended_perms_data *dontaudit; @@ -246,6 +248,7 @@ struct extended_perms_decision { struct extended_perms { u16 len; /* length associated decision chain */ + u8 base_perms; /* which base permissions are covered */ struct extended_perms_data drivers; /* flag drivers that are used */ }; @@ -257,6 +260,7 @@ void security_compute_av(u32 ssid, u32 tsid, u16 tclass, struct extended_perms *xperms); void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 tclass, u8 driver, + u8 base_perm, struct extended_perms_decision *xpermd); void security_compute_av_user(u32 ssid, u32 tsid, u16 tclass, @@ -289,7 +293,7 @@ int security_context_to_sid_default(const char *scontext, u32 scontext_len, int security_context_to_sid_force(const char *scontext, u32 scontext_len, u32 *sid); -int security_get_user_sids(u32 callsid, char *username, u32 **sids, u32 *nel); +int security_get_user_sids(u32 fromsid, const char *username, u32 **sids, u32 *nel); int security_port_sid(u8 protocol, u16 port, u32 *out_sid); @@ -307,7 +311,7 @@ int security_validate_transition(u32 oldsid, u32 newsid, u32 tasksid, int security_validate_transition_user(u32 oldsid, u32 newsid, u32 tasksid, u16 tclass); -int security_bounded_transition(u32 oldsid, u32 newsid); +int security_bounded_transition(u32 old_sid, u32 new_sid); int security_sid_mls_copy(u32 sid, u32 mls_sid, u32 *new_sid); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 6cd5bb0ba380..47480eb2189b 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1515,7 +1515,7 @@ static const struct file_operations sel_avc_hash_stats_ops = { #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS static struct avc_cache_stats *sel_avc_get_stat_idx(loff_t *idx) { - int cpu; + loff_t cpu; for (cpu = *idx; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) @@ -2001,7 +2001,7 @@ static int sel_fill_super(struct super_block *sb, struct fs_context *fc) [SEL_POLICY] = {"policy", &sel_policy_ops, S_IRUGO}, [SEL_VALIDATE_TRANS] = {"validatetrans", &sel_transition_ops, S_IWUGO}, - /* last one */ {""} + /* last one */ {"", NULL, 0} }; ret = selinux_fs_info_create(sb); diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c index 8e400dd736b7..c2c31521cace 100644 --- a/security/selinux/ss/avtab.c +++ b/security/selinux/ss/avtab.c @@ -336,10 +336,10 @@ static const uint16_t spec_order[] = { }; /* clang-format on */ -int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, +int avtab_read_item(struct avtab *a, struct policy_file *fp, struct policydb *pol, int (*insertf)(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p), - void *p) + void *p, bool conditional) { __le16 buf16[4]; u16 enabled; @@ -457,6 +457,13 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, "was specified\n", vers); return -EINVAL; + } else if ((vers < POLICYDB_VERSION_COND_XPERMS) && + (key.specified & AVTAB_XPERMS) && conditional) { + pr_err("SELinux: avtab: policy version %u does not " + "support extended permissions rules in conditional " + "policies and one was specified\n", + vers); + return -EINVAL; } else if (key.specified & AVTAB_XPERMS) { memset(&xperms, 0, sizeof(struct avtab_extended_perms)); rc = next_entry(&xperms.specified, fp, sizeof(u8)); @@ -500,7 +507,7 @@ static int avtab_insertf(struct avtab *a, const struct avtab_key *k, return avtab_insert(a, k, d); } -int avtab_read(struct avtab *a, void *fp, struct policydb *pol) +int avtab_read(struct avtab *a, struct policy_file *fp, struct policydb *pol) { int rc; __le32 buf[1]; @@ -523,7 +530,7 @@ int avtab_read(struct avtab *a, void *fp, struct policydb *pol) goto bad; for (i = 0; i < nel; i++) { - rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL); + rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL, false); if (rc) { if (rc == -ENOMEM) pr_err("SELinux: avtab: out of memory\n"); @@ -543,7 +550,7 @@ bad: goto out; } -int avtab_write_item(struct policydb *p, const struct avtab_node *cur, void *fp) +int avtab_write_item(struct policydb *p, const struct avtab_node *cur, struct policy_file *fp) { __le16 buf16[4]; __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)]; @@ -579,7 +586,7 @@ int avtab_write_item(struct policydb *p, const struct avtab_node *cur, void *fp) return 0; } -int avtab_write(struct policydb *p, struct avtab *a, void *fp) +int avtab_write(struct policydb *p, struct avtab *a, struct policy_file *fp) { u32 i; int rc = 0; diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h index f4407185401c..850b3453f259 100644 --- a/security/selinux/ss/avtab.h +++ b/security/selinux/ss/avtab.h @@ -89,7 +89,7 @@ struct avtab { }; void avtab_init(struct avtab *h); -int avtab_alloc(struct avtab *, u32); +int avtab_alloc(struct avtab *h, u32 nrules); int avtab_alloc_dup(struct avtab *new, const struct avtab *orig); void avtab_destroy(struct avtab *h); @@ -105,15 +105,16 @@ static inline void avtab_hash_eval(struct avtab *h, const char *tag) #endif struct policydb; -int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, +struct policy_file; +int avtab_read_item(struct avtab *a, struct policy_file *fp, struct policydb *pol, int (*insert)(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p), - void *p); + void *p, bool conditional); -int avtab_read(struct avtab *a, void *fp, struct policydb *pol); +int avtab_read(struct avtab *a, struct policy_file *fp, struct policydb *pol); int avtab_write_item(struct policydb *p, const struct avtab_node *cur, - void *fp); -int avtab_write(struct policydb *p, struct avtab *a, void *fp); + struct policy_file *fp); +int avtab_write(struct policydb *p, struct avtab *a, struct policy_file *fp); struct avtab_node *avtab_insert_nonunique(struct avtab *h, const struct avtab_key *key, diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index 64ba95e40a6f..1bebfcb9c6a1 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -206,7 +206,7 @@ static int bool_isvalid(struct cond_bool_datum *b) return 1; } -int cond_read_bool(struct policydb *p, struct symtab *s, void *fp) +int cond_read_bool(struct policydb *p, struct symtab *s, struct policy_file *fp) { char *key = NULL; struct cond_bool_datum *booldatum; @@ -230,17 +230,11 @@ int cond_read_bool(struct policydb *p, struct symtab *s, void *fp) goto err; len = le32_to_cpu(buf[2]); - if (((len == 0) || (len == (u32)-1))) - goto err; - rc = -ENOMEM; - key = kmalloc(len + 1, GFP_KERNEL); - if (!key) - goto err; - rc = next_entry(key, fp, len); + rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto err; - key[len] = '\0'; + rc = symtab_insert(s, key, booldatum); if (rc) goto err; @@ -323,7 +317,7 @@ static int cond_insertf(struct avtab *a, const struct avtab_key *k, return 0; } -static int cond_read_av_list(struct policydb *p, void *fp, +static int cond_read_av_list(struct policydb *p, struct policy_file *fp, struct cond_av_list *list, struct cond_av_list *other) { @@ -349,7 +343,7 @@ static int cond_read_av_list(struct policydb *p, void *fp, for (i = 0; i < len; i++) { data.dst = &list->nodes[i]; rc = avtab_read_item(&p->te_cond_avtab, fp, p, cond_insertf, - &data); + &data, true); if (rc) { kfree(list->nodes); list->nodes = NULL; @@ -375,7 +369,7 @@ static int expr_node_isvalid(struct policydb *p, struct cond_expr_node *expr) return 1; } -static int cond_read_node(struct policydb *p, struct cond_node *node, void *fp) +static int cond_read_node(struct policydb *p, struct cond_node *node, struct policy_file *fp) { __le32 buf[2]; u32 i, len; @@ -415,7 +409,7 @@ static int cond_read_node(struct policydb *p, struct cond_node *node, void *fp) return cond_read_av_list(p, fp, &node->false_list, &node->true_list); } -int cond_read_list(struct policydb *p, void *fp) +int cond_read_list(struct policydb *p, struct policy_file *fp) { __le32 buf[1]; u32 i, len; @@ -453,7 +447,7 @@ int cond_write_bool(void *vkey, void *datum, void *ptr) char *key = vkey; struct cond_bool_datum *booldatum = datum; struct policy_data *pd = ptr; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; __le32 buf[3]; u32 len; int rc; @@ -536,7 +530,7 @@ static int cond_write_node(struct policydb *p, struct cond_node *node, return 0; } -int cond_write_list(struct policydb *p, void *fp) +int cond_write_list(struct policydb *p, struct policy_file *fp) { u32 i; __le32 buf[1]; diff --git a/security/selinux/ss/conditional.h b/security/selinux/ss/conditional.h index 8827715bad75..468e98ad3ea1 100644 --- a/security/selinux/ss/conditional.h +++ b/security/selinux/ss/conditional.h @@ -68,10 +68,10 @@ int cond_destroy_bool(void *key, void *datum, void *p); int cond_index_bool(void *key, void *datum, void *datap); -int cond_read_bool(struct policydb *p, struct symtab *s, void *fp); -int cond_read_list(struct policydb *p, void *fp); +int cond_read_bool(struct policydb *p, struct symtab *s, struct policy_file *fp); +int cond_read_list(struct policydb *p, struct policy_file *fp); int cond_write_bool(void *key, void *datum, void *ptr); -int cond_write_list(struct policydb *p, void *fp); +int cond_write_list(struct policydb *p, struct policy_file *fp); void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd, struct extended_perms *xperms); diff --git a/security/selinux/ss/context.c b/security/selinux/ss/context.c index e39990f494dd..a528b7f76280 100644 --- a/security/selinux/ss/context.c +++ b/security/selinux/ss/context.c @@ -20,7 +20,7 @@ u32 context_compute_hash(const struct context *c) * context struct with only the len & str set (and vice versa) * under a given policy. Since context structs from different * policies should never meet, it is safe to hash valid and - * invalid contexts differently. The context_cmp() function + * invalid contexts differently. The context_equal() function * already operates under the same assumption. */ if (c->len) diff --git a/security/selinux/ss/context.h b/security/selinux/ss/context.h index 7ccab2e6965f..dd3b9b5b588e 100644 --- a/security/selinux/ss/context.h +++ b/security/selinux/ss/context.h @@ -132,13 +132,13 @@ out: return rc; } -static inline int mls_context_cmp(const struct context *c1, - const struct context *c2) +static inline bool mls_context_equal(const struct context *c1, + const struct context *c2) { return ((c1->range.level[0].sens == c2->range.level[0].sens) && - ebitmap_cmp(&c1->range.level[0].cat, &c2->range.level[0].cat) && + ebitmap_equal(&c1->range.level[0].cat, &c2->range.level[0].cat) && (c1->range.level[1].sens == c2->range.level[1].sens) && - ebitmap_cmp(&c1->range.level[1].cat, &c2->range.level[1].cat)); + ebitmap_equal(&c1->range.level[1].cat, &c2->range.level[1].cat)); } static inline void mls_context_destroy(struct context *c) @@ -188,15 +188,15 @@ static inline void context_destroy(struct context *c) mls_context_destroy(c); } -static inline int context_cmp(const struct context *c1, - const struct context *c2) +static inline bool context_equal(const struct context *c1, + const struct context *c2) { if (c1->len && c2->len) return (c1->len == c2->len && !strcmp(c1->str, c2->str)); if (c1->len || c2->len) return 0; return ((c1->user == c2->user) && (c1->role == c2->role) && - (c1->type == c2->type) && mls_context_cmp(c1, c2)); + (c1->type == c2->type) && mls_context_equal(c1, c2)); } u32 context_compute_hash(const struct context *c); diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c index 99c01be15115..43bc19e21960 100644 --- a/security/selinux/ss/ebitmap.c +++ b/security/selinux/ss/ebitmap.c @@ -25,12 +25,12 @@ static struct kmem_cache *ebitmap_node_cachep __ro_after_init; -int ebitmap_cmp(const struct ebitmap *e1, const struct ebitmap *e2) +bool ebitmap_equal(const struct ebitmap *e1, const struct ebitmap *e2) { const struct ebitmap_node *n1, *n2; if (e1->highbit != e2->highbit) - return 0; + return false; n1 = e1->node; n2 = e2->node; @@ -41,9 +41,9 @@ int ebitmap_cmp(const struct ebitmap *e1, const struct ebitmap *e2) } if (n1 || n2) - return 0; + return false; - return 1; + return true; } int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src) @@ -360,7 +360,7 @@ void ebitmap_destroy(struct ebitmap *e) e->node = NULL; } -int ebitmap_read(struct ebitmap *e, void *fp) +int ebitmap_read(struct ebitmap *e, struct policy_file *fp) { struct ebitmap_node *n = NULL; u32 mapunit, count, startbit, index, i; @@ -478,7 +478,7 @@ bad: goto out; } -int ebitmap_write(const struct ebitmap *e, void *fp) +int ebitmap_write(const struct ebitmap *e, struct policy_file *fp) { struct ebitmap_node *n; u32 bit, count, last_bit, last_startbit; diff --git a/security/selinux/ss/ebitmap.h b/security/selinux/ss/ebitmap.h index ba2ac3da1153..c9569998f287 100644 --- a/security/selinux/ss/ebitmap.h +++ b/security/selinux/ss/ebitmap.h @@ -120,7 +120,7 @@ static inline void ebitmap_node_clr_bit(struct ebitmap_node *n, u32 bit) (bit) < ebitmap_length(e); \ (bit) = ebitmap_next_positive(e, &(n), bit)) -int ebitmap_cmp(const struct ebitmap *e1, const struct ebitmap *e2); +bool ebitmap_equal(const struct ebitmap *e1, const struct ebitmap *e2); int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src); int ebitmap_and(struct ebitmap *dst, const struct ebitmap *e1, const struct ebitmap *e2); @@ -129,8 +129,9 @@ int ebitmap_contains(const struct ebitmap *e1, const struct ebitmap *e2, int ebitmap_get_bit(const struct ebitmap *e, u32 bit); int ebitmap_set_bit(struct ebitmap *e, u32 bit, int value); void ebitmap_destroy(struct ebitmap *e); -int ebitmap_read(struct ebitmap *e, void *fp); -int ebitmap_write(const struct ebitmap *e, void *fp); +struct policy_file; +int ebitmap_read(struct ebitmap *e, struct policy_file *fp); +int ebitmap_write(const struct ebitmap *e, struct policy_file *fp); u32 ebitmap_hash(const struct ebitmap *e, u32 hash); #ifdef CONFIG_NETLABEL diff --git a/security/selinux/ss/mls.c b/security/selinux/ss/mls.c index 989c809d310d..a6e49269f535 100644 --- a/security/selinux/ss/mls.c +++ b/security/selinux/ss/mls.c @@ -171,7 +171,7 @@ int mls_level_isvalid(struct policydb *p, struct mls_level *l) * levdatum->level->cat and no bit in l->cat is larger than * p->p_cats.nprim. */ - return ebitmap_contains(&levdatum->level->cat, &l->cat, + return ebitmap_contains(&levdatum->level.cat, &l->cat, p->p_cats.nprim); } @@ -289,7 +289,7 @@ int mls_context_to_sid(struct policydb *pol, char oldc, char *scontext, levdatum = symtab_search(&pol->p_levels, sensitivity); if (!levdatum) return -EINVAL; - context->range.level[l].sens = levdatum->level->sens; + context->range.level[l].sens = levdatum->level.sens; /* Extract category set. */ while (next_cat != NULL) { @@ -456,7 +456,7 @@ int mls_convert_context(struct policydb *oldp, struct policydb *newp, if (!levdatum) return -EINVAL; - newc->range.level[l].sens = levdatum->level->sens; + newc->range.level[l].sens = levdatum->level.sens; ebitmap_for_each_positive_bit(&oldc->range.level[l].cat, node, i) diff --git a/security/selinux/ss/mls_types.h b/security/selinux/ss/mls_types.h index 7ef6e8cb0cf4..51df2ebd1211 100644 --- a/security/selinux/ss/mls_types.h +++ b/security/selinux/ss/mls_types.h @@ -29,7 +29,7 @@ struct mls_range { static inline int mls_level_eq(const struct mls_level *l1, const struct mls_level *l2) { - return ((l1->sens == l2->sens) && ebitmap_cmp(&l1->cat, &l2->cat)); + return ((l1->sens == l2->sens) && ebitmap_equal(&l1->cat, &l2->cat)); } static inline int mls_level_dom(const struct mls_level *l1, diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index 383f3ae82a73..9ea971943713 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -155,6 +155,11 @@ static const struct policydb_compat_info policydb_compat[] = { .sym_num = SYM_NUM, .ocon_num = OCON_NUM, }, + { + .version = POLICYDB_VERSION_COND_XPERMS, + .sym_num = SYM_NUM, + .ocon_num = OCON_NUM, + }, }; static const struct policydb_compat_info * @@ -296,9 +301,7 @@ static int sens_destroy(void *key, void *datum, void *p) kfree(key); if (datum) { levdatum = datum; - if (levdatum->level) - ebitmap_destroy(&levdatum->level->cat); - kfree(levdatum->level); + ebitmap_destroy(&levdatum->level.cat); } kfree(datum); return 0; @@ -630,11 +633,11 @@ static int sens_index(void *key, void *datum, void *datap) p = datap; if (!levdatum->isalias) { - if (!levdatum->level->sens || - levdatum->level->sens > p->p_levels.nprim) + if (!levdatum->level.sens || + levdatum->level.sens > p->p_levels.nprim) return -EINVAL; - p->sym_val_to_name[SYM_LEVELS][levdatum->level->sens - 1] = key; + p->sym_val_to_name[SYM_LEVELS][levdatum->level.sens - 1] = key; } return 0; @@ -992,7 +995,7 @@ int policydb_context_isvalid(struct policydb *p, struct context *c) * Read a MLS range structure from a policydb binary * representation file. */ -static int mls_read_range_helper(struct mls_range *r, void *fp) +static int mls_read_range_helper(struct mls_range *r, struct policy_file *fp) { __le32 buf[2]; u32 items; @@ -1052,7 +1055,7 @@ out: * from a policydb binary representation file. */ static int context_read_and_validate(struct context *c, struct policydb *p, - void *fp) + struct policy_file *fp) { __le32 buf[3]; int rc; @@ -1090,7 +1093,7 @@ out: * binary representation file. */ -static int str_read(char **strp, gfp_t flags, void *fp, u32 len) +int str_read(char **strp, gfp_t flags, struct policy_file *fp, u32 len) { int rc; char *str; @@ -1113,7 +1116,7 @@ static int str_read(char **strp, gfp_t flags, void *fp, u32 len) return 0; } -static int perm_read(struct policydb *p, struct symtab *s, void *fp) +static int perm_read(struct policydb *p, struct symtab *s, struct policy_file *fp) { char *key = NULL; struct perm_datum *perdatum; @@ -1146,7 +1149,7 @@ bad: return rc; } -static int common_read(struct policydb *p, struct symtab *s, void *fp) +static int common_read(struct policydb *p, struct symtab *s, struct policy_file *fp) { char *key = NULL; struct common_datum *comdatum; @@ -1198,7 +1201,7 @@ static void type_set_init(struct type_set *t) ebitmap_init(&t->negset); } -static int type_set_read(struct type_set *t, void *fp) +static int type_set_read(struct type_set *t, struct policy_file *fp) { __le32 buf[1]; int rc; @@ -1217,7 +1220,7 @@ static int type_set_read(struct type_set *t, void *fp) } static int read_cons_helper(struct policydb *p, struct constraint_node **nodep, - u32 ncons, int allowxtarget, void *fp) + u32 ncons, int allowxtarget, struct policy_file *fp) { struct constraint_node *c, *lc; struct constraint_expr *e, *le; @@ -1311,7 +1314,7 @@ static int read_cons_helper(struct policydb *p, struct constraint_node **nodep, return 0; } -static int class_read(struct policydb *p, struct symtab *s, void *fp) +static int class_read(struct policydb *p, struct symtab *s, struct policy_file *fp) { char *key = NULL; struct class_datum *cladatum; @@ -1408,7 +1411,7 @@ bad: return rc; } -static int role_read(struct policydb *p, struct symtab *s, void *fp) +static int role_read(struct policydb *p, struct symtab *s, struct policy_file *fp) { char *key = NULL; struct role_datum *role; @@ -1465,7 +1468,7 @@ bad: return rc; } -static int type_read(struct policydb *p, struct symtab *s, void *fp) +static int type_read(struct policydb *p, struct symtab *s, struct policy_file *fp) { char *key = NULL; struct type_datum *typdatum; @@ -1517,7 +1520,7 @@ bad: * Read a MLS level structure from a policydb binary * representation file. */ -static int mls_read_level(struct mls_level *lp, void *fp) +static int mls_read_level(struct mls_level *lp, struct policy_file *fp) { __le32 buf[1]; int rc; @@ -1539,7 +1542,7 @@ static int mls_read_level(struct mls_level *lp, void *fp) return 0; } -static int user_read(struct policydb *p, struct symtab *s, void *fp) +static int user_read(struct policydb *p, struct symtab *s, struct policy_file *fp) { char *key = NULL; struct user_datum *usrdatum; @@ -1590,7 +1593,7 @@ bad: return rc; } -static int sens_read(struct policydb *p, struct symtab *s, void *fp) +static int sens_read(struct policydb *p, struct symtab *s, struct policy_file *fp) { char *key = NULL; struct level_datum *levdatum; @@ -1613,12 +1616,7 @@ static int sens_read(struct policydb *p, struct symtab *s, void *fp) if (rc) goto bad; - rc = -ENOMEM; - levdatum->level = kmalloc(sizeof(*levdatum->level), GFP_KERNEL); - if (!levdatum->level) - goto bad; - - rc = mls_read_level(levdatum->level, fp); + rc = mls_read_level(&levdatum->level, fp); if (rc) goto bad; @@ -1631,7 +1629,7 @@ bad: return rc; } -static int cat_read(struct policydb *p, struct symtab *s, void *fp) +static int cat_read(struct policydb *p, struct symtab *s, struct policy_file *fp) { char *key = NULL; struct cat_datum *catdatum; @@ -1666,7 +1664,7 @@ bad: /* clang-format off */ static int (*const read_f[SYM_NUM])(struct policydb *p, struct symtab *s, - void *fp) = { + struct policy_file *fp) = { common_read, class_read, role_read, @@ -1836,7 +1834,7 @@ u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name) return 1U << (perdatum->value - 1); } -static int range_read(struct policydb *p, void *fp) +static int range_read(struct policydb *p, struct policy_file *fp) { struct range_trans *rt = NULL; struct mls_range *r = NULL; @@ -1913,7 +1911,7 @@ out: return rc; } -static int filename_trans_read_helper_compat(struct policydb *p, void *fp) +static int filename_trans_read_helper_compat(struct policydb *p, struct policy_file *fp) { struct filename_trans_key key, *ft = NULL; struct filename_trans_datum *last, *datum = NULL; @@ -1998,7 +1996,7 @@ out: return rc; } -static int filename_trans_read_helper(struct policydb *p, void *fp) +static int filename_trans_read_helper(struct policydb *p, struct policy_file *fp) { struct filename_trans_key *ft = NULL; struct filename_trans_datum **dst, *datum, *first = NULL; @@ -2087,7 +2085,7 @@ out: return rc; } -static int filename_trans_read(struct policydb *p, void *fp) +static int filename_trans_read(struct policydb *p, struct policy_file *fp) { u32 nel, i; __le32 buf[1]; @@ -2128,7 +2126,7 @@ static int filename_trans_read(struct policydb *p, void *fp) return 0; } -static int genfs_read(struct policydb *p, void *fp) +static int genfs_read(struct policydb *p, struct policy_file *fp) { int rc; u32 i, j, nel, nel2, len, len2; @@ -2242,7 +2240,7 @@ out: } static int ocontext_read(struct policydb *p, - const struct policydb_compat_info *info, void *fp) + const struct policydb_compat_info *info, struct policy_file *fp) { int rc; unsigned int i; @@ -2439,7 +2437,7 @@ out: * Read the configuration data from a policy database binary * representation file into a policy database structure. */ -int policydb_read(struct policydb *p, void *fp) +int policydb_read(struct policydb *p, struct policy_file *fp) { struct role_allow *ra, *lra; struct role_trans_key *rtk = NULL; @@ -2475,24 +2473,18 @@ int policydb_read(struct policydb *p, void *fp) goto bad; } - rc = -ENOMEM; - policydb_str = kmalloc(len + 1, GFP_KERNEL); - if (!policydb_str) { - pr_err("SELinux: unable to allocate memory for policydb " - "string of length %d\n", - len); - goto bad; - } - - rc = next_entry(policydb_str, fp, len); + rc = str_read(&policydb_str, GFP_KERNEL, fp, len); if (rc) { - pr_err("SELinux: truncated policydb string identifier\n"); - kfree(policydb_str); + if (rc == -ENOMEM) { + pr_err("SELinux: unable to allocate memory for policydb string of length %d\n", + len); + } else { + pr_err("SELinux: truncated policydb string identifier\n"); + } goto bad; } rc = -EINVAL; - policydb_str[len] = '\0'; if (strcmp(policydb_str, POLICYDB_STRING)) { pr_err("SELinux: policydb string %s does not match " "my string %s\n", @@ -2762,7 +2754,7 @@ bad: * Write a MLS level structure to a policydb binary * representation file. */ -static int mls_write_level(struct mls_level *l, void *fp) +static int mls_write_level(struct mls_level *l, struct policy_file *fp) { __le32 buf[1]; int rc; @@ -2783,7 +2775,7 @@ static int mls_write_level(struct mls_level *l, void *fp) * Write a MLS range structure to a policydb binary * representation file. */ -static int mls_write_range_helper(struct mls_range *r, void *fp) +static int mls_write_range_helper(struct mls_range *r, struct policy_file *fp) { __le32 buf[3]; size_t items; @@ -2823,7 +2815,7 @@ static int sens_write(void *vkey, void *datum, void *ptr) char *key = vkey; struct level_datum *levdatum = datum; struct policy_data *pd = ptr; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; __le32 buf[2]; size_t len; int rc; @@ -2839,7 +2831,7 @@ static int sens_write(void *vkey, void *datum, void *ptr) if (rc) return rc; - rc = mls_write_level(levdatum->level, fp); + rc = mls_write_level(&levdatum->level, fp); if (rc) return rc; @@ -2851,7 +2843,7 @@ static int cat_write(void *vkey, void *datum, void *ptr) char *key = vkey; struct cat_datum *catdatum = datum; struct policy_data *pd = ptr; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; __le32 buf[3]; size_t len; int rc; @@ -2876,7 +2868,7 @@ static int role_trans_write_one(void *key, void *datum, void *ptr) struct role_trans_key *rtk = key; struct role_trans_datum *rtd = datum; struct policy_data *pd = ptr; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; struct policydb *p = pd->p; __le32 buf[3]; int rc; @@ -2896,7 +2888,7 @@ static int role_trans_write_one(void *key, void *datum, void *ptr) return 0; } -static int role_trans_write(struct policydb *p, void *fp) +static int role_trans_write(struct policydb *p, struct policy_file *fp) { struct policy_data pd = { .p = p, .fp = fp }; __le32 buf[1]; @@ -2910,7 +2902,7 @@ static int role_trans_write(struct policydb *p, void *fp) return hashtab_map(&p->role_tr, role_trans_write_one, &pd); } -static int role_allow_write(struct role_allow *r, void *fp) +static int role_allow_write(struct role_allow *r, struct policy_file *fp) { struct role_allow *ra; __le32 buf[2]; @@ -2938,7 +2930,7 @@ static int role_allow_write(struct role_allow *r, void *fp) * Write a security context structure * to a policydb binary representation file. */ -static int context_write(struct policydb *p, struct context *c, void *fp) +static int context_write(struct policydb *p, struct context *c, struct policy_file *fp) { int rc; __le32 buf[3]; @@ -2991,7 +2983,7 @@ static int common_write(void *vkey, void *datum, void *ptr) char *key = vkey; struct common_datum *comdatum = datum; struct policy_data *pd = ptr; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; __le32 buf[4]; size_t len; int rc; @@ -3016,7 +3008,7 @@ static int common_write(void *vkey, void *datum, void *ptr) return 0; } -static int type_set_write(struct type_set *t, void *fp) +static int type_set_write(struct type_set *t, struct policy_file *fp) { int rc; __le32 buf[1]; @@ -3035,7 +3027,7 @@ static int type_set_write(struct type_set *t, void *fp) } static int write_cons_helper(struct policydb *p, struct constraint_node *node, - void *fp) + struct policy_file *fp) { struct constraint_node *c; struct constraint_expr *e; @@ -3086,7 +3078,7 @@ static int class_write(void *vkey, void *datum, void *ptr) char *key = vkey; struct class_datum *cladatum = datum; struct policy_data *pd = ptr; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; struct policydb *p = pd->p; struct constraint_node *c; __le32 buf[6]; @@ -3171,7 +3163,7 @@ static int role_write(void *vkey, void *datum, void *ptr) char *key = vkey; struct role_datum *role = datum; struct policy_data *pd = ptr; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; struct policydb *p = pd->p; __le32 buf[3]; size_t items, len; @@ -3211,7 +3203,7 @@ static int type_write(void *vkey, void *datum, void *ptr) struct type_datum *typdatum = datum; struct policy_data *pd = ptr; struct policydb *p = pd->p; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; __le32 buf[4]; int rc; size_t items, len; @@ -3252,7 +3244,7 @@ static int user_write(void *vkey, void *datum, void *ptr) struct user_datum *usrdatum = datum; struct policy_data *pd = ptr; struct policydb *p = pd->p; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; __le32 buf[3]; size_t items, len; int rc; @@ -3301,7 +3293,8 @@ static int (*const write_f[SYM_NUM])(void *key, void *datum, void *datap) = { /* clang-format on */ static int ocontext_write(struct policydb *p, - const struct policydb_compat_info *info, void *fp) + const struct policydb_compat_info *info, + struct policy_file *fp) { unsigned int i, j; int rc; @@ -3437,7 +3430,7 @@ static int ocontext_write(struct policydb *p, return 0; } -static int genfs_write(struct policydb *p, void *fp) +static int genfs_write(struct policydb *p, struct policy_file *fp) { struct genfs *genfs; struct ocontext *c; @@ -3495,7 +3488,7 @@ static int range_write_helper(void *key, void *data, void *ptr) struct range_trans *rt = key; struct mls_range *r = data; struct policy_data *pd = ptr; - void *fp = pd->fp; + struct policy_file *fp = pd->fp; struct policydb *p = pd->p; int rc; @@ -3517,7 +3510,7 @@ static int range_write_helper(void *key, void *data, void *ptr) return 0; } -static int range_write(struct policydb *p, void *fp) +static int range_write(struct policydb *p, struct policy_file *fp) { __le32 buf[1]; int rc; @@ -3544,7 +3537,7 @@ static int filename_write_helper_compat(void *key, void *data, void *ptr) struct filename_trans_key *ft = key; struct filename_trans_datum *datum = data; struct ebitmap_node *node; - void *fp = ptr; + struct policy_file *fp = ptr; __le32 buf[4]; int rc; u32 bit, len = strlen(ft->name); @@ -3581,7 +3574,7 @@ static int filename_write_helper(void *key, void *data, void *ptr) { struct filename_trans_key *ft = key; struct filename_trans_datum *datum; - void *fp = ptr; + struct policy_file *fp = ptr; __le32 buf[3]; int rc; u32 ndatum, len = strlen(ft->name); @@ -3626,7 +3619,7 @@ static int filename_write_helper(void *key, void *data, void *ptr) return 0; } -static int filename_trans_write(struct policydb *p, void *fp) +static int filename_trans_write(struct policydb *p, struct policy_file *fp) { __le32 buf[1]; int rc; @@ -3658,7 +3651,7 @@ static int filename_trans_write(struct policydb *p, void *fp) * structure to a policy database binary representation * file. */ -int policydb_write(struct policydb *p, void *fp) +int policydb_write(struct policydb *p, struct policy_file *fp) { unsigned int num_syms; int rc; diff --git a/security/selinux/ss/policydb.h b/security/selinux/ss/policydb.h index 4bba386264a3..25650224b6e7 100644 --- a/security/selinux/ss/policydb.h +++ b/security/selinux/ss/policydb.h @@ -126,7 +126,7 @@ struct user_datum { /* Sensitivity attributes */ struct level_datum { - struct mls_level *level; /* sensitivity and associated categories */ + struct mls_level level; /* sensitivity and associated categories */ unsigned char isalias; /* is this sensitivity an alias for another? */ }; @@ -144,7 +144,7 @@ struct range_trans { /* Boolean data type */ struct cond_bool_datum { - __u32 value; /* internal type value */ + u32 value; /* internal type value */ int state; }; @@ -312,14 +312,19 @@ struct policydb { u32 process_trans_perms; } __randomize_layout; +struct policy_file { + char *data; + size_t len; +}; + extern void policydb_destroy(struct policydb *p); extern int policydb_load_isids(struct policydb *p, struct sidtab *s); extern int policydb_context_isvalid(struct policydb *p, struct context *c); extern int policydb_class_isvalid(struct policydb *p, unsigned int class); extern int policydb_type_isvalid(struct policydb *p, unsigned int type); extern int policydb_role_isvalid(struct policydb *p, unsigned int role); -extern int policydb_read(struct policydb *p, void *fp); -extern int policydb_write(struct policydb *p, void *fp); +extern int policydb_read(struct policydb *p, struct policy_file *fp); +extern int policydb_write(struct policydb *p, struct policy_file *fp); extern struct filename_trans_datum * policydb_filenametr_search(struct policydb *p, struct filename_trans_key *key); @@ -342,14 +347,9 @@ policydb_roletr_search(struct policydb *p, struct role_trans_key *key); #define POLICYDB_MAGIC SELINUX_MAGIC #define POLICYDB_STRING "SE Linux" -struct policy_file { - char *data; - size_t len; -}; - struct policy_data { struct policydb *p; - void *fp; + struct policy_file *fp; }; static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes) @@ -386,6 +386,8 @@ static inline char *sym_name(struct policydb *p, unsigned int sym_num, return p->sym_val_to_name[sym_num][element_nr]; } +extern int str_read(char **strp, gfp_t flags, struct policy_file *fp, u32 len); + extern u16 string_to_security_class(struct policydb *p, const char *name); extern u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name); diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 971c45d576ba..8478842fbf9e 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -582,7 +582,7 @@ static void type_attribute_bounds_av(struct policydb *policydb, } /* - * Flag which drivers have permissions. + * Flag which drivers have permissions and which base permissions are covered. */ void services_compute_xperms_drivers( struct extended_perms *xperms, @@ -592,12 +592,19 @@ void services_compute_xperms_drivers( switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLDRIVER: + xperms->base_perms |= AVC_EXT_IOCTL; /* if one or more driver has all permissions allowed */ for (i = 0; i < ARRAY_SIZE(xperms->drivers.p); i++) xperms->drivers.p[i] |= node->datum.u.xperms->perms.p[i]; break; case AVTAB_XPERMS_IOCTLFUNCTION: + xperms->base_perms |= AVC_EXT_IOCTL; + /* if allowing permissions within a driver */ + security_xperm_set(xperms->drivers.p, + node->datum.u.xperms->driver); + break; case AVTAB_XPERMS_NLMSG: + xperms->base_perms |= AVC_EXT_NLMSG; /* if allowing permissions within a driver */ security_xperm_set(xperms->drivers.p, node->datum.u.xperms->driver); @@ -631,8 +638,7 @@ static void context_struct_compute_av(struct policydb *policydb, avd->auditallow = 0; avd->auditdeny = 0xffffffff; if (xperms) { - memset(&xperms->drivers, 0, sizeof(xperms->drivers)); - xperms->len = 0; + memset(xperms, 0, sizeof(*xperms)); } if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) { @@ -946,7 +952,7 @@ static void avd_init(struct selinux_policy *policy, struct av_decision *avd) } static void update_xperms_extended_data(u8 specified, - struct extended_perms_data *from, + const struct extended_perms_data *from, struct extended_perms_data *xp_data) { unsigned int i; @@ -967,38 +973,52 @@ static void update_xperms_extended_data(u8 specified, void services_compute_xperms_decision(struct extended_perms_decision *xpermd, struct avtab_node *node) { + u16 specified; + switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLFUNCTION: - case AVTAB_XPERMS_NLMSG: - if (xpermd->driver != node->datum.u.xperms->driver) + if (xpermd->base_perm != AVC_EXT_IOCTL || + xpermd->driver != node->datum.u.xperms->driver) return; break; case AVTAB_XPERMS_IOCTLDRIVER: - if (!security_xperm_test(node->datum.u.xperms->perms.p, - xpermd->driver)) + if (xpermd->base_perm != AVC_EXT_IOCTL || + !security_xperm_test(node->datum.u.xperms->perms.p, + xpermd->driver)) + return; + break; + case AVTAB_XPERMS_NLMSG: + if (xpermd->base_perm != AVC_EXT_NLMSG || + xpermd->driver != node->datum.u.xperms->driver) return; break; default: - BUG(); + pr_warn_once( + "SELinux: unknown extended permission (%u) will be ignored\n", + node->datum.u.xperms->specified); + return; } - if (node->key.specified == AVTAB_XPERMS_ALLOWED) { + specified = node->key.specified & ~(AVTAB_ENABLED | AVTAB_ENABLED_OLD); + + if (specified == AVTAB_XPERMS_ALLOWED) { xpermd->used |= XPERMS_ALLOWED; update_xperms_extended_data(node->datum.u.xperms->specified, &node->datum.u.xperms->perms, xpermd->allowed); - } else if (node->key.specified == AVTAB_XPERMS_AUDITALLOW) { + } else if (specified == AVTAB_XPERMS_AUDITALLOW) { xpermd->used |= XPERMS_AUDITALLOW; update_xperms_extended_data(node->datum.u.xperms->specified, &node->datum.u.xperms->perms, xpermd->auditallow); - } else if (node->key.specified == AVTAB_XPERMS_DONTAUDIT) { + } else if (specified == AVTAB_XPERMS_DONTAUDIT) { xpermd->used |= XPERMS_DONTAUDIT; update_xperms_extended_data(node->datum.u.xperms->specified, &node->datum.u.xperms->perms, xpermd->dontaudit); } else { - BUG(); + pr_warn_once("SELinux: unknown specified key (%u)\n", + node->key.specified); } } @@ -1006,6 +1026,7 @@ void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 orig_tclass, u8 driver, + u8 base_perm, struct extended_perms_decision *xpermd) { struct selinux_policy *policy; @@ -1019,6 +1040,7 @@ void security_compute_xperms_decision(u32 ssid, struct ebitmap_node *snode, *tnode; unsigned int i, j; + xpermd->base_perm = base_perm; xpermd->driver = driver; xpermd->used = 0; memset(xpermd->allowed->p, 0, sizeof(xpermd->allowed->p)); @@ -2593,17 +2615,15 @@ out: return rc; } -static int match_ipv6_addrmask(u32 *input, u32 *addr, u32 *mask) +static bool match_ipv6_addrmask(const u32 input[4], const u32 addr[4], const u32 mask[4]) { - int i, fail = 0; + int i; for (i = 0; i < 4; i++) - if (addr[i] != (input[i] & mask[i])) { - fail = 1; - break; - } + if (addr[i] != (input[i] & mask[i])) + return false; - return !fail; + return true; } /** @@ -2708,7 +2728,7 @@ out: */ int security_get_user_sids(u32 fromsid, - char *username, + const char *username, u32 **sids, u32 *nel) { @@ -3030,7 +3050,7 @@ err: } -int security_set_bools(u32 len, int *values) +int security_set_bools(u32 len, const int *values) { struct selinux_state *state = &selinux_state; struct selinux_policy *newpolicy, *oldpolicy; @@ -3329,7 +3349,7 @@ int security_net_peersid_resolve(u32 nlbl_sid, u32 nlbl_type, __func__, xfrm_sid); goto out; } - rc = (mls_context_cmp(nlbl_ctx, xfrm_ctx) ? 0 : -EACCES); + rc = (mls_context_equal(nlbl_ctx, xfrm_ctx) ? 0 : -EACCES); if (rc) goto out; diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c index c8848cbba81f..59f8c09158ef 100644 --- a/security/selinux/ss/sidtab.c +++ b/security/selinux/ss/sidtab.c @@ -66,7 +66,7 @@ static u32 context_to_sid(struct sidtab *s, struct context *context, u32 hash) hash_for_each_possible_rcu(s->context_to_sid, entry, list, hash) { if (entry->hash != hash) continue; - if (context_cmp(&entry->context, context)) { + if (context_equal(&entry->context, context)) { sid = entry->sid; break; } @@ -114,12 +114,12 @@ int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context) int sidtab_hash_stats(struct sidtab *sidtab, char *page) { - int i; + unsigned int i; int chain_len = 0; int slots_used = 0; int entries = 0; int max_chain_len = 0; - int cur_bucket = 0; + unsigned int cur_bucket = 0; struct sidtab_entry *entry; rcu_read_lock(); diff --git a/security/smack/smack.h b/security/smack/smack.h index dbf8d7226eb5..4608b07607a3 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -280,6 +280,7 @@ int smk_access(struct smack_known *, struct smack_known *, int smk_tskacc(struct task_smack *, struct smack_known *, u32, struct smk_audit_info *); int smk_curacc(struct smack_known *, u32, struct smk_audit_info *); +int smack_str_from_perm(char *string, int access); struct smack_known *smack_from_secid(const u32); char *smk_parse_smack(const char *string, int len); int smk_netlbl_mls(int, char *, struct netlbl_lsm_secattr *, int); diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c index 585e5e35710b..3727379623e2 100644 --- a/security/smack/smack_access.c +++ b/security/smack/smack_access.c @@ -275,7 +275,6 @@ int smk_curacc(struct smack_known *obj_known, return smk_tskacc(tsp, obj_known, mode, a); } -#ifdef CONFIG_AUDIT /** * smack_str_from_perm : helper to transalate an int to a * readable string @@ -283,7 +282,7 @@ int smk_curacc(struct smack_known *obj_known, * @access : the int * */ -static inline void smack_str_from_perm(char *string, int access) +int smack_str_from_perm(char *string, int access) { int i = 0; @@ -299,8 +298,15 @@ static inline void smack_str_from_perm(char *string, int access) string[i++] = 't'; if (access & MAY_LOCK) string[i++] = 'l'; + if (access & MAY_BRINGUP) + string[i++] = 'b'; + if (i == 0) + string[i++] = '-'; string[i] = '\0'; + return i; } + +#ifdef CONFIG_AUDIT /** * smack_log_callback - SMACK specific information * will be called by generic audit code diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 0c476282e279..239773cdcdcf 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -107,23 +107,7 @@ static char *smk_bu_mess[] = { static void smk_bu_mode(int mode, char *s) { - int i = 0; - - if (mode & MAY_READ) - s[i++] = 'r'; - if (mode & MAY_WRITE) - s[i++] = 'w'; - if (mode & MAY_EXEC) - s[i++] = 'x'; - if (mode & MAY_APPEND) - s[i++] = 'a'; - if (mode & MAY_TRANSMUTE) - s[i++] = 't'; - if (mode & MAY_LOCK) - s[i++] = 'l'; - if (i == 0) - s[i++] = '-'; - s[i] = '\0'; + smack_str_from_perm(s, mode); } #endif @@ -4817,41 +4801,48 @@ static int smack_ismaclabel(const char *name) return (strcmp(name, XATTR_SMACK_SUFFIX) == 0); } +/** + * smack_to_secctx - fill a lsm_context + * @skp: Smack label + * @cp: destination + * + * Fill the passed @cp and return the length of the string + */ +static int smack_to_secctx(struct smack_known *skp, struct lsm_context *cp) +{ + int len = strlen(skp->smk_known); + + if (cp) { + cp->context = skp->smk_known; + cp->len = len; + cp->id = LSM_ID_SMACK; + } + return len; +} + /** * smack_secid_to_secctx - return the smack label for a secid * @secid: incoming integer - * @secdata: destination - * @seclen: how long it is + * @cp: destination * * Exists for networking code. */ -static int smack_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +static int smack_secid_to_secctx(u32 secid, struct lsm_context *cp) { - struct smack_known *skp = smack_from_secid(secid); - - if (secdata) - *secdata = skp->smk_known; - *seclen = strlen(skp->smk_known); - return 0; + return smack_to_secctx(smack_from_secid(secid), cp); } /** * smack_lsmprop_to_secctx - return the smack label * @prop: includes incoming Smack data - * @secdata: destination - * @seclen: how long it is + * @cp: destination * * Exists for audit code. */ -static int smack_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, - u32 *seclen) +static int smack_lsmprop_to_secctx(struct lsm_prop *prop, + struct lsm_context *cp) { - struct smack_known *skp = prop->smack.skp; - - if (secdata) - *secdata = skp->smk_known; - *seclen = strlen(skp->smk_known); - return 0; + return smack_to_secctx(prop->smack.skp, cp); } /** @@ -4891,12 +4882,13 @@ static int smack_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) ctx, ctxlen, 0, NULL); } -static int smack_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) +static int smack_inode_getsecctx(struct inode *inode, struct lsm_context *cp) { struct smack_known *skp = smk_of_inode(inode); - *ctx = skp->smk_known; - *ctxlen = strlen(skp->smk_known); + cp->context = skp->smk_known; + cp->len = strlen(skp->smk_known); + cp->id = LSM_ID_SMACK; return 0; } diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index 1401412fd794..357188f764ce 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -562,6 +562,7 @@ static void smk_seq_stop(struct seq_file *s, void *v) static void smk_rule_show(struct seq_file *s, struct smack_rule *srp, int max) { + char acc[SMK_NUM_ACCESS_TYPE + 1]; /* * Don't show any rules with label names too long for * interface file (/smack/load or /smack/load2) @@ -575,28 +576,11 @@ static void smk_rule_show(struct seq_file *s, struct smack_rule *srp, int max) if (srp->smk_access == 0) return; - seq_printf(s, "%s %s", + smack_str_from_perm(acc, srp->smk_access); + seq_printf(s, "%s %s %s\n", srp->smk_subject->smk_known, - srp->smk_object->smk_known); - - seq_putc(s, ' '); - - if (srp->smk_access & MAY_READ) - seq_putc(s, 'r'); - if (srp->smk_access & MAY_WRITE) - seq_putc(s, 'w'); - if (srp->smk_access & MAY_EXEC) - seq_putc(s, 'x'); - if (srp->smk_access & MAY_APPEND) - seq_putc(s, 'a'); - if (srp->smk_access & MAY_TRANSMUTE) - seq_putc(s, 't'); - if (srp->smk_access & MAY_LOCK) - seq_putc(s, 'l'); - if (srp->smk_access & MAY_BRINGUP) - seq_putc(s, 'b'); - - seq_putc(s, '\n'); + srp->smk_object->smk_known, + acc); } /* diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index 5c7b059a332a..d9fa69632147 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -2024,6 +2024,36 @@ static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header) if (!buffer) return; snprintf(buffer, len - 1, "%s", cp); + if (*cp == 'f' && strchr(buffer, ':')) { + /* Automatically replace 2 or more digits with \$ pattern. */ + char *cp2; + + /* e.g. file read proc:/$PID/stat */ + cp = strstr(buffer, " proc:/"); + if (cp && simple_strtoul(cp + 7, &cp2, 10) >= 10 && *cp2 == '/') { + *(cp + 7) = '\\'; + *(cp + 8) = '$'; + memmove(cp + 9, cp2, strlen(cp2) + 1); + goto ok; + } + /* e.g. file ioctl pipe:[$INO] $CMD */ + cp = strstr(buffer, " pipe:["); + if (cp && simple_strtoul(cp + 7, &cp2, 10) >= 10 && *cp2 == ']') { + *(cp + 7) = '\\'; + *(cp + 8) = '$'; + memmove(cp + 9, cp2, strlen(cp2) + 1); + goto ok; + } + /* e.g. file ioctl socket:[$INO] $CMD */ + cp = strstr(buffer, " socket:["); + if (cp && simple_strtoul(cp + 9, &cp2, 10) >= 10 && *cp2 == ']') { + *(cp + 9) = '\\'; + *(cp + 10) = '$'; + memmove(cp + 11, cp2, strlen(cp2) + 1); + goto ok; + } + } +ok: if (realpath) tomoyo_addprintf(buffer, len, " exec.%s", realpath); if (argv0) @@ -2665,7 +2695,7 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, if (head->w.avail >= head->writebuf_size - 1) { const int len = head->writebuf_size * 2; - char *cp = kzalloc(len, GFP_NOFS); + char *cp = kzalloc(len, GFP_NOFS | __GFP_NOWARN); if (!cp) { error = -ENOMEM; diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index aed9e3ef2c9e..3a7b0874cf44 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -722,10 +722,17 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) ee->bprm = bprm; ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; - /* Get symlink's pathname of program. */ + /* + * Get symlink's pathname of program, but fallback to realpath if + * symlink's pathname does not exist or symlink's pathname refers + * to proc filesystem (e.g. /dev/fd/<num> or /proc/self/fd/<num> ). + */ exename.name = tomoyo_realpath_nofollow(original_name); + if (exename.name && !strncmp(exename.name, "proc:/", 6)) { + kfree(exename.name); + exename.name = NULL; + } if (!exename.name) { - /* Fallback to realpath if symlink's pathname does not exist. */ exename.name = tomoyo_realpath_from_path(&bprm->file->f_path); if (!exename.name) goto out; diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index e1a5e13ea269..1971710620c1 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -76,7 +76,6 @@ static void report_access(const char *access, struct task_struct *target, struct task_struct *agent) { struct access_report_info *info; - char agent_comm[sizeof(agent->comm)]; assert_spin_locked(&target->alloc_lock); /* for target->comm */ @@ -86,8 +85,7 @@ static void report_access(const char *access, struct task_struct *target, */ pr_notice_ratelimited( "ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n", - access, target->comm, target->pid, - get_task_comm(agent_comm, agent), agent->pid); + access, target->comm, target->pid, agent->comm, agent->pid); return; } @@ -454,7 +452,7 @@ static int yama_dointvec_minmax(const struct ctl_table *table, int write, static int max_scope = YAMA_SCOPE_NO_ATTACH; -static struct ctl_table yama_sysctl_table[] = { +static const struct ctl_table yama_sysctl_table[] = { { .procname = "ptrace_scope", .data = &ptrace_scope, diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 86ed2fbee0c8..840bb9cfe789 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -1025,7 +1025,7 @@ static u64 snd_compr_seqno_next(struct snd_compr_stream *stream) static int snd_compr_task_new(struct snd_compr_stream *stream, struct snd_compr_task *utask) { struct snd_compr_task_runtime *task; - int retval; + int retval, fd_i, fd_o; if (stream->runtime->total_tasks >= stream->runtime->fragments) return -EBUSY; @@ -1039,19 +1039,27 @@ static int snd_compr_task_new(struct snd_compr_stream *stream, struct snd_compr_ retval = stream->ops->task_create(stream, task); if (retval < 0) goto cleanup; - utask->input_fd = dma_buf_fd(task->input, O_WRONLY|O_CLOEXEC); - if (utask->input_fd < 0) { - retval = utask->input_fd; + /* similar functionality as in dma_buf_fd(), but ensure that both + file descriptors are allocated before fd_install() */ + if (!task->input || !task->input->file || !task->output || !task->output->file) { + retval = -EINVAL; goto cleanup; } - utask->output_fd = dma_buf_fd(task->output, O_RDONLY|O_CLOEXEC); - if (utask->output_fd < 0) { - retval = utask->output_fd; + fd_i = get_unused_fd_flags(O_WRONLY|O_CLOEXEC); + if (fd_i < 0) + goto cleanup; + fd_o = get_unused_fd_flags(O_RDONLY|O_CLOEXEC); + if (fd_o < 0) { + put_unused_fd(fd_i); goto cleanup; } /* keep dmabuf reference until freed with task free ioctl */ - dma_buf_get(utask->input_fd); - dma_buf_get(utask->output_fd); + get_dma_buf(task->input); + get_dma_buf(task->output); + fd_install(fd_i, task->input->file); + fd_install(fd_o, task->output->file); + utask->input_fd = fd_i; + utask->output_fd = fd_o; list_add_tail(&task->list, &stream->runtime->tasks); stream->runtime->total_tasks++; return 0; @@ -1069,7 +1077,7 @@ static int snd_compr_task_create(struct snd_compr_stream *stream, unsigned long return -EPERM; task = memdup_user((void __user *)arg, sizeof(*task)); if (IS_ERR(task)) - return PTR_ERR(no_free_ptr(task)); + return PTR_ERR(task); retval = snd_compr_task_new(stream, task); if (retval >= 0) if (copy_to_user((void __user *)arg, task, sizeof(*task))) @@ -1130,7 +1138,7 @@ static int snd_compr_task_start_ioctl(struct snd_compr_stream *stream, unsigned return -EPERM; task = memdup_user((void __user *)arg, sizeof(*task)); if (IS_ERR(task)) - return PTR_ERR(no_free_ptr(task)); + return PTR_ERR(task); retval = snd_compr_task_start(stream, task); if (retval >= 0) if (copy_to_user((void __user *)arg, task, sizeof(*task))) @@ -1174,18 +1182,18 @@ typedef void (*snd_compr_seq_func_t)(struct snd_compr_stream *stream, static int snd_compr_task_seq(struct snd_compr_stream *stream, unsigned long arg, snd_compr_seq_func_t fcn) { - struct snd_compr_task_runtime *task; + struct snd_compr_task_runtime *task, *temp; __u64 seqno; int retval; if (stream->runtime->state != SNDRV_PCM_STATE_SETUP) return -EPERM; - retval = get_user(seqno, (__u64 __user *)arg); - if (retval < 0) - return retval; + retval = copy_from_user(&seqno, (__u64 __user *)arg, sizeof(seqno)); + if (retval) + return -EFAULT; retval = 0; if (seqno == 0) { - list_for_each_entry_reverse(task, &stream->runtime->tasks, list) + list_for_each_entry_safe_reverse(task, temp, &stream->runtime->tasks, list) fcn(stream, task); } else { task = snd_compr_find_task(stream, seqno); @@ -1221,7 +1229,7 @@ static int snd_compr_task_status_ioctl(struct snd_compr_stream *stream, unsigned return -EPERM; status = memdup_user((void __user *)arg, sizeof(*status)); if (IS_ERR(status)) - return PTR_ERR(no_free_ptr(status)); + return PTR_ERR(status); retval = snd_compr_task_status(stream, status); if (retval >= 0) if (copy_to_user((void __user *)arg, status, sizeof(*status))) @@ -1247,6 +1255,7 @@ void snd_compr_task_finished(struct snd_compr_stream *stream, } EXPORT_SYMBOL_GPL(snd_compr_task_finished); +MODULE_IMPORT_NS("DMA_BUF"); #endif /* CONFIG_SND_COMPRESS_ACCEL */ static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg) diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 13b71069ae18..b3853583d2ae 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -505,7 +505,7 @@ static void *snd_dma_wc_alloc(struct snd_dma_buffer *dmab, size_t size) if (!p) return NULL; dmab->addr = dma_map_single(dmab->dev.dev, p, size, DMA_BIDIRECTIONAL); - if (dmab->addr == DMA_MAPPING_ERROR) { + if (dma_mapping_error(dmab->dev.dev, dmab->addr)) { do_free_pages(dmab->area, size, true); return NULL; } diff --git a/sound/core/memory.c b/sound/core/memory.c index 2d2d0094c897..d683442b4c97 100644 --- a/sound/core/memory.c +++ b/sound/core/memory.c @@ -27,38 +27,43 @@ int copy_to_user_fromio(void __user *dst, const volatile void __iomem *src, size if (import_ubuf(ITER_DEST, dst, count, &iter)) return -EFAULT; - return copy_to_iter_fromio(&iter, (const void __iomem *)src, count); + if (copy_to_iter_fromio((const void __iomem *)src, count, &iter) != count) + return -EFAULT; + return 0; } EXPORT_SYMBOL(copy_to_user_fromio); /** * copy_to_iter_fromio - copy data from mmio-space to iov_iter - * @dst: the destination iov_iter * @src: the source pointer on mmio * @count: the data size to copy in bytes + * @dst: the destination iov_iter * * Copies the data from mmio-space to iov_iter. * - * Return: Zero if successful, or non-zero on failure. + * Return: number of bytes to be copied */ -int copy_to_iter_fromio(struct iov_iter *dst, const void __iomem *src, - size_t count) +size_t copy_to_iter_fromio(const void __iomem *src, size_t count, + struct iov_iter *dst) { #if defined(__i386__) || defined(CONFIG_SPARC32) - return copy_to_iter((const void __force *)src, count, dst) == count ? 0 : -EFAULT; + return copy_to_iter((const void __force *)src, count, dst); #else char buf[256]; + size_t res = 0; + while (count) { size_t c = count; if (c > sizeof(buf)) c = sizeof(buf); memcpy_fromio(buf, (void __iomem *)src, c); if (copy_to_iter(buf, c, dst) != c) - return -EFAULT; + return res; count -= c; src += c; + res += c; } - return 0; + return res; #endif } EXPORT_SYMBOL(copy_to_iter_fromio); @@ -79,37 +84,43 @@ int copy_from_user_toio(volatile void __iomem *dst, const void __user *src, size if (import_ubuf(ITER_SOURCE, (void __user *)src, count, &iter)) return -EFAULT; - return copy_from_iter_toio((void __iomem *)dst, &iter, count); + if (copy_from_iter_toio((void __iomem *)dst, count, &iter) != count) + return -EFAULT; + return 0; } EXPORT_SYMBOL(copy_from_user_toio); /** * copy_from_iter_toio - copy data from iov_iter to mmio-space * @dst: the destination pointer on mmio-space - * @src: the source iov_iter * @count: the data size to copy in bytes + * @src: the source iov_iter * * Copies the data from iov_iter to mmio-space. * - * Return: Zero if successful, or non-zero on failure. + * Return: number of bytes to be copied */ -int copy_from_iter_toio(void __iomem *dst, struct iov_iter *src, size_t count) +size_t copy_from_iter_toio(void __iomem *dst, size_t count, + struct iov_iter *src) { #if defined(__i386__) || defined(CONFIG_SPARC32) - return copy_from_iter((void __force *)dst, count, src) == count ? 0 : -EFAULT; + return copy_from_iter((void __force *)dst, count, src); #else char buf[256]; + size_t res = 0; + while (count) { size_t c = count; if (c > sizeof(buf)) c = sizeof(buf); if (copy_from_iter(buf, c, src) != c) - return -EFAULT; + return res; memcpy_toio(dst, buf, c); count -= c; dst += c; + res += c; } - return 0; + return res; #endif } EXPORT_SYMBOL(copy_from_iter_toio); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 8a3384342e8d..6c2b6a62d9d2 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3245,7 +3245,7 @@ static int snd_pcm_xfern_frames_ioctl(struct snd_pcm_substream *substream, if (copy_from_user(&xfern, _xfern, sizeof(xfern))) return -EFAULT; - bufs = memdup_user(xfern.bufs, sizeof(void *) * runtime->channels); + bufs = memdup_array_user(xfern.bufs, runtime->channels, sizeof(void *)); if (IS_ERR(bufs)) return PTR_ERR(bufs); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 348ce1b7725e..70a958ac1112 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -629,12 +629,15 @@ static int snd_rawmidi_info(struct snd_rawmidi_substream *substream, info->subdevice = substream->number; info->stream = substream->stream; info->flags = rmidi->info_flags; + if (substream->inactive) + info->flags |= SNDRV_RAWMIDI_INFO_STREAM_INACTIVE; strcpy(info->id, rmidi->id); strcpy(info->name, rmidi->name); strcpy(info->subname, substream->name); info->subdevices_count = substream->pstr->substream_count; info->subdevices_avail = (substream->pstr->substream_count - substream->pstr->substream_opened); + info->tied_device = rmidi->tied_device; return 0; } diff --git a/sound/core/seq/Kconfig b/sound/core/seq/Kconfig index 0374bbf51cd4..e4f58cb985d4 100644 --- a/sound/core/seq/Kconfig +++ b/sound/core/seq/Kconfig @@ -62,7 +62,7 @@ config SND_SEQ_VIRMIDI config SND_SEQ_UMP bool "Support for UMP events" - default y if SND_SEQ_UMP_CLIENT + default SND_UMP help Say Y here to enable the support for handling UMP (Universal MIDI Packet) events via ALSA sequencer infrastructure, which is an @@ -71,6 +71,6 @@ config SND_SEQ_UMP among legacy and UMP clients. config SND_SEQ_UMP_CLIENT - def_tristate SND_UMP + def_tristate SND_UMP && SND_SEQ_UMP endif # SND_SEQUENCER diff --git a/sound/core/seq/oss/seq_oss_device.h b/sound/core/seq/oss/seq_oss_device.h index 98dd20b42976..6163a00bc8de 100644 --- a/sound/core/seq/oss/seq_oss_device.h +++ b/sound/core/seq/oss/seq_oss_device.h @@ -55,7 +55,6 @@ struct seq_oss_chinfo { struct seq_oss_synthinfo { struct snd_seq_oss_arg arg; struct seq_oss_chinfo *ch; - struct seq_oss_synth_sysex *sysex; int nr_voices; int opened; int is_midi; @@ -157,8 +156,4 @@ snd_seq_oss_fill_addr(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, ev->dest.port = dest_port; } - -/* misc. functions for proc interface */ -char *enabled_str(bool b); - #endif /* __SEQ_OSS_DEVICE_H */ diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c index 676246fa02f1..e6d7d83ed0e7 100644 --- a/sound/core/seq/oss/seq_oss_init.c +++ b/sound/core/seq/oss/seq_oss_init.c @@ -111,7 +111,7 @@ snd_seq_oss_create_client(void) /* - * receive annoucement from system port, and check the midi device + * receive announcement from system port, and check the midi device */ static int receive_announce(struct snd_seq_event *ev, int direct, void *private, int atomic, int hop) @@ -449,12 +449,6 @@ snd_seq_oss_reset(struct seq_oss_devinfo *dp) /* * misc. functions for proc interface */ -char * -enabled_str(bool b) -{ - return b ? "enabled" : "disabled"; -} - static const char * filemode_str(int val) { diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index e3394919daa0..9de47e098b29 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -26,13 +26,6 @@ * definition of synth info records */ -/* sysex buffer */ -struct seq_oss_synth_sysex { - int len; - int skip; - unsigned char buf[MAX_SYSEX_BUFLEN]; -}; - /* synth info */ struct seq_oss_synth { int seq_device; @@ -318,8 +311,6 @@ snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp) } snd_use_lock_free(&rec->use_lock); } - kfree(info->sysex); - info->sysex = NULL; kfree(info->ch); info->ch = NULL; } @@ -395,8 +386,6 @@ snd_seq_oss_synth_reset(struct seq_oss_devinfo *dp, int dev) info = get_synthinfo_nospec(dp, dev); if (!info || !info->opened) return; - if (info->sysex) - info->sysex->len = 0; /* reset sysex */ reset_channels(info); if (info->is_midi) { if (midi_synth_dev.opened <= 0) @@ -408,8 +397,6 @@ snd_seq_oss_synth_reset(struct seq_oss_devinfo *dp, int dev) dp->file_mode) < 0) { midi_synth_dev.opened--; info->opened = 0; - kfree(info->sysex); - info->sysex = NULL; kfree(info->ch); info->ch = NULL; } @@ -482,63 +469,26 @@ snd_seq_oss_synth_info(struct seq_oss_devinfo *dp, int dev) /* * receive OSS 6 byte sysex packet: - * the full sysex message will be sent if it reaches to the end of data - * (0xff). + * the event is filled and prepared for sending immediately + * (i.e. sysex messages are fragmented) */ int snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf, struct snd_seq_event *ev) { - int i, send; - unsigned char *dest; - struct seq_oss_synth_sysex *sysex; - struct seq_oss_synthinfo *info; + unsigned char *p; + int len = 6; - info = snd_seq_oss_synth_info(dp, dev); - if (!info) - return -ENXIO; + p = memchr(buf, 0xff, 6); + if (p) + len = p - buf + 1; - sysex = info->sysex; - if (sysex == NULL) { - sysex = kzalloc(sizeof(*sysex), GFP_KERNEL); - if (sysex == NULL) - return -ENOMEM; - info->sysex = sysex; - } - - send = 0; - dest = sysex->buf + sysex->len; - /* copy 6 byte packet to the buffer */ - for (i = 0; i < 6; i++) { - if (buf[i] == 0xff) { - send = 1; - break; - } - dest[i] = buf[i]; - sysex->len++; - if (sysex->len >= MAX_SYSEX_BUFLEN) { - sysex->len = 0; - sysex->skip = 1; - break; - } - } - - if (sysex->len && send) { - if (sysex->skip) { - sysex->skip = 0; - sysex->len = 0; - return -EINVAL; /* skip */ - } - /* copy the data to event record and send it */ - ev->flags = SNDRV_SEQ_EVENT_LENGTH_VARIABLE; - if (snd_seq_oss_synth_addr(dp, dev, ev)) - return -EINVAL; - ev->data.ext.len = sysex->len; - ev->data.ext.ptr = sysex->buf; - sysex->len = 0; - return 0; - } - - return -EINVAL; /* skip */ + /* copy the data to event record and send it */ + if (snd_seq_oss_synth_addr(dp, dev, ev)) + return -EINVAL; + ev->flags = SNDRV_SEQ_EVENT_LENGTH_VARIABLE; + ev->data.ext.len = len; + ev->data.ext.ptr = buf; + return 0; } /* @@ -658,8 +608,8 @@ snd_seq_oss_synth_info_read(struct snd_info_buffer *buf) rec->synth_type, rec->synth_subtype, rec->nr_voices); snd_iprintf(buf, " capabilities : ioctl %s / load_patch %s\n", - enabled_str((long)rec->oper.ioctl), - enabled_str((long)rec->oper.load_patch)); + str_enabled_disabled((long)rec->oper.ioctl), + str_enabled_disabled((long)rec->oper.load_patch)); snd_use_lock_free(&rec->use_lock); } } diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 3930e2f9082f..073b56dc2225 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1275,10 +1275,16 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, if (client->type != client_info->type) return -EINVAL; - /* check validity of midi_version field */ - if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3) && - client_info->midi_version > SNDRV_SEQ_CLIENT_UMP_MIDI_2_0) - return -EINVAL; + if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3)) { + /* check validity of midi_version field */ + if (client_info->midi_version > SNDRV_SEQ_CLIENT_UMP_MIDI_2_0) + return -EINVAL; + + /* check if UMP is supported in kernel */ + if (!IS_ENABLED(CONFIG_SND_SEQ_UMP) && + client_info->midi_version > 0) + return -EINVAL; + } /* fill the info fields */ if (client_info->name[0]) @@ -1290,6 +1296,10 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, client->midi_version = client_info->midi_version; memcpy(client->event_filter, client_info->event_filter, 32); client->group_filter = client_info->group_filter; + + /* notify the change */ + snd_seq_system_client_ev_client_change(client->number); + return 0; } @@ -1413,6 +1423,9 @@ static int snd_seq_ioctl_set_port_info(struct snd_seq_client *client, void *arg) if (port) { snd_seq_set_port_info(port, info); snd_seq_port_unlock(port); + /* notify the change */ + snd_seq_system_client_ev_port_change(info->addr.client, + info->addr.port); } return 0; } @@ -1469,7 +1482,7 @@ int snd_seq_client_notify_subscription(int client, int port, event.data.connect.dest = info->dest; event.data.connect.sender = info->sender; - return snd_seq_system_notify(client, port, &event); /* non-atomic */ + return snd_seq_system_notify(client, port, &event, false); /* non-atomic */ } @@ -2223,6 +2236,16 @@ static int snd_seq_ioctl_client_ump_info(struct snd_seq_client *caller, error: mutex_unlock(&cptr->ioctl_mutex); snd_seq_client_unlock(cptr); + if (!err && cmd == SNDRV_SEQ_IOCTL_SET_CLIENT_UMP_INFO) { + if (type == SNDRV_SEQ_CLIENT_UMP_INFO_ENDPOINT) + snd_seq_system_ump_notify(client, 0, + SNDRV_SEQ_EVENT_UMP_EP_CHANGE, + false); + else + snd_seq_system_ump_notify(client, type - 1, + SNDRV_SEQ_EVENT_UMP_BLOCK_CHANGE, + false); + } return err; } #endif diff --git a/sound/core/seq/seq_system.c b/sound/core/seq/seq_system.c index 80267290190d..853920f79016 100644 --- a/sound/core/seq/seq_system.c +++ b/sound/core/seq/seq_system.c @@ -49,12 +49,14 @@ static int sysclient = -1; /* port id numbers for this client */ static int announce_port = -1; +/* number of subscriptions to announce port */ +static int announce_subscribed; /* fill standard header data, source port & channel are filled in */ static int setheader(struct snd_seq_event * ev, int client, int port) { - if (announce_port < 0) + if (announce_port < 0 || !announce_subscribed) return -ENODEV; memset(ev, 0, sizeof(struct snd_seq_event)); @@ -76,26 +78,27 @@ static int setheader(struct snd_seq_event * ev, int client, int port) /* entry points for broadcasting system events */ -void snd_seq_system_broadcast(int client, int port, int type) +void snd_seq_system_broadcast(int client, int port, int type, bool atomic) { struct snd_seq_event ev; if (setheader(&ev, client, port) < 0) return; ev.type = type; - snd_seq_kernel_client_dispatch(sysclient, &ev, 0, 0); + snd_seq_kernel_client_dispatch(sysclient, &ev, atomic, 0); } EXPORT_SYMBOL_GPL(snd_seq_system_broadcast); /* entry points for broadcasting system events */ -int snd_seq_system_notify(int client, int port, struct snd_seq_event *ev) +int snd_seq_system_notify(int client, int port, struct snd_seq_event *ev, + bool atomic) { ev->flags = SNDRV_SEQ_EVENT_LENGTH_FIXED; ev->source.client = sysclient; ev->source.port = announce_port; ev->dest.client = client; ev->dest.port = port; - return snd_seq_kernel_client_dispatch(sysclient, ev, 0, 0); + return snd_seq_kernel_client_dispatch(sysclient, ev, atomic, 0); } /* call-back handler for timer events */ @@ -104,6 +107,22 @@ static int event_input_timer(struct snd_seq_event * ev, int direct, void *privat return snd_seq_control_queue(ev, atomic, hop); } +static int sys_announce_subscribe(void *private_data, + struct snd_seq_port_subscribe *info) +{ + announce_subscribed++; + return 0; +} + +static int sys_announce_unsubscribe(void *private_data, + struct snd_seq_port_subscribe *info) +{ + if (snd_BUG_ON(!announce_subscribed)) + return 0; + announce_subscribed--; + return 0; +} + /* register our internal client */ int __init snd_seq_system_client_init(void) { @@ -143,7 +162,10 @@ int __init snd_seq_system_client_init(void) /* register announcement port */ strcpy(port->name, "Announce"); port->capability = SNDRV_SEQ_PORT_CAP_READ|SNDRV_SEQ_PORT_CAP_SUBS_READ; /* for broadcast only */ - port->kernel = NULL; + pcallbacks.event_input = NULL; + pcallbacks.subscribe = sys_announce_subscribe; + pcallbacks.unsubscribe = sys_announce_unsubscribe; + port->kernel = &pcallbacks; port->type = 0; port->flags = SNDRV_SEQ_PORT_FLG_GIVEN_PORT; port->addr.client = sysclient; diff --git a/sound/core/seq/seq_system.h b/sound/core/seq/seq_system.h index 4fe88ad40346..62e513f74871 100644 --- a/sound/core/seq/seq_system.h +++ b/sound/core/seq/seq_system.h @@ -10,16 +10,31 @@ /* entry points for broadcasting system events */ -void snd_seq_system_broadcast(int client, int port, int type); +void snd_seq_system_broadcast(int client, int port, int type, bool atomic); -#define snd_seq_system_client_ev_client_start(client) snd_seq_system_broadcast(client, 0, SNDRV_SEQ_EVENT_CLIENT_START) -#define snd_seq_system_client_ev_client_exit(client) snd_seq_system_broadcast(client, 0, SNDRV_SEQ_EVENT_CLIENT_EXIT) -#define snd_seq_system_client_ev_client_change(client) snd_seq_system_broadcast(client, 0, SNDRV_SEQ_EVENT_CLIENT_CHANGE) -#define snd_seq_system_client_ev_port_start(client, port) snd_seq_system_broadcast(client, port, SNDRV_SEQ_EVENT_PORT_START) -#define snd_seq_system_client_ev_port_exit(client, port) snd_seq_system_broadcast(client, port, SNDRV_SEQ_EVENT_PORT_EXIT) -#define snd_seq_system_client_ev_port_change(client, port) snd_seq_system_broadcast(client, port, SNDRV_SEQ_EVENT_PORT_CHANGE) +/* normal system notification event broadcast */ +#define notify_event(client, port, type) \ + snd_seq_system_broadcast(client, port, type, false) -int snd_seq_system_notify(int client, int port, struct snd_seq_event *ev); +/* notify UMP EP/FB change event */ +static inline void snd_seq_system_ump_notify(int client, int block, int type, + bool atomic) +{ + /* reuse the existing snd_seq_system_broadcast(): + * struct snd_seq_ev_ump_notify is compatible with struct snd_seq_addr + */ + snd_seq_system_broadcast(client, block, type, atomic); +} + +#define snd_seq_system_client_ev_client_start(client) notify_event(client, 0, SNDRV_SEQ_EVENT_CLIENT_START) +#define snd_seq_system_client_ev_client_exit(client) notify_event(client, 0, SNDRV_SEQ_EVENT_CLIENT_EXIT) +#define snd_seq_system_client_ev_client_change(client) notify_event(client, 0, SNDRV_SEQ_EVENT_CLIENT_CHANGE) +#define snd_seq_system_client_ev_port_start(client, port) notify_event(client, port, SNDRV_SEQ_EVENT_PORT_START) +#define snd_seq_system_client_ev_port_exit(client, port) notify_event(client, port, SNDRV_SEQ_EVENT_PORT_EXIT) +#define snd_seq_system_client_ev_port_change(client, port) notify_event(client, port, SNDRV_SEQ_EVENT_PORT_CHANGE) + +int snd_seq_system_notify(int client, int port, struct snd_seq_event *ev, + bool atomic); /* register our internal client */ int snd_seq_system_client_init(void); diff --git a/sound/core/seq/seq_ump_client.c b/sound/core/seq/seq_ump_client.c index e956f17f3792..1255351b59ce 100644 --- a/sound/core/seq/seq_ump_client.c +++ b/sound/core/seq/seq_ump_client.c @@ -272,8 +272,6 @@ static void update_port_infos(struct seq_ump_client *client) new); if (err < 0) continue; - /* notify to system port */ - snd_seq_system_client_ev_port_change(client->seq_client, i); } } @@ -390,6 +388,33 @@ static void handle_group_notify(struct work_struct *work) setup_client_group_filter(client); } +/* UMP EP change notification */ +static int seq_ump_notify_ep_change(struct snd_ump_endpoint *ump) +{ + struct seq_ump_client *client = ump->seq_client; + struct snd_seq_client *cptr; + int client_id; + + if (!client) + return -ENODEV; + client_id = client->seq_client; + cptr = snd_seq_kernel_client_get(client_id); + if (!cptr) + return -ENODEV; + + snd_seq_system_ump_notify(client_id, 0, SNDRV_SEQ_EVENT_UMP_EP_CHANGE, + true); + + /* update sequencer client name if needed */ + if (*ump->core.name && strcmp(ump->core.name, cptr->name)) { + strscpy(cptr->name, ump->core.name, sizeof(cptr->name)); + snd_seq_system_client_ev_client_change(client_id); + } + + snd_seq_kernel_client_put(cptr); + return 0; +} + /* UMP FB change notification */ static int seq_ump_notify_fb_change(struct snd_ump_endpoint *ump, struct snd_ump_block *fb) @@ -399,20 +424,29 @@ static int seq_ump_notify_fb_change(struct snd_ump_endpoint *ump, if (!client) return -ENODEV; schedule_work(&client->group_notify_work); + snd_seq_system_ump_notify(client->seq_client, fb->info.block_id, + SNDRV_SEQ_EVENT_UMP_BLOCK_CHANGE, + true); return 0; } /* UMP protocol change notification; just update the midi_version field */ static int seq_ump_switch_protocol(struct snd_ump_endpoint *ump) { - if (!ump->seq_client) + struct seq_ump_client *client = ump->seq_client; + + if (!client) return -ENODEV; - setup_client_midi_version(ump->seq_client); + setup_client_midi_version(client); + snd_seq_system_ump_notify(client->seq_client, 0, + SNDRV_SEQ_EVENT_UMP_EP_CHANGE, + true); return 0; } static const struct snd_seq_ump_ops seq_ump_ops = { .input_receive = seq_ump_input_receive, + .notify_ep_change = seq_ump_notify_ep_change, .notify_fb_change = seq_ump_notify_fb_change, .switch_protocol = seq_ump_switch_protocol, }; diff --git a/sound/core/ump.c b/sound/core/ump.c index fe4d39ae1159..8d8681a42ca5 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -37,6 +37,7 @@ static int process_legacy_output(struct snd_ump_endpoint *ump, u32 *buffer, int count); static void process_legacy_input(struct snd_ump_endpoint *ump, const u32 *src, int words); +static void ump_legacy_set_rawmidi_name(struct snd_ump_endpoint *ump); static void update_legacy_names(struct snd_ump_endpoint *ump); #else static inline int process_legacy_output(struct snd_ump_endpoint *ump, @@ -48,11 +49,42 @@ static inline void process_legacy_input(struct snd_ump_endpoint *ump, const u32 *src, int words) { } +static inline void ump_legacy_set_rawmidi_name(struct snd_ump_endpoint *ump) +{ +} static inline void update_legacy_names(struct snd_ump_endpoint *ump) { } #endif +/* copy a string safely with stripping non-printable letters */ +static void safe_copy_string(void *dst, size_t max_dst_size, + const void *src, size_t max_src_size) +{ + const unsigned char *s = src; + unsigned char *d = dst; + + if (!max_dst_size--) + return; + for (s = src; max_dst_size && *s && max_src_size--; s++) { + if (!isascii(*s) || !isprint(*s)) + continue; + *d++ = *s; + max_dst_size--; + } + *d = 0; +} + +/* append a string safely with stripping non-printable letters */ +static void safe_append_string(void *dst, size_t max_dst_size, + const void *src, size_t max_src_size) +{ + unsigned char *d = dst; + size_t len = strlen(d); + + safe_copy_string(d + len, max_dst_size - len, src, max_src_size); +} + static const struct snd_rawmidi_global_ops snd_ump_rawmidi_ops = { .dev_register = snd_ump_dev_register, .dev_unregister = snd_ump_dev_unregister, @@ -565,16 +597,10 @@ void snd_ump_update_group_attrs(struct snd_ump_endpoint *ump) } if (!*fb->info.name) continue; - if (!*group->name) { - /* store the first matching name */ - strscpy(group->name, fb->info.name, - sizeof(group->name)); - } else { - /* when overlapping, concat names */ + if (*group->name) strlcat(group->name, ", ", sizeof(group->name)); - strlcat(group->name, fb->info.name, - sizeof(group->name)); - } + safe_append_string(group->name, sizeof(group->name), + fb->info.name, sizeof(fb->info.name)); } } } @@ -669,6 +695,15 @@ static void choose_default_protocol(struct snd_ump_endpoint *ump) ump->info.protocol |= SNDRV_UMP_EP_INFO_PROTO_MIDI1; } +/* notify the EP info/name change to sequencer */ +static void seq_notify_ep_change(struct snd_ump_endpoint *ump) +{ +#if IS_ENABLED(CONFIG_SND_SEQUENCER) + if (ump->parsed && ump->seq_ops && ump->seq_ops->notify_ep_change) + ump->seq_ops->notify_ep_change(ump); +#endif +} + /* handle EP info stream message; update the UMP attributes */ static int ump_handle_ep_info_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) @@ -693,6 +728,7 @@ static int ump_handle_ep_info_msg(struct snd_ump_endpoint *ump, ump->info.protocol &= ump->info.protocol_caps; choose_default_protocol(ump); + seq_notify_ep_change(ump); return 1; /* finished */ } @@ -715,24 +751,46 @@ static int ump_handle_device_info_msg(struct snd_ump_endpoint *ump, ump->info.family_id, ump->info.model_id, ump->info.sw_revision); + seq_notify_ep_change(ump); return 1; /* finished */ } +/* set up the core rawmidi name from UMP EP name string */ +static void ump_set_rawmidi_name(struct snd_ump_endpoint *ump) +{ + safe_copy_string(ump->core.name, sizeof(ump->core.name), + ump->info.name, sizeof(ump->info.name)); +} + /* handle EP name stream message; update the UMP name string */ static int ump_handle_ep_name_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) { - return ump_append_string(ump, ump->info.name, sizeof(ump->info.name), - buf->raw, 2); + int ret; + + ret = ump_append_string(ump, ump->info.name, sizeof(ump->info.name), + buf->raw, 2); + if (ret && ump->parsed) { + ump_set_rawmidi_name(ump); + ump_legacy_set_rawmidi_name(ump); + seq_notify_ep_change(ump); + } + + return ret; } /* handle EP product id stream message; update the UMP product_id string */ static int ump_handle_product_id_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) { - return ump_append_string(ump, ump->info.product_id, - sizeof(ump->info.product_id), - buf->raw, 2); + int ret; + + ret = ump_append_string(ump, ump->info.product_id, + sizeof(ump->info.product_id), + buf->raw, 2); + if (ret) + seq_notify_ep_change(ump); + return ret; } /* notify the protocol change to sequencer */ @@ -1045,6 +1103,8 @@ int snd_ump_parse_endpoint(struct snd_ump_endpoint *ump) if (err < 0) ump_dbg(ump, "Unable to get UMP EP name string\n"); + ump_set_rawmidi_name(ump); + /* Request Endpoint Product ID */ err = ump_req_msg(ump, msg, UMP_STREAM_MSG_REQUEST_PRODUCT_ID, UMP_STREAM_MSG_STATUS_PRODUCT_ID); @@ -1244,14 +1304,14 @@ static int fill_legacy_mapping(struct snd_ump_endpoint *ump) num = 0; for (i = 0; i < SNDRV_UMP_MAX_GROUPS; i++) - if ((group_maps & (1U << i)) && ump->groups[i].valid) + if (group_maps & (1U << i)) ump->legacy_mapping[num++] = i; return num; } -static void fill_substream_names(struct snd_ump_endpoint *ump, - struct snd_rawmidi *rmidi, int dir) +static void update_legacy_substreams(struct snd_ump_endpoint *ump, + struct snd_rawmidi *rmidi, int dir) { struct snd_rawmidi_substream *s; const char *name; @@ -1261,10 +1321,11 @@ static void fill_substream_names(struct snd_ump_endpoint *ump, idx = ump->legacy_mapping[s->number]; name = ump->groups[idx].name; if (!*name) - name = ump->info.name; + name = ump->core.name; scnprintf(s->name, sizeof(s->name), "Group %d (%.16s)%s", idx + 1, name, ump->groups[idx].active ? "" : " [Inactive]"); + s->inactive = !ump->groups[idx].active; } } @@ -1272,8 +1333,16 @@ static void update_legacy_names(struct snd_ump_endpoint *ump) { struct snd_rawmidi *rmidi = ump->legacy_rmidi; - fill_substream_names(ump, rmidi, SNDRV_RAWMIDI_STREAM_INPUT); - fill_substream_names(ump, rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT); + update_legacy_substreams(ump, rmidi, SNDRV_RAWMIDI_STREAM_INPUT); + update_legacy_substreams(ump, rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT); +} + +static void ump_legacy_set_rawmidi_name(struct snd_ump_endpoint *ump) +{ + struct snd_rawmidi *rmidi = ump->legacy_rmidi; + + snprintf(rmidi->name, sizeof(rmidi->name), "%.68s (MIDI 1.0)", + ump->core.name); } int snd_ump_attach_legacy_rawmidi(struct snd_ump_endpoint *ump, @@ -1306,14 +1375,15 @@ int snd_ump_attach_legacy_rawmidi(struct snd_ump_endpoint *ump, if (output) snd_rawmidi_set_ops(rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT, &snd_ump_legacy_output_ops); - snprintf(rmidi->name, sizeof(rmidi->name), "%.68s (MIDI 1.0)", - ump->info.name); rmidi->info_flags = ump->core.info_flags & ~SNDRV_RAWMIDI_INFO_UMP; rmidi->ops = &snd_ump_legacy_ops; rmidi->private_data = ump; ump->legacy_rmidi = rmidi; + ump_legacy_set_rawmidi_name(ump); update_legacy_names(ump); + snd_rawmidi_tie_devices(rmidi, &ump->core); + ump_dbg(ump, "Created a legacy rawmidi #%d (%s)\n", device, id); return 0; } diff --git a/sound/firewire/fireface/ff-protocol-former.c b/sound/firewire/fireface/ff-protocol-former.c index efd59e9d9935..0907d0a2296f 100644 --- a/sound/firewire/fireface/ff-protocol-former.c +++ b/sound/firewire/fireface/ff-protocol-former.c @@ -135,13 +135,13 @@ static void dump_clock_config(struct snd_ff *ff, struct snd_info_buffer *buffer) snd_iprintf(buffer, "Output S/PDIF format: %s (Emphasis: %s)\n", (data & 0x00000020) ? "Professional" : "Consumer", - (data & 0x00000040) ? "on" : "off"); + str_on_off(data & 0x00000040)); snd_iprintf(buffer, "Optical output interface format: %s\n", (data & 0x00000100) ? "S/PDIF" : "ADAT"); snd_iprintf(buffer, "Word output single speed: %s\n", - (data & 0x00002000) ? "on" : "off"); + str_on_off(data & 0x00002000)); snd_iprintf(buffer, "S/PDIF input interface: %s\n", (data & 0x00000200) ? "Optical" : "Coaxial"); diff --git a/sound/hda/hdac_component.c b/sound/hda/hdac_component.c index bb37e7e0bd79..9c82a2864a2f 100644 --- a/sound/hda/hdac_component.c +++ b/sound/hda/hdac_component.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/component.h> +#include <linux/string_choices.h> #include <sound/core.h> #include <sound/hdaudio.h> #include <sound/hda_component.h> @@ -42,8 +43,7 @@ int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable) if (!acomp->ops->codec_wake_override) return 0; - dev_dbg(bus->dev, "%s codec wakeup\n", - enable ? "enable" : "disable"); + dev_dbg(bus->dev, "%s codec wakeup\n", str_enable_disable(enable)); acomp->ops->codec_wake_override(acomp->dev, enable); @@ -67,8 +67,7 @@ void snd_hdac_display_power(struct hdac_bus *bus, unsigned int idx, bool enable) { struct drm_audio_component *acomp = bus->audio_component; - dev_dbg(bus->dev, "display power %s\n", - enable ? "enable" : "disable"); + dev_dbg(bus->dev, "display power %s\n", str_enable_disable(enable)); mutex_lock(&bus->lock); if (enable) diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index 2670792f43b4..4e85a838ad7e 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -492,32 +492,21 @@ static int setup_bdle(struct hdac_bus *bus, } /** - * snd_hdac_stream_setup_periods - set up BDL entries + * snd_hdac_stream_setup_bdle - set up BDL entries * @azx_dev: HD-audio core stream to set up + * @dmab: allocated DMA buffer + * @runtime: substream runtime, optional * * Set up the buffer descriptor table of the given stream based on the * period and buffer sizes of the assigned PCM substream. */ -int snd_hdac_stream_setup_periods(struct hdac_stream *azx_dev) +static int snd_hdac_stream_setup_bdle(struct hdac_stream *azx_dev, struct snd_dma_buffer *dmab, + struct snd_pcm_runtime *runtime) { struct hdac_bus *bus = azx_dev->bus; - struct snd_pcm_substream *substream = azx_dev->substream; - struct snd_compr_stream *cstream = azx_dev->cstream; - struct snd_pcm_runtime *runtime = NULL; - struct snd_dma_buffer *dmab; - __le32 *bdl; int i, ofs, periods, period_bytes; int pos_adj, pos_align; - - if (substream) { - runtime = substream->runtime; - dmab = snd_pcm_get_dma_buf(substream); - } else if (cstream) { - dmab = snd_pcm_get_dma_buf(cstream); - } else { - WARN(1, "No substream or cstream assigned\n"); - return -EINVAL; - } + __le32 *bdl; /* reset BDL address */ snd_hdac_stream_writel(azx_dev, SD_BDLPL, 0); @@ -571,6 +560,33 @@ int snd_hdac_stream_setup_periods(struct hdac_stream *azx_dev) azx_dev->bufsize, period_bytes); return -EINVAL; } + +/** + * snd_hdac_stream_setup_periods - set up BDL entries + * @azx_dev: HD-audio core stream to set up + * + * Set up the buffer descriptor table of the given stream based on the + * period and buffer sizes of the assigned PCM substream. + */ +int snd_hdac_stream_setup_periods(struct hdac_stream *azx_dev) +{ + struct snd_pcm_substream *substream = azx_dev->substream; + struct snd_compr_stream *cstream = azx_dev->cstream; + struct snd_pcm_runtime *runtime = NULL; + struct snd_dma_buffer *dmab; + + if (substream) { + runtime = substream->runtime; + dmab = snd_pcm_get_dma_buf(substream); + } else if (cstream) { + dmab = snd_pcm_get_dma_buf(cstream); + } else { + WARN(1, "No substream or cstream assigned\n"); + return -EINVAL; + } + + return snd_hdac_stream_setup_bdle(azx_dev, dmab, runtime); +} EXPORT_SYMBOL_GPL(snd_hdac_stream_setup_periods); /** @@ -923,7 +939,6 @@ int snd_hdac_dsp_prepare(struct hdac_stream *azx_dev, unsigned int format, unsigned int byte_size, struct snd_dma_buffer *bufp) { struct hdac_bus *bus = azx_dev->bus; - __le32 *bdl; int err; snd_hdac_dsp_lock(azx_dev); @@ -943,18 +958,14 @@ int snd_hdac_dsp_prepare(struct hdac_stream *azx_dev, unsigned int format, azx_dev->substream = NULL; azx_dev->bufsize = byte_size; - azx_dev->period_bytes = byte_size; + /* It is recommended to transfer the firmware in two or more chunks. */ + azx_dev->period_bytes = byte_size / 2; azx_dev->format_val = format; + azx_dev->no_period_wakeup = 1; snd_hdac_stream_reset(azx_dev); - /* reset BDL address */ - snd_hdac_stream_writel(azx_dev, SD_BDLPL, 0); - snd_hdac_stream_writel(azx_dev, SD_BDLPU, 0); - - azx_dev->frags = 0; - bdl = (__le32 *)azx_dev->bdl.area; - err = setup_bdle(bus, bufp, azx_dev, &bdl, 0, byte_size, 0); + err = snd_hdac_stream_setup_bdle(azx_dev, bufp, NULL); if (err < 0) goto error; diff --git a/sound/isa/sb/sb16_csp.c b/sound/isa/sb/sb16_csp.c index 071ba85f76bb..7034072c80d4 100644 --- a/sound/isa/sb/sb16_csp.c +++ b/sound/isa/sb/sb16_csp.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/module.h> +#include <linux/string_choices.h> #include <sound/core.h> #include <sound/control.h> #include <sound/info.h> @@ -1157,8 +1158,8 @@ static void info_read(struct snd_info_entry *entry, struct snd_info_buffer *buff ((p->acc_rates & SNDRV_SB_CSP_RATE_44100) ? "44100Hz" : "")); } if (p->mode == SNDRV_SB_CSP_MODE_QSOUND) { - snd_iprintf(buffer, "QSound decoder %sabled\n", - p->q_enabled ? "en" : "dis"); + snd_iprintf(buffer, "QSound decoder %s\n", + str_enabled_disabled(p->q_enabled)); } else { snd_iprintf(buffer, "PCM format ID: 0x%x (%s/%s) [%s/%s] [%s/%s]\n", p->acc_format, diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c index 25f93e56cfc7..6e710dce5c60 100644 --- a/sound/pci/ac97/ac97_codec.c +++ b/sound/pci/ac97/ac97_codec.c @@ -1864,7 +1864,7 @@ void snd_ac97_get_name(struct snd_ac97 *ac97, unsigned int id, char *name, int m strcat(name, " "); strcat(name, pid->name); if (pid->mask != 0xffffffff) - sprintf(name + strlen(name), " rev %d", id & ~pid->mask); + sprintf(name + strlen(name), " rev %u", id & ~pid->mask); if (ac97 && pid->patch) { if ((modem && (pid->flags & AC97_MODEM_PATCH)) || (! modem && ! (pid->flags & AC97_MODEM_PATCH))) diff --git a/sound/pci/ac97/ac97_proc.c b/sound/pci/ac97/ac97_proc.c index 5426f7bc9884..518834964b7b 100644 --- a/sound/pci/ac97/ac97_proc.c +++ b/sound/pci/ac97/ac97_proc.c @@ -161,12 +161,12 @@ static void snd_ac97_proc_read_main(struct snd_ac97 *ac97, struct snd_info_buffe "Mic select : %s\n" "ADC/DAC loopback : %s\n", val & 0x8000 ? "post" : "pre", - val & 0x4000 ? "on" : "off", - val & 0x2000 ? "on" : "off", - val & 0x1000 ? "on" : "off", + str_on_off(val & 0x4000), + str_on_off(val & 0x2000), + str_on_off(val & 0x1000), val & 0x0200 ? "Mic" : "MIX", val & 0x0100 ? "Mic2" : "Mic1", - val & 0x0080 ? "on" : "off"); + str_on_off(val & 0x0080)); if (ac97->ext_id & AC97_EI_DRA) snd_iprintf(buffer, "Double rate slots: %s\n", double_rate_slots[(val >> 10) & 3]); diff --git a/sound/pci/ad1889.c b/sound/pci/ad1889.c index 50e30704bf6f..9ed778b6b03c 100644 --- a/sound/pci/ad1889.c +++ b/sound/pci/ad1889.c @@ -626,7 +626,7 @@ snd_ad1889_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffe reg = ad1889_readw(chip, AD_DS_WSMC); snd_iprintf(buffer, "Wave output: %s\n", - (reg & AD_DS_WSMC_WAEN) ? "enabled" : "disabled"); + str_enabled_disabled(reg & AD_DS_WSMC_WAEN)); snd_iprintf(buffer, "Wave Channels: %s\n", (reg & AD_DS_WSMC_WAST) ? "stereo" : "mono"); snd_iprintf(buffer, "Wave Quality: %d-bit linear\n", @@ -642,7 +642,7 @@ snd_ad1889_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffe snd_iprintf(buffer, "Synthesis output: %s\n", - reg & AD_DS_WSMC_SYEN ? "enabled" : "disabled"); + str_enabled_disabled(reg & AD_DS_WSMC_SYEN)); /* SYRQ is at offset 4 */ tmp = (reg & AD_DS_WSMC_SYRQ) ? @@ -654,7 +654,7 @@ snd_ad1889_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffe reg = ad1889_readw(chip, AD_DS_RAMC); snd_iprintf(buffer, "ADC input: %s\n", - (reg & AD_DS_RAMC_ADEN) ? "enabled" : "disabled"); + str_enabled_disabled(reg & AD_DS_RAMC_ADEN)); snd_iprintf(buffer, "ADC Channels: %s\n", (reg & AD_DS_RAMC_ADST) ? "stereo" : "mono"); snd_iprintf(buffer, "ADC Quality: %d-bit linear\n", @@ -669,7 +669,7 @@ snd_ad1889_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffe (reg & AD_DS_RAMC_ADST) ? "stereo" : "mono"); snd_iprintf(buffer, "Resampler input: %s\n", - reg & AD_DS_RAMC_REEN ? "enabled" : "disabled"); + str_enabled_disabled(reg & AD_DS_RAMC_REEN)); /* RERQ is at offset 12 */ tmp = (reg & AD_DS_RAMC_RERQ) ? diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c index e3cac73517d6..cb8593c376ee 100644 --- a/sound/pci/cmipci.c +++ b/sound/pci/cmipci.c @@ -3084,7 +3084,7 @@ static int snd_cmipci_create(struct snd_card *card, struct pci_dev *pci, } } } - sprintf(card->shortname, "C-Media CMI%d", val); + sprintf(card->shortname, "C-Media CMI%u", val); if (cm->chip_version < 68) scnprintf(modelstr, sizeof(modelstr), " (model %d)", cm->chip_version); diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c index 83aaf9441ef3..9993b02d2968 100644 --- a/sound/pci/ctxfi/ctdaio.c +++ b/sound/pci/ctxfi/ctdaio.c @@ -211,52 +211,30 @@ static int dao_set_right_input(struct dao *dao, struct rsc *input) return 0; } -static int dao_clear_left_input(struct dao *dao) +static int dao_clear_input(struct dao *dao, unsigned int start, unsigned int end) { - struct imapper *entry; - struct daio *daio = &dao->daio; - int i; + unsigned int i; - if (!dao->imappers[0]) + if (!dao->imappers[start]) return 0; - - entry = dao->imappers[0]; - dao->mgr->imap_delete(dao->mgr, entry); - /* Program conjugate resources */ - for (i = 1; i < daio->rscl.msr; i++) { - entry = dao->imappers[i]; - dao->mgr->imap_delete(dao->mgr, entry); + for (i = start; i < end; i++) { + dao->mgr->imap_delete(dao->mgr, dao->imappers[i]); dao->imappers[i] = NULL; } - kfree(dao->imappers[0]); - dao->imappers[0] = NULL; - return 0; } + +static int dao_clear_left_input(struct dao *dao) +{ + return dao_clear_input(dao, 0, dao->daio.rscl.msr); +} + static int dao_clear_right_input(struct dao *dao) { - struct imapper *entry; - struct daio *daio = &dao->daio; - int i; - - if (!dao->imappers[daio->rscl.msr]) - return 0; - - entry = dao->imappers[daio->rscl.msr]; - dao->mgr->imap_delete(dao->mgr, entry); - /* Program conjugate resources */ - for (i = 1; i < daio->rscr.msr; i++) { - entry = dao->imappers[daio->rscl.msr + i]; - dao->mgr->imap_delete(dao->mgr, entry); - dao->imappers[daio->rscl.msr + i] = NULL; - } - - kfree(dao->imappers[daio->rscl.msr]); - dao->imappers[daio->rscl.msr] = NULL; - - return 0; + return dao_clear_input(dao, dao->daio.rscl.msr, + dao->daio.rscl.msr + dao->daio.rscr.msr); } static const struct dao_rsc_ops dao_ops = { diff --git a/sound/pci/emu10k1/emuproc.c b/sound/pci/emu10k1/emuproc.c index 737c28d31b41..bd4734dc04cd 100644 --- a/sound/pci/emu10k1/emuproc.c +++ b/sound/pci/emu10k1/emuproc.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/init.h> +#include <linux/string_choices.h> #include <sound/core.h> #include <sound/emu10k1.h> #include "p16v.h" @@ -32,9 +33,9 @@ static void snd_emu10k1_proc_spdif_status(struct snd_emu10k1 * emu, snd_iprintf(buffer, "\n%s\n", title); if (status != 0xffffffff) { - snd_iprintf(buffer, "Professional Mode : %s\n", (status & SPCS_PROFESSIONAL) ? "yes" : "no"); - snd_iprintf(buffer, "Not Audio Data : %s\n", (status & SPCS_NOTAUDIODATA) ? "yes" : "no"); - snd_iprintf(buffer, "Copyright : %s\n", (status & SPCS_COPYRIGHT) ? "yes" : "no"); + snd_iprintf(buffer, "Professional Mode : %s\n", str_yes_no(status & SPCS_PROFESSIONAL)); + snd_iprintf(buffer, "Not Audio Data : %s\n", str_yes_no(status & SPCS_NOTAUDIODATA)); + snd_iprintf(buffer, "Copyright : %s\n", str_yes_no(status & SPCS_COPYRIGHT)); snd_iprintf(buffer, "Emphasis : %s\n", emphasis[(status & SPCS_EMPHASISMASK) >> 3]); snd_iprintf(buffer, "Mode : %i\n", (status & SPCS_MODEMASK) >> 6); snd_iprintf(buffer, "Category Code : 0x%x\n", (status & SPCS_CATEGORYCODEMASK) >> 8); @@ -46,9 +47,9 @@ static void snd_emu10k1_proc_spdif_status(struct snd_emu10k1 * emu, if (rate_reg > 0) { rate = snd_emu10k1_ptr_read(emu, rate_reg, 0); - snd_iprintf(buffer, "S/PDIF Valid : %s\n", rate & SRCS_SPDIFVALID ? "on" : "off"); - snd_iprintf(buffer, "S/PDIF Locked : %s\n", rate & SRCS_SPDIFLOCKED ? "on" : "off"); - snd_iprintf(buffer, "Rate Locked : %s\n", rate & SRCS_RATELOCKED ? "on" : "off"); + snd_iprintf(buffer, "S/PDIF Valid : %s\n", str_on_off(rate & SRCS_SPDIFVALID)); + snd_iprintf(buffer, "S/PDIF Locked : %s\n", str_on_off(rate & SRCS_SPDIFLOCKED)); + snd_iprintf(buffer, "Rate Locked : %s\n", str_on_off(rate & SRCS_RATELOCKED)); /* From ((Rate * 48000 ) / 262144); */ snd_iprintf(buffer, "Estimated Sample Rate : %d\n", ((rate & 0xFFFFF ) * 375) >> 11); } @@ -208,7 +209,7 @@ static void snd_emu10k1_proc_spdif_read(struct snd_info_entry *entry, #if 0 val = snd_emu10k1_ptr_read(emu, ZVSRCS, 0); snd_iprintf(buffer, "\nZoomed Video\n"); - snd_iprintf(buffer, "Rate Locked : %s\n", val & SRCS_RATELOCKED ? "on" : "off"); + snd_iprintf(buffer, "Rate Locked : %s\n", str_on_off(val & SRCS_RATELOCKED)); snd_iprintf(buffer, "Estimated Sample Rate : 0x%x\n", val & SRCS_ESTSAMPLERATE); #endif } diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c index 18928b905939..71c89e4e3090 100644 --- a/sound/pci/ens1370.c +++ b/sound/pci/ens1370.c @@ -1850,12 +1850,12 @@ static void snd_ensoniq_proc_read(struct snd_info_entry *entry, snd_iprintf(buffer, "Ensoniq AudioPCI " CHIP_NAME "\n\n"); snd_iprintf(buffer, "Joystick enable : %s\n", - ensoniq->ctrl & ES_JYSTK_EN ? "on" : "off"); + str_on_off(ensoniq->ctrl & ES_JYSTK_EN)); #ifdef CHIP1370 snd_iprintf(buffer, "MIC +5V bias : %s\n", - ensoniq->ctrl & ES_1370_XCTL1 ? "on" : "off"); + str_on_off(ensoniq->ctrl & ES_1370_XCTL1)); snd_iprintf(buffer, "Line In to AOUT : %s\n", - ensoniq->ctrl & ES_1370_XCTL0 ? "on" : "off"); + str_on_off(ensoniq->ctrl & ES_1370_XCTL0)); #else snd_iprintf(buffer, "Joystick port : 0x%x\n", (ES_1371_JOY_ASELI(ensoniq->ctrl) * 8) + 0x200); diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig index 68f1eee9e5c9..e393578cbe68 100644 --- a/sound/pci/hda/Kconfig +++ b/sound/pci/hda/Kconfig @@ -206,6 +206,20 @@ config SND_HDA_SCODEC_TAS2781_I2C comment "Set to Y if you want auto-loading the side codec driver" depends on SND_HDA=y && SND_HDA_SCODEC_TAS2781_I2C=m +config SND_HDA_SCODEC_TAS2781_SPI + tristate "Build TAS2781 HD-audio side codec support for SPI Bus" + depends on SPI_MASTER + depends on ACPI + depends on EFI + depends on SND_SOC + select CRC32 + help + Say Y or M here to include TAS2781 SPI HD-audio side codec support + in snd-hda-intel driver, such as ALC287. + +comment "Set to Y if you want auto-loading the side codec driver" + depends on SND_HDA=y && SND_HDA_SCODEC_TAS2781_SPI=m + config SND_HDA_CODEC_REALTEK tristate "Build Realtek HD-audio codec support" select SND_HDA_GENERIC diff --git a/sound/pci/hda/Makefile b/sound/pci/hda/Makefile index 80210f845df2..210c406dfbc5 100644 --- a/sound/pci/hda/Makefile +++ b/sound/pci/hda/Makefile @@ -40,6 +40,7 @@ snd-hda-scodec-cs35l56-spi-y := cs35l56_hda_spi.o snd-hda-cs-dsp-ctls-y := hda_cs_dsp_ctl.o snd-hda-scodec-component-y := hda_component.o snd-hda-scodec-tas2781-i2c-y := tas2781_hda_i2c.o +snd-hda-scodec-tas2781-spi-y := tas2781_hda_spi.o tas2781_spi_fwlib.o # common driver obj-$(CONFIG_SND_HDA) := snd-hda-codec.o @@ -72,6 +73,7 @@ obj-$(CONFIG_SND_HDA_SCODEC_CS35L56_SPI) += snd-hda-scodec-cs35l56-spi.o obj-$(CONFIG_SND_HDA_CS_DSP_CONTROLS) += snd-hda-cs-dsp-ctls.o obj-$(CONFIG_SND_HDA_SCODEC_COMPONENT) += snd-hda-scodec-component.o obj-$(CONFIG_SND_HDA_SCODEC_TAS2781_I2C) += snd-hda-scodec-tas2781-i2c.o +obj-$(CONFIG_SND_HDA_SCODEC_TAS2781_SPI) += snd-hda-scodec-tas2781-spi.o # this must be the last entry after codec drivers; # otherwise the codec patches won't be hooked before the PCI probe diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c index 84393f4f429d..8923813ce424 100644 --- a/sound/pci/hda/hda_auto_parser.c +++ b/sound/pci/hda/hda_auto_parser.c @@ -80,7 +80,11 @@ static int compare_input_type(const void *ap, const void *bp) /* In case one has boost and the other one has not, pick the one with boost first. */ - return (int)(b->has_boost_on_pin - a->has_boost_on_pin); + if (a->has_boost_on_pin != b->has_boost_on_pin) + return (int)(b->has_boost_on_pin - a->has_boost_on_pin); + + /* Keep the original order */ + return a->order - b->order; } /* Reorder the surround channels @@ -400,6 +404,8 @@ int snd_hda_parse_pin_defcfg(struct hda_codec *codec, reorder_outputs(cfg->speaker_outs, cfg->speaker_pins); /* sort inputs in the order of AUTO_PIN_* type */ + for (i = 0; i < cfg->num_inputs; i++) + cfg->inputs[i].order = i; sort(cfg->inputs, cfg->num_inputs, sizeof(cfg->inputs[0]), compare_input_type, NULL); diff --git a/sound/pci/hda/hda_auto_parser.h b/sound/pci/hda/hda_auto_parser.h index 579b11beac71..87af3d8c02f7 100644 --- a/sound/pci/hda/hda_auto_parser.h +++ b/sound/pci/hda/hda_auto_parser.h @@ -37,6 +37,7 @@ struct auto_pin_cfg_item { unsigned int is_headset_mic:1; unsigned int is_headphone_mic:1; /* Mic-only in headphone jack */ unsigned int has_boost_on_pin:1; + int order; }; struct auto_pin_cfg; diff --git a/sound/pci/hda/hda_hwdep.c b/sound/pci/hda/hda_hwdep.c index 727f39acedfc..9325e5c3cbe6 100644 --- a/sound/pci/hda/hda_hwdep.c +++ b/sound/pci/hda/hda_hwdep.c @@ -84,10 +84,8 @@ static int hda_hwdep_ioctl_compat(struct snd_hwdep *hw, struct file *file, static int hda_hwdep_open(struct snd_hwdep *hw, struct file *file) { -#ifndef CONFIG_SND_DEBUG_VERBOSE if (!capable(CAP_SYS_RAWIO)) return -EACCES; -#endif return 0; } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 4a62440adfaf..7d7f9aac50a9 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2738,9 +2738,9 @@ static const struct pci_device_id azx_ids[] = { { PCI_VDEVICE(ZHAOXIN, 0x3288), .driver_data = AZX_DRIVER_ZHAOXIN }, /* Loongson HDAudio*/ { PCI_VDEVICE(LOONGSON, PCI_DEVICE_ID_LOONGSON_HDA), - .driver_data = AZX_DRIVER_LOONGSON }, + .driver_data = AZX_DRIVER_LOONGSON | AZX_DCAPS_NO_TCSEL }, { PCI_VDEVICE(LOONGSON, PCI_DEVICE_ID_LOONGSON_HDMI), - .driver_data = AZX_DRIVER_LOONGSON }, + .driver_data = AZX_DRIVER_LOONGSON | AZX_DCAPS_NO_TCSEL }, { 0, } }; MODULE_DEVICE_TABLE(pci, azx_ids); diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c index 265fd4737893..140e24bf4d7f 100644 --- a/sound/pci/hda/hda_sysfs.c +++ b/sound/pci/hda/hda_sysfs.c @@ -648,7 +648,7 @@ static const struct hda_patch_item patch_items[NUM_LINE_MODES] = { }, }; -/* check the line starting with '[' -- change the parser mode accodingly */ +/* check the line starting with '[' -- change the parser mode accordingly */ static int parse_line_mode(char *buf, struct hda_bus *bus) { int i; diff --git a/sound/pci/hda/ideapad_hotkey_led_helper.c b/sound/pci/hda/ideapad_hotkey_led_helper.c new file mode 100644 index 000000000000..c10d97964d49 --- /dev/null +++ b/sound/pci/hda/ideapad_hotkey_led_helper.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Ideapad helper functions for Lenovo Ideapad LED control, + * It should be included from codec driver. + */ + +#if IS_ENABLED(CONFIG_IDEAPAD_LAPTOP) + +#include <linux/acpi.h> +#include <linux/leds.h> + +static bool is_ideapad(struct hda_codec *codec) +{ + return (codec->core.subsystem_id >> 16 == 0x17aa) && + (acpi_dev_found("LHK2019") || acpi_dev_found("VPC2004")); +} + +static void hda_fixup_ideapad_acpi(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + if (!is_ideapad(codec)) + return; + snd_hda_gen_add_mute_led_cdev(codec, NULL); + snd_hda_gen_add_micmute_led_cdev(codec, NULL); + } +} + +#else /* CONFIG_IDEAPAD_LAPTOP */ + +static void hda_fixup_ideapad_acpi(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ +} + +#endif /* CONFIG_IDEAPAD_LAPTOP */ diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 538c37a78a56..4985e72b9094 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -291,6 +291,7 @@ enum { CXT_FIXUP_GPIO1, CXT_FIXUP_ASPIRE_DMIC, CXT_FIXUP_THINKPAD_ACPI, + CXT_FIXUP_LENOVO_XPAD_ACPI, CXT_FIXUP_OLPC_XO, CXT_FIXUP_CAP_MIX_AMP, CXT_FIXUP_TOSHIBA_P105, @@ -313,6 +314,9 @@ enum { /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" +/* for hda_fixup_ideapad_acpi() */ +#include "ideapad_hotkey_led_helper.c" + static void cxt_fixup_stereo_dmic(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -928,6 +932,12 @@ static const struct hda_fixup cxt_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = hda_fixup_thinkpad_acpi, }, + [CXT_FIXUP_LENOVO_XPAD_ACPI] = { + .type = HDA_FIXUP_FUNC, + .v.func = hda_fixup_ideapad_acpi, + .chained = true, + .chain_id = CXT_FIXUP_THINKPAD_ACPI, + }, [CXT_FIXUP_OLPC_XO] = { .type = HDA_FIXUP_FUNC, .v.func = cxt_fixup_olpc_xo, @@ -1119,7 +1129,7 @@ static const struct hda_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo G50-70", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x397b, "Lenovo S205", CXT_FIXUP_STEREO_DMIC), - SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", CXT_FIXUP_THINKPAD_ACPI), + SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad/Ideapad", CXT_FIXUP_LENOVO_XPAD_ACPI), SND_PCI_QUIRK(0x1c06, 0x2011, "Lemote A1004", CXT_PINCFG_LEMOTE_A1004), SND_PCI_QUIRK(0x1c06, 0x2012, "Lemote A1205", CXT_PINCFG_LEMOTE_A1205), HDA_CODEC_QUIRK(0x2782, 0x12c3, "Sirius Gen1", CXT_PINCFG_TOP_SPEAKER), @@ -1133,6 +1143,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = { { .id = CXT_FIXUP_HEADPHONE_MIC_PIN, .name = "headphone-mic-pin" }, { .id = CXT_PINCFG_LENOVO_TP410, .name = "tp410" }, { .id = CXT_FIXUP_THINKPAD_ACPI, .name = "thinkpad" }, + { .id = CXT_FIXUP_LENOVO_XPAD_ACPI, .name = "thinkpad-ideapad" }, { .id = CXT_PINCFG_LEMOTE_A1004, .name = "lemote-a1004" }, { .id = CXT_PINCFG_LEMOTE_A1205, .name = "lemote-a1205" }, { .id = CXT_FIXUP_OLPC_XO, .name = "olpc-xo" }, diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 61ba5dc35b8b..8192be394d0d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -890,9 +890,7 @@ static void alc_ssid_check(struct hda_codec *codec, const hda_nid_t *ports) } } -/* - */ - +/* inverted digital-mic */ static void alc_fixup_inv_dmic(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -5902,7 +5900,7 @@ static void alc_determine_headset_type(struct hda_codec *codec) } codec_dbg(codec, "Headset jack detected iPhone-style headset: %s\n", - is_ctia ? "yes" : "no"); + str_yes_no(is_ctia)); spec->current_headset_type = is_ctia ? ALC_HEADSET_TYPE_CTIA : ALC_HEADSET_TYPE_OMTP; } @@ -6934,6 +6932,15 @@ static void alc_fixup_thinkpad_acpi(struct hda_codec *codec, hda_fixup_thinkpad_acpi(codec, fix, action); } +/* for hda_fixup_ideapad_acpi() */ +#include "ideapad_hotkey_led_helper.c" + +static void alc_fixup_ideapad_acpi(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + hda_fixup_ideapad_acpi(codec, fix, action); +} + /* Fixup for Lenovo Legion 15IMHg05 speaker output on headset removal. */ static void alc287_fixup_legion_15imhg05_speakers(struct hda_codec *codec, const struct hda_fixup *fix, @@ -7128,6 +7135,11 @@ static void tas2781_fixup_i2c(struct hda_codec *cdc, comp_generic_fixup(cdc, action, "i2c", "TIAS2781", "-%s:00", 1); } +static void tas2781_fixup_spi(struct hda_codec *cdc, const struct hda_fixup *fix, int action) +{ + comp_generic_fixup(cdc, action, "spi", "TXNW2781", "-%s:00-tas2781-hda.%d", 2); +} + static void yoga7_14arb7_fixup_i2c(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { @@ -7485,6 +7497,16 @@ static void alc287_fixup_lenovo_thinkpad_with_alc1318(struct hda_codec *codec, spec->gen.pcm_playback_hook = alc287_alc1318_playback_pcm_hook; } +/* + * Clear COEF 0x0d (PCBEEP passthrough) bit 0x40 where BIOS sets it wrongly + * at PM resume + */ +static void alc283_fixup_dell_hp_resume(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action == HDA_FIXUP_ACT_INIT) + alc_write_coef_idx(codec, 0xd, 0x2800); +} enum { ALC269_FIXUP_GPIO2, @@ -7556,6 +7578,7 @@ enum { ALC290_FIXUP_SUBWOOFER, ALC290_FIXUP_SUBWOOFER_HSJACK, ALC269_FIXUP_THINKPAD_ACPI, + ALC269_FIXUP_LENOVO_XPAD_ACPI, ALC269_FIXUP_DMIC_THINKPAD_ACPI, ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13, ALC269VC_FIXUP_INFINIX_Y4_MAX, @@ -7762,6 +7785,7 @@ enum { ALC236_FIXUP_DELL_DUAL_CODECS, ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI, ALC287_FIXUP_TAS2781_I2C, + ALC245_FIXUP_TAS2781_SPI_2, ALC287_FIXUP_YOGA7_14ARB7_I2C, ALC245_FIXUP_HP_MUTE_LED_COEFBIT, ALC245_FIXUP_HP_X360_MUTE_LEDS, @@ -7785,6 +7809,7 @@ enum { ALC269_FIXUP_VAIO_VJFH52_MIC_NO_PRESENCE, ALC233_FIXUP_MEDION_MTL_SPK, ALC294_FIXUP_BASS_SPEAKER_15, + ALC283_FIXUP_DELL_HP_RESUME, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -8327,6 +8352,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_SKU_IGNORE, }, + [ALC269_FIXUP_LENOVO_XPAD_ACPI] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_ideapad_acpi, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + }, [ALC269_FIXUP_DMIC_THINKPAD_ACPI] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_inv_dmic, @@ -9986,6 +10017,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_THINKPAD_HEADSET_JACK, }, + [ALC245_FIXUP_TAS2781_SPI_2] = { + .type = HDA_FIXUP_FUNC, + .v.func = tas2781_fixup_spi, + .chained = true, + .chain_id = ALC285_FIXUP_HP_GPIO_LED, + }, [ALC287_FIXUP_YOGA7_14ARB7_I2C] = { .type = HDA_FIXUP_FUNC, .v.func = yoga7_14arb7_fixup_i2c, @@ -10117,6 +10154,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc294_fixup_bass_speaker_15, }, + [ALC283_FIXUP_DELL_HP_RESUME] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc283_fixup_dell_hp_resume, + }, }; static const struct hda_quirk alc269_fixup_tbl[] = { @@ -10158,6 +10199,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x1360, "Acer Aspire A115", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x141f, "Acer Spin SP513-54N", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x142b, "Acer Swift SF314-42", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), @@ -10176,6 +10218,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x05f4, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x05f5, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x05f6, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0604, "Dell Venue 11 Pro 7130", ALC283_FIXUP_DELL_HP_RESUME), SND_PCI_QUIRK(0x1028, 0x0615, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK), SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK), SND_PCI_QUIRK(0x1028, 0x062c, "Dell Latitude E5550", ALC292_FIXUP_DELL_E7X), @@ -10388,6 +10431,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8870, "HP ZBook Fury 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8873, "HP ZBook Studio 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x887a, "HP Laptop 15s-eq2xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), + SND_PCI_QUIRK(0x103c, 0x887c, "HP Laptop 14s-fq1xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x888a, "HP ENVY x360 Convertible 15-eu0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS), SND_PCI_QUIRK(0x103c, 0x888d, "HP ZBook Power 15.6 inch G8 Mobile Workstation PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8895, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED), @@ -10548,6 +10592,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8d84, "HP EliteBook X G1i", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8d91, "HP ZBook Firefly 14 G12", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8d92, "HP ZBook Firefly 16 G12", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8de8, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2), + SND_PCI_QUIRK(0x103c, 0x8de9, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2), SND_PCI_QUIRK(0x103c, 0x8e18, "HP ZBook Firefly 14 G12A", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8e19, "HP ZBook Firefly 14 G12A", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8e1a, "HP ZBook Firefly 14 G12A", ALC285_FIXUP_HP_GPIO_LED), @@ -10641,6 +10687,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e1f, "ASUS Vivobook 15 X1504VAP", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS), + SND_PCI_QUIRK(0x1043, 0x1e63, "ASUS H7606W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), + SND_PCI_QUIRK(0x1043, 0x1e83, "ASUS GA605W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RCLA72", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x1043, 0x1ed3, "ASUS HN7306W", ALC287_FIXUP_CS35L41_I2C_2), @@ -10886,7 +10934,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), HDA_CODEC_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x386e, "Yoga Pro 7 14ARP8", ALC285_FIXUP_SPEAKER2_TO_DAC1), - HDA_CODEC_QUIRK(0x17aa, 0x386f, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), + HDA_CODEC_QUIRK(0x17aa, 0x38a8, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */ SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C), SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), @@ -10930,8 +10978,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38e0, "Yoga Y990 Intel VECO Dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38f8, "Yoga Book 9i", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38df, "Y990 YG DUAL", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x17aa, 0x38f9, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x38f9, "Thinkbook 16P Gen5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x38fd, "ThinkBook plus Gen5 Hybrid", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC), @@ -10961,6 +11009,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), SND_PCI_QUIRK(0x17aa, 0x9e56, "Lenovo ZhaoYang CF4620Z", ALC286_FIXUP_SONY_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1849, 0x0269, "Positivo Master C6400", ALC269VB_FIXUP_ASUS_ZENBOOK), SND_PCI_QUIRK(0x1849, 0x1233, "ASRock NUC Box 1100", ALC233_FIXUP_NO_AUDIO_JACK), SND_PCI_QUIRK(0x1849, 0xa233, "Positivo Master C6300", ALC269_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1854, 0x0440, "LG CQ6", ALC256_FIXUP_HEADPHONE_AMP_VOL), @@ -10995,6 +11044,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), + SND_PCI_QUIRK(0x1f66, 0x0105, "Ayaneo Portable Game Player", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), @@ -11009,6 +11059,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 /* Below is a quirk table taken from the old code. @@ -11065,7 +11116,7 @@ static const struct hda_quirk alc269_fixup_vendor_tbl[] = { SND_PCI_QUIRK_VENDOR(0x1025, "Acer Aspire", ALC271_FIXUP_DMIC), SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO), - SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", ALC269_FIXUP_THINKPAD_ACPI), + SND_PCI_QUIRK_VENDOR(0x17aa, "Lenovo XPAD", ALC269_FIXUP_LENOVO_XPAD_ACPI), SND_PCI_QUIRK_VENDOR(0x19e5, "Huawei Matebook", ALC255_FIXUP_MIC_MUTE_LED), {} }; @@ -11130,6 +11181,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC290_FIXUP_MONO_SPEAKERS_HSJACK, .name = "mono-speakers"}, {.id = ALC290_FIXUP_SUBWOOFER_HSJACK, .name = "alc290-subwoofer"}, {.id = ALC269_FIXUP_THINKPAD_ACPI, .name = "thinkpad"}, + {.id = ALC269_FIXUP_LENOVO_XPAD_ACPI, .name = "lenovo-xpad-led"}, {.id = ALC269_FIXUP_DMIC_THINKPAD_ACPI, .name = "dmic-thinkpad"}, {.id = ALC255_FIXUP_ACER_MIC_NO_PRESENCE, .name = "alc255-acer"}, {.id = ALC255_FIXUP_ASUS_MIC_NO_PRESENCE, .name = "alc255-asus"}, diff --git a/sound/pci/hda/tas2781-spi.h b/sound/pci/hda/tas2781-spi.h new file mode 100644 index 000000000000..ecfc3c8bb821 --- /dev/null +++ b/sound/pci/hda/tas2781-spi.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// +// ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier +// +// Copyright (C) 2024 Texas Instruments Incorporated +// https://www.ti.com +// +// The TAS2781 driver implements a flexible and configurable +// algo coefficient setting for TAS2781 chips. +// +// Author: Baojun Xu <baojun.xu@ti.com> +// + +#ifndef __TAS2781_SPI_H__ +#define __TAS2781_SPI_H__ + +#define TASDEVICE_RATES \ + (SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000 | \ + SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_88200) + +#define TASDEVICE_FORMATS \ + (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE | \ + SNDRV_PCM_FMTBIT_S32_LE) + +#define TASDEVICE_MAX_BOOK_NUM 256 +#define TASDEVICE_MAX_PAGE 256 + +#define TASDEVICE_MAX_SIZE (TASDEVICE_MAX_BOOK_NUM * TASDEVICE_MAX_PAGE) + +/* PAGE Control Register (available in page0 of each book) */ +#define TASDEVICE_PAGE_SELECT 0x00 +#define TASDEVICE_BOOKCTL_PAGE 0x00 +#define TASDEVICE_BOOKCTL_REG GENMASK(7, 1) +#define TASDEVICE_BOOK_ID(reg) (((reg) & GENMASK(24, 16)) >> 16) +#define TASDEVICE_PAGE_ID(reg) (((reg) & GENMASK(15, 8)) >> 8) +#define TASDEVICE_REG_ID(reg) (((reg) & GENMASK(7, 1)) >> 1) +#define TASDEVICE_PAGE_REG(reg) ((reg) & GENMASK(15, 1)) +#define TASDEVICE_REG(book, page, reg) \ + (((book) << 16) | ((page) << 8) | ((reg) << 1)) + +/* Software Reset */ +#define TAS2781_REG_SWRESET TASDEVICE_REG(0x0, 0x0, 0x01) +#define TAS2781_REG_SWRESET_RESET BIT(0) + +/* System Reset Check Register */ +#define TAS2781_REG_CLK_CONFIG TASDEVICE_REG(0x0, 0x0, 0x5c) +#define TAS2781_REG_CLK_CONFIG_RESET (0x19) +#define TAS2781_PRE_POST_RESET_CFG 3 + +/* Block Checksum */ +#define TASDEVICE_CHECKSUM TASDEVICE_REG(0x0, 0x0, 0x7e) + +/* Volume control */ +#define TAS2781_DVC_LVL TASDEVICE_REG(0x0, 0x0, 0x1a) +#define TAS2781_AMP_LEVEL TASDEVICE_REG(0x0, 0x0, 0x03) +#define TAS2781_AMP_LEVEL_MASK GENMASK(5, 1) + +#define TASDEVICE_CMD_SING_W 0x1 +#define TASDEVICE_CMD_BURST 0x2 +#define TASDEVICE_CMD_DELAY 0x3 +#define TASDEVICE_CMD_FIELD_W 0x4 + +#define TAS2781_SPI_MAX_FREQ (4 * HZ_PER_MHZ) + +#define TASDEVICE_CRC8_POLYNOMIAL 0x4d +#define TASDEVICE_SPEAKER_CALIBRATION_SIZE 20 + +/* Flag of calibration registers address. */ +#define TASDEVICE_CALIBRATION_REG_ADDRESS BIT(7) + +#define TASDEVICE_CALIBRATION_DATA_NAME L"CALI_DATA" +#define TASDEVICE_CALIBRATION_DATA_SIZE 256 + +enum calib_data { + R0_VAL = 0, + INV_R0, + R0LOW, + POWER, + TLIM, + CALIB_MAX +}; + +struct tasdevice_priv { + struct tasdevice_fw *cali_data_fmw; + struct tasdevice_rca rcabin; + struct tasdevice_fw *fmw; + struct gpio_desc *reset; + struct mutex codec_lock; + struct regmap *regmap; + struct device *dev; + struct tm tm; + + unsigned char crc8_lkp_tbl[CRC8_TABLE_SIZE]; + unsigned char coef_binaryname[64]; + unsigned char rca_binaryname[64]; + unsigned char dev_name[32]; + + bool force_fwload_status; + bool playback_started; + bool is_loading; + bool is_loaderr; + unsigned int cali_reg_array[CALIB_MAX]; + unsigned int cali_data[CALIB_MAX]; + unsigned int err_code; + void *codec; + int cur_book; + int cur_prog; + int cur_conf; + int fw_state; + int index; + int irq; + + int (*fw_parse_variable_header)(struct tasdevice_priv *tas_priv, + const struct firmware *fmw, + int offset); + int (*fw_parse_program_data)(struct tasdevice_priv *tas_priv, + struct tasdevice_fw *tas_fmw, + const struct firmware *fmw, int offset); + int (*fw_parse_configuration_data)(struct tasdevice_priv *tas_priv, + struct tasdevice_fw *tas_fmw, + const struct firmware *fmw, + int offset); + int (*tasdevice_load_block)(struct tasdevice_priv *tas_priv, + struct tasdev_blk *block); + + int (*save_calibration)(struct tasdevice_priv *tas_priv); + void (*apply_calibration)(struct tasdevice_priv *tas_priv); +}; + +int tasdevice_spi_dev_read(struct tasdevice_priv *tas_priv, + unsigned int reg, unsigned int *value); +int tasdevice_spi_dev_write(struct tasdevice_priv *tas_priv, + unsigned int reg, unsigned int value); +int tasdevice_spi_dev_bulk_write(struct tasdevice_priv *tas_priv, + unsigned int reg, unsigned char *p_data, + unsigned int n_length); +int tasdevice_spi_dev_bulk_read(struct tasdevice_priv *tas_priv, + unsigned int reg, unsigned char *p_data, + unsigned int n_length); +int tasdevice_spi_dev_update_bits(struct tasdevice_priv *tasdevice, + unsigned int reg, unsigned int mask, + unsigned int value); + +void tasdevice_spi_select_cfg_blk(void *context, int conf_no, + unsigned char block_type); +void tasdevice_spi_config_info_remove(void *context); +int tasdevice_spi_dsp_parser(void *context); +int tasdevice_spi_rca_parser(void *context, const struct firmware *fmw); +void tasdevice_spi_dsp_remove(void *context); +void tasdevice_spi_calbin_remove(void *context); +int tasdevice_spi_select_tuningprm_cfg(void *context, int prm, int cfg_no, + int rca_conf_no); +int tasdevice_spi_prmg_load(void *context, int prm_no); +int tasdevice_spi_prmg_calibdata_load(void *context, int prm_no); +void tasdevice_spi_tuning_switch(void *context, int state); +int tas2781_spi_load_calibration(void *context, char *file_name, + unsigned short i); +#endif /* __TAS2781_SPI_H__ */ diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 0af015806aba..0e42b87dadb8 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -142,6 +142,9 @@ static int tas2781_read_acpi(struct tasdevice_priv *p, const char *hid) } sub = acpi_get_subsystem_id(ACPI_HANDLE(physdev)); if (IS_ERR(sub)) { + /* No subsys id in older tas2563 projects. */ + if (!strncmp(hid, "INT8866", sizeof("INT8866"))) + goto end_2563; dev_err(p->dev, "Failed to get SUBSYS ID.\n"); ret = PTR_ERR(sub); goto err; @@ -164,6 +167,7 @@ static int tas2781_read_acpi(struct tasdevice_priv *p, const char *hid) p->speaker_id = NULL; } +end_2563: acpi_dev_free_resource_list(&resources); strscpy(p->dev_name, hid, sizeof(p->dev_name)); put_device(physdev); diff --git a/sound/pci/hda/tas2781_hda_spi.c b/sound/pci/hda/tas2781_hda_spi.c new file mode 100644 index 000000000000..a42fa990e7b9 --- /dev/null +++ b/sound/pci/hda/tas2781_hda_spi.c @@ -0,0 +1,1265 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// TAS2781 HDA SPI driver +// +// Copyright 2024 Texas Instruments, Inc. +// +// Author: Baojun Xu <baojun.xu@ti.com> + +#include <linux/acpi.h> +#include <linux/array_size.h> +#include <linux/bits.h> +#include <linux/cleanup.h> +#include <linux/crc8.h> +#include <linux/crc32.h> +#include <linux/efi.h> +#include <linux/firmware.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/pm_runtime.h> +#include <linux/property.h> +#include <linux/regmap.h> +#include <linux/spi/spi.h> +#include <linux/time.h> +#include <linux/types.h> +#include <linux/units.h> + +#include <sound/hda_codec.h> +#include <sound/soc.h> +#include <sound/tas2781-dsp.h> +#include <sound/tlv.h> +#include <sound/tas2781-tlv.h> + +#include "tas2781-spi.h" + +#include "hda_local.h" +#include "hda_auto_parser.h" +#include "hda_component.h" +#include "hda_jack.h" +#include "hda_generic.h" + +/* + * No standard control callbacks for SNDRV_CTL_ELEM_IFACE_CARD + * Define two controls, one is Volume control callbacks, the other is + * flag setting control callbacks. + */ + +/* Volume control callbacks for tas2781 */ +#define ACARD_SINGLE_RANGE_EXT_TLV(xname, xreg, xshift, xmin, xmax, xinvert, \ + xhandler_get, xhandler_put, tlv_array) { \ + .iface = SNDRV_CTL_ELEM_IFACE_CARD, .name = (xname), \ + .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \ + SNDRV_CTL_ELEM_ACCESS_READWRITE, \ + .tlv.p = (tlv_array), \ + .info = snd_soc_info_volsw_range, \ + .get = xhandler_get, .put = xhandler_put, \ + .private_value = (unsigned long)&(struct soc_mixer_control) { \ + .reg = xreg, .rreg = xreg, \ + .shift = xshift, .rshift = xshift,\ + .min = xmin, .max = xmax, .invert = xinvert, \ + } \ +} + +/* Flag control callbacks for tas2781 */ +#define ACARD_SINGLE_BOOL_EXT(xname, xdata, xhandler_get, xhandler_put) { \ + .iface = SNDRV_CTL_ELEM_IFACE_CARD, \ + .name = xname, \ + .info = snd_ctl_boolean_mono_info, \ + .get = xhandler_get, \ + .put = xhandler_put, \ + .private_value = xdata, \ +} + +struct tas2781_hda { + struct tasdevice_priv *priv; + struct acpi_device *dacpi; + struct snd_kcontrol *dsp_prog_ctl; + struct snd_kcontrol *dsp_conf_ctl; + struct snd_kcontrol *snd_ctls[3]; + struct snd_kcontrol *prof_ctl; +}; + +static const struct regmap_range_cfg tasdevice_ranges[] = { + { + .range_min = 0, + .range_max = TASDEVICE_MAX_SIZE, + .selector_reg = TASDEVICE_PAGE_SELECT, + .selector_mask = GENMASK(7, 0), + .selector_shift = 0, + .window_start = 0, + .window_len = TASDEVICE_MAX_PAGE, + }, +}; + +static const struct regmap_config tasdevice_regmap = { + .reg_bits = 8, + .val_bits = 8, + .zero_flag_mask = true, + .cache_type = REGCACHE_NONE, + .ranges = tasdevice_ranges, + .num_ranges = ARRAY_SIZE(tasdevice_ranges), + .max_register = TASDEVICE_MAX_SIZE, +}; + +static int tasdevice_spi_switch_book(struct tasdevice_priv *tas_priv, int reg) +{ + struct regmap *map = tas_priv->regmap; + + if (tas_priv->cur_book != TASDEVICE_BOOK_ID(reg)) { + int ret = regmap_write(map, TASDEVICE_BOOKCTL_REG, + TASDEVICE_BOOK_ID(reg)); + if (ret < 0) { + dev_err(tas_priv->dev, "Switch Book E=%d\n", ret); + return ret; + } + tas_priv->cur_book = TASDEVICE_BOOK_ID(reg); + } + return 0; +} + +int tasdevice_spi_dev_read(struct tasdevice_priv *tas_priv, + unsigned int reg, + unsigned int *val) +{ + struct regmap *map = tas_priv->regmap; + int ret; + + ret = tasdevice_spi_switch_book(tas_priv, reg); + if (ret < 0) + return ret; + + /* + * In our TAS2781 SPI mode, if read from other book (not book 0), + * or read from page number larger than 1 in book 0, one more byte + * read is needed, and first byte is a dummy byte, need to be ignored. + */ + if ((TASDEVICE_BOOK_ID(reg) > 0) || (TASDEVICE_PAGE_ID(reg) > 1)) { + unsigned char data[2]; + + ret = regmap_bulk_read(map, TASDEVICE_PAGE_REG(reg) | 1, + data, sizeof(data)); + *val = data[1]; + } else { + ret = regmap_read(map, TASDEVICE_PAGE_REG(reg) | 1, val); + } + if (ret < 0) + dev_err(tas_priv->dev, "%s, E=%d\n", __func__, ret); + + return ret; +} + +int tasdevice_spi_dev_write(struct tasdevice_priv *tas_priv, + unsigned int reg, + unsigned int value) +{ + struct regmap *map = tas_priv->regmap; + int ret; + + ret = tasdevice_spi_switch_book(tas_priv, reg); + if (ret < 0) + return ret; + + ret = regmap_write(map, TASDEVICE_PAGE_REG(reg), value); + if (ret < 0) + dev_err(tas_priv->dev, "%s, E=%d\n", __func__, ret); + + return ret; +} + +int tasdevice_spi_dev_bulk_write(struct tasdevice_priv *tas_priv, + unsigned int reg, + unsigned char *data, + unsigned int len) +{ + struct regmap *map = tas_priv->regmap; + int ret; + + ret = tasdevice_spi_switch_book(tas_priv, reg); + if (ret < 0) + return ret; + + ret = regmap_bulk_write(map, TASDEVICE_PAGE_REG(reg), data, len); + if (ret < 0) + dev_err(tas_priv->dev, "%s, E=%d\n", __func__, ret); + + return ret; +} + +int tasdevice_spi_dev_bulk_read(struct tasdevice_priv *tas_priv, + unsigned int reg, + unsigned char *data, + unsigned int len) +{ + struct regmap *map = tas_priv->regmap; + int ret; + + ret = tasdevice_spi_switch_book(tas_priv, reg); + if (ret < 0) + return ret; + + if (len > TASDEVICE_MAX_PAGE) + len = TASDEVICE_MAX_PAGE; + /* + * In our TAS2781 SPI mode, if read from other book (not book 0), + * or read from page number larger than 1 in book 0, one more byte + * read is needed, and first byte is a dummy byte, need to be ignored. + */ + if ((TASDEVICE_BOOK_ID(reg) > 0) || (TASDEVICE_PAGE_ID(reg) > 1)) { + unsigned char buf[TASDEVICE_MAX_PAGE+1]; + + ret = regmap_bulk_read(map, TASDEVICE_PAGE_REG(reg) | 1, buf, + len + 1); + memcpy(data, buf + 1, len); + } else { + ret = regmap_bulk_read(map, TASDEVICE_PAGE_REG(reg) | 1, data, + len); + } + if (ret < 0) + dev_err(tas_priv->dev, "%s, E=%d\n", __func__, ret); + + return ret; +} + +int tasdevice_spi_dev_update_bits(struct tasdevice_priv *tas_priv, + unsigned int reg, + unsigned int mask, + unsigned int value) +{ + struct regmap *map = tas_priv->regmap; + int ret, val; + + /* + * In our TAS2781 SPI mode, read/write was masked in last bit of + * address, it cause regmap_update_bits() not work as expected. + */ + ret = tasdevice_spi_dev_read(tas_priv, reg, &val); + if (ret < 0) { + dev_err(tas_priv->dev, "%s, E=%d\n", __func__, ret); + return ret; + } + ret = regmap_write(map, TASDEVICE_PAGE_REG(reg), + (val & ~mask) | (mask & value)); + if (ret < 0) + dev_err(tas_priv->dev, "%s, E=%d\n", __func__, ret); + + return ret; +} + +static void tas2781_spi_reset(struct tasdevice_priv *tas_dev) +{ + int ret; + + if (tas_dev->reset) { + gpiod_set_value_cansleep(tas_dev->reset, 0); + fsleep(800); + gpiod_set_value_cansleep(tas_dev->reset, 1); + } + ret = tasdevice_spi_dev_write(tas_dev, TAS2781_REG_SWRESET, + TAS2781_REG_SWRESET_RESET); + if (ret < 0) + dev_err(tas_dev->dev, "dev sw-reset fail, %d\n", ret); + fsleep(1000); +} + +static int tascodec_spi_init(struct tasdevice_priv *tas_priv, + void *codec, struct module *module, + void (*cont)(const struct firmware *fw, void *context)) +{ + int ret; + + /* + * Codec Lock Hold to ensure that codec_probe and firmware parsing and + * loading do not simultaneously execute. + */ + guard(mutex)(&tas_priv->codec_lock); + + scnprintf(tas_priv->rca_binaryname, + sizeof(tas_priv->rca_binaryname), "%sRCA%d.bin", + tas_priv->dev_name, tas_priv->index); + crc8_populate_msb(tas_priv->crc8_lkp_tbl, TASDEVICE_CRC8_POLYNOMIAL); + tas_priv->codec = codec; + ret = request_firmware_nowait(module, FW_ACTION_UEVENT, + tas_priv->rca_binaryname, tas_priv->dev, GFP_KERNEL, tas_priv, + cont); + if (ret) + dev_err(tas_priv->dev, "request_firmware_nowait err:0x%08x\n", + ret); + + return ret; +} + +static void tasdevice_spi_init(struct tasdevice_priv *tas_priv) +{ + tas_priv->cur_prog = -1; + tas_priv->cur_conf = -1; + + tas_priv->cur_book = -1; + tas_priv->cur_prog = -1; + tas_priv->cur_conf = -1; + + /* Store default registers address for calibration data. */ + tas_priv->cali_reg_array[0] = TASDEVICE_REG(0, 0x17, 0x74); + tas_priv->cali_reg_array[1] = TASDEVICE_REG(0, 0x18, 0x0c); + tas_priv->cali_reg_array[2] = TASDEVICE_REG(0, 0x18, 0x14); + tas_priv->cali_reg_array[3] = TASDEVICE_REG(0, 0x13, 0x70); + tas_priv->cali_reg_array[4] = TASDEVICE_REG(0, 0x18, 0x7c); + + mutex_init(&tas_priv->codec_lock); +} + +static int tasdevice_spi_amp_putvol(struct tasdevice_priv *tas_priv, + struct snd_ctl_elem_value *ucontrol, + struct soc_mixer_control *mc) +{ + unsigned int invert = mc->invert; + unsigned char mask; + int max = mc->max; + int val, ret; + + mask = rounddown_pow_of_two(max); + mask <<= mc->shift; + val = clamp(invert ? max - ucontrol->value.integer.value[0] : + ucontrol->value.integer.value[0], 0, max); + ret = tasdevice_spi_dev_update_bits(tas_priv, + mc->reg, mask, (unsigned int)(val << mc->shift)); + if (ret) + dev_err(tas_priv->dev, "set AMP vol error in dev %d\n", + tas_priv->index); + + return ret; +} + +static int tasdevice_spi_amp_getvol(struct tasdevice_priv *tas_priv, + struct snd_ctl_elem_value *ucontrol, + struct soc_mixer_control *mc) +{ + unsigned int invert = mc->invert; + unsigned char mask = 0; + int max = mc->max; + int ret, val; + + /* Read the primary device */ + ret = tasdevice_spi_dev_read(tas_priv, mc->reg, &val); + if (ret) { + dev_err(tas_priv->dev, "%s, get AMP vol error\n", __func__); + return ret; + } + + mask = rounddown_pow_of_two(max); + mask <<= mc->shift; + val = (val & mask) >> mc->shift; + val = clamp(invert ? max - val : val, 0, max); + ucontrol->value.integer.value[0] = val; + + return ret; +} + +static int tasdevice_spi_digital_putvol(struct tasdevice_priv *tas_priv, + struct snd_ctl_elem_value *ucontrol, + struct soc_mixer_control *mc) +{ + unsigned int invert = mc->invert; + int max = mc->max; + int val, ret; + + val = clamp(invert ? max - ucontrol->value.integer.value[0] : + ucontrol->value.integer.value[0], 0, max); + ret = tasdevice_spi_dev_write(tas_priv, mc->reg, (unsigned int)val); + if (ret) + dev_err(tas_priv->dev, "set digital vol err in dev %d\n", + tas_priv->index); + + return ret; +} + +static int tasdevice_spi_digital_getvol(struct tasdevice_priv *tas_priv, + struct snd_ctl_elem_value *ucontrol, + struct soc_mixer_control *mc) +{ + unsigned int invert = mc->invert; + int max = mc->max; + int ret, val; + + /* Read the primary device as the whole */ + ret = tasdevice_spi_dev_read(tas_priv, mc->reg, &val); + if (ret) { + dev_err(tas_priv->dev, "%s, get digital vol err\n", __func__); + return ret; + } + + val = clamp(invert ? max - val : val, 0, max); + ucontrol->value.integer.value[0] = val; + + return ret; +} + +static int tas2781_read_acpi(struct tas2781_hda *tas_hda, + const char *hid, + int id) +{ + struct tasdevice_priv *p = tas_hda->priv; + struct acpi_device *adev; + struct device *physdev; + u32 values[HDA_MAX_COMPONENTS]; + const char *property; + size_t nval; + int ret, i; + + adev = acpi_dev_get_first_match_dev(hid, NULL, -1); + if (!adev) { + dev_err(p->dev, "Failed to find ACPI device: %s\n", hid); + return -ENODEV; + } + + strscpy(p->dev_name, hid, sizeof(p->dev_name)); + tas_hda->dacpi = adev; + physdev = get_device(acpi_get_first_physical_node(adev)); + acpi_dev_put(adev); + + property = "ti,dev-index"; + ret = device_property_count_u32(physdev, property); + if (ret <= 0 || ret > ARRAY_SIZE(values)) { + ret = -EINVAL; + goto err; + } + nval = ret; + + ret = device_property_read_u32_array(physdev, property, values, nval); + if (ret) + goto err; + + p->index = U8_MAX; + for (i = 0; i < nval; i++) { + if (values[i] == id) { + p->index = i; + break; + } + } + if (p->index == U8_MAX) { + dev_dbg(p->dev, "No index found in %s\n", property); + ret = -ENODEV; + goto err; + } + + if (p->index == 0) { + /* All of amps share same RESET pin. */ + p->reset = devm_gpiod_get_index_optional(physdev, "reset", + p->index, GPIOD_OUT_LOW); + if (IS_ERR(p->reset)) { + ret = PTR_ERR(p->reset); + dev_err_probe(p->dev, ret, "Failed on reset GPIO\n"); + goto err; + } + } + put_device(physdev); + + return 0; +err: + dev_err(p->dev, "read acpi error, ret: %d\n", ret); + put_device(physdev); + acpi_dev_put(adev); + + return ret; +} + +static void tas2781_hda_playback_hook(struct device *dev, int action) +{ + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + + if (action == HDA_GEN_PCM_ACT_OPEN) { + pm_runtime_get_sync(dev); + guard(mutex)(&tas_hda->priv->codec_lock); + tasdevice_spi_tuning_switch(tas_hda->priv, 0); + } else if (action == HDA_GEN_PCM_ACT_CLOSE) { + guard(mutex)(&tas_hda->priv->codec_lock); + tasdevice_spi_tuning_switch(tas_hda->priv, 1); + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + } +} + +static int tasdevice_info_profile(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_info *uinfo) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + + uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 1; + uinfo->value.integer.min = 0; + uinfo->value.integer.max = tas_priv->rcabin.ncfgs - 1; + + return 0; +} + +static int tasdevice_get_profile_id(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + + ucontrol->value.integer.value[0] = tas_priv->rcabin.profile_cfg_id; + + return 0; +} + +static int tasdevice_set_profile_id(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + int max = tas_priv->rcabin.ncfgs - 1; + int val; + + val = clamp(ucontrol->value.integer.value[0], 0, max); + if (tas_priv->rcabin.profile_cfg_id != val) { + tas_priv->rcabin.profile_cfg_id = val; + return 1; + } + + return 0; +} + +static int tasdevice_info_programs(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_info *uinfo) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + + uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 1; + uinfo->value.integer.min = 0; + uinfo->value.integer.max = tas_priv->fmw->nr_programs - 1; + + return 0; +} + +static int tasdevice_info_config(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_info *uinfo) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + + uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 1; + uinfo->value.integer.min = 0; + uinfo->value.integer.max = tas_priv->fmw->nr_configurations - 1; + + return 0; +} + +static int tasdevice_program_get(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + + ucontrol->value.integer.value[0] = tas_priv->cur_prog; + + return 0; +} + +static int tasdevice_program_put(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + int nr_program = ucontrol->value.integer.value[0]; + int max = tas_priv->fmw->nr_programs - 1; + int val; + + val = clamp(nr_program, 0, max); + + if (tas_priv->cur_prog != val) { + tas_priv->cur_prog = val; + return 1; + } + + return 0; +} + +static int tasdevice_config_get(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + + ucontrol->value.integer.value[0] = tas_priv->cur_conf; + + return 0; +} + +static int tasdevice_config_put(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + int max = tas_priv->fmw->nr_configurations - 1; + int val; + + val = clamp(ucontrol->value.integer.value[0], 0, max); + + if (tas_priv->cur_conf != val) { + tas_priv->cur_conf = val; + return 1; + } + + return 0; +} + +/* + * tas2781_digital_getvol - get the volum control + * @kcontrol: control pointer + * @ucontrol: User data + * + * Customer Kcontrol for tas2781 is primarily for regmap booking, paging + * depends on internal regmap mechanism. + * tas2781 contains book and page two-level register map, especially + * book switching will set the register BXXP00R7F, after switching to the + * correct book, then leverage the mechanism for paging to access the + * register. + * + * Return 0 if succeeded. + */ +static int tas2781_digital_getvol(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + struct soc_mixer_control *mc = + (struct soc_mixer_control *)kcontrol->private_value; + + return tasdevice_spi_digital_getvol(tas_priv, ucontrol, mc); +} + +static int tas2781_amp_getvol(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + struct soc_mixer_control *mc = + (struct soc_mixer_control *)kcontrol->private_value; + + return tasdevice_spi_amp_getvol(tas_priv, ucontrol, mc); +} + +static int tas2781_digital_putvol(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + struct soc_mixer_control *mc = + (struct soc_mixer_control *)kcontrol->private_value; + + /* The check of the given value is in tasdevice_digital_putvol. */ + return tasdevice_spi_digital_putvol(tas_priv, ucontrol, mc); +} + +static int tas2781_amp_putvol(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + struct soc_mixer_control *mc = + (struct soc_mixer_control *)kcontrol->private_value; + + /* The check of the given value is in tasdevice_amp_putvol. */ + return tasdevice_spi_amp_putvol(tas_priv, ucontrol, mc); +} + +static int tas2781_force_fwload_get(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + + ucontrol->value.integer.value[0] = (int)tas_priv->force_fwload_status; + dev_dbg(tas_priv->dev, "%s : Force FWload %s\n", __func__, + str_on_off(tas_priv->force_fwload_status)); + + return 0; +} + +static int tas2781_force_fwload_put(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + bool change, val = (bool)ucontrol->value.integer.value[0]; + + if (tas_priv->force_fwload_status == val) { + change = false; + } else { + change = true; + tas_priv->force_fwload_status = val; + } + dev_dbg(tas_priv->dev, "%s : Force FWload %s\n", __func__, + str_on_off(tas_priv->force_fwload_status)); + + return change; +} + +static const struct snd_kcontrol_new tas2781_snd_controls[] = { + ACARD_SINGLE_RANGE_EXT_TLV("Speaker Analog Gain 0", TAS2781_AMP_LEVEL, + 1, 0, 20, 0, tas2781_amp_getvol, + tas2781_amp_putvol, amp_vol_tlv), + ACARD_SINGLE_RANGE_EXT_TLV("Speaker Digital Gain 0", TAS2781_DVC_LVL, + 0, 0, 200, 1, tas2781_digital_getvol, + tas2781_digital_putvol, dvc_tlv), + ACARD_SINGLE_BOOL_EXT("Speaker Force Firmware Load 0", 0, + tas2781_force_fwload_get, tas2781_force_fwload_put), + ACARD_SINGLE_RANGE_EXT_TLV("Speaker Analog Gain 1", TAS2781_AMP_LEVEL, + 1, 0, 20, 0, tas2781_amp_getvol, + tas2781_amp_putvol, amp_vol_tlv), + ACARD_SINGLE_RANGE_EXT_TLV("Speaker Digital Gain 1", TAS2781_DVC_LVL, + 0, 0, 200, 1, tas2781_digital_getvol, + tas2781_digital_putvol, dvc_tlv), + ACARD_SINGLE_BOOL_EXT("Speaker Force Firmware Load 1", 0, + tas2781_force_fwload_get, tas2781_force_fwload_put), +}; + +static const struct snd_kcontrol_new tas2781_prof_ctrl[] = { +{ + .name = "Speaker Profile Id - 0", + .iface = SNDRV_CTL_ELEM_IFACE_CARD, + .info = tasdevice_info_profile, + .get = tasdevice_get_profile_id, + .put = tasdevice_set_profile_id, +}, +{ + .name = "Speaker Profile Id - 1", + .iface = SNDRV_CTL_ELEM_IFACE_CARD, + .info = tasdevice_info_profile, + .get = tasdevice_get_profile_id, + .put = tasdevice_set_profile_id, +}, +}; +static const struct snd_kcontrol_new tas2781_dsp_prog_ctrl[] = { +{ + .name = "Speaker Program Id 0", + .iface = SNDRV_CTL_ELEM_IFACE_CARD, + .info = tasdevice_info_programs, + .get = tasdevice_program_get, + .put = tasdevice_program_put, +}, +{ + .name = "Speaker Program Id 1", + .iface = SNDRV_CTL_ELEM_IFACE_CARD, + .info = tasdevice_info_programs, + .get = tasdevice_program_get, + .put = tasdevice_program_put, +}, +}; + +static const struct snd_kcontrol_new tas2781_dsp_conf_ctrl[] = { +{ + .name = "Speaker Config Id 0", + .iface = SNDRV_CTL_ELEM_IFACE_CARD, + .info = tasdevice_info_config, + .get = tasdevice_config_get, + .put = tasdevice_config_put, +}, +{ + .name = "Speaker Config Id 1", + .iface = SNDRV_CTL_ELEM_IFACE_CARD, + .info = tasdevice_info_config, + .get = tasdevice_config_get, + .put = tasdevice_config_put, +}, +}; + +static void tas2781_apply_calib(struct tasdevice_priv *tas_priv) +{ + int i, rc; + + /* + * If no calibration data exist in tasdevice_priv *tas_priv, + * calibration apply will be ignored, and use default values + * in firmware binary, which was loaded during firmware download. + */ + if (tas_priv->cali_data[0] == 0) + return; + /* + * Calibration data was saved in tasdevice_priv *tas_priv as: + * unsigned int cali_data[CALIB_MAX]; + * and every data (in 4 bytes) will be saved in register which in + * book 0, and page number in page_array[], offset was saved in + * rgno_array[]. + */ + for (i = 0; i < CALIB_MAX; i++) { + rc = tasdevice_spi_dev_bulk_write(tas_priv, + tas_priv->cali_reg_array[i], + (unsigned char *)&tas_priv->cali_data[i], 4); + if (rc < 0) + dev_err(tas_priv->dev, + "chn %d calib %d bulk_wr err = %d\n", + tas_priv->index, i, rc); + } +} + +/* + * Update the calibration data, including speaker impedance, f0, etc, + * into algo. Calibrate data is done by manufacturer in the factory. + * These data are used by Algo for calculating the speaker temperature, + * speaker membrane excursion and f0 in real time during playback. + * Calibration data format in EFI is V2, since 2024. + */ +static int tas2781_save_calibration(struct tasdevice_priv *tas_priv) +{ + /* + * GUID was used for data access in BIOS, it was provided by board + * manufactory, like HP: "{02f9af02-7734-4233-b43d-93fe5aa35db3}" + */ + efi_guid_t efi_guid = + EFI_GUID(0x02f9af02, 0x7734, 0x4233, + 0xb4, 0x3d, 0x93, 0xfe, 0x5a, 0xa3, 0x5d, 0xb3); + static efi_char16_t efi_name[] = TASDEVICE_CALIBRATION_DATA_NAME; + unsigned char data[TASDEVICE_CALIBRATION_DATA_SIZE], *buf; + unsigned int attr, crc, offset, *tmp_val; + struct tm *tm = &tas_priv->tm; + unsigned long total_sz = 0; + efi_status_t status; + + tas_priv->cali_data[0] = 0; + status = efi.get_variable(efi_name, &efi_guid, &attr, &total_sz, data); + if (status == EFI_BUFFER_TOO_SMALL) { + if (total_sz > TASDEVICE_CALIBRATION_DATA_SIZE) + return -ENOMEM; + /* Get variable contents into buffer */ + status = efi.get_variable(efi_name, &efi_guid, &attr, + &total_sz, data); + } + if (status != EFI_SUCCESS) + return status; + + tmp_val = (unsigned int *)data; + if (tmp_val[0] == 2781) { + /* + * New features were added in calibrated Data V3: + * 1. Added calibration registers address define in + * a node, marked as Device id == 0x80. + * New features were added in calibrated Data V2: + * 1. Added some the fields to store the link_id and + * uniqie_id for multi-link solutions + * 2. Support flexible number of devices instead of + * fixed one in V1. + * Layout of calibrated data V2 in UEFI(total 256 bytes): + * ChipID (2781, 4 bytes) + * Device-Sum (4 bytes) + * TimeStamp of Calibration (4 bytes) + * for (i = 0; i < Device-Sum; i++) { + * Device #i index_info () { + * SDW link id (2bytes) + * SDW unique_id (2bytes) + * } // if Device number is 0x80, mean it's + * calibration registers address. + * Calibrated Data of Device #i (20 bytes) + * } + * CRC (4 bytes) + * Reserved (the rest) + */ + crc = crc32(~0, data, (3 + tmp_val[1] * 6) * 4) ^ ~0; + + if (crc != tmp_val[3 + tmp_val[1] * 6]) + return 0; + + time64_to_tm(tmp_val[2], 0, tm); + for (int j = 0; j < tmp_val[1]; j++) { + offset = j * 6 + 3; + if (tmp_val[offset] == tas_priv->index) { + for (int i = 0; i < CALIB_MAX; i++) + tas_priv->cali_data[i] = + tmp_val[offset + i + 1]; + } else if (tmp_val[offset] == + TASDEVICE_CALIBRATION_REG_ADDRESS) { + for (int i = 0; i < CALIB_MAX; i++) { + buf = &data[(offset + i + 1) * 4]; + tas_priv->cali_reg_array[i] = + TASDEVICE_REG(buf[1], buf[2], + buf[3]); + } + } + tas_priv->apply_calibration(tas_priv); + } + } else { + /* + * Calibration data is in V1 format. + * struct cali_data { + * char cali_data[20]; + * } + * + * struct { + * struct cali_data cali_data[4]; + * int TimeStamp of Calibration (4 bytes) + * int CRC (4 bytes) + * } ueft; + */ + crc = crc32(~0, data, 84) ^ ~0; + if (crc == tmp_val[21]) { + time64_to_tm(tmp_val[20], 0, tm); + for (int i = 0; i < CALIB_MAX; i++) + tas_priv->cali_data[i] = + tmp_val[tas_priv->index * 5 + i]; + tas_priv->apply_calibration(tas_priv); + } + } + + return 0; +} + +static void tas2781_hda_remove_controls(struct tas2781_hda *tas_hda) +{ + struct hda_codec *codec = tas_hda->priv->codec; + + snd_ctl_remove(codec->card, tas_hda->dsp_prog_ctl); + + snd_ctl_remove(codec->card, tas_hda->dsp_conf_ctl); + + for (int i = ARRAY_SIZE(tas_hda->snd_ctls) - 1; i >= 0; i--) + snd_ctl_remove(codec->card, tas_hda->snd_ctls[i]); + + snd_ctl_remove(codec->card, tas_hda->prof_ctl); +} + +static void tasdev_fw_ready(const struct firmware *fmw, void *context) +{ + struct tasdevice_priv *tas_priv = context; + struct tas2781_hda *tas_hda = dev_get_drvdata(tas_priv->dev); + struct hda_codec *codec = tas_priv->codec; + int i, j, ret; + + pm_runtime_get_sync(tas_priv->dev); + guard(mutex)(&tas_priv->codec_lock); + + ret = tasdevice_spi_rca_parser(tas_priv, fmw); + if (ret) + goto out; + + /* Add control one time only. */ + tas_hda->prof_ctl = snd_ctl_new1(&tas2781_prof_ctrl[tas_priv->index], + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->prof_ctl); + if (ret) { + dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", + tas2781_prof_ctrl[tas_priv->index].name, ret); + goto out; + } + j = tas_priv->index * ARRAY_SIZE(tas2781_snd_controls) / 2; + for (i = 0; i < 3; i++) { + tas_hda->snd_ctls[i] = snd_ctl_new1(&tas2781_snd_controls[i+j], + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->snd_ctls[i]); + if (ret) { + dev_err(tas_priv->dev, + "Failed to add KControl %s = %d\n", + tas2781_snd_controls[i+tas_priv->index*3].name, + ret); + goto out; + } + } + + tasdevice_spi_dsp_remove(tas_priv); + + tas_priv->fw_state = TASDEVICE_DSP_FW_PENDING; + scnprintf(tas_priv->coef_binaryname, 64, "TAS2XXX%08X-%01d.bin", + codec->core.subsystem_id, tas_priv->index); + ret = tasdevice_spi_dsp_parser(tas_priv); + if (ret) { + dev_err(tas_priv->dev, "dspfw load %s error\n", + tas_priv->coef_binaryname); + tas_priv->fw_state = TASDEVICE_DSP_FW_FAIL; + goto out; + } + + /* Add control one time only. */ + tas_hda->dsp_prog_ctl = + snd_ctl_new1(&tas2781_dsp_prog_ctrl[tas_priv->index], + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->dsp_prog_ctl); + if (ret) { + dev_err(tas_priv->dev, + "Failed to add KControl %s = %d\n", + tas2781_dsp_prog_ctrl[tas_priv->index].name, ret); + goto out; + } + + tas_hda->dsp_conf_ctl = + snd_ctl_new1(&tas2781_dsp_conf_ctrl[tas_priv->index], + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->dsp_conf_ctl); + if (ret) { + dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", + tas2781_dsp_conf_ctrl[tas_priv->index].name, ret); + goto out; + } + + /* Perform AMP reset before firmware download. */ + tas_priv->rcabin.profile_cfg_id = TAS2781_PRE_POST_RESET_CFG; + tasdevice_spi_tuning_switch(tas_priv, 0); + tas2781_spi_reset(tas_priv); + tas_priv->rcabin.profile_cfg_id = 0; + tasdevice_spi_tuning_switch(tas_priv, 1); + + tas_priv->fw_state = TASDEVICE_DSP_FW_ALL_OK; + ret = tasdevice_spi_prmg_load(tas_priv, 0); + if (ret < 0) { + dev_err(tas_priv->dev, "FW download failed = %d\n", ret); + goto out; + } + if (tas_priv->fmw->nr_programs > 0) + tas_priv->cur_prog = 0; + if (tas_priv->fmw->nr_configurations > 0) + tas_priv->cur_conf = 0; + + /* + * If calibrated data occurs error, dsp will still works with default + * calibrated data inside algo. + */ + tas_priv->save_calibration(tas_priv); + +out: + if (fmw) + release_firmware(fmw); + pm_runtime_mark_last_busy(tas_hda->priv->dev); + pm_runtime_put_autosuspend(tas_hda->priv->dev); +} + +static int tas2781_hda_bind(struct device *dev, struct device *master, + void *master_data) +{ + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + struct hda_component_parent *parent = master_data; + struct hda_component *comp; + struct hda_codec *codec; + int ret; + + comp = hda_component_from_index(parent, tas_hda->priv->index); + if (!comp) + return -EINVAL; + + if (comp->dev) + return -EBUSY; + + codec = parent->codec; + + pm_runtime_get_sync(dev); + + comp->dev = dev; + + strscpy(comp->name, dev_name(dev), sizeof(comp->name)); + + ret = tascodec_spi_init(tas_hda->priv, codec, THIS_MODULE, + tasdev_fw_ready); + if (!ret) + comp->playback_hook = tas2781_hda_playback_hook; + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return ret; +} + +static void tas2781_hda_unbind(struct device *dev, struct device *master, + void *master_data) +{ + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + struct hda_component_parent *parent = master_data; + struct hda_component *comp; + + comp = hda_component_from_index(parent, tas_hda->priv->index); + if (comp && (comp->dev == dev)) { + comp->dev = NULL; + memset(comp->name, 0, sizeof(comp->name)); + comp->playback_hook = NULL; + } + + tas2781_hda_remove_controls(tas_hda); + + tasdevice_spi_config_info_remove(tas_hda->priv); + tasdevice_spi_dsp_remove(tas_hda->priv); + + tas_hda->priv->fw_state = TASDEVICE_DSP_FW_PENDING; +} + +static const struct component_ops tas2781_hda_comp_ops = { + .bind = tas2781_hda_bind, + .unbind = tas2781_hda_unbind, +}; + +static void tas2781_hda_remove(struct device *dev) +{ + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + + component_del(tas_hda->priv->dev, &tas2781_hda_comp_ops); + + pm_runtime_get_sync(tas_hda->priv->dev); + pm_runtime_disable(tas_hda->priv->dev); + + pm_runtime_put_noidle(tas_hda->priv->dev); + + mutex_destroy(&tas_hda->priv->codec_lock); +} + +static int tas2781_hda_spi_probe(struct spi_device *spi) +{ + struct tasdevice_priv *tas_priv; + struct tas2781_hda *tas_hda; + const char *device_name; + int ret = 0; + + tas_hda = devm_kzalloc(&spi->dev, sizeof(*tas_hda), GFP_KERNEL); + if (!tas_hda) + return -ENOMEM; + + spi->max_speed_hz = TAS2781_SPI_MAX_FREQ; + + tas_priv = devm_kzalloc(&spi->dev, sizeof(*tas_priv), GFP_KERNEL); + if (!tas_priv) + return -ENOMEM; + tas_priv->dev = &spi->dev; + tas_hda->priv = tas_priv; + tas_priv->regmap = devm_regmap_init_spi(spi, &tasdevice_regmap); + if (IS_ERR(tas_priv->regmap)) { + ret = PTR_ERR(tas_priv->regmap); + dev_err(tas_priv->dev, "Failed to allocate regmap: %d\n", + ret); + return ret; + } + if (strstr(dev_name(&spi->dev), "TXNW2781")) { + device_name = "TXNW2781"; + tas_priv->save_calibration = tas2781_save_calibration; + tas_priv->apply_calibration = tas2781_apply_calib; + } else { + dev_err(tas_priv->dev, "Unmatched spi dev %s\n", + dev_name(&spi->dev)); + return -ENODEV; + } + + tas_priv->irq = spi->irq; + dev_set_drvdata(&spi->dev, tas_hda); + ret = tas2781_read_acpi(tas_hda, device_name, + spi_get_chipselect(spi, 0)); + if (ret) + return dev_err_probe(tas_priv->dev, ret, + "Platform not supported\n"); + + tasdevice_spi_init(tas_priv); + + ret = component_add(tas_priv->dev, &tas2781_hda_comp_ops); + if (ret) { + dev_err(tas_priv->dev, "Register component fail: %d\n", ret); + return ret; + } + + pm_runtime_set_autosuspend_delay(tas_priv->dev, 3000); + pm_runtime_use_autosuspend(tas_priv->dev); + pm_runtime_mark_last_busy(tas_priv->dev); + pm_runtime_set_active(tas_priv->dev); + pm_runtime_get_noresume(tas_priv->dev); + pm_runtime_enable(tas_priv->dev); + + pm_runtime_put_autosuspend(tas_priv->dev); + + return 0; +} + +static void tas2781_hda_spi_remove(struct spi_device *spi) +{ + tas2781_hda_remove(&spi->dev); +} + +static int tas2781_runtime_suspend(struct device *dev) +{ + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + + guard(mutex)(&tas_hda->priv->codec_lock); + + tasdevice_spi_tuning_switch(tas_hda->priv, 1); + + tas_hda->priv->cur_book = -1; + tas_hda->priv->cur_conf = -1; + + return 0; +} + +static int tas2781_runtime_resume(struct device *dev) +{ + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + + guard(mutex)(&tas_hda->priv->codec_lock); + + tasdevice_spi_tuning_switch(tas_hda->priv, 0); + + return 0; +} + +static int tas2781_system_suspend(struct device *dev) +{ + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; + + /* Shutdown chip before system suspend */ + tasdevice_spi_tuning_switch(tas_hda->priv, 1); + tas2781_spi_reset(tas_hda->priv); + /* + * Reset GPIO may be shared, so cannot reset here. + * However beyond this point, amps may be powered down. + */ + return 0; +} + +static int tas2781_system_resume(struct device *dev) +{ + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + int ret, val; + + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + guard(mutex)(&tas_hda->priv->codec_lock); + ret = tasdevice_spi_dev_read(tas_hda->priv, TAS2781_REG_CLK_CONFIG, + &val); + if (ret < 0) + return ret; + + if (val == TAS2781_REG_CLK_CONFIG_RESET) { + tas_hda->priv->cur_book = -1; + tas_hda->priv->cur_conf = -1; + tas_hda->priv->cur_prog = -1; + + ret = tasdevice_spi_prmg_load(tas_hda->priv, 0); + if (ret < 0) { + dev_err(tas_hda->priv->dev, + "FW download failed = %d\n", ret); + return ret; + } + + if (tas_hda->priv->playback_started) + tasdevice_spi_tuning_switch(tas_hda->priv, 0); + } + + return ret; +} + +static const struct dev_pm_ops tas2781_hda_pm_ops = { + RUNTIME_PM_OPS(tas2781_runtime_suspend, tas2781_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(tas2781_system_suspend, tas2781_system_resume) +}; + +static const struct spi_device_id tas2781_hda_spi_id[] = { + { "tas2781-hda", }, + {} +}; + +static const struct acpi_device_id tas2781_acpi_hda_match[] = { + {"TXNW2781", }, + {} +}; +MODULE_DEVICE_TABLE(acpi, tas2781_acpi_hda_match); + +static struct spi_driver tas2781_hda_spi_driver = { + .driver = { + .name = "tas2781-hda", + .acpi_match_table = tas2781_acpi_hda_match, + .pm = &tas2781_hda_pm_ops, + }, + .id_table = tas2781_hda_spi_id, + .probe = tas2781_hda_spi_probe, + .remove = tas2781_hda_spi_remove, +}; +module_spi_driver(tas2781_hda_spi_driver); + +MODULE_DESCRIPTION("TAS2781 HDA SPI Driver"); +MODULE_AUTHOR("Baojun, Xu, <baojun.xug@ti.com>"); +MODULE_LICENSE("GPL"); diff --git a/sound/pci/hda/tas2781_spi_fwlib.c b/sound/pci/hda/tas2781_spi_fwlib.c new file mode 100644 index 000000000000..0e2acbc3c900 --- /dev/null +++ b/sound/pci/hda/tas2781_spi_fwlib.c @@ -0,0 +1,2006 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// TAS2781 HDA SPI driver +// +// Copyright 2024 Texas Instruments, Inc. +// +// Author: Baojun Xu <baojun.xu@ti.com> + +#include <linux/crc8.h> +#include <linux/firmware.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/unaligned.h> +#include <sound/pcm_params.h> +#include <sound/soc.h> +#include <sound/tas2781-dsp.h> +#include <sound/tlv.h> + +#include "tas2781-spi.h" + +#define OFFSET_ERROR_BIT BIT(31) + +#define ERROR_PRAM_CRCCHK 0x0000000 +#define ERROR_YRAM_CRCCHK 0x0000001 +#define PPC_DRIVER_CRCCHK 0x00000200 + +#define TAS2781_SA_COEFF_SWAP_REG TASDEVICE_REG(0, 0x35, 0x2c) +#define TAS2781_YRAM_BOOK1 140 +#define TAS2781_YRAM1_PAGE 42 +#define TAS2781_YRAM1_START_REG 88 + +#define TAS2781_YRAM2_START_PAGE 43 +#define TAS2781_YRAM2_END_PAGE 49 +#define TAS2781_YRAM2_START_REG 8 +#define TAS2781_YRAM2_END_REG 127 + +#define TAS2781_YRAM3_PAGE 50 +#define TAS2781_YRAM3_START_REG 8 +#define TAS2781_YRAM3_END_REG 27 + +/* should not include B0_P53_R44-R47 */ +#define TAS2781_YRAM_BOOK2 0 +#define TAS2781_YRAM4_START_PAGE 50 +#define TAS2781_YRAM4_END_PAGE 60 + +#define TAS2781_YRAM5_PAGE 61 +#define TAS2781_YRAM5_START_REG TAS2781_YRAM3_START_REG +#define TAS2781_YRAM5_END_REG TAS2781_YRAM3_END_REG + +#define TASDEVICE_MAXPROGRAM_NUM_KERNEL 5 +#define TASDEVICE_MAXCONFIG_NUM_KERNEL_MULTIPLE_AMPS 64 +#define TASDEVICE_MAXCONFIG_NUM_KERNEL 10 +#define MAIN_ALL_DEVICES_1X 0x01 +#define MAIN_DEVICE_A_1X 0x02 +#define MAIN_DEVICE_B_1X 0x03 +#define MAIN_DEVICE_C_1X 0x04 +#define MAIN_DEVICE_D_1X 0x05 +#define COEFF_DEVICE_A_1X 0x12 +#define COEFF_DEVICE_B_1X 0x13 +#define COEFF_DEVICE_C_1X 0x14 +#define COEFF_DEVICE_D_1X 0x15 +#define PRE_DEVICE_A_1X 0x22 +#define PRE_DEVICE_B_1X 0x23 +#define PRE_DEVICE_C_1X 0x24 +#define PRE_DEVICE_D_1X 0x25 +#define PRE_SOFTWARE_RESET_DEVICE_A 0x41 +#define PRE_SOFTWARE_RESET_DEVICE_B 0x42 +#define PRE_SOFTWARE_RESET_DEVICE_C 0x43 +#define PRE_SOFTWARE_RESET_DEVICE_D 0x44 +#define POST_SOFTWARE_RESET_DEVICE_A 0x45 +#define POST_SOFTWARE_RESET_DEVICE_B 0x46 +#define POST_SOFTWARE_RESET_DEVICE_C 0x47 +#define POST_SOFTWARE_RESET_DEVICE_D 0x48 + +struct tas_crc { + unsigned char offset; + unsigned char len; +}; + +struct blktyp_devidx_map { + unsigned char blktyp; + unsigned char dev_idx; +}; + +/* fixed m68k compiling issue: mapping table can save code field */ +static const struct blktyp_devidx_map ppc3_tas2781_mapping_table[] = { + { MAIN_ALL_DEVICES_1X, 0x80 }, + { MAIN_DEVICE_A_1X, 0x81 }, + { COEFF_DEVICE_A_1X, 0x81 }, + { PRE_DEVICE_A_1X, 0x81 }, + { PRE_SOFTWARE_RESET_DEVICE_A, 0xC1 }, + { POST_SOFTWARE_RESET_DEVICE_A, 0xC1 }, + { MAIN_DEVICE_B_1X, 0x82 }, + { COEFF_DEVICE_B_1X, 0x82 }, + { PRE_DEVICE_B_1X, 0x82 }, + { PRE_SOFTWARE_RESET_DEVICE_B, 0xC2 }, + { POST_SOFTWARE_RESET_DEVICE_B, 0xC2 }, + { MAIN_DEVICE_C_1X, 0x83 }, + { COEFF_DEVICE_C_1X, 0x83 }, + { PRE_DEVICE_C_1X, 0x83 }, + { PRE_SOFTWARE_RESET_DEVICE_C, 0xC3 }, + { POST_SOFTWARE_RESET_DEVICE_C, 0xC3 }, + { MAIN_DEVICE_D_1X, 0x84 }, + { COEFF_DEVICE_D_1X, 0x84 }, + { PRE_DEVICE_D_1X, 0x84 }, + { PRE_SOFTWARE_RESET_DEVICE_D, 0xC4 }, + { POST_SOFTWARE_RESET_DEVICE_D, 0xC4 }, +}; + +static const struct blktyp_devidx_map ppc3_mapping_table[] = { + { MAIN_ALL_DEVICES_1X, 0x80 }, + { MAIN_DEVICE_A_1X, 0x81 }, + { COEFF_DEVICE_A_1X, 0xC1 }, + { PRE_DEVICE_A_1X, 0xC1 }, + { MAIN_DEVICE_B_1X, 0x82 }, + { COEFF_DEVICE_B_1X, 0xC2 }, + { PRE_DEVICE_B_1X, 0xC2 }, + { MAIN_DEVICE_C_1X, 0x83 }, + { COEFF_DEVICE_C_1X, 0xC3 }, + { PRE_DEVICE_C_1X, 0xC3 }, + { MAIN_DEVICE_D_1X, 0x84 }, + { COEFF_DEVICE_D_1X, 0xC4 }, + { PRE_DEVICE_D_1X, 0xC4 }, +}; + +static const struct blktyp_devidx_map non_ppc3_mapping_table[] = { + { MAIN_ALL_DEVICES, 0x80 }, + { MAIN_DEVICE_A, 0x81 }, + { COEFF_DEVICE_A, 0xC1 }, + { PRE_DEVICE_A, 0xC1 }, + { MAIN_DEVICE_B, 0x82 }, + { COEFF_DEVICE_B, 0xC2 }, + { PRE_DEVICE_B, 0xC2 }, + { MAIN_DEVICE_C, 0x83 }, + { COEFF_DEVICE_C, 0xC3 }, + { PRE_DEVICE_C, 0xC3 }, + { MAIN_DEVICE_D, 0x84 }, + { COEFF_DEVICE_D, 0xC4 }, + { PRE_DEVICE_D, 0xC4 }, +}; + +/* + * Device support different configurations for different scene, + * like voice, music, calibration, was write in regbin file. + * Will be stored into tas_priv after regbin was loaded. + */ +static struct tasdevice_config_info *tasdevice_add_config( + struct tasdevice_priv *tas_priv, unsigned char *config_data, + unsigned int config_size, int *status) +{ + struct tasdevice_config_info *cfg_info; + struct tasdev_blk_data **bk_da; + unsigned int config_offset = 0; + unsigned int i; + + /* + * In most projects are many audio cases, such as music, handfree, + * receiver, games, audio-to-haptics, PMIC record, bypass mode, + * portrait, landscape, etc. Even in multiple audios, one or + * two of the chips will work for the special case, such as + * ultrasonic application. In order to support these variable-numbers + * of audio cases, flexible configs have been introduced in the + * DSP firmware. + */ + cfg_info = kzalloc(sizeof(*cfg_info), GFP_KERNEL); + if (!cfg_info) { + *status = -ENOMEM; + return NULL; + } + + if (tas_priv->rcabin.fw_hdr.binary_version_num >= 0x105) { + if ((config_offset + 64) > config_size) { + *status = -EINVAL; + dev_err(tas_priv->dev, "add conf: Out of boundary\n"); + goto config_err; + } + config_offset += 64; + } + + if ((config_offset + 4) > config_size) { + *status = -EINVAL; + dev_err(tas_priv->dev, "add config: Out of boundary\n"); + goto config_err; + } + + /* + * convert data[offset], data[offset + 1], data[offset + 2] and + * data[offset + 3] into host + */ + cfg_info->nblocks = get_unaligned_be32(&config_data[config_offset]); + config_offset += 4; + + /* + * Several kinds of dsp/algorithm firmwares can run on tas2781, + * the number and size of blk are not fixed and different among + * these firmwares. + */ + bk_da = cfg_info->blk_data = kcalloc(cfg_info->nblocks, + sizeof(*bk_da), GFP_KERNEL); + if (!bk_da) { + *status = -ENOMEM; + goto config_err; + } + cfg_info->real_nblocks = 0; + for (i = 0; i < cfg_info->nblocks; i++) { + if (config_offset + 12 > config_size) { + *status = -EINVAL; + dev_err(tas_priv->dev, + "%s: Out of boundary: i = %d nblocks = %u!\n", + __func__, i, cfg_info->nblocks); + goto block_err; + } + bk_da[i] = kzalloc(sizeof(*bk_da[i]), GFP_KERNEL); + if (!bk_da[i]) { + *status = -ENOMEM; + goto block_err; + } + + bk_da[i]->dev_idx = config_data[config_offset]; + config_offset++; + + bk_da[i]->block_type = config_data[config_offset]; + config_offset++; + + bk_da[i]->yram_checksum = + get_unaligned_be16(&config_data[config_offset]); + config_offset += 2; + bk_da[i]->block_size = + get_unaligned_be32(&config_data[config_offset]); + config_offset += 4; + + bk_da[i]->n_subblks = + get_unaligned_be32(&config_data[config_offset]); + + config_offset += 4; + + if (config_offset + bk_da[i]->block_size > config_size) { + *status = -EINVAL; + dev_err(tas_priv->dev, + "%s: Out of boundary: i = %d blks = %u!\n", + __func__, i, cfg_info->nblocks); + goto block_err; + } + /* instead of kzalloc+memcpy */ + bk_da[i]->regdata = kmemdup(&config_data[config_offset], + bk_da[i]->block_size, GFP_KERNEL); + if (!bk_da[i]->regdata) { + *status = -ENOMEM; + i++; + goto block_err; + } + + config_offset += bk_da[i]->block_size; + cfg_info->real_nblocks += 1; + } + + return cfg_info; +block_err: + for (int j = 0; j < i; j++) + kfree(bk_da[j]); + kfree(bk_da); +config_err: + kfree(cfg_info); + return NULL; +} + +/* Regbin file parser function. */ +int tasdevice_spi_rca_parser(void *context, const struct firmware *fmw) +{ + struct tasdevice_priv *tas_priv = context; + struct tasdevice_config_info **cfg_info; + struct tasdevice_rca_hdr *fw_hdr; + struct tasdevice_rca *rca; + unsigned int total_config_sz = 0; + int offset = 0, ret = 0, i; + unsigned char *buf; + + rca = &tas_priv->rcabin; + fw_hdr = &rca->fw_hdr; + if (!fmw || !fmw->data) { + dev_err(tas_priv->dev, "Failed to read %s\n", + tas_priv->rca_binaryname); + tas_priv->fw_state = TASDEVICE_DSP_FW_FAIL; + return -EINVAL; + } + buf = (unsigned char *)fmw->data; + fw_hdr->img_sz = get_unaligned_be32(&buf[offset]); + offset += 4; + if (fw_hdr->img_sz != fmw->size) { + dev_err(tas_priv->dev, + "File size not match, %d %u", (int)fmw->size, + fw_hdr->img_sz); + tas_priv->fw_state = TASDEVICE_DSP_FW_FAIL; + return -EINVAL; + } + + fw_hdr->checksum = get_unaligned_be32(&buf[offset]); + offset += 4; + fw_hdr->binary_version_num = get_unaligned_be32(&buf[offset]); + if (fw_hdr->binary_version_num < 0x103) { + dev_err(tas_priv->dev, "File version 0x%04x is too low", + fw_hdr->binary_version_num); + tas_priv->fw_state = TASDEVICE_DSP_FW_FAIL; + return -EINVAL; + } + offset += 4; + fw_hdr->drv_fw_version = get_unaligned_be32(&buf[offset]); + offset += 8; + fw_hdr->plat_type = buf[offset++]; + fw_hdr->dev_family = buf[offset++]; + fw_hdr->reserve = buf[offset++]; + fw_hdr->ndev = buf[offset++]; + if (offset + TASDEVICE_DEVICE_SUM > fw_hdr->img_sz) { + dev_err(tas_priv->dev, "rca_ready: Out of boundary!\n"); + tas_priv->fw_state = TASDEVICE_DSP_FW_FAIL; + return -EINVAL; + } + + for (i = 0; i < TASDEVICE_DEVICE_SUM; i++, offset++) + fw_hdr->devs[i] = buf[offset]; + + fw_hdr->nconfig = get_unaligned_be32(&buf[offset]); + offset += 4; + + for (i = 0; i < TASDEVICE_CONFIG_SUM; i++) { + fw_hdr->config_size[i] = get_unaligned_be32(&buf[offset]); + offset += 4; + total_config_sz += fw_hdr->config_size[i]; + } + + if (fw_hdr->img_sz - total_config_sz != (unsigned int)offset) { + dev_err(tas_priv->dev, "Bin file err %d - %d != %d!\n", + fw_hdr->img_sz, total_config_sz, (int)offset); + tas_priv->fw_state = TASDEVICE_DSP_FW_FAIL; + return -EINVAL; + } + + cfg_info = kcalloc(fw_hdr->nconfig, sizeof(*cfg_info), GFP_KERNEL); + if (!cfg_info) { + tas_priv->fw_state = TASDEVICE_DSP_FW_FAIL; + return -ENOMEM; + } + rca->cfg_info = cfg_info; + rca->ncfgs = 0; + for (i = 0; i < (int)fw_hdr->nconfig; i++) { + rca->ncfgs += 1; + cfg_info[i] = tasdevice_add_config(tas_priv, &buf[offset], + fw_hdr->config_size[i], &ret); + if (ret) { + tas_priv->fw_state = TASDEVICE_DSP_FW_FAIL; + return ret; + } + offset += (int)fw_hdr->config_size[i]; + } + + return ret; +} + +/* fixed m68k compiling issue: mapping table can save code field */ +static unsigned char map_dev_idx(struct tasdevice_fw *tas_fmw, + struct tasdev_blk *block) +{ + struct blktyp_devidx_map *p = + (struct blktyp_devidx_map *)non_ppc3_mapping_table; + struct tasdevice_dspfw_hdr *fw_hdr = &tas_fmw->fw_hdr; + struct tasdevice_fw_fixed_hdr *fw_fixed_hdr = &fw_hdr->fixed_hdr; + int i, n = ARRAY_SIZE(non_ppc3_mapping_table); + unsigned char dev_idx = 0; + + if (fw_fixed_hdr->ppcver >= PPC3_VERSION_TAS2781) { + p = (struct blktyp_devidx_map *)ppc3_tas2781_mapping_table; + n = ARRAY_SIZE(ppc3_tas2781_mapping_table); + } else if (fw_fixed_hdr->ppcver >= PPC3_VERSION) { + p = (struct blktyp_devidx_map *)ppc3_mapping_table; + n = ARRAY_SIZE(ppc3_mapping_table); + } + + for (i = 0; i < n; i++) { + if (block->type == p[i].blktyp) { + dev_idx = p[i].dev_idx; + break; + } + } + + return dev_idx; +} + +/* Block parser function. */ +static int fw_parse_block_data_kernel(struct tasdevice_fw *tas_fmw, + struct tasdev_blk *block, const struct firmware *fmw, int offset) +{ + const unsigned char *data = fmw->data; + + if (offset + 16 > fmw->size) { + dev_err(tas_fmw->dev, "%s: File Size error\n", __func__); + return -EINVAL; + } + + /* + * Convert data[offset], data[offset + 1], data[offset + 2] and + * data[offset + 3] into host. + */ + block->type = get_unaligned_be32(&data[offset]); + offset += 4; + + block->is_pchksum_present = data[offset++]; + block->pchksum = data[offset++]; + block->is_ychksum_present = data[offset++]; + block->ychksum = data[offset++]; + block->blk_size = get_unaligned_be32(&data[offset]); + offset += 4; + block->nr_subblocks = get_unaligned_be32(&data[offset]); + offset += 4; + + /* + * Fixed m68k compiling issue: + * 1. mapping table can save code field. + * 2. storing the dev_idx as a member of block can reduce unnecessary + * time and system resource comsumption of dev_idx mapping every + * time the block data writing to the dsp. + */ + block->dev_idx = map_dev_idx(tas_fmw, block); + + if (offset + block->blk_size > fmw->size) { + dev_err(tas_fmw->dev, "%s: nSublocks error\n", __func__); + return -EINVAL; + } + /* instead of kzalloc+memcpy */ + block->data = kmemdup(&data[offset], block->blk_size, GFP_KERNEL); + if (!block->data) + return -ENOMEM; + + offset += block->blk_size; + + return offset; +} + +/* Data of block parser function. */ +static int fw_parse_data_kernel(struct tasdevice_fw *tas_fmw, + struct tasdevice_data *img_data, const struct firmware *fmw, + int offset) +{ + const unsigned char *data = fmw->data; + struct tasdev_blk *blk; + unsigned int i; + + if (offset + 4 > fmw->size) { + dev_err(tas_fmw->dev, "%s: File Size error\n", __func__); + return -EINVAL; + } + img_data->nr_blk = get_unaligned_be32(&data[offset]); + offset += 4; + + img_data->dev_blks = kcalloc(img_data->nr_blk, + sizeof(struct tasdev_blk), GFP_KERNEL); + if (!img_data->dev_blks) + return -ENOMEM; + + for (i = 0; i < img_data->nr_blk; i++) { + blk = &img_data->dev_blks[i]; + offset = fw_parse_block_data_kernel( + tas_fmw, blk, fmw, offset); + if (offset < 0) { + kfree(img_data->dev_blks); + return -EINVAL; + } + } + + return offset; +} + +/* Data of DSP program parser function. */ +static int fw_parse_program_data_kernel( + struct tasdevice_priv *tas_priv, struct tasdevice_fw *tas_fmw, + const struct firmware *fmw, int offset) +{ + struct tasdevice_prog *program; + unsigned int i; + + for (i = 0; i < tas_fmw->nr_programs; i++) { + program = &tas_fmw->programs[i]; + if (offset + 72 > fmw->size) { + dev_err(tas_priv->dev, "%s: mpName error\n", __func__); + return -EINVAL; + } + /* skip 72 unused byts */ + offset += 72; + + offset = fw_parse_data_kernel(tas_fmw, &program->dev_data, + fmw, offset); + if (offset < 0) + break; + } + + return offset; +} + +/* Data of DSP configurations parser function. */ +static int fw_parse_configuration_data_kernel(struct tasdevice_priv *tas_priv, + struct tasdevice_fw *tas_fmw, const struct firmware *fmw, int offset) +{ + const unsigned char *data = fmw->data; + struct tasdevice_config *config; + unsigned int i; + + for (i = 0; i < tas_fmw->nr_configurations; i++) { + config = &tas_fmw->configs[i]; + if (offset + 80 > fmw->size) { + dev_err(tas_priv->dev, "%s: mpName error\n", __func__); + return -EINVAL; + } + memcpy(config->name, &data[offset], 64); + /* skip extra 16 bytes */ + offset += 80; + + offset = fw_parse_data_kernel(tas_fmw, &config->dev_data, + fmw, offset); + if (offset < 0) + break; + } + + return offset; +} + +/* DSP firmware file header parser function for early PPC3 firmware binary. */ +static int fw_parse_variable_header_kernel(struct tasdevice_priv *tas_priv, + const struct firmware *fmw, int offset) +{ + struct tasdevice_fw *tas_fmw = tas_priv->fmw; + struct tasdevice_dspfw_hdr *fw_hdr = &tas_fmw->fw_hdr; + struct tasdevice_config *config; + struct tasdevice_prog *program; + const unsigned char *buf = fmw->data; + unsigned short max_confs; + unsigned int i; + + if (offset + 12 + 4 * TASDEVICE_MAXPROGRAM_NUM_KERNEL > fmw->size) { + dev_err(tas_priv->dev, "%s: File Size error\n", __func__); + return -EINVAL; + } + fw_hdr->device_family = get_unaligned_be16(&buf[offset]); + if (fw_hdr->device_family != 0) { + dev_err(tas_priv->dev, "%s:not TAS device\n", __func__); + return -EINVAL; + } + offset += 2; + fw_hdr->device = get_unaligned_be16(&buf[offset]); + if (fw_hdr->device >= TASDEVICE_DSP_TAS_MAX_DEVICE || + fw_hdr->device == 6) { + dev_err(tas_priv->dev, "Unsupported dev %d\n", fw_hdr->device); + return -EINVAL; + } + offset += 2; + + tas_fmw->nr_programs = get_unaligned_be32(&buf[offset]); + offset += 4; + + if (tas_fmw->nr_programs == 0 || + tas_fmw->nr_programs > TASDEVICE_MAXPROGRAM_NUM_KERNEL) { + dev_err(tas_priv->dev, "mnPrograms is invalid\n"); + return -EINVAL; + } + + tas_fmw->programs = kcalloc(tas_fmw->nr_programs, + sizeof(*tas_fmw->programs), GFP_KERNEL); + if (!tas_fmw->programs) + return -ENOMEM; + + for (i = 0; i < tas_fmw->nr_programs; i++) { + program = &tas_fmw->programs[i]; + program->prog_size = get_unaligned_be32(&buf[offset]); + offset += 4; + } + + /* Skip the unused prog_size */ + offset += 4 * (TASDEVICE_MAXPROGRAM_NUM_KERNEL - tas_fmw->nr_programs); + + tas_fmw->nr_configurations = get_unaligned_be32(&buf[offset]); + offset += 4; + + /* + * The max number of config in firmware greater than 4 pieces of + * tas2781s is different from the one lower than 4 pieces of + * tas2781s. + */ + max_confs = TASDEVICE_MAXCONFIG_NUM_KERNEL; + if (tas_fmw->nr_configurations == 0 || + tas_fmw->nr_configurations > max_confs) { + dev_err(tas_priv->dev, "%s: Conf is invalid\n", __func__); + kfree(tas_fmw->programs); + return -EINVAL; + } + + if (offset + 4 * max_confs > fmw->size) { + dev_err(tas_priv->dev, "%s: mpConfigurations err\n", __func__); + kfree(tas_fmw->programs); + return -EINVAL; + } + + tas_fmw->configs = kcalloc(tas_fmw->nr_configurations, + sizeof(*tas_fmw->configs), GFP_KERNEL); + if (!tas_fmw->configs) { + kfree(tas_fmw->programs); + return -ENOMEM; + } + + for (i = 0; i < tas_fmw->nr_programs; i++) { + config = &tas_fmw->configs[i]; + config->cfg_size = get_unaligned_be32(&buf[offset]); + offset += 4; + } + + /* Skip the unused configs */ + offset += 4 * (max_confs - tas_fmw->nr_programs); + + return offset; +} + +/* + * In sub-block data, have three type sub-block: + * 1. Single byte write. + * 2. Multi-byte write. + * 3. Delay. + * 4. Bits update. + * This function perform single byte write to device. + */ +static int tasdevice_single_byte_wr(void *context, int dev_idx, + unsigned char *data, int sublocksize) +{ + struct tasdevice_priv *tas_priv = context; + unsigned short len = get_unaligned_be16(&data[2]); + int i, subblk_offset, rc; + + subblk_offset = 4; + if (subblk_offset + 4 * len > sublocksize) { + dev_err(tas_priv->dev, "process_block: Out of boundary\n"); + return 0; + } + + for (i = 0; i < len; i++) { + if (dev_idx == (tas_priv->index + 1) || dev_idx == 0) { + rc = tasdevice_spi_dev_write(tas_priv, + TASDEVICE_REG(data[subblk_offset], + data[subblk_offset + 1], + data[subblk_offset + 2]), + data[subblk_offset + 3]); + if (rc < 0) { + dev_err(tas_priv->dev, + "process_block: single write error\n"); + subblk_offset |= OFFSET_ERROR_BIT; + } + } + subblk_offset += 4; + } + + return subblk_offset; +} + +/* + * In sub-block data, have three type sub-block: + * 1. Single byte write. + * 2. Multi-byte write. + * 3. Delay. + * 4. Bits update. + * This function perform multi-write to device. + */ +static int tasdevice_burst_wr(void *context, int dev_idx, unsigned char *data, + int sublocksize) +{ + struct tasdevice_priv *tas_priv = context; + unsigned short len = get_unaligned_be16(&data[2]); + int subblk_offset, rc; + + subblk_offset = 4; + if (subblk_offset + 4 + len > sublocksize) { + dev_err(tas_priv->dev, "%s: BST Out of boundary\n", __func__); + subblk_offset |= OFFSET_ERROR_BIT; + } + if (len % 4) { + dev_err(tas_priv->dev, "%s:Bst-len(%u)not div by 4\n", + __func__, len); + subblk_offset |= OFFSET_ERROR_BIT; + } + + if (dev_idx == (tas_priv->index + 1) || dev_idx == 0) { + rc = tasdevice_spi_dev_bulk_write(tas_priv, + TASDEVICE_REG(data[subblk_offset], + data[subblk_offset + 1], + data[subblk_offset + 2]), + &data[subblk_offset + 4], len); + if (rc < 0) { + dev_err(tas_priv->dev, "%s: bulk_write error = %d\n", + __func__, rc); + subblk_offset |= OFFSET_ERROR_BIT; + } + } + subblk_offset += (len + 4); + + return subblk_offset; +} + +/* Just delay for ms.*/ +static int tasdevice_delay(void *context, int dev_idx, unsigned char *data, + int sublocksize) +{ + struct tasdevice_priv *tas_priv = context; + unsigned int sleep_time, subblk_offset = 2; + + if (subblk_offset + 2 > sublocksize) { + dev_err(tas_priv->dev, "%s: delay Out of boundary\n", + __func__); + subblk_offset |= OFFSET_ERROR_BIT; + } + if (dev_idx == (tas_priv->index + 1) || dev_idx == 0) { + sleep_time = get_unaligned_be16(&data[2]) * 1000; + fsleep(sleep_time); + } + subblk_offset += 2; + + return subblk_offset; +} + +/* + * In sub-block data, have three type sub-block: + * 1. Single byte write. + * 2. Multi-byte write. + * 3. Delay. + * 4. Bits update. + * This function perform bits update. + */ +static int tasdevice_field_wr(void *context, int dev_idx, unsigned char *data, + int sublocksize) +{ + struct tasdevice_priv *tas_priv = context; + int rc, subblk_offset = 2; + + if (subblk_offset + 6 > sublocksize) { + dev_err(tas_priv->dev, "%s: bit write Out of boundary\n", + __func__); + subblk_offset |= OFFSET_ERROR_BIT; + } + if (dev_idx == (tas_priv->index + 1) || dev_idx == 0) { + rc = tasdevice_spi_dev_update_bits(tas_priv, + TASDEVICE_REG(data[subblk_offset + 2], + data[subblk_offset + 3], + data[subblk_offset + 4]), + data[subblk_offset + 1], + data[subblk_offset + 5]); + if (rc < 0) { + dev_err(tas_priv->dev, "%s: update_bits error = %d\n", + __func__, rc); + subblk_offset |= OFFSET_ERROR_BIT; + } + } + subblk_offset += 6; + + return subblk_offset; +} + +/* Data block process function. */ +static int tasdevice_process_block(void *context, unsigned char *data, + unsigned char dev_idx, int sublocksize) +{ + struct tasdevice_priv *tas_priv = context; + int blktyp = dev_idx & 0xC0, subblk_offset; + unsigned char subblk_typ = data[1]; + + switch (subblk_typ) { + case TASDEVICE_CMD_SING_W: + subblk_offset = tasdevice_single_byte_wr(tas_priv, + dev_idx & 0x4f, data, sublocksize); + break; + case TASDEVICE_CMD_BURST: + subblk_offset = tasdevice_burst_wr(tas_priv, + dev_idx & 0x4f, data, sublocksize); + break; + case TASDEVICE_CMD_DELAY: + subblk_offset = tasdevice_delay(tas_priv, + dev_idx & 0x4f, data, sublocksize); + break; + case TASDEVICE_CMD_FIELD_W: + subblk_offset = tasdevice_field_wr(tas_priv, + dev_idx & 0x4f, data, sublocksize); + break; + default: + subblk_offset = 2; + break; + } + if (((subblk_offset & OFFSET_ERROR_BIT) != 0) && blktyp != 0) { + if (blktyp == 0x80) { + tas_priv->cur_prog = -1; + tas_priv->cur_conf = -1; + } else + tas_priv->cur_conf = -1; + } + subblk_offset &= ~OFFSET_ERROR_BIT; + + return subblk_offset; +} + +/* + * Device support different configurations for different scene, + * this function was used for choose different config. + */ +void tasdevice_spi_select_cfg_blk(void *pContext, int conf_no, + unsigned char block_type) +{ + struct tasdevice_priv *tas_priv = pContext; + struct tasdevice_rca *rca = &tas_priv->rcabin; + struct tasdevice_config_info **cfg_info = rca->cfg_info; + struct tasdev_blk_data **blk_data; + unsigned int j, k; + + if (conf_no >= rca->ncfgs || conf_no < 0 || !cfg_info) { + dev_err(tas_priv->dev, "conf_no should be not more than %u\n", + rca->ncfgs); + return; + } + blk_data = cfg_info[conf_no]->blk_data; + + for (j = 0; j < cfg_info[conf_no]->real_nblocks; j++) { + unsigned int length = 0, rc = 0; + + if (block_type > 5 || block_type < 2) { + dev_err(tas_priv->dev, + "block_type should be in range from 2 to 5\n"); + break; + } + if (block_type != blk_data[j]->block_type) + continue; + + for (k = 0; k < blk_data[j]->n_subblks; k++) { + tas_priv->is_loading = true; + + rc = tasdevice_process_block(tas_priv, + blk_data[j]->regdata + length, + blk_data[j]->dev_idx, + blk_data[j]->block_size - length); + length += rc; + if (blk_data[j]->block_size < length) { + dev_err(tas_priv->dev, + "%s: %u %u out of boundary\n", + __func__, length, + blk_data[j]->block_size); + break; + } + } + if (length != blk_data[j]->block_size) + dev_err(tas_priv->dev, "%s: %u %u size is not same\n", + __func__, length, blk_data[j]->block_size); + } +} + +/* Block process function. */ +static int tasdevice_load_block_kernel( + struct tasdevice_priv *tasdevice, struct tasdev_blk *block) +{ + const unsigned int blk_size = block->blk_size; + unsigned char *data = block->data; + unsigned int i, length; + + for (i = 0, length = 0; i < block->nr_subblocks; i++) { + int rc = tasdevice_process_block(tasdevice, data + length, + block->dev_idx, blk_size - length); + if (rc < 0) { + dev_err(tasdevice->dev, + "%s: %u %u sublock write error\n", + __func__, length, blk_size); + return rc; + } + length += rc; + if (blk_size < length) { + dev_err(tasdevice->dev, "%s: %u %u out of boundary\n", + __func__, length, blk_size); + rc = -ENOMEM; + return rc; + } + } + + return 0; +} + +/* DSP firmware file header parser function. */ +static int fw_parse_variable_hdr(struct tasdevice_priv *tas_priv, + struct tasdevice_dspfw_hdr *fw_hdr, + const struct firmware *fmw, int offset) +{ + const unsigned char *buf = fmw->data; + int len = strlen((char *)&buf[offset]); + + len++; + + if (offset + len + 8 > fmw->size) { + dev_err(tas_priv->dev, "%s: File Size error\n", __func__); + return -EINVAL; + } + + offset += len; + + fw_hdr->device_family = get_unaligned_be32(&buf[offset]); + if (fw_hdr->device_family != 0) { + dev_err(tas_priv->dev, "%s: not TAS device\n", __func__); + return -EINVAL; + } + offset += 4; + + fw_hdr->device = get_unaligned_be32(&buf[offset]); + if (fw_hdr->device >= TASDEVICE_DSP_TAS_MAX_DEVICE || + fw_hdr->device == 6) { + dev_err(tas_priv->dev, "Unsupported dev %d\n", fw_hdr->device); + return -EINVAL; + } + offset += 4; + fw_hdr->ndev = 1; + + return offset; +} + +/* DSP firmware file header parser function for size variabled header. */ +static int fw_parse_variable_header_git(struct tasdevice_priv + *tas_priv, const struct firmware *fmw, int offset) +{ + struct tasdevice_fw *tas_fmw = tas_priv->fmw; + struct tasdevice_dspfw_hdr *fw_hdr = &tas_fmw->fw_hdr; + + offset = fw_parse_variable_hdr(tas_priv, fw_hdr, fmw, offset); + + return offset; +} + +/* DSP firmware file block parser function. */ +static int fw_parse_block_data(struct tasdevice_fw *tas_fmw, + struct tasdev_blk *block, const struct firmware *fmw, int offset) +{ + unsigned char *data = (unsigned char *)fmw->data; + int n; + + if (offset + 8 > fmw->size) { + dev_err(tas_fmw->dev, "%s: Type error\n", __func__); + return -EINVAL; + } + block->type = get_unaligned_be32(&data[offset]); + offset += 4; + + if (tas_fmw->fw_hdr.fixed_hdr.drv_ver >= PPC_DRIVER_CRCCHK) { + if (offset + 8 > fmw->size) { + dev_err(tas_fmw->dev, "PChkSumPresent error\n"); + return -EINVAL; + } + block->is_pchksum_present = data[offset]; + offset++; + + block->pchksum = data[offset]; + offset++; + + block->is_ychksum_present = data[offset]; + offset++; + + block->ychksum = data[offset]; + offset++; + } else { + block->is_pchksum_present = 0; + block->is_ychksum_present = 0; + } + + block->nr_cmds = get_unaligned_be32(&data[offset]); + offset += 4; + + n = block->nr_cmds * 4; + if (offset + n > fmw->size) { + dev_err(tas_fmw->dev, + "%s: File Size(%lu) error offset = %d n = %d\n", + __func__, (unsigned long)fmw->size, offset, n); + return -EINVAL; + } + /* instead of kzalloc+memcpy */ + block->data = kmemdup(&data[offset], n, GFP_KERNEL); + if (!block->data) + return -ENOMEM; + + offset += n; + + return offset; +} + +/* + * When parsing error occurs, all the memory resource will be released + * in the end of tasdevice_rca_ready. + */ +static int fw_parse_data(struct tasdevice_fw *tas_fmw, + struct tasdevice_data *img_data, const struct firmware *fmw, + int offset) +{ + const unsigned char *data = (unsigned char *)fmw->data; + struct tasdev_blk *blk; + unsigned int i, n; + + if (offset + 64 > fmw->size) { + dev_err(tas_fmw->dev, "%s: Name error\n", __func__); + return -EINVAL; + } + memcpy(img_data->name, &data[offset], 64); + offset += 64; + + n = strlen((char *)&data[offset]); + n++; + if (offset + n + 2 > fmw->size) { + dev_err(tas_fmw->dev, "%s: Description error\n", __func__); + return -EINVAL; + } + offset += n; + img_data->nr_blk = get_unaligned_be16(&data[offset]); + offset += 2; + + img_data->dev_blks = kcalloc(img_data->nr_blk, + sizeof(*img_data->dev_blks), GFP_KERNEL); + if (!img_data->dev_blks) + return -ENOMEM; + + for (i = 0; i < img_data->nr_blk; i++) { + blk = &img_data->dev_blks[i]; + offset = fw_parse_block_data(tas_fmw, blk, fmw, offset); + if (offset < 0) + return -EINVAL; + } + + return offset; +} + +/* + * When parsing error occurs, all the memory resource will be released + * in the end of tasdevice_rca_ready. + */ +static int fw_parse_program_data(struct tasdevice_priv *tas_priv, + struct tasdevice_fw *tas_fmw, const struct firmware *fmw, int offset) +{ + unsigned char *buf = (unsigned char *)fmw->data; + struct tasdevice_prog *program; + int i; + + if (offset + 2 > fmw->size) { + dev_err(tas_priv->dev, "%s: File Size error\n", __func__); + return -EINVAL; + } + tas_fmw->nr_programs = get_unaligned_be16(&buf[offset]); + offset += 2; + + if (tas_fmw->nr_programs == 0) { + /* Not error in calibration Data file, return directly */ + dev_dbg(tas_priv->dev, "%s: No Programs data, maybe calbin\n", + __func__); + return offset; + } + + tas_fmw->programs = + kcalloc(tas_fmw->nr_programs, sizeof(*tas_fmw->programs), + GFP_KERNEL); + if (!tas_fmw->programs) + return -ENOMEM; + + for (i = 0; i < tas_fmw->nr_programs; i++) { + int n = 0; + + program = &tas_fmw->programs[i]; + if (offset + 64 > fmw->size) { + dev_err(tas_priv->dev, "%s: mpName error\n", __func__); + return -EINVAL; + } + offset += 64; + + n = strlen((char *)&buf[offset]); + /* skip '\0' and 5 unused bytes */ + n += 6; + if (offset + n > fmw->size) { + dev_err(tas_priv->dev, "Description err\n"); + return -EINVAL; + } + + offset += n; + + offset = fw_parse_data(tas_fmw, &program->dev_data, fmw, + offset); + if (offset < 0) + return offset; + } + + return offset; +} + +/* + * When parsing error occurs, all the memory resource will be released + * in the end of tasdevice_rca_ready. + */ +static int fw_parse_configuration_data(struct tasdevice_priv *tas_priv, + struct tasdevice_fw *tas_fmw, const struct firmware *fmw, int offset) +{ + unsigned char *data = (unsigned char *)fmw->data; + struct tasdevice_config *config; + unsigned int i, n; + + if (offset + 2 > fmw->size) { + dev_err(tas_priv->dev, "%s: File Size error\n", __func__); + return -EINVAL; + } + tas_fmw->nr_configurations = get_unaligned_be16(&data[offset]); + offset += 2; + + if (tas_fmw->nr_configurations == 0) { + dev_err(tas_priv->dev, "%s: Conf is zero\n", __func__); + /* Not error for calibration Data file, return directly */ + return offset; + } + tas_fmw->configs = kcalloc(tas_fmw->nr_configurations, + sizeof(*tas_fmw->configs), GFP_KERNEL); + if (!tas_fmw->configs) + return -ENOMEM; + for (i = 0; i < tas_fmw->nr_configurations; i++) { + config = &tas_fmw->configs[i]; + if (offset + 64 > fmw->size) { + dev_err(tas_priv->dev, "File Size err\n"); + return -EINVAL; + } + memcpy(config->name, &data[offset], 64); + offset += 64; + + n = strlen((char *)&data[offset]); + n += 15; + if (offset + n > fmw->size) { + dev_err(tas_priv->dev, "Description err\n"); + return -EINVAL; + } + offset += n; + offset = fw_parse_data(tas_fmw, &config->dev_data, + fmw, offset); + if (offset < 0) + break; + } + + return offset; +} + +/* yram5 page check. */ +static bool check_inpage_yram_rg(struct tas_crc *cd, + unsigned char reg, unsigned char len) +{ + bool in = false; + + if (reg <= TAS2781_YRAM5_END_REG && + reg >= TAS2781_YRAM5_START_REG) { + if (reg + len > TAS2781_YRAM5_END_REG) + cd->len = TAS2781_YRAM5_END_REG - reg + 1; + else + cd->len = len; + cd->offset = reg; + in = true; + } else if (reg < TAS2781_YRAM5_START_REG) { + if (reg + len > TAS2781_YRAM5_START_REG) { + cd->offset = TAS2781_YRAM5_START_REG; + cd->len = len - TAS2781_YRAM5_START_REG + reg; + in = true; + } + } + + return in; +} + +/* DSP firmware yram block check. */ +static bool check_inpage_yram_bk1(struct tas_crc *cd, + unsigned char page, unsigned char reg, unsigned char len) +{ + bool in = false; + + if (page == TAS2781_YRAM1_PAGE) { + if (reg >= TAS2781_YRAM1_START_REG) { + cd->offset = reg; + cd->len = len; + in = true; + } else if (reg + len > TAS2781_YRAM1_START_REG) { + cd->offset = TAS2781_YRAM1_START_REG; + cd->len = len - TAS2781_YRAM1_START_REG + reg; + in = true; + } + } else if (page == TAS2781_YRAM3_PAGE) { + in = check_inpage_yram_rg(cd, reg, len); + } + + return in; +} + +/* + * Return Code: + * true -- the registers are in the inpage yram + * false -- the registers are NOT in the inpage yram + */ +static bool check_inpage_yram(struct tas_crc *cd, unsigned char book, + unsigned char page, unsigned char reg, unsigned char len) +{ + bool in = false; + + if (book == TAS2781_YRAM_BOOK1) + in = check_inpage_yram_bk1(cd, page, reg, len); + else if (book == TAS2781_YRAM_BOOK2 && page == TAS2781_YRAM5_PAGE) + in = check_inpage_yram_rg(cd, reg, len); + + return in; +} + +/* yram4 page check. */ +static bool check_inblock_yram_bk(struct tas_crc *cd, + unsigned char page, unsigned char reg, unsigned char len) +{ + bool in = false; + + if ((page >= TAS2781_YRAM4_START_PAGE && + page <= TAS2781_YRAM4_END_PAGE) || + (page >= TAS2781_YRAM2_START_PAGE && + page <= TAS2781_YRAM2_END_PAGE)) { + if (reg <= TAS2781_YRAM2_END_REG && + reg >= TAS2781_YRAM2_START_REG) { + cd->offset = reg; + cd->len = len; + in = true; + } else if (reg < TAS2781_YRAM2_START_REG) { + if (reg + len - 1 >= TAS2781_YRAM2_START_REG) { + cd->offset = TAS2781_YRAM2_START_REG; + cd->len = reg + len - TAS2781_YRAM2_START_REG; + in = true; + } + } + } + + return in; +} + +/* + * Return Code: + * true -- the registers are in the inblock yram + * false -- the registers are NOT in the inblock yram + */ +static bool check_inblock_yram(struct tas_crc *cd, unsigned char book, + unsigned char page, unsigned char reg, unsigned char len) +{ + bool in = false; + + if (book == TAS2781_YRAM_BOOK1 || book == TAS2781_YRAM_BOOK2) + in = check_inblock_yram_bk(cd, page, reg, len); + + return in; +} + +/* yram page check. */ +static bool check_yram(struct tas_crc *cd, unsigned char book, + unsigned char page, unsigned char reg, unsigned char len) +{ + bool in; + + in = check_inpage_yram(cd, book, page, reg, len); + if (!in) + in = check_inblock_yram(cd, book, page, reg, len); + + return in; +} + +/* Checksum for data block. */ +static int tasdev_multibytes_chksum(struct tasdevice_priv *tasdevice, + unsigned char book, unsigned char page, + unsigned char reg, unsigned int len) +{ + struct tas_crc crc_data; + unsigned char crc_chksum = 0; + unsigned char nBuf1[128]; + int ret = 0, i; + bool in; + + if ((reg + len - 1) > 127) { + ret = -EINVAL; + dev_err(tasdevice->dev, "firmware error\n"); + goto end; + } + + if ((book == TASDEVICE_BOOK_ID(TAS2781_SA_COEFF_SWAP_REG)) && + (page == TASDEVICE_PAGE_ID(TAS2781_SA_COEFF_SWAP_REG)) && + (reg == TASDEVICE_REG_ID(TAS2781_SA_COEFF_SWAP_REG)) && + (len == 4)) { + /* DSP swap command, pass */ + ret = 0; + goto end; + } + + in = check_yram(&crc_data, book, page, reg, len); + if (!in) + goto end; + + if (len == 1) { + dev_err(tasdevice->dev, "firmware error\n"); + ret = -EINVAL; + goto end; + } + + ret = tasdevice_spi_dev_bulk_read(tasdevice, + TASDEVICE_REG(book, page, crc_data.offset), + nBuf1, crc_data.len); + if (ret < 0) + goto end; + + for (i = 0; i < crc_data.len; i++) { + if ((book == TASDEVICE_BOOK_ID(TAS2781_SA_COEFF_SWAP_REG)) && + (page == TASDEVICE_PAGE_ID(TAS2781_SA_COEFF_SWAP_REG)) && + ((i + crc_data.offset) >= + TASDEVICE_REG_ID(TAS2781_SA_COEFF_SWAP_REG)) && + ((i + crc_data.offset) <= + (TASDEVICE_REG_ID(TAS2781_SA_COEFF_SWAP_REG) + 4))) + /* DSP swap command, bypass */ + continue; + else + crc_chksum += crc8(tasdevice->crc8_lkp_tbl, &nBuf1[i], + 1, 0); + } + + ret = crc_chksum; + +end: + return ret; +} + +/* Checksum for single register. */ +static int do_singlereg_checksum(struct tasdevice_priv *tasdevice, + unsigned char book, unsigned char page, + unsigned char reg, unsigned char val) +{ + struct tas_crc crc_data; + unsigned int nData1; + int ret = 0; + bool in; + + /* DSP swap command, pass */ + if ((book == TASDEVICE_BOOK_ID(TAS2781_SA_COEFF_SWAP_REG)) && + (page == TASDEVICE_PAGE_ID(TAS2781_SA_COEFF_SWAP_REG)) && + (reg >= TASDEVICE_REG_ID(TAS2781_SA_COEFF_SWAP_REG)) && + (reg <= (TASDEVICE_REG_ID(TAS2781_SA_COEFF_SWAP_REG) + 4))) + return 0; + + in = check_yram(&crc_data, book, page, reg, 1); + if (!in) + return 0; + ret = tasdevice_spi_dev_read(tasdevice, + TASDEVICE_REG(book, page, reg), &nData1); + if (ret < 0) + return ret; + + if (nData1 != val) { + dev_err(tasdevice->dev, + "B[0x%x]P[0x%x]R[0x%x] W[0x%x], R[0x%x]\n", + book, page, reg, val, nData1); + tasdevice->err_code |= ERROR_YRAM_CRCCHK; + return -EAGAIN; + } + + ret = crc8(tasdevice->crc8_lkp_tbl, &val, 1, 0); + + return ret; +} + +/* Block type check. */ +static void set_err_prg_cfg(unsigned int type, struct tasdevice_priv *p) +{ + if ((type == MAIN_ALL_DEVICES) || (type == MAIN_DEVICE_A) || + (type == MAIN_DEVICE_B) || (type == MAIN_DEVICE_C) || + (type == MAIN_DEVICE_D)) + p->cur_prog = -1; + else + p->cur_conf = -1; +} + +/* Checksum for data bytes. */ +static int tasdev_bytes_chksum(struct tasdevice_priv *tas_priv, + struct tasdev_blk *block, unsigned char book, + unsigned char page, unsigned char reg, unsigned int len, + unsigned char val, unsigned char *crc_chksum) +{ + int ret; + + if (len > 1) + ret = tasdev_multibytes_chksum(tas_priv, book, page, reg, + len); + else + ret = do_singlereg_checksum(tas_priv, book, page, reg, val); + + if (ret > 0) { + *crc_chksum += ret; + goto end; + } + + if (ret != -EAGAIN) + goto end; + + block->nr_retry--; + if (block->nr_retry > 0) + goto end; + + set_err_prg_cfg(block->type, tas_priv); + +end: + return ret; +} + +/* Multi-data byte write. */ +static int tasdev_multibytes_wr(struct tasdevice_priv *tas_priv, + struct tasdev_blk *block, unsigned char book, + unsigned char page, unsigned char reg, unsigned char *data, + unsigned int len, unsigned int *nr_cmds, + unsigned char *crc_chksum) +{ + int ret; + + if (len > 1) { + ret = tasdevice_spi_dev_bulk_write(tas_priv, + TASDEVICE_REG(book, page, reg), data + 3, len); + if (ret < 0) + return ret; + if (block->is_ychksum_present) + ret = tasdev_bytes_chksum(tas_priv, block, + book, page, reg, len, 0, crc_chksum); + } else { + ret = tasdevice_spi_dev_write(tas_priv, + TASDEVICE_REG(book, page, reg), data[3]); + if (ret < 0) + return ret; + if (block->is_ychksum_present) + ret = tasdev_bytes_chksum(tas_priv, block, book, + page, reg, 1, data[3], crc_chksum); + } + + if (!block->is_ychksum_present || ret >= 0) { + *nr_cmds += 1; + if (len >= 2) + *nr_cmds += ((len - 2) / 4) + 1; + } + + return ret; +} + +/* Checksum for block. */ +static int tasdev_block_chksum(struct tasdevice_priv *tas_priv, + struct tasdev_blk *block) +{ + unsigned int nr_value; + int ret; + + ret = tasdevice_spi_dev_read(tas_priv, TASDEVICE_CHECKSUM, &nr_value); + if (ret < 0) { + dev_err(tas_priv->dev, "%s: read error %d.\n", __func__, ret); + set_err_prg_cfg(block->type, tas_priv); + return ret; + } + + if ((nr_value & 0xff) != block->pchksum) { + dev_err(tas_priv->dev, "%s: PChkSum err %d ", __func__, ret); + dev_err(tas_priv->dev, "PChkSum = 0x%x, Reg = 0x%x\n", + block->pchksum, (nr_value & 0xff)); + tas_priv->err_code |= ERROR_PRAM_CRCCHK; + ret = -EAGAIN; + block->nr_retry--; + + if (block->nr_retry <= 0) + set_err_prg_cfg(block->type, tas_priv); + } else { + tas_priv->err_code &= ~ERROR_PRAM_CRCCHK; + } + + return ret; +} + +/* Firmware block load function. */ +static int tasdev_load_blk(struct tasdevice_priv *tas_priv, + struct tasdev_blk *block) +{ + unsigned int sleep_time, len, nr_cmds; + unsigned char offset, book, page, val; + unsigned char *data = block->data; + unsigned char crc_chksum = 0; + int ret = 0; + + while (block->nr_retry > 0) { + if (block->is_pchksum_present) { + ret = tasdevice_spi_dev_write(tas_priv, + TASDEVICE_CHECKSUM, 0); + if (ret < 0) + break; + } + + if (block->is_ychksum_present) + crc_chksum = 0; + + nr_cmds = 0; + + while (nr_cmds < block->nr_cmds) { + data = block->data + nr_cmds * 4; + + book = data[0]; + page = data[1]; + offset = data[2]; + val = data[3]; + + nr_cmds++; + /* Single byte write */ + if (offset <= 0x7F) { + ret = tasdevice_spi_dev_write(tas_priv, + TASDEVICE_REG(book, page, offset), + val); + if (ret < 0) + break; + if (block->is_ychksum_present) { + ret = tasdev_bytes_chksum(tas_priv, + block, book, page, offset, + 1, val, &crc_chksum); + if (ret < 0) + break; + } + continue; + } + /* sleep command */ + if (offset == 0x81) { + /* book -- data[0] page -- data[1] */ + sleep_time = ((book << 8) + page)*1000; + fsleep(sleep_time); + continue; + } + /* Multiple bytes write */ + if (offset == 0x85) { + data += 4; + len = (book << 8) + page; + book = data[0]; + page = data[1]; + offset = data[2]; + ret = tasdev_multibytes_wr(tas_priv, + block, book, page, offset, data, + len, &nr_cmds, &crc_chksum); + if (ret < 0) + break; + } + } + if (ret == -EAGAIN) { + if (block->nr_retry > 0) + continue; + } else if (ret < 0) { + /* err in current device, skip it */ + break; + } + + if (block->is_pchksum_present) { + ret = tasdev_block_chksum(tas_priv, block); + if (ret == -EAGAIN) { + if (block->nr_retry > 0) + continue; + } else if (ret < 0) { + /* err in current device, skip it */ + break; + } + } + + if (block->is_ychksum_present) { + /* TBD, open it when FW ready */ + dev_err(tas_priv->dev, + "Blk YChkSum: FW = 0x%x, YCRC = 0x%x\n", + block->ychksum, crc_chksum); + + tas_priv->err_code &= + ~ERROR_YRAM_CRCCHK; + ret = 0; + } + /* skip current blk */ + break; + } + + return ret; +} + +/* Firmware block load function. */ +static int tasdevice_load_block(struct tasdevice_priv *tas_priv, + struct tasdev_blk *block) +{ + int ret = 0; + + block->nr_retry = 6; + if (tas_priv->is_loading == false) + return 0; + ret = tasdev_load_blk(tas_priv, block); + if (ret < 0) + dev_err(tas_priv->dev, "Blk (%d) load error\n", block->type); + + return ret; +} + +/* + * Select firmware binary parser & load callback functions by ppc3 version + * and firmware binary version. + */ +static int dspfw_default_callback(struct tasdevice_priv *tas_priv, + unsigned int drv_ver, unsigned int ppcver) +{ + int rc = 0; + + if (drv_ver == 0x100) { + if (ppcver >= PPC3_VERSION) { + tas_priv->fw_parse_variable_header = + fw_parse_variable_header_kernel; + tas_priv->fw_parse_program_data = + fw_parse_program_data_kernel; + tas_priv->fw_parse_configuration_data = + fw_parse_configuration_data_kernel; + tas_priv->tasdevice_load_block = + tasdevice_load_block_kernel; + } else if (ppcver == 0x00) { + tas_priv->fw_parse_variable_header = + fw_parse_variable_header_git; + tas_priv->fw_parse_program_data = + fw_parse_program_data; + tas_priv->fw_parse_configuration_data = + fw_parse_configuration_data; + tas_priv->tasdevice_load_block = + tasdevice_load_block; + } else { + dev_err(tas_priv->dev, + "Wrong PPCVer :0x%08x\n", ppcver); + rc = -EINVAL; + } + } else { + dev_err(tas_priv->dev, "Wrong DrvVer : 0x%02x\n", drv_ver); + rc = -EINVAL; + } + + return rc; +} + +/* DSP firmware binary file header parser function. */ +static int fw_parse_header(struct tasdevice_priv *tas_priv, + struct tasdevice_fw *tas_fmw, const struct firmware *fmw, int offset) +{ + struct tasdevice_dspfw_hdr *fw_hdr = &tas_fmw->fw_hdr; + struct tasdevice_fw_fixed_hdr *fw_fixed_hdr = &fw_hdr->fixed_hdr; + static const unsigned char magic_number[] = {0x35, 0x35, 0x35, 0x32, }; + const unsigned char *buf = (unsigned char *)fmw->data; + + if (offset + 92 > fmw->size) { + dev_err(tas_priv->dev, "%s: File Size error\n", __func__); + offset = -EINVAL; + goto out; + } + if (memcmp(&buf[offset], magic_number, 4)) { + dev_err(tas_priv->dev, "%s: Magic num NOT match\n", __func__); + offset = -EINVAL; + goto out; + } + offset += 4; + + /* + * Convert data[offset], data[offset + 1], data[offset + 2] and + * data[offset + 3] into host + */ + fw_fixed_hdr->fwsize = get_unaligned_be32(&buf[offset]); + offset += 4; + if (fw_fixed_hdr->fwsize != fmw->size) { + dev_err(tas_priv->dev, "File size not match, %lu %u", + (unsigned long)fmw->size, fw_fixed_hdr->fwsize); + offset = -EINVAL; + goto out; + } + offset += 4; + fw_fixed_hdr->ppcver = get_unaligned_be32(&buf[offset]); + offset += 8; + fw_fixed_hdr->drv_ver = get_unaligned_be32(&buf[offset]); + offset += 72; + +out: + return offset; +} + +/* DSP firmware binary file parser function. */ +static int tasdevice_dspfw_ready(const struct firmware *fmw, void *context) +{ + struct tasdevice_priv *tas_priv = context; + struct tasdevice_fw_fixed_hdr *fw_fixed_hdr; + struct tasdevice_fw *tas_fmw; + int offset = 0, ret = 0; + + if (!fmw || !fmw->data) { + dev_err(tas_priv->dev, "%s: Failed to read firmware %s\n", + __func__, tas_priv->coef_binaryname); + return -EINVAL; + } + + tas_priv->fmw = kzalloc(sizeof(*tas_priv->fmw), GFP_KERNEL); + if (!tas_priv->fmw) + return -ENOMEM; + tas_fmw = tas_priv->fmw; + tas_fmw->dev = tas_priv->dev; + offset = fw_parse_header(tas_priv, tas_fmw, fmw, offset); + + if (offset == -EINVAL) + return -EINVAL; + + fw_fixed_hdr = &tas_fmw->fw_hdr.fixed_hdr; + /* Support different versions of firmware */ + switch (fw_fixed_hdr->drv_ver) { + case 0x301: + case 0x302: + case 0x502: + case 0x503: + tas_priv->fw_parse_variable_header = + fw_parse_variable_header_kernel; + tas_priv->fw_parse_program_data = + fw_parse_program_data_kernel; + tas_priv->fw_parse_configuration_data = + fw_parse_configuration_data_kernel; + tas_priv->tasdevice_load_block = + tasdevice_load_block_kernel; + break; + case 0x202: + case 0x400: + tas_priv->fw_parse_variable_header = + fw_parse_variable_header_git; + tas_priv->fw_parse_program_data = + fw_parse_program_data; + tas_priv->fw_parse_configuration_data = + fw_parse_configuration_data; + tas_priv->tasdevice_load_block = + tasdevice_load_block; + break; + default: + ret = dspfw_default_callback(tas_priv, + fw_fixed_hdr->drv_ver, fw_fixed_hdr->ppcver); + if (ret) + return ret; + break; + } + + offset = tas_priv->fw_parse_variable_header(tas_priv, fmw, offset); + if (offset < 0) + return offset; + + offset = tas_priv->fw_parse_program_data(tas_priv, tas_fmw, fmw, + offset); + if (offset < 0) + return offset; + + offset = tas_priv->fw_parse_configuration_data(tas_priv, + tas_fmw, fmw, offset); + if (offset < 0) + ret = offset; + + return ret; +} + +/* DSP firmware binary file parser function. */ +int tasdevice_spi_dsp_parser(void *context) +{ + struct tasdevice_priv *tas_priv = context; + const struct firmware *fw_entry; + int ret; + + ret = request_firmware(&fw_entry, tas_priv->coef_binaryname, + tas_priv->dev); + if (ret) { + dev_err(tas_priv->dev, "%s: load %s error\n", __func__, + tas_priv->coef_binaryname); + return ret; + } + + ret = tasdevice_dspfw_ready(fw_entry, tas_priv); + release_firmware(fw_entry); + fw_entry = NULL; + + return ret; +} + +/* DSP firmware program block data remove function. */ +static void tasdev_dsp_prog_blk_remove(struct tasdevice_prog *prog) +{ + struct tasdevice_data *tas_dt; + struct tasdev_blk *blk; + unsigned int i; + + if (!prog) + return; + + tas_dt = &prog->dev_data; + + if (!tas_dt->dev_blks) + return; + + for (i = 0; i < tas_dt->nr_blk; i++) { + blk = &tas_dt->dev_blks[i]; + kfree(blk->data); + } + kfree(tas_dt->dev_blks); +} + +/* DSP firmware program block data remove function. */ +static void tasdev_dsp_prog_remove(struct tasdevice_prog *prog, + unsigned short nr) +{ + int i; + + for (i = 0; i < nr; i++) + tasdev_dsp_prog_blk_remove(&prog[i]); + kfree(prog); +} + +/* DSP firmware config block data remove function. */ +static void tasdev_dsp_cfg_blk_remove(struct tasdevice_config *cfg) +{ + struct tasdevice_data *tas_dt; + struct tasdev_blk *blk; + unsigned int i; + + if (cfg) { + tas_dt = &cfg->dev_data; + + if (!tas_dt->dev_blks) + return; + + for (i = 0; i < tas_dt->nr_blk; i++) { + blk = &tas_dt->dev_blks[i]; + kfree(blk->data); + } + kfree(tas_dt->dev_blks); + } +} + +/* DSP firmware config remove function. */ +static void tasdev_dsp_cfg_remove(struct tasdevice_config *config, + unsigned short nr) +{ + int i; + + for (i = 0; i < nr; i++) + tasdev_dsp_cfg_blk_remove(&config[i]); + kfree(config); +} + +/* DSP firmware remove function. */ +void tasdevice_spi_dsp_remove(void *context) +{ + struct tasdevice_priv *tas_dev = context; + + if (!tas_dev->fmw) + return; + + if (tas_dev->fmw->programs) + tasdev_dsp_prog_remove(tas_dev->fmw->programs, + tas_dev->fmw->nr_programs); + if (tas_dev->fmw->configs) + tasdev_dsp_cfg_remove(tas_dev->fmw->configs, + tas_dev->fmw->nr_configurations); + kfree(tas_dev->fmw); + tas_dev->fmw = NULL; +} + +/* DSP firmware calibration data remove function. */ +static void tas2781_clear_calfirmware(struct tasdevice_fw *tas_fmw) +{ + struct tasdevice_calibration *calibration; + struct tasdev_blk *block; + unsigned int blks; + int i; + + if (!tas_fmw->calibrations) + goto out; + + for (i = 0; i < tas_fmw->nr_calibrations; i++) { + calibration = &tas_fmw->calibrations[i]; + if (!calibration) + continue; + + if (!calibration->dev_data.dev_blks) + continue; + + for (blks = 0; blks < calibration->dev_data.nr_blk; blks++) { + block = &calibration->dev_data.dev_blks[blks]; + if (!block) + continue; + kfree(block->data); + } + kfree(calibration->dev_data.dev_blks); + } + kfree(tas_fmw->calibrations); +out: + kfree(tas_fmw); +} + +/* Calibration data from firmware remove function. */ +void tasdevice_spi_calbin_remove(void *context) +{ + struct tasdevice_priv *tas_priv = context; + + if (tas_priv->cali_data_fmw) { + tas2781_clear_calfirmware(tas_priv->cali_data_fmw); + tas_priv->cali_data_fmw = NULL; + } +} + +/* Configuration remove function. */ +void tasdevice_spi_config_info_remove(void *context) +{ + struct tasdevice_priv *tas_priv = context; + struct tasdevice_rca *rca = &tas_priv->rcabin; + struct tasdevice_config_info **ci = rca->cfg_info; + unsigned int i, j; + + if (!ci) + return; + for (i = 0; i < rca->ncfgs; i++) { + if (!ci[i]) + continue; + if (ci[i]->blk_data) { + for (j = 0; j < ci[i]->real_nblocks; j++) { + if (!ci[i]->blk_data[j]) + continue; + kfree(ci[i]->blk_data[j]->regdata); + kfree(ci[i]->blk_data[j]); + } + kfree(ci[i]->blk_data); + } + kfree(ci[i]); + } + kfree(ci); +} + +/* DSP firmware program block data load function. */ +static int tasdevice_load_data(struct tasdevice_priv *tas_priv, + struct tasdevice_data *dev_data) +{ + struct tasdev_blk *block; + unsigned int i; + int ret = 0; + + for (i = 0; i < dev_data->nr_blk; i++) { + block = &dev_data->dev_blks[i]; + ret = tas_priv->tasdevice_load_block(tas_priv, block); + if (ret < 0) + break; + } + + return ret; +} + +/* DSP firmware program load interface function. */ +int tasdevice_spi_prmg_load(void *context, int prm_no) +{ + struct tasdevice_priv *tas_priv = context; + struct tasdevice_fw *tas_fmw = tas_priv->fmw; + struct tasdevice_prog *program; + struct tasdevice_config *conf; + int ret = 0; + + if (!tas_fmw) { + dev_err(tas_priv->dev, "%s: Firmware is NULL\n", __func__); + return -EINVAL; + } + if (prm_no >= 0 && prm_no <= tas_fmw->nr_programs) { + tas_priv->cur_conf = 0; + tas_priv->is_loading = true; + program = &tas_fmw->programs[prm_no]; + ret = tasdevice_load_data(tas_priv, &program->dev_data); + if (ret < 0) { + dev_err(tas_priv->dev, "Program failed %d.\n", ret); + return ret; + } + tas_priv->cur_prog = prm_no; + + conf = &tas_fmw->configs[tas_priv->cur_conf]; + ret = tasdevice_load_data(tas_priv, &conf->dev_data); + if (ret < 0) + dev_err(tas_priv->dev, "Config failed %d.\n", ret); + } else { + dev_err(tas_priv->dev, + "%s: prm(%d) is not in range of Programs %u\n", + __func__, prm_no, tas_fmw->nr_programs); + return -EINVAL; + } + + return ret; +} + +/* RCABIN configuration switch interface function. */ +void tasdevice_spi_tuning_switch(void *context, int state) +{ + struct tasdevice_priv *tas_priv = context; + int profile_cfg_id = tas_priv->rcabin.profile_cfg_id; + + if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) { + dev_err(tas_priv->dev, "DSP bin file not loaded\n"); + return; + } + + if (state == 0) + tasdevice_spi_select_cfg_blk(tas_priv, profile_cfg_id, + TASDEVICE_BIN_BLK_PRE_POWER_UP); + else + tasdevice_spi_select_cfg_blk(tas_priv, profile_cfg_id, + TASDEVICE_BIN_BLK_PRE_SHUTDOWN); +} diff --git a/sound/pci/lola/lola_clock.c b/sound/pci/lola/lola_clock.c index cafd30e30913..2e73fbf335ed 100644 --- a/sound/pci/lola/lola_clock.c +++ b/sound/pci/lola/lola_clock.c @@ -35,7 +35,7 @@ unsigned int lola_sample_rate_convert(unsigned int coded) default: return 0; /* error */ } - /* ajustement */ + /* adjustement */ switch (coded & 0x60) { case (0 << 5): break; case (1 << 5): freq = (freq * 999) / 1000; break; diff --git a/sound/pci/nm256/nm256.c b/sound/pci/nm256/nm256.c index 11ba7d4eac2a..44085237fb44 100644 --- a/sound/pci/nm256/nm256.c +++ b/sound/pci/nm256/nm256.c @@ -696,7 +696,9 @@ snd_nm256_playback_copy(struct snd_pcm_substream *substream, struct snd_pcm_runtime *runtime = substream->runtime; struct nm256_stream *s = runtime->private_data; - return copy_from_iter_toio(s->bufptr + pos, src, count); + if (copy_from_iter_toio(s->bufptr + pos, count, src) != count) + return -EFAULT; + return 0; } /* @@ -710,7 +712,9 @@ snd_nm256_capture_copy(struct snd_pcm_substream *substream, struct snd_pcm_runtime *runtime = substream->runtime; struct nm256_stream *s = runtime->private_data; - return copy_to_iter_fromio(dst, s->bufptr + pos, count); + if (copy_to_iter_fromio(s->bufptr + pos, count, dst) != count) + return -EFAULT; + return 0; } #endif /* !__i386__ */ diff --git a/sound/pci/rme32.c b/sound/pci/rme32.c index 02144bbee6d5..a8c2ceaadef5 100644 --- a/sound/pci/rme32.c +++ b/sound/pci/rme32.c @@ -256,8 +256,10 @@ static int snd_rme32_playback_copy(struct snd_pcm_substream *substream, { struct rme32 *rme32 = snd_pcm_substream_chip(substream); - return copy_from_iter_toio(rme32->iobase + RME32_IO_DATA_BUFFER + pos, - src, count); + if (copy_from_iter_toio(rme32->iobase + RME32_IO_DATA_BUFFER + pos, + count, src) != count) + return -EFAULT; + return 0; } /* copy callback for halfduplex mode */ @@ -267,9 +269,10 @@ static int snd_rme32_capture_copy(struct snd_pcm_substream *substream, { struct rme32 *rme32 = snd_pcm_substream_chip(substream); - return copy_to_iter_fromio(dst, - rme32->iobase + RME32_IO_DATA_BUFFER + pos, - count); + if (copy_to_iter_fromio(rme32->iobase + RME32_IO_DATA_BUFFER + pos, + count, dst) != count) + return -EFAULT; + return 0; } /* diff --git a/sound/pci/rme96.c b/sound/pci/rme96.c index d50ad25574ad..1265a7efac60 100644 --- a/sound/pci/rme96.c +++ b/sound/pci/rme96.c @@ -322,8 +322,10 @@ snd_rme96_playback_copy(struct snd_pcm_substream *substream, { struct rme96 *rme96 = snd_pcm_substream_chip(substream); - return copy_from_iter_toio(rme96->iobase + RME96_IO_PLAY_BUFFER + pos, - src, count); + if (copy_from_iter_toio(rme96->iobase + RME96_IO_PLAY_BUFFER + pos, + count, src) != count) + return -EFAULT; + return 0; } static int @@ -333,9 +335,10 @@ snd_rme96_capture_copy(struct snd_pcm_substream *substream, { struct rme96 *rme96 = snd_pcm_substream_chip(substream); - return copy_to_iter_fromio(dst, - rme96->iobase + RME96_IO_REC_BUFFER + pos, - count); + if (copy_to_iter_fromio(rme96->iobase + RME96_IO_REC_BUFFER + pos, + count, dst) != count) + return -EFAULT; + return 0; } /* diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 1c504a591948..fd3dfbad397a 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -3444,7 +3444,7 @@ snd_hdsp_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) snd_iprintf(buffer, "MIDI1 Input status: 0x%x\n", hdsp_read(hdsp, HDSP_midiStatusIn0)); snd_iprintf(buffer, "MIDI2 Output status: 0x%x\n", hdsp_read(hdsp, HDSP_midiStatusOut1)); snd_iprintf(buffer, "MIDI2 Input status: 0x%x\n", hdsp_read(hdsp, HDSP_midiStatusIn1)); - snd_iprintf(buffer, "Use Midi Tasklet: %s\n", hdsp->use_midi_work ? "on" : "off"); + snd_iprintf(buffer, "Use Midi Tasklet: %s\n", str_on_off(hdsp->use_midi_work)); snd_iprintf(buffer, "\n"); @@ -3452,8 +3452,8 @@ snd_hdsp_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) snd_iprintf(buffer, "Buffer Size (Latency): %d samples (2 periods of %lu bytes)\n", x, (unsigned long) hdsp->period_bytes); snd_iprintf(buffer, "Hardware pointer (frames): %ld\n", hdsp_hw_pointer(hdsp)); - snd_iprintf(buffer, "Precise pointer: %s\n", hdsp->precise_ptr ? "on" : "off"); - snd_iprintf(buffer, "Line out: %s\n", (hdsp->control_register & HDSP_LineOut) ? "on" : "off"); + snd_iprintf(buffer, "Precise pointer: %s\n", str_on_off(hdsp->precise_ptr)); + snd_iprintf(buffer, "Line out: %s\n", str_on_off(hdsp->control_register & HDSP_LineOut)); snd_iprintf(buffer, "Firmware version: %d\n", (status2&HDSP_version0)|(status2&HDSP_version1)<<1|(status2&HDSP_version2)<<2); @@ -3750,8 +3750,8 @@ snd_hdsp_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) snd_iprintf(buffer, "Phones Gain : %s\n", tmp); snd_iprintf(buffer, "XLR Breakout Cable : %s\n", - hdsp_toggle_setting(hdsp, HDSP_XLRBreakoutCable) ? - "yes" : "no"); + str_yes_no(hdsp_toggle_setting(hdsp, + HDSP_XLRBreakoutCable))); if (hdsp->control_register & HDSP_AnalogExtensionBoard) snd_iprintf(buffer, "AEB : on (ADAT1 internal)\n"); diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index d7290463d654..f89718b19d23 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -4927,14 +4927,14 @@ snd_hdspm_proc_read_madi(struct snd_info_entry *entry, x, (unsigned long) hdspm->period_bytes); snd_iprintf(buffer, "Line out: %s\n", - (hdspm->control_register & HDSPM_LineOut) ? "on " : "off"); + str_on_off(hdspm->control_register & HDSPM_LineOut)); snd_iprintf(buffer, "ClearTrackMarker = %s, Transmit in %s Channel Mode, " "Auto Input %s\n", - (hdspm->control_register & HDSPM_clr_tms) ? "on" : "off", + str_on_off(hdspm->control_register & HDSPM_clr_tms), (hdspm->control_register & HDSPM_TX_64ch) ? "64" : "56", - (hdspm->control_register & HDSPM_AutoInp) ? "on" : "off"); + str_on_off(hdspm->control_register & HDSPM_AutoInp)); if (!(hdspm->control_register & HDSPM_ClockModeMaster)) @@ -5088,12 +5088,9 @@ snd_hdspm_proc_read_aes32(struct snd_info_entry * entry, snd_iprintf(buffer, "ClearTrackMarker %s, Emphasis %s, Dolby %s\n", - (hdspm-> - control_register & HDSPM_clr_tms) ? "on" : "off", - (hdspm-> - control_register & HDSPM_Emphasis) ? "on" : "off", - (hdspm-> - control_register & HDSPM_Dolby) ? "on" : "off"); + str_on_off(hdspm->control_register & HDSPM_clr_tms), + str_on_off(hdspm->control_register & HDSPM_Emphasis), + str_on_off(hdspm->control_register & HDSPM_Dolby)); pref_syncref = hdspm_pref_sync_ref(hdspm); diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c index d066c70ae160..5b8dd7b0a02c 100644 --- a/sound/pci/rme9652/rme9652.c +++ b/sound/pci/rme9652/rme9652.c @@ -1561,8 +1561,7 @@ snd_rme9652_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buff x, (unsigned long) rme9652->period_bytes); snd_iprintf(buffer, "Hardware pointer (frames): %ld\n", rme9652_hw_pointer(rme9652)); - snd_iprintf(buffer, "Passthru: %s\n", - rme9652->passthru ? "yes" : "no"); + snd_iprintf(buffer, "Passthru: %s\n", str_yes_no(rme9652->passthru)); if ((rme9652->control_register & (RME9652_Master | RME9652_wsel)) == 0) { snd_iprintf(buffer, "Clock mode: autosync\n"); @@ -1685,7 +1684,7 @@ snd_rme9652_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buff snd_iprintf(buffer, "\n"); snd_iprintf(buffer, "Timecode signal: %s\n", - (status & RME9652_tc_valid) ? "yes" : "no"); + str_yes_no(status & RME9652_tc_valid)); /* thru modes */ diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c index f91cbf6eeca0..c30eaf1038e7 100644 --- a/sound/pci/sonicvibes.c +++ b/sound/pci/sonicvibes.c @@ -1118,7 +1118,7 @@ static void snd_sonicvibes_proc_read(struct snd_info_entry *entry, tmp = sonic->srs_space & 0x0f; snd_iprintf(buffer, "SRS 3D : %s\n", - sonic->srs_space & 0x80 ? "off" : "on"); + str_off_on(sonic->srs_space & 0x80)); snd_iprintf(buffer, "SRS Space : %s\n", tmp == 0x00 ? "100%" : tmp == 0x01 ? "75%" : @@ -1135,9 +1135,9 @@ static void snd_sonicvibes_proc_read(struct snd_info_entry *entry, tmp == 0x00 ? "on-board ROM" : tmp == 0x01 ? "PCI bus" : "on-board ROM + PCI bus"); tmp = sonic->mpu_switch; - snd_iprintf(buffer, "Onboard synth : %s\n", tmp & 0x01 ? "on" : "off"); - snd_iprintf(buffer, "Ext. Rx to synth : %s\n", tmp & 0x02 ? "on" : "off"); - snd_iprintf(buffer, "MIDI to ext. Tx : %s\n", tmp & 0x04 ? "on" : "off"); + snd_iprintf(buffer, "Onboard synth : %s\n", str_on_off(tmp & 0x01)); + snd_iprintf(buffer, "Ext. Rx to synth : %s\n", str_on_off(tmp & 0x02)); + snd_iprintf(buffer, "MIDI to ext. Tx : %s\n", str_on_off(tmp & 0x04)); } static void snd_sonicvibes_proc_init(struct sonicvibes *sonic) diff --git a/sound/pci/trident/trident_main.c b/sound/pci/trident/trident_main.c index e98eea1e6d81..8039f445bee2 100644 --- a/sound/pci/trident/trident_main.c +++ b/sound/pci/trident/trident_main.c @@ -3278,9 +3278,9 @@ static void snd_trident_proc_read(struct snd_info_entry *entry, snd_iprintf(buffer, "Spurious IRQs : %d\n", trident->spurious_irq_count); snd_iprintf(buffer, "Spurious IRQ dlta: %d\n", trident->spurious_irq_max_delta); if (trident->device == TRIDENT_DEVICE_ID_NX || trident->device == TRIDENT_DEVICE_ID_SI7018) - snd_iprintf(buffer, "IEC958 Mixer Out : %s\n", trident->spdif_ctrl == 0x28 ? "on" : "off"); + snd_iprintf(buffer, "IEC958 Mixer Out : %s\n", str_on_off(trident->spdif_ctrl == 0x28)); if (trident->device == TRIDENT_DEVICE_ID_NX) { - snd_iprintf(buffer, "Rear Speakers : %s\n", trident->ac97_ctrl & 0x00000010 ? "on" : "off"); + snd_iprintf(buffer, "Rear Speakers : %s\n", str_on_off(trident->ac97_ctrl & 0x00000010)); if (trident->tlb.entries) { snd_iprintf(buffer,"\nVirtual Memory\n"); snd_iprintf(buffer, "Memory Maximum : %d\n", trident->tlb.memhdr->size); diff --git a/sound/ppc/keywest.c b/sound/ppc/keywest.c index 3d3513d9def5..4ce81ac7f700 100644 --- a/sound/ppc/keywest.c +++ b/sound/ppc/keywest.c @@ -61,12 +61,6 @@ static int keywest_attach_adapter(struct i2c_adapter *adapter) return -ENODEV; } - /* - * Let i2c-core delete that device on driver removal. - * This is safe because i2c-core holds the core_lock mutex for us. - */ - list_add_tail(&keywest_ctx->client->detected, - &to_i2c_driver(keywest_ctx->client->dev.driver)->clients); return 0; } @@ -99,6 +93,7 @@ static struct i2c_driver keywest_driver = { void snd_pmac_keywest_cleanup(struct pmac_keywest *i2c) { if (keywest_ctx && keywest_ctx == i2c) { + i2c_unregister_device(keywest_ctx->client); i2c_del_driver(&keywest_driver); keywest_ctx = NULL; } diff --git a/sound/sh/sh_dac_audio.c b/sound/sh/sh_dac_audio.c index a4d07438ad64..3f5422145c5e 100644 --- a/sound/sh/sh_dac_audio.c +++ b/sound/sh/sh_dac_audio.c @@ -163,7 +163,7 @@ static int snd_sh_dac_pcm_copy(struct snd_pcm_substream *substream, /* channel is not used (interleaved data) */ struct snd_sh_dac *chip = snd_pcm_substream_chip(substream); - if (copy_from_iter(chip->data_buffer + pos, src, count) != count) + if (copy_from_iter(chip->data_buffer + pos, count, src) != count) return -EFAULT; chip->buffer_end = chip->data_buffer + pos + count; diff --git a/sound/soc/amd/Kconfig b/sound/soc/amd/Kconfig index c7590d4989bb..803521178279 100644 --- a/sound/soc/amd/Kconfig +++ b/sound/soc/amd/Kconfig @@ -105,7 +105,7 @@ config SND_SOC_AMD_ACP6x config SND_SOC_AMD_YC_MACH tristate "AMD YC support for DMIC" select SND_SOC_DMIC - depends on SND_SOC_AMD_ACP6x + depends on SND_SOC_AMD_ACP6x && ACPI help This option enables machine driver for Yellow Carp platform using dmic. ACP IP has PDM Decoder block with DMA controller. diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c index 1f59ee248771..89e99ed4275a 100644 --- a/sound/soc/amd/acp/acp-i2s.c +++ b/sound/soc/amd/acp/acp-i2s.c @@ -181,6 +181,7 @@ static int acp_i2s_set_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, u32 rx_mas break; default: dev_err(dev, "Unknown chip revision %d\n", chip->acp_rev); + spin_unlock_irq(&adata->acp_lock); return -EINVAL; } } diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c index 823a69bf778b..8b556950b855 100644 --- a/sound/soc/amd/ps/pci-ps.c +++ b/sound/soc/amd/ps/pci-ps.c @@ -83,6 +83,7 @@ static int acp63_init(void __iomem *acp_base, struct device *dev) return ret; } acp63_enable_interrupts(acp_base); + writel(0, acp_base + ACP_ZSC_DSP_CTRL); return 0; } @@ -97,6 +98,7 @@ static int acp63_deinit(void __iomem *acp_base, struct device *dev) return ret; } writel(0, acp_base + ACP_CONTROL); + writel(1, acp_base + ACP_ZSC_DSP_CTRL); return 0; } @@ -312,6 +314,7 @@ static struct snd_soc_acpi_mach *acp63_sdw_machine_select(struct device *dev) if (mach && mach->link_mask) { mach->mach_params.links = mach->links; mach->mach_params.link_mask = mach->link_mask; + mach->mach_params.subsystem_rev = acp_data->acp_rev; return mach; } } @@ -375,11 +378,18 @@ static int get_acp63_device_config(struct pci_dev *pci, struct acp63_dev_data *a { struct acpi_device *pdm_dev; const union acpi_object *obj; + acpi_handle handle; + acpi_integer dmic_status; u32 config; bool is_dmic_dev = false; bool is_sdw_dev = false; + bool wov_en, dmic_en; int ret; + /* IF WOV entry not found, enable dmic based on acp-audio-device-type entry*/ + wov_en = true; + dmic_en = false; + config = readl(acp_data->acp63_base + ACP_PIN_CONFIG); switch (config) { case ACP_CONFIG_4: @@ -412,10 +422,18 @@ static int get_acp63_device_config(struct pci_dev *pci, struct acp63_dev_data *a if (!acpi_dev_get_property(pdm_dev, "acp-audio-device-type", ACPI_TYPE_INTEGER, &obj) && obj->integer.value == ACP_DMIC_DEV) - is_dmic_dev = true; + dmic_en = true; } + + handle = ACPI_HANDLE(&pci->dev); + ret = acpi_evaluate_integer(handle, "_WOV", NULL, &dmic_status); + if (!ACPI_FAILURE(ret)) + wov_en = dmic_status; } + if (dmic_en && wov_en) + is_dmic_dev = true; + if (acp_data->is_sdw_config) { ret = acp_scan_sdw_devices(&pci->dev, ACP63_SDW_ADDR); if (!ret && acp_data->info.link_mask) @@ -654,8 +672,10 @@ static int __maybe_unused snd_acp63_suspend(struct device *dev) adata = dev_get_drvdata(dev); if (adata->is_sdw_dev) { adata->sdw_en_stat = check_acp_sdw_enable_status(adata); - if (adata->sdw_en_stat) + if (adata->sdw_en_stat) { + writel(1, adata->acp63_base + ACP_ZSC_DSP_CTRL); return 0; + } } ret = acp63_deinit(adata->acp63_base, dev); if (ret) @@ -670,9 +690,10 @@ static int __maybe_unused snd_acp63_runtime_resume(struct device *dev) int ret; adata = dev_get_drvdata(dev); - if (adata->sdw_en_stat) + if (adata->sdw_en_stat) { + writel(0, adata->acp63_base + ACP_ZSC_DSP_CTRL); return 0; - + } ret = acp63_init(adata->acp63_base, dev); if (ret) { dev_err(dev, "ACP init failed\n"); @@ -690,8 +711,10 @@ static int __maybe_unused snd_acp63_resume(struct device *dev) int ret; adata = dev_get_drvdata(dev); - if (adata->sdw_en_stat) + if (adata->sdw_en_stat) { + writel(0, adata->acp63_base + ACP_ZSC_DSP_CTRL); return 0; + } ret = acp63_init(adata->acp63_base, dev); if (ret) diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index ecf57a6cb7c3..b16587d8f97a 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -304,6 +304,34 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "83AS"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83L3"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83N6"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83Q2"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"), + } + }, { .driver_data = &acp6x_card, .matches = { diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 0f2df7c91e18..ee35f3aa5521 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -692,7 +692,7 @@ config SND_SOC_AW88261 the input amplitude. config SND_SOC_AW88081 - tristate "Soc Audio for awinic aw88081" + tristate "Soc Audio for awinic aw88081/aw88083" depends on I2C select REGMAP_I2C select SND_SOC_AW88395_LIB @@ -2451,6 +2451,7 @@ config SND_SOC_WM8993 config SND_SOC_WM8994 tristate + depends on MFD_WM8994 config SND_SOC_WM8995 tristate diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile index f37e82ddb7a1..d7ad795603c1 100644 --- a/sound/soc/codecs/Makefile +++ b/sound/soc/codecs/Makefile @@ -80,7 +80,7 @@ snd-soc-cs35l56-shared-y := cs35l56-shared.o snd-soc-cs35l56-i2c-y := cs35l56-i2c.o snd-soc-cs35l56-spi-y := cs35l56-spi.o snd-soc-cs35l56-sdw-y := cs35l56-sdw.o -snd-soc-cs40l50-objs := cs40l50-codec.o +snd-soc-cs40l50-y := cs40l50-codec.o snd-soc-cs42l42-y := cs42l42.o snd-soc-cs42l42-i2c-y := cs42l42-i2c.o snd-soc-cs42l42-sdw-y := cs42l42-sdw.o @@ -92,7 +92,7 @@ snd-soc-cs42l52-y := cs42l52.o snd-soc-cs42l56-y := cs42l56.o snd-soc-cs42l73-y := cs42l73.o snd-soc-cs42l83-i2c-y := cs42l83-i2c.o -snd-soc-cs42l84-objs := cs42l84.o +snd-soc-cs42l84-y := cs42l84.o snd-soc-cs4234-y := cs4234.o snd-soc-cs4265-y := cs4265.o snd-soc-cs4270-y := cs4270.o @@ -334,8 +334,8 @@ snd-soc-wcd-classh-y := wcd-clsh-v2.o snd-soc-wcd-mbhc-y := wcd-mbhc-v2.o snd-soc-wcd9335-y := wcd9335.o snd-soc-wcd934x-y := wcd934x.o -snd-soc-wcd937x-objs := wcd937x.o -snd-soc-wcd937x-sdw-objs := wcd937x-sdw.o +snd-soc-wcd937x-y := wcd937x.o +snd-soc-wcd937x-sdw-y := wcd937x-sdw.o snd-soc-wcd938x-y := wcd938x.o snd-soc-wcd938x-sdw-y := wcd938x-sdw.o snd-soc-wcd939x-y := wcd939x.o diff --git a/sound/soc/codecs/ad193x-i2c.c b/sound/soc/codecs/ad193x-i2c.c index 15d74bb31c4c..6aa168e01fbb 100644 --- a/sound/soc/codecs/ad193x-i2c.c +++ b/sound/soc/codecs/ad193x-i2c.c @@ -23,7 +23,6 @@ MODULE_DEVICE_TABLE(i2c, ad193x_id); static int ad193x_i2c_probe(struct i2c_client *client) { struct regmap_config config; - const struct i2c_device_id *id = i2c_match_id(ad193x_id, client); config = ad193x_regmap_config; config.val_bits = 8; @@ -31,7 +30,7 @@ static int ad193x_i2c_probe(struct i2c_client *client) return ad193x_probe(&client->dev, devm_regmap_init_i2c(client, &config), - (enum ad193x_type)id->driver_data); + (uintptr_t)i2c_get_match_data(client)); } static struct i2c_driver ad193x_i2c_driver = { diff --git a/sound/soc/codecs/adau1761-i2c.c b/sound/soc/codecs/adau1761-i2c.c index a554255186ae..eba7e4f42c78 100644 --- a/sound/soc/codecs/adau1761-i2c.c +++ b/sound/soc/codecs/adau1761-i2c.c @@ -14,12 +14,9 @@ #include "adau1761.h" -static const struct i2c_device_id adau1761_i2c_ids[]; - static int adau1761_i2c_probe(struct i2c_client *client) { struct regmap_config config; - const struct i2c_device_id *id = i2c_match_id(adau1761_i2c_ids, client); config = adau1761_regmap_config; config.val_bits = 8; @@ -27,7 +24,7 @@ static int adau1761_i2c_probe(struct i2c_client *client) return adau1761_probe(&client->dev, devm_regmap_init_i2c(client, &config), - id->driver_data, NULL); + (uintptr_t)i2c_get_match_data(client), NULL); } static void adau1761_i2c_remove(struct i2c_client *client) diff --git a/sound/soc/codecs/adau1781-i2c.c b/sound/soc/codecs/adau1781-i2c.c index 3a170fd78ff3..cb67fde8d9a8 100644 --- a/sound/soc/codecs/adau1781-i2c.c +++ b/sound/soc/codecs/adau1781-i2c.c @@ -14,12 +14,9 @@ #include "adau1781.h" -static const struct i2c_device_id adau1781_i2c_ids[]; - static int adau1781_i2c_probe(struct i2c_client *client) { struct regmap_config config; - const struct i2c_device_id *id = i2c_match_id(adau1781_i2c_ids, client); config = adau1781_regmap_config; config.val_bits = 8; @@ -27,7 +24,7 @@ static int adau1781_i2c_probe(struct i2c_client *client) return adau1781_probe(&client->dev, devm_regmap_init_i2c(client, &config), - id->driver_data, NULL); + (uintptr_t)i2c_get_match_data(client), NULL); } static void adau1781_i2c_remove(struct i2c_client *client) diff --git a/sound/soc/codecs/adau1977-i2c.c b/sound/soc/codecs/adau1977-i2c.c index 24c7b9c84c19..441c8079246a 100644 --- a/sound/soc/codecs/adau1977-i2c.c +++ b/sound/soc/codecs/adau1977-i2c.c @@ -14,12 +14,9 @@ #include "adau1977.h" -static const struct i2c_device_id adau1977_i2c_ids[]; - static int adau1977_i2c_probe(struct i2c_client *client) { struct regmap_config config; - const struct i2c_device_id *id = i2c_match_id(adau1977_i2c_ids, client); config = adau1977_regmap_config; config.val_bits = 8; @@ -27,7 +24,7 @@ static int adau1977_i2c_probe(struct i2c_client *client) return adau1977_probe(&client->dev, devm_regmap_init_i2c(client, &config), - id->driver_data, NULL); + (uintptr_t)i2c_get_match_data(client), NULL); } static const struct i2c_device_id adau1977_i2c_ids[] = { diff --git a/sound/soc/codecs/alc5623.c b/sound/soc/codecs/alc5623.c index b24c32206884..fbf723758079 100644 --- a/sound/soc/codecs/alc5623.c +++ b/sound/soc/codecs/alc5623.c @@ -987,9 +987,9 @@ static int alc5623_i2c_probe(struct i2c_client *client) struct alc5623_priv *alc5623; struct device_node *np; unsigned int vid1, vid2; + unsigned int matched_id; int ret; u32 val32; - const struct i2c_device_id *id; alc5623 = devm_kzalloc(&client->dev, sizeof(struct alc5623_priv), GFP_KERNEL); @@ -1016,12 +1016,12 @@ static int alc5623_i2c_probe(struct i2c_client *client) } vid2 >>= 8; - id = i2c_match_id(alc5623_i2c_table, client); + matched_id = (uintptr_t)i2c_get_match_data(client); - if ((vid1 != 0x10ec) || (vid2 != id->driver_data)) { + if ((vid1 != 0x10ec) || (vid2 != matched_id)) { dev_err(&client->dev, "unknown or wrong codec\n"); - dev_err(&client->dev, "Expected %x:%lx, got %x:%x\n", - 0x10ec, id->driver_data, + dev_err(&client->dev, "Expected %x:%x, got %x:%x\n", + 0x10ec, matched_id, vid1, vid2); return -ENODEV; } diff --git a/sound/soc/codecs/alc5632.c b/sound/soc/codecs/alc5632.c index d5021f266930..72f4622204ff 100644 --- a/sound/soc/codecs/alc5632.c +++ b/sound/soc/codecs/alc5632.c @@ -1108,7 +1108,7 @@ static int alc5632_i2c_probe(struct i2c_client *client) struct alc5632_priv *alc5632; int ret, ret1, ret2; unsigned int vid1, vid2; - const struct i2c_device_id *id; + unsigned int matched_id; alc5632 = devm_kzalloc(&client->dev, sizeof(struct alc5632_priv), GFP_KERNEL); @@ -1134,9 +1134,9 @@ static int alc5632_i2c_probe(struct i2c_client *client) vid2 >>= 8; - id = i2c_match_id(alc5632_i2c_table, client); + matched_id = (uintptr_t)i2c_get_match_data(client); - if ((vid1 != 0x10EC) || (vid2 != id->driver_data)) { + if ((vid1 != 0x10EC) || (vid2 != matched_id)) { dev_err(&client->dev, "Device is not a ALC5632: VID1=0x%x, VID2=0x%x\n", vid1, vid2); return -EINVAL; diff --git a/sound/soc/codecs/aw88081.c b/sound/soc/codecs/aw88081.c index 58b8e002d76f..ad16ab6812cd 100644 --- a/sound/soc/codecs/aw88081.c +++ b/sound/soc/codecs/aw88081.c @@ -14,13 +14,18 @@ #include "aw88081.h" #include "aw88395/aw88395_device.h" +enum aw8808x_type { + AW88081, + AW88083, +}; + struct aw88081 { struct aw_device *aw_pa; struct mutex lock; struct delayed_work start_work; struct regmap *regmap; struct aw_container *aw_cfg; - + enum aw8808x_type devtype; bool phase_sync; }; @@ -32,6 +37,14 @@ static const struct regmap_config aw88081_regmap_config = { .val_format_endian = REGMAP_ENDIAN_BIG, }; +static const struct regmap_config aw88083_regmap_config = { + .val_bits = 16, + .reg_bits = 8, + .max_register = AW88083_REG_MAX, + .reg_format_endian = REGMAP_ENDIAN_LITTLE, + .val_format_endian = REGMAP_ENDIAN_BIG, +}; + static int aw88081_dev_get_iis_status(struct aw_device *aw_dev) { unsigned int reg_val; @@ -196,6 +209,41 @@ static void aw88081_dev_amppd(struct aw_device *aw_dev, bool amppd) ~AW88081_EN_PA_MASK, AW88081_EN_PA_WORKING_VALUE); } +static void aw88083_i2c_wen(struct aw88081 *aw88081, bool flag) +{ + struct aw_device *aw_dev = aw88081->aw_pa; + + if (aw88081->devtype != AW88083) + return; + + if (flag) + regmap_update_bits(aw_dev->regmap, AW88081_SYSCTRL_REG, + ~AW88083_I2C_WEN_MASK, AW88083_I2C_WEN_ENABLE_VALUE); + else + regmap_update_bits(aw_dev->regmap, AW88081_SYSCTRL_REG, + ~AW88083_I2C_WEN_MASK, AW88083_I2C_WEN_DISABLE_VALUE); +} + +static void aw88083_dev_amppd(struct aw_device *aw_dev, bool amppd) +{ + if (amppd) + regmap_update_bits(aw_dev->regmap, AW88081_SYSCTRL_REG, + ~AW88083_AMPPD_MASK, AW88083_AMPPD_POWER_DOWN_VALUE); + else + regmap_update_bits(aw_dev->regmap, AW88081_SYSCTRL_REG, + ~AW88083_AMPPD_MASK, AW88083_AMPPD_WORKING_VALUE); +} + +static void aw88083_dev_pllpd(struct aw_device *aw_dev, bool pllpd) +{ + if (pllpd) + regmap_update_bits(aw_dev->regmap, AW88081_SYSCTRL_REG, + ~AW88083_PLL_PD_MASK, AW88083_PLL_PD_WORKING_VALUE); + else + regmap_update_bits(aw_dev->regmap, AW88081_SYSCTRL_REG, + ~AW88083_PLL_PD_MASK, AW88083_PLL_PD_POWER_DOWN_VALUE); +} + static void aw88081_dev_clear_int_status(struct aw_device *aw_dev) { unsigned int int_status; @@ -284,12 +332,90 @@ static void aw88081_dev_uls_hmute(struct aw_device *aw_dev, bool uls_hmute) AW88081_ULS_HMUTE_DISABLE_VALUE); } +static int aw88081_dev_reg_value_check(struct aw_device *aw_dev, + unsigned char reg_addr, unsigned short *reg_val) +{ + unsigned int read_vol; + + if (reg_addr == AW88081_SYSCTRL_REG) { + *reg_val &= ~(~AW88081_EN_PA_MASK | + ~AW88081_PWDN_MASK | + ~AW88081_HMUTE_MASK | + ~AW88081_ULS_HMUTE_MASK); + + *reg_val |= AW88081_EN_PA_POWER_DOWN_VALUE | + AW88081_PWDN_POWER_DOWN_VALUE | + AW88081_HMUTE_ENABLE_VALUE | + AW88081_ULS_HMUTE_ENABLE_VALUE; + } + + if (reg_addr == AW88081_SYSCTRL2_REG) { + read_vol = (*reg_val & (~AW88081_VOL_MASK)) >> AW88081_VOL_START_BIT; + aw_dev->volume_desc.init_volume = read_vol; + } + + /* i2stxen */ + if (reg_addr == AW88081_I2SCTRL3_REG) { + /* close tx */ + *reg_val &= AW88081_I2STXEN_MASK; + *reg_val |= AW88081_I2STXEN_DISABLE_VALUE; + } + + return 0; +} + +static int aw88083_dev_reg_value_check(struct aw_device *aw_dev, + unsigned char reg_addr, unsigned short *reg_val) +{ + unsigned int read_vol; + + if (reg_addr == AW88081_SYSCTRL_REG) { + *reg_val &= ~(~AW88083_AMPPD_MASK | + ~AW88081_PWDN_MASK | + ~AW88081_HMUTE_MASK | + ~AW88083_I2C_WEN_MASK); + + *reg_val |= AW88083_AMPPD_POWER_DOWN_VALUE | + AW88081_PWDN_POWER_DOWN_VALUE | + AW88081_HMUTE_ENABLE_VALUE | + AW88083_I2C_WEN_ENABLE_VALUE; + } + + if (reg_addr == AW88081_SYSCTRL2_REG) { + read_vol = (*reg_val & (~AW88081_VOL_MASK)) >> AW88081_VOL_START_BIT; + aw_dev->volume_desc.init_volume = read_vol; + } + + return 0; +} + +static int aw88081_reg_value_check(struct aw88081 *aw88081, + unsigned char reg_addr, unsigned short *reg_val) +{ + struct aw_device *aw_dev = aw88081->aw_pa; + int ret; + + switch (aw88081->devtype) { + case AW88081: + ret = aw88081_dev_reg_value_check(aw_dev, reg_addr, reg_val); + break; + case AW88083: + ret = aw88083_dev_reg_value_check(aw_dev, reg_addr, reg_val); + break; + default: + dev_err(aw_dev->dev, "unsupported device\n"); + ret = -EINVAL; + break; + } + + return ret; +} + static int aw88081_dev_reg_update(struct aw88081 *aw88081, unsigned char *data, unsigned int len) { struct aw_device *aw_dev = aw88081->aw_pa; struct aw_volume_desc *vol_desc = &aw_dev->volume_desc; - unsigned int read_vol; int data_len, i, ret; int16_t *reg_data; u16 reg_val; @@ -312,30 +438,9 @@ static int aw88081_dev_reg_update(struct aw88081 *aw88081, reg_addr = reg_data[i]; reg_val = reg_data[i + 1]; - if (reg_addr == AW88081_SYSCTRL_REG) { - reg_val &= ~(~AW88081_EN_PA_MASK | - ~AW88081_PWDN_MASK | - ~AW88081_HMUTE_MASK | - ~AW88081_ULS_HMUTE_MASK); - - reg_val |= AW88081_EN_PA_POWER_DOWN_VALUE | - AW88081_PWDN_POWER_DOWN_VALUE | - AW88081_HMUTE_ENABLE_VALUE | - AW88081_ULS_HMUTE_ENABLE_VALUE; - } - - if (reg_addr == AW88081_SYSCTRL2_REG) { - read_vol = (reg_val & (~AW88081_VOL_MASK)) >> - AW88081_VOL_START_BIT; - aw_dev->volume_desc.init_volume = read_vol; - } - - /* i2stxen */ - if (reg_addr == AW88081_I2SCTRL3_REG) { - /* close tx */ - reg_val &= AW88081_I2STXEN_MASK; - reg_val |= AW88081_I2STXEN_DISABLE_VALUE; - } + ret = aw88081_reg_value_check(aw88081, reg_addr, ®_val); + if (ret) + return ret; ret = regmap_write(aw_dev->regmap, reg_addr, reg_val); if (ret) @@ -474,8 +579,60 @@ pll_check_fail: return ret; } -static int aw88081_dev_stop(struct aw_device *aw_dev) +static int aw88083_dev_start(struct aw88081 *aw88081) { + struct aw_device *aw_dev = aw88081->aw_pa; + + if (aw_dev->status == AW88081_DEV_PW_ON) { + dev_dbg(aw_dev->dev, "already power on"); + return 0; + } + + aw88083_i2c_wen(aw88081, true); + + /* power on */ + aw88081_dev_pwd(aw_dev, false); + usleep_range(AW88081_2000_US, AW88081_2000_US + 10); + + aw88083_dev_pllpd(aw_dev, true); + /* amppd on */ + aw88083_dev_amppd(aw_dev, false); + usleep_range(AW88081_2000_US, AW88081_2000_US + 50); + + /* close mute */ + aw88081_dev_mute(aw_dev, false); + + aw88083_i2c_wen(aw88081, false); + + aw_dev->status = AW88081_DEV_PW_ON; + + return 0; +} + +static int aw88081_device_start(struct aw88081 *aw88081) +{ + int ret; + + switch (aw88081->devtype) { + case AW88081: + ret = aw88081_dev_start(aw88081); + break; + case AW88083: + ret = aw88083_dev_start(aw88081); + break; + default: + ret = -EINVAL; + dev_err(aw88081->aw_pa->dev, "unsupported device\n"); + break; + } + + return ret; +} + +static int aw88081_dev_stop(struct aw88081 *aw88081) +{ + struct aw_device *aw_dev = aw88081->aw_pa; + if (aw_dev->status == AW88081_DEV_PW_OFF) { dev_dbg(aw_dev->dev, "already power off"); return 0; @@ -503,6 +660,56 @@ static int aw88081_dev_stop(struct aw_device *aw_dev) return 0; } +static int aw88083_dev_stop(struct aw88081 *aw88081) +{ + struct aw_device *aw_dev = aw88081->aw_pa; + + if (aw_dev->status == AW88081_DEV_PW_OFF) { + dev_dbg(aw_dev->dev, "already power off"); + return 0; + } + + aw_dev->status = AW88081_DEV_PW_OFF; + + aw88083_i2c_wen(aw88081, true); + /* set mute */ + aw88081_dev_mute(aw_dev, true); + + usleep_range(AW88081_2000_US, AW88081_2000_US + 100); + + /* enable amppd */ + aw88083_dev_amppd(aw_dev, true); + + aw88083_dev_pllpd(aw_dev, false); + + /* set power down */ + aw88081_dev_pwd(aw_dev, true); + + aw88083_i2c_wen(aw88081, false); + + return 0; +} + +static int aw88081_stop(struct aw88081 *aw88081) +{ + int ret; + + switch (aw88081->devtype) { + case AW88081: + ret = aw88081_dev_stop(aw88081); + break; + case AW88083: + ret = aw88083_dev_stop(aw88081); + break; + default: + dev_err(aw88081->aw_pa->dev, "unsupported device\n"); + ret = -EINVAL; + break; + } + + return ret; +} + static int aw88081_reg_update(struct aw88081 *aw88081, bool force) { struct aw_device *aw_dev = aw88081->aw_pa; @@ -540,7 +747,7 @@ static void aw88081_start_pa(struct aw88081 *aw88081) dev_err(aw88081->aw_pa->dev, "fw update failed, cnt:%d\n", i); continue; } - ret = aw88081_dev_start(aw88081); + ret = aw88081_device_start(aw88081); if (ret) { dev_err(aw88081->aw_pa->dev, "aw88081 device start failed. retry = %d", i); continue; @@ -745,7 +952,7 @@ static int aw88081_profile_set(struct snd_kcontrol *kcontrol, } if (aw88081->aw_pa->status) { - aw88081_dev_stop(aw88081->aw_pa); + aw88081_stop(aw88081); aw88081_start(aw88081, AW88081_SYNC_START); } @@ -781,12 +988,16 @@ static int aw88081_volume_set(struct snd_kcontrol *kcontrol, if (value < mc->min || value > mc->max) return -EINVAL; + aw88083_i2c_wen(aw88081, true); + if (vol_desc->ctl_volume != value) { vol_desc->ctl_volume = value; aw88081_dev_set_volume(aw88081->aw_pa, vol_desc->ctl_volume); return 1; } + aw88083_i2c_wen(aw88081, false); + return 0; } @@ -860,13 +1071,19 @@ static int aw88081_init(struct aw88081 *aw88081, struct i2c_client *i2c, struct dev_err(&i2c->dev, "%s read chipid error. ret = %d", __func__, ret); return ret; } - if (chip_id != AW88081_CHIP_ID) { + + switch (chip_id) { + case AW88081_CHIP_ID: + dev_dbg(&i2c->dev, "chip id = 0x%x\n", chip_id); + break; + case AW88083_CHIP_ID: + dev_dbg(&i2c->dev, "chip id = 0x%x\n", chip_id); + break; + default: dev_err(&i2c->dev, "unsupported device"); return -ENXIO; } - dev_dbg(&i2c->dev, "chip id = %x\n", chip_id); - aw_dev = devm_kzalloc(&i2c->dev, sizeof(*aw_dev), GFP_KERNEL); if (!aw_dev) return -ENOMEM; @@ -875,7 +1092,7 @@ static int aw88081_init(struct aw88081 *aw88081, struct i2c_client *i2c, struct aw_dev->i2c = i2c; aw_dev->regmap = regmap; aw_dev->dev = &i2c->dev; - aw_dev->chip_id = AW88081_CHIP_ID; + aw_dev->chip_id = chip_id; aw_dev->acf = NULL; aw_dev->prof_info.prof_desc = NULL; aw_dev->prof_info.prof_type = AW88395_DEV_NONE_TYPE_ID; @@ -912,21 +1129,8 @@ static int aw88081_dev_init(struct aw88081 *aw88081, struct aw_container *aw_cfg return ret; } - aw88081_dev_clear_int_status(aw_dev); - - aw88081_dev_uls_hmute(aw_dev, true); - - aw88081_dev_mute(aw_dev, true); - - usleep_range(AW88081_5000_US, AW88081_5000_US + 10); - - aw88081_dev_i2s_tx_enable(aw_dev, false); - - usleep_range(AW88081_1000_US, AW88081_1000_US + 100); - - aw88081_dev_amppd(aw_dev, true); - - aw88081_dev_pwd(aw_dev, true); + aw_dev->status = AW88081_DEV_PW_ON; + aw88081_stop(aw88081); return 0; } @@ -977,7 +1181,7 @@ static int aw88081_playback_event(struct snd_soc_dapm_widget *w, aw88081_start(aw88081, AW88081_ASYNC_START); break; case SND_SOC_DAPM_POST_PMD: - aw88081_dev_stop(aw88081->aw_pa); + aw88081_stop(aw88081); break; default: break; @@ -1036,8 +1240,17 @@ static const struct snd_soc_component_driver soc_codec_dev_aw88081 = { .num_controls = ARRAY_SIZE(aw88081_controls), }; +static const struct i2c_device_id aw88081_i2c_id[] = { + { AW88081_I2C_NAME, AW88081}, + { AW88083_I2C_NAME, AW88083}, + { } +}; +MODULE_DEVICE_TABLE(i2c, aw88081_i2c_id); + static int aw88081_i2c_probe(struct i2c_client *i2c) { + const struct regmap_config *regmap_config; + const struct i2c_device_id *id; struct aw88081 *aw88081; int ret; @@ -1049,11 +1262,25 @@ static int aw88081_i2c_probe(struct i2c_client *i2c) if (!aw88081) return -ENOMEM; + id = i2c_match_id(aw88081_i2c_id, i2c); + aw88081->devtype = id->driver_data; + mutex_init(&aw88081->lock); i2c_set_clientdata(i2c, aw88081); - aw88081->regmap = devm_regmap_init_i2c(i2c, &aw88081_regmap_config); + switch (aw88081->devtype) { + case AW88081: + regmap_config = &aw88081_regmap_config; + break; + case AW88083: + regmap_config = &aw88083_regmap_config; + break; + default: + return -EINVAL; + } + + aw88081->regmap = devm_regmap_init_i2c(i2c, regmap_config); if (IS_ERR(aw88081->regmap)) return dev_err_probe(&i2c->dev, PTR_ERR(aw88081->regmap), "failed to init regmap\n"); @@ -1068,12 +1295,6 @@ static int aw88081_i2c_probe(struct i2c_client *i2c) aw88081_dai, ARRAY_SIZE(aw88081_dai)); } -static const struct i2c_device_id aw88081_i2c_id[] = { - { AW88081_I2C_NAME }, - { } -}; -MODULE_DEVICE_TABLE(i2c, aw88081_i2c_id); - static struct i2c_driver aw88081_i2c_driver = { .driver = { .name = AW88081_I2C_NAME, diff --git a/sound/soc/codecs/aw88081.h b/sound/soc/codecs/aw88081.h index b4bf7288021a..7a4564270ab3 100644 --- a/sound/soc/codecs/aw88081.h +++ b/sound/soc/codecs/aw88081.h @@ -231,6 +231,49 @@ #define AW88081_CCO_MUX_BYPASS_VALUE \ (AW88081_CCO_MUX_BYPASS << AW88081_CCO_MUX_START_BIT) +#define AW88083_I2C_WEN_START_BIT (14) +#define AW88083_I2C_WEN_BITS_LEN (2) +#define AW88083_I2C_WEN_MASK \ + (~(((1<<AW88083_I2C_WEN_BITS_LEN)-1) << AW88083_I2C_WEN_START_BIT)) + +#define AW88083_I2C_WEN_DISABLE (0) +#define AW88083_I2C_WEN_DISABLE_VALUE \ + (AW88083_I2C_WEN_DISABLE << AW88083_I2C_WEN_START_BIT) + +#define AW88083_I2C_WEN_ENABLE (2) +#define AW88083_I2C_WEN_ENABLE_VALUE \ + (AW88083_I2C_WEN_ENABLE << AW88083_I2C_WEN_START_BIT) + +#define AW88083_PLL_PD_START_BIT (2) +#define AW88083_PLL_PD_BITS_LEN (1) +#define AW88083_PLL_PD_MASK \ + (~(((1<<AW88083_PLL_PD_BITS_LEN)-1) << AW88083_PLL_PD_START_BIT)) + +#define AW88083_PLL_PD_POWER_DOWN (1) +#define AW88083_PLL_PD_POWER_DOWN_VALUE \ + (AW88083_PLL_PD_POWER_DOWN << AW88083_PLL_PD_START_BIT) + +#define AW88083_PLL_PD_WORKING (0) +#define AW88083_PLL_PD_WORKING_VALUE \ + (AW88083_PLL_PD_WORKING << AW88083_PLL_PD_START_BIT) + +#define AW88083_AMPPD_START_BIT (1) +#define AW88083_AMPPD_BITS_LEN (1) +#define AW88083_AMPPD_MASK \ + (~(((1<<AW88083_AMPPD_BITS_LEN)-1) << AW88083_AMPPD_START_BIT)) + +#define AW88083_AMPPD_WORKING (0) +#define AW88083_AMPPD_WORKING_VALUE \ + (AW88083_AMPPD_WORKING << AW88083_AMPPD_START_BIT) + +#define AW88083_AMPPD_POWER_DOWN (1) +#define AW88083_AMPPD_POWER_DOWN_VALUE \ + (AW88083_AMPPD_POWER_DOWN << AW88083_AMPPD_START_BIT) + +#define AW88083_REG_MAX (0x7D) +#define AW88083_I2C_NAME "aw88083" +#define AW88083_CHIP_ID 0x2407 + #define AW88081_START_RETRIES (5) #define AW88081_START_WORK_DELAY_MS (0) diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index ae045c88c48d..735a1e487c6f 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -646,6 +646,12 @@ static struct snd_soc_dai_driver cs35l56_dai[] = { .rates = CS35L56_RATES, .formats = CS35L56_RX_FORMATS, }, + .symmetric_rate = 1, + .ops = &cs35l56_sdw_dai_ops, + }, + { + .name = "cs35l56-sdw1c", + .id = 2, .capture = { .stream_name = "SDW1 Capture", .channels_min = 1, @@ -655,7 +661,7 @@ static struct snd_soc_dai_driver cs35l56_dai[] = { }, .symmetric_rate = 1, .ops = &cs35l56_sdw_dai_ops, - } + }, }; static int cs35l56_write_cal(struct cs35l56_private *cs35l56) diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c index 4236f78beec0..d2a2daefc2ec 100644 --- a/sound/soc/codecs/cs42l43.c +++ b/sound/soc/codecs/cs42l43.c @@ -12,7 +12,7 @@ #include <linux/device.h> #include <linux/err.h> #include <linux/errno.h> -#include <linux/find.h> +#include <linux/bitmap.h> #include <linux/gcd.h> #include <linux/irq.h> #include <linux/irqdomain.h> @@ -2404,6 +2404,7 @@ static int cs42l43_codec_runtime_resume(struct device *dev) static const struct dev_pm_ops cs42l43_codec_pm_ops = { RUNTIME_PM_OPS(NULL, cs42l43_codec_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) }; static const struct platform_device_id cs42l43_codec_id_table[] = { diff --git a/sound/soc/codecs/cs42l51-i2c.c b/sound/soc/codecs/cs42l51-i2c.c index e7cc50096297..f171bd66fcac 100644 --- a/sound/soc/codecs/cs42l51-i2c.c +++ b/sound/soc/codecs/cs42l51-i2c.c @@ -13,9 +13,9 @@ #include "cs42l51.h" -static struct i2c_device_id cs42l51_i2c_id[] = { - {"cs42l51"}, - {} +static const struct i2c_device_id cs42l51_i2c_id[] = { + { "cs42l51" }, + { } }; MODULE_DEVICE_TABLE(i2c, cs42l51_i2c_id); diff --git a/sound/soc/codecs/cs42l84.c b/sound/soc/codecs/cs42l84.c index 17d5c96e334d..88cf3c03986e 100644 --- a/sound/soc/codecs/cs42l84.c +++ b/sound/soc/codecs/cs42l84.c @@ -1087,7 +1087,7 @@ static const struct of_device_id cs42l84_of_match[] = { MODULE_DEVICE_TABLE(of, cs42l84_of_match); static const struct i2c_device_id cs42l84_id[] = { - {"cs42l84", 0}, + { "cs42l84" }, {} }; MODULE_DEVICE_TABLE(i2c, cs42l84_id); diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c index ca4cc954efa8..eb97ac73ec06 100644 --- a/sound/soc/codecs/da7213.c +++ b/sound/soc/codecs/da7213.c @@ -2203,6 +2203,8 @@ static int da7213_i2c_probe(struct i2c_client *i2c) return ret; } + mutex_init(&da7213->ctrl_lock); + pm_runtime_set_autosuspend_delay(&i2c->dev, 100); pm_runtime_use_autosuspend(&i2c->dev); pm_runtime_set_active(&i2c->dev); diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c index 61729e5b50a8..e7bd561a8f40 100644 --- a/sound/soc/codecs/es8316.c +++ b/sound/soc/codecs/es8316.c @@ -39,7 +39,9 @@ struct es8316_priv { struct snd_soc_jack *jack; int irq; unsigned int sysclk; - unsigned int allowed_rates[ARRAY_SIZE(supported_mclk_lrck_ratios)]; + /* ES83xx supports halving the MCLK so it supports twice as many rates + */ + unsigned int allowed_rates[ARRAY_SIZE(supported_mclk_lrck_ratios) * 2]; struct snd_pcm_hw_constraint_list sysclk_constraints; bool jd_inverted; }; @@ -99,7 +101,7 @@ static const struct snd_kcontrol_new es8316_snd_controls[] = { SOC_DOUBLE_R_TLV("DAC Playback Volume", ES8316_DAC_VOLL, ES8316_DAC_VOLR, 0, 0xc0, 1, dac_vol_tlv), SOC_SINGLE("DAC Soft Ramp Switch", ES8316_DAC_SET1, 4, 1, 1), - SOC_SINGLE("DAC Soft Ramp Rate", ES8316_DAC_SET1, 2, 4, 0), + SOC_SINGLE("DAC Soft Ramp Rate", ES8316_DAC_SET1, 2, 3, 0), SOC_SINGLE("DAC Notch Filter Switch", ES8316_DAC_SET2, 6, 1, 0), SOC_SINGLE("DAC Double Fs Switch", ES8316_DAC_SET2, 7, 1, 0), SOC_SINGLE("DAC Stereo Enhancement", ES8316_DAC_SET3, 0, 7, 0), @@ -386,6 +388,12 @@ static int es8316_set_dai_sysclk(struct snd_soc_dai *codec_dai, if (freq % ratio == 0) es8316->allowed_rates[count++] = freq / ratio; + + /* We also check if the halved MCLK produces a valid rate + * since the codec supports halving the MCLK. + */ + if ((freq / ratio) % 2 == 0) + es8316->allowed_rates[count++] = freq / ratio / 2; } if (count) { diff --git a/sound/soc/codecs/es8323.c b/sound/soc/codecs/es8323.c index 6f4fa36ea34d..a9822998199f 100644 --- a/sound/soc/codecs/es8323.c +++ b/sound/soc/codecs/es8323.c @@ -758,7 +758,7 @@ static int es8323_i2c_probe(struct i2c_client *i2c_client) } static const struct i2c_device_id es8323_i2c_id[] = { - { "es8323", 0 }, + { "es8323" }, { } }; MODULE_DEVICE_TABLE(i2c, es8323_i2c_id); diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c index a5603b617688..066d92b54312 100644 --- a/sound/soc/codecs/es8326.c +++ b/sound/soc/codecs/es8326.c @@ -616,7 +616,7 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction) 0x0F, 0x0F); if (es8326->version > ES8326_VERSION_B) { regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x40); - regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x10); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x30); } } } else { @@ -631,6 +631,8 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction) regmap_write(es8326->regmap, ES8326_HPR_OFFSET_INI, offset_r); es8326->calibrated = true; } + regmap_update_bits(es8326->regmap, ES8326_CLK_INV, 0xc0, 0x00); + regmap_update_bits(es8326->regmap, ES8326_CLK_MUX, 0x80, 0x00); if (direction == SNDRV_PCM_STREAM_PLAYBACK) { regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x01); usleep_range(1000, 5000); @@ -645,7 +647,7 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction) } else { msleep(300); if (es8326->version > ES8326_VERSION_B) { - regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x50); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x70); regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x00); } regmap_update_bits(es8326->regmap, ES8326_ADC_MUTE, @@ -676,6 +678,10 @@ static int es8326_set_bias_level(struct snd_soc_component *codec, regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00); regmap_update_bits(es8326->regmap, ES8326_CLK_CTL, 0x20, 0x20); regmap_update_bits(es8326->regmap, ES8326_RESET, 0x02, 0x00); + if (es8326->version > ES8326_VERSION_B) { + regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x40); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x30); + } break; case SND_SOC_BIAS_PREPARE: break; @@ -683,6 +689,12 @@ static int es8326_set_bias_level(struct snd_soc_component *codec, regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x3b); regmap_update_bits(es8326->regmap, ES8326_CLK_CTL, 0x20, 0x00); regmap_write(es8326->regmap, ES8326_SDINOUT1_IO, ES8326_IO_INPUT); + if (es8326->version > ES8326_VERSION_B) { + regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x40); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x10); + } + regmap_update_bits(es8326->regmap, ES8326_CLK_INV, 0xc0, 0xc0); + regmap_update_bits(es8326->regmap, ES8326_CLK_MUX, 0x80, 0x80); break; case SND_SOC_BIAS_OFF: clk_disable_unprepare(es8326->mclk); @@ -773,7 +785,10 @@ static void es8326_jack_button_handler(struct work_struct *work) case 0x6f: case 0x4b: /* button volume up */ - cur_button = SND_JACK_BTN_1; + if ((iface == 0x6f) && (es8326->version > ES8326_VERSION_B)) + cur_button = SND_JACK_BTN_0; + else + cur_button = SND_JACK_BTN_1; break; case 0x27: /* button volume down */ @@ -896,7 +911,7 @@ static void es8326_jack_detect_handler(struct work_struct *work) regmap_write(es8326->regmap, ES8326_INT_SOURCE, (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON)); regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x1f); - regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x08); + regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x0d); queue_delayed_work(system_wq, &es8326->jack_detect_work, msecs_to_jiffies(400)); es8326->hp = 1; @@ -1008,7 +1023,7 @@ static void es8326_init(struct snd_soc_component *component) struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component); regmap_write(es8326->regmap, ES8326_RESET, 0x1f); - regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E); + regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x3E); regmap_write(es8326->regmap, ES8326_ANA_LP, 0xf0); usleep_range(10000, 15000); regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xd9); @@ -1082,7 +1097,7 @@ static void es8326_init(struct snd_soc_component *component) regmap_write(es8326->regmap, ES8326_ADC2_SRC, 0x66); es8326_disable_micbias(es8326->component); if (es8326->version > ES8326_VERSION_B) { - regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x73, 0x13); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x73, 0x10); regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x40); } diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index d9df29a26f4f..69f98975e14a 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -714,7 +714,7 @@ static int hdmi_codec_mute(struct snd_soc_dai *dai, int mute, int direction) */ if (hcp->hcd.ops->mute_stream && (direction == SNDRV_PCM_STREAM_PLAYBACK || - !hcp->hcd.ops->no_capture_mute)) + !hcp->hcd.no_capture_mute)) return hcp->hcd.ops->mute_stream(dai->dev->parent, hcp->hcd.data, mute, direction); @@ -995,7 +995,7 @@ static int hdmi_of_xlate_dai_id(struct snd_soc_component *component, int ret = -ENOTSUPP; /* see snd_soc_get_dai_id() */ if (hcp->hcd.ops->get_dai_id) - ret = hcp->hcd.ops->get_dai_id(component, endpoint); + ret = hcp->hcd.ops->get_dai_id(component, endpoint, hcp->hcd.data); return ret; } diff --git a/sound/soc/codecs/madera.c b/sound/soc/codecs/madera.c index b24d6472ad5f..a840a2eb92b9 100644 --- a/sound/soc/codecs/madera.c +++ b/sound/soc/codecs/madera.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/pm_runtime.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include <sound/pcm.h> #include <sound/pcm_params.h> #include <sound/tlv.h> @@ -3965,7 +3966,7 @@ static int madera_enable_fll(struct madera_fll *fll) } madera_fll_dbg(fll, "Enabling FLL, initially %s\n", - already_enabled ? "enabled" : "disabled"); + str_enabled_disabled(already_enabled)); if (fll->fout < MADERA_FLL_MIN_FOUT || fll->fout > MADERA_FLL_MAX_FOUT) { @@ -4252,7 +4253,7 @@ static int madera_enable_fll_ao(struct madera_fll *fll, pm_runtime_get_sync(madera->dev); madera_fll_dbg(fll, "Enabling FLL_AO, initially %s\n", - already_enabled ? "enabled" : "disabled"); + str_enabled_disabled(already_enabled)); /* FLL_AO_HOLD must be set before configuring any registers */ regmap_update_bits(fll->madera->regmap, @@ -4576,7 +4577,7 @@ static int madera_fllhj_enable(struct madera_fll *fll) pm_runtime_get_sync(madera->dev); madera_fll_dbg(fll, "Enabling FLL, initially %s\n", - already_enabled ? "enabled" : "disabled"); + str_enabled_disabled(already_enabled)); /* FLLn_HOLD must be set before configuring any registers */ regmap_update_bits(fll->madera->regmap, diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c index 8915f5250695..37e61d8d4be6 100644 --- a/sound/soc/codecs/max98088.c +++ b/sound/soc/codecs/max98088.c @@ -1731,7 +1731,6 @@ MODULE_DEVICE_TABLE(i2c, max98088_i2c_id); static int max98088_i2c_probe(struct i2c_client *i2c) { struct max98088_priv *max98088; - const struct i2c_device_id *id; max98088 = devm_kzalloc(&i2c->dev, sizeof(struct max98088_priv), GFP_KERNEL); @@ -1747,8 +1746,7 @@ static int max98088_i2c_probe(struct i2c_client *i2c) if (PTR_ERR(max98088->mclk) == -EPROBE_DEFER) return PTR_ERR(max98088->mclk); - id = i2c_match_id(max98088_i2c_id, i2c); - max98088->devtype = id->driver_data; + max98088->devtype = (uintptr_t)i2c_get_match_data(i2c); i2c_set_clientdata(i2c, max98088); max98088->pdata = i2c->dev.platform_data; diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 2adf744c6526..790e2ae6dc18 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -2543,8 +2543,6 @@ MODULE_DEVICE_TABLE(i2c, max98090_i2c_id); static int max98090_i2c_probe(struct i2c_client *i2c) { struct max98090_priv *max98090; - const struct acpi_device_id *acpi_id; - kernel_ulong_t driver_data = 0; int ret; pr_debug("max98090_i2c_probe\n"); @@ -2554,21 +2552,7 @@ static int max98090_i2c_probe(struct i2c_client *i2c) if (max98090 == NULL) return -ENOMEM; - if (ACPI_HANDLE(&i2c->dev)) { - acpi_id = acpi_match_device(i2c->dev.driver->acpi_match_table, - &i2c->dev); - if (!acpi_id) { - dev_err(&i2c->dev, "No driver data\n"); - return -EINVAL; - } - driver_data = acpi_id->driver_data; - } else { - const struct i2c_device_id *i2c_id = - i2c_match_id(max98090_i2c_id, i2c); - driver_data = i2c_id->driver_data; - } - - max98090->devtype = driver_data; + max98090->devtype = (uintptr_t)i2c_get_match_data(i2c); i2c_set_clientdata(i2c, max98090); max98090->pdata = i2c->dev.platform_data; diff --git a/sound/soc/codecs/max98095.c b/sound/soc/codecs/max98095.c index 7e525d49328d..cfb63fe69267 100644 --- a/sound/soc/codecs/max98095.c +++ b/sound/soc/codecs/max98095.c @@ -2115,7 +2115,6 @@ static int max98095_i2c_probe(struct i2c_client *i2c) { struct max98095_priv *max98095; int ret; - const struct i2c_device_id *id; max98095 = devm_kzalloc(&i2c->dev, sizeof(struct max98095_priv), GFP_KERNEL); @@ -2131,8 +2130,7 @@ static int max98095_i2c_probe(struct i2c_client *i2c) return ret; } - id = i2c_match_id(max98095_i2c_id, i2c); - max98095->devtype = id->driver_data; + max98095->devtype = (uintptr_t)i2c_get_match_data(i2c); i2c_set_clientdata(i2c, max98095); max98095->pdata = i2c->dev.platform_data; diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c index 12540397fd4d..5aaf8c496300 100644 --- a/sound/soc/codecs/nau8824.c +++ b/sound/soc/codecs/nau8824.c @@ -368,13 +368,13 @@ static const struct snd_kcontrol_new nau8824_snd_controls[] = { SOC_ENUM("DAC Oversampling Rate", nau8824_dac_oversampl_enum), SOC_SINGLE_TLV("Speaker Right DACR Volume", - NAU8824_REG_CLASSD_GAIN_1, 8, 0x1f, 0, spk_vol_tlv), + NAU8824_REG_CLASSD_GAIN_1, 8, 0x19, 0, spk_vol_tlv), SOC_SINGLE_TLV("Speaker Left DACL Volume", - NAU8824_REG_CLASSD_GAIN_2, 0, 0x1f, 0, spk_vol_tlv), + NAU8824_REG_CLASSD_GAIN_2, 0, 0x19, 0, spk_vol_tlv), SOC_SINGLE_TLV("Speaker Left DACR Volume", - NAU8824_REG_CLASSD_GAIN_1, 0, 0x1f, 0, spk_vol_tlv), + NAU8824_REG_CLASSD_GAIN_1, 0, 0x19, 0, spk_vol_tlv), SOC_SINGLE_TLV("Speaker Right DACL Volume", - NAU8824_REG_CLASSD_GAIN_2, 8, 0x1f, 0, spk_vol_tlv), + NAU8824_REG_CLASSD_GAIN_2, 8, 0x19, 0, spk_vol_tlv), SOC_SINGLE_TLV("Headphone Right DACR Volume", NAU8824_REG_ATT_PORT0, 8, 0x1f, 0, hp_vol_tlv), diff --git a/sound/soc/codecs/ntp8835.c b/sound/soc/codecs/ntp8835.c index 796e1410496f..2cc4c6395f55 100644 --- a/sound/soc/codecs/ntp8835.c +++ b/sound/soc/codecs/ntp8835.c @@ -454,7 +454,7 @@ static int ntp8835_i2c_probe(struct i2c_client *i2c) } static const struct i2c_device_id ntp8835_i2c_id[] = { - { "ntp8835", 0 }, + { "ntp8835" }, {} }; MODULE_DEVICE_TABLE(i2c, ntp8835_i2c_id); diff --git a/sound/soc/codecs/ntp8918.c b/sound/soc/codecs/ntp8918.c index 0493ab6acbe4..a332893fc51d 100644 --- a/sound/soc/codecs/ntp8918.c +++ b/sound/soc/codecs/ntp8918.c @@ -371,7 +371,7 @@ static int ntp8918_i2c_probe(struct i2c_client *i2c) } static const struct i2c_device_id ntp8918_i2c_id[] = { - { "ntp8918", 0 }, + { "ntp8918" }, {} }; MODULE_DEVICE_TABLE(i2c, ntp8918_i2c_id); diff --git a/sound/soc/codecs/pcm186x-i2c.c b/sound/soc/codecs/pcm186x-i2c.c index a514ebd1b68a..a50f9f6e39c1 100644 --- a/sound/soc/codecs/pcm186x-i2c.c +++ b/sound/soc/codecs/pcm186x-i2c.c @@ -33,8 +33,7 @@ MODULE_DEVICE_TABLE(i2c, pcm186x_i2c_id); static int pcm186x_i2c_probe(struct i2c_client *i2c) { - const struct i2c_device_id *id = i2c_match_id(pcm186x_i2c_id, i2c); - const enum pcm186x_type type = (enum pcm186x_type)id->driver_data; + const enum pcm186x_type type = (uintptr_t)i2c_get_match_data(i2c); int irq = i2c->irq; struct regmap *regmap; diff --git a/sound/soc/codecs/pcm6240.c b/sound/soc/codecs/pcm6240.c index 5d99877f8839..4ff39e0b95b2 100644 --- a/sound/soc/codecs/pcm6240.c +++ b/sound/soc/codecs/pcm6240.c @@ -2059,7 +2059,6 @@ static char *str_to_upper(char *str) static int pcmdevice_i2c_probe(struct i2c_client *i2c) { - const struct i2c_device_id *id = i2c_match_id(pcmdevice_i2c_id, i2c); struct pcmdevice_priv *pcm_dev; struct device_node *np; unsigned int dev_addrs[PCMDEVICE_MAX_I2C_DEVICES]; @@ -2069,7 +2068,7 @@ static int pcmdevice_i2c_probe(struct i2c_client *i2c) if (!pcm_dev) return -ENOMEM; - pcm_dev->chip_id = (id != NULL) ? id->driver_data : 0; + pcm_dev->chip_id = (uintptr_t)i2c_get_match_data(i2c); pcm_dev->dev = &i2c->dev; pcm_dev->client = i2c; diff --git a/sound/soc/codecs/peb2466.c b/sound/soc/codecs/peb2466.c index bb9ca6354ae1..a989cfe058f0 100644 --- a/sound/soc/codecs/peb2466.c +++ b/sound/soc/codecs/peb2466.c @@ -26,8 +26,7 @@ struct peb2466_lookup { unsigned int count; }; -#define PEB2466_TLV_SIZE (sizeof((unsigned int []){TLV_DB_SCALE_ITEM(0, 0, 0)}) / \ - sizeof(unsigned int)) +#define PEB2466_TLV_SIZE ARRAY_SIZE(((unsigned int[]){TLV_DB_SCALE_ITEM(0, 0, 0)})) struct peb2466_lkup_ctrl { int reg; diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c index 2b3c0f9e178c..9cb74962161a 100644 --- a/sound/soc/codecs/rt5514.c +++ b/sound/soc/codecs/rt5514.c @@ -1091,8 +1091,7 @@ static int rt5514_set_bias_level(struct snd_soc_component *component, static int rt5514_probe(struct snd_soc_component *component) { struct rt5514_priv *rt5514 = snd_soc_component_get_drvdata(component); - struct platform_device *pdev = container_of(component->dev, - struct platform_device, dev); + struct platform_device *pdev = to_platform_device(component->dev); rt5514->mclk = devm_clk_get_optional(component->dev, "mclk"); if (IS_ERR(rt5514->mclk)) diff --git a/sound/soc/codecs/rt5682-i2c.c b/sound/soc/codecs/rt5682-i2c.c index ff9e14fad0cd..a8820435d1e0 100644 --- a/sound/soc/codecs/rt5682-i2c.c +++ b/sound/soc/codecs/rt5682-i2c.c @@ -186,6 +186,12 @@ static int rt5682_i2c_probe(struct i2c_client *i2c) return -ENODEV; } + regmap_read(rt5682->regmap, RT5682_INT_DEVICE_ID, &val); + if (val == 0x6956) { + dev_dbg(&i2c->dev, "ALC5682I-VE device\n"); + rt5682->ve_ic = true; + } + mutex_init(&rt5682->calibrate_mutex); rt5682_calibrate(rt5682); diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index aa163ec40862..b4d72fc4a44d 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -395,6 +395,7 @@ bool rt5682_volatile_register(struct device *dev, unsigned int reg) case RT5682_4BTN_IL_CMD_1: case RT5682_AJD1_CTRL: case RT5682_HP_CALIB_CTRL_1: + case RT5682_INT_DEVICE_ID: case RT5682_DEVICE_ID: case RT5682_I2C_MODE: case RT5682_HP_CALIB_CTRL_10: @@ -419,6 +420,7 @@ bool rt5682_readable_register(struct device *dev, unsigned int reg) { switch (reg) { case RT5682_RESET: + case RT5682_INT_DEVICE_ID: case RT5682_VERSION_ID: case RT5682_VENDOR_ID: case RT5682_DEVICE_ID: @@ -3139,7 +3141,10 @@ void rt5682_calibrate(struct rt5682_priv *rt5682) regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x0100); regmap_write(rt5682->regmap, RT5682_HP_IMP_SENS_CTRL_19, 0x3800); regmap_write(rt5682->regmap, RT5682_CHOP_DAC, 0x3000); - regmap_write(rt5682->regmap, RT5682_CALIB_ADC_CTRL, 0x7005); + if (rt5682->ve_ic) + regmap_write(rt5682->regmap, RT5682_CHOP_ADC, 0x7005); + else + regmap_write(rt5682->regmap, RT5682_CALIB_ADC_CTRL, 0x7005); regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0x686c); regmap_write(rt5682->regmap, RT5682_CAL_REC, 0x0d0d); regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_2, 0x0321); @@ -3168,7 +3173,10 @@ void rt5682_calibrate(struct rt5682_priv *rt5682) regmap_write(rt5682->regmap, RT5682_GLB_CLK, 0x0000); regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x0000); regmap_write(rt5682->regmap, RT5682_CHOP_DAC, 0x2000); - regmap_write(rt5682->regmap, RT5682_CALIB_ADC_CTRL, 0x2005); + if (rt5682->ve_ic) + regmap_write(rt5682->regmap, RT5682_CHOP_ADC, 0x2005); + else + regmap_write(rt5682->regmap, RT5682_CALIB_ADC_CTRL, 0x2005); regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0xc0c4); regmap_write(rt5682->regmap, RT5682_CAL_REC, 0x0c0c); diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h index b2d9e87af259..de43a5d99403 100644 --- a/sound/soc/codecs/rt5682.h +++ b/sound/soc/codecs/rt5682.h @@ -22,6 +22,7 @@ /* Info */ #define RT5682_RESET 0x0000 +#define RT5682_INT_DEVICE_ID 0x00f9 #define RT5682_VERSION_ID 0x00fd #define RT5682_VENDOR_ID 0x00fe #define RT5682_DEVICE_ID 0x00ff @@ -1446,6 +1447,7 @@ struct rt5682_priv { bool hw_init; bool first_hw_init; bool is_sdw; + bool ve_ic; #ifdef CONFIG_COMMON_CLK struct clk_hw dai_clks_hw[RT5682_DAI_NUM_CLKS]; diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c index ec255ada44e0..cd702574c84b 100644 --- a/sound/soc/codecs/rt715-sdw.c +++ b/sound/soc/codecs/rt715-sdw.c @@ -372,47 +372,6 @@ static const struct regmap_config rt715_sdw_regmap = { .use_single_write = true, }; -int hda_to_sdw(unsigned int nid, unsigned int verb, unsigned int payload, - unsigned int *sdw_addr_h, unsigned int *sdw_data_h, - unsigned int *sdw_addr_l, unsigned int *sdw_data_l) -{ - unsigned int offset_h, offset_l, e_verb; - - if (((verb & 0xff) != 0) || verb == 0xf00) { /* 12 bits command */ - if (verb == 0x7ff) /* special case */ - offset_h = 0; - else - offset_h = 0x3000; - - if (verb & 0x800) /* get command */ - e_verb = (verb - 0xf00) | 0x80; - else /* set command */ - e_verb = (verb - 0x700); - - *sdw_data_h = payload; /* 7 bits payload */ - *sdw_addr_l = *sdw_data_l = 0; - } else { /* 4 bits command */ - if ((verb & 0x800) == 0x800) { /* read */ - offset_h = 0x9000; - offset_l = 0xa000; - } else { /* write */ - offset_h = 0x7000; - offset_l = 0x8000; - } - e_verb = verb >> 8; - *sdw_data_h = (payload >> 8); /* 16 bits payload [15:8] */ - *sdw_addr_l = (e_verb << 8) | nid | 0x80; /* 0x80: valid bit */ - *sdw_addr_l += offset_l; - *sdw_data_l = payload & 0xff; - } - - *sdw_addr_h = (e_verb << 8) | nid; - *sdw_addr_h += offset_h; - - return 0; -} -EXPORT_SYMBOL(hda_to_sdw); - static int rt715_update_status(struct sdw_slave *slave, enum sdw_slave_status status) { diff --git a/sound/soc/codecs/rt715.h b/sound/soc/codecs/rt715.h index 6e37bf64e12f..a0c56aa1003a 100644 --- a/sound/soc/codecs/rt715.h +++ b/sound/soc/codecs/rt715.h @@ -220,8 +220,5 @@ int rt715_io_init(struct device *dev, struct sdw_slave *slave); int rt715_init(struct device *dev, struct regmap *sdw_regmap, struct regmap *regmap, struct sdw_slave *slave); -int hda_to_sdw(unsigned int nid, unsigned int verb, unsigned int payload, - unsigned int *sdw_addr_h, unsigned int *sdw_data_h, - unsigned int *sdw_addr_l, unsigned int *sdw_data_l); int rt715_clock_config(struct device *dev); #endif /* __RT715_H__ */ diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c index 908846e994df..e17a142d03b9 100644 --- a/sound/soc/codecs/rt722-sdca.c +++ b/sound/soc/codecs/rt722-sdca.c @@ -1468,13 +1468,18 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) 0x008d); /* check HP calibration FSM status */ for (loop_check = 0; loop_check < chk_cnt; loop_check++) { + usleep_range(10000, 11000); ret = rt722_sdca_index_read(rt722, RT722_VENDOR_CALI, RT722_DAC_DC_CALI_CTL3, &calib_status); - if (ret < 0 || loop_check == chk_cnt) + if (ret < 0) dev_dbg(&rt722->slave->dev, "calibration failed!, ret=%d\n", ret); if ((calib_status & 0x0040) == 0x0) break; } + + if (loop_check == chk_cnt) + dev_dbg(&rt722->slave->dev, "%s, calibration time-out!\n", __func__); + /* Set ADC09 power entity floating control */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ADC0A_08_PDE_FLOAT_CTL, 0x2a12); diff --git a/sound/soc/codecs/sma1307.c b/sound/soc/codecs/sma1307.c index f2cea6186d98..480bcea48541 100644 --- a/sound/soc/codecs/sma1307.c +++ b/sound/soc/codecs/sma1307.c @@ -2011,8 +2011,8 @@ static void sma1307_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id sma1307_i2c_id[] = { - { "sma1307a", 0 }, - { "sma1307aq", 0 }, + { "sma1307a" }, + { "sma1307aq" }, { } }; diff --git a/sound/soc/codecs/ssm2602-i2c.c b/sound/soc/codecs/ssm2602-i2c.c index 596096466cd4..49c74cba17c7 100644 --- a/sound/soc/codecs/ssm2602-i2c.c +++ b/sound/soc/codecs/ssm2602-i2c.c @@ -13,8 +13,6 @@ #include "ssm2602.h" -static const struct i2c_device_id ssm2602_i2c_id[]; - /* * ssm2602 2 wire address is determined by GPIO5 * state during powerup. @@ -23,8 +21,7 @@ static const struct i2c_device_id ssm2602_i2c_id[]; */ static int ssm2602_i2c_probe(struct i2c_client *client) { - const struct i2c_device_id *id = i2c_match_id(ssm2602_i2c_id, client); - return ssm2602_probe(&client->dev, id->driver_data, + return ssm2602_probe(&client->dev, (uintptr_t)i2c_get_match_data(client), devm_regmap_init_i2c(client, &ssm2602_regmap_config)); } diff --git a/sound/soc/codecs/tas2562.c b/sound/soc/codecs/tas2562.c index 54561ae598b8..fef7ce39f664 100644 --- a/sound/soc/codecs/tas2562.c +++ b/sound/soc/codecs/tas2562.c @@ -731,16 +731,14 @@ static int tas2562_probe(struct i2c_client *client) struct device *dev = &client->dev; struct tas2562_data *data; int ret; - const struct i2c_device_id *id; data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; - id = i2c_match_id(tas2562_id, client); data->client = client; data->dev = &client->dev; - data->model_id = id->driver_data; + data->model_id = (uintptr_t)i2c_get_match_data(client); tas2562_parse_dt(data); diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index fb8cd2284fe8..a730ab6ad4e3 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -78,7 +78,7 @@ static const struct bulk_reg_val tas2781_cali_start_reg[] = { X2781_CL_STT_VAL(TAS2781_PRM_INT_MASK_REG, 0xfe, false), X2781_CL_STT_VAL(TAS2781_PRM_CLK_CFG_REG, 0xdd, false), X2781_CL_STT_VAL(TAS2781_PRM_RSVD_REG, 0x20, false), - X2781_CL_STT_VAL(TAS2781_PRM_TEST_57_REG, 0x14, false), + X2781_CL_STT_VAL(TAS2781_PRM_TEST_57_REG, 0x14, true), X2781_CL_STT_VAL(TAS2781_PRM_TEST_62_REG, 0x45, true), X2781_CL_STT_VAL(TAS2781_PRM_PVDD_UVLO_REG, 0x03, false), X2781_CL_STT_VAL(TAS2781_PRM_CHNL_0_REG, 0xa8, false), @@ -489,14 +489,11 @@ static int tas2563_calib_start_put(struct snd_kcontrol *kcontrol, struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); struct tasdevice_priv *tas_priv = snd_soc_component_get_drvdata(comp); const int sum = ARRAY_SIZE(tas2563_cali_start_reg); - int rc = 1; int i, j; guard(mutex)(&tas_priv->codec_lock); - if (tas_priv->chip_id != TAS2563) { - rc = -1; - goto out; - } + if (tas_priv->chip_id != TAS2563) + return -1; for (i = 0; i < tas_priv->ndev; i++) { struct tasdevice *tasdev = tas_priv->tasdevice; @@ -523,8 +520,8 @@ static int tas2563_calib_start_put(struct snd_kcontrol *kcontrol, q[j].val, 4); } } -out: - return rc; + + return 1; } static void tas2563_calib_stop_put(struct tasdevice_priv *tas_priv) @@ -576,7 +573,7 @@ static int tasdev_cali_data_put(struct snd_kcontrol *kcontrol, struct cali_reg *p = &cali_data->cali_reg_array; unsigned char *src = ucontrol->value.bytes.data; unsigned char *dst = cali_data->data; - int rc = 1, i = 0; + int i = 0; int j; guard(mutex)(&priv->codec_lock); @@ -605,7 +602,7 @@ static int tasdev_cali_data_put(struct snd_kcontrol *kcontrol, i += 3; memcpy(dst, &src[i], cali_data->total_sz); - return rc; + return 1; } static int tas2781_latch_reg_get(struct snd_kcontrol *kcontrol, @@ -1115,25 +1112,21 @@ static int tasdevice_dsp_create_ctrls(struct tasdevice_priv *tas_priv) char *conf_name, *prog_name; int nr_controls = 4; int mix_index = 0; - int ret; /* Alloc kcontrol via devm_kzalloc, which don't manually * free the kcontrol */ dsp_ctrls = devm_kcalloc(tas_priv->dev, nr_controls, sizeof(dsp_ctrls[0]), GFP_KERNEL); - if (!dsp_ctrls) { - ret = -ENOMEM; - goto out; - } + if (!dsp_ctrls) + return -ENOMEM; /* Create mixer items for selecting the active Program and Config */ prog_name = devm_kstrdup(tas_priv->dev, "Speaker Program Id", GFP_KERNEL); - if (!prog_name) { - ret = -ENOMEM; - goto out; - } + if (!prog_name) + return -ENOMEM; + dsp_ctrls[mix_index].name = prog_name; dsp_ctrls[mix_index].iface = SNDRV_CTL_ELEM_IFACE_MIXER; dsp_ctrls[mix_index].info = tasdevice_info_programs; @@ -1143,10 +1136,9 @@ static int tasdevice_dsp_create_ctrls(struct tasdevice_priv *tas_priv) conf_name = devm_kstrdup(tas_priv->dev, "Speaker Config Id", GFP_KERNEL); - if (!conf_name) { - ret = -ENOMEM; - goto out; - } + if (!conf_name) + return -ENOMEM; + dsp_ctrls[mix_index].name = conf_name; dsp_ctrls[mix_index].iface = SNDRV_CTL_ELEM_IFACE_MIXER; dsp_ctrls[mix_index].info = tasdevice_info_configurations; @@ -1156,10 +1148,9 @@ static int tasdevice_dsp_create_ctrls(struct tasdevice_priv *tas_priv) active_dev_num = devm_kstrdup(tas_priv->dev, "Activate Tasdevice Num", GFP_KERNEL); - if (!active_dev_num) { - ret = -ENOMEM; - goto out; - } + if (!active_dev_num) + return -ENOMEM; + dsp_ctrls[mix_index].name = active_dev_num; dsp_ctrls[mix_index].iface = SNDRV_CTL_ELEM_IFACE_MIXER; dsp_ctrls[mix_index].info = tasdevice_info_active_num; @@ -1168,21 +1159,17 @@ static int tasdevice_dsp_create_ctrls(struct tasdevice_priv *tas_priv) mix_index++; chip_id = devm_kstrdup(tas_priv->dev, "Tasdevice Chip Id", GFP_KERNEL); - if (!chip_id) { - ret = -ENOMEM; - goto out; - } + if (!chip_id) + return -ENOMEM; + dsp_ctrls[mix_index].name = chip_id; dsp_ctrls[mix_index].iface = SNDRV_CTL_ELEM_IFACE_MIXER; dsp_ctrls[mix_index].info = tasdevice_info_chip_id; dsp_ctrls[mix_index].get = tasdevice_get_chip_id; mix_index++; - ret = snd_soc_add_component_controls(tas_priv->codec, dsp_ctrls, + return snd_soc_add_component_controls(tas_priv->codec, dsp_ctrls, nr_controls < mix_index ? nr_controls : mix_index); - -out: - return ret; } static int tasdevice_create_cali_ctrls(struct tasdevice_priv *priv) @@ -1469,7 +1456,6 @@ static int tasdevice_hw_params(struct snd_pcm_substream *substream, unsigned int slot_width; unsigned int fsrate; int bclk_rate; - int rc = 0; fsrate = params_rate(params); switch (fsrate) { @@ -1479,8 +1465,7 @@ static int tasdevice_hw_params(struct snd_pcm_substream *substream, default: dev_err(tas_priv->dev, "%s: incorrect sample rate = %u\n", __func__, fsrate); - rc = -EINVAL; - goto out; + return -EINVAL; } slot_width = params_width(params); @@ -1493,20 +1478,17 @@ static int tasdevice_hw_params(struct snd_pcm_substream *substream, default: dev_err(tas_priv->dev, "%s: incorrect slot width = %u\n", __func__, slot_width); - rc = -EINVAL; - goto out; + return -EINVAL; } bclk_rate = snd_soc_params_to_bclk(params); if (bclk_rate < 0) { dev_err(tas_priv->dev, "%s: incorrect bclk rate = %d\n", __func__, bclk_rate); - rc = bclk_rate; - goto out; + return bclk_rate; } -out: - return rc; + return 0; } static int tasdevice_set_dai_sysclk(struct snd_soc_dai *codec_dai, @@ -1663,7 +1645,6 @@ static void tasdevice_parse_dt(struct tasdevice_priv *tas_priv) static int tasdevice_i2c_probe(struct i2c_client *i2c) { - const struct i2c_device_id *id = i2c_match_id(tasdevice_id, i2c); const struct acpi_device_id *acpi_id; struct tasdevice_priv *tas_priv; int ret; @@ -1685,7 +1666,7 @@ static int tasdevice_i2c_probe(struct i2c_client *i2c) tas_priv->chip_id = acpi_id->driver_data; tas_priv->isacpi = true; } else { - tas_priv->chip_id = id ? id->driver_data : 0; + tas_priv->chip_id = (uintptr_t)i2c_get_match_data(i2c); tas_priv->isacpi = false; } diff --git a/sound/soc/codecs/tas5720.c b/sound/soc/codecs/tas5720.c index 6dd6c0896eff..f0361822061f 100644 --- a/sound/soc/codecs/tas5720.c +++ b/sound/soc/codecs/tas5720.c @@ -43,7 +43,6 @@ static const char * const tas5720_supply_names[] = { struct tas5720_data { struct snd_soc_component *component; struct regmap *regmap; - struct i2c_client *tas5720_client; enum tas572x_type devtype; struct regulator_bulk_data supplies[TAS5720_NUM_SUPPLIES]; struct delayed_work fault_check_work; @@ -729,7 +728,6 @@ static int tas5720_probe(struct i2c_client *client) struct device *dev = &client->dev; struct tas5720_data *data; const struct regmap_config *regmap_config; - const struct i2c_device_id *id; int ret; int i; @@ -737,11 +735,9 @@ static int tas5720_probe(struct i2c_client *client) if (!data) return -ENOMEM; - id = i2c_match_id(tas5720_id, client); - data->tas5720_client = client; - data->devtype = id->driver_data; + data->devtype = (uintptr_t)i2c_get_match_data(client); - switch (id->driver_data) { + switch (data->devtype) { case TAS5720: regmap_config = &tas5720_regmap_config; break; @@ -774,7 +770,7 @@ static int tas5720_probe(struct i2c_client *client) dev_set_drvdata(dev, data); - switch (id->driver_data) { + switch (data->devtype) { case TAS5720: ret = devm_snd_soc_register_component(&client->dev, &soc_component_dev_tas5720, diff --git a/sound/soc/codecs/tlv320adc3xxx.c b/sound/soc/codecs/tlv320adc3xxx.c index 868e8a91e05b..1a50ff675244 100644 --- a/sound/soc/codecs/tlv320adc3xxx.c +++ b/sound/soc/codecs/tlv320adc3xxx.c @@ -1401,7 +1401,6 @@ static int adc3xxx_i2c_probe(struct i2c_client *i2c) { struct device *dev = &i2c->dev; struct adc3xxx *adc3xxx = NULL; - const struct i2c_device_id *id; int ret; adc3xxx = devm_kzalloc(dev, sizeof(struct adc3xxx), GFP_KERNEL); @@ -1466,8 +1465,7 @@ static int adc3xxx_i2c_probe(struct i2c_client *i2c) i2c_set_clientdata(i2c, adc3xxx); - id = i2c_match_id(adc3xxx_i2c_id, i2c); - adc3xxx->type = id->driver_data; + adc3xxx->type = (uintptr_t)i2c_get_match_data(i2c); /* Reset codec chip */ gpiod_set_value_cansleep(adc3xxx->rst_pin, 1); diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c index d81ab9c25c29..4b3f9128ec37 100644 --- a/sound/soc/codecs/tlv320aic31xx.c +++ b/sound/soc/codecs/tlv320aic31xx.c @@ -1736,12 +1736,8 @@ static int aic31xx_i2c_probe(struct i2c_client *i2c) { struct aic31xx_priv *aic31xx; unsigned int micbias_value = MICBIAS_2_0V; - const struct i2c_device_id *id = i2c_match_id(aic31xx_i2c_id, i2c); int i, ret; - dev_dbg(&i2c->dev, "## %s: %s codec_type = %d\n", __func__, - id->name, (int)id->driver_data); - aic31xx = devm_kzalloc(&i2c->dev, sizeof(*aic31xx), GFP_KERNEL); if (!aic31xx) return -ENOMEM; @@ -1758,7 +1754,7 @@ static int aic31xx_i2c_probe(struct i2c_client *i2c) aic31xx->dev = &i2c->dev; aic31xx->irq = i2c->irq; - aic31xx->codec_type = id->driver_data; + aic31xx->codec_type = (uintptr_t)i2c_get_match_data(i2c); dev_set_drvdata(aic31xx->dev, aic31xx); diff --git a/sound/soc/codecs/tlv320aic3x-i2c.c b/sound/soc/codecs/tlv320aic3x-i2c.c index bb33fd3dfb4f..0b585925c1ac 100644 --- a/sound/soc/codecs/tlv320aic3x-i2c.c +++ b/sound/soc/codecs/tlv320aic3x-i2c.c @@ -31,14 +31,13 @@ static int aic3x_i2c_probe(struct i2c_client *i2c) { struct regmap *regmap; struct regmap_config config; - const struct i2c_device_id *id = i2c_match_id(aic3x_i2c_id, i2c); config = aic3x_regmap; config.reg_bits = 8; config.val_bits = 8; regmap = devm_regmap_init_i2c(i2c, &config); - return aic3x_probe(&i2c->dev, regmap, id->driver_data); + return aic3x_probe(&i2c->dev, regmap, (uintptr_t)i2c_get_match_data(i2c)); } static void aic3x_i2c_remove(struct i2c_client *i2c) diff --git a/sound/soc/codecs/tpa6130a2.c b/sound/soc/codecs/tpa6130a2.c index 5bc486283fde..b5472fa1bdda 100644 --- a/sound/soc/codecs/tpa6130a2.c +++ b/sound/soc/codecs/tpa6130a2.c @@ -222,7 +222,6 @@ static int tpa6130a2_probe(struct i2c_client *client) struct tpa6130a2_data *data; struct tpa6130a2_platform_data *pdata = client->dev.platform_data; struct device_node *np = client->dev.of_node; - const struct i2c_device_id *id; const char *regulator; unsigned int version; int ret; @@ -251,8 +250,7 @@ static int tpa6130a2_probe(struct i2c_client *client) i2c_set_clientdata(client, data); - id = i2c_match_id(tpa6130a2_id, client); - data->id = id->driver_data; + data->id = (uintptr_t)i2c_get_match_data(client); if (data->power_gpio >= 0) { ret = devm_gpio_request(dev, data->power_gpio, diff --git a/sound/soc/codecs/uda1342.c b/sound/soc/codecs/uda1342.c index 3d49a7869948..b0b29012842d 100644 --- a/sound/soc/codecs/uda1342.c +++ b/sound/soc/codecs/uda1342.c @@ -319,7 +319,7 @@ static DEFINE_RUNTIME_DEV_PM_OPS(uda1342_pm_ops, uda1342_suspend, uda1342_resume, NULL); static const struct i2c_device_id uda1342_i2c_id[] = { - { "uda1342", 0 }, + { "uda1342" }, { } }; MODULE_DEVICE_TABLE(i2c, uda1342_i2c_id); diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c index a2521e16c099..7cef43bb2a88 100644 --- a/sound/soc/codecs/wcd9335.c +++ b/sound/soc/codecs/wcd9335.c @@ -159,6 +159,8 @@ {"AMIC MUX" #id, "ADC5", "ADC5"}, \ {"AMIC MUX" #id, "ADC6", "ADC6"} +#define NUM_CODEC_DAIS 7 + enum { WCD9335_RX0 = 0, WCD9335_RX1, diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index 829bf055622a..aef82532f8cf 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -2196,18 +2196,7 @@ static int wm8904_i2c_probe(struct i2c_client *i2c) return ret; } - if (i2c->dev.of_node) { - const struct of_device_id *match; - - match = of_match_node(wm8904_of_match, i2c->dev.of_node); - if (match == NULL) - return -EINVAL; - wm8904->devtype = (uintptr_t)match->data; - } else { - const struct i2c_device_id *id = - i2c_match_id(wm8904_i2c_id, i2c); - wm8904->devtype = id->driver_data; - } + wm8904->devtype = (uintptr_t)i2c_get_match_data(i2c); i2c_set_clientdata(i2c, wm8904); wm8904->pdata = i2c->dev.platform_data; diff --git a/sound/soc/codecs/wm8985.c b/sound/soc/codecs/wm8985.c index 8606e0752a60..da00db5b0172 100644 --- a/sound/soc/codecs/wm8985.c +++ b/sound/soc/codecs/wm8985.c @@ -1166,12 +1166,10 @@ static struct spi_driver wm8985_spi_driver = { #endif #if IS_ENABLED(CONFIG_I2C) -static const struct i2c_device_id wm8985_i2c_id[]; static int wm8985_i2c_probe(struct i2c_client *i2c) { struct wm8985_priv *wm8985; - const struct i2c_device_id *id = i2c_match_id(wm8985_i2c_id, i2c); int ret; wm8985 = devm_kzalloc(&i2c->dev, sizeof *wm8985, GFP_KERNEL); @@ -1180,7 +1178,7 @@ static int wm8985_i2c_probe(struct i2c_client *i2c) i2c_set_clientdata(i2c, wm8985); - wm8985->dev_type = id->driver_data; + wm8985->dev_type = (uintptr_t)i2c_get_match_data(i2c); wm8985->regmap = devm_regmap_init_i2c(i2c, &wm8985_regmap); if (IS_ERR(wm8985->regmap)) { diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index 8e88830e8e57..c4cf3cff58de 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -6,8 +6,11 @@ comment "Common SoC Audio options for Freescale CPUs:" config SND_SOC_FSL_ASRC tristate "Asynchronous Sample Rate Converter (ASRC) module support" depends on HAS_DMA + select DMA_SHARED_BUFFER select REGMAP_MMIO select SND_SOC_GENERIC_DMAENGINE_PCM + select SND_COMPRESS_ACCEL + select SND_COMPRESS_OFFLOAD help Say Y if you want to add Asynchronous Sample Rate Converter (ASRC) support for the Freescale CPUs. @@ -29,8 +32,8 @@ config SND_SOC_FSL_SAI config SND_SOC_FSL_MQS tristate "Medium Quality Sound (MQS) module support" depends on SND_SOC_FSL_SAI + depends on IMX_SCMI_MISC_DRV || !IMX_SCMI_MISC_DRV select REGMAP_MMIO - select IMX_SCMI_MISC_DRV if IMX_SCMI_MISC_EXT !=n help Say Y if you want to add Medium Quality Sound (MQS) support for the Freescale CPUs. diff --git a/sound/soc/fsl/Makefile b/sound/soc/fsl/Makefile index ad97244b5cc3..d656a9ab54e3 100644 --- a/sound/soc/fsl/Makefile +++ b/sound/soc/fsl/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_SND_SOC_P1022_RDK) += snd-soc-p1022-rdk.o # Freescale SSI/DMA/SAI/SPDIF Support snd-soc-fsl-audmix-y := fsl_audmix.o snd-soc-fsl-asoc-card-y := fsl-asoc-card.o -snd-soc-fsl-asrc-y := fsl_asrc.o fsl_asrc_dma.o +snd-soc-fsl-asrc-y := fsl_asrc.o fsl_asrc_dma.o fsl_asrc_m2m.o snd-soc-fsl-lpc3xxx-y := lpc3xxx-pcm.o lpc3xxx-i2s.o snd-soc-fsl-sai-y := fsl_sai.o snd-soc-fsl-ssi-y := fsl_ssi.o diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index 02e1594e8223..2bad9cb1daaf 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -932,7 +932,7 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) if (!asrc_pdev) priv->card.num_dapm_routes /= 2; - if (of_property_read_bool(np, "audio-routing")) { + if (of_property_present(np, "audio-routing")) { ret = snd_soc_of_parse_audio_routing(&priv->card, "audio-routing"); if (ret) { dev_err(&pdev->dev, "failed to parse audio-routing: %d\n", ret); diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c index bd5c46d763c0..677529916dc0 100644 --- a/sound/soc/fsl/fsl_asrc.c +++ b/sound/soc/fsl/fsl_asrc.c @@ -1063,6 +1063,139 @@ static int fsl_asrc_get_fifo_addr(u8 dir, enum asrc_pair_index index) return REG_ASRDx(dir, index); } +/* Get sample numbers in FIFO */ +static unsigned int fsl_asrc_get_output_fifo_size(struct fsl_asrc_pair *pair) +{ + struct fsl_asrc *asrc = pair->asrc; + enum asrc_pair_index index = pair->index; + u32 val; + + regmap_read(asrc->regmap, REG_ASRFST(index), &val); + + val &= ASRFSTi_OUTPUT_FIFO_MASK; + + return val >> ASRFSTi_OUTPUT_FIFO_SHIFT; +} + +static int fsl_asrc_m2m_prepare(struct fsl_asrc_pair *pair) +{ + struct fsl_asrc_pair_priv *pair_priv = pair->private; + struct fsl_asrc *asrc = pair->asrc; + struct device *dev = &asrc->pdev->dev; + struct asrc_config config; + int ret; + + /* fill config */ + config.pair = pair->index; + config.channel_num = pair->channels; + config.input_sample_rate = pair->rate[IN]; + config.output_sample_rate = pair->rate[OUT]; + config.input_format = pair->sample_format[IN]; + config.output_format = pair->sample_format[OUT]; + config.inclk = INCLK_NONE; + config.outclk = OUTCLK_ASRCK1_CLK; + + pair_priv->config = &config; + ret = fsl_asrc_config_pair(pair, true); + if (ret) { + dev_err(dev, "failed to config pair: %d\n", ret); + return ret; + } + + pair->first_convert = 1; + + return 0; +} + +static int fsl_asrc_m2m_start(struct fsl_asrc_pair *pair) +{ + if (pair->first_convert) { + fsl_asrc_start_pair(pair); + pair->first_convert = 0; + } + /* + * Clear DMA request during the stall state of ASRC: + * During STALL state, the remaining in input fifo would never be + * smaller than the input threshold while the output fifo would not + * be bigger than output one. Thus the DMA request would be cleared. + */ + fsl_asrc_set_watermarks(pair, ASRC_FIFO_THRESHOLD_MIN, + ASRC_FIFO_THRESHOLD_MAX); + + /* Update the real input threshold to raise DMA request */ + fsl_asrc_set_watermarks(pair, ASRC_M2M_INPUTFIFO_WML, + ASRC_M2M_OUTPUTFIFO_WML); + + return 0; +} + +static int fsl_asrc_m2m_stop(struct fsl_asrc_pair *pair) +{ + if (!pair->first_convert) { + fsl_asrc_stop_pair(pair); + pair->first_convert = 1; + } + + return 0; +} + +/* calculate capture data length according to output data length and sample rate */ +static int fsl_asrc_m2m_calc_out_len(struct fsl_asrc_pair *pair, int input_buffer_length) +{ + unsigned int in_width, out_width; + unsigned int channels = pair->channels; + unsigned int in_samples, out_samples; + unsigned int out_length; + + in_width = snd_pcm_format_physical_width(pair->sample_format[IN]) / 8; + out_width = snd_pcm_format_physical_width(pair->sample_format[OUT]) / 8; + + in_samples = input_buffer_length / in_width / channels; + out_samples = pair->rate[OUT] * in_samples / pair->rate[IN]; + out_length = (out_samples - ASRC_OUTPUT_LAST_SAMPLE) * out_width * channels; + + return out_length; +} + +static int fsl_asrc_m2m_get_maxburst(u8 dir, struct fsl_asrc_pair *pair) +{ + struct fsl_asrc *asrc = pair->asrc; + struct fsl_asrc_priv *asrc_priv = asrc->private; + int wml = (dir == IN) ? ASRC_M2M_INPUTFIFO_WML : ASRC_M2M_OUTPUTFIFO_WML; + + if (!asrc_priv->soc->use_edma) + return wml * pair->channels; + else + return 1; +} + +static int fsl_asrc_m2m_get_cap(struct fsl_asrc_m2m_cap *cap) +{ + cap->fmt_in = FSL_ASRC_FORMATS; + cap->fmt_out = FSL_ASRC_FORMATS | SNDRV_PCM_FMTBIT_S8; + + cap->rate_in = supported_asrc_rate; + cap->rate_in_count = ARRAY_SIZE(supported_asrc_rate); + cap->rate_out = supported_asrc_rate; + cap->rate_out_count = ARRAY_SIZE(supported_asrc_rate); + cap->chan_min = 1; + cap->chan_max = 10; + + return 0; +} + +static int fsl_asrc_m2m_pair_resume(struct fsl_asrc_pair *pair) +{ + struct fsl_asrc *asrc = pair->asrc; + int i; + + for (i = 0; i < pair->channels * 4; i++) + regmap_write(asrc->regmap, REG_ASRDI(pair->index), 0); + + pair->first_convert = 1; + return 0; +} + static int fsl_asrc_runtime_resume(struct device *dev); static int fsl_asrc_runtime_suspend(struct device *dev); @@ -1147,6 +1280,15 @@ static int fsl_asrc_probe(struct platform_device *pdev) asrc->get_fifo_addr = fsl_asrc_get_fifo_addr; asrc->pair_priv_size = sizeof(struct fsl_asrc_pair_priv); + asrc->m2m_prepare = fsl_asrc_m2m_prepare; + asrc->m2m_start = fsl_asrc_m2m_start; + asrc->m2m_stop = fsl_asrc_m2m_stop; + asrc->get_output_fifo_size = fsl_asrc_get_output_fifo_size; + asrc->m2m_calc_out_len = fsl_asrc_m2m_calc_out_len; + asrc->m2m_get_maxburst = fsl_asrc_m2m_get_maxburst; + asrc->m2m_pair_resume = fsl_asrc_m2m_pair_resume; + asrc->m2m_get_cap = fsl_asrc_m2m_get_cap; + if (of_device_is_compatible(np, "fsl,imx35-asrc")) { asrc_priv->clk_map[IN] = input_clk_map_imx35; asrc_priv->clk_map[OUT] = output_clk_map_imx35; @@ -1242,6 +1384,12 @@ static int fsl_asrc_probe(struct platform_device *pdev) goto err_pm_get_sync; } + ret = fsl_asrc_m2m_init(asrc); + if (ret) { + dev_err(&pdev->dev, "failed to init m2m device %d\n", ret); + return ret; + } + return 0; err_pm_get_sync: @@ -1254,6 +1402,10 @@ err_pm_disable: static void fsl_asrc_remove(struct platform_device *pdev) { + struct fsl_asrc *asrc = dev_get_drvdata(&pdev->dev); + + fsl_asrc_m2m_exit(asrc); + pm_runtime_disable(&pdev->dev); if (!pm_runtime_status_suspended(&pdev->dev)) fsl_asrc_runtime_suspend(&pdev->dev); @@ -1355,10 +1507,29 @@ static int fsl_asrc_runtime_suspend(struct device *dev) return 0; } +static int fsl_asrc_suspend(struct device *dev) +{ + struct fsl_asrc *asrc = dev_get_drvdata(dev); + int ret; + + fsl_asrc_m2m_suspend(asrc); + ret = pm_runtime_force_suspend(dev); + return ret; +} + +static int fsl_asrc_resume(struct device *dev) +{ + struct fsl_asrc *asrc = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + fsl_asrc_m2m_resume(asrc); + return ret; +} + static const struct dev_pm_ops fsl_asrc_pm = { - SET_RUNTIME_PM_OPS(fsl_asrc_runtime_suspend, fsl_asrc_runtime_resume, NULL) - SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + RUNTIME_PM_OPS(fsl_asrc_runtime_suspend, fsl_asrc_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(fsl_asrc_suspend, fsl_asrc_resume) }; static const struct fsl_asrc_soc_data fsl_asrc_imx35_data = { @@ -1396,7 +1567,7 @@ static struct platform_driver fsl_asrc_driver = { .driver = { .name = "fsl-asrc", .of_match_table = fsl_asrc_ids, - .pm = &fsl_asrc_pm, + .pm = pm_ptr(&fsl_asrc_pm), }, }; module_platform_driver(fsl_asrc_driver); diff --git a/sound/soc/fsl/fsl_asrc.h b/sound/soc/fsl/fsl_asrc.h index 86d2422ad606..1c492eb237f5 100644 --- a/sound/soc/fsl/fsl_asrc.h +++ b/sound/soc/fsl/fsl_asrc.h @@ -12,6 +12,8 @@ #include "fsl_asrc_common.h" +#define ASRC_M2M_INPUTFIFO_WML 0x4 +#define ASRC_M2M_OUTPUTFIFO_WML 0x2 #define ASRC_DMA_BUFFER_NUM 2 #define ASRC_INPUTFIFO_THRESHOLD 32 #define ASRC_OUTPUTFIFO_THRESHOLD 32 diff --git a/sound/soc/fsl/fsl_asrc_common.h b/sound/soc/fsl/fsl_asrc_common.h index 7e1c13ca37f1..0cd595b0f629 100644 --- a/sound/soc/fsl/fsl_asrc_common.h +++ b/sound/soc/fsl/fsl_asrc_common.h @@ -21,6 +21,26 @@ enum asrc_pair_index { #define PAIR_CTX_NUM 0x4 +/** + * struct fsl_asrc_m2m_cap - capability data + * @fmt_in: input sample format + * @fmt_out: output sample format + * @chan_min: minimum channel number + * @chan_max: maximum channel number + * @rate_in: minimum rate + * @rate_out: maximum rete + */ +struct fsl_asrc_m2m_cap { + u64 fmt_in; + u64 fmt_out; + int chan_min; + int chan_max; + const unsigned int *rate_in; + int rate_in_count; + const unsigned int *rate_out; + int rate_out_count; +}; + /** * fsl_asrc_pair: ASRC Pair common data * @@ -34,6 +54,14 @@ enum asrc_pair_index { * @pos: hardware pointer position * @req_dma_chan: flag to release dev_to_dev chan * @private: pair private area + * @complete: dma task complete + * @sample_format: format of m2m + * @rate: rate of m2m + * @buf_len: buffer length of m2m + * @dma_buffer: buffer pointers + * @first_convert: start of conversion + * @ratio_mod_flag: flag for new ratio modifier + * @ratio_mod: ratio modification */ struct fsl_asrc_pair { struct fsl_asrc *asrc; @@ -49,6 +77,16 @@ struct fsl_asrc_pair { bool req_dma_chan; void *private; + + /* used for m2m */ + struct completion complete[2]; + snd_pcm_format_t sample_format[2]; + unsigned int rate[2]; + unsigned int buf_len[2]; + struct snd_dma_buffer dma_buffer[2]; + unsigned int first_convert; + bool ratio_mod_flag; + unsigned int ratio_mod; }; /** @@ -62,6 +100,7 @@ struct fsl_asrc_pair { * @mem_clk: clock source to access register * @ipg_clk: clock source to drive peripheral * @spba_clk: SPBA clock (optional, depending on SoC design) + * @card: compress sound card * @lock: spin lock for resource protection * @pair: pair pointers * @channel_avail: non-occupied channel numbers @@ -72,6 +111,17 @@ struct fsl_asrc_pair { * @request_pair: function pointer * @release_pair: function pointer * @get_fifo_addr: function pointer + * @m2m_get_cap: function pointer + * @m2m_prepare: function pointer + * @m2m_start: function pointer + * @m2m_unprepare: function pointer + * @m2m_stop: function pointer + * @m2m_calc_out_len: function pointer + * @m2m_get_maxburst: function pointer + * @m2m_pair_suspend: function pointer + * @m2m_pair_resume: function pointer + * @m2m_set_ratio_mod: function pointer + * @get_output_fifo_size: function pointer * @pair_priv_size: size of pair private struct. * @private: private data structure */ @@ -84,6 +134,7 @@ struct fsl_asrc { struct clk *mem_clk; struct clk *ipg_clk; struct clk *spba_clk; + struct snd_card *card; spinlock_t lock; /* spin lock for resource protection */ struct fsl_asrc_pair *pair[PAIR_CTX_NUM]; @@ -97,6 +148,20 @@ struct fsl_asrc { int (*request_pair)(int channels, struct fsl_asrc_pair *pair); void (*release_pair)(struct fsl_asrc_pair *pair); int (*get_fifo_addr)(u8 dir, enum asrc_pair_index index); + int (*m2m_get_cap)(struct fsl_asrc_m2m_cap *cap); + + int (*m2m_prepare)(struct fsl_asrc_pair *pair); + int (*m2m_start)(struct fsl_asrc_pair *pair); + int (*m2m_unprepare)(struct fsl_asrc_pair *pair); + int (*m2m_stop)(struct fsl_asrc_pair *pair); + + int (*m2m_calc_out_len)(struct fsl_asrc_pair *pair, int input_buffer_length); + int (*m2m_get_maxburst)(u8 dir, struct fsl_asrc_pair *pair); + int (*m2m_pair_suspend)(struct fsl_asrc_pair *pair); + int (*m2m_pair_resume)(struct fsl_asrc_pair *pair); + int (*m2m_set_ratio_mod)(struct fsl_asrc_pair *pair, int val); + + unsigned int (*get_output_fifo_size)(struct fsl_asrc_pair *pair); size_t pair_priv_size; void *private; @@ -105,4 +170,9 @@ struct fsl_asrc { #define DRV_NAME "fsl-asrc-dai" extern struct snd_soc_component_driver fsl_asrc_component; +int fsl_asrc_m2m_init(struct fsl_asrc *asrc); +void fsl_asrc_m2m_exit(struct fsl_asrc *asrc); +int fsl_asrc_m2m_resume(struct fsl_asrc *asrc); +int fsl_asrc_m2m_suspend(struct fsl_asrc *asrc); + #endif /* _FSL_ASRC_COMMON_H */ diff --git a/sound/soc/fsl/fsl_asrc_m2m.c b/sound/soc/fsl/fsl_asrc_m2m.c new file mode 100644 index 000000000000..f46881f71e43 --- /dev/null +++ b/sound/soc/fsl/fsl_asrc_m2m.c @@ -0,0 +1,729 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Copyright (C) 2014-2016 Freescale Semiconductor, Inc. +// Copyright (C) 2019-2024 NXP +// +// Freescale ASRC Memory to Memory (M2M) driver + +#include <linux/dma/imx-dma.h> +#include <linux/dma-buf.h> +#include <linux/dma-mapping.h> +#include <linux/pm_runtime.h> +#include <sound/asound.h> +#include <sound/dmaengine_pcm.h> +#include <sound/initval.h> + +#include "fsl_asrc_common.h" + +#define DIR_STR(dir) (dir) == IN ? "in" : "out" + +#define ASRC_xPUT_DMA_CALLBACK(dir) \ + (((dir) == IN) ? asrc_input_dma_callback \ + : asrc_output_dma_callback) + +/* Maximum output and capture buffer size */ +#define ASRC_M2M_BUFFER_SIZE (512 * 1024) + +/* Maximum output and capture period size */ +#define ASRC_M2M_PERIOD_SIZE (48 * 1024) + +/* dma complete callback */ +static void asrc_input_dma_callback(void *data) +{ + struct fsl_asrc_pair *pair = (struct fsl_asrc_pair *)data; + + complete(&pair->complete[IN]); +} + +/* dma complete callback */ +static void asrc_output_dma_callback(void *data) +{ + struct fsl_asrc_pair *pair = (struct fsl_asrc_pair *)data; + + complete(&pair->complete[OUT]); +} + +/** + *asrc_read_last_fifo: read all the remaining data from FIFO + *@pair: Structure pointer of fsl_asrc_pair + *@dma_vaddr: virtual address of capture buffer + *@length: payload length of capture buffer + */ +static void asrc_read_last_fifo(struct fsl_asrc_pair *pair, void *dma_vaddr, u32 *length) +{ + struct fsl_asrc *asrc = pair->asrc; + enum asrc_pair_index index = pair->index; + u32 i, reg, size, t_size = 0, width; + u32 *reg32 = NULL; + u16 *reg16 = NULL; + u8 *reg24 = NULL; + + width = snd_pcm_format_physical_width(pair->sample_format[OUT]); + if (width == 32) + reg32 = dma_vaddr + *length; + else if (width == 16) + reg16 = dma_vaddr + *length; + else + reg24 = dma_vaddr + *length; +retry: + size = asrc->get_output_fifo_size(pair); + if (size + *length > ASRC_M2M_BUFFER_SIZE) + goto end; + + for (i = 0; i < size * pair->channels; i++) { + regmap_read(asrc->regmap, asrc->get_fifo_addr(OUT, index), ®); + if (reg32) { + *reg32++ = reg; + } else if (reg16) { + *reg16++ = (u16)reg; + } else { + *reg24++ = (u8)reg; + *reg24++ = (u8)(reg >> 8); + *reg24++ = (u8)(reg >> 16); + } + } + t_size += size; + + /* In case there is data left in FIFO */ + if (size) + goto retry; +end: + /* Update payload length */ + if (reg32) + *length += t_size * pair->channels * 4; + else if (reg16) + *length += t_size * pair->channels * 2; + else + *length += t_size * pair->channels * 3; +} + +/* config dma channel */ +static int asrc_dmaconfig(struct fsl_asrc_pair *pair, + struct dma_chan *chan, + u32 dma_addr, dma_addr_t buf_addr, u32 buf_len, + int dir, int width) +{ + struct fsl_asrc *asrc = pair->asrc; + struct device *dev = &asrc->pdev->dev; + struct dma_slave_config slave_config; + enum dma_slave_buswidth buswidth; + unsigned int sg_len, max_period_size; + struct scatterlist *sg; + int ret, i; + + switch (width) { + case 8: + buswidth = DMA_SLAVE_BUSWIDTH_1_BYTE; + break; + case 16: + buswidth = DMA_SLAVE_BUSWIDTH_2_BYTES; + break; + case 24: + buswidth = DMA_SLAVE_BUSWIDTH_3_BYTES; + break; + case 32: + buswidth = DMA_SLAVE_BUSWIDTH_4_BYTES; + break; + default: + dev_err(dev, "invalid word width\n"); + return -EINVAL; + } + + memset(&slave_config, 0, sizeof(slave_config)); + if (dir == IN) { + slave_config.direction = DMA_MEM_TO_DEV; + slave_config.dst_addr = dma_addr; + slave_config.dst_addr_width = buswidth; + slave_config.dst_maxburst = asrc->m2m_get_maxburst(IN, pair); + } else { + slave_config.direction = DMA_DEV_TO_MEM; + slave_config.src_addr = dma_addr; + slave_config.src_addr_width = buswidth; + slave_config.src_maxburst = asrc->m2m_get_maxburst(OUT, pair); + } + + ret = dmaengine_slave_config(chan, &slave_config); + if (ret) { + dev_err(dev, "failed to config dmaengine for %s task: %d\n", + DIR_STR(dir), ret); + return -EINVAL; + } + + max_period_size = rounddown(ASRC_M2M_PERIOD_SIZE, width * pair->channels / 8); + /* scatter gather mode */ + sg_len = buf_len / max_period_size; + if (buf_len % max_period_size) + sg_len += 1; + + sg = kmalloc_array(sg_len, sizeof(*sg), GFP_KERNEL); + if (!sg) + return -ENOMEM; + + sg_init_table(sg, sg_len); + for (i = 0; i < (sg_len - 1); i++) { + sg_dma_address(&sg[i]) = buf_addr + i * max_period_size; + sg_dma_len(&sg[i]) = max_period_size; + } + sg_dma_address(&sg[i]) = buf_addr + i * max_period_size; + sg_dma_len(&sg[i]) = buf_len - i * max_period_size; + + pair->desc[dir] = dmaengine_prep_slave_sg(chan, sg, sg_len, + slave_config.direction, + DMA_PREP_INTERRUPT); + kfree(sg); + if (!pair->desc[dir]) { + dev_err(dev, "failed to prepare dmaengine for %s task\n", DIR_STR(dir)); + return -EINVAL; + } + + pair->desc[dir]->callback = ASRC_xPUT_DMA_CALLBACK(dir); + pair->desc[dir]->callback_param = pair; + + return 0; +} + +/* main function of converter */ +static int asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_task_runtime *task) +{ + struct fsl_asrc *asrc = pair->asrc; + struct device *dev = &asrc->pdev->dev; + enum asrc_pair_index index = pair->index; + struct snd_dma_buffer *src_buf, *dst_buf; + unsigned int in_buf_len; + unsigned int out_dma_len; + unsigned int width; + u32 fifo_addr; + int ret = 0; + + /* set ratio mod */ + if (asrc->m2m_set_ratio_mod) { + if (pair->ratio_mod_flag) { + asrc->m2m_set_ratio_mod(pair, pair->ratio_mod); + pair->ratio_mod_flag = false; + } + } + + src_buf = &pair->dma_buffer[IN]; + dst_buf = &pair->dma_buffer[OUT]; + + width = snd_pcm_format_physical_width(pair->sample_format[IN]); + fifo_addr = asrc->paddr + asrc->get_fifo_addr(IN, index); + + in_buf_len = task->input_size; + + if (in_buf_len < width * pair->channels / 8 || + in_buf_len > ASRC_M2M_BUFFER_SIZE || + in_buf_len % (width * pair->channels / 8)) { + dev_err(dev, "out buffer size is error: [%d]\n", in_buf_len); + ret = -EINVAL; + goto end; + } + + /* dma config for output dma channel */ + ret = asrc_dmaconfig(pair, + pair->dma_chan[IN], + fifo_addr, + src_buf->addr, + in_buf_len, IN, width); + if (ret) { + dev_err(dev, "out dma config error\n"); + goto end; + } + + width = snd_pcm_format_physical_width(pair->sample_format[OUT]); + fifo_addr = asrc->paddr + asrc->get_fifo_addr(OUT, index); + out_dma_len = asrc->m2m_calc_out_len(pair, in_buf_len); + if (out_dma_len > 0 && out_dma_len <= ASRC_M2M_BUFFER_SIZE) { + /* dma config for capture dma channel */ + ret = asrc_dmaconfig(pair, + pair->dma_chan[OUT], + fifo_addr, + dst_buf->addr, + out_dma_len, OUT, width); + if (ret) { + dev_err(dev, "cap dma config error\n"); + goto end; + } + } else if (out_dma_len > ASRC_M2M_BUFFER_SIZE) { + dev_err(dev, "cap buffer size error\n"); + ret = -EINVAL; + goto end; + } + + reinit_completion(&pair->complete[IN]); + reinit_completion(&pair->complete[OUT]); + + /* Submit DMA request */ + dmaengine_submit(pair->desc[IN]); + dma_async_issue_pending(pair->desc[IN]->chan); + if (out_dma_len > 0) { + dmaengine_submit(pair->desc[OUT]); + dma_async_issue_pending(pair->desc[OUT]->chan); + } + + asrc->m2m_start(pair); + + if (!wait_for_completion_interruptible_timeout(&pair->complete[IN], 10 * HZ)) { + dev_err(dev, "out DMA task timeout\n"); + ret = -ETIMEDOUT; + goto end; + } + + if (out_dma_len > 0) { + if (!wait_for_completion_interruptible_timeout(&pair->complete[OUT], 10 * HZ)) { + dev_err(dev, "cap DMA task timeout\n"); + ret = -ETIMEDOUT; + goto end; + } + } + + /* read the last words from FIFO */ + asrc_read_last_fifo(pair, dst_buf->area, &out_dma_len); + /* update payload length for capture */ + task->output_size = out_dma_len; +end: + return ret; +} + +static int fsl_asrc_m2m_comp_open(struct snd_compr_stream *stream) +{ + struct fsl_asrc *asrc = stream->private_data; + struct snd_compr_runtime *runtime = stream->runtime; + struct device *dev = &asrc->pdev->dev; + struct fsl_asrc_pair *pair; + int size, ret; + + pair = kzalloc(sizeof(*pair) + asrc->pair_priv_size, GFP_KERNEL); + if (!pair) + return -ENOMEM; + + pair->private = (void *)pair + sizeof(struct fsl_asrc_pair); + pair->asrc = asrc; + + init_completion(&pair->complete[IN]); + init_completion(&pair->complete[OUT]); + + runtime->private_data = pair; + + size = ASRC_M2M_BUFFER_SIZE; + ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, dev, size, &pair->dma_buffer[IN]); + if (ret) + goto error_alloc_in_buf; + + ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, dev, size, &pair->dma_buffer[OUT]); + if (ret) + goto error_alloc_out_buf; + + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "Failed to power up asrc\n"); + goto err_pm_runtime; + } + + return 0; + +err_pm_runtime: + snd_dma_free_pages(&pair->dma_buffer[OUT]); +error_alloc_out_buf: + snd_dma_free_pages(&pair->dma_buffer[IN]); +error_alloc_in_buf: + kfree(pair); + return ret; +} + +static int fsl_asrc_m2m_comp_release(struct snd_compr_stream *stream) +{ + struct fsl_asrc *asrc = stream->private_data; + struct snd_compr_runtime *runtime = stream->runtime; + struct fsl_asrc_pair *pair = runtime->private_data; + struct device *dev = &asrc->pdev->dev; + + pm_runtime_put_sync(dev); + + snd_dma_free_pages(&pair->dma_buffer[IN]); + snd_dma_free_pages(&pair->dma_buffer[OUT]); + + kfree(runtime->private_data); + + return 0; +} + +static int fsl_asrc_m2m_comp_set_params(struct snd_compr_stream *stream, + struct snd_compr_params *params) +{ + struct fsl_asrc *asrc = stream->private_data; + struct snd_compr_runtime *runtime = stream->runtime; + struct fsl_asrc_pair *pair = runtime->private_data; + struct fsl_asrc_m2m_cap cap; + int ret, i; + + ret = asrc->m2m_get_cap(&cap); + if (ret) + return -EINVAL; + + if (pcm_format_to_bits((__force snd_pcm_format_t)params->codec.format) & cap.fmt_in) + pair->sample_format[IN] = (__force snd_pcm_format_t)params->codec.format; + else + return -EINVAL; + + if (pcm_format_to_bits((__force snd_pcm_format_t)params->codec.pcm_format) & cap.fmt_out) + pair->sample_format[OUT] = (__force snd_pcm_format_t)params->codec.pcm_format; + else + return -EINVAL; + + /* check input rate is in scope */ + for (i = 0; i < cap.rate_in_count; i++) + if (params->codec.sample_rate == cap.rate_in[i]) { + pair->rate[IN] = params->codec.sample_rate; + break; + } + if (i == cap.rate_in_count) + return -EINVAL; + + /* check output rate is in scope */ + for (i = 0; i < cap.rate_out_count; i++) + if (params->codec.options.src_d.out_sample_rate == cap.rate_out[i]) { + pair->rate[OUT] = params->codec.options.src_d.out_sample_rate; + break; + } + if (i == cap.rate_out_count) + return -EINVAL; + + if (params->codec.ch_in != params->codec.ch_out || + params->codec.ch_in < cap.chan_min || + params->codec.ch_in > cap.chan_max) + return -EINVAL; + + pair->channels = params->codec.ch_in; + pair->buf_len[IN] = params->buffer.fragment_size; + pair->buf_len[OUT] = params->buffer.fragment_size; + + return 0; +} + +static int fsl_asrc_m2m_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma) +{ + struct snd_dma_buffer *dmab = dmabuf->priv; + + return snd_dma_buffer_mmap(dmab, vma); +} + +static struct sg_table *fsl_asrc_m2m_map_dma_buf(struct dma_buf_attachment *attachment, + enum dma_data_direction direction) +{ + struct snd_dma_buffer *dmab = attachment->dmabuf->priv; + struct sg_table *sgt; + + sgt = kmalloc(sizeof(*sgt), GFP_KERNEL); + if (!sgt) + return NULL; + + if (dma_get_sgtable(attachment->dev, sgt, dmab->area, dmab->addr, dmab->bytes) < 0) + goto free; + + if (dma_map_sgtable(attachment->dev, sgt, direction, 0)) + goto free; + + return sgt; + +free: + sg_free_table(sgt); + kfree(sgt); + return NULL; +} + +static void fsl_asrc_m2m_unmap_dma_buf(struct dma_buf_attachment *attachment, + struct sg_table *table, + enum dma_data_direction direction) +{ + dma_unmap_sgtable(attachment->dev, table, direction, 0); +} + +static void fsl_asrc_m2m_release(struct dma_buf *dmabuf) +{ + /* buffer is released by fsl_asrc_m2m_comp_release() */ +} + +static const struct dma_buf_ops fsl_asrc_m2m_dma_buf_ops = { + .mmap = fsl_asrc_m2m_mmap, + .map_dma_buf = fsl_asrc_m2m_map_dma_buf, + .unmap_dma_buf = fsl_asrc_m2m_unmap_dma_buf, + .release = fsl_asrc_m2m_release, +}; + +static int fsl_asrc_m2m_comp_task_create(struct snd_compr_stream *stream, + struct snd_compr_task_runtime *task) +{ + DEFINE_DMA_BUF_EXPORT_INFO(exp_info_in); + DEFINE_DMA_BUF_EXPORT_INFO(exp_info_out); + struct fsl_asrc *asrc = stream->private_data; + struct snd_compr_runtime *runtime = stream->runtime; + struct fsl_asrc_pair *pair = runtime->private_data; + struct device *dev = &asrc->pdev->dev; + int ret; + + exp_info_in.ops = &fsl_asrc_m2m_dma_buf_ops; + exp_info_in.size = ASRC_M2M_BUFFER_SIZE; + exp_info_in.flags = O_RDWR; + exp_info_in.priv = &pair->dma_buffer[IN]; + task->input = dma_buf_export(&exp_info_in); + if (IS_ERR(task->input)) { + ret = PTR_ERR(task->input); + return ret; + } + + exp_info_out.ops = &fsl_asrc_m2m_dma_buf_ops; + exp_info_out.size = ASRC_M2M_BUFFER_SIZE; + exp_info_out.flags = O_RDWR; + exp_info_out.priv = &pair->dma_buffer[OUT]; + task->output = dma_buf_export(&exp_info_out); + if (IS_ERR(task->output)) { + ret = PTR_ERR(task->output); + return ret; + } + + /* Request asrc pair/context */ + ret = asrc->request_pair(pair->channels, pair); + if (ret) { + dev_err(dev, "failed to request pair: %d\n", ret); + goto err_request_pair; + } + + ret = asrc->m2m_prepare(pair); + if (ret) { + dev_err(dev, "failed to start pair part one: %d\n", ret); + goto err_start_part_one; + } + + /* Request dma channels */ + pair->dma_chan[IN] = asrc->get_dma_channel(pair, IN); + if (!pair->dma_chan[IN]) { + dev_err(dev, "[ctx%d] failed to get input DMA channel\n", pair->index); + ret = -EBUSY; + goto err_dma_channel_in; + } + + pair->dma_chan[OUT] = asrc->get_dma_channel(pair, OUT); + if (!pair->dma_chan[OUT]) { + dev_err(dev, "[ctx%d] failed to get output DMA channel\n", pair->index); + ret = -EBUSY; + goto err_dma_channel_out; + } + + return 0; + +err_dma_channel_out: + dma_release_channel(pair->dma_chan[IN]); +err_dma_channel_in: + if (asrc->m2m_unprepare) + asrc->m2m_unprepare(pair); +err_start_part_one: + asrc->release_pair(pair); +err_request_pair: + return ret; +} + +static int fsl_asrc_m2m_comp_task_start(struct snd_compr_stream *stream, + struct snd_compr_task_runtime *task) +{ + struct snd_compr_runtime *runtime = stream->runtime; + struct fsl_asrc_pair *pair = runtime->private_data; + + return asrc_m2m_device_run(pair, task); +} + +static int fsl_asrc_m2m_comp_task_stop(struct snd_compr_stream *stream, + struct snd_compr_task_runtime *task) +{ + return 0; +} + +static int fsl_asrc_m2m_comp_task_free(struct snd_compr_stream *stream, + struct snd_compr_task_runtime *task) +{ + struct fsl_asrc *asrc = stream->private_data; + struct snd_compr_runtime *runtime = stream->runtime; + struct fsl_asrc_pair *pair = runtime->private_data; + + /* Stop & release pair/context */ + if (asrc->m2m_stop) + asrc->m2m_stop(pair); + + if (asrc->m2m_unprepare) + asrc->m2m_unprepare(pair); + asrc->release_pair(pair); + + /* Release dma channel */ + if (pair->dma_chan[IN]) + dma_release_channel(pair->dma_chan[IN]); + if (pair->dma_chan[OUT]) + dma_release_channel(pair->dma_chan[OUT]); + + return 0; +} + +static int fsl_asrc_m2m_get_caps(struct snd_compr_stream *cstream, + struct snd_compr_caps *caps) +{ + caps->num_codecs = 1; + caps->min_fragment_size = 4096; + caps->max_fragment_size = 4096; + caps->min_fragments = 1; + caps->max_fragments = 1; + caps->codecs[0] = SND_AUDIOCODEC_PCM; + + return 0; +} + +static int fsl_asrc_m2m_fill_codec_caps(struct fsl_asrc *asrc, + struct snd_compr_codec_caps *codec) +{ + struct fsl_asrc_m2m_cap cap; + snd_pcm_format_t k; + int j = 0; + int ret; + + ret = asrc->m2m_get_cap(&cap); + if (ret) + return -EINVAL; + + pcm_for_each_format(k) { + if (pcm_format_to_bits(k) & cap.fmt_in) { + codec->descriptor[j].max_ch = cap.chan_max; + memcpy(codec->descriptor[j].sample_rates, + cap.rate_in, + cap.rate_in_count * sizeof(__u32)); + codec->descriptor[j].num_sample_rates = cap.rate_in_count; + codec->descriptor[j].formats = (__force __u32)k; + codec->descriptor[j].pcm_formats = cap.fmt_out; + codec->descriptor[j].src.out_sample_rate_min = cap.rate_out[0]; + codec->descriptor[j].src.out_sample_rate_max = + cap.rate_out[cap.rate_out_count - 1]; + j++; + } + } + + codec->codec = SND_AUDIOCODEC_PCM; + codec->num_descriptors = j; + return 0; +} + +static int fsl_asrc_m2m_get_codec_caps(struct snd_compr_stream *stream, + struct snd_compr_codec_caps *codec) +{ + struct fsl_asrc *asrc = stream->private_data; + + return fsl_asrc_m2m_fill_codec_caps(asrc, codec); +} + +static struct snd_compr_ops fsl_asrc_m2m_compr_ops = { + .open = fsl_asrc_m2m_comp_open, + .free = fsl_asrc_m2m_comp_release, + .set_params = fsl_asrc_m2m_comp_set_params, + .get_caps = fsl_asrc_m2m_get_caps, + .get_codec_caps = fsl_asrc_m2m_get_codec_caps, + .task_create = fsl_asrc_m2m_comp_task_create, + .task_start = fsl_asrc_m2m_comp_task_start, + .task_stop = fsl_asrc_m2m_comp_task_stop, + .task_free = fsl_asrc_m2m_comp_task_free, +}; + +int fsl_asrc_m2m_suspend(struct fsl_asrc *asrc) +{ + struct fsl_asrc_pair *pair; + int i; + + for (i = 0; i < PAIR_CTX_NUM; i++) { + pair = asrc->pair[i]; + if (!pair || !pair->dma_buffer[IN].area || !pair->dma_buffer[OUT].area) + continue; + if (!completion_done(&pair->complete[IN])) { + if (pair->dma_chan[IN]) + dmaengine_terminate_all(pair->dma_chan[IN]); + asrc_input_dma_callback((void *)pair); + } + if (!completion_done(&pair->complete[OUT])) { + if (pair->dma_chan[OUT]) + dmaengine_terminate_all(pair->dma_chan[OUT]); + asrc_output_dma_callback((void *)pair); + } + + if (asrc->m2m_pair_suspend) + asrc->m2m_pair_suspend(pair); + } + + return 0; +} +EXPORT_SYMBOL_GPL(fsl_asrc_m2m_suspend); + +int fsl_asrc_m2m_resume(struct fsl_asrc *asrc) +{ + struct fsl_asrc_pair *pair; + int i; + + for (i = 0; i < PAIR_CTX_NUM; i++) { + pair = asrc->pair[i]; + if (!pair) + continue; + if (asrc->m2m_pair_resume) + asrc->m2m_pair_resume(pair); + } + + return 0; +} +EXPORT_SYMBOL_GPL(fsl_asrc_m2m_resume); + +int fsl_asrc_m2m_init(struct fsl_asrc *asrc) +{ + struct device *dev = &asrc->pdev->dev; + struct snd_card *card; + struct snd_compr *compr; + int ret; + + ret = snd_card_new(dev, SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1, + THIS_MODULE, 0, &card); + if (ret < 0) + return ret; + + strscpy(card->driver, "fsl-asrc-m2m", sizeof(card->driver)); + strscpy(card->shortname, "ASRC-M2M", sizeof(card->shortname)); + strscpy(card->longname, "ASRC-M2M", sizeof(card->shortname)); + + asrc->card = card; + + compr = devm_kzalloc(dev, sizeof(*compr), GFP_KERNEL); + if (!compr) { + ret = -ENOMEM; + goto err; + } + + compr->ops = &fsl_asrc_m2m_compr_ops; + compr->private_data = asrc; + + ret = snd_compress_new(card, 0, SND_COMPRESS_ACCEL, "ASRC M2M", compr); + if (ret < 0) + goto err; + + ret = snd_card_register(card); + if (ret < 0) + goto err; + + return 0; +err: + snd_card_free(card); + return ret; +} +EXPORT_SYMBOL_GPL(fsl_asrc_m2m_init); + +void fsl_asrc_m2m_exit(struct fsl_asrc *asrc) +{ + struct snd_card *card = asrc->card; + + snd_card_free(card); +} +EXPORT_SYMBOL_GPL(fsl_asrc_m2m_exit); + +MODULE_IMPORT_NS("DMA_BUF"); +MODULE_AUTHOR("Shengjiu Wang <Shengjiu.Wang@nxp.com>"); +MODULE_DESCRIPTION("Freescale ASRC M2M driver"); +MODULE_LICENSE("GPL"); diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c index d22f0621c465..f404a39009e1 100644 --- a/sound/soc/fsl/fsl_easrc.c +++ b/sound/soc/fsl/fsl_easrc.c @@ -1861,6 +1861,224 @@ static int fsl_easrc_get_fifo_addr(u8 dir, enum asrc_pair_index index) return REG_EASRC_FIFO(dir, index); } +/* Get sample numbers in FIFO */ +static unsigned int fsl_easrc_get_output_fifo_size(struct fsl_asrc_pair *pair) +{ + struct fsl_asrc *asrc = pair->asrc; + enum asrc_pair_index index = pair->index; + u32 val; + + regmap_read(asrc->regmap, REG_EASRC_SFS(index), &val); + val &= EASRC_SFS_NSGO_MASK; + + return val >> EASRC_SFS_NSGO_SHIFT; +} + +static int fsl_easrc_m2m_prepare(struct fsl_asrc_pair *pair) +{ + struct fsl_easrc_ctx_priv *ctx_priv = pair->private; + struct fsl_asrc *asrc = pair->asrc; + struct device *dev = &asrc->pdev->dev; + int ret; + + ctx_priv->in_params.sample_rate = pair->rate[IN]; + ctx_priv->in_params.sample_format = pair->sample_format[IN]; + ctx_priv->out_params.sample_rate = pair->rate[OUT]; + ctx_priv->out_params.sample_format = pair->sample_format[OUT]; + + ctx_priv->in_params.fifo_wtmk = FSL_EASRC_INPUTFIFO_WML; + ctx_priv->out_params.fifo_wtmk = FSL_EASRC_OUTPUTFIFO_WML; + /* Fill the right half of the re-sampler with zeros */ + ctx_priv->rs_init_mode = 0x2; + /* Zero fill the right half of the prefilter */ + ctx_priv->pf_init_mode = 0x2; + + ret = fsl_easrc_set_ctx_format(pair, + &ctx_priv->in_params.sample_format, + &ctx_priv->out_params.sample_format); + if (ret) { + dev_err(dev, "failed to set context format: %d\n", ret); + return ret; + } + + ret = fsl_easrc_config_context(asrc, pair->index); + if (ret) { + dev_err(dev, "failed to config context %d\n", ret); + return ret; + } + + ctx_priv->in_params.iterations = 1; + ctx_priv->in_params.group_len = pair->channels; + ctx_priv->in_params.access_len = pair->channels; + ctx_priv->out_params.iterations = 1; + ctx_priv->out_params.group_len = pair->channels; + ctx_priv->out_params.access_len = pair->channels; + + ret = fsl_easrc_set_ctx_organziation(pair); + if (ret) { + dev_err(dev, "failed to set fifo organization\n"); + return ret; + } + + /* The context start flag */ + pair->first_convert = 1; + return 0; +} + +static int fsl_easrc_m2m_start(struct fsl_asrc_pair *pair) +{ + /* start context once */ + if (pair->first_convert) { + fsl_easrc_start_context(pair); + pair->first_convert = 0; + } + + return 0; +} + +static int fsl_easrc_m2m_stop(struct fsl_asrc_pair *pair) +{ + /* Stop pair/context */ + if (!pair->first_convert) { + fsl_easrc_stop_context(pair); + pair->first_convert = 1; + } + + return 0; +} + +/* calculate capture data length according to output data length and sample rate */ +static int fsl_easrc_m2m_calc_out_len(struct fsl_asrc_pair *pair, int input_buffer_length) +{ + struct fsl_asrc *easrc = pair->asrc; + struct fsl_easrc_priv *easrc_priv = easrc->private; + struct fsl_easrc_ctx_priv *ctx_priv = pair->private; + unsigned int in_rate = ctx_priv->in_params.norm_rate; + unsigned int out_rate = ctx_priv->out_params.norm_rate; + unsigned int channels = pair->channels; + unsigned int in_samples, out_samples; + unsigned int in_width, out_width; + unsigned int out_length; + unsigned int frac_bits; + u64 val1, val2; + + switch (easrc_priv->rs_num_taps) { + case EASRC_RS_32_TAPS: + /* integer bits = 5; */ + frac_bits = 39; + break; + case EASRC_RS_64_TAPS: + /* integer bits = 6; */ + frac_bits = 38; + break; + case EASRC_RS_128_TAPS: + /* integer bits = 7; */ + frac_bits = 37; + break; + default: + return -EINVAL; + } + + val1 = (u64)in_rate << frac_bits; + do_div(val1, out_rate); + val1 += (s64)ctx_priv->ratio_mod << (frac_bits - 31); + + in_width = snd_pcm_format_physical_width(ctx_priv->in_params.sample_format) / 8; + out_width = snd_pcm_format_physical_width(ctx_priv->out_params.sample_format) / 8; + + ctx_priv->in_filled_len += input_buffer_length; + if (ctx_priv->in_filled_len <= ctx_priv->in_filled_sample * in_width * channels) { + out_length = 0; + } else { + in_samples = ctx_priv->in_filled_len / (in_width * channels) - + ctx_priv->in_filled_sample; + + /* right shift 12 bit to make ratio in 32bit space */ + val2 = (u64)in_samples << (frac_bits - 12); + val1 = val1 >> 12; + do_div(val2, val1); + out_samples = val2; + + out_length = out_samples * out_width * channels; + ctx_priv->in_filled_len = ctx_priv->in_filled_sample * in_width * channels; + } + + return out_length; +} + +static int fsl_easrc_m2m_get_maxburst(u8 dir, struct fsl_asrc_pair *pair) +{ + struct fsl_easrc_ctx_priv *ctx_priv = pair->private; + + if (dir == IN) + return ctx_priv->in_params.fifo_wtmk * pair->channels; + else + return ctx_priv->out_params.fifo_wtmk * pair->channels; +} + +static int fsl_easrc_m2m_pair_suspend(struct fsl_asrc_pair *pair) +{ + fsl_easrc_stop_context(pair); + + return 0; +} + +static int fsl_easrc_m2m_pair_resume(struct fsl_asrc_pair *pair) +{ + struct fsl_easrc_ctx_priv *ctx_priv = pair->private; + + pair->first_convert = 1; + ctx_priv->in_filled_len = 0; + + return 0; +} + +/* val is Q31 */ +static int fsl_easrc_m2m_set_ratio_mod(struct fsl_asrc_pair *pair, int val) +{ + struct fsl_easrc_ctx_priv *ctx_priv = pair->private; + struct fsl_asrc *easrc = pair->asrc; + struct fsl_easrc_priv *easrc_priv = easrc->private; + unsigned int frac_bits; + + ctx_priv->ratio_mod += val; + + switch (easrc_priv->rs_num_taps) { + case EASRC_RS_32_TAPS: + /* integer bits = 5; */ + frac_bits = 39; + break; + case EASRC_RS_64_TAPS: + /* integer bits = 6; */ + frac_bits = 38; + break; + case EASRC_RS_128_TAPS: + /* integer bits = 7; */ + frac_bits = 37; + break; + default: + return -EINVAL; + } + + val <<= (frac_bits - 31); + regmap_write(easrc->regmap, REG_EASRC_RUC(pair->index), EASRC_RSUC_RS_RM(val)); + + return 0; +} + +static int fsl_easrc_m2m_get_cap(struct fsl_asrc_m2m_cap *cap) +{ + cap->fmt_in = FSL_EASRC_FORMATS; + cap->fmt_out = FSL_EASRC_FORMATS | SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE; + cap->rate_in = easrc_rates; + cap->rate_in_count = ARRAY_SIZE(easrc_rates); + cap->rate_out = easrc_rates; + cap->rate_out_count = ARRAY_SIZE(easrc_rates); + cap->chan_min = 1; + cap->chan_max = 32; + return 0; +} + static const struct of_device_id fsl_easrc_dt_ids[] = { { .compatible = "fsl,imx8mn-easrc",}, {} @@ -1926,6 +2144,16 @@ static int fsl_easrc_probe(struct platform_device *pdev) easrc->release_pair = fsl_easrc_release_context; easrc->get_fifo_addr = fsl_easrc_get_fifo_addr; easrc->pair_priv_size = sizeof(struct fsl_easrc_ctx_priv); + easrc->m2m_prepare = fsl_easrc_m2m_prepare; + easrc->m2m_start = fsl_easrc_m2m_start; + easrc->m2m_stop = fsl_easrc_m2m_stop; + easrc->get_output_fifo_size = fsl_easrc_get_output_fifo_size; + easrc->m2m_calc_out_len = fsl_easrc_m2m_calc_out_len; + easrc->m2m_get_maxburst = fsl_easrc_m2m_get_maxburst; + easrc->m2m_pair_suspend = fsl_easrc_m2m_pair_suspend; + easrc->m2m_pair_resume = fsl_easrc_m2m_pair_resume; + easrc->m2m_set_ratio_mod = fsl_easrc_m2m_set_ratio_mod; + easrc->m2m_get_cap = fsl_easrc_m2m_get_cap; easrc_priv->rs_num_taps = EASRC_RS_32_TAPS; easrc_priv->const_coeff = 0x3FF0000000000000; @@ -1976,6 +2204,12 @@ static int fsl_easrc_probe(struct platform_device *pdev) goto err_pm_disable; } + ret = fsl_asrc_m2m_init(easrc); + if (ret) { + dev_err(&pdev->dev, "failed to init m2m device %d\n", ret); + return ret; + } + return 0; err_pm_disable: @@ -1985,6 +2219,10 @@ err_pm_disable: static void fsl_easrc_remove(struct platform_device *pdev) { + struct fsl_asrc *easrc = dev_get_drvdata(&pdev->dev); + + fsl_asrc_m2m_exit(easrc); + pm_runtime_disable(&pdev->dev); } @@ -2085,10 +2323,29 @@ disable_mem_clk: return ret; } +static int fsl_easrc_suspend(struct device *dev) +{ + struct fsl_asrc *easrc = dev_get_drvdata(dev); + int ret; + + fsl_asrc_m2m_suspend(easrc); + ret = pm_runtime_force_suspend(dev); + return ret; +} + +static int fsl_easrc_resume(struct device *dev) +{ + struct fsl_asrc *easrc = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + fsl_asrc_m2m_resume(easrc); + return ret; +} + static const struct dev_pm_ops fsl_easrc_pm_ops = { RUNTIME_PM_OPS(fsl_easrc_runtime_suspend, fsl_easrc_runtime_resume, NULL) - SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + SYSTEM_SLEEP_PM_OPS(fsl_easrc_suspend, fsl_easrc_resume) }; static struct platform_driver fsl_easrc_driver = { diff --git a/sound/soc/fsl/fsl_easrc.h b/sound/soc/fsl/fsl_easrc.h index 7c70dac52713..c9f770862662 100644 --- a/sound/soc/fsl/fsl_easrc.h +++ b/sound/soc/fsl/fsl_easrc.h @@ -601,6 +601,8 @@ struct fsl_easrc_slot { * @out_missed_sample: sample missed in output * @st1_addexp: exponent added for stage1 * @st2_addexp: exponent added for stage2 + * @ratio_mod: update ratio + * @in_filled_len: input filled length */ struct fsl_easrc_ctx_priv { struct fsl_easrc_io_params in_params; @@ -618,6 +620,8 @@ struct fsl_easrc_ctx_priv { int out_missed_sample; int st1_addexp; int st2_addexp; + int ratio_mod; + unsigned int in_filled_len; }; /** diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 8c15389c9a04..1075598a6647 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -35,6 +35,15 @@ #define MICFIL_AUDIO_PLL2 1 #define MICFIL_CLK_EXT3 2 +static const unsigned int fsl_micfil_rates[] = { + 8000, 11025, 16000, 22050, 32000, 44100, 48000, +}; + +static const struct snd_pcm_hw_constraint_list fsl_micfil_rate_constraints = { + .count = ARRAY_SIZE(fsl_micfil_rates), + .list = fsl_micfil_rates, +}; + enum quality { QUALITY_HIGH, QUALITY_MEDIUM, @@ -80,6 +89,7 @@ struct fsl_micfil_soc_data { bool use_verid; bool volume_sx; u64 formats; + int fifo_offset; }; static struct fsl_micfil_soc_data fsl_micfil_imx8mm = { @@ -89,6 +99,7 @@ static struct fsl_micfil_soc_data fsl_micfil_imx8mm = { .dataline = 0xf, .formats = SNDRV_PCM_FMTBIT_S16_LE, .volume_sx = true, + .fifo_offset = 0, }; static struct fsl_micfil_soc_data fsl_micfil_imx8mp = { @@ -98,6 +109,7 @@ static struct fsl_micfil_soc_data fsl_micfil_imx8mp = { .dataline = 0xf, .formats = SNDRV_PCM_FMTBIT_S32_LE, .volume_sx = false, + .fifo_offset = 0, }; static struct fsl_micfil_soc_data fsl_micfil_imx93 = { @@ -109,12 +121,26 @@ static struct fsl_micfil_soc_data fsl_micfil_imx93 = { .use_edma = true, .use_verid = true, .volume_sx = false, + .fifo_offset = 0, +}; + +static struct fsl_micfil_soc_data fsl_micfil_imx943 = { + .imx = true, + .fifos = 8, + .fifo_depth = 32, + .dataline = 0xf, + .formats = SNDRV_PCM_FMTBIT_S32_LE, + .use_edma = true, + .use_verid = true, + .volume_sx = false, + .fifo_offset = -4, }; static const struct of_device_id fsl_micfil_dt_ids[] = { { .compatible = "fsl,imx8mm-micfil", .data = &fsl_micfil_imx8mm }, { .compatible = "fsl,imx8mp-micfil", .data = &fsl_micfil_imx8mp }, { .compatible = "fsl,imx93-micfil", .data = &fsl_micfil_imx93 }, + { .compatible = "fsl,imx943-micfil", .data = &fsl_micfil_imx943 }, {} }; MODULE_DEVICE_TABLE(of, fsl_micfil_dt_ids); @@ -486,29 +512,12 @@ static int fsl_micfil_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct fsl_micfil *micfil = snd_soc_dai_get_drvdata(dai); - unsigned int rates[MICFIL_NUM_RATES] = {8000, 11025, 16000, 22050, 32000, 44100, 48000}; - int i, j, k = 0; - u64 clk_rate; if (!micfil) { dev_err(dai->dev, "micfil dai priv_data not set\n"); return -EINVAL; } - micfil->constraint_rates.list = micfil->constraint_rates_list; - micfil->constraint_rates.count = 0; - - for (j = 0; j < MICFIL_NUM_RATES; j++) { - for (i = 0; i < MICFIL_CLK_SRC_NUM; i++) { - clk_rate = clk_get_rate(micfil->clk_src[i]); - if (clk_rate != 0 && do_div(clk_rate, rates[j]) == 0) { - micfil->constraint_rates_list[k++] = rates[j]; - micfil->constraint_rates.count++; - break; - } - } - } - if (micfil->constraint_rates.count > 0) snd_pcm_hw_constraint_list(substream->runtime, 0, SNDRV_PCM_HW_PARAM_RATE, @@ -801,7 +810,7 @@ static int fsl_micfil_hw_params(struct snd_pcm_substream *substream, ret = regmap_update_bits(micfil->regmap, REG_MICFIL_CTRL2, MICFIL_CTRL2_CLKDIV | MICFIL_CTRL2_CICOSR, FIELD_PREP(MICFIL_CTRL2_CLKDIV, clk_div) | - FIELD_PREP(MICFIL_CTRL2_CICOSR, 16 - osr)); + FIELD_PREP(MICFIL_CTRL2_CICOSR, 32 - osr)); /* Configure CIC OSR in VADCICOSR */ regmap_update_bits(micfil->regmap, REG_MICFIL_VAD0_CTRL1, @@ -940,9 +949,39 @@ static const struct reg_default fsl_micfil_reg_defaults[] = { {REG_MICFIL_VAD0_ZCD, 0x00000004}, }; +static const struct reg_default fsl_micfil_reg_defaults_v2[] = { + {REG_MICFIL_CTRL1, 0x00000000}, + {REG_MICFIL_CTRL2, 0x00000000}, + {REG_MICFIL_STAT, 0x00000000}, + {REG_MICFIL_FIFO_CTRL, 0x0000001F}, + {REG_MICFIL_FIFO_STAT, 0x00000000}, + {REG_MICFIL_DATACH0 - 0x4, 0x00000000}, + {REG_MICFIL_DATACH1 - 0x4, 0x00000000}, + {REG_MICFIL_DATACH2 - 0x4, 0x00000000}, + {REG_MICFIL_DATACH3 - 0x4, 0x00000000}, + {REG_MICFIL_DATACH4 - 0x4, 0x00000000}, + {REG_MICFIL_DATACH5 - 0x4, 0x00000000}, + {REG_MICFIL_DATACH6 - 0x4, 0x00000000}, + {REG_MICFIL_DATACH7 - 0x4, 0x00000000}, + {REG_MICFIL_DC_CTRL, 0x00000000}, + {REG_MICFIL_OUT_CTRL, 0x00000000}, + {REG_MICFIL_OUT_STAT, 0x00000000}, + {REG_MICFIL_VAD0_CTRL1, 0x00000000}, + {REG_MICFIL_VAD0_CTRL2, 0x000A0000}, + {REG_MICFIL_VAD0_STAT, 0x00000000}, + {REG_MICFIL_VAD0_SCONFIG, 0x00000000}, + {REG_MICFIL_VAD0_NCONFIG, 0x80000000}, + {REG_MICFIL_VAD0_NDATA, 0x00000000}, + {REG_MICFIL_VAD0_ZCD, 0x00000004}, +}; + static bool fsl_micfil_readable_reg(struct device *dev, unsigned int reg) { struct fsl_micfil *micfil = dev_get_drvdata(dev); + int ofs = micfil->soc->fifo_offset; + + if (reg >= (REG_MICFIL_DATACH0 + ofs) && reg <= (REG_MICFIL_DATACH7 + ofs)) + return true; switch (reg) { case REG_MICFIL_CTRL1: @@ -950,14 +989,6 @@ static bool fsl_micfil_readable_reg(struct device *dev, unsigned int reg) case REG_MICFIL_STAT: case REG_MICFIL_FIFO_CTRL: case REG_MICFIL_FIFO_STAT: - case REG_MICFIL_DATACH0: - case REG_MICFIL_DATACH1: - case REG_MICFIL_DATACH2: - case REG_MICFIL_DATACH3: - case REG_MICFIL_DATACH4: - case REG_MICFIL_DATACH5: - case REG_MICFIL_DATACH6: - case REG_MICFIL_DATACH7: case REG_MICFIL_DC_CTRL: case REG_MICFIL_OUT_CTRL: case REG_MICFIL_OUT_STAT: @@ -1011,17 +1042,15 @@ static bool fsl_micfil_writeable_reg(struct device *dev, unsigned int reg) static bool fsl_micfil_volatile_reg(struct device *dev, unsigned int reg) { + struct fsl_micfil *micfil = dev_get_drvdata(dev); + int ofs = micfil->soc->fifo_offset; + + if (reg >= (REG_MICFIL_DATACH0 + ofs) && reg <= (REG_MICFIL_DATACH7 + ofs)) + return true; + switch (reg) { case REG_MICFIL_STAT: case REG_MICFIL_FIFO_STAT: - case REG_MICFIL_DATACH0: - case REG_MICFIL_DATACH1: - case REG_MICFIL_DATACH2: - case REG_MICFIL_DATACH3: - case REG_MICFIL_DATACH4: - case REG_MICFIL_DATACH5: - case REG_MICFIL_DATACH6: - case REG_MICFIL_DATACH7: case REG_MICFIL_OUT_STAT: case REG_MICFIL_VERID: case REG_MICFIL_PARAM: @@ -1047,6 +1076,20 @@ static const struct regmap_config fsl_micfil_regmap_config = { .cache_type = REGCACHE_MAPLE, }; +static const struct regmap_config fsl_micfil_regmap_config_v2 = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + + .max_register = REG_MICFIL_VAD0_ZCD, + .reg_defaults = fsl_micfil_reg_defaults_v2, + .num_reg_defaults = ARRAY_SIZE(fsl_micfil_reg_defaults_v2), + .readable_reg = fsl_micfil_readable_reg, + .volatile_reg = fsl_micfil_volatile_reg, + .writeable_reg = fsl_micfil_writeable_reg, + .cache_type = REGCACHE_MAPLE, +}; + /* END OF REGMAP */ static irqreturn_t micfil_isr(int irq, void *devid) @@ -1239,14 +1282,26 @@ static int fsl_micfil_probe(struct platform_device *pdev) if (IS_ERR(micfil->clk_src[MICFIL_CLK_EXT3])) micfil->clk_src[MICFIL_CLK_EXT3] = NULL; + fsl_asoc_constrain_rates(&micfil->constraint_rates, + &fsl_micfil_rate_constraints, + micfil->clk_src[MICFIL_AUDIO_PLL1], + micfil->clk_src[MICFIL_AUDIO_PLL2], + micfil->clk_src[MICFIL_CLK_EXT3], + micfil->constraint_rates_list); + /* init regmap */ regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(regs)) return PTR_ERR(regs); - micfil->regmap = devm_regmap_init_mmio(&pdev->dev, - regs, - &fsl_micfil_regmap_config); + if (of_device_is_compatible(np, "fsl,imx943-micfil")) + micfil->regmap = devm_regmap_init_mmio(&pdev->dev, + regs, + &fsl_micfil_regmap_config_v2); + else + micfil->regmap = devm_regmap_init_mmio(&pdev->dev, + regs, + &fsl_micfil_regmap_config); if (IS_ERR(micfil->regmap)) { dev_err(&pdev->dev, "failed to init MICFIL regmap: %ld\n", PTR_ERR(micfil->regmap)); @@ -1315,7 +1370,7 @@ static int fsl_micfil_probe(struct platform_device *pdev) } micfil->dma_params_rx.chan_name = "rx"; - micfil->dma_params_rx.addr = res->start + REG_MICFIL_DATACH0; + micfil->dma_params_rx.addr = res->start + REG_MICFIL_DATACH0 + micfil->soc->fifo_offset; micfil->dma_params_rx.maxburst = MICFIL_DMA_MAXBURST_RX; platform_set_drvdata(pdev, micfil); diff --git a/sound/soc/fsl/fsl_micfil.h b/sound/soc/fsl/fsl_micfil.h index b7798a7cbf2a..aa3661ea4ffc 100644 --- a/sound/soc/fsl/fsl_micfil.h +++ b/sound/soc/fsl/fsl_micfil.h @@ -62,7 +62,7 @@ #define MICFIL_QSEL_VLOW1_QUALITY 5 #define MICFIL_QSEL_VLOW2_QUALITY 4 -#define MICFIL_CTRL2_CICOSR GENMASK(19, 16) +#define MICFIL_CTRL2_CICOSR GENMASK(20, 16) #define MICFIL_CTRL2_CLKDIV GENMASK(7, 0) /* MICFIL Status Register -- REG_MICFIL_STAT 0x08 */ diff --git a/sound/soc/fsl/fsl_mqs.c b/sound/soc/fsl/fsl_mqs.c index 0513e9e8402e..e34e5ea98de5 100644 --- a/sound/soc/fsl/fsl_mqs.c +++ b/sound/soc/fsl/fsl_mqs.c @@ -410,12 +410,40 @@ static const struct fsl_mqs_soc_data fsl_mqs_imx95_netc_data = { .div_shift = 9, }; +static const struct fsl_mqs_soc_data fsl_mqs_imx943_aon_data = { + .type = TYPE_REG_SM, + .ctrl_off = 0x88, + .en_mask = BIT(1), + .en_shift = 1, + .rst_mask = BIT(2), + .rst_shift = 2, + .osr_mask = BIT(3), + .osr_shift = 3, + .div_mask = GENMASK(15, 8), + .div_shift = 8, +}; + +static const struct fsl_mqs_soc_data fsl_mqs_imx943_wakeup_data = { + .type = TYPE_REG_GPR, + .ctrl_off = 0x10, + .en_mask = BIT(1), + .en_shift = 1, + .rst_mask = BIT(2), + .rst_shift = 2, + .osr_mask = BIT(3), + .osr_shift = 3, + .div_mask = GENMASK(15, 8), + .div_shift = 8, +}; + static const struct of_device_id fsl_mqs_dt_ids[] = { { .compatible = "fsl,imx8qm-mqs", .data = &fsl_mqs_imx8qm_data }, { .compatible = "fsl,imx6sx-mqs", .data = &fsl_mqs_imx6sx_data }, { .compatible = "fsl,imx93-mqs", .data = &fsl_mqs_imx93_data }, { .compatible = "fsl,imx95-aonmix-mqs", .data = &fsl_mqs_imx95_aon_data }, { .compatible = "fsl,imx95-netcmix-mqs", .data = &fsl_mqs_imx95_netc_data }, + { .compatible = "fsl,imx943-aonmix-mqs", .data = &fsl_mqs_imx943_aon_data }, + { .compatible = "fsl,imx943-wakeupmix-mqs", .data = &fsl_mqs_imx943_wakeup_data }, {} }; MODULE_DEVICE_TABLE(of, fsl_mqs_dt_ids); diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 634168d2bb6e..c4eb87c5d39e 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -885,7 +885,7 @@ static int fsl_sai_startup(struct snd_pcm_substream *substream, sai->dma_params_rx.maxburst); ret = snd_pcm_hw_constraint_list(substream->runtime, 0, - SNDRV_PCM_HW_PARAM_RATE, &fsl_sai_rate_constraints); + SNDRV_PCM_HW_PARAM_RATE, &sai->constraint_rates); return ret; } @@ -1442,6 +1442,11 @@ static int fsl_sai_probe(struct platform_device *pdev) fsl_asoc_get_pll_clocks(&pdev->dev, &sai->pll8k_clk, &sai->pll11k_clk); + fsl_asoc_constrain_rates(&sai->constraint_rates, + &fsl_sai_rate_constraints, + sai->pll8k_clk, sai->pll11k_clk, NULL, + sai->constraint_rates_list); + /* Use Multi FIFO mode depending on the support from SDMA script */ ret = of_property_read_u32_array(np, "dmas", dmas, 4); if (!sai->soc_data->use_edma && !ret && dmas[2] == IMX_DMATYPE_MULTI_SAI) diff --git a/sound/soc/fsl/fsl_sai.h b/sound/soc/fsl/fsl_sai.h index 9c4d19fe22c6..0e25e2fc7ce0 100644 --- a/sound/soc/fsl/fsl_sai.h +++ b/sound/soc/fsl/fsl_sai.h @@ -9,6 +9,7 @@ #include <linux/dma/imx-dma.h> #include <sound/dmaengine_pcm.h> +#define FAL_SAI_NUM_RATES 20 #define FSL_SAI_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\ SNDRV_PCM_FMTBIT_S20_3LE |\ SNDRV_PCM_FMTBIT_S24_LE |\ @@ -309,6 +310,8 @@ struct fsl_sai { struct pinctrl *pinctrl; struct pinctrl_state *pins_state; struct sdma_peripheral_config audio_config[2]; + struct snd_pcm_hw_constraint_list constraint_rates; + unsigned int constraint_rates_list[FAL_SAI_NUM_RATES]; }; #define TX 1 diff --git a/sound/soc/fsl/fsl_utils.c b/sound/soc/fsl/fsl_utils.c index a5ab27c2f711..d69a6b9795bf 100644 --- a/sound/soc/fsl/fsl_utils.c +++ b/sound/soc/fsl/fsl_utils.c @@ -152,6 +152,51 @@ void fsl_asoc_reparent_pll_clocks(struct device *dev, struct clk *clk, } EXPORT_SYMBOL(fsl_asoc_reparent_pll_clocks); +/** + * fsl_asoc_constrain_rates - constrain rates according to clocks + * + * @target_constr: target constraint + * @original_constr: original constraint + * @pll8k_clk: PLL clock pointer for 8kHz + * @pll11k_clk: PLL clock pointer for 11kHz + * @ext_clk: External clock pointer + * @target_rates: target rates array + * + * This function constrain rates according to clocks + */ +void fsl_asoc_constrain_rates(struct snd_pcm_hw_constraint_list *target_constr, + const struct snd_pcm_hw_constraint_list *original_constr, + struct clk *pll8k_clk, struct clk *pll11k_clk, + struct clk *ext_clk, int *target_rates) +{ + int i, j, k = 0; + u64 clk_rate[3]; + + *target_constr = *original_constr; + if (pll8k_clk || pll11k_clk || ext_clk) { + target_constr->list = target_rates; + target_constr->count = 0; + for (i = 0; i < original_constr->count; i++) { + clk_rate[0] = clk_get_rate(pll8k_clk); + clk_rate[1] = clk_get_rate(pll11k_clk); + clk_rate[2] = clk_get_rate(ext_clk); + for (j = 0; j < 3; j++) { + if (clk_rate[j] != 0 && + do_div(clk_rate[j], original_constr->list[i]) == 0) { + target_rates[k++] = original_constr->list[i]; + target_constr->count++; + break; + } + } + } + + /* protection for if there is no proper rate found*/ + if (!target_constr->count) + *target_constr = *original_constr; + } +} +EXPORT_SYMBOL(fsl_asoc_constrain_rates); + MODULE_AUTHOR("Timur Tabi <timur@freescale.com>"); MODULE_DESCRIPTION("Freescale ASoC utility code"); MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/fsl/fsl_utils.h b/sound/soc/fsl/fsl_utils.h index 4d5f3d93bc81..21b25a11ecda 100644 --- a/sound/soc/fsl/fsl_utils.h +++ b/sound/soc/fsl/fsl_utils.h @@ -26,4 +26,9 @@ void fsl_asoc_get_pll_clocks(struct device *dev, struct clk **pll8k_clk, void fsl_asoc_reparent_pll_clocks(struct device *dev, struct clk *clk, struct clk *pll8k_clk, struct clk *pll11k_clk, u64 ratio); + +void fsl_asoc_constrain_rates(struct snd_pcm_hw_constraint_list *target_constr, + const struct snd_pcm_hw_constraint_list *original_constr, + struct clk *pll8k_clk, struct clk *pll11k_clk, + struct clk *ext_clk, int *target_rates); #endif /* _FSL_UTILS_H */ diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index 9c184ab73468..c59c1af5a98a 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -19,6 +19,7 @@ #include "imx-pcm.h" #define FSL_XCVR_CAPDS_SIZE 256 +#define SPDIF_NUM_RATES 7 enum fsl_xcvr_pll_verison { PLL_MX8MP, @@ -37,6 +38,8 @@ struct fsl_xcvr { const struct fsl_xcvr_soc_data *soc_data; struct platform_device *pdev; struct regmap *regmap; + struct regmap *regmap_phy; + struct regmap *regmap_pll; struct clk *ipg_clk; struct clk *pll_ipg_clk; struct clk *phy_clk; @@ -55,6 +58,8 @@ struct fsl_xcvr { u8 cap_ds[FSL_XCVR_CAPDS_SIZE]; struct work_struct work_rst; spinlock_t lock; /* Protect hw_reset and trigger */ + struct snd_pcm_hw_constraint_list spdif_constr_rates; + u32 spdif_constr_rates_list[SPDIF_NUM_RATES]; }; static const struct fsl_xcvr_pll_conf { @@ -257,7 +262,7 @@ static int fsl_xcvr_ai_write(struct fsl_xcvr *xcvr, u8 reg, u32 data, bool phy) idx = BIT(phy ? 26 : 24); tidx = BIT(phy ? 27 : 25); - regmap_write(xcvr->regmap, FSL_XCVR_PHY_AI_CTRL_CLR, 0xFF); + regmap_write(xcvr->regmap, FSL_XCVR_PHY_AI_CTRL_CLR, 0xFF | FSL_XCVR_PHY_AI_CTRL_AI_RWB); regmap_write(xcvr->regmap, FSL_XCVR_PHY_AI_CTRL_SET, reg); regmap_write(xcvr->regmap, FSL_XCVR_PHY_AI_WDATA, data); regmap_write(xcvr->regmap, FSL_XCVR_PHY_AI_CTRL_TOG, idx); @@ -271,6 +276,59 @@ static int fsl_xcvr_ai_write(struct fsl_xcvr *xcvr, u8 reg, u32 data, bool phy) return ret; } +static int fsl_xcvr_ai_read(struct fsl_xcvr *xcvr, u8 reg, u32 *data, bool phy) +{ + struct device *dev = &xcvr->pdev->dev; + u32 val, idx, tidx; + int ret; + + idx = BIT(phy ? 26 : 24); + tidx = BIT(phy ? 27 : 25); + + regmap_write(xcvr->regmap, FSL_XCVR_PHY_AI_CTRL_CLR, 0xFF | FSL_XCVR_PHY_AI_CTRL_AI_RWB); + regmap_write(xcvr->regmap, FSL_XCVR_PHY_AI_CTRL_SET, reg | FSL_XCVR_PHY_AI_CTRL_AI_RWB); + regmap_write(xcvr->regmap, FSL_XCVR_PHY_AI_CTRL_TOG, idx); + + ret = regmap_read_poll_timeout(xcvr->regmap, FSL_XCVR_PHY_AI_CTRL, val, + (val & idx) == ((val & tidx) >> 1), + 10, 10000); + if (ret) + dev_err(dev, "AI timeout: failed to read %s reg 0x%02x\n", + phy ? "PHY" : "PLL", reg); + + regmap_read(xcvr->regmap, FSL_XCVR_PHY_AI_RDATA, data); + + return ret; +} + +static int fsl_xcvr_phy_reg_read(void *context, unsigned int reg, unsigned int *val) +{ + struct fsl_xcvr *xcvr = context; + + return fsl_xcvr_ai_read(xcvr, reg, val, 1); +} + +static int fsl_xcvr_phy_reg_write(void *context, unsigned int reg, unsigned int val) +{ + struct fsl_xcvr *xcvr = context; + + return fsl_xcvr_ai_write(xcvr, reg, val, 1); +} + +static int fsl_xcvr_pll_reg_read(void *context, unsigned int reg, unsigned int *val) +{ + struct fsl_xcvr *xcvr = context; + + return fsl_xcvr_ai_read(xcvr, reg, val, 0); +} + +static int fsl_xcvr_pll_reg_write(void *context, unsigned int reg, unsigned int val) +{ + struct fsl_xcvr *xcvr = context; + + return fsl_xcvr_ai_write(xcvr, reg, val, 0); +} + static int fsl_xcvr_en_phy_pll(struct fsl_xcvr *xcvr, u32 freq, bool tx) { struct device *dev = &xcvr->pdev->dev; @@ -303,55 +361,55 @@ static int fsl_xcvr_en_phy_pll(struct fsl_xcvr *xcvr, u32 freq, bool tx) switch (xcvr->soc_data->pll_ver) { case PLL_MX8MP: /* PLL: BANDGAP_SET: EN_VBG (enable bandgap) */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_BANDGAP_SET, - FSL_XCVR_PLL_BANDGAP_EN_VBG, 0); + regmap_set_bits(xcvr->regmap_pll, FSL_XCVR_PLL_BANDGAP, + FSL_XCVR_PLL_BANDGAP_EN_VBG); /* PLL: CTRL0: DIV_INTEGER */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_CTRL0, fsl_xcvr_pll_cfg[i].mfi, 0); + regmap_write(xcvr->regmap_pll, FSL_XCVR_PLL_CTRL0, fsl_xcvr_pll_cfg[i].mfi); /* PLL: NUMERATOR: MFN */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_NUM, fsl_xcvr_pll_cfg[i].mfn, 0); + regmap_write(xcvr->regmap_pll, FSL_XCVR_PLL_NUM, fsl_xcvr_pll_cfg[i].mfn); /* PLL: DENOMINATOR: MFD */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_DEN, fsl_xcvr_pll_cfg[i].mfd, 0); + regmap_write(xcvr->regmap_pll, FSL_XCVR_PLL_DEN, fsl_xcvr_pll_cfg[i].mfd); /* PLL: CTRL0_SET: HOLD_RING_OFF, POWER_UP */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_CTRL0_SET, - FSL_XCVR_PLL_CTRL0_HROFF | FSL_XCVR_PLL_CTRL0_PWP, 0); + regmap_set_bits(xcvr->regmap_pll, FSL_XCVR_PLL_CTRL0, + FSL_XCVR_PLL_CTRL0_HROFF | FSL_XCVR_PLL_CTRL0_PWP); udelay(25); /* PLL: CTRL0: Clear Hold Ring Off */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_CTRL0_CLR, - FSL_XCVR_PLL_CTRL0_HROFF, 0); + regmap_clear_bits(xcvr->regmap_pll, FSL_XCVR_PLL_CTRL0, + FSL_XCVR_PLL_CTRL0_HROFF); udelay(100); if (tx) { /* TX is enabled for SPDIF only */ /* PLL: POSTDIV: PDIV0 */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_PDIV, - FSL_XCVR_PLL_PDIVx(log2, 0), 0); + regmap_write(xcvr->regmap_pll, FSL_XCVR_PLL_PDIV, + FSL_XCVR_PLL_PDIVx(log2, 0)); /* PLL: CTRL_SET: CLKMUX0_EN */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_CTRL0_SET, - FSL_XCVR_PLL_CTRL0_CM0_EN, 0); + regmap_set_bits(xcvr->regmap_pll, FSL_XCVR_PLL_CTRL0, + FSL_XCVR_PLL_CTRL0_CM0_EN); } else if (xcvr->mode == FSL_XCVR_MODE_EARC) { /* eARC RX */ /* PLL: POSTDIV: PDIV1 */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_PDIV, - FSL_XCVR_PLL_PDIVx(log2, 1), 0); + regmap_write(xcvr->regmap_pll, FSL_XCVR_PLL_PDIV, + FSL_XCVR_PLL_PDIVx(log2, 1)); /* PLL: CTRL_SET: CLKMUX1_EN */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_CTRL0_SET, - FSL_XCVR_PLL_CTRL0_CM1_EN, 0); + regmap_set_bits(xcvr->regmap_pll, FSL_XCVR_PLL_CTRL0, + FSL_XCVR_PLL_CTRL0_CM1_EN); } else { /* SPDIF / ARC RX */ /* PLL: POSTDIV: PDIV2 */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_PDIV, - FSL_XCVR_PLL_PDIVx(log2, 2), 0); + regmap_write(xcvr->regmap_pll, FSL_XCVR_PLL_PDIV, + FSL_XCVR_PLL_PDIVx(log2, 2)); /* PLL: CTRL_SET: CLKMUX2_EN */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PLL_CTRL0_SET, - FSL_XCVR_PLL_CTRL0_CM2_EN, 0); + regmap_set_bits(xcvr->regmap_pll, FSL_XCVR_PLL_CTRL0, + FSL_XCVR_PLL_CTRL0_CM2_EN); } break; case PLL_MX95: val = fsl_xcvr_pll_cfg[i].mfi << FSL_XCVR_GP_PLL_DIV_MFI_SHIFT | div; - fsl_xcvr_ai_write(xcvr, FSL_XCVR_GP_PLL_DIV, val, 0); + regmap_write(xcvr->regmap_pll, FSL_XCVR_GP_PLL_DIV, val); val = fsl_xcvr_pll_cfg[i].mfn << FSL_XCVR_GP_PLL_NUMERATOR_MFN_SHIFT; - fsl_xcvr_ai_write(xcvr, FSL_XCVR_GP_PLL_NUMERATOR, val, 0); - fsl_xcvr_ai_write(xcvr, FSL_XCVR_GP_PLL_DENOMINATOR, - fsl_xcvr_pll_cfg[i].mfd, 0); + regmap_write(xcvr->regmap_pll, FSL_XCVR_GP_PLL_NUMERATOR, val); + regmap_write(xcvr->regmap_pll, FSL_XCVR_GP_PLL_DENOMINATOR, + fsl_xcvr_pll_cfg[i].mfd); val = FSL_XCVR_GP_PLL_CTRL_POWERUP | FSL_XCVR_GP_PLL_CTRL_CLKMUX_EN; - fsl_xcvr_ai_write(xcvr, FSL_XCVR_GP_PLL_CTRL, val, 0); + regmap_write(xcvr->regmap_pll, FSL_XCVR_GP_PLL_CTRL, val); break; default: dev_err(dev, "Error for PLL version %d\n", xcvr->soc_data->pll_ver); @@ -360,22 +418,22 @@ static int fsl_xcvr_en_phy_pll(struct fsl_xcvr *xcvr, u32 freq, bool tx) if (xcvr->mode == FSL_XCVR_MODE_EARC) { /* eARC mode */ /* PHY: CTRL_SET: TX_DIFF_OE, PHY_EN */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PHY_CTRL_SET, - FSL_XCVR_PHY_CTRL_TSDIFF_OE | - FSL_XCVR_PHY_CTRL_PHY_EN, 1); + regmap_set_bits(xcvr->regmap_phy, FSL_XCVR_PHY_CTRL, + FSL_XCVR_PHY_CTRL_TSDIFF_OE | + FSL_XCVR_PHY_CTRL_PHY_EN); /* PHY: CTRL2_SET: EARC_TX_MODE */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PHY_CTRL2_SET, - FSL_XCVR_PHY_CTRL2_EARC_TXMS, 1); + regmap_set_bits(xcvr->regmap_phy, FSL_XCVR_PHY_CTRL2, + FSL_XCVR_PHY_CTRL2_EARC_TXMS); } else if (!tx) { /* SPDIF / ARC RX mode */ if (xcvr->mode == FSL_XCVR_MODE_SPDIF) /* PHY: CTRL_SET: SPDIF_EN */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PHY_CTRL_SET, - FSL_XCVR_PHY_CTRL_SPDIF_EN, 1); + regmap_set_bits(xcvr->regmap_phy, FSL_XCVR_PHY_CTRL, + FSL_XCVR_PHY_CTRL_SPDIF_EN); else /* PHY: CTRL_SET: ARC RX setup */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PHY_CTRL_SET, - FSL_XCVR_PHY_CTRL_PHY_EN | - FSL_XCVR_PHY_CTRL_RX_CM_EN | - fsl_xcvr_phy_arc_cfg[xcvr->arc_mode], 1); + regmap_set_bits(xcvr->regmap_phy, FSL_XCVR_PHY_CTRL, + FSL_XCVR_PHY_CTRL_PHY_EN | + FSL_XCVR_PHY_CTRL_RX_CM_EN | + fsl_xcvr_phy_arc_cfg[xcvr->arc_mode]); } dev_dbg(dev, "PLL Fexp: %u, Fout: %u, mfi: %u, mfn: %u, mfd: %d, div: %u, pdiv0: %u\n", @@ -416,17 +474,17 @@ static int fsl_xcvr_en_aud_pll(struct fsl_xcvr *xcvr, u32 freq) if (xcvr->mode == FSL_XCVR_MODE_EARC) { /* eARC mode */ /* PHY: CTRL_SET: TX_DIFF_OE, PHY_EN */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PHY_CTRL_SET, - FSL_XCVR_PHY_CTRL_TSDIFF_OE | - FSL_XCVR_PHY_CTRL_PHY_EN, 1); + regmap_set_bits(xcvr->regmap_phy, FSL_XCVR_PHY_CTRL, + FSL_XCVR_PHY_CTRL_TSDIFF_OE | + FSL_XCVR_PHY_CTRL_PHY_EN); /* PHY: CTRL2_SET: EARC_TX_MODE */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PHY_CTRL2_SET, - FSL_XCVR_PHY_CTRL2_EARC_TXMS, 1); + regmap_set_bits(xcvr->regmap_phy, FSL_XCVR_PHY_CTRL2, + FSL_XCVR_PHY_CTRL2_EARC_TXMS); } else { /* SPDIF mode */ /* PHY: CTRL_SET: TX_CLK_AUD_SS | SPDIF_EN */ - fsl_xcvr_ai_write(xcvr, FSL_XCVR_PHY_CTRL_SET, - FSL_XCVR_PHY_CTRL_TX_CLK_AUD_SS | - FSL_XCVR_PHY_CTRL_SPDIF_EN, 1); + regmap_set_bits(xcvr->regmap_phy, FSL_XCVR_PHY_CTRL, + FSL_XCVR_PHY_CTRL_TX_CLK_AUD_SS | + FSL_XCVR_PHY_CTRL_SPDIF_EN); } dev_dbg(dev, "PLL Fexp: %u\n", freq); @@ -448,7 +506,7 @@ static int fsl_xcvr_prepare(struct snd_pcm_substream *substream, switch (xcvr->mode) { case FSL_XCVR_MODE_SPDIF: if (xcvr->soc_data->spdif_only && tx) { - ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_TX_DPTH_CTRL_SET, + ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_TX_DPTH_CTRL, FSL_XCVR_TX_DPTH_CTRL_BYPASS_FEM, FSL_XCVR_TX_DPTH_CTRL_BYPASS_FEM); if (ret < 0) { @@ -466,8 +524,8 @@ static int fsl_xcvr_prepare(struct snd_pcm_substream *substream, return ret; } - ret = regmap_write(xcvr->regmap, FSL_XCVR_TX_DPTH_CTRL_SET, - FSL_XCVR_TX_DPTH_CTRL_FRM_FMT); + ret = regmap_set_bits(xcvr->regmap, FSL_XCVR_TX_DPTH_CTRL, + FSL_XCVR_TX_DPTH_CTRL_FRM_FMT); if (ret < 0) { dev_err(dai->dev, "Failed to set TX_DPTH: %d\n", ret); return ret; @@ -484,11 +542,11 @@ static int fsl_xcvr_prepare(struct snd_pcm_substream *substream, * Clear RX FIFO, flip RX FIFO bits, * disable eARC related HW mode detects */ - ret = regmap_write(xcvr->regmap, FSL_XCVR_RX_DPTH_CTRL_SET, - FSL_XCVR_RX_DPTH_CTRL_STORE_FMT | - FSL_XCVR_RX_DPTH_CTRL_CLR_RX_FIFO | - FSL_XCVR_RX_DPTH_CTRL_COMP | - FSL_XCVR_RX_DPTH_CTRL_LAYB_CTRL); + ret = regmap_set_bits(xcvr->regmap, FSL_XCVR_RX_DPTH_CTRL, + FSL_XCVR_RX_DPTH_CTRL_STORE_FMT | + FSL_XCVR_RX_DPTH_CTRL_CLR_RX_FIFO | + FSL_XCVR_RX_DPTH_CTRL_COMP | + FSL_XCVR_RX_DPTH_CTRL_LAYB_CTRL); if (ret < 0) { dev_err(dai->dev, "Failed to set RX_DPTH: %d\n", ret); return ret; @@ -505,18 +563,18 @@ static int fsl_xcvr_prepare(struct snd_pcm_substream *substream, case FSL_XCVR_MODE_EARC: if (!tx) { /** Clear RX FIFO, flip RX FIFO bits */ - ret = regmap_write(xcvr->regmap, FSL_XCVR_RX_DPTH_CTRL_SET, - FSL_XCVR_RX_DPTH_CTRL_STORE_FMT | - FSL_XCVR_RX_DPTH_CTRL_CLR_RX_FIFO); + ret = regmap_set_bits(xcvr->regmap, FSL_XCVR_RX_DPTH_CTRL, + FSL_XCVR_RX_DPTH_CTRL_STORE_FMT | + FSL_XCVR_RX_DPTH_CTRL_CLR_RX_FIFO); if (ret < 0) { dev_err(dai->dev, "Failed to set RX_DPTH: %d\n", ret); return ret; } /** Enable eARC related HW mode detects */ - ret = regmap_write(xcvr->regmap, FSL_XCVR_RX_DPTH_CTRL_CLR, - FSL_XCVR_RX_DPTH_CTRL_COMP | - FSL_XCVR_RX_DPTH_CTRL_LAYB_CTRL); + ret = regmap_clear_bits(xcvr->regmap, FSL_XCVR_RX_DPTH_CTRL, + FSL_XCVR_RX_DPTH_CTRL_COMP | + FSL_XCVR_RX_DPTH_CTRL_LAYB_CTRL); if (ret < 0) { dev_err(dai->dev, "Failed to clr TX_DPTH: %d\n", ret); return ret; @@ -585,8 +643,12 @@ static int fsl_xcvr_startup(struct snd_pcm_substream *substream, switch (xcvr->mode) { case FSL_XCVR_MODE_SPDIF: case FSL_XCVR_MODE_ARC: - ret = fsl_xcvr_constr(substream, &fsl_xcvr_spdif_channels_constr, - &fsl_xcvr_spdif_rates_constr); + if (xcvr->soc_data->spdif_only && tx) + ret = fsl_xcvr_constr(substream, &fsl_xcvr_spdif_channels_constr, + &xcvr->spdif_constr_rates); + else + ret = fsl_xcvr_constr(substream, &fsl_xcvr_spdif_channels_constr, + &fsl_xcvr_spdif_rates_constr); break; case FSL_XCVR_MODE_EARC: ret = fsl_xcvr_constr(substream, &fsl_xcvr_earc_channels_constr, @@ -696,9 +758,9 @@ static int fsl_xcvr_trigger(struct snd_pcm_substream *substream, int cmd, } fallthrough; case FSL_XCVR_MODE_SPDIF: - ret = regmap_write(xcvr->regmap, - FSL_XCVR_TX_DPTH_CTRL_SET, - FSL_XCVR_TX_DPTH_CTRL_STRT_DATA_TX); + ret = regmap_set_bits(xcvr->regmap, + FSL_XCVR_TX_DPTH_CTRL, + FSL_XCVR_TX_DPTH_CTRL_STRT_DATA_TX); if (ret < 0) { dev_err(dai->dev, "Failed to start DATA_TX: %d\n", ret); goto release_lock; @@ -754,9 +816,9 @@ static int fsl_xcvr_trigger(struct snd_pcm_substream *substream, int cmd, if (tx) { switch (xcvr->mode) { case FSL_XCVR_MODE_SPDIF: - ret = regmap_write(xcvr->regmap, - FSL_XCVR_TX_DPTH_CTRL_CLR, - FSL_XCVR_TX_DPTH_CTRL_STRT_DATA_TX); + ret = regmap_clear_bits(xcvr->regmap, + FSL_XCVR_TX_DPTH_CTRL, + FSL_XCVR_TX_DPTH_CTRL_STRT_DATA_TX); if (ret < 0) { dev_err(dai->dev, "Failed to stop DATA_TX: %d\n", ret); goto release_lock; @@ -1169,6 +1231,7 @@ static bool fsl_xcvr_writeable_reg(struct device *dev, unsigned int reg) case FSL_XCVR_RX_DPTH_CNTR_CTRL_SET: case FSL_XCVR_RX_DPTH_CNTR_CTRL_CLR: case FSL_XCVR_RX_DPTH_CNTR_CTRL_TOG: + case FSL_XCVR_TX_DPTH_CTRL: case FSL_XCVR_TX_DPTH_CTRL_SET: case FSL_XCVR_TX_DPTH_CTRL_CLR: case FSL_XCVR_TX_DPTH_CTRL_TOG: @@ -1190,7 +1253,49 @@ static bool fsl_xcvr_writeable_reg(struct device *dev, unsigned int reg) static bool fsl_xcvr_volatile_reg(struct device *dev, unsigned int reg) { - return fsl_xcvr_readable_reg(dev, reg); + switch (reg) { + case FSL_XCVR_EXT_STATUS: + case FSL_XCVR_EXT_ISR: + case FSL_XCVR_EXT_ISR_SET: + case FSL_XCVR_EXT_ISR_CLR: + case FSL_XCVR_EXT_ISR_TOG: + case FSL_XCVR_ISR: + case FSL_XCVR_ISR_SET: + case FSL_XCVR_ISR_CLR: + case FSL_XCVR_ISR_TOG: + case FSL_XCVR_PHY_AI_CTRL: + case FSL_XCVR_PHY_AI_CTRL_SET: + case FSL_XCVR_PHY_AI_CTRL_CLR: + case FSL_XCVR_PHY_AI_CTRL_TOG: + case FSL_XCVR_PHY_AI_RDATA: + case FSL_XCVR_RX_CS_DATA_0: + case FSL_XCVR_RX_CS_DATA_1: + case FSL_XCVR_RX_CS_DATA_2: + case FSL_XCVR_RX_CS_DATA_3: + case FSL_XCVR_RX_CS_DATA_4: + case FSL_XCVR_RX_CS_DATA_5: + case FSL_XCVR_RX_DPTH_CNTR_CTRL: + case FSL_XCVR_RX_DPTH_CNTR_CTRL_SET: + case FSL_XCVR_RX_DPTH_CNTR_CTRL_CLR: + case FSL_XCVR_RX_DPTH_CNTR_CTRL_TOG: + case FSL_XCVR_RX_DPTH_TSCR: + case FSL_XCVR_RX_DPTH_BCR: + case FSL_XCVR_RX_DPTH_BCTR: + case FSL_XCVR_RX_DPTH_BCRR: + case FSL_XCVR_TX_DPTH_CNTR_CTRL: + case FSL_XCVR_TX_DPTH_CNTR_CTRL_SET: + case FSL_XCVR_TX_DPTH_CNTR_CTRL_CLR: + case FSL_XCVR_TX_DPTH_CNTR_CTRL_TOG: + case FSL_XCVR_TX_DPTH_TSCR: + case FSL_XCVR_TX_DPTH_BCR: + case FSL_XCVR_TX_DPTH_BCTR: + case FSL_XCVR_TX_DPTH_BCRR: + case FSL_XCVR_DEBUG_REG_0: + case FSL_XCVR_DEBUG_REG_1: + return true; + default: + return false; + } } static const struct regmap_config fsl_xcvr_regmap_cfg = { @@ -1206,6 +1311,49 @@ static const struct regmap_config fsl_xcvr_regmap_cfg = { .cache_type = REGCACHE_FLAT, }; +static const struct reg_default fsl_xcvr_phy_reg_defaults[] = { + { FSL_XCVR_PHY_CTRL, 0x58200804 }, + { FSL_XCVR_PHY_STATUS, 0x00000000 }, + { FSL_XCVR_PHY_ANALOG_TRIM, 0x00260F13 }, + { FSL_XCVR_PHY_SLEW_RATE_TRIM, 0x00000411 }, + { FSL_XCVR_PHY_DATA_TEST_DELAY, 0x00990000 }, + { FSL_XCVR_PHY_TEST_CTRL, 0x00000000 }, + { FSL_XCVR_PHY_DIFF_CDR_CTRL, 0x016D0009 }, + { FSL_XCVR_PHY_CTRL2, 0x80000000 }, +}; + +static const struct regmap_config fsl_xcvr_regmap_phy_cfg = { + .reg_bits = 8, + .reg_stride = 4, + .val_bits = 32, + .max_register = FSL_XCVR_PHY_CTRL2_TOG, + .reg_defaults = fsl_xcvr_phy_reg_defaults, + .num_reg_defaults = ARRAY_SIZE(fsl_xcvr_phy_reg_defaults), + .cache_type = REGCACHE_FLAT, + .reg_read = fsl_xcvr_phy_reg_read, + .reg_write = fsl_xcvr_phy_reg_write, +}; + +static const struct regmap_config fsl_xcvr_regmap_pllv0_cfg = { + .reg_bits = 8, + .reg_stride = 4, + .val_bits = 32, + .max_register = FSL_XCVR_PLL_STAT0_TOG, + .cache_type = REGCACHE_FLAT, + .reg_read = fsl_xcvr_pll_reg_read, + .reg_write = fsl_xcvr_pll_reg_write, +}; + +static const struct regmap_config fsl_xcvr_regmap_pllv1_cfg = { + .reg_bits = 8, + .reg_stride = 4, + .val_bits = 32, + .max_register = FSL_XCVR_GP_PLL_STATUS_TOG, + .cache_type = REGCACHE_FLAT, + .reg_read = fsl_xcvr_pll_reg_read, + .reg_write = fsl_xcvr_pll_reg_write, +}; + static void reset_rx_work(struct work_struct *work) { struct fsl_xcvr *xcvr = container_of(work, struct fsl_xcvr, work_rst); @@ -1405,6 +1553,15 @@ static int fsl_xcvr_probe(struct platform_device *pdev) fsl_asoc_get_pll_clocks(dev, &xcvr->pll8k_clk, &xcvr->pll11k_clk); + if (xcvr->soc_data->spdif_only) { + if (!(xcvr->pll8k_clk || xcvr->pll11k_clk)) + xcvr->pll8k_clk = xcvr->phy_clk; + fsl_asoc_constrain_rates(&xcvr->spdif_constr_rates, + &fsl_xcvr_spdif_rates_constr, + xcvr->pll8k_clk, xcvr->pll11k_clk, NULL, + xcvr->spdif_constr_rates_list); + } + xcvr->ram_addr = devm_platform_ioremap_resource_byname(pdev, "ram"); if (IS_ERR(xcvr->ram_addr)) return PTR_ERR(xcvr->ram_addr); @@ -1421,6 +1578,40 @@ static int fsl_xcvr_probe(struct platform_device *pdev) return PTR_ERR(xcvr->regmap); } + if (xcvr->soc_data->use_phy) { + xcvr->regmap_phy = devm_regmap_init(dev, NULL, xcvr, + &fsl_xcvr_regmap_phy_cfg); + if (IS_ERR(xcvr->regmap_phy)) { + dev_err(dev, "failed to init XCVR PHY regmap: %ld\n", + PTR_ERR(xcvr->regmap_phy)); + return PTR_ERR(xcvr->regmap_phy); + } + + switch (xcvr->soc_data->pll_ver) { + case PLL_MX8MP: + xcvr->regmap_pll = devm_regmap_init(dev, NULL, xcvr, + &fsl_xcvr_regmap_pllv0_cfg); + if (IS_ERR(xcvr->regmap_pll)) { + dev_err(dev, "failed to init XCVR PLL regmap: %ld\n", + PTR_ERR(xcvr->regmap_pll)); + return PTR_ERR(xcvr->regmap_pll); + } + break; + case PLL_MX95: + xcvr->regmap_pll = devm_regmap_init(dev, NULL, xcvr, + &fsl_xcvr_regmap_pllv1_cfg); + if (IS_ERR(xcvr->regmap_pll)) { + dev_err(dev, "failed to init XCVR PLL regmap: %ld\n", + PTR_ERR(xcvr->regmap_pll)); + return PTR_ERR(xcvr->regmap_pll); + } + break; + default: + dev_err(dev, "Error for PLL version %d\n", xcvr->soc_data->pll_ver); + return -EINVAL; + } + } + xcvr->reset = devm_reset_control_get_optional_exclusive(dev, NULL); if (IS_ERR(xcvr->reset)) { dev_err(dev, "failed to get XCVR reset control\n"); @@ -1454,6 +1645,10 @@ static int fsl_xcvr_probe(struct platform_device *pdev) platform_set_drvdata(pdev, xcvr); pm_runtime_enable(dev); regcache_cache_only(xcvr->regmap, true); + if (xcvr->soc_data->use_phy) { + regcache_cache_only(xcvr->regmap_phy, true); + regcache_cache_only(xcvr->regmap_pll, true); + } /* * Register platform component before registering cpu dai for there @@ -1492,7 +1687,8 @@ static int fsl_xcvr_runtime_suspend(struct device *dev) struct fsl_xcvr *xcvr = dev_get_drvdata(dev); int ret; - if (!xcvr->soc_data->spdif_only) { + if (!xcvr->soc_data->spdif_only && + xcvr->mode == FSL_XCVR_MODE_EARC) { /* Assert M0+ reset */ ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_CTRL, FSL_XCVR_EXT_CTRL_CORE_RESET, @@ -1502,6 +1698,10 @@ static int fsl_xcvr_runtime_suspend(struct device *dev) } regcache_cache_only(xcvr->regmap, true); + if (xcvr->soc_data->use_phy) { + regcache_cache_only(xcvr->regmap_phy, true); + regcache_cache_only(xcvr->regmap_pll, true); + } clk_disable_unprepare(xcvr->spba_clk); clk_disable_unprepare(xcvr->phy_clk); @@ -1546,6 +1746,12 @@ static int fsl_xcvr_runtime_resume(struct device *dev) goto stop_phy_clk; } + ret = reset_control_deassert(xcvr->reset); + if (ret) { + dev_err(dev, "failed to deassert M0+ reset.\n"); + goto stop_spba_clk; + } + regcache_cache_only(xcvr->regmap, false); regcache_mark_dirty(xcvr->regmap); ret = regcache_sync(xcvr->regmap); @@ -1555,31 +1761,49 @@ static int fsl_xcvr_runtime_resume(struct device *dev) goto stop_spba_clk; } - if (xcvr->soc_data->spdif_only) - return 0; + if (xcvr->soc_data->use_phy) { + ret = regmap_write(xcvr->regmap, FSL_XCVR_PHY_AI_CTRL_SET, + FSL_XCVR_PHY_AI_CTRL_AI_RESETN); + if (ret < 0) { + dev_err(dev, "Error while release PHY reset: %d\n", ret); + goto stop_spba_clk; + } - ret = reset_control_deassert(xcvr->reset); - if (ret) { - dev_err(dev, "failed to deassert M0+ reset.\n"); - goto stop_spba_clk; + regcache_cache_only(xcvr->regmap_phy, false); + regcache_mark_dirty(xcvr->regmap_phy); + ret = regcache_sync(xcvr->regmap_phy); + if (ret) { + dev_err(dev, "failed to sync phy regcache.\n"); + goto stop_spba_clk; + } + + regcache_cache_only(xcvr->regmap_pll, false); + regcache_mark_dirty(xcvr->regmap_pll); + ret = regcache_sync(xcvr->regmap_pll); + if (ret) { + dev_err(dev, "failed to sync pll regcache.\n"); + goto stop_spba_clk; + } } - ret = fsl_xcvr_load_firmware(xcvr); - if (ret) { - dev_err(dev, "failed to load firmware.\n"); - goto stop_spba_clk; - } + if (xcvr->mode == FSL_XCVR_MODE_EARC) { + ret = fsl_xcvr_load_firmware(xcvr); + if (ret) { + dev_err(dev, "failed to load firmware.\n"); + goto stop_spba_clk; + } - /* Release M0+ reset */ - ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_CTRL, - FSL_XCVR_EXT_CTRL_CORE_RESET, 0); - if (ret < 0) { - dev_err(dev, "M0+ core release failed: %d\n", ret); - goto stop_spba_clk; - } + /* Release M0+ reset */ + ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_CTRL, + FSL_XCVR_EXT_CTRL_CORE_RESET, 0); + if (ret < 0) { + dev_err(dev, "M0+ core release failed: %d\n", ret); + goto stop_spba_clk; + } - /* Let M0+ core complete firmware initialization */ - msleep(50); + /* Let M0+ core complete firmware initialization */ + msleep(50); + } return 0; diff --git a/sound/soc/fsl/fsl_xcvr.h b/sound/soc/fsl/fsl_xcvr.h index c72cb05184df..dade3945cc0c 100644 --- a/sound/soc/fsl/fsl_xcvr.h +++ b/sound/soc/fsl/fsl_xcvr.h @@ -234,6 +234,7 @@ #define FSL_XCVR_TX_DPTH_CTRL_TM_NO_PRE_BME GENMASK(31, 30) #define FSL_XCVR_PHY_AI_CTRL_AI_RESETN BIT(15) +#define FSL_XCVR_PHY_AI_CTRL_AI_RWB BIT(31) #define FSL_XCVR_PLL_CTRL0 0x00 #define FSL_XCVR_PLL_CTRL0_SET 0x04 @@ -241,13 +242,25 @@ #define FSL_XCVR_PLL_NUM 0x20 #define FSL_XCVR_PLL_DEN 0x30 #define FSL_XCVR_PLL_PDIV 0x40 +#define FSL_XCVR_PLL_BANDGAP 0x50 #define FSL_XCVR_PLL_BANDGAP_SET 0x54 +#define FSL_XCVR_PLL_STAT0 0x60 +#define FSL_XCVR_PLL_STAT0_TOG 0x6c + #define FSL_XCVR_PHY_CTRL 0x00 #define FSL_XCVR_PHY_CTRL_SET 0x04 #define FSL_XCVR_PHY_CTRL_CLR 0x08 +#define FSL_XCVR_PHY_CTRL_TOG 0x0c +#define FSL_XCVR_PHY_STATUS 0x10 +#define FSL_XCVR_PHY_ANALOG_TRIM 0x20 +#define FSL_XCVR_PHY_SLEW_RATE_TRIM 0x30 +#define FSL_XCVR_PHY_DATA_TEST_DELAY 0x40 +#define FSL_XCVR_PHY_TEST_CTRL 0x50 +#define FSL_XCVR_PHY_DIFF_CDR_CTRL 0x60 #define FSL_XCVR_PHY_CTRL2 0x70 #define FSL_XCVR_PHY_CTRL2_SET 0x74 #define FSL_XCVR_PHY_CTRL2_CLR 0x78 +#define FSL_XCVR_PHY_CTRL2_TOG 0x7c #define FSL_XCVR_PLL_BANDGAP_EN_VBG BIT(0) #define FSL_XCVR_PLL_CTRL0_HROFF BIT(13) diff --git a/sound/soc/fsl/imx-audmux.c b/sound/soc/fsl/imx-audmux.c index 43e14f2eca8d..cc2918ee2cf5 100644 --- a/sound/soc/fsl/imx-audmux.c +++ b/sound/soc/fsl/imx-audmux.c @@ -237,7 +237,7 @@ static int imx_audmux_parse_dt_defaults(struct platform_device *pdev, child); continue; } - if (!of_property_read_bool(child, "fsl,port-config")) { + if (!of_property_present(child, "fsl,port-config")) { dev_warn(&pdev->dev, "child node \"%pOF\" does not have property fsl,port-config\n", child); continue; diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index 95a57fda0250..ac043ad367ac 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -529,7 +529,7 @@ static int imx_card_parse_of(struct imx_card_data *data) } /* DAPM routes */ - if (of_property_read_bool(dev->of_node, "audio-routing")) { + if (of_property_present(dev->of_node, "audio-routing")) { ret = snd_soc_of_parse_audio_routing(card, "audio-routing"); if (ret) return ret; diff --git a/sound/soc/fsl/imx-rpmsg.c b/sound/soc/fsl/imx-rpmsg.c index ce98d2288193..7cd3aa4c8706 100644 --- a/sound/soc/fsl/imx-rpmsg.c +++ b/sound/soc/fsl/imx-rpmsg.c @@ -218,7 +218,7 @@ static int imx_rpmsg_probe(struct platform_device *pdev) if (ret) goto fail; - if (of_property_read_bool(np, "audio-routing")) { + if (of_property_present(np, "audio-routing")) { ret = snd_soc_of_parse_audio_routing(&data->card, "audio-routing"); if (ret) { dev_err(&pdev->dev, "failed to parse audio-routing: %d\n", ret); diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c index 7655425a3deb..7c422535b01a 100644 --- a/sound/soc/generic/audio-graph-card.c +++ b/sound/soc/generic/audio-graph-card.c @@ -81,18 +81,14 @@ static void graph_parse_convert(struct device *dev, struct simple_util_data *adata) { struct device_node *top = dev->of_node; - struct device_node *port = ep_to_port(ep); - struct device_node *ports = port_to_ports(port); - struct device_node *node = of_graph_get_port_parent(ep); + struct device_node *port __free(device_node) = ep_to_port(ep); + struct device_node *ports __free(device_node) = port_to_ports(port); + struct device_node *node __free(device_node) = of_graph_get_port_parent(ep); simple_util_parse_convert(top, NULL, adata); simple_util_parse_convert(ports, NULL, adata); simple_util_parse_convert(port, NULL, adata); simple_util_parse_convert(ep, NULL, adata); - - of_node_put(port); - of_node_put(ports); - of_node_put(node); } static int graph_parse_node(struct simple_util_priv *priv, @@ -140,10 +136,10 @@ static int graph_link_init(struct simple_util_priv *priv, struct device_node *top = dev->of_node; struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); - struct device_node *port_cpu = ep_to_port(ep_cpu); - struct device_node *port_codec = ep_to_port(ep_codec); - struct device_node *ports_cpu = port_to_ports(port_cpu); - struct device_node *ports_codec = port_to_ports(port_codec); + struct device_node *port_cpu __free(device_node) = ep_to_port(ep_cpu); + struct device_node *port_codec __free(device_node) = ep_to_port(ep_codec); + struct device_node *ports_cpu __free(device_node) = port_to_ports(port_cpu); + struct device_node *ports_codec __free(device_node) = port_to_ports(port_codec); enum snd_soc_trigger_order trigger_start = SND_SOC_TRIGGER_ORDER_DEFAULT; enum snd_soc_trigger_order trigger_stop = SND_SOC_TRIGGER_ORDER_DEFAULT; bool playback_only = 0, capture_only = 0; @@ -152,7 +148,7 @@ static int graph_link_init(struct simple_util_priv *priv, ret = simple_util_parse_daifmt(dev, ep_cpu, ep_codec, NULL, &dai_link->dai_fmt); if (ret < 0) - goto init_end; + return ret; graph_util_parse_link_direction(top, &playback_only, &capture_only); graph_util_parse_link_direction(port_cpu, &playback_only, &capture_only); @@ -187,14 +183,7 @@ static int graph_link_init(struct simple_util_priv *priv, if (priv->ops) dai_link->ops = priv->ops; - ret = simple_util_set_dailink_name(dev, dai_link, name); -init_end: - of_node_put(ports_cpu); - of_node_put(ports_codec); - of_node_put(port_cpu); - of_node_put(port_codec); - - return ret; + return simple_util_set_dailink_name(dev, dai_link, name); } static int graph_dai_link_of_dpcm(struct simple_util_priv *priv, @@ -250,8 +239,6 @@ static int graph_dai_link_of_dpcm(struct simple_util_priv *priv, } else { struct snd_soc_codec_conf *cconf = simple_props_to_codec_conf(dai_props, 0); struct snd_soc_dai_link_component *codecs = snd_soc_link_to_codec(dai_link, 0); - struct device_node *port; - struct device_node *ports; /* CPU is dummy */ @@ -267,14 +254,12 @@ static int graph_dai_link_of_dpcm(struct simple_util_priv *priv, "be.%pOFP.%s", codecs->of_node, codecs->dai_name); /* check "prefix" from top node */ - port = ep_to_port(ep); - ports = port_to_ports(port); + struct device_node *port __free(device_node) = ep_to_port(ep); + struct device_node *ports __free(device_node) = port_to_ports(port); + snd_soc_of_parse_node_prefix(top, cconf, codecs->of_node, "prefix"); snd_soc_of_parse_node_prefix(ports, cconf, codecs->of_node, "prefix"); snd_soc_of_parse_node_prefix(port, cconf, codecs->of_node, "prefix"); - - of_node_put(ports); - of_node_put(port); } graph_parse_convert(dev, ep, &dai_props->adata); @@ -361,8 +346,6 @@ static int __graph_for_each_link(struct simple_util_priv *priv, struct device *dev = simple_priv_to_dev(priv); struct device_node *node = dev->of_node; struct device_node *cpu_port; - struct device_node *codec_ep; - struct device_node *codec_port; struct device_node *codec_port_old = NULL; struct simple_util_data adata; int rc, ret = 0; @@ -374,8 +357,8 @@ static int __graph_for_each_link(struct simple_util_priv *priv, /* loop for all CPU endpoint */ for_each_of_graph_port_endpoint(cpu_port, cpu_ep) { /* get codec */ - codec_ep = of_graph_get_remote_endpoint(cpu_ep); - codec_port = ep_to_port(codec_ep); + struct device_node *codec_ep __free(device_node) = of_graph_get_remote_endpoint(cpu_ep); + struct device_node *codec_port __free(device_node) = ep_to_port(codec_ep); /* get convert-xxx property */ memset(&adata, 0, sizeof(adata)); @@ -399,9 +382,6 @@ static int __graph_for_each_link(struct simple_util_priv *priv, ret = func_noml(priv, cpu_ep, codec_ep, li); } - of_node_put(codec_ep); - of_node_put(codec_port); - if (ret < 0) return ret; diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c index 1f5c4e8ff1b9..ee94b256b770 100644 --- a/sound/soc/generic/audio-graph-card2.c +++ b/sound/soc/generic/audio-graph-card2.c @@ -331,10 +331,9 @@ static int graph_lnk_is_multi(struct device_node *lnk) return __graph_get_type(lnk) == GRAPH_MULTI; } -static struct device_node *graph_get_next_multi_ep(struct device_node **port) +static struct device_node *graph_get_next_multi_ep(struct device_node **port, int idx) { - struct device_node *ports = port_to_ports(*port); - struct device_node *ep = NULL; + struct device_node *ports __free(device_node) = port_to_ports(*port); struct device_node *rep = NULL; /* @@ -352,15 +351,22 @@ static struct device_node *graph_get_next_multi_ep(struct device_node **port) * port@1 { rep1 }; * }; */ - *port = of_graph_get_next_port(ports, *port); + + /* + * Don't use of_graph_get_next_port() here + * + * In overlay case, "port" are not necessarily in order. So we need to use + * of_graph_get_port_by_id() instead + */ + of_node_put(*port); + + *port = of_graph_get_port_by_id(ports, idx); if (*port) { - ep = of_graph_get_next_port_endpoint(*port, NULL); + struct device_node *ep __free(device_node) = of_graph_get_next_port_endpoint(*port, NULL); + rep = of_graph_get_remote_endpoint(ep); } - of_node_put(ep); - of_node_put(ports); - return rep; } @@ -373,16 +379,13 @@ static const struct snd_soc_ops graph_ops = { static void graph_parse_convert(struct device_node *ep, struct simple_dai_props *props) { - struct device_node *port = ep_to_port(ep); - struct device_node *ports = port_to_ports(port); + struct device_node *port __free(device_node) = ep_to_port(ep); + struct device_node *ports __free(device_node) = port_to_ports(port); struct simple_util_data *adata = &props->adata; simple_util_parse_convert(ports, NULL, adata); simple_util_parse_convert(port, NULL, adata); simple_util_parse_convert(ep, NULL, adata); - - of_node_put(port); - of_node_put(ports); } static int __graph_parse_node(struct simple_util_priv *priv, @@ -471,14 +474,11 @@ static int __graph_parse_node(struct simple_util_priv *priv, if (!is_cpu && gtype == GRAPH_DPCM) { struct snd_soc_dai_link_component *codecs = snd_soc_link_to_codec(dai_link, idx); struct snd_soc_codec_conf *cconf = simple_props_to_codec_conf(dai_props, idx); - struct device_node *rport = ep_to_port(ep); - struct device_node *rports = port_to_ports(rport); + struct device_node *rport __free(device_node) = ep_to_port(ep); + struct device_node *rports __free(device_node) = port_to_ports(rport); snd_soc_of_parse_node_prefix(rports, cconf, codecs->of_node, "prefix"); snd_soc_of_parse_node_prefix(rport, cconf, codecs->of_node, "prefix"); - - of_node_put(rport); - of_node_put(rports); } if (is_cpu) { @@ -526,25 +526,21 @@ static int graph_parse_node_multi_nm(struct snd_soc_dai_link *dai_link, * }; * }; */ - struct device_node *mcpu_ep = of_graph_get_next_port_endpoint(mcpu_port, NULL); - struct device_node *mcpu_ports = port_to_ports(mcpu_port); - struct device_node *mcpu_port_top = of_graph_get_next_port(mcpu_ports, NULL); - struct device_node *mcpu_ep_top = of_graph_get_next_port_endpoint(mcpu_port_top, NULL); - struct device_node *mcodec_ep_top = of_graph_get_remote_endpoint(mcpu_ep_top); - struct device_node *mcodec_port_top = ep_to_port(mcodec_ep_top); - struct device_node *mcodec_ports = port_to_ports(mcodec_port_top); + struct device_node *mcpu_ep __free(device_node) = of_graph_get_next_port_endpoint(mcpu_port, NULL); + struct device_node *mcpu_ports __free(device_node) = port_to_ports(mcpu_port); + struct device_node *mcpu_port_top __free(device_node) = of_graph_get_next_port(mcpu_ports, NULL); + struct device_node *mcpu_ep_top __free(device_node) = of_graph_get_next_port_endpoint(mcpu_port_top, NULL); + struct device_node *mcodec_ep_top __free(device_node) = of_graph_get_remote_endpoint(mcpu_ep_top); + struct device_node *mcodec_port_top __free(device_node) = ep_to_port(mcodec_ep_top); + struct device_node *mcodec_ports __free(device_node) = port_to_ports(mcodec_port_top); int nm_max = max(dai_link->num_cpus, dai_link->num_codecs); int ret = 0; - if (cpu_idx > dai_link->num_cpus) { - ret = -EINVAL; - goto mcpu_err; - } + if (cpu_idx > dai_link->num_cpus) + return -EINVAL; for_each_of_graph_port_endpoint(mcpu_port, mcpu_ep_n) { - struct device_node *mcodec_ep_n; - struct device_node *mcodec_port; - int codec_idx; + int codec_idx = 0; /* ignore 1st ep which is for element */ if (mcpu_ep_n == mcpu_ep) @@ -553,16 +549,13 @@ static int graph_parse_node_multi_nm(struct snd_soc_dai_link *dai_link, if (*nm_idx > nm_max) break; - mcodec_ep_n = of_graph_get_remote_endpoint(mcpu_ep_n); - mcodec_port = ep_to_port(mcodec_ep_n); + struct device_node *mcodec_ep_n __free(device_node) = of_graph_get_remote_endpoint(mcpu_ep_n); + struct device_node *mcodec_port __free(device_node) = ep_to_port(mcodec_ep_n); - if (mcodec_ports != port_to_ports(mcodec_port)) { - ret = -EINVAL; - goto mcpu_err; - } - - codec_idx = 0; ret = -EINVAL; + if (mcodec_ports != port_to_ports(mcodec_port)) + break; + for_each_of_graph_port(mcodec_ports, mcodec_port_i) { /* ignore 1st port which is for pair connection */ @@ -582,18 +575,9 @@ static int graph_parse_node_multi_nm(struct snd_soc_dai_link *dai_link, } codec_idx++; } - of_node_put(mcodec_port); - of_node_put(mcodec_ep_n); if (ret < 0) break; } -mcpu_err: - of_node_put(mcpu_ep); - of_node_put(mcpu_port_top); - of_node_put(mcpu_ep_top); - of_node_put(mcodec_ep_top); - of_node_put(mcodec_port_top); - of_node_put(mcodec_ports); return ret; } @@ -605,7 +589,6 @@ static int graph_parse_node_multi(struct simple_util_priv *priv, { struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct device *dev = simple_priv_to_dev(priv); - struct device_node *ep; int ret = -ENOMEM; int nm_idx = 0; int nm_max = max(dai_link->num_cpus, dai_link->num_codecs); @@ -640,12 +623,11 @@ static int graph_parse_node_multi(struct simple_util_priv *priv, * }; * }; */ - ep = graph_get_next_multi_ep(&port); + struct device_node *ep __free(device_node) = graph_get_next_multi_ep(&port, idx + 1); if (!ep) break; ret = __graph_parse_node(priv, gtype, ep, li, is_cpu, idx); - of_node_put(ep); if (ret < 0) goto multi_err; @@ -666,30 +648,26 @@ multi_err: static int graph_parse_node_single(struct simple_util_priv *priv, enum graph_type gtype, - struct device_node *port, + struct device_node *ep, struct link_info *li, int is_cpu) { - struct device_node *ep = of_graph_get_next_port_endpoint(port, NULL); - int ret = __graph_parse_node(priv, gtype, ep, li, is_cpu, 0); - - of_node_put(ep); - - return ret; + return __graph_parse_node(priv, gtype, ep, li, is_cpu, 0); } static int graph_parse_node(struct simple_util_priv *priv, enum graph_type gtype, - struct device_node *port, + struct device_node *ep, struct link_info *li, int is_cpu) { + struct device_node *port __free(device_node) = ep_to_port(ep); + if (graph_lnk_is_multi(port)) return graph_parse_node_multi(priv, gtype, port, li, is_cpu); else - return graph_parse_node_single(priv, gtype, port, li, is_cpu); + return graph_parse_node_single(priv, gtype, ep, li, is_cpu); } -static void graph_parse_daifmt(struct device_node *node, - unsigned int *daifmt, unsigned int *bit_frame) +static void graph_parse_daifmt(struct device_node *node, unsigned int *daifmt) { unsigned int fmt; @@ -714,16 +692,6 @@ static void graph_parse_daifmt(struct device_node *node, * }; */ - /* - * clock_provider: - * - * It can be judged it is provider - * if (A) or (B) or (C) has bitclock-master / frame-master flag. - * - * use "or" - */ - *bit_frame |= snd_soc_daifmt_parse_clock_provider_as_bitmap(node, NULL); - #define update_daifmt(name) \ if (!(*daifmt & SND_SOC_DAIFMT_##name##_MASK) && \ (fmt & SND_SOC_DAIFMT_##name##_MASK)) \ @@ -741,51 +709,64 @@ static void graph_parse_daifmt(struct device_node *node, update_daifmt(INV); } +static unsigned int graph_parse_bitframe(struct device_node *ep) +{ + struct device_node *port __free(device_node) = ep_to_port(ep); + struct device_node *ports __free(device_node) = port_to_ports(port); + + return snd_soc_daifmt_clock_provider_from_bitmap( + snd_soc_daifmt_parse_clock_provider_as_bitmap(ep, NULL) | + snd_soc_daifmt_parse_clock_provider_as_bitmap(port, NULL) | + snd_soc_daifmt_parse_clock_provider_as_bitmap(ports, NULL)); +} + static void graph_link_init(struct simple_util_priv *priv, struct device_node *lnk, - struct device_node *port_cpu, - struct device_node *port_codec, + struct device_node *ep_cpu, + struct device_node *ep_codec, struct link_info *li, int is_cpu_node) { struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); - struct device_node *ep_cpu, *ep_codec; - struct device_node *ports_cpu, *ports_codec; - unsigned int daifmt = 0, daiclk = 0; + struct device_node *port_cpu = ep_to_port(ep_cpu); + struct device_node *port_codec = ep_to_port(ep_codec); + struct device_node *multi_cpu_port = NULL, *multi_codec_port = NULL; + struct snd_soc_dai_link_component *dlc; + unsigned int daifmt = 0; bool playback_only = 0, capture_only = 0; enum snd_soc_trigger_order trigger_start = SND_SOC_TRIGGER_ORDER_DEFAULT; enum snd_soc_trigger_order trigger_stop = SND_SOC_TRIGGER_ORDER_DEFAULT; - unsigned int bit_frame = 0; + int multi_cpu_port_idx = 1, multi_codec_port_idx = 1; + int i; - of_node_get(port_cpu); if (graph_lnk_is_multi(port_cpu)) { - ep_cpu = graph_get_next_multi_ep(&port_cpu); + multi_cpu_port = port_cpu; + ep_cpu = graph_get_next_multi_ep(&multi_cpu_port, multi_cpu_port_idx++); of_node_put(port_cpu); port_cpu = ep_to_port(ep_cpu); } else { - ep_cpu = of_graph_get_next_port_endpoint(port_cpu, NULL); + of_node_get(ep_cpu); } - ports_cpu = port_to_ports(port_cpu); + struct device_node *ports_cpu __free(device_node) = port_to_ports(port_cpu); - of_node_get(port_codec); if (graph_lnk_is_multi(port_codec)) { - ep_codec = graph_get_next_multi_ep(&port_codec); + multi_codec_port = port_codec; + ep_codec = graph_get_next_multi_ep(&multi_codec_port, multi_codec_port_idx++); of_node_put(port_codec); port_codec = ep_to_port(ep_codec); } else { - ep_codec = of_graph_get_next_port_endpoint(port_codec, NULL); + of_node_get(ep_codec); } - ports_codec = port_to_ports(port_codec); + struct device_node *ports_codec __free(device_node) = port_to_ports(port_codec); - - graph_parse_daifmt(ep_cpu, &daifmt, &bit_frame); - graph_parse_daifmt(ep_codec, &daifmt, &bit_frame); - graph_parse_daifmt(port_cpu, &daifmt, &bit_frame); - graph_parse_daifmt(port_codec, &daifmt, &bit_frame); - graph_parse_daifmt(ports_cpu, &daifmt, &bit_frame); - graph_parse_daifmt(ports_codec, &daifmt, &bit_frame); - graph_parse_daifmt(lnk, &daifmt, &bit_frame); + graph_parse_daifmt(ep_cpu, &daifmt); + graph_parse_daifmt(ep_codec, &daifmt); + graph_parse_daifmt(port_cpu, &daifmt); + graph_parse_daifmt(port_codec, &daifmt); + graph_parse_daifmt(ports_cpu, &daifmt); + graph_parse_daifmt(ports_codec, &daifmt); + graph_parse_daifmt(lnk, &daifmt); graph_util_parse_link_direction(lnk, &playback_only, &capture_only); graph_util_parse_link_direction(ports_cpu, &playback_only, &capture_only); @@ -811,14 +792,21 @@ static void graph_link_init(struct simple_util_priv *priv, graph_util_parse_trigger_order(priv, ep_cpu, &trigger_start, &trigger_stop); graph_util_parse_trigger_order(priv, ep_codec, &trigger_start, &trigger_stop); - /* - * convert bit_frame - * We need to flip clock_provider if it was CPU node, - * because it is Codec base. - */ - daiclk = snd_soc_daifmt_clock_provider_from_bitmap(bit_frame); - if (is_cpu_node) - daiclk = snd_soc_daifmt_clock_provider_flipped(daiclk); + for_each_link_cpus(dai_link, i, dlc) { + dlc->ext_fmt = graph_parse_bitframe(ep_cpu); + + if (multi_cpu_port) + ep_cpu = graph_get_next_multi_ep(&multi_cpu_port, multi_cpu_port_idx++); + } + + for_each_link_codecs(dai_link, i, dlc) { + dlc->ext_fmt = graph_parse_bitframe(ep_codec); + + if (multi_codec_port) + ep_codec = graph_get_next_multi_ep(&multi_codec_port, multi_codec_port_idx++); + } + + /*** Don't use port_cpu / port_codec after here ***/ dai_link->playback_only = playback_only; dai_link->capture_only = capture_only; @@ -826,14 +814,12 @@ static void graph_link_init(struct simple_util_priv *priv, dai_link->trigger_start = trigger_start; dai_link->trigger_stop = trigger_stop; - dai_link->dai_fmt = daifmt | daiclk; + dai_link->dai_fmt = daifmt; dai_link->init = simple_util_dai_init; dai_link->ops = &graph_ops; if (priv->ops) dai_link->ops = priv->ops; - of_node_put(ports_cpu); - of_node_put(ports_codec); of_node_put(port_cpu); of_node_put(port_codec); of_node_put(ep_cpu); @@ -845,8 +831,8 @@ int audio_graph2_link_normal(struct simple_util_priv *priv, struct link_info *li) { struct device_node *cpu_port = lnk; - struct device_node *cpu_ep = of_graph_get_next_port_endpoint(cpu_port, NULL); - struct device_node *codec_port = of_graph_get_remote_port(cpu_ep); + struct device_node *cpu_ep __free(device_node) = of_graph_get_next_port_endpoint(cpu_port, NULL); + struct device_node *codec_ep __free(device_node) = of_graph_get_remote_endpoint(cpu_ep); int ret; /* @@ -854,21 +840,18 @@ int audio_graph2_link_normal(struct simple_util_priv *priv, * see * __graph_parse_node() :: DAI Naming */ - ret = graph_parse_node(priv, GRAPH_NORMAL, codec_port, li, 0); + ret = graph_parse_node(priv, GRAPH_NORMAL, codec_ep, li, 0); if (ret < 0) - goto err; + return ret; /* * call CPU, and set DAI Name */ - ret = graph_parse_node(priv, GRAPH_NORMAL, cpu_port, li, 1); + ret = graph_parse_node(priv, GRAPH_NORMAL, cpu_ep, li, 1); if (ret < 0) - goto err; + return ret; - graph_link_init(priv, lnk, cpu_port, codec_port, li, 1); -err: - of_node_put(codec_port); - of_node_put(cpu_ep); + graph_link_init(priv, lnk, cpu_ep, codec_ep, li, 1); return ret; } @@ -878,17 +861,17 @@ int audio_graph2_link_dpcm(struct simple_util_priv *priv, struct device_node *lnk, struct link_info *li) { - struct device_node *ep = of_graph_get_next_port_endpoint(lnk, NULL); - struct device_node *rep = of_graph_get_remote_endpoint(ep); - struct device_node *cpu_port = NULL; - struct device_node *codec_port = NULL; + struct device_node *ep __free(device_node) = of_graph_get_next_port_endpoint(lnk, NULL); + struct device_node *rep __free(device_node) = of_graph_get_remote_endpoint(ep); + struct device_node *cpu_ep = NULL; + struct device_node *codec_ep = NULL; struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); int is_cpu = graph_util_is_ports0(lnk); int ret; if (is_cpu) { - cpu_port = of_graph_get_remote_port(ep); /* rport */ + cpu_ep = rep; /* * dpcm { @@ -917,12 +900,12 @@ int audio_graph2_link_dpcm(struct simple_util_priv *priv, dai_link->dynamic = 1; dai_link->dpcm_merged_format = 1; - ret = graph_parse_node(priv, GRAPH_DPCM, cpu_port, li, 1); + ret = graph_parse_node(priv, GRAPH_DPCM, cpu_ep, li, 1); if (ret) - goto err; + return ret; } else { - codec_port = of_graph_get_remote_port(ep); /* rport */ + codec_ep = rep; /* * dpcm { @@ -953,20 +936,15 @@ int audio_graph2_link_dpcm(struct simple_util_priv *priv, dai_link->no_pcm = 1; dai_link->be_hw_params_fixup = simple_util_be_hw_params_fixup; - ret = graph_parse_node(priv, GRAPH_DPCM, codec_port, li, 0); + ret = graph_parse_node(priv, GRAPH_DPCM, codec_ep, li, 0); if (ret < 0) - goto err; + return ret; } graph_parse_convert(ep, dai_props); /* at node of <dpcm> */ graph_parse_convert(rep, dai_props); /* at node of <CPU/Codec> */ - graph_link_init(priv, lnk, cpu_port, codec_port, li, is_cpu); -err: - of_node_put(ep); - of_node_put(rep); - of_node_put(cpu_port); - of_node_put(codec_port); + graph_link_init(priv, lnk, cpu_ep, codec_ep, li, is_cpu); return ret; } @@ -977,9 +955,9 @@ int audio_graph2_link_c2c(struct simple_util_priv *priv, struct link_info *li) { struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); - struct device_node *port0, *port1, *ports; - struct device_node *codec0_port, *codec1_port; - struct device_node *ep0, *ep1; + struct device_node *port0 = lnk; + struct device_node *ports __free(device_node) = port_to_ports(port0); + struct device_node *port1 __free(device_node) = of_graph_get_next_port(ports, port0); u32 val = 0; int ret = -EINVAL; @@ -999,10 +977,6 @@ int audio_graph2_link_c2c(struct simple_util_priv *priv, * }; * }; */ - of_node_get(lnk); - port0 = lnk; - ports = port_to_ports(port0); - port1 = of_graph_get_next_port(ports, port0); /* * Card2 can use original Codec2Codec settings if DT has. @@ -1019,7 +993,7 @@ int audio_graph2_link_c2c(struct simple_util_priv *priv, c2c_conf = devm_kzalloc(dev, sizeof(*c2c_conf), GFP_KERNEL); if (!c2c_conf) - goto err1; + return ret; c2c_conf->formats = SNDRV_PCM_FMTBIT_S32_LE; /* update ME */ c2c_conf->rates = SNDRV_PCM_RATE_8000_384000; @@ -1032,38 +1006,29 @@ int audio_graph2_link_c2c(struct simple_util_priv *priv, dai_link->num_c2c_params = 1; } - ep0 = of_graph_get_next_port_endpoint(port0, NULL); - ep1 = of_graph_get_next_port_endpoint(port1, NULL); + struct device_node *ep0 __free(device_node) = of_graph_get_next_port_endpoint(port0, NULL); + struct device_node *ep1 __free(device_node) = of_graph_get_next_port_endpoint(port1, NULL); - codec0_port = of_graph_get_remote_port(ep0); - codec1_port = of_graph_get_remote_port(ep1); + struct device_node *codec0_ep __free(device_node) = of_graph_get_remote_endpoint(ep0); + struct device_node *codec1_ep __free(device_node) = of_graph_get_remote_endpoint(ep1); /* * call Codec first. * see * __graph_parse_node() :: DAI Naming */ - ret = graph_parse_node(priv, GRAPH_C2C, codec1_port, li, 0); + ret = graph_parse_node(priv, GRAPH_C2C, codec1_ep, li, 0); if (ret < 0) - goto err2; + return ret; /* * call CPU, and set DAI Name */ - ret = graph_parse_node(priv, GRAPH_C2C, codec0_port, li, 1); + ret = graph_parse_node(priv, GRAPH_C2C, codec0_ep, li, 1); if (ret < 0) - goto err2; + return ret; - graph_link_init(priv, lnk, codec0_port, codec1_port, li, 1); -err2: - of_node_put(ep0); - of_node_put(ep1); - of_node_put(codec0_port); - of_node_put(codec1_port); -err1: - of_node_put(ports); - of_node_put(port0); - of_node_put(port1); + graph_link_init(priv, lnk, codec0_ep, codec1_ep, li, 1); return ret; } @@ -1153,8 +1118,8 @@ static int graph_count_normal(struct simple_util_priv *priv, struct link_info *li) { struct device_node *cpu_port = lnk; - struct device_node *cpu_ep = of_graph_get_next_port_endpoint(cpu_port, NULL); - struct device_node *codec_port = of_graph_get_remote_port(cpu_ep); + struct device_node *cpu_ep __free(device_node) = of_graph_get_next_port_endpoint(cpu_port, NULL); + struct device_node *codec_port __free(device_node) = of_graph_get_remote_port(cpu_ep); /* * CPU { @@ -1171,9 +1136,6 @@ static int graph_count_normal(struct simple_util_priv *priv, li->num[li->link].codecs = graph_counter(codec_port); - of_node_put(cpu_ep); - of_node_put(codec_port); - return 0; } @@ -1181,8 +1143,8 @@ static int graph_count_dpcm(struct simple_util_priv *priv, struct device_node *lnk, struct link_info *li) { - struct device_node *ep = of_graph_get_next_port_endpoint(lnk, NULL); - struct device_node *rport = of_graph_get_remote_port(ep); + struct device_node *ep __free(device_node) = of_graph_get_next_port_endpoint(lnk, NULL); + struct device_node *rport __free(device_node) = of_graph_get_remote_port(ep); /* * dpcm { @@ -1211,9 +1173,6 @@ static int graph_count_dpcm(struct simple_util_priv *priv, li->num[li->link].codecs = graph_counter(rport); /* BE */ } - of_node_put(ep); - of_node_put(rport); - return 0; } @@ -1221,13 +1180,13 @@ static int graph_count_c2c(struct simple_util_priv *priv, struct device_node *lnk, struct link_info *li) { - struct device_node *ports = port_to_ports(lnk); - struct device_node *port0 = lnk; - struct device_node *port1 = of_graph_get_next_port(ports, of_node_get(port0)); - struct device_node *ep0 = of_graph_get_next_port_endpoint(port0, NULL); - struct device_node *ep1 = of_graph_get_next_port_endpoint(port1, NULL); - struct device_node *codec0 = of_graph_get_remote_port(ep0); - struct device_node *codec1 = of_graph_get_remote_port(ep1); + struct device_node *ports __free(device_node) = port_to_ports(lnk); + struct device_node *port0 = of_node_get(lnk); + struct device_node *port1 = of_node_get(of_graph_get_next_port(ports, of_node_get(port0))); + struct device_node *ep0 __free(device_node) = of_graph_get_next_port_endpoint(port0, NULL); + struct device_node *ep1 __free(device_node) = of_graph_get_next_port_endpoint(port1, NULL); + struct device_node *codec0 __free(device_node) = of_graph_get_remote_port(ep0); + struct device_node *codec1 __free(device_node) = of_graph_get_remote_port(ep1); /* * codec2codec { @@ -1247,13 +1206,6 @@ static int graph_count_c2c(struct simple_util_priv *priv, li->num[li->link].codecs = graph_counter(codec1); - of_node_put(ports); - of_node_put(port1); - of_node_put(ep0); - of_node_put(ep1); - of_node_put(codec0); - of_node_put(codec1); - return 0; } diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 24b371f32066..dd414634b4ac 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -139,10 +139,9 @@ int simple_util_parse_tdm_width_map(struct device *dev, struct device_node *np, int n, i, ret; u32 *p; - if (!of_property_read_bool(np, "dai-tdm-slot-width-map")) - return 0; - n = of_property_count_elems_of_size(np, "dai-tdm-slot-width-map", sizeof(u32)); + if (n <= 0) + return 0; if (n % 3) { dev_err(dev, "Invalid number of cells for dai-tdm-slot-width-map\n"); return -EINVAL; @@ -296,7 +295,7 @@ int simple_util_startup(struct snd_pcm_substream *substream) { struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct simple_util_priv *priv = snd_soc_card_get_drvdata(rtd->card); - struct simple_dai_props *props = simple_priv_to_props(priv, rtd->id); + struct simple_dai_props *props = runtime_simple_priv_to_props(priv, rtd); struct simple_util_dai *dai; unsigned int fixed_sysclk = 0; int i1, i2, i; @@ -357,7 +356,7 @@ void simple_util_shutdown(struct snd_pcm_substream *substream) { struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct simple_util_priv *priv = snd_soc_card_get_drvdata(rtd->card); - struct simple_dai_props *props = simple_priv_to_props(priv, rtd->id); + struct simple_dai_props *props = runtime_simple_priv_to_props(priv, rtd); struct simple_util_dai *dai; int i; @@ -365,8 +364,7 @@ void simple_util_shutdown(struct snd_pcm_substream *substream) struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, i); if (props->mclk_fs && !dai->clk_fixed && !snd_soc_dai_active(cpu_dai)) - snd_soc_dai_set_sysclk(cpu_dai, - 0, 0, SND_SOC_CLOCK_OUT); + snd_soc_dai_set_sysclk(cpu_dai, 0, 0, dai->clk_direction); simple_clk_disable(dai); } @@ -374,8 +372,7 @@ void simple_util_shutdown(struct snd_pcm_substream *substream) struct snd_soc_dai *codec_dai = snd_soc_rtd_to_codec(rtd, i); if (props->mclk_fs && !dai->clk_fixed && !snd_soc_dai_active(codec_dai)) - snd_soc_dai_set_sysclk(codec_dai, - 0, 0, SND_SOC_CLOCK_IN); + snd_soc_dai_set_sysclk(codec_dai, 0, 0, dai->clk_direction); simple_clk_disable(dai); } @@ -448,7 +445,7 @@ int simple_util_hw_params(struct snd_pcm_substream *substream, struct simple_util_dai *pdai; struct snd_soc_dai *sdai; struct simple_util_priv *priv = snd_soc_card_get_drvdata(rtd->card); - struct simple_dai_props *props = simple_priv_to_props(priv, rtd->id); + struct simple_dai_props *props = runtime_simple_priv_to_props(priv, rtd); unsigned int mclk, mclk_fs = 0; int i, ret; @@ -483,13 +480,15 @@ int simple_util_hw_params(struct snd_pcm_substream *substream, } for_each_rtd_codec_dais(rtd, i, sdai) { - ret = snd_soc_dai_set_sysclk(sdai, 0, mclk, SND_SOC_CLOCK_IN); + pdai = simple_props_to_dai_codec(props, i); + ret = snd_soc_dai_set_sysclk(sdai, 0, mclk, pdai->clk_direction); if (ret && ret != -ENOTSUPP) return ret; } for_each_rtd_cpu_dais(rtd, i, sdai) { - ret = snd_soc_dai_set_sysclk(sdai, 0, mclk, SND_SOC_CLOCK_OUT); + pdai = simple_props_to_dai_cpu(props, i); + ret = snd_soc_dai_set_sysclk(sdai, 0, mclk, pdai->clk_direction); if (ret && ret != -ENOTSUPP) return ret; } @@ -517,7 +516,7 @@ int simple_util_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, struct snd_pcm_hw_params *params) { struct simple_util_priv *priv = snd_soc_card_get_drvdata(rtd->card); - struct simple_dai_props *dai_props = simple_priv_to_props(priv, rtd->id); + struct simple_dai_props *dai_props = runtime_simple_priv_to_props(priv, rtd); struct simple_util_data *data = &dai_props->adata; struct snd_interval *rate = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE); struct snd_interval *channels = hw_param_interval(params, SNDRV_PCM_HW_PARAM_CHANNELS); @@ -628,7 +627,7 @@ static int simple_init_for_codec2codec(struct snd_soc_pcm_runtime *rtd, int simple_util_dai_init(struct snd_soc_pcm_runtime *rtd) { struct simple_util_priv *priv = snd_soc_card_get_drvdata(rtd->card); - struct simple_dai_props *props = simple_priv_to_props(priv, rtd->id); + struct simple_dai_props *props = runtime_simple_priv_to_props(priv, rtd); struct simple_util_dai *dai; int i, ret; @@ -713,7 +712,7 @@ int simple_util_parse_routing(struct snd_soc_card *card, snprintf(prop, sizeof(prop), "%s%s", prefix, "routing"); - if (!of_property_read_bool(node, prop)) + if (!of_property_present(node, prop)) return 0; return snd_soc_of_parse_audio_routing(card, prop); @@ -731,7 +730,7 @@ int simple_util_parse_widgets(struct snd_soc_card *card, snprintf(prop, sizeof(prop), "%s%s", prefix, "widgets"); - if (of_property_read_bool(node, prop)) + if (of_property_present(node, prop)) return snd_soc_of_parse_audio_simple_widgets(card, prop); /* no widgets is not error */ @@ -1005,36 +1004,27 @@ EXPORT_SYMBOL_GPL(graph_util_card_probe); int graph_util_is_ports0(struct device_node *np) { - struct device_node *port, *ports, *ports0, *top; - int ret; + struct device_node *parent __free(device_node) = of_get_parent(np); + struct device_node *port; /* np is "endpoint" or "port" */ - if (of_node_name_eq(np, "endpoint")) { - port = of_get_parent(np); - } else { + if (of_node_name_eq(np, "endpoint")) + port = parent; + else port = np; - of_node_get(port); - } - ports = of_get_parent(port); - top = of_get_parent(ports); - ports0 = of_get_child_by_name(top, "ports"); + struct device_node *ports __free(device_node) = of_get_parent(port); + struct device_node *top __free(device_node) = of_get_parent(ports); + struct device_node *ports0 __free(device_node) = of_get_child_by_name(top, "ports"); - ret = ports0 == ports; - - of_node_put(port); - of_node_put(ports); - of_node_put(ports0); - of_node_put(top); - - return ret; + return ports0 == ports; } EXPORT_SYMBOL_GPL(graph_util_is_ports0); static int graph_get_dai_id(struct device_node *ep) { - struct device_node *node; - struct device_node *endpoint; + struct device_node *node __free(device_node) = of_graph_get_port_parent(ep); + struct device_node *port __free(device_node) = of_get_parent(ep); struct of_endpoint info; int i, id; int ret; @@ -1053,16 +1043,16 @@ static int graph_get_dai_id(struct device_node *ep) * only of_graph_parse_endpoint(). * We need to check "reg" property */ - if (of_property_present(ep, "reg")) - return info.id; - node = of_get_parent(ep); - ret = of_property_present(node, "reg"); - of_node_put(node); + /* check port first */ + ret = of_property_present(port, "reg"); if (ret) return info.port; + + /* check endpoint 2nd as backup */ + if (of_property_present(ep, "reg")) + return info.id; } - node = of_graph_get_port_parent(ep); /* * Non HDMI sound case, counting port/endpoint on its DT @@ -1070,14 +1060,14 @@ static int graph_get_dai_id(struct device_node *ep) */ i = 0; id = -1; - for_each_endpoint_of_node(node, endpoint) { - if (endpoint == ep) + for_each_of_graph_port(node, p) { + if (port == p) { id = i; + break; + } i++; } - of_node_put(node); - if (id < 0) return -ENODEV; @@ -1087,7 +1077,6 @@ static int graph_get_dai_id(struct device_node *ep) int graph_util_parse_dai(struct device *dev, struct device_node *ep, struct snd_soc_dai_link_component *dlc, int *is_single_link) { - struct device_node *node; struct of_phandle_args args = {}; struct snd_soc_dai *dai; int ret; @@ -1095,7 +1084,7 @@ int graph_util_parse_dai(struct device *dev, struct device_node *ep, if (!ep) return 0; - node = of_graph_get_port_parent(ep); + struct device_node *node __free(device_node) = of_graph_get_port_parent(ep); /* * Try to find from DAI node @@ -1136,10 +1125,8 @@ int graph_util_parse_dai(struct device *dev, struct device_node *ep, * if he unbinded CPU or Codec. */ ret = snd_soc_get_dlc(&args, dlc); - if (ret < 0) { - of_node_put(node); + if (ret < 0) return ret; - } parse_dai_end: if (is_single_link) diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index 76a1d05e2ebe..afe7e79ffdbd 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -120,14 +120,12 @@ static void simple_parse_convert(struct device *dev, struct simple_util_data *adata) { struct device_node *top = dev->of_node; - struct device_node *node = of_get_parent(np); + struct device_node *node __free(device_node) = of_get_parent(np); simple_util_parse_convert(top, PREFIX, adata); simple_util_parse_convert(node, PREFIX, adata); simple_util_parse_convert(node, NULL, adata); simple_util_parse_convert(np, NULL, adata); - - of_node_put(node); } static int simple_parse_node(struct simple_util_priv *priv, @@ -176,7 +174,7 @@ static int simple_link_init(struct simple_util_priv *priv, struct device_node *top = dev->of_node; struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); - struct device_node *node = of_get_parent(cpu); + struct device_node *node __free(device_node) = of_get_parent(cpu); enum snd_soc_trigger_order trigger_start = SND_SOC_TRIGGER_ORDER_DEFAULT; enum snd_soc_trigger_order trigger_stop = SND_SOC_TRIGGER_ORDER_DEFAULT; bool playback_only = 0, capture_only = 0; @@ -185,7 +183,7 @@ static int simple_link_init(struct simple_util_priv *priv, ret = simple_util_parse_daifmt(dev, node, codec, prefix, &dai_link->dai_fmt); if (ret < 0) - goto init_end; + return ret; graph_util_parse_link_direction(top, &playback_only, &capture_only); graph_util_parse_link_direction(node, &playback_only, &capture_only); @@ -215,11 +213,7 @@ static int simple_link_init(struct simple_util_priv *priv, dai_link->init = simple_util_dai_init; dai_link->ops = &simple_ops; - ret = simple_util_set_dailink_name(dev, dai_link, name); -init_end: - of_node_put(node); - - return ret; + return simple_util_set_dailink_name(dev, dai_link, name); } static int simple_dai_link_of_dpcm(struct simple_util_priv *priv, @@ -232,7 +226,7 @@ static int simple_dai_link_of_dpcm(struct simple_util_priv *priv, struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); struct device_node *top = dev->of_node; - struct device_node *node = of_get_parent(np); + struct device_node *node __free(device_node) = of_get_parent(np); char *prefix = ""; char dai_name[64]; int ret; @@ -296,7 +290,6 @@ static int simple_dai_link_of_dpcm(struct simple_util_priv *priv, out_put_node: li->link++; - of_node_put(node); return ret; } @@ -312,15 +305,13 @@ static int simple_dai_link_of(struct simple_util_priv *priv, struct snd_soc_dai_link_component *codecs = snd_soc_link_to_codec(dai_link, 0); struct snd_soc_dai_link_component *platforms = snd_soc_link_to_platform(dai_link, 0); struct device_node *cpu = NULL; - struct device_node *node = NULL; - struct device_node *plat = NULL; char dai_name[64]; char prop[128]; char *prefix = ""; int ret, single_cpu = 0; cpu = np; - node = of_get_parent(np); + struct device_node *node __free(device_node) = of_get_parent(np); dev_dbg(dev, "link_of (%pOF)\n", node); @@ -329,7 +320,7 @@ static int simple_dai_link_of(struct simple_util_priv *priv, prefix = PREFIX; snprintf(prop, sizeof(prop), "%splat", prefix); - plat = of_get_child_by_name(node, prop); + struct device_node *plat __free(device_node) = of_get_child_by_name(node, prop); ret = simple_parse_node(priv, cpu, li, prefix, &single_cpu); if (ret < 0) @@ -352,9 +343,6 @@ static int simple_dai_link_of(struct simple_util_priv *priv, ret = simple_link_init(priv, cpu, codec, li, prefix, dai_name); dai_link_of_err: - of_node_put(plat); - of_node_put(node); - li->link++; return ret; @@ -374,7 +362,6 @@ static int __simple_for_each_link(struct simple_util_priv *priv, struct device *dev = simple_priv_to_dev(priv); struct device_node *top = dev->of_node; struct device_node *node; - struct device_node *add_devs; uintptr_t dpcm_selectable = (uintptr_t)of_device_get_match_data(dev); bool is_top = 0; int ret = 0; @@ -386,14 +373,11 @@ static int __simple_for_each_link(struct simple_util_priv *priv, is_top = 1; } - add_devs = of_get_child_by_name(top, PREFIX "additional-devs"); + struct device_node *add_devs __free(device_node) = of_get_child_by_name(top, PREFIX "additional-devs"); /* loop for all dai-link */ do { struct simple_util_data adata; - struct device_node *codec; - struct device_node *plat; - struct device_node *np; int num = of_get_child_count(node); /* Skip additional-devs node */ @@ -403,26 +387,26 @@ static int __simple_for_each_link(struct simple_util_priv *priv, } /* get codec */ - codec = of_get_child_by_name(node, is_top ? - PREFIX "codec" : "codec"); + struct device_node *codec __free(device_node) = + of_get_child_by_name(node, is_top ? PREFIX "codec" : "codec"); if (!codec) { ret = -ENODEV; goto error; } /* get platform */ - plat = of_get_child_by_name(node, is_top ? - PREFIX "plat" : "plat"); + struct device_node *plat __free(device_node) = + of_get_child_by_name(node, is_top ? PREFIX "plat" : "plat"); /* get convert-xxx property */ memset(&adata, 0, sizeof(adata)); - for_each_child_of_node(node, np) { + for_each_child_of_node_scoped(node, np) { if (np == add_devs) continue; simple_parse_convert(dev, np, &adata); } /* loop for all CPU/Codec node */ - for_each_child_of_node(node, np) { + for_each_child_of_node_scoped(node, np) { if (plat == np || add_devs == np) continue; /* @@ -452,22 +436,16 @@ static int __simple_for_each_link(struct simple_util_priv *priv, ret = func_noml(priv, np, codec, li, is_top); } - if (ret < 0) { - of_node_put(codec); - of_node_put(plat); - of_node_put(np); + if (ret < 0) goto error; - } } - of_node_put(codec); - of_node_put(plat); node = of_get_next_child(top, node); } while (!is_top && node); error: - of_node_put(add_devs); of_node_put(node); + return ret; } @@ -514,15 +492,13 @@ static void simple_depopulate_aux(void *data) static int simple_populate_aux(struct simple_util_priv *priv) { struct device *dev = simple_priv_to_dev(priv); - struct device_node *node; + struct device_node *node __free(device_node) = of_get_child_by_name(dev->of_node, PREFIX "additional-devs"); int ret; - node = of_get_child_by_name(dev->of_node, PREFIX "additional-devs"); if (!node) return 0; ret = of_platform_populate(node, NULL, NULL, dev); - of_node_put(node); if (ret) return ret; diff --git a/sound/soc/intel/avs/apl.c b/sound/soc/intel/avs/apl.c index 27516ef57185..3dccf0a57a3a 100644 --- a/sound/soc/intel/avs/apl.c +++ b/sound/soc/intel/avs/apl.c @@ -12,6 +12,7 @@ #include "avs.h" #include "messages.h" #include "path.h" +#include "registers.h" #include "topology.h" static irqreturn_t avs_apl_dsp_interrupt(struct avs_dev *adev) @@ -125,7 +126,7 @@ int avs_apl_coredump(struct avs_dev *adev, union avs_notify_msg *msg) struct avs_apl_log_buffer_layout layout; void __iomem *addr, *buf; size_t dump_size; - u16 offset = 0; + u32 offset = 0; u8 *dump, *pos; dump_size = AVS_FW_REGS_SIZE + msg->ext.coredump.stack_dump_size; diff --git a/sound/soc/intel/avs/cnl.c b/sound/soc/intel/avs/cnl.c index bd3c4bb8bf5a..03f8fb0dc187 100644 --- a/sound/soc/intel/avs/cnl.c +++ b/sound/soc/intel/avs/cnl.c @@ -9,6 +9,7 @@ #include <sound/hdaudio_ext.h> #include "avs.h" #include "messages.h" +#include "registers.h" static void avs_cnl_ipc_interrupt(struct avs_dev *adev) { diff --git a/sound/soc/intel/avs/core.c b/sound/soc/intel/avs/core.c index 73d4bde9b2f7..0e750e9e01d9 100644 --- a/sound/soc/intel/avs/core.c +++ b/sound/soc/intel/avs/core.c @@ -829,10 +829,10 @@ static const struct avs_spec jsl_desc = { .hipc = &cnl_hipc_spec, }; -#define AVS_TGL_BASED_SPEC(sname) \ +#define AVS_TGL_BASED_SPEC(sname, min) \ static const struct avs_spec sname##_desc = { \ .name = #sname, \ - .min_fw_version = { 10, 29, 0, 5646 }, \ + .min_fw_version = { 10, min, 0, 5646 }, \ .dsp_ops = &avs_tgl_dsp_ops, \ .core_init_mask = 1, \ .attributes = AVS_PLATATTR_IMR, \ @@ -840,11 +840,11 @@ static const struct avs_spec sname##_desc = { \ .hipc = &cnl_hipc_spec, \ } -AVS_TGL_BASED_SPEC(lkf); -AVS_TGL_BASED_SPEC(tgl); -AVS_TGL_BASED_SPEC(ehl); -AVS_TGL_BASED_SPEC(adl); -AVS_TGL_BASED_SPEC(adl_n); +AVS_TGL_BASED_SPEC(lkf, 28); +AVS_TGL_BASED_SPEC(tgl, 29); +AVS_TGL_BASED_SPEC(ehl, 30); +AVS_TGL_BASED_SPEC(adl, 35); +AVS_TGL_BASED_SPEC(adl_n, 35); static const struct pci_device_id avs_ids[] = { { PCI_DEVICE_DATA(INTEL, HDA_SKL_LP, &skl_desc) }, @@ -902,3 +902,13 @@ MODULE_AUTHOR("Cezary Rojewski <cezary.rojewski@intel.com>"); MODULE_AUTHOR("Amadeusz Slawinski <amadeuszx.slawinski@linux.intel.com>"); MODULE_DESCRIPTION("Intel cAVS sound driver"); MODULE_LICENSE("GPL"); +MODULE_FIRMWARE("intel/skl/dsp_basefw.bin"); +MODULE_FIRMWARE("intel/apl/dsp_basefw.bin"); +MODULE_FIRMWARE("intel/cnl/dsp_basefw.bin"); +MODULE_FIRMWARE("intel/icl/dsp_basefw.bin"); +MODULE_FIRMWARE("intel/jsl/dsp_basefw.bin"); +MODULE_FIRMWARE("intel/lkf/dsp_basefw.bin"); +MODULE_FIRMWARE("intel/tgl/dsp_basefw.bin"); +MODULE_FIRMWARE("intel/ehl/dsp_basefw.bin"); +MODULE_FIRMWARE("intel/adl/dsp_basefw.bin"); +MODULE_FIRMWARE("intel/adl_n/dsp_basefw.bin"); diff --git a/sound/soc/intel/avs/debugfs.c b/sound/soc/intel/avs/debugfs.c index 1767ded4d983..8c4edda97f75 100644 --- a/sound/soc/intel/avs/debugfs.c +++ b/sound/soc/intel/avs/debugfs.c @@ -10,6 +10,7 @@ #include <linux/kfifo.h> #include <linux/wait.h> #include <linux/sched/signal.h> +#include <linux/string_helpers.h> #include <sound/soc.h> #include "avs.h" #include "messages.h" diff --git a/sound/soc/intel/avs/ipc.c b/sound/soc/intel/avs/ipc.c index 4fba46e77c47..08ed9d96738a 100644 --- a/sound/soc/intel/avs/ipc.c +++ b/sound/soc/intel/avs/ipc.c @@ -184,10 +184,11 @@ static void avs_dsp_receive_rx(struct avs_dev *adev, u64 header) { struct avs_ipc *ipc = adev->ipc; union avs_reply_msg msg = AVS_MSG(header); - u64 reg; + u32 sts, lec; - reg = readq(avs_sram_addr(adev, AVS_FW_REGS_WINDOW)); - trace_avs_ipc_reply_msg(header, reg); + sts = snd_hdac_adsp_readl(adev, AVS_FW_REG_STATUS(adev)); + lec = snd_hdac_adsp_readl(adev, AVS_FW_REG_ERROR(adev)); + trace_avs_ipc_reply_msg(header, sts, lec); ipc->rx.header = header; /* Abort copying payload if request processing was unsuccessful. */ @@ -209,10 +210,11 @@ static void avs_dsp_process_notification(struct avs_dev *adev, u64 header) union avs_notify_msg msg = AVS_MSG(header); size_t data_size = 0; void *data = NULL; - u64 reg; + u32 sts, lec; - reg = readq(avs_sram_addr(adev, AVS_FW_REGS_WINDOW)); - trace_avs_ipc_notify_msg(header, reg); + sts = snd_hdac_adsp_readl(adev, AVS_FW_REG_STATUS(adev)); + lec = snd_hdac_adsp_readl(adev, AVS_FW_REG_ERROR(adev)); + trace_avs_ipc_notify_msg(header, sts, lec); /* Ignore spurious notifications until handshake is established. */ if (!adev->ipc->ready && msg.notify_msg_type != AVS_NOTIFY_FW_READY) { @@ -367,13 +369,16 @@ static void avs_ipc_msg_init(struct avs_ipc *ipc, struct avs_ipc_msg *reply) static void avs_dsp_send_tx(struct avs_dev *adev, struct avs_ipc_msg *tx, bool read_fwregs) { const struct avs_spec *const spec = adev->spec; - u64 reg = ULONG_MAX; + u32 sts = UINT_MAX; + u32 lec = UINT_MAX; tx->header |= spec->hipc->req_busy_mask; - if (read_fwregs) - reg = readq(avs_sram_addr(adev, AVS_FW_REGS_WINDOW)); + if (read_fwregs) { + sts = snd_hdac_adsp_readl(adev, AVS_FW_REG_STATUS(adev)); + lec = snd_hdac_adsp_readl(adev, AVS_FW_REG_ERROR(adev)); + } - trace_avs_request(tx, reg); + trace_avs_request(tx, sts, lec); if (tx->size) memcpy_toio(avs_downlink_addr(adev), tx->data, tx->size); diff --git a/sound/soc/intel/avs/loader.c b/sound/soc/intel/avs/loader.c index 890efd2f1fea..9ff7818395cd 100644 --- a/sound/soc/intel/avs/loader.c +++ b/sound/soc/intel/avs/loader.c @@ -167,7 +167,8 @@ int avs_cldma_load_basefw(struct avs_dev *adev, struct firmware *fw) (reg & AVS_ROM_INIT_DONE) == AVS_ROM_INIT_DONE, AVS_ROM_INIT_POLLING_US, SKL_ROM_INIT_TIMEOUT_US); if (ret < 0) { - dev_err(adev->dev, "rom init timeout: %d\n", ret); + dev_err(adev->dev, "rom init failed: %d, status: 0x%08x, lec: 0x%08x\n", + ret, reg, snd_hdac_adsp_readl(adev, AVS_FW_REG_ERROR(adev))); avs_dsp_core_disable(adev, AVS_MAIN_CORE_MASK); return ret; } @@ -180,7 +181,8 @@ int avs_cldma_load_basefw(struct avs_dev *adev, struct firmware *fw) AVS_FW_INIT_POLLING_US, AVS_FW_INIT_TIMEOUT_US); hda_cldma_stop(cl); if (ret < 0) { - dev_err(adev->dev, "transfer fw failed: %d\n", ret); + dev_err(adev->dev, "transfer fw failed: %d, status: 0x%08x, lec: 0x%08x\n", + ret, reg, snd_hdac_adsp_readl(adev, AVS_FW_REG_ERROR(adev))); avs_dsp_core_disable(adev, AVS_MAIN_CORE_MASK); return ret; } @@ -308,12 +310,13 @@ avs_hda_init_rom(struct avs_dev *adev, unsigned int dma_id, bool purge) } /* await ROM init */ - ret = snd_hdac_adsp_readq_poll(adev, spec->sram->rom_status_offset, reg, + ret = snd_hdac_adsp_readl_poll(adev, spec->sram->rom_status_offset, reg, (reg & 0xF) == AVS_ROM_INIT_DONE || (reg & 0xF) == APL_ROM_FW_ENTERED, AVS_ROM_INIT_POLLING_US, APL_ROM_INIT_TIMEOUT_US); if (ret < 0) { - dev_err(adev->dev, "rom init timeout: %d\n", ret); + dev_err(adev->dev, "rom init failed: %d, status: 0x%08x, lec: 0x%08x\n", + ret, reg, snd_hdac_adsp_readl(adev, AVS_FW_REG_ERROR(adev))); goto err; } @@ -337,15 +340,15 @@ static int avs_imr_load_basefw(struct avs_dev *adev) /* DMA id ignored when flashing from IMR as no transfer occurs. */ ret = avs_hda_init_rom(adev, 0, false); - if (ret < 0) { - dev_err(adev->dev, "rom init failed: %d\n", ret); + if (ret < 0) return ret; - } ret = wait_for_completion_timeout(&adev->fw_ready, msecs_to_jiffies(AVS_FW_INIT_TIMEOUT_MS)); if (!ret) { - dev_err(adev->dev, "firmware ready timeout\n"); + dev_err(adev->dev, "firmware ready timeout, status: 0x%08x, lec: 0x%08x\n", + snd_hdac_adsp_readl(adev, AVS_FW_REG_STATUS(adev)), + snd_hdac_adsp_readl(adev, AVS_FW_REG_ERROR(adev))); avs_dsp_core_disable(adev, AVS_MAIN_CORE_MASK); return -ETIMEDOUT; } @@ -392,7 +395,7 @@ int avs_hda_load_basefw(struct avs_dev *adev, struct firmware *fw) ret = avs_hda_init_rom(adev, dma_id, true); if (!ret) break; - dev_info(adev->dev, "#%d rom init fail: %d\n", i + 1, ret); + dev_info(adev->dev, "#%d rom init failed: %d\n", i + 1, ret); } if (ret < 0) goto cleanup_resources; @@ -404,7 +407,8 @@ int avs_hda_load_basefw(struct avs_dev *adev, struct firmware *fw) AVS_FW_INIT_POLLING_US, AVS_FW_INIT_TIMEOUT_US); snd_hdac_dsp_trigger(hstream, false); if (ret < 0) { - dev_err(adev->dev, "transfer fw failed: %d\n", ret); + dev_err(adev->dev, "transfer fw failed: %d, status: 0x%08x, lec: 0x%08x\n", + ret, reg, snd_hdac_adsp_readl(adev, AVS_FW_REG_ERROR(adev))); avs_dsp_core_disable(adev, AVS_MAIN_CORE_MASK); } @@ -584,7 +588,9 @@ static int avs_dsp_load_basefw(struct avs_dev *adev) ret = wait_for_completion_timeout(&adev->fw_ready, msecs_to_jiffies(AVS_FW_INIT_TIMEOUT_MS)); if (!ret) { - dev_err(adev->dev, "firmware ready timeout\n"); + dev_err(adev->dev, "firmware ready timeout, status: 0x%08x, lec: 0x%08x\n", + snd_hdac_adsp_readl(adev, AVS_FW_REG_STATUS(adev)), + snd_hdac_adsp_readl(adev, AVS_FW_REG_ERROR(adev))); avs_dsp_core_disable(adev, AVS_MAIN_CORE_MASK); ret = -ETIMEDOUT; goto release_fw; @@ -675,16 +681,12 @@ int avs_dsp_first_boot_firmware(struct avs_dev *adev) } ret = avs_ipc_get_hw_config(adev, &adev->hw_cfg); - if (ret) { - dev_err(adev->dev, "get hw cfg failed: %d\n", ret); + if (ret) return AVS_IPC_RET(ret); - } ret = avs_ipc_get_fw_config(adev, &adev->fw_cfg); - if (ret) { - dev_err(adev->dev, "get fw cfg failed: %d\n", ret); + if (ret) return AVS_IPC_RET(ret); - } adev->core_refs = devm_kcalloc(adev->dev, adev->hw_cfg.dsp_cores, sizeof(*adev->core_refs), GFP_KERNEL); diff --git a/sound/soc/intel/avs/messages.c b/sound/soc/intel/avs/messages.c index ec458bd51b10..30b666f8909b 100644 --- a/sound/soc/intel/avs/messages.c +++ b/sound/soc/intel/avs/messages.c @@ -400,10 +400,12 @@ int avs_ipc_get_fw_config(struct avs_dev *adev, struct avs_fw_cfg *cfg) AVS_BASEFW_FIRMWARE_CONFIG, NULL, 0, &payload, &payload_size); if (ret) - return ret; + goto err; /* Non-zero payload expected for FIRMWARE_CONFIG. */ - if (!payload_size) - return -EREMOTEIO; + if (!payload_size) { + ret = -EREMOTEIO; + goto err; + } while (offset < payload_size) { tlv = (struct avs_tlv *)(payload + offset); @@ -502,6 +504,9 @@ int avs_ipc_get_fw_config(struct avs_dev *adev, struct avs_fw_cfg *cfg) /* No longer needed, free it as it's owned by the get_large_config() caller. */ kfree(payload); +err: + if (ret) + dev_err(adev->dev, "get fw cfg failed: %d\n", ret); return ret; } @@ -517,10 +522,12 @@ int avs_ipc_get_hw_config(struct avs_dev *adev, struct avs_hw_cfg *cfg) AVS_BASEFW_HARDWARE_CONFIG, NULL, 0, &payload, &payload_size); if (ret) - return ret; + goto err; /* Non-zero payload expected for HARDWARE_CONFIG. */ - if (!payload_size) - return -EREMOTEIO; + if (!payload_size) { + ret = -EREMOTEIO; + goto err; + } while (offset < payload_size) { tlv = (struct avs_tlv *)(payload + offset); @@ -590,6 +597,9 @@ int avs_ipc_get_hw_config(struct avs_dev *adev, struct avs_hw_cfg *cfg) exit: /* No longer needed, free it as it's owned by the get_large_config() caller. */ kfree(payload); +err: + if (ret) + dev_err(adev->dev, "get hw cfg failed: %d\n", ret); return ret; } diff --git a/sound/soc/intel/avs/messages.h b/sound/soc/intel/avs/messages.h index d0bdb7d9266c..0378633c7f96 100644 --- a/sound/soc/intel/avs/messages.h +++ b/sound/soc/intel/avs/messages.h @@ -859,8 +859,7 @@ static_assert(sizeof(struct avs_aec_cfg) == 92); struct avs_asrc_cfg { struct avs_modcfg_base base; u32 out_freq; - u32 rsvd0:1; - u32 mode:1; + u32 mode:2; u32 rsvd2:2; u32 disable_jitter_buffer:1; u32 rsvd3:27; diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c index 945f9c0a6a54..4bfbcb5a5ae8 100644 --- a/sound/soc/intel/avs/pcm.c +++ b/sound/soc/intel/avs/pcm.c @@ -161,6 +161,7 @@ static int avs_dai_be_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dpcm *dpcm; be = snd_soc_substream_to_rtd(substream); + /* dpcm_fe_dai_open() guarantees the list is not empty at this point. */ for_each_dpcm_fe(be, substream->stream, dpcm) { fe = dpcm->fe; fe_hw_params = &fe->dpcm[substream->stream].hw_params; @@ -576,6 +577,7 @@ static int avs_dai_fe_hw_params(struct snd_pcm_substream *substream, hdac_stream(host_stream)->format_val = 0; fe = snd_soc_substream_to_rtd(substream); + /* dpcm_fe_dai_open() guarantees the list is not empty at this point. */ for_each_dpcm_be(fe, substream->stream, dpcm) { be = dpcm->be; be_hw_params = &be->dpcm[substream->stream].hw_params; @@ -1564,6 +1566,7 @@ static int avs_component_hda_probe(struct snd_soc_component *component) if (ret < 0) { dev_err(component->dev, "create widgets failed: %d\n", ret); + snd_soc_unregister_dai(dai); goto exit; } } @@ -1578,8 +1581,8 @@ exit: static void avs_component_hda_remove(struct snd_soc_component *component) { - avs_component_hda_unregister_dais(component); avs_component_remove(component); + avs_component_hda_unregister_dais(component); } static int avs_component_hda_open(struct snd_soc_component *component, diff --git a/sound/soc/intel/avs/registers.h b/sound/soc/intel/avs/registers.h index f76e91cff2a9..368ede05f2cd 100644 --- a/sound/soc/intel/avs/registers.h +++ b/sound/soc/intel/avs/registers.h @@ -9,6 +9,8 @@ #ifndef __SOUND_SOC_INTEL_AVS_REGS_H #define __SOUND_SOC_INTEL_AVS_REGS_H +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/iopoll.h> #include <linux/sizes.h> #define AZX_PCIREG_PGCTL 0x44 @@ -74,7 +76,7 @@ /* Constants used when accessing SRAM, space shared with firmware */ #define AVS_FW_REG_BASE(adev) ((adev)->spec->sram->base_offset) #define AVS_FW_REG_STATUS(adev) (AVS_FW_REG_BASE(adev) + 0x0) -#define AVS_FW_REG_ERROR_CODE(adev) (AVS_FW_REG_BASE(adev) + 0x4) +#define AVS_FW_REG_ERROR(adev) (AVS_FW_REG_BASE(adev) + 0x4) #define AVS_WINDOW_CHUNK_SIZE SZ_4K #define AVS_FW_REGS_SIZE AVS_WINDOW_CHUNK_SIZE @@ -98,4 +100,47 @@ #define avs_downlink_addr(adev) \ avs_sram_addr(adev, AVS_DOWNLINK_WINDOW) +#define snd_hdac_adsp_writeb(adev, reg, value) \ + snd_hdac_reg_writeb(&(adev)->base.core, (adev)->dsp_ba + (reg), value) +#define snd_hdac_adsp_readb(adev, reg) \ + snd_hdac_reg_readb(&(adev)->base.core, (adev)->dsp_ba + (reg)) +#define snd_hdac_adsp_writew(adev, reg, value) \ + snd_hdac_reg_writew(&(adev)->base.core, (adev)->dsp_ba + (reg), value) +#define snd_hdac_adsp_readw(adev, reg) \ + snd_hdac_reg_readw(&(adev)->base.core, (adev)->dsp_ba + (reg)) +#define snd_hdac_adsp_writel(adev, reg, value) \ + snd_hdac_reg_writel(&(adev)->base.core, (adev)->dsp_ba + (reg), value) +#define snd_hdac_adsp_readl(adev, reg) \ + snd_hdac_reg_readl(&(adev)->base.core, (adev)->dsp_ba + (reg)) +#define snd_hdac_adsp_writeq(adev, reg, value) \ + snd_hdac_reg_writeq(&(adev)->base.core, (adev)->dsp_ba + (reg), value) +#define snd_hdac_adsp_readq(adev, reg) \ + snd_hdac_reg_readq(&(adev)->base.core, (adev)->dsp_ba + (reg)) + +#define snd_hdac_adsp_updateb(adev, reg, mask, val) \ + snd_hdac_adsp_writeb(adev, reg, \ + (snd_hdac_adsp_readb(adev, reg) & ~(mask)) | (val)) +#define snd_hdac_adsp_updatew(adev, reg, mask, val) \ + snd_hdac_adsp_writew(adev, reg, \ + (snd_hdac_adsp_readw(adev, reg) & ~(mask)) | (val)) +#define snd_hdac_adsp_updatel(adev, reg, mask, val) \ + snd_hdac_adsp_writel(adev, reg, \ + (snd_hdac_adsp_readl(adev, reg) & ~(mask)) | (val)) +#define snd_hdac_adsp_updateq(adev, reg, mask, val) \ + snd_hdac_adsp_writeq(adev, reg, \ + (snd_hdac_adsp_readq(adev, reg) & ~(mask)) | (val)) + +#define snd_hdac_adsp_readb_poll(adev, reg, val, cond, delay_us, timeout_us) \ + readb_poll_timeout((adev)->dsp_ba + (reg), val, cond, \ + delay_us, timeout_us) +#define snd_hdac_adsp_readw_poll(adev, reg, val, cond, delay_us, timeout_us) \ + readw_poll_timeout((adev)->dsp_ba + (reg), val, cond, \ + delay_us, timeout_us) +#define snd_hdac_adsp_readl_poll(adev, reg, val, cond, delay_us, timeout_us) \ + readl_poll_timeout((adev)->dsp_ba + (reg), val, cond, \ + delay_us, timeout_us) +#define snd_hdac_adsp_readq_poll(adev, reg, val, cond, delay_us, timeout_us) \ + readq_poll_timeout((adev)->dsp_ba + (reg), val, cond, \ + delay_us, timeout_us) + #endif /* __SOUND_SOC_INTEL_AVS_REGS_H */ diff --git a/sound/soc/intel/avs/skl.c b/sound/soc/intel/avs/skl.c index 34f859d6e5a4..d66ef000de9e 100644 --- a/sound/soc/intel/avs/skl.c +++ b/sound/soc/intel/avs/skl.c @@ -12,6 +12,7 @@ #include "avs.h" #include "cldma.h" #include "messages.h" +#include "registers.h" void avs_skl_ipc_interrupt(struct avs_dev *adev) { diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c index 5cda527020c7..d612f20ed989 100644 --- a/sound/soc/intel/avs/topology.c +++ b/sound/soc/intel/avs/topology.c @@ -1466,7 +1466,7 @@ avs_tplg_path_template_create(struct snd_soc_component *comp, struct avs_tplg *o static const struct avs_tplg_token_parser mod_init_config_parsers[] = { { - .token = AVS_TKN_MOD_INIT_CONFIG_ID_U32, + .token = AVS_TKN_INIT_CONFIG_ID_U32, .type = SND_SOC_TPLG_TUPLE_TYPE_WORD, .offset = offsetof(struct avs_tplg_init_config, id), .parse = avs_parse_word_token, @@ -1519,7 +1519,7 @@ static int avs_tplg_parse_initial_configs(struct snd_soc_component *comp, esize = le32_to_cpu(tuples->size) + le32_to_cpu(tmp->size); ret = parse_dictionary_entries(comp, tuples, esize, config, 1, sizeof(*config), - AVS_TKN_MOD_INIT_CONFIG_ID_U32, + AVS_TKN_INIT_CONFIG_ID_U32, mod_init_config_parsers, ARRAY_SIZE(mod_init_config_parsers)); diff --git a/sound/soc/intel/avs/trace.h b/sound/soc/intel/avs/trace.h index c9eaa5a60ed3..f4288d0ad5ef 100644 --- a/sound/soc/intel/avs/trace.h +++ b/sound/soc/intel/avs/trace.h @@ -37,60 +37,62 @@ TRACE_EVENT(avs_dsp_core_op, void trace_avs_msg_payload(const void *data, size_t size); -#define trace_avs_request(msg, fwregs) \ +#define trace_avs_request(msg, sts, lec) \ ({ \ - trace_avs_ipc_request_msg((msg)->header, fwregs); \ + trace_avs_ipc_request_msg((msg)->header, sts, lec); \ trace_avs_msg_payload((msg)->data, (msg)->size); \ }) -#define trace_avs_reply(msg, fwregs) \ +#define trace_avs_reply(msg, sts, lec) \ ({ \ - trace_avs_ipc_reply_msg((msg)->header, fwregs); \ + trace_avs_ipc_reply_msg((msg)->header, sts, lec); \ trace_avs_msg_payload((msg)->data, (msg)->size); \ }) -#define trace_avs_notify(msg, fwregs) \ +#define trace_avs_notify(msg, sts, lec) \ ({ \ - trace_avs_ipc_notify_msg((msg)->header, fwregs); \ + trace_avs_ipc_notify_msg((msg)->header, sts, lec); \ trace_avs_msg_payload((msg)->data, (msg)->size); \ }) #endif DECLARE_EVENT_CLASS(avs_ipc_msg_hdr, - TP_PROTO(u64 header, u64 fwregs), + TP_PROTO(u64 header, u32 sts, u32 lec), - TP_ARGS(header, fwregs), + TP_ARGS(header, sts, lec), TP_STRUCT__entry( __field(u64, header) - __field(u64, fwregs) + __field(u32, sts) + __field(u32, lec) ), TP_fast_assign( __entry->header = header; - __entry->fwregs = fwregs; + __entry->sts = sts; + __entry->lec = lec; ), TP_printk("primary: 0x%08X, extension: 0x%08X,\n" - "fwstatus: 0x%08X, fwerror: 0x%08X", + "status: 0x%08X, error: 0x%08X", lower_32_bits(__entry->header), upper_32_bits(__entry->header), - lower_32_bits(__entry->fwregs), upper_32_bits(__entry->fwregs)) + __entry->sts, __entry->lec) ); DEFINE_EVENT(avs_ipc_msg_hdr, avs_ipc_request_msg, - TP_PROTO(u64 header, u64 fwregs), - TP_ARGS(header, fwregs) + TP_PROTO(u64 header, u32 sts, u32 lec), + TP_ARGS(header, sts, lec) ); DEFINE_EVENT(avs_ipc_msg_hdr, avs_ipc_reply_msg, - TP_PROTO(u64 header, u64 fwregs), - TP_ARGS(header, fwregs) + TP_PROTO(u64 header, u32 sts, u32 lec), + TP_ARGS(header, sts, lec) ); DEFINE_EVENT(avs_ipc_msg_hdr, avs_ipc_notify_msg, - TP_PROTO(u64 header, u64 fwregs), - TP_ARGS(header, fwregs) + TP_PROTO(u64 header, u32 sts, u32 lec), + TP_ARGS(header, sts, lec) ); TRACE_EVENT_CONDITION(avs_ipc_msg_payload, diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 9caa4407c1ca..6446cda0f857 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -1132,7 +1132,22 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, - { /* Vexia Edu Atla 10 tablet */ + { + /* Vexia Edu Atla 10 tablet 5V version */ + .matches = { + /* Having all 3 of these not set is somewhat unique */ + DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."), + DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."), + DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."), + /* Above strings are too generic, also match on BIOS date */ + DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_JD_NOT_INV | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, + { /* Vexia Edu Atla 10 tablet 9V version */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"), diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c index 22668bac74a1..0554c7e2cb34 100644 --- a/sound/soc/intel/boards/skl_hda_dsp_generic.c +++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c @@ -124,8 +124,6 @@ static int skl_hda_audio_probe(struct platform_device *pdev) return ret; card->dev = &pdev->dev; - if (!snd_soc_acpi_sof_parent(&pdev->dev)) - card->disable_route_checks = true; if (mach->mach_params.dmic_num > 0) { card->components = devm_kasprintf(card->dev, GFP_KERNEL, diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index f3369e569abc..b0d35fda7b17 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -22,6 +22,8 @@ static int quirk_override = -1; module_param_named(quirk, quirk_override, int, 0444); MODULE_PARM_DESC(quirk, "Board-specific quirk override"); +#define DMIC_DEFAULT_CHANNELS 2 + static void log_quirks(struct device *dev) { if (SOC_SDW_JACK_JDSRC(sof_sdw_quirk)) @@ -42,6 +44,8 @@ static void log_quirks(struct device *dev) dev_dbg(dev, "quirk SOC_SDW_CODEC_SPKR enabled\n"); if (sof_sdw_quirk & SOC_SDW_SIDECAR_AMPS) dev_dbg(dev, "quirk SOC_SDW_SIDECAR_AMPS enabled\n"); + if (sof_sdw_quirk & SOC_SDW_CODEC_MIC) + dev_dbg(dev, "quirk SOC_SDW_CODEC_MIC enabled\n"); } static int sof_sdw_quirk_cb(const struct dmi_system_id *id) @@ -608,31 +612,47 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "3838") + DMI_MATCH(DMI_PRODUCT_NAME, "83JX") }, - .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), }, { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "3832") + DMI_MATCH(DMI_PRODUCT_NAME, "83LC") }, - .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), }, { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "380E") + DMI_MATCH(DMI_PRODUCT_NAME, "83MC") }, - .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), + }, { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83NM") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), }, { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "233C") + DMI_MATCH(DMI_PRODUCT_NAME, "83HM") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | + SOC_SDW_CODEC_MIC), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21QB") }, /* Note this quirk excludes the CODEC mic */ .driver_data = (void *)(SOC_SDW_CODEC_MIC), @@ -641,9 +661,26 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "233B") + DMI_MATCH(DMI_PRODUCT_NAME, "21QA") }, - .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + /* Note this quirk excludes the CODEC mic */ + .driver_data = (void *)(SOC_SDW_CODEC_MIC), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21Q6") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21Q7") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), }, /* ArrowLake devices */ @@ -1110,22 +1147,24 @@ static int sof_card_dai_links_create(struct snd_soc_card *card) hdmi_num = SOF_PRE_TGL_HDMI_COUNT; /* enable dmic01 & dmic16k */ - if (sof_sdw_quirk & SOC_SDW_PCH_DMIC || mach_params->dmic_num) { - if (ctx->ignore_internal_dmic) - dev_warn(dev, "Ignoring PCH DMIC\n"); - else - dmic_num = 2; + if (ctx->ignore_internal_dmic) { + dev_dbg(dev, "SoundWire DMIC is used, ignoring internal DMIC\n"); + mach_params->dmic_num = 0; + } else if (mach_params->dmic_num) { + dmic_num = 2; + } else if (sof_sdw_quirk & SOC_SDW_PCH_DMIC) { + dmic_num = 2; + /* + * mach_params->dmic_num will be used to set the cfg-mics value of + * card->components string. Set it to the default value. + */ + mach_params->dmic_num = DMIC_DEFAULT_CHANNELS; } - /* - * mach_params->dmic_num will be used to set the cfg-mics value of card->components - * string. Overwrite it to the actual number of PCH DMICs used in the device. - */ - mach_params->dmic_num = dmic_num; if (sof_sdw_quirk & SOF_SSP_BT_OFFLOAD_PRESENT) bt_num = 1; - dev_dbg(dev, "sdw %d, ssp %d, dmic %d, hdmi %d, bt: %d\n", + dev_dbg(dev, "DAI link numbers: sdw %d, ssp %d, dmic %d, hdmi %d, bt: %d\n", sdw_be_num, ssp_num, dmic_num, intel_ctx->hdmi.idisp_codec ? hdmi_num : 0, bt_num); diff --git a/sound/soc/intel/common/soc-acpi-intel-arl-match.c b/sound/soc/intel/common/soc-acpi-intel-arl-match.c index 24d850df77ca..32147dc9d2d6 100644 --- a/sound/soc/intel/common/soc-acpi-intel-arl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-arl-match.c @@ -138,7 +138,7 @@ static const struct snd_soc_acpi_adr_device cs35l56_2_r1_adr[] = { }, }; -static const struct snd_soc_acpi_adr_device cs35l56_3_l1_adr[] = { +static const struct snd_soc_acpi_adr_device cs35l56_3_l3_adr[] = { { .adr = 0x00033301fa355601ull, .num_endpoints = 1, @@ -147,6 +147,24 @@ static const struct snd_soc_acpi_adr_device cs35l56_3_l1_adr[] = { }, }; +static const struct snd_soc_acpi_adr_device cs35l56_2_r3_adr[] = { + { + .adr = 0x00023301fa355601ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "AMP2" + }, +}; + +static const struct snd_soc_acpi_adr_device cs35l56_3_l1_adr[] = { + { + .adr = 0x00033101fa355601ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "AMP1" + }, +}; + static const struct snd_soc_acpi_endpoint cs42l43_endpoints[] = { { /* Jack Playback Endpoint */ .num = 0, @@ -304,6 +322,25 @@ static const struct snd_soc_acpi_link_adr arl_cs42l43_l0_cs35l56_2_l23[] = { .num_adr = ARRAY_SIZE(cs35l56_2_r1_adr), .adr_d = cs35l56_2_r1_adr, }, + { + .mask = BIT(3), + .num_adr = ARRAY_SIZE(cs35l56_3_l3_adr), + .adr_d = cs35l56_3_l3_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr arl_cs42l43_l0_cs35l56_3_l23[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs42l43_0_adr), + .adr_d = cs42l43_0_adr, + }, + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(cs35l56_2_r3_adr), + .adr_d = cs35l56_2_r3_adr, + }, { .mask = BIT(3), .num_adr = ARRAY_SIZE(cs35l56_3_l1_adr), @@ -406,6 +443,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_arl_sdw_machines[] = { .drv_name = "sof_sdw", .sof_tplg_filename = "sof-arl-cs42l43-l0-cs35l56-l23.tplg", }, + { + .link_mask = BIT(0) | BIT(2) | BIT(3), + .links = arl_cs42l43_l0_cs35l56_3_l23, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-arl-cs42l43-l0-cs35l56-l23.tplg", + }, { .link_mask = BIT(0) | BIT(2), .links = arl_cs42l43_l0_cs35l56_l2, diff --git a/sound/soc/intel/common/soc-acpi-intel-lnl-match.c b/sound/soc/intel/common/soc-acpi-intel-lnl-match.c index 98a9c36d7a4c..0b4a9c27c47e 100644 --- a/sound/soc/intel/common/soc-acpi-intel-lnl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-lnl-match.c @@ -91,6 +91,23 @@ static const struct snd_soc_acpi_endpoint rt722_endpoints[] = { }, }; +static const struct snd_soc_acpi_endpoint jack_dmic_endpoints[] = { + /* Jack Endpoint */ + { + .num = 0, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + /* DMIC Endpoint */ + { + .num = 1, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, +}; + static const struct snd_soc_acpi_endpoint jack_amp_g1_dmic_endpoints_endpoints[] = { /* Jack Endpoint */ { @@ -295,6 +312,24 @@ static const struct snd_soc_acpi_adr_device rt1320_1_group1_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt1320_1_group2_adr[] = { + { + .adr = 0x000130025D132001ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "rt1320-1" + } +}; + +static const struct snd_soc_acpi_adr_device rt1320_3_group2_adr[] = { + { + .adr = 0x000330025D132001ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "rt1320-2" + } +}; + static const struct snd_soc_acpi_adr_device rt713_0_adr[] = { { .adr = 0x000031025D071301ull, @@ -304,6 +339,15 @@ static const struct snd_soc_acpi_adr_device rt713_0_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt713_vb_2_adr[] = { + { + .adr = 0x000230025d071301ull, + .num_endpoints = ARRAY_SIZE(jack_dmic_endpoints), + .endpoints = jack_dmic_endpoints, + .name_prefix = "rt713" + } +}; + static const struct snd_soc_acpi_adr_device rt714_0_adr[] = { { .adr = 0x000030025D071401ull, @@ -453,6 +497,25 @@ static const struct snd_soc_acpi_link_adr lnl_sdw_rt713_l0_rt1318_l1[] = { {} }; +static const struct snd_soc_acpi_link_adr lnl_sdw_rt713_vb_l2_rt1320_l13[] = { + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(rt713_vb_2_adr), + .adr_d = rt713_vb_2_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(rt1320_1_group2_adr), + .adr_d = rt1320_1_group2_adr, + }, + { + .mask = BIT(3), + .num_adr = ARRAY_SIZE(rt1320_3_group2_adr), + .adr_d = rt1320_3_group2_adr, + }, + {} +}; + static const struct snd_soc_acpi_link_adr lnl_sdw_rt712_vb_l2_rt1320_l1[] = { { .mask = BIT(2), @@ -550,6 +613,13 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_lnl_sdw_machines[] = { .machine_check = snd_soc_acpi_intel_sdca_is_device_rt712_vb, .sof_tplg_filename = "sof-lnl-rt712-l2-rt1320-l1.tplg" }, + { + .link_mask = BIT(1) | BIT(2) | BIT(3), + .links = lnl_sdw_rt713_vb_l2_rt1320_l13, + .drv_name = "sof_sdw", + .machine_check = snd_soc_acpi_intel_sdca_is_device_rt712_vb, + .sof_tplg_filename = "sof-lnl-rt713-l2-rt1320-l13.tplg" + }, {}, }; EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_lnl_sdw_machines); diff --git a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c index 03fc5a187012..770e2194a283 100644 --- a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c @@ -441,6 +441,179 @@ static const struct snd_soc_acpi_adr_device cs42l43_0_adr[] = { } }; +/* CS42L43 - speaker DAI aggregated with 4 amps */ +static const struct snd_soc_acpi_endpoint cs42l43_4amp_spkagg_endpoints[] = { + { /* Jack Playback Endpoint */ + .num = 0, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + { /* DMIC Capture Endpoint */ + .num = 1, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + { /* Jack Capture Endpoint */ + .num = 2, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + { /* Speaker Playback Endpoint */ + .num = 3, + .aggregated = 1, + .group_position = 4, + .group_id = 1, + }, +}; + +/* CS42L43 on link3 aggregated with 4 amps */ +static const struct snd_soc_acpi_adr_device cs42l43_l3_4amp_spkagg_adr[] = { + { + .adr = 0x00033001FA424301ull, + .num_endpoints = ARRAY_SIZE(cs42l43_4amp_spkagg_endpoints), + .endpoints = cs42l43_4amp_spkagg_endpoints, + .name_prefix = "cs42l43" + } +}; + +static const struct snd_soc_acpi_endpoint cs35l56_l_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 0, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 0, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_r_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 1, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 1, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_2_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 2, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 2, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_3_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 3, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 3, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_4_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 4, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 4, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_5_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 5, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 5, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_6_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 6, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 6, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_7_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 7, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 7, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_adr_device cs35l56_0_adr[] = { + { + .adr = 0x00003301FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "AMP1" + }, + { + .adr = 0x00003201FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_2_endpoint, + .name_prefix = "AMP2" + } +}; + static const struct snd_soc_acpi_adr_device cs35l56_1_adr[] = { { .adr = 0x00013701FA355601ull, @@ -471,17 +644,71 @@ static const struct snd_soc_acpi_adr_device cs35l56_2_adr[] = { } }; +static const struct snd_soc_acpi_adr_device cs35l56_0_fb_adr[] = { + { + .adr = 0x00003301FA355601ull, + .num_endpoints = ARRAY_SIZE(cs35l56_l_fb_endpoints), + .endpoints = cs35l56_l_fb_endpoints, + .name_prefix = "AMP1" + }, + { + .adr = 0x00003201FA355601ull, + .num_endpoints = ARRAY_SIZE(cs35l56_2_fb_endpoints), + .endpoints = cs35l56_2_fb_endpoints, + .name_prefix = "AMP2" + }, + { + .adr = 0x00003101FA355601ull, + .num_endpoints = ARRAY_SIZE(cs35l56_4_fb_endpoints), + .endpoints = cs35l56_4_fb_endpoints, + .name_prefix = "AMP3" + }, + { + .adr = 0x00003001FA355601ull, + .num_endpoints = ARRAY_SIZE(cs35l56_6_fb_endpoints), + .endpoints = cs35l56_6_fb_endpoints, + .name_prefix = "AMP4" + }, +}; + +static const struct snd_soc_acpi_adr_device cs35l56_1_fb_adr[] = { + { + .adr = 0x00013701FA355601ull, + .num_endpoints = ARRAY_SIZE(cs35l56_r_fb_endpoints), + .endpoints = cs35l56_r_fb_endpoints, + .name_prefix = "AMP8" + }, + { + .adr = 0x00013601FA355601ull, + .num_endpoints = ARRAY_SIZE(cs35l56_3_fb_endpoints), + .endpoints = cs35l56_3_fb_endpoints, + .name_prefix = "AMP7" + }, + { + .adr = 0x00013501FA355601ull, + .num_endpoints = ARRAY_SIZE(cs35l56_5_fb_endpoints), + .endpoints = cs35l56_5_fb_endpoints, + .name_prefix = "AMP6" + }, + { + .adr = 0x00013401FA355601ull, + .num_endpoints = ARRAY_SIZE(cs35l56_7_fb_endpoints), + .endpoints = cs35l56_7_fb_endpoints, + .name_prefix = "AMP5" + }, +}; + static const struct snd_soc_acpi_adr_device cs35l56_2_r_adr[] = { { .adr = 0x00023201FA355601ull, - .num_endpoints = 1, - .endpoints = &spk_r_endpoint, + .num_endpoints = ARRAY_SIZE(cs35l56_r_fb_endpoints), + .endpoints = cs35l56_r_fb_endpoints, .name_prefix = "AMP3" }, { .adr = 0x00023301FA355601ull, - .num_endpoints = 1, - .endpoints = &spk_3_endpoint, + .num_endpoints = ARRAY_SIZE(cs35l56_3_fb_endpoints), + .endpoints = cs35l56_3_fb_endpoints, .name_prefix = "AMP4" } @@ -490,14 +717,14 @@ static const struct snd_soc_acpi_adr_device cs35l56_2_r_adr[] = { static const struct snd_soc_acpi_adr_device cs35l56_3_l_adr[] = { { .adr = 0x00033001fa355601ull, - .num_endpoints = 1, - .endpoints = &spk_l_endpoint, + .num_endpoints = ARRAY_SIZE(cs35l56_l_fb_endpoints), + .endpoints = cs35l56_l_fb_endpoints, .name_prefix = "AMP1" }, { .adr = 0x00033101fa355601ull, - .num_endpoints = 1, - .endpoints = &spk_2_endpoint, + .num_endpoints = ARRAY_SIZE(cs35l56_2_fb_endpoints), + .endpoints = cs35l56_2_fb_endpoints, .name_prefix = "AMP2" } }; @@ -765,6 +992,40 @@ static const struct snd_soc_acpi_link_adr cs42l43_link0_cs35l56_link2_link3[] = {} }; +static const struct snd_soc_acpi_link_adr cs42l43_link3_cs35l56_x4_link0_link1_spkagg[] = { + /* Expected order: jack -> amp */ + { + .mask = BIT(3), + .num_adr = ARRAY_SIZE(cs42l43_l3_4amp_spkagg_adr), + .adr_d = cs42l43_l3_4amp_spkagg_adr, + }, + { + .mask = BIT(1), + .num_adr = 2, + .adr_d = cs35l56_1_adr, + }, + { + .mask = BIT(0), + .num_adr = 2, + .adr_d = cs35l56_0_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr mtl_cs35l56_x8_link0_link1_fb[] = { + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs35l56_1_fb_adr), + .adr_d = cs35l56_1_fb_adr, + }, + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs35l56_0_fb_adr), + .adr_d = cs35l56_0_fb_adr, + }, + {} +}; + /* this table is used when there is no I2S codec present */ struct snd_soc_acpi_mach snd_soc_acpi_intel_mtl_sdw_machines[] = { /* mockup tests need to be first */ @@ -841,12 +1102,24 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_mtl_sdw_machines[] = { .drv_name = "sof_sdw", .sof_tplg_filename = "sof-mtl-cs42l43-l0-cs35l56-l23.tplg", }, + { + .link_mask = BIT(0) | BIT(1) | BIT(3), + .links = cs42l43_link3_cs35l56_x4_link0_link1_spkagg, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-mtl-cs42l43-l3-cs35l56-l01-spkagg.tplg", + }, { .link_mask = GENMASK(2, 0), .links = mtl_cs42l43_cs35l56, .drv_name = "sof_sdw", .sof_tplg_filename = "sof-mtl-cs42l43-l0-cs35l56-l12.tplg", }, + { + .link_mask = BIT(0) | BIT(1), + .links = mtl_cs35l56_x8_link0_link1_fb, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-mtl-cs35l56-l01-fb8.tplg" + }, { .link_mask = BIT(0), .links = mtl_cs42l43_l0, diff --git a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c index f1c0d7a02cda..9eb4a43e3e7a 100644 --- a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c @@ -8,6 +8,7 @@ #include <sound/soc-acpi.h> #include <sound/soc-acpi-intel-match.h> +#include "soc-acpi-intel-sdca-quirks.h" #include "soc-acpi-intel-sdw-mockup-match.h" #include <sound/soc-acpi-intel-ssp-common.h> @@ -35,6 +36,20 @@ static const struct snd_soc_acpi_endpoint single_endpoint = { .group_id = 0, }; +static const struct snd_soc_acpi_endpoint spk_l_endpoint = { + .num = 0, + .aggregated = 1, + .group_position = 0, + .group_id = 1, +}; + +static const struct snd_soc_acpi_endpoint spk_r_endpoint = { + .num = 0, + .aggregated = 1, + .group_position = 1, + .group_id = 1, +}; + /* * Multi-function codecs with three endpoints created for * headset, amp and dmic functions. @@ -60,6 +75,47 @@ static const struct snd_soc_acpi_endpoint rt_mf_endpoints[] = { }, }; +static const struct snd_soc_acpi_endpoint jack_dmic_endpoints[] = { + /* Jack Endpoint */ + { + .num = 0, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + /* DMIC Endpoint */ + { + .num = 1, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, +}; + +static const struct snd_soc_acpi_endpoint jack_amp_g1_dmic_endpoints_endpoints[] = { + /* Jack Endpoint */ + { + .num = 0, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + /* Amp Endpoint, work as spk_l_endpoint */ + { + .num = 1, + .aggregated = 1, + .group_position = 0, + .group_id = 1, + }, + /* DMIC Endpoint */ + { + .num = 2, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, +}; + static const struct snd_soc_acpi_adr_device rt711_sdca_0_adr[] = { { .adr = 0x000030025D071101ull, @@ -69,6 +125,24 @@ static const struct snd_soc_acpi_adr_device rt711_sdca_0_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt712_vb_2_group1_adr[] = { + { + .adr = 0x000230025D071201ull, + .num_endpoints = ARRAY_SIZE(jack_amp_g1_dmic_endpoints_endpoints), + .endpoints = jack_amp_g1_dmic_endpoints_endpoints, + .name_prefix = "rt712" + } +}; + +static const struct snd_soc_acpi_adr_device rt713_vb_2_adr[] = { + { + .adr = 0x000230025d071301ull, + .num_endpoints = ARRAY_SIZE(jack_dmic_endpoints), + .endpoints = jack_dmic_endpoints, + .name_prefix = "rt713" + } +}; + static const struct snd_soc_acpi_adr_device rt721_3_single_adr[] = { { .adr = 0x000330025d072101ull, @@ -114,6 +188,33 @@ static const struct snd_soc_acpi_adr_device rt722_3_single_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt1320_1_group1_adr[] = { + { + .adr = 0x000130025D132001ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "rt1320-1" + } +}; + +static const struct snd_soc_acpi_adr_device rt1320_1_group2_adr[] = { + { + .adr = 0x000130025D132001ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "rt1320-1" + } +}; + +static const struct snd_soc_acpi_adr_device rt1320_3_group2_adr[] = { + { + .adr = 0x000330025D132001ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "rt1320-2" + } +}; + static const struct snd_soc_acpi_link_adr ptl_rt722_only[] = { { .mask = BIT(0), @@ -150,6 +251,39 @@ static const struct snd_soc_acpi_link_adr ptl_rvp[] = { {} }; +static const struct snd_soc_acpi_link_adr lnl_sdw_rt713_vb_l2_rt1320_l13[] = { + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(rt713_vb_2_adr), + .adr_d = rt713_vb_2_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(rt1320_1_group2_adr), + .adr_d = rt1320_1_group2_adr, + }, + { + .mask = BIT(3), + .num_adr = ARRAY_SIZE(rt1320_3_group2_adr), + .adr_d = rt1320_3_group2_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr lnl_sdw_rt712_vb_l2_rt1320_l1[] = { + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(rt712_vb_2_group1_adr), + .adr_d = rt712_vb_2_group1_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(rt1320_1_group1_adr), + .adr_d = rt1320_1_group1_adr, + }, + {} +}; + /* this table is used when there is no I2S codec present */ struct snd_soc_acpi_mach snd_soc_acpi_intel_ptl_sdw_machines[] = { /* mockup tests need to be first */ @@ -201,6 +335,20 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_ptl_sdw_machines[] = { .drv_name = "sof_sdw", .sof_tplg_filename = "sof-ptl-rt722.tplg", }, + { + .link_mask = BIT(1) | BIT(2), + .links = lnl_sdw_rt712_vb_l2_rt1320_l1, + .drv_name = "sof_sdw", + .machine_check = snd_soc_acpi_intel_sdca_is_device_rt712_vb, + .sof_tplg_filename = "sof-lnl-rt712-l2-rt1320-l1.tplg" + }, + { + .link_mask = BIT(1) | BIT(2) | BIT(3), + .links = lnl_sdw_rt713_vb_l2_rt1320_l13, + .drv_name = "sof_sdw", + .machine_check = snd_soc_acpi_intel_sdca_is_device_rt712_vb, + .sof_tplg_filename = "sof-lnl-rt713-l2-rt1320-l13.tplg" + }, {}, }; EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_ptl_sdw_machines); diff --git a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c index 161ba532d270..6f8c06413665 100644 --- a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c @@ -536,6 +536,194 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_tgl_machines[] = { }; EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_tgl_machines); +static const struct snd_soc_acpi_endpoint cs35l56_l_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 0, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 0, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_r_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 1, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 1, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_2_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 2, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 2, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_3_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 3, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 3, + .group_id = 2, + }, +}; + +static const struct snd_soc_acpi_endpoint cs35l56_4_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 4, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 4, + .group_id = 2, + } +}; + +static const struct snd_soc_acpi_endpoint cs35l56_5_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 5, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 5, + .group_id = 2, + } +}; + +static const struct snd_soc_acpi_endpoint cs35l56_6_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 6, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 6, + .group_id = 2, + } +}; + +static const struct snd_soc_acpi_endpoint cs35l56_7_fb_endpoints[] = { + { /* Speaker Playback Endpoint */ + .num = 0, + .aggregated = 1, + .group_position = 7, + .group_id = 1, + }, + { /* Feedback Capture Endpoint */ + .num = 1, + .aggregated = 1, + .group_position = 7, + .group_id = 2, + } +}; + +static const struct snd_soc_acpi_adr_device cs35l56_sdw_eight_1_4_fb_adr[] = { + { + .adr = 0x00003301fa355601, + .num_endpoints = ARRAY_SIZE(cs35l56_l_fb_endpoints), + .endpoints = cs35l56_l_fb_endpoints, + .name_prefix = "AMP1" + }, + { + .adr = 0x00003201fa355601, + .num_endpoints = ARRAY_SIZE(cs35l56_2_fb_endpoints), + .endpoints = cs35l56_2_fb_endpoints, + .name_prefix = "AMP2" + }, + { + .adr = 0x00003101fa355601, + .num_endpoints = ARRAY_SIZE(cs35l56_4_fb_endpoints), + .endpoints = cs35l56_4_fb_endpoints, + .name_prefix = "AMP3" + }, + { + .adr = 0x00003001fa355601, + .num_endpoints = ARRAY_SIZE(cs35l56_6_fb_endpoints), + .endpoints = cs35l56_6_fb_endpoints, + .name_prefix = "AMP4" + }, +}; + +static const struct snd_soc_acpi_adr_device cs35l56_sdw_eight_5_8_fb_adr[] = { + { + .adr = 0x00013701fa355601, + .num_endpoints = ARRAY_SIZE(cs35l56_r_fb_endpoints), + .endpoints = cs35l56_r_fb_endpoints, + .name_prefix = "AMP8" + }, + { + .adr = 0x00013601fa355601, + .num_endpoints = ARRAY_SIZE(cs35l56_3_fb_endpoints), + .endpoints = cs35l56_3_fb_endpoints, + .name_prefix = "AMP7" + }, + { + .adr = 0x00013501fa355601, + .num_endpoints = ARRAY_SIZE(cs35l56_5_fb_endpoints), + .endpoints = cs35l56_5_fb_endpoints, + .name_prefix = "AMP6" + }, + { + .adr = 0x00013401fa355601, + .num_endpoints = ARRAY_SIZE(cs35l56_7_fb_endpoints), + .endpoints = cs35l56_7_fb_endpoints, + .name_prefix = "AMP5" + }, +}; + +static const struct snd_soc_acpi_link_adr up_extreme_cs35l56_sdw_eight[] = { + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs35l56_sdw_eight_5_8_fb_adr), + .adr_d = cs35l56_sdw_eight_5_8_fb_adr, + }, + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs35l56_sdw_eight_1_4_fb_adr), + .adr_d = cs35l56_sdw_eight_1_4_fb_adr, + }, + {} +}; + /* this table is used when there is no I2S codec present */ struct snd_soc_acpi_mach snd_soc_acpi_intel_tgl_sdw_machines[] = { /* mockup tests need to be first */ @@ -635,6 +823,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_tgl_sdw_machines[] = { .drv_name = "sof_sdw", .sof_tplg_filename = "sof-tgl-rt711.tplg", }, + { + .link_mask = BIT(0) | BIT(1), + .links = up_extreme_cs35l56_sdw_eight, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-tgl-cs35l56-l01-fb8.tplg" + }, {}, }; EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_tgl_sdw_machines); diff --git a/sound/soc/intel/keembay/kmb_platform.c b/sound/soc/intel/keembay/kmb_platform.c index aa5de167e790..4ed71d11ad77 100644 --- a/sound/soc/intel/keembay/kmb_platform.c +++ b/sound/soc/intel/keembay/kmb_platform.c @@ -869,7 +869,7 @@ static int kmb_plat_dai_probe(struct platform_device *pdev) kmb_i2s->fifo_th = (1 << COMP1_FIFO_DEPTH(comp1_reg)) / 2; - kmb_i2s->use_pio = !(of_property_read_bool(np, "dmas")); + kmb_i2s->use_pio = !of_property_present(np, "dmas"); if (kmb_i2s->use_pio) { irq = platform_get_irq_optional(pdev, 0); diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c index 9b72b2a7ae91..6b6330583941 100644 --- a/sound/soc/mediatek/common/mtk-afe-platform-driver.c +++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c @@ -120,8 +120,8 @@ int mtk_afe_pcm_new(struct snd_soc_component *component, struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component); size = afe->mtk_afe_hardware->buffer_bytes_max; - snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, - afe->dev, size, size); + snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, afe->dev, 0, size); + return 0; } EXPORT_SYMBOL_GPL(mtk_afe_pcm_new); diff --git a/sound/soc/mediatek/common/mtk-soundcard-driver.c b/sound/soc/mediatek/common/mtk-soundcard-driver.c index 3bbf42c42805..f4314dddc460 100644 --- a/sound/soc/mediatek/common/mtk-soundcard-driver.c +++ b/sound/soc/mediatek/common/mtk-soundcard-driver.c @@ -221,7 +221,7 @@ int mtk_soundcard_common_probe(struct platform_device *pdev) card->name = pdata->card_name; } - needs_legacy_probe = !of_property_read_bool(pdev->dev.of_node, "audio-routing"); + needs_legacy_probe = !of_property_present(pdev->dev.of_node, "audio-routing"); if (needs_legacy_probe) { /* * If we have no .soc_probe() callback there's no way of using @@ -262,7 +262,7 @@ int mtk_soundcard_common_probe(struct platform_device *pdev) adsp_node = NULL; if (adsp_node) { - if (of_property_read_bool(pdev->dev.of_node, "mediatek,dai-link")) { + if (of_property_present(pdev->dev.of_node, "mediatek,dai-link")) { ret = mtk_sof_dailink_parse_of(card, pdev->dev.of_node, "mediatek,dai-link", card->dai_link, card->num_links); diff --git a/sound/soc/mediatek/mt8192/mt8192-afe-pcm.c b/sound/soc/mediatek/mt8192/mt8192-afe-pcm.c index 9b502f4cd6ea..80cda7bf5ccc 100644 --- a/sound/soc/mediatek/mt8192/mt8192-afe-pcm.c +++ b/sound/soc/mediatek/mt8192/mt8192-afe-pcm.c @@ -2158,27 +2158,26 @@ static int mt8192_afe_pcm_dev_probe(struct platform_device *pdev) { struct mtk_base_afe *afe; struct mt8192_afe_private *afe_priv; - struct device *dev; + struct device *dev = &pdev->dev; struct reset_control *rstc; int i, ret, irq_id; - ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(34)); + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(34)); if (ret) return ret; - afe = devm_kzalloc(&pdev->dev, sizeof(*afe), GFP_KERNEL); + afe = devm_kzalloc(dev, sizeof(*afe), GFP_KERNEL); if (!afe) return -ENOMEM; platform_set_drvdata(pdev, afe); - afe->platform_priv = devm_kzalloc(&pdev->dev, sizeof(*afe_priv), + afe->platform_priv = devm_kzalloc(dev, sizeof(*afe_priv), GFP_KERNEL); if (!afe->platform_priv) return -ENOMEM; afe_priv = afe->platform_priv; - afe->dev = &pdev->dev; - dev = afe->dev; + afe->dev = dev; /* init audio related clock */ ret = mt8192_init_clock(afe); @@ -2196,7 +2195,7 @@ static int mt8192_afe_pcm_dev_probe(struct platform_device *pdev) if (ret) return dev_err_probe(dev, ret, "failed to trigger audio reset\n"); - ret = devm_pm_runtime_enable(&pdev->dev); + ret = devm_pm_runtime_enable(dev); if (ret) return ret; @@ -2212,13 +2211,13 @@ static int mt8192_afe_pcm_dev_probe(struct platform_device *pdev) /* enable clock for regcache get default value from hw */ afe_priv->pm_runtime_bypass_reg_ctl = true; - pm_runtime_get_sync(&pdev->dev); + pm_runtime_get_sync(dev); ret = regmap_reinit_cache(afe->regmap, &mt8192_afe_regmap_config); if (ret) return dev_err_probe(dev, ret, "regmap_reinit_cache fail\n"); - pm_runtime_put_sync(&pdev->dev); + pm_runtime_put_sync(dev); afe_priv->pm_runtime_bypass_reg_ctl = false; regcache_cache_only(afe->regmap, true); @@ -2285,7 +2284,7 @@ static int mt8192_afe_pcm_dev_probe(struct platform_device *pdev) afe->runtime_suspend = mt8192_afe_runtime_suspend; /* register platform */ - ret = devm_snd_soc_register_component(&pdev->dev, + ret = devm_snd_soc_register_component(dev, &mtk_afe_pcm_platform, afe->dai_drivers, afe->num_dai_drivers); diff --git a/sound/soc/mediatek/mt8365/Makefile b/sound/soc/mediatek/mt8365/Makefile index 52ba45a8498a..b197025e34bb 100644 --- a/sound/soc/mediatek/mt8365/Makefile +++ b/sound/soc/mediatek/mt8365/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # MTK Platform driver -snd-soc-mt8365-pcm-objs := \ +snd-soc-mt8365-pcm-y := \ mt8365-afe-clk.o \ mt8365-afe-pcm.o \ mt8365-dai-adda.o \ diff --git a/sound/soc/mediatek/mt8365/mt8365-mt6357.c b/sound/soc/mediatek/mt8365/mt8365-mt6357.c index d398e83ea052..9f28d6bf0323 100644 --- a/sound/soc/mediatek/mt8365/mt8365-mt6357.c +++ b/sound/soc/mediatek/mt8365/mt8365-mt6357.c @@ -6,12 +6,19 @@ * Authors: Nicolas Belin <nbelin@baylibre.com> */ +#include <linux/array_size.h> +#include <linux/dev_printk.h> +#include <linux/err.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> -#include <linux/of_gpio.h> +#include <linux/pinctrl/consumer.h> +#include <linux/platform_device.h> +#include <linux/types.h> + #include <sound/soc.h> #include <sound/pcm_params.h> + #include "mt8365-afe-common.h" -#include <linux/pinctrl/consumer.h> #include "../common/mtk-soc-card.h" #include "../common/mtk-soundcard-driver.h" diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c index 928cf5cb5999..7ee60a58a336 100644 --- a/sound/soc/qcom/common.c +++ b/sound/soc/qcom/common.c @@ -44,20 +44,20 @@ int qcom_snd_parse_of(struct snd_soc_card *card) return ret; } - if (of_property_read_bool(dev->of_node, "widgets")) { + if (of_property_present(dev->of_node, "widgets")) { ret = snd_soc_of_parse_audio_simple_widgets(card, "widgets"); if (ret) return ret; } /* DAPM routes */ - if (of_property_read_bool(dev->of_node, "audio-routing")) { + if (of_property_present(dev->of_node, "audio-routing")) { ret = snd_soc_of_parse_audio_routing(card, "audio-routing"); if (ret) return ret; } /* Deprecated, only for compatibility with old device trees */ - if (of_property_read_bool(dev->of_node, "qcom,audio-routing")) { + if (of_property_present(dev->of_node, "qcom,audio-routing")) { ret = snd_soc_of_parse_audio_routing(card, "qcom,audio-routing"); if (ret) return ret; diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c index addd2c4bdd3e..9946f12254b3 100644 --- a/sound/soc/qcom/lpass-platform.c +++ b/sound/soc/qcom/lpass-platform.c @@ -1232,14 +1232,16 @@ static int lpass_platform_copy(struct snd_soc_component *component, if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { if (is_cdc_dma_port(dai_id)) { - ret = copy_from_iter_toio(dma_buf, buf, bytes); + if (copy_from_iter_toio(dma_buf, bytes, buf) != bytes) + ret = -EFAULT; } else { if (copy_from_iter((void __force *)dma_buf, bytes, buf) != bytes) ret = -EFAULT; } } else if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) { if (is_cdc_dma_port(dai_id)) { - ret = copy_to_iter_fromio(buf, dma_buf, bytes); + if (copy_to_iter_fromio(dma_buf, bytes, buf) != bytes) + ret = -EFAULT; } else { if (copy_to_iter((void __force *)dma_buf, bytes, buf) != bytes) ret = -EFAULT; diff --git a/sound/soc/qcom/sc7180.c b/sound/soc/qcom/sc7180.c index bc030ce29680..d95710b1ea4e 100644 --- a/sound/soc/qcom/sc7180.c +++ b/sound/soc/qcom/sc7180.c @@ -513,7 +513,7 @@ static int sc7180_snd_platform_probe(struct platform_device *pdev) card->controls = sc7180_snd_controls; card->num_controls = ARRAY_SIZE(sc7180_snd_controls); - if (of_property_read_bool(dev->of_node, "dmic-gpios")) { + if (of_property_present(dev->of_node, "dmic-gpios")) { card->dapm_widgets = sc7180_snd_dual_mic_widgets, card->num_dapm_widgets = ARRAY_SIZE(sc7180_snd_dual_mic_widgets), card->controls = sc7180_snd_dual_mic_controls, diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c index a479d7e5b7fb..fcc7df75346f 100644 --- a/sound/soc/qcom/sdm845.c +++ b/sound/soc/qcom/sdm845.c @@ -215,6 +215,7 @@ static int sdm845_snd_hw_params(struct snd_pcm_substream *substream, ret = sdm845_slim_snd_hw_params(substream, params); break; case QUATERNARY_MI2S_RX: + case SECONDARY_MI2S_RX: break; default: pr_err("%s: invalid dai id 0x%x\n", __func__, cpu_dai->id); @@ -356,6 +357,7 @@ static int sdm845_snd_startup(struct snd_pcm_substream *substream) snd_soc_dai_set_fmt(codec_dai, codec_dai_fmt); break; + case SECONDARY_MI2S_RX: case SECONDARY_MI2S_TX: codec_dai_fmt |= SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_I2S; if (++(data->sec_mi2s_clk_count) == 1) { @@ -371,8 +373,6 @@ static int sdm845_snd_startup(struct snd_pcm_substream *substream) Q6AFE_LPASS_CLK_ID_QUAD_MI2S_IBIT, MI2S_BCLK_RATE, SNDRV_PCM_STREAM_PLAYBACK); snd_soc_dai_set_fmt(cpu_dai, fmt); - - break; case QUATERNARY_TDM_RX_0: @@ -441,6 +441,7 @@ static void sdm845_snd_shutdown(struct snd_pcm_substream *substream) } break; + case SECONDARY_MI2S_RX: case SECONDARY_MI2S_TX: if (--(data->sec_mi2s_clk_count) == 0) { snd_soc_dai_set_sysclk(cpu_dai, diff --git a/sound/soc/renesas/Kconfig b/sound/soc/renesas/Kconfig index 426632996a0a..cb01fb36355f 100644 --- a/sound/soc/renesas/Kconfig +++ b/sound/soc/renesas/Kconfig @@ -67,7 +67,7 @@ config SND_SH7760_AC97 config SND_SIU_MIGOR tristate "SIU sound support on Migo-R" - depends on SH_MIGOR && I2C + depends on SH_MIGOR && I2C && DMADEVICES select SND_SOC_SH4_SIU select SND_SOC_WM8978 help diff --git a/sound/soc/renesas/rcar/adg.c b/sound/soc/renesas/rcar/adg.c index 0f190abf00e7..191f212d338c 100644 --- a/sound/soc/renesas/rcar/adg.c +++ b/sound/soc/renesas/rcar/adg.c @@ -374,12 +374,12 @@ int rsnd_adg_ssi_clk_try_start(struct rsnd_mod *ssi_mod, unsigned int rate) return 0; } -void rsnd_adg_clk_control(struct rsnd_priv *priv, int enable) +int rsnd_adg_clk_control(struct rsnd_priv *priv, int enable) { struct rsnd_adg *adg = rsnd_priv_to_adg(priv); struct rsnd_mod *adg_mod = rsnd_mod_get(adg); struct clk *clk; - int i; + int ret = 0, i; if (enable) { rsnd_mod_bset(adg_mod, BRGCKR, 0x80770000, adg->ckr); @@ -389,18 +389,33 @@ void rsnd_adg_clk_control(struct rsnd_priv *priv, int enable) for_each_rsnd_clkin(clk, adg, i) { if (enable) { - clk_prepare_enable(clk); + ret = clk_prepare_enable(clk); /* * We shouldn't use clk_get_rate() under * atomic context. Let's keep it when * rsnd_adg_clk_enable() was called */ + if (ret < 0) + break; + adg->clkin_rate[i] = clk_get_rate(clk); } else { - clk_disable_unprepare(clk); + if (adg->clkin_rate[i]) + clk_disable_unprepare(clk); + + adg->clkin_rate[i] = 0; } } + + /* + * rsnd_adg_clk_enable() might return error (_disable() will not). + * We need to rollback in such case + */ + if (ret < 0) + rsnd_adg_clk_disable(priv); + + return ret; } static struct clk *rsnd_adg_create_null_clk(struct rsnd_priv *priv, @@ -753,7 +768,10 @@ int rsnd_adg_probe(struct rsnd_priv *priv) if (ret) return ret; - rsnd_adg_clk_enable(priv); + ret = rsnd_adg_clk_enable(priv); + if (ret) + return ret; + rsnd_adg_clk_dbg_info(priv, NULL); return 0; diff --git a/sound/soc/renesas/rcar/core.c b/sound/soc/renesas/rcar/core.c index e2234928c9e8..d3709fd0409e 100644 --- a/sound/soc/renesas/rcar/core.c +++ b/sound/soc/renesas/rcar/core.c @@ -2086,9 +2086,7 @@ static int __maybe_unused rsnd_resume(struct device *dev) { struct rsnd_priv *priv = dev_get_drvdata(dev); - rsnd_adg_clk_enable(priv); - - return 0; + return rsnd_adg_clk_enable(priv); } static const struct dev_pm_ops rsnd_pm_ops = { diff --git a/sound/soc/renesas/rcar/rsnd.h b/sound/soc/renesas/rcar/rsnd.h index 3c164d8e3b16..a5f54b65313c 100644 --- a/sound/soc/renesas/rcar/rsnd.h +++ b/sound/soc/renesas/rcar/rsnd.h @@ -608,7 +608,7 @@ int rsnd_adg_set_cmd_timsel_gen2(struct rsnd_mod *cmd_mod, struct rsnd_dai_stream *io); #define rsnd_adg_clk_enable(priv) rsnd_adg_clk_control(priv, 1) #define rsnd_adg_clk_disable(priv) rsnd_adg_clk_control(priv, 0) -void rsnd_adg_clk_control(struct rsnd_priv *priv, int enable); +int rsnd_adg_clk_control(struct rsnd_priv *priv, int enable); void rsnd_adg_clk_dbg_info(struct rsnd_priv *priv, struct seq_file *m); /* diff --git a/sound/soc/renesas/rz-ssi.c b/sound/soc/renesas/rz-ssi.c index 6efd017aaa7f..3a0af4ca7ab6 100644 --- a/sound/soc/renesas/rz-ssi.c +++ b/sound/soc/renesas/rz-ssi.c @@ -9,6 +9,7 @@ #include <linux/clk.h> #include <linux/dmaengine.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/module.h> #include <linux/pm_runtime.h> #include <linux/reset.h> @@ -71,7 +72,7 @@ #define PREALLOC_BUFFER (SZ_32K) #define PREALLOC_BUFFER_MAX (SZ_32K) -#define SSI_RATES SNDRV_PCM_RATE_8000_48000 /* 8k-44.1kHz */ +#define SSI_RATES SNDRV_PCM_RATE_8000_48000 /* 8k-48kHz */ #define SSI_FMTS SNDRV_PCM_FMTBIT_S16_LE #define SSI_CHAN_MIN 2 #define SSI_CHAN_MAX 2 @@ -99,7 +100,6 @@ struct rz_ssi_stream { struct rz_ssi_priv { void __iomem *base; - struct platform_device *pdev; struct reset_control *rstc; struct device *dev; struct clk *sfr_clk; @@ -163,16 +163,7 @@ static void rz_ssi_reg_mask_setl(struct rz_ssi_priv *priv, uint reg, writel(val, (priv->base + reg)); } -static inline struct snd_soc_dai * -rz_ssi_get_dai(struct snd_pcm_substream *substream) -{ - struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); - - return snd_soc_rtd_to_cpu(rtd, 0); -} - -static inline bool rz_ssi_stream_is_play(struct rz_ssi_priv *ssi, - struct snd_pcm_substream *substream) +static inline bool rz_ssi_stream_is_play(struct snd_pcm_substream *substream) { return substream->stream == SNDRV_PCM_STREAM_PLAYBACK; } @@ -244,22 +235,21 @@ static void rz_ssi_stream_init(struct rz_ssi_stream *strm, static void rz_ssi_stream_quit(struct rz_ssi_priv *ssi, struct rz_ssi_stream *strm) { - struct snd_soc_dai *dai = rz_ssi_get_dai(strm->substream); + struct device *dev = ssi->dev; rz_ssi_set_substream(strm, NULL); if (strm->oerr_num > 0) - dev_info(dai->dev, "overrun = %d\n", strm->oerr_num); + dev_info(dev, "overrun = %d\n", strm->oerr_num); if (strm->uerr_num > 0) - dev_info(dai->dev, "underrun = %d\n", strm->uerr_num); + dev_info(dev, "underrun = %d\n", strm->uerr_num); } static int rz_ssi_clk_setup(struct rz_ssi_priv *ssi, unsigned int rate, unsigned int channels) { - static s8 ckdv[16] = { 1, 2, 4, 8, 16, 32, 64, 128, - 6, 12, 24, 48, 96, -1, -1, -1 }; + static u8 ckdv[] = { 1, 2, 4, 8, 16, 32, 64, 128, 6, 12, 24, 48, 96 }; unsigned int channel_bits = 32; /* System Word Length */ unsigned long bclk_rate = rate * channels * channel_bits; unsigned int div; @@ -318,7 +308,8 @@ static int rz_ssi_clk_setup(struct rz_ssi_priv *ssi, unsigned int rate, static void rz_ssi_set_idle(struct rz_ssi_priv *ssi) { - int timeout; + u32 tmp; + int ret; /* Disable irqs */ rz_ssi_reg_mask_setl(ssi, SSICR, SSICR_TUIEN | SSICR_TOIEN | @@ -331,15 +322,9 @@ static void rz_ssi_set_idle(struct rz_ssi_priv *ssi) SSISR_RUIRQ), 0); /* Wait for idle */ - timeout = 100; - while (--timeout) { - if (rz_ssi_reg_readl(ssi, SSISR) & SSISR_IIRQ) - break; - udelay(1); - } - - if (!timeout) - dev_info(ssi->dev, "timeout waiting for SSI idle\n"); + ret = readl_poll_timeout_atomic(ssi->base + SSISR, tmp, (tmp & SSISR_IIRQ), 1, 100); + if (ret) + dev_warn_ratelimited(ssi->dev, "timeout waiting for SSI idle\n"); /* Hold FIFOs in reset */ rz_ssi_reg_mask_setl(ssi, SSIFCR, 0, SSIFCR_FIFO_RST); @@ -347,7 +332,7 @@ static void rz_ssi_set_idle(struct rz_ssi_priv *ssi) static int rz_ssi_start(struct rz_ssi_priv *ssi, struct rz_ssi_stream *strm) { - bool is_play = rz_ssi_stream_is_play(ssi, strm->substream); + bool is_play = rz_ssi_stream_is_play(strm->substream); bool is_full_duplex; u32 ssicr, ssifcr; @@ -403,6 +388,15 @@ static int rz_ssi_start(struct rz_ssi_priv *ssi, struct rz_ssi_stream *strm) return 0; } +static int rz_ssi_swreset(struct rz_ssi_priv *ssi) +{ + u32 tmp; + + rz_ssi_reg_mask_setl(ssi, SSIFCR, 0, SSIFCR_SSIRST); + rz_ssi_reg_mask_setl(ssi, SSIFCR, SSIFCR_SSIRST, 0); + return readl_poll_timeout_atomic(ssi->base + SSIFCR, tmp, !(tmp & SSIFCR_SSIRST), 1, 5); +} + static int rz_ssi_stop(struct rz_ssi_priv *ssi, struct rz_ssi_stream *strm) { strm->running = 0; @@ -415,8 +409,12 @@ static int rz_ssi_stop(struct rz_ssi_priv *ssi, struct rz_ssi_stream *strm) rz_ssi_reg_mask_setl(ssi, SSICR, SSICR_TEN | SSICR_REN, 0); /* Cancel all remaining DMA transactions */ - if (rz_ssi_is_dma_enabled(ssi)) - dmaengine_terminate_async(strm->dma_ch); + if (rz_ssi_is_dma_enabled(ssi)) { + if (ssi->playback.dma_ch) + dmaengine_terminate_async(ssi->playback.dma_ch); + if (ssi->capture.dma_ch) + dmaengine_terminate_async(ssi->capture.dma_ch); + } rz_ssi_set_idle(ssi); @@ -523,6 +521,8 @@ static int rz_ssi_pio_send(struct rz_ssi_priv *ssi, struct rz_ssi_stream *strm) sample_space = strm->fifo_sample_size; ssifsr = rz_ssi_reg_readl(ssi, SSIFSR); sample_space -= (ssifsr >> SSIFSR_TDC_SHIFT) & SSIFSR_TDC_MASK; + if (sample_space < 0) + return -EINVAL; /* Only add full frames at a time */ while (frames_left && (sample_space >= runtime->channels)) { @@ -680,7 +680,7 @@ static int rz_ssi_dma_transfer(struct rz_ssi_priv *ssi, */ return 0; - dir = rz_ssi_stream_is_play(ssi, substream) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM; + dir = rz_ssi_stream_is_play(substream) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM; /* Always transfer 1 period */ amount = runtime->period_size; @@ -784,6 +784,32 @@ no_dma: return -ENODEV; } +static int rz_ssi_trigger_resume(struct rz_ssi_priv *ssi) +{ + int ret; + + if (rz_ssi_is_stream_running(&ssi->playback) || + rz_ssi_is_stream_running(&ssi->capture)) + return 0; + + ret = rz_ssi_swreset(ssi); + if (ret) + return ret; + + return rz_ssi_clk_setup(ssi, ssi->hw_params_cache.rate, + ssi->hw_params_cache.channels); +} + +static void rz_ssi_streams_suspend(struct rz_ssi_priv *ssi) +{ + if (rz_ssi_is_stream_running(&ssi->playback) || + rz_ssi_is_stream_running(&ssi->capture)) + return; + + ssi->playback.dma_buffer_pos = 0; + ssi->capture.dma_buffer_pos = 0; +} + static int rz_ssi_dai_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { @@ -792,21 +818,21 @@ static int rz_ssi_dai_trigger(struct snd_pcm_substream *substream, int cmd, int ret = 0, i, num_transfer = 1; switch (cmd) { - case SNDRV_PCM_TRIGGER_START: - /* Soft Reset */ - if (!rz_ssi_is_stream_running(&ssi->playback) && - !rz_ssi_is_stream_running(&ssi->capture)) { - rz_ssi_reg_mask_setl(ssi, SSIFCR, 0, SSIFCR_SSIRST); - rz_ssi_reg_mask_setl(ssi, SSIFCR, SSIFCR_SSIRST, 0); - udelay(5); - } + case SNDRV_PCM_TRIGGER_RESUME: + ret = rz_ssi_trigger_resume(ssi); + if (ret) + return ret; - rz_ssi_stream_init(strm, substream); + fallthrough; + + case SNDRV_PCM_TRIGGER_START: + if (cmd == SNDRV_PCM_TRIGGER_START) + rz_ssi_stream_init(strm, substream); if (ssi->dma_rt) { bool is_playback; - is_playback = rz_ssi_stream_is_play(ssi, substream); + is_playback = rz_ssi_stream_is_play(substream); ret = rz_ssi_dma_slave_config(ssi, ssi->playback.dma_ch, is_playback); /* Fallback to pio */ @@ -829,6 +855,12 @@ static int rz_ssi_dai_trigger(struct snd_pcm_substream *substream, int cmd, ret = rz_ssi_start(ssi, strm); break; + + case SNDRV_PCM_TRIGGER_SUSPEND: + rz_ssi_stop(ssi, strm); + rz_ssi_streams_suspend(ssi); + break; + case SNDRV_PCM_TRIGGER_STOP: rz_ssi_stop(ssi, strm); rz_ssi_stream_quit(ssi, strm); @@ -925,6 +957,7 @@ static int rz_ssi_dai_hw_params(struct snd_pcm_substream *substream, SNDRV_PCM_HW_PARAM_SAMPLE_BITS)->min; unsigned int channels = params_channels(params); unsigned int rate = params_rate(params); + int ret; if (sample_bits != 16) { dev_err(ssi->dev, "Unsupported sample width: %d\n", @@ -951,6 +984,10 @@ static int rz_ssi_dai_hw_params(struct snd_pcm_substream *substream, rz_ssi_cache_hw_params(ssi, rate, channels, strm->sample_width, sample_bits); + ret = rz_ssi_swreset(ssi); + if (ret) + return ret; + return rz_ssi_clk_setup(ssi, rate, channels); } @@ -963,7 +1000,8 @@ static const struct snd_soc_dai_ops rz_ssi_dai_ops = { static const struct snd_pcm_hardware rz_ssi_pcm_hardware = { .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_MMAP | - SNDRV_PCM_INFO_MMAP_VALID, + SNDRV_PCM_INFO_MMAP_VALID | + SNDRV_PCM_INFO_RESUME, .buffer_bytes_max = PREALLOC_BUFFER, .period_bytes_min = 32, .period_bytes_max = 8192, @@ -986,7 +1024,8 @@ static int rz_ssi_pcm_open(struct snd_soc_component *component, static snd_pcm_uframes_t rz_ssi_pcm_pointer(struct snd_soc_component *component, struct snd_pcm_substream *substream) { - struct snd_soc_dai *dai = rz_ssi_get_dai(substream); + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct snd_soc_dai *dai = snd_soc_rtd_to_cpu(rtd, 0); struct rz_ssi_priv *ssi = snd_soc_dai_get_drvdata(dai); struct rz_ssi_stream *strm = rz_ssi_stream_get(ssi, substream); @@ -1031,37 +1070,37 @@ static const struct snd_soc_component_driver rz_ssi_soc_component = { static int rz_ssi_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; struct rz_ssi_priv *ssi; struct clk *audio_clk; struct resource *res; int ret; - ssi = devm_kzalloc(&pdev->dev, sizeof(*ssi), GFP_KERNEL); + ssi = devm_kzalloc(dev, sizeof(*ssi), GFP_KERNEL); if (!ssi) return -ENOMEM; - ssi->pdev = pdev; - ssi->dev = &pdev->dev; + ssi->dev = dev; ssi->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(ssi->base)) return PTR_ERR(ssi->base); ssi->phys = res->start; - ssi->clk = devm_clk_get(&pdev->dev, "ssi"); + ssi->clk = devm_clk_get(dev, "ssi"); if (IS_ERR(ssi->clk)) return PTR_ERR(ssi->clk); - ssi->sfr_clk = devm_clk_get(&pdev->dev, "ssi_sfr"); + ssi->sfr_clk = devm_clk_get(dev, "ssi_sfr"); if (IS_ERR(ssi->sfr_clk)) return PTR_ERR(ssi->sfr_clk); - audio_clk = devm_clk_get(&pdev->dev, "audio_clk1"); + audio_clk = devm_clk_get(dev, "audio_clk1"); if (IS_ERR(audio_clk)) return dev_err_probe(&pdev->dev, PTR_ERR(audio_clk), "no audio clk1"); ssi->audio_clk_1 = clk_get_rate(audio_clk); - audio_clk = devm_clk_get(&pdev->dev, "audio_clk2"); + audio_clk = devm_clk_get(dev, "audio_clk2"); if (IS_ERR(audio_clk)) return dev_err_probe(&pdev->dev, PTR_ERR(audio_clk), "no audio clk2"); @@ -1074,13 +1113,13 @@ static int rz_ssi_probe(struct platform_device *pdev) ssi->audio_mck = ssi->audio_clk_1 ? ssi->audio_clk_1 : ssi->audio_clk_2; /* Detect DMA support */ - ret = rz_ssi_dma_request(ssi, &pdev->dev); + ret = rz_ssi_dma_request(ssi, dev); if (ret < 0) { - dev_warn(&pdev->dev, "DMA not available, using PIO\n"); + dev_warn(dev, "DMA not available, using PIO\n"); ssi->playback.transfer = rz_ssi_pio_send; ssi->capture.transfer = rz_ssi_pio_recv; } else { - dev_info(&pdev->dev, "DMA enabled"); + dev_info(dev, "DMA enabled"); ssi->playback.transfer = rz_ssi_dma_transfer; ssi->capture.transfer = rz_ssi_dma_transfer; } @@ -1089,21 +1128,20 @@ static int rz_ssi_probe(struct platform_device *pdev) ssi->capture.priv = ssi; spin_lock_init(&ssi->lock); - dev_set_drvdata(&pdev->dev, ssi); + dev_set_drvdata(dev, ssi); /* Error Interrupt */ ssi->irq_int = platform_get_irq_byname(pdev, "int_req"); if (ssi->irq_int < 0) { - rz_ssi_release_dma_channels(ssi); - return ssi->irq_int; + ret = ssi->irq_int; + goto err_release_dma_chs; } - ret = devm_request_irq(&pdev->dev, ssi->irq_int, &rz_ssi_interrupt, - 0, dev_name(&pdev->dev), ssi); + ret = devm_request_irq(dev, ssi->irq_int, &rz_ssi_interrupt, + 0, dev_name(dev), ssi); if (ret < 0) { - rz_ssi_release_dma_channels(ssi); - return dev_err_probe(&pdev->dev, ret, - "irq request error (int_req)\n"); + dev_err_probe(dev, ret, "irq request error (int_req)\n"); + goto err_release_dma_chs; } if (!rz_ssi_is_dma_enabled(ssi)) { @@ -1115,11 +1153,11 @@ static int rz_ssi_probe(struct platform_device *pdev) if (ssi->irq_rt < 0) return ssi->irq_rt; - ret = devm_request_irq(&pdev->dev, ssi->irq_rt, + ret = devm_request_irq(dev, ssi->irq_rt, &rz_ssi_interrupt, 0, - dev_name(&pdev->dev), ssi); + dev_name(dev), ssi); if (ret < 0) - return dev_err_probe(&pdev->dev, ret, + return dev_err_probe(dev, ret, "irq request error (dma_rt)\n"); } else { if (ssi->irq_tx < 0) @@ -1128,52 +1166,48 @@ static int rz_ssi_probe(struct platform_device *pdev) if (ssi->irq_rx < 0) return ssi->irq_rx; - ret = devm_request_irq(&pdev->dev, ssi->irq_tx, + ret = devm_request_irq(dev, ssi->irq_tx, &rz_ssi_interrupt, 0, - dev_name(&pdev->dev), ssi); + dev_name(dev), ssi); if (ret < 0) - return dev_err_probe(&pdev->dev, ret, + return dev_err_probe(dev, ret, "irq request error (dma_tx)\n"); - ret = devm_request_irq(&pdev->dev, ssi->irq_rx, + ret = devm_request_irq(dev, ssi->irq_rx, &rz_ssi_interrupt, 0, - dev_name(&pdev->dev), ssi); + dev_name(dev), ssi); if (ret < 0) - return dev_err_probe(&pdev->dev, ret, + return dev_err_probe(dev, ret, "irq request error (dma_rx)\n"); } } - ssi->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + ssi->rstc = devm_reset_control_get_exclusive(dev, NULL); if (IS_ERR(ssi->rstc)) { ret = PTR_ERR(ssi->rstc); - goto err_reset; + goto err_release_dma_chs; } - reset_control_deassert(ssi->rstc); - pm_runtime_enable(&pdev->dev); - ret = pm_runtime_resume_and_get(&pdev->dev); + /* Default 0 for power saving. Can be overridden via sysfs. */ + pm_runtime_set_autosuspend_delay(dev, 0); + pm_runtime_use_autosuspend(dev); + ret = devm_pm_runtime_enable(dev); if (ret < 0) { - dev_err(&pdev->dev, "pm_runtime_resume_and_get failed\n"); - goto err_pm; + dev_err(dev, "Failed to enable runtime PM!\n"); + goto err_release_dma_chs; } - ret = devm_snd_soc_register_component(&pdev->dev, &rz_ssi_soc_component, + ret = devm_snd_soc_register_component(dev, &rz_ssi_soc_component, rz_ssi_soc_dai, ARRAY_SIZE(rz_ssi_soc_dai)); if (ret < 0) { - dev_err(&pdev->dev, "failed to register snd component\n"); - goto err_snd_soc; + dev_err(dev, "failed to register snd component\n"); + goto err_release_dma_chs; } return 0; -err_snd_soc: - pm_runtime_put(ssi->dev); -err_pm: - pm_runtime_disable(ssi->dev); - reset_control_assert(ssi->rstc); -err_reset: +err_release_dma_chs: rz_ssi_release_dma_channels(ssi); return ret; @@ -1185,8 +1219,6 @@ static void rz_ssi_remove(struct platform_device *pdev) rz_ssi_release_dma_channels(ssi); - pm_runtime_put(ssi->dev); - pm_runtime_disable(ssi->dev); reset_control_assert(ssi->rstc); } @@ -1196,10 +1228,30 @@ static const struct of_device_id rz_ssi_of_match[] = { }; MODULE_DEVICE_TABLE(of, rz_ssi_of_match); +static int rz_ssi_runtime_suspend(struct device *dev) +{ + struct rz_ssi_priv *ssi = dev_get_drvdata(dev); + + return reset_control_assert(ssi->rstc); +} + +static int rz_ssi_runtime_resume(struct device *dev) +{ + struct rz_ssi_priv *ssi = dev_get_drvdata(dev); + + return reset_control_deassert(ssi->rstc); +} + +static const struct dev_pm_ops rz_ssi_pm_ops = { + RUNTIME_PM_OPS(rz_ssi_runtime_suspend, rz_ssi_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) +}; + static struct platform_driver rz_ssi_driver = { .driver = { .name = "rz-ssi-pcm-audio", .of_match_table = rz_ssi_of_match, + .pm = pm_ptr(&rz_ssi_pm_ops), }, .probe = rz_ssi_probe, .remove = rz_ssi_remove, diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c index d1f28699652f..7f5fcaecee4b 100644 --- a/sound/soc/rockchip/rockchip_i2s_tdm.c +++ b/sound/soc/rockchip/rockchip_i2s_tdm.c @@ -22,7 +22,6 @@ #define DRV_NAME "rockchip-i2s-tdm" -#define DEFAULT_MCLK_FS 256 #define CH_GRP_MAX 4 /* The max channel 8 / 2 */ #define MULTIPLEX_CH_MAX 10 @@ -70,6 +69,8 @@ struct rk_i2s_tdm_dev { bool has_playback; bool has_capture; struct snd_soc_dai_driver *dai; + unsigned int mclk_rx_freq; + unsigned int mclk_tx_freq; }; static int to_ch_num(unsigned int val) @@ -514,33 +515,6 @@ static void rockchip_i2s_tdm_xfer_resume(struct snd_pcm_substream *substream, I2S_XFER_RXS_START); } -static int rockchip_i2s_ch_to_io(unsigned int ch, bool substream_capture) -{ - if (substream_capture) { - switch (ch) { - case I2S_CHN_4: - return I2S_IO_6CH_OUT_4CH_IN; - case I2S_CHN_6: - return I2S_IO_4CH_OUT_6CH_IN; - case I2S_CHN_8: - return I2S_IO_2CH_OUT_8CH_IN; - default: - return I2S_IO_8CH_OUT_2CH_IN; - } - } else { - switch (ch) { - case I2S_CHN_4: - return I2S_IO_4CH_OUT_6CH_IN; - case I2S_CHN_6: - return I2S_IO_6CH_OUT_4CH_IN; - case I2S_CHN_8: - return I2S_IO_8CH_OUT_2CH_IN; - default: - return I2S_IO_2CH_OUT_8CH_IN; - } - } -} - static int rockchip_i2s_io_multiplex(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { @@ -577,7 +551,6 @@ static int rockchip_i2s_io_multiplex(struct snd_pcm_substream *substream, return -EINVAL; } - rockchip_i2s_ch_to_io(val, true); } else { struct snd_pcm_str *capture_str = &substream->pcm->streams[SNDRV_PCM_STREAM_CAPTURE]; @@ -645,6 +618,27 @@ static int rockchip_i2s_trcm_mode(struct snd_pcm_substream *substream, return 0; } +static int rockchip_i2s_tdm_set_sysclk(struct snd_soc_dai *cpu_dai, int stream, + unsigned int freq, int dir) +{ + struct rk_i2s_tdm_dev *i2s_tdm = to_info(cpu_dai); + + if (i2s_tdm->clk_trcm) { + i2s_tdm->mclk_tx_freq = freq; + i2s_tdm->mclk_rx_freq = freq; + } else { + if (stream == SNDRV_PCM_STREAM_PLAYBACK) + i2s_tdm->mclk_tx_freq = freq; + else + i2s_tdm->mclk_rx_freq = freq; + } + + dev_dbg(i2s_tdm->dev, "The target mclk_%s freq is: %d\n", + stream ? "rx" : "tx", freq); + + return 0; +} + static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) @@ -659,15 +653,19 @@ static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream, if (i2s_tdm->clk_trcm == TRCM_TX) { mclk = i2s_tdm->mclk_tx; + mclk_rate = i2s_tdm->mclk_tx_freq; } else if (i2s_tdm->clk_trcm == TRCM_RX) { mclk = i2s_tdm->mclk_rx; + mclk_rate = i2s_tdm->mclk_rx_freq; } else if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { mclk = i2s_tdm->mclk_tx; + mclk_rate = i2s_tdm->mclk_tx_freq; } else { mclk = i2s_tdm->mclk_rx; + mclk_rate = i2s_tdm->mclk_rx_freq; } - err = clk_set_rate(mclk, DEFAULT_MCLK_FS * params_rate(params)); + err = clk_set_rate(mclk, mclk_rate); if (err) return err; @@ -827,6 +825,7 @@ static const struct snd_soc_dai_ops rockchip_i2s_tdm_dai_ops = { .hw_params = rockchip_i2s_tdm_hw_params, .set_bclk_ratio = rockchip_i2s_tdm_set_bclk_ratio, .set_fmt = rockchip_i2s_tdm_set_fmt, + .set_sysclk = rockchip_i2s_tdm_set_sysclk, .set_tdm_slot = rockchip_dai_tdm_slot, .trigger = rockchip_i2s_tdm_trigger, }; diff --git a/sound/soc/samsung/Kconfig b/sound/soc/samsung/Kconfig index 4b1ea7b2c796..60b4b7b75215 100644 --- a/sound/soc/samsung/Kconfig +++ b/sound/soc/samsung/Kconfig @@ -127,8 +127,9 @@ config SND_SOC_SAMSUNG_TM2_WM5110 config SND_SOC_SAMSUNG_ARIES_WM8994 tristate "SoC I2S Audio support for WM8994 on Aries" - depends on SND_SOC_SAMSUNG && MFD_WM8994 && IIO && EXTCON + depends on SND_SOC_SAMSUNG && I2C && IIO && EXTCON select SND_SOC_BT_SCO + select MFD_WM8994 select SND_SOC_WM8994 select SND_SAMSUNG_I2S help @@ -140,8 +141,9 @@ config SND_SOC_SAMSUNG_ARIES_WM8994 config SND_SOC_SAMSUNG_MIDAS_WM1811 tristate "SoC I2S Audio support for Midas boards" - depends on SND_SOC_SAMSUNG && IIO + depends on SND_SOC_SAMSUNG && I2C && IIO select SND_SAMSUNG_I2S + select MFD_WM8994 select SND_SOC_WM8994 help Say Y if you want to add support for SoC audio on the Midas boards. diff --git a/sound/soc/sdca/Makefile b/sound/soc/sdca/Makefile index c296bd5a0a7c..5d1ddbbfbf62 100644 --- a/sound/soc/sdca/Makefile +++ b/sound/soc/sdca/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -snd-soc-sdca-objs := sdca_functions.o sdca_device.o +snd-soc-sdca-y := sdca_functions.o sdca_device.o obj-$(CONFIG_SND_SOC_SDCA) += snd-soc-sdca.o diff --git a/sound/soc/sdca/sdca_device.c b/sound/soc/sdca/sdca_device.c index 80d663777eb5..b6399b773986 100644 --- a/sound/soc/sdca/sdca_device.c +++ b/sound/soc/sdca/sdca_device.c @@ -7,6 +7,8 @@ */ #include <linux/acpi.h> +#include <linux/module.h> +#include <linux/property.h> #include <linux/soundwire/sdw.h> #include <sound/sdca.h> #include <sound/sdca_function.h> diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index 652865329968..38071bc838b9 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -6,88 +6,77 @@ * https://www.mipi.org/mipi-sdca-v1-0-download */ +#define dev_fmt(fmt) "%s: " fmt, __func__ + #include <linux/acpi.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/property.h> #include <linux/soundwire/sdw.h> +#include <linux/types.h> #include <sound/sdca.h> #include <sound/sdca_function.h> -static int patch_sdca_function_type(struct device *dev, - u32 interface_revision, - u32 *function_type, - const char **function_name) +static int patch_sdca_function_type(u32 interface_revision, u32 *function_type) { - unsigned long function_type_patch = 0; - /* * Unfortunately early SDCA specifications used different indices for Functions, * for backwards compatibility we have to reorder the values found */ - if (interface_revision >= 0x0801) - goto skip_early_draft_order; - - switch (*function_type) { - case 1: - function_type_patch = SDCA_FUNCTION_TYPE_SMART_AMP; - break; - case 2: - function_type_patch = SDCA_FUNCTION_TYPE_SMART_MIC; - break; - case 3: - function_type_patch = SDCA_FUNCTION_TYPE_SPEAKER_MIC; - break; - case 4: - function_type_patch = SDCA_FUNCTION_TYPE_UAJ; - break; - case 5: - function_type_patch = SDCA_FUNCTION_TYPE_RJ; - break; - case 6: - function_type_patch = SDCA_FUNCTION_TYPE_HID; - break; - default: - dev_warn(dev, "%s: SDCA version %#x unsupported function type %d, skipped\n", - __func__, interface_revision, *function_type); - return -EINVAL; + if (interface_revision < 0x0801) { + switch (*function_type) { + case 1: + *function_type = SDCA_FUNCTION_TYPE_SMART_AMP; + break; + case 2: + *function_type = SDCA_FUNCTION_TYPE_SMART_MIC; + break; + case 3: + *function_type = SDCA_FUNCTION_TYPE_SPEAKER_MIC; + break; + case 4: + *function_type = SDCA_FUNCTION_TYPE_UAJ; + break; + case 5: + *function_type = SDCA_FUNCTION_TYPE_RJ; + break; + case 6: + *function_type = SDCA_FUNCTION_TYPE_HID; + break; + default: + return -EINVAL; + } } -skip_early_draft_order: - if (function_type_patch) - *function_type = function_type_patch; - - /* now double-check the values */ - switch (*function_type) { - case SDCA_FUNCTION_TYPE_SMART_AMP: - *function_name = SDCA_FUNCTION_TYPE_SMART_AMP_NAME; - break; - case SDCA_FUNCTION_TYPE_SMART_MIC: - *function_name = SDCA_FUNCTION_TYPE_SMART_MIC_NAME; - break; - case SDCA_FUNCTION_TYPE_UAJ: - *function_name = SDCA_FUNCTION_TYPE_UAJ_NAME; - break; - case SDCA_FUNCTION_TYPE_HID: - *function_name = SDCA_FUNCTION_TYPE_HID_NAME; - break; - case SDCA_FUNCTION_TYPE_SIMPLE_AMP: - case SDCA_FUNCTION_TYPE_SIMPLE_MIC: - case SDCA_FUNCTION_TYPE_SPEAKER_MIC: - case SDCA_FUNCTION_TYPE_RJ: - case SDCA_FUNCTION_TYPE_IMP_DEF: - dev_warn(dev, "%s: found unsupported SDCA function type %d, skipped\n", - __func__, *function_type); - return -EINVAL; - default: - dev_err(dev, "%s: found invalid SDCA function type %d, skipped\n", - __func__, *function_type); - return -EINVAL; - } - - dev_info(dev, "%s: found SDCA function %s (type %d)\n", - __func__, *function_name, *function_type); - return 0; } +static const char *get_sdca_function_name(u32 function_type) +{ + switch (function_type) { + case SDCA_FUNCTION_TYPE_SMART_AMP: + return SDCA_FUNCTION_TYPE_SMART_AMP_NAME; + case SDCA_FUNCTION_TYPE_SMART_MIC: + return SDCA_FUNCTION_TYPE_SMART_MIC_NAME; + case SDCA_FUNCTION_TYPE_UAJ: + return SDCA_FUNCTION_TYPE_UAJ_NAME; + case SDCA_FUNCTION_TYPE_HID: + return SDCA_FUNCTION_TYPE_HID_NAME; + case SDCA_FUNCTION_TYPE_SIMPLE_AMP: + return SDCA_FUNCTION_TYPE_SIMPLE_AMP_NAME; + case SDCA_FUNCTION_TYPE_SIMPLE_MIC: + return SDCA_FUNCTION_TYPE_SIMPLE_MIC_NAME; + case SDCA_FUNCTION_TYPE_SPEAKER_MIC: + return SDCA_FUNCTION_TYPE_SPEAKER_MIC_NAME; + case SDCA_FUNCTION_TYPE_RJ: + return SDCA_FUNCTION_TYPE_RJ_NAME; + case SDCA_FUNCTION_TYPE_IMP_DEF: + return SDCA_FUNCTION_TYPE_IMP_DEF_NAME; + default: + return NULL; + } +} + static int find_sdca_function(struct acpi_device *adev, void *data) { struct fwnode_handle *function_node = acpi_fwnode_handle(adev); @@ -101,21 +90,16 @@ static int find_sdca_function(struct acpi_device *adev, void *data) int ret; if (sdca_data->num_functions >= SDCA_MAX_FUNCTION_COUNT) { - dev_err(dev, "%s: maximum number of functions exceeded\n", __func__); + dev_err(dev, "maximum number of functions exceeded\n"); return -EINVAL; } - /* - * The number of functions cannot exceed 8, we could use - * acpi_get_local_address() but the value is stored as u64 so - * we might as well avoid casts and intermediate levels - */ ret = acpi_get_local_u64_address(adev->handle, &addr); if (ret < 0) return ret; - if (!addr) { - dev_err(dev, "%s: no addr\n", __func__); + if (!addr || addr > 0x7) { + dev_err(dev, "invalid addr: 0x%llx\n", addr); return -ENODEV; } @@ -140,15 +124,25 @@ static int find_sdca_function(struct acpi_device *adev, void *data) fwnode_handle_put(control5); if (ret < 0) { - dev_err(dev, "%s: the function type can only be determined from ACPI information\n", - __func__); + dev_err(dev, "function type only supported as DisCo constant\n"); return ret; } - ret = patch_sdca_function_type(dev, sdca_data->interface_revision, - &function_type, &function_name); - if (ret < 0) + ret = patch_sdca_function_type(sdca_data->interface_revision, &function_type); + if (ret < 0) { + dev_err(dev, "SDCA version %#x invalid function type %d\n", + sdca_data->interface_revision, function_type); return ret; + } + + function_name = get_sdca_function_name(function_type); + if (!function_name) { + dev_err(dev, "invalid SDCA function type %d\n", function_type); + return -EINVAL; + } + + dev_info(dev, "SDCA function %s (type %d) at 0x%llx\n", + function_name, function_type, addr); /* store results */ func_index = sdca_data->num_functions; diff --git a/sound/soc/sdw_utils/soc_sdw_cs_amp.c b/sound/soc/sdw_utils/soc_sdw_cs_amp.c index a0bb626c5cb8..4b6181cf2971 100644 --- a/sound/soc/sdw_utils/soc_sdw_cs_amp.c +++ b/sound/soc/sdw_utils/soc_sdw_cs_amp.c @@ -15,6 +15,7 @@ #include <sound/soc_sdw_utils.h> #define CODEC_NAME_SIZE 8 +#define CS_AMP_CHANNELS_PER_AMP 4 int asoc_sdw_cs_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai *dai) { @@ -48,6 +49,51 @@ int asoc_sdw_cs_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai } EXPORT_SYMBOL_NS(asoc_sdw_cs_spk_rtd_init, "SND_SOC_SDW_UTILS"); +int asoc_sdw_cs_spk_feedback_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai *dai) +{ + const struct snd_soc_dai_link *dai_link = rtd->dai_link; + const struct snd_soc_dai_link_ch_map *ch_map; + const struct snd_soc_dai_link_component *codec_dlc; + struct snd_soc_dai *codec_dai; + u8 ch_slot[8] = {}; + unsigned int amps_per_bus, ch_per_amp, mask; + int i, ret; + + WARN_ON(dai_link->num_cpus > ARRAY_SIZE(ch_slot)); + + /* + * CS35L56 has 4 TX channels. When the capture is aggregated the + * same bus slots will be allocated to all the amps on a bus. Only + * one amp on that bus can be transmitting in each slot so divide + * the available 4 slots between all the amps on a bus. + */ + amps_per_bus = dai_link->num_codecs / dai_link->num_cpus; + if ((amps_per_bus == 0) || (amps_per_bus > CS_AMP_CHANNELS_PER_AMP)) { + dev_err(rtd->card->dev, "Illegal num_codecs:%u / num_cpus:%u\n", + dai_link->num_codecs, dai_link->num_cpus); + return -EINVAL; + } + + ch_per_amp = CS_AMP_CHANNELS_PER_AMP / amps_per_bus; + + for_each_rtd_ch_maps(rtd, i, ch_map) { + codec_dlc = snd_soc_link_to_codec(rtd->dai_link, i); + codec_dai = snd_soc_find_dai(codec_dlc); + mask = GENMASK(ch_per_amp - 1, 0) << ch_slot[ch_map->cpu]; + + ret = snd_soc_dai_set_tdm_slot(codec_dai, 0, mask, 4, 32); + if (ret < 0) { + dev_err(rtd->card->dev, "Failed to set TDM slot:%d\n", ret); + return ret; + } + + ch_slot[ch_map->cpu] += ch_per_amp; + } + + return 0; +} +EXPORT_SYMBOL_NS(asoc_sdw_cs_spk_feedback_rtd_init, "SND_SOC_SDW_UTILS"); + int asoc_sdw_cs_amp_init(struct snd_soc_card *card, struct snd_soc_dai_link *dai_links, struct asoc_sdw_codec_info *info, diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index 937fa3ce59df..6ee7d30b8ece 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -488,10 +488,10 @@ struct asoc_sdw_codec_info codec_info_list[] = { .part_id = 0x3556, .dais = { { - .direction = {true, true}, + .direction = {true, false}, .dai_name = "cs35l56-sdw1", .dai_type = SOC_SDW_DAI_TYPE_AMP, - .dailink = {SOC_SDW_AMP_OUT_DAI_ID, SOC_SDW_AMP_IN_DAI_ID}, + .dailink = {SOC_SDW_AMP_OUT_DAI_ID, SOC_SDW_UNUSED_DAI_ID}, .init = asoc_sdw_cs_amp_init, .rtd_init = asoc_sdw_cs_spk_rtd_init, .controls = generic_spk_controls, @@ -499,8 +499,15 @@ struct asoc_sdw_codec_info codec_info_list[] = { .widgets = generic_spk_widgets, .num_widgets = ARRAY_SIZE(generic_spk_widgets), }, + { + .direction = {false, true}, + .dai_name = "cs35l56-sdw1c", + .dai_type = SOC_SDW_DAI_TYPE_AMP, + .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_AMP_IN_DAI_ID}, + .rtd_init = asoc_sdw_cs_spk_feedback_rtd_init, + }, }, - .dai_num = 1, + .dai_num = 2, }, { .part_id = 0x4242, diff --git a/sound/soc/soc-card.c b/sound/soc/soc-card.c index 8e9546fe7428..e6eb71b3010a 100644 --- a/sound/soc/soc-card.c +++ b/sound/soc/soc-card.c @@ -219,7 +219,7 @@ int snd_soc_card_set_bias_level(struct snd_soc_card *card, { int ret = 0; - if (card && card->set_bias_level) + if (card->set_bias_level) ret = card->set_bias_level(card, dapm, level); return soc_card_ret(card, ret); @@ -231,7 +231,7 @@ int snd_soc_card_set_bias_level_post(struct snd_soc_card *card, { int ret = 0; - if (card && card->set_bias_level_post) + if (card->set_bias_level_post) ret = card->set_bias_level_post(card, dapm, level); return soc_card_ret(card, ret); diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index a1dace4bb616..3c6d8aef4130 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1449,23 +1449,46 @@ int snd_soc_runtime_set_dai_fmt(struct snd_soc_pcm_runtime *rtd, { struct snd_soc_dai *cpu_dai; struct snd_soc_dai *codec_dai; + unsigned int ext_fmt; unsigned int i; int ret; if (!dai_fmt) return 0; + /* + * dai_fmt has 4 types + * 1. SND_SOC_DAIFMT_FORMAT_MASK + * 2. SND_SOC_DAIFMT_CLOCK + * 3. SND_SOC_DAIFMT_INV + * 4. SND_SOC_DAIFMT_CLOCK_PROVIDER + * + * 4. CLOCK_PROVIDER is set from Codec perspective in dai_fmt. So it will be flipped + * when this function calls set_fmt() for CPU (CBx_CFx -> Bx_Cx). see below. + * This mean, we can't set CPU/Codec both are clock consumer for example. + * New idea handles 4. in each dai->ext_fmt. It can keep compatibility. + * + * Legacy + * dai_fmt includes 1, 2, 3, 4 + * + * New idea + * dai_fmt includes 1, 2, 3 + * ext_fmt includes 4 + */ for_each_rtd_codec_dais(rtd, i, codec_dai) { - ret = snd_soc_dai_set_fmt(codec_dai, dai_fmt); + ext_fmt = rtd->dai_link->codecs[i].ext_fmt; + ret = snd_soc_dai_set_fmt(codec_dai, dai_fmt | ext_fmt); if (ret != 0 && ret != -ENOTSUPP) return ret; } /* Flip the polarity for the "CPU" end of link */ + /* Will effect only for 4. SND_SOC_DAIFMT_CLOCK_PROVIDER */ dai_fmt = snd_soc_daifmt_clock_provider_flipped(dai_fmt); for_each_rtd_cpu_dais(rtd, i, cpu_dai) { - ret = snd_soc_dai_set_fmt(cpu_dai, dai_fmt); + ext_fmt = rtd->dai_link->cpus[i].ext_fmt; + ret = snd_soc_dai_set_fmt(cpu_dai, dai_fmt | ext_fmt); if (ret != 0 && ret != -ENOTSUPP) return ret; } @@ -1644,18 +1667,8 @@ static int soc_probe_component(struct snd_soc_card *card, ret = snd_soc_dapm_add_routes(dapm, component->driver->dapm_routes, component->driver->num_dapm_routes); - if (ret < 0) { - if (card->disable_route_checks) { - dev_info(card->dev, - "%s: disable_route_checks set, ignoring errors on add_routes\n", - __func__); - } else { - dev_err(card->dev, - "%s: snd_soc_dapm_add_routes failed: %d\n", - __func__, ret); - goto err_probe; - } - } + if (ret < 0) + goto err_probe; /* see for_each_card_components */ list_add(&component->card_list, &card->component_dev_list); @@ -2234,18 +2247,8 @@ static int snd_soc_bind_card(struct snd_soc_card *card) ret = snd_soc_dapm_add_routes(&card->dapm, card->dapm_routes, card->num_dapm_routes); - if (ret < 0) { - if (card->disable_route_checks) { - dev_info(card->dev, - "%s: disable_route_checks set, ignoring errors on add_routes\n", - __func__); - } else { - dev_err(card->dev, - "%s: snd_soc_dapm_add_routes failed: %d\n", - __func__, ret); - goto probe_end; - } - } + if (ret < 0) + goto probe_end; ret = snd_soc_dapm_add_routes(&card->dapm, card->of_dapm_routes, card->num_of_dapm_routes); @@ -3389,6 +3392,9 @@ unsigned int snd_soc_daifmt_parse_clock_provider_raw(struct device_node *np, char prop[128]; unsigned int bit, frame; + if (!np) + return 0; + if (!prefix) prefix = ""; diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c index 34ba1a93a4c9..ca0308f6d41c 100644 --- a/sound/soc/soc-dai.c +++ b/sound/soc/soc-dai.c @@ -360,6 +360,22 @@ int snd_soc_dai_set_tristate(struct snd_soc_dai *dai, int tristate) } EXPORT_SYMBOL_GPL(snd_soc_dai_set_tristate); +int snd_soc_dai_prepare(struct snd_soc_dai *dai, + struct snd_pcm_substream *substream) +{ + int ret = 0; + + if (!snd_soc_dai_stream_valid(dai, substream->stream)) + return 0; + + if (dai->driver->ops && + dai->driver->ops->prepare) + ret = dai->driver->ops->prepare(substream, dai); + + return soc_dai_ret(dai, ret); +} +EXPORT_SYMBOL_GPL(snd_soc_dai_prepare); + /** * snd_soc_dai_digital_mute - configure DAI system or master clock. * @dai: DAI @@ -577,14 +593,9 @@ int snd_soc_pcm_dai_prepare(struct snd_pcm_substream *substream) int i, ret; for_each_rtd_dais(rtd, i, dai) { - if (!snd_soc_dai_stream_valid(dai, substream->stream)) - continue; - if (dai->driver->ops && - dai->driver->ops->prepare) { - ret = dai->driver->ops->prepare(substream, dai); - if (ret < 0) - return soc_dai_ret(dai, ret); - } + ret = snd_soc_dai_prepare(dai, substream); + if (ret < 0) + return ret; } return 0; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 99521c784a9b..b5116b700d73 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -730,7 +730,7 @@ static int snd_soc_dapm_set_bias_level(struct snd_soc_dapm_context *dapm, if (ret != 0) goto out; - if (!card || dapm != &card->dapm) + if (dapm != &card->dapm) ret = snd_soc_dapm_force_bias_level(dapm, level); if (ret != 0) @@ -4013,6 +4013,18 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, break; case SND_SOC_DAPM_POST_PMU: + snd_soc_dapm_widget_for_each_source_path(w, path) { + source = path->source->priv; + + snd_soc_dai_prepare(source, substream); + } + + snd_soc_dapm_widget_for_each_sink_path(w, path) { + sink = path->sink->priv; + + snd_soc_dai_prepare(sink, substream); + } + snd_soc_dapm_widget_for_each_sink_path(w, path) { sink = path->sink->priv; diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 1150455619aa..88b3ad5a2552 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -38,7 +38,6 @@ static inline int _soc_pcm_ret(struct snd_soc_pcm_runtime *rtd, switch (ret) { case -EPROBE_DEFER: case -ENOTSUPP: - case -EINVAL: break; default: dev_err(rtd->dev, @@ -986,7 +985,13 @@ static int __soc_pcm_prepare(struct snd_soc_pcm_runtime *rtd, } out: - return soc_pcm_ret(rtd, ret); + /* + * Don't use soc_pcm_ret() on .prepare callback to lower error log severity + * + * We don't want to log an error since we do not want to give userspace a way to do a + * denial-of-service attack on the syslog / diskspace. + */ + return ret; } /* PCM prepare ops for non-DPCM streams */ @@ -998,6 +1003,13 @@ static int soc_pcm_prepare(struct snd_pcm_substream *substream) snd_soc_dpcm_mutex_lock(rtd); ret = __soc_pcm_prepare(rtd, substream); snd_soc_dpcm_mutex_unlock(rtd); + + /* + * Don't use soc_pcm_ret() on .prepare callback to lower error log severity + * + * We don't want to log an error since we do not want to give userspace a way to do a + * denial-of-service attack on the syslog / diskspace. + */ return ret; } @@ -2539,7 +2551,13 @@ int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream) be->dpcm[stream].state = SND_SOC_DPCM_STATE_PREPARE; } - return soc_pcm_ret(fe, ret); + /* + * Don't use soc_pcm_ret() on .prepare callback to lower error log severity + * + * We don't want to log an error since we do not want to give userspace a way to do a + * denial-of-service attack on the syslog / diskspace. + */ + return ret; } static int dpcm_fe_dai_prepare(struct snd_pcm_substream *substream) @@ -2579,7 +2597,13 @@ out: dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); snd_soc_dpcm_mutex_unlock(fe); - return soc_pcm_ret(fe, ret); + /* + * Don't use soc_pcm_ret() on .prepare callback to lower error log severity + * + * We don't want to log an error since we do not want to give userspace a way to do a + * denial-of-service attack on the syslog / diskspace. + */ + return ret; } static int dpcm_run_update_shutdown(struct snd_soc_pcm_runtime *fe, int stream) diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 43003d2d3666..9f4da061eff9 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1101,14 +1101,8 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg, } ret = snd_soc_dapm_add_routes(dapm, route, 1); - if (ret) { - if (!dapm->card->disable_route_checks) { - dev_err(tplg->dev, "ASoC: dapm_add_routes failed: %d\n", ret); - break; - } - dev_info(tplg->dev, - "ASoC: disable_route_checks set, ignoring dapm_add_routes errors\n"); - } + if (ret) + break; } return ret; diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c index 0b85b29d1067..1e7bf00d7c46 100644 --- a/sound/soc/sof/imx/imx8.c +++ b/sound/soc/sof/imx/imx8.c @@ -175,8 +175,7 @@ static int imx8_run(struct snd_sof_dev *sdev) static int imx8_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct device_node *np = pdev->dev.of_node; struct device_node *res_node; struct resource *mmio; @@ -606,11 +605,32 @@ static struct snd_sof_of_mach sof_imx8_machs[] = { .sof_tplg_filename = "sof-imx8-wm8960.tplg", .drv_name = "asoc-audio-graph-card2", }, + { + .compatible = "fsl,imx8qxp-mek-wcpu", + .sof_tplg_filename = "sof-imx8-wm8962.tplg", + .drv_name = "asoc-audio-graph-card2", + }, { .compatible = "fsl,imx8qm-mek", .sof_tplg_filename = "sof-imx8-wm8960.tplg", .drv_name = "asoc-audio-graph-card2", }, + { + .compatible = "fsl,imx8qm-mek-revd", + .sof_tplg_filename = "sof-imx8-wm8962.tplg", + .drv_name = "asoc-audio-graph-card2", + }, + { + .compatible = "fsl,imx8qxp-mek-bb", + .sof_tplg_filename = "sof-imx8-cs42888.tplg", + .drv_name = "asoc-audio-graph-card2", + }, + { + .compatible = "fsl,imx8qm-mek-bb", + .sof_tplg_filename = "sof-imx8-cs42888.tplg", + .drv_name = "asoc-audio-graph-card2", + }, + {} }; diff --git a/sound/soc/sof/imx/imx8m.c b/sound/soc/sof/imx/imx8m.c index ff42743efa79..3cabdebac558 100644 --- a/sound/soc/sof/imx/imx8m.c +++ b/sound/soc/sof/imx/imx8m.c @@ -144,8 +144,7 @@ static int imx8m_reset(struct snd_sof_dev *sdev) static int imx8m_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct device_node *np = pdev->dev.of_node; struct device_node *res_node; struct resource *mmio; @@ -294,6 +293,17 @@ static struct snd_soc_dai_driver imx8m_dai[] = { .channels_max = 32, }, }, +{ + .name = "sai2", + .playback = { + .channels_min = 1, + .channels_max = 32, + }, + .capture = { + .channels_min = 1, + .channels_max = 32, + }, +}, { .name = "sai3", .playback = { @@ -305,6 +315,39 @@ static struct snd_soc_dai_driver imx8m_dai[] = { .channels_max = 32, }, }, +{ + .name = "sai5", + .playback = { + .channels_min = 1, + .channels_max = 32, + }, + .capture = { + .channels_min = 1, + .channels_max = 32, + }, +}, +{ + .name = "sai6", + .playback = { + .channels_min = 1, + .channels_max = 32, + }, + .capture = { + .channels_min = 1, + .channels_max = 32, + }, +}, +{ + .name = "sai7", + .playback = { + .channels_min = 1, + .channels_max = 32, + }, + .capture = { + .channels_min = 1, + .channels_max = 32, + }, +}, { .name = "micfil", .capture = { @@ -471,6 +514,11 @@ static const struct snd_sof_dsp_ops sof_imx8m_ops = { }; static struct snd_sof_of_mach sof_imx8mp_machs[] = { + { + .compatible = "fsl,imx8mp-evk-revb4", + .sof_tplg_filename = "sof-imx8mp-wm8962.tplg", + .drv_name = "asoc-audio-graph-card2", + }, { .compatible = "fsl,imx8mp-evk", .sof_tplg_filename = "sof-imx8mp-wm8960.tplg", diff --git a/sound/soc/sof/imx/imx8ulp.c b/sound/soc/sof/imx/imx8ulp.c index 6965791ab6ef..0704da27e69d 100644 --- a/sound/soc/sof/imx/imx8ulp.c +++ b/sound/soc/sof/imx/imx8ulp.c @@ -155,8 +155,7 @@ static int imx8ulp_reset(struct snd_sof_dev *sdev) static int imx8ulp_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct device_node *np = pdev->dev.of_node; struct device_node *res_node; struct resource *mmio; diff --git a/sound/soc/sof/intel/atom.c b/sound/soc/sof/intel/atom.c index 30e981c558c6..0d364bcdcfa9 100644 --- a/sound/soc/sof/intel/atom.c +++ b/sound/soc/sof/intel/atom.c @@ -78,20 +78,20 @@ void atom_dump(struct snd_sof_dev *sdev, u32 flags) imrd = snd_sof_dsp_read64(sdev, DSP_BAR, SHIM_IMRD); dev_err(sdev->dev, "error: ipc host -> DSP: pending %s complete %s raw 0x%llx\n", - (panic & SHIM_IPCX_BUSY) ? "yes" : "no", - (panic & SHIM_IPCX_DONE) ? "yes" : "no", panic); + str_yes_no(panic & SHIM_IPCX_BUSY), + str_yes_no(panic & SHIM_IPCX_DONE), panic); dev_err(sdev->dev, "error: mask host: pending %s complete %s raw 0x%llx\n", - (imrx & SHIM_IMRX_BUSY) ? "yes" : "no", - (imrx & SHIM_IMRX_DONE) ? "yes" : "no", imrx); + str_yes_no(imrx & SHIM_IMRX_BUSY), + str_yes_no(imrx & SHIM_IMRX_DONE), imrx); dev_err(sdev->dev, "error: ipc DSP -> host: pending %s complete %s raw 0x%llx\n", - (status & SHIM_IPCD_BUSY) ? "yes" : "no", - (status & SHIM_IPCD_DONE) ? "yes" : "no", status); + str_yes_no(status & SHIM_IPCD_BUSY), + str_yes_no(status & SHIM_IPCD_DONE), status); dev_err(sdev->dev, "error: mask DSP: pending %s complete %s raw 0x%llx\n", - (imrd & SHIM_IMRD_BUSY) ? "yes" : "no", - (imrd & SHIM_IMRD_DONE) ? "yes" : "no", imrd); + str_yes_no(imrd & SHIM_IMRD_BUSY), + str_yes_no(imrd & SHIM_IMRD_DONE), imrd); } EXPORT_SYMBOL_NS(atom_dump, "SND_SOC_SOF_INTEL_ATOM_HIFI_EP"); diff --git a/sound/soc/sof/intel/bdw.c b/sound/soc/sof/intel/bdw.c index c4d92f3508b6..e1f0e38c2407 100644 --- a/sound/soc/sof/intel/bdw.c +++ b/sound/soc/sof/intel/bdw.c @@ -266,20 +266,20 @@ static void bdw_dump(struct snd_sof_dev *sdev, u32 flags) imrd = snd_sof_dsp_read(sdev, BDW_DSP_BAR, SHIM_IMRD); dev_err(sdev->dev, "error: ipc host -> DSP: pending %s complete %s raw 0x%8.8x\n", - (panic & SHIM_IPCX_BUSY) ? "yes" : "no", - (panic & SHIM_IPCX_DONE) ? "yes" : "no", panic); + str_yes_no(panic & SHIM_IPCX_BUSY), + str_yes_no(panic & SHIM_IPCX_DONE), panic); dev_err(sdev->dev, "error: mask host: pending %s complete %s raw 0x%8.8x\n", - (imrx & SHIM_IMRX_BUSY) ? "yes" : "no", - (imrx & SHIM_IMRX_DONE) ? "yes" : "no", imrx); + str_yes_no(imrx & SHIM_IMRX_BUSY), + str_yes_no(imrx & SHIM_IMRX_DONE), imrx); dev_err(sdev->dev, "error: ipc DSP -> host: pending %s complete %s raw 0x%8.8x\n", - (status & SHIM_IPCD_BUSY) ? "yes" : "no", - (status & SHIM_IPCD_DONE) ? "yes" : "no", status); + str_yes_no(status & SHIM_IPCD_BUSY), + str_yes_no(status & SHIM_IPCD_DONE), status); dev_err(sdev->dev, "error: mask DSP: pending %s complete %s raw 0x%8.8x\n", - (imrd & SHIM_IMRD_BUSY) ? "yes" : "no", - (imrd & SHIM_IMRD_DONE) ? "yes" : "no", imrd); + str_yes_no(imrd & SHIM_IMRD_BUSY), + str_yes_no(imrd & SHIM_IMRD_DONE), imrd); } /* @@ -410,8 +410,7 @@ static int bdw_probe(struct snd_sof_dev *sdev) { struct snd_sof_pdata *pdata = sdev->pdata; const struct sof_dev_desc *desc = pdata->desc; - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); const struct sof_intel_dsp_desc *chip; struct resource *mmio; u32 base, size; diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c index 536d4c89d2f0..cae7dc0036c6 100644 --- a/sound/soc/sof/intel/byt.c +++ b/sound/soc/sof/intel/byt.c @@ -109,8 +109,7 @@ static int byt_acpi_probe(struct snd_sof_dev *sdev) { struct snd_sof_pdata *pdata = sdev->pdata; const struct sof_dev_desc *desc = pdata->desc; - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); const struct sof_intel_dsp_desc *chip; struct resource *mmio; u32 base, size; diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index c13f89b7065e..da12aabc1bb8 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -103,8 +103,10 @@ hda_dai_get_ops(struct snd_pcm_substream *substream, struct snd_soc_dai *cpu_dai return sdai->platform_private; } -int hda_link_dma_cleanup(struct snd_pcm_substream *substream, struct hdac_ext_stream *hext_stream, - struct snd_soc_dai *cpu_dai) +static int +hda_link_dma_cleanup(struct snd_pcm_substream *substream, + struct hdac_ext_stream *hext_stream, + struct snd_soc_dai *cpu_dai, bool release) { const struct hda_dai_widget_dma_ops *ops = hda_dai_get_ops(substream, cpu_dai); struct sof_intel_hda_stream *hda_stream; @@ -128,6 +130,17 @@ int hda_link_dma_cleanup(struct snd_pcm_substream *substream, struct hdac_ext_st snd_hdac_ext_bus_link_clear_stream_id(hlink, stream_tag); } + if (!release) { + /* + * Force stream reconfiguration without releasing the channel on + * subsequent stream restart (without free), including LinkDMA + * reset. + * The stream is released via hda_dai_hw_free() + */ + hext_stream->link_prepared = 0; + return 0; + } + if (ops->release_hext_stream) ops->release_hext_stream(sdev, cpu_dai, substream); @@ -211,7 +224,7 @@ static int __maybe_unused hda_dai_hw_free(struct snd_pcm_substream *substream, if (!hext_stream) return 0; - return hda_link_dma_cleanup(substream, hext_stream, cpu_dai); + return hda_link_dma_cleanup(substream, hext_stream, cpu_dai, true); } static int __maybe_unused hda_dai_hw_params_data(struct snd_pcm_substream *substream, @@ -304,7 +317,8 @@ static int __maybe_unused hda_dai_trigger(struct snd_pcm_substream *substream, i switch (cmd) { case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: - ret = hda_link_dma_cleanup(substream, hext_stream, dai); + ret = hda_link_dma_cleanup(substream, hext_stream, dai, + cmd == SNDRV_PCM_TRIGGER_STOP ? false : true); if (ret < 0) { dev_err(sdev->dev, "%s: failed to clean up link DMA\n", __func__); return ret; @@ -489,6 +503,12 @@ int sdw_hda_dai_hw_params(struct snd_pcm_substream *substream, int ret; int i; + if (!w) { + dev_err(cpu_dai->dev, "%s widget not found, check amp link num in the topology\n", + cpu_dai->name); + return -EINVAL; + } + ops = hda_dai_get_ops(substream, cpu_dai); if (!ops) { dev_err(cpu_dai->dev, "DAI widget ops not set\n"); @@ -568,6 +588,12 @@ int sdw_hda_dai_hw_params(struct snd_pcm_substream *substream, */ for_each_rtd_cpu_dais(rtd, i, dai) { w = snd_soc_dai_get_widget(dai, substream->stream); + if (!w) { + dev_err(cpu_dai->dev, + "%s widget not found, check amp link num in the topology\n", + dai->name); + return -EINVAL; + } ipc4_copier = widget_to_copier(w); memcpy(&ipc4_copier->dma_config_tlv[cpu_dai_id], dma_config_tlv, sizeof(*dma_config_tlv)); @@ -660,8 +686,7 @@ static int hda_dai_suspend(struct hdac_bus *bus) } ret = hda_link_dma_cleanup(hext_stream->link_substream, - hext_stream, - cpu_dai); + hext_stream, cpu_dai, true); if (ret < 0) return ret; } diff --git a/sound/soc/sof/intel/hda-pcm.c b/sound/soc/sof/intel/hda-pcm.c index 5b5e484f9acf..1dd8d2092c3b 100644 --- a/sound/soc/sof/intel/hda-pcm.c +++ b/sound/soc/sof/intel/hda-pcm.c @@ -37,6 +37,11 @@ static bool hda_disable_rewinds; module_param_named(disable_rewinds, hda_disable_rewinds, bool, 0444); MODULE_PARM_DESC(disable_rewinds, "SOF HDA disable rewinds"); +static int hda_force_pause_support = -1; +module_param_named(force_pause_support, hda_force_pause_support, int, 0444); +MODULE_PARM_DESC(force_pause_support, + "Pause support: -1: Use default, 0: Disable, 1: Enable (default -1)"); + u32 hda_dsp_get_mult_div(struct snd_sof_dev *sdev, int rate) { switch (rate) { @@ -240,6 +245,16 @@ int hda_dsp_pcm_open(struct snd_sof_dev *sdev, if (hda_always_enable_dmi_l1 && direction == SNDRV_PCM_STREAM_CAPTURE) runtime->hw.info &= ~SNDRV_PCM_INFO_PAUSE; + /* + * Do not advertise the PAUSE support if it is forced to be disabled via + * module parameter or if the pause_supported is false for the PCM + * device + */ + if (hda_force_pause_support == 0 || + (hda_force_pause_support == -1 && + !spcm->stream[substream->stream].pause_supported)) + runtime->hw.info &= ~SNDRV_PCM_INFO_PAUSE; + if (hda_always_enable_dmi_l1 || direction == SNDRV_PCM_STREAM_PLAYBACK || spcm->stream[substream->stream].d0i3_compatible) diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index f991785f727e..be689f6e10c8 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -63,6 +63,11 @@ static int sdw_params_stream(struct device *dev, struct snd_soc_dapm_widget *w = snd_soc_dai_get_widget(d, params_data->substream->stream); struct snd_sof_dai_config_data data = { 0 }; + if (!w) { + dev_err(dev, "%s widget not found, check amp link num in the topology\n", + d->name); + return -EINVAL; + } data.dai_index = (params_data->link_id << 8) | d->id; data.dai_data = params_data->alh_stream_id; data.dai_node_id = data.dai_data; diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h index 22bd9c3c8216..ee4ccc1a5490 100644 --- a/sound/soc/sof/intel/hda.h +++ b/sound/soc/sof/intel/hda.h @@ -1038,8 +1038,6 @@ const struct hda_dai_widget_dma_ops * hda_select_dai_widget_ops(struct snd_sof_dev *sdev, struct snd_sof_widget *swidget); int hda_dai_config(struct snd_soc_dapm_widget *w, unsigned int flags, struct snd_sof_dai_config_data *data); -int hda_link_dma_cleanup(struct snd_pcm_substream *substream, struct hdac_ext_stream *hext_stream, - struct snd_soc_dai *cpu_dai); static inline struct snd_sof_dev *widget_to_sdev(struct snd_soc_dapm_widget *w) { diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index b55eb977e443..c04c62478827 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -2827,7 +2827,7 @@ static int sof_ipc4_widget_setup(struct snd_sof_dev *sdev, struct snd_sof_widget msg->primary |= SOF_IPC4_MOD_INSTANCE(swidget->instance_id); msg->extension &= ~SOF_IPC4_MOD_EXT_PARAM_SIZE_MASK; - msg->extension |= ipc_size >> 2; + msg->extension |= SOF_IPC4_MOD_EXT_PARAM_SIZE(ipc_size >> 2); msg->extension &= ~SOF_IPC4_MOD_EXT_PPL_ID_MASK; msg->extension |= SOF_IPC4_MOD_EXT_PPL_ID(pipe_widget->instance_id); diff --git a/sound/soc/sof/mediatek/mt8186/mt8186.c b/sound/soc/sof/mediatek/mt8186/mt8186.c index 9955dfa520ae..31437fdd4e92 100644 --- a/sound/soc/sof/mediatek/mt8186/mt8186.c +++ b/sound/soc/sof/mediatek/mt8186/mt8186.c @@ -238,7 +238,7 @@ static int mt8186_run(struct snd_sof_dev *sdev) static int mt8186_dsp_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct adsp_priv *priv; int ret; diff --git a/sound/soc/sof/mediatek/mt8195/mt8195.c b/sound/soc/sof/mediatek/mt8195/mt8195.c index 6032b566c679..371563d7ce79 100644 --- a/sound/soc/sof/mediatek/mt8195/mt8195.c +++ b/sound/soc/sof/mediatek/mt8195/mt8195.c @@ -228,7 +228,7 @@ static int mt8195_run(struct snd_sof_dev *sdev) static int mt8195_dsp_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct adsp_priv *priv; int ret; @@ -341,7 +341,7 @@ static int mt8195_dsp_shutdown(struct snd_sof_dev *sdev) static void mt8195_dsp_remove(struct snd_sof_dev *sdev) { - struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct adsp_priv *priv = sdev->pdata->hw_pdata; platform_device_unregister(priv->ipc_dev); @@ -351,7 +351,7 @@ static void mt8195_dsp_remove(struct snd_sof_dev *sdev) static int mt8195_dsp_suspend(struct snd_sof_dev *sdev, u32 target_state) { - struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); int ret; u32 reset_sw, dbg_pc; diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h index 01b819dd8498..62f3c11a9216 100644 --- a/sound/soc/sof/sof-audio.h +++ b/sound/soc/sof/sof-audio.h @@ -332,6 +332,7 @@ struct snd_sof_pcm_stream { struct work_struct period_elapsed_work; struct snd_soc_dapm_widget_list *list; /* list of connected DAPM widgets */ bool d0i3_compatible; /* DSP can be in D0I3 when this pcm is opened */ + bool pause_supported; /* PCM device supports PAUSE operation */ unsigned int dsp_max_burst_size_in_ms; /* The maximum size of the host DMA burst in ms */ /* * flag to indicate that the DSP pipelines should be kept diff --git a/sound/soc/sof/sof-client-ipc-flood-test.c b/sound/soc/sof/sof-client-ipc-flood-test.c index b35c98896968..11b6f7da2882 100644 --- a/sound/soc/sof/sof-client-ipc-flood-test.c +++ b/sound/soc/sof/sof-client-ipc-flood-test.c @@ -158,7 +158,6 @@ static ssize_t sof_ipc_flood_dfs_write(struct file *file, const char __user *buf unsigned long ipc_duration_ms = 0; bool flood_duration_test = false; unsigned long ipc_count = 0; - struct dentry *dentry; int err; char *string; int ret; @@ -182,14 +181,7 @@ static ssize_t sof_ipc_flood_dfs_write(struct file *file, const char __user *buf * ipc_duration_ms test floods the DSP for the time specified * in the debugfs entry. */ - dentry = file->f_path.dentry; - if (strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_COUNT) && - strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_DURATION)) { - ret = -EINVAL; - goto out; - } - - if (!strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_DURATION)) + if (debugfs_get_aux_num(file)) flood_duration_test = true; /* test completion criterion */ @@ -252,22 +244,15 @@ static ssize_t sof_ipc_flood_dfs_read(struct file *file, char __user *buffer, struct sof_ipc_flood_priv *priv = cdev->data; size_t size_ret; - struct dentry *dentry; + if (*ppos) + return 0; - dentry = file->f_path.dentry; - if (!strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_COUNT) || - !strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_DURATION)) { - if (*ppos) - return 0; + count = min_t(size_t, count, strlen(priv->buf)); + size_ret = copy_to_user(buffer, priv->buf, count); + if (size_ret) + return -EFAULT; - count = min_t(size_t, count, strlen(priv->buf)); - size_ret = copy_to_user(buffer, priv->buf, count); - if (size_ret) - return -EFAULT; - - *ppos += count; - return count; - } + *ppos += count; return count; } @@ -320,12 +305,12 @@ static int sof_ipc_flood_probe(struct auxiliary_device *auxdev, priv->dfs_root = debugfs_create_dir(dev_name(dev), debugfs_root); if (!IS_ERR_OR_NULL(priv->dfs_root)) { /* create read-write ipc_flood_count debugfs entry */ - debugfs_create_file(DEBUGFS_IPC_FLOOD_COUNT, 0644, priv->dfs_root, - cdev, &sof_ipc_flood_fops); + debugfs_create_file_aux_num(DEBUGFS_IPC_FLOOD_COUNT, 0644, + priv->dfs_root, cdev, 0, &sof_ipc_flood_fops); /* create read-write ipc_flood_duration_ms debugfs entry */ - debugfs_create_file(DEBUGFS_IPC_FLOOD_DURATION, 0644, - priv->dfs_root, cdev, &sof_ipc_flood_fops); + debugfs_create_file_aux_num(DEBUGFS_IPC_FLOOD_DURATION, 0644, + priv->dfs_root, cdev, 1, &sof_ipc_flood_fops); if (auxdev->id == 0) { /* diff --git a/sound/soc/sof/sof-priv.h b/sound/soc/sof/sof-priv.h index 843be3b6415d..abbb5ee7e08c 100644 --- a/sound/soc/sof/sof-priv.h +++ b/sound/soc/sof/sof-priv.h @@ -76,14 +76,6 @@ bool sof_debug_check_flag(int mask); #define SOF_IPC_DSP_REPLY 0 #define SOF_IPC_HOST_REPLY 1 -/* convenience constructor for DAI driver streams */ -#define SOF_DAI_STREAM(sname, scmin, scmax, srates, sfmt) \ - {.stream_name = sname, .channels_min = scmin, .channels_max = scmax, \ - .rates = srates, .formats = sfmt} - -#define SOF_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE | \ - SNDRV_PCM_FMTBIT_S32_LE | SNDRV_PCM_FMTBIT_FLOAT) - /* So far the primary core on all DSPs has ID 0 */ #define SOF_DSP_PRIMARY_CORE 0 diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index b3fca5fd87d6..688cc7ac1714 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -407,6 +407,10 @@ static const struct sof_topology_token stream_tokens[] = { offsetof(struct snd_sof_pcm, stream[0].d0i3_compatible)}, {SOF_TKN_STREAM_CAPTURE_COMPATIBLE_D0I3, SND_SOC_TPLG_TUPLE_TYPE_BOOL, get_token_u16, offsetof(struct snd_sof_pcm, stream[1].d0i3_compatible)}, + {SOF_TKN_STREAM_PLAYBACK_PAUSE_SUPPORTED, SND_SOC_TPLG_TUPLE_TYPE_BOOL, get_token_u16, + offsetof(struct snd_sof_pcm, stream[0].pause_supported)}, + {SOF_TKN_STREAM_CAPTURE_PAUSE_SUPPORTED, SND_SOC_TPLG_TUPLE_TYPE_BOOL, get_token_u16, + offsetof(struct snd_sof_pcm, stream[1].pause_supported)}, }; /* Leds */ diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c index 933a0913237c..886b3fa537d2 100644 --- a/sound/soc/sunxi/sun4i-codec.c +++ b/sound/soc/sunxi/sun4i-codec.c @@ -5,6 +5,7 @@ * Copyright 2015 Maxime Ripard <maxime.ripard@free-electrons.com> * Copyright 2015 Adam Sampson <ats@offog.org> * Copyright 2016 Chen-Yu Tsai <wens@csie.org> + * Copyright 2018 Mesih Kilinc <mesihkilinc@gmail.com> * * Based on the Allwinner SDK driver, released under the GPL. */ @@ -265,6 +266,64 @@ /* TODO H3 DAP (Digital Audio Processing) bits */ +#define SUN4I_DMA_MAX_BURST (8) + +/* suniv specific registers */ + +#define SUNIV_DMA_MAX_BURST (4) + +/* Codec DAC digital controls and FIFO registers */ +#define SUNIV_CODEC_ADC_FIFOC (0x10) +#define SUNIV_CODEC_ADC_FIFOC_EN_AD (28) +#define SUNIV_CODEC_ADC_FIFOS (0x14) +#define SUNIV_CODEC_ADC_RXDATA (0x18) + +/* Output mixer and gain controls */ +#define SUNIV_CODEC_OM_DACA_CTRL (0x20) +#define SUNIV_CODEC_OM_DACA_CTRL_DACAREN (31) +#define SUNIV_CODEC_OM_DACA_CTRL_DACALEN (30) +#define SUNIV_CODEC_OM_DACA_CTRL_RMIXEN (29) +#define SUNIV_CODEC_OM_DACA_CTRL_LMIXEN (28) +#define SUNIV_CODEC_OM_DACA_CTRL_RHPPAMUTE (27) +#define SUNIV_CODEC_OM_DACA_CTRL_LHPPAMUTE (26) +#define SUNIV_CODEC_OM_DACA_CTRL_RHPIS (25) +#define SUNIV_CODEC_OM_DACA_CTRL_LHPIS (24) +#define SUNIV_CODEC_OM_DACA_CTRL_HPCOM_CTL (22) +#define SUNIV_CODEC_OM_DACA_CTRL_COMPTEN (21) +#define SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_MICIN (20) +#define SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_LINEIN (19) +#define SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_FMIN (18) +#define SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_RDAC (17) +#define SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_LDAC (16) +#define SUNIV_CODEC_OM_DACA_CTRL_HPPAEN (15) +#define SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_MICIN (12) +#define SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_LINEIN (11) +#define SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_FMIN (10) +#define SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_LDAC (9) +#define SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_RDAC (8) +#define SUNIV_CODEC_OM_DACA_CTRL_LTLNMUTE (7) +#define SUNIV_CODEC_OM_DACA_CTRL_RTLNMUTE (6) +#define SUNIV_CODEC_OM_DACA_CTRL_HPVOL (0) + +/* Analog Input Mixer controls */ +#define SUNIV_CODEC_ADC_ACTL (0x24) +#define SUNIV_CODEC_ADC_ADCEN (31) +#define SUNIV_CODEC_ADC_MICG (24) +#define SUNIV_CODEC_ADC_LINEINVOL (21) +#define SUNIV_CODEC_ADC_ADCG (16) +#define SUNIV_CODEC_ADC_ADCMIX_MIC (13) +#define SUNIV_CODEC_ADC_ADCMIX_FMINL (12) +#define SUNIV_CODEC_ADC_ADCMIX_FMINR (11) +#define SUNIV_CODEC_ADC_ADCMIX_LINEIN (10) +#define SUNIV_CODEC_ADC_ADCMIX_LOUT (9) +#define SUNIV_CODEC_ADC_ADCMIX_ROUT (8) +#define SUNIV_CODEC_ADC_PASPEEDSELECT (7) +#define SUNIV_CODEC_ADC_FMINVOL (4) +#define SUNIV_CODEC_ADC_MICAMPEN (3) +#define SUNIV_CODEC_ADC_MICBOOST (0) + +#define SUNIV_CODEC_ADC_DBG (0x4c) + struct sun4i_codec { struct device *dev; struct regmap *regmap; @@ -1255,6 +1314,228 @@ static const struct snd_soc_component_driver sun8i_a23_codec_codec = { .endianness = 1, }; +/*suniv F1C100s codec */ + +/* headphone controls */ +static const char * const suniv_codec_hp_src_enum_text[] = { + "DAC", "Mixer", +}; + +static SOC_ENUM_DOUBLE_DECL(suniv_codec_hp_src_enum, + SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_LHPIS, + SUNIV_CODEC_OM_DACA_CTRL_RHPIS, + suniv_codec_hp_src_enum_text); + +static const struct snd_kcontrol_new suniv_codec_hp_src[] = { + SOC_DAPM_ENUM("Headphone Source Playback Route", + suniv_codec_hp_src_enum), +}; + +/* mixer controls */ +static const struct snd_kcontrol_new suniv_codec_adc_mixer_controls[] = { + SOC_DAPM_SINGLE("Right Out Capture Switch", SUNIV_CODEC_ADC_ACTL, + SUNIV_CODEC_ADC_ADCMIX_ROUT, 1, 0), + SOC_DAPM_SINGLE("Left Out Capture Switch", SUNIV_CODEC_ADC_ACTL, + SUNIV_CODEC_ADC_ADCMIX_LOUT, 1, 0), + SOC_DAPM_SINGLE("Line In Capture Switch", SUNIV_CODEC_ADC_ACTL, + SUNIV_CODEC_ADC_ADCMIX_LINEIN, 1, 0), + SOC_DAPM_SINGLE("Right FM In Capture Switch", SUNIV_CODEC_ADC_ACTL, + SUNIV_CODEC_ADC_ADCMIX_FMINR, 1, 0), + SOC_DAPM_SINGLE("Left FM In Capture Switch", SUNIV_CODEC_ADC_ACTL, + SUNIV_CODEC_ADC_ADCMIX_FMINL, 1, 0), + SOC_DAPM_SINGLE("Mic Capture Switch", SUNIV_CODEC_ADC_ACTL, + SUNIV_CODEC_ADC_ADCMIX_MIC, 1, 0), +}; + +static const struct snd_kcontrol_new suniv_codec_dac_lmixer_controls[] = { + SOC_DAPM_SINGLE("Right DAC Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_RDAC, 1, 0), + SOC_DAPM_SINGLE("Left DAC Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_LDAC, 1, 0), + SOC_DAPM_SINGLE("FM In Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_FMIN, 1, 0), + SOC_DAPM_SINGLE("Line In Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_LINEIN, 1, 0), + SOC_DAPM_SINGLE("Mic In Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_LMIXMUTE_MICIN, 1, 0), +}; + +static const struct snd_kcontrol_new suniv_codec_dac_rmixer_controls[] = { + SOC_DAPM_SINGLE("Left DAC Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_LDAC, 1, 0), + SOC_DAPM_SINGLE("Right DAC Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_RDAC, 1, 0), + SOC_DAPM_SINGLE("FM In Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_FMIN, 1, 0), + SOC_DAPM_SINGLE("Line In Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_LINEIN, 1, 0), + SOC_DAPM_SINGLE("Mic In Playback Switch", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_RMIXMUTE_MICIN, 1, 0), +}; + +static const DECLARE_TLV_DB_SCALE(suniv_codec_dvol_scale, -7308, 116, 0); +static const DECLARE_TLV_DB_SCALE(suniv_codec_hp_vol_scale, -6300, 100, 1); +static const DECLARE_TLV_DB_SCALE(suniv_codec_out_mixer_pregain_scale, + -450, 150, 0); + +static const DECLARE_TLV_DB_RANGE(suniv_codec_mic_gain_scale, + 0, 0, TLV_DB_SCALE_ITEM(0, 0, 0), + 1, 7, TLV_DB_SCALE_ITEM(2400, 300, 0), +); + +static const struct snd_kcontrol_new suniv_codec_codec_widgets[] = { + SOC_SINGLE_TLV("DAC Playback Volume", SUN4I_CODEC_DAC_DPC, + SUN4I_CODEC_DAC_DPC_DVOL, 0x3f, 1, + suniv_codec_dvol_scale), + SOC_SINGLE_TLV("Headphone Playback Volume", + SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_HPVOL, 0x3f, 0, + suniv_codec_hp_vol_scale), + SOC_DOUBLE("Headphone Playback Switch", + SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_LHPPAMUTE, + SUNIV_CODEC_OM_DACA_CTRL_RHPPAMUTE, 1, 0), + SOC_SINGLE_TLV("Line In Playback Volume", + SUNIV_CODEC_ADC_ACTL, SUNIV_CODEC_ADC_LINEINVOL, + 0x7, 0, suniv_codec_out_mixer_pregain_scale), + SOC_SINGLE_TLV("FM In Playback Volume", + SUNIV_CODEC_ADC_ACTL, SUNIV_CODEC_ADC_FMINVOL, + 0x7, 0, suniv_codec_out_mixer_pregain_scale), + SOC_SINGLE_TLV("Mic In Playback Volume", + SUNIV_CODEC_ADC_ACTL, SUNIV_CODEC_ADC_MICG, + 0x7, 0, suniv_codec_out_mixer_pregain_scale), + + /* Microphone Amp boost gains */ + SOC_SINGLE_TLV("Mic Boost Volume", SUNIV_CODEC_ADC_ACTL, + SUNIV_CODEC_ADC_MICBOOST, 0x7, 0, + suniv_codec_mic_gain_scale), + SOC_SINGLE_TLV("ADC Capture Volume", + SUNIV_CODEC_ADC_ACTL, SUNIV_CODEC_ADC_ADCG, + 0x7, 0, suniv_codec_out_mixer_pregain_scale), +}; + +static const struct snd_soc_dapm_widget suniv_codec_codec_dapm_widgets[] = { + /* Microphone inputs */ + SND_SOC_DAPM_INPUT("MIC"), + + /* Microphone Bias */ + /* deleted: HBIAS, MBIAS */ + + /* Mic input path */ + SND_SOC_DAPM_PGA("Mic Amplifier", SUNIV_CODEC_ADC_ACTL, + SUNIV_CODEC_ADC_MICAMPEN, 0, NULL, 0), + + /* Line In */ + SND_SOC_DAPM_INPUT("LINEIN"), + + /* FM In */ + SND_SOC_DAPM_INPUT("FMINR"), + SND_SOC_DAPM_INPUT("FMINL"), + + /* Digital parts of the ADCs */ + SND_SOC_DAPM_SUPPLY("ADC Enable", SUNIV_CODEC_ADC_FIFOC, + SUNIV_CODEC_ADC_FIFOC_EN_AD, 0, + NULL, 0), + + /* Analog parts of the ADCs */ + SND_SOC_DAPM_ADC("ADC", "Codec Capture", SUNIV_CODEC_ADC_ACTL, + SUNIV_CODEC_ADC_ADCEN, 0), + + /* ADC Mixers */ + SOC_MIXER_ARRAY("ADC Mixer", SUNIV_CODEC_ADC_ACTL, + SND_SOC_NOPM, 0, + suniv_codec_adc_mixer_controls), + + /* Digital parts of the DACs */ + SND_SOC_DAPM_SUPPLY("DAC Enable", SUN4I_CODEC_DAC_DPC, + SUN4I_CODEC_DAC_DPC_EN_DA, 0, + NULL, 0), + + /* Analog parts of the DACs */ + SND_SOC_DAPM_DAC("Left DAC", "Codec Playback", + SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_DACALEN, 0), + SND_SOC_DAPM_DAC("Right DAC", "Codec Playback", + SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_DACAREN, 0), + + /* Mixers */ + SOC_MIXER_ARRAY("Left Mixer", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_LMIXEN, 0, + suniv_codec_dac_lmixer_controls), + SOC_MIXER_ARRAY("Right Mixer", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_RMIXEN, 0, + suniv_codec_dac_rmixer_controls), + + /* Headphone output path */ + SND_SOC_DAPM_MUX("Headphone Source Playback Route", + SND_SOC_NOPM, 0, 0, suniv_codec_hp_src), + SND_SOC_DAPM_OUT_DRV("Headphone Amp", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_HPPAEN, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("HPCOM Protection", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_COMPTEN, 0, NULL, 0), + SND_SOC_DAPM_REG(snd_soc_dapm_supply, "HPCOM", SUNIV_CODEC_OM_DACA_CTRL, + SUNIV_CODEC_OM_DACA_CTRL_HPCOM_CTL, 0x3, 0x3, 0), + SND_SOC_DAPM_OUTPUT("HP"), +}; + +static const struct snd_soc_dapm_route suniv_codec_codec_dapm_routes[] = { + /* DAC Routes */ + { "Left DAC", NULL, "DAC Enable" }, + { "Right DAC", NULL, "DAC Enable" }, + + /* Microphone Routes */ + { "Mic Amplifier", NULL, "MIC"}, + + /* Left Mixer Routes */ + { "Left Mixer", "Right DAC Playback Switch", "Right DAC" }, + { "Left Mixer", "Left DAC Playback Switch", "Left DAC" }, + { "Left Mixer", "FM In Playback Switch", "FMINL" }, + { "Left Mixer", "Line In Playback Switch", "LINEIN" }, + { "Left Mixer", "Mic In Playback Switch", "Mic Amplifier" }, + + /* Right Mixer Routes */ + { "Right Mixer", "Left DAC Playback Switch", "Left DAC" }, + { "Right Mixer", "Right DAC Playback Switch", "Right DAC" }, + { "Right Mixer", "FM In Playback Switch", "FMINR" }, + { "Right Mixer", "Line In Playback Switch", "LINEIN" }, + { "Right Mixer", "Mic In Playback Switch", "Mic Amplifier" }, + + /* ADC Mixer Routes */ + { "ADC Mixer", "Right Out Capture Switch", "Right Mixer" }, + { "ADC Mixer", "Left Out Capture Switch", "Left Mixer" }, + { "ADC Mixer", "Line In Capture Switch", "LINEIN" }, + { "ADC Mixer", "Right FM In Capture Switch", "FMINR" }, + { "ADC Mixer", "Left FM In Capture Switch", "FMINL" }, + { "ADC Mixer", "Mic Capture Switch", "Mic Amplifier" }, + + /* Headphone Routes */ + { "Headphone Source Playback Route", "DAC", "Left DAC" }, + { "Headphone Source Playback Route", "DAC", "Right DAC" }, + { "Headphone Source Playback Route", "Mixer", "Left Mixer" }, + { "Headphone Source Playback Route", "Mixer", "Right Mixer" }, + { "Headphone Amp", NULL, "Headphone Source Playback Route" }, + { "HP", NULL, "Headphone Amp" }, + { "HPCOM", NULL, "HPCOM Protection" }, + + /* ADC Routes */ + { "ADC", NULL, "ADC Mixer" }, + { "ADC", NULL, "ADC Enable" }, +}; + +static const struct snd_soc_component_driver suniv_codec_codec = { + .controls = suniv_codec_codec_widgets, + .num_controls = ARRAY_SIZE(suniv_codec_codec_widgets), + .dapm_widgets = suniv_codec_codec_dapm_widgets, + .num_dapm_widgets = ARRAY_SIZE(suniv_codec_codec_dapm_widgets), + .dapm_routes = suniv_codec_codec_dapm_routes, + .num_dapm_routes = ARRAY_SIZE(suniv_codec_codec_dapm_routes), + .idle_bias_on = 1, + .use_pmdown_time = 1, + .endianness = 1, +}; + static const struct snd_soc_component_driver sun4i_codec_component = { .name = "sun4i-codec", .legacy_dai_naming = 1, @@ -1701,6 +1982,56 @@ static struct snd_soc_card *sun50i_h616_codec_create_card(struct device *dev) return card; }; +static const struct snd_soc_dapm_widget suniv_codec_card_dapm_widgets[] = { + SND_SOC_DAPM_HP("Headphone", NULL), + SND_SOC_DAPM_LINE("Line In", NULL), + SND_SOC_DAPM_LINE("Right FM In", NULL), + SND_SOC_DAPM_LINE("Left FM In", NULL), + SND_SOC_DAPM_MIC("Mic", NULL), + SND_SOC_DAPM_SPK("Speaker", sun4i_codec_spk_event), +}; + +/* Connect digital side enables to analog side widgets */ +static const struct snd_soc_dapm_route suniv_codec_card_routes[] = { + /* ADC Routes */ + { "ADC", NULL, "ADC Enable" }, + { "Codec Capture", NULL, "ADC" }, + + /* DAC Routes */ + { "Left DAC", NULL, "DAC Enable" }, + { "Right DAC", NULL, "DAC Enable" }, + { "Left DAC", NULL, "Codec Playback" }, + { "Right DAC", NULL, "Codec Playback" }, +}; + +static struct snd_soc_card *suniv_codec_create_card(struct device *dev) +{ + struct snd_soc_card *card; + int ret; + + card = devm_kzalloc(dev, sizeof(*card), GFP_KERNEL); + if (!card) + return ERR_PTR(-ENOMEM); + + card->dai_link = sun4i_codec_create_link(dev, &card->num_links); + if (!card->dai_link) + return ERR_PTR(-ENOMEM); + + card->dev = dev; + card->name = "F1C100s Audio Codec"; + card->dapm_widgets = suniv_codec_card_dapm_widgets; + card->num_dapm_widgets = ARRAY_SIZE(suniv_codec_card_dapm_widgets); + card->dapm_routes = suniv_codec_card_routes; + card->num_dapm_routes = ARRAY_SIZE(suniv_codec_card_routes); + card->fully_routed = true; + + ret = snd_soc_of_parse_audio_routing(card, "allwinner,audio-routing"); + if (ret) + dev_warn(dev, "failed to parse audio-routing: %d\n", ret); + + return card; +}; + static const struct regmap_config sun4i_codec_regmap_config = { .reg_bits = 32, .reg_stride = 4, @@ -1751,6 +2082,13 @@ static const struct regmap_config sun50i_h616_codec_regmap_config = { .cache_type = REGCACHE_NONE, }; +static const struct regmap_config suniv_codec_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = SUNIV_CODEC_ADC_DBG, +}; + struct sun4i_codec_quirks { const struct regmap_config *regmap_config; const struct snd_soc_component_driver *codec; @@ -1761,6 +2099,7 @@ struct sun4i_codec_quirks { unsigned int reg_adc_rxdata; /* RX FIFO offset for DMA config */ bool has_reset; bool playback_only; + u32 dma_max_burst; }; static const struct sun4i_codec_quirks sun4i_codec_quirks = { @@ -1771,6 +2110,7 @@ static const struct sun4i_codec_quirks sun4i_codec_quirks = { .reg_dac_fifoc = REG_FIELD(SUN4I_CODEC_DAC_FIFOC, 0, 31), .reg_dac_txdata = SUN4I_CODEC_DAC_TXDATA, .reg_adc_rxdata = SUN4I_CODEC_ADC_RXDATA, + .dma_max_burst = SUN4I_DMA_MAX_BURST, }; static const struct sun4i_codec_quirks sun6i_a31_codec_quirks = { @@ -1782,6 +2122,7 @@ static const struct sun4i_codec_quirks sun6i_a31_codec_quirks = { .reg_dac_txdata = SUN4I_CODEC_DAC_TXDATA, .reg_adc_rxdata = SUN6I_CODEC_ADC_RXDATA, .has_reset = true, + .dma_max_burst = SUN4I_DMA_MAX_BURST, }; static const struct sun4i_codec_quirks sun7i_codec_quirks = { @@ -1792,6 +2133,7 @@ static const struct sun4i_codec_quirks sun7i_codec_quirks = { .reg_dac_fifoc = REG_FIELD(SUN4I_CODEC_DAC_FIFOC, 0, 31), .reg_dac_txdata = SUN4I_CODEC_DAC_TXDATA, .reg_adc_rxdata = SUN4I_CODEC_ADC_RXDATA, + .dma_max_burst = SUN4I_DMA_MAX_BURST, }; static const struct sun4i_codec_quirks sun8i_a23_codec_quirks = { @@ -1803,6 +2145,7 @@ static const struct sun4i_codec_quirks sun8i_a23_codec_quirks = { .reg_dac_txdata = SUN4I_CODEC_DAC_TXDATA, .reg_adc_rxdata = SUN6I_CODEC_ADC_RXDATA, .has_reset = true, + .dma_max_burst = SUN4I_DMA_MAX_BURST, }; static const struct sun4i_codec_quirks sun8i_h3_codec_quirks = { @@ -1819,6 +2162,7 @@ static const struct sun4i_codec_quirks sun8i_h3_codec_quirks = { .reg_dac_txdata = SUN8I_H3_CODEC_DAC_TXDATA, .reg_adc_rxdata = SUN6I_CODEC_ADC_RXDATA, .has_reset = true, + .dma_max_burst = SUN4I_DMA_MAX_BURST, }; static const struct sun4i_codec_quirks sun8i_v3s_codec_quirks = { @@ -1834,6 +2178,7 @@ static const struct sun4i_codec_quirks sun8i_v3s_codec_quirks = { .reg_dac_txdata = SUN8I_H3_CODEC_DAC_TXDATA, .reg_adc_rxdata = SUN6I_CODEC_ADC_RXDATA, .has_reset = true, + .dma_max_burst = SUN4I_DMA_MAX_BURST, }; static const struct sun4i_codec_quirks sun50i_h616_codec_quirks = { @@ -1843,6 +2188,19 @@ static const struct sun4i_codec_quirks sun50i_h616_codec_quirks = { .reg_dac_fifoc = REG_FIELD(SUN50I_H616_CODEC_DAC_FIFOC, 0, 31), .reg_dac_txdata = SUN8I_H3_CODEC_DAC_TXDATA, .has_reset = true, + .dma_max_burst = SUN4I_DMA_MAX_BURST, +}; + +static const struct sun4i_codec_quirks suniv_f1c100s_codec_quirks = { + .regmap_config = &suniv_codec_regmap_config, + .codec = &suniv_codec_codec, + .create_card = suniv_codec_create_card, + .reg_adc_fifoc = REG_FIELD(SUNIV_CODEC_ADC_FIFOC, 0, 31), + .reg_dac_fifoc = REG_FIELD(SUN4I_CODEC_DAC_FIFOC, 0, 31), + .reg_dac_txdata = SUN4I_CODEC_DAC_TXDATA, + .reg_adc_rxdata = SUNIV_CODEC_ADC_RXDATA, + .has_reset = true, + .dma_max_burst = SUNIV_DMA_MAX_BURST, }; static const struct of_device_id sun4i_codec_of_match[] = { @@ -1874,6 +2232,10 @@ static const struct of_device_id sun4i_codec_of_match[] = { .compatible = "allwinner,sun50i-h616-codec", .data = &sun50i_h616_codec_quirks, }, + { + .compatible = "allwinner,suniv-f1c100s-codec", + .data = &suniv_f1c100s_codec_quirks, + }, {} }; MODULE_DEVICE_TABLE(of, sun4i_codec_of_match); @@ -1911,7 +2273,7 @@ static int sun4i_codec_probe(struct platform_device *pdev) } /* Get the clocks from the DT */ - scodec->clk_apb = devm_clk_get(&pdev->dev, "apb"); + scodec->clk_apb = devm_clk_get_enabled(&pdev->dev, "apb"); if (IS_ERR(scodec->clk_apb)) { dev_err(&pdev->dev, "Failed to get the APB clock\n"); return PTR_ERR(scodec->clk_apb); @@ -1924,8 +2286,7 @@ static int sun4i_codec_probe(struct platform_device *pdev) } if (quirks->has_reset) { - scodec->rst = devm_reset_control_get_exclusive(&pdev->dev, - NULL); + scodec->rst = devm_reset_control_get_exclusive_deasserted(&pdev->dev, NULL); if (IS_ERR(scodec->rst)) { dev_err(&pdev->dev, "Failed to get reset control\n"); return PTR_ERR(scodec->rst); @@ -1961,32 +2322,16 @@ static int sun4i_codec_probe(struct platform_device *pdev) return ret; } - /* Enable the bus clock */ - if (clk_prepare_enable(scodec->clk_apb)) { - dev_err(&pdev->dev, "Failed to enable the APB clock\n"); - return -EINVAL; - } - - /* Deassert the reset control */ - if (scodec->rst) { - ret = reset_control_deassert(scodec->rst); - if (ret) { - dev_err(&pdev->dev, - "Failed to deassert the reset control\n"); - goto err_clk_disable; - } - } - /* DMA configuration for TX FIFO */ scodec->playback_dma_data.addr = res->start + quirks->reg_dac_txdata; - scodec->playback_dma_data.maxburst = 8; + scodec->playback_dma_data.maxburst = quirks->dma_max_burst; scodec->playback_dma_data.addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; if (!quirks->playback_only) { /* DMA configuration for RX FIFO */ scodec->capture_dma_data.addr = res->start + quirks->reg_adc_rxdata; - scodec->capture_dma_data.maxburst = 8; + scodec->capture_dma_data.maxburst = quirks->dma_max_burst; scodec->capture_dma_data.addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; } @@ -1994,7 +2339,7 @@ static int sun4i_codec_probe(struct platform_device *pdev) &sun4i_codec_dai, 1); if (ret) { dev_err(&pdev->dev, "Failed to register our codec\n"); - goto err_assert_reset; + return ret; } ret = devm_snd_soc_register_component(&pdev->dev, @@ -2002,20 +2347,20 @@ static int sun4i_codec_probe(struct platform_device *pdev) &dummy_cpu_dai, 1); if (ret) { dev_err(&pdev->dev, "Failed to register our DAI\n"); - goto err_assert_reset; + return ret; } ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); if (ret) { dev_err(&pdev->dev, "Failed to register against DMAEngine\n"); - goto err_assert_reset; + return ret; } card = quirks->create_card(&pdev->dev); if (IS_ERR(card)) { ret = PTR_ERR(card); dev_err(&pdev->dev, "Failed to create our card\n"); - goto err_assert_reset; + return ret; } snd_soc_card_set_drvdata(card, scodec); @@ -2023,28 +2368,17 @@ static int sun4i_codec_probe(struct platform_device *pdev) ret = snd_soc_register_card(card); if (ret) { dev_err_probe(&pdev->dev, ret, "Failed to register our card\n"); - goto err_assert_reset; + return ret; } return 0; - -err_assert_reset: - if (scodec->rst) - reset_control_assert(scodec->rst); -err_clk_disable: - clk_disable_unprepare(scodec->clk_apb); - return ret; } static void sun4i_codec_remove(struct platform_device *pdev) { struct snd_soc_card *card = platform_get_drvdata(pdev); - struct sun4i_codec *scodec = snd_soc_card_get_drvdata(card); snd_soc_unregister_card(card); - if (scodec->rst) - reset_control_assert(scodec->rst); - clk_disable_unprepare(scodec->clk_apb); } static struct platform_driver sun4i_codec_driver = { @@ -2063,4 +2397,5 @@ MODULE_AUTHOR("Jon Smirl <jonsmirl@gmail.com>"); MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>"); MODULE_AUTHOR("Chen-Yu Tsai <wens@csie.org>"); MODULE_AUTHOR("Ryan Walklin <ryan@testtoast.com"); +MODULE_AUTHOR("Mesih Kilinc <mesikilinc@gmail.com>"); MODULE_LICENSE("GPL"); diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c index 0aa416423246..41caf1795d09 100644 --- a/sound/soc/sunxi/sun4i-spdif.c +++ b/sound/soc/sunxi/sun4i-spdif.c @@ -176,6 +176,7 @@ struct sun4i_spdif_quirks { unsigned int reg_dac_txdata; bool has_reset; unsigned int val_fctl_ftx; + unsigned int mclk_multiplier; }; struct sun4i_spdif_dev { @@ -201,6 +202,10 @@ static void sun4i_spdif_configure(struct sun4i_spdif_dev *host) regmap_update_bits(host->regmap, SUN4I_SPDIF_FCTL, quirks->val_fctl_ftx, quirks->val_fctl_ftx); + /* Valid data at the MSB of TXFIFO Register */ + regmap_update_bits(host->regmap, SUN4I_SPDIF_FCTL, + SUN4I_SPDIF_FCTL_TXIM, 0); + /* clear TX counter */ regmap_write(host->regmap, SUN4I_SPDIF_TXCNT, 0); } @@ -282,14 +287,17 @@ static int sun4i_spdif_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } + host->dma_params_tx.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; switch (params_format(params)) { case SNDRV_PCM_FORMAT_S16_LE: fmt |= SUN4I_SPDIF_TXCFG_FMT16BIT; + host->dma_params_tx.addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; break; case SNDRV_PCM_FORMAT_S20_3LE: fmt |= SUN4I_SPDIF_TXCFG_FMT20BIT; break; case SNDRV_PCM_FORMAT_S24_LE: + case SNDRV_PCM_FORMAT_S32_LE: fmt |= SUN4I_SPDIF_TXCFG_FMT24BIT; break; default: @@ -313,6 +321,7 @@ static int sun4i_spdif_hw_params(struct snd_pcm_substream *substream, default: return -EINVAL; } + mclk *= host->quirks->mclk_multiplier; ret = clk_set_rate(host->spdif_clk, mclk); if (ret < 0) { @@ -321,9 +330,6 @@ static int sun4i_spdif_hw_params(struct snd_pcm_substream *substream, return ret; } - regmap_update_bits(host->regmap, SUN4I_SPDIF_FCTL, - SUN4I_SPDIF_FCTL_TXIM, SUN4I_SPDIF_FCTL_TXIM); - switch (rate) { case 22050: case 24000: @@ -347,6 +353,7 @@ static int sun4i_spdif_hw_params(struct snd_pcm_substream *substream, default: return -EINVAL; } + mclk_div *= host->quirks->mclk_multiplier; reg_val = 0; reg_val |= SUN4I_SPDIF_TXCFG_ASS; @@ -522,9 +529,10 @@ static const struct regmap_config sun4i_spdif_regmap_config = { #define SUN4I_RATES SNDRV_PCM_RATE_8000_192000 -#define SUN4I_FORMATS (SNDRV_PCM_FORMAT_S16_LE | \ - SNDRV_PCM_FORMAT_S20_3LE | \ - SNDRV_PCM_FORMAT_S24_LE) +#define SUN4I_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | \ + SNDRV_PCM_FMTBIT_S20_3LE | \ + SNDRV_PCM_FMTBIT_S24_LE | \ + SNDRV_PCM_FMTBIT_S32_LE) static struct snd_soc_dai_driver sun4i_spdif_dai = { .playback = { @@ -540,24 +548,28 @@ static struct snd_soc_dai_driver sun4i_spdif_dai = { static const struct sun4i_spdif_quirks sun4i_a10_spdif_quirks = { .reg_dac_txdata = SUN4I_SPDIF_TXFIFO, .val_fctl_ftx = SUN4I_SPDIF_FCTL_FTX, + .mclk_multiplier = 1, }; static const struct sun4i_spdif_quirks sun6i_a31_spdif_quirks = { .reg_dac_txdata = SUN4I_SPDIF_TXFIFO, .val_fctl_ftx = SUN4I_SPDIF_FCTL_FTX, .has_reset = true, + .mclk_multiplier = 1, }; static const struct sun4i_spdif_quirks sun8i_h3_spdif_quirks = { .reg_dac_txdata = SUN8I_SPDIF_TXFIFO, .val_fctl_ftx = SUN4I_SPDIF_FCTL_FTX, .has_reset = true, + .mclk_multiplier = 4, }; static const struct sun4i_spdif_quirks sun50i_h6_spdif_quirks = { .reg_dac_txdata = SUN8I_SPDIF_TXFIFO, .val_fctl_ftx = SUN50I_H6_SPDIF_FCTL_FTX, .has_reset = true, + .mclk_multiplier = 1, }; static const struct of_device_id sun4i_spdif_of_match[] = { diff --git a/sound/soc/xilinx/xlnx_spdif.c b/sound/soc/xilinx/xlnx_spdif.c index 7febb3830dc2..017a64ab9f1e 100644 --- a/sound/soc/xilinx/xlnx_spdif.c +++ b/sound/soc/xilinx/xlnx_spdif.c @@ -248,41 +248,35 @@ static int xlnx_spdif_probe(struct platform_device *pdev) if (!ctx) return -ENOMEM; - ctx->axi_clk = devm_clk_get(dev, "s_axi_aclk"); + ctx->axi_clk = devm_clk_get_enabled(dev, "s_axi_aclk"); if (IS_ERR(ctx->axi_clk)) { ret = PTR_ERR(ctx->axi_clk); dev_err(dev, "failed to get s_axi_aclk(%d)\n", ret); return ret; } - ret = clk_prepare_enable(ctx->axi_clk); - if (ret) { - dev_err(dev, "failed to enable s_axi_aclk(%d)\n", ret); - return ret; - } ctx->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(ctx->base)) { - ret = PTR_ERR(ctx->base); - goto clk_err; - } + if (IS_ERR(ctx->base)) + return PTR_ERR(ctx->base); + ret = of_property_read_u32(node, "xlnx,spdif-mode", &ctx->mode); if (ret < 0) { dev_err(dev, "cannot get SPDIF mode\n"); - goto clk_err; + return ret; } if (ctx->mode) { dai_drv = &xlnx_spdif_tx_dai; } else { ret = platform_get_irq(pdev, 0); if (ret < 0) - goto clk_err; + return ret; + ret = devm_request_irq(dev, ret, xlnx_spdifrx_irq_handler, 0, "XLNX_SPDIF_RX", ctx); if (ret) { dev_err(dev, "spdif rx irq request failed\n"); - ret = -ENODEV; - goto clk_err; + return -ENODEV; } init_waitqueue_head(&ctx->chsts_q); @@ -292,7 +286,7 @@ static int xlnx_spdif_probe(struct platform_device *pdev) ret = of_property_read_u32(node, "xlnx,aud_clk_i", &ctx->aclk); if (ret < 0) { dev_err(dev, "cannot get aud_clk_i value\n"); - goto clk_err; + return ret; } dev_set_drvdata(dev, ctx); @@ -301,22 +295,13 @@ static int xlnx_spdif_probe(struct platform_device *pdev) dai_drv, 1); if (ret) { dev_err(dev, "SPDIF component registration failed\n"); - goto clk_err; + return ret; } writel(XSPDIF_SOFT_RESET_VALUE, ctx->base + XSPDIF_SOFT_RESET_REG); dev_info(dev, "%s DAI registered\n", dai_drv->name); -clk_err: - clk_disable_unprepare(ctx->axi_clk); - return ret; -} - -static void xlnx_spdif_remove(struct platform_device *pdev) -{ - struct spdif_dev_data *ctx = dev_get_drvdata(&pdev->dev); - - clk_disable_unprepare(ctx->axi_clk); + return 0; } static struct platform_driver xlnx_spdif_driver = { @@ -325,7 +310,6 @@ static struct platform_driver xlnx_spdif_driver = { .of_match_table = xlnx_spdif_of_match, }, .probe = xlnx_spdif_probe, - .remove = xlnx_spdif_remove, }; module_platform_driver(xlnx_spdif_driver); diff --git a/sound/usb/Makefile b/sound/usb/Makefile index 0532499dbc6d..30bd5348477b 100644 --- a/sound/usb/Makefile +++ b/sound/usb/Makefile @@ -6,6 +6,7 @@ snd-usb-audio-y := card.o \ clock.o \ endpoint.o \ + fcp.o \ format.o \ helper.o \ implicit.o \ diff --git a/sound/usb/fcp.c b/sound/usb/fcp.c new file mode 100644 index 000000000000..7df65041ace5 --- /dev/null +++ b/sound/usb/fcp.c @@ -0,0 +1,1134 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Focusrite Control Protocol Driver for ALSA + * + * Copyright (c) 2024-2025 by Geoffrey D. Bennett <g at b4.vu> + */ +/* + * DOC: Theory of Operation + * + * The Focusrite Control Protocol (FCP) driver provides a minimal + * kernel interface that allows a user-space driver (primarily + * fcp-server) to communicate with Focusrite USB audio interfaces + * using their vendor-specific protocol. This protocol is used by + * Scarlett 2nd Gen, 3rd Gen, 4th Gen, Clarett USB, Clarett+, and + * Vocaster series devices. + * + * Unlike the existing scarlett2 driver which implements all controls + * in kernel space, this driver takes a lighter-weight approach by + * moving most functionality to user space. The only control + * implemented in kernel space is the Level Meter, since it requires + * frequent polling of volatile data. + * + * The driver provides an hwdep interface that allows the user-space + * driver to: + * - Initialise the protocol + * - Send arbitrary FCP commands to the device + * - Receive notifications from the device + * - Configure the Level Meter control + * + * Usage Flow + * ---------- + * 1. Open the hwdep device (requires CAP_SYS_RAWIO) + * 2. Get protocol version using FCP_IOCTL_PVERSION + * 3. Initialise protocol using FCP_IOCTL_INIT + * 4. Send commands using FCP_IOCTL_CMD + * 5. Receive notifications using read() + * 6. Optionally set up the Level Meter control using + * FCP_IOCTL_SET_METER_MAP + * 7. Optionally add labels to the Level Meter control using + * FCP_IOCTL_SET_METER_LABELS + * + * Level Meter + * ----------- + * The Level Meter is implemented as an ALSA control that provides + * real-time level monitoring. When the control is read, the driver + * requests the current meter levels from the device, translates the + * levels using the configured mapping, and returns the result to the + * user. The mapping between device meters and the ALSA control's + * channels is configured with FCP_IOCTL_SET_METER_MAP. + * + * Labels for the Level Meter channels can be set using + * FCP_IOCTL_SET_METER_LABELS and read by applications through the + * control's TLV data. The labels are transferred as a sequence of + * null-terminated strings. + */ + +#include <linux/slab.h> +#include <linux/usb.h> + +#include <sound/control.h> +#include <sound/hwdep.h> +#include <sound/tlv.h> + +#include <uapi/sound/fcp.h> + +#include "usbaudio.h" +#include "mixer.h" +#include "helper.h" + +#include "fcp.h" + +/* notify waiting to send to *file */ +struct fcp_notify { + wait_queue_head_t queue; + u32 event; + spinlock_t lock; +}; + +struct fcp_data { + struct usb_mixer_interface *mixer; + + struct mutex mutex; /* serialise access to the device */ + struct completion cmd_done; /* wait for command completion */ + struct file *file; /* hwdep file */ + + struct fcp_notify notify; + + u8 bInterfaceNumber; + u8 bEndpointAddress; + u16 wMaxPacketSize; + u8 bInterval; + + uint16_t step0_resp_size; + uint16_t step2_resp_size; + uint32_t init1_opcode; + uint32_t init2_opcode; + + u8 init; + u16 seq; + + u8 num_meter_slots; + s16 *meter_level_map; + __le32 *meter_levels; + struct snd_kcontrol *meter_ctl; + + unsigned int *meter_labels_tlv; + int meter_labels_tlv_size; +}; + +/*** USB Interactions ***/ + +/* FCP Command ACK notification bit */ +#define FCP_NOTIFY_ACK 1 + +/* Vendor-specific USB control requests */ +#define FCP_USB_REQ_STEP0 0 +#define FCP_USB_REQ_CMD_TX 2 +#define FCP_USB_REQ_CMD_RX 3 + +/* Focusrite Control Protocol opcodes that the kernel side needs to + * know about + */ +#define FCP_USB_REBOOT 0x00000003 +#define FCP_USB_GET_METER 0x00001001 +#define FCP_USB_FLASH_ERASE 0x00004002 +#define FCP_USB_FLASH_WRITE 0x00004004 + +#define FCP_USB_METER_LEVELS_GET_MAGIC 1 + +#define FCP_SEGMENT_APP_GOLD 0 + +/* Forward declarations */ +static int fcp_init(struct usb_mixer_interface *mixer, + void *step0_resp, void *step2_resp); + +/* FCP command request/response format */ +struct fcp_usb_packet { + __le32 opcode; + __le16 size; + __le16 seq; + __le32 error; + __le32 pad; + u8 data[]; +}; + +static void fcp_fill_request_header(struct fcp_data *private, + struct fcp_usb_packet *req, + u32 opcode, u16 req_size) +{ + /* sequence must go up by 1 for each request */ + u16 seq = private->seq++; + + req->opcode = cpu_to_le32(opcode); + req->size = cpu_to_le16(req_size); + req->seq = cpu_to_le16(seq); + req->error = 0; + req->pad = 0; +} + +static int fcp_usb_tx(struct usb_device *dev, int interface, + void *buf, u16 size) +{ + return snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), + FCP_USB_REQ_CMD_TX, + USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT, + 0, interface, buf, size); +} + +static int fcp_usb_rx(struct usb_device *dev, int interface, + void *buf, u16 size) +{ + return snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), + FCP_USB_REQ_CMD_RX, + USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN, + 0, interface, buf, size); +} + +/* Send an FCP command and get the response */ +static int fcp_usb(struct usb_mixer_interface *mixer, u32 opcode, + const void *req_data, u16 req_size, + void *resp_data, u16 resp_size) +{ + struct fcp_data *private = mixer->private_data; + struct usb_device *dev = mixer->chip->dev; + struct fcp_usb_packet *req __free(kfree) = NULL; + struct fcp_usb_packet *resp __free(kfree) = NULL; + size_t req_buf_size = struct_size(req, data, req_size); + size_t resp_buf_size = struct_size(resp, data, resp_size); + int retries = 0; + const int max_retries = 5; + int err; + + if (!mixer->urb) + return -ENODEV; + + req = kmalloc(req_buf_size, GFP_KERNEL); + if (!req) + return -ENOMEM; + + resp = kmalloc(resp_buf_size, GFP_KERNEL); + if (!resp) + return -ENOMEM; + + /* build request message */ + fcp_fill_request_header(private, req, opcode, req_size); + if (req_size) + memcpy(req->data, req_data, req_size); + + /* send the request and retry on EPROTO */ +retry: + err = fcp_usb_tx(dev, private->bInterfaceNumber, req, req_buf_size); + if (err == -EPROTO && ++retries <= max_retries) { + msleep(1 << (retries - 1)); + goto retry; + } + + if (err != req_buf_size) { + usb_audio_err(mixer->chip, + "FCP request %08x failed: %d\n", opcode, err); + return -EINVAL; + } + + if (!wait_for_completion_timeout(&private->cmd_done, + msecs_to_jiffies(1000))) { + usb_audio_err(mixer->chip, + "FCP request %08x timed out\n", opcode); + + return -ETIMEDOUT; + } + + /* send a second message to get the response */ + err = fcp_usb_rx(dev, private->bInterfaceNumber, resp, resp_buf_size); + + /* validate the response */ + + if (err < 0) { + + /* ESHUTDOWN and EPROTO are valid responses to a + * reboot request + */ + if (opcode == FCP_USB_REBOOT && + (err == -ESHUTDOWN || err == -EPROTO)) + return 0; + + usb_audio_err(mixer->chip, + "FCP read response %08x failed: %d\n", + opcode, err); + return -EINVAL; + } + + if (err < sizeof(*resp)) { + usb_audio_err(mixer->chip, + "FCP response %08x too short: %d\n", + opcode, err); + return -EINVAL; + } + + if (req->seq != resp->seq) { + usb_audio_err(mixer->chip, + "FCP response %08x seq mismatch %d/%d\n", + opcode, + le16_to_cpu(req->seq), le16_to_cpu(resp->seq)); + return -EINVAL; + } + + if (req->opcode != resp->opcode) { + usb_audio_err(mixer->chip, + "FCP response %08x opcode mismatch %08x\n", + opcode, le32_to_cpu(resp->opcode)); + return -EINVAL; + } + + if (resp->error) { + usb_audio_err(mixer->chip, + "FCP response %08x error %d\n", + opcode, le32_to_cpu(resp->error)); + return -EINVAL; + } + + if (err != resp_buf_size) { + usb_audio_err(mixer->chip, + "FCP response %08x buffer size mismatch %d/%zu\n", + opcode, err, resp_buf_size); + return -EINVAL; + } + + if (resp_size != le16_to_cpu(resp->size)) { + usb_audio_err(mixer->chip, + "FCP response %08x size mismatch %d/%d\n", + opcode, resp_size, le16_to_cpu(resp->size)); + return -EINVAL; + } + + if (resp_data && resp_size > 0) + memcpy(resp_data, resp->data, resp_size); + + return 0; +} + +static int fcp_reinit(struct usb_mixer_interface *mixer) +{ + struct fcp_data *private = mixer->private_data; + void *step0_resp __free(kfree) = NULL; + void *step2_resp __free(kfree) = NULL; + + if (mixer->urb) + return 0; + + step0_resp = kmalloc(private->step0_resp_size, GFP_KERNEL); + if (!step0_resp) + return -ENOMEM; + step2_resp = kmalloc(private->step2_resp_size, GFP_KERNEL); + if (!step2_resp) + return -ENOMEM; + + return fcp_init(mixer, step0_resp, step2_resp); +} + +/*** Control Functions ***/ + +/* helper function to create a new control */ +static int fcp_add_new_ctl(struct usb_mixer_interface *mixer, + const struct snd_kcontrol_new *ncontrol, + int index, int channels, const char *name, + struct snd_kcontrol **kctl_return) +{ + struct snd_kcontrol *kctl; + struct usb_mixer_elem_info *elem; + int err; + + elem = kzalloc(sizeof(*elem), GFP_KERNEL); + if (!elem) + return -ENOMEM; + + /* We set USB_MIXER_BESPOKEN type, so that the core USB mixer code + * ignores them for resume and other operations. + * Also, the head.id field is set to 0, as we don't use this field. + */ + elem->head.mixer = mixer; + elem->control = index; + elem->head.id = 0; + elem->channels = channels; + elem->val_type = USB_MIXER_BESPOKEN; + + kctl = snd_ctl_new1(ncontrol, elem); + if (!kctl) { + kfree(elem); + return -ENOMEM; + } + kctl->private_free = snd_usb_mixer_elem_free; + + strscpy(kctl->id.name, name, sizeof(kctl->id.name)); + + err = snd_usb_mixer_add_control(&elem->head, kctl); + if (err < 0) + return err; + + if (kctl_return) + *kctl_return = kctl; + + return 0; +} + +/*** Level Meter Control ***/ + +static int fcp_meter_ctl_info(struct snd_kcontrol *kctl, + struct snd_ctl_elem_info *uinfo) +{ + struct usb_mixer_elem_info *elem = kctl->private_data; + + uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = elem->channels; + uinfo->value.integer.min = 0; + uinfo->value.integer.max = 4095; + uinfo->value.integer.step = 1; + return 0; +} + +static int fcp_meter_ctl_get(struct snd_kcontrol *kctl, + struct snd_ctl_elem_value *ucontrol) +{ + struct usb_mixer_elem_info *elem = kctl->private_data; + struct usb_mixer_interface *mixer = elem->head.mixer; + struct fcp_data *private = mixer->private_data; + int num_meter_slots, resp_size; + __le32 *resp = private->meter_levels; + int i, err = 0; + + struct { + __le16 pad; + __le16 num_meters; + __le32 magic; + } __packed req; + + guard(mutex)(&private->mutex); + + err = fcp_reinit(mixer); + if (err < 0) + return err; + + num_meter_slots = private->num_meter_slots; + resp_size = num_meter_slots * sizeof(u32); + + req.pad = 0; + req.num_meters = cpu_to_le16(num_meter_slots); + req.magic = cpu_to_le32(FCP_USB_METER_LEVELS_GET_MAGIC); + err = fcp_usb(mixer, FCP_USB_GET_METER, + &req, sizeof(req), resp, resp_size); + if (err < 0) + return err; + + /* copy & translate from resp[] using meter_level_map[] */ + for (i = 0; i < elem->channels; i++) { + int idx = private->meter_level_map[i]; + int value = idx < 0 ? 0 : le32_to_cpu(resp[idx]); + + ucontrol->value.integer.value[i] = value; + } + + return 0; +} + +static int fcp_meter_tlv_callback(struct snd_kcontrol *kctl, + int op_flag, unsigned int size, + unsigned int __user *tlv) +{ + struct usb_mixer_elem_info *elem = kctl->private_data; + struct usb_mixer_interface *mixer = elem->head.mixer; + struct fcp_data *private = mixer->private_data; + + guard(mutex)(&private->mutex); + + if (op_flag == SNDRV_CTL_TLV_OP_READ) { + if (private->meter_labels_tlv_size == 0) + return 0; + + if (size > private->meter_labels_tlv_size) + size = private->meter_labels_tlv_size; + + if (copy_to_user(tlv, private->meter_labels_tlv, size)) + return -EFAULT; + + return size; + } + + return -EINVAL; +} + +static const struct snd_kcontrol_new fcp_meter_ctl = { + .iface = SNDRV_CTL_ELEM_IFACE_PCM, + .access = SNDRV_CTL_ELEM_ACCESS_READ | + SNDRV_CTL_ELEM_ACCESS_VOLATILE, + .info = fcp_meter_ctl_info, + .get = fcp_meter_ctl_get, + .tlv = { .c = fcp_meter_tlv_callback }, +}; + +/*** hwdep interface ***/ + +/* FCP initialisation */ +static int fcp_ioctl_init(struct usb_mixer_interface *mixer, + struct fcp_init __user *arg) +{ + struct fcp_init init; + struct usb_device *dev = mixer->chip->dev; + struct fcp_data *private = mixer->private_data; + void *resp __free(kfree) = NULL; + void *step2_resp; + int err, buf_size; + + if (usb_pipe_type_check(dev, usb_sndctrlpipe(dev, 0))) + return -EINVAL; + + /* Get initialisation parameters */ + if (copy_from_user(&init, arg, sizeof(init))) + return -EFAULT; + + /* Validate the response sizes */ + if (init.step0_resp_size < 1 || + init.step0_resp_size > 255 || + init.step2_resp_size < 1 || + init.step2_resp_size > 255) + return -EINVAL; + + /* Allocate response buffer */ + buf_size = init.step0_resp_size + init.step2_resp_size; + + resp = kmalloc(buf_size, GFP_KERNEL); + if (!resp) + return -ENOMEM; + + private->step0_resp_size = init.step0_resp_size; + private->step2_resp_size = init.step2_resp_size; + private->init1_opcode = init.init1_opcode; + private->init2_opcode = init.init2_opcode; + + step2_resp = resp + private->step0_resp_size; + + err = fcp_init(mixer, resp, step2_resp); + if (err < 0) + return err; + + if (copy_to_user(arg->resp, resp, buf_size)) + return -EFAULT; + + return 0; +} + +/* Check that the command is allowed + * Don't permit erasing/writing segment 0 (App_Gold) + */ +static int fcp_validate_cmd(u32 opcode, void *data, u16 size) +{ + if (opcode == FCP_USB_FLASH_ERASE) { + struct { + __le32 segment_num; + __le32 pad; + } __packed *req = data; + + if (size != sizeof(*req)) + return -EINVAL; + + if (le32_to_cpu(req->segment_num) == FCP_SEGMENT_APP_GOLD) + return -EPERM; + + if (req->pad != 0) + return -EINVAL; + + } else if (opcode == FCP_USB_FLASH_WRITE) { + struct { + __le32 segment_num; + __le32 offset; + __le32 pad; + u8 data[]; + } __packed *req = data; + + if (size < sizeof(*req)) + return -EINVAL; + + if (le32_to_cpu(req->segment_num) == FCP_SEGMENT_APP_GOLD) + return -EPERM; + + if (req->pad != 0) + return -EINVAL; + } + + return 0; +} + +/* Execute an FCP command specified by the user */ +static int fcp_ioctl_cmd(struct usb_mixer_interface *mixer, + struct fcp_cmd __user *arg) +{ + struct fcp_cmd cmd; + int err, buf_size; + void *data __free(kfree) = NULL; + + /* get opcode and request/response size */ + if (copy_from_user(&cmd, arg, sizeof(cmd))) + return -EFAULT; + + /* validate request and response sizes */ + if (cmd.req_size > 4096 || cmd.resp_size > 4096) + return -EINVAL; + + /* reinit if needed */ + err = fcp_reinit(mixer); + if (err < 0) + return err; + + /* allocate request/response buffer */ + buf_size = max(cmd.req_size, cmd.resp_size); + + if (buf_size > 0) { + data = kmalloc(buf_size, GFP_KERNEL); + if (!data) + return -ENOMEM; + } + + /* copy request from user */ + if (cmd.req_size > 0) + if (copy_from_user(data, arg->data, cmd.req_size)) + return -EFAULT; + + /* check that the command is allowed */ + err = fcp_validate_cmd(cmd.opcode, data, cmd.req_size); + if (err < 0) + return err; + + /* send request, get response */ + err = fcp_usb(mixer, cmd.opcode, + data, cmd.req_size, data, cmd.resp_size); + if (err < 0) + return err; + + /* copy response to user */ + if (cmd.resp_size > 0) + if (copy_to_user(arg->data, data, cmd.resp_size)) + return -EFAULT; + + return 0; +} + +/* Validate the Level Meter map passed by the user */ +static int validate_meter_map(const s16 *map, int map_size, int meter_slots) +{ + int i; + + for (i = 0; i < map_size; i++) + if (map[i] < -1 || map[i] >= meter_slots) + return -EINVAL; + + return 0; +} + +/* Set the Level Meter map and add the control */ +static int fcp_ioctl_set_meter_map(struct usb_mixer_interface *mixer, + struct fcp_meter_map __user *arg) +{ + struct fcp_meter_map map; + struct fcp_data *private = mixer->private_data; + s16 *tmp_map __free(kfree) = NULL; + int err; + + if (copy_from_user(&map, arg, sizeof(map))) + return -EFAULT; + + /* Don't allow changing the map size or meter slots once set */ + if (private->meter_ctl) { + struct usb_mixer_elem_info *elem = + private->meter_ctl->private_data; + + if (map.map_size != elem->channels || + map.meter_slots != private->num_meter_slots) + return -EINVAL; + } + + /* Validate the map size */ + if (map.map_size < 1 || map.map_size > 255 || + map.meter_slots < 1 || map.meter_slots > 255) + return -EINVAL; + + /* Allocate and copy the map data */ + tmp_map = kmalloc_array(map.map_size, sizeof(s16), GFP_KERNEL); + if (!tmp_map) + return -ENOMEM; + + if (copy_from_user(tmp_map, arg->map, map.map_size * sizeof(s16))) + return -EFAULT; + + err = validate_meter_map(tmp_map, map.map_size, map.meter_slots); + if (err < 0) + return err; + + /* If the control doesn't exist, create it */ + if (!private->meter_ctl) { + s16 *new_map __free(kfree) = NULL; + __le32 *meter_levels __free(kfree) = NULL; + + /* Allocate buffer for the map */ + new_map = kmalloc_array(map.map_size, sizeof(s16), GFP_KERNEL); + if (!new_map) + return -ENOMEM; + + /* Allocate buffer for reading meter levels */ + meter_levels = kmalloc_array(map.meter_slots, sizeof(__le32), + GFP_KERNEL); + if (!meter_levels) + return -ENOMEM; + + /* Create the Level Meter control */ + err = fcp_add_new_ctl(mixer, &fcp_meter_ctl, 0, map.map_size, + "Level Meter", &private->meter_ctl); + if (err < 0) + return err; + + /* Success; save the pointers in private and don't free them */ + private->meter_level_map = new_map; + private->meter_levels = meter_levels; + private->num_meter_slots = map.meter_slots; + new_map = NULL; + meter_levels = NULL; + } + + /* Install the new map */ + memcpy(private->meter_level_map, tmp_map, map.map_size * sizeof(s16)); + + return 0; +} + +/* Set the Level Meter labels */ +static int fcp_ioctl_set_meter_labels(struct usb_mixer_interface *mixer, + struct fcp_meter_labels __user *arg) +{ + struct fcp_meter_labels labels; + struct fcp_data *private = mixer->private_data; + unsigned int *tlv_data; + unsigned int tlv_size, data_size; + + if (copy_from_user(&labels, arg, sizeof(labels))) + return -EFAULT; + + /* Remove existing labels if size is zero */ + if (!labels.labels_size) { + + /* Clear TLV read/callback bits if labels were present */ + if (private->meter_labels_tlv) { + private->meter_ctl->vd[0].access &= + ~(SNDRV_CTL_ELEM_ACCESS_TLV_READ | + SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK); + snd_ctl_notify(mixer->chip->card, + SNDRV_CTL_EVENT_MASK_INFO, + &private->meter_ctl->id); + } + + kfree(private->meter_labels_tlv); + private->meter_labels_tlv = NULL; + private->meter_labels_tlv_size = 0; + + return 0; + } + + /* Validate size */ + if (labels.labels_size > 4096) + return -EINVAL; + + /* Calculate padded data size */ + data_size = ALIGN(labels.labels_size, sizeof(unsigned int)); + + /* Calculate total TLV size including header */ + tlv_size = sizeof(unsigned int) * 2 + data_size; + + /* Allocate, set up TLV header, and copy the labels data */ + tlv_data = kzalloc(tlv_size, GFP_KERNEL); + if (!tlv_data) + return -ENOMEM; + tlv_data[0] = SNDRV_CTL_TLVT_FCP_CHANNEL_LABELS; + tlv_data[1] = data_size; + if (copy_from_user(&tlv_data[2], arg->labels, labels.labels_size)) { + kfree(tlv_data); + return -EFAULT; + } + + /* Set TLV read/callback bits if labels weren't present */ + if (!private->meter_labels_tlv) { + private->meter_ctl->vd[0].access |= + SNDRV_CTL_ELEM_ACCESS_TLV_READ | + SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK; + snd_ctl_notify(mixer->chip->card, + SNDRV_CTL_EVENT_MASK_INFO, + &private->meter_ctl->id); + } + + /* Swap in the new labels */ + kfree(private->meter_labels_tlv); + private->meter_labels_tlv = tlv_data; + private->meter_labels_tlv_size = tlv_size; + + return 0; +} + +static int fcp_hwdep_open(struct snd_hwdep *hw, struct file *file) +{ + struct usb_mixer_interface *mixer = hw->private_data; + struct fcp_data *private = mixer->private_data; + + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + private->file = file; + + return 0; +} + +static int fcp_hwdep_ioctl(struct snd_hwdep *hw, struct file *file, + unsigned int cmd, unsigned long arg) +{ + struct usb_mixer_interface *mixer = hw->private_data; + struct fcp_data *private = mixer->private_data; + void __user *argp = (void __user *)arg; + + guard(mutex)(&private->mutex); + + switch (cmd) { + + case FCP_IOCTL_PVERSION: + return put_user(FCP_HWDEP_VERSION, + (int __user *)argp) ? -EFAULT : 0; + break; + + case FCP_IOCTL_INIT: + return fcp_ioctl_init(mixer, argp); + + case FCP_IOCTL_CMD: + if (!private->init) + return -EINVAL; + return fcp_ioctl_cmd(mixer, argp); + + case FCP_IOCTL_SET_METER_MAP: + if (!private->init) + return -EINVAL; + return fcp_ioctl_set_meter_map(mixer, argp); + + case FCP_IOCTL_SET_METER_LABELS: + if (!private->init) + return -EINVAL; + if (!private->meter_ctl) + return -EINVAL; + return fcp_ioctl_set_meter_labels(mixer, argp); + + default: + return -ENOIOCTLCMD; + } + + /* not reached */ +} + +static long fcp_hwdep_read(struct snd_hwdep *hw, char __user *buf, + long count, loff_t *offset) +{ + struct usb_mixer_interface *mixer = hw->private_data; + struct fcp_data *private = mixer->private_data; + unsigned long flags; + long ret = 0; + u32 event; + + if (count < sizeof(event)) + return -EINVAL; + + ret = wait_event_interruptible(private->notify.queue, + private->notify.event); + if (ret) + return ret; + + spin_lock_irqsave(&private->notify.lock, flags); + event = private->notify.event; + private->notify.event = 0; + spin_unlock_irqrestore(&private->notify.lock, flags); + + if (copy_to_user(buf, &event, sizeof(event))) + return -EFAULT; + + return sizeof(event); +} + +static __poll_t fcp_hwdep_poll(struct snd_hwdep *hw, + struct file *file, + poll_table *wait) +{ + struct usb_mixer_interface *mixer = hw->private_data; + struct fcp_data *private = mixer->private_data; + __poll_t mask = 0; + + poll_wait(file, &private->notify.queue, wait); + + if (private->notify.event) + mask |= EPOLLIN | EPOLLRDNORM; + + return mask; +} + +static int fcp_hwdep_release(struct snd_hwdep *hw, struct file *file) +{ + struct usb_mixer_interface *mixer = hw->private_data; + struct fcp_data *private = mixer->private_data; + + if (!private) + return 0; + + private->file = NULL; + + return 0; +} + +static int fcp_hwdep_init(struct usb_mixer_interface *mixer) +{ + struct snd_hwdep *hw; + int err; + + err = snd_hwdep_new(mixer->chip->card, "Focusrite Control", 0, &hw); + if (err < 0) + return err; + + hw->private_data = mixer; + hw->exclusive = 1; + hw->ops.open = fcp_hwdep_open; + hw->ops.ioctl = fcp_hwdep_ioctl; + hw->ops.ioctl_compat = fcp_hwdep_ioctl; + hw->ops.read = fcp_hwdep_read; + hw->ops.poll = fcp_hwdep_poll; + hw->ops.release = fcp_hwdep_release; + + return 0; +} + +/*** Cleanup ***/ + +static void fcp_cleanup_urb(struct usb_mixer_interface *mixer) +{ + if (!mixer->urb) + return; + + usb_kill_urb(mixer->urb); + kfree(mixer->urb->transfer_buffer); + usb_free_urb(mixer->urb); + mixer->urb = NULL; +} + +static void fcp_private_free(struct usb_mixer_interface *mixer) +{ + struct fcp_data *private = mixer->private_data; + + fcp_cleanup_urb(mixer); + + kfree(private->meter_level_map); + kfree(private->meter_levels); + kfree(private->meter_labels_tlv); + kfree(private); + mixer->private_data = NULL; +} + +static void fcp_private_suspend(struct usb_mixer_interface *mixer) +{ + fcp_cleanup_urb(mixer); +} + +/*** Callbacks ***/ + +static void fcp_notify(struct urb *urb) +{ + struct usb_mixer_interface *mixer = urb->context; + struct fcp_data *private = mixer->private_data; + int len = urb->actual_length; + int ustatus = urb->status; + u32 data; + + if (ustatus != 0 || len != 8) + goto requeue; + + data = le32_to_cpu(*(__le32 *)urb->transfer_buffer); + + /* Handle command acknowledgement */ + if (data & FCP_NOTIFY_ACK) { + complete(&private->cmd_done); + data &= ~FCP_NOTIFY_ACK; + } + + if (data) { + unsigned long flags; + + spin_lock_irqsave(&private->notify.lock, flags); + private->notify.event |= data; + spin_unlock_irqrestore(&private->notify.lock, flags); + + wake_up_interruptible(&private->notify.queue); + } + +requeue: + if (ustatus != -ENOENT && + ustatus != -ECONNRESET && + ustatus != -ESHUTDOWN) { + urb->dev = mixer->chip->dev; + usb_submit_urb(urb, GFP_ATOMIC); + } else { + complete(&private->cmd_done); + } +} + +/* Submit a URB to receive notifications from the device */ +static int fcp_init_notify(struct usb_mixer_interface *mixer) +{ + struct usb_device *dev = mixer->chip->dev; + struct fcp_data *private = mixer->private_data; + unsigned int pipe = usb_rcvintpipe(dev, private->bEndpointAddress); + void *transfer_buffer; + int err; + + /* Already set up */ + if (mixer->urb) + return 0; + + if (usb_pipe_type_check(dev, pipe)) + return -EINVAL; + + mixer->urb = usb_alloc_urb(0, GFP_KERNEL); + if (!mixer->urb) + return -ENOMEM; + + transfer_buffer = kmalloc(private->wMaxPacketSize, GFP_KERNEL); + if (!transfer_buffer) { + usb_free_urb(mixer->urb); + mixer->urb = NULL; + return -ENOMEM; + } + + usb_fill_int_urb(mixer->urb, dev, pipe, + transfer_buffer, private->wMaxPacketSize, + fcp_notify, mixer, private->bInterval); + + init_completion(&private->cmd_done); + + err = usb_submit_urb(mixer->urb, GFP_KERNEL); + if (err) { + usb_audio_err(mixer->chip, + "%s: usb_submit_urb failed: %d\n", + __func__, err); + kfree(transfer_buffer); + usb_free_urb(mixer->urb); + mixer->urb = NULL; + } + + return err; +} + +/*** Initialisation ***/ + +static int fcp_init(struct usb_mixer_interface *mixer, + void *step0_resp, void *step2_resp) +{ + struct fcp_data *private = mixer->private_data; + struct usb_device *dev = mixer->chip->dev; + int err; + + err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), + FCP_USB_REQ_STEP0, + USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN, + 0, private->bInterfaceNumber, + step0_resp, private->step0_resp_size); + if (err < 0) + return err; + + err = fcp_init_notify(mixer); + if (err < 0) + return err; + + private->seq = 0; + private->init = 1; + + err = fcp_usb(mixer, private->init1_opcode, NULL, 0, NULL, 0); + if (err < 0) + return err; + + err = fcp_usb(mixer, private->init2_opcode, + NULL, 0, step2_resp, private->step2_resp_size); + if (err < 0) + return err; + + return 0; +} + +static int fcp_init_private(struct usb_mixer_interface *mixer) +{ + struct fcp_data *private = + kzalloc(sizeof(struct fcp_data), GFP_KERNEL); + + if (!private) + return -ENOMEM; + + mutex_init(&private->mutex); + init_waitqueue_head(&private->notify.queue); + spin_lock_init(&private->notify.lock); + + mixer->private_data = private; + mixer->private_free = fcp_private_free; + mixer->private_suspend = fcp_private_suspend; + + private->mixer = mixer; + + return 0; +} + +/* Look through the interface descriptors for the Focusrite Control + * interface (bInterfaceClass = 255 Vendor Specific Class) and set + * bInterfaceNumber, bEndpointAddress, wMaxPacketSize, and bInterval + * in private + */ +static int fcp_find_fc_interface(struct usb_mixer_interface *mixer) +{ + struct snd_usb_audio *chip = mixer->chip; + struct fcp_data *private = mixer->private_data; + struct usb_host_config *config = chip->dev->actconfig; + int i; + + for (i = 0; i < config->desc.bNumInterfaces; i++) { + struct usb_interface *intf = config->interface[i]; + struct usb_interface_descriptor *desc = + &intf->altsetting[0].desc; + struct usb_endpoint_descriptor *epd; + + if (desc->bInterfaceClass != 255) + continue; + + epd = get_endpoint(intf->altsetting, 0); + private->bInterfaceNumber = desc->bInterfaceNumber; + private->bEndpointAddress = epd->bEndpointAddress & + USB_ENDPOINT_NUMBER_MASK; + private->wMaxPacketSize = le16_to_cpu(epd->wMaxPacketSize); + private->bInterval = epd->bInterval; + return 0; + } + + usb_audio_err(chip, "Focusrite vendor-specific interface not found\n"); + return -EINVAL; +} + +int snd_fcp_init(struct usb_mixer_interface *mixer) +{ + struct snd_usb_audio *chip = mixer->chip; + int err; + + /* only use UAC_VERSION_2 */ + if (!mixer->protocol) + return 0; + + err = fcp_init_private(mixer); + if (err < 0) + return err; + + err = fcp_find_fc_interface(mixer); + if (err < 0) + return err; + + err = fcp_hwdep_init(mixer); + if (err < 0) + return err; + + usb_audio_info(chip, + "Focusrite Control Protocol Driver ready (pid=0x%04x); " + "report any issues to " + "https://github.com/geoffreybennett/fcp-support/issues", + USB_ID_PRODUCT(chip->usb_id)); + + return err; +} diff --git a/sound/usb/fcp.h b/sound/usb/fcp.h new file mode 100644 index 000000000000..d58cc7db75b1 --- /dev/null +++ b/sound/usb/fcp.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __USBAUDIO_FCP_H +#define __USBAUDIO_FCP_H + +int snd_fcp_init(struct usb_mixer_interface *mixer); + +#endif /* __USBAUDIO_FCP_H */ diff --git a/sound/usb/line6/toneport.c b/sound/usb/line6/toneport.c index ca2c6f5de407..c073b38cd673 100644 --- a/sound/usb/line6/toneport.c +++ b/sound/usb/line6/toneport.c @@ -386,7 +386,7 @@ static int toneport_setup(struct usb_line6_toneport *toneport) toneport_update_led(toneport); schedule_delayed_work(&toneport->line6.startup_work, - msecs_to_jiffies(TONEPORT_PCM_DELAY * 1000)); + secs_to_jiffies(TONEPORT_PCM_DELAY)); return 0; } diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 23fcd680167d..ed6127b0389f 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -38,6 +38,7 @@ #include "mixer_us16x08.h" #include "mixer_s1810c.h" #include "helper.h" +#include "fcp.h" struct std_mono_table { unsigned int unitid, control, cmask; @@ -4090,6 +4091,12 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer) err = snd_scarlett2_init(mixer); break; + case USB_ID(0x1235, 0x821b): /* Focusrite Scarlett 16i16 4th Gen */ + case USB_ID(0x1235, 0x821c): /* Focusrite Scarlett 18i16 4th Gen */ + case USB_ID(0x1235, 0x821d): /* Focusrite Scarlett 18i20 4th Gen */ + err = snd_fcp_init(mixer); + break; + case USB_ID(0x041e, 0x323b): /* Creative Sound Blaster E1 */ err = snd_soundblaster_e1_switch_create(mixer); break; diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index 7f595c1752a5..288d22e6a0b2 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -166,6 +166,7 @@ #include "helper.h" #include "mixer_scarlett2.h" +#include "fcp.h" /* device_setup value to allow turning MSD mode back on */ #define SCARLETT2_MSD_ENABLE 0x02 @@ -173,6 +174,9 @@ /* device_setup value to disable this mixer driver */ #define SCARLETT2_DISABLE 0x04 +/* device_setup value to use the FCP driver instead */ +#define SCARLETT2_USE_FCP_DRIVER 0x08 + /* some gui mixers can't handle negative ctl values */ #define SCARLETT2_VOLUME_BIAS 127 @@ -9702,6 +9706,10 @@ int snd_scarlett2_init(struct usb_mixer_interface *mixer) if (!mixer->protocol) return 0; + /* check if the user wants to use the FCP driver instead */ + if (chip->setup & SCARLETT2_USE_FCP_DRIVER) + return snd_fcp_init(mixer); + /* find entry in scarlett2_devices */ entry = get_scarlett2_device_entry(mixer); if (!entry) { diff --git a/sound/usb/mixer_us16x08.c b/sound/usb/mixer_us16x08.c index 6eb7d93b358d..20ac32635f1f 100644 --- a/sound/usb/mixer_us16x08.c +++ b/sound/usb/mixer_us16x08.c @@ -687,7 +687,7 @@ static int snd_us16x08_meter_get(struct snd_kcontrol *kcontrol, struct usb_mixer_elem_info *elem = kcontrol->private_data; struct snd_usb_audio *chip = elem->head.mixer->chip; struct snd_us16x08_meter_store *store = elem->private_data; - u8 meter_urb[64]; + u8 meter_urb[64] = {0}; switch (kcontrol->private_value) { case 0: { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 8ba0aff8be2e..a97efb7b131e 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2239,6 +2239,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x0c45, 0x6340, /* Sonix HD USB Camera */ QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x0d8c, 0x0014, /* USB Audio Device */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */ @@ -2341,6 +2343,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */ QUIRK_FLAG_CTL_MSG_DELAY_1M), + DEVICE_FLG(0x2fc6, 0xf0b7, /* iBasso DC07 Pro */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */ diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 1334214546d7..100ad3dc091a 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -192,60 +192,77 @@ static int get_family_id(int sd) } #define average_ms(t, c) (t / 1000000ULL / (c ? c : 1)) +#define delay_ms(t) (t / 1000000ULL) static void print_delayacct(struct taskstats *t) { - printf("\n\nCPU %15s%15s%15s%15s%15s\n" - " %15llu%15llu%15llu%15llu%15.3fms\n" - "IO %15s%15s%15s\n" - " %15llu%15llu%15.3fms\n" - "SWAP %15s%15s%15s\n" - " %15llu%15llu%15.3fms\n" - "RECLAIM %12s%15s%15s\n" - " %15llu%15llu%15.3fms\n" - "THRASHING%12s%15s%15s\n" - " %15llu%15llu%15.3fms\n" - "COMPACT %12s%15s%15s\n" - " %15llu%15llu%15.3fms\n" - "WPCOPY %12s%15s%15s\n" - " %15llu%15llu%15.3fms\n" - "IRQ %15s%15s%15s\n" - " %15llu%15llu%15.3fms\n", + printf("\n\nCPU %15s%15s%15s%15s%15s%15s\n" + " %15llu%15llu%15llu%15llu%15.3fms%13.6fms\n" + "IO %15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms\n" + "SWAP %15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms\n" + "RECLAIM %12s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms\n" + "THRASHING%12s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms\n" + "COMPACT %12s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms\n" + "WPCOPY %12s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms\n" + "IRQ %15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms\n", "count", "real total", "virtual total", - "delay total", "delay average", + "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->cpu_count, (unsigned long long)t->cpu_run_real_total, (unsigned long long)t->cpu_run_virtual_total, (unsigned long long)t->cpu_delay_total, average_ms((double)t->cpu_delay_total, t->cpu_count), - "count", "delay total", "delay average", + delay_ms((double)t->cpu_delay_max), + delay_ms((double)t->cpu_delay_min), + "count", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->blkio_count, (unsigned long long)t->blkio_delay_total, average_ms((double)t->blkio_delay_total, t->blkio_count), - "count", "delay total", "delay average", + delay_ms((double)t->blkio_delay_max), + delay_ms((double)t->blkio_delay_min), + "count", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->swapin_count, (unsigned long long)t->swapin_delay_total, average_ms((double)t->swapin_delay_total, t->swapin_count), - "count", "delay total", "delay average", + delay_ms((double)t->swapin_delay_max), + delay_ms((double)t->swapin_delay_min), + "count", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->freepages_count, (unsigned long long)t->freepages_delay_total, average_ms((double)t->freepages_delay_total, t->freepages_count), - "count", "delay total", "delay average", + delay_ms((double)t->freepages_delay_max), + delay_ms((double)t->freepages_delay_min), + "count", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->thrashing_count, (unsigned long long)t->thrashing_delay_total, average_ms((double)t->thrashing_delay_total, t->thrashing_count), - "count", "delay total", "delay average", + delay_ms((double)t->thrashing_delay_max), + delay_ms((double)t->thrashing_delay_min), + "count", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->compact_count, (unsigned long long)t->compact_delay_total, average_ms((double)t->compact_delay_total, t->compact_count), - "count", "delay total", "delay average", + delay_ms((double)t->compact_delay_max), + delay_ms((double)t->compact_delay_min), + "count", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->wpcopy_count, (unsigned long long)t->wpcopy_delay_total, average_ms((double)t->wpcopy_delay_total, t->wpcopy_count), - "count", "delay total", "delay average", + delay_ms((double)t->wpcopy_delay_max), + delay_ms((double)t->wpcopy_delay_min), + "count", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->irq_count, (unsigned long long)t->irq_delay_total, - average_ms((double)t->irq_delay_total, t->irq_count)); + average_ms((double)t->irq_delay_total, t->irq_count), + delay_ms((double)t->irq_delay_max), + delay_ms((double)t->irq_delay_min)); } static void task_context_switch_counts(struct taskstats *t) diff --git a/tools/accounting/procacct.c b/tools/accounting/procacct.c index 90c4a37f53d9..e8dee05a6264 100644 --- a/tools/accounting/procacct.c +++ b/tools/accounting/procacct.c @@ -274,12 +274,11 @@ int main(int argc, char *argv[]) int maskset = 0; char *logfile = NULL; int cfd = 0; - int forking = 0; struct msgtemplate msg; - while (!forking) { - c = getopt(argc, argv, "m:vr:"); + while (1) { + c = getopt(argc, argv, "m:vr:w:"); if (c < 0) break; diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h index cd8420e8c3ad..150416682e2c 100644 --- a/tools/arch/arm64/include/asm/sysreg.h +++ b/tools/arch/arm64/include/asm/sysreg.h @@ -11,6 +11,7 @@ #include <linux/bits.h> #include <linux/stringify.h> +#include <linux/kasan-tags.h> #include <asm/gpr-num.h> @@ -108,6 +109,9 @@ #define set_pstate_ssbs(x) asm volatile(SET_PSTATE_SSBS(x)) #define set_pstate_dit(x) asm volatile(SET_PSTATE_DIT(x)) +/* Register-based PAN access, for save/restore purposes */ +#define SYS_PSTATE_PAN sys_reg(3, 0, 4, 2, 3) + #define __SYS_BARRIER_INSN(CRm, op2, Rt) \ __emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f)) @@ -123,6 +127,37 @@ #define SYS_DC_CIGSW sys_insn(1, 0, 7, 14, 4) #define SYS_DC_CIGDSW sys_insn(1, 0, 7, 14, 6) +#define SYS_IC_IALLUIS sys_insn(1, 0, 7, 1, 0) +#define SYS_IC_IALLU sys_insn(1, 0, 7, 5, 0) +#define SYS_IC_IVAU sys_insn(1, 3, 7, 5, 1) + +#define SYS_DC_IVAC sys_insn(1, 0, 7, 6, 1) +#define SYS_DC_IGVAC sys_insn(1, 0, 7, 6, 3) +#define SYS_DC_IGDVAC sys_insn(1, 0, 7, 6, 5) + +#define SYS_DC_CVAC sys_insn(1, 3, 7, 10, 1) +#define SYS_DC_CGVAC sys_insn(1, 3, 7, 10, 3) +#define SYS_DC_CGDVAC sys_insn(1, 3, 7, 10, 5) + +#define SYS_DC_CVAU sys_insn(1, 3, 7, 11, 1) + +#define SYS_DC_CVAP sys_insn(1, 3, 7, 12, 1) +#define SYS_DC_CGVAP sys_insn(1, 3, 7, 12, 3) +#define SYS_DC_CGDVAP sys_insn(1, 3, 7, 12, 5) + +#define SYS_DC_CVADP sys_insn(1, 3, 7, 13, 1) +#define SYS_DC_CGVADP sys_insn(1, 3, 7, 13, 3) +#define SYS_DC_CGDVADP sys_insn(1, 3, 7, 13, 5) + +#define SYS_DC_CIVAC sys_insn(1, 3, 7, 14, 1) +#define SYS_DC_CIGVAC sys_insn(1, 3, 7, 14, 3) +#define SYS_DC_CIGDVAC sys_insn(1, 3, 7, 14, 5) + +/* Data cache zero operations */ +#define SYS_DC_ZVA sys_insn(1, 3, 7, 4, 1) +#define SYS_DC_GVA sys_insn(1, 3, 7, 4, 3) +#define SYS_DC_GZVA sys_insn(1, 3, 7, 4, 4) + /* * Automatically generated definitions for system registers, the * manual encodings below are in the process of being converted to @@ -162,6 +197,84 @@ #define SYS_DBGDTRTX_EL0 sys_reg(2, 3, 0, 5, 0) #define SYS_DBGVCR32_EL2 sys_reg(2, 4, 0, 7, 0) +#define SYS_BRBINF_EL1(n) sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 0)) +#define SYS_BRBINFINJ_EL1 sys_reg(2, 1, 9, 1, 0) +#define SYS_BRBSRC_EL1(n) sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 1)) +#define SYS_BRBSRCINJ_EL1 sys_reg(2, 1, 9, 1, 1) +#define SYS_BRBTGT_EL1(n) sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 2)) +#define SYS_BRBTGTINJ_EL1 sys_reg(2, 1, 9, 1, 2) +#define SYS_BRBTS_EL1 sys_reg(2, 1, 9, 0, 2) + +#define SYS_BRBCR_EL1 sys_reg(2, 1, 9, 0, 0) +#define SYS_BRBFCR_EL1 sys_reg(2, 1, 9, 0, 1) +#define SYS_BRBIDR0_EL1 sys_reg(2, 1, 9, 2, 0) + +#define SYS_TRCITECR_EL1 sys_reg(3, 0, 1, 2, 3) +#define SYS_TRCACATR(m) sys_reg(2, 1, 2, ((m & 7) << 1), (2 | (m >> 3))) +#define SYS_TRCACVR(m) sys_reg(2, 1, 2, ((m & 7) << 1), (0 | (m >> 3))) +#define SYS_TRCAUTHSTATUS sys_reg(2, 1, 7, 14, 6) +#define SYS_TRCAUXCTLR sys_reg(2, 1, 0, 6, 0) +#define SYS_TRCBBCTLR sys_reg(2, 1, 0, 15, 0) +#define SYS_TRCCCCTLR sys_reg(2, 1, 0, 14, 0) +#define SYS_TRCCIDCCTLR0 sys_reg(2, 1, 3, 0, 2) +#define SYS_TRCCIDCCTLR1 sys_reg(2, 1, 3, 1, 2) +#define SYS_TRCCIDCVR(m) sys_reg(2, 1, 3, ((m & 7) << 1), 0) +#define SYS_TRCCLAIMCLR sys_reg(2, 1, 7, 9, 6) +#define SYS_TRCCLAIMSET sys_reg(2, 1, 7, 8, 6) +#define SYS_TRCCNTCTLR(m) sys_reg(2, 1, 0, (4 | (m & 3)), 5) +#define SYS_TRCCNTRLDVR(m) sys_reg(2, 1, 0, (0 | (m & 3)), 5) +#define SYS_TRCCNTVR(m) sys_reg(2, 1, 0, (8 | (m & 3)), 5) +#define SYS_TRCCONFIGR sys_reg(2, 1, 0, 4, 0) +#define SYS_TRCDEVARCH sys_reg(2, 1, 7, 15, 6) +#define SYS_TRCDEVID sys_reg(2, 1, 7, 2, 7) +#define SYS_TRCEVENTCTL0R sys_reg(2, 1, 0, 8, 0) +#define SYS_TRCEVENTCTL1R sys_reg(2, 1, 0, 9, 0) +#define SYS_TRCEXTINSELR(m) sys_reg(2, 1, 0, (8 | (m & 3)), 4) +#define SYS_TRCIDR0 sys_reg(2, 1, 0, 8, 7) +#define SYS_TRCIDR10 sys_reg(2, 1, 0, 2, 6) +#define SYS_TRCIDR11 sys_reg(2, 1, 0, 3, 6) +#define SYS_TRCIDR12 sys_reg(2, 1, 0, 4, 6) +#define SYS_TRCIDR13 sys_reg(2, 1, 0, 5, 6) +#define SYS_TRCIDR1 sys_reg(2, 1, 0, 9, 7) +#define SYS_TRCIDR2 sys_reg(2, 1, 0, 10, 7) +#define SYS_TRCIDR3 sys_reg(2, 1, 0, 11, 7) +#define SYS_TRCIDR4 sys_reg(2, 1, 0, 12, 7) +#define SYS_TRCIDR5 sys_reg(2, 1, 0, 13, 7) +#define SYS_TRCIDR6 sys_reg(2, 1, 0, 14, 7) +#define SYS_TRCIDR7 sys_reg(2, 1, 0, 15, 7) +#define SYS_TRCIDR8 sys_reg(2, 1, 0, 0, 6) +#define SYS_TRCIDR9 sys_reg(2, 1, 0, 1, 6) +#define SYS_TRCIMSPEC(m) sys_reg(2, 1, 0, (m & 7), 7) +#define SYS_TRCITEEDCR sys_reg(2, 1, 0, 2, 1) +#define SYS_TRCOSLSR sys_reg(2, 1, 1, 1, 4) +#define SYS_TRCPRGCTLR sys_reg(2, 1, 0, 1, 0) +#define SYS_TRCQCTLR sys_reg(2, 1, 0, 1, 1) +#define SYS_TRCRSCTLR(m) sys_reg(2, 1, 1, (m & 15), (0 | (m >> 4))) +#define SYS_TRCRSR sys_reg(2, 1, 0, 10, 0) +#define SYS_TRCSEQEVR(m) sys_reg(2, 1, 0, (m & 3), 4) +#define SYS_TRCSEQRSTEVR sys_reg(2, 1, 0, 6, 4) +#define SYS_TRCSEQSTR sys_reg(2, 1, 0, 7, 4) +#define SYS_TRCSSCCR(m) sys_reg(2, 1, 1, (m & 7), 2) +#define SYS_TRCSSCSR(m) sys_reg(2, 1, 1, (8 | (m & 7)), 2) +#define SYS_TRCSSPCICR(m) sys_reg(2, 1, 1, (m & 7), 3) +#define SYS_TRCSTALLCTLR sys_reg(2, 1, 0, 11, 0) +#define SYS_TRCSTATR sys_reg(2, 1, 0, 3, 0) +#define SYS_TRCSYNCPR sys_reg(2, 1, 0, 13, 0) +#define SYS_TRCTRACEIDR sys_reg(2, 1, 0, 0, 1) +#define SYS_TRCTSCTLR sys_reg(2, 1, 0, 12, 0) +#define SYS_TRCVICTLR sys_reg(2, 1, 0, 0, 2) +#define SYS_TRCVIIECTLR sys_reg(2, 1, 0, 1, 2) +#define SYS_TRCVIPCSSCTLR sys_reg(2, 1, 0, 3, 2) +#define SYS_TRCVISSCTLR sys_reg(2, 1, 0, 2, 2) +#define SYS_TRCVMIDCCTLR0 sys_reg(2, 1, 3, 2, 2) +#define SYS_TRCVMIDCCTLR1 sys_reg(2, 1, 3, 3, 2) +#define SYS_TRCVMIDCVR(m) sys_reg(2, 1, 3, ((m & 7) << 1), 1) + +/* ETM */ +#define SYS_TRCOSLAR sys_reg(2, 1, 1, 0, 4) + +#define SYS_BRBCR_EL2 sys_reg(2, 4, 9, 0, 0) + #define SYS_MIDR_EL1 sys_reg(3, 0, 0, 0, 0) #define SYS_MPIDR_EL1 sys_reg(3, 0, 0, 0, 5) #define SYS_REVIDR_EL1 sys_reg(3, 0, 0, 0, 6) @@ -170,8 +283,6 @@ #define SYS_RGSR_EL1 sys_reg(3, 0, 1, 0, 5) #define SYS_GCR_EL1 sys_reg(3, 0, 1, 0, 6) -#define SYS_TRFCR_EL1 sys_reg(3, 0, 1, 2, 1) - #define SYS_TCR_EL1 sys_reg(3, 0, 2, 0, 2) #define SYS_APIAKEYLO_EL1 sys_reg(3, 0, 2, 1, 0) @@ -202,15 +313,38 @@ #define SYS_ERXCTLR_EL1 sys_reg(3, 0, 5, 4, 1) #define SYS_ERXSTATUS_EL1 sys_reg(3, 0, 5, 4, 2) #define SYS_ERXADDR_EL1 sys_reg(3, 0, 5, 4, 3) +#define SYS_ERXPFGF_EL1 sys_reg(3, 0, 5, 4, 4) +#define SYS_ERXPFGCTL_EL1 sys_reg(3, 0, 5, 4, 5) +#define SYS_ERXPFGCDN_EL1 sys_reg(3, 0, 5, 4, 6) #define SYS_ERXMISC0_EL1 sys_reg(3, 0, 5, 5, 0) #define SYS_ERXMISC1_EL1 sys_reg(3, 0, 5, 5, 1) +#define SYS_ERXMISC2_EL1 sys_reg(3, 0, 5, 5, 2) +#define SYS_ERXMISC3_EL1 sys_reg(3, 0, 5, 5, 3) #define SYS_TFSR_EL1 sys_reg(3, 0, 5, 6, 0) #define SYS_TFSRE0_EL1 sys_reg(3, 0, 5, 6, 1) #define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0) #define SYS_PAR_EL1_F BIT(0) +/* When PAR_EL1.F == 1 */ #define SYS_PAR_EL1_FST GENMASK(6, 1) +#define SYS_PAR_EL1_PTW BIT(8) +#define SYS_PAR_EL1_S BIT(9) +#define SYS_PAR_EL1_AssuredOnly BIT(12) +#define SYS_PAR_EL1_TopLevel BIT(13) +#define SYS_PAR_EL1_Overlay BIT(14) +#define SYS_PAR_EL1_DirtyBit BIT(15) +#define SYS_PAR_EL1_F1_IMPDEF GENMASK_ULL(63, 48) +#define SYS_PAR_EL1_F1_RES0 (BIT(7) | BIT(10) | GENMASK_ULL(47, 16)) +#define SYS_PAR_EL1_RES1 BIT(11) +/* When PAR_EL1.F == 0 */ +#define SYS_PAR_EL1_SH GENMASK_ULL(8, 7) +#define SYS_PAR_EL1_NS BIT(9) +#define SYS_PAR_EL1_F0_IMPDEF BIT(10) +#define SYS_PAR_EL1_NSE BIT(11) +#define SYS_PAR_EL1_PA GENMASK_ULL(51, 12) +#define SYS_PAR_EL1_ATTR GENMASK_ULL(63, 56) +#define SYS_PAR_EL1_F0_RES0 (GENMASK_ULL(6, 1) | GENMASK_ULL(55, 52)) /*** Statistical Profiling Extension ***/ #define PMSEVFR_EL1_RES0_IMP \ @@ -274,6 +408,8 @@ #define SYS_ICC_IGRPEN0_EL1 sys_reg(3, 0, 12, 12, 6) #define SYS_ICC_IGRPEN1_EL1 sys_reg(3, 0, 12, 12, 7) +#define SYS_ACCDATA_EL1 sys_reg(3, 0, 13, 0, 5) + #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0) #define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7) @@ -286,7 +422,6 @@ #define SYS_PMCNTENCLR_EL0 sys_reg(3, 3, 9, 12, 2) #define SYS_PMOVSCLR_EL0 sys_reg(3, 3, 9, 12, 3) #define SYS_PMSWINC_EL0 sys_reg(3, 3, 9, 12, 4) -#define SYS_PMSELR_EL0 sys_reg(3, 3, 9, 12, 5) #define SYS_PMCEID0_EL0 sys_reg(3, 3, 9, 12, 6) #define SYS_PMCEID1_EL0 sys_reg(3, 3, 9, 12, 7) #define SYS_PMCCNTR_EL0 sys_reg(3, 3, 9, 13, 0) @@ -369,6 +504,7 @@ #define SYS_SCTLR_EL2 sys_reg(3, 4, 1, 0, 0) #define SYS_ACTLR_EL2 sys_reg(3, 4, 1, 0, 1) +#define SYS_SCTLR2_EL2 sys_reg(3, 4, 1, 0, 3) #define SYS_HCR_EL2 sys_reg(3, 4, 1, 1, 0) #define SYS_MDCR_EL2 sys_reg(3, 4, 1, 1, 1) #define SYS_CPTR_EL2 sys_reg(3, 4, 1, 1, 2) @@ -381,13 +517,15 @@ #define SYS_VTTBR_EL2 sys_reg(3, 4, 2, 1, 0) #define SYS_VTCR_EL2 sys_reg(3, 4, 2, 1, 2) -#define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) -#define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4) -#define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5) +#define SYS_VNCR_EL2 sys_reg(3, 4, 2, 2, 0) #define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6) #define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0) #define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1) #define SYS_SP_EL1 sys_reg(3, 4, 4, 1, 0) +#define SYS_SPSR_irq sys_reg(3, 4, 4, 3, 0) +#define SYS_SPSR_abt sys_reg(3, 4, 4, 3, 1) +#define SYS_SPSR_und sys_reg(3, 4, 4, 3, 2) +#define SYS_SPSR_fiq sys_reg(3, 4, 4, 3, 3) #define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1) #define SYS_AFSR0_EL2 sys_reg(3, 4, 5, 1, 0) #define SYS_AFSR1_EL2 sys_reg(3, 4, 5, 1, 1) @@ -449,24 +587,49 @@ #define SYS_CONTEXTIDR_EL2 sys_reg(3, 4, 13, 0, 1) #define SYS_TPIDR_EL2 sys_reg(3, 4, 13, 0, 2) +#define SYS_SCXTNUM_EL2 sys_reg(3, 4, 13, 0, 7) + +#define __AMEV_op2(m) (m & 0x7) +#define __AMEV_CRm(n, m) (n | ((m & 0x8) >> 3)) +#define __SYS__AMEVCNTVOFF0n_EL2(m) sys_reg(3, 4, 13, __AMEV_CRm(0x8, m), __AMEV_op2(m)) +#define SYS_AMEVCNTVOFF0n_EL2(m) __SYS__AMEVCNTVOFF0n_EL2(m) +#define __SYS__AMEVCNTVOFF1n_EL2(m) sys_reg(3, 4, 13, __AMEV_CRm(0xA, m), __AMEV_op2(m)) +#define SYS_AMEVCNTVOFF1n_EL2(m) __SYS__AMEVCNTVOFF1n_EL2(m) #define SYS_CNTVOFF_EL2 sys_reg(3, 4, 14, 0, 3) #define SYS_CNTHCTL_EL2 sys_reg(3, 4, 14, 1, 0) +#define SYS_CNTHP_TVAL_EL2 sys_reg(3, 4, 14, 2, 0) +#define SYS_CNTHP_CTL_EL2 sys_reg(3, 4, 14, 2, 1) +#define SYS_CNTHP_CVAL_EL2 sys_reg(3, 4, 14, 2, 2) +#define SYS_CNTHV_TVAL_EL2 sys_reg(3, 4, 14, 3, 0) +#define SYS_CNTHV_CTL_EL2 sys_reg(3, 4, 14, 3, 1) +#define SYS_CNTHV_CVAL_EL2 sys_reg(3, 4, 14, 3, 2) /* VHE encodings for architectural EL0/1 system registers */ +#define SYS_BRBCR_EL12 sys_reg(2, 5, 9, 0, 0) #define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0) +#define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2) +#define SYS_SCTLR2_EL12 sys_reg(3, 5, 1, 0, 3) +#define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0) +#define SYS_TRFCR_EL12 sys_reg(3, 5, 1, 2, 1) +#define SYS_SMCR_EL12 sys_reg(3, 5, 1, 2, 6) #define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0) #define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1) #define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2) +#define SYS_TCR2_EL12 sys_reg(3, 5, 2, 0, 3) #define SYS_SPSR_EL12 sys_reg(3, 5, 4, 0, 0) #define SYS_ELR_EL12 sys_reg(3, 5, 4, 0, 1) #define SYS_AFSR0_EL12 sys_reg(3, 5, 5, 1, 0) #define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1) #define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0) #define SYS_TFSR_EL12 sys_reg(3, 5, 5, 6, 0) +#define SYS_FAR_EL12 sys_reg(3, 5, 6, 0, 0) +#define SYS_PMSCR_EL12 sys_reg(3, 5, 9, 9, 0) #define SYS_MAIR_EL12 sys_reg(3, 5, 10, 2, 0) #define SYS_AMAIR_EL12 sys_reg(3, 5, 10, 3, 0) #define SYS_VBAR_EL12 sys_reg(3, 5, 12, 0, 0) +#define SYS_CONTEXTIDR_EL12 sys_reg(3, 5, 13, 0, 1) +#define SYS_SCXTNUM_EL12 sys_reg(3, 5, 13, 0, 7) #define SYS_CNTKCTL_EL12 sys_reg(3, 5, 14, 1, 0) #define SYS_CNTP_TVAL_EL02 sys_reg(3, 5, 14, 2, 0) #define SYS_CNTP_CTL_EL02 sys_reg(3, 5, 14, 2, 1) @@ -477,6 +640,183 @@ #define SYS_SP_EL2 sys_reg(3, 6, 4, 1, 0) +/* AT instructions */ +#define AT_Op0 1 +#define AT_CRn 7 + +#define OP_AT_S1E1R sys_insn(AT_Op0, 0, AT_CRn, 8, 0) +#define OP_AT_S1E1W sys_insn(AT_Op0, 0, AT_CRn, 8, 1) +#define OP_AT_S1E0R sys_insn(AT_Op0, 0, AT_CRn, 8, 2) +#define OP_AT_S1E0W sys_insn(AT_Op0, 0, AT_CRn, 8, 3) +#define OP_AT_S1E1RP sys_insn(AT_Op0, 0, AT_CRn, 9, 0) +#define OP_AT_S1E1WP sys_insn(AT_Op0, 0, AT_CRn, 9, 1) +#define OP_AT_S1E1A sys_insn(AT_Op0, 0, AT_CRn, 9, 2) +#define OP_AT_S1E2R sys_insn(AT_Op0, 4, AT_CRn, 8, 0) +#define OP_AT_S1E2W sys_insn(AT_Op0, 4, AT_CRn, 8, 1) +#define OP_AT_S12E1R sys_insn(AT_Op0, 4, AT_CRn, 8, 4) +#define OP_AT_S12E1W sys_insn(AT_Op0, 4, AT_CRn, 8, 5) +#define OP_AT_S12E0R sys_insn(AT_Op0, 4, AT_CRn, 8, 6) +#define OP_AT_S12E0W sys_insn(AT_Op0, 4, AT_CRn, 8, 7) +#define OP_AT_S1E2A sys_insn(AT_Op0, 4, AT_CRn, 9, 2) + +/* TLBI instructions */ +#define TLBI_Op0 1 + +#define TLBI_Op1_EL1 0 /* Accessible from EL1 or higher */ +#define TLBI_Op1_EL2 4 /* Accessible from EL2 or higher */ + +#define TLBI_CRn_XS 8 /* Extra Slow (the common one) */ +#define TLBI_CRn_nXS 9 /* not Extra Slow (which nobody uses)*/ + +#define TLBI_CRm_IPAIS 0 /* S2 Inner-Shareable */ +#define TLBI_CRm_nROS 1 /* non-Range, Outer-Sharable */ +#define TLBI_CRm_RIS 2 /* Range, Inner-Sharable */ +#define TLBI_CRm_nRIS 3 /* non-Range, Inner-Sharable */ +#define TLBI_CRm_IPAONS 4 /* S2 Outer and Non-Shareable */ +#define TLBI_CRm_ROS 5 /* Range, Outer-Sharable */ +#define TLBI_CRm_RNS 6 /* Range, Non-Sharable */ +#define TLBI_CRm_nRNS 7 /* non-Range, Non-Sharable */ + +#define OP_TLBI_VMALLE1OS sys_insn(1, 0, 8, 1, 0) +#define OP_TLBI_VAE1OS sys_insn(1, 0, 8, 1, 1) +#define OP_TLBI_ASIDE1OS sys_insn(1, 0, 8, 1, 2) +#define OP_TLBI_VAAE1OS sys_insn(1, 0, 8, 1, 3) +#define OP_TLBI_VALE1OS sys_insn(1, 0, 8, 1, 5) +#define OP_TLBI_VAALE1OS sys_insn(1, 0, 8, 1, 7) +#define OP_TLBI_RVAE1IS sys_insn(1, 0, 8, 2, 1) +#define OP_TLBI_RVAAE1IS sys_insn(1, 0, 8, 2, 3) +#define OP_TLBI_RVALE1IS sys_insn(1, 0, 8, 2, 5) +#define OP_TLBI_RVAALE1IS sys_insn(1, 0, 8, 2, 7) +#define OP_TLBI_VMALLE1IS sys_insn(1, 0, 8, 3, 0) +#define OP_TLBI_VAE1IS sys_insn(1, 0, 8, 3, 1) +#define OP_TLBI_ASIDE1IS sys_insn(1, 0, 8, 3, 2) +#define OP_TLBI_VAAE1IS sys_insn(1, 0, 8, 3, 3) +#define OP_TLBI_VALE1IS sys_insn(1, 0, 8, 3, 5) +#define OP_TLBI_VAALE1IS sys_insn(1, 0, 8, 3, 7) +#define OP_TLBI_RVAE1OS sys_insn(1, 0, 8, 5, 1) +#define OP_TLBI_RVAAE1OS sys_insn(1, 0, 8, 5, 3) +#define OP_TLBI_RVALE1OS sys_insn(1, 0, 8, 5, 5) +#define OP_TLBI_RVAALE1OS sys_insn(1, 0, 8, 5, 7) +#define OP_TLBI_RVAE1 sys_insn(1, 0, 8, 6, 1) +#define OP_TLBI_RVAAE1 sys_insn(1, 0, 8, 6, 3) +#define OP_TLBI_RVALE1 sys_insn(1, 0, 8, 6, 5) +#define OP_TLBI_RVAALE1 sys_insn(1, 0, 8, 6, 7) +#define OP_TLBI_VMALLE1 sys_insn(1, 0, 8, 7, 0) +#define OP_TLBI_VAE1 sys_insn(1, 0, 8, 7, 1) +#define OP_TLBI_ASIDE1 sys_insn(1, 0, 8, 7, 2) +#define OP_TLBI_VAAE1 sys_insn(1, 0, 8, 7, 3) +#define OP_TLBI_VALE1 sys_insn(1, 0, 8, 7, 5) +#define OP_TLBI_VAALE1 sys_insn(1, 0, 8, 7, 7) +#define OP_TLBI_VMALLE1OSNXS sys_insn(1, 0, 9, 1, 0) +#define OP_TLBI_VAE1OSNXS sys_insn(1, 0, 9, 1, 1) +#define OP_TLBI_ASIDE1OSNXS sys_insn(1, 0, 9, 1, 2) +#define OP_TLBI_VAAE1OSNXS sys_insn(1, 0, 9, 1, 3) +#define OP_TLBI_VALE1OSNXS sys_insn(1, 0, 9, 1, 5) +#define OP_TLBI_VAALE1OSNXS sys_insn(1, 0, 9, 1, 7) +#define OP_TLBI_RVAE1ISNXS sys_insn(1, 0, 9, 2, 1) +#define OP_TLBI_RVAAE1ISNXS sys_insn(1, 0, 9, 2, 3) +#define OP_TLBI_RVALE1ISNXS sys_insn(1, 0, 9, 2, 5) +#define OP_TLBI_RVAALE1ISNXS sys_insn(1, 0, 9, 2, 7) +#define OP_TLBI_VMALLE1ISNXS sys_insn(1, 0, 9, 3, 0) +#define OP_TLBI_VAE1ISNXS sys_insn(1, 0, 9, 3, 1) +#define OP_TLBI_ASIDE1ISNXS sys_insn(1, 0, 9, 3, 2) +#define OP_TLBI_VAAE1ISNXS sys_insn(1, 0, 9, 3, 3) +#define OP_TLBI_VALE1ISNXS sys_insn(1, 0, 9, 3, 5) +#define OP_TLBI_VAALE1ISNXS sys_insn(1, 0, 9, 3, 7) +#define OP_TLBI_RVAE1OSNXS sys_insn(1, 0, 9, 5, 1) +#define OP_TLBI_RVAAE1OSNXS sys_insn(1, 0, 9, 5, 3) +#define OP_TLBI_RVALE1OSNXS sys_insn(1, 0, 9, 5, 5) +#define OP_TLBI_RVAALE1OSNXS sys_insn(1, 0, 9, 5, 7) +#define OP_TLBI_RVAE1NXS sys_insn(1, 0, 9, 6, 1) +#define OP_TLBI_RVAAE1NXS sys_insn(1, 0, 9, 6, 3) +#define OP_TLBI_RVALE1NXS sys_insn(1, 0, 9, 6, 5) +#define OP_TLBI_RVAALE1NXS sys_insn(1, 0, 9, 6, 7) +#define OP_TLBI_VMALLE1NXS sys_insn(1, 0, 9, 7, 0) +#define OP_TLBI_VAE1NXS sys_insn(1, 0, 9, 7, 1) +#define OP_TLBI_ASIDE1NXS sys_insn(1, 0, 9, 7, 2) +#define OP_TLBI_VAAE1NXS sys_insn(1, 0, 9, 7, 3) +#define OP_TLBI_VALE1NXS sys_insn(1, 0, 9, 7, 5) +#define OP_TLBI_VAALE1NXS sys_insn(1, 0, 9, 7, 7) +#define OP_TLBI_IPAS2E1IS sys_insn(1, 4, 8, 0, 1) +#define OP_TLBI_RIPAS2E1IS sys_insn(1, 4, 8, 0, 2) +#define OP_TLBI_IPAS2LE1IS sys_insn(1, 4, 8, 0, 5) +#define OP_TLBI_RIPAS2LE1IS sys_insn(1, 4, 8, 0, 6) +#define OP_TLBI_ALLE2OS sys_insn(1, 4, 8, 1, 0) +#define OP_TLBI_VAE2OS sys_insn(1, 4, 8, 1, 1) +#define OP_TLBI_ALLE1OS sys_insn(1, 4, 8, 1, 4) +#define OP_TLBI_VALE2OS sys_insn(1, 4, 8, 1, 5) +#define OP_TLBI_VMALLS12E1OS sys_insn(1, 4, 8, 1, 6) +#define OP_TLBI_RVAE2IS sys_insn(1, 4, 8, 2, 1) +#define OP_TLBI_RVALE2IS sys_insn(1, 4, 8, 2, 5) +#define OP_TLBI_ALLE2IS sys_insn(1, 4, 8, 3, 0) +#define OP_TLBI_VAE2IS sys_insn(1, 4, 8, 3, 1) +#define OP_TLBI_ALLE1IS sys_insn(1, 4, 8, 3, 4) +#define OP_TLBI_VALE2IS sys_insn(1, 4, 8, 3, 5) +#define OP_TLBI_VMALLS12E1IS sys_insn(1, 4, 8, 3, 6) +#define OP_TLBI_IPAS2E1OS sys_insn(1, 4, 8, 4, 0) +#define OP_TLBI_IPAS2E1 sys_insn(1, 4, 8, 4, 1) +#define OP_TLBI_RIPAS2E1 sys_insn(1, 4, 8, 4, 2) +#define OP_TLBI_RIPAS2E1OS sys_insn(1, 4, 8, 4, 3) +#define OP_TLBI_IPAS2LE1OS sys_insn(1, 4, 8, 4, 4) +#define OP_TLBI_IPAS2LE1 sys_insn(1, 4, 8, 4, 5) +#define OP_TLBI_RIPAS2LE1 sys_insn(1, 4, 8, 4, 6) +#define OP_TLBI_RIPAS2LE1OS sys_insn(1, 4, 8, 4, 7) +#define OP_TLBI_RVAE2OS sys_insn(1, 4, 8, 5, 1) +#define OP_TLBI_RVALE2OS sys_insn(1, 4, 8, 5, 5) +#define OP_TLBI_RVAE2 sys_insn(1, 4, 8, 6, 1) +#define OP_TLBI_RVALE2 sys_insn(1, 4, 8, 6, 5) +#define OP_TLBI_ALLE2 sys_insn(1, 4, 8, 7, 0) +#define OP_TLBI_VAE2 sys_insn(1, 4, 8, 7, 1) +#define OP_TLBI_ALLE1 sys_insn(1, 4, 8, 7, 4) +#define OP_TLBI_VALE2 sys_insn(1, 4, 8, 7, 5) +#define OP_TLBI_VMALLS12E1 sys_insn(1, 4, 8, 7, 6) +#define OP_TLBI_IPAS2E1ISNXS sys_insn(1, 4, 9, 0, 1) +#define OP_TLBI_RIPAS2E1ISNXS sys_insn(1, 4, 9, 0, 2) +#define OP_TLBI_IPAS2LE1ISNXS sys_insn(1, 4, 9, 0, 5) +#define OP_TLBI_RIPAS2LE1ISNXS sys_insn(1, 4, 9, 0, 6) +#define OP_TLBI_ALLE2OSNXS sys_insn(1, 4, 9, 1, 0) +#define OP_TLBI_VAE2OSNXS sys_insn(1, 4, 9, 1, 1) +#define OP_TLBI_ALLE1OSNXS sys_insn(1, 4, 9, 1, 4) +#define OP_TLBI_VALE2OSNXS sys_insn(1, 4, 9, 1, 5) +#define OP_TLBI_VMALLS12E1OSNXS sys_insn(1, 4, 9, 1, 6) +#define OP_TLBI_RVAE2ISNXS sys_insn(1, 4, 9, 2, 1) +#define OP_TLBI_RVALE2ISNXS sys_insn(1, 4, 9, 2, 5) +#define OP_TLBI_ALLE2ISNXS sys_insn(1, 4, 9, 3, 0) +#define OP_TLBI_VAE2ISNXS sys_insn(1, 4, 9, 3, 1) +#define OP_TLBI_ALLE1ISNXS sys_insn(1, 4, 9, 3, 4) +#define OP_TLBI_VALE2ISNXS sys_insn(1, 4, 9, 3, 5) +#define OP_TLBI_VMALLS12E1ISNXS sys_insn(1, 4, 9, 3, 6) +#define OP_TLBI_IPAS2E1OSNXS sys_insn(1, 4, 9, 4, 0) +#define OP_TLBI_IPAS2E1NXS sys_insn(1, 4, 9, 4, 1) +#define OP_TLBI_RIPAS2E1NXS sys_insn(1, 4, 9, 4, 2) +#define OP_TLBI_RIPAS2E1OSNXS sys_insn(1, 4, 9, 4, 3) +#define OP_TLBI_IPAS2LE1OSNXS sys_insn(1, 4, 9, 4, 4) +#define OP_TLBI_IPAS2LE1NXS sys_insn(1, 4, 9, 4, 5) +#define OP_TLBI_RIPAS2LE1NXS sys_insn(1, 4, 9, 4, 6) +#define OP_TLBI_RIPAS2LE1OSNXS sys_insn(1, 4, 9, 4, 7) +#define OP_TLBI_RVAE2OSNXS sys_insn(1, 4, 9, 5, 1) +#define OP_TLBI_RVALE2OSNXS sys_insn(1, 4, 9, 5, 5) +#define OP_TLBI_RVAE2NXS sys_insn(1, 4, 9, 6, 1) +#define OP_TLBI_RVALE2NXS sys_insn(1, 4, 9, 6, 5) +#define OP_TLBI_ALLE2NXS sys_insn(1, 4, 9, 7, 0) +#define OP_TLBI_VAE2NXS sys_insn(1, 4, 9, 7, 1) +#define OP_TLBI_ALLE1NXS sys_insn(1, 4, 9, 7, 4) +#define OP_TLBI_VALE2NXS sys_insn(1, 4, 9, 7, 5) +#define OP_TLBI_VMALLS12E1NXS sys_insn(1, 4, 9, 7, 6) + +/* Misc instructions */ +#define OP_GCSPUSHX sys_insn(1, 0, 7, 7, 4) +#define OP_GCSPOPCX sys_insn(1, 0, 7, 7, 5) +#define OP_GCSPOPX sys_insn(1, 0, 7, 7, 6) +#define OP_GCSPUSHM sys_insn(1, 3, 7, 7, 0) + +#define OP_BRB_IALL sys_insn(1, 1, 7, 2, 4) +#define OP_BRB_INJ sys_insn(1, 1, 7, 2, 5) +#define OP_CFP_RCTX sys_insn(1, 3, 7, 3, 4) +#define OP_DVP_RCTX sys_insn(1, 3, 7, 3, 5) +#define OP_COSP_RCTX sys_insn(1, 3, 7, 3, 6) +#define OP_CPP_RCTX sys_insn(1, 3, 7, 3, 7) + /* Common SCTLR_ELx flags. */ #define SCTLR_ELx_ENTP2 (BIT(60)) #define SCTLR_ELx_DSSBS (BIT(44)) @@ -555,16 +895,14 @@ /* Position the attr at the correct index */ #define MAIR_ATTRIDX(attr, idx) ((attr) << ((idx) * 8)) -/* id_aa64pfr0 */ -#define ID_AA64PFR0_EL1_ELx_64BIT_ONLY 0x1 -#define ID_AA64PFR0_EL1_ELx_32BIT_64BIT 0x2 - /* id_aa64mmfr0 */ #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN 0x0 +#define ID_AA64MMFR0_EL1_TGRAN4_LPA2 ID_AA64MMFR0_EL1_TGRAN4_52_BIT #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX 0x7 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN 0x0 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX 0x7 #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN 0x1 +#define ID_AA64MMFR0_EL1_TGRAN16_LPA2 ID_AA64MMFR0_EL1_TGRAN16_52_BIT #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX 0xf #define ARM64_MIN_PARANGE_BITS 32 @@ -572,6 +910,7 @@ #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT 0x0 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE 0x1 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN 0x2 +#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2 0x3 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX 0x7 #ifdef CONFIG_ARM64_PA_BITS_52 @@ -582,11 +921,13 @@ #if defined(CONFIG_ARM64_4K_PAGES) #define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN4_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_LPA2 ID_AA64MMFR0_EL1_TGRAN4_52_BIT #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT #elif defined(CONFIG_ARM64_16K_PAGES) #define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN16_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_LPA2 ID_AA64MMFR0_EL1_TGRAN16_52_BIT #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT @@ -610,6 +951,19 @@ #define SYS_GCR_EL1_RRND (BIT(16)) #define SYS_GCR_EL1_EXCL_MASK 0xffffUL +#ifdef CONFIG_KASAN_HW_TAGS +/* + * KASAN always uses a whole byte for its tags. With CONFIG_KASAN_HW_TAGS it + * only uses tags in the range 0xF0-0xFF, which we map to MTE tags 0x0-0xF. + */ +#define __MTE_TAG_MIN (KASAN_TAG_MIN & 0xf) +#define __MTE_TAG_MAX (KASAN_TAG_MAX & 0xf) +#define __MTE_TAG_INCL GENMASK(__MTE_TAG_MAX, __MTE_TAG_MIN) +#define KERNEL_GCR_EL1_EXCL (SYS_GCR_EL1_EXCL_MASK & ~__MTE_TAG_INCL) +#else +#define KERNEL_GCR_EL1_EXCL SYS_GCR_EL1_EXCL_MASK +#endif + #define KERNEL_GCR_EL1 (SYS_GCR_EL1_RRND | KERNEL_GCR_EL1_EXCL) /* RGSR_EL1 Definitions */ @@ -626,15 +980,6 @@ /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */ #define SYS_MPIDR_SAFE_VAL (BIT(31)) -#define TRFCR_ELx_TS_SHIFT 5 -#define TRFCR_ELx_TS_MASK ((0x3UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_ELx_TS_VIRTUAL ((0x1UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_ELx_TS_GUEST_PHYSICAL ((0x2UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_ELx_TS_PHYSICAL ((0x3UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_EL2_CX BIT(3) -#define TRFCR_ELx_ExTRE BIT(1) -#define TRFCR_ELx_E0TRE BIT(0) - /* GIC Hypervisor interface registers */ /* ICH_MISR_EL2 bit definitions */ #define ICH_MISR_EOI (1 << 0) @@ -716,6 +1061,22 @@ #define PIRx_ELx_PERM(idx, perm) ((perm) << ((idx) * 4)) +/* + * Permission Overlay Extension (POE) permission encodings. + */ +#define POE_NONE UL(0x0) +#define POE_R UL(0x1) +#define POE_X UL(0x2) +#define POE_RX UL(0x3) +#define POE_W UL(0x4) +#define POE_RW UL(0x5) +#define POE_XW UL(0x6) +#define POE_RXW UL(0x7) +#define POE_MASK UL(0xf) + +/* Initial value for Permission Overlay Extension for EL0 */ +#define POR_EL0_INIT POE_RXW + #define ARM64_FEATURE_FIELD_BITS 4 /* Defined for compatibility only, do not add new users. */ @@ -789,15 +1150,21 @@ /* * For registers without architectural names, or simply unsupported by * GAS. + * + * __check_r forces warnings to be generated by the compiler when + * evaluating r which wouldn't normally happen due to being passed to + * the assembler via __stringify(r). */ #define read_sysreg_s(r) ({ \ u64 __val; \ + u32 __maybe_unused __check_r = (u32)(r); \ asm volatile(__mrs_s("%0", r) : "=r" (__val)); \ __val; \ }) #define write_sysreg_s(v, r) do { \ u64 __val = (u64)(v); \ + u32 __maybe_unused __check_r = (u32)(r); \ asm volatile(__msr_s(r, "%x0") : : "rZ" (__val)); \ } while (0) @@ -827,6 +1194,8 @@ par; \ }) +#define SYS_FIELD_VALUE(reg, field, val) reg##_##field##_##val + #define SYS_FIELD_GET(reg, field, val) \ FIELD_GET(reg##_##field##_MASK, val) @@ -834,7 +1203,8 @@ FIELD_PREP(reg##_##field##_MASK, val) #define SYS_FIELD_PREP_ENUM(reg, field, val) \ - FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val) + FIELD_PREP(reg##_##field##_MASK, \ + SYS_FIELD_VALUE(reg, field, val)) #endif diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 156b62a163c5..8a48cc2536f5 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -226,7 +226,7 @@ static int load_xbc_from_initrd(int fd, char **buf) /* Wrong Checksum */ rcsum = xbc_calc_checksum(*buf, size); if (csum != rcsum) { - pr_err("checksum error: %d != %d\n", csum, rcsum); + pr_err("checksum error: %u != %u\n", csum, rcsum); return -EINVAL; } @@ -395,7 +395,7 @@ static int apply_xbc(const char *path, const char *xbc_path) xbc_get_info(&ret, NULL); printf("\tNumber of nodes: %d\n", ret); printf("\tSize: %u bytes\n", (unsigned int)size); - printf("\tChecksum: %d\n", (unsigned int)csum); + printf("\tChecksum: %u\n", (unsigned int)csum); /* TODO: Check the options by schema */ xbc_exit(); diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst index 3f6bca03ad2e..d47dddc2b4ee 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -24,7 +24,7 @@ BTF COMMANDS ============= | **bpftool** **btf** { **show** | **list** } [**id** *BTF_ID*] -| **bpftool** **btf dump** *BTF_SRC* [**format** *FORMAT*] +| **bpftool** **btf dump** *BTF_SRC* [**format** *FORMAT*] [**root_id** *ROOT_ID*] | **bpftool** **btf help** | | *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* } @@ -43,7 +43,7 @@ bpftool btf { show | list } [id *BTF_ID*] that hold open file descriptors (FDs) against BTF objects. On such kernels bpftool will automatically emit this information as well. -bpftool btf dump *BTF_SRC* +bpftool btf dump *BTF_SRC* [format *FORMAT*] [root_id *ROOT_ID*] Dump BTF entries from a given *BTF_SRC*. When **id** is specified, BTF object with that ID will be loaded and all @@ -67,6 +67,11 @@ bpftool btf dump *BTF_SRC* formatting, the output is sorted by default. Use the **unsorted** option to avoid sorting the output. + **root_id** option can be used to filter a dump to a single type and all + its dependent types. It cannot be used with any other types of filtering + (such as the "key", "value", or "kv" arguments when dumping BTF for a map). + It can be passed multiple times to dump multiple types. + bpftool btf help Print short help message. diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index a4263dfb5e03..dd9f3ec84201 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -106,6 +106,7 @@ FEATURE_TESTS += libbfd-liberty FEATURE_TESTS += libbfd-liberty-z FEATURE_TESTS += disassembler-four-args FEATURE_TESTS += disassembler-init-styled +FEATURE_TESTS += libelf-zstd FEATURE_DISPLAY := clang-bpf-co-re FEATURE_DISPLAY += llvm @@ -132,6 +133,12 @@ endif LIBS = $(LIBBPF) -lelf -lz LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz + +ifeq ($(feature-libelf-zstd),1) +LIBS += -lzstd +LIBS_BOOTSTRAP += -lzstd +endif + ifeq ($(feature-libcap), 1) CFLAGS += -DUSE_LIBCAP LIBS += -lcap diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 0c541498c301..1ce409a6cbd9 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -930,19 +930,24 @@ _bpftool() format) COMPREPLY=( $( compgen -W "c raw" -- "$cur" ) ) ;; + root_id) + return 0; + ;; c) - COMPREPLY=( $( compgen -W "unsorted" -- "$cur" ) ) + COMPREPLY=( $( compgen -W "unsorted root_id" -- "$cur" ) ) ;; *) # emit extra options case ${words[3]} in id|file) + COMPREPLY=( $( compgen -W "root_id" -- "$cur" ) ) _bpftool_once_attr 'format' ;; map|prog) if [[ ${words[3]} == "map" ]] && [[ $cword == 6 ]]; then COMPREPLY+=( $( compgen -W "key value kv all" -- "$cur" ) ) fi + COMPREPLY=( $( compgen -W "root_id" -- "$cur" ) ) _bpftool_once_attr 'format' ;; *) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index d005e4fd6128..2636655ac180 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -27,6 +27,8 @@ #define KFUNC_DECL_TAG "bpf_kfunc" #define FASTCALL_DECL_TAG "bpf_fastcall" +#define MAX_ROOT_IDS 16 + static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_UNKN] = "UNKNOWN", [BTF_KIND_INT] = "INT", @@ -880,12 +882,14 @@ static int do_dump(int argc, char **argv) { bool dump_c = false, sort_dump_c = true; struct btf *btf = NULL, *base = NULL; - __u32 root_type_ids[2]; + __u32 root_type_ids[MAX_ROOT_IDS]; + bool have_id_filtering; int root_type_cnt = 0; __u32 btf_id = -1; const char *src; int fd = -1; int err = 0; + int i; if (!REQ_ARGS(2)) { usage(); @@ -973,6 +977,8 @@ static int do_dump(int argc, char **argv) goto done; } + have_id_filtering = !!root_type_cnt; + while (argc) { if (is_prefix(*argv, "format")) { NEXT_ARG(); @@ -992,6 +998,36 @@ static int do_dump(int argc, char **argv) goto done; } NEXT_ARG(); + } else if (is_prefix(*argv, "root_id")) { + __u32 root_id; + char *end; + + if (have_id_filtering) { + p_err("cannot use root_id with other type filtering"); + err = -EINVAL; + goto done; + } else if (root_type_cnt == MAX_ROOT_IDS) { + p_err("only %d root_id are supported", MAX_ROOT_IDS); + err = -E2BIG; + goto done; + } + + NEXT_ARG(); + root_id = strtoul(*argv, &end, 0); + if (*end) { + err = -1; + p_err("can't parse %s as root ID", *argv); + goto done; + } + for (i = 0; i < root_type_cnt; i++) { + if (root_type_ids[i] == root_id) { + err = -EINVAL; + p_err("duplicate root_id %d supplied", root_id); + goto done; + } + } + root_type_ids[root_type_cnt++] = root_id; + NEXT_ARG(); } else if (is_prefix(*argv, "unsorted")) { sort_dump_c = false; NEXT_ARG(); @@ -1017,6 +1053,17 @@ static int do_dump(int argc, char **argv) } } + /* Invalid root IDs causes half emitted boilerplate and then unclean + * exit. It's an ugly user experience, so handle common error here. + */ + for (i = 0; i < root_type_cnt; i++) { + if (root_type_ids[i] >= btf__type_cnt(btf)) { + err = -EINVAL; + p_err("invalid root ID: %u", root_type_ids[i]); + goto done; + } + } + if (dump_c) { if (json_output) { p_err("JSON output for C-syntax dump is not supported"); @@ -1391,7 +1438,7 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s { show | list } [id BTF_ID]\n" - " %1$s %2$s dump BTF_SRC [format FORMAT]\n" + " %1$s %2$s dump BTF_SRC [format FORMAT] [root_id ROOT_ID]\n" " %1$s %2$s help\n" "\n" " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n" diff --git a/tools/bpf/bpftool/cfg.c b/tools/bpf/bpftool/cfg.c index eec437cca2ea..e3785f9a697d 100644 --- a/tools/bpf/bpftool/cfg.c +++ b/tools/bpf/bpftool/cfg.c @@ -302,6 +302,7 @@ static bool func_add_bb_edges(struct func_node *func) insn = bb->tail; if (!is_jmp_insn(insn->code) || + BPF_OP(insn->code) == BPF_CALL || BPF_OP(insn->code) == BPF_EXIT) { e->dst = bb_next(bb); e->flags |= EDGE_FLAG_FALLTHROUGH; diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 4dbc4fcdf473..24fecdf8e430 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -885,6 +885,28 @@ probe_v3_isa_extension(const char *define_prefix, __u32 ifindex) "V3_ISA_EXTENSION"); } +/* + * Probe for the v4 instruction set extension introduced in commit 1f9a1ea821ff + * ("bpf: Support new sign-extension load insns"). + */ +static void +probe_v4_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[5] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP32_IMM(BPF_JEQ, BPF_REG_0, 1, 1), + BPF_JMP32_A(1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v4_isa_extension", + "ISA extension v4", + "V4_ISA_EXTENSION"); +} + static void section_system_config(enum probe_component target, const char *define_prefix) { @@ -1029,6 +1051,7 @@ static void section_misc(const char *define_prefix, __u32 ifindex) probe_bounded_loops(define_prefix, ifindex); probe_v2_isa_extension(define_prefix, ifindex); probe_v3_isa_extension(define_prefix, ifindex); + probe_v4_isa_extension(define_prefix, ifindex); print_end_section(); } diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index bd9f960bce3d..d47191c6e55e 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -141,6 +141,7 @@ struct object { }; static int verbose; +static int warnings; static int eprintf(int level, int var, const char *fmt, ...) { @@ -604,6 +605,7 @@ static int symbols_resolve(struct object *obj) if (id->id) { pr_info("WARN: multiple IDs found for '%s': %d, %d - using %d\n", str, id->id, type_id, id->id); + warnings++; } else { id->id = type_id; (*nr)--; @@ -625,8 +627,10 @@ static int id_patch(struct object *obj, struct btf_id *id) int i; /* For set, set8, id->id may be 0 */ - if (!id->id && !id->is_set && !id->is_set8) + if (!id->id && !id->is_set && !id->is_set8) { pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name); + warnings++; + } for (i = 0; i < id->addr_cnt; i++) { unsigned long addr = id->addr[i]; @@ -782,6 +786,7 @@ int main(int argc, const char **argv) .funcs = RB_ROOT, .sets = RB_ROOT, }; + bool fatal_warnings = false; struct option btfid_options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show errors, etc)"), @@ -789,6 +794,8 @@ int main(int argc, const char **argv) "BTF data"), OPT_STRING('b', "btf_base", &obj.base_btf_path, "file", "path of file providing base BTF"), + OPT_BOOLEAN(0, "fatal_warnings", &fatal_warnings, + "turn warnings into errors"), OPT_END() }; int err = -1; @@ -823,7 +830,8 @@ int main(int argc, const char **argv) if (symbols_patch(&obj)) goto out; - err = 0; + if (!(fatal_warnings && warnings)) + err = 0; out: if (obj.efile.elf) { elf_end(obj.efile.elf); diff --git a/tools/build/Build.include b/tools/build/Build.include index c2a95ab47379..e45b2eb0d24a 100644 --- a/tools/build/Build.include +++ b/tools/build/Build.include @@ -13,6 +13,8 @@ comma := , squote := ' pound := \# +empty := +space := $(empty) $(empty) ### # Name of target with a '.' as filename prefix. foo/bar.o => foo/.bar.o diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 5fb3fb3d97e0..e710ed67a1b4 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -12,26 +12,6 @@ PHONY := __build __build: -ifeq ($(V),1) - quiet = - Q = -else - quiet=quiet_ - Q=@ -endif - -# If the user is running make -s (silent mode), suppress echoing of commands -# make-4.0 (and later) keep single letter options in the 1st word of MAKEFLAGS. -ifeq ($(filter 3.%,$(MAKE_VERSION)),) -short-opts := $(firstword -$(MAKEFLAGS)) -else -short-opts := $(filter-out --%,$(MAKEFLAGS)) -endif - -ifneq ($(findstring s,$(short-opts)),) - quiet=silent_ -endif - build-dir := $(srctree)/tools/build # Define $(fixdep) for dep-cmd function diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index bca47d136f05..1931b6321314 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -28,6 +28,41 @@ endef # the rule that uses them - an example for that is the 'bionic' # feature check. ] # +# These + the ones in FEATURE_TESTS_EXTRA are included in +# tools/build/feature/test-all.c and we try to build it all together +# then setting all those features to '1' meaning they are all enabled. +# +# There are things like fortify-source that will be set to 1 because test-all +# is built with the flags needed to test if its enabled, resulting in +# +# $ rm -rf /tmp/b ; mkdir /tmp/b ; make -C tools/perf O=/tmp/b feature-dump +# $ grep fortify-source /tmp/b/FEATURE-DUMP +# feature-fortify-source=1 +# $ +# +# All the others should have lines in tools/build/feature/test-all.c like: +# +# #define main main_test_disassembler_init_styled +# # include "test-disassembler-init-styled.c" +# #undef main +# +# #define main main_test_libzstd +# # include "test-libzstd.c" +# #undef main +# +# int main(int argc, char *argv[]) +# { +# main_test_disassembler_four_args(); +# main_test_libzstd(); +# return 0; +# } +# +# If the sample above works, then we end up with these lines in the FEATURE-DUMP +# file: +# +# feature-disassembler-four-args=1 +# feature-libzstd=1 +# FEATURE_TESTS_BASIC := \ backtrace \ libdw \ @@ -38,17 +73,16 @@ FEATURE_TESTS_BASIC := \ glibc \ libbfd \ libbfd-buildid \ - libcap \ libelf \ libelf-getphdrnum \ libelf-gelf_getnote \ libelf-getshdrstrndx \ + libelf-zstd \ libnuma \ numa_num_possible_cpus \ libperl \ libpython \ libslang \ - libslang-include-subdir \ libtraceevent \ libtracefs \ libcpupower \ @@ -89,13 +123,6 @@ FEATURE_TESTS_EXTRA := \ libbfd-liberty \ libbfd-liberty-z \ libopencsd \ - libunwind-x86 \ - libunwind-x86_64 \ - libunwind-arm \ - libunwind-aarch64 \ - libunwind-debug-frame \ - libunwind-debug-frame-arm \ - libunwind-debug-frame-aarch64 \ cxx \ llvm \ clang \ @@ -122,7 +149,6 @@ FEATURE_DISPLAY ?= \ glibc \ libbfd \ libbfd-buildid \ - libcap \ libelf \ libnuma \ numa_num_possible_cpus \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 043dfd00fce7..cb1e3e2feedf 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -13,7 +13,6 @@ FILES= \ test-gtk2.bin \ test-gtk2-infobar.bin \ test-hello.bin \ - test-libaudit.bin \ test-libbfd.bin \ test-libbfd-buildid.bin \ test-disassembler-four-args.bin \ @@ -28,6 +27,7 @@ FILES= \ test-libelf-getphdrnum.bin \ test-libelf-gelf_getnote.bin \ test-libelf-getshdrstrndx.bin \ + test-libelf-zstd.bin \ test-libdebuginfod.bin \ test-libnuma.bin \ test-numa_num_possible_cpus.bin \ @@ -110,7 +110,7 @@ all: $(FILES) __BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS) BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1 BUILD_BFD = $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl - BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap + BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS) BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1 @@ -196,6 +196,9 @@ $(OUTPUT)test-libelf-gelf_getnote.bin: $(OUTPUT)test-libelf-getshdrstrndx.bin: $(BUILD) -lelf +$(OUTPUT)test-libelf-zstd.bin: + $(BUILD) -lelf -lz -lzstd + $(OUTPUT)test-libdebuginfod.bin: $(BUILD) -ldebuginfod @@ -228,9 +231,6 @@ $(OUTPUT)test-libunwind-debug-frame-arm.bin: $(OUTPUT)test-libunwind-debug-frame-aarch64.bin: $(BUILD) -lelf -llzma -lunwind-aarch64 -$(OUTPUT)test-libaudit.bin: - $(BUILD) -laudit - $(OUTPUT)test-libslang.bin: $(BUILD) -lslang diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 59ef3d7fe6a4..03ddaac6f4c4 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -58,8 +58,8 @@ # include "test-libelf-getshdrstrndx.c" #undef main -#define main main_test_libunwind -# include "test-libunwind.c" +#define main main_test_libelf_zstd +# include "test-libelf-zstd.c" #undef main #define main main_test_libslang @@ -170,6 +170,14 @@ # include "test-libzstd.c" #undef main +#define main main_test_libtraceevent +# include "test-libtraceevent.c" +#undef main + +#define main main_test_libtracefs +# include "test-libtracefs.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -184,7 +192,6 @@ int main(int argc, char *argv[]) main_test_libelf_getphdrnum(); main_test_libelf_gelf_getnote(); main_test_libelf_getshdrstrndx(); - main_test_libunwind(); main_test_libslang(); main_test_libbfd(); main_test_libbfd_buildid(); @@ -208,6 +215,8 @@ int main(int argc, char *argv[]) main_test_reallocarray(); main_test_disassembler_four_args(); main_test_libzstd(); + main_test_libtraceevent(); + main_test_libtracefs(); return 0; } diff --git a/tools/build/feature/test-libaudit.c b/tools/build/feature/test-libaudit.c deleted file mode 100644 index f5b0863fa1ec..000000000000 --- a/tools/build/feature/test-libaudit.c +++ /dev/null @@ -1,11 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <libaudit.h> - -extern int printf(const char *format, ...); - -int main(void) -{ - printf("error message: %s\n", audit_errno_to_name(0)); - - return audit_open(); -} diff --git a/tools/build/feature/test-libelf-zstd.c b/tools/build/feature/test-libelf-zstd.c new file mode 100644 index 000000000000..a1324a1db3bb --- /dev/null +++ b/tools/build/feature/test-libelf-zstd.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stddef.h> +#include <libelf.h> + +int main(void) +{ + elf_compress(NULL, ELFCOMPRESS_ZSTD, 0); + return 0; +} diff --git a/tools/hv/.gitignore b/tools/hv/.gitignore new file mode 100644 index 000000000000..0c5bc15d602f --- /dev/null +++ b/tools/hv/.gitignore @@ -0,0 +1,3 @@ +hv_fcopy_uio_daemon +hv_kvp_daemon +hv_vss_daemon diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 7a00f3066a98..0198321d14a2 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -35,8 +35,6 @@ #define WIN8_SRV_MINOR 1 #define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) -#define MAX_FOLDER_NAME 15 -#define MAX_PATH_LEN 15 #define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" #define FCOPY_VER_COUNT 1 @@ -51,7 +49,7 @@ static const int fw_versions[] = { #define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ -unsigned char desc[HV_RING_SIZE]; +static unsigned char desc[HV_RING_SIZE]; static int target_fd; static char target_fname[PATH_MAX]; @@ -409,8 +407,8 @@ int main(int argc, char *argv[]) struct vmbus_br txbr, rxbr; void *ring; uint32_t len = HV_RING_SIZE; - char uio_name[MAX_FOLDER_NAME] = {0}; - char uio_dev_path[MAX_PATH_LEN] = {0}; + char uio_name[NAME_MAX] = {0}; + char uio_dev_path[PATH_MAX] = {0}; static struct option long_options[] = { {"help", no_argument, 0, 'h' }, @@ -468,8 +466,10 @@ int main(int argc, char *argv[]) */ ret = pread(fcopy_fd, &tmp, sizeof(int), 0); if (ret < 0) { + if (errno == EINTR || errno == EAGAIN) + continue; syslog(LOG_ERR, "pread failed: %s", strerror(errno)); - continue; + goto close; } len = HV_RING_SIZE; diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh index 058c17b46ffc..268521234d4b 100755 --- a/tools/hv/hv_get_dns_info.sh +++ b/tools/hv/hv_get_dns_info.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh # This example script parses /etc/resolv.conf to retrive DNS information. # In the interest of keeping the KVP daemon code free of distro specific @@ -10,4 +10,4 @@ # this script can be based on the Network Manager APIs for retrieving DNS # entries. -cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }' +exec awk '/^nameserver/ { print $2 }' /etc/resolv.conf 2>/dev/null diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index ae57bf69ad4a..04ba035d67e9 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -725,7 +725,7 @@ static void kvp_get_ipconfig_info(char *if_name, * . */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s", "hv_get_dns_info"); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dns_info", if_name); /* * Execute the command to gather DNS info. @@ -742,7 +742,7 @@ static void kvp_get_ipconfig_info(char *if_name, * Enabled: DHCP enabled. */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dhcp_info", if_name); file = popen(cmd, "r"); if (file == NULL) @@ -1606,8 +1606,9 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) * invoke the external script to do its magic. */ - str_len = snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s %s", - "hv_set_ifconfig", if_filename, nm_filename); + str_len = snprintf(cmd, sizeof(cmd), "exec %s %s %s", + KVP_SCRIPTS_PATH "hv_set_ifconfig", + if_filename, nm_filename); /* * This is a little overcautious, but it's necessary to suppress some * false warnings from gcc 8.0.1. diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index 440a91b35823..2f8baed2b8f7 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1 cp $1 /etc/sysconfig/network-scripts/ -chmod 600 $2 +umask 0177 interface=$(echo $2 | awk -F - '{ print $2 }') filename="${2##*/}" diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index 65aa8ce142e5..bcc6df79301a 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -273,6 +273,16 @@ .off = OFF, \ .imm = 0 }) +/* Unconditional jumps, gotol pc + imm32 */ + +#define BPF_JMP32_A(IMM) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_JA, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + /* Function call */ #define BPF_EMIT_CALL(FUNC) \ diff --git a/tools/include/linux/kasan-tags.h b/tools/include/linux/kasan-tags.h new file mode 100644 index 000000000000..4f85f562512c --- /dev/null +++ b/tools/include/linux/kasan-tags.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KASAN_TAGS_H +#define _LINUX_KASAN_TAGS_H + +#define KASAN_TAG_KERNEL 0xFF /* native kernel pointers tag */ +#define KASAN_TAG_INVALID 0xFE /* inaccessible memory tag */ +#define KASAN_TAG_MAX 0xFD /* maximum value for random tags */ + +#ifdef CONFIG_KASAN_HW_TAGS +#define KASAN_TAG_MIN 0xF0 /* minimum value for random tags */ +#else +#define KASAN_TAG_MIN 0x00 /* minimum value for random tags */ +#endif + +#endif /* LINUX_KASAN_TAGS_H */ diff --git a/tools/include/linux/objtool_types.h b/tools/include/linux/objtool_types.h index 453a4f4ef39d..df5d9fa84dba 100644 --- a/tools/include/linux/objtool_types.h +++ b/tools/include/linux/objtool_types.h @@ -54,4 +54,16 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_SAVE 6 #define UNWIND_HINT_TYPE_RESTORE 7 +/* + * Annotate types + */ +#define ANNOTYPE_NOENDBR 1 +#define ANNOTYPE_RETPOLINE_SAFE 2 +#define ANNOTYPE_INSTR_BEGIN 3 +#define ANNOTYPE_INSTR_END 4 +#define ANNOTYPE_UNRET_BEGIN 5 +#define ANNOTYPE_IGNORE_ALTS 6 +#define ANNOTYPE_INTRA_FUNCTION_CALL 7 +#define ANNOTYPE_REACHABLE 8 + #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 7b82bc3cf107..d4a5c2399a66 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -23,6 +23,7 @@ #include <linux/prctl.h> #include <linux/resource.h> #include <linux/utsname.h> +#include <linux/signal.h> #include "arch.h" #include "errno.h" @@ -1225,6 +1226,23 @@ pid_t waitpid(pid_t pid, int *status, int options) } +/* + * int waitid(idtype_t idtype, id_t id, siginfo_t *infop, int options); + */ + +static __attribute__((unused)) +int sys_waitid(int which, pid_t pid, siginfo_t *infop, int options, struct rusage *rusage) +{ + return my_syscall5(__NR_waitid, which, pid, infop, options, rusage); +} + +static __attribute__((unused)) +int waitid(int which, pid_t pid, siginfo_t *infop, int options) +{ + return __sysret(sys_waitid(which, pid, infop, options, NULL)); +} + + /* * ssize_t write(int fd, const void *buf, size_t count); */ diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h index 281df9139d2b..ffff554a5230 100644 --- a/tools/include/uapi/asm-generic/socket.h +++ b/tools/include/uapi/asm-generic/socket.h @@ -126,6 +126,8 @@ #define SCM_TS_OPT_ID 78 +#define SO_RCVPRIORITY 79 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4162afc6b5d0..2acf9b336371 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1573,6 +1573,16 @@ union bpf_attr { * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. */ __s32 prog_token_fd; + /* The fd_array_cnt can be used to pass the length of the + * fd_array array. In this case all the [map] file descriptors + * passed in this array will be bound to the program, even if + * the maps are not referenced directly. The functionality is + * similar to the BPF_PROG_BIND_MAP syscall, but maps can be + * used by the verifier during the program load. If provided, + * then the fd_array[0,...,fd_array_cnt-1] is expected to be + * continuous. + */ + __u32 fd_array_cnt; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 8516c1ccd57a..7e46ca4cd31b 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -1315,6 +1315,8 @@ enum { IFLA_NETKIT_MODE, IFLA_NETKIT_SCRUB, IFLA_NETKIT_PEER_SCRUB, + IFLA_NETKIT_HEADROOM, + IFLA_NETKIT_TAILROOM, __IFLA_NETKIT_MAX, }; #define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index 2f082b01ff22..42ec5ddaab8d 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -117,12 +117,12 @@ struct xdp_options { ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1) /* Request transmit timestamp. Upon completion, put it into tx_timestamp - * field of union xsk_tx_metadata. + * field of struct xsk_tx_metadata. */ #define XDP_TXMD_FLAGS_TIMESTAMP (1 << 0) /* Request transmit checksum offload. Checksum start position and offset - * are communicated via csum_start and csum_offset fields of union + * are communicated via csum_start and csum_offset fields of struct * xsk_tx_metadata. */ #define XDP_TXMD_FLAGS_CHECKSUM (1 << 1) diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h index bb6ea517efb5..c53cde425406 100644 --- a/tools/include/uapi/linux/stddef.h +++ b/tools/include/uapi/linux/stddef.h @@ -8,6 +8,13 @@ #define __always_inline __inline__ #endif +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + /** * __struct_group() - Create a mirrored named and anonyomous struct * @@ -20,14 +27,14 @@ * and size: one anonymous and one named. The former's members can be used * normally without sub-struct naming, and the latter can be used to * reason about the start, end, and size of the group of struct members. - * The named struct can also be explicitly tagged for layer reuse, as well - * as both having struct attributes appended. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. */ #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ union { \ struct { MEMBERS } ATTRS; \ - struct TAG { MEMBERS } ATTRS NAME; \ - } + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ + } ATTRS /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 337fde770e45..edec23406dbc 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -296,7 +296,7 @@ int filename__read_int(const char *filename, int *value) int fd = open(filename, O_RDONLY), err = -1; if (fd < 0) - return -1; + return -errno; if (read(fd, line, sizeof(line)) > 0) { *value = atoi(line); @@ -314,7 +314,7 @@ static int filename__read_ull_base(const char *filename, int fd = open(filename, O_RDONLY), err = -1; if (fd < 0) - return -1; + return -errno; if (read(fd, line, sizeof(line)) > 0) { *value = strtoull(line, NULL, base); @@ -372,7 +372,7 @@ int filename__write_int(const char *filename, int value) char buf[64]; if (fd < 0) - return err; + return -errno; sprintf(buf, "%d", value); if (write(fd, buf, sizeof(buf)) == sizeof(buf)) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index becdfa701c75..359f73ead613 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -238,7 +238,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd); + const size_t attr_sz = offsetofend(union bpf_attr, fd_array_cnt); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -311,6 +311,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.line_info_cnt = OPTS_GET(opts, line_info_cnt, 0); attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL)); + attr.fd_array_cnt = OPTS_GET(opts, fd_array_cnt, 0); if (log_level) { attr.log_buf = ptr_to_u64(log_buf); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index a4a7b1ad1b63..435da95d2058 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -107,9 +107,12 @@ struct bpf_prog_load_opts { */ __u32 log_true_size; __u32 token_fd; + + /* if set, provides the length of fd_array */ + __u32 fd_array_cnt; size_t :0; }; -#define bpf_prog_load_opts__last_field token_fd +#define bpf_prog_load_opts__last_field fd_array_cnt LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 12468ae0d573..48c66f3a9200 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -283,7 +283,7 @@ static int btf_parse_str_sec(struct btf *btf) return -EINVAL; } if (!btf->base_btf && start[0]) { - pr_debug("Invalid BTF string section\n"); + pr_debug("Malformed BTF string section, did you forget to provide base BTF?\n"); return -EINVAL; } return 0; @@ -1186,6 +1186,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, elf = elf_begin(fd, ELF_C_READ, NULL); if (!elf) { + err = -LIBBPF_ERRNO__FORMAT; pr_warn("failed to open %s as ELF file\n", path); goto done; } diff --git a/tools/lib/bpf/btf_relocate.c b/tools/lib/bpf/btf_relocate.c index b72f83e15156..53d1f3541bce 100644 --- a/tools/lib/bpf/btf_relocate.c +++ b/tools/lib/bpf/btf_relocate.c @@ -212,7 +212,7 @@ static int btf_relocate_map_distilled_base(struct btf_relocate *r) * need to match both name and size, otherwise embedding the base * struct/union in the split type is invalid. */ - for (id = r->nr_dist_base_types; id < r->nr_split_types; id++) { + for (id = r->nr_dist_base_types; id < r->nr_dist_base_types + r->nr_split_types; id++) { err = btf_mark_embedded_composite_type_ids(r, id); if (err) goto done; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 66173ddb5a2d..194809da5172 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1731,12 +1731,24 @@ static int sys_memfd_create(const char *name, unsigned flags) #ifndef MFD_CLOEXEC #define MFD_CLOEXEC 0x0001U #endif +#ifndef MFD_NOEXEC_SEAL +#define MFD_NOEXEC_SEAL 0x0008U +#endif static int create_placeholder_fd(void) { + unsigned int flags = MFD_CLOEXEC | MFD_NOEXEC_SEAL; + const char *name = "libbpf-placeholder-fd"; int fd; - fd = ensure_good_fd(sys_memfd_create("libbpf-placeholder-fd", MFD_CLOEXEC)); + fd = ensure_good_fd(sys_memfd_create(name, flags)); + if (fd >= 0) + return fd; + else if (errno != EINVAL) + return -errno; + + /* Possibly running on kernel without MFD_NOEXEC_SEAL */ + fd = ensure_good_fd(sys_memfd_create(name, flags & ~MFD_NOEXEC_SEAL)); if (fd < 0) return -errno; return fd; @@ -11375,9 +11387,33 @@ static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type, struct kprobe_multi_resolve *res = data->res; int err; - if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) + if (!glob_match(sym_name, res->pattern)) return 0; + if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) { + /* Some versions of kernel strip out .llvm.<hash> suffix from + * function names reported in available_filter_functions, but + * don't do so for kallsyms. While this is clearly a kernel + * bug (fixed by [0]) we try to accommodate that in libbpf to + * make multi-kprobe usability a bit better: if no match is + * found, we will strip .llvm. suffix and try one more time. + * + * [0] fb6a421fb615 ("kallsyms: Match symbols exactly with CONFIG_LTO_CLANG") + */ + char sym_trim[256], *psym_trim = sym_trim, *sym_sfx; + + if (!(sym_sfx = strstr(sym_name, ".llvm."))) + return 0; + + /* psym_trim vs sym_trim dance is done to avoid pointer vs array + * coercion differences and get proper `const char **` pointer + * which avail_func_cmp() expects + */ + snprintf(sym_trim, sizeof(sym_trim), "%.*s", (int)(sym_sfx - sym_name), sym_name); + if (!bsearch(&psym_trim, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) + return 0; + } + err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, sizeof(*res->addrs), res->cnt + 1); if (err) return err; @@ -11522,7 +11558,7 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, struct bpf_link *link = NULL; const unsigned long *addrs; int err, link_fd, prog_fd; - bool retprobe, session; + bool retprobe, session, unique_match; const __u64 *cookies; const char **syms; size_t cnt; @@ -11541,6 +11577,7 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, addrs = OPTS_GET(opts, addrs, false); cnt = OPTS_GET(opts, cnt, false); cookies = OPTS_GET(opts, cookies, false); + unique_match = OPTS_GET(opts, unique_match, false); if (!pattern && !addrs && !syms) return libbpf_err_ptr(-EINVAL); @@ -11548,6 +11585,8 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, return libbpf_err_ptr(-EINVAL); if (!pattern && !cnt) return libbpf_err_ptr(-EINVAL); + if (!pattern && unique_match) + return libbpf_err_ptr(-EINVAL); if (addrs && syms) return libbpf_err_ptr(-EINVAL); @@ -11558,6 +11597,14 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, err = libbpf_available_kallsyms_parse(&res); if (err) goto error; + + if (unique_match && res.cnt != 1) { + pr_warn("prog '%s': failed to find a unique match for '%s' (%zu matches)\n", + prog->name, pattern, res.cnt); + err = -EINVAL; + goto error; + } + addrs = res.addrs; cnt = res.cnt; } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index b2ce3a72b11d..3020ee45303a 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -552,10 +552,12 @@ struct bpf_kprobe_multi_opts { bool retprobe; /* create session kprobes */ bool session; + /* enforce unique match */ + bool unique_match; size_t :0; }; -#define bpf_kprobe_multi_opts__last_field session +#define bpf_kprobe_multi_opts__last_field unique_match LIBBPF_API struct bpf_link * bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, @@ -1796,9 +1798,14 @@ struct bpf_linker_file_opts { struct bpf_linker; LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts); +LIBBPF_API struct bpf_linker *bpf_linker__new_fd(int fd, struct bpf_linker_opts *opts); LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, const struct bpf_linker_file_opts *opts); +LIBBPF_API int bpf_linker__add_fd(struct bpf_linker *linker, int fd, + const struct bpf_linker_file_opts *opts); +LIBBPF_API int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz, + const struct bpf_linker_file_opts *opts); LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 54b6f312cfa8..a8b2936a1646 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -432,4 +432,8 @@ LIBBPF_1.5.0 { } LIBBPF_1.4.0; LIBBPF_1.6.0 { + global: + bpf_linker__add_buf; + bpf_linker__add_fd; + bpf_linker__new_fd; } LIBBPF_1.5.0; diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index cf71d149fe26..b52f71c59616 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -4,6 +4,10 @@ * * Copyright (c) 2021 Facebook */ +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif + #include <stdbool.h> #include <stddef.h> #include <stdio.h> @@ -16,6 +20,7 @@ #include <elf.h> #include <libelf.h> #include <fcntl.h> +#include <sys/mman.h> #include "libbpf.h" #include "btf.h" #include "libbpf_internal.h" @@ -152,15 +157,19 @@ struct bpf_linker { /* global (including extern) ELF symbols */ int glob_sym_cnt; struct glob_sym *glob_syms; + + bool fd_is_owned; }; #define pr_warn_elf(fmt, ...) \ libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1)) -static int init_output_elf(struct bpf_linker *linker, const char *file); +static int init_output_elf(struct bpf_linker *linker); -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, - const struct bpf_linker_file_opts *opts, +static int bpf_linker_add_file(struct bpf_linker *linker, int fd, + const char *filename); + +static int linker_load_obj_file(struct bpf_linker *linker, struct src_obj *obj); static int linker_sanity_check_elf(struct src_obj *obj); static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec); @@ -191,7 +200,7 @@ void bpf_linker__free(struct bpf_linker *linker) if (linker->elf) elf_end(linker->elf); - if (linker->fd >= 0) + if (linker->fd >= 0 && linker->fd_is_owned) close(linker->fd); strset__free(linker->strtab_strs); @@ -233,9 +242,63 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts if (!linker) return errno = ENOMEM, NULL; - linker->fd = -1; + linker->filename = strdup(filename); + if (!linker->filename) { + err = -ENOMEM; + goto err_out; + } - err = init_output_elf(linker, filename); + linker->fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644); + if (linker->fd < 0) { + err = -errno; + pr_warn("failed to create '%s': %d\n", filename, err); + goto err_out; + } + linker->fd_is_owned = true; + + err = init_output_elf(linker); + if (err) + goto err_out; + + return linker; + +err_out: + bpf_linker__free(linker); + return errno = -err, NULL; +} + +struct bpf_linker *bpf_linker__new_fd(int fd, struct bpf_linker_opts *opts) +{ + struct bpf_linker *linker; + char filename[32]; + int err; + + if (fd < 0) + return errno = EINVAL, NULL; + + if (!OPTS_VALID(opts, bpf_linker_opts)) + return errno = EINVAL, NULL; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn_elf("libelf initialization failed"); + return errno = EINVAL, NULL; + } + + linker = calloc(1, sizeof(*linker)); + if (!linker) + return errno = ENOMEM, NULL; + + snprintf(filename, sizeof(filename), "fd:%d", fd); + linker->filename = strdup(filename); + if (!linker->filename) { + err = -ENOMEM; + goto err_out; + } + + linker->fd = fd; + linker->fd_is_owned = false; + + err = init_output_elf(linker); if (err) goto err_out; @@ -294,23 +357,12 @@ static Elf64_Sym *add_new_sym(struct bpf_linker *linker, size_t *sym_idx) return sym; } -static int init_output_elf(struct bpf_linker *linker, const char *file) +static int init_output_elf(struct bpf_linker *linker) { int err, str_off; Elf64_Sym *init_sym; struct dst_sec *sec; - linker->filename = strdup(file); - if (!linker->filename) - return -ENOMEM; - - linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644); - if (linker->fd < 0) { - err = -errno; - pr_warn("failed to create '%s': %s\n", file, errstr(err)); - return err; - } - linker->elf = elf_begin(linker->fd, ELF_C_WRITE, NULL); if (!linker->elf) { pr_warn_elf("failed to create ELF object"); @@ -436,19 +488,16 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) return 0; } -int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, - const struct bpf_linker_file_opts *opts) +static int bpf_linker_add_file(struct bpf_linker *linker, int fd, + const char *filename) { struct src_obj obj = {}; int err = 0; - if (!OPTS_VALID(opts, bpf_linker_file_opts)) - return libbpf_err(-EINVAL); + obj.filename = filename; + obj.fd = fd; - if (!linker->elf) - return libbpf_err(-EINVAL); - - err = err ?: linker_load_obj_file(linker, filename, opts, &obj); + err = err ?: linker_load_obj_file(linker, &obj); err = err ?: linker_append_sec_data(linker, &obj); err = err ?: linker_append_elf_syms(linker, &obj); err = err ?: linker_append_elf_relos(linker, &obj); @@ -463,12 +512,91 @@ int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, free(obj.sym_map); if (obj.elf) elf_end(obj.elf); - if (obj.fd >= 0) - close(obj.fd); + return err; +} + +int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts) +{ + int fd, err; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + fd = open(filename, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + err = -errno; + pr_warn("failed to open file '%s': %s\n", filename, errstr(err)); + return libbpf_err(err); + } + + err = bpf_linker_add_file(linker, fd, filename); + close(fd); return libbpf_err(err); } +int bpf_linker__add_fd(struct bpf_linker *linker, int fd, + const struct bpf_linker_file_opts *opts) +{ + char filename[32]; + int err; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + if (fd < 0) + return libbpf_err(-EINVAL); + + snprintf(filename, sizeof(filename), "fd:%d", fd); + err = bpf_linker_add_file(linker, fd, filename); + return libbpf_err(err); +} + +int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz, + const struct bpf_linker_file_opts *opts) +{ + char filename[32]; + int fd, written, ret; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + snprintf(filename, sizeof(filename), "mem:%p+%zu", buf, buf_sz); + + fd = memfd_create(filename, 0); + if (fd < 0) { + ret = -errno; + pr_warn("failed to create memfd '%s': %s\n", filename, errstr(ret)); + return libbpf_err(ret); + } + + written = 0; + while (written < buf_sz) { + ret = write(fd, buf, buf_sz); + if (ret < 0) { + ret = -errno; + pr_warn("failed to write '%s': %s\n", filename, errstr(ret)); + goto err_out; + } + written += ret; + } + + ret = bpf_linker_add_file(linker, fd, filename); +err_out: + close(fd); + return libbpf_err(ret); +} + static bool is_dwarf_sec_name(const char *name) { /* approximation, but the actual list is too long */ @@ -534,8 +662,7 @@ static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name) return sec; } -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, - const struct bpf_linker_file_opts *opts, +static int linker_load_obj_file(struct bpf_linker *linker, struct src_obj *obj) { int err = 0; @@ -554,36 +681,26 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, #error "Unknown __BYTE_ORDER__" #endif - pr_debug("linker: adding object file '%s'...\n", filename); + pr_debug("linker: adding object file '%s'...\n", obj->filename); - obj->filename = filename; - - obj->fd = open(filename, O_RDONLY | O_CLOEXEC); - if (obj->fd < 0) { - err = -errno; - pr_warn("failed to open file '%s': %s\n", filename, errstr(err)); - return err; - } obj->elf = elf_begin(obj->fd, ELF_C_READ_MMAP, NULL); if (!obj->elf) { - err = -errno; - pr_warn_elf("failed to parse ELF file '%s'", filename); - return err; + pr_warn_elf("failed to parse ELF file '%s'", obj->filename); + return -EINVAL; } /* Sanity check ELF file high-level properties */ ehdr = elf64_getehdr(obj->elf); if (!ehdr) { - err = -errno; - pr_warn_elf("failed to get ELF header for %s", filename); - return err; + pr_warn_elf("failed to get ELF header for %s", obj->filename); + return -EINVAL; } /* Linker output endianness set by first input object */ obj_byteorder = ehdr->e_ident[EI_DATA]; if (obj_byteorder != ELFDATA2LSB && obj_byteorder != ELFDATA2MSB) { err = -EOPNOTSUPP; - pr_warn("unknown byte order of ELF file %s\n", filename); + pr_warn("unknown byte order of ELF file %s\n", obj->filename); return err; } if (link_byteorder == ELFDATANONE) { @@ -593,7 +710,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, obj_byteorder == ELFDATA2MSB ? "big" : "little"); } else if (link_byteorder != obj_byteorder) { err = -EOPNOTSUPP; - pr_warn("byte order mismatch with ELF file %s\n", filename); + pr_warn("byte order mismatch with ELF file %s\n", obj->filename); return err; } @@ -601,14 +718,13 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, || ehdr->e_machine != EM_BPF || ehdr->e_ident[EI_CLASS] != ELFCLASS64) { err = -EOPNOTSUPP; - pr_warn_elf("unsupported kind of ELF file %s", filename); + pr_warn_elf("unsupported kind of ELF file %s", obj->filename); return err; } if (elf_getshdrstrndx(obj->elf, &obj->shstrs_sec_idx)) { - err = -errno; - pr_warn_elf("failed to get SHSTRTAB section index for %s", filename); - return err; + pr_warn_elf("failed to get SHSTRTAB section index for %s", obj->filename); + return -EINVAL; } scn = NULL; @@ -618,26 +734,23 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, shdr = elf64_getshdr(scn); if (!shdr) { - err = -errno; pr_warn_elf("failed to get section #%zu header for %s", - sec_idx, filename); - return err; + sec_idx, obj->filename); + return -EINVAL; } sec_name = elf_strptr(obj->elf, obj->shstrs_sec_idx, shdr->sh_name); if (!sec_name) { - err = -errno; pr_warn_elf("failed to get section #%zu name for %s", - sec_idx, filename); - return err; + sec_idx, obj->filename); + return -EINVAL; } data = elf_getdata(scn, 0); if (!data) { - err = -errno; pr_warn_elf("failed to get section #%zu (%s) data from %s", - sec_idx, sec_name, filename); - return err; + sec_idx, sec_name, obj->filename); + return -EINVAL; } sec = add_src_sec(obj, sec_name); @@ -672,7 +785,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, err = libbpf_get_error(obj->btf); if (err) { pr_warn("failed to parse .BTF from %s: %s\n", - filename, errstr(err)); + obj->filename, errstr(err)); return err; } sec->skipped = true; @@ -683,7 +796,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, err = libbpf_get_error(obj->btf_ext); if (err) { pr_warn("failed to parse .BTF.ext from '%s': %s\n", - filename, errstr(err)); + obj->filename, errstr(err)); return err; } sec->skipped = true; @@ -700,7 +813,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, break; default: pr_warn("unrecognized section #%zu (%s) in %s\n", - sec_idx, sec_name, filename); + sec_idx, sec_name, obj->filename); err = -EINVAL; return err; } @@ -2680,22 +2793,23 @@ int bpf_linker__finalize(struct bpf_linker *linker) /* Finalize ELF layout */ if (elf_update(linker->elf, ELF_C_NULL) < 0) { - err = -errno; + err = -EINVAL; pr_warn_elf("failed to finalize ELF layout"); return libbpf_err(err); } /* Write out final ELF contents */ if (elf_update(linker->elf, ELF_C_WRITE) < 0) { - err = -errno; + err = -EINVAL; pr_warn_elf("failed to write ELF contents"); return libbpf_err(err); } elf_end(linker->elf); - close(linker->fd); - linker->elf = NULL; + + if (linker->fd_is_owned) + close(linker->fd); linker->fd = -1; return 0; diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 5f085736c6c4..4e4a52742b01 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -661,7 +661,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * * [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation */ usdt_abs_ip = note.loc_addr; - if (base_addr) + if (base_addr && note.base_addr) usdt_abs_ip += base_addr - note.base_addr; /* When attaching uprobes (which is what USDTs basically are) diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt index fcfb9499ef9c..59aabdd3cabf 100644 --- a/tools/lib/perf/Documentation/libperf.txt +++ b/tools/lib/perf/Documentation/libperf.txt @@ -39,7 +39,6 @@ SYNOPSIS struct perf_cpu_map *perf_cpu_map__new_any_cpu(void); struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); - struct perf_cpu_map *perf_cpu_map__read(FILE *file); struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, struct perf_cpu_map *other); diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index cae799ad44e1..fcc47214062a 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <errno.h> #include <perf/cpumap.h> #include <stdlib.h> #include <linux/refcount.h> @@ -10,6 +11,9 @@ #include <ctype.h> #include <limits.h> #include "internal.h" +#include <api/fs/fs.h> + +#define MAX_NR_CPUS 4096 void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus) { @@ -100,12 +104,12 @@ static struct perf_cpu_map *cpu_map__new_sysconf(void) static struct perf_cpu_map *cpu_map__new_sysfs_online(void) { struct perf_cpu_map *cpus = NULL; - FILE *onlnf; + char *buf = NULL; + size_t buf_len; - onlnf = fopen("/sys/devices/system/cpu/online", "r"); - if (onlnf) { - cpus = perf_cpu_map__read(onlnf); - fclose(onlnf); + if (sysfs__read_str("devices/system/cpu/online", &buf, &buf_len) >= 0) { + cpus = perf_cpu_map__new(buf); + free(buf); } return cpus; } @@ -158,62 +162,6 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu return cpus; } -struct perf_cpu_map *perf_cpu_map__read(FILE *file) -{ - struct perf_cpu_map *cpus = NULL; - int nr_cpus = 0; - struct perf_cpu *tmp_cpus = NULL, *tmp; - int max_entries = 0; - int n, cpu, prev; - char sep; - - sep = 0; - prev = -1; - for (;;) { - n = fscanf(file, "%u%c", &cpu, &sep); - if (n <= 0) - break; - if (prev >= 0) { - int new_max = nr_cpus + cpu - prev - 1; - - WARN_ONCE(new_max >= MAX_NR_CPUS, "Perf can support %d CPUs. " - "Consider raising MAX_NR_CPUS\n", MAX_NR_CPUS); - - if (new_max >= max_entries) { - max_entries = new_max + MAX_NR_CPUS / 2; - tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); - if (tmp == NULL) - goto out_free_tmp; - tmp_cpus = tmp; - } - - while (++prev < cpu) - tmp_cpus[nr_cpus++].cpu = prev; - } - if (nr_cpus == max_entries) { - max_entries += MAX_NR_CPUS; - tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); - if (tmp == NULL) - goto out_free_tmp; - tmp_cpus = tmp; - } - - tmp_cpus[nr_cpus++].cpu = cpu; - if (n == 2 && sep == '-') - prev = cpu; - else - prev = -1; - if (n == 1 || sep == '\n') - break; - } - - if (nr_cpus > 0) - cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); -out_free_tmp: - free(tmp_cpus); - return cpus; -} - struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) { struct perf_cpu_map *cpus = NULL; @@ -238,7 +186,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) p = NULL; start_cpu = strtoul(cpu_list, &p, 0); if (start_cpu >= INT_MAX - || (*p != '\0' && *p != ',' && *p != '-')) + || (*p != '\0' && *p != ',' && *p != '-' && *p != '\n')) goto invalid; if (*p == '-') { @@ -246,7 +194,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) p = NULL; end_cpu = strtoul(cpu_list, &p, 0); - if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',')) + if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',' && *p != '\n')) goto invalid; if (end_cpu < start_cpu) @@ -265,7 +213,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) goto invalid; if (nr_cpus == max_entries) { - max_entries += MAX_NR_CPUS; + max_entries += max(end_cpu - start_cpu + 1, 16UL); tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); if (tmp == NULL) goto invalid; @@ -279,14 +227,15 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) cpu_list = p; } - if (nr_cpus > 0) + if (nr_cpus > 0) { cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else if (*cpu_list != '\0') { + } else if (*cpu_list != '\0') { pr_warning("Unexpected characters at end of cpu list ('%s'), using online CPUs.", cpu_list); cpus = perf_cpu_map__new_online_cpus(); - } else + } else { cpus = perf_cpu_map__new_any_cpu(); + } invalid: free(tmp_cpus); out: @@ -436,46 +385,49 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu } /* - * Merge two cpumaps + * Merge two cpumaps. * - * orig either gets freed and replaced with a new map, or reused - * with no reference count change (similar to "realloc") - * other has its reference count increased. + * If 'other' is subset of '*orig', '*orig' keeps itself with no reference count + * change (similar to "realloc"). + * + * If '*orig' is subset of 'other', '*orig' reuses 'other' with its reference + * count increased. + * + * Otherwise, '*orig' gets freed and replaced with a new map. */ - -struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, - struct perf_cpu_map *other) +int perf_cpu_map__merge(struct perf_cpu_map **orig, struct perf_cpu_map *other) { struct perf_cpu *tmp_cpus; int tmp_len; int i, j, k; struct perf_cpu_map *merged; - if (perf_cpu_map__is_subset(orig, other)) - return orig; - if (perf_cpu_map__is_subset(other, orig)) { - perf_cpu_map__put(orig); - return perf_cpu_map__get(other); + if (perf_cpu_map__is_subset(*orig, other)) + return 0; + if (perf_cpu_map__is_subset(other, *orig)) { + perf_cpu_map__put(*orig); + *orig = perf_cpu_map__get(other); + return 0; } - tmp_len = __perf_cpu_map__nr(orig) + __perf_cpu_map__nr(other); + tmp_len = __perf_cpu_map__nr(*orig) + __perf_cpu_map__nr(other); tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu)); if (!tmp_cpus) - return NULL; + return -ENOMEM; /* Standard merge algorithm from wikipedia */ i = j = k = 0; - while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) { - if (__perf_cpu_map__cpu(orig, i).cpu <= __perf_cpu_map__cpu(other, j).cpu) { - if (__perf_cpu_map__cpu(orig, i).cpu == __perf_cpu_map__cpu(other, j).cpu) + while (i < __perf_cpu_map__nr(*orig) && j < __perf_cpu_map__nr(other)) { + if (__perf_cpu_map__cpu(*orig, i).cpu <= __perf_cpu_map__cpu(other, j).cpu) { + if (__perf_cpu_map__cpu(*orig, i).cpu == __perf_cpu_map__cpu(other, j).cpu) j++; - tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++); + tmp_cpus[k++] = __perf_cpu_map__cpu(*orig, i++); } else tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++); } - while (i < __perf_cpu_map__nr(orig)) - tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++); + while (i < __perf_cpu_map__nr(*orig)) + tmp_cpus[k++] = __perf_cpu_map__cpu(*orig, i++); while (j < __perf_cpu_map__nr(other)) tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++); @@ -483,8 +435,9 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, merged = cpu_map__trim_new(k, tmp_cpus); free(tmp_cpus); - perf_cpu_map__put(orig); - return merged; + perf_cpu_map__put(*orig); + *orig = merged; + return 0; } struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig, diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 83c43dc13313..b1f4c8176b32 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -89,7 +89,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, evsel->threads = perf_thread_map__get(evlist->threads); } - evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus); + perf_cpu_map__merge(&evlist->all_cpus, evsel->cpus); } static void perf_evlist__propagate_maps(struct perf_evlist *evlist) diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 49649eb51ce4..e2be2d17c32b 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -21,10 +21,6 @@ DECLARE_RC_STRUCT(perf_cpu_map) { struct perf_cpu map[]; }; -#ifndef MAX_NR_CPUS -#define MAX_NR_CPUS 2048 -#endif - struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus); int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu); bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b); diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 90457d17fb2f..188a667babc6 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -3,7 +3,6 @@ #define __LIBPERF_CPUMAP_H #include <perf/core.h> -#include <stdio.h> #include <stdbool.h> /** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */ @@ -37,10 +36,9 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_online_cpus(void); * perf_cpu_map__new_online_cpus is returned. */ LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); -LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file); LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); -LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, - struct perf_cpu_map *other); +LIBPERF_API int perf_cpu_map__merge(struct perf_cpu_map **orig, + struct perf_cpu_map *other); LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig, struct perf_cpu_map *other); LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map index 2aa79b696032..fdd8304fe9d0 100644 --- a/tools/lib/perf/libperf.map +++ b/tools/lib/perf/libperf.map @@ -6,7 +6,6 @@ LIBPERF_0.0.1 { perf_cpu_map__get; perf_cpu_map__put; perf_cpu_map__new; - perf_cpu_map__read; perf_cpu_map__nr; perf_cpu_map__cpu; perf_cpu_map__has_any_cpu_or_is_empty; diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index d1cdf2a8f826..211df5a93ad9 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -1,5 +1,17 @@ # SPDX-License-Identifier: GPL-2.0 +include ../../scripts/Makefile.arch + +INSTALL ?= install +prefix ?= /usr +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif +libdir ?= $(prefix)/$(libdir_relative) +includedir ?= $(prefix)/include + SUBDIRS = lib generated samples all: $(SUBDIRS) libynl.a @@ -21,5 +33,20 @@ clean distclean: fi \ done rm -f libynl.a + rm -rf pyynl/__pycache__ + rm -rf pyynl/lib/__pycache__ + rm -rf pyynl.egg-info + rm -rf build -.PHONY: all clean distclean $(SUBDIRS) +install: libynl.a lib/*.h + @echo -e "\tINSTALL libynl.a" + @$(INSTALL) -d $(DESTDIR)$(libdir) + @$(INSTALL) -m 0644 libynl.a $(DESTDIR)$(libdir)/libynl.a + @echo -e "\tINSTALL libynl headers" + @$(INSTALL) -d $(DESTDIR)$(includedir)/ynl + @$(INSTALL) -m 0644 lib/*.h $(DESTDIR)$(includedir)/ynl/ + @echo -e "\tINSTALL pyynl" + @pip install --prefix=$(DESTDIR)$(prefix) . + @make -C generated install + +.PHONY: all clean distclean install $(SUBDIRS) diff --git a/tools/net/ynl/generated/.gitignore b/tools/net/ynl/generated/.gitignore index ade488626d26..859a6fb446e1 100644 --- a/tools/net/ynl/generated/.gitignore +++ b/tools/net/ynl/generated/.gitignore @@ -1,2 +1,3 @@ *-user.c *-user.h +*.rst diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile index 7db5240de58a..21f9e299dc75 100644 --- a/tools/net/ynl/generated/Makefile +++ b/tools/net/ynl/generated/Makefile @@ -7,32 +7,44 @@ ifeq ("$(DEBUG)","1") CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan endif +INSTALL ?= install +prefix ?= /usr +datarootdir ?= $(prefix)/share +docdir ?= $(datarootdir)/doc +includedir ?= $(prefix)/include + include ../Makefile.deps YNL_GEN_ARG_ethtool:=--user-header linux/ethtool_netlink.h \ --exclude-op stats-get -TOOL:=../ynl-gen-c.py +TOOL:=../pyynl/ynl_gen_c.py +TOOL_RST:=../pyynl/ynl_gen_rst.py +SPECS_DIR:=../../../../Documentation/netlink/specs GENS_PATHS=$(shell grep -nrI --files-without-match \ 'protocol: netlink' \ - ../../../../Documentation/netlink/specs/) -GENS=$(patsubst ../../../../Documentation/netlink/specs/%.yaml,%,${GENS_PATHS}) + $(SPECS_DIR)) +GENS=$(patsubst $(SPECS_DIR)/%.yaml,%,${GENS_PATHS}) SRCS=$(patsubst %,%-user.c,${GENS}) HDRS=$(patsubst %,%-user.h,${GENS}) OBJS=$(patsubst %,%-user.o,${GENS}) -all: protos.a $(HDRS) $(SRCS) $(KHDRS) $(KSRCS) $(UAPI) +SPECS_PATHS=$(wildcard $(SPECS_DIR)/*.yaml) +SPECS=$(patsubst $(SPECS_DIR)/%.yaml,%,${SPECS_PATHS}) +RSTS=$(patsubst %,%.rst,${SPECS}) + +all: protos.a $(HDRS) $(SRCS) $(KHDRS) $(KSRCS) $(UAPI) $(RSTS) protos.a: $(OBJS) @echo -e "\tAR $@" @ar rcs $@ $(OBJS) -%-user.h: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) +%-user.h: $(SPECS_DIR)/%.yaml $(TOOL) @echo -e "\tGEN $@" @$(TOOL) --mode user --header --spec $< -o $@ $(YNL_GEN_ARG_$*) -%-user.c: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) +%-user.c: $(SPECS_DIR)/%.yaml $(TOOL) @echo -e "\tGEN $@" @$(TOOL) --mode user --source --spec $< -o $@ $(YNL_GEN_ARG_$*) @@ -40,14 +52,37 @@ protos.a: $(OBJS) @echo -e "\tCC $@" @$(COMPILE.c) $(CFLAGS_$*) -o $@ $< +%.rst: $(SPECS_DIR)/%.yaml $(TOOL_RST) + @echo -e "\tGEN_RST $@" + @$(TOOL_RST) -o $@ -i $< + clean: rm -f *.o distclean: clean - rm -f *.c *.h *.a + rm -f *.c *.h *.a *.rst regen: @../ynl-regen.sh -.PHONY: all clean distclean regen +install-headers: $(HDRS) + @echo -e "\tINSTALL generated headers" + @$(INSTALL) -d $(DESTDIR)$(includedir)/ynl + @$(INSTALL) -m 0644 *.h $(DESTDIR)$(includedir)/ynl/ + +install-rsts: $(RSTS) + @echo -e "\tINSTALL generated docs" + @$(INSTALL) -d $(DESTDIR)$(docdir)/ynl + @$(INSTALL) -m 0644 $(RSTS) $(DESTDIR)$(docdir)/ynl/ + +install-specs: + @echo -e "\tINSTALL specs" + @$(INSTALL) -d $(DESTDIR)$(datarootdir)/ynl + @$(INSTALL) -m 0644 ../../../../Documentation/netlink/*.yaml $(DESTDIR)$(datarootdir)/ynl/ + @$(INSTALL) -d $(DESTDIR)$(datarootdir)/ynl/specs + @$(INSTALL) -m 0644 $(SPECS_DIR)/*.yaml $(DESTDIR)$(datarootdir)/ynl/specs/ + +install: install-headers install-rsts install-specs + +.PHONY: all clean distclean regen install install-headers install-rsts install-specs .DEFAULT_GOAL: all diff --git a/tools/net/ynl/lib/.gitignore b/tools/net/ynl/lib/.gitignore index 296c4035dbf2..a4383358ec72 100644 --- a/tools/net/ynl/lib/.gitignore +++ b/tools/net/ynl/lib/.gitignore @@ -1,2 +1 @@ -__pycache__/ *.d diff --git a/tools/net/ynl/lib/Makefile b/tools/net/ynl/lib/Makefile index 94c49cca3dca..4b2b98704ff9 100644 --- a/tools/net/ynl/lib/Makefile +++ b/tools/net/ynl/lib/Makefile @@ -19,7 +19,6 @@ ynl.a: $(OBJS) clean: rm -f *.o *.d *~ - rm -rf __pycache__ distclean: clean rm -f *.a diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index e16cef160bc2..ce32cb35007d 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -95,7 +95,7 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off, ynl_attr_for_each_payload(start, data_len, attr) { astart_off = (char *)attr - (char *)start; - aend_off = astart_off + ynl_attr_data_len(attr); + aend_off = (char *)ynl_attr_data_end(attr) - (char *)start; if (aend_off <= off) continue; diff --git a/tools/net/ynl/pyproject.toml b/tools/net/ynl/pyproject.toml new file mode 100644 index 000000000000..a81d8779b0e0 --- /dev/null +++ b/tools/net/ynl/pyproject.toml @@ -0,0 +1,24 @@ +[build-system] +requires = ["setuptools>=61.0"] +build-backend = "setuptools.build_meta" + +[project] +name = "pyynl" +authors = [ + {name = "Donald Hunter", email = "donald.hunter@gmail.com"}, + {name = "Jakub Kicinski", email = "kuba@kernel.org"}, +] +description = "yaml netlink (ynl)" +version = "0.0.1" +requires-python = ">=3.9" +dependencies = [ + "pyyaml==6.*", + "jsonschema==4.*" +] + +[tool.setuptools.packages.find] +include = ["pyynl", "pyynl.lib"] + +[project.scripts] +ynl = "pyynl.cli:main" +ynl-ethtool = "pyynl.ethtool:main" diff --git a/tools/net/ynl/pyynl/.gitignore b/tools/net/ynl/pyynl/.gitignore new file mode 100644 index 000000000000..b801cd2d016e --- /dev/null +++ b/tools/net/ynl/pyynl/.gitignore @@ -0,0 +1,2 @@ +__pycache__/ +lib/__pycache__/ diff --git a/tools/net/ynl/pyynl/__init__.py b/tools/net/ynl/pyynl/__init__.py new file mode 100644 index 000000000000..e69de29bb2d1 diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/pyynl/cli.py similarity index 70% rename from tools/net/ynl/cli.py rename to tools/net/ynl/pyynl/cli.py index 41d9fa5c818d..794e3c7dcc65 100755 --- a/tools/net/ynl/cli.py +++ b/tools/net/ynl/pyynl/cli.py @@ -3,6 +3,7 @@ import argparse import json +import os import pathlib import pprint import sys @@ -10,6 +11,24 @@ import sys sys.path.append(pathlib.Path(__file__).resolve().parent.as_posix()) from lib import YnlFamily, Netlink, NlError +sys_schema_dir='/usr/share/ynl' +relative_schema_dir='../../../../Documentation/netlink' + +def schema_dir(): + script_dir = os.path.dirname(os.path.abspath(__file__)) + schema_dir = os.path.abspath(f"{script_dir}/{relative_schema_dir}") + if not os.path.isdir(schema_dir): + schema_dir = sys_schema_dir + if not os.path.isdir(schema_dir): + raise Exception(f"Schema directory {schema_dir} does not exist") + return schema_dir + +def spec_dir(): + spec_dir = schema_dir() + '/specs' + if not os.path.isdir(spec_dir): + raise Exception(f"Spec directory {spec_dir} does not exist") + return spec_dir + class YnlEncoder(json.JSONEncoder): def default(self, obj): @@ -32,7 +51,14 @@ def main(): parser = argparse.ArgumentParser(description=description, epilog=epilog) - parser.add_argument('--spec', dest='spec', type=str, required=True) + spec_group = parser.add_mutually_exclusive_group(required=True) + spec_group.add_argument('--family', dest='family', type=str, + help='name of the netlink FAMILY') + spec_group.add_argument('--list-families', action='store_true', + help='list all netlink families supported by YNL (has spec)') + spec_group.add_argument('--spec', dest='spec', type=str, + help='choose the family by SPEC file path') + parser.add_argument('--schema', dest='schema', type=str) parser.add_argument('--no-schema', action='store_true') parser.add_argument('--json', dest='json_text', type=str) @@ -70,6 +96,12 @@ def main(): else: pprint.PrettyPrinter().pprint(msg) + if args.list_families: + for filename in sorted(os.listdir(spec_dir())): + if filename.endswith('.yaml'): + print(filename.removesuffix('.yaml')) + return + if args.no_schema: args.schema = '' @@ -77,7 +109,16 @@ def main(): if args.json_text: attrs = json.loads(args.json_text) - ynl = YnlFamily(args.spec, args.schema, args.process_unknown, + if args.family: + spec = f"{spec_dir()}/{args.family}.yaml" + if args.schema is None and spec.startswith(sys_schema_dir): + args.schema = '' # disable schema validation when installed + else: + spec = args.spec + if not os.path.isfile(spec): + raise Exception(f"Spec file {spec} does not exist") + + ynl = YnlFamily(spec, args.schema, args.process_unknown, recv_size=args.dbg_small_recv) if args.dbg_small_recv: ynl.set_recv_dbg(True) diff --git a/tools/net/ynl/ethtool.py b/tools/net/ynl/pyynl/ethtool.py similarity index 98% rename from tools/net/ynl/ethtool.py rename to tools/net/ynl/pyynl/ethtool.py index ebb0a11f67bf..af7fddd7b085 100755 --- a/tools/net/ynl/ethtool.py +++ b/tools/net/ynl/pyynl/ethtool.py @@ -11,6 +11,7 @@ import os sys.path.append(pathlib.Path(__file__).resolve().parent.as_posix()) from lib import YnlFamily +from cli import schema_dir, spec_dir def args_to_req(ynl, op_name, args, req): """ @@ -156,10 +157,8 @@ def main(): args = parser.parse_args() script_abs_dir = os.path.dirname(os.path.abspath(sys.argv[0])) - spec = os.path.join(script_abs_dir, - '../../../Documentation/netlink/specs/ethtool.yaml') - schema = os.path.join(script_abs_dir, - '../../../Documentation/netlink/genetlink-legacy.yaml') + spec = os.path.join(spec_dir(), 'ethtool.yaml') + schema = os.path.join(schema_dir(), 'genetlink-legacy.yaml') ynl = YnlFamily(spec, schema) diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/pyynl/lib/__init__.py similarity index 100% rename from tools/net/ynl/lib/__init__.py rename to tools/net/ynl/pyynl/lib/__init__.py diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/pyynl/lib/nlspec.py similarity index 99% rename from tools/net/ynl/lib/nlspec.py rename to tools/net/ynl/pyynl/lib/nlspec.py index a745739655ad..314ec8007496 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/pyynl/lib/nlspec.py @@ -219,7 +219,10 @@ class SpecAttrSet(SpecElement): else: real_set = family.attr_sets[self.subset_of] for elem in self.yaml['attributes']: - attr = real_set[elem['name']] + real_attr = real_set[elem['name']] + combined_elem = real_attr.yaml | elem + attr = self.new_attr(combined_elem, real_attr.value) + self.attrs[attr.name] = attr self.attrs_by_val[attr.value] = attr diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py similarity index 93% rename from tools/net/ynl/lib/ynl.py rename to tools/net/ynl/pyynl/lib/ynl.py index 01ec01a90e76..08f8bf89cfc2 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -556,10 +556,10 @@ class YnlFamily(SpecFamily): if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED attr_payload = b'' - sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs) + sub_space = attr['nested-attributes'] + sub_attrs = SpaceAttrs(self.attr_sets[sub_space], value, search_attrs) for subname, subvalue in value.items(): - attr_payload += self._add_attr(attr['nested-attributes'], - subname, subvalue, sub_attrs) + attr_payload += self._add_attr(sub_space, subname, subvalue, sub_attrs) elif attr["type"] == 'flag': if not value: # If value is absent or false then skip attribute creation. @@ -733,41 +733,45 @@ class YnlFamily(SpecFamily): self._rsp_add(rsp, attr_name, None, self._decode_unknown(attr)) continue - if attr_spec["type"] == 'nest': - subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'], search_attrs) - decoded = subdict - elif attr_spec["type"] == 'string': - decoded = attr.as_strz() - elif attr_spec["type"] == 'binary': - decoded = self._decode_binary(attr, attr_spec) - elif attr_spec["type"] == 'flag': - decoded = True - elif attr_spec.is_auto_scalar: - decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order) - elif attr_spec["type"] in NlAttr.type_formats: - decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) - if 'enum' in attr_spec: - decoded = self._decode_enum(decoded, attr_spec) - elif attr_spec.display_hint: - decoded = self._formatted_string(decoded, attr_spec.display_hint) - elif attr_spec["type"] == 'indexed-array': - decoded = self._decode_array_attr(attr, attr_spec) - elif attr_spec["type"] == 'bitfield32': - value, selector = struct.unpack("II", attr.raw) - if 'enum' in attr_spec: - value = self._decode_enum(value, attr_spec) - selector = self._decode_enum(selector, attr_spec) - decoded = {"value": value, "selector": selector} - elif attr_spec["type"] == 'sub-message': - decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) - elif attr_spec["type"] == 'nest-type-value': - decoded = self._decode_nest_type_value(attr, attr_spec) - else: - if not self.process_unknown: - raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') - decoded = self._decode_unknown(attr) + try: + if attr_spec["type"] == 'nest': + subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'], search_attrs) + decoded = subdict + elif attr_spec["type"] == 'string': + decoded = attr.as_strz() + elif attr_spec["type"] == 'binary': + decoded = self._decode_binary(attr, attr_spec) + elif attr_spec["type"] == 'flag': + decoded = True + elif attr_spec.is_auto_scalar: + decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order) + elif attr_spec["type"] in NlAttr.type_formats: + decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) + if 'enum' in attr_spec: + decoded = self._decode_enum(decoded, attr_spec) + elif attr_spec.display_hint: + decoded = self._formatted_string(decoded, attr_spec.display_hint) + elif attr_spec["type"] == 'indexed-array': + decoded = self._decode_array_attr(attr, attr_spec) + elif attr_spec["type"] == 'bitfield32': + value, selector = struct.unpack("II", attr.raw) + if 'enum' in attr_spec: + value = self._decode_enum(value, attr_spec) + selector = self._decode_enum(selector, attr_spec) + decoded = {"value": value, "selector": selector} + elif attr_spec["type"] == 'sub-message': + decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) + elif attr_spec["type"] == 'nest-type-value': + decoded = self._decode_nest_type_value(attr, attr_spec) + else: + if not self.process_unknown: + raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') + decoded = self._decode_unknown(attr) - self._rsp_add(rsp, attr_spec["name"], attr_spec.is_multi, decoded) + self._rsp_add(rsp, attr_spec["name"], attr_spec.is_multi, decoded) + except: + print(f"Error decoding '{attr_spec.name}' from '{space}'") + raise return rsp diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/pyynl/ynl_gen_c.py similarity index 95% rename from tools/net/ynl/ynl-gen-c.py rename to tools/net/ynl/pyynl/ynl_gen_c.py index d8201c4b1520..c2eabc90dce8 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -79,6 +79,20 @@ class Type(SpecAttr): self.enum_name = None delattr(self, "enum_name") + def _get_real_attr(self): + # if the attr is for a subset return the "real" attr (just one down, does not recurse) + return self.family.attr_sets[self.attr_set.subset_of][self.name] + + def set_request(self): + self.request = True + if self.attr_set.subset_of: + self._get_real_attr().set_request() + + def set_reply(self): + self.reply = True + if self.attr_set.subset_of: + self._get_real_attr().set_reply() + def get_limit(self, limit, default=None): value = self.checks.get(limit, default) if value is None: @@ -106,6 +120,10 @@ class Type(SpecAttr): enum_name = f"{self.attr_set.name_prefix}{self.name}" self.enum_name = c_upper(enum_name) + if self.attr_set.subset_of: + if self.checks != self._get_real_attr().checks: + raise Exception("Overriding checks not supported by codegen, yet") + def is_multi_val(self): return None @@ -801,6 +819,8 @@ class EnumSet(SpecEnumSet): self.user_type = 'int' self.value_pfx = yaml.get('name-prefix', f"{family.ident_name}-{yaml['name']}-") + self.header = yaml.get('header', None) + self.enum_cnt_name = yaml.get('enum-cnt-name', None) super().__init__(family, yaml) @@ -1117,17 +1137,17 @@ class Family(SpecFamily): for _, struct in self.pure_nested_structs.items(): if struct.request: for _, arg in struct.member_list(): - arg.request = True + arg.set_request() if struct.reply: for _, arg in struct.member_list(): - arg.reply = True + arg.set_reply() for root_set, rs_members in self.root_sets.items(): for attr, spec in self.attr_sets[root_set].items(): if attr in rs_members['request']: - spec.request = True + spec.set_request() if attr in rs_members['reply']: - spec.reply = True + spec.set_reply() def _load_global_policy(self): global_set = set() @@ -1763,7 +1783,14 @@ def parse_rsp_nested(ri, struct): f'{struct.ptr_name}dst = yarg->data;'] init_lines = [] - _multi_parse(ri, struct, init_lines, local_vars) + if struct.member_list(): + _multi_parse(ri, struct, init_lines, local_vars) + else: + # Empty nest + ri.cw.block_start() + ri.cw.p('return 0;') + ri.cw.block_end() + ri.cw.nl() def parse_rsp_msg(ri, deref=False): @@ -2384,6 +2411,17 @@ def print_kernel_family_struct_src(family, cw): if not kernel_can_gen_family_struct(family): return + if 'sock-priv' in family.kernel_family: + # Generate "trampolines" to make CFI happy + cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_init", + [f"{family.c_name}_nl_sock_priv_init(priv);"], + ["void *priv"]) + cw.nl() + cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_destroy", + [f"{family.c_name}_nl_sock_priv_destroy(priv);"], + ["void *priv"]) + cw.nl() + cw.block_start(f"struct genl_family {family.ident_name}_nl_family __ro_after_init =") cw.p('.name\t\t= ' + family.fam_key + ',') cw.p('.version\t= ' + family.ver_key + ',') @@ -2401,9 +2439,8 @@ def print_kernel_family_struct_src(family, cw): cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.c_name}_nl_mcgrps),') if 'sock-priv' in family.kernel_family: cw.p(f'.sock_priv_size\t= sizeof({family.kernel_family["sock-priv"]}),') - # Force cast here, actual helpers take pointer to the real type. - cw.p(f'.sock_priv_init\t= (void *){family.c_name}_nl_sock_priv_init,') - cw.p(f'.sock_priv_destroy = (void *){family.c_name}_nl_sock_priv_destroy,') + cw.p(f'.sock_priv_init\t= __{family.c_name}_nl_sock_priv_init,') + cw.p(f'.sock_priv_destroy = __{family.c_name}_nl_sock_priv_destroy,') cw.block_end(';') @@ -2417,6 +2454,87 @@ def uapi_enum_start(family, cw, obj, ckey='', enum_name='enum-name'): cw.block_start(line=start_line) +def render_uapi_unified(family, cw, max_by_define, separate_ntf): + max_name = c_upper(family.get('cmd-max-name', f"{family.op_prefix}MAX")) + cnt_name = c_upper(family.get('cmd-cnt-name', f"__{family.op_prefix}MAX")) + max_value = f"({cnt_name} - 1)" + + uapi_enum_start(family, cw, family['operations'], 'enum-name') + val = 0 + for op in family.msgs.values(): + if separate_ntf and ('notify' in op or 'event' in op): + continue + + suffix = ',' + if op.value != val: + suffix = f" = {op.value}," + val = op.value + cw.p(op.enum_name + suffix) + val += 1 + cw.nl() + cw.p(cnt_name + ('' if max_by_define else ',')) + if not max_by_define: + cw.p(f"{max_name} = {max_value}") + cw.block_end(line=';') + if max_by_define: + cw.p(f"#define {max_name} {max_value}") + cw.nl() + + +def render_uapi_directional(family, cw, max_by_define): + max_name = f"{family.op_prefix}USER_MAX" + cnt_name = f"__{family.op_prefix}USER_CNT" + max_value = f"({cnt_name} - 1)" + + cw.block_start(line='enum') + cw.p(c_upper(f'{family.name}_MSG_USER_NONE = 0,')) + val = 0 + for op in family.msgs.values(): + if 'do' in op and 'event' not in op: + suffix = ',' + if op.value and op.value != val: + suffix = f" = {op.value}," + val = op.value + cw.p(op.enum_name + suffix) + val += 1 + cw.nl() + cw.p(cnt_name + ('' if max_by_define else ',')) + if not max_by_define: + cw.p(f"{max_name} = {max_value}") + cw.block_end(line=';') + if max_by_define: + cw.p(f"#define {max_name} {max_value}") + cw.nl() + + max_name = f"{family.op_prefix}KERNEL_MAX" + cnt_name = f"__{family.op_prefix}KERNEL_CNT" + max_value = f"({cnt_name} - 1)" + + cw.block_start(line='enum') + cw.p(c_upper(f'{family.name}_MSG_KERNEL_NONE = 0,')) + val = 0 + for op in family.msgs.values(): + if ('do' in op and 'reply' in op['do']) or 'notify' in op or 'event' in op: + enum_name = op.enum_name + if 'event' not in op and 'notify' not in op: + enum_name = f'{enum_name}_REPLY' + + suffix = ',' + if op.value and op.value != val: + suffix = f" = {op.value}," + val = op.value + cw.p(enum_name + suffix) + val += 1 + cw.nl() + cw.p(cnt_name + ('' if max_by_define else ',')) + if not max_by_define: + cw.p(f"{max_name} = {max_value}") + cw.block_end(line=';') + if max_by_define: + cw.p(f"#define {max_name} {max_value}") + cw.nl() + + def render_uapi(family, cw): hdr_prot = f"_UAPI_LINUX_{c_upper(family.uapi_header_name)}_H" hdr_prot = hdr_prot.replace('/', '_') @@ -2440,6 +2558,9 @@ def render_uapi(family, cw): if const['type'] == 'enum' or const['type'] == 'flags': enum = family.consts[const['name']] + if enum.header: + continue + if enum.has_doc(): if enum.has_entry_doc(): cw.p('/**') @@ -2472,9 +2593,12 @@ def render_uapi(family, cw): max_val = f' = {enum.get_mask()},' cw.p(max_name + max_val) else: + cnt_name = enum.enum_cnt_name max_name = c_upper(name_pfx + 'max') - cw.p('__' + max_name + ',') - cw.p(max_name + ' = (__' + max_name + ' - 1)') + if not cnt_name: + cnt_name = '__' + name_pfx + 'max' + cw.p(c_upper(cnt_name) + ',') + cw.p(max_name + ' = (' + c_upper(cnt_name) + ' - 1)') cw.block_end(line=';') cw.nl() elif const['type'] == 'const': @@ -2503,7 +2627,8 @@ def render_uapi(family, cw): val = attr.value val += 1 cw.p(attr.enum_name + suffix) - cw.nl() + if attr_set.items(): + cw.nl() cw.p(attr_set.cnt_name + ('' if max_by_define else ',')) if not max_by_define: cw.p(f"{attr_set.max_name} = {max_value}") @@ -2515,30 +2640,12 @@ def render_uapi(family, cw): # Commands separate_ntf = 'async-prefix' in family['operations'] - max_name = c_upper(family.get('cmd-max-name', f"{family.op_prefix}MAX")) - cnt_name = c_upper(family.get('cmd-cnt-name', f"__{family.op_prefix}MAX")) - max_value = f"({cnt_name} - 1)" - - uapi_enum_start(family, cw, family['operations'], 'enum-name') - val = 0 - for op in family.msgs.values(): - if separate_ntf and ('notify' in op or 'event' in op): - continue - - suffix = ',' - if op.value != val: - suffix = f" = {op.value}," - val = op.value - cw.p(op.enum_name + suffix) - val += 1 - cw.nl() - cw.p(cnt_name + ('' if max_by_define else ',')) - if not max_by_define: - cw.p(f"{max_name} = {max_value}") - cw.block_end(line=';') - if max_by_define: - cw.p(f"#define {max_name} {max_value}") - cw.nl() + if family.msg_id_model == 'unified': + render_uapi_unified(family, cw, max_by_define, separate_ntf) + elif family.msg_id_model == 'directional': + render_uapi_directional(family, cw, max_by_define) + else: + raise Exception(f'Unsupported message enum-model {family.msg_id_model}') if separate_ntf: uapi_enum_start(family, cw, family['operations'], enum_name='async-enum') @@ -2635,7 +2742,8 @@ def find_kernel_root(full_path): def main(): parser = argparse.ArgumentParser(description='Netlink simple parsing generator') - parser.add_argument('--mode', dest='mode', type=str, required=True) + parser.add_argument('--mode', dest='mode', type=str, required=True, + choices=('user', 'kernel', 'uapi')) parser.add_argument('--spec', dest='spec', type=str, required=True) parser.add_argument('--header', dest='header', action='store_true', default=None) parser.add_argument('--source', dest='header', action='store_false') @@ -2662,13 +2770,6 @@ def main(): os.sys.exit(1) return - supported_models = ['unified'] - if args.mode in ['user', 'kernel']: - supported_models += ['directional'] - if parsed.msg_id_model not in supported_models: - print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation') - os.sys.exit(1) - cw = CodeWriter(BaseNlLib(), args.out_file, overwrite=(not args.cmp_out)) _, spec_kernel = find_kernel_root(args.spec) @@ -2696,7 +2797,10 @@ def main(): cw.p('#define ' + hdr_prot) cw.nl() - hdr_file=os.path.basename(args.out_file[:-2]) + ".h" + if args.out_file: + hdr_file = os.path.basename(args.out_file[:-2]) + ".h" + else: + hdr_file = "generated_header_file.h" if args.mode == 'kernel': cw.p('#include <net/netlink.h>') @@ -2718,12 +2822,17 @@ def main(): else: cw.p(f'#include "{hdr_file}"') cw.p('#include "ynl.h"') - headers = [parsed.uapi_header] + headers = [] for definition in parsed['definitions']: if 'header' in definition: headers.append(definition['header']) + if args.mode == 'user': + headers.append(parsed.uapi_header) + seen_header = [] for one in headers: - cw.p(f"#include <{one}>") + if one not in seen_header: + cw.p(f"#include <{one}>") + seen_header.append(one) cw.nl() if args.mode == "user": diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/pyynl/ynl_gen_rst.py similarity index 100% rename from tools/net/ynl/ynl-gen-rst.py rename to tools/net/ynl/pyynl/ynl_gen_rst.py diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index a37304dcc88e..81b4ecd89100 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -1,7 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause -TOOL=$(dirname $(realpath $0))/ynl-gen-c.py +TOOL=$(dirname $(realpath $0))/pyynl/ynl_gen_c.py force= search= diff --git a/tools/objtool/arch/loongarch/special.c b/tools/objtool/arch/loongarch/special.c index 9bba1e9318e0..87230ed570fd 100644 --- a/tools/objtool/arch/loongarch/special.c +++ b/tools/objtool/arch/loongarch/special.c @@ -9,7 +9,8 @@ bool arch_support_alt_relocation(struct special_alt *special_alt, } struct reloc *arch_find_switch_table(struct objtool_file *file, - struct instruction *insn) + struct instruction *insn, + unsigned long *table_size) { return NULL; } diff --git a/tools/objtool/arch/powerpc/special.c b/tools/objtool/arch/powerpc/special.c index d33868147196..51610689abf7 100644 --- a/tools/objtool/arch/powerpc/special.c +++ b/tools/objtool/arch/powerpc/special.c @@ -13,7 +13,8 @@ bool arch_support_alt_relocation(struct special_alt *special_alt, } struct reloc *arch_find_switch_table(struct objtool_file *file, - struct instruction *insn) + struct instruction *insn, + unsigned long *table_size) { exit(-1); } diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c index 4ea0f9815fda..9c1c9df09aaa 100644 --- a/tools/objtool/arch/x86/special.c +++ b/tools/objtool/arch/x86/special.c @@ -109,7 +109,8 @@ bool arch_support_alt_relocation(struct special_alt *special_alt, * NOTE: MITIGATION_RETPOLINE made it harder still to decode dynamic jumps. */ struct reloc *arch_find_switch_table(struct objtool_file *file, - struct instruction *insn) + struct instruction *insn, + unsigned long *table_size) { struct reloc *text_reloc, *rodata_reloc; struct section *table_sec; @@ -158,5 +159,6 @@ struct reloc *arch_find_switch_table(struct objtool_file *file, if (reloc_type(text_reloc) == R_X86_64_PC32) file->ignore_unreachables = true; + *table_size = 0; return rodata_reloc; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4ce176ad411f..753dbc4f8198 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -150,6 +150,15 @@ static inline struct reloc *insn_jump_table(struct instruction *insn) return NULL; } +static inline unsigned long insn_jump_table_size(struct instruction *insn) +{ + if (insn->type == INSN_JUMP_DYNAMIC || + insn->type == INSN_CALL_DYNAMIC) + return insn->_jump_table_size; + + return 0; +} + static bool is_jump_table_jump(struct instruction *insn) { struct alt_group *alt_group = insn->alt_group; @@ -614,108 +623,6 @@ static int init_pv_ops(struct objtool_file *file) return 0; } -static struct instruction *find_last_insn(struct objtool_file *file, - struct section *sec) -{ - struct instruction *insn = NULL; - unsigned int offset; - unsigned int end = (sec->sh.sh_size > 10) ? sec->sh.sh_size - 10 : 0; - - for (offset = sec->sh.sh_size - 1; offset >= end && !insn; offset--) - insn = find_insn(file, sec, offset); - - return insn; -} - -/* - * Mark "ud2" instructions and manually annotated dead ends. - */ -static int add_dead_ends(struct objtool_file *file) -{ - struct section *rsec; - struct reloc *reloc; - struct instruction *insn; - uint64_t offset; - - /* - * Check for manually annotated dead ends. - */ - rsec = find_section_by_name(file->elf, ".rela.discard.unreachable"); - if (!rsec) - goto reachable; - - for_each_reloc(rsec, reloc) { - if (reloc->sym->type == STT_SECTION) { - offset = reloc_addend(reloc); - } else if (reloc->sym->local_label) { - offset = reloc->sym->offset; - } else { - WARN("unexpected relocation symbol type in %s", rsec->name); - return -1; - } - - insn = find_insn(file, reloc->sym->sec, offset); - if (insn) - insn = prev_insn_same_sec(file, insn); - else if (offset == reloc->sym->sec->sh.sh_size) { - insn = find_last_insn(file, reloc->sym->sec); - if (!insn) { - WARN("can't find unreachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, offset); - return -1; - } - } else { - WARN("can't find unreachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, offset); - return -1; - } - - insn->dead_end = true; - } - -reachable: - /* - * These manually annotated reachable checks are needed for GCC 4.4, - * where the Linux unreachable() macro isn't supported. In that case - * GCC doesn't know the "ud2" is fatal, so it generates code as if it's - * not a dead end. - */ - rsec = find_section_by_name(file->elf, ".rela.discard.reachable"); - if (!rsec) - return 0; - - for_each_reloc(rsec, reloc) { - if (reloc->sym->type == STT_SECTION) { - offset = reloc_addend(reloc); - } else if (reloc->sym->local_label) { - offset = reloc->sym->offset; - } else { - WARN("unexpected relocation symbol type in %s", rsec->name); - return -1; - } - - insn = find_insn(file, reloc->sym->sec, offset); - if (insn) - insn = prev_insn_same_sec(file, insn); - else if (offset == reloc->sym->sec->sh.sh_size) { - insn = find_last_insn(file, reloc->sym->sec); - if (!insn) { - WARN("can't find reachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, offset); - return -1; - } - } else { - WARN("can't find reachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, offset); - return -1; - } - - insn->dead_end = false; - } - - return 0; -} - static int create_static_call_sections(struct objtool_file *file) { struct static_call_site *site; @@ -1309,40 +1216,6 @@ static void add_uaccess_safe(struct objtool_file *file) } } -/* - * FIXME: For now, just ignore any alternatives which add retpolines. This is - * a temporary hack, as it doesn't allow ORC to unwind from inside a retpoline. - * But it at least allows objtool to understand the control flow *around* the - * retpoline. - */ -static int add_ignore_alternatives(struct objtool_file *file) -{ - struct section *rsec; - struct reloc *reloc; - struct instruction *insn; - - rsec = find_section_by_name(file->elf, ".rela.discard.ignore_alts"); - if (!rsec) - return 0; - - for_each_reloc(rsec, reloc) { - if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", rsec->name); - return -1; - } - - insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); - if (!insn) { - WARN("bad .discard.ignore_alts entry"); - return -1; - } - - insn->ignore_alts = true; - } - - return 0; -} - /* * Symbols that replace INSN_CALL_DYNAMIC, every (tail) call to such a symbol * will be added to the .retpoline_sites section. @@ -2073,6 +1946,7 @@ out: static int add_jump_table(struct objtool_file *file, struct instruction *insn, struct reloc *next_table) { + unsigned long table_size = insn_jump_table_size(insn); struct symbol *pfunc = insn_func(insn)->pfunc; struct reloc *table = insn_jump_table(insn); struct instruction *dest_insn; @@ -2087,6 +1961,8 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, for_each_reloc_from(table->sec, reloc) { /* Check for the end of the table: */ + if (table_size && reloc_offset(reloc) - reloc_offset(table) >= table_size) + break; if (reloc != table && reloc == next_table) break; @@ -2131,12 +2007,12 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, * find_jump_table() - Given a dynamic jump, find the switch jump table * associated with it. */ -static struct reloc *find_jump_table(struct objtool_file *file, - struct symbol *func, - struct instruction *insn) +static void find_jump_table(struct objtool_file *file, struct symbol *func, + struct instruction *insn) { struct reloc *table_reloc; struct instruction *dest_insn, *orig_insn = insn; + unsigned long table_size; /* * Backward search using the @first_jump_src links, these help avoid @@ -2157,17 +2033,17 @@ static struct reloc *find_jump_table(struct objtool_file *file, insn->jump_dest->offset > orig_insn->offset)) break; - table_reloc = arch_find_switch_table(file, insn); + table_reloc = arch_find_switch_table(file, insn, &table_size); if (!table_reloc) continue; dest_insn = find_insn(file, table_reloc->sym->sec, reloc_addend(table_reloc)); if (!dest_insn || !insn_func(dest_insn) || insn_func(dest_insn)->pfunc != func) continue; - return table_reloc; + orig_insn->_jump_table = table_reloc; + orig_insn->_jump_table_size = table_size; + break; } - - return NULL; } /* @@ -2178,7 +2054,6 @@ static void mark_func_jump_tables(struct objtool_file *file, struct symbol *func) { struct instruction *insn, *last = NULL; - struct reloc *reloc; func_for_each_insn(file, func, insn) { if (!last) @@ -2201,9 +2076,7 @@ static void mark_func_jump_tables(struct objtool_file *file, if (insn->type != INSN_JUMP_DYNAMIC) continue; - reloc = find_jump_table(file, func, insn); - if (reloc) - insn->_jump_table = reloc; + find_jump_table(file, func, insn); } } @@ -2373,52 +2246,109 @@ static int read_unwind_hints(struct objtool_file *file) return 0; } -static int read_noendbr_hints(struct objtool_file *file) +static int read_annotate(struct objtool_file *file, + int (*func)(struct objtool_file *file, int type, struct instruction *insn)) { + struct section *sec; struct instruction *insn; - struct section *rsec; struct reloc *reloc; + uint64_t offset; + int type, ret; - rsec = find_section_by_name(file->elf, ".rela.discard.noendbr"); - if (!rsec) + sec = find_section_by_name(file->elf, ".discard.annotate_insn"); + if (!sec) return 0; - for_each_reloc(rsec, reloc) { - insn = find_insn(file, reloc->sym->sec, - reloc->sym->offset + reloc_addend(reloc)); + if (!sec->rsec) + return 0; + + if (sec->sh.sh_entsize != 8) { + static bool warned = false; + if (!warned) { + WARN("%s: dodgy linker, sh_entsize != 8", sec->name); + warned = true; + } + sec->sh.sh_entsize = 8; + } + + for_each_reloc(sec->rsec, reloc) { + type = *(u32 *)(sec->data->d_buf + (reloc_idx(reloc) * sec->sh.sh_entsize) + 4); + + offset = reloc->sym->offset + reloc_addend(reloc); + insn = find_insn(file, reloc->sym->sec, offset); + if (!insn) { - WARN("bad .discard.noendbr entry"); + WARN("bad .discard.annotate_insn entry: %d of type %d", reloc_idx(reloc), type); return -1; } - insn->noendbr = 1; + ret = func(file, type, insn); + if (ret < 0) + return ret; } return 0; } -static int read_retpoline_hints(struct objtool_file *file) +static int __annotate_early(struct objtool_file *file, int type, struct instruction *insn) { - struct section *rsec; - struct instruction *insn; - struct reloc *reloc; + switch (type) { + case ANNOTYPE_IGNORE_ALTS: + insn->ignore_alts = true; + break; - rsec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); - if (!rsec) + /* + * Must be before read_unwind_hints() since that needs insn->noendbr. + */ + case ANNOTYPE_NOENDBR: + insn->noendbr = 1; + break; + + default: + break; + } + + return 0; +} + +static int __annotate_ifc(struct objtool_file *file, int type, struct instruction *insn) +{ + unsigned long dest_off; + + if (type != ANNOTYPE_INTRA_FUNCTION_CALL) return 0; - for_each_reloc(rsec, reloc) { - if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", rsec->name); - return -1; - } + if (insn->type != INSN_CALL) { + WARN_INSN(insn, "intra_function_call not a direct call"); + return -1; + } - insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); - if (!insn) { - WARN("bad .discard.retpoline_safe entry"); - return -1; - } + /* + * Treat intra-function CALLs as JMPs, but with a stack_op. + * See add_call_destinations(), which strips stack_ops from + * normal CALLs. + */ + insn->type = INSN_JUMP_UNCONDITIONAL; + dest_off = arch_jump_destination(insn); + insn->jump_dest = find_insn(file, insn->sec, dest_off); + if (!insn->jump_dest) { + WARN_INSN(insn, "can't find call dest at %s+0x%lx", + insn->sec->name, dest_off); + return -1; + } + + return 0; +} + +static int __annotate_late(struct objtool_file *file, int type, struct instruction *insn) +{ + switch (type) { + case ANNOTYPE_NOENDBR: + /* early */ + break; + + case ANNOTYPE_RETPOLINE_SAFE: if (insn->type != INSN_JUMP_DYNAMIC && insn->type != INSN_CALL_DYNAMIC && insn->type != INSN_RETURN && @@ -2428,130 +2358,35 @@ static int read_retpoline_hints(struct objtool_file *file) } insn->retpoline_safe = true; - } - - return 0; -} - -static int read_instr_hints(struct objtool_file *file) -{ - struct section *rsec; - struct instruction *insn; - struct reloc *reloc; - - rsec = find_section_by_name(file->elf, ".rela.discard.instr_end"); - if (!rsec) - return 0; - - for_each_reloc(rsec, reloc) { - if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", rsec->name); - return -1; - } - - insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); - if (!insn) { - WARN("bad .discard.instr_end entry"); - return -1; - } - - insn->instr--; - } - - rsec = find_section_by_name(file->elf, ".rela.discard.instr_begin"); - if (!rsec) - return 0; - - for_each_reloc(rsec, reloc) { - if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", rsec->name); - return -1; - } - - insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); - if (!insn) { - WARN("bad .discard.instr_begin entry"); - return -1; - } + break; + case ANNOTYPE_INSTR_BEGIN: insn->instr++; - } + break; - return 0; -} + case ANNOTYPE_INSTR_END: + insn->instr--; + break; -static int read_validate_unret_hints(struct objtool_file *file) -{ - struct section *rsec; - struct instruction *insn; - struct reloc *reloc; - - rsec = find_section_by_name(file->elf, ".rela.discard.validate_unret"); - if (!rsec) - return 0; - - for_each_reloc(rsec, reloc) { - if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", rsec->name); - return -1; - } - - insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); - if (!insn) { - WARN("bad .discard.instr_end entry"); - return -1; - } + case ANNOTYPE_UNRET_BEGIN: insn->unret = 1; - } + break; - return 0; -} + case ANNOTYPE_IGNORE_ALTS: + /* early */ + break; + case ANNOTYPE_INTRA_FUNCTION_CALL: + /* ifc */ + break; -static int read_intra_function_calls(struct objtool_file *file) -{ - struct instruction *insn; - struct section *rsec; - struct reloc *reloc; + case ANNOTYPE_REACHABLE: + insn->dead_end = false; + break; - rsec = find_section_by_name(file->elf, ".rela.discard.intra_function_calls"); - if (!rsec) - return 0; - - for_each_reloc(rsec, reloc) { - unsigned long dest_off; - - if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", - rsec->name); - return -1; - } - - insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); - if (!insn) { - WARN("bad .discard.intra_function_call entry"); - return -1; - } - - if (insn->type != INSN_CALL) { - WARN_INSN(insn, "intra_function_call not a direct call"); - return -1; - } - - /* - * Treat intra-function CALLs as JMPs, but with a stack_op. - * See add_call_destinations(), which strips stack_ops from - * normal CALLs. - */ - insn->type = INSN_JUMP_UNCONDITIONAL; - - dest_off = arch_jump_destination(insn); - insn->jump_dest = find_insn(file, insn->sec, dest_off); - if (!insn->jump_dest) { - WARN_INSN(insn, "can't find call dest at %s+0x%lx", - insn->sec->name, dest_off); - return -1; - } + default: + WARN_INSN(insn, "Unknown annotation type: %d", type); + break; } return 0; @@ -2666,14 +2501,7 @@ static int decode_sections(struct objtool_file *file) add_ignores(file); add_uaccess_safe(file); - ret = add_ignore_alternatives(file); - if (ret) - return ret; - - /* - * Must be before read_unwind_hints() since that needs insn->noendbr. - */ - ret = read_noendbr_hints(file); + ret = read_annotate(file, __annotate_early); if (ret) return ret; @@ -2695,7 +2523,7 @@ static int decode_sections(struct objtool_file *file) * Must be before add_call_destination(); it changes INSN_CALL to * INSN_JUMP. */ - ret = read_intra_function_calls(file); + ret = read_annotate(file, __annotate_ifc); if (ret) return ret; @@ -2703,14 +2531,6 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - /* - * Must be after add_call_destinations() such that it can override - * dead_end_function() marks. - */ - ret = add_dead_ends(file); - if (ret) - return ret; - ret = add_jump_table_alts(file); if (ret) return ret; @@ -2719,15 +2539,11 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - ret = read_retpoline_hints(file); - if (ret) - return ret; - - ret = read_instr_hints(file); - if (ret) - return ret; - - ret = read_validate_unret_hints(file); + /* + * Must be after add_call_destinations() such that it can override + * dead_end_function() marks. + */ + ret = read_annotate(file, __annotate_late); if (ret) return ret; @@ -3820,9 +3636,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; case INSN_CONTEXT_SWITCH: - if (func && (!next_insn || !next_insn->hint)) { - WARN_INSN(insn, "unsupported instruction in callable function"); - return 1; + if (func) { + if (!next_insn || !next_insn->hint) { + WARN_INSN(insn, "unsupported instruction in callable function"); + return 1; + } + break; } return 0; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index daa46f1f0965..e1cd13cd28a3 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -71,7 +71,10 @@ struct instruction { struct instruction *first_jump_src; union { struct symbol *_call_dest; - struct reloc *_jump_table; + struct { + struct reloc *_jump_table; + unsigned long _jump_table_size; + }; }; struct alternative *alts; struct symbol *sym; diff --git a/tools/objtool/include/objtool/special.h b/tools/objtool/include/objtool/special.h index 86d4af9c5aa9..e7ee7ffccefd 100644 --- a/tools/objtool/include/objtool/special.h +++ b/tools/objtool/include/objtool/special.h @@ -38,5 +38,6 @@ bool arch_support_alt_relocation(struct special_alt *special_alt, struct instruction *insn, struct reloc *reloc); struct reloc *arch_find_switch_table(struct objtool_file *file, - struct instruction *insn); + struct instruction *insn, + unsigned long *table_size); #endif /* _SPECIAL_H */ diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index f37614cc2c1b..b2174894f9f7 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -19,6 +19,7 @@ NORETURN(__x64_sys_exit_group) NORETURN(arch_cpu_idle_dead) NORETURN(bch2_trans_in_restart_error) NORETURN(bch2_trans_restart_error) +NORETURN(bch2_trans_unlocked_error) NORETURN(cpu_bringup_and_idle) NORETURN(cpu_startup_entry) NORETURN(do_exit) diff --git a/tools/pci/Build b/tools/pci/Build deleted file mode 100644 index c375aea21790..000000000000 --- a/tools/pci/Build +++ /dev/null @@ -1 +0,0 @@ -pcitest-y += pcitest.o diff --git a/tools/pci/Makefile b/tools/pci/Makefile deleted file mode 100644 index 62d41f1a1e2c..000000000000 --- a/tools/pci/Makefile +++ /dev/null @@ -1,58 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -include ../scripts/Makefile.include - -bindir ?= /usr/bin - -ifeq ($(srctree),) -srctree := $(patsubst %/,%,$(dir $(CURDIR))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -endif - -# Do not use make's built-in rules -# (this improves performance and avoids hard-to-debug behaviour); -MAKEFLAGS += -r - -CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include - -ALL_TARGETS := pcitest -ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) - -SCRIPTS := pcitest.sh - -all: $(ALL_PROGRAMS) - -export srctree OUTPUT CC LD CFLAGS -include $(srctree)/tools/build/Makefile.include - -# -# We need the following to be outside of kernel tree -# -$(OUTPUT)include/linux/: ../../include/uapi/linux/ - mkdir -p $(OUTPUT)include/linux/ 2>&1 || true - ln -sf $(CURDIR)/../../include/uapi/linux/pcitest.h $@ - -prepare: $(OUTPUT)include/linux/ - -PCITEST_IN := $(OUTPUT)pcitest-in.o -$(PCITEST_IN): prepare FORCE - $(Q)$(MAKE) $(build)=pcitest -$(OUTPUT)pcitest: $(PCITEST_IN) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ - -clean: - rm -f $(ALL_PROGRAMS) - rm -rf $(OUTPUT)include/ - find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete - -install: $(ALL_PROGRAMS) - install -d -m 755 $(DESTDIR)$(bindir); \ - for program in $(ALL_PROGRAMS); do \ - install $$program $(DESTDIR)$(bindir); \ - done; \ - for script in $(SCRIPTS); do \ - install $$script $(DESTDIR)$(bindir); \ - done - -FORCE: - -.PHONY: all install clean FORCE prepare diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c deleted file mode 100644 index 7b530d838d40..000000000000 --- a/tools/pci/pcitest.c +++ /dev/null @@ -1,250 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/** - * Userspace PCI Endpoint Test Module - * - * Copyright (C) 2017 Texas Instruments - * Author: Kishon Vijay Abraham I <kishon@ti.com> - */ - -#include <errno.h> -#include <fcntl.h> -#include <stdbool.h> -#include <stdio.h> -#include <stdlib.h> -#include <sys/ioctl.h> -#include <unistd.h> - -#include <linux/pcitest.h> - -static char *result[] = { "NOT OKAY", "OKAY" }; -static char *irq[] = { "LEGACY", "MSI", "MSI-X" }; - -struct pci_test { - char *device; - char barnum; - bool legacyirq; - unsigned int msinum; - unsigned int msixnum; - int irqtype; - bool set_irqtype; - bool get_irqtype; - bool clear_irq; - bool read; - bool write; - bool copy; - unsigned long size; - bool use_dma; -}; - -static int run_test(struct pci_test *test) -{ - struct pci_endpoint_test_xfer_param param = {}; - int ret = -EINVAL; - int fd; - - fd = open(test->device, O_RDWR); - if (fd < 0) { - perror("can't open PCI Endpoint Test device"); - return -ENODEV; - } - - if (test->barnum >= 0 && test->barnum <= 5) { - ret = ioctl(fd, PCITEST_BAR, test->barnum); - fprintf(stdout, "BAR%d:\t\t", test->barnum); - if (ret < 0) - fprintf(stdout, "TEST FAILED\n"); - else - fprintf(stdout, "%s\n", result[ret]); - } - - if (test->set_irqtype) { - ret = ioctl(fd, PCITEST_SET_IRQTYPE, test->irqtype); - fprintf(stdout, "SET IRQ TYPE TO %s:\t\t", irq[test->irqtype]); - if (ret < 0) - fprintf(stdout, "FAILED\n"); - else - fprintf(stdout, "%s\n", result[ret]); - } - - if (test->get_irqtype) { - ret = ioctl(fd, PCITEST_GET_IRQTYPE); - fprintf(stdout, "GET IRQ TYPE:\t\t"); - if (ret < 0) - fprintf(stdout, "FAILED\n"); - else - fprintf(stdout, "%s\n", irq[ret]); - } - - if (test->clear_irq) { - ret = ioctl(fd, PCITEST_CLEAR_IRQ); - fprintf(stdout, "CLEAR IRQ:\t\t"); - if (ret < 0) - fprintf(stdout, "FAILED\n"); - else - fprintf(stdout, "%s\n", result[ret]); - } - - if (test->legacyirq) { - ret = ioctl(fd, PCITEST_LEGACY_IRQ, 0); - fprintf(stdout, "LEGACY IRQ:\t"); - if (ret < 0) - fprintf(stdout, "TEST FAILED\n"); - else - fprintf(stdout, "%s\n", result[ret]); - } - - if (test->msinum > 0 && test->msinum <= 32) { - ret = ioctl(fd, PCITEST_MSI, test->msinum); - fprintf(stdout, "MSI%u:\t\t", test->msinum); - if (ret < 0) - fprintf(stdout, "TEST FAILED\n"); - else - fprintf(stdout, "%s\n", result[ret]); - } - - if (test->msixnum > 0 && test->msixnum <= 2048) { - ret = ioctl(fd, PCITEST_MSIX, test->msixnum); - fprintf(stdout, "MSI-X%u:\t\t", test->msixnum); - if (ret < 0) - fprintf(stdout, "TEST FAILED\n"); - else - fprintf(stdout, "%s\n", result[ret]); - } - - if (test->write) { - param.size = test->size; - if (test->use_dma) - param.flags = PCITEST_FLAGS_USE_DMA; - ret = ioctl(fd, PCITEST_WRITE, ¶m); - fprintf(stdout, "WRITE (%7lu bytes):\t\t", test->size); - if (ret < 0) - fprintf(stdout, "TEST FAILED\n"); - else - fprintf(stdout, "%s\n", result[ret]); - } - - if (test->read) { - param.size = test->size; - if (test->use_dma) - param.flags = PCITEST_FLAGS_USE_DMA; - ret = ioctl(fd, PCITEST_READ, ¶m); - fprintf(stdout, "READ (%7lu bytes):\t\t", test->size); - if (ret < 0) - fprintf(stdout, "TEST FAILED\n"); - else - fprintf(stdout, "%s\n", result[ret]); - } - - if (test->copy) { - param.size = test->size; - if (test->use_dma) - param.flags = PCITEST_FLAGS_USE_DMA; - ret = ioctl(fd, PCITEST_COPY, ¶m); - fprintf(stdout, "COPY (%7lu bytes):\t\t", test->size); - if (ret < 0) - fprintf(stdout, "TEST FAILED\n"); - else - fprintf(stdout, "%s\n", result[ret]); - } - - fflush(stdout); - close(fd); - return (ret < 0) ? ret : 1 - ret; /* return 0 if test succeeded */ -} - -int main(int argc, char **argv) -{ - int c; - struct pci_test *test; - - test = calloc(1, sizeof(*test)); - if (!test) { - perror("Fail to allocate memory for pci_test\n"); - return -ENOMEM; - } - - /* since '0' is a valid BAR number, initialize it to -1 */ - test->barnum = -1; - - /* set default size as 100KB */ - test->size = 0x19000; - - /* set default endpoint device */ - test->device = "/dev/pci-endpoint-test.0"; - - while ((c = getopt(argc, argv, "D:b:m:x:i:deIlhrwcs:")) != EOF) - switch (c) { - case 'D': - test->device = optarg; - continue; - case 'b': - test->barnum = atoi(optarg); - if (test->barnum < 0 || test->barnum > 5) - goto usage; - continue; - case 'l': - test->legacyirq = true; - continue; - case 'm': - test->msinum = atoi(optarg); - if (test->msinum < 1 || test->msinum > 32) - goto usage; - continue; - case 'x': - test->msixnum = atoi(optarg); - if (test->msixnum < 1 || test->msixnum > 2048) - goto usage; - continue; - case 'i': - test->irqtype = atoi(optarg); - if (test->irqtype < 0 || test->irqtype > 2) - goto usage; - test->set_irqtype = true; - continue; - case 'I': - test->get_irqtype = true; - continue; - case 'r': - test->read = true; - continue; - case 'w': - test->write = true; - continue; - case 'c': - test->copy = true; - continue; - case 'e': - test->clear_irq = true; - continue; - case 's': - test->size = strtoul(optarg, NULL, 0); - continue; - case 'd': - test->use_dma = true; - continue; - case 'h': - default: -usage: - fprintf(stderr, - "usage: %s [options]\n" - "Options:\n" - "\t-D <dev> PCI endpoint test device {default: /dev/pci-endpoint-test.0}\n" - "\t-b <bar num> BAR test (bar number between 0..5)\n" - "\t-m <msi num> MSI test (msi number between 1..32)\n" - "\t-x <msix num> \tMSI-X test (msix number between 1..2048)\n" - "\t-i <irq type> \tSet IRQ type (0 - Legacy, 1 - MSI, 2 - MSI-X)\n" - "\t-e Clear IRQ\n" - "\t-I Get current IRQ type configured\n" - "\t-d Use DMA\n" - "\t-l Legacy IRQ test\n" - "\t-r Read buffer test\n" - "\t-w Write buffer test\n" - "\t-c Copy buffer test\n" - "\t-s <size> Size of buffer {default: 100KB}\n" - "\t-h Print this help message\n", - argv[0]); - return -EINVAL; - } - - return run_test(test); -} diff --git a/tools/pci/pcitest.sh b/tools/pci/pcitest.sh deleted file mode 100644 index 75ed48ff2990..000000000000 --- a/tools/pci/pcitest.sh +++ /dev/null @@ -1,72 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -echo "BAR tests" -echo - -bar=0 - -while [ $bar -lt 6 ] -do - pcitest -b $bar - bar=`expr $bar + 1` -done -echo - -echo "Interrupt tests" -echo - -pcitest -i 0 -pcitest -l - -pcitest -i 1 -msi=1 - -while [ $msi -lt 33 ] -do - pcitest -m $msi - msi=`expr $msi + 1` -done -echo - -pcitest -i 2 -msix=1 - -while [ $msix -lt 2049 ] -do - pcitest -x $msix - msix=`expr $msix + 1` -done -echo - -echo "Read Tests" -echo - -pcitest -i 1 - -pcitest -r -s 1 -pcitest -r -s 1024 -pcitest -r -s 1025 -pcitest -r -s 1024000 -pcitest -r -s 1024001 -echo - -echo "Write Tests" -echo - -pcitest -w -s 1 -pcitest -w -s 1024 -pcitest -w -s 1025 -pcitest -w -s 1024000 -pcitest -w -s 1024001 -echo - -echo "Copy Tests" -echo - -pcitest -c -s 1 -pcitest -c -s 1024 -pcitest -c -s 1025 -pcitest -c -s 1024000 -pcitest -c -s 1024001 -echo diff --git a/tools/perf/Documentation/perf-arm-spe.txt b/tools/perf/Documentation/perf-arm-spe.txt index de2b0b479249..37afade4f1b2 100644 --- a/tools/perf/Documentation/perf-arm-spe.txt +++ b/tools/perf/Documentation/perf-arm-spe.txt @@ -150,6 +150,7 @@ arm_spe/load_filter=1,min_latency=10/' pct_enable=1 - collect physical timestamp instead of virtual timestamp (PMSCR.PCT) - requires privilege store_filter=1 - collect stores only (PMSFCR.ST) ts_enable=1 - enable timestamping with value of generic timer (PMSCR.TS) + discard=1 - enable SPE PMU events but don't collect sample data - see 'Discard mode' (PMBLIMITR.FM = DISCARD) +++*+++ Latency is the total latency from the point at which sampling started on that instruction, rather than only the execution latency. @@ -220,6 +221,31 @@ Common errors Increase sampling interval (see above) +PMU events +~~~~~~~~~~ + +SPE has events that can be counted on core PMUs. These are prefixed with +SAMPLE_, for example SAMPLE_POP, SAMPLE_FEED, SAMPLE_COLLISION and +SAMPLE_FEED_BR. + +These events will only count when an SPE event is running on the same core that +the PMU event is opened on, otherwise they read as 0. There are various ways to +ensure that the PMU event and SPE event are scheduled together depending on the +way the event is opened. For example opening both events as per-process events +on the same process, although it's not guaranteed that the PMU event is enabled +first when context switching. For that reason it may be better to open the PMU +event as a systemwide event and then open SPE on the process of interest. + +Discard mode +~~~~~~~~~~~~ + +SPE related (SAMPLE_* etc) core PMU events can be used without the overhead of +collecting sample data if discard mode is supported (optional from Armv8.6). +First run a system wide SPE session (or on the core of interest) using options +to minimize output. Then run perf stat: + + perf record -e arm_spe/discard/ -a -N -B --no-bpf-event -o - > /dev/null & + perf stat -e SAMPLE_FEED_LD SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-check.txt b/tools/perf/Documentation/perf-check.txt index 31741499e786..a764a4629220 100644 --- a/tools/perf/Documentation/perf-check.txt +++ b/tools/perf/Documentation/perf-check.txt @@ -51,7 +51,6 @@ feature:: dwarf_getlocations / HAVE_LIBDW_SUPPORT dwarf-unwind / HAVE_DWARF_UNWIND_SUPPORT auxtrace / HAVE_AUXTRACE_SUPPORT - libaudit / HAVE_LIBAUDIT_SUPPORT libbfd / HAVE_LIBBFD_SUPPORT libcapstone / HAVE_LIBCAPSTONE_SUPPORT libcrypto / HAVE_LIBCRYPTO_SUPPORT @@ -67,7 +66,6 @@ feature:: libunwind / HAVE_LIBUNWIND_SUPPORT lzma / HAVE_LZMA_SUPPORT numa_num_possible_cpus / HAVE_LIBNUMA_SUPPORT - syscall_table / HAVE_SYSCALL_TABLE_SUPPORT zlib / HAVE_ZLIB_SUPPORT zstd / HAVE_ZSTD_SUPPORT diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 1f668d4724e3..36ebebc875ea 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -40,7 +40,7 @@ The '$HOME/.perfconfig' file is used to store a per-user configuration. The file '$(sysconfdir)/perfconfig' can be used to store a system-wide default configuration. -One an disable reading config files by setting the PERF_CONFIG environment +One can disable reading config files by setting the PERF_CONFIG environment variable to /dev/null, or provide an alternate config file by setting that variable. diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index eaec8253be68..b77f58c4d2fd 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -148,6 +148,17 @@ OPTIONS for 'perf ftrace latency' --use-nsec:: Use nano-second instead of micro-second as a base unit of the histogram. +--bucket-range=:: + Bucket range in ms or ns (according to -n/--use-nsec), default is log2() mode. + +--min-latency=:: + Minimum latency for the start of the first bucket, in ms or ns (according to + -n/--use-nsec). + +--max-latency=:: + Maximum latency for the start of the last bucket, in ms or ns (according to + -n/--use-nsec). The setting is ignored if the value results in more than + 22 buckets. OPTIONS for 'perf ftrace profile' --------------------------------- @@ -190,6 +201,14 @@ OPTIONS for 'perf ftrace profile' Sort the result by the given field. Available values are: total, avg, max, count, name. Default is 'total'. +--graph-opts:: + List of options allowed to set: + + - nosleep-time - Measure on-CPU time only for function_graph tracer. + - noirqs - Ignore functions that happen inside interrupt. + - thresh=<n> - Setup trace duration threshold in microseconds. + - depth=<n> - Set max depth for function graph tracer to follow. + SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 59ab1ff9d75f..cc0f37f0fa5a 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -151,7 +151,7 @@ displayed as follows: There are two ways that instructions-per-cycle (IPC) can be calculated depending on the recording. -If the 'cyc' config term (see config terms section below) was used, then IPC +If the 'cyc' config term (see <<_config_terms,config terms>> section below) was used, then IPC and cycle events are calculated using the cycle count from CYC packets, otherwise MTC packets are used - refer to the 'mtc' config term. When MTC is used, however, the values are less accurate because the timing is less accurate. @@ -239,7 +239,7 @@ which is the same as -e intel_pt/tsc=1,noretcomp=0/ -Note there are now new config terms - see section 'config terms' further below. +Note there are other config terms - see section <<_config_terms,config terms>> further below. The config terms are listed in /sys/devices/intel_pt/format. They are bit fields within the config member of the struct perf_event_attr which is @@ -311,218 +311,271 @@ perf_event_attr is displayed if the -vv option is used e.g. config terms ~~~~~~~~~~~~ -The June 2015 version of Intel 64 and IA-32 Architectures Software Developer -Manuals, Chapter 36 Intel Processor Trace, defined new Intel PT features. -Some of the features are reflect in new config terms. All the config terms are -described below. - -tsc Always supported. Produces TSC timestamp packets to provide - timing information. In some cases it is possible to decode - without timing information, for example a per-thread context - that does not overlap executable memory maps. - - The default config selects tsc (i.e. tsc=1). - -noretcomp Always supported. Disables "return compression" so a TIP packet - is produced when a function returns. Causes more packets to be - produced but might make decoding more reliable. - - The default config does not select noretcomp (i.e. noretcomp=0). - -psb_period Allows the frequency of PSB packets to be specified. - - The PSB packet is a synchronization packet that provides a - starting point for decoding or recovery from errors. - - Support for psb_period is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/psb_cyc - - which contains "1" if the feature is supported and "0" - otherwise. - - Valid values are given by: - - /sys/bus/event_source/devices/intel_pt/caps/psb_periods - - which contains a hexadecimal value, the bits of which represent - valid values e.g. bit 2 set means value 2 is valid. - - The psb_period value is converted to the approximate number of - trace bytes between PSB packets as: - - 2 ^ (value + 11) - - e.g. value 3 means 16KiB bytes between PSBs - - If an invalid value is entered, the error message - will give a list of valid values e.g. - - $ perf record -e intel_pt/psb_period=15/u uname - Invalid psb_period for intel_pt. Valid values are: 0-5 - - If MTC packets are selected, the default config selects a value - of 3 (i.e. psb_period=3) or the nearest lower value that is - supported (0 is always supported). Otherwise the default is 0. - - If decoding is expected to be reliable and the buffer is large - then a large PSB period can be used. - - Because a TSC packet is produced with PSB, the PSB period can - also affect the granularity to timing information in the absence - of MTC or CYC. - -mtc Produces MTC timing packets. - - MTC packets provide finer grain timestamp information than TSC - packets. MTC packets record time using the hardware crystal - clock (CTC) which is related to TSC packets using a TMA packet. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/mtc - - which contains "1" if the feature is supported and - "0" otherwise. - - The frequency of MTC packets can also be specified - see - mtc_period below. - -mtc_period Specifies how frequently MTC packets are produced - see mtc - above for how to determine if MTC packets are supported. - - Valid values are given by: - - /sys/bus/event_source/devices/intel_pt/caps/mtc_periods - - which contains a hexadecimal value, the bits of which represent - valid values e.g. bit 2 set means value 2 is valid. - - The mtc_period value is converted to the MTC frequency as: - - CTC-frequency / (2 ^ value) - - e.g. value 3 means one eighth of CTC-frequency - - Where CTC is the hardware crystal clock, the frequency of which - can be related to TSC via values provided in cpuid leaf 0x15. - - If an invalid value is entered, the error message - will give a list of valid values e.g. - - $ perf record -e intel_pt/mtc_period=15/u uname - Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9 - - The default value is 3 or the nearest lower value - that is supported (0 is always supported). - -cyc Produces CYC timing packets. - - CYC packets provide even finer grain timestamp information than - MTC and TSC packets. A CYC packet contains the number of CPU - cycles since the last CYC packet. Unlike MTC and TSC packets, - CYC packets are only sent when another packet is also sent. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/psb_cyc - - which contains "1" if the feature is supported and - "0" otherwise. - - The number of CYC packets produced can be reduced by specifying - a threshold - see cyc_thresh below. - -cyc_thresh Specifies how frequently CYC packets are produced - see cyc - above for how to determine if CYC packets are supported. - - Valid cyc_thresh values are given by: - - /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds - - which contains a hexadecimal value, the bits of which represent - valid values e.g. bit 2 set means value 2 is valid. - - The cyc_thresh value represents the minimum number of CPU cycles - that must have passed before a CYC packet can be sent. The - number of CPU cycles is: - - 2 ^ (value - 1) - - e.g. value 4 means 8 CPU cycles must pass before a CYC packet - can be sent. Note a CYC packet is still only sent when another - packet is sent, not at, e.g. every 8 CPU cycles. - - If an invalid value is entered, the error message - will give a list of valid values e.g. - - $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname - Invalid cyc_thresh for intel_pt. Valid values are: 0-12 - - CYC packets are not requested by default. - -pt Specifies pass-through which enables the 'branch' config term. - - The default config selects 'pt' if it is available, so a user will - never need to specify this term. - -branch Enable branch tracing. Branch tracing is enabled by default so to - disable branch tracing use 'branch=0'. - - The default config selects 'branch' if it is available. - -ptw Enable PTWRITE packets which are produced when a ptwrite instruction - is executed. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/ptwrite - - which contains "1" if the feature is supported and - "0" otherwise. - - As an alternative, refer to "Emulated PTWRITE" further below. - -fup_on_ptw Enable a FUP packet to follow the PTWRITE packet. The FUP packet - provides the address of the ptwrite instruction. In the absence of - fup_on_ptw, the decoder will use the address of the previous branch - if branch tracing is enabled, otherwise the address will be zero. - Note that fup_on_ptw will work even when branch tracing is disabled. - -pwr_evt Enable power events. The power events provide information about - changes to the CPU C-state. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/power_event_trace - - which contains "1" if the feature is supported and - "0" otherwise. - -event Enable Event Trace. The events provide information about asynchronous - events. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/event_trace - - which contains "1" if the feature is supported and - "0" otherwise. - -notnt Disable TNT packets. Without TNT packets, it is not possible to walk - executable code to reconstruct control flow, however FUP, TIP, TIP.PGE - and TIP.PGD packets still indicate asynchronous control flow, and (if - return compression is disabled - see noretcomp) return statements. - The advantage of eliminating TNT packets is reducing the size of the - trace and corresponding tracing overhead. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/tnt_disable - - which contains "1" if the feature is supported and - "0" otherwise. - +Config terms are parameters specified with the -e intel_pt// event option, +for example: + + -e intel_pt/cyc/ + +which selects cycle accurate mode. Each config term can have a value which +defaults to 1, so the above is the same as: + + -e intel_pt/cyc=1/ + +Some terms are set by default, so must be set to 0 to turn them off. For +example, to turn off branch tracing: + + -e intel_pt/branch=0/ + +Multiple config terms are separated by commas, for example: + + -e intel_pt/cyc,mtc_period=9/ + +There are also common config terms, see linkperf:perf-record[1] documentation. + +Intel PT config terms are described below. + +*tsc*:: +Always supported. Produces TSC timestamp packets to provide +timing information. In some cases it is possible to decode +without timing information, for example a per-thread context +that does not overlap executable memory maps. ++ +The default config selects tsc (i.e. tsc=1). + +*noretcomp*:: +Always supported. Disables "return compression" so a TIP packet +is produced when a function returns. Causes more packets to be +produced but might make decoding more reliable. ++ +The default config does not select noretcomp (i.e. noretcomp=0). + +*psb_period*:: +Allows the frequency of PSB packets to be specified. ++ +The PSB packet is a synchronization packet that provides a +starting point for decoding or recovery from errors. ++ +Support for psb_period is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/psb_cyc ++ +which contains "1" if the feature is supported and "0" +otherwise. ++ +Valid values are given by: ++ + /sys/bus/event_source/devices/intel_pt/caps/psb_periods ++ +which contains a hexadecimal value, the bits of which represent +valid values e.g. bit 2 set means value 2 is valid. ++ +The psb_period value is converted to the approximate number of +trace bytes between PSB packets as: ++ + 2 ^ (value + 11) ++ +e.g. value 3 means 16KiB bytes between PSBs ++ +If an invalid value is entered, the error message +will give a list of valid values e.g. ++ + $ perf record -e intel_pt/psb_period=15/u uname + Invalid psb_period for intel_pt. Valid values are: 0-5 ++ +If MTC packets are selected, the default config selects a value +of 3 (i.e. psb_period=3) or the nearest lower value that is +supported (0 is always supported). Otherwise the default is 0. ++ +If decoding is expected to be reliable and the buffer is large +then a large PSB period can be used. ++ +Because a TSC packet is produced with PSB, the PSB period can +also affect the granularity to timing information in the absence +of MTC or CYC. + +*mtc*:: +Produces MTC timing packets. ++ +MTC packets provide finer grain timestamp information than TSC +packets. MTC packets record time using the hardware crystal +clock (CTC) which is related to TSC packets using a TMA packet. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/mtc ++ +which contains "1" if the feature is supported and +"0" otherwise. ++ +The frequency of MTC packets can also be specified - see +mtc_period below. + +*mtc_period*:: +Specifies how frequently MTC packets are produced - see mtc +above for how to determine if MTC packets are supported. ++ +Valid values are given by: ++ + /sys/bus/event_source/devices/intel_pt/caps/mtc_periods ++ +which contains a hexadecimal value, the bits of which represent +valid values e.g. bit 2 set means value 2 is valid. ++ +The mtc_period value is converted to the MTC frequency as: + + CTC-frequency / (2 ^ value) ++ +e.g. value 3 means one eighth of CTC-frequency ++ +Where CTC is the hardware crystal clock, the frequency of which +can be related to TSC via values provided in cpuid leaf 0x15. ++ +If an invalid value is entered, the error message +will give a list of valid values e.g. ++ + $ perf record -e intel_pt/mtc_period=15/u uname + Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9 ++ +The default value is 3 or the nearest lower value +that is supported (0 is always supported). + +*cyc*:: +Produces CYC timing packets. ++ +CYC packets provide even finer grain timestamp information than +MTC and TSC packets. A CYC packet contains the number of CPU +cycles since the last CYC packet. Unlike MTC and TSC packets, +CYC packets are only sent when another packet is also sent. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/psb_cyc ++ +which contains "1" if the feature is supported and +"0" otherwise. ++ +The number of CYC packets produced can be reduced by specifying +a threshold - see cyc_thresh below. + +*cyc_thresh*:: +Specifies how frequently CYC packets are produced - see cyc +above for how to determine if CYC packets are supported. ++ +Valid cyc_thresh values are given by: ++ + /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds ++ +which contains a hexadecimal value, the bits of which represent +valid values e.g. bit 2 set means value 2 is valid. ++ +The cyc_thresh value represents the minimum number of CPU cycles +that must have passed before a CYC packet can be sent. The +number of CPU cycles is: ++ + 2 ^ (value - 1) ++ +e.g. value 4 means 8 CPU cycles must pass before a CYC packet +can be sent. Note a CYC packet is still only sent when another +packet is sent, not at, e.g. every 8 CPU cycles. ++ +If an invalid value is entered, the error message +will give a list of valid values e.g. ++ + $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname + Invalid cyc_thresh for intel_pt. Valid values are: 0-12 ++ +CYC packets are not requested by default. + +*pt*:: +Specifies pass-through which enables the 'branch' config term. ++ +The default config selects 'pt' if it is available, so a user will +never need to specify this term. + +*branch*:: +Enable branch tracing. Branch tracing is enabled by default so to +disable branch tracing use 'branch=0'. ++ +The default config selects 'branch' if it is available. + +*ptw*:: +Enable PTWRITE packets which are produced when a ptwrite instruction +is executed. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/ptwrite ++ +which contains "1" if the feature is supported and +"0" otherwise. ++ +As an alternative, refer to "Emulated PTWRITE" further below. + +*fup_on_ptw*:: +Enable a FUP packet to follow the PTWRITE packet. The FUP packet +provides the address of the ptwrite instruction. In the absence of +fup_on_ptw, the decoder will use the address of the previous branch +if branch tracing is enabled, otherwise the address will be zero. +Note that fup_on_ptw will work even when branch tracing is disabled. + +*pwr_evt*:: +Enable power events. The power events provide information about +changes to the CPU C-state. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/power_event_trace ++ +which contains "1" if the feature is supported and +"0" otherwise. + +*event*:: +Enable Event Trace. The events provide information about asynchronous +events. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/event_trace ++ +which contains "1" if the feature is supported and +"0" otherwise. + +*notnt*:: +Disable TNT packets. Without TNT packets, it is not possible to walk +executable code to reconstruct control flow, however FUP, TIP, TIP.PGE +and TIP.PGD packets still indicate asynchronous control flow, and (if +return compression is disabled - see noretcomp) return statements. +The advantage of eliminating TNT packets is reducing the size of the +trace and corresponding tracing overhead. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/tnt_disable ++ +which contains "1" if the feature is supported and +"0" otherwise. + +*aux-action=start-paused*:: +Start tracing paused, refer to the section <<_pause_or_resume_tracing,Pause or Resume Tracing>> + + +config terms on other events +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Some Intel PT features work with other events, features such as AUX area sampling +and PEBS-via-PT. In those cases, the other events can have config terms below: + +*aux-sample-size*:: + Used to set the AUX area sample size, refer to the section + <<_aux_area_sampling_option,AUX area sampling option>> + +*aux-output*:: + Used to select PEBS-via-PT, refer to the + section <<_pebs_via_intel_pt,PEBS via Intel PT>> + +*aux-action*:: + Used to pause or resume tracing, refer to the section + <<_pause_or_resume_tracing,Pause or Resume Tracing>> AUX area sampling option ~~~~~~~~~~~~~~~~~~~~~~~~ @@ -596,7 +649,8 @@ The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap s nor snapshot size is specified, then the default is 4MiB for privileged users (or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users. If an unprivileged user does not specify mmap pages, the mmap pages will be -reduced as described in the 'new auxtrace mmap size option' section below. +reduced as described in the <<_new_auxtrace_mmap_size_option,new auxtrace mmap size option>> +section below. The snapshot size is displayed if the option -vv is used e.g. @@ -952,11 +1006,11 @@ transaction start, commit or abort. Note that "instructions", "cycles", "branches" and "transactions" events depend on code flow packets which can be disabled by using the config term -"branch=0". Refer to the config terms section above. +"branch=0". Refer to the <<_config_terms,config terms>> section above. "ptwrite" events record the payload of the ptwrite instruction and whether "fup_on_ptw" was used. "ptwrite" events depend on PTWRITE packets which are -recorded only if the "ptw" config term was used. Refer to the config terms +recorded only if the "ptw" config term was used. Refer to the <<_config_terms,config terms>> section above. perf script "synth" field displays "ptwrite" information like this: "ip: 0 payload: 0x123456789abcdef0" where "ip" is 1 if "fup_on_ptw" was used. @@ -964,7 +1018,7 @@ used. "Power" events correspond to power event packets and CBR (core-to-bus ratio) packets. While CBR packets are always recorded when tracing is enabled, power event packets are recorded only if the "pwr_evt" config term was used. Refer to -the config terms section above. The power events record information about +the <<_config_terms,config terms>> section above. The power events record information about C-state changes, whereas CBR is indicative of CPU frequency. perf script "event,synth" fields display information like this: @@ -1120,7 +1174,7 @@ What *will* be decoded with the (single) q option: - asynchronous branches such as interrupts - indirect branches - function return target address *if* the noretcomp config term (refer - config terms section) was used + <<_config_terms,config terms>> section) was used - start of (control-flow) tracing - end of (control-flow) tracing, if it is not out of context - power events, ptwrite, transaction start and abort @@ -1133,7 +1187,7 @@ Repeating the q option (double-q i.e. qq) results in even faster decoding and ev less detail. The decoder decodes only extended PSB (PSB+) packets, getting the instruction pointer if there is a FUP packet within PSB+ (i.e. between PSB and PSBEND). Note PSB packets occur regularly in the trace based on the psb_period -config term (refer config terms section). There will be a FUP packet if the +config term (refer <<_config_terms,config terms>> section). There will be a FUP packet if the PSB+ occurs while control flow is being traced. What will *not* be decoded with the qq option: @@ -1867,6 +1921,108 @@ For pipe mode, the order of events and timestamps can presumably be messed up. +Pause or Resume Tracing +----------------------- + +With newer Kernels, it is possible to use other selected events to pause +or resume Intel PT tracing. This is configured by using the "aux-action" +config term: + +"aux-action=pause" is used with events that are to pause Intel PT tracing. + +"aux-action=resume" is used with events that are to resume Intel PT tracing. + +"aux-action=start-paused" is used with the Intel PT event to start in a +paused state. + +For example, to trace only the uname system call (sys_newuname) when running the +command line utility uname: + + $ perf record --kcore -e intel_pt/aux-action=start-paused/k,syscalls:sys_enter_newuname/aux-action=resume/,syscalls:sys_exit_newuname/aux-action=pause/ uname + Linux + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 0.043 MB perf.data ] + $ perf script --call-trace + uname 30805 [000] 24001.058782799: name: 0x7ffc9c1865b0 + uname 30805 [000] 24001.058784424: psb offs: 0 + uname 30805 [000] 24001.058784424: cbr: 39 freq: 3904 MHz (139%) + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __x64_sys_newuname + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) down_read + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __cond_resched + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) in_lock_functions + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_sub + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) up_read + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) in_lock_functions + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) preempt_count_sub + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) _copy_to_user + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_to_user_mode + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_work + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) perf_syscall_exit + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_alloc + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_get_recursion_context + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_tp_event + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_update + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) tracing_gen_ctx_irq_test + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_event + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __perf_event_account_interrupt + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __this_cpu_preempt_check + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_output_forward + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_aux_pause + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) ring_buffer_get + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_lock + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_unlock + uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) pt_event_stop + uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) native_write_msr + uname 30805 [000] 24001.058785463: ([kernel.kallsyms]) native_write_msr + uname 30805 [000] 24001.058785639: 0x0 + +The example above uses tracepoints, but any kind of sampled event can be used. + +For example: + + Tracing between arch_cpu_idle_enter() and arch_cpu_idle_exit() using breakpoint events: + + $ sudo cat /proc/kallsyms | sort | grep ' arch_cpu_idle_enter\| arch_cpu_idle_exit' + ffffffffb605bf60 T arch_cpu_idle_enter + ffffffffb614d8a0 W arch_cpu_idle_exit + $ sudo perf record --kcore -a -e intel_pt/aux-action=start-paused/k -e mem:0xffffffffb605bf60:x/aux-action=resume/ -e mem:0xffffffffb614d8a0:x/aux-action=pause/ -- sleep 1 + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 1.387 MB perf.data ] + + Tracing __alloc_pages() using kprobes: + + $ sudo perf probe --add '__alloc_pages order' + Added new event: probe:__alloc_pages (on __alloc_pages with order) + $ sudo perf probe --add __alloc_pages%return + Added new event: probe:__alloc_pages__return (on __alloc_pages%return) + $ sudo perf record --kcore -aR -e intel_pt/aux-action=start-paused/k -e probe:__alloc_pages/aux-action=resume/ -e probe:__alloc_pages__return/aux-action=pause/ -- sleep 1 + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 1.490 MB perf.data ] + + Tracing starting at main() using a uprobe event: + + $ sudo perf probe -x /usr/bin/uname main + Added new event: probe_uname:main (on main in /usr/bin/uname) + $ sudo perf record -e intel_pt/-aux-action=start-paused/u -e probe_uname:main/aux-action=resume/ -- uname + Linux + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 0.031 MB perf.data ] + + Tracing occasionally using cycles events with different periods: + + $ perf record --kcore -a -m,64M -e intel_pt/aux-action=start-paused/k -e cycles/aux-action=pause,period=1000000/Pk -e cycles/aux-action=resume,period=10500000/Pk -- firefox + [ perf record: Woken up 19 times to write data ] + [ perf record: Captured and wrote 16.561 MB perf.data ] + + EXAMPLE ------- diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 57a940399de0..d3793054f7d3 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -187,8 +187,8 @@ CONTENTION OPTIONS Show lock contention only for given lock types (comma separated list). Available values are: semaphore, spinlock, rwlock, rwlock:R, rwlock:W, rwsem, rwsem:R, rwsem:W, - rtmutex, rwlock-rt, rwlock-rt:R, rwlock-rt:W, pcpu-sem, pcpu-sem:R, pcpu-sem:W, - mutex + rtmutex, rwlock-rt, rwlock-rt:R, rwlock-rt:W, percpu-rwmem, pcpu-sem, + pcpu-sem:R, pcpu-sem:W, mutex Note that RW-variant of locks have :R and :W suffix. Names without the suffix are shortcuts for the both variants. Ex) rwsem = rwsem:R + rwsem:W. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 242223240a08..80686d590de2 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -68,6 +68,10 @@ OPTIONS like this: name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\'. - 'aux-output': Generate AUX records instead of events. This requires that an AUX area event is also provided. + - 'aux-action': "pause" or "resume" to pause or resume an AUX + area event (the group leader) when this event occurs. + "start-paused" on an AUX area event itself, will + start in a paused state. - 'aux-sample-size': Set sample size for AUX area sampling. If the '--aux-sample' option has been used, set aux-sample-size=0 to disable AUX area sampling for the event. diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt index efcdec528a8f..32da0d1fa86a 100644 --- a/tools/perf/Documentation/perf-test.txt +++ b/tools/perf/Documentation/perf-test.txt @@ -28,18 +28,22 @@ OPTIONS Tests to skip (comma separated numeric list). -v:: +-vv:: +-vvv:: --verbose:: - Be more verbose. + With a single '-v', verbose level 1, only failing test output + is displayed. With '-vv' and higher all test output is shown. -S:: --sequential:: - Run tests one after the other, this is the default mode. + Run all tests one after the other. By default "exclusive" + tests are run sequentially, but other tests are run in + parallel to speed execution. --p:: ---parallel:: - Run tests in parallel, speeds up the whole process but is not safe with - the current infrastructure, where some tests that compete for some resources, - for instance, 'perf probe' tests that add/remove probes or clean all probes, etc. +-r:: +--runs-per-test:: + Run each test the given number of times, by default once. This + option can be useful to determine if a test is flaky. -F:: --dont-fork:: diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 6e0cc50bbc13..fb3d2af33844 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -241,6 +241,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. printing using the existing 'perf trace' syscall arg beautifiers to map integer arguments to strings (pid to comm, syscall id to syscall name, etc). +--force-btf:: + Use btf_dump to pretty print syscall argument data, instead of using hand-crafted pretty + printers. This option is intended for testing BTF integration in perf trace. btf_dump-based + pretty-printing serves as a fallback to hand-crafted pretty printers, as the latter can + better pretty-print integer flags and struct pointers. PAGEFAULTS ---------- diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index dc42de1785ce..364b55b00b48 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,5 +1,8 @@ +COPYING +LICENSES/preferred/GPL-2.0 arch/arm64/tools/gen-sysreg.awk arch/arm64/tools/sysreg +arch/*/include/uapi/asm/bpf_perf_event.h tools/perf tools/arch tools/scripts diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 2916d59c88cd..a148ca9efca9 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -28,63 +28,58 @@ include $(srctree)/tools/scripts/Makefile.arch $(call detected_var,SRCARCH) -ifneq ($(NO_SYSCALL_TABLE),1) - NO_SYSCALL_TABLE := 1 - - ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 powerpc arm64 s390 mips loongarch riscv)) - NO_SYSCALL_TABLE := 0 - endif - - ifneq ($(NO_SYSCALL_TABLE),1) - CFLAGS += -DHAVE_SYSCALL_TABLE_SUPPORT - endif -endif +CFLAGS += -I$(OUTPUT)arch/$(SRCARCH)/include/generated # Additional ARCH settings for ppc ifeq ($(SRCARCH),powerpc) - CFLAGS += -I$(OUTPUT)arch/powerpc/include/generated - LIBUNWIND_LIBS := -lunwind -lunwind-ppc64 + ifndef NO_LIBUNWIND + LIBUNWIND_LIBS := -lunwind -lunwind-ppc64 + endif endif # Additional ARCH settings for x86 ifeq ($(SRCARCH),x86) $(call detected,CONFIG_X86) - CFLAGS += -I$(OUTPUT)arch/x86/include/generated ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S - LIBUNWIND_LIBS = -lunwind-x86_64 -lunwind -llzma + ifndef NO_LIBUNWIND + LIBUNWIND_LIBS = -lunwind-x86_64 -lunwind -llzma + endif $(call detected,CONFIG_X86_64) else - LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind + ifndef NO_LIBUNWIND + LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind + endif endif endif ifeq ($(SRCARCH),arm) - LIBUNWIND_LIBS = -lunwind -lunwind-arm + ifndef NO_LIBUNWIND + LIBUNWIND_LIBS = -lunwind -lunwind-arm + endif endif ifeq ($(SRCARCH),arm64) - CFLAGS += -I$(OUTPUT)arch/arm64/include/generated - LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 + ifndef NO_LIBUNWIND + LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 + endif endif ifeq ($(SRCARCH),loongarch) - CFLAGS += -I$(OUTPUT)arch/loongarch/include/generated - LIBUNWIND_LIBS = -lunwind -lunwind-loongarch64 + ifndef NO_LIBUNWIND + LIBUNWIND_LIBS = -lunwind -lunwind-loongarch64 + endif endif ifeq ($(ARCH),s390) - CFLAGS += -fPIC -I$(OUTPUT)arch/s390/include/generated + CFLAGS += -fPIC endif ifeq ($(ARCH),mips) - CFLAGS += -I$(OUTPUT)arch/mips/include/generated - LIBUNWIND_LIBS = -lunwind -lunwind-mips -endif - -ifeq ($(ARCH),riscv) - CFLAGS += -I$(OUTPUT)arch/riscv/include/generated + ifndef NO_LIBUNWIND + LIBUNWIND_LIBS = -lunwind -lunwind-mips + endif endif # So far there's only x86 and arm libdw unwind support merged in perf. @@ -121,16 +116,18 @@ ifdef LIBUNWIND_DIR $(foreach libunwind_arch,$(LIBUNWIND_ARCHS),$(call libunwind_arch_set_flags,$(libunwind_arch))) endif -# Set per-feature check compilation flags -FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS) -FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS) -FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS) -FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS) - -FEATURE_CHECK_LDFLAGS-libunwind-arm += -lunwind -lunwind-arm -FEATURE_CHECK_LDFLAGS-libunwind-aarch64 += -lunwind -lunwind-aarch64 -FEATURE_CHECK_LDFLAGS-libunwind-x86 += -lunwind -llzma -lunwind-x86 -FEATURE_CHECK_LDFLAGS-libunwind-x86_64 += -lunwind -llzma -lunwind-x86_64 +ifndef NO_LIBUNWIND + # Set per-feature check compilation flags + FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS) + FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS) + FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS) + FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS) + + FEATURE_CHECK_LDFLAGS-libunwind-arm += -lunwind -lunwind-arm + FEATURE_CHECK_LDFLAGS-libunwind-aarch64 += -lunwind -lunwind-aarch64 + FEATURE_CHECK_LDFLAGS-libunwind-x86 += -lunwind -llzma -lunwind-x86 + FEATURE_CHECK_LDFLAGS-libunwind-x86_64 += -lunwind -llzma -lunwind-x86_64 +endif FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto @@ -155,7 +152,7 @@ ifdef LIBDW_DIR endif DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) - DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd + DWARFLIBS += -lelf -lz -llzma -lbz2 LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw).0.0 LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION))) @@ -550,6 +547,12 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_ELF_GETSHDRSTRNDX_SUPPORT endif + ifeq ($(feature-libelf-zstd), 1) + ifdef NO_LIBZSTD + $(error Error: libzstd is required by libelf, please do not set NO_LIBZSTD) + endif + endif + ifndef NO_LIBDEBUGINFOD $(call feature_check,libdebuginfod) ifeq ($(feature-libdebuginfod), 1) @@ -734,26 +737,25 @@ ifeq ($(dwarf-post-unwind),1) $(call detected,CONFIG_DWARF_UNWIND) endif -ifndef NO_LOCAL_LIBUNWIND - ifeq ($(SRCARCH),$(filter $(SRCARCH),arm arm64)) - $(call feature_check,libunwind-debug-frame) - ifneq ($(feature-libunwind-debug-frame), 1) - $(warning No debug_frame support found in libunwind) +ifndef NO_LIBUNWIND + ifndef NO_LOCAL_LIBUNWIND + ifeq ($(SRCARCH),$(filter $(SRCARCH),arm arm64)) + $(call feature_check,libunwind-debug-frame) + ifneq ($(feature-libunwind-debug-frame), 1) + $(warning No debug_frame support found in libunwind) + CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME + endif + else + # non-ARM has no dwarf_find_debug_frame() function: CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME endif - else - # non-ARM has no dwarf_find_debug_frame() function: - CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME + EXTLIBS += $(LIBUNWIND_LIBS) + LDFLAGS += $(LIBUNWIND_LIBS) + endif + ifeq ($(findstring -static,${LDFLAGS}),-static) + # gcc -static links libgcc_eh which contans piece of libunwind + LIBUNWIND_LDFLAGS += -Wl,--allow-multiple-definition endif - EXTLIBS += $(LIBUNWIND_LIBS) - LDFLAGS += $(LIBUNWIND_LIBS) -endif -ifeq ($(findstring -static,${LDFLAGS}),-static) - # gcc -static links libgcc_eh which contans piece of libunwind - LIBUNWIND_LDFLAGS += -Wl,--allow-multiple-definition -endif - -ifndef NO_LIBUNWIND CFLAGS += -DHAVE_LIBUNWIND_SUPPORT CFLAGS += $(LIBUNWIND_CFLAGS) LDFLAGS += $(LIBUNWIND_LDFLAGS) @@ -761,21 +763,7 @@ ifndef NO_LIBUNWIND endif ifneq ($(NO_LIBTRACEEVENT),1) - ifeq ($(NO_SYSCALL_TABLE),0) - $(call detected,CONFIG_TRACE) - else - ifndef NO_LIBAUDIT - $(call feature_check,libaudit) - ifneq ($(feature-libaudit), 1) - $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev) - NO_LIBAUDIT := 1 - else - CFLAGS += -DHAVE_LIBAUDIT_SUPPORT - EXTLIBS += -laudit - $(call detected,CONFIG_TRACE) - endif - endif - endif + $(call detected,CONFIG_TRACE) endif ifndef NO_LIBCRYPTO @@ -1172,7 +1160,6 @@ endif # libtraceevent is a recommended dependency picked up from the system. ifneq ($(NO_LIBTRACEEVENT),1) - $(call feature_check,libtraceevent) ifeq ($(feature-libtraceevent), 1) CFLAGS += -DHAVE_LIBTRACEEVENT $(shell $(PKG_CONFIG) --cflags libtraceevent) LDFLAGS += $(shell $(PKG_CONFIG) --libs-only-L libtraceevent) @@ -1188,7 +1175,6 @@ ifneq ($(NO_LIBTRACEEVENT),1) $(error ERROR: libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel and/or set LIBTRACEEVENT_DIR or build with NO_LIBTRACEEVENT=1) endif - $(call feature_check,libtracefs) ifeq ($(feature-libtracefs), 1) CFLAGS += $(shell $(PKG_CONFIG) --cflags libtracefs) LDFLAGS += $(shell $(PKG_CONFIG) --libs-only-L libtracefs) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index d74241a15131..55d6ce9ea52f 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -59,8 +59,6 @@ include ../scripts/utilities.mak # # Define NO_LIBNUMA if you do not want numa perf benchmark # -# Define NO_LIBAUDIT if you do not want libaudit support -# # Define NO_LIBBIONIC if you do not want bionic support # # Define NO_LIBCRYPTO if you do not want libcrypto (openssl) support @@ -119,10 +117,6 @@ include ../scripts/utilities.mak # # Define LIBBPF_DYNAMIC to enable libbpf dynamic linking. # -# Define NO_SYSCALL_TABLE=1 to disable the use of syscall id to/from name tables -# generated from the kernel .tbl or unistd.h files and use, if available, libaudit -# for doing the conversions to/from strings/id. -# # Define NO_LIBPFM4 to disable libpfm4 events extension. # # Define NO_LIBDEBUGINFOD if you do not want support debuginfod @@ -167,12 +161,47 @@ export VPATH SOURCE := $(shell ln -sf $(srctree)/tools/perf $(OUTPUT)/source) endif +# Beautify output +# --------------------------------------------------------------------------- +# +# Most of build commands in Kbuild start with "cmd_". You can optionally define +# "quiet_cmd_*". If defined, the short log is printed. Otherwise, no log from +# that command is printed by default. +# +# e.g.) +# quiet_cmd_depmod = DEPMOD $(MODLIB) +# cmd_depmod = $(srctree)/scripts/depmod.sh $(DEPMOD) $(KERNELRELEASE) +# +# A simple variant is to prefix commands with $(Q) - that's useful +# for commands that shall be hidden in non-verbose mode. +# +# $(Q)$(MAKE) $(build)=scripts/basic +# +# To put more focus on warnings, be less verbose as default +# Use 'make V=1' to see the full commands + ifeq ($(V),1) + quiet = Q = else - Q = @ + quiet=quiet_ + Q=@ endif +# If the user is running make -s (silent mode), suppress echoing of commands +# make-4.0 (and later) keep single letter options in the 1st word of MAKEFLAGS. +ifeq ($(filter 3.%,$(MAKE_VERSION)),) +short-opts := $(firstword -$(MAKEFLAGS)) +else +short-opts := $(filter-out --%,$(MAKEFLAGS)) +endif + +ifneq ($(findstring s,$(short-opts)),) + quiet=silent_ +endif + +export quiet Q + # Do not use make's built-in rules # (this improves performance and avoids hard-to-debug behaviour); MAKEFLAGS += -r @@ -310,6 +339,7 @@ ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump) FEATURE_TESTS := all endif endif +include $(srctree)/tools/perf/scripts/Makefile.syscalls include Makefile.config endif @@ -487,6 +517,9 @@ endif EXTLIBS := $(call filter-out,$(EXCLUDE_EXTLIBS),$(EXTLIBS)) LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group +PERFLIBS_PY := $(call filter-out,$(LIBPERF_BENCH) $(LIBPERF_TEST),$(PERFLIBS)) +LIBS_PY = -Wl,--whole-archive $(PERFLIBS_PY) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group + export INSTALL SHELL_PATH ### Build rules @@ -735,9 +768,9 @@ all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) # Create python binding output directory if not already present $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python') -$(OUTPUT)python/perf$(PYTHON_EXTENSION_SUFFIX): util/python.c util/setup.py $(PERFLIBS) +$(OUTPUT)python/perf$(PYTHON_EXTENSION_SUFFIX): util/python.c util/setup.py $(PERFLIBS_PY) $(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \ - CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBS)' \ + CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBS_PY)' \ $(PYTHON_WORD) util/setup.py \ --quiet build_ext; \ cp $(PYTHON_EXTBUILD_LIB)perf*.so $(OUTPUT)python/ @@ -1094,11 +1127,6 @@ endif $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(call QUIET_INSTALL, perf-iostat) \ $(INSTALL) $(OUTPUT)perf-iostat -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' -ifndef NO_LIBAUDIT - $(call QUIET_INSTALL, strace/groups) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'; \ - $(INSTALL) trace/strace/groups/* -m 644 -t '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)' -endif ifndef NO_LIBPERL $(call QUIET_INSTALL, perl-scripts) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \ diff --git a/tools/perf/arch/alpha/entry/syscalls/Kbuild b/tools/perf/arch/alpha/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/alpha/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/alpha/entry/syscalls/Makefile.syscalls b/tools/perf/arch/alpha/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..690168aac34d --- /dev/null +++ b/tools/perf/arch/alpha/entry/syscalls/Makefile.syscalls @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_64 += + +syscalltbl = $(srctree)/tools/perf/arch/alpha/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/alpha/entry/syscalls/syscall.tbl b/tools/perf/arch/alpha/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..74720667fe09 --- /dev/null +++ b/tools/perf/arch/alpha/entry/syscalls/syscall.tbl @@ -0,0 +1,504 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for alpha +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The <abi> is always "common" for this file +# +0 common osf_syscall alpha_syscall_zero +1 common exit sys_exit +2 common fork alpha_fork +3 common read sys_read +4 common write sys_write +5 common osf_old_open sys_ni_syscall +6 common close sys_close +7 common osf_wait4 sys_osf_wait4 +8 common osf_old_creat sys_ni_syscall +9 common link sys_link +10 common unlink sys_unlink +11 common osf_execve sys_ni_syscall +12 common chdir sys_chdir +13 common fchdir sys_fchdir +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common chown sys_chown +17 common brk sys_osf_brk +18 common osf_getfsstat sys_ni_syscall +19 common lseek sys_lseek +20 common getxpid sys_getxpid +21 common osf_mount sys_osf_mount +22 common umount2 sys_umount +23 common setuid sys_setuid +24 common getxuid sys_getxuid +25 common exec_with_loader sys_ni_syscall +26 common ptrace sys_ptrace +27 common osf_nrecvmsg sys_ni_syscall +28 common osf_nsendmsg sys_ni_syscall +29 common osf_nrecvfrom sys_ni_syscall +30 common osf_naccept sys_ni_syscall +31 common osf_ngetpeername sys_ni_syscall +32 common osf_ngetsockname sys_ni_syscall +33 common access sys_access +34 common osf_chflags sys_ni_syscall +35 common osf_fchflags sys_ni_syscall +36 common sync sys_sync +37 common kill sys_kill +38 common osf_old_stat sys_ni_syscall +39 common setpgid sys_setpgid +40 common osf_old_lstat sys_ni_syscall +41 common dup sys_dup +42 common pipe sys_alpha_pipe +43 common osf_set_program_attributes sys_osf_set_program_attributes +44 common osf_profil sys_ni_syscall +45 common open sys_open +46 common osf_old_sigaction sys_ni_syscall +47 common getxgid sys_getxgid +48 common osf_sigprocmask sys_osf_sigprocmask +49 common osf_getlogin sys_ni_syscall +50 common osf_setlogin sys_ni_syscall +51 common acct sys_acct +52 common sigpending sys_sigpending +54 common ioctl sys_ioctl +55 common osf_reboot sys_ni_syscall +56 common osf_revoke sys_ni_syscall +57 common symlink sys_symlink +58 common readlink sys_readlink +59 common execve sys_execve +60 common umask sys_umask +61 common chroot sys_chroot +62 common osf_old_fstat sys_ni_syscall +63 common getpgrp sys_getpgrp +64 common getpagesize sys_getpagesize +65 common osf_mremap sys_ni_syscall +66 common vfork alpha_vfork +67 common stat sys_newstat +68 common lstat sys_newlstat +69 common osf_sbrk sys_ni_syscall +70 common osf_sstk sys_ni_syscall +71 common mmap sys_osf_mmap +72 common osf_old_vadvise sys_ni_syscall +73 common munmap sys_munmap +74 common mprotect sys_mprotect +75 common madvise sys_madvise +76 common vhangup sys_vhangup +77 common osf_kmodcall sys_ni_syscall +78 common osf_mincore sys_ni_syscall +79 common getgroups sys_getgroups +80 common setgroups sys_setgroups +81 common osf_old_getpgrp sys_ni_syscall +82 common setpgrp sys_setpgid +83 common osf_setitimer compat_sys_setitimer +84 common osf_old_wait sys_ni_syscall +85 common osf_table sys_ni_syscall +86 common osf_getitimer compat_sys_getitimer +87 common gethostname sys_gethostname +88 common sethostname sys_sethostname +89 common getdtablesize sys_getdtablesize +90 common dup2 sys_dup2 +91 common fstat sys_newfstat +92 common fcntl sys_fcntl +93 common osf_select sys_osf_select +94 common poll sys_poll +95 common fsync sys_fsync +96 common setpriority sys_setpriority +97 common socket sys_socket +98 common connect sys_connect +99 common accept sys_accept +100 common getpriority sys_osf_getpriority +101 common send sys_send +102 common recv sys_recv +103 common sigreturn sys_sigreturn +104 common bind sys_bind +105 common setsockopt sys_setsockopt +106 common listen sys_listen +107 common osf_plock sys_ni_syscall +108 common osf_old_sigvec sys_ni_syscall +109 common osf_old_sigblock sys_ni_syscall +110 common osf_old_sigsetmask sys_ni_syscall +111 common sigsuspend sys_sigsuspend +112 common osf_sigstack sys_osf_sigstack +113 common recvmsg sys_recvmsg +114 common sendmsg sys_sendmsg +115 common osf_old_vtrace sys_ni_syscall +116 common osf_gettimeofday sys_osf_gettimeofday +117 common osf_getrusage sys_osf_getrusage +118 common getsockopt sys_getsockopt +120 common readv sys_readv +121 common writev sys_writev +122 common osf_settimeofday sys_osf_settimeofday +123 common fchown sys_fchown +124 common fchmod sys_fchmod +125 common recvfrom sys_recvfrom +126 common setreuid sys_setreuid +127 common setregid sys_setregid +128 common rename sys_rename +129 common truncate sys_truncate +130 common ftruncate sys_ftruncate +131 common flock sys_flock +132 common setgid sys_setgid +133 common sendto sys_sendto +134 common shutdown sys_shutdown +135 common socketpair sys_socketpair +136 common mkdir sys_mkdir +137 common rmdir sys_rmdir +138 common osf_utimes sys_osf_utimes +139 common osf_old_sigreturn sys_ni_syscall +140 common osf_adjtime sys_ni_syscall +141 common getpeername sys_getpeername +142 common osf_gethostid sys_ni_syscall +143 common osf_sethostid sys_ni_syscall +144 common getrlimit sys_getrlimit +145 common setrlimit sys_setrlimit +146 common osf_old_killpg sys_ni_syscall +147 common setsid sys_setsid +148 common quotactl sys_quotactl +149 common osf_oldquota sys_ni_syscall +150 common getsockname sys_getsockname +153 common osf_pid_block sys_ni_syscall +154 common osf_pid_unblock sys_ni_syscall +156 common sigaction sys_osf_sigaction +157 common osf_sigwaitprim sys_ni_syscall +158 common osf_nfssvc sys_ni_syscall +159 common osf_getdirentries sys_osf_getdirentries +160 common osf_statfs sys_osf_statfs +161 common osf_fstatfs sys_osf_fstatfs +163 common osf_asynch_daemon sys_ni_syscall +164 common osf_getfh sys_ni_syscall +165 common osf_getdomainname sys_osf_getdomainname +166 common setdomainname sys_setdomainname +169 common osf_exportfs sys_ni_syscall +181 common osf_alt_plock sys_ni_syscall +184 common osf_getmnt sys_ni_syscall +187 common osf_alt_sigpending sys_ni_syscall +188 common osf_alt_setsid sys_ni_syscall +199 common osf_swapon sys_swapon +200 common msgctl sys_old_msgctl +201 common msgget sys_msgget +202 common msgrcv sys_msgrcv +203 common msgsnd sys_msgsnd +204 common semctl sys_old_semctl +205 common semget sys_semget +206 common semop sys_semop +207 common osf_utsname sys_osf_utsname +208 common lchown sys_lchown +209 common shmat sys_shmat +210 common shmctl sys_old_shmctl +211 common shmdt sys_shmdt +212 common shmget sys_shmget +213 common osf_mvalid sys_ni_syscall +214 common osf_getaddressconf sys_ni_syscall +215 common osf_msleep sys_ni_syscall +216 common osf_mwakeup sys_ni_syscall +217 common msync sys_msync +218 common osf_signal sys_ni_syscall +219 common osf_utc_gettime sys_ni_syscall +220 common osf_utc_adjtime sys_ni_syscall +222 common osf_security sys_ni_syscall +223 common osf_kloadcall sys_ni_syscall +224 common osf_stat sys_osf_stat +225 common osf_lstat sys_osf_lstat +226 common osf_fstat sys_osf_fstat +227 common osf_statfs64 sys_osf_statfs64 +228 common osf_fstatfs64 sys_osf_fstatfs64 +233 common getpgid sys_getpgid +234 common getsid sys_getsid +235 common sigaltstack sys_sigaltstack +236 common osf_waitid sys_ni_syscall +237 common osf_priocntlset sys_ni_syscall +238 common osf_sigsendset sys_ni_syscall +239 common osf_set_speculative sys_ni_syscall +240 common osf_msfs_syscall sys_ni_syscall +241 common osf_sysinfo sys_osf_sysinfo +242 common osf_uadmin sys_ni_syscall +243 common osf_fuser sys_ni_syscall +244 common osf_proplist_syscall sys_osf_proplist_syscall +245 common osf_ntp_adjtime sys_ni_syscall +246 common osf_ntp_gettime sys_ni_syscall +247 common osf_pathconf sys_ni_syscall +248 common osf_fpathconf sys_ni_syscall +250 common osf_uswitch sys_ni_syscall +251 common osf_usleep_thread sys_osf_usleep_thread +252 common osf_audcntl sys_ni_syscall +253 common osf_audgen sys_ni_syscall +254 common sysfs sys_sysfs +255 common osf_subsys_info sys_ni_syscall +256 common osf_getsysinfo sys_osf_getsysinfo +257 common osf_setsysinfo sys_osf_setsysinfo +258 common osf_afs_syscall sys_ni_syscall +259 common osf_swapctl sys_ni_syscall +260 common osf_memcntl sys_ni_syscall +261 common osf_fdatasync sys_ni_syscall +300 common bdflush sys_ni_syscall +301 common sethae sys_sethae +302 common mount sys_mount +303 common old_adjtimex sys_old_adjtimex +304 common swapoff sys_swapoff +305 common getdents sys_getdents +306 common create_module sys_ni_syscall +307 common init_module sys_init_module +308 common delete_module sys_delete_module +309 common get_kernel_syms sys_ni_syscall +310 common syslog sys_syslog +311 common reboot sys_reboot +312 common clone alpha_clone +313 common uselib sys_uselib +314 common mlock sys_mlock +315 common munlock sys_munlock +316 common mlockall sys_mlockall +317 common munlockall sys_munlockall +318 common sysinfo sys_sysinfo +319 common _sysctl sys_ni_syscall +# 320 was sys_idle +321 common oldumount sys_oldumount +322 common swapon sys_swapon +323 common times sys_times +324 common personality sys_personality +325 common setfsuid sys_setfsuid +326 common setfsgid sys_setfsgid +327 common ustat sys_ustat +328 common statfs sys_statfs +329 common fstatfs sys_fstatfs +330 common sched_setparam sys_sched_setparam +331 common sched_getparam sys_sched_getparam +332 common sched_setscheduler sys_sched_setscheduler +333 common sched_getscheduler sys_sched_getscheduler +334 common sched_yield sys_sched_yield +335 common sched_get_priority_max sys_sched_get_priority_max +336 common sched_get_priority_min sys_sched_get_priority_min +337 common sched_rr_get_interval sys_sched_rr_get_interval +338 common afs_syscall sys_ni_syscall +339 common uname sys_newuname +340 common nanosleep sys_nanosleep +341 common mremap sys_mremap +342 common nfsservctl sys_ni_syscall +343 common setresuid sys_setresuid +344 common getresuid sys_getresuid +345 common pciconfig_read sys_pciconfig_read +346 common pciconfig_write sys_pciconfig_write +347 common query_module sys_ni_syscall +348 common prctl sys_prctl +349 common pread64 sys_pread64 +350 common pwrite64 sys_pwrite64 +351 common rt_sigreturn sys_rt_sigreturn +352 common rt_sigaction sys_rt_sigaction +353 common rt_sigprocmask sys_rt_sigprocmask +354 common rt_sigpending sys_rt_sigpending +355 common rt_sigtimedwait sys_rt_sigtimedwait +356 common rt_sigqueueinfo sys_rt_sigqueueinfo +357 common rt_sigsuspend sys_rt_sigsuspend +358 common select sys_select +359 common gettimeofday sys_gettimeofday +360 common settimeofday sys_settimeofday +361 common getitimer sys_getitimer +362 common setitimer sys_setitimer +363 common utimes sys_utimes +364 common getrusage sys_getrusage +365 common wait4 sys_wait4 +366 common adjtimex sys_adjtimex +367 common getcwd sys_getcwd +368 common capget sys_capget +369 common capset sys_capset +370 common sendfile sys_sendfile64 +371 common setresgid sys_setresgid +372 common getresgid sys_getresgid +373 common dipc sys_ni_syscall +374 common pivot_root sys_pivot_root +375 common mincore sys_mincore +376 common pciconfig_iobase sys_pciconfig_iobase +377 common getdents64 sys_getdents64 +378 common gettid sys_gettid +379 common readahead sys_readahead +# 380 is unused +381 common tkill sys_tkill +382 common setxattr sys_setxattr +383 common lsetxattr sys_lsetxattr +384 common fsetxattr sys_fsetxattr +385 common getxattr sys_getxattr +386 common lgetxattr sys_lgetxattr +387 common fgetxattr sys_fgetxattr +388 common listxattr sys_listxattr +389 common llistxattr sys_llistxattr +390 common flistxattr sys_flistxattr +391 common removexattr sys_removexattr +392 common lremovexattr sys_lremovexattr +393 common fremovexattr sys_fremovexattr +394 common futex sys_futex +395 common sched_setaffinity sys_sched_setaffinity +396 common sched_getaffinity sys_sched_getaffinity +397 common tuxcall sys_ni_syscall +398 common io_setup sys_io_setup +399 common io_destroy sys_io_destroy +400 common io_getevents sys_io_getevents +401 common io_submit sys_io_submit +402 common io_cancel sys_io_cancel +405 common exit_group sys_exit_group +406 common lookup_dcookie sys_ni_syscall +407 common epoll_create sys_epoll_create +408 common epoll_ctl sys_epoll_ctl +409 common epoll_wait sys_epoll_wait +410 common remap_file_pages sys_remap_file_pages +411 common set_tid_address sys_set_tid_address +412 common restart_syscall sys_restart_syscall +413 common fadvise64 sys_fadvise64 +414 common timer_create sys_timer_create +415 common timer_settime sys_timer_settime +416 common timer_gettime sys_timer_gettime +417 common timer_getoverrun sys_timer_getoverrun +418 common timer_delete sys_timer_delete +419 common clock_settime sys_clock_settime +420 common clock_gettime sys_clock_gettime +421 common clock_getres sys_clock_getres +422 common clock_nanosleep sys_clock_nanosleep +423 common semtimedop sys_semtimedop +424 common tgkill sys_tgkill +425 common stat64 sys_stat64 +426 common lstat64 sys_lstat64 +427 common fstat64 sys_fstat64 +428 common vserver sys_ni_syscall +429 common mbind sys_ni_syscall +430 common get_mempolicy sys_ni_syscall +431 common set_mempolicy sys_ni_syscall +432 common mq_open sys_mq_open +433 common mq_unlink sys_mq_unlink +434 common mq_timedsend sys_mq_timedsend +435 common mq_timedreceive sys_mq_timedreceive +436 common mq_notify sys_mq_notify +437 common mq_getsetattr sys_mq_getsetattr +438 common waitid sys_waitid +439 common add_key sys_add_key +440 common request_key sys_request_key +441 common keyctl sys_keyctl +442 common ioprio_set sys_ioprio_set +443 common ioprio_get sys_ioprio_get +444 common inotify_init sys_inotify_init +445 common inotify_add_watch sys_inotify_add_watch +446 common inotify_rm_watch sys_inotify_rm_watch +447 common fdatasync sys_fdatasync +448 common kexec_load sys_kexec_load +449 common migrate_pages sys_migrate_pages +450 common openat sys_openat +451 common mkdirat sys_mkdirat +452 common mknodat sys_mknodat +453 common fchownat sys_fchownat +454 common futimesat sys_futimesat +455 common fstatat64 sys_fstatat64 +456 common unlinkat sys_unlinkat +457 common renameat sys_renameat +458 common linkat sys_linkat +459 common symlinkat sys_symlinkat +460 common readlinkat sys_readlinkat +461 common fchmodat sys_fchmodat +462 common faccessat sys_faccessat +463 common pselect6 sys_pselect6 +464 common ppoll sys_ppoll +465 common unshare sys_unshare +466 common set_robust_list sys_set_robust_list +467 common get_robust_list sys_get_robust_list +468 common splice sys_splice +469 common sync_file_range sys_sync_file_range +470 common tee sys_tee +471 common vmsplice sys_vmsplice +472 common move_pages sys_move_pages +473 common getcpu sys_getcpu +474 common epoll_pwait sys_epoll_pwait +475 common utimensat sys_utimensat +476 common signalfd sys_signalfd +477 common timerfd sys_ni_syscall +478 common eventfd sys_eventfd +479 common recvmmsg sys_recvmmsg +480 common fallocate sys_fallocate +481 common timerfd_create sys_timerfd_create +482 common timerfd_settime sys_timerfd_settime +483 common timerfd_gettime sys_timerfd_gettime +484 common signalfd4 sys_signalfd4 +485 common eventfd2 sys_eventfd2 +486 common epoll_create1 sys_epoll_create1 +487 common dup3 sys_dup3 +488 common pipe2 sys_pipe2 +489 common inotify_init1 sys_inotify_init1 +490 common preadv sys_preadv +491 common pwritev sys_pwritev +492 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +493 common perf_event_open sys_perf_event_open +494 common fanotify_init sys_fanotify_init +495 common fanotify_mark sys_fanotify_mark +496 common prlimit64 sys_prlimit64 +497 common name_to_handle_at sys_name_to_handle_at +498 common open_by_handle_at sys_open_by_handle_at +499 common clock_adjtime sys_clock_adjtime +500 common syncfs sys_syncfs +501 common setns sys_setns +502 common accept4 sys_accept4 +503 common sendmmsg sys_sendmmsg +504 common process_vm_readv sys_process_vm_readv +505 common process_vm_writev sys_process_vm_writev +506 common kcmp sys_kcmp +507 common finit_module sys_finit_module +508 common sched_setattr sys_sched_setattr +509 common sched_getattr sys_sched_getattr +510 common renameat2 sys_renameat2 +511 common getrandom sys_getrandom +512 common memfd_create sys_memfd_create +513 common execveat sys_execveat +514 common seccomp sys_seccomp +515 common bpf sys_bpf +516 common userfaultfd sys_userfaultfd +517 common membarrier sys_membarrier +518 common mlock2 sys_mlock2 +519 common copy_file_range sys_copy_file_range +520 common preadv2 sys_preadv2 +521 common pwritev2 sys_pwritev2 +522 common statx sys_statx +523 common io_pgetevents sys_io_pgetevents +524 common pkey_mprotect sys_pkey_mprotect +525 common pkey_alloc sys_pkey_alloc +526 common pkey_free sys_pkey_free +527 common rseq sys_rseq +528 common statfs64 sys_statfs64 +529 common fstatfs64 sys_fstatfs64 +530 common getegid sys_getegid +531 common geteuid sys_geteuid +532 common getppid sys_getppid +# all other architectures have common numbers for new syscall, alpha +# is the exception. +534 common pidfd_send_signal sys_pidfd_send_signal +535 common io_uring_setup sys_io_uring_setup +536 common io_uring_enter sys_io_uring_enter +537 common io_uring_register sys_io_uring_register +538 common open_tree sys_open_tree +539 common move_mount sys_move_mount +540 common fsopen sys_fsopen +541 common fsconfig sys_fsconfig +542 common fsmount sys_fsmount +543 common fspick sys_fspick +544 common pidfd_open sys_pidfd_open +545 common clone3 alpha_clone3 +546 common close_range sys_close_range +547 common openat2 sys_openat2 +548 common pidfd_getfd sys_pidfd_getfd +549 common faccessat2 sys_faccessat2 +550 common process_madvise sys_process_madvise +551 common epoll_pwait2 sys_epoll_pwait2 +552 common mount_setattr sys_mount_setattr +553 common quotactl_fd sys_quotactl_fd +554 common landlock_create_ruleset sys_landlock_create_ruleset +555 common landlock_add_rule sys_landlock_add_rule +556 common landlock_restrict_self sys_landlock_restrict_self +# 557 reserved for memfd_secret +558 common process_mrelease sys_process_mrelease +559 common futex_waitv sys_futex_waitv +560 common set_mempolicy_home_node sys_ni_syscall +561 common cachestat sys_cachestat +562 common fchmodat2 sys_fchmodat2 +563 common map_shadow_stack sys_map_shadow_stack +564 common futex_wake sys_futex_wake +565 common futex_wait sys_futex_wait +566 common futex_requeue sys_futex_requeue +567 common statmount sys_statmount +568 common listmount sys_listmount +569 common lsm_get_self_attr sys_lsm_get_self_attr +570 common lsm_set_self_attr sys_lsm_set_self_attr +571 common lsm_list_modules sys_lsm_list_modules +572 common mseal sys_mseal diff --git a/tools/perf/arch/alpha/include/syscall_table.h b/tools/perf/arch/alpha/include/syscall_table.h new file mode 100644 index 000000000000..b53e31c15805 --- /dev/null +++ b/tools/perf/arch/alpha/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_64.h> diff --git a/tools/perf/arch/arc/entry/syscalls/Kbuild b/tools/perf/arch/arc/entry/syscalls/Kbuild new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/arc/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/arc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/arc/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..391d30ab7a83 --- /dev/null +++ b/tools/perf/arch/arc/entry/syscalls/Makefile.syscalls @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += arc time32 renameat stat64 rlimit diff --git a/tools/perf/arch/arc/include/syscall_table.h b/tools/perf/arch/arc/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/arc/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/arm/entry/syscalls/Kbuild b/tools/perf/arch/arm/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9d777540f089 --- /dev/null +++ b/tools/perf/arch/arm/entry/syscalls/Kbuild @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += oabi +syscalltbl = $(srctree)/tools/perf/arch/arm/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/arm/entry/syscalls/Makefile.syscalls b/tools/perf/arch/arm/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/arm/entry/syscalls/Makefile.syscalls @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..49eeb2ad8dbd --- /dev/null +++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl @@ -0,0 +1,483 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# Linux system call numbers and entry vectors +# +# The format is: +# <num> <abi> <name> [<entry point> [<oabi compat entry point>]] +# +# Where abi is: +# common - for system calls shared between oabi and eabi (may have compat) +# oabi - for oabi-only system calls (may have compat) +# eabi - for eabi-only system calls +# +# For each syscall number, "common" is mutually exclusive with oabi and eabi +# +0 common restart_syscall sys_restart_syscall +1 common exit sys_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open +6 common close sys_close +# 7 was sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve +12 common chdir sys_chdir +13 oabi time sys_time32 +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown16 +# 17 was sys_break +# 18 was sys_stat +19 common lseek sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +22 oabi umount sys_oldumount +23 common setuid sys_setuid16 +24 common getuid sys_getuid16 +25 oabi stime sys_stime32 +26 common ptrace sys_ptrace +27 oabi alarm sys_alarm +# 28 was sys_fstat +29 common pause sys_pause +30 oabi utime sys_utime32 +# 31 was sys_stty +# 32 was sys_gtty +33 common access sys_access +34 common nice sys_nice +# 35 was sys_ftime +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times +# 44 was sys_prof +45 common brk sys_brk +46 common setgid sys_setgid16 +47 common getgid sys_getgid16 +# 48 was sys_signal +49 common geteuid sys_geteuid16 +50 common getegid sys_getegid16 +51 common acct sys_acct +52 common umount2 sys_umount +# 53 was sys_lock +54 common ioctl sys_ioctl +55 common fcntl sys_fcntl +# 56 was sys_mpx +57 common setpgid sys_setpgid +# 58 was sys_ulimit +# 59 was sys_olduname +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common sigaction sys_sigaction +# 68 was sys_sgetmask +# 69 was sys_ssetmask +70 common setreuid sys_setreuid16 +71 common setregid sys_setregid16 +72 common sigsuspend sys_sigsuspend +73 common sigpending sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit +# Back compat 2GB limited rlimit +76 oabi getrlimit sys_old_getrlimit +77 common getrusage sys_getrusage +78 common gettimeofday sys_gettimeofday +79 common settimeofday sys_settimeofday +80 common getgroups sys_getgroups16 +81 common setgroups sys_setgroups16 +82 oabi select sys_old_select +83 common symlink sys_symlink +# 84 was sys_lstat +85 common readlink sys_readlink +86 common uselib sys_uselib +87 common swapon sys_swapon +88 common reboot sys_reboot +89 oabi readdir sys_old_readdir +90 oabi mmap sys_old_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate +93 common ftruncate sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown16 +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +# 98 was sys_profil +99 common statfs sys_statfs +100 common fstatfs sys_fstatfs +# 101 was sys_ioperm +102 oabi socketcall sys_socketcall sys_oabi_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer +105 common getitimer sys_getitimer +106 common stat sys_newstat +107 common lstat sys_newlstat +108 common fstat sys_newfstat +# 109 was sys_uname +# 110 was sys_iopl +111 common vhangup sys_vhangup +# 112 was sys_idle +# syscall to call a syscall! +113 oabi syscall sys_syscall +114 common wait4 sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo +117 oabi ipc sys_ipc sys_oabi_ipc +118 common fsync sys_fsync +119 common sigreturn sys_sigreturn_wrapper +120 common clone sys_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +# 123 was sys_modify_ldt +124 common adjtimex sys_adjtimex_time32 +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask +# 127 was sys_create_module +128 common init_module sys_init_module +129 common delete_module sys_delete_module +# 130 was sys_get_kernel_syms +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 common personality sys_personality +# 137 was sys_afs_syscall +138 common setfsuid sys_setfsuid16 +139 common setfsgid sys_setfsgid16 +140 common _llseek sys_llseek +141 common getdents sys_getdents +142 common _newselect sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 +163 common mremap sys_mremap +164 common setresuid sys_setresuid16 +165 common getresuid sys_getresuid16 +# 166 was sys_vm86 +# 167 was sys_query_module +168 common poll sys_poll +169 common nfsservctl +170 common setresgid sys_setresgid16 +171 common getresgid sys_getresgid16 +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn_wrapper +174 common rt_sigaction sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 +178 common rt_sigqueueinfo sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend +180 common pread64 sys_pread64 sys_oabi_pread64 +181 common pwrite64 sys_pwrite64 sys_oabi_pwrite64 +182 common chown sys_chown16 +183 common getcwd sys_getcwd +184 common capget sys_capget +185 common capset sys_capset +186 common sigaltstack sys_sigaltstack +187 common sendfile sys_sendfile +# 188 reserved +# 189 reserved +190 common vfork sys_vfork +# SuS compliant getrlimit +191 common ugetrlimit sys_getrlimit +192 common mmap2 sys_mmap2 +193 common truncate64 sys_truncate64 sys_oabi_truncate64 +194 common ftruncate64 sys_ftruncate64 sys_oabi_ftruncate64 +195 common stat64 sys_stat64 sys_oabi_stat64 +196 common lstat64 sys_lstat64 sys_oabi_lstat64 +197 common fstat64 sys_fstat64 sys_oabi_fstat64 +198 common lchown32 sys_lchown +199 common getuid32 sys_getuid +200 common getgid32 sys_getgid +201 common geteuid32 sys_geteuid +202 common getegid32 sys_getegid +203 common setreuid32 sys_setreuid +204 common setregid32 sys_setregid +205 common getgroups32 sys_getgroups +206 common setgroups32 sys_setgroups +207 common fchown32 sys_fchown +208 common setresuid32 sys_setresuid +209 common getresuid32 sys_getresuid +210 common setresgid32 sys_setresgid +211 common getresgid32 sys_getresgid +212 common chown32 sys_chown +213 common setuid32 sys_setuid +214 common setgid32 sys_setgid +215 common setfsuid32 sys_setfsuid +216 common setfsgid32 sys_setfsgid +217 common getdents64 sys_getdents64 +218 common pivot_root sys_pivot_root +219 common mincore sys_mincore +220 common madvise sys_madvise +221 common fcntl64 sys_fcntl64 sys_oabi_fcntl64 +# 222 for tux +# 223 is unused +224 common gettid sys_gettid +225 common readahead sys_readahead sys_oabi_readahead +226 common setxattr sys_setxattr +227 common lsetxattr sys_lsetxattr +228 common fsetxattr sys_fsetxattr +229 common getxattr sys_getxattr +230 common lgetxattr sys_lgetxattr +231 common fgetxattr sys_fgetxattr +232 common listxattr sys_listxattr +233 common llistxattr sys_llistxattr +234 common flistxattr sys_flistxattr +235 common removexattr sys_removexattr +236 common lremovexattr sys_lremovexattr +237 common fremovexattr sys_fremovexattr +238 common tkill sys_tkill +239 common sendfile64 sys_sendfile64 +240 common futex sys_futex_time32 +241 common sched_setaffinity sys_sched_setaffinity +242 common sched_getaffinity sys_sched_getaffinity +243 common io_setup sys_io_setup +244 common io_destroy sys_io_destroy +245 common io_getevents sys_io_getevents_time32 +246 common io_submit sys_io_submit +247 common io_cancel sys_io_cancel +248 common exit_group sys_exit_group +249 common lookup_dcookie sys_ni_syscall +250 common epoll_create sys_epoll_create +251 common epoll_ctl sys_epoll_ctl sys_oabi_epoll_ctl +252 common epoll_wait sys_epoll_wait +253 common remap_file_pages sys_remap_file_pages +# 254 for set_thread_area +# 255 for get_thread_area +256 common set_tid_address sys_set_tid_address +257 common timer_create sys_timer_create +258 common timer_settime sys_timer_settime32 +259 common timer_gettime sys_timer_gettime32 +260 common timer_getoverrun sys_timer_getoverrun +261 common timer_delete sys_timer_delete +262 common clock_settime sys_clock_settime32 +263 common clock_gettime sys_clock_gettime32 +264 common clock_getres sys_clock_getres_time32 +265 common clock_nanosleep sys_clock_nanosleep_time32 +266 common statfs64 sys_statfs64_wrapper +267 common fstatfs64 sys_fstatfs64_wrapper +268 common tgkill sys_tgkill +269 common utimes sys_utimes_time32 +270 common arm_fadvise64_64 sys_arm_fadvise64_64 +271 common pciconfig_iobase sys_pciconfig_iobase +272 common pciconfig_read sys_pciconfig_read +273 common pciconfig_write sys_pciconfig_write +274 common mq_open sys_mq_open +275 common mq_unlink sys_mq_unlink +276 common mq_timedsend sys_mq_timedsend_time32 +277 common mq_timedreceive sys_mq_timedreceive_time32 +278 common mq_notify sys_mq_notify +279 common mq_getsetattr sys_mq_getsetattr +280 common waitid sys_waitid +281 common socket sys_socket +282 common bind sys_bind sys_oabi_bind +283 common connect sys_connect sys_oabi_connect +284 common listen sys_listen +285 common accept sys_accept +286 common getsockname sys_getsockname +287 common getpeername sys_getpeername +288 common socketpair sys_socketpair +289 common send sys_send +290 common sendto sys_sendto sys_oabi_sendto +291 common recv sys_recv +292 common recvfrom sys_recvfrom +293 common shutdown sys_shutdown +294 common setsockopt sys_setsockopt +295 common getsockopt sys_getsockopt +296 common sendmsg sys_sendmsg sys_oabi_sendmsg +297 common recvmsg sys_recvmsg +298 common semop sys_semop sys_oabi_semop +299 common semget sys_semget +300 common semctl sys_old_semctl +301 common msgsnd sys_msgsnd +302 common msgrcv sys_msgrcv +303 common msgget sys_msgget +304 common msgctl sys_old_msgctl +305 common shmat sys_shmat +306 common shmdt sys_shmdt +307 common shmget sys_shmget +308 common shmctl sys_old_shmctl +309 common add_key sys_add_key +310 common request_key sys_request_key +311 common keyctl sys_keyctl +312 common semtimedop sys_semtimedop_time32 sys_oabi_semtimedop +313 common vserver +314 common ioprio_set sys_ioprio_set +315 common ioprio_get sys_ioprio_get +316 common inotify_init sys_inotify_init +317 common inotify_add_watch sys_inotify_add_watch +318 common inotify_rm_watch sys_inotify_rm_watch +319 common mbind sys_mbind +320 common get_mempolicy sys_get_mempolicy +321 common set_mempolicy sys_set_mempolicy +322 common openat sys_openat +323 common mkdirat sys_mkdirat +324 common mknodat sys_mknodat +325 common fchownat sys_fchownat +326 common futimesat sys_futimesat_time32 +327 common fstatat64 sys_fstatat64 sys_oabi_fstatat64 +328 common unlinkat sys_unlinkat +329 common renameat sys_renameat +330 common linkat sys_linkat +331 common symlinkat sys_symlinkat +332 common readlinkat sys_readlinkat +333 common fchmodat sys_fchmodat +334 common faccessat sys_faccessat +335 common pselect6 sys_pselect6_time32 +336 common ppoll sys_ppoll_time32 +337 common unshare sys_unshare +338 common set_robust_list sys_set_robust_list +339 common get_robust_list sys_get_robust_list +340 common splice sys_splice +341 common arm_sync_file_range sys_sync_file_range2 +342 common tee sys_tee +343 common vmsplice sys_vmsplice +344 common move_pages sys_move_pages +345 common getcpu sys_getcpu +346 common epoll_pwait sys_epoll_pwait +347 common kexec_load sys_kexec_load +348 common utimensat sys_utimensat_time32 +349 common signalfd sys_signalfd +350 common timerfd_create sys_timerfd_create +351 common eventfd sys_eventfd +352 common fallocate sys_fallocate +353 common timerfd_settime sys_timerfd_settime32 +354 common timerfd_gettime sys_timerfd_gettime32 +355 common signalfd4 sys_signalfd4 +356 common eventfd2 sys_eventfd2 +357 common epoll_create1 sys_epoll_create1 +358 common dup3 sys_dup3 +359 common pipe2 sys_pipe2 +360 common inotify_init1 sys_inotify_init1 +361 common preadv sys_preadv +362 common pwritev sys_pwritev +363 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +364 common perf_event_open sys_perf_event_open +365 common recvmmsg sys_recvmmsg_time32 +366 common accept4 sys_accept4 +367 common fanotify_init sys_fanotify_init +368 common fanotify_mark sys_fanotify_mark +369 common prlimit64 sys_prlimit64 +370 common name_to_handle_at sys_name_to_handle_at +371 common open_by_handle_at sys_open_by_handle_at +372 common clock_adjtime sys_clock_adjtime32 +373 common syncfs sys_syncfs +374 common sendmmsg sys_sendmmsg +375 common setns sys_setns +376 common process_vm_readv sys_process_vm_readv +377 common process_vm_writev sys_process_vm_writev +378 common kcmp sys_kcmp +379 common finit_module sys_finit_module +380 common sched_setattr sys_sched_setattr +381 common sched_getattr sys_sched_getattr +382 common renameat2 sys_renameat2 +383 common seccomp sys_seccomp +384 common getrandom sys_getrandom +385 common memfd_create sys_memfd_create +386 common bpf sys_bpf +387 common execveat sys_execveat +388 common userfaultfd sys_userfaultfd +389 common membarrier sys_membarrier +390 common mlock2 sys_mlock2 +391 common copy_file_range sys_copy_file_range +392 common preadv2 sys_preadv2 +393 common pwritev2 sys_pwritev2 +394 common pkey_mprotect sys_pkey_mprotect +395 common pkey_alloc sys_pkey_alloc +396 common pkey_free sys_pkey_free +397 common statx sys_statx +398 common rseq sys_rseq +399 common io_pgetevents sys_io_pgetevents_time32 +400 common migrate_pages sys_migrate_pages +401 common kexec_file_load sys_kexec_file_load +# 402 is unused +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/arm/include/syscall_table.h b/tools/perf/arch/arm/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/arm/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 91570d5d428e..087e099fb453 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -1,25 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 PERF_HAVE_JITDUMP := 1 HAVE_KVM_STAT_SUPPORT := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/arm64/include/generated/asm -header := $(out)/syscalls.c -incpath := $(srctree)/tools -sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h -sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, arm64) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/arm64/entry/syscalls/Kbuild b/tools/perf/arch/arm64/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/arm64/entry/syscalls/Makefile.syscalls b/tools/perf/arch/arm64/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..e7e78c2d1c02 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/Makefile.syscalls @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscall_abis_64 += renameat rlimit memfd_secret + +syscalltbl = $(srctree)/tools/perf/arch/arm64/entry/syscalls/syscall_%.tbl diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl deleted file mode 100755 index 27d747c92d44..000000000000 --- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,46 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# powerpc script. -# -# Copyright IBM Corp. 2017 -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> -# Changed by: Kim Phillips <kim.phillips@arm.com> - -gcc=$1 -hostcc=$2 -incpath=$3 -input=$4 - -if ! test -r $input; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_sc_table() -{ - local sc nr max_nr - - while read sc nr; do - printf "%s\n" " [$nr] = \"$sc\"," - max_nr=$nr - done - - echo "#define SYSCALLTBL_ARM64_MAX_ID $max_nr" -} - -create_table() -{ - echo "#include \"$input\"" - echo "static const char *const syscalltbl_arm64[] = {" - create_sc_table - echo "};" -} - -$gcc -E -dM -x c -I $incpath/include/uapi $input \ - |awk '$2 ~ "__NR" && $3 !~ "__NR3264_" { - sub("^#define __NR(3264)?_", ""); - print | "sort -k2 -n"}' \ - |create_table diff --git a/tools/perf/arch/arm64/entry/syscalls/syscall_32.tbl b/tools/perf/arch/arm64/entry/syscalls/syscall_32.tbl new file mode 100644 index 000000000000..9a37930d4e26 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/syscall_32.tbl @@ -0,0 +1,476 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# AArch32 (compat) system call definitions. +# +# Copyright (C) 2001-2005 Russell King +# Copyright (C) 2012 ARM Ltd. +# +# This file corresponds to arch/arm/tools/syscall.tbl +# for the native EABI syscalls and should be kept in sync +# Instead of the OABI syscalls, it contains pointers to +# the compat entry points where they differ from the native +# syscalls. +# +0 common restart_syscall sys_restart_syscall +1 common exit sys_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open compat_sys_open +6 common close sys_close +# 7 was sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve compat_sys_execve +12 common chdir sys_chdir +# 13 was sys_time +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown16 +# 17 was sys_break +# 18 was sys_stat +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +# 22 was sys_umount +23 common setuid sys_setuid16 +24 common getuid sys_getuid16 +# 25 was sys_stime +26 common ptrace sys_ptrace compat_sys_ptrace +# 27 was sys_alarm +# 28 was sys_fstat +29 common pause sys_pause +# 30 was sys_utime +# 31 was sys_stty +# 32 was sys_gtty +33 common access sys_access +34 common nice sys_nice +# 35 was sys_ftime +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times compat_sys_times +# 44 was sys_prof +45 common brk sys_brk +46 common setgid sys_setgid16 +47 common getgid sys_getgid16 +# 48 was sys_signal +49 common geteuid sys_geteuid16 +50 common getegid sys_getegid16 +51 common acct sys_acct +52 common umount2 sys_umount +# 53 was sys_lock +54 common ioctl sys_ioctl compat_sys_ioctl +55 common fcntl sys_fcntl compat_sys_fcntl +# 56 was sys_mpx +57 common setpgid sys_setpgid +# 58 was sys_ulimit +# 59 was sys_olduname +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat compat_sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common sigaction sys_sigaction compat_sys_sigaction +# 68 was sys_sgetmask +# 69 was sys_ssetmask +70 common setreuid sys_setreuid16 +71 common setregid sys_setregid16 +72 common sigsuspend sys_sigsuspend +73 common sigpending sys_sigpending compat_sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit compat_sys_setrlimit +# 76 was compat_sys_getrlimit +77 common getrusage sys_getrusage compat_sys_getrusage +78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 common settimeofday sys_settimeofday compat_sys_settimeofday +80 common getgroups sys_getgroups16 +81 common setgroups sys_setgroups16 +# 82 was compat_sys_select +83 common symlink sys_symlink +# 84 was sys_lstat +85 common readlink sys_readlink +86 common uselib sys_uselib +87 common swapon sys_swapon +88 common reboot sys_reboot +# 89 was sys_readdir +# 90 was sys_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate compat_sys_truncate +93 common ftruncate sys_ftruncate compat_sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown16 +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +# 98 was sys_profil +99 common statfs sys_statfs compat_sys_statfs +100 common fstatfs sys_fstatfs compat_sys_fstatfs +# 101 was sys_ioperm +# 102 was sys_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer compat_sys_setitimer +105 common getitimer sys_getitimer compat_sys_getitimer +106 common stat sys_newstat compat_sys_newstat +107 common lstat sys_newlstat compat_sys_newlstat +108 common fstat sys_newfstat compat_sys_newfstat +# 109 was sys_uname +# 110 was sys_iopl +111 common vhangup sys_vhangup +# 112 was sys_idle +# 113 was sys_syscall +114 common wait4 sys_wait4 compat_sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo compat_sys_sysinfo +# 117 was sys_ipc +118 common fsync sys_fsync +119 common sigreturn sys_sigreturn_wrapper compat_sys_sigreturn +120 common clone sys_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +# 123 was sys_modify_ldt +124 common adjtimex sys_adjtimex_time32 +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask +# 127 was sys_create_module +128 common init_module sys_init_module +129 common delete_module sys_delete_module +# 130 was sys_get_kernel_syms +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 common personality sys_personality +# 137 was sys_afs_syscall +138 common setfsuid sys_setfsuid16 +139 common setfsgid sys_setfsgid16 +140 common _llseek sys_llseek +141 common getdents sys_getdents compat_sys_getdents +142 common _newselect sys_select compat_sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 +163 common mremap sys_mremap +164 common setresuid sys_setresuid16 +165 common getresuid sys_getresuid16 +# 166 was sys_vm86 +# 167 was sys_query_module +168 common poll sys_poll +169 common nfsservctl sys_ni_syscall +170 common setresgid sys_setresgid16 +171 common getresgid sys_getresgid16 +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn_wrapper compat_sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +180 common pread64 sys_pread64 compat_sys_aarch32_pread64 +181 common pwrite64 sys_pwrite64 compat_sys_aarch32_pwrite64 +182 common chown sys_chown16 +183 common getcwd sys_getcwd +184 common capget sys_capget +185 common capset sys_capset +186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +187 common sendfile sys_sendfile compat_sys_sendfile +# 188 reserved +# 189 reserved +190 common vfork sys_vfork +# SuS compliant getrlimit +191 common ugetrlimit sys_getrlimit compat_sys_getrlimit +192 common mmap2 sys_mmap2 compat_sys_aarch32_mmap2 +193 common truncate64 sys_truncate64 compat_sys_aarch32_truncate64 +194 common ftruncate64 sys_ftruncate64 compat_sys_aarch32_ftruncate64 +195 common stat64 sys_stat64 +196 common lstat64 sys_lstat64 +197 common fstat64 sys_fstat64 +198 common lchown32 sys_lchown +199 common getuid32 sys_getuid +200 common getgid32 sys_getgid +201 common geteuid32 sys_geteuid +202 common getegid32 sys_getegid +203 common setreuid32 sys_setreuid +204 common setregid32 sys_setregid +205 common getgroups32 sys_getgroups +206 common setgroups32 sys_setgroups +207 common fchown32 sys_fchown +208 common setresuid32 sys_setresuid +209 common getresuid32 sys_getresuid +210 common setresgid32 sys_setresgid +211 common getresgid32 sys_getresgid +212 common chown32 sys_chown +213 common setuid32 sys_setuid +214 common setgid32 sys_setgid +215 common setfsuid32 sys_setfsuid +216 common setfsgid32 sys_setfsgid +217 common getdents64 sys_getdents64 +218 common pivot_root sys_pivot_root +219 common mincore sys_mincore +220 common madvise sys_madvise +221 common fcntl64 sys_fcntl64 compat_sys_fcntl64 +# 222 for tux +# 223 is unused +224 common gettid sys_gettid +225 common readahead sys_readahead compat_sys_aarch32_readahead +226 common setxattr sys_setxattr +227 common lsetxattr sys_lsetxattr +228 common fsetxattr sys_fsetxattr +229 common getxattr sys_getxattr +230 common lgetxattr sys_lgetxattr +231 common fgetxattr sys_fgetxattr +232 common listxattr sys_listxattr +233 common llistxattr sys_llistxattr +234 common flistxattr sys_flistxattr +235 common removexattr sys_removexattr +236 common lremovexattr sys_lremovexattr +237 common fremovexattr sys_fremovexattr +238 common tkill sys_tkill +239 common sendfile64 sys_sendfile64 +240 common futex sys_futex_time32 +241 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +242 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +243 common io_setup sys_io_setup compat_sys_io_setup +244 common io_destroy sys_io_destroy +245 common io_getevents sys_io_getevents_time32 +246 common io_submit sys_io_submit compat_sys_io_submit +247 common io_cancel sys_io_cancel +248 common exit_group sys_exit_group +249 common lookup_dcookie sys_ni_syscall +250 common epoll_create sys_epoll_create +251 common epoll_ctl sys_epoll_ctl +252 common epoll_wait sys_epoll_wait +253 common remap_file_pages sys_remap_file_pages +# 254 for set_thread_area +# 255 for get_thread_area +256 common set_tid_address sys_set_tid_address +257 common timer_create sys_timer_create compat_sys_timer_create +258 common timer_settime sys_timer_settime32 +259 common timer_gettime sys_timer_gettime32 +260 common timer_getoverrun sys_timer_getoverrun +261 common timer_delete sys_timer_delete +262 common clock_settime sys_clock_settime32 +263 common clock_gettime sys_clock_gettime32 +264 common clock_getres sys_clock_getres_time32 +265 common clock_nanosleep sys_clock_nanosleep_time32 +266 common statfs64 sys_statfs64_wrapper compat_sys_aarch32_statfs64 +267 common fstatfs64 sys_fstatfs64_wrapper compat_sys_aarch32_fstatfs64 +268 common tgkill sys_tgkill +269 common utimes sys_utimes_time32 +270 common arm_fadvise64_64 sys_arm_fadvise64_64 compat_sys_aarch32_fadvise64_64 +271 common pciconfig_iobase sys_pciconfig_iobase +272 common pciconfig_read sys_pciconfig_read +273 common pciconfig_write sys_pciconfig_write +274 common mq_open sys_mq_open compat_sys_mq_open +275 common mq_unlink sys_mq_unlink +276 common mq_timedsend sys_mq_timedsend_time32 +277 common mq_timedreceive sys_mq_timedreceive_time32 +278 common mq_notify sys_mq_notify compat_sys_mq_notify +279 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +280 common waitid sys_waitid compat_sys_waitid +281 common socket sys_socket +282 common bind sys_bind +283 common connect sys_connect +284 common listen sys_listen +285 common accept sys_accept +286 common getsockname sys_getsockname +287 common getpeername sys_getpeername +288 common socketpair sys_socketpair +289 common send sys_send +290 common sendto sys_sendto +291 common recv sys_recv compat_sys_recv +292 common recvfrom sys_recvfrom compat_sys_recvfrom +293 common shutdown sys_shutdown +294 common setsockopt sys_setsockopt +295 common getsockopt sys_getsockopt +296 common sendmsg sys_sendmsg compat_sys_sendmsg +297 common recvmsg sys_recvmsg compat_sys_recvmsg +298 common semop sys_semop +299 common semget sys_semget +300 common semctl sys_old_semctl compat_sys_old_semctl +301 common msgsnd sys_msgsnd compat_sys_msgsnd +302 common msgrcv sys_msgrcv compat_sys_msgrcv +303 common msgget sys_msgget +304 common msgctl sys_old_msgctl compat_sys_old_msgctl +305 common shmat sys_shmat compat_sys_shmat +306 common shmdt sys_shmdt +307 common shmget sys_shmget +308 common shmctl sys_old_shmctl compat_sys_old_shmctl +309 common add_key sys_add_key +310 common request_key sys_request_key +311 common keyctl sys_keyctl compat_sys_keyctl +312 common semtimedop sys_semtimedop_time32 +313 common vserver sys_ni_syscall +314 common ioprio_set sys_ioprio_set +315 common ioprio_get sys_ioprio_get +316 common inotify_init sys_inotify_init +317 common inotify_add_watch sys_inotify_add_watch +318 common inotify_rm_watch sys_inotify_rm_watch +319 common mbind sys_mbind +320 common get_mempolicy sys_get_mempolicy +321 common set_mempolicy sys_set_mempolicy +322 common openat sys_openat compat_sys_openat +323 common mkdirat sys_mkdirat +324 common mknodat sys_mknodat +325 common fchownat sys_fchownat +326 common futimesat sys_futimesat_time32 +327 common fstatat64 sys_fstatat64 +328 common unlinkat sys_unlinkat +329 common renameat sys_renameat +330 common linkat sys_linkat +331 common symlinkat sys_symlinkat +332 common readlinkat sys_readlinkat +333 common fchmodat sys_fchmodat +334 common faccessat sys_faccessat +335 common pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +336 common ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +337 common unshare sys_unshare +338 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +339 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +340 common splice sys_splice +341 common arm_sync_file_range sys_sync_file_range2 compat_sys_aarch32_sync_file_range2 +342 common tee sys_tee +343 common vmsplice sys_vmsplice +344 common move_pages sys_move_pages +345 common getcpu sys_getcpu +346 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +347 common kexec_load sys_kexec_load compat_sys_kexec_load +348 common utimensat sys_utimensat_time32 +349 common signalfd sys_signalfd compat_sys_signalfd +350 common timerfd_create sys_timerfd_create +351 common eventfd sys_eventfd +352 common fallocate sys_fallocate compat_sys_aarch32_fallocate +353 common timerfd_settime sys_timerfd_settime32 +354 common timerfd_gettime sys_timerfd_gettime32 +355 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +356 common eventfd2 sys_eventfd2 +357 common epoll_create1 sys_epoll_create1 +358 common dup3 sys_dup3 +359 common pipe2 sys_pipe2 +360 common inotify_init1 sys_inotify_init1 +361 common preadv sys_preadv compat_sys_preadv +362 common pwritev sys_pwritev compat_sys_pwritev +363 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +364 common perf_event_open sys_perf_event_open +365 common recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +366 common accept4 sys_accept4 +367 common fanotify_init sys_fanotify_init +368 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +369 common prlimit64 sys_prlimit64 +370 common name_to_handle_at sys_name_to_handle_at +371 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +372 common clock_adjtime sys_clock_adjtime32 +373 common syncfs sys_syncfs +374 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +375 common setns sys_setns +376 common process_vm_readv sys_process_vm_readv +377 common process_vm_writev sys_process_vm_writev +378 common kcmp sys_kcmp +379 common finit_module sys_finit_module +380 common sched_setattr sys_sched_setattr +381 common sched_getattr sys_sched_getattr +382 common renameat2 sys_renameat2 +383 common seccomp sys_seccomp +384 common getrandom sys_getrandom +385 common memfd_create sys_memfd_create +386 common bpf sys_bpf +387 common execveat sys_execveat compat_sys_execveat +388 common userfaultfd sys_userfaultfd +389 common membarrier sys_membarrier +390 common mlock2 sys_mlock2 +391 common copy_file_range sys_copy_file_range +392 common preadv2 sys_preadv2 compat_sys_preadv2 +393 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +394 common pkey_mprotect sys_pkey_mprotect +395 common pkey_alloc sys_pkey_alloc +396 common pkey_free sys_pkey_free +397 common statx sys_statx +398 common rseq sys_rseq +399 common io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +400 common migrate_pages sys_migrate_pages +401 common kexec_file_load sys_kexec_file_load +# 402 is unused +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 common ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 common io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 +417 common recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/tools/perf/arch/arm64/entry/syscalls/syscall_64.tbl b/tools/perf/arch/arm64/entry/syscalls/syscall_64.tbl new file mode 120000 index 000000000000..4fdd58f10c15 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/syscall_64.tbl @@ -0,0 +1 @@ +../../../../../scripts/syscall.tbl \ No newline at end of file diff --git a/tools/perf/arch/arm64/include/syscall_table.h b/tools/perf/arch/arm64/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/arm64/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 22b19dcc6beb..4301181b8e45 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -274,33 +274,9 @@ static void arm_spe_setup_evsel(struct evsel *evsel, struct perf_cpu_map *cpus) evsel__set_sample_bit(evsel, PHYS_ADDR); } -static int arm_spe_recording_options(struct auxtrace_record *itr, - struct evlist *evlist, - struct record_opts *opts) +static int arm_spe_setup_aux_buffer(struct record_opts *opts) { - struct arm_spe_recording *sper = - container_of(itr, struct arm_spe_recording, itr); - struct evsel *evsel, *tmp; - struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); - struct evsel *tracking_evsel; - int err; - - sper->evlist = evlist; - - evlist__for_each_entry(evlist, evsel) { - if (evsel__is_aux_event(evsel)) { - if (!strstarts(evsel->pmu->name, ARM_SPE_PMU_NAME)) { - pr_err("Found unexpected auxtrace event: %s\n", - evsel->pmu->name); - return -EINVAL; - } - opts->full_auxtrace = true; - } - } - - if (!opts->full_auxtrace) - return 0; /* * we are in snapshot mode. @@ -330,6 +306,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); return -EINVAL; } + + pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME, + opts->auxtrace_snapshot_size); } /* We are in full trace mode but '-m,xyz' wasn't specified */ @@ -355,14 +334,15 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, } } - if (opts->auxtrace_snapshot_mode) - pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME, - opts->auxtrace_snapshot_size); + return 0; +} - evlist__for_each_entry_safe(evlist, tmp, evsel) { - if (evsel__is_aux_event(evsel)) - arm_spe_setup_evsel(evsel, cpus); - } +static int arm_spe_setup_tracking_event(struct evlist *evlist, + struct record_opts *opts) +{ + int err; + struct evsel *tracking_evsel; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; /* Add dummy event to keep tracking */ err = parse_event(evlist, "dummy:u"); @@ -388,6 +368,52 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, return 0; } +static int arm_spe_recording_options(struct auxtrace_record *itr, + struct evlist *evlist, + struct record_opts *opts) +{ + struct arm_spe_recording *sper = + container_of(itr, struct arm_spe_recording, itr); + struct evsel *evsel, *tmp; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; + bool discard = false; + int err; + + sper->evlist = evlist; + + evlist__for_each_entry(evlist, evsel) { + if (evsel__is_aux_event(evsel)) { + if (!strstarts(evsel->pmu->name, ARM_SPE_PMU_NAME)) { + pr_err("Found unexpected auxtrace event: %s\n", + evsel->pmu->name); + return -EINVAL; + } + opts->full_auxtrace = true; + } + } + + if (!opts->full_auxtrace) + return 0; + + evlist__for_each_entry_safe(evlist, tmp, evsel) { + if (evsel__is_aux_event(evsel)) { + arm_spe_setup_evsel(evsel, cpus); + if (evsel->core.attr.config & + perf_pmu__format_bits(evsel->pmu, "discard")) + discard = true; + } + } + + if (discard) + return 0; + + err = arm_spe_setup_aux_buffer(opts); + if (err) + return err; + + return arm_spe_setup_tracking_event(evlist, opts); +} + static int arm_spe_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused, struct record_opts *opts, const char *str) diff --git a/tools/perf/arch/csky/entry/syscalls/Kbuild b/tools/perf/arch/csky/entry/syscalls/Kbuild new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/csky/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/csky/entry/syscalls/Makefile.syscalls b/tools/perf/arch/csky/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..ea2dd10d0571 --- /dev/null +++ b/tools/perf/arch/csky/entry/syscalls/Makefile.syscalls @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += csky time32 stat64 rlimit diff --git a/tools/perf/arch/csky/include/syscall_table.h b/tools/perf/arch/csky/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/csky/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile index 52544d59245b..087e099fb453 100644 --- a/tools/perf/arch/loongarch/Makefile +++ b/tools/perf/arch/loongarch/Makefile @@ -1,25 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 PERF_HAVE_JITDUMP := 1 HAVE_KVM_STAT_SUPPORT := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/loongarch/include/generated/asm -header := $(out)/syscalls.c -incpath := $(srctree)/tools -sysdef := $(srctree)/tools/arch/loongarch/include/uapi/asm/unistd.h -sysprf := $(srctree)/tools/perf/arch/loongarch/entry/syscalls/ -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, loongarch) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/loongarch/entry/syscalls/Kbuild b/tools/perf/arch/loongarch/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/loongarch/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/loongarch/entry/syscalls/Makefile.syscalls b/tools/perf/arch/loongarch/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..47d32da2aed8 --- /dev/null +++ b/tools/perf/arch/loongarch/entry/syscalls/Makefile.syscalls @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_64 += diff --git a/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl b/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl deleted file mode 100755 index c10ad3580aef..000000000000 --- a/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,45 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# powerpc script. -# -# Author(s): Ming Wang <wangming01@loongson.cn> -# Author(s): Huacai Chen <chenhuacai@loongson.cn> -# Copyright (C) 2020-2023 Loongson Technology Corporation Limited - -gcc=$1 -hostcc=$2 -incpath=$3 -input=$4 - -if ! test -r $input; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_sc_table() -{ - local sc nr max_nr - - while read sc nr; do - printf "%s\n" " [$nr] = \"$sc\"," - max_nr=$nr - done - - echo "#define SYSCALLTBL_LOONGARCH_MAX_ID $max_nr" -} - -create_table() -{ - echo "#include \"$input\"" - echo "static const char *const syscalltbl_loongarch[] = {" - create_sc_table - echo "};" -} - -$gcc -E -dM -x c -I $incpath/include/uapi $input \ - |awk '$2 ~ "__NR" && $3 !~ "__NR3264_" { - sub("^#define __NR(3264)?_", ""); - print | "sort -k2 -n"}' \ - |create_table diff --git a/tools/perf/arch/loongarch/include/syscall_table.h b/tools/perf/arch/loongarch/include/syscall_table.h new file mode 100644 index 000000000000..9d0646d3455c --- /dev/null +++ b/tools/perf/arch/loongarch/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscall_table_64.h> diff --git a/tools/perf/arch/mips/Makefile b/tools/perf/arch/mips/Makefile deleted file mode 100644 index 827168f1077a..000000000000 --- a/tools/perf/arch/mips/Makefile +++ /dev/null @@ -1,18 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Syscall table generation for perf -out := $(OUTPUT)arch/mips/include/generated/asm -header := $(out)/syscalls_n64.c -sysprf := $(srctree)/tools/perf/arch/mips/entry/syscalls -sysdef := $(sysprf)/syscall_n64.tbl -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, mips) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/mips/entry/syscalls/Kbuild b/tools/perf/arch/mips/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/mips/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/mips/entry/syscalls/Makefile.syscalls b/tools/perf/arch/mips/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..9ee914bdfb05 --- /dev/null +++ b/tools/perf/arch/mips/entry/syscalls/Makefile.syscalls @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_64 += n64 + +syscalltbl = $(srctree)/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl diff --git a/tools/perf/arch/mips/entry/syscalls/mksyscalltbl b/tools/perf/arch/mips/entry/syscalls/mksyscalltbl deleted file mode 100644 index c0d93f959c4e..000000000000 --- a/tools/perf/arch/mips/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,32 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# s390 script. -# -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# Changed by: Tiezhu Yang <yangtiezhu@loongson.cn> - -SYSCALL_TBL=$1 - -if ! test -r $SYSCALL_TBL; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_table() -{ - local max_nr nr abi sc discard - - echo 'static const char *const syscalltbl_mips_n64[] = {' - while read nr abi sc discard; do - printf '\t[%d] = "%s",\n' $nr $sc - max_nr=$nr - done - echo '};' - echo "#define SYSCALLTBL_MIPS_N64_MAX_ID $max_nr" -} - -grep -E "^[[:digit:]]+[[:space:]]+(n64)" $SYSCALL_TBL \ - |sort -k1 -n \ - |create_table diff --git a/tools/perf/arch/mips/include/syscall_table.h b/tools/perf/arch/mips/include/syscall_table.h new file mode 100644 index 000000000000..b53e31c15805 --- /dev/null +++ b/tools/perf/arch/mips/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_64.h> diff --git a/tools/perf/arch/parisc/entry/syscalls/Kbuild b/tools/perf/arch/parisc/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/parisc/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/parisc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/parisc/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..ae326fecb83b --- /dev/null +++ b/tools/perf/arch/parisc/entry/syscalls/Makefile.syscalls @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscall_abis_64 += + +syscalltbl = $(srctree)/tools/perf/arch/parisc/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/parisc/entry/syscalls/syscall.tbl b/tools/perf/arch/parisc/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..66dc406b12e4 --- /dev/null +++ b/tools/perf/arch/parisc/entry/syscalls/syscall.tbl @@ -0,0 +1,463 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for parisc +# +# The format is: +# <number> <abi> <name> <entry point> <compat entry point> +# +# The <abi> can be common, 64, or 32 for this file. +# +0 common restart_syscall sys_restart_syscall +1 common exit sys_exit +2 common fork sys_fork_wrapper +3 common read sys_read +4 common write sys_write +5 common open sys_open compat_sys_open +6 common close sys_close +7 common waitpid sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve compat_sys_execve +12 common chdir sys_chdir +13 32 time sys_time32 +13 64 time sys_time +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown +17 common socket sys_socket +18 common stat sys_newstat compat_sys_newstat +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +22 common bind sys_bind +23 common setuid sys_setuid +24 common getuid sys_getuid +25 32 stime sys_stime32 +25 64 stime sys_stime +26 common ptrace sys_ptrace compat_sys_ptrace +27 common alarm sys_alarm +28 common fstat sys_newfstat compat_sys_newfstat +29 common pause sys_pause +30 32 utime sys_utime32 +30 64 utime sys_utime +31 common connect sys_connect +32 common listen sys_listen +33 common access sys_access +34 common nice sys_nice +35 common accept sys_accept +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times compat_sys_times +44 common getsockname sys_getsockname +45 common brk sys_brk +46 common setgid sys_setgid +47 common getgid sys_getgid +48 common signal sys_signal +49 common geteuid sys_geteuid +50 common getegid sys_getegid +51 common acct sys_acct +52 common umount2 sys_umount +53 common getpeername sys_getpeername +54 common ioctl sys_ioctl compat_sys_ioctl +55 common fcntl sys_fcntl compat_sys_fcntl +56 common socketpair sys_socketpair +57 common setpgid sys_setpgid +58 common send sys_send +59 common uname sys_newuname +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat compat_sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common pivot_root sys_pivot_root +68 common sgetmask sys_sgetmask sys32_unimplemented +69 common ssetmask sys_ssetmask sys32_unimplemented +70 common setreuid sys_setreuid +71 common setregid sys_setregid +72 common mincore sys_mincore +73 common sigpending sys_sigpending compat_sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit compat_sys_setrlimit +76 common getrlimit sys_getrlimit compat_sys_getrlimit +77 common getrusage sys_getrusage compat_sys_getrusage +78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 common settimeofday sys_settimeofday compat_sys_settimeofday +80 common getgroups sys_getgroups +81 common setgroups sys_setgroups +82 common sendto sys_sendto +83 common symlink sys_symlink +84 common lstat sys_newlstat compat_sys_newlstat +85 common readlink sys_readlink +86 common uselib sys_ni_syscall +87 common swapon sys_swapon +88 common reboot sys_reboot +89 common mmap2 sys_mmap2 +90 common mmap sys_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate compat_sys_truncate +93 common ftruncate sys_ftruncate compat_sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +98 common recv sys_recv compat_sys_recv +99 common statfs sys_statfs compat_sys_statfs +100 common fstatfs sys_fstatfs compat_sys_fstatfs +101 common stat64 sys_stat64 +# 102 was socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer compat_sys_setitimer +105 common getitimer sys_getitimer compat_sys_getitimer +106 common capget sys_capget +107 common capset sys_capset +108 32 pread64 parisc_pread64 +108 64 pread64 sys_pread64 +109 32 pwrite64 parisc_pwrite64 +109 64 pwrite64 sys_pwrite64 +110 common getcwd sys_getcwd +111 common vhangup sys_vhangup +112 common fstat64 sys_fstat64 +113 common vfork sys_vfork_wrapper +114 common wait4 sys_wait4 compat_sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo compat_sys_sysinfo +117 common shutdown sys_shutdown +118 common fsync sys_fsync +119 common madvise parisc_madvise +120 common clone sys_clone_wrapper +121 common setdomainname sys_setdomainname +122 common sendfile sys_sendfile compat_sys_sendfile +123 common recvfrom sys_recvfrom compat_sys_recvfrom +124 32 adjtimex sys_adjtimex_time32 +124 64 adjtimex sys_adjtimex +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask +# 127 was create_module +128 common init_module sys_init_module +129 common delete_module sys_delete_module +# 130 was get_kernel_syms +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 32 personality parisc_personality +136 64 personality sys_personality +# 137 was afs_syscall +138 common setfsuid sys_setfsuid +139 common setfsgid sys_setfsgid +140 common _llseek sys_llseek +141 common getdents sys_getdents compat_sys_getdents +142 common _newselect sys_select compat_sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +161 64 sched_rr_get_interval sys_sched_rr_get_interval +162 32 nanosleep sys_nanosleep_time32 +162 64 nanosleep sys_nanosleep +163 common mremap sys_mremap +164 common setresuid sys_setresuid +165 common getresuid sys_getresuid +166 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +# 167 was query_module +168 common poll sys_poll +# 169 was nfsservctl +170 common setresgid sys_setresgid +171 common getresgid sys_getresgid +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn_wrapper +174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +177 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +177 64 rt_sigtimedwait sys_rt_sigtimedwait +178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +180 common chown sys_chown +181 common setsockopt sys_setsockopt sys_setsockopt +182 common getsockopt sys_getsockopt sys_getsockopt +183 common sendmsg sys_sendmsg compat_sys_sendmsg +184 common recvmsg sys_recvmsg compat_sys_recvmsg +185 common semop sys_semop +186 common semget sys_semget +187 common semctl sys_semctl compat_sys_semctl +188 common msgsnd sys_msgsnd compat_sys_msgsnd +189 common msgrcv sys_msgrcv compat_sys_msgrcv +190 common msgget sys_msgget +191 common msgctl sys_msgctl compat_sys_msgctl +192 common shmat sys_shmat compat_sys_shmat +193 common shmdt sys_shmdt +194 common shmget sys_shmget +195 common shmctl sys_shmctl compat_sys_shmctl +# 196 was getpmsg +# 197 was putpmsg +198 common lstat64 sys_lstat64 +199 32 truncate64 parisc_truncate64 +199 64 truncate64 sys_truncate64 +200 32 ftruncate64 parisc_ftruncate64 +200 64 ftruncate64 sys_ftruncate64 +201 common getdents64 sys_getdents64 +202 common fcntl64 sys_fcntl64 compat_sys_fcntl64 +# 203 was attrctl +# 204 was acl_get +# 205 was acl_set +206 common gettid sys_gettid +207 32 readahead parisc_readahead +207 64 readahead sys_readahead +208 common tkill sys_tkill +209 common sendfile64 sys_sendfile64 compat_sys_sendfile64 +210 32 futex sys_futex_time32 +210 64 futex sys_futex +211 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +212 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +# 213 was set_thread_area +# 214 was get_thread_area +215 common io_setup sys_io_setup compat_sys_io_setup +216 common io_destroy sys_io_destroy +217 32 io_getevents sys_io_getevents_time32 +217 64 io_getevents sys_io_getevents +218 common io_submit sys_io_submit compat_sys_io_submit +219 common io_cancel sys_io_cancel +# 220 was alloc_hugepages +# 221 was free_hugepages +222 common exit_group sys_exit_group +223 common lookup_dcookie sys_ni_syscall +224 common epoll_create sys_epoll_create +225 common epoll_ctl sys_epoll_ctl +226 common epoll_wait sys_epoll_wait +227 common remap_file_pages sys_remap_file_pages +228 32 semtimedop sys_semtimedop_time32 +228 64 semtimedop sys_semtimedop +229 common mq_open sys_mq_open compat_sys_mq_open +230 common mq_unlink sys_mq_unlink +231 32 mq_timedsend sys_mq_timedsend_time32 +231 64 mq_timedsend sys_mq_timedsend +232 32 mq_timedreceive sys_mq_timedreceive_time32 +232 64 mq_timedreceive sys_mq_timedreceive +233 common mq_notify sys_mq_notify compat_sys_mq_notify +234 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +235 common waitid sys_waitid compat_sys_waitid +236 32 fadvise64_64 parisc_fadvise64_64 +236 64 fadvise64_64 sys_fadvise64_64 +237 common set_tid_address sys_set_tid_address +238 common setxattr sys_setxattr +239 common lsetxattr sys_lsetxattr +240 common fsetxattr sys_fsetxattr +241 common getxattr sys_getxattr +242 common lgetxattr sys_lgetxattr +243 common fgetxattr sys_fgetxattr +244 common listxattr sys_listxattr +245 common llistxattr sys_llistxattr +246 common flistxattr sys_flistxattr +247 common removexattr sys_removexattr +248 common lremovexattr sys_lremovexattr +249 common fremovexattr sys_fremovexattr +250 common timer_create sys_timer_create compat_sys_timer_create +251 32 timer_settime sys_timer_settime32 +251 64 timer_settime sys_timer_settime +252 32 timer_gettime sys_timer_gettime32 +252 64 timer_gettime sys_timer_gettime +253 common timer_getoverrun sys_timer_getoverrun +254 common timer_delete sys_timer_delete +255 32 clock_settime sys_clock_settime32 +255 64 clock_settime sys_clock_settime +256 32 clock_gettime sys_clock_gettime32 +256 64 clock_gettime sys_clock_gettime +257 32 clock_getres sys_clock_getres_time32 +257 64 clock_getres sys_clock_getres +258 32 clock_nanosleep sys_clock_nanosleep_time32 +258 64 clock_nanosleep sys_clock_nanosleep +259 common tgkill sys_tgkill +260 common mbind sys_mbind +261 common get_mempolicy sys_get_mempolicy +262 common set_mempolicy sys_set_mempolicy +# 263 was vserver +264 common add_key sys_add_key +265 common request_key sys_request_key +266 common keyctl sys_keyctl compat_sys_keyctl +267 common ioprio_set sys_ioprio_set +268 common ioprio_get sys_ioprio_get +269 common inotify_init sys_inotify_init +270 common inotify_add_watch sys_inotify_add_watch +271 common inotify_rm_watch sys_inotify_rm_watch +272 common migrate_pages sys_migrate_pages +273 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +273 64 pselect6 sys_pselect6 +274 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +274 64 ppoll sys_ppoll +275 common openat sys_openat compat_sys_openat +276 common mkdirat sys_mkdirat +277 common mknodat sys_mknodat +278 common fchownat sys_fchownat +279 32 futimesat sys_futimesat_time32 +279 64 futimesat sys_futimesat +280 common fstatat64 sys_fstatat64 +281 common unlinkat sys_unlinkat +282 common renameat sys_renameat +283 common linkat sys_linkat +284 common symlinkat sys_symlinkat +285 common readlinkat sys_readlinkat +286 common fchmodat sys_fchmodat +287 common faccessat sys_faccessat +288 common unshare sys_unshare +289 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +290 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +291 common splice sys_splice +292 32 sync_file_range parisc_sync_file_range +292 64 sync_file_range sys_sync_file_range +293 common tee sys_tee +294 common vmsplice sys_vmsplice +295 common move_pages sys_move_pages +296 common getcpu sys_getcpu +297 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +298 common statfs64 sys_statfs64 compat_sys_statfs64 +299 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +300 common kexec_load sys_kexec_load compat_sys_kexec_load +301 32 utimensat sys_utimensat_time32 +301 64 utimensat sys_utimensat +302 common signalfd sys_signalfd compat_sys_signalfd +# 303 was timerfd +304 common eventfd sys_eventfd +305 32 fallocate parisc_fallocate +305 64 fallocate sys_fallocate +306 common timerfd_create parisc_timerfd_create +307 32 timerfd_settime sys_timerfd_settime32 +307 64 timerfd_settime sys_timerfd_settime +308 32 timerfd_gettime sys_timerfd_gettime32 +308 64 timerfd_gettime sys_timerfd_gettime +309 common signalfd4 parisc_signalfd4 parisc_compat_signalfd4 +310 common eventfd2 parisc_eventfd2 +311 common epoll_create1 sys_epoll_create1 +312 common dup3 sys_dup3 +313 common pipe2 parisc_pipe2 +314 common inotify_init1 parisc_inotify_init1 +315 common preadv sys_preadv compat_sys_preadv +316 common pwritev sys_pwritev compat_sys_pwritev +317 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +318 common perf_event_open sys_perf_event_open +319 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +319 64 recvmmsg sys_recvmmsg +320 common accept4 sys_accept4 +321 common prlimit64 sys_prlimit64 +322 common fanotify_init sys_fanotify_init +323 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +324 32 clock_adjtime sys_clock_adjtime32 +324 64 clock_adjtime sys_clock_adjtime +325 common name_to_handle_at sys_name_to_handle_at +326 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +327 common syncfs sys_syncfs +328 common setns sys_setns +329 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +330 common process_vm_readv sys_process_vm_readv +331 common process_vm_writev sys_process_vm_writev +332 common kcmp sys_kcmp +333 common finit_module sys_finit_module +334 common sched_setattr sys_sched_setattr +335 common sched_getattr sys_sched_getattr +336 32 utimes sys_utimes_time32 +336 64 utimes sys_utimes +337 common renameat2 sys_renameat2 +338 common seccomp sys_seccomp +339 common getrandom sys_getrandom +340 common memfd_create sys_memfd_create +341 common bpf sys_bpf +342 common execveat sys_execveat compat_sys_execveat +343 common membarrier sys_membarrier +344 common userfaultfd parisc_userfaultfd +345 common mlock2 sys_mlock2 +346 common copy_file_range sys_copy_file_range +347 common preadv2 sys_preadv2 compat_sys_preadv2 +348 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +349 common statx sys_statx +350 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +350 64 io_pgetevents sys_io_pgetevents +351 common pkey_mprotect sys_pkey_mprotect +352 common pkey_alloc sys_pkey_alloc +353 common pkey_free sys_pkey_free +354 common rseq sys_rseq +355 common kexec_file_load sys_kexec_file_load sys_kexec_file_load +356 common cacheflush sys_cacheflush +# up to 402 is unassigned and reserved for arch specific syscalls +403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 32 clock_settime64 sys_clock_settime sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 32 timer_settime64 sys_timer_settime sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3_wrapper +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/tools/perf/arch/parisc/include/syscall_table.h b/tools/perf/arch/parisc/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/parisc/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index dc8f4fb8e324..a295a80ea078 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -1,28 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_JITDUMP := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/powerpc/include/generated/asm -header32 := $(out)/syscalls_32.c -header64 := $(out)/syscalls_64.c -sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls -sysdef := $(sysprf)/syscall.tbl -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header64): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@ - -$(header32): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64) - -archheaders: $(header32) $(header64) diff --git a/tools/perf/arch/powerpc/entry/syscalls/Kbuild b/tools/perf/arch/powerpc/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/powerpc/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/powerpc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/powerpc/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..e35afbc57c79 --- /dev/null +++ b/tools/perf/arch/powerpc/entry/syscalls/Makefile.syscalls @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += nospu +syscall_abis_64 += nospu + +syscalltbl = $(srctree)/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl deleted file mode 100755 index 0eb316fe6dd1..000000000000 --- a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,39 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# s390 script. -# -# Copyright IBM Corp. 2017 -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> - -wordsize=$1 -SYSCALL_TBL=$2 - -if ! test -r $SYSCALL_TBL; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_table() -{ - local wordsize=$1 - local max_nr nr abi sc discard - max_nr=-1 - nr=0 - - echo "static const char *const syscalltbl_powerpc_${wordsize}[] = {" - while read nr abi sc discard; do - if [ "$max_nr" -lt "$nr" ]; then - printf '\t[%d] = "%s",\n' $nr $sc - max_nr=$nr - fi - done - echo '};' - echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr" -} - -grep -E "^[[:digit:]]+[[:space:]]+(common|spu|nospu|${wordsize})" $SYSCALL_TBL \ - |sort -k1 -n \ - |create_table ${wordsize} diff --git a/tools/perf/arch/powerpc/include/syscall_table.h b/tools/perf/arch/powerpc/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/powerpc/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index e8e6e6fc6f17..bd36cfd420a2 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -16,6 +16,7 @@ #define PVR_POWER9 0x004E #define PVR_POWER10 0x0080 +#define PVR_POWER11 0x0082 static const struct sample_reg sample_reg_masks[] = { SMPL_REG(r0, PERF_REG_POWERPC_R0), @@ -207,7 +208,7 @@ uint64_t arch__intr_reg_mask(void) version = (((mfspr(SPRN_PVR)) >> 16) & 0xFFFF); if (version == PVR_POWER9) extended_mask = PERF_REG_PMU_MASK_300; - else if (version == PVR_POWER10) + else if ((version == PVR_POWER10) || (version == PVR_POWER11)) extended_mask = PERF_REG_PMU_MASK_31; else return mask; diff --git a/tools/perf/arch/riscv/Makefile b/tools/perf/arch/riscv/Makefile index 18ad078000e2..087e099fb453 100644 --- a/tools/perf/arch/riscv/Makefile +++ b/tools/perf/arch/riscv/Makefile @@ -1,25 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 PERF_HAVE_JITDUMP := 1 HAVE_KVM_STAT_SUPPORT := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/riscv/include/generated/asm -header := $(out)/syscalls.c -incpath := $(srctree)/tools -sysdef := $(srctree)/tools/arch/riscv/include/uapi/asm/unistd.h -sysprf := $(srctree)/tools/perf/arch/riscv/entry/syscalls/ -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, riscv) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/riscv/entry/syscalls/Kbuild b/tools/perf/arch/riscv/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/riscv/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/riscv/entry/syscalls/Makefile.syscalls b/tools/perf/arch/riscv/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..9668fd1faf60 --- /dev/null +++ b/tools/perf/arch/riscv/entry/syscalls/Makefile.syscalls @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += riscv memfd_secret +syscall_abis_64 += riscv rlimit memfd_secret diff --git a/tools/perf/arch/riscv/entry/syscalls/mksyscalltbl b/tools/perf/arch/riscv/entry/syscalls/mksyscalltbl deleted file mode 100755 index c59f5e852b97..000000000000 --- a/tools/perf/arch/riscv/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,47 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# powerpc script. -# -# Copyright IBM Corp. 2017 -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> -# Changed by: Kim Phillips <kim.phillips@arm.com> -# Changed by: Björn Töpel <bjorn@rivosinc.com> - -gcc=$1 -hostcc=$2 -incpath=$3 -input=$4 - -if ! test -r $input; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_sc_table() -{ - local sc nr max_nr - - while read sc nr; do - printf "%s\n" " [$nr] = \"$sc\"," - max_nr=$nr - done - - echo "#define SYSCALLTBL_RISCV_MAX_ID $max_nr" -} - -create_table() -{ - echo "#include \"$input\"" - echo "static const char *const syscalltbl_riscv[] = {" - create_sc_table - echo "};" -} - -$gcc -E -dM -x c -I $incpath/include/uapi $input \ - |awk '$2 ~ "__NR" && $3 !~ "__NR3264_" { - sub("^#define __NR(3264)?_", ""); - print | "sort -k2 -n"}' \ - |create_table diff --git a/tools/perf/arch/riscv/include/syscall_table.h b/tools/perf/arch/riscv/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/riscv/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index c431c21b11ef..0033698a65ce 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -1,24 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_JITDUMP := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/s390/include/generated/asm -header := $(out)/syscalls_64.c -sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls -sysdef := $(sysprf)/syscall.tbl -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, s390) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/s390/entry/syscalls/Kbuild b/tools/perf/arch/s390/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/s390/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/s390/entry/syscalls/Makefile.syscalls b/tools/perf/arch/s390/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..9762d7abf17c --- /dev/null +++ b/tools/perf/arch/s390/entry/syscalls/Makefile.syscalls @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_64 += renameat rlimit memfd_secret + +syscalltbl = $(srctree)/tools/perf/arch/s390/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl deleted file mode 100755 index 52eb88a77c94..000000000000 --- a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,32 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf -# -# Copyright IBM Corp. 2017, 2018 -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# - -SYSCALL_TBL=$1 - -if ! test -r $SYSCALL_TBL; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_table() -{ - local max_nr nr abi sc discard - - echo 'static const char *const syscalltbl_s390_64[] = {' - while read nr abi sc discard; do - printf '\t[%d] = "%s",\n' $nr $sc - max_nr=$nr - done - echo '};' - echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr" -} - -grep -E "^[[:digit:]]+[[:space:]]+(common|64)" $SYSCALL_TBL \ - |sort -k1 -n \ - |create_table diff --git a/tools/perf/arch/s390/include/syscall_table.h b/tools/perf/arch/s390/include/syscall_table.h new file mode 100644 index 000000000000..b53e31c15805 --- /dev/null +++ b/tools/perf/arch/s390/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_64.h> diff --git a/tools/perf/arch/sh/entry/syscalls/Kbuild b/tools/perf/arch/sh/entry/syscalls/Kbuild new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/sh/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/sh/entry/syscalls/Makefile.syscalls b/tools/perf/arch/sh/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..25080390e4ed --- /dev/null +++ b/tools/perf/arch/sh/entry/syscalls/Makefile.syscalls @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscalltbl = $(srctree)/tools/perf/arch/sh/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..c8cad33bf250 --- /dev/null +++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl @@ -0,0 +1,472 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for sh +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The <abi> is always "common" for this file +# +0 common restart_syscall sys_restart_syscall +1 common exit sys_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open +6 common close sys_close +7 common waitpid sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve +12 common chdir sys_chdir +13 common time sys_time32 +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown16 +# 17 was break +18 common oldstat sys_stat +19 common lseek sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +22 common umount sys_oldumount +23 common setuid sys_setuid16 +24 common getuid sys_getuid16 +25 common stime sys_stime32 +26 common ptrace sys_ptrace +27 common alarm sys_alarm +28 common oldfstat sys_fstat +29 common pause sys_pause +30 common utime sys_utime32 +# 31 was stty +# 32 was gtty +33 common access sys_access +34 common nice sys_nice +# 35 was ftime +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_sh_pipe +43 common times sys_times +# 44 was prof +45 common brk sys_brk +46 common setgid sys_setgid16 +47 common getgid sys_getgid16 +48 common signal sys_signal +49 common geteuid sys_geteuid16 +50 common getegid sys_getegid16 +51 common acct sys_acct +52 common umount2 sys_umount +# 53 was lock +54 common ioctl sys_ioctl +55 common fcntl sys_fcntl +# 56 was mpx +57 common setpgid sys_setpgid +# 58 was ulimit +# 59 was olduname +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common sigaction sys_sigaction +68 common sgetmask sys_sgetmask +69 common ssetmask sys_ssetmask +70 common setreuid sys_setreuid16 +71 common setregid sys_setregid16 +72 common sigsuspend sys_sigsuspend +73 common sigpending sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit +76 common getrlimit sys_old_getrlimit +77 common getrusage sys_getrusage +78 common gettimeofday sys_gettimeofday +79 common settimeofday sys_settimeofday +80 common getgroups sys_getgroups16 +81 common setgroups sys_setgroups16 +# 82 was select +83 common symlink sys_symlink +84 common oldlstat sys_lstat +85 common readlink sys_readlink +86 common uselib sys_uselib +87 common swapon sys_swapon +88 common reboot sys_reboot +89 common readdir sys_old_readdir +90 common mmap old_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate +93 common ftruncate sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown16 +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +# 98 was profil +99 common statfs sys_statfs +100 common fstatfs sys_fstatfs +# 101 was ioperm +102 common socketcall sys_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer +105 common getitimer sys_getitimer +106 common stat sys_newstat +107 common lstat sys_newlstat +108 common fstat sys_newfstat +109 common olduname sys_uname +# 110 was iopl +111 common vhangup sys_vhangup +# 112 was idle +# 113 was vm86old +114 common wait4 sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo +117 common ipc sys_ipc +118 common fsync sys_fsync +119 common sigreturn sys_sigreturn +120 common clone sys_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +123 common cacheflush sys_cacheflush +124 common adjtimex sys_adjtimex_time32 +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask +# 127 was create_module +128 common init_module sys_init_module +129 common delete_module sys_delete_module +# 130 was get_kernel_syms +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 common personality sys_personality +# 137 was afs_syscall +138 common setfsuid sys_setfsuid16 +139 common setfsgid sys_setfsgid16 +140 common _llseek sys_llseek +141 common getdents sys_getdents +142 common _newselect sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 +163 common mremap sys_mremap +164 common setresuid sys_setresuid16 +165 common getresuid sys_getresuid16 +# 166 was vm86 +# 167 was query_module +168 common poll sys_poll +169 common nfsservctl sys_ni_syscall +170 common setresgid sys_setresgid16 +171 common getresgid sys_getresgid16 +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 +178 common rt_sigqueueinfo sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend +180 common pread64 sys_pread_wrapper +181 common pwrite64 sys_pwrite_wrapper +182 common chown sys_chown16 +183 common getcwd sys_getcwd +184 common capget sys_capget +185 common capset sys_capset +186 common sigaltstack sys_sigaltstack +187 common sendfile sys_sendfile +# 188 is reserved for getpmsg +# 189 is reserved for putpmsg +190 common vfork sys_vfork +191 common ugetrlimit sys_getrlimit +192 common mmap2 sys_mmap2 +193 common truncate64 sys_truncate64 +194 common ftruncate64 sys_ftruncate64 +195 common stat64 sys_stat64 +196 common lstat64 sys_lstat64 +197 common fstat64 sys_fstat64 +198 common lchown32 sys_lchown +199 common getuid32 sys_getuid +200 common getgid32 sys_getgid +201 common geteuid32 sys_geteuid +202 common getegid32 sys_getegid +203 common setreuid32 sys_setreuid +204 common setregid32 sys_setregid +205 common getgroups32 sys_getgroups +206 common setgroups32 sys_setgroups +207 common fchown32 sys_fchown +208 common setresuid32 sys_setresuid +209 common getresuid32 sys_getresuid +210 common setresgid32 sys_setresgid +211 common getresgid32 sys_getresgid +212 common chown32 sys_chown +213 common setuid32 sys_setuid +214 common setgid32 sys_setgid +215 common setfsuid32 sys_setfsuid +216 common setfsgid32 sys_setfsgid +217 common pivot_root sys_pivot_root +218 common mincore sys_mincore +219 common madvise sys_madvise +220 common getdents64 sys_getdents64 +221 common fcntl64 sys_fcntl64 +# 222 is reserved for tux +# 223 is unused +224 common gettid sys_gettid +225 common readahead sys_readahead +226 common setxattr sys_setxattr +227 common lsetxattr sys_lsetxattr +228 common fsetxattr sys_fsetxattr +229 common getxattr sys_getxattr +230 common lgetxattr sys_lgetxattr +231 common fgetxattr sys_fgetxattr +232 common listxattr sys_listxattr +233 common llistxattr sys_llistxattr +234 common flistxattr sys_flistxattr +235 common removexattr sys_removexattr +236 common lremovexattr sys_lremovexattr +237 common fremovexattr sys_fremovexattr +238 common tkill sys_tkill +239 common sendfile64 sys_sendfile64 +240 common futex sys_futex_time32 +241 common sched_setaffinity sys_sched_setaffinity +242 common sched_getaffinity sys_sched_getaffinity +# 243 is reserved for set_thread_area +# 244 is reserved for get_thread_area +245 common io_setup sys_io_setup +246 common io_destroy sys_io_destroy +247 common io_getevents sys_io_getevents_time32 +248 common io_submit sys_io_submit +249 common io_cancel sys_io_cancel +250 common fadvise64 sys_fadvise64 +# 251 is unused +252 common exit_group sys_exit_group +253 common lookup_dcookie sys_ni_syscall +254 common epoll_create sys_epoll_create +255 common epoll_ctl sys_epoll_ctl +256 common epoll_wait sys_epoll_wait +257 common remap_file_pages sys_remap_file_pages +258 common set_tid_address sys_set_tid_address +259 common timer_create sys_timer_create +260 common timer_settime sys_timer_settime32 +261 common timer_gettime sys_timer_gettime32 +262 common timer_getoverrun sys_timer_getoverrun +263 common timer_delete sys_timer_delete +264 common clock_settime sys_clock_settime32 +265 common clock_gettime sys_clock_gettime32 +266 common clock_getres sys_clock_getres_time32 +267 common clock_nanosleep sys_clock_nanosleep_time32 +268 common statfs64 sys_statfs64 +269 common fstatfs64 sys_fstatfs64 +270 common tgkill sys_tgkill +271 common utimes sys_utimes_time32 +272 common fadvise64_64 sys_fadvise64_64_wrapper +# 273 is reserved for vserver +274 common mbind sys_mbind +275 common get_mempolicy sys_get_mempolicy +276 common set_mempolicy sys_set_mempolicy +277 common mq_open sys_mq_open +278 common mq_unlink sys_mq_unlink +279 common mq_timedsend sys_mq_timedsend_time32 +280 common mq_timedreceive sys_mq_timedreceive_time32 +281 common mq_notify sys_mq_notify +282 common mq_getsetattr sys_mq_getsetattr +283 common kexec_load sys_kexec_load +284 common waitid sys_waitid +285 common add_key sys_add_key +286 common request_key sys_request_key +287 common keyctl sys_keyctl +288 common ioprio_set sys_ioprio_set +289 common ioprio_get sys_ioprio_get +290 common inotify_init sys_inotify_init +291 common inotify_add_watch sys_inotify_add_watch +292 common inotify_rm_watch sys_inotify_rm_watch +# 293 is unused +294 common migrate_pages sys_migrate_pages +295 common openat sys_openat +296 common mkdirat sys_mkdirat +297 common mknodat sys_mknodat +298 common fchownat sys_fchownat +299 common futimesat sys_futimesat_time32 +300 common fstatat64 sys_fstatat64 +301 common unlinkat sys_unlinkat +302 common renameat sys_renameat +303 common linkat sys_linkat +304 common symlinkat sys_symlinkat +305 common readlinkat sys_readlinkat +306 common fchmodat sys_fchmodat +307 common faccessat sys_faccessat +308 common pselect6 sys_pselect6_time32 +309 common ppoll sys_ppoll_time32 +310 common unshare sys_unshare +311 common set_robust_list sys_set_robust_list +312 common get_robust_list sys_get_robust_list +313 common splice sys_splice +314 common sync_file_range sys_sh_sync_file_range6 +315 common tee sys_tee +316 common vmsplice sys_vmsplice +317 common move_pages sys_move_pages +318 common getcpu sys_getcpu +319 common epoll_pwait sys_epoll_pwait +320 common utimensat sys_utimensat_time32 +321 common signalfd sys_signalfd +322 common timerfd_create sys_timerfd_create +323 common eventfd sys_eventfd +324 common fallocate sys_fallocate +325 common timerfd_settime sys_timerfd_settime32 +326 common timerfd_gettime sys_timerfd_gettime32 +327 common signalfd4 sys_signalfd4 +328 common eventfd2 sys_eventfd2 +329 common epoll_create1 sys_epoll_create1 +330 common dup3 sys_dup3 +331 common pipe2 sys_pipe2 +332 common inotify_init1 sys_inotify_init1 +333 common preadv sys_preadv +334 common pwritev sys_pwritev +335 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +336 common perf_event_open sys_perf_event_open +337 common fanotify_init sys_fanotify_init +338 common fanotify_mark sys_fanotify_mark +339 common prlimit64 sys_prlimit64 +340 common socket sys_socket +341 common bind sys_bind +342 common connect sys_connect +343 common listen sys_listen +344 common accept sys_accept +345 common getsockname sys_getsockname +346 common getpeername sys_getpeername +347 common socketpair sys_socketpair +348 common send sys_send +349 common sendto sys_sendto +350 common recv sys_recv +351 common recvfrom sys_recvfrom +352 common shutdown sys_shutdown +353 common setsockopt sys_setsockopt +354 common getsockopt sys_getsockopt +355 common sendmsg sys_sendmsg +356 common recvmsg sys_recvmsg +357 common recvmmsg sys_recvmmsg_time32 +358 common accept4 sys_accept4 +359 common name_to_handle_at sys_name_to_handle_at +360 common open_by_handle_at sys_open_by_handle_at +361 common clock_adjtime sys_clock_adjtime32 +362 common syncfs sys_syncfs +363 common sendmmsg sys_sendmmsg +364 common setns sys_setns +365 common process_vm_readv sys_process_vm_readv +366 common process_vm_writev sys_process_vm_writev +367 common kcmp sys_kcmp +368 common finit_module sys_finit_module +369 common sched_getattr sys_sched_getattr +370 common sched_setattr sys_sched_setattr +371 common renameat2 sys_renameat2 +372 common seccomp sys_seccomp +373 common getrandom sys_getrandom +374 common memfd_create sys_memfd_create +375 common bpf sys_bpf +376 common execveat sys_execveat +377 common userfaultfd sys_userfaultfd +378 common membarrier sys_membarrier +379 common mlock2 sys_mlock2 +380 common copy_file_range sys_copy_file_range +381 common preadv2 sys_preadv2 +382 common pwritev2 sys_pwritev2 +383 common statx sys_statx +384 common pkey_mprotect sys_pkey_mprotect +385 common pkey_alloc sys_pkey_alloc +386 common pkey_free sys_pkey_free +387 common rseq sys_rseq +388 common sync_file_range2 sys_sync_file_range2 +# room for arch specific syscalls +393 common semget sys_semget +394 common semctl sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl +397 common shmat sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd +401 common msgrcv sys_msgrcv +402 common msgctl sys_msgctl +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +# 435 reserved for clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/sh/include/syscall_table.h b/tools/perf/arch/sh/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/sh/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/sparc/entry/syscalls/Kbuild b/tools/perf/arch/sparc/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/sparc/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/sparc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/sparc/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..212c1800b644 --- /dev/null +++ b/tools/perf/arch/sparc/entry/syscalls/Makefile.syscalls @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscall_abis_64 += +syscalltbl = $(srctree)/tools/perf/arch/sparc/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..727f99d333b3 --- /dev/null +++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl @@ -0,0 +1,514 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for sparc +# +# The format is: +# <number> <abi> <name> <entry point> <compat entry point> +# +# The <abi> can be common, 64, or 32 for this file. +# +0 common restart_syscall sys_restart_syscall +1 32 exit sys_exit sparc_exit +1 64 exit sparc_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open compat_sys_open +6 common close sys_close +7 common wait4 sys_wait4 compat_sys_wait4 +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 32 execv sunos_execv +11 64 execv sys_nis_syscall +12 common chdir sys_chdir +13 32 chown sys_chown16 +13 64 chown sys_chown +14 common mknod sys_mknod +15 common chmod sys_chmod +16 32 lchown sys_lchown16 +16 64 lchown sys_lchown +17 common brk sys_brk +18 common perfctr sys_nis_syscall +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid +21 common capget sys_capget +22 common capset sys_capset +23 32 setuid sys_setuid16 +23 64 setuid sys_setuid +24 32 getuid sys_getuid16 +24 64 getuid sys_getuid +25 common vmsplice sys_vmsplice +26 common ptrace sys_ptrace compat_sys_ptrace +27 common alarm sys_alarm +28 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +29 32 pause sys_pause +29 64 pause sys_nis_syscall +30 32 utime sys_utime32 +30 64 utime sys_utime +31 32 lchown32 sys_lchown +32 32 fchown32 sys_fchown +33 common access sys_access +34 common nice sys_nice +35 32 chown32 sys_chown +36 common sync sys_sync +37 common kill sys_kill +38 common stat sys_newstat compat_sys_newstat +39 32 sendfile sys_sendfile compat_sys_sendfile +39 64 sendfile sys_sendfile64 +40 common lstat sys_newlstat compat_sys_newlstat +41 common dup sys_dup +42 common pipe sys_sparc_pipe +43 common times sys_times compat_sys_times +44 32 getuid32 sys_getuid +45 common umount2 sys_umount +46 32 setgid sys_setgid16 +46 64 setgid sys_setgid +47 32 getgid sys_getgid16 +47 64 getgid sys_getgid +48 common signal sys_signal +49 32 geteuid sys_geteuid16 +49 64 geteuid sys_geteuid +50 32 getegid sys_getegid16 +50 64 getegid sys_getegid +51 common acct sys_acct +52 64 memory_ordering sys_memory_ordering +53 32 getgid32 sys_getgid +54 common ioctl sys_ioctl compat_sys_ioctl +55 common reboot sys_reboot +56 32 mmap2 sys_mmap2 sys32_mmap2 +57 common symlink sys_symlink +58 common readlink sys_readlink +59 32 execve sys_execve sys32_execve +59 64 execve sys64_execve +60 common umask sys_umask +61 common chroot sys_chroot +62 common fstat sys_newfstat compat_sys_newfstat +63 common fstat64 sys_fstat64 compat_sys_fstat64 +64 common getpagesize sys_getpagesize +65 common msync sys_msync +66 common vfork sys_vfork +67 common pread64 sys_pread64 compat_sys_pread64 +68 common pwrite64 sys_pwrite64 compat_sys_pwrite64 +69 32 geteuid32 sys_geteuid +70 32 getegid32 sys_getegid +71 common mmap sys_mmap +72 32 setreuid32 sys_setreuid +73 32 munmap sys_munmap +73 64 munmap sys_64_munmap +74 common mprotect sys_mprotect +75 common madvise sys_madvise +76 common vhangup sys_vhangup +77 32 truncate64 sys_truncate64 compat_sys_truncate64 +78 common mincore sys_mincore +79 32 getgroups sys_getgroups16 +79 64 getgroups sys_getgroups +80 32 setgroups sys_setgroups16 +80 64 setgroups sys_setgroups +81 common getpgrp sys_getpgrp +82 32 setgroups32 sys_setgroups +83 common setitimer sys_setitimer compat_sys_setitimer +84 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64 +85 common swapon sys_swapon +86 common getitimer sys_getitimer compat_sys_getitimer +87 32 setuid32 sys_setuid +88 common sethostname sys_sethostname +89 32 setgid32 sys_setgid +90 common dup2 sys_dup2 +91 32 setfsuid32 sys_setfsuid +92 common fcntl sys_fcntl compat_sys_fcntl +93 common select sys_select compat_sys_select +94 32 setfsgid32 sys_setfsgid +95 common fsync sys_fsync +96 common setpriority sys_setpriority +97 common socket sys_socket +98 common connect sys_connect +99 common accept sys_accept +100 common getpriority sys_getpriority +101 common rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn +102 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +103 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +104 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +105 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +105 64 rt_sigtimedwait sys_rt_sigtimedwait +106 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +107 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +108 32 setresuid32 sys_setresuid +108 64 setresuid sys_setresuid +109 32 getresuid32 sys_getresuid +109 64 getresuid sys_getresuid +110 32 setresgid32 sys_setresgid +110 64 setresgid sys_setresgid +111 32 getresgid32 sys_getresgid +111 64 getresgid sys_getresgid +112 32 setregid32 sys_setregid +113 common recvmsg sys_recvmsg compat_sys_recvmsg +114 common sendmsg sys_sendmsg compat_sys_sendmsg +115 32 getgroups32 sys_getgroups +116 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +117 common getrusage sys_getrusage compat_sys_getrusage +118 common getsockopt sys_getsockopt sys_getsockopt +119 common getcwd sys_getcwd +120 common readv sys_readv +121 common writev sys_writev +122 common settimeofday sys_settimeofday compat_sys_settimeofday +123 32 fchown sys_fchown16 +123 64 fchown sys_fchown +124 common fchmod sys_fchmod +125 common recvfrom sys_recvfrom compat_sys_recvfrom +126 32 setreuid sys_setreuid16 +126 64 setreuid sys_setreuid +127 32 setregid sys_setregid16 +127 64 setregid sys_setregid +128 common rename sys_rename +129 common truncate sys_truncate compat_sys_truncate +130 common ftruncate sys_ftruncate compat_sys_ftruncate +131 common flock sys_flock +132 common lstat64 sys_lstat64 compat_sys_lstat64 +133 common sendto sys_sendto +134 common shutdown sys_shutdown +135 common socketpair sys_socketpair +136 common mkdir sys_mkdir +137 common rmdir sys_rmdir +138 32 utimes sys_utimes_time32 +138 64 utimes sys_utimes +139 common stat64 sys_stat64 compat_sys_stat64 +140 common sendfile64 sys_sendfile64 +141 common getpeername sys_getpeername +142 32 futex sys_futex_time32 +142 64 futex sys_futex +143 common gettid sys_gettid +144 common getrlimit sys_getrlimit compat_sys_getrlimit +145 common setrlimit sys_setrlimit compat_sys_setrlimit +146 common pivot_root sys_pivot_root +147 common prctl sys_prctl +148 common pciconfig_read sys_pciconfig_read +149 common pciconfig_write sys_pciconfig_write +150 common getsockname sys_getsockname +151 common inotify_init sys_inotify_init +152 common inotify_add_watch sys_inotify_add_watch +153 common poll sys_poll +154 common getdents64 sys_getdents64 +155 32 fcntl64 sys_fcntl64 compat_sys_fcntl64 +156 common inotify_rm_watch sys_inotify_rm_watch +157 common statfs sys_statfs compat_sys_statfs +158 common fstatfs sys_fstatfs compat_sys_fstatfs +159 common umount sys_oldumount +160 common sched_set_affinity sys_sched_setaffinity compat_sys_sched_setaffinity +161 common sched_get_affinity sys_sched_getaffinity compat_sys_sched_getaffinity +162 common getdomainname sys_getdomainname +163 common setdomainname sys_setdomainname +164 64 utrap_install sys_utrap_install +165 common quotactl sys_quotactl +166 common set_tid_address sys_set_tid_address +167 common mount sys_mount +168 common ustat sys_ustat compat_sys_ustat +169 common setxattr sys_setxattr +170 common lsetxattr sys_lsetxattr +171 common fsetxattr sys_fsetxattr +172 common getxattr sys_getxattr +173 common lgetxattr sys_lgetxattr +174 common getdents sys_getdents compat_sys_getdents +175 common setsid sys_setsid +176 common fchdir sys_fchdir +177 common fgetxattr sys_fgetxattr +178 common listxattr sys_listxattr +179 common llistxattr sys_llistxattr +180 common flistxattr sys_flistxattr +181 common removexattr sys_removexattr +182 common lremovexattr sys_lremovexattr +183 32 sigpending sys_sigpending compat_sys_sigpending +183 64 sigpending sys_nis_syscall +184 common query_module sys_ni_syscall +185 common setpgid sys_setpgid +186 common fremovexattr sys_fremovexattr +187 common tkill sys_tkill +188 32 exit_group sys_exit_group sparc_exit_group +188 64 exit_group sparc_exit_group +189 common uname sys_newuname +190 common init_module sys_init_module +191 32 personality sys_personality sys_sparc64_personality +191 64 personality sys_sparc64_personality +192 32 remap_file_pages sys_sparc_remap_file_pages sys_remap_file_pages +192 64 remap_file_pages sys_remap_file_pages +193 common epoll_create sys_epoll_create +194 common epoll_ctl sys_epoll_ctl +195 common epoll_wait sys_epoll_wait +196 common ioprio_set sys_ioprio_set +197 common getppid sys_getppid +198 32 sigaction sys_sparc_sigaction compat_sys_sparc_sigaction +198 64 sigaction sys_nis_syscall +199 common sgetmask sys_sgetmask +200 common ssetmask sys_ssetmask +201 32 sigsuspend sys_sigsuspend +201 64 sigsuspend sys_nis_syscall +202 common oldlstat sys_newlstat compat_sys_newlstat +203 common uselib sys_uselib +204 32 readdir sys_old_readdir compat_sys_old_readdir +204 64 readdir sys_nis_syscall +205 common readahead sys_readahead compat_sys_readahead +206 common socketcall sys_socketcall compat_sys_socketcall +207 common syslog sys_syslog +208 common lookup_dcookie sys_ni_syscall +209 common fadvise64 sys_fadvise64 compat_sys_fadvise64 +210 common fadvise64_64 sys_fadvise64_64 compat_sys_fadvise64_64 +211 common tgkill sys_tgkill +212 common waitpid sys_waitpid +213 common swapoff sys_swapoff +214 common sysinfo sys_sysinfo compat_sys_sysinfo +215 32 ipc sys_ipc compat_sys_ipc +215 64 ipc sys_sparc_ipc +216 32 sigreturn sys_sigreturn sys32_sigreturn +216 64 sigreturn sys_nis_syscall +217 common clone sys_clone +218 common ioprio_get sys_ioprio_get +219 32 adjtimex sys_adjtimex_time32 +219 64 adjtimex sys_sparc_adjtimex +220 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask +220 64 sigprocmask sys_nis_syscall +221 common create_module sys_ni_syscall +222 common delete_module sys_delete_module +223 common get_kernel_syms sys_ni_syscall +224 common getpgid sys_getpgid +225 common bdflush sys_ni_syscall +226 common sysfs sys_sysfs +227 common afs_syscall sys_nis_syscall +228 common setfsuid sys_setfsuid16 +229 common setfsgid sys_setfsgid16 +230 common _newselect sys_select compat_sys_select +231 32 time sys_time32 +232 common splice sys_splice +233 32 stime sys_stime32 +233 64 stime sys_stime +234 common statfs64 sys_statfs64 compat_sys_statfs64 +235 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +236 common _llseek sys_llseek +237 common mlock sys_mlock +238 common munlock sys_munlock +239 common mlockall sys_mlockall +240 common munlockall sys_munlockall +241 common sched_setparam sys_sched_setparam +242 common sched_getparam sys_sched_getparam +243 common sched_setscheduler sys_sched_setscheduler +244 common sched_getscheduler sys_sched_getscheduler +245 common sched_yield sys_sched_yield +246 common sched_get_priority_max sys_sched_get_priority_max +247 common sched_get_priority_min sys_sched_get_priority_min +248 32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +248 64 sched_rr_get_interval sys_sched_rr_get_interval +249 32 nanosleep sys_nanosleep_time32 +249 64 nanosleep sys_nanosleep +250 32 mremap sys_mremap +250 64 mremap sys_64_mremap +251 common _sysctl sys_ni_syscall +252 common getsid sys_getsid +253 common fdatasync sys_fdatasync +254 32 nfsservctl sys_ni_syscall sys_nis_syscall +254 64 nfsservctl sys_nis_syscall +255 common sync_file_range sys_sync_file_range compat_sys_sync_file_range +256 32 clock_settime sys_clock_settime32 +256 64 clock_settime sys_clock_settime +257 32 clock_gettime sys_clock_gettime32 +257 64 clock_gettime sys_clock_gettime +258 32 clock_getres sys_clock_getres_time32 +258 64 clock_getres sys_clock_getres +259 32 clock_nanosleep sys_clock_nanosleep_time32 +259 64 clock_nanosleep sys_clock_nanosleep +260 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +261 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +262 32 timer_settime sys_timer_settime32 +262 64 timer_settime sys_timer_settime +263 32 timer_gettime sys_timer_gettime32 +263 64 timer_gettime sys_timer_gettime +264 common timer_getoverrun sys_timer_getoverrun +265 common timer_delete sys_timer_delete +266 common timer_create sys_timer_create compat_sys_timer_create +# 267 was vserver +267 common vserver sys_nis_syscall +268 common io_setup sys_io_setup compat_sys_io_setup +269 common io_destroy sys_io_destroy +270 common io_submit sys_io_submit compat_sys_io_submit +271 common io_cancel sys_io_cancel +272 32 io_getevents sys_io_getevents_time32 +272 64 io_getevents sys_io_getevents +273 common mq_open sys_mq_open compat_sys_mq_open +274 common mq_unlink sys_mq_unlink +275 32 mq_timedsend sys_mq_timedsend_time32 +275 64 mq_timedsend sys_mq_timedsend +276 32 mq_timedreceive sys_mq_timedreceive_time32 +276 64 mq_timedreceive sys_mq_timedreceive +277 common mq_notify sys_mq_notify compat_sys_mq_notify +278 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +279 common waitid sys_waitid compat_sys_waitid +280 common tee sys_tee +281 common add_key sys_add_key +282 common request_key sys_request_key +283 common keyctl sys_keyctl compat_sys_keyctl +284 common openat sys_openat compat_sys_openat +285 common mkdirat sys_mkdirat +286 common mknodat sys_mknodat +287 common fchownat sys_fchownat +288 32 futimesat sys_futimesat_time32 +288 64 futimesat sys_futimesat +289 common fstatat64 sys_fstatat64 compat_sys_fstatat64 +290 common unlinkat sys_unlinkat +291 common renameat sys_renameat +292 common linkat sys_linkat +293 common symlinkat sys_symlinkat +294 common readlinkat sys_readlinkat +295 common fchmodat sys_fchmodat +296 common faccessat sys_faccessat +297 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +297 64 pselect6 sys_pselect6 +298 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +298 64 ppoll sys_ppoll +299 common unshare sys_unshare +300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +301 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +302 common migrate_pages sys_migrate_pages +303 common mbind sys_mbind +304 common get_mempolicy sys_get_mempolicy +305 common set_mempolicy sys_set_mempolicy +306 common kexec_load sys_kexec_load compat_sys_kexec_load +307 common move_pages sys_move_pages +308 common getcpu sys_getcpu +309 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +310 32 utimensat sys_utimensat_time32 +310 64 utimensat sys_utimensat +311 common signalfd sys_signalfd compat_sys_signalfd +312 common timerfd_create sys_timerfd_create +313 common eventfd sys_eventfd +314 common fallocate sys_fallocate compat_sys_fallocate +315 32 timerfd_settime sys_timerfd_settime32 +315 64 timerfd_settime sys_timerfd_settime +316 32 timerfd_gettime sys_timerfd_gettime32 +316 64 timerfd_gettime sys_timerfd_gettime +317 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +318 common eventfd2 sys_eventfd2 +319 common epoll_create1 sys_epoll_create1 +320 common dup3 sys_dup3 +321 common pipe2 sys_pipe2 +322 common inotify_init1 sys_inotify_init1 +323 common accept4 sys_accept4 +324 common preadv sys_preadv compat_sys_preadv +325 common pwritev sys_pwritev compat_sys_pwritev +326 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +327 common perf_event_open sys_perf_event_open +328 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +328 64 recvmmsg sys_recvmmsg +329 common fanotify_init sys_fanotify_init +330 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +331 common prlimit64 sys_prlimit64 +332 common name_to_handle_at sys_name_to_handle_at +333 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +334 32 clock_adjtime sys_clock_adjtime32 +334 64 clock_adjtime sys_sparc_clock_adjtime +335 common syncfs sys_syncfs +336 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +337 common setns sys_setns +338 common process_vm_readv sys_process_vm_readv +339 common process_vm_writev sys_process_vm_writev +340 32 kern_features sys_ni_syscall sys_kern_features +340 64 kern_features sys_kern_features +341 common kcmp sys_kcmp +342 common finit_module sys_finit_module +343 common sched_setattr sys_sched_setattr +344 common sched_getattr sys_sched_getattr +345 common renameat2 sys_renameat2 +346 common seccomp sys_seccomp +347 common getrandom sys_getrandom +348 common memfd_create sys_memfd_create +349 common bpf sys_bpf +350 32 execveat sys_execveat sys32_execveat +350 64 execveat sys64_execveat +351 common membarrier sys_membarrier +352 common userfaultfd sys_userfaultfd +353 common bind sys_bind +354 common listen sys_listen +355 common setsockopt sys_setsockopt sys_setsockopt +356 common mlock2 sys_mlock2 +357 common copy_file_range sys_copy_file_range +358 common preadv2 sys_preadv2 compat_sys_preadv2 +359 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +360 common statx sys_statx +361 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +361 64 io_pgetevents sys_io_pgetevents +362 common pkey_mprotect sys_pkey_mprotect +363 common pkey_alloc sys_pkey_alloc +364 common pkey_free sys_pkey_free +365 common rseq sys_rseq +# room for arch specific syscalls +392 64 semtimedop sys_semtimedop +393 common semget sys_semget +394 common semctl sys_semctl compat_sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl compat_sys_shmctl +397 common shmat sys_shmat compat_sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd compat_sys_msgsnd +401 common msgrcv sys_msgrcv compat_sys_msgrcv +402 common msgctl sys_msgctl compat_sys_msgctl +403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 32 clock_settime64 sys_clock_settime sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 32 timer_settime64 sys_timer_settime sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +# 435 reserved for clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/sparc/include/syscall_table.h b/tools/perf/arch/sparc/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/sparc/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/x86/Build b/tools/perf/arch/x86/Build index 87d057491343..02a1ca780a20 100644 --- a/tools/perf/arch/x86/Build +++ b/tools/perf/arch/x86/Build @@ -2,7 +2,6 @@ perf-util-y += util/ perf-test-y += tests/ ifdef SHELLCHECK - SHELL_TESTS := entry/syscalls/syscalltbl.sh TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) else SHELL_TESTS := diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index a6b6e0a9308a..a295a80ea078 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -1,28 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_JITDUMP := 1 - -### -# Syscall table generation -# - -generated := $(OUTPUT)arch/x86/include/generated -out := $(generated)/asm -header := $(out)/syscalls_64.c -header_32 := $(out)/syscalls_32.c -sys := $(srctree)/tools/perf/arch/x86/entry/syscalls -systbl := $(sys)/syscalltbl.sh - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sys)/syscall_64.tbl $(systbl) - $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ - -$(header_32): $(sys)/syscall_32.tbl $(systbl) - $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_32.tbl 'x86' > $@ - -clean:: - $(call QUIET_CLEAN, x86) $(RM) -r $(header) $(generated) - -archheaders: $(header) $(header_32) diff --git a/tools/perf/arch/x86/entry/syscalls/Kbuild b/tools/perf/arch/x86/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/x86/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/x86/entry/syscalls/Makefile.syscalls b/tools/perf/arch/x86/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..db3d5d6d4e56 --- /dev/null +++ b/tools/perf/arch/x86/entry/syscalls/Makefile.syscalls @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += i386 +syscall_abis_64 += + +syscalltbl = $(srctree)/tools/perf/arch/x86/entry/syscalls/syscall_%.tbl diff --git a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh deleted file mode 100755 index 2b71f99933a5..000000000000 --- a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh +++ /dev/null @@ -1,42 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -in="$1" -arch="$2" - -syscall_macro() { - nr="$1" - name="$2" - - echo " [$nr] = \"$name\"," -} - -emit() { - nr="$1" - entry="$2" - - syscall_macro "$nr" "$entry" -} - -echo "static const char *const syscalltbl_${arch}[] = {" - -sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX) -grep '^[0-9]' "$in" | sort -n > $sorted_table - -max_nr=0 -# the params are: nr abi name entry compat -# use _ for intentionally unused variables according to SC2034 -while read nr _ name _ _; do - if [ $nr -ge 512 ] ; then # discard compat sycalls - break - fi - - emit "$nr" "$name" - max_nr=$nr -done < $sorted_table - -rm -f $sorted_table - -echo "};" - -echo "#define SYSCALLTBL_${arch}_MAX_ID ${max_nr}" diff --git a/tools/perf/arch/x86/include/syscall_table.h b/tools/perf/arch/x86/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/x86/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 848327378694..06d7c0205b3d 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -15,6 +15,6 @@ perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-util-$(CONFIG_AUXTRACE) += auxtrace.o -perf-util-$(CONFIG_AUXTRACE) += archinsn.o +perf-util-y += archinsn.o perf-util-$(CONFIG_AUXTRACE) += intel-pt.o perf-util-$(CONFIG_AUXTRACE) += intel-bts.o diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index 366b44d0bb7e..00f645a0c18a 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -403,6 +403,10 @@ void iostat_prefix(struct evlist *evlist, struct iio_root_port *rp = evlist->selected->priv; if (rp) { + /* + * TODO: This is the incorrect format in JSON mode. + * See prepare_timestamp() + */ if (ts) sprintf(prefix, "%6lu.%09lu%s%04x:%02x%s", ts->tv_sec, ts->tv_nsec, diff --git a/tools/perf/arch/xtensa/entry/syscalls/Kbuild b/tools/perf/arch/xtensa/entry/syscalls/Kbuild new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/xtensa/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/xtensa/entry/syscalls/Makefile.syscalls b/tools/perf/arch/xtensa/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..d4aa2358460c --- /dev/null +++ b/tools/perf/arch/xtensa/entry/syscalls/Makefile.syscalls @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscalltbl = $(srctree)/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..37effc1b134e --- /dev/null +++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl @@ -0,0 +1,439 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for xtensa +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The <abi> is always "common" for this file +# +0 common spill sys_ni_syscall +1 common xtensa sys_ni_syscall +2 common available4 sys_ni_syscall +3 common available5 sys_ni_syscall +4 common available6 sys_ni_syscall +5 common available7 sys_ni_syscall +6 common available8 sys_ni_syscall +7 common available9 sys_ni_syscall +# File Operations +8 common open sys_open +9 common close sys_close +10 common dup sys_dup +11 common dup2 sys_dup2 +12 common read sys_read +13 common write sys_write +14 common select sys_select +15 common lseek sys_lseek +16 common poll sys_poll +17 common _llseek sys_llseek +18 common epoll_wait sys_epoll_wait +19 common epoll_ctl sys_epoll_ctl +20 common epoll_create sys_epoll_create +21 common creat sys_creat +22 common truncate sys_truncate +23 common ftruncate sys_ftruncate +24 common readv sys_readv +25 common writev sys_writev +26 common fsync sys_fsync +27 common fdatasync sys_fdatasync +28 common truncate64 sys_truncate64 +29 common ftruncate64 sys_ftruncate64 +30 common pread64 sys_pread64 +31 common pwrite64 sys_pwrite64 +32 common link sys_link +33 common rename sys_rename +34 common symlink sys_symlink +35 common readlink sys_readlink +36 common mknod sys_mknod +37 common pipe sys_pipe +38 common unlink sys_unlink +39 common rmdir sys_rmdir +40 common mkdir sys_mkdir +41 common chdir sys_chdir +42 common fchdir sys_fchdir +43 common getcwd sys_getcwd +44 common chmod sys_chmod +45 common chown sys_chown +46 common stat sys_newstat +47 common stat64 sys_stat64 +48 common lchown sys_lchown +49 common lstat sys_newlstat +50 common lstat64 sys_lstat64 +51 common available51 sys_ni_syscall +52 common fchmod sys_fchmod +53 common fchown sys_fchown +54 common fstat sys_newfstat +55 common fstat64 sys_fstat64 +56 common flock sys_flock +57 common access sys_access +58 common umask sys_umask +59 common getdents sys_getdents +60 common getdents64 sys_getdents64 +61 common fcntl64 sys_fcntl64 +62 common fallocate sys_fallocate +63 common fadvise64_64 xtensa_fadvise64_64 +64 common utime sys_utime32 +65 common utimes sys_utimes_time32 +66 common ioctl sys_ioctl +67 common fcntl sys_fcntl +68 common setxattr sys_setxattr +69 common getxattr sys_getxattr +70 common listxattr sys_listxattr +71 common removexattr sys_removexattr +72 common lsetxattr sys_lsetxattr +73 common lgetxattr sys_lgetxattr +74 common llistxattr sys_llistxattr +75 common lremovexattr sys_lremovexattr +76 common fsetxattr sys_fsetxattr +77 common fgetxattr sys_fgetxattr +78 common flistxattr sys_flistxattr +79 common fremovexattr sys_fremovexattr +# File Map / Shared Memory Operations +80 common mmap2 sys_mmap_pgoff +81 common munmap sys_munmap +82 common mprotect sys_mprotect +83 common brk sys_brk +84 common mlock sys_mlock +85 common munlock sys_munlock +86 common mlockall sys_mlockall +87 common munlockall sys_munlockall +88 common mremap sys_mremap +89 common msync sys_msync +90 common mincore sys_mincore +91 common madvise sys_madvise +92 common shmget sys_shmget +93 common shmat xtensa_shmat +94 common shmctl sys_old_shmctl +95 common shmdt sys_shmdt +# Socket Operations +96 common socket sys_socket +97 common setsockopt sys_setsockopt +98 common getsockopt sys_getsockopt +99 common shutdown sys_shutdown +100 common bind sys_bind +101 common connect sys_connect +102 common listen sys_listen +103 common accept sys_accept +104 common getsockname sys_getsockname +105 common getpeername sys_getpeername +106 common sendmsg sys_sendmsg +107 common recvmsg sys_recvmsg +108 common send sys_send +109 common recv sys_recv +110 common sendto sys_sendto +111 common recvfrom sys_recvfrom +112 common socketpair sys_socketpair +113 common sendfile sys_sendfile +114 common sendfile64 sys_sendfile64 +115 common sendmmsg sys_sendmmsg +# Process Operations +116 common clone sys_clone +117 common execve sys_execve +118 common exit sys_exit +119 common exit_group sys_exit_group +120 common getpid sys_getpid +121 common wait4 sys_wait4 +122 common waitid sys_waitid +123 common kill sys_kill +124 common tkill sys_tkill +125 common tgkill sys_tgkill +126 common set_tid_address sys_set_tid_address +127 common gettid sys_gettid +128 common setsid sys_setsid +129 common getsid sys_getsid +130 common prctl sys_prctl +131 common personality sys_personality +132 common getpriority sys_getpriority +133 common setpriority sys_setpriority +134 common setitimer sys_setitimer +135 common getitimer sys_getitimer +136 common setuid sys_setuid +137 common getuid sys_getuid +138 common setgid sys_setgid +139 common getgid sys_getgid +140 common geteuid sys_geteuid +141 common getegid sys_getegid +142 common setreuid sys_setreuid +143 common setregid sys_setregid +144 common setresuid sys_setresuid +145 common getresuid sys_getresuid +146 common setresgid sys_setresgid +147 common getresgid sys_getresgid +148 common setpgid sys_setpgid +149 common getpgid sys_getpgid +150 common getppid sys_getppid +151 common getpgrp sys_getpgrp +# 152 was set_thread_area +152 common reserved152 sys_ni_syscall +# 153 was get_thread_area +153 common reserved153 sys_ni_syscall +154 common times sys_times +155 common acct sys_acct +156 common sched_setaffinity sys_sched_setaffinity +157 common sched_getaffinity sys_sched_getaffinity +158 common capget sys_capget +159 common capset sys_capset +160 common ptrace sys_ptrace +161 common semtimedop sys_semtimedop_time32 +162 common semget sys_semget +163 common semop sys_semop +164 common semctl sys_old_semctl +165 common available165 sys_ni_syscall +166 common msgget sys_msgget +167 common msgsnd sys_msgsnd +168 common msgrcv sys_msgrcv +169 common msgctl sys_old_msgctl +170 common available170 sys_ni_syscall +# File System +171 common umount2 sys_umount +172 common mount sys_mount +173 common swapon sys_swapon +174 common chroot sys_chroot +175 common pivot_root sys_pivot_root +176 common umount sys_oldumount +177 common swapoff sys_swapoff +178 common sync sys_sync +179 common syncfs sys_syncfs +180 common setfsuid sys_setfsuid +181 common setfsgid sys_setfsgid +182 common sysfs sys_sysfs +183 common ustat sys_ustat +184 common statfs sys_statfs +185 common fstatfs sys_fstatfs +186 common statfs64 sys_statfs64 +187 common fstatfs64 sys_fstatfs64 +# System +188 common setrlimit sys_setrlimit +189 common getrlimit sys_getrlimit +190 common getrusage sys_getrusage +191 common futex sys_futex_time32 +192 common gettimeofday sys_gettimeofday +193 common settimeofday sys_settimeofday +194 common adjtimex sys_adjtimex_time32 +195 common nanosleep sys_nanosleep_time32 +196 common getgroups sys_getgroups +197 common setgroups sys_setgroups +198 common sethostname sys_sethostname +199 common setdomainname sys_setdomainname +200 common syslog sys_syslog +201 common vhangup sys_vhangup +202 common uselib sys_uselib +203 common reboot sys_reboot +204 common quotactl sys_quotactl +# 205 was old nfsservctl +205 common nfsservctl sys_ni_syscall +206 common _sysctl sys_ni_syscall +207 common bdflush sys_ni_syscall +208 common uname sys_newuname +209 common sysinfo sys_sysinfo +210 common init_module sys_init_module +211 common delete_module sys_delete_module +212 common sched_setparam sys_sched_setparam +213 common sched_getparam sys_sched_getparam +214 common sched_setscheduler sys_sched_setscheduler +215 common sched_getscheduler sys_sched_getscheduler +216 common sched_get_priority_max sys_sched_get_priority_max +217 common sched_get_priority_min sys_sched_get_priority_min +218 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +219 common sched_yield sys_sched_yield +222 common available222 sys_ni_syscall +# Signal Handling +223 common restart_syscall sys_restart_syscall +224 common sigaltstack sys_sigaltstack +225 common rt_sigreturn xtensa_rt_sigreturn +226 common rt_sigaction sys_rt_sigaction +227 common rt_sigprocmask sys_rt_sigprocmask +228 common rt_sigpending sys_rt_sigpending +229 common rt_sigtimedwait sys_rt_sigtimedwait_time32 +230 common rt_sigqueueinfo sys_rt_sigqueueinfo +231 common rt_sigsuspend sys_rt_sigsuspend +# Message +232 common mq_open sys_mq_open +233 common mq_unlink sys_mq_unlink +234 common mq_timedsend sys_mq_timedsend_time32 +235 common mq_timedreceive sys_mq_timedreceive_time32 +236 common mq_notify sys_mq_notify +237 common mq_getsetattr sys_mq_getsetattr +238 common available238 sys_ni_syscall +239 common io_setup sys_io_setup +# IO +240 common io_destroy sys_io_destroy +241 common io_submit sys_io_submit +242 common io_getevents sys_io_getevents_time32 +243 common io_cancel sys_io_cancel +244 common clock_settime sys_clock_settime32 +245 common clock_gettime sys_clock_gettime32 +246 common clock_getres sys_clock_getres_time32 +247 common clock_nanosleep sys_clock_nanosleep_time32 +# Timer +248 common timer_create sys_timer_create +249 common timer_delete sys_timer_delete +250 common timer_settime sys_timer_settime32 +251 common timer_gettime sys_timer_gettime32 +252 common timer_getoverrun sys_timer_getoverrun +# System +253 common reserved253 sys_ni_syscall +254 common lookup_dcookie sys_ni_syscall +255 common available255 sys_ni_syscall +256 common add_key sys_add_key +257 common request_key sys_request_key +258 common keyctl sys_keyctl +259 common available259 sys_ni_syscall +260 common readahead sys_readahead +261 common remap_file_pages sys_remap_file_pages +262 common migrate_pages sys_migrate_pages +263 common mbind sys_mbind +264 common get_mempolicy sys_get_mempolicy +265 common set_mempolicy sys_set_mempolicy +266 common unshare sys_unshare +267 common move_pages sys_move_pages +268 common splice sys_splice +269 common tee sys_tee +270 common vmsplice sys_vmsplice +271 common available271 sys_ni_syscall +272 common pselect6 sys_pselect6_time32 +273 common ppoll sys_ppoll_time32 +274 common epoll_pwait sys_epoll_pwait +275 common epoll_create1 sys_epoll_create1 +276 common inotify_init sys_inotify_init +277 common inotify_add_watch sys_inotify_add_watch +278 common inotify_rm_watch sys_inotify_rm_watch +279 common inotify_init1 sys_inotify_init1 +280 common getcpu sys_getcpu +281 common kexec_load sys_ni_syscall +282 common ioprio_set sys_ioprio_set +283 common ioprio_get sys_ioprio_get +284 common set_robust_list sys_set_robust_list +285 common get_robust_list sys_get_robust_list +286 common available286 sys_ni_syscall +287 common available287 sys_ni_syscall +# Relative File Operations +288 common openat sys_openat +289 common mkdirat sys_mkdirat +290 common mknodat sys_mknodat +291 common unlinkat sys_unlinkat +292 common renameat sys_renameat +293 common linkat sys_linkat +294 common symlinkat sys_symlinkat +295 common readlinkat sys_readlinkat +296 common utimensat sys_utimensat_time32 +297 common fchownat sys_fchownat +298 common futimesat sys_futimesat_time32 +299 common fstatat64 sys_fstatat64 +300 common fchmodat sys_fchmodat +301 common faccessat sys_faccessat +302 common available302 sys_ni_syscall +303 common available303 sys_ni_syscall +304 common signalfd sys_signalfd +# 305 was timerfd +306 common eventfd sys_eventfd +307 common recvmmsg sys_recvmmsg_time32 +308 common setns sys_setns +309 common signalfd4 sys_signalfd4 +310 common dup3 sys_dup3 +311 common pipe2 sys_pipe2 +312 common timerfd_create sys_timerfd_create +313 common timerfd_settime sys_timerfd_settime32 +314 common timerfd_gettime sys_timerfd_gettime32 +315 common available315 sys_ni_syscall +316 common eventfd2 sys_eventfd2 +317 common preadv sys_preadv +318 common pwritev sys_pwritev +319 common available319 sys_ni_syscall +320 common fanotify_init sys_fanotify_init +321 common fanotify_mark sys_fanotify_mark +322 common process_vm_readv sys_process_vm_readv +323 common process_vm_writev sys_process_vm_writev +324 common name_to_handle_at sys_name_to_handle_at +325 common open_by_handle_at sys_open_by_handle_at +326 common sync_file_range2 sys_sync_file_range2 +327 common perf_event_open sys_perf_event_open +328 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +329 common clock_adjtime sys_clock_adjtime32 +330 common prlimit64 sys_prlimit64 +331 common kcmp sys_kcmp +332 common finit_module sys_finit_module +333 common accept4 sys_accept4 +334 common sched_setattr sys_sched_setattr +335 common sched_getattr sys_sched_getattr +336 common renameat2 sys_renameat2 +337 common seccomp sys_seccomp +338 common getrandom sys_getrandom +339 common memfd_create sys_memfd_create +340 common bpf sys_bpf +341 common execveat sys_execveat +342 common userfaultfd sys_userfaultfd +343 common membarrier sys_membarrier +344 common mlock2 sys_mlock2 +345 common copy_file_range sys_copy_file_range +346 common preadv2 sys_preadv2 +347 common pwritev2 sys_pwritev2 +348 common pkey_mprotect sys_pkey_mprotect +349 common pkey_alloc sys_pkey_alloc +350 common pkey_free sys_pkey_free +351 common statx sys_statx +352 common rseq sys_rseq +# 353 through 402 are unassigned to sync up with generic numbers +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/xtensa/include/syscall_table.h b/tools/perf/arch/xtensa/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/xtensa/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index ef5c4257844d..20fe4f72b4af 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -420,7 +420,12 @@ static int cmpworker(const void *p1, const void *p2) struct worker *w1 = (struct worker *) p1; struct worker *w2 = (struct worker *) p2; - return w1->tid > w2->tid; + + if (w1->tid > w2->tid) + return 1; + if (w1->tid < w2->tid) + return -1; + return 0; } int bench_epoll_wait(int argc, const char **argv) diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c index a759eb2328be..f55c07e4be94 100644 --- a/tools/perf/bench/inject-buildid.c +++ b/tools/perf/bench/inject-buildid.c @@ -52,7 +52,7 @@ struct bench_dso { static int nr_dsos; static struct bench_dso *dsos; -extern int cmd_inject(int argc, const char *argv[]); +extern int main(int argc, const char **argv); static const struct option options[] = { OPT_UINTEGER('i', "iterations", &iterations, @@ -294,7 +294,7 @@ static int setup_injection(struct bench_data *data, bool build_id_all) if (data->pid == 0) { const char **inject_argv; - int inject_argc = 2; + int inject_argc = 3; close(data->input_pipe[1]); close(data->output_pipe[0]); @@ -318,15 +318,16 @@ static int setup_injection(struct bench_data *data, bool build_id_all) if (inject_argv == NULL) exit(1); - inject_argv[0] = strdup("inject"); - inject_argv[1] = strdup("-b"); + inject_argv[0] = strdup("perf"); + inject_argv[1] = strdup("inject"); + inject_argv[2] = strdup("-b"); if (build_id_all) - inject_argv[2] = strdup("--buildid-all"); + inject_argv[3] = strdup("--buildid-all"); /* signal that we're ready to go */ close(ready_pipe[1]); - cmd_inject(inject_argc, inject_argv); + main(inject_argc, inject_argv); exit(0); } diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index bb87e6e7687d..836ae0122dab 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -7,6 +7,7 @@ * a histogram of results, along various sorting keys. */ #include "builtin.h" +#include "perf.h" #include "util/color.h" #include <linux/list.h> diff --git a/tools/perf/builtin-check.c b/tools/perf/builtin-check.c index 2346536a5ee1..61a11a9b4e75 100644 --- a/tools/perf/builtin-check.c +++ b/tools/perf/builtin-check.c @@ -31,7 +31,6 @@ struct feature_status supported_features[] = { FEATURE_STATUS("dwarf_getlocations", HAVE_LIBDW_SUPPORT), FEATURE_STATUS("dwarf-unwind", HAVE_DWARF_UNWIND_SUPPORT), FEATURE_STATUS("auxtrace", HAVE_AUXTRACE_SUPPORT), - FEATURE_STATUS("libaudit", HAVE_LIBAUDIT_SUPPORT), FEATURE_STATUS("libbfd", HAVE_LIBBFD_SUPPORT), FEATURE_STATUS("libcapstone", HAVE_LIBCAPSTONE_SUPPORT), FEATURE_STATUS("libcrypto", HAVE_LIBCRYPTO_SUPPORT), @@ -47,7 +46,6 @@ struct feature_status supported_features[] = { FEATURE_STATUS("libunwind", HAVE_LIBUNWIND_SUPPORT), FEATURE_STATUS("lzma", HAVE_LZMA_SUPPORT), FEATURE_STATUS("numa_num_possible_cpus", HAVE_LIBNUMA_SUPPORT), - FEATURE_STATUS("syscall_table", HAVE_SYSCALL_TABLE_SUPPORT), FEATURE_STATUS("zlib", HAVE_ZLIB_SUPPORT), FEATURE_STATUS("zstd", HAVE_ZSTD_SUPPORT), diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index 2e8363778935..45b5312fbe83 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -154,6 +154,44 @@ static int parse_config_arg(char *arg, char **var, char **value) return 0; } +int perf_config__set_variable(const char *var, const char *value) +{ + char path[PATH_MAX]; + char *user_config = mkpath(path, sizeof(path), "%s/.perfconfig", getenv("HOME")); + const char *config_filename; + struct perf_config_set *set; + int ret = -1; + + if (use_system_config) + config_exclusive_filename = perf_etc_perfconfig(); + else if (use_user_config) + config_exclusive_filename = user_config; + + if (!config_exclusive_filename) + config_filename = user_config; + else + config_filename = config_exclusive_filename; + + set = perf_config_set__new(); + if (!set) + goto out_err; + + if (perf_config_set__collect(set, config_filename, var, value) < 0) { + pr_err("Failed to add '%s=%s'\n", var, value); + goto out_err; + } + + if (set_config(set, config_filename) < 0) { + pr_err("Failed to set the configs on %s\n", config_filename); + goto out_err; + } + + ret = 0; +out_err: + perf_config_set__delete(set); + return ret; +} + int cmd_config(int argc, const char **argv) { int i, ret = -1; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 82fb7773e03e..ae490d58af92 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -6,6 +6,7 @@ * DSOs and symbol information, sort them and produce a diff. */ #include "builtin.h" +#include "perf.h" #include "util/debug.h" #include "util/event.h" @@ -1019,12 +1020,12 @@ static int process_base_stream(struct data__file *data_base, continue; es_base = evsel_streams__entry(data_base->evlist_streams, - evsel_base->core.idx); + evsel_base); if (!es_base) return -1; es_pair = evsel_streams__entry(data_pair->evlist_streams, - evsel_pair->core.idx); + evsel_pair); if (!es_pair) return -1; diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index a56cf8b0a7d4..cfd770ec7286 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -43,6 +43,8 @@ static volatile sig_atomic_t workload_exec_errno; static volatile sig_atomic_t done; +static struct stats latency_stats; /* for tracepoints */ + static void sig_handler(int sig __maybe_unused) { done = true; @@ -726,9 +728,11 @@ out: return (done && !workload_exec_errno) ? 0 : -1; } -static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf, - bool use_nsec) +static void make_histogram(struct perf_ftrace *ftrace, int buckets[], + char *buf, size_t len, char *linebuf) { + int min_latency = ftrace->min_latency; + int max_latency = ftrace->max_latency; char *p, *q; char *unit; double num; @@ -774,16 +778,34 @@ static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf, if (!unit || strncmp(unit, " us", 3)) goto next; - if (use_nsec) + if (ftrace->use_nsec) num *= 1000; - i = log2(num); - if (i < 0) - i = 0; + i = 0; + if (num < min_latency) + goto do_inc; + + num -= min_latency; + + if (!ftrace->bucket_range) { + i = log2(num); + if (i < 0) + i = 0; + } else { + // Less than 1 unit (ms or ns), or, in the future, + // than the min latency desired. + if (num > 0) // 1st entry: [ 1 unit .. bucket_range units ] + i = num / ftrace->bucket_range + 1; + if (num >= max_latency - min_latency) + i = NUM_BUCKET -1; + } if (i >= NUM_BUCKET) i = NUM_BUCKET - 1; + num += min_latency; +do_inc: buckets[i]++; + update_stats(&latency_stats, num); next: /* empty the line buffer for the next output */ @@ -794,8 +816,10 @@ next: strcat(linebuf, p); } -static void display_histogram(int buckets[], bool use_nsec) +static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) { + int min_latency = ftrace->min_latency; + bool use_nsec = ftrace->use_nsec; int i; int total = 0; int bar_total = 46; /* to fit in 80 column */ @@ -814,30 +838,74 @@ static void display_histogram(int buckets[], bool use_nsec) " DURATION ", "COUNT", bar_total, "GRAPH"); bar_len = buckets[0] * bar_total / total; - printf(" %4d - %-4d %s | %10d | %.*s%*s |\n", - 0, 1, use_nsec ? "ns" : "us", buckets[0], bar_len, bar, bar_total - bar_len, ""); + + printf(" %4d - %4d %s | %10d | %.*s%*s |\n", + 0, min_latency ?: 1, use_nsec ? "ns" : "us", + buckets[0], bar_len, bar, bar_total - bar_len, ""); for (i = 1; i < NUM_BUCKET - 1; i++) { - int start = (1 << (i - 1)); - int stop = 1 << i; + unsigned int start, stop; const char *unit = use_nsec ? "ns" : "us"; - if (start >= 1024) { - start >>= 10; - stop >>= 10; - unit = use_nsec ? "us" : "ms"; + if (!ftrace->bucket_range) { + start = (1 << (i - 1)); + stop = 1 << i; + + if (start >= 1024) { + start >>= 10; + stop >>= 10; + unit = use_nsec ? "us" : "ms"; + } + } else { + start = (i - 1) * ftrace->bucket_range + min_latency; + stop = i * ftrace->bucket_range + min_latency; + + if (start >= ftrace->max_latency) + break; + if (stop > ftrace->max_latency) + stop = ftrace->max_latency; + + if (start >= 1000) { + double dstart = start / 1000.0, + dstop = stop / 1000.0; + printf(" %4.2f - %-4.2f", dstart, dstop); + unit = use_nsec ? "us" : "ms"; + goto print_bucket_info; + } } + + printf(" %4d - %4d", start, stop); +print_bucket_info: bar_len = buckets[i] * bar_total / total; - printf(" %4d - %-4d %s | %10d | %.*s%*s |\n", - start, stop, unit, buckets[i], bar_len, bar, + printf(" %s | %10d | %.*s%*s |\n", unit, buckets[i], bar_len, bar, bar_total - bar_len, ""); } bar_len = buckets[NUM_BUCKET - 1] * bar_total / total; - printf(" %4d - %-4s %s | %10d | %.*s%*s |\n", - 1, "...", use_nsec ? "ms" : " s", buckets[NUM_BUCKET - 1], + if (!ftrace->bucket_range) { + printf(" %4d - %-4s %s", 1, "...", use_nsec ? "ms" : "s "); + } else { + unsigned int upper_outlier = (NUM_BUCKET - 2) * ftrace->bucket_range + min_latency; + if (upper_outlier > ftrace->max_latency) + upper_outlier = ftrace->max_latency; + + if (upper_outlier >= 1000) { + double dstart = upper_outlier / 1000.0; + + printf(" %4.2f - %-4s %s", dstart, "...", use_nsec ? "us" : "ms"); + } else { + printf(" %4d - %4s %s", upper_outlier, "...", use_nsec ? "ns" : "us"); + } + } + printf(" | %10d | %.*s%*s |\n", buckets[NUM_BUCKET - 1], bar_len, bar, bar_total - bar_len, ""); + printf("\n# statistics (in %s)\n", ftrace->use_nsec ? "nsec" : "usec"); + printf(" total time: %20.0f\n", latency_stats.mean * latency_stats.n); + printf(" avg time: %20.0f\n", latency_stats.mean); + printf(" max time: %20"PRIu64"\n", latency_stats.max); + printf(" min time: %20"PRIu64"\n", latency_stats.min); + printf(" count: %20.0f\n", latency_stats.n); } static int prepare_func_latency(struct perf_ftrace *ftrace) @@ -876,6 +944,8 @@ static int prepare_func_latency(struct perf_ftrace *ftrace) if (fd < 0) pr_err("failed to open trace_pipe\n"); + init_stats(&latency_stats); + put_tracing_file(trace_file); return fd; } @@ -905,7 +975,7 @@ static int stop_func_latency(struct perf_ftrace *ftrace) static int read_func_latency(struct perf_ftrace *ftrace, int buckets[]) { if (ftrace->target.use_bpf) - return perf_ftrace__latency_read_bpf(ftrace, buckets); + return perf_ftrace__latency_read_bpf(ftrace, buckets, &latency_stats); return 0; } @@ -951,7 +1021,7 @@ static int __cmd_latency(struct perf_ftrace *ftrace) if (n < 0) break; - make_histogram(buckets, buf, n, line, ftrace->use_nsec); + make_histogram(ftrace, buckets, buf, n, line); } } @@ -968,12 +1038,12 @@ static int __cmd_latency(struct perf_ftrace *ftrace) int n = read(trace_fd, buf, sizeof(buf) - 1); if (n <= 0) break; - make_histogram(buckets, buf, n, line, ftrace->use_nsec); + make_histogram(ftrace, buckets, buf, n, line); } read_func_latency(ftrace, buckets); - display_histogram(buckets, ftrace->use_nsec); + display_histogram(ftrace, buckets); out: close(trace_fd); @@ -996,6 +1066,7 @@ static int prepare_func_profile(struct perf_ftrace *ftrace) { ftrace->tracer = "function_graph"; ftrace->graph_tail = 1; + ftrace->graph_verbose = 0; ftrace->profile_hash = hashmap__new(profile_hash, profile_equal, NULL); if (ftrace->profile_hash == NULL) @@ -1558,6 +1629,12 @@ int cmd_ftrace(int argc, const char **argv) #endif OPT_BOOLEAN('n', "use-nsec", &ftrace.use_nsec, "Use nano-second histogram"), + OPT_UINTEGER(0, "bucket-range", &ftrace.bucket_range, + "Bucket range in ms or ns (-n/--use-nsec), default is log2() mode"), + OPT_UINTEGER(0, "min-latency", &ftrace.min_latency, + "Minimum latency (1st bucket). Works only with --bucket-range."), + OPT_UINTEGER(0, "max-latency", &ftrace.max_latency, + "Maximum latency (last bucket). Works only with --bucket-range and total buckets less than 22."), OPT_PARENT(common_options), }; const struct option profile_options[] = { @@ -1576,6 +1653,9 @@ int cmd_ftrace(int argc, const char **argv) OPT_CALLBACK('s', "sort", &profile_sort, "key", "Sort result by key: total (default), avg, max, count, name.", parse_sort_key), + OPT_CALLBACK(0, "graph-opts", &ftrace, "options", + "Graph tracer options, available options: nosleep-time,noirqs,thresh=<n>,depth=<n>", + parse_graph_tracer_opts), OPT_PARENT(common_options), }; const struct option *options = ftrace_options; @@ -1653,6 +1733,29 @@ int cmd_ftrace(int argc, const char **argv) ret = -EINVAL; goto out_delete_filters; } + if (!ftrace.bucket_range && ftrace.min_latency) { + pr_err("--min-latency works only with --bucket-range\n"); + parse_options_usage(ftrace_usage, options, + "min-latency", /*short_opt=*/false); + ret = -EINVAL; + goto out_delete_filters; + } + if (ftrace.bucket_range && !ftrace.min_latency) { + /* default min latency should be the bucket range */ + ftrace.min_latency = ftrace.bucket_range; + } + if (!ftrace.bucket_range && ftrace.max_latency) { + pr_err("--max-latency works only with --bucket-range\n"); + parse_options_usage(ftrace_usage, options, + "max-latency", /*short_opt=*/false); + ret = -EINVAL; + goto out_delete_filters; + } + if (ftrace.bucket_range && !ftrace.max_latency) { + /* default max latency should depend on bucket range and num_buckets */ + ftrace.max_latency = (NUM_BUCKET - 2) * ftrace.bucket_range + + ftrace.min_latency; + } cmd_func = __cmd_latency; break; case PERF_FTRACE_PROFILE: diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 0854d3cd9f6a..7be6fb6df595 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -447,9 +447,7 @@ int cmd_help(int argc, const char **argv) #ifdef HAVE_LIBELF_SUPPORT "probe", #endif -#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT) "trace", -#endif NULL }; const char *builtin_help_usage[] = { "perf help [--all] [--man|--web|--info] [command]", diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index d6989195a061..11e49cafa3af 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -2367,10 +2367,10 @@ int cmd_inject(int argc, const char **argv) }; int ret; const char *known_build_ids = NULL; - bool build_ids; - bool build_id_all; - bool mmap2_build_ids; - bool mmap2_build_id_all; + bool build_ids = false; + bool build_id_all = false; + bool mmap2_build_ids = false; + bool mmap2_build_id_all = false; struct option options[] = { OPT_BOOLEAN('b', "build-ids", &build_ids, diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 4d8d94146f8d..67fb1946ef13 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -761,6 +761,7 @@ static int parse_gfp_flags(struct evsel *evsel, struct perf_sample *sample, }; struct trace_seq seq; char *str, *pos = NULL; + const struct tep_event *tp_format; if (nr_gfps) { struct gfp_flag key = { @@ -772,8 +773,9 @@ static int parse_gfp_flags(struct evsel *evsel, struct perf_sample *sample, } trace_seq_init(&seq); - tep_print_event(evsel->tp_format->tep, - &seq, &record, "%s", TEP_PRINT_INFO); + tp_format = evsel__tp_format(evsel); + if (tp_format) + tep_print_event(tp_format->tep, &seq, &record, "%s", TEP_PRINT_INFO); str = strtok_r(seq.buffer, " ", &pos); while (str) { @@ -2012,13 +2014,13 @@ int cmd_kmem(int argc, const char **argv) if (kmem_page) { struct evsel *evsel = evlist__find_tracepoint_by_name(session->evlist, "kmem:mm_page_alloc"); + const struct tep_event *tp_format = evsel ? evsel__tp_format(evsel) : NULL; - if (evsel == NULL) { + if (tp_format == NULL) { pr_err(errmsg, "page", "page"); goto out_delete; } - - kmem_page_size = tep_get_page_size(evsel->tp_format->tep); + kmem_page_size = tep_get_page_size(tp_format->tep); symbol_conf.use_callchain = true; } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 274568d712d1..67fd2b006b0b 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -615,67 +615,6 @@ static const char *get_filename_for_perf_kvm(void) #if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) -void exit_event_get_key(struct evsel *evsel, - struct perf_sample *sample, - struct event_key *key) -{ - key->info = 0; - key->key = evsel__intval(evsel, sample, kvm_exit_reason); -} - -bool kvm_exit_event(struct evsel *evsel) -{ - return evsel__name_is(evsel, kvm_exit_trace); -} - -bool exit_event_begin(struct evsel *evsel, - struct perf_sample *sample, struct event_key *key) -{ - if (kvm_exit_event(evsel)) { - exit_event_get_key(evsel, sample, key); - return true; - } - - return false; -} - -bool kvm_entry_event(struct evsel *evsel) -{ - return evsel__name_is(evsel, kvm_entry_trace); -} - -bool exit_event_end(struct evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) -{ - return kvm_entry_event(evsel); -} - -static const char *get_exit_reason(struct perf_kvm_stat *kvm, - struct exit_reasons_table *tbl, - u64 exit_code) -{ - while (tbl->reason != NULL) { - if (tbl->exit_code == exit_code) - return tbl->reason; - tbl++; - } - - pr_err("unknown kvm exit code:%lld on %s\n", - (unsigned long long)exit_code, kvm->exit_reasons_isa); - return "UNKNOWN"; -} - -void exit_event_decode_key(struct perf_kvm_stat *kvm, - struct event_key *key, - char *decode) -{ - const char *exit_reason = get_exit_reason(kvm, key->exit_reasons, - key->key); - - scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", exit_reason); -} - static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) { struct kvm_reg_events_ops *events_ops = kvm_reg_events_ops; diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c index 8234410cba4c..c41a68d073de 100644 --- a/tools/perf/builtin-kwork.c +++ b/tools/perf/builtin-kwork.c @@ -6,6 +6,7 @@ */ #include "builtin.h" +#include "perf.h" #include "util/data.h" #include "util/evlist.h" @@ -1103,7 +1104,8 @@ static char *evsel__softirq_name(struct evsel *evsel, u64 num) char *name = NULL; bool found = false; struct tep_print_flag_sym *sym = NULL; - struct tep_print_arg *args = evsel->tp_format->print_fmt.args; + const struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_print_arg *args = tp_format ? tp_format->print_fmt.args : NULL; if ((args == NULL) || (args->next == NULL)) return NULL; @@ -1846,7 +1848,7 @@ static void process_skipped_events(struct perf_kwork *kwork, } } -struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork, +static struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork, struct kwork_class *class, struct kwork_work *key) { @@ -2344,6 +2346,7 @@ int cmd_kwork(int argc, const char **argv) .all_runtime = 0, .all_count = 0, .nr_skipped_events = { 0 }, + .add_work = perf_kwork_add_work, }; static const char default_report_sort_order[] = "runtime, max, count"; static const char default_latency_sort_order[] = "avg, max, count"; diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 062e2b56a2ab..5d405cd8e696 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -46,15 +46,6 @@ static struct perf_session *session; static struct target target; -/* based on kernel/lockdep.c */ -#define LOCKHASH_BITS 12 -#define LOCKHASH_SIZE (1UL << LOCKHASH_BITS) - -static struct hlist_head *lockhash_table; - -#define __lockhashfn(key) hash_long((unsigned long)key, LOCKHASH_BITS) -#define lockhashentry(key) (lockhash_table + __lockhashfn((key))) - static struct rb_root thread_stats; static bool combine_locks; @@ -67,24 +58,13 @@ static unsigned long bpf_map_entries = MAX_ENTRIES; static int max_stack_depth = CONTENTION_STACK_DEPTH; static int stack_skip = CONTENTION_STACK_SKIP; static int print_nr_entries = INT_MAX / 2; -static LIST_HEAD(callstack_filters); static const char *output_name = NULL; static FILE *lock_output; -struct callstack_filter { - struct list_head list; - char name[]; -}; - static struct lock_filter filters; static enum lock_aggr_mode aggr_mode = LOCK_AGGR_ADDR; -static bool needs_callstack(void) -{ - return !list_empty(&callstack_filters); -} - static struct thread_stat *thread_stat_find(u32 tid) { struct rb_node *node; @@ -477,93 +457,6 @@ static struct lock_stat *pop_from_result(void) return container_of(node, struct lock_stat, rb); } -struct lock_stat *lock_stat_find(u64 addr) -{ - struct hlist_head *entry = lockhashentry(addr); - struct lock_stat *ret; - - hlist_for_each_entry(ret, entry, hash_entry) { - if (ret->addr == addr) - return ret; - } - return NULL; -} - -struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags) -{ - struct hlist_head *entry = lockhashentry(addr); - struct lock_stat *ret, *new; - - hlist_for_each_entry(ret, entry, hash_entry) { - if (ret->addr == addr) - return ret; - } - - new = zalloc(sizeof(struct lock_stat)); - if (!new) - goto alloc_failed; - - new->addr = addr; - new->name = strdup(name); - if (!new->name) { - free(new); - goto alloc_failed; - } - - new->flags = flags; - new->wait_time_min = ULLONG_MAX; - - hlist_add_head(&new->hash_entry, entry); - return new; - -alloc_failed: - pr_err("memory allocation failed\n"); - return NULL; -} - -bool match_callstack_filter(struct machine *machine, u64 *callstack) -{ - struct map *kmap; - struct symbol *sym; - u64 ip; - const char *arch = perf_env__arch(machine->env); - - if (list_empty(&callstack_filters)) - return true; - - for (int i = 0; i < max_stack_depth; i++) { - struct callstack_filter *filter; - - /* - * In powerpc, the callchain saved by kernel always includes - * first three entries as the NIP (next instruction pointer), - * LR (link register), and the contents of LR save area in the - * second stack frame. In certain scenarios its possible to have - * invalid kernel instruction addresses in either LR or the second - * stack frame's LR. In that case, kernel will store that address as - * zero. - * - * The below check will continue to look into callstack, - * incase first or second callstack index entry has 0 - * address for powerpc. - */ - if (!callstack || (!callstack[i] && (strcmp(arch, "powerpc") || - (i != 1 && i != 2)))) - break; - - ip = callstack[i]; - sym = machine__find_kernel_symbol(machine, ip, &kmap); - if (sym == NULL) - continue; - - list_for_each_entry(filter, &callstack_filters, list) { - if (strstr(sym->name, filter->name)) - return true; - } - } - return false; -} - struct trace_lock_handler { /* it's used on CONFIG_LOCKDEP */ int (*acquire_event)(struct evsel *evsel, @@ -1165,7 +1058,7 @@ static int report_lock_contention_begin_event(struct evsel *evsel, if (callstack == NULL) return -ENOMEM; - if (!match_callstack_filter(machine, callstack)) { + if (!match_callstack_filter(machine, callstack, max_stack_depth)) { free(callstack); return 0; } @@ -1575,8 +1468,13 @@ static void sort_result(void) static const struct { unsigned int flags; - const char *str; - const char *name; + /* + * Name of the lock flags (access), with delimeter ':'. + * For example, rwsem:R of rwsem:W. + */ + const char *flags_name; + /* Name of the lock (type), for example, rwlock or rwsem. */ + const char *lock_name; } lock_type_table[] = { { 0, "semaphore", "semaphore" }, { LCB_F_SPIN, "spinlock", "spinlock" }, @@ -1591,45 +1489,32 @@ static const struct { { LCB_F_PERCPU | LCB_F_WRITE, "pcpu-sem:W", "percpu-rwsem" }, { LCB_F_MUTEX, "mutex", "mutex" }, { LCB_F_MUTEX | LCB_F_SPIN, "mutex", "mutex" }, - /* alias for get_type_flag() */ - { LCB_F_MUTEX | LCB_F_SPIN, "mutex-spin", "mutex" }, + /* alias for optimistic spinning only */ + { LCB_F_MUTEX | LCB_F_SPIN, "mutex:spin", "mutex-spin" }, }; -static const char *get_type_str(unsigned int flags) +static const char *get_type_flags_name(unsigned int flags) { - flags &= LCB_F_MAX_FLAGS - 1; + flags &= LCB_F_TYPE_MASK; for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { if (lock_type_table[i].flags == flags) - return lock_type_table[i].str; + return lock_type_table[i].flags_name; } return "unknown"; } -static const char *get_type_name(unsigned int flags) +static const char *get_type_lock_name(unsigned int flags) { - flags &= LCB_F_MAX_FLAGS - 1; + flags &= LCB_F_TYPE_MASK; for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { if (lock_type_table[i].flags == flags) - return lock_type_table[i].name; + return lock_type_table[i].lock_name; } return "unknown"; } -static unsigned int get_type_flag(const char *str) -{ - for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { - if (!strcmp(lock_type_table[i].name, str)) - return lock_type_table[i].flags; - } - for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { - if (!strcmp(lock_type_table[i].str, str)) - return lock_type_table[i].flags; - } - return UINT_MAX; -} - static void lock_filter_finish(void) { zfree(&filters.types); @@ -1646,6 +1531,12 @@ static void lock_filter_finish(void) zfree(&filters.cgrps); filters.nr_cgrps = 0; + + for (int i = 0; i < filters.nr_slabs; i++) + free(filters.slabs[i]); + + zfree(&filters.slabs); + filters.nr_slabs = 0; } static void sort_contention_result(void) @@ -1732,7 +1623,7 @@ static void print_lock_stat_stdio(struct lock_contention *con, struct lock_stat switch (aggr_mode) { case LOCK_AGGR_CALLER: - fprintf(lock_output, " %10s %s\n", get_type_str(st->flags), st->name); + fprintf(lock_output, " %10s %s\n", get_type_flags_name(st->flags), st->name); break; case LOCK_AGGR_TASK: pid = st->addr; @@ -1742,7 +1633,7 @@ static void print_lock_stat_stdio(struct lock_contention *con, struct lock_stat break; case LOCK_AGGR_ADDR: fprintf(lock_output, " %016llx %s (%s)\n", (unsigned long long)st->addr, - st->name, get_type_name(st->flags)); + st->name, get_type_lock_name(st->flags)); break; case LOCK_AGGR_CGROUP: fprintf(lock_output, " %s\n", st->name); @@ -1783,7 +1674,7 @@ static void print_lock_stat_csv(struct lock_contention *con, struct lock_stat *s switch (aggr_mode) { case LOCK_AGGR_CALLER: - fprintf(lock_output, "%s%s %s", get_type_str(st->flags), sep, st->name); + fprintf(lock_output, "%s%s %s", get_type_flags_name(st->flags), sep, st->name); if (verbose <= 0) fprintf(lock_output, "\n"); break; @@ -1795,7 +1686,7 @@ static void print_lock_stat_csv(struct lock_contention *con, struct lock_stat *s break; case LOCK_AGGR_ADDR: fprintf(lock_output, "%llx%s %s%s %s\n", (unsigned long long)st->addr, sep, - st->name, sep, get_type_name(st->flags)); + st->name, sep, get_type_lock_name(st->flags)); break; case LOCK_AGGR_CGROUP: fprintf(lock_output, "%s\n",st->name); @@ -2150,7 +2041,8 @@ static int __cmd_contention(int argc, const char **argv) goto out_delete; } - if (lock_contention_prepare(&con) < 0) { + err = lock_contention_prepare(&con); + if (err < 0) { pr_err("lock contention BPF setup failed\n"); goto out_delete; } @@ -2171,10 +2063,14 @@ static int __cmd_contention(int argc, const char **argv) } } - if (setup_output_field(true, output_fields)) + err = setup_output_field(true, output_fields); + if (err) { + pr_err("Failed to setup output field\n"); goto out_delete; + } - if (select_key(true)) + err = select_key(true); + if (err) goto out_delete; if (symbol_conf.field_sep) { @@ -2350,29 +2246,61 @@ static int parse_lock_type(const struct option *opt __maybe_unused, const char * int unset __maybe_unused) { char *s, *tmp, *tok; - int ret = 0; s = strdup(str); if (s == NULL) return -1; for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - unsigned int flags = get_type_flag(tok); + bool found = false; - if (flags == -1U) { - pr_err("Unknown lock flags: %s\n", tok); - ret = -1; - break; + /* `tok` is a flags name if it contains ':'. */ + if (strchr(tok, ':')) { + for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { + if (!strcmp(lock_type_table[i].flags_name, tok) && + add_lock_type(lock_type_table[i].flags)) { + found = true; + break; + } + } + + if (!found) { + pr_err("Unknown lock flags name: %s\n", tok); + free(s); + return -1; + } + + continue; } - if (!add_lock_type(flags)) { - ret = -1; - break; + /* + * Otherwise `tok` is a lock name. + * Single lock name could contain multiple flags. + * Replace alias `pcpu-sem` with actual name `percpu-rwsem. + */ + if (!strcmp(tok, "pcpu-sem")) + tok = (char *)"percpu-rwsem"; + for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { + if (!strcmp(lock_type_table[i].lock_name, tok)) { + if (add_lock_type(lock_type_table[i].flags)) { + found = true; + } else { + free(s); + return -1; + } + } } + + if (!found) { + pr_err("Unknown lock name: %s\n", tok); + free(s); + return -1; + } + } free(s); - return ret; + return 0; } static bool add_lock_addr(unsigned long addr) @@ -2412,6 +2340,27 @@ static bool add_lock_sym(char *name) return true; } +static bool add_lock_slab(char *name) +{ + char **tmp; + char *sym = strdup(name); + + if (sym == NULL) { + pr_err("Memory allocation failure\n"); + return false; + } + + tmp = realloc(filters.slabs, (filters.nr_slabs + 1) * sizeof(*filters.slabs)); + if (tmp == NULL) { + pr_err("Memory allocation failure\n"); + return false; + } + + tmp[filters.nr_slabs++] = sym; + filters.slabs = tmp; + return true; +} + static int parse_lock_addr(const struct option *opt __maybe_unused, const char *str, int unset __maybe_unused) { @@ -2435,6 +2384,14 @@ static int parse_lock_addr(const struct option *opt __maybe_unused, const char * continue; } + if (*tok == '&') { + if (!add_lock_slab(tok + 1)) { + ret = -1; + break; + } + continue; + } + /* * At this moment, we don't have kernel symbols. Save the symbols * in a separate list and resolve them to addresses later. @@ -2449,34 +2406,6 @@ static int parse_lock_addr(const struct option *opt __maybe_unused, const char * return ret; } -static int parse_call_stack(const struct option *opt __maybe_unused, const char *str, - int unset __maybe_unused) -{ - char *s, *tmp, *tok; - int ret = 0; - - s = strdup(str); - if (s == NULL) - return -1; - - for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - struct callstack_filter *entry; - - entry = malloc(sizeof(*entry) + strlen(tok) + 1); - if (entry == NULL) { - pr_err("Memory allocation failure\n"); - free(s); - return -1; - } - - strcpy(entry->name, tok); - list_add_tail(&entry->list, &callstack_filters); - } - - free(s); - return ret; -} - static int parse_output(const struct option *opt __maybe_unused, const char *str, int unset __maybe_unused) { diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 651188c1d825..99d5e1491a28 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -4,6 +4,7 @@ #include <sys/stat.h> #include <unistd.h> #include "builtin.h" +#include "perf.h" #include <subcmd/parse-options.h> #include "util/auxtrace.h" diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f83252472921..5db1aedf48df 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -860,7 +860,9 @@ static int record__auxtrace_init(struct record *rec) if (err) return err; - auxtrace_regroup_aux_output(rec->evlist); + err = auxtrace_parse_aux_action(rec->evlist); + if (err) + return err; return auxtrace_parse_filters(rec->evlist); } @@ -1748,10 +1750,8 @@ static void record__init_features(struct record *rec) if (rec->no_buildid) perf_header__clear_feat(&session->header, HEADER_BUILD_ID); -#ifdef HAVE_LIBTRACEEVENT if (!have_tracepoints(&rec->evlist->core.entries)) perf_header__clear_feat(&session->header, HEADER_TRACING_DATA); -#endif if (!rec->opts.branch_stack) perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 048c91960ba9..f5fbd670d619 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -348,11 +348,9 @@ static int process_read_event(const struct perf_tool *tool, struct report *rep = container_of(tool, struct report, tool); if (rep->show_threads) { - const char *name = evsel__name(evsel); int err = perf_read_values_add_value(&rep->show_threads_values, event->read.pid, event->read.tid, - evsel->core.idx, - name, + evsel, event->read.value); if (err) @@ -1422,7 +1420,7 @@ int cmd_report(int argc, const char **argv) OPT_STRING(0, "addr2line", &addr2line_path, "path", "addr2line binary to use for line numbers"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, - "Disable symbol demangling"), + "Symbol demangling. Enabled by default, use --no-demangle to disable."), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"), diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 7049c60ebf77..26ece6e9bfd1 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "builtin.h" +#include "perf.h" #include "perf-sys.h" #include "util/cpumap.h" diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9e47905f75a6..33667b534634 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -85,15 +85,12 @@ static bool system_wide; static bool print_flags; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); -static struct perf_stat_config stat_config; static int max_blocks; static bool native_arch; static struct dlfilter *dlfilter; static int dlargc; static char **dlargv; -unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; - enum perf_output_field { PERF_OUTPUT_COMM = 1ULL << 0, PERF_OUTPUT_TID = 1ULL << 1, @@ -224,6 +221,10 @@ enum { OUTPUT_TYPE_MAX }; +// We need to refactor the evsel->priv use in in 'perf script' to allow for +// using that area, that is being used only in some cases. +#define OUTPUT_TYPE_UNSET -1 + /* default set to maintain compatibility with current format */ static struct { bool user_set; @@ -397,6 +398,14 @@ static inline int output_type(unsigned int type) return OUTPUT_TYPE_OTHER; } +static inline int evsel__output_type(struct evsel *evsel) +{ + if (evsel->script_output_type == OUTPUT_TYPE_UNSET) + evsel->script_output_type = output_type(evsel->core.attr.type); + + return evsel->script_output_type; +} + static bool output_set_by_user(void) { int j; @@ -421,13 +430,13 @@ static const char *output_field2str(enum perf_output_field field) return str; } -#define PRINT_FIELD(x) (output[output_type(attr->type)].fields & PERF_OUTPUT_##x) +#define PRINT_FIELD(x) (output[evsel__output_type(evsel)].fields & PERF_OUTPUT_##x) static int evsel__do_check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg, enum perf_output_field field, bool allow_user_set) { struct perf_event_attr *attr = &evsel->core.attr; - int type = output_type(attr->type); + int type = evsel__output_type(evsel); const char *evname; if (attr->sample_type & sample_type) @@ -461,7 +470,6 @@ static int evsel__check_stype(struct evsel *evsel, u64 sample_type, const char * static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) { - struct perf_event_attr *attr = &evsel->core.attr; bool allow_user_set; if (evsel__is_dummy_event(evsel)) @@ -578,9 +586,9 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return 0; } -static void set_print_ip_opts(struct perf_event_attr *attr) +static void evsel__set_print_ip_opts(struct evsel *evsel) { - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) @@ -610,7 +618,7 @@ static struct evsel *find_first_output_type(struct evlist *evlist, evlist__for_each_entry(evlist, evsel) { if (evsel__is_dummy_event(evsel)) continue; - if (output_type(evsel->core.attr.type) == (int)type) + if (evsel__output_type(evsel) == (int)type) return evsel; } return NULL; @@ -652,7 +660,7 @@ static int perf_session__check_output_opt(struct perf_session *session) if (output[j].fields & PERF_OUTPUT_DSOFF) output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(&evsel->core.attr); + evsel__set_print_ip_opts(evsel); tod |= output[j].fields & PERF_OUTPUT_TOD; } @@ -688,7 +696,7 @@ static int perf_session__check_output_opt(struct perf_session *session) output[j].fields |= PERF_OUTPUT_SYM; output[j].fields |= PERF_OUTPUT_SYMOFFSET; output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(&evsel->core.attr); + evsel__set_print_ip_opts(evsel); goto out; } } @@ -792,7 +800,6 @@ static int perf_sample__fprintf_start(struct perf_script *script, struct evsel *evsel, u32 type, FILE *fp) { - struct perf_event_attr *attr = &evsel->core.attr; unsigned long secs; unsigned long long nsecs; int printed = 0; @@ -944,7 +951,7 @@ static int print_bstack_flags(FILE *fp, struct branch_entry *br) static int perf_sample__fprintf_brstack(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); @@ -983,7 +990,7 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); @@ -1021,7 +1028,7 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); @@ -1188,7 +1195,7 @@ out: return ret; } -static int any_dump_insn(struct perf_event_attr *attr __maybe_unused, +static int any_dump_insn(struct evsel *evsel __maybe_unused, struct perf_insn *x, uint64_t ip, u8 *inbuf, int inlen, int *lenp, FILE *fp) @@ -1216,15 +1223,14 @@ static int add_padding(FILE *fp, int printed, int padding) static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, struct perf_insn *x, u8 *inbuf, int len, int insn, FILE *fp, int *total_cycles, - struct perf_event_attr *attr, - struct thread *thread, struct evsel *evsel, + struct thread *thread, u64 br_cntr) { int ilen = 0; int printed = fprintf(fp, "\t%016" PRIx64 "\t", ip); - printed += add_padding(fp, any_dump_insn(attr, x, ip, inbuf, len, &ilen, fp), 30); + printed += add_padding(fp, any_dump_insn(evsel, x, ip, inbuf, len, &ilen, fp), 30); printed += fprintf(fp, "\t"); if (PRINT_FIELD(BRSTACKINSNLEN)) @@ -1280,7 +1286,7 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, static int ip__fprintf_sym(uint64_t addr, struct thread *thread, u8 cpumode, int cpu, struct symbol **lastsym, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct addr_location al; int off, printed = 0, ret = 0; @@ -1356,10 +1362,10 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, machine, thread, &x.is64bit, &x.cpumode, false); if (len > 0) { printed += ip__fprintf_sym(entries[nr - 1].from, thread, - x.cpumode, x.cpu, &lastsym, attr, fp); + x.cpumode, x.cpu, &lastsym, evsel, fp); printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1], &x, buffer, len, 0, fp, &total_cycles, - attr, thread, evsel, br_cntr); + evsel, thread, br_cntr); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, entries[nr - 1].from); } @@ -1387,19 +1393,19 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, for (off = 0; off < (unsigned)len; off += ilen) { uint64_t ip = start + off; - printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); + printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, evsel, fp); if (ip == end) { if (PRINT_FIELD(BRCNTR) && sample->branch_stack_cntr) br_cntr = sample->branch_stack_cntr[i]; printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp, - &total_cycles, attr, thread, evsel, br_cntr); + &total_cycles, evsel, thread, br_cntr); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, ip); break; } else { ilen = 0; printed += fprintf(fp, "\t%016" PRIx64 "\t", ip); - printed += any_dump_insn(attr, &x, ip, buffer + off, len - off, &ilen, fp); + printed += any_dump_insn(evsel, &x, ip, buffer + off, len - off, &ilen, fp); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "\tilen: %d", ilen); printed += fprintf(fp, "\n"); @@ -1438,7 +1444,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, end = start + 128; } len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true); - printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp); + printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, evsel, fp); if (len <= 0) { /* Print at least last IP if basic block did not work */ len = grab_bb(buffer, sample->ip, sample->ip, @@ -1447,7 +1453,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, goto out; ilen = 0; printed += fprintf(fp, "\t%016" PRIx64 "\t", sample->ip); - printed += any_dump_insn(attr, &x, sample->ip, buffer, len, &ilen, fp); + printed += any_dump_insn(evsel, &x, sample->ip, buffer, len, &ilen, fp); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "\tilen: %d", ilen); printed += fprintf(fp, "\n"); @@ -1458,7 +1464,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, for (off = 0; off <= end - start; off += ilen) { ilen = 0; printed += fprintf(fp, "\t%016" PRIx64 "\t", start + off); - printed += any_dump_insn(attr, &x, start + off, buffer + off, len - off, &ilen, fp); + printed += any_dump_insn(evsel, &x, start + off, buffer + off, len - off, &ilen, fp); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "\tilen: %d", ilen); printed += fprintf(fp, "\n"); @@ -1482,13 +1488,13 @@ out: static int perf_sample__fprintf_addr(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct addr_location al; int printed = fprintf(fp, "%16" PRIx64, sample->addr); addr_location__init(&al); - if (!sample_addr_correlates_sym(attr)) + if (!sample_addr_correlates_sym(&evsel->core.attr)) goto out; thread__resolve(thread, &al, sample); @@ -1515,11 +1521,10 @@ static const char *resolve_branch_sym(struct perf_sample *sample, struct addr_location *addr_al, u64 *ip) { - struct perf_event_attr *attr = &evsel->core.attr; const char *name = NULL; if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) { - if (sample_addr_correlates_sym(attr)) { + if (sample_addr_correlates_sym(&evsel->core.attr)) { if (!addr_al->thread) thread__resolve(thread, addr_al, sample); if (addr_al->sym) @@ -1545,7 +1550,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, struct addr_location *addr_al, FILE *fp) { - struct perf_event_attr *attr = &evsel->core.attr; size_t depth = thread_stack__depth(thread, sample->cpu); const char *name = NULL; static int spacing; @@ -1589,19 +1593,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, return len + dlen; } -__weak void arch_fetch_insn(struct perf_sample *sample __maybe_unused, - struct thread *thread __maybe_unused, - struct machine *machine __maybe_unused) -{ -} - -void script_fetch_insn(struct perf_sample *sample, struct thread *thread, - struct machine *machine) -{ - if (sample->insn_len == 0 && native_arch) - arch_fetch_insn(sample, thread, machine); -} - static int perf_sample__fprintf_insn(struct perf_sample *sample, struct evsel *evsel, struct perf_event_attr *attr, @@ -1611,7 +1602,7 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample, { int printed = 0; - script_fetch_insn(sample, thread, machine); + script_fetch_insn(sample, thread, machine, native_arch); if (PRINT_FIELD(INSNLEN)) printed += fprintf(fp, " ilen: %d", sample->insn_len); @@ -1630,7 +1621,7 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample, } static int perf_sample__fprintf_ipc(struct perf_sample *sample, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { unsigned int ipc; @@ -1651,7 +1642,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, struct machine *machine, FILE *fp) { struct perf_event_attr *attr = &evsel->core.attr; - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); bool print_srcline_last = false; int printed = 0; @@ -1688,10 +1679,10 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) && !output[type].user_set)) { printed += fprintf(fp, " => "); - printed += perf_sample__fprintf_addr(sample, thread, attr, fp); + printed += perf_sample__fprintf_addr(sample, thread, evsel, fp); } - printed += perf_sample__fprintf_ipc(sample, attr, fp); + printed += perf_sample__fprintf_ipc(sample, evsel, fp); if (print_srcline_last) printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp); @@ -1709,87 +1700,6 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, return printed; } -static struct { - u32 flags; - const char *name; -} sample_flags[] = { - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"}, - {PERF_IP_FLAG_BRANCH, "jmp"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT, "hw int"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMENTRY, "vmentry"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMEXIT, "vmexit"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_BRANCH_MISS, "br miss"}, - {0, NULL} -}; - -static const char *sample_flags_to_name(u32 flags) -{ - int i; - - for (i = 0; sample_flags[i].name ; i++) { - if (sample_flags[i].flags == flags) - return sample_flags[i].name; - } - - return NULL; -} - -int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz) -{ - u32 xf = PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_INTR_DISABLE | - PERF_IP_FLAG_INTR_TOGGLE; - const char *chars = PERF_IP_FLAG_CHARS; - const size_t n = strlen(PERF_IP_FLAG_CHARS); - const char *name = NULL; - size_t i, pos = 0; - char xs[16] = {0}; - - if (flags & xf) - snprintf(xs, sizeof(xs), "(%s%s%s)", - flags & PERF_IP_FLAG_IN_TX ? "x" : "", - flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", - flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); - - name = sample_flags_to_name(flags & ~xf); - if (name) - return snprintf(str, sz, "%-15s%6s", name, xs); - - if (flags & PERF_IP_FLAG_TRACE_BEGIN) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_BEGIN)); - if (name) - return snprintf(str, sz, "tr strt %-7s%6s", name, xs); - } - - if (flags & PERF_IP_FLAG_TRACE_END) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_END)); - if (name) - return snprintf(str, sz, "tr end %-7s%6s", name, xs); - } - - for (i = 0; i < n; i++, flags >>= 1) { - if ((flags & 1) && pos < sz) - str[pos++] = chars[i]; - } - for (; i < 32; i++, flags >>= 1) { - if ((flags & 1) && pos < sz) - str[pos++] = '?'; - } - if (pos < sz) - str[pos] = 0; - - return pos; -} - static int perf_sample__fprintf_flags(u32 flags, FILE *fp) { char str[SAMPLE_FLAGS_BUF_SIZE]; @@ -2254,7 +2164,7 @@ static void process_event(struct perf_script *script, { struct thread *thread = al->thread; struct perf_event_attr *attr = &evsel->core.attr; - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); struct evsel_script *es = evsel->priv; FILE *fp = es->fp; char str[PAGE_SIZE_NAME_LEN]; @@ -2289,15 +2199,20 @@ static void process_event(struct perf_script *script, } #ifdef HAVE_LIBTRACEEVENT if (PRINT_FIELD(TRACE) && sample->raw_data) { - event_format__fprintf(evsel->tp_format, sample->cpu, - sample->raw_data, sample->raw_size, fp); + const struct tep_event *tp_format = evsel__tp_format(evsel); + + if (tp_format) { + event_format__fprintf(tp_format, sample->cpu, + sample->raw_data, sample->raw_size, + fp); + } } #endif if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH)) perf_sample__fprintf_synth(sample, evsel, fp); if (PRINT_FIELD(ADDR)) - perf_sample__fprintf_addr(sample, thread, attr, fp); + perf_sample__fprintf_addr(sample, thread, evsel, fp); if (PRINT_FIELD(DATA_SRC)) data_src__fprintf(sample->data_src, fp); @@ -2347,11 +2262,11 @@ static void process_event(struct perf_script *script, perf_sample__fprintf_uregs(sample, attr, arch, fp); if (PRINT_FIELD(BRSTACK)) - perf_sample__fprintf_brstack(sample, thread, attr, fp); + perf_sample__fprintf_brstack(sample, thread, evsel, fp); else if (PRINT_FIELD(BRSTACKSYM)) - perf_sample__fprintf_brstacksym(sample, thread, attr, fp); + perf_sample__fprintf_brstacksym(sample, thread, evsel, fp); else if (PRINT_FIELD(BRSTACKOFF)) - perf_sample__fprintf_brstackoff(sample, thread, attr, fp); + perf_sample__fprintf_brstackoff(sample, thread, evsel, fp); if (evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT)) perf_sample__fprintf_bpf_output(sample, fp); @@ -2366,7 +2281,7 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(CODE_PAGE_SIZE)) fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str)); - perf_sample__fprintf_ipc(sample, attr, fp); + perf_sample__fprintf_ipc(sample, evsel, fp); fprintf(fp, "\n"); @@ -2599,14 +2514,14 @@ static int process_attr(const struct perf_tool *tool, union perf_event *event, sample_type & PERF_SAMPLE_BRANCH_STACK || (sample_type & PERF_SAMPLE_REGS_USER && sample_type & PERF_SAMPLE_STACK_USER))) { - int type = output_type(evsel->core.attr.type); + int type = evsel__output_type(evsel); if (!(output[type].user_unset_fields & PERF_OUTPUT_IP)) output[type].fields |= PERF_OUTPUT_IP; if (!(output[type].user_unset_fields & PERF_OUTPUT_SYM)) output[type].fields |= PERF_OUTPUT_SYM; } - set_print_ip_opts(&evsel->core.attr); + evsel__set_print_ip_opts(evsel); return 0; } @@ -2959,79 +2874,18 @@ static int __cmd_script(struct perf_script *script) return ret; } -struct script_spec { - struct list_head node; - struct scripting_ops *ops; - char spec[]; -}; - -static LIST_HEAD(script_specs); - -static struct script_spec *script_spec__new(const char *spec, - struct scripting_ops *ops) +static int list_available_languages_cb(struct scripting_ops *ops, const char *spec) { - struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1); - - if (s != NULL) { - strcpy(s->spec, spec); - s->ops = ops; - } - - return s; -} - -static void script_spec__add(struct script_spec *s) -{ - list_add_tail(&s->node, &script_specs); -} - -static struct script_spec *script_spec__find(const char *spec) -{ - struct script_spec *s; - - list_for_each_entry(s, &script_specs, node) - if (strcasecmp(s->spec, spec) == 0) - return s; - return NULL; -} - -int script_spec_register(const char *spec, struct scripting_ops *ops) -{ - struct script_spec *s; - - s = script_spec__find(spec); - if (s) - return -1; - - s = script_spec__new(spec, ops); - if (!s) - return -1; - else - script_spec__add(s); - + fprintf(stderr, " %-42s [%s]\n", spec, ops->name); return 0; } -static struct scripting_ops *script_spec__lookup(const char *spec) -{ - struct script_spec *s = script_spec__find(spec); - if (!s) - return NULL; - - return s->ops; -} - static void list_available_languages(void) { - struct script_spec *s; - fprintf(stderr, "\n"); fprintf(stderr, "Scripting language extensions (used in " "perf script -s [spec:]script.[spec]):\n\n"); - - list_for_each_entry(s, &script_specs, node) - fprintf(stderr, " %-42s [%s]\n", s->spec, s->ops->name); - + script_spec__for_each(&list_available_languages_cb); fprintf(stderr, "\n"); } @@ -3523,144 +3377,6 @@ static void free_dlarg(void) free(dlargv); } -/* - * Some scripts specify the required events in their "xxx-record" file, - * this function will check if the events in perf.data match those - * mentioned in the "xxx-record". - * - * Fixme: All existing "xxx-record" are all in good formats "-e event ", - * which is covered well now. And new parsing code should be added to - * cover the future complex formats like event groups etc. - */ -static int check_ev_match(char *dir_name, char *scriptname, - struct perf_session *session) -{ - char filename[MAXPATHLEN], evname[128]; - char line[BUFSIZ], *p; - struct evsel *pos; - int match, len; - FILE *fp; - - scnprintf(filename, MAXPATHLEN, "%s/bin/%s-record", dir_name, scriptname); - - fp = fopen(filename, "r"); - if (!fp) - return -1; - - while (fgets(line, sizeof(line), fp)) { - p = skip_spaces(line); - if (*p == '#') - continue; - - while (strlen(p)) { - p = strstr(p, "-e"); - if (!p) - break; - - p += 2; - p = skip_spaces(p); - len = strcspn(p, " \t"); - if (!len) - break; - - snprintf(evname, len + 1, "%s", p); - - match = 0; - evlist__for_each_entry(session->evlist, pos) { - if (evsel__name_is(pos, evname)) { - match = 1; - break; - } - } - - if (!match) { - fclose(fp); - return -1; - } - } - } - - fclose(fp); - return 0; -} - -/* - * Return -1 if none is found, otherwise the actual scripts number. - * - * Currently the only user of this function is the script browser, which - * will list all statically runnable scripts, select one, execute it and - * show the output in a perf browser. - */ -int find_scripts(char **scripts_array, char **scripts_path_array, int num, - int pathlen) -{ - struct dirent *script_dirent, *lang_dirent; - char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; - DIR *scripts_dir, *lang_dir; - struct perf_session *session; - struct perf_data data = { - .path = input_name, - .mode = PERF_DATA_MODE_READ, - }; - char *temp; - int i = 0; - - session = perf_session__new(&data, NULL); - if (IS_ERR(session)) - return PTR_ERR(session); - - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); - - scripts_dir = opendir(scripts_path); - if (!scripts_dir) { - perf_session__delete(session); - return -1; - } - - for_each_lang(scripts_path, scripts_dir, lang_dirent) { - scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent->d_name); -#ifndef HAVE_LIBPERL_SUPPORT - if (strstr(lang_path, "perl")) - continue; -#endif -#ifndef HAVE_LIBPYTHON_SUPPORT - if (strstr(lang_path, "python")) - continue; -#endif - - lang_dir = opendir(lang_path); - if (!lang_dir) - continue; - - for_each_script(lang_path, lang_dir, script_dirent) { - /* Skip those real time scripts: xxxtop.p[yl] */ - if (strstr(script_dirent->d_name, "top.")) - continue; - if (i >= num) - break; - snprintf(scripts_path_array[i], pathlen, "%s/%s", - lang_path, - script_dirent->d_name); - temp = strchr(script_dirent->d_name, '.'); - snprintf(scripts_array[i], - (temp - script_dirent->d_name) + 1, - "%s", script_dirent->d_name); - - if (check_ev_match(lang_path, - scripts_array[i], session)) - continue; - - i++; - } - closedir(lang_dir); - } - - closedir(scripts_dir); - perf_session__delete(session); - return i; -} - static char *get_script_path(const char *script_root, const char *suffix) { struct dirent *script_dirent, *lang_dirent; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index fdf5172646a5..77e327d4a9a7 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -112,8 +112,6 @@ static struct target target = { .uid = UINT_MAX, }; -#define METRIC_ONLY_LEN 20 - static volatile sig_atomic_t child_pid = -1; static int detailed_run = 0; static bool transaction_run; @@ -151,21 +149,6 @@ static struct perf_stat perf_stat; static volatile sig_atomic_t done = 0; -static struct perf_stat_config stat_config = { - .aggr_mode = AGGR_GLOBAL, - .aggr_level = MAX_CACHE_LVL + 1, - .scale = true, - .unit_width = 4, /* strlen("unit") */ - .run_count = 1, - .metric_only_len = METRIC_ONLY_LEN, - .walltime_nsecs_stats = &walltime_nsecs_stats, - .ru_stats = &ru_stats, - .big_num = true, - .ctl_fd = -1, - .ctl_fd_ack = -1, - .iostat_run = false, -}; - /* Options set from the command line. */ struct opt_aggr_mode { bool node, socket, die, cluster, cache, core, thread, no_aggr; @@ -1071,16 +1054,6 @@ static void sig_atexit(void) kill(getpid(), signr); } -void perf_stat__set_big_num(int set) -{ - stat_config.big_num = (set != 0); -} - -void perf_stat__set_no_csv_summary(int set) -{ - stat_config.no_csv_summary = (set != 0); -} - static int stat__set_big_num(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset) { diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 724a79386321..4fd31d29b2ab 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -267,9 +267,9 @@ static void perf_top__show_details(struct perf_top *top) if (top->evlist->enabled) { if (top->zero) - symbol__annotate_zero_histogram(symbol, top->sym_evsel->core.idx); + symbol__annotate_zero_histogram(symbol, top->sym_evsel); else - symbol__annotate_decay_histogram(symbol, top->sym_evsel->core.idx); + symbol__annotate_decay_histogram(symbol, top->sym_evsel); } if (more != 0) printf("%d lines not displayed, maybe increase display entries [e]\n", more); @@ -809,7 +809,7 @@ static void perf_event__process_sample(const struct perf_tool *tool, * invalid --vmlinux ;-) */ if (!machine->kptr_restrict_warned && !top->vmlinux_warned && - __map__is_kernel(al.map) && map__has_symbols(al.map)) { + __map__is_kernel(al.map) && !map__has_symbols(al.map)) { if (symbol_conf.vmlinux_name) { char serr[256]; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6a1a128fe645..d466447ae928 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -389,7 +389,12 @@ static struct syscall_arg_fmt *evsel__syscall_arg_fmt(struct evsel *evsel) } if (et->fmt == NULL) { - et->fmt = calloc(evsel->tp_format->format.nr_fields, sizeof(struct syscall_arg_fmt)); + const struct tep_event *tp_format = evsel__tp_format(evsel); + + if (tp_format == NULL) + goto out_delete; + + et->fmt = calloc(tp_format->format.nr_fields, sizeof(struct syscall_arg_fmt)); if (et->fmt == NULL) goto out_delete; } @@ -1108,7 +1113,6 @@ static bool syscall_arg__strtoul_btf_type(char *bf __maybe_unused, size_t size _ .strtoul = STUL_STRARRAY_FLAGS, \ .parm = &strarray__##array, } -#include "trace/beauty/arch_errno_names.c" #include "trace/beauty/eventfd.c" #include "trace/beauty/futex_op.c" #include "trace/beauty/futex_val3.c" @@ -2069,30 +2073,11 @@ static int trace__read_syscall_info(struct trace *trace, int id) const char *name = syscalltbl__name(trace->sctbl, id); int err; -#ifdef HAVE_SYSCALL_TABLE_SUPPORT if (trace->syscalls.table == NULL) { trace->syscalls.table = calloc(trace->sctbl->syscalls.max_id + 1, sizeof(*sc)); if (trace->syscalls.table == NULL) return -ENOMEM; } -#else - if (id > trace->sctbl->syscalls.max_id || (id == 0 && trace->syscalls.table == NULL)) { - // When using libaudit we don't know beforehand what is the max syscall id - struct syscall *table = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc)); - - if (table == NULL) - return -ENOMEM; - - // Need to memset from offset 0 and +1 members if brand new - if (trace->syscalls.table == NULL) - memset(table, 0, (id + 1) * sizeof(*sc)); - else - memset(table + trace->sctbl->syscalls.max_id + 1, 0, (id - trace->sctbl->syscalls.max_id) * sizeof(*sc)); - - trace->syscalls.table = table; - trace->sctbl->syscalls.max_id = id; - } -#endif sc = trace->syscalls.table + id; if (sc->nonexistent) return -EEXIST; @@ -2122,8 +2107,12 @@ static int trace__read_syscall_info(struct trace *trace, int id) return PTR_ERR(sc->tp_format); } + /* + * The tracepoint format contains __syscall_nr field, so it's one more + * than the actual number of syscall arguments. + */ if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? - RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields)) + RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields - 1)) return -ENOMEM; sc->args = sc->tp_format->format.fields; @@ -2154,8 +2143,12 @@ static int evsel__init_tp_arg_scnprintf(struct evsel *evsel, bool *use_btf) struct syscall_arg_fmt *fmt = evsel__syscall_arg_fmt(evsel); if (fmt != NULL) { - syscall_arg_fmt__init_array(fmt, evsel->tp_format->format.fields, use_btf); - return 0; + const struct tep_event *tp_format = evsel__tp_format(evsel); + + if (tp_format) { + syscall_arg_fmt__init_array(fmt, tp_format->format.fields, use_btf); + return 0; + } } return -ENOMEM; @@ -2439,18 +2432,7 @@ static struct syscall *trace__syscall_info(struct trace *trace, err = -EINVAL; -#ifdef HAVE_SYSCALL_TABLE_SUPPORT if (id > trace->sctbl->syscalls.max_id) { -#else - if (id >= trace->sctbl->syscalls.max_id) { - /* - * With libaudit we don't know beforehand what is the max_id, - * so we let trace__read_syscall_info() figure that out as we - * go on reading syscalls. - */ - err = trace__read_syscall_info(trace, id); - if (err) -#endif goto out_cant_read; } @@ -2581,7 +2563,6 @@ static int trace__fprintf_sample(struct trace *trace, struct evsel *evsel, static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, int raw_augmented_args_size) { - void *augmented_args = NULL; /* * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter * and there we get all 6 syscall args plus the tracepoint common fields @@ -2599,10 +2580,24 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam int args_size = raw_augmented_args_size ?: sc->args_size; *augmented_args_size = sample->raw_size - args_size; - if (*augmented_args_size > 0) - augmented_args = sample->raw_data + args_size; + if (*augmented_args_size > 0) { + static uintptr_t argbuf[1024]; /* assuming single-threaded */ - return augmented_args; + if ((size_t)(*augmented_args_size) > sizeof(argbuf)) + return NULL; + + /* + * The perf ring-buffer is 8-byte aligned but sample->raw_data + * is not because it's preceded by u32 size. Later, beautifier + * will use the augmented args with stricter alignments like in + * some struct. To make sure it's aligned, let's copy the args + * into a static buffer as it's single-threaded for now. + */ + memcpy(argbuf, sample->raw_data + args_size, *augmented_args_size); + + return argbuf; + } + return NULL; } static void syscall__exit(struct syscall *sc) @@ -3027,7 +3022,8 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel, { char bf[2048]; size_t size = sizeof(bf); - struct tep_format_field *field = evsel->tp_format->format.fields; + const struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *field = tp_format ? tp_format->format.fields : NULL; struct syscall_arg_fmt *arg = __evsel__syscall_arg_fmt(evsel); size_t printed = 0, btf_printed; unsigned long val; @@ -3145,11 +3141,13 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel, if (evsel__is_bpf_output(evsel)) { bpf_output__fprintf(trace, sample); - } else if (evsel->tp_format) { - if (strncmp(evsel->tp_format->name, "sys_enter_", 10) || - trace__fprintf_sys_enter(trace, evsel, sample)) { + } else { + const struct tep_event *tp_format = evsel__tp_format(evsel); + + if (tp_format && (strncmp(tp_format->name, "sys_enter_", 10) || + trace__fprintf_sys_enter(trace, evsel, sample))) { if (trace->libtraceevent_print) { - event_format__fprintf(evsel->tp_format, sample->cpu, + event_format__fprintf(tp_format, sample->cpu, sample->raw_data, sample->raw_size, trace->output); } else { @@ -4077,17 +4075,23 @@ static int ordered_events__deliver_event(struct ordered_events *oe, static struct syscall_arg_fmt *evsel__find_syscall_arg_fmt_by_name(struct evsel *evsel, char *arg, char **type) { - struct tep_format_field *field; struct syscall_arg_fmt *fmt = __evsel__syscall_arg_fmt(evsel); + const struct tep_event *tp_format; - if (evsel->tp_format == NULL || fmt == NULL) + if (!fmt) return NULL; - for (field = evsel->tp_format->format.fields; field; field = field->next, ++fmt) + tp_format = evsel__tp_format(evsel); + if (!tp_format) + return NULL; + + for (const struct tep_format_field *field = tp_format->format.fields; field; + field = field->next, ++fmt) { if (strcmp(field->name, arg) == 0) { *type = field->type; return fmt; } + } return NULL; } @@ -4843,13 +4847,18 @@ static void evsel__set_syscall_arg_fmt(struct evsel *evsel, const char *name) const struct syscall_fmt *scfmt = syscall_fmt__find(name); if (scfmt) { - int skip = 0; + const struct tep_event *tp_format = evsel__tp_format(evsel); - if (strcmp(evsel->tp_format->format.fields->name, "__syscall_nr") == 0 || - strcmp(evsel->tp_format->format.fields->name, "nr") == 0) - ++skip; + if (tp_format) { + int skip = 0; - memcpy(fmt + skip, scfmt->arg, (evsel->tp_format->format.nr_fields - skip) * sizeof(*fmt)); + if (strcmp(tp_format->format.fields->name, "__syscall_nr") == 0 || + strcmp(tp_format->format.fields->name, "nr") == 0) + ++skip; + + memcpy(fmt + skip, scfmt->arg, + (tp_format->format.nr_fields - skip) * sizeof(*fmt)); + } } } } @@ -4859,10 +4868,16 @@ static int evlist__set_syscall_tp_fields(struct evlist *evlist, bool *use_btf) struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->priv || !evsel->tp_format) + const struct tep_event *tp_format; + + if (evsel->priv) continue; - if (strcmp(evsel->tp_format->system, "syscalls")) { + tp_format = evsel__tp_format(evsel); + if (!tp_format) + continue; + + if (strcmp(tp_format->system, "syscalls")) { evsel__init_tp_arg_scnprintf(evsel, use_btf); continue; } @@ -4870,20 +4885,24 @@ static int evlist__set_syscall_tp_fields(struct evlist *evlist, bool *use_btf) if (evsel__init_syscall_tp(evsel)) return -1; - if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) { + if (!strncmp(tp_format->name, "sys_enter_", 10)) { struct syscall_tp *sc = __evsel__syscall_tp(evsel); if (__tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64))) return -1; - evsel__set_syscall_arg_fmt(evsel, evsel->tp_format->name + sizeof("sys_enter_") - 1); - } else if (!strncmp(evsel->tp_format->name, "sys_exit_", 9)) { + evsel__set_syscall_arg_fmt(evsel, + tp_format->name + sizeof("sys_enter_") - 1); + } else if (!strncmp(tp_format->name, "sys_exit_", 9)) { struct syscall_tp *sc = __evsel__syscall_tp(evsel); - if (__tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap)) + if (__tp_field__init_uint(&sc->ret, sizeof(u64), + sc->id.offset + sizeof(u64), + evsel->needs_swap)) return -1; - evsel__set_syscall_arg_fmt(evsel, evsel->tp_format->name + sizeof("sys_exit_") - 1); + evsel__set_syscall_arg_fmt(evsel, + tp_format->name + sizeof("sys_exit_") - 1); } } diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 94f4b3769bf7..a07e93c53848 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -2,10 +2,6 @@ #ifndef BUILTIN_H #define BUILTIN_H -#include <stddef.h> -#include <linux/compiler.h> -#include <tools/config.h> - struct feature_status { const char *name; const char *macro; @@ -56,6 +52,4 @@ int cmd_ftrace(int argc, const char **argv); int cmd_daemon(int argc, const char **argv); int cmd_kwork(int argc, const char **argv); -int find_scripts(char **scripts_array, char **scripts_path_array, int num, - int pathlen); #endif diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index a05c1c105c51..d3c6e10dce73 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -71,6 +71,7 @@ FILES=( "include/uapi/asm-generic/ioctls.h" "include/uapi/asm-generic/mman-common.h" "include/uapi/asm-generic/unistd.h" + "scripts/syscall.tbl" ) declare -a SYNC_CHECK_FILES @@ -201,6 +202,14 @@ check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscall check_2 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl check_2 tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl check_2 tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl +check_2 tools/perf/arch/arm/entry/syscalls/syscall.tbl arch/arm/tools/syscall.tbl +check_2 tools/perf/arch/sh/entry/syscalls/syscall.tbl arch/sh/kernel/syscalls/syscall.tbl +check_2 tools/perf/arch/sparc/entry/syscalls/syscall.tbl arch/sparc/kernel/syscalls/syscall.tbl +check_2 tools/perf/arch/xtensa/entry/syscalls/syscall.tbl arch/xtensa/kernel/syscalls/syscall.tbl +check_2 tools/perf/arch/alpha/entry/syscalls/syscall.tbl arch/alpha/entry/syscalls/syscall.tbl +check_2 tools/perf/arch/parisc/entry/syscalls/syscall.tbl arch/parisc/entry/syscalls/syscall.tbl +check_2 tools/perf/arch/arm64/entry/syscalls/syscall_32.tbl arch/arm64/entry/syscalls/syscall_32.tbl +check_2 tools/perf/arch/arm64/entry/syscalls/syscall_64.tbl arch/arm64/entry/syscalls/syscall_64.tbl for i in "${BEAUTY_FILES[@]}" do diff --git a/tools/perf/perf.c b/tools/perf/perf.c index a2987f2cfe1a..f0617cc41f5f 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -84,7 +84,7 @@ static struct cmd_struct commands[] = { #endif { "kvm", cmd_kvm, 0 }, { "test", cmd_test, 0 }, -#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)) +#if defined(HAVE_LIBTRACEEVENT) { "trace", cmd_trace, 0 }, #endif { "inject", cmd_inject, 0 }, @@ -514,10 +514,6 @@ int main(int argc, const char **argv) fprintf(stderr, "trace command not available: missing libtraceevent devel package at build time.\n"); goto out; -#elif !defined(HAVE_LIBAUDIT_SUPPORT) && !defined(HAVE_SYSCALL_TABLE_SUPPORT) - fprintf(stderr, - "trace command not available: missing audit-libs devel package at build time.\n"); - goto out; #else setup_path(); argv[0] = "trace"; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index c004dd4e65a3..3cb40965549f 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -3,7 +3,7 @@ #define _PERF_PERF_H #ifndef MAX_NR_CPUS -#define MAX_NR_CPUS 2048 +#define MAX_NR_CPUS 4096 #endif enum perf_affinity { diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json index 4404b8e91690..7126fbf292e0 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json @@ -5,7 +5,7 @@ }, { "ArchStdEvent": "EXC_RETURN", - "PublicDescription": "Counts any architecturally executed exception return instructions. Eg: AArch64: ERET" + "PublicDescription": "Counts any architecturally executed exception return instructions. For example: AArch64: ERET" }, { "ArchStdEvent": "EXC_UNDEF", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json index 428810f855b8..c5dcdcf43c58 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json @@ -5,6 +5,6 @@ }, { "ArchStdEvent": "CNT_CYCLES", - "PublicDescription": "Counts constant frequency cycles" + "PublicDescription": "Increments at a constant frequency equal to the rate of increment of the System Counter, CNTPCT_EL0." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json index da7c129f2569..799d106d5173 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json @@ -1,11 +1,11 @@ [ { "ArchStdEvent": "L1D_CACHE_REFILL", - "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line. This event does not count cache line allocations from preload instructions or from hardware cache prefetching." + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line." }, { "ArchStdEvent": "L1D_CACHE", - "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) count as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted." + "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) counts as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted." }, { "ArchStdEvent": "L1D_CACHE_WB", @@ -17,7 +17,7 @@ }, { "ArchStdEvent": "L1D_CACHE_RD", - "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches count as both a write access and read access." + "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches counts as both a write access and read access." }, { "ArchStdEvent": "L1D_CACHE_WR", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json index 0e31d0daf88b..ed8291ab9737 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json @@ -1,11 +1,11 @@ [ { "ArchStdEvent": "L2D_CACHE", - "PublicDescription": "Counts level 2 cache accesses. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level caches or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache." + "PublicDescription": "Counts accesses to the level 2 cache due to data accesses. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level data cache or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache." }, { "ArchStdEvent": "L2D_CACHE_REFILL", - "PublicDescription": "Counts cache line refills into the level 2 cache. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts cache line refills into the level 2 cache. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_WB", @@ -13,23 +13,23 @@ }, { "ArchStdEvent": "L2D_CACHE_ALLOCATE", - "PublicDescription": "TBD" + "PublicDescription": "Counts level 2 cache line allocates that do not fetch data from outside the level 2 data or unified cache." }, { "ArchStdEvent": "L2D_CACHE_RD", - "PublicDescription": "Counts level 2 cache accesses due to memory read operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts level 2 data cache accesses due to memory read operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_WR", - "PublicDescription": "Counts level 2 cache accesses due to memory write operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts level 2 cache accesses due to memory write operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_REFILL_RD", - "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_REFILL_WR", - "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_WB_VICTIM", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json index 45bfba532df7..4a2e72fc5ada 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json @@ -9,11 +9,11 @@ }, { "ArchStdEvent": "L3D_CACHE", - "PublicDescription": "Counts level 3 cache accesses. level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." + "PublicDescription": "Counts level 3 cache accesses. Level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." }, { "ArchStdEvent": "L3D_CACHE_RD", - "PublicDescription": "TBD" + "PublicDescription": "Counts level 3 cache accesses caused by any memory read operation. Level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." }, { "ArchStdEvent": "L3D_CACHE_LMISS_RD", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json index bb712d57d58a..fd5a2e0099b8 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json @@ -1,10 +1,10 @@ [ { "ArchStdEvent": "LL_CACHE_RD", - "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources." + "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for the L3 cache. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources." }, { "ArchStdEvent": "LL_CACHE_MISS_RD", - "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations." + "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for L3 cache. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json index 106a97f8b2e7..bb3491012a8f 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json @@ -33,7 +33,7 @@ }, { "ArchStdEvent": "MEM_ACCESS_CHECKED", - "PublicDescription": "Counts the number of memory read and write accesses in a cycle that are tag checked by the Memory Tagging Extension (MTE)." + "PublicDescription": "Counts the number of memory read and write accesses counted by MEM_ACCESS that are tag checked by the Memory Tagging Extension (MTE). This event is implemented as the sum of MEM_ACCESS_CHECKED_RD and MEM_ACCESS_CHECKED_WR" }, { "ArchStdEvent": "MEM_ACCESS_CHECKED_RD", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json index 5f449270b448..97d352f94323 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json @@ -5,7 +5,7 @@ }, { "MetricName": "backend_stalled_cycles", - "MetricExpr": "((STALL_BACKEND / CPU_CYCLES) * 100)", + "MetricExpr": "STALL_BACKEND / CPU_CYCLES * 100", "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the backend unit of the processor.", "MetricGroup": "Cycle_Accounting", "ScaleUnit": "1percent of cycles" @@ -16,45 +16,45 @@ }, { "MetricName": "branch_misprediction_ratio", - "MetricExpr": "(BR_MIS_PRED_RETIRED / BR_RETIRED)", + "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED", "BriefDescription": "This metric measures the ratio of branches mispredicted to the total number of branches architecturally executed. This gives an indication of the effectiveness of the branch prediction unit.", "MetricGroup": "Miss_Ratio;Branch_Effectiveness", - "ScaleUnit": "1per branch" + "ScaleUnit": "100percent of branches" }, { "MetricName": "branch_mpki", - "MetricExpr": "((BR_MIS_PRED_RETIRED / INST_RETIRED) * 1000)", + "MetricExpr": "BR_MIS_PRED_RETIRED / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of branch mispredictions per thousand instructions executed.", "MetricGroup": "MPKI;Branch_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "branch_percentage", - "MetricExpr": "(((BR_IMMED_SPEC + BR_INDIRECT_SPEC) / INST_SPEC) * 100)", + "MetricExpr": "(BR_IMMED_SPEC + BR_INDIRECT_SPEC) / INST_SPEC * 100", "BriefDescription": "This metric measures branch operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "crypto_percentage", - "MetricExpr": "((CRYPTO_SPEC / INST_SPEC) * 100)", + "MetricExpr": "CRYPTO_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "dtlb_mpki", - "MetricExpr": "((DTLB_WALK / INST_RETIRED) * 1000)", + "MetricExpr": "DTLB_WALK / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of data TLB Walks per thousand instructions executed.", "MetricGroup": "MPKI;DTLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "dtlb_walk_ratio", - "MetricExpr": "(DTLB_WALK / L1D_TLB)", + "MetricExpr": "DTLB_WALK / L1D_TLB", "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.", "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "ArchStdEvent": "frontend_bound", @@ -62,147 +62,147 @@ }, { "MetricName": "frontend_stalled_cycles", - "MetricExpr": "((STALL_FRONTEND / CPU_CYCLES) * 100)", + "MetricExpr": "STALL_FRONTEND / CPU_CYCLES * 100", "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the frontend unit of the processor.", "MetricGroup": "Cycle_Accounting", "ScaleUnit": "1percent of cycles" }, { "MetricName": "integer_dp_percentage", - "MetricExpr": "((DP_SPEC / INST_SPEC) * 100)", + "MetricExpr": "DP_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "ipc", - "MetricExpr": "(INST_RETIRED / CPU_CYCLES)", + "MetricExpr": "INST_RETIRED / CPU_CYCLES", "BriefDescription": "This metric measures the number of instructions retired per cycle.", "MetricGroup": "General", "ScaleUnit": "1per cycle" }, { "MetricName": "itlb_mpki", - "MetricExpr": "((ITLB_WALK / INST_RETIRED) * 1000)", + "MetricExpr": "ITLB_WALK / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of instruction TLB Walks per thousand instructions executed.", "MetricGroup": "MPKI;ITLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "itlb_walk_ratio", - "MetricExpr": "(ITLB_WALK / L1I_TLB)", + "MetricExpr": "ITLB_WALK / L1I_TLB", "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.", "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "MetricName": "l1d_cache_miss_ratio", - "MetricExpr": "(L1D_CACHE_REFILL / L1D_CACHE)", + "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE", "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.", "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "l1d_cache_mpki", - "MetricExpr": "((L1D_CACHE_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L1D_CACHE_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 1 data cache accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;L1D_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l1d_tlb_miss_ratio", - "MetricExpr": "(L1D_TLB_REFILL / L1D_TLB)", + "MetricExpr": "L1D_TLB_REFILL / L1D_TLB", "BriefDescription": "This metric measures the ratio of level 1 data TLB accesses missed to the total number of level 1 data TLB accesses. This gives an indication of the effectiveness of the level 1 data TLB.", "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "MetricName": "l1d_tlb_mpki", - "MetricExpr": "((L1D_TLB_REFILL / INST_RETIRED) * 1000)", - "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricExpr": "L1D_TLB_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 data TLB accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;DTLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l1i_cache_miss_ratio", - "MetricExpr": "(L1I_CACHE_REFILL / L1I_CACHE)", + "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE", "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.", "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "l1i_cache_mpki", - "MetricExpr": "((L1I_CACHE_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L1I_CACHE_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 1 instruction cache accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;L1I_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l1i_tlb_miss_ratio", - "MetricExpr": "(L1I_TLB_REFILL / L1I_TLB)", + "MetricExpr": "L1I_TLB_REFILL / L1I_TLB", "BriefDescription": "This metric measures the ratio of level 1 instruction TLB accesses missed to the total number of level 1 instruction TLB accesses. This gives an indication of the effectiveness of the level 1 instruction TLB.", "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "MetricName": "l1i_tlb_mpki", - "MetricExpr": "((L1I_TLB_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L1I_TLB_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;ITLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l2_cache_miss_ratio", - "MetricExpr": "(L2D_CACHE_REFILL / L2D_CACHE)", + "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE", "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "l2_cache_mpki", - "MetricExpr": "((L2D_CACHE_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L2D_CACHE_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 2 unified cache accesses missed per thousand instructions executed. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", "MetricGroup": "MPKI;L2_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l2_tlb_miss_ratio", - "MetricExpr": "(L2D_TLB_REFILL / L2D_TLB)", + "MetricExpr": "L2D_TLB_REFILL / L2D_TLB", "BriefDescription": "This metric measures the ratio of level 2 unified TLB accesses missed to the total number of level 2 unified TLB accesses. This gives an indication of the effectiveness of the level 2 TLB.", "MetricGroup": "Miss_Ratio;ITLB_Effectiveness;DTLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "MetricName": "l2_tlb_mpki", - "MetricExpr": "((L2D_TLB_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L2D_TLB_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 2 unified TLB accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;ITLB_Effectiveness;DTLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "ll_cache_read_hit_ratio", - "MetricExpr": "((LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD)", + "MetricExpr": "(LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD", "BriefDescription": "This metric measures the ratio of last level cache read accesses hit in the cache to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", "MetricGroup": "LL_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "ll_cache_read_miss_ratio", - "MetricExpr": "(LL_CACHE_MISS_RD / LL_CACHE_RD)", + "MetricExpr": "LL_CACHE_MISS_RD / LL_CACHE_RD", "BriefDescription": "This metric measures the ratio of last level cache read accesses missed to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", "MetricGroup": "Miss_Ratio;LL_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "ll_cache_read_mpki", - "MetricExpr": "((LL_CACHE_MISS_RD / INST_RETIRED) * 1000)", + "MetricExpr": "LL_CACHE_MISS_RD / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of last level cache read accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;LL_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "load_percentage", - "MetricExpr": "((LD_SPEC / INST_SPEC) * 100)", + "MetricExpr": "LD_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" @@ -213,21 +213,21 @@ }, { "MetricName": "scalar_fp_percentage", - "MetricExpr": "((VFP_SPEC / INST_SPEC) * 100)", + "MetricExpr": "VFP_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "simd_percentage", - "MetricExpr": "((ASE_SPEC / INST_SPEC) * 100)", + "MetricExpr": "ASE_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "store_percentage", - "MetricExpr": "((ST_SPEC / INST_SPEC) * 100)", + "MetricExpr": "ST_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" @@ -300,5 +300,12 @@ "MetricGroup": "Operation_Mix", "MetricName": "branch_indirect_spec_rate", "ScaleUnit": "100%" + }, + { + "MetricName": "sve_all_percentage", + "MetricExpr": "SVE_INST_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations, including loads and stores, as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json index f297b049b62f..337e6a916f2b 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json @@ -9,7 +9,7 @@ }, { "ArchStdEvent": "CID_WRITE_RETIRED", - "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR register, which usually contain the kernel PID and can be output with hardware trace." + "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR_EL1 register, which usually contain the kernel PID and can be output with hardware trace." }, { "ArchStdEvent": "TTBR_WRITE_RETIRED", @@ -17,7 +17,7 @@ }, { "ArchStdEvent": "BR_RETIRED", - "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted." + "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted. Note that exception generating instructions, exception return instructions and context synchronization instructions are not counted." }, { "ArchStdEvent": "BR_MIS_PRED_RETIRED", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json index 1af961f8a6c8..a7ea0d4c4ea4 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json @@ -5,7 +5,7 @@ }, { "ArchStdEvent": "BR_PRED", - "PublicDescription": "Counts branches speculatively executed and were predicted right." + "PublicDescription": "Counts all speculatively executed branches." }, { "ArchStdEvent": "INST_SPEC", @@ -29,7 +29,7 @@ }, { "ArchStdEvent": "LDREX_SPEC", - "PublicDescription": "Counts Load-Exclusive operations that have been speculatively executed. Eg: LDREX, LDX" + "PublicDescription": "Counts Load-Exclusive operations that have been speculatively executed. For example: LDREX, LDX" }, { "ArchStdEvent": "STREX_PASS_SPEC", @@ -73,15 +73,15 @@ }, { "ArchStdEvent": "BR_IMMED_SPEC", - "PublicDescription": "Counts immediate branch operations which are speculatively executed." + "PublicDescription": "Counts direct branch operations which are speculatively executed." }, { "ArchStdEvent": "BR_RETURN_SPEC", - "PublicDescription": "Counts procedure return operations (RET) which are speculatively executed." + "PublicDescription": "Counts procedure return operations (RET, RETAA and RETAB) which are speculatively executed." }, { "ArchStdEvent": "BR_INDIRECT_SPEC", - "PublicDescription": "Counts indirect branch operations including procedure returns, which are speculatively executed. This includes operations that force a software change of the PC, other than exception-generating operations. Eg: BR Xn, RET" + "PublicDescription": "Counts indirect branch operations including procedure returns, which are speculatively executed. This includes operations that force a software change of the PC, other than exception-generating operations and direct branch instructions. Some examples of the instructions counted by this event include BR Xn, RET, etc..." }, { "ArchStdEvent": "ISB_SPEC", @@ -97,11 +97,11 @@ }, { "ArchStdEvent": "RC_LD_SPEC", - "PublicDescription": "Counts any load acquire operations that are speculatively executed. Eg: LDAR, LDARH, LDARB" + "PublicDescription": "Counts any load acquire operations that are speculatively executed. For example: LDAR, LDARH, LDARB" }, { "ArchStdEvent": "RC_ST_SPEC", - "PublicDescription": "Counts any store release operations that are speculatively executed. Eg: STLR, STLRH, STLRB'" + "PublicDescription": "Counts any store release operations that are speculatively executed. For example: STLR, STLRH, STLRB" }, { "ArchStdEvent": "ASE_INST_SPEC", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json index bbbebc805034..1fcba19dfb7d 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json @@ -1,7 +1,7 @@ [ { "ArchStdEvent": "STALL_FRONTEND", - "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. All the frontend slots were empty during the cycle when this event counts." + "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. STALL_FRONTEND_SLOTS counts SLOTS during the cycle when this event counts." }, { "ArchStdEvent": "STALL_BACKEND", @@ -9,11 +9,11 @@ }, { "ArchStdEvent": "STALL", - "PublicDescription": "Counts cycles when no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)." + "PublicDescription": "Counts cycles when no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall). This event is the sum of STALL_FRONTEND and STALL_BACKEND" }, { "ArchStdEvent": "STALL_SLOT_BACKEND", - "PublicDescription": "Counts slots per cycle in which no operations are sent from the rename unit to the backend due to backend resource constraints." + "PublicDescription": "Counts slots per cycle in which no operations are sent from the rename unit to the backend due to backend resource constraints. STALL_BACKEND counts during the cycle when STALL_SLOT_BACKEND counts at least 1." }, { "ArchStdEvent": "STALL_SLOT_FRONTEND", @@ -21,7 +21,7 @@ }, { "ArchStdEvent": "STALL_SLOT", - "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)." + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall). STALL_SLOT is the sum of STALL_SLOT_FRONTEND and STALL_SLOT_BACKEND." }, { "ArchStdEvent": "STALL_BACKEND_MEM", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json index b550af1831f5..5704f1e83af9 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json @@ -25,11 +25,11 @@ }, { "ArchStdEvent": "DTLB_WALK", - "PublicDescription": "Counts data memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Note that partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + "PublicDescription": "Counts number of demand data translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event counts walks triggered by software preloads, but not walks triggered by hardware prefetchers, and that this event does not count walks triggered by TLB maintenance operations." }, { "ArchStdEvent": "ITLB_WALK", - "PublicDescription": "Counts instruction memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + "PublicDescription": "Counts number of instruction translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." }, { "ArchStdEvent": "L1D_TLB_REFILL_RD", diff --git a/tools/perf/pmu-events/arch/arm64/common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json index 492083b99256..dddecc946575 100644 --- a/tools/perf/pmu-events/arch/arm64/common-and-microarch.json +++ b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json @@ -533,6 +533,11 @@ "EventName": "SVE_INST_SPEC", "BriefDescription": "SVE operations speculatively executed" }, + { + "EventCode": "0x8007", + "EventName": "ASE_SVE_INST_SPEC", + "BriefDescription": "Operation speculatively executed, Advanced SIMD or SVE." + }, { "PublicDescription": "Microarchitectural operation, Operations speculatively executed.", "EventCode": "0x8008", @@ -551,48 +556,393 @@ "EventName": "FP_SPEC", "BriefDescription": "Floating-point Operations speculatively executed." }, + { + "EventCode": "0x8011", + "EventName": "ASE_FP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD." + }, + { + "EventCode": "0x8012", + "EventName": "SVE_FP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE." + }, + { + "EventCode": "0x8013", + "EventName": "ASE_SVE_FP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE." + }, { "PublicDescription": "Floating-point half-precision operations speculatively executed", "EventCode": "0x8014", "EventName": "FP_HP_SPEC", "BriefDescription": "Floating-point half-precision operations speculatively executed" }, + { + "EventCode": "0x8015", + "EventName": "ASE_FP_HP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD half precision." + }, + { + "EventCode": "0x8016", + "EventName": "SVE_FP_HP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE half precision." + }, + { + "EventCode": "0x8017", + "EventName": "ASE_SVE_FP_HP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE half precision." + }, { "PublicDescription": "Floating-point single-precision operations speculatively executed", "EventCode": "0x8018", "EventName": "FP_SP_SPEC", "BriefDescription": "Floating-point single-precision operations speculatively executed" }, + { + "EventCode": "0x8019", + "EventName": "ASE_FP_SP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD single precision." + }, + { + "EventCode": "0x801A", + "EventName": "SVE_FP_SP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE single precision." + }, + { + "EventCode": "0x801B", + "EventName": "ASE_SVE_FP_SP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE single precision." + }, { "PublicDescription": "Floating-point double-precision operations speculatively executed", "EventCode": "0x801C", "EventName": "FP_DP_SPEC", "BriefDescription": "Floating-point double-precision operations speculatively executed" }, + { + "EventCode": "0x801D", + "EventName": "ASE_FP_DP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD double precision." + }, + { + "EventCode": "0x801E", + "EventName": "SVE_FP_DP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE double precision." + }, + { + "EventCode": "0x801F", + "EventName": "ASE_SVE_FP_DP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE double precision." + }, + { + "EventCode": "0x8020", + "EventName": "FP_DIV_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, divide." + }, + { + "EventCode": "0x8021", + "EventName": "ASE_FP_DIV_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD divide." + }, + { + "EventCode": "0x8022", + "EventName": "SVE_FP_DIV_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE divide." + }, + { + "EventCode": "0x8023", + "EventName": "ASE_SVE_FP_DIV_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE divide." + }, + { + "EventCode": "0x8024", + "EventName": "FP_SQRT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, square root." + }, + { + "EventCode": "0x8025", + "EventName": "ASE_FP_SQRT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD square root." + }, + { + "EventCode": "0x8026", + "EventName": "SVE_FP_SQRT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE square root." + }, + { + "EventCode": "0x8027", + "EventName": "ASE_SVE_FP_SQRT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE square-root." + }, { "PublicDescription": "Floating-point FMA Operations speculatively executed.", "EventCode": "0x8028", "EventName": "FP_FMA_SPEC", "BriefDescription": "Floating-point FMA Operations speculatively executed." }, + { + "EventCode": "0x8029", + "EventName": "ASE_FP_FMA_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD FMA." + }, + { + "EventCode": "0x802A", + "EventName": "SVE_FP_FMA_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE FMA." + }, + { + "EventCode": "0x802B", + "EventName": "ASE_SVE_FP_FMA_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE FMA." + }, + { + "EventCode": "0x802C", + "EventName": "FP_MUL_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, multiply." + }, + { + "EventCode": "0x802D", + "EventName": "ASE_FP_MUL_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD multiply." + }, + { + "EventCode": "0x802E", + "EventName": "SVE_FP_MUL_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE multiply." + }, + { + "EventCode": "0x802F", + "EventName": "ASE_SVE_FP_MUL_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE multiply." + }, + { + "EventCode": "0x8030", + "EventName": "FP_ADDSUB_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, add or subtract." + }, + { + "EventCode": "0x8031", + "EventName": "ASE_FP_ADDSUB_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD add or subtract." + }, + { + "EventCode": "0x8032", + "EventName": "SVE_FP_ADDSUB_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE add or subtract." + }, + { + "EventCode": "0x8033", + "EventName": "ASE_SVE_FP_ADDSUB_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE add or subtract." + }, { "PublicDescription": "Floating-point reciprocal estimate Operations speculatively executed.", "EventCode": "0x8034", "EventName": "FP_RECPE_SPEC", "BriefDescription": "Floating-point reciprocal estimate Operations speculatively executed." }, + { + "EventCode": "0x8035", + "EventName": "ASE_FP_RECPE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD reciprocal estimate." + }, + { + "EventCode": "0x8036", + "EventName": "SVE_FP_RECPE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE reciprocal estimate." + }, + { + "EventCode": "0x8037", + "EventName": "ASE_SVE_FP_RECPE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE reciprocal estimate." + }, { "PublicDescription": "floating-point convert Operations speculatively executed.", "EventCode": "0x8038", "EventName": "FP_CVT_SPEC", "BriefDescription": "floating-point convert Operations speculatively executed." }, + { + "EventCode": "0x8039", + "EventName": "ASE_FP_CVT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD convert." + }, + { + "EventCode": "0x803A", + "EventName": "SVE_FP_CVT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE convert." + }, + { + "EventCode": "0x803B", + "EventName": "ASE_SVE_FP_CVT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE convert." + }, + { + "EventCode": "0x803C", + "EventName": "SVE_FP_AREDUCE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE accumulating reduction." + }, + { + "EventCode": "0x803D", + "EventName": "ASE_FP_PREDUCE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD pairwise add step." + }, + { + "EventCode": "0x803E", + "EventName": "SVE_FP_VREDUCE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE vector reduction." + }, + { + "EventCode": "0x803F", + "EventName": "ASE_SVE_FP_VREDUCE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE vector reduction." + }, + { + "EventCode": "0x8040", + "EventName": "INT_SPEC", + "BriefDescription": "Integer Operation speculatively executed." + }, + { + "EventCode": "0x8041", + "EventName": "ASE_INT_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD." + }, + { + "EventCode": "0x8042", + "EventName": "SVE_INT_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE." + }, { "PublicDescription": "Advanced SIMD and SVE integer Operations speculatively executed.", "EventCode": "0x8043", "EventName": "ASE_SVE_INT_SPEC", "BriefDescription": "Advanced SIMD and SVE integer Operations speculatively executed." }, + { + "EventCode": "0x8044", + "EventName": "INT_DIV_SPEC", + "BriefDescription": "Integer Operation speculatively executed, divide." + }, + { + "EventCode": "0x8045", + "EventName": "INT_DIV64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, 64-bit divide." + }, + { + "EventCode": "0x8046", + "EventName": "SVE_INT_DIV_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE divide." + }, + { + "EventCode": "0x8047", + "EventName": "SVE_INT_DIV64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE 64-bit divide." + }, + { + "EventCode": "0x8048", + "EventName": "INT_MUL_SPEC", + "BriefDescription": "Integer Operation speculatively executed, multiply." + }, + { + "EventCode": "0x8049", + "EventName": "ASE_INT_MUL_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD multiply." + }, + { + "EventCode": "0x804A", + "EventName": "SVE_INT_MUL_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE multiply." + }, + { + "EventCode": "0x804B", + "EventName": "ASE_SVE_INT_MUL_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD or SVE multiply." + }, + { + "EventCode": "0x804C", + "EventName": "INT_MUL64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, 64\u00d764 multiply." + }, + { + "EventCode": "0x804D", + "EventName": "SVE_INT_MUL64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE 64\u00d764 multiply." + }, + { + "EventCode": "0x804E", + "EventName": "INT_MULH64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, 64\u00d764 multiply returning high part." + }, + { + "EventCode": "0x804F", + "EventName": "SVE_INT_MULH64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE 64\u00d764 multiply high part." + }, + { + "EventCode": "0x8058", + "EventName": "NONFP_SPEC", + "BriefDescription": "Non-floating-point Operation speculatively executed." + }, + { + "EventCode": "0x8059", + "EventName": "ASE_NONFP_SPEC", + "BriefDescription": "Non-floating-point Operation speculatively executed, Advanced SIMD." + }, + { + "EventCode": "0x805A", + "EventName": "SVE_NONFP_SPEC", + "BriefDescription": "Non-floating-point Operation speculatively executed, SVE." + }, + { + "EventCode": "0x805B", + "EventName": "ASE_SVE_NONFP_SPEC", + "BriefDescription": "Non-floating-point Operation speculatively executed, Advanced SIMD or SVE." + }, + { + "EventCode": "0x805D", + "EventName": "ASE_INT_VREDUCE_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD reduction." + }, + { + "EventCode": "0x805E", + "EventName": "SVE_INT_VREDUCE_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE reduction." + }, + { + "EventCode": "0x805F", + "EventName": "ASE_SVE_INT_VREDUCE_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD or SVE reduction." + }, + { + "EventCode": "0x8060", + "EventName": "SVE_PERM_SPEC", + "BriefDescription": "Operation speculatively executed, SVE permute." + }, + { + "EventCode": "0x8065", + "EventName": "SVE_XPIPE_Z2R_SPEC", + "BriefDescription": "Operation speculatively executed, SVE vector to scalar cross-pipe." + }, + { + "EventCode": "0x8066", + "EventName": "SVE_XPIPE_R2Z_SPEC", + "BriefDescription": "Operation speculatively executed, SVE scalar to vector cross-pipe." + }, + { + "EventCode": "0x8068", + "EventName": "SVE_PGEN_SPEC", + "BriefDescription": "Operation speculatively executed, SVE predicate generating." + }, + { + "EventCode": "0x8069", + "EventName": "SVE_PGEN_FLG_SPEC", + "BriefDescription": "Operation speculatively executed, SVE predicate flag setting." + }, + { + "EventCode": "0x806D", + "EventName": "SVE_PPERM_SPEC", + "BriefDescription": "Operation speculatively executed, SVE predicate permute." + }, { "PublicDescription": "SVE predicated Operations speculatively executed.", "EventCode": "0x8074", @@ -629,6 +979,16 @@ "EventName": "SVE_MOVPRFX_SPEC", "BriefDescription": "SVE MOVPRFX Operations speculatively executed." }, + { + "EventCode": "0x807D", + "EventName": "SVE_MOVPRFX_Z_SPEC", + "BriefDescription": "Operation speculatively executed, SVE MOVPRFX zeroing predication." + }, + { + "EventCode": "0x807E", + "EventName": "SVE_MOVPRFX_M_SPEC", + "BriefDescription": "Operation speculatively executed, SVE MOVPRFX merging predication." + }, { "PublicDescription": "SVE MOVPRFX unfused Operations speculatively executed.", "EventCode": "0x807F", @@ -695,6 +1055,16 @@ "EventName": "SVE_PRF_CONTIG_SPEC", "BriefDescription": "SVE contiguous prefetch element Operations speculatively executed." }, + { + "EventCode": "0x80A1", + "EventName": "SVE_LDNT_CONTIG_SPEC", + "BriefDescription": "Operation speculatively executed, SVE non-temporal contiguous load element." + }, + { + "EventCode": "0x80A2", + "EventName": "SVE_STNT_CONTIG_SPEC", + "BriefDescription": "Operation speculatively executed, SVE non-temporal contiguous store element." + }, { "PublicDescription": "Advanced SIMD and SVE contiguous load multiple vector Operations speculatively executed.", "EventCode": "0x80A5", @@ -785,6 +1155,16 @@ "EventName": "FP_DP_FIXED_OPS_SPEC", "BriefDescription": "Non-scalable double-precision floating-point element Operations speculatively executed." }, + { + "EventCode": "0x80C8", + "EventName": "INT_SCALE_OPS_SPEC", + "BriefDescription": "Scalable integer element arithmetic operations Speculatively executed." + }, + { + "EventCode": "0x80C9", + "EventName": "INT_FIXED_OPS_SPEC", + "BriefDescription": "Non-scalable integer element arithmetic operations Speculatively executed." + }, { "PublicDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed", "EventCode": "0x80E3", @@ -808,5 +1188,340 @@ "EventCode": "0x80EF", "EventName": "ASE_SVE_INT64_SPEC", "BriefDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed" + }, + { + "EventCode": "0x80F3", + "EventName": "ASE_SVE_FP_DOT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE dot-product." + }, + { + "EventCode": "0x80F7", + "EventName": "ASE_SVE_FP_MMLA_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE matrix multiply." + }, + { + "EventCode": "0x80FB", + "EventName": "ASE_SVE_INT_DOT_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD or SVE dot-product." + }, + { + "EventCode": "0x80FF", + "EventName": "ASE_SVE_INT_MMLA_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD or SVE matrix multiply." + }, + { + "EventCode": "0x8128", + "EventName": "DTLB_WALK_PERCYC", + "BriefDescription": "Data translation table walks in progress." + }, + { + "EventCode": "0x8129", + "EventName": "ITLB_WALK_PERCYC", + "BriefDescription": "Instruction translation table walks in progress." + }, + { + "EventCode": "0x8136", + "EventName": "DTLB_STEP", + "BriefDescription": "Data TLB translation table walk, step." + }, + { + "EventCode": "0x8137", + "EventName": "ITLB_STEP", + "BriefDescription": "Instruction TLB translation table walk, step." + }, + { + "EventCode": "0x8138", + "EventName": "DTLB_WALK_LARGE", + "BriefDescription": "Data TLB large page translation table walk." + }, + { + "EventCode": "0x8139", + "EventName": "ITLB_WALK_LARGE", + "BriefDescription": "Instruction TLB large page translation table walk." + }, + { + "EventCode": "0x813A", + "EventName": "DTLB_WALK_SMALL", + "BriefDescription": "Data TLB small page translation table walk." + }, + { + "EventCode": "0x813B", + "EventName": "ITLB_WALK_SMALL", + "BriefDescription": "Instruction TLB small page translation table walk." + }, + { + "EventCode": "0x8144", + "EventName": "L1D_CACHE_MISS", + "BriefDescription": "Level 1 data cache demand access miss." + }, + { + "EventCode": "0x8145", + "EventName": "L1I_CACHE_HWPRF", + "BriefDescription": "Level 1 instruction cache hardware prefetch." + }, + { + "EventCode": "0x814C", + "EventName": "L2D_CACHE_MISS", + "BriefDescription": "Level 2 data cache demand access miss." + }, + { + "EventCode": "0x8154", + "EventName": "L1D_CACHE_HWPRF", + "BriefDescription": "Level 1 data cache hardware prefetch." + }, + { + "EventCode": "0x8155", + "EventName": "L2D_CACHE_HWPRF", + "BriefDescription": "Level 2 data cache hardware prefetch." + }, + { + "EventCode": "0x8158", + "EventName": "STALL_FRONTEND_MEMBOUND", + "BriefDescription": "Frontend stall cycles, memory bound." + }, + { + "EventCode": "0x8159", + "EventName": "STALL_FRONTEND_L1I", + "BriefDescription": "Frontend stall cycles, level 1 instruction cache." + }, + { + "EventCode": "0x815A", + "EventName": "STALL_FRONTEND_L2I", + "BriefDescription": "Frontend stall cycles, level 2 instruction cache." + }, + { + "EventCode": "0x815B", + "EventName": "STALL_FRONTEND_MEM", + "BriefDescription": "Frontend stall cycles, last level PE cache or memory." + }, + { + "EventCode": "0x815C", + "EventName": "STALL_FRONTEND_TLB", + "BriefDescription": "Frontend stall cycles, TLB." + }, + { + "EventCode": "0x8160", + "EventName": "STALL_FRONTEND_CPUBOUND", + "BriefDescription": "Frontend stall cycles, processor bound." + }, + { + "EventCode": "0x8161", + "EventName": "STALL_FRONTEND_FLOW", + "BriefDescription": "Frontend stall cycles, flow control." + }, + { + "EventCode": "0x8162", + "EventName": "STALL_FRONTEND_FLUSH", + "BriefDescription": "Frontend stall cycles, flush recovery." + }, + { + "EventCode": "0x8163", + "EventName": "STALL_FRONTEND_RENAME", + "BriefDescription": "Frontend stall cycles, rename full." + }, + { + "EventCode": "0x8164", + "EventName": "STALL_BACKEND_MEMBOUND", + "BriefDescription": "Backend stall cycles, memory bound." + }, + { + "EventCode": "0x8165", + "EventName": "STALL_BACKEND_L1D", + "BriefDescription": "Backend stall cycles, level 1 data cache." + }, + { + "EventCode": "0x8166", + "EventName": "STALL_BACKEND_L2D", + "BriefDescription": "Backend stall cycles, level 2 data cache." + }, + { + "EventCode": "0x8167", + "EventName": "STALL_BACKEND_TLB", + "BriefDescription": "Backend stall cycles, TLB." + }, + { + "EventCode": "0x8168", + "EventName": "STALL_BACKEND_ST", + "BriefDescription": "Backend stall cycles, store." + }, + { + "EventCode": "0x816A", + "EventName": "STALL_BACKEND_CPUBOUND", + "BriefDescription": "Backend stall cycles, processor bound." + }, + { + "EventCode": "0x816B", + "EventName": "STALL_BACKEND_BUSY", + "BriefDescription": "Backend stall cycles, backend busy." + }, + { + "EventCode": "0x816C", + "EventName": "STALL_BACKEND_ILOCK", + "BriefDescription": "Backend stall cycles, input dependency." + }, + { + "EventCode": "0x816D", + "EventName": "STALL_BACKEND_RENAME", + "BriefDescription": "Backend stall cycles, rename full." + }, + { + "EventCode": "0x816E", + "EventName": "STALL_BACKEND_ATOMIC", + "BriefDescription": "Backend stall cycles, atomic operation." + }, + { + "EventCode": "0x816F", + "EventName": "STALL_BACKEND_MEMCPYSET", + "BriefDescription": "Backend stall cycles, Memory Copy or Set operation." + }, + { + "EventCode": "0x8186", + "EventName": "UOP_RETIRED", + "BriefDescription": "Micro-operation architecturally executed." + }, + { + "EventCode": "0x8188", + "EventName": "DTLB_WALK_BLOCK", + "BriefDescription": "Data TLB block translation table walk." + }, + { + "EventCode": "0x8189", + "EventName": "ITLB_WALK_BLOCK", + "BriefDescription": "Instruction TLB block translation table walk." + }, + { + "EventCode": "0x818A", + "EventName": "DTLB_WALK_PAGE", + "BriefDescription": "Data TLB page translation table walk." + }, + { + "EventCode": "0x818B", + "EventName": "ITLB_WALK_PAGE", + "BriefDescription": "Instruction TLB page translation table walk." + }, + { + "EventCode": "0x81B8", + "EventName": "L1I_CACHE_REFILL_HWPRF", + "BriefDescription": "Level 1 instruction cache refill, hardware prefetch." + }, + { + "EventCode": "0x81BC", + "EventName": "L1D_CACHE_REFILL_HWPRF", + "BriefDescription": "Level 1 data cache refill, hardware prefetch." + }, + { + "EventCode": "0x81BD", + "EventName": "L2D_CACHE_REFILL_HWPRF", + "BriefDescription": "Level 2 data cache refill, hardware prefetch." + }, + { + "EventCode": "0x81C0", + "EventName": "L1I_CACHE_HIT_RD", + "BriefDescription": "Level 1 instruction cache demand fetch hit." + }, + { + "EventCode": "0x81C4", + "EventName": "L1D_CACHE_HIT_RD", + "BriefDescription": "Level 1 data cache demand access hit, read." + }, + { + "EventCode": "0x81C5", + "EventName": "L2D_CACHE_HIT_RD", + "BriefDescription": "Level 2 data cache demand access hit, read." + }, + { + "EventCode": "0x81C8", + "EventName": "L1D_CACHE_HIT_WR", + "BriefDescription": "Level 1 data cache demand access hit, write." + }, + { + "EventCode": "0x81C9", + "EventName": "L2D_CACHE_HIT_WR", + "BriefDescription": "Level 2 data cache demand access hit, write." + }, + { + "EventCode": "0x8200", + "EventName": "L1I_CACHE_HIT", + "BriefDescription": "Level 1 instruction cache hit." + }, + { + "EventCode": "0x8204", + "EventName": "L1D_CACHE_HIT", + "BriefDescription": "Level 1 data cache hit." + }, + { + "EventCode": "0x8205", + "EventName": "L2D_CACHE_HIT", + "BriefDescription": "Level 2 data cache hit." + }, + { + "EventCode": "0x8240", + "EventName": "L1I_LFB_HIT_RD", + "BriefDescription": "Level 1 instruction cache demand fetch line-fill buffer hit." + }, + { + "EventCode": "0x8244", + "EventName": "L1D_LFB_HIT_RD", + "BriefDescription": "Level 1 data cache demand access line-fill buffer hit, read." + }, + { + "EventCode": "0x8245", + "EventName": "L2D_LFB_HIT_RD", + "BriefDescription": "Level 2 data cache demand access line-fill buffer hit, read." + }, + { + "EventCode": "0x8248", + "EventName": "L1D_LFB_HIT_WR", + "BriefDescription": "Level 1 data cache demand access line-fill buffer hit, write." + }, + { + "EventCode": "0x8249", + "EventName": "L2D_LFB_HIT_WR", + "BriefDescription": "Level 2 data cache demand access line-fill buffer hit, write." + }, + { + "EventCode": "0x8280", + "EventName": "L1I_CACHE_PRF", + "BriefDescription": "Level 1 instruction cache, preload or prefetch hit." + }, + { + "EventCode": "0x8284", + "EventName": "L1D_CACHE_PRF", + "BriefDescription": "Level 1 data cache, preload or prefetch hit." + }, + { + "EventCode": "0x8285", + "EventName": "L2D_CACHE_PRF", + "BriefDescription": "Level 2 data cache, preload or prefetch hit." + }, + { + "EventCode": "0x8288", + "EventName": "L1I_CACHE_REFILL_PRF", + "BriefDescription": "Level 1 instruction cache refill, preload or prefetch hit." + }, + { + "EventCode": "0x828C", + "EventName": "L1D_CACHE_REFILL_PRF", + "BriefDescription": "Level 1 data cache refill, preload or prefetch hit." + }, + { + "EventCode": "0x828D", + "EventName": "L2D_CACHE_REFILL_PRF", + "BriefDescription": "Level 2 data cache refill, preload or prefetch hit." + }, + { + "EventCode": "0x8320", + "EventName": "L1D_CACHE_REFILL_PERCYC", + "BriefDescription": "Level 1 data or unified cache refills in progress." + }, + { + "EventCode": "0x8321", + "EventName": "L2D_CACHE_REFILL_PERCYC", + "BriefDescription": "Level 2 data or unified cache refills in progress." + }, + { + "EventCode": "0x8324", + "EventName": "L1I_CACHE_REFILL_PERCYC", + "BriefDescription": "Level 1 instruction or unified cache refills in progress." } ] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/core-imp-def.json new file mode 100644 index 000000000000..52f5ca1482fe --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/core-imp-def.json @@ -0,0 +1,6 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_PRF", + "BriefDescription": "This event counts fetch counted by either Level 1 instruction hardware prefetch or Level 1 instruction software prefetch." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/cycle_accounting.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/cycle_accounting.json new file mode 100644 index 000000000000..24ff5d8dbb98 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/cycle_accounting.json @@ -0,0 +1,122 @@ +[ + { + "EventCode": "0x0182", + "EventName": "LD_COMP_WAIT_L1_MISS", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted load/store/prefetch operation waits for L2 cache access." + }, + { + "EventCode": "0x0183", + "EventName": "LD_COMP_WAIT_L1_MISS_EX", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted integer load operation waits for L2 cache access." + }, + { + "EventCode": "0x0184", + "EventName": "LD_COMP_WAIT", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted load/store/prefetch operation waits for L1D cache, L2 cache and memory access." + }, + { + "EventCode": "0x0185", + "EventName": "LD_COMP_WAIT_EX", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted integer load operation waits for L1D cache, L2 cache and memory access." + }, + { + "EventCode": "0x0186", + "EventName": "LD_COMP_WAIT_PFP_BUSY", + "BriefDescription": "This event counts every cycle that no instruction was committed due to the lack of an available prefetch port." + }, + { + "EventCode": "0x0187", + "EventName": "LD_COMP_WAIT_PFP_BUSY_EX", + "BriefDescription": "This event counts the LD_COMP_WAIT_PFP_BUSY caused by an integer load operation." + }, + { + "EventCode": "0x0188", + "EventName": "LD_COMP_WAIT_PFP_BUSY_SWPF", + "BriefDescription": "This event counts the LD_COMP_WAIT_PFP_BUSY caused by a software prefetch instruction." + }, + { + "EventCode": "0x0189", + "EventName": "EU_COMP_WAIT", + "BriefDescription": "This event counts every cycle that no instruction was committed and the oldest and uncommitted instruction is an integer or floating-point/SIMD instruction." + }, + { + "EventCode": "0x018A", + "EventName": "FL_COMP_WAIT", + "BriefDescription": "This event counts every cycle that no instruction was committed and the oldest and uncommitted instruction is a floating-point/SIMD instruction." + }, + { + "EventCode": "0x018B", + "EventName": "BR_COMP_WAIT", + "BriefDescription": "This event counts every cycle that no instruction was committed and the oldest and uncommitted instruction is a branch instruction." + }, + { + "EventCode": "0x018C", + "EventName": "ROB_EMPTY", + "BriefDescription": "This event counts every cycle that no instruction was committed because the CSE is empty." + }, + { + "EventCode": "0x018D", + "EventName": "ROB_EMPTY_STQ_BUSY", + "BriefDescription": "This event counts every cycle that no instruction was committed because the CSE is empty and the store port (SP) is full." + }, + { + "EventCode": "0x018E", + "EventName": "WFE_WFI_CYCLE", + "BriefDescription": "This event counts every cycle that the instruction unit is halted by the WFE/WFI instruction." + }, + { + "EventCode": "0x018F", + "EventName": "RETENTION_CYCLE", + "BriefDescription": "This event counts every cycle that the instruction unit is halted by the RETENTION state." + }, + { + "EventCode": "0x0190", + "EventName": "_0INST_COMMIT", + "BriefDescription": "This event counts every cycle that no instruction was committed, but counts at the time when commits MOVPRFX only." + }, + { + "EventCode": "0x0191", + "EventName": "_1INST_COMMIT", + "BriefDescription": "This event counts every cycle that one instruction is committed." + }, + { + "EventCode": "0x0192", + "EventName": "_2INST_COMMIT", + "BriefDescription": "This event counts every cycle that two instructions are committed." + }, + { + "EventCode": "0x0193", + "EventName": "_3INST_COMMIT", + "BriefDescription": "This event counts every cycle that three instructions are committed." + }, + { + "EventCode": "0x0194", + "EventName": "_4INST_COMMIT", + "BriefDescription": "This event counts every cycle that four instructions are committed." + }, + { + "EventCode": "0x0195", + "EventName": "_5INST_COMMIT", + "BriefDescription": "This event counts every cycle that five instructions are committed." + }, + { + "EventCode": "0x0198", + "EventName": "UOP_ONLY_COMMIT", + "BriefDescription": "This event counts every cycle that only any micro-operations are committed." + }, + { + "EventCode": "0x0199", + "EventName": "SINGLE_MOVPRFX_COMMIT", + "BriefDescription": "This event counts every cycle that only the MOVPRFX instruction is committed." + }, + { + "EventCode": "0x019C", + "EventName": "LD_COMP_WAIT_L2_MISS", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted load/store/prefetch operation waits for L2 cache miss." + }, + { + "EventCode": "0x019D", + "EventName": "LD_COMP_WAIT_L2_MISS_EX", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted integer load operation waits for L2 cache miss." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/energy.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/energy.json new file mode 100644 index 000000000000..b55173f71e42 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/energy.json @@ -0,0 +1,17 @@ +[ + { + "EventCode": "0x01F0", + "EventName": "EA_CORE", + "BriefDescription": "This event counts energy consumption of core." + }, + { + "EventCode": "0x03F0", + "EventName": "EA_L3", + "BriefDescription": "This event counts energy consumption of L3 cache." + }, + { + "EventCode": "0x03F1", + "EventName": "EA_LDO_LOSS", + "BriefDescription": "This event counts energy consumption of LDO loss." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/exception.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/exception.json new file mode 100644 index 000000000000..f231712fe261 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/exception.json @@ -0,0 +1,42 @@ +[ + { + "ArchStdEvent": "EXC_TAKEN", + "BriefDescription": "This event counts each exception taken." + }, + { + "ArchStdEvent": "EXC_RETURN", + "BriefDescription": "This event counts each executed exception return instruction." + }, + { + "ArchStdEvent": "EXC_UNDEF", + "BriefDescription": "This event counts only other synchronous exceptions that are taken locally." + }, + { + "ArchStdEvent": "EXC_SVC", + "BriefDescription": "This event counts only Supervisor Call exceptions that are taken locally." + }, + { + "ArchStdEvent": "EXC_PABORT", + "BriefDescription": "This event counts only Instruction Abort exceptions that are taken locally." + }, + { + "ArchStdEvent": "EXC_DABORT", + "BriefDescription": "This event counts only Data Abort or SError interrupt exceptions that are taken locally." + }, + { + "ArchStdEvent": "EXC_IRQ", + "BriefDescription": "This event counts only IRQ exceptions that are taken locally, including Virtual IRQ exceptions." + }, + { + "ArchStdEvent": "EXC_FIQ", + "BriefDescription": "This event counts only FIQ exceptions that are taken locally, including Virtual FIQ exceptions." + }, + { + "ArchStdEvent": "EXC_SMC", + "BriefDescription": "This event counts only Secure Monitor Call exceptions. The counter does not increment on SMC instructions trapped as a Hyp Trap exception." + }, + { + "ArchStdEvent": "EXC_HVC", + "BriefDescription": "This event counts for both Hypervisor Call exceptions taken locally in the hypervisor and those taken as an exception from Non-secure EL1." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/fp_operation.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/fp_operation.json new file mode 100644 index 000000000000..a3c368959199 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/fp_operation.json @@ -0,0 +1,209 @@ +[ + { + "EventCode": "0x0105", + "EventName": "FP_MV_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point move operations." + }, + { + "EventCode": "0x0112", + "EventName": "FP_LD_SPEC", + "BriefDescription": "This event counts architecturally executed NOSIMD load operations that using SIMD&FP registers." + }, + { + "EventCode": "0x0113", + "EventName": "FP_ST_SPEC", + "BriefDescription": "This event counts architecturally executed NOSIMD store operations that using SIMD&FP registers." + }, + { + "ArchStdEvent": "ASE_FP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point operation." + }, + { + "ArchStdEvent": "SVE_FP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point operations." + }, + { + "ArchStdEvent": "FP_HP_SPEC", + "BriefDescription": "This event counts architecturally executed half-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_FP_HP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD half-precision floating-point operation." + }, + { + "ArchStdEvent": "SVE_FP_HP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE half-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_HP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE half-precision floating-point operations." + }, + { + "ArchStdEvent": "FP_SP_SPEC", + "BriefDescription": "This event counts architecturally executed single-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_FP_SP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD single-precision floating-point operation." + }, + { + "ArchStdEvent": "SVE_FP_SP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE single-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_SP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE single-precision floating-point operations." + }, + { + "ArchStdEvent": "FP_DP_SPEC", + "BriefDescription": "This event counts architecturally executed double-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_FP_DP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD double-precision floating-point operation." + }, + { + "ArchStdEvent": "SVE_FP_DP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE double-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_DP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE double-precision floating-point operations." + }, + { + "ArchStdEvent": "FP_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point divide operation." + }, + { + "ArchStdEvent": "ASE_FP_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point divide operation." + }, + { + "ArchStdEvent": "SVE_FP_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point divide operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point divide operations." + }, + { + "ArchStdEvent": "FP_SQRT_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point square root operation." + }, + { + "ArchStdEvent": "ASE_FP_SQRT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point square root operation." + }, + { + "ArchStdEvent": "SVE_FP_SQRT_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point square root operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_SQRT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point square root operations." + }, + { + "ArchStdEvent": "ASE_FP_FMA_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point FMA operation." + }, + { + "ArchStdEvent": "SVE_FP_FMA_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point FMA operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_FMA_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point FMA operations." + }, + { + "ArchStdEvent": "FP_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point multiply operations." + }, + { + "ArchStdEvent": "ASE_FP_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point multiply operation." + }, + { + "ArchStdEvent": "SVE_FP_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point multiply operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point multiply operations." + }, + { + "ArchStdEvent": "FP_ADDSUB_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point add or subtract operations." + }, + { + "ArchStdEvent": "ASE_FP_ADDSUB_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point add or subtract operation." + }, + { + "ArchStdEvent": "SVE_FP_ADDSUB_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point add or subtract operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_ADDSUB_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point add or subtract operations." + }, + { + "ArchStdEvent": "ASE_FP_RECPE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point reciprocal estimate operations." + }, + { + "ArchStdEvent": "SVE_FP_RECPE_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point reciprocal estimate operations." + }, + { + "ArchStdEvent": "ASE_SVE_FP_RECPE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point reciprocal estimate operations." + }, + { + "ArchStdEvent": "ASE_FP_CVT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point convert operation." + }, + { + "ArchStdEvent": "SVE_FP_CVT_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point convert operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_CVT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point convert operations." + }, + { + "ArchStdEvent": "SVE_FP_AREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point accumulating reduction operations." + }, + { + "ArchStdEvent": "ASE_FP_PREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point pairwise add step operations." + }, + { + "ArchStdEvent": "SVE_FP_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point vector reduction operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point vector reduction operations." + }, + { + "ArchStdEvent": "FP_SCALE_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed SVE arithmetic operations. See FP_SCALE_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by (128 / CSIZE) and by twice that amount for operations that would also be counted by SVE_FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_FIXED_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed v8SIMD&FP arithmetic operations. See FP_FIXED_OPS_SPEC of ARMv9 Reference Manual for more information. The event counter is incremented by the specified number of elements for Advanced SIMD operations or by 1 for scalar operations, and by twice those amounts for operations that would also be counted by FP_FMA_SPEC." + }, + { + "ArchStdEvent": "ASE_SVE_FP_DOT_SPEC", + "BriefDescription": "This event counts architecturally executed microarchitectural Advanced SIMD or SVE floating-point dot-product operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_MMLA_SPEC", + "BriefDescription": "This event counts architecturally executed microarchitectural Advanced SIMD or SVE floating-point matrix multiply operation." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/gcycle.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/gcycle.json new file mode 100644 index 000000000000..b4ceddc0d25e --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/gcycle.json @@ -0,0 +1,97 @@ +[ + { + "EventCode": "0x0880", + "EventName": "GCYCLES", + "BriefDescription": "This event counts the number of cycles at 100MHz." + }, + { + "EventCode": "0x0890", + "EventName": "FL0_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 0." + }, + { + "EventCode": "0x0891", + "EventName": "FL1_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 1." + }, + { + "EventCode": "0x0892", + "EventName": "FL2_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 2." + }, + { + "EventCode": "0x0893", + "EventName": "FL3_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 3." + }, + { + "EventCode": "0x0894", + "EventName": "FL4_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 4." + }, + { + "EventCode": "0x0895", + "EventName": "FL5_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 5." + }, + { + "EventCode": "0x0896", + "EventName": "FL6_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 6." + }, + { + "EventCode": "0x0897", + "EventName": "FL7_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 7." + }, + { + "EventCode": "0x0898", + "EventName": "FL8_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 8." + }, + { + "EventCode": "0x0899", + "EventName": "FL9_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 9." + }, + { + "EventCode": "0x089A", + "EventName": "FL10_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 10." + }, + { + "EventCode": "0x089B", + "EventName": "FL11_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 11." + }, + { + "EventCode": "0x089C", + "EventName": "FL12_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 12." + }, + { + "EventCode": "0x089D", + "EventName": "FL13_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 13." + }, + { + "EventCode": "0x089E", + "EventName": "FL14_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 14." + }, + { + "EventCode": "0x089F", + "EventName": "FL15_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 15." + }, + { + "EventCode": "0x08A0", + "EventName": "RETENTION_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the RETENTION state." + }, + { + "EventCode": "0x08A1", + "EventName": "RETENTION_COUNT", + "BriefDescription": "This event counts the number of changes from the normal state to the RETENTION state." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/general.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/general.json new file mode 100644 index 000000000000..32f0fbfc4de4 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/general.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES", + "BriefDescription": "This event counts every cycle." + }, + { + "ArchStdEvent": "CNT_CYCLES", + "BriefDescription": "This event counts the constant frequency cycles counter increments at a constant frequency equal to the rate of increment of the System counter." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/hwpf.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/hwpf.json new file mode 100644 index 000000000000..a784a032f353 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/hwpf.json @@ -0,0 +1,52 @@ +[ + { + "EventCode": "0x0230", + "EventName": "L1HWPF_STREAM_PF", + "BriefDescription": "This event counts streaming prefetch requests to L1D cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0231", + "EventName": "L1HWPF_STRIDE_PF", + "BriefDescription": "This event counts stride prefetch requests to L1D cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0232", + "EventName": "L1HWPF_PFTGT_PF", + "BriefDescription": "This event counts LDS prefetch requests to L1D cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0234", + "EventName": "L2HWPF_STREAM_PF", + "BriefDescription": "This event counts streaming prefetch requests to L2 cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0235", + "EventName": "L2HWPF_STRIDE_PF", + "BriefDescription": "This event counts stride prefetch requests to L2 cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0237", + "EventName": "L2HWPF_OTHER", + "BriefDescription": "This event counts prefetch requests to L2 cache generated by the other causes." + }, + { + "EventCode": "0x0238", + "EventName": "L3HWPF_STREAM_PF", + "BriefDescription": "This event counts streaming prefetch requests to L3 cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0239", + "EventName": "L3HWPF_STRIDE_PF", + "BriefDescription": "This event counts stride prefetch requests to L3 cache generated by hardware prefetcher." + }, + { + "EventCode": "0x023B", + "EventName": "L3HWPF_OTHER", + "BriefDescription": "This event counts prefetch requests to L3 cache generated by the other causes." + }, + { + "EventCode": "0x023C", + "EventName": "L1IHWPF_NEXTLINE_PF", + "BriefDescription": "This event counts next line's prefetch requests to L1I cache generated by hardware prefetcher." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1d_cache.json new file mode 100644 index 000000000000..b0818a2fedb0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1d_cache.json @@ -0,0 +1,113 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_REFILL", + "BriefDescription": "This event counts operations that cause a refill of the L1D cache. See L1D_CACHE_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L1D cache. See L1D_CACHE of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_CACHE_WB", + "BriefDescription": "This event counts every write-back of data from the L1D cache. See L1D_CACHE_WB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD", + "BriefDescription": "This event counts operations that cause a refill of the L1D cache that incurs additional latency." + }, + { + "ArchStdEvent": "L1D_CACHE_RD", + "BriefDescription": "This event counts L1D CACHE caused by read access." + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + "BriefDescription": "This event counts L1D CACHE caused by write access." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by read access." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by write access." + }, + { + "EventCode": "0x0200", + "EventName": "L1D_CACHE_DM", + "BriefDescription": "This event counts L1D_CACHE caused by demand access." + }, + { + "EventCode": "0x0201", + "EventName": "L1D_CACHE_DM_RD", + "BriefDescription": "This event counts L1D_CACHE caused by demand read access." + }, + { + "EventCode": "0x0202", + "EventName": "L1D_CACHE_DM_WR", + "BriefDescription": "This event counts L1D_CACHE caused by demand write access." + }, + { + "EventCode": "0x0208", + "EventName": "L1D_CACHE_REFILL_DM", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by demand access." + }, + { + "EventCode": "0x0209", + "EventName": "L1D_CACHE_REFILL_DM_RD", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by demand read access." + }, + { + "EventCode": "0x020A", + "EventName": "L1D_CACHE_REFILL_DM_WR", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by demand write access." + }, + { + "EventCode": "0x020D", + "EventName": "L1D_CACHE_BTC", + "BriefDescription": "This event counts demand access that hits cache line with shared status and requests exclusive access in the Level 1 data cache, causing a coherence access to outside of the Level 1 caches of this PE." + }, + { + "ArchStdEvent": "L1D_CACHE_MISS", + "BriefDescription": "This event counts demand access that misses in the Level 1 data cache, causing an access to outside of the Level 1 caches of this PE." + }, + { + "ArchStdEvent": "L1D_CACHE_HWPRF", + "BriefDescription": "This event counts access counted by L1D_CACHE that is due to a hardware prefetch." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_HWPRF", + "BriefDescription": "This event counts hardware prefetch counted by L1D_CACHE_HWPRF that causes a refill of the Level 1 data cache from outside of the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_HIT_RD", + "BriefDescription": "This event counts demand read counted by L1D_CACHE_RD that hits in the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_HIT_WR", + "BriefDescription": "This event counts demand write counted by L1D_CACHE_WR that hits in the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_HIT", + "BriefDescription": "This event counts access counted by L1D_CACHE that hits in the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_LFB_HIT_RD", + "BriefDescription": "This event counts demand access counted by L1D_CACHE_HIT_RD that hits a cache line that is in the process of being loaded into the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_LFB_HIT_WR", + "BriefDescription": "This event counts demand access counted by L1D_CACHE_HIT_WR that hits a cache line that is in the process of being loaded into the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_PRF", + "BriefDescription": "This event counts fetch counted by either Level 1 data hardware prefetch or Level 1 data software prefetch." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_PRF", + "BriefDescription": "This event counts hardware prefetch counted by L1D_CACHE_PRF that causes a refill of the Level 1 data cache from outside of the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_PERCYC", + "BriefDescription": "The counter counts by the number of cache refills counted by L1D_CACHE_REFILL in progress on each Processor cycle." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1i_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1i_cache.json new file mode 100644 index 000000000000..8680d8ec461d --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1i_cache.json @@ -0,0 +1,52 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL", + "BriefDescription": "This event counts operations that cause a refill of the L1I cache. See L1I_CACHE_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1I_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L1I cache. See L1I_CACHE of ARMv9 Reference Manual for more information." + }, + { + "EventCode": "0x0207", + "EventName": "L1I_CACHE_DM_RD", + "BriefDescription": "This event counts L1I_CACHE caused by demand read access." + }, + { + "EventCode": "0x020F", + "EventName": "L1I_CACHE_REFILL_DM_RD", + "BriefDescription": "This event counts L1I_CACHE_REFILL caused by demand read access." + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS", + "BriefDescription": "This event counts operations that cause a refill of the L1I cache that incurs additional latency." + }, + { + "ArchStdEvent": "L1I_CACHE_HWPRF", + "BriefDescription": "This event counts access counted by L1I_CACHE that is due to a hardware prefetch." + }, + { + "ArchStdEvent": "L1I_CACHE_REFILL_HWPRF", + "BriefDescription": "This event counts hardware prefetch counted by L1I_CACHE_HWPRF that causes a refill of the Level 1 instruction cache from outside of the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_HIT_RD", + "BriefDescription": "This event counts demand fetch counted by L1I_CACHE_DM_RD that hits in the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_HIT", + "BriefDescription": "This event counts access counted by L1I_CACHE that hits in the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_LFB_HIT_RD", + "BriefDescription": "This event counts demand access counted by L1I_CACHE_HIT_RD that hits a cache line that is in the process of being loaded into the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_REFILL_PRF", + "BriefDescription": "This event counts hardware prefetch counted by L1I_CACHE_PRF that causes a refill of the Level 1 instruction cache from outside of the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_REFILL_PERCYC", + "BriefDescription": "The counter counts by the number of cache refills counted by L1I_CACHE_REFILL in progress on each Processor cycle." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l2_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l2_cache.json new file mode 100644 index 000000000000..9e092752e6db --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l2_cache.json @@ -0,0 +1,160 @@ +[ + { + "ArchStdEvent": "L2D_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L2 cache. See L2D_CACHE of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL", + "BriefDescription": "This event counts operations that cause a refill of the L2 cache. See L2D_CACHE_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_CACHE_WB", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by L2 replace, non-temporal-store and DC ZVA." + }, + { + "ArchStdEvent": "L2I_TLB_REFILL", + "BriefDescription": "This event counts operations that cause a TLB refill of the L2I TLB. See L2I_TLB_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2I_TLB", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I TLB. See L2I_TLB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_CACHE_RD", + "BriefDescription": "This event counts L2D CACHE caused by read access." + }, + { + "ArchStdEvent": "L2D_CACHE_WR", + "BriefDescription": "This event counts L2D CACHE caused by write access." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD", + "BriefDescription": "This event counts L2D CACHE_REFILL caused by read access." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR", + "BriefDescription": "This event counts L2D CACHE_REFILL caused by write access." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by L2 replace." + }, + { + "EventCode": "0x0300", + "EventName": "L2D_CACHE_DM", + "BriefDescription": "This event counts L2D_CACHE caused by demand access." + }, + { + "EventCode": "0x0301", + "EventName": "L2D_CACHE_DM_RD", + "BriefDescription": "This event counts L2D_CACHE caused by demand read access." + }, + { + "EventCode": "0x0302", + "EventName": "L2D_CACHE_DM_WR", + "BriefDescription": "This event counts L2D_CACHE caused by demand write access." + }, + { + "EventCode": "0x0305", + "EventName": "L2D_CACHE_HWPRF_ADJACENT", + "BriefDescription": "This event counts L2D_CACHE caused by hardware adjacent prefetch access." + }, + { + "EventCode": "0x0308", + "EventName": "L2D_CACHE_REFILL_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand access." + }, + { + "EventCode": "0x0309", + "EventName": "L2D_CACHE_REFILL_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand read access." + }, + { + "EventCode": "0x030A", + "EventName": "L2D_CACHE_REFILL_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand write access." + }, + { + "EventCode": "0x030B", + "EventName": "L2D_CACHE_REFILL_DM_WR_EXCL", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand write exclusive access." + }, + { + "EventCode": "0x030C", + "EventName": "L2D_CACHE_REFILL_DM_WR_ATOM", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand write atomic access." + }, + { + "EventCode": "0x030D", + "EventName": "L2D_CACHE_BTC", + "BriefDescription": "This event counts demand access that hits cache line with shared status and requests exclusive access in the Level 1 data and Level 2 caches, causing a coherence access to outside of the Level 1 and Level 2 caches of this PE." + }, + { + "EventCode": "0x03B0", + "EventName": "L2D_CACHE_WB_VICTIM_CLEAN", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by L2 replace where the data is clean. In this case, the data will usually be written to L3 cache." + }, + { + "EventCode": "0x03B1", + "EventName": "L2D_CACHE_WB_NT", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by non-temporal-store." + }, + { + "EventCode": "0x03B2", + "EventName": "L2D_CACHE_WB_DCZVA", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by DC ZVA." + }, + { + "EventCode": "0x03B3", + "EventName": "L2D_CACHE_FB", + "BriefDescription": "This event counts every flush-back (drop) of data from the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD", + "BriefDescription": "This event counts operations that cause a refill of the L2D cache that incurs additional latency." + }, + { + "ArchStdEvent": "L2D_CACHE_MISS", + "BriefDescription": "This event counts demand access that misses in the Level 1 data and Level 2 caches, causing an access to outside of the Level 1 and Level 2 caches of this PE." + }, + { + "ArchStdEvent": "L2D_CACHE_HWPRF", + "BriefDescription": "This event counts access counted by L2D_CACHE that is due to a hardware prefetch." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_HWPRF", + "BriefDescription": "This event counts hardware prefetch counted by L2D_CACHE_HWPRF that causes a refill of the Level 2 cache, or any Level 1 data and instruction cache of this PE, from outside of those caches." + }, + { + "ArchStdEvent": "L2D_CACHE_HIT_RD", + "BriefDescription": "This event counts demand read counted by L2D_CACHE_RD that hits in the Level 2 data cache." + }, + { + "ArchStdEvent": "L2D_CACHE_HIT_WR", + "BriefDescription": "This event counts demand write counted by L2D_CACHE_WR that hits in the Level 2 data cache." + }, + { + "ArchStdEvent": "L2D_CACHE_HIT", + "BriefDescription": "This event counts access counted by L2D_CACHE that hits in the Level 2 data cache." + }, + { + "ArchStdEvent": "L2D_LFB_HIT_RD", + "BriefDescription": "This event counts demand access counted by L2D_CACHE_HIT_RD that hits a recently fetched line in the Level 2 cache." + }, + { + "ArchStdEvent": "L2D_LFB_HIT_WR", + "BriefDescription": "This event counts demand access counted by L2D_CACHE_HIT_WR that hits a recently fetched line in the Level 2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_PRF", + "BriefDescription": "This event counts fetch counted by either Level 2 data hardware prefetch or Level 2 data software prefetch." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_PRF", + "BriefDescription": "This event counts hardware prefetch counted by L2D_CACHE_PRF that causes a refill of the Level 2 data cache from outside of the Level 1 data cache." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_PERCYC", + "BriefDescription": "The counter counts by the number of cache refills counted by L2D_CACHE_REFILL in progress on each Processor cycle." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l3_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l3_cache.json new file mode 100644 index 000000000000..3f3e0d22ac68 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l3_cache.json @@ -0,0 +1,159 @@ +[ + { + "ArchStdEvent": "L3D_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L3 cache, as defined by the sum of L2D_CACHE_REFILL_L3D_CACHE and L2D_CACHE_WB_VICTIM_CLEAN events." + }, + { + "ArchStdEvent": "L3D_CACHE_RD", + "BriefDescription": "This event counts access counted by L3D_CACHE that is a Memory-read operation, as defined by the L2D_CACHE_REFILL_L3D_CACHE events." + }, + { + "EventCode": "0x0390", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L3 cache." + }, + { + "EventCode": "0x0391", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by demand access." + }, + { + "EventCode": "0x0392", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by demand read access." + }, + { + "EventCode": "0x0393", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by demand write access." + }, + { + "EventCode": "0x0394", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_PRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by prefetch access." + }, + { + "EventCode": "0x0395", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_HWPRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by hardware prefetch access." + }, + { + "EventCode": "0x0396", + "EventName": "L2D_CACHE_REFILL_L3D_MISS", + "BriefDescription": "This event counts operations that cause a miss of the L3 cache." + }, + { + "EventCode": "0x0397", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by demand access." + }, + { + "EventCode": "0x0398", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by demand read access." + }, + { + "EventCode": "0x0399", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by demand write access." + }, + { + "EventCode": "0x039A", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by prefetch access." + }, + { + "EventCode": "0x039B", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_HWPRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by hardware prefetch access." + }, + { + "EventCode": "0x039C", + "EventName": "L2D_CACHE_REFILL_L3D_HIT", + "BriefDescription": "This event counts operations that cause a hit of the L3 cache." + }, + { + "EventCode": "0x039D", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by demand access." + }, + { + "EventCode": "0x039E", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by demand read access." + }, + { + "EventCode": "0x039F", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by demand write access." + }, + { + "EventCode": "0x03A0", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_PRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by prefetch access." + }, + { + "EventCode": "0x03A1", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_HWPRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by hardware prefetch access." + }, + { + "EventCode": "0x03A2", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT", + "BriefDescription": "This event counts the number of L3 cache misses where the requests hit the PFTGT buffer." + }, + { + "EventCode": "0x03A3", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT caused by demand access." + }, + { + "EventCode": "0x03A4", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT caused by demand read access." + }, + { + "EventCode": "0x03A5", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT caused by demand write access." + }, + { + "EventCode": "0x03A6", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_L_MEM", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access the memory in the same socket as the requests." + }, + { + "EventCode": "0x03A7", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_FR_MEM", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access the memory in the different socket from the requests." + }, + { + "EventCode": "0x03A8", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_L_L2", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access the different L2 cache from the requests in the same Numa nodes as the requests." + }, + { + "EventCode": "0x03A9", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_NR_L2", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access L2 cache in the different Numa nodes from the requests in the same socket as the requests." + }, + { + "EventCode": "0x03AA", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_NR_L3", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access L3 cache in the different Numa nodes from the requests in the same socket as the requests." + }, + { + "EventCode": "0x03AB", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_FR_L2", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access L2 cache in the different socket from the requests." + }, + { + "EventCode": "0x03AC", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_FR_L3", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access L3 cache in the different socket from the requests." + }, + { + "ArchStdEvent": "L3D_CACHE_LMISS_RD", + "BriefDescription": "This event counts access counted by L3D_CACHE that is not completed by the L3D cache, and a Memory-read operation, as defined by the L2D_CACHE_REFILL_L3D_MISS events." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/ll_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/ll_cache.json new file mode 100644 index 000000000000..a441b84729ab --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/ll_cache.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "LL_CACHE_RD", + "BriefDescription": "This event counts access counted by L3D_CACHE that is a Memory-read operation, as defined by the L2D_CACHE_REFILL_L3D_CACHE events." + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD", + "BriefDescription": "This event counts access counted by L3D_CACHE that is not completed by the L3D cache, and a Memory-read operation, as defined by the L2D_CACHE_REFILL_L3D_MISS events." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/memory.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/memory.json new file mode 100644 index 000000000000..4ef125e3a253 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/memory.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "MEM_ACCESS", + "BriefDescription": "This event counts architecturally executed memory-reading instructions and memory-writing instructions, as defined by the LDST_SPEC events." + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + "BriefDescription": "This event counts architecturally executed memory-reading instructions, as defined by the LD_SPEC events." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pipeline.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pipeline.json new file mode 100644 index 000000000000..3cc3105f4a5e --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pipeline.json @@ -0,0 +1,208 @@ +[ + { + "EventCode": "0x01A0", + "EventName": "EAGA_VAL", + "BriefDescription": "This event counts valid cycles of EAGA pipeline." + }, + { + "EventCode": "0x01A1", + "EventName": "EAGB_VAL", + "BriefDescription": "This event counts valid cycles of EAGB pipeline." + }, + { + "EventCode": "0x01A3", + "EventName": "PRX_VAL", + "BriefDescription": "This event counts valid cycles of PRX pipeline." + }, + { + "EventCode": "0x01A4", + "EventName": "EXA_VAL", + "BriefDescription": "This event counts valid cycles of EXA pipeline." + }, + { + "EventCode": "0x01A5", + "EventName": "EXB_VAL", + "BriefDescription": "This event counts valid cycles of EXB pipeline." + }, + { + "EventCode": "0x01A6", + "EventName": "EXC_VAL", + "BriefDescription": "This event counts valid cycles of EXC pipeline." + }, + { + "EventCode": "0x01A7", + "EventName": "EXD_VAL", + "BriefDescription": "This event counts valid cycles of EXD pipeline." + }, + { + "EventCode": "0x01A8", + "EventName": "FLA_VAL", + "BriefDescription": "This event counts valid cycles of FLA pipeline." + }, + { + "EventCode": "0x01A9", + "EventName": "FLB_VAL", + "BriefDescription": "This event counts valid cycles of FLB pipeline." + }, + { + "EventCode": "0x01AA", + "EventName": "STEA_VAL", + "BriefDescription": "This event counts valid cycles of STEA pipeline." + }, + { + "EventCode": "0x01AB", + "EventName": "STEB_VAL", + "BriefDescription": "This event counts valid cycles of STEB pipeline." + }, + { + "EventCode": "0x01AC", + "EventName": "STFL_VAL", + "BriefDescription": "This event counts valid cycles of STFL pipeline." + }, + { + "EventCode": "0x01AD", + "EventName": "STPX_VAL", + "BriefDescription": "This event counts valid cycles of STPX pipeline." + }, + { + "EventCode": "0x01B0", + "EventName": "FLA_VAL_PRD_CNT", + "BriefDescription": "This event counts the number of 1's in the predicate bits of request in FLA pipeline, where it is corrected so that it becomes 32 when all bits are 1." + }, + { + "EventCode": "0x01B1", + "EventName": "FLB_VAL_PRD_CNT", + "BriefDescription": "This event counts the number of 1's in the predicate bits of request in FLB pipeline, where it is corrected so that it becomes 32 when all bits are 1." + }, + { + "EventCode": "0x01B2", + "EventName": "FLA_VAL_FOR_PRD", + "BriefDescription": "This event counts valid cycles of FLA pipeline." + }, + { + "EventCode": "0x01B3", + "EventName": "FLB_VAL_FOR_PRD", + "BriefDescription": "This event counts valid cycles of FLB pipeline." + }, + { + "EventCode": "0x0240", + "EventName": "L1_PIPE0_VAL", + "BriefDescription": "This event counts valid cycles of L1D cache pipeline#0." + }, + { + "EventCode": "0x0241", + "EventName": "L1_PIPE1_VAL", + "BriefDescription": "This event counts valid cycles of L1D cache pipeline#1." + }, + { + "EventCode": "0x0242", + "EventName": "L1_PIPE2_VAL", + "BriefDescription": "This event counts valid cycles of L1D cache pipeline#2." + }, + { + "EventCode": "0x0250", + "EventName": "L1_PIPE0_COMP", + "BriefDescription": "This event counts completed requests in L1D cache pipeline#0." + }, + { + "EventCode": "0x0251", + "EventName": "L1_PIPE1_COMP", + "BriefDescription": "This event counts completed requests in L1D cache pipeline#1." + }, + { + "EventCode": "0x025A", + "EventName": "L1_PIPE_ABORT_STLD_INTLK", + "BriefDescription": "This event counts aborted requests in L1D pipelines that due to store-load interlock." + }, + { + "EventCode": "0x026C", + "EventName": "L1I_PIPE_COMP", + "BriefDescription": "This event counts completed requests in L1I cache pipeline." + }, + { + "EventCode": "0x026D", + "EventName": "L1I_PIPE_VAL", + "BriefDescription": "This event counts valid cycles of L1I cache pipeline." + }, + { + "EventCode": "0x0278", + "EventName": "L1_PIPE0_VAL_IU_TAG_ADRS_SCE", + "BriefDescription": "This event counts requests in L1D cache pipeline#0 that its sce bit of tagged address is 1." + }, + { + "EventCode": "0x0279", + "EventName": "L1_PIPE1_VAL_IU_TAG_ADRS_SCE", + "BriefDescription": "This event counts requests in L1D cache pipeline#1 that its sce bit of tagged address is 1." + }, + { + "EventCode": "0x02A0", + "EventName": "L1_PIPE0_VAL_IU_NOT_SEC0", + "BriefDescription": "This event counts requests in L1D cache pipeline#0 that its sector cache ID is not 0." + }, + { + "EventCode": "0x02A1", + "EventName": "L1_PIPE1_VAL_IU_NOT_SEC0", + "BriefDescription": "This event counts requests in L1D cache pipeline#1 that its sector cache ID is not 0." + }, + { + "EventCode": "0x02B0", + "EventName": "L1_PIPE_COMP_GATHER_2FLOW", + "BriefDescription": "This event counts the number of times where 2 elements of the gather instructions became 2 flows because 2 elements could not be combined." + }, + { + "EventCode": "0x02B1", + "EventName": "L1_PIPE_COMP_GATHER_1FLOW", + "BriefDescription": "This event counts the number of times where 2 elements of the gather instructions became 1 flow because 2 elements could be combined." + }, + { + "EventCode": "0x02B2", + "EventName": "L1_PIPE_COMP_GATHER_0FLOW", + "BriefDescription": "This event counts the number of times where 2 elements of the gather instructions became 0 flow because both predicate values are 0." + }, + { + "EventCode": "0x02B3", + "EventName": "L1_PIPE_COMP_SCATTER_1FLOW", + "BriefDescription": "This event counts the number of flows of the scatter instructions." + }, + { + "EventCode": "0x02B8", + "EventName": "L1_PIPE0_COMP_PRD_CNT", + "BriefDescription": "This event counts the number of 1's in the predicate bits of request in L1D cache pipeline#0, where it is corrected so that it becomes 64 when all bits are 1." + }, + { + "EventCode": "0x02B9", + "EventName": "L1_PIPE1_COMP_PRD_CNT", + "BriefDescription": "This event counts the number of 1's in the predicate bits of request in L1D cache pipeline#1, where it is corrected so that it becomes 64 when all bits are 1." + }, + { + "EventCode": "0x0330", + "EventName": "L2_PIPE_VAL", + "BriefDescription": "This event counts valid cycles of L2 cache pipeline." + }, + { + "EventCode": "0x0350", + "EventName": "L2_PIPE_COMP_ALL", + "BriefDescription": "This event counts completed requests in L2 cache pipeline." + }, + { + "EventCode": "0x0370", + "EventName": "L2_PIPE_COMP_PF_L2MIB_MCH", + "BriefDescription": "This event counts operations where software or hardware prefetch hits an L2 cache refill buffer allocated by demand access." + }, + { + "ArchStdEvent": "STALL_FRONTEND_TLB", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_MEMBOUND when there is a demand instruction miss in the instruction TLB." + }, + { + "ArchStdEvent": "STALL_BACKEND_TLB", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when there is a demand data miss in the data TLB." + }, + { + "ArchStdEvent": "STALL_BACKEND_ST", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when the backend is stalled waiting for a store." + }, + { + "ArchStdEvent": "STALL_BACKEND_ILOCK", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND when operations are available from the frontend but at least one is not ready to be sent to the backend because of an input dependency." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pmu.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pmu.json new file mode 100644 index 000000000000..65bd6cdd0dd5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pmu.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "PMU_OVFS", + "BriefDescription": "This event counts the event generated each time one of the condition occurs described in Arm Architecture Reference Manual for A-profile architecture. This event is only for output to the trace unit." + }, + { + "ArchStdEvent": "PMU_HOVFS", + "BriefDescription": "This event counts the event generated each time an event is counted by an event counter <n> and all of the condition occur described in Arm Architecture Reference Manual for A-profile architecture. This event is only for output to the trace unit." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/retired.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/retired.json new file mode 100644 index 000000000000..de56aafec2dc --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/retired.json @@ -0,0 +1,30 @@ +[ + { + "ArchStdEvent": "SW_INCR", + "BriefDescription": "This event counts on writes to the PMSWINC register." + }, + { + "ArchStdEvent": "INST_RETIRED", + "BriefDescription": "This event counts every architecturally executed instruction." + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED", + "BriefDescription": "This event counts every write to CONTEXTIDR." + }, + { + "ArchStdEvent": "BR_RETIRED", + "BriefDescription": "This event counts architecturally executed branch instruction." + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "BriefDescription": "This event counts architecturally executed branch instruction which was mispredicted." + }, + { + "ArchStdEvent": "OP_RETIRED", + "BriefDescription": "This event counts every architecturally executed micro-operation." + }, + { + "ArchStdEvent": "UOP_RETIRED", + "BriefDescription": "This event counts micro-operation that would be executed in a Simple sequential execution of the program." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/spec_operation.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/spec_operation.json new file mode 100644 index 000000000000..4841b43e2871 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/spec_operation.json @@ -0,0 +1,171 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED", + "BriefDescription": "This event counts each correction to the predicted program flow that occurs because of a misprediction from, or no prediction from, the branch prediction resources and that relates to instructions that the branch prediction resources are capable of predicting." + }, + { + "ArchStdEvent": "BR_PRED", + "BriefDescription": "This event counts every branch or other change in the program flow that the branch prediction resources are capable of predicting." + }, + { + "ArchStdEvent": "INST_SPEC", + "BriefDescription": "This event counts every architecturally executed instruction." + }, + { + "ArchStdEvent": "OP_SPEC", + "BriefDescription": "This event counts every speculatively executed micro-operation." + }, + { + "ArchStdEvent": "LDREX_SPEC", + "BriefDescription": "This event counts architecturally executed load-exclusive instructions." + }, + { + "ArchStdEvent": "STREX_SPEC", + "BriefDescription": "This event counts architecturally executed store-exclusive instructions." + }, + { + "ArchStdEvent": "LD_SPEC", + "BriefDescription": "This event counts architecturally executed memory-reading instructions, as defined by the LD_RETIRED event." + }, + { + "ArchStdEvent": "ST_SPEC", + "BriefDescription": "This event counts architecturally executed memory-writing instructions, as defined by the ST_RETIRED event. This event counts DCZVA as a store operation." + }, + { + "ArchStdEvent": "LDST_SPEC", + "BriefDescription": "This event counts architecturally executed memory-reading instructions and memory-writing instructions, as defined by the LD_RETIRED and ST_RETIRED events." + }, + { + "ArchStdEvent": "DP_SPEC", + "BriefDescription": "This event counts architecturally executed integer data-processing instructions. See DP_SPEC of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "ASE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD data-processing instructions." + }, + { + "ArchStdEvent": "VFP_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point data-processing instructions." + }, + { + "ArchStdEvent": "PC_WRITE_SPEC", + "BriefDescription": "This event counts only software changes of the PC that defined by the instruction architecturally executed, condition code check pass, software change of the PC event." + }, + { + "ArchStdEvent": "CRYPTO_SPEC", + "BriefDescription": "This event counts architecturally executed cryptographic instructions, except PMULL and VMULL." + }, + { + "ArchStdEvent": "BR_IMMED_SPEC", + "BriefDescription": "This event counts architecturally executed immediate branch instructions." + }, + { + "ArchStdEvent": "BR_RETURN_SPEC", + "BriefDescription": "This event counts architecturally executed procedure return operations that defined by the BR_RETURN_RETIRED event." + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC", + "BriefDescription": "This event counts architecturally executed indirect branch instructions that includes software change of the PC other than exception-generating instructions and immediate branch instructions." + }, + { + "ArchStdEvent": "ISB_SPEC", + "BriefDescription": "This event counts architecturally executed Instruction Synchronization Barrier instructions." + }, + { + "ArchStdEvent": "DSB_SPEC", + "BriefDescription": "This event counts architecturally executed Data Synchronization Barrier instructions." + }, + { + "ArchStdEvent": "DMB_SPEC", + "BriefDescription": "This event counts architecturally executed Data Memory Barrier instructions, excluding the implied barrier operations of load/store operations with release consistency semantics." + }, + { + "ArchStdEvent": "CSDB_SPEC", + "BriefDescription": "This event counts speculatively executed control speculation barrier instructions." + }, + { + "EventCode": "0x0108", + "EventName": "PRD_SPEC", + "BriefDescription": "This event counts architecturally executed operations that using predicate register." + }, + { + "EventCode": "0x0109", + "EventName": "IEL_SPEC", + "BriefDescription": "This event counts architecturally executed inter-element manipulation operations." + }, + { + "EventCode": "0x010A", + "EventName": "IREG_SPEC", + "BriefDescription": "This event counts architecturally executed inter-register manipulation operations." + }, + { + "EventCode": "0x011A", + "EventName": "BC_LD_SPEC", + "BriefDescription": "This event counts architecturally executed SIMD broadcast floating-point load operations." + }, + { + "EventCode": "0x011B", + "EventName": "DCZVA_SPEC", + "BriefDescription": "This event counts architecturally executed zero blocking operations due to the DC ZVA instruction." + }, + { + "EventCode": "0x0121", + "EventName": "EFFECTIVE_INST_SPEC", + "BriefDescription": "This event counts architecturally executed instructions, excluding the MOVPRFX instruction." + }, + { + "EventCode": "0x0123", + "EventName": "PRE_INDEX_SPEC", + "BriefDescription": "This event counts architecturally executed operations that uses pre-index as its addressing mode." + }, + { + "EventCode": "0x0124", + "EventName": "POST_INDEX_SPEC", + "BriefDescription": "This event counts architecturally executed operations that uses post-index as its addressing mode." + }, + { + "EventCode": "0x0139", + "EventName": "UOP_SPLIT", + "BriefDescription": "This event counts the occurrence count of the micro-operation split." + }, + { + "ArchStdEvent": "ASE_INST_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD operations." + }, + { + "ArchStdEvent": "INT_SPEC", + "BriefDescription": "This event counts architecturally executed operations due to scalar, Advanced SIMD, and SVE instructions listed in Integer instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "INT_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed integer divide operation." + }, + { + "ArchStdEvent": "INT_DIV64_SPEC", + "BriefDescription": "This event counts architecturally executed 64-bit integer divide operation." + }, + { + "ArchStdEvent": "INT_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed integer multiply operation." + }, + { + "ArchStdEvent": "INT_MUL64_SPEC", + "BriefDescription": "This event counts architecturally executed integer 64-bit x 64-bit multiply operation." + }, + { + "ArchStdEvent": "INT_MULH64_SPEC", + "BriefDescription": "This event counts architecturally executed integer 64-bit x 64-bit multiply returning high part operation." + }, + { + "ArchStdEvent": "NONFP_SPEC", + "BriefDescription": "This event counts architecturally executed non-floating-point operations." + }, + { + "ArchStdEvent": "INT_SCALE_OPS_SPEC", + "BriefDescription": "This event counts each integer ALU operation counted by SVE_INT_SPEC. See ALU operation counts section of ARMv9 Reference Manual for information on the counter increment for different types of instruction." + }, + { + "ArchStdEvent": "INT_FIXED_OPS_SPEC", + "BriefDescription": "This event counts each integer ALU operation counted by INT_SPEC that is not counted by SVE_INT_SPEC. See ALU operation counts section of ARMv9 Reference Manual for information on the counter increment for different types of instruction." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/stall.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/stall.json new file mode 100644 index 000000000000..5fb81e2a0a07 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/stall.json @@ -0,0 +1,94 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND", + "BriefDescription": "This event counts every cycle counted by the CPU_CYCLES event on that no operation was issued because there are no operations available to issue for this PE from the frontend." + }, + { + "ArchStdEvent": "STALL_BACKEND", + "BriefDescription": "This event counts every cycle counted by the CPU_CYCLES event on that no operation was issued because the backend is unable to accept any operations." + }, + { + "ArchStdEvent": "STALL", + "BriefDescription": "This event counts every cycle that no instruction was dispatched from decode unit." + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND", + "BriefDescription": "This event counts every cycle that no instruction was dispatched from decode unit due to the backend." + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND", + "BriefDescription": "This event counts every cycle that no instruction was dispatched from decode unit due to the frontend." + }, + { + "ArchStdEvent": "STALL_SLOT", + "BriefDescription": "This event counts every cycle that no instruction or operation Slot was dispatched from decode unit." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM", + "BriefDescription": "This event counts every cycle that no instruction was dispatched from decode unit due to memory stall." + }, + { + "ArchStdEvent": "STALL_FRONTEND_MEMBOUND", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND when no instructions are delivered from the memory system." + }, + { + "ArchStdEvent": "STALL_FRONTEND_L1I", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_MEMBOUND when there is a demand instruction miss in the first level of instruction cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_L2I", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_MEMBOUND when there is a demand instruction miss in the second level of instruction cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_MEM", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_MEMBOUND when there is a demand instruction miss in the last level of instruction cache within the PE clock domain or a non-cacheable instruction fetch in progress." + }, + { + "ArchStdEvent": "STALL_FRONTEND_CPUBOUND", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND when the frontend is stalled on a frontend processor resource, not including memory." + }, + { + "ArchStdEvent": "STALL_FRONTEND_FLOW", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_CPUBOUND when the frontend is stalled on unavailability of prediction flow resources." + }, + { + "ArchStdEvent": "STALL_FRONTEND_FLUSH", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_CPUBOUND when the frontend is recovering from a pipeline flush." + }, + { + "ArchStdEvent": "STALL_FRONTEND_RENAME", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_CPUBOUND when operations are available from the frontend but at least one is not ready to be sent to the backend because no rename register is available." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEMBOUND", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND when the backend is waiting for a memory access to complete." + }, + { + "ArchStdEvent": "STALL_BACKEND_L1D", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when there is a demand data miss in L1D cache." + }, + { + "ArchStdEvent": "STALL_BACKEND_L2D", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when there is a demand data miss in L2D cache." + }, + { + "ArchStdEvent": "STALL_BACKEND_CPUBOUND", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND when the backend is stalled on a processor resource, not including memory." + }, + { + "ArchStdEvent": "STALL_BACKEND_BUSY", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND when operations are available from the frontend but the backend is not able to accept an operation because an execution unit is busy." + }, + { + "ArchStdEvent": "STALL_BACKEND_RENAME", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_CPUBOUND when operations are available from the frontend but at least one is not ready to be sent to the backend because no rename register is available." + }, + { + "ArchStdEvent": "STALL_BACKEND_ATOMIC", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when the backend is processing an Atomic operation." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEMCPYSET", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when the backend is processing a Memory Copy or Set instruction." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/sve.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/sve.json new file mode 100644 index 000000000000..e66b5af00f90 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/sve.json @@ -0,0 +1,254 @@ +[ + { + "ArchStdEvent": "SIMD_INST_RETIRED", + "BriefDescription": "This event counts architecturally executed SIMD instructions, excluding the Advanced SIMD scalar instructions and the instructions listed in Non-SIMD SVE instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "SVE_INST_RETIRED", + "BriefDescription": "This event counts architecturally executed SVE instructions, including the instructions listed in Non-SIMD SVE instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "SVE_INST_SPEC", + "BriefDescription": "This event counts architecturally executed SVE instructions, including the instructions listed in Non-SIMD SVE instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "ASE_SVE_INST_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE operations." + }, + { + "ArchStdEvent": "UOP_SPEC", + "BriefDescription": "This event counts all architecturally executed micro-operations." + }, + { + "ArchStdEvent": "SVE_MATH_SPEC", + "BriefDescription": "This event counts architecturally executed math function operations due to the SVE FTSMUL, FTMAD, FTSSEL, and FEXPA instructions." + }, + { + "ArchStdEvent": "FP_SPEC", + "BriefDescription": "This event counts architecturally executed operations due to scalar, Advanced SIMD, and SVE instructions listed in Floating-point instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "FP_FMA_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point fused multiply-add and multiply-subtract operations." + }, + { + "ArchStdEvent": "FP_RECPE_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point reciprocal estimate operations due to the Advanced SIMD scalar, Advanced SIMD vector, and SVE FRECPE and FRSQRTE instructions." + }, + { + "ArchStdEvent": "FP_CVT_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point convert operations due to the scalar, Advanced SIMD, and SVE floating-point conversion instructions listed in Floating-point conversions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "ASE_INT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD integer operations." + }, + { + "ArchStdEvent": "SVE_INT_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer operations." + }, + { + "ArchStdEvent": "ASE_SVE_INT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE integer operations." + }, + { + "ArchStdEvent": "SVE_INT_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer divide operation." + }, + { + "ArchStdEvent": "SVE_INT_DIV64_SPEC", + "BriefDescription": "This event counts architecturally executed SVE 64-bit integer divide operation." + }, + { + "ArchStdEvent": "ASE_INT_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD integer multiply operation." + }, + { + "ArchStdEvent": "SVE_INT_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer multiply operation." + }, + { + "ArchStdEvent": "ASE_SVE_INT_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE integer multiply operations." + }, + { + "ArchStdEvent": "SVE_INT_MUL64_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer 64-bit x 64-bit multiply operation." + }, + { + "ArchStdEvent": "SVE_INT_MULH64_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer 64-bit x 64-bit multiply returning high part operations." + }, + { + "ArchStdEvent": "ASE_NONFP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD non-floating-point operations." + }, + { + "ArchStdEvent": "SVE_NONFP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE non-floating-point operations." + }, + { + "ArchStdEvent": "ASE_SVE_NONFP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE non-floating-point operations." + }, + { + "ArchStdEvent": "ASE_INT_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD integer reduction operation." + }, + { + "ArchStdEvent": "SVE_INT_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer reduction operation." + }, + { + "ArchStdEvent": "ASE_SVE_INT_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE integer reduction operations." + }, + { + "ArchStdEvent": "SVE_PERM_SPEC", + "BriefDescription": "This event counts architecturally executed vector or predicate permute operation." + }, + { + "ArchStdEvent": "SVE_XPIPE_Z2R_SPEC", + "BriefDescription": "This event counts architecturally executed vector to general-purpose scalar cross-pipeline transfer operation." + }, + { + "ArchStdEvent": "SVE_XPIPE_R2Z_SPEC", + "BriefDescription": "This event counts architecturally executed general-purpose scalar to vector cross-pipeline transfer operation." + }, + { + "ArchStdEvent": "SVE_PGEN_SPEC", + "BriefDescription": "This event counts architecturally executed predicate-generating operation." + }, + { + "ArchStdEvent": "SVE_PGEN_FLG_SPEC", + "BriefDescription": "This event counts architecturally executed predicate-generating operation that sets condition flags." + }, + { + "ArchStdEvent": "SVE_PPERM_SPEC", + "BriefDescription": "This event counts architecturally executed predicate permute operation." + }, + { + "ArchStdEvent": "SVE_PRED_SPEC", + "BriefDescription": "This event counts architecturally executed SIMD data-processing and load/store operations due to SVE instructions with a Governing predicate operand that determines the Active elements." + }, + { + "ArchStdEvent": "SVE_MOVPRFX_SPEC", + "BriefDescription": "This event counts architecturally executed operations due to MOVPRFX instructions, whether or not they were fused with the prefixed instruction." + }, + { + "ArchStdEvent": "SVE_MOVPRFX_Z_SPEC", + "BriefDescription": "This event counts architecturally executed operation counted by SVE_MOVPRFX_SPEC where the operation uses zeroing predication." + }, + { + "ArchStdEvent": "SVE_MOVPRFX_M_SPEC", + "BriefDescription": "This event counts architecturally executed operation counted by SVE_MOVPRFX_SPEC where the operation uses merging predication." + }, + { + "ArchStdEvent": "SVE_MOVPRFX_U_SPEC", + "BriefDescription": "This event counts architecturally executed operations due to MOVPRFX instructions that were not fused with the prefixed instruction." + }, + { + "ArchStdEvent": "ASE_SVE_LD_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to SVE and Advanced SIMD load instructions." + }, + { + "ArchStdEvent": "ASE_SVE_ST_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to SVE and Advanced SIMD store instructions." + }, + { + "ArchStdEvent": "PRF_SPEC", + "BriefDescription": "This event counts architecturally executed prefetch operations due to scalar PRFM, PRFUM and SVE PRF instructions." + }, + { + "ArchStdEvent": "BASE_LD_REG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to an instruction that loads a general-purpose register." + }, + { + "ArchStdEvent": "BASE_ST_REG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to an instruction that stores a general-purpose register, excluding the DC ZVA instruction." + }, + { + "ArchStdEvent": "SVE_LDR_REG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to an SVE LDR instruction." + }, + { + "ArchStdEvent": "SVE_STR_REG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to an SVE STR instruction." + }, + { + "ArchStdEvent": "SVE_LDR_PREG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to an SVE LDR (predicate) instruction." + }, + { + "ArchStdEvent": "SVE_STR_PREG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to an SVE STR (predicate) instruction." + }, + { + "ArchStdEvent": "SVE_PRF_CONTIG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that prefetch memory due to an SVE predicated single contiguous element prefetch instruction." + }, + { + "ArchStdEvent": "SVE_LDNT_CONTIG_SPEC", + "BriefDescription": "This event counts architecturally executed operation that reads from memory with a non-temporal hint due to an SVE non-temporal contiguous element load instruction." + }, + { + "ArchStdEvent": "SVE_STNT_CONTIG_SPEC", + "BriefDescription": "This event counts architecturally executed operation that writes to memory with a non-temporal hint due to an SVE non-temporal contiguous element store instruction." + }, + { + "ArchStdEvent": "ASE_SVE_LD_MULTI_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to SVE and Advanced SIMD multiple vector contiguous structure load instructions." + }, + { + "ArchStdEvent": "ASE_SVE_ST_MULTI_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to SVE and Advanced SIMD multiple vector contiguous structure store instructions." + }, + { + "ArchStdEvent": "SVE_LD_GATHER_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to SVE non-contiguous gather-load instructions." + }, + { + "ArchStdEvent": "SVE_ST_SCATTER_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to SVE non-contiguous scatter-store instructions." + }, + { + "ArchStdEvent": "SVE_PRF_GATHER_SPEC", + "BriefDescription": "This event counts architecturally executed operations that prefetch memory due to SVE non-contiguous gather-prefetch instructions." + }, + { + "ArchStdEvent": "SVE_LDFF_SPEC", + "BriefDescription": "This event counts architecturally executed memory read operations due to SVE First-fault and Non-fault load instructions." + }, + { + "ArchStdEvent": "FP_HP_SCALE_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed SVE half-precision arithmetic operations. See FP_HP_SCALE_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by 8, or by 16 for operations that would also be counted by SVE_FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_HP_FIXED_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed v8SIMD&FP half-precision arithmetic operations. See FP_HP_FIXED_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by the number of 16-bit elements for Advanced SIMD operations, or by 1 for scalar operations, and by twice those amounts for operations that would also be counted by FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_SP_SCALE_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed SVE single-precision arithmetic operations. See FP_SP_SCALE_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by 4, or by 8 for operations that would also be counted by SVE_FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_SP_FIXED_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed v8SIMD&FP single-precision arithmetic operations. See FP_SP_FIXED_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by the number of 32-bit elements for Advanced SIMD operations, or by 1 for scalar operations, and by twice those amounts for operations that would also be counted by FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_DP_SCALE_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed SVE double-precision arithmetic operations. See FP_DP_SCALE_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by 2, or by 4 for operations that would also be counted by SVE_FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_DP_FIXED_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed v8SIMD&FP double-precision arithmetic operations. See FP_DP_FIXED_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by 2 for Advanced SIMD operations, or by 1 for scalar operations, and by twice those amounts for operations that would also be counted by FP_FMA_SPEC." + }, + { + "ArchStdEvent": "ASE_SVE_INT_DOT_SPEC", + "BriefDescription": "This event counts architecturally executed microarchitectural Advanced SIMD or SVE integer dot-product operation." + }, + { + "ArchStdEvent": "ASE_SVE_INT_MMLA_SPEC", + "BriefDescription": "This event counts architecturally executed microarchitectural Advanced SIMD or SVE integer matrix multiply operation." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/tlb.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/tlb.json new file mode 100644 index 000000000000..edc7cb8696c8 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/tlb.json @@ -0,0 +1,362 @@ +[ + { + "ArchStdEvent": "L1I_TLB_REFILL", + "BriefDescription": "This event counts operations that cause a TLB refill of the L1I TLB. See L1I_TLB_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL", + "BriefDescription": "This event counts operations that cause a TLB refill of the L1D TLB. See L1D_TLB_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_TLB", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D TLB. See L1D_TLB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1I_TLB", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I TLB. See L1I_TLB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL", + "BriefDescription": "This event counts operations that cause a TLB refill of the L2D TLB. See L2D_TLB_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_TLB", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D TLB. See L2D_TLB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "DTLB_WALK", + "BriefDescription": "This event counts data TLB access with at least one translation table walk." + }, + { + "ArchStdEvent": "ITLB_WALK", + "BriefDescription": "This event counts instruction TLB access with at least one translation table walk." + }, + { + "EventCode": "0x0C00", + "EventName": "L1I_TLB_4K", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 4KB page." + }, + { + "EventCode": "0x0C01", + "EventName": "L1I_TLB_64K", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 64KB page." + }, + { + "EventCode": "0x0C02", + "EventName": "L1I_TLB_2M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 2MB page." + }, + { + "EventCode": "0x0C03", + "EventName": "L1I_TLB_32M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 32MB page." + }, + { + "EventCode": "0x0C04", + "EventName": "L1I_TLB_512M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 512MB page." + }, + { + "EventCode": "0x0C05", + "EventName": "L1I_TLB_1G", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 1GB page." + }, + { + "EventCode": "0x0C06", + "EventName": "L1I_TLB_16G", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 16GB page." + }, + { + "EventCode": "0x0C08", + "EventName": "L1D_TLB_4K", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 4KB page." + }, + { + "EventCode": "0x0C09", + "EventName": "L1D_TLB_64K", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 64KB page." + }, + { + "EventCode": "0x0C0A", + "EventName": "L1D_TLB_2M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 2MB page." + }, + { + "EventCode": "0x0C0B", + "EventName": "L1D_TLB_32M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 32MB page." + }, + { + "EventCode": "0x0C0C", + "EventName": "L1D_TLB_512M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 512MB page." + }, + { + "EventCode": "0x0C0D", + "EventName": "L1D_TLB_1G", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 1GB page." + }, + { + "EventCode": "0x0C0E", + "EventName": "L1D_TLB_16G", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 16GB page." + }, + { + "EventCode": "0x0C10", + "EventName": "L1I_TLB_REFILL_4K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 4KB page." + }, + { + "EventCode": "0x0C11", + "EventName": "L1I_TLB_REFILL_64K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 64KB page." + }, + { + "EventCode": "0x0C12", + "EventName": "L1I_TLB_REFILL_2M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 2MB page." + }, + { + "EventCode": "0x0C13", + "EventName": "L1I_TLB_REFILL_32M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 32MB page." + }, + { + "EventCode": "0x0C14", + "EventName": "L1I_TLB_REFILL_512M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 512MB page." + }, + { + "EventCode": "0x0C15", + "EventName": "L1I_TLB_REFILL_1G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 1GB page." + }, + { + "EventCode": "0x0C16", + "EventName": "L1I_TLB_REFILL_16G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 16GB page." + }, + { + "EventCode": "0x0C18", + "EventName": "L1D_TLB_REFILL_4K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 4KB page." + }, + { + "EventCode": "0x0C19", + "EventName": "L1D_TLB_REFILL_64K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 64KB page." + }, + { + "EventCode": "0x0C1A", + "EventName": "L1D_TLB_REFILL_2M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 2MB page." + }, + { + "EventCode": "0x0C1B", + "EventName": "L1D_TLB_REFILL_32M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 32MB page." + }, + { + "EventCode": "0x0C1C", + "EventName": "L1D_TLB_REFILL_512M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 512MB page." + }, + { + "EventCode": "0x0C1D", + "EventName": "L1D_TLB_REFILL_1G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 1GB page." + }, + { + "EventCode": "0x0C1E", + "EventName": "L1D_TLB_REFILL_16G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 16GB page." + }, + { + "EventCode": "0x0C20", + "EventName": "L2I_TLB_4K", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 4KB page." + }, + { + "EventCode": "0x0C21", + "EventName": "L2I_TLB_64K", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 64KB page." + }, + { + "EventCode": "0x0C22", + "EventName": "L2I_TLB_2M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 2MB page." + }, + { + "EventCode": "0x0C23", + "EventName": "L2I_TLB_32M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 32MB page." + }, + { + "EventCode": "0x0C24", + "EventName": "L2I_TLB_512M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 512MB page." + }, + { + "EventCode": "0x0C25", + "EventName": "L2I_TLB_1G", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 1GB page." + }, + { + "EventCode": "0x0C26", + "EventName": "L2I_TLB_16G", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 16GB page." + }, + { + "EventCode": "0x0C28", + "EventName": "L2D_TLB_4K", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 4KB page." + }, + { + "EventCode": "0x0C29", + "EventName": "L2D_TLB_64K", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 64KB page." + }, + { + "EventCode": "0x0C2A", + "EventName": "L2D_TLB_2M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 2MB page." + }, + { + "EventCode": "0x0C2B", + "EventName": "L2D_TLB_32M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 32MB page." + }, + { + "EventCode": "0x0C2C", + "EventName": "L2D_TLB_512M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 512MB page." + }, + { + "EventCode": "0x0C2D", + "EventName": "L2D_TLB_1G", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 1GB page." + }, + { + "EventCode": "0x0C2E", + "EventName": "L2D_TLB_16G", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 16GB page." + }, + { + "EventCode": "0x0C30", + "EventName": "L2I_TLB_REFILL_4K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2Iin 4KB page." + }, + { + "EventCode": "0x0C31", + "EventName": "L2I_TLB_REFILL_64K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 64KB page." + }, + { + "EventCode": "0x0C32", + "EventName": "L2I_TLB_REFILL_2M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 2MB page." + }, + { + "EventCode": "0x0C33", + "EventName": "L2I_TLB_REFILL_32M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 32MB page." + }, + { + "EventCode": "0x0C34", + "EventName": "L2I_TLB_REFILL_512M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 512MB page." + }, + { + "EventCode": "0x0C35", + "EventName": "L2I_TLB_REFILL_1G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 1GB page." + }, + { + "EventCode": "0x0C36", + "EventName": "L2I_TLB_REFILL_16G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 16GB page." + }, + { + "EventCode": "0x0C38", + "EventName": "L2D_TLB_REFILL_4K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 4KB page." + }, + { + "EventCode": "0x0C39", + "EventName": "L2D_TLB_REFILL_64K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 64KB page." + }, + { + "EventCode": "0x0C3A", + "EventName": "L2D_TLB_REFILL_2M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 2MB page." + }, + { + "EventCode": "0x0C3B", + "EventName": "L2D_TLB_REFILL_32M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 32MB page." + }, + { + "EventCode": "0x0C3C", + "EventName": "L2D_TLB_REFILL_512M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 512MB page." + }, + { + "EventCode": "0x0C3D", + "EventName": "L2D_TLB_REFILL_1G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 1GB page." + }, + { + "EventCode": "0x0C3E", + "EventName": "L2D_TLB_REFILL_16G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 16GB page." + }, + { + "ArchStdEvent": "DTLB_WALK_PERCYC", + "BriefDescription": "This event counts the number of DTLB_WALK events in progress on each Processor cycle." + }, + { + "ArchStdEvent": "ITLB_WALK_PERCYC", + "BriefDescription": "This event counts the number of ITLB_WALK events in progress on each Processor cycle." + }, + { + "ArchStdEvent": "DTLB_STEP", + "BriefDescription": "This event counts translation table walk access made by a refill of the data TLB." + }, + { + "ArchStdEvent": "ITLB_STEP", + "BriefDescription": "This event counts translation table walk access made by a refill of the instruction TLB." + }, + { + "ArchStdEvent": "DTLB_WALK_LARGE", + "BriefDescription": "This event counts translation table walk counted by DTLB_WALK where the result of the walk yields a large page size." + }, + { + "ArchStdEvent": "ITLB_WALK_LARGE", + "BriefDescription": "This event counts translation table walk counted by ITLB_WALK where the result of the walk yields a large page size." + }, + { + "ArchStdEvent": "DTLB_WALK_SMALL", + "BriefDescription": "This event counts translation table walk counted by DTLB_WALK where the result of the walk yields a small page size." + }, + { + "ArchStdEvent": "ITLB_WALK_SMALL", + "BriefDescription": "This event counts translation table walk counted by ITLB_WALK where the result of the walk yields a small page size." + }, + { + "ArchStdEvent": "DTLB_WALK_BLOCK", + "BriefDescription": "This event counts translation table walk counted by DTLB_WALK where the result of the walk yields a Block." + }, + { + "ArchStdEvent": "ITLB_WALK_BLOCK", + "BriefDescription": "This event counts translation table walk counted by ITLB_WALK where the result of the walk yields a Block." + }, + { + "ArchStdEvent": "DTLB_WALK_PAGE", + "BriefDescription": "This event counts translation table walk counted by DTLB_WALK where the result of the walk yields a Page." + }, + { + "ArchStdEvent": "ITLB_WALK_PAGE", + "BriefDescription": "This event counts translation table walk counted by ITLB_WALK where the result of the walk yields a Page." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/trace.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/trace.json new file mode 100644 index 000000000000..0c6e5054c9b5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/trace.json @@ -0,0 +1,18 @@ +[ + { + "ArchStdEvent": "TRB_WRAP", + "BriefDescription": "This event counts the event generated each time the current write pointer is wrapped to the base pointer." + }, + { + "ArchStdEvent": "TRB_TRIG", + "BriefDescription": "This event counts the event generated when a Trace Buffer Extension Trigger Event occurs." + }, + { + "ArchStdEvent": "TRCEXTOUT0", + "BriefDescription": "This event counts the event generated each time an event is signaled by the trace unit external event 0." + }, + { + "ArchStdEvent": "CTI_TRIGOUT4", + "BriefDescription": "This event counts the event generated each time an event is signaled on CTI output trigger 4." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index f4d1ca4d1493..5c846fe90513 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -39,6 +39,7 @@ 0x00000000420f5160,v1,cavium/thunderx2,core 0x00000000430f0af0,v1,cavium/thunderx2,core 0x00000000460f0010,v1,fujitsu/a64fx,core +0x00000000460f0030,v1,fujitsu/monaka,core 0x00000000480fd010,v1,hisilicon/hip08,core 0x00000000500f0000,v1,ampere/emag,core 0x00000000c00fac30,v1,ampere/ampereone,core diff --git a/tools/perf/pmu-events/arch/arm64/recommended.json b/tools/perf/pmu-events/arch/arm64/recommended.json index 210afa856091..a3b4941ae90c 100644 --- a/tools/perf/pmu-events/arch/arm64/recommended.json +++ b/tools/perf/pmu-events/arch/arm64/recommended.json @@ -317,6 +317,11 @@ "EventName": "DMB_SPEC", "BriefDescription": "Barrier speculatively executed, DMB" }, + { + "EventCode": "0x7F", + "EventName": "CSDB_SPEC", + "BriefDescription": "Barrier Speculatively executed, CSDB." + }, { "PublicDescription": "Exception taken, Other synchronous", "EventCode": "0x81", diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index d781a377757a..3e204700b59a 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -430,8 +430,11 @@ class JsonEvent: def to_c_string(self, metric: bool) -> str: """Representation of the event as a C struct initializer.""" + def fix_comment(s: str) -> str: + return s.replace('*/', r'\*\/') + s = self.build_c_string(metric) - return f'{{ { _bcs.offsets[s] } }}, /* {s} */\n' + return f'{{ { _bcs.offsets[s] } }}, /* {fix_comment(s)} */\n' @lru_cache(maxsize=None) @@ -461,12 +464,16 @@ def preprocess_arch_std_files(archpath: str) -> None: """Read in all architecture standard events.""" global _arch_std_events for item in os.scandir(archpath): - if item.is_file() and item.name.endswith('.json'): + if not item.is_file() or not item.name.endswith('.json'): + continue + try: for event in read_json_events(item.path, topic=''): if event.name: _arch_std_events[event.name.lower()] = event if event.metric_name: _arch_std_events[event.metric_name.lower()] = event + except Exception as e: + raise RuntimeError(f'Failure processing \'{item.name}\' in \'{archpath}\'') from e def add_events_table_entries(item: os.DirEntry, topic: str) -> None: @@ -1252,7 +1259,10 @@ def main() -> None: item_path = '/'.join(parents) + ('/' if len(parents) > 0 else '') + item.name if 'test' not in item_path and 'common' not in item_path and item_path not in _args.model.split(','): continue - action(parents, item) + try: + action(parents, item) + except Exception as e: + raise RuntimeError(f'Action failure for \'{item.name}\' in {parents}') from e if item.is_dir(): ftw(item.path, parents + [item.name], action) diff --git a/tools/perf/scripts/Makefile.syscalls b/tools/perf/scripts/Makefile.syscalls new file mode 100644 index 000000000000..8bf55333262e --- /dev/null +++ b/tools/perf/scripts/Makefile.syscalls @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: GPL-2.0 +# This Makefile generates headers in +# tools/perf/arch/$(SRCARCH)/include/generated/asm from the architecture's +# syscall table. This will either be from the generic syscall table, or from a +# table that is specific to that architecture. + +PHONY := all +all: + +obj := $(OUTPUT)arch/$(SRCARCH)/include/generated/asm + +syscall_abis_32 := common,32 +syscall_abis_64 := common,64 +syscalltbl := $(srctree)/tools/scripts/syscall.tbl + +# let architectures override $(syscall_abis_%) and $(syscalltbl) +-include $(srctree)/tools/perf/arch/$(SRCARCH)/entry/syscalls/Makefile.syscalls +include $(srctree)/tools/build/Build.include +-include $(srctree)/tools/perf/arch/$(SRCARCH)/entry/syscalls/Kbuild + +systbl := $(srctree)/tools/perf/scripts/syscalltbl.sh + +syscall-y := $(addprefix $(obj)/, $(syscall-y)) + +# Remove stale wrappers when the corresponding files are removed from generic-y +old-headers := $(wildcard $(obj)/*.h) +unwanted := $(filter-out $(syscall-y),$(old-headers)) + +quiet_cmd_remove = REMOVE $(unwanted) + cmd_remove = rm -f $(unwanted) + +quiet_cmd_systbl = SYSTBL $@ + cmd_systbl = $(CONFIG_SHELL) $(systbl) \ + $(if $(systbl-args-$*),$(systbl-args-$*),$(systbl-args)) \ + --abis $(subst $(space),$(comma),$(strip $(syscall_abis_$*))) \ + $< $@ + +all: $(syscall-y) + $(if $(unwanted),$(call cmd,remove)) + @: + +$(obj)/syscalls_%.h: $(syscalltbl) $(systbl) FORCE + $(call if_changed,systbl) + +targets := $(syscall-y) + +# Create output directory. Skip it if at least one old header exists +# since we know the output directory already exists. +ifeq ($(old-headers),) +$(shell mkdir -p $(obj)) +endif + +PHONY += FORCE + +FORCE: + +existing-targets := $(wildcard $(sort $(targets))) + +-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd) + +.PHONY: $(PHONY) diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c index 01f54d6724a5..60dcfe56d4d9 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c @@ -24,16 +24,6 @@ #include "../../../util/srcline.h" #include "../../../util/srccode.h" -#if PY_MAJOR_VERSION < 3 -#define _PyCapsule_GetPointer(arg1, arg2) \ - PyCObject_AsVoidPtr(arg1) -#define _PyBytes_FromStringAndSize(arg1, arg2) \ - PyString_FromStringAndSize((arg1), (arg2)) -#define _PyUnicode_AsUTF8(arg) \ - PyString_AsString(arg) - -PyMODINIT_FUNC initperf_trace_context(void); -#else #define _PyCapsule_GetPointer(arg1, arg2) \ PyCapsule_GetPointer((arg1), (arg2)) #define _PyBytes_FromStringAndSize(arg1, arg2) \ @@ -42,7 +32,6 @@ PyMODINIT_FUNC initperf_trace_context(void); PyUnicode_AsUTF8(arg) PyMODINIT_FUNC PyInit_perf_trace_context(void); -#endif static struct scripting_context *get_args(PyObject *args, const char *name, PyObject **arg2) { @@ -104,7 +93,7 @@ static PyObject *perf_sample_insn(PyObject *obj, PyObject *args) if (c->sample->ip && !c->sample->insn_len && thread__maps(c->al->thread)) { struct machine *machine = maps__machine(thread__maps(c->al->thread)); - script_fetch_insn(c->sample, c->al->thread, machine); + script_fetch_insn(c->sample, c->al->thread, machine, /*native_arch=*/true); } if (!c->sample->insn_len) Py_RETURN_NONE; /* N.B. This is a return statement */ @@ -213,12 +202,6 @@ static PyMethodDef ContextMethods[] = { { NULL, NULL, 0, NULL} }; -#if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC initperf_trace_context(void) -{ - (void) Py_InitModule("perf_trace_context", ContextMethods); -} -#else PyMODINIT_FUNC PyInit_perf_trace_context(void) { static struct PyModuleDef moduledef = { @@ -240,4 +223,3 @@ PyMODINIT_FUNC PyInit_perf_trace_context(void) return mod; } -#endif diff --git a/tools/perf/scripts/python/mem-phys-addr.py b/tools/perf/scripts/python/mem-phys-addr.py index 1f332e72b9b0..5e237a5a5f1b 100644 --- a/tools/perf/scripts/python/mem-phys-addr.py +++ b/tools/perf/scripts/python/mem-phys-addr.py @@ -3,98 +3,125 @@ # # Copyright (c) 2018, Intel Corporation. -from __future__ import division -from __future__ import print_function - import os import sys -import struct import re import bisect import collections +from dataclasses import dataclass +from typing import (Dict, Optional) sys.path.append(os.environ['PERF_EXEC_PATH'] + \ - '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') -#physical address ranges for System RAM -system_ram = [] -#physical address ranges for Persistent Memory -pmem = [] -#file object for proc iomem -f = None -#Count for each type of memory -load_mem_type_cnt = collections.Counter() -#perf event name -event_name = None +@dataclass(frozen=True) +class IomemEntry: + """Read from a line in /proc/iomem""" + begin: int + end: int + indent: int + label: str + +# Physical memory layout from /proc/iomem. Key is the indent and then +# a list of ranges. +iomem: Dict[int, list[IomemEntry]] = collections.defaultdict(list) +# Child nodes from the iomem parent. +children: Dict[IomemEntry, set[IomemEntry]] = collections.defaultdict(set) +# Maximum indent seen before an entry in the iomem file. +max_indent: int = 0 +# Count for each range of memory. +load_mem_type_cnt: Dict[IomemEntry, int] = collections.Counter() +# Perf event name set from the first sample in the data. +event_name: Optional[str] = None def parse_iomem(): - global f - f = open('/proc/iomem', 'r') - for i, j in enumerate(f): - m = re.split('-|:',j,2) - if m[2].strip() == 'System RAM': - system_ram.append(int(m[0], 16)) - system_ram.append(int(m[1], 16)) - if m[2].strip() == 'Persistent Memory': - pmem.append(int(m[0], 16)) - pmem.append(int(m[1], 16)) + """Populate iomem from /proc/iomem file""" + global iomem + global max_indent + global children + with open('/proc/iomem', 'r', encoding='ascii') as f: + for line in f: + indent = 0 + while line[indent] == ' ': + indent += 1 + if indent > max_indent: + max_indent = indent + m = re.split('-|:', line, 2) + begin = int(m[0], 16) + end = int(m[1], 16) + label = m[2].strip() + entry = IomemEntry(begin, end, indent, label) + # Before adding entry, search for a parent node using its begin. + if indent > 0: + parent = find_memory_type(begin) + assert parent, f"Given indent expected a parent for {label}" + children[parent].add(entry) + iomem[indent].append(entry) + +def find_memory_type(phys_addr) -> Optional[IomemEntry]: + """Search iomem for the range containing phys_addr with the maximum indent""" + for i in range(max_indent, -1, -1): + if i not in iomem: + continue + position = bisect.bisect_right(iomem[i], phys_addr, + key=lambda entry: entry.begin) + if position is None: + continue + iomem_entry = iomem[i][position-1] + if iomem_entry.begin <= phys_addr <= iomem_entry.end: + return iomem_entry + print(f"Didn't find {phys_addr}") + return None def print_memory_type(): - print("Event: %s" % (event_name)) - print("%-40s %10s %10s\n" % ("Memory type", "count", "percentage"), end='') - print("%-40s %10s %10s\n" % ("----------------------------------------", - "-----------", "-----------"), - end=''); - total = sum(load_mem_type_cnt.values()) - for mem_type, count in sorted(load_mem_type_cnt.most_common(), \ - key = lambda kv: (kv[1], kv[0]), reverse = True): - print("%-40s %10d %10.1f%%\n" % - (mem_type, count, 100 * count / total), - end='') + print(f"Event: {event_name}") + print(f"{'Memory type':<40} {'count':>10} {'percentage':>10}") + print(f"{'-' * 40:<40} {'-' * 10:>10} {'-' * 10:>10}") + total = sum(load_mem_type_cnt.values()) + # Add count from children into the parent. + for i in range(max_indent, -1, -1): + if i not in iomem: + continue + for entry in iomem[i]: + global children + for child in children[entry]: + if load_mem_type_cnt[child] > 0: + load_mem_type_cnt[entry] += load_mem_type_cnt[child] + + def print_entries(entries): + """Print counts from parents down to their children""" + global children + for entry in sorted(entries, + key = lambda entry: load_mem_type_cnt[entry], + reverse = True): + count = load_mem_type_cnt[entry] + if count > 0: + mem_type = ' ' * entry.indent + f"{entry.begin:x}-{entry.end:x} : {entry.label}" + percent = 100 * count / total + print(f"{mem_type:<40} {count:>10} {percent:>10.1f}") + print_entries(children[entry]) + + print_entries(iomem[0]) def trace_begin(): - parse_iomem() + parse_iomem() def trace_end(): - print_memory_type() - f.close() - -def is_system_ram(phys_addr): - #/proc/iomem is sorted - position = bisect.bisect(system_ram, phys_addr) - if position % 2 == 0: - return False - return True - -def is_persistent_mem(phys_addr): - position = bisect.bisect(pmem, phys_addr) - if position % 2 == 0: - return False - return True - -def find_memory_type(phys_addr): - if phys_addr == 0: - return "N/A" - if is_system_ram(phys_addr): - return "System RAM" - - if is_persistent_mem(phys_addr): - return "Persistent Memory" - - #slow path, search all - f.seek(0, 0) - for j in f: - m = re.split('-|:',j,2) - if int(m[0], 16) <= phys_addr <= int(m[1], 16): - return m[2] - return "N/A" + print_memory_type() def process_event(param_dict): - name = param_dict["ev_name"] - sample = param_dict["sample"] - phys_addr = sample["phys_addr"] + if "sample" not in param_dict: + return - global event_name - if event_name == None: - event_name = name - load_mem_type_cnt[find_memory_type(phys_addr)] += 1 + sample = param_dict["sample"] + if "phys_addr" not in sample: + return + + phys_addr = sample["phys_addr"] + entry = find_memory_type(phys_addr) + if entry: + load_mem_type_cnt[entry] += 1 + + global event_name + if event_name is None: + event_name = param_dict["ev_name"] diff --git a/tools/perf/scripts/syscalltbl.sh b/tools/perf/scripts/syscalltbl.sh new file mode 100755 index 000000000000..1ce0d5aa8b50 --- /dev/null +++ b/tools/perf/scripts/syscalltbl.sh @@ -0,0 +1,86 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate a syscall table header. +# +# Each line of the syscall table should have the following format: +# +# NR ABI NAME [NATIVE] [COMPAT] +# +# NR syscall number +# ABI ABI name +# NAME syscall name +# NATIVE native entry point (optional) +# COMPAT compat entry point (optional) + +set -e + +usage() { + echo >&2 "usage: $0 [--abis ABIS] INFILE OUTFILE" >&2 + echo >&2 + echo >&2 " INFILE input syscall table" + echo >&2 " OUTFILE output header file" + echo >&2 + echo >&2 "options:" + echo >&2 " --abis ABIS ABI(s) to handle (By default, all lines are handled)" + exit 1 +} + +# default unless specified by options +abis= + +while [ $# -gt 0 ] +do + case $1 in + --abis) + abis=$(echo "($2)" | tr ',' '|') + shift 2;; + -*) + echo "$1: unknown option" >&2 + usage;; + *) + break;; + esac +done + +if [ $# -ne 2 ]; then + usage +fi + +infile="$1" +outfile="$2" + +nxt=0 + +syscall_macro() { + nr="$1" + name="$2" + + echo " [$nr] = \"$name\"," +} + +emit() { + nr="$1" + entry="$2" + + syscall_macro "$nr" "$entry" +} + +echo "static const char *const syscalltbl[] = {" > $outfile + +sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX) +grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | sort -n > $sorted_table + +max_nr=0 +# the params are: nr abi name entry compat +# use _ for intentionally unused variables according to SC2034 +while read nr _ name _ _; do + emit "$nr" "$name" >> $outfile + max_nr=$nr +done < $sorted_table + +rm -f $sorted_table + +echo "};" >> $outfile + +echo "#define SYSCALLTBL_MAX_ID ${max_nr}" >> $outfile diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index ec4e1f034742..4bf8d3f5eae7 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -5,10 +5,10 @@ perf-test-y += tests-scripts.o perf-test-y += parse-events.o perf-test-y += dso-data.o perf-test-y += vmlinux-kallsyms.o -perf-test-$(CONFIG_LIBTRACEEVENT) += openat-syscall.o -perf-test-$(CONFIG_LIBTRACEEVENT) += openat-syscall-all-cpus.o +perf-test-y += openat-syscall.o +perf-test-y += openat-syscall-all-cpus.o perf-test-$(CONFIG_LIBTRACEEVENT) += openat-syscall-tp-fields.o -perf-test-$(CONFIG_LIBTRACEEVENT) += mmap-basic.o +perf-test-y += mmap-basic.o perf-test-y += perf-record.o perf-test-y += evsel-roundtrip-name.o perf-test-$(CONFIG_LIBTRACEEVENT) += evsel-tp-sched.o diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 4751dd3c6f67..14d30a5053be 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -42,6 +42,8 @@ static bool dont_fork; /* Fork the tests in parallel and wait for their completion. */ static bool sequential; +/* Number of times each test is run. */ +static unsigned int runs_per_test = 1; const char *dso_to_test; const char *test_objdump_path = "objdump"; @@ -60,11 +62,9 @@ static struct test_suite *arch_tests[] = { static struct test_suite *generic_tests[] = { &suite__vmlinux_matches_kallsyms, -#ifdef HAVE_LIBTRACEEVENT &suite__openat_syscall_event, &suite__openat_syscall_event_on_all_cpus, &suite__basic_mmap, -#endif &suite__mem, &suite__parse_events, &suite__expr, @@ -151,58 +151,51 @@ static struct test_workload *workloads[] = { #define workloads__for_each(workload) \ for (unsigned i = 0; i < ARRAY_SIZE(workloads) && ({ workload = workloads[i]; 1; }); i++) -static int num_subtests(const struct test_suite *t) +#define test_suite__for_each_test_case(suite, idx) \ + for (idx = 0; (suite)->test_cases && (suite)->test_cases[idx].name != NULL; idx++) + +static int test_suite__num_test_cases(const struct test_suite *t) { int num; - if (!t->test_cases) - return 0; - - num = 0; - while (t->test_cases[num].name) - num++; + test_suite__for_each_test_case(t, num); return num; } -static bool has_subtests(const struct test_suite *t) -{ - return num_subtests(t) > 1; -} - -static const char *skip_reason(const struct test_suite *t, int subtest) +static const char *skip_reason(const struct test_suite *t, int test_case) { if (!t->test_cases) return NULL; - return t->test_cases[subtest >= 0 ? subtest : 0].skip_reason; + return t->test_cases[test_case >= 0 ? test_case : 0].skip_reason; } -static const char *test_description(const struct test_suite *t, int subtest) +static const char *test_description(const struct test_suite *t, int test_case) { - if (t->test_cases && subtest >= 0) - return t->test_cases[subtest].desc; + if (t->test_cases && test_case >= 0) + return t->test_cases[test_case].desc; return t->desc; } -static test_fnptr test_function(const struct test_suite *t, int subtest) +static test_fnptr test_function(const struct test_suite *t, int test_case) { - if (subtest <= 0) + if (test_case <= 0) return t->test_cases[0].run_case; - return t->test_cases[subtest].run_case; + return t->test_cases[test_case].run_case; } -static bool test_exclusive(const struct test_suite *t, int subtest) +static bool test_exclusive(const struct test_suite *t, int test_case) { - if (subtest <= 0) + if (test_case <= 0) return t->test_cases[0].exclusive; - return t->test_cases[subtest].exclusive; + return t->test_cases[test_case].exclusive; } -static bool perf_test__matches(const char *desc, int curr, int argc, const char *argv[]) +static bool perf_test__matches(const char *desc, int suite_num, int argc, const char *argv[]) { int i; @@ -214,7 +207,7 @@ static bool perf_test__matches(const char *desc, int curr, int argc, const char long nr = strtoul(argv[i], &end, 10); if (*end == '\0') { - if (nr == curr + 1) + if (nr == suite_num + 1) return true; continue; } @@ -229,8 +222,8 @@ static bool perf_test__matches(const char *desc, int curr, int argc, const char struct child_test { struct child_process process; struct test_suite *test; - int test_num; - int subtest; + int suite_num; + int test_case_num; }; static jmp_buf run_test_jmp_buf; @@ -260,7 +253,7 @@ static int run_test_child(struct child_process *process) pr_debug("--- start ---\n"); pr_debug("test child forked, pid %d\n", getpid()); - err = test_function(child->test, child->subtest)(child->test, child->subtest); + err = test_function(child->test, child->test_case_num)(child->test, child->test_case_num); pr_debug("---- end(%d) ----\n", err); err_out: @@ -272,15 +265,16 @@ err_out: #define TEST_RUNNING -3 -static int print_test_result(struct test_suite *t, int i, int subtest, int result, int width, - int running) +static int print_test_result(struct test_suite *t, int curr_suite, int curr_test_case, + int result, int width, int running) { - if (has_subtests(t)) { + if (test_suite__num_test_cases(t) > 1) { int subw = width > 2 ? width - 2 : width; - pr_info("%3d.%1d: %-*s:", i + 1, subtest + 1, subw, test_description(t, subtest)); + pr_info("%3d.%1d: %-*s:", curr_suite + 1, curr_test_case + 1, subw, + test_description(t, curr_test_case)); } else - pr_info("%3d: %-*s:", i + 1, width, test_description(t, subtest)); + pr_info("%3d: %-*s:", curr_suite + 1, width, test_description(t, curr_test_case)); switch (result) { case TEST_RUNNING: @@ -290,7 +284,7 @@ static int print_test_result(struct test_suite *t, int i, int subtest, int resul pr_info(" Ok\n"); break; case TEST_SKIP: { - const char *reason = skip_reason(t, subtest); + const char *reason = skip_reason(t, curr_test_case); if (reason) color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", reason); @@ -312,7 +306,7 @@ static void finish_test(struct child_test **child_tests, int running_test, int c { struct child_test *child_test = child_tests[running_test]; struct test_suite *t; - int i, subi, err; + int curr_suite, curr_test_case, err; bool err_done = false; struct strbuf err_output = STRBUF_INIT; int last_running = -1; @@ -323,15 +317,15 @@ static void finish_test(struct child_test **child_tests, int running_test, int c return; } t = child_test->test; - i = child_test->test_num; - subi = child_test->subtest; + curr_suite = child_test->suite_num; + curr_test_case = child_test->test_case_num; err = child_test->process.err; /* * For test suites with subtests, display the suite name ahead of the * sub test names. */ - if (has_subtests(t) && subi == 0) - pr_info("%3d: %-*s:\n", i + 1, width, test_description(t, -1)); + if (test_suite__num_test_cases(t) > 1 && curr_test_case == 0) + pr_info("%3d: %-*s:\n", curr_suite + 1, width, test_description(t, -1)); /* * Busy loop reading from the child's stdout/stderr that are set to be @@ -340,10 +334,11 @@ static void finish_test(struct child_test **child_tests, int running_test, int c if (err > 0) fcntl(err, F_SETFL, O_NONBLOCK); if (verbose > 1) { - if (has_subtests(t)) - pr_info("%3d.%1d: %s:\n", i + 1, subi + 1, test_description(t, subi)); + if (test_suite__num_test_cases(t) > 1) + pr_info("%3d.%1d: %s:\n", curr_suite + 1, curr_test_case + 1, + test_description(t, curr_test_case)); else - pr_info("%3d: %s:\n", i + 1, test_description(t, -1)); + pr_info("%3d: %s:\n", curr_suite + 1, test_description(t, -1)); } while (!err_done) { struct pollfd pfds[1] = { @@ -368,7 +363,8 @@ static void finish_test(struct child_test **child_tests, int running_test, int c */ fprintf(debug_file(), PERF_COLOR_DELETE_LINE); } - print_test_result(t, i, subi, TEST_RUNNING, width, running); + print_test_result(t, curr_suite, curr_test_case, TEST_RUNNING, + width, running); last_running = running; } } @@ -406,14 +402,14 @@ static void finish_test(struct child_test **child_tests, int running_test, int c fprintf(stderr, "%s", err_output.buf); strbuf_release(&err_output); - print_test_result(t, i, subi, ret, width, /*running=*/0); + print_test_result(t, curr_suite, curr_test_case, ret, width, /*running=*/0); if (err > 0) close(err); zfree(&child_tests[running_test]); } -static int start_test(struct test_suite *test, int i, int subi, struct child_test **child, - int width, int pass) +static int start_test(struct test_suite *test, int curr_suite, int curr_test_case, + struct child_test **child, int width, int pass) { int err; @@ -421,17 +417,18 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes if (dont_fork) { if (pass == 1) { pr_debug("--- start ---\n"); - err = test_function(test, subi)(test, subi); + err = test_function(test, curr_test_case)(test, curr_test_case); pr_debug("---- end ----\n"); - print_test_result(test, i, subi, err, width, /*running=*/0); + print_test_result(test, curr_suite, curr_test_case, err, width, + /*running=*/0); } return 0; } - if (pass == 1 && !sequential && test_exclusive(test, subi)) { + if (pass == 1 && !sequential && test_exclusive(test, curr_test_case)) { /* When parallel, skip exclusive tests on the first pass. */ return 0; } - if (pass != 1 && (sequential || !test_exclusive(test, subi))) { + if (pass != 1 && (sequential || !test_exclusive(test, curr_test_case))) { /* Sequential and non-exclusive tests were run on the first pass. */ return 0; } @@ -440,8 +437,8 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes return -ENOMEM; (*child)->test = test; - (*child)->test_num = i; - (*child)->subtest = subi; + (*child)->suite_num = curr_suite; + (*child)->test_case_num = curr_test_case; (*child)->process.pid = -1; (*child)->process.no_stdin = 1; if (verbose <= 0) { @@ -481,20 +478,16 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], int err = 0; for (struct test_suite **t = suites; *t; t++) { - int len = strlen(test_description(*t, -1)); + int i, len = strlen(test_description(*t, -1)); if (width < len) width = len; - if (has_subtests(*t)) { - for (int subi = 0, subn = num_subtests(*t); subi < subn; subi++) { - len = strlen(test_description(*t, subi)); - if (width < len) - width = len; - num_tests++; - } - } else { - num_tests++; + test_suite__for_each_test_case(*t, i) { + len = strlen(test_description(*t, i)); + if (width < len) + width = len; + num_tests += runs_per_test; } } child_tests = calloc(num_tests, sizeof(*child_tests)); @@ -512,7 +505,7 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], continue; pr_debug3("Killing %d pid %d\n", - child_test->test_num + 1, + child_test->suite_num + 1, child_test->process.pid); kill(child_test->process.pid, err); } @@ -528,50 +521,48 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], */ for (int pass = 1; pass <= 2; pass++) { int child_test_num = 0; - int i = 0; + int curr_suite = 0; - for (struct test_suite **t = suites; *t; t++) { - int curr = i++; + for (struct test_suite **t = suites; *t; t++, curr_suite++) { + int curr_test_case; - if (!perf_test__matches(test_description(*t, -1), curr, argc, argv)) { + if (!perf_test__matches(test_description(*t, -1), curr_suite, argc, argv)) { /* * Test suite shouldn't be run based on - * description. See if subtest should. + * description. See if any test case should. */ bool skip = true; - for (int subi = 0, subn = num_subtests(*t); subi < subn; subi++) { - if (perf_test__matches(test_description(*t, subi), - curr, argc, argv)) + test_suite__for_each_test_case(*t, curr_test_case) { + if (perf_test__matches(test_description(*t, curr_test_case), + curr_suite, argc, argv)) { skip = false; + break; + } } - if (skip) continue; } - if (intlist__find(skiplist, i)) { - pr_info("%3d: %-*s:", curr + 1, width, test_description(*t, -1)); + if (intlist__find(skiplist, curr_suite + 1)) { + pr_info("%3d: %-*s:", curr_suite + 1, width, + test_description(*t, -1)); color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); continue; } - if (!has_subtests(*t)) { - err = start_test(*t, curr, -1, &child_tests[child_test_num++], - width, pass); - if (err) - goto err_out; - continue; - } - for (int subi = 0, subn = num_subtests(*t); subi < subn; subi++) { - if (!perf_test__matches(test_description(*t, subi), - curr, argc, argv)) - continue; + for (unsigned int run = 0; run < runs_per_test; run++) { + test_suite__for_each_test_case(*t, curr_test_case) { + if (!perf_test__matches(test_description(*t, curr_test_case), + curr_suite, argc, argv)) + continue; - err = start_test(*t, curr, subi, &child_tests[child_test_num++], - width, pass); - if (err) - goto err_out; + err = start_test(*t, curr_suite, curr_test_case, + &child_tests[child_test_num++], + width, pass); + if (err) + goto err_out; + } } } if (!sequential) { @@ -592,25 +583,24 @@ err_out: return err; } -static int perf_test__list(struct test_suite **suites, int argc, const char **argv) +static int perf_test__list(FILE *fp, struct test_suite **suites, int argc, const char **argv) { - int i = 0; + int curr_suite = 0; - for (struct test_suite **t = suites; *t; t++) { - int curr = i++; + for (struct test_suite **t = suites; *t; t++, curr_suite++) { + int curr_test_case; - if (!perf_test__matches(test_description(*t, -1), curr, argc, argv)) + if (!perf_test__matches(test_description(*t, -1), curr_suite, argc, argv)) continue; - pr_info("%3d: %s\n", i, test_description(*t, -1)); + fprintf(fp, "%3d: %s\n", curr_suite + 1, test_description(*t, -1)); - if (has_subtests(*t)) { - int subn = num_subtests(*t); - int subi; + if (test_suite__num_test_cases(*t) <= 1) + continue; - for (subi = 0; subi < subn; subi++) - pr_info("%3d:%1d: %s\n", i, subi + 1, - test_description(*t, subi)); + test_suite__for_each_test_case(*t, curr_test_case) { + fprintf(fp, "%3d.%1d: %s\n", curr_suite + 1, curr_test_case + 1, + test_description(*t, curr_test_case)); } } return 0; @@ -667,27 +657,24 @@ static struct test_suite **build_suites(void) if (suites[2] == NULL) suites[2] = create_script_test_suites(); -#define for_each_test(t) \ +#define for_each_suite(suite) \ for (size_t i = 0, j = 0; i < ARRAY_SIZE(suites); i++, j = 0) \ - while ((t = suites[i][j++]) != NULL) + while ((suite = suites[i][j++]) != NULL) - for_each_test(t) + for_each_suite(t) num_suites++; result = calloc(num_suites + 1, sizeof(struct test_suite *)); for (int pass = 1; pass <= 2; pass++) { - for_each_test(t) { + for_each_suite(t) { bool exclusive = false; + int curr_test_case; - if (!has_subtests(t)) { - exclusive = test_exclusive(t, -1); - } else { - for (int subi = 0, subn = num_subtests(t); subi < subn; subi++) { - if (test_exclusive(t, subi)) { - exclusive = true; - break; - } + test_suite__for_each_test_case(t, curr_test_case) { + if (test_exclusive(t, curr_test_case)) { + exclusive = true; + break; } } if ((!exclusive && pass == 1) || (exclusive && pass == 2)) @@ -695,7 +682,7 @@ static struct test_suite **build_suites(void) } } return result; -#undef for_each_test +#undef for_each_suite } int cmd_test(int argc, const char **argv) @@ -715,6 +702,8 @@ int cmd_test(int argc, const char **argv) "Do not fork for testcase"), OPT_BOOLEAN('S', "sequential", &sequential, "Run the tests one after another rather than in parallel"), + OPT_UINTEGER('r', "runs-per-test", &runs_per_test, + "Run each test the given number of times, default 1"), OPT_STRING('w', "workload", &workload, "work", "workload to run for testing, use '--list-workloads' to list the available ones."), OPT_BOOLEAN(0, "list-workloads", &list_workloads, "List the available builtin workloads to use with -w/--workload"), OPT_STRING(0, "dso", &dso_to_test, "dso", "dso to test"), @@ -738,7 +727,7 @@ int cmd_test(int argc, const char **argv) argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0); if (argc >= 1 && !strcmp(argv[0], "list")) { suites = build_suites(); - ret = perf_test__list(suites, argc - 1, argv + 1); + ret = perf_test__list(stdout, suites, argc - 1, argv + 1); free(suites); return ret; } diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 27c82cfb7e7d..b1abb34d7818 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <linux/kconfig.h> #include <linux/kernel.h> #include <linux/types.h> #include <inttypes.h> @@ -8,6 +9,7 @@ #include <stdio.h> #include <string.h> #include <sys/param.h> +#include <sys/utsname.h> #include <perf/cpumap.h> #include <perf/evlist.h> #include <perf/mmap.h> @@ -176,16 +178,104 @@ static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr) return err; } +/* + * Only gets GNU objdump version. Returns 0 for llvm-objdump. + */ +static int objdump_version(void) +{ + size_t line_len; + char cmd[PATH_MAX * 2]; + char *line = NULL; + const char *fmt; + FILE *f; + int ret; + + int version_tmp, version_num = 0; + char *version = 0, *token; + + fmt = "%s --version"; + ret = snprintf(cmd, sizeof(cmd), fmt, test_objdump_path); + if (ret <= 0 || (size_t)ret >= sizeof(cmd)) + return -1; + /* Ignore objdump errors */ + strcat(cmd, " 2>/dev/null"); + f = popen(cmd, "r"); + if (!f) { + pr_debug("popen failed\n"); + return -1; + } + /* Get first line of objdump --version output */ + ret = getline(&line, &line_len, f); + pclose(f); + if (ret < 0) { + pr_debug("getline failed\n"); + return -1; + } + + token = strsep(&line, " "); + if (token != NULL && !strcmp(token, "GNU")) { + // version is last part of first line of objdump --version output. + while ((token = strsep(&line, " "))) + version = token; + + // Convert version into a format we can compare with + token = strsep(&version, "."); + version_num = atoi(token); + if (version_num) + version_num *= 10000; + + token = strsep(&version, "."); + version_tmp = atoi(token); + if (token) + version_num += version_tmp * 100; + + token = strsep(&version, "."); + version_tmp = atoi(token); + if (token) + version_num += version_tmp; + } + + return version_num; +} + static int read_via_objdump(const char *filename, u64 addr, void *buf, size_t len) { + u64 stop_address = addr + len; + struct utsname uname_buf; char cmd[PATH_MAX * 2]; const char *fmt; FILE *f; int ret; + ret = uname(&uname_buf); + if (ret) { + pr_debug("uname failed\n"); + return -1; + } + + if (!strncmp(uname_buf.machine, "riscv", 5)) { + int version = objdump_version(); + + /* Default to this workaround if version parsing fails */ + if (version < 0 || version > 24100) { + /* + * Starting at riscv objdump version 2.41, dumping in + * the middle of an instruction is not supported. riscv + * instructions are aligned along 2-byte intervals and + * can be either 2-bytes or 4-bytes. This makes it + * possible that the stop-address lands in the middle of + * a 4-byte instruction. Increase the stop_address by + * two to ensure an instruction is not cut in half, but + * leave the len as-is so only the expected number of + * bytes are collected. + */ + stop_address += 2; + } + } + fmt = "%s -z -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s"; - ret = snprintf(cmd, sizeof(cmd), fmt, test_objdump_path, addr, addr + len, + ret = snprintf(cmd, sizeof(cmd), fmt, test_objdump_path, addr, stop_address, filename); if (ret <= 0 || (size_t)ret >= sizeof(cmd)) return -1; diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 2f0168b2a5a9..2354246afc5a 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -156,21 +156,54 @@ static int test__cpu_map_print(struct test_suite *test __maybe_unused, int subte return 0; } -static int test__cpu_map_merge(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +static int __test__cpu_map_merge(const char *lhs, const char *rhs, int nr, const char *expected) { - struct perf_cpu_map *a = perf_cpu_map__new("4,2,1"); - struct perf_cpu_map *b = perf_cpu_map__new("4,5,7"); - struct perf_cpu_map *c = perf_cpu_map__merge(a, b); + struct perf_cpu_map *a = perf_cpu_map__new(lhs); + struct perf_cpu_map *b = perf_cpu_map__new(rhs); char buf[100]; - TEST_ASSERT_VAL("failed to merge map: bad nr", perf_cpu_map__nr(c) == 5); - cpu_map__snprint(c, buf, sizeof(buf)); - TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7")); + perf_cpu_map__merge(&a, b); + TEST_ASSERT_VAL("failed to merge map: bad nr", perf_cpu_map__nr(a) == nr); + cpu_map__snprint(a, buf, sizeof(buf)); + TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, expected)); perf_cpu_map__put(b); - perf_cpu_map__put(c); + + /* + * If 'b' is a superset of 'a', 'a' points to the same map with the + * map 'b'. In this case, the owner 'b' has released the resource above + * but 'a' still keeps the ownership, the reference counter should be 1. + */ + TEST_ASSERT_VAL("unexpected refcnt: bad result", + refcount_read(perf_cpu_map__refcnt(a)) == 1); + + perf_cpu_map__put(a); return 0; } +static int test__cpu_map_merge(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + int ret; + + ret = __test__cpu_map_merge("4,2,1", "4,5,7", 5, "1-2,4-5,7"); + if (ret) + return ret; + ret = __test__cpu_map_merge("1-8", "6-9", 9, "1-9"); + if (ret) + return ret; + ret = __test__cpu_map_merge("1-8,12-20", "6-9,15", 18, "1-9,12-20"); + if (ret) + return ret; + ret = __test__cpu_map_merge("4,2,1", "1", 3, "1-2,4"); + if (ret) + return ret; + ret = __test__cpu_map_merge("1", "4,2,1", 3, "1-2,4"); + if (ret) + return ret; + ret = __test__cpu_map_merge("1", "1", 1, "1"); + return ret; +} + static int __test__cpu_map_intersect(const char *lhs, const char *rhs, int nr, const char *expected) { struct perf_cpu_map *a = perf_cpu_map__new(lhs); @@ -219,30 +252,29 @@ static int test__cpu_map_equal(struct test_suite *test __maybe_unused, int subte struct perf_cpu_map *empty = perf_cpu_map__intersect(one, two); struct perf_cpu_map *pair = perf_cpu_map__new("1-2"); struct perf_cpu_map *tmp; - struct perf_cpu_map *maps[] = {empty, any, one, two, pair}; + struct perf_cpu_map **maps[] = {&empty, &any, &one, &two, &pair}; for (size_t i = 0; i < ARRAY_SIZE(maps); i++) { /* Maps equal themself. */ - TEST_ASSERT_VAL("equal", perf_cpu_map__equal(maps[i], maps[i])); + TEST_ASSERT_VAL("equal", perf_cpu_map__equal(*maps[i], *maps[i])); for (size_t j = 0; j < ARRAY_SIZE(maps); j++) { /* Maps dont't equal each other. */ if (i == j) continue; - TEST_ASSERT_VAL("not equal", !perf_cpu_map__equal(maps[i], maps[j])); + TEST_ASSERT_VAL("not equal", !perf_cpu_map__equal(*maps[i], *maps[j])); } } /* Maps equal made maps. */ - tmp = perf_cpu_map__merge(perf_cpu_map__get(one), two); - TEST_ASSERT_VAL("pair", perf_cpu_map__equal(pair, tmp)); - perf_cpu_map__put(tmp); + perf_cpu_map__merge(&two, one); + TEST_ASSERT_VAL("pair", perf_cpu_map__equal(pair, two)); tmp = perf_cpu_map__intersect(pair, one); TEST_ASSERT_VAL("one", perf_cpu_map__equal(one, tmp)); perf_cpu_map__put(tmp); for (size_t i = 0; i < ARRAY_SIZE(maps); i++) - perf_cpu_map__put(maps[i]); + perf_cpu_map__put(*maps[i]); return TEST_OK; } diff --git a/tools/perf/tests/event_groups.c b/tools/perf/tests/event_groups.c index ccd9d8b2903f..c119ff114948 100644 --- a/tools/perf/tests/event_groups.c +++ b/tools/perf/tests/event_groups.c @@ -10,9 +10,10 @@ #include "header.h" #include "../perf-sys.h" -/* hw: cycles, sw: context-switch, uncore: [arch dependent] */ +/* hw: cycles,instructions sw: context-switch, uncore: [arch dependent] */ static int types[] = {0, 1, -1}; static unsigned long configs[] = {0, 3, 0}; +static unsigned long configs_hw[] = {1}; #define NR_UNCORE_PMUS 5 @@ -93,7 +94,18 @@ static int run_test(int i, int j, int k) return erroneous ? 0 : -1; } - sibling_fd2 = event_open(types[k], configs[k], group_fd); + /* + * if all three events (leader and two sibling events) + * are hardware events, use instructions as one of the + * sibling event. There is event constraint in powerpc that + * events using same counter cannot be programmed in a group. + * Since PERF_COUNT_HW_INSTRUCTIONS is a generic hardware + * event and present in all platforms, lets use that. + */ + if (!i && !j && !k) + sibling_fd2 = event_open(types[k], configs_hw[k], group_fd); + else + sibling_fd2 = event_open(types[k], configs[k], group_fd); if (sibling_fd2 == -1) { close(sibling_fd1); close(group_fd); @@ -124,9 +136,18 @@ static int test__event_groups(struct test_suite *text __maybe_unused, int subtes if (r) ret = TEST_FAIL; - pr_debug("0x%x 0x%lx, 0x%x 0x%lx, 0x%x 0x%lx: %s\n", - types[i], configs[i], types[j], configs[j], - types[k], configs[k], r ? "Fail" : "Pass"); + /* + * For all three events as HW events, second sibling + * event is picked from configs_hw. So print accordingly + */ + if (!i && !j && !k) + pr_debug("0x%x 0x%lx, 0x%x 0x%lx, 0x%x 0x%lx: %s\n", + types[i], configs[i], types[j], configs[j], + types[k], configs_hw[k], r ? "Fail" : "Pass"); + else + pr_debug("0x%x 0x%lx, 0x%x 0x%lx, 0x%x 0x%lx: %s\n", + types[i], configs[i], types[j], configs[j], + types[k], configs[k], r ? "Fail" : "Pass"); } } } diff --git a/tools/perf/tests/make b/tools/perf/tests/make index a7fcbd589752..0ee94caf9ec1 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -86,7 +86,6 @@ make_no_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=1 make_no_backtrace := NO_BACKTRACE=1 make_no_libcapstone := NO_CAPSTONE=1 make_no_libnuma := NO_LIBNUMA=1 -make_no_libaudit := NO_LIBAUDIT=1 make_no_libbionic := NO_LIBBIONIC=1 make_no_auxtrace := NO_AUXTRACE=1 make_no_libbpf := NO_LIBBPF=1 @@ -97,7 +96,6 @@ make_no_libllvm := NO_LIBLLVM=1 make_with_babeltrace:= LIBBABELTRACE=1 make_with_coresight := CORESIGHT=1 make_no_sdt := NO_SDT=1 -make_no_syscall_tbl := NO_SYSCALL_TABLE=1 make_no_libpfm4 := NO_LIBPFM4=1 make_with_gtk2 := GTK2=1 make_refcnt_check := EXTRA_CFLAGS="-DREFCNT_CHECKING=1" @@ -122,10 +120,10 @@ make_static := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX3 # all the NO_* variable combined make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_GTK2=1 make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_BACKTRACE=1 -make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 +make_minimal += NO_LIBNUMA=1 NO_LIBBIONIC=1 make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 make_minimal += NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 NO_LIBZSTD=1 -make_minimal += NO_LIBCAP=1 NO_SYSCALL_TABLE=1 NO_CAPSTONE=1 +make_minimal += NO_LIBCAP=1 NO_CAPSTONE=1 # $(run) contains all available tests run := make_pure @@ -158,7 +156,6 @@ run += make_no_libdw_dwarf_unwind run += make_no_backtrace run += make_no_libcapstone run += make_no_libnuma -run += make_no_libaudit run += make_no_libbionic run += make_no_auxtrace run += make_no_libbpf diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 82a19674a38f..5ec2e5607987 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -54,8 +54,6 @@ static bool test_perf_config(const struct perf_evsel *evsel, __u64 expected_conf return (evsel->attr.config & PERF_HW_EVENT_MASK) == expected_config; } -#ifdef HAVE_LIBTRACEEVENT - #if defined(__s390x__) /* Return true if kvm module is available and loaded. Test this * and return success when trace point kvm_s390_create_vm @@ -112,7 +110,6 @@ static int test__checkevent_tracepoint_multi(struct evlist *evlist) } return TEST_OK; } -#endif /* HAVE_LIBTRACEEVENT */ static int test__checkevent_raw(struct evlist *evlist) { @@ -311,7 +308,6 @@ static int test__checkevent_breakpoint_rw(struct evlist *evlist) return TEST_OK; } -#ifdef HAVE_LIBTRACEEVENT static int test__checkevent_tracepoint_modifier(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); @@ -340,7 +336,6 @@ test__checkevent_tracepoint_multi_modifier(struct evlist *evlist) return test__checkevent_tracepoint_multi(evlist); } -#endif /* HAVE_LIBTRACEEVENT */ static int test__checkevent_raw_modifier(struct evlist *evlist) { @@ -629,7 +624,6 @@ static int test__checkevent_pmu(struct evlist *evlist) return TEST_OK; } -#ifdef HAVE_LIBTRACEEVENT static int test__checkevent_list(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); @@ -671,7 +665,6 @@ static int test__checkevent_list(struct evlist *evlist) return TEST_OK; } -#endif static int test__checkevent_pmu_name(struct evlist *evlist) { @@ -971,7 +964,6 @@ static int test__group2(struct evlist *evlist) return TEST_OK; } -#ifdef HAVE_LIBTRACEEVENT static int test__group3(struct evlist *evlist __maybe_unused) { struct evsel *evsel, *group1_leader = NULL, *group2_leader = NULL; @@ -1078,7 +1070,6 @@ static int test__group3(struct evlist *evlist __maybe_unused) } return TEST_OK; } -#endif static int test__group4(struct evlist *evlist __maybe_unused) { @@ -1813,7 +1804,6 @@ static int test__term_equal_legacy(struct evlist *evlist) return TEST_OK; } -#ifdef HAVE_LIBTRACEEVENT static int count_tracepoints(void) { struct dirent *events_ent; @@ -1867,7 +1857,6 @@ static int test__all_tracepoints(struct evlist *evlist) return test__checkevent_tracepoint_multi(evlist); } -#endif /* HAVE_LIBTRACEVENT */ struct evlist_test { const char *name; @@ -1876,7 +1865,6 @@ struct evlist_test { }; static const struct evlist_test test__events[] = { -#ifdef HAVE_LIBTRACEEVENT { .name = "syscalls:sys_enter_openat", .check = test__checkevent_tracepoint, @@ -1887,7 +1875,6 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_tracepoint_multi, /* 1 */ }, -#endif { .name = "r1a", .check = test__checkevent_raw, @@ -1938,7 +1925,6 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_breakpoint_w, /* 1 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "syscalls:sys_enter_openat:k", .check = test__checkevent_tracepoint_modifier, @@ -1949,7 +1935,6 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_tracepoint_multi_modifier, /* 3 */ }, -#endif { .name = "r1a:kp", .check = test__checkevent_raw_modifier, @@ -1995,13 +1980,11 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_breakpoint_w_modifier, /* 2 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "r1,syscalls:sys_enter_openat:k,1:1:hp", .check = test__checkevent_list, /* 3 */ }, -#endif { .name = "instructions:G", .check = test__checkevent_exclude_host_modifier, @@ -2032,13 +2015,11 @@ static const struct evlist_test test__events[] = { .check = test__group2, /* 9 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "group1{syscalls:sys_enter_openat:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u", .check = test__group3, /* 0 */ }, -#endif { .name = "{cycles:u,instructions:kp}:p", .check = test__group4, @@ -2049,13 +2030,11 @@ static const struct evlist_test test__events[] = { .check = test__group5, /* 2 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "*:*", .check = test__all_tracepoints, /* 3 */ }, -#endif { .name = "{cycles,cache-misses:G}:H", .check = test__group_gh1, @@ -2111,7 +2090,7 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_breakpoint_len_rw_modifier, /* 4 */ }, -#if defined(__s390x__) && defined(HAVE_LIBTRACEEVENT) +#if defined(__s390x__) { .name = "kvm-s390:kvm_s390_create_vm", .check = test__checkevent_tracepoint, @@ -2265,13 +2244,11 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_breakpoint_2_events, /* 3 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "9p:9p_client_req", .check = test__checkevent_tracepoint, /* 4 */ }, -#endif }; static const struct evlist_test test__events_pmu[] = { diff --git a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh index bead723e34af..8226449ac5c3 100755 --- a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh +++ b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_probe :: Reject blacklisted probes (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -22,7 +22,7 @@ TEST_RESULT=0 BLACKFUNC_LIST=`head -n 5 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2` if [ -z "$BLACKFUNC_LIST" ]; then print_overall_skipped - exit 0 + exit 2 fi # try to find vmlinux with DWARF debug info diff --git a/tools/perf/tests/shell/base_probe/test_adding_kernel.sh b/tools/perf/tests/shell/base_probe/test_adding_kernel.sh index d541ffd44a93..df288cf90cd6 100755 --- a/tools/perf/tests/shell/base_probe/test_adding_kernel.sh +++ b/tools/perf/tests/shell/base_probe/test_adding_kernel.sh @@ -1,5 +1,5 @@ #!/bin/bash -# Add 'perf probe's, list and remove them +# perf_probe :: Add probes, list and remove them (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -33,7 +33,7 @@ fi check_kprobes_available if [ $? -ne 0 ]; then print_overall_skipped - exit 0 + exit 2 fi @@ -169,7 +169,7 @@ print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "force-adding probes :: second pr (( TEST_RESULT += $? )) # adding existing probe with '--force' should pass -NO_OF_PROBES=`$CMD_PERF probe -l | wc -l` +NO_OF_PROBES=`$CMD_PERF probe -l $TEST_PROBE| wc -l` $CMD_PERF probe --force --add $TEST_PROBE 2> $LOGS_DIR/adding_kernel_forceadd_03.err PERF_EXIT_CODE=$? @@ -205,7 +205,7 @@ print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "using doubled probe" $CMD_PERF probe --del \* 2> $LOGS_DIR/adding_kernel_removing_wildcard.err PERF_EXIT_CODE=$? -../common/check_all_lines_matched.pl "Removed event: probe:$TEST_PROBE" "Removed event: probe:${TEST_PROBE}_1" < $LOGS_DIR/adding_kernel_removing_wildcard.err +../common/check_all_patterns_found.pl "Removed event: probe:$TEST_PROBE" "Removed event: probe:${TEST_PROBE}_1" < $LOGS_DIR/adding_kernel_removing_wildcard.err CHECK_EXIT_CODE=$? print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "removing multiple probes" diff --git a/tools/perf/tests/shell/base_probe/test_basic.sh b/tools/perf/tests/shell/base_probe/test_basic.sh index 09669ec479f2..9d8b5afbeddd 100755 --- a/tools/perf/tests/shell/base_probe/test_basic.sh +++ b/tools/perf/tests/shell/base_probe/test_basic.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_probe :: Basic perf probe functionality (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -19,7 +19,7 @@ TEST_RESULT=0 if ! check_kprobes_available; then print_overall_skipped - exit 0 + exit 2 fi diff --git a/tools/perf/tests/shell/base_probe/test_invalid_options.sh b/tools/perf/tests/shell/base_probe/test_invalid_options.sh index 1fedfd8b0d0d..92f7254eb32a 100755 --- a/tools/perf/tests/shell/base_probe/test_invalid_options.sh +++ b/tools/perf/tests/shell/base_probe/test_invalid_options.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_probe :: Reject invalid options (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -19,9 +19,12 @@ TEST_RESULT=0 if ! check_kprobes_available; then print_overall_skipped - exit 0 + exit 2 fi +# Check for presence of DWARF +$CMD_PERF check feature -q dwarf +[ $? -ne 0 ] && HINT_FAIL="Some of the tests need DWARF to run" ### missing argument @@ -75,5 +78,5 @@ done # print overall results -print_overall_results "$TEST_RESULT" +print_overall_results "$TEST_RESULT" $HINT_FAIL exit $? diff --git a/tools/perf/tests/shell/base_probe/test_line_semantics.sh b/tools/perf/tests/shell/base_probe/test_line_semantics.sh index d8f4bde0f585..20435b6bf6bc 100755 --- a/tools/perf/tests/shell/base_probe/test_line_semantics.sh +++ b/tools/perf/tests/shell/base_probe/test_line_semantics.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_probe :: Check patterns for line semantics (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -20,9 +20,12 @@ TEST_RESULT=0 if ! check_kprobes_available; then print_overall_skipped - exit 0 + exit 2 fi +# Check for presence of DWARF +$CMD_PERF check feature -q dwarf +[ $? -ne 0 ] && HINT_FAIL="Some of the tests need DWARF to run" ### acceptable --line descriptions @@ -51,5 +54,5 @@ done # print overall results -print_overall_results "$TEST_RESULT" +print_overall_results "$TEST_RESULT" $HINT_FAIL exit $? diff --git a/tools/perf/tests/shell/base_report/setup.sh b/tools/perf/tests/shell/base_report/setup.sh index 4caa496660c6..b03501b2e8fc 100755 --- a/tools/perf/tests/shell/base_report/setup.sh +++ b/tools/perf/tests/shell/base_report/setup.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perftool-testsuite :: perf_report # SPDX-License-Identifier: GPL-2.0 # diff --git a/tools/perf/tests/shell/base_report/test_basic.sh b/tools/perf/tests/shell/base_report/test_basic.sh index 47677cbd4df3..2398eba4d3fd 100755 --- a/tools/perf/tests/shell/base_report/test_basic.sh +++ b/tools/perf/tests/shell/base_report/test_basic.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_report :: Basic perf report options (exclusive) # SPDX-License-Identifier: GPL-2.0 # diff --git a/tools/perf/tests/shell/common/init.sh b/tools/perf/tests/shell/common/init.sh index 075f17623c8e..26c7525651e0 100644 --- a/tools/perf/tests/shell/common/init.sh +++ b/tools/perf/tests/shell/common/init.sh @@ -46,10 +46,13 @@ print_results() print_overall_results() { RETVAL="$1"; shift + TASK_COMMENT="$*" + test -n "$TASK_COMMENT" && TASK_COMMENT=":: $TASK_COMMENT" + if [ $RETVAL -eq 0 ]; then _echo "$MALLPASS## [ PASS ] ##$MEND $TEST_NAME :: $THIS_TEST_NAME SUMMARY" else - _echo "$MALLFAIL## [ FAIL ] ##$MEND $TEST_NAME :: $THIS_TEST_NAME SUMMARY :: $RETVAL failures found" + _echo "$MALLFAIL## [ FAIL ] ##$MEND $TEST_NAME :: $THIS_TEST_NAME SUMMARY :: $RETVAL failures found $TASK_COMMENT" fi return $RETVAL } @@ -85,7 +88,7 @@ consider_skipping() # the runmode of a testcase needs to be at least the current suite's runmode if [ $PERFTOOL_TESTSUITE_RUNMODE -lt $TESTCASE_RUNMODE ]; then print_overall_skipped - exit 0 + exit 2 fi } diff --git a/tools/perf/tests/shell/coresight/Makefile b/tools/perf/tests/shell/coresight/Makefile index b070e779703e..fa08fd9a5991 100644 --- a/tools/perf/tests/shell/coresight/Makefile +++ b/tools/perf/tests/shell/coresight/Makefile @@ -24,6 +24,6 @@ CLEANDIRS = $(SUBDIRS:%=clean-%) clean: $(CLEANDIRS) $(CLEANDIRS): - $(call QUIET_CLEAN, test-$(@:clean-%=%)) $(Q)$(MAKE) -C $(@:clean-%=%) clean >/dev/null + $(call QUIET_CLEAN, test-$(@:clean-%=%)) $(MAKE) -C $(@:clean-%=%) clean >/dev/null .PHONY: all clean $(SUBDIRS) $(CLEANDIRS) $(INSTALLDIRS) diff --git a/tools/perf/tests/shell/ftrace.sh b/tools/perf/tests/shell/ftrace.sh index 2df05052c324..c243731d2fbf 100755 --- a/tools/perf/tests/shell/ftrace.sh +++ b/tools/perf/tests/shell/ftrace.sh @@ -67,11 +67,8 @@ test_ftrace_latency() { test_ftrace_profile() { echo "perf ftrace profile test" - perf ftrace profile -m 16M sleep 0.1 > "${output}" + perf ftrace profile --graph-opts depth=5 sleep 0.1 > "${output}" grep ^# "${output}" - grep sleep "${output}" - grep schedule "${output}" - grep execve "${output}" time_re="[[:space:]]+1[[:digit:]]{5}\.[[:digit:]]{3}" # 100283.000 100283.000 100283.000 1 __x64_sys_clock_nanosleep # Check for one *clock_nanosleep line with a Count of just 1 that takes a bit more than 0.1 seconds diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py index 8ddb85586131..b066d721f897 100644 --- a/tools/perf/tests/shell/lib/perf_json_output_lint.py +++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py @@ -69,16 +69,16 @@ def check_json_output(expected_items): for item in json.loads(input): if expected_items != -1: count = len(item) - if count != expected_items and count >= 1 and count <= 7 and 'metric-value' in item: + if count not in expected_items and count >= 1 and count <= 7 and 'metric-value' in item: # Events that generate >1 metric may have isolated metric # values and possibly other prefixes like interval, core, # aggregate-number, or event-runtime/pcnt-running from multiplexing. pass - elif count != expected_items and count >= 1 and count <= 5 and 'metricgroup' in item: + elif count not in expected_items and count >= 1 and count <= 5 and 'metricgroup' in item: pass - elif count == expected_items + 1 and 'metric-threshold' in item: + elif count - 1 in expected_items and 'metric-threshold' in item: pass - elif count != expected_items: + elif count not in expected_items: raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}' f' in \'{item}\'') for key, value in item.items(): @@ -90,11 +90,11 @@ def check_json_output(expected_items): try: if args.no_args or args.system_wide or args.event: - expected_items = 7 + expected_items = [5, 7] elif args.interval or args.per_thread or args.system_wide_no_aggr: - expected_items = 8 + expected_items = [6, 8] elif args.per_core or args.per_socket or args.per_node or args.per_die or args.per_cluster or args.per_cache: - expected_items = 9 + expected_items = [7, 9] else: # If no option is specified, don't check the number of items. expected_items = -1 diff --git a/tools/perf/tests/shell/perftool-testsuite_probe.sh b/tools/perf/tests/shell/perftool-testsuite_probe.sh index a0fec33a0358..7b1bfd0f888f 100755 --- a/tools/perf/tests/shell/perftool-testsuite_probe.sh +++ b/tools/perf/tests/shell/perftool-testsuite_probe.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perftool-testsuite_probe +# perftool-testsuite_probe (exclusive) # SPDX-License-Identifier: GPL-2.0 test -d "$(dirname "$0")/base_probe" || exit 2 diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 47a26f25db9f..d5e5193cceb6 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -1,5 +1,5 @@ #!/bin/sh -# probe libc's inet_pton & backtrace it with ping +# probe libc's inet_pton & backtrace it with ping (exclusive) # Installs a probe on libc's inet_pton function, that will use uprobes, # then use 'perf trace' on a ping to localhost asking for just one packet @@ -43,17 +43,8 @@ trace_libc_inet_pton_backtrace() { echo "((__GI_)?getaddrinfo|text_to_binary_address)\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "(gaih_inet|main)\+0x[[:xdigit:]]+[[:space:]]\(inlined|.*/bin/ping.*\)$" >> $expected ;; - ppc64|ppc64le) - eventattr='max-stack=4' - # Add gaih_inet to expected backtrace only if it is part of libc. - if nm $libc | grep -F -q gaih_inet.; then - echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected - fi - echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected - echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected - ;; *) - eventattr='max-stack=3' + eventattr='max-stack=4' echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; esac @@ -76,14 +67,25 @@ trace_libc_inet_pton_backtrace() { fi perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script - exec 3<$perf_script exec 4<$expected - while read line <&3 && read -r pattern <&4; do + while read -r pattern <&4; do + echo "Pattern: $pattern" [ -z "$pattern" ] && break - echo $line - echo "$line" | grep -E -q "$pattern" - if [ $? -ne 0 ] ; then - printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line" + + found=0 + + # Search lines in the perf script result + exec 3<$perf_script + while read line <&3; do + [ -z "$line" ] && break + echo " Matching: $line" + ! echo "$line" | grep -E -q "$pattern" + found=$? + [ $found -eq 1 ] && break + done + + if [ $found -ne 1 ] ; then + printf "FAIL: Didn't find the expected backtrace entry \"%s\"\n" "$pattern" return 1 fi done diff --git a/tools/perf/tests/shell/stat+std_output.sh b/tools/perf/tests/shell/stat+std_output.sh index cbf2894b2c84..0f7967be60af 100755 --- a/tools/perf/tests/shell/stat+std_output.sh +++ b/tools/perf/tests/shell/stat+std_output.sh @@ -13,7 +13,7 @@ stat_output=$(mktemp /tmp/__perf_test.stat_output.std.XXXXX) event_name=(cpu-clock task-clock context-switches cpu-migrations page-faults stalled-cycles-frontend stalled-cycles-backend cycles instructions branches branch-misses) event_metric=("CPUs utilized" "CPUs utilized" "/sec" "/sec" "/sec" "frontend cycles idle" "backend cycles idle" "GHz" "insn per cycle" "/sec" "of all branches") -skip_metric=("stalled cycles per insn" "tma_" "retiring" "frontend_bound" "bad_speculation" "backend_bound") +skip_metric=("stalled cycles per insn" "tma_" "retiring" "frontend_bound" "bad_speculation" "backend_bound" "TopdownL1" "percent of slots") cleanup() { rm -f "${stat_output}" diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 7a8adf81e4b3..68323d636fb7 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -187,7 +187,11 @@ test_hybrid() { # Run default Perf stat cycles_events=$(perf stat -- true 2>&1 | grep -E "/cycles/[uH]*| cycles[:uH]* " -c) - if [ "$pmus" -ne "$cycles_events" ] + # The expectation is that default output will have a cycles events on each + # hybrid PMU. In situations with no cycles PMU events, like virtualized, this + # can fall back to task-clock and so the end count may be 0. Fail if neither + # condition holds. + if [ "$pmus" -ne "$cycles_events" ] && [ "0" -ne "$cycles_events" ] then echo "hybrid test [Found $pmus PMUs but $cycles_events cycles events. Failed]" err=1 diff --git a/tools/perf/tests/shell/test_arm_spe.sh b/tools/perf/tests/shell/test_arm_spe.sh index 3258368634f7..a69aab70dd8a 100755 --- a/tools/perf/tests/shell/test_arm_spe.sh +++ b/tools/perf/tests/shell/test_arm_spe.sh @@ -107,7 +107,37 @@ arm_spe_system_wide_test() { arm_spe_report "SPE system-wide testing" $err } +arm_spe_discard_test() { + echo "SPE discard mode" + + for f in /sys/bus/event_source/devices/arm_spe_*; do + if [ -e "$f/format/discard" ]; then + cpu=$(cut -c -1 "$f/cpumask") + break + fi + done + + if [ -z $cpu ]; then + arm_spe_report "SPE discard mode not present" 2 + return + fi + + # Test can use wildcard SPE instance and Perf will only open the event + # on instances that have that format flag. But make sure the target + # runs on an instance with discard mode otherwise we're not testing + # anything. + perf record -o ${perfdata} -e arm_spe/discard/ -N -B --no-bpf-event \ + -- taskset --cpu-list $cpu true + + if perf report -i ${perfdata} --stats | grep 'AUX events\|AUXTRACE events'; then + arm_spe_report "SPE discard mode found unexpected data" 1 + else + arm_spe_report "SPE discard mode" 0 + fi +} + arm_spe_snapshot_test arm_spe_system_wide_test +arm_spe_discard_test exit $glb_err diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh index 5f14d0cb013f..e01df7581393 100755 --- a/tools/perf/tests/shell/test_brstack.sh +++ b/tools/perf/tests/shell/test_brstack.sh @@ -30,7 +30,7 @@ test_user_branches() { echo "Testing user branch stack sampling" perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1 - perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script + perf script -i $TMPDIR/perf.data --fields brstacksym | tr -s ' ' '\n' > $TMPDIR/perf.script # example of branch entries: # brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL @@ -59,7 +59,7 @@ test_filter() { echo "Testing branch stack filtering permutation ($test_filter_filter,$test_filter_expect)" perf record -o $TMPDIR/perf.data --branch-filter $test_filter_filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1 - perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script + perf script -i $TMPDIR/perf.data --fields brstack | tr -s ' ' '\n' | grep '.' > $TMPDIR/perf.script # fail if we find any branch type that doesn't match any of the expected ones # also consider UNKNOWN branch types (-) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index e6f0070975f6..f3a9a040bacc 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -644,6 +644,33 @@ test_pipe() return 0 } +test_pause_resume() +{ + echo "--- Test with pause / resume ---" + if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt/aux-action=start-paused/u uname ; then + echo "SKIP: pause / resume is not supported" + return 2 + fi + if ! perf_record_no_bpf -o "${perfdatafile}" \ + -e intel_pt/aux-action=start-paused/u \ + -e instructions/period=50000,aux-action=resume,name=Resume/u \ + -e instructions/period=100000,aux-action=pause,name=Pause/u uname ; then + echo "perf record with pause / resume failed" + return 1 + fi + if ! perf script -i "${perfdatafile}" --itrace=b -Fperiod,event | \ + awk 'BEGIN {paused=1;branches=0} + /Resume/ {paused=0} + /branches/ {if (paused) exit 1;branches=1} + /Pause/ {paused=1} + END {if (!branches) exit 1}' ; then + echo "perf record with pause / resume failed" + return 1 + fi + echo OK + return 0 +} + count_result() { if [ "$1" -eq 2 ] ; then @@ -672,6 +699,7 @@ test_power_event || ret=$? ; count_result $ret ; ret=0 test_no_tnt || ret=$? ; count_result $ret ; ret=0 test_event_trace || ret=$? ; count_result $ret ; ret=0 test_pipe || ret=$? ; count_result $ret ; ret=0 +test_pause_resume || ret=$? ; count_result $ret ; ret=0 cleanup diff --git a/tools/perf/tests/shell/test_task_analyzer.sh b/tools/perf/tests/shell/test_task_analyzer.sh index 7d76fc63d995..e194fcf61df3 100755 --- a/tools/perf/tests/shell/test_task_analyzer.sh +++ b/tools/perf/tests/shell/test_task_analyzer.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf script task-analyzer tests +# perf script task-analyzer tests (exclusive) # SPDX-License-Identifier: GPL-2.0 tmpdir=$(mktemp -d /tmp/perf-script-task-analyzer-XXXXX) diff --git a/tools/perf/tests/shell/trace_btf_enum.sh b/tools/perf/tests/shell/trace_btf_enum.sh index 5a3b8a5a9b5c..8d1e6bbeac90 100755 --- a/tools/perf/tests/shell/trace_btf_enum.sh +++ b/tools/perf/tests/shell/trace_btf_enum.sh @@ -26,8 +26,12 @@ check_vmlinux() { trace_landlock() { echo "Tracing syscall ${syscall}" - # test flight just to see if landlock_add_rule and libbpf are available - $TESTPROG + # test flight just to see if landlock_add_rule is available + if ! perf trace $TESTPROG 2>&1 | grep -q landlock + then + echo "No landlock system call found, skipping to non-syscall tracing." + return + fi if perf trace -e $syscall $TESTPROG 2>&1 | \ grep -q -E ".*landlock_add_rule\(ruleset_fd: 11, rule_type: (LANDLOCK_RULE_PATH_BENEATH|LANDLOCK_RULE_NET_PORT), rule_attr: 0x[a-f0-9]+, flags: 45\) = -1.*" diff --git a/tools/perf/tests/shell/trace_btf_general.sh b/tools/perf/tests/shell/trace_btf_general.sh new file mode 100755 index 000000000000..e9ee727f3433 --- /dev/null +++ b/tools/perf/tests/shell/trace_btf_general.sh @@ -0,0 +1,94 @@ +#!/bin/bash +# perf trace BTF general tests +# SPDX-License-Identifier: GPL-2.0 + +err=0 +set -e + +# shellcheck source=lib/probe.sh +. "$(dirname $0)"/lib/probe.sh + +file1=$(mktemp /tmp/file1_XXXX) +file2=$(echo $file1 | sed 's/file1/file2/g') + +buffer="buffer content" +perf_config_tmp=$(mktemp /tmp/.perfconfig_XXXXX) + +trap cleanup EXIT TERM INT HUP + +check_vmlinux() { + echo "Checking if vmlinux BTF exists" + if [ ! -f /sys/kernel/btf/vmlinux ] + then + echo "Skipped due to missing vmlinux BTF" + return 2 + fi + return 0 +} + +trace_test_string() { + echo "Testing perf trace's string augmentation" + if ! perf trace -e renameat* --max-events=1 -- mv ${file1} ${file2} 2>&1 | \ + grep -q -E "^mv/[0-9]+ renameat(2)?\(.*, \"${file1}\", .*, \"${file2}\", .*\) += +[0-9]+$" + then + echo "String augmentation test failed" + err=1 + fi +} + +trace_test_buffer() { + echo "Testing perf trace's buffer augmentation" + # echo will insert a newline (\10) at the end of the buffer + if ! perf trace -e write --max-events=1 -- echo "${buffer}" 2>&1 | \ + grep -q -E "^echo/[0-9]+ write\([0-9]+, ${buffer}.*, [0-9]+\) += +[0-9]+$" + then + echo "Buffer augmentation test failed" + err=1 + fi +} + +trace_test_struct_btf() { + echo "Testing perf trace's struct augmentation" + if ! perf trace -e clock_nanosleep --force-btf --max-events=1 -- sleep 1 2>&1 | \ + grep -q -E "^sleep/[0-9]+ clock_nanosleep\(0, 0, \{1,\}, 0x[0-9a-f]+\) += +[0-9]+$" + then + echo "BTF struct augmentation test failed" + err=1 + fi +} + +cleanup() { + rm -rf ${file1} ${file2} ${perf_config_tmp} +} + +trap_cleanup() { + echo "Unexpected signal in ${FUNCNAME[1]}" + cleanup + exit 1 +} + +# don't overwrite user's perf config +trace_config() { + export PERF_CONFIG=${perf_config_tmp} + perf config trace.show_arg_names=false trace.show_duration=false \ + trace.show_timestamp=false trace.args_alignment=0 +} + +skip_if_no_perf_trace || exit 2 +check_vmlinux || exit 2 + +trace_config + +trace_test_string + +if [ $err = 0 ]; then + trace_test_buffer +fi + +if [ $err = 0 ]; then + trace_test_struct_btf +fi + +cleanup + +exit $err diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c index e6fd934b027a..a67c756f90b8 100644 --- a/tools/perf/tests/sigtrap.c +++ b/tools/perf/tests/sigtrap.c @@ -56,6 +56,7 @@ static struct perf_event_attr make_event_attr(void) #ifdef HAVE_BPF_SKEL #include <bpf/btf.h> +#include <util/btf.h> static struct btf *btf; @@ -73,21 +74,6 @@ static void btf__exit(void) btf = NULL; } -static const struct btf_member *__btf_type__find_member_by_name(int type_id, const char *member_name) -{ - const struct btf_type *t = btf__type_by_id(btf, type_id); - const struct btf_member *m; - int i; - - for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { - const char *current_member_name = btf__name_by_offset(btf, m->name_off); - if (!strcmp(current_member_name, member_name)) - return m; - } - - return NULL; -} - static bool attr_has_sigtrap(void) { int id; @@ -101,7 +87,7 @@ static bool attr_has_sigtrap(void) if (id < 0) return false; - return __btf_type__find_member_by_name(id, "sigtrap") != NULL; + return __btf_type__find_member_by_name(btf, id, "sigtrap") != NULL; } static bool kernel_with_sleepable_spinlocks(void) @@ -119,7 +105,7 @@ static bool kernel_with_sleepable_spinlocks(void) return false; // Only RT has a "lock" member for "struct spinlock" - member = __btf_type__find_member_by_name(id, "lock"); + member = __btf_type__find_member_by_name(btf, id, "lock"); if (member == NULL) return false; diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c index 6468cc0d0204..d60983657bad 100644 --- a/tools/perf/tests/stat.c +++ b/tools/perf/tests/stat.c @@ -27,7 +27,7 @@ static int process_stat_config_event(const struct perf_tool *tool __maybe_unused struct machine *machine __maybe_unused) { struct perf_record_stat_config *config = &event->stat_config; - struct perf_stat_config stat_config = {}; + struct perf_stat_config test_stat_config = {}; #define HAS(term, val) \ has_term(config, PERF_STAT_CONFIG_TERM__##term, val) @@ -39,25 +39,27 @@ static int process_stat_config_event(const struct perf_tool *tool __maybe_unused #undef HAS - perf_event__read_stat_config(&stat_config, config); + perf_event__read_stat_config(&test_stat_config, config); - TEST_ASSERT_VAL("wrong aggr_mode", stat_config.aggr_mode == AGGR_CORE); - TEST_ASSERT_VAL("wrong scale", stat_config.scale == 1); - TEST_ASSERT_VAL("wrong interval", stat_config.interval == 1); + TEST_ASSERT_VAL("wrong aggr_mode", test_stat_config.aggr_mode == AGGR_CORE); + TEST_ASSERT_VAL("wrong scale", test_stat_config.scale == 1); + TEST_ASSERT_VAL("wrong interval", test_stat_config.interval == 1); return 0; } static int test__synthesize_stat_config(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - struct perf_stat_config stat_config = { + struct perf_stat_config test_stat_config = { .aggr_mode = AGGR_CORE, .scale = 1, .interval = 1, }; TEST_ASSERT_VAL("failed to synthesize stat_config", - !perf_event__synthesize_stat_config(NULL, &stat_config, process_stat_config_event, NULL)); + !perf_event__synthesize_stat_config(NULL, &test_stat_config, + process_stat_config_event, + NULL)); return 0; } diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 5cab17a1942e..576f82a15015 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -583,4 +583,4 @@ out_err: goto out; } -DEFINE_SUITE("Track with sched_switch", switch_tracking); +DEFINE_SUITE_EXCLUSIVE("Track with sched_switch", switch_tracking); diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c index cf3ae0c1d871..1d5759d08141 100644 --- a/tools/perf/tests/tests-scripts.c +++ b/tools/perf/tests/tests-scripts.c @@ -174,7 +174,7 @@ static void append_script(int dir_fd, const char *name, char *desc, char filename[PATH_MAX], link[128]; struct test_suite *test_suite, **result_tmp; struct test_case *tests; - size_t len; + ssize_t len; char *exclusive; snprintf(link, sizeof(link), "/proc/%d/fd/%d", getpid(), dir_fd); diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index cb58b43aa063..8aea344536b8 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -81,6 +81,16 @@ struct test_suite { .test_cases = tests__##_name, \ } +#define DEFINE_SUITE_EXCLUSIVE(description, _name) \ + struct test_case tests__##_name[] = { \ + TEST_CASE_EXCLUSIVE(description, _name),\ + { .name = NULL, } \ + }; \ + struct test_suite suite__##_name = { \ + .desc = description, \ + .test_cases = tests__##_name, \ + } + /* Tests */ DECLARE_SUITE(vmlinux_matches_kallsyms); DECLARE_SUITE(openat_syscall_event); diff --git a/tools/perf/tests/workloads/landlock.c b/tools/perf/tests/workloads/landlock.c index e2b5ef647c09..1f285b7b6236 100644 --- a/tools/perf/tests/workloads/landlock.c +++ b/tools/perf/tests/workloads/landlock.c @@ -10,7 +10,7 @@ * 'perf test' workload) we just add the required types and defines here instead * of including linux/landlock, that isn't available in older systems. * - * We are not interested in the the result of the syscall, just in intercepting + * We are not interested in the result of the syscall, just in intercepting * its arguments. */ diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh index 30d3889b2957..b22890b8d272 100755 --- a/tools/perf/trace/beauty/arch_errno_names.sh +++ b/tools/perf/trace/beauty/arch_errno_names.sh @@ -57,7 +57,8 @@ create_arch_errno_table_func() archlist="$1" default="$2" - printf 'arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch)\n' + printf 'static arch_syscalls__strerrno_t *\n' + printf 'arch_syscalls__strerrno_function(const char *arch)\n' printf '{\n' for arch in $archlist; do arch_str=$(arch_string "$arch") diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index d7e727345dab..135d6ce88fb3 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -754,7 +754,7 @@ static int annotate_browser__run(struct annotate_browser *browser, hbt->timer(hbt->arg); if (delay_secs != 0) { - symbol__annotate_decay_histogram(sym, evsel->core.idx); + symbol__annotate_decay_histogram(sym, evsel); hists__scnprintf_title(hists, title, sizeof(title)); annotate_browser__show(&browser->b, title, help); } diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index e437d7889de6..2d04ece833aa 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -1,16 +1,18 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../builtin.h" -#include "../../perf.h" #include "../../util/util.h" // perf_exe() #include "../util.h" +#include "../../util/evlist.h" #include "../../util/hist.h" #include "../../util/debug.h" +#include "../../util/session.h" #include "../../util/symbol.h" #include "../browser.h" #include "../libslang.h" #include "config.h" +#include <linux/err.h> #include <linux/string.h> #include <linux/zalloc.h> +#include <subcmd/exec-cmd.h> #include <stdlib.h> #define SCRIPT_NAMELEN 128 @@ -77,6 +79,177 @@ static int scripts_config(const char *var, const char *value, void *data) return 0; } +/* + * Some scripts specify the required events in their "xxx-record" file, + * this function will check if the events in perf.data match those + * mentioned in the "xxx-record". + * + * Fixme: All existing "xxx-record" are all in good formats "-e event ", + * which is covered well now. And new parsing code should be added to + * cover the future complex formats like event groups etc. + */ +static int check_ev_match(int dir_fd, const char *scriptname, struct perf_session *session) +{ + char line[BUFSIZ]; + FILE *fp; + + { + char filename[FILENAME_MAX + 5]; + int fd; + + scnprintf(filename, sizeof(filename), "bin/%s-record", scriptname); + fd = openat(dir_fd, filename, O_RDONLY); + if (fd == -1) + return -1; + fp = fdopen(fd, "r"); + if (!fp) + return -1; + } + + while (fgets(line, sizeof(line), fp)) { + char *p = skip_spaces(line); + + if (*p == '#') + continue; + + while (strlen(p)) { + int match, len; + struct evsel *pos; + char evname[128]; + + p = strstr(p, "-e"); + if (!p) + break; + + p += 2; + p = skip_spaces(p); + len = strcspn(p, " \t"); + if (!len) + break; + + snprintf(evname, len + 1, "%s", p); + + match = 0; + evlist__for_each_entry(session->evlist, pos) { + if (evsel__name_is(pos, evname)) { + match = 1; + break; + } + } + + if (!match) { + fclose(fp); + return -1; + } + } + } + + fclose(fp); + return 0; +} + +/* + * Return -1 if none is found, otherwise the actual scripts number. + * + * Currently the only user of this function is the script browser, which + * will list all statically runnable scripts, select one, execute it and + * show the output in a perf browser. + */ +static int find_scripts(char **scripts_array, char **scripts_path_array, int num, + int pathlen) +{ + struct dirent *script_dirent, *lang_dirent; + int scripts_dir_fd, lang_dir_fd; + DIR *scripts_dir, *lang_dir; + struct perf_session *session; + struct perf_data data = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; + char *temp; + int i = 0; + const char *exec_path = get_argv_exec_path(); + + session = perf_session__new(&data, NULL); + if (IS_ERR(session)) + return PTR_ERR(session); + + { + char scripts_path[PATH_MAX]; + + snprintf(scripts_path, sizeof(scripts_path), "%s/scripts", exec_path); + scripts_dir_fd = open(scripts_path, O_DIRECTORY); + pr_err("Failed to open directory '%s'", scripts_path); + if (scripts_dir_fd == -1) { + perf_session__delete(session); + return -1; + } + } + scripts_dir = fdopendir(scripts_dir_fd); + if (!scripts_dir) { + close(scripts_dir_fd); + perf_session__delete(session); + return -1; + } + + while ((lang_dirent = readdir(scripts_dir)) != NULL) { + if (lang_dirent->d_type != DT_DIR && + (lang_dirent->d_type == DT_UNKNOWN && + !is_directory_at(scripts_dir_fd, lang_dirent->d_name))) + continue; + if (!strcmp(lang_dirent->d_name, ".") || !strcmp(lang_dirent->d_name, "..")) + continue; + +#ifndef HAVE_LIBPERL_SUPPORT + if (strstr(lang_dirent->d_name, "perl")) + continue; +#endif +#ifndef HAVE_LIBPYTHON_SUPPORT + if (strstr(lang_dirent->d_name, "python")) + continue; +#endif + + lang_dir_fd = openat(scripts_dir_fd, lang_dirent->d_name, O_DIRECTORY); + if (lang_dir_fd == -1) + continue; + lang_dir = fdopendir(lang_dir_fd); + if (!lang_dir) { + close(lang_dir_fd); + continue; + } + while ((script_dirent = readdir(lang_dir)) != NULL) { + if (script_dirent->d_type == DT_DIR) + continue; + if (script_dirent->d_type == DT_UNKNOWN && + is_directory_at(lang_dir_fd, script_dirent->d_name)) + continue; + /* Skip those real time scripts: xxxtop.p[yl] */ + if (strstr(script_dirent->d_name, "top.")) + continue; + if (i >= num) + break; + scnprintf(scripts_path_array[i], pathlen, "%s/scripts/%s/%s", + exec_path, + lang_dirent->d_name, + script_dirent->d_name); + temp = strchr(script_dirent->d_name, '.'); + snprintf(scripts_array[i], + (temp - script_dirent->d_name) + 1, + "%s", script_dirent->d_name); + + if (check_ev_match(lang_dir_fd, scripts_array[i], session)) + continue; + + i++; + } + closedir(lang_dir); + } + + closedir(scripts_dir); + perf_session__delete(session); + return i; +} + /* * When success, will copy the full path of the selected script * into the buffer pointed by script_name, and return 0. diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 6da24aa039eb..8920e298420a 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -3,6 +3,7 @@ #include "util/sort.h" #include "util/debug.h" #include "util/annotate.h" +#include "util/evlist.h" #include "util/evsel.h" #include "util/map.h" #include "util/dso.h" @@ -26,7 +27,7 @@ static const char *const col_names[] = { }; static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym, - struct disasm_line *dl, int evidx) + struct disasm_line *dl, const struct evsel *evsel) { struct annotation *notes; struct sym_hist *symhist; @@ -42,8 +43,8 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym, return 0; notes = symbol__annotation(sym); - symhist = annotation__histogram(notes, evidx); - entry = annotated_source__hist_entry(notes->src, evidx, dl->al.offset); + symhist = annotation__histogram(notes, evsel); + entry = annotated_source__hist_entry(notes->src, evsel, dl->al.offset); if (entry) nr_samples = entry->nr_samples; @@ -139,16 +140,17 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct map_symbol *ms, gtk_list_store_append(store, &iter); if (evsel__is_group_event(evsel)) { - for (i = 0; i < evsel->core.nr_members; i++) { + struct evsel *cur_evsel; + + for_each_group_evsel(cur_evsel, evsel__leader(evsel)) { ret += perf_gtk__get_percent(s + ret, sizeof(s) - ret, sym, pos, - evsel->core.idx + i); + cur_evsel); ret += scnprintf(s + ret, sizeof(s) - ret, " "); } } else { - ret = perf_gtk__get_percent(s, sizeof(s), sym, pos, - evsel->core.idx); + ret = perf_gtk__get_percent(s, sizeof(s), sym, pos, evsel); } if (ret) diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index e5491995adf0..34fda1d5eccb 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -121,7 +121,7 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, const char *fmtstr, hpp_snprint_fn print_fn, enum perf_hpp_fmt_type fmtype) { - int len = fmt->user_len ?: fmt->len; + int len = max(fmt->user_len ?: fmt->len, (int)strlen(fmt->name)); if (symbol_conf.field_sep) { return __hpp__fmt(hpp, he, get_field, fmtstr, 1, diff --git a/tools/perf/util/Build b/tools/perf/util/Build index c06d2ee9024c..5ec97e8d6b6d 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -86,7 +86,7 @@ perf-util-y += pmu-bison.o perf-util-y += hwmon_pmu.o perf-util-y += tool_pmu.o perf-util-y += svghelper.o -perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-info.o +perf-util-y += trace-event-info.o perf-util-y += trace-event-scripting.o perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event.o perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-parse.o @@ -121,8 +121,10 @@ perf-util-y += spark.o perf-util-y += topdown.o perf-util-y += iostat.o perf-util-y += stream.o +perf-util-y += kvm-stat.o +perf-util-y += lock-contention.o perf-util-$(CONFIG_AUXTRACE) += auxtrace.o -perf-util-$(CONFIG_AUXTRACE) += intel-pt-decoder/ +perf-util-y += intel-pt-decoder/ perf-util-$(CONFIG_AUXTRACE) += intel-pt.o perf-util-$(CONFIG_AUXTRACE) += intel-bts.o perf-util-$(CONFIG_AUXTRACE) += arm-spe.o @@ -168,6 +170,7 @@ perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-flex.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-bison.o +perf-util-$(CONFIG_PERF_BPF_SKEL) += btf.o ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 32e15c9f53f3..31bb326b07a6 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -209,7 +209,7 @@ static int __symbol__account_cycles(struct cyc_hist *ch, } static int __symbol__inc_addr_samples(struct map_symbol *ms, - struct annotated_source *src, int evidx, u64 addr, + struct annotated_source *src, struct evsel *evsel, u64 addr, struct perf_sample *sample) { struct symbol *sym = ms->sym; @@ -228,14 +228,14 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms, } offset = addr - sym->start; - h = annotated_source__histogram(src, evidx); + h = annotated_source__histogram(src, evsel); if (h == NULL) { pr_debug("%s(%d): ENOMEM! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 ", func: %d\n", __func__, __LINE__, sym->name, sym->start, addr, sym->end, sym->type == STT_FUNC); return -ENOMEM; } - hash_key = offset << 16 | evidx; + hash_key = offset << 16 | evsel->core.idx; if (!hashmap__find(src->samples, hash_key, &entry)) { entry = zalloc(sizeof(*entry)); if (entry == NULL) @@ -252,7 +252,7 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms, pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64 ", evidx=%d] => nr_samples: %" PRIu64 ", period: %" PRIu64 "\n", - sym->start, sym->name, addr, addr - sym->start, evidx, + sym->start, sym->name, addr, addr - sym->start, evsel->core.idx, entry->nr_samples, entry->period); return 0; } @@ -323,7 +323,7 @@ static int symbol__inc_addr_samples(struct map_symbol *ms, if (sym == NULL) return 0; src = symbol__hists(sym, evsel->evlist->core.nr_entries); - return src ? __symbol__inc_addr_samples(ms, src, evsel->core.idx, addr, sample) : 0; + return src ? __symbol__inc_addr_samples(ms, src, evsel, addr, sample) : 0; } static int symbol__account_br_cntr(struct annotated_branch *branch, @@ -861,15 +861,14 @@ static void calc_percent(struct annotation *notes, s64 offset, s64 end) { struct hists *hists = evsel__hists(evsel); - int evidx = evsel->core.idx; - struct sym_hist *sym_hist = annotation__histogram(notes, evidx); + struct sym_hist *sym_hist = annotation__histogram(notes, evsel); unsigned int hits = 0; u64 period = 0; while (offset < end) { struct sym_hist_entry *entry; - entry = annotated_source__hist_entry(notes->src, evidx, offset); + entry = annotated_source__hist_entry(notes->src, evsel, offset); if (entry) { hits += entry->nr_samples; period += entry->period; @@ -1140,15 +1139,14 @@ static void print_summary(struct rb_root *root, const char *filename) static void symbol__annotate_hits(struct symbol *sym, struct evsel *evsel) { - int evidx = evsel->core.idx; struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evidx); + struct sym_hist *h = annotation__histogram(notes, evsel); u64 len = symbol__size(sym), offset; for (offset = 0; offset < len; ++offset) { struct sym_hist_entry *entry; - entry = annotated_source__hist_entry(notes->src, evidx, offset); + entry = annotated_source__hist_entry(notes->src, evsel, offset); if (entry && entry->nr_samples != 0) printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2, sym->start + offset, entry->nr_samples); @@ -1178,7 +1176,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) const char *d_filename; const char *evsel_name = evsel__name(evsel); struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evsel->core.idx); + struct sym_hist *h = annotation__histogram(notes, evsel); struct annotation_line *pos, *queue = NULL; struct annotation_options *opts = &annotate_opts; u64 start = map__rip_2objdump(map, sym->start); @@ -1364,18 +1362,18 @@ out_free_filename: return err; } -void symbol__annotate_zero_histogram(struct symbol *sym, int evidx) +void symbol__annotate_zero_histogram(struct symbol *sym, struct evsel *evsel) { struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evidx); + struct sym_hist *h = annotation__histogram(notes, evsel); memset(h, 0, sizeof(*notes->src->histograms) * notes->src->nr_histograms); } -void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) +void symbol__annotate_decay_histogram(struct symbol *sym, struct evsel *evsel) { struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evidx); + struct sym_hist *h = annotation__histogram(notes, evsel); struct annotation_line *al; h->nr_samples = 0; @@ -1385,7 +1383,7 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) if (al->offset == -1) continue; - entry = annotated_source__hist_entry(notes->src, evidx, al->offset); + entry = annotated_source__hist_entry(notes->src, evsel, al->offset); if (entry == NULL) continue; @@ -2102,6 +2100,57 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, return 0; } +const char * const perf_disassembler__strs[] = { + [PERF_DISASM_UNKNOWN] = "unknown", + [PERF_DISASM_LLVM] = "llvm", + [PERF_DISASM_CAPSTONE] = "capstone", + [PERF_DISASM_OBJDUMP] = "objdump", +}; + + +static void annotation_options__add_disassembler(struct annotation_options *options, + enum perf_disassembler dis) +{ + for (u8 i = 0; i < ARRAY_SIZE(options->disassemblers); i++) { + if (options->disassemblers[i] == dis) { + /* Disassembler is already present then don't add again. */ + return; + } + if (options->disassemblers[i] == PERF_DISASM_UNKNOWN) { + /* Found a free slot. */ + options->disassemblers[i] = dis; + return; + } + } + pr_err("Failed to add disassembler %d\n", dis); +} + +static int annotation_options__add_disassemblers_str(struct annotation_options *options, + const char *str) +{ + while (str && *str != '\0') { + const char *comma = strchr(str, ','); + int len = comma ? comma - str : (int)strlen(str); + bool match = false; + + for (u8 i = 0; i < ARRAY_SIZE(perf_disassembler__strs); i++) { + const char *dis_str = perf_disassembler__strs[i]; + + if (len == (int)strlen(dis_str) && !strncmp(str, dis_str, len)) { + annotation_options__add_disassembler(options, i); + match = true; + break; + } + } + if (!match) { + pr_err("Invalid disassembler '%.*s'\n", len, str); + return -1; + } + str = comma ? comma + 1 : NULL; + } + return 0; +} + static int annotation__config(const char *var, const char *value, void *data) { struct annotation_options *opt = data; @@ -2117,11 +2166,10 @@ static int annotation__config(const char *var, const char *value, void *data) else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL) opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL; } else if (!strcmp(var, "annotate.disassemblers")) { - opt->disassemblers_str = strdup(value); - if (!opt->disassemblers_str) { - pr_err("Not enough memory for annotate.disassemblers\n"); - return -1; - } + int err = annotation_options__add_disassemblers_str(opt, value); + + if (err) + return err; } else if (!strcmp(var, "annotate.hide_src_code")) { opt->hide_src_code = perf_config_bool("hide_src_code", value); } else if (!strcmp(var, "annotate.jump_arrows")) { @@ -2187,9 +2235,25 @@ void annotation_options__exit(void) zfree(&annotate_opts.objdump_path); } +static void annotation_options__default_init_disassemblers(struct annotation_options *options) +{ + if (options->disassemblers[0] != PERF_DISASM_UNKNOWN) { + /* Already initialized. */ + return; + } +#ifdef HAVE_LIBLLVM_SUPPORT + annotation_options__add_disassembler(options, PERF_DISASM_LLVM); +#endif +#ifdef HAVE_LIBCAPSTONE_SUPPORT + annotation_options__add_disassembler(options, PERF_DISASM_CAPSTONE); +#endif + annotation_options__add_disassembler(options, PERF_DISASM_OBJDUMP); +} + void annotation_config__init(void) { perf_config(annotation__config, &annotate_opts); + annotation_options__default_init_disassemblers(&annotate_opts); } static unsigned int parse_percent_type(char *str1, char *str2) diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 194a05cbc506..98db1b88daf4 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -15,6 +15,7 @@ #include "hashmap.h" #include "disasm.h" #include "branch.h" +#include "evsel.h" struct hist_browser_timer; struct hist_entry; @@ -23,7 +24,6 @@ struct map_symbol; struct addr_map_symbol; struct option; struct perf_sample; -struct evsel; struct symbol; struct annotated_data_type; @@ -34,8 +34,13 @@ struct annotated_data_type; #define ANNOTATION__BR_CNTR_WIDTH 30 #define ANNOTATION_DUMMY_LEN 256 -// llvm, capstone, objdump -#define MAX_DISASSEMBLERS 3 +enum perf_disassembler { + PERF_DISASM_UNKNOWN = 0, + PERF_DISASM_LLVM, + PERF_DISASM_CAPSTONE, + PERF_DISASM_OBJDUMP, +}; +#define MAX_DISASSEMBLERS (PERF_DISASM_OBJDUMP + 1) struct annotation_options { bool hide_src_code, @@ -52,14 +57,12 @@ struct annotation_options { annotate_src, full_addr; u8 offset_level; - u8 nr_disassemblers; + u8 disassemblers[MAX_DISASSEMBLERS]; int min_pcnt; int max_lines; int context; char *objdump_path; char *disassembler_style; - const char *disassemblers_str; - const char *disassemblers[MAX_DISASSEMBLERS]; const char *prefix; const char *prefix_strip; unsigned int percent_type; @@ -134,6 +137,8 @@ struct disasm_line { struct annotation_line al; }; +extern const char * const perf_disassembler__strs[]; + void annotation_line__add(struct annotation_line *al, struct list_head *head); static inline double annotation_data__percent(struct annotation_data *data, @@ -373,21 +378,23 @@ static inline u8 annotation__br_cntr_width(void) void annotation__update_column_widths(struct annotation *notes); void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms); -static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, int idx) +static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, + const struct evsel *evsel) { - return &src->histograms[idx]; + return &src->histograms[evsel->core.idx]; } -static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx) +static inline struct sym_hist *annotation__histogram(struct annotation *notes, + const struct evsel *evsel) { - return annotated_source__histogram(notes->src, idx); + return annotated_source__histogram(notes->src, evsel); } static inline struct sym_hist_entry * -annotated_source__hist_entry(struct annotated_source *src, int idx, u64 offset) +annotated_source__hist_entry(struct annotated_source *src, const struct evsel *evsel, u64 offset) { struct sym_hist_entry *entry; - long key = offset << 16 | idx; + long key = offset << 16 | evsel->core.idx; if (!hashmap__find(src->samples, key, &entry)) return NULL; @@ -441,6 +448,7 @@ enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP, SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE, SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF, + SYMBOL_ANNOTATE_ERRNO__COULDNT_DETERMINE_FILE_TYPE, __SYMBOL_ANNOTATE_ERRNO__END, }; @@ -448,8 +456,8 @@ enum symbol_disassemble_errno { int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen); int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel); -void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); -void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); +void symbol__annotate_zero_histogram(struct symbol *sym, struct evsel *evsel); +void symbol__annotate_decay_histogram(struct symbol *sym, struct evsel *evsel); void annotated_source__purge(struct annotated_source *as); int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel); diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h index 358c611eeddb..4bcd627e859f 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -67,6 +67,15 @@ enum arm_spe_common_data_source { ARM_SPE_COMMON_DS_DRAM = 0xe, }; +enum arm_spe_ampereone_data_source { + ARM_SPE_AMPEREONE_LOCAL_CHIP_CACHE_OR_DEVICE = 0x0, + ARM_SPE_AMPEREONE_SLC = 0x3, + ARM_SPE_AMPEREONE_REMOTE_CHIP_CACHE = 0x5, + ARM_SPE_AMPEREONE_DDR = 0x7, + ARM_SPE_AMPEREONE_L1D = 0x8, + ARM_SPE_AMPEREONE_L2D = 0x9, +}; + struct arm_spe_record { enum arm_spe_sample_type type; int err; diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index dbf13f47879c..12761c39788f 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -103,6 +103,18 @@ struct arm_spe_queue { u32 flags; }; +struct data_source_handle { + const struct midr_range *midr_ranges; + void (*ds_synth)(const struct arm_spe_record *record, + union perf_mem_data_src *data_src); +}; + +#define DS(range, func) \ + { \ + .midr_ranges = range, \ + .ds_synth = arm_spe__synth_##func, \ + } + static void arm_spe_dump(struct arm_spe *spe __maybe_unused, unsigned char *buf, size_t len) { @@ -443,6 +455,11 @@ static const struct midr_range common_ds_encoding_cpus[] = { {}, }; +static const struct midr_range ampereone_ds_encoding_cpus[] = { + MIDR_ALL_VERSIONS(MIDR_AMPERE1A), + {}, +}; + static void arm_spe__sample_flags(struct arm_spe_queue *speq) { const struct arm_spe_record *record = &speq->decoder->record; @@ -532,6 +549,49 @@ static void arm_spe__synth_data_source_common(const struct arm_spe_record *recor } } +/* + * Source is IMPDEF. Here we convert the source code used on AmpereOne cores + * to the common (Neoverse, Cortex) to avoid duplicating the decoding code. + */ +static void arm_spe__synth_data_source_ampereone(const struct arm_spe_record *record, + union perf_mem_data_src *data_src) +{ + struct arm_spe_record common_record; + + switch (record->source) { + case ARM_SPE_AMPEREONE_LOCAL_CHIP_CACHE_OR_DEVICE: + common_record.source = ARM_SPE_COMMON_DS_PEER_CORE; + break; + case ARM_SPE_AMPEREONE_SLC: + common_record.source = ARM_SPE_COMMON_DS_SYS_CACHE; + break; + case ARM_SPE_AMPEREONE_REMOTE_CHIP_CACHE: + common_record.source = ARM_SPE_COMMON_DS_REMOTE; + break; + case ARM_SPE_AMPEREONE_DDR: + common_record.source = ARM_SPE_COMMON_DS_DRAM; + break; + case ARM_SPE_AMPEREONE_L1D: + common_record.source = ARM_SPE_COMMON_DS_L1D; + break; + case ARM_SPE_AMPEREONE_L2D: + common_record.source = ARM_SPE_COMMON_DS_L2; + break; + default: + pr_warning_once("AmpereOne: Unknown data source (0x%x)\n", + record->source); + return; + } + + common_record.op = record->op; + arm_spe__synth_data_source_common(&common_record, data_src); +} + +static const struct data_source_handle data_source_handles[] = { + DS(common_ds_encoding_cpus, data_source_common), + DS(ampereone_ds_encoding_cpus, data_source_ampereone), +}; + static void arm_spe__synth_memory_level(const struct arm_spe_record *record, union perf_mem_data_src *data_src) { @@ -555,12 +615,14 @@ static void arm_spe__synth_memory_level(const struct arm_spe_record *record, data_src->mem_lvl |= PERF_MEM_LVL_REM_CCE1; } -static bool arm_spe__is_common_ds_encoding(struct arm_spe_queue *speq) +static bool arm_spe__synth_ds(struct arm_spe_queue *speq, + const struct arm_spe_record *record, + union perf_mem_data_src *data_src) { struct arm_spe *spe = speq->spe; - bool is_in_cpu_list; u64 *metadata = NULL; - u64 midr = 0; + u64 midr; + unsigned int i; /* Metadata version 1 assumes all CPUs are the same (old behavior) */ if (spe->metadata_ver == 1) { @@ -592,18 +654,20 @@ static bool arm_spe__is_common_ds_encoding(struct arm_spe_queue *speq) midr = metadata[ARM_SPE_CPU_MIDR]; } - is_in_cpu_list = is_midr_in_range_list(midr, common_ds_encoding_cpus); - if (is_in_cpu_list) - return true; - else - return false; + for (i = 0; i < ARRAY_SIZE(data_source_handles); i++) { + if (is_midr_in_range_list(midr, data_source_handles[i].midr_ranges)) { + data_source_handles[i].ds_synth(record, data_src); + return true; + } + } + + return false; } static u64 arm_spe__synth_data_source(struct arm_spe_queue *speq, const struct arm_spe_record *record) { union perf_mem_data_src data_src = { .mem_op = PERF_MEM_OP_NA }; - bool is_common = arm_spe__is_common_ds_encoding(speq); if (record->op & ARM_SPE_OP_LD) data_src.mem_op = PERF_MEM_OP_LOAD; @@ -612,9 +676,7 @@ static u64 arm_spe__synth_data_source(struct arm_spe_queue *speq, else return 0; - if (is_common) - arm_spe__synth_data_source_common(record, &data_src); - else + if (!arm_spe__synth_ds(speq, record, &data_src)) arm_spe__synth_memory_level(record, &data_src); if (record->type & (ARM_SPE_TLB_ACCESS | ARM_SPE_TLB_MISS)) { diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index ca8682966fae..4d1633d87eff 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -810,19 +810,76 @@ no_opt: return auxtrace_validate_aux_sample_size(evlist, opts); } -void auxtrace_regroup_aux_output(struct evlist *evlist) +static struct aux_action_opt { + const char *str; + u32 aux_action; + bool aux_event_opt; +} aux_action_opts[] = { + {"start-paused", BIT(0), true}, + {"pause", BIT(1), false}, + {"resume", BIT(2), false}, + {.str = NULL}, +}; + +static const struct aux_action_opt *auxtrace_parse_aux_action_str(const char *str) +{ + const struct aux_action_opt *opt; + + if (!str) + return NULL; + + for (opt = aux_action_opts; opt->str; opt++) + if (!strcmp(str, opt->str)) + return opt; + + return NULL; +} + +int auxtrace_parse_aux_action(struct evlist *evlist) { - struct evsel *evsel, *aux_evsel = NULL; struct evsel_config_term *term; + struct evsel *aux_evsel = NULL; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel__is_aux_event(evsel)) + bool is_aux_event = evsel__is_aux_event(evsel); + const struct aux_action_opt *opt; + + if (is_aux_event) aux_evsel = evsel; - term = evsel__get_config_term(evsel, AUX_OUTPUT); + term = evsel__get_config_term(evsel, AUX_ACTION); + if (!term) { + if (evsel__get_config_term(evsel, AUX_OUTPUT)) + goto regroup; + continue; + } + opt = auxtrace_parse_aux_action_str(term->val.str); + if (!opt) { + pr_err("Bad aux-action '%s'\n", term->val.str); + return -EINVAL; + } + if (opt->aux_event_opt && !is_aux_event) { + pr_err("aux-action '%s' can only be used with AUX area event\n", + term->val.str); + return -EINVAL; + } + if (!opt->aux_event_opt && is_aux_event) { + pr_err("aux-action '%s' cannot be used for AUX area event itself\n", + term->val.str); + return -EINVAL; + } + evsel->core.attr.aux_action = opt->aux_action; +regroup: /* If possible, group with the AUX event */ - if (term && aux_evsel) + if (aux_evsel) evlist__regroup(evlist, aux_evsel, evsel); + if (!evsel__is_aux_event(evsel__leader(evsel))) { + pr_err("Events with aux-action must have AUX area event group leader\n"); + return -EINVAL; + } } + + return 0; } struct auxtrace_record *__weak diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index dddaf4f3ffed..b0db84d27b25 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -578,7 +578,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, int auxtrace_parse_sample_options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts, const char *str); -void auxtrace_regroup_aux_output(struct evlist *evlist); +int auxtrace_parse_aux_action(struct evlist *evlist); int auxtrace_record__options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts); @@ -799,8 +799,10 @@ int auxtrace_parse_sample_options(struct auxtrace_record *itr __maybe_unused, } static inline -void auxtrace_regroup_aux_output(struct evlist *evlist __maybe_unused) +int auxtrace_parse_aux_action(struct evlist *evlist __maybe_unused) { + pr_err("AUX area tracing not supported\n"); + return -EINVAL; } static inline diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 13608237c50e..c81444059ad0 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -289,7 +289,10 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, } info_node->info_linear = info_linear; - perf_env__insert_bpf_prog_info(env, info_node); + if (!perf_env__insert_bpf_prog_info(env, info_node)) { + free(info_linear); + free(info_node); + } info_linear = NULL; /* @@ -480,7 +483,10 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id) info_node = malloc(sizeof(struct bpf_prog_info_node)); if (info_node) { info_node->info_linear = info_linear; - perf_env__insert_bpf_prog_info(env, info_node); + if (!perf_env__insert_bpf_prog_info(env, info_node)) { + free(info_linear); + free(info_node); + } } else free(info_linear); diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c index 06d1c4018407..25fc280e414a 100644 --- a/tools/perf/util/bpf_ftrace.c +++ b/tools/perf/util/bpf_ftrace.c @@ -11,6 +11,7 @@ #include "util/debug.h" #include "util/evlist.h" #include "util/bpf_counter.h" +#include "util/stat.h" #include "util/bpf_skel/func_latency.skel.h" @@ -36,6 +37,9 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) return -1; } + skel->rodata->bucket_range = ftrace->bucket_range; + skel->rodata->min_latency = ftrace->min_latency; + /* don't need to set cpu filter for system-wide mode */ if (ftrace->target.cpu_list) { ncpus = perf_cpu_map__nr(ftrace->evlist->core.user_requested_cpus); @@ -83,6 +87,8 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) } } + skel->bss->min = INT64_MAX; + skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin, false, func->name); if (IS_ERR(skel->links.func_begin)) { @@ -119,7 +125,7 @@ int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) } int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, - int buckets[]) + int buckets[], struct stats *stats) { int i, fd, err; u32 idx; @@ -143,6 +149,13 @@ int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, buckets[idx] += hist[i]; } + if (skel->bss->count) { + stats->mean = skel->bss->total / skel->bss->count; + stats->n = skel->bss->count; + stats->max = skel->bss->max; + stats->min = skel->bss->min; + } + free(hist); return 0; } diff --git a/tools/perf/util/bpf_kwork.c b/tools/perf/util/bpf_kwork.c index 6c7126b7670d..5cff755c71fa 100644 --- a/tools/perf/util/bpf_kwork.c +++ b/tools/perf/util/bpf_kwork.c @@ -285,7 +285,7 @@ static int add_work(struct perf_kwork *kwork, (bpf_trace->get_work_name(key, &tmp.name))) return -1; - work = perf_kwork_add_work(kwork, tmp.class, &tmp); + work = kwork->add_work(kwork, tmp.class, &tmp); if (work == NULL) return -1; diff --git a/tools/perf/util/bpf_kwork_top.c b/tools/perf/util/bpf_kwork_top.c index 7261cad43468..b6f187dd9136 100644 --- a/tools/perf/util/bpf_kwork_top.c +++ b/tools/perf/util/bpf_kwork_top.c @@ -255,7 +255,7 @@ static int add_work(struct perf_kwork *kwork, struct work_key *key, bpf_trace = kwork_class_bpf_supported_list[type]; tmp.class = bpf_trace->class; - work = perf_kwork_add_work(kwork, tmp.class, &tmp); + work = kwork->add_work(kwork, tmp.class, &tmp); if (!work) return -1; diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 41a1ad087895..fc8666222399 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -2,6 +2,7 @@ #include "util/cgroup.h" #include "util/debug.h" #include "util/evlist.h" +#include "util/hashmap.h" #include "util/machine.h" #include "util/map.h" #include "util/symbol.h" @@ -12,17 +13,106 @@ #include <linux/zalloc.h> #include <linux/string.h> #include <bpf/bpf.h> +#include <bpf/btf.h> #include <inttypes.h> #include "bpf_skel/lock_contention.skel.h" #include "bpf_skel/lock_data.h" static struct lock_contention_bpf *skel; +static bool has_slab_iter; +static struct hashmap slab_hash; + +static size_t slab_cache_hash(long key, void *ctx __maybe_unused) +{ + return key; +} + +static bool slab_cache_equal(long key1, long key2, void *ctx __maybe_unused) +{ + return key1 == key2; +} + +static void check_slab_cache_iter(struct lock_contention *con) +{ + struct btf *btf = btf__load_vmlinux_btf(); + s32 ret; + + hashmap__init(&slab_hash, slab_cache_hash, slab_cache_equal, /*ctx=*/NULL); + + if (btf == NULL) { + pr_debug("BTF loading failed: %s\n", strerror(errno)); + return; + } + + ret = btf__find_by_name_kind(btf, "bpf_iter__kmem_cache", BTF_KIND_STRUCT); + if (ret < 0) { + bpf_program__set_autoload(skel->progs.slab_cache_iter, false); + pr_debug("slab cache iterator is not available: %d\n", ret); + goto out; + } + + has_slab_iter = true; + + bpf_map__set_max_entries(skel->maps.slab_caches, con->map_nr_entries); +out: + btf__free(btf); +} + +static void run_slab_cache_iter(void) +{ + int fd; + char buf[256]; + long key, *prev_key; + + if (!has_slab_iter) + return; + + fd = bpf_iter_create(bpf_link__fd(skel->links.slab_cache_iter)); + if (fd < 0) { + pr_debug("cannot create slab cache iter: %d\n", fd); + return; + } + + /* This will run the bpf program */ + while (read(fd, buf, sizeof(buf)) > 0) + continue; + + close(fd); + + /* Read the slab cache map and build a hash with IDs */ + fd = bpf_map__fd(skel->maps.slab_caches); + prev_key = NULL; + while (!bpf_map_get_next_key(fd, prev_key, &key)) { + struct slab_cache_data *data; + + data = malloc(sizeof(*data)); + if (data == NULL) + break; + + if (bpf_map_lookup_elem(fd, &key, data) < 0) + break; + + hashmap__add(&slab_hash, data->id, data); + prev_key = &key; + } +} + +static void exit_slab_cache_iter(void) +{ + struct hashmap_entry *cur; + unsigned bkt; + + hashmap__for_each_entry(&slab_hash, cur, bkt) + free(cur->pvalue); + + hashmap__clear(&slab_hash); +} int lock_contention_prepare(struct lock_contention *con) { int i, fd; - int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1; + int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1, nslabs = 1; struct evlist *evlist = con->evlist; struct target *target = con->target; @@ -109,6 +199,15 @@ int lock_contention_prepare(struct lock_contention *con) skel->rodata->use_cgroup_v2 = 1; } + check_slab_cache_iter(con); + + if (con->filters->nr_slabs && has_slab_iter) { + skel->rodata->has_slab = 1; + nslabs = con->filters->nr_slabs; + } + + bpf_map__set_max_entries(skel->maps.slab_filter, nslabs); + if (lock_contention_bpf__load(skel) < 0) { pr_err("Failed to load lock-contention BPF skeleton\n"); return -1; @@ -179,6 +278,36 @@ int lock_contention_prepare(struct lock_contention *con) bpf_program__set_autoload(skel->progs.collect_lock_syms, false); lock_contention_bpf__attach(skel); + + /* run the slab iterator after attaching */ + run_slab_cache_iter(); + + if (con->filters->nr_slabs) { + u8 val = 1; + int cache_fd; + long key, *prev_key; + + fd = bpf_map__fd(skel->maps.slab_filter); + + /* Read the slab cache map and build a hash with its address */ + cache_fd = bpf_map__fd(skel->maps.slab_caches); + prev_key = NULL; + while (!bpf_map_get_next_key(cache_fd, prev_key, &key)) { + struct slab_cache_data data; + + if (bpf_map_lookup_elem(cache_fd, &key, &data) < 0) + break; + + for (i = 0; i < con->filters->nr_slabs; i++) { + if (!strcmp(con->filters->slabs[i], data.name)) { + bpf_map_update_elem(fd, &key, &val, BPF_ANY); + break; + } + } + prev_key = &key; + } + } + return 0; } @@ -347,6 +476,7 @@ static const char *lock_contention_get_name(struct lock_contention *con, if (con->aggr_mode == LOCK_AGGR_ADDR) { int lock_fd = bpf_map__fd(skel->maps.lock_syms); + struct slab_cache_data *slab_data; /* per-process locks set upper bits of the flags */ if (flags & LCD_F_MMAP_LOCK) @@ -365,6 +495,12 @@ static const char *lock_contention_get_name(struct lock_contention *con, return "rq_lock"; } + /* look slab_hash for dynamic locks in a slab object */ + if (hashmap__find(&slab_hash, flags & LCB_F_SLAB_ID_MASK, &slab_data)) { + snprintf(name_buf, sizeof(name_buf), "&%s", slab_data->name); + return name_buf; + } + return ""; } @@ -458,7 +594,7 @@ int lock_contention_read(struct lock_contention *con) if (con->save_callstack) { bpf_map_lookup_elem(stack, &key.stack_id, stack_trace); - if (!match_callstack_filter(machine, stack_trace)) { + if (!match_callstack_filter(machine, stack_trace, con->max_stack)) { con->nr_filtered += data.count; goto next; } @@ -539,5 +675,7 @@ int lock_contention_finish(struct lock_contention *con) cgroup__put(cgrp); } + exit_slab_cache_iter(); + return 0; } diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c index a590a8ac1f9d..4269b41d1771 100644 --- a/tools/perf/util/bpf_off_cpu.c +++ b/tools/perf/util/bpf_off_cpu.c @@ -100,6 +100,11 @@ static void check_sched_switch_args(void) const struct btf_type *t1, *t2, *t3; u32 type_id; + if (!btf) { + pr_debug("Missing btf, check if CONFIG_DEBUG_INFO_BTF is enabled\n"); + goto cleanup; + } + type_id = btf__find_by_name_kind(btf, "btf_trace_sched_switch", BTF_KIND_TYPEDEF); if ((s32)type_id < 0) diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 4a62ed593e84..e4352881e3fa 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -431,9 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid) static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) { bool augmented, do_output = false; - int zero = 0, size, aug_size, index, - value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); + int zero = 0, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */ + s64 aug_size, size; unsigned int nr, *beauty_map; struct beauty_payload_enter *payload; void *arg, *payload_offset; @@ -484,14 +484,11 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } else if (size > 0 && size <= value_size) { /* struct */ if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, size, arg)) augmented = true; - } else if (size < 0 && size >= -6) { /* buffer */ + } else if ((int)size < 0 && size >= -6) { /* buffer */ index = -(size + 1); barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick. index &= 7; // Satisfy the bounds checking with the verifier in some kernels. - aug_size = args->args[index]; - - if (aug_size > TRACE_AUG_MAX_BUF) - aug_size = TRACE_AUG_MAX_BUF; + aug_size = args->args[index] > TRACE_AUG_MAX_BUF ? TRACE_AUG_MAX_BUF : args->args[index]; if (aug_size > 0) { if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, aug_size, arg)) diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c index f613dc9cb123..fb144811b34f 100644 --- a/tools/perf/util/bpf_skel/func_latency.bpf.c +++ b/tools/perf/util/bpf_skel/func_latency.bpf.c @@ -38,9 +38,18 @@ struct { int enabled = 0; +// stats +__s64 total; +__s64 count; +__s64 max; +__s64 min; + const volatile int has_cpu = 0; const volatile int has_task = 0; const volatile int use_nsec = 0; +const volatile unsigned int bucket_range; +const volatile unsigned int min_latency; +const volatile unsigned int max_latency; SEC("kprobe/func") int BPF_PROG(func_begin) @@ -92,7 +101,7 @@ int BPF_PROG(func_end) start = bpf_map_lookup_elem(&functime, &tid); if (start) { __s64 delta = bpf_ktime_get_ns() - *start; - __u32 key; + __u32 key = 0; __u64 *hist; bpf_map_delete_elem(&functime, &tid); @@ -100,17 +109,52 @@ int BPF_PROG(func_end) if (delta < 0) return 0; + if (bucket_range != 0) { + delta /= cmp_base; + + if (min_latency > 0) { + if (delta > min_latency) + delta -= min_latency; + else + goto do_lookup; + } + + // Less than 1 unit (ms or ns), or, in the future, + // than the min latency desired. + if (delta > 0) { // 1st entry: [ 1 unit .. bucket_range units ) + // clang 12 doesn't like s64 / u32 division + key = (__u64)delta / bucket_range + 1; + if (key >= NUM_BUCKET || + delta >= max_latency - min_latency) + key = NUM_BUCKET - 1; + } + + delta += min_latency; + goto do_lookup; + } // calculate index using delta for (key = 0; key < (NUM_BUCKET - 1); key++) { if (delta < (cmp_base << key)) break; } +do_lookup: hist = bpf_map_lookup_elem(&latency, &key); if (!hist) return 0; *hist += 1; + + if (bucket_range == 0) + delta /= cmp_base; + + __sync_fetch_and_add(&total, delta); + __sync_fetch_and_add(&count, 1); + + if (delta > max) + max = delta; + if (delta < min) + min = delta; } return 0; diff --git a/tools/perf/util/bpf_skel/kwork_top.bpf.c b/tools/perf/util/bpf_skel/kwork_top.bpf.c index 594da91965a2..73e32e063030 100644 --- a/tools/perf/util/bpf_skel/kwork_top.bpf.c +++ b/tools/perf/util/bpf_skel/kwork_top.bpf.c @@ -18,7 +18,9 @@ enum kwork_class_type { }; #define MAX_ENTRIES 102400 -#define MAX_NR_CPUS 2048 +#ifndef MAX_NR_CPUS +#define MAX_NR_CPUS 4096 +#endif #define PF_KTHREAD 0x00200000 #define MAX_COMMAND_LEN 16 diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 1069bda5d733..6533ea9b044c 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -100,6 +100,20 @@ struct { __uint(max_entries, 1); } cgroup_filter SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(long)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} slab_filter SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(long)); + __uint(value_size, sizeof(struct slab_cache_data)); + __uint(max_entries, 1); +} slab_caches SEC(".maps"); + struct rw_semaphore___old { struct task_struct *owner; } __attribute__((preserve_access_index)); @@ -116,12 +130,15 @@ struct mm_struct___new { struct rw_semaphore mmap_lock; } __attribute__((preserve_access_index)); +extern struct kmem_cache *bpf_get_kmem_cache(u64 addr) __ksym __weak; + /* control flags */ const volatile int has_cpu; const volatile int has_task; const volatile int has_type; const volatile int has_addr; const volatile int has_cgroup; +const volatile int has_slab; const volatile int needs_callstack; const volatile int stack_skip; const volatile int lock_owner; @@ -136,6 +153,8 @@ int perf_subsys_id = -1; __u64 end_ts; +__u32 slab_cache_id; + /* error stat */ int task_fail; int stack_fail; @@ -202,7 +221,7 @@ static inline int can_record(u64 *ctx) __u64 addr = ctx[0]; ok = bpf_map_lookup_elem(&addr_filter, &addr); - if (!ok) + if (!ok && !has_slab) return 0; } @@ -215,6 +234,17 @@ static inline int can_record(u64 *ctx) return 0; } + if (has_slab && bpf_get_kmem_cache) { + __u8 *ok; + __u64 addr = ctx[0]; + long kmem_cache_addr; + + kmem_cache_addr = (long)bpf_get_kmem_cache(addr); + ok = bpf_map_lookup_elem(&slab_filter, &kmem_cache_addr); + if (!ok) + return 0; + } + return 1; } @@ -487,8 +517,28 @@ int contention_end(u64 *ctx) }; int err; - if (aggr_mode == LOCK_AGGR_ADDR) - first.flags |= check_lock_type(pelem->lock, pelem->flags); + if (aggr_mode == LOCK_AGGR_ADDR) { + first.flags |= check_lock_type(pelem->lock, + pelem->flags & LCB_F_TYPE_MASK); + + /* Check if it's from a slab object */ + if (bpf_get_kmem_cache) { + struct kmem_cache *s; + struct slab_cache_data *d; + + s = bpf_get_kmem_cache(pelem->lock); + if (s != NULL) { + /* + * Save the ID of the slab cache in the flags + * (instead of full address) to reduce the + * space in the contention_data. + */ + d = bpf_map_lookup_elem(&slab_caches, &s); + if (d != NULL) + first.flags |= d->id; + } + } + } err = bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST); if (err < 0) { @@ -563,4 +613,43 @@ int BPF_PROG(end_timestamp) return 0; } +/* + * bpf_iter__kmem_cache added recently so old kernels don't have it in the + * vmlinux.h. But we cannot add it here since it will cause a compiler error + * due to redefinition of the struct on later kernels. + * + * So it uses a CO-RE trick to access the member only if it has the type. + * This will support both old and new kernels without compiler errors. + */ +struct bpf_iter__kmem_cache___new { + struct kmem_cache *s; +} __attribute__((preserve_access_index)); + +SEC("iter/kmem_cache") +int slab_cache_iter(void *ctx) +{ + struct kmem_cache *s = NULL; + struct slab_cache_data d; + const char *nameptr; + + if (bpf_core_type_exists(struct bpf_iter__kmem_cache)) { + struct bpf_iter__kmem_cache___new *iter = ctx; + + s = iter->s; + } + + if (s == NULL) + return 0; + + nameptr = s->name; + bpf_probe_read_kernel_str(d.name, sizeof(d.name), nameptr); + + d.id = ++slab_cache_id << LCB_F_SLAB_ID_SHIFT; + if (d.id >= LCB_F_SLAB_ID_END) + return 0; + + bpf_map_update_elem(&slab_caches, &s, &d, BPF_NOEXIST); + return 0; +} + char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index de12892f992f..c15f734d7fc4 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -32,7 +32,15 @@ struct contention_task_data { #define LCD_F_MMAP_LOCK (1U << 31) #define LCD_F_SIGHAND_LOCK (1U << 30) -#define LCB_F_MAX_FLAGS (1U << 7) +#define LCB_F_SLAB_ID_SHIFT 16 +#define LCB_F_SLAB_ID_START (1U << 16) +#define LCB_F_SLAB_ID_END (1U << 26) +#define LCB_F_SLAB_ID_MASK 0x03FF0000U + +#define LCB_F_TYPE_MAX (1U << 7) +#define LCB_F_TYPE_MASK 0x0000007FU + +#define SLAB_NAME_MAX 28 struct contention_data { u64 total_time; @@ -54,4 +62,9 @@ enum lock_class_sym { LOCK_CLASS_RQLOCK, }; +struct slab_cache_data { + u32 id; + char name[SLAB_NAME_MAX]; +}; + #endif /* UTIL_BPF_SKEL_LOCK_DATA_H */ diff --git a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h index 4dcad7b682bd..7b81d3173917 100644 --- a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h @@ -195,4 +195,12 @@ struct bpf_perf_event_data_kern { */ struct rq {}; +struct kmem_cache { + const char *name; +} __attribute__((preserve_access_index)); + +struct bpf_iter__kmem_cache { + struct kmem_cache *s; +} __attribute__((preserve_access_index)); + #endif // __VMLINUX_H diff --git a/tools/perf/util/btf.c b/tools/perf/util/btf.c new file mode 100644 index 000000000000..bb163fe87767 --- /dev/null +++ b/tools/perf/util/btf.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Copyright (C) 2024, Red Hat, Inc + */ + +#include <bpf/btf.h> +#include <util/btf.h> +#include <string.h> + +const struct btf_member *__btf_type__find_member_by_name(struct btf *btf, + int type_id, const char *member_name) +{ + const struct btf_type *t = btf__type_by_id(btf, type_id); + const struct btf_member *m; + int i; + + for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { + const char *current_member_name = btf__name_by_offset(btf, m->name_off); + + if (!strcmp(current_member_name, member_name)) + return m; + } + + return NULL; +} diff --git a/tools/perf/util/btf.h b/tools/perf/util/btf.h new file mode 100644 index 000000000000..05e6e5bf23d6 --- /dev/null +++ b/tools/perf/util/btf.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_UTIL_BTF +#define __PERF_UTIL_BTF 1 + +struct btf; +struct btf_member; + +const struct btf_member *__btf_type__find_member_by_name(struct btf *btf, + int type_id, const char *member_name); +#endif // __PERF_UTIL_BTF diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 0f759dd96db7..fbcc0626f9ce 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -473,7 +473,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, leader = NULL; evlist__for_each_entry(orig_list, pos) { - evsel = evsel__clone(pos); + evsel = evsel__clone(/*dest=*/NULL, pos); if (evsel == NULL) goto out_err; diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 68f9407ca74b..2d07c9257a1a 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -13,6 +13,7 @@ #include <sys/param.h> #include "cache.h" #include "callchain.h" +#include "header.h" #include <subcmd/exec-cmd.h> #include "util/event.h" /* proc_map_timeout */ #include "util/hist.h" /* perf_hist_config */ @@ -34,6 +35,22 @@ #define DEBUG_CACHE_DIR ".debug" +#define METRIC_ONLY_LEN 20 + +struct perf_stat_config stat_config = { + .aggr_mode = AGGR_GLOBAL, + .aggr_level = MAX_CACHE_LVL + 1, + .scale = true, + .unit_width = 4, /* strlen("unit") */ + .run_count = 1, + .metric_only_len = METRIC_ONLY_LEN, + .walltime_nsecs_stats = &walltime_nsecs_stats, + .ru_stats = &ru_stats, + .big_num = true, + .ctl_fd = -1, + .ctl_fd_ack = -1, + .iostat_run = false, +}; char buildid_dir[MAXPATHLEN]; /* root dir for buildid, binary cache */ @@ -455,6 +472,16 @@ static int perf_ui_config(const char *var, const char *value) return 0; } +void perf_stat__set_big_num(int set) +{ + stat_config.big_num = (set != 0); +} + +static void perf_stat__set_no_csv_summary(int set) +{ + stat_config.no_csv_summary = (set != 0); +} + static int perf_stat_config(const char *var, const char *value) { if (!strcmp(var, "stat.big-num")) diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index 9971313d61c1..a727c95cb119 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -50,6 +50,7 @@ int perf_config_set__collect(struct perf_config_set *set, const char *file_name, const char *var, const char *value); void perf_config__exit(void); void perf_config__refresh(void); +int perf_config__set_variable(const char *var, const char *value); /** * perf_config_sections__for_each - iterate thru all the sections diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 27094211edd8..5c329ad614e9 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -293,7 +293,7 @@ struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data) die = cpu__get_die_id(cpu); /* There is no die_id on legacy system. */ - if (die == -1) + if (die < 0) die = 0; /* @@ -322,7 +322,7 @@ struct aggr_cpu_id aggr_cpu_id__cluster(struct perf_cpu cpu, void *data) struct aggr_cpu_id id; /* There is no cluster_id on legacy system. */ - if (cluster == -1) + if (cluster < 0) cluster = 0; id = aggr_cpu_id__die(cpu, data); diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index f0599c61fab4..5e7ff09fbc95 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -426,8 +426,9 @@ static int add_tracepoint_values(struct ctf_writer *cw, struct evsel *evsel, struct perf_sample *sample) { - struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; - struct tep_format_field *fields = evsel->tp_format->format.fields; + const struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *common_fields = tp_format->format.common_fields; + struct tep_format_field *fields = tp_format->format.fields; int ret; ret = add_tracepoint_fields_values(cw, event_class, event, @@ -1064,8 +1065,9 @@ static int add_tracepoint_types(struct ctf_writer *cw, struct evsel *evsel, struct bt_ctf_event_class *class) { - struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; - struct tep_format_field *fields = evsel->tp_format->format.fields; + const struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *common_fields = tp_format ? tp_format->format.common_fields : NULL; + struct tep_format_field *fields = tp_format ? tp_format->format.fields : NULL; int ret; ret = add_tracepoint_fields_types(cw, common_fields, class); diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c index 8304cd2d4a9c..d9f805bf6fb0 100644 --- a/tools/perf/util/data-convert-json.c +++ b/tools/perf/util/data-convert-json.c @@ -230,12 +230,12 @@ static int process_sample_event(const struct perf_tool *tool, #ifdef HAVE_LIBTRACEEVENT if (sample->raw_data) { - int i; - struct tep_format_field **fields; + struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field **fields = tp_format ? tep_event_fields(tp_format) : NULL; - fields = tep_event_fields(evsel->tp_format); if (fields) { - i = 0; + int i = 0; + while (fields[i]) { struct trace_seq s; diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index 41a2b08670dc..50c5c206b70e 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -1245,6 +1245,9 @@ int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, s scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.", dso__long_name(dso)); break; + case SYMBOL_ANNOTATE_ERRNO__COULDNT_DETERMINE_FILE_TYPE: + scnprintf(buf, buflen, "Couldn't determine the file %s type.", dso__long_name(dso)); + break; default: scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum); break; @@ -2213,56 +2216,6 @@ out_free_command: return err; } -static int annotation_options__init_disassemblers(struct annotation_options *options) -{ - char *disassembler; - - if (options->disassemblers_str == NULL) { - const char *default_disassemblers_str = -#ifdef HAVE_LIBLLVM_SUPPORT - "llvm," -#endif -#ifdef HAVE_LIBCAPSTONE_SUPPORT - "capstone," -#endif - "objdump"; - - options->disassemblers_str = strdup(default_disassemblers_str); - if (!options->disassemblers_str) - goto out_enomem; - } - - disassembler = strdup(options->disassemblers_str); - if (disassembler == NULL) - goto out_enomem; - - while (1) { - char *comma = strchr(disassembler, ','); - - if (comma != NULL) - *comma = '\0'; - - options->disassemblers[options->nr_disassemblers++] = strim(disassembler); - - if (comma == NULL) - break; - - disassembler = comma + 1; - - if (options->nr_disassemblers >= MAX_DISASSEMBLERS) { - pr_debug("annotate.disassemblers can have at most %d entries, ignoring \"%s\"\n", - MAX_DISASSEMBLERS, disassembler); - break; - } - } - - return 0; - -out_enomem: - pr_err("Not enough memory for annotate.disassemblers\n"); - return -1; -} - int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { struct annotation_options *options = args->options; @@ -2271,7 +2224,6 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) char symfs_filename[PATH_MAX]; bool delete_extract = false; struct kcore_extract kce; - const char *disassembler; bool decomp = false; int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename)); @@ -2289,7 +2241,7 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) } else if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) { return symbol__disassemble_bpf_image(sym, args); } else if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) { - return -1; + return SYMBOL_ANNOTATE_ERRNO__COULDNT_DETERMINE_FILE_TYPE; } else if (dso__is_kcore(dso)) { kce.addr = map__rip_2objdump(map, sym->start); kce.kcore_filename = symfs_filename; @@ -2331,28 +2283,26 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) } } - err = annotation_options__init_disassemblers(options); - if (err) - goto out_remove_tmp; - err = -1; + for (u8 i = 0; i < ARRAY_SIZE(options->disassemblers) && err != 0; i++) { + enum perf_disassembler dis = options->disassemblers[i]; - for (int i = 0; i < options->nr_disassemblers && err != 0; ++i) { - disassembler = options->disassemblers[i]; - - if (!strcmp(disassembler, "llvm")) + switch (dis) { + case PERF_DISASM_LLVM: err = symbol__disassemble_llvm(symfs_filename, sym, args); - else if (!strcmp(disassembler, "capstone")) + break; + case PERF_DISASM_CAPSTONE: err = symbol__disassemble_capstone(symfs_filename, sym, args); - else if (!strcmp(disassembler, "objdump")) + break; + case PERF_DISASM_OBJDUMP: err = symbol__disassemble_objdump(symfs_filename, sym, args); - else - pr_debug("Unknown disassembler %s, skipping...\n", disassembler); - } - - if (err == 0) { - pr_debug("Disassembled with %s\nannotate.disassemblers=%s\n", - disassembler, options->disassemblers_str); + break; + case PERF_DISASM_UNKNOWN: /* End of disassemblers. */ + default: + goto out_remove_tmp; + } + if (err == 0) + pr_debug("Disassembled with %s\n", perf_disassembler__strs[dis]); } out_remove_tmp: if (decomp) diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index 7d180bdaedbc..ddacef881af2 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -234,7 +234,8 @@ static const __u8 *dlfilter__insn(void *ctx, __u32 *len) struct machine *machine = maps__machine(thread__maps(al->thread)); if (machine) - script_fetch_insn(d->sample, al->thread, machine); + script_fetch_insn(d->sample, al->thread, machine, + /*native_arch=*/true); } } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index e2843ca2edd9..cae4f6d63318 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -24,15 +24,19 @@ struct perf_env perf_env; #include "bpf-utils.h" #include <bpf/libbpf.h> -void perf_env__insert_bpf_prog_info(struct perf_env *env, +bool perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) { + bool ret; + down_write(&env->bpf_progs.lock); - __perf_env__insert_bpf_prog_info(env, info_node); + ret = __perf_env__insert_bpf_prog_info(env, info_node); up_write(&env->bpf_progs.lock); + + return ret; } -void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) +bool __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) { __u32 prog_id = info_node->info_linear->info.id; struct bpf_prog_info_node *node; @@ -50,13 +54,14 @@ void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info p = &(*p)->rb_right; } else { pr_debug("duplicated bpf prog info %u\n", prog_id); - return; + return false; } } rb_link_node(&info_node->rb_node, parent, p); rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos); env->bpf_progs.infos_cnt++; + return true; } struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, @@ -326,10 +331,13 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) for (idx = 0; idx < nr_cpus; ++idx) { struct perf_cpu cpu = { .cpu = idx }; + int core_id = cpu__get_core_id(cpu); + int socket_id = cpu__get_socket_id(cpu); + int die_id = cpu__get_die_id(cpu); - env->cpu[idx].core_id = cpu__get_core_id(cpu); - env->cpu[idx].socket_id = cpu__get_socket_id(cpu); - env->cpu[idx].die_id = cpu__get_die_id(cpu); + env->cpu[idx].core_id = core_id >= 0 ? core_id : -1; + env->cpu[idx].socket_id = socket_id >= 0 ? socket_id : -1; + env->cpu[idx].die_id = die_id >= 0 ? die_id : -1; } env->nr_cpus_avail = nr_cpus; @@ -472,15 +480,19 @@ const char *perf_env__arch(struct perf_env *env) return normalize_arch(arch_name); } +#if defined(HAVE_LIBTRACEEVENT) +#include "trace/beauty/arch_errno_names.c" +#endif + const char *perf_env__arch_strerrno(struct perf_env *env __maybe_unused, int err __maybe_unused) { -#if defined(HAVE_SYSCALL_TABLE_SUPPORT) && defined(HAVE_LIBTRACEEVENT) +#if defined(HAVE_LIBTRACEEVENT) if (env->arch_strerrno == NULL) env->arch_strerrno = arch_syscalls__strerrno_function(perf_env__arch(env)); return env->arch_strerrno ? env->arch_strerrno(err) : "no arch specific strerrno function"; #else - return "!(HAVE_SYSCALL_TABLE_SUPPORT && HAVE_LIBTRACEEVENT)"; + return "!HAVE_LIBTRACEEVENT"; #endif } diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index ae604c4edbb7..d90e343cf1fa 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -56,8 +56,6 @@ struct pmu_caps { typedef const char *(arch_syscalls__strerrno_t)(int err); -arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch); - struct perf_env { char *hostname; char *os_release; @@ -176,9 +174,9 @@ const char *perf_env__raw_arch(struct perf_env *env); int perf_env__nr_cpus_avail(struct perf_env *env); void perf_env__init(struct perf_env *env); -void __perf_env__insert_bpf_prog_info(struct perf_env *env, +bool __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); -void perf_env__insert_bpf_prog_info(struct perf_env *env, +bool perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, __u32 prog_id); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index d22c5df1701e..bc144388f892 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -395,6 +395,7 @@ void evsel__init(struct evsel *evsel, evsel->group_pmu_name = NULL; evsel->skippable = false; evsel->alternate_hw_config = PERF_COUNT_HW_MAX; + evsel->script_output_type = -1; // FIXME: OUTPUT_TYPE_UNSET, see builtin-script.c } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -454,7 +455,7 @@ static int evsel__copy_config_terms(struct evsel *dst, struct evsel *src) * The assumption is that @orig is not configured nor opened yet. * So we only care about the attributes that can be set while it's parsed. */ -struct evsel *evsel__clone(struct evsel *orig) +struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig) { struct evsel *evsel; @@ -467,7 +468,11 @@ struct evsel *evsel__clone(struct evsel *orig) if (orig->bpf_obj) return NULL; - evsel = evsel__new(&orig->core.attr); + if (dest) + evsel = dest; + else + evsel = evsel__new(&orig->core.attr); + if (evsel == NULL) return NULL; @@ -512,11 +517,12 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->core.leader = orig->core.leader; evsel->max_events = orig->max_events; - free((char *)evsel->unit); - evsel->unit = strdup(orig->unit); - if (evsel->unit == NULL) - goto out_err; - + zfree(&evsel->unit); + if (orig->unit) { + evsel->unit = strdup(orig->unit); + if (evsel->unit == NULL) + goto out_err; + } evsel->scale = orig->scale; evsel->snapshot = orig->snapshot; evsel->per_pkg = orig->per_pkg; @@ -544,53 +550,101 @@ out_err: return NULL; } +static int trace_event__id(const char *sys, const char *name) +{ + char *tp_dir = get_events_file(sys); + char path[PATH_MAX]; + int id, err; + + if (!tp_dir) + return -1; + + scnprintf(path, PATH_MAX, "%s/%s/id", tp_dir, name); + put_events_file(tp_dir); + err = filename__read_int(path, &id); + if (err) + return err; + + return id; +} + /* * Returns pointer with encoded error via <linux/err.h> interface. */ -#ifdef HAVE_LIBTRACEEVENT struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool format) { + struct perf_event_attr attr = { + .type = PERF_TYPE_TRACEPOINT, + .sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), + }; struct evsel *evsel = zalloc(perf_evsel__object.size); - int err = -ENOMEM; + int err = -ENOMEM, id = -1; - if (evsel == NULL) { + if (evsel == NULL) goto out_err; - } else { - struct perf_event_attr attr = { - .type = PERF_TYPE_TRACEPOINT, - .sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | - PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), - }; - if (asprintf(&evsel->name, "%s:%s", sys, name) < 0) + + if (asprintf(&evsel->name, "%s:%s", sys, name) < 0) + goto out_free; + +#ifdef HAVE_LIBTRACEEVENT + evsel->tp_sys = strdup(sys); + if (!evsel->tp_sys) + goto out_free; + + evsel->tp_name = strdup(name); + if (!evsel->tp_name) + goto out_free; +#endif + + event_attr_init(&attr); + + if (format) { + id = trace_event__id(sys, name); + if (id < 0) { + err = id; goto out_free; - - event_attr_init(&attr); - - if (format) { - evsel->tp_format = trace_event__tp_format(sys, name); - if (IS_ERR(evsel->tp_format)) { - err = PTR_ERR(evsel->tp_format); - goto out_free; - } - attr.config = evsel->tp_format->id; - } else { - attr.config = (__u64) -1; } - - - attr.sample_period = 1; - evsel__init(evsel, &attr, idx); } - + attr.config = (__u64)id; + attr.sample_period = 1; + evsel__init(evsel, &attr, idx); return evsel; out_free: zfree(&evsel->name); +#ifdef HAVE_LIBTRACEEVENT + zfree(&evsel->tp_sys); + zfree(&evsel->tp_name); +#endif free(evsel); out_err: return ERR_PTR(err); } + +#ifdef HAVE_LIBTRACEEVENT +struct tep_event *evsel__tp_format(struct evsel *evsel) +{ + struct tep_event *tp_format = evsel->tp_format; + + if (tp_format) + return tp_format; + + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) + return NULL; + + tp_format = trace_event__tp_format(evsel->tp_sys, evsel->tp_name); + if (IS_ERR(tp_format)) { + int err = -PTR_ERR(evsel->tp_format); + + pr_err("Error getting tracepoint format '%s' '%s'(%d)\n", + evsel__name(evsel), strerror(err), err); + return NULL; + } + evsel->tp_format = tp_format; + return evsel->tp_format; +} #endif const char *const evsel__hw_names[PERF_COUNT_HW_MAX] = { @@ -1103,6 +1157,9 @@ static void evsel__apply_config_terms(struct evsel *evsel, case EVSEL__CONFIG_TERM_AUX_OUTPUT: attr->aux_output = term->val.aux_output ? 1 : 0; break; + case EVSEL__CONFIG_TERM_AUX_ACTION: + /* Already applied by auxtrace */ + break; case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: /* Already applied by auxtrace */ break; @@ -1587,6 +1644,10 @@ void evsel__exit(struct evsel *evsel) perf_thread_map__put(evsel->core.threads); zfree(&evsel->group_name); zfree(&evsel->name); +#ifdef HAVE_LIBTRACEEVENT + zfree(&evsel->tp_sys); + zfree(&evsel->tp_name); +#endif zfree(&evsel->filter); zfree(&evsel->group_pmu_name); zfree(&evsel->unit); @@ -2090,16 +2151,17 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, return err; } -static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) +static bool __has_attr_feature(struct perf_event_attr *attr, + struct perf_cpu cpu, unsigned long flags) { - int fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1, + int fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, cpu.cpu, /*group_fd=*/-1, flags); close(fd); if (fd < 0) { attr->exclude_kernel = 1; - fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1, + fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, cpu.cpu, /*group_fd=*/-1, flags); close(fd); } @@ -2107,7 +2169,7 @@ static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) if (fd < 0) { attr->exclude_hv = 1; - fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1, + fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, cpu.cpu, /*group_fd=*/-1, flags); close(fd); } @@ -2115,7 +2177,7 @@ static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) if (fd < 0) { attr->exclude_guest = 1; - fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1, + fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, cpu.cpu, /*group_fd=*/-1, flags); close(fd); } @@ -2127,6 +2189,13 @@ static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) return fd >= 0; } +static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) +{ + struct perf_cpu cpu = {.cpu = -1}; + + return __has_attr_feature(attr, cpu, flags); +} + static void evsel__detect_missing_pmu_features(struct evsel *evsel) { struct perf_event_attr attr = { @@ -2215,7 +2284,65 @@ found: errno = old_errno; } -static bool evsel__detect_missing_features(struct evsel *evsel) +static bool evsel__probe_aux_action(struct evsel *evsel, struct perf_cpu cpu) +{ + struct perf_event_attr attr = evsel->core.attr; + int old_errno = errno; + + attr.disabled = 1; + attr.aux_start_paused = 1; + + if (__has_attr_feature(&attr, cpu, /*flags=*/0)) { + errno = old_errno; + return true; + } + + /* + * EOPNOTSUPP means the kernel supports the feature but the PMU does + * not, so keep that distinction if possible. + */ + if (errno != EOPNOTSUPP) + errno = old_errno; + + return false; +} + +static void evsel__detect_missing_aux_action_feature(struct evsel *evsel, struct perf_cpu cpu) +{ + static bool detection_done; + struct evsel *leader; + + /* + * Don't bother probing aux_action if it is not being used or has been + * probed before. + */ + if (!evsel->core.attr.aux_action || detection_done) + return; + + detection_done = true; + + /* + * The leader is an AUX area event. If it has failed, assume the feature + * is not supported. + */ + leader = evsel__leader(evsel); + if (evsel == leader) { + perf_missing_features.aux_action = true; + return; + } + + /* + * AUX area event with aux_action must have been opened successfully + * already, so feature is supported. + */ + if (leader->core.attr.aux_action) + return; + + if (!evsel__probe_aux_action(leader, cpu)) + perf_missing_features.aux_action = true; +} + +static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu cpu) { static bool detection_done = false; struct perf_event_attr attr = { @@ -2225,6 +2352,8 @@ static bool evsel__detect_missing_features(struct evsel *evsel) }; int old_errno; + evsel__detect_missing_aux_action_feature(evsel, cpu); + evsel__detect_missing_pmu_features(evsel); if (evsel__has_br_stack(evsel)) @@ -2439,6 +2568,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int idx, thread, nthreads; int pid = -1, err, old_errno; enum rlimit_action set_rlimit = NO_CHANGE; + struct perf_cpu cpu; if (evsel__is_retire_lat(evsel)) return tpebs_start(evsel->evlist); @@ -2476,6 +2606,7 @@ fallback_missing_features: } for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { + cpu = perf_cpu_map__cpu(cpus, idx); for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; @@ -2496,10 +2627,9 @@ retry_open: /* Debug message used by test scripts */ pr_debug2_peo("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", - pid, perf_cpu_map__cpu(cpus, idx).cpu, group_fd, evsel->open_flags); + pid, cpu.cpu, group_fd, evsel->open_flags); - fd = sys_perf_event_open(&evsel->core.attr, pid, - perf_cpu_map__cpu(cpus, idx).cpu, + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, group_fd, evsel->open_flags); FD(evsel, idx, thread) = fd; @@ -2515,8 +2645,7 @@ retry_open: bpf_counter__install_pe(evsel, idx, fd); if (unlikely(test_attr__enabled())) { - test_attr__open(&evsel->core.attr, pid, - perf_cpu_map__cpu(cpus, idx), + test_attr__open(&evsel->core.attr, pid, cpu, fd, group_fd, evsel->open_flags); } @@ -2571,7 +2700,7 @@ try_fallback: if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit)) goto retry_open; - if (err == -EINVAL && evsel__detect_missing_features(evsel)) + if (err == -EINVAL && evsel__detect_missing_features(evsel, cpu)) goto fallback_missing_features; if (evsel__precise_ip_fallback(evsel)) @@ -3218,12 +3347,16 @@ u16 evsel__id_hdr_size(const struct evsel *evsel) #ifdef HAVE_LIBTRACEEVENT struct tep_format_field *evsel__field(struct evsel *evsel, const char *name) { - return tep_find_field(evsel->tp_format, name); + struct tep_event *tp_format = evsel__tp_format(evsel); + + return tp_format ? tep_find_field(tp_format, name) : NULL; } struct tep_format_field *evsel__common_field(struct evsel *evsel, const char *name) { - return tep_find_common_field(evsel->tp_format, name); + struct tep_event *tp_format = evsel__tp_format(evsel); + + return tp_format ? tep_find_common_field(tp_format, name) : NULL; } void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name) @@ -3448,6 +3581,78 @@ static bool find_process(const char *name) return ret ? false : true; } +static int dump_perf_event_processes(char *msg, size_t size) +{ + DIR *proc_dir; + struct dirent *proc_entry; + int printed = 0; + + proc_dir = opendir(procfs__mountpoint()); + if (!proc_dir) + return 0; + + /* Walk through the /proc directory. */ + while ((proc_entry = readdir(proc_dir)) != NULL) { + char buf[256]; + DIR *fd_dir; + struct dirent *fd_entry; + int fd_dir_fd; + + if (proc_entry->d_type != DT_DIR || + !isdigit(proc_entry->d_name[0]) || + strlen(proc_entry->d_name) > sizeof(buf) - 4) + continue; + + scnprintf(buf, sizeof(buf), "%s/fd", proc_entry->d_name); + fd_dir_fd = openat(dirfd(proc_dir), buf, O_DIRECTORY); + if (fd_dir_fd == -1) + continue; + fd_dir = fdopendir(fd_dir_fd); + if (!fd_dir) { + close(fd_dir_fd); + continue; + } + while ((fd_entry = readdir(fd_dir)) != NULL) { + ssize_t link_size; + + if (fd_entry->d_type != DT_LNK) + continue; + link_size = readlinkat(fd_dir_fd, fd_entry->d_name, buf, sizeof(buf)); + if (link_size < 0) + continue; + /* Take care as readlink doesn't null terminate the string. */ + if (!strncmp(buf, "anon_inode:[perf_event]", link_size)) { + int cmdline_fd; + ssize_t cmdline_size; + + scnprintf(buf, sizeof(buf), "%s/cmdline", proc_entry->d_name); + cmdline_fd = openat(dirfd(proc_dir), buf, O_RDONLY); + if (cmdline_fd == -1) + continue; + cmdline_size = read(cmdline_fd, buf, sizeof(buf) - 1); + close(cmdline_fd); + if (cmdline_size < 0) + continue; + buf[cmdline_size] = '\0'; + for (ssize_t i = 0; i < cmdline_size; i++) { + if (buf[i] == '\0') + buf[i] = ' '; + } + + if (printed == 0) + printed += scnprintf(msg, size, "Possible processes:\n"); + + printed += scnprintf(msg + printed, size - printed, + "%s %s\n", proc_entry->d_name, buf); + break; + } + } + closedir(fd_dir); + } + closedir(proc_dir); + return printed; +} + int __weak arch_evsel__open_strerror(struct evsel *evsel __maybe_unused, char *msg __maybe_unused, size_t size __maybe_unused) @@ -3481,7 +3686,7 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, printed += scnprintf(msg, size, "No permission to enable %s event.\n\n", evsel__name(evsel)); - return scnprintf(msg + printed, size - printed, + return printed + scnprintf(msg + printed, size - printed, "Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open\n" "access to performance monitoring and observability operations for processes\n" "without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability.\n" @@ -3526,6 +3731,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "%s: PMU Hardware doesn't support 'aux_output' feature", evsel__name(evsel)); + if (evsel->core.attr.aux_action) + return scnprintf(msg, size, + "%s: PMU Hardware doesn't support 'aux_action' feature", + evsel__name(evsel)); if (evsel->core.attr.sample_period != 0) return scnprintf(msg, size, "%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'", @@ -3544,6 +3753,11 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "The PMU counters are busy/taken by another profiler.\n" "We found oprofile daemon running, please stop it and try again."); + printed += scnprintf( + msg, size, + "The PMU %s counters are busy and in use by another process.\n", + evsel->pmu ? evsel->pmu->name : ""); + return printed + dump_perf_event_processes(msg + printed, size - printed); break; case EINVAL: if (evsel->core.attr.sample_type & PERF_SAMPLE_CODE_PAGE_SIZE && perf_missing_features.code_page_size) @@ -3556,6 +3770,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "clockid feature not supported."); if (perf_missing_features.clockid_wrong) return scnprintf(msg, size, "wrong clockid (%d).", clockid); + if (perf_missing_features.aux_action) + return scnprintf(msg, size, "The 'aux_action' feature is not supported, update the kernel."); if (perf_missing_features.aux_output) return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); if (!target__has_cpu(target)) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 04934a7af174..5e789fa80590 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -59,6 +59,8 @@ struct evsel { char *group_name; const char *group_pmu_name; #ifdef HAVE_LIBTRACEEVENT + char *tp_sys; + char *tp_name; struct tep_event *tp_format; #endif char *filter; @@ -119,6 +121,7 @@ struct evsel { bool default_metricgroup; /* A member of the Default metricgroup */ struct hashmap *per_pkg_mask; int err; + int script_output_type; struct { evsel__sb_cb_t *cb; void *data; @@ -205,6 +208,7 @@ struct perf_missing_features { bool weight_struct; bool read_lost; bool branch_counters; + bool aux_action; bool inherit_sample_read; }; @@ -241,26 +245,23 @@ static inline struct evsel *evsel__new(struct perf_event_attr *attr) return evsel__new_idx(attr, 0); } -struct evsel *evsel__clone(struct evsel *orig); +struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig); int copy_config_terms(struct list_head *dst, struct list_head *src); void free_config_terms(struct list_head *config_terms); -#ifdef HAVE_LIBTRACEEVENT -struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool format); - /* * Returns pointer with encoded error via <linux/err.h> interface. */ +struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool format); static inline struct evsel *evsel__newtp(const char *sys, const char *name) { return evsel__newtp_idx(sys, name, 0, true); } -#endif #ifdef HAVE_LIBTRACEEVENT -struct tep_event *event_format__new(const char *sys, const char *name); +struct tep_event *evsel__tp_format(struct evsel *evsel); #endif void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx); diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h index aee6f808b512..af52a1516d0b 100644 --- a/tools/perf/util/evsel_config.h +++ b/tools/perf/util/evsel_config.h @@ -25,6 +25,7 @@ enum evsel_term_type { EVSEL__CONFIG_TERM_BRANCH, EVSEL__CONFIG_TERM_PERCORE, EVSEL__CONFIG_TERM_AUX_OUTPUT, + EVSEL__CONFIG_TERM_AUX_ACTION, EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE, EVSEL__CONFIG_TERM_CFG_CHG, }; diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 86b7f46f9e2a..103984b29b1e 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -81,13 +81,15 @@ int evsel__fprintf(struct evsel *evsel, struct perf_attr_details *details, FILE #ifdef HAVE_LIBTRACEEVENT if (details->trace_fields) { struct tep_format_field *field; + const struct tep_event *tp_format; if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { printed += comma_fprintf(fp, &first, " (not a tracepoint)"); goto out; } - field = evsel->tp_format->format.fields; + tp_format = evsel__tp_format(evsel); + field = tp_format ? tp_format->format.fields : NULL; if (field == NULL) { printed += comma_fprintf(fp, &first, " (no trace field)"); goto out; diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index f289044a1f7c..c221dcce6666 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -285,7 +285,7 @@ struct expr_parse_ctx *expr__ctx_new(void) { struct expr_parse_ctx *ctx; - ctx = malloc(sizeof(struct expr_parse_ctx)); + ctx = calloc(1, sizeof(struct expr_parse_ctx)); if (!ctx) return NULL; @@ -294,9 +294,6 @@ struct expr_parse_ctx *expr__ctx_new(void) free(ctx); return NULL; } - ctx->sctx.user_requested_cpu_list = NULL; - ctx->sctx.runtime = 0; - ctx->sctx.system_wide = false; return ctx; } diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h index bae649ef50e8..5dee2caba0fe 100644 --- a/tools/perf/util/ftrace.h +++ b/tools/perf/util/ftrace.h @@ -7,6 +7,7 @@ struct evlist; struct hashamp; +struct stats; struct perf_ftrace { struct evlist *evlist; @@ -20,6 +21,9 @@ struct perf_ftrace { unsigned long percpu_buffer_size; bool inherit; bool use_nsec; + unsigned int bucket_range; + unsigned int min_latency; + unsigned int max_latency; int graph_depth; int func_stack_trace; int func_irq_info; @@ -43,7 +47,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace); int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace); int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace); int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace, - int buckets[]); + int buckets[], struct stats *stats); int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace); #else /* !HAVE_BPF_SKEL */ @@ -68,7 +72,8 @@ perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) static inline int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, - int buckets[] __maybe_unused) + int buckets[] __maybe_unused, + struct stats *stats __maybe_unused) { return -1; } diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index 1b5140e5ce99..6a73c903d690 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -38,7 +38,7 @@ do done echo "#endif /* HAVE_LIBELF_SUPPORT */" -echo "#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT))" +echo "#if defined(HAVE_LIBTRACEEVENT)" sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt | sort | while read cmd @@ -51,7 +51,7 @@ do p }' "Documentation/perf-$cmd.txt" done -echo "#endif /* HAVE_LIBTRACEEVENT && (HAVE_LIBAUDIT_SUPPORT || HAVE_SYSCALL_TABLE_SUPPORT) */" +echo "#endif /* HAVE_LIBTRACEEVENT */" echo "#ifdef HAVE_LIBTRACEEVENT" sed -n -e 's/^perf-\([^ ]*\)[ ].* traceevent.*/\1/p' command-list.txt | diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 3451e542b69a..d06aa86352d3 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -3158,7 +3158,10 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) /* after reading from file, translate offset to address */ bpil_offs_to_addr(info_linear); info_node->info_linear = info_linear; - __perf_env__insert_bpf_prog_info(env, info_node); + if (!__perf_env__insert_bpf_prog_info(env, info_node)) { + free(info_linear); + free(info_node); + } } up_write(&env->bpf_progs.lock); @@ -3205,7 +3208,8 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) if (__do_read(ff, node->data, data_size)) goto out; - __perf_env__insert_btf(env, node); + if (!__perf_env__insert_btf(env, node)) + free(node); node = NULL; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index fff134565801..0f30f843c566 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -32,6 +32,9 @@ #include <linux/time64.h> #include <linux/zalloc.h> +static int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); +static int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); + static bool hists__filter_entry_by_dso(struct hists *hists, struct hist_entry *he); static bool hists__filter_entry_by_thread(struct hists *hists, @@ -1292,19 +1295,35 @@ out: return err; } -int64_t -hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) +static int64_t +hist_entry__cmp_impl(struct perf_hpp_list *hpp_list, struct hist_entry *left, + struct hist_entry *right, unsigned long fn_offset, + bool ignore_dynamic, bool ignore_skipped) { struct hists *hists = left->hists; struct perf_hpp_fmt *fmt; - int64_t cmp = 0; + perf_hpp_fmt_cmp_t *fn; + int64_t cmp; - hists__for_each_sort_list(hists, fmt) { - if (perf_hpp__is_dynamic_entry(fmt) && + /* + * Never collapse filtered and non-filtered entries. + * Note this is not the same as having an extra (invisible) fmt + * that corresponds to the filtered status. + */ + cmp = (int64_t)!!left->filtered - (int64_t)!!right->filtered; + if (cmp) + return cmp; + + perf_hpp_list__for_each_sort_list(hpp_list, fmt) { + if (ignore_dynamic && perf_hpp__is_dynamic_entry(fmt) && !perf_hpp__defined_dynamic_entry(fmt, hists)) continue; - cmp = fmt->cmp(fmt, left, right); + if (ignore_skipped && perf_hpp__should_skip(fmt, hists)) + continue; + + fn = (void *)fmt + fn_offset; + cmp = (*fn)(fmt, left, right); if (cmp) break; } @@ -1312,24 +1331,34 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) return cmp; } +int64_t +hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_impl(left->hists->hpp_list, left, right, + offsetof(struct perf_hpp_fmt, cmp), true, false); +} + +static int64_t +hist_entry__sort(struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_impl(left->hists->hpp_list, left, right, + offsetof(struct perf_hpp_fmt, sort), false, true); +} + int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) { - struct hists *hists = left->hists; - struct perf_hpp_fmt *fmt; - int64_t cmp = 0; + return hist_entry__cmp_impl(left->hists->hpp_list, left, right, + offsetof(struct perf_hpp_fmt, collapse), true, false); +} - hists__for_each_sort_list(hists, fmt) { - if (perf_hpp__is_dynamic_entry(fmt) && - !perf_hpp__defined_dynamic_entry(fmt, hists)) - continue; - - cmp = fmt->collapse(fmt, left, right); - if (cmp) - break; - } - - return cmp; +static int64_t +hist_entry__collapse_hierarchy(struct perf_hpp_list *hpp_list, + struct hist_entry *left, + struct hist_entry *right) +{ + return hist_entry__cmp_impl(hpp_list, left, right, + offsetof(struct perf_hpp_fmt, collapse), false, false); } void hist_entry__delete(struct hist_entry *he) @@ -1503,14 +1532,7 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists, while (*p != NULL) { parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node_in); - - cmp = 0; - perf_hpp_list__for_each_sort_list(hpp_list, fmt) { - cmp = fmt->collapse(fmt, iter, he); - if (cmp) - break; - } - + cmp = hist_entry__collapse_hierarchy(hpp_list, iter, he); if (!cmp) { he_stat__add_stat(&iter->stat, &he->stat); return iter; @@ -1730,24 +1752,6 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) return 0; } -static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b) -{ - struct hists *hists = a->hists; - struct perf_hpp_fmt *fmt; - int64_t cmp = 0; - - hists__for_each_sort_list(hists, fmt) { - if (perf_hpp__should_skip(fmt, a->hists)) - continue; - - cmp = fmt->sort(fmt, a, b); - if (cmp) - break; - } - - return cmp; -} - static void hists__reset_filter_stats(struct hists *hists) { hists->nr_non_filtered_entries = 0; @@ -2449,21 +2453,15 @@ static struct hist_entry *add_dummy_hierarchy_entry(struct hists *hists, struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; - struct perf_hpp_fmt *fmt; bool leftmost = true; p = &root->rb_root.rb_node; while (*p != NULL) { - int64_t cmp = 0; + int64_t cmp; parent = *p; he = rb_entry(parent, struct hist_entry, rb_node_in); - - perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) { - cmp = fmt->collapse(fmt, he, pair); - if (cmp) - break; - } + cmp = hist_entry__collapse_hierarchy(he->hpp_list, he, pair); if (!cmp) goto out; @@ -2521,16 +2519,10 @@ static struct hist_entry *hists__find_hierarchy_entry(struct rb_root_cached *roo while (n) { struct hist_entry *iter; - struct perf_hpp_fmt *fmt; - int64_t cmp = 0; + int64_t cmp; iter = rb_entry(n, struct hist_entry, rb_node_in); - perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) { - cmp = fmt->collapse(fmt, iter, he); - if (cmp) - break; - } - + cmp = hist_entry__collapse_hierarchy(he->hpp_list, iter, he); if (cmp < 0) n = n->rb_left; else if (cmp > 0) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 1131056924d9..46c8373e3146 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -342,8 +342,6 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, struct perf_hpp; struct perf_hpp_fmt; -int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); -int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); int hist_entry__transaction_len(void); int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, struct hists *hists); @@ -452,6 +450,9 @@ struct perf_hpp { bool skip; }; +typedef int64_t (*perf_hpp_fmt_cmp_t)( + struct perf_hpp_fmt *, struct hist_entry *, struct hist_entry *); + struct perf_hpp_fmt { const char *name; int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, @@ -463,12 +464,9 @@ struct perf_hpp_fmt { struct hist_entry *he); int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he); - int64_t (*cmp)(struct perf_hpp_fmt *fmt, - struct hist_entry *a, struct hist_entry *b); - int64_t (*collapse)(struct perf_hpp_fmt *fmt, - struct hist_entry *a, struct hist_entry *b); - int64_t (*sort)(struct perf_hpp_fmt *fmt, - struct hist_entry *a, struct hist_entry *b); + perf_hpp_fmt_cmp_t cmp; + perf_hpp_fmt_cmp_t collapse; + perf_hpp_fmt_cmp_t sort; bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); void (*free)(struct perf_hpp_fmt *fmt); diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 30793d08c6d4..5b8f0149167d 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -7,16 +7,24 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table $(call rule_mkdir) @$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@ -# Busybox's diff doesn't have -I, avoid warning in the case +ifeq ($(SRCARCH),x86) + perf-util-y += inat.o insn.o +else + perf-util-$(CONFIG_AUXTRACE) += inat.o insn.o +endif -$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c +$(OUTPUT)util/intel-pt-decoder/inat.o: $(srctree)/tools/arch/x86/lib/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder +CFLAGS_inat.o += -I$(OUTPUT)util/intel-pt-decoder + +$(OUTPUT)util/intel-pt-decoder/insn.o: $(srctree)/tools/arch/x86/lib/insn.c + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) ifeq ($(CC_NO_CLANG), 1) - CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init + CFLAGS_insn.o += -Wno-override-init endif -CFLAGS_intel-pt-insn-decoder.o += -Wno-packed +CFLAGS_insn.o += -Wno-packed diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 47cf35799a4d..8fabddc1c0da 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -11,9 +11,6 @@ #include <byteswap.h> #include "../../../arch/x86/include/asm/insn.h" -#include "../../../arch/x86/lib/inat.c" -#include "../../../arch/x86/lib/insn.c" - #include "event.h" #include "intel-pt-insn-decoder.h" diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 346513e5e9b7..f23e21502bf8 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -737,7 +737,7 @@ jit_inject(struct jit_buf_desc *jd, const char *path) * as captured in the RECORD_MMAP record */ static int -jit_detect(const char *mmap_name, pid_t pid, struct nsinfo *nsi) +jit_detect(const char *mmap_name, pid_t pid, struct nsinfo *nsi, bool *in_pidns) { char *p; char *end = NULL; @@ -773,11 +773,16 @@ jit_detect(const char *mmap_name, pid_t pid, struct nsinfo *nsi) if (!end) return -1; + *in_pidns = pid == nsinfo__nstgid(nsi); /* * pid does not match mmap pid * pid==0 in system-wide mode (synthesized) + * + * If the pid in the file name is equal to the nstgid, then + * the agent ran inside a container and perf outside the + * container, so record it for further use in jit_inject(). */ - if (pid && pid2 != nsinfo__nstgid(nsi)) + if (pid && !(pid2 == pid || *in_pidns)) return -1; /* * validate suffix @@ -830,6 +835,7 @@ jit_process(struct perf_session *session, struct nsinfo *nsi; struct evsel *first; struct jit_buf_desc jd; + bool in_pidns = false; int ret; thread = machine__findnew_thread(machine, pid, tid); @@ -844,7 +850,7 @@ jit_process(struct perf_session *session, /* * first, detect marker mmap (i.e., the jitdump mmap) */ - if (jit_detect(filename, pid, nsi)) { + if (jit_detect(filename, pid, nsi, &in_pidns)) { nsinfo__put(nsi); /* @@ -866,6 +872,9 @@ jit_process(struct perf_session *session, jd.machine = machine; jd.nsi = nsi; + if (in_pidns) + nsinfo__set_in_pidns(nsi); + /* * track sample_type to compute id_all layout * perf sets the same sample type to all events as of now diff --git a/tools/perf/util/kvm-stat.c b/tools/perf/util/kvm-stat.c new file mode 100644 index 000000000000..38ace736db5c --- /dev/null +++ b/tools/perf/util/kvm-stat.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "debug.h" +#include "evsel.h" +#include "kvm-stat.h" + +#if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) + +bool kvm_exit_event(struct evsel *evsel) +{ + return evsel__name_is(evsel, kvm_exit_trace); +} + +void exit_event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = evsel__intval(evsel, sample, kvm_exit_reason); +} + + +bool exit_event_begin(struct evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + if (kvm_exit_event(evsel)) { + exit_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +bool kvm_entry_event(struct evsel *evsel) +{ + return evsel__name_is(evsel, kvm_entry_trace); +} + +bool exit_event_end(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return kvm_entry_event(evsel); +} + +static const char *get_exit_reason(struct perf_kvm_stat *kvm, + struct exit_reasons_table *tbl, + u64 exit_code) +{ + while (tbl->reason != NULL) { + if (tbl->exit_code == exit_code) + return tbl->reason; + tbl++; + } + + pr_err("unknown kvm exit code:%lld on %s\n", + (unsigned long long)exit_code, kvm->exit_reasons_isa); + return "UNKNOWN"; +} + +void exit_event_decode_key(struct perf_kvm_stat *kvm, + struct event_key *key, + char *decode) +{ + const char *exit_reason = get_exit_reason(kvm, key->exit_reasons, + key->key); + + scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", exit_reason); +} + +#endif diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 3e9ac754c3d1..4249542544bb 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -115,6 +115,8 @@ struct kvm_reg_events_ops { struct kvm_events_ops *ops; }; +#if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) + void exit_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); @@ -127,6 +129,7 @@ bool exit_event_end(struct evsel *evsel, void exit_event_decode_key(struct perf_kvm_stat *kvm, struct event_key *key, char *decode); +#endif bool kvm_exit_event(struct evsel *evsel); bool kvm_entry_event(struct evsel *evsel); diff --git a/tools/perf/util/kwork.h b/tools/perf/util/kwork.h index 76fe2a821bcf..db00269b73f2 100644 --- a/tools/perf/util/kwork.h +++ b/tools/perf/util/kwork.h @@ -1,6 +1,7 @@ #ifndef PERF_UTIL_KWORK_H #define PERF_UTIL_KWORK_H +#include "perf.h" #include "util/tool.h" #include "util/time-utils.h" @@ -251,12 +252,14 @@ struct perf_kwork { * perf kwork top data */ struct kwork_top_stat top_stat; -}; -struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork, + /* Add work callback. */ + struct kwork_work *(*add_work)(struct perf_kwork *kwork, struct kwork_class *class, struct kwork_work *key); +}; + #ifdef HAVE_BPF_SKEL int perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork); diff --git a/tools/perf/util/llvm-c-helpers.cpp b/tools/perf/util/llvm-c-helpers.cpp index 663bcaba2041..004081bd12c9 100644 --- a/tools/perf/util/llvm-c-helpers.cpp +++ b/tools/perf/util/llvm-c-helpers.cpp @@ -18,7 +18,6 @@ extern "C" { #include <linux/zalloc.h> } -#include "symbol_conf.h" #include "llvm-c-helpers.h" extern "C" diff --git a/tools/perf/util/lock-contention.c b/tools/perf/util/lock-contention.c new file mode 100644 index 000000000000..92e7b7b572a2 --- /dev/null +++ b/tools/perf/util/lock-contention.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "debug.h" +#include "env.h" +#include "lock-contention.h" +#include "machine.h" +#include "symbol.h" + +#include <limits.h> +#include <string.h> + +#include <linux/hash.h> +#include <linux/zalloc.h> + +#define __lockhashfn(key) hash_long((unsigned long)key, LOCKHASH_BITS) +#define lockhashentry(key) (lockhash_table + __lockhashfn((key))) + +struct callstack_filter { + struct list_head list; + char name[]; +}; + +static LIST_HEAD(callstack_filters); +struct hlist_head *lockhash_table; + +int parse_call_stack(const struct option *opt __maybe_unused, const char *str, + int unset __maybe_unused) +{ + char *s, *tmp, *tok; + int ret = 0; + + s = strdup(str); + if (s == NULL) + return -1; + + for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { + struct callstack_filter *entry; + + entry = malloc(sizeof(*entry) + strlen(tok) + 1); + if (entry == NULL) { + pr_err("Memory allocation failure\n"); + free(s); + return -1; + } + + strcpy(entry->name, tok); + list_add_tail(&entry->list, &callstack_filters); + } + + free(s); + return ret; +} + +bool needs_callstack(void) +{ + return !list_empty(&callstack_filters); +} + +struct lock_stat *lock_stat_find(u64 addr) +{ + struct hlist_head *entry = lockhashentry(addr); + struct lock_stat *ret; + + hlist_for_each_entry(ret, entry, hash_entry) { + if (ret->addr == addr) + return ret; + } + return NULL; +} + +struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags) +{ + struct hlist_head *entry = lockhashentry(addr); + struct lock_stat *ret, *new; + + hlist_for_each_entry(ret, entry, hash_entry) { + if (ret->addr == addr) + return ret; + } + + new = zalloc(sizeof(struct lock_stat)); + if (!new) + goto alloc_failed; + + new->addr = addr; + new->name = strdup(name); + if (!new->name) { + free(new); + goto alloc_failed; + } + + new->flags = flags; + new->wait_time_min = ULLONG_MAX; + + hlist_add_head(&new->hash_entry, entry); + return new; + +alloc_failed: + pr_err("memory allocation failed\n"); + return NULL; +} + +bool match_callstack_filter(struct machine *machine, u64 *callstack, int max_stack_depth) +{ + struct map *kmap; + struct symbol *sym; + u64 ip; + const char *arch = perf_env__arch(machine->env); + + if (list_empty(&callstack_filters)) + return true; + + for (int i = 0; i < max_stack_depth; i++) { + struct callstack_filter *filter; + + /* + * In powerpc, the callchain saved by kernel always includes + * first three entries as the NIP (next instruction pointer), + * LR (link register), and the contents of LR save area in the + * second stack frame. In certain scenarios its possible to have + * invalid kernel instruction addresses in either LR or the second + * stack frame's LR. In that case, kernel will store that address as + * zero. + * + * The below check will continue to look into callstack, + * incase first or second callstack index entry has 0 + * address for powerpc. + */ + if (!callstack || (!callstack[i] && (strcmp(arch, "powerpc") || + (i != 1 && i != 2)))) + break; + + ip = callstack[i]; + sym = machine__find_kernel_symbol(machine, ip, &kmap); + if (sym == NULL) + continue; + + list_for_each_entry(filter, &callstack_filters, list) { + if (strstr(sym->name, filter->name)) + return true; + } + } + return false; +} diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h index 1a7248ff3889..a09f7fe877df 100644 --- a/tools/perf/util/lock-contention.h +++ b/tools/perf/util/lock-contention.h @@ -10,10 +10,12 @@ struct lock_filter { int nr_addrs; int nr_syms; int nr_cgrps; + int nr_slabs; unsigned int *types; unsigned long *addrs; char **syms; u64 *cgrps; + char **slabs; }; struct lock_stat { @@ -67,10 +69,11 @@ struct lock_stat { */ #define MAX_LOCK_DEPTH 48 -struct lock_stat *lock_stat_find(u64 addr); -struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags); +/* based on kernel/lockdep.c */ +#define LOCKHASH_BITS 12 +#define LOCKHASH_SIZE (1UL << LOCKHASH_BITS) -bool match_callstack_filter(struct machine *machine, u64 *callstack); +extern struct hlist_head *lockhash_table; /* * struct lock_seq_stat: @@ -148,8 +151,17 @@ struct lock_contention { bool save_callstack; }; -#ifdef HAVE_BPF_SKEL +struct option; +int parse_call_stack(const struct option *opt, const char *str, int unset); +bool needs_callstack(void); +struct lock_stat *lock_stat_find(u64 addr); +struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags); + +bool match_callstack_filter(struct machine *machine, u64 *callstack, int max_stack_depth); + + +#ifdef HAVE_BPF_SKEL int lock_contention_prepare(struct lock_contention *con); int lock_contention_start(void); int lock_contention_stop(void); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 27d5345d2b30..2d51badfbf2e 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1003,7 +1003,7 @@ static int machine__get_running_kernel_start(struct machine *machine, err = kallsyms__get_symbol_start(filename, "_edata", &addr); if (err) - err = kallsyms__get_function_start(filename, "_etext", &addr); + err = kallsyms__get_symbol_start(filename, "_etext", &addr); if (!err) *end = addr; @@ -1468,6 +1468,8 @@ static int machine__create_modules(struct machine *machine) if (modules__parse(modules, machine, machine__create_module)) return -1; + maps__fixup_end(machine__kernel_maps(machine)); + if (!machine__set_modules_path(machine)) return 0; diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 432399cbe5dd..09c9cc326c08 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -1136,8 +1136,13 @@ struct map *maps__find_next_entry(struct maps *maps, struct map *map) struct map *result = NULL; down_read(maps__lock(maps)); + while (!maps__maps_by_address_sorted(maps)) { + up_read(maps__lock(maps)); + maps__sort_by_address(maps); + down_read(maps__lock(maps)); + } i = maps__by_address_index(maps, map); - if (i < maps__nr_maps(maps)) + if (++i < maps__nr_maps(maps)) result = map__get(maps__maps_by_address(maps)[i]); up_read(maps__lock(maps)); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index bf5090f5220b..3692e988c86e 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -258,6 +258,7 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr) const char *s; char *copy; struct perf_cpu_map *cpu_map = NULL; + int ret; while ((pmu = perf_pmus__scan_mem(pmu)) != NULL) { for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) { @@ -283,7 +284,9 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr) rec_argv[i++] = "-e"; rec_argv[i++] = copy; - cpu_map = perf_cpu_map__merge(cpu_map, pmu->cpus); + ret = perf_cpu_map__merge(&cpu_map, pmu->cpus); + if (ret < 0) + return ret; } } diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index cb185c5659d6..68f5de2d79c7 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -266,11 +266,16 @@ pid_t nsinfo__pid(const struct nsinfo *nsi) return RC_CHK_ACCESS(nsi)->pid; } -pid_t nsinfo__in_pidns(const struct nsinfo *nsi) +bool nsinfo__in_pidns(const struct nsinfo *nsi) { return RC_CHK_ACCESS(nsi)->in_pidns; } +void nsinfo__set_in_pidns(struct nsinfo *nsi) +{ + RC_CHK_ACCESS(nsi)->in_pidns = true; +} + void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc) { diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 8c0731c6cbb7..e95c79b80e27 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -58,7 +58,8 @@ void nsinfo__clear_need_setns(struct nsinfo *nsi); pid_t nsinfo__tgid(const struct nsinfo *nsi); pid_t nsinfo__nstgid(const struct nsinfo *nsi); pid_t nsinfo__pid(const struct nsinfo *nsi); -pid_t nsinfo__in_pidns(const struct nsinfo *nsi); +bool nsinfo__in_pidns(const struct nsinfo *nsi); +void nsinfo__set_in_pidns(struct nsinfo *nsi); void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc); void nsinfo__mountns_exit(struct nscookie *nc); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index afeb8d815bbf..1e23faa364b1 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -489,7 +489,6 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name, return found_supported ? 0 : -EINVAL; } -#ifdef HAVE_LIBTRACEEVENT static void tracepoint_error(struct parse_events_error *e, int err, const char *sys, const char *name, int column) { @@ -644,7 +643,6 @@ static int add_tracepoint_multi_sys(struct parse_events_state *parse_state, closedir(events_dir); return ret; } -#endif /* HAVE_LIBTRACEEVENT */ size_t default_breakpoint_len(void) { @@ -795,6 +793,7 @@ const char *parse_events__term_type_str(enum parse_events__term_type term_type) [PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config", [PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore", [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output", + [PARSE_EVENTS__TERM_TYPE_AUX_ACTION] = "aux-action", [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size", [PARSE_EVENTS__TERM_TYPE_METRIC_ID] = "metric-id", [PARSE_EVENTS__TERM_TYPE_RAW] = "raw", @@ -844,6 +843,7 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_er case PARSE_EVENTS__TERM_TYPE_OVERWRITE: case PARSE_EVENTS__TERM_TYPE_DRV_CFG: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: case PARSE_EVENTS__TERM_TYPE_RAW: case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: @@ -963,6 +963,9 @@ do { \ case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: CHECK_TYPE_VAL(NUM); break; + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: + CHECK_TYPE_VAL(STR); + break; case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: CHECK_TYPE_VAL(NUM); if (term->val.num > UINT_MAX) { @@ -1066,7 +1069,6 @@ static int config_term_pmu(struct perf_event_attr *attr, return config_term_common(attr, term, err); } -#ifdef HAVE_LIBTRACEEVENT static int config_term_tracepoint(struct perf_event_attr *attr, struct parse_events_term *term, struct parse_events_error *err) @@ -1081,6 +1083,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_OVERWRITE: case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: return config_term_common(attr, term, err); case PARSE_EVENTS__TERM_TYPE_USER: @@ -1111,7 +1114,6 @@ static int config_term_tracepoint(struct perf_event_attr *attr, return 0; } -#endif static int config_attr(struct perf_event_attr *attr, const struct parse_events_terms *head, @@ -1217,6 +1219,9 @@ do { \ ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0, term->weak); break; + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: + ADD_CONFIG_TERM_STR(AUX_ACTION, term->val.str, term->weak); + break; case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size, term->val.num, term->weak); @@ -1279,6 +1284,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *head case PARSE_EVENTS__TERM_TYPE_DRV_CFG: case PARSE_EVENTS__TERM_TYPE_PERCORE: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: case PARSE_EVENTS__TERM_TYPE_METRIC_ID: case PARSE_EVENTS__TERM_TYPE_RAW: @@ -1303,7 +1309,7 @@ int parse_events_add_tracepoint(struct parse_events_state *parse_state, struct parse_events_terms *head_config, void *loc_) { YYLTYPE *loc = loc_; -#ifdef HAVE_LIBTRACEEVENT + if (head_config) { struct perf_event_attr attr; @@ -1318,16 +1324,6 @@ int parse_events_add_tracepoint(struct parse_events_state *parse_state, else return add_tracepoint_event(parse_state, list, sys, event, err, head_config, loc); -#else - (void)parse_state; - (void)list; - (void)sys; - (void)event; - (void)head_config; - parse_events_error__handle(err, loc->first_column, strdup("unsupported tracepoint"), - strdup("libtraceevent is necessary for tracepoint support")); - return -1; -#endif } static int __parse_events_add_numeric(struct parse_events_state *parse_state, diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 3f4334ec6231..e176a34ab088 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -74,6 +74,7 @@ enum parse_events__term_type { PARSE_EVENTS__TERM_TYPE_DRV_CFG, PARSE_EVENTS__TERM_TYPE_PERCORE, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT, + PARSE_EVENTS__TERM_TYPE_AUX_ACTION, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE, PARSE_EVENTS__TERM_TYPE_METRIC_ID, PARSE_EVENTS__TERM_TYPE_RAW, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 14e5bd856a18..bf7f73548605 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -321,6 +321,7 @@ overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); } no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); } percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } +aux-action { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } cpu-cycles|cycles { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); } diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index 00adf872bf00..2e62f272fda8 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -68,14 +68,12 @@ bool is_directory(const char *base_path, const struct dirent *dent) return S_ISDIR(st.st_mode); } -bool is_executable_file(const char *base_path, const struct dirent *dent) +bool is_directory_at(int dir_fd, const char *path) { - char path[PATH_MAX]; struct stat st; - snprintf(path, sizeof(path), "%s/%s", base_path, dent->d_name); - if (stat(path, &st)) + if (fstatat(dir_fd, path, &st, /*flags=*/0)) return false; - return !S_ISDIR(st.st_mode) && (st.st_mode & S_IXUSR); + return S_ISDIR(st.st_mode); } diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h index d94902c22222..fb850fb55c60 100644 --- a/tools/perf/util/path.h +++ b/tools/perf/util/path.h @@ -12,6 +12,6 @@ int path__join3(char *bf, size_t size, const char *path1, const char *path2, con bool is_regular_file(const char *file); bool is_directory(const char *base_path, const struct dirent *dent); -bool is_executable_file(const char *base_path, const struct dirent *dent); +bool is_directory_at(int dir_fd, const char *path); #endif /* _PERF_PATH_H */ diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index 59fbbba79697..c7f3543b9921 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -212,7 +212,6 @@ static void __p_config_hw_cache_id(char *buf, size_t size, u64 value) } } -#ifdef HAVE_LIBTRACEEVENT static void __p_config_tracepoint_id(char *buf, size_t size, u64 value) { char *str = tracepoint_id_to_name(value); @@ -220,7 +219,6 @@ static void __p_config_tracepoint_id(char *buf, size_t size, u64 value) print_id_hex(str); free(str); } -#endif static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 value) { @@ -238,9 +236,7 @@ static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type case PERF_TYPE_HW_CACHE: return __p_config_hw_cache_id(buf, size, value); case PERF_TYPE_TRACEPOINT: -#ifdef HAVE_LIBTRACEEVENT return __p_config_tracepoint_id(buf, size, value); -#endif case PERF_TYPE_RAW: case PERF_TYPE_BREAKPOINT: default: @@ -335,6 +331,9 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(sample_max_stack, p_unsigned); PRINT_ATTRf(aux_sample_size, p_unsigned); PRINT_ATTRf(sig_data, p_unsigned); + PRINT_ATTRf(aux_start_paused, p_unsigned); + PRINT_ATTRf(aux_pause, p_unsigned); + PRINT_ATTRf(aux_resume, p_unsigned); return ret; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 08a9d0bd9301..6206c8fe2bf9 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -12,6 +12,7 @@ #include <stdbool.h> #include <dirent.h> #include <api/fs/fs.h> +#include <api/io.h> #include <locale.h> #include <fnmatch.h> #include <math.h> @@ -748,26 +749,35 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, int err_loc, struct lis * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) * may have a "cpus" file. */ -static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *name, bool is_core) +static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *pmu_name, bool is_core) { - struct perf_cpu_map *cpus; const char *templates[] = { "cpumask", "cpus", NULL }; const char **template; - char pmu_name[PATH_MAX]; - struct perf_pmu pmu = {.name = pmu_name}; - FILE *file; - strlcpy(pmu_name, name, sizeof(pmu_name)); for (template = templates; *template; template++) { - file = perf_pmu__open_file_at(&pmu, dirfd, *template); - if (!file) + struct io io; + char buf[128]; + char *cpumask = NULL; + size_t cpumask_len; + ssize_t ret; + struct perf_cpu_map *cpus; + + io.fd = perf_pmu__pathname_fd(dirfd, pmu_name, *template, O_RDONLY); + if (io.fd < 0) continue; - cpus = perf_cpu_map__read(file); - fclose(file); + + io__init(&io, io.fd, buf, sizeof(buf)); + ret = io__getline(&io, &cpumask, &cpumask_len); + close(io.fd); + if (ret < 0) + continue; + + cpus = perf_cpu_map__new(cpumask); + free(cpumask); if (cpus) return cpus; } @@ -1763,6 +1773,7 @@ int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_call "no-overwrite", "percore", "aux-output", + "aux-action=(pause|resume|start-paused)", "aux-sample-size=number", }; struct perf_pmu_format *format; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index eaa0318e9b87..307ad6242a4e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1383,20 +1383,20 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) if (p == buf) { semantic_error("No file/function name in '%s'.\n", p); err = -EINVAL; - goto err; + goto out; } *(p++) = '\0'; err = parse_line_num(&p, &lr->start, "start line"); if (err) - goto err; + goto out; if (*p == '+' || *p == '-') { const char c = *(p++); err = parse_line_num(&p, &lr->end, "end line"); if (err) - goto err; + goto out; if (c == '+') { lr->end += lr->start; @@ -1416,11 +1416,11 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) if (lr->start > lr->end) { semantic_error("Start line must be smaller" " than end line.\n"); - goto err; + goto out; } if (*p != '\0') { semantic_error("Tailing with invalid str '%s'.\n", p); - goto err; + goto out; } } @@ -1431,7 +1431,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) lr->file = strdup_esq(p); if (lr->file == NULL) { err = -ENOMEM; - goto err; + goto out; } } if (*buf != '\0') @@ -1439,7 +1439,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) if (!lr->function && !lr->file) { semantic_error("Only '@*' is not allowed.\n"); err = -EINVAL; - goto err; + goto out; } } else if (strpbrk_esq(buf, "/.")) lr->file = strdup_esq(buf); @@ -1448,10 +1448,10 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) else { /* Invalid name */ semantic_error("'%s' is not a valid function name.\n", buf); err = -EINVAL; - goto err; + goto out; } -err: +out: free(buf); return err; } @@ -2775,7 +2775,7 @@ int show_perf_probe_events(struct strfilter *filter) static int get_new_event_name(char *buf, size_t len, const char *base, struct strlist *namelist, bool ret_event, - bool allow_suffix) + bool allow_suffix, bool not_C_symname) { int i, ret; char *p, *nbase; @@ -2786,10 +2786,24 @@ static int get_new_event_name(char *buf, size_t len, const char *base, if (!nbase) return -ENOMEM; - /* Cut off the dot suffixes (e.g. .const, .isra) and version suffixes */ - p = strpbrk(nbase, ".@"); - if (p && p != nbase) - *p = '\0'; + if (not_C_symname) { + /* Replace non-alnum with '_' */ + char *s, *d; + + s = d = nbase; + do { + if (*s && !isalnum(*s)) { + if (d != nbase && *(d - 1) != '_') + *d++ = '_'; + } else + *d++ = *s; + } while (*s++); + } else { + /* Cut off the dot suffixes (e.g. .const, .isra) and version suffixes */ + p = strpbrk(nbase, ".@"); + if (p && p != nbase) + *p = '\0'; + } /* Try no suffix number */ ret = e_snprintf(buf, len, "%s%s", nbase, ret_event ? "__return" : ""); @@ -2884,6 +2898,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, bool allow_suffix) { const char *event, *group; + bool not_C_symname = true; char buf[MAX_EVENT_NAME_LEN]; int ret; @@ -2898,8 +2913,10 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, (strncmp(pev->point.function, "0x", 2) != 0) && !strisglob(pev->point.function)) event = pev->point.function; - else + else { event = tev->point.realname; + not_C_symname = !is_known_C_lang(tev->lang); + } } if (pev->group && !pev->sdt) group = pev->group; @@ -2916,7 +2933,8 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, /* Get an unused new event name */ ret = get_new_event_name(buf, sizeof(buf), event, namelist, - tev->point.retprobe, allow_suffix); + tev->point.retprobe, allow_suffix, + not_C_symname); if (ret < 0) return ret; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 61a5f4ff4e9c..71905ede0207 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -58,6 +58,7 @@ struct probe_trace_event { char *group; /* Group name */ struct probe_trace_point point; /* Trace point */ int nargs; /* Number of args */ + int lang; /* Dwarf language code */ bool uprobes; /* uprobes only */ struct probe_trace_arg *args; /* Arguments */ }; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 7f2ee0cb43ca..1e769b68da37 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -35,6 +35,19 @@ /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 +bool is_known_C_lang(int lang) +{ + switch (lang) { + case DW_LANG_C89: + case DW_LANG_C: + case DW_LANG_C99: + case DW_LANG_C11: + return true; + default: + return false; + } +} + /* * Probe finder related functions */ @@ -1270,6 +1283,8 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) goto end; } + tev->lang = dwarf_srclang(dwarf_diecu(sc_die, &pf->cu_die, NULL, NULL)); + pr_debug("Probe point found: %s+%lu\n", tev->point.symbol, tev->point.offset); diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index be7b46ea2460..dcf6cc1e1cbe 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -26,6 +26,9 @@ static inline int is_c_varname(const char *name) #include "dwarf-aux.h" #include "debuginfo.h" +/* Check the language code is known C */ +bool is_known_C_lang(int lang); + /* Find probe_trace_events specified by perf_probe_event from debuginfo */ int debuginfo__find_trace_events(struct debuginfo *dbg, struct perf_probe_event *pev, @@ -103,6 +106,8 @@ struct line_finder { int found; }; +#else +#define is_known_C_lang(lang) (false) #endif /* HAVE_LIBDW_SUPPORT */ #endif /*_PROBE_FINDER_H */ diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 2096cdbaa53b..b4bc57859f73 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -13,30 +13,12 @@ #include "evsel.h" #include "event.h" #include "print_binary.h" +#include "strbuf.h" #include "thread_map.h" #include "trace-event.h" #include "mmap.h" -#include "util/bpf-filter.h" -#include "util/env.h" -#include "util/kvm-stat.h" -#include "util/stat.h" -#include "util/kwork.h" #include "util/sample.h" -#include "util/lock-contention.h" #include <internal/lib.h> -#include "../builtin.h" - -#if PY_MAJOR_VERSION < 3 -#define _PyUnicode_FromString(arg) \ - PyString_FromString(arg) -#define _PyUnicode_AsString(arg) \ - PyString_AsString(arg) -#define _PyUnicode_FromFormat(...) \ - PyString_FromFormat(__VA_ARGS__) -#define _PyLong_FromLong(arg) \ - PyInt_FromLong(arg) - -#else #define _PyUnicode_FromString(arg) \ PyUnicode_FromString(arg) @@ -44,22 +26,8 @@ PyUnicode_FromFormat(__VA_ARGS__) #define _PyLong_FromLong(arg) \ PyLong_FromLong(arg) -#endif -#ifndef Py_TYPE -#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type) -#endif - -/* Define PyVarObject_HEAD_INIT for python 2.5 */ -#ifndef PyVarObject_HEAD_INIT -# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size, -#endif - -#if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC initperf(void); -#else PyMODINIT_FUNC PyInit_perf(void); -#endif #define member_def(type, member, ptype, help) \ { #member, ptype, \ @@ -89,7 +57,7 @@ struct pyrf_event { sample_member_def(sample_period, period, T_ULONGLONG, "event period"), \ sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"), -static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object."); +static const char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object."); static PyMemberDef pyrf_mmap_event__members[] = { sample_members @@ -104,7 +72,7 @@ static PyMemberDef pyrf_mmap_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_mmap_event__repr(const struct pyrf_event *pevent) { PyObject *ret; char *s; @@ -117,7 +85,7 @@ static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent) pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) { ret = PyErr_NoMemory(); } else { - ret = _PyUnicode_FromString(s); + ret = PyUnicode_FromString(s); free(s); } return ret; @@ -133,7 +101,7 @@ static PyTypeObject pyrf_mmap_event__type = { .tp_repr = (reprfunc)pyrf_mmap_event__repr, }; -static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object."); +static const char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object."); static PyMemberDef pyrf_task_event__members[] = { sample_members @@ -146,9 +114,9 @@ static PyMemberDef pyrf_task_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_task_event__repr(const struct pyrf_event *pevent) { - return _PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, " + return PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, " "ptid: %u, time: %" PRI_lu64 "}", pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit", pevent->event.fork.pid, @@ -168,7 +136,7 @@ static PyTypeObject pyrf_task_event__type = { .tp_repr = (reprfunc)pyrf_task_event__repr, }; -static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object."); +static const char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object."); static PyMemberDef pyrf_comm_event__members[] = { sample_members @@ -179,9 +147,9 @@ static PyMemberDef pyrf_comm_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_comm_event__repr(const struct pyrf_event *pevent) { - return _PyUnicode_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }", + return PyUnicode_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }", pevent->event.comm.pid, pevent->event.comm.tid, pevent->event.comm.comm); @@ -197,7 +165,7 @@ static PyTypeObject pyrf_comm_event__type = { .tp_repr = (reprfunc)pyrf_comm_event__repr, }; -static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object."); +static const char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object."); static PyMemberDef pyrf_throttle_event__members[] = { sample_members @@ -208,11 +176,12 @@ static PyMemberDef pyrf_throttle_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_throttle_event__repr(const struct pyrf_event *pevent) { - struct perf_record_throttle *te = (struct perf_record_throttle *)(&pevent->event.header + 1); + const struct perf_record_throttle *te = (const struct perf_record_throttle *) + (&pevent->event.header + 1); - return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRI_lu64 ", id: %" PRI_lu64 + return PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRI_lu64 ", id: %" PRI_lu64 ", stream_id: %" PRI_lu64 " }", pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un", te->time, te->id, te->stream_id); @@ -228,7 +197,7 @@ static PyTypeObject pyrf_throttle_event__type = { .tp_repr = (reprfunc)pyrf_throttle_event__repr, }; -static char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object."); +static const char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object."); static PyMemberDef pyrf_lost_event__members[] = { sample_members @@ -237,7 +206,7 @@ static PyMemberDef pyrf_lost_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_lost_event__repr(const struct pyrf_event *pevent) { PyObject *ret; char *s; @@ -247,7 +216,7 @@ static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent) pevent->event.lost.id, pevent->event.lost.lost) < 0) { ret = PyErr_NoMemory(); } else { - ret = _PyUnicode_FromString(s); + ret = PyUnicode_FromString(s); free(s); } return ret; @@ -263,7 +232,7 @@ static PyTypeObject pyrf_lost_event__type = { .tp_repr = (reprfunc)pyrf_lost_event__repr, }; -static char pyrf_read_event__doc[] = PyDoc_STR("perf read event object."); +static const char pyrf_read_event__doc[] = PyDoc_STR("perf read event object."); static PyMemberDef pyrf_read_event__members[] = { sample_members @@ -272,9 +241,9 @@ static PyMemberDef pyrf_read_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_read_event__repr(const struct pyrf_event *pevent) { - return _PyUnicode_FromFormat("{ type: read, pid: %u, tid: %u }", + return PyUnicode_FromFormat("{ type: read, pid: %u, tid: %u }", pevent->event.read.pid, pevent->event.read.tid); /* @@ -293,7 +262,7 @@ static PyTypeObject pyrf_read_event__type = { .tp_repr = (reprfunc)pyrf_read_event__repr, }; -static char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object."); +static const char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object."); static PyMemberDef pyrf_sample_event__members[] = { sample_members @@ -301,7 +270,7 @@ static PyMemberDef pyrf_sample_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_sample_event__repr(const struct pyrf_event *pevent) { PyObject *ret; char *s; @@ -309,20 +278,20 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) if (asprintf(&s, "{ type: sample }") < 0) { ret = PyErr_NoMemory(); } else { - ret = _PyUnicode_FromString(s); + ret = PyUnicode_FromString(s); free(s); } return ret; } #ifdef HAVE_LIBTRACEEVENT -static bool is_tracepoint(struct pyrf_event *pevent) +static bool is_tracepoint(const struct pyrf_event *pevent) { return pevent->evsel->core.attr.type == PERF_TYPE_TRACEPOINT; } static PyObject* -tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) +tracepoint_field(const struct pyrf_event *pe, struct tep_format_field *field) { struct tep_handle *pevent = field->event->tep; void *data = pe->sample.raw_data; @@ -343,7 +312,7 @@ tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { - ret = _PyUnicode_FromString((char *)data + offset); + ret = PyUnicode_FromString((char *)data + offset); } else { ret = PyByteArray_FromStringAndSize((const char *) data + offset, len); field->flags &= ~TEP_FIELD_IS_STRING; @@ -411,7 +380,7 @@ static PyTypeObject pyrf_sample_event__type = { .tp_getattro = (getattrofunc) pyrf_sample_event__getattro, }; -static char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object."); +static const char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object."); static PyMemberDef pyrf_context_switch_event__members[] = { sample_members @@ -421,7 +390,7 @@ static PyMemberDef pyrf_context_switch_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_context_switch_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_context_switch_event__repr(const struct pyrf_event *pevent) { PyObject *ret; char *s; @@ -432,7 +401,7 @@ static PyObject *pyrf_context_switch_event__repr(struct pyrf_event *pevent) !!(pevent->event.header.misc & PERF_RECORD_MISC_SWITCH_OUT)) < 0) { ret = PyErr_NoMemory(); } else { - ret = _PyUnicode_FromString(s); + ret = PyUnicode_FromString(s); free(s); } return ret; @@ -501,7 +470,7 @@ static PyTypeObject *pyrf_event__type[] = { [PERF_RECORD_SWITCH_CPU_WIDE] = &pyrf_context_switch_event__type, }; -static PyObject *pyrf_event__new(union perf_event *event) +static PyObject *pyrf_event__new(const union perf_event *event) { struct pyrf_event *pevent; PyTypeObject *ptype; @@ -569,7 +538,7 @@ static PySequenceMethods pyrf_cpu_map__sequence_methods = { .sq_item = pyrf_cpu_map__item, }; -static char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object."); +static const char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object."); static PyTypeObject pyrf_cpu_map__type = { PyVarObject_HEAD_INIT(NULL, 0) @@ -638,7 +607,7 @@ static PySequenceMethods pyrf_thread_map__sequence_methods = { .sq_item = pyrf_thread_map__item, }; -static char pyrf_thread_map__doc[] = PyDoc_STR("thread map object."); +static const char pyrf_thread_map__doc[] = PyDoc_STR("thread map object."); static PyTypeObject pyrf_thread_map__type = { PyVarObject_HEAD_INIT(NULL, 0) @@ -812,6 +781,17 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, return Py_None; } +static PyObject *pyrf_evsel__str(PyObject *self) +{ + struct pyrf_evsel *pevsel = (void *)self; + struct evsel *evsel = &pevsel->evsel; + + if (!evsel->pmu) + return PyUnicode_FromFormat("evsel(%s)", evsel__name(evsel)); + + return PyUnicode_FromFormat("evsel(%s/%s/)", evsel->pmu->name, evsel__name(evsel)); +} + static PyMethodDef pyrf_evsel__methods[] = { { .ml_name = "open", @@ -822,7 +802,7 @@ static PyMethodDef pyrf_evsel__methods[] = { { .ml_name = NULL, } }; -static char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object."); +static const char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object."); static PyTypeObject pyrf_evsel__type = { PyVarObject_HEAD_INIT(NULL, 0) @@ -833,6 +813,8 @@ static PyTypeObject pyrf_evsel__type = { .tp_doc = pyrf_evsel__doc, .tp_methods = pyrf_evsel__methods, .tp_init = (initproc)pyrf_evsel__init, + .tp_str = pyrf_evsel__str, + .tp_repr = pyrf_evsel__str, }; static int pyrf_evsel__setup_types(void) @@ -918,17 +900,8 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, for (i = 0; i < evlist->core.pollfd.nr; ++i) { PyObject *file; -#if PY_MAJOR_VERSION < 3 - FILE *fp = fdopen(evlist->core.pollfd.entries[i].fd, "r"); - - if (fp == NULL) - goto free_list; - - file = PyFile_FromFile(fp, "perf", "r", NULL); -#else file = PyFile_FromFd(evlist->core.pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 0); -#endif if (file == NULL) goto free_list; @@ -1098,8 +1071,10 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i) struct pyrf_evlist *pevlist = (void *)obj; struct evsel *pos; - if (i >= pevlist->evlist.core.nr_entries) + if (i >= pevlist->evlist.core.nr_entries) { + PyErr_SetString(PyExc_IndexError, "Index out of range"); return NULL; + } evlist__for_each_entry(&pevlist->evlist, pos) { if (i-- == 0) @@ -1109,12 +1084,36 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i) return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel)); } +static PyObject *pyrf_evlist__str(PyObject *self) +{ + struct pyrf_evlist *pevlist = (void *)self; + struct evsel *pos; + struct strbuf sb = STRBUF_INIT; + bool first = true; + PyObject *result; + + strbuf_addstr(&sb, "evlist(["); + evlist__for_each_entry(&pevlist->evlist, pos) { + if (!first) + strbuf_addch(&sb, ','); + if (!pos->pmu) + strbuf_addstr(&sb, evsel__name(pos)); + else + strbuf_addf(&sb, "%s/%s/", pos->pmu->name, evsel__name(pos)); + first = false; + } + strbuf_addstr(&sb, "])"); + result = PyUnicode_FromString(sb.buf); + strbuf_release(&sb); + return result; +} + static PySequenceMethods pyrf_evlist__sequence_methods = { .sq_length = pyrf_evlist__length, .sq_item = pyrf_evlist__item, }; -static char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object."); +static const char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object."); static PyTypeObject pyrf_evlist__type = { PyVarObject_HEAD_INIT(NULL, 0) @@ -1126,6 +1125,8 @@ static PyTypeObject pyrf_evlist__type = { .tp_doc = pyrf_evlist__doc, .tp_methods = pyrf_evlist__methods, .tp_init = (initproc)pyrf_evlist__init, + .tp_repr = pyrf_evlist__str, + .tp_str = pyrf_evlist__str, }; static int pyrf_evlist__setup_types(void) @@ -1136,10 +1137,12 @@ static int pyrf_evlist__setup_types(void) #define PERF_CONST(name) { #name, PERF_##name } -static struct { +struct perf_constant { const char *name; int value; -} perf__constants[] = { +}; + +static const struct perf_constant perf__constants[] = { PERF_CONST(TYPE_HARDWARE), PERF_CONST(TYPE_SOFTWARE), PERF_CONST(TYPE_TRACEPOINT), @@ -1234,12 +1237,66 @@ static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel, tp_format = trace_event__tp_format(sys, name); if (IS_ERR(tp_format)) - return _PyLong_FromLong(-1); + return PyLong_FromLong(-1); - return _PyLong_FromLong(tp_format->id); + return PyLong_FromLong(tp_format->id); #endif // HAVE_LIBTRACEEVENT } +static PyObject *pyrf_evsel__from_evsel(struct evsel *evsel) +{ + struct pyrf_evsel *pevsel = PyObject_New(struct pyrf_evsel, &pyrf_evsel__type); + + if (!pevsel) + return NULL; + + memset(&pevsel->evsel, 0, sizeof(pevsel->evsel)); + evsel__init(&pevsel->evsel, &evsel->core.attr, evsel->core.idx); + + evsel__clone(&pevsel->evsel, evsel); + return (PyObject *)pevsel; +} + +static PyObject *pyrf_evlist__from_evlist(struct evlist *evlist) +{ + struct pyrf_evlist *pevlist = PyObject_New(struct pyrf_evlist, &pyrf_evlist__type); + struct evsel *pos; + + if (!pevlist) + return NULL; + + memset(&pevlist->evlist, 0, sizeof(pevlist->evlist)); + evlist__init(&pevlist->evlist, evlist->core.all_cpus, evlist->core.threads); + evlist__for_each_entry(evlist, pos) { + struct pyrf_evsel *pevsel = (void *)pyrf_evsel__from_evsel(pos); + + evlist__add(&pevlist->evlist, &pevsel->evsel); + } + return (PyObject *)pevlist; +} + +static PyObject *pyrf__parse_events(PyObject *self, PyObject *args) +{ + const char *input; + struct evlist evlist = {}; + struct parse_events_error err; + PyObject *result; + + if (!PyArg_ParseTuple(args, "s", &input)) + return NULL; + + parse_events_error__init(&err); + evlist__init(&evlist, NULL, NULL); + if (parse_events(&evlist, input, &err)) { + parse_events_error__print(&err, input); + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + result = pyrf_evlist__from_evlist(&evlist); + evlist__exit(&evlist); + return result; +} + static PyMethodDef perf__methods[] = { { .ml_name = "tracepoint", @@ -1247,21 +1304,20 @@ static PyMethodDef perf__methods[] = { .ml_flags = METH_VARARGS | METH_KEYWORDS, .ml_doc = PyDoc_STR("Get tracepoint config.") }, + { + .ml_name = "parse_events", + .ml_meth = (PyCFunction) pyrf__parse_events, + .ml_flags = METH_VARARGS, + .ml_doc = PyDoc_STR("Parse a string of events and return an evlist.") + }, { .ml_name = NULL, } }; -#if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC initperf(void) -#else PyMODINIT_FUNC PyInit_perf(void) -#endif { PyObject *obj; int i; PyObject *dict; -#if PY_MAJOR_VERSION < 3 - PyObject *module = Py_InitModule("perf", perf__methods); -#else static struct PyModuleDef moduledef = { PyModuleDef_HEAD_INIT, "perf", /* m_name */ @@ -1274,7 +1330,6 @@ PyMODINIT_FUNC PyInit_perf(void) NULL, /* m_free */ }; PyObject *module = PyModule_Create(&moduledef); -#endif if (module == NULL || pyrf_event__setup_types() < 0 || @@ -1282,11 +1337,7 @@ PyMODINIT_FUNC PyInit_perf(void) pyrf_evsel__setup_types() < 0 || pyrf_thread_map__setup_types() < 0 || pyrf_cpu_map__setup_types() < 0) -#if PY_MAJOR_VERSION < 3 - return; -#else return module; -#endif /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); @@ -1335,7 +1386,7 @@ PyMODINIT_FUNC PyInit_perf(void) goto error; for (i = 0; perf__constants[i].name != NULL; i++) { - obj = _PyLong_FromLong(perf__constants[i].value); + obj = PyLong_FromLong(perf__constants[i].value); if (obj == NULL) goto error; PyDict_SetItemString(dict, perf__constants[i].name, obj); @@ -1345,109 +1396,5 @@ PyMODINIT_FUNC PyInit_perf(void) error: if (PyErr_Occurred()) PyErr_SetString(PyExc_ImportError, "perf: Init failed!"); -#if PY_MAJOR_VERSION >= 3 return module; -#endif -} - - -/* The following are stubs to avoid dragging in builtin-* objects. */ -/* TODO: move the code out of the builtin-* file into util. */ - -unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; - -#ifdef HAVE_KVM_STAT_SUPPORT -bool kvm_entry_event(struct evsel *evsel __maybe_unused) -{ - return false; -} - -bool kvm_exit_event(struct evsel *evsel __maybe_unused) -{ - return false; -} - -bool exit_event_begin(struct evsel *evsel __maybe_unused, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) -{ - return false; -} - -bool exit_event_end(struct evsel *evsel __maybe_unused, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) -{ - return false; -} - -void exit_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, - struct event_key *key __maybe_unused, - char *decode __maybe_unused) -{ -} -#endif // HAVE_KVM_STAT_SUPPORT - -int find_scripts(char **scripts_array __maybe_unused, char **scripts_path_array __maybe_unused, - int num __maybe_unused, int pathlen __maybe_unused) -{ - return -1; -} - -void perf_stat__set_no_csv_summary(int set __maybe_unused) -{ -} - -void perf_stat__set_big_num(int set __maybe_unused) -{ -} - -int script_spec_register(const char *spec __maybe_unused, struct scripting_ops *ops __maybe_unused) -{ - return -1; -} - -arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch __maybe_unused) -{ - return NULL; -} - -struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork __maybe_unused, - struct kwork_class *class __maybe_unused, - struct kwork_work *key __maybe_unused) -{ - return NULL; -} - -void script_fetch_insn(struct perf_sample *sample __maybe_unused, - struct thread *thread __maybe_unused, - struct machine *machine __maybe_unused) -{ -} - -int perf_sample__sprintf_flags(u32 flags __maybe_unused, char *str __maybe_unused, - size_t sz __maybe_unused) -{ - return -1; -} - -bool match_callstack_filter(struct machine *machine __maybe_unused, u64 *callstack __maybe_unused) -{ - return false; -} - -struct lock_stat *lock_stat_find(u64 addr __maybe_unused) -{ - return NULL; -} - -struct lock_stat *lock_stat_findnew(u64 addr __maybe_unused, const char *name __maybe_unused, - int flags __maybe_unused) -{ - return NULL; -} - -int cmd_inject(int argc __maybe_unused, const char *argv[] __maybe_unused) -{ - return -1; } diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 85b7f188f729..e261a57b87d4 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -344,7 +344,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, struct addr_location *al) { struct thread *thread = al->thread; - struct tep_event *event = evsel->tp_format; + struct tep_event *event; struct tep_format_field *field; static char handler[256]; unsigned long long val; @@ -362,6 +362,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return; + event = evsel__tp_format(evsel); if (!event) { pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config); return; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 8bdae066e839..b1b5e94537e4 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -58,22 +58,6 @@ #include "mem-events.h" #include "util/perf_regs.h" -#if PY_MAJOR_VERSION < 3 -#define _PyUnicode_FromString(arg) \ - PyString_FromString(arg) -#define _PyUnicode_FromStringAndSize(arg1, arg2) \ - PyString_FromStringAndSize((arg1), (arg2)) -#define _PyBytes_FromStringAndSize(arg1, arg2) \ - PyString_FromStringAndSize((arg1), (arg2)) -#define _PyLong_FromLong(arg) \ - PyInt_FromLong(arg) -#define _PyLong_AsLong(arg) \ - PyInt_AsLong(arg) -#define _PyCapsule_New(arg1, arg2, arg3) \ - PyCObject_FromVoidPtr((arg1), (arg2)) - -PyMODINIT_FUNC initperf_trace_context(void); -#else #define _PyUnicode_FromString(arg) \ PyUnicode_FromString(arg) #define _PyUnicode_FromStringAndSize(arg1, arg2) \ @@ -88,7 +72,6 @@ PyMODINIT_FUNC initperf_trace_context(void); PyCapsule_New((arg1), (arg2), (arg3)) PyMODINIT_FUNC PyInit_perf_trace_context(void); -#endif #ifdef HAVE_LIBTRACEEVENT #define TRACE_EVENT_TYPE_MAX \ @@ -181,17 +164,7 @@ static int get_argument_count(PyObject *handler) { int arg_count = 0; - /* - * The attribute for the code object is func_code in Python 2, - * whereas it is __code__ in Python 3.0+. - */ - PyObject *code_obj = PyObject_GetAttrString(handler, - "func_code"); - if (PyErr_Occurred()) { - PyErr_Clear(); - code_obj = PyObject_GetAttrString(handler, - "__code__"); - } + PyObject *code_obj = code_obj = PyObject_GetAttrString(handler, "__code__"); PyErr_Clear(); if (code_obj) { PyObject *arg_count_obj = PyObject_GetAttrString(code_obj, @@ -949,7 +922,7 @@ static void python_process_tracepoint(struct perf_sample *sample, struct addr_location *al, struct addr_location *addr_al) { - struct tep_event *event = evsel->tp_format; + struct tep_event *event; PyObject *handler, *context, *t, *obj = NULL, *callchain; PyObject *dict = NULL, *all_entries_dict = NULL; static char handler_name[256]; @@ -966,6 +939,7 @@ static void python_process_tracepoint(struct perf_sample *sample, bitmap_zero(events_defined, TRACE_EVENT_TYPE_MAX); + event = evsel__tp_format(evsel); if (!event) { snprintf(handler_name, sizeof(handler_name), "ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config); @@ -1902,12 +1876,6 @@ static void set_table_handlers(struct tables *tables) tables->synth_handler = get_handler("synth_data"); } -#if PY_MAJOR_VERSION < 3 -static void _free_command_line(const char **command_line, int num) -{ - free(command_line); -} -#else static void _free_command_line(wchar_t **command_line, int num) { int i; @@ -1915,7 +1883,6 @@ static void _free_command_line(wchar_t **command_line, int num) PyMem_RawFree(command_line[i]); free(command_line); } -#endif /* @@ -1925,30 +1892,12 @@ static int python_start_script(const char *script, int argc, const char **argv, struct perf_session *session) { struct tables *tables = &tables_global; -#if PY_MAJOR_VERSION < 3 - const char **command_line; -#else wchar_t **command_line; -#endif - /* - * Use a non-const name variable to cope with python 2.6's - * PyImport_AppendInittab prototype - */ - char buf[PATH_MAX], name[19] = "perf_trace_context"; + char buf[PATH_MAX]; int i, err = 0; FILE *fp; scripting_context->session = session; -#if PY_MAJOR_VERSION < 3 - command_line = malloc((argc + 1) * sizeof(const char *)); - if (!command_line) - return -1; - - command_line[0] = script; - for (i = 1; i < argc + 1; i++) - command_line[i] = argv[i - 1]; - PyImport_AppendInittab(name, initperf_trace_context); -#else command_line = malloc((argc + 1) * sizeof(wchar_t *)); if (!command_line) return -1; @@ -1956,15 +1905,10 @@ static int python_start_script(const char *script, int argc, const char **argv, command_line[0] = Py_DecodeLocale(script, NULL); for (i = 1; i < argc + 1; i++) command_line[i] = Py_DecodeLocale(argv[i - 1], NULL); - PyImport_AppendInittab(name, PyInit_perf_trace_context); -#endif + PyImport_AppendInittab("perf_trace_context", PyInit_perf_trace_context); Py_Initialize(); -#if PY_MAJOR_VERSION < 3 - PySys_SetArgv(argc + 1, (char **)command_line); -#else PySys_SetArgv(argc + 1, command_line); -#endif fp = fopen(script, "r"); if (!fp) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 507e6cba9545..c06e3020a976 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -37,6 +37,7 @@ #include "arch/common.h" #include "units.h" #include "annotate.h" +#include "perf.h" #include <internal/lib.h> static int perf_session__deliver_event(struct perf_session *session, diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 9dd60c7869a2..3dd33721823f 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1038,17 +1038,19 @@ static char *get_trace_output(struct hist_entry *he) .data = he->raw_data, .size = he->raw_size, }; + struct tep_event *tp_format; evsel = hists_to_evsel(he->hists); trace_seq_init(&seq); - if (symbol_conf.raw_trace) { - tep_print_fields(&seq, he->raw_data, he->raw_size, - evsel->tp_format); - } else { - tep_print_event(evsel->tp_format->tep, - &seq, &rec, "%s", TEP_PRINT_INFO); + tp_format = evsel__tp_format(evsel); + if (tp_format) { + if (symbol_conf.raw_trace) + tep_print_fields(&seq, he->raw_data, he->raw_size, tp_format); + else + tep_print_event(tp_format->tep, &seq, &rec, "%s", TEP_PRINT_INFO); } + /* * Trim the buffer, it starts at 4KB and we're not going to * add anything more to this buffer. @@ -3293,9 +3295,8 @@ static int __dynamic_dimension__add(struct evsel *evsel, static int add_evsel_fields(struct evsel *evsel, bool raw_trace, int level) { int ret; - struct tep_format_field *field; - - field = evsel->tp_format->format.fields; + struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *field = tp_format ? tp_format->format.fields : NULL; while (field) { ret = __dynamic_dimension__add(evsel, field, raw_trace, level); if (ret < 0) @@ -3328,13 +3329,19 @@ static int add_all_matching_fields(struct evlist *evlist, { int ret = -ESRCH; struct evsel *evsel; - struct tep_format_field *field; evlist__for_each_entry(evlist, evsel) { + struct tep_event *tp_format; + struct tep_format_field *field; + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) continue; - field = tep_find_any_field(evsel->tp_format, field_name); + tp_format = evsel__tp_format(evsel); + if (tp_format == NULL) + continue; + + field = tep_find_any_field(tp_format, field_name); if (field == NULL) continue; @@ -3416,7 +3423,9 @@ static int add_dynamic_entry(struct evlist *evlist, const char *tok, if (!strcmp(field_name, "*")) { ret = add_evsel_fields(evsel, raw_trace, level); } else { - struct tep_format_field *field = tep_find_any_field(evsel->tp_format, field_name); + struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *field = + tp_format ? tep_find_any_field(tp_format, field_name) : NULL; if (field == NULL) { pr_debug("Cannot find event field for %s.%s\n", diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 53dcdf07f5a2..ba79f73e1cf5 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -114,23 +114,59 @@ static void print_running_csv(struct perf_stat_config *config, u64 run, u64 ena) fprintf(config->output, "%s%" PRIu64 "%s%.2f", config->csv_sep, run, config->csv_sep, enabled_percent); } +struct outstate { + /* Std mode: insert a newline before the next metric */ + bool newline; + /* JSON mode: track need for comma for a previous field or not */ + bool first; + /* Num CSV separators remaining to pad out when not all fields are printed */ + int csv_col_pad; -static void print_running_json(struct perf_stat_config *config, u64 run, u64 ena) + /* + * The following don't track state across fields, but are here as a shortcut to + * pass data to the print functions. The alternative would be to update the + * function signatures of the entire print stack to pass them through. + */ + /* Place to output to */ + FILE * const fh; + /* Lines are timestamped in --interval-print mode */ + char timestamp[64]; + /* Num items aggregated in current line. See struct perf_stat_aggr.nr */ + int aggr_nr; + /* Core/socket/die etc ID for the current line */ + struct aggr_cpu_id id; + /* Event for current line */ + struct evsel *evsel; + /* Cgroup for current line */ + struct cgroup *cgrp; +}; + +static const char *json_sep(struct outstate *os) +{ + const char *sep = os->first ? "" : ", "; + + os->first = false; + return sep; +} + +#define json_out(os, format, ...) fprintf((os)->fh, "%s" format, json_sep(os), ##__VA_ARGS__) + +static void print_running_json(struct outstate *os, u64 run, u64 ena) { double enabled_percent = 100; if (run != ena) enabled_percent = 100 * run / ena; - fprintf(config->output, "\"event-runtime\" : %" PRIu64 ", \"pcnt-running\" : %.2f, ", - run, enabled_percent); + json_out(os, "\"event-runtime\" : %" PRIu64 ", \"pcnt-running\" : %.2f", + run, enabled_percent); } -static void print_running(struct perf_stat_config *config, +static void print_running(struct perf_stat_config *config, struct outstate *os, u64 run, u64 ena, bool before_metric) { if (config->json_output) { if (before_metric) - print_running_json(config, run, ena); + print_running_json(os, run, ena); } else if (config->csv_output) { if (before_metric) print_running_csv(config, run, ena); @@ -153,20 +189,20 @@ static void print_noise_pct_csv(struct perf_stat_config *config, fprintf(config->output, "%s%.2f%%", config->csv_sep, pct); } -static void print_noise_pct_json(struct perf_stat_config *config, +static void print_noise_pct_json(struct outstate *os, double pct) { - fprintf(config->output, "\"variance\" : %.2f, ", pct); + json_out(os, "\"variance\" : %.2f", pct); } -static void print_noise_pct(struct perf_stat_config *config, +static void print_noise_pct(struct perf_stat_config *config, struct outstate *os, double total, double avg, bool before_metric) { double pct = rel_stddev_stats(total, avg); if (config->json_output) { if (before_metric) - print_noise_pct_json(config, pct); + print_noise_pct_json(os, pct); } else if (config->csv_output) { if (before_metric) print_noise_pct_csv(config, pct); @@ -176,7 +212,7 @@ static void print_noise_pct(struct perf_stat_config *config, } } -static void print_noise(struct perf_stat_config *config, +static void print_noise(struct perf_stat_config *config, struct outstate *os, struct evsel *evsel, double avg, bool before_metric) { struct perf_stat_evsel *ps; @@ -185,7 +221,7 @@ static void print_noise(struct perf_stat_config *config, return; ps = evsel->stats; - print_noise_pct(config, stddev_stats(&ps->res_stats), avg, before_metric); + print_noise_pct(config, os, stddev_stats(&ps->res_stats), avg, before_metric); } static void print_cgroup_std(struct perf_stat_config *config, const char *cgrp_name) @@ -198,18 +234,19 @@ static void print_cgroup_csv(struct perf_stat_config *config, const char *cgrp_n fprintf(config->output, "%s%s", config->csv_sep, cgrp_name); } -static void print_cgroup_json(struct perf_stat_config *config, const char *cgrp_name) +static void print_cgroup_json(struct outstate *os, const char *cgrp_name) { - fprintf(config->output, "\"cgroup\" : \"%s\", ", cgrp_name); + json_out(os, "\"cgroup\" : \"%s\"", cgrp_name); } -static void print_cgroup(struct perf_stat_config *config, struct cgroup *cgrp) +static void print_cgroup(struct perf_stat_config *config, struct outstate *os, + struct cgroup *cgrp) { if (nr_cgroups || config->cgroup_list) { const char *cgrp_name = cgrp ? cgrp->name : ""; if (config->json_output) - print_cgroup_json(config, cgrp_name); + print_cgroup_json(os, cgrp_name); else if (config->csv_output) print_cgroup_csv(config, cgrp_name); else @@ -324,47 +361,45 @@ static void print_aggr_id_csv(struct perf_stat_config *config, } } -static void print_aggr_id_json(struct perf_stat_config *config, +static void print_aggr_id_json(struct perf_stat_config *config, struct outstate *os, struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { - FILE *output = config->output; - switch (config->aggr_mode) { case AGGR_CORE: - fprintf(output, "\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d, ", + json_out(os, "\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d", id.socket, id.die, id.core, aggr_nr); break; case AGGR_CACHE: - fprintf(output, "\"cache\" : \"S%d-D%d-L%d-ID%d\", \"aggregate-number\" : %d, ", + json_out(os, "\"cache\" : \"S%d-D%d-L%d-ID%d\", \"aggregate-number\" : %d", id.socket, id.die, id.cache_lvl, id.cache, aggr_nr); break; case AGGR_CLUSTER: - fprintf(output, "\"cluster\" : \"S%d-D%d-CLS%d\", \"aggregate-number\" : %d, ", + json_out(os, "\"cluster\" : \"S%d-D%d-CLS%d\", \"aggregate-number\" : %d", id.socket, id.die, id.cluster, aggr_nr); break; case AGGR_DIE: - fprintf(output, "\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d, ", + json_out(os, "\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d", id.socket, id.die, aggr_nr); break; case AGGR_SOCKET: - fprintf(output, "\"socket\" : \"S%d\", \"aggregate-number\" : %d, ", + json_out(os, "\"socket\" : \"S%d\", \"aggregate-number\" : %d", id.socket, aggr_nr); break; case AGGR_NODE: - fprintf(output, "\"node\" : \"N%d\", \"aggregate-number\" : %d, ", + json_out(os, "\"node\" : \"N%d\", \"aggregate-number\" : %d", id.node, aggr_nr); break; case AGGR_NONE: if (evsel->percore && !config->percore_show_thread) { - fprintf(output, "\"core\" : \"S%d-D%d-C%d\"", + json_out(os, "\"core\" : \"S%d-D%d-C%d\"", id.socket, id.die, id.core); } else if (id.cpu.cpu > -1) { - fprintf(output, "\"cpu\" : \"%d\", ", + json_out(os, "\"cpu\" : \"%d\"", id.cpu.cpu); } break; case AGGR_THREAD: - fprintf(output, "\"thread\" : \"%s-%d\", ", + json_out(os, "\"thread\" : \"%s-%d\"", perf_thread_map__comm(evsel->core.threads, id.thread_idx), perf_thread_map__pid(evsel->core.threads, id.thread_idx)); break; @@ -376,29 +411,17 @@ static void print_aggr_id_json(struct perf_stat_config *config, } } -static void aggr_printout(struct perf_stat_config *config, +static void aggr_printout(struct perf_stat_config *config, struct outstate *os, struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { if (config->json_output) - print_aggr_id_json(config, evsel, id, aggr_nr); + print_aggr_id_json(config, os, evsel, id, aggr_nr); else if (config->csv_output) print_aggr_id_csv(config, evsel, id, aggr_nr); else print_aggr_id_std(config, evsel, id, aggr_nr); } -struct outstate { - FILE *fh; - bool newline; - bool first; - const char *prefix; - int nfields; - int aggr_nr; - struct aggr_cpu_id id; - struct evsel *evsel; - struct cgroup *cgrp; -}; - static void new_line_std(struct perf_stat_config *config __maybe_unused, void *ctx) { @@ -411,9 +434,9 @@ static inline void __new_line_std_csv(struct perf_stat_config *config, struct outstate *os) { fputc('\n', os->fh); - if (os->prefix) - fputs(os->prefix, os->fh); - aggr_printout(config, os->evsel, os->id, os->aggr_nr); + if (config->interval) + fputs(os->timestamp, os->fh); + aggr_printout(config, os, os->evsel, os->id, os->aggr_nr); } static inline void __new_line_std(struct outstate *os) @@ -464,7 +487,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx) int i; __new_line_std_csv(config, os); - for (i = 0; i < os->nfields; i++) + for (i = 0; i < os->csv_col_pad; i++) fputs(config->csv_sep, os->fh); } @@ -499,9 +522,9 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused, FILE *out = os->fh; if (unit) { - fprintf(out, "\"metric-value\" : \"%f\", \"metric-unit\" : \"%s\"", val, unit); + json_out(os, "\"metric-value\" : \"%f\", \"metric-unit\" : \"%s\"", val, unit); if (thresh != METRIC_THRESHOLD_UNKNOWN) { - fprintf(out, ", \"metric-threshold\" : \"%s\"", + json_out(os, "\"metric-threshold\" : \"%s\"", metric_threshold_classify__str(thresh)); } } @@ -514,9 +537,11 @@ static void new_line_json(struct perf_stat_config *config, void *ctx) struct outstate *os = ctx; fputs("\n{", os->fh); - if (os->prefix) - fprintf(os->fh, "%s", os->prefix); - aggr_printout(config, os->evsel, os->id, os->aggr_nr); + os->first = true; + if (config->interval) + json_out(os, "%s", os->timestamp); + + aggr_printout(config, os, os->evsel, os->id, os->aggr_nr); } static void print_metricgroup_header_json(struct perf_stat_config *config, @@ -526,7 +551,7 @@ static void print_metricgroup_header_json(struct perf_stat_config *config, if (!metricgroup_name) return; - fprintf(config->output, "\"metricgroup\" : \"%s\"}", metricgroup_name); + json_out((struct outstate *) ctx, "\"metricgroup\" : \"%s\"}", metricgroup_name); new_line_json(config, ctx); } @@ -539,12 +564,12 @@ static void print_metricgroup_header_csv(struct perf_stat_config *config, if (!metricgroup_name) { /* Leave space for running and enabling */ - for (i = 0; i < os->nfields - 2; i++) + for (i = 0; i < os->csv_col_pad - 2; i++) fputs(config->csv_sep, os->fh); return; } - for (i = 0; i < os->nfields; i++) + for (i = 0; i < os->csv_col_pad; i++) fputs(config->csv_sep, os->fh); fprintf(config->output, "%s", metricgroup_name); new_line_csv(config, ctx); @@ -644,7 +669,6 @@ static void print_metric_only_json(struct perf_stat_config *config __maybe_unuse const char *unit, double val) { struct outstate *os = ctx; - FILE *out = os->fh; char buf[64], *ends; char tbuf[1024]; const char *vals; @@ -661,13 +685,7 @@ static void print_metric_only_json(struct perf_stat_config *config __maybe_unuse *ends = 0; if (!vals[0]) vals = "none"; - fprintf(out, "%s\"%s\" : \"%s\"", os->first ? "" : ", ", unit, vals); - os->first = false; -} - -static void new_line_metric(struct perf_stat_config *config __maybe_unused, - void *ctx __maybe_unused) -{ + json_out(os, "\"%s\" : \"%s\"", unit, vals); } static void print_metric_header(struct perf_stat_config *config, @@ -743,28 +761,27 @@ static void print_counter_value_csv(struct perf_stat_config *config, fprintf(output, "%s", evsel__name(evsel)); } -static void print_counter_value_json(struct perf_stat_config *config, +static void print_counter_value_json(struct outstate *os, struct evsel *evsel, double avg, bool ok) { - FILE *output = config->output; const char *bad_count = evsel->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED; if (ok) - fprintf(output, "\"counter-value\" : \"%f\", ", avg); + json_out(os, "\"counter-value\" : \"%f\"", avg); else - fprintf(output, "\"counter-value\" : \"%s\", ", bad_count); + json_out(os, "\"counter-value\" : \"%s\"", bad_count); if (evsel->unit) - fprintf(output, "\"unit\" : \"%s\", ", evsel->unit); + json_out(os, "\"unit\" : \"%s\"", evsel->unit); - fprintf(output, "\"event\" : \"%s\", ", evsel__name(evsel)); + json_out(os, "\"event\" : \"%s\"", evsel__name(evsel)); } -static void print_counter_value(struct perf_stat_config *config, +static void print_counter_value(struct perf_stat_config *config, struct outstate *os, struct evsel *evsel, double avg, bool ok) { if (config->json_output) - print_counter_value_json(config, evsel, avg, ok); + print_counter_value_json(os, evsel, avg, ok); else if (config->csv_output) print_counter_value_csv(config, evsel, avg, ok); else @@ -772,12 +789,13 @@ static void print_counter_value(struct perf_stat_config *config, } static void abs_printout(struct perf_stat_config *config, + struct outstate *os, struct aggr_cpu_id id, int aggr_nr, struct evsel *evsel, double avg, bool ok) { - aggr_printout(config, evsel, id, aggr_nr); - print_counter_value(config, evsel, avg, ok); - print_cgroup(config, evsel->cgrp); + aggr_printout(config, os, evsel, id, aggr_nr); + print_counter_value(config, os, evsel, avg, ok); + print_cgroup(config, os, evsel->cgrp); } static bool is_mixed_hw_group(struct evsel *counter) @@ -831,22 +849,23 @@ static void printout(struct perf_stat_config *config, struct outstate *os, if (config->csv_output) { pm = config->metric_only ? print_metric_only_csv : print_metric_csv; - nl = config->metric_only ? new_line_metric : new_line_csv; + nl = config->metric_only ? NULL : new_line_csv; pmh = print_metricgroup_header_csv; - os->nfields = 4 + (counter->cgrp ? 1 : 0); + os->csv_col_pad = 4 + (counter->cgrp ? 1 : 0); } else if (config->json_output) { pm = config->metric_only ? print_metric_only_json : print_metric_json; - nl = config->metric_only ? new_line_metric : new_line_json; + nl = config->metric_only ? NULL : new_line_json; pmh = print_metricgroup_header_json; } else { pm = config->metric_only ? print_metric_only : print_metric_std; - nl = config->metric_only ? new_line_metric : new_line_std; + nl = config->metric_only ? NULL : new_line_std; pmh = print_metricgroup_header_std; } if (run == 0 || ena == 0 || counter->counts->scaled == -1) { if (config->metric_only) { - pm(config, os, METRIC_THRESHOLD_UNKNOWN, "", "", 0); + pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, + /*unit=*/NULL, /*val=*/0); return; } @@ -868,17 +887,17 @@ static void printout(struct perf_stat_config *config, struct outstate *os, out.force_header = false; if (!config->metric_only && !counter->default_metricgroup) { - abs_printout(config, os->id, os->aggr_nr, counter, uval, ok); + abs_printout(config, os, os->id, os->aggr_nr, counter, uval, ok); - print_noise(config, counter, noise, /*before_metric=*/true); - print_running(config, run, ena, /*before_metric=*/true); + print_noise(config, os, counter, noise, /*before_metric=*/true); + print_running(config, os, run, ena, /*before_metric=*/true); } if (ok) { if (!config->metric_only && counter->default_metricgroup) { void *from = NULL; - aggr_printout(config, os->evsel, os->id, os->aggr_nr); + aggr_printout(config, os, os->evsel, os->id, os->aggr_nr); /* Print out all the metricgroup with the same metric event. */ do { int num = 0; @@ -891,8 +910,8 @@ static void printout(struct perf_stat_config *config, struct outstate *os, __new_line_std_csv(config, os); } - print_noise(config, counter, noise, /*before_metric=*/true); - print_running(config, run, ena, /*before_metric=*/true); + print_noise(config, os, counter, noise, /*before_metric=*/true); + print_running(config, os, run, ena, /*before_metric=*/true); from = perf_stat__print_shadow_stats_metricgroup(config, counter, aggr_idx, &num, from, &out, &config->metric_events); @@ -901,12 +920,12 @@ static void printout(struct perf_stat_config *config, struct outstate *os, perf_stat__print_shadow_stats(config, counter, uval, aggr_idx, &out, &config->metric_events); } else { - pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, /*unit=*/"", /*val=*/0); + pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, /*unit=*/NULL, /*val=*/0); } if (!config->metric_only) { - print_noise(config, counter, noise, /*before_metric=*/false); - print_running(config, run, ena, /*before_metric=*/false); + print_noise(config, os, counter, noise, /*before_metric=*/false); + print_running(config, os, run, ena, /*before_metric=*/false); } } @@ -1083,12 +1102,17 @@ static void print_counter_aggrdata(struct perf_stat_config *config, return; if (!metric_only) { - if (config->json_output) + if (config->json_output) { + os->first = true; fputc('{', output); - if (os->prefix) - fprintf(output, "%s", os->prefix); - else if (config->summary && config->csv_output && - !config->no_csv_summary && !config->interval) + } + if (config->interval) { + if (config->json_output) + json_out(os, "%s", os->timestamp); + else + fprintf(output, "%s", os->timestamp); + } else if (config->summary && config->csv_output && + !config->no_csv_summary) fprintf(output, "%s%s", "summary", config->csv_sep); } @@ -1114,15 +1138,19 @@ static void print_metric_begin(struct perf_stat_config *config, if (config->json_output) fputc('{', config->output); - if (os->prefix) - fprintf(config->output, "%s", os->prefix); + if (config->interval) { + if (config->json_output) + json_out(os, "%s", os->timestamp); + else + fprintf(config->output, "%s", os->timestamp); + } evsel = evlist__first(evlist); id = config->aggr_map->map[aggr_idx]; aggr = &evsel->stats->aggr[aggr_idx]; - aggr_printout(config, evsel, id, aggr->nr); + aggr_printout(config, os, evsel, id, aggr->nr); - print_cgroup(config, os->cgrp ? : evsel->cgrp); + print_cgroup(config, os, os->cgrp ? : evsel->cgrp); } static void print_metric_end(struct perf_stat_config *config, struct outstate *os) @@ -1301,7 +1329,7 @@ static void print_metric_headers(struct perf_stat_config *config, struct perf_stat_output_ctx out = { .ctx = &os, .print_metric = print_metric_header, - .new_line = new_line_metric, + .new_line = NULL, .force_header = true, }; @@ -1336,20 +1364,20 @@ static void print_metric_headers(struct perf_stat_config *config, fputc('\n', config->output); } -static void prepare_interval(struct perf_stat_config *config, - char *prefix, size_t len, struct timespec *ts) +static void prepare_timestamp(struct perf_stat_config *config, + struct outstate *os, struct timespec *ts) { if (config->iostat_run) return; if (config->json_output) - scnprintf(prefix, len, "\"interval\" : %lu.%09lu, ", + scnprintf(os->timestamp, sizeof(os->timestamp), "\"interval\" : %lu.%09lu", (unsigned long) ts->tv_sec, ts->tv_nsec); else if (config->csv_output) - scnprintf(prefix, len, "%lu.%09lu%s", + scnprintf(os->timestamp, sizeof(os->timestamp), "%lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep); else - scnprintf(prefix, len, "%6lu.%09lu ", + scnprintf(os->timestamp, sizeof(os->timestamp), "%6lu.%09lu ", (unsigned long) ts->tv_sec, ts->tv_nsec); } @@ -1557,7 +1585,7 @@ static void print_footer(struct perf_stat_config *config) fprintf(output, " %17.*f +- %.*f seconds time elapsed", precision, avg, precision, sd); - print_noise_pct(config, sd, avg, /*before_metric=*/false); + print_noise_pct(config, NULL, sd, avg, /*before_metric=*/false); } fprintf(output, "\n\n"); @@ -1672,9 +1700,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf int argc, const char **argv) { bool metric_only = config->metric_only; - int interval = config->interval; struct evsel *counter; - char buf[64]; struct outstate os = { .fh = config->output, .first = true, @@ -1685,10 +1711,8 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf if (config->iostat_run) evlist->selected = evlist__first(evlist); - if (interval) { - os.prefix = buf; - prepare_interval(config, buf, sizeof(buf), ts); - } + if (config->interval) + prepare_timestamp(config, &os, ts); print_header(config, _target, evlist, argc, argv); @@ -1707,7 +1731,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf case AGGR_THREAD: case AGGR_GLOBAL: if (config->iostat_run) { - iostat_print_counters(evlist, config, ts, buf, + iostat_print_counters(evlist, config, ts, os.timestamp, (iostat_print_counter_t)print_counter, &os); } else if (config->cgroup_list) { print_cgroup_counter(config, evlist, &os); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 47718610d5d8..fa8b2a1048ff 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -327,7 +327,8 @@ static void print_instructions(struct perf_stat_config *config, "insn per cycle", 0); } if (max_stalled && instructions) { - out->new_line(config, ctxp); + if (out->new_line) + out->new_line(config, ctxp); print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%7.2f ", "stalled cycles per insn", max_stalled / instructions); } @@ -670,7 +671,7 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config, } } - if ((*num)++ > 0) + if ((*num)++ > 0 && out->new_line) out->new_line(config, ctxp); generic_metric(config, mexp, evsel, aggr_idx, out); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 6f8cff3cd39a..2fda9acd7374 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -117,8 +117,9 @@ struct perf_stat_config { unsigned int topdown_level; }; +extern struct perf_stat_config stat_config; + void perf_stat__set_big_num(int set); -void perf_stat__set_no_csv_summary(int set); void update_stats(struct stats *stats, u64 val); double avg_stats(struct stats *stats); diff --git a/tools/perf/util/stream.c b/tools/perf/util/stream.c index 545e44981a27..3de4a6130853 100644 --- a/tools/perf/util/stream.c +++ b/tools/perf/util/stream.c @@ -52,7 +52,6 @@ static struct evlist_streams *evlist_streams__new(int nr_evsel, goto err; s->nr_streams_max = nr_streams_max; - s->evsel_idx = -1; } els->ev_streams = es; @@ -139,7 +138,7 @@ static int evlist__init_callchain_streams(struct evlist *evlist, hists__output_resort(hists, NULL); init_hot_callchain(hists, &es[i]); - es[i].evsel_idx = pos->core.idx; + es[i].evsel = pos; i++; } @@ -166,12 +165,12 @@ struct evlist_streams *evlist__create_streams(struct evlist *evlist, } struct evsel_streams *evsel_streams__entry(struct evlist_streams *els, - int evsel_idx) + const struct evsel *evsel) { struct evsel_streams *es = els->ev_streams; for (int i = 0; i < els->nr_evsel; i++) { - if (es[i].evsel_idx == evsel_idx) + if (es[i].evsel == evsel) return &es[i]; } diff --git a/tools/perf/util/stream.h b/tools/perf/util/stream.h index bee768874fea..50f7e6e04982 100644 --- a/tools/perf/util/stream.h +++ b/tools/perf/util/stream.h @@ -2,7 +2,9 @@ #ifndef __PERF_STREAM_H #define __PERF_STREAM_H -#include "callchain.h" +struct callchain_node; +struct evlist; +struct evsel; struct stream { struct callchain_node *cnode; @@ -11,9 +13,9 @@ struct stream { struct evsel_streams { struct stream *streams; + const struct evsel *evsel; int nr_streams_max; int nr_streams; - int evsel_idx; u64 streams_hits; }; @@ -22,15 +24,13 @@ struct evlist_streams { int nr_evsel; }; -struct evlist; - void evlist_streams__delete(struct evlist_streams *els); struct evlist_streams *evlist__create_streams(struct evlist *evlist, int nr_streams_max); struct evsel_streams *evsel_streams__entry(struct evlist_streams *els, - int evsel_idx); + const struct evsel *evsel); void evsel_streams__match(struct evsel_streams *es_base, struct evsel_streams *es_pair); diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 308fc7ec88cc..c0e927bbadf6 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -254,11 +254,20 @@ char *strpbrk_esc(char *str, const char *stopset) do { ptr = strpbrk(str, stopset); - if (ptr == str || - (ptr == str + 1 && *(ptr - 1) != '\\')) + if (!ptr) { + /* stopset not in str. */ break; + } + if (ptr == str) { + /* stopset character is first in str. */ + break; + } + if (ptr == str + 1 && str[0] != '\\') { + /* stopset chacter is second and wasn't preceded by a '\'. */ + break; + } str = ptr + 1; - } while (ptr && *(ptr - 1) == '\\' && *(ptr - 2) != '\\'); + } while (ptr[-1] == '\\' && ptr[-2] != '\\'); return ptr; } diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 2b04f47f4db0..b1d259f590e9 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -21,6 +21,7 @@ #include <perf/cpumap.h> #include "env.h" +#include "perf.h" #include "svghelper.h" static u64 first_time, last_time; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index e398abfd13a0..66fd1249660a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -287,8 +287,9 @@ static bool want_demangle(bool is_kernel_sym) * Demangle C++ function signature, typically replaced by demangle-cxx.cpp * version. */ -__weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, - bool modifiers __maybe_unused) +#ifndef HAVE_CXA_DEMANGLE_SUPPORT +char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, + bool modifiers __maybe_unused) { #ifdef HAVE_LIBBFD_SUPPORT int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); @@ -302,6 +303,7 @@ __weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __mayb return NULL; #endif } +#endif /* !HAVE_CXA_DEMANGLE_SUPPORT */ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 0037f1163919..49b08adc6ee3 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -154,6 +154,13 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb) else if ((a == 0) && (b > 0)) return SYMBOL_B; + if (syma->type != symb->type) { + if (syma->type == STT_NOTYPE) + return SYMBOL_B; + if (symb->type == STT_NOTYPE) + return SYMBOL_A; + } + /* Prefer a non weak symbol over a weak one */ a = syma->binding == STB_WEAK; b = symb->binding == STB_WEAK; @@ -257,7 +264,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) * like in: * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi] */ - if (prev->end == prev->start && prev->type != STT_NOTYPE) { + if (prev->end == prev->start) { const char *prev_mod; const char *curr_mod; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a58444c4aed1..6923b0d5efed 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1686,12 +1686,16 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo } if (type & PERF_SAMPLE_RAW) { - u.val32[0] = sample->raw_size; - *array = u.val64; - array = (void *)array + sizeof(u32); + u32 *array32 = (void *)array; - memcpy(array, sample->raw_data, sample->raw_size); - array = (void *)array + sample->raw_size; + *array32 = sample->raw_size; + array32++; + + memcpy(array32, sample->raw_data, sample->raw_size); + array = (void *)(array32 + (sample->raw_size / sizeof(u32))); + + /* make sure the array is 64-bit aligned */ + BUG_ON(((long)array) % sizeof(u64)); } if (type & PERF_SAMPLE_BRANCH_STACK) { diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 69d8dcf5cf28..928aca4cd6e9 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -10,52 +10,12 @@ #include <linux/compiler.h> #include <linux/zalloc.h> -#ifdef HAVE_SYSCALL_TABLE_SUPPORT #include <string.h> #include "string2.h" -#if defined(__x86_64__) -#include <asm/syscalls_64.c> -const int syscalltbl_native_max_id = SYSCALLTBL_x86_64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_x86_64; -#elif defined(__i386__) -#include <asm/syscalls_32.c> -const int syscalltbl_native_max_id = SYSCALLTBL_x86_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_x86; -#elif defined(__s390x__) -#include <asm/syscalls_64.c> -const int syscalltbl_native_max_id = SYSCALLTBL_S390_64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_s390_64; -#elif defined(__powerpc64__) -#include <asm/syscalls_64.c> -const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_powerpc_64; -#elif defined(__powerpc__) -#include <asm/syscalls_32.c> -const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_powerpc_32; -#elif defined(__aarch64__) -#include <asm/syscalls.c> -const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_arm64; -#elif defined(__mips__) -#include <asm/syscalls_n64.c> -const int syscalltbl_native_max_id = SYSCALLTBL_MIPS_N64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_mips_n64; -#elif defined(__loongarch__) -#include <asm/syscalls.c> -const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_loongarch; -#elif defined(__riscv) -#include <asm/syscalls.c> -const int syscalltbl_native_max_id = SYSCALLTBL_RISCV_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_riscv; -#else -const int syscalltbl_native_max_id = 0; -static const char *const syscalltbl_native[] = { - [0] = "unknown", -}; -#endif +#include <syscall_table.h> +const int syscalltbl_native_max_id = SYSCALLTBL_MAX_ID; +static const char *const *syscalltbl_native = syscalltbl; struct syscall { int id; @@ -163,47 +123,3 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g *idx = -1; return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); } - -#else /* HAVE_SYSCALL_TABLE_SUPPORT */ - -#include <libaudit.h> - -struct syscalltbl *syscalltbl__new(void) -{ - struct syscalltbl *tbl = zalloc(sizeof(*tbl)); - if (tbl) - tbl->audit_machine = audit_detect_machine(); - return tbl; -} - -void syscalltbl__delete(struct syscalltbl *tbl) -{ - free(tbl); -} - -const char *syscalltbl__name(const struct syscalltbl *tbl, int id) -{ - return audit_syscall_to_name(id, tbl->audit_machine); -} - -int syscalltbl__id(struct syscalltbl *tbl, const char *name) -{ - return audit_name_to_syscall(name, tbl->audit_machine); -} - -int syscalltbl__id_at_idx(struct syscalltbl *tbl __maybe_unused, int idx) -{ - return idx; -} - -int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused, - const char *syscall_glob __maybe_unused, int *idx __maybe_unused) -{ - return -1; -} - -int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx) -{ - return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); -} -#endif /* HAVE_SYSCALL_TABLE_SUPPORT */ diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h index 2b53b7ed25a6..362411a6d849 100644 --- a/tools/perf/util/syscalltbl.h +++ b/tools/perf/util/syscalltbl.h @@ -3,7 +3,6 @@ #define __PERF_SYSCALLTBL_H struct syscalltbl { - int audit_machine; struct { int max_id; int nr_entries; diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 41d53e1b43e7..9c015fc2bcfb 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -99,7 +99,7 @@ unsigned long long read_size(struct tep_event *event, void *ptr, int size) return tep_read_number(event->tep, ptr, size); } -void event_format__fprintf(struct tep_event *event, +void event_format__fprintf(const struct tep_event *event, int cpu, void *data, int size, FILE *fp) { struct tep_record record; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 5596fcda2c10..4e81e02a4f18 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -13,14 +13,94 @@ #include <event-parse.h> #endif +#include "archinsn.h" #include "debug.h" +#include "event.h" #include "trace-event.h" #include "evsel.h" +#include <linux/perf_event.h> #include <linux/zalloc.h> #include "util/sample.h" +unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; + struct scripting_context *scripting_context; +struct script_spec { + struct list_head node; + struct scripting_ops *ops; + char spec[]; +}; + +static LIST_HEAD(script_specs); + +static struct script_spec *script_spec__new(const char *spec, + struct scripting_ops *ops) +{ + struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1); + + if (s != NULL) { + strcpy(s->spec, spec); + s->ops = ops; + } + + return s; +} + +static void script_spec__add(struct script_spec *s) +{ + list_add_tail(&s->node, &script_specs); +} + +static struct script_spec *script_spec__find(const char *spec) +{ + struct script_spec *s; + + list_for_each_entry(s, &script_specs, node) + if (strcasecmp(s->spec, spec) == 0) + return s; + return NULL; +} + +static int script_spec_register(const char *spec, struct scripting_ops *ops) +{ + struct script_spec *s; + + s = script_spec__find(spec); + if (s) + return -1; + + s = script_spec__new(spec, ops); + if (!s) + return -1; + + script_spec__add(s); + return 0; +} + +struct scripting_ops *script_spec__lookup(const char *spec) +{ + struct script_spec *s = script_spec__find(spec); + + if (!s) + return NULL; + + return s->ops; +} + +int script_spec__for_each(int (*cb)(struct scripting_ops *ops, const char *spec)) +{ + struct script_spec *s; + int ret = 0; + + list_for_each_entry(s, &script_specs, node) { + ret = cb(s->ops, s->spec); + if (ret) + break; + } + return ret; +} + void scripting_context__update(struct scripting_context *c, union perf_event *event, struct perf_sample *sample, @@ -28,12 +108,14 @@ void scripting_context__update(struct scripting_context *c, struct addr_location *al, struct addr_location *addr_al) { - c->event_data = sample->raw_data; - c->pevent = NULL; #ifdef HAVE_LIBTRACEEVENT - if (evsel->tp_format) - c->pevent = evsel->tp_format->tep; + const struct tep_event *tp_format = evsel__tp_format(evsel); + + c->pevent = tp_format ? tp_format->tep : NULL; +#else + c->pevent = NULL; #endif + c->event_data = sample->raw_data; c->event = event; c->sample = sample; c->evsel = evsel; @@ -191,3 +273,100 @@ void setup_perl_scripting(void) } #endif #endif + +#if !defined(__i386__) && !defined(__x86_64__) +void arch_fetch_insn(struct perf_sample *sample __maybe_unused, + struct thread *thread __maybe_unused, + struct machine *machine __maybe_unused) +{ +} +#endif + +void script_fetch_insn(struct perf_sample *sample, struct thread *thread, + struct machine *machine, bool native_arch) +{ + if (sample->insn_len == 0 && native_arch) + arch_fetch_insn(sample, thread, machine); +} + +static const struct { + u32 flags; + const char *name; +} sample_flags[] = { + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"}, + {PERF_IP_FLAG_BRANCH, "jmp"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT, + "hw int"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMENTRY, "vmentry"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMEXIT, "vmexit"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_BRANCH_MISS, "br miss"}, + {0, NULL} +}; + +static const char *sample_flags_to_name(u32 flags) +{ + int i; + + for (i = 0; sample_flags[i].name ; i++) { + if (sample_flags[i].flags == flags) + return sample_flags[i].name; + } + + return NULL; +} + +int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz) +{ + u32 xf = PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_INTR_DISABLE | + PERF_IP_FLAG_INTR_TOGGLE; + const char *chars = PERF_IP_FLAG_CHARS; + const size_t n = strlen(PERF_IP_FLAG_CHARS); + const char *name = NULL; + size_t i, pos = 0; + char xs[16] = {0}; + + if (flags & xf) + snprintf(xs, sizeof(xs), "(%s%s%s)", + flags & PERF_IP_FLAG_IN_TX ? "x" : "", + flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", + flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); + + name = sample_flags_to_name(flags & ~xf); + if (name) + return snprintf(str, sz, "%-15s%6s", name, xs); + + if (flags & PERF_IP_FLAG_TRACE_BEGIN) { + name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_BEGIN)); + if (name) + return snprintf(str, sz, "tr strt %-7s%6s", name, xs); + } + + if (flags & PERF_IP_FLAG_TRACE_END) { + name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_END)); + if (name) + return snprintf(str, sz, "tr end %-7s%6s", name, xs); + } + + for (i = 0; i < n; i++, flags >>= 1) { + if ((flags & 1) && pos < sz) + str[pos++] = chars[i]; + } + for (; i < 32; i++, flags >>= 1) { + if ((flags & 1) && pos < sz) + str[pos++] = '?'; + } + if (pos < sz) + str[pos] = 0; + + return pos; +} diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 79b939f947dd..ac9fde2f980c 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -39,7 +39,7 @@ trace_event__tp_format(const char *sys, const char *name); struct tep_event *trace_event__tp_format_id(int id); -void event_format__fprintf(struct tep_event *event, +void event_format__fprintf(const struct tep_event *event, int cpu, void *data, int size, FILE *fp); int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size); @@ -113,10 +113,11 @@ struct scripting_ops { extern unsigned int scripting_max_stack; -int script_spec_register(const char *spec, struct scripting_ops *ops); +struct scripting_ops *script_spec__lookup(const char *spec); +int script_spec__for_each(int (*cb)(struct scripting_ops *ops, const char *spec)); void script_fetch_insn(struct perf_sample *sample, struct thread *thread, - struct machine *machine); + struct machine *machine, bool native_arch); void setup_perl_scripting(void); void setup_python_scripting(void); diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index b9823f414f10..ec72d29f3d58 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -8,6 +8,7 @@ #include "values.h" #include "debug.h" +#include "evsel.h" int perf_read_values_init(struct perf_read_values *values) { @@ -22,21 +23,17 @@ int perf_read_values_init(struct perf_read_values *values) values->threads = 0; values->counters_max = 16; - values->counterrawid = malloc(values->counters_max - * sizeof(*values->counterrawid)); - values->countername = malloc(values->counters_max - * sizeof(*values->countername)); - if (!values->counterrawid || !values->countername) { - pr_debug("failed to allocate read_values counters arrays"); + values->counters = malloc(values->counters_max * sizeof(*values->counters)); + if (!values->counters) { + pr_debug("failed to allocate read_values counters array"); goto out_free_counter; } - values->counters = 0; + values->num_counters = 0; return 0; out_free_counter: - zfree(&values->counterrawid); - zfree(&values->countername); + zfree(&values->counters); out_free_pid: zfree(&values->pid); zfree(&values->tid); @@ -56,10 +53,7 @@ void perf_read_values_destroy(struct perf_read_values *values) zfree(&values->value); zfree(&values->pid); zfree(&values->tid); - zfree(&values->counterrawid); - for (i = 0; i < values->counters; i++) - zfree(&values->countername[i]); - zfree(&values->countername); + zfree(&values->counters); } static int perf_read_values__enlarge_threads(struct perf_read_values *values) @@ -116,81 +110,71 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values, static int perf_read_values__enlarge_counters(struct perf_read_values *values) { - char **countername; - int i, counters_max = values->counters_max * 2; - u64 *counterrawid = realloc(values->counterrawid, counters_max * sizeof(*values->counterrawid)); + int counters_max = values->counters_max * 2; + struct evsel **new_counters = realloc(values->counters, + counters_max * sizeof(*values->counters)); - if (!counterrawid) { - pr_debug("failed to enlarge read_values rawid array"); + if (!new_counters) { + pr_debug("failed to enlarge read_values counters array"); goto out_enomem; } - countername = realloc(values->countername, counters_max * sizeof(*values->countername)); - if (!countername) { - pr_debug("failed to enlarge read_values rawid array"); - goto out_free_rawid; - } - - for (i = 0; i < values->threads; i++) { + for (int i = 0; i < values->threads; i++) { u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value)); - int j; if (!value) { pr_debug("failed to enlarge read_values ->values array"); - goto out_free_name; + goto out_free_counters; } - for (j = values->counters_max; j < counters_max; j++) + for (int j = values->counters_max; j < counters_max; j++) value[j] = 0; values->value[i] = value; } values->counters_max = counters_max; - values->counterrawid = counterrawid; - values->countername = countername; + values->counters = new_counters; return 0; -out_free_name: - free(countername); -out_free_rawid: - free(counterrawid); +out_free_counters: + free(new_counters); out_enomem: return -ENOMEM; } static int perf_read_values__findnew_counter(struct perf_read_values *values, - u64 rawid, const char *name) + struct evsel *evsel) { int i; - for (i = 0; i < values->counters; i++) - if (values->counterrawid[i] == rawid) + for (i = 0; i < values->num_counters; i++) + if (values->counters[i] == evsel) return i; - if (values->counters == values->counters_max) { - i = perf_read_values__enlarge_counters(values); - if (i) - return i; + if (values->num_counters == values->counters_max) { + int err = perf_read_values__enlarge_counters(values); + + if (err) + return err; } - i = values->counters++; - values->counterrawid[i] = rawid; - values->countername[i] = strdup(name); + i = values->num_counters++; + values->counters[i] = evsel; return i; } int perf_read_values_add_value(struct perf_read_values *values, u32 pid, u32 tid, - u64 rawid, const char *name, u64 value) + struct evsel *evsel, u64 value) { int tindex, cindex; tindex = perf_read_values__findnew_thread(values, pid, tid); if (tindex < 0) return tindex; - cindex = perf_read_values__findnew_counter(values, rawid, name); + cindex = perf_read_values__findnew_counter(values, evsel); if (cindex < 0) return cindex; @@ -205,15 +189,15 @@ static void perf_read_values__display_pretty(FILE *fp, int pidwidth, tidwidth; int *counterwidth; - counterwidth = malloc(values->counters * sizeof(*counterwidth)); + counterwidth = malloc(values->num_counters * sizeof(*counterwidth)); if (!counterwidth) { fprintf(fp, "INTERNAL ERROR: Failed to allocate counterwidth array\n"); return; } tidwidth = 3; pidwidth = 3; - for (j = 0; j < values->counters; j++) - counterwidth[j] = strlen(values->countername[j]); + for (j = 0; j < values->num_counters; j++) + counterwidth[j] = strlen(evsel__name(values->counters[j])); for (i = 0; i < values->threads; i++) { int width; @@ -223,7 +207,7 @@ static void perf_read_values__display_pretty(FILE *fp, width = snprintf(NULL, 0, "%d", values->tid[i]); if (width > tidwidth) tidwidth = width; - for (j = 0; j < values->counters; j++) { + for (j = 0; j < values->num_counters; j++) { width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]); if (width > counterwidth[j]) counterwidth[j] = width; @@ -231,14 +215,14 @@ static void perf_read_values__display_pretty(FILE *fp, } fprintf(fp, "# %*s %*s", pidwidth, "PID", tidwidth, "TID"); - for (j = 0; j < values->counters; j++) - fprintf(fp, " %*s", counterwidth[j], values->countername[j]); + for (j = 0; j < values->num_counters; j++) + fprintf(fp, " %*s", counterwidth[j], evsel__name(values->counters[j])); fprintf(fp, "\n"); for (i = 0; i < values->threads; i++) { fprintf(fp, " %*d %*d", pidwidth, values->pid[i], tidwidth, values->tid[i]); - for (j = 0; j < values->counters; j++) + for (j = 0; j < values->num_counters; j++) fprintf(fp, " %*" PRIu64, counterwidth[j], values->value[i][j]); fprintf(fp, "\n"); @@ -266,16 +250,16 @@ static void perf_read_values__display_raw(FILE *fp, if (width > tidwidth) tidwidth = width; } - for (j = 0; j < values->counters; j++) { - width = strlen(values->countername[j]); + for (j = 0; j < values->num_counters; j++) { + width = strlen(evsel__name(values->counters[j])); if (width > namewidth) namewidth = width; - width = snprintf(NULL, 0, "%" PRIx64, values->counterrawid[j]); + width = snprintf(NULL, 0, "%x", values->counters[j]->core.idx); if (width > rawwidth) rawwidth = width; } for (i = 0; i < values->threads; i++) { - for (j = 0; j < values->counters; j++) { + for (j = 0; j < values->num_counters; j++) { width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]); if (width > countwidth) countwidth = width; @@ -287,12 +271,12 @@ static void perf_read_values__display_raw(FILE *fp, namewidth, "Name", rawwidth, "Raw", countwidth, "Count"); for (i = 0; i < values->threads; i++) - for (j = 0; j < values->counters; j++) - fprintf(fp, " %*d %*d %*s %*" PRIx64 " %*" PRIu64, + for (j = 0; j < values->num_counters; j++) + fprintf(fp, " %*d %*d %*s %*x %*" PRIu64, pidwidth, values->pid[i], tidwidth, values->tid[i], - namewidth, values->countername[j], - rawwidth, values->counterrawid[j], + namewidth, evsel__name(values->counters[j]), + rawwidth, values->counters[j]->core.idx, countwidth, values->value[i][j]); } diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h index 791c1ad606c2..bbca33daca19 100644 --- a/tools/perf/util/values.h +++ b/tools/perf/util/values.h @@ -5,14 +5,15 @@ #include <stdio.h> #include <linux/types.h> +struct evsel; + struct perf_read_values { int threads; int threads_max; u32 *pid, *tid; - int counters; + int num_counters; int counters_max; - u64 *counterrawid; - char **countername; + struct evsel **counters; u64 **value; }; @@ -21,7 +22,7 @@ void perf_read_values_destroy(struct perf_read_values *values); int perf_read_values_add_value(struct perf_read_values *values, u32 pid, u32 tid, - u64 rawid, const char *name, u64 value); + struct evsel *evsel, u64 value); void perf_read_values_display(FILE *fp, struct perf_read_values *values, int raw); diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index 175004ce44b2..51a95239fe06 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -87,11 +87,19 @@ INSTALL_SCRIPT = ${INSTALL} -m 644 # to something more interesting, like "arm-linux-". If you want # to compile vs uClibc, that can be done here as well. CROSS ?= #/usr/i386-linux-uclibc/usr/bin/i386-uclibc- +ifneq ($(CROSS), ) +CC = $(CROSS)gcc +LD = $(CROSS)gcc +AR = $(CROSS)ar +STRIP = $(CROSS)strip +RANLIB = $(CROSS)ranlib +else CC ?= $(CROSS)gcc LD ?= $(CROSS)gcc AR ?= $(CROSS)ar STRIP ?= $(CROSS)strip RANLIB ?= $(CROSS)ranlib +endif HOSTCC = gcc MKDIR = mkdir diff --git a/tools/power/cpupower/bindings/python/Makefile b/tools/power/cpupower/bindings/python/Makefile index e1ebb1d60cd4..741f21477432 100644 --- a/tools/power/cpupower/bindings/python/Makefile +++ b/tools/power/cpupower/bindings/python/Makefile @@ -11,6 +11,7 @@ HAVE_PYCONFIG := $(shell if which python-config >/dev/null 2>&1; then echo 1; el LIB_DIR := ../../lib PY_INCLUDE = $(firstword $(shell python-config --includes)) OBJECTS_LIB = $(wildcard $(LIB_DIR)/*.o) +INSTALL_DIR = $(shell python3 -c "import site; print(site.getsitepackages()[0])") all: _raw_pylibcpupower.so @@ -28,6 +29,15 @@ else ifeq ($(HAVE_PYCONFIG),0) endif swig -python raw_pylibcpupower.swg +# Only installs the Python bindings +install: _raw_pylibcpupower.so + install -D _raw_pylibcpupower.so $(INSTALL_DIR)/_raw_pylibcpupower.so + install -D raw_pylibcpupower.py $(INSTALL_DIR)/raw_pylibcpupower.py + +uninstall: + rm -f $(INSTALL_DIR)/_raw_pylibcpupower.so + rm -f $(INSTALL_DIR)/raw_pylibcpupower.py + # Will only clean the bindings folder; will not clean the actual cpupower folder clean: rm -f raw_pylibcpupower.py raw_pylibcpupower_wrap.c raw_pylibcpupower_wrap.o _raw_pylibcpupower.so diff --git a/tools/power/cpupower/bindings/python/README b/tools/power/cpupower/bindings/python/README index 0a4bb2581e8a..952e2e02fd32 100644 --- a/tools/power/cpupower/bindings/python/README +++ b/tools/power/cpupower/bindings/python/README @@ -48,6 +48,31 @@ To run the test script: $ python test_raw_pylibcpupower.py +developing/using the bindings directly +-------------------------------------- + +You need to add the Python bindings directory to your $PYTHONPATH. + +You would set the path in the Bash terminal or in the Bash profile: + +PYTHONPATH=~/linux/tools/power/cpupower/bindings/python:$PYTHONPATH + +This allows you to set a specific repo of the bindings to use. + + +installing/uninstalling +----------------------- + +Python uses a system specific site-packages folder to look up modules to import +by default. You do not need to install cpupower to use the SWIG bindings. + +You can install and uninstall the bindings to the site-packages with: + +sudo make install + +sudo make uninstall + + credits ------- diff --git a/tools/power/cpupower/bindings/python/raw_pylibcpupower.swg b/tools/power/cpupower/bindings/python/raw_pylibcpupower.swg index 96556d87a745..d82af6fa93c3 100644 --- a/tools/power/cpupower/bindings/python/raw_pylibcpupower.swg +++ b/tools/power/cpupower/bindings/python/raw_pylibcpupower.swg @@ -134,6 +134,9 @@ void cpufreq_put_stats(struct cpufreq_stats *stats); unsigned long cpufreq_get_transitions(unsigned int cpu); +char *cpufreq_get_energy_performance_preference(unsigned int cpu); +void cpufreq_put_energy_performance_preference(char *ptr); + int cpufreq_set_policy(unsigned int cpu, struct cpufreq_policy *policy); int cpufreq_modify_policy_min(unsigned int cpu, unsigned long min_freq); @@ -160,6 +163,8 @@ int cpuidle_state_disable(unsigned int cpu, unsigned int idlestate, unsigned int disable); unsigned long cpuidle_state_latency(unsigned int cpu, unsigned int idlestate); +unsigned long cpuidle_state_residency(unsigned int cpu, + unsigned int idlestate); unsigned long cpuidle_state_usage(unsigned int cpu, unsigned int idlestate); unsigned long long cpuidle_state_time(unsigned int cpu, diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c index 1516d23c17c9..8dda3db2dff0 100644 --- a/tools/power/cpupower/lib/cpufreq.c +++ b/tools/power/cpupower/lib/cpufreq.c @@ -102,6 +102,10 @@ unsigned long cpufreq_get_sysfs_value_from_table(unsigned int cpu, if (len == 0) return 0; + if (!strcmp(linebuf, "enabled\n")) + return 1; + if (!strcmp(linebuf, "disabled\n")) + return 0; value = strtoul(linebuf, &endp, 0); if (endp == linebuf || errno == ERANGE) @@ -123,12 +127,14 @@ static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu, enum cpufreq_string { SCALING_DRIVER, SCALING_GOVERNOR, + ENERGY_PERFORMANCE_PREFERENCE, MAX_CPUFREQ_STRING_FILES }; static const char *cpufreq_string_files[MAX_CPUFREQ_STRING_FILES] = { [SCALING_DRIVER] = "scaling_driver", [SCALING_GOVERNOR] = "scaling_governor", + [ENERGY_PERFORMANCE_PREFERENCE] = "energy_performance_preference", }; @@ -203,6 +209,18 @@ unsigned long cpufreq_get_transition_latency(unsigned int cpu) return sysfs_cpufreq_get_one_value(cpu, CPUINFO_LATENCY); } +char *cpufreq_get_energy_performance_preference(unsigned int cpu) +{ + return sysfs_cpufreq_get_one_string(cpu, ENERGY_PERFORMANCE_PREFERENCE); +} + +void cpufreq_put_energy_performance_preference(char *ptr) +{ + if (!ptr) + return; + free(ptr); +} + int cpufreq_get_hardware_limits(unsigned int cpu, unsigned long *min, unsigned long *max) diff --git a/tools/power/cpupower/lib/cpufreq.h b/tools/power/cpupower/lib/cpufreq.h index 2f3c84035806..bfc617311ebd 100644 --- a/tools/power/cpupower/lib/cpufreq.h +++ b/tools/power/cpupower/lib/cpufreq.h @@ -68,6 +68,14 @@ unsigned long cpufreq_get_freq_hardware(unsigned int cpu); unsigned long cpufreq_get_transition_latency(unsigned int cpu); +/* determine energy performance preference + * + * returns NULL on failure, else the string that represents the energy performance + * preference requested. + */ +char *cpufreq_get_energy_performance_preference(unsigned int cpu); +void cpufreq_put_energy_performance_preference(char *ptr); + /* determine hardware CPU frequency limits * * These may be limited further by thermal, energy or other diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index c96b77365c63..fc750e127404 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -120,7 +120,6 @@ static void print_duration(unsigned long duration) } else printf("%lu ns", duration); } - return; } static int get_boost_mode_x86(unsigned int cpu) @@ -255,7 +254,12 @@ static int get_freq_kernel(unsigned int cpu, unsigned int human) static int get_freq_hardware(unsigned int cpu, unsigned int human) { - unsigned long freq = cpufreq_get_freq_hardware(cpu); + unsigned long freq; + + if (cpupower_cpu_info.caps & CPUPOWER_CAP_APERF) + return -EINVAL; + + freq = cpufreq_get_freq_hardware(cpu); printf(_(" current CPU frequency: ")); if (!freq) { printf("Unable to call hardware\n"); @@ -418,12 +422,32 @@ static int get_freq_stats(unsigned int cpu, unsigned int human) return 0; } +/* --epp / -z */ + +static int get_epp(unsigned int cpu, bool interactive) +{ + char *epp; + + epp = cpufreq_get_energy_performance_preference(cpu); + if (!epp) + return -EINVAL; + if (interactive) + printf(_(" energy performance preference: %s\n"), epp); + + cpufreq_put_energy_performance_preference(epp); + + return 0; +} + /* --latency / -y */ static int get_latency(unsigned int cpu, unsigned int human) { unsigned long latency = cpufreq_get_transition_latency(cpu); + if (!get_epp(cpu, false)) + return -EINVAL; + printf(_(" maximum transition latency: ")); if (!latency || latency == UINT_MAX) { printf(_(" Cannot determine or is not supported.\n")); @@ -457,6 +481,7 @@ static void debug_output_one(unsigned int cpu) get_related_cpus(cpu); get_affected_cpus(cpu); get_latency(cpu, 1); + get_epp(cpu, true); get_hardware_limits(cpu, 1); freqs = cpufreq_get_available_frequencies(cpu); @@ -497,6 +522,7 @@ static struct option info_opts[] = { {"human", no_argument, NULL, 'm'}, {"no-rounding", no_argument, NULL, 'n'}, {"performance", no_argument, NULL, 'c'}, + {"epp", no_argument, NULL, 'z'}, { }, }; @@ -510,7 +536,7 @@ int cmd_freq_info(int argc, char **argv) int output_param = 0; do { - ret = getopt_long(argc, argv, "oefwldpgrasmybnc", info_opts, + ret = getopt_long(argc, argv, "oefwldpgrasmybncz", info_opts, NULL); switch (ret) { case '?': @@ -534,6 +560,7 @@ int cmd_freq_info(int argc, char **argv) case 's': case 'y': case 'c': + case 'z': if (output_param) { output_param = -1; cont = 0; @@ -643,6 +670,9 @@ int cmd_freq_info(int argc, char **argv) case 'c': ret = get_perf_cap(cpu); break; + case 'z': + ret = get_epp(cpu, true); + break; } if (ret) return ret; diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c index 0a56e22240fc..795562e879de 100644 --- a/tools/power/cpupower/utils/helpers/amd.c +++ b/tools/power/cpupower/utils/helpers/amd.c @@ -177,6 +177,8 @@ enum amd_pstate_value { AMD_PSTATE_HIGHEST_PERF, AMD_PSTATE_MAX_FREQ, AMD_PSTATE_LOWEST_NONLINEAR_FREQ, + AMD_PSTATE_HW_PREFCORE, + AMD_PSTATE_PREFCORE_RANKING, MAX_AMD_PSTATE_VALUE_READ_FILES, }; @@ -184,6 +186,8 @@ static const char *amd_pstate_value_files[MAX_AMD_PSTATE_VALUE_READ_FILES] = { [AMD_PSTATE_HIGHEST_PERF] = "amd_pstate_highest_perf", [AMD_PSTATE_MAX_FREQ] = "amd_pstate_max_freq", [AMD_PSTATE_LOWEST_NONLINEAR_FREQ] = "amd_pstate_lowest_nonlinear_freq", + [AMD_PSTATE_HW_PREFCORE] = "amd_pstate_hw_prefcore", + [AMD_PSTATE_PREFCORE_RANKING] = "amd_pstate_prefcore_ranking", }; static unsigned long amd_pstate_get_data(unsigned int cpu, @@ -215,7 +219,9 @@ void amd_pstate_boost_init(unsigned int cpu, int *support, int *active) void amd_pstate_show_perf_and_freq(unsigned int cpu, int no_rounding) { - printf(_(" AMD PSTATE Highest Performance: %lu. Maximum Frequency: "), + + printf(_(" amd-pstate limits:\n")); + printf(_(" Highest Performance: %lu. Maximum Frequency: "), amd_pstate_get_data(cpu, AMD_PSTATE_HIGHEST_PERF)); /* * If boost isn't active, the cpuinfo_max doesn't indicate real max @@ -224,22 +230,26 @@ void amd_pstate_show_perf_and_freq(unsigned int cpu, int no_rounding) print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_MAX_FREQ), no_rounding); printf(".\n"); - printf(_(" AMD PSTATE Nominal Performance: %lu. Nominal Frequency: "), + printf(_(" Nominal Performance: %lu. Nominal Frequency: "), acpi_cppc_get_data(cpu, NOMINAL_PERF)); print_speed(acpi_cppc_get_data(cpu, NOMINAL_FREQ) * 1000, no_rounding); printf(".\n"); - printf(_(" AMD PSTATE Lowest Non-linear Performance: %lu. Lowest Non-linear Frequency: "), + printf(_(" Lowest Non-linear Performance: %lu. Lowest Non-linear Frequency: "), acpi_cppc_get_data(cpu, LOWEST_NONLINEAR_PERF)); print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_LOWEST_NONLINEAR_FREQ), no_rounding); printf(".\n"); - printf(_(" AMD PSTATE Lowest Performance: %lu. Lowest Frequency: "), + printf(_(" Lowest Performance: %lu. Lowest Frequency: "), acpi_cppc_get_data(cpu, LOWEST_PERF)); print_speed(acpi_cppc_get_data(cpu, LOWEST_FREQ) * 1000, no_rounding); printf(".\n"); + + printf(_(" Preferred Core Support: %lu. Preferred Core Ranking: %lu.\n"), + amd_pstate_get_data(cpu, AMD_PSTATE_HW_PREFCORE), + amd_pstate_get_data(cpu, AMD_PSTATE_PREFCORE_RANKING)); } /* AMD P-State Helper Functions ************************************/ diff --git a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c index 55e55b6b42f9..f5a2a326b1b7 100644 --- a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c @@ -117,7 +117,7 @@ static int hsw_ext_start(void) for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - hsw_ext_get_count(num, &val, cpu); + is_valid[cpu] = !hsw_ext_get_count(num, &val, cpu); previous_count[num][cpu] = val; } } @@ -134,7 +134,7 @@ static int hsw_ext_stop(void) for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - is_valid[cpu] = !hsw_ext_get_count(num, &val, cpu); + is_valid[cpu] |= !hsw_ext_get_count(num, &val, cpu); current_count[num][cpu] = val; } } diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index ae6af354a81d..73b6b10cbdd2 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -33,7 +33,7 @@ static int mperf_get_count_percent(unsigned int self_id, double *percent, unsigned int cpu); static int mperf_get_count_freq(unsigned int id, unsigned long long *count, unsigned int cpu); -static struct timespec time_start, time_end; +static struct timespec *time_start, *time_end; static cstate_t mperf_cstates[MPERF_CSTATE_COUNT] = { { @@ -148,7 +148,7 @@ static int mperf_measure_stats(unsigned int cpu) ret = get_aperf_mperf(cpu, &aval, &mval); aperf_current_count[cpu] = aval; mperf_current_count[cpu] = mval; - is_valid[cpu] = !ret; + is_valid[cpu] |= !ret; return 0; } @@ -174,7 +174,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); } else if (max_freq_mode == MAX_FREQ_SYSFS) { - timediff = max_frequency * timespec_diff_us(time_start, time_end); + timediff = max_frequency * timespec_diff_us(time_start[cpu], time_end[cpu]); *percent = 100.0 * mperf_diff / timediff; dprint("%s: MAXFREQ - mperf_diff: %llu, time_diff: %llu\n", mperf_cstates[id].name, mperf_diff, timediff); @@ -207,7 +207,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; - time_diff = timespec_diff_us(time_start, time_end); + time_diff = timespec_diff_us(time_start[cpu], time_end[cpu]); max_frequency = tsc_diff / time_diff; } @@ -226,9 +226,8 @@ static int mperf_start(void) { int cpu; - clock_gettime(CLOCK_REALTIME, &time_start); - for (cpu = 0; cpu < cpu_count; cpu++) { + clock_gettime(CLOCK_REALTIME, &time_start[cpu]); mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); } @@ -243,9 +242,9 @@ static int mperf_stop(void) for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); mperf_get_tsc(&tsc_at_measure_end[cpu]); + clock_gettime(CLOCK_REALTIME, &time_end[cpu]); } - clock_gettime(CLOCK_REALTIME, &time_end); return 0; } @@ -349,6 +348,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); + time_start = calloc(cpu_count, sizeof(struct timespec)); + time_end = calloc(cpu_count, sizeof(struct timespec)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -361,6 +362,8 @@ void mperf_unregister(void) free(aperf_current_count); free(tsc_at_measure_start); free(tsc_at_measure_end); + free(time_start); + free(time_end); free(is_valid); } diff --git a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c index 16eaf006f61f..6b1733782ffa 100644 --- a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c @@ -151,7 +151,7 @@ static int nhm_stop(void) for (num = 0; num < NHM_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - is_valid[cpu] = !nhm_get_count(num, &val, cpu); + is_valid[cpu] |= !nhm_get_count(num, &val, cpu); current_count[num][cpu] = val; } } diff --git a/tools/power/cpupower/utils/idle_monitor/snb_idle.c b/tools/power/cpupower/utils/idle_monitor/snb_idle.c index 811d63ab17a7..5969b88a85b4 100644 --- a/tools/power/cpupower/utils/idle_monitor/snb_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/snb_idle.c @@ -115,7 +115,7 @@ static int snb_start(void) for (num = 0; num < SNB_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - snb_get_count(num, &val, cpu); + is_valid[cpu] = !snb_get_count(num, &val, cpu); previous_count[num][cpu] = val; } } @@ -132,7 +132,7 @@ static int snb_stop(void) for (num = 0; num < SNB_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { - is_valid[cpu] = !snb_get_count(num, &val, cpu); + is_valid[cpu] |= !snb_get_count(num, &val, cpu); current_count[num][cpu] = val; } } diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 5127be34869e..fadfb02b8611 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -16,7 +16,7 @@ struct process_cmd_struct { int arg; }; -static const char *version_str = "v1.20"; +static const char *version_str = "v1.21"; static const int supported_api_ver = 3; static struct isst_if_platform_info isst_platform_info; diff --git a/tools/power/x86/intel-speed-select/isst-core-tpmi.c b/tools/power/x86/intel-speed-select/isst-core-tpmi.c index 32ea70c7dbd8..da53aaa27fc9 100644 --- a/tools/power/x86/intel-speed-select/isst-core-tpmi.c +++ b/tools/power/x86/intel-speed-select/isst-core-tpmi.c @@ -329,7 +329,7 @@ static int tpmi_get_get_trls(struct isst_id *id, int config_index, return 0; } -static int tpmi_get_get_trl(struct isst_id *id, int level, int config_index, +static int tpmi_get_get_trl(struct isst_id *id, int config_index, int level, int *trl) { struct isst_pkg_ctdp_level_info ctdp_level; diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index a7f7ed01421c..99bf905ade81 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -136,7 +136,7 @@ displays the statistics gathered since it was forked. The system configuration dump (if --quiet is not used) is followed by statistics. The first row of the statistics labels the content of each column (below). The second row of statistics is the system summary line. The system summary line has a '-' in the columns for the Package, Core, and CPU. The contents of the system summary line depends on the type of column. Columns that count items (eg. IRQ) show the sum across all CPUs in the system. Columns that show a percentage show the average across all CPUs in the system. Columns that dump raw MSR values simply show 0 in the summary. After the system summary row, each row describes a specific Package/Core/CPU. Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system. .SH COLUMN DESCRIPTIONS .PP -\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any. This counter is disabled by default, and is enabled with "--enable usec", or --debug. On the summary row, usec refers to the total elapsed time to collect the counters on all cpus. +\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any. This counter is disabled by default, and is enabled with "--enable usec", or --debug. On the summary row, usec refers to the total elapsed time to snapshot the procfs/sysfs and collect the counters on all cpus. .PP \fBTime_Of_Day_Seconds\fP For each CPU, the gettimeofday(2) value (seconds.subsec since Epoch) when the counters ending the measurement interval were collected. This column is disabled by default, and can be enabled with "--enable Time_Of_Day_Seconds" or "--debug". On the summary row, Time_Of_Day_Seconds refers to the timestamp following collection of counters on the last CPU. .PP @@ -190,7 +190,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors. .PP -\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). Disabled by default. Enable with --enable SysWatt. +\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). .PP \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary. .PP @@ -516,14 +516,40 @@ that they count at TSC rate, which is true on all processors tested to date. Volume 3B: System Programming Guide" https://www.intel.com/products/processor/manuals/ +.SH RUN THE LATEST VERSION +If turbostat complains that it doesn't recognize your processor, +please try the latest version. + +The latest version of turbostat does not require the latest version of the Linux kernel. +However, some features, such as perf(1) counters, do require kernel support. + +The latest turbostat release is available in the upstream Linux Kernel source tree. +eg. "git pull https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git" +and run make in tools/power/x86/turbostat/. + +n.b. "make install" will update your system manually, but a distro update may subsequently downgrade your turbostat to an older version. +For this reason, manually installing to /usr/local/bin may be what you want. + +Note that turbostat/Makefile has a "make snapshot" target, which will create a tar file +that can build without a local kernel source tree. + +If the upstream version isn't new enough, the development tree can be found here: +"git pull https://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat" + +If the development tree doesn't work, please contact the author via chat, +or via email with the word "turbostat" on the Subject line. + .SH FILES .ta .nf +/sys/bus/event_source/devices/ /dev/cpu/*/msr +/sys/class/intel_pmt/ +/sys/devices/system/cpu/ .fi .SH "SEE ALSO" -msr(4), vmstat(8) +perf(1), msr(4), vmstat(8) .PP .SH AUTHOR .nf diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 58a487c225a7..8d5011a0bf60 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -3,7 +3,7 @@ * turbostat -- show CPU frequency and C-state residency * on modern Intel and AMD processors. * - * Copyright (c) 2024 Intel Corporation. + * Copyright (c) 2025 Intel Corporation. * Len Brown <len.brown@intel.com> */ @@ -95,6 +95,8 @@ #define INTEL_ECORE_TYPE 0x20 #define INTEL_PCORE_TYPE 0x40 +#define ROUND_UP_TO_PAGE_SIZE(n) (((n) + 0x1000UL-1UL) & ~(0x1000UL-1UL)) + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC, COUNTER_K2M }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT, FORMAT_AVERAGE }; @@ -202,6 +204,8 @@ struct msr_counter bic[] = { { 0x0, "Die%c6", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "SysWatt", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "Sys_J", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "NMI", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "CPU%c1e", NULL, 0, 0, 0, NULL, 0 }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -266,14 +270,16 @@ struct msr_counter bic[] = { #define BIC_Diec6 (1ULL << 58) #define BIC_SysWatt (1ULL << 59) #define BIC_Sys_J (1ULL << 60) +#define BIC_NMI (1ULL << 61) +#define BIC_CPU_c1e (1ULL << 62) -#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) -#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) +#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die) +#define BIC_THERMAL_PWR (BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__ | BIC_SysWatt) #define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ) -#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) -#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) +#define BIC_IDLE (BIC_Busy | BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) +#define BIC_OTHER (BIC_IRQ | BIC_NMI | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) -#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC | BIC_SysWatt | BIC_Sys_J) +#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; @@ -326,6 +332,7 @@ unsigned int rapl_joules; unsigned int summary_only; unsigned int list_header_only; unsigned int dump_only; +unsigned int force_load; unsigned int has_aperf; unsigned int has_aperf_access; unsigned int has_epb; @@ -353,7 +360,7 @@ unsigned long long cpuidle_cur_sys_lpi_us; unsigned int tj_max; unsigned int tj_max_override; double rapl_power_units, rapl_time_units; -double rapl_dram_energy_units, rapl_energy_units; +double rapl_dram_energy_units, rapl_energy_units, rapl_psys_energy_units; double rapl_joule_counter_range; unsigned int crystal_hz; unsigned long long tsc_hz; @@ -365,6 +372,9 @@ unsigned int has_hwp_activity_window; /* IA32_HWP_REQUEST[bits 41:32] */ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ unsigned int first_counter_read = 1; + +static struct timeval procsysfs_tv_begin; + int ignore_stdin; bool no_msr; bool no_perf; @@ -419,6 +429,7 @@ struct platform_features { bool has_per_core_rapl; /* Indicates cores energy collection is per-core, not per-package. AMD specific for now */ bool has_rapl_divisor; /* Divisor for Energy unit raw value from MSR_RAPL_POWER_UNIT */ bool has_fixed_rapl_unit; /* Fixed Energy Unit used for DRAM RAPL Domain */ + bool has_fixed_rapl_psys_unit; /* Fixed Energy Unit used for PSYS RAPL Domain */ int rapl_quirk_tdp; /* Hardcoded TDP value when cannot be retrieved from hardware */ int tcc_offset_bits; /* TCC Offset bits in MSR_IA32_TEMPERATURE_TARGET */ bool enable_tsc_tweak; /* Use CPU Base freq instead of TSC freq for aperf/mperf counter */ @@ -819,6 +830,7 @@ static const struct platform_features spr_features = { .has_msr_core_c1_res = 1, .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, + .has_fixed_rapl_psys_unit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, }; @@ -1024,6 +1036,7 @@ static const struct platform_data turbostat_pdata[] = { { INTEL_ARROWLAKE_U, &adl_features }, { INTEL_ARROWLAKE, &adl_features }, { INTEL_LUNARLAKE_M, &lnl_features }, + { INTEL_PANTHERLAKE_L, &lnl_features }, { INTEL_ATOM_SILVERMONT, &slv_features }, { INTEL_ATOM_SILVERMONT_D, &slvd_features }, { INTEL_ATOM_AIRMONT, &amt_features }, @@ -1036,6 +1049,7 @@ static const struct platform_data turbostat_pdata[] = { { INTEL_ATOM_GRACEMONT, &adl_features }, { INTEL_ATOM_CRESTMONT_X, &srf_features }, { INTEL_ATOM_CRESTMONT, &grr_features }, + { INTEL_ATOM_DARKMONT_X, &srf_features }, { INTEL_XEON_PHI_KNL, &knl_features }, { INTEL_XEON_PHI_KNM, &knl_features }, /* @@ -1054,9 +1068,10 @@ void probe_platform_features(unsigned int family, unsigned int model) { int i; - platform = &default_features; if (authentic_amd || hygon_genuine) { + /* fallback to default features on unsupported models */ + force_load++; if (max_extended_level >= 0x80000007) { unsigned int eax, ebx, ecx, edx; @@ -1065,11 +1080,11 @@ void probe_platform_features(unsigned int family, unsigned int model) if ((edx & (1 << 14)) && family >= 0x17) platform = &amd_features_with_rapl; } - return; + goto end; } if (!genuine_intel) - return; + goto end; for (i = 0; turbostat_pdata[i].features; i++) { if (VFM_FAMILY(turbostat_pdata[i].vfm) == family && VFM_MODEL(turbostat_pdata[i].vfm) == model) { @@ -1077,6 +1092,19 @@ void probe_platform_features(unsigned int family, unsigned int model) return; } } + +end: + if (force_load && !platform) { + fprintf(outf, "Forced to run on unsupported platform!\n"); + platform = &default_features; + } + + if (platform) + return; + + fprintf(stderr, "Unsupported platform detected.\n" + "\tSee RUN THE LATEST VERSION on turbostat(8)\n"); + exit(1); } /* Model specific support End */ @@ -1094,8 +1122,8 @@ int backwards_count; char *progname; #define CPU_SUBSET_MAXCPUS 1024 /* need to use before probe... */ -cpu_set_t *cpu_present_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset; -size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size; +cpu_set_t *cpu_present_set, *cpu_possible_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset; +size_t cpu_present_setsize, cpu_possible_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size; #define MAX_ADDED_THREAD_COUNTERS 24 #define MAX_ADDED_CORE_COUNTERS 8 #define MAX_ADDED_PACKAGE_COUNTERS 16 @@ -1271,7 +1299,7 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr = MSR_PLATFORM_ENERGY_STATUS, .msr_mask = 0x00000000FFFFFFFF, .msr_shift = 0, - .platform_rapl_msr_scale = &rapl_energy_units, + .platform_rapl_msr_scale = &rapl_psys_energy_units, .rci_index = RAPL_RCI_INDEX_ENERGY_PLATFORM, .bic = BIC_SysWatt | BIC_Sys_J, .compat_scale = 1.0, @@ -1510,6 +1538,17 @@ static struct msr_counter_arch_info msr_counter_arch_infos[] = { #define PMT_COUNTER_MTL_DC6_LSB 0 #define PMT_COUNTER_MTL_DC6_MSB 63 #define PMT_MTL_DC6_GUID 0x1a067102 +#define PMT_MTL_DC6_SEQ 0 + +#define PMT_COUNTER_CWF_MC1E_OFFSET_BASE 20936 +#define PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT 24 +#define PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE 12 +#define PMT_COUNTER_CWF_CPUS_PER_MODULE 4 +#define PMT_COUNTER_CWF_MC1E_LSB 0 +#define PMT_COUNTER_CWF_MC1E_MSB 63 +#define PMT_CWF_MC1E_GUID 0x14421519 + +unsigned long long tcore_clock_freq_hz = 800000000; #define PMT_COUNTER_NAME_SIZE_BYTES 16 #define PMT_COUNTER_TYPE_NAME_SIZE_BYTES 32 @@ -1533,6 +1572,7 @@ struct pmt_mmio { enum pmt_datatype { PMT_TYPE_RAW, PMT_TYPE_XTAL_TIME, + PMT_TYPE_TCORE_CLOCK, }; struct pmt_domain_info { @@ -1562,6 +1602,93 @@ struct pmt_counter { struct pmt_domain_info *domains; }; +/* + * PMT telemetry directory iterator. + * Used to iterate telemetry files in sysfs in correct order. + */ +struct pmt_diriter_t { + DIR *dir; + struct dirent **namelist; + unsigned int num_names; + unsigned int current_name_idx; +}; + +int pmt_telemdir_filter(const struct dirent *e) +{ + unsigned int dummy; + + return sscanf(e->d_name, "telem%u", &dummy); +} + +int pmt_telemdir_sort(const struct dirent **a, const struct dirent **b) +{ + unsigned int aidx = 0, bidx = 0; + + sscanf((*a)->d_name, "telem%u", &aidx); + sscanf((*b)->d_name, "telem%u", &bidx); + + return aidx >= bidx; +} + +const struct dirent *pmt_diriter_next(struct pmt_diriter_t *iter) +{ + const struct dirent *ret = NULL; + + if (!iter->dir) + return NULL; + + if (iter->current_name_idx >= iter->num_names) + return NULL; + + ret = iter->namelist[iter->current_name_idx]; + ++iter->current_name_idx; + + return ret; +} + +const struct dirent *pmt_diriter_begin(struct pmt_diriter_t *iter, const char *pmt_root_path) +{ + int num_names = iter->num_names; + + if (!iter->dir) { + iter->dir = opendir(pmt_root_path); + if (iter->dir == NULL) + return NULL; + + num_names = scandir(pmt_root_path, &iter->namelist, pmt_telemdir_filter, pmt_telemdir_sort); + if (num_names == -1) + return NULL; + } + + iter->current_name_idx = 0; + iter->num_names = num_names; + + return pmt_diriter_next(iter); +} + +void pmt_diriter_init(struct pmt_diriter_t *iter) +{ + memset(iter, 0, sizeof(*iter)); +} + +void pmt_diriter_remove(struct pmt_diriter_t *iter) +{ + if (iter->namelist) { + for (unsigned int i = 0; i < iter->num_names; i++) { + free(iter->namelist[i]); + iter->namelist[i] = NULL; + } + } + + free(iter->namelist); + iter->namelist = NULL; + iter->num_names = 0; + iter->current_name_idx = 0; + + closedir(iter->dir); + iter->dir = NULL; +} + unsigned int pmt_counter_get_width(const struct pmt_counter *p) { return (p->msb - p->lsb) + 1; @@ -1611,6 +1738,7 @@ struct thread_data { unsigned long long c1; unsigned long long instr_count; unsigned long long irq_count; + unsigned long long nmi_count; unsigned int smi_count; unsigned int cpu_id; unsigned int apic_id; @@ -1917,6 +2045,7 @@ struct timeval tv_even, tv_odd, tv_delta; int *irq_column_2_cpu; /* /proc/interrupts column numbers */ int *irqs_per_cpu; /* indexed by cpu_num */ +int *nmi_per_cpu; /* indexed by cpu_num */ void setup_all_buffers(bool startup); @@ -1944,6 +2073,8 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk { int retval, pkg_no, core_no, thread_no, node_no; + retval = 0; + for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) { for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { @@ -1959,14 +2090,12 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk c = GET_CORE(core_base, core_no, node_no, pkg_no); p = GET_PKG(pkg_base, pkg_no); - retval = func(t, c, p); - if (retval) - return retval; + retval |= func(t, c, p); } } } } - return 0; + return retval; } int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p) @@ -2085,13 +2214,17 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) int probe_msr(int cpu, off_t offset) { ssize_t retval; - unsigned long long dummy; + unsigned long long value; assert(!no_msr); - retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset); + retval = pread(get_msr_fd(cpu), &value, sizeof(value), offset); - if (retval != sizeof(dummy)) + /* + * Expect MSRs to accumulate some non-zero value since the system was powered on. + * Treat zero as a read failure. + */ + if (retval != sizeof(value) || value == 0) return 1; return 0; @@ -2135,41 +2268,54 @@ void help(void) "when COMMAND completes.\n" "If no COMMAND is specified, turbostat wakes every 5-seconds\n" "to print statistics, until interrupted.\n" - " -a, --add add a counter\n" + " -a, --add counter\n" + " add a counter\n" " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" " eg. --add perf/cstate_pkg/c2-residency,package,delta,percent,perfPC2\n" " eg. --add pmt,name=XTAL,type=raw,domain=package0,offset=0,lsb=0,msb=63,guid=0x1a067102\n" - " -c, --cpu cpu-set limit output to summary plus cpu-set:\n" + " -c, --cpu cpu-set\n" + " limit output to summary plus cpu-set:\n" " {core | package | j,k,l..m,n-p }\n" - " -d, --debug displays usec, Time_Of_Day_Seconds and more debugging\n" + " -d, --debug\n" + " displays usec, Time_Of_Day_Seconds and more debugging\n" " debug messages are printed to stderr\n" - " -D, --Dump displays the raw counter values\n" - " -e, --enable [all | column]\n" + " -D, --Dump\n" + " displays the raw counter values\n" + " -e, --enable [all | column]\n" " shows all or the specified disabled column\n" - " -H, --hide [column|column,column,...]\n" + " -f, --force\n" + " force load turbostat with minimum default features on unsupported platforms.\n" + " -H, --hide [column | column,column,...]\n" " hide the specified column(s)\n" " -i, --interval sec.subsec\n" - " Override default 5-second measurement interval\n" - " -J, --Joules displays energy in Joules instead of Watts\n" - " -l, --list list column headers only\n" - " -M, --no-msr Disable all uses of the MSR driver\n" - " -P, --no-perf Disable all uses of the perf API\n" + " override default 5-second measurement interval\n" + " -J, --Joules\n" + " displays energy in Joules instead of Watts\n" + " -l, --list\n" + " list column headers only\n" + " -M, --no-msr\n" + " disable all uses of the MSR driver\n" + " -P, --no-perf\n" + " disable all uses of the perf API\n" " -n, --num_iterations num\n" " number of the measurement iterations\n" " -N, --header_iterations num\n" " print header every num iterations\n" " -o, --out file\n" " create or truncate \"file\" for all output\n" - " -q, --quiet skip decoding system configuration header\n" - " -s, --show [column|column,column,...]\n" + " -q, --quiet\n" + " skip decoding system configuration header\n" + " -s, --show [column | column,column,...]\n" " show only the specified column(s)\n" " -S, --Summary\n" " limits output to 1-line system summary per interval\n" " -T, --TCC temperature\n" " sets the Thermal Control Circuit temperature in\n" " degrees Celsius\n" - " -h, --help print this help message\n" - " -v, --version print version information\n" "\n" "For more help, run \"man turbostat\"\n"); + " -h, --help\n" + " print this help message\n" + " -v, --version\n" + " print version information\n\nFor more help, run \"man turbostat\"\n"); } /* @@ -2289,6 +2435,12 @@ void print_header(char *delim) else outp += sprintf(outp, "%sIRQ", (printed++ ? delim : "")); } + if (DO_BIC(BIC_NMI)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s NMI", (printed++ ? delim : "")); + else + outp += sprintf(outp, "%sNMI", (printed++ ? delim : "")); + } if (DO_BIC(BIC_SMI)) outp += sprintf(outp, "%sSMI", (printed++ ? delim : "")); @@ -2335,6 +2487,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: + case PMT_TYPE_TCORE_CLOCK: outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2409,6 +2562,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: + case PMT_TYPE_TCORE_CLOCK: outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2540,6 +2694,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: + case PMT_TYPE_TCORE_CLOCK: outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2575,6 +2730,8 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p if (DO_BIC(BIC_IRQ)) outp += sprintf(outp, "IRQ: %lld\n", t->irq_count); + if (DO_BIC(BIC_NMI)) + outp += sprintf(outp, "IRQ: %lld\n", t->nmi_count); if (DO_BIC(BIC_SMI)) outp += sprintf(outp, "SMI: %d\n", t->smi_count); @@ -2794,6 +2951,14 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->irq_count); } + /* NMI */ + if (DO_BIC(BIC_NMI)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->nmi_count); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->nmi_count); + } + /* SMI */ if (DO_BIC(BIC_SMI)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->smi_count); @@ -2848,7 +3013,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) { const unsigned long value_raw = t->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + double value_converted; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2860,8 +3025,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: + value_converted = 100.0 * value_raw / crystal_hz / interval_float; outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; + + case PMT_TYPE_TCORE_CLOCK: + value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float; + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); } } @@ -2928,7 +3098,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) { const unsigned long value_raw = c->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + double value_converted; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2940,8 +3110,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: + value_converted = 100.0 * value_raw / crystal_hz / interval_float; outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; + + case PMT_TYPE_TCORE_CLOCK: + value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float; + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); } } @@ -3126,7 +3301,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) { const unsigned long value_raw = p->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + double value_converted; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -3138,8 +3313,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: + value_converted = 100.0 * value_raw / crystal_hz / interval_float; outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; + + case PMT_TYPE_TCORE_CLOCK: + value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float; + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); } } @@ -3409,6 +3589,9 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d if (DO_BIC(BIC_IRQ)) old->irq_count = new->irq_count - old->irq_count; + if (DO_BIC(BIC_NMI)) + old->nmi_count = new->nmi_count - old->nmi_count; + if (DO_BIC(BIC_SMI)) old->smi_count = new->smi_count - old->smi_count; @@ -3447,12 +3630,10 @@ int delta_cpu(struct thread_data *t, struct core_data *c, /* always calculate thread delta */ retval = delta_thread(t, t2, c2); /* c2 is core delta */ - if (retval) - return retval; /* calculate package delta only for 1st core in package */ if (is_cpu_first_core_in_package(t, c, p)) - retval = delta_package(p, p2); + retval |= delta_package(p, p2); return retval; } @@ -3489,6 +3670,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data t->instr_count = 0; t->irq_count = 0; + t->nmi_count = 0; t->smi_count = 0; c->c3 = 0; @@ -3580,7 +3762,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) /* remember first tv_begin */ if (average.threads.tv_begin.tv_sec == 0) - average.threads.tv_begin = t->tv_begin; + average.threads.tv_begin = procsysfs_tv_begin; /* remember last tv_end */ average.threads.tv_end = t->tv_end; @@ -3593,6 +3775,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.threads.instr_count += t->instr_count; average.threads.irq_count += t->irq_count; + average.threads.nmi_count += t->nmi_count; average.threads.smi_count += t->smi_count; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { @@ -3734,6 +3917,9 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data if (average.threads.irq_count > 9999999) sums_need_wide_columns = 1; + if (average.threads.nmi_count > 9999999) + sums_need_wide_columns = 1; + average.cores.c3 /= topo.allowed_cores; average.cores.c6 /= topo.allowed_cores; @@ -4546,7 +4732,8 @@ unsigned long pmt_gen_value_mask(unsigned int lsb, unsigned int msb) unsigned long pmt_read_counter(struct pmt_counter *ppmt, unsigned int domain_id) { - assert(domain_id < ppmt->num_domains); + if (domain_id >= ppmt->num_domains) + return 0; const unsigned long *pmmio = ppmt->domains[domain_id].pcounter; const unsigned long value = pmmio ? *pmmio : 0; @@ -4590,6 +4777,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (DO_BIC(BIC_IRQ)) t->irq_count = irqs_per_cpu[cpu]; + if (DO_BIC(BIC_NMI)) + t->nmi_count = nmi_per_cpu[cpu]; get_cstate_counters(cpu, t, c, p); @@ -5335,6 +5524,7 @@ void free_all_buffers(void) free(irq_column_2_cpu); free(irqs_per_cpu); + free(nmi_per_cpu); for (i = 0; i <= topo.max_cpu_num; ++i) { if (cpus[i].put_ids) @@ -5566,6 +5756,8 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, { int retval, pkg_no, node_no, core_no, thread_no; + retval = 0; + for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) { for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { @@ -5587,14 +5779,12 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, p = GET_PKG(pkg_base, pkg_no); p2 = GET_PKG(pkg_base2, pkg_no); - retval = func(t, c, p, t2, c2, p2); - if (retval) - return retval; + retval |= func(t, c, p, t2, c2, p2); } } } } - return 0; + return retval; } /* @@ -5791,31 +5981,37 @@ int snapshot_proc_interrupts(void) irq_column_2_cpu[column] = cpu_number; irqs_per_cpu[cpu_number] = 0; + nmi_per_cpu[cpu_number] = 0; } /* read /proc/interrupt count lines and sum up irqs per cpu */ while (1) { int column; char buf[64]; + int this_row_is_nmi = 0; - retval = fscanf(fp, " %s:", buf); /* flush irq# "N:" */ + retval = fscanf(fp, " %s:", buf); /* irq# "N:" */ if (retval != 1) break; + if (strncmp(buf, "NMI", strlen("NMI")) == 0) + this_row_is_nmi = 1; + /* read the count per cpu */ for (column = 0; column < topo.num_cpus; ++column) { int cpu_number, irq_count; retval = fscanf(fp, " %d", &irq_count); + if (retval != 1) break; cpu_number = irq_column_2_cpu[column]; irqs_per_cpu[cpu_number] += irq_count; - + if (this_row_is_nmi) + nmi_per_cpu[cpu_number] += irq_count; } - while (getc(fp) != '\n') ; /* flush interrupt description */ } @@ -5912,7 +6108,9 @@ int snapshot_sys_lpi_us(void) */ int snapshot_proc_sysfs_files(void) { - if (DO_BIC(BIC_IRQ)) + gettimeofday(&procsysfs_tv_begin, (struct timezone *)NULL); + + if (DO_BIC(BIC_IRQ) || DO_BIC(BIC_NMI)) if (snapshot_proc_interrupts()) return 1; @@ -7043,6 +7241,11 @@ void rapl_probe_intel(void) else rapl_dram_energy_units = rapl_energy_units; + if (platform->has_fixed_rapl_psys_unit) + rapl_psys_energy_units = 1.0; + else + rapl_psys_energy_units = rapl_energy_units; + time_unit = msr >> 16 & 0xF; if (time_unit == 0) time_unit = 0xA; @@ -8233,6 +8436,7 @@ void process_cpuid() aperf_mperf_multiplier = platform->need_perf_multiplier ? 1024 : 1; BIC_PRESENT(BIC_IRQ); + BIC_PRESENT(BIC_NMI); BIC_PRESENT(BIC_TSC_MHz); } @@ -8292,6 +8496,33 @@ int dir_filter(const struct dirent *dirp) return 0; } +char *possible_file = "/sys/devices/system/cpu/possible"; +char possible_buf[1024]; + +int initialize_cpu_possible_set(void) +{ + FILE *fp; + + fp = fopen(possible_file, "r"); + if (!fp) { + warn("open %s", possible_file); + return -1; + } + if (fread(possible_buf, sizeof(char), 1024, fp) == 0) { + warn("read %s", possible_file); + goto err; + } + if (parse_cpu_str(possible_buf, cpu_possible_set, cpu_possible_setsize)) { + warnx("%s: cpu str malformat %s\n", possible_file, cpu_effective_str); + goto err; + } + return 0; + +err: + fclose(fp); + return -1; +} + void topology_probe(bool startup) { int i; @@ -8323,6 +8554,16 @@ void topology_probe(bool startup) CPU_ZERO_S(cpu_present_setsize, cpu_present_set); for_all_proc_cpus(mark_cpu_present); + /* + * Allocate and initialize cpu_possible_set + */ + cpu_possible_set = CPU_ALLOC((topo.max_cpu_num + 1)); + if (cpu_possible_set == NULL) + err(3, "CPU_ALLOC"); + cpu_possible_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1)); + CPU_ZERO_S(cpu_possible_setsize, cpu_possible_set); + initialize_cpu_possible_set(); + /* * Allocate and initialize cpu_effective_set */ @@ -8583,7 +8824,11 @@ void allocate_irq_buffers(void) irqs_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int)); if (irqs_per_cpu == NULL) - err(-1, "calloc %d", topo.max_cpu_num + 1); + err(-1, "calloc %d IRQ", topo.max_cpu_num + 1); + + nmi_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int)); + if (nmi_per_cpu == NULL) + err(-1, "calloc %d NMI", topo.max_cpu_num + 1); } int update_topo(struct thread_data *t, struct core_data *c, struct pkg_data *p) @@ -8854,49 +9099,36 @@ int parse_telem_info_file(int fd_dir, const char *info_filename, const char *for struct pmt_mmio *pmt_mmio_open(unsigned int target_guid) { - DIR *dirp; - struct dirent *entry; + struct pmt_diriter_t pmt_iter; + const struct dirent *entry; struct stat st; - unsigned int telem_idx; int fd_telem_dir, fd_pmt; unsigned long guid, size, offset; size_t mmap_size; void *mmio; - struct pmt_mmio *ret = NULL; + struct pmt_mmio *head = NULL, *last = NULL; + struct pmt_mmio *new_pmt = NULL; if (stat(SYSFS_TELEM_PATH, &st) == -1) return NULL; - dirp = opendir(SYSFS_TELEM_PATH); - if (dirp == NULL) + pmt_diriter_init(&pmt_iter); + entry = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH); + if (!entry) { + pmt_diriter_remove(&pmt_iter); return NULL; + } - for (;;) { - entry = readdir(dirp); - - if (entry == NULL) + for ( ; entry != NULL; entry = pmt_diriter_next(&pmt_iter)) { + if (fstatat(dirfd(pmt_iter.dir), entry->d_name, &st, 0) == -1) break; - if (strcmp(entry->d_name, ".") == 0) - continue; - - if (strcmp(entry->d_name, "..") == 0) - continue; - - if (sscanf(entry->d_name, "telem%u", &telem_idx) != 1) - continue; - - if (fstatat(dirfd(dirp), entry->d_name, &st, 0) == -1) { - break; - } - if (!S_ISDIR(st.st_mode)) continue; - fd_telem_dir = openat(dirfd(dirp), entry->d_name, O_RDONLY); - if (fd_telem_dir == -1) { + fd_telem_dir = openat(dirfd(pmt_iter.dir), entry->d_name, O_RDONLY); + if (fd_telem_dir == -1) break; - } if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) { close(fd_telem_dir); @@ -8924,38 +9156,54 @@ struct pmt_mmio *pmt_mmio_open(unsigned int target_guid) if (fd_pmt == -1) goto loop_cleanup_and_break; - mmap_size = (size + 0x1000UL) & (~0x1000UL); + mmap_size = ROUND_UP_TO_PAGE_SIZE(size); mmio = mmap(0, mmap_size, PROT_READ, MAP_SHARED, fd_pmt, 0); if (mmio != MAP_FAILED) { - if (debug) fprintf(stderr, "%s: 0x%lx mmaped at: %p\n", __func__, guid, mmio); - ret = calloc(1, sizeof(*ret)); + new_pmt = calloc(1, sizeof(*new_pmt)); - if (!ret) { + if (!new_pmt) { fprintf(stderr, "%s: Failed to allocate pmt_mmio\n", __func__); exit(1); } - ret->guid = guid; - ret->mmio_base = mmio; - ret->pmt_offset = offset; - ret->size = size; + /* + * Create linked list of mmaped regions, + * but preserve the ordering from sysfs. + * Ordering is important for the user to + * use the seq=%u parameter when adding a counter. + */ + new_pmt->guid = guid; + new_pmt->mmio_base = mmio; + new_pmt->pmt_offset = offset; + new_pmt->size = size; + new_pmt->next = pmt_mmios; - ret->next = pmt_mmios; - pmt_mmios = ret; + if (last) + last->next = new_pmt; + else + head = new_pmt; + + last = new_pmt; } loop_cleanup_and_break: close(fd_pmt); close(fd_telem_dir); - break; } - closedir(dirp); + pmt_diriter_remove(&pmt_iter); - return ret; + /* + * If we found something, stick just + * created linked list to the front. + */ + if (head) + pmt_mmios = head; + + return head; } struct pmt_mmio *pmt_mmio_find(unsigned int guid) @@ -8992,7 +9240,7 @@ void *pmt_get_counter_pointer(struct pmt_mmio *pmmio, unsigned long counter_offs return ret; } -struct pmt_mmio *pmt_add_guid(unsigned int guid) +struct pmt_mmio *pmt_add_guid(unsigned int guid, unsigned int seq) { struct pmt_mmio *ret; @@ -9000,6 +9248,11 @@ struct pmt_mmio *pmt_add_guid(unsigned int guid) if (!ret) ret = pmt_mmio_open(guid); + while (ret && seq) { + ret = ret->next; + --seq; + } + return ret; } @@ -9046,7 +9299,7 @@ void pmt_counter_add_domain(struct pmt_counter *pcounter, unsigned long *pmmio, pcounter->domains[domain_id].pcounter = pmmio; } -int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, +int pmt_add_counter(unsigned int guid, unsigned int seq, const char *name, enum pmt_datatype type, unsigned int lsb, unsigned int msb, unsigned int offset, enum counter_scope scope, enum counter_format format, unsigned int domain_id, enum pmt_open_mode mode) { @@ -9066,10 +9319,10 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, exit(1); } - mmio = pmt_add_guid(guid); + mmio = pmt_add_guid(guid, seq); if (!mmio) { if (mode != PMT_OPEN_TRY) { - fprintf(stderr, "%s: failed to map PMT MMIO for guid %x\n", __func__, guid); + fprintf(stderr, "%s: failed to map PMT MMIO for guid %x, seq %u\n", __func__, guid, seq); exit(1); } @@ -9124,10 +9377,68 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, void pmt_init(void) { + int cpu_num; + unsigned long seq, offset, mod_num; + if (BIC_IS_ENABLED(BIC_Diec6)) { - pmt_add_counter(PMT_MTL_DC6_GUID, "Die%c6", PMT_TYPE_XTAL_TIME, PMT_COUNTER_MTL_DC6_LSB, - PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, SCOPE_PACKAGE, FORMAT_DELTA, - 0, PMT_OPEN_TRY); + pmt_add_counter(PMT_MTL_DC6_GUID, PMT_MTL_DC6_SEQ, "Die%c6", PMT_TYPE_XTAL_TIME, + PMT_COUNTER_MTL_DC6_LSB, PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, + SCOPE_PACKAGE, FORMAT_DELTA, 0, PMT_OPEN_TRY); + } + + if (BIC_IS_ENABLED(BIC_CPU_c1e)) { + seq = 0; + offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE; + mod_num = 0; /* Relative module number for current PMT file. */ + + /* Open the counter for each CPU. */ + for (cpu_num = 0; cpu_num < topo.max_cpu_num;) { + + if (cpu_is_not_allowed(cpu_num)) + goto next_loop_iter; + + /* + * Set the scope to CPU, even though CWF report the counter per module. + * CPUs inside the same module will read from the same location, instead of reporting zeros. + * + * CWF with newer firmware might require a PMT_TYPE_XTAL_TIME intead of PMT_TYPE_TCORE_CLOCK. + */ + pmt_add_counter(PMT_CWF_MC1E_GUID, seq, "CPU%c1e", PMT_TYPE_TCORE_CLOCK, + PMT_COUNTER_CWF_MC1E_LSB, PMT_COUNTER_CWF_MC1E_MSB, offset, SCOPE_CPU, + FORMAT_DELTA, cpu_num, PMT_OPEN_TRY); + + /* + * Rather complex logic for each time we go to the next loop iteration, + * so keep it as a label. + */ +next_loop_iter: + /* + * Advance the cpu number and check if we should also advance offset to + * the next counter inside the PMT file. + * + * On Clearwater Forest platform, the counter is reported per module, + * so open the same counter for all of the CPUs inside the module. + * That way, reported table show the correct value for all of the CPUs inside the module, + * instead of zeros. + */ + ++cpu_num; + if (cpu_num % PMT_COUNTER_CWF_CPUS_PER_MODULE == 0) { + offset += PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT; + ++mod_num; + } + + /* + * There are PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE in each PMT file. + * + * If that number is reached, seq must be incremented to advance to the next file in a sequence. + * Offset inside that file and a module counter has to be reset. + */ + if (mod_num == PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE) { + ++seq; + offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE; + mod_num = 0; + } + } } } @@ -9163,6 +9474,18 @@ void turbostat_init() } } +void affinitize_child(void) +{ + /* Prefer cpu_possible_set, if available */ + if (sched_setaffinity(0, cpu_possible_setsize, cpu_possible_set)) { + warn("sched_setaffinity cpu_possible_set"); + + /* Otherwise, allow child to run on same cpu set as turbostat */ + if (sched_setaffinity(0, cpu_allowed_setsize, cpu_allowed_set)) + warn("sched_setaffinity cpu_allowed_set"); + } +} + int fork_it(char **argv) { pid_t child_pid; @@ -9178,6 +9501,7 @@ int fork_it(char **argv) child_pid = fork(); if (!child_pid) { /* child */ + affinitize_child(); execvp(argv[0], argv); err(errno, "exec %s", argv[0]); } else { @@ -9204,10 +9528,9 @@ int fork_it(char **argv) timersub(&tv_odd, &tv_even, &tv_delta); if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS)) fprintf(outf, "%s: Counter reset detected\n", progname); - else { - compute_average(EVEN_COUNTERS); - format_all_counters(EVEN_COUNTERS); - } + + compute_average(EVEN_COUNTERS); + format_all_counters(EVEN_COUNTERS); fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec / 1000000.0); @@ -9236,7 +9559,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2024.11.30 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2025.02.02 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -9561,7 +9884,7 @@ next: } if ((msr_num == 0) && (path == NULL) && (perf_device[0] == '\0' || perf_event[0] == '\0')) { - fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event ) required\n"); + fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event) required\n"); fail++; } @@ -9599,15 +9922,100 @@ bool starts_with(const char *str, const char *prefix) return strncmp(prefix, str, strlen(prefix)) == 0; } +int pmt_parse_from_path(const char *target_path, unsigned int *out_guid, unsigned int *out_seq) +{ + struct pmt_diriter_t pmt_iter; + const struct dirent *dirname; + struct stat stat, target_stat; + int fd_telem_dir = -1; + int fd_target_dir; + unsigned int seq = 0; + unsigned long guid, target_guid; + int ret = -1; + + fd_target_dir = open(target_path, O_RDONLY | O_DIRECTORY); + if (fd_target_dir == -1) { + return -1; + } + + if (fstat(fd_target_dir, &target_stat) == -1) { + fprintf(stderr, "%s: Failed to stat the target: %s", __func__, strerror(errno)); + exit(1); + } + + if (parse_telem_info_file(fd_target_dir, "guid", "%lx", &target_guid)) { + fprintf(stderr, "%s: Failed to parse the target guid file: %s", __func__, strerror(errno)); + exit(1); + } + + close(fd_target_dir); + + pmt_diriter_init(&pmt_iter); + + for (dirname = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH); dirname != NULL; + dirname = pmt_diriter_next(&pmt_iter)) { + + fd_telem_dir = openat(dirfd(pmt_iter.dir), dirname->d_name, O_RDONLY | O_DIRECTORY); + if (fd_telem_dir == -1) + continue; + + if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) { + fprintf(stderr, "%s: Failed to parse the guid file: %s", __func__, strerror(errno)); + continue; + } + + if (fstat(fd_telem_dir, &stat) == -1) { + fprintf(stderr, "%s: Failed to stat %s directory: %s", __func__, + dirname->d_name, strerror(errno)); + continue; + } + + /* + * If reached the same directory as target, exit the loop. + * Seq has the correct value now. + */ + if (stat.st_dev == target_stat.st_dev && stat.st_ino == target_stat.st_ino) { + ret = 0; + break; + } + + /* + * If reached directory with the same guid, + * but it's not the target directory yet, + * increment seq and continue the search. + */ + if (guid == target_guid) + ++seq; + + close(fd_telem_dir); + fd_telem_dir = -1; + } + + pmt_diriter_remove(&pmt_iter); + + if (fd_telem_dir != -1) + close(fd_telem_dir); + + if (!ret) { + *out_guid = target_guid; + *out_seq = seq; + } + + return ret; +} + void parse_add_command_pmt(char *add_command) { char *name = NULL; char *type_name = NULL; char *format_name = NULL; + char *direct_path = NULL; + static const char direct_path_prefix[] = "path="; unsigned int offset; unsigned int lsb; unsigned int msb; unsigned int guid; + unsigned int seq = 0; /* By default, pick first file in a sequence with a given GUID. */ unsigned int domain_id; enum counter_scope scope = 0; enum pmt_datatype type = PMT_TYPE_RAW; @@ -9687,6 +10095,13 @@ void parse_add_command_pmt(char *add_command) goto next; } + if (sscanf(add_command, "seq=%x", &seq) == 1) + goto next; + + if (strncmp(add_command, direct_path_prefix, strlen(direct_path_prefix)) == 0) { + direct_path = add_command + strlen(direct_path_prefix); + goto next; + } next: add_command = strchr(add_command, ','); if (add_command) { @@ -9737,6 +10152,11 @@ next: has_type = true; } + if (strcmp("tcore_clock", type_name) == 0) { + type = PMT_TYPE_TCORE_CLOCK; + has_type = true; + } + if (!has_type) { printf("%s: invalid %s: %s\n", __func__, "type", type_name); exit(1); @@ -9758,8 +10178,24 @@ next: exit(1); } + if (direct_path && has_guid) { + printf("%s: path and guid+seq parameters are mutually exclusive\n" + "notice: passed guid=0x%x and path=%s\n", __func__, guid, direct_path); + exit(1); + } + + if (direct_path) { + if (pmt_parse_from_path(direct_path, &guid, &seq)) { + printf("%s: failed to parse PMT file from %s\n", __func__, direct_path); + exit(1); + } + + /* GUID was just infered from the direct path. */ + has_guid = true; + } + if (!has_guid) { - printf("%s: missing %s\n", __func__, "guid"); + printf("%s: missing %s\n", __func__, "guid or path"); exit(1); } @@ -9773,7 +10209,7 @@ next: exit(1); } - pmt_add_counter(guid, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED); + pmt_add_counter(guid, seq, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED); } void parse_add_command(char *add_command) @@ -9921,6 +10357,7 @@ void cmdline(int argc, char **argv) { "Dump", no_argument, 0, 'D' }, { "debug", no_argument, 0, 'd' }, /* internal, not documented */ { "enable", required_argument, 0, 'e' }, + { "force", no_argument, 0, 'f' }, { "interval", required_argument, 0, 'i' }, { "IPC", no_argument, 0, 'I' }, { "num_iterations", required_argument, 0, 'n' }, @@ -9981,6 +10418,9 @@ void cmdline(int argc, char **argv) /* --enable specified counter */ bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST); break; + case 'f': + force_load++; + break; case 'd': debug++; ENABLE_BIC(BIC_DISABLED_BY_DEFAULT); diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 2f36b7b6418d..f3e15e9efa76 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -9,7 +9,7 @@ #ifdef LSP #define __bpf__ -#include "../vmlinux/vmlinux.h" +#include "../vmlinux.h" #else #include "vmlinux.h" #endif @@ -24,6 +24,10 @@ #define PF_EXITING 0x00000004 #define CLOCK_MONOTONIC 1 +extern int LINUX_KERNEL_VERSION __kconfig; +extern const char CONFIG_CC_VERSION_TEXT[64] __kconfig __weak; +extern const char CONFIG_LOCALVERSION[64] __kconfig __weak; + /* * Earlier versions of clang/pahole lost upper 32bits in 64bit enums which can * lead to really confusing misbehaviors. Let's trigger a build failure. @@ -40,9 +44,9 @@ void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_fl void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak; u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; -bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym; -void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym; -void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym; +bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym __weak; +void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak; +void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak; bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; u32 scx_bpf_reenqueue_local(void) __ksym; @@ -72,6 +76,7 @@ bool scx_bpf_task_running(const struct task_struct *p) __ksym; s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym; struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym; struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym __weak; +u64 scx_bpf_now(void) __ksym __weak; /* * Use the following as @it__iter when calling scx_bpf_dsq_move[_vtime]() from @@ -98,7 +103,7 @@ void ___scx_bpf_bstr_format_checker(const char *fmt, ...) {} _Pragma("GCC diagnostic push") \ _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ ___bpf_fill(___param, args); \ - _Pragma("GCC diagnostic pop") \ + _Pragma("GCC diagnostic pop") /* * scx_bpf_exit() wraps the scx_bpf_exit_bstr() kfunc with variadic arguments @@ -136,6 +141,20 @@ void ___scx_bpf_bstr_format_checker(const char *fmt, ...) {} ___scx_bpf_bstr_format_checker(fmt, ##args); \ }) +/* + * scx_bpf_dump_header() is a wrapper around scx_bpf_dump that adds a header + * of system information for debugging. + */ +#define scx_bpf_dump_header() \ +({ \ + scx_bpf_dump("kernel: %d.%d.%d %s\ncc: %s\n", \ + LINUX_KERNEL_VERSION >> 16, \ + LINUX_KERNEL_VERSION >> 8 & 0xFF, \ + LINUX_KERNEL_VERSION & 0xFF, \ + CONFIG_LOCALVERSION, \ + CONFIG_CC_VERSION_TEXT); \ +}) + #define BPF_STRUCT_OPS(name, args...) \ SEC("struct_ops/"#name) \ BPF_PROG(name, ##args) @@ -317,6 +336,66 @@ u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym; u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym; +int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_words) __ksym; +int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym; +void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym; + +#define def_iter_struct(name) \ +struct bpf_iter_##name { \ + struct bpf_iter_bits it; \ + const struct cpumask *bitmap; \ +}; + +#define def_iter_new(name) \ +static inline int bpf_iter_##name##_new( \ + struct bpf_iter_##name *it, const u64 *unsafe_ptr__ign, u32 nr_words) \ +{ \ + it->bitmap = scx_bpf_get_##name##_cpumask(); \ + return bpf_iter_bits_new(&it->it, (const u64 *)it->bitmap, \ + sizeof(struct cpumask) / 8); \ +} + +#define def_iter_next(name) \ +static inline int *bpf_iter_##name##_next(struct bpf_iter_##name *it) { \ + return bpf_iter_bits_next(&it->it); \ +} + +#define def_iter_destroy(name) \ +static inline void bpf_iter_##name##_destroy(struct bpf_iter_##name *it) { \ + scx_bpf_put_cpumask(it->bitmap); \ + bpf_iter_bits_destroy(&it->it); \ +} +#define def_for_each_cpu(cpu, name) for_each_##name##_cpu(cpu) + +/// Provides iterator for possible and online cpus. +/// +/// # Example +/// +/// ``` +/// static inline void example_use() { +/// int *cpu; +/// +/// for_each_possible_cpu(cpu){ +/// bpf_printk("CPU %d is possible", *cpu); +/// } +/// +/// for_each_online_cpu(cpu){ +/// bpf_printk("CPU %d is online", *cpu); +/// } +/// } +/// ``` +def_iter_struct(possible); +def_iter_new(possible); +def_iter_next(possible); +def_iter_destroy(possible); +#define for_each_possible_cpu(cpu) bpf_for_each(possible, cpu, NULL, 0) + +def_iter_struct(online); +def_iter_new(online); +def_iter_next(online); +def_iter_destroy(online); +#define for_each_online_cpu(cpu) bpf_for_each(online, cpu, NULL, 0) + /* * Access a cpumask in read-only mode (typically to check bits). */ @@ -329,6 +408,100 @@ static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; +/* + * Time helpers, most of which are from jiffies.h. + */ + +/** + * time_delta - Calculate the delta between new and old time stamp + * @after: first comparable as u64 + * @before: second comparable as u64 + * + * Return: the time difference, which is >= 0 + */ +static inline s64 time_delta(u64 after, u64 before) +{ + return (s64)(after - before) > 0 ? : 0; +} + +/** + * time_after - returns true if the time a is after time b. + * @a: first comparable as u64 + * @b: second comparable as u64 + * + * Do this with "<0" and ">=0" to only test the sign of the result. A + * good compiler would generate better code (and a really good compiler + * wouldn't care). Gcc is currently neither. + * + * Return: %true is time a is after time b, otherwise %false. + */ +static inline bool time_after(u64 a, u64 b) +{ + return (s64)(b - a) < 0; +} + +/** + * time_before - returns true if the time a is before time b. + * @a: first comparable as u64 + * @b: second comparable as u64 + * + * Return: %true is time a is before time b, otherwise %false. + */ +static inline bool time_before(u64 a, u64 b) +{ + return time_after(b, a); +} + +/** + * time_after_eq - returns true if the time a is after or the same as time b. + * @a: first comparable as u64 + * @b: second comparable as u64 + * + * Return: %true is time a is after or the same as time b, otherwise %false. + */ +static inline bool time_after_eq(u64 a, u64 b) +{ + return (s64)(a - b) >= 0; +} + +/** + * time_before_eq - returns true if the time a is before or the same as time b. + * @a: first comparable as u64 + * @b: second comparable as u64 + * + * Return: %true is time a is before or the same as time b, otherwise %false. + */ +static inline bool time_before_eq(u64 a, u64 b) +{ + return time_after_eq(b, a); +} + +/** + * time_in_range - Calculate whether a is in the range of [b, c]. + * @a: time to test + * @b: beginning of the range + * @c: end of the range + * + * Return: %true is time a is in the range [b, c], otherwise %false. + */ +static inline bool time_in_range(u64 a, u64 b, u64 c) +{ + return time_after_eq(a, b) && time_before_eq(a, c); +} + +/** + * time_in_range_open - Calculate whether a is in the range of [b, c). + * @a: time to test + * @b: beginning of the range + * @c: end of the range + * + * Return: %true is time a is in the range [b, c), otherwise %false. + */ +static inline bool time_in_range_open(u64 a, u64 b, u64 c) +{ + return time_after_eq(a, b) && time_before(a, c); +} + /* * Other helpers @@ -423,5 +596,6 @@ static inline u32 log2_u64(u64 v) } #include "compat.bpf.h" +#include "enums.bpf.h" #endif /* __SCX_COMMON_BPF_H */ diff --git a/tools/sched_ext/include/scx/common.h b/tools/sched_ext/include/scx/common.h index 5b0f90152152..dc18b99e55cd 100644 --- a/tools/sched_ext/include/scx/common.h +++ b/tools/sched_ext/include/scx/common.h @@ -71,5 +71,11 @@ typedef int64_t s64; #include "user_exit_info.h" #include "compat.h" +#include "enums.h" + +/* not available when building kernel tools/sched_ext */ +#if __has_include(<lib/sdt_task.h>) +#include <lib/sdt_task.h> +#endif #endif /* __SCHED_EXT_COMMON_H */ diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h index d56520100a26..50e1499ae093 100644 --- a/tools/sched_ext/include/scx/compat.bpf.h +++ b/tools/sched_ext/include/scx/compat.bpf.h @@ -125,6 +125,11 @@ bool scx_bpf_dispatch_vtime_from_dsq___compat(struct bpf_iter_scx_dsq *it__iter, false; \ }) +#define scx_bpf_now() \ + (bpf_ksym_exists(scx_bpf_now) ? \ + scx_bpf_now() : \ + bpf_ktime_get_ns()) + /* * Define sched_ext_ops. This may be expanded to define multiple variants for * backward compatibility. See compat.h::SCX_OPS_LOAD/ATTACH(). diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h index cc56ff9aa252..b50280e2ba2b 100644 --- a/tools/sched_ext/include/scx/compat.h +++ b/tools/sched_ext/include/scx/compat.h @@ -149,6 +149,7 @@ static inline long scx_hotplug_seq(void) __skel = __scx_name##__open(); \ SCX_BUG_ON(!__skel, "Could not open " #__scx_name); \ __skel->struct_ops.__ops_name->hotplug_seq = scx_hotplug_seq(); \ + SCX_ENUM_INIT(__skel); \ __skel; \ }) diff --git a/tools/sched_ext/include/scx/enums.autogen.bpf.h b/tools/sched_ext/include/scx/enums.autogen.bpf.h new file mode 100644 index 000000000000..0e941a0d6f88 --- /dev/null +++ b/tools/sched_ext/include/scx/enums.autogen.bpf.h @@ -0,0 +1,105 @@ +/* + * WARNING: This file is autogenerated from scripts/gen_enums.py. If you would + * like to access an enum that is currently missing, add it to the script + * and run it from the root directory to update this file. + */ + +const volatile u64 __SCX_OPS_NAME_LEN __weak; +#define SCX_OPS_NAME_LEN __SCX_OPS_NAME_LEN + +const volatile u64 __SCX_SLICE_DFL __weak; +#define SCX_SLICE_DFL __SCX_SLICE_DFL + +const volatile u64 __SCX_SLICE_INF __weak; +#define SCX_SLICE_INF __SCX_SLICE_INF + +const volatile u64 __SCX_DSQ_FLAG_BUILTIN __weak; +#define SCX_DSQ_FLAG_BUILTIN __SCX_DSQ_FLAG_BUILTIN + +const volatile u64 __SCX_DSQ_FLAG_LOCAL_ON __weak; +#define SCX_DSQ_FLAG_LOCAL_ON __SCX_DSQ_FLAG_LOCAL_ON + +const volatile u64 __SCX_DSQ_INVALID __weak; +#define SCX_DSQ_INVALID __SCX_DSQ_INVALID + +const volatile u64 __SCX_DSQ_GLOBAL __weak; +#define SCX_DSQ_GLOBAL __SCX_DSQ_GLOBAL + +const volatile u64 __SCX_DSQ_LOCAL __weak; +#define SCX_DSQ_LOCAL __SCX_DSQ_LOCAL + +const volatile u64 __SCX_DSQ_LOCAL_ON __weak; +#define SCX_DSQ_LOCAL_ON __SCX_DSQ_LOCAL_ON + +const volatile u64 __SCX_DSQ_LOCAL_CPU_MASK __weak; +#define SCX_DSQ_LOCAL_CPU_MASK __SCX_DSQ_LOCAL_CPU_MASK + +const volatile u64 __SCX_TASK_QUEUED __weak; +#define SCX_TASK_QUEUED __SCX_TASK_QUEUED + +const volatile u64 __SCX_TASK_RESET_RUNNABLE_AT __weak; +#define SCX_TASK_RESET_RUNNABLE_AT __SCX_TASK_RESET_RUNNABLE_AT + +const volatile u64 __SCX_TASK_DEQD_FOR_SLEEP __weak; +#define SCX_TASK_DEQD_FOR_SLEEP __SCX_TASK_DEQD_FOR_SLEEP + +const volatile u64 __SCX_TASK_STATE_SHIFT __weak; +#define SCX_TASK_STATE_SHIFT __SCX_TASK_STATE_SHIFT + +const volatile u64 __SCX_TASK_STATE_BITS __weak; +#define SCX_TASK_STATE_BITS __SCX_TASK_STATE_BITS + +const volatile u64 __SCX_TASK_STATE_MASK __weak; +#define SCX_TASK_STATE_MASK __SCX_TASK_STATE_MASK + +const volatile u64 __SCX_TASK_CURSOR __weak; +#define SCX_TASK_CURSOR __SCX_TASK_CURSOR + +const volatile u64 __SCX_TASK_NONE __weak; +#define SCX_TASK_NONE __SCX_TASK_NONE + +const volatile u64 __SCX_TASK_INIT __weak; +#define SCX_TASK_INIT __SCX_TASK_INIT + +const volatile u64 __SCX_TASK_READY __weak; +#define SCX_TASK_READY __SCX_TASK_READY + +const volatile u64 __SCX_TASK_ENABLED __weak; +#define SCX_TASK_ENABLED __SCX_TASK_ENABLED + +const volatile u64 __SCX_TASK_NR_STATES __weak; +#define SCX_TASK_NR_STATES __SCX_TASK_NR_STATES + +const volatile u64 __SCX_TASK_DSQ_ON_PRIQ __weak; +#define SCX_TASK_DSQ_ON_PRIQ __SCX_TASK_DSQ_ON_PRIQ + +const volatile u64 __SCX_KICK_IDLE __weak; +#define SCX_KICK_IDLE __SCX_KICK_IDLE + +const volatile u64 __SCX_KICK_PREEMPT __weak; +#define SCX_KICK_PREEMPT __SCX_KICK_PREEMPT + +const volatile u64 __SCX_KICK_WAIT __weak; +#define SCX_KICK_WAIT __SCX_KICK_WAIT + +const volatile u64 __SCX_ENQ_WAKEUP __weak; +#define SCX_ENQ_WAKEUP __SCX_ENQ_WAKEUP + +const volatile u64 __SCX_ENQ_HEAD __weak; +#define SCX_ENQ_HEAD __SCX_ENQ_HEAD + +const volatile u64 __SCX_ENQ_PREEMPT __weak; +#define SCX_ENQ_PREEMPT __SCX_ENQ_PREEMPT + +const volatile u64 __SCX_ENQ_REENQ __weak; +#define SCX_ENQ_REENQ __SCX_ENQ_REENQ + +const volatile u64 __SCX_ENQ_LAST __weak; +#define SCX_ENQ_LAST __SCX_ENQ_LAST + +const volatile u64 __SCX_ENQ_CLEAR_OPSS __weak; +#define SCX_ENQ_CLEAR_OPSS __SCX_ENQ_CLEAR_OPSS + +const volatile u64 __SCX_ENQ_DSQ_PRIQ __weak; +#define SCX_ENQ_DSQ_PRIQ __SCX_ENQ_DSQ_PRIQ + diff --git a/tools/sched_ext/include/scx/enums.autogen.h b/tools/sched_ext/include/scx/enums.autogen.h new file mode 100644 index 000000000000..88137a140e72 --- /dev/null +++ b/tools/sched_ext/include/scx/enums.autogen.h @@ -0,0 +1,41 @@ +/* + * WARNING: This file is autogenerated from scripts/gen_enums.py. If you would + * like to access an enum that is currently missing, add it to the script + * and run it from the root directory to update this file. + */ + +#define SCX_ENUM_INIT(skel) do { \ + SCX_ENUM_SET(skel, scx_public_consts, SCX_OPS_NAME_LEN); \ + SCX_ENUM_SET(skel, scx_public_consts, SCX_SLICE_DFL); \ + SCX_ENUM_SET(skel, scx_public_consts, SCX_SLICE_INF); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_FLAG_BUILTIN); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_FLAG_LOCAL_ON); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_INVALID); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_GLOBAL); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_LOCAL); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_LOCAL_ON); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_LOCAL_CPU_MASK); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_QUEUED); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_RESET_RUNNABLE_AT); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_DEQD_FOR_SLEEP); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_STATE_SHIFT); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_STATE_BITS); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_STATE_MASK); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_CURSOR); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_NONE); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_INIT); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_READY); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_ENABLED); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_NR_STATES); \ + SCX_ENUM_SET(skel, scx_ent_dsq_flags, SCX_TASK_DSQ_ON_PRIQ); \ + SCX_ENUM_SET(skel, scx_kick_flags, SCX_KICK_IDLE); \ + SCX_ENUM_SET(skel, scx_kick_flags, SCX_KICK_PREEMPT); \ + SCX_ENUM_SET(skel, scx_kick_flags, SCX_KICK_WAIT); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_WAKEUP); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_HEAD); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_PREEMPT); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_REENQ); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_LAST); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_CLEAR_OPSS); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_DSQ_PRIQ); \ +} while (0) diff --git a/tools/sched_ext/include/scx/enums.bpf.h b/tools/sched_ext/include/scx/enums.bpf.h new file mode 100644 index 000000000000..af704c5d6334 --- /dev/null +++ b/tools/sched_ext/include/scx/enums.bpf.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Convenience macros for getting/setting struct scx_enums instances. + * + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + */ +#ifndef __SCX_ENUMS_BPF_H +#define __SCX_ENUMS_BPF_H + +#include "enums.autogen.bpf.h" + +#endif /* __SCX_ENUMS_BPF_H */ diff --git a/tools/sched_ext/include/scx/enums.h b/tools/sched_ext/include/scx/enums.h new file mode 100644 index 000000000000..34cbebe974b7 --- /dev/null +++ b/tools/sched_ext/include/scx/enums.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Define struct scx_enums that stores the load-time values of enums + * used by the BPF program. + * + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + */ + +#ifndef __SCX_ENUMS_H +#define __SCX_ENUMS_H + +static inline void __ENUM_set(u64 *val, char *type, char *name) +{ + bool res; + + res = __COMPAT_read_enum(type, name, val); + SCX_BUG_ON(!res, "enum not found(%s)", name); +} + +#define SCX_ENUM_SET(skel, type, name) do { \ + __ENUM_set(&skel->rodata->__##name, #type, #name); \ + } while (0) + + +#include "enums.autogen.h" + +#endif /* __SCX_ENUMS_H */ diff --git a/tools/sched_ext/include/scx/user_exit_info.h b/tools/sched_ext/include/scx/user_exit_info.h index 8ce2734402e1..66f856640ee7 100644 --- a/tools/sched_ext/include/scx/user_exit_info.h +++ b/tools/sched_ext/include/scx/user_exit_info.h @@ -10,6 +10,11 @@ #ifndef __USER_EXIT_INFO_H #define __USER_EXIT_INFO_H +#ifdef LSP +#define __bpf__ +#include "../vmlinux.h" +#endif + enum uei_sizes { UEI_REASON_LEN = 128, UEI_MSG_LEN = 1024, @@ -25,9 +30,7 @@ struct user_exit_info { #ifdef __bpf__ -#ifdef LSP -#include "../vmlinux/vmlinux.h" -#else +#ifndef LSP #include "vmlinux.h" #endif #include <bpf/bpf_core_read.h> diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c index e6fad6211f6c..50bc1737c167 100644 --- a/tools/sched_ext/scx_central.bpf.c +++ b/tools/sched_ext/scx_central.bpf.c @@ -57,7 +57,7 @@ enum { const volatile s32 central_cpu; const volatile u32 nr_cpu_ids = 1; /* !0 for veristat, set during init */ -const volatile u64 slice_ns = SCX_SLICE_DFL; +const volatile u64 slice_ns; bool timer_pinned = true; u64 nr_total, nr_locals, nr_queued, nr_lost_pids; @@ -87,11 +87,6 @@ struct { __type(value, struct central_timer); } central_timer SEC(".maps"); -static bool vtime_before(u64 a, u64 b) -{ - return (s64)(a - b) < 0; -} - s32 BPF_STRUCT_OPS(central_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { @@ -245,7 +240,7 @@ void BPF_STRUCT_OPS(central_running, struct task_struct *p) s32 cpu = scx_bpf_task_cpu(p); u64 *started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids); if (started_at) - *started_at = bpf_ktime_get_ns() ?: 1; /* 0 indicates idle */ + *started_at = scx_bpf_now() ?: 1; /* 0 indicates idle */ } void BPF_STRUCT_OPS(central_stopping, struct task_struct *p, bool runnable) @@ -258,7 +253,7 @@ void BPF_STRUCT_OPS(central_stopping, struct task_struct *p, bool runnable) static int central_timerfn(void *map, int *key, struct bpf_timer *timer) { - u64 now = bpf_ktime_get_ns(); + u64 now = scx_bpf_now(); u64 nr_to_kick = nr_queued; s32 i, curr_cpu; @@ -279,7 +274,7 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer) /* kick iff the current one exhausted its slice */ started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids); if (started_at && *started_at && - vtime_before(now, *started_at + slice_ns)) + time_before(now, *started_at + slice_ns)) continue; /* and there's something pending */ diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index 21deea320bd7..1e9f74525d8f 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -58,6 +58,7 @@ restart: skel->rodata->central_cpu = 0; skel->rodata->nr_cpu_ids = libbpf_num_possible_cpus(); + skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL"); while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) { switch (opt) { @@ -97,7 +98,7 @@ restart: SCX_BUG_ON(!cpuset, "Failed to allocate cpuset"); CPU_ZERO(cpuset); CPU_SET(skel->rodata->central_cpu, cpuset); - SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset), + SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset), "Failed to affinitize to central CPU %d (max %d)", skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1); CPU_FREE(cpuset); diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c index 4e3afcd260bf..2c720e3ecad5 100644 --- a/tools/sched_ext/scx_flatcg.bpf.c +++ b/tools/sched_ext/scx_flatcg.bpf.c @@ -57,7 +57,7 @@ enum { char _license[] SEC("license") = "GPL"; const volatile u32 nr_cpus = 32; /* !0 for veristat, set during init */ -const volatile u64 cgrp_slice_ns = SCX_SLICE_DFL; +const volatile u64 cgrp_slice_ns; const volatile bool fifo_sched; u64 cvtime_now; @@ -137,11 +137,6 @@ static u64 div_round_up(u64 dividend, u64 divisor) return (dividend + divisor - 1) / divisor; } -static bool vtime_before(u64 a, u64 b) -{ - return (s64)(a - b) < 0; -} - static bool cgv_node_less(struct bpf_rb_node *a, const struct bpf_rb_node *b) { struct cgv_node *cgc_a, *cgc_b; @@ -271,7 +266,7 @@ static void cgrp_cap_budget(struct cgv_node *cgv_node, struct fcg_cgrp_ctx *cgc) */ max_budget = (cgrp_slice_ns * nr_cpus * cgc->hweight) / (2 * FCG_HWEIGHT_ONE); - if (vtime_before(cvtime, cvtime_now - max_budget)) + if (time_before(cvtime, cvtime_now - max_budget)) cvtime = cvtime_now - max_budget; cgv_node->cvtime = cvtime; @@ -401,7 +396,7 @@ void BPF_STRUCT_OPS(fcg_enqueue, struct task_struct *p, u64 enq_flags) * Limit the amount of budget that an idling task can accumulate * to one slice. */ - if (vtime_before(tvtime, cgc->tvtime_now - SCX_SLICE_DFL)) + if (time_before(tvtime, cgc->tvtime_now - SCX_SLICE_DFL)) tvtime = cgc->tvtime_now - SCX_SLICE_DFL; scx_bpf_dsq_insert_vtime(p, cgrp->kn->id, SCX_SLICE_DFL, @@ -535,7 +530,7 @@ void BPF_STRUCT_OPS(fcg_running, struct task_struct *p) * from multiple CPUs and thus racy. Any error should be * contained and temporary. Let's just live with it. */ - if (vtime_before(cgc->tvtime_now, p->scx.dsq_vtime)) + if (time_before(cgc->tvtime_now, p->scx.dsq_vtime)) cgc->tvtime_now = p->scx.dsq_vtime; } bpf_cgroup_release(cgrp); @@ -645,7 +640,7 @@ static bool try_pick_next_cgroup(u64 *cgidp) cgv_node = container_of(rb_node, struct cgv_node, rb_node); cgid = cgv_node->cgid; - if (vtime_before(cvtime_now, cgv_node->cvtime)) + if (time_before(cvtime_now, cgv_node->cvtime)) cvtime_now = cgv_node->cvtime; /* @@ -734,7 +729,7 @@ void BPF_STRUCT_OPS(fcg_dispatch, s32 cpu, struct task_struct *prev) struct fcg_cpu_ctx *cpuc; struct fcg_cgrp_ctx *cgc; struct cgroup *cgrp; - u64 now = bpf_ktime_get_ns(); + u64 now = scx_bpf_now(); bool picked_next = false; cpuc = find_cpu_ctx(); @@ -744,7 +739,7 @@ void BPF_STRUCT_OPS(fcg_dispatch, s32 cpu, struct task_struct *prev) if (!cpuc->cur_cgid) goto pick_next_cgroup; - if (vtime_before(now, cpuc->cur_at + cgrp_slice_ns)) { + if (time_before(now, cpuc->cur_at + cgrp_slice_ns)) { if (scx_bpf_dsq_move_to_local(cpuc->cur_cgid)) { stat_inc(FCG_STAT_CNS_KEEP); return; @@ -920,14 +915,14 @@ void BPF_STRUCT_OPS(fcg_cgroup_move, struct task_struct *p, struct cgroup *from, struct cgroup *to) { struct fcg_cgrp_ctx *from_cgc, *to_cgc; - s64 vtime_delta; + s64 delta; /* find_cgrp_ctx() triggers scx_ops_error() on lookup failures */ if (!(from_cgc = find_cgrp_ctx(from)) || !(to_cgc = find_cgrp_ctx(to))) return; - vtime_delta = p->scx.dsq_vtime - from_cgc->tvtime_now; - p->scx.dsq_vtime = to_cgc->tvtime_now + vtime_delta; + delta = time_delta(p->scx.dsq_vtime, from_cgc->tvtime_now); + p->scx.dsq_vtime = to_cgc->tvtime_now + delta; } s32 BPF_STRUCT_OPS_SLEEPABLE(fcg_init) diff --git a/tools/sched_ext/scx_flatcg.c b/tools/sched_ext/scx_flatcg.c index 5d24ca9c29d9..6dd423eeb4ff 100644 --- a/tools/sched_ext/scx_flatcg.c +++ b/tools/sched_ext/scx_flatcg.c @@ -137,6 +137,7 @@ restart: skel = SCX_OPS_OPEN(flatcg_ops, scx_flatcg); skel->rodata->nr_cpus = libbpf_num_possible_cpus(); + skel->rodata->cgrp_slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL"); while ((opt = getopt(argc, argv, "s:i:dfvh")) != -1) { double v; diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index ee264947e0c3..3a20bb0c014a 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -33,7 +33,7 @@ enum consts { char _license[] SEC("license") = "GPL"; -const volatile u64 slice_ns = SCX_SLICE_DFL; +const volatile u64 slice_ns; const volatile u32 stall_user_nth; const volatile u32 stall_kernel_nth; const volatile u32 dsp_inf_loop_after; diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c index ac45a02b4055..c4912ab2e76f 100644 --- a/tools/sched_ext/scx_qmap.c +++ b/tools/sched_ext/scx_qmap.c @@ -64,6 +64,8 @@ int main(int argc, char **argv) skel = SCX_OPS_OPEN(qmap_ops, scx_qmap); + skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL"); + while ((opt = getopt(argc, argv, "s:e:t:T:l:b:PHd:D:Spvh")) != -1) { switch (opt) { case 's': diff --git a/tools/sched_ext/scx_simple.bpf.c b/tools/sched_ext/scx_simple.bpf.c index 31f915b286c6..e6de99dba7db 100644 --- a/tools/sched_ext/scx_simple.bpf.c +++ b/tools/sched_ext/scx_simple.bpf.c @@ -52,11 +52,6 @@ static void stat_inc(u32 idx) (*cnt_p)++; } -static inline bool vtime_before(u64 a, u64 b) -{ - return (s64)(a - b) < 0; -} - s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { bool is_idle = false; @@ -84,7 +79,7 @@ void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags) * Limit the amount of budget that an idling task can accumulate * to one slice. */ - if (vtime_before(vtime, vtime_now - SCX_SLICE_DFL)) + if (time_before(vtime, vtime_now - SCX_SLICE_DFL)) vtime = vtime_now - SCX_SLICE_DFL; scx_bpf_dsq_insert_vtime(p, SHARED_DSQ, SCX_SLICE_DFL, vtime, @@ -108,7 +103,7 @@ void BPF_STRUCT_OPS(simple_running, struct task_struct *p) * thus racy. Any error should be contained and temporary. Let's just * live with it. */ - if (vtime_before(vtime_now, p->scx.dsq_vtime)) + if (time_before(vtime_now, p->scx.dsq_vtime)) vtime_now = p->scx.dsq_vtime; } diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl new file mode 100644 index 000000000000..ebbdb3c42e9f --- /dev/null +++ b/tools/scripts/syscall.tbl @@ -0,0 +1,409 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# This file contains the system call numbers for all of the +# more recently added architectures. +# +# As a basic principle, no duplication of functionality +# should be added, e.g. we don't use lseek when llseek +# is present. New architectures should use this file +# and implement the less feature-full calls in user space. +# +0 common io_setup sys_io_setup compat_sys_io_setup +1 common io_destroy sys_io_destroy +2 common io_submit sys_io_submit compat_sys_io_submit +3 common io_cancel sys_io_cancel +4 time32 io_getevents sys_io_getevents_time32 +4 64 io_getevents sys_io_getevents +5 common setxattr sys_setxattr +6 common lsetxattr sys_lsetxattr +7 common fsetxattr sys_fsetxattr +8 common getxattr sys_getxattr +9 common lgetxattr sys_lgetxattr +10 common fgetxattr sys_fgetxattr +11 common listxattr sys_listxattr +12 common llistxattr sys_llistxattr +13 common flistxattr sys_flistxattr +14 common removexattr sys_removexattr +15 common lremovexattr sys_lremovexattr +16 common fremovexattr sys_fremovexattr +17 common getcwd sys_getcwd +18 common lookup_dcookie sys_ni_syscall +19 common eventfd2 sys_eventfd2 +20 common epoll_create1 sys_epoll_create1 +21 common epoll_ctl sys_epoll_ctl +22 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +23 common dup sys_dup +24 common dup3 sys_dup3 +25 32 fcntl64 sys_fcntl64 compat_sys_fcntl64 +25 64 fcntl sys_fcntl +26 common inotify_init1 sys_inotify_init1 +27 common inotify_add_watch sys_inotify_add_watch +28 common inotify_rm_watch sys_inotify_rm_watch +29 common ioctl sys_ioctl compat_sys_ioctl +30 common ioprio_set sys_ioprio_set +31 common ioprio_get sys_ioprio_get +32 common flock sys_flock +33 common mknodat sys_mknodat +34 common mkdirat sys_mkdirat +35 common unlinkat sys_unlinkat +36 common symlinkat sys_symlinkat +37 common linkat sys_linkat +# renameat is superseded with flags by renameat2 +38 renameat renameat sys_renameat +39 common umount2 sys_umount +40 common mount sys_mount +41 common pivot_root sys_pivot_root +42 common nfsservctl sys_ni_syscall +43 32 statfs64 sys_statfs64 compat_sys_statfs64 +43 64 statfs sys_statfs +44 32 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +44 64 fstatfs sys_fstatfs +45 32 truncate64 sys_truncate64 compat_sys_truncate64 +45 64 truncate sys_truncate +46 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64 +46 64 ftruncate sys_ftruncate +47 common fallocate sys_fallocate compat_sys_fallocate +48 common faccessat sys_faccessat +49 common chdir sys_chdir +50 common fchdir sys_fchdir +51 common chroot sys_chroot +52 common fchmod sys_fchmod +53 common fchmodat sys_fchmodat +54 common fchownat sys_fchownat +55 common fchown sys_fchown +56 common openat sys_openat +57 common close sys_close +58 common vhangup sys_vhangup +59 common pipe2 sys_pipe2 +60 common quotactl sys_quotactl +61 common getdents64 sys_getdents64 +62 32 llseek sys_llseek +62 64 lseek sys_lseek +63 common read sys_read +64 common write sys_write +65 common readv sys_readv sys_readv +66 common writev sys_writev sys_writev +67 common pread64 sys_pread64 compat_sys_pread64 +68 common pwrite64 sys_pwrite64 compat_sys_pwrite64 +69 common preadv sys_preadv compat_sys_preadv +70 common pwritev sys_pwritev compat_sys_pwritev +71 32 sendfile64 sys_sendfile64 +71 64 sendfile sys_sendfile64 +72 time32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +72 64 pselect6 sys_pselect6 +73 time32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +73 64 ppoll sys_ppoll +74 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +75 common vmsplice sys_vmsplice +76 common splice sys_splice +77 common tee sys_tee +78 common readlinkat sys_readlinkat +79 stat64 fstatat64 sys_fstatat64 +79 64 newfstatat sys_newfstatat +80 stat64 fstat64 sys_fstat64 +80 64 fstat sys_newfstat +81 common sync sys_sync +82 common fsync sys_fsync +83 common fdatasync sys_fdatasync +84 common sync_file_range sys_sync_file_range compat_sys_sync_file_range +85 common timerfd_create sys_timerfd_create +86 time32 timerfd_settime sys_timerfd_settime32 +86 64 timerfd_settime sys_timerfd_settime +87 time32 timerfd_gettime sys_timerfd_gettime32 +87 64 timerfd_gettime sys_timerfd_gettime +88 time32 utimensat sys_utimensat_time32 +88 64 utimensat sys_utimensat +89 common acct sys_acct +90 common capget sys_capget +91 common capset sys_capset +92 common personality sys_personality +93 common exit sys_exit +94 common exit_group sys_exit_group +95 common waitid sys_waitid compat_sys_waitid +96 common set_tid_address sys_set_tid_address +97 common unshare sys_unshare +98 time32 futex sys_futex_time32 +98 64 futex sys_futex +99 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +100 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +101 time32 nanosleep sys_nanosleep_time32 +101 64 nanosleep sys_nanosleep +102 common getitimer sys_getitimer compat_sys_getitimer +103 common setitimer sys_setitimer compat_sys_setitimer +104 common kexec_load sys_kexec_load compat_sys_kexec_load +105 common init_module sys_init_module +106 common delete_module sys_delete_module +107 common timer_create sys_timer_create compat_sys_timer_create +108 time32 timer_gettime sys_timer_gettime32 +108 64 timer_gettime sys_timer_gettime +109 common timer_getoverrun sys_timer_getoverrun +110 time32 timer_settime sys_timer_settime32 +110 64 timer_settime sys_timer_settime +111 common timer_delete sys_timer_delete +112 time32 clock_settime sys_clock_settime32 +112 64 clock_settime sys_clock_settime +113 time32 clock_gettime sys_clock_gettime32 +113 64 clock_gettime sys_clock_gettime +114 time32 clock_getres sys_clock_getres_time32 +114 64 clock_getres sys_clock_getres +115 time32 clock_nanosleep sys_clock_nanosleep_time32 +115 64 clock_nanosleep sys_clock_nanosleep +116 common syslog sys_syslog +117 common ptrace sys_ptrace compat_sys_ptrace +118 common sched_setparam sys_sched_setparam +119 common sched_setscheduler sys_sched_setscheduler +120 common sched_getscheduler sys_sched_getscheduler +121 common sched_getparam sys_sched_getparam +122 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +123 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +124 common sched_yield sys_sched_yield +125 common sched_get_priority_max sys_sched_get_priority_max +126 common sched_get_priority_min sys_sched_get_priority_min +127 time32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +127 64 sched_rr_get_interval sys_sched_rr_get_interval +128 common restart_syscall sys_restart_syscall +129 common kill sys_kill +130 common tkill sys_tkill +131 common tgkill sys_tgkill +132 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +133 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +134 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +135 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +136 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +137 time32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +137 64 rt_sigtimedwait sys_rt_sigtimedwait +138 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +139 common rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn +140 common setpriority sys_setpriority +141 common getpriority sys_getpriority +142 common reboot sys_reboot +143 common setregid sys_setregid +144 common setgid sys_setgid +145 common setreuid sys_setreuid +146 common setuid sys_setuid +147 common setresuid sys_setresuid +148 common getresuid sys_getresuid +149 common setresgid sys_setresgid +150 common getresgid sys_getresgid +151 common setfsuid sys_setfsuid +152 common setfsgid sys_setfsgid +153 common times sys_times compat_sys_times +154 common setpgid sys_setpgid +155 common getpgid sys_getpgid +156 common getsid sys_getsid +157 common setsid sys_setsid +158 common getgroups sys_getgroups +159 common setgroups sys_setgroups +160 common uname sys_newuname +161 common sethostname sys_sethostname +162 common setdomainname sys_setdomainname +# getrlimit and setrlimit are superseded with prlimit64 +163 rlimit getrlimit sys_getrlimit compat_sys_getrlimit +164 rlimit setrlimit sys_setrlimit compat_sys_setrlimit +165 common getrusage sys_getrusage compat_sys_getrusage +166 common umask sys_umask +167 common prctl sys_prctl +168 common getcpu sys_getcpu +169 time32 gettimeofday sys_gettimeofday compat_sys_gettimeofday +169 64 gettimeofday sys_gettimeofday +170 time32 settimeofday sys_settimeofday compat_sys_settimeofday +170 64 settimeofday sys_settimeofday +171 time32 adjtimex sys_adjtimex_time32 +171 64 adjtimex sys_adjtimex +172 common getpid sys_getpid +173 common getppid sys_getppid +174 common getuid sys_getuid +175 common geteuid sys_geteuid +176 common getgid sys_getgid +177 common getegid sys_getegid +178 common gettid sys_gettid +179 common sysinfo sys_sysinfo compat_sys_sysinfo +180 common mq_open sys_mq_open compat_sys_mq_open +181 common mq_unlink sys_mq_unlink +182 time32 mq_timedsend sys_mq_timedsend_time32 +182 64 mq_timedsend sys_mq_timedsend +183 time32 mq_timedreceive sys_mq_timedreceive_time32 +183 64 mq_timedreceive sys_mq_timedreceive +184 common mq_notify sys_mq_notify compat_sys_mq_notify +185 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +186 common msgget sys_msgget +187 common msgctl sys_msgctl compat_sys_msgctl +188 common msgrcv sys_msgrcv compat_sys_msgrcv +189 common msgsnd sys_msgsnd compat_sys_msgsnd +190 common semget sys_semget +191 common semctl sys_semctl compat_sys_semctl +192 time32 semtimedop sys_semtimedop_time32 +192 64 semtimedop sys_semtimedop +193 common semop sys_semop +194 common shmget sys_shmget +195 common shmctl sys_shmctl compat_sys_shmctl +196 common shmat sys_shmat compat_sys_shmat +197 common shmdt sys_shmdt +198 common socket sys_socket +199 common socketpair sys_socketpair +200 common bind sys_bind +201 common listen sys_listen +202 common accept sys_accept +203 common connect sys_connect +204 common getsockname sys_getsockname +205 common getpeername sys_getpeername +206 common sendto sys_sendto +207 common recvfrom sys_recvfrom compat_sys_recvfrom +208 common setsockopt sys_setsockopt sys_setsockopt +209 common getsockopt sys_getsockopt sys_getsockopt +210 common shutdown sys_shutdown +211 common sendmsg sys_sendmsg compat_sys_sendmsg +212 common recvmsg sys_recvmsg compat_sys_recvmsg +213 common readahead sys_readahead compat_sys_readahead +214 common brk sys_brk +215 common munmap sys_munmap +216 common mremap sys_mremap +217 common add_key sys_add_key +218 common request_key sys_request_key +219 common keyctl sys_keyctl compat_sys_keyctl +220 common clone sys_clone +221 common execve sys_execve compat_sys_execve +222 32 mmap2 sys_mmap2 +222 64 mmap sys_mmap +223 32 fadvise64_64 sys_fadvise64_64 compat_sys_fadvise64_64 +223 64 fadvise64 sys_fadvise64_64 +224 common swapon sys_swapon +225 common swapoff sys_swapoff +226 common mprotect sys_mprotect +227 common msync sys_msync +228 common mlock sys_mlock +229 common munlock sys_munlock +230 common mlockall sys_mlockall +231 common munlockall sys_munlockall +232 common mincore sys_mincore +233 common madvise sys_madvise +234 common remap_file_pages sys_remap_file_pages +235 common mbind sys_mbind +236 common get_mempolicy sys_get_mempolicy +237 common set_mempolicy sys_set_mempolicy +238 common migrate_pages sys_migrate_pages +239 common move_pages sys_move_pages +240 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +241 common perf_event_open sys_perf_event_open +242 common accept4 sys_accept4 +243 time32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +243 64 recvmmsg sys_recvmmsg +# Architectures may provide up to 16 syscalls of their own between 244 and 259 +244 arc cacheflush sys_cacheflush +245 arc arc_settls sys_arc_settls +246 arc arc_gettls sys_arc_gettls +247 arc sysfs sys_sysfs +248 arc arc_usr_cmpxchg sys_arc_usr_cmpxchg + +244 csky set_thread_area sys_set_thread_area +245 csky cacheflush sys_cacheflush + +244 nios2 cacheflush sys_cacheflush + +244 or1k or1k_atomic sys_or1k_atomic + +258 riscv riscv_hwprobe sys_riscv_hwprobe +259 riscv riscv_flush_icache sys_riscv_flush_icache + +260 time32 wait4 sys_wait4 compat_sys_wait4 +260 64 wait4 sys_wait4 +261 common prlimit64 sys_prlimit64 +262 common fanotify_init sys_fanotify_init +263 common fanotify_mark sys_fanotify_mark +264 common name_to_handle_at sys_name_to_handle_at +265 common open_by_handle_at sys_open_by_handle_at +266 time32 clock_adjtime sys_clock_adjtime32 +266 64 clock_adjtime sys_clock_adjtime +267 common syncfs sys_syncfs +268 common setns sys_setns +269 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +270 common process_vm_readv sys_process_vm_readv +271 common process_vm_writev sys_process_vm_writev +272 common kcmp sys_kcmp +273 common finit_module sys_finit_module +274 common sched_setattr sys_sched_setattr +275 common sched_getattr sys_sched_getattr +276 common renameat2 sys_renameat2 +277 common seccomp sys_seccomp +278 common getrandom sys_getrandom +279 common memfd_create sys_memfd_create +280 common bpf sys_bpf +281 common execveat sys_execveat compat_sys_execveat +282 common userfaultfd sys_userfaultfd +283 common membarrier sys_membarrier +284 common mlock2 sys_mlock2 +285 common copy_file_range sys_copy_file_range +286 common preadv2 sys_preadv2 compat_sys_preadv2 +287 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +288 common pkey_mprotect sys_pkey_mprotect +289 common pkey_alloc sys_pkey_alloc +290 common pkey_free sys_pkey_free +291 common statx sys_statx +292 time32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +292 64 io_pgetevents sys_io_pgetevents +293 common rseq sys_rseq +294 common kexec_file_load sys_kexec_file_load +# 295 through 402 are unassigned to sync up with generic numbers don't use +403 32 clock_gettime64 sys_clock_gettime +404 32 clock_settime64 sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime +409 32 timer_settime64 sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +447 memfd_secret memfd_secret sys_memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index d0337c11f9ee..cc8948f49117 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -725,7 +725,7 @@ static void default_mock_decoder(struct cxl_decoder *cxld) cxld->reset = mock_decoder_reset; } -static int first_decoder(struct device *dev, void *data) +static int first_decoder(struct device *dev, const void *data) { struct cxl_decoder *cxld; diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 347c1e7b37bd..8d731bd63988 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -401,6 +401,10 @@ struct cxl_test_gen_media gen_media = { .channel = 1, .rank = 30, }, + .component_id = { 0x3, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .cme_threshold_ev_flags = 3, + .cme_count = { 33, 0, 0 }, + .sub_type = 0x2, }, }; @@ -429,6 +433,11 @@ struct cxl_test_dram dram = { .bank_group = 5, .bank = 2, .column = {0xDE, 0xAD}, + .component_id = { 0x1, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .sub_channel = 8, + .cme_threshold_ev_flags = 2, + .cvme_count = { 14, 0, 0 }, + .sub_type = 0x5, }, }; @@ -456,7 +465,10 @@ struct cxl_test_mem_module mem_module = { .dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef }, .cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, .cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, - } + }, + /* .validity_flags = <set below> */ + .component_id = { 0x2, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .event_sub_type = 0x3, }, }; @@ -478,13 +490,18 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds, static void cxl_mock_add_event_logs(struct mock_event_store *mes) { - put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, + put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK | + CXL_GMER_VALID_COMPONENT | CXL_GMER_VALID_COMPONENT_ID_FORMAT, &gen_media.rec.media_hdr.validity_flags); put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP | - CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN, + CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN | CXL_DER_VALID_SUB_CHANNEL | + CXL_DER_VALID_COMPONENT | CXL_DER_VALID_COMPONENT_ID_FORMAT, &dram.rec.media_hdr.validity_flags); + put_unaligned_le16(CXL_MMER_VALID_COMPONENT | CXL_MMER_VALID_COMPONENT_ID_FORMAT, + &mem_module.rec.validity_flags); + mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed); mes_add_event(mes, CXL_EVENT_TYPE_INFO, (struct cxl_event_record_raw *)&gen_media); diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 450c7566c33f..af2594e4f35d 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -228,16 +228,16 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, "CXL"); -int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, +int __wrap_cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds, struct cxl_endpoint_dvsec_info *info) { int rc = 0, index; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - if (ops && ops->is_mock_dev(dev)) + if (ops && ops->is_mock_dev(cxlds->dev)) rc = 0; else - rc = cxl_dvsec_rr_decode(dev, port, info); + rc = cxl_dvsec_rr_decode(cxlds, info); put_cxl_mock_ops(index); return rc; diff --git a/tools/testing/ktest/examples/include/defaults.conf b/tools/testing/ktest/examples/include/defaults.conf index 63a1a83f4f0b..f6d8517a471e 100644 --- a/tools/testing/ktest/examples/include/defaults.conf +++ b/tools/testing/ktest/examples/include/defaults.conf @@ -46,7 +46,7 @@ CLEAR_LOG = 1 SSH_USER = root -# For accesing the machine, we will ssh to root@machine. +# For accessing the machine, we will ssh to root@machine. SSH := ssh ${SSH_USER}@${MACHINE} # Update this. The default here is ktest will ssh to the target box diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index dacad94e2be4..8c8da966c641 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1245,7 +1245,7 @@ sub __read_config { # Config variables are only active while reading the # config and can be defined anywhere. They also ignore # TEST_START and DEFAULTS, but are skipped if they are in - # on of these sections that have SKIP defined. + # one of these sections that have SKIP defined. # The save variable can be # defined multiple times and the new one simply overrides # the previous one. @@ -2419,6 +2419,11 @@ sub get_version { return if ($have_version); doprint "$make kernelrelease ... "; $version = `$make -s kernelrelease | tail -1`; + if (!length($version)) { + run_command "$make allnoconfig" or return 0; + doprint "$make kernelrelease ... "; + $version = `$make -s kernelrelease | tail -1`; + } chomp($version); doprint "$version\n"; $have_version = 1; @@ -2960,8 +2965,6 @@ sub run_bisect_test { my $failed = 0; my $result; - my $output; - my $ret; $in_bisect = 1; diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config index b3b00269a52a..b0049be00c70 100644 --- a/tools/testing/kunit/configs/all_tests.config +++ b/tools/testing/kunit/configs/all_tests.config @@ -38,9 +38,6 @@ CONFIG_IWLWIFI=y CONFIG_DAMON=y CONFIG_DAMON_VADDR=y CONFIG_DAMON_PADDR=y -CONFIG_DEBUG_FS=y -CONFIG_DAMON_DBGFS=y -CONFIG_DAMON_DBGFS_DEPRECATED=y CONFIG_REGMAP_BUILD=y diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 676fa99a8b19..7f9ae55fd6d5 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -312,7 +312,16 @@ def massage_argv(argv: Sequence[str]) -> Sequence[str]: return list(map(massage_arg, argv)) def get_default_jobs() -> int: - return len(os.sched_getaffinity(0)) + if sys.version_info >= (3, 13): + if (ncpu := os.process_cpu_count()) is not None: + return ncpu + raise RuntimeError("os.process_cpu_count() returned None") + # See https://github.com/python/cpython/blob/b61fece/Lib/os.py#L1175-L1186. + if sys.platform != "darwin": + return len(os.sched_getaffinity(0)) + if (ncpu := os.cpu_count()) is not None: + return ncpu + raise RuntimeError("os.cpu_count() returned None") def add_common_opts(parser: argparse.ArgumentParser) -> None: parser.add_argument('--build_dir', diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index e76d7894b6c5..d30f90eae9a4 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -125,6 +125,9 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): '-append', ' '.join(params + [self._kernel_command_line]), '-no-reboot', '-nographic', + '-accel', 'kvm', + '-accel', 'hvf', + '-accel', 'tcg', '-serial', self._serial] + self._extra_qemu_params # Note: shlex.join() does what we want, but requires python 3.8+. print('Running tests with:\n$', ' '.join(shlex.quote(arg) for arg in qemu_command)) diff --git a/tools/testing/kunit/qemu_configs/arm64.py b/tools/testing/kunit/qemu_configs/arm64.py index d3ff27024755..5c44d3a87e6d 100644 --- a/tools/testing/kunit/qemu_configs/arm64.py +++ b/tools/testing/kunit/qemu_configs/arm64.py @@ -9,4 +9,4 @@ CONFIG_SERIAL_AMBA_PL011_CONSOLE=y''', qemu_arch='aarch64', kernel_path='arch/arm64/boot/Image.gz', kernel_command_line='console=ttyAMA0', - extra_qemu_params=['-machine', 'virt', '-cpu', 'max,pauth-impdef=on']) + extra_qemu_params=['-machine', 'virt', '-cpu', 'max']) diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index cffaf2245d4f..eaff1b036989 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -227,6 +227,7 @@ static void *load_creator(void *ptr) unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) - (1 << order); item_insert_order(tree, index, order); + xa_set_mark(tree, index, XA_MARK_1); item_delete_rcu(tree, index); } } @@ -242,8 +243,11 @@ static void *load_worker(void *ptr) rcu_register_thread(); while (!stop_iteration) { + unsigned long find_index = (2 << RADIX_TREE_MAP_SHIFT) + 1; struct item *item = xa_load(ptr, index); assert(!xa_is_internal(item)); + item = xa_find(ptr, &find_index, index, XA_MARK_1); + assert(!xa_is_internal(item)); } rcu_unregister_thread(); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 2401e973c359..8daac70c2f9d 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -18,6 +18,7 @@ TARGETS += devices/error_logs TARGETS += devices/probe TARGETS += dmabuf-heaps TARGETS += drivers/dma-buf +TARGETS += drivers/ntsync TARGETS += drivers/s390x/uvdevice TARGETS += drivers/net TARGETS += drivers/net/bonding @@ -72,6 +73,7 @@ TARGETS += net/packetdrill TARGETS += net/rds TARGETS += net/tcp_ao TARGETS += nsfs +TARGETS += pci_endpoint TARGETS += pcie_bwctrl TARGETS += perf_events TARGETS += pidfd diff --git a/tools/testing/selftests/acct/acct_syscall.c b/tools/testing/selftests/acct/acct_syscall.c index e44e8fe1f4a3..87c044fb9293 100644 --- a/tools/testing/selftests/acct/acct_syscall.c +++ b/tools/testing/selftests/acct/acct_syscall.c @@ -24,7 +24,7 @@ int main(void) // Check if test is run a root if (geteuid()) { - ksft_test_result_skip("This test needs root to run!\n"); + ksft_exit_skip("This test needs root to run!\n"); return 1; } diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 944279160fed..8dab90ad22bb 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -27,5 +27,5 @@ include ../lib.mk $(OUTPUT)/libatest.so: conf.c alsa-local.h $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@ -$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) alsa-local.h +$(OUTPUT)/%: %.c $(OUTPUT)/libatest.so alsa-local.h $(CC) $(CFLAGS) $< $(LDLIBS) -latest -o $@ diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 0029ed9c5c9a..35f521e5f41c 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -46,6 +46,12 @@ static void atomics_sigill(void) asm volatile(".inst 0xb82003ff" : : : ); } +static void cmpbr_sigill(void) +{ + /* Not implemented, too complicated and unreliable anyway */ +} + + static void crc32_sigill(void) { /* CRC32W W0, W0, W1 */ @@ -82,6 +88,18 @@ static void f8fma_sigill(void) asm volatile(".inst 0xec0fc00"); } +static void f8mm4_sigill(void) +{ + /* FMMLA V0.4SH, V0.16B, V0.16B */ + asm volatile(".inst 0x6e00ec00"); +} + +static void f8mm8_sigill(void) +{ + /* FMMLA V0.4S, V0.16B, V0.16B */ + asm volatile(".inst 0x6e80ec00"); +} + static void faminmax_sigill(void) { /* FAMIN V0.4H, V0.4H, V0.4H */ @@ -98,6 +116,12 @@ static void fpmr_sigill(void) asm volatile("mrs x0, S3_3_C4_C4_2" : : : "x0"); } +static void fprcvt_sigill(void) +{ + /* FCVTAS S0, H0 */ + asm volatile(".inst 0x1efa0000"); +} + static void gcs_sigill(void) { unsigned long *gcspr; @@ -226,6 +250,42 @@ static void sme2p1_sigill(void) asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); } +static void sme2p2_sigill(void) +{ + /* SMSTART SM */ + asm volatile("msr S0_3_C4_C3_3, xzr" : : : ); + + /* UXTB Z0.D, P0/Z, Z0.D */ + asm volatile(".inst 0x4c1a000" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void sme_aes_sigill(void) +{ + /* SMSTART SM */ + asm volatile("msr S0_3_C4_C3_3, xzr" : : : ); + + /* AESD z0.b, z0.b, z0.b */ + asm volatile(".inst 0x4522e400" : : : "z0"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void sme_sbitperm_sigill(void) +{ + /* SMSTART SM */ + asm volatile("msr S0_3_C4_C3_3, xzr" : : : ); + + /* BDEP Z0.B, Z0.B, Z0.B */ + asm volatile(".inst 0x4500b400" : : : "z0"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + static void smei16i32_sigill(void) { /* SMSTART */ @@ -339,8 +399,44 @@ static void smesf8fma_sigill(void) /* SMSTART */ asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); - /* FMLALB V0.8H, V0.16B, V0.16B */ - asm volatile(".inst 0xec0fc00"); + /* FMLALB Z0.8H, Z0.B, Z0.B */ + asm volatile(".inst 0x64205000"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesfexpa_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FEXPA Z0.D, Z0.D */ + asm volatile(".inst 0x04e0b800"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesmop4_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* SMOP4A ZA0.S, Z0.B, { Z0.B - Z1.B } */ + asm volatile(".inst 0x80108000"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smestmop_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* STMOPA ZA0.S, { Z0.H - Z1.H }, Z0.H, Z20[0] */ + asm volatile(".inst 0x80408008"); /* SMSTOP */ asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); @@ -364,18 +460,42 @@ static void sve2p1_sigill(void) asm volatile(".inst 0x65000000" : : : "z0"); } +static void sve2p2_sigill(void) +{ + /* NOT Z0.D, P0/Z, Z0.D */ + asm volatile(".inst 0x4cea000" : : : "z0"); +} + static void sveaes_sigill(void) { /* AESD z0.b, z0.b, z0.b */ asm volatile(".inst 0x4522e400" : : : "z0"); } +static void sveaes2_sigill(void) +{ + /* AESD {Z0.B - Z1.B }, { Z0.B - Z1.B }, Z0.Q */ + asm volatile(".inst 0x4522ec00" : : : "z0"); +} + static void sveb16b16_sigill(void) { /* BFADD Z0.H, Z0.H, Z0.H */ asm volatile(".inst 0x65000000" : : : ); } +static void svebfscale_sigill(void) +{ + /* BFSCALE Z0.H, P0/M, Z0.H, Z0.H */ + asm volatile(".inst 0x65098000" : : : "z0"); +} + +static void svef16mm_sigill(void) +{ + /* FMMLA Z0.S, Z0.H, Z0.H */ + asm volatile(".inst 0x6420e400"); +} + static void svepmull_sigill(void) { /* PMULLB Z0.Q, Z0.D, Z0.D */ @@ -394,6 +514,12 @@ static void svesha3_sigill(void) asm volatile(".inst 0x4203800" : : : "z0"); } +static void sveeltperm_sigill(void) +{ + /* COMPACT Z0.B, P0, Z0.B */ + asm volatile(".inst 0x5218000" : : : "x0"); +} + static void svesm4_sigill(void) { /* SM4E Z0.S, Z0.S, Z0.S */ @@ -469,6 +595,13 @@ static const struct hwcap_data { .cpuinfo = "aes", .sigill_fn = aes_sigill, }, + { + .name = "CMPBR", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_CMPBR, + .cpuinfo = "cmpbr", + .sigill_fn = cmpbr_sigill, + }, { .name = "CRC32", .at_hwcap = AT_HWCAP, @@ -523,6 +656,20 @@ static const struct hwcap_data { .cpuinfo = "f8fma", .sigill_fn = f8fma_sigill, }, + { + .name = "F8MM8", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_F8MM8, + .cpuinfo = "f8mm8", + .sigill_fn = f8mm8_sigill, + }, + { + .name = "F8MM4", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_F8MM4, + .cpuinfo = "f8mm4", + .sigill_fn = f8mm4_sigill, + }, { .name = "FAMINMAX", .at_hwcap = AT_HWCAP2, @@ -545,6 +692,13 @@ static const struct hwcap_data { .sigill_fn = fpmr_sigill, .sigill_reliable = true, }, + { + .name = "FPRCVT", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_FPRCVT, + .cpuinfo = "fprcvt", + .sigill_fn = fprcvt_sigill, + }, { .name = "GCS", .at_hwcap = AT_HWCAP, @@ -691,6 +845,20 @@ static const struct hwcap_data { .cpuinfo = "sme2p1", .sigill_fn = sme2p1_sigill, }, + { + .name = "SME 2.2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME2P2, + .cpuinfo = "sme2p2", + .sigill_fn = sme2p2_sigill, + }, + { + .name = "SME AES", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_AES, + .cpuinfo = "smeaes", + .sigill_fn = sme_aes_sigill, + }, { .name = "SME I16I32", .at_hwcap = AT_HWCAP2, @@ -740,6 +908,13 @@ static const struct hwcap_data { .cpuinfo = "smelutv2", .sigill_fn = smelutv2_sigill, }, + { + .name = "SME SBITPERM", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_SBITPERM, + .cpuinfo = "smesbitperm", + .sigill_fn = sme_sbitperm_sigill, + }, { .name = "SME SF8FMA", .at_hwcap = AT_HWCAP2, @@ -761,6 +936,27 @@ static const struct hwcap_data { .cpuinfo = "smesf8dp4", .sigill_fn = smesf8dp4_sigill, }, + { + .name = "SME SFEXPA", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_SFEXPA, + .cpuinfo = "smesfexpa", + .sigill_fn = smesfexpa_sigill, + }, + { + .name = "SME SMOP4", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_SMOP4, + .cpuinfo = "smesmop4", + .sigill_fn = smesmop4_sigill, + }, + { + .name = "SME STMOP", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_STMOP, + .cpuinfo = "smestmop", + .sigill_fn = smestmop_sigill, + }, { .name = "SVE", .at_hwcap = AT_HWCAP, @@ -783,6 +979,13 @@ static const struct hwcap_data { .cpuinfo = "sve2p1", .sigill_fn = sve2p1_sigill, }, + { + .name = "SVE 2.2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE2P2, + .cpuinfo = "sve2p2", + .sigill_fn = sve2p2_sigill, + }, { .name = "SVE AES", .at_hwcap = AT_HWCAP2, @@ -790,6 +993,34 @@ static const struct hwcap_data { .cpuinfo = "sveaes", .sigill_fn = sveaes_sigill, }, + { + .name = "SVE AES2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_AES2, + .cpuinfo = "sveaes2", + .sigill_fn = sveaes2_sigill, + }, + { + .name = "SVE BFSCALE", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_BFSCALE, + .cpuinfo = "svebfscale", + .sigill_fn = svebfscale_sigill, + }, + { + .name = "SVE ELTPERM", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_ELTPERM, + .cpuinfo = "sveeltperm", + .sigill_fn = sveeltperm_sigill, + }, + { + .name = "SVE F16MM", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_F16MM, + .cpuinfo = "svef16mm", + .sigill_fn = svef16mm_sigill, + }, { .name = "SVE2 B16B16", .at_hwcap = AT_HWCAP2, diff --git a/tools/testing/selftests/arm64/fp/kernel-test.c b/tools/testing/selftests/arm64/fp/kernel-test.c index 859345379044..348e8bef62c7 100644 --- a/tools/testing/selftests/arm64/fp/kernel-test.c +++ b/tools/testing/selftests/arm64/fp/kernel-test.c @@ -46,8 +46,7 @@ static void handle_kick_signal(int sig, siginfo_t *info, void *context) } static char *drivers[] = { - "crct10dif-arm64-ce", - /* "crct10dif-arm64-neon", - Same priority as generic */ + "crct10dif-arm64", "sha1-ce", "sha224-arm64", "sha224-arm64-neon", diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index e9c377001f93..e2a2c46c008b 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -18,7 +18,6 @@ feature urandom_read test_sockmap test_lirc_mode2_user -test_flow_dissector flow_dissector_load test_tcpnotify_user test_libbpf diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 7eeb3cbe18c7..87551628e112 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -41,7 +41,7 @@ srctree := $(patsubst %/,%,$(dir $(srctree))) srctree := $(patsubst %/,%,$(dir $(srctree))) endif -CFLAGS += -g $(OPT_FLAGS) -rdynamic \ +CFLAGS += -g $(OPT_FLAGS) -rdynamic -std=gnu11 \ -Wall -Werror -fno-omit-frame-pointer \ $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ @@ -54,21 +54,6 @@ PCAP_LIBS := $(shell $(PKG_CONFIG) --libs libpcap 2>/dev/null) LDLIBS += $(PCAP_LIBS) CFLAGS += $(PCAP_CFLAGS) -# The following tests perform type punning and they may break strict -# aliasing rules, which are exploited by both GCC and clang by default -# while optimizing. This can lead to broken programs. -progs/bind4_prog.c-CFLAGS := -fno-strict-aliasing -progs/bind6_prog.c-CFLAGS := -fno-strict-aliasing -progs/dynptr_fail.c-CFLAGS := -fno-strict-aliasing -progs/linked_list_fail.c-CFLAGS := -fno-strict-aliasing -progs/map_kptr_fail.c-CFLAGS := -fno-strict-aliasing -progs/syscall.c-CFLAGS := -fno-strict-aliasing -progs/test_pkt_md_access.c-CFLAGS := -fno-strict-aliasing -progs/test_sk_lookup.c-CFLAGS := -fno-strict-aliasing -progs/timer_crash.c-CFLAGS := -fno-strict-aliasing -progs/test_global_func9.c-CFLAGS := -fno-strict-aliasing -progs/verifier_nocsr.c-CFLAGS := -fno-strict-aliasing - # Some utility functions use LLVM libraries jit_disasm_helpers.c-CFLAGS = $(LLVM_CFLAGS) @@ -103,18 +88,6 @@ progs/btf_dump_test_case_packing.c-bpf_gcc-CFLAGS := -Wno-error progs/btf_dump_test_case_padding.c-bpf_gcc-CFLAGS := -Wno-error progs/btf_dump_test_case_syntax.c-bpf_gcc-CFLAGS := -Wno-error -# The following tests do type-punning, via the __imm_insn macro, from -# `struct bpf_insn' to long and then uses the value. This triggers an -# "is used uninitialized" warning in GCC due to strict-aliasing -# rules. -progs/verifier_ref_tracking.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_unpriv.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_cgroup_storage.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_ld_ind.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_map_ret_val.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_spill_fill.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_subprog_precision.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_uninit.c-bpf_gcc-CFLAGS := -fno-strict-aliasing endif ifneq ($(CLANG_CPUV4),) @@ -127,13 +100,10 @@ TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c) # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ - test_xdp_redirect.sh \ test_xdp_redirect_multi.sh \ - test_xdp_meta.sh \ test_tunnel.sh \ test_lwt_seg6local.sh \ test_lirc_mode2.sh \ - test_flow_dissector.sh \ test_xdp_vlan_mode_generic.sh \ test_xdp_vlan_mode_native.sh \ test_lwt_ip_encap.sh \ @@ -151,17 +121,16 @@ TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh ima_setup.sh verify_sig_setup.sh \ test_xdp_vlan.sh test_bpftool.py +TEST_KMODS := bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ + bpf_test_modorder_y.ko +TEST_KMOD_TARGETS = $(addprefix $(OUTPUT)/,$(TEST_KMODS)) + # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = \ bench \ - bpf_testmod.ko \ - bpf_test_modorder_x.ko \ - bpf_test_modorder_y.ko \ - bpf_test_no_cfi.ko \ flow_dissector_load \ runqslower \ test_cpp \ - test_flow_dissector \ test_lirc_mode2_user \ veristat \ xdp_features \ @@ -184,8 +153,9 @@ override define CLEAN $(Q)$(RM) -r $(TEST_GEN_PROGS) $(Q)$(RM) -r $(TEST_GEN_PROGS_EXTENDED) $(Q)$(RM) -r $(TEST_GEN_FILES) + $(Q)$(RM) -r $(TEST_KMODS) $(Q)$(RM) -r $(EXTRA_CLEAN) - $(Q)$(MAKE) -C bpf_testmod clean + $(Q)$(MAKE) -C test_kmods clean $(Q)$(MAKE) docs-clean endef @@ -203,9 +173,9 @@ ifeq ($(shell expr $(MAKE_VERSION) \>= 4.4), 1) $(let OUTPUT,$(OUTPUT)/,\ $(eval include ../../../build/Makefile.feature)) else -OUTPUT := $(OUTPUT)/ +override OUTPUT := $(OUTPUT)/ $(eval include ../../../build/Makefile.feature) -OUTPUT := $(patsubst %/,%,$(OUTPUT)) +override OUTPUT := $(patsubst %/,%,$(OUTPUT)) endif endif @@ -251,7 +221,7 @@ endif # to build individual tests. # NOTE: Semicolon at the end is critical to override lib.mk's default static # rule for binaries. -$(notdir $(TEST_GEN_PROGS) \ +$(notdir $(TEST_GEN_PROGS) $(TEST_KMODS) \ $(TEST_GEN_PROGS_EXTENDED)): %: $(OUTPUT)/% ; # sort removes libbpf duplicates when not cross-building @@ -305,37 +275,19 @@ $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $< -o $@ \ $(shell $(PKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto) -$(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch]) - $(call msg,MOD,,$@) - $(Q)$(RM) bpf_testmod/bpf_testmod.ko # force re-compilation - $(Q)$(MAKE) $(submake_extras) -C bpf_testmod \ - RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ +# This should really be a grouped target, but make versions before 4.3 don't +# support that for regular rules. However, pattern matching rules are implicitly +# treated as grouped even with older versions of make, so as a workaround, the +# subst() turns the rule into a pattern matching rule +$(addprefix test_kmods/,$(subst .ko,%ko,$(TEST_KMODS))): $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard test_kmods/Makefile test_kmods/*.[ch]) + $(Q)$(RM) test_kmods/*.ko test_kmods/*.mod.o # force re-compilation + $(Q)$(MAKE) $(submake_extras) -C test_kmods \ + RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ EXTRA_CFLAGS='' EXTRA_LDFLAGS='' - $(Q)cp bpf_testmod/bpf_testmod.ko $@ -$(OUTPUT)/bpf_test_no_cfi.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_no_cfi/Makefile bpf_test_no_cfi/*.[ch]) +$(TEST_KMOD_TARGETS): $(addprefix test_kmods/,$(TEST_KMODS)) $(call msg,MOD,,$@) - $(Q)$(RM) bpf_test_no_cfi/bpf_test_no_cfi.ko # force re-compilation - $(Q)$(MAKE) $(submake_extras) -C bpf_test_no_cfi \ - RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ - EXTRA_CFLAGS='' EXTRA_LDFLAGS='' - $(Q)cp bpf_test_no_cfi/bpf_test_no_cfi.ko $@ - -$(OUTPUT)/bpf_test_modorder_x.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_modorder_x/Makefile bpf_test_modorder_x/*.[ch]) - $(call msg,MOD,,$@) - $(Q)$(RM) bpf_test_modorder_x/bpf_test_modorder_x.ko # force re-compilation - $(Q)$(MAKE) $(submake_extras) -C bpf_test_modorder_x \ - RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ - EXTRA_CFLAGS='' EXTRA_LDFLAGS='' - $(Q)cp bpf_test_modorder_x/bpf_test_modorder_x.ko $@ - -$(OUTPUT)/bpf_test_modorder_y.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_modorder_y/Makefile bpf_test_modorder_y/*.[ch]) - $(call msg,MOD,,$@) - $(Q)$(RM) bpf_test_modorder_y/bpf_test_modorder_y.ko # force re-compilation - $(Q)$(MAKE) $(submake_extras) -C bpf_test_modorder_y \ - RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ - EXTRA_CFLAGS='' EXTRA_LDFLAGS='' - $(Q)cp bpf_test_modorder_y/bpf_test_modorder_y.ko $@ + $(Q)cp test_kmods/$(@F) $@ DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool @@ -480,10 +432,10 @@ $(shell $(1) $(2) -dM -E - </dev/null | grep -E 'MIPS(EL|EB)|_MIPS_SZ(PTR|LONG) endef # Determine target endianness. -IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ +IS_LITTLE_ENDIAN := $(shell $(CC) -dM -E - </dev/null | \ grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__') -MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) -BPF_TARGET_ENDIAN=$(if $(IS_LITTLE_ENDIAN),--target=bpfel,--target=bpfeb) +MENDIAN:=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) +BPF_TARGET_ENDIAN:=$(if $(IS_LITTLE_ENDIAN),--target=bpfel,--target=bpfeb) ifneq ($(CROSS_COMPILE),) CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) @@ -493,6 +445,8 @@ CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \ -I$(abspath $(OUTPUT)/../usr/include) \ + -std=gnu11 \ + -fno-strict-aliasing \ -Wno-compare-distinct-pointer-types # TODO: enable me -Wsign-compare @@ -760,14 +714,12 @@ TRUNNER_EXTRA_SOURCES := test_progs.c \ json_writer.c \ flow_dissector_load.h \ ip_check_defrag_frags.h -TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ - $(OUTPUT)/bpf_test_no_cfi.ko \ - $(OUTPUT)/bpf_test_modorder_x.ko \ - $(OUTPUT)/bpf_test_modorder_y.ko \ +TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \ $(OUTPUT)/liburandom_read.so \ $(OUTPUT)/xdp_synproxy \ $(OUTPUT)/sign-file \ $(OUTPUT)/uprobe_multi \ + $(TEST_KMOD_TARGETS) \ ima_setup.sh \ verify_sig_setup.sh \ $(wildcard progs/btf_dump_test_case_*.c) \ @@ -834,9 +786,12 @@ $(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ # Make sure we are able to include and link libbpf against c++. +CXXFLAGS += $(CFLAGS) +CXXFLAGS := $(subst -D_GNU_SOURCE=,,$(CXXFLAGS)) +CXXFLAGS := $(subst -std=gnu11,-std=gnu++11,$(CXXFLAGS)) $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) - $(Q)$(CXX) $(subst -D_GNU_SOURCE=,,$(CFLAGS)) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ + $(Q)$(CXX) $(CXXFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ # Benchmark runner $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ) @@ -894,12 +849,9 @@ $(OUTPUT)/uprobe_multi: uprobe_multi.c uprobe_multi.ld EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ - feature bpftool \ + feature bpftool $(TEST_KMOD_TARGETS) \ $(addprefix $(OUTPUT)/,*.o *.d *.skel.h *.lskel.h *.subskel.h \ - no_alu32 cpuv4 bpf_gcc bpf_testmod.ko \ - bpf_test_no_cfi.ko \ - bpf_test_modorder_x.ko \ - bpf_test_modorder_y.ko \ + no_alu32 cpuv4 bpf_gcc \ liburandom_read.so) \ $(OUTPUT)/FEATURE-DUMP.selftests diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile b/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile deleted file mode 100644 index 40b25b98ad1b..000000000000 --- a/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile +++ /dev/null @@ -1,19 +0,0 @@ -BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) - -ifeq ($(V),1) -Q = -else -Q = @ -endif - -MODULES = bpf_test_modorder_x.ko - -obj-m += bpf_test_modorder_x.o - -all: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules - -clean: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean - diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile b/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile deleted file mode 100644 index 52c3ab9d84e2..000000000000 --- a/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile +++ /dev/null @@ -1,19 +0,0 @@ -BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) - -ifeq ($(V),1) -Q = -else -Q = @ -endif - -MODULES = bpf_test_modorder_y.ko - -obj-m += bpf_test_modorder_y.o - -all: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules - -clean: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean - diff --git a/tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile b/tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile deleted file mode 100644 index ed5143b79edf..000000000000 --- a/tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile +++ /dev/null @@ -1,19 +0,0 @@ -BPF_TEST_NO_CFI_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(BPF_TEST_NO_CFI_DIR)/../../../../..) - -ifeq ($(V),1) -Q = -else -Q = @ -endif - -MODULES = bpf_test_no_cfi.ko - -obj-m += bpf_test_no_cfi.o - -all: - +$(Q)make -C $(KDIR) M=$(BPF_TEST_NO_CFI_DIR) modules - -clean: - +$(Q)make -C $(KDIR) M=$(BPF_TEST_NO_CFI_DIR) clean - diff --git a/tools/testing/selftests/bpf/bpf_testmod/Makefile b/tools/testing/selftests/bpf/bpf_testmod/Makefile deleted file mode 100644 index 15cb36c4483a..000000000000 --- a/tools/testing/selftests/bpf/bpf_testmod/Makefile +++ /dev/null @@ -1,20 +0,0 @@ -BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) - -ifeq ($(V),1) -Q = -else -Q = @ -endif - -MODULES = bpf_testmod.ko - -obj-m += bpf_testmod.o -CFLAGS_bpf_testmod.o = -I$(src) - -all: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules - -clean: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean - diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 4ca84c8d9116..c378d5d07e02 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -58,6 +58,7 @@ CONFIG_MPLS=y CONFIG_MPLS_IPTUNNEL=y CONFIG_MPLS_ROUTING=y CONFIG_MPTCP=y +CONFIG_NET_ACT_GACT=y CONFIG_NET_ACT_SKBMOD=y CONFIG_NET_CLS=y CONFIG_NET_CLS_ACT=y diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 27784946b01b..80844a5fb1fe 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -21,7 +21,7 @@ #include <linux/limits.h> #include <linux/ip.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <netinet/tcp.h> #include <net/if.h> diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 5764155b6d25..ebec8a8d6f81 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -14,6 +14,7 @@ typedef __u16 __sum16; #include <linux/sockios.h> #include <linux/err.h> #include <netinet/tcp.h> +#include <netinet/udp.h> #include <bpf/bpf_endian.h> #include <net/if.h> @@ -105,6 +106,45 @@ static __u16 csum_fold(__u32 csum) return (__u16)~csum; } +static __wsum csum_partial(const void *buf, int len, __wsum sum) +{ + __u16 *p = (__u16 *)buf; + int num_u16 = len >> 1; + int i; + + for (i = 0; i < num_u16; i++) + sum += p[i]; + + return sum; +} + +static inline __sum16 build_ip_csum(struct iphdr *iph) +{ + __u32 sum = 0; + __u16 *p; + + iph->check = 0; + p = (void *)iph; + sum = csum_partial(p, iph->ihl << 2, 0); + + return csum_fold(sum); +} + +/** + * csum_tcpudp_magic - compute IP pseudo-header checksum + * + * Compute the IPv4 pseudo header checksum. The helper can take a + * accumulated sum from the transport layer to accumulate it and directly + * return the transport layer + * + * @saddr: IP source address + * @daddr: IP dest address + * @len: IP data size + * @proto: transport layer protocol + * @csum: The accumulated partial sum to add to the computation + * + * Returns the folded sum + */ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __wsum csum) @@ -120,6 +160,21 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, return csum_fold((__u32)s); } +/** + * csum_ipv6_magic - compute IPv6 pseudo-header checksum + * + * Compute the ipv6 pseudo header checksum. The helper can take a + * accumulated sum from the transport layer to accumulate it and directly + * return the transport layer + * + * @saddr: IPv6 source address + * @daddr: IPv6 dest address + * @len: IPv6 data size + * @proto: transport layer protocol + * @csum: The accumulated partial sum to add to the computation + * + * Returns the folded sum + */ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, @@ -139,6 +194,47 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, return csum_fold((__u32)s); } +/** + * build_udp_v4_csum - compute UDP checksum for UDP over IPv4 + * + * Compute the checksum to embed in UDP header, composed of the sum of IP + * pseudo-header checksum, UDP header checksum and UDP data checksum + * @iph IP header + * @udph UDP header, which must be immediately followed by UDP data + * + * Returns the total checksum + */ + +static inline __sum16 build_udp_v4_csum(const struct iphdr *iph, + const struct udphdr *udph) +{ + unsigned long sum; + + sum = csum_partial(udph, ntohs(udph->len), 0); + return csum_tcpudp_magic(iph->saddr, iph->daddr, ntohs(udph->len), + IPPROTO_UDP, sum); +} + +/** + * build_udp_v6_csum - compute UDP checksum for UDP over IPv6 + * + * Compute the checksum to embed in UDP header, composed of the sum of IPv6 + * pseudo-header checksum, UDP header checksum and UDP data checksum + * @ip6h IPv6 header + * @udph UDP header, which must be immediately followed by UDP data + * + * Returns the total checksum + */ +static inline __sum16 build_udp_v6_csum(const struct ipv6hdr *ip6h, + const struct udphdr *udph) +{ + unsigned long sum; + + sum = csum_partial(udph, ntohs(udph->len), 0); + return csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ntohs(udph->len), + IPPROTO_UDP, sum); +} + struct tmonitor_ctx; #ifdef TRAFFIC_MONITOR diff --git a/tools/testing/selftests/bpf/prog_tests/btf_distill.c b/tools/testing/selftests/bpf/prog_tests/btf_distill.c index ca84726d5ac1..fb67ae195a73 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_distill.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_distill.c @@ -385,7 +385,7 @@ static void test_distilled_base_missing_err(void) "[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED"); btf5 = btf__new_empty(); if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf")) - return; + goto cleanup; btf__add_int(btf5, "int", 4, BTF_INT_SIGNED); /* [1] int */ VALIDATE_RAW_BTF( btf5, @@ -478,7 +478,7 @@ static void test_distilled_base_multi_err2(void) "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED"); btf5 = btf__new_empty(); if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf")) - return; + goto cleanup; btf__add_int(btf5, "int", 4, BTF_INT_SIGNED); /* [1] int */ btf__add_int(btf5, "int", 4, BTF_INT_SIGNED); /* [2] int */ VALIDATE_RAW_BTF( @@ -601,6 +601,76 @@ cleanup: btf__free(base); } +/* If a needed composite type, which is the member of composite type + * in the split BTF, has a different size in the base BTF we wish to + * relocate with, btf__relocate() should error out. + */ +static void test_distilled_base_embedded_err(void) +{ + struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL, *btf5 = NULL; + + btf1 = btf__new_empty(); + if (!ASSERT_OK_PTR(btf1, "empty_main_btf")) + return; + + btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */ + btf__add_struct(btf1, "s1", 4); /* [2] struct s1 { */ + btf__add_field(btf1, "f1", 1, 0, 0); /* int f1; */ + /* } */ + VALIDATE_RAW_BTF( + btf1, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's1' size=4 vlen=1\n" + "\t'f1' type_id=1 bits_offset=0"); + + btf2 = btf__new_empty_split(btf1); + if (!ASSERT_OK_PTR(btf2, "empty_split_btf")) + goto cleanup; + + btf__add_struct(btf2, "with_embedded", 8); /* [3] struct with_embedded { */ + btf__add_field(btf2, "e1", 2, 0, 0); /* struct s1 e1; */ + /* } */ + + VALIDATE_RAW_BTF( + btf2, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's1' size=4 vlen=1\n" + "\t'f1' type_id=1 bits_offset=0", + "[3] STRUCT 'with_embedded' size=8 vlen=1\n" + "\t'e1' type_id=2 bits_offset=0"); + + if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4), + "distilled_base") || + !ASSERT_OK_PTR(btf3, "distilled_base") || + !ASSERT_OK_PTR(btf4, "distilled_split") || + !ASSERT_EQ(2, btf__type_cnt(btf3), "distilled_base_type_cnt")) + goto cleanup; + + VALIDATE_RAW_BTF( + btf4, + "[1] STRUCT 's1' size=4 vlen=0", + "[2] STRUCT 'with_embedded' size=8 vlen=1\n" + "\t'e1' type_id=1 bits_offset=0"); + + btf5 = btf__new_empty(); + if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf")) + goto cleanup; + + btf__add_int(btf5, "int", 4, BTF_INT_SIGNED); /* [1] int */ + /* struct with the same name but different size */ + btf__add_struct(btf5, "s1", 8); /* [2] struct s1 { */ + btf__add_field(btf5, "f1", 1, 0, 0); /* int f1; */ + /* } */ + + ASSERT_EQ(btf__relocate(btf4, btf5), -EINVAL, "relocate_split"); +cleanup: + btf__free(btf5); + btf__free(btf4); + btf__free(btf3); + btf__free(btf2); + btf__free(btf1); +} + void test_btf_distill(void) { if (test__start_subtest("distilled_base")) @@ -613,6 +683,8 @@ void test_btf_distill(void) test_distilled_base_multi_err(); if (test__start_subtest("distilled_base_multi_err2")) test_distilled_base_multi_err2(); + if (test__start_subtest("distilled_base_embedded_err")) + test_distilled_base_embedded_err(); if (test__start_subtest("distilled_base_vmlinux")) test_distilled_base_vmlinux(); if (test__start_subtest("distilled_endianness")) diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c new file mode 100644 index 000000000000..e1a90c10db8c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "cgroup_skb_direct_packet_access.skel.h" + +void test_cgroup_skb_prog_run_direct_packet_access(void) +{ + int err; + struct cgroup_skb_direct_packet_access *skel; + char test_skb[64] = {}; + + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = test_skb, + .data_size_in = sizeof(test_skb), + ); + + skel = cgroup_skb_direct_packet_access__open_and_load(); + if (!ASSERT_OK_PTR(skel, "cgroup_skb_direct_packet_access__open_and_load")) + return; + + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.direct_packet_access), &topts); + ASSERT_OK(err, "bpf_prog_test_run_opts err"); + ASSERT_EQ(topts.retval, 1, "retval"); + + ASSERT_NEQ(skel->bss->data_end, 0, "data_end"); + + cgroup_skb_direct_packet_access__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 1c682550e0e7..e10ea92c3fe2 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -2,7 +2,7 @@ #define _GNU_SOURCE #include <test_progs.h> #include "progs/core_reloc_types.h" -#include "bpf_testmod/bpf_testmod.h" +#include "test_kmods/bpf_testmod.h" #include <linux/limits.h> #include <sys/mman.h> #include <sys/syscall.h> diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c new file mode 100644 index 000000000000..a1d52e73fb16 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c @@ -0,0 +1,441 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include <linux/btf.h> +#include <bpf/bpf.h> + +#include "../test_btf.h" + +static inline int new_map(void) +{ + const char *name = NULL; + __u32 max_entries = 1; + __u32 value_size = 8; + __u32 key_size = 4; + + return bpf_map_create(BPF_MAP_TYPE_ARRAY, name, + key_size, value_size, + max_entries, NULL); +} + +static int new_btf(void) +{ + struct btf_blob { + struct btf_header btf_hdr; + __u32 types[8]; + __u32 str; + } raw_btf = { + .btf_hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(raw_btf.types), + .str_off = offsetof(struct btf_blob, str) - offsetof(struct btf_blob, types), + .str_len = sizeof(raw_btf.str), + }, + .types = { + /* long */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), /* [1] */ + /* unsigned long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + }, + }; + + return bpf_btf_load(&raw_btf, sizeof(raw_btf), NULL); +} + +#define Close(FD) do { \ + if ((FD) >= 0) { \ + close(FD); \ + FD = -1; \ + } \ +} while(0) + +static bool map_exists(__u32 id) +{ + int fd; + + fd = bpf_map_get_fd_by_id(id); + if (fd >= 0) { + close(fd); + return true; + } + return false; +} + +static bool btf_exists(__u32 id) +{ + int fd; + + fd = bpf_btf_get_fd_by_id(id); + if (fd >= 0) { + close(fd); + return true; + } + return false; +} + +static inline int bpf_prog_get_map_ids(int prog_fd, __u32 *nr_map_ids, __u32 *map_ids) +{ + __u32 len = sizeof(struct bpf_prog_info); + struct bpf_prog_info info; + int err; + + memset(&info, 0, len); + info.nr_map_ids = *nr_map_ids, + info.map_ids = ptr_to_u64(map_ids), + + err = bpf_prog_get_info_by_fd(prog_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) + return -1; + + *nr_map_ids = info.nr_map_ids; + + return 0; +} + +static int __load_test_prog(int map_fd, const int *fd_array, int fd_array_cnt) +{ + /* A trivial program which uses one map */ + struct bpf_insn insns[] = { + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts); + + opts.fd_array = fd_array; + opts.fd_array_cnt = fd_array_cnt; + + return bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, ARRAY_SIZE(insns), &opts); +} + +static int load_test_prog(const int *fd_array, int fd_array_cnt) +{ + int map_fd; + int ret; + + map_fd = new_map(); + if (!ASSERT_GE(map_fd, 0, "new_map")) + return map_fd; + + ret = __load_test_prog(map_fd, fd_array, fd_array_cnt); + close(map_fd); + return ret; +} + +static bool check_expected_map_ids(int prog_fd, int expected, __u32 *map_ids, __u32 *nr_map_ids) +{ + int err; + + err = bpf_prog_get_map_ids(prog_fd, nr_map_ids, map_ids); + if (!ASSERT_OK(err, "bpf_prog_get_map_ids")) + return false; + if (!ASSERT_EQ(*nr_map_ids, expected, "unexpected nr_map_ids")) + return false; + + return true; +} + +/* + * Load a program, which uses one map. No fd_array maps are present. + * On return only one map is expected to be bound to prog. + */ +static void check_fd_array_cnt__no_fd_array(void) +{ + __u32 map_ids[16]; + __u32 nr_map_ids; + int prog_fd = -1; + + prog_fd = load_test_prog(NULL, 0); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + return; + nr_map_ids = ARRAY_SIZE(map_ids); + check_expected_map_ids(prog_fd, 1, map_ids, &nr_map_ids); + close(prog_fd); +} + +/* + * Load a program, which uses one map, and pass two extra, non-equal, maps in + * fd_array with fd_array_cnt=2. On return three maps are expected to be bound + * to the program. + */ +static void check_fd_array_cnt__fd_array_ok(void) +{ + int extra_fds[2] = { -1, -1 }; + __u32 map_ids[16]; + __u32 nr_map_ids; + int prog_fd = -1; + + extra_fds[0] = new_map(); + if (!ASSERT_GE(extra_fds[0], 0, "new_map")) + goto cleanup; + extra_fds[1] = new_map(); + if (!ASSERT_GE(extra_fds[1], 0, "new_map")) + goto cleanup; + prog_fd = load_test_prog(extra_fds, 2); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + goto cleanup; + nr_map_ids = ARRAY_SIZE(map_ids); + if (!check_expected_map_ids(prog_fd, 3, map_ids, &nr_map_ids)) + goto cleanup; + + /* maps should still exist when original file descriptors are closed */ + Close(extra_fds[0]); + Close(extra_fds[1]); + if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map_ids[0] should exist")) + goto cleanup; + if (!ASSERT_EQ(map_exists(map_ids[1]), true, "map_ids[1] should exist")) + goto cleanup; + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[1]); + Close(extra_fds[0]); + Close(prog_fd); +} + +/* + * Load a program with a few extra maps duplicated in the fd_array. + * After the load maps should only be referenced once. + */ +static void check_fd_array_cnt__duplicated_maps(void) +{ + int extra_fds[4] = { -1, -1, -1, -1 }; + __u32 map_ids[16]; + __u32 nr_map_ids; + int prog_fd = -1; + + extra_fds[0] = extra_fds[2] = new_map(); + if (!ASSERT_GE(extra_fds[0], 0, "new_map")) + goto cleanup; + extra_fds[1] = extra_fds[3] = new_map(); + if (!ASSERT_GE(extra_fds[1], 0, "new_map")) + goto cleanup; + prog_fd = load_test_prog(extra_fds, 4); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + goto cleanup; + nr_map_ids = ARRAY_SIZE(map_ids); + if (!check_expected_map_ids(prog_fd, 3, map_ids, &nr_map_ids)) + goto cleanup; + + /* maps should still exist when original file descriptors are closed */ + Close(extra_fds[0]); + Close(extra_fds[1]); + if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map should exist")) + goto cleanup; + if (!ASSERT_EQ(map_exists(map_ids[1]), true, "map should exist")) + goto cleanup; + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[1]); + Close(extra_fds[0]); + Close(prog_fd); +} + +/* + * Check that if maps which are referenced by a program are + * passed in fd_array, then they will be referenced only once + */ +static void check_fd_array_cnt__referenced_maps_in_fd_array(void) +{ + int extra_fds[1] = { -1 }; + __u32 map_ids[16]; + __u32 nr_map_ids; + int prog_fd = -1; + + extra_fds[0] = new_map(); + if (!ASSERT_GE(extra_fds[0], 0, "new_map")) + goto cleanup; + prog_fd = __load_test_prog(extra_fds[0], extra_fds, 1); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + goto cleanup; + nr_map_ids = ARRAY_SIZE(map_ids); + if (!check_expected_map_ids(prog_fd, 1, map_ids, &nr_map_ids)) + goto cleanup; + + /* map should still exist when original file descriptor is closed */ + Close(extra_fds[0]); + if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map should exist")) + goto cleanup; + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[0]); + Close(prog_fd); +} + +static int get_btf_id_by_fd(int btf_fd, __u32 *id) +{ + struct bpf_btf_info info; + __u32 info_len = sizeof(info); + int err; + + memset(&info, 0, info_len); + err = bpf_btf_get_info_by_fd(btf_fd, &info, &info_len); + if (err) + return err; + if (id) + *id = info.id; + return 0; +} + +/* + * Check that fd_array operates properly for btfs. Namely, to check that + * passing a btf fd in fd_array increases its reference count, do the + * following: + * 1) Create a new btf, it's referenced only by a file descriptor, so refcnt=1 + * 2) Load a BPF prog with fd_array[0] = btf_fd; now btf's refcnt=2 + * 3) Close the btf_fd, now refcnt=1 + * Wait and check that BTF stil exists. + */ +static void check_fd_array_cnt__referenced_btfs(void) +{ + int extra_fds[1] = { -1 }; + int prog_fd = -1; + __u32 btf_id; + int tries; + int err; + + extra_fds[0] = new_btf(); + if (!ASSERT_GE(extra_fds[0], 0, "new_btf")) + goto cleanup; + prog_fd = load_test_prog(extra_fds, 1); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + goto cleanup; + + /* btf should still exist when original file descriptor is closed */ + err = get_btf_id_by_fd(extra_fds[0], &btf_id); + if (!ASSERT_GE(err, 0, "get_btf_id_by_fd")) + goto cleanup; + + Close(extra_fds[0]); + + if (!ASSERT_GE(kern_sync_rcu(), 0, "kern_sync_rcu 1")) + goto cleanup; + + if (!ASSERT_EQ(btf_exists(btf_id), true, "btf should exist")) + goto cleanup; + + Close(prog_fd); + + /* The program is freed by a workqueue, so no reliable + * way to sync, so just wait a bit (max ~1 second). */ + for (tries = 100; tries >= 0; tries--) { + usleep(1000); + + if (!btf_exists(btf_id)) + break; + + if (tries) + continue; + + PRINT_FAIL("btf should have been freed"); + } + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[0]); + Close(prog_fd); +} + +/* + * Test that a program with trash in fd_array can't be loaded: + * only map and BTF file descriptors should be accepted. + */ +static void check_fd_array_cnt__fd_array_with_trash(void) +{ + int extra_fds[3] = { -1, -1, -1 }; + int prog_fd = -1; + + extra_fds[0] = new_map(); + if (!ASSERT_GE(extra_fds[0], 0, "new_map")) + goto cleanup; + extra_fds[1] = new_btf(); + if (!ASSERT_GE(extra_fds[1], 0, "new_btf")) + goto cleanup; + + /* trash 1: not a file descriptor */ + extra_fds[2] = 0xbeef; + prog_fd = load_test_prog(extra_fds, 3); + if (!ASSERT_EQ(prog_fd, -EBADF, "prog should have been rejected with -EBADF")) + goto cleanup; + + /* trash 2: not a map or btf */ + extra_fds[2] = socket(AF_INET, SOCK_STREAM, 0); + if (!ASSERT_GE(extra_fds[2], 0, "socket")) + goto cleanup; + + prog_fd = load_test_prog(extra_fds, 3); + if (!ASSERT_EQ(prog_fd, -EINVAL, "prog should have been rejected with -EINVAL")) + goto cleanup; + + /* Validate that the prog is ok if trash is removed */ + Close(extra_fds[2]); + extra_fds[2] = new_btf(); + if (!ASSERT_GE(extra_fds[2], 0, "new_btf")) + goto cleanup; + + prog_fd = load_test_prog(extra_fds, 3); + if (!ASSERT_GE(prog_fd, 0, "prog should have been loaded")) + goto cleanup; + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[2]); + Close(extra_fds[1]); + Close(extra_fds[0]); +} + +/* + * Test that a program with too big fd_array can't be loaded. + */ +static void check_fd_array_cnt__fd_array_too_big(void) +{ + int extra_fds[65]; + int prog_fd = -1; + int i; + + for (i = 0; i < 65; i++) { + extra_fds[i] = new_map(); + if (!ASSERT_GE(extra_fds[i], 0, "new_map")) + goto cleanup_fds; + } + + prog_fd = load_test_prog(extra_fds, 65); + ASSERT_EQ(prog_fd, -E2BIG, "prog should have been rejected with -E2BIG"); + +cleanup_fds: + while (i > 0) + Close(extra_fds[--i]); +} + +void test_fd_array_cnt(void) +{ + if (test__start_subtest("no-fd-array")) + check_fd_array_cnt__no_fd_array(); + + if (test__start_subtest("fd-array-ok")) + check_fd_array_cnt__fd_array_ok(); + + if (test__start_subtest("fd-array-dup-input")) + check_fd_array_cnt__duplicated_maps(); + + if (test__start_subtest("fd-array-ref-maps-in-array")) + check_fd_array_cnt__referenced_maps_in_fd_array(); + + if (test__start_subtest("fd-array-ref-btfs")) + check_fd_array_cnt__referenced_btfs(); + + if (test__start_subtest("fd-array-trash-input")) + check_fd_array_cnt__fd_array_with_trash(); + + if (test__start_subtest("fd-array-2big")) + check_fd_array_cnt__fd_array_too_big(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index d50cbd8040d4..e59af2aa6601 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -171,6 +171,10 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel, /* See also arch_adjust_kprobe_addr(). */ if (skel->kconfig->CONFIG_X86_KERNEL_IBT) entry_offset = 4; + if (skel->kconfig->CONFIG_PPC64 && + skel->kconfig->CONFIG_KPROBES_ON_FTRACE && + !skel->kconfig->CONFIG_PPC_FTRACE_OUT_OF_LINE) + entry_offset = 4; err = verify_perf_link_info(link_fd, type, kprobe_addr, 0, entry_offset); ASSERT_OK(err, "verify_perf_link_info"); } else { diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index cfcc90cb7ffb..08bae13248c4 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -7,39 +7,14 @@ #include "bpf_flow.skel.h" +#define TEST_NS "flow_dissector_ns" #define FLOW_CONTINUE_SADDR 0x7f00007f /* 127.0.0.127 */ +#define TEST_NAME_MAX_LEN 64 #ifndef IP_MF #define IP_MF 0x2000 #endif -#define CHECK_FLOW_KEYS(desc, got, expected) \ - _CHECK(memcmp(&got, &expected, sizeof(got)) != 0, \ - desc, \ - topts.duration, \ - "nhoff=%u/%u " \ - "thoff=%u/%u " \ - "addr_proto=0x%x/0x%x " \ - "is_frag=%u/%u " \ - "is_first_frag=%u/%u " \ - "is_encap=%u/%u " \ - "ip_proto=0x%x/0x%x " \ - "n_proto=0x%x/0x%x " \ - "flow_label=0x%x/0x%x " \ - "sport=%u/%u " \ - "dport=%u/%u\n", \ - got.nhoff, expected.nhoff, \ - got.thoff, expected.thoff, \ - got.addr_proto, expected.addr_proto, \ - got.is_frag, expected.is_frag, \ - got.is_first_frag, expected.is_first_frag, \ - got.is_encap, expected.is_encap, \ - got.ip_proto, expected.ip_proto, \ - got.n_proto, expected.n_proto, \ - got.flow_label, expected.flow_label, \ - got.sport, expected.sport, \ - got.dport, expected.dport) - struct ipv4_pkt { struct ethhdr eth; struct iphdr iph; @@ -89,6 +64,19 @@ struct dvlan_ipv6_pkt { struct tcphdr tcp; } __packed; +struct gre_base_hdr { + __be16 flags; + __be16 protocol; +} gre_base_hdr; + +struct gre_minimal_pkt { + struct ethhdr eth; + struct iphdr iph; + struct gre_base_hdr gre_hdr; + struct iphdr iph_inner; + struct tcphdr tcp; +} __packed; + struct test { const char *name; union { @@ -98,6 +86,7 @@ struct test { struct ipv6_pkt ipv6; struct ipv6_frag_pkt ipv6_frag; struct dvlan_ipv6_pkt dvlan_ipv6; + struct gre_minimal_pkt gre_minimal; } pkt; struct bpf_flow_keys keys; __u32 flags; @@ -106,7 +95,6 @@ struct test { #define VLAN_HLEN 4 -static __u32 duration; struct test tests[] = { { .name = "ipv4", @@ -444,8 +432,137 @@ struct test tests[] = { }, .retval = BPF_FLOW_DISSECTOR_CONTINUE, }, + { + .name = "ip-gre", + .pkt.gre_minimal = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_GRE, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .gre_hdr = { + .flags = 0, + .protocol = __bpf_constant_htons(ETH_P_IP), + }, + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES - + sizeof(struct iphdr)), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr) * 2 + + sizeof(struct gre_base_hdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + .sport = 80, + .dport = 8080, + }, + .retval = BPF_OK, + }, + { + .name = "ip-gre-no-encap", + .pkt.ipip = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_GRE, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES - + sizeof(struct iphdr)), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr) + + sizeof(struct gre_base_hdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_GRE, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + }, + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + .retval = BPF_OK, + }, }; +void serial_test_flow_dissector_namespace(void) +{ + struct bpf_flow *skel; + struct nstoken *ns; + int err, prog_fd; + + skel = bpf_flow__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open/load skeleton")) + return; + + prog_fd = bpf_program__fd(skel->progs._dissect); + if (!ASSERT_OK_FD(prog_fd, "get dissector fd")) + goto out_destroy_skel; + + /* We must be able to attach a flow dissector to root namespace */ + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + if (!ASSERT_OK(err, "attach on root namespace ok")) + goto out_destroy_skel; + + err = make_netns(TEST_NS); + if (!ASSERT_OK(err, "create non-root net namespace")) + goto out_destroy_skel; + + /* We must not be able to additionally attach a flow dissector to a + * non-root net namespace + */ + ns = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(ns, "enter non-root net namespace")) + goto out_clean_ns; + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + if (!ASSERT_ERR(err, + "refuse new flow dissector in non-root net namespace")) + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + else + ASSERT_EQ(errno, EEXIST, + "refused because of already attached prog"); + close_netns(ns); + + /* If no flow dissector is attached to the root namespace, we must + * be able to attach one to a non-root net namespace + */ + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + ns = open_netns(TEST_NS); + ASSERT_OK_PTR(ns, "enter non-root net namespace"); + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + close_netns(ns); + ASSERT_OK(err, "accept new flow dissector in non-root net namespace"); + + /* If a flow dissector is attached to non-root net namespace, attaching + * a flow dissector to root namespace must fail + */ + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + if (!ASSERT_ERR(err, "refuse new flow dissector on root namespace")) + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + else + ASSERT_EQ(errno, EEXIST, + "refused because of already attached prog"); + + ns = open_netns(TEST_NS); + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + close_netns(ns); +out_clean_ns: + remove_netns(TEST_NS); +out_destroy_skel: + bpf_flow__destroy(skel); +} + static int create_tap(const char *ifname) { struct ifreq ifr = { @@ -533,22 +650,27 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) return 0; } -static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) +static void run_tests_skb_less(int tap_fd, struct bpf_map *keys, + char *test_suffix) { + char test_name[TEST_NAME_MAX_LEN]; int i, err, keys_fd; keys_fd = bpf_map__fd(keys); - if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd)) + if (!ASSERT_OK_FD(keys_fd, "bpf_map__fd")) return; for (i = 0; i < ARRAY_SIZE(tests); i++) { /* Keep in sync with 'flags' from eth_get_headlen. */ __u32 eth_get_headlen_flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG; - LIBBPF_OPTS(bpf_test_run_opts, topts); struct bpf_flow_keys flow_keys = {}; __u32 key = (__u32)(tests[i].keys.sport) << 16 | tests[i].keys.dport; + snprintf(test_name, TEST_NAME_MAX_LEN, "%s-%s", tests[i].name, + test_suffix); + if (!test__start_subtest(test_name)) + continue; /* For skb-less case we can't pass input flags; run * only the tests that have a matching set of flags. @@ -558,78 +680,139 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) continue; err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt)); - CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); + if (!ASSERT_EQ(err, sizeof(tests[i].pkt), "tx_tap")) + continue; /* check the stored flow_keys only if BPF_OK expected */ if (tests[i].retval != BPF_OK) continue; err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys); - ASSERT_OK(err, "bpf_map_lookup_elem"); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + continue; - CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + ASSERT_MEMEQ(&flow_keys, &tests[i].keys, + sizeof(struct bpf_flow_keys), + "returned flow keys"); err = bpf_map_delete_elem(keys_fd, &key); ASSERT_OK(err, "bpf_map_delete_elem"); } } -static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd) +void test_flow_dissector_skb_less_direct_attach(void) { - int err, prog_fd; + int err, prog_fd, tap_fd; + struct bpf_flow *skel; + struct netns_obj *ns; + + ns = netns_new("flow_dissector_skb_less_indirect_attach_ns", true); + if (!ASSERT_OK_PTR(ns, "create and open netns")) + return; + + skel = bpf_flow__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open/load skeleton")) + goto out_clean_ns; + + err = init_prog_array(skel->obj, skel->maps.jmp_table); + if (!ASSERT_OK(err, "init_prog_array")) + goto out_destroy_skel; prog_fd = bpf_program__fd(skel->progs._dissect); - if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd)) - return; + if (!ASSERT_OK_FD(prog_fd, "bpf_program__fd")) + goto out_destroy_skel; err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); - if (CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno)) - return; + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out_destroy_skel; - run_tests_skb_less(tap_fd, skel->maps.last_dissection); + tap_fd = create_tap("tap0"); + if (!ASSERT_OK_FD(tap_fd, "create_tap")) + goto out_destroy_skel; + err = ifup("tap0"); + if (!ASSERT_OK(err, "ifup")) + goto out_close_tap; + + run_tests_skb_less(tap_fd, skel->maps.last_dissection, + "non-skb-direct-attach"); err = bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); - CHECK(err, "bpf_prog_detach2", "err %d errno %d\n", err, errno); + ASSERT_OK(err, "bpf_prog_detach2"); + +out_close_tap: + close(tap_fd); +out_destroy_skel: + bpf_flow__destroy(skel); +out_clean_ns: + netns_free(ns); } -static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd) +void test_flow_dissector_skb_less_indirect_attach(void) { + int err, net_fd, tap_fd; + struct bpf_flow *skel; struct bpf_link *link; - int err, net_fd; + struct netns_obj *ns; + + ns = netns_new("flow_dissector_skb_less_indirect_attach_ns", true); + if (!ASSERT_OK_PTR(ns, "create and open netns")) + return; + + skel = bpf_flow__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open/load skeleton")) + goto out_clean_ns; net_fd = open("/proc/self/ns/net", O_RDONLY); - if (CHECK(net_fd < 0, "open(/proc/self/ns/net)", "err %d\n", errno)) - return; + if (!ASSERT_OK_FD(net_fd, "open(/proc/self/ns/net")) + goto out_destroy_skel; + + err = init_prog_array(skel->obj, skel->maps.jmp_table); + if (!ASSERT_OK(err, "init_prog_array")) + goto out_destroy_skel; + + tap_fd = create_tap("tap0"); + if (!ASSERT_OK_FD(tap_fd, "create_tap")) + goto out_close_ns; + err = ifup("tap0"); + if (!ASSERT_OK(err, "ifup")) + goto out_close_tap; link = bpf_program__attach_netns(skel->progs._dissect, net_fd); if (!ASSERT_OK_PTR(link, "attach_netns")) - goto out_close; + goto out_close_tap; - run_tests_skb_less(tap_fd, skel->maps.last_dissection); + run_tests_skb_less(tap_fd, skel->maps.last_dissection, + "non-skb-indirect-attach"); err = bpf_link__destroy(link); - CHECK(err, "bpf_link__destroy", "err %d\n", err); -out_close: + ASSERT_OK(err, "bpf_link__destroy"); + +out_close_tap: + close(tap_fd); +out_close_ns: close(net_fd); +out_destroy_skel: + bpf_flow__destroy(skel); +out_clean_ns: + netns_free(ns); } -void test_flow_dissector(void) +void test_flow_dissector_skb(void) { - int i, err, prog_fd, keys_fd = -1, tap_fd; + char test_name[TEST_NAME_MAX_LEN]; struct bpf_flow *skel; + int i, err, prog_fd; skel = bpf_flow__open_and_load(); - if (CHECK(!skel, "skel", "failed to open/load skeleton\n")) + if (!ASSERT_OK_PTR(skel, "open/load skeleton")) return; - prog_fd = bpf_program__fd(skel->progs._dissect); - if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd)) - goto out_destroy_skel; - keys_fd = bpf_map__fd(skel->maps.last_dissection); - if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd)) - goto out_destroy_skel; err = init_prog_array(skel->obj, skel->maps.jmp_table); - if (CHECK(err, "init_prog_array", "err %d\n", err)) + if (!ASSERT_OK(err, "init_prog_array")) + goto out_destroy_skel; + + prog_fd = bpf_program__fd(skel->progs._dissect); + if (!ASSERT_OK_FD(prog_fd, "bpf_program__fd")) goto out_destroy_skel; for (i = 0; i < ARRAY_SIZE(tests); i++) { @@ -641,6 +824,10 @@ void test_flow_dissector(void) ); static struct bpf_flow_keys ctx = {}; + snprintf(test_name, TEST_NAME_MAX_LEN, "%s-skb", tests[i].name); + if (!test__start_subtest(test_name)) + continue; + if (tests[i].flags) { topts.ctx_in = &ctx; topts.ctx_size_in = sizeof(ctx); @@ -656,26 +843,12 @@ void test_flow_dissector(void) continue; ASSERT_EQ(topts.data_size_out, sizeof(flow_keys), "test_run data_size_out"); - CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + ASSERT_MEMEQ(&flow_keys, &tests[i].keys, + sizeof(struct bpf_flow_keys), + "returned flow keys"); } - /* Do the same tests but for skb-less flow dissector. - * We use a known path in the net/tun driver that calls - * eth_get_headlen and we manually export bpf_flow_keys - * via BPF map in this case. - */ - - tap_fd = create_tap("tap0"); - CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d\n", tap_fd, errno); - err = ifup("tap0"); - CHECK(err, "ifup", "err %d errno %d\n", err, errno); - - /* Test direct prog attachment */ - test_skb_less_prog_attach(skel, tap_fd); - /* Test indirect prog attachment via link */ - test_skb_less_link_create(skel, tap_fd); - - close(tap_fd); out_destroy_skel: bpf_flow__destroy(skel); } + diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c new file mode 100644 index 000000000000..3729fbfd3084 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c @@ -0,0 +1,792 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <bpf/bpf.h> +#include <linux/bpf.h> +#include <bpf/libbpf.h> +#include <arpa/inet.h> +#include <asm/byteorder.h> +#include <netinet/udp.h> +#include <poll.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/time.h> +#include <unistd.h> +#include "test_progs.h" +#include "network_helpers.h" +#include "bpf_util.h" +#include "bpf_flow.skel.h" + +#define CFG_PORT_INNER 8000 +#define CFG_PORT_GUE 6080 +#define SUBTEST_NAME_MAX_LEN 32 +#define TEST_NAME_MAX_LEN (32 + SUBTEST_NAME_MAX_LEN) +#define MAX_SOURCE_PORTS 3 +#define TEST_PACKETS_COUNT 10 +#define TEST_PACKET_LEN 100 +#define TEST_PACKET_PATTERN 'a' +#define TEST_IPV4 "192.168.0.1/32" +#define TEST_IPV6 "100::a/128" +#define TEST_TUNNEL_REMOTE "127.0.0.2" +#define TEST_TUNNEL_LOCAL "127.0.0.1" + +#define INIT_ADDR4(addr4, port) \ + { \ + .sin_family = AF_INET, \ + .sin_port = __constant_htons(port), \ + .sin_addr.s_addr = __constant_htonl(addr4), \ + } + +#define INIT_ADDR6(addr6, port) \ + { \ + .sin6_family = AF_INET6, \ + .sin6_port = __constant_htons(port), \ + .sin6_addr = addr6, \ + } +#define TEST_IN4_SRC_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK + 2, 0) +#define TEST_IN4_DST_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK, CFG_PORT_INNER) +#define TEST_OUT4_SRC_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK + 1, 0) +#define TEST_OUT4_DST_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK, 0) + +#define TEST_IN6_SRC_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0) +#define TEST_IN6_DST_ADDR_DEFAULT \ + INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER) +#define TEST_OUT6_SRC_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0) +#define TEST_OUT6_DST_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0) + +#define TEST_IN4_SRC_ADDR_DISSECT_CONTINUE INIT_ADDR4(INADDR_LOOPBACK + 126, 0) +#define TEST_IN4_SRC_ADDR_IPIP INIT_ADDR4((in_addr_t)0x01010101, 0) +#define TEST_IN4_DST_ADDR_IPIP INIT_ADDR4((in_addr_t)0xC0A80001, CFG_PORT_INNER) + +struct grehdr { + uint16_t unused; + uint16_t protocol; +} __packed; + +struct guehdr { + union { + struct { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 hlen : 5, control : 1, version : 2; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 version : 2, control : 1, hlen : 5; +#else +#error "Please fix <asm/byteorder.h>" +#endif + __u8 proto_ctype; + __be16 flags; + }; + __be32 word; + }; +}; + +static char buf[ETH_DATA_LEN]; + +struct test_configuration { + char name[SUBTEST_NAME_MAX_LEN]; + int (*test_setup)(void); + void (*test_teardown)(void); + int source_ports[MAX_SOURCE_PORTS]; + int cfg_l3_inner; + struct sockaddr_in in_saddr4; + struct sockaddr_in in_daddr4; + struct sockaddr_in6 in_saddr6; + struct sockaddr_in6 in_daddr6; + int cfg_l3_outer; + struct sockaddr_in out_saddr4; + struct sockaddr_in out_daddr4; + struct sockaddr_in6 out_saddr6; + struct sockaddr_in6 out_daddr6; + int cfg_encap_proto; + uint8_t cfg_dsfield_inner; + uint8_t cfg_dsfield_outer; + int cfg_l3_extra; + struct sockaddr_in extra_saddr4; + struct sockaddr_in extra_daddr4; + struct sockaddr_in6 extra_saddr6; + struct sockaddr_in6 extra_daddr6; +}; + +static unsigned long util_gettime(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static void build_ipv4_header(void *header, uint8_t proto, uint32_t src, + uint32_t dst, int payload_len, uint8_t tos) +{ + struct iphdr *iph = header; + + iph->ihl = 5; + iph->version = 4; + iph->tos = tos; + iph->ttl = 8; + iph->tot_len = htons(sizeof(*iph) + payload_len); + iph->id = htons(1337); + iph->protocol = proto; + iph->saddr = src; + iph->daddr = dst; + iph->check = build_ip_csum((void *)iph); +} + +static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield) +{ + uint16_t val, *ptr = (uint16_t *)ip6h; + + val = ntohs(*ptr); + val &= 0xF00F; + val |= ((uint16_t)dsfield) << 4; + *ptr = htons(val); +} + +static void build_ipv6_header(void *header, uint8_t proto, + const struct sockaddr_in6 *src, + const struct sockaddr_in6 *dst, int payload_len, + uint8_t dsfield) +{ + struct ipv6hdr *ip6h = header; + + ip6h->version = 6; + ip6h->payload_len = htons(payload_len); + ip6h->nexthdr = proto; + ip6h->hop_limit = 8; + ipv6_set_dsfield(ip6h, dsfield); + + memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr)); + memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr)); +} + +static void build_udp_header(void *header, int payload_len, uint16_t sport, + uint16_t dport, int family) +{ + struct udphdr *udph = header; + int len = sizeof(*udph) + payload_len; + + udph->source = htons(sport); + udph->dest = htons(dport); + udph->len = htons(len); + udph->check = 0; + if (family == AF_INET) + udph->check = build_udp_v4_csum(header - sizeof(struct iphdr), + udph); + else + udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr), + udph); +} + +static void build_gue_header(void *header, uint8_t proto) +{ + struct guehdr *gueh = header; + + gueh->proto_ctype = proto; +} + +static void build_gre_header(void *header, uint16_t proto) +{ + struct grehdr *greh = header; + + greh->protocol = htons(proto); +} + +static int l3_length(int family) +{ + if (family == AF_INET) + return sizeof(struct iphdr); + else + return sizeof(struct ipv6hdr); +} + +static int build_packet(const struct test_configuration *test, uint16_t sport) +{ + int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0; + int el3_len = 0, packet_len; + + memset(buf, 0, ETH_DATA_LEN); + + if (test->cfg_l3_extra) + el3_len = l3_length(test->cfg_l3_extra); + + /* calculate header offsets */ + if (test->cfg_encap_proto) { + ol3_len = l3_length(test->cfg_l3_outer); + + if (test->cfg_encap_proto == IPPROTO_GRE) + ol4_len = sizeof(struct grehdr); + else if (test->cfg_encap_proto == IPPROTO_UDP) + ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr); + } + + il3_len = l3_length(test->cfg_l3_inner); + il4_len = sizeof(struct udphdr); + + packet_len = el3_len + ol3_len + ol4_len + il3_len + il4_len + + TEST_PACKET_LEN; + if (!ASSERT_LE(packet_len, sizeof(buf), "check packet size")) + return -1; + + /* + * Fill packet from inside out, to calculate correct checksums. + * But create ip before udp headers, as udp uses ip for pseudo-sum. + */ + memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len, + TEST_PACKET_PATTERN, TEST_PACKET_LEN); + + /* add zero byte for udp csum padding */ + buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + TEST_PACKET_LEN] = + 0; + + switch (test->cfg_l3_inner) { + case PF_INET: + build_ipv4_header(buf + el3_len + ol3_len + ol4_len, + IPPROTO_UDP, test->in_saddr4.sin_addr.s_addr, + test->in_daddr4.sin_addr.s_addr, + il4_len + TEST_PACKET_LEN, + test->cfg_dsfield_inner); + break; + case PF_INET6: + build_ipv6_header(buf + el3_len + ol3_len + ol4_len, + IPPROTO_UDP, &test->in_saddr6, + &test->in_daddr6, il4_len + TEST_PACKET_LEN, + test->cfg_dsfield_inner); + break; + } + + build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len, + TEST_PACKET_LEN, sport, CFG_PORT_INNER, + test->cfg_l3_inner); + + if (!test->cfg_encap_proto) + return il3_len + il4_len + TEST_PACKET_LEN; + + switch (test->cfg_l3_outer) { + case PF_INET: + build_ipv4_header(buf + el3_len, test->cfg_encap_proto, + test->out_saddr4.sin_addr.s_addr, + test->out_daddr4.sin_addr.s_addr, + ol4_len + il3_len + il4_len + TEST_PACKET_LEN, + test->cfg_dsfield_outer); + break; + case PF_INET6: + build_ipv6_header(buf + el3_len, test->cfg_encap_proto, + &test->out_saddr6, &test->out_daddr6, + ol4_len + il3_len + il4_len + TEST_PACKET_LEN, + test->cfg_dsfield_outer); + break; + } + + switch (test->cfg_encap_proto) { + case IPPROTO_UDP: + build_gue_header(buf + el3_len + ol3_len + ol4_len - + sizeof(struct guehdr), + test->cfg_l3_inner == PF_INET ? IPPROTO_IPIP : + IPPROTO_IPV6); + build_udp_header(buf + el3_len + ol3_len, + sizeof(struct guehdr) + il3_len + il4_len + + TEST_PACKET_LEN, + sport, CFG_PORT_GUE, test->cfg_l3_outer); + break; + case IPPROTO_GRE: + build_gre_header(buf + el3_len + ol3_len, + test->cfg_l3_inner == PF_INET ? ETH_P_IP : + ETH_P_IPV6); + break; + } + + switch (test->cfg_l3_extra) { + case PF_INET: + build_ipv4_header(buf, + test->cfg_l3_outer == PF_INET ? IPPROTO_IPIP : + IPPROTO_IPV6, + test->extra_saddr4.sin_addr.s_addr, + test->extra_daddr4.sin_addr.s_addr, + ol3_len + ol4_len + il3_len + il4_len + + TEST_PACKET_LEN, + 0); + break; + case PF_INET6: + build_ipv6_header(buf, + test->cfg_l3_outer == PF_INET ? IPPROTO_IPIP : + IPPROTO_IPV6, + &test->extra_saddr6, &test->extra_daddr6, + ol3_len + ol4_len + il3_len + il4_len + + TEST_PACKET_LEN, + 0); + break; + } + + return el3_len + ol3_len + ol4_len + il3_len + il4_len + + TEST_PACKET_LEN; +} + +/* sender transmits encapsulated over RAW or unencap'd over UDP */ +static int setup_tx(const struct test_configuration *test) +{ + int family, fd, ret; + + if (test->cfg_l3_extra) + family = test->cfg_l3_extra; + else if (test->cfg_l3_outer) + family = test->cfg_l3_outer; + else + family = test->cfg_l3_inner; + + fd = socket(family, SOCK_RAW, IPPROTO_RAW); + if (!ASSERT_OK_FD(fd, "setup tx socket")) + return fd; + + if (test->cfg_l3_extra) { + if (test->cfg_l3_extra == PF_INET) + ret = connect(fd, (void *)&test->extra_daddr4, + sizeof(test->extra_daddr4)); + else + ret = connect(fd, (void *)&test->extra_daddr6, + sizeof(test->extra_daddr6)); + if (!ASSERT_OK(ret, "connect")) { + close(fd); + return ret; + } + } else if (test->cfg_l3_outer) { + /* connect to destination if not encapsulated */ + if (test->cfg_l3_outer == PF_INET) + ret = connect(fd, (void *)&test->out_daddr4, + sizeof(test->out_daddr4)); + else + ret = connect(fd, (void *)&test->out_daddr6, + sizeof(test->out_daddr6)); + if (!ASSERT_OK(ret, "connect")) { + close(fd); + return ret; + } + } else { + /* otherwise using loopback */ + if (test->cfg_l3_inner == PF_INET) + ret = connect(fd, (void *)&test->in_daddr4, + sizeof(test->in_daddr4)); + else + ret = connect(fd, (void *)&test->in_daddr6, + sizeof(test->in_daddr6)); + if (!ASSERT_OK(ret, "connect")) { + close(fd); + return ret; + } + } + + return fd; +} + +/* receiver reads unencapsulated UDP */ +static int setup_rx(const struct test_configuration *test) +{ + int fd, ret; + + fd = socket(test->cfg_l3_inner, SOCK_DGRAM, 0); + if (!ASSERT_OK_FD(fd, "socket rx")) + return fd; + + if (test->cfg_l3_inner == PF_INET) + ret = bind(fd, (void *)&test->in_daddr4, + sizeof(test->in_daddr4)); + else + ret = bind(fd, (void *)&test->in_daddr6, + sizeof(test->in_daddr6)); + if (!ASSERT_OK(ret, "bind rx")) { + close(fd); + return ret; + } + + return fd; +} + +static int do_tx(int fd, const char *pkt, int len) +{ + int ret; + + ret = write(fd, pkt, len); + return ret != len; +} + +static int do_poll(int fd, short events, int timeout) +{ + struct pollfd pfd; + int ret; + + pfd.fd = fd; + pfd.events = events; + + ret = poll(&pfd, 1, timeout); + return ret; +} + +static int do_rx(int fd) +{ + char rbuf; + int ret, num = 0; + + while (1) { + ret = recv(fd, &rbuf, 1, MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + break; + if (ret < 0) + return -1; + if (!ASSERT_EQ(rbuf, TEST_PACKET_PATTERN, "check pkt pattern")) + return -1; + num++; + } + + return num; +} + +static int run_test(const struct test_configuration *test, + int source_port_index) +{ + int fdt = -1, fdr = -1, len, tx = 0, rx = 0, err; + unsigned long tstop, tcur; + + fdr = setup_rx(test); + fdt = setup_tx(test); + if (!ASSERT_OK_FD(fdr, "setup rx") || !ASSERT_OK_FD(fdt, "setup tx")) { + err = -1; + goto out_close_sockets; + } + + len = build_packet(test, + (uint16_t)test->source_ports[source_port_index]); + if (!ASSERT_GT(len, 0, "build test packet")) + return -1; + + tcur = util_gettime(); + tstop = tcur; + + while (tx < TEST_PACKETS_COUNT) { + if (!ASSERT_OK(do_tx(fdt, buf, len), "do_tx")) + break; + tx++; + err = do_rx(fdr); + if (!ASSERT_GE(err, 0, "do_rx")) + break; + rx += err; + } + + /* read straggler packets, if any */ + if (rx < tx) { + tstop = util_gettime() + 100; + while (rx < tx) { + tcur = util_gettime(); + if (tcur >= tstop) + break; + + err = do_poll(fdr, POLLIN, tstop - tcur); + if (err < 0) + break; + err = do_rx(fdr); + if (err >= 0) + rx += err; + } + } + +out_close_sockets: + close(fdt); + close(fdr); + return rx; +} + +static int attach_and_configure_program(struct bpf_flow *skel) +{ + struct bpf_map *prog_array = skel->maps.jmp_table; + int main_prog_fd, sub_prog_fd, map_fd, i, err; + struct bpf_program *prog; + char prog_name[32]; + + main_prog_fd = bpf_program__fd(skel->progs._dissect); + if (main_prog_fd < 0) + return main_prog_fd; + + err = bpf_prog_attach(main_prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + if (err) + return err; + + map_fd = bpf_map__fd(prog_array); + if (map_fd < 0) + return map_fd; + + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!prog) + return -1; + + sub_prog_fd = bpf_program__fd(prog); + if (sub_prog_fd < 0) + return -1; + + err = bpf_map_update_elem(map_fd, &i, &sub_prog_fd, BPF_ANY); + if (err) + return -1; + } + + return main_prog_fd; +} + +static void detach_program(struct bpf_flow *skel, int prog_fd) +{ + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); +} + +static int set_port_drop(int pf, bool multi_port) +{ + SYS(fail, "tc qdisc add dev lo ingress"); + SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s", + "dev lo", + "parent FFFF:", + "protocol", pf == PF_INET6 ? "ipv6" : "ip", + "pref 1337", + "flower", + "ip_proto udp", + "src_port", multi_port ? "8-10" : "9", + "action drop"); + return 0; + +fail_delete_qdisc: + SYS_NOFAIL("tc qdisc del dev lo ingress"); +fail: + return 1; +} + +static void remove_filter(void) +{ + SYS_NOFAIL("tc filter del dev lo ingress"); + SYS_NOFAIL("tc qdisc del dev lo ingress"); +} + +static int ipv4_setup(void) +{ + return set_port_drop(PF_INET, false); +} + +static int ipv6_setup(void) +{ + return set_port_drop(PF_INET6, false); +} + +static int port_range_setup(void) +{ + return set_port_drop(PF_INET, true); +} + +static int set_addresses(void) +{ + SYS(out, "ip -4 addr add %s dev lo", TEST_IPV4); + SYS(out_remove_ipv4, "ip -6 addr add %s dev lo", TEST_IPV6); + return 0; +out_remove_ipv4: + SYS_NOFAIL("ip -4 addr del %s dev lo", TEST_IPV4); +out: + return -1; +} + +static void unset_addresses(void) +{ + SYS_NOFAIL("ip -4 addr del %s dev lo", TEST_IPV4); + SYS_NOFAIL("ip -6 addr del %s dev lo", TEST_IPV6); +} + +static int ipip_setup(void) +{ + if (!ASSERT_OK(set_addresses(), "configure addresses")) + return -1; + if (!ASSERT_OK(set_port_drop(PF_INET, false), "set filter")) + goto out_unset_addresses; + SYS(out_remove_filter, + "ip link add ipip_test type ipip remote %s local %s dev lo", + TEST_TUNNEL_REMOTE, TEST_TUNNEL_LOCAL); + SYS(out_clean_netif, "ip link set ipip_test up"); + return 0; + +out_clean_netif: + SYS_NOFAIL("ip link del ipip_test"); +out_remove_filter: + remove_filter(); +out_unset_addresses: + unset_addresses(); + return -1; +} + +static void ipip_shutdown(void) +{ + SYS_NOFAIL("ip link del ipip_test"); + remove_filter(); + unset_addresses(); +} + +static int gre_setup(void) +{ + if (!ASSERT_OK(set_addresses(), "configure addresses")) + return -1; + if (!ASSERT_OK(set_port_drop(PF_INET, false), "set filter")) + goto out_unset_addresses; + SYS(out_remove_filter, + "ip link add gre_test type gre remote %s local %s dev lo", + TEST_TUNNEL_REMOTE, TEST_TUNNEL_LOCAL); + SYS(out_clean_netif, "ip link set gre_test up"); + return 0; + +out_clean_netif: + SYS_NOFAIL("ip link del ipip_test"); +out_remove_filter: + remove_filter(); +out_unset_addresses: + unset_addresses(); + return -1; +} + +static void gre_shutdown(void) +{ + SYS_NOFAIL("ip link del gre_test"); + remove_filter(); + unset_addresses(); +} + +static const struct test_configuration tests_input[] = { + { + .name = "ipv4", + .test_setup = ipv4_setup, + .test_teardown = remove_filter, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_DEFAULT, + .in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT + }, + { + .name = "ipv4_continue_dissect", + .test_setup = ipv4_setup, + .test_teardown = remove_filter, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_DISSECT_CONTINUE, + .in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT }, + { + .name = "ipip", + .test_setup = ipip_setup, + .test_teardown = ipip_shutdown, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_IPIP, + .in_daddr4 = TEST_IN4_DST_ADDR_IPIP, + .out_saddr4 = TEST_OUT4_SRC_ADDR_DEFAULT, + .out_daddr4 = TEST_OUT4_DST_ADDR_DEFAULT, + .cfg_l3_outer = PF_INET, + .cfg_encap_proto = IPPROTO_IPIP, + + }, + { + .name = "gre", + .test_setup = gre_setup, + .test_teardown = gre_shutdown, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_IPIP, + .in_daddr4 = TEST_IN4_DST_ADDR_IPIP, + .out_saddr4 = TEST_OUT4_SRC_ADDR_DEFAULT, + .out_daddr4 = TEST_OUT4_DST_ADDR_DEFAULT, + .cfg_l3_outer = PF_INET, + .cfg_encap_proto = IPPROTO_GRE, + }, + { + .name = "port_range", + .test_setup = port_range_setup, + .test_teardown = remove_filter, + .source_ports = { 7, 9, 11 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_DEFAULT, + .in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT }, + { + .name = "ipv6", + .test_setup = ipv6_setup, + .test_teardown = remove_filter, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET6, + .in_saddr6 = TEST_IN6_SRC_ADDR_DEFAULT, + .in_daddr6 = TEST_IN6_DST_ADDR_DEFAULT + }, +}; + +struct test_ctx { + struct bpf_flow *skel; + struct netns_obj *ns; + int prog_fd; +}; + +static int test_global_init(struct test_ctx *ctx) +{ + int err; + + ctx->skel = bpf_flow__open_and_load(); + if (!ASSERT_OK_PTR(ctx->skel, "open and load flow_dissector")) + return -1; + + ctx->ns = netns_new("flow_dissector_classification", true); + if (!ASSERT_OK_PTR(ctx->ns, "switch ns")) + goto out_destroy_skel; + + err = write_sysctl("/proc/sys/net/ipv4/conf/default/rp_filter", "0"); + err |= write_sysctl("/proc/sys/net/ipv4/conf/all/rp_filter", "0"); + err |= write_sysctl("/proc/sys/net/ipv4/conf/lo/rp_filter", "0"); + if (!ASSERT_OK(err, "configure net tunables")) + goto out_clean_ns; + + ctx->prog_fd = attach_and_configure_program(ctx->skel); + if (!ASSERT_OK_FD(ctx->prog_fd, "attach and configure program")) + goto out_clean_ns; + return 0; +out_clean_ns: + netns_free(ctx->ns); +out_destroy_skel: + bpf_flow__destroy(ctx->skel); + return -1; +} + +static void test_global_shutdown(struct test_ctx *ctx) +{ + detach_program(ctx->skel, ctx->prog_fd); + netns_free(ctx->ns); + bpf_flow__destroy(ctx->skel); +} + +void test_flow_dissector_classification(void) +{ + struct test_ctx ctx; + const struct test_configuration *test; + int i; + + if (test_global_init(&ctx)) + return; + + for (i = 0; i < ARRAY_SIZE(tests_input); i++) { + if (!test__start_subtest(tests_input[i].name)) + continue; + test = &tests_input[i]; + /* All tests are expected to have one rx-ok port first, + * then a non-working rx port, and finally a rx-ok port + */ + if (test->test_setup && + !ASSERT_OK(test->test_setup(), "init filter")) + continue; + + ASSERT_EQ(run_test(test, 0), TEST_PACKETS_COUNT, + "test first port"); + ASSERT_EQ(run_test(test, 1), 0, "test second port"); + ASSERT_EQ(run_test(test, 2), TEST_PACKETS_COUNT, + "test third port"); + if (test->test_teardown) + test->test_teardown(); + } + test_global_shutdown(&ctx); +} diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c new file mode 100644 index 000000000000..b7b77a6b2979 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025. Huawei Technologies Co., Ltd */ +#define _GNU_SOURCE +#include <unistd.h> +#include <sys/syscall.h> +#include <test_progs.h> + +#include "free_timer.skel.h" + +struct run_ctx { + struct bpf_program *start_prog; + struct bpf_program *overwrite_prog; + pthread_barrier_t notify; + int loop; + bool start; + bool stop; +}; + +static void start_threads(struct run_ctx *ctx) +{ + ctx->start = true; +} + +static void stop_threads(struct run_ctx *ctx) +{ + ctx->stop = true; + /* Guarantee the order between ->stop and ->start */ + __atomic_store_n(&ctx->start, true, __ATOMIC_RELEASE); +} + +static int wait_for_start(struct run_ctx *ctx) +{ + while (!__atomic_load_n(&ctx->start, __ATOMIC_ACQUIRE)) + usleep(10); + + return ctx->stop; +} + +static void *overwrite_timer_fn(void *arg) +{ + struct run_ctx *ctx = arg; + int loop, fd, err; + cpu_set_t cpuset; + long ret = 0; + + /* Pin on CPU 0 */ + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset); + + /* Is the thread being stopped ? */ + err = wait_for_start(ctx); + if (err) + return NULL; + + fd = bpf_program__fd(ctx->overwrite_prog); + loop = ctx->loop; + while (loop-- > 0) { + LIBBPF_OPTS(bpf_test_run_opts, opts); + + /* Wait for start thread to complete */ + pthread_barrier_wait(&ctx->notify); + + /* Overwrite timers */ + err = bpf_prog_test_run_opts(fd, &opts); + if (err) + ret |= 1; + else if (opts.retval) + ret |= 2; + + /* Notify start thread to start timers */ + pthread_barrier_wait(&ctx->notify); + } + + return (void *)ret; +} + +static void *start_timer_fn(void *arg) +{ + struct run_ctx *ctx = arg; + int loop, fd, err; + cpu_set_t cpuset; + long ret = 0; + + /* Pin on CPU 1 */ + CPU_ZERO(&cpuset); + CPU_SET(1, &cpuset); + pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset); + + /* Is the thread being stopped ? */ + err = wait_for_start(ctx); + if (err) + return NULL; + + fd = bpf_program__fd(ctx->start_prog); + loop = ctx->loop; + while (loop-- > 0) { + LIBBPF_OPTS(bpf_test_run_opts, opts); + + /* Run the prog to start timer */ + err = bpf_prog_test_run_opts(fd, &opts); + if (err) + ret |= 4; + else if (opts.retval) + ret |= 8; + + /* Notify overwrite thread to do overwrite */ + pthread_barrier_wait(&ctx->notify); + + /* Wait for overwrite thread to complete */ + pthread_barrier_wait(&ctx->notify); + } + + return (void *)ret; +} + +void test_free_timer(void) +{ + struct free_timer *skel; + struct bpf_program *prog; + struct run_ctx ctx; + pthread_t tid[2]; + void *ret; + int err; + + skel = free_timer__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_load")) + return; + + memset(&ctx, 0, sizeof(ctx)); + + prog = bpf_object__find_program_by_name(skel->obj, "start_timer"); + if (!ASSERT_OK_PTR(prog, "find start prog")) + goto out; + ctx.start_prog = prog; + + prog = bpf_object__find_program_by_name(skel->obj, "overwrite_timer"); + if (!ASSERT_OK_PTR(prog, "find overwrite prog")) + goto out; + ctx.overwrite_prog = prog; + + pthread_barrier_init(&ctx.notify, NULL, 2); + ctx.loop = 10; + + err = pthread_create(&tid[0], NULL, start_timer_fn, &ctx); + if (!ASSERT_OK(err, "create start_timer")) + goto out; + + err = pthread_create(&tid[1], NULL, overwrite_timer_fn, &ctx); + if (!ASSERT_OK(err, "create overwrite_timer")) { + stop_threads(&ctx); + goto out; + } + + start_threads(&ctx); + + ret = NULL; + err = pthread_join(tid[0], &ret); + ASSERT_EQ(err | (long)ret, 0, "start_timer"); + ret = NULL; + err = pthread_join(tid[1], &ret); + ASSERT_EQ(err | (long)ret, 0, "overwrite_timer"); +out: + free_timer__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index 66ab1cae923e..e19ef509ebf8 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -397,6 +397,31 @@ cleanup: kprobe_multi_session_cookie__destroy(skel); } +static void test_unique_match(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + struct kprobe_multi *skel = NULL; + struct bpf_link *link = NULL; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kprobe_multi__open_and_load")) + return; + + opts.unique_match = true; + skel->bss->pid = getpid(); + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, + "bpf_fentry_test*", &opts); + if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_multi_opts")) + bpf_link__destroy(link); + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, + "bpf_fentry_test8*", &opts); + if (ASSERT_OK_PTR(link, "bpf_program__attach_kprobe_multi_opts")) + bpf_link__destroy(link); + + kprobe_multi__destroy(skel); +} + static size_t symbol_hash(long key, void *ctx __maybe_unused) { return str_hash((const char *) key); @@ -765,5 +790,7 @@ void test_kprobe_multi_test(void) test_session_skel_api(); if (test__start_subtest("session_cookie")) test_session_cookie_skel_api(); + if (test__start_subtest("unique_match")) + test_unique_match(); RUN_TESTS(kprobe_multi_verifier); } diff --git a/tools/testing/selftests/bpf/prog_tests/missed.c b/tools/testing/selftests/bpf/prog_tests/missed.c index 70d90c43537c..ed8857ae914a 100644 --- a/tools/testing/selftests/bpf/prog_tests/missed.c +++ b/tools/testing/selftests/bpf/prog_tests/missed.c @@ -85,6 +85,7 @@ static void test_missed_kprobe_recursion(void) ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test3)), 1, "test3_recursion_misses"); ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test4)), 1, "test4_recursion_misses"); ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test5)), 1, "test5_recursion_misses"); + ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test6)), 1, "test6_recursion_misses"); cleanup: missed_kprobe_recursion__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h new file mode 100644 index 000000000000..1bdfb79ef009 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h @@ -0,0 +1,394 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __SOCKET_HELPERS__ +#define __SOCKET_HELPERS__ + +#include <linux/vm_sockets.h> + +/* include/linux/net.h */ +#define SOCK_TYPE_MASK 0xf + +#define IO_TIMEOUT_SEC 30 +#define MAX_STRERR_LEN 256 + +/* workaround for older vm_sockets.h */ +#ifndef VMADDR_CID_LOCAL +#define VMADDR_CID_LOCAL 1 +#endif + +/* include/linux/cleanup.h */ +#define __get_and_null(p, nullvalue) \ + ({ \ + __auto_type __ptr = &(p); \ + __auto_type __val = *__ptr; \ + *__ptr = nullvalue; \ + __val; \ + }) + +#define take_fd(fd) __get_and_null(fd, -EBADF) + +/* Wrappers that fail the test on error and report it. */ + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + + +#define xaccept_nonblock(fd, addr, len) \ + ({ \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +static inline void close_fd(int *fd) +{ + if (*fd >= 0) + xclose(*fd); +} + +#define __close_fd __attribute__((cleanup(close_fd))) + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static inline void init_addr_loopback4(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static inline void init_addr_loopback6(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); + + addr->svm_family = AF_VSOCK; + addr->svm_port = VMADDR_PORT_ANY; + addr->svm_cid = VMADDR_CID_LOCAL; + *len = sizeof(*addr); +} + +static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + case AF_VSOCK: + init_addr_loopback_vsock(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static inline int socket_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len = 0; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + if (sotype & SOCK_DGRAM) + return s; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static inline int socket_loopback(int family, int sotype) +{ + return socket_loopback_reuseport(family, sotype, -1); +} + +static inline int poll_connect(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set wfds; + int r, eval; + socklen_t esize = sizeof(eval); + + FD_ZERO(&wfds); + FD_SET(fd, &wfds); + + r = select(fd + 1, NULL, &wfds, NULL, &timeout); + if (r == 0) + errno = ETIME; + if (r != 1) + return -1; + + if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0) + return -1; + if (eval != 0) { + errno = eval; + return -1; + } + + return 0; +} + +static inline int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static inline int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + + +static inline int create_pair(int family, int sotype, int *p0, int *p1) +{ + __close_fd int s, c = -1, p = -1; + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int err; + + s = socket_loopback(family, sotype); + if (s < 0) + return s; + + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + c = xsocket(family, sotype, 0); + if (c < 0) + return c; + + err = connect(c, sockaddr(&addr), len); + if (err) { + if (errno != EINPROGRESS) { + FAIL_ERRNO("connect"); + return err; + } + + err = poll_connect(c, IO_TIMEOUT_SEC); + if (err) { + FAIL_ERRNO("poll_connect"); + return err; + } + } + + switch (sotype & SOCK_TYPE_MASK) { + case SOCK_DGRAM: + err = xgetsockname(c, sockaddr(&addr), &len); + if (err) + return err; + + err = xconnect(s, sockaddr(&addr), len); + if (err) + return err; + + *p0 = take_fd(s); + break; + case SOCK_STREAM: + case SOCK_SEQPACKET: + p = xaccept_nonblock(s, NULL, NULL); + if (p < 0) + return p; + + *p0 = take_fd(p); + break; + default: + FAIL("Unsupported socket type %#x", sotype); + return -EOPNOTSUPP; + } + + *p1 = take_fd(c); + return 0; +} + +static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, + int *p0, int *p1) +{ + int err; + + err = create_pair(family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + + return err; +} + +#endif // __SOCKET_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 248754296d97..884ad87783d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -12,6 +12,7 @@ #include "test_sockmap_progs_query.skel.h" #include "test_sockmap_pass_prog.skel.h" #include "test_sockmap_drop_prog.skel.h" +#include "test_sockmap_change_tail.skel.h" #include "bpf_iter_sockmap.skel.h" #include "sockmap_helpers.h" @@ -643,6 +644,54 @@ out: test_sockmap_drop_prog__destroy(drop); } +static void test_sockmap_skb_verdict_change_tail(void) +{ + struct test_sockmap_change_tail *skel; + int err, map, verdict; + int c1, p1, sent, recvd; + int zero = 0; + char buf[2]; + + skel = test_sockmap_change_tail__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1); + if (!ASSERT_OK(err, "create_pair()")) + goto out; + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + sent = xsend(p1, "Tr", 2, 0); + ASSERT_EQ(sent, 2, "xsend(p1)"); + recvd = recv(c1, buf, 2, 0); + ASSERT_EQ(recvd, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + sent = xsend(p1, "G", 1, 0); + ASSERT_EQ(sent, 1, "xsend(p1)"); + recvd = recv(c1, buf, 2, 0); + ASSERT_EQ(recvd, 2, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + sent = xsend(p1, "E", 1, 0); + ASSERT_EQ(sent, 1, "xsend(p1)"); + recvd = recv(c1, buf, 1, 0); + ASSERT_EQ(recvd, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + +out_close: + close(c1); + close(p1); +out: + test_sockmap_change_tail__destroy(skel); +} + static void test_sockmap_skb_verdict_peek_helper(int map) { int err, c1, p1, zero = 0, sent, recvd, avail; @@ -1058,6 +1107,8 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_fionread(true); if (test__start_subtest("sockmap skb_verdict fionread on drop")) test_sockmap_skb_verdict_fionread(false); + if (test__start_subtest("sockmap skb_verdict change tail")) + test_sockmap_skb_verdict_change_tail(); if (test__start_subtest("sockmap skb_verdict msg_f_peek")) test_sockmap_skb_verdict_peek(); if (test__start_subtest("sockmap skb_verdict msg_f_peek with link")) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h index 38e35c72bdaa..3e5571dd578d 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -1,139 +1,12 @@ #ifndef __SOCKMAP_HELPERS__ #define __SOCKMAP_HELPERS__ -#include <linux/vm_sockets.h> +#include "socket_helpers.h" -/* include/linux/net.h */ -#define SOCK_TYPE_MASK 0xf - -#define IO_TIMEOUT_SEC 30 -#define MAX_STRERR_LEN 256 #define MAX_TEST_NAME 80 -/* workaround for older vm_sockets.h */ -#ifndef VMADDR_CID_LOCAL -#define VMADDR_CID_LOCAL 1 -#endif - #define __always_unused __attribute__((__unused__)) -/* include/linux/cleanup.h */ -#define __get_and_null(p, nullvalue) \ - ({ \ - __auto_type __ptr = &(p); \ - __auto_type __val = *__ptr; \ - *__ptr = nullvalue; \ - __val; \ - }) - -#define take_fd(fd) __get_and_null(fd, -EBADF) - -#define _FAIL(errnum, fmt...) \ - ({ \ - error_at_line(0, (errnum), __func__, __LINE__, fmt); \ - CHECK_FAIL(true); \ - }) -#define FAIL(fmt...) _FAIL(0, fmt) -#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) -#define FAIL_LIBBPF(err, msg) \ - ({ \ - char __buf[MAX_STRERR_LEN]; \ - libbpf_strerror((err), __buf, sizeof(__buf)); \ - FAIL("%s: %s", (msg), __buf); \ - }) - -/* Wrappers that fail the test on error and report it. */ - -#define xaccept_nonblock(fd, addr, len) \ - ({ \ - int __ret = \ - accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("accept"); \ - __ret; \ - }) - -#define xbind(fd, addr, len) \ - ({ \ - int __ret = bind((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("bind"); \ - __ret; \ - }) - -#define xclose(fd) \ - ({ \ - int __ret = close((fd)); \ - if (__ret == -1) \ - FAIL_ERRNO("close"); \ - __ret; \ - }) - -#define xconnect(fd, addr, len) \ - ({ \ - int __ret = connect((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("connect"); \ - __ret; \ - }) - -#define xgetsockname(fd, addr, len) \ - ({ \ - int __ret = getsockname((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockname"); \ - __ret; \ - }) - -#define xgetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = getsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockopt(" #name ")"); \ - __ret; \ - }) - -#define xlisten(fd, backlog) \ - ({ \ - int __ret = listen((fd), (backlog)); \ - if (__ret == -1) \ - FAIL_ERRNO("listen"); \ - __ret; \ - }) - -#define xsetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = setsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("setsockopt(" #name ")"); \ - __ret; \ - }) - -#define xsend(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = send((fd), (buf), (len), (flags)); \ - if (__ret == -1) \ - FAIL_ERRNO("send"); \ - __ret; \ - }) - -#define xrecv_nonblock(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ - IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("recv"); \ - __ret; \ - }) - -#define xsocket(family, sotype, flags) \ - ({ \ - int __ret = socket(family, sotype, flags); \ - if (__ret == -1) \ - FAIL_ERRNO("socket"); \ - __ret; \ - }) - #define xbpf_map_delete_elem(fd, key) \ ({ \ int __ret = bpf_map_delete_elem((fd), (key)); \ @@ -193,130 +66,6 @@ __ret; \ }) -static inline void close_fd(int *fd) -{ - if (*fd >= 0) - xclose(*fd); -} - -#define __close_fd __attribute__((cleanup(close_fd))) - -static inline int poll_connect(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set wfds; - int r, eval; - socklen_t esize = sizeof(eval); - - FD_ZERO(&wfds); - FD_SET(fd, &wfds); - - r = select(fd + 1, NULL, &wfds, NULL, &timeout); - if (r == 0) - errno = ETIME; - if (r != 1) - return -1; - - if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0) - return -1; - if (eval != 0) { - errno = eval; - return -1; - } - - return 0; -} - -static inline int poll_read(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set rfds; - int r; - - FD_ZERO(&rfds); - FD_SET(fd, &rfds); - - r = select(fd + 1, &rfds, NULL, NULL, &timeout); - if (r == 0) - errno = ETIME; - - return r == 1 ? 0 : -1; -} - -static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return accept(fd, addr, len); -} - -static inline int recv_timeout(int fd, void *buf, size_t len, int flags, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return recv(fd, buf, len, flags); -} - -static inline void init_addr_loopback4(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); - - addr4->sin_family = AF_INET; - addr4->sin_port = 0; - addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - *len = sizeof(*addr4); -} - -static inline void init_addr_loopback6(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); - - addr6->sin6_family = AF_INET6; - addr6->sin6_port = 0; - addr6->sin6_addr = in6addr_loopback; - *len = sizeof(*addr6); -} - -static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); - - addr->svm_family = AF_VSOCK; - addr->svm_port = VMADDR_PORT_ANY; - addr->svm_cid = VMADDR_CID_LOCAL; - *len = sizeof(*addr); -} - -static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, - socklen_t *len) -{ - switch (family) { - case AF_INET: - init_addr_loopback4(ss, len); - return; - case AF_INET6: - init_addr_loopback6(ss, len); - return; - case AF_VSOCK: - init_addr_loopback_vsock(ss, len); - return; - default: - FAIL("unsupported address family %d", family); - } -} - -static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) -{ - return (struct sockaddr *)ss; -} - static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) { u64 value; @@ -334,136 +83,4 @@ static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); } -static inline int enable_reuseport(int s, int progfd) -{ - int err, one = 1; - - err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); - if (err) - return -1; - err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, - sizeof(progfd)); - if (err) - return -1; - - return 0; -} - -static inline int socket_loopback_reuseport(int family, int sotype, int progfd) -{ - struct sockaddr_storage addr; - socklen_t len = 0; - int err, s; - - init_addr_loopback(family, &addr, &len); - - s = xsocket(family, sotype, 0); - if (s == -1) - return -1; - - if (progfd >= 0) - enable_reuseport(s, progfd); - - err = xbind(s, sockaddr(&addr), len); - if (err) - goto close; - - if (sotype & SOCK_DGRAM) - return s; - - err = xlisten(s, SOMAXCONN); - if (err) - goto close; - - return s; -close: - xclose(s); - return -1; -} - -static inline int socket_loopback(int family, int sotype) -{ - return socket_loopback_reuseport(family, sotype, -1); -} - -static inline int create_pair(int family, int sotype, int *p0, int *p1) -{ - __close_fd int s, c = -1, p = -1; - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); - int err; - - s = socket_loopback(family, sotype); - if (s < 0) - return s; - - err = xgetsockname(s, sockaddr(&addr), &len); - if (err) - return err; - - c = xsocket(family, sotype, 0); - if (c < 0) - return c; - - err = connect(c, sockaddr(&addr), len); - if (err) { - if (errno != EINPROGRESS) { - FAIL_ERRNO("connect"); - return err; - } - - err = poll_connect(c, IO_TIMEOUT_SEC); - if (err) { - FAIL_ERRNO("poll_connect"); - return err; - } - } - - switch (sotype & SOCK_TYPE_MASK) { - case SOCK_DGRAM: - err = xgetsockname(c, sockaddr(&addr), &len); - if (err) - return err; - - err = xconnect(s, sockaddr(&addr), len); - if (err) - return err; - - *p0 = take_fd(s); - break; - case SOCK_STREAM: - case SOCK_SEQPACKET: - p = xaccept_nonblock(s, NULL, NULL); - if (p < 0) - return p; - - *p0 = take_fd(p); - break; - default: - FAIL("Unsupported socket type %#x", sotype); - return -EOPNOTSUPP; - } - - *p1 = take_fd(c); - return 0; -} - -static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, - int *p0, int *p1) -{ - int err; - - err = create_pair(family, sotype, c0, p0); - if (err) - return err; - - err = create_pair(family, sotype, c1, p1); - if (err) { - close(*c0); - close(*p0); - } - - return err; -} - #endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 05d0e07da394..ba6b3ec1156a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -2,7 +2,7 @@ #include <test_progs.h> #include "cgroup_helpers.h" -#include <linux/tcp.h> +#include <netinet/tcp.h> #include <linux/netlink.h> #include "sockopt_sk.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c new file mode 100644 index 000000000000..74752233e779 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <error.h> +#include <test_progs.h> +#include <linux/pkt_cls.h> + +#include "test_tc_change_tail.skel.h" +#include "socket_helpers.h" + +#define LO_IFINDEX 1 + +void test_tc_change_tail(void) +{ + LIBBPF_OPTS(bpf_tcx_opts, tcx_opts); + struct test_tc_change_tail *skel = NULL; + struct bpf_link *link; + int c1, p1; + char buf[2]; + int ret; + + skel = test_tc_change_tail__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tc_change_tail__open_and_load")) + return; + + link = bpf_program__attach_tcx(skel->progs.change_tail, LO_IFINDEX, + &tcx_opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_tcx")) + goto destroy; + + skel->links.change_tail = link; + ret = create_pair(AF_INET, SOCK_DGRAM, &c1, &p1); + if (!ASSERT_OK(ret, "create_pair")) + goto destroy; + + ret = xsend(p1, "Tr", 2, 0); + ASSERT_EQ(ret, 2, "xsend(p1)"); + ret = recv(c1, buf, 2, 0); + ASSERT_EQ(ret, 2, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + ret = xsend(p1, "G", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 2, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + ret = xsend(p1, "E", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 1, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + + ret = xsend(p1, "Z", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 1, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + + close(c1); + close(p1); +destroy: + test_tc_change_tail__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c index 151a4210028f..2461d183dee5 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c @@ -14,10 +14,16 @@ #include "netlink_helpers.h" #include "tc_helpers.h" +#define NETKIT_HEADROOM 32 +#define NETKIT_TAILROOM 8 + #define MARK 42 #define PRIO 0xeb9f #define ICMP_ECHO 8 +#define FLAG_ADJUST_ROOM (1 << 0) +#define FLAG_SAME_NETNS (1 << 1) + struct icmphdr { __u8 type; __u8 code; @@ -35,7 +41,7 @@ struct iplink_req { }; static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, - bool same_netns, int scrub, int peer_scrub) + int scrub, int peer_scrub, __u32 flags) { struct rtnl_handle rth = { .fd = -1 }; struct iplink_req req = {}; @@ -63,6 +69,10 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, addattr32(&req.n, sizeof(req), IFLA_NETKIT_SCRUB, scrub); addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_SCRUB, peer_scrub); addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode); + if (flags & FLAG_ADJUST_ROOM) { + addattr16(&req.n, sizeof(req), IFLA_NETKIT_HEADROOM, NETKIT_HEADROOM); + addattr16(&req.n, sizeof(req), IFLA_NETKIT_TAILROOM, NETKIT_TAILROOM); + } addattr_nest_end(&req.n, data); addattr_nest_end(&req.n, linkinfo); @@ -87,7 +97,7 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, " addr ee:ff:bb:cc:aa:dd"), "set hwaddress"); } - if (same_netns) { + if (flags & FLAG_SAME_NETNS) { ASSERT_OK(system("ip link set dev " netkit_peer " up"), "up peer"); ASSERT_OK(system("ip addr add dev " netkit_peer " 10.0.0.2/24"), @@ -184,8 +194,8 @@ void serial_test_tc_netkit_basic(void) int err, ifindex; err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, 0); if (err) return; @@ -299,8 +309,8 @@ static void serial_test_tc_netkit_multi_links_target(int mode, int target) int err, ifindex; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, 0); if (err) return; @@ -428,8 +438,8 @@ static void serial_test_tc_netkit_multi_opts_target(int mode, int target) int err, ifindex; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, 0); if (err) return; @@ -543,8 +553,8 @@ void serial_test_tc_netkit_device(void) int err, ifindex, ifindex2; err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS, - &ifindex, true, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, FLAG_SAME_NETNS); if (err) return; @@ -655,8 +665,8 @@ static void serial_test_tc_netkit_neigh_links_target(int mode, int target) int err, ifindex; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, 0); if (err) return; @@ -733,8 +743,8 @@ static void serial_test_tc_netkit_pkt_type_mode(int mode) struct bpf_link *link; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, true, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, FLAG_SAME_NETNS); if (err) return; @@ -799,7 +809,7 @@ void serial_test_tc_netkit_pkt_type(void) serial_test_tc_netkit_pkt_type_mode(NETKIT_L3); } -static void serial_test_tc_netkit_scrub_type(int scrub) +static void serial_test_tc_netkit_scrub_type(int scrub, bool room) { LIBBPF_OPTS(bpf_netkit_opts, optl); struct test_tc_link *skel; @@ -807,7 +817,8 @@ static void serial_test_tc_netkit_scrub_type(int scrub) int err, ifindex; err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, scrub, scrub); + &ifindex, scrub, scrub, + room ? FLAG_ADJUST_ROOM : 0); if (err) return; @@ -842,6 +853,8 @@ static void serial_test_tc_netkit_scrub_type(int scrub) ASSERT_EQ(skel->bss->seen_tc8, true, "seen_tc8"); ASSERT_EQ(skel->bss->mark, scrub == NETKIT_SCRUB_NONE ? MARK : 0, "mark"); ASSERT_EQ(skel->bss->prio, scrub == NETKIT_SCRUB_NONE ? PRIO : 0, "prio"); + ASSERT_EQ(skel->bss->headroom, room ? NETKIT_HEADROOM : 0, "headroom"); + ASSERT_EQ(skel->bss->tailroom, room ? NETKIT_TAILROOM : 0, "tailroom"); cleanup: test_tc_link__destroy(skel); @@ -852,6 +865,6 @@ cleanup: void serial_test_tc_netkit_scrub(void) { - serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT); - serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE); + serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT, false); + serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE, true); } diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 3ee40ee9413a..8a0e1ff8a2dc 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -52,6 +52,8 @@ #include "verifier_map_ptr_mixing.skel.h" #include "verifier_map_ret_val.skel.h" #include "verifier_masking.skel.h" +#include "verifier_may_goto_1.skel.h" +#include "verifier_may_goto_2.skel.h" #include "verifier_meta_access.skel.h" #include "verifier_movsx.skel.h" #include "verifier_mtu.skel.h" @@ -98,6 +100,7 @@ #include "verifier_xdp_direct_packet_access.skel.h" #include "verifier_bits_iter.skel.h" #include "verifier_lsm.skel.h" +#include "irq.skel.h" #define MAX_ENTRIES 11 @@ -181,6 +184,8 @@ void test_verifier_map_ptr(void) { RUN(verifier_map_ptr); } void test_verifier_map_ptr_mixing(void) { RUN(verifier_map_ptr_mixing); } void test_verifier_map_ret_val(void) { RUN(verifier_map_ret_val); } void test_verifier_masking(void) { RUN(verifier_masking); } +void test_verifier_may_goto_1(void) { RUN(verifier_may_goto_1); } +void test_verifier_may_goto_2(void) { RUN(verifier_may_goto_2); } void test_verifier_meta_access(void) { RUN(verifier_meta_access); } void test_verifier_movsx(void) { RUN(verifier_movsx); } void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); } @@ -225,6 +230,7 @@ void test_verifier_xdp(void) { RUN(verifier_xdp); } void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); } void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); } void test_verifier_lsm(void) { RUN(verifier_lsm); } +void test_irq(void) { RUN(irq); } void test_verifier_mtu(void) { RUN(verifier_mtu); } static int init_test_val_map(struct bpf_object *obj, char *map_name) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 53d6ad8c2257..b2b2d85dbb1b 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -82,6 +82,8 @@ static void test_xdp_adjust_tail_grow2(void) /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ #if defined(__s390x__) int tailroom = 512; +#elif defined(__powerpc__) + int tailroom = 384; #else int tailroom = 320; #endif diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index 6d8b54124cb3..fb952703653e 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -17,7 +17,7 @@ #include "network_helpers.h" #include <linux/if_bonding.h> #include <linux/limits.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <uapi/linux/netdev.h> #include "xdp_dummy.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index e6a783c7f5db..937da9b7532a 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -2,6 +2,14 @@ #include <test_progs.h> #include <network_helpers.h> #include "test_xdp_context_test_run.skel.h" +#include "test_xdp_meta.skel.h" + +#define TX_ADDR "10.0.0.1" +#define RX_ADDR "10.0.0.2" +#define RX_NAME "veth0" +#define TX_NAME "veth1" +#define TX_NETNS "xdp_context_tx" +#define RX_NETNS "xdp_context_rx" void test_xdp_context_error(int prog_fd, struct bpf_test_run_opts opts, __u32 data_meta, __u32 data, __u32 data_end, @@ -103,3 +111,82 @@ void test_xdp_context_test_run(void) test_xdp_context_test_run__destroy(skel); } + +void test_xdp_context_functional(void) +{ + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + struct netns_obj *rx_ns = NULL, *tx_ns = NULL; + struct bpf_program *tc_prog, *xdp_prog; + struct test_xdp_meta *skel = NULL; + struct nstoken *nstoken = NULL; + int rx_ifindex; + int ret; + + tx_ns = netns_new(TX_NETNS, false); + if (!ASSERT_OK_PTR(tx_ns, "create tx_ns")) + return; + + rx_ns = netns_new(RX_NETNS, false); + if (!ASSERT_OK_PTR(rx_ns, "create rx_ns")) + goto close; + + SYS(close, "ip link add " RX_NAME " netns " RX_NETNS + " type veth peer name " TX_NAME " netns " TX_NETNS); + + nstoken = open_netns(RX_NETNS); + if (!ASSERT_OK_PTR(nstoken, "setns rx_ns")) + goto close; + + SYS(close, "ip addr add " RX_ADDR "/24 dev " RX_NAME); + SYS(close, "ip link set dev " RX_NAME " up"); + + skel = test_xdp_meta__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open and load skeleton")) + goto close; + + rx_ifindex = if_nametoindex(RX_NAME); + if (!ASSERT_GE(rx_ifindex, 0, "if_nametoindex rx")) + goto close; + + tc_hook.ifindex = rx_ifindex; + ret = bpf_tc_hook_create(&tc_hook); + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + goto close; + + tc_prog = bpf_object__find_program_by_name(skel->obj, "ing_cls"); + if (!ASSERT_OK_PTR(tc_prog, "open ing_cls prog")) + goto close; + + tc_opts.prog_fd = bpf_program__fd(tc_prog); + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto close; + + xdp_prog = bpf_object__find_program_by_name(skel->obj, "ing_xdp"); + if (!ASSERT_OK_PTR(xdp_prog, "open ing_xdp prog")) + goto close; + + ret = bpf_xdp_attach(rx_ifindex, + bpf_program__fd(xdp_prog), + 0, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto close; + + close_netns(nstoken); + + nstoken = open_netns(TX_NETNS); + if (!ASSERT_OK_PTR(nstoken, "setns tx_ns")) + goto close; + + SYS(close, "ip addr add " TX_ADDR "/24 dev " TX_NAME); + SYS(close, "ip link set dev " TX_NAME " up"); + ASSERT_OK(SYS_NOFAIL("ping -c 1 " RX_ADDR), "ping"); + +close: + close_netns(nstoken); + test_xdp_meta__destroy(skel); + netns_free(rx_ns); + netns_free(tx_ns); +} + diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index bad0ea167be7..7dac044664ac 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -7,10 +7,11 @@ #include <linux/if_link.h> #include <linux/ipv6.h> #include <linux/in6.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <bpf/bpf_endian.h> #include <uapi/linux/netdev.h> #include "test_xdp_do_redirect.skel.h" +#include "xdp_dummy.skel.h" struct udp_packet { struct ethhdr eth; @@ -246,3 +247,166 @@ out: SYS_NOFAIL("ip netns del testns"); test_xdp_do_redirect__destroy(skel); } + +#define NS_NB 3 +#define NS0 "NS0" +#define NS1 "NS1" +#define NS2 "NS2" +#define IPV4_NETWORK "10.1.1" +#define VETH1_INDEX 111 +#define VETH2_INDEX 222 + +struct test_data { + struct netns_obj *ns[NS_NB]; + u32 xdp_flags; +}; + +static void cleanup(struct test_data *data) +{ + int i; + + for (i = 0; i < NS_NB; i++) + netns_free(data->ns[i]); +} + +/** + * ping_setup - + * Create two veth peers and forward packets in-between using XDP + * + * ------------ ------------ + * | NS1 | | NS2 | + * | veth0 | | veth0 | + * | 10.1.1.1 | | 10.1.1.2 | + * -----|------ ------|----- + * | | + * | | + * -----|-----------------------|------- + * | veth1 veth2 | + * | (id:111) (id:222) | + * | | | | + * | ----- xdp forwarding ----- | + * | | + * | NS0 | + * ------------------------------------- + */ +static int ping_setup(struct test_data *data) +{ + int i; + + data->ns[0] = netns_new(NS0, false); + if (!ASSERT_OK_PTR(data->ns[0], "create ns")) + return -1; + + for (i = 1; i < NS_NB; i++) { + char ns_name[4] = {}; + + snprintf(ns_name, 4, "NS%d", i); + data->ns[i] = netns_new(ns_name, false); + if (!ASSERT_OK_PTR(data->ns[i], "create ns")) + goto fail; + + SYS(fail, + "ip -n %s link add veth%d index %d%d%d type veth peer name veth0 netns %s", + NS0, i, i, i, i, ns_name); + SYS(fail, "ip -n %s link set veth%d up", NS0, i); + + SYS(fail, "ip -n %s addr add %s.%d/24 dev veth0", ns_name, IPV4_NETWORK, i); + SYS(fail, "ip -n %s link set veth0 up", ns_name); + } + + return 0; + +fail: + cleanup(data); + return -1; +} + +static void ping_test(struct test_data *data) +{ + struct test_xdp_do_redirect *skel = NULL; + struct xdp_dummy *skel_dummy = NULL; + struct nstoken *nstoken = NULL; + int i, ret; + + skel_dummy = xdp_dummy__open_and_load(); + if (!ASSERT_OK_PTR(skel_dummy, "open and load xdp_dummy skeleton")) + goto close; + + for (i = 1; i < NS_NB; i++) { + char ns_name[4] = {}; + + snprintf(ns_name, 4, "NS%d", i); + nstoken = open_netns(ns_name); + if (!ASSERT_OK_PTR(nstoken, "open ns")) + goto close; + + ret = bpf_xdp_attach(if_nametoindex("veth0"), + bpf_program__fd(skel_dummy->progs.xdp_dummy_prog), + data->xdp_flags, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach dummy_prog")) + goto close; + + close_netns(nstoken); + nstoken = NULL; + } + + skel = test_xdp_do_redirect__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open and load skeleton")) + goto close; + + nstoken = open_netns(NS0); + if (!ASSERT_OK_PTR(nstoken, "open NS0")) + goto close; + + ret = bpf_xdp_attach(VETH2_INDEX, + bpf_program__fd(skel->progs.xdp_redirect_to_111), + data->xdp_flags, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto close; + + ret = bpf_xdp_attach(VETH1_INDEX, + bpf_program__fd(skel->progs.xdp_redirect_to_222), + data->xdp_flags, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto close; + + close_netns(nstoken); + nstoken = NULL; + + nstoken = open_netns(NS1); + if (!ASSERT_OK_PTR(nstoken, "open NS1")) + goto close; + + SYS(close, "ping -c 1 %s.2 > /dev/null", IPV4_NETWORK); + +close: + close_netns(nstoken); + xdp_dummy__destroy(skel_dummy); + test_xdp_do_redirect__destroy(skel); +} + + +static void xdp_redirect_ping(u32 xdp_flags) +{ + struct test_data data = {}; + + if (ping_setup(&data) < 0) + return; + + data.xdp_flags = xdp_flags; + ping_test(&data); + cleanup(&data); +} + +void test_xdp_index_redirect(void) +{ + if (test__start_subtest("noflag")) + xdp_redirect_ping(0); + + if (test__start_subtest("drvflag")) + xdp_redirect_ping(XDP_FLAGS_DRV_MODE); + + if (test__start_subtest("skbflag")) + xdp_redirect_ping(XDP_FLAGS_SKB_MODE); +} + diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c index e1bf141d3401..3f9146d83d79 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c @@ -3,7 +3,7 @@ #include <network_helpers.h> #include <bpf/btf.h> #include <linux/if_link.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <net/if.h> #include <unistd.h> diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index c87ee2bf558c..3d47878ef6bf 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -10,7 +10,7 @@ #include <linux/errqueue.h> #include <linux/if_link.h> #include <linux/net_tstamp.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <sys/mman.h> #include <net/if.h> #include <poll.h> @@ -133,23 +133,6 @@ static void close_xsk(struct xsk *xsk) munmap(xsk->umem_area, UMEM_SIZE); } -static void ip_csum(struct iphdr *iph) -{ - __u32 sum = 0; - __u16 *p; - int i; - - iph->check = 0; - p = (void *)iph; - for (i = 0; i < sizeof(*iph) / sizeof(*p); i++) - sum += p[i]; - - while (sum >> 16) - sum = (sum & 0xffff) + (sum >> 16); - - iph->check = ~sum; -} - static int generate_packet(struct xsk *xsk, __u16 dst_port) { struct xsk_tx_metadata *meta; @@ -192,7 +175,7 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port) iph->protocol = IPPROTO_UDP; ASSERT_EQ(inet_pton(FAMILY, TX_ADDR, &iph->saddr), 1, "inet_pton(TX_ADDR)"); ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)"); - ip_csum(iph); + iph->check = build_ip_csum(iph); udph->source = htons(UDP_SOURCE_PORT); udph->dest = htons(dst_port); diff --git a/tools/testing/selftests/bpf/progs/bad_struct_ops.c b/tools/testing/selftests/bpf/progs/bad_struct_ops.c index b7e175cd0af0..b3f77b4561c8 100644 --- a/tools/testing/selftests/bpf/progs/bad_struct_ops.c +++ b/tools/testing/selftests/bpf/progs/bad_struct_ops.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c index 56c764df8196..5d6fc7f01ebb 100644 --- a/tools/testing/selftests/bpf/progs/cb_refs.c +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -2,7 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr *ptr; diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_direct_packet_access.c b/tools/testing/selftests/bpf/progs/cgroup_skb_direct_packet_access.c new file mode 100644 index 000000000000..e32b07d802bb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_skb_direct_packet_access.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u32 data_end; + +SEC("cgroup_skb/ingress") +int direct_packet_access(struct __sk_buff *skb) +{ + data_end = skb->data_end; + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index dfd817d0348c..bd8f15229f5c 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -192,7 +192,7 @@ done: /* Can't add a dynptr to a map */ SEC("?raw_tp") -__failure __msg("invalid indirect read from stack") +__failure __msg("invalid read from stack") int add_dynptr_to_map1(void *ctx) { struct bpf_dynptr ptr; @@ -210,7 +210,7 @@ int add_dynptr_to_map1(void *ctx) /* Can't add a struct with an embedded dynptr to a map */ SEC("?raw_tp") -__failure __msg("invalid indirect read from stack") +__failure __msg("invalid read from stack") int add_dynptr_to_map2(void *ctx) { struct test_info x; @@ -398,7 +398,7 @@ int data_slice_missing_null_check2(void *ctx) * dynptr argument */ SEC("?raw_tp") -__failure __msg("invalid indirect read from stack") +__failure __msg("invalid read from stack") int invalid_helper1(void *ctx) { struct bpf_dynptr ptr; diff --git a/tools/testing/selftests/bpf/progs/epilogue_exit.c b/tools/testing/selftests/bpf/progs/epilogue_exit.c index 33d3a57bee90..35fec7c75bef 100644 --- a/tools/testing/selftests/bpf/progs/epilogue_exit.c +++ b/tools/testing/selftests/bpf/progs/epilogue_exit.c @@ -4,8 +4,8 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/epilogue_tailcall.c b/tools/testing/selftests/bpf/progs/epilogue_tailcall.c index 7275dd594de0..153514691ba4 100644 --- a/tools/testing/selftests/bpf/progs/epilogue_tailcall.c +++ b/tools/testing/selftests/bpf/progs/epilogue_tailcall.c @@ -4,8 +4,8 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c index fe0f3fa5aab6..8a0fdff89927 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_fail.c +++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c @@ -131,7 +131,7 @@ int reject_subprog_with_lock(void *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_rcu_read_lock-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_rcu_read_lock-ed region") int reject_with_rcu_read_lock(void *ctx) { bpf_rcu_read_lock(); @@ -147,7 +147,7 @@ __noinline static int throwing_subprog(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_rcu_read_lock-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_rcu_read_lock-ed region") int reject_subprog_with_rcu_read_lock(void *ctx) { bpf_rcu_read_lock(); diff --git a/tools/testing/selftests/bpf/progs/find_vma.c b/tools/testing/selftests/bpf/progs/find_vma.c index 38034fb82530..02b82774469c 100644 --- a/tools/testing/selftests/bpf/progs/find_vma.c +++ b/tools/testing/selftests/bpf/progs/find_vma.c @@ -25,7 +25,7 @@ static long check_vma(struct task_struct *task, struct vm_area_struct *vma, { if (vma->vm_file) bpf_probe_read_kernel_str(d_iname, DNAME_INLINE_LEN - 1, - vma->vm_file->f_path.dentry->d_iname); + vma->vm_file->f_path.dentry->d_shortname.string); /* check for VM_EXEC */ if (vma->vm_flags & VM_EXEC) diff --git a/tools/testing/selftests/bpf/progs/free_timer.c b/tools/testing/selftests/bpf/progs/free_timer.c new file mode 100644 index 000000000000..4501ae8fc414 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/free_timer.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025. Huawei Technologies Co., Ltd */ +#include <linux/bpf.h> +#include <time.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#define MAX_ENTRIES 8 + +struct map_value { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, MAX_ENTRIES); +} map SEC(".maps"); + +static int timer_cb(void *map, void *key, struct map_value *value) +{ + volatile int sum = 0; + int i; + + bpf_for(i, 0, 1024 * 1024) sum += i; + + return 0; +} + +static int start_cb(int key) +{ + struct map_value *value; + + value = bpf_map_lookup_elem(&map, (void *)&key); + if (!value) + return 0; + + bpf_timer_init(&value->timer, &map, CLOCK_MONOTONIC); + bpf_timer_set_callback(&value->timer, timer_cb); + /* Hope 100us will be enough to wake-up and run the overwrite thread */ + bpf_timer_start(&value->timer, 100000, BPF_F_TIMER_CPU_PIN); + + return 0; +} + +static int overwrite_cb(int key) +{ + struct map_value zero = {}; + + /* Free the timer which may run on other CPU */ + bpf_map_update_elem(&map, (void *)&key, &zero, BPF_ANY); + + return 0; +} + +SEC("syscall") +int BPF_PROG(start_timer) +{ + bpf_loop(MAX_ENTRIES, start_cb, NULL, 0); + return 0; +} + +SEC("syscall") +int BPF_PROG(overwrite_timer) +{ + bpf_loop(MAX_ENTRIES, overwrite_cb, NULL, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/irq.c b/tools/testing/selftests/bpf/progs/irq.c new file mode 100644 index 000000000000..b0b53d980964 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/irq.c @@ -0,0 +1,444 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +unsigned long global_flags; + +extern void bpf_local_irq_save(unsigned long *) __weak __ksym; +extern void bpf_local_irq_restore(unsigned long *) __weak __ksym; +extern int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void *unsafe_ptr__ign, u64 flags) __weak __ksym; + +SEC("?tc") +__failure __msg("arg#0 doesn't point to an irq flag on stack") +int irq_save_bad_arg(struct __sk_buff *ctx) +{ + bpf_local_irq_save(&global_flags); + return 0; +} + +SEC("?tc") +__failure __msg("arg#0 doesn't point to an irq flag on stack") +int irq_restore_bad_arg(struct __sk_buff *ctx) +{ + bpf_local_irq_restore(&global_flags); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_2(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_3(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + bpf_local_irq_save(&flags3); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_3_minus_2(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + bpf_local_irq_save(&flags3); + bpf_local_irq_restore(&flags3); + bpf_local_irq_restore(&flags2); + return 0; +} + +static __noinline void local_irq_save(unsigned long *flags) +{ + bpf_local_irq_save(flags); +} + +static __noinline void local_irq_restore(unsigned long *flags) +{ + bpf_local_irq_restore(flags); +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_1_subprog(struct __sk_buff *ctx) +{ + unsigned long flags; + + local_irq_save(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_2_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + + local_irq_save(&flags1); + local_irq_save(&flags2); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_3_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save(&flags1); + local_irq_save(&flags2); + local_irq_save(&flags3); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_3_minus_2_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save(&flags1); + local_irq_save(&flags2); + local_irq_save(&flags3); + local_irq_restore(&flags3); + local_irq_restore(&flags2); + return 0; +} + +SEC("?tc") +__success +int irq_balance(struct __sk_buff *ctx) +{ + unsigned long flags; + + local_irq_save(&flags); + local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__success +int irq_balance_n(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save(&flags1); + local_irq_save(&flags2); + local_irq_save(&flags3); + local_irq_restore(&flags3); + local_irq_restore(&flags2); + local_irq_restore(&flags1); + return 0; +} + +static __noinline void local_irq_balance(void) +{ + unsigned long flags; + + local_irq_save(&flags); + local_irq_restore(&flags); +} + +static __noinline void local_irq_balance_n(void) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save(&flags1); + local_irq_save(&flags2); + local_irq_save(&flags3); + local_irq_restore(&flags3); + local_irq_restore(&flags2); + local_irq_restore(&flags1); +} + +SEC("?tc") +__success +int irq_balance_subprog(struct __sk_buff *ctx) +{ + local_irq_balance(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("sleepable helper bpf_copy_from_user#") +int irq_sleepable_helper(void *ctx) +{ + unsigned long flags; + u32 data; + + local_irq_save(&flags); + bpf_copy_from_user(&data, sizeof(data), NULL); + local_irq_restore(&flags); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("kernel func bpf_copy_from_user_str is sleepable within IRQ-disabled region") +int irq_sleepable_kfunc(void *ctx) +{ + unsigned long flags; + u32 data; + + local_irq_save(&flags); + bpf_copy_from_user_str(&data, sizeof(data), NULL, 0); + local_irq_restore(&flags); + return 0; +} + +int __noinline global_local_irq_balance(void) +{ + local_irq_balance_n(); + return 0; +} + +SEC("?tc") +__failure __msg("global function calls are not allowed with IRQs disabled") +int irq_global_subprog(struct __sk_buff *ctx) +{ + unsigned long flags; + + bpf_local_irq_save(&flags); + global_local_irq_balance(); + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_restore_ooo(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + bpf_local_irq_restore(&flags1); + bpf_local_irq_restore(&flags2); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_restore_ooo_3(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + bpf_local_irq_restore(&flags2); + bpf_local_irq_save(&flags3); + bpf_local_irq_restore(&flags1); + bpf_local_irq_restore(&flags3); + return 0; +} + +static __noinline void local_irq_save_3(unsigned long *flags1, unsigned long *flags2, + unsigned long *flags3) +{ + local_irq_save(flags1); + local_irq_save(flags2); + local_irq_save(flags3); +} + +SEC("?tc") +__success +int irq_restore_3_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save_3(&flags1, &flags2, &flags3); + bpf_local_irq_restore(&flags3); + bpf_local_irq_restore(&flags2); + bpf_local_irq_restore(&flags1); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_restore_4_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + unsigned long flags4; + + local_irq_save_3(&flags1, &flags2, &flags3); + bpf_local_irq_restore(&flags3); + bpf_local_irq_save(&flags4); + bpf_local_irq_restore(&flags4); + bpf_local_irq_restore(&flags1); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_restore_ooo_3_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save_3(&flags1, &flags2, &flags3); + bpf_local_irq_restore(&flags3); + bpf_local_irq_restore(&flags2); + bpf_local_irq_save(&flags3); + bpf_local_irq_restore(&flags1); + return 0; +} + +SEC("?tc") +__failure __msg("expected an initialized") +int irq_restore_invalid(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags = 0xfaceb00c; + + bpf_local_irq_save(&flags1); + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("expected uninitialized") +int irq_save_invalid(struct __sk_buff *ctx) +{ + unsigned long flags1; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags1); + return 0; +} + +SEC("?tc") +__failure __msg("expected an initialized") +int irq_restore_iter(struct __sk_buff *ctx) +{ + struct bpf_iter_num it; + + bpf_iter_num_new(&it, 0, 42); + bpf_local_irq_restore((unsigned long *)&it); + return 0; +} + +SEC("?tc") +__failure __msg("Unreleased reference id=1") +int irq_save_iter(struct __sk_buff *ctx) +{ + struct bpf_iter_num it; + + /* Ensure same sized slot has st->ref_obj_id set, so we reject based on + * slot_type != STACK_IRQ_FLAG... + */ + _Static_assert(sizeof(it) == sizeof(unsigned long), "broken iterator size"); + + bpf_iter_num_new(&it, 0, 42); + bpf_local_irq_save((unsigned long *)&it); + bpf_local_irq_restore((unsigned long *)&it); + return 0; +} + +SEC("?tc") +__failure __msg("expected an initialized") +int irq_flag_overwrite(struct __sk_buff *ctx) +{ + unsigned long flags; + + bpf_local_irq_save(&flags); + flags = 0xdeadbeef; + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("expected an initialized") +int irq_flag_overwrite_partial(struct __sk_buff *ctx) +{ + unsigned long flags; + + bpf_local_irq_save(&flags); + *(((char *)&flags) + 1) = 0xff; + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_ooo_refs_array(struct __sk_buff *ctx) +{ + unsigned long flags[4]; + struct { int i; } *p; + + /* refs=1 */ + bpf_local_irq_save(&flags[0]); + + /* refs=1,2 */ + p = bpf_obj_new(typeof(*p)); + if (!p) { + bpf_local_irq_restore(&flags[0]); + return 0; + } + + /* refs=1,2,3 */ + bpf_local_irq_save(&flags[1]); + + /* refs=1,2,3,4 */ + bpf_local_irq_save(&flags[2]); + + /* Now when we remove ref=2, the verifier must not break the ordering in + * the refs array between 1,3,4. With an older implementation, the + * verifier would swap the last element with the removed element, but to + * maintain the stack property we need to use memmove. + */ + bpf_obj_drop(p); + + /* Save and restore to reset active_irq_id to 3, as the ordering is now + * refs=1,4,3. When restoring the linear scan will find prev_id in order + * as 3 instead of 4. + */ + bpf_local_irq_save(&flags[3]); + bpf_local_irq_restore(&flags[3]); + + /* With the incorrect implementation, we can release flags[1], flags[2], + * and flags[0], i.e. in the wrong order. + */ + bpf_local_irq_restore(&flags[1]); + bpf_local_irq_restore(&flags[2]); + bpf_local_irq_restore(&flags[0]); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 7c969c127573..190822b2f08b 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -524,11 +524,11 @@ int iter_subprog_iters(const void *ctx) } struct { - __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(type, BPF_MAP_TYPE_HASH); __type(key, int); __type(value, int); __uint(max_entries, 1000); -} arr_map SEC(".maps"); +} hash_map SEC(".maps"); SEC("?raw_tp") __failure __msg("invalid mem access 'scalar'") @@ -539,7 +539,7 @@ int iter_err_too_permissive1(const void *ctx) MY_PID_GUARD(); - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); if (!map_val) return 0; @@ -561,12 +561,12 @@ int iter_err_too_permissive2(const void *ctx) MY_PID_GUARD(); - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); if (!map_val) return 0; bpf_repeat(1000000) { - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); } *map_val = 123; @@ -585,7 +585,7 @@ int iter_err_too_permissive3(const void *ctx) MY_PID_GUARD(); bpf_repeat(1000000) { - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); found = true; } @@ -606,7 +606,7 @@ int iter_tricky_but_fine(const void *ctx) MY_PID_GUARD(); bpf_repeat(1000000) { - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); if (map_val) { found = true; break; diff --git a/tools/testing/selftests/bpf/progs/iters_testmod.c b/tools/testing/selftests/bpf/progs/iters_testmod.c index df1d3db60b1b..9e4b45201e69 100644 --- a/tools/testing/selftests/bpf/progs/iters_testmod.c +++ b/tools/testing/selftests/bpf/progs/iters_testmod.c @@ -4,7 +4,7 @@ #include "bpf_experimental.h" #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c index f9789e668297..82190d79de37 100644 --- a/tools/testing/selftests/bpf/progs/jit_probe_mem.c +++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" static struct prog_test_ref_kfunc __kptr *v; long total_sum = -1; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c index 7632d9ecb253..b9670e9a6e3d 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("tc") int kfunc_destructive_test(void) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c index 08fae306539c..a1963497f0bf 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c @@ -2,7 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct syscall_test_args { __u8 data[16]; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c index d532af07decf..48f64827cd93 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_race.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_fail(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index f502f755f567..8b86113a0126 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -2,7 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_test4(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index 2380c75e74ce..8e150e85b50d 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" extern const int bpf_prog_active __ksym; int active_res = -1; diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c index b092a72b2c9d..d736506a4c80 100644 --- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -6,7 +6,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> #include "../bpf_experimental.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct plain_local; diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c index ab0ce1d01a4a..edaba481db9d 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr.c +++ b/tools/testing/selftests/bpf/progs/map_kptr.c @@ -2,7 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr; diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c index 450bb373b179..4c0ff01f1a96 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c @@ -4,7 +4,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct map_value { char buf[8]; @@ -345,7 +345,7 @@ int reject_indirect_global_func_access(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("Unreleased reference id=5 alloc_insn=") +__failure __msg("Unreleased reference id=4 alloc_insn=") int kptr_xchg_ref_state(struct __sk_buff *ctx) { struct prog_test_ref_kfunc *p; diff --git a/tools/testing/selftests/bpf/progs/missed_kprobe.c b/tools/testing/selftests/bpf/progs/missed_kprobe.c index 7f9ef701f5de..51a4fe64c917 100644 --- a/tools/testing/selftests/bpf/progs/missed_kprobe.c +++ b/tools/testing/selftests/bpf/progs/missed_kprobe.c @@ -2,7 +2,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c b/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c index 8ea71cbd6c45..29c18d869ec1 100644 --- a/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c +++ b/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c @@ -2,7 +2,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; @@ -46,3 +46,9 @@ int test5(struct pt_regs *ctx) { return 0; } + +SEC("kprobe.session/bpf_kfunc_common_test") +int test6(struct pt_regs *ctx) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/nested_acquire.c b/tools/testing/selftests/bpf/progs/nested_acquire.c index 8e521a21d995..49ad7b9adf56 100644 --- a/tools/testing/selftests/bpf/progs/nested_acquire.c +++ b/tools/testing/selftests/bpf/progs/nested_acquire.c @@ -4,7 +4,7 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/preempt_lock.c b/tools/testing/selftests/bpf/progs/preempt_lock.c index 885377e83607..6c5797bf0ead 100644 --- a/tools/testing/selftests/bpf/progs/preempt_lock.c +++ b/tools/testing/selftests/bpf/progs/preempt_lock.c @@ -5,8 +5,10 @@ #include "bpf_misc.h" #include "bpf_experimental.h" +extern int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void *unsafe_ptr__ign, u64 flags) __weak __ksym; + SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_1(struct __sk_buff *ctx) { bpf_preempt_disable(); @@ -14,7 +16,7 @@ int preempt_lock_missing_1(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_2(struct __sk_buff *ctx) { bpf_preempt_disable(); @@ -23,7 +25,7 @@ int preempt_lock_missing_2(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_3(struct __sk_buff *ctx) { bpf_preempt_disable(); @@ -33,7 +35,7 @@ int preempt_lock_missing_3(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_3_minus_2(struct __sk_buff *ctx) { bpf_preempt_disable(); @@ -55,7 +57,7 @@ static __noinline void preempt_enable(void) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_1_subprog(struct __sk_buff *ctx) { preempt_disable(); @@ -63,7 +65,7 @@ int preempt_lock_missing_1_subprog(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_2_subprog(struct __sk_buff *ctx) { preempt_disable(); @@ -72,7 +74,7 @@ int preempt_lock_missing_2_subprog(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_2_minus_1_subprog(struct __sk_buff *ctx) { preempt_disable(); @@ -113,6 +115,18 @@ int preempt_sleepable_helper(void *ctx) return 0; } +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("kernel func bpf_copy_from_user_str is sleepable within non-preemptible region") +int preempt_sleepable_kfunc(void *ctx) +{ + u32 data; + + bpf_preempt_disable(); + bpf_copy_from_user_str(&data, sizeof(data), NULL, 0); + bpf_preempt_enable(); + return 0; +} + int __noinline preempt_global_subprog(void) { preempt_balance_subprog(); diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue.c b/tools/testing/selftests/bpf/progs/pro_epilogue.c index 44bc3f06b4b6..d97d6e07ef5c 100644 --- a/tools/testing/selftests/bpf/progs/pro_epilogue.c +++ b/tools/testing/selftests/bpf/progs/pro_epilogue.c @@ -4,8 +4,8 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c b/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c index 3529e53be355..6048d79be48b 100644 --- a/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c +++ b/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c @@ -4,8 +4,8 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sock_addr_kern.c b/tools/testing/selftests/bpf/progs/sock_addr_kern.c index 8386bb15ccdc..84ad515eafd6 100644 --- a/tools/testing/selftests/bpf/progs/sock_addr_kern.c +++ b/tools/testing/selftests/bpf/progs/sock_addr_kern.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Google LLC */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("syscall") int init_sock(struct init_sock_args *args) diff --git a/tools/testing/selftests/bpf/progs/struct_ops_detach.c b/tools/testing/selftests/bpf/progs/struct_ops_detach.c index d7fdcabe7d90..284a5b008e0c 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_detach.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_detach.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c b/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c index 3c822103bd40..d8cc99f5c2e2 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c index b450f72e744a..ccab3935aa42 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c index 6283099ec383..8b5515f4f724 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c index 4c56d4a9d9f4..71c420c3a5a6 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_module.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c b/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c index 9efcc6e4d356..5b23ea817f1f 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c b/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c index fa2021388485..5d0937fa07be 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c index 8ea57e5348ab..0e4d2ff63ab8 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c index 1f55ec4cee37..58d5d8dc2235 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c index f2f300d50988..31e58389bb8b 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c index 0f4dfb770c32..b698cc62a371 100644 --- a/tools/testing/selftests/bpf/progs/syscall.c +++ b/tools/testing/selftests/bpf/progs/syscall.c @@ -76,9 +76,9 @@ static int btf_load(void) .magic = BTF_MAGIC, .version = BTF_VERSION, .hdr_len = sizeof(struct btf_header), - .type_len = sizeof(__u32) * 8, - .str_off = sizeof(__u32) * 8, - .str_len = sizeof(__u32), + .type_len = sizeof(raw_btf.types), + .str_off = offsetof(struct btf_blob, str) - offsetof(struct btf_blob, types), + .str_len = sizeof(raw_btf.str), }, .types = { /* long */ diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index 683c8aaa63da..f344c6835e84 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -15,7 +15,7 @@ #include <linux/ipv6.h> #include <linux/pkt_cls.h> #include <linux/tcp.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h index 233b089d1fba..eb55cb8a3dbd 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.h +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h @@ -10,7 +10,7 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include <linux/udp.h> +#include <netinet/udp.h> /* offsetof() is used in static asserts, and the libbpf-redefined CO-RE * friendly version breaks compilation for older clang versions <= 15 diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c index 464515b824b9..d0f7670351e5 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c @@ -15,7 +15,7 @@ #include <linux/ipv6.h> #include <linux/pkt_cls.h> #include <linux/tcp.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c index 6afa834756e9..fac33a14f200 100644 --- a/tools/testing/selftests/bpf/progs/test_fill_link_info.c +++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c @@ -6,13 +6,20 @@ #include <stdbool.h> extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak; +extern bool CONFIG_PPC_FTRACE_OUT_OF_LINE __kconfig __weak; +extern bool CONFIG_KPROBES_ON_FTRACE __kconfig __weak; +extern bool CONFIG_PPC64 __kconfig __weak; -/* This function is here to have CONFIG_X86_KERNEL_IBT - * used and added to object BTF. +/* This function is here to have CONFIG_X86_KERNEL_IBT, + * CONFIG_PPC_FTRACE_OUT_OF_LINE, CONFIG_KPROBES_ON_FTRACE, + * CONFIG_PPC6 used and added to object BTF. */ int unused(void) { - return CONFIG_X86_KERNEL_IBT ? 0 : 1; + return CONFIG_X86_KERNEL_IBT || + CONFIG_PPC_FTRACE_OUT_OF_LINE || + CONFIG_KPROBES_ON_FTRACE || + CONFIG_PPC64 ? 0 : 1; } SEC("kprobe") diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c index 5da001ca57a5..09d027bd3ea8 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func10.c +++ b/tools/testing/selftests/bpf/progs/test_global_func10.c @@ -26,7 +26,7 @@ __noinline int foo(const struct Big *big) } SEC("cgroup_skb/ingress") -__failure __msg("invalid indirect access to stack") +__failure __msg("invalid read from stack") int global_func10(struct __sk_buff *skb) { const struct Small small = {.x = skb->len }; diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c index 7ac7e1de34d8..0ad1bf1ede8d 100644 --- a/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c +++ b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c @@ -4,7 +4,7 @@ #include <bpf/bpf_helpers.h> #include "bpf_misc.h" #include "bpf_kfuncs.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("tc") int kfunc_dynptr_nullable_test1(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c index cc1a012d038f..fb07f5773888 100644 --- a/tools/testing/selftests/bpf/progs/test_module_attach.c +++ b/tools/testing/selftests/bpf/progs/test_module_attach.c @@ -5,7 +5,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_core_read.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" __u32 raw_tp_read_sz = 0; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c new file mode 100644 index 000000000000..2796dd8545eb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 ByteDance */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +long change_tail_ret = 1; + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + char *data, *data_end; + + bpf_skb_pull_data(skb, 1); + data = (char *)(unsigned long)skb->data; + data_end = (char *)(unsigned long)skb->data_end; + + if (data + 1 > data_end) + return SK_PASS; + + if (data[0] == 'T') { /* Trim the packet */ + change_tail_ret = bpf_skb_change_tail(skb, skb->len - 1, 0); + return SK_PASS; + } else if (data[0] == 'G') { /* Grow the packet */ + change_tail_ret = bpf_skb_change_tail(skb, skb->len + 1, 0); + return SK_PASS; + } else if (data[0] == 'E') { /* Error */ + change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + return SK_PASS; + } + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c new file mode 100644 index 000000000000..28edafe803f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <linux/pkt_cls.h> + +long change_tail_ret = 1; + +static __always_inline struct iphdr *parse_ip_header(struct __sk_buff *skb, int *ip_proto) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = data; + struct iphdr *iph; + + /* Verify Ethernet header */ + if ((void *)(data + sizeof(*eth)) > data_end) + return NULL; + + /* Skip Ethernet header to get to IP header */ + iph = (void *)(data + sizeof(struct ethhdr)); + + /* Verify IP header */ + if ((void *)(data + sizeof(struct ethhdr) + sizeof(*iph)) > data_end) + return NULL; + + /* Basic IP header validation */ + if (iph->version != 4) /* Only support IPv4 */ + return NULL; + + if (iph->ihl < 5) /* Minimum IP header length */ + return NULL; + + *ip_proto = iph->protocol; + return iph; +} + +static __always_inline struct udphdr *parse_udp_header(struct __sk_buff *skb, struct iphdr *iph) +{ + void *data_end = (void *)(long)skb->data_end; + void *hdr = (void *)iph; + struct udphdr *udp; + + /* Calculate UDP header position */ + udp = hdr + (iph->ihl * 4); + hdr = (void *)udp; + + /* Verify UDP header bounds */ + if ((void *)(hdr + sizeof(*udp)) > data_end) + return NULL; + + return udp; +} + +SEC("tc/ingress") +int change_tail(struct __sk_buff *skb) +{ + int len = skb->len; + struct udphdr *udp; + struct iphdr *iph; + void *data_end; + char *payload; + int ip_proto; + + bpf_skb_pull_data(skb, len); + + data_end = (void *)(long)skb->data_end; + iph = parse_ip_header(skb, &ip_proto); + if (!iph) + return TCX_PASS; + + if (ip_proto != IPPROTO_UDP) + return TCX_PASS; + + udp = parse_udp_header(skb, iph); + if (!udp) + return TCX_PASS; + + payload = (char *)udp + (sizeof(struct udphdr)); + if (payload + 1 > (char *)data_end) + return TCX_PASS; + + if (payload[0] == 'T') { /* Trim the packet */ + change_tail_ret = bpf_skb_change_tail(skb, len - 1, 0); + if (!change_tail_ret) + bpf_skb_change_tail(skb, len, 0); + return TCX_PASS; + } else if (payload[0] == 'G') { /* Grow the packet */ + change_tail_ret = bpf_skb_change_tail(skb, len + 1, 0); + if (!change_tail_ret) + bpf_skb_change_tail(skb, len, 0); + return TCX_PASS; + } else if (payload[0] == 'E') { /* Error */ + change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + return TCX_PASS; + } else if (payload[0] == 'Z') { /* Zero */ + change_tail_ret = bpf_skb_change_tail(skb, 0, 0); + return TCX_PASS; + } + return TCX_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c index 10d825928499..630f12e51b07 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_link.c +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -8,6 +8,7 @@ #include <linux/if_packet.h> #include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char LICENSE[] SEC("license") = "GPL"; @@ -27,6 +28,7 @@ bool seen_host; bool seen_mcast; int mark, prio; +unsigned short headroom, tailroom; SEC("tc/ingress") int tc1(struct __sk_buff *skb) @@ -104,11 +106,24 @@ out: return TCX_PASS; } +struct sk_buff { + struct net_device *dev; +}; + +struct net_device { + unsigned short needed_headroom; + unsigned short needed_tailroom; +}; + SEC("tc/egress") int tc8(struct __sk_buff *skb) { + struct net_device *dev = BPF_CORE_READ((struct sk_buff *)skb, dev); + seen_tc8 = true; mark = skb->mark; prio = skb->priority; + headroom = BPF_CORE_READ(dev, needed_headroom); + tailroom = BPF_CORE_READ(dev, needed_tailroom); return TCX_PASS; } diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c index bba3e37f749b..39ff06f2c834 100644 --- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c +++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c @@ -3,7 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" #include "bpf_misc.h" SEC("tp_btf/bpf_testmod_test_nullable_bare") diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 81bb38d72ced..dc74d8cf9e3f 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -10,6 +10,8 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ #if defined(__TARGET_ARCH_s390) int tailroom = 512; +#elif defined(__TARGET_ARCH_powerpc) + int tailroom = 384; #else int tailroom = 320; #endif diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c index 3abf068b8446..5928ed0911ca 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c @@ -98,6 +98,18 @@ int xdp_count_pkts(struct xdp_md *xdp) return XDP_DROP; } +SEC("xdp") +int xdp_redirect_to_111(struct xdp_md *xdp) +{ + return bpf_redirect(111, 0); +} + +SEC("xdp") +int xdp_redirect_to_222(struct xdp_md *xdp) +{ + return bpf_redirect(222, 0); +} + SEC("tc") int tc_count_pkts(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index a7c4a7d49fe6..fe2d71ae0e71 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -8,7 +8,7 @@ #define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1) #define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem -SEC("t") +SEC("tc") int ing_cls(struct __sk_buff *ctx) { __u8 *data, *data_meta, *data_end; @@ -28,7 +28,7 @@ int ing_cls(struct __sk_buff *ctx) return diff ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("x") +SEC("xdp") int ing_xdp(struct xdp_md *ctx) { __u8 *data, *data_meta, *data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c deleted file mode 100644 index b778cad45485..000000000000 --- a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c +++ /dev/null @@ -1,26 +0,0 @@ -/* Copyright (c) 2017 VMware - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ -#include <linux/bpf.h> -#include <bpf/bpf_helpers.h> - -SEC("redirect_to_111") -int xdp_redirect_to_111(struct xdp_md *xdp) -{ - return bpf_redirect(111, 0); -} -SEC("redirect_to_222") -int xdp_redirect_to_222(struct xdp_md *xdp) -{ - return bpf_redirect(222, 0); -} - -char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/uninit_stack.c b/tools/testing/selftests/bpf/progs/uninit_stack.c index 8a403470e557..046a204c8fc6 100644 --- a/tools/testing/selftests/bpf/progs/uninit_stack.c +++ b/tools/testing/selftests/bpf/progs/uninit_stack.c @@ -70,7 +70,8 @@ __naked int helper_uninit_to_misc(void *ctx) r1 = r10; \ r1 += -128; \ r2 = 32; \ - call %[bpf_trace_printk]; \ + r3 = 0; \ + call %[bpf_probe_read_user]; \ /* Call to dummy() forces print_verifier_state(..., true), \ * thus showing the stack state, matched by __msg(). \ */ \ @@ -79,7 +80,7 @@ __naked int helper_uninit_to_misc(void *ctx) exit; \ " : - : __imm(bpf_trace_printk), + : __imm(bpf_probe_read_user), __imm(dummy) : __clobber_all); } diff --git a/tools/testing/selftests/bpf/progs/unsupported_ops.c b/tools/testing/selftests/bpf/progs/unsupported_ops.c index 9180365a3568..8aa2e0dd624e 100644 --- a/tools/testing/selftests/bpf/progs/unsupported_ops.c +++ b/tools/testing/selftests/bpf/progs/unsupported_ops.c @@ -4,7 +4,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_array_access.c b/tools/testing/selftests/bpf/progs/verifier_array_access.c index 4195aa824ba5..29eb9568633f 100644 --- a/tools/testing/selftests/bpf/progs/verifier_array_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_array_access.c @@ -28,6 +28,20 @@ struct { __uint(map_flags, BPF_F_WRONLY_PROG); } map_array_wo SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, struct test_val); +} map_array_pcpu SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, struct test_val); +} map_array SEC(".maps"); + struct { __uint(type, BPF_MAP_TYPE_HASH); __uint(max_entries, 1); @@ -525,4 +539,178 @@ l0_%=: exit; \ : __clobber_all); } +SEC("socket") +__description("valid map access into an array using constant without nullness") +__success __retval(4) __log_level(2) +__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -8) = {{(1|r[0-9])}}") +unsigned int an_array_with_a_constant_no_nullness(void) +{ + /* Need 8-byte alignment for spill tracking */ + __u32 __attribute__((aligned(8))) key = 1; + struct test_val *val; + + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("valid multiple map access into an array using constant without nullness") +__success __retval(8) __log_level(2) +__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -16) = {{(0|r[0-9])}}") +__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -8) = {{(1|r[0-9])}}") +unsigned int multiple_array_with_a_constant_no_nullness(void) +{ + __u32 __attribute__((aligned(8))) key = 1; + __u32 __attribute__((aligned(8))) key2 = 0; + struct test_val *val, *val2; + + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + val2 = bpf_map_lookup_elem(&map_array, &key2); + val2->index = offsetof(struct test_val, foo); + + return val->index + val2->index; +} + +SEC("socket") +__description("valid map access into an array using natural aligned 32-bit constant 0 without nullness") +__success __retval(4) +unsigned int an_array_with_a_32bit_constant_0_no_nullness(void) +{ + /* Unlike the above tests, 32-bit zeroing is precisely tracked even + * if writes are not aligned to BPF_REG_SIZE. This tests that our + * STACK_ZERO handling functions. + */ + struct test_val *val; + __u32 key = 0; + + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("valid map access into a pcpu array using constant without nullness") +__success __retval(4) __log_level(2) +__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -8) = {{(1|r[0-9])}}") +unsigned int a_pcpu_array_with_a_constant_no_nullness(void) +{ + __u32 __attribute__((aligned(8))) key = 1; + struct test_val *val; + + val = bpf_map_lookup_elem(&map_array_pcpu, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("invalid map access into an array using constant without nullness") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int an_array_with_a_constant_no_nullness_out_of_bounds(void) +{ + /* Out of bounds */ + __u32 __attribute__((aligned(8))) key = 3; + struct test_val *val; + + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("invalid map access into an array using constant smaller than key_size") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int an_array_with_a_constant_too_small(void) +{ + __u32 __attribute__((aligned(8))) key; + struct test_val *val; + + /* Mark entire key as STACK_MISC */ + bpf_probe_read_user(&key, sizeof(key), NULL); + + /* Spilling only the bottom byte results in a tnum const of 1. + * We want to check that the verifier rejects it, as the spill is < 4B. + */ + *(__u8 *)&key = 1; + val = bpf_map_lookup_elem(&map_array, &key); + + /* Should fail, as verifier cannot prove in-bound lookup */ + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("invalid map access into an array using constant larger than key_size") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int an_array_with_a_constant_too_big(void) +{ + struct test_val *val; + __u64 key = 1; + + /* Even if the constant value is < max_entries, if the spill size is + * larger than the key size, the set bits may not be where we expect them + * to be on different endian architectures. + */ + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("invalid elided lookup using const and non-const key") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int mixed_const_and_non_const_key_lookup(void) +{ + __u32 __attribute__((aligned(8))) key; + struct test_val *val; + __u32 rand; + + rand = bpf_get_prandom_u32(); + key = rand > 42 ? 1 : rand; + val = bpf_map_lookup_elem(&map_array, &key); + + return val->index; +} + +SEC("socket") +__failure __msg("invalid read from stack R2 off=4096 size=4") +__naked void key_lookup_at_invalid_fp(void) +{ + asm volatile (" \ + r1 = %[map_array] ll; \ + r2 = r10; \ + r2 += 4096; \ + call %[bpf_map_lookup_elem]; \ + r0 = *(u64*)(r0 + 0); \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array) + : __clobber_all); +} + +volatile __u32 __attribute__((aligned(8))) global_key; + +SEC("socket") +__description("invalid elided lookup using non-stack key") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int non_stack_key_lookup(void) +{ + struct test_val *val; + + global_key = 1; + val = bpf_map_lookup_elem(&map_array, (void *)&global_key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c index 8d77cc5323d3..fb62e09f2114 100644 --- a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c @@ -28,7 +28,7 @@ __naked void stack_out_of_bounds(void) SEC("socket") __description("uninitialized stack1") __success __log_level(4) __msg("stack depth 8") -__failure_unpriv __msg_unpriv("invalid indirect read from stack") +__failure_unpriv __msg_unpriv("invalid read from stack") __naked void uninitialized_stack1(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index a0bb7fb40ea5..0eb33bb801b5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -1200,4 +1200,138 @@ l0_%=: r0 = 0; \ : __clobber_all); } +SEC("tc") +__description("multiply mixed sign bounds. test 1") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=umin=0x1bc16d5cd4927ee1,smax=umax=0x1bc16d674ec80000,smax32=0x7ffffeff,umax32=0xfffffeff,var_off=(0x1bc16d4000000000; 0x3ffffffeff))") +__naked void mult_mixed0_sign(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0xf;" + "r6 -= 1000000000;" + "r7 &= 0xf;" + "r7 -= 2000000000;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiply mixed sign bounds. test 2") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=smin32=-100,smax=smax32=200)") +__naked void mult_mixed1_sign(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0xf;" + "r6 -= 0xa;" + "r7 &= 0xf;" + "r7 -= 0x14;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiply negative bounds") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=umin=smin32=umin32=0x3ff280b0,smax=umax=smax32=umax32=0x3fff0001,var_off=(0x3ff00000; 0xf81ff))") +__naked void mult_sign_bounds(void) +{ + asm volatile ( + "r8 = 0x7fff;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0xa;" + "r6 -= r8;" + "r7 &= 0xf;" + "r7 -= r8;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiply bounds that don't cross signed boundary") +__success __log_level(2) +__msg("r8 *= r6 {{.*}}; R6_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=11,var_off=(0x0; 0xb)) R8_w=scalar(smin=0,smax=umax=0x7b96bb0a94a3a7cd,var_off=(0x0; 0x7fffffffffffffff))") +__naked void mult_no_sign_crossing(void) +{ + asm volatile ( + "r6 = 0xb;" + "r8 = 0xb3c3f8c99262687 ll;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= r7;" + "r8 *= r6;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiplication overflow, result in unbounded reg. test 1") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar()") +__naked void mult_unsign_ovf(void) +{ + asm volatile ( + "r8 = 0x7ffffffffff ll;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0x7fffffff;" + "r7 &= r8;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiplication overflow, result in unbounded reg. test 2") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar()") +__naked void mult_sign_ovf(void) +{ + asm volatile ( + "r8 = 0x7ffffffff ll;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0xa;" + "r6 -= r8;" + "r7 &= 0x7fffffff;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_const_or.c b/tools/testing/selftests/bpf/progs/verifier_const_or.c index ba8922b2eebd..68c568c3c3a0 100644 --- a/tools/testing/selftests/bpf/progs/verifier_const_or.c +++ b/tools/testing/selftests/bpf/progs/verifier_const_or.c @@ -25,7 +25,7 @@ __naked void constant_should_keep_constant_type(void) SEC("tracepoint") __description("constant register |= constant should not bypass stack boundary checks") -__failure __msg("invalid indirect access to stack R1 off=-48 size=58") +__failure __msg("invalid write to stack R1 off=-48 size=58") __naked void not_bypass_stack_boundary_checks_1(void) { asm volatile (" \ @@ -62,7 +62,7 @@ __naked void register_should_keep_constant_type(void) SEC("tracepoint") __description("constant register |= constant register should not bypass stack boundary checks") -__failure __msg("invalid indirect access to stack R1 off=-48 size=58") +__failure __msg("invalid write to stack R1 off=-48 size=58") __naked void not_bypass_stack_boundary_checks_2(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c b/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c index 50c6b22606f6..f2c54e4d89eb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c +++ b/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c @@ -67,7 +67,7 @@ SEC("socket") __description("helper access to variable memory: stack, bitwise AND, zero included") /* in privileged mode reads from uninitialized stack locations are permitted */ __success __failure_unpriv -__msg_unpriv("invalid indirect read from stack R2 off -64+0 size 64") +__msg_unpriv("invalid read from stack R2 off -64+0 size 64") __retval(0) __naked void stack_bitwise_and_zero_included(void) { @@ -100,7 +100,7 @@ __naked void stack_bitwise_and_zero_included(void) SEC("tracepoint") __description("helper access to variable memory: stack, bitwise AND + JMP, wrong max") -__failure __msg("invalid indirect access to stack R1 off=-64 size=65") +__failure __msg("invalid write to stack R1 off=-64 size=65") __naked void bitwise_and_jmp_wrong_max(void) { asm volatile (" \ @@ -187,7 +187,7 @@ l0_%=: r0 = 0; \ SEC("tracepoint") __description("helper access to variable memory: stack, JMP, bounds + offset") -__failure __msg("invalid indirect access to stack R1 off=-64 size=65") +__failure __msg("invalid write to stack R1 off=-64 size=65") __naked void memory_stack_jmp_bounds_offset(void) { asm volatile (" \ @@ -211,7 +211,7 @@ l0_%=: r0 = 0; \ SEC("tracepoint") __description("helper access to variable memory: stack, JMP, wrong max") -__failure __msg("invalid indirect access to stack R1 off=-64 size=65") +__failure __msg("invalid write to stack R1 off=-64 size=65") __naked void memory_stack_jmp_wrong_max(void) { asm volatile (" \ @@ -260,7 +260,7 @@ SEC("socket") __description("helper access to variable memory: stack, JMP, no min check") /* in privileged mode reads from uninitialized stack locations are permitted */ __success __failure_unpriv -__msg_unpriv("invalid indirect read from stack R2 off -64+0 size 64") +__msg_unpriv("invalid read from stack R2 off -64+0 size 64") __retval(0) __naked void stack_jmp_no_min_check(void) { @@ -750,7 +750,7 @@ SEC("socket") __description("helper access to variable memory: 8 bytes leak") /* in privileged mode reads from uninitialized stack locations are permitted */ __success __failure_unpriv -__msg_unpriv("invalid indirect read from stack R2 off -64+32 size 64") +__msg_unpriv("invalid read from stack R2 off -64+32 size 64") __retval(0) __naked void variable_memory_8_bytes_leak(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c index 5f2efb895edb..59e34d558654 100644 --- a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c +++ b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c @@ -96,7 +96,7 @@ __naked void arg_ptr_to_long_misaligned(void) SEC("cgroup/sysctl") __description("arg pointer to long size < sizeof(long)") -__failure __msg("invalid indirect access to stack R4 off=-4 size=8") +__failure __msg("invalid write to stack R4 off=-4 size=8") __naked void to_long_size_sizeof_long(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c index 4eaab1468eb7..7d088ba99ea5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c @@ -47,7 +47,7 @@ l0_%=: r0 = 0; \ SEC("xdp") __description("map in map state pruning") -__success __msg("processed 26 insns") +__success __msg("processed 15 insns") __log_level(2) __retval(0) __flag(BPF_F_TEST_STATE_FREQ) __naked void map_in_map_state_pruning(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c new file mode 100644 index 000000000000..e81097c96fe2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +SEC("raw_tp") +__description("may_goto 0") +__arch_x86_64 +__xlated("0: r0 = 1") +__xlated("1: exit") +__success +__naked void may_goto_simple(void) +{ + asm volatile ( + ".8byte %[may_goto];" + "r0 = 1;" + ".8byte %[may_goto];" + "exit;" + : + : __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) + : __clobber_all); +} + +SEC("raw_tp") +__description("batch 2 of may_goto 0") +__arch_x86_64 +__xlated("0: r0 = 1") +__xlated("1: exit") +__success +__naked void may_goto_batch_0(void) +{ + asm volatile ( + ".8byte %[may_goto1];" + ".8byte %[may_goto1];" + "r0 = 1;" + ".8byte %[may_goto1];" + ".8byte %[may_goto1];" + "exit;" + : + : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) + : __clobber_all); +} + +SEC("raw_tp") +__description("may_goto batch with offsets 2/1/0") +__arch_x86_64 +__xlated("0: r0 = 1") +__xlated("1: exit") +__success +__naked void may_goto_batch_1(void) +{ + asm volatile ( + ".8byte %[may_goto1];" + ".8byte %[may_goto2];" + ".8byte %[may_goto3];" + "r0 = 1;" + ".8byte %[may_goto1];" + ".8byte %[may_goto2];" + ".8byte %[may_goto3];" + "exit;" + : + : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)), + __imm_insn(may_goto2, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 1 /* offset */, 0)), + __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) + : __clobber_all); +} + +SEC("raw_tp") +__description("may_goto batch with offsets 2/0") +__arch_x86_64 +__xlated("0: *(u64 *)(r10 -8) = 8388608") +__xlated("1: r11 = *(u64 *)(r10 -8)") +__xlated("2: if r11 == 0x0 goto pc+3") +__xlated("3: r11 -= 1") +__xlated("4: *(u64 *)(r10 -8) = r11") +__xlated("5: r0 = 1") +__xlated("6: r0 = 2") +__xlated("7: exit") +__success +__naked void may_goto_batch_2(void) +{ + asm volatile ( + ".8byte %[may_goto1];" + ".8byte %[may_goto3];" + "r0 = 1;" + "r0 = 2;" + "exit;" + : + : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)), + __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_2.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_2.c new file mode 100644 index 000000000000..b891faf50660 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_2.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include "bpf_misc.h" +#include "bpf_experimental.h" + +int gvar; + +SEC("raw_tp") +__description("C code with may_goto 0") +__success +int may_goto_c_code(void) +{ + int i, tmp[3]; + + for (i = 0; i < 3 && can_loop; i++) + tmp[i] = 0; + + for (i = 0; i < 3 && can_loop; i++) + tmp[i] = gvar - i; + + for (i = 0; i < 3 && can_loop; i++) + gvar += tmp[i]; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_mtu.c b/tools/testing/selftests/bpf/progs/verifier_mtu.c index 4ccf1ebc42d1..256956ea1ac5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_mtu.c +++ b/tools/testing/selftests/bpf/progs/verifier_mtu.c @@ -8,7 +8,7 @@ SEC("tc/ingress") __description("uninit/mtu: write rejected") __success __caps_unpriv(CAP_BPF|CAP_NET_ADMIN) -__failure_unpriv __msg_unpriv("invalid indirect read from stack") +__failure_unpriv __msg_unpriv("invalid read from stack") int tc_uninit_mtu(struct __sk_buff *ctx) { __u32 mtu; diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c index 7cc83acac727..c689665e07b9 100644 --- a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c @@ -236,7 +236,7 @@ __naked void load_bytes_spilled_regs_data(void) SEC("tc") __description("raw_stack: skb_load_bytes, invalid access 1") -__failure __msg("invalid indirect access to stack R3 off=-513 size=8") +__failure __msg("invalid write to stack R3 off=-513 size=8") __naked void load_bytes_invalid_access_1(void) { asm volatile (" \ @@ -255,7 +255,7 @@ __naked void load_bytes_invalid_access_1(void) SEC("tc") __description("raw_stack: skb_load_bytes, invalid access 2") -__failure __msg("invalid indirect access to stack R3 off=-1 size=8") +__failure __msg("invalid write to stack R3 off=-1 size=8") __naked void load_bytes_invalid_access_2(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c index 3f679de73229..d9d7b05cf6d2 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c @@ -187,7 +187,7 @@ l0_%=: r6 = r0; \ SEC("cgroup/skb") __description("spin_lock: test6 missing unlock") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_spin_lock-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_spin_lock-ed region") __failure_unpriv __msg_unpriv("") __naked void spin_lock_test6_missing_unlock(void) { @@ -530,4 +530,30 @@ l1_%=: exit; \ : __clobber_all); } +SEC("tc") +__description("spin_lock: loop within a locked region") +__success __failure_unpriv __msg_unpriv("") +__retval(0) +int bpf_loop_inside_locked_region(void) +{ + const int zero = 0; + struct val *val; + int i, j = 0; + + val = bpf_map_lookup_elem(&map_spin_lock, &zero); + if (!val) + return -1; + + bpf_spin_lock(&val->l); + bpf_for(i, 0, 10) { + j++; + /* Silence "unused variable" warnings. */ + if (j == 10) + break; + } + bpf_spin_unlock(&val->l); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv.c b/tools/testing/selftests/bpf/progs/verifier_unpriv.c index 7ea535bfbacd..a4a5e2071604 100644 --- a/tools/testing/selftests/bpf/progs/verifier_unpriv.c +++ b/tools/testing/selftests/bpf/progs/verifier_unpriv.c @@ -199,7 +199,7 @@ __naked void pass_pointer_to_helper_function(void) SEC("socket") __description("unpriv: indirectly pass pointer on stack to helper function") __success __failure_unpriv -__msg_unpriv("invalid indirect read from stack R2 off -8+0 size 8") +__msg_unpriv("invalid read from stack R2 off -8+0 size 8") __retval(0) __naked void on_stack_to_helper_function(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_var_off.c b/tools/testing/selftests/bpf/progs/verifier_var_off.c index c810f4f6f479..1d36d01b746e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_var_off.c +++ b/tools/testing/selftests/bpf/progs/verifier_var_off.c @@ -203,7 +203,7 @@ __naked void stack_write_clobbers_spilled_regs(void) SEC("sockops") __description("indirect variable-offset stack access, unbounded") -__failure __msg("invalid unbounded variable-offset indirect access to stack R4") +__failure __msg("invalid unbounded variable-offset write to stack R4") __naked void variable_offset_stack_access_unbounded(void) { asm volatile (" \ @@ -236,7 +236,7 @@ l0_%=: r0 = 0; \ SEC("lwt_in") __description("indirect variable-offset stack access, max out of bound") -__failure __msg("invalid variable-offset indirect access to stack R2") +__failure __msg("invalid variable-offset read from stack R2") __naked void access_max_out_of_bound(void) { asm volatile (" \ @@ -269,7 +269,7 @@ __naked void access_max_out_of_bound(void) */ SEC("socket") __description("indirect variable-offset stack access, zero-sized, max out of bound") -__failure __msg("invalid variable-offset indirect access to stack R1") +__failure __msg("invalid variable-offset write to stack R1") __naked void zero_sized_access_max_out_of_bound(void) { asm volatile (" \ @@ -294,7 +294,7 @@ __naked void zero_sized_access_max_out_of_bound(void) SEC("lwt_in") __description("indirect variable-offset stack access, min out of bound") -__failure __msg("invalid variable-offset indirect access to stack R2") +__failure __msg("invalid variable-offset read from stack R2") __naked void access_min_out_of_bound(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/wq.c b/tools/testing/selftests/bpf/progs/wq.c index f8d3ae0c29ae..2f1ba08c293e 100644 --- a/tools/testing/selftests/bpf/progs/wq.c +++ b/tools/testing/selftests/bpf/progs/wq.c @@ -5,7 +5,7 @@ #include "bpf_experimental.h" #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/wq_failures.c b/tools/testing/selftests/bpf/progs/wq_failures.c index 25b51a72fe0f..4240211a1900 100644 --- a/tools/testing/selftests/bpf/progs/wq_failures.c +++ b/tools/testing/selftests/bpf/progs/wq_failures.c @@ -5,7 +5,7 @@ #include "bpf_experimental.h" #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h index ca0162b4dc57..1fcfa5160231 100644 --- a/tools/testing/selftests/bpf/sdt.h +++ b/tools/testing/selftests/bpf/sdt.h @@ -102,6 +102,8 @@ # define STAP_SDT_ARG_CONSTRAINT nZr # elif defined __arm__ # define STAP_SDT_ARG_CONSTRAINT g +# elif defined __loongarch__ +# define STAP_SDT_ARG_CONSTRAINT nmr # else # define STAP_SDT_ARG_CONSTRAINT nor # endif diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py index 0ed67b6b31dd..238121fda5b6 100755 --- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py +++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py @@ -66,7 +66,7 @@ class ArrayParser(BlockParser): def __init__(self, reader, array_name): self.array_name = array_name - self.start_marker = re.compile(f'(static )?const bool {self.array_name}\[.*\] = {{\n') + self.start_marker = re.compile(fr'(static )?const bool {self.array_name}\[.*\] = {{\n') super().__init__(reader) def search_block(self): @@ -80,7 +80,7 @@ class ArrayParser(BlockParser): Parse a block and return data as a dictionary. Items to extract must be on separate lines in the file. """ - pattern = re.compile('\[(BPF_\w*)\]\s*= (true|false),?$') + pattern = re.compile(r'\[(BPF_\w*)\]\s*= (true|false),?$') entries = set() while True: line = self.reader.readline() @@ -178,7 +178,7 @@ class FileExtractor(object): @enum_name: name of the enum to parse """ start_marker = re.compile(f'enum {enum_name} {{\n') - pattern = re.compile('^\s*(BPF_\w+),?(\s+/\*.*\*/)?$') + pattern = re.compile(r'^\s*(BPF_\w+),?(\s+/\*.*\*/)?$') end_marker = re.compile('^};') parser = BlockParser(self.reader) parser.search_block(start_marker) @@ -226,8 +226,8 @@ class FileExtractor(object): @block_name: name of the blog to parse, 'TYPE' in the example """ - start_marker = re.compile(f'\*{block_name}\* := {{') - pattern = re.compile('\*\*([\w/-]+)\*\*') + start_marker = re.compile(fr'\*{block_name}\* := {{') + pattern = re.compile(r'\*\*([\w/-]+)\*\*') end_marker = re.compile('}\n') return self.__get_description_list(start_marker, pattern, end_marker) @@ -245,8 +245,8 @@ class FileExtractor(object): @block_name: name of the blog to parse, 'TYPE' in the example """ - start_marker = re.compile(f'"\s*{block_name} := {{') - pattern = re.compile('([\w/]+) [|}]') + start_marker = re.compile(fr'"\s*{block_name} := {{') + pattern = re.compile(r'([\w/]+) [|}]') end_marker = re.compile('}') return self.__get_description_list(start_marker, pattern, end_marker) @@ -264,8 +264,8 @@ class FileExtractor(object): @macro: macro starting the block, 'HELP_SPEC_OPTIONS' in the example """ - start_marker = re.compile(f'"\s*{macro}\s*" [|}}]') - pattern = re.compile('([\w-]+) ?(?:\||}[ }\]])') + start_marker = re.compile(fr'"\s*{macro}\s*" [|}}]') + pattern = re.compile(r'([\w-]+) ?(?:\||}[ }\]])') end_marker = re.compile('}\\\\n') return self.__get_description_list(start_marker, pattern, end_marker) @@ -283,8 +283,8 @@ class FileExtractor(object): @block_name: name of the blog to parse, 'TYPE' in the example """ - start_marker = re.compile(f'local {block_name}=\'') - pattern = re.compile('(?:.*=\')?([\w/]+)') + start_marker = re.compile(fr'local {block_name}=\'') + pattern = re.compile(r'(?:.*=\')?([\w/]+)') end_marker = re.compile('\'$') return self.__get_description_list(start_marker, pattern, end_marker) @@ -316,7 +316,7 @@ class MainHeaderFileExtractor(SourceFileExtractor): {'-p', '-d', '--pretty', '--debug', '--json', '-j'} """ start_marker = re.compile(f'"OPTIONS :=') - pattern = re.compile('([\w-]+) ?(?:\||}[ }\]"])') + pattern = re.compile(r'([\w-]+) ?(?:\||}[ }\]"])') end_marker = re.compile('#define') parser = InlineListParser(self.reader) @@ -338,8 +338,8 @@ class ManSubstitutionsExtractor(SourceFileExtractor): {'-p', '-d', '--pretty', '--debug', '--json', '-j'} """ - start_marker = re.compile('\|COMMON_OPTIONS\| replace:: {') - pattern = re.compile('\*\*([\w/-]+)\*\*') + start_marker = re.compile(r'\|COMMON_OPTIONS\| replace:: {') + pattern = re.compile(r'\*\*([\w/-]+)\*\*') end_marker = re.compile('}$') parser = InlineListParser(self.reader) diff --git a/tools/testing/selftests/bpf/test_flow_dissector.c b/tools/testing/selftests/bpf/test_flow_dissector.c deleted file mode 100644 index 571cc076dd7d..000000000000 --- a/tools/testing/selftests/bpf/test_flow_dissector.c +++ /dev/null @@ -1,780 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Inject packets with all sorts of encapsulation into the kernel. - * - * IPv4/IPv6 outer layer 3 - * GRE/GUE/BARE outer layer 4, where bare is IPIP/SIT/IPv4-in-IPv6/.. - * IPv4/IPv6 inner layer 3 - */ - -#define _GNU_SOURCE - -#include <stddef.h> -#include <arpa/inet.h> -#include <asm/byteorder.h> -#include <error.h> -#include <errno.h> -#include <linux/if_packet.h> -#include <linux/if_ether.h> -#include <linux/ipv6.h> -#include <netinet/ip.h> -#include <netinet/in.h> -#include <netinet/udp.h> -#include <poll.h> -#include <stdbool.h> -#include <stdlib.h> -#include <stdio.h> -#include <string.h> -#include <sys/ioctl.h> -#include <sys/socket.h> -#include <sys/stat.h> -#include <sys/time.h> -#include <sys/types.h> -#include <unistd.h> - -#define CFG_PORT_INNER 8000 - -/* Add some protocol definitions that do not exist in userspace */ - -struct grehdr { - uint16_t unused; - uint16_t protocol; -} __attribute__((packed)); - -struct guehdr { - union { - struct { -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u8 hlen:5, - control:1, - version:2; -#elif defined (__BIG_ENDIAN_BITFIELD) - __u8 version:2, - control:1, - hlen:5; -#else -#error "Please fix <asm/byteorder.h>" -#endif - __u8 proto_ctype; - __be16 flags; - }; - __be32 word; - }; -}; - -static uint8_t cfg_dsfield_inner; -static uint8_t cfg_dsfield_outer; -static uint8_t cfg_encap_proto; -static bool cfg_expect_failure = false; -static int cfg_l3_extra = AF_UNSPEC; /* optional SIT prefix */ -static int cfg_l3_inner = AF_UNSPEC; -static int cfg_l3_outer = AF_UNSPEC; -static int cfg_num_pkt = 10; -static int cfg_num_secs = 0; -static char cfg_payload_char = 'a'; -static int cfg_payload_len = 100; -static int cfg_port_gue = 6080; -static bool cfg_only_rx; -static bool cfg_only_tx; -static int cfg_src_port = 9; - -static char buf[ETH_DATA_LEN]; - -#define INIT_ADDR4(name, addr4, port) \ - static struct sockaddr_in name = { \ - .sin_family = AF_INET, \ - .sin_port = __constant_htons(port), \ - .sin_addr.s_addr = __constant_htonl(addr4), \ - }; - -#define INIT_ADDR6(name, addr6, port) \ - static struct sockaddr_in6 name = { \ - .sin6_family = AF_INET6, \ - .sin6_port = __constant_htons(port), \ - .sin6_addr = addr6, \ - }; - -INIT_ADDR4(in_daddr4, INADDR_LOOPBACK, CFG_PORT_INNER) -INIT_ADDR4(in_saddr4, INADDR_LOOPBACK + 2, 0) -INIT_ADDR4(out_daddr4, INADDR_LOOPBACK, 0) -INIT_ADDR4(out_saddr4, INADDR_LOOPBACK + 1, 0) -INIT_ADDR4(extra_daddr4, INADDR_LOOPBACK, 0) -INIT_ADDR4(extra_saddr4, INADDR_LOOPBACK + 1, 0) - -INIT_ADDR6(in_daddr6, IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER) -INIT_ADDR6(in_saddr6, IN6ADDR_LOOPBACK_INIT, 0) -INIT_ADDR6(out_daddr6, IN6ADDR_LOOPBACK_INIT, 0) -INIT_ADDR6(out_saddr6, IN6ADDR_LOOPBACK_INIT, 0) -INIT_ADDR6(extra_daddr6, IN6ADDR_LOOPBACK_INIT, 0) -INIT_ADDR6(extra_saddr6, IN6ADDR_LOOPBACK_INIT, 0) - -static unsigned long util_gettime(void) -{ - struct timeval tv; - - gettimeofday(&tv, NULL); - return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); -} - -static void util_printaddr(const char *msg, struct sockaddr *addr) -{ - unsigned long off = 0; - char nbuf[INET6_ADDRSTRLEN]; - - switch (addr->sa_family) { - case PF_INET: - off = __builtin_offsetof(struct sockaddr_in, sin_addr); - break; - case PF_INET6: - off = __builtin_offsetof(struct sockaddr_in6, sin6_addr); - break; - default: - error(1, 0, "printaddr: unsupported family %u\n", - addr->sa_family); - } - - if (!inet_ntop(addr->sa_family, ((void *) addr) + off, nbuf, - sizeof(nbuf))) - error(1, errno, "inet_ntop"); - - fprintf(stderr, "%s: %s\n", msg, nbuf); -} - -static unsigned long add_csum_hword(const uint16_t *start, int num_u16) -{ - unsigned long sum = 0; - int i; - - for (i = 0; i < num_u16; i++) - sum += start[i]; - - return sum; -} - -static uint16_t build_ip_csum(const uint16_t *start, int num_u16, - unsigned long sum) -{ - sum += add_csum_hword(start, num_u16); - - while (sum >> 16) - sum = (sum & 0xffff) + (sum >> 16); - - return ~sum; -} - -static void build_ipv4_header(void *header, uint8_t proto, - uint32_t src, uint32_t dst, - int payload_len, uint8_t tos) -{ - struct iphdr *iph = header; - - iph->ihl = 5; - iph->version = 4; - iph->tos = tos; - iph->ttl = 8; - iph->tot_len = htons(sizeof(*iph) + payload_len); - iph->id = htons(1337); - iph->protocol = proto; - iph->saddr = src; - iph->daddr = dst; - iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0); -} - -static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield) -{ - uint16_t val, *ptr = (uint16_t *)ip6h; - - val = ntohs(*ptr); - val &= 0xF00F; - val |= ((uint16_t) dsfield) << 4; - *ptr = htons(val); -} - -static void build_ipv6_header(void *header, uint8_t proto, - struct sockaddr_in6 *src, - struct sockaddr_in6 *dst, - int payload_len, uint8_t dsfield) -{ - struct ipv6hdr *ip6h = header; - - ip6h->version = 6; - ip6h->payload_len = htons(payload_len); - ip6h->nexthdr = proto; - ip6h->hop_limit = 8; - ipv6_set_dsfield(ip6h, dsfield); - - memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr)); - memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr)); -} - -static uint16_t build_udp_v4_csum(const struct iphdr *iph, - const struct udphdr *udph, - int num_words) -{ - unsigned long pseudo_sum; - int num_u16 = sizeof(iph->saddr); /* halfwords: twice byte len */ - - pseudo_sum = add_csum_hword((void *) &iph->saddr, num_u16); - pseudo_sum += htons(IPPROTO_UDP); - pseudo_sum += udph->len; - return build_ip_csum((void *) udph, num_words, pseudo_sum); -} - -static uint16_t build_udp_v6_csum(const struct ipv6hdr *ip6h, - const struct udphdr *udph, - int num_words) -{ - unsigned long pseudo_sum; - int num_u16 = sizeof(ip6h->saddr); /* halfwords: twice byte len */ - - pseudo_sum = add_csum_hword((void *) &ip6h->saddr, num_u16); - pseudo_sum += htons(ip6h->nexthdr); - pseudo_sum += ip6h->payload_len; - return build_ip_csum((void *) udph, num_words, pseudo_sum); -} - -static void build_udp_header(void *header, int payload_len, - uint16_t dport, int family) -{ - struct udphdr *udph = header; - int len = sizeof(*udph) + payload_len; - - udph->source = htons(cfg_src_port); - udph->dest = htons(dport); - udph->len = htons(len); - udph->check = 0; - if (family == AF_INET) - udph->check = build_udp_v4_csum(header - sizeof(struct iphdr), - udph, len >> 1); - else - udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr), - udph, len >> 1); -} - -static void build_gue_header(void *header, uint8_t proto) -{ - struct guehdr *gueh = header; - - gueh->proto_ctype = proto; -} - -static void build_gre_header(void *header, uint16_t proto) -{ - struct grehdr *greh = header; - - greh->protocol = htons(proto); -} - -static int l3_length(int family) -{ - if (family == AF_INET) - return sizeof(struct iphdr); - else - return sizeof(struct ipv6hdr); -} - -static int build_packet(void) -{ - int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0; - int el3_len = 0; - - if (cfg_l3_extra) - el3_len = l3_length(cfg_l3_extra); - - /* calculate header offsets */ - if (cfg_encap_proto) { - ol3_len = l3_length(cfg_l3_outer); - - if (cfg_encap_proto == IPPROTO_GRE) - ol4_len = sizeof(struct grehdr); - else if (cfg_encap_proto == IPPROTO_UDP) - ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr); - } - - il3_len = l3_length(cfg_l3_inner); - il4_len = sizeof(struct udphdr); - - if (el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len >= - sizeof(buf)) - error(1, 0, "packet too large\n"); - - /* - * Fill packet from inside out, to calculate correct checksums. - * But create ip before udp headers, as udp uses ip for pseudo-sum. - */ - memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len, - cfg_payload_char, cfg_payload_len); - - /* add zero byte for udp csum padding */ - buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len] = 0; - - switch (cfg_l3_inner) { - case PF_INET: - build_ipv4_header(buf + el3_len + ol3_len + ol4_len, - IPPROTO_UDP, - in_saddr4.sin_addr.s_addr, - in_daddr4.sin_addr.s_addr, - il4_len + cfg_payload_len, - cfg_dsfield_inner); - break; - case PF_INET6: - build_ipv6_header(buf + el3_len + ol3_len + ol4_len, - IPPROTO_UDP, - &in_saddr6, &in_daddr6, - il4_len + cfg_payload_len, - cfg_dsfield_inner); - break; - } - - build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len, - cfg_payload_len, CFG_PORT_INNER, cfg_l3_inner); - - if (!cfg_encap_proto) - return il3_len + il4_len + cfg_payload_len; - - switch (cfg_l3_outer) { - case PF_INET: - build_ipv4_header(buf + el3_len, cfg_encap_proto, - out_saddr4.sin_addr.s_addr, - out_daddr4.sin_addr.s_addr, - ol4_len + il3_len + il4_len + cfg_payload_len, - cfg_dsfield_outer); - break; - case PF_INET6: - build_ipv6_header(buf + el3_len, cfg_encap_proto, - &out_saddr6, &out_daddr6, - ol4_len + il3_len + il4_len + cfg_payload_len, - cfg_dsfield_outer); - break; - } - - switch (cfg_encap_proto) { - case IPPROTO_UDP: - build_gue_header(buf + el3_len + ol3_len + ol4_len - - sizeof(struct guehdr), - cfg_l3_inner == PF_INET ? IPPROTO_IPIP - : IPPROTO_IPV6); - build_udp_header(buf + el3_len + ol3_len, - sizeof(struct guehdr) + il3_len + il4_len + - cfg_payload_len, - cfg_port_gue, cfg_l3_outer); - break; - case IPPROTO_GRE: - build_gre_header(buf + el3_len + ol3_len, - cfg_l3_inner == PF_INET ? ETH_P_IP - : ETH_P_IPV6); - break; - } - - switch (cfg_l3_extra) { - case PF_INET: - build_ipv4_header(buf, - cfg_l3_outer == PF_INET ? IPPROTO_IPIP - : IPPROTO_IPV6, - extra_saddr4.sin_addr.s_addr, - extra_daddr4.sin_addr.s_addr, - ol3_len + ol4_len + il3_len + il4_len + - cfg_payload_len, 0); - break; - case PF_INET6: - build_ipv6_header(buf, - cfg_l3_outer == PF_INET ? IPPROTO_IPIP - : IPPROTO_IPV6, - &extra_saddr6, &extra_daddr6, - ol3_len + ol4_len + il3_len + il4_len + - cfg_payload_len, 0); - break; - } - - return el3_len + ol3_len + ol4_len + il3_len + il4_len + - cfg_payload_len; -} - -/* sender transmits encapsulated over RAW or unencap'd over UDP */ -static int setup_tx(void) -{ - int family, fd, ret; - - if (cfg_l3_extra) - family = cfg_l3_extra; - else if (cfg_l3_outer) - family = cfg_l3_outer; - else - family = cfg_l3_inner; - - fd = socket(family, SOCK_RAW, IPPROTO_RAW); - if (fd == -1) - error(1, errno, "socket tx"); - - if (cfg_l3_extra) { - if (cfg_l3_extra == PF_INET) - ret = connect(fd, (void *) &extra_daddr4, - sizeof(extra_daddr4)); - else - ret = connect(fd, (void *) &extra_daddr6, - sizeof(extra_daddr6)); - if (ret) - error(1, errno, "connect tx"); - } else if (cfg_l3_outer) { - /* connect to destination if not encapsulated */ - if (cfg_l3_outer == PF_INET) - ret = connect(fd, (void *) &out_daddr4, - sizeof(out_daddr4)); - else - ret = connect(fd, (void *) &out_daddr6, - sizeof(out_daddr6)); - if (ret) - error(1, errno, "connect tx"); - } else { - /* otherwise using loopback */ - if (cfg_l3_inner == PF_INET) - ret = connect(fd, (void *) &in_daddr4, - sizeof(in_daddr4)); - else - ret = connect(fd, (void *) &in_daddr6, - sizeof(in_daddr6)); - if (ret) - error(1, errno, "connect tx"); - } - - return fd; -} - -/* receiver reads unencapsulated UDP */ -static int setup_rx(void) -{ - int fd, ret; - - fd = socket(cfg_l3_inner, SOCK_DGRAM, 0); - if (fd == -1) - error(1, errno, "socket rx"); - - if (cfg_l3_inner == PF_INET) - ret = bind(fd, (void *) &in_daddr4, sizeof(in_daddr4)); - else - ret = bind(fd, (void *) &in_daddr6, sizeof(in_daddr6)); - if (ret) - error(1, errno, "bind rx"); - - return fd; -} - -static int do_tx(int fd, const char *pkt, int len) -{ - int ret; - - ret = write(fd, pkt, len); - if (ret == -1) - error(1, errno, "send"); - if (ret != len) - error(1, errno, "send: len (%d < %d)\n", ret, len); - - return 1; -} - -static int do_poll(int fd, short events, int timeout) -{ - struct pollfd pfd; - int ret; - - pfd.fd = fd; - pfd.events = events; - - ret = poll(&pfd, 1, timeout); - if (ret == -1) - error(1, errno, "poll"); - if (ret && !(pfd.revents & POLLIN)) - error(1, errno, "poll: unexpected event 0x%x\n", pfd.revents); - - return ret; -} - -static int do_rx(int fd) -{ - char rbuf; - int ret, num = 0; - - while (1) { - ret = recv(fd, &rbuf, 1, MSG_DONTWAIT); - if (ret == -1 && errno == EAGAIN) - break; - if (ret == -1) - error(1, errno, "recv"); - if (rbuf != cfg_payload_char) - error(1, 0, "recv: payload mismatch"); - num++; - } - - return num; -} - -static int do_main(void) -{ - unsigned long tstop, treport, tcur; - int fdt = -1, fdr = -1, len, tx = 0, rx = 0; - - if (!cfg_only_tx) - fdr = setup_rx(); - if (!cfg_only_rx) - fdt = setup_tx(); - - len = build_packet(); - - tcur = util_gettime(); - treport = tcur + 1000; - tstop = tcur + (cfg_num_secs * 1000); - - while (1) { - if (!cfg_only_rx) - tx += do_tx(fdt, buf, len); - - if (!cfg_only_tx) - rx += do_rx(fdr); - - if (cfg_num_secs) { - tcur = util_gettime(); - if (tcur >= tstop) - break; - if (tcur >= treport) { - fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx); - tx = 0; - rx = 0; - treport = tcur + 1000; - } - } else { - if (tx == cfg_num_pkt) - break; - } - } - - /* read straggler packets, if any */ - if (rx < tx) { - tstop = util_gettime() + 100; - while (rx < tx) { - tcur = util_gettime(); - if (tcur >= tstop) - break; - - do_poll(fdr, POLLIN, tstop - tcur); - rx += do_rx(fdr); - } - } - - fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx); - - if (fdr != -1 && close(fdr)) - error(1, errno, "close rx"); - if (fdt != -1 && close(fdt)) - error(1, errno, "close tx"); - - /* - * success (== 0) only if received all packets - * unless failure is expected, in which case none must arrive. - */ - if (cfg_expect_failure) - return rx != 0; - else - return rx != tx; -} - - -static void __attribute__((noreturn)) usage(const char *filepath) -{ - fprintf(stderr, "Usage: %s [-e gre|gue|bare|none] [-i 4|6] [-l len] " - "[-O 4|6] [-o 4|6] [-n num] [-t secs] [-R] [-T] " - "[-s <osrc> [-d <odst>] [-S <isrc>] [-D <idst>] " - "[-x <otos>] [-X <itos>] [-f <isport>] [-F]\n", - filepath); - exit(1); -} - -static void parse_addr(int family, void *addr, const char *optarg) -{ - int ret; - - ret = inet_pton(family, optarg, addr); - if (ret == -1) - error(1, errno, "inet_pton"); - if (ret == 0) - error(1, 0, "inet_pton: bad string"); -} - -static void parse_addr4(struct sockaddr_in *addr, const char *optarg) -{ - parse_addr(AF_INET, &addr->sin_addr, optarg); -} - -static void parse_addr6(struct sockaddr_in6 *addr, const char *optarg) -{ - parse_addr(AF_INET6, &addr->sin6_addr, optarg); -} - -static int parse_protocol_family(const char *filepath, const char *optarg) -{ - if (!strcmp(optarg, "4")) - return PF_INET; - if (!strcmp(optarg, "6")) - return PF_INET6; - - usage(filepath); -} - -static void parse_opts(int argc, char **argv) -{ - int c; - - while ((c = getopt(argc, argv, "d:D:e:f:Fhi:l:n:o:O:Rs:S:t:Tx:X:")) != -1) { - switch (c) { - case 'd': - if (cfg_l3_outer == AF_UNSPEC) - error(1, 0, "-d must be preceded by -o"); - if (cfg_l3_outer == AF_INET) - parse_addr4(&out_daddr4, optarg); - else - parse_addr6(&out_daddr6, optarg); - break; - case 'D': - if (cfg_l3_inner == AF_UNSPEC) - error(1, 0, "-D must be preceded by -i"); - if (cfg_l3_inner == AF_INET) - parse_addr4(&in_daddr4, optarg); - else - parse_addr6(&in_daddr6, optarg); - break; - case 'e': - if (!strcmp(optarg, "gre")) - cfg_encap_proto = IPPROTO_GRE; - else if (!strcmp(optarg, "gue")) - cfg_encap_proto = IPPROTO_UDP; - else if (!strcmp(optarg, "bare")) - cfg_encap_proto = IPPROTO_IPIP; - else if (!strcmp(optarg, "none")) - cfg_encap_proto = IPPROTO_IP; /* == 0 */ - else - usage(argv[0]); - break; - case 'f': - cfg_src_port = strtol(optarg, NULL, 0); - break; - case 'F': - cfg_expect_failure = true; - break; - case 'h': - usage(argv[0]); - break; - case 'i': - if (!strcmp(optarg, "4")) - cfg_l3_inner = PF_INET; - else if (!strcmp(optarg, "6")) - cfg_l3_inner = PF_INET6; - else - usage(argv[0]); - break; - case 'l': - cfg_payload_len = strtol(optarg, NULL, 0); - break; - case 'n': - cfg_num_pkt = strtol(optarg, NULL, 0); - break; - case 'o': - cfg_l3_outer = parse_protocol_family(argv[0], optarg); - break; - case 'O': - cfg_l3_extra = parse_protocol_family(argv[0], optarg); - break; - case 'R': - cfg_only_rx = true; - break; - case 's': - if (cfg_l3_outer == AF_INET) - parse_addr4(&out_saddr4, optarg); - else - parse_addr6(&out_saddr6, optarg); - break; - case 'S': - if (cfg_l3_inner == AF_INET) - parse_addr4(&in_saddr4, optarg); - else - parse_addr6(&in_saddr6, optarg); - break; - case 't': - cfg_num_secs = strtol(optarg, NULL, 0); - break; - case 'T': - cfg_only_tx = true; - break; - case 'x': - cfg_dsfield_outer = strtol(optarg, NULL, 0); - break; - case 'X': - cfg_dsfield_inner = strtol(optarg, NULL, 0); - break; - } - } - - if (cfg_only_rx && cfg_only_tx) - error(1, 0, "options: cannot combine rx-only and tx-only"); - - if (cfg_encap_proto && cfg_l3_outer == AF_UNSPEC) - error(1, 0, "options: must specify outer with encap"); - else if ((!cfg_encap_proto) && cfg_l3_outer != AF_UNSPEC) - error(1, 0, "options: cannot combine no-encap and outer"); - else if ((!cfg_encap_proto) && cfg_l3_extra != AF_UNSPEC) - error(1, 0, "options: cannot combine no-encap and extra"); - - if (cfg_l3_inner == AF_UNSPEC) - cfg_l3_inner = AF_INET6; - if (cfg_l3_inner == AF_INET6 && cfg_encap_proto == IPPROTO_IPIP) - cfg_encap_proto = IPPROTO_IPV6; - - /* RFC 6040 4.2: - * on decap, if outer encountered congestion (CE == 0x3), - * but inner cannot encode ECN (NoECT == 0x0), then drop packet. - */ - if (((cfg_dsfield_outer & 0x3) == 0x3) && - ((cfg_dsfield_inner & 0x3) == 0x0)) - cfg_expect_failure = true; -} - -static void print_opts(void) -{ - if (cfg_l3_inner == PF_INET6) { - util_printaddr("inner.dest6", (void *) &in_daddr6); - util_printaddr("inner.source6", (void *) &in_saddr6); - } else { - util_printaddr("inner.dest4", (void *) &in_daddr4); - util_printaddr("inner.source4", (void *) &in_saddr4); - } - - if (!cfg_l3_outer) - return; - - fprintf(stderr, "encap proto: %u\n", cfg_encap_proto); - - if (cfg_l3_outer == PF_INET6) { - util_printaddr("outer.dest6", (void *) &out_daddr6); - util_printaddr("outer.source6", (void *) &out_saddr6); - } else { - util_printaddr("outer.dest4", (void *) &out_daddr4); - util_printaddr("outer.source4", (void *) &out_saddr4); - } - - if (!cfg_l3_extra) - return; - - if (cfg_l3_outer == PF_INET6) { - util_printaddr("extra.dest6", (void *) &extra_daddr6); - util_printaddr("extra.source6", (void *) &extra_saddr6); - } else { - util_printaddr("extra.dest4", (void *) &extra_daddr4); - util_printaddr("extra.source4", (void *) &extra_saddr4); - } - -} - -int main(int argc, char **argv) -{ - parse_opts(argc, argv); - print_opts(); - return do_main(); -} diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh deleted file mode 100755 index 4b298863797a..000000000000 --- a/tools/testing/selftests/bpf/test_flow_dissector.sh +++ /dev/null @@ -1,178 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Load BPF flow dissector and verify it correctly dissects traffic - -BPF_FILE="bpf_flow.bpf.o" -export TESTNAME=test_flow_dissector -unmount=0 - -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - -msg="skip all tests:" -if [ $UID != 0 ]; then - echo $msg please run this as root >&2 - exit $ksft_skip -fi - -# This test needs to be run in a network namespace with in_netns.sh. Check if -# this is the case and run it with in_netns.sh if it is being run in the root -# namespace. -if [[ -z $(ip netns identify $$) ]]; then - err=0 - if bpftool="$(which bpftool)"; then - echo "Testing global flow dissector..." - - $bpftool prog loadall $BPF_FILE /sys/fs/bpf/flow \ - type flow_dissector - - if ! unshare --net $bpftool prog attach pinned \ - /sys/fs/bpf/flow/_dissect flow_dissector; then - echo "Unexpected unsuccessful attach in namespace" >&2 - err=1 - fi - - $bpftool prog attach pinned /sys/fs/bpf/flow/_dissect \ - flow_dissector - - if unshare --net $bpftool prog attach pinned \ - /sys/fs/bpf/flow/_dissect flow_dissector; then - echo "Unexpected successful attach in namespace" >&2 - err=1 - fi - - if ! $bpftool prog detach pinned \ - /sys/fs/bpf/flow/_dissect flow_dissector; then - echo "Failed to detach flow dissector" >&2 - err=1 - fi - - rm -rf /sys/fs/bpf/flow - else - echo "Skipping root flow dissector test, bpftool not found" >&2 - fi - - # Run the rest of the tests in a net namespace. - ../net/in_netns.sh "$0" "$@" - err=$(( $err + $? )) - - if (( $err == 0 )); then - echo "selftests: $TESTNAME [PASS]"; - else - echo "selftests: $TESTNAME [FAILED]"; - fi - - exit $err -fi - -# Determine selftest success via shell exit code -exit_handler() -{ - set +e - - # Cleanup - tc filter del dev lo ingress pref 1337 2> /dev/null - tc qdisc del dev lo ingress 2> /dev/null - ./flow_dissector_load -d 2> /dev/null - if [ $unmount -ne 0 ]; then - umount bpffs 2> /dev/null - fi -} - -# Exit script immediately (well catched by trap handler) if any -# program/thing exits with a non-zero status. -set -e - -# (Use 'trap -l' to list meaning of numbers) -trap exit_handler 0 2 3 6 9 - -# Mount BPF file system -if /bin/mount | grep /sys/fs/bpf > /dev/null; then - echo "bpffs already mounted" -else - echo "bpffs not mounted. Mounting..." - unmount=1 - /bin/mount bpffs /sys/fs/bpf -t bpf -fi - -# Attach BPF program -./flow_dissector_load -p $BPF_FILE -s _dissect - -# Setup -tc qdisc add dev lo ingress -echo 0 > /proc/sys/net/ipv4/conf/default/rp_filter -echo 0 > /proc/sys/net/ipv4/conf/all/rp_filter -echo 0 > /proc/sys/net/ipv4/conf/lo/rp_filter - -echo "Testing IPv4..." -# Drops all IP/UDP packets coming from port 9 -tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \ - udp src_port 9 action drop - -# Send 10 IPv4/UDP packets from port 8. Filter should not drop any. -./test_flow_dissector -i 4 -f 8 -# Send 10 IPv4/UDP packets from port 9. Filter should drop all. -./test_flow_dissector -i 4 -f 9 -F -# Send 10 IPv4/UDP packets from port 10. Filter should not drop any. -./test_flow_dissector -i 4 -f 10 - -echo "Testing IPv4 from 127.0.0.127 (fallback to generic dissector)..." -# Send 10 IPv4/UDP packets from port 8. Filter should not drop any. -./test_flow_dissector -i 4 -S 127.0.0.127 -f 8 -# Send 10 IPv4/UDP packets from port 9. Filter should drop all. -./test_flow_dissector -i 4 -S 127.0.0.127 -f 9 -F -# Send 10 IPv4/UDP packets from port 10. Filter should not drop any. -./test_flow_dissector -i 4 -S 127.0.0.127 -f 10 - -echo "Testing IPIP..." -# Send 10 IPv4/IPv4/UDP packets from port 8. Filter should not drop any. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 8 -# Send 10 IPv4/IPv4/UDP packets from port 9. Filter should drop all. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 9 -F -# Send 10 IPv4/IPv4/UDP packets from port 10. Filter should not drop any. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 10 - -echo "Testing IPv4 + GRE..." -# Send 10 IPv4/GRE/IPv4/UDP packets from port 8. Filter should not drop any. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 8 -# Send 10 IPv4/GRE/IPv4/UDP packets from port 9. Filter should drop all. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 9 -F -# Send 10 IPv4/GRE/IPv4/UDP packets from port 10. Filter should not drop any. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 10 - -tc filter del dev lo ingress pref 1337 - -echo "Testing port range..." -# Drops all IP/UDP packets coming from port 8-10 -tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \ - udp src_port 8-10 action drop - -# Send 10 IPv4/UDP packets from port 7. Filter should not drop any. -./test_flow_dissector -i 4 -f 7 -# Send 10 IPv4/UDP packets from port 9. Filter should drop all. -./test_flow_dissector -i 4 -f 9 -F -# Send 10 IPv4/UDP packets from port 11. Filter should not drop any. -./test_flow_dissector -i 4 -f 11 - -tc filter del dev lo ingress pref 1337 - -echo "Testing IPv6..." -# Drops all IPv6/UDP packets coming from port 9 -tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \ - udp src_port 9 action drop - -# Send 10 IPv6/UDP packets from port 8. Filter should not drop any. -./test_flow_dissector -i 6 -f 8 -# Send 10 IPv6/UDP packets from port 9. Filter should drop all. -./test_flow_dissector -i 6 -f 9 -F -# Send 10 IPv6/UDP packets from port 10. Filter should not drop any. -./test_flow_dissector -i 6 -f 10 - -exit 0 diff --git a/tools/testing/selftests/bpf/bpf_testmod/.gitignore b/tools/testing/selftests/bpf/test_kmods/.gitignore similarity index 100% rename from tools/testing/selftests/bpf/bpf_testmod/.gitignore rename to tools/testing/selftests/bpf/test_kmods/.gitignore diff --git a/tools/testing/selftests/bpf/test_kmods/Makefile b/tools/testing/selftests/bpf/test_kmods/Makefile new file mode 100644 index 000000000000..d4e50c4509c9 --- /dev/null +++ b/tools/testing/selftests/bpf/test_kmods/Makefile @@ -0,0 +1,21 @@ +TEST_KMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(TEST_KMOD_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ + bpf_test_modorder_y.ko + +$(foreach m,$(MODULES),$(eval obj-m += $(m:.ko=.o))) + +CFLAGS_bpf_testmod.o = -I$(src) + +all: + $(Q)$(MAKE) -C $(KDIR) M=$(TEST_KMOD_DIR) modules + +clean: + $(Q)$(MAKE) -C $(KDIR) M=$(TEST_KMOD_DIR) clean diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_x.c similarity index 100% rename from tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c rename to tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_x.c diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_y.c similarity index 100% rename from tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c rename to tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_y.c diff --git a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_no_cfi.c similarity index 100% rename from tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c rename to tools/testing/selftests/bpf/test_kmods/bpf_test_no_cfi.c diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h similarity index 100% rename from tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h rename to tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c similarity index 100% rename from tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c rename to tools/testing/selftests/bpf/test_kmods/bpf_testmod.c diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h similarity index 100% rename from tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h rename to tools/testing/selftests/bpf/test_kmods/bpf_testmod.h diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h similarity index 100% rename from tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h rename to tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 6088d8222d59..c9e745d49493 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -1282,6 +1282,21 @@ void crash_handler(int signum) backtrace_symbols_fd(bt, sz, STDERR_FILENO); } +void hexdump(const char *prefix, const void *buf, size_t len) +{ + for (int i = 0; i < len; i++) { + if (!(i % 16)) { + if (i) + fprintf(stdout, "\n"); + fprintf(stdout, "%s", prefix); + } + if (i && !(i % 8) && (i % 16)) + fprintf(stdout, "\t"); + fprintf(stdout, "%02X ", ((uint8_t *)(buf))[i]); + } + fprintf(stdout, "\n"); +} + static void sigint_handler(int signum) { int i; diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 74de33ae37e5..404d0d4915d5 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -185,6 +185,7 @@ void test__end_subtest(void); void test__skip(void); void test__fail(void); int test__join_cgroup(const char *path); +void hexdump(const char *prefix, const void *buf, size_t len); #define PRINT_FAIL(format...) \ ({ \ @@ -344,6 +345,20 @@ int test__join_cgroup(const char *path); ___ok; \ }) +#define ASSERT_MEMEQ(actual, expected, len, name) ({ \ + static int duration = 0; \ + const void *__act = actual; \ + const void *__exp = expected; \ + int __len = len; \ + bool ___ok = memcmp(__act, __exp, __len) == 0; \ + CHECK(!___ok, (name), "unexpected memory mismatch\n"); \ + fprintf(stdout, "actual:\n"); \ + hexdump("\t", __act, __len); \ + fprintf(stdout, "expected:\n"); \ + hexdump("\t", __exp, __len); \ + ___ok; \ +}) + #define ASSERT_OK(res, name) ({ \ static int duration = 0; \ long long ___res = (res); \ diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index 7989ec608454..cb55a908bb0d 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -305,6 +305,7 @@ else client_connect verify_data server_listen + wait_for_port ${port} ${netcat_opt} fi # serverside, use BPF for decap diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh deleted file mode 100755 index 2740322c1878..000000000000 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ /dev/null @@ -1,58 +0,0 @@ -#!/bin/sh - -BPF_FILE="test_xdp_meta.bpf.o" -# Kselftest framework requirement - SKIP code is 4. -readonly KSFT_SKIP=4 -readonly NS1="ns1-$(mktemp -u XXXXXX)" -readonly NS2="ns2-$(mktemp -u XXXXXX)" - -cleanup() -{ - if [ "$?" = "0" ]; then - echo "selftests: test_xdp_meta [PASS]"; - else - echo "selftests: test_xdp_meta [FAILED]"; - fi - - set +e - ip link del veth1 2> /dev/null - ip netns del ${NS1} 2> /dev/null - ip netns del ${NS2} 2> /dev/null -} - -ip link set dev lo xdp off 2>/dev/null > /dev/null -if [ $? -ne 0 ];then - echo "selftests: [SKIP] Could not run test without the ip xdp support" - exit $KSFT_SKIP -fi -set -e - -ip netns add ${NS1} -ip netns add ${NS2} - -trap cleanup 0 2 3 6 9 - -ip link add veth1 type veth peer name veth2 - -ip link set veth1 netns ${NS1} -ip link set veth2 netns ${NS2} - -ip netns exec ${NS1} ip addr add 10.1.1.11/24 dev veth1 -ip netns exec ${NS2} ip addr add 10.1.1.22/24 dev veth2 - -ip netns exec ${NS1} tc qdisc add dev veth1 clsact -ip netns exec ${NS2} tc qdisc add dev veth2 clsact - -ip netns exec ${NS1} tc filter add dev veth1 ingress bpf da obj ${BPF_FILE} sec t -ip netns exec ${NS2} tc filter add dev veth2 ingress bpf da obj ${BPF_FILE} sec t - -ip netns exec ${NS1} ip link set dev veth1 xdp obj ${BPF_FILE} sec x -ip netns exec ${NS2} ip link set dev veth2 xdp obj ${BPF_FILE} sec x - -ip netns exec ${NS1} ip link set dev veth1 up -ip netns exec ${NS2} ip link set dev veth2 up - -ip netns exec ${NS1} ping -c 1 10.1.1.22 -ip netns exec ${NS2} ping -c 1 10.1.1.11 - -exit 0 diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh deleted file mode 100755 index 0746a4fde9d3..000000000000 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ /dev/null @@ -1,79 +0,0 @@ -#!/bin/bash -# Create 2 namespaces with two veth peers, and -# forward packets in-between using generic XDP -# -# NS1(veth11) NS2(veth22) -# | | -# | | -# (veth1, ------ (veth2, -# id:111) id:222) -# | xdp forwarding | -# ------------------ - -readonly NS1="ns1-$(mktemp -u XXXXXX)" -readonly NS2="ns2-$(mktemp -u XXXXXX)" -ret=0 - -setup() -{ - - local xdpmode=$1 - - ip netns add ${NS1} - ip netns add ${NS2} - - ip link add veth1 index 111 type veth peer name veth11 netns ${NS1} - ip link add veth2 index 222 type veth peer name veth22 netns ${NS2} - - ip link set veth1 up - ip link set veth2 up - ip -n ${NS1} link set dev veth11 up - ip -n ${NS2} link set dev veth22 up - - ip -n ${NS1} addr add 10.1.1.11/24 dev veth11 - ip -n ${NS2} addr add 10.1.1.22/24 dev veth22 -} - -cleanup() -{ - ip link del veth1 2> /dev/null - ip link del veth2 2> /dev/null - ip netns del ${NS1} 2> /dev/null - ip netns del ${NS2} 2> /dev/null -} - -test_xdp_redirect() -{ - local xdpmode=$1 - - setup - - ip link set dev veth1 $xdpmode off &> /dev/null - if [ $? -ne 0 ];then - echo "selftests: test_xdp_redirect $xdpmode [SKIP]" - return 0 - fi - - ip -n ${NS1} link set veth11 $xdpmode obj xdp_dummy.bpf.o sec xdp &> /dev/null - ip -n ${NS2} link set veth22 $xdpmode obj xdp_dummy.bpf.o sec xdp &> /dev/null - ip link set dev veth1 $xdpmode obj test_xdp_redirect.bpf.o sec redirect_to_222 &> /dev/null - ip link set dev veth2 $xdpmode obj test_xdp_redirect.bpf.o sec redirect_to_111 &> /dev/null - - if ip netns exec ${NS1} ping -c 1 10.1.1.22 &> /dev/null && - ip netns exec ${NS2} ping -c 1 10.1.1.11 &> /dev/null; then - echo "selftests: test_xdp_redirect $xdpmode [PASS]"; - else - ret=1 - echo "selftests: test_xdp_redirect $xdpmode [FAILED]"; - fi - - cleanup -} - -set -e -trap cleanup 2 3 6 9 - -test_xdp_redirect xdpgeneric -test_xdp_redirect xdpdrv - -exit $ret diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 2d742fdac6b9..81943c6254e6 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -293,6 +293,10 @@ static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *st return 0; } #else +# ifndef PROCMAP_QUERY_VMA_EXECUTABLE +# define PROCMAP_QUERY_VMA_EXECUTABLE 0x04 +# endif + static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { return -EOPNOTSUPP; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 7afc2619ab14..18596ae0b0c1 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -2252,7 +2252,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 7 }, - .errstr_unpriv = "invalid indirect read from stack R2 off -8+0 size 8", + .errstr_unpriv = "invalid read from stack R2 off -8+0 size 8", .result_unpriv = REJECT, /* in privileged mode reads from uninitialized stack locations are permitted */ .result = ACCEPT, diff --git a/tools/testing/selftests/bpf/verifier/map_kptr.c b/tools/testing/selftests/bpf/verifier/map_kptr.c index f420c0312aa0..4b39f8472f9b 100644 --- a/tools/testing/selftests/bpf/verifier/map_kptr.c +++ b/tools/testing/selftests/bpf/verifier/map_kptr.c @@ -373,7 +373,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .fixup_map_kptr = { 1 }, .result = REJECT, - .errstr = "Unreleased reference id=5 alloc_insn=20", + .errstr = "Unreleased reference id=4 alloc_insn=20", .fixup_kfunc_btf_id = { { "bpf_kfunc_call_test_acquire", 15 }, } diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index e12ef953fba8..06af5029885b 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -21,11 +21,20 @@ #include <gelf.h> #include <float.h> #include <math.h> +#include <limits.h> #ifndef ARRAY_SIZE #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #endif +#ifndef max +#define max(a, b) ((a) > (b) ? (a) : (b)) +#endif + +#ifndef min +#define min(a, b) ((a) < (b) ? (a) : (b)) +#endif + enum stat_id { VERDICT, DURATION, @@ -34,6 +43,11 @@ enum stat_id { PEAK_STATES, MAX_STATES_PER_INSN, MARK_READ_MAX_LEN, + SIZE, + JITED_SIZE, + STACK, + PROG_TYPE, + ATTACH_TYPE, FILE_NAME, PROG_NAME, @@ -203,7 +217,8 @@ const char argp_program_doc[] = "\n" "USAGE: veristat <obj-file> [<obj-file>...]\n" " OR: veristat -C <baseline.csv> <comparison.csv>\n" -" OR: veristat -R <results.csv>\n"; +" OR: veristat -R <results.csv>\n" +" OR: veristat -vl2 <to_analyze.bpf.o>\n"; enum { OPT_LOG_FIXED = 1000, @@ -215,7 +230,7 @@ static const struct argp_option opts[] = { { "version", 'V', NULL, 0, "Print version" }, { "verbose", 'v', NULL, 0, "Verbose mode" }, { "debug", 'd', NULL, 0, "Debug mode (turns on libbpf debug logging)" }, - { "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" }, + { "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode, 2 for full verification log)" }, { "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" }, { "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" }, { "top-n", 'n', "N", 0, "Emit only up to first N results." }, @@ -640,19 +655,21 @@ cleanup: } static const struct stat_specs default_output_spec = { - .spec_cnt = 7, + .spec_cnt = 8, .ids = { FILE_NAME, PROG_NAME, VERDICT, DURATION, - TOTAL_INSNS, TOTAL_STATES, PEAK_STATES, + TOTAL_INSNS, TOTAL_STATES, SIZE, JITED_SIZE }, }; static const struct stat_specs default_csv_output_spec = { - .spec_cnt = 9, + .spec_cnt = 14, .ids = { FILE_NAME, PROG_NAME, VERDICT, DURATION, TOTAL_INSNS, TOTAL_STATES, PEAK_STATES, MAX_STATES_PER_INSN, MARK_READ_MAX_LEN, + SIZE, JITED_SIZE, PROG_TYPE, ATTACH_TYPE, + STACK, }, }; @@ -688,6 +705,11 @@ static struct stat_def { [PEAK_STATES] = { "Peak states", {"peak_states"}, }, [MAX_STATES_PER_INSN] = { "Max states per insn", {"max_states_per_insn"}, }, [MARK_READ_MAX_LEN] = { "Max mark read length", {"max_mark_read_len", "mark_read"}, }, + [SIZE] = { "Program size", {"prog_size"}, }, + [JITED_SIZE] = { "Jited size", {"prog_size_jited"}, }, + [STACK] = {"Stack depth", {"stack_depth", "stack"}, }, + [PROG_TYPE] = { "Program type", {"prog_type"}, }, + [ATTACH_TYPE] = { "Attach type", {"attach_type", }, }, }; static bool parse_stat_id_var(const char *name, size_t len, int *id, @@ -835,7 +857,8 @@ static char verif_log_buf[64 * 1024]; static int parse_verif_log(char * const buf, size_t buf_sz, struct verif_stats *s) { const char *cur; - int pos, lines; + int pos, lines, sub_stack, cnt = 0; + char *state = NULL, *token, stack[512]; buf[buf_sz - 1] = '\0'; @@ -853,15 +876,22 @@ static int parse_verif_log(char * const buf, size_t buf_sz, struct verif_stats * if (1 == sscanf(cur, "verification time %ld usec\n", &s->stats[DURATION])) continue; - if (6 == sscanf(cur, "processed %ld insns (limit %*d) max_states_per_insn %ld total_states %ld peak_states %ld mark_read %ld", + if (5 == sscanf(cur, "processed %ld insns (limit %*d) max_states_per_insn %ld total_states %ld peak_states %ld mark_read %ld", &s->stats[TOTAL_INSNS], &s->stats[MAX_STATES_PER_INSN], &s->stats[TOTAL_STATES], &s->stats[PEAK_STATES], &s->stats[MARK_READ_MAX_LEN])) continue; - } + if (1 == sscanf(cur, "stack depth %511s", stack)) + continue; + } + while ((token = strtok_r(cnt++ ? NULL : stack, "+", &state))) { + if (sscanf(token, "%d", &sub_stack) == 0) + break; + s->stats[STACK] += sub_stack; + } return 0; } @@ -884,7 +914,7 @@ static int line_cnt_cmp(const void *a, const void *b) const struct line_cnt *b_cnt = (const struct line_cnt *)b; if (a_cnt->cnt != b_cnt->cnt) - return a_cnt->cnt < b_cnt->cnt ? -1 : 1; + return a_cnt->cnt > b_cnt->cnt ? -1 : 1; return strcmp(a_cnt->line, b_cnt->line); } @@ -1032,6 +1062,41 @@ static int guess_prog_type_by_ctx_name(const char *ctx_name, return -ESRCH; } +/* Make sure only target program is referenced from struct_ops map, + * otherwise libbpf would automatically set autocreate for all + * referenced programs. + * See libbpf.c:bpf_object_adjust_struct_ops_autoload. + */ +static void mask_unrelated_struct_ops_progs(struct bpf_object *obj, + struct bpf_map *map, + struct bpf_program *prog) +{ + struct btf *btf = bpf_object__btf(obj); + const struct btf_type *t, *mt; + struct btf_member *m; + int i, moff; + size_t data_sz, ptr_sz = sizeof(void *); + void *data; + + t = btf__type_by_id(btf, bpf_map__btf_value_type_id(map)); + if (!btf_is_struct(t)) + return; + + data = bpf_map__initial_value(map, &data_sz); + for (i = 0; i < btf_vlen(t); i++) { + m = &btf_members(t)[i]; + mt = btf__type_by_id(btf, m->type); + if (!btf_is_ptr(mt)) + continue; + moff = m->offset / 8; + if (moff + ptr_sz > data_sz) + continue; + if (memcmp(data + moff, &prog, ptr_sz) == 0) + continue; + memset(data + moff, 0, ptr_sz); + } +} + static void fixup_obj(struct bpf_object *obj, struct bpf_program *prog, const char *filename) { struct bpf_map *map; @@ -1047,6 +1112,9 @@ static void fixup_obj(struct bpf_object *obj, struct bpf_program *prog, const ch case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_CGROUP_STORAGE: break; + case BPF_MAP_TYPE_STRUCT_OPS: + mask_unrelated_struct_ops_progs(obj, map, prog); + break; default: if (bpf_map__max_entries(map) == 0) bpf_map__set_max_entries(map, 1); @@ -1146,8 +1214,11 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf char *buf; int buf_sz, log_level; struct verif_stats *stats; + struct bpf_prog_info info; + __u32 info_len = sizeof(info); int err = 0; void *tmp; + int fd; if (!should_process_file_prog(base_filename, bpf_program__name(prog))) { env.progs_skipped++; @@ -1196,6 +1267,15 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf stats->file_name = strdup(base_filename); stats->prog_name = strdup(bpf_program__name(prog)); stats->stats[VERDICT] = err == 0; /* 1 - success, 0 - failure */ + stats->stats[SIZE] = bpf_program__insn_cnt(prog); + stats->stats[PROG_TYPE] = bpf_program__type(prog); + stats->stats[ATTACH_TYPE] = bpf_program__expected_attach_type(prog); + + memset(&info, 0, info_len); + fd = bpf_program__fd(prog); + if (fd > 0 && bpf_prog_get_info_by_fd(fd, &info, &info_len) == 0) + stats->stats[JITED_SIZE] = info.jited_prog_len; + parse_verif_log(buf, buf_sz, stats); if (env.verbose) { @@ -1309,6 +1389,11 @@ static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2, case PROG_NAME: cmp = strcmp(s1->prog_name, s2->prog_name); break; + case ATTACH_TYPE: + case PROG_TYPE: + case SIZE: + case JITED_SIZE: + case STACK: case VERDICT: case DURATION: case TOTAL_INSNS: @@ -1523,12 +1608,27 @@ static void prepare_value(const struct verif_stats *s, enum stat_id id, else *str = s->stats[VERDICT] ? "success" : "failure"; break; + case ATTACH_TYPE: + if (!s) + *str = "N/A"; + else + *str = libbpf_bpf_attach_type_str(s->stats[ATTACH_TYPE]) ?: "N/A"; + break; + case PROG_TYPE: + if (!s) + *str = "N/A"; + else + *str = libbpf_bpf_prog_type_str(s->stats[PROG_TYPE]) ?: "N/A"; + break; case DURATION: case TOTAL_INSNS: case TOTAL_STATES: case PEAK_STATES: case MAX_STATES_PER_INSN: case MARK_READ_MAX_LEN: + case STACK: + case SIZE: + case JITED_SIZE: *val = s ? s->stats[id] : 0; break; default: @@ -1612,7 +1712,10 @@ static int parse_stat_value(const char *str, enum stat_id id, struct verif_stats case TOTAL_STATES: case PEAK_STATES: case MAX_STATES_PER_INSN: - case MARK_READ_MAX_LEN: { + case MARK_READ_MAX_LEN: + case SIZE: + case JITED_SIZE: + case STACK: { long val; int err, n; @@ -1625,6 +1728,42 @@ static int parse_stat_value(const char *str, enum stat_id id, struct verif_stats st->stats[id] = val; break; } + case PROG_TYPE: { + enum bpf_prog_type prog_type = 0; + const char *type; + + while ((type = libbpf_bpf_prog_type_str(prog_type))) { + if (strcmp(type, str) == 0) { + st->stats[id] = prog_type; + break; + } + prog_type++; + } + + if (!type) { + fprintf(stderr, "Unrecognized prog type %s\n", str); + return -EINVAL; + } + break; + } + case ATTACH_TYPE: { + enum bpf_attach_type attach_type = 0; + const char *type; + + while ((type = libbpf_bpf_attach_type_str(attach_type))) { + if (strcmp(type, str) == 0) { + st->stats[id] = attach_type; + break; + } + attach_type++; + } + + if (!type) { + fprintf(stderr, "Unrecognized attach type %s\n", str); + return -EINVAL; + } + break; + } default: fprintf(stderr, "Unrecognized stat #%d\n", id); return -EINVAL; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 6f9956eed797..6f7b15d6c6ed 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -27,7 +27,7 @@ #include <linux/errqueue.h> #include <linux/if_link.h> #include <linux/net_tstamp.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <linux/sockios.h> #include <linux/if_xdp.h> #include <sys/mman.h> @@ -79,7 +79,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id) .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, - .flags = XSK_UMEM__DEFAULT_FLAGS, + .flags = XDP_UMEM_TX_METADATA_LEN, .tx_metadata_len = sizeof(struct xsk_tx_metadata), }; __u32 idx = 0; @@ -551,6 +551,7 @@ static void hwtstamp_enable(const char *ifname) { struct hwtstamp_config cfg = { .rx_filter = HWTSTAMP_FILTER_ALL, + .tx_type = HWTSTAMP_TX_ON, }; hwtstamp_ioctl(SIOCGHWTSTAMP, ifname, &saved_hwtstamp_cfg); diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 03c1bdaed2c3..400a696a0d21 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -86,15 +86,15 @@ echo "" > test/cpuset.cpus # # If isolated CPUs have been reserved at boot time (as shown in -# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-7 +# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8 # that will be used by this script for testing purpose. If not, some of -# the tests may fail incorrectly. These isolated CPUs will also be removed -# before being compared with the expected results. +# the tests may fail incorrectly. These pre-isolated CPUs should stay in +# an isolated state throughout the testing process for now. # BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated) if [[ -n "$BOOT_ISOLCPUS" ]] then - [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 7 ]] && + [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] && skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested" echo "Pre-isolated CPUs: $BOOT_ISOLCPUS" fi @@ -683,15 +683,19 @@ check_isolcpus() EXPECT_VAL2=$EXPECT_VAL fi + # + # Appending pre-isolated CPUs + # Even though CPU #8 isn't used for testing, it can't be pre-isolated + # to make appending those CPUs easier. + # + [[ -n "$BOOT_ISOLCPUS" ]] && { + EXPECT_VAL=${EXPECT_VAL:+${EXPECT_VAL},}${BOOT_ISOLCPUS} + EXPECT_VAL2=${EXPECT_VAL2:+${EXPECT_VAL2},}${BOOT_ISOLCPUS} + } + # # Check cpuset.cpus.isolated cpumask # - if [[ -z "$BOOT_ISOLCPUS" ]] - then - ISOLCPUS=$(cat $ISCPUS) - else - ISOLCPUS=$(cat $ISCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") - fi [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && { # Take a 50ms pause and try again pause 0.05 @@ -731,8 +735,6 @@ check_isolcpus() fi done [[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU - [[ -n "BOOT_ISOLCPUS" ]] && - ISOLCPUS=$(echo $ISOLCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") [[ "$EXPECT_VAL" = "$ISOLCPUS" ]] } @@ -836,8 +838,11 @@ run_state_test() # if available [[ -n "$ICPUS" ]] && { check_isolcpus $ICPUS - [[ $? -ne 0 ]] && test_fail $I "isolated CPU" \ - "Expect $ICPUS, get $ISOLCPUS instead" + [[ $? -ne 0 ]] && { + [[ -n "$BOOT_ISOLCPUS" ]] && ICPUS=${ICPUS},${BOOT_ISOLCPUS} + test_fail $I "isolated CPU" \ + "Expect $ICPUS, get $ISOLCPUS instead" + } } reset_cgroup_states # diff --git a/tools/testing/selftests/coredump/Makefile b/tools/testing/selftests/coredump/Makefile new file mode 100644 index 000000000000..ed210037b29d --- /dev/null +++ b/tools/testing/selftests/coredump/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +CFLAGS = $(KHDR_INCLUDES) + +TEST_GEN_PROGS := stackdump_test +TEST_FILES := stackdump + +include ../lib.mk diff --git a/tools/testing/selftests/coredump/README.rst b/tools/testing/selftests/coredump/README.rst new file mode 100644 index 000000000000..164a7aa181c8 --- /dev/null +++ b/tools/testing/selftests/coredump/README.rst @@ -0,0 +1,50 @@ +coredump selftest +================= + +Background context +------------------ + +`coredump` is a feature which dumps a process's memory space when the process terminates +unexpectedly (e.g. due to segmentation fault), which can be useful for debugging. By default, +`coredump` dumps the memory to the file named `core`, but this behavior can be changed by writing a +different file name to `/proc/sys/kernel/core_pattern`. Furthermore, `coredump` can be piped to a +user-space program by writing the pipe symbol (`|`) followed by the command to be executed to +`/proc/sys/kernel/core_pattern`. For the full description, see `man 5 core`. + +The piped user program may be interested in reading the stack pointers of the crashed process. The +crashed process's stack pointers can be read from `procfs`: it is the `kstkesp` field in +`/proc/$PID/stat`. See `man 5 proc` for all the details. + +The problem +----------- +While a thread is active, the stack pointer is unsafe to read and therefore the `kstkesp` field +reads zero. But when the thread is dead (e.g. during a coredump), this field should have valid +value. + +However, this was broken in the past and `kstkesp` was zero even during coredump: + +* commit 0a1eb2d474ed ("fs/proc: Stop reporting eip and esp in /proc/PID/stat") changed kstkesp to + always be zero + +* commit fd7d56270b52 ("fs/proc: Report eip/esp in /prod/PID/stat for coredumping") fixed it for the + coredumping thread. However, other threads in a coredumping process still had the problem. + +* commit cb8f381f1613 ("fs/proc/array.c: allow reporting eip/esp for all coredumping threads") fixed + for all threads in a coredumping process. + +* commit 92307383082d ("coredump: Don't perform any cleanups before dumping core") broke it again + for the other threads in a coredumping process. + +The problem has been fixed now, but considering the history, it may appear again in the future. + +The goal of this test +--------------------- +This test detects problem with reading `kstkesp` during coredump by doing the following: + +#. Tell the kernel to execute the "stackdump" script when a coredump happens. This script + reads the stack pointers of all threads of crashed processes. + +#. Spawn a child process who creates some threads and then crashes. + +#. Read the output from the "stackdump" script, and make sure all stack pointer values are + non-zero. diff --git a/tools/testing/selftests/coredump/stackdump b/tools/testing/selftests/coredump/stackdump new file mode 100755 index 000000000000..96714ce42d12 --- /dev/null +++ b/tools/testing/selftests/coredump/stackdump @@ -0,0 +1,14 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +CRASH_PROGRAM_ID=$1 +STACKDUMP_FILE=$2 + +TMP=$(mktemp) + +for t in /proc/$CRASH_PROGRAM_ID/task/*; do + tid=$(basename $t) + cat /proc/$tid/stat | awk '{print $29}' >> $TMP +done + +mv $TMP $STACKDUMP_FILE diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c new file mode 100644 index 000000000000..137b2364a082 --- /dev/null +++ b/tools/testing/selftests/coredump/stackdump_test.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <fcntl.h> +#include <libgen.h> +#include <linux/limits.h> +#include <pthread.h> +#include <string.h> +#include <sys/resource.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +#define STACKDUMP_FILE "stack_values" +#define STACKDUMP_SCRIPT "stackdump" +#define NUM_THREAD_SPAWN 128 + +static void *do_nothing(void *) +{ + while (1) + pause(); +} + +static void crashing_child(void) +{ + pthread_t thread; + int i; + + for (i = 0; i < NUM_THREAD_SPAWN; ++i) + pthread_create(&thread, NULL, do_nothing, NULL); + + /* crash on purpose */ + i = *(int *)NULL; +} + +FIXTURE(coredump) +{ + char original_core_pattern[256]; +}; + +FIXTURE_SETUP(coredump) +{ + char buf[PATH_MAX]; + FILE *file; + char *dir; + int ret; + + file = fopen("/proc/sys/kernel/core_pattern", "r"); + ASSERT_NE(NULL, file); + + ret = fread(self->original_core_pattern, 1, sizeof(self->original_core_pattern), file); + ASSERT_TRUE(ret || feof(file)); + ASSERT_LT(ret, sizeof(self->original_core_pattern)); + + self->original_core_pattern[ret] = '\0'; + + ret = fclose(file); + ASSERT_EQ(0, ret); +} + +FIXTURE_TEARDOWN(coredump) +{ + const char *reason; + FILE *file; + int ret; + + unlink(STACKDUMP_FILE); + + file = fopen("/proc/sys/kernel/core_pattern", "w"); + if (!file) { + reason = "Unable to open core_pattern"; + goto fail; + } + + ret = fprintf(file, "%s", self->original_core_pattern); + if (ret < 0) { + reason = "Unable to write to core_pattern"; + goto fail; + } + + ret = fclose(file); + if (ret) { + reason = "Unable to close core_pattern"; + goto fail; + } + + return; +fail: + /* This should never happen */ + fprintf(stderr, "Failed to cleanup stackdump test: %s\n", reason); +} + +TEST_F(coredump, stackdump) +{ + struct sigaction action = {}; + unsigned long long stack; + char *test_dir, *line; + size_t line_length; + char buf[PATH_MAX]; + int ret, i; + FILE *file; + pid_t pid; + + /* + * Step 1: Setup core_pattern so that the stackdump script is executed when the child + * process crashes + */ + ret = readlink("/proc/self/exe", buf, sizeof(buf)); + ASSERT_NE(-1, ret); + ASSERT_LT(ret, sizeof(buf)); + buf[ret] = '\0'; + + test_dir = dirname(buf); + + file = fopen("/proc/sys/kernel/core_pattern", "w"); + ASSERT_NE(NULL, file); + + ret = fprintf(file, "|%1$s/%2$s %%P %1$s/%3$s", test_dir, STACKDUMP_SCRIPT, STACKDUMP_FILE); + ASSERT_LT(0, ret); + + ret = fclose(file); + ASSERT_EQ(0, ret); + + /* Step 2: Create a process who spawns some threads then crashes */ + pid = fork(); + ASSERT_TRUE(pid >= 0); + if (pid == 0) + crashing_child(); + + /* + * Step 3: Wait for the stackdump script to write the stack pointers to the stackdump file + */ + for (i = 0; i < 10; ++i) { + file = fopen(STACKDUMP_FILE, "r"); + if (file) + break; + sleep(1); + } + ASSERT_NE(file, NULL); + + /* Step 4: Make sure all stack pointer values are non-zero */ + for (i = 0; -1 != getline(&line, &line_length, file); ++i) { + stack = strtoull(line, NULL, 10); + ASSERT_NE(stack, 0); + } + + ASSERT_EQ(i, 1 + NUM_THREAD_SPAWN); + + fclose(file); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/cpufreq/.gitignore b/tools/testing/selftests/cpufreq/.gitignore new file mode 100644 index 000000000000..67604e91e068 --- /dev/null +++ b/tools/testing/selftests/cpufreq/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +cpufreq_selftest.* diff --git a/tools/testing/selftests/cpufreq/Makefile b/tools/testing/selftests/cpufreq/Makefile index c86ca8342222..9b2ccb10b0cf 100644 --- a/tools/testing/selftests/cpufreq/Makefile +++ b/tools/testing/selftests/cpufreq/Makefile @@ -3,6 +3,7 @@ all: TEST_PROGS := main.sh TEST_FILES := cpu.sh cpufreq.sh governor.sh module.sh special-tests.sh +EXTRA_CLEAN := cpufreq_selftest.dmesg_cpufreq.txt cpufreq_selftest.dmesg_full.txt cpufreq_selftest.txt include ../lib.mk diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore index 2ab675fecb6b..2f0297657c81 100644 --- a/tools/testing/selftests/damon/.gitignore +++ b/tools/testing/selftests/damon/.gitignore @@ -1,6 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -huge_count_read_write -debugfs_target_ids_read_before_terminate_race -debugfs_target_ids_pid_leak access_memory access_memory_even diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 812f656260fb..ecbf07afc6dd 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -1,15 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for damon selftests -TEST_GEN_FILES += huge_count_read_write -TEST_GEN_FILES += debugfs_target_ids_read_before_terminate_race -TEST_GEN_FILES += debugfs_target_ids_pid_leak TEST_GEN_FILES += access_memory access_memory_even -TEST_FILES = _chk_dependency.sh _debugfs_common.sh _damon_sysfs.py +TEST_FILES = _chk_dependency.sh _damon_sysfs.py # functionality tests -TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh TEST_PROGS += sysfs.sh TEST_PROGS += sysfs_update_schemes_tried_regions_wss_estimation.py TEST_PROGS += damos_quota.py damos_quota_goal.py damos_apply_interval.py @@ -17,11 +13,6 @@ TEST_PROGS += damos_tried_regions.py damon_nr_regions.py TEST_PROGS += reclaim.sh lru_sort.sh # regression tests (reproducers of previously found bugs) -TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh -TEST_PROGS += debugfs_duplicate_context_creation.sh -TEST_PROGS += debugfs_rm_non_contexts.sh -TEST_PROGS += debugfs_target_ids_read_before_terminate_race.sh -TEST_PROGS += debugfs_target_ids_pid_leak.sh TEST_PROGS += sysfs_update_removed_scheme_dir.sh TEST_PROGS += sysfs_update_schemes_tried_regions_hang.py diff --git a/tools/testing/selftests/damon/config b/tools/testing/selftests/damon/config index 0daf38974eb0..a68a9fead5dc 100644 --- a/tools/testing/selftests/damon/config +++ b/tools/testing/selftests/damon/config @@ -1,6 +1,5 @@ CONFIG_DAMON=y CONFIG_DAMON_SYSFS=y -CONFIG_DAMON_DBGFS=y CONFIG_DAMON_PADDR=y CONFIG_DAMON_VADDR=y CONFIG_DAMON_RECLAIM=y diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh deleted file mode 100755 index 902e312bca89..000000000000 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ /dev/null @@ -1,17 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test attrs file -# =============== - -file="$DBGFS/attrs" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4 5" "$orig_content" "valid input" -test_write_fail "$file" "1 2 3 4" "$orig_content" "no enough fields" -test_write_fail "$file" "1 2 3 5 4" "$orig_content" \ - "min_nr_regions > max_nr_regions" -test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written" -echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh b/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh deleted file mode 100755 index bd6c22d96ead..000000000000 --- a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh +++ /dev/null @@ -1,27 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test duplicated context creation -# ================================ - -if ! echo foo > "$DBGFS/mk_contexts" -then - echo "context creation failed" - exit 1 -fi - -if echo foo > "$DBGFS/mk_contexts" 2> /dev/null -then - echo "duplicate context creation success" - exit 1 -fi - -if ! echo foo > "$DBGFS/rm_contexts" -then - echo "context deletion failed" - exit 1 -fi - -exit 0 diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh deleted file mode 100755 index effbea33dc16..000000000000 --- a/tools/testing/selftests/damon/debugfs_empty_targets.sh +++ /dev/null @@ -1,21 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test empty targets case -# ======================= - -orig_target_ids=$(cat "$DBGFS/target_ids") -echo "" > "$DBGFS/target_ids" - -if [ -f "$DBGFS/monitor_on_DEPRECATED" ] -then - monitor_on_file="$DBGFS/monitor_on_DEPRECATED" -else - monitor_on_file="$DBGFS/monitor_on" -fi - -orig_monitor_on=$(cat "$monitor_on_file") -test_write_fail "$monitor_on_file" "on" "orig_monitor_on" "empty target ids" -echo "$orig_target_ids" > "$DBGFS/target_ids" diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh deleted file mode 100755 index 922cadac2950..000000000000 --- a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh +++ /dev/null @@ -1,22 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test huge count read write -# ========================== - -dmesg -C - -for file in "$DBGFS/"* -do - ./huge_count_read_write "$file" -done - -if dmesg | grep -q WARNING -then - dmesg - exit 1 -else - exit 0 -fi diff --git a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh b/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh deleted file mode 100755 index f3ffeb1343cf..000000000000 --- a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test putting non-ctx files/dirs to rm_contexts file -# =================================================== - -dmesg -C - -for file in "$DBGFS/"* -do - (echo "$(basename "$f")" > "$DBGFS/rm_contexts") &> /dev/null - if dmesg | grep -q BUG - then - dmesg - exit 1 - fi -done diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh deleted file mode 100755 index 5b39ab44731c..000000000000 --- a/tools/testing/selftests/damon/debugfs_schemes.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test schemes file -# ================= - -file="$DBGFS/schemes" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \ - "$orig_content" "valid input" -test_write_fail "$file" "1 2 -3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines" -test_write_succ "$file" "" "$orig_content" "disabling" -test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \ - "$orig_content" "wrong condition ranges" -echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh deleted file mode 100755 index 49aeabdb0aae..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test target_ids file -# ==================== - -file="$DBGFS/target_ids" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input" -test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input" -test_content "$file" "$orig_content" "1 2" "non-integer was there" -test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input" -test_content "$file" "$orig_content" "" "wrong input written" -test_write_succ "$file" "" "$orig_content" "empty input" -test_content "$file" "$orig_content" "" "empty input written" -echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c deleted file mode 100644 index 0cc2eef7d142..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c +++ /dev/null @@ -1,68 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Author: SeongJae Park <sj@kernel.org> - */ - -#define _GNU_SOURCE - -#include <fcntl.h> -#include <stdbool.h> -#include <stdint.h> -#include <stdio.h> -#include <stdlib.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <sys/time.h> -#include <unistd.h> - -#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids" - -static void write_targetid_exit(void) -{ - int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); - char pid_str[128]; - - snprintf(pid_str, sizeof(pid_str), "%d", getpid()); - write(target_ids_fd, pid_str, sizeof(pid_str)); - close(target_ids_fd); - exit(0); -} - -unsigned long msec_timestamp(void) -{ - struct timeval tv; - - gettimeofday(&tv, NULL); - return tv.tv_sec * 1000UL + tv.tv_usec / 1000; -} - -int main(int argc, char *argv[]) -{ - unsigned long start_ms; - int time_to_run, nr_forks = 0; - - if (argc != 2) { - fprintf(stderr, "Usage: %s <msecs to run>\n", argv[0]); - exit(1); - } - time_to_run = atoi(argv[1]); - - start_ms = msec_timestamp(); - while (true) { - int pid = fork(); - - if (pid < 0) { - fprintf(stderr, "fork() failed\n"); - exit(1); - } - if (pid == 0) - write_targetid_exit(); - wait(NULL); - nr_forks++; - - if (msec_timestamp() - start_ms > time_to_run) - break; - } - printf("%d\n", nr_forks); - return 0; -} diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh deleted file mode 100755 index 31fe33c2b032..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh +++ /dev/null @@ -1,22 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -before=$(grep "^pid " /proc/slabinfo | awk '{print $2}') - -nr_leaks=$(./debugfs_target_ids_pid_leak 1000) -expected_after_max=$((before + nr_leaks / 2)) - -after=$(grep "^pid " /proc/slabinfo | awk '{print $2}') - -echo > /sys/kernel/debug/damon/target_ids - -echo "tried $nr_leaks pid leak" -echo "number of active pid slabs: $before -> $after" -echo "(up to $expected_after_max expected)" -if [ $after -gt $expected_after_max ] -then - echo "maybe pids are leaking" - exit 1 -else - exit 0 -fi diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c deleted file mode 100644 index b06f52a8ce2d..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c +++ /dev/null @@ -1,80 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Author: SeongJae Park <sj@kernel.org> - */ -#define _GNU_SOURCE - -#include <fcntl.h> -#include <stdbool.h> -#include <stdint.h> -#include <stdio.h> -#include <stdlib.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <time.h> -#include <unistd.h> - -#define DBGFS_MONITOR_ON "/sys/kernel/debug/damon/monitor_on_DEPRECATED" -#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids" - -static void turn_damon_on_exit(void) -{ - int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); - int monitor_on_fd = open(DBGFS_MONITOR_ON, O_RDWR); - char pid_str[128]; - - snprintf(pid_str, sizeof(pid_str), "%d", getpid()); - write(target_ids_fd, pid_str, sizeof(pid_str)); - write(monitor_on_fd, "on\n", 3); - close(target_ids_fd); - close(monitor_on_fd); - usleep(1000); - exit(0); -} - -static void try_race(void) -{ - int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); - int pid = fork(); - int buf[256]; - - if (pid < 0) { - fprintf(stderr, "fork() failed\n"); - exit(1); - } - if (pid == 0) - turn_damon_on_exit(); - while (true) { - int status; - - read(target_ids_fd, buf, sizeof(buf)); - if (waitpid(-1, &status, WNOHANG) == pid) - break; - } - close(target_ids_fd); -} - -static inline uint64_t ts_to_ms(struct timespec *ts) -{ - return (uint64_t)ts->tv_sec * 1000 + (uint64_t)ts->tv_nsec / 1000000; -} - -int main(int argc, char *argv[]) -{ - struct timespec start_time, now; - int runtime_ms; - - if (argc != 2) { - fprintf(stderr, "Usage: %s <runtime in ms>\n", argv[0]); - exit(1); - } - runtime_ms = atoi(argv[1]); - clock_gettime(CLOCK_MONOTONIC, &start_time); - while (true) { - try_race(); - clock_gettime(CLOCK_MONOTONIC, &now); - if (ts_to_ms(&now) - ts_to_ms(&start_time) > runtime_ms) - break; - } - return 0; -} diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh deleted file mode 100755 index fc793c4c9aea..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh +++ /dev/null @@ -1,14 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -dmesg -C - -./debugfs_target_ids_read_before_terminate_race 5000 - -if dmesg | grep -q dbgfs_target_ids_read -then - dmesg - exit 1 -else - exit 0 -fi diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c deleted file mode 100644 index 53e69a669668..000000000000 --- a/tools/testing/selftests/damon/huge_count_read_write.c +++ /dev/null @@ -1,46 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Author: SeongJae Park <sj@kernel.org> - */ - -#include <fcntl.h> -#include <stdlib.h> -#include <unistd.h> -#include <stdio.h> - -#pragma GCC diagnostic push -#if __GNUC__ >= 11 && __GNUC_MINOR__ >= 1 -/* Ignore read(2) overflow and write(2) overread compile warnings */ -#pragma GCC diagnostic ignored "-Wstringop-overread" -#pragma GCC diagnostic ignored "-Wstringop-overflow" -#endif - -void write_read_with_huge_count(char *file) -{ - int filedesc = open(file, O_RDWR); - char buf[256]; - int ret; - - printf("%s %s\n", __func__, file); - if (filedesc < 0) { - fprintf(stderr, "failed opening %s\n", file); - exit(1); - } - - write(filedesc, "", 0xfffffffful); - ret = read(filedesc, buf, 0xfffffffful); - close(filedesc); -} - -#pragma GCC diagnostic pop - -int main(int argc, char *argv[]) -{ - if (argc != 2) { - fprintf(stderr, "Usage: %s <file>\n", argv[0]); - exit(1); - } - write_read_with_huge_count(argv[1]); - - return 0; -} diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 0fec8f9801ad..137470bdee0c 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -1,15 +1,18 @@ # SPDX-License-Identifier: GPL-2.0 TEST_INCLUDES := $(wildcard lib/py/*.py) \ + $(wildcard lib/sh/*.sh) \ ../../net/net_helper.sh \ ../../net/lib.sh \ TEST_PROGS := \ netcons_basic.sh \ + netcons_overflow.sh \ ping.py \ queues.py \ stats.py \ shaper.py \ + hds.py \ # end of TEST_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 03a089165d3f..2b10854e4b1e 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -10,7 +10,7 @@ TEST_PROGS := \ mode-2-recovery-updelay.sh \ bond_options.sh \ bond-eth-type-change.sh \ - bond_macvlan.sh + bond_macvlan_ipvlan.sh TEST_FILES := \ lag_lib.sh \ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh deleted file mode 100755 index b609fb6231f4..000000000000 --- a/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh +++ /dev/null @@ -1,99 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Test macvlan over balance-alb - -lib_dir=$(dirname "$0") -source ${lib_dir}/bond_topo_2d1c.sh - -m1_ns="m1-$(mktemp -u XXXXXX)" -m2_ns="m1-$(mktemp -u XXXXXX)" -m1_ip4="192.0.2.11" -m1_ip6="2001:db8::11" -m2_ip4="192.0.2.12" -m2_ip6="2001:db8::12" - -cleanup() -{ - ip -n ${m1_ns} link del macv0 - ip netns del ${m1_ns} - ip -n ${m2_ns} link del macv0 - ip netns del ${m2_ns} - - client_destroy - server_destroy - gateway_destroy -} - -check_connection() -{ - local ns=${1} - local target=${2} - local message=${3:-"macvlan_over_bond"} - RET=0 - - - ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null - check_err $? "ping failed" - log_test "$mode: $message" -} - -macvlan_over_bond() -{ - local param="$1" - RET=0 - - # setup new bond mode - bond_reset "${param}" - - ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge - ip -n ${s_ns} link set macv0 netns ${m1_ns} - ip -n ${m1_ns} link set dev macv0 up - ip -n ${m1_ns} addr add ${m1_ip4}/24 dev macv0 - ip -n ${m1_ns} addr add ${m1_ip6}/24 dev macv0 - - ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge - ip -n ${s_ns} link set macv0 netns ${m2_ns} - ip -n ${m2_ns} link set dev macv0 up - ip -n ${m2_ns} addr add ${m2_ip4}/24 dev macv0 - ip -n ${m2_ns} addr add ${m2_ip6}/24 dev macv0 - - sleep 2 - - check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server" - check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server" - check_connection "${c_ns}" "${m1_ip4}" "IPv4: client->macvlan_1" - check_connection "${c_ns}" "${m1_ip6}" "IPv6: client->macvlan_1" - check_connection "${c_ns}" "${m2_ip4}" "IPv4: client->macvlan_2" - check_connection "${c_ns}" "${m2_ip6}" "IPv6: client->macvlan_2" - check_connection "${m1_ns}" "${m2_ip4}" "IPv4: macvlan_1->macvlan_2" - check_connection "${m1_ns}" "${m2_ip6}" "IPv6: macvlan_1->macvlan_2" - - - sleep 5 - - check_connection "${s_ns}" "${c_ip4}" "IPv4: server->client" - check_connection "${s_ns}" "${c_ip6}" "IPv6: server->client" - check_connection "${m1_ns}" "${c_ip4}" "IPv4: macvlan_1->client" - check_connection "${m1_ns}" "${c_ip6}" "IPv6: macvlan_1->client" - check_connection "${m2_ns}" "${c_ip4}" "IPv4: macvlan_2->client" - check_connection "${m2_ns}" "${c_ip6}" "IPv6: macvlan_2->client" - check_connection "${m2_ns}" "${m1_ip4}" "IPv4: macvlan_2->macvlan_2" - check_connection "${m2_ns}" "${m1_ip6}" "IPv6: macvlan_2->macvlan_2" - - ip -n ${c_ns} neigh flush dev eth0 -} - -trap cleanup EXIT - -setup_prepare -ip netns add ${m1_ns} -ip netns add ${m2_ns} - -modes="active-backup balance-tlb balance-alb" - -for mode in $modes; do - macvlan_over_bond "mode $mode" -done - -exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh new file mode 100755 index 000000000000..c4711272fe45 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh @@ -0,0 +1,96 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test macvlan/ipvlan over bond + +lib_dir=$(dirname "$0") +source ${lib_dir}/bond_topo_2d1c.sh + +xvlan1_ns="xvlan1-$(mktemp -u XXXXXX)" +xvlan2_ns="xvlan2-$(mktemp -u XXXXXX)" +xvlan1_ip4="192.0.2.11" +xvlan1_ip6="2001:db8::11" +xvlan2_ip4="192.0.2.12" +xvlan2_ip6="2001:db8::12" + +cleanup() +{ + client_destroy + server_destroy + gateway_destroy + + ip netns del ${xvlan1_ns} + ip netns del ${xvlan2_ns} +} + +check_connection() +{ + local ns=${1} + local target=${2} + local message=${3} + RET=0 + + ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null + check_err $? "ping failed" + log_test "${bond_mode}/${xvlan_type}_${xvlan_mode}: ${message}" +} + +xvlan_over_bond() +{ + local param="$1" + local xvlan_type="$2" + local xvlan_mode="$3" + RET=0 + + # setup new bond mode + bond_reset "${param}" + + ip -n ${s_ns} link add link bond0 name ${xvlan_type}0 type ${xvlan_type} mode ${xvlan_mode} + ip -n ${s_ns} link set ${xvlan_type}0 netns ${xvlan1_ns} + ip -n ${xvlan1_ns} link set dev ${xvlan_type}0 up + ip -n ${xvlan1_ns} addr add ${xvlan1_ip4}/24 dev ${xvlan_type}0 + ip -n ${xvlan1_ns} addr add ${xvlan1_ip6}/24 dev ${xvlan_type}0 + + ip -n ${s_ns} link add link bond0 name ${xvlan_type}0 type ${xvlan_type} mode ${xvlan_mode} + ip -n ${s_ns} link set ${xvlan_type}0 netns ${xvlan2_ns} + ip -n ${xvlan2_ns} link set dev ${xvlan_type}0 up + ip -n ${xvlan2_ns} addr add ${xvlan2_ip4}/24 dev ${xvlan_type}0 + ip -n ${xvlan2_ns} addr add ${xvlan2_ip6}/24 dev ${xvlan_type}0 + + sleep 2 + + check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server" + check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server" + check_connection "${c_ns}" "${xvlan1_ip4}" "IPv4: client->${xvlan_type}_1" + check_connection "${c_ns}" "${xvlan1_ip6}" "IPv6: client->${xvlan_type}_1" + check_connection "${c_ns}" "${xvlan2_ip4}" "IPv4: client->${xvlan_type}_2" + check_connection "${c_ns}" "${xvlan2_ip6}" "IPv6: client->${xvlan_type}_2" + check_connection "${xvlan1_ns}" "${xvlan2_ip4}" "IPv4: ${xvlan_type}_1->${xvlan_type}_2" + check_connection "${xvlan1_ns}" "${xvlan2_ip6}" "IPv6: ${xvlan_type}_1->${xvlan_type}_2" + + check_connection "${s_ns}" "${c_ip4}" "IPv4: server->client" + check_connection "${s_ns}" "${c_ip6}" "IPv6: server->client" + check_connection "${xvlan1_ns}" "${c_ip4}" "IPv4: ${xvlan_type}_1->client" + check_connection "${xvlan1_ns}" "${c_ip6}" "IPv6: ${xvlan_type}_1->client" + check_connection "${xvlan2_ns}" "${c_ip4}" "IPv4: ${xvlan_type}_2->client" + check_connection "${xvlan2_ns}" "${c_ip6}" "IPv6: ${xvlan_type}_2->client" + check_connection "${xvlan2_ns}" "${xvlan1_ip4}" "IPv4: ${xvlan_type}_2->${xvlan_type}_1" + check_connection "${xvlan2_ns}" "${xvlan1_ip6}" "IPv6: ${xvlan_type}_2->${xvlan_type}_1" + + ip -n ${c_ns} neigh flush dev eth0 +} + +trap cleanup EXIT + +setup_prepare +ip netns add ${xvlan1_ns} +ip netns add ${xvlan2_ns} + +bond_modes="active-backup balance-tlb balance-alb" + +for bond_mode in ${bond_modes}; do + xvlan_over_bond "mode ${bond_mode}" macvlan bridge + xvlan_over_bond "mode ${bond_mode}" ipvlan l2 +done + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index 899d7fb6ea8e..dad4e5fda4db 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -3,6 +3,7 @@ CONFIG_BRIDGE=y CONFIG_DUMMY=y CONFIG_IPV6=y CONFIG_MACVLAN=y +CONFIG_IPVLAN=y CONFIG_NET_ACT_GACT=y CONFIG_NET_CLS_FLOWER=y CONFIG_NET_SCH_INGRESS=y diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py new file mode 100755 index 000000000000..394971b25c0b --- /dev/null +++ b/tools/testing/selftests/drivers/net/hds.py @@ -0,0 +1,120 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import errno +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx +from lib.py import EthtoolFamily, NlError +from lib.py import NetDrvEnv + +def get_hds(cfg, netnl) -> None: + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'tcp-data-split' not in rings: + raise KsftSkipEx('tcp-data-split not supported by device') + +def get_hds_thresh(cfg, netnl) -> None: + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'hds-thresh' not in rings: + raise KsftSkipEx('hds-thresh not supported by device') + +def set_hds_enable(cfg, netnl) -> None: + try: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'tcp-data-split': 'enabled'}) + except NlError as e: + if e.error == errno.EINVAL: + raise KsftSkipEx("disabling of HDS not supported by the device") + elif e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("ring-set not supported by the device") + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'tcp-data-split' not in rings: + raise KsftSkipEx('tcp-data-split not supported by device') + + ksft_eq('enabled', rings['tcp-data-split']) + +def set_hds_disable(cfg, netnl) -> None: + try: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'tcp-data-split': 'disabled'}) + except NlError as e: + if e.error == errno.EINVAL: + raise KsftSkipEx("disabling of HDS not supported by the device") + elif e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("ring-set not supported by the device") + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'tcp-data-split' not in rings: + raise KsftSkipEx('tcp-data-split not supported by device') + + ksft_eq('disabled', rings['tcp-data-split']) + +def set_hds_thresh_zero(cfg, netnl) -> None: + try: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': 0}) + except NlError as e: + if e.error == errno.EINVAL: + raise KsftSkipEx("hds-thresh-set not supported by the device") + elif e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("ring-set not supported by the device") + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'hds-thresh' not in rings: + raise KsftSkipEx('hds-thresh not supported by device') + + ksft_eq(0, rings['hds-thresh']) + +def set_hds_thresh_max(cfg, netnl) -> None: + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'hds-thresh' not in rings: + raise KsftSkipEx('hds-thresh not supported by device') + try: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': rings['hds-thresh-max']}) + except NlError as e: + if e.error == errno.EINVAL: + raise KsftSkipEx("hds-thresh-set not supported by the device") + elif e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("ring-set not supported by the device") + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + ksft_eq(rings['hds-thresh'], rings['hds-thresh-max']) + +def set_hds_thresh_gt(cfg, netnl) -> None: + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'hds-thresh' not in rings: + raise KsftSkipEx('hds-thresh not supported by device') + if 'hds-thresh-max' not in rings: + raise KsftSkipEx('hds-thresh-max not defined by device') + hds_gt = rings['hds-thresh-max'] + 1 + with ksft_raises(NlError) as e: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_gt}) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + +def main() -> None: + with NetDrvEnv(__file__, queue_count=3) as cfg: + ksft_run([get_hds, + get_hds_thresh, + set_hds_disable, + set_hds_enable, + set_hds_thresh_zero, + set_hds_thresh_max, + set_hds_thresh_gt], + args=(cfg, EthtoolFamily())) + ksft_exit() + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 8e502a1f8f9b..19a6969643f4 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -619,9 +619,6 @@ int do_server(struct memory_buffer *mem) fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", page_aligned_frags, non_page_aligned_frags); - fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", - page_aligned_frags, non_page_aligned_frags); - cleanup: free(tmp_mem); diff --git a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py index 05b6fbb3fcdd..ad192fef3117 100755 --- a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py +++ b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py @@ -21,9 +21,9 @@ def _enable_pp_allocation_fail(): if not os.path.exists("/sys/kernel/debug/fail_function"): raise KsftSkipEx("Kernel built without function error injection (or DebugFS)") - if not os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_pages"): + if not os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"): with open("/sys/kernel/debug/fail_function/inject", "w") as fp: - fp.write("page_pool_alloc_pages\n") + fp.write("page_pool_alloc_netmems\n") _write_fail_config({ "verbose": 0, @@ -37,7 +37,7 @@ def _disable_pp_allocation_fail(): if not os.path.exists("/sys/kernel/debug/fail_function"): return - if os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_pages"): + if os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"): with open("/sys/kernel/debug/fail_function/inject", "w") as fp: fp.write("\n") diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index 1ea9bb695e94..987e452d3a45 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -5,7 +5,7 @@ import time from pathlib import Path from lib.py import KsftSkipEx, KsftXfailEx from lib.py import ksft_setup -from lib.py import cmd, ethtool, ip +from lib.py import cmd, ethtool, ip, CmdExitFailure from lib.py import NetNS, NetdevSimDev from .remote import Remote @@ -48,6 +48,7 @@ class NetDrvEnv: else: self._ns = NetdevSimDev(**kwargs) self.dev = self._ns.nsims[0].dev + self.ifname = self.dev['ifname'] self.ifindex = self.dev['ifindex'] def __enter__(self): @@ -234,7 +235,12 @@ class NetDrvEpEnv: Good drivers will tell us via ethtool what their sync period is. """ if self._stats_settle_time is None: - data = ethtool("-c " + self.ifname, json=True)[0] + data = {} + try: + data = ethtool("-c " + self.ifname, json=True)[0] + except CmdExitFailure as e: + if "Operation not supported" not in e.cmd.stderr: + raise self._stats_settle_time = 0.025 + \ data.get('stats-block-usecs', 0) / 1000 / 1000 diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh new file mode 100644 index 000000000000..3acaba41ac7b --- /dev/null +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -0,0 +1,225 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This file contains functions and helpers to support the netconsole +# selftests +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +LIBDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +SRCIF="" # to be populated later +SRCIP=192.0.2.1 +DSTIF="" # to be populated later +DSTIP=192.0.2.2 + +PORT="6666" +MSG="netconsole selftest" +USERDATA_KEY="key" +USERDATA_VALUE="value" +TARGET=$(mktemp -u netcons_XXXXX) +DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk) +NETCONS_CONFIGFS="/sys/kernel/config/netconsole" +NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" +# NAMESPACE will be populated by setup_ns with a random value +NAMESPACE="" + +# IDs for netdevsim +NSIM_DEV_1_ID=$((256 + RANDOM % 256)) +NSIM_DEV_2_ID=$((512 + RANDOM % 256)) +NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device" + +# Used to create and delete namespaces +source "${LIBDIR}"/../../../../net/lib.sh +source "${LIBDIR}"/../../../../net/net_helper.sh + +# Create netdevsim interfaces +create_ifaces() { + + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" + udevadm settle 2> /dev/null || true + + local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID" + local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID" + + # These are global variables + SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \ + -path "$NSIM1"/net -exec basename {} \;) + DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \ + -path "$NSIM2"/net -exec basename {} \;) +} + +link_ifaces() { + local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" + local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex) + local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex) + + exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}" + exec {INITNS_FD}</proc/self/ns/net + + # Bind the dst interface to namespace + ip link set "${DSTIF}" netns "${NAMESPACE}" + + # Linking one device to the other one (on the other namespace} + if ! echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX" > $NSIM_DEV_SYS_LINK + then + echo "linking netdevsim1 with netdevsim2 should succeed" + cleanup + exit "${ksft_skip}" + fi +} + +function configure_ip() { + # Configure the IPs for both interfaces + ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}" + ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up + + ip addr add "${SRCIP}"/24 dev "${SRCIF}" + ip link set "${SRCIF}" up +} + +function set_network() { + # setup_ns function is coming from lib.sh + setup_ns NAMESPACE + + # Create both interfaces, and assign the destination to a different + # namespace + create_ifaces + + # Link both interfaces back to back + link_ifaces + + configure_ip +} + +function create_dynamic_target() { + DSTMAC=$(ip netns exec "${NAMESPACE}" \ + ip link show "${DSTIF}" | awk '/ether/ {print $2}') + + # Create a dynamic target + mkdir "${NETCONS_PATH}" + + echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip + echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip + echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac + echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name + + echo 1 > "${NETCONS_PATH}"/enabled +} + +function cleanup() { + local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" + + # delete netconsole dynamic reconfiguration + echo 0 > "${NETCONS_PATH}"/enabled + # Remove all the keys that got created during the selftest + find "${NETCONS_PATH}/userdata/" -mindepth 1 -type d -delete + # Remove the configfs entry + rmdir "${NETCONS_PATH}" + + # Delete netdevsim devices + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" + + # this is coming from lib.sh + cleanup_all_ns + + # Restoring printk configurations + echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk +} + +function set_user_data() { + if [[ ! -d "${NETCONS_PATH}""/userdata" ]] + then + echo "Userdata path not available in ${NETCONS_PATH}/userdata" + exit "${ksft_skip}" + fi + + KEY_PATH="${NETCONS_PATH}/userdata/${USERDATA_KEY}" + mkdir -p "${KEY_PATH}" + VALUE_PATH="${KEY_PATH}""/value" + echo "${USERDATA_VALUE}" > "${VALUE_PATH}" +} + +function listen_port_and_save_to() { + local OUTPUT=${1} + # Just wait for 2 seconds + timeout 2 ip netns exec "${NAMESPACE}" \ + socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" +} + +function validate_result() { + local TMPFILENAME="$1" + + # TMPFILENAME will contain something like: + # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM + # key=value + + # Check if the file exists + if [ ! -f "$TMPFILENAME" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${TMPFILENAME}"; then + echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then + echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + + # Delete the file once it is validated, otherwise keep it + # for debugging purposes + rm "${TMPFILENAME}" + exit "${ksft_pass}" +} + +function check_for_dependencies() { + if [ "$(id -u)" -ne 0 ]; then + echo "This test must be run as root" >&2 + exit "${ksft_skip}" + fi + + if ! which socat > /dev/null ; then + echo "SKIP: socat(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which ip > /dev/null ; then + echo "SKIP: ip(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which udevadm > /dev/null ; then + echo "SKIP: udevadm(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if [ ! -f "${NSIM_DEV_SYS_NEW}" ]; then + echo "SKIP: file ${NSIM_DEV_SYS_NEW} does not exist. Check if CONFIG_NETDEVSIM is enabled" >&2 + exit "${ksft_skip}" + fi + + if [ ! -d "${NETCONS_CONFIGFS}" ]; then + echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 + exit "${ksft_skip}" + fi + + if ip link show "${DSTIF}" 2> /dev/null; then + echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2 + exit "${ksft_skip}" + fi + + if ip addr list | grep -E "inet.*(${SRCIP}|${DSTIP})" 2> /dev/null; then + echo "SKIP: IPs already in use. Skipping it" >&2 + exit "${ksft_skip}" + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh index b79542a4dcc7..4a11bf1d514a 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh @@ -12,6 +12,7 @@ ALL_TESTS=" bridge_rif_remaster_port " +REQUIRE_TEAMD="yes" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh index e28f978104f3..b8bbe94f4736 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh @@ -10,6 +10,7 @@ ALL_TESTS=" lag_rif_nomaster_addr " +REQUIRE_TEAMD="yes" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh index 6318cfa6434c..d1a9d379eaf3 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh @@ -10,6 +10,7 @@ ALL_TESTS=" lag_rif_nomaster_addr " +REQUIRE_TEAMD="yes" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index b175f4d966e5..fe765da498e8 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -18,224 +18,8 @@ set -euo pipefail SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") -# Simple script to test dynamic targets in netconsole -SRCIF="" # to be populated later -SRCIP=192.0.2.1 -DSTIF="" # to be populated later -DSTIP=192.0.2.2 +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh -PORT="6666" -MSG="netconsole selftest" -USERDATA_KEY="key" -USERDATA_VALUE="value" -TARGET=$(mktemp -u netcons_XXXXX) -DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk) -NETCONS_CONFIGFS="/sys/kernel/config/netconsole" -NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" -KEY_PATH="${NETCONS_PATH}/userdata/${USERDATA_KEY}" -# NAMESPACE will be populated by setup_ns with a random value -NAMESPACE="" - -# IDs for netdevsim -NSIM_DEV_1_ID=$((256 + RANDOM % 256)) -NSIM_DEV_2_ID=$((512 + RANDOM % 256)) -NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device" - -# Used to create and delete namespaces -source "${SCRIPTDIR}"/../../net/lib.sh -source "${SCRIPTDIR}"/../../net/net_helper.sh - -# Create netdevsim interfaces -create_ifaces() { - - echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" - echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" - udevadm settle 2> /dev/null || true - - local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID" - local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID" - - # These are global variables - SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \ - -path "$NSIM1"/net -exec basename {} \;) - DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \ - -path "$NSIM2"/net -exec basename {} \;) -} - -link_ifaces() { - local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" - local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex) - local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex) - - exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}" - exec {INITNS_FD}</proc/self/ns/net - - # Bind the dst interface to namespace - ip link set "${DSTIF}" netns "${NAMESPACE}" - - # Linking one device to the other one (on the other namespace} - if ! echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX" > $NSIM_DEV_SYS_LINK - then - echo "linking netdevsim1 with netdevsim2 should succeed" - cleanup - exit "${ksft_skip}" - fi -} - -function configure_ip() { - # Configure the IPs for both interfaces - ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}" - ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up - - ip addr add "${SRCIP}"/24 dev "${SRCIF}" - ip link set "${SRCIF}" up -} - -function set_network() { - # setup_ns function is coming from lib.sh - setup_ns NAMESPACE - - # Create both interfaces, and assign the destination to a different - # namespace - create_ifaces - - # Link both interfaces back to back - link_ifaces - - configure_ip -} - -function create_dynamic_target() { - DSTMAC=$(ip netns exec "${NAMESPACE}" \ - ip link show "${DSTIF}" | awk '/ether/ {print $2}') - - # Create a dynamic target - mkdir "${NETCONS_PATH}" - - echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip - echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip - echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac - echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name - - echo 1 > "${NETCONS_PATH}"/enabled -} - -function cleanup() { - local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" - - # delete netconsole dynamic reconfiguration - echo 0 > "${NETCONS_PATH}"/enabled - # Remove key - rmdir "${KEY_PATH}" - # Remove the configfs entry - rmdir "${NETCONS_PATH}" - - # Delete netdevsim devices - echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" - echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" - - # this is coming from lib.sh - cleanup_all_ns - - # Restoring printk configurations - echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk -} - -function set_user_data() { - if [[ ! -d "${NETCONS_PATH}""/userdata" ]] - then - echo "Userdata path not available in ${NETCONS_PATH}/userdata" - exit "${ksft_skip}" - fi - - mkdir -p "${KEY_PATH}" - VALUE_PATH="${KEY_PATH}""/value" - echo "${USERDATA_VALUE}" > "${VALUE_PATH}" -} - -function listen_port_and_save_to() { - local OUTPUT=${1} - # Just wait for 2 seconds - timeout 2 ip netns exec "${NAMESPACE}" \ - socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" -} - -function validate_result() { - local TMPFILENAME="$1" - - # TMPFILENAME will contain something like: - # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM - # key=value - - # Check if the file exists - if [ ! -f "$TMPFILENAME" ]; then - echo "FAIL: File was not generated." >&2 - exit "${ksft_fail}" - fi - - if ! grep -q "${MSG}" "${TMPFILENAME}"; then - echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2 - cat "${TMPFILENAME}" >&2 - exit "${ksft_fail}" - fi - - if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then - echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2 - cat "${TMPFILENAME}" >&2 - exit "${ksft_fail}" - fi - - # Delete the file once it is validated, otherwise keep it - # for debugging purposes - rm "${TMPFILENAME}" - exit "${ksft_pass}" -} - -function check_for_dependencies() { - if [ "$(id -u)" -ne 0 ]; then - echo "This test must be run as root" >&2 - exit "${ksft_skip}" - fi - - if ! which socat > /dev/null ; then - echo "SKIP: socat(1) is not available" >&2 - exit "${ksft_skip}" - fi - - if ! which ip > /dev/null ; then - echo "SKIP: ip(1) is not available" >&2 - exit "${ksft_skip}" - fi - - if ! which udevadm > /dev/null ; then - echo "SKIP: udevadm(1) is not available" >&2 - exit "${ksft_skip}" - fi - - if [ ! -f "${NSIM_DEV_SYS_NEW}" ]; then - echo "SKIP: file ${NSIM_DEV_SYS_NEW} does not exist. Check if CONFIG_NETDEVSIM is enabled" >&2 - exit "${ksft_skip}" - fi - - if [ ! -d "${NETCONS_CONFIGFS}" ]; then - echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 - exit "${ksft_skip}" - fi - - if ip link show "${DSTIF}" 2> /dev/null; then - echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2 - exit "${ksft_skip}" - fi - - if ip addr list | grep -E "inet.*(${SRCIP}|${DSTIP})" 2> /dev/null; then - echo "SKIP: IPs already in use. Skipping it" >&2 - exit "${ksft_skip}" - fi -} - -# ========== # -# Start here # -# ========== # modprobe netdevsim 2> /dev/null || true modprobe netconsole 2> /dev/null || true diff --git a/tools/testing/selftests/drivers/net/netcons_overflow.sh b/tools/testing/selftests/drivers/net/netcons_overflow.sh new file mode 100755 index 000000000000..29bad56448a2 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_overflow.sh @@ -0,0 +1,67 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This test verifies that users can successfully create up to +# MAX_USERDATA_ITEMS userdata entries without encountering any failures. +# +# Additionally, it tests for expected failure when attempting to exceed this +# maximum limit. +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh +# This is coming from netconsole code. Check for it in drivers/net/netconsole.c +MAX_USERDATA_ITEMS=16 + +# Function to create userdata entries +function create_userdata_max_entries() { + # All these keys should be created without any error + for i in $(seq $MAX_USERDATA_ITEMS) + do + # USERDATA_KEY is used by set_user_data + USERDATA_KEY="key"${i} + set_user_data + done +} + +# Function to verify the entry limit +function verify_entry_limit() { + # Allowing the test to fail without exiting, since the next command + # will fail + set +e + mkdir "${NETCONS_PATH}/userdata/key_that_will_fail" 2> /dev/null + ret="$?" + set -e + if [ "$ret" -eq 0 ]; + then + echo "Adding more than ${MAX_USERDATA_ITEMS} entries in userdata should fail, but it didn't" >&2 + ls "${NETCONS_PATH}/userdata/" >&2 + exit "${ksft_fail}" + fi +} + +# ========== # +# Start here # +# ========== # + +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2> /dev/null || true + +# Check for basic system dependency and exit if not found +check_for_dependencies + +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target +# populate the maximum number of supported keys in userdata +create_userdata_max_entries +# Verify an additional entry is not allowed +verify_entry_limit +exit "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh index fd13c8cfb7a8..b411fe66510f 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh @@ -58,9 +58,12 @@ for root in mq mqprio; do ethtool -L $NDEV combined 4 n_child_assert 4 "One real queue, rest default" - # Graft some - tcq replace parent 100:1 handle 204: - n_child_assert 3 "Grafted" + # Remove real one + tcq del parent 100:4 handle 204: + + # Replace default with pfifo + tcq replace parent 100:1 handle 205: pfifo limit 1000 + n_child_assert 3 "Deleting real one, replacing default one with pfifo" ethtool -L $NDEV combined 1 n_child_assert 1 "Grafted, one" diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 384cfa3d38a6..92c2f0376c08 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -142,7 +142,7 @@ function pre_ethtool { } function check_table { - local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1 local -n expected=$2 local last=$3 @@ -212,7 +212,7 @@ function check_tables { } function print_table { - local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1 read -a have < $path tree $NSIM_DEV_DFS/ @@ -641,7 +641,7 @@ for port in 0 1; do NSIM_NETDEV=`get_netdev_name old_netdevs` ip link set dev $NSIM_NETDEV up - echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error msg="1 - create VxLANs v6" exp0=( 0 0 0 0 ) @@ -663,7 +663,7 @@ for port in 0 1; do new_geneve gnv0 20000 msg="2 - destroy GENEVE" - echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error exp1=( `mke 20000 2` 0 0 0 ) del_dev gnv0 @@ -764,7 +764,7 @@ for port in 0 1; do msg="create VxLANs v4" new_vxlan vxlan0 10000 $NSIM_NETDEV - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="NIC device goes down" @@ -775,7 +775,7 @@ for port in 0 1; do fi check_tables - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="NIC device goes up again" @@ -789,7 +789,7 @@ for port in 0 1; do del_dev vxlan0 check_tables - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="destroy NIC" @@ -896,7 +896,7 @@ msg="vacate VxLAN in overflow table" exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) del_dev vxlan2 -echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset +echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="tunnels destroyed 2" diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 30f29096e27c..38303da957ee 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -1,32 +1,37 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -from lib.py import ksft_run, ksft_exit, ksft_eq, KsftSkipEx -from lib.py import EthtoolFamily, NetdevFamily +from lib.py import ksft_disruptive, ksft_exit, ksft_run +from lib.py import ksft_eq, ksft_raises, KsftSkipEx +from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import NetDrvEnv -from lib.py import cmd +from lib.py import cmd, defer, ip +import errno import glob -def sys_get_queues(ifname) -> int: - folders = glob.glob(f'/sys/class/net/{ifname}/queues/rx-*') +def sys_get_queues(ifname, qtype='rx') -> int: + folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*') return len(folders) -def nl_get_queues(cfg, nl): +def nl_get_queues(cfg, nl, qtype='rx'): queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True) if queues: - return len([q for q in queues if q['type'] == 'rx']) + return len([q for q in queues if q['type'] == qtype]) return None def get_queues(cfg, nl) -> None: - queues = nl_get_queues(cfg, nl) - if not queues: - raise KsftSkipEx('queue-get not supported by device') + snl = NetdevFamily(recv_size=4096) - expected = sys_get_queues(cfg.dev['ifname']) - ksft_eq(queues, expected) + for qtype in ['rx', 'tx']: + queues = nl_get_queues(cfg, snl, qtype) + if not queues: + raise KsftSkipEx('queue-get not supported by device') + + expected = sys_get_queues(cfg.dev['ifname'], qtype) + ksft_eq(queues, expected) def addremove_queues(cfg, nl) -> None: @@ -56,9 +61,27 @@ def addremove_queues(cfg, nl) -> None: ksft_eq(queues, expected) +@ksft_disruptive +def check_down(cfg, nl) -> None: + # Check the NAPI IDs before interface goes down and hides them + napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True) + + ip(f"link set dev {cfg.dev['ifname']} down") + defer(ip, f"link set dev {cfg.dev['ifname']} up") + + with ksft_raises(NlError) as cm: + nl.queue_get({'ifindex': cfg.ifindex, 'id': 0, 'type': 'rx'}) + ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT) + + if napis: + with ksft_raises(NlError) as cm: + nl.napi_get({'id': napis[0]['id']}) + ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT) + + def main() -> None: - with NetDrvEnv(__file__, queue_count=3) as cfg: - ksft_run([get_queues, addremove_queues], args=(cfg, NetdevFamily())) + with NetDrvEnv(__file__, queue_count=100) as cfg: + ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily())) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 63e3c045a3b2..efcc1e10575b 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -2,12 +2,15 @@ # SPDX-License-Identifier: GPL-2.0 import errno +import subprocess +import time from lib.py import ksft_run, ksft_exit, ksft_pr -from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx +from lib.py import ksft_ge, ksft_eq, ksft_is, ksft_in, ksft_lt, ksft_true, ksft_raises +from lib.py import KsftSkipEx, KsftXfailEx from lib.py import ksft_disruptive from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError from lib.py import NetDrvEnv -from lib.py import ip, defer +from lib.py import cmd, ip, defer ethnl = EthtoolFamily() netfam = NetdevFamily() @@ -110,6 +113,23 @@ def qstat_by_ifindex(cfg) -> None: ksft_ge(triple[1][key], triple[0][key], comment="bad key: " + key) ksft_ge(triple[2][key], triple[1][key], comment="bad key: " + key) + # Sanity check the dumps + queues = NetdevFamily(recv_size=4096).qstats_get({"scope": "queue"}, dump=True) + # Reformat the output into {ifindex: {rx: [id, id, ...], tx: [id, id, ...]}} + parsed = {} + for entry in queues: + ifindex = entry["ifindex"] + if ifindex not in parsed: + parsed[ifindex] = {"rx":[], "tx": []} + parsed[ifindex][entry["queue-type"]].append(entry['queue-id']) + # Now, validate + for ifindex, queues in parsed.items(): + for qtype in ['rx', 'tx']: + ksft_eq(len(queues[qtype]), len(set(queues[qtype])), + comment="repeated queue keys") + ksft_eq(len(queues[qtype]), max(queues[qtype]) + 1, + comment="missing queue keys") + # Test invalid dumps # 0 is invalid with ksft_raises(NlError) as cm: @@ -157,10 +177,95 @@ def check_down(cfg) -> None: netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True) +def __run_inf_loop(body): + body = body.strip() + if body[-1] != ';': + body += ';' + + return subprocess.Popen(f"while true; do {body} done", shell=True, + stdout=subprocess.PIPE, stderr=subprocess.PIPE) + + +def __stats_increase_sanely(old, new) -> None: + for k in old.keys(): + ksft_ge(new[k], old[k]) + ksft_lt(new[k] - old[k], 1 << 31, comment="likely wrapping error") + + +def procfs_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, which is not an exclusive + lock, make sure drivers can handle parallel reads of stats. + """ + one = __run_inf_loop("cat /proc/net/dev") + defer(one.kill) + two = __run_inf_loop("cat /proc/net/dev") + defer(two.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(one.poll(), None) + ksft_is(two.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + time.sleep(2) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + # defers will kill the loops + + +@ksft_disruptive +def procfs_downup_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, drivers often try + to sleep when reading the stats, or don't protect against races. + """ + # Max out the queues, we'll flip between max and 1 + channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + if channels['combined-count'] == 0: + rx_type = 'rx' + else: + rx_type = 'combined' + cur_queue_cnt = channels[f'{rx_type}-count'] + max_queue_cnt = channels[f'{rx_type}-max'] + + cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}") + defer(cmd, f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}") + + # Real test stats + stats = __run_inf_loop("cat /proc/net/dev") + defer(stats.kill) + + ipset = f"ip link set dev {cfg.ifname}" + defer(ip, f"link set dev {cfg.ifname} up") + # The "echo -n 1" lets us count iterations below + updown = f"{ipset} down; sleep 0.05; {ipset} up; sleep 0.05; " + \ + f"ethtool -L {cfg.ifname} {rx_type} 1; " + \ + f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}; " + \ + "echo -n 1" + updown = __run_inf_loop(updown) + kill_updown = defer(updown.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(stats.poll(), None) + ksft_is(updown.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + # We're looking for crashes, give it extra time + time.sleep(9) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + + kill_updown.exec() + stdout, _ = updown.communicate(timeout=5) + ksft_pr("completed up/down cycles:", len(stdout.decode('utf-8'))) + + def main() -> None: - with NetDrvEnv(__file__) as cfg: + with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, - check_down], + check_down, procfs_hammer, procfs_downup_hammer], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/ntsync/.gitignore b/tools/testing/selftests/drivers/ntsync/.gitignore new file mode 100644 index 000000000000..848573a3d3ea --- /dev/null +++ b/tools/testing/selftests/drivers/ntsync/.gitignore @@ -0,0 +1 @@ +ntsync diff --git a/tools/testing/selftests/drivers/ntsync/Makefile b/tools/testing/selftests/drivers/ntsync/Makefile new file mode 100644 index 000000000000..dbf2b055c0b2 --- /dev/null +++ b/tools/testing/selftests/drivers/ntsync/Makefile @@ -0,0 +1,7 @@ +# SPDX-LICENSE-IDENTIFIER: GPL-2.0-only +TEST_GEN_PROGS := ntsync + +CFLAGS += $(KHDR_INCLUDES) +LDLIBS += -lpthread + +include ../../lib.mk diff --git a/tools/testing/selftests/drivers/ntsync/config b/tools/testing/selftests/drivers/ntsync/config new file mode 100644 index 000000000000..60539c826d06 --- /dev/null +++ b/tools/testing/selftests/drivers/ntsync/config @@ -0,0 +1 @@ +CONFIG_WINESYNC=y diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c new file mode 100644 index 000000000000..3aad311574c4 --- /dev/null +++ b/tools/testing/selftests/drivers/ntsync/ntsync.c @@ -0,0 +1,1343 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Various unit tests for the "ntsync" synchronization primitive driver. + * + * Copyright (C) 2021-2022 Elizabeth Figura <zfigura@codeweavers.com> + */ + +#define _GNU_SOURCE +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <time.h> +#include <pthread.h> +#include <linux/ntsync.h> +#include "../../kselftest_harness.h" + +static int read_sem_state(int sem, __u32 *count, __u32 *max) +{ + struct ntsync_sem_args args; + int ret; + + memset(&args, 0xcc, sizeof(args)); + ret = ioctl(sem, NTSYNC_IOC_SEM_READ, &args); + *count = args.count; + *max = args.max; + return ret; +} + +#define check_sem_state(sem, count, max) \ + ({ \ + __u32 __count, __max; \ + int ret = read_sem_state((sem), &__count, &__max); \ + EXPECT_EQ(0, ret); \ + EXPECT_EQ((count), __count); \ + EXPECT_EQ((max), __max); \ + }) + +static int release_sem(int sem, __u32 *count) +{ + return ioctl(sem, NTSYNC_IOC_SEM_RELEASE, count); +} + +static int read_mutex_state(int mutex, __u32 *count, __u32 *owner) +{ + struct ntsync_mutex_args args; + int ret; + + memset(&args, 0xcc, sizeof(args)); + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &args); + *count = args.count; + *owner = args.owner; + return ret; +} + +#define check_mutex_state(mutex, count, owner) \ + ({ \ + __u32 __count, __owner; \ + int ret = read_mutex_state((mutex), &__count, &__owner); \ + EXPECT_EQ(0, ret); \ + EXPECT_EQ((count), __count); \ + EXPECT_EQ((owner), __owner); \ + }) + +static int unlock_mutex(int mutex, __u32 owner, __u32 *count) +{ + struct ntsync_mutex_args args; + int ret; + + args.owner = owner; + args.count = 0xdeadbeef; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_UNLOCK, &args); + *count = args.count; + return ret; +} + +static int read_event_state(int event, __u32 *signaled, __u32 *manual) +{ + struct ntsync_event_args args; + int ret; + + memset(&args, 0xcc, sizeof(args)); + ret = ioctl(event, NTSYNC_IOC_EVENT_READ, &args); + *signaled = args.signaled; + *manual = args.manual; + return ret; +} + +#define check_event_state(event, signaled, manual) \ + ({ \ + __u32 __signaled, __manual; \ + int ret = read_event_state((event), &__signaled, &__manual); \ + EXPECT_EQ(0, ret); \ + EXPECT_EQ((signaled), __signaled); \ + EXPECT_EQ((manual), __manual); \ + }) + +static int wait_objs(int fd, unsigned long request, __u32 count, + const int *objs, __u32 owner, int alert, __u32 *index) +{ + struct ntsync_wait_args args = {0}; + struct timespec timeout; + int ret; + + clock_gettime(CLOCK_MONOTONIC, &timeout); + + args.timeout = timeout.tv_sec * 1000000000 + timeout.tv_nsec; + args.count = count; + args.objs = (uintptr_t)objs; + args.owner = owner; + args.index = 0xdeadbeef; + args.alert = alert; + ret = ioctl(fd, request, &args); + *index = args.index; + return ret; +} + +static int wait_any(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index) +{ + return wait_objs(fd, NTSYNC_IOC_WAIT_ANY, count, objs, owner, 0, index); +} + +static int wait_all(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index) +{ + return wait_objs(fd, NTSYNC_IOC_WAIT_ALL, count, objs, owner, 0, index); +} + +static int wait_any_alert(int fd, __u32 count, const int *objs, + __u32 owner, int alert, __u32 *index) +{ + return wait_objs(fd, NTSYNC_IOC_WAIT_ANY, + count, objs, owner, alert, index); +} + +static int wait_all_alert(int fd, __u32 count, const int *objs, + __u32 owner, int alert, __u32 *index) +{ + return wait_objs(fd, NTSYNC_IOC_WAIT_ALL, + count, objs, owner, alert, index); +} + +TEST(semaphore_state) +{ + struct ntsync_sem_args sem_args; + struct timespec timeout; + __u32 count, index; + int fd, ret, sem; + + clock_gettime(CLOCK_MONOTONIC, &timeout); + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 3; + sem_args.max = 2; + sem = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_EQ(-1, sem); + EXPECT_EQ(EINVAL, errno); + + sem_args.count = 2; + sem_args.max = 2; + sem = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, sem); + check_sem_state(sem, 2, 2); + + count = 0; + ret = release_sem(sem, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, count); + check_sem_state(sem, 2, 2); + + count = 1; + ret = release_sem(sem, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOVERFLOW, errno); + check_sem_state(sem, 2, 2); + + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(sem, 1, 2); + + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(sem, 0, 2); + + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + count = 3; + ret = release_sem(sem, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOVERFLOW, errno); + check_sem_state(sem, 0, 2); + + count = 2; + ret = release_sem(sem, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + check_sem_state(sem, 2, 2); + + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(0, ret); + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(0, ret); + + count = 1; + ret = release_sem(sem, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + check_sem_state(sem, 1, 2); + + count = ~0u; + ret = release_sem(sem, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOVERFLOW, errno); + check_sem_state(sem, 1, 2); + + close(sem); + + close(fd); +} + +TEST(mutex_state) +{ + struct ntsync_mutex_args mutex_args; + __u32 owner, count, index; + struct timespec timeout; + int fd, ret, mutex; + + clock_gettime(CLOCK_MONOTONIC, &timeout); + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + mutex_args.owner = 123; + mutex_args.count = 0; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_EQ(-1, mutex); + EXPECT_EQ(EINVAL, errno); + + mutex_args.owner = 0; + mutex_args.count = 2; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_EQ(-1, mutex); + EXPECT_EQ(EINVAL, errno); + + mutex_args.owner = 123; + mutex_args.count = 2; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, mutex); + check_mutex_state(mutex, 2, 123); + + ret = unlock_mutex(mutex, 0, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + ret = unlock_mutex(mutex, 456, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EPERM, errno); + check_mutex_state(mutex, 2, 123); + + ret = unlock_mutex(mutex, 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, count); + check_mutex_state(mutex, 1, 123); + + ret = unlock_mutex(mutex, 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, count); + check_mutex_state(mutex, 0, 0); + + ret = unlock_mutex(mutex, 123, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EPERM, errno); + + ret = wait_any(fd, 1, &mutex, 456, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 1, 456); + + ret = wait_any(fd, 1, &mutex, 456, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 2, 456); + + ret = unlock_mutex(mutex, 456, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, count); + check_mutex_state(mutex, 1, 456); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + owner = 0; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + owner = 123; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EPERM, errno); + check_mutex_state(mutex, 1, 456); + + owner = 456; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(0, ret); + + memset(&mutex_args, 0xcc, sizeof(mutex_args)); + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, mutex_args.count); + EXPECT_EQ(0, mutex_args.owner); + + memset(&mutex_args, 0xcc, sizeof(mutex_args)); + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, mutex_args.count); + EXPECT_EQ(0, mutex_args.owner); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 1, 123); + + owner = 123; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(0, ret); + + memset(&mutex_args, 0xcc, sizeof(mutex_args)); + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, mutex_args.count); + EXPECT_EQ(0, mutex_args.owner); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 1, 123); + + close(mutex); + + mutex_args.owner = 0; + mutex_args.count = 0; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, mutex); + check_mutex_state(mutex, 0, 0); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 1, 123); + + close(mutex); + + mutex_args.owner = 123; + mutex_args.count = ~0u; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, mutex); + check_mutex_state(mutex, ~0u, 123); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + close(mutex); + + close(fd); +} + +TEST(manual_event_state) +{ + struct ntsync_event_args event_args; + __u32 index, signaled; + int fd, event, ret; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + event_args.manual = 1; + event_args.signaled = 0; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + check_event_state(event, 0, 1); + + signaled = 0xdeadbeef; + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 1, 1); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 1, 1); + + ret = wait_any(fd, 1, &event, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_event_state(event, 1, 1); + + signaled = 0xdeadbeef; + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 0, 1); + + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 0, 1); + + ret = wait_any(fd, 1, &event, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + + ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 0, 1); + + ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 0, 1); + + close(event); + + close(fd); +} + +TEST(auto_event_state) +{ + struct ntsync_event_args event_args; + __u32 index, signaled; + int fd, event, ret; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + event_args.manual = 0; + event_args.signaled = 1; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + check_event_state(event, 1, 0); + + signaled = 0xdeadbeef; + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 1, 0); + + ret = wait_any(fd, 1, &event, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_event_state(event, 0, 0); + + signaled = 0xdeadbeef; + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 0, 0); + + ret = wait_any(fd, 1, &event, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + + ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 0, 0); + + ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 0, 0); + + close(event); + + close(fd); +} + +TEST(test_wait_any) +{ + int objs[NTSYNC_MAX_WAIT_COUNT + 1], fd, ret; + struct ntsync_mutex_args mutex_args = {0}; + struct ntsync_sem_args sem_args = {0}; + __u32 owner, index, count, i; + struct timespec timeout; + + clock_gettime(CLOCK_MONOTONIC, &timeout); + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 2; + sem_args.max = 3; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + mutex_args.owner = 0; + mutex_args.count = 0; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, objs[1]); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 0, 0); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 0, 0); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 1, 123); + + count = 1; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 1, 123); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 2, 123); + + ret = wait_any(fd, 2, objs, 456, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + owner = 123; + ret = ioctl(objs[1], NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(0, ret); + + ret = wait_any(fd, 2, objs, 456, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(1, index); + + ret = wait_any(fd, 2, objs, 456, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, index); + + close(objs[1]); + + /* test waiting on the same object twice */ + + count = 2; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + + objs[1] = objs[0]; + ret = wait_any(fd, 2, objs, 456, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 1, 3); + + ret = wait_any(fd, 0, NULL, 456, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + for (i = 1; i < NTSYNC_MAX_WAIT_COUNT + 1; ++i) + objs[i] = objs[0]; + + ret = wait_any(fd, NTSYNC_MAX_WAIT_COUNT, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = wait_any(fd, NTSYNC_MAX_WAIT_COUNT + 1, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + ret = wait_any(fd, -1, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + close(objs[0]); + + close(fd); +} + +TEST(test_wait_all) +{ + struct ntsync_event_args event_args = {0}; + struct ntsync_mutex_args mutex_args = {0}; + struct ntsync_sem_args sem_args = {0}; + __u32 owner, index, count; + int objs[2], fd, ret; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 2; + sem_args.max = 3; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + mutex_args.owner = 0; + mutex_args.count = 0; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, objs[1]); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 1, 123); + + ret = wait_all(fd, 2, objs, 456, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 1, 123); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 2, 123); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 2, 123); + + count = 3; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 2, 3); + check_mutex_state(objs[1], 3, 123); + + owner = 123; + ret = ioctl(objs[1], NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(0, ret); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 1, 123); + + close(objs[1]); + + event_args.manual = true; + event_args.signaled = true; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, objs[1]); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 0, 3); + check_event_state(objs[1], 1, 1); + + close(objs[1]); + + /* test waiting on the same object twice */ + objs[1] = objs[0]; + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + close(objs[0]); + + close(fd); +} + +struct wake_args { + int fd; + int obj; +}; + +struct wait_args { + int fd; + unsigned long request; + struct ntsync_wait_args *args; + int ret; + int err; +}; + +static void *wait_thread(void *arg) +{ + struct wait_args *args = arg; + + args->ret = ioctl(args->fd, args->request, args->args); + args->err = errno; + return NULL; +} + +static __u64 get_abs_timeout(unsigned int ms) +{ + struct timespec timeout; + clock_gettime(CLOCK_MONOTONIC, &timeout); + return (timeout.tv_sec * 1000000000) + timeout.tv_nsec + (ms * 1000000); +} + +static int wait_for_thread(pthread_t thread, unsigned int ms) +{ + struct timespec timeout; + + clock_gettime(CLOCK_REALTIME, &timeout); + timeout.tv_nsec += ms * 1000000; + timeout.tv_sec += (timeout.tv_nsec / 1000000000); + timeout.tv_nsec %= 1000000000; + return pthread_timedjoin_np(thread, NULL, &timeout); +} + +TEST(wake_any) +{ + struct ntsync_event_args event_args = {0}; + struct ntsync_mutex_args mutex_args = {0}; + struct ntsync_wait_args wait_args = {0}; + struct ntsync_sem_args sem_args = {0}; + struct wait_args thread_args; + __u32 count, index, signaled; + int objs[2], fd, ret; + pthread_t thread; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 0; + sem_args.max = 3; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + mutex_args.owner = 123; + mutex_args.count = 1; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, objs[1]); + + /* test waking the semaphore */ + + wait_args.timeout = get_abs_timeout(1000); + wait_args.objs = (uintptr_t)objs; + wait_args.count = 2; + wait_args.owner = 456; + wait_args.index = 0xdeadbeef; + thread_args.fd = fd; + thread_args.args = &wait_args; + thread_args.request = NTSYNC_IOC_WAIT_ANY; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + count = 1; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + check_sem_state(objs[0], 0, 3); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(0, wait_args.index); + + /* test waking the mutex */ + + /* first grab it again for owner 123 */ + ret = wait_any(fd, 1, &objs[1], 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + wait_args.timeout = get_abs_timeout(1000); + wait_args.owner = 456; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = unlock_mutex(objs[1], 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, count); + + ret = pthread_tryjoin_np(thread, NULL); + EXPECT_EQ(EBUSY, ret); + + ret = unlock_mutex(objs[1], 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, mutex_args.count); + check_mutex_state(objs[1], 1, 456); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + close(objs[1]); + + /* test waking events */ + + event_args.manual = false; + event_args.signaled = false; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, objs[1]); + + wait_args.timeout = get_abs_timeout(1000); + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(objs[1], 0, 0); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + wait_args.timeout = get_abs_timeout(1000); + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(objs[1], 0, 0); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + close(objs[1]); + + event_args.manual = true; + event_args.signaled = false; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, objs[1]); + + wait_args.timeout = get_abs_timeout(1000); + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(objs[1], 1, 1); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + + wait_args.timeout = get_abs_timeout(1000); + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(objs[1], 0, 1); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + /* delete an object while it's being waited on */ + + wait_args.timeout = get_abs_timeout(200); + wait_args.owner = 123; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + close(objs[0]); + close(objs[1]); + + ret = wait_for_thread(thread, 200); + EXPECT_EQ(0, ret); + EXPECT_EQ(-1, thread_args.ret); + EXPECT_EQ(ETIMEDOUT, thread_args.err); + + close(fd); +} + +TEST(wake_all) +{ + struct ntsync_event_args manual_event_args = {0}; + struct ntsync_event_args auto_event_args = {0}; + struct ntsync_mutex_args mutex_args = {0}; + struct ntsync_wait_args wait_args = {0}; + struct ntsync_sem_args sem_args = {0}; + struct wait_args thread_args; + __u32 count, index, signaled; + int objs[4], fd, ret; + pthread_t thread; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 0; + sem_args.max = 3; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + mutex_args.owner = 123; + mutex_args.count = 1; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, objs[1]); + + manual_event_args.manual = true; + manual_event_args.signaled = true; + objs[2] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &manual_event_args); + EXPECT_LE(0, objs[2]); + + auto_event_args.manual = false; + auto_event_args.signaled = true; + objs[3] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &auto_event_args); + EXPECT_EQ(0, objs[3]); + + wait_args.timeout = get_abs_timeout(1000); + wait_args.objs = (uintptr_t)objs; + wait_args.count = 4; + wait_args.owner = 456; + thread_args.fd = fd; + thread_args.args = &wait_args; + thread_args.request = NTSYNC_IOC_WAIT_ALL; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + count = 1; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + + ret = pthread_tryjoin_np(thread, NULL); + EXPECT_EQ(EBUSY, ret); + + check_sem_state(objs[0], 1, 3); + + ret = wait_any(fd, 1, &objs[0], 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = unlock_mutex(objs[1], 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, count); + + ret = pthread_tryjoin_np(thread, NULL); + EXPECT_EQ(EBUSY, ret); + + check_mutex_state(objs[1], 0, 0); + + ret = ioctl(objs[2], NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + + count = 2; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + check_sem_state(objs[0], 2, 3); + + ret = ioctl(objs[3], NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + + ret = ioctl(objs[2], NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + + ret = ioctl(objs[3], NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 1, 456); + check_event_state(objs[2], 1, 1); + check_event_state(objs[3], 0, 0); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + + /* delete an object while it's being waited on */ + + wait_args.timeout = get_abs_timeout(200); + wait_args.owner = 123; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + close(objs[0]); + close(objs[1]); + close(objs[2]); + close(objs[3]); + + ret = wait_for_thread(thread, 200); + EXPECT_EQ(0, ret); + EXPECT_EQ(-1, thread_args.ret); + EXPECT_EQ(ETIMEDOUT, thread_args.err); + + close(fd); +} + +TEST(alert_any) +{ + struct ntsync_event_args event_args = {0}; + struct ntsync_wait_args wait_args = {0}; + struct ntsync_sem_args sem_args = {0}; + __u32 index, count, signaled; + struct wait_args thread_args; + int objs[2], event, fd, ret; + pthread_t thread; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 0; + sem_args.max = 2; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + sem_args.count = 1; + sem_args.max = 2; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[1]); + + event_args.manual = true; + event_args.signaled = true; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + ret = wait_any_alert(fd, 0, NULL, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + + ret = wait_any_alert(fd, 0, NULL, 123, event, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, index); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, index); + + /* test wakeup via alert */ + + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + + wait_args.timeout = get_abs_timeout(1000); + wait_args.objs = (uintptr_t)objs; + wait_args.count = 2; + wait_args.owner = 123; + wait_args.index = 0xdeadbeef; + wait_args.alert = event; + thread_args.fd = fd; + thread_args.args = &wait_args; + thread_args.request = NTSYNC_IOC_WAIT_ANY; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(2, wait_args.index); + + close(event); + + /* test with an auto-reset event */ + + event_args.manual = false; + event_args.signaled = true; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + count = 1; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, index); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + close(event); + + close(objs[0]); + close(objs[1]); + + close(fd); +} + +TEST(alert_all) +{ + struct ntsync_event_args event_args = {0}; + struct ntsync_wait_args wait_args = {0}; + struct ntsync_sem_args sem_args = {0}; + struct wait_args thread_args; + __u32 index, count, signaled; + int objs[2], event, fd, ret; + pthread_t thread; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 2; + sem_args.max = 2; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + sem_args.count = 1; + sem_args.max = 2; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[1]); + + event_args.manual = true; + event_args.signaled = true; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, index); + + /* test wakeup via alert */ + + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + + wait_args.timeout = get_abs_timeout(1000); + wait_args.objs = (uintptr_t)objs; + wait_args.count = 2; + wait_args.owner = 123; + wait_args.index = 0xdeadbeef; + wait_args.alert = event; + thread_args.fd = fd; + thread_args.args = &wait_args; + thread_args.request = NTSYNC_IOC_WAIT_ALL; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(2, wait_args.index); + + close(event); + + /* test with an auto-reset event */ + + event_args.manual = false; + event_args.signaled = true; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + count = 2; + ret = release_sem(objs[1], &count); + EXPECT_EQ(0, ret); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, index); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + close(event); + + close(objs[0]); + close(objs[1]); + + close(fd); +} + +#define STRESS_LOOPS 10000 +#define STRESS_THREADS 4 + +static unsigned int stress_counter; +static int stress_device, stress_start_event, stress_mutex; + +static void *stress_thread(void *arg) +{ + struct ntsync_wait_args wait_args = {0}; + __u32 index, count, i; + int ret; + + wait_args.timeout = UINT64_MAX; + wait_args.count = 1; + wait_args.objs = (uintptr_t)&stress_start_event; + wait_args.owner = gettid(); + wait_args.index = 0xdeadbeef; + + ioctl(stress_device, NTSYNC_IOC_WAIT_ANY, &wait_args); + + wait_args.objs = (uintptr_t)&stress_mutex; + + for (i = 0; i < STRESS_LOOPS; ++i) { + ioctl(stress_device, NTSYNC_IOC_WAIT_ANY, &wait_args); + + ++stress_counter; + + unlock_mutex(stress_mutex, wait_args.owner, &count); + } + + return NULL; +} + +TEST(stress_wait) +{ + struct ntsync_event_args event_args; + struct ntsync_mutex_args mutex_args; + pthread_t threads[STRESS_THREADS]; + __u32 signaled, i; + int ret; + + stress_device = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, stress_device); + + mutex_args.owner = 0; + mutex_args.count = 0; + stress_mutex = ioctl(stress_device, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, stress_mutex); + + event_args.manual = 1; + event_args.signaled = 0; + stress_start_event = ioctl(stress_device, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, stress_start_event); + + for (i = 0; i < STRESS_THREADS; ++i) + pthread_create(&threads[i], NULL, stress_thread, NULL); + + ret = ioctl(stress_start_event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + + for (i = 0; i < STRESS_THREADS; ++i) { + ret = pthread_join(threads[i], NULL); + EXPECT_EQ(0, ret); + } + + EXPECT_EQ(STRESS_LOOPS * STRESS_THREADS, stress_counter); + + close(stress_start_event); + close(stress_mutex); + close(stress_device); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh index d374878cc0ba..c62544b966ae 100755 --- a/tools/testing/selftests/efivarfs/efivarfs.sh +++ b/tools/testing/selftests/efivarfs/efivarfs.sh @@ -76,11 +76,11 @@ test_create_empty() : > $file - if [ ! -e $file ]; then - echo "$file can not be created without writing" >&2 + if [ -e $file ]; then + echo "$file can be created without writing" >&2 + file_cleanup $file exit 1 fi - file_cleanup $file } test_create_read() @@ -89,10 +89,13 @@ test_create_read() ./create-read $file if [ $? -ne 0 ]; then echo "create and read $file failed" + exit 1 + fi + if [ -e $file ]; then + echo "file still exists and should not" file_cleanup $file exit 1 fi - file_cleanup $file } test_delete() @@ -202,6 +205,158 @@ test_invalid_filenames() exit $ret } +test_no_set_size() +{ + local attrs='\x07\x00\x00\x00' + local file=$efivarfs_mount/$FUNCNAME-$test_guid + local ret=0 + + printf "$attrs\x00" > $file + [ -e $file -a -s $file ] || exit 1 + chattr -i $file + : > $file + if [ $? != 0 ]; then + echo "variable file failed to accept truncation" + ret=1 + elif [ -e $file -a ! -s $file ]; then + echo "file can be truncated to zero size" + ret=1 + fi + rm $file || exit 1 + + exit $ret +} + +setup_test_multiple() +{ + ## + # we're going to do multi-threaded tests, so create a set of + # pipes for synchronization. We use pipes 1..3 to start the + # stalled shell job and pipes 4..6 as indicators that the job + # has started. If you need more than 3 jobs the two +3's below + # need increasing + ## + + declare -ag p + + # empty is because arrays number from 0 but jobs number from 1 + p[0]="" + + for f in 1 2 3 4 5 6; do + p[$f]=/tmp/efivarfs_pipe${f} + mknod ${p[$f]} p + done + + declare -g var=$efivarfs_mount/test_multiple-$test_guid + + cleanup() { + for f in ${p[@]}; do + rm -f ${f} + done + if [ -e $var ]; then + file_cleanup $var + fi + } + trap cleanup exit + + waitstart() { + cat ${p[$[$1+3]]} > /dev/null + } + + waitpipe() { + echo 1 > ${p[$[$1+3]]} + cat ${p[$1]} > /dev/null + } + + endjob() { + echo 1 > ${p[$1]} + wait -n %$1 + } +} + +test_multiple_zero_size() +{ + ## + # check for remove on last close, set up three threads all + # holding the variable (one write and two reads) and then + # close them sequentially (waiting for completion) and check + # the state of the variable + ## + + { waitpipe 1; echo 1; } > $var 2> /dev/null & + waitstart 1 + # zero length file should exist + [ -e $var ] || exit 1 + # second and third delayed close + { waitpipe 2; } < $var & + waitstart 2 + { waitpipe 3; } < $var & + waitstart 3 + # close first fd + endjob 1 + # var should only be deleted on last close + [ -e $var ] || exit 1 + # close second fd + endjob 2 + [ -e $var ] || exit 1 + # file should go on last close + endjob 3 + [ ! -e $var ] || exit 1 +} + +test_multiple_create() +{ + ## + # set multiple threads to access the variable but delay + # the final write to check the close of 2 and 3. The + # final write should succeed in creating the variable + ## + { waitpipe 1; printf '\x07\x00\x00\x00\x54'; } > $var & + waitstart 1 + [ -e $var -a ! -s $var ] || exit 1 + { waitpipe 2; } < $var & + waitstart 2 + { waitpipe 3; } < $var & + waitstart 3 + # close second and third fds + endjob 2 + # var should only be created (have size) on last close + [ -e $var -a ! -s $var ] || exit 1 + endjob 3 + [ -e $var -a ! -s $var ] || exit 1 + # close first fd + endjob 1 + # variable should still exist + [ -s $var ] || exit 1 + file_cleanup $var +} + +test_multiple_delete_on_write() { + ## + # delete the variable on final write; seqencing similar + # to test_multiple_create() + ## + printf '\x07\x00\x00\x00\x54' > $var + chattr -i $var + { waitpipe 1; printf '\x07\x00\x00\x00'; } > $var & + waitstart 1 + [ -e $var -a -s $var ] || exit 1 + { waitpipe 2; } < $var & + waitstart 2 + { waitpipe 3; } < $var & + waitstart 3 + # close first fd; write should set variable size to zero + endjob 1 + # var should only be deleted on last close + [ -e $var -a ! -s $var ] || exit 1 + endjob 2 + [ -e $var ] || exit 1 + # close last fd + endjob 3 + # variable should now be removed + [ ! -e $var ] || exit 1 +} + check_prereqs rc=0 @@ -214,5 +369,10 @@ run_test test_zero_size_delete run_test test_open_unlink run_test test_valid_filenames run_test test_invalid_filenames +run_test test_no_set_size +setup_test_multiple +run_test test_multiple_zero_size +run_test test_multiple_create +run_test test_multiple_delete_on_write exit $rc diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore index a0dc5d4bf733..7f3d1ae762ec 100644 --- a/tools/testing/selftests/exec/.gitignore +++ b/tools/testing/selftests/exec/.gitignore @@ -9,9 +9,13 @@ execveat.ephemeral execveat.denatured non-regular null-argv +/check-exec +/false +/inc /load_address.* !load_address.c /recursion-depth +/set-exec xxxxxxxx* pipe S_I*.test diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index ba012bc5aab9..45a3cfc435cf 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -1,26 +1,33 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS = -Wall CFLAGS += -Wno-nonnull +CFLAGS += $(KHDR_INCLUDES) + +LDLIBS += -lcap ALIGNS := 0x1000 0x200000 0x1000000 ALIGN_PIES := $(patsubst %,load_address.%,$(ALIGNS)) ALIGN_STATIC_PIES := $(patsubst %,load_address.static.%,$(ALIGNS)) ALIGNMENT_TESTS := $(ALIGN_PIES) $(ALIGN_STATIC_PIES) -TEST_PROGS := binfmt_script.py +TEST_PROGS := binfmt_script.py check-exec-tests.sh TEST_GEN_PROGS := execveat non-regular $(ALIGNMENT_TESTS) +TEST_GEN_PROGS_EXTENDED := false inc set-exec script-exec.inc script-noexec.inc TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir # Makefile is a run-time dependency, since it's accessed by the execveat test TEST_FILES := Makefile TEST_GEN_PROGS += recursion-depth TEST_GEN_PROGS += null-argv +TEST_GEN_PROGS += check-exec EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx* \ $(OUTPUT)/S_I*.test include ../lib.mk +CHECK_EXEC_SAMPLES := $(top_srcdir)/samples/check-exec + $(OUTPUT)/subdir: mkdir -p $@ $(OUTPUT)/script: Makefile @@ -38,3 +45,13 @@ $(OUTPUT)/load_address.0x%: load_address.c $(OUTPUT)/load_address.static.0x%: load_address.c $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=$(lastword $(subst ., ,$@)) \ -fPIE -static-pie $< -o $@ +$(OUTPUT)/false: false.c + $(CC) $(CFLAGS) $(LDFLAGS) -static $< -o $@ +$(OUTPUT)/inc: $(CHECK_EXEC_SAMPLES)/inc.c + $(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ +$(OUTPUT)/set-exec: $(CHECK_EXEC_SAMPLES)/set-exec.c + $(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ +$(OUTPUT)/script-exec.inc: $(CHECK_EXEC_SAMPLES)/script-exec.inc + cp $< $@ +$(OUTPUT)/script-noexec.inc: $(CHECK_EXEC_SAMPLES)/script-noexec.inc + cp $< $@ diff --git a/tools/testing/selftests/exec/check-exec-tests.sh b/tools/testing/selftests/exec/check-exec-tests.sh new file mode 100755 index 000000000000..87102906ae3c --- /dev/null +++ b/tools/testing/selftests/exec/check-exec-tests.sh @@ -0,0 +1,205 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test the "inc" interpreter. +# +# See include/uapi/linux/securebits.h, include/uapi/linux/fcntl.h and +# samples/check-exec/inc.c +# +# Copyright © 2024 Microsoft Corporation + +set -u -e -o pipefail + +EXPECTED_OUTPUT="1" +exec 2>/dev/null + +DIR="$(dirname $(readlink -f "$0"))" +source "${DIR}"/../kselftest/ktap_helpers.sh + +exec_direct() { + local expect="$1" + local script="$2" + shift 2 + local ret=0 + local out + + # Updates PATH for `env` to execute the `inc` interpreter. + out="$(PATH="." "$@" "${script}")" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for direct file execution: ${ret}" + return 1 + fi + if [[ ${ret} -eq 0 && "${out}" != "${EXPECTED_OUTPUT}" ]]; then + echo "ERROR: Wrong output for direct file execution: ${out}" + return 1 + fi +} + +exec_indirect() { + local expect="$1" + local script="$2" + shift 2 + local ret=0 + local out + + # Script passed as argument. + out="$("$@" ./inc "${script}")" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for indirect file execution: ${ret}" + return 1 + fi + if [[ ${ret} -eq 0 && "${out}" != "${EXPECTED_OUTPUT}" ]]; then + echo "ERROR: Wrong output for indirect file execution: ${out}" + return 1 + fi +} + +exec_stdin_reg() { + local expect="$1" + local script="$2" + shift 2 + local ret=0 + local out + + # Executing stdin must be allowed if the related file is executable. + out="$("$@" ./inc -i < "${script}")" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for stdin regular file execution: ${ret}" + return 1 + fi + if [[ ${ret} -eq 0 && "${out}" != "${EXPECTED_OUTPUT}" ]]; then + echo "ERROR: Wrong output for stdin regular file execution: ${out}" + return 1 + fi +} + +exec_stdin_pipe() { + local expect="$1" + shift + local ret=0 + local out + + # A pipe is not executable. + out="$(cat script-exec.inc | "$@" ./inc -i)" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for stdin pipe execution: ${ret}" + return 1 + fi +} + +exec_argument() { + local expect="$1" + local ret=0 + shift + local out + + # Script not coming from a file must not be executed. + out="$("$@" ./inc -c "$(< script-exec.inc)")" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for arbitrary argument execution: ${ret}" + return 1 + fi + if [[ ${ret} -eq 0 && "${out}" != "${EXPECTED_OUTPUT}" ]]; then + echo "ERROR: Wrong output for arbitrary argument execution: ${out}" + return 1 + fi +} + +exec_interactive() { + exec_stdin_pipe "$@" + exec_argument "$@" +} + +ktap_test() { + ktap_test_result "$*" "$@" +} + +ktap_print_header +ktap_set_plan 28 + +# Without secbit configuration, nothing is changed. + +ktap_print_msg "By default, executable scripts are allowed to be interpreted and executed." +ktap_test exec_direct 0 script-exec.inc +ktap_test exec_indirect 0 script-exec.inc + +ktap_print_msg "By default, executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-exec.inc + +ktap_print_msg "By default, non-executable scripts are allowed to be interpreted, but not directly executed." +# We get 126 because of direct execution by Bash. +ktap_test exec_direct 126 script-noexec.inc +ktap_test exec_indirect 0 script-noexec.inc + +ktap_print_msg "By default, non-executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-noexec.inc + +ktap_print_msg "By default, interactive commands are allowed to be interpreted." +ktap_test exec_interactive 0 + +# With only file restriction: protect non-malicious users from inadvertent errors (e.g. python ~/Downloads/*.py). + +ktap_print_msg "With -f, executable scripts are allowed to be interpreted and executed." +ktap_test exec_direct 0 script-exec.inc ./set-exec -f -- +ktap_test exec_indirect 0 script-exec.inc ./set-exec -f -- + +ktap_print_msg "With -f, executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-exec.inc ./set-exec -f -- + +ktap_print_msg "With -f, non-executable scripts are not allowed to be executed nor interpreted." +# Direct execution of non-executable script is alwayse denied by the kernel. +ktap_test exec_direct 1 script-noexec.inc ./set-exec -f -- +ktap_test exec_indirect 1 script-noexec.inc ./set-exec -f -- + +ktap_print_msg "With -f, non-executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-noexec.inc ./set-exec -f -- + +ktap_print_msg "With -f, interactive commands are allowed to be interpreted." +ktap_test exec_interactive 0 ./set-exec -f -- + +# With only denied interactive commands: check or monitor script content (e.g. with LSM). + +ktap_print_msg "With -i, executable scripts are allowed to be interpreted and executed." +ktap_test exec_direct 0 script-exec.inc ./set-exec -i -- +ktap_test exec_indirect 0 script-exec.inc ./set-exec -i -- + +ktap_print_msg "With -i, executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-exec.inc ./set-exec -i -- + +ktap_print_msg "With -i, non-executable scripts are allowed to be interpreted, but not directly executed." +# Direct execution of non-executable script is alwayse denied by the kernel. +ktap_test exec_direct 1 script-noexec.inc ./set-exec -i -- +ktap_test exec_indirect 0 script-noexec.inc ./set-exec -i -- + +ktap_print_msg "With -i, non-executable stdin is not allowed to be interpreted." +ktap_test exec_stdin_reg 1 script-noexec.inc ./set-exec -i -- + +ktap_print_msg "With -i, interactive commands are not allowed to be interpreted." +ktap_test exec_interactive 1 ./set-exec -i -- + +# With both file restriction and denied interactive commands: only allow executable scripts. + +ktap_print_msg "With -fi, executable scripts are allowed to be interpreted and executed." +ktap_test exec_direct 0 script-exec.inc ./set-exec -fi -- +ktap_test exec_indirect 0 script-exec.inc ./set-exec -fi -- + +ktap_print_msg "With -fi, executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-exec.inc ./set-exec -fi -- + +ktap_print_msg "With -fi, non-executable scripts are not allowed to be interpreted nor executed." +# Direct execution of non-executable script is alwayse denied by the kernel. +ktap_test exec_direct 1 script-noexec.inc ./set-exec -fi -- +ktap_test exec_indirect 1 script-noexec.inc ./set-exec -fi -- + +ktap_print_msg "With -fi, non-executable stdin is not allowed to be interpreted." +ktap_test exec_stdin_reg 1 script-noexec.inc ./set-exec -fi -- + +ktap_print_msg "With -fi, interactive commands are not allowed to be interpreted." +ktap_test exec_interactive 1 ./set-exec -fi -- + +ktap_finished diff --git a/tools/testing/selftests/exec/check-exec.c b/tools/testing/selftests/exec/check-exec.c new file mode 100644 index 000000000000..55bce47e56b7 --- /dev/null +++ b/tools/testing/selftests/exec/check-exec.c @@ -0,0 +1,463 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test execveat(2) with AT_EXECVE_CHECK, and prctl(2) with + * SECBIT_EXEC_RESTRICT_FILE, SECBIT_EXEC_DENY_INTERACTIVE, and their locked + * counterparts. + * + * Copyright © 2018-2020 ANSSI + * Copyright © 2024 Microsoft Corporation + * + * Author: Mickaël Salaün <mic@digikod.net> + */ + +#include <asm-generic/unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/prctl.h> +#include <linux/securebits.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/capability.h> +#include <sys/mount.h> +#include <sys/prctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/sysmacros.h> +#include <unistd.h> + +/* Defines AT_EXECVE_CHECK without type conflicts. */ +#define _ASM_GENERIC_FCNTL_H +#include <linux/fcntl.h> + +#include "../kselftest_harness.h" + +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + +static void drop_privileges(struct __test_metadata *const _metadata) +{ + const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED; + cap_t cap_p; + + if ((cap_get_secbits() & noroot) != noroot) + EXPECT_EQ(0, cap_set_secbits(noroot)); + + cap_p = cap_get_proc(); + EXPECT_NE(NULL, cap_p); + EXPECT_NE(-1, cap_clear(cap_p)); + + /* + * Drops everything, especially CAP_SETPCAP, CAP_DAC_OVERRIDE, and + * CAP_DAC_READ_SEARCH. + */ + EXPECT_NE(-1, cap_set_proc(cap_p)); + EXPECT_NE(-1, cap_free(cap_p)); +} + +static int test_secbits_set(const unsigned int secbits) +{ + int err; + + err = prctl(PR_SET_SECUREBITS, secbits); + if (err) + return errno; + return 0; +} + +FIXTURE(access) +{ + int memfd, pipefd; + int pipe_fds[2], socket_fds[2]; +}; + +FIXTURE_VARIANT(access) +{ + const bool mount_exec; + const bool file_exec; +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(access, mount_exec_file_exec) { + /* clang-format on */ + .mount_exec = true, + .file_exec = true, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(access, mount_exec_file_noexec) { + /* clang-format on */ + .mount_exec = true, + .file_exec = false, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(access, mount_noexec_file_exec) { + /* clang-format on */ + .mount_exec = false, + .file_exec = true, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(access, mount_noexec_file_noexec) { + /* clang-format on */ + .mount_exec = false, + .file_exec = false, +}; + +static const char binary_path[] = "./false"; +static const char workdir_path[] = "./test-mount"; +static const char reg_file_path[] = "./test-mount/regular_file"; +static const char dir_path[] = "./test-mount/directory"; +static const char block_dev_path[] = "./test-mount/block_device"; +static const char char_dev_path[] = "./test-mount/character_device"; +static const char fifo_path[] = "./test-mount/fifo"; + +FIXTURE_SETUP(access) +{ + int procfd_path_size; + static const char path_template[] = "/proc/self/fd/%d"; + char procfd_path[sizeof(path_template) + 10]; + + /* Makes sure we are not already restricted nor locked. */ + EXPECT_EQ(0, test_secbits_set(0)); + + /* + * Cleans previous workspace if any error previously happened (don't + * check errors). + */ + umount(workdir_path); + rmdir(workdir_path); + + /* Creates a clean mount point. */ + ASSERT_EQ(0, mkdir(workdir_path, 00700)); + ASSERT_EQ(0, mount("test", workdir_path, "tmpfs", + MS_MGC_VAL | (variant->mount_exec ? 0 : MS_NOEXEC), + "mode=0700,size=9m")); + + /* Creates a regular file. */ + ASSERT_EQ(0, mknod(reg_file_path, + S_IFREG | (variant->file_exec ? 0700 : 0600), 0)); + /* Creates a directory. */ + ASSERT_EQ(0, mkdir(dir_path, variant->file_exec ? 0700 : 0600)); + /* Creates a character device: /dev/null. */ + ASSERT_EQ(0, mknod(char_dev_path, S_IFCHR | 0400, makedev(1, 3))); + /* Creates a block device: /dev/loop0 */ + ASSERT_EQ(0, mknod(block_dev_path, S_IFBLK | 0400, makedev(7, 0))); + /* Creates a fifo. */ + ASSERT_EQ(0, mknod(fifo_path, S_IFIFO | 0600, 0)); + + /* Creates a regular file without user mount point. */ + self->memfd = memfd_create("test-exec-probe", MFD_CLOEXEC); + ASSERT_LE(0, self->memfd); + /* Sets mode, which must be ignored by the exec check. */ + ASSERT_EQ(0, fchmod(self->memfd, variant->file_exec ? 0700 : 0600)); + + /* Creates a pipefs file descriptor. */ + ASSERT_EQ(0, pipe(self->pipe_fds)); + procfd_path_size = snprintf(procfd_path, sizeof(procfd_path), + path_template, self->pipe_fds[0]); + ASSERT_LT(procfd_path_size, sizeof(procfd_path)); + self->pipefd = open(procfd_path, O_RDWR | O_CLOEXEC); + ASSERT_LE(0, self->pipefd); + ASSERT_EQ(0, fchmod(self->pipefd, variant->file_exec ? 0700 : 0600)); + + /* Creates a socket file descriptor. */ + ASSERT_EQ(0, socketpair(AF_UNIX, SOCK_DGRAM | SOCK_CLOEXEC, 0, + self->socket_fds)); +} + +FIXTURE_TEARDOWN_PARENT(access) +{ + /* There is no need to unlink the test files. */ + EXPECT_EQ(0, umount(workdir_path)); + EXPECT_EQ(0, rmdir(workdir_path)); +} + +static void fill_exec_fd(struct __test_metadata *_metadata, const int fd_out) +{ + char buf[1024]; + size_t len; + int fd_in; + + fd_in = open(binary_path, O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd_in); + /* Cannot use copy_file_range(2) because of EXDEV. */ + len = read(fd_in, buf, sizeof(buf)); + EXPECT_LE(0, len); + while (len > 0) { + EXPECT_EQ(len, write(fd_out, buf, len)) + { + TH_LOG("Failed to write: %s (%d)", strerror(errno), + errno); + } + len = read(fd_in, buf, sizeof(buf)); + EXPECT_LE(0, len); + } + EXPECT_EQ(0, close(fd_in)); +} + +static void fill_exec_path(struct __test_metadata *_metadata, + const char *const path) +{ + int fd_out; + + fd_out = open(path, O_CLOEXEC | O_WRONLY); + ASSERT_LE(0, fd_out) + { + TH_LOG("Failed to open %s: %s", path, strerror(errno)); + } + fill_exec_fd(_metadata, fd_out); + EXPECT_EQ(0, close(fd_out)); +} + +static void test_exec_fd(struct __test_metadata *_metadata, const int fd, + const int err_code) +{ + char *const argv[] = { "", NULL }; + int access_ret, access_errno; + + /* + * If we really execute fd, filled with the "false" binary, the current + * thread will exits with an error, which will be interpreted by the + * test framework as an error. With AT_EXECVE_CHECK, we only check a + * potential successful execution. + */ + access_ret = sys_execveat(fd, "", argv, NULL, + AT_EMPTY_PATH | AT_EXECVE_CHECK); + access_errno = errno; + if (err_code) { + EXPECT_EQ(-1, access_ret); + EXPECT_EQ(err_code, access_errno) + { + TH_LOG("Wrong error for execveat(2): %s (%d)", + strerror(access_errno), errno); + } + } else { + EXPECT_EQ(0, access_ret) + { + TH_LOG("Access denied: %s", strerror(access_errno)); + } + } +} + +static void test_exec_path(struct __test_metadata *_metadata, + const char *const path, const int err_code) +{ + int flags = O_CLOEXEC; + int fd; + + /* Do not block on pipes. */ + if (path == fifo_path) + flags |= O_NONBLOCK; + + fd = open(path, flags | O_RDONLY); + ASSERT_LE(0, fd) + { + TH_LOG("Failed to open %s: %s", path, strerror(errno)); + } + test_exec_fd(_metadata, fd, err_code); + EXPECT_EQ(0, close(fd)); +} + +/* Tests that we don't get ENOEXEC. */ +TEST_F(access, regular_file_empty) +{ + const int exec = variant->mount_exec && variant->file_exec; + + test_exec_path(_metadata, reg_file_path, exec ? 0 : EACCES); + + drop_privileges(_metadata); + test_exec_path(_metadata, reg_file_path, exec ? 0 : EACCES); +} + +TEST_F(access, regular_file_elf) +{ + const int exec = variant->mount_exec && variant->file_exec; + + fill_exec_path(_metadata, reg_file_path); + + test_exec_path(_metadata, reg_file_path, exec ? 0 : EACCES); + + drop_privileges(_metadata); + test_exec_path(_metadata, reg_file_path, exec ? 0 : EACCES); +} + +/* Tests that we don't get ENOEXEC. */ +TEST_F(access, memfd_empty) +{ + const int exec = variant->file_exec; + + test_exec_fd(_metadata, self->memfd, exec ? 0 : EACCES); + + drop_privileges(_metadata); + test_exec_fd(_metadata, self->memfd, exec ? 0 : EACCES); +} + +TEST_F(access, memfd_elf) +{ + const int exec = variant->file_exec; + + fill_exec_fd(_metadata, self->memfd); + + test_exec_fd(_metadata, self->memfd, exec ? 0 : EACCES); + + drop_privileges(_metadata); + test_exec_fd(_metadata, self->memfd, exec ? 0 : EACCES); +} + +TEST_F(access, non_regular_files) +{ + test_exec_path(_metadata, dir_path, EACCES); + test_exec_path(_metadata, block_dev_path, EACCES); + test_exec_path(_metadata, char_dev_path, EACCES); + test_exec_path(_metadata, fifo_path, EACCES); + test_exec_fd(_metadata, self->socket_fds[0], EACCES); + test_exec_fd(_metadata, self->pipefd, EACCES); +} + +/* clang-format off */ +FIXTURE(secbits) {}; +/* clang-format on */ + +FIXTURE_VARIANT(secbits) +{ + const bool is_privileged; + const int error; +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(secbits, priv) { + /* clang-format on */ + .is_privileged = true, + .error = 0, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(secbits, unpriv) { + /* clang-format on */ + .is_privileged = false, + .error = EPERM, +}; + +FIXTURE_SETUP(secbits) +{ + /* Makes sure no exec bits are set. */ + EXPECT_EQ(0, test_secbits_set(0)); + EXPECT_EQ(0, prctl(PR_GET_SECUREBITS)); + + if (!variant->is_privileged) + drop_privileges(_metadata); +} + +FIXTURE_TEARDOWN(secbits) +{ +} + +TEST_F(secbits, legacy) +{ + EXPECT_EQ(variant->error, test_secbits_set(0)); +} + +#define CHILD(...) \ + do { \ + pid_t child = vfork(); \ + EXPECT_LE(0, child); \ + if (child == 0) { \ + __VA_ARGS__; \ + _exit(0); \ + } \ + } while (0) + +TEST_F(secbits, exec) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_RESTRICT_FILE; + EXPECT_EQ(0, test_secbits_set(secbits)); + EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS)); + CHILD(EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS))); + + secbits |= SECBIT_EXEC_DENY_INTERACTIVE; + EXPECT_EQ(0, test_secbits_set(secbits)); + EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS)); + CHILD(EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS))); + + secbits &= ~(SECBIT_EXEC_RESTRICT_FILE | SECBIT_EXEC_DENY_INTERACTIVE); + EXPECT_EQ(0, test_secbits_set(secbits)); + EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS)); + CHILD(EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS))); +} + +TEST_F(secbits, check_locked_set) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_RESTRICT_FILE; + EXPECT_EQ(0, test_secbits_set(secbits)); + secbits |= SECBIT_EXEC_RESTRICT_FILE_LOCKED; + EXPECT_EQ(0, test_secbits_set(secbits)); + + /* Checks lock set but unchanged. */ + EXPECT_EQ(variant->error, test_secbits_set(secbits)); + CHILD(EXPECT_EQ(variant->error, test_secbits_set(secbits))); + + secbits &= ~SECBIT_EXEC_RESTRICT_FILE; + EXPECT_EQ(EPERM, test_secbits_set(0)); + CHILD(EXPECT_EQ(EPERM, test_secbits_set(0))); +} + +TEST_F(secbits, check_locked_unset) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_RESTRICT_FILE_LOCKED; + EXPECT_EQ(0, test_secbits_set(secbits)); + + /* Checks lock unset but unchanged. */ + EXPECT_EQ(variant->error, test_secbits_set(secbits)); + CHILD(EXPECT_EQ(variant->error, test_secbits_set(secbits))); + + secbits &= ~SECBIT_EXEC_RESTRICT_FILE; + EXPECT_EQ(EPERM, test_secbits_set(0)); + CHILD(EXPECT_EQ(EPERM, test_secbits_set(0))); +} + +TEST_F(secbits, restrict_locked_set) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_DENY_INTERACTIVE; + EXPECT_EQ(0, test_secbits_set(secbits)); + secbits |= SECBIT_EXEC_DENY_INTERACTIVE_LOCKED; + EXPECT_EQ(0, test_secbits_set(secbits)); + + /* Checks lock set but unchanged. */ + EXPECT_EQ(variant->error, test_secbits_set(secbits)); + CHILD(EXPECT_EQ(variant->error, test_secbits_set(secbits))); + + secbits &= ~SECBIT_EXEC_DENY_INTERACTIVE; + EXPECT_EQ(EPERM, test_secbits_set(0)); + CHILD(EXPECT_EQ(EPERM, test_secbits_set(0))); +} + +TEST_F(secbits, restrict_locked_unset) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_DENY_INTERACTIVE_LOCKED; + EXPECT_EQ(0, test_secbits_set(secbits)); + + /* Checks lock unset but unchanged. */ + EXPECT_EQ(variant->error, test_secbits_set(secbits)); + CHILD(EXPECT_EQ(variant->error, test_secbits_set(secbits))); + + secbits &= ~SECBIT_EXEC_DENY_INTERACTIVE; + EXPECT_EQ(EPERM, test_secbits_set(0)); + CHILD(EXPECT_EQ(EPERM, test_secbits_set(0))); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/exec/config b/tools/testing/selftests/exec/config new file mode 100644 index 000000000000..c308079867b3 --- /dev/null +++ b/tools/testing/selftests/exec/config @@ -0,0 +1,2 @@ +CONFIG_BLK_DEV=y +CONFIG_BLK_DEV_LOOP=y diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c index 071e03532cba..8fb7395fd35b 100644 --- a/tools/testing/selftests/exec/execveat.c +++ b/tools/testing/selftests/exec/execveat.c @@ -23,9 +23,11 @@ #include "../kselftest.h" -#define TESTS_EXPECTED 51 +#define TESTS_EXPECTED 54 #define TEST_NAME_LEN (PATH_MAX * 4) +#define CHECK_COMM "CHECK_COMM" + static char longpath[2 * PATH_MAX] = ""; static char *envp[] = { "IN_TEST=yes", NULL, NULL }; static char *argv[] = { "execveat", "99", NULL }; @@ -237,6 +239,29 @@ static int check_execveat_pathmax(int root_dfd, const char *src, int is_script) return fail; } +static int check_execveat_comm(int fd, char *argv0, char *expected) +{ + char buf[128], *old_env, *old_argv0; + int ret; + + snprintf(buf, sizeof(buf), CHECK_COMM "=%s", expected); + + old_env = envp[1]; + envp[1] = buf; + + old_argv0 = argv[0]; + argv[0] = argv0; + + ksft_print_msg("Check execveat(AT_EMPTY_PATH)'s comm is %s\n", + expected); + ret = check_execveat_invoked_rc(fd, "", AT_EMPTY_PATH, 0, 0); + + envp[1] = old_env; + argv[0] = old_argv0; + + return ret; +} + static int run_tests(void) { int fail = 0; @@ -389,6 +414,14 @@ static int run_tests(void) fail += check_execveat_pathmax(root_dfd, "execveat", 0); fail += check_execveat_pathmax(root_dfd, "script", 1); + + /* /proc/pid/comm gives filename by default */ + fail += check_execveat_comm(fd, "sentinel", "execveat"); + /* /proc/pid/comm gives argv[0] when invoked via link */ + fail += check_execveat_comm(fd_symlink, "sentinel", "execveat"); + /* /proc/pid/comm gives filename if NULL is passed */ + fail += check_execveat_comm(fd, NULL, "execveat"); + return fail; } @@ -415,9 +448,13 @@ int main(int argc, char **argv) int ii; int rc; const char *verbose = getenv("VERBOSE"); + const char *check_comm = getenv(CHECK_COMM); - if (argc >= 2) { - /* If we are invoked with an argument, don't run tests. */ + if (argc >= 2 || check_comm) { + /* + * If we are invoked with an argument, or no arguments but a + * command to check, don't run tests. + */ const char *in_test = getenv("IN_TEST"); if (verbose) { @@ -426,6 +463,38 @@ int main(int argc, char **argv) ksft_print_msg("\t[%d]='%s\n'", ii, argv[ii]); } + /* If the tests wanted us to check the command, do so. */ + if (check_comm) { + /* TASK_COMM_LEN == 16 */ + char buf[32]; + int fd, ret; + + fd = open("/proc/self/comm", O_RDONLY); + if (fd < 0) { + ksft_perror("open() comm failed"); + exit(1); + } + + ret = read(fd, buf, sizeof(buf)); + if (ret < 0) { + ksft_perror("read() comm failed"); + close(fd); + exit(1); + } + close(fd); + + // trim off the \n + buf[ret-1] = 0; + + if (strcmp(buf, check_comm)) { + ksft_print_msg("bad comm, got: %s expected: %s\n", + buf, check_comm); + exit(1); + } + + exit(0); + } + /* Check expected environment transferred. */ if (!in_test || strcmp(in_test, "yes") != 0) { ksft_print_msg("no IN_TEST=yes in env\n"); diff --git a/tools/testing/selftests/exec/false.c b/tools/testing/selftests/exec/false.c new file mode 100644 index 000000000000..104383ec3a79 --- /dev/null +++ b/tools/testing/selftests/exec/false.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +int main(void) +{ + return 1; +} diff --git a/tools/testing/selftests/nsfs/.gitignore b/tools/testing/selftests/filesystems/nsfs/.gitignore similarity index 78% rename from tools/testing/selftests/nsfs/.gitignore rename to tools/testing/selftests/filesystems/nsfs/.gitignore index ed79ebdf286e..92a8249006d1 100644 --- a/tools/testing/selftests/nsfs/.gitignore +++ b/tools/testing/selftests/filesystems/nsfs/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only owner pidns +iterate_mntns diff --git a/tools/testing/selftests/nsfs/Makefile b/tools/testing/selftests/filesystems/nsfs/Makefile similarity index 50% rename from tools/testing/selftests/nsfs/Makefile rename to tools/testing/selftests/filesystems/nsfs/Makefile index dd9bd50b7b93..231aaa7dfd95 100644 --- a/tools/testing/selftests/nsfs/Makefile +++ b/tools/testing/selftests/filesystems/nsfs/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -TEST_GEN_PROGS := owner pidns +TEST_GEN_PROGS := owner pidns iterate_mntns CFLAGS := -Wall -Werror -include ../lib.mk +include ../../lib.mk diff --git a/tools/testing/selftests/nsfs/config b/tools/testing/selftests/filesystems/nsfs/config similarity index 100% rename from tools/testing/selftests/nsfs/config rename to tools/testing/selftests/filesystems/nsfs/config diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c new file mode 100644 index 000000000000..457cf76f3c5f --- /dev/null +++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Christian Brauner <brauner@kernel.org> + +#define _GNU_SOURCE +#include <fcntl.h> +#include <sched.h> +#include <stdio.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/mount.h> +#include <unistd.h> + +#include "../../kselftest_harness.h" + +#define MNT_NS_COUNT 11 +#define MNT_NS_LAST_INDEX 10 + +struct mnt_ns_info { + __u32 size; + __u32 nr_mounts; + __u64 mnt_ns_id; +}; + +#define MNT_NS_INFO_SIZE_VER0 16 /* size of first published struct */ + +/* Get information about namespace. */ +#define NS_MNT_GET_INFO _IOR(0xb7, 10, struct mnt_ns_info) +/* Get next namespace. */ +#define NS_MNT_GET_NEXT _IOR(0xb7, 11, struct mnt_ns_info) +/* Get previous namespace. */ +#define NS_MNT_GET_PREV _IOR(0xb7, 12, struct mnt_ns_info) + +FIXTURE(iterate_mount_namespaces) { + int fd_mnt_ns[MNT_NS_COUNT]; + __u64 mnt_ns_id[MNT_NS_COUNT]; +}; + +FIXTURE_SETUP(iterate_mount_namespaces) +{ + for (int i = 0; i < MNT_NS_COUNT; i++) + self->fd_mnt_ns[i] = -EBADF; + + /* + * Creating a new user namespace let's us guarantee that we only see + * mount namespaces that we did actually create. + */ + ASSERT_EQ(unshare(CLONE_NEWUSER), 0); + + for (int i = 0; i < MNT_NS_COUNT; i++) { + struct mnt_ns_info info = {}; + + ASSERT_EQ(unshare(CLONE_NEWNS), 0); + self->fd_mnt_ns[i] = open("/proc/self/ns/mnt", O_RDONLY | O_CLOEXEC); + ASSERT_GE(self->fd_mnt_ns[i], 0); + ASSERT_EQ(ioctl(self->fd_mnt_ns[i], NS_MNT_GET_INFO, &info), 0); + self->mnt_ns_id[i] = info.mnt_ns_id; + } +} + +FIXTURE_TEARDOWN(iterate_mount_namespaces) +{ + for (int i = 0; i < MNT_NS_COUNT; i++) { + if (self->fd_mnt_ns[i] < 0) + continue; + ASSERT_EQ(close(self->fd_mnt_ns[i]), 0); + } +} + +TEST_F(iterate_mount_namespaces, iterate_all_forward) +{ + int fd_mnt_ns_cur, count = 0; + + fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[0], F_DUPFD_CLOEXEC); + ASSERT_GE(fd_mnt_ns_cur, 0); + + for (;; count++) { + struct mnt_ns_info info = {}; + int fd_mnt_ns_next; + + fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info); + if (fd_mnt_ns_next < 0 && errno == ENOENT) + break; + ASSERT_GE(fd_mnt_ns_next, 0); + ASSERT_EQ(close(fd_mnt_ns_cur), 0); + fd_mnt_ns_cur = fd_mnt_ns_next; + } + ASSERT_EQ(count, MNT_NS_LAST_INDEX); +} + +TEST_F(iterate_mount_namespaces, iterate_all_backwards) +{ + int fd_mnt_ns_cur, count = 0; + + fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[MNT_NS_LAST_INDEX], F_DUPFD_CLOEXEC); + ASSERT_GE(fd_mnt_ns_cur, 0); + + for (;; count++) { + struct mnt_ns_info info = {}; + int fd_mnt_ns_prev; + + fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info); + if (fd_mnt_ns_prev < 0 && errno == ENOENT) + break; + ASSERT_GE(fd_mnt_ns_prev, 0); + ASSERT_EQ(close(fd_mnt_ns_cur), 0); + fd_mnt_ns_cur = fd_mnt_ns_prev; + } + ASSERT_EQ(count, MNT_NS_LAST_INDEX); +} + +TEST_F(iterate_mount_namespaces, iterate_forward) +{ + int fd_mnt_ns_cur; + + ASSERT_EQ(setns(self->fd_mnt_ns[0], CLONE_NEWNS), 0); + + fd_mnt_ns_cur = self->fd_mnt_ns[0]; + for (int i = 1; i < MNT_NS_COUNT; i++) { + struct mnt_ns_info info = {}; + int fd_mnt_ns_next; + + fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info); + ASSERT_GE(fd_mnt_ns_next, 0); + ASSERT_EQ(close(fd_mnt_ns_cur), 0); + fd_mnt_ns_cur = fd_mnt_ns_next; + ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); + } +} + +TEST_F(iterate_mount_namespaces, iterate_backward) +{ + int fd_mnt_ns_cur; + + ASSERT_EQ(setns(self->fd_mnt_ns[MNT_NS_LAST_INDEX], CLONE_NEWNS), 0); + + fd_mnt_ns_cur = self->fd_mnt_ns[MNT_NS_LAST_INDEX]; + for (int i = MNT_NS_LAST_INDEX - 1; i >= 0; i--) { + struct mnt_ns_info info = {}; + int fd_mnt_ns_prev; + + fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info); + ASSERT_GE(fd_mnt_ns_prev, 0); + ASSERT_EQ(close(fd_mnt_ns_cur), 0); + fd_mnt_ns_cur = fd_mnt_ns_prev; + ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); + } +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/nsfs/owner.c b/tools/testing/selftests/filesystems/nsfs/owner.c similarity index 100% rename from tools/testing/selftests/nsfs/owner.c rename to tools/testing/selftests/filesystems/nsfs/owner.c diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/filesystems/nsfs/pidns.c similarity index 100% rename from tools/testing/selftests/nsfs/pidns.c rename to tools/testing/selftests/filesystems/nsfs/pidns.c diff --git a/tools/testing/selftests/filesystems/statmount/.gitignore b/tools/testing/selftests/filesystems/statmount/.gitignore index 82a4846cbc4b..973363ad66a2 100644 --- a/tools/testing/selftests/filesystems/statmount/.gitignore +++ b/tools/testing/selftests/filesystems/statmount/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only +statmount_test_ns /*_test diff --git a/tools/testing/selftests/filesystems/statmount/Makefile b/tools/testing/selftests/filesystems/statmount/Makefile index 3af3136e35a4..14ee91a41650 100644 --- a/tools/testing/selftests/filesystems/statmount/Makefile +++ b/tools/testing/selftests/filesystems/statmount/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-or-later CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) -TEST_GEN_PROGS := statmount_test statmount_test_ns +TEST_GEN_PROGS := statmount_test statmount_test_ns listmount_test include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/statmount/listmount_test.c b/tools/testing/selftests/filesystems/statmount/listmount_test.c new file mode 100644 index 000000000000..15f0834f7557 --- /dev/null +++ b/tools/testing/selftests/filesystems/statmount/listmount_test.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Christian Brauner <brauner@kernel.org> + +#define _GNU_SOURCE +#include <fcntl.h> +#include <sched.h> +#include <stdio.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/mount.h> +#include <unistd.h> + +#include "statmount.h" +#include "../../kselftest_harness.h" + +#ifndef LISTMOUNT_REVERSE +#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ +#endif + +#define LISTMNT_BUFFER 10 + +/* Check that all mount ids are in increasing order. */ +TEST(listmount_forward) +{ + uint64_t list[LISTMNT_BUFFER], last_mnt_id = 0; + + for (;;) { + ssize_t nr_mounts; + + nr_mounts = listmount(LSMT_ROOT, 0, last_mnt_id, + list, LISTMNT_BUFFER, 0); + ASSERT_GE(nr_mounts, 0); + if (nr_mounts == 0) + break; + + for (size_t cur = 0; cur < nr_mounts; cur++) { + if (cur < nr_mounts - 1) + ASSERT_LT(list[cur], list[cur + 1]); + last_mnt_id = list[cur]; + } + } +} + +/* Check that all mount ids are in decreasing order. */ +TEST(listmount_backward) +{ + uint64_t list[LISTMNT_BUFFER], last_mnt_id = 0; + + for (;;) { + ssize_t nr_mounts; + + nr_mounts = listmount(LSMT_ROOT, 0, last_mnt_id, + list, LISTMNT_BUFFER, LISTMOUNT_REVERSE); + ASSERT_GE(nr_mounts, 0); + if (nr_mounts == 0) + break; + + for (size_t cur = 0; cur < nr_mounts; cur++) { + if (cur < nr_mounts - 1) + ASSERT_GT(list[cur], list[cur + 1]); + last_mnt_id = list[cur]; + } + } +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index a1e955d2de4c..49d96bb16355 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -6,4 +6,6 @@ TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* +TEST_GEN_PROGS = poll + include ../lib.mk diff --git a/tools/testing/selftests/ftrace/poll.c b/tools/testing/selftests/ftrace/poll.c new file mode 100644 index 000000000000..53258f7515e7 --- /dev/null +++ b/tools/testing/selftests/ftrace/poll.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Simple poll on a file. + * + * Copyright (c) 2024 Google LLC. + */ + +#include <errno.h> +#include <fcntl.h> +#include <poll.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#define BUFSIZE 4096 + +/* + * Usage: + * poll [-I|-P] [-t timeout] FILE + */ +int main(int argc, char *argv[]) +{ + struct pollfd pfd = {.events = POLLIN}; + char buf[BUFSIZE]; + int timeout = -1; + int ret, opt; + + while ((opt = getopt(argc, argv, "IPt:")) != -1) { + switch (opt) { + case 'I': + pfd.events = POLLIN; + break; + case 'P': + pfd.events = POLLPRI; + break; + case 't': + timeout = atoi(optarg); + break; + default: + fprintf(stderr, "Usage: %s [-I|-P] [-t timeout] FILE\n", + argv[0]); + return -1; + } + } + if (optind >= argc) { + fprintf(stderr, "Error: Polling file is not specified\n"); + return -1; + } + + pfd.fd = open(argv[optind], O_RDONLY); + if (pfd.fd < 0) { + fprintf(stderr, "failed to open %s", argv[optind]); + perror("open"); + return -1; + } + + /* Reset poll by read if POLLIN is specified. */ + if (pfd.events & POLLIN) + do {} while (read(pfd.fd, buf, BUFSIZE) == BUFSIZE); + + ret = poll(&pfd, 1, timeout); + if (ret < 0 && errno != EINTR) { + perror("poll"); + return -1; + } + close(pfd.fd); + + /* If timeout happned (ret == 0), exit code is 1 */ + if (ret == 0) + return 1; + + return 0; +} diff --git a/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc b/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc index 35e8d47d6072..8a7ce647a60d 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc @@ -15,11 +15,11 @@ find_alternate_gid() { tac /etc/group | grep -v ":$original_gid:" | head -1 | cut -d: -f3 } -mount_tracefs_with_options() { +remount_tracefs_with_options() { local mount_point="$1" local options="$2" - mount -t tracefs -o "$options" nodev "$mount_point" + mount -t tracefs -o "remount,$options" nodev "$mount_point" setup } @@ -81,7 +81,7 @@ test_gid_mount_option() { # Unmount existing tracefs instance and mount with new GID unmount_tracefs "$mount_point" - mount_tracefs_with_options "$mount_point" "$new_options" + remount_tracefs_with_options "$mount_point" "$new_options" check_gid "$mount_point" "$other_group" @@ -92,7 +92,7 @@ test_gid_mount_option() { # Unmount and remount with the original GID unmount_tracefs "$mount_point" - mount_tracefs_with_options "$mount_point" "$mount_options" + remount_tracefs_with_options "$mount_point" "$mount_options" check_gid "$mount_point" "$original_group" } diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_repeat.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_repeat.tc new file mode 100644 index 000000000000..b4ad09237e2a --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_repeat.tc @@ -0,0 +1,19 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Generic dynamic event - Repeating add/remove fprobe events +# requires: dynamic_events "f[:[<group>/][<event>]] <func-name>[%return] [<args>]":README + +echo 0 > events/enable +echo > dynamic_events + +PLACE=$FUNCTION_FORK +REPEAT_TIMES=64 + +for i in `seq 1 $REPEAT_TIMES`; do + echo "f:myevent $PLACE" >> dynamic_events + grep -q myevent dynamic_events + test -d events/fprobes/myevent + echo > dynamic_events +done + +clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc index a275decdc880..86c76679c56e 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc @@ -6,8 +6,10 @@ echo 0 > events/enable echo > dynamic_events +REALBIN=`readlink -f /bin/sh` + echo 'cat /proc/$$/maps' | /bin/sh | \ - grep "r-xp .*/bin/.*sh$" | \ + grep "r-xp .*${REALBIN}$" | \ awk '{printf "p:myevent %s:0x%s\n", $6,$3 }' >> uprobe_events grep -q myevent uprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc index 61877d166451..c9425a34fae3 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc @@ -16,9 +16,7 @@ aarch64) REG=%r0 ;; esac -check_error 'f^100 vfs_read' # MAXACT_NO_KPROBE -check_error 'f^1a111 vfs_read' # BAD_MAXACT -check_error 'f^100000 vfs_read' # MAXACT_TOO_BIG +check_error 'f^100 vfs_read' # BAD_MAXACT check_error 'f ^non_exist_func' # BAD_PROBE_ADDR (enoent) check_error 'f ^vfs_read+10' # BAD_PROBE_ADDR diff --git a/tools/testing/selftests/ftrace/test.d/event/event-mod.tc b/tools/testing/selftests/ftrace/test.d/event/event-mod.tc new file mode 100644 index 000000000000..175243cd9ab7 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/event-mod.tc @@ -0,0 +1,191 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event tracing - enable/disable with module event +# requires: set_event "Can enable module events via: :mod:":README +# flags: instance + +rmmod trace-events-sample ||: +if ! modprobe trace-events-sample ; then + echo "No trace-events sample module - please make CONFIG_SAMPLE_TRACE_EVENTS=m" + exit_unresolved; +fi +trap "rmmod trace-events-sample" EXIT + +# Set events for the module +echo ":mod:trace-events-sample" > set_event + +test_all_enabled() { + + # Check if more than one is enabled + grep -q sample-trace:foo_bar set_event + grep -q sample-trace:foo_bar_with_cond set_event + grep -q sample-trace:foo_bar_with_fn set_event + + # All of them should be enabled. Check via the enable file + val=`cat events/sample-trace/enable` + if [ $val -ne 1 ]; then + exit_fail + fi +} + +clear_events() { + echo > set_event + val=`cat events/enable` + if [ "$val" != "0" ]; then + exit_fail + fi + count=`cat set_event | wc -l` + if [ $count -ne 0 ]; then + exit_fail + fi +} + +test_all_enabled + +echo clear all events +echo 0 > events/enable + +echo Confirm the events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo And the set_event file is empty + +cnt=`wc -l set_event` +if [ $cnt -ne 0 ]; then + exit_fail +fi + +echo now enable all events +echo 1 > events/enable + +echo Confirm the events are enabled again +val=`cat events/sample-trace/enable` +if [ $val -ne 1 ]; then + exit_fail +fi + +echo disable just the module events +echo '!:mod:trace-events-sample' >> set_event + +echo Should have mix of events enabled +val=`cat events/enable` +if [ "$val" != "X" ]; then + exit_fail +fi + +echo Confirm the module events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo 0 > events/enable + +echo now enable the system events +echo 'sample-trace:mod:trace-events-sample' > set_event + +test_all_enabled + +echo clear all events +echo 0 > events/enable + +echo Confirm the events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo Test enabling foo_bar only +echo 'foo_bar:mod:trace-events-sample' > set_event + +grep -q sample-trace:foo_bar set_event + +echo make sure nothing is found besides foo_bar +if grep -q -v sample-trace:foo_bar set_event ; then + exit_fail +fi + +echo Append another using the system and event name +echo 'sample-trace:foo_bar_with_cond:mod:trace-events-sample' >> set_event + +grep -q sample-trace:foo_bar set_event +grep -q sample-trace:foo_bar_with_cond set_event + +count=`cat set_event | wc -l` + +if [ $count -ne 2 ]; then + exit_fail +fi + +clear_events + +rmmod trace-events-sample + +echo ':mod:trace-events-sample' > set_event + +echo make sure that the module shows up, and '-' is converted to '_' +grep -q '\*:\*:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +test_all_enabled + +clear_events + +rmmod trace-events-sample + +echo Enable just the system events +echo 'sample-trace:mod:trace-events-sample' > set_event +grep -q 'sample-trace:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +test_all_enabled + +clear_events + +rmmod trace-events-sample + +echo Enable event with just event name +echo 'foo_bar:mod:trace-events-sample' > set_event +grep -q 'foo_bar:mod:trace_events_sample' set_event + +echo Enable another event with both system and event name +echo 'sample-trace:foo_bar_with_cond:mod:trace-events-sample' >> set_event +grep -q 'sample-trace:foo_bar_with_cond:mod:trace_events_sample' set_event +echo Make sure the other event was still there +grep -q 'foo_bar:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +echo There should be no :mod: cached events +if grep -q ':mod:' set_event; then + exit_fail +fi + +echo two events should be enabled +count=`cat set_event | wc -l` +if [ $count -ne 2 ]; then + exit_fail +fi + +echo only two events should be enabled +val=`cat events/sample-trace/enable` +if [ "$val" != "X" ]; then + exit_fail +fi + +val=`cat events/sample-trace/foo_bar/enable` +if [ "$val" != "1" ]; then + exit_fail +fi + +val=`cat events/sample-trace/foo_bar_with_cond/enable` +if [ "$val" != "1" ]; then + exit_fail +fi + +clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc new file mode 100644 index 000000000000..8d275e3238d9 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc @@ -0,0 +1,74 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test poll wait on histogram +# requires: set_event events/sched/sched_process_free/trigger events/sched/sched_process_free/hist +# flags: instance + +POLL=${FTRACETEST_ROOT}/poll + +if [ ! -x ${POLL} ]; then + echo "poll program is not compiled!" + exit_unresolved +fi + +EVENT=events/sched/sched_process_free/ + +# Check poll ops is supported. Before implementing poll on hist file, it +# returns soon with POLLIN | POLLOUT, but not POLLPRI. + +# This must wait >1 sec and return 1 (timeout). +set +e +${POLL} -I -t 1000 ${EVENT}/hist +ret=$? +set -e +if [ ${ret} != 1 ]; then + echo "poll on hist file is not supported" + exit_unsupported +fi + +# Test POLLIN +echo > trace +echo 'hist:key=comm if comm =="sleep"' > ${EVENT}/trigger +echo 1 > ${EVENT}/enable + +# This sleep command will exit after 2 seconds. +sleep 2 & +BGPID=$! +# if timeout happens, poll returns 1. +${POLL} -I -t 4000 ${EVENT}/hist +echo 0 > tracing_on + +if [ -d /proc/${BGPID} ]; then + echo "poll exits too soon" + kill -KILL ${BGPID} ||: + exit_fail +fi + +if ! grep -qw "sleep" trace; then + echo "poll exits before event happens" + exit_fail +fi + +# Test POLLPRI +echo > trace +echo 1 > tracing_on + +# This sleep command will exit after 2 seconds. +sleep 2 & +BGPID=$! +# if timeout happens, poll returns 1. +${POLL} -P -t 4000 ${EVENT}/hist +echo 0 > tracing_on + +if [ -d /proc/${BGPID} ]; then + echo "poll exits too soon" + kill -KILL ${BGPID} ||: + exit_fail +fi + +if ! grep -qw "sleep" trace; then + echo "poll exits before event happens" + exit_fail +fi + +exit_pass diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 6fb66a687f17..bbc29ed9c60a 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -46,12 +46,6 @@ remove_chip() { rmdir $CONFIGFS_DIR/$CHIP || fail "Unable to remove the chip" } -configfs_cleanup() { - for CHIP in `ls $CONFIGFS_DIR/`; do - remove_chip $CHIP - done -} - create_chip() { local CHIP=$1 @@ -105,6 +99,13 @@ disable_chip() { echo 0 > $CONFIGFS_DIR/$CHIP/live || fail "Unable to disable the chip" } +configfs_cleanup() { + for CHIP in `ls $CONFIGFS_DIR/`; do + disable_chip $CHIP + remove_chip $CHIP + done +} + configfs_chip_name() { local CHIP=$1 local BANK=$2 @@ -181,6 +182,7 @@ create_chip chip create_bank chip bank enable_chip chip test -n `cat $CONFIGFS_DIR/chip/bank/chip_name` || fail "chip_name doesn't work" +disable_chip chip remove_chip chip echo "1.2. chip_name returns 'none' if the chip is still pending" @@ -195,6 +197,7 @@ create_chip chip create_bank chip bank enable_chip chip test -n `cat $CONFIGFS_DIR/chip/dev_name` || fail "dev_name doesn't work" +disable_chip chip remove_chip chip echo "2. Creating and configuring simulated chips" @@ -204,6 +207,7 @@ create_chip chip create_bank chip bank enable_chip chip test "`get_chip_num_lines chip bank`" = "1" || fail "default number of lines is not 1" +disable_chip chip remove_chip chip echo "2.2. Number of lines can be specified" @@ -212,6 +216,7 @@ create_bank chip bank set_num_lines chip bank 16 enable_chip chip test "`get_chip_num_lines chip bank`" = "16" || fail "number of lines is not 16" +disable_chip chip remove_chip chip echo "2.3. Label can be set" @@ -220,6 +225,7 @@ create_bank chip bank set_label chip bank foobar enable_chip chip test "`get_chip_label chip bank`" = "foobar" || fail "label is incorrect" +disable_chip chip remove_chip chip echo "2.4. Label can be left empty" @@ -227,6 +233,7 @@ create_chip chip create_bank chip bank enable_chip chip test -z "`cat $CONFIGFS_DIR/chip/bank/label`" || fail "label is not empty" +disable_chip chip remove_chip chip echo "2.5. Line names can be configured" @@ -238,6 +245,7 @@ set_line_name chip bank 2 bar enable_chip chip test "`get_line_name chip bank 0`" = "foo" || fail "line name is incorrect" test "`get_line_name chip bank 2`" = "bar" || fail "line name is incorrect" +disable_chip chip remove_chip chip echo "2.6. Line config can remain unused if offset is greater than number of lines" @@ -248,6 +256,7 @@ set_line_name chip bank 5 foobar enable_chip chip test "`get_line_name chip bank 0`" = "" || fail "line name is incorrect" test "`get_line_name chip bank 1`" = "" || fail "line name is incorrect" +disable_chip chip remove_chip chip echo "2.7. Line configfs directory names are sanitized" @@ -267,6 +276,7 @@ for CHIP in $CHIPS; do enable_chip $CHIP done for CHIP in $CHIPS; do + disable_chip $CHIP remove_chip $CHIP done @@ -278,6 +288,7 @@ echo foobar > $CONFIGFS_DIR/chip/bank/label 2> /dev/null && \ fail "Setting label of a live chip should fail" echo 8 > $CONFIGFS_DIR/chip/bank/num_lines 2> /dev/null && \ fail "Setting number of lines of a live chip should fail" +disable_chip chip remove_chip chip echo "2.10. Can't create line items when chip is live" @@ -285,6 +296,7 @@ create_chip chip create_bank chip bank enable_chip chip mkdir $CONFIGFS_DIR/chip/bank/line0 2> /dev/null && fail "Creating line item should fail" +disable_chip chip remove_chip chip echo "2.11. Probe errors are propagated to user-space" @@ -316,6 +328,7 @@ mkdir -p $CONFIGFS_DIR/chip/bank/line4/hog enable_chip chip $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 4 2> /dev/null && \ fail "Setting the value of a hogged line shouldn't succeed" +disable_chip chip remove_chip chip echo "3. Controlling simulated chips" @@ -331,6 +344,7 @@ test "$?" = "1" || fail "pull set incorrectly" sysfs_set_pull chip bank 0 pull-down $BASE_DIR/gpio-mockup-cdev /dev/`configfs_chip_name chip bank` 1 test "$?" = "0" || fail "pull set incorrectly" +disable_chip chip remove_chip chip echo "3.2. Pull can be read from sysfs" @@ -344,6 +358,7 @@ SYSFS_PATH=/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull test `cat $SYSFS_PATH` = "pull-down" || fail "reading the pull failed" sysfs_set_pull chip bank 0 pull-up test `cat $SYSFS_PATH` = "pull-up" || fail "reading the pull failed" +disable_chip chip remove_chip chip echo "3.3. Incorrect input in sysfs is rejected" @@ -355,6 +370,7 @@ DEVNAME=`configfs_dev_name chip` CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull" echo foobar > $SYSFS_PATH 2> /dev/null && fail "invalid input not detected" +disable_chip chip remove_chip chip echo "3.4. Can't write to value" @@ -365,6 +381,7 @@ DEVNAME=`configfs_dev_name chip` CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" echo 1 > $SYSFS_PATH 2> /dev/null && fail "writing to 'value' succeeded unexpectedly" +disable_chip chip remove_chip chip echo "4. Simulated GPIO chips are functional" @@ -382,6 +399,7 @@ $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 0 & sleep 0.1 # FIXME Any better way? test `cat $SYSFS_PATH` = "1" || fail "incorrect value read from sysfs" kill $! +disable_chip chip remove_chip chip echo "4.2. Bias settings work correctly" @@ -394,6 +412,7 @@ CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" +disable_chip chip remove_chip chip echo "GPIO $MODULE test PASS" diff --git a/tools/testing/selftests/hid/.gitignore b/tools/testing/selftests/hid/.gitignore index 746c62361f77..933f483815b2 100644 --- a/tools/testing/selftests/hid/.gitignore +++ b/tools/testing/selftests/hid/.gitignore @@ -1,5 +1,6 @@ bpftool *.skel.h +/host-tools /tools hid_bpf hidraw diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index c75ea4094870..e9dbb84c100a 100644 --- a/tools/testing/selftests/ipc/msgque.c +++ b/tools/testing/selftests/ipc/msgque.c @@ -194,7 +194,7 @@ int fill_msgque(struct msgque_data *msgque) int main(int argc, char **argv) { - int msg, pid, err; + int err; struct msgque_data msgque; if (getuid() != 0) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 29fedf609611..cdf91b0ca40f 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -18,7 +18,8 @@ * ksft_print_msg(fmt, ...); * ksft_perror(msg); * - * and finally report the pass/fail/skip/xfail state of the test with one of: + * and finally report the pass/fail/skip/xfail/xpass state of the test + * with one of: * * ksft_test_result(condition, fmt, ...); * ksft_test_result_report(result, fmt, ...); @@ -26,6 +27,7 @@ * ksft_test_result_fail(fmt, ...); * ksft_test_result_skip(fmt, ...); * ksft_test_result_xfail(fmt, ...); + * ksft_test_result_xpass(fmt, ...); * ksft_test_result_error(fmt, ...); * ksft_test_result_code(exit_code, test_name, fmt, ...); * @@ -147,6 +149,11 @@ static inline void ksft_set_plan(unsigned int plan) static inline void ksft_print_cnts(void) { + if (ksft_cnt.ksft_xskip > 0) + printf( + "# %u skipped test(s) detected. Consider enabling relevant config options to improve coverage.\n", + ksft_cnt.ksft_xskip + ); if (ksft_plan != ksft_test_num()) printf("# Planned tests != run tests (%u != %u)\n", ksft_plan, ksft_test_num()); @@ -227,6 +234,20 @@ static inline __printf(1, 2) void ksft_test_result_xfail(const char *msg, ...) va_end(args); } +static inline __printf(1, 2) void ksft_test_result_xpass(const char *msg, ...) +{ + int saved_errno = errno; + va_list args; + + ksft_cnt.ksft_xpass++; + + va_start(args, msg); + printf("ok %u # XPASS ", ksft_test_num()); + errno = saved_errno; + vprintf(msg, args); + va_end(args); +} + static inline __printf(1, 2) void ksft_test_result_skip(const char *msg, ...) { int saved_errno = errno; @@ -318,6 +339,9 @@ void ksft_test_result_code(int exit_code, const char *test_name, case KSFT_XFAIL: \ ksft_test_result_xfail(fmt, ##__VA_ARGS__); \ break; \ + case KSFT_XPASS: \ + ksft_test_result_xpass(fmt, ##__VA_ARGS__); \ + break; \ case KSFT_SKIP: \ ksft_test_result_skip(fmt, ##__VA_ARGS__); \ break; \ @@ -403,7 +427,7 @@ static inline __noreturn __printf(1, 2) void ksft_exit_skip(const char *msg, ... */ if (ksft_plan || ksft_test_num()) { ksft_cnt.ksft_xskip++; - printf("ok %d # SKIP ", 1 + ksft_test_num()); + printf("ok %u # SKIP ", 1 + ksft_test_num()); } else { printf("1..0 # SKIP "); } diff --git a/tools/testing/selftests/kselftest/ksft.py b/tools/testing/selftests/kselftest/ksft.py index bf215790a89d..0e030837fc17 100644 --- a/tools/testing/selftests/kselftest/ksft.py +++ b/tools/testing/selftests/kselftest/ksft.py @@ -27,6 +27,9 @@ def set_plan(num_tests): def print_cnts(): + if ksft_cnt['skip'] > 0: + print(f"# {ksft_cnt['skip']} skipped test(s) detected. Consider enabling relevant config options to improve coverage.") + print( f"# Totals: pass:{ksft_cnt['pass']} fail:{ksft_cnt['fail']} xfail:0 xpass:0 skip:{ksft_cnt['skip']} error:0" ) diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh index 79a125eb24c2..32dbfe9da2c4 100644 --- a/tools/testing/selftests/kselftest/ktap_helpers.sh +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -7,6 +7,7 @@ KTAP_TESTNO=1 KTAP_CNT_PASS=0 KTAP_CNT_FAIL=0 +KTAP_CNT_XFAIL=0 KTAP_CNT_SKIP=0 KSFT_PASS=0 @@ -40,7 +41,7 @@ ktap_skip_all() { __ktap_test() { result="$1" description="$2" - directive="$3" # optional + directive="${3:-}" # optional local directive_str= [ ! -z "$directive" ] && directive_str="# $directive" @@ -69,6 +70,16 @@ ktap_test_skip() { KTAP_CNT_SKIP=$((KTAP_CNT_SKIP+1)) } +ktap_test_xfail() { + description="$1" + + result="ok" + directive="XFAIL" + __ktap_test "$result" "$description" "$directive" + + KTAP_CNT_XFAIL=$((KTAP_CNT_XFAIL+1)) +} + ktap_test_fail() { description="$1" @@ -99,7 +110,7 @@ ktap_exit_fail_msg() { ktap_finished() { ktap_print_totals - if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP)) -eq "$KSFT_NUM_TESTS" ]; then + if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP + KTAP_CNT_XFAIL)) -eq "$KSFT_NUM_TESTS" ]; then exit "$KSFT_PASS" else exit "$KSFT_FAIL" @@ -107,5 +118,9 @@ ktap_finished() { } ktap_print_totals() { - echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0" + if [ "$KTAP_CNT_SKIP" -gt 0 ]; then + echo "# $KTAP_CNT_SKIP skipped test(s) detected. " \ + "Consider enabling relevant config options to improve coverage." + fi + echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:$KTAP_CNT_XFAIL xpass:0 skip:$KTAP_CNT_SKIP error:0" } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index a5a72415e37b..666c9fde76da 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -760,33 +760,33 @@ /* Report with actual signedness to avoid weird output. */ \ switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \ case 0: { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ + uintmax_t __exp_print = (uintmax_t)__exp; \ + uintmax_t __seen_print = (uintmax_t)__seen; \ + __TH_LOG("Expected %s (%ju) %s %s (%ju)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ } \ case 1: { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - long long __seen_print = (intptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%lld)", \ + uintmax_t __exp_print = (uintmax_t)__exp; \ + intmax_t __seen_print = (intmax_t)__seen; \ + __TH_LOG("Expected %s (%ju) %s %s (%jd)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ } \ case 2: { \ - long long __exp_print = (intptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%lld) %s %s (%llu)", \ + intmax_t __exp_print = (intmax_t)__exp; \ + uintmax_t __seen_print = (uintmax_t)__seen; \ + __TH_LOG("Expected %s (%jd) %s %s (%ju)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ } \ case 3: { \ - long long __exp_print = (intptr_t)__exp; \ - long long __seen_print = (intptr_t)__seen; \ - __TH_LOG("Expected %s (%lld) %s %s (%lld)", \ + intmax_t __exp_print = (intmax_t)__exp; \ + intmax_t __seen_print = (intmax_t)__seen; \ + __TH_LOG("Expected %s (%jd) %s %s (%jd)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 7f57abf936e7..1d41a046a7bf 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -9,3 +9,4 @@ !config !settings !Makefile +!Makefile.kvm \ No newline at end of file diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 41593d2e7de9..20af35a91d6f 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -1,347 +1,16 @@ # SPDX-License-Identifier: GPL-2.0-only -include ../../../build/Build.include - -all: - top_srcdir = ../../../.. include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) -ifeq ($(ARCH),x86) - ARCH_DIR := x86_64 -else ifeq ($(ARCH),arm64) - ARCH_DIR := aarch64 -else ifeq ($(ARCH),s390) - ARCH_DIR := s390x -else - ARCH_DIR := $(ARCH) -endif - -LIBKVM += lib/assert.c -LIBKVM += lib/elf.c -LIBKVM += lib/guest_modes.c -LIBKVM += lib/io.c -LIBKVM += lib/kvm_util.c -LIBKVM += lib/memstress.c -LIBKVM += lib/guest_sprintf.c -LIBKVM += lib/rbtree.c -LIBKVM += lib/sparsebit.c -LIBKVM += lib/test_util.c -LIBKVM += lib/ucall_common.c -LIBKVM += lib/userfaultfd_util.c - -LIBKVM_STRING += lib/string_override.c - -LIBKVM_x86_64 += lib/x86_64/apic.c -LIBKVM_x86_64 += lib/x86_64/handlers.S -LIBKVM_x86_64 += lib/x86_64/hyperv.c -LIBKVM_x86_64 += lib/x86_64/memstress.c -LIBKVM_x86_64 += lib/x86_64/pmu.c -LIBKVM_x86_64 += lib/x86_64/processor.c -LIBKVM_x86_64 += lib/x86_64/sev.c -LIBKVM_x86_64 += lib/x86_64/svm.c -LIBKVM_x86_64 += lib/x86_64/ucall.c -LIBKVM_x86_64 += lib/x86_64/vmx.c - -LIBKVM_aarch64 += lib/aarch64/gic.c -LIBKVM_aarch64 += lib/aarch64/gic_v3.c -LIBKVM_aarch64 += lib/aarch64/gic_v3_its.c -LIBKVM_aarch64 += lib/aarch64/handlers.S -LIBKVM_aarch64 += lib/aarch64/processor.c -LIBKVM_aarch64 += lib/aarch64/spinlock.c -LIBKVM_aarch64 += lib/aarch64/ucall.c -LIBKVM_aarch64 += lib/aarch64/vgic.c - -LIBKVM_s390x += lib/s390x/diag318_test_handler.c -LIBKVM_s390x += lib/s390x/processor.c -LIBKVM_s390x += lib/s390x/ucall.c -LIBKVM_s390x += lib/s390x/facility.c - -LIBKVM_riscv += lib/riscv/handlers.S -LIBKVM_riscv += lib/riscv/processor.c -LIBKVM_riscv += lib/riscv/ucall.c - -# Non-compiled test targets -TEST_PROGS_x86_64 += x86_64/nx_huge_pages_test.sh - -# Compiled test targets -TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test -TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test -TEST_GEN_PROGS_x86_64 += x86_64/dirty_log_page_splitting_test -TEST_GEN_PROGS_x86_64 += x86_64/feature_msrs_test -TEST_GEN_PROGS_x86_64 += x86_64/exit_on_emulation_failure_test -TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test -TEST_GEN_PROGS_x86_64 += x86_64/hwcr_msr_test -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_evmcs -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_extended_hypercalls -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_ipi -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_tlb_flush -TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test -TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test -TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test -TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test -TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test -TEST_GEN_PROGS_x86_64 += x86_64/pmu_counters_test -TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test -TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test -TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test -TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id -TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test -TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test -TEST_GEN_PROGS_x86_64 += x86_64/smm_test -TEST_GEN_PROGS_x86_64 += x86_64/state_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test -TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test -TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test -TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_shutdown_test -TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test -TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync -TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test -TEST_GEN_PROGS_x86_64 += x86_64/ucna_injection_test -TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test -TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_exception_with_invalid_guest_state -TEST_GEN_PROGS_x86_64 += x86_64/vmx_msrs_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state -TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test -TEST_GEN_PROGS_x86_64 += x86_64/apic_bus_clock_test -TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test -TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test -TEST_GEN_PROGS_x86_64 += x86_64/xcr0_cpuid_test -TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test -TEST_GEN_PROGS_x86_64 += x86_64/debug_regs -TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_caps_test -TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test -TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test -TEST_GEN_PROGS_x86_64 += x86_64/sev_init2_tests -TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests -TEST_GEN_PROGS_x86_64 += x86_64/sev_smoke_test -TEST_GEN_PROGS_x86_64 += x86_64/amx_test -TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test -TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test -TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test -TEST_GEN_PROGS_x86_64 += access_tracking_perf_test -TEST_GEN_PROGS_x86_64 += coalesced_io_test -TEST_GEN_PROGS_x86_64 += demand_paging_test -TEST_GEN_PROGS_x86_64 += dirty_log_test -TEST_GEN_PROGS_x86_64 += dirty_log_perf_test -TEST_GEN_PROGS_x86_64 += guest_memfd_test -TEST_GEN_PROGS_x86_64 += guest_print_test -TEST_GEN_PROGS_x86_64 += hardware_disable_test -TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus -TEST_GEN_PROGS_x86_64 += kvm_page_table_test -TEST_GEN_PROGS_x86_64 += max_guest_memory_test -TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test -TEST_GEN_PROGS_x86_64 += memslot_perf_test -TEST_GEN_PROGS_x86_64 += rseq_test -TEST_GEN_PROGS_x86_64 += set_memory_region_test -TEST_GEN_PROGS_x86_64 += steal_time -TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test -TEST_GEN_PROGS_x86_64 += system_counter_offset_test -TEST_GEN_PROGS_x86_64 += pre_fault_memory_test - -# Compiled outputs used by test targets -TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test - -TEST_GEN_PROGS_aarch64 += aarch64/aarch32_id_regs -TEST_GEN_PROGS_aarch64 += aarch64/arch_timer_edge_cases -TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions -TEST_GEN_PROGS_aarch64 += aarch64/hypercalls -TEST_GEN_PROGS_aarch64 += aarch64/mmio_abort -TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test -TEST_GEN_PROGS_aarch64 += aarch64/psci_test -TEST_GEN_PROGS_aarch64 += aarch64/set_id_regs -TEST_GEN_PROGS_aarch64 += aarch64/smccc_filter -TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config -TEST_GEN_PROGS_aarch64 += aarch64/vgic_init -TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq -TEST_GEN_PROGS_aarch64 += aarch64/vgic_lpi_stress -TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access -TEST_GEN_PROGS_aarch64 += aarch64/no-vgic-v3 -TEST_GEN_PROGS_aarch64 += access_tracking_perf_test -TEST_GEN_PROGS_aarch64 += arch_timer -TEST_GEN_PROGS_aarch64 += coalesced_io_test -TEST_GEN_PROGS_aarch64 += demand_paging_test -TEST_GEN_PROGS_aarch64 += dirty_log_test -TEST_GEN_PROGS_aarch64 += dirty_log_perf_test -TEST_GEN_PROGS_aarch64 += guest_print_test -TEST_GEN_PROGS_aarch64 += get-reg-list -TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus -TEST_GEN_PROGS_aarch64 += kvm_page_table_test -TEST_GEN_PROGS_aarch64 += memslot_modification_stress_test -TEST_GEN_PROGS_aarch64 += memslot_perf_test -TEST_GEN_PROGS_aarch64 += rseq_test -TEST_GEN_PROGS_aarch64 += set_memory_region_test -TEST_GEN_PROGS_aarch64 += steal_time -TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test - -TEST_GEN_PROGS_s390x = s390x/memop -TEST_GEN_PROGS_s390x += s390x/resets -TEST_GEN_PROGS_s390x += s390x/sync_regs_test -TEST_GEN_PROGS_s390x += s390x/tprot -TEST_GEN_PROGS_s390x += s390x/cmma_test -TEST_GEN_PROGS_s390x += s390x/debug_test -TEST_GEN_PROGS_s390x += s390x/cpumodel_subfuncs_test -TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test -TEST_GEN_PROGS_s390x += s390x/ucontrol_test -TEST_GEN_PROGS_s390x += demand_paging_test -TEST_GEN_PROGS_s390x += dirty_log_test -TEST_GEN_PROGS_s390x += guest_print_test -TEST_GEN_PROGS_s390x += kvm_create_max_vcpus -TEST_GEN_PROGS_s390x += kvm_page_table_test -TEST_GEN_PROGS_s390x += rseq_test -TEST_GEN_PROGS_s390x += set_memory_region_test -TEST_GEN_PROGS_s390x += kvm_binary_stats_test - -TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test -TEST_GEN_PROGS_riscv += riscv/ebreak_test -TEST_GEN_PROGS_riscv += arch_timer -TEST_GEN_PROGS_riscv += coalesced_io_test -TEST_GEN_PROGS_riscv += demand_paging_test -TEST_GEN_PROGS_riscv += dirty_log_test -TEST_GEN_PROGS_riscv += get-reg-list -TEST_GEN_PROGS_riscv += guest_print_test -TEST_GEN_PROGS_riscv += kvm_binary_stats_test -TEST_GEN_PROGS_riscv += kvm_create_max_vcpus -TEST_GEN_PROGS_riscv += kvm_page_table_test -TEST_GEN_PROGS_riscv += set_memory_region_test -TEST_GEN_PROGS_riscv += steal_time - -SPLIT_TESTS += arch_timer -SPLIT_TESTS += get-reg-list - -TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR)) -TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR)) -TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR)) -LIBKVM += $(LIBKVM_$(ARCH_DIR)) - -OVERRIDE_TARGETS = 1 - -# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most -# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`, -# which causes the environment variable to override the makefile). -include ../lib.mk - -INSTALL_HDR_PATH = $(top_srcdir)/usr -LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ -LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include +ifeq ($(ARCH),$(filter $(ARCH),arm64 s390 riscv x86 x86_64)) +# Top-level selftests allows ARCH=x86_64 :-( ifeq ($(ARCH),x86_64) -LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include + ARCH := x86 +endif +include Makefile.kvm else -LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include +# Empty targets for unsupported architectures +all: +clean: endif -CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ - -Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \ - -fno-builtin-memcmp -fno-builtin-memcpy \ - -fno-builtin-memset -fno-builtin-strnlen \ - -fno-stack-protector -fno-PIE -fno-strict-aliasing \ - -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_TOOL_ARCH_INCLUDE) \ - -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(ARCH_DIR) \ - -I ../rseq -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES) -ifeq ($(ARCH),s390) - CFLAGS += -march=z10 -endif -ifeq ($(ARCH),x86) -ifeq ($(shell echo "void foo(void) { }" | $(CC) -march=x86-64-v2 -x c - -c -o /dev/null 2>/dev/null; echo "$$?"),0) - CFLAGS += -march=x86-64-v2 -endif -endif -ifeq ($(ARCH),arm64) -tools_dir := $(top_srcdir)/tools -arm64_tools_dir := $(tools_dir)/arch/arm64/tools/ - -ifneq ($(abs_objdir),) -arm64_hdr_outdir := $(abs_objdir)/tools/ -else -arm64_hdr_outdir := $(tools_dir)/ -endif - -GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/ -CFLAGS += -I$(GEN_HDRS) - -$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*) - $(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir) -endif - -no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ - $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) - -# On s390, build the testcases KVM-enabled -pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \ - $(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste) - -LDLIBS += -ldl -LDFLAGS += -pthread $(no-pie-option) $(pgste-option) - -LIBKVM_C := $(filter %.c,$(LIBKVM)) -LIBKVM_S := $(filter %.S,$(LIBKVM)) -LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) -LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) -LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING)) -LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) -SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS)) -SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH_DIR)/%.o, $(SPLIT_TESTS)) - -TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS)) -TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED)) -TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ)) -TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS)) -TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TEST_GEN_OBJ)) --include $(TEST_DEP_FILES) - -$(shell mkdir -p $(sort $(OUTPUT)/$(ARCH_DIR) $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) - -$(filter-out $(SPLIT_TEST_GEN_PROGS), $(TEST_GEN_PROGS)) \ -$(TEST_GEN_PROGS_EXTENDED): %: %.o - $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@ -$(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ - -$(SPLIT_TEST_GEN_PROGS): $(OUTPUT)/%: $(OUTPUT)/%.o $(OUTPUT)/$(ARCH_DIR)/%.o - $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@ -$(SPLIT_TEST_GEN_OBJ): $(OUTPUT)/$(ARCH_DIR)/%.o: $(ARCH_DIR)/%.c - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ - -EXTRA_CLEAN += $(GEN_HDRS) \ - $(LIBKVM_OBJS) \ - $(SPLIT_TEST_GEN_OBJ) \ - $(TEST_DEP_FILES) \ - $(TEST_GEN_OBJ) \ - cscope.* - -$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS) - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ - -$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS) - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ - -# Compile the string overrides as freestanding to prevent the compiler from -# generating self-referential code, e.g. without "freestanding" the compiler may -# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion. -$(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@ - -$(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) -$(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS) -$(TEST_GEN_PROGS): $(LIBKVM_OBJS) -$(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS) -$(TEST_GEN_OBJ): $(GEN_HDRS) - -cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib .. -cscope: - $(RM) cscope.* - (find $(include_paths) -name '*.h' \ - -exec realpath --relative-base=$(PWD) {} \;; \ - find . -name '*.c' \ - -exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files - cscope -b diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm new file mode 100644 index 000000000000..4277b983cace --- /dev/null +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -0,0 +1,330 @@ +# SPDX-License-Identifier: GPL-2.0-only +include ../../../build/Build.include + +all: + +LIBKVM += lib/assert.c +LIBKVM += lib/elf.c +LIBKVM += lib/guest_modes.c +LIBKVM += lib/io.c +LIBKVM += lib/kvm_util.c +LIBKVM += lib/memstress.c +LIBKVM += lib/guest_sprintf.c +LIBKVM += lib/rbtree.c +LIBKVM += lib/sparsebit.c +LIBKVM += lib/test_util.c +LIBKVM += lib/ucall_common.c +LIBKVM += lib/userfaultfd_util.c + +LIBKVM_STRING += lib/string_override.c + +LIBKVM_x86 += lib/x86/apic.c +LIBKVM_x86 += lib/x86/handlers.S +LIBKVM_x86 += lib/x86/hyperv.c +LIBKVM_x86 += lib/x86/memstress.c +LIBKVM_x86 += lib/x86/pmu.c +LIBKVM_x86 += lib/x86/processor.c +LIBKVM_x86 += lib/x86/sev.c +LIBKVM_x86 += lib/x86/svm.c +LIBKVM_x86 += lib/x86/ucall.c +LIBKVM_x86 += lib/x86/vmx.c + +LIBKVM_arm64 += lib/arm64/gic.c +LIBKVM_arm64 += lib/arm64/gic_v3.c +LIBKVM_arm64 += lib/arm64/gic_v3_its.c +LIBKVM_arm64 += lib/arm64/handlers.S +LIBKVM_arm64 += lib/arm64/processor.c +LIBKVM_arm64 += lib/arm64/spinlock.c +LIBKVM_arm64 += lib/arm64/ucall.c +LIBKVM_arm64 += lib/arm64/vgic.c + +LIBKVM_s390 += lib/s390/diag318_test_handler.c +LIBKVM_s390 += lib/s390/processor.c +LIBKVM_s390 += lib/s390/ucall.c +LIBKVM_s390 += lib/s390/facility.c + +LIBKVM_riscv += lib/riscv/handlers.S +LIBKVM_riscv += lib/riscv/processor.c +LIBKVM_riscv += lib/riscv/ucall.c + +# Non-compiled test targets +TEST_PROGS_x86 += x86/nx_huge_pages_test.sh + +# Compiled test targets +TEST_GEN_PROGS_x86 = x86/cpuid_test +TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test +TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test +TEST_GEN_PROGS_x86 += x86/feature_msrs_test +TEST_GEN_PROGS_x86 += x86/exit_on_emulation_failure_test +TEST_GEN_PROGS_x86 += x86/fix_hypercall_test +TEST_GEN_PROGS_x86 += x86/hwcr_msr_test +TEST_GEN_PROGS_x86 += x86/hyperv_clock +TEST_GEN_PROGS_x86 += x86/hyperv_cpuid +TEST_GEN_PROGS_x86 += x86/hyperv_evmcs +TEST_GEN_PROGS_x86 += x86/hyperv_extended_hypercalls +TEST_GEN_PROGS_x86 += x86/hyperv_features +TEST_GEN_PROGS_x86 += x86/hyperv_ipi +TEST_GEN_PROGS_x86 += x86/hyperv_svm_test +TEST_GEN_PROGS_x86 += x86/hyperv_tlb_flush +TEST_GEN_PROGS_x86 += x86/kvm_clock_test +TEST_GEN_PROGS_x86 += x86/kvm_pv_test +TEST_GEN_PROGS_x86 += x86/monitor_mwait_test +TEST_GEN_PROGS_x86 += x86/nested_exceptions_test +TEST_GEN_PROGS_x86 += x86/platform_info_test +TEST_GEN_PROGS_x86 += x86/pmu_counters_test +TEST_GEN_PROGS_x86 += x86/pmu_event_filter_test +TEST_GEN_PROGS_x86 += x86/private_mem_conversions_test +TEST_GEN_PROGS_x86 += x86/private_mem_kvm_exits_test +TEST_GEN_PROGS_x86 += x86/set_boot_cpu_id +TEST_GEN_PROGS_x86 += x86/set_sregs_test +TEST_GEN_PROGS_x86 += x86/smaller_maxphyaddr_emulation_test +TEST_GEN_PROGS_x86 += x86/smm_test +TEST_GEN_PROGS_x86 += x86/state_test +TEST_GEN_PROGS_x86 += x86/vmx_preemption_timer_test +TEST_GEN_PROGS_x86 += x86/svm_vmcall_test +TEST_GEN_PROGS_x86 += x86/svm_int_ctl_test +TEST_GEN_PROGS_x86 += x86/svm_nested_shutdown_test +TEST_GEN_PROGS_x86 += x86/svm_nested_soft_inject_test +TEST_GEN_PROGS_x86 += x86/tsc_scaling_sync +TEST_GEN_PROGS_x86 += x86/sync_regs_test +TEST_GEN_PROGS_x86 += x86/ucna_injection_test +TEST_GEN_PROGS_x86 += x86/userspace_io_test +TEST_GEN_PROGS_x86 += x86/userspace_msr_exit_test +TEST_GEN_PROGS_x86 += x86/vmx_apic_access_test +TEST_GEN_PROGS_x86 += x86/vmx_close_while_nested_test +TEST_GEN_PROGS_x86 += x86/vmx_dirty_log_test +TEST_GEN_PROGS_x86 += x86/vmx_exception_with_invalid_guest_state +TEST_GEN_PROGS_x86 += x86/vmx_msrs_test +TEST_GEN_PROGS_x86 += x86/vmx_invalid_nested_guest_state +TEST_GEN_PROGS_x86 += x86/vmx_set_nested_state_test +TEST_GEN_PROGS_x86 += x86/vmx_tsc_adjust_test +TEST_GEN_PROGS_x86 += x86/vmx_nested_tsc_scaling_test +TEST_GEN_PROGS_x86 += x86/apic_bus_clock_test +TEST_GEN_PROGS_x86 += x86/xapic_ipi_test +TEST_GEN_PROGS_x86 += x86/xapic_state_test +TEST_GEN_PROGS_x86 += x86/xcr0_cpuid_test +TEST_GEN_PROGS_x86 += x86/xss_msr_test +TEST_GEN_PROGS_x86 += x86/debug_regs +TEST_GEN_PROGS_x86 += x86/tsc_msrs_test +TEST_GEN_PROGS_x86 += x86/vmx_pmu_caps_test +TEST_GEN_PROGS_x86 += x86/xen_shinfo_test +TEST_GEN_PROGS_x86 += x86/xen_vmcall_test +TEST_GEN_PROGS_x86 += x86/sev_init2_tests +TEST_GEN_PROGS_x86 += x86/sev_migrate_tests +TEST_GEN_PROGS_x86 += x86/sev_smoke_test +TEST_GEN_PROGS_x86 += x86/amx_test +TEST_GEN_PROGS_x86 += x86/max_vcpuid_cap_test +TEST_GEN_PROGS_x86 += x86/triple_fault_event_test +TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test +TEST_GEN_PROGS_x86 += access_tracking_perf_test +TEST_GEN_PROGS_x86 += coalesced_io_test +TEST_GEN_PROGS_x86 += demand_paging_test +TEST_GEN_PROGS_x86 += dirty_log_test +TEST_GEN_PROGS_x86 += dirty_log_perf_test +TEST_GEN_PROGS_x86 += guest_memfd_test +TEST_GEN_PROGS_x86 += guest_print_test +TEST_GEN_PROGS_x86 += hardware_disable_test +TEST_GEN_PROGS_x86 += kvm_create_max_vcpus +TEST_GEN_PROGS_x86 += kvm_page_table_test +TEST_GEN_PROGS_x86 += memslot_modification_stress_test +TEST_GEN_PROGS_x86 += memslot_perf_test +TEST_GEN_PROGS_x86 += mmu_stress_test +TEST_GEN_PROGS_x86 += rseq_test +TEST_GEN_PROGS_x86 += set_memory_region_test +TEST_GEN_PROGS_x86 += steal_time +TEST_GEN_PROGS_x86 += kvm_binary_stats_test +TEST_GEN_PROGS_x86 += system_counter_offset_test +TEST_GEN_PROGS_x86 += pre_fault_memory_test + +# Compiled outputs used by test targets +TEST_GEN_PROGS_EXTENDED_x86 += x86/nx_huge_pages_test + +TEST_GEN_PROGS_arm64 += arm64/aarch32_id_regs +TEST_GEN_PROGS_arm64 += arm64/arch_timer_edge_cases +TEST_GEN_PROGS_arm64 += arm64/debug-exceptions +TEST_GEN_PROGS_arm64 += arm64/hypercalls +TEST_GEN_PROGS_arm64 += arm64/mmio_abort +TEST_GEN_PROGS_arm64 += arm64/page_fault_test +TEST_GEN_PROGS_arm64 += arm64/psci_test +TEST_GEN_PROGS_arm64 += arm64/set_id_regs +TEST_GEN_PROGS_arm64 += arm64/smccc_filter +TEST_GEN_PROGS_arm64 += arm64/vcpu_width_config +TEST_GEN_PROGS_arm64 += arm64/vgic_init +TEST_GEN_PROGS_arm64 += arm64/vgic_irq +TEST_GEN_PROGS_arm64 += arm64/vgic_lpi_stress +TEST_GEN_PROGS_arm64 += arm64/vpmu_counter_access +TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3 +TEST_GEN_PROGS_arm64 += access_tracking_perf_test +TEST_GEN_PROGS_arm64 += arch_timer +TEST_GEN_PROGS_arm64 += coalesced_io_test +TEST_GEN_PROGS_arm64 += demand_paging_test +TEST_GEN_PROGS_arm64 += dirty_log_test +TEST_GEN_PROGS_arm64 += dirty_log_perf_test +TEST_GEN_PROGS_arm64 += guest_print_test +TEST_GEN_PROGS_arm64 += get-reg-list +TEST_GEN_PROGS_arm64 += kvm_create_max_vcpus +TEST_GEN_PROGS_arm64 += kvm_page_table_test +TEST_GEN_PROGS_arm64 += memslot_modification_stress_test +TEST_GEN_PROGS_arm64 += memslot_perf_test +TEST_GEN_PROGS_arm64 += mmu_stress_test +TEST_GEN_PROGS_arm64 += rseq_test +TEST_GEN_PROGS_arm64 += set_memory_region_test +TEST_GEN_PROGS_arm64 += steal_time +TEST_GEN_PROGS_arm64 += kvm_binary_stats_test + +TEST_GEN_PROGS_s390 = s390/memop +TEST_GEN_PROGS_s390 += s390/resets +TEST_GEN_PROGS_s390 += s390/sync_regs_test +TEST_GEN_PROGS_s390 += s390/tprot +TEST_GEN_PROGS_s390 += s390/cmma_test +TEST_GEN_PROGS_s390 += s390/debug_test +TEST_GEN_PROGS_s390 += s390/cpumodel_subfuncs_test +TEST_GEN_PROGS_s390 += s390/shared_zeropage_test +TEST_GEN_PROGS_s390 += s390/ucontrol_test +TEST_GEN_PROGS_s390 += demand_paging_test +TEST_GEN_PROGS_s390 += dirty_log_test +TEST_GEN_PROGS_s390 += guest_print_test +TEST_GEN_PROGS_s390 += kvm_create_max_vcpus +TEST_GEN_PROGS_s390 += kvm_page_table_test +TEST_GEN_PROGS_s390 += rseq_test +TEST_GEN_PROGS_s390 += set_memory_region_test +TEST_GEN_PROGS_s390 += kvm_binary_stats_test + +TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test +TEST_GEN_PROGS_riscv += riscv/ebreak_test +TEST_GEN_PROGS_riscv += arch_timer +TEST_GEN_PROGS_riscv += coalesced_io_test +TEST_GEN_PROGS_riscv += demand_paging_test +TEST_GEN_PROGS_riscv += dirty_log_test +TEST_GEN_PROGS_riscv += get-reg-list +TEST_GEN_PROGS_riscv += guest_print_test +TEST_GEN_PROGS_riscv += kvm_binary_stats_test +TEST_GEN_PROGS_riscv += kvm_create_max_vcpus +TEST_GEN_PROGS_riscv += kvm_page_table_test +TEST_GEN_PROGS_riscv += set_memory_region_test +TEST_GEN_PROGS_riscv += steal_time + +SPLIT_TESTS += arch_timer +SPLIT_TESTS += get-reg-list + +TEST_PROGS += $(TEST_PROGS_$(ARCH)) +TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH)) +TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH)) +LIBKVM += $(LIBKVM_$(ARCH)) + +OVERRIDE_TARGETS = 1 + +# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most +# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`, +# which causes the environment variable to override the makefile). +include ../lib.mk + +INSTALL_HDR_PATH = $(top_srcdir)/usr +LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ +LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include +LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include +CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ + -Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \ + -fno-builtin-memcmp -fno-builtin-memcpy \ + -fno-builtin-memset -fno-builtin-strnlen \ + -fno-stack-protector -fno-PIE -fno-strict-aliasing \ + -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_TOOL_ARCH_INCLUDE) \ + -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(ARCH) \ + -I ../rseq -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES) +ifeq ($(ARCH),s390) + CFLAGS += -march=z10 +endif +ifeq ($(ARCH),x86) +ifeq ($(shell echo "void foo(void) { }" | $(CC) -march=x86-64-v2 -x c - -c -o /dev/null 2>/dev/null; echo "$$?"),0) + CFLAGS += -march=x86-64-v2 +endif +endif +ifeq ($(ARCH),arm64) +tools_dir := $(top_srcdir)/tools +arm64_tools_dir := $(tools_dir)/arch/arm64/tools/ + +ifneq ($(abs_objdir),) +arm64_hdr_outdir := $(abs_objdir)/tools/ +else +arm64_hdr_outdir := $(tools_dir)/ +endif + +GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/ +CFLAGS += -I$(GEN_HDRS) + +$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*) + $(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir) +endif + +no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ + $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) + +# On s390, build the testcases KVM-enabled +pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \ + $(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste) + +LDLIBS += -ldl +LDFLAGS += -pthread $(no-pie-option) $(pgste-option) + +LIBKVM_C := $(filter %.c,$(LIBKVM)) +LIBKVM_S := $(filter %.S,$(LIBKVM)) +LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) +LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) +LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING)) +LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) +SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS)) +SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH)/%.o, $(SPLIT_TESTS)) + +TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS)) +TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED)) +TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ)) +TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS)) +TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TEST_GEN_OBJ)) +-include $(TEST_DEP_FILES) + +$(shell mkdir -p $(sort $(OUTPUT)/$(ARCH) $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) + +$(filter-out $(SPLIT_TEST_GEN_PROGS), $(TEST_GEN_PROGS)) \ +$(TEST_GEN_PROGS_EXTENDED): %: %.o + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@ +$(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +$(SPLIT_TEST_GEN_PROGS): $(OUTPUT)/%: $(OUTPUT)/%.o $(OUTPUT)/$(ARCH)/%.o + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@ +$(SPLIT_TEST_GEN_OBJ): $(OUTPUT)/$(ARCH)/%.o: $(ARCH)/%.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +EXTRA_CLEAN += $(GEN_HDRS) \ + $(LIBKVM_OBJS) \ + $(SPLIT_TEST_GEN_OBJ) \ + $(TEST_DEP_FILES) \ + $(TEST_GEN_OBJ) \ + cscope.* + +$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS) + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS) + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +# Compile the string overrides as freestanding to prevent the compiler from +# generating self-referential code, e.g. without "freestanding" the compiler may +# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion. +$(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@ + +$(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) +$(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS) +$(TEST_GEN_PROGS): $(LIBKVM_OBJS) +$(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS) +$(TEST_GEN_OBJ): $(GEN_HDRS) + +cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib .. +cscope: + $(RM) cscope.* + (find $(include_paths) -name '*.h' \ + -exec realpath --relative-base=$(PWD) {} \;; \ + find . -name '*.c' \ + -exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files + cscope -b diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c similarity index 93% rename from tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c rename to tools/testing/selftests/kvm/arm64/aarch32_id_regs.c index 8e5bd07a3727..cef8f7323ceb 100644 --- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c @@ -97,7 +97,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) uint64_t reg_id = raz_wi_reg_ids[i]; uint64_t val; - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); /* @@ -106,7 +106,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) */ vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL); - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); } } @@ -126,14 +126,14 @@ static void test_user_raz_invariant(struct kvm_vcpu *vcpu) uint64_t reg_id = raz_invariant_reg_ids[i]; uint64_t val; - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); r = __vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL); TEST_ASSERT(r < 0 && errno == EINVAL, "unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno); - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); } } @@ -144,10 +144,10 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu) { uint64_t val, el0; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); - return el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY; + return el0 == ID_AA64PFR0_EL1_EL0_IMP; } int main(void) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/arm64/arch_timer.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/arch_timer.c rename to tools/testing/selftests/kvm/arm64/arch_timer.c diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/arch_timer_edge_cases.c rename to tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c similarity index 99% rename from tools/testing/selftests/kvm/aarch64/debug-exceptions.c rename to tools/testing/selftests/kvm/arm64/debug-exceptions.c index ff7a949fc96a..c7fb55c9135b 100644 --- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c @@ -501,7 +501,7 @@ void test_single_step_from_userspace(int test_cnt) TEST_ASSERT(ss_enable, "Unexpected KVM_EXIT_DEBUG"); /* Check if the current pc is expected. */ - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc); + pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); TEST_ASSERT(!test_pc || pc == test_pc, "Unexpected pc 0x%lx (expected 0x%lx)", pc, test_pc); @@ -583,7 +583,7 @@ int main(int argc, char *argv[]) uint64_t aa64dfr0; vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &aa64dfr0); + aa64dfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); __TEST_REQUIRE(debug_version(aa64dfr0) >= 6, "Armv8 debug architecture not supported."); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/arm64/get-reg-list.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/get-reg-list.c rename to tools/testing/selftests/kvm/arm64/get-reg-list.c diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/arm64/hypercalls.c similarity index 98% rename from tools/testing/selftests/kvm/aarch64/hypercalls.c rename to tools/testing/selftests/kvm/arm64/hypercalls.c index 9d192ce0078d..ec54ec7726e9 100644 --- a/tools/testing/selftests/kvm/aarch64/hypercalls.c +++ b/tools/testing/selftests/kvm/arm64/hypercalls.c @@ -173,7 +173,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu) const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i]; /* First 'read' should be an upper limit of the features supported */ - vcpu_get_reg(vcpu, reg_info->reg, &val); + val = vcpu_get_reg(vcpu, reg_info->reg); TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), "Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx", reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val); @@ -184,7 +184,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu) "Failed to clear all the features of reg: 0x%lx; ret: %d", reg_info->reg, errno); - vcpu_get_reg(vcpu, reg_info->reg, &val); + val = vcpu_get_reg(vcpu, reg_info->reg); TEST_ASSERT(val == 0, "Expected all the features to be cleared for reg: 0x%lx", reg_info->reg); @@ -214,7 +214,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu) * Before starting the VM, the test clears all the bits. * Check if that's still the case. */ - vcpu_get_reg(vcpu, reg_info->reg, &val); + val = vcpu_get_reg(vcpu, reg_info->reg); TEST_ASSERT(val == 0, "Expected all the features to be cleared for reg: 0x%lx", reg_info->reg); diff --git a/tools/testing/selftests/kvm/aarch64/mmio_abort.c b/tools/testing/selftests/kvm/arm64/mmio_abort.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/mmio_abort.c rename to tools/testing/selftests/kvm/arm64/mmio_abort.c diff --git a/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c similarity index 98% rename from tools/testing/selftests/kvm/aarch64/no-vgic-v3.c rename to tools/testing/selftests/kvm/arm64/no-vgic-v3.c index 58304bbc2036..ebd70430c89d 100644 --- a/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c +++ b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c @@ -164,7 +164,7 @@ int main(int argc, char *argv[]) uint64_t pfr0; vm = vm_create_with_one_vcpu(&vcpu, NULL); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &pfr0); + pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); __TEST_REQUIRE(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), pfr0), "GICv3 not supported."); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/page_fault_test.c rename to tools/testing/selftests/kvm/arm64/page_fault_test.c diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/arm64/psci_test.c similarity index 96% rename from tools/testing/selftests/kvm/aarch64/psci_test.c rename to tools/testing/selftests/kvm/arm64/psci_test.c index eaa7655fefc1..ab491ee9e5f7 100644 --- a/tools/testing/selftests/kvm/aarch64/psci_test.c +++ b/tools/testing/selftests/kvm/arm64/psci_test.c @@ -111,8 +111,8 @@ static void assert_vcpu_reset(struct kvm_vcpu *vcpu) { uint64_t obs_pc, obs_x0; - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &obs_pc); - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0]), &obs_x0); + obs_pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); + obs_x0 = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0])); TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR, "unexpected target cpu pc: %lx (expected: %lx)", @@ -152,7 +152,7 @@ static void host_test_cpu_on(void) */ vcpu_power_off(target); - vcpu_get_reg(target, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr); + target_mpidr = vcpu_get_reg(target, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1)); vcpu_args_set(source, 1, target_mpidr & MPIDR_HWID_BITMASK); enter_guest(source); @@ -244,7 +244,7 @@ static void host_test_system_off2(void) setup_vm(guest_test_system_off2, &source, &target); - vcpu_get_reg(target, KVM_REG_ARM_PSCI_VERSION, &psci_version); + psci_version = vcpu_get_reg(target, KVM_REG_ARM_PSCI_VERSION); TEST_ASSERT(psci_version >= PSCI_VERSION(1, 3), "Unexpected PSCI version %lu.%lu", diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c similarity index 96% rename from tools/testing/selftests/kvm/aarch64/set_id_regs.c rename to tools/testing/selftests/kvm/arm64/set_id_regs.c index a79b7f18452d..217541fe6536 100644 --- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -152,7 +152,6 @@ static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGENDEL0, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, SNSMEM, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGEND, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, ASIDBITS, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, PARANGE, 0), REG_FTR_END, }; @@ -346,7 +345,7 @@ static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg, uint64_t mask = ftr_bits->mask; uint64_t val, new_val, ftr; - vcpu_get_reg(vcpu, reg, &val); + val = vcpu_get_reg(vcpu, reg); ftr = (val & mask) >> shift; ftr = get_safe_value(ftr_bits, ftr); @@ -356,7 +355,7 @@ static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg, val |= ftr; vcpu_set_reg(vcpu, reg, val); - vcpu_get_reg(vcpu, reg, &new_val); + new_val = vcpu_get_reg(vcpu, reg); TEST_ASSERT_EQ(new_val, val); return new_val; @@ -370,7 +369,7 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg, uint64_t val, old_val, ftr; int r; - vcpu_get_reg(vcpu, reg, &val); + val = vcpu_get_reg(vcpu, reg); ftr = (val & mask) >> shift; ftr = get_invalid_value(ftr_bits, ftr); @@ -384,7 +383,7 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg, TEST_ASSERT(r < 0 && errno == EINVAL, "Unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno); - vcpu_get_reg(vcpu, reg, &val); + val = vcpu_get_reg(vcpu, reg); TEST_ASSERT_EQ(val, old_val); } @@ -471,7 +470,7 @@ static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu) } /* Get the id register value */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); /* Try to set MPAM=0. This should always be possible. */ val &= ~ID_AA64PFR0_EL1_MPAM_MASK; @@ -508,7 +507,7 @@ static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu) } /* Get the id register value */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); /* Try to set MPAM_frac=0. This should always be possible. */ val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK; @@ -576,7 +575,7 @@ static void test_clidr(struct kvm_vcpu *vcpu) uint64_t clidr; int level; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1), &clidr); + clidr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1)); /* find the first empty level in the cache hierarchy */ for (level = 1; level < 7; level++) { @@ -601,7 +600,7 @@ static void test_ctr(struct kvm_vcpu *vcpu) { u64 ctr; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CTR_EL0), &ctr); + ctr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CTR_EL0)); ctr &= ~CTR_EL0_DIC_MASK; if (ctr & CTR_EL0_IminLine_MASK) ctr--; @@ -617,7 +616,7 @@ static void test_vcpu_ftr_id_regs(struct kvm_vcpu *vcpu) test_clidr(vcpu); test_ctr(vcpu); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1)); val++; vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), val); @@ -630,7 +629,7 @@ static void test_assert_id_reg_unchanged(struct kvm_vcpu *vcpu, uint32_t encodin size_t idx = encoding_to_range_idx(encoding); uint64_t observed; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding), &observed); + observed = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding)); TEST_ASSERT_EQ(test_reg_vals[idx], observed); } @@ -665,9 +664,9 @@ int main(void) vm = vm_create_with_one_vcpu(&vcpu, guest_code); /* Check for AARCH64 only system */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); - aarch64_only = (el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY); + aarch64_only = (el0 == ID_AA64PFR0_EL1_EL0_IMP); ksft_print_header(); diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/arm64/smccc_filter.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/smccc_filter.c rename to tools/testing/selftests/kvm/arm64/smccc_filter.c diff --git a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c b/tools/testing/selftests/kvm/arm64/vcpu_width_config.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/vcpu_width_config.c rename to tools/testing/selftests/kvm/arm64/vcpu_width_config.c diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/arm64/vgic_init.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/vgic_init.c rename to tools/testing/selftests/kvm/arm64/vgic_init.c diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/vgic_irq.c rename to tools/testing/selftests/kvm/arm64/vgic_irq.c diff --git a/tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c similarity index 100% rename from tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c rename to tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c similarity index 97% rename from tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c rename to tools/testing/selftests/kvm/arm64/vpmu_counter_access.c index f9c0c86d7e85..f16b3b27e32e 100644 --- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c +++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c @@ -440,8 +440,7 @@ static void create_vpmu_vm(void *guest_code) "Failed to create vgic-v3, skipping"); /* Make sure that PMUv3 support is indicated in the ID register */ - vcpu_get_reg(vpmu_vm.vcpu, - KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &dfr0); + dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0); TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF && pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP, @@ -484,7 +483,7 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail) create_vpmu_vm(guest_code); vcpu = vpmu_vm.vcpu; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr_orig); + pmcr_orig = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); pmcr = pmcr_orig; /* @@ -493,7 +492,7 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail) */ set_pmcr_n(&pmcr, pmcr_n); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), pmcr); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr); + pmcr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); if (expect_fail) TEST_ASSERT(pmcr_orig == pmcr, @@ -521,7 +520,7 @@ static void run_access_test(uint64_t pmcr_n) vcpu = vpmu_vm.vcpu; /* Save the initial sp to restore them later to run the guest again */ - vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1), &sp); + sp = vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1)); run_vcpu(vcpu, pmcr_n); @@ -572,12 +571,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n) * Test if the 'set' and 'clr' variants of the registers * are initialized based on the number of valid counters. */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(set_reg_id), reg_val); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(clr_reg_id), reg_val); @@ -589,12 +588,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n) */ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), max_counters_mask); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(set_reg_id), reg_val); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(clr_reg_id), reg_val); @@ -625,7 +624,7 @@ static uint64_t get_pmcr_n_limit(void) uint64_t pmcr; create_vpmu_vm(guest_code); - vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr); + pmcr = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); destroy_vpmu_vm(); return get_pmcr_n(pmcr); } diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 9f24303acb8c..e79817bd0e29 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -21,7 +21,7 @@ #include "ucall_common.h" #ifdef __aarch64__ -#include "aarch64/vgic.h" +#include "arm64/vgic.h" static int gic_fd; diff --git a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h b/tools/testing/selftests/kvm/include/arm64/arch_timer.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/arch_timer.h rename to tools/testing/selftests/kvm/include/arm64/arch_timer.h diff --git a/tools/testing/selftests/kvm/include/aarch64/delay.h b/tools/testing/selftests/kvm/include/arm64/delay.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/delay.h rename to tools/testing/selftests/kvm/include/arm64/delay.h diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/arm64/gic.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/gic.h rename to tools/testing/selftests/kvm/include/arm64/gic.h diff --git a/tools/testing/selftests/kvm/include/aarch64/gic_v3.h b/tools/testing/selftests/kvm/include/arm64/gic_v3.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/gic_v3.h rename to tools/testing/selftests/kvm/include/arm64/gic_v3.h diff --git a/tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h rename to tools/testing/selftests/kvm/include/arm64/gic_v3_its.h diff --git a/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h rename to tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/processor.h rename to tools/testing/selftests/kvm/include/arm64/processor.h diff --git a/tools/testing/selftests/kvm/include/aarch64/spinlock.h b/tools/testing/selftests/kvm/include/arm64/spinlock.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/spinlock.h rename to tools/testing/selftests/kvm/include/arm64/spinlock.h diff --git a/tools/testing/selftests/kvm/include/aarch64/ucall.h b/tools/testing/selftests/kvm/include/arm64/ucall.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/ucall.h rename to tools/testing/selftests/kvm/include/arm64/ucall.h diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/arm64/vgic.h similarity index 100% rename from tools/testing/selftests/kvm/include/aarch64/vgic.h rename to tools/testing/selftests/kvm/include/arm64/vgic.h diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index bc7c242480d6..4c4e5a847f67 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -702,16 +702,22 @@ static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t va return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); } -static inline void vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +static inline uint64_t vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id) { - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + uint64_t val; + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + + TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); + return val; } static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) { struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); + vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); } diff --git a/tools/testing/selftests/kvm/include/s390x/debug_print.h b/tools/testing/selftests/kvm/include/s390/debug_print.h similarity index 100% rename from tools/testing/selftests/kvm/include/s390x/debug_print.h rename to tools/testing/selftests/kvm/include/s390/debug_print.h diff --git a/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h b/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h similarity index 100% rename from tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h rename to tools/testing/selftests/kvm/include/s390/diag318_test_handler.h diff --git a/tools/testing/selftests/kvm/include/s390x/facility.h b/tools/testing/selftests/kvm/include/s390/facility.h similarity index 100% rename from tools/testing/selftests/kvm/include/s390x/facility.h rename to tools/testing/selftests/kvm/include/s390/facility.h diff --git a/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h b/tools/testing/selftests/kvm/include/s390/kvm_util_arch.h similarity index 100% rename from tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h rename to tools/testing/selftests/kvm/include/s390/kvm_util_arch.h diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390/processor.h similarity index 100% rename from tools/testing/selftests/kvm/include/s390x/processor.h rename to tools/testing/selftests/kvm/include/s390/processor.h diff --git a/tools/testing/selftests/kvm/include/s390x/sie.h b/tools/testing/selftests/kvm/include/s390/sie.h similarity index 100% rename from tools/testing/selftests/kvm/include/s390x/sie.h rename to tools/testing/selftests/kvm/include/s390/sie.h diff --git a/tools/testing/selftests/kvm/include/s390x/ucall.h b/tools/testing/selftests/kvm/include/s390/ucall.h similarity index 100% rename from tools/testing/selftests/kvm/include/s390x/ucall.h rename to tools/testing/selftests/kvm/include/s390/ucall.h diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86/apic.h similarity index 98% rename from tools/testing/selftests/kvm/include/x86_64/apic.h rename to tools/testing/selftests/kvm/include/x86/apic.h index 51990094effd..80fe9f69b38d 100644 --- a/tools/testing/selftests/kvm/include/x86_64/apic.h +++ b/tools/testing/selftests/kvm/include/x86/apic.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/apic.h - * * Copyright (C) 2021, Google LLC. */ diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86/evmcs.h similarity index 99% rename from tools/testing/selftests/kvm/include/x86_64/evmcs.h rename to tools/testing/selftests/kvm/include/x86/evmcs.h index 901caf0e0939..5a74bb30e2f8 100644 --- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86/evmcs.h @@ -1,9 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * tools/testing/selftests/kvm/include/x86_64/evmcs.h - * * Copyright (C) 2018, Red Hat, Inc. - * */ #ifndef SELFTEST_KVM_EVMCS_H diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86/hyperv.h similarity index 99% rename from tools/testing/selftests/kvm/include/x86_64/hyperv.h rename to tools/testing/selftests/kvm/include/x86/hyperv.h index 6849e2552f1b..f13e532be240 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86/hyperv.h @@ -1,9 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * tools/testing/selftests/kvm/include/x86_64/hyperv.h - * * Copyright (C) 2021, Red Hat, Inc. - * */ #ifndef SELFTEST_KVM_HYPERV_H diff --git a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h similarity index 100% rename from tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h rename to tools/testing/selftests/kvm/include/x86/kvm_util_arch.h diff --git a/tools/testing/selftests/kvm/include/x86_64/mce.h b/tools/testing/selftests/kvm/include/x86/mce.h similarity index 94% rename from tools/testing/selftests/kvm/include/x86_64/mce.h rename to tools/testing/selftests/kvm/include/x86/mce.h index 6119321f3f5d..295f2d554754 100644 --- a/tools/testing/selftests/kvm/include/x86_64/mce.h +++ b/tools/testing/selftests/kvm/include/x86/mce.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/mce.h - * * Copyright (C) 2022, Google LLC. */ diff --git a/tools/testing/selftests/kvm/include/x86_64/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h similarity index 100% rename from tools/testing/selftests/kvm/include/x86_64/pmu.h rename to tools/testing/selftests/kvm/include/x86/pmu.h diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h similarity index 99% rename from tools/testing/selftests/kvm/include/x86_64/processor.h rename to tools/testing/selftests/kvm/include/x86/processor.h index 645200e95f89..d60da8966772 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/processor.h - * * Copyright (C) 2018, Google LLC. */ @@ -29,6 +27,8 @@ extern uint64_t guest_tsc_khz; #define MAX_NR_CPUID_ENTRIES 100 #endif +#define NONCANONICAL 0xaaaaaaaaaaaaaaaaull + /* Forced emulation prefix, used to invoke the emulator unconditionally. */ #define KVM_FEP "ud2; .byte 'k', 'v', 'm';" @@ -571,6 +571,11 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } +static inline void set_idt(const struct desc_ptr *idt_desc) +{ + __asm__ __volatile__("lidt %0"::"m"(*idt_desc)); +} + static inline u64 xgetbv(u32 index) { u32 eax, edx; @@ -1012,10 +1017,19 @@ static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries) void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid); +static inline void vcpu_get_cpuid(struct kvm_vcpu *vcpu) +{ + vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); +} + static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function, uint32_t index) { + TEST_ASSERT(vcpu->cpuid, "Must do vcpu_init_cpuid() first (or equivalent)"); + + vcpu_get_cpuid(vcpu); + return (struct kvm_cpuid_entry2 *)get_cpuid_entry(vcpu->cpuid, function, index); } @@ -1036,7 +1050,7 @@ static inline int __vcpu_set_cpuid(struct kvm_vcpu *vcpu) return r; /* On success, refresh the cache to pick up adjustments made by KVM. */ - vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); + vcpu_get_cpuid(vcpu); return 0; } @@ -1046,12 +1060,7 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) vcpu_ioctl(vcpu, KVM_SET_CPUID2, vcpu->cpuid); /* Refresh the cache to pick up adjustments made by KVM. */ - vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); -} - -static inline void vcpu_get_cpuid(struct kvm_vcpu *vcpu) -{ - vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); + vcpu_get_cpuid(vcpu); } void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, diff --git a/tools/testing/selftests/kvm/include/x86_64/sev.h b/tools/testing/selftests/kvm/include/x86/sev.h similarity index 100% rename from tools/testing/selftests/kvm/include/x86_64/sev.h rename to tools/testing/selftests/kvm/include/x86/sev.h diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86/svm.h similarity index 98% rename from tools/testing/selftests/kvm/include/x86_64/svm.h rename to tools/testing/selftests/kvm/include/x86/svm.h index 4803e1056055..29cffd0a9181 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm.h +++ b/tools/testing/selftests/kvm/include/x86/svm.h @@ -1,10 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* - * tools/testing/selftests/kvm/include/x86_64/svm.h - * This is a copy of arch/x86/include/asm/svm.h - * - */ - #ifndef SELFTEST_KVM_SVM_H #define SELFTEST_KVM_SVM_H diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86/svm_util.h similarity index 94% rename from tools/testing/selftests/kvm/include/x86_64/svm_util.h rename to tools/testing/selftests/kvm/include/x86/svm_util.h index 044f0f872ba9..b74c6dcddcbd 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86/svm_util.h @@ -1,8 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/svm_utils.h - * Header for nested SVM testing - * * Copyright (C) 2020, Red Hat, Inc. */ diff --git a/tools/testing/selftests/kvm/include/x86_64/ucall.h b/tools/testing/selftests/kvm/include/x86/ucall.h similarity index 100% rename from tools/testing/selftests/kvm/include/x86_64/ucall.h rename to tools/testing/selftests/kvm/include/x86/ucall.h diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86/vmx.h similarity index 99% rename from tools/testing/selftests/kvm/include/x86_64/vmx.h rename to tools/testing/selftests/kvm/include/x86/vmx.h index 5f0c0a29c556..edb3c391b982 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86/vmx.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/vmx.h - * * Copyright (C) 2018, Google LLC. */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/arm64/gic.c similarity index 100% rename from tools/testing/selftests/kvm/lib/aarch64/gic.c rename to tools/testing/selftests/kvm/lib/arm64/gic.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/arm64/gic_private.h similarity index 100% rename from tools/testing/selftests/kvm/lib/aarch64/gic_private.h rename to tools/testing/selftests/kvm/lib/arm64/gic_private.h diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c similarity index 100% rename from tools/testing/selftests/kvm/lib/aarch64/gic_v3.c rename to tools/testing/selftests/kvm/lib/arm64/gic_v3.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c similarity index 100% rename from tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c rename to tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/handlers.S b/tools/testing/selftests/kvm/lib/arm64/handlers.S similarity index 100% rename from tools/testing/selftests/kvm/lib/aarch64/handlers.S rename to tools/testing/selftests/kvm/lib/arm64/handlers.S diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c similarity index 98% rename from tools/testing/selftests/kvm/lib/aarch64/processor.c rename to tools/testing/selftests/kvm/lib/arm64/processor.c index 698e34f39241..7ba3aa3755f3 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/arm64/processor.c @@ -281,8 +281,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) */ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1); + sctlr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1)); + tcr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1)); /* Configure base granule size */ switch (vm->mode) { @@ -360,8 +360,8 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { uint64_t pstate, pc; - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate), &pstate); - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc); + pstate = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate)); + pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); fprintf(stream, "%*spstate: 0x%.16lx pc: 0x%.16lx\n", indent, "", pstate, pc); diff --git a/tools/testing/selftests/kvm/lib/aarch64/spinlock.c b/tools/testing/selftests/kvm/lib/arm64/spinlock.c similarity index 100% rename from tools/testing/selftests/kvm/lib/aarch64/spinlock.c rename to tools/testing/selftests/kvm/lib/arm64/spinlock.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/arm64/ucall.c similarity index 100% rename from tools/testing/selftests/kvm/lib/aarch64/ucall.c rename to tools/testing/selftests/kvm/lib/arm64/ucall.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/arm64/vgic.c similarity index 100% rename from tools/testing/selftests/kvm/lib/aarch64/vgic.c rename to tools/testing/selftests/kvm/lib/arm64/vgic.c diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 480e3a40d197..33fefeb3ca44 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1648,7 +1648,8 @@ int _vcpu_run(struct kvm_vcpu *vcpu) rc = __vcpu_run(vcpu); } while (rc == -1 && errno == EINTR); - assert_on_unhandled_exception(vcpu); + if (!rc) + assert_on_unhandled_exception(vcpu); return rc; } diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index 6ae47b3d6b25..dd663bcf0cc0 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -221,39 +221,39 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { struct kvm_riscv_core core; - vcpu_get_reg(vcpu, RISCV_CORE_REG(mode), &core.mode); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &core.regs.pc); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra), &core.regs.ra); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp), &core.regs.sp); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp), &core.regs.gp); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp), &core.regs.tp); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0), &core.regs.t0); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1), &core.regs.t1); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2), &core.regs.t2); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0), &core.regs.s0); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1), &core.regs.s1); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0), &core.regs.a0); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1), &core.regs.a1); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2), &core.regs.a2); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3), &core.regs.a3); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4), &core.regs.a4); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5), &core.regs.a5); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6), &core.regs.a6); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7), &core.regs.a7); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2), &core.regs.s2); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3), &core.regs.s3); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4), &core.regs.s4); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5), &core.regs.s5); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6), &core.regs.s6); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7), &core.regs.s7); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8), &core.regs.s8); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9), &core.regs.s9); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10), &core.regs.s10); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11), &core.regs.s11); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3), &core.regs.t3); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4), &core.regs.t4); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5), &core.regs.t5); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6), &core.regs.t6); + core.mode = vcpu_get_reg(vcpu, RISCV_CORE_REG(mode)); + core.regs.pc = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc)); + core.regs.ra = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra)); + core.regs.sp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp)); + core.regs.gp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp)); + core.regs.tp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp)); + core.regs.t0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0)); + core.regs.t1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1)); + core.regs.t2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2)); + core.regs.s0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0)); + core.regs.s1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1)); + core.regs.a0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0)); + core.regs.a1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1)); + core.regs.a2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2)); + core.regs.a3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3)); + core.regs.a4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4)); + core.regs.a5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5)); + core.regs.a6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6)); + core.regs.a7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7)); + core.regs.s2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2)); + core.regs.s3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3)); + core.regs.s4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4)); + core.regs.s5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5)); + core.regs.s6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6)); + core.regs.s7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7)); + core.regs.s8 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8)); + core.regs.s9 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9)); + core.regs.s10 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10)); + core.regs.s11 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11)); + core.regs.t3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3)); + core.regs.t4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4)); + core.regs.t5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5)); + core.regs.t6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6)); fprintf(stream, " MODE: 0x%lx\n", core.mode); diff --git a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c b/tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c similarity index 100% rename from tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c rename to tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c diff --git a/tools/testing/selftests/kvm/lib/s390x/facility.c b/tools/testing/selftests/kvm/lib/s390/facility.c similarity index 100% rename from tools/testing/selftests/kvm/lib/s390x/facility.c rename to tools/testing/selftests/kvm/lib/s390/facility.c diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390/processor.c similarity index 100% rename from tools/testing/selftests/kvm/lib/s390x/processor.c rename to tools/testing/selftests/kvm/lib/s390/processor.c diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390/ucall.c similarity index 100% rename from tools/testing/selftests/kvm/lib/s390x/ucall.c rename to tools/testing/selftests/kvm/lib/s390/ucall.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/apic.c b/tools/testing/selftests/kvm/lib/x86/apic.c similarity index 100% rename from tools/testing/selftests/kvm/lib/x86_64/apic.c rename to tools/testing/selftests/kvm/lib/x86/apic.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86/handlers.S similarity index 100% rename from tools/testing/selftests/kvm/lib/x86_64/handlers.S rename to tools/testing/selftests/kvm/lib/x86/handlers.S diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86/hyperv.c similarity index 100% rename from tools/testing/selftests/kvm/lib/x86_64/hyperv.c rename to tools/testing/selftests/kvm/lib/x86/hyperv.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/memstress.c b/tools/testing/selftests/kvm/lib/x86/memstress.c similarity index 98% rename from tools/testing/selftests/kvm/lib/x86_64/memstress.c rename to tools/testing/selftests/kvm/lib/x86/memstress.c index d61e623afc8c..7f5d62a65c68 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/memstress.c +++ b/tools/testing/selftests/kvm/lib/x86/memstress.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * x86_64-specific extensions to memstress.c. + * x86-specific extensions to memstress.c. * * Copyright (C) 2022, Google, Inc. */ diff --git a/tools/testing/selftests/kvm/lib/x86_64/pmu.c b/tools/testing/selftests/kvm/lib/x86/pmu.c similarity index 100% rename from tools/testing/selftests/kvm/lib/x86_64/pmu.c rename to tools/testing/selftests/kvm/lib/x86/pmu.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c similarity index 99% rename from tools/testing/selftests/kvm/lib/x86_64/processor.c rename to tools/testing/selftests/kvm/lib/x86/processor.c index 636b29ba8985..bd5a802fa7a5 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * tools/testing/selftests/kvm/lib/x86_64/processor.c - * * Copyright (C) 2018, Google LLC. */ diff --git a/tools/testing/selftests/kvm/lib/x86_64/sev.c b/tools/testing/selftests/kvm/lib/x86/sev.c similarity index 100% rename from tools/testing/selftests/kvm/lib/x86_64/sev.c rename to tools/testing/selftests/kvm/lib/x86/sev.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86/svm.c similarity index 99% rename from tools/testing/selftests/kvm/lib/x86_64/svm.c rename to tools/testing/selftests/kvm/lib/x86/svm.c index 5495a92dfd5a..d239c2097391 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86/svm.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * tools/testing/selftests/kvm/lib/x86_64/svm.c * Helpers used for nested SVM testing * Largely inspired from KVM unit test svm.c * diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86/ucall.c similarity index 100% rename from tools/testing/selftests/kvm/lib/x86_64/ucall.c rename to tools/testing/selftests/kvm/lib/x86/ucall.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c similarity index 99% rename from tools/testing/selftests/kvm/lib/x86_64/vmx.c rename to tools/testing/selftests/kvm/lib/x86/vmx.c index d7ac122820bf..d4d1208dd023 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86/vmx.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * tools/testing/selftests/kvm/lib/x86_64/vmx.c - * * Copyright (C) 2018, Google LLC. */ diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c similarity index 60% rename from tools/testing/selftests/kvm/max_guest_memory_test.c rename to tools/testing/selftests/kvm/mmu_stress_test.c index 0b9678858b6d..d9c76b4c0d88 100644 --- a/tools/testing/selftests/kvm/max_guest_memory_test.c +++ b/tools/testing/selftests/kvm/mmu_stress_test.c @@ -15,16 +15,62 @@ #include "test_util.h" #include "guest_modes.h" #include "processor.h" +#include "ucall_common.h" + +static bool mprotect_ro_done; static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) { uint64_t gpa; + int i; - for (;;) { + for (i = 0; i < 2; i++) { for (gpa = start_gpa; gpa < end_gpa; gpa += stride) - *((volatile uint64_t *)gpa) = gpa; - GUEST_SYNC(0); + vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa); + GUEST_SYNC(i); } + + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) + *((volatile uint64_t *)gpa); + GUEST_SYNC(2); + + /* + * Write to the region while mprotect(PROT_READ) is underway. Keep + * looping until the memory is guaranteed to be read-only, otherwise + * vCPUs may complete their writes and advance to the next stage + * prematurely. + * + * For architectures that support skipping the faulting instruction, + * generate the store via inline assembly to ensure the exact length + * of the instruction is known and stable (vcpu_arch_put_guest() on + * fixed-length architectures should work, but the cost of paranoia + * is low in this case). For x86, hand-code the exact opcode so that + * there is no room for variability in the generated instruction. + */ + do { + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) +#ifdef __x86_64__ + asm volatile(".byte 0x48,0x89,0x00" :: "a"(gpa) : "memory"); /* mov %rax, (%rax) */ +#elif defined(__aarch64__) + asm volatile("str %0, [%0]" :: "r" (gpa) : "memory"); +#else + vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa); +#endif + } while (!READ_ONCE(mprotect_ro_done)); + + /* + * Only architectures that write the entire range can explicitly sync, + * as other architectures will be stuck on the write fault. + */ +#if defined(__x86_64__) || defined(__aarch64__) + GUEST_SYNC(3); +#endif + + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) + vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa); + GUEST_SYNC(4); + + GUEST_ASSERT(0); } struct vcpu_info { @@ -51,34 +97,100 @@ static void rendezvous_with_boss(void) } } -static void run_vcpu(struct kvm_vcpu *vcpu) +static void assert_sync_stage(struct kvm_vcpu *vcpu, int stage) +{ + struct ucall uc; + + TEST_ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC); + TEST_ASSERT_EQ(uc.args[1], stage); +} + +static void run_vcpu(struct kvm_vcpu *vcpu, int stage) { vcpu_run(vcpu); - TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); + assert_sync_stage(vcpu, stage); } static void *vcpu_worker(void *data) { + struct kvm_sregs __maybe_unused sregs; struct vcpu_info *info = data; struct kvm_vcpu *vcpu = info->vcpu; struct kvm_vm *vm = vcpu->vm; - struct kvm_sregs sregs; + int r; vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size); rendezvous_with_boss(); - run_vcpu(vcpu); + /* Stage 0, write all of guest memory. */ + run_vcpu(vcpu, 0); rendezvous_with_boss(); - vcpu_sregs_get(vcpu, &sregs); #ifdef __x86_64__ + vcpu_sregs_get(vcpu, &sregs); /* Toggle CR0.WP to trigger a MMU context reset. */ sregs.cr0 ^= X86_CR0_WP; -#endif vcpu_sregs_set(vcpu, &sregs); +#endif rendezvous_with_boss(); - run_vcpu(vcpu); + /* Stage 1, re-write all of guest memory. */ + run_vcpu(vcpu, 1); + rendezvous_with_boss(); + + /* Stage 2, read all of guest memory, which is now read-only. */ + run_vcpu(vcpu, 2); + + /* + * Stage 3, write guest memory and verify KVM returns -EFAULT for once + * the mprotect(PROT_READ) lands. Only architectures that support + * validating *all* of guest memory sync for this stage, as vCPUs will + * be stuck on the faulting instruction for other architectures. Go to + * stage 3 without a rendezvous + */ + do { + r = _vcpu_run(vcpu); + } while (!r); + TEST_ASSERT(r == -1 && errno == EFAULT, + "Expected EFAULT on write to RO memory, got r = %d, errno = %d", r, errno); + +#if defined(__x86_64__) || defined(__aarch64__) + /* + * Verify *all* writes from the guest hit EFAULT due to the VMA now + * being read-only. x86 and arm64 only at this time as skipping the + * instruction that hits the EFAULT requires advancing the program + * counter, which is arch specific and relies on inline assembly. + */ +#ifdef __x86_64__ + vcpu->run->kvm_valid_regs = KVM_SYNC_X86_REGS; +#endif + for (;;) { + r = _vcpu_run(vcpu); + if (!r) + break; + TEST_ASSERT_EQ(errno, EFAULT); +#if defined(__x86_64__) + WRITE_ONCE(vcpu->run->kvm_dirty_regs, KVM_SYNC_X86_REGS); + vcpu->run->s.regs.regs.rip += 3; +#elif defined(__aarch64__) + vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), + vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)) + 4); +#endif + + } + assert_sync_stage(vcpu, 3); +#endif /* __x86_64__ || __aarch64__ */ + rendezvous_with_boss(); + + /* + * Stage 4. Run to completion, waiting for mprotect(PROT_WRITE) to + * make the memory writable again. + */ + do { + r = _vcpu_run(vcpu); + } while (r && errno == EFAULT); + TEST_ASSERT_EQ(r, 0); + assert_sync_stage(vcpu, 4); rendezvous_with_boss(); return NULL; @@ -161,7 +273,7 @@ int main(int argc, char *argv[]) const uint64_t start_gpa = SZ_4G; const int first_slot = 1; - struct timespec time_start, time_run1, time_reset, time_run2; + struct timespec time_start, time_run1, time_reset, time_run2, time_ro, time_rw; uint64_t max_gpa, gpa, slot_size, max_mem, i; int max_slots, slot, opt, fd; bool hugepages = false; @@ -209,7 +321,13 @@ int main(int argc, char *argv[]) vcpus = malloc(nr_vcpus * sizeof(*vcpus)); TEST_ASSERT(vcpus, "Failed to allocate vCPU array"); - vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus); + vm = __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, +#ifdef __x86_64__ + max_mem / SZ_1G, +#else + max_mem / vm_guest_mode_params[VM_MODE_DEFAULT].page_size, +#endif + guest_code, vcpus); max_gpa = vm->max_gfn << vm->page_shift; TEST_ASSERT(max_gpa > (4 * slot_size), "MAXPHYADDR <4gb "); @@ -259,14 +377,28 @@ int main(int argc, char *argv[]) rendezvous_with_vcpus(&time_reset, "reset"); rendezvous_with_vcpus(&time_run2, "run 2"); + mprotect(mem, slot_size, PROT_READ); + usleep(10); + mprotect_ro_done = true; + sync_global_to_guest(vm, mprotect_ro_done); + + rendezvous_with_vcpus(&time_ro, "mprotect RO"); + mprotect(mem, slot_size, PROT_READ | PROT_WRITE); + rendezvous_with_vcpus(&time_rw, "mprotect RW"); + + time_rw = timespec_sub(time_rw, time_ro); + time_ro = timespec_sub(time_ro, time_run2); time_run2 = timespec_sub(time_run2, time_reset); - time_reset = timespec_sub(time_reset, time_run1); + time_reset = timespec_sub(time_reset, time_run1); time_run1 = timespec_sub(time_run1, time_start); - pr_info("run1 = %ld.%.9lds, reset = %ld.%.9lds, run2 = %ld.%.9lds\n", + pr_info("run1 = %ld.%.9lds, reset = %ld.%.9lds, run2 = %ld.%.9lds, " + "ro = %ld.%.9lds, rw = %ld.%.9lds\n", time_run1.tv_sec, time_run1.tv_nsec, time_reset.tv_sec, time_reset.tv_nsec, - time_run2.tv_sec, time_run2.tv_nsec); + time_run2.tv_sec, time_run2.tv_nsec, + time_ro.tv_sec, time_ro.tv_nsec, + time_rw.tv_sec, time_rw.tv_nsec); /* * Delete even numbered slots (arbitrary) and unmap the first half of diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c index 2c792228ac0b..9e370800a6a2 100644 --- a/tools/testing/selftests/kvm/riscv/arch_timer.c +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -93,7 +93,7 @@ struct kvm_vm *test_vm_create(void) vcpu_init_vector_tables(vcpus[i]); /* Initialize guest timer frequency. */ - vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency), &timer_freq); + timer_freq = vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency)); sync_global_to_guest(vm, timer_freq); pr_debug("timer_freq: %lu\n", timer_freq); diff --git a/tools/testing/selftests/kvm/riscv/ebreak_test.c b/tools/testing/selftests/kvm/riscv/ebreak_test.c index 0e0712854953..cfed6c727bfc 100644 --- a/tools/testing/selftests/kvm/riscv/ebreak_test.c +++ b/tools/testing/selftests/kvm/riscv/ebreak_test.c @@ -60,7 +60,7 @@ int main(void) TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &pc); + pc = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc)); TEST_ASSERT_EQ(pc, LABEL_ADDRESS(sw_bp_1)); /* skip sw_bp_1 */ diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 4bc1051848e5..8515921dfdbf 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -52,6 +52,8 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVVPTC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZABHA: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZACAS: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZAWRS: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA: @@ -71,6 +73,7 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICCRSE: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR: @@ -112,6 +115,7 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SUSP: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR: @@ -429,6 +433,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), KVM_ISA_EXT_ARR(SVPBMT), + KVM_ISA_EXT_ARR(SVVPTC), + KVM_ISA_EXT_ARR(ZABHA), KVM_ISA_EXT_ARR(ZACAS), KVM_ISA_EXT_ARR(ZAWRS), KVM_ISA_EXT_ARR(ZBA), @@ -448,6 +454,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(ZFHMIN), KVM_ISA_EXT_ARR(ZICBOM), KVM_ISA_EXT_ARR(ZICBOZ), + KVM_ISA_EXT_ARR(ZICCRSE), KVM_ISA_EXT_ARR(ZICNTR), KVM_ISA_EXT_ARR(ZICOND), KVM_ISA_EXT_ARR(ZICSR), @@ -535,10 +542,11 @@ static const char *sbi_ext_single_id_to_str(__u64 reg_off) KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SRST), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_HSM), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_PMU), + KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN), + KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SUSP), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_STA), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_EXPERIMENTAL), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_VENDOR), - KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN), }; if (reg_off >= ARRAY_SIZE(kvm_sbi_ext_reg_name)) @@ -949,6 +957,7 @@ KVM_SBI_EXT_SUBLIST_CONFIG(base, BASE); KVM_SBI_EXT_SUBLIST_CONFIG(sta, STA); KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU); KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN); +KVM_SBI_EXT_SIMPLE_CONFIG(susp, SUSP); KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA); KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F); @@ -964,6 +973,8 @@ KVM_ISA_EXT_SIMPLE_CONFIG(svadu, SVADU); KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL); KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT); KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT); +KVM_ISA_EXT_SIMPLE_CONFIG(svvptc, SVVPTC); +KVM_ISA_EXT_SIMPLE_CONFIG(zabha, ZABHA); KVM_ISA_EXT_SIMPLE_CONFIG(zacas, ZACAS); KVM_ISA_EXT_SIMPLE_CONFIG(zawrs, ZAWRS); KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA); @@ -983,6 +994,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH); KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN); KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM); KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ); +KVM_ISA_EXT_SIMPLE_CONFIG(ziccrse, ZICCRSE); KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR); KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND); KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR); @@ -1017,6 +1029,7 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_sbi_sta, &config_sbi_pmu, &config_sbi_dbcn, + &config_sbi_susp, &config_aia, &config_fp_f, &config_fp_d, @@ -1031,6 +1044,8 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_svinval, &config_svnapot, &config_svpbmt, + &config_svvptc, + &config_zabha, &config_zacas, &config_zawrs, &config_zba, @@ -1050,6 +1065,7 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_zfhmin, &config_zicbom, &config_zicboz, + &config_ziccrse, &config_zicntr, &config_zicond, &config_zicsr, diff --git a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c index f299cbfd23ca..f45c0ecc902d 100644 --- a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c +++ b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c @@ -608,7 +608,7 @@ static void test_vm_events_overflow(void *guest_code) vcpu_init_vector_tables(vcpu); /* Initialize guest timer frequency. */ - vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency), &timer_freq); + timer_freq = vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency)); sync_global_to_guest(vm, timer_freq); run_vcpu(vcpu); diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390/cmma_test.c similarity index 100% rename from tools/testing/selftests/kvm/s390x/cmma_test.c rename to tools/testing/selftests/kvm/s390/cmma_test.c diff --git a/tools/testing/selftests/kvm/s390x/config b/tools/testing/selftests/kvm/s390/config similarity index 100% rename from tools/testing/selftests/kvm/s390x/config rename to tools/testing/selftests/kvm/s390/config diff --git a/tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c similarity index 100% rename from tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c rename to tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390/debug_test.c similarity index 100% rename from tools/testing/selftests/kvm/s390x/debug_test.c rename to tools/testing/selftests/kvm/s390/debug_test.c diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390/memop.c similarity index 100% rename from tools/testing/selftests/kvm/s390x/memop.c rename to tools/testing/selftests/kvm/s390/memop.c diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390/resets.c similarity index 99% rename from tools/testing/selftests/kvm/s390x/resets.c rename to tools/testing/selftests/kvm/s390/resets.c index 357943f2bea8..b58f75b381e5 100644 --- a/tools/testing/selftests/kvm/s390x/resets.c +++ b/tools/testing/selftests/kvm/s390/resets.c @@ -61,7 +61,7 @@ static void test_one_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t value) { uint64_t eval_reg; - vcpu_get_reg(vcpu, id, &eval_reg); + eval_reg = vcpu_get_reg(vcpu, id); TEST_ASSERT(eval_reg == value, "value == 0x%lx", value); } diff --git a/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c similarity index 100% rename from tools/testing/selftests/kvm/s390x/shared_zeropage_test.c rename to tools/testing/selftests/kvm/s390/shared_zeropage_test.c diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390/sync_regs_test.c similarity index 100% rename from tools/testing/selftests/kvm/s390x/sync_regs_test.c rename to tools/testing/selftests/kvm/s390/sync_regs_test.c diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390/tprot.c similarity index 100% rename from tools/testing/selftests/kvm/s390x/tprot.c rename to tools/testing/selftests/kvm/s390/tprot.c diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390/ucontrol_test.c similarity index 80% rename from tools/testing/selftests/kvm/s390x/ucontrol_test.c rename to tools/testing/selftests/kvm/s390/ucontrol_test.c index 0c112319dab1..135ee22856cf 100644 --- a/tools/testing/selftests/kvm/s390x/ucontrol_test.c +++ b/tools/testing/selftests/kvm/s390/ucontrol_test.c @@ -210,10 +210,13 @@ TEST_F(uc_kvm, uc_attr_mem_limit) struct kvm_device_attr attr = { .group = KVM_S390_VM_MEM_CTRL, .attr = KVM_S390_VM_MEM_LIMIT_SIZE, - .addr = (unsigned long)&limit, + .addr = (u64)&limit, }; int rc; + rc = ioctl(self->vm_fd, KVM_HAS_DEVICE_ATTR, &attr); + EXPECT_EQ(0, rc); + rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr); EXPECT_EQ(0, rc); EXPECT_EQ(~0UL, limit); @@ -635,4 +638,171 @@ TEST_F(uc_kvm, uc_skey) uc_assert_diag44(self); } +static char uc_flic_b[PAGE_SIZE]; +static struct kvm_s390_io_adapter uc_flic_ioa = { .id = 0 }; +static struct kvm_s390_io_adapter_req uc_flic_ioam = { .id = 0 }; +static struct kvm_s390_ais_req uc_flic_asim = { .isc = 0 }; +static struct kvm_s390_ais_all uc_flic_asima = { .simm = 0 }; +static struct uc_flic_attr_test { + char *name; + struct kvm_device_attr a; + int hasrc; + int geterrno; + int seterrno; +} uc_flic_attr_tests[] = { + { + .name = "KVM_DEV_FLIC_GET_ALL_IRQS", + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_GET_ALL_IRQS, + .addr = (u64)&uc_flic_b, + .attr = PAGE_SIZE, + }, + }, + { + .name = "KVM_DEV_FLIC_ENQUEUE", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_ENQUEUE, }, + }, + { + .name = "KVM_DEV_FLIC_CLEAR_IRQS", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_CLEAR_IRQS, }, + }, + { + .name = "KVM_DEV_FLIC_ADAPTER_REGISTER", + .geterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_ADAPTER_REGISTER, + .addr = (u64)&uc_flic_ioa, + }, + }, + { + .name = "KVM_DEV_FLIC_ADAPTER_MODIFY", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_ADAPTER_MODIFY, + .addr = (u64)&uc_flic_ioam, + .attr = sizeof(uc_flic_ioam), + }, + }, + { + .name = "KVM_DEV_FLIC_CLEAR_IO_IRQ", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_CLEAR_IO_IRQ, + .attr = 32, + }, + }, + { + .name = "KVM_DEV_FLIC_AISM", + .geterrno = EINVAL, + .seterrno = ENOTSUP, + .a = { + .group = KVM_DEV_FLIC_AISM, + .addr = (u64)&uc_flic_asim, + }, + }, + { + .name = "KVM_DEV_FLIC_AIRQ_INJECT", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_AIRQ_INJECT, }, + }, + { + .name = "KVM_DEV_FLIC_AISM_ALL", + .geterrno = ENOTSUP, + .seterrno = ENOTSUP, + .a = { + .group = KVM_DEV_FLIC_AISM_ALL, + .addr = (u64)&uc_flic_asima, + .attr = sizeof(uc_flic_asima), + }, + }, + { + .name = "KVM_DEV_FLIC_APF_ENABLE", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_APF_ENABLE, }, + }, + { + .name = "KVM_DEV_FLIC_APF_DISABLE_WAIT", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, }, + }, +}; + +TEST_F(uc_kvm, uc_flic_attrs) +{ + struct kvm_create_device cd = { .type = KVM_DEV_TYPE_FLIC }; + struct kvm_device_attr attr; + u64 value; + int rc, i; + + rc = ioctl(self->vm_fd, KVM_CREATE_DEVICE, &cd); + ASSERT_EQ(0, rc) TH_LOG("create device failed with err %s (%i)", + strerror(errno), errno); + + for (i = 0; i < ARRAY_SIZE(uc_flic_attr_tests); i++) { + TH_LOG("test %s", uc_flic_attr_tests[i].name); + attr = (struct kvm_device_attr) { + .group = uc_flic_attr_tests[i].a.group, + .attr = uc_flic_attr_tests[i].a.attr, + .addr = uc_flic_attr_tests[i].a.addr, + }; + if (attr.addr == 0) + attr.addr = (u64)&value; + + rc = ioctl(cd.fd, KVM_HAS_DEVICE_ATTR, &attr); + EXPECT_EQ(uc_flic_attr_tests[i].hasrc, !!rc) + TH_LOG("expected dev attr missing %s", + uc_flic_attr_tests[i].name); + + rc = ioctl(cd.fd, KVM_GET_DEVICE_ATTR, &attr); + EXPECT_EQ(!!uc_flic_attr_tests[i].geterrno, !!rc) + TH_LOG("get dev attr rc not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + if (uc_flic_attr_tests[i].geterrno) + EXPECT_EQ(uc_flic_attr_tests[i].geterrno, errno) + TH_LOG("get dev attr errno not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + + rc = ioctl(cd.fd, KVM_SET_DEVICE_ATTR, &attr); + EXPECT_EQ(!!uc_flic_attr_tests[i].seterrno, !!rc) + TH_LOG("set sev attr rc not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + if (uc_flic_attr_tests[i].seterrno) + EXPECT_EQ(uc_flic_attr_tests[i].seterrno, errno) + TH_LOG("set dev attr errno not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + } + + close(cd.fd); +} + +TEST_F(uc_kvm, uc_set_gsi_routing) +{ + struct kvm_irq_routing *routing = kvm_gsi_routing_create(); + struct kvm_irq_routing_entry ue = { + .type = KVM_IRQ_ROUTING_S390_ADAPTER, + .gsi = 1, + .u.adapter = (struct kvm_irq_routing_s390_adapter) { + .ind_addr = 0, + }, + }; + int rc; + + routing->entries[0] = ue; + routing->nr = 1; + rc = ioctl(self->vm_fd, KVM_SET_GSI_ROUTING, routing); + ASSERT_EQ(-1, rc) TH_LOG("err %s (%i)", strerror(errno), errno); + ASSERT_EQ(EINVAL, errno) TH_LOG("err %s (%i)", strerror(errno), errno); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index a8267628e9ed..bc440d5aba57 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -17,9 +17,9 @@ #include <processor.h> /* - * s390x needs at least 1MB alignment, and the x86_64 MOVE/DELETE tests need a - * 2MB sized and aligned region so that the initial region corresponds to - * exactly one large page. + * s390 needs at least 1MB alignment, and the x86 MOVE/DELETE tests need a 2MB + * sized and aligned region so that the initial region corresponds to exactly + * one large page. */ #define MEM_REGION_SIZE 0x200000 @@ -235,7 +235,7 @@ static void guest_code_delete_memory_region(void) * in the guest will never succeed, and so isn't an option. */ memset(&idt, 0, sizeof(idt)); - __asm__ __volatile__("lidt %0" :: "m"(idt)); + set_idt(&idt); GUEST_SYNC(0); @@ -553,6 +553,56 @@ static void test_add_overlapping_private_memory_regions(void) close(memfd); kvm_vm_free(vm); } + +static void guest_code_mmio_during_vectoring(void) +{ + const struct desc_ptr idt_desc = { + .address = MEM_REGION_GPA, + .size = 0xFFF, + }; + + set_idt(&idt_desc); + + /* Generate a #GP by dereferencing a non-canonical address */ + *((uint8_t *)NONCANONICAL) = 0x1; + + GUEST_ASSERT(0); +} + +/* + * This test points the IDT descriptor base to an MMIO address. It should cause + * a KVM internal error when an event occurs in the guest. + */ +static void test_mmio_during_vectoring(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + u64 expected_gpa; + + pr_info("Testing MMIO during vectoring error handling\n"); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code_mmio_during_vectoring); + virt_map(vm, MEM_REGION_GPA, MEM_REGION_GPA, 1); + + run = vcpu->run; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR); + TEST_ASSERT(run->internal.suberror == KVM_INTERNAL_ERROR_DELIVERY_EV, + "Unexpected suberror = %d", vcpu->run->internal.suberror); + TEST_ASSERT(run->internal.ndata != 4, "Unexpected internal error data array size = %d", + run->internal.ndata); + + /* The reported GPA should be IDT base + offset of the GP vector */ + expected_gpa = MEM_REGION_GPA + GP_VECTOR * sizeof(struct idt_entry); + + TEST_ASSERT(run->internal.data[3] == expected_gpa, + "Unexpected GPA = %llx (expected %lx)", + vcpu->run->internal.data[3], expected_gpa); + + kvm_vm_free(vm); +} #endif int main(int argc, char *argv[]) @@ -568,6 +618,7 @@ int main(int argc, char *argv[]) * KVM_RUN fails with ENOEXEC or EFAULT. */ test_zero_memory_regions(); + test_mmio_during_vectoring(); #endif test_invalid_memory_region_flags(); diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index a8d3afa0b86b..cce2520af720 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -269,9 +269,8 @@ static void guest_code(int cpu) static bool is_steal_time_supported(struct kvm_vcpu *vcpu) { uint64_t id = RISCV_SBI_EXT_REG(KVM_RISCV_SBI_EXT_STA); - unsigned long enabled; + unsigned long enabled = vcpu_get_reg(vcpu, id); - vcpu_get_reg(vcpu, id, &enabled); TEST_ASSERT(enabled == 0 || enabled == 1, "Expected boolean result"); return enabled; diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86/amx_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/amx_test.c rename to tools/testing/selftests/kvm/x86/amx_test.c diff --git a/tools/testing/selftests/kvm/x86_64/apic_bus_clock_test.c b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/apic_bus_clock_test.c rename to tools/testing/selftests/kvm/x86/apic_bus_clock_test.c diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86/cpuid_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/cpuid_test.c rename to tools/testing/selftests/kvm/x86/cpuid_test.c diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86/cr4_cpuid_sync_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c rename to tools/testing/selftests/kvm/x86/cr4_cpuid_sync_test.c diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86/debug_regs.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/debug_regs.c rename to tools/testing/selftests/kvm/x86/debug_regs.c diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c rename to tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86/exit_on_emulation_failure_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c rename to tools/testing/selftests/kvm/x86/exit_on_emulation_failure_test.c diff --git a/tools/testing/selftests/kvm/x86_64/feature_msrs_test.c b/tools/testing/selftests/kvm/x86/feature_msrs_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/feature_msrs_test.c rename to tools/testing/selftests/kvm/x86/feature_msrs_test.c diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c rename to tools/testing/selftests/kvm/x86/fix_hypercall_test.c diff --git a/tools/testing/selftests/kvm/x86_64/flds_emulation.h b/tools/testing/selftests/kvm/x86/flds_emulation.h similarity index 100% rename from tools/testing/selftests/kvm/x86_64/flds_emulation.h rename to tools/testing/selftests/kvm/x86/flds_emulation.h diff --git a/tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c rename to tools/testing/selftests/kvm/x86/hwcr_msr_test.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86/hyperv_clock.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/hyperv_clock.c rename to tools/testing/selftests/kvm/x86/hyperv_clock.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c rename to tools/testing/selftests/kvm/x86/hyperv_cpuid.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86/hyperv_evmcs.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c rename to tools/testing/selftests/kvm/x86/hyperv_evmcs.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c rename to tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86/hyperv_features.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/hyperv_features.c rename to tools/testing/selftests/kvm/x86/hyperv_features.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86/hyperv_ipi.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/hyperv_ipi.c rename to tools/testing/selftests/kvm/x86/hyperv_ipi.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86/hyperv_svm_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c rename to tools/testing/selftests/kvm/x86/hyperv_svm_test.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c rename to tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86/kvm_clock_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/kvm_clock_test.c rename to tools/testing/selftests/kvm/x86/kvm_clock_test.c diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86/kvm_pv_test.c similarity index 76% rename from tools/testing/selftests/kvm/x86_64/kvm_pv_test.c rename to tools/testing/selftests/kvm/x86/kvm_pv_test.c index 78878b3a2725..1b805cbdb47b 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86/kvm_pv_test.c @@ -139,11 +139,13 @@ static void test_pv_unhalt(void) struct kvm_vm *vm; struct kvm_cpuid_entry2 *ent; u32 kvm_sig_old; + int r; + + if (!(kvm_check_cap(KVM_CAP_X86_DISABLE_EXITS) & KVM_X86_DISABLE_EXITS_HLT)) + return; pr_info("testing KVM_FEATURE_PV_UNHALT\n"); - TEST_REQUIRE(KVM_CAP_X86_DISABLE_EXITS); - /* KVM_PV_UNHALT test */ vm = vm_create_with_one_vcpu(&vcpu, guest_main); vcpu_set_cpuid_feature(vcpu, X86_FEATURE_KVM_PV_UNHALT); @@ -151,19 +153,45 @@ static void test_pv_unhalt(void) TEST_ASSERT(vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), "Enabling X86_FEATURE_KVM_PV_UNHALT had no effect"); - /* Make sure KVM clears vcpu->arch.kvm_cpuid */ + /* Verify KVM disallows disabling exits after vCPU creation. */ + r = __vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, KVM_X86_DISABLE_EXITS_HLT); + TEST_ASSERT(r && errno == EINVAL, + "Disabling exits after vCPU creation didn't fail as expected"); + + kvm_vm_free(vm); + + /* Verify that KVM clear PV_UNHALT from guest CPUID. */ + vm = vm_create(1); + vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, KVM_X86_DISABLE_EXITS_HLT); + + vcpu = vm_vcpu_add(vm, 0, NULL); + TEST_ASSERT(!vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "vCPU created with PV_UNHALT set by default"); + + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_KVM_PV_UNHALT); + TEST_ASSERT(!vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "PV_UNHALT set in guest CPUID when HLT-exiting is disabled"); + + /* + * Clobber the KVM PV signature and verify KVM does NOT clear PV_UNHALT + * when KVM PV is not present, and DOES clear PV_UNHALT when switching + * back to the correct signature.. + */ ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE); kvm_sig_old = ent->ebx; ent->ebx = 0xdeadbeef; vcpu_set_cpuid(vcpu); - vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, KVM_X86_DISABLE_EXITS_HLT); + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_KVM_PV_UNHALT); + TEST_ASSERT(vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "PV_UNHALT cleared when using bogus KVM PV signature"); + ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE); ent->ebx = kvm_sig_old; vcpu_set_cpuid(vcpu); TEST_ASSERT(!vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), - "KVM_FEATURE_PV_UNHALT is set with KVM_CAP_X86_DISABLE_EXITS"); + "PV_UNHALT set in guest CPUID when HLT-exiting is disabled"); /* FIXME: actually test KVM_FEATURE_PV_UNHALT feature */ diff --git a/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c b/tools/testing/selftests/kvm/x86/max_vcpuid_cap_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c rename to tools/testing/selftests/kvm/x86/max_vcpuid_cap_test.c diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c rename to tools/testing/selftests/kvm/x86/monitor_mwait_test.c diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c rename to tools/testing/selftests/kvm/x86/nested_exceptions_test.c diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c rename to tools/testing/selftests/kvm/x86/nx_huge_pages_test.c diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.sh similarity index 100% rename from tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh rename to tools/testing/selftests/kvm/x86/nx_huge_pages_test.sh diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86/platform_info_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/platform_info_test.c rename to tools/testing/selftests/kvm/x86/platform_info_test.c diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/pmu_counters_test.c rename to tools/testing/selftests/kvm/x86/pmu_counters_test.c diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c rename to tools/testing/selftests/kvm/x86/pmu_event_filter_test.c diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c rename to tools/testing/selftests/kvm/x86/private_mem_conversions_test.c diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c rename to tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c diff --git a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c b/tools/testing/selftests/kvm/x86/recalc_apic_map_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c rename to tools/testing/selftests/kvm/x86/recalc_apic_map_test.c diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c rename to tools/testing/selftests/kvm/x86/set_boot_cpu_id.c diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86/set_sregs_test.c similarity index 75% rename from tools/testing/selftests/kvm/x86_64/set_sregs_test.c rename to tools/testing/selftests/kvm/x86/set_sregs_test.c index c021c0795a96..f4095a3d1278 100644 --- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86/set_sregs_test.c @@ -41,13 +41,15 @@ do { \ TEST_ASSERT(!memcmp(&new, &orig, sizeof(new)), "KVM modified sregs"); \ } while (0) +#define KVM_ALWAYS_ALLOWED_CR4 (X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | \ + X86_CR4_DE | X86_CR4_PSE | X86_CR4_PAE | \ + X86_CR4_MCE | X86_CR4_PGE | X86_CR4_PCE | \ + X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT) + static uint64_t calc_supported_cr4_feature_bits(void) { - uint64_t cr4; + uint64_t cr4 = KVM_ALWAYS_ALLOWED_CR4; - cr4 = X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE | - X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE | X86_CR4_PGE | - X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT; if (kvm_cpu_has(X86_FEATURE_UMIP)) cr4 |= X86_CR4_UMIP; if (kvm_cpu_has(X86_FEATURE_LA57)) @@ -72,36 +74,31 @@ static uint64_t calc_supported_cr4_feature_bits(void) return cr4; } -int main(int argc, char *argv[]) +static void test_cr_bits(struct kvm_vcpu *vcpu, uint64_t cr4) { struct kvm_sregs sregs; - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - uint64_t cr4; int rc, i; - /* - * Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and - * use it to verify all supported CR4 bits can be set prior to defining - * the vCPU model, i.e. without doing KVM_SET_CPUID2. - */ - vm = vm_create_barebones(); - vcpu = __vm_vcpu_add(vm, 0); - vcpu_sregs_get(vcpu, &sregs); - - sregs.cr0 = 0; - sregs.cr4 |= calc_supported_cr4_feature_bits(); - cr4 = sregs.cr4; - + sregs.cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + sregs.cr4 |= cr4; rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(!rc, "Failed to set supported CR4 bits (0x%lx)", cr4); + TEST_ASSERT(!!(sregs.cr4 & X86_CR4_OSXSAVE) == + (vcpu->cpuid && vcpu_cpuid_has(vcpu, X86_FEATURE_OSXSAVE)), + "KVM didn't %s OSXSAVE in CPUID as expected", + (sregs.cr4 & X86_CR4_OSXSAVE) ? "set" : "clear"); + + TEST_ASSERT(!!(sregs.cr4 & X86_CR4_PKE) == + (vcpu->cpuid && vcpu_cpuid_has(vcpu, X86_FEATURE_OSPKE)), + "KVM didn't %s OSPKE in CPUID as expected", + (sregs.cr4 & X86_CR4_PKE) ? "set" : "clear"); + vcpu_sregs_get(vcpu, &sregs); TEST_ASSERT(sregs.cr4 == cr4, "sregs.CR4 (0x%llx) != CR4 (0x%lx)", sregs.cr4, cr4); - /* Verify all unsupported features are rejected by KVM. */ TEST_INVALID_CR_BIT(vcpu, cr4, sregs, X86_CR4_UMIP); TEST_INVALID_CR_BIT(vcpu, cr4, sregs, X86_CR4_LA57); TEST_INVALID_CR_BIT(vcpu, cr4, sregs, X86_CR4_VMXE); @@ -119,10 +116,28 @@ int main(int argc, char *argv[]) /* NW without CD is illegal, as is PG without PE. */ TEST_INVALID_CR_BIT(vcpu, cr0, sregs, X86_CR0_NW); TEST_INVALID_CR_BIT(vcpu, cr0, sregs, X86_CR0_PG); +} +int main(int argc, char *argv[]) +{ + struct kvm_sregs sregs; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int rc; + + /* + * Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and + * use it to verify KVM enforces guest CPUID even if *userspace* never + * sets CPUID. + */ + vm = vm_create_barebones(); + vcpu = __vm_vcpu_add(vm, 0); + test_cr_bits(vcpu, KVM_ALWAYS_ALLOWED_CR4); kvm_vm_free(vm); - /* Create a "real" VM and verify APIC_BASE can be set. */ + /* Create a "real" VM with a fully populated guest CPUID and verify + * APIC_BASE and all supported CR4 can be set. + */ vm = vm_create_with_one_vcpu(&vcpu, NULL); vcpu_sregs_get(vcpu, &sregs); @@ -135,6 +150,8 @@ int main(int argc, char *argv[]) TEST_ASSERT(!rc, "Couldn't set IA32_APIC_BASE to %llx (valid)", sregs.apic_base); + test_cr_bits(vcpu, calc_supported_cr4_feature_bits()); + kvm_vm_free(vm); return 0; diff --git a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c b/tools/testing/selftests/kvm/x86/sev_init2_tests.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/sev_init2_tests.c rename to tools/testing/selftests/kvm/x86/sev_init2_tests.c diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c rename to tools/testing/selftests/kvm/x86/sev_migrate_tests.c diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c similarity index 99% rename from tools/testing/selftests/kvm/x86_64/sev_smoke_test.c rename to tools/testing/selftests/kvm/x86/sev_smoke_test.c index ae77698e6e97..a1a688e75266 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c @@ -155,7 +155,7 @@ static void guest_shutdown_code(void) /* Clobber the IDT so that #UD is guaranteed to trigger SHUTDOWN. */ memset(&idt, 0, sizeof(idt)); - __asm__ __volatile__("lidt %0" :: "m"(idt)); + set_idt(&idt); __asm__ __volatile__("ud2"); } diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c rename to tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/smm_test.c rename to tools/testing/selftests/kvm/x86/smm_test.c diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86/state_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/state_test.c rename to tools/testing/selftests/kvm/x86/state_test.c diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c rename to tools/testing/selftests/kvm/x86/svm_int_ctl_test.c diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c rename to tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c rename to tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86/svm_vmcall_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c rename to tools/testing/selftests/kvm/x86/svm_vmcall_test.c diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86/sync_regs_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/sync_regs_test.c rename to tools/testing/selftests/kvm/x86/sync_regs_test.c diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86/triple_fault_event_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c rename to tools/testing/selftests/kvm/x86/triple_fault_event_test.c diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86/tsc_msrs_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c rename to tools/testing/selftests/kvm/x86/tsc_msrs_test.c diff --git a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c rename to tools/testing/selftests/kvm/x86/tsc_scaling_sync.c diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86/ucna_injection_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/ucna_injection_test.c rename to tools/testing/selftests/kvm/x86/ucna_injection_test.c diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86/userspace_io_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/userspace_io_test.c rename to tools/testing/selftests/kvm/x86/userspace_io_test.c diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c rename to tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c rename to tools/testing/selftests/kvm/x86/vmx_apic_access_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c rename to tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c rename to tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c rename to tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c rename to tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c b/tools/testing/selftests/kvm/x86/vmx_msrs_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c rename to tools/testing/selftests/kvm/x86/vmx_msrs_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c rename to tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c rename to tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c rename to tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86/vmx_set_nested_state_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c rename to tools/testing/selftests/kvm/x86/vmx_set_nested_state_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c rename to tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c rename to tools/testing/selftests/kvm/x86/xapic_ipi_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86/xapic_state_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/xapic_state_test.c rename to tools/testing/selftests/kvm/x86/xapic_state_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c rename to tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c rename to tools/testing/selftests/kvm/x86/xen_shinfo_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86/xen_vmcall_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c rename to tools/testing/selftests/kvm/x86/xen_vmcall_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86/xss_msr_test.c similarity index 100% rename from tools/testing/selftests/kvm/x86_64/xss_msr_test.c rename to tools/testing/selftests/kvm/x86/xss_msr_test.c diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index 348e2dbdb4e0..5cb0828f0514 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -10,14 +10,14 @@ src_test := $(wildcard *_test.c) TEST_GEN_PROGS := $(src_test:.c=) -TEST_GEN_PROGS_EXTENDED := true +TEST_GEN_PROGS_EXTENDED := true sandbox-and-launch wait-pipe # Short targets: -$(TEST_GEN_PROGS): LDLIBS += -lcap +$(TEST_GEN_PROGS): LDLIBS += -lcap -lpthread $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static include ../lib.mk # Targets with $(OUTPUT)/ prefix: -$(TEST_GEN_PROGS): LDLIBS += -lcap +$(TEST_GEN_PROGS): LDLIBS += -lcap -lpthread $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 61056fa074bb..a604ea5d8297 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -9,17 +9,15 @@ #include <arpa/inet.h> #include <errno.h> -#include <linux/landlock.h> #include <linux/securebits.h> #include <sys/capability.h> #include <sys/socket.h> -#include <sys/syscall.h> -#include <sys/types.h> #include <sys/un.h> #include <sys/wait.h> #include <unistd.h> #include "../kselftest_harness.h" +#include "wrappers.h" #define TMP_DIR "tmp" @@ -30,33 +28,8 @@ /* TEST_F_FORK() should not be used for new tests. */ #define TEST_F_FORK(fixture_name, test_name) TEST_F(fixture_name, test_name) -#ifndef landlock_create_ruleset -static inline int -landlock_create_ruleset(const struct landlock_ruleset_attr *const attr, - const size_t size, const __u32 flags) -{ - return syscall(__NR_landlock_create_ruleset, attr, size, flags); -} -#endif - -#ifndef landlock_add_rule -static inline int landlock_add_rule(const int ruleset_fd, - const enum landlock_rule_type rule_type, - const void *const rule_attr, - const __u32 flags) -{ - return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type, rule_attr, - flags); -} -#endif - -#ifndef landlock_restrict_self -static inline int landlock_restrict_self(const int ruleset_fd, - const __u32 flags) -{ - return syscall(__NR_landlock_restrict_self, ruleset_fd, flags); -} -#endif +static const char bin_sandbox_and_launch[] = "./sandbox-and-launch"; +static const char bin_wait_pipe[] = "./wait-pipe"; static void _init_caps(struct __test_metadata *const _metadata, bool drop_all) { @@ -250,11 +223,6 @@ struct service_fixture { }; }; -static pid_t __maybe_unused sys_gettid(void) -{ - return syscall(__NR_gettid); -} - static void __maybe_unused set_unix_address(struct service_fixture *const srv, const unsigned short index) { diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 6788762188fe..aa6f2c1cbec7 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -37,6 +37,10 @@ #include <linux/fs.h> #include <linux/mount.h> +/* Defines AT_EXECVE_CHECK without type conflicts. */ +#define _ASM_GENERIC_FCNTL_H +#include <linux/fcntl.h> + #include "common.h" #ifndef renameat2 @@ -55,11 +59,17 @@ int open_tree(int dfd, const char *filename, unsigned int flags) } #endif +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + #ifndef RENAME_EXCHANGE #define RENAME_EXCHANGE (1 << 1) #endif -#define BINARY_PATH "./true" +static const char bin_true[] = "./true"; /* Paths (sibling number and depth) */ static const char dir_s1d1[] = TMP_DIR "/s1d1"; @@ -85,6 +95,9 @@ static const char file1_s3d1[] = TMP_DIR "/s3d1/f1"; /* dir_s3d2 is a mount point. */ static const char dir_s3d2[] = TMP_DIR "/s3d1/s3d2"; static const char dir_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3"; +static const char file1_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3/f1"; +static const char dir_s3d4[] = TMP_DIR "/s3d1/s3d2/s3d4"; +static const char file1_s3d4[] = TMP_DIR "/s3d1/s3d2/s3d4/f1"; /* * layout1 hierarchy: @@ -108,8 +121,11 @@ static const char dir_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3"; * │   └── f2 * └── s3d1 *    ├── f1 - * └── s3d2 - * └── s3d3 + * └── s3d2 [mount point] + *    ├── s3d3 + *    │ └── f1 + *    └── s3d4 + *    └── f1 */ static bool fgrep(FILE *const inf, const char *const str) @@ -358,7 +374,8 @@ static void create_layout1(struct __test_metadata *const _metadata) ASSERT_EQ(0, mount_opt(&mnt_tmp, dir_s3d2)); clear_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, mkdir(dir_s3d3, 0700)); + create_file(_metadata, file1_s3d3); + create_file(_metadata, file1_s3d4); } static void remove_layout1(struct __test_metadata *const _metadata) @@ -378,7 +395,8 @@ static void remove_layout1(struct __test_metadata *const _metadata) EXPECT_EQ(0, remove_path(dir_s2d2)); EXPECT_EQ(0, remove_path(file1_s3d1)); - EXPECT_EQ(0, remove_path(dir_s3d3)); + EXPECT_EQ(0, remove_path(file1_s3d3)); + EXPECT_EQ(0, remove_path(file1_s3d4)); set_cap(_metadata, CAP_SYS_ADMIN); umount(dir_s3d2); clear_cap(_metadata, CAP_SYS_ADMIN); @@ -1957,8 +1975,8 @@ TEST_F_FORK(layout1, relative_chroot_chdir) test_relative_path(_metadata, REL_CHROOT_CHDIR); } -static void copy_binary(struct __test_metadata *const _metadata, - const char *const dst_path) +static void copy_file(struct __test_metadata *const _metadata, + const char *const src_path, const char *const dst_path) { int dst_fd, src_fd; struct stat statbuf; @@ -1968,11 +1986,10 @@ static void copy_binary(struct __test_metadata *const _metadata, { TH_LOG("Failed to open \"%s\": %s", dst_path, strerror(errno)); } - src_fd = open(BINARY_PATH, O_RDONLY | O_CLOEXEC); + src_fd = open(src_path, O_RDONLY | O_CLOEXEC); ASSERT_LE(0, src_fd) { - TH_LOG("Failed to open \"" BINARY_PATH "\": %s", - strerror(errno)); + TH_LOG("Failed to open \"%s\": %s", src_path, strerror(errno)); } ASSERT_EQ(0, fstat(src_fd, &statbuf)); ASSERT_EQ(statbuf.st_size, @@ -2003,11 +2020,26 @@ static void test_execute(struct __test_metadata *const _metadata, const int err, ASSERT_EQ(1, WIFEXITED(status)); ASSERT_EQ(err ? 2 : 0, WEXITSTATUS(status)) { - TH_LOG("Unexpected return code for \"%s\": %s", path, - strerror(errno)); + TH_LOG("Unexpected return code for \"%s\"", path); }; } +static void test_check_exec(struct __test_metadata *const _metadata, + const int err, const char *const path) +{ + int ret; + char *const argv[] = { (char *)path, NULL }; + + ret = sys_execveat(AT_FDCWD, path, argv, NULL, + AT_EMPTY_PATH | AT_EXECVE_CHECK); + if (err) { + EXPECT_EQ(-1, ret); + EXPECT_EQ(errno, err); + } else { + EXPECT_EQ(0, ret); + } +} + TEST_F_FORK(layout1, execute) { const struct rule rules[] = { @@ -2021,9 +2053,13 @@ TEST_F_FORK(layout1, execute) create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); - copy_binary(_metadata, file1_s1d1); - copy_binary(_metadata, file1_s1d2); - copy_binary(_metadata, file1_s1d3); + copy_file(_metadata, bin_true, file1_s1d1); + copy_file(_metadata, bin_true, file1_s1d2); + copy_file(_metadata, bin_true, file1_s1d3); + + /* Checks before file1_s1d1 being denied. */ + test_execute(_metadata, 0, file1_s1d1); + test_check_exec(_metadata, 0, file1_s1d1); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -2031,14 +2067,94 @@ TEST_F_FORK(layout1, execute) ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY)); ASSERT_EQ(0, test_open(file1_s1d1, O_RDONLY)); test_execute(_metadata, EACCES, file1_s1d1); + test_check_exec(_metadata, EACCES, file1_s1d1); ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY)); ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY)); test_execute(_metadata, 0, file1_s1d2); + test_check_exec(_metadata, 0, file1_s1d2); ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY)); ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY)); test_execute(_metadata, 0, file1_s1d3); + test_check_exec(_metadata, 0, file1_s1d3); +} + +TEST_F_FORK(layout1, umount_sandboxer) +{ + int pipe_child[2], pipe_parent[2]; + char buf_parent; + pid_t child; + int status; + + copy_file(_metadata, bin_sandbox_and_launch, file1_s3d3); + ASSERT_EQ(0, pipe2(pipe_child, 0)); + ASSERT_EQ(0, pipe2(pipe_parent, 0)); + + child = fork(); + ASSERT_LE(0, child); + if (child == 0) { + char pipe_child_str[12], pipe_parent_str[12]; + char *const argv[] = { (char *)file1_s3d3, + (char *)bin_wait_pipe, pipe_child_str, + pipe_parent_str, NULL }; + + /* Passes the pipe FDs to the executed binary and its child. */ + EXPECT_EQ(0, close(pipe_child[0])); + EXPECT_EQ(0, close(pipe_parent[1])); + snprintf(pipe_child_str, sizeof(pipe_child_str), "%d", + pipe_child[1]); + snprintf(pipe_parent_str, sizeof(pipe_parent_str), "%d", + pipe_parent[0]); + + /* + * We need bin_sandbox_and_launch (copied inside the mount as + * file1_s3d3) to execute bin_wait_pipe (outside the mount) to + * make sure the mount point will not be EBUSY because of + * file1_s3d3 being in use. This avoids a potential race + * condition between the following read() and umount() calls. + */ + ASSERT_EQ(0, execve(argv[0], argv, NULL)) + { + TH_LOG("Failed to execute \"%s\": %s", argv[0], + strerror(errno)); + }; + _exit(1); + return; + } + + EXPECT_EQ(0, close(pipe_child[1])); + EXPECT_EQ(0, close(pipe_parent[0])); + + /* Waits for the child to sandbox itself. */ + EXPECT_EQ(1, read(pipe_child[0], &buf_parent, 1)); + + /* Tests that the sandboxer is tied to its mount point. */ + set_cap(_metadata, CAP_SYS_ADMIN); + EXPECT_EQ(-1, umount(dir_s3d2)); + EXPECT_EQ(EBUSY, errno); + clear_cap(_metadata, CAP_SYS_ADMIN); + + /* Signals the child to launch a grandchild. */ + EXPECT_EQ(1, write(pipe_parent[1], ".", 1)); + + /* Waits for the grandchild. */ + EXPECT_EQ(1, read(pipe_child[0], &buf_parent, 1)); + + /* Tests that the domain's sandboxer is not tied to its mount point. */ + set_cap(_metadata, CAP_SYS_ADMIN); + EXPECT_EQ(0, umount(dir_s3d2)) + { + TH_LOG("Failed to umount \"%s\": %s", dir_s3d2, + strerror(errno)); + }; + clear_cap(_metadata, CAP_SYS_ADMIN); + + /* Signals the grandchild to terminate. */ + EXPECT_EQ(1, write(pipe_parent[1], ".", 1)); + ASSERT_EQ(child, waitpid(child, &status, 0)); + ASSERT_EQ(1, WIFEXITED(status)); + ASSERT_EQ(0, WEXITSTATUS(status)); } TEST_F_FORK(layout1, link) @@ -2444,6 +2560,44 @@ TEST_F_FORK(layout1, refer_mount_root_deny) EXPECT_EQ(0, close(root_fd)); } +TEST_F_FORK(layout1, refer_part_mount_tree_is_allowed) +{ + const struct rule layer1[] = { + { + /* Parent mount point. */ + .path = dir_s3d1, + .access = LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_MAKE_REG, + }, + { + /* + * Removing the source file is allowed because its + * access rights are already a superset of the + * destination. + */ + .path = dir_s3d4, + .access = LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_MAKE_REG | + LANDLOCK_ACCESS_FS_REMOVE_FILE, + }, + {}, + }; + int ruleset_fd; + + ASSERT_EQ(0, unlink(file1_s3d3)); + ruleset_fd = create_ruleset(_metadata, + LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_MAKE_REG | + LANDLOCK_ACCESS_FS_REMOVE_FILE, + layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + ASSERT_EQ(0, rename(file1_s3d4, file1_s3d3)); +} + TEST_F_FORK(layout1, reparent_link) { const struct rule layer1[] = { diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c index a19db4d0b3bd..8f31b673ff2d 100644 --- a/tools/testing/selftests/landlock/ptrace_test.c +++ b/tools/testing/selftests/landlock/ptrace_test.c @@ -22,8 +22,6 @@ /* Copied from security/yama/yama_lsm.c */ #define YAMA_SCOPE_DISABLED 0 #define YAMA_SCOPE_RELATIONAL 1 -#define YAMA_SCOPE_CAPABILITY 2 -#define YAMA_SCOPE_NO_ATTACH 3 static void create_domain(struct __test_metadata *const _metadata) { diff --git a/tools/testing/selftests/landlock/sandbox-and-launch.c b/tools/testing/selftests/landlock/sandbox-and-launch.c new file mode 100644 index 000000000000..3e32e1a51ac5 --- /dev/null +++ b/tools/testing/selftests/landlock/sandbox-and-launch.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Sandbox itself and execute another program (in a different mount point). + * + * Used by layout1.umount_sandboxer from fs_test.c + * + * Copyright © 2024-2025 Microsoft Corporation + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/prctl.h> +#include <unistd.h> + +#include "wrappers.h" + +int main(int argc, char *argv[]) +{ + struct landlock_ruleset_attr ruleset_attr = { + .scoped = LANDLOCK_SCOPE_SIGNAL, + }; + int pipe_child, pipe_parent, ruleset_fd; + char buf; + + /* + * The first argument must be the file descriptor number of a pipe. + * The second argument must be the program to execute. + */ + if (argc != 4) { + fprintf(stderr, "Wrong number of arguments (not three)\n"); + return 1; + } + + pipe_child = atoi(argv[2]); + pipe_parent = atoi(argv[3]); + + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + if (ruleset_fd < 0) { + perror("Failed to create ruleset"); + return 1; + } + + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) { + perror("Failed to call prctl()"); + return 1; + } + + if (landlock_restrict_self(ruleset_fd, 0)) { + perror("Failed to restrict self"); + return 1; + } + + if (close(ruleset_fd)) { + perror("Failed to close ruleset"); + return 1; + } + + /* Signals that we are sandboxed. */ + errno = 0; + if (write(pipe_child, ".", 1) != 1) { + perror("Failed to write to the second argument"); + return 1; + } + + /* Waits for the parent to try to umount. */ + if (read(pipe_parent, &buf, 1) != 1) { + perror("Failed to write to the third argument"); + return 1; + } + + /* Shifts arguments. */ + argv[0] = argv[1]; + argv[1] = argv[2]; + argv[2] = argv[3]; + argv[3] = NULL; + execve(argv[0], argv, NULL); + perror("Failed to execute the provided binary"); + return 1; +} diff --git a/tools/testing/selftests/landlock/wait-pipe.c b/tools/testing/selftests/landlock/wait-pipe.c new file mode 100644 index 000000000000..0dbcd260a0fa --- /dev/null +++ b/tools/testing/selftests/landlock/wait-pipe.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Write in a pipe and wait. + * + * Used by layout1.umount_sandboxer from fs_test.c + * + * Copyright © 2024-2025 Microsoft Corporation + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +int main(int argc, char *argv[]) +{ + int pipe_child, pipe_parent; + char buf; + + /* The first argument must be the file descriptor number of a pipe. */ + if (argc != 3) { + fprintf(stderr, "Wrong number of arguments (not two)\n"); + return 1; + } + + pipe_child = atoi(argv[1]); + pipe_parent = atoi(argv[2]); + + /* Signals that we are waiting. */ + if (write(pipe_child, ".", 1) != 1) { + perror("Failed to write to first argument"); + return 1; + } + + /* Waits for the parent do its test. */ + if (read(pipe_parent, &buf, 1) != 1) { + perror("Failed to write to the second argument"); + return 1; + } + + return 0; +} diff --git a/tools/testing/selftests/landlock/wrappers.h b/tools/testing/selftests/landlock/wrappers.h new file mode 100644 index 000000000000..65548323e45d --- /dev/null +++ b/tools/testing/selftests/landlock/wrappers.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Syscall wrappers + * + * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> + * Copyright © 2019-2020 ANSSI + * Copyright © 2021-2025 Microsoft Corporation + */ + +#define _GNU_SOURCE +#include <linux/landlock.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <unistd.h> + +#ifndef landlock_create_ruleset +static inline int +landlock_create_ruleset(const struct landlock_ruleset_attr *const attr, + const size_t size, const __u32 flags) +{ + return syscall(__NR_landlock_create_ruleset, attr, size, flags); +} +#endif + +#ifndef landlock_add_rule +static inline int landlock_add_rule(const int ruleset_fd, + const enum landlock_rule_type rule_type, + const void *const rule_attr, + const __u32 flags) +{ + return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type, rule_attr, + flags); +} +#endif + +#ifndef landlock_restrict_self +static inline int landlock_restrict_self(const int ruleset_fd, + const __u32 flags) +{ + return syscall(__NR_landlock_restrict_self, ruleset_fd, flags); +} +#endif + +static inline pid_t sys_gettid(void) +{ + return syscall(__NR_gettid); +} diff --git a/tools/testing/selftests/livepatch/test-callbacks.sh b/tools/testing/selftests/livepatch/test-callbacks.sh index 37bbc3fb2780..2a03deb26a12 100755 --- a/tools/testing/selftests/livepatch/test-callbacks.sh +++ b/tools/testing/selftests/livepatch/test-callbacks.sh @@ -259,7 +259,7 @@ $MOD_TARGET: ${MOD_TARGET}_init % insmod test_modules/$MOD_LIVEPATCH.ko pre_patch_ret=-19 livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition -test_klp_callbacks_demo: pre_patch_callback: vmlinux +$MOD_LIVEPATCH: pre_patch_callback: vmlinux livepatch: pre-patch callback failed for object 'vmlinux' livepatch: failed to enable patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': canceling patching transition, going to unpatch diff --git a/tools/testing/selftests/livepatch/test-sysfs.sh b/tools/testing/selftests/livepatch/test-sysfs.sh index 2c91428d2997..58fe1d96997c 100755 --- a/tools/testing/selftests/livepatch/test-sysfs.sh +++ b/tools/testing/selftests/livepatch/test-sysfs.sh @@ -5,6 +5,8 @@ . $(dirname $0)/functions.sh MOD_LIVEPATCH=test_klp_livepatch +MOD_LIVEPATCH2=test_klp_callbacks_demo +MOD_LIVEPATCH3=test_klp_syscall setup_config @@ -19,6 +21,8 @@ check_sysfs_rights "$MOD_LIVEPATCH" "enabled" "-rw-r--r--" check_sysfs_value "$MOD_LIVEPATCH" "enabled" "1" check_sysfs_rights "$MOD_LIVEPATCH" "force" "--w-------" check_sysfs_rights "$MOD_LIVEPATCH" "replace" "-r--r--r--" +check_sysfs_rights "$MOD_LIVEPATCH" "stack_order" "-r--r--r--" +check_sysfs_value "$MOD_LIVEPATCH" "stack_order" "1" check_sysfs_rights "$MOD_LIVEPATCH" "transition" "-r--r--r--" check_sysfs_value "$MOD_LIVEPATCH" "transition" "0" check_sysfs_rights "$MOD_LIVEPATCH" "vmlinux/patched" "-r--r--r--" @@ -131,4 +135,71 @@ livepatch: '$MOD_LIVEPATCH': completing unpatching transition livepatch: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH" +start_test "sysfs test stack_order value" + +load_lp $MOD_LIVEPATCH + +check_sysfs_value "$MOD_LIVEPATCH" "stack_order" "1" + +load_lp $MOD_LIVEPATCH2 + +check_sysfs_value "$MOD_LIVEPATCH2" "stack_order" "2" + +load_lp $MOD_LIVEPATCH3 + +check_sysfs_value "$MOD_LIVEPATCH3" "stack_order" "3" + +disable_lp $MOD_LIVEPATCH2 +unload_lp $MOD_LIVEPATCH2 + +check_sysfs_value "$MOD_LIVEPATCH" "stack_order" "1" +check_sysfs_value "$MOD_LIVEPATCH3" "stack_order" "2" + +disable_lp $MOD_LIVEPATCH3 +unload_lp $MOD_LIVEPATCH3 + +disable_lp $MOD_LIVEPATCH +unload_lp $MOD_LIVEPATCH + +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko +livepatch: enabling patch '$MOD_LIVEPATCH' +livepatch: '$MOD_LIVEPATCH': initializing patching transition +livepatch: '$MOD_LIVEPATCH': starting patching transition +livepatch: '$MOD_LIVEPATCH': completing patching transition +livepatch: '$MOD_LIVEPATCH': patching complete +% insmod test_modules/$MOD_LIVEPATCH2.ko +livepatch: enabling patch '$MOD_LIVEPATCH2' +livepatch: '$MOD_LIVEPATCH2': initializing patching transition +$MOD_LIVEPATCH2: pre_patch_callback: vmlinux +livepatch: '$MOD_LIVEPATCH2': starting patching transition +livepatch: '$MOD_LIVEPATCH2': completing patching transition +$MOD_LIVEPATCH2: post_patch_callback: vmlinux +livepatch: '$MOD_LIVEPATCH2': patching complete +% insmod test_modules/$MOD_LIVEPATCH3.ko +livepatch: enabling patch '$MOD_LIVEPATCH3' +livepatch: '$MOD_LIVEPATCH3': initializing patching transition +livepatch: '$MOD_LIVEPATCH3': starting patching transition +livepatch: '$MOD_LIVEPATCH3': completing patching transition +livepatch: '$MOD_LIVEPATCH3': patching complete +% echo 0 > $SYSFS_KLP_DIR/$MOD_LIVEPATCH2/enabled +livepatch: '$MOD_LIVEPATCH2': initializing unpatching transition +$MOD_LIVEPATCH2: pre_unpatch_callback: vmlinux +livepatch: '$MOD_LIVEPATCH2': starting unpatching transition +livepatch: '$MOD_LIVEPATCH2': completing unpatching transition +$MOD_LIVEPATCH2: post_unpatch_callback: vmlinux +livepatch: '$MOD_LIVEPATCH2': unpatching complete +% rmmod $MOD_LIVEPATCH2 +% echo 0 > $SYSFS_KLP_DIR/$MOD_LIVEPATCH3/enabled +livepatch: '$MOD_LIVEPATCH3': initializing unpatching transition +livepatch: '$MOD_LIVEPATCH3': starting unpatching transition +livepatch: '$MOD_LIVEPATCH3': completing unpatching transition +livepatch: '$MOD_LIVEPATCH3': unpatching complete +% rmmod $MOD_LIVEPATCH3 +% echo 0 > $SYSFS_KLP_DIR/$MOD_LIVEPATCH/enabled +livepatch: '$MOD_LIVEPATCH': initializing unpatching transition +livepatch: '$MOD_LIVEPATCH': starting unpatching transition +livepatch: '$MOD_LIVEPATCH': completing unpatching transition +livepatch: '$MOD_LIVEPATCH': unpatching complete +% rmmod $MOD_LIVEPATCH" + exit 0 diff --git a/tools/testing/selftests/lsm/lsm_set_self_attr_test.c b/tools/testing/selftests/lsm/lsm_set_self_attr_test.c index 66dec47e3ca3..732e89fe99c0 100644 --- a/tools/testing/selftests/lsm/lsm_set_self_attr_test.c +++ b/tools/testing/selftests/lsm/lsm_set_self_attr_test.c @@ -56,16 +56,15 @@ TEST(flags_zero_lsm_set_self_attr) TEST(flags_overset_lsm_set_self_attr) { const long page_size = sysconf(_SC_PAGESIZE); - char *ctx = calloc(page_size, 1); + struct lsm_ctx *ctx = calloc(page_size, 1); __u32 size = page_size; - struct lsm_ctx *tctx = (struct lsm_ctx *)ctx; ASSERT_NE(NULL, ctx); if (attr_lsm_count()) { - ASSERT_LE(1, lsm_get_self_attr(LSM_ATTR_CURRENT, tctx, &size, + ASSERT_LE(1, lsm_get_self_attr(LSM_ATTR_CURRENT, ctx, &size, 0)); } - ASSERT_EQ(-1, lsm_set_self_attr(LSM_ATTR_CURRENT | LSM_ATTR_PREV, tctx, + ASSERT_EQ(-1, lsm_set_self_attr(LSM_ATTR_CURRENT | LSM_ATTR_PREV, ctx, size, 0)); free(ctx); diff --git a/tools/testing/selftests/media_tests/regression_test.txt b/tools/testing/selftests/media_tests/regression_test.txt index 2627367681f7..9d0fcd98c085 100644 --- a/tools/testing/selftests/media_tests/regression_test.txt +++ b/tools/testing/selftests/media_tests/regression_test.txt @@ -1,5 +1,5 @@ Testing for regressions in Media Controller API register, ioctl, syscall, -and unregister paths. There have a few problems that result in user-after +and unregister paths. There have a few problems that result in use-after free on media_device, media_devnode, and cdev pointers when the driver is unbound while ioctl is in progress. @@ -15,11 +15,11 @@ Build media_device_test cd tools/testing/selftests/media_tests make -Regressions test for cdev user-after free error on /dev/mediaX when driver +Regressions test for cdev use-after-free error on /dev/mediaX when driver is unbound: Start media_device_test to regression test media devnode dynamic alloc -and cdev user-after-free fixes. This opens media dev files and sits in +and cdev use-after-free fixes. This opens media dev files and sits in a loop running media ioctl MEDIA_IOC_DEVICE_INFO command once every 10 seconds. The idea is when device file goes away, media devnode and cdev should stick around until this test exits. @@ -40,4 +40,4 @@ keep ioctls going while bind/unbind runs. Copy bind_unbind_sample.txt and make changes to specify the driver name and number to run bind and unbind. Start the bind_unbind.sh -Run dmesg looking for any user-after free errors or mutex lock errors. +Run dmesg looking for any use-after-free errors or mutex lock errors. diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 95af2d78fd31..5b993924cc3f 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -9,6 +9,7 @@ #include <fcntl.h> #include <linux/memfd.h> #include <sched.h> +#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <signal.h> @@ -170,7 +171,7 @@ static void mfd_fail_new(const char *name, unsigned int flags) r = sys_memfd_create(name, flags); if (r >= 0) { printf("memfd_create(\"%s\", %u) succeeded, but failure expected\n", - name, flags); + name ? name : "NULL", flags); close(r); abort(); } @@ -281,6 +282,24 @@ static void *mfd_assert_mmap_shared(int fd) return p; } +static void *mfd_assert_mmap_read_shared(int fd) +{ + void *p; + + p = mmap(NULL, + mfd_def_size, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + static void *mfd_assert_mmap_private(int fd) { void *p; @@ -979,6 +998,30 @@ static void test_seal_future_write(void) close(fd); } +static void test_seal_write_map_read_shared(void) +{ + int fd; + void *p; + + printf("%s SEAL-WRITE-MAP-READ\n", memfd_str); + + fd = mfd_assert_new("kern_memfd_seal_write_map_read", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + + p = mfd_assert_mmap_read_shared(fd); + + mfd_assert_read(fd); + mfd_assert_read_shared(fd); + mfd_fail_write(fd); + + munmap(p, mfd_def_size); + close(fd); +} + /* * Test SEAL_SHRINK * Test whether SEAL_SHRINK actually prevents shrinking @@ -1557,6 +1600,11 @@ static void test_share_fork(char *banner, char *b_suffix) close(fd); } +static bool pid_ns_supported(void) +{ + return access("/proc/self/ns/pid", F_OK) == 0; +} + int main(int argc, char **argv) { pid_t pid; @@ -1587,12 +1635,17 @@ int main(int argc, char **argv) test_seal_write(); test_seal_future_write(); + test_seal_write_map_read_shared(); test_seal_shrink(); test_seal_grow(); test_seal_resize(); - test_sysctl_simple(); - test_sysctl_nested(); + if (pid_ns_supported()) { + test_sysctl_simple(); + test_sysctl_nested(); + } else { + printf("PID namespaces are not supported; skipping sysctl tests\n"); + } test_share_dup("SHARE-DUP", ""); test_share_mmap("SHARE-MMAP", ""); diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 8f01f4da1c0d..121000c28c10 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -27,6 +27,7 @@ protection_keys_64 madv_populate uffd-stress uffd-unit-tests +uffd-wp-mremap mlock-intersect-test mlock-random-test virtual_address_range @@ -36,6 +37,9 @@ map_fixed_noreplace write_to_hugetlbfs hmm-tests memfd_secret +hugetlb_dio +pkey_sighandler_tests_32 +pkey_sighandler_tests_64 soft-dirty split_huge_page_test ksm_tests @@ -49,7 +53,6 @@ va_high_addr_switch hugetlb_fault_after_madv hugetlb_madv_vs_map mseal_test -seal_elf droppable hugetlb_dio pkey_sighandler_tests_32 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 3de23ea4663f..63ce39d024bb 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -33,9 +33,16 @@ endif # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +CFLAGS = -Wall -O2 -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +# Some distributions (such as Ubuntu) configure GCC so that _FORTIFY_SOURCE is +# automatically enabled at -O1 or above. This triggers various unused-result +# warnings where functions such as read() or write() are called and their +# return value is not checked. Disable _FORTIFY_SOURCE to silence those +# warnings. +CFLAGS += -U_FORTIFY_SOURCE + KDIR ?= /lib/modules/$(shell uname -r)/build ifneq (,$(wildcard $(KDIR)/Module.symvers)) ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h)) @@ -75,13 +82,13 @@ TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test TEST_GEN_FILES += mseal_test -TEST_GEN_FILES += seal_elf TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress TEST_GEN_FILES += uffd-unit-tests +TEST_GEN_FILES += uffd-wp-mremap TEST_GEN_FILES += split_huge_page_test TEST_GEN_FILES += ksm_tests TEST_GEN_FILES += ksm_functional_tests @@ -152,11 +159,16 @@ $(TEST_GEN_FILES): vm_util.c thp_settings.c $(OUTPUT)/uffd-stress: uffd-common.c $(OUTPUT)/uffd-unit-tests: uffd-common.c +$(OUTPUT)/uffd-wp-mremap: uffd-common.c +$(OUTPUT)/protection_keys: pkey_util.c +$(OUTPUT)/pkey_sighandler_tests: pkey_util.c ifeq ($(ARCH),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) +$(BINARIES_32) $(BINARIES_64): pkey_util.c + define gen-target-rule-32 $(1) $(1)_32: $(OUTPUT)/$(1)_32 .PHONY: $(1) $(1)_32 diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config index 4309916f629e..a28baa536332 100644 --- a/tools/testing/selftests/mm/config +++ b/tools/testing/selftests/mm/config @@ -7,3 +7,4 @@ CONFIG_TEST_HMM=m CONFIG_GUP_TEST=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_MEM_SOFT_DIRTY=y +CONFIG_ANON_VMA_NAME=y diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 32c6ccc2a6be..9446673645eb 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -758,7 +758,7 @@ static void do_run_with_base_page(test_fn fn, bool swapout) } /* Populate a base page. */ - memset(mem, 0, pagesize); + memset(mem, 1, pagesize); if (swapout) { madvise(mem, pagesize, MADV_PAGEOUT); @@ -824,12 +824,12 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize) * Try to populate a THP. Touch the first sub-page and test if * we get the last sub-page populated automatically. */ - mem[0] = 0; + mem[0] = 1; if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { ksft_test_result_skip("Did not get a THP populated\n"); goto munmap; } - memset(mem, 0, thpsize); + memset(mem, 1, thpsize); size = thpsize; switch (thp_run) { @@ -1012,7 +1012,7 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize) } /* Populate an huge page. */ - memset(mem, 0, hugetlbsize); + memset(mem, 1, hugetlbsize); /* * We need a total of two hugetlb pages to handle COW/unsharing @@ -1482,7 +1482,7 @@ static void run_with_zeropage(non_anon_test_fn fn, const char *desc) } smem = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1583,7 +1583,7 @@ static void run_with_memfd(non_anon_test_fn fn, const char *desc) goto close; } smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1634,7 +1634,7 @@ static void run_with_tmpfile(non_anon_test_fn fn, const char *desc) goto close; } smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1684,7 +1684,7 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc, goto close; } smem = mmap(NULL, hugetlbsize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1696,7 +1696,7 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc, fn(mem, smem, hugetlbsize); munmap: munmap(mem, hugetlbsize); - if (mem != MAP_FAILED) + if (smem != MAP_FAILED) munmap(smem, hugetlbsize); close: close(fd); diff --git a/tools/testing/selftests/mm/guard-pages.c b/tools/testing/selftests/mm/guard-pages.c index 7cdf815d0d63..ece37212a8a2 100644 --- a/tools/testing/selftests/mm/guard-pages.c +++ b/tools/testing/selftests/mm/guard-pages.c @@ -55,6 +55,12 @@ static int pidfd_open(pid_t pid, unsigned int flags) return syscall(SYS_pidfd_open, pid, flags); } +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t n, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, n, advice, flags); +} + /* * Enable our signal catcher and try to read/write the specified buffer. The * return value indicates whether the read/write succeeds without a fatal @@ -419,7 +425,7 @@ TEST_F(guard_pages, process_madvise) ASSERT_EQ(munmap(&ptr_region[99 * page_size], page_size), 0); /* Now guard in one step. */ - count = process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0); + count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0); /* OK we don't have permission to do this, skip. */ if (count == -1 && errno == EPERM) @@ -440,7 +446,7 @@ TEST_F(guard_pages, process_madvise) ASSERT_FALSE(try_read_write_buf(&ptr3[19 * page_size])); /* Now do the same with unguard... */ - count = process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0); + count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0); /* ...and everything should now succeed. */ @@ -990,7 +996,7 @@ TEST_F(guard_pages, fork) MAP_ANON | MAP_PRIVATE, -1, 0); ASSERT_NE(ptr, MAP_FAILED); - /* Establish guard apges in the first 5 pages. */ + /* Establish guard pages in the first 5 pages. */ ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0); pid = fork(); @@ -1029,6 +1035,77 @@ TEST_F(guard_pages, fork) ASSERT_EQ(munmap(ptr, 10 * page_size), 0); } +/* + * Assert expected behaviour after we fork populated ranges of anonymous memory + * and then guard and unguard the range. + */ +TEST_F(guard_pages, fork_cow) +{ + const unsigned long page_size = self->page_size; + char *ptr; + pid_t pid; + int i; + + /* Map 10 pages. */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Populate range. */ + for (i = 0; i < 10 * page_size; i++) { + char chr = 'a' + (i % 26); + + ptr[i] = chr; + } + + pid = fork(); + ASSERT_NE(pid, -1); + if (!pid) { + /* This is the child process now. */ + + /* Ensure the range is as expected. */ + for (i = 0; i < 10 * page_size; i++) { + char expected = 'a' + (i % 26); + char actual = ptr[i]; + + ASSERT_EQ(actual, expected); + } + + /* Establish guard pages across the whole range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + /* Remove it. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* + * By removing the guard pages, the page tables will be + * cleared. Assert that we are looking at the zero page now. + */ + for (i = 0; i < 10 * page_size; i++) { + char actual = ptr[i]; + + ASSERT_EQ(actual, '\0'); + } + + exit(0); + } + + /* Parent process. */ + + /* Parent simply waits on child. */ + waitpid(pid, NULL, 0); + + /* Ensure the range is unchanged in parent anon range. */ + for (i = 0; i < 10 * page_size; i++) { + char expected = 'a' + (i % 26); + char actual = ptr[i]; + + ASSERT_EQ(actual, expected); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + /* * Assert that forking a process with VMAs that do have VM_WIPEONFORK set * behave as expected. diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index b748c48908d9..dcdd5bb20f3d 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -776,7 +776,7 @@ err_out: int main(int argc, char *argv[]) { - int ret, opt; + int ret = 0, opt; int prot = 0; int ksm_scan_limit_sec = KSM_SCAN_LIMIT_SEC_DEFAULT; int merge_type = KSM_MERGE_TYPE_DEFAULT; diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 64bcbb7151cf..1e3a595fbf01 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -204,4 +204,103 @@ TEST_F_TIMEOUT(migration, private_anon_thp, 2*RUNTIME) ASSERT_EQ(pthread_cancel(self->threads[i]), 0); } +/* + * migration test with shared anon THP page + */ + +TEST_F_TIMEOUT(migration, shared_anon_thp, 2*RUNTIME) +{ + pid_t pid; + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, 2 * TWOMEG, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + ptr = (uint64_t *) ALIGN((uintptr_t) ptr, TWOMEG); + ASSERT_EQ(madvise(ptr, TWOMEG, MADV_HUGEPAGE), 0); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) { + pid = fork(); + if (!pid) { + prctl(PR_SET_PDEATHSIG, SIGHUP); + /* Parent may have died before prctl so check now. */ + if (getppid() == 1) + kill(getpid(), SIGHUP); + access_mem(ptr); + } else { + self->pids[i] = pid; + } + } + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(kill(self->pids[i], SIGTERM), 0); +} + +/* + * migration test with private anon hugetlb page + */ +TEST_F_TIMEOUT(migration, private_anon_htlb, 2*RUNTIME) +{ + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) + if (pthread_create(&self->threads[i], NULL, access_mem, ptr)) + perror("Couldn't create thread"); + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(pthread_cancel(self->threads[i]), 0); +} + +/* + * migration test with shared anon hugetlb page + */ +TEST_F_TIMEOUT(migration, shared_anon_htlb, 2*RUNTIME) +{ + pid_t pid; + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) { + pid = fork(); + if (!pid) { + prctl(PR_SET_PDEATHSIG, SIGHUP); + /* Parent may have died before prctl so check now. */ + if (getppid() == 1) + kill(getpid(), SIGHUP); + access_mem(ptr); + } else { + self->pids[i] = pid; + } + } + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(kill(self->pids[i], SIGTERM), 0); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c index 1db134063c38..af2fce496912 100644 --- a/tools/testing/selftests/mm/mkdirty.c +++ b/tools/testing/selftests/mm/mkdirty.c @@ -280,6 +280,7 @@ static void test_uffdio_copy(void) dst = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE|MAP_ANON, -1, 0); if (dst == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); + free(src); return; } diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 5a3a9bcba640..bb84476a177f 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -34,7 +34,7 @@ struct config { unsigned long long dest_alignment; unsigned long long region_size; int overlapping; - int dest_preamble_size; + unsigned int dest_preamble_size; }; struct test { @@ -328,7 +328,7 @@ static void mremap_move_within_range(unsigned int pattern_seed, char *rand_addr) { char *test_name = "mremap mremap move within range"; void *src, *dest; - int i, success = 1; + unsigned int i, success = 1; size_t size = SIZE_MB(20); void *ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, @@ -384,7 +384,7 @@ out: static long long remap_region(struct config c, unsigned int threshold_mb, char *rand_addr) { - void *addr, *src_addr, *dest_addr, *dest_preamble_addr; + void *addr, *src_addr, *dest_addr, *dest_preamble_addr = NULL; unsigned long long t, d; struct timespec t_start = {0, 0}, t_end = {0, 0}; long long start_ns, end_ns, align_mask, ret, offset; @@ -569,7 +569,7 @@ static void mremap_move_1mb_from_start(unsigned int pattern_seed, { char *test_name = "mremap move 1mb from start at 1MB+256KB aligned src"; void *src = NULL, *dest = NULL; - int i, success = 1; + unsigned int i, success = 1; /* Config to reuse get_source_mapping() to do an aligned mmap. */ struct config c = { @@ -636,7 +636,7 @@ out: static void run_mremap_test_case(struct test test_case, int *failures, unsigned int threshold_mb, - unsigned int pattern_seed, char *rand_addr) + char *rand_addr) { long long remap_time = remap_region(test_case.config, threshold_mb, rand_addr); @@ -708,7 +708,8 @@ static int parse_args(int argc, char **argv, unsigned int *threshold_mb, int main(int argc, char **argv) { int failures = 0; - int i, run_perf_tests; + unsigned int i; + int run_perf_tests; unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD; /* hard-coded test configs */ @@ -831,7 +832,7 @@ int main(int argc, char **argv) for (i = 0; i < ARRAY_SIZE(test_cases); i++) run_mremap_test_case(test_cases[i], &failures, threshold_mb, - pattern_seed, rand_addr); + rand_addr); maps_fp = fopen("/proc/self/maps", "r"); @@ -853,7 +854,7 @@ int main(int argc, char **argv) "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:"); for (i = 0; i < ARRAY_SIZE(perf_test_cases); i++) run_mremap_test_case(perf_test_cases[i], &failures, - threshold_mb, pattern_seed, + threshold_mb, rand_addr); } diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c index 01675c412b2a..ad17005521a8 100644 --- a/tools/testing/selftests/mm/mseal_test.c +++ b/tools/testing/selftests/mm/mseal_test.c @@ -802,7 +802,7 @@ static void test_seal_mprotect_partial_mprotect_tail(bool seal) } -static void test_seal_mprotect_two_vma_with_gap(bool seal) +static void test_seal_mprotect_two_vma_with_gap(void) { void *ptr; unsigned long page_size = getpagesize(); @@ -1864,7 +1864,7 @@ static void test_seal_madvise_nodiscard(bool seal) REPORT_TEST_PASS(); } -int main(int argc, char **argv) +int main(void) { bool test_seal = seal_support(); @@ -1913,8 +1913,8 @@ int main(int argc, char **argv) test_seal_mprotect_partial_mprotect(false); test_seal_mprotect_partial_mprotect(true); - test_seal_mprotect_two_vma_with_gap(false); - test_seal_mprotect_two_vma_with_gap(true); + test_seal_mprotect_two_vma_with_gap(); + test_seal_mprotect_two_vma_with_gap(); test_seal_mprotect_merge(false); test_seal_mprotect_merge(true); diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index bcc73b4e805c..57b4bba2b45f 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -34,8 +34,8 @@ #define PAGEMAP "/proc/self/pagemap" int pagemap_fd; int uffd; -int page_size; -int hpage_size; +unsigned int page_size; +unsigned int hpage_size; const char *progname; #define LEN(region) ((region.end - region.start)/page_size) @@ -235,7 +235,9 @@ int get_reads(struct page_region *vec, int vec_size) int sanity_tests_sd(void) { - int mem_size, vec_size, ret, ret2, ret3, i, num_pages = 1000, total_pages = 0; + unsigned long long mem_size, vec_size, i, total_pages = 0; + long ret, ret2, ret3; + int num_pages = 1000; int total_writes, total_reads, reads, count; struct page_region *vec, *vec2; char *mem, *m[2]; @@ -321,9 +323,9 @@ int sanity_tests_sd(void) ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == mem_size/(page_size * 2), + ksft_test_result((unsigned long long)ret == mem_size/(page_size * 2), "%s Repeated pattern of written and non-written pages\n", __func__); /* 4. Repeated pattern of written and non-written pages in parts */ @@ -331,21 +333,21 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, num_pages/2 - 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ret2 = pagemap_ioctl(mem, mem_size, vec, 2, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret2 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno)); ret3 = pagemap_ioctl(mem, mem_size, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret3 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret3, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret3, errno, strerror(errno)); ksft_test_result((ret + ret3) == num_pages/2 && ret2 == 2, - "%s Repeated pattern of written and non-written pages in parts %d %d %d\n", + "%s Repeated pattern of written and non-written pages in parts %ld %ld %ld\n", __func__, ret, ret3, ret2); /* 5. Repeated pattern of written and non-written pages max_pages */ @@ -357,13 +359,13 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, num_pages/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ret2 = pagemap_ioctl(mem, mem_size, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret2 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno)); ksft_test_result(ret == num_pages/2 && ret2 == 1, "%s Repeated pattern of written and non-written pages max_pages\n", @@ -378,12 +380,12 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ret2 = pagemap_ioctl(mem, mem_size, vec2, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret2 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno)); ksft_test_result(ret == 1 && LEN(vec[0]) == 2 && vec[0].start == (uintptr_t)(mem + page_size) && @@ -416,7 +418,7 @@ int sanity_tests_sd(void) ret = pagemap_ioctl(m[1], mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && LEN(vec[0]) == mem_size/page_size, "%s Two regions\n", __func__); @@ -448,7 +450,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); for (i = 0; i < mem_size/page_size; i += 2) mem[i * page_size]++; @@ -457,7 +459,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); total_pages += ret; @@ -465,7 +467,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); total_pages += ret; @@ -473,7 +475,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); total_pages += ret; @@ -515,9 +517,9 @@ int sanity_tests_sd(void) vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); - if (ret > vec_size) + if ((unsigned long)ret > vec_size) break; reads = get_reads(vec, ret); @@ -554,63 +556,63 @@ int sanity_tests_sd(void) ret = pagemap_ioc(mem, 0, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 0 && walk_end == (long)mem, "Walk_end: Same start and end address\n"); ret = pagemap_ioc(mem, 0, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 0 && walk_end == (long)mem, "Walk_end: Same start and end with WP\n"); ret = pagemap_ioc(mem, 0, vec, 0, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 0 && walk_end == (long)mem, "Walk_end: Same start and end with 0 output buffer\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: Big vec\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: vec of minimum length\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, vec_size/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size/2), "Walk_end: Half max pages\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size), "Walk_end: 1 max page\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, -1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: max pages\n"); @@ -621,49 +623,49 @@ int sanity_tests_sd(void) ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_end sparse: Big vec\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2), "Walk_end sparse: vec of minimum length\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2), "Walk_end sparse: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size/2, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_end sparse: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_end sparse: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, vec_size/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_endsparse : Half max pages\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2), "Walk_end: 1 max page\n"); @@ -674,9 +676,10 @@ int sanity_tests_sd(void) return 0; } -int base_tests(char *prefix, char *mem, int mem_size, int skip) +int base_tests(char *prefix, char *mem, unsigned long long mem_size, int skip) { - int vec_size, written; + unsigned long long vec_size; + int written; struct page_region *vec, *vec2; if (skip) { @@ -799,8 +802,8 @@ int hpage_unit_tests(void) char *map; int ret, ret2; size_t num_pages = 10; - int map_size = hpage_size * num_pages; - int vec_size = map_size/page_size; + unsigned long long map_size = hpage_size * num_pages; + unsigned long long vec_size = map_size/page_size; struct page_region *vec, *vec2; vec = malloc(sizeof(struct page_region) * vec_size); @@ -1047,7 +1050,8 @@ static void test_simple(void) int sanity_tests(void) { - int mem_size, vec_size, ret, fd, i, buf_size; + unsigned long long mem_size, vec_size; + int ret, fd, i, buf_size; struct page_region *vec; char *mem, *fmem; struct stat sbuf; @@ -1312,7 +1316,9 @@ static ssize_t get_dirty_pages_reset(char *mem, unsigned int count, { struct pm_scan_arg arg = {0}; struct page_region rgns[256]; - int i, j, cnt, ret; + unsigned long long i, j; + long ret; + int cnt; arg.size = sizeof(struct pm_scan_arg); arg.start = (uintptr_t)mem; @@ -1330,7 +1336,7 @@ static ssize_t get_dirty_pages_reset(char *mem, unsigned int count, ksft_exit_fail_msg("ioctl failed\n"); cnt = 0; - for (i = 0; i < ret; ++i) { + for (i = 0; i < (unsigned long)ret; ++i) { if (rgns[i].categories != PAGE_IS_WRITTEN) ksft_exit_fail_msg("wrong flags\n"); @@ -1384,9 +1390,10 @@ void *thread_proc(void *mem) static void transact_test(int page_size) { unsigned int i, count, extra_pages; + unsigned int c; pthread_t th; char *mem; - int ret, c; + int ret; if (pthread_barrier_init(&start_barrier, NULL, nthreads + 1)) ksft_exit_fail_msg("pthread_barrier_init\n"); @@ -1405,9 +1412,9 @@ static void transact_test(int page_size) memset(mem, 0, 0x1000 * nthreads * pages_per_thread); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); - ksft_test_result(count > 0, "%s count %d\n", __func__, count); + ksft_test_result(count > 0, "%s count %u\n", __func__, count); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); - ksft_test_result(count == 0, "%s count %d\n", __func__, count); + ksft_test_result(count == 0, "%s count %u\n", __func__, count); finish = 0; for (i = 0; i < nthreads; ++i) @@ -1429,7 +1436,7 @@ static void transact_test(int page_size) ksft_exit_fail_msg("pthread_barrier_wait\n"); if (count > nthreads * access_per_thread) - ksft_exit_fail_msg("Too big count %d expected %d, iter %d\n", + ksft_exit_fail_msg("Too big count %u expected %u, iter %u\n", count, nthreads * access_per_thread, i); c = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); @@ -1454,7 +1461,7 @@ static void transact_test(int page_size) * access and application gets page fault again for the same write. */ if (count < nthreads * access_per_thread) { - ksft_test_result_fail("Lost update, iter %d, %d vs %d.\n", i, count, + ksft_test_result_fail("Lost update, iter %u, %u vs %u.\n", i, count, nthreads * access_per_thread); return; } @@ -1467,15 +1474,16 @@ static void transact_test(int page_size) finish = 1; pthread_barrier_wait(&end_barrier); - ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %d.\n", __func__, + ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %u.\n", __func__, extra_pages, 100.0 * extra_pages / (iter_count * nthreads * access_per_thread), extra_thread_faults); } -int main(int argc, char *argv[]) +int main(int __attribute__((unused)) argc, char *argv[]) { - int mem_size, shmid, buf_size, fd, i, ret; + int shmid, buf_size, fd, i, ret; + unsigned long long mem_size; char *mem, *map, *fmem; struct stat sbuf; diff --git a/tools/testing/selftests/mm/pkey-arm64.h b/tools/testing/selftests/mm/pkey-arm64.h index d9d2100eafc0..8e9685e03c44 100644 --- a/tools/testing/selftests/mm/pkey-arm64.h +++ b/tools/testing/selftests/mm/pkey-arm64.h @@ -30,7 +30,7 @@ #define NR_PKEYS 8 #define NR_RESERVED_PKEYS 1 /* pkey-0 */ -#define PKEY_ALLOW_ALL 0x77777777 +#define PKEY_REG_ALLOW_ALL 0x77777777 #define PKEY_REG_ALLOW_NONE 0x0 #define PKEY_BITS_PER_PKEY 4 @@ -81,11 +81,11 @@ static inline int get_arch_reserved_keys(void) return NR_RESERVED_PKEYS; } -void expect_fault_on_read_execonly_key(void *p1, int pkey) +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) { } -void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { return PTR_ERR_ENOTSUP; } diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index f7cfe163b0ff..f080e97b39be 100644 --- a/tools/testing/selftests/mm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h @@ -13,22 +13,22 @@ #include <ucontext.h> #include <sys/mman.h> +#include <linux/types.h> + #include "../kselftest.h" /* Define some kernel-like types */ -#define u8 __u8 -#define u16 __u16 -#define u32 __u32 -#define u64 __u64 +typedef __u8 u8; +typedef __u16 u16; +typedef __u32 u32; +typedef __u64 u64; #define PTR_ERR_ENOTSUP ((void *)-ENOTSUP) #ifndef DEBUG_LEVEL #define DEBUG_LEVEL 0 #endif -#define DPRINT_IN_SIGNAL_BUF_SIZE 4096 extern int dprint_in_signal; -extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; extern int test_nr; extern int iteration_nr; @@ -83,17 +83,18 @@ extern void abort_hooks(void); #ifndef noinline # define noinline __attribute__((noinline)) #endif +#ifndef __maybe_unused +# define __maybe_unused __attribute__((__unused__)) +#endif -noinline int read_ptr(int *ptr) -{ - /* Keep GCC from optimizing this away somehow */ - barrier(); - return *ptr; -} - -void expected_pkey_fault(int pkey); int sys_pkey_alloc(unsigned long flags, unsigned long init_val); int sys_pkey_free(unsigned long pkey); +int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey); + +/* For functions called from protection_keys.c only */ +noinline int read_ptr(int *ptr); +void expected_pkey_fault(int pkey); int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, unsigned long pkey); void record_pkey_malloc(void *ptr, long size, int prot); @@ -171,38 +172,6 @@ static inline void write_pkey_reg(u64 pkey_reg) pkey_reg, __read_pkey_reg()); } -/* - * These are technically racy. since something could - * change PKEY register between the read and the write. - */ -static inline void __pkey_access_allow(int pkey, int do_allow) -{ - u64 pkey_reg = read_pkey_reg(); - int bit = pkey * 2; - - if (do_allow) - pkey_reg &= (1<<bit); - else - pkey_reg |= (1<<bit); - - dprintf4("pkey_reg now: %016llx\n", read_pkey_reg()); - write_pkey_reg(pkey_reg); -} - -static inline void __pkey_write_allow(int pkey, int do_allow_write) -{ - u64 pkey_reg = read_pkey_reg(); - int bit = pkey * 2 + 1; - - if (do_allow_write) - pkey_reg &= (1<<bit); - else - pkey_reg |= (1<<bit); - - write_pkey_reg(pkey_reg); - dprintf4("pkey_reg now: %016llx\n", read_pkey_reg()); -} - #define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1)) #define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1)) #define ALIGN_PTR_UP(p, ptr_align_to) \ diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 3d0c0bdae5bc..1bad310d282a 100644 --- a/tools/testing/selftests/mm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h @@ -91,7 +91,7 @@ static inline int get_arch_reserved_keys(void) return NR_RESERVED_PKEYS_64K_3KEYS; } -void expect_fault_on_read_execonly_key(void *p1, int pkey) +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) { /* * powerpc does not allow userspace to change permissions of exec-only @@ -105,7 +105,7 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey) /* 4-byte instructions * 16384 = 64K page */ #define __page_o_noops() asm(".rept 16384 ; nop; .endr") -void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { void *ptr; int ret; diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h index ac91777c8917..f7ecd335df1e 100644 --- a/tools/testing/selftests/mm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h @@ -113,7 +113,7 @@ static inline u32 pkey_bit_position(int pkey) #define XSTATE_PKEY 0x200 #define XSTATE_BV_OFFSET 512 -int pkey_reg_xstate_offset(void) +static inline int pkey_reg_xstate_offset(void) { unsigned int eax; unsigned int ebx; @@ -148,7 +148,7 @@ static inline int get_arch_reserved_keys(void) return NR_RESERVED_PKEYS; } -void expect_fault_on_read_execonly_key(void *p1, int pkey) +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) { int ptr_contents; @@ -157,7 +157,7 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey) expected_pkey_fault(pkey); } -void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { return PTR_ERR_ENOTSUP; } diff --git a/tools/testing/selftests/mm/pkey_sighandler_tests.c b/tools/testing/selftests/mm/pkey_sighandler_tests.c index c593a426341c..1ac8c8809880 100644 --- a/tools/testing/selftests/mm/pkey_sighandler_tests.c +++ b/tools/testing/selftests/mm/pkey_sighandler_tests.c @@ -32,11 +32,9 @@ #define STACK_SIZE PTHREAD_STACK_MIN -void expected_pkey_fault(int pkey) {} - -pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER; -pthread_cond_t cond = PTHREAD_COND_INITIALIZER; -siginfo_t siginfo = {0}; +static pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER; +static pthread_cond_t cond = PTHREAD_COND_INITIALIZER; +static siginfo_t siginfo = {0}; /* * We need to use inline assembly instead of glibc's syscall because glibc's @@ -163,7 +161,7 @@ static void *thread_segv_with_pkey0_disabled(void *ptr) __write_pkey_reg(pkey_reg_restrictive_default()); /* Segfault (with SEGV_MAPERR) */ - *(int *) (0x1) = 1; + *(volatile int *)NULL = 1; return NULL; } @@ -179,7 +177,6 @@ static void *thread_segv_pkuerr_stack(void *ptr) static void *thread_segv_maperr_ptr(void *ptr) { stack_t *stack = ptr; - int *bad = (int *)1; u64 pkey_reg; /* @@ -195,7 +192,7 @@ static void *thread_segv_maperr_ptr(void *ptr) __write_pkey_reg(pkey_reg); /* Segfault */ - *bad = 1; + *(volatile int *)NULL = 1; syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); return NULL; } @@ -234,7 +231,7 @@ static void test_sigsegv_handler_with_pkey0_disabled(void) ksft_test_result(siginfo.si_signo == SIGSEGV && siginfo.si_code == SEGV_MAPERR && - siginfo.si_addr == (void *)1, + siginfo.si_addr == NULL, "%s\n", __func__); } @@ -314,11 +311,11 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) __write_pkey_reg(pkey_reg); /* Protect the new stack with MPK 1 */ - pkey = pkey_alloc(0, 0); - pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); + pkey = sys_pkey_alloc(0, 0); + sys_mprotect_pkey(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); /* Set up alternate signal stack that will use the default MPK */ - sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, + sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); sigstack.ss_flags = 0; sigstack.ss_size = STACK_SIZE; @@ -349,7 +346,7 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) ksft_test_result(siginfo.si_signo == SIGSEGV && siginfo.si_code == SEGV_MAPERR && - siginfo.si_addr == (void *)1, + siginfo.si_addr == NULL, "%s\n", __func__); } @@ -487,11 +484,11 @@ static void test_pkru_sigreturn(void) __write_pkey_reg(pkey_reg); /* Protect the stack with MPK 2 */ - pkey = pkey_alloc(0, 0); - pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); + pkey = sys_pkey_alloc(0, 0); + sys_mprotect_pkey(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); /* Set up alternate signal stack that will use the default MPK */ - sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, + sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); sigstack.ss_flags = 0; sigstack.ss_size = STACK_SIZE; @@ -538,6 +535,9 @@ int main(int argc, char *argv[]) ksft_print_header(); ksft_set_plan(ARRAY_SIZE(pkey_tests)); + if (!is_pkeys_supported()) + ksft_exit_skip("pkeys not supported\n"); + for (i = 0; i < ARRAY_SIZE(pkey_tests); i++) (*pkey_tests[i])(); diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c new file mode 100644 index 000000000000..ca4ad0d44ab2 --- /dev/null +++ b/tools/testing/selftests/mm/pkey_util.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <sys/syscall.h> +#include <unistd.h> + +#include "pkey-helpers.h" + +int sys_pkey_alloc(unsigned long flags, unsigned long init_val) +{ + int ret = syscall(SYS_pkey_alloc, flags, init_val); + dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n", + __func__, flags, init_val, ret, errno); + return ret; +} + +int sys_pkey_free(unsigned long pkey) +{ + int ret = syscall(SYS_pkey_free, pkey); + dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret); + return ret; +} + +int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey) +{ + int sret; + + dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__, + ptr, size, orig_prot, pkey); + + errno = 0; + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); + if (errno) { + dprintf2("SYS_mprotect_key sret: %d\n", sret); + dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); + dprintf2("SYS_mprotect_key failed, errno: %d\n", errno); + if (DEBUG_LEVEL >= 2) + perror("SYS_mprotect_pkey"); + } + return sret; +} diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 4990f7ab4cb7..a4683f2476f2 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -53,9 +53,15 @@ int test_nr; u64 shadow_pkey_reg; int dprint_in_signal; -char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; -void cat_into_file(char *str, char *file) +noinline int read_ptr(int *ptr) +{ + /* Keep GCC from optimizing this away somehow */ + barrier(); + return *ptr; +} + +static void cat_into_file(char *str, char *file) { int fd = open(file, O_RDWR); int ret; @@ -82,7 +88,7 @@ void cat_into_file(char *str, char *file) #if CONTROL_TRACING > 0 static int warned_tracing; -int tracing_root_ok(void) +static int tracing_root_ok(void) { if (geteuid() != 0) { if (!warned_tracing) @@ -95,7 +101,7 @@ int tracing_root_ok(void) } #endif -void tracing_on(void) +static void tracing_on(void) { #if CONTROL_TRACING > 0 #define TRACEDIR "/sys/kernel/tracing" @@ -119,7 +125,7 @@ void tracing_on(void) #endif } -void tracing_off(void) +static void tracing_off(void) { #if CONTROL_TRACING > 0 if (!tracing_root_ok()) @@ -153,7 +159,7 @@ __attribute__((__aligned__(65536))) #else __attribute__((__aligned__(PAGE_SIZE))) #endif -void lots_o_noops_around_write(int *write_to_me) +static void lots_o_noops_around_write(int *write_to_me) { dprintf3("running %s()\n", __func__); __page_o_noops(); @@ -164,7 +170,7 @@ void lots_o_noops_around_write(int *write_to_me) dprintf3("%s() done\n", __func__); } -void dump_mem(void *dumpme, int len_bytes) +static void dump_mem(void *dumpme, int len_bytes) { char *c = (void *)dumpme; int i; @@ -207,7 +213,7 @@ static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags) return 0; } -void pkey_disable_set(int pkey, int flags) +static void pkey_disable_set(int pkey, int flags) { unsigned long syscall_flags = 0; int ret; @@ -245,7 +251,7 @@ void pkey_disable_set(int pkey, int flags) pkey, flags); } -void pkey_disable_clear(int pkey, int flags) +static void pkey_disable_clear(int pkey, int flags) { unsigned long syscall_flags = 0; int ret; @@ -271,19 +277,19 @@ void pkey_disable_clear(int pkey, int flags) pkey, read_pkey_reg()); } -void pkey_write_allow(int pkey) +__maybe_unused static void pkey_write_allow(int pkey) { pkey_disable_clear(pkey, PKEY_DISABLE_WRITE); } -void pkey_write_deny(int pkey) +__maybe_unused static void pkey_write_deny(int pkey) { pkey_disable_set(pkey, PKEY_DISABLE_WRITE); } -void pkey_access_allow(int pkey) +__maybe_unused static void pkey_access_allow(int pkey) { pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS); } -void pkey_access_deny(int pkey) +__maybe_unused static void pkey_access_deny(int pkey) { pkey_disable_set(pkey, PKEY_DISABLE_ACCESS); } @@ -301,9 +307,9 @@ static char *si_code_str(int si_code) return "UNKNOWN"; } -int pkey_faults; -int last_si_pkey = -1; -void signal_handler(int signum, siginfo_t *si, void *vucontext) +static int pkey_faults; +static int last_si_pkey = -1; +static void signal_handler(int signum, siginfo_t *si, void *vucontext) { ucontext_t *uctxt = vucontext; int trapno; @@ -390,27 +396,21 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) /* restore access and let the faulting instruction continue */ pkey_access_allow(siginfo_pkey); #elif defined(__aarch64__) - aarch64_write_signal_pkey(uctxt, PKEY_ALLOW_ALL); + aarch64_write_signal_pkey(uctxt, PKEY_REG_ALLOW_ALL); #endif /* arch */ pkey_faults++; dprintf1("<<<<==================================================\n"); dprint_in_signal = 0; } -int wait_all_children(void) -{ - int status; - return waitpid(-1, &status, 0); -} - -void sig_chld(int x) +static void sig_chld(int x) { dprint_in_signal = 1; dprintf2("[%d] SIGCHLD: %d\n", getpid(), x); dprint_in_signal = 0; } -void setup_sigsegv_handler(void) +static void setup_sigsegv_handler(void) { int r, rs; struct sigaction newact; @@ -436,13 +436,13 @@ void setup_sigsegv_handler(void) pkey_assert(r == 0); } -void setup_handlers(void) +static void setup_handlers(void) { signal(SIGCHLD, &sig_chld); setup_sigsegv_handler(); } -pid_t fork_lazy_child(void) +static pid_t fork_lazy_child(void) { pid_t forkret; @@ -460,35 +460,7 @@ pid_t fork_lazy_child(void) return forkret; } -int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, - unsigned long pkey) -{ - int sret; - - dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__, - ptr, size, orig_prot, pkey); - - errno = 0; - sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); - if (errno) { - dprintf2("SYS_mprotect_key sret: %d\n", sret); - dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); - dprintf2("SYS_mprotect_key failed, errno: %d\n", errno); - if (DEBUG_LEVEL >= 2) - perror("SYS_mprotect_pkey"); - } - return sret; -} - -int sys_pkey_alloc(unsigned long flags, unsigned long init_val) -{ - int ret = syscall(SYS_pkey_alloc, flags, init_val); - dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n", - __func__, flags, init_val, ret, errno); - return ret; -} - -int alloc_pkey(void) +static int alloc_pkey(void) { int ret; unsigned long init_val = 0x0; @@ -534,19 +506,12 @@ int alloc_pkey(void) return ret; } -int sys_pkey_free(unsigned long pkey) -{ - int ret = syscall(SYS_pkey_free, pkey); - dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret); - return ret; -} - /* * I had a bug where pkey bits could be set by mprotect() but * not cleared. This ensures we get lots of random bit sets * and clears on the vma and pte pkey bits. */ -int alloc_random_pkey(void) +static int alloc_random_pkey(void) { int max_nr_pkey_allocs; int ret; @@ -629,7 +594,7 @@ struct pkey_malloc_record { }; struct pkey_malloc_record *pkey_malloc_records; struct pkey_malloc_record *pkey_last_malloc_record; -long nr_pkey_malloc_records; +static long nr_pkey_malloc_records; void record_pkey_malloc(void *ptr, long size, int prot) { long i; @@ -667,7 +632,7 @@ void record_pkey_malloc(void *ptr, long size, int prot) nr_pkey_malloc_records++; } -void free_pkey_malloc(void *ptr) +static void free_pkey_malloc(void *ptr) { long i; int ret; @@ -694,8 +659,7 @@ void free_pkey_malloc(void *ptr) pkey_assert(false); } - -void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) +static void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) { void *ptr; int ret; @@ -715,7 +679,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) return ptr; } -void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) +static void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) { int ret; void *ptr; @@ -745,10 +709,10 @@ void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) return ptr; } -int hugetlb_setup_ok; +static int hugetlb_setup_ok; #define SYSFS_FMT_NR_HUGE_PAGES "/sys/kernel/mm/hugepages/hugepages-%ldkB/nr_hugepages" #define GET_NR_HUGE_PAGES 10 -void setup_hugetlbfs(void) +static void setup_hugetlbfs(void) { int err; int fd; @@ -796,7 +760,7 @@ void setup_hugetlbfs(void) hugetlb_setup_ok = 1; } -void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) +static void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) { void *ptr; int flags = MAP_ANONYMOUS|MAP_PRIVATE|MAP_HUGETLB; @@ -817,42 +781,15 @@ void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) return ptr; } -void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey) -{ - void *ptr; - int fd; - - dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__, - size, prot, pkey); - pkey_assert(pkey < NR_PKEYS); - fd = open("/dax/foo", O_RDWR); - pkey_assert(fd >= 0); - - ptr = mmap(0, size, prot, MAP_SHARED, fd, 0); - pkey_assert(ptr != (void *)-1); - - mprotect_pkey(ptr, size, prot, pkey); - - record_pkey_malloc(ptr, size, prot); - - dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr); - close(fd); - return ptr; -} - -void *(*pkey_malloc[])(long size, int prot, u16 pkey) = { +static void *(*pkey_malloc[])(long size, int prot, u16 pkey) = { malloc_pkey_with_mprotect, malloc_pkey_with_mprotect_subpage, malloc_pkey_anon_huge, malloc_pkey_hugetlb -/* can not do direct with the pkey_mprotect() API: - malloc_pkey_mmap_direct, - malloc_pkey_mmap_dax, -*/ }; -void *malloc_pkey(long size, int prot, u16 pkey) +static void *malloc_pkey(long size, int prot, u16 pkey) { void *ret; static int malloc_type; @@ -882,7 +819,7 @@ void *malloc_pkey(long size, int prot, u16 pkey) return ret; } -int last_pkey_faults; +static int last_pkey_faults; #define UNKNOWN_PKEY -2 void expected_pkey_fault(int pkey) { @@ -905,7 +842,7 @@ void expected_pkey_fault(int pkey) */ if (__read_pkey_reg() != 0) #elif defined(__aarch64__) - if (__read_pkey_reg() != PKEY_ALLOW_ALL) + if (__read_pkey_reg() != PKEY_REG_ALLOW_ALL) #else if (__read_pkey_reg() != shadow_pkey_reg) #endif /* arch */ @@ -924,9 +861,9 @@ void expected_pkey_fault(int pkey) pkey_assert(last_pkey_faults == pkey_faults); \ } while (0) -int test_fds[10] = { -1 }; -int nr_test_fds; -void __save_test_fd(int fd) +static int test_fds[10] = { -1 }; +static int nr_test_fds; +static void __save_test_fd(int fd) { pkey_assert(fd >= 0); pkey_assert(nr_test_fds < ARRAY_SIZE(test_fds)); @@ -934,14 +871,14 @@ void __save_test_fd(int fd) nr_test_fds++; } -int get_test_read_fd(void) +static int get_test_read_fd(void) { int test_fd = open("/etc/passwd", O_RDONLY); __save_test_fd(test_fd); return test_fd; } -void close_test_fds(void) +static void close_test_fds(void) { int i; @@ -954,7 +891,7 @@ void close_test_fds(void) nr_test_fds = 0; } -void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) +static void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) { int i, err; int max_nr_pkey_allocs; @@ -1006,7 +943,7 @@ void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) pkey_assert(!err); } -void test_read_of_write_disabled_region(int *ptr, u16 pkey) +static void test_read_of_write_disabled_region(int *ptr, u16 pkey) { int ptr_contents; @@ -1016,7 +953,7 @@ void test_read_of_write_disabled_region(int *ptr, u16 pkey) dprintf1("*ptr: %d\n", ptr_contents); dprintf1("\n"); } -void test_read_of_access_disabled_region(int *ptr, u16 pkey) +static void test_read_of_access_disabled_region(int *ptr, u16 pkey) { int ptr_contents; @@ -1028,7 +965,7 @@ void test_read_of_access_disabled_region(int *ptr, u16 pkey) expected_pkey_fault(pkey); } -void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr, +static void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr, u16 pkey) { int ptr_contents; @@ -1045,7 +982,7 @@ void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr, expected_pkey_fault(pkey); } -void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr, +static void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr, u16 pkey) { *ptr = __LINE__; @@ -1056,14 +993,14 @@ void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr, expected_pkey_fault(pkey); } -void test_write_of_write_disabled_region(int *ptr, u16 pkey) +static void test_write_of_write_disabled_region(int *ptr, u16 pkey) { dprintf1("disabling write access to PKEY[%02d], doing write\n", pkey); pkey_write_deny(pkey); *ptr = __LINE__; expected_pkey_fault(pkey); } -void test_write_of_access_disabled_region(int *ptr, u16 pkey) +static void test_write_of_access_disabled_region(int *ptr, u16 pkey) { dprintf1("disabling access to PKEY[%02d], doing write\n", pkey); pkey_access_deny(pkey); @@ -1071,7 +1008,7 @@ void test_write_of_access_disabled_region(int *ptr, u16 pkey) expected_pkey_fault(pkey); } -void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr, +static void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr, u16 pkey) { *ptr = __LINE__; @@ -1082,7 +1019,7 @@ void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr, expected_pkey_fault(pkey); } -void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) +static void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) { int ret; int test_fd = get_test_read_fd(); @@ -1094,7 +1031,8 @@ void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) dprintf1("read ret: %d\n", ret); pkey_assert(ret); } -void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) + +static void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) { int ret; int test_fd = get_test_read_fd(); @@ -1107,7 +1045,7 @@ void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) pkey_assert(ret); } -void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) +static void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) { int pipe_ret, vmsplice_ret; struct iovec iov; @@ -1129,7 +1067,7 @@ void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) close(pipe_fds[1]); } -void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) +static void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) { int ignored = 0xdada; int futex_ret; @@ -1147,7 +1085,7 @@ void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) } /* Assumes that all pkeys other than 'pkey' are unallocated */ -void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) +static void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) { int err; int i; @@ -1170,7 +1108,7 @@ void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) } /* Assumes that all pkeys other than 'pkey' are unallocated */ -void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) +static void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) { int err; int bad_pkey = NR_PKEYS+99; @@ -1180,7 +1118,7 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) pkey_assert(err); } -void become_child(void) +static void become_child(void) { pid_t forkret; @@ -1196,7 +1134,7 @@ void become_child(void) } /* Assumes that all pkeys other than 'pkey' are unallocated */ -void test_pkey_alloc_exhaust(int *ptr, u16 pkey) +static void test_pkey_alloc_exhaust(int *ptr, u16 pkey) { int err; int allocated_pkeys[NR_PKEYS] = {0}; @@ -1263,7 +1201,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) } } -void arch_force_pkey_reg_init(void) +static void arch_force_pkey_reg_init(void) { #if defined(__i386__) || defined(__x86_64__) /* arch */ u64 *buf; @@ -1302,7 +1240,7 @@ void arch_force_pkey_reg_init(void) * a long-running test that continually checks the pkey * register. */ -void test_pkey_init_state(int *ptr, u16 pkey) +static void test_pkey_init_state(int *ptr, u16 pkey) { int err; int allocated_pkeys[NR_PKEYS] = {0}; @@ -1340,7 +1278,7 @@ void test_pkey_init_state(int *ptr, u16 pkey) * have to call pkey_alloc() to use it first. Make sure that it * is usable. */ -void test_mprotect_with_pkey_0(int *ptr, u16 pkey) +static void test_mprotect_with_pkey_0(int *ptr, u16 pkey) { long size; int prot; @@ -1364,7 +1302,7 @@ void test_mprotect_with_pkey_0(int *ptr, u16 pkey) mprotect_pkey(ptr, size, prot, pkey); } -void test_ptrace_of_child(int *ptr, u16 pkey) +static void test_ptrace_of_child(int *ptr, u16 pkey) { __attribute__((__unused__)) int peek_result; pid_t child_pid; @@ -1440,7 +1378,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey) free(plain_ptr_unaligned); } -void *get_pointer_to_instructions(void) +static void *get_pointer_to_instructions(void) { void *p1; @@ -1461,7 +1399,7 @@ void *get_pointer_to_instructions(void) return p1; } -void test_executing_on_unreadable_memory(int *ptr, u16 pkey) +static void test_executing_on_unreadable_memory(int *ptr, u16 pkey) { void *p1; int scratch; @@ -1493,7 +1431,7 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey) pkey_assert(!ret); } -void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) +static void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) { void *p1; int scratch; @@ -1542,7 +1480,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) } #if defined(__i386__) || defined(__x86_64__) -void test_ptrace_modifies_pkru(int *ptr, u16 pkey) +static void test_ptrace_modifies_pkru(int *ptr, u16 pkey) { u32 new_pkru; pid_t child; @@ -1665,7 +1603,7 @@ void test_ptrace_modifies_pkru(int *ptr, u16 pkey) #endif #if defined(__aarch64__) -void test_ptrace_modifies_pkru(int *ptr, u16 pkey) +static void test_ptrace_modifies_pkru(int *ptr, u16 pkey) { pid_t child; int status, ret; @@ -1742,7 +1680,7 @@ void test_ptrace_modifies_pkru(int *ptr, u16 pkey) } #endif -void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) +static void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) { int size = PAGE_SIZE; int sret; @@ -1756,7 +1694,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) pkey_assert(sret < 0); } -void (*pkey_tests[])(int *ptr, u16 pkey) = { +static void (*pkey_tests[])(int *ptr, u16 pkey) = { test_read_of_write_disabled_region, test_read_of_access_disabled_region, test_read_of_access_disabled_region_with_page_already_mapped, @@ -1782,7 +1720,7 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = { #endif }; -void run_tests_once(void) +static void run_tests_once(void) { int *ptr; int prot = PROT_READ|PROT_WRITE; @@ -1816,7 +1754,7 @@ void run_tests_once(void) iteration_nr++; } -void pkey_setup_shadow(void) +static void pkey_setup_shadow(void) { shadow_pkey_reg = __read_pkey_reg(); } diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 2fc290d9430c..333c468c2699 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -45,6 +45,8 @@ separated by spaces: vmalloc smoke tests - hmm hmm smoke tests +- madv_guard + test madvise(2) MADV_GUARD_INSTALL and MADV_GUARD_REMOVE options - madv_populate test memadvise(2) MADV_POPULATE_{READ,WRITE} options - memfd_secret @@ -307,6 +309,7 @@ CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 3 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem-private 20 16 +CATEGORY="userfaultfd" run_test ./uffd-wp-mremap #cleanup echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages @@ -375,6 +378,9 @@ CATEGORY="mremap" run_test ./mremap_dontunmap CATEGORY="hmm" run_test bash ./test_hmm.sh smoke +# MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests +CATEGORY="madv_guard" run_test ./guard-pages + # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c deleted file mode 100644 index d9f8ba8d5050..000000000000 --- a/tools/testing/selftests/mm/seal_elf.c +++ /dev/null @@ -1,137 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE -#include <sys/mman.h> -#include <stdint.h> -#include <asm-generic/unistd.h> -#include <string.h> -#include <sys/time.h> -#include <sys/resource.h> -#include <stdbool.h> -#include "../kselftest.h" -#include <syscall.h> -#include <errno.h> -#include <stdio.h> -#include <stdlib.h> -#include <fcntl.h> -#include <sys/ioctl.h> -#include <sys/vfs.h> -#include <sys/stat.h> -#include "mseal_helpers.h" - -/* - * define sys_xyx to call syscall directly. - */ -static int sys_mseal(void *start, size_t len) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mseal, start, len, 0); - return sret; -} - -static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mprotect, ptr, size, prot); - return sret; -} - -static bool seal_support(void) -{ - int ret; - void *ptr; - unsigned long page_size = getpagesize(); - - ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (ptr == (void *) -1) - return false; - - ret = sys_mseal(ptr, page_size); - if (ret < 0) - return false; - - return true; -} - -const char somestr[4096] = {"READONLY"}; - -static void test_seal_elf(void) -{ - int ret; - FILE *maps; - char line[512]; - uintptr_t addr_start, addr_end; - char prot[5]; - char filename[256]; - unsigned long page_size = getpagesize(); - unsigned long long ptr = (unsigned long long) somestr; - char *somestr2 = (char *)somestr; - - /* - * Modify the protection of readonly somestr - */ - if (((unsigned long long)ptr % page_size) != 0) - ptr = (unsigned long long)ptr & ~(page_size - 1); - - ksft_print_msg("somestr = %s\n", somestr); - ksft_print_msg("change protection to rw\n"); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE); - FAIL_TEST_IF_FALSE(!ret); - *somestr2 = 'A'; - ksft_print_msg("somestr is modified to: %s\n", somestr); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ); - FAIL_TEST_IF_FALSE(!ret); - - maps = fopen("/proc/self/maps", "r"); - FAIL_TEST_IF_FALSE(maps); - - /* - * apply sealing to elf binary - */ - while (fgets(line, sizeof(line), maps)) { - if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]", - &addr_start, &addr_end, prot, filename) == 4) { - if (strlen(filename)) { - /* - * seal the mapping if read only. - */ - if (strstr(prot, "r-")) { - ret = sys_mseal((void *)addr_start, addr_end - addr_start); - FAIL_TEST_IF_FALSE(!ret); - ksft_print_msg("sealed: %lx-%lx %s %s\n", - addr_start, addr_end, prot, filename); - if ((uintptr_t) somestr >= addr_start && - (uintptr_t) somestr <= addr_end) - ksft_print_msg("mapping for somestr found\n"); - } - } - } - } - fclose(maps); - - ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE); - FAIL_TEST_IF_FALSE(ret < 0); - ksft_print_msg("somestr is sealed, mprotect is rejected\n"); - - REPORT_TEST_PASS(); -} - -int main(int argc, char **argv) -{ - bool test_seal = seal_support(); - - ksft_print_header(); - ksft_print_msg("pid=%d\n", getpid()); - - if (!test_seal) - ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); - - ksft_set_plan(1); - - test_seal_elf(); - - ksft_finished(); -} diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index bdfa5d085f00..8e1462ce0532 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -128,7 +128,7 @@ static void test_mprotect(int pagemap_fd, int pagesize, bool anon) { const char *type[] = {"file", "anon"}; const char *fname = "./soft-dirty-test-file"; - int test_fd; + int test_fd = 0; char *map; if (anon) { diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index eb6d1b9fc362..3f353f3d070f 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -108,38 +108,28 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hp unsigned long rss_anon_before, rss_anon_after; size_t i; - if (!check_huge_anon(one_page, 4, pmd_pagesize)) { - printf("No THP is allocated\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 4, pmd_pagesize)) + ksft_exit_fail_msg("No THP is allocated\n"); rss_anon_before = rss_anon(); - if (!rss_anon_before) { - printf("No RssAnon is allocated before split\n"); - exit(EXIT_FAILURE); - } + if (!rss_anon_before) + ksft_exit_fail_msg("No RssAnon is allocated before split\n"); /* split all THPs */ write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, (uint64_t)one_page + len, 0); for (i = 0; i < len; i++) - if (one_page[i] != (char)0) { - printf("%ld byte corrupted\n", i); - exit(EXIT_FAILURE); - } + if (one_page[i] != (char)0) + ksft_exit_fail_msg("%ld byte corrupted\n", i); - if (!check_huge_anon(one_page, 0, pmd_pagesize)) { - printf("Still AnonHugePages not split\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 0, pmd_pagesize)) + ksft_exit_fail_msg("Still AnonHugePages not split\n"); rss_anon_after = rss_anon(); - if (rss_anon_after >= rss_anon_before) { - printf("Incorrect RssAnon value. Before: %ld After: %ld\n", + if (rss_anon_after >= rss_anon_before) + ksft_exit_fail_msg("Incorrect RssAnon value. Before: %ld After: %ld\n", rss_anon_before, rss_anon_after); - exit(EXIT_FAILURE); - } } void split_pmd_zero_pages(void) @@ -150,11 +140,11 @@ void split_pmd_zero_pages(void) one_page = allocate_zero_filled_hugepage(len); verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len); - printf("Split zero filled huge pages successful\n"); + ksft_test_result_pass("Split zero filled huge pages successful\n"); free(one_page); } -void split_pmd_thp(void) +void split_pmd_thp_to_order(int order) { char *one_page; size_t len = 4 * pmd_pagesize; @@ -174,7 +164,7 @@ void split_pmd_thp(void) /* split all THPs */ write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, - (uint64_t)one_page + len, 0); + (uint64_t)one_page + len, order); for (i = 0; i < len; i++) if (one_page[i] != (char)i) @@ -184,7 +174,7 @@ void split_pmd_thp(void) if (!check_huge_anon(one_page, 0, pmd_pagesize)) ksft_exit_fail_msg("Still AnonHugePages not split\n"); - ksft_test_result_pass("Split huge pages successful\n"); + ksft_test_result_pass("Split huge pages to order %d successful\n", order); free(one_page); } @@ -491,7 +481,7 @@ int main(int argc, char **argv) if (argc > 1) optional_xfs_path = argv[1]; - ksft_set_plan(3+9); + ksft_set_plan(1+8+2+9); pagesize = getpagesize(); pageshift = ffs(pagesize) - 1; @@ -502,7 +492,11 @@ int main(int argc, char **argv) fd_size = 2 * pmd_pagesize; split_pmd_zero_pages(); - split_pmd_thp(); + + for (i = 0; i < 9; i++) + if (i != 1) + split_pmd_thp_to_order(i); + split_pte_mapped_thp(); split_file_backed_thp(); diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c index 577eaab6266f..ad872af1c81a 100644 --- a/tools/testing/selftests/mm/thp_settings.c +++ b/tools/testing/selftests/mm/thp_settings.c @@ -87,7 +87,7 @@ int write_file(const char *path, const char *buf, size_t buflen) return (unsigned int) numwritten; } -const unsigned long read_num(const char *path) +unsigned long read_num(const char *path) { char buf[21]; @@ -172,7 +172,7 @@ void thp_write_string(const char *name, const char *val) } } -const unsigned long thp_read_num(const char *name) +unsigned long thp_read_num(const char *name) { char path[PATH_MAX]; int ret; diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h index 876235a23460..fc131d23d593 100644 --- a/tools/testing/selftests/mm/thp_settings.h +++ b/tools/testing/selftests/mm/thp_settings.h @@ -64,12 +64,12 @@ struct thp_settings { int read_file(const char *path, char *buf, size_t buflen); int write_file(const char *path, const char *buf, size_t buflen); -const unsigned long read_num(const char *path); +unsigned long read_num(const char *path); void write_num(const char *path, unsigned long num); int thp_read_string(const char *name, const char * const strings[]); void thp_write_string(const char *name, const char *val); -const unsigned long thp_read_num(const char *name); +unsigned long thp_read_num(const char *name); void thp_write_num(const char *name, unsigned long num); void thp_write_settings(struct thp_settings *settings); diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index a2e71b1636e7..9ff71fa1f9bf 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -1122,7 +1122,7 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, char c; unsigned long long count; struct uffd_args args = { 0 }; - char *orig_area_src, *orig_area_dst; + char *orig_area_src = NULL, *orig_area_dst = NULL; unsigned long step_size, step_count; unsigned long src_offs = 0; unsigned long dst_offs = 0; @@ -1190,7 +1190,7 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, nr, count, count_verify[src_offs + nr + i]); } } - if (step_size > page_size) { + if (chunk_size > page_size) { area_src = orig_area_src; area_dst = orig_area_dst; } diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c new file mode 100644 index 000000000000..2c4f984bd73c --- /dev/null +++ b/tools/testing/selftests/mm/uffd-wp-mremap.c @@ -0,0 +1,380 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define _GNU_SOURCE +#include <stdbool.h> +#include <stdint.h> +#include <fcntl.h> +#include <assert.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include "../kselftest.h" +#include "thp_settings.h" +#include "uffd-common.h" + +static int pagemap_fd; +static size_t pagesize; +static int nr_pagesizes = 1; +static int nr_thpsizes; +static size_t thpsizes[20]; +static int nr_hugetlbsizes; +static size_t hugetlbsizes[10]; + +static int sz2ord(size_t size) +{ + return __builtin_ctzll(size / pagesize); +} + +static int detect_thp_sizes(size_t sizes[], int max) +{ + int count = 0; + unsigned long orders; + size_t kb; + int i; + + /* thp not supported at all. */ + if (!read_pmd_pagesize()) + return 0; + + orders = thp_supported_orders(); + + for (i = 0; orders && count < max; i++) { + if (!(orders & (1UL << i))) + continue; + orders &= ~(1UL << i); + kb = (pagesize >> 10) << i; + sizes[count++] = kb * 1024; + ksft_print_msg("[INFO] detected THP size: %zu KiB\n", kb); + } + + return count; +} + +static void *mmap_aligned(size_t size, int prot, int flags) +{ + size_t mmap_size = size * 2; + char *mmap_mem, *mem; + + mmap_mem = mmap(NULL, mmap_size, prot, flags, -1, 0); + if (mmap_mem == MAP_FAILED) + return mmap_mem; + + mem = (char *)(((uintptr_t)mmap_mem + size - 1) & ~(size - 1)); + munmap(mmap_mem, mem - mmap_mem); + munmap(mem + size, mmap_mem + mmap_size - mem - size); + + return mem; +} + +static void *alloc_one_folio(size_t size, bool private, bool hugetlb) +{ + bool thp = !hugetlb && size > pagesize; + int flags = MAP_ANONYMOUS; + int prot = PROT_READ | PROT_WRITE; + char *mem, *addr; + + assert((size & (size - 1)) == 0); + + if (private) + flags |= MAP_PRIVATE; + else + flags |= MAP_SHARED; + + /* + * For THP, we must explicitly enable the THP size, allocate twice the + * required space then manually align. + */ + if (thp) { + struct thp_settings settings = *thp_current_settings(); + + if (private) + settings.hugepages[sz2ord(size)].enabled = THP_ALWAYS; + else + settings.shmem_hugepages[sz2ord(size)].enabled = SHMEM_ALWAYS; + + thp_push_settings(&settings); + + mem = mmap_aligned(size, prot, flags); + } else { + if (hugetlb) { + flags |= MAP_HUGETLB; + flags |= __builtin_ctzll(size) << MAP_HUGE_SHIFT; + } + + mem = mmap(NULL, size, prot, flags, -1, 0); + } + + if (mem == MAP_FAILED) { + mem = NULL; + goto out; + } + + assert(((uintptr_t)mem & (size - 1)) == 0); + + /* + * Populate the folio by writing the first byte and check that all pages + * are populated. Finally set the whole thing to non-zero data to avoid + * kernel from mapping it back to the zero page. + */ + mem[0] = 1; + for (addr = mem; addr < mem + size; addr += pagesize) { + if (!pagemap_is_populated(pagemap_fd, addr)) { + munmap(mem, size); + mem = NULL; + goto out; + } + } + memset(mem, 1, size); +out: + if (thp) + thp_pop_settings(); + + return mem; +} + +static bool check_uffd_wp_state(void *mem, size_t size, bool expect) +{ + uint64_t pte; + void *addr; + + for (addr = mem; addr < mem + size; addr += pagesize) { + pte = pagemap_get_entry(pagemap_fd, addr); + if (!!(pte & PM_UFFD_WP) != expect) { + ksft_test_result_fail("uffd-wp not %s for pte %lu!\n", + expect ? "set" : "clear", + (addr - mem) / pagesize); + return false; + } + } + + return true; +} + +static bool range_is_swapped(void *addr, size_t size) +{ + for (; size; addr += pagesize, size -= pagesize) + if (!pagemap_is_swapped(pagemap_fd, addr)) + return false; + return true; +} + +static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb) +{ + struct uffdio_writeprotect wp_prms; + uint64_t features = 0; + void *addr = NULL; + void *mem = NULL; + + assert(!(hugetlb && swapout)); + + ksft_print_msg("[RUN] %s(size=%zu, private=%s, swapout=%s, hugetlb=%s)\n", + __func__, + size, + private ? "true" : "false", + swapout ? "true" : "false", + hugetlb ? "true" : "false"); + + /* Allocate a folio of required size and type. */ + mem = alloc_one_folio(size, private, hugetlb); + if (!mem) { + ksft_test_result_fail("alloc_one_folio() failed\n"); + goto out; + } + + /* Register range for uffd-wp. */ + if (userfaultfd_open(&features)) { + ksft_test_result_fail("userfaultfd_open() failed\n"); + goto out; + } + if (uffd_register(uffd, mem, size, false, true, false)) { + ksft_test_result_fail("uffd_register() failed\n"); + goto out; + } + wp_prms.mode = UFFDIO_WRITEPROTECT_MODE_WP; + wp_prms.range.start = (uintptr_t)mem; + wp_prms.range.len = size; + if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp_prms)) { + ksft_test_result_fail("ioctl(UFFDIO_WRITEPROTECT) failed\n"); + goto out; + } + + if (swapout) { + madvise(mem, size, MADV_PAGEOUT); + if (!range_is_swapped(mem, size)) { + ksft_test_result_skip("MADV_PAGEOUT did not work, is swap enabled?\n"); + goto out; + } + } + + /* Check that uffd-wp is set for all PTEs in range. */ + if (!check_uffd_wp_state(mem, size, true)) + goto out; + + /* + * Move the mapping to a new, aligned location. Since + * UFFD_FEATURE_EVENT_REMAP is not set, we expect the uffd-wp bit for + * each PTE to be cleared in the new mapping. + */ + addr = mmap_aligned(size, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS); + if (addr == MAP_FAILED) { + ksft_test_result_fail("mmap_aligned() failed\n"); + goto out; + } + if (mremap(mem, size, size, MREMAP_FIXED | MREMAP_MAYMOVE, addr) == MAP_FAILED) { + ksft_test_result_fail("mremap() failed\n"); + munmap(addr, size); + goto out; + } + mem = addr; + + /* Check that uffd-wp is cleared for all PTEs in range. */ + if (!check_uffd_wp_state(mem, size, false)) + goto out; + + ksft_test_result_pass("%s(size=%zu, private=%s, swapout=%s, hugetlb=%s)\n", + __func__, + size, + private ? "true" : "false", + swapout ? "true" : "false", + hugetlb ? "true" : "false"); +out: + if (mem) + munmap(mem, size); + if (uffd >= 0) { + close(uffd); + uffd = -1; + } +} + +struct testcase { + size_t *sizes; + int *nr_sizes; + bool private; + bool swapout; + bool hugetlb; +}; + +static const struct testcase testcases[] = { + /* base pages. */ + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = false, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = true, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = false, + .swapout = true, + .hugetlb = false, + }, + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = true, + .swapout = true, + .hugetlb = false, + }, + + /* thp. */ + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = false, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = true, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = false, + .swapout = true, + .hugetlb = false, + }, + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = true, + .swapout = true, + .hugetlb = false, + }, + + /* hugetlb. */ + { + .sizes = hugetlbsizes, + .nr_sizes = &nr_hugetlbsizes, + .private = false, + .swapout = false, + .hugetlb = true, + }, + { + .sizes = hugetlbsizes, + .nr_sizes = &nr_hugetlbsizes, + .private = true, + .swapout = false, + .hugetlb = true, + }, +}; + +int main(int argc, char **argv) +{ + struct thp_settings settings; + int i, j, plan = 0; + + pagesize = getpagesize(); + nr_thpsizes = detect_thp_sizes(thpsizes, ARRAY_SIZE(thpsizes)); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); + + /* If THP is supported, save THP settings and initially disable THP. */ + if (nr_thpsizes) { + thp_save_settings(); + thp_read_settings(&settings); + for (i = 0; i < NR_ORDERS; i++) { + settings.hugepages[i].enabled = THP_NEVER; + settings.shmem_hugepages[i].enabled = SHMEM_NEVER; + } + thp_push_settings(&settings); + } + + for (i = 0; i < ARRAY_SIZE(testcases); i++) + plan += *testcases[i].nr_sizes; + ksft_set_plan(plan); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_fail_msg("opening pagemap failed\n"); + + for (i = 0; i < ARRAY_SIZE(testcases); i++) { + const struct testcase *tc = &testcases[i]; + + for (j = 0; j < *tc->nr_sizes; j++) + test_one_folio(tc->sizes[j], tc->private, tc->swapout, + tc->hugetlb); + } + + /* If THP is supported, restore original THP settings. */ + if (nr_thpsizes) + thp_restore_settings(); + + i = ksft_get_fail_cnt(); + if (i) + ksft_exit_fail_msg("%d out of %d tests failed\n", + i, ksft_test_num()); + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 2a2b69e91950..b380e102b22f 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -10,10 +10,12 @@ #include <string.h> #include <unistd.h> #include <errno.h> +#include <sys/prctl.h> #include <sys/mman.h> #include <sys/time.h> #include <fcntl.h> +#include "vm_util.h" #include "../kselftest.h" /* @@ -82,6 +84,24 @@ static void validate_addr(char *ptr, int high_addr) ksft_exit_fail_msg("Bad address %lx\n", addr); } +static void mark_range(char *ptr, size_t size) +{ + if (prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, ptr, size, "virtual_address_range") == -1) { + if (errno == EINVAL) { + /* Depends on CONFIG_ANON_VMA_NAME */ + ksft_test_result_skip("prctl(PR_SET_VMA_ANON_NAME) not supported\n"); + ksft_finished(); + } else { + ksft_exit_fail_perror("prctl(PR_SET_VMA_ANON_NAME) failed\n"); + } + } +} + +static int is_marked_vma(const char *vma_name) +{ + return vma_name && !strcmp(vma_name, "[anon:virtual_address_range]\n"); +} + static int validate_lower_address_hint(void) { char *ptr; @@ -116,12 +136,17 @@ static int validate_complete_va_space(void) prev_end_addr = 0; while (fgets(line, sizeof(line), file)) { + const char *vma_name = NULL; + int vma_name_start = 0; unsigned long hop; - if (sscanf(line, "%lx-%lx %s[rwxp-]", - &start_addr, &end_addr, prot) != 3) + if (sscanf(line, "%lx-%lx %4s %*s %*s %*s %n", + &start_addr, &end_addr, prot, &vma_name_start) != 3) ksft_exit_fail_msg("cannot parse /proc/self/maps\n"); + if (vma_name_start) + vma_name = line + vma_name_start; + /* end of userspace mappings; ignore vsyscall mapping */ if (start_addr & (1UL << 63)) return 0; @@ -135,6 +160,9 @@ static int validate_complete_va_space(void) if (prot[0] != 'r') continue; + if (check_vmflag_io((void *)start_addr)) + continue; + /* * Confirm whether MAP_CHUNK_SIZE chunk can be found or not. * If write succeeds, no need to check MAP_CHUNK_SIZE - 1 @@ -149,6 +177,9 @@ static int validate_complete_va_space(void) return 1; lseek(fd, 0, SEEK_SET); + if (is_marked_vma(vma_name)) + munmap((char *)(start_addr + hop), MAP_CHUNK_SIZE); + hop += MAP_CHUNK_SIZE; } } @@ -166,7 +197,7 @@ int main(int argc, char *argv[]) ksft_set_plan(1); for (i = 0; i < NR_CHUNKS_LOW; i++) { - ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (ptr[i] == MAP_FAILED) { @@ -175,6 +206,7 @@ int main(int argc, char *argv[]) break; } + mark_range(ptr[i], MAP_CHUNK_SIZE); validate_addr(ptr[i], 0); } lchunks = i; @@ -186,12 +218,13 @@ int main(int argc, char *argv[]) for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hint_addr(); - hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (hptr[i] == MAP_FAILED) break; + mark_range(ptr[i], MAP_CHUNK_SIZE); validate_addr(hptr[i], 1); } hchunks = i; diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index d8d0cf04bb57..a36734fb62f3 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -2,6 +2,7 @@ #include <string.h> #include <fcntl.h> #include <dirent.h> +#include <inttypes.h> #include <sys/ioctl.h> #include <linux/userfaultfd.h> #include <linux/fs.h> @@ -138,7 +139,7 @@ void clear_softdirty(void) ksft_exit_fail_msg("opening clear_refs failed\n"); ret = write(fd, ctrl, strlen(ctrl)); close(fd); - if (ret != strlen(ctrl)) + if (ret != (signed int)strlen(ctrl)) ksft_exit_fail_msg("writing clear_refs failed\n"); } @@ -193,13 +194,11 @@ err_out: return rss_anon; } -bool __check_huge(void *addr, char *pattern, int nr_hpages, - uint64_t hpage_size) +char *__get_smap_entry(void *addr, const char *pattern, char *buf, size_t len) { - uint64_t thp = -1; int ret; FILE *fp; - char buffer[MAX_LINE_LENGTH]; + char *entry = NULL; char addr_pattern[MAX_LINE_LENGTH]; ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", @@ -211,23 +210,40 @@ bool __check_huge(void *addr, char *pattern, int nr_hpages, if (!fp) ksft_exit_fail_msg("%s: Failed to open file %s\n", __func__, SMAP_FILE_PATH); - if (!check_for_pattern(fp, addr_pattern, buffer, sizeof(buffer))) + if (!check_for_pattern(fp, addr_pattern, buf, len)) goto err_out; - /* - * Fetch the pattern in the same block and check the number of - * hugepages. - */ - if (!check_for_pattern(fp, pattern, buffer, sizeof(buffer))) + /* Fetch the pattern in the same block */ + if (!check_for_pattern(fp, pattern, buf, len)) goto err_out; - snprintf(addr_pattern, MAX_LINE_LENGTH, "%s%%9ld kB", pattern); + /* Trim trailing newline */ + entry = strchr(buf, '\n'); + if (entry) + *entry = '\0'; - if (sscanf(buffer, addr_pattern, &thp) != 1) - ksft_exit_fail_msg("Reading smap error\n"); + entry = buf + strlen(pattern); err_out: fclose(fp); + return entry; +} + +bool __check_huge(void *addr, char *pattern, int nr_hpages, + uint64_t hpage_size) +{ + char buffer[MAX_LINE_LENGTH]; + uint64_t thp = -1; + char *entry; + + entry = __get_smap_entry(addr, pattern, buffer, sizeof(buffer)); + if (!entry) + goto err_out; + + if (sscanf(entry, "%9" SCNu64 " kB", &thp) != 1) + ksft_exit_fail_msg("Reading smap error\n"); + +err_out: return thp == (nr_hpages * (hpage_size >> 10)); } @@ -384,3 +400,27 @@ unsigned long get_free_hugepages(void) fclose(f); return fhp; } + +bool check_vmflag_io(void *addr) +{ + char buffer[MAX_LINE_LENGTH]; + const char *flags; + size_t flaglen; + + flags = __get_smap_entry(addr, "VmFlags:", buffer, sizeof(buffer)); + if (!flags) + ksft_exit_fail_msg("%s: No VmFlags for %p\n", __func__, addr); + + while (true) { + flags += strspn(flags, " "); + + flaglen = strcspn(flags, " "); + if (!flaglen) + return false; + + if (flaglen == strlen("io") && !memcmp(flags, "io", flaglen)) + return true; + + flags += flaglen; + } +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 2eaed8209925..b60ac68a9dc8 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -53,6 +53,7 @@ int uffd_unregister(int uffd, void *addr, uint64_t len); int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls); unsigned long get_free_hugepages(void); +bool check_vmflag_io(void *addr); /* * On ppc64 this will only work with radix 2M hugepage size diff --git a/tools/testing/selftests/mm/write_to_hugetlbfs.c b/tools/testing/selftests/mm/write_to_hugetlbfs.c index 1289d311efd7..34c91f7e6128 100644 --- a/tools/testing/selftests/mm/write_to_hugetlbfs.c +++ b/tools/testing/selftests/mm/write_to_hugetlbfs.c @@ -89,7 +89,7 @@ int main(int argc, char **argv) size = atoi(optarg); break; case 'p': - strncpy(path, optarg, sizeof(path)); + strncpy(path, optarg, sizeof(path) - 1); break; case 'm': if (atoi(optarg) >= MAX_METHOD) { diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index cb2fc601de66..73ee88d6b043 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -32,6 +32,7 @@ TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh +TEST_PROGS += cmsg_so_priority.sh TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh TEST_PROGS += netns-name.sh TEST_PROGS += nl_netdev.py @@ -95,6 +96,7 @@ TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += fdb_flush.sh fdb_notify.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh +TEST_PROGS += vlan_bridge_binding.sh TEST_PROGS += bpf_offload.py TEST_PROGS += ipv6_route_update_soft_lockup.sh TEST_PROGS += busy_poll_test.sh diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py index d10f420e4ef6..fd0d959914e4 100755 --- a/tools/testing/selftests/net/bpf_offload.py +++ b/tools/testing/selftests/net/bpf_offload.py @@ -215,12 +215,14 @@ def bpftool_map_list_wait(expected=0, n_retry=20, ns=""): raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps)) def bpftool_prog_load(sample, file_name, maps=[], prog_type="xdp", dev=None, - fail=True, include_stderr=False): + fail=True, include_stderr=False, dev_bind=None): args = "prog load %s %s" % (os.path.join(bpf_test_dir, sample), file_name) if prog_type is not None: args += " type " + prog_type if dev is not None: args += " dev " + dev + elif dev_bind is not None: + args += " xdpmeta_dev " + dev_bind if len(maps): args += " map " + " map ".join(maps) @@ -980,6 +982,16 @@ try: rm("/sys/fs/bpf/offload") sim.wait_for_flush() + bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/devbound", + dev_bind=sim['ifname']) + devbound = bpf_pinned("/sys/fs/bpf/devbound") + start_test("Test dev-bound program in generic mode...") + ret, _, err = sim.set_xdp(devbound, "generic", fail=False, include_stderr=True) + fail(ret == 0, "devbound program in generic mode allowed") + check_extack(err, "Can't attach device-bound programs in generic mode.", args) + rm("/sys/fs/bpf/devbound") + sim.wait_for_flush() + start_test("Test XDP load failure...") sim.dfs["dev/bpf_bind_verifier_accept"] = 0 ret, _, err = bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/offload", diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c index 99b0e8c17fca..04c7ff577bb8 100644 --- a/tools/testing/selftests/net/busy_poller.c +++ b/tools/testing/selftests/net/busy_poller.c @@ -54,16 +54,16 @@ struct epoll_params { #define EPIOCGPARAMS _IOR(EPOLL_IOC_TYPE, 0x02, struct epoll_params) #endif -static uint32_t cfg_port = 8000; +static uint16_t cfg_port = 8000; static struct in_addr cfg_bind_addr = { .s_addr = INADDR_ANY }; static char *cfg_outfile; static int cfg_max_events = 8; -static int cfg_ifindex; +static uint32_t cfg_ifindex; /* busy poll params */ static uint32_t cfg_busy_poll_usecs; -static uint32_t cfg_busy_poll_budget; -static uint32_t cfg_prefer_busy_poll; +static uint16_t cfg_busy_poll_budget; +static uint8_t cfg_prefer_busy_poll; /* IRQ params */ static uint32_t cfg_defer_hard_irqs; @@ -79,6 +79,7 @@ static void usage(const char *filepath) static void parse_opts(int argc, char **argv) { + unsigned long long tmp; int ret; int c; @@ -86,31 +87,40 @@ static void parse_opts(int argc, char **argv) usage(argv[0]); while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:")) != -1) { + /* most options take integer values, except o and b, so reduce + * code duplication a bit for the common case by calling + * strtoull here and leave bounds checking and casting per + * option below. + */ + if (c != 'o' && c != 'b') + tmp = strtoull(optarg, NULL, 0); + switch (c) { case 'u': - cfg_busy_poll_usecs = strtoul(optarg, NULL, 0); - if (cfg_busy_poll_usecs == ULONG_MAX || - cfg_busy_poll_usecs > UINT32_MAX) + if (tmp == ULLONG_MAX || tmp > UINT32_MAX) error(1, ERANGE, "busy_poll_usecs too large"); + + cfg_busy_poll_usecs = (uint32_t)tmp; break; case 'P': - cfg_prefer_busy_poll = strtoul(optarg, NULL, 0); - if (cfg_prefer_busy_poll == ULONG_MAX || - cfg_prefer_busy_poll > 1) + if (tmp == ULLONG_MAX || tmp > 1) error(1, ERANGE, "prefer busy poll should be 0 or 1"); + + cfg_prefer_busy_poll = (uint8_t)tmp; break; case 'g': - cfg_busy_poll_budget = strtoul(optarg, NULL, 0); - if (cfg_busy_poll_budget == ULONG_MAX || - cfg_busy_poll_budget > UINT16_MAX) + if (tmp == ULLONG_MAX || tmp > UINT16_MAX) error(1, ERANGE, "busy poll budget must be [0, UINT16_MAX]"); + + cfg_busy_poll_budget = (uint16_t)tmp; break; case 'p': - cfg_port = strtoul(optarg, NULL, 0); - if (cfg_port > UINT16_MAX) + if (tmp == ULLONG_MAX || tmp > UINT16_MAX) error(1, ERANGE, "port must be <= 65535"); + + cfg_port = (uint16_t)tmp; break; case 'b': ret = inet_aton(optarg, &cfg_bind_addr); @@ -124,41 +134,39 @@ static void parse_opts(int argc, char **argv) error(1, 0, "outfile invalid"); break; case 'm': - cfg_max_events = strtol(optarg, NULL, 0); - - if (cfg_max_events == LONG_MIN || - cfg_max_events == LONG_MAX || - cfg_max_events <= 0) + if (tmp == ULLONG_MAX || tmp > INT_MAX) error(1, ERANGE, - "max events must be > 0 and < LONG_MAX"); + "max events must be > 0 and <= INT_MAX"); + + cfg_max_events = (int)tmp; break; case 'd': - cfg_defer_hard_irqs = strtoul(optarg, NULL, 0); - - if (cfg_defer_hard_irqs == ULONG_MAX || - cfg_defer_hard_irqs > INT32_MAX) + if (tmp == ULLONG_MAX || tmp > INT32_MAX) error(1, ERANGE, "defer_hard_irqs must be <= INT32_MAX"); + + cfg_defer_hard_irqs = (uint32_t)tmp; break; case 'r': - cfg_gro_flush_timeout = strtoull(optarg, NULL, 0); - - if (cfg_gro_flush_timeout == ULLONG_MAX) + if (tmp == ULLONG_MAX || tmp > UINT64_MAX) error(1, ERANGE, - "gro_flush_timeout must be < ULLONG_MAX"); + "gro_flush_timeout must be < UINT64_MAX"); + + cfg_gro_flush_timeout = (uint64_t)tmp; break; case 's': - cfg_irq_suspend_timeout = strtoull(optarg, NULL, 0); - - if (cfg_irq_suspend_timeout == ULLONG_MAX) + if (tmp == ULLONG_MAX || tmp > UINT64_MAX) error(1, ERANGE, "irq_suspend_timeout must be < ULLONG_MAX"); + + cfg_irq_suspend_timeout = (uint64_t)tmp; break; case 'i': - cfg_ifindex = strtoul(optarg, NULL, 0); - if (cfg_ifindex == ULONG_MAX) + if (tmp == ULLONG_MAX || tmp > INT_MAX) error(1, ERANGE, - "ifindex must be < ULONG_MAX"); + "ifindex must be <= INT_MAX"); + + cfg_ifindex = (int)tmp; break; } } @@ -215,7 +223,7 @@ static void setup_queue(void) struct netdev_napi_set_req *set_req = NULL; struct ynl_sock *ys; struct ynl_error yerr; - uint32_t napi_id; + uint32_t napi_id = 0; ys = ynl_sock_create(&ynl_netdev_family, &yerr); if (!ys) @@ -277,8 +285,8 @@ static void run_poller(void) * here */ epoll_params.busy_poll_usecs = cfg_busy_poll_usecs; - epoll_params.busy_poll_budget = (uint16_t)cfg_busy_poll_budget; - epoll_params.prefer_busy_poll = (uint8_t)cfg_prefer_busy_poll; + epoll_params.busy_poll_budget = cfg_busy_poll_budget; + epoll_params.prefer_busy_poll = cfg_prefer_busy_poll; epoll_params.__pad = 0; val = 1; @@ -342,5 +350,9 @@ int main(int argc, char *argv[]) parse_opts(argc, argv); setup_queue(); run_poller(); + + if (cfg_outfile) + free(cfg_outfile); + return 0; } diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index 876c2db02a63..bc314382e4e1 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -59,6 +59,7 @@ struct options { unsigned int proto; } sock; struct option_cmsg_u32 mark; + struct option_cmsg_u32 priority; struct { bool ena; unsigned int delay; @@ -97,6 +98,8 @@ static void __attribute__((noreturn)) cs_usage(const char *bin) "\n" "\t\t-m val Set SO_MARK with given value\n" "\t\t-M val Set SO_MARK via setsockopt\n" + "\t\t-P val Set SO_PRIORITY via setsockopt\n" + "\t\t-Q val Set SO_PRIORITY via cmsg\n" "\t\t-d val Set SO_TXTIME with given delay (usec)\n" "\t\t-t Enable time stamp reporting\n" "\t\t-f val Set don't fragment via cmsg\n" @@ -115,7 +118,7 @@ static void cs_parse_args(int argc, char *argv[]) { int o; - while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:")) != -1) { + while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:Q:")) != -1) { switch (o) { case 's': opt.silent_send = true; @@ -148,6 +151,10 @@ static void cs_parse_args(int argc, char *argv[]) opt.mark.ena = true; opt.mark.val = atoi(optarg); break; + case 'Q': + opt.priority.ena = true; + opt.priority.val = atoi(optarg); + break; case 'M': opt.sockopt.mark = atoi(optarg); break; @@ -252,6 +259,8 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, SOL_SOCKET, SO_MARK, &opt.mark); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_SOCKET, SO_PRIORITY, &opt.priority); ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag); ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, diff --git a/tools/testing/selftests/net/cmsg_so_priority.sh b/tools/testing/selftests/net/cmsg_so_priority.sh new file mode 100755 index 000000000000..ee07d8653262 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_so_priority.sh @@ -0,0 +1,151 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +readonly KSFT_SKIP=4 + +IP4=192.0.2.1/24 +TGT4=192.0.2.2 +TGT4_RAW=192.0.2.3 +IP6=2001:db8::1/64 +TGT6=2001:db8::2 +TGT6_RAW=2001:db8::3 +PORT=1234 +TOTAL_TESTS=0 +FAILED_TESTS=0 + +if ! command -v jq &> /dev/null; then + echo "SKIP cmsg_so_priroity.sh test: jq is not installed." >&2 + exit "$KSFT_SKIP" +fi + +check_result() { + ((TOTAL_TESTS++)) + if [ "$1" -ne 0 ]; then + ((FAILED_TESTS++)) + fi +} + +cleanup() +{ + cleanup_ns $NS +} + +trap cleanup EXIT + +setup_ns NS + +create_filter() { + local handle=$1 + local vlan_prio=$2 + local ip_type=$3 + local proto=$4 + local dst_ip=$5 + local ip_proto + + if [[ "$proto" == "u" ]]; then + ip_proto="udp" + elif [[ "$ip_type" == "ipv4" && "$proto" == "i" ]]; then + ip_proto="icmp" + elif [[ "$ip_type" == "ipv6" && "$proto" == "i" ]]; then + ip_proto="icmpv6" + fi + + tc -n $NS filter add dev dummy1 \ + egress pref 1 handle "$handle" proto 802.1q \ + flower vlan_prio "$vlan_prio" vlan_ethtype "$ip_type" \ + dst_ip "$dst_ip" ${ip_proto:+ip_proto $ip_proto} \ + action pass +} + +ip -n $NS link set dev lo up +ip -n $NS link add name dummy1 up type dummy + +ip -n $NS link add link dummy1 name dummy1.10 up type vlan id 10 \ + egress-qos-map 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 + +ip -n $NS address add $IP4 dev dummy1.10 +ip -n $NS address add $IP6 dev dummy1.10 nodad + +ip netns exec $NS sysctl -wq net.ipv4.ping_group_range='0 2147483647' + +ip -n $NS neigh add $TGT4 lladdr 00:11:22:33:44:55 nud permanent \ + dev dummy1.10 +ip -n $NS neigh add $TGT6 lladdr 00:11:22:33:44:55 nud permanent \ + dev dummy1.10 +ip -n $NS neigh add $TGT4_RAW lladdr 00:11:22:33:44:66 nud permanent \ + dev dummy1.10 +ip -n $NS neigh add $TGT6_RAW lladdr 00:11:22:33:44:66 nud permanent \ + dev dummy1.10 + +tc -n $NS qdisc add dev dummy1 clsact + +FILTER_COUNTER=10 + +for i in 4 6; do + for proto in u i r; do + echo "Test IPV$i, prot: $proto" + for priority in {0..7}; do + if [[ $i == 4 && $proto == "r" ]]; then + TGT=$TGT4_RAW + elif [[ $i == 6 && $proto == "r" ]]; then + TGT=$TGT6_RAW + elif [ $i == 4 ]; then + TGT=$TGT4 + else + TGT=$TGT6 + fi + + handle="${FILTER_COUNTER}${priority}" + + create_filter $handle $priority ipv$i $proto $TGT + + pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \ + | jq ".[] | select(.options.handle == ${handle}) | \ + .options.actions[0].stats.packets") + + if [[ $pkts == 0 ]]; then + check_result 0 + else + echo "prio $priority: expected 0, got $pkts" + check_result 1 + fi + + ip netns exec $NS ./cmsg_sender -$i -Q $priority \ + -p $proto $TGT $PORT + + pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \ + | jq ".[] | select(.options.handle == ${handle}) | \ + .options.actions[0].stats.packets") + if [[ $pkts == 1 ]]; then + check_result 0 + else + echo "prio $priority -Q: expected 1, got $pkts" + check_result 1 + fi + + ip netns exec $NS ./cmsg_sender -$i -P $priority \ + -p $proto $TGT $PORT + + pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \ + | jq ".[] | select(.options.handle == ${handle}) | \ + .options.actions[0].stats.packets") + if [[ $pkts == 2 ]]; then + check_result 0 + else + echo "prio $priority -P: expected 2, got $pkts" + check_result 1 + fi + done + FILTER_COUNTER=$((FILTER_COUNTER + 10)) + done +done + +if [ $FAILED_TESTS -ne 0 ]; then + echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed" + exit 1 +else + echo "OK - All $TOTAL_TESTS tests passed" + exit 0 +fi diff --git a/tools/testing/selftests/net/cmsg_time.sh b/tools/testing/selftests/net/cmsg_time.sh index 1d7e756644bc..478af0aefa97 100755 --- a/tools/testing/selftests/net/cmsg_time.sh +++ b/tools/testing/selftests/net/cmsg_time.sh @@ -34,13 +34,28 @@ BAD=0 TOTAL=0 check_result() { + local ret=$1 + local got=$2 + local exp=$3 + local case=$4 + local xfail=$5 + local xf= + local inc= + + if [ "$xfail" == "xfail" ]; then + xf="(XFAIL)" + inc=0 + else + inc=1 + fi + ((TOTAL++)) - if [ $1 -ne 0 ]; then - echo " Case $4 returned $1, expected 0" - ((BAD++)) + if [ $ret -ne 0 ]; then + echo " Case $case returned $ret, expected 0 $xf" + ((BAD+=inc)) elif [ "$2" != "$3" ]; then - echo " Case $4 returned '$2', expected '$3'" - ((BAD++)) + echo " Case $case returned '$got', expected '$exp' $xf" + ((BAD+=inc)) fi } @@ -66,14 +81,14 @@ for i in "-4 $TGT4" "-6 $TGT6"; do awk '/SND/ { if ($3 > 1000) print "OK"; }') check_result $? "$ts" "OK" "$prot - TXTIME abs" - [ "$KSFT_MACHINE_SLOW" = yes ] && delay=8000 || delay=1000 + [ "$KSFT_MACHINE_SLOW" = yes ] && xfail=xfail - ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d $delay | + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d 1000 | awk '/SND/ {snd=$3} /SCHED/ {sch=$3} - END { if (snd - sch > '$((delay/2))') print "OK"; - else print snd, "-", sch, "<", '$((delay/2))'; }') - check_result $? "$ts" "OK" "$prot - TXTIME rel" + END { if (snd - sch > 500) print "OK"; + else print snd, "-", sch, "<", 500; }') + check_result $? "$ts" "OK" "$prot - TXTIME rel" $xfail done done diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh index c03151e7791c..c159230c9b62 100755 --- a/tools/testing/selftests/net/fdb_notify.sh +++ b/tools/testing/selftests/net/fdb_notify.sh @@ -49,7 +49,7 @@ test_dup_vxlan_self() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan" dev vx self dst 192.0.2.1 do_test_dup del "vxlan" dev vx self dst 192.0.2.1 @@ -59,7 +59,7 @@ test_dup_vxlan_master() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan master" dev vx master do_test_dup del "vxlan master" dev vx master @@ -79,7 +79,7 @@ test_dup_macvlan_master() ip_link_add br up type bridge vlan_filtering 1 ip_link_add dd up type dummy ip_link_add mv up link dd type macvlan mode passthru - ip_link_master mv br + ip_link_set_master mv br do_test_dup add "macvlan master" dev mv self do_test_dup del "macvlan master" dev mv self diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 1d58b3b87465..847936363a12 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -291,6 +291,37 @@ fib_rule6_test() "$getnomatch" "iif dscp redirect to table" \ "iif dscp no redirect to table" fi + + fib_check_iproute_support "flowlabel" "flowlabel" + if [ $? -eq 0 ]; then + match="flowlabel 0xfffff" + getmatch="flowlabel 0xfffff" + getnomatch="flowlabel 0xf" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "flowlabel redirect to table" \ + "flowlabel no redirect to table" + + match="flowlabel 0xfffff" + getmatch="from $SRC_IP6 iif $DEV flowlabel 0xfffff" + getnomatch="from $SRC_IP6 iif $DEV flowlabel 0xf" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "iif flowlabel redirect to table" \ + "iif flowlabel no redirect to table" + + match="flowlabel 0x08000/0x08000" + getmatch="flowlabel 0xfffff" + getnomatch="flowlabel 0xf7fff" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "flowlabel masked redirect to table" \ + "flowlabel masked no redirect to table" + + match="flowlabel 0x08000/0x08000" + getmatch="from $SRC_IP6 iif $DEV flowlabel 0xfffff" + getnomatch="from $SRC_IP6 iif $DEV flowlabel 0xf7fff" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "iif flowlabel masked redirect to table" \ + "iif flowlabel masked no redirect to table" + fi } fib_rule6_vrf_test() diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 7d885cff8d79..00bde7b6f39e 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -105,6 +105,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ + vxlan_reserved.sh \ vxlan_symmetric_ipv6.sh \ vxlan_symmetric.sh diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh index 1c8a26046589..2b5700b61ffa 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh @@ -1,7 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding" +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding pvid_change" NUM_NETIFS=4 source lib.sh @@ -77,12 +77,16 @@ cleanup() ping_ipv4() { - ping_test $h1 192.0.2.2 + local msg=$1 + + ping_test $h1 192.0.2.2 "$msg" } ping_ipv6() { - ping6_test $h1 2001:db8:1::2 + local msg=$1 + + ping6_test $h1 2001:db8:1::2 "$msg" } learning() @@ -95,6 +99,21 @@ flooding() flood_test $swp2 $h1 $h2 } +pvid_change() +{ + # Test that the changing of the VLAN-aware PVID does not affect + # VLAN-unaware forwarding + bridge vlan add vid 3 dev $swp1 pvid untagged + + ping_ipv4 " with bridge port $swp1 PVID changed" + ping_ipv6 " with bridge port $swp1 PVID changed" + + bridge vlan del vid 3 dev $swp1 + + ping_ipv4 " with bridge port $swp1 PVID deleted" + ping_ipv6 " with bridge port $swp1 PVID deleted" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7337f398f9cc..8de80acf249e 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -68,6 +68,7 @@ declare -A NETIFS=( : "${REQUIRE_JQ:=yes}" : "${REQUIRE_MZ:=yes}" : "${REQUIRE_MTOOLS:=no}" +: "${REQUIRE_TEAMD:=no}" # Whether to override MAC addresses on interfaces participating in the test. : "${STABLE_MAC_ADDRS:=no}" @@ -321,6 +322,9 @@ fi if [[ "$REQUIRE_MZ" = "yes" ]]; then require_command $MZ fi +if [[ "$REQUIRE_TEAMD" = "yes" ]]; then + require_command $TEAMD +fi if [[ "$REQUIRE_MTOOLS" = "yes" ]]; then # https://github.com/troglobit/mtools require_command msend @@ -932,13 +936,6 @@ packets_rate() echo $(((t1 - t0) / interval)) } -mac_get() -{ - local if_name=$1 - - ip -j link show dev $if_name | jq -r '.[]["address"]' -} - ether_addr_to_u64() { local addr="$1" diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index c35548767756..ecd34f364125 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -7,7 +7,6 @@ ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \ NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes -REQUIRE_MZ=no source lib.sh diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh index fe4d7c906a70..a20d22d1df36 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -49,6 +49,7 @@ ALL_TESTS=" test_mirror_gretap_second " +REQUIRE_TEAMD="yes" NUM_NETIFS=6 source lib.sh source mirror_lib.sh diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh index 1261e6f46e34..ff7049582d35 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh @@ -53,6 +53,7 @@ ALL_TESTS=" test_mirror_gretap_second " +REQUIRE_TEAMD="yes" NUM_NETIFS=6 source lib.sh source mirror_lib.sh diff --git a/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh index e064b946e821..16583a470ec3 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh @@ -109,6 +109,7 @@ ALL_TESTS=" ping_ipv4 ping_ipv6 " +REQUIRE_TEAMD="yes" NUM_NETIFS=8 source lib.sh diff --git a/tools/testing/selftests/net/forwarding/router_bridge_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh index f05ffe213c46..2a4cd1af1b85 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_lag.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh @@ -76,6 +76,7 @@ ping_ipv4 ping_ipv6 "} +REQUIRE_TEAMD="yes" NUM_NETIFS=8 : ${lib_dir:=.} source $lib_dir/lib.sh diff --git a/tools/testing/selftests/net/forwarding/vxlan_reserved.sh b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh new file mode 100755 index 000000000000..46c31794b91b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh @@ -0,0 +1,352 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|---------------+ +# | +# +----|--------------------------------+ +# | SW | | +# | +--|------------------------------+ | +# | | + $swp1 BR1 (802.1d) | | +# | | | | +# | | + vx1 (vxlan) | | +# | | local 192.0.2.17 | | +# | | id 1000 dstport $VXPORT | | +# | +---------------------------------+ | +# | | +# | 192.0.2.32/28 via 192.0.2.18 | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +--|----------------------------------+ +# | +# +--|----------------------------------+ +# | | | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | +# | VRP2 (vrf) | +# +-------------------------------------+ + +: ${VXPORT:=4789} +: ${ALL_TESTS:=" + default_test + plain_test + reserved_0_test + reserved_10_test + reserved_31_test + reserved_56_test + reserved_63_test + "} + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 + defer simple_if_fini $h1 192.0.2.1/28 + + tc qdisc add dev $h1 clsact + defer tc qdisc del dev $h1 clsact + + tc filter add dev $h1 ingress pref 77 \ + prot ip flower skip_hw ip_proto icmp action drop + defer tc filter del dev $h1 ingress pref 77 +} + +switch_create() +{ + ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip_link_set_addr br1 $(mac_get $swp1) + ip_link_set_up br1 + + ip_link_set_up $rp1 + ip_addr_add $rp1 192.0.2.17/28 + ip_route_add 192.0.2.32/28 nexthop via 192.0.2.18 + + ip_link_set_master $swp1 br1 + ip_link_set_up $swp1 +} + +vrp2_create() +{ + simple_if_init $rp2 192.0.2.18/28 + defer simple_if_fini $rp2 192.0.2.18/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + vrf_prepare + defer vrf_cleanup + + forwarding_enable + defer forwarding_restore + + h1_create + switch_create + + vrp2_create +} + +vxlan_header_bytes() +{ + local vni=$1; shift + local -a extra_bits=("$@") + local -a bits + local i + + for ((i=0; i < 64; i++)); do + bits[i]=0 + done + + # Bit 4 is the I flag and is always on. + bits[4]=1 + + for i in ${extra_bits[@]}; do + bits[i]=1 + done + + # Bits 32..55 carry the VNI + local mask=0x800000 + for ((i=0; i < 24; i++)); do + bits[$((i + 32))]=$(((vni & mask) != 0)) + ((mask >>= 1)) + done + + local bytes + for ((i=0; i < 8; i++)); do + local byte=0 + local j + for ((j=0; j < 8; j++)); do + local bit=${bits[8 * i + j]} + ((byte += bit << (7 - j))) + done + bytes+=$(printf %02x $byte): + done + + echo ${bytes%:} +} + +neg_bytes() +{ + local bytes=$1; shift + + local -A neg=([0]=f [1]=e [2]=d [3]=c [4]=b [5]=a [6]=9 [7]=8 + [8]=7 [9]=6 [a]=5 [b]=4 [c]=3 [d]=2 [e]=1 [f]=0 [:]=:) + local out + local i + + for ((i=0; i < ${#bytes}; i++)); do + local c=${bytes:$i:1} + out+=${neg[$c]} + done + echo $out +} + +vxlan_ping_do() +{ + local count=$1; shift + local dev=$1; shift + local next_hop_mac=$1; shift + local dest_ip=$1; shift + local dest_mac=$1; shift + local vni=$1; shift + local reserved_bits=$1; shift + + local vxlan_header=$(vxlan_header_bytes $vni $reserved_bits) + + $MZ $dev -c $count -d 100msec -q \ + -b $next_hop_mac -B $dest_ip \ + -t udp sp=23456,dp=$VXPORT,p=$(: + )"$vxlan_header:"$( : VXLAN + )"$dest_mac:"$( : ETH daddr + )"00:11:22:33:44:55:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:54:"$( : IP total length + )"99:83:"$( : IP identification + )"40:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"01:"$( : IP proto + )"00:00:"$( : IP header csum + )"$(ipv4_to_bytes 192.0.2.3):"$( : IP saddr + )"$(ipv4_to_bytes 192.0.2.1):"$( : IP daddr + )"08:"$( : ICMP type + )"00:"$( : ICMP code + )"8b:f2:"$( : ICMP csum + )"1f:6a:"$( : ICMP request identifier + )"00:01:"$( : ICMP request seq. number + )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload + )"6d:74:0b:00:00:00:00:00:"$( : + )"10:11:12:13:14:15:16:17:"$( : + )"18:19:1a:1b:1c:1d:1e:1f:"$( : + )"20:21:22:23:24:25:26:27:"$( : + )"28:29:2a:2b:2c:2d:2e:2f:"$( : + )"30:31:32:33:34:35:36:37" +} + +vxlan_device_add() +{ + ip_link_add vx1 up type vxlan id 1000 \ + local 192.0.2.17 dstport "$VXPORT" \ + nolearning noudpcsum tos inherit ttl 100 "$@" + ip_link_set_master vx1 br1 +} + +vxlan_all_reserved_bits() +{ + local i + + for ((i=0; i < 64; i++)); do + if ((i == 4 || i >= 32 && i < 56)); then + continue + fi + echo $i + done +} + +vxlan_ping_vanilla() +{ + vxlan_ping_do 10 $rp2 $(mac_get $rp1) 192.0.2.17 $(mac_get $h1) 1000 +} + +vxlan_ping_reserved() +{ + for bit in $(vxlan_all_reserved_bits); do + vxlan_ping_do 1 $rp2 $(mac_get $rp1) \ + 192.0.2.17 $(mac_get $h1) 1000 "$bit" + ((n++)) + done +} + +vxlan_ping_test() +{ + local what=$1; shift + local get_stat=$1; shift + local expect=$1; shift + + RET=0 + + local t0=$($get_stat) + + "$@" + check_err $? "Failure when running $@" + + local t1=$($get_stat) + local delta=$((t1 - t0)) + + ((expect == delta)) + check_err $? "Expected to capture $expect packets, got $delta." + + log_test "$what" +} + +__default_test_do() +{ + local n_allowed_bits=$1; shift + local what=$1; shift + + vxlan_ping_test "$what: clean packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + 10 vxlan_ping_vanilla + + local t0=$(link_stats_get vx1 rx errors) + vxlan_ping_test "$what: mangled packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + $n_allowed_bits vxlan_ping_reserved + local t1=$(link_stats_get vx1 rx errors) + + RET=0 + local expect=$((39 - n_allowed_bits)) + local delta=$((t1 - t0)) + ((expect == delta)) + check_err $? "Expected $expect error packets, got $delta." + log_test "$what: drops reported" +} + +default_test_do() +{ + vxlan_device_add + __default_test_do 0 "Default" +} + +default_test() +{ + in_defer_scope \ + default_test_do +} + +plain_test_do() +{ + vxlan_device_add reserved_bits 0xf7ffffff000000ff + __default_test_do 0 "reserved_bits 0xf7ffffff000000ff" +} + +plain_test() +{ + in_defer_scope \ + plain_test_do +} + +reserved_test() +{ + local bit=$1; shift + + local allowed_bytes=$(vxlan_header_bytes 0xffffff $bit) + local reserved_bytes=$(neg_bytes $allowed_bytes) + local reserved_bits=${reserved_bytes//:/} + + vxlan_device_add reserved_bits 0x$reserved_bits + __default_test_do 1 "reserved_bits 0x$reserved_bits" +} + +reserved_0_test() +{ + in_defer_scope \ + reserved_test 0 +} + +reserved_10_test() +{ + in_defer_scope \ + reserved_test 10 +} + +reserved_31_test() +{ + in_defer_scope \ + reserved_test 31 +} + +reserved_56_test() +{ + in_defer_scope \ + reserved_test 56 +} + +reserved_63_test() +{ + in_defer_scope \ + reserved_test 63 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c index be4a30a0d02a..9b44a091802c 100644 --- a/tools/testing/selftests/net/ipsec.c +++ b/tools/testing/selftests/net/ipsec.c @@ -227,7 +227,8 @@ static int rtattr_pack(struct nlmsghdr *nh, size_t req_sz, attr->rta_len = RTA_LENGTH(size); attr->rta_type = rta_type; - memcpy(RTA_DATA(attr), payload, size); + if (payload) + memcpy(RTA_DATA(attr), payload, size); return 0; } diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 8994fec1c38f..0bd9a038a1f0 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -435,6 +435,13 @@ xfail_on_veth() fi } +mac_get() +{ + local if_name=$1 + + ip -j link show dev $if_name | jq -r '.[]["address"]' +} + kill_process() { local pid=$1; shift @@ -451,7 +458,7 @@ ip_link_add() defer ip link del dev "$name" } -ip_link_master() +ip_link_set_master() { local member=$1; shift local master=$1; shift @@ -459,3 +466,62 @@ ip_link_master() ip link set dev "$member" master "$master" defer ip link set dev "$member" nomaster } + +ip_link_set_addr() +{ + local name=$1; shift + local addr=$1; shift + + local old_addr=$(mac_get "$name") + ip link set dev "$name" address "$addr" + defer ip link set dev "$name" address "$old_addr" +} + +ip_link_is_up() +{ + local name=$1; shift + + local state=$(ip -j link show "$name" | + jq -r '(.[].flags[] | select(. == "UP")) // "DOWN"') + [[ $state == "UP" ]] +} + +ip_link_set_up() +{ + local name=$1; shift + + if ! ip_link_is_up "$name"; then + ip link set dev "$name" up + defer ip link set dev "$name" down + fi +} + +ip_link_set_down() +{ + local name=$1; shift + + if ip_link_is_up "$name"; then + ip link set dev "$name" down + defer ip link set dev "$name" up + fi +} + +ip_addr_add() +{ + local name=$1; shift + + ip addr add dev "$name" "$@" + defer ip addr del dev "$name" "$@" +} + +ip_route_add() +{ + ip route add "$@" + defer ip route del "$@" +} + +bridge_vlan_add() +{ + bridge vlan add "$@" + defer bridge vlan del "$@" +} diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index 18b9443454a9..bc6b6762baf3 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../../usr/include/ $(KHDR_INCLUDES) # Additional include paths needed by kselftest.h CFLAGS += -I../../ diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 477ae76de93d..3efe005436cd 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -71,6 +71,11 @@ def ksft_in(a, b, comment=""): _fail("Check failed", a, "not in", b, comment) +def ksft_is(a, b, comment=""): + if a is not b: + _fail("Check failed", a, "is not", b, comment) + + def ksft_ge(a, b, comment=""): if a < b: _fail("Check failed", a, "<", b, comment) diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 72590c3f90f1..9e3bcddcf3e8 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -10,7 +10,9 @@ import time class CmdExitFailure(Exception): - pass + def __init__(self, msg, cmd_obj): + super().__init__(msg) + self.cmd = cmd_obj class cmd: @@ -48,7 +50,7 @@ class cmd: if len(stderr) > 0 and stderr[-1] == "\n": stderr = stderr[:-1] raise CmdExitFailure("Command failed: %s\nSTDOUT: %s\nSTDERR: %s" % - (self.proc.args, stdout, stderr)) + (self.proc.args, stdout, stderr), self) class bkg(cmd): diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index a0d689d58c57..ad1e36baee2a 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -13,14 +13,14 @@ try: SPEC_PATH = KSFT_DIR / "net/lib/specs" sys.path.append(tools_full_path.as_posix()) - from net.lib.ynl.lib import YnlFamily, NlError + from net.lib.ynl.pyynl.lib import YnlFamily, NlError else: # Running in tree tools_full_path = KSRC / "tools" SPEC_PATH = KSRC / "Documentation/netlink/specs" sys.path.append(tools_full_path.as_posix()) - from net.ynl.lib import YnlFamily, NlError + from net.ynl.pyynl.lib import YnlFamily, NlError except ModuleNotFoundError as e: ksft_pr("Failed importing `ynl` library from kernel sources") ksft_pr(str(e)) @@ -32,23 +32,23 @@ except ModuleNotFoundError as e: # Set schema='' to avoid jsonschema validation, it's slow # class EthtoolFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('ethtool.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class RtnlFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetdevFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetshaperFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 8e3fc05a5397..c76525fe2b84 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -2,7 +2,7 @@ top_srcdir = ../../../../.. -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 4209b9569039..414addef9a45 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -25,6 +25,8 @@ #include <sys/types.h> #include <sys/mman.h> +#include <arpa/inet.h> + #include <netdb.h> #include <netinet/in.h> @@ -1211,23 +1213,42 @@ static void parse_setsock_options(const char *name) exit(1); } -void xdisconnect(int fd, int addrlen) +void xdisconnect(int fd) { - struct sockaddr_storage empty; + socklen_t addrlen = sizeof(struct sockaddr_storage); + struct sockaddr_storage addr, empty; int msec_sleep = 10; - int queued = 1; - int i; + void *raw_addr; + int i, cmdlen; + char cmd[128]; + + /* get the local address and convert it to string */ + if (getsockname(fd, (struct sockaddr *)&addr, &addrlen) < 0) + xerror("getsockname"); + + if (addr.ss_family == AF_INET) + raw_addr = &(((struct sockaddr_in *)&addr)->sin_addr); + else if (addr.ss_family == AF_INET6) + raw_addr = &(((struct sockaddr_in6 *)&addr)->sin6_addr); + else + xerror("bad family"); + + strcpy(cmd, "ss -M | grep -q "); + cmdlen = strlen(cmd); + if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen], + sizeof(cmd) - cmdlen)) + xerror("inet_ntop"); shutdown(fd, SHUT_WR); - /* while until the pending data is completely flushed, the later + /* + * wait until the pending data is completely flushed and all + * the MPTCP sockets reached the closed status. * disconnect will bypass/ignore/drop any pending data. */ for (i = 0; ; i += msec_sleep) { - if (ioctl(fd, SIOCOUTQ, &queued) < 0) - xerror("can't query out socket queue: %d", errno); - - if (!queued) + /* closed socket are not listed by 'ss' */ + if (system(cmd) != 0) break; if (i > poll_timeout) @@ -1281,9 +1302,9 @@ again: return ret; if (cfg_truncate > 0) { - xdisconnect(fd, peer->ai_addrlen); + xdisconnect(fd); } else if (--cfg_repeat > 0) { - xdisconnect(fd, peer->ai_addrlen); + xdisconnect(fd); /* the socket could be unblocking at this point, we need the * connect to be blocking diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index b48b4e56826a..5e3c56253274 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -137,7 +137,7 @@ TEST_GROUP="" #shellcheck disable=SC2317 cleanup() { - rm -f "$cin_disconnect" "$cout_disconnect" + rm -f "$cin_disconnect" rm -f "$cin" "$cout" rm -f "$sin" "$sout" rm -f "$capout" @@ -155,7 +155,6 @@ cin=$(mktemp) cout=$(mktemp) capout=$(mktemp) cin_disconnect="$cin".disconnect -cout_disconnect="$cout".disconnect trap cleanup EXIT mptcp_lib_ns_init ns1 ns2 ns3 ns4 @@ -445,12 +444,8 @@ do_transfer() printf "(duration %05sms) " "${duration}" if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" - cat /tmp/${listener_ns}.out - echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" - [ ${listener_ns} != ${connector_ns} ] && cat /tmp/${connector_ns}.out + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ + "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" echo cat "$capout" @@ -587,7 +582,7 @@ make_file() mptcp_lib_make_file $name 1024 $ksize dd if=/dev/urandom conv=notrunc of="$name" oflag=append bs=1 count=$rem 2> /dev/null - echo "Created $name (size $(du -b "$name")) containing data sent by $who" + echo "Created $name (size $(stat -c "%s" "$name") B) containing data sent by $who" } run_tests_lo() diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index c07e2bd3a315..13a3b68181ee 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1039,13 +1039,8 @@ do_transfer() if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then fail_test "client exit code $retc, server $rets" - echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" - cat /tmp/${listener_ns}.out - echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" - cat /tmp/${connector_ns}.out - + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ + "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" return 1 fi diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 975d4d4c862a..051e289d7967 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -107,6 +107,27 @@ mptcp_lib_pr_info() { mptcp_lib_print_info "INFO: ${*}" } +# $1-2: listener/connector ns ; $3 port ; $4-5 listener/connector stat file +mptcp_lib_pr_err_stats() { + local lns="${1}" + local cns="${2}" + local port="${3}" + local lstat="${4}" + local cstat="${5}" + + echo -en "${MPTCP_LIB_COLOR_RED}" + { + printf "\nnetns %s (listener) socket stat for %d:\n" "${lns}" "${port}" + ip netns exec "${lns}" ss -Menitam -o "sport = :${port}" + cat "${lstat}" + + printf "\nnetns %s (connector) socket stat for %d:\n" "${cns}" "${port}" + ip netns exec "${cns}" ss -Menitam -o "dport = :${port}" + [ "${lstat}" != "${cstat}" ] && cat "${cstat}" + } 1>&2 + echo -en "${MPTCP_LIB_COLOR_RESET}" +} + # SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all # features using the last version of the kernel and the selftests to make sure # a test is not being skipped by mistake. diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 5e8d5b83e2d0..418a903c3a4d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -169,6 +169,11 @@ do_transfer() cmsg+=",TCPINQ" fi + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat -n + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat -n + timeout ${timeout_test} \ ip netns exec ${listener_ns} \ $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ @@ -189,14 +194,16 @@ do_transfer() wait $spid local rets=$? + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat | grep Tcp > /tmp/${listener_ns}.out + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat | grep Tcp > /tmp/${connector_ns}.out + print_title "Transfer ${ip:2}" if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" - - echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ + "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" mptcp_lib_result_fail "transfer ${ip}" diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 8fa77c8e9b65..9c2a415976cb 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -155,6 +155,11 @@ do_transfer() sleep 1 fi + NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ + nstat -n + NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ + nstat -n + timeout ${timeout_test} \ ip netns exec ${ns3} \ ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ @@ -180,25 +185,27 @@ do_transfer() kill ${cappid_connector} fi + NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ + nstat | grep Tcp > /tmp/${ns3}.out + NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ + nstat | grep Tcp > /tmp/${ns1}.out + cmp $sin $cout > /dev/null 2>&1 local cmps=$? cmp $cin $sout > /dev/null 2>&1 local cmpc=$? - printf "%-16s" " max $max_time " if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \ [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then + printf "%-16s" " max $max_time " mptcp_lib_pr_ok cat "$capout" return 0 fi - mptcp_lib_pr_fail - echo "client exit code $retc, server $rets" 1>&2 - echo -e "\nnetns ${ns3} socket stat for $port:" 1>&2 - ip netns exec ${ns3} ss -nita 1>&2 -o "sport = :$port" - echo -e "\nnetns ${ns1} socket stat for $port:" 1>&2 - ip netns exec ${ns1} ss -nita 1>&2 -o "dport = :$port" + mptcp_lib_pr_fail "client exit code $retc, server $rets" + mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" \ + "/tmp/${ns3}.out" "/tmp/${ns1}.out" ls -l $sin $cout ls -l $cin $sout diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py index 93d9d914529b..93e8cb671c3d 100755 --- a/tools/testing/selftests/net/nl_netdev.py +++ b/tools/testing/selftests/net/nl_netdev.py @@ -18,6 +18,23 @@ def lo_check(nf) -> None: ksft_eq(len(lo_info['xdp-rx-metadata-features']), 0) +def napi_list_check(nf) -> None: + with NetdevSimDev(queue_count=100) as nsimdev: + nsim = nsimdev.nsims[0] + + ip(f"link set dev {nsim.ifname} up") + + napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True) + ksft_eq(len(napis), 100) + + for q in [50, 0, 99]: + for i in range(4): + nsim.dfs_write("queue_reset", f"{q} {i}") + napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True) + ksft_eq(len(napis), 100, + comment=f"queue count after reset queue {q} mode {i}") + + def page_pool_check(nf) -> None: with NetdevSimDev() as nsimdev: nsim = nsimdev.nsims[0] @@ -89,7 +106,7 @@ def page_pool_check(nf) -> None: def main() -> None: nf = NetdevFamily() - ksft_run([empty_check, lo_check, page_pool_check], + ksft_run([empty_check, lo_check, page_pool_check, napi_list_check], args=(nf, )) ksft_exit() diff --git a/tools/testing/selftests/net/openvswitch/Makefile b/tools/testing/selftests/net/openvswitch/Makefile index 2f1508abc826..3fd1da2ec07d 100644 --- a/tools/testing/selftests/net/openvswitch/Makefile +++ b/tools/testing/selftests/net/openvswitch/Makefile @@ -2,7 +2,7 @@ top_srcdir = ../../../../.. -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := openvswitch.sh diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index cc0bfae2bafa..960e1ab4dd04 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -171,8 +171,10 @@ ovs_add_netns_and_veths () { ovs_add_if "$1" "$2" "$4" -u || return 1 fi - [ $TRACING -eq 1 ] && ovs_netns_spawn_daemon "$1" "$ns" \ - tcpdump -i any -s 65535 + if [ $TRACING -eq 1 ]; then + ovs_netns_spawn_daemon "$1" "$3" tcpdump -l -i any -s 6553 + ovs_wait grep -q "listening on any" ${ovs_dir}/stderr + fi return 0 } diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index 4071c133f29e..ef8b25a606d8 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -23,7 +23,7 @@ if [ $# -ne 1 ]; then ktap_exit_fail_msg "usage: $0 <script>" exit "$KSFT_FAIL" fi -script="$1" +script="$(basename $1)" if [ -z "$(which packetdrill)" ]; then ktap_skip_all "packetdrill not found in PATH" @@ -31,16 +31,32 @@ if [ -z "$(which packetdrill)" ]; then fi declare -a optargs +failfunc=ktap_test_fail + if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then optargs+=('--tolerance_usecs=14000') + + # xfail tests that are known flaky with dbg config, not fixable. + # still run them for coverage (and expect 100% pass without dbg). + declare -ar xfail_list=( + "tcp_eor_no-coalesce-retrans.pkt" + "tcp_fast_recovery_prr-ss.*.pkt" + "tcp_slow_start_slow-start-after-win-update.pkt" + "tcp_timestamping.*.pkt" + "tcp_user_timeout_user-timeout-probe.pkt" + "tcp_zerocopy_epoll_.*.pkt" + "tcp_tcp_info_tcp-info-.*-limited.pkt" + ) + readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$" + [[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail fi ktap_print_header ktap_set_plan 2 -unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $(basename $script) > /dev/null \ - && ktap_test_pass "ipv4" || ktap_test_fail "ipv4" -unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $(basename $script) > /dev/null \ - && ktap_test_pass "ipv6" || ktap_test_fail "ipv6" +unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $script > /dev/null \ + && ktap_test_pass "ipv4" || $failfunc "ipv4" +unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $script > /dev/null \ + && ktap_test_pass "ipv6" || $failfunc "ipv6" ktap_finished diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt new file mode 100644 index 000000000000..38535701656e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test for blocking accept. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0...0.200 accept(3, ..., ...) = 4 + + +.1 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 257 + + +.1 write(4, ..., 2000) = 2000 + +0 > P. 1:2001(2000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt new file mode 100644 index 000000000000..3692ef102381 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test for blocking connect. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + + +.1...0.200 connect(3, ..., ...) = 0 + + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.1 < S. 0:0(0) ack 1 win 5792 <mss 1460,nop,wscale 2,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt new file mode 100644 index 000000000000..914eabab367a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test for blocking read. +--tolerance_usecs=10000 + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 + + +0...0.100 read(4, ..., 2000) = 2000 + +.1 < P. 1:2001(2000) ack 1 win 257 + +0 > . 1:1(0) ack 2001 + + +.1...0.200 read(4, ..., 2000) = 2000 + +.1 < P. 2001:4001(2000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 + + +.1 < P. 4001:6001(2000) ack 1 win 257 + +0 > . 1:1(0) ack 6001 + +0...0.000 read(4, ..., 1000) = 1000 + +0...0.000 read(4, ..., 1000) = 1000 diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt new file mode 100644 index 000000000000..cec5a0725d95 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test for blocking write. +--tolerance_usecs=10000 + +`./defaults.sh +./set_sysctls.py /proc/sys/net/ipv4/tcp_min_tso_segs=10 +` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 50000 <mss 1000,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 50000 + +0 accept(3, ..., ...) = 4 + +// Kernel doubles our value -> sk->sk_sndbuf is set to 42000 + +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [21000], 4) = 0 + +0 getsockopt(4, SOL_SOCKET, SO_SNDBUF, [42000], [4]) = 0 + +// A write of 60000 does not block. + +0...0.300 write(4, ..., 61000) = 61000 // this write() blocks + + +.1 < . 1:1(0) ack 10001 win 50000 + + +.1 < . 1:1(0) ack 30001 win 50000 + +// This ACK should wakeup the write(). An ACK of 35001 does not. + +.1 < . 1:1(0) ack 36001 win 50000 + +// Reset to sysctls defaults. +`/tmp/sysctl_restore_${PPID}.sh` diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt new file mode 100644 index 000000000000..8514d6bdbb6d --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test basic connection teardown where local process closes first: +// the local process calls close() first, so we send a FIN, and receive an ACK. +// Then we receive a FIN and ACK it. + +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +.01...0.011 connect(3, ..., ...) = 0 + +0 > S 0:0(0) <...> + +0 < S. 0:0(0) ack 1 win 32768 <mss 1000,nop,wscale 6,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 + + +0 write(3, ..., 1000) = 1000 + +0 > P. 1:1001(1000) ack 1 + +0 < . 1:1(0) ack 1001 win 257 + + +0 close(3) = 0 + +0 > F. 1001:1001(0) ack 1 + +0 < . 1:1(0) ack 1002 win 257 + + +0 < F. 1:1(0) ack 1002 win 257 + +0 > . 1002:1002(0) ack 2 diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt new file mode 100644 index 000000000000..04103134bd99 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test to make sure no RST is being sent when close() +// is called on a socket with SYN_SENT state. + +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <...> + +// Application decideds to close the socket in SYN_SENT state +// Make sure no RST is sent after close(). + +0 close(3) = 0 + +// Receive syn-ack to trigger the send side packet examination: +// If a RESET were sent right after close(), it would have failed with +// a mismatched timestamp. + +.1 < S. 0:0(0) ack 1 win 32000 <mss 1460,nop,wscale 7> + +0 > R 1:1(0) diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt new file mode 100644 index 000000000000..5f3a2914213a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +// Verify behavior for the sequence: remote side sends FIN, then we close(). +// Since the remote side (client) closes first, we test our LAST_ACK code path. + +`./defaults.sh` + +// Initialize a server socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +0 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + +// Client closes first. + +.01 < F. 1:1(0) ack 1 win 257 + +0 > . 1:1(0) ack 2 + +// App notices that client closed. + +0 read(4, ..., 1000) = 0 + +// Then we close. + +.01 close(4) = 0 + +0 > F. 1:1(0) ack 2 + +// Client ACKs our FIN. + +.01 < . 2:2(0) ack 2 win 257 + +// Verify that we send RST in response to any incoming segments +// (because the kernel no longer has any record of this socket). + +.01 < . 2:2(0) ack 2 win 257 + +0 > R 2:2(0) diff --git a/tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt b/tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt new file mode 100644 index 000000000000..643baf3267cf --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test ECN: verify that Linux TCP ECN sending code uses ECT0 (not ECT1). +// +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=1 # fully enabled +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 + +// ECN handshake: send EW flags in SYN packet, E flag in SYN-ACK response ++.002 ... 0.004 connect(4, ..., ...) = 0 + + +0 > SEW 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> ++.002 < SE. 0:0(0) ack 1 win 32767 <mss 1000,nop,wscale 6,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 + +// Write 1 MSS. ++.002 write(4, ..., 1000) = 1000 +// Send 1 MSS with ect0. + +0 > [ect0] P. 1:1001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt new file mode 100644 index 000000000000..f95b9b3c9fa1 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP does not append any data from consequent writes to the tail +// skb created for the chunk. The large chunk itself should be packetized as +// usual. +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on +// the tail. + +0 write(4, ..., 10400) = 10400 + +// Write another 10040B chunk with no coalescing options. + +0 send(4, ..., 10400, MSG_EOR) = 10400 + +// Write a 2KB chunk. This chunk should not be appended to the packets created +// the previous chunk. + +0 write(4, ..., 2000) = 2000 + + +0 > P. 1:10001(10000) ack 1 ++.001 < . 1:1(0) ack 10001 win 514 +// Now we have enough room to send out the 2 x 400B packets out. + +0 > P. 10001:20801(10800) ack 1 ++.001 < . 1:1(0) ack 20801 win 514 +// This 2KB packet should be sent alone. + +0 > P. 20801:22801(2000) ack 1 ++.001 < . 1:1(0) ack 22801 win 514 diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt new file mode 100644 index 000000000000..2ff66075288e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP does not append any data from consequent writes to the tail +// skb created for the chunk. Also, when packets are retransmitted, they +// will not be coalesce into the same skb. +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on +// the tail. + +0 write(4, ..., 10400) = 10400 + +// Write 10 400B chunks with no coalescing options. + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 +// This chunk should not be appended to the skbs created for the previous chunk. + +0 write(4, ..., 10000) = 10000 + + +0 > P. 1:10001(10000) ack 1 ++.001 < . 1:1(0) ack 10001 win 514 +// Now we have enough room to send out the 2 x 400B packets out. + +0 > P. 10001:10801(800) ack 1 +// The 9 remaining 400B chunks should be sent as individual packets. + +0 > P. 10801:11201(400) ack 1 + +0 > P. 11201:11601(400) ack 1 + +0 > P. 11601:12001(400) ack 1 + +0 > P. 12001:12401(400) ack 1 + +0 > P. 12401:12801(400) ack 1 + +0 > P. 12801:13201(400) ack 1 + +0 > P. 13201:13601(400) ack 1 + +0 > P. 13601:14001(400) ack 1 + +0 > P. 14001:14401(400) ack 1 +// The last 10KB chunk should be sent separately. + +0 > P. 14401:24401(10000) ack 1 + ++.001 < . 1:1(0) ack 10401 win 514 ++.001 < . 1:1(0) ack 10801 win 514 ++.001 < . 1:1(0) ack 11201 win 514 ++.001 < . 1:1(0) ack 11601 win 514 ++.001 < . 1:1(0) ack 12001 win 514 <sack 13201:14401,nop,nop> +// TCP should fill the hole but no coalescing should happen, and all +// retransmissions should be sent out as individual packets. + +// Note : This is timeout based retransmit. +// Do not put +0 here or flakes will come back. ++.004~+.008 > P. 12001:12401(400) ack 1 + ++.001 < . 1:1(0) ack 12401 win 514 <sack 13201:14401,nop,nop> + +0 > P. 12401:12801(400) ack 1 + +0 > P. 12801:13201(400) ack 1 ++.001 < . 1:1(0) ack 12801 win 514 <sack 13201:14401,nop,nop> ++.001 < . 1:1(0) ack 14401 win 514 ++.001 < . 1:1(0) ack 24401 win 514 diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt new file mode 100644 index 000000000000..77039c5aac39 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP does not append any data from consequent writes to the tail +// skb created for the chunk. +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on +// the tail. + +0 write(4, ..., 10400) = 10400 + +// Write a 400B chunk with no coalescing options. + +0 send(4, ..., 400, MSG_EOR) = 400 + +// This chunk should not be appended to the skbs created for the previous chunk. + +0 write(4, ..., 10000) = 10000 + + +0 > P. 1:10001(10000) ack 1 ++.001 < . 1:1(0) ack 10001 win 514 +// Now we have enough room to send out the 2 x 400B packets out. + +0 > P. 10001:10801(800) ack 1 + +0 > P. 10801:20801(10000) ack 1 ++.001 < . 1:1(0) ack 10401 win 514 ++.001 < . 1:1(0) ack 10801 win 514 ++.001 < . 1:1(0) ack 20801 win 514 diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt new file mode 100644 index 000000000000..dd5a06250595 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP does not append any data from consequent writes to the tail +// skb created for the chunk even though we have 10 back-to-back small +// writes. +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on +// the tail. + +0 write(4, ..., 10400) = 10400 + +// Write 10 400B chunks with no coalescing options. + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 +// This chunk should not be appended to the skbs created for the previous chunk. + +0 write(4, ..., 10000) = 10000 + + +0 > P. 1:10001(10000) ack 1 ++.001 < . 1:1(0) ack 10001 win 514 +// Now we have enough room to send out the 2 x 400B packets out. + +0 > P. 10001:10801(800) ack 1 +// The 9 remaining 400B chunks should be sent as individual packets. + +0 > P. 10801:11201(400) ack 1 + +0 > P. 11201:11601(400) ack 1 + +0 > P. 11601:12001(400) ack 1 + +0 > P. 12001:12401(400) ack 1 + +0 > P. 12401:12801(400) ack 1 + +0 > P. 12801:13201(400) ack 1 + +0 > P. 13201:13601(400) ack 1 + +0 > P. 13601:14001(400) ack 1 + +0 > P. 14001:14401(400) ack 1 +// The last 10KB chunk should be sent separately. + +0 > P. 14401:24401(10000) ack 1 + ++.001 < . 1:1(0) ack 10401 win 514 ++.001 < . 1:1(0) ack 10801 win 514 ++.001 < . 1:1(0) ack 11201 win 514 ++.001 < . 1:1(0) ack 11601 win 514 ++.001 < . 1:1(0) ack 12001 win 514 ++.001 < . 1:1(0) ack 12401 win 514 ++.001 < . 1:1(0) ack 12801 win 514 ++.001 < . 1:1(0) ack 13201 win 514 ++.001 < . 1:1(0) ack 13601 win 514 ++.001 < . 1:1(0) ack 14001 win 514 ++.001 < . 1:1(0) ack 14401 win 514 ++.001 < . 1:1(0) ack 24401 win 514 diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt new file mode 100644 index 000000000000..0d3c8077e830 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test PRR-slowstart implementation. +// In this variant we test a simple case where in-flight == ssthresh +// all the way through recovery, so during fast recovery we send one segment +// for each segment SACKed/ACKed. + +// Set up config. +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> +// RTT 100ms + +.1 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Send 10 data segments. + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// Lost packet 1:1001. + +.11 < . 1:1(0) ack 1 win 320 <sack 1001:2001,nop,nop> + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:3001,nop,nop> + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:4001,nop,nop> +// Enter fast recovery. + +0 > . 1:1001(1000) ack 1 + +.01 %{ +assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state +assert tcpi_snd_cwnd == 7, tcpi_snd_cwnd +assert tcpi_snd_ssthresh == 7, tcpi_snd_ssthresh +}% + +// Write some more, which we will send 1 MSS at a time, +// as in-flight segments are SACKed or ACKed. + +.01 write(4, ..., 7000) = 7000 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:5001,nop,nop> + +0 > . 10001:11001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:6001,nop,nop> + +0 > . 11001:12001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:7001,nop,nop> + +0 > . 12001:13001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:8001,nop,nop> + +0 > . 13001:14001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:9001,nop,nop> + +0 > . 14001:15001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:10001,nop,nop> + +0 > . 15001:16001(1000) ack 1 + + +.02 < . 1:1(0) ack 10001 win 320 + +0 > P. 16001:17001(1000) ack 1 +// Leave fast recovery. + +.01 %{ +assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state +assert tcpi_snd_cwnd == 7, tcpi_snd_cwnd +assert tcpi_snd_ssthresh == 7, tcpi_snd_ssthresh +}% + + +.03 < . 1:1(0) ack 12001 win 320 + +.02 < . 1:1(0) ack 14001 win 320 + +.02 < . 1:1(0) ack 16001 win 320 + +.02 < . 1:1(0) ack 17001 win 320 diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt new file mode 100644 index 000000000000..7842a10b6967 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test PRR-slowstart implementation. The sender sends 20 packets. Packet +// 1 to 4, and 11 to 16 are dropped. +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + + +.01 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Write 20 data segments. + +0 write(4, ..., 20000) = 20000 + +0 > P. 1:10001(10000) ack 1 + +// Receive first DUPACK, entering PRR part + +.01 < . 1:1(0) ack 1 win 320 <sack 4001:5001,nop,nop> + +0 > . 10001:11001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:6001,nop,nop> + +0 > . 11001:12001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:7001,nop,nop> + +0 > . 1:1001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:8001,nop,nop> + +0 > . 1001:2001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:9001,nop,nop> + +0 > . 2001:3001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:10001,nop,nop> + +0 > . 3001:4001(1000) ack 1 +// Enter PRR CRB ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:11001,nop,nop> + +0 > . 12001:13001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:12001,nop,nop> + +0 > . 13001:14001(1000) ack 1 +// Enter PRR slow start + +.01 < . 1:1(0) ack 1001 win 320 <sack 4001:12001,nop,nop> + +0 > P. 14001:16001(2000) ack 1 ++.002 < . 1:1(0) ack 1001 win 320 <sack 2001:12001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 > . 16001:17001(1000) ack 1 +// inflight reaches ssthresh, goes into packet conservation mode ++.002 < . 1:1(0) ack 1001 win 320 <sack 2001:13001,nop,nop> + +0 > . 17001:18001(1000) ack 1 ++.002 < . 1:1(0) ack 1001 win 320 <sack 2001:14001,nop,nop> + +0 > . 18001:19001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt new file mode 100644 index 000000000000..b66d7644c3b6 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test PRR-slowstart implementation. The sender sends 20 packets. Packet +// 1 to 4 are lost. The sender writes another 10 packets. +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + + +.01 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Send 20 data segments. + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// Lost packet 1,2,3,4 + +.01 < . 1:1(0) ack 1 win 320 <sack 4001:5001,nop,nop> ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:6001,nop,nop> + +0 < . 1:1(0) ack 1 win 320 <sack 4001:7001,nop,nop> + +0 > . 1:1001(1000) ack 1 + +0 < . 1:1(0) ack 1 win 320 <sack 4001:8001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 < . 1:1(0) ack 1 win 320 <sack 4001:9001,nop,nop> + +0 > . 2001:3001(1000) ack 1 + +0 < . 1:1(0) ack 1 win 320 <sack 4001:10001,nop,nop> + +0 > . 3001:4001(1000) ack 1 + +// Receiver ACKs all data. + +.01 < . 1:1(0) ack 1001 win 320 <sack 4001:10001,nop,nop> + +0 < . 1:1(0) ack 2001 win 320 <sack 4001:10001,nop,nop> + +0 < . 1:1(0) ack 3001 win 320 <sack 4001:10001,nop,nop> + +0 < . 1:1(0) ack 10001 win 320 + +// Writes another 10 packets, which the ssthresh*mss amount +// should be sent right away + +.01 write(4, ..., 10000) = 10000 + +0 > . 10001:17001(7000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt new file mode 100644 index 000000000000..8e87bfecabb5 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test PRR-slowstart implementation. +// In this variant we verify that the sender uses SACK info on an ACK +// below snd_una. + +// Set up config. +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 8> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> +// RTT 10ms + +.01 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Send 10 data segments. + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// Lost packet 1:1001,4001:5001,7001:8001. + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:2001,nop,nop> + +0 < . 1:1(0) ack 1 win 320 <sack 1001:3001,nop,nop> + +0 < . 1:1(0) ack 1 win 320 <sack 1001:3001 8001:9001,nop,nop> + +0 > . 1:1001(1000) ack 1 + ++.012 < . 1:1(0) ack 4001 win 320 <sack 8001:9001,nop,nop> + +0 > . 4001:7001(3000) ack 1 + + +0 write(4, ..., 10000) = 10000 + +// The following ACK was reordered - delayed so that it arrives with +// an ACK field below snd_una. Here we check that the newly-SACKed +// 2MSS at 5001:7001 cause us to send out 2 more MSS. ++.002 < . 1:1(0) ack 3001 win 320 <sack 5001:7001,nop,nop> + +0 > . 7001:8001(1000) ack 1 + +0 > . 10001:11001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt new file mode 100644 index 000000000000..96b01eb5b7a4 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test RFC 3042 "Limited Transmit": "sending a new data segment in +// response to each of the first two duplicate acknowledgments that +// arrive at the sender". +// This variation tests a receiver that doesn't support SACK. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Write some data, and send the initial congestion window. + +0 write(4, ..., 15000) = 15000 + +0 > P. 1:10001(10000) ack 1 + +// Limited transmit: on first dupack, send a new data segment. + +.11 < . 1:1(0) ack 1 win 320 + +0 > . 10001:11001(1000) ack 1 + +// Limited transmit: on second dupack, send a new data segment. + +.01 < . 1:1(0) ack 1 win 320 + +0 > . 11001:12001(1000) ack 1 + +// It turned out to be reordering, not loss. +// We have one packet newly acked (1001:3001 were DUP-ACK'd) +// So we revert state back to Open. Slow start cwnd from 10 to 11 +// and send 11 - 9 = 2 packets + +.01 < . 1:1(0) ack 3001 win 320 + +0 > P. 12001:14001(2000) ack 1 + + +.02 < . 1:1(0) ack 5001 win 320 + +0 > P. 14001:15001(1000) ack 1 + +// Client gradually ACKs all data. + +.02 < . 1:1(0) ack 7001 win 320 + +.02 < . 1:1(0) ack 9001 win 320 + +.02 < . 1:1(0) ack 11001 win 320 + +.02 < . 1:1(0) ack 13001 win 320 + +.02 < . 1:1(0) ack 15001 win 320 + +// Clean up. + +.17 close(4) = 0 + +0 > F. 15001:15001(0) ack 1 + +.1 < F. 1:1(0) ack 15002 win 257 + +0 > . 15002:15002(0) ack 2 diff --git a/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt new file mode 100644 index 000000000000..642da51ec3a4 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test RFC 3042 "Limited Transmit": "sending a new data segment in +// response to each of the first two duplicate acknowledgments that +// arrive at the sender". +// This variation tests a receiver that supports SACK. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Write some data, and send the initial congestion window. + +0 write(4, ..., 15000) = 15000 + +0 > P. 1:10001(10000) ack 1 + +// Limited transmit: on first dupack, send a new data segment. + +.11 < . 1:1(0) ack 1 win 320 <sack 1001:2001,nop,nop> + +0 > . 10001:11001(1000) ack 1 + +// Limited transmit: on second dupack, send a new data segment. + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:3001,nop,nop> + +0 > . 11001:12001(1000) ack 1 + +// It turned out to be reordering, not loss. + +.01 < . 1:1(0) ack 3001 win 320 + +0 > P. 12001:14001(2000) ack 1 + + +.02 < . 1:1(0) ack 5001 win 320 + +0 > P. 14001:15001(1000) ack 1 + +// Client gradually ACKs all data. + +.02 < . 1:1(0) ack 7001 win 320 + +.02 < . 1:1(0) ack 9001 win 320 + +.02 < . 1:1(0) ack 11001 win 320 + +.02 < . 1:1(0) ack 13001 win 320 + +.02 < . 1:1(0) ack 15001 win 320 + +// Clean up. + +.17 close(4) = 0 + +0 > F. 15001:15001(0) ack 1 + +.1 < F. 1:1(0) ack 15002 win 257 + +0 > . 15002:15002(0) ack 2 diff --git a/tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt new file mode 100644 index 000000000000..7adae7a9ef4a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +// This is a test inspired by an Android client app using SSL. This +// test verifies using TCP_NODELAY would save application latency +// (Perhaps even better with TCP_NAGLE). +// +`./defaults.sh +ethtool -K tun0 tso off gso off +./set_sysctls.py /proc/sys/net/ipv4/tcp_timestamps=0` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 + +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + + +0 connect(4, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < S. 0:0(0) ack 1 win 5792 <mss 974,nop,nop,sackOK,nop,wscale 7> + +0 > . 1:1(0) ack 1 + +// SSL handshake (resumed session) + +0 write(4, ..., 517) = 517 + +0 > P. 1:518(517) ack 1 + +.1 < . 1:1(0) ack 518 win 229 + + +0 < P. 1:144(143) ack 1 win 229 + +0 > . 518:518(0) ack 144 + +0 read(4, ..., 1000) = 143 + +// Application POST header (51B) and body (2002B) + +0 write(4, ..., 51) = 51 + +0 > P. 518:569(51) ack 144 + +.03 write(4, ..., 2002) = 2002 + +0 > . 569:1543(974) ack 144 + +0 > P. 1543:2517(974) ack 144 +// Without disabling Nagle, this packet will not happen until the remote ACK. + +0 > P. 2517:2571(54) ack 144 + + +.1 < . 1:1(0) ack 2571 win 229 + +// Reset sysctls +`/tmp/sysctl_restore_${PPID}.sh` diff --git a/tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt b/tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt new file mode 100644 index 000000000000..fa9c01813996 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test the MSG_MORE flag will correctly corks the tiny writes +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 +// Disable Nagle by default on this socket. + +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + +// Test the basic case: MSG_MORE overwrites TCP_NODELAY and enables Nagle. + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 40}], msg_flags=0}, MSG_MORE) = 40 + +.21~+.215 > P. 1:41(40) ack 1 + +.01 < . 1:1(0) ack 41 win 257 + +// Test unsetting MSG_MORE releases the packet + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 100}], msg_flags=0}, MSG_MORE) = 100 ++.005 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 160}], msg_flags=0}, MSG_MORE) = 160 + +.01 sendmsg(4, {msg_name(...)=..., + msg_iov(3)=[{..., 100}, {..., 200}, {..., 195}], + msg_flags=0}, MSG_MORE) = 495 ++.008 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 5}], msg_flags=0}, 0) = 5 + +0 > P. 41:801(760) ack 1 + +.02 < . 1:1(0) ack 801 win 257 + + +// Test >MSS write will unleash MSS packets but hold on the remaining data. + +.1 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 3100}], msg_flags=0}, MSG_MORE) = 3100 + +0 > . 801:3801(3000) ack 1 ++.003 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 50}], msg_flags=0}, MSG_MORE) = 50 + + +.01 < . 1:1(0) ack 2801 win 257 +// Err... we relase the remaining right after the ACK? note that PUSH is reset + +0 > . 3801:3951(150) ack 1 + +// Test we'll hold on the subsequent writes when inflight (3801:3951) > 0 ++.001 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 1}], msg_flags=0}, MSG_MORE) = 1 ++.002 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 2}], msg_flags=0}, MSG_MORE) = 2 ++.003 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 3}], msg_flags=0}, MSG_MORE) = 3 ++.004 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 4}], msg_flags=0}, MSG_MORE) = 4 + +.02 < . 1:1(0) ack 3951 win 257 + +0 > . 3951:3961(10) ack 1 + +.02 < . 1:1(0) ack 3961 win 257 + + +// Test the case a MSG_MORE send followed by a write flushes the data + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 20}], msg_flags=0}, MSG_MORE) = 20 + +.05 write(4, ..., 20) = 20 + +0 > P. 3961:4001(40) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt b/tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt new file mode 100644 index 000000000000..0ddec5f7dc1a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP_CORK and TCP_NODELAY sockopt behavior +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 +// Set TCP_CORK sockopt to hold small packets + +0 setsockopt(4, SOL_TCP, TCP_CORK, [1], 4) = 0 + + +0 write(4, ..., 40) = 40 + +.05 write(4, ..., 40) = 40 + +// Unset TCP_CORK should push pending bytes out + +.01 setsockopt(4, SOL_TCP, TCP_CORK, [0], 4) = 0 + +0 > P. 1:81(80) ack 1 + +.01 < . 1:1(0) ack 81 win 257 + +// Set TCP_CORK sockopt to hold small packets + +0 setsockopt(4, SOL_TCP, TCP_CORK, [1], 4) = 0 + + +0 write(4, ..., 40) = 40 + +.05 write(4, ..., 40) = 40 + +// Set TCP_NODELAY sockopt should push pending bytes out + +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + +0 > P. 81:161(80) ack 1 + +.01 < . 1:1(0) ack 161 win 257 + +// Set MSG_MORE to hold small packets + +0 send(4, ..., 40, MSG_MORE) = 40 + +.05 send(4, ..., 40, MSG_MORE) = 40 + +// Set TCP_NODELAY sockopt should push pending bytes out + +.01 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + +0 > . 161:241(80) ack 1 + +.01 < . 1:1(0) ack 241 win 257 diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt new file mode 100644 index 000000000000..310ef31518da --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +// Verify that setsockopt calls that force a route refresh do not +// cause problems matching SACKs with packets in the write queue. +// This variant tests IP_TOS. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_IP, IP_MTU_DISCOVER, [IP_PMTUDISC_DONT], 1) = 0 + +0...0.010 connect(3, ..., ...) = 0 + + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.01 < S. 0:0(0) ack 1 win 65535 <mss 1460,nop,wscale 2,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 + + +.01 write(3, ..., 5840) = 5840 + +0 > P. 1:5841(5840) ack 1 + +.01 < . 1:1(0) ack 5841 win 65535 + + +.01 write(3, ..., 5840) = 5840 + +0 > P. 5841:11681(5840) ack 1 + +.01 < . 1:1(0) ack 11681 win 65535 + + +.01 write(3, ..., 14600) = 14600 + +0 > P. 11681:26281(14600) ack 1 + +// Try the socket option that we know can force a route refresh. + +0 setsockopt(3, SOL_IP, IP_TOS, [4], 1) = 0 +// Then revert to avoid routing/mangling/etc implications of that setting. + +0 setsockopt(3, SOL_IP, IP_TOS, [0], 1) = 0 + +// Verify that we do not retransmit the SACKed segments. + +.01 < . 1:1(0) ack 13141 win 65535 <sack 16061:17521 20441:26281,nop,nop> + +0 > . 13141:16061(2920) ack 1 + +0 > P. 17521:20441(2920) ack 1 + +.01 < . 1:1(0) ack 26281 win 65535 diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt new file mode 100644 index 000000000000..f185e1ac57ea --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb. +// This variant tests non-FACK SACK with SACKs coming in the order +// 2 6 8 3 9, to test what happens when we get a new SACKed range +// (for packet 3) that is on the right of an existing SACKed range +// (for packet 2). + +`./defaults.sh` + +// Establish a connection and send 10 MSS. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + + +.1 < . 1:1(0) ack 1 win 257 <sack 2001:3001,nop,nop> ++.001 < . 1:1(0) ack 1 win 257 <sack 2001:3001 6001:7001,nop,nop> ++.001 < . 1:1(0) ack 1 win 257 <sack 2001:3001 6001:7001 8001:9001,nop,nop> + +// 3 SACKed packets, so we enter Fast Recovery. + +0 > . 1:1001(1000) ack 1 + +0 %{ assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state }% + +0 %{ assert tcpi_lost == 6, tcpi_lost }% + +// SACK for 3001:4001. +// This SACK for an adjacent range causes the sender to +// shift the newly-SACKed range onto the previous skb. ++.007 < . 1:1(0) ack 1 win 257 <sack 2001:4001 6001:7001 8001:9001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 %{ assert tcpi_lost == 5, tcpi_lost }% + +0 %{ assert tcpi_reordering == 6, tcpi_reordering }% // 8001:9001 -> 3001:4001 is 6 + +// SACK for 9001:10001. + +.01 < . 1:1(0) ack 1 win 257 <sack 2001:4001 6001:7001 8001:10001,nop,nop> + +0 %{ assert tcpi_lost == 5, tcpi_lost }% + +// ACK for 1:1001 as packets from t=0.303 arrive. ++.083 < . 1:1(0) ack 1001 win 257 <sack 2001:4001 6001:7001 8001:10001,nop,nop> + +0 %{ assert tcpi_lost == 4,tcpi_lost }% + +// ACK for 1:4001 as packets from t=0.310 arrive. ++.017 < . 1:1(0) ack 4001 win 257 <sack 6001:7001 8001:10001,nop,nop> + +0 %{ assert tcpi_lost == 3,tcpi_lost }% + +// ACK for 1:7001 as packets from t=0.320 arrive. + +.01 < . 1:1(0) ack 7001 win 257 <sack 8001:10001,nop,nop> + +// ACK for all data as packets from t=0.403 arrive. + +.1 < . 1:1(0) ack 10001 win 257 + +0 %{ +assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state +assert tcpi_unacked == 0, tcpi_unacked +assert tcpi_sacked == 0, tcpi_sacked +assert tcpi_lost == 0, tcpi_lost +assert tcpi_retrans == 0, tcpi_retrans +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt new file mode 100644 index 000000000000..0093b4973934 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb. +// This variant tests the case where we mark packets 0-4 lost, then +// get a SACK for 3, and then a SACK for 4. + +`./defaults.sh` + +// Establish a connection and send 10 MSS. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// SACK for 7001:8001. Using RACK we delay the fast retransmit. + +.1 < . 1:1(0) ack 1 win 257 <sack 7001:8001,nop,nop> +// RACK reordering timer ++.027 > . 1:1001(1000) ack 1 + +0 %{ +assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state +assert tcpi_lost == 7, tcpi_lost # RACK thinks 1:7001 are lost +assert tcpi_reordering == 3, tcpi_reordering +}% + +// SACK for 3001:4001. ++.002 < . 1:1(0) ack 1 win 257 <sack 3001:4001 7001:8001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 %{ +assert tcpi_lost == 6, tcpi_lost # since 3001:4001 is no longer lost +assert tcpi_reordering == 5, tcpi_reordering # 7001:8001 -> 3001:4001 +}% + +// SACK for 4001:5001. +// This SACK for an adjacent range causes the sender to +// shift the newly-SACKed range onto the previous skb. +// It uses the RFC3517 algorithm to mark 1:3001 lost +// because >=3 higher-sequence packets are SACKed. ++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:8001,nop,nop> + +0 > . 2001:3001(1000) ack 1 + +0 %{ +assert tcpi_lost == 5,tcpi_lost # SACK/RFC3517 thinks 1:3001 are lost +}% + +// SACK for 8001:9001. ++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:9001,nop,nop> + +// SACK for 9001:10001. ++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:10001,nop,nop> + +0 > . 5001:6001(1000) ack 1 + +// To simplify clean-up, say we get an ACK for all data. + +.1 < . 1:1(0) ack 10001 win 257 + +0 %{ +assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state +assert tcpi_unacked == 0, tcpi_unacked +assert tcpi_sacked == 0, tcpi_sacked +assert tcpi_lost == 0, tcpi_lost +assert tcpi_retrans == 0, tcpi_retrans +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt new file mode 100644 index 000000000000..980a832dc81c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb. +// This variant tests the case where we mark packets 0-4 lost, then +// get a SACK for 5, and then a SACK for 6. + +`./defaults.sh` + +// Establish a connection and send 10 MSS. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// SACK for 7001:8001. Using RACK we delay a fast retransmit. + +.1 < . 1:1(0) ack 1 win 257 <sack 7001:8001,nop,nop> ++.027 > . 1:1001(1000) ack 1 + +0 %{ +assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state +assert tcpi_lost == 7,tcpi_lost # RACK thinks 1:7001 are lost +assert tcpi_reordering == 3, tcpi_reordering +}% + +// SACK for 5001:6001. + +0 < . 1:1(0) ack 1 win 257 <sack 5001:6001 7001:8001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 %{ +assert tcpi_lost == 6, tcpi_lost +assert tcpi_reordering == 3, tcpi_reordering # 7001:8001 -> 5001:6001 is 3 +}% + +// SACK for 6001:7001. +// This SACK for an adjacent range causes the sender to +// shift the newly-SACKed range onto the previous skb. + +0 < . 1:1(0) ack 1 win 257 <sack 5001:8001,nop,nop> + +0 > . 2001:3001(1000) ack 1 + +0 %{ assert tcpi_lost == 5, tcpi_lost }% + +// SACK for 8001:9001. + +0 < . 1:1(0) ack 1 win 257 <sack 5001:9001,nop,nop> + +0 > . 3001:4001(1000) ack 1 + +// SACK for 9001:10001. + +0 < . 1:1(0) ack 1 win 257 <sack 5001:10001,nop,nop> + +0 > . 4001:5001(1000) ack 1 + +// To simplify clean-up, say we get an ACK for all data. + +.1 < . 1:1(0) ack 10001 win 257 + +0 %{ +assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state +assert tcpi_unacked == 0, tcpi_unacked +assert tcpi_sacked == 0, tcpi_sacked +assert tcpi_lost == 0, tcpi_lost +assert tcpi_retrans == 0, tcpi_retrans +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt b/tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt new file mode 100644 index 000000000000..6740859a1360 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +// Simplest possible test of open() and then sendfile(). +// We write some zeroes into a file (since packetdrill expects payloads +// to be all zeroes) and then open() the file, then use sendfile() +// and verify that the correct number of zeroes goes out. + +`./defaults.sh +/bin/rm -f /tmp/testfile +/bin/dd bs=1 count=5 if=/dev/zero of=/tmp/testfile status=none +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +0 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + + +0 open("/tmp/testfile", O_RDONLY) = 5 + +0 sendfile(4, 5, [0], 5) = 5 + +0 > P. 1:6(5) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt b/tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt new file mode 100644 index 000000000000..0cbd43253236 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +`./defaults.sh` + +// Initialize a server socket + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_IP, IP_FREEBIND, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Connection should get accepted + +0 < S 0:0(0) win 32972 <mss 1460,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <...> + +0 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 + + +0 pipe([5, 6]) = 0 + +0 < U. 1:101(100) ack 1 win 257 urg 100 + +0 splice(4, NULL, 6, NULL, 99, 0) = 99 + +0 splice(4, NULL, 6, NULL, 1, 0) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt new file mode 100644 index 000000000000..8940726a3ec2 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP fastopen behavior with NULL as buffer pointer, but a non-zero +// buffer length. +`./defaults.sh +./set_sysctls.py /proc/sys/net/ipv4/tcp_timestamps=0` + +// Cache warmup: send a Fast Open cookie request + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 ++0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0 ++0 connect(3, ..., ...) = -1 EINPROGRESS (Operation is now in progress) ++0 > S 0:0(0) <mss 1460,nop,nop,sackOK,nop,wscale 8,FO,nop,nop> ++0 < S. 123:123(0) ack 1 win 14600 <mss 1460,nop,nop,sackOK,nop,wscale 6,FO abcd1234,nop,nop> ++0 > . 1:1(0) ack 1 ++0 close(3) = 0 ++0 > F. 1:1(0) ack 1 ++0 < F. 1:1(0) ack 2 win 92 ++0 > . 2:2(0) ack 2 + +// Test with MSG_FASTOPEN without TCP_FASTOPEN_CONNECT. ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0 ++0 sendto(4, NULL, 1, MSG_FASTOPEN, ..., ...) = -1 ++0 close(4) = 0 + +// Test with TCP_FASTOPEN_CONNECT without MSG_FASTOPEN. ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 5 ++0 fcntl(5, F_SETFL, O_RDWR|O_NONBLOCK) = 0 ++0 setsockopt(5, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0 ++0 connect(5, ..., ...) = 0 ++0 sendto(5, NULL, 1, 0, ..., ...) = -1 ++0 close(5) = 0 + +// Test with both TCP_FASTOPEN_CONNECT and MSG_FASTOPEN. ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 6 ++0 fcntl(6, F_SETFL, O_RDWR|O_NONBLOCK) = 0 ++0 setsockopt(6, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0 ++0 connect(6, ..., ...) = 0 ++0 sendto(6, NULL, 1, MSG_FASTOPEN, ..., ...) = -1 ++0 close(6) = 0 + +`/tmp/sysctl_restore_${PPID}.sh` diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt new file mode 100644 index 000000000000..b2b2cdf27e20 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that we correctly skip zero-length IOVs. +`./defaults.sh` + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 + +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(4)=[{..., 0}, {..., 40}, {..., 0}, {..., 20}], + msg_flags=0}, 0) = 60 + +0 > P. 1:61(60) ack 1 + +.01 < . 1:1(0) ack 61 win 257 + + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(4)=[{..., 0}, {..., 0}, {..., 0}, {..., 0}], + msg_flags=0}, MSG_ZEROCOPY) = 0 + + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(4)=[{..., 0}, {..., 10}, {..., 0}, {..., 50}], + msg_flags=0}, MSG_ZEROCOPY) = 60 + +0 > P. 61:121(60) ack 1 + +.01 < . 1:1(0) ack 121 win 257 diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt new file mode 100644 index 000000000000..59f5903f285c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test kernel behavior with NULL as buffer pointer + +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.2 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + + +0 write(4, NULL, 1000) = -1 EFAULT (Bad address) + +0 send(4, NULL, 1000, 0) = -1 EFAULT (Bad address) + +0 sendto(4, NULL, 1000, 0, ..., ...) = -1 EFAULT (Bad address) + + +0 < . 1:1001(1000) ack 1 win 200 + +0 read(4, NULL, 1000) = -1 EFAULT (Bad address) + +0 recv(4, NULL, 1000, 0) = -1 EFAULT (Bad address) + +0 recvfrom(4, NULL, 1000, 0, ..., ...) = -1 EFAULT (Bad address) diff --git a/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt new file mode 100644 index 000000000000..d7fdb43a8e89 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test tcpi_last_data_recv for active session +`./defaults.sh` + +// Create a socket and set it to non-blocking. ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) ++0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + ++0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) ++0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> ++.030 < S. 0:0(0) ack 1 win 10000 <mss 1000,sackOK,nop,nop,nop,wscale 8> ++0 > . 1:1(0) ack 1 + ++1 %{ assert 990 <= tcpi_last_data_recv <= 1010, tcpi_last_data_recv }% + ++0 < . 1:1001(1000) ack 1 win 300 ++0 > . 1:1(0) ack 1001 + ++0 %{ assert tcpi_last_data_recv <= 10, tcpi_last_data_recv }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt new file mode 100644 index 000000000000..a9bcd46f6cb6 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test rwnd limited time in tcp_info for client side. + +`./defaults.sh` + +// Create a socket and set it to non-blocking. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +// Server advertises 0 receive window. + +.01 < S. 0:0(0) ack 1 win 0 <mss 1000,nop,nop,sackOK> + + +0 > . 1:1(0) ack 1 + +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0 + +0 fcntl(3, F_SETFL, O_RDWR) = 0 // set back to blocking + +// Make sure that initial rwnd limited time is 0. + +0 %{ assert tcpi_rwnd_limited == 0, tcpi_rwnd_limited }% + +// Receive window limited time starts here. + +0 write(3, ..., 1000) = 1000 + +// Check that rwnd limited time in tcp_info is around 0.1s. + +.1 %{ assert 98000 <= tcpi_rwnd_limited <= 110000, tcpi_rwnd_limited }% + +// Server opens the receive window. + +.1 < . 1:1(0) ack 1 win 2000 + +// Check that rwnd limited time in tcp_info is around 0.2s. + +0 %{ assert 198000 <= tcpi_rwnd_limited <= 210000, tcpi_rwnd_limited }% + + +0 > P. 1:1001(1000) ack 1 + +// Server advertises a very small receive window. + +.03 < . 1:1(0) ack 1001 win 10 + +// Receive window limited time starts again. + +0 write(3, ..., 1000) = 1000 + +// Server opens the receive window again. + +.1 < . 1:1(0) ack 1001 win 2000 +// Check that rwnd limited time in tcp_info is around 0.3s +// and busy time is 0.3 + 0.03 (server opened small window temporarily). + +0 %{ assert 298000 <= tcpi_rwnd_limited <= 310000, tcpi_rwnd_limited;\ + assert 328000 <= tcpi_busy_time <= 340000, tcpi_busy_time;\ +}% + + +0 > P. 1001:2001(1000) ack 1 + +.02 < . 1:1(0) ack 2001 win 2000 + +0 %{ assert 348000 <= tcpi_busy_time <= 360000, tcpi_busy_time }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt new file mode 100644 index 000000000000..f0de2acd0f8e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test send-buffer-limited time in tcp_info for client side. +`./defaults.sh` + +// Create a socket and set it to non-blocking. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.01 < S. 0:0(0) ack 1 win 10000 <mss 1000,sackOK,nop,nop,nop,wscale 8> + +0 > . 1:1(0) ack 1 + +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0 + +0 fcntl(3, F_SETFL, O_RDWR) = 0 // set back to blocking + +0 setsockopt(3, SOL_SOCKET, SO_SNDBUF, [10000], 4) = 0 + +0 getsockopt(3, SOL_SOCKET, SO_SNDBUF, [20000], [4]) = 0 + + +.09...0.14 write(3, ..., 150000) = 150000 + + +.01 < . 1:1(0) ack 10001 win 10000 + + +.01 < . 1:1(0) ack 30001 win 10000 + +// cwnd goes from 40(60KB) to 80(120KB), and that we hit the tiny sndbuf limit 10KB + +.01 < . 1:1(0) ack 70001 win 10000 + + +.02 < . 1:1(0) ack 95001 win 10000 + +0 %{ assert 19000 <= tcpi_sndbuf_limited <= 21000, tcpi_sndbuf_limited; \ + assert 49000 <= tcpi_busy_time <= 52000, tcpi_busy_time; \ + assert 0 == tcpi_rwnd_limited, tcpi_rwnd_limited }% + +// This ack frees up enough buffer so we are no longer +// buffer limited (socket flag SOCK_NOSPACE is cleared) + +.02 < . 1:1(0) ack 150001 win 10000 + +0 %{ assert 19000 <= tcpi_sndbuf_limited <= 21000, tcpi_sndbuf_limited;\ + assert 69000 <= tcpi_busy_time <= 73000, tcpi_busy_time;\ + assert 0 == tcpi_rwnd_limited, tcpi_rwnd_limited }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt b/tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt new file mode 100644 index 000000000000..2087ec0c746a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that tx timestamping sends timestamps only for +// the last byte of each sendmsg. +`./defaults.sh +` + +// Create a socket and set it to non-blocking. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +// Establish connection and verify that there was no error. + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.01 < S. 0:0(0) ack 1 win 20000 <mss 1000,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 + +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0 + +0 fcntl(3, F_SETFL, O_RDWR) = 0 // set back to blocking + + +0 setsockopt(3, SOL_SOCKET, SO_TIMESTAMPING, + [SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_ID], 4) = 0 + + +0 write(3, ..., 11000) = 11000 + +0 > P. 1:10001(10000) ack 1 + +.01 < . 1:1(0) ack 10001 win 4000 + +0 > P. 10001:11001(1000) ack 1 + +.01 < . 1:1(0) ack 11001 win 4000 + +// Make sure that internal TCP timestamps are not overwritten and we have sane +// RTT measurement. + +0 %{ +assert 5000 <= tcpi_rtt <= 20000, 'srtt=%d us' % tcpi_rtt +}% + +// SCM_TSTAMP_SCHED for the last byte should be received almost immediately +// once 10001 is acked at t=20ms. +// setsockopt(..., [SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_OPT_ID], ...) +// is called after when SYN is acked. So, we expect the last byte of the first +// chunk to have a timestamp key of 10999 (i.e., 11000 - 1). + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SCHED, + ee_data=10999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SND for the last byte should be received almost immediately +// once 10001 is acked at t=20ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SND, + ee_data=10999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_ACK for the last byte should be received at t=30ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=30000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_ACK, + ee_data=10999}} + ]}, MSG_ERRQUEUE) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt b/tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt new file mode 100644 index 000000000000..876024a31110 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test tx timestamping for partial writes (IPv4). +`./defaults.sh +` + +// Create a socket and set it to non-blocking. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +// Establish connection and verify that there was no error. + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.01 < S. 0:0(0) ack 1 win 2000 <mss 1000,sackOK,TS val 700 ecr 100,nop,wscale 7> + +0 > . 1:1(0) ack 1 <nop,nop,TS val 200 ecr 700> + +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0 + + +0 setsockopt(3, SOL_SOCKET, SO_SNDBUF, [1000], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_TIMESTAMPING, + [SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_ID], 4) = 0 + +// We have a partial write. + +0 write(3, ..., 10000) = 2964 + +0 > . 1:989(988) ack 1 <nop,nop,TS val 110 ecr 700> + +0 > P. 989:1977(988) ack 1 <nop,nop,TS val 110 ecr 700> + +.01 < . 1:1(0) ack 1977 win 92 <nop,nop,TS val 800 ecr 200> + +0 > P. 1977:2965(988) ack 1 <nop,nop,TS val 114 ecr 800> + +.01 < . 1:1(0) ack 2965 win 92 <nop,nop,TS val 800 ecr 200> + +// Make sure that internal TCP timestamps are not overwritten and we have sane +// RTT measurement. + +0 %{ +assert 5000 <= tcpi_rtt <= 20000, 'srtt=%d us' % tcpi_rtt +}% + +// SCM_TSTAMP_SCHED for the first chunk should be received almost immediately +// after the first ack at t=20ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SCHED, + ee_data=2963}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SND for the first chunk should be received almost immediately +// after the first ack at t=20ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SND, + ee_data=2963}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_ACK for the first chunk should be received after the last ack at +// t=30ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=30000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_ACK, + ee_data=2963}} + ]}, MSG_ERRQUEUE) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt b/tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt new file mode 100644 index 000000000000..84d94780e6be --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test tx timestamping for server-side (IPv4). +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +0 setsockopt(4, SOL_SOCKET, SO_TIMESTAMPING, + [SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_ID], 4) = 0 + +// Write two 2KB chunks. +// setsockopt(..., [SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_OPT_ID], ...) +// is called after when SYN is acked. So, we expect the last byte of the first +// and the second chunks to have timestamp keys of 1999 (i.e., 2000 - 1) and +// 3999 (i.e., 4000 - 1) respectively. + +0 write(4, ..., 2000) = 2000 + +0 write(4, ..., 2000) = 2000 + +0 > P. 1:2001(2000) ack 1 + +0 > P. 2001:4001(2000) ack 1 + +.01 < . 1:1(0) ack 2001 win 514 + +.01 < . 1:1(0) ack 4001 win 514 + +// Make sure that internal TCP timestamps are not overwritten and we have sane +// RTT measurement. + +0 %{ +assert 5000 <= tcpi_rtt <= 20000, 'srtt=%d us' % tcpi_rtt +}% + +// SCM_TSTAMP_SCHED for the first chunk should be received almost immediately +// after write at t=10ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=10000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SCHED, + ee_data=1999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SND for the first chunk should be received almost immediately +// after write at t=10ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=10000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SND, + ee_data=1999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SCHED for the second chunk should be received almost immediately +// after that at t=10ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=10000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SCHED, + ee_data=3999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SND for the second chunk should be received almost immediately +// after that at t=10ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=10000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SND, + ee_data=3999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_ACK for the first chunk should be received at t=20ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_ACK, + ee_data=1999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_ACK for the second chunk should be received at t=30ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=30000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_ACK, + ee_data=3999}} + ]}, MSG_ERRQUEUE) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt new file mode 100644 index 000000000000..e61424a7bd0a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that we send FIN packet with correct TSval +--tcp_ts_tick_usecs=1000 +--tolerance_usecs=7000 + +`./defaults.sh` + +// Create a socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Establish a connection. + +0 < S 0:0(0) win 20000 <mss 1000,sackOK,TS val 100 ecr 0> + +0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 100 ecr 100> + +.1 < . 1:1(0) ack 1 win 20000 <nop,nop,TS val 200 ecr 100> + +0 accept(3, ..., ...) = 4 + + +1 close(4) = 0 +// Check that FIN TSval is updated properly, one second has passed since last sent packet. + +0 > F. 1:1(0) ack 1 <nop,nop,TS val 1200 ecr 200> diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt new file mode 100644 index 000000000000..174ce9a1bfc0 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that we reject TS val updates on a packet with invalid ACK sequence + +`./defaults.sh +` + +// Create a socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Establish a connection. + +.1 < S 0:0(0) win 20000 <mss 1000,sackOK,TS val 100 ecr 0> + +0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 100 ecr 100> + +.1 < . 1:1(0) ack 1 win 20000 <nop,nop,TS val 200 ecr 100> + +0 accept(3, ..., ...) = 4 + +// bad packet with high tsval (its ACK sequence is above our sndnxt) + +0 < F. 1:1(0) ack 9999 win 20000 <nop,nop,TS val 200000 ecr 100> + + + +0 < . 1:1001(1000) ack 1 win 20000 <nop,nop,TS val 201 ecr 100> + +0 > . 1:1(0) ack 1001 <nop,nop,TS val 200 ecr 201> diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt new file mode 100644 index 000000000000..2e3b3bb7493a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that we send RST packet with correct TSval +--tcp_ts_tick_usecs=1000 + +`./defaults.sh` + +// Create a socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Establish a connection. + +0 < S 0:0(0) win 20000 <mss 1000,sackOK,TS val 100 ecr 0> + +0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 100 ecr 100> + +.1 < . 1:1(0) ack 1 win 20000 <nop,nop,TS val 200 ecr 100> + +0 accept(3, ..., ...) = 4 + + +0 < . 1:1001(1000) ack 1 win 20000 <nop,nop,TS val 201 ecr 100> + +0 > . 1:1(0) ack 1001 <nop,nop,TS val 200 ecr 201> + + +1 close(4) = 0 +// Check that RST TSval is updated properly, one second has passed since last sent packet. + +0 > R. 1:1(0) ack 1001 <nop,nop,TS val 1200 ecr 201> diff --git a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt new file mode 100644 index 000000000000..183051ba0cae --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 + +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + + +0 < S 0:0(0) win 0 <mss 1460> + +0 > S. 0:0(0) ack 1 <mss 1460> + + +.1 < . 1:1(0) ack 1 win 65530 + +0 accept(3, ..., ...) = 4 + + +0 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0 + +0 write(4, ..., 24) = 24 + +0 > P. 1:25(24) ack 1 + +.1 < . 1:1(0) ack 25 win 65530 + +0 %{ assert tcpi_probes == 0, tcpi_probes; \ + assert tcpi_backoff == 0, tcpi_backoff }% + +// install a qdisc dropping all packets + +0 `tc qdisc delete dev tun0 root 2>/dev/null ; tc qdisc add dev tun0 root pfifo limit 0` + +0 write(4, ..., 24) = 24 + // When qdisc is congested we retry every 500ms + // (TCP_RESOURCE_PROBE_INTERVAL) and therefore + // we retry 6 times before hitting 3s timeout. + // First verify that the connection is alive: ++3.250 write(4, ..., 24) = 24 + // Now verify that shortly after that the socket is dead: + +.100 write(4, ..., 24) = -1 ETIMEDOUT (Connection timed out) + + +0 %{ assert tcpi_probes == 6, tcpi_probes; \ + assert tcpi_backoff == 0, tcpi_backoff }% + +0 close(4) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt new file mode 100644 index 000000000000..2efe02bfba9c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +`./defaults.sh` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +.1 < . 1:1(0) ack 1 win 32792 + + + +0 accept(3, ..., ...) = 4 + +// Okay, we received nothing, and decide to close this idle socket. +// We set TCP_USER_TIMEOUT to 3 seconds because really it is not worth +// trying hard to cleanly close this flow, at the price of keeping +// a TCP structure in kernel for about 1 minute ! + +2 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0 + +0 close(4) = 0 + + +0 > F. 1:1(0) ack 1 + +.3~+.400 > F. 1:1(0) ack 1 + +.3~+.400 > F. 1:1(0) ack 1 + +.6~+.800 > F. 1:1(0) ack 1 + +// We finally receive something from the peer, but it is way too late +// Our socket vanished because TCP_USER_TIMEOUT was really small + +0 < . 1:2(1) ack 1 win 32792 + +0 > R 1:1(0) diff --git a/tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt b/tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt new file mode 100644 index 000000000000..8bd60226ccfc --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +// Verify that established connections drop a segment without the ACK flag set. + +`./defaults.sh` + +// Create a socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Establish a connection. + +0 < S 0:0(0) win 20000 <mss 1000,sackOK,nop,nop> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +.01 < . 1:1(0) ack 1 win 20000 + +0 accept(3, ..., ...) = 4 + +// Receive a segment with no flags set, verify that it's not enqueued. + +.01 < - 1:1001(1000) win 20000 + +0 ioctl(4, SIOCINQ, [0]) = 0 + +// Receive a segment with ACK flag set, verify that it is enqueued. + +.01 < . 1:1001(1000) ack 1 win 20000 + +0 ioctl(4, SIOCINQ, [1000]) = 0 diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 1a706d03bb6b..9a85f93c33d8 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -44,9 +44,11 @@ struct tls_crypto_info_keys { }; static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, - struct tls_crypto_info_keys *tls12) + struct tls_crypto_info_keys *tls12, + char key_generation) { - memset(tls12, 0, sizeof(*tls12)); + memset(tls12, key_generation, sizeof(*tls12)); + memset(tls12, 0, sizeof(struct tls_crypto_info)); switch (cipher_type) { case TLS_CIPHER_CHACHA20_POLY1305: @@ -275,7 +277,7 @@ TEST_F(tls_basic, recseq_wrap) if (self->notls) SKIP(return, "no TLS support"); - tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12); + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12, 0); memset(&tls12.aes128.rec_seq, 0xff, sizeof(tls12.aes128.rec_seq)); ASSERT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); @@ -391,7 +393,7 @@ FIXTURE_SETUP(tls) SKIP(return, "Unsupported cipher in FIPS mode"); tls_crypto_info_init(variant->tls_version, variant->cipher_type, - &tls12); + &tls12, 0); ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); @@ -1175,7 +1177,7 @@ TEST_F(tls, bidir) struct tls_crypto_info_keys tls12; tls_crypto_info_init(variant->tls_version, variant->cipher_type, - &tls12); + &tls12, 0); ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12, tls12.len); @@ -1614,7 +1616,7 @@ TEST_F(tls, getsockopt) EXPECT_EQ(get.crypto_info.cipher_type, variant->cipher_type); /* get the full crypto_info */ - tls_crypto_info_init(variant->tls_version, variant->cipher_type, &expect); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &expect, 0); len = expect.len; memrnd(&get, sizeof(get)); EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), 0); @@ -1668,6 +1670,464 @@ TEST_F(tls, recv_efault) EXPECT_EQ(memcmp(rec2, recv_mem + 9, ret - 9), 0); } +#define TLS_RECORD_TYPE_HANDSHAKE 0x16 +/* key_update, length 1, update_not_requested */ +static const char key_update_msg[] = "\x18\x00\x00\x01\x00"; +static void tls_send_keyupdate(struct __test_metadata *_metadata, int fd) +{ + size_t len = sizeof(key_update_msg); + + EXPECT_EQ(tls_send_cmsg(fd, TLS_RECORD_TYPE_HANDSHAKE, + (char *)key_update_msg, len, 0), + len); +} + +static void tls_recv_keyupdate(struct __test_metadata *_metadata, int fd, int flags) +{ + char buf[100]; + + EXPECT_EQ(tls_recv_cmsg(_metadata, fd, TLS_RECORD_TYPE_HANDSHAKE, buf, sizeof(buf), flags), + sizeof(key_update_msg)); + EXPECT_EQ(memcmp(buf, key_update_msg, sizeof(key_update_msg)), 0); +} + +/* set the key to 0 then 1 for RX, immediately to 1 for TX */ +TEST_F(tls_basic, rekey_rx) +{ + struct tls_crypto_info_keys tls12_0, tls12_1; + char const *test_str = "test_message"; + int send_len = strlen(test_str) + 1; + char buf[20]; + int ret; + + if (self->notls) + return; + + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls12_0, 0); + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls12_1, 1); + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_1, tls12_1.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_0, tls12_0.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_1, tls12_1.len); + EXPECT_EQ(ret, 0); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +} + +/* set the key to 0 then 1 for TX, immediately to 1 for RX */ +TEST_F(tls_basic, rekey_tx) +{ + struct tls_crypto_info_keys tls12_0, tls12_1; + char const *test_str = "test_message"; + int send_len = strlen(test_str) + 1; + char buf[20]; + int ret; + + if (self->notls) + return; + + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls12_0, 0); + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls12_1, 1); + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_0, tls12_0.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_1, tls12_1.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_1, tls12_1.len); + EXPECT_EQ(ret, 0); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +} + +TEST_F(tls, rekey) +{ + char const *test_str_1 = "test_message_before_rekey"; + char const *test_str_2 = "test_message_after_rekey"; + struct tls_crypto_info_keys tls12; + int send_len; + char buf[100]; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + /* initial send/recv */ + send_len = strlen(test_str_1) + 1; + EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + /* send after rekey */ + send_len = strlen(test_str_2) + 1; + EXPECT_EQ(send(self->fd, test_str_2, send_len, 0), send_len); + + /* can't receive the KeyUpdate without a control message */ + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* recv blocking -> -EKEYEXPIRED */ + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* recv non-blocking -> -EKEYEXPIRED */ + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* update RX key */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + /* recv after rekey */ + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str_2, send_len), 0); +} + +TEST_F(tls, rekey_fail) +{ + char const *test_str_1 = "test_message_before_rekey"; + char const *test_str_2 = "test_message_after_rekey"; + struct tls_crypto_info_keys tls12; + int send_len; + char buf[100]; + + /* initial send/recv */ + send_len = strlen(test_str_1) + 1; + EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + + if (variant->tls_version != TLS_1_3_VERSION) { + /* just check that rekey is not supported and return */ + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1); + EXPECT_EQ(errno, EBUSY); + return; + } + + /* successful update */ + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + /* invalid update: change of version */ + tls_crypto_info_init(TLS_1_2_VERSION, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1); + EXPECT_EQ(errno, EINVAL); + + /* invalid update (RX socket): change of version */ + tls_crypto_info_init(TLS_1_2_VERSION, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), -1); + EXPECT_EQ(errno, EINVAL); + + /* invalid update: change of cipher */ + if (variant->cipher_type == TLS_CIPHER_AES_GCM_256) + tls_crypto_info_init(variant->tls_version, TLS_CIPHER_CHACHA20_POLY1305, &tls12, 1); + else + tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_256, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1); + EXPECT_EQ(errno, EINVAL); + + /* send after rekey, the invalid updates shouldn't have an effect */ + send_len = strlen(test_str_2) + 1; + EXPECT_EQ(send(self->fd, test_str_2, send_len, 0), send_len); + + /* can't receive the KeyUpdate without a control message */ + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* recv blocking -> -EKEYEXPIRED */ + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* recv non-blocking -> -EKEYEXPIRED */ + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* update RX key */ + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + /* recv after rekey */ + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str_2, send_len), 0); +} + +TEST_F(tls, rekey_peek) +{ + char const *test_str_1 = "test_message_before_rekey"; + struct tls_crypto_info_keys tls12; + int send_len; + char buf[100]; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + send_len = strlen(test_str_1) + 1; + EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + /* can't receive the KeyUpdate without a control message */ + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_PEEK), -1); + + /* peek KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, MSG_PEEK); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* update RX key */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); +} + +TEST_F(tls, splice_rekey) +{ + int send_len = TLS_PAYLOAD_MAX_LEN / 2; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + struct tls_crypto_info_keys tls12; + int p[2]; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + memrnd(mem_send, sizeof(mem_send)); + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); + + /* can't splice the KeyUpdate */ + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), -1); + EXPECT_EQ(errno, EINVAL); + + /* peek KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, MSG_PEEK); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* can't splice before updating the key */ + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* update RX key */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, rekey_peek_splice) +{ + char const *test_str_1 = "test_message_before_rekey"; + struct tls_crypto_info_keys tls12; + int send_len; + char buf[100]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int p[2]; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + ASSERT_GE(pipe(p), 0); + + send_len = strlen(test_str_1) + 1; + EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_recv, test_str_1, send_len), 0); +} + +TEST_F(tls, rekey_getsockopt) +{ + struct tls_crypto_info_keys tls12; + struct tls_crypto_info_keys tls12_get; + socklen_t len; + + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 0); + + len = tls12.len; + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_get, &len), 0); + EXPECT_EQ(len, tls12.len); + EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0); + + len = tls12.len; + EXPECT_EQ(getsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_get, &len), 0); + EXPECT_EQ(len, tls12.len); + EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0); + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + tls_recv_keyupdate(_metadata, self->cfd, 0); + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + len = tls12.len; + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_get, &len), 0); + EXPECT_EQ(len, tls12.len); + EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0); + + len = tls12.len; + EXPECT_EQ(getsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_get, &len), 0); + EXPECT_EQ(len, tls12.len); + EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0); +} + +TEST_F(tls, rekey_poll_pending) +{ + char const *test_str = "test_message_after_rekey"; + struct tls_crypto_info_keys tls12; + struct pollfd pfd = { }; + int send_len; + int ret; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* send immediately after rekey */ + send_len = strlen(test_str) + 1; + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + + /* key hasn't been updated, expect cfd to be non-readable */ + pfd.fd = self->cfd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + + ret = fork(); + ASSERT_GE(ret, 0); + + if (ret) { + int pid2, status; + + /* wait before installing the new key */ + sleep(1); + + /* update RX key while poll() is sleeping */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + pid2 = wait(&status); + EXPECT_EQ(pid2, ret); + EXPECT_EQ(status, 0); + } else { + pfd.fd = self->cfd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5000), 1); + + exit(!__test_passed(_metadata)); + } +} + +TEST_F(tls, rekey_poll_delay) +{ + char const *test_str = "test_message_after_rekey"; + struct tls_crypto_info_keys tls12; + struct pollfd pfd = { }; + int send_len; + int ret; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + ret = fork(); + ASSERT_GE(ret, 0); + + if (ret) { + int pid2, status; + + /* wait before installing the new key */ + sleep(1); + + /* update RX key while poll() is sleeping */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + sleep(1); + send_len = strlen(test_str) + 1; + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + + pid2 = wait(&status); + EXPECT_EQ(pid2, ret); + EXPECT_EQ(status, 0); + } else { + pfd.fd = self->cfd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5000), 1); + exit(!__test_passed(_metadata)); + } +} + FIXTURE(tls_err) { int fd, cfd; @@ -1696,7 +2156,7 @@ FIXTURE_SETUP(tls_err) int ret; tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128, - &tls12); + &tls12, 0); ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls); @@ -2118,7 +2578,7 @@ TEST(tls_v6ops) { int sfd, ret, fd; socklen_t len, len2; - tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12); + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12, 0); addr.sin6_family = AF_INET6; addr.sin6_addr = in6addr_any; @@ -2177,7 +2637,7 @@ TEST(prequeue) { len = sizeof(addr); memrnd(buf, sizeof(buf)); - tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls12); + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls12, 0); addr.sin_family = AF_INET; addr.sin_addr.s_addr = htonl(INADDR_ANY); diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index 640bc43452fa..88fa1d53ba2b 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -92,6 +92,9 @@ run_udp() { echo "udp" run_in_netns ${args} + echo "udp sendmmsg" + run_in_netns ${args} -m + echo "udp gso" run_in_netns ${args} -S 0 diff --git a/tools/testing/selftests/net/vlan_bridge_binding.sh b/tools/testing/selftests/net/vlan_bridge_binding.sh new file mode 100755 index 000000000000..e7cb8c678bde --- /dev/null +++ b/tools/testing/selftests/net/vlan_bridge_binding.sh @@ -0,0 +1,256 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +ALL_TESTS=" + test_binding_on + test_binding_off + test_binding_toggle_on + test_binding_toggle_off + test_binding_toggle_on_when_upper_down + test_binding_toggle_off_when_upper_down + test_binding_toggle_on_when_lower_down + test_binding_toggle_off_when_lower_down +" + +setup_prepare() +{ + local port + + ip_link_add br up type bridge vlan_filtering 1 + + for port in d1 d2 d3; do + ip_link_add $port type veth peer name r$port + ip_link_set_up $port + ip_link_set_up r$port + ip_link_set_master $port br + done + + bridge_vlan_add vid 11 dev br self + bridge_vlan_add vid 11 dev d1 master + + bridge_vlan_add vid 12 dev br self + bridge_vlan_add vid 12 dev d2 master + + bridge_vlan_add vid 13 dev br self + bridge_vlan_add vid 13 dev d1 master + bridge_vlan_add vid 13 dev d2 master + + bridge_vlan_add vid 14 dev br self + bridge_vlan_add vid 14 dev d1 master + bridge_vlan_add vid 14 dev d2 master + bridge_vlan_add vid 14 dev d3 master +} + +operstate_is() +{ + local dev=$1; shift + local expect=$1; shift + + local operstate=$(ip -j link show $dev | jq -r .[].operstate) + if [[ $operstate == UP ]]; then + operstate=1 + elif [[ $operstate == DOWN || $operstate == LOWERLAYERDOWN ]]; then + operstate=0 + fi + echo -n $operstate + [[ $operstate == $expect ]] +} + +check_operstate() +{ + local dev=$1; shift + local expect=$1; shift + local operstate + + operstate=$(busywait 1000 \ + operstate_is "$dev" "$expect") + check_err $? "Got operstate of $operstate, expected $expect" +} + +add_one_vlan() +{ + local link=$1; shift + local id=$1; shift + + ip_link_add $link.$id link $link type vlan id $id "$@" +} + +add_vlans() +{ + add_one_vlan br 11 "$@" + add_one_vlan br 12 "$@" + add_one_vlan br 13 "$@" + add_one_vlan br 14 "$@" +} + +set_vlans() +{ + ip link set dev br.11 "$@" + ip link set dev br.12 "$@" + ip link set dev br.13 "$@" + ip link set dev br.14 "$@" +} + +down_netdevs() +{ + local dev + + for dev in "$@"; do + ip_link_set_down $dev + done +} + +check_operstates() +{ + local opst_11=$1; shift + local opst_12=$1; shift + local opst_13=$1; shift + local opst_14=$1; shift + + check_operstate br.11 $opst_11 + check_operstate br.12 $opst_12 + check_operstate br.13 $opst_13 + check_operstate br.14 $opst_14 +} + +do_test_binding() +{ + local inject=$1; shift + local what=$1; shift + local opsts_d1=$1; shift + local opsts_d2=$1; shift + local opsts_d12=$1; shift + local opsts_d123=$1; shift + + RET=0 + + defer_scope_push + down_netdevs d1 + $inject + check_operstates $opsts_d1 + defer_scope_pop + + defer_scope_push + down_netdevs d2 + $inject + check_operstates $opsts_d2 + defer_scope_pop + + defer_scope_push + down_netdevs d1 d2 + $inject + check_operstates $opsts_d12 + defer_scope_pop + + defer_scope_push + down_netdevs d1 d2 d3 + $inject + check_operstates $opsts_d123 + defer_scope_pop + + log_test "Test bridge_binding $what" +} + +do_test_binding_on() +{ + local inject=$1; shift + local what=$1; shift + + do_test_binding "$inject" "$what" \ + "0 1 1 1" \ + "1 0 1 1" \ + "0 0 0 1" \ + "0 0 0 0" +} + +do_test_binding_off() +{ + local inject=$1; shift + local what=$1; shift + + do_test_binding "$inject" "$what" \ + "1 1 1 1" \ + "1 1 1 1" \ + "1 1 1 1" \ + "0 0 0 0" +} + +test_binding_on() +{ + add_vlans bridge_binding on + set_vlans up + do_test_binding_on : "on" +} + +test_binding_off() +{ + add_vlans bridge_binding off + set_vlans up + do_test_binding_off : "off" +} + +test_binding_toggle_on() +{ + add_vlans bridge_binding off + set_vlans up + set_vlans type vlan bridge_binding on + do_test_binding_on : "off->on" +} + +test_binding_toggle_off() +{ + add_vlans bridge_binding on + set_vlans up + set_vlans type vlan bridge_binding off + do_test_binding_off : "on->off" +} + +dfr_set_binding_on() +{ + set_vlans type vlan bridge_binding on + defer set_vlans type vlan bridge_binding off +} + +dfr_set_binding_off() +{ + set_vlans type vlan bridge_binding off + defer set_vlans type vlan bridge_binding on +} + +test_binding_toggle_on_when_lower_down() +{ + add_vlans bridge_binding off + set_vlans up + do_test_binding_on dfr_set_binding_on "off->on when lower down" +} + +test_binding_toggle_off_when_lower_down() +{ + add_vlans bridge_binding on + set_vlans up + do_test_binding_off dfr_set_binding_off "on->off when lower down" +} + +test_binding_toggle_on_when_upper_down() +{ + add_vlans bridge_binding off + set_vlans type vlan bridge_binding on + set_vlans up + do_test_binding_on : "off->on when upper down" +} + +test_binding_toggle_off_when_upper_down() +{ + add_vlans bridge_binding on + set_vlans type vlan bridge_binding off + set_vlans up + do_test_binding_off : "on->off when upper down" +} + +trap defer_scopes_cleanup EXIT +setup_prepare +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk index d43afe243779..12e7cae251be 100644 --- a/tools/testing/selftests/net/ynl.mk +++ b/tools/testing/selftests/net/ynl.mk @@ -31,7 +31,8 @@ $(OUTPUT)/libynl.a: $(YNL_SPECS) $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig $(Q)cp $(top_srcdir)/tools/net/ynl/libynl.a $(OUTPUT)/libynl.a EXTRA_CLEAN += \ - $(top_srcdir)/tools/net/ynl/lib/__pycache__ \ + $(top_srcdir)/tools/net/ynl/pyynl/__pycache__ \ + $(top_srcdir)/tools/net/ynl/pyynl/lib/__pycache__ \ $(top_srcdir)/tools/net/ynl/lib/*.[ado] \ $(OUTPUT)/.libynl-*.sig \ $(OUTPUT)/libynl.a diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index e92e0b885861..7d14a7c0cb62 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -43,6 +43,7 @@ cc-option = $(call __cc-option, $(CC),$(CLANG_CROSS_FLAGS),$(1),$(2)) # configure default variants for target kernel supported architectures XARCH_powerpc = ppc XARCH_mips = mips32le +XARCH_riscv = riscv64 XARCH = $(or $(XARCH_$(ARCH)),$(ARCH)) # map from user input variants to their kernel supported architectures @@ -51,6 +52,8 @@ ARCH_ppc64 = powerpc ARCH_ppc64le = powerpc ARCH_mips32le = mips ARCH_mips32be = mips +ARCH_riscv32 = riscv +ARCH_riscv64 = riscv ARCH := $(or $(ARCH_$(XARCH)),$(XARCH)) # kernel image names by architecture @@ -65,6 +68,8 @@ IMAGE_ppc = vmlinux IMAGE_ppc64 = vmlinux IMAGE_ppc64le = arch/powerpc/boot/zImage IMAGE_riscv = arch/riscv/boot/Image +IMAGE_riscv32 = arch/riscv/boot/Image +IMAGE_riscv64 = arch/riscv/boot/Image IMAGE_s390 = arch/s390/boot/bzImage IMAGE_loongarch = arch/loongarch/boot/vmlinuz.efi IMAGE = $(objtree)/$(IMAGE_$(XARCH)) @@ -82,6 +87,8 @@ DEFCONFIG_ppc = pmac32_defconfig DEFCONFIG_ppc64 = powernv_be_defconfig DEFCONFIG_ppc64le = powernv_defconfig DEFCONFIG_riscv = defconfig +DEFCONFIG_riscv32 = rv32_defconfig +DEFCONFIG_riscv64 = defconfig DEFCONFIG_s390 = defconfig DEFCONFIG_loongarch = defconfig DEFCONFIG = $(DEFCONFIG_$(XARCH)) @@ -104,6 +111,8 @@ QEMU_ARCH_ppc = ppc QEMU_ARCH_ppc64 = ppc64 QEMU_ARCH_ppc64le = ppc64 QEMU_ARCH_riscv = riscv64 +QEMU_ARCH_riscv32 = riscv32 +QEMU_ARCH_riscv64 = riscv64 QEMU_ARCH_s390 = s390x QEMU_ARCH_loongarch = loongarch64 QEMU_ARCH = $(QEMU_ARCH_$(XARCH)) @@ -130,6 +139,8 @@ QEMU_ARGS_ppc = -M g3beige -append "console=ttyS0 panic=-1 $(TEST:%=NOLIB QEMU_ARGS_ppc64 = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_ppc64le = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_riscv32 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_riscv64 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_s390 = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS = -m 1G $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 6fba7025c5e3..0e0e3b48a8c3 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -302,7 +302,10 @@ int expect_syszr(int expr, int llen) { int ret = 0; - if (expr) { + if (errno == ENOSYS) { + llen += printf(" = ENOSYS"); + result(llen, SKIPPED); + } else if (expr) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); result(llen, FAIL); @@ -342,7 +345,10 @@ int expect_sysne(int expr, int llen, int val) { int ret = 0; - if (expr == val) { + if (errno == ENOSYS) { + llen += printf(" = ENOSYS"); + result(llen, SKIPPED); + } else if (expr == val) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); result(llen, FAIL); @@ -367,7 +373,9 @@ int expect_syserr2(int expr, int expret, int experr1, int experr2, int llen) int _errno = errno; llen += printf(" = %d %s ", expr, errorname(_errno)); - if (expr != expret || (_errno != experr1 && _errno != experr2)) { + if (errno == ENOSYS) { + result(llen, SKIPPED); + } else if (expr != expret || (_errno != experr1 && _errno != experr2)) { ret = 1; if (experr2 == 0) llen += printf(" != (%d %s) ", expret, errorname(experr1)); @@ -1229,19 +1237,20 @@ int run_stdlib(int min, int max) static int expect_vfprintf(int llen, int c, const char *expected, const char *fmt, ...) { - int ret, fd; + int ret, pipefd[2]; ssize_t w, r; char buf[100]; FILE *memfile; va_list args; - fd = open("/tmp", O_TMPFILE | O_EXCL | O_RDWR, 0600); - if (fd == -1) { - result(llen, SKIPPED); - return 0; + ret = pipe(pipefd); + if (ret == -1) { + llen += printf(" pipe() != %s", strerror(errno)); + result(llen, FAIL); + return 1; } - memfile = fdopen(fd, "w+"); + memfile = fdopen(pipefd[1], "w"); if (!memfile) { result(llen, FAIL); return 1; @@ -1257,13 +1266,10 @@ static int expect_vfprintf(int llen, int c, const char *expected, const char *fm return 1; } - fflush(memfile); - lseek(fd, 0, SEEK_SET); - - r = read(fd, buf, sizeof(buf) - 1); - fclose(memfile); + r = read(pipefd[0], buf, sizeof(buf) - 1); + if (r != w) { llen += printf(" written(%d) != read(%d)", (int)w, (int)r); result(llen, FAIL); @@ -1323,7 +1329,8 @@ static int run_protection(int min __attribute__((unused)), int max __attribute__((unused))) { pid_t pid; - int llen = 0, status; + int llen = 0, ret; + siginfo_t siginfo = {}; struct rlimit rlimit = { 0, 0 }; llen += printf("0 -fstackprotector "); @@ -1361,10 +1368,11 @@ static int run_protection(int min __attribute__((unused)), return 1; default: - pid = waitpid(pid, &status, 0); + ret = waitid(P_PID, pid, &siginfo, WEXITED); - if (pid == -1 || !WIFSIGNALED(status) || WTERMSIG(status) != SIGABRT) { - llen += printf("waitpid()"); + if (ret != 0 || siginfo.si_signo != SIGCHLD || + siginfo.si_code != CLD_KILLED || siginfo.si_status != SIGABRT) { + llen += printf("waitid()"); result(llen, FAIL); return 1; } diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh index e7ecda4ae796..9c5160c53881 100755 --- a/tools/testing/selftests/nolibc/run-tests.sh +++ b/tools/testing/selftests/nolibc/run-tests.sh @@ -17,7 +17,7 @@ perform_download=0 test_mode=system werror=1 llvm= -archs="i386 x86_64 arm64 arm mips32le mips32be ppc ppc64 ppc64le riscv s390 loongarch" +archs="i386 x86_64 arm64 arm mips32le mips32be ppc ppc64 ppc64le riscv32 riscv64 s390 loongarch" TEMP=$(getopt -o 'j:d:c:b:a:m:pelh' -n "$0" -- "$@") @@ -143,6 +143,13 @@ test_arch() { arch=$1 ct_arch=$(crosstool_arch "$arch") ct_abi=$(crosstool_abi "$1") + + if [ ! -d "${download_location}gcc-${crosstool_version}-nolibc/${ct_arch}-${ct_abi}/bin/." ]; then + echo "No toolchain found in ${download_location}gcc-${crosstool_version}-nolibc/${ct_arch}-${ct_abi}." + echo "Did you install the toolchains or set the correct arch ? Rerun with -h for help." + return 1 + fi + cross_compile=$(realpath "${download_location}gcc-${crosstool_version}-nolibc/${ct_arch}-${ct_abi}/bin/${ct_arch}-${ct_abi}-") build_dir="${build_location}/${arch}" if [ "$werror" -ne 0 ]; then diff --git a/tools/testing/selftests/pci_endpoint/.gitignore b/tools/testing/selftests/pci_endpoint/.gitignore new file mode 100644 index 000000000000..6a4837a3e034 --- /dev/null +++ b/tools/testing/selftests/pci_endpoint/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +pci_endpoint_test diff --git a/tools/testing/selftests/pci_endpoint/Makefile b/tools/testing/selftests/pci_endpoint/Makefile new file mode 100644 index 000000000000..bf21ebf20b4a --- /dev/null +++ b/tools/testing/selftests/pci_endpoint/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -O2 -Wl,-no-as-needed -Wall $(KHDR_INCLUDES) +LDFLAGS += -lrt -lpthread -lm + +TEST_GEN_PROGS = pci_endpoint_test + +include ../lib.mk diff --git a/tools/testing/selftests/pci_endpoint/config b/tools/testing/selftests/pci_endpoint/config new file mode 100644 index 000000000000..7cdcf117db8d --- /dev/null +++ b/tools/testing/selftests/pci_endpoint/config @@ -0,0 +1,4 @@ +CONFIG_PCI_ENDPOINT=y +CONFIG_PCI_ENDPOINT_CONFIGFS=y +CONFIG_PCI_EPF_TEST=m +CONFIG_PCI_ENDPOINT_TEST=m diff --git a/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c new file mode 100644 index 000000000000..c267b822c108 --- /dev/null +++ b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Kselftest for PCI Endpoint Subsystem + * + * Copyright (c) 2022 Samsung Electronics Co., Ltd. + * https://www.samsung.com + * Author: Aman Gupta <aman1.gupta@samsung.com> + * + * Copyright (c) 2024, Linaro Ltd. + * Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> + */ + +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ioctl.h> +#include <unistd.h> + +#include "../../../../include/uapi/linux/pcitest.h" + +#include "../kselftest_harness.h" + +#define pci_ep_ioctl(cmd, arg) \ +({ \ + ret = ioctl(self->fd, cmd, arg); \ + ret = ret < 0 ? -errno : 0; \ +}) + +static const char *test_device = "/dev/pci-endpoint-test.0"; +static const unsigned long test_size[5] = { 1, 1024, 1025, 1024000, 1024001 }; + +FIXTURE(pci_ep_bar) +{ + int fd; +}; + +FIXTURE_SETUP(pci_ep_bar) +{ + self->fd = open(test_device, O_RDWR); + + ASSERT_NE(-1, self->fd) TH_LOG("Can't open PCI Endpoint Test device"); +} + +FIXTURE_TEARDOWN(pci_ep_bar) +{ + close(self->fd); +} + +FIXTURE_VARIANT(pci_ep_bar) +{ + int barno; +}; + +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR0) { .barno = 0 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR1) { .barno = 1 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR2) { .barno = 2 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR3) { .barno = 3 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR4) { .barno = 4 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR5) { .barno = 5 }; + +TEST_F(pci_ep_bar, BAR_TEST) +{ + int ret; + + pci_ep_ioctl(PCITEST_BAR, variant->barno); + EXPECT_FALSE(ret) TH_LOG("Test failed for BAR%d", variant->barno); +} + +FIXTURE(pci_ep_basic) +{ + int fd; +}; + +FIXTURE_SETUP(pci_ep_basic) +{ + self->fd = open(test_device, O_RDWR); + + ASSERT_NE(-1, self->fd) TH_LOG("Can't open PCI Endpoint Test device"); +} + +FIXTURE_TEARDOWN(pci_ep_basic) +{ + close(self->fd); +} + +TEST_F(pci_ep_basic, CONSECUTIVE_BAR_TEST) +{ + int ret; + + pci_ep_ioctl(PCITEST_BARS, 0); + EXPECT_FALSE(ret) TH_LOG("Consecutive BAR test failed"); +} + +TEST_F(pci_ep_basic, LEGACY_IRQ_TEST) +{ + int ret; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 0); + ASSERT_EQ(0, ret) TH_LOG("Can't set Legacy IRQ type"); + + pci_ep_ioctl(PCITEST_LEGACY_IRQ, 0); + EXPECT_FALSE(ret) TH_LOG("Test failed for Legacy IRQ"); +} + +TEST_F(pci_ep_basic, MSI_TEST) +{ + int ret, i; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type"); + + for (i = 1; i <= 32; i++) { + pci_ep_ioctl(PCITEST_MSI, i); + EXPECT_FALSE(ret) TH_LOG("Test failed for MSI%d", i); + } +} + +TEST_F(pci_ep_basic, MSIX_TEST) +{ + int ret, i; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 2); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI-X IRQ type"); + + for (i = 1; i <= 2048; i++) { + pci_ep_ioctl(PCITEST_MSIX, i); + EXPECT_FALSE(ret) TH_LOG("Test failed for MSI-X%d", i); + } +} + +FIXTURE(pci_ep_data_transfer) +{ + int fd; +}; + +FIXTURE_SETUP(pci_ep_data_transfer) +{ + self->fd = open(test_device, O_RDWR); + + ASSERT_NE(-1, self->fd) TH_LOG("Can't open PCI Endpoint Test device"); +} + +FIXTURE_TEARDOWN(pci_ep_data_transfer) +{ + close(self->fd); +} + +FIXTURE_VARIANT(pci_ep_data_transfer) +{ + bool use_dma; +}; + +FIXTURE_VARIANT_ADD(pci_ep_data_transfer, memcpy) +{ + .use_dma = false, +}; + +FIXTURE_VARIANT_ADD(pci_ep_data_transfer, dma) +{ + .use_dma = true, +}; + +TEST_F(pci_ep_data_transfer, READ_TEST) +{ + struct pci_endpoint_test_xfer_param param = {}; + int ret, i; + + if (variant->use_dma) + param.flags = PCITEST_FLAGS_USE_DMA; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type"); + + for (i = 0; i < ARRAY_SIZE(test_size); i++) { + param.size = test_size[i]; + pci_ep_ioctl(PCITEST_READ, ¶m); + EXPECT_FALSE(ret) TH_LOG("Test failed for size (%ld)", + test_size[i]); + } +} + +TEST_F(pci_ep_data_transfer, WRITE_TEST) +{ + struct pci_endpoint_test_xfer_param param = {}; + int ret, i; + + if (variant->use_dma) + param.flags = PCITEST_FLAGS_USE_DMA; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type"); + + for (i = 0; i < ARRAY_SIZE(test_size); i++) { + param.size = test_size[i]; + pci_ep_ioctl(PCITEST_WRITE, ¶m); + EXPECT_FALSE(ret) TH_LOG("Test failed for size (%ld)", + test_size[i]); + } +} + +TEST_F(pci_ep_data_transfer, COPY_TEST) +{ + struct pci_endpoint_test_xfer_param param = {}; + int ret, i; + + if (variant->use_dma) + param.flags = PCITEST_FLAGS_USE_DMA; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type"); + + for (i = 0; i < ARRAY_SIZE(test_size); i++) { + param.size = test_size[i]; + pci_ep_ioctl(PCITEST_COPY, ¶m); + EXPECT_FALSE(ret) TH_LOG("Test failed for size (%ld)", + test_size[i]); + } +} +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pid_namespace/.gitignore b/tools/testing/selftests/pid_namespace/.gitignore index 93ab9d7e5b7e..5118f0f3edf4 100644 --- a/tools/testing/selftests/pid_namespace/.gitignore +++ b/tools/testing/selftests/pid_namespace/.gitignore @@ -1 +1,2 @@ +pid_max regression_enomem diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile index 9286a1d22cd3..b972f55d07ae 100644 --- a/tools/testing/selftests/pid_namespace/Makefile +++ b/tools/testing/selftests/pid_namespace/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g $(KHDR_INCLUDES) -TEST_GEN_PROGS = regression_enomem +TEST_GEN_PROGS = regression_enomem pid_max LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h diff --git a/tools/testing/selftests/pid_namespace/pid_max.c b/tools/testing/selftests/pid_namespace/pid_max.c new file mode 100644 index 000000000000..51c414faabb0 --- /dev/null +++ b/tools/testing/selftests/pid_namespace/pid_max.c @@ -0,0 +1,358 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#define _GNU_SOURCE +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/types.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/wait.h> + +#include "../kselftest_harness.h" +#include "../pidfd/pidfd.h" + +#define __STACK_SIZE (8 * 1024 * 1024) +static pid_t do_clone(int (*fn)(void *), void *arg, int flags) +{ + char *stack; + pid_t ret; + + stack = malloc(__STACK_SIZE); + if (!stack) + return -ENOMEM; + +#ifdef __ia64__ + ret = __clone2(fn, stack, __STACK_SIZE, flags | SIGCHLD, arg); +#else + ret = clone(fn, stack + __STACK_SIZE, flags | SIGCHLD, arg); +#endif + free(stack); + return ret; +} + +static int pid_max_cb(void *data) +{ + int fd, ret; + pid_t pid; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return -1; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return -1; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return -1; + } + + ret = write(fd, "500", sizeof("500") - 1); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return -1; + } + + for (int i = 0; i < 501; i++) { + pid = fork(); + if (pid == 0) + exit(EXIT_SUCCESS); + wait_for_pid(pid); + if (pid > 500) { + fprintf(stderr, "Managed to create pid number beyond limit\n"); + return -1; + } + } + + return 0; +} + +static int pid_max_nested_inner(void *data) +{ + int fret = -1; + pid_t pids[2]; + int fd, i, ret; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return fret; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return fret; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return fret; + } + + ret = write(fd, "500", sizeof("500") - 1); + close(fd); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return fret; + } + + pids[0] = fork(); + if (pids[0] < 0) { + fprintf(stderr, "Failed to create first new process\n"); + return fret; + } + + if (pids[0] == 0) + exit(EXIT_SUCCESS); + + pids[1] = fork(); + wait_for_pid(pids[0]); + if (pids[1] >= 0) { + if (pids[1] == 0) + exit(EXIT_SUCCESS); + wait_for_pid(pids[1]); + + fprintf(stderr, "Managed to create process even though ancestor pid namespace had a limit\n"); + return fret; + } + + /* Now make sure that we wrap pids at 400. */ + for (i = 0; i < 510; i++) { + pid_t pid; + + pid = fork(); + if (pid < 0) + return fret; + + if (pid == 0) + exit(EXIT_SUCCESS); + + wait_for_pid(pid); + if (pid >= 500) { + fprintf(stderr, "Managed to create process with pid %d beyond configured limit\n", pid); + return fret; + } + } + + return 0; +} + +static int pid_max_nested_outer(void *data) +{ + int fret = -1, nr_procs = 400; + pid_t pids[1000]; + int fd, i, ret; + pid_t pid; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return fret; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return fret; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return fret; + } + + ret = write(fd, "400", sizeof("400") - 1); + close(fd); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return fret; + } + + /* + * Create 397 processes. This leaves room for do_clone() (398) and + * one more 399. So creating another process needs to fail. + */ + for (nr_procs = 0; nr_procs < 396; nr_procs++) { + pid = fork(); + if (pid < 0) + goto reap; + + if (pid == 0) + exit(EXIT_SUCCESS); + + pids[nr_procs] = pid; + } + + pid = do_clone(pid_max_nested_inner, NULL, CLONE_NEWPID | CLONE_NEWNS); + if (pid < 0) { + fprintf(stderr, "%m - Failed to clone nested pidns\n"); + goto reap; + } + + if (wait_for_pid(pid)) { + fprintf(stderr, "%m - Nested pid_max failed\n"); + goto reap; + } + + fret = 0; + +reap: + for (int i = 0; i < nr_procs; i++) + wait_for_pid(pids[i]); + + return fret; +} + +static int pid_max_nested_limit_inner(void *data) +{ + int fret = -1, nr_procs = 400; + int fd, ret; + pid_t pid; + pid_t pids[1000]; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return fret; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return fret; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return fret; + } + + ret = write(fd, "500", sizeof("500") - 1); + close(fd); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return fret; + } + + for (nr_procs = 0; nr_procs < 500; nr_procs++) { + pid = fork(); + if (pid < 0) + break; + + if (pid == 0) + exit(EXIT_SUCCESS); + + pids[nr_procs] = pid; + } + + if (nr_procs >= 400) { + fprintf(stderr, "Managed to create processes beyond the configured outer limit\n"); + goto reap; + } + + fret = 0; + +reap: + for (int i = 0; i < nr_procs; i++) + wait_for_pid(pids[i]); + + return fret; +} + +static int pid_max_nested_limit_outer(void *data) +{ + int fd, ret; + pid_t pid; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return -1; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return -1; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return -1; + } + + ret = write(fd, "400", sizeof("400") - 1); + close(fd); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return -1; + } + + pid = do_clone(pid_max_nested_limit_inner, NULL, CLONE_NEWPID | CLONE_NEWNS); + if (pid < 0) { + fprintf(stderr, "%m - Failed to clone nested pidns\n"); + return -1; + } + + if (wait_for_pid(pid)) { + fprintf(stderr, "%m - Nested pid_max failed\n"); + return -1; + } + + return 0; +} + +TEST(pid_max_simple) +{ + pid_t pid; + + + pid = do_clone(pid_max_cb, NULL, CLONE_NEWPID | CLONE_NEWNS); + ASSERT_GT(pid, 0); + ASSERT_EQ(0, wait_for_pid(pid)); +} + +TEST(pid_max_nested_limit) +{ + pid_t pid; + + pid = do_clone(pid_max_nested_limit_outer, NULL, CLONE_NEWPID | CLONE_NEWNS); + ASSERT_GT(pid, 0); + ASSERT_EQ(0, wait_for_pid(pid)); +} + +TEST(pid_max_nested) +{ + pid_t pid; + + pid = do_clone(pid_max_nested_outer, NULL, CLONE_NEWPID | CLONE_NEWNS); + ASSERT_GT(pid, 0); + ASSERT_EQ(0, wait_for_pid(pid)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 973198a3ec3d..bf92481f925c 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -6,3 +6,5 @@ pidfd_wait pidfd_fdinfo_test pidfd_getfd_test pidfd_setns_test +pidfd_file_handle_test +pidfd_bind_mount diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index d731e3e76d5b..301343a11b62 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -2,7 +2,8 @@ CFLAGS += -g $(KHDR_INCLUDES) -pthread -Wall TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \ - pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test + pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test \ + pidfd_file_handle_test pidfd_bind_mount include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 88d6830ee004..0b96ac4b8ce5 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -12,11 +12,11 @@ #include <stdlib.h> #include <string.h> #include <syscall.h> -#include <sys/mount.h> #include <sys/types.h> #include <sys/wait.h> #include "../kselftest.h" +#include "../clone3/clone3_selftests.h" #ifndef P_PIDFD #define P_PIDFD 3 @@ -68,6 +68,11 @@ #define PIDFD_SKIP 3 #define PIDFD_XFAIL 4 +static inline int sys_waitid(int which, pid_t pid, siginfo_t *info, int options) +{ + return syscall(__NR_waitid, which, pid, info, options, NULL); +} + static inline int wait_for_pid(pid_t pid) { int status, ret; @@ -114,4 +119,37 @@ static inline int sys_memfd_create(const char *name, unsigned int flags) return syscall(__NR_memfd_create, name, flags); } +static inline pid_t create_child(int *pidfd, unsigned flags) +{ + struct __clone_args args = { + .flags = CLONE_PIDFD | flags, + .exit_signal = SIGCHLD, + .pidfd = ptr_to_u64(pidfd), + }; + + return sys_clone3(&args, sizeof(struct __clone_args)); +} + +static inline ssize_t read_nointr(int fd, void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = read(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + +static inline ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = write(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + #endif /* __PIDFD_H */ diff --git a/tools/testing/selftests/pidfd/pidfd_bind_mount.c b/tools/testing/selftests/pidfd/pidfd_bind_mount.c new file mode 100644 index 000000000000..7822dd080258 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_bind_mount.c @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Christian Brauner <brauner@kernel.org> + +#define _GNU_SOURCE +#include <fcntl.h> +#include <limits.h> +#include <sched.h> +#include <stdio.h> +#include <string.h> +#include <linux/fs.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <sys/mount.h> +#include <unistd.h> + +#include "pidfd.h" +#include "../kselftest_harness.h" + +#ifndef __NR_open_tree + #if defined __alpha__ + #define __NR_open_tree 538 + #elif defined _MIPS_SIM + #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */ + #define __NR_open_tree 4428 + #endif + #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */ + #define __NR_open_tree 6428 + #endif + #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */ + #define __NR_open_tree 5428 + #endif + #elif defined __ia64__ + #define __NR_open_tree (428 + 1024) + #else + #define __NR_open_tree 428 + #endif +#endif + +#ifndef __NR_move_mount + #if defined __alpha__ + #define __NR_move_mount 539 + #elif defined _MIPS_SIM + #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */ + #define __NR_move_mount 4429 + #endif + #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */ + #define __NR_move_mount 6429 + #endif + #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */ + #define __NR_move_mount 5429 + #endif + #elif defined __ia64__ + #define __NR_move_mount (428 + 1024) + #else + #define __NR_move_mount 429 + #endif +#endif + +#ifndef MOVE_MOUNT_F_EMPTY_PATH +#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */ +#endif + +#ifndef MOVE_MOUNT_F_EMPTY_PATH +#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ +#endif + +static inline int sys_move_mount(int from_dfd, const char *from_pathname, + int to_dfd, const char *to_pathname, + unsigned int flags) +{ + return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd, + to_pathname, flags); +} + +#ifndef OPEN_TREE_CLONE +#define OPEN_TREE_CLONE 1 +#endif + +#ifndef OPEN_TREE_CLOEXEC +#define OPEN_TREE_CLOEXEC O_CLOEXEC +#endif + +#ifndef AT_RECURSIVE +#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */ +#endif + +static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags) +{ + return syscall(__NR_open_tree, dfd, filename, flags); +} + +FIXTURE(pidfd_bind_mount) { + char template[PATH_MAX]; + int fd_tmp; + int pidfd; + struct stat st1; + struct stat st2; + __u32 gen1; + __u32 gen2; + bool must_unmount; +}; + +FIXTURE_SETUP(pidfd_bind_mount) +{ + self->fd_tmp = -EBADF; + self->must_unmount = false; + ASSERT_EQ(unshare(CLONE_NEWNS), 0); + ASSERT_LE(snprintf(self->template, PATH_MAX, "%s", P_tmpdir "/pidfd_bind_mount_XXXXXX"), PATH_MAX); + self->fd_tmp = mkstemp(self->template); + ASSERT_GE(self->fd_tmp, 0); + self->pidfd = sys_pidfd_open(getpid(), 0); + ASSERT_GE(self->pidfd, 0); + ASSERT_GE(fstat(self->pidfd, &self->st1), 0); + ASSERT_EQ(ioctl(self->pidfd, FS_IOC_GETVERSION, &self->gen1), 0); +} + +FIXTURE_TEARDOWN(pidfd_bind_mount) +{ + ASSERT_EQ(close(self->fd_tmp), 0); + if (self->must_unmount) + ASSERT_EQ(umount2(self->template, 0), 0); + ASSERT_EQ(unlink(self->template), 0); +} + +/* + * Test that a detached mount can be created for a pidfd and then + * attached to the filesystem hierarchy. + */ +TEST_F(pidfd_bind_mount, bind_mount) +{ + int fd_tree; + + fd_tree = sys_open_tree(self->pidfd, "", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | AT_EMPTY_PATH); + ASSERT_GE(fd_tree, 0); + + ASSERT_EQ(move_mount(fd_tree, "", self->fd_tmp, "", MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH), 0); + self->must_unmount = true; + + ASSERT_EQ(close(fd_tree), 0); +} + +/* Test that a pidfd can be reopened through procfs. */ +TEST_F(pidfd_bind_mount, reopen) +{ + int pidfd; + char proc_path[PATH_MAX]; + + sprintf(proc_path, "/proc/self/fd/%d", self->pidfd); + pidfd = open(proc_path, O_RDONLY | O_NOCTTY | O_CLOEXEC); + ASSERT_GE(pidfd, 0); + + ASSERT_GE(fstat(self->pidfd, &self->st2), 0); + ASSERT_EQ(ioctl(self->pidfd, FS_IOC_GETVERSION, &self->gen2), 0); + + ASSERT_TRUE(self->st1.st_dev == self->st2.st_dev && self->st1.st_ino == self->st2.st_ino); + ASSERT_TRUE(self->gen1 == self->gen2); + + ASSERT_EQ(close(pidfd), 0); +} + +/* + * Test that a detached mount can be created for a pidfd and then + * attached to the filesystem hierarchy and reopened. + */ +TEST_F(pidfd_bind_mount, bind_mount_reopen) +{ + int fd_tree, fd_pidfd_mnt; + + fd_tree = sys_open_tree(self->pidfd, "", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | AT_EMPTY_PATH); + ASSERT_GE(fd_tree, 0); + + ASSERT_EQ(move_mount(fd_tree, "", self->fd_tmp, "", MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH), 0); + self->must_unmount = true; + + fd_pidfd_mnt = openat(-EBADF, self->template, O_RDONLY | O_NOCTTY | O_CLOEXEC); + ASSERT_GE(fd_pidfd_mnt, 0); + + ASSERT_GE(fstat(fd_tree, &self->st2), 0); + ASSERT_EQ(ioctl(fd_pidfd_mnt, FS_IOC_GETVERSION, &self->gen2), 0); + + ASSERT_TRUE(self->st1.st_dev == self->st2.st_dev && self->st1.st_ino == self->st2.st_ino); + ASSERT_TRUE(self->gen1 == self->gen2); + + ASSERT_EQ(close(fd_tree), 0); + ASSERT_EQ(close(fd_pidfd_mnt), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd_file_handle_test.c b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c new file mode 100644 index 000000000000..439b9c6c0457 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c @@ -0,0 +1,503 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <linux/types.h> +#include <poll.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> +#include <sys/socket.h> +#include <linux/kcmp.h> +#include <sys/stat.h> + +#include "pidfd.h" +#include "../kselftest_harness.h" + +FIXTURE(file_handle) +{ + pid_t pid; + int pidfd; + + pid_t child_pid1; + int child_pidfd1; + + pid_t child_pid2; + int child_pidfd2; + + pid_t child_pid3; + int child_pidfd3; +}; + +FIXTURE_SETUP(file_handle) +{ + int ret; + int ipc_sockets[2]; + char c; + + self->pid = getpid(); + self->pidfd = sys_pidfd_open(self->pid, 0); + ASSERT_GE(self->pidfd, 0); + + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + + self->child_pid1 = create_child(&self->child_pidfd1, CLONE_NEWUSER); + EXPECT_GE(self->child_pid1, 0); + + if (self->child_pid1 == 0) { + close(ipc_sockets[0]); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + + pause(); + _exit(EXIT_SUCCESS); + } + + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + + self->child_pid2 = create_child(&self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWPID); + EXPECT_GE(self->child_pid2, 0); + + if (self->child_pid2 == 0) { + close(ipc_sockets[0]); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + + pause(); + _exit(EXIT_SUCCESS); + } + + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + + self->child_pid3 = create_child(&self->child_pidfd3, CLONE_NEWUSER | CLONE_NEWPID); + EXPECT_GE(self->child_pid3, 0); + + if (self->child_pid3 == 0) { + close(ipc_sockets[0]); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + + pause(); + _exit(EXIT_SUCCESS); + } + + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); +} + +FIXTURE_TEARDOWN(file_handle) +{ + EXPECT_EQ(close(self->pidfd), 0); + + EXPECT_EQ(sys_pidfd_send_signal(self->child_pidfd1, SIGKILL, NULL, 0), 0); + if (self->child_pidfd1 >= 0) + EXPECT_EQ(0, close(self->child_pidfd1)); + + EXPECT_EQ(sys_waitid(P_PID, self->child_pid1, NULL, WEXITED), 0); + + EXPECT_EQ(sys_pidfd_send_signal(self->child_pidfd2, SIGKILL, NULL, 0), 0); + if (self->child_pidfd2 >= 0) + EXPECT_EQ(0, close(self->child_pidfd2)); + + EXPECT_EQ(sys_waitid(P_PID, self->child_pid2, NULL, WEXITED), 0); + + if (self->child_pidfd3 >= 0) { + EXPECT_EQ(sys_pidfd_send_signal(self->child_pidfd3, SIGKILL, NULL, 0), 0); + EXPECT_EQ(0, close(self->child_pidfd3)); + EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED), 0); + } +} + +/* + * Test that we can decode a pidfs file handle in the same pid + * namespace. + */ +TEST_F(file_handle, file_handle_same_pidns) +{ + int mnt_id; + struct file_handle *fh; + int pidfd = -EBADF; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd1, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd1, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, O_CLOEXEC); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, O_NONBLOCK); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + free(fh); +} + +/* + * Test that we can decode a pidfs file handle from a child pid + * namespace. + */ +TEST_F(file_handle, file_handle_child_pidns) +{ + int mnt_id; + struct file_handle *fh; + int pidfd = -EBADF; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd2, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, O_CLOEXEC); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, O_NONBLOCK); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + free(fh); +} + +/* + * Test that we fail to decode a pidfs file handle from an ancestor + * child pid namespace. + */ +TEST_F(file_handle, file_handle_foreign_pidns) +{ + int mnt_id; + struct file_handle *fh; + pid_t pid; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->pidfd, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(setns(self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWPID), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int pidfd = open_by_handle_at(self->pidfd, fh, 0); + if (pidfd >= 0) { + TH_LOG("Managed to open pidfd outside of the caller's pid namespace hierarchy"); + _exit(1); + } + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); + + free(fh); +} + +/* + * Test that we can decode a pidfs file handle of a process that has + * exited but not been reaped. + */ +TEST_F(file_handle, pid_has_exited) +{ + int mnt_id, pidfd, child_pidfd3; + struct file_handle *fh; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd3, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd3, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + child_pidfd3 = self->child_pidfd3; + self->child_pidfd3 = -EBADF; + EXPECT_EQ(sys_pidfd_send_signal(child_pidfd3, SIGKILL, NULL, 0), 0); + EXPECT_EQ(close(child_pidfd3), 0); + EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED | WNOWAIT), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED), 0); +} + +/* + * Test that we fail to decode a pidfs file handle of a process that has + * already been reaped. + */ +TEST_F(file_handle, pid_has_been_reaped) +{ + int mnt_id, pidfd, child_pidfd3; + struct file_handle *fh; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd3, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd3, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + child_pidfd3 = self->child_pidfd3; + self->child_pidfd3 = -EBADF; + EXPECT_EQ(sys_pidfd_send_signal(child_pidfd3, SIGKILL, NULL, 0), 0); + EXPECT_EQ(close(child_pidfd3), 0); + EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_LT(pidfd, 0); +} + +/* + * Test valid flags to open a pidfd file handle. Note, that + * PIDFD_NONBLOCK is defined as O_NONBLOCK and O_NONBLOCK is an alias to + * O_NDELAY. Also note that PIDFD_THREAD is an alias for O_EXCL. + */ +TEST_F(file_handle, open_by_handle_at_valid_flags) +{ + int mnt_id; + struct file_handle *fh; + int pidfd = -EBADF; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd2, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, + O_RDONLY | + O_WRONLY | + O_RDWR | + O_NONBLOCK | + O_NDELAY | + O_CLOEXEC | + O_EXCL); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); +} + +/* + * Test that invalid flags passed to open a pidfd file handle are + * rejected. + */ +TEST_F(file_handle, open_by_handle_at_invalid_flags) +{ + int mnt_id; + struct file_handle *fh; + int pidfd = -EBADF; + static const struct invalid_pidfs_file_handle_flags { + int oflag; + const char *oflag_name; + } invalid_pidfs_file_handle_flags[] = { + { FASYNC, "FASYNC" }, + { O_CREAT, "O_CREAT" }, + { O_NOCTTY, "O_NOCTTY" }, + { O_CREAT, "O_CREAT" }, + { O_TRUNC, "O_TRUNC" }, + { O_APPEND, "O_APPEND" }, + { O_SYNC, "O_SYNC" }, + { O_DSYNC, "O_DSYNC" }, + { O_DIRECT, "O_DIRECT" }, + { O_DIRECTORY, "O_DIRECTORY" }, + { O_NOFOLLOW, "O_NOFOLLOW" }, + { O_NOATIME, "O_NOATIME" }, + { O_PATH, "O_PATH" }, + { O_TMPFILE, "O_TMPFILE" }, + /* + * O_LARGEFILE is added implicitly by + * open_by_handle_at() so pidfs simply masks it off. + */ + }; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + for (int i = 0; i < ARRAY_SIZE(invalid_pidfs_file_handle_flags); i++) { + pidfd = open_by_handle_at(self->pidfd, fh, invalid_pidfs_file_handle_flags[i].oflag); + ASSERT_LT(pidfd, 0) { + TH_LOG("open_by_handle_at() succeeded with invalid flags: %s", invalid_pidfs_file_handle_flags[i].oflag_name); + } + } +} + +/* Test that lookup fails. */ +TEST_F(file_handle, lookup_must_fail) +{ + int mnt_id; + struct file_handle *fh; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_NE(name_to_handle_at(self->child_pidfd2, "lookup-is-not-possible-with-pidfs", fh, &mnt_id, AT_EMPTY_PATH), 0); + ASSERT_EQ(errno, ENOTDIR); + ASSERT_NE(name_to_handle_at(self->child_pidfd2, "lookup-is-not-possible-with-pidfs", fh, &mnt_id, 0), 0); + ASSERT_EQ(errno, ENOTDIR); +} + +#ifndef AT_HANDLE_CONNECTABLE +#define AT_HANDLE_CONNECTABLE 0x002 +#endif + +/* + * Test that AT_HANDLE_CONNECTABLE is rejected. Connectable file handles + * don't make sense for pidfs. Note that currently AT_HANDLE_CONNECTABLE + * is rejected because it is incompatible with AT_EMPTY_PATH which is + * required with pidfds as we don't support lookup. + */ +TEST_F(file_handle, invalid_name_to_handle_at_flags) +{ + int mnt_id; + struct file_handle *fh; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_NE(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH | AT_HANDLE_CONNECTABLE), 0); +} + +#ifndef AT_HANDLE_FID +#define AT_HANDLE_FID 0x200 +#endif + +/* + * Test that a request with AT_HANDLE_FID always leads to decodable file + * handle as pidfs always provides export operations. + */ +TEST_F(file_handle, valid_name_to_handle_at_flags) +{ + int mnt_id, pidfd; + struct file_handle *fh; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH | AT_HANDLE_FID), 0); + + ASSERT_EQ(fstat(self->child_pidfd2, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index 7c2a4349170a..222f8131283b 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -19,7 +19,6 @@ #include <linux/ioctl.h> #include "pidfd.h" -#include "../clone3/clone3_selftests.h" #include "../kselftest_harness.h" #ifndef PIDFS_IOCTL_MAGIC @@ -118,22 +117,6 @@ FIXTURE(current_nsset) int child_pidfd_derived_nsfds2[PIDFD_NS_MAX]; }; -static int sys_waitid(int which, pid_t pid, int options) -{ - return syscall(__NR_waitid, which, pid, NULL, options, NULL); -} - -pid_t create_child(int *pidfd, unsigned flags) -{ - struct __clone_args args = { - .flags = CLONE_PIDFD | flags, - .exit_signal = SIGCHLD, - .pidfd = ptr_to_u64(pidfd), - }; - - return sys_clone3(&args, sizeof(struct clone_args)); -} - static bool switch_timens(void) { int fd, ret; @@ -150,28 +133,6 @@ static bool switch_timens(void) return ret == 0; } -static ssize_t read_nointr(int fd, void *buf, size_t count) -{ - ssize_t ret; - - do { - ret = read(fd, buf, count); - } while (ret < 0 && errno == EINTR); - - return ret; -} - -static ssize_t write_nointr(int fd, const void *buf, size_t count) -{ - ssize_t ret; - - do { - ret = write(fd, buf, count); - } while (ret < 0 && errno == EINTR); - - return ret; -} - FIXTURE_SETUP(current_nsset) { int i, proc_fd, ret; @@ -229,7 +190,7 @@ FIXTURE_SETUP(current_nsset) _exit(EXIT_SUCCESS); } - ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, WEXITED | WNOWAIT), 0); + ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, NULL, WEXITED | WNOWAIT), 0); self->pidfd = sys_pidfd_open(self->pid, 0); EXPECT_GE(self->pidfd, 0) { @@ -432,9 +393,9 @@ FIXTURE_TEARDOWN(current_nsset) EXPECT_EQ(0, close(self->child_pidfd1)); if (self->child_pidfd2 >= 0) EXPECT_EQ(0, close(self->child_pidfd2)); - ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, WEXITED), 0); - ASSERT_EQ(sys_waitid(P_PID, self->child_pid1, WEXITED), 0); - ASSERT_EQ(sys_waitid(P_PID, self->child_pid2, WEXITED), 0); + ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, NULL, WEXITED), 0); + ASSERT_EQ(sys_waitid(P_PID, self->child_pid1, NULL, WEXITED), 0); + ASSERT_EQ(sys_waitid(P_PID, self->child_pid2, NULL, WEXITED), 0); } static int preserve_ns(const int pid, const char *ns) diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 9faa686f90e4..e9728e86b4f2 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -497,7 +497,7 @@ static int child_poll_leader_exit_test(void *args) pthread_create(&t2, NULL, test_pidfd_poll_leader_exit_thread, NULL); /* - * glibc exit calls exit_group syscall, so explicity call exit only + * glibc exit calls exit_group syscall, so explicitly call exit only * so that only the group leader exits, leaving the threads alone. */ *child_exit_secs = time(NULL); diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 0dcb8365ddc3..1e2d49751cde 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -26,22 +26,11 @@ #define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) #endif -static pid_t sys_clone3(struct clone_args *args) -{ - return syscall(__NR_clone3, args, sizeof(struct clone_args)); -} - -static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options, - struct rusage *ru) -{ - return syscall(__NR_waitid, which, pid, info, options, ru); -} - TEST(wait_simple) { int pidfd = -1; pid_t parent_tid = -1; - struct clone_args args = { + struct __clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), .pidfd = ptr_to_u64(&pidfd), .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, @@ -55,7 +44,7 @@ TEST(wait_simple) pidfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC); ASSERT_GE(pidfd, 0); - pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_NE(pid, 0); EXPECT_EQ(close(pidfd), 0); pidfd = -1; @@ -63,18 +52,18 @@ TEST(wait_simple) pidfd = open("/dev/null", O_RDONLY | O_CLOEXEC); ASSERT_GE(pidfd, 0); - pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_NE(pid, 0); EXPECT_EQ(close(pidfd), 0); pidfd = -1; - pid = sys_clone3(&args); + pid = sys_clone3(&args, sizeof(args)); ASSERT_GE(pid, 0); if (pid == 0) exit(EXIT_SUCCESS); - pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_GE(pid, 0); ASSERT_EQ(WIFEXITED(info.si_status), true); ASSERT_EQ(WEXITSTATUS(info.si_status), 0); @@ -89,7 +78,7 @@ TEST(wait_states) { int pidfd = -1; pid_t parent_tid = -1; - struct clone_args args = { + struct __clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), .pidfd = ptr_to_u64(&pidfd), .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, @@ -102,7 +91,7 @@ TEST(wait_states) }; ASSERT_EQ(pipe(pfd), 0); - pid = sys_clone3(&args); + pid = sys_clone3(&args, sizeof(args)); ASSERT_GE(pid, 0); if (pid == 0) { @@ -117,28 +106,28 @@ TEST(wait_states) } close(pfd[0]); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_STOPPED); ASSERT_EQ(info.si_pid, parent_tid); ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED), 0); ASSERT_EQ(write(pfd[1], "C", 1), 1); close(pfd[1]); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_CONTINUED); ASSERT_EQ(info.si_pid, parent_tid); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_STOPPED); ASSERT_EQ(info.si_pid, parent_tid); ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0), 0); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_KILLED); ASSERT_EQ(info.si_pid, parent_tid); @@ -151,7 +140,7 @@ TEST(wait_nonblock) int pidfd; unsigned int flags = 0; pid_t parent_tid = -1; - struct clone_args args = { + struct __clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), .flags = CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, @@ -173,12 +162,12 @@ TEST(wait_nonblock) SKIP(return, "Skipping PIDFD_NONBLOCK test"); } - ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_LT(ret, 0); ASSERT_EQ(errno, ECHILD); EXPECT_EQ(close(pidfd), 0); - pid = sys_clone3(&args); + pid = sys_clone3(&args, sizeof(args)); ASSERT_GE(pid, 0); if (pid == 0) { @@ -201,7 +190,7 @@ TEST(wait_nonblock) * Callers need to see EAGAIN/EWOULDBLOCK with non-blocking pidfd when * child processes exist but none have exited. */ - ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_LT(ret, 0); ASSERT_EQ(errno, EAGAIN); @@ -210,19 +199,19 @@ TEST(wait_nonblock) * WNOHANG raised explicitly when child processes exist but none have * exited. */ - ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED | WNOHANG, NULL); + ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED | WNOHANG); ASSERT_EQ(ret, 0); ASSERT_EQ(fcntl(pidfd, F_SETFL, (flags & ~O_NONBLOCK)), 0); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_STOPPED); ASSERT_EQ(info.si_pid, parent_tid); ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_EXITED); ASSERT_EQ(info.si_pid, parent_tid); diff --git a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c index 580fcac0a09f..b71ef8a493ed 100644 --- a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c +++ b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c @@ -20,7 +20,7 @@ static int test_gettimeofday(void) gettimeofday(&tv_end, NULL); } - timersub(&tv_start, &tv_end, &tv_diff); + timersub(&tv_end, &tv_start, &tv_diff); printf("time = %.6f\n", tv_diff.tv_sec + (tv_diff.tv_usec) * 1e-6); diff --git a/tools/testing/selftests/powerpc/include/pkeys.h b/tools/testing/selftests/powerpc/include/pkeys.h index 51729d9a7111..3a0129467de6 100644 --- a/tools/testing/selftests/powerpc/include/pkeys.h +++ b/tools/testing/selftests/powerpc/include/pkeys.h @@ -35,10 +35,18 @@ #define __NR_pkey_alloc 384 #define __NR_pkey_free 385 +#ifndef NT_PPC_PKEY +#define NT_PPC_PKEY 0x110 +#endif + #define PKEY_BITS_PER_PKEY 2 #define NR_PKEYS 32 #define PKEY_BITS_MASK ((1UL << PKEY_BITS_PER_PKEY) - 1) +#define AMR_BITS_PER_PKEY 2 +#define PKEY_REG_BITS (sizeof(u64) * 8) +#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) + inline unsigned long pkeyreg_get(void) { return mfspr(SPRN_AMR); diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c index f6da4cb30cd6..f061434af452 100644 --- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c @@ -16,26 +16,7 @@ #include <unistd.h> #include "ptrace.h" #include "child.h" - -#ifndef __NR_pkey_alloc -#define __NR_pkey_alloc 384 -#endif - -#ifndef __NR_pkey_free -#define __NR_pkey_free 385 -#endif - -#ifndef NT_PPC_PKEY -#define NT_PPC_PKEY 0x110 -#endif - -#ifndef PKEY_DISABLE_EXECUTE -#define PKEY_DISABLE_EXECUTE 0x4 -#endif - -#define AMR_BITS_PER_PKEY 2 -#define PKEY_REG_BITS (sizeof(u64) * 8) -#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) +#include "pkeys.h" #define CORE_FILE_LIMIT (5 * 1024 * 1024) /* 5 MB should be enough */ @@ -61,16 +42,6 @@ struct shared_info { time_t core_time; }; -static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) -{ - return syscall(__NR_pkey_alloc, flags, init_access_rights); -} - -static int sys_pkey_free(int pkey) -{ - return syscall(__NR_pkey_free, pkey); -} - static int increase_core_file_limit(void) { struct rlimit rlim; diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c index d89474377f11..fc633014424f 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c @@ -7,26 +7,7 @@ */ #include "ptrace.h" #include "child.h" - -#ifndef __NR_pkey_alloc -#define __NR_pkey_alloc 384 -#endif - -#ifndef __NR_pkey_free -#define __NR_pkey_free 385 -#endif - -#ifndef NT_PPC_PKEY -#define NT_PPC_PKEY 0x110 -#endif - -#ifndef PKEY_DISABLE_EXECUTE -#define PKEY_DISABLE_EXECUTE 0x4 -#endif - -#define AMR_BITS_PER_PKEY 2 -#define PKEY_REG_BITS (sizeof(u64) * 8) -#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) +#include "pkeys.h" static const char user_read[] = "[User Read (Running)]"; static const char user_write[] = "[User Write (Running)]"; @@ -61,11 +42,6 @@ struct shared_info { unsigned long invalid_uamor; }; -static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) -{ - return syscall(__NR_pkey_alloc, flags, init_access_rights); -} - static int child(struct shared_info *info) { unsigned long reg; diff --git a/tools/testing/selftests/powerpc/vphn/test-vphn.c b/tools/testing/selftests/powerpc/vphn/test-vphn.c index 81d3069ffb84..f348f54914a9 100644 --- a/tools/testing/selftests/powerpc/vphn/test-vphn.c +++ b/tools/testing/selftests/powerpc/vphn/test-vphn.c @@ -275,7 +275,7 @@ static struct test { } }, { - /* Parse a 32-bit value split accross two consecutives 64-bit + /* Parse a 32-bit value split across two consecutives 64-bit * input values. */ "vphn: 16-bit value followed by 2 x 32-bit values", diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh index 134cdef5a6e0..48a8052d5dae 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh @@ -181,10 +181,11 @@ done # Function to check for presence of a file on the specified system. # Complain if the system cannot be reached, and retry after a wait. -# Currently just waits forever if a machine disappears. +# Currently just waits 15 minutes if a machine disappears. # # Usage: checkremotefile system pathname checkremotefile () { + local nsshfails=0 local ret local sleeptime=60 @@ -195,6 +196,11 @@ checkremotefile () { if test "$ret" -eq 255 then echo " ---" ssh failure to $1 checking for file $2, retry after $sleeptime seconds. `date` | tee -a "$oldrun/remote-log" + nsshfails=$((nsshfails+1)) + if ((nsshfails > 15)) + then + return 255 + fi elif test "$ret" -eq 0 then return 0 @@ -268,12 +274,23 @@ echo All batches started. `date` | tee -a "$oldrun/remote-log" for i in $systems do echo " ---" Waiting for $i `date` | tee -a "$oldrun/remote-log" - while checkremotefile "$i" "$resdir/$ds/remote.run" + while : do + checkremotefile "$i" "$resdir/$ds/remote.run" + ret=$? + if test "$ret" -eq 1 + then + echo " ---" Collecting results from $i `date` | tee -a "$oldrun/remote-log" + ( cd "$oldrun"; ssh -o BatchMode=yes $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - ) + break; + fi + if test "$ret" -eq 255 + then + echo System $i persistent ssh failure, lost results `date` | tee -a "$oldrun/remote-log" + break; + fi sleep 30 done - echo " ---" Collecting results from $i `date` | tee -a "$oldrun/remote-log" - ( cd "$oldrun"; ssh -o BatchMode=yes $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - ) done ( kvm-end-run-stats.sh "$oldrun" "$starttime"; echo $? > $T/exitcode ) | tee -a "$oldrun/remote-log" diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot index 8e50bfd4b710..90318591dae2 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot @@ -5,3 +5,4 @@ rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 threadirqs rcutree.use_softirq=0 +rcutorture.preempt_duration=10 diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile index f408bd6bfc3d..984534cfbf1b 100644 --- a/tools/testing/selftests/resctrl/Makefile +++ b/tools/testing/selftests/resctrl/Makefile @@ -8,5 +8,6 @@ TEST_GEN_PROGS := resctrl_tests LOCAL_HDRS += $(wildcard *.h) include ../lib.mk +CFLAGS += -I$(top_srcdir)/tools/include $(OUTPUT)/resctrl_tests: $(wildcard *.c) diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index 3bbf3042fb06..d09e693dc739 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -169,8 +169,8 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param return ret; ret = check_results(¶m, span, n); - if (ret && (get_vendor() == ARCH_INTEL)) - ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support()) + ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n"); return ret; } diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index 536d9089d2f6..c7e9adc0368f 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -201,6 +201,8 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param return ret; ret = check_results(); + if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support()) + ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n"); return ret; } diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 315b2ef3b3bc..84d8bc250539 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -160,8 +160,8 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param return ret; ret = check_results(param.fill_buf ? param.fill_buf->buf_size : 0); - if (ret && (get_vendor() == ARCH_INTEL)) - ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support()) + ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n"); return ret; } diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index dab1953fc7a0..cd3adfc14969 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -11,6 +11,7 @@ #include <signal.h> #include <dirent.h> #include <stdbool.h> +#include <ctype.h> #include <sys/stat.h> #include <sys/ioctl.h> #include <sys/mount.h> @@ -21,6 +22,7 @@ #include <sys/eventfd.h> #include <asm/unistd.h> #include <linux/perf_event.h> +#include <linux/compiler.h> #include "../kselftest.h" #define MB (1024 * 1024) @@ -156,8 +158,11 @@ struct perf_event_read { */ extern volatile int *value_sink; +extern int snc_unreliable; + extern char llc_occup_path[1024]; +int snc_nodes_per_l3_cache(void); int get_vendor(void); bool check_resctrlfs_support(void); int filter_dmesg(void); @@ -198,6 +203,7 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(const struct resctrl_test *test); void signal_handler_unregister(void); unsigned int count_bits(unsigned long n); +int snc_kernel_support(void); void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config); void perf_event_initialize_read_format(struct perf_event_read *pe_read); diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 3335af815b21..5154ffd821c4 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -118,7 +118,7 @@ static bool test_vendor_specific_check(const struct resctrl_test *test) static void run_single_test(const struct resctrl_test *test, const struct user_params *uparams) { - int ret; + int ret, snc_mode; if (test->disabled) return; @@ -128,8 +128,15 @@ static void run_single_test(const struct resctrl_test *test, const struct user_p return; } + snc_mode = snc_nodes_per_l3_cache(); + ksft_print_msg("Starting %s test ...\n", test->name); + if (snc_mode == 1 && snc_unreliable && get_vendor() == ARCH_INTEL) { + ksft_test_result_skip("SNC detection unreliable due to offline CPUs. Test results may not be accurate if SNC enabled.\n"); + return; + } + if (test_prepare(test)) { ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); return; diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index d38d6dd90be4..195f04c4d158 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -13,6 +13,8 @@ #include "resctrl.h" +int snc_unreliable; + static int find_resctrl_mount(char *buffer) { FILE *mounts; @@ -156,6 +158,98 @@ int get_domain_id(const char *resource, int cpu_no, int *domain_id) return 0; } +/* + * Count number of CPUs in a /sys bitmap + */ +static unsigned int count_sys_bitmap_bits(char *name) +{ + FILE *fp = fopen(name, "r"); + int count = 0, c; + + if (!fp) + return 0; + + while ((c = fgetc(fp)) != EOF) { + if (!isxdigit(c)) + continue; + switch (c) { + case 'f': + count++; + fallthrough; + case '7': case 'b': case 'd': case 'e': + count++; + fallthrough; + case '3': case '5': case '6': case '9': case 'a': case 'c': + count++; + fallthrough; + case '1': case '2': case '4': case '8': + count++; + break; + } + } + fclose(fp); + + return count; +} + +static bool cpus_offline_empty(void) +{ + char offline_cpus_str[64]; + FILE *fp; + + fp = fopen("/sys/devices/system/cpu/offline", "r"); + if (!fp) { + ksft_perror("Could not open /sys/devices/system/cpu/offline"); + return 0; + } + + if (fscanf(fp, "%63s", offline_cpus_str) < 0) { + if (!errno) { + fclose(fp); + return 1; + } + ksft_perror("Could not read /sys/devices/system/cpu/offline"); + } + + fclose(fp); + + return 0; +} + +/* + * Detect SNC by comparing #CPUs in node0 with #CPUs sharing LLC with CPU0. + * If any CPUs are offline declare the detection as unreliable. + */ +int snc_nodes_per_l3_cache(void) +{ + int node_cpus, cache_cpus; + static int snc_mode; + + if (!snc_mode) { + snc_mode = 1; + if (!cpus_offline_empty()) { + ksft_print_msg("Runtime SNC detection unreliable due to offline CPUs.\n"); + ksft_print_msg("Setting SNC mode to disabled.\n"); + snc_unreliable = 1; + return snc_mode; + } + node_cpus = count_sys_bitmap_bits("/sys/devices/system/node/node0/cpumap"); + cache_cpus = count_sys_bitmap_bits("/sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_map"); + + if (!node_cpus || !cache_cpus) { + ksft_print_msg("Could not determine Sub-NUMA Cluster mode.\n"); + snc_unreliable = 1; + return snc_mode; + } + snc_mode = cache_cpus / node_cpus; + + if (snc_mode > 1) + ksft_print_msg("SNC-%d mode discovered.\n", snc_mode); + } + + return snc_mode; +} + /* * get_cache_size - Get cache size for a specified CPU * @cpu_no: CPU number @@ -211,6 +305,17 @@ int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size break; } + /* + * The amount of cache represented by each bit in the masks + * in the schemata file is reduced by a factor equal to SNC + * nodes per L3 cache. + * E.g. on a SNC-2 system with a 100MB L3 cache a test that + * allocates memory from its local SNC node (default behavior + * without using libnuma) will only see 50 MB llc_occupancy + * with a fully populated L3 mask in the schemata file. + */ + if (cache_num == 3) + *cache_size /= snc_nodes_per_l3_cache(); return 0; } @@ -852,3 +957,35 @@ unsigned int count_bits(unsigned long n) return count; } + +/** + * snc_kernel_support - Check for existence of mon_sub_L3_00 file that indicates + * SNC resctrl support on the kernel side. + * + * Return: 0 if not supported, 1 if SNC is disabled or SNC discovery is + * unreliable or SNC is both enabled and supported. + */ +int snc_kernel_support(void) +{ + char node_path[PATH_MAX]; + struct stat statbuf; + int ret; + + ret = snc_nodes_per_l3_cache(); + /* + * If SNC is disabled then its kernel support isn't important. If SNC + * got disabled because the discovery process was unreliable the + * snc_unreliable variable was set. It can be used to verify the SNC + * discovery reliability elsewhere in the selftest. + */ + if (ret == 1) + return ret; + + snprintf(node_path, sizeof(node_path), "%s/%s", RESCTRL_PATH, + "mon_data/mon_L3_00/mon_sub_L3_00"); + + if (!stat(node_path, &statbuf)) + return 1; + + return 0; +} diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c index d10a847130fb..a58f520f2f41 100644 --- a/tools/testing/selftests/ring-buffer/map_test.c +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -233,12 +233,18 @@ TEST_F(map, data_mmap) ASSERT_NE(data, MAP_FAILED); munmap(data, data_len); - /* Overflow the available subbufs by 1 */ + /* Offset within ring-buffer bounds, mapping size overflow */ meta_len += desc->meta->subbuf_size * 2; data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, desc->cpu_fd, meta_len); ASSERT_EQ(data, MAP_FAILED); + /* Offset outside ring-buffer bounds */ + data_len = desc->meta->subbuf_size * desc->meta->nr_subbufs; + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, + desc->cpu_fd, data_len + (desc->meta->subbuf_size * 2)); + ASSERT_EQ(data, MAP_FAILED); + /* Verify meta-page padding */ if (desc->meta->meta_page_size > getpagesize()) { data_len = desc->meta->meta_page_size; diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c index dee41b7ee3e3..059d2e87eb1f 100644 --- a/tools/testing/selftests/riscv/abi/pointer_masking.c +++ b/tools/testing/selftests/riscv/abi/pointer_masking.c @@ -185,8 +185,20 @@ static void test_fork_exec(void) } } +static bool pwrite_wrapper(int fd, void *buf, size_t count, const char *msg) +{ + int ret = pwrite(fd, buf, count, 0); + + if (ret != count) { + ksft_perror(msg); + return false; + } + return true; +} + static void test_tagged_addr_abi_sysctl(void) { + char *err_pwrite_msg = "failed to write to /proc/sys/abi/tagged_addr_disabled\n"; char value; int fd; @@ -200,14 +212,18 @@ static void test_tagged_addr_abi_sysctl(void) } value = '1'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, - "sysctl disabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '1'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, + "sysctl disabled\n"); value = '0'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, - "sysctl enabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '0'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, + "sysctl enabled\n"); set_tagged_addr_ctrl(0, false); diff --git a/tools/testing/selftests/riscv/vector/.gitignore b/tools/testing/selftests/riscv/vector/.gitignore index 9ae7964491d5..7d9c87cd0649 100644 --- a/tools/testing/selftests/riscv/vector/.gitignore +++ b/tools/testing/selftests/riscv/vector/.gitignore @@ -1,3 +1,4 @@ vstate_exec_nolibc vstate_prctl -v_initval_nolibc +v_initval +v_exec_initval_nolibc diff --git a/tools/testing/selftests/riscv/vector/Makefile b/tools/testing/selftests/riscv/vector/Makefile index bfff0ff4f3be..6f7497f4e7b3 100644 --- a/tools/testing/selftests/riscv/vector/Makefile +++ b/tools/testing/selftests/riscv/vector/Makefile @@ -2,18 +2,27 @@ # Copyright (C) 2021 ARM Limited # Originally tools/testing/arm64/abi/Makefile -TEST_GEN_PROGS := vstate_prctl v_initval_nolibc -TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc +TEST_GEN_PROGS := v_initval vstate_prctl +TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc v_exec_initval_nolibc include ../../lib.mk -$(OUTPUT)/vstate_prctl: vstate_prctl.c ../hwprobe/sys_hwprobe.S +$(OUTPUT)/sys_hwprobe.o: ../hwprobe/sys_hwprobe.S + $(CC) -static -c -o$@ $(CFLAGS) $^ + +$(OUTPUT)/v_helpers.o: v_helpers.c + $(CC) -static -c -o$@ $(CFLAGS) $^ + +$(OUTPUT)/vstate_prctl: vstate_prctl.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ $(OUTPUT)/vstate_exec_nolibc: vstate_exec_nolibc.c $(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \ -Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc -$(OUTPUT)/v_initval_nolibc: v_initval_nolibc.c +$(OUTPUT)/v_initval: v_initval.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o + $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ + +$(OUTPUT)/v_exec_initval_nolibc: v_exec_initval_nolibc.c $(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \ -Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc diff --git a/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c new file mode 100644 index 000000000000..35c0812e32de --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Get values of vector registers as soon as the program starts to test if + * is properly cleaning the values before starting a new program. Vector + * registers are caller saved, so no function calls may happen before reading + * the values. To further ensure consistency, this file is compiled without + * libc and without auto-vectorization. + * + * To be "clean" all values must be either all ones or all zeroes. + */ + +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) + +int main(int argc, char **argv) +{ + char prev_value = 0, value; + unsigned long vl; + int first = 1; + + if (argc > 2 && strcmp(argv[2], "x")) + asm volatile ( + // 0 | zimm[10:0] | rs1 | 1 1 1 | rd |1010111| vsetvli + // vsetvli t4, x0, e8, m1, d1 + ".4byte 0b00000000000000000111111011010111\n\t" + "mv %[vl], t4\n\t" + : [vl] "=r" (vl) : : "t4" + ); + else + asm volatile ( + ".option push\n\t" + ".option arch, +v\n\t" + "vsetvli %[vl], x0, e8, m1, ta, ma\n\t" + ".option pop\n\t" + : [vl] "=r" (vl) + ); + +#define CHECK_VECTOR_REGISTER(register) ({ \ + for (int i = 0; i < vl; i++) { \ + asm volatile ( \ + ".option push\n\t" \ + ".option arch, +v\n\t" \ + "vmv.x.s %0, " __stringify(register) "\n\t" \ + "vsrl.vi " __stringify(register) ", " __stringify(register) ", 8\n\t" \ + ".option pop\n\t" \ + : "=r" (value)); \ + if (first) { \ + first = 0; \ + } else if (value != prev_value || !(value == 0x00 || value == 0xff)) { \ + printf("Register " __stringify(register) \ + " values not clean! value: %u\n", value); \ + exit(-1); \ + } \ + prev_value = value; \ + } \ +}) + + CHECK_VECTOR_REGISTER(v0); + CHECK_VECTOR_REGISTER(v1); + CHECK_VECTOR_REGISTER(v2); + CHECK_VECTOR_REGISTER(v3); + CHECK_VECTOR_REGISTER(v4); + CHECK_VECTOR_REGISTER(v5); + CHECK_VECTOR_REGISTER(v6); + CHECK_VECTOR_REGISTER(v7); + CHECK_VECTOR_REGISTER(v8); + CHECK_VECTOR_REGISTER(v9); + CHECK_VECTOR_REGISTER(v10); + CHECK_VECTOR_REGISTER(v11); + CHECK_VECTOR_REGISTER(v12); + CHECK_VECTOR_REGISTER(v13); + CHECK_VECTOR_REGISTER(v14); + CHECK_VECTOR_REGISTER(v15); + CHECK_VECTOR_REGISTER(v16); + CHECK_VECTOR_REGISTER(v17); + CHECK_VECTOR_REGISTER(v18); + CHECK_VECTOR_REGISTER(v19); + CHECK_VECTOR_REGISTER(v20); + CHECK_VECTOR_REGISTER(v21); + CHECK_VECTOR_REGISTER(v22); + CHECK_VECTOR_REGISTER(v23); + CHECK_VECTOR_REGISTER(v24); + CHECK_VECTOR_REGISTER(v25); + CHECK_VECTOR_REGISTER(v26); + CHECK_VECTOR_REGISTER(v27); + CHECK_VECTOR_REGISTER(v28); + CHECK_VECTOR_REGISTER(v29); + CHECK_VECTOR_REGISTER(v30); + CHECK_VECTOR_REGISTER(v31); + +#undef CHECK_VECTOR_REGISTER + + return 0; +} diff --git a/tools/testing/selftests/riscv/vector/v_helpers.c b/tools/testing/selftests/riscv/vector/v_helpers.c new file mode 100644 index 000000000000..01a8799dcb78 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_helpers.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../hwprobe/hwprobe.h" +#include <asm/vendor/thead.h> +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/wait.h> + +bool is_xtheadvector_supported(void) +{ + struct riscv_hwprobe pair; + + pair.key = RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0; + riscv_hwprobe(&pair, 1, 0, NULL, 0); + return pair.value & RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR; +} + +bool is_vector_supported(void) +{ + struct riscv_hwprobe pair; + + pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; + riscv_hwprobe(&pair, 1, 0, NULL, 0); + return pair.value & RISCV_HWPROBE_EXT_ZVE32X; +} + +int launch_test(char *next_program, int test_inherit, int xtheadvector) +{ + char *exec_argv[4], *exec_envp[1]; + int rc, pid, status; + + pid = fork(); + if (pid < 0) { + printf("fork failed %d", pid); + return -1; + } + + if (!pid) { + exec_argv[0] = next_program; + exec_argv[1] = test_inherit != 0 ? "x" : NULL; + exec_argv[2] = xtheadvector != 0 ? "x" : NULL; + exec_argv[3] = NULL; + exec_envp[0] = NULL; + /* launch the program again to check inherit */ + rc = execve(next_program, exec_argv, exec_envp); + if (rc) { + perror("execve"); + printf("child execve failed %d\n", rc); + exit(-1); + } + } + + rc = waitpid(-1, &status, 0); + if (rc < 0) { + printf("waitpid failed\n"); + return -3; + } + + if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) || + WIFSIGNALED(status)) { + printf("child exited abnormally\n"); + return -4; + } + + return WEXITSTATUS(status); +} diff --git a/tools/testing/selftests/riscv/vector/v_helpers.h b/tools/testing/selftests/riscv/vector/v_helpers.h new file mode 100644 index 000000000000..763cddfe26da --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_helpers.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#include <stdbool.h> + +bool is_xtheadvector_supported(void); + +bool is_vector_supported(void); + +int launch_test(char *next_program, int test_inherit, int xtheadvector); diff --git a/tools/testing/selftests/riscv/vector/v_initval.c b/tools/testing/selftests/riscv/vector/v_initval.c new file mode 100644 index 000000000000..be9e1d18ad29 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_initval.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../../kselftest_harness.h" +#include "v_helpers.h" + +#define NEXT_PROGRAM "./v_exec_initval_nolibc" + +TEST(v_initval) +{ + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + + ASSERT_EQ(0, launch_test(NEXT_PROGRAM, 0, xtheadvector)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c deleted file mode 100644 index 1dd94197da30..000000000000 --- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c +++ /dev/null @@ -1,68 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include "../../kselftest.h" -#define MAX_VSIZE (8192 * 32) - -void dump(char *ptr, int size) -{ - int i = 0; - - for (i = 0; i < size; i++) { - if (i != 0) { - if (i % 16 == 0) - printf("\n"); - else if (i % 8 == 0) - printf(" "); - } - printf("%02x ", ptr[i]); - } - printf("\n"); -} - -int main(void) -{ - int i; - unsigned long vl; - char *datap, *tmp; - - datap = malloc(MAX_VSIZE); - if (!datap) { - ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE); - exit(-1); - } - - tmp = datap; - asm volatile ( - ".option push\n\t" - ".option arch, +v\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vse8.v v0, (%2)\n\t" - "add %1, %2, %0\n\t" - "vse8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl), "=r" (tmp) : "r" (datap) : "memory"); - - ksft_print_msg("vl = %lu\n", vl); - - if (datap[0] != 0x00 && datap[0] != 0xff) { - ksft_test_result_fail("v-regesters are not properly initialized\n"); - dump(datap, vl * 4); - exit(-1); - } - - for (i = 1; i < vl * 4; i++) { - if (datap[i] != datap[0]) { - ksft_test_result_fail("detect stale values on v-regesters\n"); - dump(datap, vl * 4); - exit(-2); - } - } - - free(datap); - ksft_exit_pass(); - return 0; -} diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c index 1f9969bed235..7b7d6f21acb4 100644 --- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c +++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c @@ -6,13 +6,16 @@ int main(int argc, char **argv) { - int rc, pid, status, test_inherit = 0; + int rc, pid, status, test_inherit = 0, xtheadvector = 0; long ctrl, ctrl_c; char *exec_argv[2], *exec_envp[2]; - if (argc > 1) + if (argc > 1 && strcmp(argv[1], "x")) test_inherit = 1; + if (argc > 2 && strcmp(argv[2], "x")) + xtheadvector = 1; + ctrl = my_syscall1(__NR_prctl, PR_RISCV_V_GET_CONTROL); if (ctrl < 0) { puts("PR_RISCV_V_GET_CONTROL is not supported\n"); @@ -53,11 +56,14 @@ int main(int argc, char **argv) puts("child's vstate_ctrl not equal to parent's\n"); exit(-1); } - asm volatile (".option push\n\t" - ".option arch, +v\n\t" - "vsetvli x0, x0, e32, m8, ta, ma\n\t" - ".option pop\n\t" - ); + if (xtheadvector) + asm volatile (".4byte 0x00007ed7"); + else + asm volatile (".option push\n\t" + ".option arch, +v\n\t" + "vsetvli x0, x0, e32, m8, ta, ma\n\t" + ".option pop\n\t" + ); exit(ctrl); } } diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c index 895177f6bf4c..62fbb17a0556 100644 --- a/tools/testing/selftests/riscv/vector/vstate_prctl.c +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -3,179 +3,244 @@ #include <unistd.h> #include <errno.h> #include <sys/wait.h> +#include <sys/types.h> +#include <stdlib.h> -#include "../hwprobe/hwprobe.h" -#include "../../kselftest.h" +#include "../../kselftest_harness.h" +#include "v_helpers.h" #define NEXT_PROGRAM "./vstate_exec_nolibc" -static int launch_test(int test_inherit) -{ - char *exec_argv[3], *exec_envp[1]; - int rc, pid, status; - pid = fork(); - if (pid < 0) { - ksft_test_result_fail("fork failed %d", pid); - return -1; - } - - if (!pid) { - exec_argv[0] = NEXT_PROGRAM; - exec_argv[1] = test_inherit != 0 ? "x" : NULL; - exec_argv[2] = NULL; - exec_envp[0] = NULL; - /* launch the program again to check inherit */ - rc = execve(NEXT_PROGRAM, exec_argv, exec_envp); - if (rc) { - perror("execve"); - ksft_test_result_fail("child execve failed %d\n", rc); - exit(-1); - } - } - - rc = waitpid(-1, &status, 0); - if (rc < 0) { - ksft_test_result_fail("waitpid failed\n"); - return -3; - } - - if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) || - WIFSIGNALED(status)) { - ksft_test_result_fail("child exited abnormally\n"); - return -4; - } - - return WEXITSTATUS(status); -} - -int test_and_compare_child(long provided, long expected, int inherit) +int test_and_compare_child(long provided, long expected, int inherit, int xtheadvector) { int rc; rc = prctl(PR_RISCV_V_SET_CONTROL, provided); if (rc != 0) { - ksft_test_result_fail("prctl with provided arg %lx failed with code %d\n", - provided, rc); + printf("prctl with provided arg %lx failed with code %d\n", + provided, rc); return -1; } - rc = launch_test(inherit); + rc = launch_test(NEXT_PROGRAM, inherit, xtheadvector); if (rc != expected) { - ksft_test_result_fail("Test failed, check %d != %ld\n", rc, - expected); + printf("Test failed, check %d != %ld\n", rc, expected); return -2; } return 0; } -#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0 -#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2 +#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0 +#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2 -int main(void) +TEST(get_control_no_v) { - struct riscv_hwprobe pair; - long flag, expected; long rc; - pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; - rc = riscv_hwprobe(&pair, 1, 0, NULL, 0); - if (rc < 0) { - ksft_test_result_fail("hwprobe() failed with %ld\n", rc); - return -1; - } + if (is_vector_supported() || is_xtheadvector_supported()) + SKIP(return, "Test expects vector to be not supported"); - if (pair.key != RISCV_HWPROBE_KEY_IMA_EXT_0) { - ksft_test_result_fail("hwprobe cannot probe RISCV_HWPROBE_KEY_IMA_EXT_0\n"); - return -2; - } + rc = prctl(PR_RISCV_V_GET_CONTROL); + EXPECT_EQ(-1, rc) + TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X"); + EXPECT_EQ(EINVAL, errno) + TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X"); +} - if (!(pair.value & RISCV_HWPROBE_EXT_ZVE32X)) { - rc = prctl(PR_RISCV_V_GET_CONTROL); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("GET_CONTROL should fail on kernel/hw without ZVE32X\n"); - return -3; - } +TEST(set_control_no_v) +{ + long rc; - rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("SET_CONTROL should fail on kernel/hw without ZVE32X\n"); - return -4; - } + if (is_vector_supported() || is_xtheadvector_supported()) + SKIP(return, "Test expects vector to be not supported"); - ksft_test_result_skip("Vector not supported\n"); - return 0; - } + rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON); + EXPECT_EQ(-1, rc) + TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X"); + EXPECT_EQ(EINVAL, errno) + TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X"); +} + +TEST(vstate_on_current) +{ + long flag; + long rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); flag = PR_RISCV_V_VSTATE_CTRL_ON; rc = prctl(PR_RISCV_V_SET_CONTROL, flag); - if (rc != 0) { - ksft_test_result_fail("Enabling V for current should always success\n"); - return -5; - } + EXPECT_EQ(0, rc) TH_LOG("Enabling V for current should always succeed"); +} + +TEST(vstate_off_eperm) +{ + long flag; + long rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); flag = PR_RISCV_V_VSTATE_CTRL_OFF; rc = prctl(PR_RISCV_V_SET_CONTROL, flag); - if (rc != -1 || errno != EPERM) { - ksft_test_result_fail("Disabling current's V alive must fail with EPERM(%d)\n", - errno); - return -5; + EXPECT_EQ(EPERM, errno) + TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno); + EXPECT_EQ(-1, rc) + TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno); +} + +TEST(vstate_on_no_nesting) +{ + long flag; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); } /* Turn on next's vector explicitly and test */ flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; - if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0)) - return -6; + + EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0, xtheadvector)); +} + +TEST(vstate_off_nesting) +{ + long flag; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn off next's vector explicitly and test */ flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; - if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 0)) - return -7; + + EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 1, xtheadvector)); +} + +TEST(vstate_on_inherit_no_nesting) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + + /* Turn on next's vector explicitly and test no inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_ON; + + EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector)); +} + +TEST(vstate_on_inherit) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn on next's vector explicitly and test inherit */ flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; expected = flag | PR_RISCV_V_VSTATE_CTRL_ON; - if (test_and_compare_child(flag, expected, 0)) - return -8; - if (test_and_compare_child(flag, expected, 1)) - return -9; + EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector)); +} + +TEST(vstate_off_inherit_no_nesting) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + /* Turn off next's vector explicitly and test no inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF; + + EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector)); +} + +TEST(vstate_off_inherit) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn off next's vector explicitly and test inherit */ flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF; - if (test_and_compare_child(flag, expected, 0)) - return -10; - if (test_and_compare_child(flag, expected, 1)) - return -11; + EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector)); +} + +/* arguments should fail with EINVAL */ +TEST(inval_set_control_1) +{ + int rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); - /* arguments should fail with EINVAL */ rc = prctl(PR_RISCV_V_SET_CONTROL, 0xff0); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +/* arguments should fail with EINVAL */ +TEST(inval_set_control_2) +{ + int rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); rc = prctl(PR_RISCV_V_SET_CONTROL, 0x3); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } - - rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } - - rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } - - ksft_test_result_pass("tests for riscv_v_vstate_ctrl pass\n"); - ksft_exit_pass(); - return 0; + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); } + +/* arguments should fail with EINVAL */ +TEST(inval_set_control_3) +{ + int rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); + + rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 2f37961240ca..05d03e679e06 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -226,8 +226,32 @@ unsigned int yield_mod_cnt, nr_abort; "addi " INJECT_ASM_REG "," INJECT_ASM_REG ", -1\n\t" \ "bnez " INJECT_ASM_REG ", 222b\n\t" \ "333:\n\t" +#elif defined(__or1k__) +#define RSEQ_INJECT_INPUT \ + , [loop_cnt_1]"m"(loop_cnt[1]) \ + , [loop_cnt_2]"m"(loop_cnt[2]) \ + , [loop_cnt_3]"m"(loop_cnt[3]) \ + , [loop_cnt_4]"m"(loop_cnt[4]) \ + , [loop_cnt_5]"m"(loop_cnt[5]) \ + , [loop_cnt_6]"m"(loop_cnt[6]) +#define INJECT_ASM_REG "r31" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "l.lwz " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \ + "l.sfeqi " INJECT_ASM_REG ", 0\n\t" \ + "l.bf 333f\n\t" \ + " l.nop\n\t" \ + "222:\n\t" \ + "l.addi " INJECT_ASM_REG "," INJECT_ASM_REG ", -1\n\t" \ + "l.sfeqi " INJECT_ASM_REG ", 0\n\t" \ + "l.bf 222f\n\t" \ + " l.nop\n\t" \ + "333:\n\t" #else #error unsupported target #endif diff --git a/tools/testing/selftests/rseq/rseq-or1k-bits.h b/tools/testing/selftests/rseq/rseq-or1k-bits.h new file mode 100644 index 000000000000..15d0e8200cd1 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-or1k-bits.h @@ -0,0 +1,412 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ + +#include "rseq-bits-template.h" + +#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \ + (defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_storev)(intptr_t *v, intptr_t expect, intptr_t newv, + int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_FINAL_STORE(v, newv, 3) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpnev_storeoffp_load)(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPNE(v, expectnot, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPNE(v, expectnot, "%l[error2]") +#endif + RSEQ_ASM_OP_R_LOAD(v) + RSEQ_ASM_OP_R_STORE(load) + RSEQ_ASM_OP_R_LOAD_OFF(voffp) + RSEQ_ASM_OP_R_FINAL_STORE(v, 3) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [v] "m" (*v), + [expectnot] "r" (expectnot), + [load] "m" (*load), + [voffp] "Ir" (voffp) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_addv)(intptr_t *v, intptr_t count, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") +#endif + RSEQ_ASM_OP_R_LOAD(v) + RSEQ_ASM_OP_R_ADD(count) + RSEQ_ASM_OP_R_FINAL_STORE(v, 3) + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [v] "m" (*v), + [count] "r" (count) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_cmpeqv_storev)(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error3]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) + RSEQ_ASM_OP_CMPEQ(v2, expect2, "%l[cmpfail]") + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") + RSEQ_ASM_OP_CMPEQ(v2, expect2, "%l[error3]") +#endif + RSEQ_ASM_OP_FINAL_STORE(v, newv, 3) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [v] "m" (*v), + [expect] "r" (expect), + [v2] "m" (*v2), + [expect2] "r" (expect2), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2, error3 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +error3: + rseq_bug("2nd expected value comparison failed"); +#endif +} + +#define RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV + +/* + * pval = *(ptr+off) + * *pval += inc; + */ +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, intptr_t inc, + int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") +#endif + RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, 3) + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [ptr] "r" (ptr), + [off] "r" (off), + [inc] "r" (inc) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) && + (defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */ + +#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \ + (defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_trystorev_storev)(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_STORE(v2, newv2) + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_TEMPLATE_MO_RELEASE + RSEQ_ASM_OP_FINAL_STORE_RELEASE(v, newv, 3) +#else + RSEQ_ASM_OP_FINAL_STORE(v, newv, 3) +#endif + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [expect] "r" (expect), + [v] "m" (*v), + [newv] "r" (newv), + [v2] "m" (*v2), + [newv2] "r" (newv2) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_trymemcpy_storev)(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len) + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_TEMPLATE_MO_RELEASE + RSEQ_ASM_OP_FINAL_STORE_RELEASE(v, newv, 3) +#else + RSEQ_ASM_OP_FINAL_STORE(v, newv, 3) +#endif + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [expect] "r" (expect), + [v] "m" (*v), + [newv] "r" (newv), + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1, RSEQ_ASM_TMP_REG_2, + RSEQ_ASM_TMP_REG_3, RSEQ_ASM_TMP_REG_4 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +#endif /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && + (defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */ + +#include "rseq-bits-reset.h" diff --git a/tools/testing/selftests/rseq/rseq-or1k-thread-pointer.h b/tools/testing/selftests/rseq/rseq-or1k-thread-pointer.h new file mode 100644 index 000000000000..cda740f7aff3 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-or1k-thread-pointer.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +#ifndef _RSEQ_OR1K_THREAD_POINTER +#define _RSEQ_OR1K_THREAD_POINTER + +static inline void *rseq_thread_pointer(void) +{ + void *__thread_register; + + __asm__ ("l.or %0, r10, r0" : "=r" (__thread_register)); + return __thread_register; +} + +#endif diff --git a/tools/testing/selftests/rseq/rseq-or1k.h b/tools/testing/selftests/rseq/rseq-or1k.h new file mode 100644 index 000000000000..9e78eebdf79a --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-or1k.h @@ -0,0 +1,181 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ + +/* + * Select the instruction "l.nop 0x35" as the RSEQ_SIG. + */ +#define RSEQ_SIG 0x15000035 + +#define rseq_smp_mb() __asm__ __volatile__ ("l.msync" ::: "memory") +#define rseq_smp_rmb() rseq_smp_mb() +#define rseq_smp_wmb() rseq_smp_mb() +#define RSEQ_ASM_TMP_REG_1 "r31" +#define RSEQ_ASM_TMP_REG_2 "r29" +#define RSEQ_ASM_TMP_REG_3 "r27" +#define RSEQ_ASM_TMP_REG_4 "r25" + +#define rseq_smp_load_acquire(p) \ +__extension__ ({ \ + rseq_unqual_scalar_typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ + rseq_smp_mb(); \ + ____p1; \ +}) + +#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb() + +#define rseq_smp_store_release(p, v) \ +do { \ + rseq_smp_mb(); \ + RSEQ_WRITE_ONCE(*(p), v); \ +} while (0) + +#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip, \ + post_commit_offset, abort_ip) \ + ".pushsection __rseq_cs, \"aw\"\n" \ + ".balign 32\n" \ + __rseq_str(label) ":\n" \ + ".long " __rseq_str(version) ", " __rseq_str(flags) "\n" \ + ".long 0x0, " __rseq_str(start_ip) ", " \ + "0x0, " __rseq_str(post_commit_offset) ", " \ + "0x0, " __rseq_str(abort_ip) "\n" \ + ".popsection\n\t" \ + ".pushsection __rseq_cs_ptr_array, \"aw\"\n" \ + ".long 0x0, " __rseq_str(label) "b\n" \ + ".popsection\n" + +#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip, \ + ((post_commit_ip) - (start_ip)), abort_ip) + +/* + * Exit points of a rseq critical section consist of all instructions outside + * of the critical section where a critical section can either branch to or + * reach through the normal course of its execution. The abort IP and the + * post-commit IP are already part of the __rseq_cs section and should not be + * explicitly defined as additional exit points. Knowing all exit points is + * useful to assist debuggers stepping over the critical section. + */ +#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip) \ + ".pushsection __rseq_exit_point_array, \"aw\"\n" \ + ".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(exit_ip) "\n" \ + ".popsection\n" + +#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ + RSEQ_INJECT_ASM(1) \ + "l.movhi " RSEQ_ASM_TMP_REG_1 ", hi(" __rseq_str(cs_label) ")\n"\ + "l.ori " RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 \ + ", lo(" __rseq_str(cs_label) ")\n"\ + "l.sw %[" __rseq_str(rseq_cs) "], " RSEQ_ASM_TMP_REG_1 "\n" \ + __rseq_str(label) ":\n" + +#define RSEQ_ASM_DEFINE_ABORT(label, abort_label) \ + "l.j 222f\n" \ + " l.nop\n" \ + ".balign 4\n" \ + ".long " __rseq_str(RSEQ_SIG) "\n" \ + __rseq_str(label) ":\n" \ + "l.j %l[" __rseq_str(abort_label) "]\n" \ + " l.nop\n" \ + "222:\n" + +#define RSEQ_ASM_OP_STORE(var, value) \ + "l.sw %[" __rseq_str(var) "], %[" __rseq_str(value) "]\n" + +#define RSEQ_ASM_OP_CMPEQ(var, expect, label) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ + "l.sfne " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "]\n" \ + "l.bf " __rseq_str(label) "\n" \ + " l.nop\n" + +#define RSEQ_ASM_OP_CMPNE(var, expect, label) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ + "l.sfeq " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "]\n" \ + "l.bf " __rseq_str(label) "\n" \ + " l.nop\n" + +#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ + RSEQ_INJECT_ASM(2) \ + RSEQ_ASM_OP_CMPEQ(current_cpu_id, cpu_id, label) + +#define RSEQ_ASM_OP_R_LOAD(var) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" + +#define RSEQ_ASM_OP_R_STORE(var) \ + "l.sw %[" __rseq_str(var) "], " RSEQ_ASM_TMP_REG_1 "\n" + +#define RSEQ_ASM_OP_R_LOAD_OFF(offset) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", " \ + "%[" __rseq_str(offset) "](" RSEQ_ASM_TMP_REG_1 ")\n" + +#define RSEQ_ASM_OP_R_ADD(count) \ + "l.add " RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 \ + ", %[" __rseq_str(count) "]\n" + +#define RSEQ_ASM_OP_FINAL_STORE(var, value, post_commit_label) \ + RSEQ_ASM_OP_STORE(var, value) \ + __rseq_str(post_commit_label) ":\n" + +#define RSEQ_ASM_OP_FINAL_STORE_RELEASE(var, value, post_commit_label) \ + "l.msync\n" \ + RSEQ_ASM_OP_STORE(var, value) \ + __rseq_str(post_commit_label) ":\n" + +#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \ + "l.sw %[" __rseq_str(var) "], " RSEQ_ASM_TMP_REG_1 "\n" \ + __rseq_str(post_commit_label) ":\n" + +#define RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len) \ + "l.sfeq %[" __rseq_str(len) "], r0\n" \ + "l.bf 333f\n" \ + " l.nop\n" \ + "l.ori " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(len) "], 0\n" \ + "l.ori " RSEQ_ASM_TMP_REG_2 ", %[" __rseq_str(src) "], 0\n" \ + "l.ori " RSEQ_ASM_TMP_REG_3 ", %[" __rseq_str(dst) "], 0\n" \ + "222:\n" \ + "l.lbz " RSEQ_ASM_TMP_REG_4 ", 0(" RSEQ_ASM_TMP_REG_2 ")\n" \ + "l.sb 0(" RSEQ_ASM_TMP_REG_3 "), " RSEQ_ASM_TMP_REG_4 "\n" \ + "l.addi " RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 ", -1\n" \ + "l.addi " RSEQ_ASM_TMP_REG_2 ", " RSEQ_ASM_TMP_REG_2 ", 1\n" \ + "l.addi " RSEQ_ASM_TMP_REG_3 ", " RSEQ_ASM_TMP_REG_3 ", 1\n" \ + "l.sfne " RSEQ_ASM_TMP_REG_1 ", r0\n" \ + "l.bf 222b\n" \ + " l.nop\n" \ + "333:\n" + +#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, post_commit_label) \ + "l.ori " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(ptr) "], 0\n" \ + RSEQ_ASM_OP_R_ADD(off) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", 0(" RSEQ_ASM_TMP_REG_1 ")\n" \ + RSEQ_ASM_OP_R_ADD(inc) \ + __rseq_str(post_commit_label) ":\n" + +/* Per-cpu-id indexing. */ + +#define RSEQ_TEMPLATE_CPU_ID +#define RSEQ_TEMPLATE_MO_RELAXED +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELAXED + +#define RSEQ_TEMPLATE_MO_RELEASE +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELEASE +#undef RSEQ_TEMPLATE_CPU_ID + +/* Per-mm-cid indexing. */ + +#define RSEQ_TEMPLATE_MM_CID +#define RSEQ_TEMPLATE_MO_RELAXED +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELAXED + +#define RSEQ_TEMPLATE_MO_RELEASE +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELEASE +#undef RSEQ_TEMPLATE_MM_CID + +/* APIs which are not based on cpu ids. */ + +#define RSEQ_TEMPLATE_CPU_ID_NONE +#define RSEQ_TEMPLATE_MO_RELAXED +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELAXED +#undef RSEQ_TEMPLATE_CPU_ID_NONE diff --git a/tools/testing/selftests/rseq/rseq-thread-pointer.h b/tools/testing/selftests/rseq/rseq-thread-pointer.h index 977c25d758b2..3d5019307a1b 100644 --- a/tools/testing/selftests/rseq/rseq-thread-pointer.h +++ b/tools/testing/selftests/rseq/rseq-thread-pointer.h @@ -12,6 +12,8 @@ #include "rseq-x86-thread-pointer.h" #elif defined(__PPC__) #include "rseq-ppc-thread-pointer.h" +#elif defined(__or1k__) +#include "rseq-or1k-thread-pointer.h" #else #include "rseq-generic-thread-pointer.h" #endif diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 5b9772cdf265..f6156790c3b4 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -61,7 +61,6 @@ unsigned int rseq_size = -1U; unsigned int rseq_flags; static int rseq_ownership; -static int rseq_reg_success; /* At least one rseq registration has succeded. */ /* Allocate a large area for the TLS. */ #define RSEQ_THREAD_AREA_ALLOC_SIZE 1024 @@ -152,14 +151,27 @@ int rseq_register_current_thread(void) } rc = sys_rseq(&__rseq_abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG); if (rc) { - if (RSEQ_READ_ONCE(rseq_reg_success)) { + /* + * After at least one thread has registered successfully + * (rseq_size > 0), the registration of other threads should + * never fail. + */ + if (RSEQ_READ_ONCE(rseq_size) > 0) { /* Incoherent success/failure within process. */ abort(); } return -1; } assert(rseq_current_cpu_raw() >= 0); - RSEQ_WRITE_ONCE(rseq_reg_success, 1); + + /* + * The first thread to register sets the rseq_size to mimic the libc + * behavior. + */ + if (RSEQ_READ_ONCE(rseq_size) == 0) { + RSEQ_WRITE_ONCE(rseq_size, get_rseq_kernel_feature_size()); + } + return 0; } @@ -235,12 +247,18 @@ void rseq_init(void) return; } rseq_ownership = 1; - if (!rseq_available()) { - rseq_size = 0; - return; - } + + /* Calculate the offset of the rseq area from the thread pointer. */ rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer(); + + /* rseq flags are deprecated, always set to 0. */ rseq_flags = 0; + + /* + * Set the size to 0 until at least one thread registers to mimic the + * libc behavior. + */ + rseq_size = 0; } static __attribute__((destructor)) diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index 4e217b620e0c..ba424ce80a71 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -60,7 +60,14 @@ extern ptrdiff_t rseq_offset; /* - * Size of the registered rseq area. 0 if the registration was + * The rseq ABI is composed of extensible feature fields. The extensions + * are done by appending additional fields at the end of the structure. + * The rseq_size defines the size of the active feature set which can be + * used by the application for the current rseq registration. Features + * starting at offset >= rseq_size are inactive and should not be used. + * + * The rseq_size is the intersection between the available allocation + * size for the rseq area and the feature size supported by the kernel. * unsuccessful. */ extern unsigned int rseq_size; @@ -122,6 +129,8 @@ static inline struct rseq_abi *rseq_get_abi(void) #include <rseq-s390.h> #elif defined(__riscv) #include <rseq-riscv.h> +#elif defined(__or1k__) +#include <rseq-or1k.h> #else #error unsupported target #endif diff --git a/tools/testing/selftests/run_kselftest.sh b/tools/testing/selftests/run_kselftest.sh index a28c1416cb89..50e03eefe7ac 100755 --- a/tools/testing/selftests/run_kselftest.sh +++ b/tools/testing/selftests/run_kselftest.sh @@ -21,7 +21,7 @@ usage() cat <<EOF Usage: $0 [OPTIONS] -s | --summary Print summary with detailed log in output.log (conflict with -p) - -p | --per_test_log Print test log in /tmp with each test name (conflict with -s) + -p | --per-test-log Print test log in /tmp with each test name (conflict with -s) -t | --test COLLECTION:TEST Run TEST from COLLECTION -c | --collection COLLECTION Run all tests from COLLECTION -l | --list List the available collection:test entries diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c index 37d9bf6fb745..6f4c3f5a1c5d 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p, * If we dispatch to a bogus DSQ that will fall back to the * builtin global DSQ, we fail gracefully. */ - scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL, + scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c index dffc97d9cdf1..e4a55027778f 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p, if (cpu >= 0) { /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ - scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, - p->scx.dsq_vtime, 0); + scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index 6a7db1502c29..fbda6bf54671 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,9 +43,12 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - target = bpf_get_prandom_u32() % nr_cpus; + if (p->nr_cpus_allowed == nr_cpus) + target = bpf_get_prandom_u32() % nr_cpus; + else + target = scx_bpf_task_cpu(p); - scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); bpf_task_release(p); } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c index 472851b56854..0ff27e57fe43 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -34,9 +34,10 @@ static enum scx_test_status run(void *ctx) /* Just sleeping is fine, plenty of scheduling events happening */ sleep(1); - SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR)); bpf_link__destroy(link); + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG)); + return SCX_TEST_PASS; } @@ -50,7 +51,7 @@ static void cleanup(void *ctx) struct scx_test dsp_local_on = { .name = "dsp_local_on", .description = "Verify we can directly dispatch tasks to a local DSQs " - "from osp.dispatch()", + "from ops.dispatch()", .setup = setup, .run = run, .cleanup = cleanup, diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c index 1efb50d61040..a7cf868d5e31 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, /* Can only call from ops.select_cpu() */ scx_bpf_select_cpu_dfl(p, 0, 0, &found); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index d75d4faf07f6..4bc36182d3ff 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -33,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags) if (exit_point == EXIT_ENQUEUE) EXIT_CLEANLY(); - scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) @@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) if (exit_point == EXIT_DISPATCH) EXIT_CLEANLY(); - scx_bpf_consume(DSQ_ID); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 4d4cd8d966db..430f5e13bf55 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -12,6 +12,8 @@ char _license[] SEC("license") = "GPL"; +#define DSQ_ID 0 + s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { @@ -20,7 +22,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags) { - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) @@ -28,7 +30,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev) { - scx_bpf_consume(SCX_DSQ_GLOBAL); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags) @@ -123,7 +125,7 @@ void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight) s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init) { - return 0; + return scx_bpf_create_dsq(DSQ_ID, -1); } void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info) diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c index eab48c7ff309..aa2d7d32dda9 100644 --- a/tools/testing/selftests/sched_ext/runner.c +++ b/tools/testing/selftests/sched_ext/runner.c @@ -22,11 +22,12 @@ const char help_fmt[] = "\n" " -t TEST Only run tests whose name includes this string\n" " -s Include print output for skipped tests\n" +" -l List all available tests\n" " -q Don't print the test descriptions during run\n" " -h Display this help and exit\n"; static volatile int exit_req; -static bool quiet, print_skipped; +static bool quiet, print_skipped, list; #define MAX_SCX_TESTS 2048 @@ -133,7 +134,7 @@ int main(int argc, char **argv) libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - while ((opt = getopt(argc, argv, "qst:h")) != -1) { + while ((opt = getopt(argc, argv, "qslt:h")) != -1) { switch (opt) { case 'q': quiet = true; @@ -141,6 +142,9 @@ int main(int argc, char **argv) case 's': print_skipped = true; break; + case 'l': + list = true; + break; case 't': filter = optarg; break; @@ -154,6 +158,13 @@ int main(int argc, char **argv) enum scx_test_status status; struct scx_test *test = &__scx_tests[i]; + if (list) { + printf("%s\n", test->name); + if (i == (__scx_num_tests - 1)) + return 0; + continue; + } + if (filter && should_skip_test(test, filter)) { /* * Printing the skipped tests and their preambles can diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c index f171ac470970..13d0f5be788d 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, } scx_bpf_put_idle_cpumask(idle_mask); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c index 9efdbb7da928..815f1d5d61ac 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p, saw_local = true; } - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags); } s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c index 59bfc4f36167..4bb99699e920 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p, cpu = prev_cpu; dispatch: - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c index 3bbd5fcdfb18..2a75de11b2cf 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching to a random DSQ should fail. */ - scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c index 0fda57fe0ecf..99d075695c97 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching twice in a row is disallowed. */ - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c index e6c67bcf5e6e..bfcb96cd4954 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -2,8 +2,8 @@ /* * A scheduler that validates that enqueue flags are properly stored and * applied at dispatch time when a task is directly dispatched from - * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and - * making the test a very basic vtime scheduler. + * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(), + * and making the test a very basic vtime scheduler. * * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. * Copyright (c) 2024 David Vernet <dvernet@meta.com> @@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p, cpu = prev_cpu; scx_bpf_test_and_clear_cpu_idle(cpu); ddsp: - scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); + scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); return cpu; } void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p) { - if (scx_bpf_consume(VTIME_DSQ)) + if (scx_bpf_dsq_move_to_local(VTIME_DSQ)) consumed = true; } diff --git a/tools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py b/tools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py new file mode 100755 index 000000000000..0f44a6199495 --- /dev/null +++ b/tools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py @@ -0,0 +1,21 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Script that checks that SFQ rejects a limit of 1 at the kernel +# level. We can't use iproute2's tc because it does not accept a limit +# of 1. + +import sys +import os + +from pyroute2 import IPRoute +from pyroute2.netlink.exceptions import NetlinkError + +ip = IPRoute() +ifidx = ip.link_lookup(ifname=sys.argv[1]) + +try: + ip.tc('add', 'sfq', ifidx, limit=1) + sys.exit(1) +except NetlinkError: + sys.exit(0) diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json index 996448afe31b..91d120548bf5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json @@ -78,10 +78,10 @@ "setup": [ "$TC qdisc add dev $DEV1 ingress" ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0xff", + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0x1f", "expExitCode": "0", "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 1 flow", - "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 255 baseclass", + "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 31 baseclass", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DEV1 ingress" diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json index 16d51936b385..50e8d72781cb 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json @@ -208,5 +208,25 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "4d6f", + "name": "Check that limit of 1 is rejected", + "category": [ + "qdisc", + "sfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "./scripts/sfq_rejects_limit_1.py $DUMMY", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "sfq", + "matchCount": "0", + "teardown": [ + ] } ] diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c index c5264594064c..83faa4e354e3 100644 --- a/tools/testing/selftests/timers/clocksource-switch.c +++ b/tools/testing/selftests/timers/clocksource-switch.c @@ -156,8 +156,8 @@ int main(int argc, char **argv) /* Check everything is sane before we start switching asynchronously */ if (do_sanity_check) { for (i = 0; i < count; i++) { - printf("Validating clocksource %s\n", - clocksource_list[i]); + ksft_print_msg("Validating clocksource %s\n", + clocksource_list[i]); if (change_clocksource(clocksource_list[i])) { status = -1; goto out; @@ -169,7 +169,7 @@ int main(int argc, char **argv) } } - printf("Running Asynchronous Switching Tests...\n"); + ksft_print_msg("Running Asynchronous Switching Tests...\n"); pid = fork(); if (!pid) return run_tests(runtime); diff --git a/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c index b5c3ddb90942..02ecfe687dc2 100644 --- a/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c +++ b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c @@ -23,45 +23,56 @@ #include <sys/mount.h> #include <unistd.h> +#include "../kselftest.h" + int main(void) { int fd; - if (unshare(CLONE_NEWNS) == -1) { - if (errno == ENOSYS || errno == EPERM) { - fprintf(stderr, "error: unshare, errno %d\n", errno); - return 4; - } - fprintf(stderr, "error: unshare, errno %d\n", errno); + // Setting up kselftest framework + ksft_print_header(); + ksft_set_plan(1); + + // Check if test is run as root + if (geteuid()) { + ksft_exit_skip("This test needs root to run!\n"); return 1; } + + if (unshare(CLONE_NEWNS) == -1) { + if (errno == ENOSYS || errno == EPERM) { + ksft_exit_skip("unshare() error: unshare, errno %d\n", errno); + } else { + ksft_exit_fail_msg("unshare() error: unshare, errno %d\n", errno); + } + } + if (mount(NULL, "/", NULL, MS_PRIVATE|MS_REC, NULL) == -1) { - fprintf(stderr, "error: mount '/', errno %d\n", errno); - return 1; + ksft_exit_fail_msg("mount() error: Root filesystem private mount: Fail %d\n", errno); } /* Our heroes: 1 root inode, 1 O_TMPFILE inode, 1 permanent inode. */ if (mount(NULL, "/tmp", "tmpfs", 0, "nr_inodes=3") == -1) { - fprintf(stderr, "error: mount tmpfs, errno %d\n", errno); - return 1; + ksft_exit_fail_msg("mount() error: Mounting tmpfs on /tmp: Fail %d\n", errno); } fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_TMPFILE, 0600); if (fd == -1) { - fprintf(stderr, "error: open 1, errno %d\n", errno); - return 1; + ksft_exit_fail_msg("openat() error: Open first temporary file: Fail %d\n", errno); } + if (linkat(fd, "", AT_FDCWD, "/tmp/1", AT_EMPTY_PATH) == -1) { - fprintf(stderr, "error: linkat, errno %d\n", errno); - return 1; + ksft_exit_fail_msg("linkat() error: Linking the temporary file: Fail %d\n", errno); + /* Ensure fd is closed on failure */ + close(fd); } close(fd); fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_TMPFILE, 0600); if (fd == -1) { - fprintf(stderr, "error: open 2, errno %d\n", errno); - return 1; + ksft_exit_fail_msg("openat() error: Opening the second temporary file: Fail %d\n", errno); } - + ksft_test_result_pass(" "); + ksft_exit_pass(); return 0; } diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c index 28f35620c499..2fe5e983cb22 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.c +++ b/tools/testing/selftests/vDSO/parse_vdso.c @@ -53,6 +53,7 @@ static struct vdso_info /* Symbol table */ ELF(Sym) *symtab; const char *symstrings; + ELF(Word) *gnu_hash; ELF_HASH_ENTRY *bucket, *chain; ELF_HASH_ENTRY nbucket, nchain; @@ -81,6 +82,16 @@ static unsigned long elf_hash(const char *name) return h; } +static uint32_t gnu_hash(const char *name) +{ + const unsigned char *s = (void *)name; + uint32_t h = 5381; + + for (; *s; s++) + h += h * 32 + *s; + return h; +} + void vdso_init_from_sysinfo_ehdr(uintptr_t base) { size_t i; @@ -123,6 +134,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) */ ELF_HASH_ENTRY *hash = 0; vdso_info.symstrings = 0; + vdso_info.gnu_hash = 0; vdso_info.symtab = 0; vdso_info.versym = 0; vdso_info.verdef = 0; @@ -143,6 +155,11 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) ((uintptr_t)dyn[i].d_un.d_ptr + vdso_info.load_offset); break; + case DT_GNU_HASH: + vdso_info.gnu_hash = + (ELF(Word) *)((uintptr_t)dyn[i].d_un.d_ptr + + vdso_info.load_offset); + break; case DT_VERSYM: vdso_info.versym = (ELF(Versym) *) ((uintptr_t)dyn[i].d_un.d_ptr @@ -155,17 +172,27 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) break; } } - if (!vdso_info.symstrings || !vdso_info.symtab || !hash) + if (!vdso_info.symstrings || !vdso_info.symtab || + (!hash && !vdso_info.gnu_hash)) return; /* Failed */ if (!vdso_info.verdef) vdso_info.versym = 0; /* Parse the hash table header. */ - vdso_info.nbucket = hash[0]; - vdso_info.nchain = hash[1]; - vdso_info.bucket = &hash[2]; - vdso_info.chain = &hash[vdso_info.nbucket + 2]; + if (vdso_info.gnu_hash) { + vdso_info.nbucket = vdso_info.gnu_hash[0]; + /* The bucket array is located after the header (4 uint32) and the bloom + * filter (size_t array of gnu_hash[2] elements). + */ + vdso_info.bucket = vdso_info.gnu_hash + 4 + + sizeof(size_t) / 4 * vdso_info.gnu_hash[2]; + } else { + vdso_info.nbucket = hash[0]; + vdso_info.nchain = hash[1]; + vdso_info.bucket = &hash[2]; + vdso_info.chain = &hash[vdso_info.nbucket + 2]; + } /* That's all we need. */ vdso_info.valid = true; @@ -209,6 +236,26 @@ static bool vdso_match_version(ELF(Versym) ver, && !strcmp(name, vdso_info.symstrings + aux->vda_name); } +static bool check_sym(ELF(Sym) *sym, ELF(Word) i, const char *name, + const char *version, unsigned long ver_hash) +{ + /* Check for a defined global or weak function w/ right name. */ + if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) + return false; + if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && + ELF64_ST_BIND(sym->st_info) != STB_WEAK) + return false; + if (strcmp(name, vdso_info.symstrings + sym->st_name)) + return false; + + /* Check symbol version. */ + if (vdso_info.versym && + !vdso_match_version(vdso_info.versym[i], version, ver_hash)) + return false; + + return true; +} + void *vdso_sym(const char *version, const char *name) { unsigned long ver_hash; @@ -216,29 +263,36 @@ void *vdso_sym(const char *version, const char *name) return 0; ver_hash = elf_hash(version); - ELF(Word) chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket]; + ELF(Word) i; - for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) { - ELF(Sym) *sym = &vdso_info.symtab[chain]; + if (vdso_info.gnu_hash) { + uint32_t h1 = gnu_hash(name), h2, *hashval; - /* Check for a defined global or weak function w/ right name. */ - if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) - continue; - if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && - ELF64_ST_BIND(sym->st_info) != STB_WEAK) - continue; - if (sym->st_shndx == SHN_UNDEF) - continue; - if (strcmp(name, vdso_info.symstrings + sym->st_name)) - continue; - - /* Check symbol version. */ - if (vdso_info.versym - && !vdso_match_version(vdso_info.versym[chain], - version, ver_hash)) - continue; - - return (void *)(vdso_info.load_offset + sym->st_value); + i = vdso_info.bucket[h1 % vdso_info.nbucket]; + if (i == 0) + return 0; + h1 |= 1; + hashval = vdso_info.bucket + vdso_info.nbucket + + (i - vdso_info.gnu_hash[1]); + for (;; i++) { + ELF(Sym) *sym = &vdso_info.symtab[i]; + h2 = *hashval++; + if (h1 == (h2 | 1) && + check_sym(sym, i, name, version, ver_hash)) + return (void *)(vdso_info.load_offset + + sym->st_value); + if (h2 & 1) + break; + } + } else { + i = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket]; + for (; i; i = vdso_info.chain[i]) { + ELF(Sym) *sym = &vdso_info.symtab[i]; + if (sym->st_shndx != SHN_UNDEF && + check_sym(sym, i, name, version, ver_hash)) + return (void *)(vdso_info.load_offset + + sym->st_value); + } } return 0; diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 0ea4f6813930..4d4a76532dc9 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -237,7 +237,7 @@ static uint64_t set_metadata(uint64_t src, unsigned long lam) * both pointers should point to the same address. * * @return: - * 0: value on the pointer with metadate and value on original are same + * 0: value on the pointer with metadata and value on original are same * 1: not same. */ static int handle_lam_test(void *src, unsigned int lam) diff --git a/tools/testing/selftests/zram/.gitignore b/tools/testing/selftests/zram/.gitignore new file mode 100644 index 000000000000..088cd9bad87a --- /dev/null +++ b/tools/testing/selftests/zram/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +err.log diff --git a/tools/testing/shared/linux/maple_tree.h b/tools/testing/shared/linux/maple_tree.h index 06c89bdcc515..f67d47d32857 100644 --- a/tools/testing/shared/linux/maple_tree.h +++ b/tools/testing/shared/linux/maple_tree.h @@ -2,6 +2,6 @@ #define atomic_t int32_t #define atomic_inc(x) uatomic_inc(x) #define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) do {} while (0) +#define atomic_set(x, y) uatomic_set(x, y) #define U8_MAX UCHAR_MAX #include "../../../../include/linux/maple_tree.h" diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h index e01f66f98982..3e1b6adc027b 100644 --- a/tools/testing/vma/linux/atomic.h +++ b/tools/testing/vma/linux/atomic.h @@ -6,7 +6,7 @@ #define atomic_t int32_t #define atomic_inc(x) uatomic_inc(x) #define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) do {} while (0) +#define atomic_set(x, y) uatomic_set(x, y) #define U8_MAX UCHAR_MAX #endif /* _LINUX_ATOMIC_H */ diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c index 8fab5e13c7c3..04ab45e27fb8 100644 --- a/tools/testing/vma/vma.c +++ b/tools/testing/vma/vma.c @@ -18,6 +18,12 @@ static bool fail_prealloc; #define vma_iter_prealloc(vmi, vma) \ (fail_prealloc ? -ENOMEM : mas_preallocate(&(vmi)->mas, (vma), GFP_KERNEL)) +#define CONFIG_DEFAULT_MMAP_MIN_ADDR 65536 + +unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; +unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; +unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; + /* * Directly import the VMA implementation here. Our vma_internal.h wrapper * provides userland-equivalent functionality for everything vma.c uses. @@ -47,6 +53,11 @@ struct task_struct *get_current(void) return &__current; } +unsigned long rlimit(unsigned int limit) +{ + return (unsigned long)-1; +} + /* Helper function to simply allocate a VMA. */ static struct vm_area_struct *alloc_vma(struct mm_struct *mm, unsigned long start, @@ -89,7 +100,7 @@ static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm, * begun. Linking to the tree will have caused this to be incremented, * which means we will get a false positive otherwise. */ - vma->vm_lock_seq = -1; + vma->vm_lock_seq = UINT_MAX; return vma; } @@ -214,7 +225,7 @@ static bool vma_write_started(struct vm_area_struct *vma) int seq = vma->vm_lock_seq; /* We reset after each check. */ - vma->vm_lock_seq = -1; + vma->vm_lock_seq = UINT_MAX; /* The vma_start_write() stub simply increments this value. */ return seq > -1; @@ -1563,6 +1574,57 @@ static bool test_expand_only_mode(void) return true; } +static bool test_mmap_region_basic(void) +{ + struct mm_struct mm = {}; + unsigned long addr; + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, &mm, 0); + + current->mm = &mm; + + /* Map at 0x300000, length 0x3000. */ + addr = __mmap_region(NULL, 0x300000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x300, NULL); + ASSERT_EQ(addr, 0x300000); + + /* Map at 0x250000, length 0x3000. */ + addr = __mmap_region(NULL, 0x250000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x250, NULL); + ASSERT_EQ(addr, 0x250000); + + /* Map at 0x303000, merging to 0x300000 of length 0x6000. */ + addr = __mmap_region(NULL, 0x303000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x303, NULL); + ASSERT_EQ(addr, 0x303000); + + /* Map at 0x24d000, merging to 0x250000 of length 0x6000. */ + addr = __mmap_region(NULL, 0x24d000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x24d, NULL); + ASSERT_EQ(addr, 0x24d000); + + ASSERT_EQ(mm.map_count, 2); + + for_each_vma(vmi, vma) { + if (vma->vm_start == 0x300000) { + ASSERT_EQ(vma->vm_end, 0x306000); + ASSERT_EQ(vma->vm_pgoff, 0x300); + } else if (vma->vm_start == 0x24d000) { + ASSERT_EQ(vma->vm_end, 0x253000); + ASSERT_EQ(vma->vm_pgoff, 0x24d); + } else { + ASSERT_FALSE(true); + } + } + + cleanup_mm(&mm, &vmi); + return true; +} + int main(void) { int num_tests = 0, num_fail = 0; @@ -1596,6 +1658,8 @@ int main(void) TEST(copy_vma); TEST(expand_only_mode); + TEST(mmap_region_basic); + #undef TEST printf("%d tests run, %d passed, %d failed.\n", diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index e76ff579e1fd..1eae23039854 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -27,11 +27,23 @@ #include <linux/rbtree.h> #include <linux/rwsem.h> +extern unsigned long stack_guard_gap; +#ifdef CONFIG_MMU +extern unsigned long mmap_min_addr; +extern unsigned long dac_mmap_min_addr; +#else +#define mmap_min_addr 0UL +#define dac_mmap_min_addr 0UL +#endif + #define VM_WARN_ON(_expr) (WARN_ON(_expr)) #define VM_WARN_ON_ONCE(_expr) (WARN_ON_ONCE(_expr)) +#define VM_WARN_ON_VMG(_expr, _vmg) (WARN_ON(_expr)) #define VM_BUG_ON(_expr) (BUG_ON(_expr)) #define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr)) +#define MMF_HAS_MDWE 28 + #define VM_NONE 0x00000000 #define VM_READ 0x00000001 #define VM_WRITE 0x00000002 @@ -39,6 +51,7 @@ #define VM_SHARED 0x00000008 #define VM_MAYREAD 0x00000010 #define VM_MAYWRITE 0x00000020 +#define VM_MAYEXEC 0x00000040 #define VM_GROWSDOWN 0x00000100 #define VM_PFNMAP 0x00000400 #define VM_LOCKED 0x00002000 @@ -51,6 +64,8 @@ #define VM_STACK VM_GROWSDOWN #define VM_SHADOW_STACK VM_NONE #define VM_SOFTDIRTY 0 +#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ +#define VM_GROWSUP VM_NONE #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) @@ -58,6 +73,20 @@ /* This mask represents all the VMA flag bits used by mlock */ #define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) +#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) + +#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) + +#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC + +#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) + +#define RLIMIT_STACK 3 /* max stack size */ +#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */ + +#define CAP_IPC_LOCK 14 + #ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED _BITUL(63) @@ -122,10 +151,22 @@ enum { TASK_COMM_LEN = 16, }; +/* + * Flags for bug emulation. + * + * These occupy the top three bytes. + */ +enum { + READ_IMPLIES_EXEC = 0x0400000, +}; + struct task_struct { char comm[TASK_COMM_LEN]; pid_t pid; struct mm_struct *mm; + + /* Used for emulating ABI behavior of previous Linux versions: */ + unsigned int personality; }; struct task_struct *get_current(void); @@ -186,6 +227,10 @@ struct mm_struct { unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ unsigned long stack_vm; /* VM_STACK */ + + unsigned long def_flags; + + unsigned long flags; /* Must use atomic bitops to access */ }; struct vma_lock { @@ -241,7 +286,7 @@ struct vm_area_struct { * counter reuse can only lead to occasional unnecessary use of the * slowpath. */ - int vm_lock_seq; + unsigned int vm_lock_seq; struct vma_lock *vm_lock; #endif @@ -373,6 +418,17 @@ struct vm_operations_struct { unsigned long addr); }; +struct vm_unmapped_area_info { +#define VM_UNMAPPED_AREA_TOPDOWN 1 + unsigned long flags; + unsigned long length; + unsigned long low_limit; + unsigned long high_limit; + unsigned long align_mask; + unsigned long align_offset; + unsigned long start_gap; +}; + static inline void vma_iter_invalidate(struct vma_iterator *vmi) { mas_pause(&vmi->mas); @@ -416,7 +472,7 @@ static inline bool vma_lock_alloc(struct vm_area_struct *vma) return false; init_rwsem(&vma->vm_lock->lock); - vma->vm_lock_seq = -1; + vma->vm_lock_seq = UINT_MAX; return true; } @@ -432,6 +488,8 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) extern const struct vm_operations_struct vma_dummy_vm_ops; +extern unsigned long rlimit(unsigned int limit); + static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); @@ -853,6 +911,11 @@ static inline void mmap_write_unlock(struct mm_struct *) { } +static inline int mmap_write_lock_killable(struct mm_struct *) +{ + return 0; +} + static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end) @@ -938,7 +1001,7 @@ static inline bool is_file_hugepages(struct file *) static inline int security_vm_enough_memory_mm(struct mm_struct *, long) { - return true; + return 0; } static inline bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long) @@ -1033,4 +1096,159 @@ static inline int mmap_file(struct file *, struct vm_area_struct *) return 0; } +static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_GROWSDOWN) + return stack_guard_gap; + + /* See reasoning around the VM_SHADOW_STACK definition */ + if (vma->vm_flags & VM_SHADOW_STACK) + return PAGE_SIZE; + + return 0; +} + +static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +{ + unsigned long gap = stack_guard_start_gap(vma); + unsigned long vm_start = vma->vm_start; + + vm_start -= gap; + if (vm_start > vma->vm_start) + vm_start = 0; + return vm_start; +} + +static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +{ + unsigned long vm_end = vma->vm_end; + + if (vma->vm_flags & VM_GROWSUP) { + vm_end += stack_guard_gap; + if (vm_end < vma->vm_end) + vm_end = -PAGE_SIZE; + } + return vm_end; +} + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} + +static inline bool vma_is_accessible(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_ACCESS_FLAGS; +} + +static inline bool capable(int cap) +{ + return true; +} + +static inline bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, + unsigned long bytes) +{ + unsigned long locked_pages, limit_pages; + + if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK)) + return true; + + locked_pages = bytes >> PAGE_SHIFT; + locked_pages += mm->locked_vm; + + limit_pages = rlimit(RLIMIT_MEMLOCK); + limit_pages >>= PAGE_SHIFT; + + return locked_pages <= limit_pages; +} + +static inline int __anon_vma_prepare(struct vm_area_struct *vma) +{ + struct anon_vma *anon_vma = calloc(1, sizeof(struct anon_vma)); + + if (!anon_vma) + return -ENOMEM; + + anon_vma->root = anon_vma; + vma->anon_vma = anon_vma; + + return 0; +} + +static inline int anon_vma_prepare(struct vm_area_struct *vma) +{ + if (likely(vma->anon_vma)) + return 0; + + return __anon_vma_prepare(vma); +} + +static inline void userfaultfd_unmap_complete(struct mm_struct *mm, + struct list_head *uf) +{ +} + +/* + * Denies creating a writable executable mapping or gaining executable permissions. + * + * This denies the following: + * + * a) mmap(PROT_WRITE | PROT_EXEC) + * + * b) mmap(PROT_WRITE) + * mprotect(PROT_EXEC) + * + * c) mmap(PROT_WRITE) + * mprotect(PROT_READ) + * mprotect(PROT_EXEC) + * + * But allows the following: + * + * d) mmap(PROT_READ | PROT_EXEC) + * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. + */ +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) +{ + /* If MDWE is disabled, we have nothing to deny. */ + if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + return false; + + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) + return true; + + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) + return true; + + return false; +} + +static inline int mapping_map_writable(struct address_space *mapping) +{ + int c = atomic_read(&mapping->i_mmap_writable); + + /* Derived from the raw_atomic_inc_unless_negative() implementation. */ + do { + if (c < 0) + return -EPERM; + } while (!__sync_bool_compare_and_swap(&mapping->i_mmap_writable, c, c+1)); + + return 0; +} + #endif /* __MM_VMA_INTERNAL_H */ diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README index 84ee217ba8ee..680ce666ceb5 100644 --- a/tools/testing/vsock/README +++ b/tools/testing/vsock/README @@ -36,6 +36,21 @@ Invoke test binaries in both directions as follows: --control-port=1234 \ --peer-cid=3 +Some tests are designed to produce kernel memory leaks. Leaks detection, +however, is deferred to Kernel Memory Leak Detector. It is recommended to enable +kmemleak (CONFIG_DEBUG_KMEMLEAK=y) and explicitly trigger a scan after each test +suite run, e.g. + + # echo clear > /sys/kernel/debug/kmemleak + # $TEST_BINARY ... + # echo "wait for any grace periods" && sleep 2 + # echo scan > /sys/kernel/debug/kmemleak + # echo "wait for kmemleak" && sleep 5 + # echo scan > /sys/kernel/debug/kmemleak + # cat /sys/kernel/debug/kmemleak + +For more information see Documentation/dev-tools/kmemleak.rst. + vsock_perf utility ------------------- 'vsock_perf' is a simple tool to measure vsock performance. It works in diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 34e9dac0a105..de25892f865f 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -96,41 +96,57 @@ void vsock_wait_remote_close(int fd) close(epollfd); } -/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */ -int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type) +/* Create socket <type>, bind to <cid, port> and return the file descriptor. */ +int vsock_bind(unsigned int cid, unsigned int port, int type) { - struct sockaddr_vm sa_client = { - .svm_family = AF_VSOCK, - .svm_cid = VMADDR_CID_ANY, - .svm_port = bind_port, - }; - struct sockaddr_vm sa_server = { + struct sockaddr_vm sa = { .svm_family = AF_VSOCK, .svm_cid = cid, .svm_port = port, }; + int fd; - int client_fd, ret; - - client_fd = socket(AF_VSOCK, type, 0); - if (client_fd < 0) { + fd = socket(AF_VSOCK, type, 0); + if (fd < 0) { perror("socket"); exit(EXIT_FAILURE); } - if (bind(client_fd, (struct sockaddr *)&sa_client, sizeof(sa_client))) { + if (bind(fd, (struct sockaddr *)&sa, sizeof(sa))) { perror("bind"); exit(EXIT_FAILURE); } + return fd; +} + +int vsock_connect_fd(int fd, unsigned int cid, unsigned int port) +{ + struct sockaddr_vm sa = { + .svm_family = AF_VSOCK, + .svm_cid = cid, + .svm_port = port, + }; + int ret; + timeout_begin(TIMEOUT); do { - ret = connect(client_fd, (struct sockaddr *)&sa_server, sizeof(sa_server)); + ret = connect(fd, (struct sockaddr *)&sa, sizeof(sa)); timeout_check("connect"); } while (ret < 0 && errno == EINTR); timeout_end(); - if (ret < 0) { + return ret; +} + +/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */ +int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type) +{ + int client_fd; + + client_fd = vsock_bind(VMADDR_CID_ANY, bind_port, type); + + if (vsock_connect_fd(client_fd, cid, port)) { perror("connect"); exit(EXIT_FAILURE); } @@ -141,17 +157,6 @@ int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_po /* Connect to <cid, port> and return the file descriptor. */ int vsock_connect(unsigned int cid, unsigned int port, int type) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = port, - .svm_cid = cid, - }, - }; - int ret; int fd; control_expectln("LISTENING"); @@ -162,20 +167,14 @@ int vsock_connect(unsigned int cid, unsigned int port, int type) exit(EXIT_FAILURE); } - timeout_begin(TIMEOUT); - do { - ret = connect(fd, &addr.sa, sizeof(addr.svm)); - timeout_check("connect"); - } while (ret < 0 && errno == EINTR); - timeout_end(); - - if (ret < 0) { + if (vsock_connect_fd(fd, cid, port)) { int old_errno = errno; close(fd); fd = -1; errno = old_errno; } + return fd; } @@ -192,28 +191,9 @@ int vsock_seqpacket_connect(unsigned int cid, unsigned int port) /* Listen on <cid, port> and return the file descriptor. */ static int vsock_listen(unsigned int cid, unsigned int port, int type) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = port, - .svm_cid = cid, - }, - }; int fd; - fd = socket(AF_VSOCK, type, 0); - if (fd < 0) { - perror("socket"); - exit(EXIT_FAILURE); - } - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } + fd = vsock_bind(cid, port, type); if (listen(fd, 1) < 0) { perror("listen"); @@ -401,7 +381,7 @@ void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret) */ void send_byte(int fd, int expected_ret, int flags) { - const uint8_t byte = 'A'; + static const uint8_t byte = 'A'; send_buf(fd, &byte, sizeof(byte), flags, expected_ret); } @@ -420,7 +400,7 @@ void recv_byte(int fd, int expected_ret, int flags) recv_buf(fd, &byte, sizeof(byte), flags, expected_ret); if (byte != 'A') { - fprintf(stderr, "unexpected byte read %c\n", byte); + fprintf(stderr, "unexpected byte read 0x%02x\n", byte); exit(EXIT_FAILURE); } } @@ -486,8 +466,7 @@ void list_tests(const struct test_case *test_cases) exit(EXIT_FAILURE); } -void skip_test(struct test_case *test_cases, size_t test_cases_len, - const char *test_id_str) +static unsigned long parse_test_id(const char *test_id_str, size_t test_cases_len) { unsigned long test_id; char *endptr = NULL; @@ -505,9 +484,35 @@ void skip_test(struct test_case *test_cases, size_t test_cases_len, exit(EXIT_FAILURE); } + return test_id; +} + +void skip_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str) +{ + unsigned long test_id = parse_test_id(test_id_str, test_cases_len); test_cases[test_id].skip = true; } +void pick_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str) +{ + static bool skip_all = true; + unsigned long test_id; + + if (skip_all) { + unsigned long i; + + for (i = 0; i < test_cases_len; ++i) + test_cases[i].skip = true; + + skip_all = false; + } + + test_id = parse_test_id(test_id_str, test_cases_len); + test_cases[test_id].skip = false; +} + unsigned long hash_djb2(const void *data, size_t len) { unsigned long hash = 5381; diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index ba84d296d8b7..d1f765ce3eee 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -39,10 +39,12 @@ struct test_case { void init_signals(void); unsigned int parse_cid(const char *str); unsigned int parse_port(const char *str); +int vsock_connect_fd(int fd, unsigned int cid, unsigned int port); int vsock_connect(unsigned int cid, unsigned int port, int type); int vsock_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp, int type); int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_bind(unsigned int cid, unsigned int port, int type); int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type); int vsock_seqpacket_connect(unsigned int cid, unsigned int port); @@ -62,6 +64,8 @@ void run_tests(const struct test_case *test_cases, void list_tests(const struct test_case *test_cases); void skip_test(struct test_case *test_cases, size_t test_cases_len, const char *test_id_str); +void pick_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str); unsigned long hash_djb2(const void *data, size_t len); size_t iovec_bytes(const struct iovec *iov, size_t iovnum); unsigned long iovec_hash_djb2(const struct iovec *iov, size_t iovnum); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 48f17641ca50..dfff8b288265 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -22,12 +22,17 @@ #include <signal.h> #include <sys/ioctl.h> #include <linux/sockios.h> +#include <linux/time64.h> #include "vsock_test_zerocopy.h" #include "timeout.h" #include "control.h" #include "util.h" +/* Basic messages for control_writeulong(), control_readulong() */ +#define CONTROL_CONTINUE 1 +#define CONTROL_DONE 0 + static void test_stream_connection_reset(const struct test_opts *opts) { union { @@ -108,24 +113,9 @@ static void test_stream_bind_only_client(const struct test_opts *opts) static void test_stream_bind_only_server(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = opts->peer_port, - .svm_cid = VMADDR_CID_ANY, - }, - }; int fd; - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } + fd = vsock_bind(VMADDR_CID_ANY, opts->peer_port, SOCK_STREAM); /* Notify the client that the server is ready */ control_writeln("BIND"); @@ -559,7 +549,7 @@ static time_t current_nsec(void) exit(EXIT_FAILURE); } - return (ts.tv_sec * 1000000000ULL) + ts.tv_nsec; + return (ts.tv_sec * NSEC_PER_SEC) + ts.tv_nsec; } #define RCVTIMEO_TIMEOUT_SEC 1 @@ -599,7 +589,7 @@ static void test_seqpacket_timeout_client(const struct test_opts *opts) } read_overhead_ns = current_nsec() - read_enter_ns - - 1000000000ULL * RCVTIMEO_TIMEOUT_SEC; + NSEC_PER_SEC * RCVTIMEO_TIMEOUT_SEC; if (read_overhead_ns > READ_OVERHEAD_NSEC) { fprintf(stderr, @@ -1473,6 +1463,331 @@ static void test_stream_cred_upd_on_set_rcvlowat(const struct test_opts *opts) test_stream_credit_update_test(opts, false); } +/* The goal of test leak_acceptq is to stress the race between connect() and + * close(listener). Implementation of client/server loops boils down to: + * + * client server + * ------ ------ + * write(CONTINUE) + * expect(CONTINUE) + * listen() + * write(LISTENING) + * expect(LISTENING) + * connect() close() + */ +#define ACCEPTQ_LEAK_RACE_TIMEOUT 2 /* seconds */ + +static void test_stream_leak_acceptq_client(const struct test_opts *opts) +{ + time_t tout; + int fd; + + tout = current_nsec() + ACCEPTQ_LEAK_RACE_TIMEOUT * NSEC_PER_SEC; + do { + control_writeulong(CONTROL_CONTINUE); + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd >= 0) + close(fd); + } while (current_nsec() < tout); + + control_writeulong(CONTROL_DONE); +} + +/* Test for a memory leak. User is expected to run kmemleak scan, see README. */ +static void test_stream_leak_acceptq_server(const struct test_opts *opts) +{ + int fd; + + while (control_readulong() == CONTROL_CONTINUE) { + fd = vsock_stream_listen(VMADDR_CID_ANY, opts->peer_port); + control_writeln("LISTENING"); + close(fd); + } +} + +/* Test for a memory leak. User is expected to run kmemleak scan, see README. */ +static void test_stream_msgzcopy_leak_errq_client(const struct test_opts *opts) +{ + struct pollfd fds = { 0 }; + int fd; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + enable_so_zerocopy_check(fd); + send_byte(fd, 1, MSG_ZEROCOPY); + + fds.fd = fd; + fds.events = 0; + if (poll(&fds, 1, -1) < 0) { + perror("poll"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_msgzcopy_leak_errq_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + recv_byte(fd, 1, 0); + vsock_wait_remote_close(fd); + close(fd); +} + +/* Test msgzcopy_leak_zcskb is meant to exercise sendmsg() error handling path, + * that might leak an skb. The idea is to fail virtio_transport_init_zcopy_skb() + * by hitting net.core.optmem_max limit in sock_omalloc(), specifically + * + * vsock_connectible_sendmsg + * virtio_transport_stream_enqueue + * virtio_transport_send_pkt_info + * virtio_transport_init_zcopy_skb + * . msg_zerocopy_realloc + * . msg_zerocopy_alloc + * . sock_omalloc + * . sk_omem_alloc + size > sysctl_optmem_max + * return -ENOMEM + * + * We abuse the implementation detail of net/socket.c:____sys_sendmsg(). + * sk_omem_alloc can be precisely bumped by sock_kmalloc(), as it is used to + * fetch user-provided control data. + * + * While this approach works for now, it relies on assumptions regarding the + * implementation and configuration (for example, order of net.core.optmem_max + * can not exceed MAX_PAGE_ORDER), which may not hold in the future. A more + * resilient testing could be implemented by leveraging the Fault injection + * framework (CONFIG_FAULT_INJECTION), e.g. + * + * client# echo N > /sys/kernel/debug/failslab/ignore-gfp-wait + * client# echo 0 > /sys/kernel/debug/failslab/verbose + * + * void client(const struct test_opts *opts) + * { + * char buf[16]; + * int f, s, i; + * + * f = open("/proc/self/fail-nth", O_WRONLY); + * + * for (i = 1; i < 32; i++) { + * control_writeulong(CONTROL_CONTINUE); + * + * s = vsock_stream_connect(opts->peer_cid, opts->peer_port); + * enable_so_zerocopy_check(s); + * + * sprintf(buf, "%d", i); + * write(f, buf, strlen(buf)); + * + * send(s, &(char){ 0 }, 1, MSG_ZEROCOPY); + * + * write(f, "0", 1); + * close(s); + * } + * + * control_writeulong(CONTROL_DONE); + * close(f); + * } + * + * void server(const struct test_opts *opts) + * { + * int fd; + * + * while (control_readulong() == CONTROL_CONTINUE) { + * fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + * vsock_wait_remote_close(fd); + * close(fd); + * } + * } + * + * Refer to Documentation/fault-injection/fault-injection.rst. + */ +#define MAX_PAGE_ORDER 10 /* usually */ +#define PAGE_SIZE 4096 + +/* Test for a memory leak. User is expected to run kmemleak scan, see README. */ +static void test_stream_msgzcopy_leak_zcskb_client(const struct test_opts *opts) +{ + size_t optmem_max, ctl_len, chunk_size; + struct msghdr msg = { 0 }; + struct iovec iov; + char *chunk; + int fd, res; + FILE *f; + + f = fopen("/proc/sys/net/core/optmem_max", "r"); + if (!f) { + perror("fopen(optmem_max)"); + exit(EXIT_FAILURE); + } + + if (fscanf(f, "%zu", &optmem_max) != 1) { + fprintf(stderr, "fscanf(optmem_max) failed\n"); + exit(EXIT_FAILURE); + } + + fclose(f); + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + enable_so_zerocopy_check(fd); + + ctl_len = optmem_max - 1; + if (ctl_len > PAGE_SIZE << MAX_PAGE_ORDER) { + fprintf(stderr, "Try with net.core.optmem_max = 100000\n"); + exit(EXIT_FAILURE); + } + + chunk_size = CMSG_SPACE(ctl_len); + chunk = malloc(chunk_size); + if (!chunk) { + perror("malloc"); + exit(EXIT_FAILURE); + } + memset(chunk, 0, chunk_size); + + iov.iov_base = &(char){ 0 }; + iov.iov_len = 1; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = chunk; + msg.msg_controllen = ctl_len; + + errno = 0; + res = sendmsg(fd, &msg, MSG_ZEROCOPY); + if (res >= 0 || errno != ENOMEM) { + fprintf(stderr, "Expected ENOMEM, got errno=%d res=%d\n", + errno, res); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_msgzcopy_leak_zcskb_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + vsock_wait_remote_close(fd); + close(fd); +} + +#define MAX_PORT_RETRIES 24 /* net/vmw_vsock/af_vsock.c */ + +/* Test attempts to trigger a transport release for an unbound socket. This can + * lead to a reference count mishandling. + */ +static void test_stream_transport_uaf_client(const struct test_opts *opts) +{ + int sockets[MAX_PORT_RETRIES]; + struct sockaddr_vm addr; + int fd, i, alen; + + fd = vsock_bind(VMADDR_CID_ANY, VMADDR_PORT_ANY, SOCK_STREAM); + + alen = sizeof(addr); + if (getsockname(fd, (struct sockaddr *)&addr, &alen)) { + perror("getsockname"); + exit(EXIT_FAILURE); + } + + for (i = 0; i < MAX_PORT_RETRIES; ++i) + sockets[i] = vsock_bind(VMADDR_CID_ANY, ++addr.svm_port, + SOCK_STREAM); + + close(fd); + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + if (!vsock_connect_fd(fd, addr.svm_cid, addr.svm_port)) { + perror("Unexpected connect() #1 success"); + exit(EXIT_FAILURE); + } + + /* Vulnerable system may crash now. */ + if (!vsock_connect_fd(fd, VMADDR_CID_HOST, VMADDR_PORT_ANY)) { + perror("Unexpected connect() #2 success"); + exit(EXIT_FAILURE); + } + + close(fd); + while (i--) + close(sockets[i]); + + control_writeln("DONE"); +} + +static void test_stream_transport_uaf_server(const struct test_opts *opts) +{ + control_expectln("DONE"); +} + +static void test_stream_connect_retry_client(const struct test_opts *opts) +{ + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + if (!vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) { + fprintf(stderr, "Unexpected connect() #1 success\n"); + exit(EXIT_FAILURE); + } + + control_writeln("LISTEN"); + control_expectln("LISTENING"); + + if (vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) { + perror("connect() #2"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_connect_retry_server(const struct test_opts *opts) +{ + int fd; + + control_expectln("LISTEN"); + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + vsock_wait_remote_close(fd); + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -1603,6 +1918,31 @@ static struct test_case test_cases[] = { .run_client = test_seqpacket_unsent_bytes_client, .run_server = test_seqpacket_unsent_bytes_server, }, + { + .name = "SOCK_STREAM leak accept queue", + .run_client = test_stream_leak_acceptq_client, + .run_server = test_stream_leak_acceptq_server, + }, + { + .name = "SOCK_STREAM MSG_ZEROCOPY leak MSG_ERRQUEUE", + .run_client = test_stream_msgzcopy_leak_errq_client, + .run_server = test_stream_msgzcopy_leak_errq_server, + }, + { + .name = "SOCK_STREAM MSG_ZEROCOPY leak completion skb", + .run_client = test_stream_msgzcopy_leak_zcskb_client, + .run_server = test_stream_msgzcopy_leak_zcskb_server, + }, + { + .name = "SOCK_STREAM transport release use-after-free", + .run_client = test_stream_transport_uaf_client, + .run_server = test_stream_transport_uaf_server, + }, + { + .name = "SOCK_STREAM retry failed connect()", + .run_client = test_stream_connect_retry_client, + .run_server = test_stream_connect_retry_server, + }, {}, }; @@ -1643,6 +1983,11 @@ static const struct option longopts[] = { .has_arg = required_argument, .val = 's', }, + { + .name = "pick", + .has_arg = required_argument, + .val = 't', + }, { .name = "help", .has_arg = no_argument, @@ -1680,6 +2025,8 @@ static void usage(void) " --peer-cid <cid> CID of the other side\n" " --peer-port <port> AF_VSOCK port used for the test [default: %d]\n" " --list List of tests that will be executed\n" + " --pick <test_id> Test ID to execute selectively;\n" + " use multiple --pick options to select more tests\n" " --skip <test_id> Test ID to skip;\n" " use multiple --skip options to skip more tests\n", DEFAULT_PEER_PORT @@ -1736,6 +2083,10 @@ int main(int argc, char **argv) skip_test(test_cases, ARRAY_SIZE(test_cases) - 1, optarg); break; + case 't': + pick_test(test_cases, ARRAY_SIZE(test_cases) - 1, + optarg); + break; case '?': default: usage(); diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index a6a7dee16622..8b5101457c70 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -85,4 +85,6 @@ clean: doc_clean fixdep-clean $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)rm -f rtla rtla-static fixdep FEATURE-DUMP rtla-* $(Q)rm -rf feature -.PHONY: FORCE clean +check: $(RTLA) + RTLA=$(RTLA) prove -o -f tests/ +.PHONY: FORCE clean check diff --git a/tools/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c index 245e9344932b..85f398b89597 100644 --- a/tools/tracing/rtla/src/osnoise.c +++ b/tools/tracing/rtla/src/osnoise.c @@ -867,7 +867,7 @@ int osnoise_set_workload(struct osnoise_context *context, bool onoff) retval = osnoise_options_set_option("OSNOISE_WORKLOAD", onoff); if (retval < 0) - return -1; + return -2; context->opt_workload = onoff; @@ -1079,6 +1079,42 @@ out_err: return NULL; } +bool osnoise_trace_is_off(struct osnoise_tool *tool, struct osnoise_tool *record) +{ + /* + * The tool instance is always present, it is the one used to collect + * data. + */ + if (!tracefs_trace_is_on(tool->trace.inst)) + return true; + + /* + * The trace record instance is only enabled when -t is set. IOW, when the system + * is tracing. + */ + return record && !tracefs_trace_is_on(record->trace.inst); +} + +/* + * osnoise_report_missed_events - report number of events dropped by trace + * buffer + */ +void +osnoise_report_missed_events(struct osnoise_tool *tool) +{ + unsigned long long total_events; + + if (tool->trace.missed_events == UINT64_MAX) + printf("unknown number of events missed, results might not be accurate\n"); + else if (tool->trace.missed_events > 0) { + total_events = tool->trace.processed_events + tool->trace.missed_events; + + printf("%lld (%.2f%%) events missed, results might not be accurate\n", + tool->trace.missed_events, + (double) tool->trace.missed_events / total_events * 100.0); + } +} + static void osnoise_usage(int err) { int i; diff --git a/tools/tracing/rtla/src/osnoise.h b/tools/tracing/rtla/src/osnoise.h index 555f4f4903cc..91835a7d8c2b 100644 --- a/tools/tracing/rtla/src/osnoise.h +++ b/tools/tracing/rtla/src/osnoise.h @@ -104,6 +104,8 @@ struct osnoise_tool { void osnoise_destroy_tool(struct osnoise_tool *top); struct osnoise_tool *osnoise_init_tool(char *tool_name); struct osnoise_tool *osnoise_init_trace_tool(char *tracer); +void osnoise_report_missed_events(struct osnoise_tool *tool); +bool osnoise_trace_is_off(struct osnoise_tool *tool, struct osnoise_tool *record); int osnoise_hist_main(int argc, char *argv[]); int osnoise_top_main(int argc, char **argv); diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index 214e2c93fde0..b4930b835b0a 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -440,6 +440,7 @@ osnoise_print_stats(struct osnoise_hist_params *params, struct osnoise_tool *too trace_seq_reset(trace->seq); osnoise_print_summary(params, trace, data); + osnoise_report_missed_events(tool); } /* @@ -970,7 +971,7 @@ int osnoise_hist_main(int argc, char *argv[]) goto out_hist; } - if (trace_is_off(&tool->trace, &record->trace)) + if (osnoise_trace_is_off(tool, record)) break; } @@ -980,7 +981,7 @@ int osnoise_hist_main(int argc, char *argv[]) return_value = 0; - if (trace_is_off(&tool->trace, &record->trace)) { + if (osnoise_trace_is_off(tool, record)) { printf("rtla osnoise hit stop tracing\n"); if (params->trace_output) { printf(" Saving trace to %s\n", params->trace_output); diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index 45647495ce3b..4772677ac762 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -280,6 +280,7 @@ osnoise_print_stats(struct osnoise_top_params *params, struct osnoise_tool *top) trace_seq_do_printf(trace->seq); trace_seq_reset(trace->seq); + osnoise_report_missed_events(top); } /* @@ -801,7 +802,7 @@ int osnoise_top_main(int argc, char **argv) if (!params->quiet) osnoise_print_stats(params, tool); - if (trace_is_off(&tool->trace, &record->trace)) + if (osnoise_trace_is_off(tool, record)) break; } @@ -810,7 +811,7 @@ int osnoise_top_main(int argc, char **argv) return_value = 0; - if (trace_is_off(&tool->trace, &record->trace)) { + if (osnoise_trace_is_off(tool, record)) { printf("osnoise hit stop tracing\n"); if (params->trace_output) { printf(" Saving trace to %s\n", params->trace_output); diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 8b66387e5f35..6d7d0a2d45b4 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -281,6 +281,21 @@ static void timerlat_hist_header(struct osnoise_tool *tool) trace_seq_reset(s); } +/* + * format_summary_value - format a line of summary value (min, max or avg) + * of hist data + */ +static void format_summary_value(struct trace_seq *seq, + int count, + unsigned long long val, + bool avg) +{ + if (count) + trace_seq_printf(seq, "%9llu ", avg ? val / count : val); + else + trace_seq_printf(seq, "%9c ", '-'); +} + /* * timerlat_print_summary - print the summary of the hist data to the output */ @@ -328,29 +343,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_irq); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].min_irq, + false); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_thread); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].min_thread, + false); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_user); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].min_user, + false); } trace_seq_printf(trace->seq, "\n"); @@ -364,29 +373,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_irq / data->hist[cpu].irq_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].sum_irq, + true); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_thread / data->hist[cpu].thread_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].sum_thread, + true); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_user / data->hist[cpu].user_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].sum_user, + true); } trace_seq_printf(trace->seq, "\n"); @@ -400,29 +403,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_irq); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].max_irq, + false); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_thread); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].max_thread, + false); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_user); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].max_user, + false); } trace_seq_printf(trace->seq, "\n"); trace_seq_do_printf(trace->seq); @@ -506,16 +503,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "min: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_irq); + format_summary_value(trace->seq, + sum.irq_count, + sum.min_irq, + false); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_thread); + format_summary_value(trace->seq, + sum.thread_count, + sum.min_thread, + false); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_user); + format_summary_value(trace->seq, + sum.user_count, + sum.min_user, + false); trace_seq_printf(trace->seq, "\n"); @@ -523,16 +526,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "avg: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_irq / sum.irq_count); + format_summary_value(trace->seq, + sum.irq_count, + sum.sum_irq, + true); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_thread / sum.thread_count); + format_summary_value(trace->seq, + sum.thread_count, + sum.sum_thread, + true); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_user / sum.user_count); + format_summary_value(trace->seq, + sum.user_count, + sum.sum_user, + true); trace_seq_printf(trace->seq, "\n"); @@ -540,16 +549,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "max: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_irq); + format_summary_value(trace->seq, + sum.irq_count, + sum.max_irq, + false); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_thread); + format_summary_value(trace->seq, + sum.thread_count, + sum.max_thread, + false); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_user); + format_summary_value(trace->seq, + sum.user_count, + sum.max_user, + false); trace_seq_printf(trace->seq, "\n"); trace_seq_do_printf(trace->seq); @@ -641,6 +656,7 @@ timerlat_print_stats(struct timerlat_hist_params *params, struct osnoise_tool *t timerlat_print_summary(params, trace, data); timerlat_print_stats_all(params, trace, data); + osnoise_report_missed_events(tool); } /* @@ -1085,12 +1101,15 @@ timerlat_hist_apply_config(struct osnoise_tool *tool, struct timerlat_hist_param } } - if (params->user_hist) { - retval = osnoise_set_workload(tool->context, 0); - if (retval) { - err_msg("Failed to set OSNOISE_WORKLOAD option\n"); - goto out_err; - } + /* + * Set workload according to type of thread if the kernel supports it. + * On kernels without support, user threads will have already failed + * on missing timerlat_fd, and kernel threads do not need it. + */ + retval = osnoise_set_workload(tool->context, params->kernel_workload); + if (retval < -1) { + err_msg("Failed to set OSNOISE_WORKLOAD option\n"); + goto out_err; } return 0; @@ -1131,9 +1150,20 @@ out_err: } static int stop_tracing; +static struct trace_instance *hist_inst = NULL; static void stop_hist(int sig) { + if (stop_tracing) { + /* + * Stop requested twice in a row; abort event processing and + * exit immediately + */ + tracefs_iterate_stop(hist_inst->inst); + return; + } stop_tracing = 1; + if (hist_inst) + trace_instance_stop(hist_inst); } /* @@ -1180,6 +1210,12 @@ int timerlat_hist_main(int argc, char *argv[]) } trace = &tool->trace; + /* + * Save trace instance into global variable so that SIGINT can stop + * the timerlat tracer. + * Otherwise, rtla could loop indefinitely when overloaded. + */ + hist_inst = trace; retval = enable_timerlat(trace); if (retval) { @@ -1327,7 +1363,7 @@ int timerlat_hist_main(int argc, char *argv[]) goto out_hist; } - if (trace_is_off(&tool->trace, &record->trace)) + if (osnoise_trace_is_off(tool, record)) break; /* is there still any user-threads ? */ @@ -1348,7 +1384,7 @@ int timerlat_hist_main(int argc, char *argv[]) return_value = 0; - if (trace_is_off(&tool->trace, &record->trace)) { + if (osnoise_trace_is_off(tool, record) && !stop_tracing) { printf("rtla timerlat hit stop tracing\n"); if (!params->no_aa) diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 059b468981e4..05a9403b01d2 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -435,6 +435,7 @@ timerlat_print_stats(struct timerlat_top_params *params, struct osnoise_tool *to trace_seq_do_printf(trace->seq); trace_seq_reset(trace->seq); + osnoise_report_missed_events(top); } /* @@ -851,12 +852,15 @@ timerlat_top_apply_config(struct osnoise_tool *top, struct timerlat_top_params * } } - if (params->user_top) { - retval = osnoise_set_workload(top->context, 0); - if (retval) { - err_msg("Failed to set OSNOISE_WORKLOAD option\n"); - goto out_err; - } + /* + * Set workload according to type of thread if the kernel supports it. + * On kernels without support, user threads will have already failed + * on missing timerlat_fd, and kernel threads do not need it. + */ + retval = osnoise_set_workload(top->context, params->kernel_workload); + if (retval < -1) { + err_msg("Failed to set OSNOISE_WORKLOAD option\n"); + goto out_err; } if (isatty(STDOUT_FILENO) && !params->quiet) @@ -900,9 +904,20 @@ out_err: } static int stop_tracing; +static struct trace_instance *top_inst = NULL; static void stop_top(int sig) { + if (stop_tracing) { + /* + * Stop requested twice in a row; abort event processing and + * exit immediately + */ + tracefs_iterate_stop(top_inst->inst); + return; + } stop_tracing = 1; + if (top_inst) + trace_instance_stop(top_inst); } /* @@ -950,6 +965,13 @@ int timerlat_top_main(int argc, char *argv[]) } trace = &top->trace; + /* + * Save trace instance into global variable so that SIGINT can stop + * the timerlat tracer. + * Otherwise, rtla could loop indefinitely when overloaded. + */ + top_inst = trace; + retval = enable_timerlat(trace); if (retval) { @@ -1093,7 +1115,7 @@ int timerlat_top_main(int argc, char *argv[]) while (!stop_tracing) { sleep(params->sleep_time); - if (params->aa_only && !trace_is_off(&top->trace, &record->trace)) + if (params->aa_only && !osnoise_trace_is_off(top, record)) continue; retval = tracefs_iterate_raw_events(trace->tep, @@ -1110,7 +1132,7 @@ int timerlat_top_main(int argc, char *argv[]) if (!params->quiet) timerlat_print_stats(params, top); - if (trace_is_off(&top->trace, &record->trace)) + if (osnoise_trace_is_off(top, record)) break; /* is there still any user-threads ? */ @@ -1131,7 +1153,7 @@ int timerlat_top_main(int argc, char *argv[]) return_value = 0; - if (trace_is_off(&top->trace, &record->trace)) { + if (osnoise_trace_is_off(top, record) && !stop_tracing) { printf("rtla timerlat hit stop tracing\n"); if (!params->no_aa) diff --git a/tools/tracing/rtla/src/trace.c b/tools/tracing/rtla/src/trace.c index 170a706248ab..728f5029d533 100644 --- a/tools/tracing/rtla/src/trace.c +++ b/tools/tracing/rtla/src/trace.c @@ -118,6 +118,8 @@ collect_registered_events(struct tep_event *event, struct tep_record *record, struct trace_instance *trace = context; struct trace_seq *s = trace->seq; + trace->processed_events++; + if (!event->handler) return 0; @@ -126,6 +128,31 @@ collect_registered_events(struct tep_event *event, struct tep_record *record, return 0; } +/* + * collect_missed_events - record number of missed events + * + * If rtla cannot keep up with events generated by tracer, events are going + * to fall out of the ring buffer. + * Collect how many events were missed so it can be reported to the user. + */ +static int +collect_missed_events(struct tep_event *event, struct tep_record *record, + int cpu, void *context) +{ + struct trace_instance *trace = context; + + if (trace->missed_events == UINT64_MAX) + return 0; + + if (record->missed_events > 0) + trace->missed_events += record->missed_events; + else + /* Events missed but no data on how many */ + trace->missed_events = UINT64_MAX; + + return 0; +} + /* * trace_instance_destroy - destroy and free a rtla trace instance */ @@ -181,6 +208,17 @@ int trace_instance_init(struct trace_instance *trace, char *tool_name) */ tracefs_trace_off(trace->inst); + /* + * Collect the number of events missed due to tracefs buffer + * overflow. + */ + trace->missed_events = 0; + tracefs_follow_missed_events(trace->inst, + collect_missed_events, + trace); + + trace->processed_events = 0; + return 0; out_err: @@ -196,6 +234,14 @@ int trace_instance_start(struct trace_instance *trace) return tracefs_trace_on(trace->inst); } +/* + * trace_instance_stop - stop tracing a given rtla instance + */ +int trace_instance_stop(struct trace_instance *trace) +{ + return tracefs_trace_off(trace->inst); +} + /* * trace_events_free - free a list of trace events */ @@ -522,25 +568,6 @@ void trace_events_destroy(struct trace_instance *instance, trace_events_free(events); } -int trace_is_off(struct trace_instance *tool, struct trace_instance *trace) -{ - /* - * The tool instance is always present, it is the one used to collect - * data. - */ - if (!tracefs_trace_is_on(tool->inst)) - return 1; - - /* - * The trace instance is only enabled when -t is set. IOW, when the system - * is tracing. - */ - if (trace && !tracefs_trace_is_on(trace->inst)) - return 1; - - return 0; -} - /* * trace_set_buffer_size - set the per-cpu tracing buffer size. */ diff --git a/tools/tracing/rtla/src/trace.h b/tools/tracing/rtla/src/trace.h index c7c92dc9a18a..3cd40dd3f06c 100644 --- a/tools/tracing/rtla/src/trace.h +++ b/tools/tracing/rtla/src/trace.h @@ -17,10 +17,13 @@ struct trace_instance { struct tracefs_instance *inst; struct tep_handle *tep; struct trace_seq *seq; + unsigned long long missed_events; + unsigned long long processed_events; }; int trace_instance_init(struct trace_instance *trace, char *tool_name); int trace_instance_start(struct trace_instance *trace); +int trace_instance_stop(struct trace_instance *trace); void trace_instance_destroy(struct trace_instance *trace); struct trace_seq *get_trace_seq(void); @@ -47,5 +50,4 @@ int trace_events_enable(struct trace_instance *instance, int trace_event_add_filter(struct trace_events *event, char *filter); int trace_event_add_trigger(struct trace_events *event, char *trigger); -int trace_is_off(struct trace_instance *tool, struct trace_instance *trace); int trace_set_buffer_size(struct trace_instance *trace, int size); diff --git a/tools/tracing/rtla/tests/engine.sh b/tools/tracing/rtla/tests/engine.sh new file mode 100644 index 000000000000..64d0446dc28e --- /dev/null +++ b/tools/tracing/rtla/tests/engine.sh @@ -0,0 +1,48 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +test_begin() { + # Count tests to allow the test harness to double-check if all were + # included correctly. + ctr=0 + [ -z "$RTLA" ] && RTLA="./rtla" + [ -n "$TEST_COUNT" ] && echo "1..$TEST_COUNT" +} + +check() { + # Simple check: run rtla with given arguments and test exit code. + # If TEST_COUNT is set, run the test. Otherwise, just count. + ctr=$(($ctr + 1)) + if [ -n "$TEST_COUNT" ] + then + # Run rtla; in case of failure, include its output as comment + # in the test results. + result=$(stdbuf -oL $TIMEOUT "$RTLA" $2 2>&1); exitcode=$? + if [ $exitcode -eq 0 ] + then + echo "ok $ctr - $1" + else + echo "not ok $ctr - $1" + # Add rtla output and exit code as comments in case of failure + echo "$result" | col -b | while read line; do echo "# $line"; done + printf "#\n# exit code %s\n" $exitcode + fi + fi +} + +set_timeout() { + TIMEOUT="timeout -v -k 15s $1" +} + +unset_timeout() { + unset TIMEOUT +} + +test_end() { + # If running without TEST_COUNT, tests are not actually run, just + # counted. In that case, re-run the test with the correct count. + [ -z "$TEST_COUNT" ] && TEST_COUNT=$ctr exec bash $0 || true +} + +# Avoid any environmental discrepancies +export LC_ALL=C +unset_timeout diff --git a/tools/tracing/rtla/tests/hwnoise.t b/tools/tracing/rtla/tests/hwnoise.t new file mode 100644 index 000000000000..bbed17580537 --- /dev/null +++ b/tools/tracing/rtla/tests/hwnoise.t @@ -0,0 +1,21 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +source tests/engine.sh +test_begin + +set_timeout 2m + +check "verify help page" \ + "hwnoise --help" +check "detect noise higher than one microsecond" \ + "hwnoise -c 0 -T 1 -d 5s -q" +check "set the automatic trace mode" \ + "hwnoise -a 5 -d 30s" +check "set scheduling param to the osnoise tracer threads" \ + "hwnoise -P F:1 -c 0 -r 900000 -d 1M -q" +check "stop the trace if a single sample is higher than 1 us" \ + "hwnoise -s 1 -T 1 -t -d 30s" +check "enable a trace event trigger" \ + "hwnoise -t -e osnoise:irq_noise trigger=\"hist:key=desc,duration:sort=desc,duration:vals=hitcount\" -d 1m" + +test_end diff --git a/tools/tracing/rtla/tests/osnoise.t b/tools/tracing/rtla/tests/osnoise.t new file mode 100644 index 000000000000..86596e547893 --- /dev/null +++ b/tools/tracing/rtla/tests/osnoise.t @@ -0,0 +1,19 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +source tests/engine.sh +test_begin + +set_timeout 2m + +check "verify help page" \ + "osnoise --help" +check "verify the --priority/-P param" \ + "osnoise top -P F:1 -c 0 -r 900000 -d 1M -q" +check "verify the --stop/-s param" \ + "osnoise top -s 30 -T 1 -t" +check "verify the --trace param" \ + "osnoise hist -s 30 -T 1 -t" +check "verify the --entries/-E param" \ + "osnoise hist -P F:1 -c 0 -r 900000 -d 1M -b 10 -E 25" + +test_end diff --git a/tools/tracing/rtla/tests/timerlat.t b/tools/tracing/rtla/tests/timerlat.t new file mode 100644 index 000000000000..e86f40e5749e --- /dev/null +++ b/tools/tracing/rtla/tests/timerlat.t @@ -0,0 +1,27 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +source tests/engine.sh +test_begin + +set_timeout 2m + +check "verify help page" \ + "timerlat --help" +check "verify -s/--stack" \ + "timerlat top -s 3 -T 10 -t" +check "verify -P/--priority" \ + "timerlat top -P F:1 -c 0 -d 1M -q" +check "test in nanoseconds" \ + "timerlat top -i 2 -c 0 -n -d 30s" +check "set the automatic trace mode" \ + "timerlat top -a 5 --dump-tasks" +check "print the auto-analysis if hits the stop tracing condition" \ + "timerlat top --aa-only 5" +check "disable auto-analysis" \ + "timerlat top -s 3 -T 10 -t --no-aa" +check "verify -c/--cpus" \ + "timerlat hist -c 0 -d 30s" +check "hist test in nanoseconds" \ + "timerlat hist -i 2 -c 0 -n -d 30s" + +test_end diff --git a/tools/verification/dot2/automata.py b/tools/verification/dot2/automata.py index bdeb98baa8b0..d9a3fe2b74bf 100644 --- a/tools/verification/dot2/automata.py +++ b/tools/verification/dot2/automata.py @@ -19,13 +19,14 @@ class Automata: invalid_state_str = "INVALID_STATE" - def __init__(self, file_path): + def __init__(self, file_path, model_name=None): self.__dot_path = file_path - self.name = self.__get_model_name() + self.name = model_name or self.__get_model_name() self.__dot_lines = self.__open_dot() self.states, self.initial_state, self.final_states = self.__get_state_variables() self.events = self.__get_event_variables() self.function = self.__create_matrix() + self.events_start, self.events_start_run = self.__store_init_events() def __get_model_name(self): basename = ntpath.basename(self.__dot_path) @@ -172,3 +173,34 @@ class Automata: cursor += 1 return matrix + + def __store_init_events(self): + events_start = [False] * len(self.events) + events_start_run = [False] * len(self.events) + for i, _ in enumerate(self.events): + curr_event_will_init = 0 + curr_event_from_init = False + curr_event_used = 0 + for j, _ in enumerate(self.states): + if self.function[j][i] != self.invalid_state_str: + curr_event_used += 1 + if self.function[j][i] == self.initial_state: + curr_event_will_init += 1 + if self.function[0][i] != self.invalid_state_str: + curr_event_from_init = True + # this event always leads to init + if curr_event_will_init and curr_event_used == curr_event_will_init: + events_start[i] = True + # this event is only called from init + if curr_event_from_init and curr_event_used == 1: + events_start_run[i] = True + return events_start, events_start_run + + def is_start_event(self, event): + return self.events_start[self.events.index(event)] + + def is_start_run_event(self, event): + # prefer handle_start_event if there + if any(self.events_start): + return False + return self.events_start_run[self.events.index(event)] diff --git a/tools/verification/dot2/dot2c.py b/tools/verification/dot2/dot2c.py index 87d8a1e1470c..fa2816ac7b61 100644 --- a/tools/verification/dot2/dot2c.py +++ b/tools/verification/dot2/dot2c.py @@ -22,8 +22,8 @@ class Dot2c(Automata): struct_automaton_def = "automaton" var_automaton_def = "aut" - def __init__(self, file_path): - super().__init__(file_path) + def __init__(self, file_path, model_name=None): + super().__init__(file_path, model_name) self.line_length = 100 def __buff_to_string(self, buff): diff --git a/tools/verification/dot2/dot2k b/tools/verification/dot2/dot2k index d4d7e52d549e..559ba191a1f6 100644 --- a/tools/verification/dot2/dot2k +++ b/tools/verification/dot2/dot2k @@ -21,25 +21,24 @@ if __name__ == '__main__': parser.add_argument('-t', "--monitor_type", dest="monitor_type", required=True) parser.add_argument('-n', "--model_name", dest="model_name", required=False) parser.add_argument("-D", "--description", dest="description", required=False) + parser.add_argument("-a", "--auto_patch", dest="auto_patch", + action="store_true", required=False, + help="Patch the kernel in place") params = parser.parse_args() print("Opening and parsing the dot file %s" % params.dot_file) try: - monitor=dot2k(params.dot_file, params.monitor_type) + monitor=dot2k(params.dot_file, params.monitor_type, vars(params)) except Exception as e: print('Error: '+ str(e)) print("Sorry : :-(") sys.exit(1) - # easier than using argparse action. - if params.model_name != None: - print(params.model_name) - print("Writing the monitor into the directory %s" % monitor.name) monitor.print_files() print("Almost done, checklist") print(" - Edit the %s/%s.c to add the instrumentation" % (monitor.name, monitor.name)) - print(" - Edit include/trace/events/rv.h to add the tracepoint entry") - print(" - Move it to the kernel's monitor directory") - print(" - Edit kernel/trace/rv/Makefile") - print(" - Edit kernel/trace/rv/Kconfig") + print(monitor.fill_tracepoint_tooltip()) + print(monitor.fill_makefile_tooltip()) + print(monitor.fill_kconfig_tooltip()) + print(monitor.fill_monitor_tooltip()) diff --git a/tools/verification/dot2/dot2k.py b/tools/verification/dot2/dot2k.py index 016550fccf1f..7547eb290b7d 100644 --- a/tools/verification/dot2/dot2k.py +++ b/tools/verification/dot2/dot2k.py @@ -14,50 +14,83 @@ import os class dot2k(Dot2c): monitor_types = { "global" : 1, "per_cpu" : 2, "per_task" : 3 } - monitor_templates_dir = "dot2k/rv_templates/" + monitor_templates_dir = "dot2/dot2k_templates/" + rv_dir = "kernel/trace/rv" monitor_type = "per_cpu" - def __init__(self, file_path, MonitorType): - super().__init__(file_path) + def __init__(self, file_path, MonitorType, extra_params={}): + super().__init__(file_path, extra_params.get("model_name")) self.monitor_type = self.monitor_types.get(MonitorType) - if self.monitor_type == None: - raise Exception("Unknown monitor type: %s" % MonitorType) + if self.monitor_type is None: + raise ValueError("Unknown monitor type: %s" % MonitorType) self.monitor_type = MonitorType self.__fill_rv_templates_dir() - self.main_c = self.__open_file(self.monitor_templates_dir + "main_" + MonitorType + ".c") + self.main_c = self.__read_file(self.monitor_templates_dir + "main.c") + self.trace_h = self.__read_file(self.monitor_templates_dir + "trace.h") + self.kconfig = self.__read_file(self.monitor_templates_dir + "Kconfig") self.enum_suffix = "_%s" % self.name + self.description = extra_params.get("description", self.name) or "auto-generated" + self.auto_patch = extra_params.get("auto_patch") + if self.auto_patch: + self.__fill_rv_kernel_dir() def __fill_rv_templates_dir(self): - if os.path.exists(self.monitor_templates_dir) == True: + if os.path.exists(self.monitor_templates_dir): return if platform.system() != "Linux": - raise Exception("I can only run on Linux.") + raise OSError("I can only run on Linux.") kernel_path = "/lib/modules/%s/build/tools/verification/dot2/dot2k_templates/" % (platform.release()) - if os.path.exists(kernel_path) == True: + if os.path.exists(kernel_path): self.monitor_templates_dir = kernel_path return - if os.path.exists("/usr/share/dot2/dot2k_templates/") == True: + if os.path.exists("/usr/share/dot2/dot2k_templates/"): self.monitor_templates_dir = "/usr/share/dot2/dot2k_templates/" return - raise Exception("Could not find the template directory, do you have the kernel source installed?") + raise FileNotFoundError("Could not find the template directory, do you have the kernel source installed?") + def __fill_rv_kernel_dir(self): - def __open_file(self, path): + # first try if we are running in the kernel tree root + if os.path.exists(self.rv_dir): + return + + # offset if we are running inside the kernel tree from verification/dot2 + kernel_path = os.path.join("../..", self.rv_dir) + + if os.path.exists(kernel_path): + self.rv_dir = kernel_path + return + + if platform.system() != "Linux": + raise OSError("I can only run on Linux.") + + kernel_path = os.path.join("/lib/modules/%s/build" % platform.release(), self.rv_dir) + + # if the current kernel is from a distro this may not be a full kernel tree + # verify that one of the files we are going to modify is available + if os.path.exists(os.path.join(kernel_path, "rv_trace.h")): + self.rv_dir = kernel_path + return + + raise FileNotFoundError("Could not find the rv directory, do you have the kernel source installed?") + + def __read_file(self, path): try: - fd = open(path) + fd = open(path, 'r') except OSError: raise Exception("Cannot open the file: %s" % path) content = fd.read() + fd.close() return content def __buff_to_string(self, buff): @@ -69,16 +102,26 @@ class dot2k(Dot2c): # cut off the last \n return string[:-1] + def fill_monitor_type(self): + return self.monitor_type.upper() + def fill_tracepoint_handlers_skel(self): buff = [] for event in self.events: buff.append("static void handle_%s(void *data, /* XXX: fill header */)" % event) buff.append("{") + handle = "handle_event" + if self.is_start_event(event): + buff.append("\t/* XXX: validate that this event always leads to the initial state */") + handle = "handle_start_event" + elif self.is_start_run_event(event): + buff.append("\t/* XXX: validate that this event is only valid in the initial state */") + handle = "handle_start_run_event" if self.monitor_type == "per_task": buff.append("\tstruct task_struct *p = /* XXX: how do I get p? */;"); - buff.append("\tda_handle_event_%s(p, %s%s);" % (self.name, event, self.enum_suffix)); + buff.append("\tda_%s_%s(p, %s%s);" % (handle, self.name, event, self.enum_suffix)); else: - buff.append("\tda_handle_event_%s(%s%s);" % (self.name, event, self.enum_suffix)); + buff.append("\tda_%s_%s(%s%s);" % (handle, self.name, event, self.enum_suffix)); buff.append("}") buff.append("") return self.__buff_to_string(buff) @@ -97,18 +140,21 @@ class dot2k(Dot2c): def fill_main_c(self): main_c = self.main_c + monitor_type = self.fill_monitor_type() min_type = self.get_minimun_type() - nr_events = self.events.__len__() + nr_events = len(self.events) tracepoint_handlers = self.fill_tracepoint_handlers_skel() tracepoint_attach = self.fill_tracepoint_attach_probe() tracepoint_detach = self.fill_tracepoint_detach_helper() - main_c = main_c.replace("MIN_TYPE", min_type) - main_c = main_c.replace("MODEL_NAME", self.name) - main_c = main_c.replace("NR_EVENTS", str(nr_events)) - main_c = main_c.replace("TRACEPOINT_HANDLERS_SKEL", tracepoint_handlers) - main_c = main_c.replace("TRACEPOINT_ATTACH", tracepoint_attach) - main_c = main_c.replace("TRACEPOINT_DETACH", tracepoint_detach) + main_c = main_c.replace("%%MONITOR_TYPE%%", monitor_type) + main_c = main_c.replace("%%MIN_TYPE%%", min_type) + main_c = main_c.replace("%%MODEL_NAME%%", self.name) + main_c = main_c.replace("%%NR_EVENTS%%", str(nr_events)) + main_c = main_c.replace("%%TRACEPOINT_HANDLERS_SKEL%%", tracepoint_handlers) + main_c = main_c.replace("%%TRACEPOINT_ATTACH%%", tracepoint_attach) + main_c = main_c.replace("%%TRACEPOINT_DETACH%%", tracepoint_detach) + main_c = main_c.replace("%%DESCRIPTION%%", self.description) return main_c @@ -137,31 +183,142 @@ class dot2k(Dot2c): return self.__buff_to_string(buff) + def fill_monitor_class_type(self): + if self.monitor_type == "per_task": + return "DA_MON_EVENTS_ID" + return "DA_MON_EVENTS_IMPLICIT" + + def fill_monitor_class(self): + if self.monitor_type == "per_task": + return "da_monitor_id" + return "da_monitor" + + def fill_tracepoint_args_skel(self, tp_type): + buff = [] + tp_args_event = [ + ("char *", "state"), + ("char *", "event"), + ("char *", "next_state"), + ("bool ", "final_state"), + ] + tp_args_error = [ + ("char *", "state"), + ("char *", "event"), + ] + tp_args_id = ("int ", "id") + tp_args = tp_args_event if tp_type == "event" else tp_args_error + if self.monitor_type == "per_task": + tp_args.insert(0, tp_args_id) + tp_proto_c = ", ".join([a+b for a,b in tp_args]) + tp_args_c = ", ".join([b for a,b in tp_args]) + buff.append(" TP_PROTO(%s)," % tp_proto_c) + buff.append(" TP_ARGS(%s)" % tp_args_c) + return self.__buff_to_string(buff) + + def fill_trace_h(self): + trace_h = self.trace_h + monitor_class = self.fill_monitor_class() + monitor_class_type = self.fill_monitor_class_type() + tracepoint_args_skel_event = self.fill_tracepoint_args_skel("event") + tracepoint_args_skel_error = self.fill_tracepoint_args_skel("error") + trace_h = trace_h.replace("%%MODEL_NAME%%", self.name) + trace_h = trace_h.replace("%%MODEL_NAME_UP%%", self.name.upper()) + trace_h = trace_h.replace("%%MONITOR_CLASS%%", monitor_class) + trace_h = trace_h.replace("%%MONITOR_CLASS_TYPE%%", monitor_class_type) + trace_h = trace_h.replace("%%TRACEPOINT_ARGS_SKEL_EVENT%%", tracepoint_args_skel_event) + trace_h = trace_h.replace("%%TRACEPOINT_ARGS_SKEL_ERROR%%", tracepoint_args_skel_error) + return trace_h + + def fill_kconfig(self): + kconfig = self.kconfig + monitor_class_type = self.fill_monitor_class_type() + kconfig = kconfig.replace("%%MODEL_NAME%%", self.name) + kconfig = kconfig.replace("%%MODEL_NAME_UP%%", self.name.upper()) + kconfig = kconfig.replace("%%MONITOR_CLASS_TYPE%%", monitor_class_type) + kconfig = kconfig.replace("%%DESCRIPTION%%", self.description) + return kconfig + + def __patch_file(self, file, marker, line): + file_to_patch = os.path.join(self.rv_dir, file) + content = self.__read_file(file_to_patch) + content = content.replace(marker, line + "\n" + marker) + self.__write_file(file_to_patch, content) + + def fill_tracepoint_tooltip(self): + monitor_class_type = self.fill_monitor_class_type() + if self.auto_patch: + self.__patch_file("rv_trace.h", + "// Add new monitors based on CONFIG_%s here" % monitor_class_type, + "#include <monitors/%s/%s_trace.h>" % (self.name, self.name)) + return " - Patching %s/rv_trace.h, double check the result" % self.rv_dir + + return """ - Edit %s/rv_trace.h: +Add this line where other tracepoints are included and %s is defined: +#include <monitors/%s/%s_trace.h> +""" % (self.rv_dir, monitor_class_type, self.name, self.name) + + def fill_kconfig_tooltip(self): + if self.auto_patch: + self.__patch_file("Kconfig", + "# Add new monitors here", + "source \"kernel/trace/rv/monitors/%s/Kconfig\"" % (self.name)) + return " - Patching %s/Kconfig, double check the result" % self.rv_dir + + return """ - Edit %s/Kconfig: +Add this line where other monitors are included: +source \"kernel/trace/rv/monitors/%s/Kconfig\" +""" % (self.rv_dir, self.name) + + def fill_makefile_tooltip(self): + name = self.name + name_up = name.upper() + if self.auto_patch: + self.__patch_file("Makefile", + "# Add new monitors here", + "obj-$(CONFIG_RV_MON_%s) += monitors/%s/%s.o" % (name_up, name, name)) + return " - Patching %s/Makefile, double check the result" % self.rv_dir + + return """ - Edit %s/Makefile: +Add this line where other monitors are included: +obj-$(CONFIG_RV_MON_%s) += monitors/%s/%s.o +""" % (self.rv_dir, name_up, name, name) + + def fill_monitor_tooltip(self): + if self.auto_patch: + return " - Monitor created in %s/monitors/%s" % (self.rv_dir, self. name) + return " - Move %s/ to the kernel's monitor directory (%s/monitors)" % (self.name, self.rv_dir) + def __create_directory(self): + path = self.name + if self.auto_patch: + path = os.path.join(self.rv_dir, "monitors", path) try: - os.mkdir(self.name) + os.mkdir(path) except FileExistsError: return except: print("Fail creating the output dir: %s" % self.name) - def __create_file(self, file_name, content): - path = "%s/%s" % (self.name, file_name) + def __write_file(self, file_name, content): try: - file = open(path, 'w') - except FileExistsError: - return + file = open(file_name, 'w') except: - print("Fail creating file: %s" % path) + print("Fail writing to file: %s" % file_name) file.write(content) file.close() + def __create_file(self, file_name, content): + path = "%s/%s" % (self.name, file_name) + if self.auto_patch: + path = os.path.join(self.rv_dir, "monitors", path) + self.__write_file(path, content) + def __get_main_name(self): path = "%s/%s" % (self.name, "main.c") - if os.path.exists(path) == False: - return "main.c" + if not os.path.exists(path): + return "main.c" return "__main.c" def print_files(self): @@ -175,3 +332,10 @@ class dot2k(Dot2c): path = "%s.h" % self.name self.__create_file(path, model_h) + + trace_h = self.fill_trace_h() + path = "%s_trace.h" % self.name + self.__create_file(path, trace_h) + + kconfig = self.fill_kconfig() + self.__create_file("Kconfig", kconfig) diff --git a/tools/verification/dot2/dot2k_templates/Kconfig b/tools/verification/dot2/dot2k_templates/Kconfig new file mode 100644 index 000000000000..90cdc1e9379e --- /dev/null +++ b/tools/verification/dot2/dot2k_templates/Kconfig @@ -0,0 +1,6 @@ +config RV_MON_%%MODEL_NAME_UP%% + depends on RV + select %%MONITOR_CLASS_TYPE%% + bool "%%MODEL_NAME%% monitor" + help + %%DESCRIPTION%% diff --git a/tools/verification/dot2/dot2k_templates/main.c b/tools/verification/dot2/dot2k_templates/main.c new file mode 100644 index 000000000000..9605ca994416 --- /dev/null +++ b/tools/verification/dot2/dot2k_templates/main.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/ftrace.h> +#include <linux/tracepoint.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/rv.h> +#include <rv/instrumentation.h> +#include <rv/da_monitor.h> + +#define MODULE_NAME "%%MODEL_NAME%%" + +/* + * XXX: include required tracepoint headers, e.g., + * #include <trace/events/sched.h> + */ +#include <rv_trace.h> + +/* + * This is the self-generated part of the monitor. Generally, there is no need + * to touch this section. + */ +#include "%%MODEL_NAME%%.h" + +/* + * Declare the deterministic automata monitor. + * + * The rv monitor reference is needed for the monitor declaration. + */ +static struct rv_monitor rv_%%MODEL_NAME%%; +DECLARE_DA_MON_%%MONITOR_TYPE%%(%%MODEL_NAME%%, %%MIN_TYPE%%); + +/* + * This is the instrumentation part of the monitor. + * + * This is the section where manual work is required. Here the kernel events + * are translated into model's event. + * + */ +%%TRACEPOINT_HANDLERS_SKEL%% +static int enable_%%MODEL_NAME%%(void) +{ + int retval; + + retval = da_monitor_init_%%MODEL_NAME%%(); + if (retval) + return retval; + +%%TRACEPOINT_ATTACH%% + + return 0; +} + +static void disable_%%MODEL_NAME%%(void) +{ + rv_%%MODEL_NAME%%.enabled = 0; + +%%TRACEPOINT_DETACH%% + + da_monitor_destroy_%%MODEL_NAME%%(); +} + +/* + * This is the monitor register section. + */ +static struct rv_monitor rv_%%MODEL_NAME%% = { + .name = "%%MODEL_NAME%%", + .description = "%%DESCRIPTION%%", + .enable = enable_%%MODEL_NAME%%, + .disable = disable_%%MODEL_NAME%%, + .reset = da_monitor_reset_all_%%MODEL_NAME%%, + .enabled = 0, +}; + +static int __init register_%%MODEL_NAME%%(void) +{ + rv_register_monitor(&rv_%%MODEL_NAME%%); + return 0; +} + +static void __exit unregister_%%MODEL_NAME%%(void) +{ + rv_unregister_monitor(&rv_%%MODEL_NAME%%); +} + +module_init(register_%%MODEL_NAME%%); +module_exit(unregister_%%MODEL_NAME%%); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("dot2k: auto-generated"); +MODULE_DESCRIPTION("%%MODEL_NAME%%: %%DESCRIPTION%%"); diff --git a/tools/verification/dot2/dot2k_templates/main_global.c b/tools/verification/dot2/dot2k_templates/main_global.c deleted file mode 100644 index a5658bfb9044..000000000000 --- a/tools/verification/dot2/dot2k_templates/main_global.c +++ /dev/null @@ -1,91 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/ftrace.h> -#include <linux/tracepoint.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/rv.h> -#include <rv/instrumentation.h> -#include <rv/da_monitor.h> - -#define MODULE_NAME "MODEL_NAME" - -/* - * XXX: include required tracepoint headers, e.g., - * #include <trace/events/sched.h> - */ -#include <trace/events/rv.h> - -/* - * This is the self-generated part of the monitor. Generally, there is no need - * to touch this section. - */ -#include "MODEL_NAME.h" - -/* - * Declare the deterministic automata monitor. - * - * The rv monitor reference is needed for the monitor declaration. - */ -static struct rv_monitor rv_MODEL_NAME; -DECLARE_DA_MON_GLOBAL(MODEL_NAME, MIN_TYPE); - -/* - * This is the instrumentation part of the monitor. - * - * This is the section where manual work is required. Here the kernel events - * are translated into model's event. - * - */ -TRACEPOINT_HANDLERS_SKEL -static int enable_MODEL_NAME(void) -{ - int retval; - - retval = da_monitor_init_MODEL_NAME(); - if (retval) - return retval; - -TRACEPOINT_ATTACH - - return 0; -} - -static void disable_MODEL_NAME(void) -{ - rv_MODEL_NAME.enabled = 0; - -TRACEPOINT_DETACH - - da_monitor_destroy_MODEL_NAME(); -} - -/* - * This is the monitor register section. - */ -static struct rv_monitor rv_MODEL_NAME = { - .name = "MODEL_NAME", - .description = "auto-generated MODEL_NAME", - .enable = enable_MODEL_NAME, - .disable = disable_MODEL_NAME, - .reset = da_monitor_reset_all_MODEL_NAME, - .enabled = 0, -}; - -static int __init register_MODEL_NAME(void) -{ - rv_register_monitor(&rv_MODEL_NAME); - return 0; -} - -static void __exit unregister_MODEL_NAME(void) -{ - rv_unregister_monitor(&rv_MODEL_NAME); -} - -module_init(register_MODEL_NAME); -module_exit(unregister_MODEL_NAME); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("dot2k: auto-generated"); -MODULE_DESCRIPTION("MODEL_NAME"); diff --git a/tools/verification/dot2/dot2k_templates/main_per_cpu.c b/tools/verification/dot2/dot2k_templates/main_per_cpu.c deleted file mode 100644 index 03539a97633f..000000000000 --- a/tools/verification/dot2/dot2k_templates/main_per_cpu.c +++ /dev/null @@ -1,91 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/ftrace.h> -#include <linux/tracepoint.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/rv.h> -#include <rv/instrumentation.h> -#include <rv/da_monitor.h> - -#define MODULE_NAME "MODEL_NAME" - -/* - * XXX: include required tracepoint headers, e.g., - * #include <linux/trace/events/sched.h> - */ -#include <trace/events/rv.h> - -/* - * This is the self-generated part of the monitor. Generally, there is no need - * to touch this section. - */ -#include "MODEL_NAME.h" - -/* - * Declare the deterministic automata monitor. - * - * The rv monitor reference is needed for the monitor declaration. - */ -static struct rv_monitor rv_MODEL_NAME; -DECLARE_DA_MON_PER_CPU(MODEL_NAME, MIN_TYPE); - -/* - * This is the instrumentation part of the monitor. - * - * This is the section where manual work is required. Here the kernel events - * are translated into model's event. - * - */ -TRACEPOINT_HANDLERS_SKEL -static int enable_MODEL_NAME(void) -{ - int retval; - - retval = da_monitor_init_MODEL_NAME(); - if (retval) - return retval; - -TRACEPOINT_ATTACH - - return 0; -} - -static void disable_MODEL_NAME(void) -{ - rv_MODEL_NAME.enabled = 0; - -TRACEPOINT_DETACH - - da_monitor_destroy_MODEL_NAME(); -} - -/* - * This is the monitor register section. - */ -static struct rv_monitor rv_MODEL_NAME = { - .name = "MODEL_NAME", - .description = "auto-generated MODEL_NAME", - .enable = enable_MODEL_NAME, - .disable = disable_MODEL_NAME, - .reset = da_monitor_reset_all_MODEL_NAME, - .enabled = 0, -}; - -static int __init register_MODEL_NAME(void) -{ - rv_register_monitor(&rv_MODEL_NAME); - return 0; -} - -static void __exit unregister_MODEL_NAME(void) -{ - rv_unregister_monitor(&rv_MODEL_NAME); -} - -module_init(register_MODEL_NAME); -module_exit(unregister_MODEL_NAME); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("dot2k: auto-generated"); -MODULE_DESCRIPTION("MODEL_NAME"); diff --git a/tools/verification/dot2/dot2k_templates/main_per_task.c b/tools/verification/dot2/dot2k_templates/main_per_task.c deleted file mode 100644 index ffd92af87a86..000000000000 --- a/tools/verification/dot2/dot2k_templates/main_per_task.c +++ /dev/null @@ -1,91 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/ftrace.h> -#include <linux/tracepoint.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/rv.h> -#include <rv/instrumentation.h> -#include <rv/da_monitor.h> - -#define MODULE_NAME "MODEL_NAME" - -/* - * XXX: include required tracepoint headers, e.g., - * #include <linux/trace/events/sched.h> - */ -#include <trace/events/rv.h> - -/* - * This is the self-generated part of the monitor. Generally, there is no need - * to touch this section. - */ -#include "MODEL_NAME.h" - -/* - * Declare the deterministic automata monitor. - * - * The rv monitor reference is needed for the monitor declaration. - */ -static struct rv_monitor rv_MODEL_NAME; -DECLARE_DA_MON_PER_TASK(MODEL_NAME, MIN_TYPE); - -/* - * This is the instrumentation part of the monitor. - * - * This is the section where manual work is required. Here the kernel events - * are translated into model's event. - * - */ -TRACEPOINT_HANDLERS_SKEL -static int enable_MODEL_NAME(void) -{ - int retval; - - retval = da_monitor_init_MODEL_NAME(); - if (retval) - return retval; - -TRACEPOINT_ATTACH - - return 0; -} - -static void disable_MODEL_NAME(void) -{ - rv_MODEL_NAME.enabled = 0; - -TRACEPOINT_DETACH - - da_monitor_destroy_MODEL_NAME(); -} - -/* - * This is the monitor register section. - */ -static struct rv_monitor rv_MODEL_NAME = { - .name = "MODEL_NAME", - .description = "auto-generated MODEL_NAME", - .enable = enable_MODEL_NAME, - .disable = disable_MODEL_NAME, - .reset = da_monitor_reset_all_MODEL_NAME, - .enabled = 0, -}; - -static int __init register_MODEL_NAME(void) -{ - rv_register_monitor(&rv_MODEL_NAME); - return 0; -} - -static void __exit unregister_MODEL_NAME(void) -{ - rv_unregister_monitor(&rv_MODEL_NAME); -} - -module_init(register_MODEL_NAME); -module_exit(unregister_MODEL_NAME); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("dot2k: auto-generated"); -MODULE_DESCRIPTION("MODEL_NAME"); diff --git a/tools/verification/dot2/dot2k_templates/trace.h b/tools/verification/dot2/dot2k_templates/trace.h new file mode 100644 index 000000000000..87d3a1308926 --- /dev/null +++ b/tools/verification/dot2/dot2k_templates/trace.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_%%MODEL_NAME_UP%% +DEFINE_EVENT(event_%%MONITOR_CLASS%%, event_%%MODEL_NAME%%, +%%TRACEPOINT_ARGS_SKEL_EVENT%%); + +DEFINE_EVENT(error_%%MONITOR_CLASS%%, error_%%MODEL_NAME%%, +%%TRACEPOINT_ARGS_SKEL_ERROR%%); +#endif /* CONFIG_RV_MON_%%MODEL_NAME_UP%% */ diff --git a/usr/include/Makefile b/usr/include/Makefile index 771e32872b2a..6c6de1b1622b 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -78,7 +78,7 @@ quiet_cmd_hdrtest = HDRTEST $< cmd_hdrtest = \ $(CC) $(c_flags) -fsyntax-only -x c /dev/null \ $(if $(filter-out $(no-header-test), $*.h), -include $< -include $<); \ - $(PERL) $(src)/headers_check.pl $(obj) $(SRCARCH) $<; \ + $(PERL) $(src)/headers_check.pl $(obj) $<; \ touch $@ $(obj)/%.hdrtest: $(obj)/%.h FORCE diff --git a/usr/include/headers_check.pl b/usr/include/headers_check.pl index b6aec5e4365f..2b70bfa5558e 100755 --- a/usr/include/headers_check.pl +++ b/usr/include/headers_check.pl @@ -3,9 +3,8 @@ # # headers_check.pl execute a number of trivial consistency checks # -# Usage: headers_check.pl dir arch [files...] +# Usage: headers_check.pl dir [files...] # dir: dir to look for included files -# arch: architecture # files: list of files to check # # The script reads the supplied files line by line and: @@ -23,7 +22,7 @@ use warnings; use strict; use File::Basename; -my ($dir, $arch, @files) = @ARGV; +my ($dir, @files) = @ARGV; my $ret = 0; my $line; @@ -54,10 +53,6 @@ sub check_include my $inc = $1; my $found; $found = stat($dir . "/" . $inc); - if (!$found) { - $inc =~ s#asm/#asm-$arch/#; - $found = stat($dir . "/" . $inc); - } if (!$found) { printf STDERR "$filename:$lineno: included file '$inc' is not exported\n"; $ret = 1; diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 47a9f68f7b24..b2aa6bf24d3a 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -118,6 +118,8 @@ static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start, .end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff, .slot = slot, .may_block = true, + /* guest memfd is relevant to only private mappings. */ + .attr_filter = KVM_FILTER_PRIVATE, }; if (!found_memslot) { @@ -259,15 +261,19 @@ static int kvm_gmem_release(struct inode *inode, struct file *file) * dereferencing the slot for existing bindings needs to be protected * against memslot updates, specifically so that unbind doesn't race * and free the memslot (kvm_gmem_get_file() will return NULL). + * + * Since .release is called only when the reference count is zero, + * after which file_ref_get() and get_file_active() fail, + * kvm_gmem_get_pfn() cannot be using the file concurrently. + * file_ref_put() provides a full barrier, and get_file_active() the + * matching acquire barrier. */ mutex_lock(&kvm->slots_lock); filemap_invalidate_lock(inode->i_mapping); xa_for_each(&gmem->bindings, index, slot) - rcu_assign_pointer(slot->gmem.file, NULL); - - synchronize_rcu(); + WRITE_ONCE(slot->gmem.file, NULL); /* * All in-flight operations are gone and new bindings can be created. @@ -296,8 +302,7 @@ static inline struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot) /* * Do not return slot->gmem.file if it has already been closed; * there might be some time between the last fput() and when - * kvm_gmem_release() clears slot->gmem.file, and you do not - * want to spin in the meanwhile. + * kvm_gmem_release() clears slot->gmem.file. */ return get_file_active(&slot->gmem.file); } @@ -508,11 +513,11 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, } /* - * No synchronize_rcu() needed, any in-flight readers are guaranteed to - * be see either a NULL file or this new file, no need for them to go - * away. + * memslots of flag KVM_MEM_GUEST_MEMFD are immutable to change, so + * kvm_gmem_bind() must occur on a new memslot. Because the memslot + * is not visible yet, kvm_gmem_get_pfn() is guaranteed to see the file. */ - rcu_assign_pointer(slot->gmem.file, file); + WRITE_ONCE(slot->gmem.file, file); slot->gmem.pgoff = start; xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL); @@ -548,8 +553,12 @@ void kvm_gmem_unbind(struct kvm_memory_slot *slot) filemap_invalidate_lock(file->f_mapping); xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); - rcu_assign_pointer(slot->gmem.file, NULL); - synchronize_rcu(); + + /* + * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() + * cannot see this memslot. + */ + WRITE_ONCE(slot->gmem.file, NULL); filemap_invalidate_unlock(file->f_mapping); fput(file); @@ -561,11 +570,12 @@ static struct folio *__kvm_gmem_get_pfn(struct file *file, pgoff_t index, kvm_pfn_t *pfn, bool *is_prepared, int *max_order) { + struct file *gmem_file = READ_ONCE(slot->gmem.file); struct kvm_gmem *gmem = file->private_data; struct folio *folio; - if (file != slot->gmem.file) { - WARN_ON_ONCE(slot->gmem.file); + if (file != gmem_file) { + WARN_ON_ONCE(gmem_file); return ERR_PTR(-EFAULT); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index de2c11dae231..faf10671eed2 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -594,6 +594,11 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm, */ gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; + /* + * HVA-based notifications aren't relevant to private + * mappings as they don't have a userspace mapping. + */ + gfn_range.attr_filter = KVM_FILTER_SHARED; /* * {gfn(page) | page intersects with [hva_start, hva_end)} = @@ -1926,16 +1931,8 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, return false; } -/* - * Allocate some memory and give it an address in the guest physical address - * space. - * - * Discontiguous memory is allowed, mostly for framebuffers. - * - * Must be called holding kvm->slots_lock for write. - */ -int __kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region2 *mem) +static int kvm_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem) { struct kvm_memory_slot *old, *new; struct kvm_memslots *slots; @@ -1945,6 +1942,8 @@ int __kvm_set_memory_region(struct kvm *kvm, int as_id, id; int r; + lockdep_assert_held(&kvm->slots_lock); + r = check_memory_region_flags(kvm, mem); if (r) return r; @@ -2056,19 +2055,19 @@ out: kfree(new); return r; } -EXPORT_SYMBOL_GPL(__kvm_set_memory_region); -int kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region2 *mem) +int kvm_set_internal_memslot(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem) { - int r; + if (WARN_ON_ONCE(mem->slot < KVM_USER_MEM_SLOTS)) + return -EINVAL; - mutex_lock(&kvm->slots_lock); - r = __kvm_set_memory_region(kvm, mem); - mutex_unlock(&kvm->slots_lock); - return r; + if (WARN_ON_ONCE(mem->flags)) + return -EINVAL; + + return kvm_set_memory_region(kvm, mem); } -EXPORT_SYMBOL_GPL(kvm_set_memory_region); +EXPORT_SYMBOL_GPL(kvm_set_internal_memslot); static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region2 *mem) @@ -2076,6 +2075,7 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, if ((u16)mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; + guard(mutex)(&kvm->slots_lock); return kvm_set_memory_region(kvm, mem); } @@ -2408,6 +2408,14 @@ static __always_inline void kvm_handle_gfn_range(struct kvm *kvm, gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; + /* + * If/when KVM supports more attributes beyond private .vs shared, this + * _could_ set KVM_FILTER_{SHARED,PRIVATE} appropriately if the entire target + * range already has the desired private vs. shared state (it's unclear + * if that is a net win). For now, KVM reaches this point if and only + * if the private flag is being toggled, i.e. all mappings are in play. + */ + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); @@ -2464,6 +2472,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, struct kvm_mmu_notifier_range pre_set_range = { .start = start, .end = end, + .arg.attributes = attributes, .handler = kvm_pre_set_memory_attributes, .on_lock = kvm_mmu_invalidate_begin, .flush_on_ret = true, @@ -4116,32 +4125,30 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id) mutex_lock(&kvm->lock); -#ifdef CONFIG_LOCKDEP - /* Ensure that lockdep knows vcpu->mutex is taken *inside* kvm->lock */ - mutex_lock(&vcpu->mutex); - mutex_unlock(&vcpu->mutex); -#endif - if (kvm_get_vcpu_by_id(kvm, id)) { r = -EEXIST; goto unlock_vcpu_destroy; } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT); + r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); + WARN_ON_ONCE(r == -EBUSY); if (r) goto unlock_vcpu_destroy; - /* Now it's all set up, let userspace reach it */ + /* + * Now it's all set up, let userspace reach it. Grab the vCPU's mutex + * so that userspace can't invoke vCPU ioctl()s until the vCPU is fully + * visible (per online_vcpus), e.g. so that KVM doesn't get tricked + * into a NULL-pointer dereference because KVM thinks the _current_ + * vCPU doesn't exist. As a bonus, taking vcpu->mutex ensures lockdep + * knows it's taken *inside* kvm->lock. + */ + mutex_lock(&vcpu->mutex); kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) - goto kvm_put_xa_release; - - if (KVM_BUG_ON(xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) { - r = -EINVAL; - goto kvm_put_xa_release; - } + goto kvm_put_xa_erase; /* * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu @@ -4149,15 +4156,17 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id) */ smp_wmb(); atomic_inc(&kvm->online_vcpus); + mutex_unlock(&vcpu->mutex); mutex_unlock(&kvm->lock); kvm_arch_vcpu_postcreate(vcpu); kvm_create_vcpu_debugfs(vcpu); return r; -kvm_put_xa_release: +kvm_put_xa_erase: + mutex_unlock(&vcpu->mutex); kvm_put_kvm_no_destroy(kvm); - xa_release(&kvm->vcpu_array, vcpu->vcpu_idx); + xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); @@ -4282,6 +4291,33 @@ static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, } #endif +static int kvm_wait_for_vcpu_online(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + /* + * In practice, this happy path will always be taken, as a well-behaved + * VMM will never invoke a vCPU ioctl() before KVM_CREATE_VCPU returns. + */ + if (likely(vcpu->vcpu_idx < atomic_read(&kvm->online_vcpus))) + return 0; + + /* + * Acquire and release the vCPU's mutex to wait for vCPU creation to + * complete (kvm_vm_ioctl_create_vcpu() holds the mutex until the vCPU + * is fully online). + */ + if (mutex_lock_killable(&vcpu->mutex)) + return -EINTR; + + mutex_unlock(&vcpu->mutex); + + if (WARN_ON_ONCE(!kvm_get_vcpu(kvm, vcpu->vcpu_idx))) + return -EIO; + + return 0; +} + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4297,6 +4333,15 @@ static long kvm_vcpu_ioctl(struct file *filp, if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) return -EINVAL; + /* + * Wait for the vCPU to be online before handling the ioctl(), as KVM + * assumes the vCPU is reachable via vcpu_array, i.e. may dereference + * a NULL pointer if userspace invokes an ioctl() before KVM is ready. + */ + r = kvm_wait_for_vcpu_online(vcpu); + if (r) + return r; + /* * Some architectures have vcpu ioctls that are asynchronous to vcpu * execution; mutex_lock() would break them.